From 1f7f7365aee8a3f34d6b273c332544619b860cda Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 7 Dec 2022 18:17:34 +0100 Subject: [PATCH 0001/4345] udf: Discard preallocation before extending file with a hole commit 16d0556568148bdcaa45d077cac9f8f7077cf70a upstream. When extending file with a hole, we tried to preserve existing preallocation for the file. However that is not very useful and complicates code because the previous extent may need to be rounded to block boundary as well (which we forgot to do thus causing data corruption for sequence like: xfs_io -f -c "pwrite 0x75e63 11008" -c "truncate 0x7b24b" \ -c "truncate 0xabaa3" -c "pwrite 0xac70b 22954" \ -c "pwrite 0x93a43 11358" -c "pwrite 0xb8e65 52211" file with 512-byte block size. Just discard preallocation before extending file to simplify things and also fix this data corruption. CC: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 46 ++++++++++++++++++---------------------------- 1 file changed, 18 insertions(+), 28 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index d32b836f6ca7..24a024901499 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -438,6 +438,12 @@ static int udf_get_block(struct inode *inode, sector_t block, iinfo->i_next_alloc_goal++; } + /* + * Block beyond EOF and prealloc extents? Just discard preallocation + * as it is not useful and complicates things. + */ + if (((loff_t)block) << inode->i_blkbits > iinfo->i_lenExtents) + udf_discard_prealloc(inode); udf_clear_extent_cache(inode); phys = inode_getblk(inode, block, &err, &new); if (!phys) @@ -487,8 +493,6 @@ static int udf_do_extend_file(struct inode *inode, uint32_t add; int count = 0, fake = !(last_ext->extLength & UDF_EXTENT_LENGTH_MASK); struct super_block *sb = inode->i_sb; - struct kernel_lb_addr prealloc_loc = {}; - uint32_t prealloc_len = 0; struct udf_inode_info *iinfo; int err; @@ -509,19 +513,6 @@ static int udf_do_extend_file(struct inode *inode, ~(sb->s_blocksize - 1); } - /* Last extent are just preallocated blocks? */ - if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == - EXT_NOT_RECORDED_ALLOCATED) { - /* Save the extent so that we can reattach it to the end */ - prealloc_loc = last_ext->extLocation; - prealloc_len = last_ext->extLength; - /* Mark the extent as a hole */ - last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); - last_ext->extLocation.logicalBlockNum = 0; - last_ext->extLocation.partitionReferenceNum = 0; - } - /* Can we merge with the previous extent? */ if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == EXT_NOT_RECORDED_NOT_ALLOCATED) { @@ -549,7 +540,7 @@ static int udf_do_extend_file(struct inode *inode, * more extents, we may need to enter possible following * empty indirect extent. */ - if (new_block_bytes || prealloc_len) + if (new_block_bytes) udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0); } @@ -583,17 +574,6 @@ static int udf_do_extend_file(struct inode *inode, } out: - /* Do we have some preallocated blocks saved? */ - if (prealloc_len) { - err = udf_add_aext(inode, last_pos, &prealloc_loc, - prealloc_len, 1); - if (err) - return err; - last_ext->extLocation = prealloc_loc; - last_ext->extLength = prealloc_len; - count++; - } - /* last_pos should point to the last written extent... */ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) last_pos->offset -= sizeof(struct short_ad); @@ -646,8 +626,17 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) else BUG(); + /* + * When creating hole in file, just don't bother with preserving + * preallocation. It likely won't be very useful anyway. + */ + udf_discard_prealloc(inode); + etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); within_final_block = (etype != -1); + /* We don't expect extents past EOF... */ + WARN_ON_ONCE(etype != -1 && + elen > ((loff_t)offset + 1) << inode->i_blkbits); if ((!epos.bh && epos.offset == udf_file_entry_alloc_offset(inode)) || (epos.bh && epos.offset == sizeof(struct allocExtDesc))) { @@ -776,10 +765,11 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, goto out_free; } - /* Are we beyond EOF? */ + /* Are we beyond EOF and preallocated extent? */ if (etype == -1) { int ret; loff_t hole_len; + isBeyondEOF = true; if (count) { if (c) From 1a075f4a549481ce6e8518d8379f193ccec6b746 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 7 Dec 2022 17:25:10 +0100 Subject: [PATCH 0002/4345] udf: Fix preallocation discarding at indirect extent boundary commit cfe4c1b25dd6d2f056afc00b7c98bcb3dd0b1fc3 upstream. When preallocation extent is the first one in the extent block, the code would corrupt extent tree header instead. Fix the problem and use udf_delete_aext() for deleting extent to avoid some code duplication. CC: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/truncate.c | 45 +++++++++++++-------------------------------- 1 file changed, 13 insertions(+), 32 deletions(-) diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index 532cda99644e..a9790fb32f5f 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -120,60 +120,41 @@ void udf_truncate_tail_extent(struct inode *inode) void udf_discard_prealloc(struct inode *inode) { - struct extent_position epos = { NULL, 0, {0, 0} }; + struct extent_position epos = {}; + struct extent_position prev_epos = {}; struct kernel_lb_addr eloc; uint32_t elen; uint64_t lbcount = 0; int8_t etype = -1, netype; - int adsize; struct udf_inode_info *iinfo = UDF_I(inode); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB || inode->i_size == iinfo->i_lenExtents) return; - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) - adsize = sizeof(struct short_ad); - else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) - adsize = sizeof(struct long_ad); - else - adsize = 0; - epos.block = iinfo->i_location; /* Find the last extent in the file */ - while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) { - etype = netype; + while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 0)) != -1) { + brelse(prev_epos.bh); + prev_epos = epos; + if (prev_epos.bh) + get_bh(prev_epos.bh); + + etype = udf_next_aext(inode, &epos, &eloc, &elen, 1); lbcount += elen; } if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) { - epos.offset -= adsize; lbcount -= elen; - extent_trunc(inode, &epos, &eloc, etype, elen, 0); - if (!epos.bh) { - iinfo->i_lenAlloc = - epos.offset - - udf_file_entry_alloc_offset(inode); - mark_inode_dirty(inode); - } else { - struct allocExtDesc *aed = - (struct allocExtDesc *)(epos.bh->b_data); - aed->lengthAllocDescs = - cpu_to_le32(epos.offset - - sizeof(struct allocExtDesc)); - if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || - UDF_SB(inode->i_sb)->s_udfrev >= 0x0201) - udf_update_tag(epos.bh->b_data, epos.offset); - else - udf_update_tag(epos.bh->b_data, - sizeof(struct allocExtDesc)); - mark_buffer_dirty_inode(epos.bh, inode); - } + udf_delete_aext(inode, prev_epos); + udf_free_blocks(inode->i_sb, inode, &eloc, 0, + DIV_ROUND_UP(elen, 1 << inode->i_blkbits)); } /* This inode entry is in-memory only and thus we don't have to mark * the inode dirty */ iinfo->i_lenExtents = lbcount; brelse(epos.bh); + brelse(prev_epos.bh); } static void udf_update_alloc_ext_desc(struct inode *inode, From db873b770d8a1ea1ec41aa6cdc9573c4623a0293 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 7 Dec 2022 17:34:33 +0100 Subject: [PATCH 0003/4345] udf: Do not bother looking for prealloc extents if i_lenExtents matches i_size commit 6ad53f0f71c52871202a7bf096feb2c59db33fc5 upstream. If rounded block-rounded i_lenExtents matches block rounded i_size, there are no preallocation extents. Do not bother walking extent linked list. CC: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/truncate.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index a9790fb32f5f..036ebd892b85 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -127,9 +127,10 @@ void udf_discard_prealloc(struct inode *inode) uint64_t lbcount = 0; int8_t etype = -1, netype; struct udf_inode_info *iinfo = UDF_I(inode); + int bsize = 1 << inode->i_blkbits; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB || - inode->i_size == iinfo->i_lenExtents) + ALIGN(inode->i_size, bsize) == ALIGN(iinfo->i_lenExtents, bsize)) return; epos.block = iinfo->i_location; From 8b2f86f82c0e215ba3404259d89315abc15144bc Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Dec 2022 13:03:30 +0100 Subject: [PATCH 0004/4345] udf: Fix extending file within last block commit 1f3868f06855c97a4954c99b36f3fc9eb8f60326 upstream. When extending file within last block it can happen that the extent is already rounded to the blocksize and thus contains the offset we want to grow up to. In such case we would mistakenly expand the last extent and make it one block longer than it should be, exposing unallocated block in a file and causing data corruption. Fix the problem by properly detecting this case and bailing out. CC: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 24a024901499..e94a18bb7f99 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -589,13 +589,17 @@ out: static void udf_do_extend_final_block(struct inode *inode, struct extent_position *last_pos, struct kernel_long_ad *last_ext, - uint32_t final_block_len) + uint32_t new_elen) { - struct super_block *sb = inode->i_sb; uint32_t added_bytes; - added_bytes = final_block_len - - (last_ext->extLength & (sb->s_blocksize - 1)); + /* + * Extent already large enough? It may be already rounded up to block + * size... + */ + if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK)) + return; + added_bytes = (last_ext->extLength & UDF_EXTENT_LENGTH_MASK) - new_elen; last_ext->extLength += added_bytes; UDF_I(inode)->i_lenExtents += added_bytes; @@ -612,12 +616,12 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) int8_t etype; struct super_block *sb = inode->i_sb; sector_t first_block = newsize >> sb->s_blocksize_bits, offset; - unsigned long partial_final_block; + loff_t new_elen; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); struct kernel_long_ad extent; int err = 0; - int within_final_block; + bool within_last_ext; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -633,9 +637,9 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) udf_discard_prealloc(inode); etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); - within_final_block = (etype != -1); + within_last_ext = (etype != -1); /* We don't expect extents past EOF... */ - WARN_ON_ONCE(etype != -1 && + WARN_ON_ONCE(within_last_ext && elen > ((loff_t)offset + 1) << inode->i_blkbits); if ((!epos.bh && epos.offset == udf_file_entry_alloc_offset(inode)) || @@ -652,19 +656,17 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) extent.extLength |= etype << 30; } - partial_final_block = newsize & (sb->s_blocksize - 1); + new_elen = ((loff_t)offset << inode->i_blkbits) | + (newsize & (sb->s_blocksize - 1)); /* File has extent covering the new size (could happen when extending * inside a block)? */ - if (within_final_block) { + if (within_last_ext) { /* Extending file within the last file block */ - udf_do_extend_final_block(inode, &epos, &extent, - partial_final_block); + udf_do_extend_final_block(inode, &epos, &extent, new_elen); } else { - loff_t add = ((loff_t)offset << sb->s_blocksize_bits) | - partial_final_block; - err = udf_do_extend_file(inode, &epos, &extent, add); + err = udf_do_extend_file(inode, &epos, &extent, new_elen); } if (err < 0) From c79538f32df12887f110dcd6b9c825b482905f24 Mon Sep 17 00:00:00 2001 From: Szymon Heidrich Date: Tue, 6 Dec 2022 15:13:01 +0100 Subject: [PATCH 0005/4345] usb: gadget: uvc: Prevent buffer overflow in setup handler commit 4c92670b16727365699fe4b19ed32013bab2c107 upstream. Setup function uvc_function_setup permits control transfer requests with up to 64 bytes of payload (UVC_MAX_REQUEST_SIZE), data stage handler for OUT transfer uses memcpy to copy req->actual bytes to uvc_event->data.data array of size 60. This may result in an overflow of 4 bytes. Fixes: cdda479f15cd ("USB gadget: video class function driver") Cc: stable Reviewed-by: Laurent Pinchart Reviewed-by: Daniel Scally Signed-off-by: Szymon Heidrich Link: https://lore.kernel.org/r/20221206141301.51305-1-szymon.heidrich@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_uvc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index fecdba85ab27..5d39aff263f0 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -213,8 +213,9 @@ uvc_function_ep0_complete(struct usb_ep *ep, struct usb_request *req) memset(&v4l2_event, 0, sizeof(v4l2_event)); v4l2_event.type = UVC_EVENT_DATA; - uvc_event->data.length = req->actual; - memcpy(&uvc_event->data.data, req->buf, req->actual); + uvc_event->data.length = min_t(unsigned int, req->actual, + sizeof(uvc_event->data.data)); + memcpy(&uvc_event->data.data, req->buf, uvc_event->data.length); v4l2_event_queue(&uvc->vdev, &v4l2_event); } } From 398215f78338e79a2b6352896c902c9461b435f1 Mon Sep 17 00:00:00 2001 From: Duke Xin Date: Sat, 19 Nov 2022 17:44:47 +0800 Subject: [PATCH 0006/4345] USB: serial: option: add Quectel EM05-G modem commit f0052d7a1edb3d8921b4e154aa8c46c4845b3714 upstream. The EM05-G modem has 2 USB configurations that are configurable via the AT command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate with the following interfaces, respectively: "RMNET" : AT + DIAG + NMEA + Modem + QMI "MBIM" : MBIM + AT + DIAG + NMEA + Modem The detailed description of the USB configuration for each mode as follows: RMNET Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 21 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0311 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms MBIM Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 16 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0311 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Duke Xin Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 537ef276c78f..5636b8f52216 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -255,6 +255,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EP06 0x0306 #define QUECTEL_PRODUCT_EM05G 0x030a #define QUECTEL_PRODUCT_EM060K 0x030b +#define QUECTEL_PRODUCT_EM05G_SG 0x0311 #define QUECTEL_PRODUCT_EM12 0x0512 #define QUECTEL_PRODUCT_RM500Q 0x0800 #define QUECTEL_PRODUCT_RM520N 0x0801 @@ -1160,6 +1161,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff), .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff), + .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x40) }, From 9895ce5ea283384bc9374dc1b218f1811b16c4aa Mon Sep 17 00:00:00 2001 From: Bruno Thomsen Date: Sun, 27 Nov 2022 18:08:11 +0100 Subject: [PATCH 0007/4345] USB: serial: cp210x: add Kamstrup RF sniffer PIDs commit e88906b169ebcb8046e8f0ad76edd09ab41cfdfe upstream. The RF sniffers are based on cp210x where the RF frontends are based on a different USB stack. RF sniffers can analyze packets meta data including power level and perform packet injection. Can be used to perform RF frontend self-test when connected to a concentrator, ex. arch/arm/boot/dts/imx7d-flex-concentrator.dts Signed-off-by: Bruno Thomsen Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/cp210x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 6b5ba6180c30..8a4a0d4dbc13 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -199,6 +199,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x16DC, 0x0015) }, /* W-IE-NE-R Plein & Baus GmbH CML Control, Monitoring and Data Logger */ { USB_DEVICE(0x17A8, 0x0001) }, /* Kamstrup Optical Eye/3-wire */ { USB_DEVICE(0x17A8, 0x0005) }, /* Kamstrup M-Bus Master MultiPort 250D */ + { USB_DEVICE(0x17A8, 0x0011) }, /* Kamstrup 444 MHz RF sniffer */ + { USB_DEVICE(0x17A8, 0x0013) }, /* Kamstrup 870 MHz RF sniffer */ { USB_DEVICE(0x17A8, 0x0101) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Int Ant) */ { USB_DEVICE(0x17A8, 0x0102) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Ext Ant) */ { USB_DEVICE(0x17F4, 0xAAAA) }, /* Wavesense Jazz blood glucose meter */ From 5b75a004167422f1f4a8af767bd4239e53b3348c Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 29 Nov 2022 15:17:49 +0100 Subject: [PATCH 0008/4345] USB: serial: f81232: fix division by zero on line-speed change commit a08ca6ebafe615c9028c53fc4c9e6c9b2b1f2888 upstream. The driver leaves the line speed unchanged in case a requested speed is not supported. Make sure to handle the case where the current speed is B0 (hangup) without dividing by zero when determining the clock source. Fixes: 268ddb5e9b62 ("USB: serial: f81232: add high baud rate support") Cc: stable@vger.kernel.org # 5.2 Cc: Ji-Ze Hong (Peter Hong) Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/f81232.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/usb/serial/f81232.c b/drivers/usb/serial/f81232.c index 0c7eacc630e0..11fe49543f26 100644 --- a/drivers/usb/serial/f81232.c +++ b/drivers/usb/serial/f81232.c @@ -130,9 +130,6 @@ static u8 const clock_table[] = { F81232_CLK_1_846_MHZ, F81232_CLK_14_77_MHZ, static int calc_baud_divisor(speed_t baudrate, speed_t clockrate) { - if (!baudrate) - return 0; - return DIV_ROUND_CLOSEST(clockrate, baudrate); } @@ -523,9 +520,14 @@ static void f81232_set_baudrate(struct tty_struct *tty, speed_t baud_list[] = { baudrate, old_baudrate, F81232_DEF_BAUDRATE }; for (i = 0; i < ARRAY_SIZE(baud_list); ++i) { - idx = f81232_find_clk(baud_list[i]); + baudrate = baud_list[i]; + if (baudrate == 0) { + tty_encode_baud_rate(tty, 0, 0); + return; + } + + idx = f81232_find_clk(baudrate); if (idx >= 0) { - baudrate = baud_list[i]; tty_encode_baud_rate(tty, baudrate, baudrate); break; } From c8bf31a00f4f921259d950f1984fbea518eba557 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 29 Nov 2022 15:18:19 +0100 Subject: [PATCH 0009/4345] USB: serial: f81534: fix division by zero on line-speed change commit 188c9c2e0c7f4ae864113f80c40bafb394062271 upstream. The driver leaves the line speed unchanged in case a requested speed is not supported. Make sure to handle the case where the current speed is B0 (hangup) without dividing by zero when determining the clock source. Fixes: 3aacac02f385 ("USB: serial: f81534: add high baud rate support") Cc: stable@vger.kernel.org # 4.16 Cc: Ji-Ze Hong (Peter Hong) Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/f81534.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/usb/serial/f81534.c b/drivers/usb/serial/f81534.c index 5661fd03e545..e952be683c63 100644 --- a/drivers/usb/serial/f81534.c +++ b/drivers/usb/serial/f81534.c @@ -538,9 +538,6 @@ static int f81534_submit_writer(struct usb_serial_port *port, gfp_t mem_flags) static u32 f81534_calc_baud_divisor(u32 baudrate, u32 clockrate) { - if (!baudrate) - return 0; - /* Round to nearest divisor */ return DIV_ROUND_CLOSEST(clockrate, baudrate); } @@ -570,9 +567,14 @@ static int f81534_set_port_config(struct usb_serial_port *port, u32 baud_list[] = {baudrate, old_baudrate, F81534_DEFAULT_BAUD_RATE}; for (i = 0; i < ARRAY_SIZE(baud_list); ++i) { - idx = f81534_find_clk(baud_list[i]); + baudrate = baud_list[i]; + if (baudrate == 0) { + tty_encode_baud_rate(tty, 0, 0); + return 0; + } + + idx = f81534_find_clk(baudrate); if (idx >= 0) { - baudrate = baud_list[i]; tty_encode_baud_rate(tty, baudrate, baudrate); break; } From 9ff7aff40ef5d5d6b271bf94fb0903c5a550f557 Mon Sep 17 00:00:00 2001 From: Reka Norman Date: Wed, 30 Nov 2022 11:19:40 +0200 Subject: [PATCH 0010/4345] xhci: Apply XHCI_RESET_TO_DEFAULT quirk to ADL-N commit fed70b61ef2c0aed54456db3d485b215f6cc3209 upstream. ADL-N systems have the same issue as ADL-P, where a large boot firmware delay is seen if USB ports are left in U3 at shutdown. So apply the XHCI_RESET_TO_DEFAULT quirk to ADL-N as well. This patch depends on commit 34cd2db408d5 ("xhci: Add quirk to reset host back to default state at shutdown"). The issue it fixes is a ~20s boot time delay when booting from S5. It affects ADL-N devices, and ADL-N support was added starting from v5.16. Cc: stable@vger.kernel.org Signed-off-by: Reka Norman Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20221130091944.2171610-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 0ee11a937011..9168b492c02b 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -59,6 +59,7 @@ #define PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI 0x9a13 #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI 0x1138 #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed +#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_PCH_XHCI 0x54ed #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba @@ -242,7 +243,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_MISSING_CAS; if (pdev->vendor == PCI_VENDOR_ID_INTEL && - pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI) + (pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_PCH_XHCI)) xhci->quirks |= XHCI_RESET_TO_DEFAULT; if (pdev->vendor == PCI_VENDOR_ID_INTEL && From f2479c3daaabccbac6c343a737615d0c595c6dc4 Mon Sep 17 00:00:00 2001 From: Tony Nguyen Date: Mon, 12 Dec 2022 11:00:31 -0800 Subject: [PATCH 0011/4345] igb: Initialize mailbox message for VF reset commit de5dc44370fbd6b46bd7f1a1e00369be54a041c8 upstream. When a MAC address is not assigned to the VF, that portion of the message sent to the VF is not set. The memory, however, is allocated from the stack meaning that information may be leaked to the VM. Initialize the message buffer to 0 so that no information is passed to the VM in this case. Fixes: 6ddbc4cf1f4d ("igb: Indicate failure on vf reset for empty mac address") Reported-by: Akihiko Odaki Signed-off-by: Tony Nguyen Reviewed-by: Akihiko Odaki Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20221212190031.3983342-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 327196d15a6a..f24f1a8ec2fb 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -7416,7 +7416,7 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf) { struct e1000_hw *hw = &adapter->hw; unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses; - u32 reg, msgbuf[3]; + u32 reg, msgbuf[3] = {}; u8 *addr = (u8 *)(&msgbuf[1]); /* process all the same items cleared in a function level reset */ From a20b5eec0742396531cdcc2b6d655ed032a75d35 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 25 Nov 2020 23:37:45 +0100 Subject: [PATCH 0012/4345] HID: ite: Add support for Acer S1002 keyboard-dock [ Upstream commit c961facb5b19634eee5bcdd91fc5bf3f1c545bc5 ] Make the hid-ite driver handle the Acer S1002 keyboard-dock, this leads to 2 improvements: 1. The non working wifi-toggle hotkey now works. 2. Toggling the touchpad on of with the hotkey will no show OSD notifications in e.g. GNOME3. The actual toggling is handled inside the keyboard, this adds support for notifying evdev listeners about this. Signed-off-by: Hans de Goede Signed-off-by: Jiri Kosina Stable-dep-of: 9ad6645a9dce ("HID: ite: Enable QUIRK_TOUCHPAD_ON_OFF_REPORT on Acer Aspire Switch V 10") Signed-off-by: Sasha Levin --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-ite.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 70a693f8f034..7fc6b204c399 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -1150,6 +1150,7 @@ #define USB_DEVICE_ID_SYNAPTICS_DELL_K12A 0x2819 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012 0x2968 #define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 +#define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1002 0x73f4 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003 0x73f5 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 742c052b0110..22bfbebceaf4 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -18,10 +18,16 @@ static __u8 *ite_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); if (quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) { + /* For Acer Aspire Switch 10 SW5-012 keyboard-dock */ if (*rsize == 188 && rdesc[162] == 0x81 && rdesc[163] == 0x02) { - hid_info(hdev, "Fixing up ITE keyboard report descriptor\n"); + hid_info(hdev, "Fixing up Acer Sw5-012 ITE keyboard report descriptor\n"); rdesc[163] = HID_MAIN_ITEM_RELATIVE; } + /* For Acer One S1002 keyboard-dock */ + if (*rsize == 188 && rdesc[185] == 0x81 && rdesc[186] == 0x02) { + hid_info(hdev, "Fixing up Acer S1002 ITE keyboard report descriptor\n"); + rdesc[186] = HID_MAIN_ITEM_RELATIVE; + } } return rdesc; @@ -101,6 +107,11 @@ static const struct hid_device_id ite_devices[] = { USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012), .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1002), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, + /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003) }, From 263a1782a618c1206e11932d4236dc3f30f856f2 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 6 Feb 2021 21:53:27 +0100 Subject: [PATCH 0013/4345] HID: ite: Enable QUIRK_TOUCHPAD_ON_OFF_REPORT on Acer Aspire Switch 10E [ Upstream commit b7c20f3815985570ac71c39b1a3e68c201109578 ] The Acer Aspire Switch 10E (SW3-016)'s keyboard-dock uses the same USB-ids as the Acer One S1003 keyboard-dock. Yet they are not entirely the same: 1. The S1003 keyboard-dock has the same report descriptors as the S1002 keyboard-dock (which has different USB-ids) 2. The Acer Aspire Switch 10E's keyboard-dock has different report descriptors from the S1002/S1003 keyboard docks and it sends 0x00880078 / 0x00880079 usage events when the touchpad is toggled on/off (which is handled internally). This means that all Acer kbd-docks handled by the hid-ite.c drivers report their touchpad being toggled on/off through these custom usage-codes with the exception of the S1003 dock, which likely is a bug of that dock. Add a QUIRK_TOUCHPAD_ON_OFF_REPORT quirk for the Aspire Switch 10E / S1003 usb-id so that the touchpad toggling will get reported to userspace on the Aspire Switch 10E. Since the Aspire Switch 10E's kbd-dock has different report-descriptors, this also requires adding support for fixing those to ite_report_fixup(). Setting the quirk will also cause ite_report_fixup() to hit the S1002/S1003 descriptors path on the S1003. Since the S1003 kbd-dock never generates any input-reports for the fixed up part of the descriptors this does not matter; and if there are versions out there which do actually send input-reports for the touchpad-toggle then the fixup should actually help to make things work. This was tested on both an Acer Aspire Switch 10E and on an Acer One S1003. Signed-off-by: Hans de Goede Signed-off-by: Jiri Kosina Stable-dep-of: 9ad6645a9dce ("HID: ite: Enable QUIRK_TOUCHPAD_ON_OFF_REPORT on Acer Aspire Switch V 10") Signed-off-by: Sasha Levin --- drivers/hid/hid-ite.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 22bfbebceaf4..14fc068affad 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -23,11 +23,16 @@ static __u8 *ite_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int hid_info(hdev, "Fixing up Acer Sw5-012 ITE keyboard report descriptor\n"); rdesc[163] = HID_MAIN_ITEM_RELATIVE; } - /* For Acer One S1002 keyboard-dock */ + /* For Acer One S1002/S1003 keyboard-dock */ if (*rsize == 188 && rdesc[185] == 0x81 && rdesc[186] == 0x02) { - hid_info(hdev, "Fixing up Acer S1002 ITE keyboard report descriptor\n"); + hid_info(hdev, "Fixing up Acer S1002/S1003 ITE keyboard report descriptor\n"); rdesc[186] = HID_MAIN_ITEM_RELATIVE; } + /* For Acer Aspire Switch 10E (SW3-016) keyboard-dock */ + if (*rsize == 210 && rdesc[184] == 0x81 && rdesc[185] == 0x02) { + hid_info(hdev, "Fixing up Acer Aspire Switch 10E (SW3-016) ITE keyboard report descriptor\n"); + rdesc[185] = HID_MAIN_ITEM_RELATIVE; + } } return rdesc; @@ -114,7 +119,8 @@ static const struct hid_device_id ite_devices[] = { /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, - USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003) }, + USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); From 1d5db0c322ae885bd18b73802ce34750c633adcf Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 8 Nov 2022 16:13:50 +0100 Subject: [PATCH 0014/4345] HID: ite: Enable QUIRK_TOUCHPAD_ON_OFF_REPORT on Acer Aspire Switch V 10 [ Upstream commit 9ad6645a9dce4d0e42daca6ebf32a154401c59d3 ] The Acer Aspire Switch V 10 (SW5-017)'s keyboard-dock uses the same ITE controller setup as other Acer Switch 2-in-1's. This needs special handling for the wifi on/off toggle hotkey as well as to properly report touchpad on/off keypresses. Add the USB-ids for the SW5-017's keyboard-dock with a quirk setting of QUIRK_TOUCHPAD_ON_OFF_REPORT to fix both issues. Cc: Rudolf Polzer Signed-off-by: Hans de Goede Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-ite.c | 5 +++++ 2 files changed, 6 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 7fc6b204c399..2001566be3f5 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -1152,6 +1152,7 @@ #define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1002 0x73f4 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003 0x73f5 +#define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_017 0x73f6 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 #define USB_VENDOR_ID_TEXAS_INSTRUMENTS 0x2047 diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 14fc068affad..b8cce9c196d8 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -121,6 +121,11 @@ static const struct hid_device_id ite_devices[] = { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003), .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, + /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_017), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); From 7c3a523c9b19ba94c3cade5b2d4612bedcf22e21 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= Date: Thu, 10 Nov 2022 18:40:56 +0100 Subject: [PATCH 0015/4345] HID: uclogic: Add HID_QUIRK_HIDINPUT_FORCE quirk MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3405a4beaaa852f3ed2a5eb3b5149932d5c3779b ] Commit f7d8e387d9ae ("HID: uclogic: Switch to Digitizer usage for styluses") changed the usage used in UCLogic from "Pen" to "Digitizer". However, the IS_INPUT_APPLICATION() macro evaluates to false for HID_DG_DIGITIZER causing issues with the XP-Pen Star G640 tablet. Add the HID_QUIRK_HIDINPUT_FORCE quirk to bypass the IS_INPUT_APPLICATION() check. Reported-by: Torge Matthies Reported-by: Alexander Zhang Tested-by: Alexander Zhang Signed-off-by: José Expósito Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-uclogic-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 4edb24195704..e4811d37ca77 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -172,6 +172,7 @@ static int uclogic_probe(struct hid_device *hdev, * than the pen, so use QUIRK_MULTI_INPUT for all tablets. */ hdev->quirks |= HID_QUIRK_MULTI_INPUT; + hdev->quirks |= HID_QUIRK_HIDINPUT_FORCE; /* Allocate and assign driver data */ drvdata = devm_kzalloc(&hdev->dev, sizeof(*drvdata), GFP_KERNEL); From f3fe6817156a2ad4b06f01afab04638a34d7c9a6 Mon Sep 17 00:00:00 2001 From: Sungwoo Kim Date: Fri, 18 Nov 2022 15:01:47 -0500 Subject: [PATCH 0016/4345] Bluetooth: L2CAP: Fix u8 overflow [ Upstream commit bcd70260ef56e0aee8a4fc6cd214a419900b0765 ] By keep sending L2CAP_CONF_REQ packets, chan->num_conf_rsp increases multiple times and eventually it will wrap around the maximum number (i.e., 255). This patch prevents this by adding a boundary check with L2CAP_MAX_CONF_RSP Btmon log: Bluetooth monitor ver 5.64 = Note: Linux version 6.1.0-rc2 (x86_64) 0.264594 = Note: Bluetooth subsystem version 2.22 0.264636 @ MGMT Open: btmon (privileged) version 1.22 {0x0001} 0.272191 = New Index: 00:00:00:00:00:00 (Primary,Virtual,hci0) [hci0] 13.877604 @ RAW Open: 9496 (privileged) version 2.22 {0x0002} 13.890741 = Open Index: 00:00:00:00:00:00 [hci0] 13.900426 (...) > ACL Data RX: Handle 200 flags 0x00 dlen 1033 #32 [hci0] 14.273106 invalid packet size (12 != 1033) 08 00 01 00 02 01 04 00 01 10 ff ff ............ > ACL Data RX: Handle 200 flags 0x00 dlen 1547 #33 [hci0] 14.273561 invalid packet size (14 != 1547) 0a 00 01 00 04 01 06 00 40 00 00 00 00 00 ........@..... > ACL Data RX: Handle 200 flags 0x00 dlen 2061 #34 [hci0] 14.274390 invalid packet size (16 != 2061) 0c 00 01 00 04 01 08 00 40 00 00 00 00 00 00 04 ........@....... > ACL Data RX: Handle 200 flags 0x00 dlen 2061 #35 [hci0] 14.274932 invalid packet size (16 != 2061) 0c 00 01 00 04 01 08 00 40 00 00 00 07 00 03 00 ........@....... = bluetoothd: Bluetooth daemon 5.43 14.401828 > ACL Data RX: Handle 200 flags 0x00 dlen 1033 #36 [hci0] 14.275753 invalid packet size (12 != 1033) 08 00 01 00 04 01 04 00 40 00 00 00 ........@... Signed-off-by: Sungwoo Kim Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index c5e4d2b8cb0b..cf56582d298a 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4449,7 +4449,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, chan->ident = cmd->ident; l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, len, rsp); - chan->num_conf_rsp++; + if (chan->num_conf_rsp < L2CAP_CONF_MAX_CONF_RSP) + chan->num_conf_rsp++; /* Reset config buffer. */ chan->conf_len = 0; From eec1c3ade48b03d381b9e4a787970d8ddaf1c0b6 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 23 Nov 2022 15:18:28 +0100 Subject: [PATCH 0017/4345] net: loopback: use NET_NAME_PREDICTABLE for name_assign_type [ Upstream commit 31d929de5a112ee1b977a89c57de74710894bbbf ] When the name_assign_type attribute was introduced (commit 685343fc3ba6, "net: add name_assign_type netdev attribute"), the loopback device was explicitly mentioned as one which would make use of NET_NAME_PREDICTABLE: The name_assign_type attribute gives hints where the interface name of a given net-device comes from. These values are currently defined: ... NET_NAME_PREDICTABLE: The ifname has been assigned by the kernel in a predictable way that is guaranteed to avoid reuse and always be the same for a given device. Examples include statically created devices like the loopback device [...] Switch to that so that reading /sys/class/net/lo/name_assign_type produces something sensible instead of returning -EINVAL. Signed-off-by: Rasmus Villemoes Reviewed-by: Jacob Keller Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/loopback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index a1c77cc00416..498e5c8013ef 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -208,7 +208,7 @@ static __net_init int loopback_net_init(struct net *net) int err; err = -ENOMEM; - dev = alloc_netdev(0, "lo", NET_NAME_UNKNOWN, loopback_setup); + dev = alloc_netdev(0, "lo", NET_NAME_PREDICTABLE, loopback_setup); if (!dev) goto out; From 1a9148dfd8e03835dc7617cee696dd18c0000e99 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Dec 2022 17:32:08 +0100 Subject: [PATCH 0018/4345] Linux 5.10.161 Link: https://lore.kernel.org/r/20221219182940.701087296@linuxfoundation.org Tested-by: Pavel Machek (CIP) Tested-by: Florian Fainelli Tested-by: Shuah Khan Tested-by: Linux Kernel Functional Testing Tested-by: Rudi Heitbaum Tested-by: Sudip Mukherjee Tested-by: Jon Hunter Tested-by: Slade Watkins Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 6f7dae2f1a4e..68f8efa0cc30 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 160 +SUBLEVEL = 161 EXTRAVERSION = NAME = Dare mighty things From 1500fed00878fd59b2d6a1832b8d3f7c261a5671 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 4 Mar 2021 12:21:05 -0700 Subject: [PATCH 0019/4345] kernel: provide create_io_thread() helper [ Upstream commit cc440e8738e5c875297ac0e90316745093be7e28 ] Provide a generic helper for setting up an io_uring worker. Returns a task_struct so that the caller can do whatever setup is needed, then call wake_up_new_task() to kick it into gear. Add a kernel_clone_args member, io_thread, which tells copy_process() to mark the task with PF_IO_WORKER. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/sched/task.h | 2 ++ kernel/fork.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+) diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index eeacb4a16fe3..4ce511437a8a 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -31,6 +31,7 @@ struct kernel_clone_args { /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; + int io_thread; struct cgroup *cgrp; struct css_set *cset; }; @@ -85,6 +86,7 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); +struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); diff --git a/kernel/fork.c b/kernel/fork.c index b877480c901f..252a40f14f72 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1949,6 +1949,8 @@ static __latent_entropy struct task_struct *copy_process( p = dup_task_struct(current, node); if (!p) goto fork_out; + if (args->io_thread) + p->flags |= PF_IO_WORKER; /* * This _must_ happen before we call free_task(), i.e. before we jump @@ -2415,6 +2417,34 @@ struct mm_struct *copy_init_mm(void) return dup_mm(NULL, &init_mm); } +/* + * This is like kernel_clone(), but shaved down and tailored to just + * creating io_uring workers. It returns a created task, or an error pointer. + * The returned task is inactive, and the caller must fire it up through + * wake_up_new_task(p). All signals are blocked in the created task. + */ +struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) +{ + unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| + CLONE_IO; + struct kernel_clone_args args = { + .flags = ((lower_32_bits(flags) | CLONE_VM | + CLONE_UNTRACED) & ~CSIGNAL), + .exit_signal = (lower_32_bits(flags) & CSIGNAL), + .stack = (unsigned long)fn, + .stack_size = (unsigned long)arg, + .io_thread = 1, + }; + struct task_struct *tsk; + + tsk = copy_process(NULL, 0, node, &args); + if (!IS_ERR(tsk)) { + sigfillset(&tsk->blocked); + sigdelsetmask(&tsk->blocked, sigmask(SIGKILL)); + } + return tsk; +} + /* * Ok, this is the main fork-routine. * From e86db87191d8f91dfe787758c6dd646c2bf0c335 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:18:36 -0600 Subject: [PATCH 0020/4345] iov_iter: add helper to save iov_iter state [ Upstream commit 8fb0f47a9d7acf620d0fd97831b69da9bc5e22ed ] In an ideal world, when someone is passed an iov_iter and returns X bytes, then X bytes would have been consumed/advanced from the iov_iter. But we have use cases that always consume the entire iterator, a few examples of that are iomap and bdev O_DIRECT. This means we cannot rely on the state of the iov_iter once we've called ->read_iter() or ->write_iter(). This would be easier if we didn't always have to deal with truncate of the iov_iter, as rewinding would be trivial without that. We recently added a commit to track the truncate state, but that grew the iov_iter by 8 bytes and wasn't the best solution. Implement a helper to save enough of the iov_iter state to sanely restore it after we've called the read/write iterator helpers. This currently only works for IOVEC/BVEC/KVEC as that's all we need, support for other iterator types are left as an exercise for the reader. Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wiacKV4Gh-MYjteU0LwNBSGpWrK-Ov25HdqB1ewinrFPg@mail.gmail.com/ Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/uio.h | 15 +++++++++++++ lib/iov_iter.c | 52 ++++++++++++++++++++++++++++----------------- 2 files changed, 48 insertions(+), 19 deletions(-) diff --git a/include/linux/uio.h b/include/linux/uio.h index 27ff8eb786dc..cedb68e49e4f 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -26,6 +26,12 @@ enum iter_type { ITER_DISCARD = 64, }; +struct iov_iter_state { + size_t iov_offset; + size_t count; + unsigned long nr_segs; +}; + struct iov_iter { /* * Bit 0 is the read/write bit, set if we're writing. @@ -55,6 +61,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i) return i->type & ~(READ | WRITE); } +static inline void iov_iter_save_state(struct iov_iter *iter, + struct iov_iter_state *state) +{ + state->iov_offset = iter->iov_offset; + state->count = iter->count; + state->nr_segs = iter->nr_segs; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -226,6 +240,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 1b0a349fbcd9..650554964f18 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1836,24 +1836,38 @@ int import_single_range(int rw, void __user *buf, size_t len, } EXPORT_SYMBOL(import_single_range); -int iov_iter_for_each_range(struct iov_iter *i, size_t bytes, - int (*f)(struct kvec *vec, void *context), - void *context) +/** + * iov_iter_restore() - Restore a &struct iov_iter to the same state as when + * iov_iter_save_state() was called. + * + * @i: &struct iov_iter to restore + * @state: state to restore from + * + * Used after iov_iter_save_state() to bring restore @i, if operations may + * have advanced it. + * + * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC + */ +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) { - struct kvec w; - int err = -EINVAL; - if (!bytes) - return 0; - - iterate_all_kinds(i, bytes, v, -EINVAL, ({ - w.iov_base = kmap(v.bv_page) + v.bv_offset; - w.iov_len = v.bv_len; - err = f(&w, context); - kunmap(v.bv_page); - err;}), ({ - w = v; - err = f(&w, context);}) - ) - return err; + if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) && + !iov_iter_is_kvec(i)) + return; + i->iov_offset = state->iov_offset; + i->count = state->count; + /* + * For the *vec iters, nr_segs + iov is constant - if we increment + * the vec, then we also decrement the nr_segs count. Hence we don't + * need to track both of these, just one is enough and we can deduct + * the other from that. ITER_KVEC and ITER_IOVEC are the same struct + * size, so we can just increment the iov pointer as they are unionzed. + * ITER_BVEC _may_ be the same size on some archs, but on others it is + * not. Be safe and handle it separately. + */ + BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); + if (iov_iter_is_bvec(i)) + i->bvec -= state->nr_segs - i->nr_segs; + else + i->iov -= state->nr_segs - i->nr_segs; + i->nr_segs = state->nr_segs; } -EXPORT_SYMBOL(iov_iter_for_each_range); From 36ec31201a3da85a112dd368be04aee05c713459 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 4 Jan 2021 00:08:41 -0500 Subject: [PATCH 0021/4345] saner calling conventions for unlazy_child() [ Upstream commit ae66db45fd309fd1c6d4e846dfc8414dfec7d6ad ] same as for the previous commit - instead of 0/-ECHILD make it return true/false, rename to try_to_unlazy_child(). Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- fs/namei.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 4375565aca66..276a84286108 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -705,19 +705,19 @@ out: } /** - * unlazy_child - try to switch to ref-walk mode. + * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * @dentry: child of nd->path.dentry - * @seq: seq number to check dentry against - * Returns: 0 on success, -ECHILD on failure + * @dentry: next dentry to step into + * @seq: seq number to check @dentry against + * Returns: true on success, false on failure * - * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry - * for ref-walk mode. @dentry must be a path found by a do_lookup call on - * @nd. Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_child() failure and + * Similar to to try_to_unlazy(), but here we have the next dentry already + * picked by rcu-walk and want to legitimize that in addition to the current + * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. + * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ -static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq) +static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq) { BUG_ON(!(nd->flags & LOOKUP_RCU)); @@ -747,7 +747,7 @@ static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned se if (unlikely(!legitimize_root(nd))) goto out_dput; rcu_read_unlock(); - return 0; + return true; out2: nd->path.mnt = NULL; @@ -755,11 +755,11 @@ out1: nd->path.dentry = NULL; out: rcu_read_unlock(); - return -ECHILD; + return false; out_dput: rcu_read_unlock(); dput(dentry); - return -ECHILD; + return false; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) @@ -1374,7 +1374,7 @@ static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, return -ENOENT; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 0; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return -ECHILD; // *path might've been clobbered by __follow_mount_rcu() path->mnt = nd->path.mnt; @@ -1495,7 +1495,7 @@ static struct dentry *lookup_fast(struct nameidata *nd, status = d_revalidate(dentry, nd->flags); if (likely(status > 0)) return dentry; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return ERR_PTR(-ECHILD); if (unlikely(status == -ECHILD)) /* we'd been told to redo it in non-rcu mode */ From c1fe7bd3e1aa85865396b464b31f28b094a4353c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 17 Dec 2020 09:19:09 -0700 Subject: [PATCH 0022/4345] fs: add support for LOOKUP_CACHED [ Upstream commit 6c6ec2b0a3e0381d886d531bd1471dfdb1509237 ] io_uring always punts opens to async context, since there's no control over whether the lookup blocks or not. Add LOOKUP_CACHED to support just doing the fast RCU based lookups, which we know will not block. If we can do a cached path resolution of the filename, then we don't have to always punt lookups for a worker. During path resolution, we always do LOOKUP_RCU first. If that fails and we terminate LOOKUP_RCU, then fail a LOOKUP_CACHED attempt as well. Cc: Al Viro Signed-off-by: Jens Axboe Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- fs/namei.c | 9 +++++++++ include/linux/namei.h | 1 + 2 files changed, 10 insertions(+) diff --git a/fs/namei.c b/fs/namei.c index 276a84286108..d047778aff16 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -686,6 +686,8 @@ static bool try_to_unlazy(struct nameidata *nd) BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; + if (nd->flags & LOOKUP_CACHED) + goto out1; if (unlikely(!legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) @@ -722,6 +724,8 @@ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsi BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; + if (nd->flags & LOOKUP_CACHED) + goto out2; if (unlikely(!legitimize_links(nd))) goto out2; if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq))) @@ -792,6 +796,7 @@ static int complete_walk(struct nameidata *nd) */ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; + nd->flags &= ~LOOKUP_CACHED; if (!try_to_unlazy(nd)) return -ECHILD; } @@ -2204,6 +2209,10 @@ static const char *path_init(struct nameidata *nd, unsigned flags) int error; const char *s = nd->name->name; + /* LOOKUP_CACHED requires RCU, ask caller to retry */ + if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) + return ERR_PTR(-EAGAIN); + if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) diff --git a/include/linux/namei.h b/include/linux/namei.h index a4bb992623c4..b9605b2b46e7 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -46,6 +46,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ +#define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) From 146fe79fff13fea7b5f3a9e913689e07fd4e6432 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 15 Feb 2021 12:03:23 -0500 Subject: [PATCH 0023/4345] fix handling of nd->depth on LOOKUP_CACHED failures in try_to_unlazy* [ Upstream commit eacd9aa8cedeb412842c7b339adbaa0477fdd5ad ] After switching to non-RCU mode, we want nd->depth to match the number of entries in nd->stack[] that need eventual path_put(). legitimize_links() takes care of that on failures; unfortunately, failure exits added for LOOKUP_CACHED do not. We could add the logics for that into those failure exits, both in try_to_unlazy() and in try_to_unlazy_next(), but since both checks are immediately followed by legitimize_links() and there's no calls of legitimize_links() other than those two... It's easier to move the check (and required handling of nd->depth on failure) into legitimize_links() itself. [caught by Jens: ... and since we are zeroing ->depth here, we need to do drop_links() first] Fixes: 6c6ec2b0a3e0 "fs: add support for LOOKUP_CACHED" Tested-by: Jens Axboe Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- fs/namei.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index d047778aff16..ec6121fb21d8 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -630,6 +630,11 @@ static inline bool legitimize_path(struct nameidata *nd, static bool legitimize_links(struct nameidata *nd) { int i; + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + return false; + } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { @@ -686,8 +691,6 @@ static bool try_to_unlazy(struct nameidata *nd) BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; - if (nd->flags & LOOKUP_CACHED) - goto out1; if (unlikely(!legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) @@ -724,8 +727,6 @@ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsi BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; - if (nd->flags & LOOKUP_CACHED) - goto out2; if (unlikely(!legitimize_links(nd))) goto out2; if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq))) From 0cf0ce8fb5b10d669072345ea855de112d0e0a43 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 6 Apr 2021 12:33:07 -0400 Subject: [PATCH 0024/4345] Make sure nd->path.mnt and nd->path.dentry are always valid pointers [ Upstream commit 7d01ef7585c07afaf487759a48486228cd065726 ] Initialize them in set_nameidata() and make sure that terminate_walk() clears them once the pointers become potentially invalid (i.e. we leave RCU mode or drop them in non-RCU one). Currently we have "path_init() always initializes them and nobody accesses them outside of path_init()/terminate_walk() segments", which is asking for trouble. With that change we would have nd->path.{mnt,dentry} 1) always valid - NULL or pointing to currently allocated objects. 2) non-NULL while we are successfully walking 3) NULL when we are not walking at all 4) contributing to refcounts whenever non-NULL outside of RCU mode. Fixes: 6c6ec2b0a3e0 ("fs: add support for LOOKUP_CACHED") Reported-by: syzbot+c88a7030da47945a3cc3@syzkaller.appspotmail.com Tested-by: Christian Brauner Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- fs/namei.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index ec6121fb21d8..fc7d562115ae 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -529,6 +529,8 @@ static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) p->stack = p->internal; p->dfd = dfd; p->name = name; + p->path.mnt = NULL; + p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; @@ -602,6 +604,8 @@ static void terminate_walk(struct nameidata *nd) rcu_read_unlock(); } nd->depth = 0; + nd->path.mnt = NULL; + nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ @@ -2243,8 +2247,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags) } nd->root.mnt = NULL; - nd->path.mnt = NULL; - nd->path.dentry = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { From 5683caa7350f389d099b72bfdb289d2073286e32 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 17 Dec 2020 09:19:10 -0700 Subject: [PATCH 0025/4345] fs: expose LOOKUP_CACHED through openat2() RESOLVE_CACHED [ Upstream commit 99668f618062816ca7ba639b007eb145b9d3d41e ] Now that we support non-blocking path resolution internally, expose it via openat2() in the struct open_how ->resolve flags. This allows applications using openat2() to limit path resolution to the extent that it is already cached. If the lookup cannot be satisfied in a non-blocking manner, openat2(2) will return -1/-EAGAIN. Cc: Al Viro Signed-off-by: Jens Axboe Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- fs/open.c | 6 ++++++ include/linux/fcntl.h | 2 +- include/uapi/linux/openat2.h | 4 ++++ 3 files changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/open.c b/fs/open.c index 3aaaad47d9ca..b3fbb4300fc9 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1099,6 +1099,12 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; + if (how->resolve & RESOLVE_CACHED) { + /* Don't bother even trying for create/truncate/tmpfile open */ + if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + lookup_flags |= LOOKUP_CACHED; + } op->lookup_flags = lookup_flags; return 0; diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 921e750843e6..766fcd973beb 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -19,7 +19,7 @@ /* List of all valid flags for the how->resolve argument: */ #define VALID_RESOLVE_FLAGS \ (RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \ - RESOLVE_BENEATH | RESOLVE_IN_ROOT) + RESOLVE_BENEATH | RESOLVE_IN_ROOT | RESOLVE_CACHED) /* List of all open_how "versions". */ #define OPEN_HOW_SIZE_VER0 24 /* sizeof first published struct */ diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h index 58b1eb711360..a5feb7604948 100644 --- a/include/uapi/linux/openat2.h +++ b/include/uapi/linux/openat2.h @@ -35,5 +35,9 @@ struct open_how { #define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." be scoped inside the dirfd (similar to chroot(2)). */ +#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be + completed through cached lookup. May + return -EAGAIN if that's not + possible. */ #endif /* _UAPI_LINUX_OPENAT2_H */ From 0b8cd5d814cb53d4109d2ba5e73dab38bf49a3b7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 23 Feb 2021 09:44:37 -0300 Subject: [PATCH 0026/4345] tools headers UAPI: Sync openat2.h with the kernel sources [ Upstream commit 1e61463cfcd0b3e7a19ba36b8a98c64ebaac5c6e ] To pick the changes in: 99668f618062816c ("fs: expose LOOKUP_CACHED through openat2() RESOLVE_CACHED") That don't result in any change in tooling, only silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/openat2.h' differs from latest version at 'include/uapi/linux/openat2.h' diff -u tools/include/uapi/linux/openat2.h include/uapi/linux/openat2.h Cc: Al Viro Cc: Jens Axboe Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/include/uapi/linux/openat2.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h index 58b1eb711360..a5feb7604948 100644 --- a/tools/include/uapi/linux/openat2.h +++ b/tools/include/uapi/linux/openat2.h @@ -35,5 +35,9 @@ struct open_how { #define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." be scoped inside the dirfd (similar to chroot(2)). */ +#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be + completed through cached lookup. May + return -EAGAIN if that's not + possible. */ #endif /* _UAPI_LINUX_OPENAT2_H */ From 069ac28d92432dd7cdac0a2c141a1b3b8d4330d5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 5 Sep 2020 11:13:35 -0600 Subject: [PATCH 0027/4345] net: provide __sys_shutdown_sock() that takes a socket [ Upstream commit b713c195d59332277a31a59c91f755e53b5b302b ] No functional changes in this patch, needed to provide io_uring support for shutdown(2). Cc: netdev@vger.kernel.org Cc: David S. Miller Acked-by: Jakub Kicinski Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/socket.h | 1 + net/socket.c | 15 ++++++++++++--- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/include/linux/socket.h b/include/linux/socket.h index 9aa530d497da..42222a84167f 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -436,5 +436,6 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); +extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); #endif /* _LINUX_SOCKET_H */ diff --git a/net/socket.c b/net/socket.c index bcf68b150fe2..c11b5239ef05 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2181,6 +2181,17 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, * Shutdown a socket. */ +int __sys_shutdown_sock(struct socket *sock, int how) +{ + int err; + + err = security_socket_shutdown(sock, how); + if (!err) + err = sock->ops->shutdown(sock, how); + + return err; +} + int __sys_shutdown(int fd, int how) { int err, fput_needed; @@ -2188,9 +2199,7 @@ int __sys_shutdown(int fd, int how) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { - err = security_socket_shutdown(sock, how); - if (!err) - err = sock->ops->shutdown(sock, how); + err = __sys_shutdown_sock(sock, how); fput_light(sock->file, fput_needed); } return err; From ad0b0137953a2c973958dadf6d222e120e278856 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 25 Aug 2021 12:25:44 +0100 Subject: [PATCH 0028/4345] net: add accept helper not installing fd [ Upstream commit d32f89da7fa8ccc8b3fb8f909d61e42b9bc39329 ] Introduce and reuse a helper that acts similarly to __sys_accept4_file() but returns struct file instead of installing file descriptor. Will be used by io_uring. Signed-off-by: Pavel Begunkov Acked-by: Jakub Kicinski Signed-off-by: Jens Axboe Acked-by: David S. Miller Link: https://lore.kernel.org/r/c57b9e8e818d93683a3d24f8ca50ca038d1da8c4.1629888991.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/socket.h | 3 ++ net/socket.c | 67 +++++++++++++++++++++++------------------- 2 files changed, 39 insertions(+), 31 deletions(-) diff --git a/include/linux/socket.h b/include/linux/socket.h index 42222a84167f..c3b35d18bcd3 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -421,6 +421,9 @@ extern int __sys_accept4_file(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags, unsigned long nofile); +extern struct file *do_accept(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); diff --git a/net/socket.c b/net/socket.c index c11b5239ef05..56c218dc80ce 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1688,30 +1688,22 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return __sys_listen(fd, backlog); } -int __sys_accept4_file(struct file *file, unsigned file_flags, +struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile) + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; - int err, len, newfd; + int err, len; struct sockaddr_storage address; - if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) - return -EINVAL; - - if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) - flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - sock = sock_from_file(file, &err); if (!sock) - goto out; + return ERR_PTR(err); - err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out; + return ERR_PTR(-ENFILE); newsock->type = sock->type; newsock->ops = sock->ops; @@ -1722,18 +1714,9 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, */ __module_get(newsock->ops->owner); - newfd = __get_unused_fd_flags(flags, nofile); - if (unlikely(newfd < 0)) { - err = newfd; - sock_release(newsock); - goto out; - } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); - if (IS_ERR(newfile)) { - err = PTR_ERR(newfile); - put_unused_fd(newfd); - goto out; - } + if (IS_ERR(newfile)) + return newfile; err = security_socket_accept(sock, newsock); if (err) @@ -1758,16 +1741,38 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, } /* File flags are not inherited via accept() unlike another OSes. */ - - fd_install(newfd, newfile); - err = newfd; -out: - return err; + return newfile; out_fd: fput(newfile); - put_unused_fd(newfd); - goto out; + return ERR_PTR(err); +} +int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags, + unsigned long nofile) +{ + struct file *newfile; + int newfd; + + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + + newfd = __get_unused_fd_flags(flags, nofile); + if (unlikely(newfd < 0)) + return newfd; + + newfile = do_accept(file, file_flags, upeer_sockaddr, upeer_addrlen, + flags); + if (IS_ERR(newfile)) { + put_unused_fd(newfd); + return PTR_ERR(newfile); + } + fd_install(newfd, newfile); + return newfd; } /* From 52cfde6bbf64f7f058efa805c6dbb6332d4de6fa Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Oct 2020 14:32:27 -0600 Subject: [PATCH 0029/4345] signal: Add task_sigpending() helper [ Upstream commit 5c251e9dc0e127bac6fc5b8e6696363d2e35f515 ] This is in preparation for maintaining signal_pending() as the decider of whether or not a schedule() loop should be broken, or continue sleeping. This is different than the core signal use cases, which really need to know whether an actual signal is pending or not. task_sigpending() returns non-zero if TIF_SIGPENDING is set. Only core kernel use cases should care about the distinction between the two, make sure those use the task_sigpending() helper. Signed-off-by: Jens Axboe Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20201026203230.386348-2-axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman --- include/linux/sched/signal.h | 9 +++++++-- kernel/events/uprobes.c | 2 +- kernel/signal.c | 8 ++++---- 3 files changed, 12 insertions(+), 7 deletions(-) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 657640015b33..86e3b091a525 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -354,11 +354,16 @@ static inline int restart_syscall(void) return -ERESTARTNOINTR; } -static inline int signal_pending(struct task_struct *p) +static inline int task_sigpending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } +static inline int signal_pending(struct task_struct *p) +{ + return task_sigpending(p); +} + static inline int __fatal_signal_pending(struct task_struct *p) { return unlikely(sigismember(&p->pending.signal, SIGKILL)); @@ -366,7 +371,7 @@ static inline int __fatal_signal_pending(struct task_struct *p) static inline int fatal_signal_pending(struct task_struct *p) { - return signal_pending(p) && __fatal_signal_pending(p); + return task_sigpending(p) && __fatal_signal_pending(p); } static inline int signal_pending_state(long state, struct task_struct *p) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e1bbb3b92921..826a2355da1e 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1973,7 +1973,7 @@ bool uprobe_deny_signal(void) WARN_ON_ONCE(utask->state != UTASK_SSTEP); - if (signal_pending(t)) { + if (task_sigpending(t)) { spin_lock_irq(&t->sighand->siglock); clear_tsk_thread_flag(t, TIF_SIGPENDING); spin_unlock_irq(&t->sighand->siglock); diff --git a/kernel/signal.c b/kernel/signal.c index d05f783d5a5e..92dc8dc63138 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -984,7 +984,7 @@ static inline bool wants_signal(int sig, struct task_struct *p) if (task_is_stopped_or_traced(p)) return false; - return task_curr(p) || !signal_pending(p); + return task_curr(p) || !task_sigpending(p); } static void complete_signal(int sig, struct task_struct *p, enum pid_type type) @@ -2813,7 +2813,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which) /* Remove the signals this thread can handle. */ sigandsets(&retarget, &retarget, &t->blocked); - if (!signal_pending(t)) + if (!task_sigpending(t)) signal_wake_up(t, 0); if (sigisemptyset(&retarget)) @@ -2847,7 +2847,7 @@ void exit_signals(struct task_struct *tsk) cgroup_threadgroup_change_end(tsk); - if (!signal_pending(tsk)) + if (!task_sigpending(tsk)) goto out; unblocked = tsk->blocked; @@ -2891,7 +2891,7 @@ long do_no_restart_syscall(struct restart_block *param) static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset) { - if (signal_pending(tsk) && !thread_group_empty(tsk)) { + if (task_sigpending(tsk) && !thread_group_empty(tsk)) { sigset_t newblocked; /* A set of now blocked but previously unblocked signals. */ sigandnsets(&newblocked, newset, ¤t->blocked); From 214f80e25176eb4d756bc9fe528ef7bf23d2f9a1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 26 Sep 2020 17:20:17 -0600 Subject: [PATCH 0030/4345] fs: make do_renameat2() take struct filename [ Upstream commit e886663cfd029b64a1d8da7efae7014526d884e9 ] Pass in the struct filename pointers instead of the user string, and update the three callers to do the same. This behaves like do_unlinkat(), which also takes a filename struct and puts it when it is done. Converting callers is then trivial. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/internal.h | 2 ++ fs/namei.c | 40 ++++++++++++++++++++++------------------ 2 files changed, 24 insertions(+), 18 deletions(-) diff --git a/fs/internal.h b/fs/internal.h index 5155f6ce95c7..95a4c9d9692f 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -77,6 +77,8 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, long do_rmdir(int dfd, struct filename *name); long do_unlinkat(int dfd, struct filename *name); int may_linkat(struct path *link); +int do_renameat2(int olddfd, struct filename *oldname, int newdfd, + struct filename *newname, unsigned int flags); /* * namespace.c diff --git a/fs/namei.c b/fs/namei.c index fc7d562115ae..4159c140fa47 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4353,8 +4353,8 @@ out: } EXPORT_SYMBOL(vfs_rename); -static int do_renameat2(int olddfd, const char __user *oldname, int newdfd, - const char __user *newname, unsigned int flags) +int do_renameat2(int olddfd, struct filename *from, int newdfd, + struct filename *to, unsigned int flags) { struct dentry *old_dentry, *new_dentry; struct dentry *trap; @@ -4362,32 +4362,30 @@ static int do_renameat2(int olddfd, const char __user *oldname, int newdfd, struct qstr old_last, new_last; int old_type, new_type; struct inode *delegated_inode = NULL; - struct filename *from; - struct filename *to; unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET; bool should_retry = false; - int error; + int error = -EINVAL; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) - return -EINVAL; + goto put_both; if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && (flags & RENAME_EXCHANGE)) - return -EINVAL; + goto put_both; if (flags & RENAME_EXCHANGE) target_flags = 0; retry: - from = filename_parentat(olddfd, getname(oldname), lookup_flags, - &old_path, &old_last, &old_type); + from = filename_parentat(olddfd, from, lookup_flags, &old_path, + &old_last, &old_type); if (IS_ERR(from)) { error = PTR_ERR(from); - goto exit; + goto put_new; } - to = filename_parentat(newdfd, getname(newname), lookup_flags, - &new_path, &new_last, &new_type); + to = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, + &new_type); if (IS_ERR(to)) { error = PTR_ERR(to); goto exit1; @@ -4480,34 +4478,40 @@ exit2: if (retry_estale(error, lookup_flags)) should_retry = true; path_put(&new_path); - putname(to); exit1: path_put(&old_path); - putname(from); if (should_retry) { should_retry = false; lookup_flags |= LOOKUP_REVAL; goto retry; } -exit: +put_both: + if (!IS_ERR(from)) + putname(from); +put_new: + if (!IS_ERR(to)) + putname(to); return error; } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { - return do_renameat2(olddfd, oldname, newdfd, newname, flags); + return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), + flags); } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { - return do_renameat2(olddfd, oldname, newdfd, newname, 0); + return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), + 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { - return do_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0); + return do_renameat2(AT_FDCWD, getname(oldname), AT_FDCWD, + getname(newname), 0); } int readlink_copy(char __user *buffer, int buflen, const char *link) From 57b20530363d127ab6a82e336275769258eb5f37 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 20 Nov 2020 17:14:40 -0600 Subject: [PATCH 0031/4345] file: Rename __close_fd_get_file close_fd_get_file [ Upstream commit 9fe83c43e71cdb8e5b9520bcb98706a2b3c680c8 ] The function close_fd_get_file is explicitly a variant of __close_fd[1]. Now that __close_fd has been renamed close_fd, rename close_fd_get_file to be consistent with close_fd. When __alloc_fd, __close_fd and __fd_install were introduced the double underscore indicated that the function took a struct files_struct parameter. The function __close_fd_get_file never has so the naming has always been inconsistent. This just cleans things up so there are not any lingering mentions or references __close_fd left in the code. [1] 80cd795630d6 ("binder: fix use-after-free due to ksys_close() during fdget()") Link: https://lkml.kernel.org/r/20201120231441.29911-23-ebiederm@xmission.com Signed-off-by: Eric W. Biederman Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 +- fs/file.c | 4 ++-- fs/io_uring.c | 2 +- include/linux/fdtable.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 4473adef2f5a..b403c7f063b0 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2255,7 +2255,7 @@ static void binder_deferred_fd_close(int fd) if (!twcb) return; init_task_work(&twcb->twork, binder_do_fd_close); - __close_fd_get_file(fd, &twcb->file); + close_fd_get_file(fd, &twcb->file); if (twcb->file) { filp_close(twcb->file, current->files); task_work_add(current, &twcb->twork, TWA_RESUME); diff --git a/fs/file.c b/fs/file.c index 8431dfde036c..aacc5bf80bd6 100644 --- a/fs/file.c +++ b/fs/file.c @@ -780,11 +780,11 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) } /* - * variant of __close_fd that gets a ref on the file for later fput. + * variant of close_fd that gets a ref on the file for later fput. * The caller must ensure that filp_close() called on the file, and then * an fput(). */ -int __close_fd_get_file(unsigned int fd, struct file **res) +int close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; struct file *file; diff --git a/fs/io_uring.c b/fs/io_uring.c index 84758e512a04..1d8173741310 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4270,7 +4270,7 @@ static int io_close(struct io_kiocb *req, bool force_nonblock, /* might be already done during nonblock submission */ if (!close->put_file) { - ret = __close_fd_get_file(close->fd, &close->put_file); + ret = close_fd_get_file(close->fd, &close->put_file); if (ret < 0) return (ret == -ENOENT) ? -EBADF : ret; } diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index a32bf47c593e..f1a99d3e5570 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -123,7 +123,7 @@ extern void __fd_install(struct files_struct *files, extern int __close_fd(struct files_struct *files, unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); -extern int __close_fd_get_file(unsigned int fd, struct file **res); +extern int close_fd_get_file(unsigned int fd, struct file **res); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); From d2136fc145be417e851dfe50703fac2af6aabe46 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 19 Jan 2021 15:41:52 -0700 Subject: [PATCH 0032/4345] fs: provide locked helper variant of close_fd_get_file() [ Upstream commit 53dec2ea74f2ef360e8455439be96a780baa6097 ] Assumes current->files->file_lock is already held on invocation. Helps the caller check the file before removing the fd, if it needs to. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/file.c | 48 +++++++++++++++++++++++++++++++----------------- fs/internal.h | 1 + 2 files changed, 32 insertions(+), 17 deletions(-) diff --git a/fs/file.c b/fs/file.c index aacc5bf80bd6..97a0cd31faec 100644 --- a/fs/file.c +++ b/fs/file.c @@ -22,6 +22,8 @@ #include #include +#include "internal.h" + unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ @@ -779,6 +781,32 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) return 0; } +/* + * See close_fd_get_file() below, this variant assumes current->files->file_lock + * is held. + */ +int __close_fd_get_file(unsigned int fd, struct file **res) +{ + struct files_struct *files = current->files; + struct file *file; + struct fdtable *fdt; + + fdt = files_fdtable(files); + if (fd >= fdt->max_fds) + goto out_err; + file = fdt->fd[fd]; + if (!file) + goto out_err; + rcu_assign_pointer(fdt->fd[fd], NULL); + __put_unused_fd(files, fd); + get_file(file); + *res = file; + return 0; +out_err: + *res = NULL; + return -ENOENT; +} + /* * variant of close_fd that gets a ref on the file for later fput. * The caller must ensure that filp_close() called on the file, and then @@ -787,27 +815,13 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) int close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; - struct file *file; - struct fdtable *fdt; + int ret; spin_lock(&files->file_lock); - fdt = files_fdtable(files); - if (fd >= fdt->max_fds) - goto out_unlock; - file = fdt->fd[fd]; - if (!file) - goto out_unlock; - rcu_assign_pointer(fdt->fd[fd], NULL); - __put_unused_fd(files, fd); + ret = __close_fd_get_file(fd, res); spin_unlock(&files->file_lock); - get_file(file); - *res = file; - return 0; -out_unlock: - spin_unlock(&files->file_lock); - *res = NULL; - return -ENOENT; + return ret; } void do_close_on_exec(struct files_struct *files) diff --git a/fs/internal.h b/fs/internal.h index 95a4c9d9692f..06d313b9beec 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -134,6 +134,7 @@ extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, const char *, const struct open_flags *); extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); +extern int __close_fd_get_file(unsigned int fd, struct file **res); long do_sys_ftruncate(unsigned int fd, loff_t length, int small); int chmod_common(const struct path *path, umode_t mode); From 3c295bd2ddaecf3509458c86bf7ba610042f3609 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Oct 2020 14:32:28 -0600 Subject: [PATCH 0033/4345] entry: Add support for TIF_NOTIFY_SIGNAL [ Upstream commit 12db8b690010ccfadf9d0b49a1e1798e47dbbe1a ] Add TIF_NOTIFY_SIGNAL handling in the generic entry code, which if set, will return true if signal_pending() is used in a wait loop. That causes an exit of the loop so that notify_signal tracehooks can be run. If the wait loop is currently inside a system call, the system call is restarted once task_work has been processed. In preparation for only having arch_do_signal() handle syscall restarts if _TIF_SIGPENDING isn't set, rename it to arch_do_signal_or_restart(). Pass in a boolean that tells the architecture specific signal handler if it should attempt to get a signal, or just process a potential syscall restart. For !CONFIG_GENERIC_ENTRY archs, add the TIF_NOTIFY_SIGNAL handling to get_signal(). This is done to minimize the needed architecture changes to support this feature. Signed-off-by: Jens Axboe Signed-off-by: Thomas Gleixner Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20201026203230.386348-3-axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/signal.c | 4 ++-- include/linux/entry-common.h | 11 ++++++++--- include/linux/entry-kvm.h | 4 ++-- include/linux/sched/signal.h | 11 ++++++++++- include/linux/tracehook.h | 27 +++++++++++++++++++++++++++ kernel/entry/common.c | 14 +++++++++++--- kernel/entry/kvm.c | 3 +++ kernel/signal.c | 14 ++++++++++++++ 8 files changed, 77 insertions(+), 11 deletions(-) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b001ba811cab..9eff48171532 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -798,11 +798,11 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -void arch_do_signal(struct pt_regs *regs) +void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { struct ksignal ksig; - if (get_signal(&ksig)) { + if (has_signal && get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); return; diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 7dff07713a07..1a128baf3628 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -37,6 +37,10 @@ # define _TIF_UPROBE (0) #endif +#ifndef _TIF_NOTIFY_SIGNAL +# define _TIF_NOTIFY_SIGNAL (0) +#endif + /* * TIF flags handled in syscall_enter_from_user_mode() */ @@ -69,7 +73,7 @@ #define EXIT_TO_USER_MODE_WORK \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | \ + _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ ARCH_EXIT_TO_USER_MODE_WORK) /** @@ -259,12 +263,13 @@ static __always_inline void arch_exit_to_user_mode(void) { } #endif /** - * arch_do_signal - Architecture specific signal delivery function + * arch_do_signal_or_restart - Architecture specific signal delivery function * @regs: Pointer to currents pt_regs + * @has_signal: actual signal to handle * * Invoked from exit_to_user_mode_loop(). */ -void arch_do_signal(struct pt_regs *regs); +void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal); /** * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit() diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 0cef17afb41a..9b93f8584ff7 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -11,8 +11,8 @@ # define ARCH_XFER_TO_GUEST_MODE_WORK (0) #endif -#define XFER_TO_GUEST_MODE_WORK \ - (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ +#define XFER_TO_GUEST_MODE_WORK \ + (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL | \ _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK) struct kvm_vcpu; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 86e3b091a525..a5373a13ba2c 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -361,6 +361,15 @@ static inline int task_sigpending(struct task_struct *p) static inline int signal_pending(struct task_struct *p) { +#if defined(TIF_NOTIFY_SIGNAL) + /* + * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same + * behavior in terms of ensuring that we break out of wait loops + * so that notify signal callbacks can be processed. + */ + if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL))) + return 1; +#endif return task_sigpending(p); } @@ -508,7 +517,7 @@ extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); static inline void restore_saved_sigmask_unless(bool interrupted) { if (interrupted) - WARN_ON(!test_thread_flag(TIF_SIGPENDING)); + WARN_ON(!signal_pending(current)); else restore_saved_sigmask(); } diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index b480e1a07ed8..f7d82e4fafd6 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -198,4 +198,31 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) blkcg_maybe_throttle_current(); } +/* + * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This + * is currently used by TWA_SIGNAL based task_work, which requires breaking + * wait loops to ensure that task_work is noticed and run. + */ +static inline void tracehook_notify_signal(void) +{ +#if defined(TIF_NOTIFY_SIGNAL) + clear_thread_flag(TIF_NOTIFY_SIGNAL); + smp_mb__after_atomic(); + if (current->task_works) + task_work_run(); +#endif +} + +/* + * Called when we have work to process from exit_to_user_mode_loop() + */ +static inline void set_notify_signal(struct task_struct *task) +{ +#if defined(TIF_NOTIFY_SIGNAL) + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE)) + kick_process(task); +#endif +} + #endif /* */ diff --git a/kernel/entry/common.c b/kernel/entry/common.c index e289e6773292..09f58853f692 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -135,7 +135,15 @@ static __always_inline void exit_to_user_mode(void) } /* Workaround to allow gradual conversion of architecture code */ -void __weak arch_do_signal(struct pt_regs *regs) { } +void __weak arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { } + +static void handle_signal_work(struct pt_regs *regs, unsigned long ti_work) +{ + if (ti_work & _TIF_NOTIFY_SIGNAL) + tracehook_notify_signal(); + + arch_do_signal_or_restart(regs, ti_work & _TIF_SIGPENDING); +} static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, unsigned long ti_work) @@ -157,8 +165,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, if (ti_work & _TIF_PATCH_PENDING) klp_update_patch_state(current); - if (ti_work & _TIF_SIGPENDING) - arch_do_signal(regs); + if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) + handle_signal_work(regs, ti_work); if (ti_work & _TIF_NOTIFY_RESUME) { tracehook_notify_resume(regs); diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 2a3139dab109..049fd06b4c3d 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -8,6 +8,9 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) do { int ret; + if (ti_work & _TIF_NOTIFY_SIGNAL) + tracehook_notify_signal(); + if (ti_work & _TIF_SIGPENDING) { kvm_handle_signal_exit(vcpu); return -EINTR; diff --git a/kernel/signal.c b/kernel/signal.c index 92dc8dc63138..269382a93119 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2520,6 +2520,20 @@ bool get_signal(struct ksignal *ksig) struct signal_struct *signal = current->signal; int signr; + /* + * For non-generic architectures, check for TIF_NOTIFY_SIGNAL so + * that the arch handlers don't all have to do it. If we get here + * without TIF_SIGPENDING, just exit after running signal work. + */ +#ifdef TIF_NOTIFY_SIGNAL + if (!IS_ENABLED(CONFIG_GENERIC_ENTRY)) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) + tracehook_notify_signal(); + if (!task_sigpending(current)) + return false; + } +#endif + if (unlikely(uprobe_deny_signal())) return false; From eb42e7b3043167d21f90204df75fa21b6d4af3ff Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Oct 2020 14:32:30 -0600 Subject: [PATCH 0034/4345] task_work: Use TIF_NOTIFY_SIGNAL if available [ Upstream commit 114518eb6430b832d2f9f5a008043b913ccf0e24 ] If the arch supports TIF_NOTIFY_SIGNAL, then use that for TWA_SIGNAL as it's more efficient than using the signal delivery method. This is especially true on threaded applications, where ->sighand is shared across threads, but it's also lighter weight on non-shared cases. io_uring is a heavy consumer of TWA_SIGNAL based task_work. A test with threads shows a nice improvement running an io_uring based echo server. stock kernel: 0.01% <= 0.1 milliseconds 95.86% <= 0.2 milliseconds 98.27% <= 0.3 milliseconds 99.71% <= 0.4 milliseconds 100.00% <= 0.5 milliseconds 100.00% <= 0.6 milliseconds 100.00% <= 0.7 milliseconds 100.00% <= 0.8 milliseconds 100.00% <= 0.9 milliseconds 100.00% <= 1.0 milliseconds 100.00% <= 1.1 milliseconds 100.00% <= 2 milliseconds 100.00% <= 3 milliseconds 100.00% <= 3 milliseconds 1378930.00 requests per second ~1600% CPU 1.38M requests/second, and all 16 CPUs are maxed out. patched kernel: 0.01% <= 0.1 milliseconds 98.24% <= 0.2 milliseconds 99.47% <= 0.3 milliseconds 99.99% <= 0.4 milliseconds 100.00% <= 0.5 milliseconds 100.00% <= 0.6 milliseconds 100.00% <= 0.7 milliseconds 100.00% <= 0.8 milliseconds 100.00% <= 0.9 milliseconds 100.00% <= 1.2 milliseconds 1666111.38 requests per second ~1450% CPU 1.67M requests/second, and we're no longer just hammering on the sighand lock. The original reporter states: "For 5.7.15 my benchmark achieves 1.6M qps and system cpu is at ~80%. for 5.7.16 or later it achieves only 1M qps and the system cpu is is at ~100%" with the only difference there being that TWA_SIGNAL is used unconditionally in 5.7.16, since it's required to be able to handle the inability to run task_work if the application is waiting in the kernel already on an event that needs task_work run to be satisfied. Also see commit 0ba9c9edcd15. Reported-by: Roman Gershman Signed-off-by: Jens Axboe Signed-off-by: Thomas Gleixner Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20201026203230.386348-5-axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman --- kernel/task_work.c | 41 +++++++++++++++++++++++++++++------------ 1 file changed, 29 insertions(+), 12 deletions(-) diff --git a/kernel/task_work.c b/kernel/task_work.c index 8d6e1217c451..15b087286bea 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -5,6 +5,34 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ +/* + * TWA_SIGNAL signaling - use TIF_NOTIFY_SIGNAL, if available, as it's faster + * than TIF_SIGPENDING as there's no dependency on ->sighand. The latter is + * shared for threads, and can cause contention on sighand->lock. Even for + * the non-threaded case TIF_NOTIFY_SIGNAL is more efficient, as no locking + * or IRQ disabling is involved for notification (or running) purposes. + */ +static void task_work_notify_signal(struct task_struct *task) +{ +#if defined(TIF_NOTIFY_SIGNAL) + set_notify_signal(task); +#else + unsigned long flags; + + /* + * Only grab the sighand lock if we don't already have some + * task_work pending. This pairs with the smp_store_mb() + * in get_signal(), see comment there. + */ + if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) && + lock_task_sighand(task, &flags)) { + task->jobctl |= JOBCTL_TASK_WORK; + signal_wake_up(task, 0); + unlock_task_sighand(task, &flags); + } +#endif +} + /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback @@ -33,7 +61,6 @@ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; - unsigned long flags; do { head = READ_ONCE(task->task_works); @@ -49,17 +76,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work, set_notify_resume(task); break; case TWA_SIGNAL: - /* - * Only grab the sighand lock if we don't already have some - * task_work pending. This pairs with the smp_store_mb() - * in get_signal(), see comment there. - */ - if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) && - lock_task_sighand(task, &flags)) { - task->jobctl |= JOBCTL_TASK_WORK; - signal_wake_up(task, 0); - unlock_task_sighand(task, &flags); - } + task_work_notify_signal(task); break; default: WARN_ON_ONCE(1); From 4b1dcf8ec9b2f11b57f1ff5dcaa1f8575c7dacb5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Oct 2020 14:32:29 -0600 Subject: [PATCH 0035/4345] x86: Wire up TIF_NOTIFY_SIGNAL [ Upstream commit c8d5ed67936fddbe2ae845fc80397718006322d7 ] The generic entry code has support for TIF_NOTIFY_SIGNAL already. Just provide the TIF bit. [ tglx: Adopted to other TIF changes in x86 ] Signed-off-by: Jens Axboe Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20201026203230.386348-4-axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/thread_info.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index e701f29b4881..012c8ee93b67 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -93,6 +93,7 @@ struct thread_info { #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ #define TIF_SLD 18 /* Restore split lock detection on context switch */ +#define TIF_NOTIFY_SIGNAL 19 /* signal notifications exist */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ @@ -121,6 +122,7 @@ struct thread_info { #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SLD (1 << TIF_SLD) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) From 2dbb0354517b1ebef40890d05ce8362e99b86179 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 12 Oct 2020 07:15:37 -0600 Subject: [PATCH 0036/4345] arc: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 53855e12588743ea128ee31f913d1c6e2f1d32c8 ] Wire up TIF_NOTIFY_SIGNAL handling for arc. Cc: linux-snps-arc@lists.infradead.org Acked-by: Vineet Gupta Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/arc/include/asm/thread_info.h | 4 +++- arch/arc/kernel/entry.S | 3 ++- arch/arc/kernel/signal.c | 2 +- 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index f9eef0e8f0b7..c0942c24d401 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -79,6 +79,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SYSCALL_AUDIT 4 /* syscall auditing active */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_SYSCALL_TRACE 15 /* syscall trace active */ /* true if poll_idle() is polling TIF_NEED_RESCHED */ @@ -89,11 +90,12 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) #define _TIF_SIGPENDING (1< Date: Thu, 22 Oct 2020 20:09:23 -0600 Subject: [PATCH 0037/4345] arm64: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 192caabd4dd92c98d23ed4334d7596af05af2fb4 ] Wire up TIF_NOTIFY_SIGNAL handling for arm64. Cc: linux-arm-kernel@lists.infradead.org Acked-by: Will Deacon Acked-by: Catalin Marinas Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/thread_info.h | 5 ++++- arch/arm64/kernel/signal.c | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 1fbab854a51b..cdcf307764aa 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -68,6 +68,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ #define TIF_FSCHECK 5 /* Check FS is USER_DS on return */ #define TIF_MTE_ASYNC_FAULT 6 /* MTE Asynchronous Tag Check Fault */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing */ #define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */ @@ -98,10 +99,12 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_SVE (1 << TIF_SVE) #define _TIF_MTE_ASYNC_FAULT (1 << TIF_MTE_ASYNC_FAULT) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ - _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT) + _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT | \ + _TIF_NOTIFY_SIGNAL) #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 0dab5679a97d..b6fbbd527dd7 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -938,7 +938,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, (void __user *)NULL, current); } - if (thread_flags & _TIF_SIGPENDING) + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_flags & _TIF_NOTIFY_RESUME) { From fe137f46d41f90e1a36134e7876db897a25b7926 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:10:55 -0600 Subject: [PATCH 0038/4345] m68k: add support for TIF_NOTIFY_SIGNAL [ Upstream commit e660653cd9f2df470d156c249631f68b9dee51ee ] Wire up TIF_NOTIFY_SIGNAL handling for m68k. Cc: linux-m68k@lists.linux-m68k.org Acked-by: Geert Uytterhoeven Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/m68k/include/asm/thread_info.h | 1 + arch/m68k/kernel/signal.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h index 3689c6718c88..15a757073fa5 100644 --- a/arch/m68k/include/asm/thread_info.h +++ b/arch/m68k/include/asm/thread_info.h @@ -60,6 +60,7 @@ static inline struct thread_info *current_thread_info(void) * bits 0-7 are tested at every exception exit * bits 8-15 are also tested at syscall exit */ +#define TIF_NOTIFY_SIGNAL 4 #define TIF_NOTIFY_RESUME 5 /* callback before returning to user */ #define TIF_SIGPENDING 6 /* signal pending */ #define TIF_NEED_RESCHED 7 /* rescheduling necessary */ diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index fd916844a683..5d12736b4b28 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -1129,7 +1129,8 @@ static void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs) { - if (test_thread_flag(TIF_SIGPENDING)) + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || + test_thread_flag(TIF_SIGPENDING)) do_signal(regs); if (test_thread_flag(TIF_NOTIFY_RESUME)) From cf3c6486731979a78851428d9e45e6f943b5fa92 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:21:21 -0600 Subject: [PATCH 0039/4345] nios32: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 42020064274c235d720d9c4b7d9a678b133e59cf ] Wire up TIF_NOTIFY_SIGNAL handling for nios32. Cc: Ley Foon Tan Acked-by: Ley Foon Tan Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/nios2/include/asm/thread_info.h | 2 ++ arch/nios2/kernel/signal.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/nios2/include/asm/thread_info.h b/arch/nios2/include/asm/thread_info.h index 7349a4fa635b..272d2c72a727 100644 --- a/arch/nios2/include/asm/thread_info.h +++ b/arch/nios2/include/asm/thread_info.h @@ -86,6 +86,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_MEMDIE 4 /* is terminating due to OOM killer */ #define TIF_SECCOMP 5 /* secure computing */ #define TIF_SYSCALL_AUDIT 6 /* syscall auditing active */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_RESTORE_SIGMASK 9 /* restore signal mask in do_signal() */ #define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling @@ -97,6 +98,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_RESTORE_SIGMASK (1 << TIF_RESTORE_SIGMASK) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c index 916180e4a997..68d626c4f1ba 100644 --- a/arch/nios2/kernel/signal.c +++ b/arch/nios2/kernel/signal.c @@ -309,7 +309,8 @@ asmlinkage int do_notify_resume(struct pt_regs *regs) if (!user_mode(regs)) return 0; - if (test_thread_flag(TIF_SIGPENDING)) { + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) { int restart = do_signal(regs); if (unlikely(restart)) { From 45b365bc6c1b57da984c70cae0c6c783ec094399 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:27:02 -0600 Subject: [PATCH 0040/4345] parisc: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 18cb3281285d2190c0605d2e53543802319bd1a1 ] Wire up TIF_NOTIFY_SIGNAL handling for parisc. Cc: linux-parisc@vger.kernel.org Acked-by: Helge Deller Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/parisc/include/asm/thread_info.h | 4 +++- arch/parisc/kernel/signal.c | 3 ++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h index 285757544cca..0bd38a972cea 100644 --- a/arch/parisc/include/asm/thread_info.h +++ b/arch/parisc/include/asm/thread_info.h @@ -52,6 +52,7 @@ struct thread_info { #define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_32BIT 4 /* 32 bit binary */ #define TIF_MEMDIE 5 /* is terminating due to OOM killer */ +#define TIF_NOTIFY_SIGNAL 6 /* signal notifications exist */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_NOTIFY_RESUME 8 /* callback before returning to user */ #define TIF_SINGLESTEP 9 /* single stepping? */ @@ -61,6 +62,7 @@ struct thread_info { #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_32BIT (1 << TIF_32BIT) @@ -72,7 +74,7 @@ struct thread_info { #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \ - _TIF_NEED_RESCHED) + _TIF_NEED_RESCHED | _TIF_NOTIFY_SIGNAL) #define _TIF_SYSCALL_TRACE_MASK (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \ _TIF_BLOCKSTEP | _TIF_SYSCALL_AUDIT | \ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT) diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 8d6c9b88eb3f..db1a47cf424d 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -609,7 +609,8 @@ do_signal(struct pt_regs *regs, long in_syscall) void do_notify_resume(struct pt_regs *regs, long in_syscall) { - if (test_thread_flag(TIF_SIGPENDING)) + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) do_signal(regs, in_syscall); if (test_thread_flag(TIF_NOTIFY_RESUME)) From abab3d4444b5f4732d741f45feb954fabb78af7f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 22 Oct 2020 20:11:56 -0600 Subject: [PATCH 0041/4345] powerpc: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 900f0713fdd730fab0f0bfa4a8ca4db2a8985bbe ] Wire up TIF_NOTIFY_SIGNAL handling for powerpc. Cc: linuxppc-dev@lists.ozlabs.org Acked-by: Michael Ellerman Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/thread_info.h | 5 ++++- arch/powerpc/kernel/signal.c | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 6de3517bea94..ff31d2fa2140 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -96,6 +96,7 @@ void arch_setup_new_exec(void); #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +#define TIF_NOTIFY_SIGNAL 3 /* signal notifications exist */ #define TIF_SYSCALL_EMU 4 /* syscall emulation active */ #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ #define TIF_PATCH_PENDING 6 /* pending live patching update */ @@ -121,6 +122,7 @@ void arch_setup_new_exec(void); #define _TIF_SYSCALL_TRACE (1<thread.regs); do_signal(current); } From 8ca2e5709922dc8c68323fdeeee099bb89a7c080 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:16:02 -0600 Subject: [PATCH 0042/4345] mips: add support for TIF_NOTIFY_SIGNAL [ Upstream commit f45c184bce15f4a314c0210519bc3b4aab408838 ] Wire up TIF_NOTIFY_SIGNAL handling for mips. Cc: linux-mips@vger.kernel.org Acked-By: Thomas Bogendoerfer Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/mips/include/asm/thread_info.h | 4 +++- arch/mips/kernel/signal.c | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index ee26f9a4575d..e2c352da3877 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -115,6 +115,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SECCOMP 4 /* secure computing */ #define TIF_NOTIFY_RESUME 5 /* callback before returning to user */ #define TIF_UPROBE 6 /* breakpointed or singlestepping */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_RESTORE_SIGMASK 9 /* restore signal mask in do_signal() */ #define TIF_USEDFPU 16 /* FPU was used by this task this quantum (SMP) */ #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ @@ -139,6 +140,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SECCOMP (1< Date: Fri, 9 Oct 2020 15:34:12 -0600 Subject: [PATCH 0043/4345] s390: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 75309018a24ddfb930c51bad8f4070b9bc2c923b ] Wire up TIF_NOTIFY_SIGNAL handling for s390. Cc: linux-s390@vger.kernel.org Acked-by: Heiko Carstens Acked-by: Sven Schnelle Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/s390/include/asm/thread_info.h | 2 ++ arch/s390/kernel/entry.S | 11 ++++++----- arch/s390/kernel/signal.c | 2 +- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 13a04fcf7762..0045341ade48 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -65,6 +65,7 @@ void arch_setup_new_exec(void); #define TIF_GUARDED_STORAGE 4 /* load guarded storage control block */ #define TIF_PATCH_PENDING 5 /* pending live patching update */ #define TIF_PGSTE 6 /* New mm's will use 4K page tables */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_ISOLATE_BP 8 /* Run process with isolated BP */ #define TIF_ISOLATE_BP_GUEST 9 /* Run KVM guests with isolated BP */ @@ -82,6 +83,7 @@ void arch_setup_new_exec(void); #define TIF_SYSCALL_TRACEPOINT 27 /* syscall tracepoint instrumentation */ #define _TIF_NOTIFY_RESUME BIT(TIF_NOTIFY_RESUME) +#define _TIF_NOTIFY_SIGNAL BIT(TIF_NOTIFY_SIGNAL) #define _TIF_SIGPENDING BIT(TIF_SIGPENDING) #define _TIF_NEED_RESCHED BIT(TIF_NEED_RESCHED) #define _TIF_UPROBE BIT(TIF_UPROBE) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 963e8cb936e2..88ecbcf097a3 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -52,7 +52,8 @@ STACK_SIZE = 1 << STACK_SHIFT STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE _TIF_WORK = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ - _TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING) + _TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING | \ + _TIF_NOTIFY_SIGNAL) _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ _TIF_SYSCALL_TRACEPOINT) _CIF_WORK = (_CIF_ASCE_PRIMARY | _CIF_ASCE_SECONDARY | _CIF_FPU) @@ -481,8 +482,8 @@ ENTRY(system_call) #endif TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART jo .Lsysc_syscall_restart - TSTMSK __TI_flags(%r12),_TIF_SIGPENDING - jo .Lsysc_sigpending + TSTMSK __TI_flags(%r12),(_TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL) + jnz .Lsysc_sigpending TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME jo .Lsysc_notify_resume TSTMSK __LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY) @@ -863,8 +864,8 @@ ENTRY(io_int_handler) TSTMSK __TI_flags(%r12),_TIF_PATCH_PENDING jo .Lio_patch_pending #endif - TSTMSK __TI_flags(%r12),_TIF_SIGPENDING - jo .Lio_sigpending + TSTMSK __TI_flags(%r12),(_TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL) + jnz .Lio_sigpending TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME jo .Lio_notify_resume TSTMSK __TI_flags(%r12),_TIF_GUARDED_STORAGE diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 9e900a8977bd..b27b6c1f058d 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -472,7 +472,7 @@ void do_signal(struct pt_regs *regs) current->thread.system_call = test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0; - if (get_signal(&ksig)) { + if (test_thread_flag(TIF_SIGPENDING) && get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ if (current->thread.system_call) { regs->int_code = current->thread.system_call; From dc808ffd9778aa013c792bb2ed369b84e346b67f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:47:28 -0600 Subject: [PATCH 0044/4345] um: add support for TIF_NOTIFY_SIGNAL [ Upstream commit a5b3cd32ff238b87e94d47b927aff117e22d13c0 ] Wire up TIF_NOTIFY_SIGNAL handling for um. Cc: linux-um@lists.infradead.org Acked-By: Anton Ivanov Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/um/include/asm/thread_info.h | 2 ++ arch/um/kernel/process.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h index 66ab6a07330b..e610e932cfe1 100644 --- a/arch/um/include/asm/thread_info.h +++ b/arch/um/include/asm/thread_info.h @@ -57,6 +57,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +#define TIF_NOTIFY_SIGNAL 3 /* signal notifications exist */ #define TIF_RESTART_BLOCK 4 #define TIF_MEMDIE 5 /* is terminating due to OOM killer */ #define TIF_SYSCALL_AUDIT 6 @@ -68,6 +69,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_MEMDIE (1 << TIF_MEMDIE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 8eb8b736abc1..067fb85fbf11 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -99,7 +99,8 @@ void interrupt_end(void) if (need_resched()) schedule(); - if (test_thread_flag(TIF_SIGPENDING)) + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) do_signal(regs); if (test_thread_flag(TIF_NOTIFY_RESUME)) tracehook_notify_resume(regs); From 3fde31e9626247e189dca71fe4723b8c722a676c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:36:35 -0600 Subject: [PATCH 0045/4345] sh: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 6d3a273355e3c8471ddf9e8ce9a7cc4472bf1ccc ] Wire up TIF_NOTIFY_SIGNAL handling for sh. Cc: linux-sh@vger.kernel.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/sh/include/asm/thread_info.h | 4 +++- arch/sh/kernel/signal_32.c | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h index 243ea5150aa0..598d0184ffea 100644 --- a/arch/sh/include/asm/thread_info.h +++ b/arch/sh/include/asm/thread_info.h @@ -105,6 +105,7 @@ extern void init_thread_xstate(void); #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +#define TIF_NOTIFY_SIGNAL 3 /* signal notifications exist */ #define TIF_SINGLESTEP 4 /* singlestepping active */ #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ #define TIF_SECCOMP 6 /* secure computing */ @@ -116,6 +117,7 @@ extern void init_thread_xstate(void); #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) @@ -132,7 +134,7 @@ extern void init_thread_xstate(void); #define _TIF_ALLWORK_MASK (_TIF_SYSCALL_TRACE | _TIF_SIGPENDING | \ _TIF_NEED_RESCHED | _TIF_SYSCALL_AUDIT | \ _TIF_SINGLESTEP | _TIF_NOTIFY_RESUME | \ - _TIF_SYSCALL_TRACEPOINT) + _TIF_SYSCALL_TRACEPOINT | _TIF_NOTIFY_SIGNAL) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK (_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \ diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index 1add47fd31f6..dd3092911efa 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -499,7 +499,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0, unsigned long thread_info_flags) { /* deal with pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs, save_r0); if (thread_info_flags & _TIF_NOTIFY_RESUME) From 12284aec880fc9f06d98d2fee28982c030cf99cf Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:24:46 -0600 Subject: [PATCH 0046/4345] openrisc: add support for TIF_NOTIFY_SIGNAL [ Upstream commit e181c0aa2e532af2b17128fbde699f8578cc0562 ] Wire up TIF_NOTIFY_SIGNAL handling for openrisc. Cc: openrisc@lists.librecores.org Acked-by: Stafford Horne Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/openrisc/include/asm/thread_info.h | 2 ++ arch/openrisc/kernel/signal.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h index 9afe68bc423b..4f9d2a261455 100644 --- a/arch/openrisc/include/asm/thread_info.h +++ b/arch/openrisc/include/asm/thread_info.h @@ -98,6 +98,7 @@ register struct thread_info *current_thread_info_reg asm("r10"); #define TIF_SINGLESTEP 4 /* restore singlestep on return to user * mode */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_SYSCALL_TRACEPOINT 8 /* for ftrace syscall instrumentation */ #define TIF_RESTORE_SIGMASK 9 #define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling * TIF_NEED_RESCHED @@ -109,6 +110,7 @@ register struct thread_info *current_thread_info_reg asm("r10"); #define _TIF_SIGPENDING (1< Date: Fri, 9 Oct 2020 14:39:00 -0600 Subject: [PATCH 0047/4345] csky: add support for TIF_NOTIFY_SIGNAL [ Upstream commit f3924d763c8af4c5d441b666c01f4de03ac9449e ] Wire up TIF_NOTIFY_SIGNAL handling for csky. Cc: linux-csky@vger.kernel.org Acked-by: Guo Ren Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/csky/include/asm/thread_info.h | 5 ++++- arch/csky/kernel/signal.c | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/csky/include/asm/thread_info.h b/arch/csky/include/asm/thread_info.h index 68e7a1227170..21456a3737c2 100644 --- a/arch/csky/include/asm/thread_info.h +++ b/arch/csky/include/asm/thread_info.h @@ -64,6 +64,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_TRACE 4 /* syscall trace active */ #define TIF_SYSCALL_TRACEPOINT 5 /* syscall tracepoint instrumentation */ #define TIF_SYSCALL_AUDIT 6 /* syscall auditing */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ #define TIF_POLLING_NRFLAG 16 /* poll_idle() is TIF_NEED_RESCHED */ #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 20 /* restore signal mask in do_signal() */ @@ -75,6 +76,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_MEMDIE (1 << TIF_MEMDIE) @@ -82,7 +84,8 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_UPROBE) + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NOTIFY_SIGNAL) #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP) diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c index 243228b0aa07..f7c1677e5971 100644 --- a/arch/csky/kernel/signal.c +++ b/arch/csky/kernel/signal.c @@ -261,7 +261,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, uprobe_notify_resume(regs); /* Handle pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) { From 19f3e328b4c6202198f27a3b899811d4a118333f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 14:45:22 -0600 Subject: [PATCH 0048/4345] hexagon: add support for TIF_NOTIFY_SIGNAL [ Upstream commit aeec8193578a71d0aee21218351849d38121ce90 ] Wire up TIF_NOTIFY_SIGNAL handling for hexagon. Cc: linux-hexagon@vger.kernel.org Acked-by: Brian Cain Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/hexagon/include/asm/thread_info.h | 2 ++ arch/hexagon/kernel/process.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h index 563da1986464..535976665bf0 100644 --- a/arch/hexagon/include/asm/thread_info.h +++ b/arch/hexagon/include/asm/thread_info.h @@ -95,6 +95,7 @@ register struct thread_info *__current_thread_info asm(QUOTED_THREADINFO_REG); #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SINGLESTEP 4 /* restore ss @ return to usr mode */ #define TIF_RESTORE_SIGMASK 6 /* restore sig mask in do_signal() */ +#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_MEMDIE 17 /* OOM killer killed process */ @@ -103,6 +104,7 @@ register struct thread_info *__current_thread_info asm(QUOTED_THREADINFO_REG); #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) /* work to do on interrupt/exception return - All but TIF_SYSCALL_TRACE */ #define _TIF_WORK_MASK (0x0000FFFF & ~_TIF_SYSCALL_TRACE) diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 67767c5ed98c..6a980cba7b29 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -174,7 +174,7 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags) return 1; } - if (thread_info_flags & _TIF_SIGPENDING) { + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { do_signal(regs); return 1; } From 02d383a59cbf8b7292947895604a2f9103f4f862 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:13:57 -0600 Subject: [PATCH 0049/4345] microblaze: add support for TIF_NOTIFY_SIGNAL [ Upstream commit f4ea089e429e0d366cd1a34a2cbe3c7b13d98d75 ] Wire up TIF_NOTIFY_SIGNAL handling for microblaze. Acked-by: Michal Simek Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/microblaze/include/asm/thread_info.h | 2 ++ arch/microblaze/kernel/signal.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h index ad8e8fcb90d3..44f5ca331862 100644 --- a/arch/microblaze/include/asm/thread_info.h +++ b/arch/microblaze/include/asm/thread_info.h @@ -107,6 +107,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ /* restore singlestep on return to user mode */ #define TIF_SINGLESTEP 4 +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_MEMDIE 6 /* is terminating due to OOM killer */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing active */ #define TIF_SECCOMP 10 /* secure computing */ @@ -119,6 +120,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c index f11a0ccccabc..5a8d173d7b75 100644 --- a/arch/microblaze/kernel/signal.c +++ b/arch/microblaze/kernel/signal.c @@ -313,7 +313,8 @@ static void do_signal(struct pt_regs *regs, int in_syscall) asmlinkage void do_notify_resume(struct pt_regs *regs, int in_syscall) { - if (test_thread_flag(TIF_SIGPENDING)) + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) do_signal(regs, in_syscall); if (test_thread_flag(TIF_NOTIFY_RESUME)) From 1bee9dbbcabbb77617fb257f964628b50ba2529c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 16:00:49 -0600 Subject: [PATCH 0050/4345] arm: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 32d59773da38cd83e497a70eb9754d4bbae3aeae ] Wire up TIF_NOTIFY_SIGNAL handling for arm. Cc: linux-arm-kernel@lists.infradead.org Acked-by: Russell King Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/arm/include/asm/thread_info.h | 7 ++++++- arch/arm/kernel/entry-common.S | 6 +++--- arch/arm/kernel/entry-v7m.S | 2 +- arch/arm/kernel/signal.c | 2 +- 4 files changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 536b6b979f63..eb7ce2747eb0 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -126,6 +126,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, * thread information flags: * TIF_USEDFPU - FPU was used by this task this quantum (SMP) * TIF_POLLING_NRFLAG - true if poll_idle() is polling TIF_NEED_RESCHED + * + * Any bit in the range of 0..15 will cause do_work_pending() to be invoked. */ #define TIF_SIGPENDING 0 /* signal pending */ #define TIF_NEED_RESCHED 1 /* rescheduling necessary */ @@ -135,6 +137,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ #define TIF_SECCOMP 7 /* seccomp syscall filtering active */ +#define TIF_NOTIFY_SIGNAL 8 /* signal notifications exist */ #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ @@ -148,6 +151,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_USING_IWMMXT (1 << TIF_USING_IWMMXT) /* Checks for any syscall work in entry-common.S */ @@ -158,7 +162,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, * Change these and you break ASM code in entry-common.S */ #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_UPROBE) + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NOTIFY_SIGNAL) #endif /* __KERNEL__ */ #endif /* __ASM_ARM_THREAD_INFO_H */ diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index bd619da73c84..9b3c737575e9 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -53,7 +53,7 @@ __ret_fast_syscall: cmp r2, #TASK_SIZE blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK + movs r1, r1, lsl #16 bne fast_work_pending @@ -90,7 +90,7 @@ __ret_fast_syscall: cmp r2, #TASK_SIZE blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK + movs r1, r1, lsl #16 beq no_work_pending UNWIND(.fnend ) ENDPROC(ret_fast_syscall) @@ -131,7 +131,7 @@ ENTRY(ret_to_user_from_irq) cmp r2, #TASK_SIZE blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] - tst r1, #_TIF_WORK_MASK + movs r1, r1, lsl #16 bne slow_work_pending no_work_pending: asm_trace_hardirqs_on save = 0 diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S index de1f20624be1..d0e898608d30 100644 --- a/arch/arm/kernel/entry-v7m.S +++ b/arch/arm/kernel/entry-v7m.S @@ -59,7 +59,7 @@ __irq_entry: get_thread_info tsk ldr r2, [tsk, #TI_FLAGS] - tst r2, #_TIF_WORK_MASK + movs r2, r2, lsl #16 beq 2f @ no work pending mov r0, #V7M_SCB_ICSR_PENDSVSET str r0, [r1, V7M_SCB_ICSR] @ raise PendSV diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 2f81d3af5f9a..a3a38d0a4c85 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -655,7 +655,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) if (unlikely(!user_mode(regs))) return 0; local_irq_enable(); - if (thread_flags & _TIF_SIGPENDING) { + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { int restart = do_signal(regs, syscall); if (unlikely(restart)) { /* From bf0b619593cd5560c55b10dbf290e6e148d1596c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:56:07 -0600 Subject: [PATCH 0051/4345] xtensa: add support for TIF_NOTIFY_SIGNAL [ Upstream commit bec58f40d6c5372d812c93cc3947f3bc97440e57 ] Wire up TIF_NOTIFY_SIGNAL handling for xtensa. Thanks to Max Filippov for making the asm correct. Cc: linux-xtensa@linux-xtensa.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/xtensa/include/asm/thread_info.h | 5 ++++- arch/xtensa/kernel/entry.S | 4 ++-- arch/xtensa/kernel/signal.c | 3 ++- 3 files changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h index 6acbbe0d87d3..a312333a9add 100644 --- a/arch/xtensa/include/asm/thread_info.h +++ b/arch/xtensa/include/asm/thread_info.h @@ -111,18 +111,21 @@ static inline struct thread_info *current_thread_info(void) #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ #define TIF_SINGLESTEP 3 /* restore singlestep on return to user mode */ #define TIF_SYSCALL_TRACEPOINT 4 /* syscall tracepoint instrumentation */ -#define TIF_MEMDIE 5 /* is terminating due to OOM killer */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_RESTORE_SIGMASK 6 /* restore signal mask in do_signal() */ #define TIF_NOTIFY_RESUME 7 /* callback before returning to user */ #define TIF_DB_DISABLED 8 /* debug trap disabled for syscall */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing active */ #define TIF_SECCOMP 10 /* secure computing */ +#define TIF_MEMDIE 11 /* is terminating due to OOM killer */ #define _TIF_SYSCALL_TRACE (1< Date: Thu, 8 Oct 2020 09:11:42 -0600 Subject: [PATCH 0052/4345] alpha: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 5a9a8897c253a075805401d38d987ec1ac1824b6 ] Wire up TIF_NOTIFY_SIGNAL handling for alpha. Cc: linux-alpha@vger.kernel.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/alpha/include/asm/thread_info.h | 2 ++ arch/alpha/kernel/entry.S | 2 +- arch/alpha/kernel/signal.c | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 807d7b9a1860..2592356e3215 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -62,6 +62,7 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SYSCALL_AUDIT 4 /* syscall audit active */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_DIE_IF_KERNEL 9 /* dik recursion lock */ #define TIF_MEMDIE 13 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 14 /* idle is polling for TIF_NEED_RESCHED */ @@ -71,6 +72,7 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define _TIF_NEED_RESCHED (1< Date: Fri, 9 Oct 2020 14:35:34 -0600 Subject: [PATCH 0053/4345] c6x: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 6d665a4d8b4264def0fbb72da3a500d9904ffe3e ] Wire up TIF_NOTIFY_SIGNAL handling for c6x. Cc: linux-c6x-dev@linux-c6x.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/c6x/include/asm/thread_info.h | 1 + arch/c6x/kernel/asm-offsets.c | 1 + arch/c6x/kernel/signal.c | 3 ++- 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/c6x/include/asm/thread_info.h b/arch/c6x/include/asm/thread_info.h index f70382844b96..dd8913d57189 100644 --- a/arch/c6x/include/asm/thread_info.h +++ b/arch/c6x/include/asm/thread_info.h @@ -82,6 +82,7 @@ struct thread_info *current_thread_info(void) #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_MEMDIE 17 /* OOM killer killed process */ diff --git a/arch/c6x/kernel/asm-offsets.c b/arch/c6x/kernel/asm-offsets.c index 0f8fde494875..4a264ef87dcb 100644 --- a/arch/c6x/kernel/asm-offsets.c +++ b/arch/c6x/kernel/asm-offsets.c @@ -116,6 +116,7 @@ void foo(void) DEFINE(_TIF_NOTIFY_RESUME, (1< #include +#include #include #include @@ -313,7 +314,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags, int syscall) { /* deal with pending signal delivery */ - if (thread_info_flags & (1 << TIF_SIGPENDING)) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs, syscall); if (thread_info_flags & (1 << TIF_NOTIFY_RESUME)) From 48e9e35d33d66519d12deea401487ea705deb596 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 14:42:33 -0600 Subject: [PATCH 0054/4345] h8300: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 2f9799ad0111ee742ccc02dd2ea2c87646746fc1 ] Wire up TIF_NOTIFY_SIGNAL handling for h8300. Cc: uclinux-h8-devel@lists.sourceforge.jp Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/h8300/include/asm/thread_info.h | 4 +++- arch/h8300/kernel/signal.c | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h index 0cdaa302d3d2..a518214d4ddd 100644 --- a/arch/h8300/include/asm/thread_info.h +++ b/arch/h8300/include/asm/thread_info.h @@ -73,6 +73,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SYSCALL_TRACEPOINT 8 /* for ftrace syscall instrumentation */ #define TIF_POLLING_NRFLAG 9 /* true if poll_idle() is polling TIF_NEED_RESCHED */ +#define TIF_NOTIFY_SIGNAL 10 /* signal notifications exist */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) @@ -83,6 +84,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) /* work to do in syscall trace */ #define _TIF_WORK_SYSCALL_MASK (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \ @@ -92,7 +94,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_ALLWORK_MASK (_TIF_SYSCALL_TRACE | _TIF_SIGPENDING | \ _TIF_NEED_RESCHED | _TIF_SYSCALL_AUDIT | \ _TIF_SINGLESTEP | _TIF_NOTIFY_RESUME | \ - _TIF_SYSCALL_TRACEPOINT) + _TIF_SYSCALL_TRACEPOINT | _TIF_NOTIFY_SIGNAL) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK (_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \ diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c index 75d9b7e626b2..75a1c36b105a 100644 --- a/arch/h8300/kernel/signal.c +++ b/arch/h8300/kernel/signal.c @@ -279,7 +279,7 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags) { - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) From 751fedb9ba5d4af62196d9b3014d4e62945c6e3f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 14:49:43 -0600 Subject: [PATCH 0055/4345] ia64: add support for TIF_NOTIFY_SIGNAL [ Upstream commit b269c229b0e89aedb7943c06673b56b6052cf5e5 ] Wire up TIF_NOTIFY_SIGNAL handling for ia64. Cc: linux-ia64@vger.kernel.org [axboe: added fixes from Mike Rapoport ] Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/ia64/include/asm/thread_info.h | 4 +++- arch/ia64/kernel/process.c | 3 ++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index 64a1011f6812..51d20cb37706 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -103,6 +103,7 @@ struct thread_info { #define TIF_SYSCALL_TRACE 2 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 3 /* syscall auditing active */ #define TIF_SINGLESTEP 4 /* restore singlestep on return to user mode */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notification exist */ #define TIF_NOTIFY_RESUME 6 /* resumption notification requested */ #define TIF_MEMDIE 17 /* is terminating due to OOM killer */ #define TIF_MCA_INIT 18 /* this task is processing MCA or INIT */ @@ -115,6 +116,7 @@ struct thread_info { #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SYSCALL_TRACEAUDIT (_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_MCA_INIT (1 << TIF_MCA_INIT) @@ -124,7 +126,7 @@ struct thread_info { /* "work to do on user-return" bits */ #define TIF_ALLWORK_MASK (_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SYSCALL_AUDIT|\ - _TIF_NEED_RESCHED|_TIF_SYSCALL_TRACE) + _TIF_NEED_RESCHED|_TIF_SYSCALL_TRACE|_TIF_NOTIFY_SIGNAL) /* like TIF_ALLWORK_BITS but sans TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT */ #define TIF_WORK_MASK (TIF_ALLWORK_MASK&~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT)) diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index c9ff8796b509..70649a5b3e88 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -171,7 +171,8 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall) } /* deal with pending signal delivery */ - if (test_thread_flag(TIF_SIGPENDING)) { + if (test_thread_flag(TIF_SIGPENDING) || + test_thread_flag(TIF_NOTIFY_SIGNAL)) { local_irq_enable(); /* force interrupt enable */ ia64_do_signal(scr, in_syscall); } From 57e833a0a03de1b1d1cfe0db2f9620b50df47502 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:18:43 -0600 Subject: [PATCH 0056/4345] nds32: add support for TIF_NOTIFY_SIGNAL [ Upstream commit b13e8bf615fe26fb6a6dfe1b5a1c65e1624dfee2 ] Wire up TIF_NOTIFY_SIGNAL handling for nds32. Cc: Nick Hu Cc: Greentime Hu Cc: Vincent Chen Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/nds32/include/asm/thread_info.h | 2 ++ arch/nds32/kernel/ex-exit.S | 2 +- arch/nds32/kernel/signal.c | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/nds32/include/asm/thread_info.h b/arch/nds32/include/asm/thread_info.h index c135111ec44e..d3967ad184f0 100644 --- a/arch/nds32/include/asm/thread_info.h +++ b/arch/nds32/include/asm/thread_info.h @@ -48,6 +48,7 @@ struct thread_info { #define TIF_NEED_RESCHED 2 #define TIF_SINGLESTEP 3 #define TIF_NOTIFY_RESUME 4 /* callback before returning to user */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_SYSCALL_TRACE 8 #define TIF_POLLING_NRFLAG 17 #define TIF_MEMDIE 18 @@ -57,6 +58,7 @@ struct thread_info { #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) diff --git a/arch/nds32/kernel/ex-exit.S b/arch/nds32/kernel/ex-exit.S index 6a2966c2d8c8..b30699911b81 100644 --- a/arch/nds32/kernel/ex-exit.S +++ b/arch/nds32/kernel/ex-exit.S @@ -120,7 +120,7 @@ work_pending: andi $p1, $r1, #_TIF_NEED_RESCHED bnez $p1, work_resched - andi $p1, $r1, #_TIF_SIGPENDING|#_TIF_NOTIFY_RESUME + andi $p1, $r1, #_TIF_SIGPENDING|#_TIF_NOTIFY_RESUME|#_TIF_NOTIFY_SIGNAL beqz $p1, no_work_pending move $r0, $sp ! 'regs' diff --git a/arch/nds32/kernel/signal.c b/arch/nds32/kernel/signal.c index 2acb94812af9..7e3ca430a223 100644 --- a/arch/nds32/kernel/signal.c +++ b/arch/nds32/kernel/signal.c @@ -376,7 +376,7 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int thread_flags) { - if (thread_flags & _TIF_SIGPENDING) + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_flags & _TIF_NOTIFY_RESUME) From 78a53ff02656da3c1e6a3e11e30ab23cf4bcb0f7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 14:29:17 -0600 Subject: [PATCH 0057/4345] riscv: add support for TIF_NOTIFY_SIGNAL [ Upstream commit 24a31b81e38309b1604f24520110aae1f83f3cbf ] Wire up TIF_NOTIFY_SIGNAL handling for riscv. Cc: linux-riscv@lists.infradead.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/riscv/include/asm/thread_info.h | 5 ++++- arch/riscv/kernel/signal.c | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index d79ae9d98999..c55e0a1f07a0 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -80,6 +80,7 @@ struct thread_info { #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing */ #define TIF_SECCOMP 8 /* syscall secure computing */ +#define TIF_NOTIFY_SIGNAL 9 /* signal notifications exist */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -88,9 +89,11 @@ struct thread_info { #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_WORK_MASK \ - (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED) + (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \ + _TIF_NOTIFY_SIGNAL) #define _TIF_SYSCALL_WORK \ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT | \ diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 529c123cf0a4..50a8225c58bc 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -312,7 +312,7 @@ asmlinkage __visible void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) { /* Handle pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) + if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) From e1402ba4df2025d66b81a8c215e452b95d1796d8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 15:44:37 -0600 Subject: [PATCH 0058/4345] sparc: add support for TIF_NOTIFY_SIGNAL [ Upstream commit f50a7052f5e70ee7a6a5e2ed08660994dc3df2a5 ] Wire up TIF_NOTIFY_SIGNAL handling for sparc. Cc: sparclinux@vger.kernel.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/sparc/include/asm/thread_info_32.h | 4 +++- arch/sparc/include/asm/thread_info_64.h | 6 ++++-- arch/sparc/kernel/signal_32.c | 2 +- arch/sparc/kernel/signal_64.c | 2 +- 4 files changed, 9 insertions(+), 5 deletions(-) diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h index 548b366165dd..45b4955b253f 100644 --- a/arch/sparc/include/asm/thread_info_32.h +++ b/arch/sparc/include/asm/thread_info_32.h @@ -104,6 +104,7 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */ +#define TIF_NOTIFY_SIGNAL 5 /* signal notifications exist */ #define TIF_USEDFPU 8 /* FPU was used by this task * this quantum (SMP) */ #define TIF_POLLING_NRFLAG 9 /* true if poll_idle() is polling @@ -115,11 +116,12 @@ register struct thread_info *current_thread_info_reg asm("g6"); #define _TIF_NOTIFY_RESUME (1< Date: Tue, 2 Mar 2021 17:22:11 -0700 Subject: [PATCH 0059/4345] ia64: don't call handle_signal() unless there's actually a signal queued [ Upstream commit f5f4fc4649ae542b1a25670b17aaf3cbb6187acc ] Sergei and John both reported that ia64 failed to boot in 5.11, and it was related to signals. Turns out the ia64 signal handling is a bit odd, it doesn't check the return value of get_signal() for whether there's a signal to deliver or not. With the introduction of TIF_NOTIFY_SIGNAL, then task_work could trigger it. Fix it by only calling handle_signal() if we actually have a real signal to deliver. This brings it in line with all other archs, too. Fixes: b269c229b0e8 ("ia64: add support for TIF_NOTIFY_SIGNAL") Reported-by: Sergei Trofimovich Reported-by: John Paul Adrian Glaubitz Tested-by: Sergei Trofimovich Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/ia64/kernel/signal.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index e67b22fc3c60..c1b299760bf7 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -341,7 +341,8 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall) * need to push through a forced SIGSEGV. */ while (1) { - get_signal(&ksig); + if (!get_signal(&ksig)) + break; /* * get_signal() may have run a debugger (via notify_parent()) From db911277a2b38b4ef98c7192728d5f4cba7863fe Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Wed, 6 Jan 2021 12:34:36 -0800 Subject: [PATCH 0060/4345] ARC: unbork 5.11 bootup: fix snafu in _TIF_NOTIFY_SIGNAL handling [ Upstream commit bb12433bf56e76789c6b08b36c546f745a6aa6e1 ] Linux 5.11.rcX was failing to boot on ARC HSDK board. Turns out we have a couple of issues, this being the first one, and I'm to blame as I didn't pay attention during review. TIF_NOTIFY_SIGNAL support requires checking multiple TIF_* bits in kernel return code path. Old code only needed to check a single bit so BBIT0 worked. New code needs to check multiple bits so AND instruction. So needs to use bit mask variant _TIF_SIGPENDING Cc: Jens Axboe Fixes: 53855e12588743ea128 ("arc: add support for TIF_NOTIFY_SIGNAL") Link: https://github.com/foss-for-synopsys-dwc-arc-processors/linux/issues/34 Signed-off-by: Vineet Gupta Signed-off-by: Greg Kroah-Hartman --- arch/arc/kernel/entry.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 676381f694d3..6ee9cb559808 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -308,7 +308,7 @@ resume_user_mode_begin: mov r0, sp ; pt_regs for arg to do_signal()/do_notify_resume() GET_CURR_THR_INFO_FLAGS r9 - and.f 0, r9, TIF_SIGPENDING|TIF_NOTIFY_SIGNAL + and.f 0, r9, _TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL bz .Lchk_notify_resume ; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs From 6e2bce21acb4f0c35521e68d74e4317fd6afd97d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Sep 2021 18:08:56 -0400 Subject: [PATCH 0061/4345] alpha: fix TIF_NOTIFY_SIGNAL handling [ Upstream commit e2c7554cc6d85f95e3c6635f270ec839ab9fe05e ] it needs to be added to _TIF_WORK_MASK, or we might not reach do_work_pending() in the first place... Fixes: 5a9a8897c253a "alpha: add support for TIF_NOTIFY_SIGNAL" Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- arch/alpha/include/asm/thread_info.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 2592356e3215..0ce1eee0924b 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -77,7 +77,7 @@ register struct thread_info *__current_thread_info __asm__("$8"); /* Work to do on interrupt/exception return. */ #define _TIF_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ - _TIF_NOTIFY_RESUME) + _TIF_NOTIFY_RESUME | _TIF_NOTIFY_SIGNAL) /* Work to do on any return to userspace. */ #define _TIF_ALLWORK_MASK (_TIF_WORK_MASK \ From 61bdeb142e8f7550826373295cb35b3571d70f62 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 16:01:33 -0600 Subject: [PATCH 0062/4345] task_work: remove legacy TWA_SIGNAL path [ Upstream commit 03941ccfda161c2680147fa5ab92aead2a79cac1 ] All archs now support TIF_NOTIFY_SIGNAL. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- kernel/task_work.c | 30 +----------------------------- 1 file changed, 1 insertion(+), 29 deletions(-) diff --git a/kernel/task_work.c b/kernel/task_work.c index 15b087286bea..9cde961875c0 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -5,34 +5,6 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ -/* - * TWA_SIGNAL signaling - use TIF_NOTIFY_SIGNAL, if available, as it's faster - * than TIF_SIGPENDING as there's no dependency on ->sighand. The latter is - * shared for threads, and can cause contention on sighand->lock. Even for - * the non-threaded case TIF_NOTIFY_SIGNAL is more efficient, as no locking - * or IRQ disabling is involved for notification (or running) purposes. - */ -static void task_work_notify_signal(struct task_struct *task) -{ -#if defined(TIF_NOTIFY_SIGNAL) - set_notify_signal(task); -#else - unsigned long flags; - - /* - * Only grab the sighand lock if we don't already have some - * task_work pending. This pairs with the smp_store_mb() - * in get_signal(), see comment there. - */ - if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) && - lock_task_sighand(task, &flags)) { - task->jobctl |= JOBCTL_TASK_WORK; - signal_wake_up(task, 0); - unlock_task_sighand(task, &flags); - } -#endif -} - /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback @@ -76,7 +48,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work, set_notify_resume(task); break; case TWA_SIGNAL: - task_work_notify_signal(task); + set_notify_signal(task); break; default: WARN_ON_ONCE(1); From 90a2c3821bbfe8435bde901953871576a1bf8c6d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 16:04:39 -0600 Subject: [PATCH 0063/4345] kernel: remove checking for TIF_NOTIFY_SIGNAL [ Upstream commit e296dc4996b8094ccde45d19090d804c4103513e ] It's available everywhere now, no need to check or add dummy defines. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/entry-common.h | 4 ---- include/linux/sched/signal.h | 2 -- include/linux/tracehook.h | 4 ---- kernel/signal.c | 2 -- 4 files changed, 12 deletions(-) diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 1a128baf3628..46c42479f950 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -37,10 +37,6 @@ # define _TIF_UPROBE (0) #endif -#ifndef _TIF_NOTIFY_SIGNAL -# define _TIF_NOTIFY_SIGNAL (0) -#endif - /* * TIF flags handled in syscall_enter_from_user_mode() */ diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index a5373a13ba2c..ae60f838ebb9 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -361,7 +361,6 @@ static inline int task_sigpending(struct task_struct *p) static inline int signal_pending(struct task_struct *p) { -#if defined(TIF_NOTIFY_SIGNAL) /* * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same * behavior in terms of ensuring that we break out of wait loops @@ -369,7 +368,6 @@ static inline int signal_pending(struct task_struct *p) */ if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL))) return 1; -#endif return task_sigpending(p); } diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index f7d82e4fafd6..ee9ab7dbc8c3 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -205,12 +205,10 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) */ static inline void tracehook_notify_signal(void) { -#if defined(TIF_NOTIFY_SIGNAL) clear_thread_flag(TIF_NOTIFY_SIGNAL); smp_mb__after_atomic(); if (current->task_works) task_work_run(); -#endif } /* @@ -218,11 +216,9 @@ static inline void tracehook_notify_signal(void) */ static inline void set_notify_signal(struct task_struct *task) { -#if defined(TIF_NOTIFY_SIGNAL) if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && !wake_up_state(task, TASK_INTERRUPTIBLE)) kick_process(task); -#endif } #endif /* */ diff --git a/kernel/signal.c b/kernel/signal.c index 269382a93119..845d4912b83a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2525,14 +2525,12 @@ bool get_signal(struct ksignal *ksig) * that the arch handlers don't all have to do it. If we get here * without TIF_SIGPENDING, just exit after running signal work. */ -#ifdef TIF_NOTIFY_SIGNAL if (!IS_ENABLED(CONFIG_GENERIC_ENTRY)) { if (test_thread_flag(TIF_NOTIFY_SIGNAL)) tracehook_notify_signal(); if (!task_sigpending(current)) return false; } -#endif if (unlikely(uprobe_deny_signal())) return false; From 4b4d2c79921a8327e9e853dc93c06b27edb3a859 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 10 Jun 2021 15:11:11 -0500 Subject: [PATCH 0064/4345] coredump: Limit what can interrupt coredumps [ Upstream commit 06af8679449d4ed282df13191fc52d5ba28ec536 ] Olivier Langlois has been struggling with coredumps being incompletely written in processes using io_uring. Olivier Langlois writes: > io_uring is a big user of task_work and any event that io_uring made a > task waiting for that occurs during the core dump generation will > generate a TIF_NOTIFY_SIGNAL. > > Here are the detailed steps of the problem: > 1. io_uring calls vfs_poll() to install a task to a file wait queue > with io_async_wake() as the wakeup function cb from io_arm_poll_handler() > 2. wakeup function ends up calling task_work_add() with TWA_SIGNAL > 3. task_work_add() sets the TIF_NOTIFY_SIGNAL bit by calling > set_notify_signal() The coredump code deliberately supports being interrupted by SIGKILL, and depends upon prepare_signal to filter out all other signals. Now that signal_pending includes wake ups for TIF_NOTIFY_SIGNAL this hack in dump_emitted by the coredump code no longer works. Make the coredump code more robust by explicitly testing for all of the wakeup conditions the coredump code supports. This prevents new wakeup conditions from breaking the coredump code, as well as fixing the current issue. The filesystem code that the coredump code uses already limits itself to only aborting on fatal_signal_pending. So it should not develop surprising wake-up reasons either. v2: Don't remove the now unnecessary code in prepare_signal. Cc: stable@vger.kernel.org Fixes: 12db8b690010 ("entry: Add support for TIF_NOTIFY_SIGNAL") Reported-by: Olivier Langlois Signed-off-by: "Eric W. Biederman" Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/coredump.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/coredump.c b/fs/coredump.c index edbaf61125c9..9d91e831ed0b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -523,7 +523,7 @@ static bool dump_interrupted(void) * but then we need to teach dump_write() to restart and clear * TIF_SIGPENDING. */ - return signal_pending(current); + return fatal_signal_pending(current) || freezing(current); } static void wait_for_dump_helpers(struct file *file) From 0f735cf52bd0b2aaca865e3d2e3dc276479e41ba Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 22 Mar 2021 09:39:12 -0600 Subject: [PATCH 0065/4345] kernel: allow fork with TIF_NOTIFY_SIGNAL pending [ Upstream commit 66ae0d1e2d9fe6ec70e73fcfdcf4b390e271c1ac ] fork() fails if signal_pending() is true, but there are two conditions that can lead to that: 1) An actual signal is pending. We want fork to fail for that one, like we always have. 2) TIF_NOTIFY_SIGNAL is pending, because the task has pending task_work. We don't need to make it fail for that case. Allow fork() to proceed if just task_work is pending, by changing the signal_pending() check to task_sigpending(). Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/fork.c b/kernel/fork.c index 252a40f14f72..b5cd5cdd3e67 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1942,7 +1942,7 @@ static __latent_entropy struct task_struct *copy_process( recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; - if (signal_pending(current)) + if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; From 000de389ad7b8094bcf714ee27e2362eb5054a1a Mon Sep 17 00:00:00 2001 From: Seth Forshee Date: Wed, 4 May 2022 13:08:40 -0500 Subject: [PATCH 0066/4345] entry/kvm: Exit to user mode when TIF_NOTIFY_SIGNAL is set [ Upstream commit 3e684903a8574ffc9475fdf13c4780a7adb506ad ] A livepatch transition may stall indefinitely when a kvm vCPU is heavily loaded. To the host, the vCPU task is a user thread which is spending a very long time in the ioctl(KVM_RUN) syscall. During livepatch transition, set_notify_signal() will be called on such tasks to interrupt the syscall so that the task can be transitioned. This interrupts guest execution, but when xfer_to_guest_mode_work() sees that TIF_NOTIFY_SIGNAL is set but not TIF_SIGPENDING it concludes that an exit to user mode is unnecessary, and guest execution is resumed without transitioning the task for the livepatch. This handling of TIF_NOTIFY_SIGNAL is incorrect, as set_notify_signal() is expected to break tasks out of interruptible kernel loops and cause them to return to userspace. Change xfer_to_guest_mode_work() to handle TIF_NOTIFY_SIGNAL the same as TIF_SIGPENDING, signaling to the vCPU run loop that an exit to userpsace is needed. Any pending task_work will be run when get_signal() is called from exit_to_user_mode_loop(), so there is no longer any need to run task work from xfer_to_guest_mode_work(). Suggested-by: "Eric W. Biederman" Cc: Petr Mladek Signed-off-by: Seth Forshee Message-Id: <20220504180840.2907296-1-sforshee@digitalocean.com> Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- kernel/entry/kvm.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 049fd06b4c3d..7b946847be78 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -8,10 +8,7 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) do { int ret; - if (ti_work & _TIF_NOTIFY_SIGNAL) - tracehook_notify_signal(); - - if (ti_work & _TIF_SIGPENDING) { + if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { kvm_handle_signal_exit(vcpu); return -EINTR; } From 320c8057eceb18c5d836fcbe0ffb0035fcfe28ff Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 17 Feb 2021 08:48:00 -0700 Subject: [PATCH 0067/4345] arch: setup PF_IO_WORKER threads like PF_KTHREAD [ Upstream commit 4727dc20e0422211a0e0c72b1ace4ed6096df8a6 ] PF_IO_WORKER are kernel threads too, but they aren't PF_KTHREAD in the sense that we don't assign ->set_child_tid with our own structure. Just ensure that every arch sets up the PF_IO_WORKER threads like kthreads in the arch implementation of copy_thread(). Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/alpha/kernel/process.c | 2 +- arch/arc/kernel/process.c | 2 +- arch/arm/kernel/process.c | 2 +- arch/arm64/kernel/process.c | 2 +- arch/csky/kernel/process.c | 2 +- arch/h8300/kernel/process.c | 2 +- arch/hexagon/kernel/process.c | 2 +- arch/ia64/kernel/process.c | 2 +- arch/m68k/kernel/process.c | 2 +- arch/microblaze/kernel/process.c | 2 +- arch/mips/kernel/process.c | 2 +- arch/nds32/kernel/process.c | 2 +- arch/nios2/kernel/process.c | 2 +- arch/openrisc/kernel/process.c | 2 +- arch/riscv/kernel/process.c | 2 +- arch/s390/kernel/process.c | 2 +- arch/sh/kernel/process_32.c | 2 +- arch/sparc/kernel/process_32.c | 2 +- arch/sparc/kernel/process_64.c | 2 +- arch/um/kernel/process.c | 2 +- arch/x86/kernel/process.c | 2 +- arch/xtensa/kernel/process.c | 2 +- 22 files changed, 22 insertions(+), 22 deletions(-) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 4c7b0414a3ff..08335b2294b3 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -249,7 +249,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childti->pcb.ksp = (unsigned long) childstack; childti->pcb.flags = 1; /* set FEN, clear everything else */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(childstack, 0, sizeof(struct switch_stack) + sizeof(struct pt_regs)); diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index a85e9c625ab5..8cf2caae93f1 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -191,7 +191,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childksp[0] = 0; /* fp */ childksp[1] = (unsigned long)ret_from_fork; /* blink */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(c_regs, 0, sizeof(struct pt_regs)); c_callee->r13 = kthread_arg; diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 9f199b1e8383..2647e48c537e 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -243,7 +243,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, thread->cpu_domain = get_domain(); #endif - if (likely(!(p->flags & PF_KTHREAD))) { + if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) { *childregs = *current_pt_regs(); childregs->ARM_r0 = 0; if (stack_start) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 22275d8518eb..3696dbcbfa80 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -398,7 +398,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, ptrauth_thread_init_kernel(p); - if (likely(!(p->flags & PF_KTHREAD))) { + if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) { *childregs = *current_pt_regs(); childregs->regs[0] = 0; diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index 69af6bc87e64..3d0ca22cd0e2 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -49,7 +49,7 @@ int copy_thread(unsigned long clone_flags, /* setup thread.sp for switch_to !!! */ p->thread.sp = (unsigned long)childstack; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); childstack->r15 = (unsigned long) ret_from_kernel_thread; childstack->r10 = kthread_arg; diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index bc1364db58fe..46b1342ce515 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -112,7 +112,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); childregs->retpc = (unsigned long) ret_from_kernel_thread; childregs->er4 = topstk; /* arg */ diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 6a980cba7b29..c61165c99ae0 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -73,7 +73,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, sizeof(*ss)); ss->lr = (unsigned long)ret_from_fork; p->thread.switch_sp = ss; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); /* r24 <- fn, r25 <- arg */ ss->r24 = usp; diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 70649a5b3e88..8159b7af5509 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -338,7 +338,7 @@ copy_thread(unsigned long clone_flags, unsigned long user_stack_base, ia64_drop_fpu(p); /* don't pick up stale state from a CPU's fph */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { if (unlikely(!user_stack_base)) { /* fork_idle() called us */ return 0; diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index 08359a6e058f..da83cc83e791 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -157,7 +157,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, */ p->thread.fs = get_fs().seg; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(frame, 0, sizeof(struct fork_frame)); frame->regs.sr = PS_S; diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index f99860771ff4..ee000ae17e39 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -59,7 +59,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, struct pt_regs *childregs = task_pt_regs(p); struct thread_info *ti = task_thread_info(p); - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* if we're creating a new kernel thread then just zeroing all * the registers. That's OK for a brand new thread.*/ memset(childregs, 0, sizeof(struct pt_regs)); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 75ebd8d7bd5d..98ecaf6f3edb 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -135,7 +135,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, /* Put the stack after the struct pt_regs. */ childksp = (unsigned long) childregs; p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ unsigned long status = p->thread.cp0_status; memset(childregs, 0, sizeof(struct pt_regs)); diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c index e01ad5d17224..c1327e552ec6 100644 --- a/arch/nds32/kernel/process.c +++ b/arch/nds32/kernel/process.c @@ -156,7 +156,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context)); - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); /* kernel thread fn */ p->thread.cpu_context.r6 = stack_start; diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 50b4eb19a6cc..c5f916ca6845 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -109,7 +109,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, struct switch_stack *childstack = ((struct switch_stack *)childregs) - 1; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childstack, 0, sizeof(struct switch_stack) + sizeof(struct pt_regs)); diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 3c98728cce24..83fba4ee4453 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -167,7 +167,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, sp -= sizeof(struct pt_regs); kregs = (struct pt_regs *)sp; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(kregs, 0, sizeof(struct pt_regs)); kregs->gpr[20] = usp; /* fn, kernel thread */ kregs->gpr[22] = arg; diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 9a8b2e60adcf..7868050ff426 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -114,7 +114,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, memset(&p->thread.s, 0, sizeof(p->thread.s)); /* p->thread holds context to be restored by __switch_to() */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); childregs->gp = gp_in_global; diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 137a170f47d4..bd7da4049707 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -127,7 +127,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, frame->sf.gprs[9] = (unsigned long) frame; /* Store access registers to kernel stack of new process. */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(&frame->childregs, 0, sizeof(struct pt_regs)); frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 80a5d1c66a51..1aa508eb0823 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -114,7 +114,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, childregs = task_pt_regs(p); p->thread.sp = (unsigned long) childregs; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); p->thread.pc = (unsigned long) ret_from_kernel_thread; childregs->regs[4] = arg; diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index a02363735915..0f9c606e1e78 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -309,7 +309,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, ti->ksp = (unsigned long) new_stack; p->thread.kregs = childregs; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { extern int nwindows; unsigned long psr; memset(new_stack, 0, STACKFRAME_SZ + TRACEREG_SZ); diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 6f8c7822fc06..7afd0a859a78 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -597,7 +597,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, sizeof(struct sparc_stackf)); t->fpsaved[0] = 0; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(child_trap_frame, 0, child_stack_sz); __thread_flag_byte_ptr(t)[TI_FLAG_BYTE_CWP] = (current_pt_regs()->tstate + 1) & TSTATE_CWP; diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 067fb85fbf11..e6c9b11b2033 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -157,7 +157,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct * p, unsigned long tls) { void (*handler)(void); - int kthread = current->flags & PF_KTHREAD; + int kthread = current->flags & (PF_KTHREAD | PF_IO_WORKER); int ret = 0; p->thread = (struct thread_struct) INIT_THREAD; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 383afcc1098b..4d46c52d9c05 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -162,7 +162,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, #endif /* Kernel thread ? */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { memset(childregs, 0, sizeof(struct pt_regs)); kthread_frame_init(frame, sp, arg); return 0; diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 397a7de56377..9534ef515d74 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -217,7 +217,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn, p->thread.sp = (unsigned long)childregs; - if (!(p->flags & PF_KTHREAD)) { + if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { struct pt_regs *regs = current_pt_regs(); unsigned long usp = usp_thread_fn ? usp_thread_fn : regs->areg[1]; From dd26e2cec74f88cb7910deec77897d04ade299bd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 23 Feb 2021 11:57:20 -0700 Subject: [PATCH 0068/4345] arch: ensure parisc/powerpc handle PF_IO_WORKER in copy_thread() [ Upstream commit 0100e6bbdbb79404e56939313662b42737026574 ] In the arch addition of PF_IO_WORKER, I missed parisc and powerpc for some reason. Fix that up, ensuring they handle PF_IO_WORKER like they do PF_KTHREAD in copy_thread(). Reported-by: Bruno Goncalves Fixes: 4727dc20e042 ("arch: setup PF_IO_WORKER threads like PF_KTHREAD") Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/process.c | 2 +- arch/powerpc/kernel/process.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index a92a23d6acd9..5e4381280c97 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -200,7 +200,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp, extern void * const ret_from_kernel_thread; extern void * const child_return; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(cregs, 0, sizeof(struct pt_regs)); if (!usp) /* idle thread */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index c43cc26bde5d..cf375d67eacb 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1684,7 +1684,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, /* Copy registers */ sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); From f0a5f0dc0131c6483908601f6e4907befb609c97 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher Date: Wed, 5 May 2021 13:03:10 +0200 Subject: [PATCH 0069/4345] x86/process: setup io_threads more like normal user space threads [ Upstream commit 50b7b6f29de3e18e9d6c09641256a0296361cfee ] As io_threads are fully set up USER threads it's clearer to separate the code path from the KTHREAD logic. The only remaining difference to user space threads is that io_threads never return to user space again. Instead they loop within the given worker function. The fact that they never return to user space means they don't have an user space thread stack. In order to indicate that to tools like gdb we reset the stack and instruction pointers to 0. This allows gdb attach to user space processes using io-uring, which like means that they have io_threads, without printing worrying message like this: warning: Selected architecture i386:x86-64 is not compatible with reported target architecture i386 warning: Architecture rejected target-supplied description The output will be something like this: (gdb) info threads Id Target Id Frame * 1 LWP 4863 "io_uring-cp-for" syscall () at ../sysdeps/unix/sysv/linux/x86_64/syscall.S:38 2 LWP 4864 "iou-mgr-4863" 0x0000000000000000 in ?? () 3 LWP 4865 "iou-wrk-4863" 0x0000000000000000 in ?? () (gdb) thread 3 [Switching to thread 3 (LWP 4865)] #0 0x0000000000000000 in ?? () (gdb) bt #0 0x0000000000000000 in ?? () Backtrace stopped: Cannot access memory at address 0x0 Fixes: 4727dc20e042 ("arch: setup PF_IO_WORKER threads like PF_KTHREAD") Link: https://lore.kernel.org/io-uring/044d0bad-6888-a211-e1d3-159a4aeed52d@polymtl.ca/T/#m1bbf5727e3d4e839603f6ec7ed79c7eebfba6267 Signed-off-by: Stefan Metzmacher cc: Linus Torvalds cc: Jens Axboe cc: Andy Lutomirski cc: linux-kernel@vger.kernel.org cc: io-uring@vger.kernel.org cc: x86@kernel.org Link: https://lore.kernel.org/r/20210505110310.237537-1-metze@samba.org Reviewed-by: Thomas Gleixner Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/process.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 4d46c52d9c05..5e17c3939dd1 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -162,7 +162,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, #endif /* Kernel thread ? */ - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(p->flags & PF_KTHREAD)) { memset(childregs, 0, sizeof(struct pt_regs)); kthread_frame_init(frame, sp, arg); return 0; @@ -178,6 +178,23 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, task_user_gs(p) = get_user_gs(current_pt_regs()); #endif + if (unlikely(p->flags & PF_IO_WORKER)) { + /* + * An IO thread is a user space thread, but it doesn't + * return to ret_after_fork(). + * + * In order to indicate that to tools like gdb, + * we reset the stack and instruction pointers. + * + * It does the same kernel frame setup to return to a kernel + * function that a kernel thread does. + */ + childregs->sp = 0; + childregs->ip = 0; + kthread_frame_init(frame, sp, arg); + return 0; + } + /* Set a new TLS for the child thread? */ if (clone_flags & CLONE_SETTLS) ret = set_new_tls(p, tls); From 9ded44b69c711455dbbddf6ec39b77ac41e4eed7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Mar 2021 09:05:22 -0600 Subject: [PATCH 0070/4345] kernel: stop masking signals in create_io_thread() [ Upstream commit b16b3855d89fba640996fefdd3a113c0aa0e380d ] This is racy - move the blocking into when the task is created and we're marking it as PF_IO_WORKER anyway. The IO threads are now prepared to handle signals like SIGSTOP as well, so clear that from the mask to allow proper stopping of IO threads. Acked-by: "Eric W. Biederman" Reported-by: Oleg Nesterov Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- kernel/fork.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index b5cd5cdd3e67..55c1a880a281 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1949,8 +1949,14 @@ static __latent_entropy struct task_struct *copy_process( p = dup_task_struct(current, node); if (!p) goto fork_out; - if (args->io_thread) + if (args->io_thread) { + /* + * Mark us an IO worker, and block any signal that isn't + * fatal or STOP + */ p->flags |= PF_IO_WORKER; + siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); + } /* * This _must_ happen before we call free_task(), i.e. before we jump @@ -2435,14 +2441,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) .stack_size = (unsigned long)arg, .io_thread = 1, }; - struct task_struct *tsk; - tsk = copy_process(NULL, 0, node, &args); - if (!IS_ERR(tsk)) { - sigfillset(&tsk->blocked); - sigdelsetmask(&tsk->blocked, sigmask(SIGKILL)); - } - return tsk; + return copy_process(NULL, 0, node, &args); } /* From 831cb78a2a5e86fe705ef4e3095c7cbc587c6a57 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Mar 2021 08:57:10 -0600 Subject: [PATCH 0071/4345] kernel: don't call do_exit() for PF_IO_WORKER threads [ Upstream commit 10442994ba195efef6fdcc0c3699e4633cb5161b ] Right now we're never calling get_signal() from PF_IO_WORKER threads, but in preparation for doing so, don't handle a fatal signal for them. The workers have state they need to cleanup when exiting, so just return instead of calling do_exit() on their behalf. The threads themselves will detect a fatal signal and do proper shutdown. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- kernel/signal.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/kernel/signal.c b/kernel/signal.c index 845d4912b83a..fb5473724f5d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2754,6 +2754,14 @@ relock: do_coredump(&ksig->info); } + /* + * PF_IO_WORKER threads will catch and exit on fatal signals + * themselves. They have cleanup that must be performed, so + * we cannot call do_exit() on their behalf. + */ + if (current->flags & PF_IO_WORKER) + goto out; + /* * Death signals, no core dump. */ @@ -2761,7 +2769,7 @@ relock: /* NOTREACHED */ } spin_unlock_irq(&sighand->siglock); - +out: ksig->sig = signr; return ksig->sig > 0; } From ed3005032993da7a3fe2e6095436e0bc2e83d011 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 1 Apr 2021 19:53:29 -0600 Subject: [PATCH 0072/4345] task_work: add helper for more targeted task_work canceling [ Upstream commit c7aab1a7c52b82d9afd7e03c398eb03dc2aa0507 ] The only exported helper we have right now is task_work_cancel(), which cancels any task_work from a given task where func matches the queued work item. This is a bit too coarse for some use cases. Add a task_work_cancel_match() that allows to more specifically target individual work items outside of purely the callback function used. task_work_cancel() can be trivially implemented on top of that, hence do so. Reviewed-by: Oleg Nesterov Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/task_work.h | 2 ++ kernel/task_work.c | 35 ++++++++++++++++++++++++++++------- 2 files changed, 30 insertions(+), 7 deletions(-) diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 0d848a1e9e62..5b8a93f288bb 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -22,6 +22,8 @@ enum task_work_notify_mode { int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); +struct callback_head *task_work_cancel_match(struct task_struct *task, + bool (*match)(struct callback_head *, void *data), void *data); struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); void task_work_run(void); diff --git a/kernel/task_work.c b/kernel/task_work.c index 9cde961875c0..e9316198c64b 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -59,18 +59,17 @@ int task_work_add(struct task_struct *task, struct callback_head *work, } /** - * task_work_cancel - cancel a pending work added by task_work_add() + * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work - * @func: identifies the work to remove - * - * Find the last queued pending work with ->func == @func and remove - * it from queue. + * @match: match function to call * * RETURNS: * The found work or NULL if not found. */ struct callback_head * -task_work_cancel(struct task_struct *task, task_work_func_t func) +task_work_cancel_match(struct task_struct *task, + bool (*match)(struct callback_head *, void *data), + void *data) { struct callback_head **pprev = &task->task_works; struct callback_head *work; @@ -86,7 +85,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func) */ raw_spin_lock_irqsave(&task->pi_lock, flags); while ((work = READ_ONCE(*pprev))) { - if (work->func != func) + if (!match(work, data)) pprev = &work->next; else if (cmpxchg(pprev, work, work->next) == work) break; @@ -96,6 +95,28 @@ task_work_cancel(struct task_struct *task, task_work_func_t func) return work; } +static bool task_work_func_match(struct callback_head *cb, void *data) +{ + return cb->func == data; +} + +/** + * task_work_cancel - cancel a pending work added by task_work_add() + * @task: the task which should execute the work + * @func: identifies the work to remove + * + * Find the last queued pending work with ->func == @func and remove + * it from queue. + * + * RETURNS: + * The found work or NULL if not found. + */ +struct callback_head * +task_work_cancel(struct task_struct *task, task_work_func_t func) +{ + return task_work_cancel_match(task, task_work_func_match, func); +} + /** * task_work_run - execute the works added by task_work_add() * From 788d0824269bef539fe31a785b1517882eafed93 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 22 Dec 2022 14:30:11 -0700 Subject: [PATCH 0073/4345] io_uring: import 5.15-stable io_uring No upstream commit exists. This imports the io_uring codebase from 5.15.85, wholesale. Changes from that code base: - Drop IOCB_ALLOC_CACHE, we don't have that in 5.10. - Drop MKDIRAT/SYMLINKAT/LINKAT. Would require further VFS backports, and we don't support these in 5.10 to begin with. - sock_from_file() old style calling convention. - Use compat_get_bitmap() only for CONFIG_COMPAT=y Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- fs/Makefile | 2 - fs/io-wq.c | 1242 ---- include/linux/io_uring.h | 48 +- include/linux/sched.h | 3 + include/linux/syscalls.h | 2 +- include/trace/events/io_uring.h | 121 +- include/uapi/linux/io_uring.h | 115 +- io_uring/Makefile | 6 + io_uring/io-wq.c | 1398 +++++ {fs => io_uring}/io-wq.h | 47 +- {fs => io_uring}/io_uring.c | 9486 +++++++++++++++++-------------- kernel/exit.c | 2 +- kernel/fork.c | 1 + kernel/sched/core.c | 2 +- 15 files changed, 6855 insertions(+), 5622 deletions(-) delete mode 100644 fs/io-wq.c create mode 100644 io_uring/Makefile create mode 100644 io_uring/io-wq.c rename {fs => io_uring}/io-wq.h (81%) rename {fs => io_uring}/io_uring.c (51%) diff --git a/Makefile b/Makefile index 68f8efa0cc30..14bb1bb37770 100644 --- a/Makefile +++ b/Makefile @@ -1128,7 +1128,7 @@ export MODORDER := $(extmod-prefix)modules.order export MODULES_NSDEPS := $(extmod-prefix)modules.nsdeps ifeq ($(KBUILD_EXTMOD),) -core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/ +core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/ io_uring/ vmlinux-dirs := $(patsubst %/,%,$(filter %/, \ $(core-y) $(core-m) $(drivers-y) $(drivers-m) \ diff --git a/fs/Makefile b/fs/Makefile index 999d1a23f036..c660ce28f149 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -32,8 +32,6 @@ obj-$(CONFIG_TIMERFD) += timerfd.o obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_AIO) += aio.o -obj-$(CONFIG_IO_URING) += io_uring.o -obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FS_DAX) += dax.o obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FS_VERITY) += verity/ diff --git a/fs/io-wq.c b/fs/io-wq.c deleted file mode 100644 index 3d5fc76b92d0..000000000000 --- a/fs/io-wq.c +++ /dev/null @@ -1,1242 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Basic worker thread pool for io_uring - * - * Copyright (C) 2019 Jens Axboe - * - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "../kernel/sched/sched.h" -#include "io-wq.h" - -#define WORKER_IDLE_TIMEOUT (5 * HZ) - -enum { - IO_WORKER_F_UP = 1, /* up and active */ - IO_WORKER_F_RUNNING = 2, /* account as running */ - IO_WORKER_F_FREE = 4, /* worker on free list */ - IO_WORKER_F_FIXED = 8, /* static idle worker */ - IO_WORKER_F_BOUND = 16, /* is doing bounded work */ -}; - -enum { - IO_WQ_BIT_EXIT = 0, /* wq exiting */ - IO_WQ_BIT_CANCEL = 1, /* cancel work on list */ - IO_WQ_BIT_ERROR = 2, /* error on setup */ -}; - -enum { - IO_WQE_FLAG_STALLED = 1, /* stalled on hash */ -}; - -/* - * One for each thread in a wqe pool - */ -struct io_worker { - refcount_t ref; - unsigned flags; - struct hlist_nulls_node nulls_node; - struct list_head all_list; - struct task_struct *task; - struct io_wqe *wqe; - - struct io_wq_work *cur_work; - spinlock_t lock; - - struct rcu_head rcu; - struct mm_struct *mm; -#ifdef CONFIG_BLK_CGROUP - struct cgroup_subsys_state *blkcg_css; -#endif - const struct cred *cur_creds; - const struct cred *saved_creds; - struct files_struct *restore_files; - struct nsproxy *restore_nsproxy; - struct fs_struct *restore_fs; -}; - -#if BITS_PER_LONG == 64 -#define IO_WQ_HASH_ORDER 6 -#else -#define IO_WQ_HASH_ORDER 5 -#endif - -#define IO_WQ_NR_HASH_BUCKETS (1u << IO_WQ_HASH_ORDER) - -struct io_wqe_acct { - unsigned nr_workers; - unsigned max_workers; - atomic_t nr_running; -}; - -enum { - IO_WQ_ACCT_BOUND, - IO_WQ_ACCT_UNBOUND, -}; - -/* - * Per-node worker thread pool - */ -struct io_wqe { - struct { - raw_spinlock_t lock; - struct io_wq_work_list work_list; - unsigned long hash_map; - unsigned flags; - } ____cacheline_aligned_in_smp; - - int node; - struct io_wqe_acct acct[2]; - - struct hlist_nulls_head free_list; - struct list_head all_list; - - struct io_wq *wq; - struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS]; -}; - -/* - * Per io_wq state - */ -struct io_wq { - struct io_wqe **wqes; - unsigned long state; - - free_work_fn *free_work; - io_wq_work_fn *do_work; - - struct task_struct *manager; - struct user_struct *user; - refcount_t refs; - struct completion done; - - struct hlist_node cpuhp_node; - - refcount_t use_refs; -}; - -static enum cpuhp_state io_wq_online; - -static bool io_worker_get(struct io_worker *worker) -{ - return refcount_inc_not_zero(&worker->ref); -} - -static void io_worker_release(struct io_worker *worker) -{ - if (refcount_dec_and_test(&worker->ref)) - wake_up_process(worker->task); -} - -/* - * Note: drops the wqe->lock if returning true! The caller must re-acquire - * the lock in that case. Some callers need to restart handling if this - * happens, so we can't just re-acquire the lock on behalf of the caller. - */ -static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) -{ - bool dropped_lock = false; - - if (worker->saved_creds) { - revert_creds(worker->saved_creds); - worker->cur_creds = worker->saved_creds = NULL; - } - - if (current->files != worker->restore_files) { - __acquire(&wqe->lock); - raw_spin_unlock_irq(&wqe->lock); - dropped_lock = true; - - task_lock(current); - current->files = worker->restore_files; - current->nsproxy = worker->restore_nsproxy; - task_unlock(current); - } - - if (current->fs != worker->restore_fs) - current->fs = worker->restore_fs; - - /* - * If we have an active mm, we need to drop the wq lock before unusing - * it. If we do, return true and let the caller retry the idle loop. - */ - if (worker->mm) { - if (!dropped_lock) { - __acquire(&wqe->lock); - raw_spin_unlock_irq(&wqe->lock); - dropped_lock = true; - } - __set_current_state(TASK_RUNNING); - kthread_unuse_mm(worker->mm); - mmput(worker->mm); - worker->mm = NULL; - } - -#ifdef CONFIG_BLK_CGROUP - if (worker->blkcg_css) { - kthread_associate_blkcg(NULL); - worker->blkcg_css = NULL; - } -#endif - if (current->signal->rlim[RLIMIT_FSIZE].rlim_cur != RLIM_INFINITY) - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - return dropped_lock; -} - -static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, - struct io_wq_work *work) -{ - if (work->flags & IO_WQ_WORK_UNBOUND) - return &wqe->acct[IO_WQ_ACCT_UNBOUND]; - - return &wqe->acct[IO_WQ_ACCT_BOUND]; -} - -static inline struct io_wqe_acct *io_wqe_get_acct(struct io_wqe *wqe, - struct io_worker *worker) -{ - if (worker->flags & IO_WORKER_F_BOUND) - return &wqe->acct[IO_WQ_ACCT_BOUND]; - - return &wqe->acct[IO_WQ_ACCT_UNBOUND]; -} - -static void io_worker_exit(struct io_worker *worker) -{ - struct io_wqe *wqe = worker->wqe; - struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); - - /* - * If we're not at zero, someone else is holding a brief reference - * to the worker. Wait for that to go away. - */ - set_current_state(TASK_INTERRUPTIBLE); - if (!refcount_dec_and_test(&worker->ref)) - schedule(); - __set_current_state(TASK_RUNNING); - - preempt_disable(); - current->flags &= ~PF_IO_WORKER; - if (worker->flags & IO_WORKER_F_RUNNING) - atomic_dec(&acct->nr_running); - if (!(worker->flags & IO_WORKER_F_BOUND)) - atomic_dec(&wqe->wq->user->processes); - worker->flags = 0; - preempt_enable(); - - raw_spin_lock_irq(&wqe->lock); - hlist_nulls_del_rcu(&worker->nulls_node); - list_del_rcu(&worker->all_list); - if (__io_worker_unuse(wqe, worker)) { - __release(&wqe->lock); - raw_spin_lock_irq(&wqe->lock); - } - acct->nr_workers--; - raw_spin_unlock_irq(&wqe->lock); - - kfree_rcu(worker, rcu); - if (refcount_dec_and_test(&wqe->wq->refs)) - complete(&wqe->wq->done); -} - -static inline bool io_wqe_run_queue(struct io_wqe *wqe) - __must_hold(wqe->lock) -{ - if (!wq_list_empty(&wqe->work_list) && - !(wqe->flags & IO_WQE_FLAG_STALLED)) - return true; - return false; -} - -/* - * Check head of free list for an available worker. If one isn't available, - * caller must wake up the wq manager to create one. - */ -static bool io_wqe_activate_free_worker(struct io_wqe *wqe) - __must_hold(RCU) -{ - struct hlist_nulls_node *n; - struct io_worker *worker; - - n = rcu_dereference(hlist_nulls_first_rcu(&wqe->free_list)); - if (is_a_nulls(n)) - return false; - - worker = hlist_nulls_entry(n, struct io_worker, nulls_node); - if (io_worker_get(worker)) { - wake_up_process(worker->task); - io_worker_release(worker); - return true; - } - - return false; -} - -/* - * We need a worker. If we find a free one, we're good. If not, and we're - * below the max number of workers, wake up the manager to create one. - */ -static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) -{ - bool ret; - - /* - * Most likely an attempt to queue unbounded work on an io_wq that - * wasn't setup with any unbounded workers. - */ - if (unlikely(!acct->max_workers)) - pr_warn_once("io-wq is not configured for unbound workers"); - - rcu_read_lock(); - ret = io_wqe_activate_free_worker(wqe); - rcu_read_unlock(); - - if (!ret && acct->nr_workers < acct->max_workers) - wake_up_process(wqe->wq->manager); -} - -static void io_wqe_inc_running(struct io_wqe *wqe, struct io_worker *worker) -{ - struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); - - atomic_inc(&acct->nr_running); -} - -static void io_wqe_dec_running(struct io_wqe *wqe, struct io_worker *worker) - __must_hold(wqe->lock) -{ - struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); - - if (atomic_dec_and_test(&acct->nr_running) && io_wqe_run_queue(wqe)) - io_wqe_wake_worker(wqe, acct); -} - -static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker) -{ - allow_kernel_signal(SIGINT); - - current->flags |= PF_IO_WORKER; - - worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); - worker->restore_files = current->files; - worker->restore_nsproxy = current->nsproxy; - worker->restore_fs = current->fs; - io_wqe_inc_running(wqe, worker); -} - -/* - * Worker will start processing some work. Move it to the busy list, if - * it's currently on the freelist - */ -static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, - struct io_wq_work *work) - __must_hold(wqe->lock) -{ - bool worker_bound, work_bound; - - if (worker->flags & IO_WORKER_F_FREE) { - worker->flags &= ~IO_WORKER_F_FREE; - hlist_nulls_del_init_rcu(&worker->nulls_node); - } - - /* - * If worker is moving from bound to unbound (or vice versa), then - * ensure we update the running accounting. - */ - worker_bound = (worker->flags & IO_WORKER_F_BOUND) != 0; - work_bound = (work->flags & IO_WQ_WORK_UNBOUND) == 0; - if (worker_bound != work_bound) { - io_wqe_dec_running(wqe, worker); - if (work_bound) { - worker->flags |= IO_WORKER_F_BOUND; - wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers--; - wqe->acct[IO_WQ_ACCT_BOUND].nr_workers++; - atomic_dec(&wqe->wq->user->processes); - } else { - worker->flags &= ~IO_WORKER_F_BOUND; - wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers++; - wqe->acct[IO_WQ_ACCT_BOUND].nr_workers--; - atomic_inc(&wqe->wq->user->processes); - } - io_wqe_inc_running(wqe, worker); - } -} - -/* - * No work, worker going to sleep. Move to freelist, and unuse mm if we - * have one attached. Dropping the mm may potentially sleep, so we drop - * the lock in that case and return success. Since the caller has to - * retry the loop in that case (we changed task state), we don't regrab - * the lock if we return success. - */ -static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) - __must_hold(wqe->lock) -{ - if (!(worker->flags & IO_WORKER_F_FREE)) { - worker->flags |= IO_WORKER_F_FREE; - hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); - } - - return __io_worker_unuse(wqe, worker); -} - -static inline unsigned int io_get_work_hash(struct io_wq_work *work) -{ - return work->flags >> IO_WQ_HASH_SHIFT; -} - -static struct io_wq_work *io_get_next_work(struct io_wqe *wqe) - __must_hold(wqe->lock) -{ - struct io_wq_work_node *node, *prev; - struct io_wq_work *work, *tail; - unsigned int hash; - - wq_list_for_each(node, prev, &wqe->work_list) { - work = container_of(node, struct io_wq_work, list); - - /* not hashed, can run anytime */ - if (!io_wq_is_hashed(work)) { - wq_list_del(&wqe->work_list, node, prev); - return work; - } - - /* hashed, can run if not already running */ - hash = io_get_work_hash(work); - if (!(wqe->hash_map & BIT(hash))) { - wqe->hash_map |= BIT(hash); - /* all items with this hash lie in [work, tail] */ - tail = wqe->hash_tail[hash]; - wqe->hash_tail[hash] = NULL; - wq_list_cut(&wqe->work_list, &tail->list, prev); - return work; - } - } - - return NULL; -} - -static void io_wq_switch_mm(struct io_worker *worker, struct io_wq_work *work) -{ - if (worker->mm) { - kthread_unuse_mm(worker->mm); - mmput(worker->mm); - worker->mm = NULL; - } - - if (mmget_not_zero(work->identity->mm)) { - kthread_use_mm(work->identity->mm); - worker->mm = work->identity->mm; - return; - } - - /* failed grabbing mm, ensure work gets cancelled */ - work->flags |= IO_WQ_WORK_CANCEL; -} - -static inline void io_wq_switch_blkcg(struct io_worker *worker, - struct io_wq_work *work) -{ -#ifdef CONFIG_BLK_CGROUP - if (!(work->flags & IO_WQ_WORK_BLKCG)) - return; - if (work->identity->blkcg_css != worker->blkcg_css) { - kthread_associate_blkcg(work->identity->blkcg_css); - worker->blkcg_css = work->identity->blkcg_css; - } -#endif -} - -static void io_wq_switch_creds(struct io_worker *worker, - struct io_wq_work *work) -{ - const struct cred *old_creds = override_creds(work->identity->creds); - - worker->cur_creds = work->identity->creds; - if (worker->saved_creds) - put_cred(old_creds); /* creds set by previous switch */ - else - worker->saved_creds = old_creds; -} - -static void io_impersonate_work(struct io_worker *worker, - struct io_wq_work *work) -{ - if ((work->flags & IO_WQ_WORK_FILES) && - current->files != work->identity->files) { - task_lock(current); - current->files = work->identity->files; - current->nsproxy = work->identity->nsproxy; - task_unlock(current); - if (!work->identity->files) { - /* failed grabbing files, ensure work gets cancelled */ - work->flags |= IO_WQ_WORK_CANCEL; - } - } - if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->identity->fs) - current->fs = work->identity->fs; - if ((work->flags & IO_WQ_WORK_MM) && work->identity->mm != worker->mm) - io_wq_switch_mm(worker, work); - if ((work->flags & IO_WQ_WORK_CREDS) && - worker->cur_creds != work->identity->creds) - io_wq_switch_creds(worker, work); - if (work->flags & IO_WQ_WORK_FSIZE) - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->identity->fsize; - else if (current->signal->rlim[RLIMIT_FSIZE].rlim_cur != RLIM_INFINITY) - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - io_wq_switch_blkcg(worker, work); -#ifdef CONFIG_AUDIT - current->loginuid = work->identity->loginuid; - current->sessionid = work->identity->sessionid; -#endif -} - -static void io_assign_current_work(struct io_worker *worker, - struct io_wq_work *work) -{ - if (work) { - /* flush pending signals before assigning new work */ - if (signal_pending(current)) - flush_signals(current); - cond_resched(); - } - -#ifdef CONFIG_AUDIT - current->loginuid = KUIDT_INIT(AUDIT_UID_UNSET); - current->sessionid = AUDIT_SID_UNSET; -#endif - - spin_lock_irq(&worker->lock); - worker->cur_work = work; - spin_unlock_irq(&worker->lock); -} - -static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work); - -static void io_worker_handle_work(struct io_worker *worker) - __releases(wqe->lock) -{ - struct io_wqe *wqe = worker->wqe; - struct io_wq *wq = wqe->wq; - - do { - struct io_wq_work *work; -get_next: - /* - * If we got some work, mark us as busy. If we didn't, but - * the list isn't empty, it means we stalled on hashed work. - * Mark us stalled so we don't keep looking for work when we - * can't make progress, any work completion or insertion will - * clear the stalled flag. - */ - work = io_get_next_work(wqe); - if (work) - __io_worker_busy(wqe, worker, work); - else if (!wq_list_empty(&wqe->work_list)) - wqe->flags |= IO_WQE_FLAG_STALLED; - - raw_spin_unlock_irq(&wqe->lock); - if (!work) - break; - io_assign_current_work(worker, work); - - /* handle a whole dependent link */ - do { - struct io_wq_work *old_work, *next_hashed, *linked; - unsigned int hash = io_get_work_hash(work); - - next_hashed = wq_next_work(work); - io_impersonate_work(worker, work); - /* - * OK to set IO_WQ_WORK_CANCEL even for uncancellable - * work, the worker function will do the right thing. - */ - if (test_bit(IO_WQ_BIT_CANCEL, &wq->state)) - work->flags |= IO_WQ_WORK_CANCEL; - - old_work = work; - linked = wq->do_work(work); - - work = next_hashed; - if (!work && linked && !io_wq_is_hashed(linked)) { - work = linked; - linked = NULL; - } - io_assign_current_work(worker, work); - wq->free_work(old_work); - - if (linked) - io_wqe_enqueue(wqe, linked); - - if (hash != -1U && !next_hashed) { - raw_spin_lock_irq(&wqe->lock); - wqe->hash_map &= ~BIT_ULL(hash); - wqe->flags &= ~IO_WQE_FLAG_STALLED; - /* skip unnecessary unlock-lock wqe->lock */ - if (!work) - goto get_next; - raw_spin_unlock_irq(&wqe->lock); - } - } while (work); - - raw_spin_lock_irq(&wqe->lock); - } while (1); -} - -static int io_wqe_worker(void *data) -{ - struct io_worker *worker = data; - struct io_wqe *wqe = worker->wqe; - struct io_wq *wq = wqe->wq; - - io_worker_start(wqe, worker); - - while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { - set_current_state(TASK_INTERRUPTIBLE); -loop: - raw_spin_lock_irq(&wqe->lock); - if (io_wqe_run_queue(wqe)) { - __set_current_state(TASK_RUNNING); - io_worker_handle_work(worker); - goto loop; - } - /* drops the lock on success, retry */ - if (__io_worker_idle(wqe, worker)) { - __release(&wqe->lock); - goto loop; - } - raw_spin_unlock_irq(&wqe->lock); - if (signal_pending(current)) - flush_signals(current); - if (schedule_timeout(WORKER_IDLE_TIMEOUT)) - continue; - /* timed out, exit unless we're the fixed worker */ - if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || - !(worker->flags & IO_WORKER_F_FIXED)) - break; - } - - if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { - raw_spin_lock_irq(&wqe->lock); - if (!wq_list_empty(&wqe->work_list)) - io_worker_handle_work(worker); - else - raw_spin_unlock_irq(&wqe->lock); - } - - io_worker_exit(worker); - return 0; -} - -/* - * Called when a worker is scheduled in. Mark us as currently running. - */ -void io_wq_worker_running(struct task_struct *tsk) -{ - struct io_worker *worker = kthread_data(tsk); - struct io_wqe *wqe = worker->wqe; - - if (!(worker->flags & IO_WORKER_F_UP)) - return; - if (worker->flags & IO_WORKER_F_RUNNING) - return; - worker->flags |= IO_WORKER_F_RUNNING; - io_wqe_inc_running(wqe, worker); -} - -/* - * Called when worker is going to sleep. If there are no workers currently - * running and we have work pending, wake up a free one or have the manager - * set one up. - */ -void io_wq_worker_sleeping(struct task_struct *tsk) -{ - struct io_worker *worker = kthread_data(tsk); - struct io_wqe *wqe = worker->wqe; - - if (!(worker->flags & IO_WORKER_F_UP)) - return; - if (!(worker->flags & IO_WORKER_F_RUNNING)) - return; - - worker->flags &= ~IO_WORKER_F_RUNNING; - - raw_spin_lock_irq(&wqe->lock); - io_wqe_dec_running(wqe, worker); - raw_spin_unlock_irq(&wqe->lock); -} - -static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) -{ - struct io_wqe_acct *acct = &wqe->acct[index]; - struct io_worker *worker; - - worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node); - if (!worker) - return false; - - refcount_set(&worker->ref, 1); - worker->nulls_node.pprev = NULL; - worker->wqe = wqe; - spin_lock_init(&worker->lock); - - worker->task = kthread_create_on_node(io_wqe_worker, worker, wqe->node, - "io_wqe_worker-%d/%d", index, wqe->node); - if (IS_ERR(worker->task)) { - kfree(worker); - return false; - } - kthread_bind_mask(worker->task, cpumask_of_node(wqe->node)); - - raw_spin_lock_irq(&wqe->lock); - hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); - list_add_tail_rcu(&worker->all_list, &wqe->all_list); - worker->flags |= IO_WORKER_F_FREE; - if (index == IO_WQ_ACCT_BOUND) - worker->flags |= IO_WORKER_F_BOUND; - if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND)) - worker->flags |= IO_WORKER_F_FIXED; - acct->nr_workers++; - raw_spin_unlock_irq(&wqe->lock); - - if (index == IO_WQ_ACCT_UNBOUND) - atomic_inc(&wq->user->processes); - - refcount_inc(&wq->refs); - wake_up_process(worker->task); - return true; -} - -static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index) - __must_hold(wqe->lock) -{ - struct io_wqe_acct *acct = &wqe->acct[index]; - - /* if we have available workers or no work, no need */ - if (!hlist_nulls_empty(&wqe->free_list) || !io_wqe_run_queue(wqe)) - return false; - return acct->nr_workers < acct->max_workers; -} - -static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data) -{ - send_sig(SIGINT, worker->task, 1); - return false; -} - -/* - * Iterate the passed in list and call the specific function for each - * worker that isn't exiting - */ -static bool io_wq_for_each_worker(struct io_wqe *wqe, - bool (*func)(struct io_worker *, void *), - void *data) -{ - struct io_worker *worker; - bool ret = false; - - list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { - if (io_worker_get(worker)) { - /* no task if node is/was offline */ - if (worker->task) - ret = func(worker, data); - io_worker_release(worker); - if (ret) - break; - } - } - - return ret; -} - -static bool io_wq_worker_wake(struct io_worker *worker, void *data) -{ - wake_up_process(worker->task); - return false; -} - -/* - * Manager thread. Tasked with creating new workers, if we need them. - */ -static int io_wq_manager(void *data) -{ - struct io_wq *wq = data; - int node; - - /* create fixed workers */ - refcount_set(&wq->refs, 1); - for_each_node(node) { - if (!node_online(node)) - continue; - if (create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND)) - continue; - set_bit(IO_WQ_BIT_ERROR, &wq->state); - set_bit(IO_WQ_BIT_EXIT, &wq->state); - goto out; - } - - complete(&wq->done); - - while (!kthread_should_stop()) { - if (current->task_works) - task_work_run(); - - for_each_node(node) { - struct io_wqe *wqe = wq->wqes[node]; - bool fork_worker[2] = { false, false }; - - if (!node_online(node)) - continue; - - raw_spin_lock_irq(&wqe->lock); - if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND)) - fork_worker[IO_WQ_ACCT_BOUND] = true; - if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND)) - fork_worker[IO_WQ_ACCT_UNBOUND] = true; - raw_spin_unlock_irq(&wqe->lock); - if (fork_worker[IO_WQ_ACCT_BOUND]) - create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND); - if (fork_worker[IO_WQ_ACCT_UNBOUND]) - create_io_worker(wq, wqe, IO_WQ_ACCT_UNBOUND); - } - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(HZ); - } - - if (current->task_works) - task_work_run(); - -out: - if (refcount_dec_and_test(&wq->refs)) { - complete(&wq->done); - return 0; - } - /* if ERROR is set and we get here, we have workers to wake */ - if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) { - rcu_read_lock(); - for_each_node(node) - io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL); - rcu_read_unlock(); - } - return 0; -} - -static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct, - struct io_wq_work *work) -{ - bool free_worker; - - if (!(work->flags & IO_WQ_WORK_UNBOUND)) - return true; - if (atomic_read(&acct->nr_running)) - return true; - - rcu_read_lock(); - free_worker = !hlist_nulls_empty(&wqe->free_list); - rcu_read_unlock(); - if (free_worker) - return true; - - if (atomic_read(&wqe->wq->user->processes) >= acct->max_workers && - !(capable(CAP_SYS_RESOURCE) || capable(CAP_SYS_ADMIN))) - return false; - - return true; -} - -static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe) -{ - struct io_wq *wq = wqe->wq; - - do { - struct io_wq_work *old_work = work; - - work->flags |= IO_WQ_WORK_CANCEL; - work = wq->do_work(work); - wq->free_work(old_work); - } while (work); -} - -static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work) -{ - unsigned int hash; - struct io_wq_work *tail; - - if (!io_wq_is_hashed(work)) { -append: - wq_list_add_tail(&work->list, &wqe->work_list); - return; - } - - hash = io_get_work_hash(work); - tail = wqe->hash_tail[hash]; - wqe->hash_tail[hash] = work; - if (!tail) - goto append; - - wq_list_add_after(&work->list, &tail->list, &wqe->work_list); -} - -static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) -{ - struct io_wqe_acct *acct = io_work_get_acct(wqe, work); - bool do_wake; - unsigned long flags; - - /* - * Do early check to see if we need a new unbound worker, and if we do, - * if we're allowed to do so. This isn't 100% accurate as there's a - * gap between this check and incrementing the value, but that's OK. - * It's close enough to not be an issue, fork() has the same delay. - */ - if (unlikely(!io_wq_can_queue(wqe, acct, work))) { - io_run_cancel(work, wqe); - return; - } - - raw_spin_lock_irqsave(&wqe->lock, flags); - io_wqe_insert_work(wqe, work); - wqe->flags &= ~IO_WQE_FLAG_STALLED; - do_wake = (work->flags & IO_WQ_WORK_CONCURRENT) || - !atomic_read(&acct->nr_running); - raw_spin_unlock_irqrestore(&wqe->lock, flags); - - if (do_wake) - io_wqe_wake_worker(wqe, acct); -} - -void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) -{ - struct io_wqe *wqe = wq->wqes[numa_node_id()]; - - io_wqe_enqueue(wqe, work); -} - -/* - * Work items that hash to the same value will not be done in parallel. - * Used to limit concurrent writes, generally hashed by inode. - */ -void io_wq_hash_work(struct io_wq_work *work, void *val) -{ - unsigned int bit; - - bit = hash_ptr(val, IO_WQ_HASH_ORDER); - work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); -} - -void io_wq_cancel_all(struct io_wq *wq) -{ - int node; - - set_bit(IO_WQ_BIT_CANCEL, &wq->state); - - rcu_read_lock(); - for_each_node(node) { - struct io_wqe *wqe = wq->wqes[node]; - - io_wq_for_each_worker(wqe, io_wqe_worker_send_sig, NULL); - } - rcu_read_unlock(); -} - -struct io_cb_cancel_data { - work_cancel_fn *fn; - void *data; - int nr_running; - int nr_pending; - bool cancel_all; -}; - -static bool io_wq_worker_cancel(struct io_worker *worker, void *data) -{ - struct io_cb_cancel_data *match = data; - unsigned long flags; - - /* - * Hold the lock to avoid ->cur_work going out of scope, caller - * may dereference the passed in work. - */ - spin_lock_irqsave(&worker->lock, flags); - if (worker->cur_work && - !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL) && - match->fn(worker->cur_work, match->data)) { - send_sig(SIGINT, worker->task, 1); - match->nr_running++; - } - spin_unlock_irqrestore(&worker->lock, flags); - - return match->nr_running && !match->cancel_all; -} - -static inline void io_wqe_remove_pending(struct io_wqe *wqe, - struct io_wq_work *work, - struct io_wq_work_node *prev) -{ - unsigned int hash = io_get_work_hash(work); - struct io_wq_work *prev_work = NULL; - - if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) { - if (prev) - prev_work = container_of(prev, struct io_wq_work, list); - if (prev_work && io_get_work_hash(prev_work) == hash) - wqe->hash_tail[hash] = prev_work; - else - wqe->hash_tail[hash] = NULL; - } - wq_list_del(&wqe->work_list, &work->list, prev); -} - -static void io_wqe_cancel_pending_work(struct io_wqe *wqe, - struct io_cb_cancel_data *match) -{ - struct io_wq_work_node *node, *prev; - struct io_wq_work *work; - unsigned long flags; - -retry: - raw_spin_lock_irqsave(&wqe->lock, flags); - wq_list_for_each(node, prev, &wqe->work_list) { - work = container_of(node, struct io_wq_work, list); - if (!match->fn(work, match->data)) - continue; - io_wqe_remove_pending(wqe, work, prev); - raw_spin_unlock_irqrestore(&wqe->lock, flags); - io_run_cancel(work, wqe); - match->nr_pending++; - if (!match->cancel_all) - return; - - /* not safe to continue after unlock */ - goto retry; - } - raw_spin_unlock_irqrestore(&wqe->lock, flags); -} - -static void io_wqe_cancel_running_work(struct io_wqe *wqe, - struct io_cb_cancel_data *match) -{ - rcu_read_lock(); - io_wq_for_each_worker(wqe, io_wq_worker_cancel, match); - rcu_read_unlock(); -} - -enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, - void *data, bool cancel_all) -{ - struct io_cb_cancel_data match = { - .fn = cancel, - .data = data, - .cancel_all = cancel_all, - }; - int node; - - /* - * First check pending list, if we're lucky we can just remove it - * from there. CANCEL_OK means that the work is returned as-new, - * no completion will be posted for it. - */ - for_each_node(node) { - struct io_wqe *wqe = wq->wqes[node]; - - io_wqe_cancel_pending_work(wqe, &match); - if (match.nr_pending && !match.cancel_all) - return IO_WQ_CANCEL_OK; - } - - /* - * Now check if a free (going busy) or busy worker has the work - * currently running. If we find it there, we'll return CANCEL_RUNNING - * as an indication that we attempt to signal cancellation. The - * completion will run normally in this case. - */ - for_each_node(node) { - struct io_wqe *wqe = wq->wqes[node]; - - io_wqe_cancel_running_work(wqe, &match); - if (match.nr_running && !match.cancel_all) - return IO_WQ_CANCEL_RUNNING; - } - - if (match.nr_running) - return IO_WQ_CANCEL_RUNNING; - if (match.nr_pending) - return IO_WQ_CANCEL_OK; - return IO_WQ_CANCEL_NOTFOUND; -} - -struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) -{ - int ret = -ENOMEM, node; - struct io_wq *wq; - - if (WARN_ON_ONCE(!data->free_work || !data->do_work)) - return ERR_PTR(-EINVAL); - if (WARN_ON_ONCE(!bounded)) - return ERR_PTR(-EINVAL); - - wq = kzalloc(sizeof(*wq), GFP_KERNEL); - if (!wq) - return ERR_PTR(-ENOMEM); - - wq->wqes = kcalloc(nr_node_ids, sizeof(struct io_wqe *), GFP_KERNEL); - if (!wq->wqes) - goto err_wq; - - ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node); - if (ret) - goto err_wqes; - - wq->free_work = data->free_work; - wq->do_work = data->do_work; - - /* caller must already hold a reference to this */ - wq->user = data->user; - - ret = -ENOMEM; - for_each_node(node) { - struct io_wqe *wqe; - int alloc_node = node; - - if (!node_online(alloc_node)) - alloc_node = NUMA_NO_NODE; - wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node); - if (!wqe) - goto err; - wq->wqes[node] = wqe; - wqe->node = alloc_node; - wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; - atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0); - if (wq->user) { - wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers = - task_rlimit(current, RLIMIT_NPROC); - } - atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0); - wqe->wq = wq; - raw_spin_lock_init(&wqe->lock); - INIT_WQ_LIST(&wqe->work_list); - INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0); - INIT_LIST_HEAD(&wqe->all_list); - } - - init_completion(&wq->done); - - wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager"); - if (!IS_ERR(wq->manager)) { - wake_up_process(wq->manager); - wait_for_completion(&wq->done); - if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) { - ret = -ENOMEM; - goto err; - } - refcount_set(&wq->use_refs, 1); - reinit_completion(&wq->done); - return wq; - } - - ret = PTR_ERR(wq->manager); - complete(&wq->done); -err: - cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); - for_each_node(node) - kfree(wq->wqes[node]); -err_wqes: - kfree(wq->wqes); -err_wq: - kfree(wq); - return ERR_PTR(ret); -} - -bool io_wq_get(struct io_wq *wq, struct io_wq_data *data) -{ - if (data->free_work != wq->free_work || data->do_work != wq->do_work) - return false; - - return refcount_inc_not_zero(&wq->use_refs); -} - -static void __io_wq_destroy(struct io_wq *wq) -{ - int node; - - cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); - - set_bit(IO_WQ_BIT_EXIT, &wq->state); - if (wq->manager) - kthread_stop(wq->manager); - - rcu_read_lock(); - for_each_node(node) - io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL); - rcu_read_unlock(); - - wait_for_completion(&wq->done); - - for_each_node(node) - kfree(wq->wqes[node]); - kfree(wq->wqes); - kfree(wq); -} - -void io_wq_destroy(struct io_wq *wq) -{ - if (refcount_dec_and_test(&wq->use_refs)) - __io_wq_destroy(wq); -} - -struct task_struct *io_wq_get_task(struct io_wq *wq) -{ - return wq->manager; -} - -static bool io_wq_worker_affinity(struct io_worker *worker, void *data) -{ - struct task_struct *task = worker->task; - struct rq_flags rf; - struct rq *rq; - - rq = task_rq_lock(task, &rf); - do_set_cpus_allowed(task, cpumask_of_node(worker->wqe->node)); - task->flags |= PF_NO_SETAFFINITY; - task_rq_unlock(rq, task, &rf); - return false; -} - -static int io_wq_cpu_online(unsigned int cpu, struct hlist_node *node) -{ - struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); - int i; - - rcu_read_lock(); - for_each_node(i) - io_wq_for_each_worker(wq->wqes[i], io_wq_worker_affinity, NULL); - rcu_read_unlock(); - return 0; -} - -static __init int io_wq_init(void) -{ - int ret; - - ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "io-wq/online", - io_wq_cpu_online, NULL); - if (ret < 0) - return ret; - io_wq_online = ret; - return 0; -} -subsys_initcall(io_wq_init); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 35b2d845704d..649a4d7c241b 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,50 +5,20 @@ #include #include -struct io_identity { - struct files_struct *files; - struct mm_struct *mm; -#ifdef CONFIG_BLK_CGROUP - struct cgroup_subsys_state *blkcg_css; -#endif - const struct cred *creds; - struct nsproxy *nsproxy; - struct fs_struct *fs; - unsigned long fsize; -#ifdef CONFIG_AUDIT - kuid_t loginuid; - unsigned int sessionid; -#endif - refcount_t count; -}; - -struct io_uring_task { - /* submission side */ - struct xarray xa; - struct wait_queue_head wait; - struct file *last; - struct percpu_counter inflight; - struct io_identity __identity; - struct io_identity *identity; - atomic_t in_idle; - bool sqpoll; -}; - #if defined(CONFIG_IO_URING) struct sock *io_uring_get_socket(struct file *file); -void __io_uring_task_cancel(void); -void __io_uring_files_cancel(struct files_struct *files); +void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); +static inline void io_uring_files_cancel(void) +{ + if (current->io_uring) + __io_uring_cancel(false); +} static inline void io_uring_task_cancel(void) { - if (current->io_uring && !xa_empty(¤t->io_uring->xa)) - __io_uring_task_cancel(); -} -static inline void io_uring_files_cancel(struct files_struct *files) -{ - if (current->io_uring && !xa_empty(¤t->io_uring->xa)) - __io_uring_files_cancel(files); + if (current->io_uring) + __io_uring_cancel(true); } static inline void io_uring_free(struct task_struct *tsk) { @@ -63,7 +33,7 @@ static inline struct sock *io_uring_get_socket(struct file *file) static inline void io_uring_task_cancel(void) { } -static inline void io_uring_files_cancel(struct files_struct *files) +static inline void io_uring_files_cancel(void) { } static inline void io_uring_free(struct task_struct *tsk) diff --git a/include/linux/sched.h b/include/linux/sched.h index b055c217eb0b..5da4b3c89f63 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -885,6 +885,9 @@ struct task_struct { /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; + /* PF_IO_WORKER */ + void *pf_io_worker; + u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index aea0ce9f3b74..a058c96cf213 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -341,7 +341,7 @@ asmlinkage long sys_io_uring_setup(u32 entries, struct io_uring_params __user *p); asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit, u32 min_complete, u32 flags, - const sigset_t __user *sig, size_t sigsz); + const void __user *argp, size_t argsz); asmlinkage long sys_io_uring_register(unsigned int fd, unsigned int op, void __user *arg, unsigned int nr_args); diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 9f0d3b7d56b0..0dd30de00e5b 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -12,11 +12,11 @@ struct io_wq_work; /** * io_uring_create - called after a new io_uring context was prepared * - * @fd: corresponding file descriptor - * @ctx: pointer to a ring context structure + * @fd: corresponding file descriptor + * @ctx: pointer to a ring context structure * @sq_entries: actual SQ size * @cq_entries: actual CQ size - * @flags: SQ ring flags, provided to io_uring_setup(2) + * @flags: SQ ring flags, provided to io_uring_setup(2) * * Allows to trace io_uring creation and provide pointer to a context, that can * be used later to find correlated events. @@ -49,15 +49,15 @@ TRACE_EVENT(io_uring_create, ); /** - * io_uring_register - called after a buffer/file/eventfd was succesfully + * io_uring_register - called after a buffer/file/eventfd was successfully * registered for a ring * - * @ctx: pointer to a ring context structure - * @opcode: describes which operation to perform + * @ctx: pointer to a ring context structure + * @opcode: describes which operation to perform * @nr_user_files: number of registered files * @nr_user_bufs: number of registered buffers * @cq_ev_fd: whether eventfs registered or not - * @ret: return code + * @ret: return code * * Allows to trace fixed files/buffers/eventfds, that could be registered to * avoid an overhead of getting references to them for every operation. This @@ -142,16 +142,16 @@ TRACE_EVENT(io_uring_queue_async_work, TP_ARGS(ctx, rw, req, work, flags), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( int, rw ) - __field( void *, req ) + __field( void *, ctx ) + __field( int, rw ) + __field( void *, req ) __field( struct io_wq_work *, work ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->ctx = ctx; - __entry->rw = rw; + __entry->rw = rw; __entry->req = req; __entry->work = work; __entry->flags = flags; @@ -196,10 +196,10 @@ TRACE_EVENT(io_uring_defer, /** * io_uring_link - called before the io_uring request added into link_list of - * another request + * another request * - * @ctx: pointer to a ring context structure - * @req: pointer to a linked request + * @ctx: pointer to a ring context structure + * @req: pointer to a linked request * @target_req: pointer to a previous request, that would contain @req * * Allows to track linked requests, to understand dependencies between requests @@ -212,8 +212,8 @@ TRACE_EVENT(io_uring_link, TP_ARGS(ctx, req, target_req), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( void *, req ) + __field( void *, ctx ) + __field( void *, req ) __field( void *, target_req ) ), @@ -244,7 +244,7 @@ TRACE_EVENT(io_uring_cqring_wait, TP_ARGS(ctx, min_events), TP_STRUCT__entry ( - __field( void *, ctx ) + __field( void *, ctx ) __field( int, min_events ) ), @@ -272,7 +272,7 @@ TRACE_EVENT(io_uring_fail_link, TP_ARGS(req, link), TP_STRUCT__entry ( - __field( void *, req ) + __field( void *, req ) __field( void *, link ) ), @@ -290,38 +290,42 @@ TRACE_EVENT(io_uring_fail_link, * @ctx: pointer to a ring context structure * @user_data: user data associated with the request * @res: result of the request + * @cflags: completion flags * */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, u64 user_data, long res), + TP_PROTO(void *ctx, u64 user_data, int res, unsigned cflags), - TP_ARGS(ctx, user_data, res), + TP_ARGS(ctx, user_data, res, cflags), TP_STRUCT__entry ( __field( void *, ctx ) __field( u64, user_data ) - __field( long, res ) + __field( int, res ) + __field( unsigned, cflags ) ), TP_fast_assign( __entry->ctx = ctx; __entry->user_data = user_data; __entry->res = res; + __entry->cflags = cflags; ), - TP_printk("ring %p, user_data 0x%llx, result %ld", + TP_printk("ring %p, user_data 0x%llx, result %d, cflags %x", __entry->ctx, (unsigned long long)__entry->user_data, - __entry->res) + __entry->res, __entry->cflags) ); - /** * io_uring_submit_sqe - called before submitting one SQE * * @ctx: pointer to a ring context structure + * @req: pointer to a submitted request * @opcode: opcode of request * @user_data: user data associated with the request + * @flags request flags * @force_nonblock: whether a context blocking or not * @sq_thread: true if sq_thread has submitted this SQE * @@ -330,41 +334,60 @@ TRACE_EVENT(io_uring_complete, */ TRACE_EVENT(io_uring_submit_sqe, - TP_PROTO(void *ctx, u8 opcode, u64 user_data, bool force_nonblock, - bool sq_thread), + TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, u32 flags, + bool force_nonblock, bool sq_thread), - TP_ARGS(ctx, opcode, user_data, force_nonblock, sq_thread), + TP_ARGS(ctx, req, opcode, user_data, flags, force_nonblock, sq_thread), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) + __field( u32, flags ) __field( bool, force_nonblock ) __field( bool, sq_thread ) ), TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; + __entry->flags = flags; __entry->force_nonblock = force_nonblock; __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, op %d, data 0x%llx, non block %d, sq_thread %d", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data, - __entry->force_nonblock, __entry->sq_thread) + TP_printk("ring %p, req %p, op %d, data 0x%llx, flags %u, " + "non block %d, sq_thread %d", __entry->ctx, __entry->req, + __entry->opcode, (unsigned long long)__entry->user_data, + __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); +/* + * io_uring_poll_arm - called after arming a poll wait if successful + * + * @ctx: pointer to a ring context structure + * @req: pointer to the armed request + * @opcode: opcode of request + * @user_data: user data associated with the request + * @mask: request poll events mask + * @events: registered events of interest + * + * Allows to track which fds are waiting for and what are the events of + * interest. + */ TRACE_EVENT(io_uring_poll_arm, - TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask, int events), + TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, + int mask, int events), - TP_ARGS(ctx, opcode, user_data, mask, events), + TP_ARGS(ctx, req, opcode, user_data, mask, events), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) __field( int, mask ) @@ -373,16 +396,17 @@ TRACE_EVENT(io_uring_poll_arm, TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; __entry->mask = mask; __entry->events = events; ), - TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x, events 0x%x", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data, - __entry->mask, __entry->events) + TP_printk("ring %p, req %p, op %d, data 0x%llx, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->opcode, + (unsigned long long) __entry->user_data, + __entry->mask, __entry->events) ); TRACE_EVENT(io_uring_poll_wake, @@ -437,27 +461,40 @@ TRACE_EVENT(io_uring_task_add, __entry->mask) ); +/* + * io_uring_task_run - called when task_work_run() executes the poll events + * notification callbacks + * + * @ctx: pointer to a ring context structure + * @req: pointer to the armed request + * @opcode: opcode of request + * @user_data: user data associated with the request + * + * Allows to track when notified poll events are processed + */ TRACE_EVENT(io_uring_task_run, - TP_PROTO(void *ctx, u8 opcode, u64 user_data), + TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data), - TP_ARGS(ctx, opcode, user_data), + TP_ARGS(ctx, req, opcode, user_data), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) ), TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; ), - TP_printk("ring %p, op %d, data 0x%llx", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data) + TP_printk("ring %p, req %p, op %d, data 0x%llx", + __entry->ctx, __entry->req, __entry->opcode, + (unsigned long long) __entry->user_data) ); #endif /* _TRACE_IO_URING_H */ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 98d8e06dea22..6481db937002 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -42,23 +42,25 @@ struct io_uring_sqe { __u32 statx_flags; __u32 fadvise_advice; __u32 splice_flags; + __u32 rename_flags; + __u32 unlink_flags; + __u32 hardlink_flags; }; __u64 user_data; /* data to be passed back at completion time */ + /* pack this to avoid bogus arm OABI complaints */ union { - struct { - /* pack this to avoid bogus arm OABI complaints */ - union { - /* index into fixed buffers, if used */ - __u16 buf_index; - /* for grouped buffer selection */ - __u16 buf_group; - } __attribute__((packed)); - /* personality to use, if used */ - __u16 personality; - __s32 splice_fd_in; - }; - __u64 __pad2[3]; + /* index into fixed buffers, if used */ + __u16 buf_index; + /* for grouped buffer selection */ + __u16 buf_group; + } __attribute__((packed)); + /* personality to use, if used */ + __u16 personality; + union { + __s32 splice_fd_in; + __u32 file_index; }; + __u64 __pad2[2]; }; enum { @@ -132,6 +134,9 @@ enum { IORING_OP_PROVIDE_BUFFERS, IORING_OP_REMOVE_BUFFERS, IORING_OP_TEE, + IORING_OP_SHUTDOWN, + IORING_OP_RENAMEAT, + IORING_OP_UNLINKAT, /* this goes last, obviously */ IORING_OP_LAST, @@ -145,14 +150,34 @@ enum { /* * sqe->timeout_flags */ -#define IORING_TIMEOUT_ABS (1U << 0) - +#define IORING_TIMEOUT_ABS (1U << 0) +#define IORING_TIMEOUT_UPDATE (1U << 1) +#define IORING_TIMEOUT_BOOTTIME (1U << 2) +#define IORING_TIMEOUT_REALTIME (1U << 3) +#define IORING_LINK_TIMEOUT_UPDATE (1U << 4) +#define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) +#define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) /* * sqe->splice_flags * extends splice(2) flags */ #define SPLICE_F_FD_IN_FIXED (1U << 31) /* the last bit of __u32 */ +/* + * POLL_ADD flags. Note that since sqe->poll_events is the flag space, the + * command flags for POLL_ADD are stored in sqe->len. + * + * IORING_POLL_ADD_MULTI Multishot poll. Sets IORING_CQE_F_MORE if + * the poll handler will continue to report + * CQEs on behalf of the same SQE. + * + * IORING_POLL_UPDATE Update existing poll request, matching + * sqe->addr as the old user_data field. + */ +#define IORING_POLL_ADD_MULTI (1U << 0) +#define IORING_POLL_UPDATE_EVENTS (1U << 1) +#define IORING_POLL_UPDATE_USER_DATA (1U << 2) + /* * IO completion data structure (Completion Queue Entry) */ @@ -166,8 +191,10 @@ struct io_uring_cqe { * cqe->flags * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID + * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries */ #define IORING_CQE_F_BUFFER (1U << 0) +#define IORING_CQE_F_MORE (1U << 1) enum { IORING_CQE_BUFFER_SHIFT = 16, @@ -226,6 +253,7 @@ struct io_cqring_offsets { #define IORING_ENTER_GETEVENTS (1U << 0) #define IORING_ENTER_SQ_WAKEUP (1U << 1) #define IORING_ENTER_SQ_WAIT (1U << 2) +#define IORING_ENTER_EXT_ARG (1U << 3) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -253,6 +281,10 @@ struct io_uring_params { #define IORING_FEAT_CUR_PERSONALITY (1U << 4) #define IORING_FEAT_FAST_POLL (1U << 5) #define IORING_FEAT_POLL_32BITS (1U << 6) +#define IORING_FEAT_SQPOLL_NONFIXED (1U << 7) +#define IORING_FEAT_EXT_ARG (1U << 8) +#define IORING_FEAT_NATIVE_WORKERS (1U << 9) +#define IORING_FEAT_RSRC_TAGS (1U << 10) /* * io_uring_register(2) opcodes and arguments @@ -272,16 +304,62 @@ enum { IORING_REGISTER_RESTRICTIONS = 11, IORING_REGISTER_ENABLE_RINGS = 12, + /* extended with tagging */ + IORING_REGISTER_FILES2 = 13, + IORING_REGISTER_FILES_UPDATE2 = 14, + IORING_REGISTER_BUFFERS2 = 15, + IORING_REGISTER_BUFFERS_UPDATE = 16, + + /* set/clear io-wq thread affinities */ + IORING_REGISTER_IOWQ_AFF = 17, + IORING_UNREGISTER_IOWQ_AFF = 18, + + /* set/get max number of io-wq workers */ + IORING_REGISTER_IOWQ_MAX_WORKERS = 19, + /* this goes last */ IORING_REGISTER_LAST }; +/* io-wq worker categories */ +enum { + IO_WQ_BOUND, + IO_WQ_UNBOUND, +}; + +/* deprecated, see struct io_uring_rsrc_update */ struct io_uring_files_update { __u32 offset; __u32 resv; __aligned_u64 /* __s32 * */ fds; }; +struct io_uring_rsrc_register { + __u32 nr; + __u32 resv; + __u64 resv2; + __aligned_u64 data; + __aligned_u64 tags; +}; + +struct io_uring_rsrc_update { + __u32 offset; + __u32 resv; + __aligned_u64 data; +}; + +struct io_uring_rsrc_update2 { + __u32 offset; + __u32 resv; + __aligned_u64 data; + __aligned_u64 tags; + __u32 nr; + __u32 resv2; +}; + +/* Skip updating fd indexes set to this value in the fd table */ +#define IORING_REGISTER_FILES_SKIP (-2) + #define IO_URING_OP_SUPPORTED (1U << 0) struct io_uring_probe_op { @@ -329,4 +407,11 @@ enum { IORING_RESTRICTION_LAST }; +struct io_uring_getevents_arg { + __u64 sigmask; + __u32 sigmask_sz; + __u32 pad; + __u64 ts; +}; + #endif diff --git a/io_uring/Makefile b/io_uring/Makefile new file mode 100644 index 000000000000..3680425df947 --- /dev/null +++ b/io_uring/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for io_uring + +obj-$(CONFIG_IO_URING) += io_uring.o +obj-$(CONFIG_IO_WQ) += io-wq.o diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c new file mode 100644 index 000000000000..6031fb319d87 --- /dev/null +++ b/io_uring/io-wq.c @@ -0,0 +1,1398 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic worker thread pool for io_uring + * + * Copyright (C) 2019 Jens Axboe + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "io-wq.h" + +#define WORKER_IDLE_TIMEOUT (5 * HZ) + +enum { + IO_WORKER_F_UP = 1, /* up and active */ + IO_WORKER_F_RUNNING = 2, /* account as running */ + IO_WORKER_F_FREE = 4, /* worker on free list */ + IO_WORKER_F_BOUND = 8, /* is doing bounded work */ +}; + +enum { + IO_WQ_BIT_EXIT = 0, /* wq exiting */ +}; + +enum { + IO_ACCT_STALLED_BIT = 0, /* stalled on hash */ +}; + +/* + * One for each thread in a wqe pool + */ +struct io_worker { + refcount_t ref; + unsigned flags; + struct hlist_nulls_node nulls_node; + struct list_head all_list; + struct task_struct *task; + struct io_wqe *wqe; + + struct io_wq_work *cur_work; + spinlock_t lock; + + struct completion ref_done; + + unsigned long create_state; + struct callback_head create_work; + int create_index; + + union { + struct rcu_head rcu; + struct work_struct work; + }; +}; + +#if BITS_PER_LONG == 64 +#define IO_WQ_HASH_ORDER 6 +#else +#define IO_WQ_HASH_ORDER 5 +#endif + +#define IO_WQ_NR_HASH_BUCKETS (1u << IO_WQ_HASH_ORDER) + +struct io_wqe_acct { + unsigned nr_workers; + unsigned max_workers; + int index; + atomic_t nr_running; + struct io_wq_work_list work_list; + unsigned long flags; +}; + +enum { + IO_WQ_ACCT_BOUND, + IO_WQ_ACCT_UNBOUND, + IO_WQ_ACCT_NR, +}; + +/* + * Per-node worker thread pool + */ +struct io_wqe { + raw_spinlock_t lock; + struct io_wqe_acct acct[2]; + + int node; + + struct hlist_nulls_head free_list; + struct list_head all_list; + + struct wait_queue_entry wait; + + struct io_wq *wq; + struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS]; + + cpumask_var_t cpu_mask; +}; + +/* + * Per io_wq state + */ +struct io_wq { + unsigned long state; + + free_work_fn *free_work; + io_wq_work_fn *do_work; + + struct io_wq_hash *hash; + + atomic_t worker_refs; + struct completion worker_done; + + struct hlist_node cpuhp_node; + + struct task_struct *task; + + struct io_wqe *wqes[]; +}; + +static enum cpuhp_state io_wq_online; + +struct io_cb_cancel_data { + work_cancel_fn *fn; + void *data; + int nr_running; + int nr_pending; + bool cancel_all; +}; + +static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index); +static void io_wqe_dec_running(struct io_worker *worker); +static bool io_acct_cancel_pending_work(struct io_wqe *wqe, + struct io_wqe_acct *acct, + struct io_cb_cancel_data *match); +static void create_worker_cb(struct callback_head *cb); +static void io_wq_cancel_tw_create(struct io_wq *wq); + +static bool io_worker_get(struct io_worker *worker) +{ + return refcount_inc_not_zero(&worker->ref); +} + +static void io_worker_release(struct io_worker *worker) +{ + if (refcount_dec_and_test(&worker->ref)) + complete(&worker->ref_done); +} + +static inline struct io_wqe_acct *io_get_acct(struct io_wqe *wqe, bool bound) +{ + return &wqe->acct[bound ? IO_WQ_ACCT_BOUND : IO_WQ_ACCT_UNBOUND]; +} + +static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, + struct io_wq_work *work) +{ + return io_get_acct(wqe, !(work->flags & IO_WQ_WORK_UNBOUND)); +} + +static inline struct io_wqe_acct *io_wqe_get_acct(struct io_worker *worker) +{ + return io_get_acct(worker->wqe, worker->flags & IO_WORKER_F_BOUND); +} + +static void io_worker_ref_put(struct io_wq *wq) +{ + if (atomic_dec_and_test(&wq->worker_refs)) + complete(&wq->worker_done); +} + +static void io_worker_cancel_cb(struct io_worker *worker) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + atomic_dec(&acct->nr_running); + raw_spin_lock(&worker->wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&worker->wqe->lock); + io_worker_ref_put(wq); + clear_bit_unlock(0, &worker->create_state); + io_worker_release(worker); +} + +static bool io_task_worker_match(struct callback_head *cb, void *data) +{ + struct io_worker *worker; + + if (cb->func != create_worker_cb) + return false; + worker = container_of(cb, struct io_worker, create_work); + return worker == data; +} + +static void io_worker_exit(struct io_worker *worker) +{ + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + while (1) { + struct callback_head *cb = task_work_cancel_match(wq->task, + io_task_worker_match, worker); + + if (!cb) + break; + io_worker_cancel_cb(worker); + } + + if (refcount_dec_and_test(&worker->ref)) + complete(&worker->ref_done); + wait_for_completion(&worker->ref_done); + + raw_spin_lock(&wqe->lock); + if (worker->flags & IO_WORKER_F_FREE) + hlist_nulls_del_rcu(&worker->nulls_node); + list_del_rcu(&worker->all_list); + preempt_disable(); + io_wqe_dec_running(worker); + worker->flags = 0; + current->flags &= ~PF_IO_WORKER; + preempt_enable(); + raw_spin_unlock(&wqe->lock); + + kfree_rcu(worker, rcu); + io_worker_ref_put(wqe->wq); + do_exit(0); +} + +static inline bool io_acct_run_queue(struct io_wqe_acct *acct) +{ + if (!wq_list_empty(&acct->work_list) && + !test_bit(IO_ACCT_STALLED_BIT, &acct->flags)) + return true; + return false; +} + +/* + * Check head of free list for an available worker. If one isn't available, + * caller must create one. + */ +static bool io_wqe_activate_free_worker(struct io_wqe *wqe, + struct io_wqe_acct *acct) + __must_hold(RCU) +{ + struct hlist_nulls_node *n; + struct io_worker *worker; + + /* + * Iterate free_list and see if we can find an idle worker to + * activate. If a given worker is on the free_list but in the process + * of exiting, keep trying. + */ + hlist_nulls_for_each_entry_rcu(worker, n, &wqe->free_list, nulls_node) { + if (!io_worker_get(worker)) + continue; + if (io_wqe_get_acct(worker) != acct) { + io_worker_release(worker); + continue; + } + if (wake_up_process(worker->task)) { + io_worker_release(worker); + return true; + } + io_worker_release(worker); + } + + return false; +} + +/* + * We need a worker. If we find a free one, we're good. If not, and we're + * below the max number of workers, create one. + */ +static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) +{ + /* + * Most likely an attempt to queue unbounded work on an io_wq that + * wasn't setup with any unbounded workers. + */ + if (unlikely(!acct->max_workers)) + pr_warn_once("io-wq is not configured for unbound workers"); + + raw_spin_lock(&wqe->lock); + if (acct->nr_workers >= acct->max_workers) { + raw_spin_unlock(&wqe->lock); + return true; + } + acct->nr_workers++; + raw_spin_unlock(&wqe->lock); + atomic_inc(&acct->nr_running); + atomic_inc(&wqe->wq->worker_refs); + return create_io_worker(wqe->wq, wqe, acct->index); +} + +static void io_wqe_inc_running(struct io_worker *worker) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + + atomic_inc(&acct->nr_running); +} + +static void create_worker_cb(struct callback_head *cb) +{ + struct io_worker *worker; + struct io_wq *wq; + struct io_wqe *wqe; + struct io_wqe_acct *acct; + bool do_create = false; + + worker = container_of(cb, struct io_worker, create_work); + wqe = worker->wqe; + wq = wqe->wq; + acct = &wqe->acct[worker->create_index]; + raw_spin_lock(&wqe->lock); + if (acct->nr_workers < acct->max_workers) { + acct->nr_workers++; + do_create = true; + } + raw_spin_unlock(&wqe->lock); + if (do_create) { + create_io_worker(wq, wqe, worker->create_index); + } else { + atomic_dec(&acct->nr_running); + io_worker_ref_put(wq); + } + clear_bit_unlock(0, &worker->create_state); + io_worker_release(worker); +} + +static bool io_queue_worker_create(struct io_worker *worker, + struct io_wqe_acct *acct, + task_work_func_t func) +{ + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + /* raced with exit, just ignore create call */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) + goto fail; + if (!io_worker_get(worker)) + goto fail; + /* + * create_state manages ownership of create_work/index. We should + * only need one entry per worker, as the worker going to sleep + * will trigger the condition, and waking will clear it once it + * runs the task_work. + */ + if (test_bit(0, &worker->create_state) || + test_and_set_bit_lock(0, &worker->create_state)) + goto fail_release; + + atomic_inc(&wq->worker_refs); + init_task_work(&worker->create_work, func); + worker->create_index = acct->index; + if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) { + /* + * EXIT may have been set after checking it above, check after + * adding the task_work and remove any creation item if it is + * now set. wq exit does that too, but we can have added this + * work item after we canceled in io_wq_exit_workers(). + */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) + io_wq_cancel_tw_create(wq); + io_worker_ref_put(wq); + return true; + } + io_worker_ref_put(wq); + clear_bit_unlock(0, &worker->create_state); +fail_release: + io_worker_release(worker); +fail: + atomic_dec(&acct->nr_running); + io_worker_ref_put(wq); + return false; +} + +static void io_wqe_dec_running(struct io_worker *worker) + __must_hold(wqe->lock) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + + if (!(worker->flags & IO_WORKER_F_UP)) + return; + + if (atomic_dec_and_test(&acct->nr_running) && io_acct_run_queue(acct)) { + atomic_inc(&acct->nr_running); + atomic_inc(&wqe->wq->worker_refs); + raw_spin_unlock(&wqe->lock); + io_queue_worker_create(worker, acct, create_worker_cb); + raw_spin_lock(&wqe->lock); + } +} + +/* + * Worker will start processing some work. Move it to the busy list, if + * it's currently on the freelist + */ +static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, + struct io_wq_work *work) + __must_hold(wqe->lock) +{ + if (worker->flags & IO_WORKER_F_FREE) { + worker->flags &= ~IO_WORKER_F_FREE; + hlist_nulls_del_init_rcu(&worker->nulls_node); + } +} + +/* + * No work, worker going to sleep. Move to freelist, and unuse mm if we + * have one attached. Dropping the mm may potentially sleep, so we drop + * the lock in that case and return success. Since the caller has to + * retry the loop in that case (we changed task state), we don't regrab + * the lock if we return success. + */ +static void __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) + __must_hold(wqe->lock) +{ + if (!(worker->flags & IO_WORKER_F_FREE)) { + worker->flags |= IO_WORKER_F_FREE; + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); + } +} + +static inline unsigned int io_get_work_hash(struct io_wq_work *work) +{ + return work->flags >> IO_WQ_HASH_SHIFT; +} + +static bool io_wait_on_hash(struct io_wqe *wqe, unsigned int hash) +{ + struct io_wq *wq = wqe->wq; + bool ret = false; + + spin_lock_irq(&wq->hash->wait.lock); + if (list_empty(&wqe->wait.entry)) { + __add_wait_queue(&wq->hash->wait, &wqe->wait); + if (!test_bit(hash, &wq->hash->map)) { + __set_current_state(TASK_RUNNING); + list_del_init(&wqe->wait.entry); + ret = true; + } + } + spin_unlock_irq(&wq->hash->wait.lock); + return ret; +} + +static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, + struct io_worker *worker) + __must_hold(wqe->lock) +{ + struct io_wq_work_node *node, *prev; + struct io_wq_work *work, *tail; + unsigned int stall_hash = -1U; + struct io_wqe *wqe = worker->wqe; + + wq_list_for_each(node, prev, &acct->work_list) { + unsigned int hash; + + work = container_of(node, struct io_wq_work, list); + + /* not hashed, can run anytime */ + if (!io_wq_is_hashed(work)) { + wq_list_del(&acct->work_list, node, prev); + return work; + } + + hash = io_get_work_hash(work); + /* all items with this hash lie in [work, tail] */ + tail = wqe->hash_tail[hash]; + + /* hashed, can run if not already running */ + if (!test_and_set_bit(hash, &wqe->wq->hash->map)) { + wqe->hash_tail[hash] = NULL; + wq_list_cut(&acct->work_list, &tail->list, prev); + return work; + } + if (stall_hash == -1U) + stall_hash = hash; + /* fast forward to a next hash, for-each will fix up @prev */ + node = &tail->list; + } + + if (stall_hash != -1U) { + bool unstalled; + + /* + * Set this before dropping the lock to avoid racing with new + * work being added and clearing the stalled bit. + */ + set_bit(IO_ACCT_STALLED_BIT, &acct->flags); + raw_spin_unlock(&wqe->lock); + unstalled = io_wait_on_hash(wqe, stall_hash); + raw_spin_lock(&wqe->lock); + if (unstalled) { + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + if (wq_has_sleeper(&wqe->wq->hash->wait)) + wake_up(&wqe->wq->hash->wait); + } + } + + return NULL; +} + +static bool io_flush_signals(void) +{ + if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) { + __set_current_state(TASK_RUNNING); + tracehook_notify_signal(); + return true; + } + return false; +} + +static void io_assign_current_work(struct io_worker *worker, + struct io_wq_work *work) +{ + if (work) { + io_flush_signals(); + cond_resched(); + } + + spin_lock(&worker->lock); + worker->cur_work = work; + spin_unlock(&worker->lock); +} + +static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work); + +static void io_worker_handle_work(struct io_worker *worker) + __releases(wqe->lock) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); + + do { + struct io_wq_work *work; +get_next: + /* + * If we got some work, mark us as busy. If we didn't, but + * the list isn't empty, it means we stalled on hashed work. + * Mark us stalled so we don't keep looking for work when we + * can't make progress, any work completion or insertion will + * clear the stalled flag. + */ + work = io_get_next_work(acct, worker); + if (work) + __io_worker_busy(wqe, worker, work); + + raw_spin_unlock(&wqe->lock); + if (!work) + break; + io_assign_current_work(worker, work); + __set_current_state(TASK_RUNNING); + + /* handle a whole dependent link */ + do { + struct io_wq_work *next_hashed, *linked; + unsigned int hash = io_get_work_hash(work); + + next_hashed = wq_next_work(work); + + if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND)) + work->flags |= IO_WQ_WORK_CANCEL; + wq->do_work(work); + io_assign_current_work(worker, NULL); + + linked = wq->free_work(work); + work = next_hashed; + if (!work && linked && !io_wq_is_hashed(linked)) { + work = linked; + linked = NULL; + } + io_assign_current_work(worker, work); + if (linked) + io_wqe_enqueue(wqe, linked); + + if (hash != -1U && !next_hashed) { + /* serialize hash clear with wake_up() */ + spin_lock_irq(&wq->hash->wait.lock); + clear_bit(hash, &wq->hash->map); + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + spin_unlock_irq(&wq->hash->wait.lock); + if (wq_has_sleeper(&wq->hash->wait)) + wake_up(&wq->hash->wait); + raw_spin_lock(&wqe->lock); + /* skip unnecessary unlock-lock wqe->lock */ + if (!work) + goto get_next; + raw_spin_unlock(&wqe->lock); + } + } while (work); + + raw_spin_lock(&wqe->lock); + } while (1); +} + +static int io_wqe_worker(void *data) +{ + struct io_worker *worker = data; + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + bool last_timeout = false; + char buf[TASK_COMM_LEN]; + + worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + + snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); + set_task_comm(current, buf); + + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + long ret; + + set_current_state(TASK_INTERRUPTIBLE); +loop: + raw_spin_lock(&wqe->lock); + if (io_acct_run_queue(acct)) { + io_worker_handle_work(worker); + goto loop; + } + /* timed out, exit unless we're the last worker */ + if (last_timeout && acct->nr_workers > 1) { + acct->nr_workers--; + raw_spin_unlock(&wqe->lock); + __set_current_state(TASK_RUNNING); + break; + } + last_timeout = false; + __io_worker_idle(wqe, worker); + raw_spin_unlock(&wqe->lock); + if (io_flush_signals()) + continue; + ret = schedule_timeout(WORKER_IDLE_TIMEOUT); + if (signal_pending(current)) { + struct ksignal ksig; + + if (!get_signal(&ksig)) + continue; + break; + } + last_timeout = !ret; + } + + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + raw_spin_lock(&wqe->lock); + io_worker_handle_work(worker); + } + + io_worker_exit(worker); + return 0; +} + +/* + * Called when a worker is scheduled in. Mark us as currently running. + */ +void io_wq_worker_running(struct task_struct *tsk) +{ + struct io_worker *worker = tsk->pf_io_worker; + + if (!worker) + return; + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (worker->flags & IO_WORKER_F_RUNNING) + return; + worker->flags |= IO_WORKER_F_RUNNING; + io_wqe_inc_running(worker); +} + +/* + * Called when worker is going to sleep. If there are no workers currently + * running and we have work pending, wake up a free one or create a new one. + */ +void io_wq_worker_sleeping(struct task_struct *tsk) +{ + struct io_worker *worker = tsk->pf_io_worker; + + if (!worker) + return; + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (!(worker->flags & IO_WORKER_F_RUNNING)) + return; + + worker->flags &= ~IO_WORKER_F_RUNNING; + + raw_spin_lock(&worker->wqe->lock); + io_wqe_dec_running(worker); + raw_spin_unlock(&worker->wqe->lock); +} + +static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker, + struct task_struct *tsk) +{ + tsk->pf_io_worker = worker; + worker->task = tsk; + set_cpus_allowed_ptr(tsk, wqe->cpu_mask); + tsk->flags |= PF_NO_SETAFFINITY; + + raw_spin_lock(&wqe->lock); + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); + list_add_tail_rcu(&worker->all_list, &wqe->all_list); + worker->flags |= IO_WORKER_F_FREE; + raw_spin_unlock(&wqe->lock); + wake_up_new_task(tsk); +} + +static bool io_wq_work_match_all(struct io_wq_work *work, void *data) +{ + return true; +} + +static inline bool io_should_retry_thread(long err) +{ + /* + * Prevent perpetual task_work retry, if the task (or its group) is + * exiting. + */ + if (fatal_signal_pending(current)) + return false; + + switch (err) { + case -EAGAIN: + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTARTNOHAND: + return true; + default: + return false; + } +} + +static void create_worker_cont(struct callback_head *cb) +{ + struct io_worker *worker; + struct task_struct *tsk; + struct io_wqe *wqe; + + worker = container_of(cb, struct io_worker, create_work); + clear_bit_unlock(0, &worker->create_state); + wqe = worker->wqe; + tsk = create_io_thread(io_wqe_worker, worker, wqe->node); + if (!IS_ERR(tsk)) { + io_init_new_worker(wqe, worker, tsk); + io_worker_release(worker); + return; + } else if (!io_should_retry_thread(PTR_ERR(tsk))) { + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + + atomic_dec(&acct->nr_running); + raw_spin_lock(&wqe->lock); + acct->nr_workers--; + if (!acct->nr_workers) { + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_all, + .cancel_all = true, + }; + + while (io_acct_cancel_pending_work(wqe, acct, &match)) + raw_spin_lock(&wqe->lock); + } + raw_spin_unlock(&wqe->lock); + io_worker_ref_put(wqe->wq); + kfree(worker); + return; + } + + /* re-create attempts grab a new worker ref, drop the existing one */ + io_worker_release(worker); + schedule_work(&worker->work); +} + +static void io_workqueue_create(struct work_struct *work) +{ + struct io_worker *worker = container_of(work, struct io_worker, work); + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + + if (!io_queue_worker_create(worker, acct, create_worker_cont)) + kfree(worker); +} + +static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) +{ + struct io_wqe_acct *acct = &wqe->acct[index]; + struct io_worker *worker; + struct task_struct *tsk; + + __set_current_state(TASK_RUNNING); + + worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node); + if (!worker) { +fail: + atomic_dec(&acct->nr_running); + raw_spin_lock(&wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&wqe->lock); + io_worker_ref_put(wq); + return false; + } + + refcount_set(&worker->ref, 1); + worker->wqe = wqe; + spin_lock_init(&worker->lock); + init_completion(&worker->ref_done); + + if (index == IO_WQ_ACCT_BOUND) + worker->flags |= IO_WORKER_F_BOUND; + + tsk = create_io_thread(io_wqe_worker, worker, wqe->node); + if (!IS_ERR(tsk)) { + io_init_new_worker(wqe, worker, tsk); + } else if (!io_should_retry_thread(PTR_ERR(tsk))) { + kfree(worker); + goto fail; + } else { + INIT_WORK(&worker->work, io_workqueue_create); + schedule_work(&worker->work); + } + + return true; +} + +/* + * Iterate the passed in list and call the specific function for each + * worker that isn't exiting + */ +static bool io_wq_for_each_worker(struct io_wqe *wqe, + bool (*func)(struct io_worker *, void *), + void *data) +{ + struct io_worker *worker; + bool ret = false; + + list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { + if (io_worker_get(worker)) { + /* no task if node is/was offline */ + if (worker->task) + ret = func(worker, data); + io_worker_release(worker); + if (ret) + break; + } + } + + return ret; +} + +static bool io_wq_worker_wake(struct io_worker *worker, void *data) +{ + set_notify_signal(worker->task); + wake_up_process(worker->task); + return false; +} + +static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe) +{ + struct io_wq *wq = wqe->wq; + + do { + work->flags |= IO_WQ_WORK_CANCEL; + wq->do_work(work); + work = wq->free_work(work); + } while (work); +} + +static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned int hash; + struct io_wq_work *tail; + + if (!io_wq_is_hashed(work)) { +append: + wq_list_add_tail(&work->list, &acct->work_list); + return; + } + + hash = io_get_work_hash(work); + tail = wqe->hash_tail[hash]; + wqe->hash_tail[hash] = work; + if (!tail) + goto append; + + wq_list_add_after(&work->list, &tail->list, &acct->work_list); +} + +static bool io_wq_work_match_item(struct io_wq_work *work, void *data) +{ + return work == data; +} + +static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned work_flags = work->flags; + bool do_create; + + /* + * If io-wq is exiting for this task, or if the request has explicitly + * been marked as one that should not get executed, cancel it here. + */ + if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) || + (work->flags & IO_WQ_WORK_CANCEL)) { + io_run_cancel(work, wqe); + return; + } + + raw_spin_lock(&wqe->lock); + io_wqe_insert_work(wqe, work); + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + + rcu_read_lock(); + do_create = !io_wqe_activate_free_worker(wqe, acct); + rcu_read_unlock(); + + raw_spin_unlock(&wqe->lock); + + if (do_create && ((work_flags & IO_WQ_WORK_CONCURRENT) || + !atomic_read(&acct->nr_running))) { + bool did_create; + + did_create = io_wqe_create_worker(wqe, acct); + if (likely(did_create)) + return; + + raw_spin_lock(&wqe->lock); + /* fatal condition, failed to create the first worker */ + if (!acct->nr_workers) { + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_item, + .data = work, + .cancel_all = false, + }; + + if (io_acct_cancel_pending_work(wqe, acct, &match)) + raw_spin_lock(&wqe->lock); + } + raw_spin_unlock(&wqe->lock); + } +} + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) +{ + struct io_wqe *wqe = wq->wqes[numa_node_id()]; + + io_wqe_enqueue(wqe, work); +} + +/* + * Work items that hash to the same value will not be done in parallel. + * Used to limit concurrent writes, generally hashed by inode. + */ +void io_wq_hash_work(struct io_wq_work *work, void *val) +{ + unsigned int bit; + + bit = hash_ptr(val, IO_WQ_HASH_ORDER); + work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); +} + +static bool io_wq_worker_cancel(struct io_worker *worker, void *data) +{ + struct io_cb_cancel_data *match = data; + + /* + * Hold the lock to avoid ->cur_work going out of scope, caller + * may dereference the passed in work. + */ + spin_lock(&worker->lock); + if (worker->cur_work && + match->fn(worker->cur_work, match->data)) { + set_notify_signal(worker->task); + match->nr_running++; + } + spin_unlock(&worker->lock); + + return match->nr_running && !match->cancel_all; +} + +static inline void io_wqe_remove_pending(struct io_wqe *wqe, + struct io_wq_work *work, + struct io_wq_work_node *prev) +{ + struct io_wqe_acct *acct = io_work_get_acct(wqe, work); + unsigned int hash = io_get_work_hash(work); + struct io_wq_work *prev_work = NULL; + + if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) { + if (prev) + prev_work = container_of(prev, struct io_wq_work, list); + if (prev_work && io_get_work_hash(prev_work) == hash) + wqe->hash_tail[hash] = prev_work; + else + wqe->hash_tail[hash] = NULL; + } + wq_list_del(&acct->work_list, &work->list, prev); +} + +static bool io_acct_cancel_pending_work(struct io_wqe *wqe, + struct io_wqe_acct *acct, + struct io_cb_cancel_data *match) + __releases(wqe->lock) +{ + struct io_wq_work_node *node, *prev; + struct io_wq_work *work; + + wq_list_for_each(node, prev, &acct->work_list) { + work = container_of(node, struct io_wq_work, list); + if (!match->fn(work, match->data)) + continue; + io_wqe_remove_pending(wqe, work, prev); + raw_spin_unlock(&wqe->lock); + io_run_cancel(work, wqe); + match->nr_pending++; + /* not safe to continue after unlock */ + return true; + } + + return false; +} + +static void io_wqe_cancel_pending_work(struct io_wqe *wqe, + struct io_cb_cancel_data *match) +{ + int i; +retry: + raw_spin_lock(&wqe->lock); + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + struct io_wqe_acct *acct = io_get_acct(wqe, i == 0); + + if (io_acct_cancel_pending_work(wqe, acct, match)) { + if (match->cancel_all) + goto retry; + return; + } + } + raw_spin_unlock(&wqe->lock); +} + +static void io_wqe_cancel_running_work(struct io_wqe *wqe, + struct io_cb_cancel_data *match) +{ + rcu_read_lock(); + io_wq_for_each_worker(wqe, io_wq_worker_cancel, match); + rcu_read_unlock(); +} + +enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, + void *data, bool cancel_all) +{ + struct io_cb_cancel_data match = { + .fn = cancel, + .data = data, + .cancel_all = cancel_all, + }; + int node; + + /* + * First check pending list, if we're lucky we can just remove it + * from there. CANCEL_OK means that the work is returned as-new, + * no completion will be posted for it. + */ + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + + io_wqe_cancel_pending_work(wqe, &match); + if (match.nr_pending && !match.cancel_all) + return IO_WQ_CANCEL_OK; + } + + /* + * Now check if a free (going busy) or busy worker has the work + * currently running. If we find it there, we'll return CANCEL_RUNNING + * as an indication that we attempt to signal cancellation. The + * completion will run normally in this case. + */ + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + + io_wqe_cancel_running_work(wqe, &match); + if (match.nr_running && !match.cancel_all) + return IO_WQ_CANCEL_RUNNING; + } + + if (match.nr_running) + return IO_WQ_CANCEL_RUNNING; + if (match.nr_pending) + return IO_WQ_CANCEL_OK; + return IO_WQ_CANCEL_NOTFOUND; +} + +static int io_wqe_hash_wake(struct wait_queue_entry *wait, unsigned mode, + int sync, void *key) +{ + struct io_wqe *wqe = container_of(wait, struct io_wqe, wait); + int i; + + list_del_init(&wait->entry); + + rcu_read_lock(); + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + struct io_wqe_acct *acct = &wqe->acct[i]; + + if (test_and_clear_bit(IO_ACCT_STALLED_BIT, &acct->flags)) + io_wqe_activate_free_worker(wqe, acct); + } + rcu_read_unlock(); + return 1; +} + +struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) +{ + int ret, node, i; + struct io_wq *wq; + + if (WARN_ON_ONCE(!data->free_work || !data->do_work)) + return ERR_PTR(-EINVAL); + if (WARN_ON_ONCE(!bounded)) + return ERR_PTR(-EINVAL); + + wq = kzalloc(struct_size(wq, wqes, nr_node_ids), GFP_KERNEL); + if (!wq) + return ERR_PTR(-ENOMEM); + ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node); + if (ret) + goto err_wq; + + refcount_inc(&data->hash->refs); + wq->hash = data->hash; + wq->free_work = data->free_work; + wq->do_work = data->do_work; + + ret = -ENOMEM; + for_each_node(node) { + struct io_wqe *wqe; + int alloc_node = node; + + if (!node_online(alloc_node)) + alloc_node = NUMA_NO_NODE; + wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node); + if (!wqe) + goto err; + wq->wqes[node] = wqe; + if (!alloc_cpumask_var(&wqe->cpu_mask, GFP_KERNEL)) + goto err; + cpumask_copy(wqe->cpu_mask, cpumask_of_node(node)); + wqe->node = alloc_node; + wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; + wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers = + task_rlimit(current, RLIMIT_NPROC); + INIT_LIST_HEAD(&wqe->wait.entry); + wqe->wait.func = io_wqe_hash_wake; + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + struct io_wqe_acct *acct = &wqe->acct[i]; + + acct->index = i; + atomic_set(&acct->nr_running, 0); + INIT_WQ_LIST(&acct->work_list); + } + wqe->wq = wq; + raw_spin_lock_init(&wqe->lock); + INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0); + INIT_LIST_HEAD(&wqe->all_list); + } + + wq->task = get_task_struct(data->task); + atomic_set(&wq->worker_refs, 1); + init_completion(&wq->worker_done); + return wq; +err: + io_wq_put_hash(data->hash); + cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); + for_each_node(node) { + if (!wq->wqes[node]) + continue; + free_cpumask_var(wq->wqes[node]->cpu_mask); + kfree(wq->wqes[node]); + } +err_wq: + kfree(wq); + return ERR_PTR(ret); +} + +static bool io_task_work_match(struct callback_head *cb, void *data) +{ + struct io_worker *worker; + + if (cb->func != create_worker_cb && cb->func != create_worker_cont) + return false; + worker = container_of(cb, struct io_worker, create_work); + return worker->wqe->wq == data; +} + +void io_wq_exit_start(struct io_wq *wq) +{ + set_bit(IO_WQ_BIT_EXIT, &wq->state); +} + +static void io_wq_cancel_tw_create(struct io_wq *wq) +{ + struct callback_head *cb; + + while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) { + struct io_worker *worker; + + worker = container_of(cb, struct io_worker, create_work); + io_worker_cancel_cb(worker); + } +} + +static void io_wq_exit_workers(struct io_wq *wq) +{ + int node; + + if (!wq->task) + return; + + io_wq_cancel_tw_create(wq); + + rcu_read_lock(); + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + + io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL); + } + rcu_read_unlock(); + io_worker_ref_put(wq); + wait_for_completion(&wq->worker_done); + + for_each_node(node) { + spin_lock_irq(&wq->hash->wait.lock); + list_del_init(&wq->wqes[node]->wait.entry); + spin_unlock_irq(&wq->hash->wait.lock); + } + put_task_struct(wq->task); + wq->task = NULL; +} + +static void io_wq_destroy(struct io_wq *wq) +{ + int node; + + cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); + + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_all, + .cancel_all = true, + }; + io_wqe_cancel_pending_work(wqe, &match); + free_cpumask_var(wqe->cpu_mask); + kfree(wqe); + } + io_wq_put_hash(wq->hash); + kfree(wq); +} + +void io_wq_put_and_exit(struct io_wq *wq) +{ + WARN_ON_ONCE(!test_bit(IO_WQ_BIT_EXIT, &wq->state)); + + io_wq_exit_workers(wq); + io_wq_destroy(wq); +} + +struct online_data { + unsigned int cpu; + bool online; +}; + +static bool io_wq_worker_affinity(struct io_worker *worker, void *data) +{ + struct online_data *od = data; + + if (od->online) + cpumask_set_cpu(od->cpu, worker->wqe->cpu_mask); + else + cpumask_clear_cpu(od->cpu, worker->wqe->cpu_mask); + return false; +} + +static int __io_wq_cpu_online(struct io_wq *wq, unsigned int cpu, bool online) +{ + struct online_data od = { + .cpu = cpu, + .online = online + }; + int i; + + rcu_read_lock(); + for_each_node(i) + io_wq_for_each_worker(wq->wqes[i], io_wq_worker_affinity, &od); + rcu_read_unlock(); + return 0; +} + +static int io_wq_cpu_online(unsigned int cpu, struct hlist_node *node) +{ + struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); + + return __io_wq_cpu_online(wq, cpu, true); +} + +static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node) +{ + struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); + + return __io_wq_cpu_online(wq, cpu, false); +} + +int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask) +{ + int i; + + rcu_read_lock(); + for_each_node(i) { + struct io_wqe *wqe = wq->wqes[i]; + + if (mask) + cpumask_copy(wqe->cpu_mask, mask); + else + cpumask_copy(wqe->cpu_mask, cpumask_of_node(i)); + } + rcu_read_unlock(); + return 0; +} + +/* + * Set max number of unbounded workers, returns old value. If new_count is 0, + * then just return the old value. + */ +int io_wq_max_workers(struct io_wq *wq, int *new_count) +{ + int prev[IO_WQ_ACCT_NR]; + bool first_node = true; + int i, node; + + BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_NR != 2); + + for (i = 0; i < 2; i++) { + if (new_count[i] > task_rlimit(current, RLIMIT_NPROC)) + new_count[i] = task_rlimit(current, RLIMIT_NPROC); + } + + for (i = 0; i < IO_WQ_ACCT_NR; i++) + prev[i] = 0; + + rcu_read_lock(); + for_each_node(node) { + struct io_wqe *wqe = wq->wqes[node]; + struct io_wqe_acct *acct; + + raw_spin_lock(&wqe->lock); + for (i = 0; i < IO_WQ_ACCT_NR; i++) { + acct = &wqe->acct[i]; + if (first_node) + prev[i] = max_t(int, acct->max_workers, prev[i]); + if (new_count[i]) + acct->max_workers = new_count[i]; + } + raw_spin_unlock(&wqe->lock); + first_node = false; + } + rcu_read_unlock(); + + for (i = 0; i < IO_WQ_ACCT_NR; i++) + new_count[i] = prev[i]; + + return 0; +} + +static __init int io_wq_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "io-wq/online", + io_wq_cpu_online, io_wq_cpu_offline); + if (ret < 0) + return ret; + io_wq_online = ret; + return 0; +} +subsys_initcall(io_wq_init); diff --git a/fs/io-wq.h b/io_uring/io-wq.h similarity index 81% rename from fs/io-wq.h rename to io_uring/io-wq.h index 75113bcd5889..bf5c4c533760 100644 --- a/fs/io-wq.h +++ b/io_uring/io-wq.h @@ -1,7 +1,7 @@ #ifndef INTERNAL_IO_WQ_H #define INTERNAL_IO_WQ_H -#include +#include struct io_wq; @@ -9,16 +9,8 @@ enum { IO_WQ_WORK_CANCEL = 1, IO_WQ_WORK_HASHED = 2, IO_WQ_WORK_UNBOUND = 4, - IO_WQ_WORK_NO_CANCEL = 8, IO_WQ_WORK_CONCURRENT = 16, - IO_WQ_WORK_FILES = 32, - IO_WQ_WORK_FS = 64, - IO_WQ_WORK_MM = 128, - IO_WQ_WORK_CREDS = 256, - IO_WQ_WORK_BLKCG = 512, - IO_WQ_WORK_FSIZE = 1024, - IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */ }; @@ -52,6 +44,7 @@ static inline void wq_list_add_after(struct io_wq_work_node *node, static inline void wq_list_add_tail(struct io_wq_work_node *node, struct io_wq_work_list *list) { + node->next = NULL; if (!list->first) { list->last = node; WRITE_ONCE(list->first, node); @@ -59,7 +52,6 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node, list->last->next = node; list->last = node; } - node->next = NULL; } static inline void wq_list_cut(struct io_wq_work_list *list, @@ -95,7 +87,6 @@ static inline void wq_list_del(struct io_wq_work_list *list, struct io_wq_work { struct io_wq_work_node list; - struct io_identity *identity; unsigned flags; }; @@ -107,37 +98,48 @@ static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) return container_of(work->list.next, struct io_wq_work, list); } -typedef void (free_work_fn)(struct io_wq_work *); -typedef struct io_wq_work *(io_wq_work_fn)(struct io_wq_work *); +typedef struct io_wq_work *(free_work_fn)(struct io_wq_work *); +typedef void (io_wq_work_fn)(struct io_wq_work *); + +struct io_wq_hash { + refcount_t refs; + unsigned long map; + struct wait_queue_head wait; +}; + +static inline void io_wq_put_hash(struct io_wq_hash *hash) +{ + if (refcount_dec_and_test(&hash->refs)) + kfree(hash); +} struct io_wq_data { - struct user_struct *user; - + struct io_wq_hash *hash; + struct task_struct *task; io_wq_work_fn *do_work; free_work_fn *free_work; }; struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data); -bool io_wq_get(struct io_wq *wq, struct io_wq_data *data); -void io_wq_destroy(struct io_wq *wq); +void io_wq_exit_start(struct io_wq *wq); +void io_wq_put_and_exit(struct io_wq *wq); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); void io_wq_hash_work(struct io_wq_work *work, void *val); +int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); +int io_wq_max_workers(struct io_wq *wq, int *new_count); + static inline bool io_wq_is_hashed(struct io_wq_work *work) { return work->flags & IO_WQ_WORK_HASHED; } -void io_wq_cancel_all(struct io_wq *wq); - typedef bool (work_cancel_fn)(struct io_wq_work *, void *); enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, void *data, bool cancel_all); -struct task_struct *io_wq_get_task(struct io_wq *wq); - #if defined(CONFIG_IO_WQ) extern void io_wq_worker_sleeping(struct task_struct *); extern void io_wq_worker_running(struct task_struct *); @@ -152,6 +154,7 @@ static inline void io_wq_worker_running(struct task_struct *tsk) static inline bool io_wq_current_is_worker(void) { - return in_task() && (current->flags & PF_IO_WORKER); + return in_task() && (current->flags & PF_IO_WORKER) && + current->pf_io_worker; } #endif diff --git a/fs/io_uring.c b/io_uring/io_uring.c similarity index 51% rename from fs/io_uring.c rename to io_uring/io_uring.c index 1d8173741310..473dbd1830a3 100644 --- a/fs/io_uring.c +++ b/io_uring/io_uring.c @@ -11,7 +11,7 @@ * before writing the tail (using smp_load_acquire to read the tail will * do). It also needs a smp_mb() before updating CQ head (ordering the * entry load(s) with the head store), pairing with an implicit barrier - * through a control-dependency in io_get_cqring (smp_store_release to + * through a control-dependency in io_get_cqe (smp_store_release to * store head will do). Failure to do so could lead to reading invalid * CQ entries. * @@ -57,7 +57,6 @@ #include #include #include -#include #include #include #include @@ -75,35 +74,43 @@ #include #include #include -#include #include #include #include #include -#include -#include +#include #define CREATE_TRACE_POINTS #include #include -#include "internal.h" +#include "../fs/internal.h" #include "io-wq.h" #define IORING_MAX_ENTRIES 32768 #define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) +#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 -/* - * Shift of 9 is 512 entries, or exactly one page on 64-bit archs - */ -#define IORING_FILE_TABLE_SHIFT 9 -#define IORING_MAX_FILES_TABLE (1U << IORING_FILE_TABLE_SHIFT) -#define IORING_FILE_TABLE_MASK (IORING_MAX_FILES_TABLE - 1) -#define IORING_MAX_FIXED_FILES (64 * IORING_MAX_FILES_TABLE) +/* only define max */ +#define IORING_MAX_FIXED_FILES (1U << 15) #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) +#define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) +#define IO_RSRC_TAG_TABLE_MAX (1U << IO_RSRC_TAG_TABLE_SHIFT) +#define IO_RSRC_TAG_TABLE_MASK (IO_RSRC_TAG_TABLE_MAX - 1) + +#define IORING_MAX_REG_BUFFERS (1U << 14) + +#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ + IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ + IOSQE_BUFFER_SELECT) +#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ + REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS) + +#define IO_TCTX_REFS_CACHE_NR (1U << 10) + struct io_uring { u32 head ____cacheline_aligned_in_smp; u32 tail ____cacheline_aligned_in_smp; @@ -162,7 +169,7 @@ struct io_rings { * Written by the application, shouldn't be modified by the * kernel. */ - u32 cq_flags; + u32 cq_flags; /* * Number of completion events lost because the queue was full; * this should be avoided by the application by making sure @@ -187,36 +194,64 @@ struct io_rings { struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; }; +enum io_uring_cmd_flags { + IO_URING_F_NONBLOCK = 1, + IO_URING_F_COMPLETE_DEFER = 2, +}; + struct io_mapped_ubuf { u64 ubuf; - size_t len; - struct bio_vec *bvec; + u64 ubuf_end; unsigned int nr_bvecs; unsigned long acct_pages; + struct bio_vec bvec[]; }; -struct fixed_file_table { - struct file **files; +struct io_ring_ctx; + +struct io_overflow_cqe { + struct io_uring_cqe cqe; + struct list_head list; }; -struct fixed_file_ref_node { +struct io_fixed_file { + /* file * with additional FFS_* flags */ + unsigned long file_ptr; +}; + +struct io_rsrc_put { + struct list_head list; + u64 tag; + union { + void *rsrc; + struct file *file; + struct io_mapped_ubuf *buf; + }; +}; + +struct io_file_table { + struct io_fixed_file *files; +}; + +struct io_rsrc_node { struct percpu_ref refs; struct list_head node; - struct list_head file_list; - struct fixed_file_data *file_data; + struct list_head rsrc_list; + struct io_rsrc_data *rsrc_data; struct llist_node llist; bool done; }; -struct fixed_file_data { - struct fixed_file_table *table; +typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc); + +struct io_rsrc_data { struct io_ring_ctx *ctx; - struct fixed_file_ref_node *node; - struct percpu_ref refs; + u64 **tags; + unsigned int nr; + rsrc_put_fn *do_put; + atomic_t refs; struct completion done; - struct list_head ref_list; - spinlock_t lock; bool quiesce; }; @@ -235,33 +270,81 @@ struct io_restriction { bool registered; }; +enum { + IO_SQ_THREAD_SHOULD_STOP = 0, + IO_SQ_THREAD_SHOULD_PARK, +}; + struct io_sq_data { refcount_t refs; + atomic_t park_pending; struct mutex lock; /* ctx's that are using this sqd */ struct list_head ctx_list; - struct list_head ctx_new_list; - struct mutex ctx_lock; struct task_struct *thread; struct wait_queue_head wait; + + unsigned sq_thread_idle; + int sq_cpu; + pid_t task_pid; + pid_t task_tgid; + + unsigned long state; + struct completion exited; +}; + +#define IO_COMPL_BATCH 32 +#define IO_REQ_CACHE_SIZE 32 +#define IO_REQ_ALLOC_BATCH 8 + +struct io_submit_link { + struct io_kiocb *head; + struct io_kiocb *last; +}; + +struct io_submit_state { + struct blk_plug plug; + struct io_submit_link link; + + /* + * io_kiocb alloc cache + */ + void *reqs[IO_REQ_CACHE_SIZE]; + unsigned int free_reqs; + + bool plug_started; + + /* + * Batch completion logic + */ + struct io_kiocb *compl_reqs[IO_COMPL_BATCH]; + unsigned int compl_nr; + /* inline/task_work completion list, under ->uring_lock */ + struct list_head free_list; + + unsigned int ios_left; }; struct io_ring_ctx { + /* const or read-mostly hot data */ struct { struct percpu_ref refs; - } ____cacheline_aligned_in_smp; - struct { + struct io_rings *rings; unsigned int flags; unsigned int compat: 1; - unsigned int limit_mem: 1; - unsigned int cq_overflow_flushed: 1; unsigned int drain_next: 1; unsigned int eventfd_async: 1; unsigned int restricted: 1; - unsigned int sqo_dead: 1; + unsigned int off_timeout_used: 1; + unsigned int drain_active: 1; + } ____cacheline_aligned_in_smp; + + /* submission data */ + struct { + struct mutex uring_lock; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -275,101 +358,59 @@ struct io_ring_ctx { * array. */ u32 *sq_array; + struct io_uring_sqe *sq_sqes; unsigned cached_sq_head; unsigned sq_entries; - unsigned sq_mask; - unsigned sq_thread_idle; - unsigned cached_sq_dropped; - unsigned cached_cq_overflow; - unsigned long sq_check_overflow; - struct list_head defer_list; - struct list_head timeout_list; - struct list_head cq_overflow_list; - struct io_uring_sqe *sq_sqes; + /* + * Fixed resources fast path, should be accessed only under + * uring_lock, and updated through io_uring_register(2) + */ + struct io_rsrc_node *rsrc_node; + struct io_file_table file_table; + unsigned nr_user_files; + unsigned nr_user_bufs; + struct io_mapped_ubuf **user_bufs; + + struct io_submit_state submit_state; + struct list_head timeout_list; + struct list_head ltimeout_list; + struct list_head cq_overflow_list; + struct xarray io_buffers; + struct xarray personalities; + u32 pers_next; + unsigned sq_thread_idle; } ____cacheline_aligned_in_smp; - struct io_rings *rings; - - /* IO offload */ - struct io_wq *io_wq; - - /* - * For SQPOLL usage - we hold a reference to the parent task, so we - * have access to the ->files - */ - struct task_struct *sqo_task; - - /* Only used for accounting purposes */ - struct mm_struct *mm_account; - -#ifdef CONFIG_BLK_CGROUP - struct cgroup_subsys_state *sqo_blkcg_css; -#endif + /* IRQ completion list, under ->completion_lock */ + struct list_head locked_free_list; + unsigned int locked_free_nr; + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ struct wait_queue_head sqo_sq_wait; - struct wait_queue_entry sqo_wait_entry; struct list_head sqd_list; - /* - * If used, fixed file set. Writers must ensure that ->refs is dead, - * readers must ensure that ->refs is alive as long as the file* is - * used. Only updated through io_uring_register(2). - */ - struct fixed_file_data *file_data; - unsigned nr_user_files; - - /* if used, fixed mapped user buffers */ - unsigned nr_user_bufs; - struct io_mapped_ubuf *user_bufs; - - struct user_struct *user; - - const struct cred *creds; - -#ifdef CONFIG_AUDIT - kuid_t loginuid; - unsigned int sessionid; -#endif - - struct completion ref_comp; - struct completion sq_thread_comp; - - /* if all else fails... */ - struct io_kiocb *fallback_req; - -#if defined(CONFIG_UNIX) - struct socket *ring_sock; -#endif - - struct xarray io_buffers; - - struct xarray personalities; - u32 pers_next; + unsigned long check_cq_overflow; struct { unsigned cached_cq_tail; unsigned cq_entries; - unsigned cq_mask; + struct eventfd_ctx *cq_ev_fd; + struct wait_queue_head poll_wait; + struct wait_queue_head cq_wait; + unsigned cq_extra; atomic_t cq_timeouts; unsigned cq_last_tm_flush; - unsigned long cq_check_overflow; - struct wait_queue_head cq_wait; - struct fasync_struct *cq_fasync; - struct eventfd_ctx *cq_ev_fd; - } ____cacheline_aligned_in_smp; - - struct { - struct mutex uring_lock; - wait_queue_head_t wait; } ____cacheline_aligned_in_smp; struct { spinlock_t completion_lock; + spinlock_t timeout_lock; + /* * ->iopoll_list is protected by the ctx->uring_lock for * io_uring instances that don't use IORING_SETUP_SQPOLL. @@ -379,17 +420,62 @@ struct io_ring_ctx { struct list_head iopoll_list; struct hlist_head *cancel_hash; unsigned cancel_hash_bits; - bool poll_multi_file; - - spinlock_t inflight_lock; - struct list_head inflight_list; + bool poll_multi_queue; } ____cacheline_aligned_in_smp; - struct delayed_work file_put_work; - struct llist_head file_put_llist; - - struct work_struct exit_work; struct io_restriction restrictions; + + /* slow path rsrc auxilary data, used by update/register */ + struct { + struct io_rsrc_node *rsrc_backup_node; + struct io_mapped_ubuf *dummy_ubuf; + struct io_rsrc_data *file_data; + struct io_rsrc_data *buf_data; + + struct delayed_work rsrc_put_work; + struct llist_head rsrc_put_llist; + struct list_head rsrc_ref_list; + spinlock_t rsrc_ref_lock; + }; + + /* Keep this last, we don't need it for the fast path */ + struct { + #if defined(CONFIG_UNIX) + struct socket *ring_sock; + #endif + /* hashed buffered write serialization */ + struct io_wq_hash *hash_map; + + /* Only used for accounting purposes */ + struct user_struct *user; + struct mm_struct *mm_account; + + /* ctx exit and cancelation */ + struct llist_head fallback_llist; + struct delayed_work fallback_work; + struct work_struct exit_work; + struct list_head tctx_list; + struct completion ref_comp; + u32 iowq_limits[2]; + bool iowq_limits_set; + }; +}; + +struct io_uring_task { + /* submission side */ + int cached_refs; + struct xarray xa; + struct wait_queue_head wait; + const struct io_ring_ctx *last; + struct io_wq *io_wq; + struct percpu_counter inflight; + atomic_t inflight_tracked; + atomic_t in_idle; + + spinlock_t task_lock; + struct io_wq_work_list task_list; + struct callback_head task_work; + bool task_running; }; /* @@ -398,20 +484,24 @@ struct io_ring_ctx { */ struct io_poll_iocb { struct file *file; - union { - struct wait_queue_head *head; - u64 addr; - }; + struct wait_queue_head *head; __poll_t events; - bool done; - bool canceled; struct wait_queue_entry wait; }; +struct io_poll_update { + struct file *file; + u64 old_user_data; + u64 new_user_data; + __poll_t events; + bool update_events; + bool update_user_data; +}; + struct io_close { struct file *file; - struct file *put_file; int fd; + u32 file_slot; }; struct io_timeout_data { @@ -419,6 +509,7 @@ struct io_timeout_data { struct hrtimer timer; struct timespec64 ts; enum hrtimer_mode mode; + u32 flags; }; struct io_accept { @@ -426,6 +517,7 @@ struct io_accept { struct sockaddr __user *addr; int __user *addr_len; int flags; + u32 file_slot; unsigned long nofile; }; @@ -447,11 +539,20 @@ struct io_timeout { u32 off; u32 target_seq; struct list_head list; + /* head of the link, used by linked timeouts only */ + struct io_kiocb *head; + /* for linked completions */ + struct io_kiocb *prev; }; struct io_timeout_rem { struct file *file; u64 addr; + + /* timeout update */ + struct timespec64 ts; + u32 flags; + bool ltimeout; }; struct io_rw { @@ -470,8 +571,9 @@ struct io_connect { struct io_sr_msg { struct file *file; union { - struct user_msghdr __user *umsg; - void __user *buf; + struct compat_msghdr __user *umsg_compat; + struct user_msghdr __user *umsg; + void __user *buf; }; int msg_flags; int bgid; @@ -482,13 +584,13 @@ struct io_sr_msg { struct io_open { struct file *file; int dfd; - bool ignore_nonblock; + u32 file_slot; struct filename *filename; struct open_how how; unsigned long nofile; }; -struct io_files_update { +struct io_rsrc_update { struct file *file; u64 arg; u32 nr_args; @@ -519,10 +621,10 @@ struct io_epoll { struct io_splice { struct file *file_out; - struct file *file_in; loff_t off_out; loff_t off_in; u64 len; + int splice_fd_in; unsigned int flags; }; @@ -544,9 +646,52 @@ struct io_statx { struct statx __user *buffer; }; +struct io_shutdown { + struct file *file; + int how; +}; + +struct io_rename { + struct file *file; + int old_dfd; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; + int flags; +}; + +struct io_unlink { + struct file *file; + int dfd; + int flags; + struct filename *filename; +}; + +struct io_mkdir { + struct file *file; + int dfd; + umode_t mode; + struct filename *filename; +}; + +struct io_symlink { + struct file *file; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; +}; + +struct io_hardlink { + struct file *file; + int old_dfd; + int new_dfd; + struct filename *oldpath; + struct filename *newpath; + int flags; +}; + struct io_completion { struct file *file; - struct list_head list; u32 cflags; }; @@ -556,7 +701,8 @@ struct io_async_connect { struct io_async_msghdr { struct iovec fast_iov[UIO_FASTIOV]; - struct iovec *iov; + /* points to an allocated iov, if NULL we use fast_iov instead */ + struct iovec *free_iov; struct sockaddr __user *uaddr; struct msghdr msg; struct sockaddr_storage addr; @@ -566,6 +712,7 @@ struct io_async_rw { struct iovec fast_iov[UIO_FASTIOV]; const struct iovec *free_iovec; struct iov_iter iter; + struct iov_iter_state iter_state; size_t bytes_done; struct wait_page_queue wpq; }; @@ -578,19 +725,24 @@ enum { REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, - REQ_F_LINK_HEAD_BIT, - REQ_F_FAIL_LINK_BIT, + /* first byte is taken by user flags, shift it to not overlap */ + REQ_F_FAIL_BIT = 8, REQ_F_INFLIGHT_BIT, REQ_F_CUR_POS_BIT, REQ_F_NOWAIT_BIT, REQ_F_LINK_TIMEOUT_BIT, - REQ_F_ISREG_BIT, REQ_F_NEED_CLEANUP_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, - REQ_F_NO_FILE_TABLE_BIT, - REQ_F_WORK_INITIALIZED_BIT, - REQ_F_LTIMEOUT_ACTIVE_BIT, + REQ_F_COMPLETE_INLINE_BIT, + REQ_F_REISSUE_BIT, + REQ_F_CREDS_BIT, + REQ_F_REFCOUNT_BIT, + REQ_F_ARM_LTIMEOUT_BIT, + /* keep async read/write and isreg together and in order */ + REQ_F_NOWAIT_READ_BIT, + REQ_F_NOWAIT_WRITE_BIT, + REQ_F_ISREG_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -610,11 +762,9 @@ enum { /* IOSQE_BUFFER_SELECT */ REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), - /* head of a link */ - REQ_F_LINK_HEAD = BIT(REQ_F_LINK_HEAD_BIT), /* fail rest of links */ - REQ_F_FAIL_LINK = BIT(REQ_F_FAIL_LINK_BIT), - /* on inflight list */ + REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), + /* on inflight list, should be cancelled and waited on exit reliably */ REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), /* read/write uses file position */ REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), @@ -622,20 +772,28 @@ enum { REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), /* has or had linked timeout */ REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), - /* regular file */ - REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), /* needs cleanup */ REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), /* already went through poll handler */ REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), /* buffer already selected */ REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), - /* doesn't need file table for this request */ - REQ_F_NO_FILE_TABLE = BIT(REQ_F_NO_FILE_TABLE_BIT), - /* io_wq_work is initialized */ - REQ_F_WORK_INITIALIZED = BIT(REQ_F_WORK_INITIALIZED_BIT), - /* linked timeout is active, i.e. prepared by link's head */ - REQ_F_LTIMEOUT_ACTIVE = BIT(REQ_F_LTIMEOUT_ACTIVE_BIT), + /* completion is deferred through io_comp_state */ + REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), + /* caller should reissue async */ + REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), + /* supports async reads */ + REQ_F_NOWAIT_READ = BIT(REQ_F_NOWAIT_READ_BIT), + /* supports async writes */ + REQ_F_NOWAIT_WRITE = BIT(REQ_F_NOWAIT_WRITE_BIT), + /* regular file */ + REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), + /* has creds assigned */ + REQ_F_CREDS = BIT(REQ_F_CREDS_BIT), + /* skip refcounting if not set */ + REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), + /* there is a linked timeout that has to be armed */ + REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), }; struct async_poll { @@ -643,6 +801,21 @@ struct async_poll { struct io_poll_iocb *double_poll; }; +typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked); + +struct io_task_work { + union { + struct io_wq_work_node node; + struct llist_node fallback_node; + }; + io_req_tw_func_t func; +}; + +enum { + IORING_RSRC_FILE = 0, + IORING_RSRC_BUFFER = 1, +}; + /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can @@ -654,6 +827,7 @@ struct io_kiocb { struct file *file; struct io_rw rw; struct io_poll_iocb poll; + struct io_poll_update poll_update; struct io_accept accept; struct io_sync sync; struct io_cancel cancel; @@ -663,13 +837,19 @@ struct io_kiocb { struct io_sr_msg sr_msg; struct io_open open; struct io_close close; - struct io_files_update files_update; + struct io_rsrc_update rsrc_update; struct io_fadvise fadvise; struct io_madvise madvise; struct io_epoll epoll; struct io_splice splice; struct io_provide_buf pbuf; struct io_statx statx; + struct io_shutdown shutdown; + struct io_rename rename; + struct io_unlink unlink; + struct io_mkdir mkdir; + struct io_symlink symlink; + struct io_hardlink hardlink; /* use only after cleaning per-op data, see io_clean_op() */ struct io_completion compl; }; @@ -685,26 +865,33 @@ struct io_kiocb { struct io_ring_ctx *ctx; unsigned int flags; - refcount_t refs; + atomic_t refs; struct task_struct *task; u64 user_data; - struct list_head link_list; + struct io_kiocb *link; + struct percpu_ref *fixed_rsrc_refs; - /* - * 1. used with ctx->iopoll_list with reads/writes - * 2. to track reqs with ->files (see io_op_def::file_table) - */ + /* used with ctx->iopoll_list with reads/writes */ struct list_head inflight_entry; - - struct list_head iopoll_entry; - - struct percpu_ref *fixed_file_refs; - struct callback_head task_work; + struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; struct async_poll *apoll; struct io_wq_work work; + const struct cred *creds; + + /* store used ubuf, so we can prevent reloading */ + struct io_mapped_ubuf *imu; + /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ + struct io_buffer *kbuf; + atomic_t poll_refs; +}; + +struct io_tctx_node { + struct list_head ctx_node; + struct task_struct *task; + struct io_ring_ctx *ctx; }; struct io_defer_entry { @@ -713,42 +900,9 @@ struct io_defer_entry { u32 seq; }; -#define IO_IOPOLL_BATCH 8 - -struct io_comp_state { - unsigned int nr; - struct list_head list; - struct io_ring_ctx *ctx; -}; - -struct io_submit_state { - struct blk_plug plug; - - /* - * io_kiocb alloc cache - */ - void *reqs[IO_IOPOLL_BATCH]; - unsigned int free_reqs; - - /* - * Batch completion logic - */ - struct io_comp_state comp; - - /* - * File reference cache - */ - struct file *file; - unsigned int fd; - unsigned int has_refs; - unsigned int ios_left; -}; - struct io_op_def { /* needs req->file assigned */ unsigned needs_file : 1; - /* don't fail if file grab fails */ - unsigned needs_file_no_error : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ @@ -760,11 +914,12 @@ struct io_op_def { unsigned pollout : 1; /* op supports buffer selection */ unsigned buffer_select : 1; - /* must always have async data allocated */ - unsigned needs_async_data : 1; + /* do prep async if is going to be punted */ + unsigned needs_async_setup : 1; + /* should block plug */ + unsigned plug : 1; /* size of async data needed, if any */ unsigned short async_size; - unsigned work_flags; }; static const struct io_op_def io_op_defs[] = { @@ -774,41 +929,36 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, - .needs_async_data = 1, + .needs_async_setup = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FILES, }, [IORING_OP_WRITEV] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, - .needs_async_data = 1, + .needs_async_setup = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FSIZE | IO_WQ_WORK_FILES, }, [IORING_OP_FSYNC] = { .needs_file = 1, - .work_flags = IO_WQ_WORK_BLKCG, }, [IORING_OP_READ_FIXED] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_BLKCG | IO_WQ_WORK_MM | - IO_WQ_WORK_FILES, }, [IORING_OP_WRITE_FIXED] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_BLKCG | IO_WQ_WORK_FSIZE | - IO_WQ_WORK_MM | IO_WQ_WORK_FILES, }, [IORING_OP_POLL_ADD] = { .needs_file = 1, @@ -817,126 +967,91 @@ static const struct io_op_def io_op_defs[] = { [IORING_OP_POLL_REMOVE] = {}, [IORING_OP_SYNC_FILE_RANGE] = { .needs_file = 1, - .work_flags = IO_WQ_WORK_BLKCG, }, [IORING_OP_SENDMSG] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, - .needs_async_data = 1, + .needs_async_setup = 1, .async_size = sizeof(struct io_async_msghdr), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, }, [IORING_OP_RECVMSG] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, - .needs_async_data = 1, + .needs_async_setup = 1, .async_size = sizeof(struct io_async_msghdr), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, }, [IORING_OP_TIMEOUT] = { - .needs_async_data = 1, .async_size = sizeof(struct io_timeout_data), - .work_flags = IO_WQ_WORK_MM, }, - [IORING_OP_TIMEOUT_REMOVE] = {}, + [IORING_OP_TIMEOUT_REMOVE] = { + /* used by timeout updates' prep() */ + }, [IORING_OP_ACCEPT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_FILES, }, [IORING_OP_ASYNC_CANCEL] = {}, [IORING_OP_LINK_TIMEOUT] = { - .needs_async_data = 1, .async_size = sizeof(struct io_timeout_data), - .work_flags = IO_WQ_WORK_MM, }, [IORING_OP_CONNECT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, - .needs_async_data = 1, + .needs_async_setup = 1, .async_size = sizeof(struct io_async_connect), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_FS, }, [IORING_OP_FALLOCATE] = { .needs_file = 1, - .work_flags = IO_WQ_WORK_BLKCG | IO_WQ_WORK_FSIZE, - }, - [IORING_OP_OPENAT] = { - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, - }, - [IORING_OP_CLOSE] = { - .needs_file = 1, - .needs_file_no_error = 1, - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_BLKCG, - }, - [IORING_OP_FILES_UPDATE] = { - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_MM, - }, - [IORING_OP_STATX] = { - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_MM | - IO_WQ_WORK_FS | IO_WQ_WORK_BLKCG, }, + [IORING_OP_OPENAT] = {}, + [IORING_OP_CLOSE] = {}, + [IORING_OP_FILES_UPDATE] = {}, + [IORING_OP_STATX] = {}, [IORING_OP_READ] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FILES, }, [IORING_OP_WRITE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, + .plug = 1, .async_size = sizeof(struct io_async_rw), - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FSIZE | IO_WQ_WORK_FILES, }, [IORING_OP_FADVISE] = { .needs_file = 1, - .work_flags = IO_WQ_WORK_BLKCG, - }, - [IORING_OP_MADVISE] = { - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG, }, + [IORING_OP_MADVISE] = {}, [IORING_OP_SEND] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, }, [IORING_OP_RECV] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, - .work_flags = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG | - IO_WQ_WORK_FS, }, [IORING_OP_OPENAT2] = { - .work_flags = IO_WQ_WORK_FILES | IO_WQ_WORK_FS | - IO_WQ_WORK_BLKCG, }, [IORING_OP_EPOLL_CTL] = { .unbound_nonreg_file = 1, - .work_flags = IO_WQ_WORK_FILES, }, [IORING_OP_SPLICE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, - .work_flags = IO_WQ_WORK_BLKCG | IO_WQ_WORK_FILES, }, [IORING_OP_PROVIDE_BUFFERS] = {}, [IORING_OP_REMOVE_BUFFERS] = {}, @@ -945,43 +1060,47 @@ static const struct io_op_def io_op_defs[] = { .hash_reg_file = 1, .unbound_nonreg_file = 1, }, + [IORING_OP_SHUTDOWN] = { + .needs_file = 1, + }, + [IORING_OP_RENAMEAT] = {}, + [IORING_OP_UNLINKAT] = {}, }; -enum io_mem_account { - ACCT_LOCKED, - ACCT_PINNED, -}; +/* requests with any of those set should undergo io_disarm_next() */ +#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) -static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node); -static struct fixed_file_ref_node *alloc_fixed_file_ref_node( - struct io_ring_ctx *ctx); +static bool io_disarm_next(struct io_kiocb *req); +static void io_uring_del_tctx_node(unsigned long index); +static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all); +static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); + +static void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags); -static void __io_complete_rw(struct io_kiocb *req, long res, long res2, - struct io_comp_state *cs); -static void io_cqring_fill_event(struct io_kiocb *req, long res); static void io_put_req(struct io_kiocb *req); -static void io_put_req_deferred(struct io_kiocb *req, int nr); -static void io_double_put_req(struct io_kiocb *req); -static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req); -static void __io_queue_linked_timeout(struct io_kiocb *req); +static void io_put_req_deferred(struct io_kiocb *req); +static void io_dismantle_req(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); -static int __io_sqe_files_update(struct io_ring_ctx *ctx, - struct io_uring_files_update *ip, - unsigned nr_args); -static void __io_clean_op(struct io_kiocb *req); -static struct file *io_file_get(struct io_submit_state *state, +static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, + struct io_uring_rsrc_update2 *up, + unsigned nr_args); +static void io_clean_op(struct io_kiocb *req); +static struct file *io_file_get(struct io_ring_ctx *ctx, struct io_kiocb *req, int fd, bool fixed); -static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs); -static void io_file_put_work(struct work_struct *work); +static void __io_queue_sqe(struct io_kiocb *req); +static void io_rsrc_put_work(struct work_struct *work); -static ssize_t io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock); -static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, - const struct iovec *fast_iov, - struct iov_iter *iter, bool force); -static void io_req_drop_files(struct io_kiocb *req); static void io_req_task_queue(struct io_kiocb *req); +static void io_submit_flush_completions(struct io_ring_ctx *ctx); +static int io_req_prep_async(struct io_kiocb *req); + +static int io_install_fixed_file(struct io_kiocb *req, struct file *file, + unsigned int issue_flags, u32 slot_index); +static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags); + +static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer); static struct kmem_cache *req_cachep; @@ -1000,21 +1119,67 @@ struct sock *io_uring_get_socket(struct file *file) } EXPORT_SYMBOL(io_uring_get_socket); -static inline void io_clean_op(struct io_kiocb *req) +static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) { - if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED)) - __io_clean_op(req); + if (!*locked) { + mutex_lock(&ctx->uring_lock); + *locked = true; + } } -static inline bool __io_match_files(struct io_kiocb *req, - struct files_struct *files) +#define io_for_each_link(pos, head) \ + for (pos = (head); pos; pos = pos->link) + +/* + * Shamelessly stolen from the mm implementation of page reference checking, + * see commit f958d7b528b1 for details. + */ +#define req_ref_zero_or_close_to_overflow(req) \ + ((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u) + +static inline bool req_ref_inc_not_zero(struct io_kiocb *req) { - if (req->file && req->file->f_op == &io_uring_fops) + WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); + return atomic_inc_not_zero(&req->refs); +} + +static inline bool req_ref_put_and_test(struct io_kiocb *req) +{ + if (likely(!(req->flags & REQ_F_REFCOUNT))) return true; - return ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_FILES)) && - req->work.identity->files == files; + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + return atomic_dec_and_test(&req->refs); +} + +static inline void req_ref_get(struct io_kiocb *req) +{ + WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + atomic_inc(&req->refs); +} + +static inline void __io_req_set_refcount(struct io_kiocb *req, int nr) +{ + if (!(req->flags & REQ_F_REFCOUNT)) { + req->flags |= REQ_F_REFCOUNT; + atomic_set(&req->refs, nr); + } +} + +static inline void io_req_set_refcount(struct io_kiocb *req) +{ + __io_req_set_refcount(req, 1); +} + +static inline void io_req_set_rsrc_node(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (!req->fixed_rsrc_refs) { + req->fixed_rsrc_refs = &ctx->rsrc_node->refs; + percpu_ref_get(req->fixed_rsrc_refs); + } } static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl) @@ -1029,157 +1194,71 @@ static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl) percpu_ref_put(ref); } -static bool io_match_task(struct io_kiocb *head, - struct task_struct *task, - struct files_struct *files) +static bool io_match_task(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) + __must_hold(&req->ctx->timeout_lock) { - struct io_kiocb *link; + struct io_kiocb *req; - if (task && head->task != task) { - /* in terms of cancelation, always match if req task is dead */ - if (head->task->flags & PF_EXITING) - return true; + if (task && head->task != task) return false; - } - if (!files) + if (cancel_all) return true; - if (__io_match_files(head, files)) - return true; - if (head->flags & REQ_F_LINK_HEAD) { - list_for_each_entry(link, &head->link_list, link_list) { - if (__io_match_files(link, files)) - return true; - } + + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; } return false; } - -static void io_sq_thread_drop_mm(void) +static bool io_match_linked(struct io_kiocb *head) { - struct mm_struct *mm = current->mm; + struct io_kiocb *req; - if (mm) { - kthread_unuse_mm(mm); - mmput(mm); - current->mm = NULL; + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; } -} - -static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx) -{ - struct mm_struct *mm; - - if (current->flags & PF_EXITING) - return -EFAULT; - if (current->mm) - return 0; - - /* Should never happen */ - if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL))) - return -EFAULT; - - task_lock(ctx->sqo_task); - mm = ctx->sqo_task->mm; - if (unlikely(!mm || !mmget_not_zero(mm))) - mm = NULL; - task_unlock(ctx->sqo_task); - - if (mm) { - kthread_use_mm(mm); - return 0; - } - - return -EFAULT; -} - -static int io_sq_thread_acquire_mm(struct io_ring_ctx *ctx, - struct io_kiocb *req) -{ - if (!(io_op_defs[req->opcode].work_flags & IO_WQ_WORK_MM)) - return 0; - return __io_sq_thread_acquire_mm(ctx); -} - -static void io_sq_thread_associate_blkcg(struct io_ring_ctx *ctx, - struct cgroup_subsys_state **cur_css) - -{ -#ifdef CONFIG_BLK_CGROUP - /* puts the old one when swapping */ - if (*cur_css != ctx->sqo_blkcg_css) { - kthread_associate_blkcg(ctx->sqo_blkcg_css); - *cur_css = ctx->sqo_blkcg_css; - } -#endif -} - -static void io_sq_thread_unassociate_blkcg(void) -{ -#ifdef CONFIG_BLK_CGROUP - kthread_associate_blkcg(NULL); -#endif -} - -static inline void req_set_fail_links(struct io_kiocb *req) -{ - if ((req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) == REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + return false; } /* - * None of these are dereferenced, they are simply used to check if any of - * them have changed. If we're under current and check they are still the - * same, we're fine to grab references to them for actual out-of-line use. + * As io_match_task() but protected against racing with linked timeouts. + * User must not hold timeout_lock. */ -static void io_init_identity(struct io_identity *id) +static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) { - id->files = current->files; - id->mm = current->mm; -#ifdef CONFIG_BLK_CGROUP - rcu_read_lock(); - id->blkcg_css = blkcg_css(); - rcu_read_unlock(); -#endif - id->creds = current_cred(); - id->nsproxy = current->nsproxy; - id->fs = current->fs; - id->fsize = rlimit(RLIMIT_FSIZE); -#ifdef CONFIG_AUDIT - id->loginuid = current->loginuid; - id->sessionid = current->sessionid; -#endif - refcount_set(&id->count, 1); + bool matched; + + if (task && head->task != task) + return false; + if (cancel_all) + return true; + + if (head->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = head->ctx; + + /* protect against races with linked timeouts */ + spin_lock_irq(&ctx->timeout_lock); + matched = io_match_linked(head); + spin_unlock_irq(&ctx->timeout_lock); + } else { + matched = io_match_linked(head); + } + return matched; } -static inline void __io_req_init_async(struct io_kiocb *req) +static inline void req_set_fail(struct io_kiocb *req) { - memset(&req->work, 0, sizeof(req->work)); - req->flags |= REQ_F_WORK_INITIALIZED; + req->flags |= REQ_F_FAIL; } -/* - * Note: must call io_req_init_async() for the first time you - * touch any members of io_wq_work. - */ -static inline void io_req_init_async(struct io_kiocb *req) +static inline void req_fail_link_node(struct io_kiocb *req, int res) { - struct io_uring_task *tctx = req->task->io_uring; - - if (req->flags & REQ_F_WORK_INITIALIZED) - return; - - __io_req_init_async(req); - - /* Grab a ref if this isn't our static identity */ - req->work.identity = tctx->identity; - if (tctx->identity != &tctx->__identity) - refcount_inc(&req->work.identity->count); -} - -static inline bool io_async_submit(struct io_ring_ctx *ctx) -{ - return ctx->flags & IORING_SETUP_SQPOLL; + req_set_fail(req); + req->result = res; } static void io_ring_ctx_ref_free(struct percpu_ref *ref) @@ -1194,6 +1273,27 @@ static inline bool io_is_timeout_noseq(struct io_kiocb *req) return !req->timeout.off; } +static void io_fallback_req_func(struct work_struct *work) +{ + struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, + fallback_work.work); + struct llist_node *node = llist_del_all(&ctx->fallback_llist); + struct io_kiocb *req, *tmp; + bool locked = false; + + percpu_ref_get(&ctx->refs); + llist_for_each_entry_safe(req, tmp, node, io_task_work.fallback_node) + req->io_task_work.func(req, &locked); + + if (locked) { + if (ctx->submit_state.compl_nr) + io_submit_flush_completions(ctx); + mutex_unlock(&ctx->uring_lock); + } + percpu_ref_put(&ctx->refs); + +} + static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) { struct io_ring_ctx *ctx; @@ -1203,10 +1303,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) if (!ctx) return NULL; - ctx->fallback_req = kmem_cache_alloc(req_cachep, GFP_KERNEL); - if (!ctx->fallback_req) - goto err; - /* * Use 5 bits less than the max cq entries, that should give us around * 32 entries per hash list if totally full and uniformly spread. @@ -1222,6 +1318,12 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) goto err; __hash_init(ctx->cancel_hash, 1U << hash_bits); + ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL); + if (!ctx->dummy_ubuf) + goto err; + /* set invalid range, so io_import_fixed() fails meeting it */ + ctx->dummy_ubuf->ubuf = -1UL; + if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) goto err; @@ -1229,232 +1331,109 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ctx->flags = p->flags; init_waitqueue_head(&ctx->sqo_sq_wait); INIT_LIST_HEAD(&ctx->sqd_list); - init_waitqueue_head(&ctx->cq_wait); + init_waitqueue_head(&ctx->poll_wait); INIT_LIST_HEAD(&ctx->cq_overflow_list); init_completion(&ctx->ref_comp); - init_completion(&ctx->sq_thread_comp); xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); - init_waitqueue_head(&ctx->wait); + init_waitqueue_head(&ctx->cq_wait); spin_lock_init(&ctx->completion_lock); + spin_lock_init(&ctx->timeout_lock); INIT_LIST_HEAD(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); - spin_lock_init(&ctx->inflight_lock); - INIT_LIST_HEAD(&ctx->inflight_list); - INIT_DELAYED_WORK(&ctx->file_put_work, io_file_put_work); - init_llist_head(&ctx->file_put_llist); + INIT_LIST_HEAD(&ctx->ltimeout_list); + spin_lock_init(&ctx->rsrc_ref_lock); + INIT_LIST_HEAD(&ctx->rsrc_ref_list); + INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work); + init_llist_head(&ctx->rsrc_put_llist); + INIT_LIST_HEAD(&ctx->tctx_list); + INIT_LIST_HEAD(&ctx->submit_state.free_list); + INIT_LIST_HEAD(&ctx->locked_free_list); + INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); return ctx; err: - if (ctx->fallback_req) - kmem_cache_free(req_cachep, ctx->fallback_req); + kfree(ctx->dummy_ubuf); kfree(ctx->cancel_hash); kfree(ctx); return NULL; } +static void io_account_cq_overflow(struct io_ring_ctx *ctx) +{ + struct io_rings *r = ctx->rings; + + WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1); + ctx->cq_extra--; +} + static bool req_need_defer(struct io_kiocb *req, u32 seq) { if (unlikely(req->flags & REQ_F_IO_DRAIN)) { struct io_ring_ctx *ctx = req->ctx; - return seq != ctx->cached_cq_tail - + READ_ONCE(ctx->cached_cq_overflow); + return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail; } return false; } -static void __io_commit_cqring(struct io_ring_ctx *ctx) -{ - struct io_rings *rings = ctx->rings; - - /* order cqe stores with ring update */ - smp_store_release(&rings->cq.tail, ctx->cached_cq_tail); -} - -static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req) -{ - if (req->work.identity == &tctx->__identity) - return; - if (refcount_dec_and_test(&req->work.identity->count)) - kfree(req->work.identity); -} - -static void io_req_clean_work(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_WORK_INITIALIZED)) - return; - - req->flags &= ~REQ_F_WORK_INITIALIZED; - - if (req->work.flags & IO_WQ_WORK_MM) { - mmdrop(req->work.identity->mm); - req->work.flags &= ~IO_WQ_WORK_MM; - } -#ifdef CONFIG_BLK_CGROUP - if (req->work.flags & IO_WQ_WORK_BLKCG) { - css_put(req->work.identity->blkcg_css); - req->work.flags &= ~IO_WQ_WORK_BLKCG; - } +#define FFS_ASYNC_READ 0x1UL +#define FFS_ASYNC_WRITE 0x2UL +#ifdef CONFIG_64BIT +#define FFS_ISREG 0x4UL +#else +#define FFS_ISREG 0x0UL #endif - if (req->work.flags & IO_WQ_WORK_CREDS) { - put_cred(req->work.identity->creds); - req->work.flags &= ~IO_WQ_WORK_CREDS; - } - if (req->work.flags & IO_WQ_WORK_FS) { - struct fs_struct *fs = req->work.identity->fs; +#define FFS_MASK ~(FFS_ASYNC_READ|FFS_ASYNC_WRITE|FFS_ISREG) - spin_lock(&req->work.identity->fs->lock); - if (--fs->users) - fs = NULL; - spin_unlock(&req->work.identity->fs->lock); - if (fs) - free_fs_struct(fs); - req->work.flags &= ~IO_WQ_WORK_FS; - } - if (req->flags & REQ_F_INFLIGHT) - io_req_drop_files(req); - - io_put_identity(req->task->io_uring, req); +static inline bool io_req_ffs_set(struct io_kiocb *req) +{ + return IS_ENABLED(CONFIG_64BIT) && (req->flags & REQ_F_FIXED_FILE); } -/* - * Create a private copy of io_identity, since some fields don't match - * the current context. - */ -static bool io_identity_cow(struct io_kiocb *req) +static void io_req_track_inflight(struct io_kiocb *req) { - struct io_uring_task *tctx = req->task->io_uring; - const struct cred *creds = NULL; - struct io_identity *id; - - if (req->work.flags & IO_WQ_WORK_CREDS) - creds = req->work.identity->creds; - - id = kmemdup(req->work.identity, sizeof(*id), GFP_KERNEL); - if (unlikely(!id)) { - req->work.flags |= IO_WQ_WORK_CANCEL; - return false; + if (!(req->flags & REQ_F_INFLIGHT)) { + req->flags |= REQ_F_INFLIGHT; + atomic_inc(&req->task->io_uring->inflight_tracked); } - - /* - * We can safely just re-init the creds we copied Either the field - * matches the current one, or we haven't grabbed it yet. The only - * exception is ->creds, through registered personalities, so handle - * that one separately. - */ - io_init_identity(id); - if (creds) - id->creds = creds; - - /* add one for this request */ - refcount_inc(&id->count); - - /* drop tctx and req identity references, if needed */ - if (tctx->identity != &tctx->__identity && - refcount_dec_and_test(&tctx->identity->count)) - kfree(tctx->identity); - if (req->work.identity != &tctx->__identity && - refcount_dec_and_test(&req->work.identity->count)) - kfree(req->work.identity); - - req->work.identity = id; - tctx->identity = id; - return true; } -static bool io_grab_identity(struct io_kiocb *req) +static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { - const struct io_op_def *def = &io_op_defs[req->opcode]; - struct io_identity *id = req->work.identity; - struct io_ring_ctx *ctx = req->ctx; + if (WARN_ON_ONCE(!req->link)) + return NULL; - if (def->work_flags & IO_WQ_WORK_FSIZE) { - if (id->fsize != rlimit(RLIMIT_FSIZE)) - return false; - req->work.flags |= IO_WQ_WORK_FSIZE; - } -#ifdef CONFIG_BLK_CGROUP - if (!(req->work.flags & IO_WQ_WORK_BLKCG) && - (def->work_flags & IO_WQ_WORK_BLKCG)) { - rcu_read_lock(); - if (id->blkcg_css != blkcg_css()) { - rcu_read_unlock(); - return false; - } - /* - * This should be rare, either the cgroup is dying or the task - * is moving cgroups. Just punt to root for the handful of ios. - */ - if (css_tryget_online(id->blkcg_css)) - req->work.flags |= IO_WQ_WORK_BLKCG; - rcu_read_unlock(); - } -#endif - if (!(req->work.flags & IO_WQ_WORK_CREDS)) { - if (id->creds != current_cred()) - return false; - get_cred(id->creds); - req->work.flags |= IO_WQ_WORK_CREDS; - } -#ifdef CONFIG_AUDIT - if (!uid_eq(current->loginuid, id->loginuid) || - current->sessionid != id->sessionid) - return false; -#endif - if (!(req->work.flags & IO_WQ_WORK_FS) && - (def->work_flags & IO_WQ_WORK_FS)) { - if (current->fs != id->fs) - return false; - spin_lock(&id->fs->lock); - if (!id->fs->in_exec) { - id->fs->users++; - req->work.flags |= IO_WQ_WORK_FS; - } else { - req->work.flags |= IO_WQ_WORK_CANCEL; - } - spin_unlock(¤t->fs->lock); - } - if (!(req->work.flags & IO_WQ_WORK_FILES) && - (def->work_flags & IO_WQ_WORK_FILES) && - !(req->flags & REQ_F_NO_FILE_TABLE)) { - if (id->files != current->files || - id->nsproxy != current->nsproxy) - return false; - atomic_inc(&id->files->count); - get_nsproxy(id->nsproxy); + req->flags &= ~REQ_F_ARM_LTIMEOUT; + req->flags |= REQ_F_LINK_TIMEOUT; - if (!(req->flags & REQ_F_INFLIGHT)) { - req->flags |= REQ_F_INFLIGHT; + /* linked timeouts should have two refs once prep'ed */ + io_req_set_refcount(req); + __io_req_set_refcount(req->link, 2); + return req->link; +} - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); - } - req->work.flags |= IO_WQ_WORK_FILES; - } - if (!(req->work.flags & IO_WQ_WORK_MM) && - (def->work_flags & IO_WQ_WORK_MM)) { - if (id->mm != current->mm) - return false; - mmgrab(id->mm); - req->work.flags |= IO_WQ_WORK_MM; - } - - return true; +static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) +{ + if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT))) + return NULL; + return __io_prep_linked_timeout(req); } static void io_prep_async_work(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; - struct io_identity *id; - io_req_init_async(req); - id = req->work.identity; + if (!(req->flags & REQ_F_CREDS)) { + req->flags |= REQ_F_CREDS; + req->creds = get_current_cred(); + } + req->work.list.next = NULL; + req->work.flags = 0; if (req->flags & REQ_F_FORCE_ASYNC) req->work.flags |= IO_WQ_WORK_CONCURRENT; @@ -1465,92 +1444,77 @@ static void io_prep_async_work(struct io_kiocb *req) if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } - - /* if we fail grabbing identity, we must COW, regrab, and retry */ - if (io_grab_identity(req)) - return; - - if (!io_identity_cow(req)) - return; - - /* can't fail at this point */ - if (!io_grab_identity(req)) - WARN_ON(1); } static void io_prep_async_link(struct io_kiocb *req) { struct io_kiocb *cur; - io_prep_async_work(req); - if (req->flags & REQ_F_LINK_HEAD) - list_for_each_entry(cur, &req->link_list, link_list) + if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + io_for_each_link(cur, req) io_prep_async_work(cur); + spin_unlock_irq(&ctx->timeout_lock); + } else { + io_for_each_link(cur, req) + io_prep_async_work(cur); + } } -static struct io_kiocb *__io_queue_async_work(struct io_kiocb *req) +static void io_queue_async_work(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link = io_prep_linked_timeout(req); + struct io_uring_task *tctx = req->task->io_uring; - trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, - &req->work, req->flags); - io_wq_enqueue(ctx->io_wq, &req->work); - return link; -} + /* must not take the lock, NULL it as a precaution */ + locked = NULL; -static void io_queue_async_work(struct io_kiocb *req) -{ - struct io_kiocb *link; + BUG_ON(!tctx); + BUG_ON(!tctx->io_wq); /* init ->work of the whole link before punting */ io_prep_async_link(req); - link = __io_queue_async_work(req); + /* + * Not expected to happen, but if we do have a bug where this _can_ + * happen, catch it here and ensure the request is marked as + * canceled. That will make io-wq go through the usual work cancel + * procedure rather than attempt to run this request (or create a new + * worker for it). + */ + if (WARN_ON_ONCE(!same_thread_group(req->task, current))) + req->work.flags |= IO_WQ_WORK_CANCEL; + + trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, + &req->work, req->flags); + io_wq_enqueue(tctx->io_wq, &req->work); if (link) io_queue_linked_timeout(link); } static void io_kill_timeout(struct io_kiocb *req, int status) + __must_hold(&req->ctx->completion_lock) + __must_hold(&req->ctx->timeout_lock) { struct io_timeout_data *io = req->async_data; - int ret; - ret = hrtimer_try_to_cancel(&io->timer); - if (ret != -1) { + if (hrtimer_try_to_cancel(&io->timer) != -1) { if (status) - req_set_fail_links(req); + req_set_fail(req); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); list_del_init(&req->timeout.list); - io_cqring_fill_event(req, status); - io_put_req_deferred(req, 1); + io_fill_cqe_req(req, status, 0); + io_put_req_deferred(req); } } -/* - * Returns true if we found and killed one or more timeouts - */ -static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, - struct files_struct *files) +static void io_queue_deferred(struct io_ring_ctx *ctx) { - struct io_kiocb *req, *tmp; - int canceled = 0; - - spin_lock_irq(&ctx->completion_lock); - list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { - if (io_match_task(req, tsk, files)) { - io_kill_timeout(req, -ECANCELED); - canceled++; - } - } - spin_unlock_irq(&ctx->completion_lock); - return canceled != 0; -} - -static void __io_queue_deferred(struct io_ring_ctx *ctx) -{ - do { + while (!list_empty(&ctx->defer_list)) { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); @@ -1559,19 +1523,16 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) list_del_init(&de->list); io_req_task_queue(de->req); kfree(de); - } while (!list_empty(&ctx->defer_list)); + } } static void io_flush_timeouts(struct io_ring_ctx *ctx) + __must_hold(&ctx->completion_lock) { + u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); struct io_kiocb *req, *tmp; - u32 seq; - - if (list_empty(&ctx->timeout_list)) - return; - - seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + spin_lock_irq(&ctx->timeout_lock); list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { u32 events_needed, events_got; @@ -1592,441 +1553,564 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx) io_kill_timeout(req, 0); } - ctx->cq_last_tm_flush = seq; + spin_unlock_irq(&ctx->timeout_lock); } -static void io_commit_cqring(struct io_ring_ctx *ctx) +static void __io_commit_cqring_flush(struct io_ring_ctx *ctx) { - io_flush_timeouts(ctx); - __io_commit_cqring(ctx); + if (ctx->off_timeout_used) + io_flush_timeouts(ctx); + if (ctx->drain_active) + io_queue_deferred(ctx); +} - if (unlikely(!list_empty(&ctx->defer_list))) - __io_queue_deferred(ctx); +static inline void io_commit_cqring(struct io_ring_ctx *ctx) +{ + if (unlikely(ctx->off_timeout_used || ctx->drain_active)) + __io_commit_cqring_flush(ctx); + /* order cqe stores with ring update */ + smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); } static inline bool io_sqring_full(struct io_ring_ctx *ctx) { struct io_rings *r = ctx->rings; - return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == r->sq_ring_entries; + return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries; } -static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) +static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) +{ + return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); +} + +static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; - unsigned tail; + unsigned tail, mask = ctx->cq_entries - 1; - tail = ctx->cached_cq_tail; /* * writes to the cq entry need to come after reading head; the * control dependency is enough as we're using WRITE_ONCE to * fill the cq entry */ - if (tail - READ_ONCE(rings->cq.head) == rings->cq_ring_entries) + if (__io_cqring_events(ctx) == ctx->cq_entries) return NULL; - ctx->cached_cq_tail++; - return &rings->cqes[tail & ctx->cq_mask]; + tail = ctx->cached_cq_tail++; + return &rings->cqes[tail & mask]; } static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) { - if (!ctx->cq_ev_fd) + if (likely(!ctx->cq_ev_fd)) return false; if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) return false; - if (!ctx->eventfd_async) - return true; - return io_wq_current_is_worker(); + return !ctx->eventfd_async || io_wq_current_is_worker(); } +/* + * This should only get called when at least one event has been posted. + * Some applications rely on the eventfd notification count only changing + * IFF a new CQE has been added to the CQ ring. There's no depedency on + * 1:1 relationship between how many times this function is called (and + * hence the eventfd count) and number of CQEs posted to the CQ ring. + */ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) { - if (wq_has_sleeper(&ctx->cq_wait)) { - wake_up_interruptible(&ctx->cq_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); + /* + * wake_up_all() may seem excessive, but io_wake_function() and + * io_should_wake() handle the termination of the loop and only + * wake as many waiters as we need to. + */ + if (wq_has_sleeper(&ctx->cq_wait)) + wake_up_all(&ctx->cq_wait); if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); + if (waitqueue_active(&ctx->poll_wait)) + wake_up_interruptible(&ctx->poll_wait); } -static void io_cqring_mark_overflow(struct io_ring_ctx *ctx) +static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) { - if (list_empty(&ctx->cq_overflow_list)) { - clear_bit(0, &ctx->sq_check_overflow); - clear_bit(0, &ctx->cq_check_overflow); - ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; + /* see waitqueue_active() comment */ + smp_mb(); + + if (ctx->flags & IORING_SETUP_SQPOLL) { + if (waitqueue_active(&ctx->cq_wait)) + wake_up_all(&ctx->cq_wait); } + if (io_should_trigger_evfd(ctx)) + eventfd_signal(ctx->cq_ev_fd, 1); + if (waitqueue_active(&ctx->poll_wait)) + wake_up_interruptible(&ctx->poll_wait); } /* Returns true if there are no backlogged entries after the flush */ -static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, - struct task_struct *tsk, - struct files_struct *files) +static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) { - struct io_rings *rings = ctx->rings; - struct io_kiocb *req, *tmp; - struct io_uring_cqe *cqe; - unsigned long flags; - LIST_HEAD(list); + bool all_flushed, posted; - if (!force) { - if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) == - rings->cq_ring_entries)) - return false; - } + if (!force && __io_cqring_events(ctx) == ctx->cq_entries) + return false; - spin_lock_irqsave(&ctx->completion_lock, flags); + posted = false; + spin_lock(&ctx->completion_lock); + while (!list_empty(&ctx->cq_overflow_list)) { + struct io_uring_cqe *cqe = io_get_cqe(ctx); + struct io_overflow_cqe *ocqe; - cqe = NULL; - list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) { - if (!io_match_task(req, tsk, files)) - continue; - - cqe = io_get_cqring(ctx); if (!cqe && !force) break; + ocqe = list_first_entry(&ctx->cq_overflow_list, + struct io_overflow_cqe, list); + if (cqe) + memcpy(cqe, &ocqe->cqe, sizeof(*cqe)); + else + io_account_cq_overflow(ctx); - list_move(&req->compl.list, &list); - if (cqe) { - WRITE_ONCE(cqe->user_data, req->user_data); - WRITE_ONCE(cqe->res, req->result); - WRITE_ONCE(cqe->flags, req->compl.cflags); - } else { - ctx->cached_cq_overflow++; - WRITE_ONCE(ctx->rings->cq_overflow, - ctx->cached_cq_overflow); - } + posted = true; + list_del(&ocqe->list); + kfree(ocqe); } - io_commit_cqring(ctx); - io_cqring_mark_overflow(ctx); - - spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); - - while (!list_empty(&list)) { - req = list_first_entry(&list, struct io_kiocb, compl.list); - list_del(&req->compl.list); - io_put_req(req); + all_flushed = list_empty(&ctx->cq_overflow_list); + if (all_flushed) { + clear_bit(0, &ctx->check_cq_overflow); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW); } - return cqe != NULL; + if (posted) + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (posted) + io_cqring_ev_posted(ctx); + return all_flushed; } -static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, - struct task_struct *tsk, - struct files_struct *files) +static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) { - if (test_bit(0, &ctx->cq_check_overflow)) { + bool ret = true; + + if (test_bit(0, &ctx->check_cq_overflow)) { /* iopoll syncs against uring_lock, not completion_lock */ if (ctx->flags & IORING_SETUP_IOPOLL) mutex_lock(&ctx->uring_lock); - __io_cqring_overflow_flush(ctx, force, tsk, files); + ret = __io_cqring_overflow_flush(ctx, false); if (ctx->flags & IORING_SETUP_IOPOLL) mutex_unlock(&ctx->uring_lock); } + + return ret; } -static void __io_cqring_fill_event(struct io_kiocb *req, long res, - unsigned int cflags) +/* must to be called somewhat shortly after putting a request */ +static inline void io_put_task(struct task_struct *task, int nr) +{ + struct io_uring_task *tctx = task->io_uring; + + if (likely(task == current)) { + tctx->cached_refs += nr; + } else { + percpu_counter_sub(&tctx->inflight, nr); + if (unlikely(atomic_read(&tctx->in_idle))) + wake_up(&tctx->wait); + put_task_struct_many(task, nr); + } +} + +static void io_task_refs_refill(struct io_uring_task *tctx) +{ + unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; + + percpu_counter_add(&tctx->inflight, refill); + refcount_add(refill, ¤t->usage); + tctx->cached_refs += refill; +} + +static inline void io_get_task_refs(int nr) +{ + struct io_uring_task *tctx = current->io_uring; + + tctx->cached_refs -= nr; + if (unlikely(tctx->cached_refs < 0)) + io_task_refs_refill(tctx); +} + +static __cold void io_uring_drop_tctx_refs(struct task_struct *task) +{ + struct io_uring_task *tctx = task->io_uring; + unsigned int refs = tctx->cached_refs; + + if (refs) { + tctx->cached_refs = 0; + percpu_counter_sub(&tctx->inflight, refs); + put_task_struct_many(task, refs); + } +} + +static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags) +{ + struct io_overflow_cqe *ocqe; + + ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT); + if (!ocqe) { + /* + * If we're in ring overflow flush mode, or in task cancel mode, + * or cannot allocate an overflow entry, then we need to drop it + * on the floor. + */ + io_account_cq_overflow(ctx); + return false; + } + if (list_empty(&ctx->cq_overflow_list)) { + set_bit(0, &ctx->check_cq_overflow); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW); + + } + ocqe->cqe.user_data = user_data; + ocqe->cqe.res = res; + ocqe->cqe.flags = cflags; + list_add_tail(&ocqe->list, &ctx->cq_overflow_list); + return true; +} + +static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags) { - struct io_ring_ctx *ctx = req->ctx; struct io_uring_cqe *cqe; - trace_io_uring_complete(ctx, req->user_data, res); + trace_io_uring_complete(ctx, user_data, res, cflags); /* * If we can't get a cq entry, userspace overflowed the * submission (by quite a lot). Increment the overflow count in * the ring. */ - cqe = io_get_cqring(ctx); + cqe = io_get_cqe(ctx); if (likely(cqe)) { - WRITE_ONCE(cqe->user_data, req->user_data); + WRITE_ONCE(cqe->user_data, user_data); WRITE_ONCE(cqe->res, res); WRITE_ONCE(cqe->flags, cflags); - } else if (ctx->cq_overflow_flushed || - atomic_read(&req->task->io_uring->in_idle)) { - /* - * If we're in ring overflow flush mode, or in task cancel mode, - * then we cannot store the request for later flushing, we need - * to drop it on the floor. - */ - ctx->cached_cq_overflow++; - WRITE_ONCE(ctx->rings->cq_overflow, ctx->cached_cq_overflow); - } else { - if (list_empty(&ctx->cq_overflow_list)) { - set_bit(0, &ctx->sq_check_overflow); - set_bit(0, &ctx->cq_check_overflow); - ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; - } - io_clean_op(req); - req->result = res; - req->compl.cflags = cflags; - refcount_inc(&req->refs); - list_add_tail(&req->compl.list, &ctx->cq_overflow_list); + return true; } + return io_cqring_event_overflow(ctx, user_data, res, cflags); } -static void io_cqring_fill_event(struct io_kiocb *req, long res) +static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags) { - __io_cqring_fill_event(req, res, 0); + __io_fill_cqe(req->ctx, req->user_data, res, cflags); } -static void io_cqring_add_event(struct io_kiocb *req, long res, long cflags) +static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, + s32 res, u32 cflags) +{ + ctx->cq_extra++; + return __io_fill_cqe(ctx, user_data, res, cflags); +} + +static void io_req_complete_post(struct io_kiocb *req, s32 res, + u32 cflags) { struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; - spin_lock_irqsave(&ctx->completion_lock, flags); - __io_cqring_fill_event(req, res, cflags); - io_commit_cqring(ctx); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - - io_cqring_ev_posted(ctx); -} - -static void io_submit_flush_completions(struct io_comp_state *cs) -{ - struct io_ring_ctx *ctx = cs->ctx; - - spin_lock_irq(&ctx->completion_lock); - while (!list_empty(&cs->list)) { - struct io_kiocb *req; - - req = list_first_entry(&cs->list, struct io_kiocb, compl.list); - list_del(&req->compl.list); - __io_cqring_fill_event(req, req->result, req->compl.cflags); - - /* - * io_free_req() doesn't care about completion_lock unless one - * of these flags is set. REQ_F_WORK_INITIALIZED is in the list - * because of a potential deadlock with req->work.fs->lock - */ - if (req->flags & (REQ_F_FAIL_LINK|REQ_F_LINK_TIMEOUT - |REQ_F_WORK_INITIALIZED)) { - spin_unlock_irq(&ctx->completion_lock); - io_put_req(req); - spin_lock_irq(&ctx->completion_lock); - } else { - io_put_req(req); + spin_lock(&ctx->completion_lock); + __io_fill_cqe(ctx, req->user_data, res, cflags); + /* + * If we're the last reference to this request, add to our locked + * free_list cache. + */ + if (req_ref_put_and_test(req)) { + if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { + if (req->flags & IO_DISARM_MASK) + io_disarm_next(req); + if (req->link) { + io_req_task_queue(req->link); + req->link = NULL; + } } - } - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); - - io_cqring_ev_posted(ctx); - cs->nr = 0; -} - -static void __io_req_complete(struct io_kiocb *req, long res, unsigned cflags, - struct io_comp_state *cs) -{ - if (!cs) { - io_cqring_add_event(req, res, cflags); - io_put_req(req); + io_dismantle_req(req); + io_put_task(req->task, 1); + list_add(&req->inflight_entry, &ctx->locked_free_list); + ctx->locked_free_nr++; } else { + if (!percpu_ref_tryget(&ctx->refs)) + req = NULL; + } + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + + if (req) { + io_cqring_ev_posted(ctx); + percpu_ref_put(&ctx->refs); + } +} + +static inline bool io_req_needs_clean(struct io_kiocb *req) +{ + return req->flags & IO_REQ_CLEAN_FLAGS; +} + +static inline void io_req_complete_state(struct io_kiocb *req, s32 res, + u32 cflags) +{ + if (io_req_needs_clean(req)) io_clean_op(req); - req->result = res; - req->compl.cflags = cflags; - list_add_tail(&req->compl.list, &cs->list); - if (++cs->nr >= 32) - io_submit_flush_completions(cs); - } + req->result = res; + req->compl.cflags = cflags; + req->flags |= REQ_F_COMPLETE_INLINE; } -static void io_req_complete(struct io_kiocb *req, long res) +static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, + s32 res, u32 cflags) { - __io_req_complete(req, res, 0, NULL); + if (issue_flags & IO_URING_F_COMPLETE_DEFER) + io_req_complete_state(req, res, cflags); + else + io_req_complete_post(req, res, cflags); } -static inline bool io_is_fallback_req(struct io_kiocb *req) +static inline void io_req_complete(struct io_kiocb *req, s32 res) { - return req == (struct io_kiocb *) - ((unsigned long) req->ctx->fallback_req & ~1UL); + __io_req_complete(req, 0, res, 0); } -static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx) +static void io_req_complete_failed(struct io_kiocb *req, s32 res) { - struct io_kiocb *req; - - req = ctx->fallback_req; - if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req)) - return req; - - return NULL; + req_set_fail(req); + io_req_complete_post(req, res, 0); } -static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx, - struct io_submit_state *state) +static void io_req_complete_fail_submit(struct io_kiocb *req) { - if (!state->free_reqs) { - gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; - size_t sz; - int ret; + /* + * We don't submit, fail them all, for that replace hardlinks with + * normal links. Extra REQ_F_LINK is tolerated. + */ + req->flags &= ~REQ_F_HARDLINK; + req->flags |= REQ_F_LINK; + io_req_complete_failed(req, req->result); +} - sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs)); - ret = kmem_cache_alloc_bulk(req_cachep, gfp, sz, state->reqs); +/* + * Don't initialise the fields below on every allocation, but do that in + * advance and keep them valid across allocations. + */ +static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx) +{ + req->ctx = ctx; + req->link = NULL; + req->async_data = NULL; + /* not necessary, but safer to zero */ + req->result = 0; +} - /* - * Bulk alloc is all-or-nothing. If we fail to get a batch, - * retry single alloc to be on the safe side. - */ - if (unlikely(ret <= 0)) { - state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); - if (!state->reqs[0]) - goto fallback; - ret = 1; - } - state->free_reqs = ret; +static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, + struct io_submit_state *state) +{ + spin_lock(&ctx->completion_lock); + list_splice_init(&ctx->locked_free_list, &state->free_list); + ctx->locked_free_nr = 0; + spin_unlock(&ctx->completion_lock); +} + +/* Returns true IFF there are requests in the cache */ +static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) +{ + struct io_submit_state *state = &ctx->submit_state; + int nr; + + /* + * If we have more than a batch's worth of requests in our IRQ side + * locked cache, grab the lock and move them over to our submission + * side cache. + */ + if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH) + io_flush_cached_locked_reqs(ctx, state); + + nr = state->free_reqs; + while (!list_empty(&state->free_list)) { + struct io_kiocb *req = list_first_entry(&state->free_list, + struct io_kiocb, inflight_entry); + + list_del(&req->inflight_entry); + state->reqs[nr++] = req; + if (nr == ARRAY_SIZE(state->reqs)) + break; } + state->free_reqs = nr; + return nr != 0; +} + +/* + * A request might get retired back into the request caches even before opcode + * handlers and io_issue_sqe() are done with it, e.g. inline completion path. + * Because of that, io_alloc_req() should be called only under ->uring_lock + * and with extra caution to not get a request that is still worked on. + */ +static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + struct io_submit_state *state = &ctx->submit_state; + gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; + int ret, i; + + BUILD_BUG_ON(ARRAY_SIZE(state->reqs) < IO_REQ_ALLOC_BATCH); + + if (likely(state->free_reqs || io_flush_cached_reqs(ctx))) + goto got_req; + + ret = kmem_cache_alloc_bulk(req_cachep, gfp, IO_REQ_ALLOC_BATCH, + state->reqs); + + /* + * Bulk alloc is all-or-nothing. If we fail to get a batch, + * retry single alloc to be on the safe side. + */ + if (unlikely(ret <= 0)) { + state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); + if (!state->reqs[0]) + return NULL; + ret = 1; + } + + for (i = 0; i < ret; i++) + io_preinit_req(state->reqs[i], ctx); + state->free_reqs = ret; +got_req: state->free_reqs--; return state->reqs[state->free_reqs]; -fallback: - return io_get_fallback_req(ctx); } -static inline void io_put_file(struct io_kiocb *req, struct file *file, - bool fixed) +static inline void io_put_file(struct file *file) { - if (fixed) - percpu_ref_put(req->fixed_file_refs); - else + if (file) fput(file); } static void io_dismantle_req(struct io_kiocb *req) { - io_clean_op(req); + unsigned int flags = req->flags; - if (req->async_data) + if (io_req_needs_clean(req)) + io_clean_op(req); + if (!(flags & REQ_F_FIXED_FILE)) + io_put_file(req->file); + if (req->fixed_rsrc_refs) + percpu_ref_put(req->fixed_rsrc_refs); + if (req->async_data) { kfree(req->async_data); - if (req->file) - io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); - - io_req_clean_work(req); + req->async_data = NULL; + } } static void __io_free_req(struct io_kiocb *req) { - struct io_uring_task *tctx = req->task->io_uring; struct io_ring_ctx *ctx = req->ctx; io_dismantle_req(req); + io_put_task(req->task, 1); - percpu_counter_dec(&tctx->inflight); - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); - put_task_struct(req->task); + spin_lock(&ctx->completion_lock); + list_add(&req->inflight_entry, &ctx->locked_free_list); + ctx->locked_free_nr++; + spin_unlock(&ctx->completion_lock); - if (likely(!io_is_fallback_req(req))) - kmem_cache_free(req_cachep, req); - else - clear_bit_unlock(0, (unsigned long *) &ctx->fallback_req); percpu_ref_put(&ctx->refs); } -static void io_kill_linked_timeout(struct io_kiocb *req) +static inline void io_remove_next_linked(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *link; - bool cancelled = false; - unsigned long flags; + struct io_kiocb *nxt = req->link; - spin_lock_irqsave(&ctx->completion_lock, flags); - link = list_first_entry_or_null(&req->link_list, struct io_kiocb, - link_list); - /* - * Can happen if a linked timeout fired and link had been like - * req -> link t-out -> link t-out [-> ...] - */ - if (link && (link->flags & REQ_F_LTIMEOUT_ACTIVE)) { + req->link = nxt->link; + nxt->link = NULL; +} + +static bool io_kill_linked_timeout(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) + __must_hold(&req->ctx->timeout_lock) +{ + struct io_kiocb *link = req->link; + + if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { struct io_timeout_data *io = link->async_data; - int ret; - list_del_init(&link->link_list); - ret = hrtimer_try_to_cancel(&io->timer); - if (ret != -1) { - io_cqring_fill_event(link, -ECANCELED); - io_commit_cqring(ctx); - cancelled = true; + io_remove_next_linked(req); + link->timeout.head = NULL; + if (hrtimer_try_to_cancel(&io->timer) != -1) { + list_del(&link->timeout.list); + io_fill_cqe_req(link, -ECANCELED, 0); + io_put_req_deferred(link); + return true; } } - req->flags &= ~REQ_F_LINK_TIMEOUT; - spin_unlock_irqrestore(&ctx->completion_lock, flags); - - if (cancelled) { - io_cqring_ev_posted(ctx); - io_put_req(link); - } + return false; } -static struct io_kiocb *io_req_link_next(struct io_kiocb *req) -{ - struct io_kiocb *nxt; - - /* - * The list should never be empty when we are called here. But could - * potentially happen if the chain is messed up, check to be on the - * safe side. - */ - if (unlikely(list_empty(&req->link_list))) - return NULL; - - nxt = list_first_entry(&req->link_list, struct io_kiocb, link_list); - list_del_init(&req->link_list); - if (!list_empty(&nxt->link_list)) - nxt->flags |= REQ_F_LINK_HEAD; - return nxt; -} - -/* - * Called if REQ_F_LINK_HEAD is set, and we fail the head request - */ static void io_fail_links(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) { - struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; + struct io_kiocb *nxt, *link = req->link; - spin_lock_irqsave(&ctx->completion_lock, flags); - while (!list_empty(&req->link_list)) { - struct io_kiocb *link = list_first_entry(&req->link_list, - struct io_kiocb, link_list); + req->link = NULL; + while (link) { + long res = -ECANCELED; + + if (link->flags & REQ_F_FAIL) + res = link->result; + + nxt = link->link; + link->link = NULL; - list_del_init(&link->link_list); trace_io_uring_fail_link(req, link); - - io_cqring_fill_event(link, -ECANCELED); - - /* - * It's ok to free under spinlock as they're not linked anymore, - * but avoid REQ_F_WORK_INITIALIZED because it may deadlock on - * work.fs->lock. - */ - if (link->flags & REQ_F_WORK_INITIALIZED) - io_put_req_deferred(link, 2); - else - io_double_put_req(link); + io_fill_cqe_req(link, res, 0); + io_put_req_deferred(link); + link = nxt; } +} - io_commit_cqring(ctx); - spin_unlock_irqrestore(&ctx->completion_lock, flags); +static bool io_disarm_next(struct io_kiocb *req) + __must_hold(&req->ctx->completion_lock) +{ + bool posted = false; - io_cqring_ev_posted(ctx); + if (req->flags & REQ_F_ARM_LTIMEOUT) { + struct io_kiocb *link = req->link; + + req->flags &= ~REQ_F_ARM_LTIMEOUT; + if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { + io_remove_next_linked(req); + io_fill_cqe_req(link, -ECANCELED, 0); + io_put_req_deferred(link); + posted = true; + } + } else if (req->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = req->ctx; + + spin_lock_irq(&ctx->timeout_lock); + posted = io_kill_linked_timeout(req); + spin_unlock_irq(&ctx->timeout_lock); + } + if (unlikely((req->flags & REQ_F_FAIL) && + !(req->flags & REQ_F_HARDLINK))) { + posted |= (req->link != NULL); + io_fail_links(req); + } + return posted; } static struct io_kiocb *__io_req_find_next(struct io_kiocb *req) { - req->flags &= ~REQ_F_LINK_HEAD; - if (req->flags & REQ_F_LINK_TIMEOUT) - io_kill_linked_timeout(req); + struct io_kiocb *nxt; /* * If LINK is set, we have dependent requests in this chain. If we @@ -2034,28 +2118,112 @@ static struct io_kiocb *__io_req_find_next(struct io_kiocb *req) * dependencies to the next request. In case of failure, fail the rest * of the chain. */ - if (likely(!(req->flags & REQ_F_FAIL_LINK))) - return io_req_link_next(req); - io_fail_links(req); - return NULL; + if (req->flags & IO_DISARM_MASK) { + struct io_ring_ctx *ctx = req->ctx; + bool posted; + + spin_lock(&ctx->completion_lock); + posted = io_disarm_next(req); + if (posted) + io_commit_cqring(req->ctx); + spin_unlock(&ctx->completion_lock); + if (posted) + io_cqring_ev_posted(ctx); + } + nxt = req->link; + req->link = NULL; + return nxt; } -static struct io_kiocb *io_req_find_next(struct io_kiocb *req) +static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) { - if (likely(!(req->flags & REQ_F_LINK_HEAD))) + if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK)))) return NULL; return __io_req_find_next(req); } -static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok) +static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked) +{ + if (!ctx) + return; + if (*locked) { + if (ctx->submit_state.compl_nr) + io_submit_flush_completions(ctx); + mutex_unlock(&ctx->uring_lock); + *locked = false; + } + percpu_ref_put(&ctx->refs); +} + +static void tctx_task_work(struct callback_head *cb) +{ + bool locked = false; + struct io_ring_ctx *ctx = NULL; + struct io_uring_task *tctx = container_of(cb, struct io_uring_task, + task_work); + + while (1) { + struct io_wq_work_node *node; + + if (!tctx->task_list.first && locked && ctx->submit_state.compl_nr) + io_submit_flush_completions(ctx); + + spin_lock_irq(&tctx->task_lock); + node = tctx->task_list.first; + INIT_WQ_LIST(&tctx->task_list); + if (!node) + tctx->task_running = false; + spin_unlock_irq(&tctx->task_lock); + if (!node) + break; + + do { + struct io_wq_work_node *next = node->next; + struct io_kiocb *req = container_of(node, struct io_kiocb, + io_task_work.node); + + if (req->ctx != ctx) { + ctx_flush_and_put(ctx, &locked); + ctx = req->ctx; + /* if not contended, grab and improve batching */ + locked = mutex_trylock(&ctx->uring_lock); + percpu_ref_get(&ctx->refs); + } + req->io_task_work.func(req, &locked); + node = next; + } while (node); + + cond_resched(); + } + + ctx_flush_and_put(ctx, &locked); + + /* relaxed read is enough as only the task itself sets ->in_idle */ + if (unlikely(atomic_read(&tctx->in_idle))) + io_uring_drop_tctx_refs(current); +} + +static void io_req_task_work_add(struct io_kiocb *req) { struct task_struct *tsk = req->task; - struct io_ring_ctx *ctx = req->ctx; + struct io_uring_task *tctx = tsk->io_uring; enum task_work_notify_mode notify; - int ret; + struct io_wq_work_node *node; + unsigned long flags; + bool running; - if (tsk->flags & PF_EXITING) - return -ESRCH; + WARN_ON_ONCE(!tctx); + + spin_lock_irqsave(&tctx->task_lock, flags); + wq_list_add_tail(&req->io_task_work.node, &tctx->task_list); + running = tctx->task_running; + if (!running) + tctx->task_running = true; + spin_unlock_irqrestore(&tctx->task_lock, flags); + + /* task_work already pending, we're done */ + if (running) + return; /* * SQPOLL kernel thread doesn't need notification, just a wakeup. For @@ -2063,85 +2231,68 @@ static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok) * processing task_work. There's no reliable way to tell if TWA_RESUME * will do the job. */ - notify = TWA_NONE; - if (!(ctx->flags & IORING_SETUP_SQPOLL) && twa_signal_ok) - notify = TWA_SIGNAL; - - ret = task_work_add(tsk, &req->task_work, notify); - if (!ret) + notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL; + if (!task_work_add(tsk, &tctx->task_work, notify)) { wake_up_process(tsk); + return; + } - return ret; + spin_lock_irqsave(&tctx->task_lock, flags); + tctx->task_running = false; + node = tctx->task_list.first; + INIT_WQ_LIST(&tctx->task_list); + spin_unlock_irqrestore(&tctx->task_lock, flags); + + while (node) { + req = container_of(node, struct io_kiocb, io_task_work.node); + node = node->next; + if (llist_add(&req->io_task_work.fallback_node, + &req->ctx->fallback_llist)) + schedule_delayed_work(&req->ctx->fallback_work, 1); + } } -static void __io_req_task_cancel(struct io_kiocb *req, int error) +static void io_req_task_cancel(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; - spin_lock_irq(&ctx->completion_lock); - io_cqring_fill_event(req, error); - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); - - io_cqring_ev_posted(ctx); - req_set_fail_links(req); - io_double_put_req(req); + /* not needed for normal modes, but SQPOLL depends on it */ + io_tw_lock(ctx, locked); + io_req_complete_failed(req, req->result); } -static void io_req_task_cancel(struct callback_head *cb) -{ - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct io_ring_ctx *ctx = req->ctx; - - mutex_lock(&ctx->uring_lock); - __io_req_task_cancel(req, -ECANCELED); - mutex_unlock(&ctx->uring_lock); - percpu_ref_put(&ctx->refs); -} - -static void __io_req_task_submit(struct io_kiocb *req) +static void io_req_task_submit(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; - mutex_lock(&ctx->uring_lock); - if (!ctx->sqo_dead && !__io_sq_thread_acquire_mm(ctx)) - __io_queue_sqe(req, NULL); + io_tw_lock(ctx, locked); + /* req->task == current here, checking PF_EXITING is safe */ + if (likely(!(req->task->flags & PF_EXITING))) + __io_queue_sqe(req); else - __io_req_task_cancel(req, -EFAULT); - mutex_unlock(&ctx->uring_lock); - - if (ctx->flags & IORING_SETUP_SQPOLL) - io_sq_thread_drop_mm(); + io_req_complete_failed(req, -EFAULT); } -static void io_req_task_submit(struct callback_head *cb) +static void io_req_task_queue_fail(struct io_kiocb *req, int ret) { - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct io_ring_ctx *ctx = req->ctx; - - __io_req_task_submit(req); - percpu_ref_put(&ctx->refs); + req->result = ret; + req->io_task_work.func = io_req_task_cancel; + io_req_task_work_add(req); } static void io_req_task_queue(struct io_kiocb *req) { - int ret; - - init_task_work(&req->task_work, io_req_task_submit); - percpu_ref_get(&req->ctx->refs); - - ret = io_req_task_work_add(req, true); - if (unlikely(ret)) { - struct task_struct *tsk; - - init_task_work(&req->task_work, io_req_task_cancel); - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); - } + req->io_task_work.func = io_req_task_submit; + io_req_task_work_add(req); } -static void io_queue_next(struct io_kiocb *req) +static void io_req_task_queue_reissue(struct io_kiocb *req) +{ + req->io_task_work.func = io_queue_async_work; + io_req_task_work_add(req); +} + +static inline void io_queue_next(struct io_kiocb *req) { struct io_kiocb *nxt = io_req_find_next(req); @@ -2155,153 +2306,118 @@ static void io_free_req(struct io_kiocb *req) __io_free_req(req); } -struct req_batch { - void *reqs[IO_IOPOLL_BATCH]; - int to_free; +static void io_free_req_work(struct io_kiocb *req, bool *locked) +{ + io_free_req(req); +} +struct req_batch { struct task_struct *task; int task_refs; + int ctx_refs; }; static inline void io_init_req_batch(struct req_batch *rb) { - rb->to_free = 0; rb->task_refs = 0; + rb->ctx_refs = 0; rb->task = NULL; } -static void __io_req_free_batch_flush(struct io_ring_ctx *ctx, - struct req_batch *rb) -{ - kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs); - percpu_ref_put_many(&ctx->refs, rb->to_free); - rb->to_free = 0; -} - static void io_req_free_batch_finish(struct io_ring_ctx *ctx, struct req_batch *rb) { - if (rb->to_free) - __io_req_free_batch_flush(ctx, rb); - if (rb->task) { - struct io_uring_task *tctx = rb->task->io_uring; - - percpu_counter_sub(&tctx->inflight, rb->task_refs); - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); - put_task_struct_many(rb->task, rb->task_refs); - rb->task = NULL; - } + if (rb->ctx_refs) + percpu_ref_put_many(&ctx->refs, rb->ctx_refs); + if (rb->task) + io_put_task(rb->task, rb->task_refs); } -static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req) +static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req, + struct io_submit_state *state) { - if (unlikely(io_is_fallback_req(req))) { - io_free_req(req); - return; - } - if (req->flags & REQ_F_LINK_HEAD) - io_queue_next(req); + io_queue_next(req); + io_dismantle_req(req); if (req->task != rb->task) { - if (rb->task) { - struct io_uring_task *tctx = rb->task->io_uring; - - percpu_counter_sub(&tctx->inflight, rb->task_refs); - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); - put_task_struct_many(rb->task, rb->task_refs); - } + if (rb->task) + io_put_task(rb->task, rb->task_refs); rb->task = req->task; rb->task_refs = 0; } rb->task_refs++; + rb->ctx_refs++; - io_dismantle_req(req); - rb->reqs[rb->to_free++] = req; - if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs))) - __io_req_free_batch_flush(req->ctx, rb); + if (state->free_reqs != ARRAY_SIZE(state->reqs)) + state->reqs[state->free_reqs++] = req; + else + list_add(&req->inflight_entry, &state->free_list); +} + +static void io_submit_flush_completions(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + struct io_submit_state *state = &ctx->submit_state; + int i, nr = state->compl_nr; + struct req_batch rb; + + spin_lock(&ctx->completion_lock); + for (i = 0; i < nr; i++) { + struct io_kiocb *req = state->compl_reqs[i]; + + __io_fill_cqe(ctx, req->user_data, req->result, + req->compl.cflags); + } + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_cqring_ev_posted(ctx); + + io_init_req_batch(&rb); + for (i = 0; i < nr; i++) { + struct io_kiocb *req = state->compl_reqs[i]; + + if (req_ref_put_and_test(req)) + io_req_free_batch(&rb, req, &ctx->submit_state); + } + + io_req_free_batch_finish(ctx, &rb); + state->compl_nr = 0; } /* * Drop reference to request, return next in chain (if there is one) if this * was the last reference to this request. */ -static struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) +static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) { struct io_kiocb *nxt = NULL; - if (refcount_dec_and_test(&req->refs)) { + if (req_ref_put_and_test(req)) { nxt = io_req_find_next(req); __io_free_req(req); } return nxt; } -static void io_put_req(struct io_kiocb *req) +static inline void io_put_req(struct io_kiocb *req) { - if (refcount_dec_and_test(&req->refs)) + if (req_ref_put_and_test(req)) io_free_req(req); } -static void io_put_req_deferred_cb(struct callback_head *cb) +static inline void io_put_req_deferred(struct io_kiocb *req) { - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - - io_free_req(req); -} - -static void io_free_req_deferred(struct io_kiocb *req) -{ - int ret; - - init_task_work(&req->task_work, io_put_req_deferred_cb); - ret = io_req_task_work_add(req, true); - if (unlikely(ret)) { - struct task_struct *tsk; - - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); + if (req_ref_put_and_test(req)) { + req->io_task_work.func = io_free_req_work; + io_req_task_work_add(req); } } -static inline void io_put_req_deferred(struct io_kiocb *req, int refs) -{ - if (refcount_sub_and_test(refs, &req->refs)) - io_free_req_deferred(req); -} - -static struct io_wq_work *io_steal_work(struct io_kiocb *req) -{ - struct io_kiocb *nxt; - - /* - * A ref is owned by io-wq in which context we're. So, if that's the - * last one, it's safe to steal next work. False negatives are Ok, - * it just will be re-punted async in io_put_work() - */ - if (refcount_read(&req->refs) != 1) - return NULL; - - nxt = io_req_find_next(req); - return nxt ? &nxt->work : NULL; -} - -static void io_double_put_req(struct io_kiocb *req) -{ - /* drop both submit and complete references */ - if (refcount_sub_and_test(2, &req->refs)) - io_free_req(req); -} - static unsigned io_cqring_events(struct io_ring_ctx *ctx) { - struct io_rings *rings = ctx->rings; - /* See comment at the top of this file */ smp_rmb(); - return ctx->cached_cq_tail - READ_ONCE(rings->cq.head); + return __io_cqring_events(ctx); } static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) @@ -2327,38 +2443,23 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) { struct io_buffer *kbuf; + if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) + return 0; kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; return io_put_kbuf(req, kbuf); } static inline bool io_run_task_work(void) { - /* - * Not safe to run on exiting task, and the task_work handling will - * not add work to such a task. - */ - if (unlikely(current->flags & PF_EXITING)) - return false; - if (current->task_works) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); - task_work_run(); + tracehook_notify_signal(); return true; } return false; } -static void io_iopoll_queue(struct list_head *again) -{ - struct io_kiocb *req; - - do { - req = list_first_entry(again, struct io_kiocb, iopoll_entry); - list_del(&req->iopoll_entry); - __io_complete_rw(req, -EAGAIN, 0, NULL); - } while (!list_empty(again)); -} - /* * Find and free completed poll iocbs */ @@ -2367,41 +2468,25 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, { struct req_batch rb; struct io_kiocb *req; - LIST_HEAD(again); /* order with ->result store in io_complete_rw_iopoll() */ smp_rmb(); io_init_req_batch(&rb); while (!list_empty(done)) { - int cflags = 0; + req = list_first_entry(done, struct io_kiocb, inflight_entry); + list_del(&req->inflight_entry); - req = list_first_entry(done, struct io_kiocb, iopoll_entry); - if (READ_ONCE(req->result) == -EAGAIN) { - req->result = 0; - req->iopoll_completed = 0; - list_move_tail(&req->iopoll_entry, &again); - continue; - } - list_del(&req->iopoll_entry); - - if (req->flags & REQ_F_BUFFER_SELECTED) - cflags = io_put_rw_kbuf(req); - - __io_cqring_fill_event(req, req->result, cflags); + io_fill_cqe_req(req, req->result, io_put_rw_kbuf(req)); (*nr_events)++; - if (refcount_dec_and_test(&req->refs)) - io_req_free_batch(&rb, req); + if (req_ref_put_and_test(req)) + io_req_free_batch(&rb, req, &ctx->submit_state); } io_commit_cqring(ctx); - if (ctx->flags & IORING_SETUP_SQPOLL) - io_cqring_ev_posted(ctx); + io_cqring_ev_posted_iopoll(ctx); io_req_free_batch_finish(ctx, &rb); - - if (!list_empty(&again)) - io_iopoll_queue(&again); } static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, @@ -2410,17 +2495,16 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, struct io_kiocb *req, *tmp; LIST_HEAD(done); bool spin; - int ret; /* * Only spin for completions if we don't have multiple devices hanging * off our complete list, and we're under the requested amount. */ - spin = !ctx->poll_multi_file && *nr_events < min; + spin = !ctx->poll_multi_queue && *nr_events < min; - ret = 0; - list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, iopoll_entry) { + list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) { struct kiocb *kiocb = &req->rw.kiocb; + int ret; /* * Move completed and retryable entries to our local lists. @@ -2428,50 +2512,27 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, * and complete those lists first, if we have entries there. */ if (READ_ONCE(req->iopoll_completed)) { - list_move_tail(&req->iopoll_entry, &done); + list_move_tail(&req->inflight_entry, &done); continue; } if (!list_empty(&done)) break; ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin); - if (ret < 0) - break; + if (unlikely(ret < 0)) + return ret; + else if (ret) + spin = false; /* iopoll may have completed current req */ if (READ_ONCE(req->iopoll_completed)) - list_move_tail(&req->iopoll_entry, &done); - - if (ret && spin) - spin = false; - ret = 0; + list_move_tail(&req->inflight_entry, &done); } if (!list_empty(&done)) io_iopoll_complete(ctx, nr_events, &done); - return ret; -} - -/* - * Poll for a minimum of 'min' events. Note that if min == 0 we consider that a - * non-spinning poll check - we'll still enter the driver poll loop, but only - * as a non-spinning completion check. - */ -static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events, - long min) -{ - while (!list_empty(&ctx->iopoll_list) && !need_resched()) { - int ret; - - ret = io_do_iopoll(ctx, nr_events, min); - if (ret < 0) - return ret; - if (*nr_events >= min) - return 0; - } - - return 1; + return 0; } /* @@ -2509,7 +2570,7 @@ static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) static int io_iopoll_check(struct io_ring_ctx *ctx, long min) { unsigned int nr_events = 0; - int iters = 0, ret = 0; + int ret = 0; /* * We disallow the app entering submit/complete with polling, but we @@ -2517,17 +2578,16 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) * that got punted to a workqueue. */ mutex_lock(&ctx->uring_lock); + /* + * Don't enter poll loop if we already have events pending. + * If we do, we can potentially be spinning for commands that + * already triggered a CQE (eg in error). + */ + if (test_bit(0, &ctx->check_cq_overflow)) + __io_cqring_overflow_flush(ctx, false); + if (io_cqring_events(ctx)) + goto out; do { - /* - * Don't enter poll loop if we already have events pending. - * If we do, we can potentially be spinning for commands that - * already triggered a CQE (eg in error). - */ - if (test_bit(0, &ctx->cq_check_overflow)) - __io_cqring_overflow_flush(ctx, false, NULL, NULL); - if (io_cqring_events(ctx)) - break; - /* * If a submit got punted to a workqueue, we can have the * application entering polling for a command before it gets @@ -2538,18 +2598,21 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) * forever, while the workqueue is stuck trying to acquire the * very same mutex. */ - if (!(++iters & 7)) { + if (list_empty(&ctx->iopoll_list)) { + u32 tail = ctx->cached_cq_tail; + mutex_unlock(&ctx->uring_lock); io_run_task_work(); mutex_lock(&ctx->uring_lock); + + /* some requests don't go through iopoll_list */ + if (tail != ctx->cached_cq_tail || + list_empty(&ctx->iopoll_list)) + break; } - - ret = io_iopoll_getevents(ctx, &nr_events, min); - if (ret <= 0) - break; - ret = 0; - } while (min && !nr_events && !need_resched()); - + ret = io_do_iopoll(ctx, &nr_events, min); + } while (!ret && nr_events < min && !need_resched()); +out: mutex_unlock(&ctx->uring_lock); return ret; } @@ -2561,79 +2624,129 @@ static void kiocb_end_write(struct io_kiocb *req) * thread. */ if (req->flags & REQ_F_ISREG) { - struct inode *inode = file_inode(req->file); + struct super_block *sb = file_inode(req->file)->i_sb; - __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); + __sb_writers_acquired(sb, SB_FREEZE_WRITE); + sb_end_write(sb); } - file_end_write(req->file); -} - -static void io_complete_rw_common(struct kiocb *kiocb, long res, - struct io_comp_state *cs) -{ - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - int cflags = 0; - - if (kiocb->ki_flags & IOCB_WRITE) - kiocb_end_write(req); - - if (res != req->result) - req_set_fail_links(req); - if (req->flags & REQ_F_BUFFER_SELECTED) - cflags = io_put_rw_kbuf(req); - __io_req_complete(req, res, cflags, cs); } #ifdef CONFIG_BLOCK -static bool io_resubmit_prep(struct io_kiocb *req, int error) +static bool io_resubmit_prep(struct io_kiocb *req) { - req_set_fail_links(req); - return false; -} -#endif + struct io_async_rw *rw = req->async_data; -static bool io_rw_reissue(struct io_kiocb *req, long res) + if (!rw) + return !io_req_prep_async(req); + iov_iter_restore(&rw->iter, &rw->iter_state); + return true; +} + +static bool io_rw_should_reissue(struct io_kiocb *req) { -#ifdef CONFIG_BLOCK umode_t mode = file_inode(req->file)->i_mode; - int ret; + struct io_ring_ctx *ctx = req->ctx; if (!S_ISBLK(mode) && !S_ISREG(mode)) return false; - if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker()) + if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() && + !(ctx->flags & IORING_SETUP_IOPOLL))) return false; /* * If ref is dying, we might be running poll reap from the exit work. * Don't attempt to reissue from that path, just let it fail with * -EAGAIN. */ - if (percpu_ref_is_dying(&req->ctx->refs)) + if (percpu_ref_is_dying(&ctx->refs)) return false; - - ret = io_sq_thread_acquire_mm(req->ctx, req); - - if (io_resubmit_prep(req, ret)) { - refcount_inc(&req->refs); - io_queue_async_work(req); - return true; - } - + /* + * Play it safe and assume not safe to re-import and reissue if we're + * not in the original thread group (or in task context). + */ + if (!same_thread_group(req->task, current) || !in_task()) + return false; + return true; +} +#else +static bool io_resubmit_prep(struct io_kiocb *req) +{ + return false; +} +static bool io_rw_should_reissue(struct io_kiocb *req) +{ + return false; +} #endif + +static bool __io_complete_rw_common(struct io_kiocb *req, long res) +{ + if (req->rw.kiocb.ki_flags & IOCB_WRITE) { + kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } + if (res != req->result) { + if ((res == -EAGAIN || res == -EOPNOTSUPP) && + io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE; + return true; + } + req_set_fail(req); + req->result = res; + } return false; } -static void __io_complete_rw(struct io_kiocb *req, long res, long res2, - struct io_comp_state *cs) +static inline int io_fixup_rw_res(struct io_kiocb *req, unsigned res) { - if (!io_rw_reissue(req, res)) - io_complete_rw_common(&req->rw.kiocb, res, cs); + struct io_async_rw *io = req->async_data; + + /* add previously done IO, if any */ + if (io && io->bytes_done > 0) { + if (res < 0) + res = io->bytes_done; + else + res += io->bytes_done; + } + return res; +} + +static void io_req_task_complete(struct io_kiocb *req, bool *locked) +{ + unsigned int cflags = io_put_rw_kbuf(req); + int res = req->result; + + if (*locked) { + struct io_ring_ctx *ctx = req->ctx; + struct io_submit_state *state = &ctx->submit_state; + + io_req_complete_state(req, res, cflags); + state->compl_reqs[state->compl_nr++] = req; + if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) + io_submit_flush_completions(ctx); + } else { + io_req_complete_post(req, res, cflags); + } +} + +static void __io_complete_rw(struct io_kiocb *req, long res, long res2, + unsigned int issue_flags) +{ + if (__io_complete_rw_common(req, res)) + return; + __io_req_complete(req, issue_flags, io_fixup_rw_res(req, res), io_put_rw_kbuf(req)); } static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - __io_complete_rw(req, res, res2, NULL); + if (__io_complete_rw_common(req, res)) + return; + req->result = io_fixup_rw_res(req, res); + req->io_task_work.func = io_req_task_complete; + io_req_task_work_add(req); } static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) @@ -2642,12 +2755,15 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); - - if (res != -EAGAIN && res != req->result) - req_set_fail_links(req); + if (unlikely(res != req->result)) { + if (res == -EAGAIN && io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE; + return; + } + } WRITE_ONCE(req->result, res); - /* order with io_poll_complete() checking ->result */ + /* order with io_iopoll_complete() checking ->result */ smp_wmb(); WRITE_ONCE(req->iopoll_completed, 1); } @@ -2655,12 +2771,17 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) /* * After the iocb has been issued, it's safe to be found on the poll list. * Adding the kiocb to the list AFTER submission ensures that we don't - * find it from a io_iopoll_getevents() thread before the issuer is done + * find it from a io_do_iopoll() thread before the issuer is done * accessing the kiocb cookie. */ static void io_iopoll_req_issued(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + const bool in_async = io_wq_current_is_worker(); + + /* workqueue context doesn't hold uring_lock, grab it now */ + if (unlikely(in_async)) + mutex_lock(&ctx->uring_lock); /* * Track whether we have multiple files in our lists. This will impact @@ -2668,14 +2789,22 @@ static void io_iopoll_req_issued(struct io_kiocb *req) * different devices. */ if (list_empty(&ctx->iopoll_list)) { - ctx->poll_multi_file = false; - } else if (!ctx->poll_multi_file) { + ctx->poll_multi_queue = false; + } else if (!ctx->poll_multi_queue) { struct io_kiocb *list_req; + unsigned int queue_num0, queue_num1; list_req = list_first_entry(&ctx->iopoll_list, struct io_kiocb, - iopoll_entry); - if (list_req->file != req->file) - ctx->poll_multi_file = true; + inflight_entry); + + if (list_req->file != req->file) { + ctx->poll_multi_queue = true; + } else { + queue_num0 = blk_qc_t_to_queue_num(list_req->rw.kiocb.ki_cookie); + queue_num1 = blk_qc_t_to_queue_num(req->rw.kiocb.ki_cookie); + if (queue_num0 != queue_num1) + ctx->poll_multi_queue = true; + } } /* @@ -2683,61 +2812,28 @@ static void io_iopoll_req_issued(struct io_kiocb *req) * it to the front so we find it first. */ if (READ_ONCE(req->iopoll_completed)) - list_add(&req->iopoll_entry, &ctx->iopoll_list); + list_add(&req->inflight_entry, &ctx->iopoll_list); else - list_add_tail(&req->iopoll_entry, &ctx->iopoll_list); + list_add_tail(&req->inflight_entry, &ctx->iopoll_list); - if ((ctx->flags & IORING_SETUP_SQPOLL) && - wq_has_sleeper(&ctx->sq_data->wait)) - wake_up(&ctx->sq_data->wait); -} + if (unlikely(in_async)) { + /* + * If IORING_SETUP_SQPOLL is enabled, sqes are either handle + * in sq thread task context or in io worker task context. If + * current task context is sq thread, we don't need to check + * whether should wake up sq thread. + */ + if ((ctx->flags & IORING_SETUP_SQPOLL) && + wq_has_sleeper(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); -static void __io_state_file_put(struct io_submit_state *state) -{ - if (state->has_refs) - fput_many(state->file, state->has_refs); - state->file = NULL; -} - -static inline void io_state_file_put(struct io_submit_state *state) -{ - if (state->file) - __io_state_file_put(state); -} - -/* - * Get as many references to a file as we have IOs left in this submission, - * assuming most submissions are for one file, or at least that each file - * has more than one submission. - */ -static struct file *__io_file_get(struct io_submit_state *state, int fd) -{ - if (!state) - return fget(fd); - - if (state->file) { - if (state->fd == fd) { - state->has_refs--; - return state->file; - } - __io_state_file_put(state); + mutex_unlock(&ctx->uring_lock); } - state->file = fget_many(fd, state->ios_left); - if (!state->file) - return NULL; - - state->fd = fd; - state->has_refs = state->ios_left - 1; - return state->file; } static bool io_bdev_nowait(struct block_device *bdev) { -#ifdef CONFIG_BLOCK return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); -#else - return true; -#endif } /* @@ -2745,19 +2841,21 @@ static bool io_bdev_nowait(struct block_device *bdev) * any file. For now, just ensure that anything potentially problematic is done * inline. */ -static bool io_file_supports_async(struct file *file, int rw) +static bool __io_file_supports_nowait(struct file *file, int rw) { umode_t mode = file_inode(file)->i_mode; if (S_ISBLK(mode)) { - if (io_bdev_nowait(file->f_inode->i_bdev)) + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(I_BDEV(file->f_mapping->host))) return true; return false; } if (S_ISSOCK(mode)) return true; if (S_ISREG(mode)) { - if (io_bdev_nowait(file->f_inode->i_sb->s_bdev) && + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(file->f_inode->i_sb->s_bdev) && file->f_op != &io_uring_fops) return true; return false; @@ -2776,20 +2874,36 @@ static bool io_file_supports_async(struct file *file, int rw) return file->f_op->write_iter != NULL; } -static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static bool io_file_supports_nowait(struct io_kiocb *req, int rw) +{ + if (rw == READ && (req->flags & REQ_F_NOWAIT_READ)) + return true; + else if (rw == WRITE && (req->flags & REQ_F_NOWAIT_WRITE)) + return true; + + return __io_file_supports_nowait(req->file, rw); +} + +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, + int rw) { struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; + struct file *file = req->file; unsigned ioprio; int ret; - if (S_ISREG(file_inode(req->file)->i_mode)) + if (!io_req_ffs_set(req) && S_ISREG(file_inode(file)->i_mode)) req->flags |= REQ_F_ISREG; kiocb->ki_pos = READ_ONCE(sqe->off); - if (kiocb->ki_pos == -1 && !(req->file->f_mode & FMODE_STREAM)) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; + if (kiocb->ki_pos == -1) { + if (!(file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = file->f_pos; + } else { + kiocb->ki_pos = 0; + } } kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); @@ -2797,6 +2911,15 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(ret)) return ret; + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw))) + req->flags |= REQ_F_NOWAIT; + ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { ret = ioprio_check_cap(ioprio); @@ -2807,10 +2930,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) } else kiocb->ki_ioprio = get_current_ioprio(); - /* don't allow async punt if RWF_NOWAIT was requested */ - if (kiocb->ki_flags & IOCB_NOWAIT) - req->flags |= REQ_F_NOWAIT; - if (ctx->flags & IORING_SETUP_IOPOLL) { if (!(kiocb->ki_flags & IOCB_DIRECT) || !kiocb->ki_filp->f_op->iopoll) @@ -2825,9 +2944,24 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) kiocb->ki_complete = io_complete_rw; } + /* used for fixed read/write too - just read unconditionally */ + req->buf_index = READ_ONCE(sqe->buf_index); + req->imu = NULL; + + if (req->opcode == IORING_OP_READ_FIXED || + req->opcode == IORING_OP_WRITE_FIXED) { + struct io_ring_ctx *ctx = req->ctx; + u16 index; + + if (unlikely(req->buf_index >= ctx->nr_user_bufs)) + return -EFAULT; + index = array_index_nospec(req->buf_index, ctx->nr_user_bufs); + req->imu = ctx->user_bufs[index]; + io_req_set_rsrc_node(req); + } + req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); - req->buf_index = READ_ONCE(sqe->buf_index); return 0; } @@ -2853,48 +2987,49 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } static void kiocb_done(struct kiocb *kiocb, ssize_t ret, - struct io_comp_state *cs) + unsigned int issue_flags) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); - struct io_async_rw *io = req->async_data; - - /* add previously done IO, if any */ - if (io && io->bytes_done > 0) { - if (ret < 0) - ret = io->bytes_done; - else - ret += io->bytes_done; - } if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; - if (ret >= 0 && kiocb->ki_complete == io_complete_rw) - __io_complete_rw(req, ret, 0, cs); + if (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) + __io_complete_rw(req, ret, 0, issue_flags); else io_rw_done(kiocb, ret); + + if (req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + if (io_resubmit_prep(req)) { + io_req_task_queue_reissue(req); + } else { + unsigned int cflags = io_put_rw_kbuf(req); + struct io_ring_ctx *ctx = req->ctx; + + ret = io_fixup_rw_res(req, ret); + req_set_fail(req); + if (!(issue_flags & IO_URING_F_NONBLOCK)) { + mutex_lock(&ctx->uring_lock); + __io_req_complete(req, issue_flags, ret, cflags); + mutex_unlock(&ctx->uring_lock); + } else { + __io_req_complete(req, issue_flags, ret, cflags); + } + } + } } -static ssize_t io_import_fixed(struct io_kiocb *req, int rw, - struct iov_iter *iter) +static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, + struct io_mapped_ubuf *imu) { - struct io_ring_ctx *ctx = req->ctx; size_t len = req->rw.len; - struct io_mapped_ubuf *imu; - u16 index, buf_index = req->buf_index; + u64 buf_end, buf_addr = req->rw.addr; size_t offset; - u64 buf_addr; - if (unlikely(buf_index >= ctx->nr_user_bufs)) - return -EFAULT; - index = array_index_nospec(buf_index, ctx->nr_user_bufs); - imu = &ctx->user_bufs[index]; - buf_addr = req->rw.addr; - - /* overflow */ - if (buf_addr + len < buf_addr) + if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end))) return -EFAULT; /* not inside the mapped region */ - if (buf_addr < imu->ubuf || buf_addr + len > imu->ubuf + imu->len) + if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end)) return -EFAULT; /* @@ -2939,7 +3074,14 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw, } } - return len; + return 0; +} + +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) +{ + if (WARN_ON_ONCE(!req->imu)) + return -EFAULT; + return __io_import_fixed(req, rw, iter, req->imu); } static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock) @@ -3080,16 +3222,14 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, return __io_iov_buffer_select(req, iov, needs_lock); } -static ssize_t __io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock) +static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, + struct iov_iter *iter, bool needs_lock) { void __user *buf = u64_to_user_ptr(req->rw.addr); size_t sqe_len = req->rw.len; + u8 opcode = req->opcode; ssize_t ret; - u8 opcode; - opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; return io_import_fixed(req, rw, iter); @@ -3114,10 +3254,8 @@ static ssize_t __io_import_iovec(int rw, struct io_kiocb *req, if (req->flags & REQ_F_BUFFER_SELECT) { ret = io_iov_buffer_select(req, *iovec, needs_lock); - if (!ret) { - ret = (*iovec)->iov_len; - iov_iter_init(iter, rw, *iovec, 1, ret); - } + if (!ret) + iov_iter_init(iter, rw, *iovec, 1, (*iovec)->iov_len); *iovec = NULL; return ret; } @@ -3126,18 +3264,6 @@ static ssize_t __io_import_iovec(int rw, struct io_kiocb *req, req->ctx->compat); } -static ssize_t io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock) -{ - struct io_async_rw *iorw = req->async_data; - - if (!iorw) - return __io_import_iovec(rw, req, iovec, iter, needs_lock); - *iovec = NULL; - return 0; -} - static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb) { return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos; @@ -3230,32 +3356,31 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, } } -static inline int __io_alloc_async_data(struct io_kiocb *req) +static inline int io_alloc_async_data(struct io_kiocb *req) { WARN_ON_ONCE(!io_op_defs[req->opcode].async_size); req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL); return req->async_data == NULL; } -static int io_alloc_async_data(struct io_kiocb *req) -{ - if (!io_op_defs[req->opcode].needs_async_data) - return 0; - - return __io_alloc_async_data(req); -} - static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, const struct iovec *fast_iov, struct iov_iter *iter, bool force) { - if (!force && !io_op_defs[req->opcode].needs_async_data) + if (!force && !io_op_defs[req->opcode].needs_async_setup) return 0; if (!req->async_data) { - if (__io_alloc_async_data(req)) + struct io_async_rw *iorw; + + if (io_alloc_async_data(req)) { + kfree(iovec); return -ENOMEM; + } io_req_map_rw(req, iovec, fast_iov, iter); + iorw = req->async_data; + /* we've copied and mapped the iter, ensure state is saved */ + iov_iter_save_state(&iorw->iter, &iorw->iter_state); } return 0; } @@ -3264,9 +3389,9 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) { struct io_async_rw *iorw = req->async_data; struct iovec *iov = iorw->fast_iov; - ssize_t ret; + int ret; - ret = __io_import_iovec(rw, req, &iov, &iorw->iter, false); + ret = io_import_iovec(rw, req, &iov, &iorw->iter, false); if (unlikely(ret < 0)) return ret; @@ -3274,24 +3399,15 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) iorw->free_iovec = iov; if (iov) req->flags |= REQ_F_NEED_CLEANUP; + iov_iter_save_state(&iorw->iter, &iorw->iter_state); return 0; } static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - ssize_t ret; - - ret = io_prep_rw(req, sqe); - if (ret) - return ret; - if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; - - /* either don't need iovec imported or already have it */ - if (!req->async_data) - return 0; - return io_rw_prep_async(req, READ); + return io_prep_rw(req, sqe, READ); } /* @@ -3310,7 +3426,6 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, struct wait_page_queue *wpq; struct io_kiocb *req = wait->private; struct wait_page_key *key = arg; - int ret; wpq = container_of(wait, struct wait_page_queue, wait); @@ -3319,22 +3434,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, req->rw.kiocb.ki_flags &= ~IOCB_WAITQ; list_del_init(&wait->entry); - - init_task_work(&req->task_work, io_req_task_submit); - percpu_ref_get(&req->ctx->refs); - - /* submit ref gets dropped, acquire a new one */ - refcount_inc(&req->refs); - ret = io_req_task_work_add(req, true); - if (unlikely(ret)) { - struct task_struct *tsk; - - /* queue just for cancelation */ - init_task_work(&req->task_work, io_req_task_cancel); - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); - } + io_req_task_queue(req); return 1; } @@ -3381,7 +3481,7 @@ static bool io_rw_should_retry(struct io_kiocb *req) return true; } -static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) +static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) { if (req->file->f_op->read_iter) return call_read_iter(req->file, &req->rw.kiocb, iter); @@ -3391,27 +3491,40 @@ static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) return -EINVAL; } -static int io_read(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static bool need_read_all(struct io_kiocb *req) +{ + return req->flags & REQ_F_ISREG || + S_ISBLK(file_inode(req->file)->i_mode); +} + +static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; - struct iov_iter iter_cp; struct io_async_rw *rw = req->async_data; - ssize_t io_size, ret, ret2; - bool no_async; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; - if (rw) + if (rw) { iter = &rw->iter; - - ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); - if (ret < 0) - return ret; - iter_cp = *iter; - io_size = iov_iter_count(iter); - req->result = io_size; - ret = 0; + state = &rw->iter_state; + /* + * We come here from an earlier attempt, restore our state to + * match in case it doesn't. It's cheap enough that we don't + * need to make this conditional. + */ + iov_iter_restore(iter, state); + iovec = NULL; + } else { + ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); + if (ret < 0) + return ret; + state = &__state; + iov_iter_save_state(iter, state); + } + req->result = iov_iter_count(iter); /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3419,127 +3532,130 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, else kiocb->ki_flags |= IOCB_NOWAIT; - /* If the file doesn't support async, just async punt */ - no_async = force_nonblock && !io_file_supports_async(req->file, READ); - if (no_async) - goto copy_iov; + if (force_nonblock && !io_file_supports_nowait(req, READ)) { + ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true); + return ret ?: -EAGAIN; + } - ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), io_size); - if (unlikely(ret)) - goto out_free; + ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } ret = io_iter_do_read(req, iter); - if (!ret) { - goto done; - } else if (ret == -EIOCBQUEUED) { - ret = 0; - goto out_free; - } else if (ret == -EAGAIN) { + if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { + req->flags &= ~REQ_F_REISSUE; /* IOPOLL retry should happen for io-wq threads */ if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) goto done; - /* no retry on NONBLOCK marked file */ - if (req->file->f_flags & O_NONBLOCK) + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (req->flags & REQ_F_NOWAIT) goto done; - /* some cases will consume bytes even on error returns */ - *iter = iter_cp; ret = 0; - goto copy_iov; - } else if (ret < 0) { - /* make sure -ERESTARTSYS -> -EINTR is done */ - goto done; - } - - /* read it all, or we did blocking attempt. no retry. */ - if (!iov_iter_count(iter) || !force_nonblock || - (req->file->f_flags & O_NONBLOCK) || !(req->flags & REQ_F_ISREG)) - goto done; - - io_size -= ret; -copy_iov: - ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); - if (ret2) { - ret = ret2; + } else if (ret == -EIOCBQUEUED) { goto out_free; - } - if (no_async) - return -EAGAIN; - rw = req->async_data; - /* it's copied and will be cleaned with ->io */ - iovec = NULL; - /* now use our persistent iterator, if we aren't already */ - iter = &rw->iter; -retry: - rw->bytes_done += ret; - /* if we can retry, do so with the callbacks armed */ - if (!io_rw_should_retry(req)) { - kiocb->ki_flags &= ~IOCB_WAITQ; - return -EAGAIN; + } else if (ret <= 0 || ret == req->result || !force_nonblock || + (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { + /* read all, failed, already did sync or don't want to retry */ + goto done; } /* - * Now retry read with the IOCB_WAITQ parts set in the iocb. If we - * get -EIOCBQUEUED, then we'll get a notification when the desired - * page gets unlocked. We can also get a partial read here, and if we - * do, then just retry at the new offset. + * Don't depend on the iter state matching what was consumed, or being + * untouched in case of error. Restore it and we'll advance it + * manually if we need to. */ - ret = io_iter_do_read(req, iter); - if (ret == -EIOCBQUEUED) { - ret = 0; - goto out_free; - } else if (ret > 0 && ret < io_size) { + iov_iter_restore(iter, state); + + ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); + if (ret2) + return ret2; + + iovec = NULL; + rw = req->async_data; + /* + * Now use our persistent iterator and state, if we aren't already. + * We've restored and mapped the iter to match. + */ + if (iter != &rw->iter) { + iter = &rw->iter; + state = &rw->iter_state; + } + + do { + /* + * We end up here because of a partial read, either from + * above or inside this loop. Advance the iter by the bytes + * that were consumed. + */ + iov_iter_advance(iter, ret); + if (!iov_iter_count(iter)) + break; + rw->bytes_done += ret; + iov_iter_save_state(iter, state); + + /* if we can retry, do so with the callbacks armed */ + if (!io_rw_should_retry(req)) { + kiocb->ki_flags &= ~IOCB_WAITQ; + return -EAGAIN; + } + + req->result = iov_iter_count(iter); + /* + * Now retry read with the IOCB_WAITQ parts set in the iocb. If + * we get -EIOCBQUEUED, then we'll get a notification when the + * desired page gets unlocked. We can also get a partial read + * here, and if we do, then just retry at the new offset. + */ + ret = io_iter_do_read(req, iter); + if (ret == -EIOCBQUEUED) + return 0; /* we got some bytes, but not all. retry. */ kiocb->ki_flags &= ~IOCB_WAITQ; - goto retry; - } + iov_iter_restore(iter, state); + } while (ret > 0); done: - kiocb_done(kiocb, ret, cs); - ret = 0; + kiocb_done(kiocb, ret, issue_flags); out_free: - /* it's reportedly faster than delegating the null check to kfree() */ + /* it's faster to check here then delegate to kfree */ if (iovec) kfree(iovec); - return ret; + return 0; } static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - ssize_t ret; - - ret = io_prep_rw(req, sqe); - if (ret) - return ret; - if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - - /* either don't need iovec imported or already have it */ - if (!req->async_data) - return 0; - return io_rw_prep_async(req, WRITE); + return io_prep_rw(req, sqe, WRITE); } -static int io_write(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; - struct iov_iter iter_cp; struct io_async_rw *rw = req->async_data; - ssize_t ret, ret2, io_size; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; - if (rw) + if (rw) { iter = &rw->iter; - - ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); - if (ret < 0) - return ret; - iter_cp = *iter; - io_size = iov_iter_count(iter); - req->result = io_size; + state = &rw->iter_state; + iov_iter_restore(iter, state); + iovec = NULL; + } else { + ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); + if (ret < 0) + return ret; + state = &__state; + iov_iter_save_state(iter, state); + } + req->result = iov_iter_count(iter); /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3548,7 +3664,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, kiocb->ki_flags |= IOCB_NOWAIT; /* If the file doesn't support async, just async punt */ - if (force_nonblock && !io_file_supports_async(req->file, WRITE)) + if (force_nonblock && !io_file_supports_nowait(req, WRITE)) goto copy_iov; /* file path doesn't support NOWAIT for non-direct_IO */ @@ -3556,7 +3672,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, (req->flags & REQ_F_ISREG)) goto copy_iov; - ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), io_size); + ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) goto out_free; @@ -3581,28 +3697,36 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, else ret2 = -EINVAL; + if (req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + ret2 = -EAGAIN; + } + /* * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just * retry them without IOCB_NOWAIT. */ if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT)) ret2 = -EAGAIN; - /* no retry on NONBLOCK marked file */ - if (ret2 == -EAGAIN && (req->file->f_flags & O_NONBLOCK)) + /* no retry on NONBLOCK nor RWF_NOWAIT */ + if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT)) goto done; if (!force_nonblock || ret2 != -EAGAIN) { /* IOPOLL retry should happen for io-wq threads */ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) goto copy_iov; done: - kiocb_done(kiocb, ret2, cs); + kiocb_done(kiocb, ret2, issue_flags); } else { copy_iov: - /* some cases will consume bytes even on error returns */ - *iter = iter_cp; + iov_iter_restore(iter, state); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); - if (!ret) + if (!ret) { + if (kiocb->ki_flags & IOCB_WRITE) + kiocb_end_write(req); return -EAGAIN; + } + return ret; } out_free: /* it's reportedly faster than delegating the null check to kfree() */ @@ -3611,37 +3735,160 @@ out_free: return ret; } +static int io_renameat_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_rename *ren = &req->rename; + const char __user *oldf, *newf; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ren->old_dfd = READ_ONCE(sqe->fd); + oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); + newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ren->new_dfd = READ_ONCE(sqe->len); + ren->flags = READ_ONCE(sqe->rename_flags); + + ren->oldpath = getname(oldf); + if (IS_ERR(ren->oldpath)) + return PTR_ERR(ren->oldpath); + + ren->newpath = getname(newf); + if (IS_ERR(ren->newpath)) { + putname(ren->oldpath); + return PTR_ERR(ren->newpath); + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_rename *ren = &req->rename; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd, + ren->newpath, ren->flags); + + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +static int io_unlinkat_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_unlink *un = &req->unlink; + const char __user *fname; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || + sqe->splice_fd_in) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + un->dfd = READ_ONCE(sqe->fd); + + un->flags = READ_ONCE(sqe->unlink_flags); + if (un->flags & ~AT_REMOVEDIR) + return -EINVAL; + + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + un->filename = getname(fname); + if (IS_ERR(un->filename)) + return PTR_ERR(un->filename); + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_unlink *un = &req->unlink; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + if (un->flags & AT_REMOVEDIR) + ret = do_rmdir(un->dfd, un->filename); + else + ret = do_unlinkat(un->dfd, un->filename); + + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +} + +static int io_shutdown_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_NET) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->ioprio || sqe->off || sqe->addr || sqe->rw_flags || + sqe->buf_index || sqe->splice_fd_in)) + return -EINVAL; + + req->shutdown.how = READ_ONCE(sqe->len); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) +{ +#if defined(CONFIG_NET) + struct socket *sock; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + sock = sock_from_file(req->file, &ret); + if (unlikely(!sock)) + return ret; + + ret = __sys_shutdown_sock(sock, req->shutdown.how); + if (ret < 0) + req_set_fail(req); + io_req_complete(req, ret); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + static int __io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_splice* sp = &req->splice; + struct io_splice *sp = &req->splice; unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - sp->file_in = NULL; sp->len = READ_ONCE(sqe->len); sp->flags = READ_ONCE(sqe->splice_flags); - if (unlikely(sp->flags & ~valid_flags)) return -EINVAL; - - sp->file_in = io_file_get(NULL, req, READ_ONCE(sqe->splice_fd_in), - (sp->flags & SPLICE_F_FD_IN_FIXED)); - if (!sp->file_in) - return -EBADF; - req->flags |= REQ_F_NEED_CLEANUP; - - if (!S_ISREG(file_inode(sp->file_in)->i_mode)) { - /* - * Splice operation will be punted aync, and here need to - * modify io_wq_work.flags, so initialize io_wq_work firstly. - */ - io_req_init_async(req); - req->work.flags |= IO_WQ_WORK_UNBOUND; - } - + sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); return 0; } @@ -3653,60 +3900,75 @@ static int io_tee_prep(struct io_kiocb *req, return __io_splice_prep(req, sqe); } -static int io_tee(struct io_kiocb *req, bool force_nonblock) +static int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + struct file *in; long ret = 0; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + + in = io_file_get(req->ctx, req, sp->splice_fd_in, + (sp->flags & SPLICE_F_FD_IN_FIXED)); + if (!in) { + ret = -EBADF; + goto done; + } + if (sp->len) ret = do_tee(in, out, sp->len, flags); - io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED)); - req->flags &= ~REQ_F_NEED_CLEANUP; - + if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) + io_put_file(in); +done: if (ret != sp->len) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_splice* sp = &req->splice; + struct io_splice *sp = &req->splice; sp->off_in = READ_ONCE(sqe->splice_off_in); sp->off_out = READ_ONCE(sqe->off); return __io_splice_prep(req, sqe); } -static int io_splice(struct io_kiocb *req, bool force_nonblock) +static int io_splice(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; + struct file *in; long ret = 0; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + in = io_file_get(req->ctx, req, sp->splice_fd_in, + (sp->flags & SPLICE_F_FD_IN_FIXED)); + if (!in) { + ret = -EBADF; + goto done; + } + poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; if (sp->len) ret = do_splice(in, poff_in, out, poff_out, sp->len, flags); - io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED)); - req->flags &= ~REQ_F_NEED_CLEANUP; - + if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) + io_put_file(in); +done: if (ret != sp->len) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -3714,24 +3976,21 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock) /* * IORING_OP_NOP just posts a completion event, nothing else. */ -static int io_nop(struct io_kiocb *req, struct io_comp_state *cs) +static int io_nop(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - __io_req_complete(req, 0, 0, cs); + __io_req_complete(req, issue_flags, 0, 0); return 0; } -static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - if (!req->file) - return -EBADF; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || @@ -3747,20 +4006,20 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_fsync(struct io_kiocb *req, bool force_nonblock) +static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) { loff_t end = req->sync.off + req->sync.len; int ret; /* fsync always requires a blocking context */ - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = vfs_fsync_range(req->file, req->sync.off, end > 0 ? end : LLONG_MAX, req->sync.flags & IORING_FSYNC_DATASYNC); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -3780,17 +4039,19 @@ static int io_fallocate_prep(struct io_kiocb *req, return 0; } -static int io_fallocate(struct io_kiocb *req, bool force_nonblock) +static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) { int ret; /* fallocate always requiring blocking context */ - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, req->sync.len); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); + else + fsnotify_modify(req->file); io_req_complete(req, ret); return 0; } @@ -3800,7 +4061,9 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe const char __user *fname; int ret; - if (unlikely(sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->ioprio || sqe->buf_index)) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -3817,20 +4080,21 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe req->open.filename = NULL; return ret; } + + req->open.file_slot = READ_ONCE(sqe->file_index); + if (req->open.file_slot && (req->open.how.flags & O_CLOEXEC)) + return -EINVAL; + req->open.nofile = rlimit(RLIMIT_NOFILE); - req->open.ignore_nonblock = false; req->flags |= REQ_F_NEED_CLEANUP; return 0; } static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - u64 flags, mode; + u64 mode = READ_ONCE(sqe->len); + u64 flags = READ_ONCE(sqe->open_flags); - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) - return -EINVAL; - mode = READ_ONCE(sqe->len); - flags = READ_ONCE(sqe->open_flags); req->open.how = build_open_how(flags, mode); return __io_openat_prep(req, sqe); } @@ -3841,8 +4105,6 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) size_t len; int ret; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) - return -EINVAL; how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); len = READ_ONCE(sqe->len); if (len < OPEN_HOW_SIZE_VER0) @@ -3856,58 +4118,75 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return __io_openat_prep(req, sqe); } -static int io_openat2(struct io_kiocb *req, bool force_nonblock) +static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) { struct open_flags op; struct file *file; + bool resolve_nonblock, nonblock_set; + bool fixed = !!req->open.file_slot; int ret; - if (force_nonblock && !req->open.ignore_nonblock) - return -EAGAIN; - ret = build_open_flags(&req->open.how, &op); if (ret) goto err; + nonblock_set = op.open_flag & O_NONBLOCK; + resolve_nonblock = req->open.how.resolve & RESOLVE_CACHED; + if (issue_flags & IO_URING_F_NONBLOCK) { + /* + * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, + * it'll always -EAGAIN + */ + if (req->open.how.flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + op.lookup_flags |= LOOKUP_CACHED; + op.open_flag |= O_NONBLOCK; + } - ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile); - if (ret < 0) - goto err; + if (!fixed) { + ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile); + if (ret < 0) + goto err; + } file = do_filp_open(req->open.dfd, req->open.filename, &op); if (IS_ERR(file)) { - put_unused_fd(ret); - ret = PTR_ERR(file); /* - * A work-around to ensure that /proc/self works that way - * that it should - if we get -EOPNOTSUPP back, then assume - * that proc_self_get_link() failed us because we're in async - * context. We should be safe to retry this from the task - * itself with force_nonblock == false set, as it should not - * block on lookup. Would be nice to know this upfront and - * avoid the async dance, but doesn't seem feasible. + * We could hang on to this 'fd' on retrying, but seems like + * marginal gain for something that is now known to be a slower + * path. So just put it, and we'll get a new one when we retry. */ - if (ret == -EOPNOTSUPP && io_wq_current_is_worker()) { - req->open.ignore_nonblock = true; - refcount_inc(&req->refs); - io_req_task_queue(req); - return 0; - } - } else { - fsnotify_open(file); - fd_install(ret, file); + if (!fixed) + put_unused_fd(ret); + + ret = PTR_ERR(file); + /* only retry if RESOLVE_CACHED wasn't already set by application */ + if (ret == -EAGAIN && + (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK))) + return -EAGAIN; + goto err; } + + if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) + file->f_flags &= ~O_NONBLOCK; + fsnotify_open(file); + + if (!fixed) + fd_install(ret, file); + else + ret = io_install_fixed_file(req, file, issue_flags, + req->open.file_slot - 1); err: putname(req->open.filename); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) - req_set_fail_links(req); - io_req_complete(req, ret); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } -static int io_openat(struct io_kiocb *req, bool force_nonblock) +static int io_openat(struct io_kiocb *req, unsigned int issue_flags) { - return io_openat2(req, force_nonblock); + return io_openat2(req, issue_flags); } static int io_remove_buffers_prep(struct io_kiocb *req, @@ -3948,6 +4227,7 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf, kfree(nxt); if (++i == nbufs) return i; + cond_resched(); } i++; kfree(buf); @@ -3956,13 +4236,13 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf, return i; } -static int io_remove_buffers(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head; int ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; io_ring_submit_lock(ctx, !force_nonblock); @@ -3973,16 +4253,11 @@ static int io_remove_buffers(struct io_kiocb *req, bool force_nonblock, if (head) ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); - /* need to hold the lock to complete IOPOLL requests */ - if (ctx->flags & IORING_SETUP_IOPOLL) { - __io_req_complete(req, ret, 0, cs); - io_ring_submit_unlock(ctx, !force_nonblock); - } else { - io_ring_submit_unlock(ctx, !force_nonblock); - __io_req_complete(req, ret, 0, cs); - } + /* complete before unlock, IOPOLL may need the lock */ + __io_req_complete(req, issue_flags, ret, 0); + io_ring_submit_unlock(ctx, !force_nonblock); return 0; } @@ -4049,13 +4324,13 @@ static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head) return i ? i : -ENOMEM; } -static int io_provide_buffers(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head, *list; int ret = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; io_ring_submit_lock(ctx, !force_nonblock); @@ -4065,21 +4340,16 @@ static int io_provide_buffers(struct io_kiocb *req, bool force_nonblock, ret = io_add_buffers(p, &head); if (ret >= 0 && !list) { - ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL); + ret = xa_insert(&ctx->io_buffers, p->bgid, head, + GFP_KERNEL_ACCOUNT); if (ret < 0) __io_remove_buffers(ctx, head, p->bgid, -1U); } if (ret < 0) - req_set_fail_links(req); - - /* need to hold the lock to complete IOPOLL requests */ - if (ctx->flags & IORING_SETUP_IOPOLL) { - __io_req_complete(req, ret, 0, cs); - io_ring_submit_unlock(ctx, !force_nonblock); - } else { - io_ring_submit_unlock(ctx, !force_nonblock); - __io_req_complete(req, ret, 0, cs); - } + req_set_fail(req); + /* complete before unlock, IOPOLL may need the lock */ + __io_req_complete(req, issue_flags, ret, 0); + io_ring_submit_unlock(ctx, !force_nonblock); return 0; } @@ -4089,7 +4359,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #if defined(CONFIG_EPOLL) if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); @@ -4110,20 +4380,20 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #endif } -static int io_epoll_ctl(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_EPOLL) struct io_epoll *ie = &req->epoll; int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock); if (force_nonblock && ret == -EAGAIN) return -EAGAIN; if (ret < 0) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; #else return -EOPNOTSUPP; @@ -4147,18 +4417,18 @@ static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) #endif } -static int io_madvise(struct io_kiocb *req, bool force_nonblock) +static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) struct io_madvise *ma = &req->madvise; int ret; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; #else @@ -4179,12 +4449,12 @@ static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_fadvise(struct io_kiocb *req, bool force_nonblock) +static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) { struct io_fadvise *fa = &req->fadvise; int ret; - if (force_nonblock) { + if (issue_flags & IO_URING_F_NONBLOCK) { switch (fa->advice) { case POSIX_FADV_NORMAL: case POSIX_FADV_RANDOM: @@ -4197,14 +4467,14 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock) ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice); if (ret < 0) - req_set_fail_links(req); - io_req_complete(req, ret); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; @@ -4220,89 +4490,96 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_statx(struct io_kiocb *req, bool force_nonblock) +static int io_statx(struct io_kiocb *req, unsigned int issue_flags) { struct io_statx *ctx = &req->statx; int ret; - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask, ctx->buffer); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - /* - * If we queue this for async, it must not be cancellable. That would - * leave the 'file' in an undeterminate state, and here need to modify - * io_wq_work.flags, so initialize io_wq_work firstly. - */ - io_req_init_async(req); - - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || - sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + sqe->rw_flags || sqe->buf_index) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; req->close.fd = READ_ONCE(sqe->fd); - if ((req->file && req->file->f_op == &io_uring_fops)) - return -EBADF; + req->close.file_slot = READ_ONCE(sqe->file_index); + if (req->close.file_slot && req->close.fd) + return -EINVAL; - req->close.put_file = NULL; return 0; } -static int io_close(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_close(struct io_kiocb *req, unsigned int issue_flags) { + struct files_struct *files = current->files; struct io_close *close = &req->close; - int ret; + struct fdtable *fdt; + struct file *file = NULL; + int ret = -EBADF; - /* might be already done during nonblock submission */ - if (!close->put_file) { - ret = close_fd_get_file(close->fd, &close->put_file); - if (ret < 0) - return (ret == -ENOENT) ? -EBADF : ret; + if (req->close.file_slot) { + ret = io_close_fixed(req, issue_flags); + goto err; + } + + spin_lock(&files->file_lock); + fdt = files_fdtable(files); + if (close->fd >= fdt->max_fds) { + spin_unlock(&files->file_lock); + goto err; + } + file = fdt->fd[close->fd]; + if (!file || file->f_op == &io_uring_fops) { + spin_unlock(&files->file_lock); + file = NULL; + goto err; } /* if the file has a flush method, be safe and punt to async */ - if (close->put_file->f_op->flush && force_nonblock) { - /* not safe to cancel at this point */ - req->work.flags |= IO_WQ_WORK_NO_CANCEL; - /* was never set, but play safe */ - req->flags &= ~REQ_F_NOWAIT; - /* avoid grabbing files - we don't need the files */ - req->flags |= REQ_F_NO_FILE_TABLE; + if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) { + spin_unlock(&files->file_lock); return -EAGAIN; } + ret = __close_fd_get_file(close->fd, &file); + spin_unlock(&files->file_lock); + if (ret < 0) { + if (ret == -ENOENT) + ret = -EBADF; + goto err; + } + /* No ->flush() or already async, safely close from here */ - ret = filp_close(close->put_file, req->work.identity->files); + ret = filp_close(file, current->files); +err: if (ret < 0) - req_set_fail_links(req); - fput(close->put_file); - close->put_file = NULL; - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + if (file) + fput(file); + __io_req_complete(req, issue_flags, ret, 0); return 0; } -static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - if (!req->file) - return -EBADF; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || @@ -4315,18 +4592,18 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock) +static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) { int ret; /* sync_file_range always requires a blocking context */ - if (force_nonblock) + if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = sync_file_range(req->file, req->sync.off, req->sync.len, req->sync.flags); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4340,55 +4617,65 @@ static int io_setup_async_msg(struct io_kiocb *req, if (async_msg) return -EAGAIN; if (io_alloc_async_data(req)) { - if (kmsg->iov != kmsg->fast_iov) - kfree(kmsg->iov); + kfree(kmsg->free_iov); return -ENOMEM; } async_msg = req->async_data; req->flags |= REQ_F_NEED_CLEANUP; memcpy(async_msg, kmsg, sizeof(*kmsg)); + if (async_msg->msg.msg_name) + async_msg->msg.msg_name = &async_msg->addr; + /* if were using fast_iov, set it to the new one */ + if (!async_msg->free_iov) + async_msg->msg.msg_iter.iov = async_msg->fast_iov; + return -EAGAIN; } static int io_sendmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { - iomsg->iov = iomsg->fast_iov; iomsg->msg.msg_name = &iomsg->addr; + iomsg->free_iov = iomsg->fast_iov; return sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg, - req->sr_msg.msg_flags, &iomsg->iov); + req->sr_msg.msg_flags, &iomsg->free_iov); } -static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_sendmsg_prep_async(struct io_kiocb *req) { - struct io_async_msghdr *async_msg = req->async_data; - struct io_sr_msg *sr = &req->sr_msg; int ret; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->addr2 || sqe->splice_fd_in || sqe->ioprio)) - return -EINVAL; - - sr->msg_flags = READ_ONCE(sqe->msg_flags); - sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); - sr->len = READ_ONCE(sqe->len); - -#ifdef CONFIG_COMPAT - if (req->ctx->compat) - sr->msg_flags |= MSG_CMSG_COMPAT; -#endif - - if (!async_msg || !io_op_defs[req->opcode].needs_async_data) - return 0; - ret = io_sendmsg_copy_hdr(req, async_msg); + ret = io_sendmsg_copy_hdr(req, req->async_data); if (!ret) req->flags |= REQ_F_NEED_CLEANUP; return ret; } -static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sr_msg *sr = &req->sr_msg; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio)) + return -EINVAL; + + sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + sr->len = READ_ONCE(sqe->len); + sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + if (sr->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + return 0; +} + +static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct socket *sock; @@ -4400,46 +4687,37 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, if (unlikely(!sock)) return ret; - if (req->async_data) { - kmsg = req->async_data; - kmsg->msg.msg_name = &kmsg->addr; - /* if iov is set, it's allocated already */ - if (!kmsg->iov) - kmsg->iov = kmsg->fast_iov; - kmsg->msg.msg_iter.iov = kmsg->iov; - } else { + kmsg = req->async_data; + if (!kmsg) { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret) return ret; kmsg = &iomsg; } - flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + flags = req->sr_msg.msg_flags; + if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) min_ret = iov_iter_count(&kmsg->msg.msg_iter); ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); - if (force_nonblock && ret == -EAGAIN) + if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; - if (kmsg->iov != kmsg->fast_iov) - kfree(kmsg->iov); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < min_ret) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } -static int io_send(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_send(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = &req->sr_msg; struct msghdr msg; @@ -4462,25 +4740,22 @@ static int io_send(struct io_kiocb *req, bool force_nonblock, msg.msg_controllen = 0; msg.msg_namelen = 0; - flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + flags = req->sr_msg.msg_flags; + if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); - if (force_nonblock && ret == -EAGAIN) + if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; if (ret < min_ret) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4500,15 +4775,14 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req, if (req->flags & REQ_F_BUFFER_SELECT) { if (iov_len > 1) return -EINVAL; - if (copy_from_user(iomsg->iov, uiov, sizeof(*uiov))) + if (copy_from_user(iomsg->fast_iov, uiov, sizeof(*uiov))) return -EFAULT; - sr->len = iomsg->iov[0].iov_len; - iov_iter_init(&iomsg->msg.msg_iter, READ, iomsg->iov, 1, - sr->len); - iomsg->iov = NULL; + sr->len = iomsg->fast_iov[0].iov_len; + iomsg->free_iov = NULL; } else { + iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV, - &iomsg->iov, &iomsg->msg.msg_iter, + &iomsg->free_iov, &iomsg->msg.msg_iter, false); if (ret > 0) ret = 0; @@ -4521,16 +4795,14 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req, static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { - struct compat_msghdr __user *msg_compat; struct io_sr_msg *sr = &req->sr_msg; struct compat_iovec __user *uiov; compat_uptr_t ptr; compat_size_t len; int ret; - msg_compat = (struct compat_msghdr __user *) sr->umsg; - ret = __get_compat_msghdr(&iomsg->msg, msg_compat, &iomsg->uaddr, - &ptr, &len); + ret = __get_compat_msghdr(&iomsg->msg, sr->umsg_compat, &iomsg->uaddr, + &ptr, &len); if (ret) return ret; @@ -4547,11 +4819,11 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, if (clen < 0) return -EINVAL; sr->len = clen; - iomsg->iov[0].iov_len = clen; - iomsg->iov = NULL; + iomsg->free_iov = NULL; } else { + iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, (struct iovec __user *)uiov, len, - UIO_FASTIOV, &iomsg->iov, + UIO_FASTIOV, &iomsg->free_iov, &iomsg->msg.msg_iter, true); if (ret < 0) return ret; @@ -4565,7 +4837,6 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { iomsg->msg.msg_name = &iomsg->addr; - iomsg->iov = iomsg->fast_iov; #ifdef CONFIG_COMPAT if (req->ctx->compat) @@ -4595,38 +4866,42 @@ static inline unsigned int io_put_recv_kbuf(struct io_kiocb *req) return io_put_kbuf(req, req->sr_msg.kbuf); } -static int io_recvmsg_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static int io_recvmsg_prep_async(struct io_kiocb *req) { - struct io_async_msghdr *async_msg = req->async_data; - struct io_sr_msg *sr = &req->sr_msg; int ret; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (unlikely(sqe->addr2 || sqe->splice_fd_in || sqe->ioprio)) - return -EINVAL; - - sr->msg_flags = READ_ONCE(sqe->msg_flags); - sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); - sr->len = READ_ONCE(sqe->len); - sr->bgid = READ_ONCE(sqe->buf_group); - -#ifdef CONFIG_COMPAT - if (req->ctx->compat) - sr->msg_flags |= MSG_CMSG_COMPAT; -#endif - - if (!async_msg || !io_op_defs[req->opcode].needs_async_data) - return 0; - ret = io_recvmsg_copy_hdr(req, async_msg); + ret = io_recvmsg_copy_hdr(req, req->async_data); if (!ret) req->flags |= REQ_F_NEED_CLEANUP; return ret; } -static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_sr_msg *sr = &req->sr_msg; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio)) + return -EINVAL; + + sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + sr->len = READ_ONCE(sqe->len); + sr->bgid = READ_ONCE(sqe->buf_group); + sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + if (sr->msg_flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + return 0; +} + +static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct socket *sock; @@ -4634,19 +4909,14 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, unsigned flags; int min_ret = 0; int ret, cflags = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; sock = sock_from_file(req->file, &ret); if (unlikely(!sock)) return ret; - if (req->async_data) { - kmsg = req->async_data; - kmsg->msg.msg_name = &kmsg->addr; - /* if iov is set, it's allocated already */ - if (!kmsg->iov) - kmsg->iov = kmsg->fast_iov; - kmsg->msg.msg_iter.iov = kmsg->iov; - } else { + kmsg = req->async_data; + if (!kmsg) { ret = io_recvmsg_copy_hdr(req, &iomsg); if (ret) return ret; @@ -4658,16 +4928,14 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, if (IS_ERR(kbuf)) return PTR_ERR(kbuf); kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr); - iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->iov, + kmsg->fast_iov[0].iov_len = req->sr_msg.len; + iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, req->sr_msg.len); } - flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + flags = req->sr_msg.msg_flags; + if (force_nonblock) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) min_ret = iov_iter_count(&kmsg->msg.msg_iter); @@ -4680,17 +4948,17 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); - if (kmsg->iov != kmsg->fast_iov) - kfree(kmsg->iov); + /* fast path, check for non-NULL to avoid function call */ + if (kmsg->free_iov) + kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail_links(req); - __io_req_complete(req, ret, cflags, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, cflags); return 0; } -static int io_recv(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_recv(struct io_kiocb *req, unsigned int issue_flags) { struct io_buffer *kbuf; struct io_sr_msg *sr = &req->sr_msg; @@ -4701,6 +4969,7 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock, unsigned flags; int min_ret = 0; int ret, cflags = 0; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; sock = sock_from_file(req->file, &ret); if (unlikely(!sock)) @@ -4724,12 +4993,9 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock, msg.msg_iocb = NULL; msg.msg_flags = 0; - flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) + flags = req->sr_msg.msg_flags; + if (force_nonblock) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); @@ -4742,8 +5008,8 @@ out_free: if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail_links(req); - __io_req_complete(req, ret, cflags, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, cflags); return 0; } @@ -4751,48 +5017,79 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_accept *accept = &req->accept; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->splice_fd_in) + if (sqe->ioprio || sqe->len || sqe->buf_index) return -EINVAL; accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); accept->flags = READ_ONCE(sqe->accept_flags); accept->nofile = rlimit(RLIMIT_NOFILE); + + accept->file_slot = READ_ONCE(sqe->file_index); + if (accept->file_slot && (accept->flags & SOCK_CLOEXEC)) + return -EINVAL; + if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK)) + accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return 0; } -static int io_accept(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_accept(struct io_kiocb *req, unsigned int issue_flags) { struct io_accept *accept = &req->accept; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; - int ret; + bool fixed = !!accept->file_slot; + struct file *file; + int ret, fd; if (req->file->f_flags & O_NONBLOCK) req->flags |= REQ_F_NOWAIT; - ret = __sys_accept4_file(req->file, file_flags, accept->addr, - accept->addr_len, accept->flags, - accept->nofile); - if (ret == -EAGAIN && force_nonblock) - return -EAGAIN; - if (ret < 0) { + if (!fixed) { + fd = __get_unused_fd_flags(accept->flags, accept->nofile); + if (unlikely(fd < 0)) + return fd; + } + file = do_accept(req->file, file_flags, accept->addr, accept->addr_len, + accept->flags); + + if (IS_ERR(file)) { + if (!fixed) + put_unused_fd(fd); + ret = PTR_ERR(file); + if (ret == -EAGAIN && force_nonblock) + return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; - req_set_fail_links(req); + req_set_fail(req); + } else if (!fixed) { + fd_install(fd, file); + ret = fd; + } else { + ret = io_install_fixed_file(req, file, issue_flags, + accept->file_slot - 1); } - __io_req_complete(req, ret, 0, cs); + __io_req_complete(req, issue_flags, ret, 0); return 0; } +static int io_connect_prep_async(struct io_kiocb *req) +{ + struct io_async_connect *io = req->async_data; + struct io_connect *conn = &req->connect; + + return move_addr_to_kernel(conn->addr, conn->addr_len, &io->address); +} + static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_connect *conn = &req->connect; - struct io_async_connect *io = req->async_data; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) @@ -4800,20 +5097,15 @@ static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); conn->addr_len = READ_ONCE(sqe->addr2); - - if (!io) - return 0; - - return move_addr_to_kernel(conn->addr, conn->addr_len, - &io->address); + return 0; } -static int io_connect(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_connect(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_connect __io, *io; unsigned file_flags; int ret; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; if (req->async_data) { io = req->async_data; @@ -4837,7 +5129,6 @@ static int io_connect(struct io_kiocb *req, bool force_nonblock, ret = -ENOMEM; goto out; } - io = req->async_data; memcpy(req->async_data, &__io, sizeof(__io)); return -EAGAIN; } @@ -4845,67 +5136,37 @@ static int io_connect(struct io_kiocb *req, bool force_nonblock, ret = -EINTR; out: if (ret < 0) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } #else /* !CONFIG_NET */ -static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - return -EOPNOTSUPP; +#define IO_NETOP_FN(op) \ +static int io_##op(struct io_kiocb *req, unsigned int issue_flags) \ +{ \ + return -EOPNOTSUPP; \ } -static int io_sendmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) -{ - return -EOPNOTSUPP; +#define IO_NETOP_PREP(op) \ +IO_NETOP_FN(op) \ +static int io_##op##_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) \ +{ \ + return -EOPNOTSUPP; \ +} \ + +#define IO_NETOP_PREP_ASYNC(op) \ +IO_NETOP_PREP(op) \ +static int io_##op##_prep_async(struct io_kiocb *req) \ +{ \ + return -EOPNOTSUPP; \ } -static int io_send(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) -{ - return -EOPNOTSUPP; -} - -static int io_recvmsg_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - return -EOPNOTSUPP; -} - -static int io_recvmsg(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) -{ - return -EOPNOTSUPP; -} - -static int io_recv(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) -{ - return -EOPNOTSUPP; -} - -static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - return -EOPNOTSUPP; -} - -static int io_accept(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) -{ - return -EOPNOTSUPP; -} - -static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - return -EOPNOTSUPP; -} - -static int io_connect(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) -{ - return -EOPNOTSUPP; -} +IO_NETOP_PREP_ASYNC(sendmsg); +IO_NETOP_PREP_ASYNC(recvmsg); +IO_NETOP_PREP_ASYNC(connect); +IO_NETOP_PREP(accept); +IO_NETOP_FN(send); +IO_NETOP_FN(recv); #endif /* CONFIG_NET */ struct io_poll_table { @@ -4915,68 +5176,47 @@ struct io_poll_table { int error; }; -static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, - __poll_t mask, task_work_func_t func) +#define IO_POLL_CANCEL_FLAG BIT(31) +#define IO_POLL_RETRY_FLAG BIT(30) +#define IO_POLL_REF_MASK GENMASK(29, 0) + +/* + * We usually have 1-2 refs taken, 128 is more than enough and we want to + * maximise the margin between this amount and the moment when it overflows. + */ +#define IO_POLL_REF_BIAS 128 + +static bool io_poll_get_ownership_slowpath(struct io_kiocb *req) { - bool twa_signal_ok; - int ret; - - /* for instances that support it check for an event match first: */ - if (mask && !(mask & poll->events)) - return 0; - - trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask); - - list_del_init(&poll->wait.entry); - - req->result = mask; - init_task_work(&req->task_work, func); - percpu_ref_get(&req->ctx->refs); + int v; /* - * If we using the signalfd wait_queue_head for this wakeup, then - * it's not safe to use TWA_SIGNAL as we could be recursing on the - * tsk->sighand->siglock on doing the wakeup. Should not be needed - * either, as the normal wakeup will suffice. + * poll_refs are already elevated and we don't have much hope for + * grabbing the ownership. Instead of incrementing set a retry flag + * to notify the loop that there might have been some change. */ - twa_signal_ok = (poll->head != &req->task->sighand->signalfd_wqh); - - /* - * If this fails, then the task is exiting. When a task exits, the - * work gets canceled, so just cancel this request as well instead - * of executing it. We can't safely execute it anyway, as we may not - * have the needed state needed for it anyway. - */ - ret = io_req_task_work_add(req, twa_signal_ok); - if (unlikely(ret)) { - struct task_struct *tsk; - - WRITE_ONCE(poll->canceled, true); - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, TWA_NONE); - wake_up_process(tsk); - } - return 1; + v = atomic_fetch_or(IO_POLL_RETRY_FLAG, &req->poll_refs); + if (v & IO_POLL_REF_MASK) + return false; + return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); } -static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll) - __acquires(&req->ctx->completion_lock) +/* + * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can + * bump it and acquire ownership. It's disallowed to modify requests while not + * owning it, that prevents from races for enqueueing task_work's and b/w + * arming poll and wakeups. + */ +static inline bool io_poll_get_ownership(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; + if (unlikely(atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS)) + return io_poll_get_ownership_slowpath(req); + return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); +} - if (!req->result && !READ_ONCE(poll->canceled)) { - struct poll_table_struct pt = { ._key = poll->events }; - - req->result = vfs_poll(req->file, &pt) & poll->events; - } - - spin_lock_irq(&ctx->completion_lock); - if (!req->result && !READ_ONCE(poll->canceled)) { - add_wait_queue(poll->head, &poll->wait); - return true; - } - - return false; +static void io_poll_mark_cancelled(struct io_kiocb *req) +{ + atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs); } static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req) @@ -4994,99 +5234,254 @@ static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req) return &req->apoll->poll; } -static void io_poll_remove_double(struct io_kiocb *req) -{ - struct io_poll_iocb *poll = io_poll_get_double(req); - - lockdep_assert_held(&req->ctx->completion_lock); - - if (poll && poll->head) { - struct wait_queue_head *head = poll->head; - - spin_lock(&head->lock); - list_del_init(&poll->wait.entry); - if (poll->wait.private) - refcount_dec(&req->refs); - poll->head = NULL; - spin_unlock(&head->lock); - } -} - -static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error) +static void io_poll_req_insert(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + struct hlist_head *list; - io_poll_remove_double(req); - req->poll.done = true; - io_cqring_fill_event(req, error ? error : mangle_poll(mask)); - io_commit_cqring(ctx); -} - -static void io_poll_task_func(struct callback_head *cb) -{ - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *nxt; - - if (io_poll_rewait(req, &req->poll)) { - spin_unlock_irq(&ctx->completion_lock); - } else { - hash_del(&req->hash_node); - io_poll_complete(req, req->result, 0); - spin_unlock_irq(&ctx->completion_lock); - - nxt = io_put_req_find_next(req); - io_cqring_ev_posted(ctx); - if (nxt) - __io_req_task_submit(nxt); - } - - percpu_ref_put(&ctx->refs); -} - -static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode, - int sync, void *key) -{ - struct io_kiocb *req = wait->private; - struct io_poll_iocb *poll = io_poll_get_single(req); - __poll_t mask = key_to_poll(key); - - /* for instances that support it check for an event match first: */ - if (mask && !(mask & poll->events)) - return 0; - - list_del_init(&wait->entry); - - if (poll && poll->head) { - bool done; - - spin_lock(&poll->head->lock); - done = list_empty(&poll->wait.entry); - if (!done) - list_del_init(&poll->wait.entry); - /* make sure double remove sees this as being gone */ - wait->private = NULL; - spin_unlock(&poll->head->lock); - if (!done) { - /* use wait func handler, so it matches the rq type */ - poll->wait.func(&poll->wait, mode, sync, key); - } - } - refcount_dec(&req->refs); - return 1; + list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)]; + hlist_add_head(&req->hash_node, list); } static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events, wait_queue_func_t wake_func) { poll->head = NULL; - poll->done = false; - poll->canceled = false; - poll->events = events; +#define IO_POLL_UNMASK (EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP) + /* mask in events that we always want/need */ + poll->events = events | IO_POLL_UNMASK; INIT_LIST_HEAD(&poll->wait.entry); init_waitqueue_func_entry(&poll->wait, wake_func); } +static inline void io_poll_remove_entry(struct io_poll_iocb *poll) +{ + struct wait_queue_head *head = smp_load_acquire(&poll->head); + + if (head) { + spin_lock_irq(&head->lock); + list_del_init(&poll->wait.entry); + poll->head = NULL; + spin_unlock_irq(&head->lock); + } +} + +static void io_poll_remove_entries(struct io_kiocb *req) +{ + struct io_poll_iocb *poll = io_poll_get_single(req); + struct io_poll_iocb *poll_double = io_poll_get_double(req); + + /* + * While we hold the waitqueue lock and the waitqueue is nonempty, + * wake_up_pollfree() will wait for us. However, taking the waitqueue + * lock in the first place can race with the waitqueue being freed. + * + * We solve this as eventpoll does: by taking advantage of the fact that + * all users of wake_up_pollfree() will RCU-delay the actual free. If + * we enter rcu_read_lock() and see that the pointer to the queue is + * non-NULL, we can then lock it without the memory being freed out from + * under us. + * + * Keep holding rcu_read_lock() as long as we hold the queue lock, in + * case the caller deletes the entry from the queue, leaving it empty. + * In that case, only RCU prevents the queue memory from being freed. + */ + rcu_read_lock(); + io_poll_remove_entry(poll); + if (poll_double) + io_poll_remove_entry(poll_double); + rcu_read_unlock(); +} + +/* + * All poll tw should go through this. Checks for poll events, manages + * references, does rewait, etc. + * + * Returns a negative error on failure. >0 when no action require, which is + * either spurious wakeup or multishot CQE is served. 0 when it's done with + * the request, then the mask is stored in req->result. + */ +static int io_poll_check_events(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_poll_iocb *poll = io_poll_get_single(req); + int v; + + /* req->task == current here, checking PF_EXITING is safe */ + if (unlikely(req->task->flags & PF_EXITING)) + io_poll_mark_cancelled(req); + + do { + v = atomic_read(&req->poll_refs); + + /* tw handler should be the owner, and so have some references */ + if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK))) + return 0; + if (v & IO_POLL_CANCEL_FLAG) + return -ECANCELED; + /* + * cqe.res contains only events of the first wake up + * and all others are be lost. Redo vfs_poll() to get + * up to date state. + */ + if ((v & IO_POLL_REF_MASK) != 1) + req->result = 0; + if (v & IO_POLL_RETRY_FLAG) { + req->result = 0; + /* + * We won't find new events that came in between + * vfs_poll and the ref put unless we clear the + * flag in advance. + */ + atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs); + v &= ~IO_POLL_RETRY_FLAG; + } + + if (!req->result) { + struct poll_table_struct pt = { ._key = poll->events }; + + req->result = vfs_poll(req->file, &pt) & poll->events; + } + + /* multishot, just fill an CQE and proceed */ + if (req->result && !(poll->events & EPOLLONESHOT)) { + __poll_t mask = mangle_poll(req->result & poll->events); + bool filled; + + spin_lock(&ctx->completion_lock); + filled = io_fill_cqe_aux(ctx, req->user_data, mask, + IORING_CQE_F_MORE); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (unlikely(!filled)) + return -ECANCELED; + io_cqring_ev_posted(ctx); + } else if (req->result) { + return 0; + } + + /* force the next iteration to vfs_poll() */ + req->result = 0; + + /* + * Release all references, retry if someone tried to restart + * task_work while we were executing it. + */ + } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) & + IO_POLL_REF_MASK); + + return 1; +} + +static void io_poll_task_func(struct io_kiocb *req, bool *locked) +{ + struct io_ring_ctx *ctx = req->ctx; + int ret; + + ret = io_poll_check_events(req); + if (ret > 0) + return; + + if (!ret) { + req->result = mangle_poll(req->result & req->poll.events); + } else { + req->result = ret; + req_set_fail(req); + } + + io_poll_remove_entries(req); + spin_lock(&ctx->completion_lock); + hash_del(&req->hash_node); + spin_unlock(&ctx->completion_lock); + io_req_complete_post(req, req->result, 0); +} + +static void io_apoll_task_func(struct io_kiocb *req, bool *locked) +{ + struct io_ring_ctx *ctx = req->ctx; + int ret; + + ret = io_poll_check_events(req); + if (ret > 0) + return; + + io_poll_remove_entries(req); + spin_lock(&ctx->completion_lock); + hash_del(&req->hash_node); + spin_unlock(&ctx->completion_lock); + + if (!ret) + io_req_task_submit(req, locked); + else + io_req_complete_failed(req, ret); +} + +static void __io_poll_execute(struct io_kiocb *req, int mask) +{ + req->result = mask; + if (req->opcode == IORING_OP_POLL_ADD) + req->io_task_work.func = io_poll_task_func; + else + req->io_task_work.func = io_apoll_task_func; + + trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask); + io_req_task_work_add(req); +} + +static inline void io_poll_execute(struct io_kiocb *req, int res) +{ + if (io_poll_get_ownership(req)) + __io_poll_execute(req, res); +} + +static void io_poll_cancel_req(struct io_kiocb *req) +{ + io_poll_mark_cancelled(req); + /* kick tw, which should complete the request */ + io_poll_execute(req, 0); +} + +static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, + void *key) +{ + struct io_kiocb *req = wait->private; + struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb, + wait); + __poll_t mask = key_to_poll(key); + + if (unlikely(mask & POLLFREE)) { + io_poll_mark_cancelled(req); + /* we have to kick tw in case it's not already */ + io_poll_execute(req, 0); + + /* + * If the waitqueue is being freed early but someone is already + * holds ownership over it, we have to tear down the request as + * best we can. That means immediately removing the request from + * its waitqueue and preventing all further accesses to the + * waitqueue via the request. + */ + list_del_init(&poll->wait.entry); + + /* + * Careful: this *must* be the last step, since as soon + * as req->head is NULL'ed out, the request can be + * completed and freed, since aio_poll_complete_work() + * will no longer need to take the waitqueue lock. + */ + smp_store_release(&poll->head, NULL); + return 1; + } + + /* for instances that support it check for an event match first */ + if (mask && !(mask & poll->events)) + return 0; + + if (io_poll_get_ownership(req)) + __io_poll_execute(req, mask); + return 1; +} + static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, struct wait_queue_head *head, struct io_poll_iocb **poll_ptr) @@ -5099,29 +5494,31 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, * if this happens. */ if (unlikely(pt->nr_entries)) { - struct io_poll_iocb *poll_one = poll; + struct io_poll_iocb *first = poll; + /* double add on the same waitqueue head, ignore */ + if (first->head == head) + return; /* already have a 2nd entry, fail a third attempt */ if (*poll_ptr) { + if ((*poll_ptr)->head == head) + return; pt->error = -EINVAL; return; } - /* double add on the same waitqueue head, ignore */ - if (poll->head == head) - return; + poll = kmalloc(sizeof(*poll), GFP_ATOMIC); if (!poll) { pt->error = -ENOMEM; return; } - io_init_poll_iocb(poll, poll_one->events, io_poll_double_wake); - refcount_inc(&req->refs); - poll->wait.private = req; + io_init_poll_iocb(poll, first->events, first->wait.func); *poll_ptr = poll; } pt->nr_entries++; poll->head = head; + poll->wait.private = req; if (poll->events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(head, &poll->wait); @@ -5129,6 +5526,73 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, add_wait_queue(head, &poll->wait); } +static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, + struct poll_table_struct *p) +{ + struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); + + __io_queue_proc(&pt->req->poll, pt, head, + (struct io_poll_iocb **) &pt->req->async_data); +} + +static int __io_arm_poll_handler(struct io_kiocb *req, + struct io_poll_iocb *poll, + struct io_poll_table *ipt, __poll_t mask) +{ + struct io_ring_ctx *ctx = req->ctx; + + INIT_HLIST_NODE(&req->hash_node); + io_init_poll_iocb(poll, mask, io_poll_wake); + poll->file = req->file; + poll->wait.private = req; + + ipt->pt._key = mask; + ipt->req = req; + ipt->error = 0; + ipt->nr_entries = 0; + + /* + * Take the ownership to delay any tw execution up until we're done + * with poll arming. see io_poll_get_ownership(). + */ + atomic_set(&req->poll_refs, 1); + mask = vfs_poll(req->file, &ipt->pt) & poll->events; + + if (mask && (poll->events & EPOLLONESHOT)) { + io_poll_remove_entries(req); + /* no one else has access to the req, forget about the ref */ + return mask; + } + if (!mask && unlikely(ipt->error || !ipt->nr_entries)) { + io_poll_remove_entries(req); + if (!ipt->error) + ipt->error = -EINVAL; + return 0; + } + + spin_lock(&ctx->completion_lock); + io_poll_req_insert(req); + spin_unlock(&ctx->completion_lock); + + if (mask) { + /* can't multishot if failed, just queue the event we've got */ + if (unlikely(ipt->error || !ipt->nr_entries)) { + poll->events |= EPOLLONESHOT; + ipt->error = 0; + } + __io_poll_execute(req, mask); + return 0; + } + + /* + * Try to release ownership. If we see a change of state, e.g. + * poll was waken up, queue up a tw, it'll deal with it. + */ + if (atomic_cmpxchg(&req->poll_refs, 1, 0) != 1) + __io_poll_execute(req, 0); + return 0; +} + static void io_async_queue_proc(struct file *file, struct wait_queue_head *head, struct poll_table_struct *p) { @@ -5138,245 +5602,87 @@ static void io_async_queue_proc(struct file *file, struct wait_queue_head *head, __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll); } -static void io_async_task_func(struct callback_head *cb) -{ - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct async_poll *apoll = req->apoll; - struct io_ring_ctx *ctx = req->ctx; +enum { + IO_APOLL_OK, + IO_APOLL_ABORTED, + IO_APOLL_READY +}; - trace_io_uring_task_run(req->ctx, req->opcode, req->user_data); - - if (io_poll_rewait(req, &apoll->poll)) { - spin_unlock_irq(&ctx->completion_lock); - percpu_ref_put(&ctx->refs); - return; - } - - /* If req is still hashed, it cannot have been canceled. Don't check. */ - if (hash_hashed(&req->hash_node)) - hash_del(&req->hash_node); - - io_poll_remove_double(req); - spin_unlock_irq(&ctx->completion_lock); - - if (!READ_ONCE(apoll->poll.canceled)) - __io_req_task_submit(req); - else - __io_req_task_cancel(req, -ECANCELED); - - percpu_ref_put(&ctx->refs); - kfree(apoll->double_poll); - kfree(apoll); -} - -static int io_async_wake(struct wait_queue_entry *wait, unsigned mode, int sync, - void *key) -{ - struct io_kiocb *req = wait->private; - struct io_poll_iocb *poll = &req->apoll->poll; - - trace_io_uring_poll_wake(req->ctx, req->opcode, req->user_data, - key_to_poll(key)); - - return __io_async_wake(req, poll, key_to_poll(key), io_async_task_func); -} - -static void io_poll_req_insert(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - struct hlist_head *list; - - list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)]; - hlist_add_head(&req->hash_node, list); -} - -static __poll_t __io_arm_poll_handler(struct io_kiocb *req, - struct io_poll_iocb *poll, - struct io_poll_table *ipt, __poll_t mask, - wait_queue_func_t wake_func) - __acquires(&ctx->completion_lock) -{ - struct io_ring_ctx *ctx = req->ctx; - bool cancel = false; - - if (req->file->f_op->may_pollfree) { - spin_lock_irq(&ctx->completion_lock); - return -EOPNOTSUPP; - } - - INIT_HLIST_NODE(&req->hash_node); - io_init_poll_iocb(poll, mask, wake_func); - poll->file = req->file; - poll->wait.private = req; - - ipt->pt._key = mask; - ipt->req = req; - ipt->error = 0; - ipt->nr_entries = 0; - - mask = vfs_poll(req->file, &ipt->pt) & poll->events; - if (unlikely(!ipt->nr_entries) && !ipt->error) - ipt->error = -EINVAL; - - spin_lock_irq(&ctx->completion_lock); - if (ipt->error) - io_poll_remove_double(req); - if (likely(poll->head)) { - spin_lock(&poll->head->lock); - if (unlikely(list_empty(&poll->wait.entry))) { - if (ipt->error) - cancel = true; - ipt->error = 0; - mask = 0; - } - if (mask || ipt->error) - list_del_init(&poll->wait.entry); - else if (cancel) - WRITE_ONCE(poll->canceled, true); - else if (!poll->done) /* actually waiting for an event */ - io_poll_req_insert(req); - spin_unlock(&poll->head->lock); - } - - return mask; -} - -static bool io_arm_poll_handler(struct io_kiocb *req) +static int io_arm_poll_handler(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; struct async_poll *apoll; struct io_poll_table ipt; - __poll_t mask, ret; - int rw; + __poll_t mask = EPOLLONESHOT | POLLERR | POLLPRI; + int ret; if (!req->file || !file_can_poll(req->file)) - return false; + return IO_APOLL_ABORTED; if (req->flags & REQ_F_POLLED) - return false; - if (def->pollin) - rw = READ; - else if (def->pollout) - rw = WRITE; - else - return false; - /* if we can't nonblock try, then no point in arming a poll handler */ - if (!io_file_supports_async(req->file, rw)) - return false; + return IO_APOLL_ABORTED; + if (!def->pollin && !def->pollout) + return IO_APOLL_ABORTED; + + if (def->pollin) { + mask |= POLLIN | POLLRDNORM; + + /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ + if ((req->opcode == IORING_OP_RECVMSG) && + (req->sr_msg.msg_flags & MSG_ERRQUEUE)) + mask &= ~POLLIN; + } else { + mask |= POLLOUT | POLLWRNORM; + } apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); if (unlikely(!apoll)) - return false; + return IO_APOLL_ABORTED; apoll->double_poll = NULL; - - req->flags |= REQ_F_POLLED; req->apoll = apoll; - - mask = 0; - if (def->pollin) - mask |= POLLIN | POLLRDNORM; - if (def->pollout) - mask |= POLLOUT | POLLWRNORM; - - /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ - if ((req->opcode == IORING_OP_RECVMSG) && - (req->sr_msg.msg_flags & MSG_ERRQUEUE)) - mask &= ~POLLIN; - - mask |= POLLERR | POLLPRI; - + req->flags |= REQ_F_POLLED; ipt.pt._qproc = io_async_queue_proc; - ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, - io_async_wake); - if (ret || ipt.error) { - io_poll_remove_double(req); - spin_unlock_irq(&ctx->completion_lock); - kfree(apoll->double_poll); - kfree(apoll); - return false; - } - spin_unlock_irq(&ctx->completion_lock); - trace_io_uring_poll_arm(ctx, req->opcode, req->user_data, mask, - apoll->poll.events); - return true; -} + ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask); + if (ret || ipt.error) + return ret ? IO_APOLL_READY : IO_APOLL_ABORTED; -static bool __io_poll_remove_one(struct io_kiocb *req, - struct io_poll_iocb *poll) -{ - bool do_complete = false; - - spin_lock(&poll->head->lock); - WRITE_ONCE(poll->canceled, true); - if (!list_empty(&poll->wait.entry)) { - list_del_init(&poll->wait.entry); - do_complete = true; - } - spin_unlock(&poll->head->lock); - hash_del(&req->hash_node); - return do_complete; -} - -static bool io_poll_remove_one(struct io_kiocb *req) -{ - bool do_complete; - - io_poll_remove_double(req); - - if (req->opcode == IORING_OP_POLL_ADD) { - do_complete = __io_poll_remove_one(req, &req->poll); - } else { - struct async_poll *apoll = req->apoll; - - /* non-poll requests have submit ref still */ - do_complete = __io_poll_remove_one(req, &apoll->poll); - if (do_complete) { - io_put_req(req); - kfree(apoll->double_poll); - kfree(apoll); - } - } - - if (do_complete) { - io_cqring_fill_event(req, -ECANCELED); - io_commit_cqring(req->ctx); - req_set_fail_links(req); - io_put_req_deferred(req, 1); - } - - return do_complete; + trace_io_uring_poll_arm(ctx, req, req->opcode, req->user_data, + mask, apoll->poll.events); + return IO_APOLL_OK; } /* * Returns true if we found and killed one or more poll requests */ static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, - struct files_struct *files) + bool cancel_all) { struct hlist_node *tmp; struct io_kiocb *req; - int posted = 0, i; + bool found = false; + int i; - spin_lock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { struct hlist_head *list; list = &ctx->cancel_hash[i]; hlist_for_each_entry_safe(req, tmp, list, hash_node) { - if (io_match_task(req, tsk, files)) - posted += io_poll_remove_one(req); + if (io_match_task_safe(req, tsk, cancel_all)) { + hlist_del_init(&req->hash_node); + io_poll_cancel_req(req); + found = true; + } } } - spin_unlock_irq(&ctx->completion_lock); - - if (posted) - io_cqring_ev_posted(ctx); - - return posted != 0; + spin_unlock(&ctx->completion_lock); + return found; } -static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) +static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr, + bool poll_only) + __must_hold(&ctx->completion_lock) { struct hlist_head *list; struct io_kiocb *req; @@ -5385,107 +5691,161 @@ static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) hlist_for_each_entry(req, list, hash_node) { if (sqe_addr != req->user_data) continue; - if (io_poll_remove_one(req)) - return 0; - return -EALREADY; + if (poll_only && req->opcode != IORING_OP_POLL_ADD) + continue; + return req; } - - return -ENOENT; + return NULL; } -static int io_poll_remove_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static bool io_poll_disarm(struct io_kiocb *req) + __must_hold(&ctx->completion_lock) { - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || - sqe->poll_events) - return -EINVAL; + if (!io_poll_get_ownership(req)) + return false; + io_poll_remove_entries(req); + hash_del(&req->hash_node); + return true; +} - req->poll.addr = READ_ONCE(sqe->addr); +static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr, + bool poll_only) + __must_hold(&ctx->completion_lock) +{ + struct io_kiocb *req = io_poll_find(ctx, sqe_addr, poll_only); + + if (!req) + return -ENOENT; + io_poll_cancel_req(req); return 0; } -/* - * Find a running poll command that matches one specified in sqe->addr, - * and remove it if found. - */ -static int io_poll_remove(struct io_kiocb *req) +static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe, + unsigned int flags) { - struct io_ring_ctx *ctx = req->ctx; - u64 addr; - int ret; - - addr = req->poll.addr; - spin_lock_irq(&ctx->completion_lock); - ret = io_poll_cancel(ctx, addr); - spin_unlock_irq(&ctx->completion_lock); - - if (ret < 0) - req_set_fail_links(req); - io_req_complete(req, ret); - return 0; -} - -static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, - void *key) -{ - struct io_kiocb *req = wait->private; - struct io_poll_iocb *poll = &req->poll; - - return __io_async_wake(req, poll, key_to_poll(key), io_poll_task_func); -} - -static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, - struct poll_table_struct *p) -{ - struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); - - __io_queue_proc(&pt->req->poll, pt, head, (struct io_poll_iocb **) &pt->req->async_data); -} - -static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - struct io_poll_iocb *poll = &req->poll; u32 events; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) - return -EINVAL; - events = READ_ONCE(sqe->poll32_events); #ifdef __BIG_ENDIAN events = swahw32(events); #endif - poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP | - (events & EPOLLEXCLUSIVE); + if (!(flags & IORING_POLL_ADD_MULTI)) + events |= EPOLLONESHOT; + return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT)); +} + +static int io_poll_update_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_poll_update *upd = &req->poll_update; + u32 flags; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) + return -EINVAL; + flags = READ_ONCE(sqe->len); + if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA | + IORING_POLL_ADD_MULTI)) + return -EINVAL; + /* meaningless without update */ + if (flags == IORING_POLL_ADD_MULTI) + return -EINVAL; + + upd->old_user_data = READ_ONCE(sqe->addr); + upd->update_events = flags & IORING_POLL_UPDATE_EVENTS; + upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA; + + upd->new_user_data = READ_ONCE(sqe->off); + if (!upd->update_user_data && upd->new_user_data) + return -EINVAL; + if (upd->update_events) + upd->events = io_poll_parse_events(sqe, flags); + else if (sqe->poll32_events) + return -EINVAL; + return 0; } -static int io_poll_add(struct io_kiocb *req) +static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_poll_iocb *poll = &req->poll; + u32 flags; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr) + return -EINVAL; + flags = READ_ONCE(sqe->len); + if (flags & ~IORING_POLL_ADD_MULTI) + return -EINVAL; + + io_req_set_refcount(req); + poll->events = io_poll_parse_events(sqe, flags); + return 0; +} + +static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) { struct io_poll_iocb *poll = &req->poll; - struct io_ring_ctx *ctx = req->ctx; struct io_poll_table ipt; - __poll_t mask; + int ret; ipt.pt._qproc = io_poll_queue_proc; - mask = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events, - io_poll_wake); + ret = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events); + if (!ret && ipt.error) + req_set_fail(req); + ret = ret ?: ipt.error; + if (ret) + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} - if (mask) { /* no async, we'd stolen it */ - ipt.error = 0; - io_poll_complete(req, mask, 0); - } - spin_unlock_irq(&ctx->completion_lock); +static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *preq; + int ret2, ret = 0; - if (mask) { - io_cqring_ev_posted(ctx); - io_put_req(req); + spin_lock(&ctx->completion_lock); + preq = io_poll_find(ctx, req->poll_update.old_user_data, true); + if (!preq || !io_poll_disarm(preq)) { + spin_unlock(&ctx->completion_lock); + ret = preq ? -EALREADY : -ENOENT; + goto out; } - return ipt.error; + spin_unlock(&ctx->completion_lock); + + if (req->poll_update.update_events || req->poll_update.update_user_data) { + /* only mask one event flags, keep behavior flags */ + if (req->poll_update.update_events) { + preq->poll.events &= ~0xffff; + preq->poll.events |= req->poll_update.events & 0xffff; + preq->poll.events |= IO_POLL_UNMASK; + } + if (req->poll_update.update_user_data) + preq->user_data = req->poll_update.new_user_data; + + ret2 = io_poll_add(preq, issue_flags); + /* successfully updated, don't complete poll request */ + if (!ret2) + goto out; + } + req_set_fail(preq); + io_req_complete(preq, -ECANCELED); +out: + if (ret < 0) + req_set_fail(req); + /* complete update request, we're done with it */ + io_req_complete(req, ret); + return 0; +} + +static void io_req_task_timeout(struct io_kiocb *req, bool *locked) +{ + req_set_fail(req); + io_req_complete_post(req, -ETIME, 0); } static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) @@ -5496,88 +5856,182 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) struct io_ring_ctx *ctx = req->ctx; unsigned long flags; - spin_lock_irqsave(&ctx->completion_lock, flags); + spin_lock_irqsave(&ctx->timeout_lock, flags); list_del_init(&req->timeout.list); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); + spin_unlock_irqrestore(&ctx->timeout_lock, flags); - io_cqring_fill_event(req, -ETIME); - io_commit_cqring(ctx); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - - io_cqring_ev_posted(ctx); - req_set_fail_links(req); - io_put_req(req); + req->io_task_work.func = io_req_task_timeout; + io_req_task_work_add(req); return HRTIMER_NORESTART; } -static int __io_timeout_cancel(struct io_kiocb *req) +static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, + __u64 user_data) + __must_hold(&ctx->timeout_lock) { - struct io_timeout_data *io = req->async_data; - int ret; + struct io_timeout_data *io; + struct io_kiocb *req; + bool found = false; - ret = hrtimer_try_to_cancel(&io->timer); - if (ret == -1) - return -EALREADY; + list_for_each_entry(req, &ctx->timeout_list, timeout.list) { + found = user_data == req->user_data; + if (found) + break; + } + if (!found) + return ERR_PTR(-ENOENT); + + io = req->async_data; + if (hrtimer_try_to_cancel(&io->timer) == -1) + return ERR_PTR(-EALREADY); list_del_init(&req->timeout.list); - - req_set_fail_links(req); - io_cqring_fill_event(req, -ECANCELED); - io_put_req_deferred(req, 1); - return 0; + return req; } static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) + __must_hold(&ctx->completion_lock) + __must_hold(&ctx->timeout_lock) { - struct io_kiocb *req; - int ret = -ENOENT; + struct io_kiocb *req = io_timeout_extract(ctx, user_data); - list_for_each_entry(req, &ctx->timeout_list, timeout.list) { - if (user_data == req->user_data) { - ret = 0; - break; - } + if (IS_ERR(req)) + return PTR_ERR(req); + + req_set_fail(req); + io_fill_cqe_req(req, -ECANCELED, 0); + io_put_req_deferred(req); + return 0; +} + +static clockid_t io_timeout_get_clock(struct io_timeout_data *data) +{ + switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) { + case IORING_TIMEOUT_BOOTTIME: + return CLOCK_BOOTTIME; + case IORING_TIMEOUT_REALTIME: + return CLOCK_REALTIME; + default: + /* can't happen, vetted at prep time */ + WARN_ON_ONCE(1); + fallthrough; + case 0: + return CLOCK_MONOTONIC; } +} - if (ret == -ENOENT) - return ret; +static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, + struct timespec64 *ts, enum hrtimer_mode mode) + __must_hold(&ctx->timeout_lock) +{ + struct io_timeout_data *io; + struct io_kiocb *req; + bool found = false; - return __io_timeout_cancel(req); + list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) { + found = user_data == req->user_data; + if (found) + break; + } + if (!found) + return -ENOENT; + + io = req->async_data; + if (hrtimer_try_to_cancel(&io->timer) == -1) + return -EALREADY; + hrtimer_init(&io->timer, io_timeout_get_clock(io), mode); + io->timer.function = io_link_timeout_fn; + hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode); + return 0; +} + +static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, + struct timespec64 *ts, enum hrtimer_mode mode) + __must_hold(&ctx->timeout_lock) +{ + struct io_kiocb *req = io_timeout_extract(ctx, user_data); + struct io_timeout_data *data; + + if (IS_ERR(req)) + return PTR_ERR(req); + + req->timeout.off = 0; /* noseq */ + data = req->async_data; + list_add_tail(&req->timeout.list, &ctx->timeout_list); + hrtimer_init(&data->timer, io_timeout_get_clock(data), mode); + data->timer.function = io_timeout_fn; + hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode); + return 0; } static int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + struct io_timeout_rem *tr = &req->timeout_rem; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; - if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->timeout_flags || - sqe->splice_fd_in) + if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->splice_fd_in) return -EINVAL; - req->timeout_rem.addr = READ_ONCE(sqe->addr); + tr->ltimeout = false; + tr->addr = READ_ONCE(sqe->addr); + tr->flags = READ_ONCE(sqe->timeout_flags); + if (tr->flags & IORING_TIMEOUT_UPDATE_MASK) { + if (hweight32(tr->flags & IORING_TIMEOUT_CLOCK_MASK) > 1) + return -EINVAL; + if (tr->flags & IORING_LINK_TIMEOUT_UPDATE) + tr->ltimeout = true; + if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS)) + return -EINVAL; + if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2))) + return -EFAULT; + } else if (tr->flags) { + /* timeout removal doesn't support flags */ + return -EINVAL; + } + return 0; } +static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags) +{ + return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS + : HRTIMER_MODE_REL; +} + /* * Remove or update an existing timeout command */ -static int io_timeout_remove(struct io_kiocb *req) +static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) { + struct io_timeout_rem *tr = &req->timeout_rem; struct io_ring_ctx *ctx = req->ctx; int ret; - spin_lock_irq(&ctx->completion_lock); - ret = io_timeout_cancel(ctx, req->timeout_rem.addr); + if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) { + spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + ret = io_timeout_cancel(ctx, tr->addr); + spin_unlock_irq(&ctx->timeout_lock); + spin_unlock(&ctx->completion_lock); + } else { + enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); + + spin_lock_irq(&ctx->timeout_lock); + if (tr->ltimeout) + ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode); + else + ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode); + spin_unlock_irq(&ctx->timeout_lock); + } - io_cqring_fill_event(req, ret); - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); - io_cqring_ev_posted(ctx); if (ret < 0) - req_set_fail_links(req); - io_put_req(req); + req_set_fail(req); + io_req_complete_post(req, ret, 0); return 0; } @@ -5596,38 +6050,52 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (off && is_timeout_link) return -EINVAL; flags = READ_ONCE(sqe->timeout_flags); - if (flags & ~IORING_TIMEOUT_ABS) + if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK)) + return -EINVAL; + /* more than one clock specified is invalid, obviously */ + if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) return -EINVAL; + INIT_LIST_HEAD(&req->timeout.list); req->timeout.off = off; + if (unlikely(off && !req->ctx->off_timeout_used)) + req->ctx->off_timeout_used = true; if (!req->async_data && io_alloc_async_data(req)) return -ENOMEM; data = req->async_data; data->req = req; + data->flags = flags; if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; - if (flags & IORING_TIMEOUT_ABS) - data->mode = HRTIMER_MODE_ABS; - else - data->mode = HRTIMER_MODE_REL; - INIT_LIST_HEAD(&req->timeout.list); - hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode); + data->mode = io_translate_timeout_mode(flags); + hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); + + if (is_timeout_link) { + struct io_submit_link *link = &req->ctx->submit_state.link; + + if (!link->head) + return -EINVAL; + if (link->last->opcode == IORING_OP_LINK_TIMEOUT) + return -EINVAL; + req->timeout.head = link->last; + link->last->flags |= REQ_F_ARM_LTIMEOUT; + } return 0; } -static int io_timeout(struct io_kiocb *req) +static int io_timeout(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_timeout_data *data = req->async_data; struct list_head *entry; u32 tail, off = req->timeout.off; - spin_lock_irq(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); /* * sqe->off holds how many events that need to occur for this @@ -5666,23 +6134,34 @@ add: list_add(&req->timeout.list, entry); data->timer.function = io_timeout_fn; hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); - spin_unlock_irq(&ctx->completion_lock); + spin_unlock_irq(&ctx->timeout_lock); return 0; } +struct io_cancel_data { + struct io_ring_ctx *ctx; + u64 user_data; +}; + static bool io_cancel_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_cancel_data *cd = data; - return req->user_data == (unsigned long) data; + return req->ctx == cd->ctx && req->user_data == cd->user_data; } -static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr) +static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data, + struct io_ring_ctx *ctx) { + struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, }; enum io_wq_cancel cancel_ret; int ret = 0; - cancel_ret = io_wq_cancel_cb(ctx->io_wq, io_cancel_cb, sqe_addr, false); + if (!tctx || !tctx->io_wq) + return -ENOENT; + + cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; @@ -5698,35 +6177,27 @@ static int io_async_cancel_one(struct io_ring_ctx *ctx, void *sqe_addr) return ret; } -static void io_async_find_and_cancel(struct io_ring_ctx *ctx, - struct io_kiocb *req, __u64 sqe_addr, - int success_ret) +static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr) { - unsigned long flags; + struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_async_cancel_one(ctx, (void *) (unsigned long) sqe_addr); - if (ret != -ENOENT) { - spin_lock_irqsave(&ctx->completion_lock, flags); - goto done; - } + WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current); - spin_lock_irqsave(&ctx->completion_lock, flags); - ret = io_timeout_cancel(ctx, sqe_addr); + ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx); if (ret != -ENOENT) - goto done; - ret = io_poll_cancel(ctx, sqe_addr); -done: - if (!ret) - ret = success_ret; - io_cqring_fill_event(req, ret); - io_commit_cqring(ctx); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); + return ret; - if (ret < 0) - req_set_fail_links(req); - io_put_req(req); + spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + ret = io_timeout_cancel(ctx, sqe_addr); + spin_unlock_irq(&ctx->timeout_lock); + if (ret != -ENOENT) + goto out; + ret = io_poll_cancel(ctx, sqe_addr, false); +out: + spin_unlock(&ctx->completion_lock); + return ret; } static int io_async_cancel_prep(struct io_kiocb *req, @@ -5744,52 +6215,72 @@ static int io_async_cancel_prep(struct io_kiocb *req, return 0; } -static int io_async_cancel(struct io_kiocb *req) +static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; - - io_async_find_and_cancel(ctx, req, req->cancel.addr, 0); - return 0; -} - -static int io_files_update_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) -{ - if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL)) - return -EINVAL; - if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) - return -EINVAL; - if (sqe->ioprio || sqe->rw_flags) - return -EINVAL; - - req->files_update.offset = READ_ONCE(sqe->off); - req->files_update.nr_args = READ_ONCE(sqe->len); - if (!req->files_update.nr_args) - return -EINVAL; - req->files_update.arg = READ_ONCE(sqe->addr); - return 0; -} - -static int io_files_update(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_uring_files_update up; + u64 sqe_addr = req->cancel.addr; + struct io_tctx_node *node; int ret; - if (force_nonblock) - return -EAGAIN; + ret = io_try_cancel_userdata(req, sqe_addr); + if (ret != -ENOENT) + goto done; - up.offset = req->files_update.offset; - up.fds = req->files_update.arg; + /* slow path, try all io-wq's */ + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = -ENOENT; + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; - mutex_lock(&ctx->uring_lock); - ret = __io_sqe_files_update(ctx, &up, req->files_update.nr_args); - mutex_unlock(&ctx->uring_lock); + ret = io_async_cancel_one(tctx, req->cancel.addr, ctx); + if (ret != -ENOENT) + break; + } + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); +done: + if (ret < 0) + req_set_fail(req); + io_req_complete_post(req, ret, 0); + return 0; +} + +static int io_rsrc_update_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + return -EINVAL; + if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) + return -EINVAL; + + req->rsrc_update.offset = READ_ONCE(sqe->off); + req->rsrc_update.nr_args = READ_ONCE(sqe->len); + if (!req->rsrc_update.nr_args) + return -EINVAL; + req->rsrc_update.arg = READ_ONCE(sqe->addr); + return 0; +} + +static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_uring_rsrc_update2 up; + int ret; + + up.offset = req->rsrc_update.offset; + up.data = req->rsrc_update.arg; + up.nr = 0; + up.tags = 0; + up.resv = 0; + up.resv2 = 0; + + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, + &up, req->rsrc_update.nr_args); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); if (ret < 0) - req_set_fail_links(req); - __io_req_complete(req, ret, 0, cs); + req_set_fail(req); + __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -5809,11 +6300,11 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_POLL_ADD: return io_poll_add_prep(req, sqe); case IORING_OP_POLL_REMOVE: - return io_poll_remove_prep(req, sqe); + return io_poll_update_prep(req, sqe); case IORING_OP_FSYNC: - return io_prep_fsync(req, sqe); + return io_fsync_prep(req, sqe); case IORING_OP_SYNC_FILE_RANGE: - return io_prep_sfr(req, sqe); + return io_sfr_prep(req, sqe); case IORING_OP_SENDMSG: case IORING_OP_SEND: return io_sendmsg_prep(req, sqe); @@ -5839,7 +6330,7 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_CLOSE: return io_close_prep(req, sqe); case IORING_OP_FILES_UPDATE: - return io_files_update_prep(req, sqe); + return io_rsrc_update_prep(req, sqe); case IORING_OP_STATX: return io_statx_prep(req, sqe); case IORING_OP_FADVISE: @@ -5858,100 +6349,131 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return io_remove_buffers_prep(req, sqe); case IORING_OP_TEE: return io_tee_prep(req, sqe); + case IORING_OP_SHUTDOWN: + return io_shutdown_prep(req, sqe); + case IORING_OP_RENAMEAT: + return io_renameat_prep(req, sqe); + case IORING_OP_UNLINKAT: + return io_unlinkat_prep(req, sqe); } printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", req->opcode); - return-EINVAL; + return -EINVAL; } -static int io_req_defer_prep(struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static int io_req_prep_async(struct io_kiocb *req) { - if (!sqe) + if (!io_op_defs[req->opcode].needs_async_setup) return 0; + if (WARN_ON_ONCE(req->async_data)) + return -EFAULT; if (io_alloc_async_data(req)) return -EAGAIN; - return io_req_prep(req, sqe); + + switch (req->opcode) { + case IORING_OP_READV: + return io_rw_prep_async(req, READ); + case IORING_OP_WRITEV: + return io_rw_prep_async(req, WRITE); + case IORING_OP_SENDMSG: + return io_sendmsg_prep_async(req); + case IORING_OP_RECVMSG: + return io_recvmsg_prep_async(req); + case IORING_OP_CONNECT: + return io_connect_prep_async(req); + } + printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n", + req->opcode); + return -EFAULT; } static u32 io_get_sequence(struct io_kiocb *req) { - struct io_kiocb *pos; - struct io_ring_ctx *ctx = req->ctx; - u32 total_submitted, nr_reqs = 1; + u32 seq = req->ctx->cached_sq_head; - if (req->flags & REQ_F_LINK_HEAD) - list_for_each_entry(pos, &req->link_list, link_list) - nr_reqs++; - - total_submitted = ctx->cached_sq_head - ctx->cached_sq_dropped; - return total_submitted - nr_reqs; + /* need original cached_sq_head, but it was increased for each req */ + io_for_each_link(req, req) + seq--; + return seq; } -static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static bool io_drain_req(struct io_kiocb *req) { + struct io_kiocb *pos; struct io_ring_ctx *ctx = req->ctx; struct io_defer_entry *de; int ret; u32 seq; + if (req->flags & REQ_F_FAIL) { + io_req_complete_fail_submit(req); + return true; + } + + /* + * If we need to drain a request in the middle of a link, drain the + * head request and the next request/link after the current link. + * Considering sequential execution of links, IOSQE_IO_DRAIN will be + * maintained for every request of our link. + */ + if (ctx->drain_next) { + req->flags |= REQ_F_IO_DRAIN; + ctx->drain_next = false; + } + /* not interested in head, start from the first linked */ + io_for_each_link(pos, req->link) { + if (pos->flags & REQ_F_IO_DRAIN) { + ctx->drain_next = true; + req->flags |= REQ_F_IO_DRAIN; + break; + } + } + /* Still need defer if there is pending req in defer list. */ + spin_lock(&ctx->completion_lock); if (likely(list_empty_careful(&ctx->defer_list) && - !(req->flags & REQ_F_IO_DRAIN))) - return 0; + !(req->flags & REQ_F_IO_DRAIN))) { + spin_unlock(&ctx->completion_lock); + ctx->drain_active = false; + return false; + } + spin_unlock(&ctx->completion_lock); seq = io_get_sequence(req); /* Still a chance to pass the sequence check */ if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) - return 0; + return false; - if (!req->async_data) { - ret = io_req_defer_prep(req, sqe); - if (ret) - return ret; - } + ret = io_req_prep_async(req); + if (ret) + goto fail; io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); - if (!de) - return -ENOMEM; + if (!de) { + ret = -ENOMEM; +fail: + io_req_complete_failed(req, ret); + return true; + } - spin_lock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) { - spin_unlock_irq(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); kfree(de); - io_queue_async_work(req); - return -EIOCBQUEUED; + io_queue_async_work(req, NULL); + return true; } trace_io_uring_defer(ctx, req, req->user_data); de->req = req; de->seq = seq; list_add_tail(&de->list, &ctx->defer_list); - spin_unlock_irq(&ctx->completion_lock); - return -EIOCBQUEUED; + spin_unlock(&ctx->completion_lock); + return true; } -static void io_req_drop_files(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; - struct io_uring_task *tctx = req->task->io_uring; - unsigned long flags; - - if (req->work.flags & IO_WQ_WORK_FILES) { - put_files_struct(req->work.identity->files); - put_nsproxy(req->work.identity->nsproxy); - } - spin_lock_irqsave(&ctx->inflight_lock, flags); - list_del(&req->inflight_entry); - spin_unlock_irqrestore(&ctx->inflight_lock, flags); - req->flags &= ~REQ_F_INFLIGHT; - req->work.flags &= ~IO_WQ_WORK_FILES; - if (atomic_read(&tctx->in_idle)) - wake_up(&tctx->wait); -} - -static void __io_clean_op(struct io_kiocb *req) +static void io_clean_op(struct io_kiocb *req) { if (req->flags & REQ_F_BUFFER_SELECTED) { switch (req->opcode) { @@ -5965,7 +6487,6 @@ static void __io_clean_op(struct io_kiocb *req) kfree(req->sr_msg.kbuf); break; } - req->flags &= ~REQ_F_BUFFER_SELECTED; } if (req->flags & REQ_F_NEED_CLEANUP) { @@ -5977,588 +6498,423 @@ static void __io_clean_op(struct io_kiocb *req) case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: { struct io_async_rw *io = req->async_data; - if (io->free_iovec) - kfree(io->free_iovec); + + kfree(io->free_iovec); break; } case IORING_OP_RECVMSG: case IORING_OP_SENDMSG: { struct io_async_msghdr *io = req->async_data; - if (io->iov != io->fast_iov) - kfree(io->iov); + + kfree(io->free_iov); break; } - case IORING_OP_SPLICE: - case IORING_OP_TEE: - io_put_file(req, req->splice.file_in, - (req->splice.flags & SPLICE_F_FD_IN_FIXED)); - break; case IORING_OP_OPENAT: case IORING_OP_OPENAT2: if (req->open.filename) putname(req->open.filename); break; + case IORING_OP_RENAMEAT: + putname(req->rename.oldpath); + putname(req->rename.newpath); + break; + case IORING_OP_UNLINKAT: + putname(req->unlink.filename); + break; } - req->flags &= ~REQ_F_NEED_CLEANUP; } + if ((req->flags & REQ_F_POLLED) && req->apoll) { + kfree(req->apoll->double_poll); + kfree(req->apoll); + req->apoll = NULL; + } + if (req->flags & REQ_F_INFLIGHT) { + struct io_uring_task *tctx = req->task->io_uring; + + atomic_dec(&tctx->inflight_tracked); + } + if (req->flags & REQ_F_CREDS) + put_cred(req->creds); + + req->flags &= ~IO_REQ_CLEAN_FLAGS; } -static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock, - struct io_comp_state *cs) +static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; + const struct cred *creds = NULL; int ret; + if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) + creds = override_creds(req->creds); + switch (req->opcode) { case IORING_OP_NOP: - ret = io_nop(req, cs); + ret = io_nop(req, issue_flags); break; case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: - ret = io_read(req, force_nonblock, cs); + ret = io_read(req, issue_flags); break; case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - ret = io_write(req, force_nonblock, cs); + ret = io_write(req, issue_flags); break; case IORING_OP_FSYNC: - ret = io_fsync(req, force_nonblock); + ret = io_fsync(req, issue_flags); break; case IORING_OP_POLL_ADD: - ret = io_poll_add(req); + ret = io_poll_add(req, issue_flags); break; case IORING_OP_POLL_REMOVE: - ret = io_poll_remove(req); + ret = io_poll_update(req, issue_flags); break; case IORING_OP_SYNC_FILE_RANGE: - ret = io_sync_file_range(req, force_nonblock); + ret = io_sync_file_range(req, issue_flags); break; case IORING_OP_SENDMSG: - ret = io_sendmsg(req, force_nonblock, cs); + ret = io_sendmsg(req, issue_flags); break; case IORING_OP_SEND: - ret = io_send(req, force_nonblock, cs); + ret = io_send(req, issue_flags); break; case IORING_OP_RECVMSG: - ret = io_recvmsg(req, force_nonblock, cs); + ret = io_recvmsg(req, issue_flags); break; case IORING_OP_RECV: - ret = io_recv(req, force_nonblock, cs); + ret = io_recv(req, issue_flags); break; case IORING_OP_TIMEOUT: - ret = io_timeout(req); + ret = io_timeout(req, issue_flags); break; case IORING_OP_TIMEOUT_REMOVE: - ret = io_timeout_remove(req); + ret = io_timeout_remove(req, issue_flags); break; case IORING_OP_ACCEPT: - ret = io_accept(req, force_nonblock, cs); + ret = io_accept(req, issue_flags); break; case IORING_OP_CONNECT: - ret = io_connect(req, force_nonblock, cs); + ret = io_connect(req, issue_flags); break; case IORING_OP_ASYNC_CANCEL: - ret = io_async_cancel(req); + ret = io_async_cancel(req, issue_flags); break; case IORING_OP_FALLOCATE: - ret = io_fallocate(req, force_nonblock); + ret = io_fallocate(req, issue_flags); break; case IORING_OP_OPENAT: - ret = io_openat(req, force_nonblock); + ret = io_openat(req, issue_flags); break; case IORING_OP_CLOSE: - ret = io_close(req, force_nonblock, cs); + ret = io_close(req, issue_flags); break; case IORING_OP_FILES_UPDATE: - ret = io_files_update(req, force_nonblock, cs); + ret = io_files_update(req, issue_flags); break; case IORING_OP_STATX: - ret = io_statx(req, force_nonblock); + ret = io_statx(req, issue_flags); break; case IORING_OP_FADVISE: - ret = io_fadvise(req, force_nonblock); + ret = io_fadvise(req, issue_flags); break; case IORING_OP_MADVISE: - ret = io_madvise(req, force_nonblock); + ret = io_madvise(req, issue_flags); break; case IORING_OP_OPENAT2: - ret = io_openat2(req, force_nonblock); + ret = io_openat2(req, issue_flags); break; case IORING_OP_EPOLL_CTL: - ret = io_epoll_ctl(req, force_nonblock, cs); + ret = io_epoll_ctl(req, issue_flags); break; case IORING_OP_SPLICE: - ret = io_splice(req, force_nonblock); + ret = io_splice(req, issue_flags); break; case IORING_OP_PROVIDE_BUFFERS: - ret = io_provide_buffers(req, force_nonblock, cs); + ret = io_provide_buffers(req, issue_flags); break; case IORING_OP_REMOVE_BUFFERS: - ret = io_remove_buffers(req, force_nonblock, cs); + ret = io_remove_buffers(req, issue_flags); break; case IORING_OP_TEE: - ret = io_tee(req, force_nonblock); + ret = io_tee(req, issue_flags); + break; + case IORING_OP_SHUTDOWN: + ret = io_shutdown(req, issue_flags); + break; + case IORING_OP_RENAMEAT: + ret = io_renameat(req, issue_flags); + break; + case IORING_OP_UNLINKAT: + ret = io_unlinkat(req, issue_flags); break; default: ret = -EINVAL; break; } + if (creds) + revert_creds(creds); if (ret) return ret; - /* If the op doesn't have a file, we're not polling for it */ - if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) { - const bool in_async = io_wq_current_is_worker(); - - /* workqueue context doesn't hold uring_lock, grab it now */ - if (in_async) - mutex_lock(&ctx->uring_lock); - + if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) io_iopoll_req_issued(req); - if (in_async) - mutex_unlock(&ctx->uring_lock); - } - return 0; } -static struct io_wq_work *io_wq_submit_work(struct io_wq_work *work) +static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) +{ + struct io_kiocb *req = container_of(work, struct io_kiocb, work); + + req = io_put_req_find_next(req); + return req ? &req->work : NULL; +} + +static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_kiocb *timeout; int ret = 0; + /* one will be dropped by ->io_free_work() after returning to io-wq */ + if (!(req->flags & REQ_F_REFCOUNT)) + __io_req_set_refcount(req, 2); + else + req_ref_get(req); + timeout = io_prep_linked_timeout(req); if (timeout) io_queue_linked_timeout(timeout); - /* if NO_CANCEL is set, we must still run the work */ - if ((work->flags & (IO_WQ_WORK_CANCEL|IO_WQ_WORK_NO_CANCEL)) == - IO_WQ_WORK_CANCEL) { + /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ + if (work->flags & IO_WQ_WORK_CANCEL) ret = -ECANCELED; - } if (!ret) { do { - ret = io_issue_sqe(req, false, NULL); + ret = io_issue_sqe(req, 0); /* * We can get EAGAIN for polled IO even though we're * forcing a sync submission from here, since we can't * wait for request slots on the block side. */ - if (ret != -EAGAIN) + if (ret != -EAGAIN || !(req->ctx->flags & IORING_SETUP_IOPOLL)) break; cond_resched(); } while (1); } - if (ret) { - struct io_ring_ctx *lock_ctx = NULL; + /* avoid locking problems by failing it from a clean context */ + if (ret) + io_req_task_queue_fail(req, ret); +} - if (req->ctx->flags & IORING_SETUP_IOPOLL) - lock_ctx = req->ctx; - - /* - * io_iopoll_complete() does not hold completion_lock to - * complete polled io, so here for polled io, we can not call - * io_req_complete() directly, otherwise there maybe concurrent - * access to cqring, defer_list, etc, which is not safe. Given - * that io_iopoll_complete() is always called under uring_lock, - * so here for polled io, we also get uring_lock to complete - * it. - */ - if (lock_ctx) - mutex_lock(&lock_ctx->uring_lock); - - req_set_fail_links(req); - io_req_complete(req, ret); - - if (lock_ctx) - mutex_unlock(&lock_ctx->uring_lock); - } - - return io_steal_work(req); +static inline struct io_fixed_file *io_fixed_file_slot(struct io_file_table *table, + unsigned i) +{ + return &table->files[i]; } static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, int index) { - struct fixed_file_table *table; + struct io_fixed_file *slot = io_fixed_file_slot(&ctx->file_table, index); - table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT]; - return table->files[index & IORING_FILE_TABLE_MASK]; + return (struct file *) (slot->file_ptr & FFS_MASK); } -static struct file *io_file_get(struct io_submit_state *state, - struct io_kiocb *req, int fd, bool fixed) +static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file) +{ + unsigned long file_ptr = (unsigned long) file; + + if (__io_file_supports_nowait(file, READ)) + file_ptr |= FFS_ASYNC_READ; + if (__io_file_supports_nowait(file, WRITE)) + file_ptr |= FFS_ASYNC_WRITE; + if (S_ISREG(file_inode(file)->i_mode)) + file_ptr |= FFS_ISREG; + file_slot->file_ptr = file_ptr; +} + +static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd) { - struct io_ring_ctx *ctx = req->ctx; struct file *file; + unsigned long file_ptr; - if (fixed) { - if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; - fd = array_index_nospec(fd, ctx->nr_user_files); - file = io_file_from_index(ctx, fd); - if (file) { - req->fixed_file_refs = &ctx->file_data->node->refs; - percpu_ref_get(req->fixed_file_refs); - } - } else { - trace_io_uring_file_get(ctx, fd); - file = __io_file_get(state, fd); - } - - if (file && file->f_op == &io_uring_fops && - !(req->flags & REQ_F_INFLIGHT)) { - io_req_init_async(req); - req->flags |= REQ_F_INFLIGHT; - - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); - } - + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) + return NULL; + fd = array_index_nospec(fd, ctx->nr_user_files); + file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; + file = (struct file *) (file_ptr & FFS_MASK); + file_ptr &= ~FFS_MASK; + /* mask in overlapping REQ_F and FFS bits */ + req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT); + io_req_set_rsrc_node(req); return file; } -static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, - int fd) +static struct file *io_file_get_normal(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd) { - bool fixed; + struct file *file = fget(fd); - fixed = (req->flags & REQ_F_FIXED_FILE) != 0; - if (unlikely(!fixed && io_async_submit(req->ctx))) - return -EBADF; + trace_io_uring_file_get(ctx, fd); - req->file = io_file_get(state, req, fd, fixed); - if (req->file || io_op_defs[req->opcode].needs_file_no_error) - return 0; - return -EBADF; + /* we don't allow fixed io_uring files */ + if (file && unlikely(file->f_op == &io_uring_fops)) + io_req_track_inflight(req); + return file; +} + +static inline struct file *io_file_get(struct io_ring_ctx *ctx, + struct io_kiocb *req, int fd, bool fixed) +{ + if (fixed) + return io_file_get_fixed(ctx, req, fd); + else + return io_file_get_normal(ctx, req, fd); +} + +static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) +{ + struct io_kiocb *prev = req->timeout.prev; + int ret = -ENOENT; + + if (prev) { + if (!(req->task->flags & PF_EXITING)) + ret = io_try_cancel_userdata(req, prev->user_data); + io_req_complete_post(req, ret ?: -ETIME, 0); + io_put_req(prev); + } else { + io_req_complete_post(req, -ETIME, 0); + } } static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) { struct io_timeout_data *data = container_of(timer, struct io_timeout_data, timer); - struct io_kiocb *req = data->req; + struct io_kiocb *prev, *req = data->req; struct io_ring_ctx *ctx = req->ctx; - struct io_kiocb *prev = NULL; unsigned long flags; - spin_lock_irqsave(&ctx->completion_lock, flags); + spin_lock_irqsave(&ctx->timeout_lock, flags); + prev = req->timeout.head; + req->timeout.head = NULL; /* * We don't expect the list to be empty, that will only happen if we * race with the completion of the linked work. */ - if (!list_empty(&req->link_list)) { - prev = list_entry(req->link_list.prev, struct io_kiocb, - link_list); - list_del_init(&req->link_list); - if (!refcount_inc_not_zero(&prev->refs)) + if (prev) { + io_remove_next_linked(prev); + if (!req_ref_inc_not_zero(prev)) prev = NULL; } - list_del(&req->timeout.list); - spin_unlock_irqrestore(&ctx->completion_lock, flags); + req->timeout.prev = prev; + spin_unlock_irqrestore(&ctx->timeout_lock, flags); - if (prev) { - io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME); - io_put_req_deferred(prev, 1); - } else { - io_cqring_add_event(req, -ETIME, 0); - io_put_req_deferred(req, 1); - } + req->io_task_work.func = io_req_task_link_timeout; + io_req_task_work_add(req); return HRTIMER_NORESTART; } -static void __io_queue_linked_timeout(struct io_kiocb *req) -{ - /* - * If the list is now empty, then our linked request finished before - * we got a chance to setup the timer - */ - if (!list_empty(&req->link_list)) { - struct io_timeout_data *data = req->async_data; - - data->timer.function = io_link_timeout_fn; - hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), - data->mode); - } -} - static void io_queue_linked_timeout(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - spin_lock_irq(&ctx->completion_lock); - __io_queue_linked_timeout(req); - spin_unlock_irq(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + /* + * If the back reference is NULL, then our linked request finished + * before we got a chance to setup the timer + */ + if (req->timeout.head) { + struct io_timeout_data *data = req->async_data; + data->timer.function = io_link_timeout_fn; + hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), + data->mode); + list_add_tail(&req->timeout.list, &ctx->ltimeout_list); + } + spin_unlock_irq(&ctx->timeout_lock); /* drop submission reference */ io_put_req(req); } -static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) -{ - struct io_kiocb *nxt; - - if (!(req->flags & REQ_F_LINK_HEAD)) - return NULL; - if (req->flags & REQ_F_LINK_TIMEOUT) - return NULL; - - nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, - link_list); - if (!nxt || nxt->opcode != IORING_OP_LINK_TIMEOUT) - return NULL; - - nxt->flags |= REQ_F_LTIMEOUT_ACTIVE; - req->flags |= REQ_F_LINK_TIMEOUT; - return nxt; -} - -static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs) +static void __io_queue_sqe(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) { struct io_kiocb *linked_timeout; - const struct cred *old_creds = NULL; int ret; -again: - linked_timeout = io_prep_linked_timeout(req); - - if ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_CREDS) && - req->work.identity->creds != current_cred()) { - if (old_creds) - revert_creds(old_creds); - if (old_creds == req->work.identity->creds) - old_creds = NULL; /* restored original creds */ - else - old_creds = override_creds(req->work.identity->creds); - } - - ret = io_issue_sqe(req, true, cs); +issue_sqe: + ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); /* * We async punt it if the file wasn't marked NOWAIT, or if the file * doesn't support non-blocking read/write attempts */ - if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { - if (!io_arm_poll_handler(req)) { + if (likely(!ret)) { + if (req->flags & REQ_F_COMPLETE_INLINE) { + struct io_ring_ctx *ctx = req->ctx; + struct io_submit_state *state = &ctx->submit_state; + + state->compl_reqs[state->compl_nr++] = req; + if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) + io_submit_flush_completions(ctx); + return; + } + + linked_timeout = io_prep_linked_timeout(req); + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); + } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { + linked_timeout = io_prep_linked_timeout(req); + + switch (io_arm_poll_handler(req)) { + case IO_APOLL_READY: + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); + goto issue_sqe; + case IO_APOLL_ABORTED: /* * Queued up for async execution, worker will release * submit reference when the iocb is actually submitted. */ - io_queue_async_work(req); + io_queue_async_work(req, NULL); + break; } if (linked_timeout) io_queue_linked_timeout(linked_timeout); - } else if (likely(!ret)) { - /* drop submission reference */ - req = io_put_req_find_next(req); - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); - - if (req) { - if (!(req->flags & REQ_F_FORCE_ASYNC)) - goto again; - io_queue_async_work(req); - } } else { - /* un-prep timeout, so it'll be killed as any other linked */ - req->flags &= ~REQ_F_LINK_TIMEOUT; - req_set_fail_links(req); - io_put_req(req); - io_req_complete(req, ret); - } - - if (old_creds) - revert_creds(old_creds); -} - -static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_comp_state *cs) -{ - int ret; - - ret = io_req_defer(req, sqe); - if (ret) { - if (ret != -EIOCBQUEUED) { -fail_req: - req_set_fail_links(req); - io_put_req(req); - io_req_complete(req, ret); - } - } else if (req->flags & REQ_F_FORCE_ASYNC) { - if (!req->async_data) { - ret = io_req_defer_prep(req, sqe); - if (unlikely(ret)) - goto fail_req; - } - io_queue_async_work(req); - } else { - if (sqe) { - ret = io_req_prep(req, sqe); - if (unlikely(ret)) - goto fail_req; - } - __io_queue_sqe(req, cs); + io_req_complete_failed(req, ret); } } -static inline void io_queue_link_head(struct io_kiocb *req, - struct io_comp_state *cs) +static inline void io_queue_sqe(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) { - if (unlikely(req->flags & REQ_F_FAIL_LINK)) { - io_put_req(req); - io_req_complete(req, -ECANCELED); - } else - io_queue_sqe(req, NULL, cs); -} + if (unlikely(req->ctx->drain_active) && io_drain_req(req)) + return; -static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **link, struct io_comp_state *cs) -{ - struct io_ring_ctx *ctx = req->ctx; - int ret; - - /* - * If we already have a head request, queue this one for async - * submittal once the head completes. If we don't have a head but - * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be - * submitted sync once the chain is complete. If none of those - * conditions are true (normal request), then just queue it. - */ - if (*link) { - struct io_kiocb *head = *link; - - /* - * Taking sequential execution of a link, draining both sides - * of the link also fullfils IOSQE_IO_DRAIN semantics for all - * requests in the link. So, it drains the head and the - * next after the link request. The last one is done via - * drain_next flag to persist the effect across calls. - */ - if (req->flags & REQ_F_IO_DRAIN) { - head->flags |= REQ_F_IO_DRAIN; - ctx->drain_next = 1; - } - ret = io_req_defer_prep(req, sqe); - if (unlikely(ret)) { - /* fail even hard links since we don't submit */ - head->flags |= REQ_F_FAIL_LINK; - return ret; - } - trace_io_uring_link(ctx, req, head); - list_add_tail(&req->link_list, &head->link_list); - - /* last request of a link, enqueue the link */ - if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { - io_queue_link_head(head, cs); - *link = NULL; - } + if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) { + __io_queue_sqe(req); + } else if (req->flags & REQ_F_FAIL) { + io_req_complete_fail_submit(req); } else { - if (unlikely(ctx->drain_next)) { - req->flags |= REQ_F_IO_DRAIN; - ctx->drain_next = 0; - } - if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { - req->flags |= REQ_F_LINK_HEAD; - INIT_LIST_HEAD(&req->link_list); + int ret = io_req_prep_async(req); - ret = io_req_defer_prep(req, sqe); - if (unlikely(ret)) - req->flags |= REQ_F_FAIL_LINK; - *link = req; - } else { - io_queue_sqe(req, sqe, cs); - } + if (unlikely(ret)) + io_req_complete_failed(req, ret); + else + io_queue_async_work(req, NULL); } - - return 0; -} - -/* - * Batched submission is done, ensure local IO is flushed out. - */ -static void io_submit_state_end(struct io_submit_state *state) -{ - if (!list_empty(&state->comp.list)) - io_submit_flush_completions(&state->comp); - blk_finish_plug(&state->plug); - io_state_file_put(state); - if (state->free_reqs) - kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs); -} - -/* - * Start submission side cache. - */ -static void io_submit_state_start(struct io_submit_state *state, - struct io_ring_ctx *ctx, unsigned int max_ios) -{ - blk_start_plug(&state->plug); - state->comp.nr = 0; - INIT_LIST_HEAD(&state->comp.list); - state->comp.ctx = ctx; - state->free_reqs = 0; - state->file = NULL; - state->ios_left = max_ios; -} - -static void io_commit_sqring(struct io_ring_ctx *ctx) -{ - struct io_rings *rings = ctx->rings; - - /* - * Ensure any loads from the SQEs are done at this point, - * since once we write the new head, the application could - * write new data to them. - */ - smp_store_release(&rings->sq.head, ctx->cached_sq_head); -} - -/* - * Fetch an sqe, if one is available. Note that sqe_ptr will point to memory - * that is mapped by userspace. This means that care needs to be taken to - * ensure that reads are stable, as we cannot rely on userspace always - * being a good citizen. If members of the sqe are validated and then later - * used, it's important that those reads are done through READ_ONCE() to - * prevent a re-load down the line. - */ -static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) -{ - u32 *sq_array = ctx->sq_array; - unsigned head; - - /* - * The cached sq head (or cq tail) serves two purposes: - * - * 1) allows us to batch the cost of updating the user visible - * head updates. - * 2) allows the kernel side to track the head on its own, even - * though the application is the one updating it. - */ - head = READ_ONCE(sq_array[ctx->cached_sq_head & ctx->sq_mask]); - if (likely(head < ctx->sq_entries)) - return &ctx->sq_sqes[head]; - - /* drop invalid entries */ - ctx->cached_sq_dropped++; - WRITE_ONCE(ctx->rings->sq_dropped, ctx->cached_sq_dropped); - return NULL; -} - -static inline void io_consume_sqe(struct io_ring_ctx *ctx) -{ - ctx->cached_sq_head++; } /* @@ -6570,7 +6926,7 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx, struct io_kiocb *req, unsigned int sqe_flags) { - if (!ctx->restricted) + if (likely(!ctx->restricted)) return true; if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) @@ -6587,382 +6943,459 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx, return true; } -#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ - IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ - IOSQE_BUFFER_SELECT) - static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct io_uring_sqe *sqe, - struct io_submit_state *state) + const struct io_uring_sqe *sqe) + __must_hold(&ctx->uring_lock) { + struct io_submit_state *state; unsigned int sqe_flags; - int id, ret; + int personality, ret = 0; + /* req is partially pre-initialised, see io_preinit_req() */ req->opcode = READ_ONCE(sqe->opcode); + /* same numerical values with corresponding REQ_F_*, safe to copy */ + req->flags = sqe_flags = READ_ONCE(sqe->flags); req->user_data = READ_ONCE(sqe->user_data); - req->async_data = NULL; req->file = NULL; - req->ctx = ctx; - req->flags = 0; - /* one is dropped after submission, the other at completion */ - refcount_set(&req->refs, 2); + req->fixed_rsrc_refs = NULL; req->task = current; - req->result = 0; - if (unlikely(req->opcode >= IORING_OP_LAST)) - return -EINVAL; - - if (unlikely(io_sq_thread_acquire_mm(ctx, req))) - return -EFAULT; - - sqe_flags = READ_ONCE(sqe->flags); /* enforce forwards compatibility on users */ if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) return -EINVAL; - - if (unlikely(!io_check_restriction(ctx, req, sqe_flags))) + if (unlikely(req->opcode >= IORING_OP_LAST)) + return -EINVAL; + if (!io_check_restriction(ctx, req, sqe_flags)) return -EACCES; if ((sqe_flags & IOSQE_BUFFER_SELECT) && !io_op_defs[req->opcode].buffer_select) return -EOPNOTSUPP; + if (unlikely(sqe_flags & IOSQE_IO_DRAIN)) + ctx->drain_active = true; - id = READ_ONCE(sqe->personality); - if (id) { - struct io_identity *iod; - - iod = xa_load(&ctx->personalities, id); - if (unlikely(!iod)) + personality = READ_ONCE(sqe->personality); + if (personality) { + req->creds = xa_load(&ctx->personalities, personality); + if (!req->creds) return -EINVAL; - refcount_inc(&iod->count); + get_cred(req->creds); + req->flags |= REQ_F_CREDS; + } + state = &ctx->submit_state; - __io_req_init_async(req); - get_cred(iod->creds); - req->work.identity = iod; - req->work.flags |= IO_WQ_WORK_CREDS; + /* + * Plug now if we have more than 1 IO left after this, and the target + * is potentially a read/write to block based storage. + */ + if (!state->plug_started && state->ios_left > 1 && + io_op_defs[req->opcode].plug) { + blk_start_plug(&state->plug); + state->plug_started = true; } - /* same numerical values with corresponding REQ_F_*, safe to copy */ - req->flags |= sqe_flags; + if (io_op_defs[req->opcode].needs_file) { + req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), + (sqe_flags & IOSQE_FIXED_FILE)); + if (unlikely(!req->file)) + ret = -EBADF; + } - if (!io_op_defs[req->opcode].needs_file) - return 0; - - ret = io_req_set_file(state, req, READ_ONCE(sqe->fd)); state->ios_left--; return ret; } -static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) +static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe *sqe) + __must_hold(&ctx->uring_lock) { - struct io_submit_state state; - struct io_kiocb *link = NULL; - int i, submitted = 0; + struct io_submit_link *link = &ctx->submit_state.link; + int ret; - /* if we have a backlog and couldn't flush it all, return BUSY */ - if (test_bit(0, &ctx->sq_check_overflow)) { - if (!__io_cqring_overflow_flush(ctx, false, NULL, NULL)) - return -EBUSY; + ret = io_init_req(ctx, req, sqe); + if (unlikely(ret)) { +fail_req: + /* fail even hard links since we don't submit */ + if (link->head) { + /* + * we can judge a link req is failed or cancelled by if + * REQ_F_FAIL is set, but the head is an exception since + * it may be set REQ_F_FAIL because of other req's failure + * so let's leverage req->result to distinguish if a head + * is set REQ_F_FAIL because of its failure or other req's + * failure so that we can set the correct ret code for it. + * init result here to avoid affecting the normal path. + */ + if (!(link->head->flags & REQ_F_FAIL)) + req_fail_link_node(link->head, -ECANCELED); + } else if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { + /* + * the current req is a normal req, we should return + * error and thus break the submittion loop. + */ + io_req_complete_failed(req, ret); + return ret; + } + req_fail_link_node(req, ret); + } else { + ret = io_req_prep(req, sqe); + if (unlikely(ret)) + goto fail_req; } + /* don't need @sqe from now on */ + trace_io_uring_submit_sqe(ctx, req, req->opcode, req->user_data, + req->flags, true, + ctx->flags & IORING_SETUP_SQPOLL); + + /* + * If we already have a head request, queue this one for async + * submittal once the head completes. If we don't have a head but + * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be + * submitted sync once the chain is complete. If none of those + * conditions are true (normal request), then just queue it. + */ + if (link->head) { + struct io_kiocb *head = link->head; + + if (!(req->flags & REQ_F_FAIL)) { + ret = io_req_prep_async(req); + if (unlikely(ret)) { + req_fail_link_node(req, ret); + if (!(head->flags & REQ_F_FAIL)) + req_fail_link_node(head, -ECANCELED); + } + } + trace_io_uring_link(ctx, req, head); + link->last->link = req; + link->last = req; + + /* last request of a link, enqueue the link */ + if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { + link->head = NULL; + io_queue_sqe(head); + } + } else { + if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { + link->head = req; + link->last = req; + } else { + io_queue_sqe(req); + } + } + + return 0; +} + +/* + * Batched submission is done, ensure local IO is flushed out. + */ +static void io_submit_state_end(struct io_submit_state *state, + struct io_ring_ctx *ctx) +{ + if (state->link.head) + io_queue_sqe(state->link.head); + if (state->compl_nr) + io_submit_flush_completions(ctx); + if (state->plug_started) + blk_finish_plug(&state->plug); +} + +/* + * Start submission side cache. + */ +static void io_submit_state_start(struct io_submit_state *state, + unsigned int max_ios) +{ + state->plug_started = false; + state->ios_left = max_ios; + /* set only head, no need to init link_last in advance */ + state->link.head = NULL; +} + +static void io_commit_sqring(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = ctx->rings; + + /* + * Ensure any loads from the SQEs are done at this point, + * since once we write the new head, the application could + * write new data to them. + */ + smp_store_release(&rings->sq.head, ctx->cached_sq_head); +} + +/* + * Fetch an sqe, if one is available. Note this returns a pointer to memory + * that is mapped by userspace. This means that care needs to be taken to + * ensure that reads are stable, as we cannot rely on userspace always + * being a good citizen. If members of the sqe are validated and then later + * used, it's important that those reads are done through READ_ONCE() to + * prevent a re-load down the line. + */ +static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) +{ + unsigned head, mask = ctx->sq_entries - 1; + unsigned sq_idx = ctx->cached_sq_head++ & mask; + + /* + * The cached sq head (or cq tail) serves two purposes: + * + * 1) allows us to batch the cost of updating the user visible + * head updates. + * 2) allows the kernel side to track the head on its own, even + * though the application is the one updating it. + */ + head = READ_ONCE(ctx->sq_array[sq_idx]); + if (likely(head < ctx->sq_entries)) + return &ctx->sq_sqes[head]; + + /* drop invalid entries */ + ctx->cq_extra--; + WRITE_ONCE(ctx->rings->sq_dropped, + READ_ONCE(ctx->rings->sq_dropped) + 1); + return NULL; +} + +static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) + __must_hold(&ctx->uring_lock) +{ + int submitted = 0; + /* make sure SQ entry isn't read before tail */ nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx)); - if (!percpu_ref_tryget_many(&ctx->refs, nr)) return -EAGAIN; + io_get_task_refs(nr); - percpu_counter_add(¤t->io_uring->inflight, nr); - refcount_add(nr, ¤t->usage); - - io_submit_state_start(&state, ctx, nr); - - for (i = 0; i < nr; i++) { + io_submit_state_start(&ctx->submit_state, nr); + while (submitted < nr) { const struct io_uring_sqe *sqe; struct io_kiocb *req; - int err; - sqe = io_get_sqe(ctx); - if (unlikely(!sqe)) { - io_consume_sqe(ctx); - break; - } - req = io_alloc_req(ctx, &state); + req = io_alloc_req(ctx); if (unlikely(!req)) { if (!submitted) submitted = -EAGAIN; break; } - io_consume_sqe(ctx); - /* will complete beyond this point, count as submitted */ - submitted++; - - err = io_init_req(ctx, req, sqe, &state); - if (unlikely(err)) { -fail_req: - io_put_req(req); - io_req_complete(req, err); + sqe = io_get_sqe(ctx); + if (unlikely(!sqe)) { + list_add(&req->inflight_entry, &ctx->submit_state.free_list); break; } - - trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data, - true, io_async_submit(ctx)); - err = io_submit_sqe(req, sqe, &link, &state.comp); - if (err) - goto fail_req; + /* will complete beyond this point, count as submitted */ + submitted++; + if (io_submit_sqe(ctx, req, sqe)) + break; } if (unlikely(submitted != nr)) { int ref_used = (submitted == -EAGAIN) ? 0 : submitted; - struct io_uring_task *tctx = current->io_uring; int unused = nr - ref_used; + current->io_uring->cached_refs += unused; percpu_ref_put_many(&ctx->refs, unused); - percpu_counter_sub(&tctx->inflight, unused); - put_task_struct_many(current, unused); } - if (link) - io_queue_link_head(link, &state.comp); - io_submit_state_end(&state); + io_submit_state_end(&ctx->submit_state, ctx); /* Commit SQ ring head once we've consumed and submitted all SQEs */ io_commit_sqring(ctx); return submitted; } +static inline bool io_sqd_events_pending(struct io_sq_data *sqd) +{ + return READ_ONCE(sqd->state); +} + static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) { /* Tell userspace we may need a wakeup call */ - spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP; - spin_unlock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP); + spin_unlock(&ctx->completion_lock); } static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) { - spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; - spin_unlock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP); + spin_unlock(&ctx->completion_lock); } -static int io_sq_wake_function(struct wait_queue_entry *wqe, unsigned mode, - int sync, void *key) +static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) { - struct io_ring_ctx *ctx = container_of(wqe, struct io_ring_ctx, sqo_wait_entry); - int ret; - - ret = autoremove_wake_function(wqe, mode, sync, key); - if (ret) { - unsigned long flags; - - spin_lock_irqsave(&ctx->completion_lock, flags); - ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; - spin_unlock_irqrestore(&ctx->completion_lock, flags); - } - return ret; -} - -enum sq_ret { - SQT_IDLE = 1, - SQT_SPIN = 2, - SQT_DID_WORK = 4, -}; - -static enum sq_ret __io_sq_thread(struct io_ring_ctx *ctx, - unsigned long start_jiffies, bool cap_entries) -{ - unsigned long timeout = start_jiffies + ctx->sq_thread_idle; - struct io_sq_data *sqd = ctx->sq_data; unsigned int to_submit; int ret = 0; -again: - if (!list_empty(&ctx->iopoll_list)) { + to_submit = io_sqring_entries(ctx); + /* if we're handling multiple rings, cap submit size for fairness */ + if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE) + to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE; + + if (!list_empty(&ctx->iopoll_list) || to_submit) { unsigned nr_events = 0; + const struct cred *creds = NULL; + + if (ctx->sq_creds != current_cred()) + creds = override_creds(ctx->sq_creds); mutex_lock(&ctx->uring_lock); - if (!list_empty(&ctx->iopoll_list) && !need_resched()) + if (!list_empty(&ctx->iopoll_list)) io_do_iopoll(ctx, &nr_events, 0); + + /* + * Don't submit if refs are dying, good for io_uring_register(), + * but also it is relied upon by io_ring_exit_work() + */ + if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) && + !(ctx->flags & IORING_SETUP_R_DISABLED)) + ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); + + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) + wake_up(&ctx->sqo_sq_wait); + if (creds) + revert_creds(creds); } - to_submit = io_sqring_entries(ctx); - - /* - * If submit got -EBUSY, flag us as needing the application - * to enter the kernel to reap and flush events. - */ - if (!to_submit || ret == -EBUSY || need_resched()) { - /* - * Drop cur_mm before scheduling, we can't hold it for - * long periods (or over schedule()). Do this before - * adding ourselves to the waitqueue, as the unuse/drop - * may sleep. - */ - io_sq_thread_drop_mm(); - - /* - * We're polling. If we're within the defined idle - * period, then let us spin without work before going - * to sleep. The exception is if we got EBUSY doing - * more IO, we should wait for the application to - * reap events and wake us up. - */ - if (!list_empty(&ctx->iopoll_list) || need_resched() || - (!time_after(jiffies, timeout) && ret != -EBUSY && - !percpu_ref_is_dying(&ctx->refs))) - return SQT_SPIN; - - prepare_to_wait(&sqd->wait, &ctx->sqo_wait_entry, - TASK_INTERRUPTIBLE); - - /* - * While doing polled IO, before going to sleep, we need - * to check if there are new reqs added to iopoll_list, - * it is because reqs may have been punted to io worker - * and will be added to iopoll_list later, hence check - * the iopoll_list again. - */ - if ((ctx->flags & IORING_SETUP_IOPOLL) && - !list_empty_careful(&ctx->iopoll_list)) { - finish_wait(&sqd->wait, &ctx->sqo_wait_entry); - goto again; - } - - to_submit = io_sqring_entries(ctx); - if (!to_submit || ret == -EBUSY) - return SQT_IDLE; - } - - finish_wait(&sqd->wait, &ctx->sqo_wait_entry); - io_ring_clear_wakeup_flag(ctx); - - /* if we're handling multiple rings, cap submit size for fairness */ - if (cap_entries && to_submit > 8) - to_submit = 8; - - mutex_lock(&ctx->uring_lock); - if (likely(!percpu_ref_is_dying(&ctx->refs) && !ctx->sqo_dead)) - ret = io_submit_sqes(ctx, to_submit); - mutex_unlock(&ctx->uring_lock); - - if (!io_sqring_full(ctx) && wq_has_sleeper(&ctx->sqo_sq_wait)) - wake_up(&ctx->sqo_sq_wait); - - return SQT_DID_WORK; + return ret; } -static void io_sqd_init_new(struct io_sq_data *sqd) +static void io_sqd_update_thread_idle(struct io_sq_data *sqd) { struct io_ring_ctx *ctx; + unsigned sq_thread_idle = 0; - while (!list_empty(&sqd->ctx_new_list)) { - ctx = list_first_entry(&sqd->ctx_new_list, struct io_ring_ctx, sqd_list); - init_wait(&ctx->sqo_wait_entry); - ctx->sqo_wait_entry.func = io_sq_wake_function; - list_move_tail(&ctx->sqd_list, &sqd->ctx_list); - complete(&ctx->sq_thread_comp); + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle); + sqd->sq_thread_idle = sq_thread_idle; +} + +static bool io_sqd_handle_event(struct io_sq_data *sqd) +{ + bool did_sig = false; + struct ksignal ksig; + + if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || + signal_pending(current)) { + mutex_unlock(&sqd->lock); + if (signal_pending(current)) + did_sig = get_signal(&ksig); + cond_resched(); + mutex_lock(&sqd->lock); } + return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); } static int io_sq_thread(void *data) { - struct cgroup_subsys_state *cur_css = NULL; - const struct cred *old_cred = NULL; struct io_sq_data *sqd = data; struct io_ring_ctx *ctx; - unsigned long start_jiffies; + unsigned long timeout = 0; + char buf[TASK_COMM_LEN]; + DEFINE_WAIT(wait); - start_jiffies = jiffies; - while (!kthread_should_stop()) { - enum sq_ret ret = 0; - bool cap_entries; + snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); + set_task_comm(current, buf); - /* - * Any changes to the sqd lists are synchronized through the - * kthread parking. This synchronizes the thread vs users, - * the users are synchronized on the sqd->ctx_lock. - */ - if (kthread_should_park()) { - kthread_parkme(); - /* - * When sq thread is unparked, in case the previous park operation - * comes from io_put_sq_data(), which means that sq thread is going - * to be stopped, so here needs to have a check. - */ - if (kthread_should_stop()) + if (sqd->sq_cpu != -1) + set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); + else + set_cpus_allowed_ptr(current, cpu_online_mask); + current->flags |= PF_NO_SETAFFINITY; + + mutex_lock(&sqd->lock); + while (1) { + bool cap_entries, sqt_spin = false; + + if (io_sqd_events_pending(sqd) || signal_pending(current)) { + if (io_sqd_handle_event(sqd)) break; + timeout = jiffies + sqd->sq_thread_idle; } - if (unlikely(!list_empty(&sqd->ctx_new_list))) - io_sqd_init_new(sqd); - cap_entries = !list_is_singular(&sqd->ctx_list); - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { - if (current->cred != ctx->creds) { - if (old_cred) - revert_creds(old_cred); - old_cred = override_creds(ctx->creds); - } - io_sq_thread_associate_blkcg(ctx, &cur_css); -#ifdef CONFIG_AUDIT - current->loginuid = ctx->loginuid; - current->sessionid = ctx->sessionid; -#endif + int ret = __io_sq_thread(ctx, cap_entries); - ret |= __io_sq_thread(ctx, start_jiffies, cap_entries); + if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list))) + sqt_spin = true; + } + if (io_run_task_work()) + sqt_spin = true; - io_sq_thread_drop_mm(); + if (sqt_spin || !time_after(jiffies, timeout)) { + cond_resched(); + if (sqt_spin) + timeout = jiffies + sqd->sq_thread_idle; + continue; } - if (ret & SQT_SPIN) { - io_run_task_work(); - io_sq_thread_drop_mm(); - cond_resched(); - } else if (ret == SQT_IDLE) { - if (kthread_should_park()) - continue; - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); + if (!io_sqd_events_pending(sqd) && !current->task_works) { + bool needs_sched = true; + + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { io_ring_set_wakeup_flag(ctx); - schedule(); - start_jiffies = jiffies; + + if ((ctx->flags & IORING_SETUP_IOPOLL) && + !list_empty_careful(&ctx->iopoll_list)) { + needs_sched = false; + break; + } + if (io_sqring_entries(ctx)) { + needs_sched = false; + break; + } + } + + if (needs_sched) { + mutex_unlock(&sqd->lock); + schedule(); + mutex_lock(&sqd->lock); + } list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_clear_wakeup_flag(ctx); } + + finish_wait(&sqd->wait, &wait); + timeout = jiffies + sqd->sq_thread_idle; } + io_uring_cancel_generic(true, sqd); + sqd->thread = NULL; + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + io_ring_set_wakeup_flag(ctx); io_run_task_work(); - io_sq_thread_drop_mm(); + mutex_unlock(&sqd->lock); - if (cur_css) - io_sq_thread_unassociate_blkcg(); - if (old_cred) - revert_creds(old_cred); - - kthread_parkme(); - - return 0; + complete(&sqd->exited); + do_exit(0); } struct io_wait_queue { struct wait_queue_entry wq; struct io_ring_ctx *ctx; - unsigned to_wait; + unsigned cq_tail; unsigned nr_timeouts; }; static inline bool io_should_wake(struct io_wait_queue *iowq) { struct io_ring_ctx *ctx = iowq->ctx; + int dist = ctx->cached_cq_tail - (int) iowq->cq_tail; /* * Wake up if we have enough events, or if a timeout occurred since we * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ - return io_cqring_events(ctx) >= iowq->to_wait || - atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; + return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; } static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, @@ -6975,7 +7408,7 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, * Cannot safely flush overflowed CQEs from here, ensure we wake up * the task, and the next invocation will do it. */ - if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->cq_check_overflow)) + if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->check_cq_overflow)) return autoremove_wake_function(curr, mode, wake_flags, key); return -1; } @@ -6986,43 +7419,60 @@ static int io_run_task_work_sig(void) return 1; if (!signal_pending(current)) return 0; - if (current->jobctl & JOBCTL_TASK_WORK) { - spin_lock_irq(¤t->sighand->siglock); - current->jobctl &= ~JOBCTL_TASK_WORK; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - return 1; - } + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) + return -ERESTARTSYS; return -EINTR; } +/* when returns >0, the caller should retry */ +static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq, + ktime_t timeout) +{ + int ret; + + /* make sure we run task_work before checking for signals */ + ret = io_run_task_work_sig(); + if (ret || io_should_wake(iowq)) + return ret; + /* let the caller flush overflows, retry */ + if (test_bit(0, &ctx->check_cq_overflow)) + return 1; + + if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) + return -ETIME; + return 1; +} + /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. */ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, - const sigset_t __user *sig, size_t sigsz) + const sigset_t __user *sig, size_t sigsz, + struct __kernel_timespec __user *uts) { - struct io_wait_queue iowq = { - .wq = { - .private = current, - .func = io_wake_function, - .entry = LIST_HEAD_INIT(iowq.wq.entry), - }, - .ctx = ctx, - .to_wait = min_events, - }; + struct io_wait_queue iowq; struct io_rings *rings = ctx->rings; - int ret = 0; + ktime_t timeout = KTIME_MAX; + int ret; do { - io_cqring_overflow_flush(ctx, false, NULL, NULL); + io_cqring_overflow_flush(ctx); if (io_cqring_events(ctx) >= min_events) return 0; if (!io_run_task_work()) break; } while (1); + if (uts) { + struct timespec64 ts; + + if (get_timespec64(&ts, uts)) + return -EFAULT; + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); + } + if (sig) { #ifdef CONFIG_COMPAT if (in_compat_syscall()) @@ -7036,35 +7486,269 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } + init_waitqueue_func_entry(&iowq.wq, io_wake_function); + iowq.wq.private = current; + INIT_LIST_HEAD(&iowq.wq.entry); + iowq.ctx = ctx; iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); + iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; + trace_io_uring_cqring_wait(ctx, min_events); do { - io_cqring_overflow_flush(ctx, false, NULL, NULL); - prepare_to_wait_exclusive(&ctx->wait, &iowq.wq, + /* if we can't even flush overflow, don't wait for more */ + if (!io_cqring_overflow_flush(ctx)) { + ret = -EBUSY; + break; + } + prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); - /* make sure we run task_work before checking for signals */ - ret = io_run_task_work_sig(); - if (ret > 0) { - finish_wait(&ctx->wait, &iowq.wq); - continue; - } - else if (ret < 0) - break; - if (io_should_wake(&iowq)) - break; - if (test_bit(0, &ctx->cq_check_overflow)) { - finish_wait(&ctx->wait, &iowq.wq); - continue; - } - schedule(); - } while (1); - finish_wait(&ctx->wait, &iowq.wq); + ret = io_cqring_wait_schedule(ctx, &iowq, timeout); + finish_wait(&ctx->cq_wait, &iowq.wq); + cond_resched(); + } while (ret > 0); restore_saved_sigmask_unless(ret == -EINTR); return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; } +static void io_free_page_table(void **table, size_t size) +{ + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); + + for (i = 0; i < nr_tables; i++) + kfree(table[i]); + kfree(table); +} + +static void **io_alloc_page_table(size_t size) +{ + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); + size_t init_size = size; + void **table; + + table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL_ACCOUNT); + if (!table) + return NULL; + + for (i = 0; i < nr_tables; i++) { + unsigned int this_size = min_t(size_t, size, PAGE_SIZE); + + table[i] = kzalloc(this_size, GFP_KERNEL_ACCOUNT); + if (!table[i]) { + io_free_page_table(table, init_size); + return NULL; + } + size -= this_size; + } + return table; +} + +static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) +{ + percpu_ref_exit(&ref_node->refs); + kfree(ref_node); +} + +static void io_rsrc_node_ref_zero(struct percpu_ref *ref) +{ + struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); + struct io_ring_ctx *ctx = node->rsrc_data->ctx; + unsigned long flags; + bool first_add = false; + unsigned long delay = HZ; + + spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); + node->done = true; + + /* if we are mid-quiesce then do not delay */ + if (node->rsrc_data->quiesce) + delay = 0; + + while (!list_empty(&ctx->rsrc_ref_list)) { + node = list_first_entry(&ctx->rsrc_ref_list, + struct io_rsrc_node, node); + /* recycle ref nodes in order */ + if (!node->done) + break; + list_del(&node->node); + first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist); + } + spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); + + if (first_add) + mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay); +} + +static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx) +{ + struct io_rsrc_node *ref_node; + + ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); + if (!ref_node) + return NULL; + + if (percpu_ref_init(&ref_node->refs, io_rsrc_node_ref_zero, + 0, GFP_KERNEL)) { + kfree(ref_node); + return NULL; + } + INIT_LIST_HEAD(&ref_node->node); + INIT_LIST_HEAD(&ref_node->rsrc_list); + ref_node->done = false; + return ref_node; +} + +static void io_rsrc_node_switch(struct io_ring_ctx *ctx, + struct io_rsrc_data *data_to_kill) +{ + WARN_ON_ONCE(!ctx->rsrc_backup_node); + WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node); + + if (data_to_kill) { + struct io_rsrc_node *rsrc_node = ctx->rsrc_node; + + rsrc_node->rsrc_data = data_to_kill; + spin_lock_irq(&ctx->rsrc_ref_lock); + list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list); + spin_unlock_irq(&ctx->rsrc_ref_lock); + + atomic_inc(&data_to_kill->refs); + percpu_ref_kill(&rsrc_node->refs); + ctx->rsrc_node = NULL; + } + + if (!ctx->rsrc_node) { + ctx->rsrc_node = ctx->rsrc_backup_node; + ctx->rsrc_backup_node = NULL; + } +} + +static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx) +{ + if (ctx->rsrc_backup_node) + return 0; + ctx->rsrc_backup_node = io_rsrc_node_alloc(ctx); + return ctx->rsrc_backup_node ? 0 : -ENOMEM; +} + +static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ctx) +{ + int ret; + + /* As we may drop ->uring_lock, other task may have started quiesce */ + if (data->quiesce) + return -ENXIO; + + data->quiesce = true; + do { + ret = io_rsrc_node_switch_start(ctx); + if (ret) + break; + io_rsrc_node_switch(ctx, data); + + /* kill initial ref, already quiesced if zero */ + if (atomic_dec_and_test(&data->refs)) + break; + mutex_unlock(&ctx->uring_lock); + flush_delayed_work(&ctx->rsrc_put_work); + ret = wait_for_completion_interruptible(&data->done); + if (!ret) { + mutex_lock(&ctx->uring_lock); + if (atomic_read(&data->refs) > 0) { + /* + * it has been revived by another thread while + * we were unlocked + */ + mutex_unlock(&ctx->uring_lock); + } else { + break; + } + } + + atomic_inc(&data->refs); + /* wait for all works potentially completing data->done */ + flush_delayed_work(&ctx->rsrc_put_work); + reinit_completion(&data->done); + + ret = io_run_task_work_sig(); + mutex_lock(&ctx->uring_lock); + } while (ret >= 0); + data->quiesce = false; + + return ret; +} + +static u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) +{ + unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK; + unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT; + + return &data->tags[table_idx][off]; +} + +static void io_rsrc_data_free(struct io_rsrc_data *data) +{ + size_t size = data->nr * sizeof(data->tags[0][0]); + + if (data->tags) + io_free_page_table((void **)data->tags, size); + kfree(data); +} + +static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put, + u64 __user *utags, unsigned nr, + struct io_rsrc_data **pdata) +{ + struct io_rsrc_data *data; + int ret = -ENOMEM; + unsigned i; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0])); + if (!data->tags) { + kfree(data); + return -ENOMEM; + } + + data->nr = nr; + data->ctx = ctx; + data->do_put = do_put; + if (utags) { + ret = -EFAULT; + for (i = 0; i < nr; i++) { + u64 *tag_slot = io_get_tag_slot(data, i); + + if (copy_from_user(tag_slot, &utags[i], + sizeof(*tag_slot))) + goto fail; + } + } + + atomic_set(&data->refs, 1); + init_completion(&data->done); + *pdata = data; + return 0; +fail: + io_rsrc_data_free(data); + return ret; +} + +static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) +{ + table->files = kvcalloc(nr_files, sizeof(table->files[0]), + GFP_KERNEL_ACCOUNT); + return !!table->files; +} + +static void io_free_file_tables(struct io_file_table *table) +{ + kvfree(table->files); + table->files = NULL; +} + static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) { #if defined(CONFIG_UNIX) @@ -7086,129 +7770,97 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) fput(file); } #endif -} - -static void io_file_ref_kill(struct percpu_ref *ref) -{ - struct fixed_file_data *data; - - data = container_of(ref, struct fixed_file_data, refs); - complete(&data->done); -} - -static void io_sqe_files_set_node(struct fixed_file_data *file_data, - struct fixed_file_ref_node *ref_node) -{ - spin_lock_bh(&file_data->lock); - file_data->node = ref_node; - list_add_tail(&ref_node->node, &file_data->ref_list); - spin_unlock_bh(&file_data->lock); - percpu_ref_get(&file_data->refs); -} - - -static void io_sqe_files_kill_node(struct fixed_file_data *data) -{ - struct fixed_file_ref_node *ref_node = NULL; - - spin_lock_bh(&data->lock); - ref_node = data->node; - spin_unlock_bh(&data->lock); - if (ref_node) - percpu_ref_kill(&ref_node->refs); -} - -static int io_file_ref_quiesce(struct fixed_file_data *data, - struct io_ring_ctx *ctx) -{ - int ret; - struct fixed_file_ref_node *backup_node; - - if (data->quiesce) - return -ENXIO; - - data->quiesce = true; - do { - backup_node = alloc_fixed_file_ref_node(ctx); - if (!backup_node) - break; - - io_sqe_files_kill_node(data); - percpu_ref_kill(&data->refs); - flush_delayed_work(&ctx->file_put_work); - - ret = wait_for_completion_interruptible(&data->done); - if (!ret) - break; - - percpu_ref_resurrect(&data->refs); - io_sqe_files_set_node(data, backup_node); - backup_node = NULL; - reinit_completion(&data->done); - mutex_unlock(&ctx->uring_lock); - ret = io_run_task_work_sig(); - mutex_lock(&ctx->uring_lock); - - if (ret < 0) - break; - backup_node = alloc_fixed_file_ref_node(ctx); - ret = -ENOMEM; - if (!backup_node) - break; - } while (1); - data->quiesce = false; - - if (backup_node) - destroy_fixed_file_ref_node(backup_node); - return ret; + io_free_file_tables(&ctx->file_table); + io_rsrc_data_free(ctx->file_data); + ctx->file_data = NULL; + ctx->nr_user_files = 0; } static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { - struct fixed_file_data *data = ctx->file_data; - unsigned nr_tables, i; + unsigned nr = ctx->nr_user_files; int ret; - /* - * percpu_ref_is_dying() is to stop parallel files unregister - * Since we possibly drop uring lock later in this function to - * run task work. - */ - if (!data || percpu_ref_is_dying(&data->refs)) + if (!ctx->file_data) return -ENXIO; - ret = io_file_ref_quiesce(data, ctx); - if (ret) - return ret; - __io_sqe_files_unregister(ctx); - nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); - for (i = 0; i < nr_tables; i++) - kfree(data->table[i].files); - kfree(data->table); - percpu_ref_exit(&data->refs); - kfree(data); - ctx->file_data = NULL; + /* + * Quiesce may unlock ->uring_lock, and while it's not held + * prevent new requests using the table. + */ ctx->nr_user_files = 0; - return 0; + ret = io_rsrc_ref_quiesce(ctx->file_data, ctx); + ctx->nr_user_files = nr; + if (!ret) + __io_sqe_files_unregister(ctx); + return ret; +} + +static void io_sq_thread_unpark(struct io_sq_data *sqd) + __releases(&sqd->lock) +{ + WARN_ON_ONCE(sqd->thread == current); + + /* + * Do the dance but not conditional clear_bit() because it'd race with + * other threads incrementing park_pending and setting the bit. + */ + clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + if (atomic_dec_return(&sqd->park_pending)) + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_unlock(&sqd->lock); +} + +static void io_sq_thread_park(struct io_sq_data *sqd) + __acquires(&sqd->lock) +{ + WARN_ON_ONCE(sqd->thread == current); + + atomic_inc(&sqd->park_pending); + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_lock(&sqd->lock); + if (sqd->thread) + wake_up_process(sqd->thread); +} + +static void io_sq_thread_stop(struct io_sq_data *sqd) +{ + WARN_ON_ONCE(sqd->thread == current); + WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)); + + set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); + mutex_lock(&sqd->lock); + if (sqd->thread) + wake_up_process(sqd->thread); + mutex_unlock(&sqd->lock); + wait_for_completion(&sqd->exited); } static void io_put_sq_data(struct io_sq_data *sqd) { if (refcount_dec_and_test(&sqd->refs)) { - /* - * The park is a bit of a work-around, without it we get - * warning spews on shutdown with SQPOLL set and affinity - * set to a single CPU. - */ - if (sqd->thread) { - kthread_park(sqd->thread); - kthread_stop(sqd->thread); - } + WARN_ON_ONCE(atomic_read(&sqd->park_pending)); + io_sq_thread_stop(sqd); kfree(sqd); } } +static void io_sq_thread_finish(struct io_ring_ctx *ctx) +{ + struct io_sq_data *sqd = ctx->sq_data; + + if (sqd) { + io_sq_thread_park(sqd); + list_del_init(&ctx->sqd_list); + io_sqd_update_thread_idle(sqd); + io_sq_thread_unpark(sqd); + + io_put_sq_data(sqd); + ctx->sq_data = NULL; + } +} + static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) { struct io_ring_ctx *ctx_attach; @@ -7229,92 +7881,46 @@ static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) fdput(f); return ERR_PTR(-EINVAL); } + if (sqd->task_tgid != current->tgid) { + fdput(f); + return ERR_PTR(-EPERM); + } refcount_inc(&sqd->refs); fdput(f); return sqd; } -static struct io_sq_data *io_get_sq_data(struct io_uring_params *p) +static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, + bool *attached) { struct io_sq_data *sqd; - if (p->flags & IORING_SETUP_ATTACH_WQ) - return io_attach_sq_data(p); + *attached = false; + if (p->flags & IORING_SETUP_ATTACH_WQ) { + sqd = io_attach_sq_data(p); + if (!IS_ERR(sqd)) { + *attached = true; + return sqd; + } + /* fall through for EPERM case, setup new sqd/task */ + if (PTR_ERR(sqd) != -EPERM) + return sqd; + } sqd = kzalloc(sizeof(*sqd), GFP_KERNEL); if (!sqd) return ERR_PTR(-ENOMEM); + atomic_set(&sqd->park_pending, 0); refcount_set(&sqd->refs, 1); INIT_LIST_HEAD(&sqd->ctx_list); - INIT_LIST_HEAD(&sqd->ctx_new_list); - mutex_init(&sqd->ctx_lock); mutex_init(&sqd->lock); init_waitqueue_head(&sqd->wait); + init_completion(&sqd->exited); return sqd; } -static void io_sq_thread_unpark(struct io_sq_data *sqd) - __releases(&sqd->lock) -{ - if (!sqd->thread) - return; - kthread_unpark(sqd->thread); - mutex_unlock(&sqd->lock); -} - -static void io_sq_thread_park(struct io_sq_data *sqd) - __acquires(&sqd->lock) -{ - if (!sqd->thread) - return; - mutex_lock(&sqd->lock); - kthread_park(sqd->thread); -} - -static void io_sq_thread_stop(struct io_ring_ctx *ctx) -{ - struct io_sq_data *sqd = ctx->sq_data; - - if (sqd) { - if (sqd->thread) { - /* - * We may arrive here from the error branch in - * io_sq_offload_create() where the kthread is created - * without being waked up, thus wake it up now to make - * sure the wait will complete. - */ - wake_up_process(sqd->thread); - wait_for_completion(&ctx->sq_thread_comp); - - io_sq_thread_park(sqd); - } - - mutex_lock(&sqd->ctx_lock); - list_del(&ctx->sqd_list); - mutex_unlock(&sqd->ctx_lock); - - if (sqd->thread) { - finish_wait(&sqd->wait, &ctx->sqo_wait_entry); - io_sq_thread_unpark(sqd); - } - - io_put_sq_data(sqd); - ctx->sq_data = NULL; - } -} - -static void io_finish_async(struct io_ring_ctx *ctx) -{ - io_sq_thread_stop(ctx); - - if (ctx->io_wq) { - io_wq_destroy(ctx->io_wq); - ctx->io_wq = NULL; - } -} - #if defined(CONFIG_UNIX) /* * Ensure the UNIX gc is aware of our file set, so we are certain that @@ -7342,7 +7948,7 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) skb->scm_io_uring = 1; nr_files = 0; - fpl->user = get_uid(ctx->user); + fpl->user = get_uid(current_user()); for (i = 0; i < nr; i++) { struct file *file = io_file_from_index(ctx, i + offset); @@ -7418,35 +8024,9 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) } #endif -static int io_sqe_alloc_file_tables(struct fixed_file_data *file_data, - unsigned nr_tables, unsigned nr_files) -{ - int i; - - for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &file_data->table[i]; - unsigned this_files; - - this_files = min(nr_files, IORING_MAX_FILES_TABLE); - table->files = kcalloc(this_files, sizeof(struct file *), - GFP_KERNEL_ACCOUNT); - if (!table->files) - break; - nr_files -= this_files; - } - - if (i == nr_tables) - return 0; - - for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &file_data->table[i]; - kfree(table->files); - } - return 1; -} - -static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file) +static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { + struct file *file = prsrc->file; #if defined(CONFIG_UNIX) struct sock *sock = ctx->ring_sock->sk; struct sk_buff_head list, *head = &sock->sk_receive_queue; @@ -7507,117 +8087,61 @@ static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file) #endif } -struct io_file_put { - struct list_head list; - struct file *file; -}; - -static void __io_file_put_work(struct fixed_file_ref_node *ref_node) +static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) { - struct fixed_file_data *file_data = ref_node->file_data; - struct io_ring_ctx *ctx = file_data->ctx; - struct io_file_put *pfile, *tmp; + struct io_rsrc_data *rsrc_data = ref_node->rsrc_data; + struct io_ring_ctx *ctx = rsrc_data->ctx; + struct io_rsrc_put *prsrc, *tmp; - list_for_each_entry_safe(pfile, tmp, &ref_node->file_list, list) { - list_del(&pfile->list); - io_ring_file_put(ctx, pfile->file); - kfree(pfile); + list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) { + list_del(&prsrc->list); + + if (prsrc->tag) { + bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL; + + io_ring_submit_lock(ctx, lock_ring); + spin_lock(&ctx->completion_lock); + io_fill_cqe_aux(ctx, prsrc->tag, 0, 0); + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_cqring_ev_posted(ctx); + io_ring_submit_unlock(ctx, lock_ring); + } + + rsrc_data->do_put(ctx, prsrc); + kfree(prsrc); } - percpu_ref_exit(&ref_node->refs); - kfree(ref_node); - percpu_ref_put(&file_data->refs); + io_rsrc_node_destroy(ref_node); + if (atomic_dec_and_test(&rsrc_data->refs)) + complete(&rsrc_data->done); } -static void io_file_put_work(struct work_struct *work) +static void io_rsrc_put_work(struct work_struct *work) { struct io_ring_ctx *ctx; struct llist_node *node; - ctx = container_of(work, struct io_ring_ctx, file_put_work.work); - node = llist_del_all(&ctx->file_put_llist); + ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work); + node = llist_del_all(&ctx->rsrc_put_llist); while (node) { - struct fixed_file_ref_node *ref_node; + struct io_rsrc_node *ref_node; struct llist_node *next = node->next; - ref_node = llist_entry(node, struct fixed_file_ref_node, llist); - __io_file_put_work(ref_node); + ref_node = llist_entry(node, struct io_rsrc_node, llist); + __io_rsrc_put_work(ref_node); node = next; } } -static void io_file_data_ref_zero(struct percpu_ref *ref) -{ - struct fixed_file_ref_node *ref_node; - struct fixed_file_data *data; - struct io_ring_ctx *ctx; - bool first_add = false; - int delay = HZ; - - ref_node = container_of(ref, struct fixed_file_ref_node, refs); - data = ref_node->file_data; - ctx = data->ctx; - - spin_lock_bh(&data->lock); - ref_node->done = true; - - while (!list_empty(&data->ref_list)) { - ref_node = list_first_entry(&data->ref_list, - struct fixed_file_ref_node, node); - /* recycle ref nodes in order */ - if (!ref_node->done) - break; - list_del(&ref_node->node); - first_add |= llist_add(&ref_node->llist, &ctx->file_put_llist); - } - spin_unlock_bh(&data->lock); - - if (percpu_ref_is_dying(&data->refs)) - delay = 0; - - if (!delay) - mod_delayed_work(system_wq, &ctx->file_put_work, 0); - else if (first_add) - queue_delayed_work(system_wq, &ctx->file_put_work, delay); -} - -static struct fixed_file_ref_node *alloc_fixed_file_ref_node( - struct io_ring_ctx *ctx) -{ - struct fixed_file_ref_node *ref_node; - - ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); - if (!ref_node) - return NULL; - - if (percpu_ref_init(&ref_node->refs, io_file_data_ref_zero, - 0, GFP_KERNEL)) { - kfree(ref_node); - return NULL; - } - INIT_LIST_HEAD(&ref_node->node); - INIT_LIST_HEAD(&ref_node->file_list); - ref_node->file_data = ctx->file_data; - ref_node->done = false; - return ref_node; -} - -static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node) -{ - percpu_ref_exit(&ref_node->refs); - kfree(ref_node); -} - static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) + unsigned nr_args, u64 __user *tags) { __s32 __user *fds = (__s32 __user *) arg; - unsigned nr_tables, i; struct file *file; - int fd, ret = -ENOMEM; - struct fixed_file_ref_node *ref_node; - struct fixed_file_data *file_data; + int fd, ret; + unsigned i; if (ctx->file_data) return -EBUSY; @@ -7627,44 +8151,34 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return -EMFILE; if (nr_args > rlimit(RLIMIT_NOFILE)) return -EMFILE; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + return ret; + ret = io_rsrc_data_alloc(ctx, io_rsrc_file_put, tags, nr_args, + &ctx->file_data); + if (ret) + return ret; - file_data = kzalloc(sizeof(*ctx->file_data), GFP_KERNEL_ACCOUNT); - if (!file_data) - return -ENOMEM; - file_data->ctx = ctx; - init_completion(&file_data->done); - INIT_LIST_HEAD(&file_data->ref_list); - spin_lock_init(&file_data->lock); - - nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE); - file_data->table = kcalloc(nr_tables, sizeof(*file_data->table), - GFP_KERNEL_ACCOUNT); - if (!file_data->table) + ret = -ENOMEM; + if (!io_alloc_file_tables(&ctx->file_table, nr_args)) goto out_free; - if (percpu_ref_init(&file_data->refs, io_file_ref_kill, - PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) - goto out_free; - - if (io_sqe_alloc_file_tables(file_data, nr_tables, nr_args)) - goto out_ref; - ctx->file_data = file_data; - for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { - struct fixed_file_table *table; - unsigned index; - if (copy_from_user(&fd, &fds[i], sizeof(fd))) { ret = -EFAULT; goto out_fput; } /* allow sparse sets */ - if (fd == -1) + if (fd == -1) { + ret = -EINVAL; + if (unlikely(*io_get_tag_slot(ctx->file_data, i))) + goto out_fput; continue; + } file = fget(fd); ret = -EBADF; - if (!file) + if (unlikely(!file)) goto out_fput; /* @@ -7678,24 +8192,16 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, fput(file); goto out_fput; } - table = &file_data->table[i >> IORING_FILE_TABLE_SHIFT]; - index = i & IORING_FILE_TABLE_MASK; - table->files[index] = file; + io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file); } ret = io_sqe_files_scm(ctx); if (ret) { - io_sqe_files_unregister(ctx); + __io_sqe_files_unregister(ctx); return ret; } - ref_node = alloc_fixed_file_ref_node(ctx); - if (!ref_node) { - io_sqe_files_unregister(ctx); - return -ENOMEM; - } - - io_sqe_files_set_node(file_data, ref_node); + io_rsrc_node_switch(ctx, NULL); return ret; out_fput: for (i = 0; i < ctx->nr_user_files; i++) { @@ -7703,14 +8209,10 @@ out_fput: if (file) fput(file); } - for (i = 0; i < nr_tables; i++) - kfree(file_data->table[i].files); + io_free_file_tables(&ctx->file_table); ctx->nr_user_files = 0; -out_ref: - percpu_ref_exit(&file_data->refs); out_free: - kfree(file_data->table); - kfree(file_data); + io_rsrc_data_free(ctx->file_data); ctx->file_data = NULL; return ret; } @@ -7758,63 +8260,159 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, #endif } -static int io_queue_file_removal(struct fixed_file_data *data, - struct file *file) +static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, + struct io_rsrc_node *node, void *rsrc) { - struct io_file_put *pfile; - struct fixed_file_ref_node *ref_node = data->node; + u64 *tag_slot = io_get_tag_slot(data, idx); + struct io_rsrc_put *prsrc; - pfile = kzalloc(sizeof(*pfile), GFP_KERNEL); - if (!pfile) + prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); + if (!prsrc) return -ENOMEM; - pfile->file = file; - list_add(&pfile->list, &ref_node->file_list); - + prsrc->tag = *tag_slot; + *tag_slot = 0; + prsrc->rsrc = rsrc; + list_add(&prsrc->list, &node->rsrc_list); return 0; } +static int io_install_fixed_file(struct io_kiocb *req, struct file *file, + unsigned int issue_flags, u32 slot_index) +{ + struct io_ring_ctx *ctx = req->ctx; + bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool needs_switch = false; + struct io_fixed_file *file_slot; + int ret = -EBADF; + + io_ring_submit_lock(ctx, !force_nonblock); + if (file->f_op == &io_uring_fops) + goto err; + ret = -ENXIO; + if (!ctx->file_data) + goto err; + ret = -EINVAL; + if (slot_index >= ctx->nr_user_files) + goto err; + + slot_index = array_index_nospec(slot_index, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); + + if (file_slot->file_ptr) { + struct file *old_file; + + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + + old_file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, slot_index, + ctx->rsrc_node, old_file); + if (ret) + goto err; + file_slot->file_ptr = 0; + needs_switch = true; + } + + *io_get_tag_slot(ctx->file_data, slot_index) = 0; + io_fixed_file_set(file_slot, file); + ret = io_sqe_file_register(ctx, file, slot_index); + if (ret) { + file_slot->file_ptr = 0; + goto err; + } + + ret = 0; +err: + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->file_data); + io_ring_submit_unlock(ctx, !force_nonblock); + if (ret) + fput(file); + return ret; +} + +static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) +{ + unsigned int offset = req->close.file_slot - 1; + struct io_ring_ctx *ctx = req->ctx; + struct io_fixed_file *file_slot; + struct file *file; + int ret; + + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = -ENXIO; + if (unlikely(!ctx->file_data)) + goto out; + ret = -EINVAL; + if (offset >= ctx->nr_user_files) + goto out; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto out; + + offset = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, offset); + ret = -EBADF; + if (!file_slot->file_ptr) + goto out; + + file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file); + if (ret) + goto out; + + file_slot->file_ptr = 0; + io_rsrc_node_switch(ctx, ctx->file_data); + ret = 0; +out: + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + return ret; +} + static int __io_sqe_files_update(struct io_ring_ctx *ctx, - struct io_uring_files_update *up, + struct io_uring_rsrc_update2 *up, unsigned nr_args) { - struct fixed_file_data *data = ctx->file_data; - struct fixed_file_ref_node *ref_node; + u64 __user *tags = u64_to_user_ptr(up->tags); + __s32 __user *fds = u64_to_user_ptr(up->data); + struct io_rsrc_data *data = ctx->file_data; + struct io_fixed_file *file_slot; struct file *file; - __s32 __user *fds; - int fd, i, err; - __u32 done; + int fd, i, err = 0; + unsigned int done; bool needs_switch = false; - if (check_add_overflow(up->offset, nr_args, &done)) - return -EOVERFLOW; - if (done > ctx->nr_user_files) + if (!ctx->file_data) + return -ENXIO; + if (up->offset + nr_args > ctx->nr_user_files) return -EINVAL; - ref_node = alloc_fixed_file_ref_node(ctx); - if (!ref_node) - return -ENOMEM; + for (done = 0; done < nr_args; done++) { + u64 tag = 0; - done = 0; - fds = u64_to_user_ptr(up->fds); - while (nr_args) { - struct fixed_file_table *table; - unsigned index; - - err = 0; - if (copy_from_user(&fd, &fds[done], sizeof(fd))) { + if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) || + copy_from_user(&fd, &fds[done], sizeof(fd))) { err = -EFAULT; break; } - i = array_index_nospec(up->offset, ctx->nr_user_files); - table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; - index = i & IORING_FILE_TABLE_MASK; - if (table->files[index]) { - file = table->files[index]; - err = io_queue_file_removal(data, file); + if ((fd == IORING_REGISTER_FILES_SKIP || fd == -1) && tag) { + err = -EINVAL; + break; + } + if (fd == IORING_REGISTER_FILES_SKIP) + continue; + + i = array_index_nospec(up->offset + done, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, i); + + if (file_slot->file_ptr) { + file = (struct file *)(file_slot->file_ptr & FFS_MASK); + err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); if (err) break; - table->files[index] = NULL; + file_slot->file_ptr = 0; needs_switch = true; } if (fd != -1) { @@ -7836,106 +8434,61 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - table->files[index] = file; + *io_get_tag_slot(data, i) = tag; + io_fixed_file_set(file_slot, file); err = io_sqe_file_register(ctx, file, i); if (err) { - table->files[index] = NULL; + file_slot->file_ptr = 0; fput(file); break; } } - nr_args--; - done++; - up->offset++; } - if (needs_switch) { - percpu_ref_kill(&data->node->refs); - io_sqe_files_set_node(data, ref_node); - } else - destroy_fixed_file_ref_node(ref_node); - + if (needs_switch) + io_rsrc_node_switch(ctx, data); return done ? done : err; } -static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) -{ - struct io_uring_files_update up; - - if (!ctx->file_data) - return -ENXIO; - if (!nr_args) - return -EINVAL; - if (copy_from_user(&up, arg, sizeof(up))) - return -EFAULT; - if (up.resv) - return -EINVAL; - - return __io_sqe_files_update(ctx, &up, nr_args); -} - -static void io_free_work(struct io_wq_work *work) -{ - struct io_kiocb *req = container_of(work, struct io_kiocb, work); - - /* Consider that io_steal_work() relies on this ref */ - io_put_req(req); -} - -static int io_init_wq_offload(struct io_ring_ctx *ctx, - struct io_uring_params *p) +static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx, + struct task_struct *task) { + struct io_wq_hash *hash; struct io_wq_data data; - struct fd f; - struct io_ring_ctx *ctx_attach; unsigned int concurrency; - int ret = 0; - data.user = ctx->user; - data.free_work = io_free_work; + mutex_lock(&ctx->uring_lock); + hash = ctx->hash_map; + if (!hash) { + hash = kzalloc(sizeof(*hash), GFP_KERNEL); + if (!hash) { + mutex_unlock(&ctx->uring_lock); + return ERR_PTR(-ENOMEM); + } + refcount_set(&hash->refs, 1); + init_waitqueue_head(&hash->wait); + ctx->hash_map = hash; + } + mutex_unlock(&ctx->uring_lock); + + data.hash = hash; + data.task = task; + data.free_work = io_wq_free_work; data.do_work = io_wq_submit_work; - if (!(p->flags & IORING_SETUP_ATTACH_WQ)) { - /* Do QD, or 4 * CPUS, whatever is smallest */ - concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); + /* Do QD, or 4 * CPUS, whatever is smallest */ + concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); - ctx->io_wq = io_wq_create(concurrency, &data); - if (IS_ERR(ctx->io_wq)) { - ret = PTR_ERR(ctx->io_wq); - ctx->io_wq = NULL; - } - return ret; - } - - f = fdget(p->wq_fd); - if (!f.file) - return -EBADF; - - if (f.file->f_op != &io_uring_fops) { - ret = -EINVAL; - goto out_fput; - } - - ctx_attach = f.file->private_data; - /* @io_wq is protected by holding the fd */ - if (!io_wq_get(ctx_attach->io_wq, &data)) { - ret = -EINVAL; - goto out_fput; - } - - ctx->io_wq = ctx_attach->io_wq; -out_fput: - fdput(f); - return ret; + return io_wq_create(concurrency, &data); } -static int io_uring_alloc_task_context(struct task_struct *task) +static int io_uring_alloc_task_context(struct task_struct *task, + struct io_ring_ctx *ctx) { struct io_uring_task *tctx; int ret; - tctx = kmalloc(sizeof(*tctx), GFP_KERNEL); + tctx = kzalloc(sizeof(*tctx), GFP_KERNEL); if (unlikely(!tctx)) return -ENOMEM; @@ -7945,14 +8498,22 @@ static int io_uring_alloc_task_context(struct task_struct *task) return ret; } + tctx->io_wq = io_init_wq_offload(ctx, task); + if (IS_ERR(tctx->io_wq)) { + ret = PTR_ERR(tctx->io_wq); + percpu_counter_destroy(&tctx->inflight); + kfree(tctx); + return ret; + } + xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); - tctx->last = NULL; atomic_set(&tctx->in_idle, 0); - tctx->sqpoll = false; - io_init_identity(&tctx->__identity); - tctx->identity = &tctx->__identity; + atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; + spin_lock_init(&tctx->task_lock); + INIT_WQ_LIST(&tctx->task_list); + init_task_work(&tctx->task_work, tctx_task_work); return 0; } @@ -7961,9 +8522,9 @@ void __io_uring_free(struct task_struct *tsk) struct io_uring_task *tctx = tsk->io_uring; WARN_ON_ONCE(!xa_empty(&tctx->xa)); - WARN_ON_ONCE(refcount_read(&tctx->identity->count) != 1); - if (tctx->identity != &tctx->__identity) - kfree(tctx->identity); + WARN_ON_ONCE(tctx->io_wq); + WARN_ON_ONCE(tctx->cached_refs); + percpu_counter_destroy(&tctx->inflight); kfree(tctx); tsk->io_uring = NULL; @@ -7974,54 +8535,71 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, { int ret; + /* Retain compatibility with failing for an invalid attach attempt */ + if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) == + IORING_SETUP_ATTACH_WQ) { + struct fd f; + + f = fdget(p->wq_fd); + if (!f.file) + return -ENXIO; + if (f.file->f_op != &io_uring_fops) { + fdput(f); + return -EINVAL; + } + fdput(f); + } if (ctx->flags & IORING_SETUP_SQPOLL) { + struct task_struct *tsk; struct io_sq_data *sqd; + bool attached; - ret = -EPERM; - if (!capable(CAP_SYS_ADMIN)) - goto err; - - sqd = io_get_sq_data(p); + sqd = io_get_sq_data(p, &attached); if (IS_ERR(sqd)) { ret = PTR_ERR(sqd); goto err; } + ctx->sq_creds = get_current_cred(); ctx->sq_data = sqd; - io_sq_thread_park(sqd); - mutex_lock(&sqd->ctx_lock); - list_add(&ctx->sqd_list, &sqd->ctx_new_list); - mutex_unlock(&sqd->ctx_lock); - io_sq_thread_unpark(sqd); - ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); if (!ctx->sq_thread_idle) ctx->sq_thread_idle = HZ; - if (sqd->thread) - goto done; + io_sq_thread_park(sqd); + list_add(&ctx->sqd_list, &sqd->ctx_list); + io_sqd_update_thread_idle(sqd); + /* don't attach to a dying SQPOLL thread, would be racy */ + ret = (attached && !sqd->thread) ? -ENXIO : 0; + io_sq_thread_unpark(sqd); + + if (ret < 0) + goto err; + if (attached) + return 0; if (p->flags & IORING_SETUP_SQ_AFF) { int cpu = p->sq_thread_cpu; ret = -EINVAL; - if (cpu >= nr_cpu_ids) - goto err; - if (!cpu_online(cpu)) - goto err; - - sqd->thread = kthread_create_on_cpu(io_sq_thread, sqd, - cpu, "io_uring-sq"); + if (cpu >= nr_cpu_ids || !cpu_online(cpu)) + goto err_sqpoll; + sqd->sq_cpu = cpu; } else { - sqd->thread = kthread_create(io_sq_thread, sqd, - "io_uring-sq"); + sqd->sq_cpu = -1; } - if (IS_ERR(sqd->thread)) { - ret = PTR_ERR(sqd->thread); - sqd->thread = NULL; - goto err; + + sqd->task_pid = current->pid; + sqd->task_tgid = current->tgid; + tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE); + if (IS_ERR(tsk)) { + ret = PTR_ERR(tsk); + goto err_sqpoll; } - ret = io_uring_alloc_task_context(sqd->thread); + + sqd->thread = tsk; + ret = io_uring_alloc_task_context(tsk, ctx); + wake_up_new_task(tsk); if (ret) goto err; } else if (p->flags & IORING_SETUP_SQ_AFF) { @@ -8030,26 +8608,14 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, goto err; } -done: - ret = io_init_wq_offload(ctx, p); - if (ret) - goto err; - return 0; +err_sqpoll: + complete(&ctx->sq_data->exited); err: - io_finish_async(ctx); + io_sq_thread_finish(ctx); return ret; } -static void io_sq_offload_start(struct io_ring_ctx *ctx) -{ - struct io_sq_data *sqd = ctx->sq_data; - - ctx->flags &= ~IORING_SETUP_R_DISABLED; - if ((ctx->flags & IORING_SETUP_SQPOLL) && sqd && sqd->thread) - wake_up_process(sqd->thread); -} - static inline void __io_unaccount_mem(struct user_struct *user, unsigned long nr_pages) { @@ -8075,37 +8641,27 @@ static inline int __io_account_mem(struct user_struct *user, return 0; } -static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages, - enum io_mem_account acct) +static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) { - if (ctx->limit_mem) + if (ctx->user) __io_unaccount_mem(ctx->user, nr_pages); - if (ctx->mm_account) { - if (acct == ACCT_LOCKED) - ctx->mm_account->locked_vm -= nr_pages; - else if (acct == ACCT_PINNED) - atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); - } + if (ctx->mm_account) + atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); } -static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages, - enum io_mem_account acct) +static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) { int ret; - if (ctx->limit_mem) { + if (ctx->user) { ret = __io_account_mem(ctx->user, nr_pages); if (ret) return ret; } - if (ctx->mm_account) { - if (acct == ACCT_LOCKED) - ctx->mm_account->locked_vm += nr_pages; - else if (acct == ACCT_PINNED) - atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); - } + if (ctx->mm_account) + atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); return 0; } @@ -8124,10 +8680,9 @@ static void io_mem_free(void *ptr) static void *io_mem_alloc(size_t size) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP | - __GFP_NORETRY; + gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; - return (void *) __get_free_pages(gfp_flags, get_order(size)); + return (void *) __get_free_pages(gfp, get_order(size)); } static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, @@ -8159,41 +8714,58 @@ static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, return off; } -static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries) +static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot) { - size_t pages; + struct io_mapped_ubuf *imu = *slot; + unsigned int i; - pages = (size_t)1 << get_order( - rings_size(sq_entries, cq_entries, NULL)); - pages += (size_t)1 << get_order( - array_size(sizeof(struct io_uring_sqe), sq_entries)); - - return pages; + if (imu != ctx->dummy_ubuf) { + for (i = 0; i < imu->nr_bvecs; i++) + unpin_user_page(imu->bvec[i].bv_page); + if (imu->acct_pages) + io_unaccount_mem(ctx, imu->acct_pages); + kvfree(imu); + } + *slot = NULL; } -static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) +static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { - int i, j; + io_buffer_unmap(ctx, &prsrc->buf); + prsrc->buf = NULL; +} - if (!ctx->user_bufs) +static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) +{ + unsigned int i; + + for (i = 0; i < ctx->nr_user_bufs; i++) + io_buffer_unmap(ctx, &ctx->user_bufs[i]); + kfree(ctx->user_bufs); + io_rsrc_data_free(ctx->buf_data); + ctx->user_bufs = NULL; + ctx->buf_data = NULL; + ctx->nr_user_bufs = 0; +} + +static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx) +{ + unsigned nr = ctx->nr_user_bufs; + int ret; + + if (!ctx->buf_data) return -ENXIO; - for (i = 0; i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; - - for (j = 0; j < imu->nr_bvecs; j++) - unpin_user_page(imu->bvec[j].bv_page); - - if (imu->acct_pages) - io_unaccount_mem(ctx, imu->acct_pages, ACCT_PINNED); - kvfree(imu->bvec); - imu->nr_bvecs = 0; - } - - kfree(ctx->user_bufs); - ctx->user_bufs = NULL; + /* + * Quiesce may unlock ->uring_lock, and while it's not held + * prevent new requests using the table. + */ ctx->nr_user_bufs = 0; - return 0; + ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx); + ctx->nr_user_bufs = nr; + if (!ret) + __io_sqe_buffers_unregister(ctx); + return ret; } static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, @@ -8245,7 +8817,7 @@ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages, /* check previously registered pages */ for (i = 0; i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; + struct io_mapped_ubuf *imu = ctx->user_bufs[i]; for (j = 0; j < imu->nr_bvecs; j++) { if (!PageCompound(imu->bvec[j].bv_page)) @@ -8264,6 +8836,7 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, { int i, ret; + imu->acct_pages = 0; for (i = 0; i < nr_pages; i++) { if (!PageCompound(pages[i])) { imu->acct_pages++; @@ -8283,149 +8856,254 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, if (!imu->acct_pages) return 0; - ret = io_account_mem(ctx, imu->acct_pages, ACCT_PINNED); + ret = io_account_mem(ctx, imu->acct_pages); if (ret) imu->acct_pages = 0; return ret; } -static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) +static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, + struct io_mapped_ubuf **pimu, + struct page **last_hpage) { + struct io_mapped_ubuf *imu = NULL; struct vm_area_struct **vmas = NULL; struct page **pages = NULL; + unsigned long off, start, end, ubuf; + size_t size; + int ret, pret, nr_pages, i; + + if (!iov->iov_base) { + *pimu = ctx->dummy_ubuf; + return 0; + } + + ubuf = (unsigned long) iov->iov_base; + end = (ubuf + iov->iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; + start = ubuf >> PAGE_SHIFT; + nr_pages = end - start; + + *pimu = NULL; + ret = -ENOMEM; + + pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + goto done; + + vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!vmas) + goto done; + + imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); + if (!imu) + goto done; + + ret = 0; + mmap_read_lock(current->mm); + pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, + pages, vmas); + if (pret == nr_pages) { + /* don't support file backed memory */ + for (i = 0; i < nr_pages; i++) { + struct vm_area_struct *vma = vmas[i]; + + if (vma_is_shmem(vma)) + continue; + if (vma->vm_file && + !is_file_hugepages(vma->vm_file)) { + ret = -EOPNOTSUPP; + break; + } + } + } else { + ret = pret < 0 ? pret : -EFAULT; + } + mmap_read_unlock(current->mm); + if (ret) { + /* + * if we did partial map, or found file backed vmas, + * release any pages we did get + */ + if (pret > 0) + unpin_user_pages(pages, pret); + goto done; + } + + ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage); + if (ret) { + unpin_user_pages(pages, pret); + goto done; + } + + off = ubuf & ~PAGE_MASK; + size = iov->iov_len; + for (i = 0; i < nr_pages; i++) { + size_t vec_len; + + vec_len = min_t(size_t, size, PAGE_SIZE - off); + imu->bvec[i].bv_page = pages[i]; + imu->bvec[i].bv_len = vec_len; + imu->bvec[i].bv_offset = off; + off = 0; + size -= vec_len; + } + /* store original address for later verification */ + imu->ubuf = ubuf; + imu->ubuf_end = ubuf + iov->iov_len; + imu->nr_bvecs = nr_pages; + *pimu = imu; + ret = 0; +done: + if (ret) + kvfree(imu); + kvfree(pages); + kvfree(vmas); + return ret; +} + +static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args) +{ + ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL); + return ctx->user_bufs ? 0 : -ENOMEM; +} + +static int io_buffer_validate(struct iovec *iov) +{ + unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1); + + /* + * Don't impose further limits on the size and buffer + * constraints here, we'll -EINVAL later when IO is + * submitted if they are wrong. + */ + if (!iov->iov_base) + return iov->iov_len ? -EFAULT : 0; + if (!iov->iov_len) + return -EFAULT; + + /* arbitrary limit, but we need something */ + if (iov->iov_len > SZ_1G) + return -EFAULT; + + if (check_add_overflow((unsigned long)iov->iov_base, acct_len, &tmp)) + return -EOVERFLOW; + + return 0; +} + +static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, + unsigned int nr_args, u64 __user *tags) +{ struct page *last_hpage = NULL; - int i, j, got_pages = 0; - int ret = -EINVAL; + struct io_rsrc_data *data; + int i, ret; + struct iovec iov; if (ctx->user_bufs) return -EBUSY; - if (!nr_args || nr_args > UIO_MAXIOV) + if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) return -EINVAL; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + return ret; + ret = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, tags, nr_args, &data); + if (ret) + return ret; + ret = io_buffers_map_alloc(ctx, nr_args); + if (ret) { + io_rsrc_data_free(data); + return ret; + } - ctx->user_bufs = kcalloc(nr_args, sizeof(struct io_mapped_ubuf), - GFP_KERNEL); - if (!ctx->user_bufs) - return -ENOMEM; - - for (i = 0; i < nr_args; i++) { - struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; - unsigned long off, start, end, ubuf; - int pret, nr_pages; - struct iovec iov; - size_t size; - + for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { ret = io_copy_iov(ctx, &iov, arg, i); if (ret) - goto err; - - /* - * Don't impose further limits on the size and buffer - * constraints here, we'll -EINVAL later when IO is - * submitted if they are wrong. - */ - ret = -EFAULT; - if (!iov.iov_base || !iov.iov_len) - goto err; - - /* arbitrary limit, but we need something */ - if (iov.iov_len > SZ_1G) - goto err; - - ubuf = (unsigned long) iov.iov_base; - end = (ubuf + iov.iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; - start = ubuf >> PAGE_SHIFT; - nr_pages = end - start; - - ret = 0; - if (!pages || nr_pages > got_pages) { - kvfree(vmas); - kvfree(pages); - pages = kvmalloc_array(nr_pages, sizeof(struct page *), - GFP_KERNEL); - vmas = kvmalloc_array(nr_pages, - sizeof(struct vm_area_struct *), - GFP_KERNEL); - if (!pages || !vmas) { - ret = -ENOMEM; - goto err; - } - got_pages = nr_pages; + break; + ret = io_buffer_validate(&iov); + if (ret) + break; + if (!iov.iov_base && *io_get_tag_slot(data, i)) { + ret = -EINVAL; + break; } - imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec), - GFP_KERNEL); - ret = -ENOMEM; - if (!imu->bvec) - goto err; - - ret = 0; - mmap_read_lock(current->mm); - pret = pin_user_pages(ubuf, nr_pages, - FOLL_WRITE | FOLL_LONGTERM, - pages, vmas); - if (pret == nr_pages) { - /* don't support file backed memory */ - for (j = 0; j < nr_pages; j++) { - struct vm_area_struct *vma = vmas[j]; - - if (vma->vm_file && - !is_file_hugepages(vma->vm_file)) { - ret = -EOPNOTSUPP; - break; - } - } - } else { - ret = pret < 0 ? pret : -EFAULT; - } - mmap_read_unlock(current->mm); - if (ret) { - /* - * if we did partial map, or found file backed vmas, - * release any pages we did get - */ - if (pret > 0) - unpin_user_pages(pages, pret); - kvfree(imu->bvec); - goto err; - } - - ret = io_buffer_account_pin(ctx, pages, pret, imu, &last_hpage); - if (ret) { - unpin_user_pages(pages, pret); - kvfree(imu->bvec); - goto err; - } - - off = ubuf & ~PAGE_MASK; - size = iov.iov_len; - for (j = 0; j < nr_pages; j++) { - size_t vec_len; - - vec_len = min_t(size_t, size, PAGE_SIZE - off); - imu->bvec[j].bv_page = pages[j]; - imu->bvec[j].bv_len = vec_len; - imu->bvec[j].bv_offset = off; - off = 0; - size -= vec_len; - } - /* store original address for later verification */ - imu->ubuf = ubuf; - imu->len = iov.iov_len; - imu->nr_bvecs = nr_pages; - - ctx->nr_user_bufs++; + ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i], + &last_hpage); + if (ret) + break; } - kvfree(pages); - kvfree(vmas); - return 0; -err: - kvfree(pages); - kvfree(vmas); - io_sqe_buffer_unregister(ctx); + + WARN_ON_ONCE(ctx->buf_data); + + ctx->buf_data = data; + if (ret) + __io_sqe_buffers_unregister(ctx); + else + io_rsrc_node_switch(ctx, NULL); return ret; } +static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, + struct io_uring_rsrc_update2 *up, + unsigned int nr_args) +{ + u64 __user *tags = u64_to_user_ptr(up->tags); + struct iovec iov, __user *iovs = u64_to_user_ptr(up->data); + struct page *last_hpage = NULL; + bool needs_switch = false; + __u32 done; + int i, err; + + if (!ctx->buf_data) + return -ENXIO; + if (up->offset + nr_args > ctx->nr_user_bufs) + return -EINVAL; + + for (done = 0; done < nr_args; done++) { + struct io_mapped_ubuf *imu; + int offset = up->offset + done; + u64 tag = 0; + + err = io_copy_iov(ctx, &iov, iovs, done); + if (err) + break; + if (tags && copy_from_user(&tag, &tags[done], sizeof(tag))) { + err = -EFAULT; + break; + } + err = io_buffer_validate(&iov); + if (err) + break; + if (!iov.iov_base && tag) { + err = -EINVAL; + break; + } + err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage); + if (err) + break; + + i = array_index_nospec(offset, ctx->nr_user_bufs); + if (ctx->user_bufs[i] != ctx->dummy_ubuf) { + err = io_queue_rsrc_removal(ctx->buf_data, i, + ctx->rsrc_node, ctx->user_bufs[i]); + if (unlikely(err)) { + io_buffer_unmap(ctx, &imu); + break; + } + ctx->user_bufs[i] = NULL; + needs_switch = true; + } + + ctx->user_bufs[i] = imu; + *io_get_tag_slot(ctx->buf_data, offset) = tag; + } + + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->buf_data); + return done ? done : err; +} + static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg) { __s32 __user *fds = arg; @@ -8440,6 +9118,7 @@ static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg) ctx->cq_ev_fd = eventfd_ctx_fdget(fd); if (IS_ERR(ctx->cq_ev_fd)) { int ret = PTR_ERR(ctx->cq_ev_fd); + ctx->cq_ev_fd = NULL; return ret; } @@ -8467,26 +9146,68 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx) __io_remove_buffers(ctx, buf, index, -1U); } -static void io_ring_ctx_free(struct io_ring_ctx *ctx) +static void io_req_cache_free(struct list_head *list) { - io_finish_async(ctx); - io_sqe_buffer_unregister(ctx); + struct io_kiocb *req, *nxt; - if (ctx->sqo_task) { - put_task_struct(ctx->sqo_task); - ctx->sqo_task = NULL; + list_for_each_entry_safe(req, nxt, list, inflight_entry) { + list_del(&req->inflight_entry); + kmem_cache_free(req_cachep, req); } +} -#ifdef CONFIG_BLK_CGROUP - if (ctx->sqo_blkcg_css) - css_put(ctx->sqo_blkcg_css); -#endif +static void io_req_caches_free(struct io_ring_ctx *ctx) +{ + struct io_submit_state *state = &ctx->submit_state; mutex_lock(&ctx->uring_lock); - io_sqe_files_unregister(ctx); + + if (state->free_reqs) { + kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs); + state->free_reqs = 0; + } + + io_flush_cached_locked_reqs(ctx, state); + io_req_cache_free(&state->free_list); + mutex_unlock(&ctx->uring_lock); +} + +static void io_wait_rsrc_data(struct io_rsrc_data *data) +{ + if (data && !atomic_dec_and_test(&data->refs)) + wait_for_completion(&data->done); +} + +static void io_ring_ctx_free(struct io_ring_ctx *ctx) +{ + io_sq_thread_finish(ctx); + + /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ + io_wait_rsrc_data(ctx->buf_data); + io_wait_rsrc_data(ctx->file_data); + + mutex_lock(&ctx->uring_lock); + if (ctx->buf_data) + __io_sqe_buffers_unregister(ctx); + if (ctx->file_data) + __io_sqe_files_unregister(ctx); + if (ctx->rings) + __io_cqring_overflow_flush(ctx, true); mutex_unlock(&ctx->uring_lock); io_eventfd_unregister(ctx); io_destroy_buffers(ctx); + if (ctx->sq_creds) + put_cred(ctx->sq_creds); + + /* there are no registered resources left, nobody uses it */ + if (ctx->rsrc_node) + io_rsrc_node_destroy(ctx->rsrc_node); + if (ctx->rsrc_backup_node) + io_rsrc_node_destroy(ctx->rsrc_backup_node); + flush_delayed_work(&ctx->rsrc_put_work); + + WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); + WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist)); #if defined(CONFIG_UNIX) if (ctx->ring_sock) { @@ -8494,6 +9215,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) sock_release(ctx->ring_sock); } #endif + WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); if (ctx->mm_account) { mmdrop(ctx->mm_account); @@ -8505,9 +9227,11 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) percpu_ref_exit(&ctx->refs); free_uid(ctx->user); - put_cred(ctx->creds); + io_req_caches_free(ctx); + if (ctx->hash_map) + io_wq_put_hash(ctx->hash_map); kfree(ctx->cancel_hash); - kmem_cache_free(req_cachep, ctx->fallback_req); + kfree(ctx->dummy_ubuf); kfree(ctx); } @@ -8516,7 +9240,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) struct io_ring_ctx *ctx = file->private_data; __poll_t mask = 0; - poll_wait(file, &ctx->cq_wait, wait); + poll_wait(file, &ctx->poll_wait, wait); /* * synchronizes with barrier from wq_has_sleeper call in * io_commit_cqring @@ -8538,49 +9262,46 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) * Users may get EPOLLIN meanwhile seeing nothing in cqring, this * pushs them to do the flush. */ - if (io_cqring_events(ctx) || test_bit(0, &ctx->cq_check_overflow)) + if (io_cqring_events(ctx) || test_bit(0, &ctx->check_cq_overflow)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } -static int io_uring_fasync(int fd, struct file *file, int on) -{ - struct io_ring_ctx *ctx = file->private_data; - - return fasync_helper(fd, file, on, &ctx->cq_fasync); -} - static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { - struct io_identity *iod; + const struct cred *creds; - iod = xa_erase(&ctx->personalities, id); - if (iod) { - put_cred(iod->creds); - if (refcount_dec_and_test(&iod->count)) - kfree(iod); + creds = xa_erase(&ctx->personalities, id); + if (creds) { + put_cred(creds); return 0; } return -EINVAL; } -static void io_ring_exit_work(struct work_struct *work) -{ - struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, - exit_work); +struct io_tctx_exit { + struct callback_head task_work; + struct completion completion; + struct io_ring_ctx *ctx; +}; +static void io_tctx_exit_cb(struct callback_head *cb) +{ + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_exit *work; + + work = container_of(cb, struct io_tctx_exit, task_work); /* - * If we're doing polled IO and end up having requests being - * submitted async (out-of-line), then completions can come in while - * we're waiting for refs to drop. We need to reap these manually, - * as nobody else will be looking for them. + * When @in_idle, we're in cancellation and it's racy to remove the + * node. It'll be removed by the end of cancellation, just ignore it. + * tctx can be NULL if the queueing of this task_work raced with + * work cancelation off the exec path. */ - do { - io_iopoll_try_reap_events(ctx); - } while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20)); - io_ring_ctx_free(ctx); + if (tctx && !atomic_read(&tctx->in_idle)) + io_uring_del_tctx_node((unsigned long)work->ctx); + complete(&work->completion); } static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) @@ -8590,41 +9311,116 @@ static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) return req->ctx == data; } +static void io_ring_exit_work(struct work_struct *work) +{ + struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work); + unsigned long timeout = jiffies + HZ * 60 * 5; + unsigned long interval = HZ / 20; + struct io_tctx_exit exit; + struct io_tctx_node *node; + int ret; + + /* + * If we're doing polled IO and end up having requests being + * submitted async (out-of-line), then completions can come in while + * we're waiting for refs to drop. We need to reap these manually, + * as nobody else will be looking for them. + */ + do { + io_uring_try_cancel_requests(ctx, NULL, true); + if (ctx->sq_data) { + struct io_sq_data *sqd = ctx->sq_data; + struct task_struct *tsk; + + io_sq_thread_park(sqd); + tsk = sqd->thread; + if (tsk && tsk->io_uring && tsk->io_uring->io_wq) + io_wq_cancel_cb(tsk->io_uring->io_wq, + io_cancel_ctx_cb, ctx, true); + io_sq_thread_unpark(sqd); + } + + if (WARN_ON_ONCE(time_after(jiffies, timeout))) { + /* there is little hope left, don't run it too often */ + interval = HZ * 60; + } + } while (!wait_for_completion_timeout(&ctx->ref_comp, interval)); + + init_completion(&exit.completion); + init_task_work(&exit.task_work, io_tctx_exit_cb); + exit.ctx = ctx; + /* + * Some may use context even when all refs and requests have been put, + * and they are free to do so while still holding uring_lock or + * completion_lock, see io_req_task_submit(). Apart from other work, + * this lock/unlock section also waits them to finish. + */ + mutex_lock(&ctx->uring_lock); + while (!list_empty(&ctx->tctx_list)) { + WARN_ON_ONCE(time_after(jiffies, timeout)); + + node = list_first_entry(&ctx->tctx_list, struct io_tctx_node, + ctx_node); + /* don't spin on a single task if cancellation failed */ + list_rotate_left(&ctx->tctx_list); + ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL); + if (WARN_ON_ONCE(ret)) + continue; + wake_up_process(node->task); + + mutex_unlock(&ctx->uring_lock); + wait_for_completion(&exit.completion); + mutex_lock(&ctx->uring_lock); + } + mutex_unlock(&ctx->uring_lock); + spin_lock(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); + + io_ring_ctx_free(ctx); +} + +/* Returns true if we found and killed one or more timeouts */ +static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, + bool cancel_all) +{ + struct io_kiocb *req, *tmp; + int canceled = 0; + + spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { + if (io_match_task(req, tsk, cancel_all)) { + io_kill_timeout(req, -ECANCELED); + canceled++; + } + } + spin_unlock_irq(&ctx->timeout_lock); + if (canceled != 0) + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + if (canceled != 0) + io_cqring_ev_posted(ctx); + return canceled != 0; +} + static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { unsigned long index; - struct io_identify *iod; + struct creds *creds; mutex_lock(&ctx->uring_lock); percpu_ref_kill(&ctx->refs); - /* if force is set, the ring is going away. always drop after that */ - - if (WARN_ON_ONCE((ctx->flags & IORING_SETUP_SQPOLL) && !ctx->sqo_dead)) - ctx->sqo_dead = 1; - - ctx->cq_overflow_flushed = 1; if (ctx->rings) - __io_cqring_overflow_flush(ctx, true, NULL, NULL); + __io_cqring_overflow_flush(ctx, true); + xa_for_each(&ctx->personalities, index, creds) + io_unregister_personality(ctx, index); mutex_unlock(&ctx->uring_lock); - io_kill_timeouts(ctx, NULL, NULL); - io_poll_remove_all(ctx, NULL, NULL); - - if (ctx->io_wq) - io_wq_cancel_cb(ctx->io_wq, io_cancel_ctx_cb, ctx, true); + io_kill_timeouts(ctx, NULL, true); + io_poll_remove_all(ctx, NULL, true); /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); - xa_for_each(&ctx->personalities, index, iod) - io_unregister_personality(ctx, index); - - /* - * Do this upfront, so we won't have a grace period where the ring - * is closed but resources aren't reaped yet. This can cause - * spurious failure in setting up a new ring. - */ - io_unaccount_mem(ctx, ring_pages(ctx->sq_entries, ctx->cq_entries), - ACCT_LOCKED); INIT_WORK(&ctx->exit_work, io_ring_exit_work); /* @@ -8647,352 +9443,290 @@ static int io_uring_release(struct inode *inode, struct file *file) struct io_task_cancel { struct task_struct *task; - struct files_struct *files; + bool all; }; static bool io_cancel_task_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_task_cancel *cancel = data; - bool ret; - if (cancel->files && (req->flags & REQ_F_LINK_TIMEOUT)) { - unsigned long flags; - struct io_ring_ctx *ctx = req->ctx; - - /* protect against races with linked timeouts */ - spin_lock_irqsave(&ctx->completion_lock, flags); - ret = io_match_task(req, cancel->task, cancel->files); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - } else { - ret = io_match_task(req, cancel->task, cancel->files); - } - return ret; + return io_match_task_safe(req, cancel->task, cancel->all); } -static void io_cancel_defer_files(struct io_ring_ctx *ctx, - struct task_struct *task, - struct files_struct *files) +static bool io_cancel_defer_files(struct io_ring_ctx *ctx, + struct task_struct *task, bool cancel_all) { - struct io_defer_entry *de = NULL; + struct io_defer_entry *de; LIST_HEAD(list); - spin_lock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); list_for_each_entry_reverse(de, &ctx->defer_list, list) { - if (io_match_task(de->req, task, files)) { + if (io_match_task_safe(de->req, task, cancel_all)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } } - spin_unlock_irq(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); + if (list_empty(&list)) + return false; while (!list_empty(&list)) { de = list_first_entry(&list, struct io_defer_entry, list); list_del_init(&de->list); - req_set_fail_links(de->req); - io_put_req(de->req); - io_req_complete(de->req, -ECANCELED); + io_req_complete_failed(de->req, -ECANCELED); kfree(de); } + return true; } -static int io_uring_count_inflight(struct io_ring_ctx *ctx, - struct task_struct *task, - struct files_struct *files) +static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) { - struct io_kiocb *req; - int cnt = 0; + struct io_tctx_node *node; + enum io_wq_cancel cret; + bool ret = false; - spin_lock_irq(&ctx->inflight_lock); - list_for_each_entry(req, &ctx->inflight_list, inflight_entry) - cnt += io_match_task(req, task, files); - spin_unlock_irq(&ctx->inflight_lock); - return cnt; -} + mutex_lock(&ctx->uring_lock); + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; -static void io_uring_cancel_files(struct io_ring_ctx *ctx, - struct task_struct *task, - struct files_struct *files) -{ - while (!list_empty_careful(&ctx->inflight_list)) { - struct io_task_cancel cancel = { .task = task, .files = files }; - DEFINE_WAIT(wait); - int inflight; - - inflight = io_uring_count_inflight(ctx, task, files); - if (!inflight) - break; - - io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); - io_poll_remove_all(ctx, task, files); - io_kill_timeouts(ctx, task, files); - /* cancellations _may_ trigger task work */ - io_run_task_work(); - - prepare_to_wait(&task->io_uring->wait, &wait, - TASK_UNINTERRUPTIBLE); - if (inflight == io_uring_count_inflight(ctx, task, files)) - schedule(); - finish_wait(&task->io_uring->wait, &wait); + /* + * io_wq will stay alive while we hold uring_lock, because it's + * killed after ctx nodes, which requires to take the lock. + */ + if (!tctx || !tctx->io_wq) + continue; + cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); } + mutex_unlock(&ctx->uring_lock); + + return ret; } -static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, - struct task_struct *task) +static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all) { + struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; + struct io_uring_task *tctx = task ? task->io_uring : NULL; + while (1) { - struct io_task_cancel cancel = { .task = task, .files = NULL, }; enum io_wq_cancel cret; bool ret = false; - cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); - if (cret != IO_WQ_CANCEL_NOTFOUND) - ret = true; + if (!task) { + ret |= io_uring_try_cancel_iowq(ctx); + } else if (tctx && tctx->io_wq) { + /* + * Cancels requests of all rings, not only @ctx, but + * it's fine as the task is in exit/exec. + */ + cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb, + &cancel, true); + ret |= (cret != IO_WQ_CANCEL_NOTFOUND); + } /* SQPOLL thread does its own polling */ - if (!(ctx->flags & IORING_SETUP_SQPOLL)) { + if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || + (ctx->sq_data && ctx->sq_data->thread == current)) { while (!list_empty_careful(&ctx->iopoll_list)) { io_iopoll_try_reap_events(ctx); ret = true; } } - ret |= io_poll_remove_all(ctx, task, NULL); - ret |= io_kill_timeouts(ctx, task, NULL); + ret |= io_cancel_defer_files(ctx, task, cancel_all); + ret |= io_poll_remove_all(ctx, task, cancel_all); + ret |= io_kill_timeouts(ctx, task, cancel_all); + if (task) + ret |= io_run_task_work(); if (!ret) break; - io_run_task_work(); cond_resched(); } } -static void io_disable_sqo_submit(struct io_ring_ctx *ctx) +static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) { - mutex_lock(&ctx->uring_lock); - ctx->sqo_dead = 1; - if (ctx->flags & IORING_SETUP_R_DISABLED) - io_sq_offload_start(ctx); - mutex_unlock(&ctx->uring_lock); + struct io_uring_task *tctx = current->io_uring; + struct io_tctx_node *node; + int ret; - /* make sure callers enter the ring to get error */ - if (ctx->rings) - io_ring_set_wakeup_flag(ctx); -} + if (unlikely(!tctx)) { + ret = io_uring_alloc_task_context(current, ctx); + if (unlikely(ret)) + return ret; -/* - * We need to iteratively cancel requests, in case a request has dependent - * hard links. These persist even for failure of cancelations, hence keep - * looping until none are found. - */ -static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, - struct files_struct *files) -{ - struct task_struct *task = current; + tctx = current->io_uring; + if (ctx->iowq_limits_set) { + unsigned int limits[2] = { ctx->iowq_limits[0], + ctx->iowq_limits[1], }; - if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { - io_disable_sqo_submit(ctx); - task = ctx->sq_data->thread; - atomic_inc(&task->io_uring->in_idle); - io_sq_thread_park(ctx->sq_data); + ret = io_wq_max_workers(tctx->io_wq, limits); + if (ret) + return ret; + } } + if (!xa_load(&tctx->xa, (unsigned long)ctx)) { + node = kmalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + node->ctx = ctx; + node->task = current; - io_cancel_defer_files(ctx, task, files); - io_cqring_overflow_flush(ctx, true, task, files); + ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx, + node, GFP_KERNEL)); + if (ret) { + kfree(node); + return ret; + } - if (!files) - __io_uring_cancel_task_requests(ctx, task); - else - io_uring_cancel_files(ctx, task, files); - - if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { - atomic_dec(&task->io_uring->in_idle); - io_sq_thread_unpark(ctx->sq_data); + mutex_lock(&ctx->uring_lock); + list_add(&node->ctx_node, &ctx->tctx_list); + mutex_unlock(&ctx->uring_lock); } + tctx->last = ctx; + return 0; } /* * Note that this task has used io_uring. We use it for cancelation purposes. */ -static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file) +static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; - int ret; - if (unlikely(!tctx)) { - ret = io_uring_alloc_task_context(current); - if (unlikely(ret)) - return ret; - tctx = current->io_uring; - } - if (tctx->last != file) { - void *old = xa_load(&tctx->xa, (unsigned long)file); - - if (!old) { - get_file(file); - ret = xa_err(xa_store(&tctx->xa, (unsigned long)file, - file, GFP_KERNEL)); - if (ret) { - fput(file); - return ret; - } - } - tctx->last = file; - } - - /* - * This is race safe in that the task itself is doing this, hence it - * cannot be going through the exit/cancel paths at the same time. - * This cannot be modified while exit/cancel is running. - */ - if (!tctx->sqpoll && (ctx->flags & IORING_SETUP_SQPOLL)) - tctx->sqpoll = true; - - return 0; + if (likely(tctx && tctx->last == ctx)) + return 0; + return __io_uring_add_tctx_node(ctx); } /* * Remove this io_uring_file -> task mapping. */ -static void io_uring_del_task_file(struct file *file) +static void io_uring_del_tctx_node(unsigned long index) { struct io_uring_task *tctx = current->io_uring; + struct io_tctx_node *node; - if (tctx->last == file) + if (!tctx) + return; + node = xa_erase(&tctx->xa, index); + if (!node) + return; + + WARN_ON_ONCE(current != node->task); + WARN_ON_ONCE(list_empty(&node->ctx_node)); + + mutex_lock(&node->ctx->uring_lock); + list_del(&node->ctx_node); + mutex_unlock(&node->ctx->uring_lock); + + if (tctx->last == node->ctx) tctx->last = NULL; - file = xa_erase(&tctx->xa, (unsigned long)file); - if (file) - fput(file); + kfree(node); } -static void io_uring_remove_task_files(struct io_uring_task *tctx) +static void io_uring_clean_tctx(struct io_uring_task *tctx) { - struct file *file; + struct io_wq *wq = tctx->io_wq; + struct io_tctx_node *node; unsigned long index; - xa_for_each(&tctx->xa, index, file) - io_uring_del_task_file(file); -} - -void __io_uring_files_cancel(struct files_struct *files) -{ - struct io_uring_task *tctx = current->io_uring; - struct file *file; - unsigned long index; - - /* make sure overflow events are dropped */ - atomic_inc(&tctx->in_idle); - xa_for_each(&tctx->xa, index, file) - io_uring_cancel_task_requests(file->private_data, files); - atomic_dec(&tctx->in_idle); - - if (files) - io_uring_remove_task_files(tctx); -} - -static s64 tctx_inflight(struct io_uring_task *tctx) -{ - unsigned long index; - struct file *file; - s64 inflight; - - inflight = percpu_counter_sum(&tctx->inflight); - if (!tctx->sqpoll) - return inflight; - - /* - * If we have SQPOLL rings, then we need to iterate and find them, and - * add the pending count for those. - */ - xa_for_each(&tctx->xa, index, file) { - struct io_ring_ctx *ctx = file->private_data; - - if (ctx->flags & IORING_SETUP_SQPOLL) { - struct io_uring_task *__tctx = ctx->sqo_task->io_uring; - - inflight += percpu_counter_sum(&__tctx->inflight); - } + xa_for_each(&tctx->xa, index, node) { + io_uring_del_tctx_node(index); + cond_resched(); } + if (wq) { + /* + * Must be after io_uring_del_task_file() (removes nodes under + * uring_lock) to avoid race with io_uring_try_cancel_iowq(). + */ + io_wq_put_and_exit(wq); + tctx->io_wq = NULL; + } +} - return inflight; +static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) +{ + if (tracked) + return atomic_read(&tctx->inflight_tracked); + return percpu_counter_sum(&tctx->inflight); } /* - * Find any io_uring fd that this task has registered or done IO on, and cancel - * requests. + * Find any io_uring ctx that this task has registered or done IO on, and cancel + * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation. */ -void __io_uring_task_cancel(void) +static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) { struct io_uring_task *tctx = current->io_uring; - DEFINE_WAIT(wait); + struct io_ring_ctx *ctx; s64 inflight; + DEFINE_WAIT(wait); + + WARN_ON_ONCE(sqd && sqd->thread != current); + + if (!current->io_uring) + return; + if (tctx->io_wq) + io_wq_exit_start(tctx->io_wq); - /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); - - /* trigger io_disable_sqo_submit() */ - if (tctx->sqpoll) - __io_uring_files_cancel(NULL); - do { + io_uring_drop_tctx_refs(current); /* read completions before cancelations */ - inflight = tctx_inflight(tctx); + inflight = tctx_inflight(tctx, !cancel_all); if (!inflight) break; - __io_uring_files_cancel(NULL); - prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); + if (!sqd) { + struct io_tctx_node *node; + unsigned long index; + + xa_for_each(&tctx->xa, index, node) { + /* sqpoll task will cancel all its requests */ + if (node->ctx->sq_data) + continue; + io_uring_try_cancel_requests(node->ctx, current, + cancel_all); + } + } else { + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + io_uring_try_cancel_requests(ctx, current, + cancel_all); + } + + prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE); + io_run_task_work(); + io_uring_drop_tctx_refs(current); /* * If we've seen completions, retry without waiting. This * avoids a race where a completion comes in before we did * prepare_to_wait(). */ - if (inflight == tctx_inflight(tctx)) + if (inflight == tctx_inflight(tctx, !cancel_all)) schedule(); finish_wait(&tctx->wait, &wait); } while (1); - atomic_dec(&tctx->in_idle); - - io_uring_remove_task_files(tctx); + io_uring_clean_tctx(tctx); + if (cancel_all) { + /* + * We shouldn't run task_works after cancel, so just leave + * ->in_idle set for normal exit. + */ + atomic_dec(&tctx->in_idle); + /* for exec all current's requests should be gone, kill tctx */ + __io_uring_free(current); + } } -static int io_uring_flush(struct file *file, void *data) +void __io_uring_cancel(bool cancel_all) { - struct io_uring_task *tctx = current->io_uring; - struct io_ring_ctx *ctx = file->private_data; - - if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) - io_uring_cancel_task_requests(ctx, NULL); - - if (!tctx) - return 0; - - /* we should have cancelled and erased it before PF_EXITING */ - WARN_ON_ONCE((current->flags & PF_EXITING) && - xa_load(&tctx->xa, (unsigned long)file)); - - /* - * fput() is pending, will be 2 if the only other ref is our potential - * task file note. If the task is exiting, drop regardless of count. - */ - if (atomic_long_read(&file->f_count) != 2) - return 0; - - if (ctx->flags & IORING_SETUP_SQPOLL) { - /* there is only one file note, which is owned by sqo_task */ - WARN_ON_ONCE(ctx->sqo_task != current && - xa_load(&tctx->xa, (unsigned long)file)); - /* sqo_dead check is for when this happens after cancellation */ - WARN_ON_ONCE(ctx->sqo_task == current && !ctx->sqo_dead && - !xa_load(&tctx->xa, (unsigned long)file)); - - io_disable_sqo_submit(ctx); - } - - if (!(ctx->flags & IORING_SETUP_SQPOLL) || ctx->sqo_task == current) - io_uring_del_task_file(file); - return 0; + io_uring_cancel_generic(cancel_all, NULL); } static void *io_uring_validate_mmap_request(struct file *file, @@ -9067,60 +9801,84 @@ static unsigned long io_uring_nommu_get_unmapped_area(struct file *file, static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) { - int ret = 0; DEFINE_WAIT(wait); do { if (!io_sqring_full(ctx)) break; - prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE); - if (unlikely(ctx->sqo_dead)) { - ret = -EOWNERDEAD; - break; - } - if (!io_sqring_full(ctx)) break; - schedule(); } while (!signal_pending(current)); finish_wait(&ctx->sqo_sq_wait, &wait); - return ret; + return 0; +} + +static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, + struct __kernel_timespec __user **ts, + const sigset_t __user **sig) +{ + struct io_uring_getevents_arg arg; + + /* + * If EXT_ARG isn't set, then we have no timespec and the argp pointer + * is just a pointer to the sigset_t. + */ + if (!(flags & IORING_ENTER_EXT_ARG)) { + *sig = (const sigset_t __user *) argp; + *ts = NULL; + return 0; + } + + /* + * EXT_ARG is set - ensure we agree on the size of it and copy in our + * timespec and sigset_t pointers if good. + */ + if (*argsz != sizeof(arg)) + return -EINVAL; + if (copy_from_user(&arg, argp, sizeof(arg))) + return -EFAULT; + if (arg.pad) + return -EINVAL; + *sig = u64_to_user_ptr(arg.sigmask); + *argsz = arg.sigmask_sz; + *ts = u64_to_user_ptr(arg.ts); + return 0; } SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, - u32, min_complete, u32, flags, const sigset_t __user *, sig, - size_t, sigsz) + u32, min_complete, u32, flags, const void __user *, argp, + size_t, argsz) { struct io_ring_ctx *ctx; - long ret = -EBADF; int submitted = 0; struct fd f; + long ret; io_run_task_work(); - if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP | - IORING_ENTER_SQ_WAIT)) + if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP | + IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG))) return -EINVAL; f = fdget(fd); - if (!f.file) + if (unlikely(!f.file)) return -EBADF; ret = -EOPNOTSUPP; - if (f.file->f_op != &io_uring_fops) + if (unlikely(f.file->f_op != &io_uring_fops)) goto out_fput; ret = -ENXIO; ctx = f.file->private_data; - if (!percpu_ref_tryget(&ctx->refs)) + if (unlikely(!percpu_ref_tryget(&ctx->refs))) goto out_fput; ret = -EBADFD; - if (ctx->flags & IORING_SETUP_R_DISABLED) + if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED)) goto out; /* @@ -9130,9 +9888,9 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, */ ret = 0; if (ctx->flags & IORING_SETUP_SQPOLL) { - io_cqring_overflow_flush(ctx, false, NULL, NULL); + io_cqring_overflow_flush(ctx); - if (unlikely(ctx->sqo_dead)) { + if (unlikely(ctx->sq_data->thread == NULL)) { ret = -EOWNERDEAD; goto out; } @@ -9145,7 +9903,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } submitted = to_submit; } else if (to_submit) { - ret = io_uring_add_task_file(ctx, f.file); + ret = io_uring_add_tctx_node(ctx); if (unlikely(ret)) goto out; mutex_lock(&ctx->uring_lock); @@ -9156,6 +9914,13 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, goto out; } if (flags & IORING_ENTER_GETEVENTS) { + const sigset_t __user *sig; + struct __kernel_timespec __user *ts; + + ret = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); + if (unlikely(ret)) + goto out; + min_complete = min(min_complete, ctx->cq_entries); /* @@ -9168,7 +9933,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, !(ctx->flags & IORING_SETUP_SQPOLL)) { ret = io_iopoll_check(ctx, min_complete); } else { - ret = io_cqring_wait(ctx, min_complete, sig, sigsz); + ret = io_cqring_wait(ctx, min_complete, sig, argsz, ts); } } @@ -9181,9 +9946,8 @@ out_fput: #ifdef CONFIG_PROC_FS static int io_uring_show_cred(struct seq_file *m, unsigned int id, - const struct io_identity *iod) + const struct cred *cred) { - const struct cred *cred = iod->creds; struct user_namespace *uns = seq_user_ns(m); struct group_info *gi; kernel_cap_t cap; @@ -9227,18 +9991,18 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) */ has_lock = mutex_trylock(&ctx->uring_lock); - if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) + if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { sq = ctx->sq_data; + if (!sq->thread) + sq = NULL; + } seq_printf(m, "SqThread:\t%d\n", sq ? task_pid_nr(sq->thread) : -1); seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1); seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); for (i = 0; has_lock && i < ctx->nr_user_files; i++) { - struct fixed_file_table *table; - struct file *f; + struct file *f = io_file_from_index(ctx, i); - table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; - f = table->files[i & IORING_FILE_TABLE_MASK]; if (f) seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); else @@ -9246,21 +10010,21 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) } seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *buf = &ctx->user_bufs[i]; + struct io_mapped_ubuf *buf = ctx->user_bufs[i]; + unsigned int len = buf->ubuf_end - buf->ubuf; - seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, - (unsigned int) buf->len); + seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len); } if (has_lock && !xa_empty(&ctx->personalities)) { unsigned long index; - const struct io_identity *iod; + const struct cred *cred; seq_printf(m, "Personalities:\n"); - xa_for_each(&ctx->personalities, index, iod) - io_uring_show_cred(m, index, iod); + xa_for_each(&ctx->personalities, index, cred) + io_uring_show_cred(m, index, cred); } seq_printf(m, "PollList:\n"); - spin_lock_irq(&ctx->completion_lock); + spin_lock(&ctx->completion_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { struct hlist_head *list = &ctx->cancel_hash[i]; struct io_kiocb *req; @@ -9269,7 +10033,7 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) seq_printf(m, " op=%d, task_works=%d\n", req->opcode, req->task->task_works != NULL); } - spin_unlock_irq(&ctx->completion_lock); + spin_unlock(&ctx->completion_lock); if (has_lock) mutex_unlock(&ctx->uring_lock); } @@ -9287,14 +10051,12 @@ static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) static const struct file_operations io_uring_fops = { .release = io_uring_release, - .flush = io_uring_flush, .mmap = io_uring_mmap, #ifndef CONFIG_MMU .get_unmapped_area = io_uring_nommu_get_unmapped_area, .mmap_capabilities = io_uring_nommu_mmap_capabilities, #endif .poll = io_uring_poll, - .fasync = io_uring_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = io_uring_show_fdinfo, #endif @@ -9324,8 +10086,6 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, rings->cq_ring_mask = p->cq_entries - 1; rings->sq_ring_entries = p->sq_entries; rings->cq_ring_entries = p->cq_entries; - ctx->sq_mask = rings->sq_ring_mask; - ctx->cq_mask = rings->cq_ring_mask; size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); if (size == SIZE_MAX) { @@ -9352,7 +10112,7 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) if (fd < 0) return fd; - ret = io_uring_add_task_file(ctx, file); + ret = io_uring_add_tctx_node(ctx); if (ret) { put_unused_fd(fd); return ret; @@ -9395,10 +10155,8 @@ static struct file *io_uring_get_file(struct io_ring_ctx *ctx) static int io_uring_create(unsigned entries, struct io_uring_params *p, struct io_uring_params __user *params) { - struct user_struct *user = NULL; struct io_ring_ctx *ctx; struct file *file; - bool limit_mem; int ret; if (!entries) @@ -9438,34 +10196,12 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, p->cq_entries = 2 * p->sq_entries; } - user = get_uid(current_user()); - limit_mem = !capable(CAP_IPC_LOCK); - - if (limit_mem) { - ret = __io_account_mem(user, - ring_pages(p->sq_entries, p->cq_entries)); - if (ret) { - free_uid(user); - return ret; - } - } - ctx = io_ring_ctx_alloc(p); - if (!ctx) { - if (limit_mem) - __io_unaccount_mem(user, ring_pages(p->sq_entries, - p->cq_entries)); - free_uid(user); + if (!ctx) return -ENOMEM; - } ctx->compat = in_compat_syscall(); - ctx->user = user; - ctx->creds = get_current_cred(); -#ifdef CONFIG_AUDIT - ctx->loginuid = current->loginuid; - ctx->sessionid = current->sessionid; -#endif - ctx->sqo_task = get_task_struct(current); + if (!capable(CAP_IPC_LOCK)) + ctx->user = get_uid(current_user()); /* * This is just grabbed for accounting purposes. When a process exits, @@ -9476,35 +10212,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, mmgrab(current->mm); ctx->mm_account = current->mm; -#ifdef CONFIG_BLK_CGROUP - /* - * The sq thread will belong to the original cgroup it was inited in. - * If the cgroup goes offline (e.g. disabling the io controller), then - * issued bios will be associated with the closest cgroup later in the - * block layer. - */ - rcu_read_lock(); - ctx->sqo_blkcg_css = blkcg_css(); - ret = css_tryget_online(ctx->sqo_blkcg_css); - rcu_read_unlock(); - if (!ret) { - /* don't init against a dying cgroup, have the user try again */ - ctx->sqo_blkcg_css = NULL; - ret = -ENODEV; - goto err; - } -#endif - - /* - * Account memory _before_ installing the file descriptor. Once - * the descriptor is installed, it can get closed at any time. Also - * do this before hitting the general error path, as ring freeing - * will un-account as well. - */ - io_account_mem(ctx, ring_pages(p->sq_entries, p->cq_entries), - ACCT_LOCKED); - ctx->limit_mem = limit_mem; - ret = io_allocate_scq_urings(ctx, p); if (ret) goto err; @@ -9512,9 +10219,11 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, ret = io_sq_offload_create(ctx, p); if (ret) goto err; - - if (!(p->flags & IORING_SETUP_R_DISABLED)) - io_sq_offload_start(ctx); + /* always set a rsrc node */ + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + io_rsrc_node_switch(ctx, NULL); memset(&p->sq_off, 0, sizeof(p->sq_off)); p->sq_off.head = offsetof(struct io_rings, sq.head); @@ -9537,7 +10246,9 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | - IORING_FEAT_POLL_32BITS; + IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | + IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | + IORING_FEAT_RSRC_TAGS; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; @@ -9556,7 +10267,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, */ ret = io_uring_install_fd(ctx, file); if (ret < 0) { - io_disable_sqo_submit(ctx); /* fput will clean it up */ fput(file); return ret; @@ -9565,7 +10275,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: - io_disable_sqo_submit(ctx); io_ring_ctx_wait_and_kill(ctx); return ret; } @@ -9643,22 +10352,16 @@ out: static int io_register_personality(struct io_ring_ctx *ctx) { - struct io_identity *iod; + const struct cred *creds; u32 id; int ret; - iod = kmalloc(sizeof(*iod), GFP_KERNEL); - if (unlikely(!iod)) - return -ENOMEM; + creds = get_current_cred(); - io_init_identity(iod); - iod->creds = get_current_cred(); - - ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)iod, + ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds, XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL); if (ret < 0) { - put_cred(iod->creds); - kfree(iod); + put_cred(creds); return ret; } return id; @@ -9742,24 +10445,273 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx) if (ctx->restrictions.registered) ctx->restricted = 1; - io_sq_offload_start(ctx); + ctx->flags &= ~IORING_SETUP_R_DISABLED; + if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); return 0; } +static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, + struct io_uring_rsrc_update2 *up, + unsigned nr_args) +{ + __u32 tmp; + int err; + + if (check_add_overflow(up->offset, nr_args, &tmp)) + return -EOVERFLOW; + err = io_rsrc_node_switch_start(ctx); + if (err) + return err; + + switch (type) { + case IORING_RSRC_FILE: + return __io_sqe_files_update(ctx, up, nr_args); + case IORING_RSRC_BUFFER: + return __io_sqe_buffers_update(ctx, up, nr_args); + } + return -EINVAL; +} + +static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct io_uring_rsrc_update2 up; + + if (!nr_args) + return -EINVAL; + memset(&up, 0, sizeof(up)); + if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) + return -EFAULT; + if (up.resv || up.resv2) + return -EINVAL; + return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); +} + +static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned size, unsigned type) +{ + struct io_uring_rsrc_update2 up; + + if (size != sizeof(up)) + return -EINVAL; + if (copy_from_user(&up, arg, sizeof(up))) + return -EFAULT; + if (!up.nr || up.resv || up.resv2) + return -EINVAL; + return __io_register_rsrc_update(ctx, type, &up, up.nr); +} + +static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, + unsigned int size, unsigned int type) +{ + struct io_uring_rsrc_register rr; + + /* keep it extendible */ + if (size != sizeof(rr)) + return -EINVAL; + + memset(&rr, 0, sizeof(rr)); + if (copy_from_user(&rr, arg, size)) + return -EFAULT; + if (!rr.nr || rr.resv || rr.resv2) + return -EINVAL; + + switch (type) { + case IORING_RSRC_FILE: + return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), + rr.nr, u64_to_user_ptr(rr.tags)); + case IORING_RSRC_BUFFER: + return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data), + rr.nr, u64_to_user_ptr(rr.tags)); + } + return -EINVAL; +} + +static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg, + unsigned len) +{ + struct io_uring_task *tctx = current->io_uring; + cpumask_var_t new_mask; + int ret; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_clear(new_mask); + if (len > cpumask_size()) + len = cpumask_size(); + +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) { + ret = compat_get_bitmap(cpumask_bits(new_mask), + (const compat_ulong_t __user *)arg, + len * 8 /* CHAR_BIT */); + } else { + ret = copy_from_user(new_mask, arg, len); + } +#else + ret = copy_from_user(new_mask, arg, len); +#endif + + if (ret) { + free_cpumask_var(new_mask); + return -EFAULT; + } + + ret = io_wq_cpu_affinity(tctx->io_wq, new_mask); + free_cpumask_var(new_mask); + return ret; +} + +static int io_unregister_iowq_aff(struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + return io_wq_cpu_affinity(tctx->io_wq, NULL); +} + +static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, + void __user *arg) + __must_hold(&ctx->uring_lock) +{ + struct io_tctx_node *node; + struct io_uring_task *tctx = NULL; + struct io_sq_data *sqd = NULL; + __u32 new_count[2]; + int i, ret; + + if (copy_from_user(new_count, arg, sizeof(new_count))) + return -EFAULT; + for (i = 0; i < ARRAY_SIZE(new_count); i++) + if (new_count[i] > INT_MAX) + return -EINVAL; + + if (ctx->flags & IORING_SETUP_SQPOLL) { + sqd = ctx->sq_data; + if (sqd) { + /* + * Observe the correct sqd->lock -> ctx->uring_lock + * ordering. Fine to drop uring_lock here, we hold + * a ref to the ctx. + */ + refcount_inc(&sqd->refs); + mutex_unlock(&ctx->uring_lock); + mutex_lock(&sqd->lock); + mutex_lock(&ctx->uring_lock); + if (sqd->thread) + tctx = sqd->thread->io_uring; + } + } else { + tctx = current->io_uring; + } + + BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits)); + + for (i = 0; i < ARRAY_SIZE(new_count); i++) + if (new_count[i]) + ctx->iowq_limits[i] = new_count[i]; + ctx->iowq_limits_set = true; + + ret = -EINVAL; + if (tctx && tctx->io_wq) { + ret = io_wq_max_workers(tctx->io_wq, new_count); + if (ret) + goto err; + } else { + memset(new_count, 0, sizeof(new_count)); + } + + if (sqd) { + mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } + + if (copy_to_user(arg, new_count, sizeof(new_count))) + return -EFAULT; + + /* that's it for SQPOLL, only the SQPOLL task creates requests */ + if (sqd) + return 0; + + /* now propagate the restriction to all registered users */ + list_for_each_entry(node, &ctx->tctx_list, ctx_node) { + struct io_uring_task *tctx = node->task->io_uring; + + if (WARN_ON_ONCE(!tctx->io_wq)) + continue; + + for (i = 0; i < ARRAY_SIZE(new_count); i++) + new_count[i] = ctx->iowq_limits[i]; + /* ignore errors, it always returns zero anyway */ + (void)io_wq_max_workers(tctx->io_wq, new_count); + } + return 0; +err: + if (sqd) { + mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } + return ret; +} + static bool io_register_op_must_quiesce(int op) { switch (op) { + case IORING_REGISTER_BUFFERS: + case IORING_UNREGISTER_BUFFERS: + case IORING_REGISTER_FILES: case IORING_UNREGISTER_FILES: case IORING_REGISTER_FILES_UPDATE: case IORING_REGISTER_PROBE: case IORING_REGISTER_PERSONALITY: case IORING_UNREGISTER_PERSONALITY: + case IORING_REGISTER_FILES2: + case IORING_REGISTER_FILES_UPDATE2: + case IORING_REGISTER_BUFFERS2: + case IORING_REGISTER_BUFFERS_UPDATE: + case IORING_REGISTER_IOWQ_AFF: + case IORING_UNREGISTER_IOWQ_AFF: + case IORING_REGISTER_IOWQ_MAX_WORKERS: return false; default: return true; } } +static int io_ctx_quiesce(struct io_ring_ctx *ctx) +{ + long ret; + + percpu_ref_kill(&ctx->refs); + + /* + * Drop uring mutex before waiting for references to exit. If another + * thread is currently inside io_uring_enter() it might need to grab the + * uring_lock to make progress. If we hold it here across the drain + * wait, then we can deadlock. It's safe to drop the mutex here, since + * no new references will come in after we've killed the percpu ref. + */ + mutex_unlock(&ctx->uring_lock); + do { + ret = wait_for_completion_interruptible(&ctx->ref_comp); + if (!ret) + break; + ret = io_run_task_work_sig(); + } while (ret >= 0); + mutex_lock(&ctx->uring_lock); + + if (ret) + io_refs_resurrect(&ctx->refs, &ctx->ref_comp); + return ret; +} + static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) __releases(ctx->uring_lock) @@ -9775,58 +10727,32 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, if (percpu_ref_is_dying(&ctx->refs)) return -ENXIO; - if (io_register_op_must_quiesce(opcode)) { - percpu_ref_kill(&ctx->refs); - - /* - * Drop uring mutex before waiting for references to exit. If - * another thread is currently inside io_uring_enter() it might - * need to grab the uring_lock to make progress. If we hold it - * here across the drain wait, then we can deadlock. It's safe - * to drop the mutex here, since no new references will come in - * after we've killed the percpu ref. - */ - mutex_unlock(&ctx->uring_lock); - do { - ret = wait_for_completion_interruptible(&ctx->ref_comp); - if (!ret) - break; - ret = io_run_task_work_sig(); - if (ret < 0) - break; - } while (1); - mutex_lock(&ctx->uring_lock); - - if (ret) { - io_refs_resurrect(&ctx->refs, &ctx->ref_comp); - return ret; - } + if (ctx->restricted) { + if (opcode >= IORING_REGISTER_LAST) + return -EINVAL; + opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); + if (!test_bit(opcode, ctx->restrictions.register_op)) + return -EACCES; } - if (ctx->restricted) { - if (opcode >= IORING_REGISTER_LAST) { - ret = -EINVAL; - goto out; - } - - if (!test_bit(opcode, ctx->restrictions.register_op)) { - ret = -EACCES; - goto out; - } + if (io_register_op_must_quiesce(opcode)) { + ret = io_ctx_quiesce(ctx); + if (ret) + return ret; } switch (opcode) { case IORING_REGISTER_BUFFERS: - ret = io_sqe_buffer_register(ctx, arg, nr_args); + ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_BUFFERS: ret = -EINVAL; if (arg || nr_args) break; - ret = io_sqe_buffer_unregister(ctx); + ret = io_sqe_buffers_unregister(ctx); break; case IORING_REGISTER_FILES: - ret = io_sqe_files_register(ctx, arg, nr_args); + ret = io_sqe_files_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_FILES: ret = -EINVAL; @@ -9835,7 +10761,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, ret = io_sqe_files_unregister(ctx); break; case IORING_REGISTER_FILES_UPDATE: - ret = io_sqe_files_update(ctx, arg, nr_args); + ret = io_register_files_update(ctx, arg, nr_args); break; case IORING_REGISTER_EVENTFD: case IORING_REGISTER_EVENTFD_ASYNC: @@ -9883,12 +10809,43 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, case IORING_REGISTER_RESTRICTIONS: ret = io_register_restrictions(ctx, arg, nr_args); break; + case IORING_REGISTER_FILES2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE); + break; + case IORING_REGISTER_FILES_UPDATE2: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_FILE); + break; + case IORING_REGISTER_BUFFERS2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER); + break; + case IORING_REGISTER_BUFFERS_UPDATE: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_BUFFER); + break; + case IORING_REGISTER_IOWQ_AFF: + ret = -EINVAL; + if (!arg || !nr_args) + break; + ret = io_register_iowq_aff(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_IOWQ_AFF: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_unregister_iowq_aff(ctx); + break; + case IORING_REGISTER_IOWQ_MAX_WORKERS: + ret = -EINVAL; + if (!arg || nr_args != 2) + break; + ret = io_register_iowq_max_workers(ctx, arg); + break; default: ret = -EINVAL; break; } -out: if (io_register_op_must_quiesce(opcode)) { /* bring the ctx back to life */ percpu_ref_reinit(&ctx->refs); @@ -9914,6 +10871,8 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, ctx = f.file->private_data; + io_run_task_work(); + mutex_lock(&ctx->uring_lock); ret = __io_uring_register(ctx, opcode, arg, nr_args); mutex_unlock(&ctx->uring_lock); @@ -9960,12 +10919,27 @@ static int __init io_uring_init(void) BUILD_BUG_SQE_ELEM(28, __u32, splice_flags); BUILD_BUG_SQE_ELEM(32, __u64, user_data); BUILD_BUG_SQE_ELEM(40, __u16, buf_index); + BUILD_BUG_SQE_ELEM(40, __u16, buf_group); BUILD_BUG_SQE_ELEM(42, __u16, personality); BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); + BUILD_BUG_SQE_ELEM(44, __u32, file_index); + + BUILD_BUG_ON(sizeof(struct io_uring_files_update) != + sizeof(struct io_uring_rsrc_update)); + BUILD_BUG_ON(sizeof(struct io_uring_rsrc_update) > + sizeof(struct io_uring_rsrc_update2)); + + /* ->buf_index is u16 */ + BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16)); + + /* should fit into one byte */ + BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); - BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int)); - req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC); + BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int)); + + req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | + SLAB_ACCOUNT); return 0; }; __initcall(io_uring_init); diff --git a/kernel/exit.c b/kernel/exit.c index ab900b661867..8989e1d1f79b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -763,7 +763,7 @@ void __noreturn do_exit(long code) schedule(); } - io_uring_files_cancel(tsk->files); + io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ /* sync mm's RSS info before statistics gathering */ diff --git a/kernel/fork.c b/kernel/fork.c index 55c1a880a281..68efe2a0b4fb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -926,6 +926,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; + tsk->pf_io_worker = NULL; account_kernel_stack(tsk, 1); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index da96a309eefe..a875bc59804e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -21,7 +21,7 @@ #include #include "../workqueue_internal.h" -#include "../../fs/io-wq.h" +#include "../../io_uring/io-wq.h" #include "../smpboot.h" #include "pelt.h" From c91ab04781f9e46c1a2143bd1ba8fc1f1aff6ebc Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 9 Oct 2020 16:03:01 -0600 Subject: [PATCH 0074/4345] signal: kill JOBCTL_TASK_WORK [ Upstream commit 98b89b649fce39dacb9dc036d6d0fdb8caff73f7 ] It's no longer used, get rid of it. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/sched/jobctl.h | 4 +--- kernel/signal.c | 20 -------------------- 2 files changed, 1 insertion(+), 23 deletions(-) diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index d2b4204ba4d3..fa067de9f1a9 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -19,7 +19,6 @@ struct task_struct; #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ -#define JOBCTL_TASK_WORK_BIT 24 /* set by TWA_SIGNAL */ #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) @@ -29,10 +28,9 @@ struct task_struct; #define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) #define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) -#define JOBCTL_TASK_WORK (1UL << JOBCTL_TASK_WORK_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) -#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK) +#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask); extern void task_clear_jobctl_trapping(struct task_struct *task); diff --git a/kernel/signal.c b/kernel/signal.c index fb5473724f5d..f528a91d6734 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2544,26 +2544,6 @@ bool get_signal(struct ksignal *ksig) relock: spin_lock_irq(&sighand->siglock); - /* - * Make sure we can safely read ->jobctl() in task_work add. As Oleg - * states: - * - * It pairs with mb (implied by cmpxchg) before READ_ONCE. So we - * roughly have - * - * task_work_add: get_signal: - * STORE(task->task_works, new_work); STORE(task->jobctl); - * mb(); mb(); - * LOAD(task->jobctl); LOAD(task->task_works); - * - * and we can rely on STORE-MB-LOAD [ in task_work_add]. - */ - smp_store_mb(current->jobctl, current->jobctl & ~JOBCTL_TASK_WORK); - if (unlikely(current->task_works)) { - spin_unlock_irq(&sighand->siglock); - task_work_run(); - goto relock; - } /* * Every stopped thread goes here after wakeup. Check to see if From 6ef2b4728a00c98cc1163212443e39d79a4c2c94 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 5 Jan 2021 11:32:43 -0700 Subject: [PATCH 0075/4345] task_work: unconditionally run task_work from get_signal() [ Upstream commit 35d0b389f3b23439ad15b610d6e43fc72fc75779 ] Song reported a boot regression in a kvm image with 5.11-rc, and bisected it down to the below patch. Debugging this issue, turns out that the boot stalled when a task is waiting on a pipe being released. As we no longer run task_work from get_signal() unless it's queued with TWA_SIGNAL, the task goes idle without running the task_work. This prevents ->release() from being called on the pipe, which another boot task is waiting on. For now, re-instate the unconditional task_work run from get_signal(). For 5.12, we'll collapse TWA_RESUME and TWA_SIGNAL, as it no longer makes sense to have a distinction between the two. This will turn task_work notification into a simple boolean, whether to notify or not. Fixes: 98b89b649fce ("signal: kill JOBCTL_TASK_WORK") Reported-by: Song Liu Tested-by: John Stultz Tested-by: Douglas Anderson Tested-by: Sedat Dilek # LLVM/Clang version 11.0.1 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- kernel/signal.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/signal.c b/kernel/signal.c index f528a91d6734..e487c4660921 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2520,6 +2520,9 @@ bool get_signal(struct ksignal *ksig) struct signal_struct *signal = current->signal; int signr; + if (unlikely(current->task_works)) + task_work_run(); + /* * For non-generic architectures, check for TIF_NOTIFY_SIGNAL so * that the arch handlers don't all have to do it. If we get here From a3025359ffa707b484b23f4df37425f36e6955fd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 17 Feb 2021 10:14:21 -0700 Subject: [PATCH 0076/4345] net: remove cmsg restriction from io_uring based send/recvmsg calls [ Upstream commit e54937963fa249595824439dc839c948188dea83 ] No need to restrict these anymore, as the worker threads are direct clones of the original task. Hence we know for a fact that we can support anything that the regular task can. Since the only user of proto_ops->flags was to flag PROTO_CMSG_DATA_ONLY, kill the member and the flag definition too. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/net.h | 3 --- net/ipv4/af_inet.c | 1 - net/ipv6/af_inet6.c | 1 - net/socket.c | 10 ---------- 4 files changed, 15 deletions(-) diff --git a/include/linux/net.h b/include/linux/net.h index 0dcd51feef02..ae713c851342 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -42,8 +42,6 @@ struct net; #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 -#define PROTO_CMSG_DATA_ONLY 0x0001 - #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types @@ -138,7 +136,6 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, struct proto_ops { int family; - unsigned int flags; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 48223c264991..8dab0d311aba 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1017,7 +1017,6 @@ static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon const struct proto_ops inet_stream_ops = { .family = PF_INET, - .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d30c9d949c1b..4df9dc9375c8 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -661,7 +661,6 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, const struct proto_ops inet6_stream_ops = { .family = PF_INET6, - .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, diff --git a/net/socket.c b/net/socket.c index 56c218dc80ce..8657112a687a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2419,10 +2419,6 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { - /* disallow ancillary data requests from this path */ - if (msg->msg_control || msg->msg_controllen) - return -EINVAL; - return ____sys_sendmsg(sock, msg, flags, NULL, 0); } @@ -2631,12 +2627,6 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { - if (msg->msg_control || msg->msg_controllen) { - /* disallow ancillary data reqs unless cmsg is plain data */ - if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY)) - return -EINVAL; - } - return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } From 87cb08dc6b4f42a491e582d3ee79c30893681193 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 15 Feb 2021 13:42:18 -0700 Subject: [PATCH 0077/4345] Revert "proc: don't allow async path resolution of /proc/thread-self components" [ Upstream commit 2587890b5e2892dfecaa5e5126bdac8076a4e6f7 ] This reverts commit 0d4370cfe36b7f1719123b621a4ec4d9c7a25f89. No longer needed, as the io-wq worker threads have the right identity. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/proc/self.c | 2 +- fs/proc/thread_self.c | 7 ------- 2 files changed, 1 insertion(+), 8 deletions(-) diff --git a/fs/proc/self.c b/fs/proc/self.c index a4012154e109..cc71ce3466dc 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -20,7 +20,7 @@ static const char *proc_self_get_link(struct dentry *dentry, * Not currently supported. Once we can inherit all of struct pid, * we can allow this. */ - if (current->flags & PF_IO_WORKER) + if (current->flags & PF_KTHREAD) return ERR_PTR(-EOPNOTSUPP); if (!tgid) diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index d56681d86d28..a553273fbd41 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -17,13 +17,6 @@ static const char *proc_thread_self_get_link(struct dentry *dentry, pid_t pid = task_pid_nr_ns(current, ns); char *name; - /* - * Not currently supported. Once we can inherit all of struct pid, - * we can allow this. - */ - if (current->flags & PF_IO_WORKER) - return ERR_PTR(-EOPNOTSUPP); - if (!pid) return ERR_PTR(-ENOENT); name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); From b76c5373f084c802964e751efb825934a9bbbbec Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 15 Feb 2021 13:42:42 -0700 Subject: [PATCH 0078/4345] Revert "proc: don't allow async path resolution of /proc/self components" [ Upstream commit 9e8d9e829c2142cf1d7756e9ed2e0b4c7569d84c ] This reverts commit 8d4c3e76e3be11a64df95ddee52e99092d42fc19. No longer needed, as the io-wq worker threads have the right identity. Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/proc/self.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/fs/proc/self.c b/fs/proc/self.c index cc71ce3466dc..72cd69bcaf4a 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,13 +16,6 @@ static const char *proc_self_get_link(struct dentry *dentry, pid_t tgid = task_tgid_nr_ns(current, ns); char *name; - /* - * Not currently supported. Once we can inherit all of struct pid, - * we can allow this. - */ - if (current->flags & PF_KTHREAD) - return ERR_PTR(-EOPNOTSUPP); - if (!tgid) return ERR_PTR(-ENOENT); /* max length of unsigned int in decimal + NULL term */ From 2f093775022b45253b0d8df0e7296e7bc0d13a7b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 20 Nov 2022 10:10:53 -0700 Subject: [PATCH 0079/4345] eventpoll: add EPOLL_URING_WAKE poll wakeup flag [ Upstream commit caf1aeaffc3b09649a56769e559333ae2c4f1802 ] We can have dependencies between epoll and io_uring. Consider an epoll context, identified by the epfd file descriptor, and an io_uring file descriptor identified by iofd. If we add iofd to the epfd context, and arm a multishot poll request for epfd with iofd, then the multishot poll request will repeatedly trigger and generate events until terminated by CQ ring overflow. This isn't a desired behavior. Add EPOLL_URING so that io_uring can pass it in as part of the poll wakeup key, and io_uring can check for that to detect a potential recursive invocation. Cc: stable@vger.kernel.org # 6.0 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/eventpoll.c | 18 ++++++++++-------- include/uapi/linux/eventpoll.h | 6 ++++++ 2 files changed, 16 insertions(+), 8 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 2f1f05315709..13d4c3d50412 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -548,7 +548,8 @@ out_unlock: */ #ifdef CONFIG_DEBUG_LOCK_ALLOC -static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi) +static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, + unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; @@ -579,16 +580,17 @@ static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi) } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; - wake_up_locked_poll(&ep->poll_wait, EPOLLIN); + wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else -static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi) +static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, + unsigned pollflags) { - wake_up_poll(&ep->poll_wait, EPOLLIN); + wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif @@ -815,7 +817,7 @@ static void ep_free(struct eventpoll *ep) /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) - ep_poll_safewake(ep, NULL); + ep_poll_safewake(ep, NULL, 0); /* * We need to lock this because we could be hit by @@ -1284,7 +1286,7 @@ out_unlock: /* We have to call this outside the lock */ if (pwake) - ep_poll_safewake(ep, epi); + ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; @@ -1589,7 +1591,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, /* We have to call this outside the lock */ if (pwake) - ep_poll_safewake(ep, NULL); + ep_poll_safewake(ep, NULL, 0); return 0; @@ -1692,7 +1694,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, /* We have to call this outside the lock */ if (pwake) - ep_poll_safewake(ep, NULL); + ep_poll_safewake(ep, NULL, 0); return 0; } diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h index 8a3432d0f0dc..e687658843b1 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -41,6 +41,12 @@ #define EPOLLMSG (__force __poll_t)0x00000400 #define EPOLLRDHUP (__force __poll_t)0x00002000 +/* + * Internal flag - wakeup generated by io_uring, used to detect recursion back + * into the io_uring poll handler. + */ +#define EPOLL_URING_WAKE ((__force __poll_t)(1U << 27)) + /* Set exclusive wakeup mode for the target file descriptor */ #define EPOLLEXCLUSIVE ((__force __poll_t)(1U << 28)) From 4ef66581d7fdbd9bfe0b399c1a2479f8ea5cfdf0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 20 Nov 2022 10:13:44 -0700 Subject: [PATCH 0080/4345] eventfd: provide a eventfd_signal_mask() helper [ Upstream commit 03e02acda8e267a8183e1e0ed289ff1ef9cd7ed8 ] This is identical to eventfd_signal(), but it allows the caller to pass in a mask to be used for the poll wakeup key. The use case is avoiding repeated multishot triggers if we have a dependency between eventfd and io_uring. If we setup an eventfd context and register that as the io_uring eventfd, and at the same time queue a multishot poll request for the eventfd context, then any CQE posted will repeatedly trigger the multishot request until it terminates when the CQ ring overflows. In preparation for io_uring detecting this circular dependency, add the mentioned helper so that io_uring can pass in EPOLL_URING as part of the poll wakeup key. Cc: stable@vger.kernel.org # 6.0 [axboe: fold in !CONFIG_EVENTFD fix from Zhang Qilong] Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/eventfd.c | 37 +++++++++++++++++++++---------------- include/linux/eventfd.h | 7 +++++++ 2 files changed, 28 insertions(+), 16 deletions(-) diff --git a/fs/eventfd.c b/fs/eventfd.c index df466ef81ddd..4a14295cffe0 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -45,21 +45,7 @@ struct eventfd_ctx { int id; }; -/** - * eventfd_signal - Adds @n to the eventfd counter. - * @ctx: [in] Pointer to the eventfd context. - * @n: [in] Value of the counter to be added to the eventfd internal counter. - * The value cannot be negative. - * - * This function is supposed to be called by the kernel in paths that do not - * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX - * value, and we signal this as overflow condition by returning a EPOLLERR - * to poll(2). - * - * Returns the amount by which the counter was incremented. This will be less - * than @n if the counter has overflowed. - */ -__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask) { unsigned long flags; @@ -80,12 +66,31 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) n = ULLONG_MAX - ctx->count; ctx->count += n; if (waitqueue_active(&ctx->wqh)) - wake_up_locked_poll(&ctx->wqh, EPOLLIN); + wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask); this_cpu_dec(eventfd_wake_count); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return n; } + +/** + * eventfd_signal - Adds @n to the eventfd counter. + * @ctx: [in] Pointer to the eventfd context. + * @n: [in] Value of the counter to be added to the eventfd internal counter. + * The value cannot be negative. + * + * This function is supposed to be called by the kernel in paths that do not + * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX + * value, and we signal this as overflow condition by returning a EPOLLERR + * to poll(2). + * + * Returns the amount by which the counter was incremented. This will be less + * than @n if the counter has overflowed. + */ +__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) +{ + return eventfd_signal_mask(ctx, n, 0); +} EXPORT_SYMBOL_GPL(eventfd_signal); static void eventfd_free_ctx(struct eventfd_ctx *ctx) diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index dc4fd8a6644d..ce1cf42740bf 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -39,6 +39,7 @@ struct file *eventfd_fget(int fd); struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); @@ -66,6 +67,12 @@ static inline int eventfd_signal(struct eventfd_ctx *ctx, int n) return -ENOSYS; } +static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, + unsigned mask) +{ + return -ENOSYS; +} + static inline void eventfd_ctx_put(struct eventfd_ctx *ctx) { From 189556b05e1770263c43fa5b4c689e7cd3fa5b4e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Dec 2022 07:04:49 -0700 Subject: [PATCH 0081/4345] io_uring: pass in EPOLL_URING_WAKE for eventfd signaling and wakeups [ Upstream commit 4464853277d0ccdb9914608dd1332f0fa2f9846f ] Pass in EPOLL_URING_WAKE when signaling eventfd or doing poll related wakups, so that we can check for a circular event dependency between eventfd and epoll. If this flag is set when our wakeup handlers are called, then we know we have a dependency that needs to terminate multishot requests. eventfd and epoll are the only such possible dependencies. Cc: stable@vger.kernel.org # 6.0 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 473dbd1830a3..945faf036ad0 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1626,13 +1626,15 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) * wake as many waiters as we need to. */ if (wq_has_sleeper(&ctx->cq_wait)) - wake_up_all(&ctx->cq_wait); + __wake_up(&ctx->cq_wait, TASK_NORMAL, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) - eventfd_signal(ctx->cq_ev_fd, 1); + eventfd_signal_mask(ctx->cq_ev_fd, 1, EPOLL_URING_WAKE); if (waitqueue_active(&ctx->poll_wait)) - wake_up_interruptible(&ctx->poll_wait); + __wake_up(&ctx->poll_wait, TASK_INTERRUPTIBLE, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) @@ -1642,12 +1644,14 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) if (ctx->flags & IORING_SETUP_SQPOLL) { if (waitqueue_active(&ctx->cq_wait)) - wake_up_all(&ctx->cq_wait); + __wake_up(&ctx->cq_wait, TASK_NORMAL, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } if (io_should_trigger_evfd(ctx)) - eventfd_signal(ctx->cq_ev_fd, 1); + eventfd_signal_mask(ctx->cq_ev_fd, 1, EPOLL_URING_WAKE); if (waitqueue_active(&ctx->poll_wait)) - wake_up_interruptible(&ctx->poll_wait); + __wake_up(&ctx->poll_wait, TASK_INTERRUPTIBLE, 0, + poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } /* Returns true if there are no backlogged entries after the flush */ @@ -5477,8 +5481,17 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (mask && !(mask & poll->events)) return 0; - if (io_poll_get_ownership(req)) + if (io_poll_get_ownership(req)) { + /* + * If we trigger a multishot poll off our own wakeup path, + * disable multishot as there is a circular dependency between + * CQ posting and triggering the event. + */ + if (mask & EPOLL_URING_WAKE) + poll->events |= EPOLLONESHOT; + __io_poll_execute(req, mask); + } return 1; } From 0fe4548663f7dc2c3b549ef54ce9bb6d40a235be Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 4 Jan 2023 11:39:24 +0100 Subject: [PATCH 0082/4345] Linux 5.10.162 Link: https://lore.kernel.org/r/20230103081308.548338576@linuxfoundation.org Tested-by: Pavel Machek (CIP) Tested-by: Guenter Roeck Tested-by: Jon Hunter Tested-by: Linux Kernel Functional Testing Tested-by: Salvatore Bonaccorso Tested-by: Florian Fainelli Tested-by: Allen Pais Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 14bb1bb37770..33422c7d149e 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 161 +SUBLEVEL = 162 EXTRAVERSION = NAME = Dare mighty things From 60184b1437db4152096cebde5f364411cfaf8501 Mon Sep 17 00:00:00 2001 From: Ivaylo Dimitrov Date: Fri, 25 Nov 2022 20:21:15 +0200 Subject: [PATCH 0083/4345] usb: musb: remove extra check in musb_gadget_vbus_draw [ Upstream commit ecec4b20d29c3d6922dafe7d2555254a454272d2 ] The checks for musb->xceiv and musb->xceiv->set_power duplicate those in usb_phy_set_power(), so there is no need of them. Moreover, not calling usb_phy_set_power() results in usb_phy_set_charger_current() not being called, so current USB config max current is not propagated through USB charger framework and charger drivers may try to draw more current than allowed or possible. Fix that by removing those extra checks and calling usb_phy_set_power() directly. Tested on Motorola Droid4 and Nokia N900 Fixes: a9081a008f84 ("usb: phy: Add USB charger support") Cc: stable Signed-off-by: Ivaylo Dimitrov Link: https://lore.kernel.org/r/1669400475-4762-1-git-send-email-ivo.g.dimitrov.75@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/musb/musb_gadget.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index c273eee35aaa..8dc657c71541 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -1628,8 +1628,6 @@ static int musb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA) { struct musb *musb = gadget_to_musb(gadget); - if (!musb->xceiv->set_power) - return -EOPNOTSUPP; return usb_phy_set_power(musb->xceiv, mA); } From 6cad948c9f4a480444b3d5afa99ef0f48da0349a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 6 Oct 2022 14:46:26 +0200 Subject: [PATCH 0084/4345] arm64: dts: qcom: ipq6018-cp01-c1: use BLSPI1 pins [ Upstream commit 4871d3c38893c8a585e3e96364b7fb91cda8322e ] When BLSPI1 (originally SPI0, later renamed in commit f82c48d46852 ("arm64: dts: qcom: ipq6018: correct QUP peripheral labels")) was added, the device node lacked respective pin configuration assignment. Fixes: 5bf635621245 ("arm64: dts: ipq6018: Add a few device nodes") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Bjorn Andersson Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221006124659.217540-2-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq6018-cp01-c1.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/ipq6018-cp01-c1.dts b/arch/arm64/boot/dts/qcom/ipq6018-cp01-c1.dts index e8eaa958c199..b867506bc7e1 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018-cp01-c1.dts +++ b/arch/arm64/boot/dts/qcom/ipq6018-cp01-c1.dts @@ -37,6 +37,8 @@ &spi_0 { cs-select = <0>; + pinctrl-0 = <&spi_0_pins>; + pinctrl-names = "default"; status = "okay"; m25p80@0 { From 5465b9a813fb700f125d03fc27459c19a71d8c40 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sun, 24 Jul 2022 17:04:20 +0300 Subject: [PATCH 0085/4345] arm64: dts: qcom: msm8996: fix GPU OPP table [ Upstream commit 0d440d811e6e2f37093e54db55bc27fe66678170 ] Fix Adreno OPP table according to the msm-3.18. Enable 624 MHz for the speed bin 3 and 560 MHz for bins 2 and 3. Fixes: 69cc3114ab0f ("arm64: dts: Add Adreno GPU definitions") Signed-off-by: Dmitry Baryshkov Acked-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220724140421.1933004-7-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8996.dtsi | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index ef5d03a15069..bc140269e4cc 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -651,17 +651,17 @@ compatible ="operating-points-v2"; /* - * 624Mhz and 560Mhz are only available on speed - * bin (1 << 0). All the rest are available on - * all bins of the hardware + * 624Mhz is only available on speed bins 0 and 3. + * 560Mhz is only available on speed bins 0, 2 and 3. + * All the rest are available on all bins of the hardware. */ opp-624000000 { opp-hz = /bits/ 64 <624000000>; - opp-supported-hw = <0x01>; + opp-supported-hw = <0x09>; }; opp-560000000 { opp-hz = /bits/ 64 <560000000>; - opp-supported-hw = <0x01>; + opp-supported-hw = <0x0d>; }; opp-510000000 { opp-hz = /bits/ 64 <510000000>; From 4cef81dec2f1ef42153e5d1eb4f1ac048e185fc8 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Thu, 13 Oct 2022 21:06:57 +0200 Subject: [PATCH 0086/4345] ARM: dts: qcom: apq8064: fix coresight compatible [ Upstream commit a42b1ee868361f1cb0492f1bdaefb43e0751e468 ] There's a typo missing the arm, prefix of arm,coresight-etb10. Fix it to make devicetree validation happier. Signed-off-by: Luca Weiss Fixes: 7a5c275fd821 ("ARM: dts: qcom: Add apq8064 CoreSight components") Reviewed-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221013190657.48499-3-luca@z3ntu.xyz Signed-off-by: Sasha Levin --- arch/arm/boot/dts/qcom-apq8064.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi index 72c4a9fc41a2..fb25ede1ce9f 100644 --- a/arch/arm/boot/dts/qcom-apq8064.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064.dtsi @@ -1571,7 +1571,7 @@ }; etb@1a01000 { - compatible = "coresight-etb10", "arm,primecell"; + compatible = "arm,coresight-etb10", "arm,primecell"; reg = <0x1a01000 0x1000>; clocks = <&rpmcc RPM_QDSS_CLK>; From 82569f7e4044cffabbb4d90ca974d903a0ffb8ca Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 10 Oct 2022 07:44:12 -0400 Subject: [PATCH 0087/4345] arm64: dts: qcom: sdm630: fix UART1 pin bias [ Upstream commit 780f836fe071a9e8703fe6a05ae00129acf83391 ] There is no "bias-no-pull" property. Assume intentions were disabling bias. Fixes: b190fb010664 ("arm64: dts: qcom: sdm630: Add sdm630 dts file") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Douglas Anderson Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221010114417.29859-1-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm630.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi index f87054575ce7..79d260c2b3c3 100644 --- a/arch/arm64/boot/dts/qcom/sdm630.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi @@ -593,7 +593,7 @@ pins = "gpio17", "gpio18", "gpio19"; function = "gpio"; drive-strength = <2>; - bias-no-pull; + bias-disable; }; }; From 82baee2263b73d51811d36e3ae45bf2f1122f9f8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 10 Oct 2022 07:44:14 -0400 Subject: [PATCH 0088/4345] arm64: dts: qcom: sdm845-cheza: fix AP suspend pin bias [ Upstream commit 9bce41fab14da8f21027dc9847535ef5e22cbe8b ] There is no "bias-no-pull" property. Assume intentions were disabling bias. Fixes: 79e7739f7b87 ("arm64: dts: qcom: sdm845-cheza: add initial cheza dt") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Douglas Anderson Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221010114417.29859-3-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi index 64fc1bfd66fa..26f6f193bd1b 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi @@ -1292,7 +1292,7 @@ ap_ts_i2c: &i2c14 { config { pins = "gpio126"; function = "gpio"; - bias-no-pull; + bias-disable; drive-strength = <2>; output-low; }; @@ -1302,7 +1302,7 @@ ap_ts_i2c: &i2c14 { config { pins = "gpio126"; function = "gpio"; - bias-no-pull; + bias-disable; drive-strength = <2>; output-high; }; From 275a67e909f784e52a0d064eb841d77a79bd3632 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Mon, 18 Jul 2022 16:03:40 +0200 Subject: [PATCH 0089/4345] arm64: dts: qcom: msm8916: Drop MSS fallback compatible [ Upstream commit ff02ac621634e82c0c34d02a79d402ae700cdfd0 ] MSM8916 was originally using the "qcom,q6v5-pil" compatible for the MSS remoteproc. Later it was decided to use SoC-specific compatibles instead, so "qcom,msm8916-mss-pil" is now the preferred compatible. Commit 60a05ed059a0 ("arm64: dts: qcom: msm8916: Add MSM8916-specific compatibles to SCM/MSS") updated the MSM8916 device tree to make use of the new compatible but still kept the old "qcom,q6v5-pil" as fallback. This is inconsistent with other SoCs and conflicts with the description in the binding documentation (which says that only one compatible should be present). Also, it has no functional advantage since older kernels could not handle this DT anyway (e.g. "power-domains" in the MSS node is only supported by kernels that also support "qcom,msm8916-mss-pil"). Make this consistent with other SoCs by using only the "qcom,msm8916-mss-pil" compatible. Fixes: 60a05ed059a0 ("arm64: dts: qcom: msm8916: Add MSM8916-specific compatibles to SCM/MSS") Signed-off-by: Stephan Gerhold Reviewed-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220718140344.1831731-2-stephan.gerhold@kernkonzept.com Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8916.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index 291276a38d7c..c32e4a3833f2 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -1249,7 +1249,7 @@ }; mpss: remoteproc@4080000 { - compatible = "qcom,msm8916-mss-pil", "qcom,q6v5-pil"; + compatible = "qcom,msm8916-mss-pil"; reg = <0x04080000 0x100>, <0x04020000 0x040>; From 933499bed78dc9daa9be8ede7c7c9be1951a2d87 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 12 Sep 2022 11:45:41 +0200 Subject: [PATCH 0090/4345] objtool, kcsan: Add volatile read/write instrumentation to whitelist [ Upstream commit 63646fcba5bb4b59a19031c21913f94e46a3d0d4 ] Adds KCSAN's volatile instrumentation to objtool's uaccess whitelist. Recent kernel change have shown that this was missing from the uaccess whitelist (since the first upstreamed version of KCSAN): mm/gup.o: warning: objtool: fault_in_readable+0x101: call to __tsan_volatile_write1() with UACCESS enabled Fixes: 75d75b7a4d54 ("kcsan: Support distinguishing volatile accesses") Signed-off-by: Marco Elver Reviewed-by: Dmitry Vyukov Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- tools/objtool/check.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index ea80b29b9913..5d64b673da2d 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -802,6 +802,16 @@ static const char *uaccess_safe_builtin[] = { "__tsan_read_write4", "__tsan_read_write8", "__tsan_read_write16", + "__tsan_volatile_read1", + "__tsan_volatile_read2", + "__tsan_volatile_read4", + "__tsan_volatile_read8", + "__tsan_volatile_read16", + "__tsan_volatile_write1", + "__tsan_volatile_write2", + "__tsan_volatile_write4", + "__tsan_volatile_write8", + "__tsan_volatile_write16", "__tsan_atomic8_load", "__tsan_atomic16_load", "__tsan_atomic32_load", From 6d1b6dc38fe01dcce6cf60ea31dcac5170718f64 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 23 Sep 2022 04:37:45 +0200 Subject: [PATCH 0091/4345] ARM: dts: stm32: Drop stm32mp15xc.dtsi from Avenger96 [ Upstream commit 3b835f1b8acef53c8882b25f40f48d7f5982c938 ] The Avenger96 is populated with STM32MP157A DHCOR SoM, drop the stm32mp15xc.dtsi which should only be included in DTs of devices which are populated with STM32MP15xC/F SoC as the stm32mp15xc.dtsi enables CRYP block not present in the STM32MP15xA/D SoC . Fixes: 7e76f82acd9e1 ("ARM: dts: stm32: Split Avenger96 into DHCOR SoM and Avenger96 board") Signed-off-by: Marek Vasut Reviewed-by: Patrice Chotard Reviewed-by: Manivannan Sadhasivam Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp157a-dhcor-avenger96.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/stm32mp157a-dhcor-avenger96.dts b/arch/arm/boot/dts/stm32mp157a-dhcor-avenger96.dts index 2e3c9fbb4eb3..275167f26fd9 100644 --- a/arch/arm/boot/dts/stm32mp157a-dhcor-avenger96.dts +++ b/arch/arm/boot/dts/stm32mp157a-dhcor-avenger96.dts @@ -13,7 +13,6 @@ /dts-v1/; #include "stm32mp157.dtsi" -#include "stm32mp15xc.dtsi" #include "stm32mp15xx-dhcor-som.dtsi" #include "stm32mp15xx-dhcor-avenger96.dtsi" From 6a2faf6fcefd7e6e91e429911c568e4e2ab52916 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 21 Oct 2022 12:00:57 +0200 Subject: [PATCH 0092/4345] ARM: dts: stm32: Fix AV96 WLAN regulator gpio property [ Upstream commit d5d577e3d50713ad11d98dbdaa48bb494346c26d ] The WLAN regulator uses 'gpios' property instead of 'gpio' to specify regulator enable GPIO. While the former is also currently handled by the Linux kernel regulator-fixed driver, the later is the correct one per DT bindings. Update the DT to use the later. Fixes: 7dd5cbba42c93 ("ARM: dts: stm32: Enable WiFi on AV96") Signed-off-by: Marek Vasut Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi index f3e0c790a4b1..723b39bb2129 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi @@ -100,7 +100,7 @@ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - gpios = <&gpioz 3 GPIO_ACTIVE_HIGH>; + gpio = <&gpioz 3 GPIO_ACTIVE_HIGH>; enable-active-high; }; }; From 8fb204a4b5ac84dc98753b06df44aa2a05a4f3aa Mon Sep 17 00:00:00 2001 From: Chen Jiahao Date: Wed, 19 Oct 2022 23:32:12 +0800 Subject: [PATCH 0093/4345] drivers: soc: ti: knav_qmss_queue: Mark knav_acc_firmwares as static [ Upstream commit adf85adc2a7199b41e7a4da083bd17274a3d6969 ] There is a sparse warning shown below: drivers/soc/ti/knav_qmss_queue.c:70:12: warning: symbol 'knav_acc_firmwares' was not declared. Should it be static? Since 'knav_acc_firmwares' is only called within knav_qmss_queue.c, mark it as static to fix the warning. Fixes: 96ee19becc3b ("soc: ti: add firmware file name as part of the driver") Signed-off-by: Chen Jiahao Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20221019153212.72350-1-chenjiahao16@huawei.com Signed-off-by: Sasha Levin --- drivers/soc/ti/knav_qmss_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c index 53e36d4328d1..baab7d558a69 100644 --- a/drivers/soc/ti/knav_qmss_queue.c +++ b/drivers/soc/ti/knav_qmss_queue.c @@ -67,7 +67,7 @@ static DEFINE_MUTEX(knav_dev_lock); * Newest followed by older ones. Search is done from start of the array * until a firmware file is found. */ -const char *knav_acc_firmwares[] = {"ks2_qmss_pdsp_acc48.bin"}; +static const char * const knav_acc_firmwares[] = {"ks2_qmss_pdsp_acc48.bin"}; static bool device_ready; bool knav_qmss_device_ready(void) From 45d180a9f64b9aead769cfc5c2d70e85c7a64f47 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Fri, 4 Nov 2022 16:30:41 +0100 Subject: [PATCH 0094/4345] soc: qcom: llcc: make irq truly optional [ Upstream commit c882c899ead3545102a4d71b5fbe73b9e4bc2657 ] The function platform_get_irq prints an error message into the kernel log when the irq isn't found. Since the interrupt is actually optional and not provided by some SoCs, use platform_get_irq_optional which does not print an error message. Fixes: c081f3060fab ("soc: qcom: Add support to register LLCC EDAC driver") Signed-off-by: Luca Weiss Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221104153041.412020-1-luca.weiss@fairphone.com Signed-off-by: Sasha Levin --- drivers/soc/qcom/llcc-qcom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 2e06f48d683d..c60fe98f03e3 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -476,7 +476,7 @@ static int qcom_llcc_probe(struct platform_device *pdev) if (ret) goto err; - drv_data->ecc_irq = platform_get_irq(pdev, 0); + drv_data->ecc_irq = platform_get_irq_optional(pdev, 0); if (drv_data->ecc_irq >= 0) { llcc_edac = platform_device_register_data(&pdev->dev, "qcom_llcc_edac", -1, drv_data, From 6213df4f5fc2e1bb1e7c832179b4258b8543fcc7 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Mon, 27 Sep 2021 14:55:40 +0100 Subject: [PATCH 0095/4345] soc: qcom: apr: make code more reuseable [ Upstream commit 99139b80c1b3d73026ed8be2de42c52e2976ab64 ] APR and other packet routers like GPR are pretty much same and interact with other drivers in similar way. Ex: GPR ports can be considered as APR services, only difference is they are allocated dynamically. Other difference is packet layout, which should not matter with the apis abstracted. Apart from this the rest of the functionality is pretty much identical across APR and GPR. Make the apr code more reusable by abstracting it service level, rather than device level so that we do not need to write new drivers for other new packet routers like GPR. This patch is in preparation to add GPR support to this driver. Signed-off-by: Srinivas Kandagatla Reviewed-by: Pierre-Louis Bossart Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210927135559.738-4-srinivas.kandagatla@linaro.org Stable-dep-of: 6d7860f5750d ("soc: qcom: apr: Add check for idr_alloc and of_property_read_string_index") Signed-off-by: Sasha Levin --- drivers/soc/qcom/apr.c | 129 +++++++++++++++++++++-------------- include/linux/soc/qcom/apr.h | 12 +++- 2 files changed, 90 insertions(+), 51 deletions(-) diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index f736d208362c..8fed91822cae 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -15,13 +15,18 @@ #include #include -struct apr { +enum { + PR_TYPE_APR = 0, +}; + +struct packet_router { struct rpmsg_endpoint *ch; struct device *dev; spinlock_t svcs_lock; spinlock_t rx_lock; struct idr svcs_idr; int dest_domain_id; + int type; struct pdr_handle *pdr; struct workqueue_struct *rxwq; struct work_struct rx_work; @@ -44,21 +49,21 @@ struct apr_rx_buf { */ int apr_send_pkt(struct apr_device *adev, struct apr_pkt *pkt) { - struct apr *apr = dev_get_drvdata(adev->dev.parent); + struct packet_router *apr = dev_get_drvdata(adev->dev.parent); struct apr_hdr *hdr; unsigned long flags; int ret; - spin_lock_irqsave(&adev->lock, flags); + spin_lock_irqsave(&adev->svc.lock, flags); hdr = &pkt->hdr; hdr->src_domain = APR_DOMAIN_APPS; - hdr->src_svc = adev->svc_id; + hdr->src_svc = adev->svc.id; hdr->dest_domain = adev->domain_id; - hdr->dest_svc = adev->svc_id; + hdr->dest_svc = adev->svc.id; ret = rpmsg_trysend(apr->ch, pkt, hdr->pkt_size); - spin_unlock_irqrestore(&adev->lock, flags); + spin_unlock_irqrestore(&adev->svc.lock, flags); return ret ? ret : hdr->pkt_size; } @@ -74,7 +79,7 @@ static void apr_dev_release(struct device *dev) static int apr_callback(struct rpmsg_device *rpdev, void *buf, int len, void *priv, u32 addr) { - struct apr *apr = dev_get_drvdata(&rpdev->dev); + struct packet_router *apr = dev_get_drvdata(&rpdev->dev); struct apr_rx_buf *abuf; unsigned long flags; @@ -100,11 +105,11 @@ static int apr_callback(struct rpmsg_device *rpdev, void *buf, return 0; } - -static int apr_do_rx_callback(struct apr *apr, struct apr_rx_buf *abuf) +static int apr_do_rx_callback(struct packet_router *apr, struct apr_rx_buf *abuf) { uint16_t hdr_size, msg_type, ver, svc_id; - struct apr_device *svc = NULL; + struct pkt_router_svc *svc; + struct apr_device *adev; struct apr_driver *adrv = NULL; struct apr_resp_pkt resp; struct apr_hdr *hdr; @@ -145,12 +150,15 @@ static int apr_do_rx_callback(struct apr *apr, struct apr_rx_buf *abuf) svc_id = hdr->dest_svc; spin_lock_irqsave(&apr->svcs_lock, flags); svc = idr_find(&apr->svcs_idr, svc_id); - if (svc && svc->dev.driver) - adrv = to_apr_driver(svc->dev.driver); + if (svc && svc->dev->driver) { + adev = svc_to_apr_device(svc); + adrv = to_apr_driver(adev->dev.driver); + } spin_unlock_irqrestore(&apr->svcs_lock, flags); - if (!adrv) { - dev_err(apr->dev, "APR: service is not registered\n"); + if (!adrv || !adev) { + dev_err(apr->dev, "APR: service is not registered (%d)\n", + svc_id); return -EINVAL; } @@ -164,20 +172,26 @@ static int apr_do_rx_callback(struct apr *apr, struct apr_rx_buf *abuf) if (resp.payload_size > 0) resp.payload = buf + hdr_size; - adrv->callback(svc, &resp); + adrv->callback(adev, &resp); return 0; } static void apr_rxwq(struct work_struct *work) { - struct apr *apr = container_of(work, struct apr, rx_work); + struct packet_router *apr = container_of(work, struct packet_router, rx_work); struct apr_rx_buf *abuf, *b; unsigned long flags; if (!list_empty(&apr->rx_list)) { list_for_each_entry_safe(abuf, b, &apr->rx_list, node) { - apr_do_rx_callback(apr, abuf); + switch (apr->type) { + case PR_TYPE_APR: + apr_do_rx_callback(apr, abuf); + break; + default: + break; + } spin_lock_irqsave(&apr->rx_lock, flags); list_del(&abuf->node); spin_unlock_irqrestore(&apr->rx_lock, flags); @@ -201,7 +215,7 @@ static int apr_device_match(struct device *dev, struct device_driver *drv) while (id->domain_id != 0 || id->svc_id != 0) { if (id->domain_id == adev->domain_id && - id->svc_id == adev->svc_id) + id->svc_id == adev->svc.id) return 1; id++; } @@ -221,14 +235,14 @@ static int apr_device_remove(struct device *dev) { struct apr_device *adev = to_apr_device(dev); struct apr_driver *adrv; - struct apr *apr = dev_get_drvdata(adev->dev.parent); + struct packet_router *apr = dev_get_drvdata(adev->dev.parent); if (dev->driver) { adrv = to_apr_driver(dev->driver); if (adrv->remove) adrv->remove(adev); spin_lock(&apr->svcs_lock); - idr_remove(&apr->svcs_idr, adev->svc_id); + idr_remove(&apr->svcs_idr, adev->svc.id); spin_unlock(&apr->svcs_lock); } @@ -257,28 +271,39 @@ struct bus_type aprbus = { EXPORT_SYMBOL_GPL(aprbus); static int apr_add_device(struct device *dev, struct device_node *np, - const struct apr_device_id *id) + u32 svc_id, u32 domain_id) { - struct apr *apr = dev_get_drvdata(dev); + struct packet_router *apr = dev_get_drvdata(dev); struct apr_device *adev = NULL; + struct pkt_router_svc *svc; int ret; adev = kzalloc(sizeof(*adev), GFP_KERNEL); if (!adev) return -ENOMEM; - spin_lock_init(&adev->lock); + adev->svc_id = svc_id; + svc = &adev->svc; + + svc->id = svc_id; + svc->pr = apr; + svc->priv = adev; + svc->dev = dev; + spin_lock_init(&svc->lock); + + adev->domain_id = domain_id; - adev->svc_id = id->svc_id; - adev->domain_id = id->domain_id; - adev->version = id->svc_version; if (np) snprintf(adev->name, APR_NAME_SIZE, "%pOFn", np); - else - strscpy(adev->name, id->name, APR_NAME_SIZE); - dev_set_name(&adev->dev, "aprsvc:%s:%x:%x", adev->name, - id->domain_id, id->svc_id); + switch (apr->type) { + case PR_TYPE_APR: + dev_set_name(&adev->dev, "aprsvc:%s:%x:%x", adev->name, + domain_id, svc_id); + break; + default: + break; + } adev->dev.bus = &aprbus; adev->dev.parent = dev; @@ -287,8 +312,7 @@ static int apr_add_device(struct device *dev, struct device_node *np, adev->dev.driver = NULL; spin_lock(&apr->svcs_lock); - idr_alloc(&apr->svcs_idr, adev, id->svc_id, - id->svc_id + 1, GFP_ATOMIC); + idr_alloc(&apr->svcs_idr, svc, svc_id, svc_id + 1, GFP_ATOMIC); spin_unlock(&apr->svcs_lock); of_property_read_string_index(np, "qcom,protection-domain", @@ -308,7 +332,7 @@ static int apr_add_device(struct device *dev, struct device_node *np, static int of_apr_add_pd_lookups(struct device *dev) { const char *service_name, *service_path; - struct apr *apr = dev_get_drvdata(dev); + struct packet_router *apr = dev_get_drvdata(dev); struct device_node *node; struct pdr_service *pds; int ret; @@ -340,13 +364,14 @@ static int of_apr_add_pd_lookups(struct device *dev) static void of_register_apr_devices(struct device *dev, const char *svc_path) { - struct apr *apr = dev_get_drvdata(dev); + struct packet_router *apr = dev_get_drvdata(dev); struct device_node *node; const char *service_path; int ret; for_each_child_of_node(dev->of_node, node) { - struct apr_device_id id = { {0} }; + u32 svc_id; + u32 domain_id; /* * This function is called with svc_path NULL during @@ -376,13 +401,13 @@ static void of_register_apr_devices(struct device *dev, const char *svc_path) continue; } - if (of_property_read_u32(node, "reg", &id.svc_id)) + if (of_property_read_u32(node, "reg", &svc_id)) continue; - id.domain_id = apr->dest_domain_id; + domain_id = apr->dest_domain_id; - if (apr_add_device(dev, node, &id)) - dev_err(dev, "Failed to add apr %d svc\n", id.svc_id); + if (apr_add_device(dev, node, svc_id, domain_id)) + dev_err(dev, "Failed to add apr %d svc\n", svc_id); } } @@ -402,7 +427,7 @@ static int apr_remove_device(struct device *dev, void *svc_path) static void apr_pd_status(int state, char *svc_path, void *priv) { - struct apr *apr = (struct apr *)priv; + struct packet_router *apr = (struct packet_router *)priv; switch (state) { case SERVREG_SERVICE_STATE_UP: @@ -417,16 +442,20 @@ static void apr_pd_status(int state, char *svc_path, void *priv) static int apr_probe(struct rpmsg_device *rpdev) { struct device *dev = &rpdev->dev; - struct apr *apr; + struct packet_router *apr; int ret; apr = devm_kzalloc(dev, sizeof(*apr), GFP_KERNEL); if (!apr) return -ENOMEM; - ret = of_property_read_u32(dev->of_node, "qcom,apr-domain", &apr->dest_domain_id); + ret = of_property_read_u32(dev->of_node, "qcom,domain", &apr->dest_domain_id); + if (ret) /* try deprecated apr-domain property */ + ret = of_property_read_u32(dev->of_node, "qcom,apr-domain", + &apr->dest_domain_id); + apr->type = PR_TYPE_APR; if (ret) { - dev_err(dev, "APR Domain ID not specified in DT\n"); + dev_err(dev, "Domain ID not specified in DT\n"); return ret; } @@ -469,7 +498,7 @@ destroy_wq: static void apr_remove(struct rpmsg_device *rpdev) { - struct apr *apr = dev_get_drvdata(&rpdev->dev); + struct packet_router *apr = dev_get_drvdata(&rpdev->dev); pdr_handle_release(apr->pdr); device_for_each_child(&rpdev->dev, NULL, apr_remove_device); @@ -506,20 +535,20 @@ void apr_driver_unregister(struct apr_driver *drv) } EXPORT_SYMBOL_GPL(apr_driver_unregister); -static const struct of_device_id apr_of_match[] = { +static const struct of_device_id pkt_router_of_match[] = { { .compatible = "qcom,apr"}, { .compatible = "qcom,apr-v2"}, {} }; -MODULE_DEVICE_TABLE(of, apr_of_match); +MODULE_DEVICE_TABLE(of, pkt_router_of_match); -static struct rpmsg_driver apr_driver = { +static struct rpmsg_driver packet_router_driver = { .probe = apr_probe, .remove = apr_remove, .callback = apr_callback, .drv = { .name = "qcom,apr", - .of_match_table = apr_of_match, + .of_match_table = pkt_router_of_match, }, }; @@ -529,7 +558,7 @@ static int __init apr_init(void) ret = bus_register(&aprbus); if (!ret) - ret = register_rpmsg_driver(&apr_driver); + ret = register_rpmsg_driver(&packet_router_driver); else bus_unregister(&aprbus); @@ -539,7 +568,7 @@ static int __init apr_init(void) static void __exit apr_exit(void) { bus_unregister(&aprbus); - unregister_rpmsg_driver(&apr_driver); + unregister_rpmsg_driver(&packet_router_driver); } subsys_initcall(apr_init); diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h index 7f0bc3cf4d61..6374763186c8 100644 --- a/include/linux/soc/qcom/apr.h +++ b/include/linux/soc/qcom/apr.h @@ -79,6 +79,15 @@ struct apr_resp_pkt { #define APR_SVC_MAJOR_VERSION(v) ((v >> 16) & 0xFF) #define APR_SVC_MINOR_VERSION(v) (v & 0xFF) +struct packet_router; +struct pkt_router_svc { + struct device *dev; + struct packet_router *pr; + spinlock_t lock; + int id; + void *priv; +}; + struct apr_device { struct device dev; uint16_t svc_id; @@ -86,11 +95,12 @@ struct apr_device { uint32_t version; char name[APR_NAME_SIZE]; const char *service_path; - spinlock_t lock; + struct pkt_router_svc svc; struct list_head node; }; #define to_apr_device(d) container_of(d, struct apr_device, dev) +#define svc_to_apr_device(d) container_of(d, struct apr_device, svc) struct apr_driver { int (*probe)(struct apr_device *sl); From a8d4fb0bf10b38e973d6910909594b6a5bf99bf5 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Mon, 7 Nov 2022 09:44:03 +0800 Subject: [PATCH 0096/4345] soc: qcom: apr: Add check for idr_alloc and of_property_read_string_index [ Upstream commit 6d7860f5750d73da2fa1a1f6c9405058a593fa32 ] As idr_alloc() and of_property_read_string_index() can return negative numbers, it should be better to check the return value and deal with the exception. Therefore, it should be better to use goto statement to stop and return error. Fixes: 6adba21eb434 ("soc: qcom: Add APR bus driver") Signed-off-by: Jiasheng Jiang Reviewed-by: Bjorn Andersson Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221107014403.3606-1-jiasheng@iscas.ac.cn Signed-off-by: Sasha Levin --- drivers/soc/qcom/apr.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index 8fed91822cae..7063e0d42c5e 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -312,11 +312,19 @@ static int apr_add_device(struct device *dev, struct device_node *np, adev->dev.driver = NULL; spin_lock(&apr->svcs_lock); - idr_alloc(&apr->svcs_idr, svc, svc_id, svc_id + 1, GFP_ATOMIC); + ret = idr_alloc(&apr->svcs_idr, svc, svc_id, svc_id + 1, GFP_ATOMIC); spin_unlock(&apr->svcs_lock); + if (ret < 0) { + dev_err(dev, "idr_alloc failed: %d\n", ret); + goto out; + } - of_property_read_string_index(np, "qcom,protection-domain", - 1, &adev->service_path); + ret = of_property_read_string_index(np, "qcom,protection-domain", + 1, &adev->service_path); + if (ret < 0) { + dev_err(dev, "Failed to read second value of qcom,protection-domain\n"); + goto out; + } dev_info(dev, "Adding APR dev: %s\n", dev_name(&adev->dev)); @@ -326,6 +334,7 @@ static int apr_add_device(struct device *dev, struct device_node *np, put_device(&adev->dev); } +out: return ret; } From 0542d56e6333795a5592b2c0dbbec95728e67352 Mon Sep 17 00:00:00 2001 From: Kory Maincent Date: Wed, 2 Nov 2022 18:10:06 +0100 Subject: [PATCH 0097/4345] arm: dts: spear600: Fix clcd interrupt [ Upstream commit 0336e2ce34e7a89832b6c214f924eb7bc58940be ] Interrupt 12 of the Interrupt controller belongs to the SMI controller, the right one for the display controller is the interrupt 13. Fixes: 8113ba917dfa ("ARM: SPEAr: DT: Update device nodes") Signed-off-by: Kory Maincent Acked-by: Viresh Kumar Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- arch/arm/boot/dts/spear600.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/spear600.dtsi b/arch/arm/boot/dts/spear600.dtsi index fd41243a0b2c..9d5a04a46b14 100644 --- a/arch/arm/boot/dts/spear600.dtsi +++ b/arch/arm/boot/dts/spear600.dtsi @@ -47,7 +47,7 @@ compatible = "arm,pl110", "arm,primecell"; reg = <0xfc200000 0x1000>; interrupt-parent = <&vic1>; - interrupts = <12>; + interrupts = <13>; status = "disabled"; }; From e325b4ee414b0d84815873e3015bb486d8ffc573 Mon Sep 17 00:00:00 2001 From: Minghao Chi Date: Mon, 18 Apr 2022 06:29:55 +0000 Subject: [PATCH 0098/4345] soc: ti: knav_qmss_queue: Use pm_runtime_resume_and_get instead of pm_runtime_get_sync [ Upstream commit 12eeb74925da70eb39d90abead9de9793be3d4c8 ] Using pm_runtime_resume_and_get is more appropriate for simplifying code. Reported-by: Zeal Robot Signed-off-by: Minghao Chi Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220418062955.2557949-1-chi.minghao@zte.com.cn Stable-dep-of: e961c0f19450 ("soc: ti: knav_qmss_queue: Fix PM disable depth imbalance in knav_queue_probe") Signed-off-by: Sasha Levin --- drivers/soc/ti/knav_qmss_queue.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c index baab7d558a69..38e2630eec36 100644 --- a/drivers/soc/ti/knav_qmss_queue.c +++ b/drivers/soc/ti/knav_qmss_queue.c @@ -1782,9 +1782,8 @@ static int knav_queue_probe(struct platform_device *pdev) INIT_LIST_HEAD(&kdev->pdsps); pm_runtime_enable(&pdev->dev); - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { - pm_runtime_put_noidle(&pdev->dev); dev_err(dev, "Failed to enable QMSS\n"); return ret; } From 6a9a31c578879420fe187cd6797a275f7de5bd08 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Tue, 8 Nov 2022 16:03:21 +0800 Subject: [PATCH 0099/4345] soc: ti: knav_qmss_queue: Fix PM disable depth imbalance in knav_queue_probe [ Upstream commit e961c0f19450fd4a26bd043dd2979990bf12caf6 ] The pm_runtime_enable will increase power disable depth. Thus a pairing decrement is needed on the error handling path to keep it balanced according to context. Fixes: 41f93af900a2 ("soc: ti: add Keystone Navigator QMSS driver") Signed-off-by: Zhang Qilong Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20221108080322.52268-2-zhangqilong3@huawei.com Signed-off-by: Sasha Levin --- drivers/soc/ti/knav_qmss_queue.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c index 38e2630eec36..20c84741639e 100644 --- a/drivers/soc/ti/knav_qmss_queue.c +++ b/drivers/soc/ti/knav_qmss_queue.c @@ -1784,6 +1784,7 @@ static int knav_queue_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { + pm_runtime_disable(&pdev->dev); dev_err(dev, "Failed to enable QMSS\n"); return ret; } From 5e88aec62e7f5497676fb560074b1067c28c5698 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Tue, 8 Nov 2022 16:03:22 +0800 Subject: [PATCH 0100/4345] soc: ti: smartreflex: Fix PM disable depth imbalance in omap_sr_probe [ Upstream commit 69460e68eb662064ab4188d4e129ff31c1f23ed9 ] The pm_runtime_enable will increase power disable depth. Thus a pairing decrement is needed on the error handling path to keep it balanced according to context. Fixes: 984aa6dbf4ca ("OMAP3: PM: Adding smartreflex driver support.") Signed-off-by: Zhang Qilong Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20221108080322.52268-3-zhangqilong3@huawei.com Signed-off-by: Sasha Levin --- drivers/soc/ti/smartreflex.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/soc/ti/smartreflex.c b/drivers/soc/ti/smartreflex.c index 5376f3d22f31..1228a0cba132 100644 --- a/drivers/soc/ti/smartreflex.c +++ b/drivers/soc/ti/smartreflex.c @@ -942,6 +942,7 @@ static int omap_sr_probe(struct platform_device *pdev) err_debugfs: debugfs_remove_recursive(sr_info->dbg_dir); err_list_del: + pm_runtime_disable(&pdev->dev); list_del(&sr_info->node); pm_runtime_put_sync(&pdev->dev); From 9afac95b87fa1816ac3362168a7d77a280380594 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Tue, 15 Nov 2022 07:02:06 +0000 Subject: [PATCH 0101/4345] perf: arm_dsu: Fix hotplug callback leak in dsu_pmu_init() [ Upstream commit facafab7611f7b872c6b9eeaff53461ef11f482e ] dsu_pmu_init() won't remove the callback added by cpuhp_setup_state_multi() when platform_driver_register() failed. Remove the callback by cpuhp_remove_multi_state() in fail path. Similar to the handling of arm_ccn_init() in commit 26242b330093 ("bus: arm-ccn: Prevent hotplug callback leak") Fixes: 7520fa99246d ("perf: ARM DynamIQ Shared Unit PMU support") Signed-off-by: Yuan Can Acked-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20221115070207.32634-2-yuancan@huawei.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/perf/arm_dsu_pmu.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c index 98e68ed7db85..1db8eccc9735 100644 --- a/drivers/perf/arm_dsu_pmu.c +++ b/drivers/perf/arm_dsu_pmu.c @@ -866,7 +866,11 @@ static int __init dsu_pmu_init(void) if (ret < 0) return ret; dsu_pmu_cpuhp_state = ret; - return platform_driver_register(&dsu_pmu_driver); + ret = platform_driver_register(&dsu_pmu_driver); + if (ret) + cpuhp_remove_multi_state(dsu_pmu_cpuhp_state); + + return ret; } static void __exit dsu_pmu_exit(void) From 359286f886feef38536eaa7e673dc3440f03b0a1 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Tue, 15 Nov 2022 19:55:40 +0800 Subject: [PATCH 0102/4345] perf/smmuv3: Fix hotplug callback leak in arm_smmu_pmu_init() [ Upstream commit 6f2d566b46436a50a80d6445e82879686b89588c ] arm_smmu_pmu_init() won't remove the callback added by cpuhp_setup_state_multi() when platform_driver_register() failed. Remove the callback by cpuhp_remove_multi_state() in fail path. Similar to the handling of arm_ccn_init() in commit 26242b330093 ("bus: arm-ccn: Prevent hotplug callback leak") Fixes: 7d839b4b9e00 ("perf/smmuv3: Add arm64 smmuv3 pmu driver") Signed-off-by: Shang XiaoJing Reviewed-by: Punit Agrawal Link: https://lore.kernel.org/r/20221115115540.6245-3-shangxiaojing@huawei.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/perf/arm_smmuv3_pmu.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index afa8efbdad8f..f5a33dbe7acb 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -870,6 +870,8 @@ static struct platform_driver smmu_pmu_driver = { static int __init arm_smmu_pmu_init(void) { + int ret; + cpuhp_state_num = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "perf/arm/pmcg:online", NULL, @@ -877,7 +879,11 @@ static int __init arm_smmu_pmu_init(void) if (cpuhp_state_num < 0) return cpuhp_state_num; - return platform_driver_register(&smmu_pmu_driver); + ret = platform_driver_register(&smmu_pmu_driver); + if (ret) + cpuhp_remove_multi_state(cpuhp_state_num); + + return ret; } module_init(arm_smmu_pmu_init); From 42d97a024ef6384b99c79871afa33a52fe637284 Mon Sep 17 00:00:00 2001 From: Jayesh Choudhary Date: Mon, 31 Oct 2022 20:55:18 +0530 Subject: [PATCH 0103/4345] arm64: dts: ti: k3-am65-main: Drop dma-coherent in crypto node [ Upstream commit b86833ab3653dbb0dc453eec4eef8615e63de4e2 ] crypto driver itself is not dma-coherent. So drop it. Fixes: b366b2409c97 ("arm64: dts: ti: k3-am6: Add crypto accelarator node") Signed-off-by: Jayesh Choudhary Signed-off-by: Nishanth Menon Reviewed-by: Manorit Chawdhry Link: https://lore.kernel.org/r/20221031152520.355653-2-j-choudhary@ti.com Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/ti/k3-am65-main.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi index d04189771c77..4265f627ca16 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi @@ -127,7 +127,6 @@ dmas = <&main_udmap 0xc000>, <&main_udmap 0x4000>, <&main_udmap 0x4001>; dma-names = "tx", "rx1", "rx2"; - dma-coherent; rng: rng@4e10000 { compatible = "inside-secure,safexcel-eip76"; From a455b0c509c938af2c5d63e28b6ca440803d1fe6 Mon Sep 17 00:00:00 2001 From: Jayesh Choudhary Date: Mon, 31 Oct 2022 20:55:19 +0530 Subject: [PATCH 0104/4345] arm64: dts: ti: k3-j721e-main: Drop dma-coherent in crypto node [ Upstream commit 26c5012403f3f1fd3bf8f7d3389ee539ae5cc162 ] crypto driver itself is not dma-coherent. So drop it. Fixes: 8ebcaaae8017 ("arm64: dts: ti: k3-j721e-main: Add crypto accelerator node") Signed-off-by: Jayesh Choudhary Signed-off-by: Nishanth Menon Reviewed-by: Manorit Chawdhry Link: https://lore.kernel.org/r/20221031152520.355653-3-j-choudhary@ti.com Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/ti/k3-j721e-main.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi index 0350ddfe2c72..691d73f0f1e0 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi @@ -367,7 +367,6 @@ dmas = <&main_udmap 0xc000>, <&main_udmap 0x4000>, <&main_udmap 0x4001>; dma-names = "tx", "rx1", "rx2"; - dma-coherent; rng: rng@4e10000 { compatible = "inside-secure,safexcel-eip76"; From a938c2a77492da4b81c8901d09f46da5bab0e96f Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 13 Oct 2022 17:22:07 +0200 Subject: [PATCH 0105/4345] arm64: dts: mt2712e: Fix unit_address_vs_reg warning for oscillators [ Upstream commit e4495a0a8b3d84816c9a46edf3ce060bbf267475 ] Rename the fixed-clock oscillators to remove the unit address. This solves unit_address_vs_reg warnings. Fixes: 5d4839709c8e ("arm64: dts: mt2712: Add clock controller device nodes") Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221013152212.416661-4-angelogioacchino.delregno@collabora.com Signed-off-by: Matthias Brugger Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt2712e.dtsi | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi index db17d0a4ed57..e0b26cd67eb3 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi @@ -160,70 +160,70 @@ #clock-cells = <0>; }; - clk26m: oscillator@0 { + clk26m: oscillator-26m { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <26000000>; clock-output-names = "clk26m"; }; - clk32k: oscillator@1 { + clk32k: oscillator-32k { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <32768>; clock-output-names = "clk32k"; }; - clkfpc: oscillator@2 { + clkfpc: oscillator-50m { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <50000000>; clock-output-names = "clkfpc"; }; - clkaud_ext_i_0: oscillator@3 { + clkaud_ext_i_0: oscillator-aud0 { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <6500000>; clock-output-names = "clkaud_ext_i_0"; }; - clkaud_ext_i_1: oscillator@4 { + clkaud_ext_i_1: oscillator-aud1 { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <196608000>; clock-output-names = "clkaud_ext_i_1"; }; - clkaud_ext_i_2: oscillator@5 { + clkaud_ext_i_2: oscillator-aud2 { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <180633600>; clock-output-names = "clkaud_ext_i_2"; }; - clki2si0_mck_i: oscillator@6 { + clki2si0_mck_i: oscillator-i2s0 { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <30000000>; clock-output-names = "clki2si0_mck_i"; }; - clki2si1_mck_i: oscillator@7 { + clki2si1_mck_i: oscillator-i2s1 { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <30000000>; clock-output-names = "clki2si1_mck_i"; }; - clki2si2_mck_i: oscillator@8 { + clki2si2_mck_i: oscillator-i2s2 { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <30000000>; clock-output-names = "clki2si2_mck_i"; }; - clktdmin_mclk_i: oscillator@9 { + clktdmin_mclk_i: oscillator-mclk { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <30000000>; From 148e77355797421dc2640dd088d8e18bf507da8d Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 13 Oct 2022 17:22:08 +0200 Subject: [PATCH 0106/4345] arm64: dts: mt2712e: Fix unit address for pinctrl node [ Upstream commit 1d4516f53a611b362db7ba7a8889923d469f57e1 ] The unit address for the pinctrl node is (0x)1000b000 and not (0x)10005000, which is the syscfg_pctl_a address instead. This fixes the following warning: arch/arm64/boot/dts/mediatek/mt2712e.dtsi:264.40-267.4: Warning (unique_unit_address): /syscfg_pctl_a@10005000: duplicate unit-address (also used in node /pinctrl@10005000) Fixes: f0c64340b748 ("arm64: dts: mt2712: add pintcrl device node.") Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221013152212.416661-5-angelogioacchino.delregno@collabora.com Signed-off-by: Matthias Brugger Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt2712e.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi index e0b26cd67eb3..cc3d1c99517d 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi @@ -266,7 +266,7 @@ reg = <0 0x10005000 0 0x1000>; }; - pio: pinctrl@10005000 { + pio: pinctrl@1000b000 { compatible = "mediatek,mt2712-pinctrl"; reg = <0 0x1000b000 0 0x1000>; mediatek,pctl-regmap = <&syscfg_pctl_a>; From 436ac713a4a3309fdcda2046360fb4cf70dc4402 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 13 Oct 2022 17:22:09 +0200 Subject: [PATCH 0107/4345] arm64: dts: mt2712-evb: Fix vproc fixed regulators unit names [ Upstream commit 377063156893bf6c088309ac799fe5c6dce2822d ] Update the names to regulator-vproc-buck{0,1} to fix unit_addres_vs_reg warnings for those. Fixes: f75dd8bdd344 ("arm64: dts: mediatek: add mt2712 cpufreq related device nodes") Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221013152212.416661-6-angelogioacchino.delregno@collabora.com Signed-off-by: Matthias Brugger Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt2712-evb.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts index 7d369fdd3117..b78d441616b1 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts @@ -26,14 +26,14 @@ stdout-path = "serial0:921600n8"; }; - cpus_fixed_vproc0: fixedregulator@0 { + cpus_fixed_vproc0: regulator-vproc-buck0 { compatible = "regulator-fixed"; regulator-name = "vproc_buck0"; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <1000000>; }; - cpus_fixed_vproc1: fixedregulator@1 { + cpus_fixed_vproc1: regulator-vproc-buck1 { compatible = "regulator-fixed"; regulator-name = "vproc_buck1"; regulator-min-microvolt = <1000000>; From 853d57e9612e1c9cb6a37e28bac39c65a6ef42a1 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 13 Oct 2022 17:22:10 +0200 Subject: [PATCH 0108/4345] arm64: dts: mt2712-evb: Fix usb vbus regulators unit names [ Upstream commit ec1ae39a8d25cfb067b5459fac7c5b7b9bce6f6a ] Update the names to regulator-usb-p{0-3}-vbus to fix unit_address_vs_reg warnings for those. Fixes: 1724f4cc5133 ("arm64: dts: Add USB3 related nodes for MT2712") Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221013152212.416661-7-angelogioacchino.delregno@collabora.com Signed-off-by: Matthias Brugger Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt2712-evb.dts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts index b78d441616b1..9d20cabf4f69 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts @@ -50,7 +50,7 @@ id-gpio = <&pio 14 GPIO_ACTIVE_HIGH>; }; - usb_p0_vbus: regulator@2 { + usb_p0_vbus: regulator-usb-p0-vbus { compatible = "regulator-fixed"; regulator-name = "p0_vbus"; regulator-min-microvolt = <5000000>; @@ -59,7 +59,7 @@ enable-active-high; }; - usb_p1_vbus: regulator@3 { + usb_p1_vbus: regulator-usb-p1-vbus { compatible = "regulator-fixed"; regulator-name = "p1_vbus"; regulator-min-microvolt = <5000000>; @@ -68,7 +68,7 @@ enable-active-high; }; - usb_p2_vbus: regulator@4 { + usb_p2_vbus: regulator-usb-p2-vbus { compatible = "regulator-fixed"; regulator-name = "p2_vbus"; regulator-min-microvolt = <5000000>; @@ -77,7 +77,7 @@ enable-active-high; }; - usb_p3_vbus: regulator@5 { + usb_p3_vbus: regulator-usb-p3-vbus { compatible = "regulator-fixed"; regulator-name = "p3_vbus"; regulator-min-microvolt = <5000000>; From 1261352836118f9f05573cfa1f36c9ca69759031 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 13 Oct 2022 17:22:11 +0200 Subject: [PATCH 0109/4345] arm64: dts: mediatek: pumpkin-common: Fix devicetree warnings [ Upstream commit 509438336ce75c8b4e6ce8e8d507dc77d0783bdd ] Fix the pinctrl submodes and optee node to remove unneeded unit address, fixing all unit_address_vs_reg warnings. Fixes: 9983822c8cf9 ("arm64: dts: mediatek: add pumpkin board dts") Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221013152212.416661-8-angelogioacchino.delregno@collabora.com Signed-off-by: Matthias Brugger Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/pumpkin-common.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/pumpkin-common.dtsi b/arch/arm64/boot/dts/mediatek/pumpkin-common.dtsi index 99c2d6fd6304..d5059735c594 100644 --- a/arch/arm64/boot/dts/mediatek/pumpkin-common.dtsi +++ b/arch/arm64/boot/dts/mediatek/pumpkin-common.dtsi @@ -17,7 +17,7 @@ }; firmware { - optee: optee@4fd00000 { + optee: optee { compatible = "linaro,optee-tz"; method = "smc"; }; @@ -209,7 +209,7 @@ }; }; - i2c0_pins_a: i2c0@0 { + i2c0_pins_a: i2c0 { pins1 { pinmux = , ; @@ -217,7 +217,7 @@ }; }; - i2c2_pins_a: i2c2@0 { + i2c2_pins_a: i2c2 { pins1 { pinmux = , ; From c2cb1683d12192bc61e4b913548efa1690d50d54 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 13 Oct 2022 17:22:12 +0200 Subject: [PATCH 0110/4345] arm64: dts: mediatek: mt6797: Fix 26M oscillator unit name [ Upstream commit 5f535cc583759c9c60d4cc9b8d221762e2d75387 ] Update its unit name to oscillator-26m and remove the unneeded unit address to fix a unit_address_vs_reg warning. Fixes: 464c510f60c6 ("arm64: dts: mediatek: add mt6797 support") Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221013152212.416661-9-angelogioacchino.delregno@collabora.com Signed-off-by: Matthias Brugger Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt6797.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/mediatek/mt6797.dtsi b/arch/arm64/boot/dts/mediatek/mt6797.dtsi index 15616231022a..c3677d77e0a4 100644 --- a/arch/arm64/boot/dts/mediatek/mt6797.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt6797.dtsi @@ -95,7 +95,7 @@ }; }; - clk26m: oscillator@0 { + clk26m: oscillator-26m { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <26000000>; From 73ab831afdc813209b47c658968abd78826591ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 18 Aug 2022 00:30:48 +0200 Subject: [PATCH 0111/4345] ARM: dts: dove: Fix assigned-addresses for every PCIe Root Port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit dcc7d8c72b64a479b8017e4332d99179deb8802d ] BDF of resource in DT assigned-addresses property of Marvell PCIe Root Port (PCI-to-PCI bridge) should match BDF in address part in that DT node name as specified resource belongs to Marvell PCIe Root Port itself. Fixes: 74ecaa403a74 ("ARM: dove: add PCIe controllers to SoC DT") Signed-off-by: Pali Rohár Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm/boot/dts/dove.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi index 89e0bdaf3a85..726d353eda68 100644 --- a/arch/arm/boot/dts/dove.dtsi +++ b/arch/arm/boot/dts/dove.dtsi @@ -129,7 +129,7 @@ pcie1: pcie@2 { device_type = "pci"; status = "disabled"; - assigned-addresses = <0x82002800 0 0x80000 0 0x2000>; + assigned-addresses = <0x82001000 0 0x80000 0 0x2000>; reg = <0x1000 0 0 0 0>; clocks = <&gate_clk 5>; marvell,pcie-port = <1>; From 697b92a648f2c0e11fe881941198b7ea2f1e6c52 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 18 Aug 2022 00:30:49 +0200 Subject: [PATCH 0112/4345] ARM: dts: armada-370: Fix assigned-addresses for every PCIe Root Port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d9208b0fa2e803d16b28d91bf1d46b7ee9ea13c6 ] BDF of resource in DT assigned-addresses property of Marvell PCIe Root Port (PCI-to-PCI bridge) should match BDF in address part in that DT node name as specified resource belongs to Marvell PCIe Root Port itself. Fixes: a09a0b7c6ff1 ("arm: mvebu: add PCIe Device Tree informations for Armada 370") Signed-off-by: Pali Rohár Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm/boot/dts/armada-370.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi index 46e6d3ed8f35..c042c416a94a 100644 --- a/arch/arm/boot/dts/armada-370.dtsi +++ b/arch/arm/boot/dts/armada-370.dtsi @@ -74,7 +74,7 @@ pcie2: pcie@2,0 { device_type = "pci"; - assigned-addresses = <0x82002800 0 0x80000 0 0x2000>; + assigned-addresses = <0x82001000 0 0x80000 0 0x2000>; reg = <0x1000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; From ea8e313bb9ba843343eb4a21e538fec4fe5e568e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 18 Aug 2022 00:30:50 +0200 Subject: [PATCH 0113/4345] ARM: dts: armada-xp: Fix assigned-addresses for every PCIe Root Port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit eab276787f456cbea89fabea110fe0728673d308 ] BDF of resource in DT assigned-addresses property of Marvell PCIe Root Port (PCI-to-PCI bridge) should match BDF in address part in that DT node name as specified resource belongs to Marvell PCIe Root Port itself. Fixes: 9d8f44f02d4a ("arm: mvebu: add PCIe Device Tree informations for Armada XP") Fixes: 12b69a599745 ("ARM: mvebu: second PCIe unit of Armada XP mv78230 is only x1 capable") Fixes: 2163e61c92d9 ("ARM: mvebu: fix second and third PCIe unit of Armada XP mv78260") Signed-off-by: Pali Rohár Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm/boot/dts/armada-xp-mv78230.dtsi | 8 ++++---- arch/arm/boot/dts/armada-xp-mv78260.dtsi | 16 ++++++++-------- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arm/boot/dts/armada-xp-mv78230.dtsi b/arch/arm/boot/dts/armada-xp-mv78230.dtsi index 8558bf6bb54c..d55fe162fc7f 100644 --- a/arch/arm/boot/dts/armada-xp-mv78230.dtsi +++ b/arch/arm/boot/dts/armada-xp-mv78230.dtsi @@ -97,7 +97,7 @@ pcie2: pcie@2,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x44000 0 0x2000>; + assigned-addresses = <0x82001000 0 0x44000 0 0x2000>; reg = <0x1000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -115,7 +115,7 @@ pcie3: pcie@3,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x48000 0 0x2000>; + assigned-addresses = <0x82001800 0 0x48000 0 0x2000>; reg = <0x1800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -133,7 +133,7 @@ pcie4: pcie@4,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x4c000 0 0x2000>; + assigned-addresses = <0x82002000 0 0x4c000 0 0x2000>; reg = <0x2000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -151,7 +151,7 @@ pcie5: pcie@5,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x80000 0 0x2000>; + assigned-addresses = <0x82002800 0 0x80000 0 0x2000>; reg = <0x2800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi index 2d85fe8ac327..fdcc81819940 100644 --- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi +++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi @@ -112,7 +112,7 @@ pcie2: pcie@2,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x44000 0 0x2000>; + assigned-addresses = <0x82001000 0 0x44000 0 0x2000>; reg = <0x1000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -130,7 +130,7 @@ pcie3: pcie@3,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x48000 0 0x2000>; + assigned-addresses = <0x82001800 0 0x48000 0 0x2000>; reg = <0x1800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -148,7 +148,7 @@ pcie4: pcie@4,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x4c000 0 0x2000>; + assigned-addresses = <0x82002000 0 0x4c000 0 0x2000>; reg = <0x2000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -166,7 +166,7 @@ pcie5: pcie@5,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x80000 0 0x2000>; + assigned-addresses = <0x82002800 0 0x80000 0 0x2000>; reg = <0x2800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -184,7 +184,7 @@ pcie6: pcie@6,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x84000 0 0x2000>; + assigned-addresses = <0x82003000 0 0x84000 0 0x2000>; reg = <0x3000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -202,7 +202,7 @@ pcie7: pcie@7,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x88000 0 0x2000>; + assigned-addresses = <0x82003800 0 0x88000 0 0x2000>; reg = <0x3800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -220,7 +220,7 @@ pcie8: pcie@8,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x8c000 0 0x2000>; + assigned-addresses = <0x82004000 0 0x8c000 0 0x2000>; reg = <0x4000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -238,7 +238,7 @@ pcie9: pcie@9,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x42000 0 0x2000>; + assigned-addresses = <0x82004800 0 0x42000 0 0x2000>; reg = <0x4800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; From ea907f30320532ddaa84206c52ccba345b43e8d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 18 Aug 2022 00:30:51 +0200 Subject: [PATCH 0114/4345] ARM: dts: armada-375: Fix assigned-addresses for every PCIe Root Port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 823956d2436f70ced74c0fe8ab99facd8abfc060 ] BDF of resource in DT assigned-addresses property of Marvell PCIe Root Port (PCI-to-PCI bridge) should match BDF in address part in that DT node name as specified resource belongs to Marvell PCIe Root Port itself. Fixes: 4de59085091f ("ARM: mvebu: add Device Tree description of the Armada 375 SoC") Signed-off-by: Pali Rohár Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm/boot/dts/armada-375.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi index 9805e507c695..d117fc4ae6d9 100644 --- a/arch/arm/boot/dts/armada-375.dtsi +++ b/arch/arm/boot/dts/armada-375.dtsi @@ -582,7 +582,7 @@ pcie1: pcie@2,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x44000 0 0x2000>; + assigned-addresses = <0x82001000 0 0x44000 0 0x2000>; reg = <0x1000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; From bac1a77b85e04c15e345f6f78894c728e9418315 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 18 Aug 2022 00:30:52 +0200 Subject: [PATCH 0115/4345] ARM: dts: armada-38x: Fix assigned-addresses for every PCIe Root Port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 44f47b7a8fa4678ce4c38ea74837e4996b9df6d6 ] BDF of resource in DT assigned-addresses property of Marvell PCIe Root Port (PCI-to-PCI bridge) should match BDF in address part in that DT node name as specified resource belongs to Marvell PCIe Root Port itself. Fixes: 0d3d96ab0059 ("ARM: mvebu: add Device Tree description of the Armada 380/385 SoCs") Signed-off-by: Pali Rohár Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm/boot/dts/armada-380.dtsi | 4 ++-- arch/arm/boot/dts/armada-385.dtsi | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/boot/dts/armada-380.dtsi b/arch/arm/boot/dts/armada-380.dtsi index cff1269f3fbf..7146cc8f082a 100644 --- a/arch/arm/boot/dts/armada-380.dtsi +++ b/arch/arm/boot/dts/armada-380.dtsi @@ -79,7 +79,7 @@ /* x1 port */ pcie@2,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x40000 0 0x2000>; + assigned-addresses = <0x82001000 0 0x40000 0 0x2000>; reg = <0x1000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -98,7 +98,7 @@ /* x1 port */ pcie@3,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x44000 0 0x2000>; + assigned-addresses = <0x82001800 0 0x44000 0 0x2000>; reg = <0x1800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; diff --git a/arch/arm/boot/dts/armada-385.dtsi b/arch/arm/boot/dts/armada-385.dtsi index f0022d10c715..f081f7cb66e5 100644 --- a/arch/arm/boot/dts/armada-385.dtsi +++ b/arch/arm/boot/dts/armada-385.dtsi @@ -84,7 +84,7 @@ /* x1 port */ pcie2: pcie@2,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x40000 0 0x2000>; + assigned-addresses = <0x82001000 0 0x40000 0 0x2000>; reg = <0x1000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -103,7 +103,7 @@ /* x1 port */ pcie3: pcie@3,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x44000 0 0x2000>; + assigned-addresses = <0x82001800 0 0x44000 0 0x2000>; reg = <0x1800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -125,7 +125,7 @@ */ pcie4: pcie@4,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x48000 0 0x2000>; + assigned-addresses = <0x82002000 0 0x48000 0 0x2000>; reg = <0x2000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; From d050513e6f5985686655c853fa090532f2eba6cc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 18 Aug 2022 00:30:53 +0200 Subject: [PATCH 0116/4345] ARM: dts: armada-39x: Fix assigned-addresses for every PCIe Root Port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 69236d2391b4d7324b11c3252921571577892e7b ] BDF of resource in DT assigned-addresses property of Marvell PCIe Root Port (PCI-to-PCI bridge) should match BDF in address part in that DT node name as specified resource belongs to Marvell PCIe Root Port itself. Fixes: 538da83ddbea ("ARM: mvebu: add Device Tree files for Armada 39x SoC and board") Signed-off-by: Pali Rohár Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm/boot/dts/armada-39x.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/armada-39x.dtsi b/arch/arm/boot/dts/armada-39x.dtsi index e0b7c2099831..9525e7b7f436 100644 --- a/arch/arm/boot/dts/armada-39x.dtsi +++ b/arch/arm/boot/dts/armada-39x.dtsi @@ -453,7 +453,7 @@ /* x1 port */ pcie@2,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x40000 0 0x2000>; + assigned-addresses = <0x82001000 0 0x40000 0 0x2000>; reg = <0x1000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -472,7 +472,7 @@ /* x1 port */ pcie@3,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x44000 0 0x2000>; + assigned-addresses = <0x82001800 0 0x44000 0 0x2000>; reg = <0x1800 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; @@ -494,7 +494,7 @@ */ pcie@4,0 { device_type = "pci"; - assigned-addresses = <0x82000800 0 0x48000 0 0x2000>; + assigned-addresses = <0x82002000 0 0x48000 0 0x2000>; reg = <0x2000 0 0 0 0>; #address-cells = <3>; #size-cells = <2>; From c1322d5f6969f37ed3efea303bd218f0ffeade85 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Wed, 27 Jul 2022 15:09:26 +0200 Subject: [PATCH 0117/4345] ARM: dts: turris-omnia: Add ethernet aliases MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f1f3e530c59a7e8c5f06172f4c28b945a6b4bfb8 ] This allows bootloader to correctly pass MAC addresses used by bootloader to individual interfaces into kernel device tree. Signed-off-by: Pali Rohár Fixes: 26ca8b52d6e1 ("ARM: dts: add support for Turris Omnia") Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm/boot/dts/armada-385-turris-omnia.dts | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/boot/dts/armada-385-turris-omnia.dts b/arch/arm/boot/dts/armada-385-turris-omnia.dts index 92e08486ec81..c0a026ac7be8 100644 --- a/arch/arm/boot/dts/armada-385-turris-omnia.dts +++ b/arch/arm/boot/dts/armada-385-turris-omnia.dts @@ -22,6 +22,12 @@ stdout-path = &uart0; }; + aliases { + ethernet0 = ð0; + ethernet1 = ð1; + ethernet2 = ð2; + }; + memory { device_type = "memory"; reg = <0x00000000 0x40000000>; /* 1024 MB */ From 872865db3b952a44f63381a557a5871e5fb33491 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Thu, 25 Aug 2022 14:21:02 +0200 Subject: [PATCH 0118/4345] ARM: dts: turris-omnia: Add switch port 6 node MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f87db2005f73876602211af0ee156817019b6bda ] Switch port 6 is connected to eth0, so add appropriate device tree node for it. Fixes: 26ca8b52d6e1 ("ARM: dts: add support for Turris Omnia") Signed-off-by: Pali Rohár Reviewed-by: Andrew Lunn Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm/boot/dts/armada-385-turris-omnia.dts | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/armada-385-turris-omnia.dts b/arch/arm/boot/dts/armada-385-turris-omnia.dts index c0a026ac7be8..320c759b4090 100644 --- a/arch/arm/boot/dts/armada-385-turris-omnia.dts +++ b/arch/arm/boot/dts/armada-385-turris-omnia.dts @@ -297,7 +297,17 @@ }; }; - /* port 6 is connected to eth0 */ + ports@6 { + reg = <6>; + label = "cpu"; + ethernet = <ð0>; + phy-mode = "rgmii-id"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; }; }; }; From 4dad729f7c24b8cbe72012f7d4ff332047a7073d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 24 Sep 2022 13:58:26 +0200 Subject: [PATCH 0119/4345] arm64: dts: armada-3720-turris-mox: Add missing interrupt for RTC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 21aad8ba615e9c39cee6c5d0b76726f63791926c ] MCP7940MT-I/MNY RTC has connected interrupt line to GPIO2_5. Fixes: 7109d817db2e ("arm64: dts: marvell: add DTS for Turris Mox") Signed-off-by: Pali Rohár Reviewed-by: Andrew Lunn Signed-off-by: Gregory CLEMENT Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts index 00e5dbf4b823..eea8d23683dc 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts @@ -124,9 +124,12 @@ /delete-property/ mrvl,i2c-fast-mode; status = "okay"; + /* MCP7940MT-I/MNY RTC */ rtc@6f { compatible = "microchip,mcp7940x"; reg = <0x6f>; + interrupt-parent = <&gpiosb>; + interrupts = <5 0>; /* GPIO2_5 */ }; }; From d1b3164d0e11a2849c22822cfc606eda34e24c36 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Fri, 2 Dec 2022 16:22:54 +0800 Subject: [PATCH 0120/4345] pstore/ram: Fix error return code in ramoops_probe() [ Upstream commit e1fce564900f8734edf15b87f028c57e14f6e28d ] In the if (dev_of_node(dev) && !pdata) path, the "err" may be assigned a value of 0, so the error return code -EINVAL may be incorrectly set to 0. To fix set valid return code before calling to goto. Fixes: 35da60941e44 ("pstore/ram: add Device Tree bindings") Signed-off-by: Wang Yufen Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/1669969374-46582-1-git-send-email-wangyufen@huawei.com Signed-off-by: Sasha Levin --- fs/pstore/ram.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index ca6d8a867285..98e579ce0d63 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -730,6 +730,7 @@ static int ramoops_probe(struct platform_device *pdev) /* Make sure we didn't get bogus platform data pointer. */ if (!pdata) { pr_err("NULL platform data\n"); + err = -EINVAL; goto fail_out; } @@ -737,6 +738,7 @@ static int ramoops_probe(struct platform_device *pdev) !pdata->ftrace_size && !pdata->pmsg_size)) { pr_err("The memory size and the record/console size must be " "non-zero\n"); + err = -EINVAL; goto fail_out; } From 480bc6a165d6fe23d3521bf273fe47bd561970b3 Mon Sep 17 00:00:00 2001 From: Doug Brown Date: Sat, 3 Dec 2022 16:51:17 -0800 Subject: [PATCH 0121/4345] ARM: mmp: fix timer_read delay [ Upstream commit e348b4014c31041e13ff370669ba3348c4d385e3 ] timer_read() was using an empty 100-iteration loop to wait for the TMR_CVWR register to capture the latest timer counter value. The delay wasn't long enough. This resulted in CPU idle time being extremely underreported on PXA168 with CONFIG_NO_HZ_IDLE=y. Switch to the approach used in the vendor kernel, which implements the capture delay by reading TMR_CVWR a few times instead. Fixes: 49cbe78637eb ("[ARM] pxa: add base support for Marvell's PXA168 processor line") Signed-off-by: Doug Brown Link: https://lore.kernel.org/r/20221204005117.53452-3-doug@schmorgal.com Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- arch/arm/mach-mmp/time.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c index 41b2e8abc9e6..708816caf859 100644 --- a/arch/arm/mach-mmp/time.c +++ b/arch/arm/mach-mmp/time.c @@ -43,18 +43,21 @@ static void __iomem *mmp_timer_base = TIMERS_VIRT_BASE; /* - * FIXME: the timer needs some delay to stablize the counter capture + * Read the timer through the CVWR register. Delay is required after requesting + * a read. The CR register cannot be directly read due to metastability issues + * documented in the PXA168 software manual. */ static inline uint32_t timer_read(void) { - int delay = 100; + uint32_t val; + int delay = 3; __raw_writel(1, mmp_timer_base + TMR_CVWR(1)); while (delay--) - cpu_relax(); + val = __raw_readl(mmp_timer_base + TMR_CVWR(1)); - return __raw_readl(mmp_timer_base + TMR_CVWR(1)); + return val; } static u64 notrace mmp_read_sched_clock(void) From 295f59cd2cdeed841850d02dddde3a122cbf6fc6 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 5 Dec 2022 15:31:36 -0800 Subject: [PATCH 0122/4345] pstore: Avoid kcore oops by vmap()ing with VM_IOREMAP [ Upstream commit e6b842741b4f39007215fd7e545cb55aa3d358a2 ] An oops can be induced by running 'cat /proc/kcore > /dev/null' on devices using pstore with the ram backend because kmap_atomic() assumes lowmem pages are accessible with __va(). Unable to handle kernel paging request at virtual address ffffff807ff2b000 Mem abort info: ESR = 0x96000006 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x06: level 2 translation fault Data abort info: ISV = 0, ISS = 0x00000006 CM = 0, WnR = 0 swapper pgtable: 4k pages, 39-bit VAs, pgdp=0000000081d87000 [ffffff807ff2b000] pgd=180000017fe18003, p4d=180000017fe18003, pud=180000017fe18003, pmd=0000000000000000 Internal error: Oops: 96000006 [#1] PREEMPT SMP Modules linked in: dm_integrity CPU: 7 PID: 21179 Comm: perf Not tainted 5.15.67-10882-ge4eb2eb988cd #1 baa443fb8e8477896a370b31a821eb2009f9bfba Hardware name: Google Lazor (rev3 - 8) (DT) pstate: a0400009 (NzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __memcpy+0x110/0x260 lr : vread+0x194/0x294 sp : ffffffc013ee39d0 x29: ffffffc013ee39f0 x28: 0000000000001000 x27: ffffff807ff2b000 x26: 0000000000001000 x25: ffffffc0085a2000 x24: ffffff802d4b3000 x23: ffffff80f8a60000 x22: ffffff802d4b3000 x21: ffffffc0085a2000 x20: ffffff8080b7bc68 x19: 0000000000001000 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: ffffffd3073f2e60 x14: ffffffffad588000 x13: 0000000000000000 x12: 0000000000000001 x11: 00000000000001a2 x10: 00680000fff2bf0b x9 : 03fffffff807ff2b x8 : 0000000000000001 x7 : 0000000000000000 x6 : 0000000000000000 x5 : ffffff802d4b4000 x4 : ffffff807ff2c000 x3 : ffffffc013ee3a78 x2 : 0000000000001000 x1 : ffffff807ff2b000 x0 : ffffff802d4b3000 Call trace: __memcpy+0x110/0x260 read_kcore+0x584/0x778 proc_reg_read+0xb4/0xe4 During early boot, memblock reserves the pages for the ramoops reserved memory node in DT that would otherwise be part of the direct lowmem mapping. Pstore's ram backend reuses those reserved pages to change the memory type (writeback or non-cached) by passing the pages to vmap() (see pfn_to_page() usage in persistent_ram_vmap() for more details) with specific flags. When read_kcore() starts iterating over the vmalloc region, it runs over the virtual address that vmap() returned for ramoops. In aligned_vread() the virtual address is passed to vmalloc_to_page() which returns the page struct for the reserved lowmem area. That lowmem page is passed to kmap_atomic(), which effectively calls page_to_virt() that assumes a lowmem page struct must be directly accessible with __va() and friends. These pages are mapped via vmap() though, and the lowmem mapping was never made, so accessing them via the lowmem virtual address oopses like above. Let's side-step this problem by passing VM_IOREMAP to vmap(). This will tell vread() to not include the ramoops region in the kcore. Instead the area will look like a bunch of zeros. The alternative is to teach kmap() about vmalloc areas that intersect with lowmem. Presumably such a change isn't a one-liner, and there isn't much interest in inspecting the ramoops region in kcore files anyway, so the most expedient route is taken for now. Cc: Brian Geffon Cc: Mike Rapoport Cc: Andrew Morton Fixes: 404a6043385d ("staging: android: persistent_ram: handle reserving and mapping memory") Signed-off-by: Stephen Boyd Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221205233136.3420802-1-swboyd@chromium.org Signed-off-by: Sasha Levin --- fs/pstore/ram_core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index aa8e0b65ff1a..184cb97c83bd 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -425,7 +425,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size, phys_addr_t addr = page_start + i * PAGE_SIZE; pages[i] = pfn_to_page(addr >> PAGE_SHIFT); } - vaddr = vmap(pages, page_count, VM_MAP, prot); + /* + * VM_IOREMAP used here to bypass this region during vread() + * and kmap_atomic() (i.e. kcore) to avoid __va() failures. + */ + vaddr = vmap(pages, page_count, VM_MAP | VM_IOREMAP, prot); kfree(pages); /* From 5b217f4e79c066b001c66e3b7aa062c2bc5c8ceb Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Thu, 24 Nov 2022 03:19:26 +0000 Subject: [PATCH 0123/4345] tpm/tpm_ftpm_tee: Fix error handling in ftpm_mod_init() [ Upstream commit 2b7d07f7acaac2c7750e420dcf4414588ede6d03 ] The ftpm_mod_init() returns the driver_register() directly without checking its return value, if driver_register() failed, the ftpm_tee_plat_driver is not unregistered. Fix by unregister ftpm_tee_plat_driver when driver_register() failed. Fixes: 9f1944c23c8c ("tpm_ftpm_tee: register driver on TEE bus") Signed-off-by: Yuan Can Reviewed-by: Maxim Uvarov Acked-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_ftpm_tee.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/char/tpm/tpm_ftpm_tee.c b/drivers/char/tpm/tpm_ftpm_tee.c index 6e3235565a4d..d9daaafdd295 100644 --- a/drivers/char/tpm/tpm_ftpm_tee.c +++ b/drivers/char/tpm/tpm_ftpm_tee.c @@ -397,7 +397,13 @@ static int __init ftpm_mod_init(void) if (rc) return rc; - return driver_register(&ftpm_tee_driver.driver); + rc = driver_register(&ftpm_tee_driver.driver); + if (rc) { + platform_driver_unregister(&ftpm_tee_plat_driver); + return rc; + } + + return 0; } static void __exit ftpm_mod_exit(void) From 6389c163c92bf7446a65114ac0cf957cc486c512 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Fri, 11 Nov 2022 11:38:53 -0800 Subject: [PATCH 0124/4345] tpm/tpm_crb: Fix error message in __crb_relinquish_locality() [ Upstream commit f5264068071964b56dc02c9dab3d11574aaca6ff ] The error message in __crb_relinquish_locality() mentions requestAccess instead of Relinquish. Fix it. Fixes: 888d867df441 ("tpm: cmd_ready command can be issued only after granting locality") Signed-off-by: Michael Kelley Acked-by: Tomas Winkler Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_crb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index a9dcf31eadd2..35c5227f3a88 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -252,7 +252,7 @@ static int __crb_relinquish_locality(struct device *dev, iowrite32(CRB_LOC_CTRL_RELINQUISH, &priv->regs_h->loc_ctrl); if (!crb_wait_for_reg_32(&priv->regs_h->loc_state, mask, value, TPM2_TIMEOUT_C)) { - dev_warn(dev, "TPM_LOC_STATE_x.requestAccess timed out\n"); + dev_warn(dev, "TPM_LOC_STATE_x.Relinquish timed out\n"); return -ETIME; } From ca9ef12bf7657687ef1c484584ce03e3c743561d Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Tue, 7 Dec 2021 09:57:55 +0000 Subject: [PATCH 0125/4345] sched/fair: Cleanup task_util and capacity type [ Upstream commit ef8df9798d469b7c45c66664550e93469749f1e8 ] task_util and capacity are comparable unsigned long values. There is no need for an intermidiate implicit signed cast. Signed-off-by: Vincent Donnefort Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20211207095755.859972-1-vincent.donnefort@arm.com Stable-dep-of: 48d5e9daa8b7 ("sched/uclamp: Fix relationship between uclamp and migration margin") Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bca0efc03a51..2d3ea0679207 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4074,7 +4074,8 @@ done: trace_sched_util_est_se_tp(&p->se); } -static inline int task_fits_capacity(struct task_struct *p, long capacity) +static inline int task_fits_capacity(struct task_struct *p, + unsigned long capacity) { return fits_capacity(uclamp_task_util(p), capacity); } @@ -6247,7 +6248,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) return best_cpu; } -static inline bool asym_fits_capacity(int task_util, int cpu) +static inline bool asym_fits_capacity(unsigned long task_util, int cpu) { if (static_branch_unlikely(&sched_asym_cpucapacity)) return fits_capacity(task_util, capacity_of(cpu)); From 2ff401441711b2b902c3b0a55113e9cd01380195 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Thu, 4 Aug 2022 15:36:01 +0100 Subject: [PATCH 0126/4345] sched/uclamp: Fix relationship between uclamp and migration margin [ Upstream commit 48d5e9daa8b767e75ed9421665b037a49ce4bc04 ] fits_capacity() verifies that a util is within 20% margin of the capacity of a CPU, which is an attempt to speed up upmigration. But when uclamp is used, this 20% margin is problematic because for example if a task is boosted to 1024, then it will not fit on any CPU according to fits_capacity() logic. Or if a task is boosted to capacity_orig_of(medium_cpu). The task will end up on big instead on the desired medium CPU. Similar corner cases exist for uclamp and usage of capacity_of(). Slightest irq pressure on biggest CPU for example will make a 1024 boosted task look like it can't fit. What we really want is for uclamp comparisons to ignore the migration margin and capacity pressure, yet retain them for when checking the _actual_ util signal. For example, task p: p->util_avg = 300 p->uclamp[UCLAMP_MIN] = 1024 Will fit a big CPU. But p->util_avg = 900 p->uclamp[UCLAMP_MIN] = 1024 will not, this should trigger overutilized state because the big CPU is now *actually* being saturated. Similar reasoning applies to capping tasks with UCLAMP_MAX. For example: p->util_avg = 1024 p->uclamp[UCLAMP_MAX] = capacity_orig_of(medium_cpu) Should fit the task on medium cpus without triggering overutilized state. Inlined comments expand more on desired behavior in more scenarios. Introduce new util_fits_cpu() function which encapsulates the new logic. The new function is not used anywhere yet, but will be used to update various users of fits_capacity() in later patches. Fixes: af24bde8df202 ("sched/uclamp: Add uclamp support to energy_compute()") Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220804143609.515789-2-qais.yousef@arm.com Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 123 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 123 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2d3ea0679207..c39d2fc3f994 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4074,6 +4074,129 @@ done: trace_sched_util_est_se_tp(&p->se); } +static inline int util_fits_cpu(unsigned long util, + unsigned long uclamp_min, + unsigned long uclamp_max, + int cpu) +{ + unsigned long capacity_orig, capacity_orig_thermal; + unsigned long capacity = capacity_of(cpu); + bool fits, uclamp_max_fits; + + /* + * Check if the real util fits without any uclamp boost/cap applied. + */ + fits = fits_capacity(util, capacity); + + if (!uclamp_is_used()) + return fits; + + /* + * We must use capacity_orig_of() for comparing against uclamp_min and + * uclamp_max. We only care about capacity pressure (by using + * capacity_of()) for comparing against the real util. + * + * If a task is boosted to 1024 for example, we don't want a tiny + * pressure to skew the check whether it fits a CPU or not. + * + * Similarly if a task is capped to capacity_orig_of(little_cpu), it + * should fit a little cpu even if there's some pressure. + * + * Only exception is for thermal pressure since it has a direct impact + * on available OPP of the system. + * + * We honour it for uclamp_min only as a drop in performance level + * could result in not getting the requested minimum performance level. + * + * For uclamp_max, we can tolerate a drop in performance level as the + * goal is to cap the task. So it's okay if it's getting less. + * + * In case of capacity inversion, which is not handled yet, we should + * honour the inverted capacity for both uclamp_min and uclamp_max all + * the time. + */ + capacity_orig = capacity_orig_of(cpu); + capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); + + /* + * We want to force a task to fit a cpu as implied by uclamp_max. + * But we do have some corner cases to cater for.. + * + * + * C=z + * | ___ + * | C=y | | + * |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _ uclamp_max + * | C=x | | | | + * | ___ | | | | + * | | | | | | | (util somewhere in this region) + * | | | | | | | + * | | | | | | | + * +---------------------------------------- + * cpu0 cpu1 cpu2 + * + * In the above example if a task is capped to a specific performance + * point, y, then when: + * + * * util = 80% of x then it does not fit on cpu0 and should migrate + * to cpu1 + * * util = 80% of y then it is forced to fit on cpu1 to honour + * uclamp_max request. + * + * which is what we're enforcing here. A task always fits if + * uclamp_max <= capacity_orig. But when uclamp_max > capacity_orig, + * the normal upmigration rules should withhold still. + * + * Only exception is when we are on max capacity, then we need to be + * careful not to block overutilized state. This is so because: + * + * 1. There's no concept of capping at max_capacity! We can't go + * beyond this performance level anyway. + * 2. The system is being saturated when we're operating near + * max capacity, it doesn't make sense to block overutilized. + */ + uclamp_max_fits = (capacity_orig == SCHED_CAPACITY_SCALE) && (uclamp_max == SCHED_CAPACITY_SCALE); + uclamp_max_fits = !uclamp_max_fits && (uclamp_max <= capacity_orig); + fits = fits || uclamp_max_fits; + + /* + * + * C=z + * | ___ (region a, capped, util >= uclamp_max) + * | C=y | | + * |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _ uclamp_max + * | C=x | | | | + * | ___ | | | | (region b, uclamp_min <= util <= uclamp_max) + * |_ _ _|_ _|_ _ _ _| _ | _ _ _| _ | _ _ _ _ _ uclamp_min + * | | | | | | | + * | | | | | | | (region c, boosted, util < uclamp_min) + * +---------------------------------------- + * cpu0 cpu1 cpu2 + * + * a) If util > uclamp_max, then we're capped, we don't care about + * actual fitness value here. We only care if uclamp_max fits + * capacity without taking margin/pressure into account. + * See comment above. + * + * b) If uclamp_min <= util <= uclamp_max, then the normal + * fits_capacity() rules apply. Except we need to ensure that we + * enforce we remain within uclamp_max, see comment above. + * + * c) If util < uclamp_min, then we are boosted. Same as (b) but we + * need to take into account the boosted value fits the CPU without + * taking margin/pressure into account. + * + * Cases (a) and (b) are handled in the 'fits' variable already. We + * just need to consider an extra check for case (c) after ensuring we + * handle the case uclamp_min > uclamp_max. + */ + uclamp_min = min(uclamp_min, uclamp_max); + if (util < uclamp_min && capacity_orig != SCHED_CAPACITY_SCALE) + fits = fits && (uclamp_min <= capacity_orig_thermal); + + return fits; +} + static inline int task_fits_capacity(struct task_struct *p, unsigned long capacity) { From 1498d2723e74eac6fb06100eeaeca560c57d754e Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 21 Oct 2022 17:10:12 +0200 Subject: [PATCH 0127/4345] cpuidle: dt: Return the correct numbers of parsed idle states [ Upstream commit ee3c2c8ad6ba6785f14a60e4081d7c82e88162a2 ] While we correctly skips to initialize an idle state from a disabled idle state node in DT, the returned value from dt_init_idle_driver() don't get adjusted accordingly. Instead the number of found idle state nodes are returned, while the callers are expecting the number of successfully initialized idle states from DT. This leads to cpuidle drivers unnecessarily continues to initialize their idle state specific data. Moreover, in the case when all idle states have been disabled in DT, we would end up registering a cpuidle driver, rather than relying on the default arch specific idle call. Fixes: 9f14da345599 ("drivers: cpuidle: implement DT based idle states infrastructure") Signed-off-by: Ulf Hansson Reviewed-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/cpuidle/dt_idle_states.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpuidle/dt_idle_states.c b/drivers/cpuidle/dt_idle_states.c index 252f2a9686a6..448bc796b0b4 100644 --- a/drivers/cpuidle/dt_idle_states.c +++ b/drivers/cpuidle/dt_idle_states.c @@ -223,6 +223,6 @@ int dt_init_idle_driver(struct cpuidle_driver *drv, * also be 0 on platforms with missing DT idle states or legacy DT * configuration predating the DT idle states bindings. */ - return i; + return state_idx - start_idx; } EXPORT_SYMBOL_GPL(dt_init_idle_driver); From ef875e1c07dd95b729ca58a2accec093af4d8812 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Sep 2021 18:18:48 -0400 Subject: [PATCH 0128/4345] alpha: fix syscall entry in !AUDUT_SYSCALL case [ Upstream commit f7b2431a6d22f7a91c567708e071dfcd6d66db14 ] We only want to take the slow path if SYSCALL_TRACE or SYSCALL_AUDIT is set; on !AUDIT_SYSCALL configs the current tree hits it whenever _any_ thread flag (including NEED_RESCHED, NOTIFY_SIGNAL, etc.) happens to be set. Fixes: a9302e843944 "alpha: Enable system-call auditing support" Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- arch/alpha/kernel/entry.S | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index e227f3a29a43..c41a5a9c3b9f 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -469,8 +469,10 @@ entSys: #ifdef CONFIG_AUDITSYSCALL lda $6, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT and $3, $6, $3 -#endif bne $3, strace +#else + blbs $3, strace /* check for SYSCALL_TRACE in disguise */ +#endif beq $4, 1f ldq $27, 0($5) 1: jsr $26, ($27), sys_ni_syscall From 9e760e0cf28fc9d9ba4eee3e97f2301a64e60526 Mon Sep 17 00:00:00 2001 From: xiongxin Date: Tue, 1 Nov 2022 10:28:39 +0800 Subject: [PATCH 0129/4345] PM: hibernate: Fix mistake in kerneldoc comment [ Upstream commit 6e5d7300cbe7c3541bc31f16db3e9266e6027b4b ] The actual maximum image size formula in hibernate_preallocate_memory() is as follows: max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE); but the one in the kerneldoc comment of the function is different and incorrect. Fixes: ddeb64870810 ("PM / Hibernate: Add sysfs knob to control size of memory for drivers") Signed-off-by: xiongxin [ rjw: Subject and changelog rewrite ] Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- kernel/power/snapshot.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 1da013f50059..f5dccd445d36 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1677,8 +1677,8 @@ static unsigned long minimum_image_size(unsigned long saveable) * /sys/power/reserved_size, respectively). To make this happen, we compute the * total number of available page frames and allocate at least * - * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 - * + 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE) + * ([page frames total] - PAGES_FOR_IO - [metadata pages]) / 2 + * - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE) * * of them, which corresponds to the maximum size of a hibernation image. * From aa5f2912bb2e17c952d223212f792b000302c26c Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Thu, 3 Nov 2022 16:12:05 +0100 Subject: [PATCH 0130/4345] fs: don't audit the capability check in simple_xattr_list() [ Upstream commit e7eda157c4071cd1e69f4b1687b0fbe1ae5e6f46 ] The check being unconditional may lead to unwanted denials reported by LSMs when a process has the capability granted by DAC, but denied by an LSM. In the case of SELinux such denials are a problem, since they can't be effectively filtered out via the policy and when not silenced, they produce noise that may hide a true problem or an attack. Checking for the capability only if any trusted xattr is actually present wouldn't really address the issue, since calling listxattr(2) on such node on its own doesn't indicate an explicit attempt to see the trusted xattrs. Additionally, it could potentially leak the presence of trusted xattrs to an unprivileged user if they can check for the denials (e.g. through dmesg). Therefore, it's best (and simplest) to keep the check unconditional and instead use ns_capable_noaudit() that will silence any associated LSM denials. Fixes: 38f38657444d ("xattr: extract simple_xattr code from tmpfs") Reported-by: Martin Pitt Suggested-by: Christian Brauner (Microsoft) Signed-off-by: Ondrej Mosnacek Reviewed-by: Christian Brauner (Microsoft) Reviewed-by: Paul Moore Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Sasha Levin --- fs/xattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xattr.c b/fs/xattr.c index cd7a563e8bcd..5a03eaadf029 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -1049,7 +1049,7 @@ static int xattr_list_one(char **buffer, ssize_t *remaining_size, ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size) { - bool trusted = capable(CAP_SYS_ADMIN); + bool trusted = ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; int err = 0; From 3ef12a4a8ef5553af9c3fd2719a616637a102568 Mon Sep 17 00:00:00 2001 From: Chen Hui Date: Tue, 8 Nov 2022 15:23:02 +0800 Subject: [PATCH 0131/4345] cpufreq: qcom-hw: Fix memory leak in qcom_cpufreq_hw_read_lut() [ Upstream commit 9901c21bcaf2f01fe5078f750d624f4ddfa8f81b ] If "cpu_dev" fails to get opp table in qcom_cpufreq_hw_read_lut(), the program will return, resulting in "table" resource is not released. Fixes: 51c843cf77bb ("cpufreq: qcom: Update the bandwidth levels on frequency change") Signed-off-by: Chen Hui Reviewed-by: Sibi Sankar Signed-off-by: Viresh Kumar Signed-off-by: Sasha Levin --- drivers/cpufreq/qcom-cpufreq-hw.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 6de07556665b..a9880998f8ba 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -158,6 +158,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev, } } else if (ret != -ENODEV) { dev_err(cpu_dev, "Invalid opp table in device tree\n"); + kfree(table); return ret; } else { policy->fast_switch_possible = true; From 294ed8bfc9375a18499a14bd2bc7c0696a492eaa Mon Sep 17 00:00:00 2001 From: Yipeng Zou Date: Fri, 4 Nov 2022 10:09:31 +0800 Subject: [PATCH 0132/4345] selftests/ftrace: event_triggers: wait longer for test_event_enable [ Upstream commit a1d6cd88c8973cfb08ee85722488b1d6d5d16327 ] In some platform, the schedule event may came slowly, delay 100ms can't cover it. I was notice that on my board which running in low cpu_freq,and this selftests allways gose fail. So maybe we can check more times here to wait longer. Fixes: 43bb45da82f9 ("selftests: ftrace: Add a selftest to test event enable/disable func trigger") Signed-off-by: Yipeng Zou Acked-by: Masami Hiramatsu (Google) Acked-by: Steven Rostedt (Google) Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- .../ftrace/test.d/ftrace/func_event_triggers.tc | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc index 3145b0f1835c..27a68bbe778b 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc @@ -38,11 +38,18 @@ cnt_trace() { test_event_enabled() { val=$1 + check_times=10 # wait for 10 * SLEEP_TIME at most - e=`cat $EVENT_ENABLE` - if [ "$e" != $val ]; then - fail "Expected $val but found $e" - fi + while [ $check_times -ne 0 ]; do + e=`cat $EVENT_ENABLE` + if [ "$e" == $val ]; then + return 0 + fi + sleep $SLEEP_TIME + check_times=$((check_times - 1)) + done + + fail "Expected $val but found $e" } run_enable_disable() { From 60a7a0aa9dd81e3374fbdbb5a75ca456d12fb46b Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Fri, 11 Nov 2022 18:36:53 +0800 Subject: [PATCH 0133/4345] perf: Fix possible memleak in pmu_dev_alloc() [ Upstream commit e8d7a90c08ce963c592fb49845f2ccc606a2ac21 ] In pmu_dev_alloc(), when dev_set_name() failed, it will goto free_dev and call put_device(pmu->dev) to release it. However pmu->dev->release is assigned after this, which makes warning and memleak. Call dev_set_name() after pmu->dev->release = pmu_dev_release to fix it. Device '(null)' does not have a release() function... WARNING: CPU: 2 PID: 441 at drivers/base/core.c:2332 device_release+0x1b9/0x240 ... Call Trace: kobject_put+0x17f/0x460 put_device+0x20/0x30 pmu_dev_alloc+0x152/0x400 perf_pmu_register+0x96b/0xee0 ... kmemleak: 1 new suspected memory leaks (see /sys/kernel/debug/kmemleak) unreferenced object 0xffff888014759000 (size 2048): comm "modprobe", pid 441, jiffies 4294931444 (age 38.332s) backtrace: [<0000000005aed3b4>] kmalloc_trace+0x27/0x110 [<000000006b38f9b8>] pmu_dev_alloc+0x50/0x400 [<00000000735f17be>] perf_pmu_register+0x96b/0xee0 [<00000000e38477f1>] 0xffffffffc0ad8603 [<000000004e162216>] do_one_initcall+0xd0/0x4e0 ... Fixes: abe43400579d ("perf: Sysfs enumeration") Signed-off-by: Chen Zhongjin Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20221111103653.91058-1-chenzhongjin@huawei.com Signed-off-by: Sasha Levin --- kernel/events/core.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index e9b354d521a3..979d7946a772 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10810,13 +10810,15 @@ static int pmu_dev_alloc(struct pmu *pmu) pmu->dev->groups = pmu->attr_groups; device_initialize(pmu->dev); - ret = dev_set_name(pmu->dev, "%s", pmu->name); - if (ret) - goto free_dev; dev_set_drvdata(pmu->dev, pmu); pmu->dev->bus = &pmu_bus; pmu->dev->release = pmu_dev_release; + + ret = dev_set_name(pmu->dev, "%s", pmu->name); + if (ret) + goto free_dev; + ret = device_add(pmu->dev); if (ret) goto free_dev; From a1014fbc83e799003b60ae2b745c65147cebb86c Mon Sep 17 00:00:00 2001 From: wuchi Date: Sat, 11 Jun 2022 21:06:34 +0800 Subject: [PATCH 0134/4345] lib/debugobjects: fix stat count and optimize debug_objects_mem_init [ Upstream commit eabb7f1ace53e127309407b2b5e74e8199e85270 ] 1. Var debug_objects_allocated tracks valid kmem_cache_alloc calls, so track it in debug_objects_replace_static_objects. Do similar things in object_cpu_offline. 2. In debug_objects_mem_init, there is no need to call function cpuhp_setup_state_nocalls when debug_objects_enabled = 0 (out of memory). Link: https://lkml.kernel.org/r/20220611130634.99741-1-wuchi.zero@gmail.com Fixes: 634d61f45d6f ("debugobjects: Percpu pool lookahead freeing/allocation") Fixes: c4b73aabd098 ("debugobjects: Track number of kmem_cache_alloc/kmem_cache_free done") Signed-off-by: wuchi Reviewed-by: Waiman Long Cc: Thomas Gleixner Cc: Christoph Hellwig Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- lib/debugobjects.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 9e14ae02306b..71bdc167a9ee 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -440,6 +440,7 @@ static int object_cpu_offline(unsigned int cpu) struct debug_percpu_free *percpu_pool; struct hlist_node *tmp; struct debug_obj *obj; + unsigned long flags; /* Remote access is safe as the CPU is dead already */ percpu_pool = per_cpu_ptr(&percpu_obj_pool, cpu); @@ -447,6 +448,12 @@ static int object_cpu_offline(unsigned int cpu) hlist_del(&obj->node); kmem_cache_free(obj_cache, obj); } + + raw_spin_lock_irqsave(&pool_lock, flags); + obj_pool_used -= percpu_pool->obj_free; + debug_objects_freed += percpu_pool->obj_free; + raw_spin_unlock_irqrestore(&pool_lock, flags); + percpu_pool->obj_free = 0; return 0; @@ -1316,6 +1323,8 @@ static int __init debug_objects_replace_static_objects(void) hlist_add_head(&obj->node, &objects); } + debug_objects_allocated += i; + /* * debug_objects_mem_init() is now called early that only one CPU is up * and interrupts have been disabled, so it is safe to replace the @@ -1384,6 +1393,7 @@ void __init debug_objects_mem_init(void) debug_objects_enabled = 0; kmem_cache_destroy(obj_cache); pr_warn("out of memory.\n"); + return; } else debug_objects_selftest(); From 2f2ae35c001213d35e49590380613978e4584389 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20P=C5=91cze?= Date: Wed, 5 Oct 2022 15:00:45 +0000 Subject: [PATCH 0135/4345] platform/x86: huawei-wmi: fix return value calculation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0b9a1dcdb6a2c841899389bf2dd7a3e0e2aa0e99 ] Previously, `huawei_wmi_input_setup()` returned the result of logical or-ing the return values of two functions that return negative errno-style error codes and one that returns `acpi_status`. If this returned value was non-zero, then it was propagated from the platform driver's probe function. That function should return a negative errno-style error code, so the result of the logical or that `huawei_wmi_input_setup()` returned was not appropriate. Fix that by checking each function separately and returning the error code unmodified. Fixes: 1ac9abeb2e5b ("platform/x86: huawei-wmi: Move to platform driver") Signed-off-by: Barnabás Pőcze Link: https://lore.kernel.org/r/20221005150032.173198-2-pobrn@protonmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/huawei-wmi.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/huawei-wmi.c b/drivers/platform/x86/huawei-wmi.c index eac3e6b4ea11..935562c870c3 100644 --- a/drivers/platform/x86/huawei-wmi.c +++ b/drivers/platform/x86/huawei-wmi.c @@ -760,6 +760,9 @@ static int huawei_wmi_input_setup(struct device *dev, const char *guid, struct input_dev **idev) { + acpi_status status; + int err; + *idev = devm_input_allocate_device(dev); if (!*idev) return -ENOMEM; @@ -769,10 +772,19 @@ static int huawei_wmi_input_setup(struct device *dev, (*idev)->id.bustype = BUS_HOST; (*idev)->dev.parent = dev; - return sparse_keymap_setup(*idev, huawei_wmi_keymap, NULL) || - input_register_device(*idev) || - wmi_install_notify_handler(guid, huawei_wmi_input_notify, - *idev); + err = sparse_keymap_setup(*idev, huawei_wmi_keymap, NULL); + if (err) + return err; + + err = input_register_device(*idev); + if (err) + return err; + + status = wmi_install_notify_handler(guid, huawei_wmi_input_notify, *idev); + if (ACPI_FAILURE(status)) + return -EIO; + + return 0; } static void huawei_wmi_input_exit(struct device *dev, const char *guid) From d5bf025c5b7169f6f1d3d9ca9a36c6f0b39e39cb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20P=C5=91cze?= Date: Mon, 14 Nov 2022 19:54:23 +0000 Subject: [PATCH 0136/4345] timerqueue: Use rb_entry_safe() in timerqueue_getnext() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2f117484329b233455ee278f2d9b0a4356835060 ] When `timerqueue_getnext()` is called on an empty timer queue, it will use `rb_entry()` on a NULL pointer, which is invalid. Fix that by using `rb_entry_safe()` which handles NULL pointers. This has not caused any issues so far because the offset of the `rb_node` member in `timerqueue_node` is 0, so `rb_entry()` is essentially a no-op. Fixes: 511885d7061e ("lib/timerqueue: Rely on rbtree semantics for next timer") Signed-off-by: Barnabás Pőcze Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20221114195421.342929-1-pobrn@protonmail.com Signed-off-by: Sasha Levin --- include/linux/timerqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index 93884086f392..adc80e29168e 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -35,7 +35,7 @@ struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head) { struct rb_node *leftmost = rb_first_cached(&head->rb_root); - return rb_entry(leftmost, struct timerqueue_node, node); + return rb_entry_safe(leftmost, struct timerqueue_node, node); } static inline void timerqueue_init(struct timerqueue_node *node) From 9f6ea28f295f5f93349391b37ccde6a68edc5eee Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 24 Oct 2022 21:08:09 +0300 Subject: [PATCH 0137/4345] proc: fixup uptime selftest [ Upstream commit 5cc81d5c81af0dee54da9a67a3ebe4be076a13db ] syscall(3) returns -1 and sets errno on error, unlike "syscall" instruction. Systems which have <= 32/64 CPUs are unaffected. Test won't bounce to all CPUs before completing if there are more of them. Link: https://lkml.kernel.org/r/Y1bUiT7VRXlXPQa1@p183 Fixes: 1f5bd0547654 ("proc: selftests: test /proc/uptime") Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- tools/testing/selftests/proc/proc-uptime-002.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/proc/proc-uptime-002.c b/tools/testing/selftests/proc/proc-uptime-002.c index e7ceabed7f51..7d0aa22bdc12 100644 --- a/tools/testing/selftests/proc/proc-uptime-002.c +++ b/tools/testing/selftests/proc/proc-uptime-002.c @@ -17,6 +17,7 @@ // while shifting across CPUs. #undef NDEBUG #include +#include #include #include #include @@ -54,7 +55,7 @@ int main(void) len += sizeof(unsigned long); free(m); m = malloc(len); - } while (sys_sched_getaffinity(0, len, m) == -EINVAL); + } while (sys_sched_getaffinity(0, len, m) == -1 && errno == EINVAL); fd = open("/proc/uptime", O_RDONLY); assert(fd >= 0); From c9a9aa02f0fa3318e0ae5774f404419a1b4759ca Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Mon, 31 Oct 2022 19:38:29 +0800 Subject: [PATCH 0138/4345] lib/fonts: fix undefined behavior in bit shift for get_default_font [ Upstream commit 6fe888c4d2fb174408e4540bb2d5602b9f507f90 ] Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. The UBSAN warning calltrace like below: UBSAN: shift-out-of-bounds in lib/fonts/fonts.c:139:20 left shift of 1 by 31 places cannot be represented in type 'int' dump_stack_lvl+0x7d/0xa5 dump_stack+0x15/0x1b ubsan_epilogue+0xe/0x4e __ubsan_handle_shift_out_of_bounds+0x1e7/0x20c get_default_font+0x1c7/0x1f0 fbcon_startup+0x347/0x3a0 do_take_over_console+0xce/0x270 do_fbcon_takeover+0xa1/0x170 do_fb_registered+0x2a8/0x340 fbcon_fb_registered+0x47/0xe0 register_framebuffer+0x294/0x4a0 __drm_fb_helper_initial_config_and_unlock+0x43c/0x880 [drm_kms_helper] drm_fb_helper_initial_config+0x52/0x80 [drm_kms_helper] drm_fbdev_client_hotplug+0x156/0x1b0 [drm_kms_helper] drm_fbdev_generic_setup+0xfc/0x290 [drm_kms_helper] bochs_pci_probe+0x6ca/0x772 [bochs] local_pci_probe+0x4d/0xb0 pci_device_probe+0x119/0x320 really_probe+0x181/0x550 __driver_probe_device+0xc6/0x220 driver_probe_device+0x32/0x100 __driver_attach+0x195/0x200 bus_for_each_dev+0xbb/0x120 driver_attach+0x27/0x30 bus_add_driver+0x22e/0x2f0 driver_register+0xa9/0x190 __pci_register_driver+0x90/0xa0 bochs_pci_driver_init+0x52/0x1000 [bochs] do_one_initcall+0x76/0x430 do_init_module+0x61/0x28a load_module+0x1f82/0x2e50 __do_sys_finit_module+0xf8/0x190 __x64_sys_finit_module+0x23/0x30 do_syscall_64+0x58/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Link: https://lkml.kernel.org/r/20221031113829.4183153-1-cuigaosheng1@huawei.com Fixes: c81f717cb9e0 ("fbcon: Fix typo and bogus logic in get_default_font") Signed-off-by: Gaosheng Cui Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- lib/fonts/fonts.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/fonts/fonts.c b/lib/fonts/fonts.c index 5f4b07b56cd9..973866438608 100644 --- a/lib/fonts/fonts.c +++ b/lib/fonts/fonts.c @@ -135,8 +135,8 @@ const struct font_desc *get_default_font(int xres, int yres, u32 font_w, if (res > 20) c += 20 - res; - if ((font_w & (1 << (f->width - 1))) && - (font_h & (1 << (f->height - 1)))) + if ((font_w & (1U << (f->width - 1))) && + (font_h & (1U << (f->height - 1)))) c += 1000; if (c > cc) { From f5f2682d3a34dd8350bf63f232d885fd95f25b92 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Tue, 1 Nov 2022 19:15:33 +0800 Subject: [PATCH 0139/4345] ocfs2: fix memory leak in ocfs2_stack_glue_init() [ Upstream commit 13b6269dd022aaa69ca8d1df374ab327504121cf ] ocfs2_table_header should be free in ocfs2_stack_glue_init() if ocfs2_sysfs_init() failed, otherwise kmemleak will report memleak. BUG: memory leak unreferenced object 0xffff88810eeb5800 (size 128): comm "modprobe", pid 4507, jiffies 4296182506 (age 55.888s) hex dump (first 32 bytes): c0 40 14 a0 ff ff ff ff 00 00 00 00 01 00 00 00 .@.............. 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<000000001e59e1cd>] __register_sysctl_table+0xca/0xef0 [<00000000c04f70f7>] 0xffffffffa0050037 [<000000001bd12912>] do_one_initcall+0xdb/0x480 [<0000000064f766c9>] do_init_module+0x1cf/0x680 [<000000002ba52db0>] load_module+0x6441/0x6f20 [<000000009772580d>] __do_sys_finit_module+0x12f/0x1c0 [<00000000380c1f22>] do_syscall_64+0x3f/0x90 [<000000004cf473bc>] entry_SYSCALL_64_after_hwframe+0x63/0xcd Link: https://lkml.kernel.org/r/41651ca1-432a-db34-eb97-d35744559de1@linux.alibaba.com Fixes: 3878f110f71a ("ocfs2: Move the hb_ctl_path sysctl into the stack glue.") Signed-off-by: Shang XiaoJing Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/ocfs2/stackglue.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 03eacb249f37..5e272e257b0b 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -705,6 +705,8 @@ static struct ctl_table_header *ocfs2_table_header; static int __init ocfs2_stack_glue_init(void) { + int ret; + strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); ocfs2_table_header = register_sysctl_table(ocfs2_root_table); @@ -714,7 +716,11 @@ static int __init ocfs2_stack_glue_init(void) return -ENOMEM; /* or something. */ } - return ocfs2_sysfs_init(); + ret = ocfs2_sysfs_init(); + if (ret) + unregister_sysctl_table(ocfs2_table_header); + + return ret; } static void __exit ocfs2_stack_glue_exit(void) From 48d42f4464d713fbdd79f334fdcd6e5be534cc67 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 4 Nov 2022 11:39:44 +0800 Subject: [PATCH 0140/4345] MIPS: vpe-mt: fix possible memory leak while module exiting [ Upstream commit 5822e8cc84ee37338ab0bdc3124f6eec04dc232d ] Afer commit 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array"), the name of device is allocated dynamically, it need be freed when module exiting, call put_device() to give up reference, so that it can be freed in kobject_cleanup() when the refcount hit to 0. The vpe_device is static, so remove kfree() from vpe_device_release(). Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array") Signed-off-by: Yang Yingliang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/kernel/vpe-mt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/vpe-mt.c b/arch/mips/kernel/vpe-mt.c index 2e003b11a098..9fd7cd48ea1d 100644 --- a/arch/mips/kernel/vpe-mt.c +++ b/arch/mips/kernel/vpe-mt.c @@ -313,7 +313,6 @@ ATTRIBUTE_GROUPS(vpe); static void vpe_device_release(struct device *cd) { - kfree(cd); } static struct class vpe_class = { @@ -497,6 +496,7 @@ out_dev: device_del(&vpe_device); out_class: + put_device(&vpe_device); class_unregister(&vpe_class); out_chrdev: @@ -509,7 +509,7 @@ void __exit vpe_module_exit(void) { struct vpe *v, *n; - device_del(&vpe_device); + device_unregister(&vpe_device); class_unregister(&vpe_class); unregister_chrdev(major, VPE_MODULE_NAME); From 911773f08ce6eae9f6203a7cdb2fd27f977b07ba Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 4 Nov 2022 11:39:45 +0800 Subject: [PATCH 0141/4345] MIPS: vpe-cmp: fix possible memory leak while module exiting [ Upstream commit c5ed1fe0801f0c66b0fbce2785239a5664629057 ] dev_set_name() allocates memory for name, it need be freed when module exiting, call put_device() to give up reference, so that it can be freed in kobject_cleanup() when the refcount hit to 0. The vpe_device is static, so remove kfree() from vpe_device_release(). Fixes: 17a1d523aa58 ("MIPS: APRP: Add VPE loader support for CMP platforms.") Signed-off-by: Yang Yingliang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/kernel/vpe-cmp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/vpe-cmp.c b/arch/mips/kernel/vpe-cmp.c index 9268ebc0f61e..903c07bdc92d 100644 --- a/arch/mips/kernel/vpe-cmp.c +++ b/arch/mips/kernel/vpe-cmp.c @@ -75,7 +75,6 @@ ATTRIBUTE_GROUPS(vpe); static void vpe_device_release(struct device *cd) { - kfree(cd); } static struct class vpe_class = { @@ -157,6 +156,7 @@ out_dev: device_del(&vpe_device); out_class: + put_device(&vpe_device); class_unregister(&vpe_class); out_chrdev: @@ -169,7 +169,7 @@ void __exit vpe_module_exit(void) { struct vpe *v, *n; - device_del(&vpe_device); + device_unregister(&vpe_device); class_unregister(&vpe_class); unregister_chrdev(major, VPE_MODULE_NAME); From e1049bf0ca5b6466e5ea6e6312ef528dbe880091 Mon Sep 17 00:00:00 2001 From: Zhao Gongyi Date: Tue, 22 Nov 2022 19:26:26 +0800 Subject: [PATCH 0142/4345] selftests/efivarfs: Add checking of the test return value [ Upstream commit c93924267fe6f2b44af1849f714ae9cd8117a9cd ] Add checking of the test return value, otherwise it will report success forever for test_create_read(). Fixes: dff6d2ae56d0 ("selftests/efivarfs: clean up test files from test_create*()") Signed-off-by: Zhao Gongyi Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/efivarfs/efivarfs.sh | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh index a90f394f9aa9..d374878cc0ba 100755 --- a/tools/testing/selftests/efivarfs/efivarfs.sh +++ b/tools/testing/selftests/efivarfs/efivarfs.sh @@ -87,6 +87,11 @@ test_create_read() { local file=$efivarfs_mount/$FUNCNAME-$test_guid ./create-read $file + if [ $? -ne 0 ]; then + echo "create and read $file failed" + file_cleanup $file + exit 1 + fi file_cleanup $file } From dac87e295cddc8ab316cff14ab2071b5221d84fa Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 11 Nov 2022 09:23:58 +0800 Subject: [PATCH 0143/4345] PNP: fix name memory leak in pnp_alloc_dev() [ Upstream commit 110d7b0325c55ff3620073ba4201845f59e22ebf ] After commit 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array"), the name of device is allocated dynamically, move dev_set_name() after pnp_add_id() to avoid memory leak. Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array") Signed-off-by: Yang Yingliang Reviewed-by: Hanjun Guo Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/pnp/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pnp/core.c b/drivers/pnp/core.c index a50ab002e9e4..14bf75ba941d 100644 --- a/drivers/pnp/core.c +++ b/drivers/pnp/core.c @@ -160,14 +160,14 @@ struct pnp_dev *pnp_alloc_dev(struct pnp_protocol *protocol, int id, dev->dev.coherent_dma_mask = dev->dma_mask; dev->dev.release = &pnp_release_device; - dev_set_name(&dev->dev, "%02x:%02x", dev->protocol->number, dev->number); - dev_id = pnp_add_id(dev, pnpid); if (!dev_id) { kfree(dev); return NULL; } + dev_set_name(&dev->dev, "%02x:%02x", dev->protocol->number, dev->number); + return dev; } From c0539d5d474ee6fa4ebc41f927a0f98f81244f25 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Fri, 18 Nov 2022 14:31:35 +0800 Subject: [PATCH 0144/4345] perf/x86/intel/uncore: Fix reference count leak in hswep_has_limit_sbox() [ Upstream commit 1ff9dd6e7071a561f803135c1d684b13c7a7d01d ] pci_get_device() will increase the reference count for the returned 'dev'. We need to call pci_dev_put() to decrease the reference count. Since 'dev' is only used in pci_read_config_dword(), let's add pci_dev_put() right after it. Fixes: 9d480158ee86 ("perf/x86/intel/uncore: Remove uncore extra PCI dev HSWEP_PCI_PCU_3") Signed-off-by: Xiongfeng Wang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kan Liang Link: https://lore.kernel.org/r/20221118063137.121512-3-wangxiongfeng2@huawei.com Signed-off-by: Sasha Levin --- arch/x86/events/intel/uncore_snbep.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 03c8047bebb3..aa5da42ff948 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -2828,6 +2828,7 @@ static bool hswep_has_limit_sbox(unsigned int device) return false; pci_read_config_dword(dev, HSWEP_PCU_CAPID4_OFFET, &capid4); + pci_dev_put(dev); if (!hswep_get_chop(capid4)) return true; From d2afced51108813256d8072c6e464b0c9f0bb890 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Fri, 18 Nov 2022 14:31:36 +0800 Subject: [PATCH 0145/4345] perf/x86/intel/uncore: Fix reference count leak in snr_uncore_mmio_map() [ Upstream commit 8ebd16c11c346751b3944d708e6c181ed4746c39 ] pci_get_device() will increase the reference count for the returned pci_dev, so snr_uncore_get_mc_dev() will return a pci_dev with its reference count increased. We need to call pci_dev_put() to decrease the reference count. Let's add the missing pci_dev_put(). Fixes: ee49532b38dd ("perf/x86/intel/uncore: Add IMC uncore support for Snow Ridge") Signed-off-by: Xiongfeng Wang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kan Liang Link: https://lore.kernel.org/r/20221118063137.121512-4-wangxiongfeng2@huawei.com Signed-off-by: Sasha Levin --- arch/x86/events/intel/uncore_snbep.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index aa5da42ff948..2fd49cd515f5 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -4681,6 +4681,8 @@ static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box, addr += box_ctl; + pci_dev_put(pdev); + box->io_addr = ioremap(addr, type->mmio_map_size); if (!box->io_addr) { pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name); From 0afcb759f6f61192f79dbd6264cb077b088718c2 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Fri, 18 Nov 2022 14:31:37 +0800 Subject: [PATCH 0146/4345] perf/x86/intel/uncore: Fix reference count leak in __uncore_imc_init_box() [ Upstream commit 17b8d847b92d815d1638f0de154654081d66b281 ] pci_get_device() will increase the reference count for the returned pci_dev, so tgl_uncore_get_mc_dev() will return a pci_dev with its reference count increased. We need to call pci_dev_put() to decrease the reference count before exiting from __uncore_imc_init_box(). Add pci_dev_put() for both normal and error path. Fixes: fdb64822443e ("perf/x86: Add Intel Tiger Lake uncore support") Signed-off-by: Xiongfeng Wang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kan Liang Link: https://lore.kernel.org/r/20221118063137.121512-5-wangxiongfeng2@huawei.com Signed-off-by: Sasha Levin --- arch/x86/events/intel/uncore_snb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index fa9289718147..a4c20e37bec2 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -1274,6 +1274,7 @@ static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) /* MCHBAR is disabled */ if (!(mch_bar & BIT(0))) { pr_warn("perf uncore: MCHBAR is disabled. Failed to map IMC free-running counters.\n"); + pci_dev_put(pdev); return; } mch_bar &= ~BIT(0); @@ -1287,6 +1288,8 @@ static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) box->io_addr = ioremap(addr, type->mmio_map_size); if (!box->io_addr) pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name); + + pci_dev_put(pdev); } static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = { From 5c0cacdd354987f8f5348d16908716f154047890 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Thu, 17 Nov 2022 08:08:23 +0000 Subject: [PATCH 0147/4345] platform/chrome: cros_usbpd_notify: Fix error handling in cros_usbpd_notify_init() [ Upstream commit 5a2d96623670155d94aca72c320c0ac27bdc6bd2 ] The following WARNING message was given when rmmod cros_usbpd_notify: Unexpected driver unregister! WARNING: CPU: 0 PID: 253 at drivers/base/driver.c:270 driver_unregister+0x8a/0xb0 Modules linked in: cros_usbpd_notify(-) CPU: 0 PID: 253 Comm: rmmod Not tainted 6.1.0-rc3 #24 ... Call Trace: cros_usbpd_notify_exit+0x11/0x1e [cros_usbpd_notify] __x64_sys_delete_module+0x3c7/0x570 ? __ia32_sys_delete_module+0x570/0x570 ? lock_is_held_type+0xe3/0x140 ? syscall_enter_from_user_mode+0x17/0x50 ? rcu_read_lock_sched_held+0xa0/0xd0 ? syscall_enter_from_user_mode+0x1c/0x50 do_syscall_64+0x37/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f333fe9b1b7 The reason is that the cros_usbpd_notify_init() does not check the return value of platform_driver_register(), and the cros_usbpd_notify can install successfully even if platform_driver_register() failed. Fix by checking the return value of platform_driver_register() and unregister cros_usbpd_notify_plat_driver when it failed. Fixes: ec2daf6e33f9 ("platform: chrome: Add cros-usbpd-notify driver") Signed-off-by: Yuan Can Reviewed-by: Brian Norris Link: https://lore.kernel.org/r/20221117080823.77549-1-yuancan@huawei.com Signed-off-by: Prashant Malani Signed-off-by: Sasha Levin --- drivers/platform/chrome/cros_usbpd_notify.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/platform/chrome/cros_usbpd_notify.c b/drivers/platform/chrome/cros_usbpd_notify.c index 7f36142ab12a..19390147ac9d 100644 --- a/drivers/platform/chrome/cros_usbpd_notify.c +++ b/drivers/platform/chrome/cros_usbpd_notify.c @@ -284,7 +284,11 @@ static int __init cros_usbpd_notify_init(void) return ret; #ifdef CONFIG_ACPI - platform_driver_register(&cros_usbpd_notify_acpi_driver); + ret = platform_driver_register(&cros_usbpd_notify_acpi_driver); + if (ret) { + platform_driver_unregister(&cros_usbpd_notify_plat_driver); + return ret; + } #endif return 0; } From f870d5863e8e2ec0019a9a237b14dda175f93a31 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Thu, 24 Nov 2022 14:51:50 +0800 Subject: [PATCH 0148/4345] irqchip: gic-pm: Use pm_runtime_resume_and_get() in gic_probe() [ Upstream commit f9ee20c85b3a3ba0afd3672630ec4f93d339f015 ] gic_probe() calls pm_runtime_get_sync() and added fail path as rpm_put to put usage_counter. However, pm_runtime_get_sync() will increment usage_counter even it failed. Fix it by replacing it with pm_runtime_resume_and_get() to keep usage counter balanced. Fixes: 9c8edddfc992 ("irqchip/gic: Add platform driver for non-root GICs that require RPM") Signed-off-by: Shang XiaoJing Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124065150.22809-1-shangxiaojing@huawei.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-gic-pm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-gic-pm.c b/drivers/irqchip/irq-gic-pm.c index 1337ceceb59b..8be7d136c3bf 100644 --- a/drivers/irqchip/irq-gic-pm.c +++ b/drivers/irqchip/irq-gic-pm.c @@ -104,7 +104,7 @@ static int gic_probe(struct platform_device *pdev) pm_runtime_enable(dev); - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) goto rpm_disable; From 2db53c7059167b63cc790366ef1a9e286e71980b Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 28 Nov 2022 14:55:12 +0800 Subject: [PATCH 0149/4345] EDAC/i10nm: fix refcount leak in pci_get_dev_wrapper() [ Upstream commit 9c8921555907f4d723f01ed2d859b66f2d14f08e ] As the comment of pci_get_domain_bus_and_slot() says, it returns a PCI device with refcount incremented, so it doesn't need to call an extra pci_dev_get() in pci_get_dev_wrapper(), and the PCI device needs to be put in the error path. Fixes: d4dc89d069aa ("EDAC, i10nm: Add a driver for Intel 10nm server processors") Signed-off-by: Yang Yingliang Reviewed-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://lore.kernel.org/r/20221128065512.3572550-1-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/edac/i10nm_base.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c index 3a7362f968c9..43dbea6b6e30 100644 --- a/drivers/edac/i10nm_base.c +++ b/drivers/edac/i10nm_base.c @@ -53,11 +53,10 @@ static struct pci_dev *pci_get_dev_wrapper(int dom, unsigned int bus, if (unlikely(pci_enable_device(pdev) < 0)) { edac_dbg(2, "Failed to enable device %02x:%02x.%x\n", bus, dev, fun); + pci_dev_put(pdev); return NULL; } - pci_dev_get(pdev); - return pdev; } From d97e58f72875a5498bfdaea0685d67059b202f95 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 28 Oct 2022 08:13:53 -0400 Subject: [PATCH 0150/4345] nfsd: don't call nfsd_file_put from client states seqfile display [ Upstream commit e0aa651068bfd520afcd357af8ecd2de005fc83d ] We had a report of this: BUG: sleeping function called from invalid context at fs/nfsd/filecache.c:440 ...with a stack trace showing nfsd_file_put being called from nfs4_show_open. This code has always tried to call fput while holding a spinlock, but we recently changed this to use the filecache, and that started triggering the might_sleep() in nfsd_file_put. states_start takes and holds the cl_lock while iterating over the client's states, and we can't sleep with that held. Have the various nfs4_show_* functions instead hold the fi_lock instead of taking a nfsd_file reference. Fixes: 78599c42ae3c ("nfsd4: add file to display list of client's opens") Link: https://bugzilla.redhat.com/show_bug.cgi?id=2138357 Reported-by: Zhi Li Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/nfs4state.c | 51 +++++++++++++++++++++++++++++---------------- 1 file changed, 33 insertions(+), 18 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 665d0eaeb8db..9a47cc66963f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -507,15 +507,26 @@ find_any_file(struct nfs4_file *f) return ret; } -static struct nfsd_file *find_deleg_file(struct nfs4_file *f) +static struct nfsd_file *find_any_file_locked(struct nfs4_file *f) { - struct nfsd_file *ret = NULL; + lockdep_assert_held(&f->fi_lock); + + if (f->fi_fds[O_RDWR]) + return f->fi_fds[O_RDWR]; + if (f->fi_fds[O_WRONLY]) + return f->fi_fds[O_WRONLY]; + if (f->fi_fds[O_RDONLY]) + return f->fi_fds[O_RDONLY]; + return NULL; +} + +static struct nfsd_file *find_deleg_file_locked(struct nfs4_file *f) +{ + lockdep_assert_held(&f->fi_lock); - spin_lock(&f->fi_lock); if (f->fi_deleg_file) - ret = nfsd_file_get(f->fi_deleg_file); - spin_unlock(&f->fi_lock); - return ret; + return f->fi_deleg_file; + return NULL; } static atomic_long_t num_delegations; @@ -2462,9 +2473,11 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; - file = find_any_file(nf); + + spin_lock(&nf->fi_lock); + file = find_any_file_locked(nf); if (!file) - return 0; + goto out; seq_printf(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); @@ -2486,8 +2499,8 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) seq_printf(s, ", "); nfs4_show_owner(s, oo); seq_printf(s, " }\n"); - nfsd_file_put(file); - +out: + spin_unlock(&nf->fi_lock); return 0; } @@ -2501,9 +2514,10 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; - file = find_any_file(nf); + spin_lock(&nf->fi_lock); + file = find_any_file_locked(nf); if (!file) - return 0; + goto out; seq_printf(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); @@ -2523,8 +2537,8 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) seq_printf(s, ", "); nfs4_show_owner(s, oo); seq_printf(s, " }\n"); - nfsd_file_put(file); - +out: + spin_unlock(&nf->fi_lock); return 0; } @@ -2536,9 +2550,10 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) ds = delegstateid(st); nf = st->sc_file; - file = find_deleg_file(nf); + spin_lock(&nf->fi_lock); + file = find_deleg_file_locked(nf); if (!file) - return 0; + goto out; seq_printf(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); @@ -2554,8 +2569,8 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) seq_printf(s, ", "); nfs4_show_fname(s, file); seq_printf(s, " }\n"); - nfsd_file_put(file); - +out: + spin_unlock(&nf->fi_lock); return 0; } From 9346517ed2c2767159060085185d6537fbfda619 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 28 Nov 2022 23:16:12 +0800 Subject: [PATCH 0151/4345] genirq/irqdesc: Don't try to remove non-existing sysfs files [ Upstream commit 9049e1ca41983ab773d7ea244bee86d7835ec9f5 ] Fault injection tests trigger warnings like this: kernfs: can not remove 'chip_name', no directory WARNING: CPU: 0 PID: 253 at fs/kernfs/dir.c:1616 kernfs_remove_by_name_ns+0xce/0xe0 RIP: 0010:kernfs_remove_by_name_ns+0xce/0xe0 Call Trace: remove_files.isra.1+0x3f/0xb0 sysfs_remove_group+0x68/0xe0 sysfs_remove_groups+0x41/0x70 __kobject_del+0x45/0xc0 kobject_del+0x29/0x40 free_desc+0x42/0x70 irq_free_descs+0x5e/0x90 The reason is that the interrupt descriptor sysfs handling does not roll back on a failing kobject_add() during allocation. If the descriptor is freed later on, kobject_del() is invoked with a not added kobject resulting in the above warnings. A proper rollback in case of a kobject_add() failure would be the straight forward solution. But this is not possible due to the way how interrupt descriptor sysfs handling works. Interrupt descriptors are allocated before sysfs becomes available. So the sysfs files for the early allocated descriptors are added later in the boot process. At this point there can be nothing useful done about a failing kobject_add(). For consistency the interrupt descriptor allocation always treats kobject_add() failures as non-critical and just emits a warning. To solve this problem, keep track in the interrupt descriptor whether kobject_add() was successful or not and make the invocation of kobject_del() conditional on that. [ tglx: Massage changelog, comments and use a state bit. ] Fixes: ecb3f394c5db ("genirq: Expose interrupt information through sysfs") Signed-off-by: Yang Yingliang Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20221128151612.1786122-1-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- kernel/irq/internals.h | 2 ++ kernel/irq/irqdesc.c | 15 +++++++++------ 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index e58342ace11f..f1d83a8b4417 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -52,6 +52,7 @@ enum { * IRQS_PENDING - irq is pending and replayed later * IRQS_SUSPENDED - irq is suspended * IRQS_NMI - irq line is used to deliver NMIs + * IRQS_SYSFS - descriptor has been added to sysfs */ enum { IRQS_AUTODETECT = 0x00000001, @@ -64,6 +65,7 @@ enum { IRQS_SUSPENDED = 0x00000800, IRQS_TIMINGS = 0x00001000, IRQS_NMI = 0x00002000, + IRQS_SYSFS = 0x00004000, }; #include "debug.h" diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index ca36c6179aa7..9b0914a063f9 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -288,22 +288,25 @@ static void irq_sysfs_add(int irq, struct irq_desc *desc) if (irq_kobj_base) { /* * Continue even in case of failure as this is nothing - * crucial. + * crucial and failures in the late irq_sysfs_init() + * cannot be rolled back. */ if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq)) pr_warn("Failed to add kobject for irq %d\n", irq); + else + desc->istate |= IRQS_SYSFS; } } static void irq_sysfs_del(struct irq_desc *desc) { /* - * If irq_sysfs_init() has not yet been invoked (early boot), then - * irq_kobj_base is NULL and the descriptor was never added. - * kobject_del() complains about a object with no parent, so make - * it conditional. + * Only invoke kobject_del() when kobject_add() was successfully + * invoked for the descriptor. This covers both early boot, where + * sysfs is not initialized yet, and the case of a failed + * kobject_add() invocation. */ - if (irq_kobj_base) + if (desc->istate & IRQS_SYSFS) kobject_del(&desc->kobj); } From 0080461624e98ccff5bf9a43441a6862ff1ca4ed Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Wed, 16 Nov 2022 19:33:39 +0800 Subject: [PATCH 0152/4345] cpufreq: amd_freq_sensitivity: Add missing pci_dev_put() [ Upstream commit 91fda1f88c0968f1491ab150bb01690525af150a ] pci_get_device() will increase the reference count for the returned pci_dev. We need to use pci_dev_put() to decrease the reference count after using pci_get_device(). Let's add it. Fixes: 59a3b3a8db16 ("cpufreq: AMD: Ignore the check for ProcFeedback in ST/CZ") Signed-off-by: Xiongfeng Wang Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/cpufreq/amd_freq_sensitivity.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c index d0b10baf039a..151771129c7b 100644 --- a/drivers/cpufreq/amd_freq_sensitivity.c +++ b/drivers/cpufreq/amd_freq_sensitivity.c @@ -124,6 +124,8 @@ static int __init amd_freq_sensitivity_init(void) if (!pcidev) { if (!boot_cpu_has(X86_FEATURE_PROC_FEEDBACK)) return -ENODEV; + } else { + pci_dev_put(pcidev); } if (rdmsrl_safe(MSR_AMD64_FREQ_SENSITIVITY_ACTUAL, &val)) From c39aa503f47115160ffb8e4bce7a34033ccd3870 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 20 Sep 2022 02:24:16 +0900 Subject: [PATCH 0153/4345] libfs: add DEFINE_SIMPLE_ATTRIBUTE_SIGNED for signed value [ Upstream commit 2e41f274f9aa71cdcc69dc1f26a3f9304a651804 ] Patch series "fix error when writing negative value to simple attribute files". The simple attribute files do not accept a negative value since the commit 488dac0c9237 ("libfs: fix error cast of negative value in simple_attr_write()"), but some attribute files want to accept a negative value. This patch (of 3): The simple attribute files do not accept a negative value since the commit 488dac0c9237 ("libfs: fix error cast of negative value in simple_attr_write()"), so we have to use a 64-bit value to write a negative value. This adds DEFINE_SIMPLE_ATTRIBUTE_SIGNED for a signed value. Link: https://lkml.kernel.org/r/20220919172418.45257-1-akinobu.mita@gmail.com Link: https://lkml.kernel.org/r/20220919172418.45257-2-akinobu.mita@gmail.com Fixes: 488dac0c9237 ("libfs: fix error cast of negative value in simple_attr_write()") Signed-off-by: Akinobu Mita Reported-by: Zhao Gongyi Reviewed-by: David Hildenbrand Reviewed-by: Greg Kroah-Hartman Cc: Alexander Viro Cc: Jonathan Corbet Cc: Oscar Salvador Cc: Rafael J. Wysocki Cc: Shuah Khan Cc: Wei Yongjun Cc: Yicong Yang Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/libfs.c | 22 +++++++++++++++++++--- include/linux/fs.h | 12 ++++++++++-- 2 files changed, 29 insertions(+), 5 deletions(-) diff --git a/fs/libfs.c b/fs/libfs.c index 7124c2e8df2f..aa0fbd720409 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -955,8 +955,8 @@ out: EXPORT_SYMBOL_GPL(simple_attr_read); /* interpret the buffer as a number to call the set function with */ -ssize_t simple_attr_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) +static ssize_t simple_attr_write_xsigned(struct file *file, const char __user *buf, + size_t len, loff_t *ppos, bool is_signed) { struct simple_attr *attr; unsigned long long val; @@ -977,7 +977,10 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, goto out; attr->set_buf[size] = '\0'; - ret = kstrtoull(attr->set_buf, 0, &val); + if (is_signed) + ret = kstrtoll(attr->set_buf, 0, &val); + else + ret = kstrtoull(attr->set_buf, 0, &val); if (ret) goto out; ret = attr->set(attr->data, val); @@ -987,8 +990,21 @@ out: mutex_unlock(&attr->mutex); return ret; } + +ssize_t simple_attr_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return simple_attr_write_xsigned(file, buf, len, ppos, false); +} EXPORT_SYMBOL_GPL(simple_attr_write); +ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return simple_attr_write_xsigned(file, buf, len, ppos, true); +} +EXPORT_SYMBOL_GPL(simple_attr_write_signed); + /** * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation * @sb: filesystem to do the file handle conversion on diff --git a/include/linux/fs.h b/include/linux/fs.h index ebfc0b2b4969..9a477e537361 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3345,7 +3345,7 @@ void simple_transaction_set(struct file *file, size_t n); * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ -#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ +#define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ @@ -3356,10 +3356,16 @@ static const struct file_operations __fops = { \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ - .write = simple_attr_write, \ + .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } +#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ + DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) + +#define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ + DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) + static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { @@ -3374,6 +3380,8 @@ ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); +ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, + size_t len, loff_t *ppos); struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, From 869a37ad6f7827893082d0796e6191e879b6a5ef Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 20 Sep 2022 02:24:17 +0900 Subject: [PATCH 0154/4345] lib/notifier-error-inject: fix error when writing -errno to debugfs file [ Upstream commit f883c3edd2c432a2931ec8773c70a570115a50fe ] The simple attribute files do not accept a negative value since the commit 488dac0c9237 ("libfs: fix error cast of negative value in simple_attr_write()"). This restores the previous behaviour by using newly introduced DEFINE_SIMPLE_ATTRIBUTE_SIGNED instead of DEFINE_SIMPLE_ATTRIBUTE. Link: https://lkml.kernel.org/r/20220919172418.45257-3-akinobu.mita@gmail.com Fixes: 488dac0c9237 ("libfs: fix error cast of negative value in simple_attr_write()") Signed-off-by: Akinobu Mita Reported-by: Zhao Gongyi Reviewed-by: David Hildenbrand Reviewed-by: Greg Kroah-Hartman Cc: Alexander Viro Cc: Jonathan Corbet Cc: Oscar Salvador Cc: Rafael J. Wysocki Cc: Shuah Khan Cc: Wei Yongjun Cc: Yicong Yang Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- lib/notifier-error-inject.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/notifier-error-inject.c b/lib/notifier-error-inject.c index 21016b32d313..2b24ea6c9497 100644 --- a/lib/notifier-error-inject.c +++ b/lib/notifier-error-inject.c @@ -15,7 +15,7 @@ static int debugfs_errno_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(fops_errno, debugfs_errno_get, debugfs_errno_set, +DEFINE_SIMPLE_ATTRIBUTE_SIGNED(fops_errno, debugfs_errno_get, debugfs_errno_set, "%lld\n"); static struct dentry *debugfs_create_errno(const char *name, umode_t mode, From f649e18c9c1036f02d372afff036f4afb1beeaf9 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 3 Jun 2021 14:58:41 +0200 Subject: [PATCH 0155/4345] docs: fault-injection: fix non-working usage of negative values [ Upstream commit 005747526d4f3c2ec995891e95cb7625161022f9 ] Fault injection uses debugfs in a way that the provided values via sysfs are interpreted as u64. Providing negative numbers results in an error: /sys/kernel/debug/fail_function# echo -1 > times sh: write error: Invalid argument Update the docs and examples to use "printf %#x " in these cases. For "retval", reword the paragraph a little and fix a typo. Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20210603125841.27436-1-wsa+renesas@sang-engineering.com Signed-off-by: Jonathan Corbet Stable-dep-of: d472cf797c4e ("debugfs: fix error when writing negative value to atomic_t debugfs file") Signed-off-by: Sasha Levin --- .../fault-injection/fault-injection.rst | 24 +++++++++++-------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/Documentation/fault-injection/fault-injection.rst b/Documentation/fault-injection/fault-injection.rst index 31ecfe44e5b4..f47d05ed0d94 100644 --- a/Documentation/fault-injection/fault-injection.rst +++ b/Documentation/fault-injection/fault-injection.rst @@ -78,8 +78,10 @@ configuration of fault-injection capabilities. - /sys/kernel/debug/fail*/times: - specifies how many times failures may happen at most. - A value of -1 means "no limit". + specifies how many times failures may happen at most. A value of -1 + means "no limit". Note, though, that this file only accepts unsigned + values. So, if you want to specify -1, you better use 'printf' instead + of 'echo', e.g.: $ printf %#x -1 > times - /sys/kernel/debug/fail*/space: @@ -167,11 +169,13 @@ configuration of fault-injection capabilities. - ERRNO: retval must be -1 to -MAX_ERRNO (-4096). - ERR_NULL: retval must be 0 or -1 to -MAX_ERRNO (-4096). -- /sys/kernel/debug/fail_function//retval: +- /sys/kernel/debug/fail_function//retval: - specifies the "error" return value to inject to the given - function for given function. This will be created when - user specifies new injection entry. + specifies the "error" return value to inject to the given function. + This will be created when the user specifies a new injection entry. + Note that this file only accepts unsigned values. So, if you want to + use a negative errno, you better use 'printf' instead of 'echo', e.g.: + $ printf %#x -12 > retval Boot option ^^^^^^^^^^^ @@ -255,7 +259,7 @@ Application Examples echo Y > /sys/kernel/debug/$FAILTYPE/task-filter echo 10 > /sys/kernel/debug/$FAILTYPE/probability echo 100 > /sys/kernel/debug/$FAILTYPE/interval - echo -1 > /sys/kernel/debug/$FAILTYPE/times + printf %#x -1 > /sys/kernel/debug/$FAILTYPE/times echo 0 > /sys/kernel/debug/$FAILTYPE/space echo 2 > /sys/kernel/debug/$FAILTYPE/verbose echo 1 > /sys/kernel/debug/$FAILTYPE/ignore-gfp-wait @@ -309,7 +313,7 @@ Application Examples echo N > /sys/kernel/debug/$FAILTYPE/task-filter echo 10 > /sys/kernel/debug/$FAILTYPE/probability echo 100 > /sys/kernel/debug/$FAILTYPE/interval - echo -1 > /sys/kernel/debug/$FAILTYPE/times + printf %#x -1 > /sys/kernel/debug/$FAILTYPE/times echo 0 > /sys/kernel/debug/$FAILTYPE/space echo 2 > /sys/kernel/debug/$FAILTYPE/verbose echo 1 > /sys/kernel/debug/$FAILTYPE/ignore-gfp-wait @@ -336,11 +340,11 @@ Application Examples FAILTYPE=fail_function FAILFUNC=open_ctree echo $FAILFUNC > /sys/kernel/debug/$FAILTYPE/inject - echo -12 > /sys/kernel/debug/$FAILTYPE/$FAILFUNC/retval + printf %#x -12 > /sys/kernel/debug/$FAILTYPE/$FAILFUNC/retval echo N > /sys/kernel/debug/$FAILTYPE/task-filter echo 100 > /sys/kernel/debug/$FAILTYPE/probability echo 0 > /sys/kernel/debug/$FAILTYPE/interval - echo -1 > /sys/kernel/debug/$FAILTYPE/times + printf %#x -1 > /sys/kernel/debug/$FAILTYPE/times echo 0 > /sys/kernel/debug/$FAILTYPE/space echo 1 > /sys/kernel/debug/$FAILTYPE/verbose From 81d26aa9036aa0254d55ec462145183aef5d5379 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 20 Sep 2022 02:24:18 +0900 Subject: [PATCH 0156/4345] debugfs: fix error when writing negative value to atomic_t debugfs file [ Upstream commit d472cf797c4e268613dbce5ec9b95d0bcae19ecb ] The simple attribute files do not accept a negative value since the commit 488dac0c9237 ("libfs: fix error cast of negative value in simple_attr_write()"), so we have to use a 64-bit value to write a negative value for a debugfs file created by debugfs_create_atomic_t(). This restores the previous behaviour by introducing DEFINE_DEBUGFS_ATTRIBUTE_SIGNED for a signed value. Link: https://lkml.kernel.org/r/20220919172418.45257-4-akinobu.mita@gmail.com Fixes: 488dac0c9237 ("libfs: fix error cast of negative value in simple_attr_write()") Signed-off-by: Akinobu Mita Reported-by: Zhao Gongyi Reviewed-by: David Hildenbrand Reviewed-by: Greg Kroah-Hartman Cc: Alexander Viro Cc: Jonathan Corbet Cc: Oscar Salvador Cc: Rafael J. Wysocki Cc: Shuah Khan Cc: Wei Yongjun Cc: Yicong Yang Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- .../fault-injection/fault-injection.rst | 10 +++---- fs/debugfs/file.c | 28 +++++++++++++++---- include/linux/debugfs.h | 19 +++++++++++-- 3 files changed, 43 insertions(+), 14 deletions(-) diff --git a/Documentation/fault-injection/fault-injection.rst b/Documentation/fault-injection/fault-injection.rst index f47d05ed0d94..47de5006f645 100644 --- a/Documentation/fault-injection/fault-injection.rst +++ b/Documentation/fault-injection/fault-injection.rst @@ -79,9 +79,7 @@ configuration of fault-injection capabilities. - /sys/kernel/debug/fail*/times: specifies how many times failures may happen at most. A value of -1 - means "no limit". Note, though, that this file only accepts unsigned - values. So, if you want to specify -1, you better use 'printf' instead - of 'echo', e.g.: $ printf %#x -1 > times + means "no limit". - /sys/kernel/debug/fail*/space: @@ -259,7 +257,7 @@ Application Examples echo Y > /sys/kernel/debug/$FAILTYPE/task-filter echo 10 > /sys/kernel/debug/$FAILTYPE/probability echo 100 > /sys/kernel/debug/$FAILTYPE/interval - printf %#x -1 > /sys/kernel/debug/$FAILTYPE/times + echo -1 > /sys/kernel/debug/$FAILTYPE/times echo 0 > /sys/kernel/debug/$FAILTYPE/space echo 2 > /sys/kernel/debug/$FAILTYPE/verbose echo 1 > /sys/kernel/debug/$FAILTYPE/ignore-gfp-wait @@ -313,7 +311,7 @@ Application Examples echo N > /sys/kernel/debug/$FAILTYPE/task-filter echo 10 > /sys/kernel/debug/$FAILTYPE/probability echo 100 > /sys/kernel/debug/$FAILTYPE/interval - printf %#x -1 > /sys/kernel/debug/$FAILTYPE/times + echo -1 > /sys/kernel/debug/$FAILTYPE/times echo 0 > /sys/kernel/debug/$FAILTYPE/space echo 2 > /sys/kernel/debug/$FAILTYPE/verbose echo 1 > /sys/kernel/debug/$FAILTYPE/ignore-gfp-wait @@ -344,7 +342,7 @@ Application Examples echo N > /sys/kernel/debug/$FAILTYPE/task-filter echo 100 > /sys/kernel/debug/$FAILTYPE/probability echo 0 > /sys/kernel/debug/$FAILTYPE/interval - printf %#x -1 > /sys/kernel/debug/$FAILTYPE/times + echo -1 > /sys/kernel/debug/$FAILTYPE/times echo 0 > /sys/kernel/debug/$FAILTYPE/space echo 1 > /sys/kernel/debug/$FAILTYPE/verbose diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 96059af28f50..42bab9270e7d 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -378,8 +378,8 @@ ssize_t debugfs_attr_read(struct file *file, char __user *buf, } EXPORT_SYMBOL_GPL(debugfs_attr_read); -ssize_t debugfs_attr_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) +static ssize_t debugfs_attr_write_xsigned(struct file *file, const char __user *buf, + size_t len, loff_t *ppos, bool is_signed) { struct dentry *dentry = F_DENTRY(file); ssize_t ret; @@ -387,12 +387,28 @@ ssize_t debugfs_attr_write(struct file *file, const char __user *buf, ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; - ret = simple_attr_write(file, buf, len, ppos); + if (is_signed) + ret = simple_attr_write_signed(file, buf, len, ppos); + else + ret = simple_attr_write(file, buf, len, ppos); debugfs_file_put(dentry); return ret; } + +ssize_t debugfs_attr_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return debugfs_attr_write_xsigned(file, buf, len, ppos, false); +} EXPORT_SYMBOL_GPL(debugfs_attr_write); +ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return debugfs_attr_write_xsigned(file, buf, len, ppos, true); +} +EXPORT_SYMBOL_GPL(debugfs_attr_write_signed); + static struct dentry *debugfs_create_mode_unsafe(const char *name, umode_t mode, struct dentry *parent, void *value, const struct file_operations *fops, @@ -748,11 +764,11 @@ static int debugfs_atomic_t_get(void *data, u64 *val) *val = atomic_read((atomic_t *)data); return 0; } -DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t, debugfs_atomic_t_get, +DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t, debugfs_atomic_t_get, debugfs_atomic_t_set, "%lld\n"); -DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, +DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, "%lld\n"); -DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, +DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n"); /** diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 2357109a8901..9a87215b5526 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -45,7 +45,7 @@ struct debugfs_u32_array { extern struct dentry *arch_debugfs_dir; -#define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ +#define DEFINE_DEBUGFS_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ @@ -56,10 +56,16 @@ static const struct file_operations __fops = { \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = debugfs_attr_read, \ - .write = debugfs_attr_write, \ + .write = (__is_signed) ? debugfs_attr_write_signed : debugfs_attr_write, \ .llseek = no_llseek, \ } +#define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ + DEFINE_DEBUGFS_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) + +#define DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ + DEFINE_DEBUGFS_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) + typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); #if defined(CONFIG_DEBUG_FS) @@ -102,6 +108,8 @@ ssize_t debugfs_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t debugfs_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); +ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf, + size_t len, loff_t *ppos); struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *new_dir, const char *new_name); @@ -249,6 +257,13 @@ static inline ssize_t debugfs_attr_write(struct file *file, return -ENODEV; } +static inline ssize_t debugfs_attr_write_signed(struct file *file, + const char __user *buf, + size_t len, loff_t *ppos) +{ + return -ENODEV; +} + static inline struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *new_dir, char *new_name) { From e403024c832b718a3225b256991cfbadc84bdaf6 Mon Sep 17 00:00:00 2001 From: Heming Zhao via Ocfs2-devel Date: Fri, 29 Apr 2022 14:37:58 -0700 Subject: [PATCH 0157/4345] ocfs2: ocfs2_mount_volume does cleanup job before return error [ Upstream commit 0737e01de9c411e4db87dcedf4a9789d41b1c5c1 ] After this patch, when error, ocfs2_fill_super doesn't take care to release resources which are allocated in ocfs2_mount_volume. Link: https://lkml.kernel.org/r/20220424130952.2436-5-heming.zhao@suse.com Signed-off-by: Heming Zhao Reviewed-by: Joseph Qi Cc: Changwei Ge Cc: Gang He Cc: Joel Becker Cc: Jun Piao Cc: Junxiao Bi Cc: Mark Fasheh Signed-off-by: Andrew Morton Stable-dep-of: ce2fcf1516d6 ("ocfs2: fix memory leak in ocfs2_mount_volume()") Signed-off-by: Sasha Levin --- fs/ocfs2/super.c | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index c0e5f1bad499..ca0d6debae97 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1787,11 +1787,10 @@ static int ocfs2_get_sector(struct super_block *sb, static int ocfs2_mount_volume(struct super_block *sb) { int status = 0; - int unlock_super = 0; struct ocfs2_super *osb = OCFS2_SB(sb); if (ocfs2_is_hard_readonly(osb)) - goto leave; + goto out; mutex_init(&osb->obs_trim_fs_mutex); @@ -1801,44 +1800,56 @@ static int ocfs2_mount_volume(struct super_block *sb) if (status == -EBADR && ocfs2_userspace_stack(osb)) mlog(ML_ERROR, "couldn't mount because cluster name on" " disk does not match the running cluster name.\n"); - goto leave; + goto out; } status = ocfs2_super_lock(osb, 1); if (status < 0) { mlog_errno(status); - goto leave; + goto out_dlm; } - unlock_super = 1; /* This will load up the node map and add ourselves to it. */ status = ocfs2_find_slot(osb); if (status < 0) { mlog_errno(status); - goto leave; + goto out_super_lock; } /* load all node-local system inodes */ status = ocfs2_init_local_system_inodes(osb); if (status < 0) { mlog_errno(status); - goto leave; + goto out_super_lock; } status = ocfs2_check_volume(osb); if (status < 0) { mlog_errno(status); - goto leave; + goto out_system_inodes; } status = ocfs2_truncate_log_init(osb); - if (status < 0) + if (status < 0) { mlog_errno(status); + goto out_system_inodes; + } -leave: - if (unlock_super) - ocfs2_super_unlock(osb, 1); + ocfs2_super_unlock(osb, 1); + return 0; +out_system_inodes: + if (osb->local_alloc_state == OCFS2_LA_ENABLED) + ocfs2_shutdown_local_alloc(osb); + ocfs2_release_system_inodes(osb); + /* before journal shutdown, we should release slot_info */ + ocfs2_free_slot_info(osb); + ocfs2_journal_shutdown(osb); +out_super_lock: + ocfs2_super_unlock(osb, 1); +out_dlm: + ocfs2_dlm_shutdown(osb, 0); +out: return status; } From 45dabd8fe8a825e325eda57c2243af8c6549babd Mon Sep 17 00:00:00 2001 From: Heming Zhao via Ocfs2-devel Date: Fri, 29 Apr 2022 14:37:58 -0700 Subject: [PATCH 0158/4345] ocfs2: rewrite error handling of ocfs2_fill_super [ Upstream commit f1e75d128b46e3b066e7b2e7cfca10491109d44d ] Current ocfs2_fill_super() uses one goto label "read_super_error" to handle all error cases. And with previous serial patches, the error handling should fork more branches to handle different error cases. This patch rewrite the error handling of ocfs2_fill_super. Link: https://lkml.kernel.org/r/20220424130952.2436-6-heming.zhao@suse.com Signed-off-by: Heming Zhao Reviewed-by: Joseph Qi Cc: Changwei Ge Cc: Gang He Cc: Joel Becker Cc: Jun Piao Cc: Junxiao Bi Cc: Mark Fasheh Signed-off-by: Andrew Morton Stable-dep-of: ce2fcf1516d6 ("ocfs2: fix memory leak in ocfs2_mount_volume()") Signed-off-by: Sasha Levin --- fs/ocfs2/super.c | 67 +++++++++++++++++++++++------------------------- 1 file changed, 32 insertions(+), 35 deletions(-) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index ca0d6debae97..72c44f7d7bd4 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -984,28 +984,27 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) if (!ocfs2_parse_options(sb, data, &parsed_options, 0)) { status = -EINVAL; - goto read_super_error; + goto out; } /* probe for superblock */ status = ocfs2_sb_probe(sb, &bh, §or_size, &stats); if (status < 0) { mlog(ML_ERROR, "superblock probe failed!\n"); - goto read_super_error; + goto out; } status = ocfs2_initialize_super(sb, bh, sector_size, &stats); - osb = OCFS2_SB(sb); - if (status < 0) { - mlog_errno(status); - goto read_super_error; - } brelse(bh); bh = NULL; + if (status < 0) + goto out; + + osb = OCFS2_SB(sb); if (!ocfs2_check_set_options(sb, &parsed_options)) { status = -EINVAL; - goto read_super_error; + goto out_super; } osb->s_mount_opt = parsed_options.mount_opt; osb->s_atime_quantum = parsed_options.atime_quantum; @@ -1022,7 +1021,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) status = ocfs2_verify_userspace_stack(osb, &parsed_options); if (status) - goto read_super_error; + goto out_super; sb->s_magic = OCFS2_SUPER_MAGIC; @@ -1036,7 +1035,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) status = -EACCES; mlog(ML_ERROR, "Readonly device detected but readonly " "mount was not specified.\n"); - goto read_super_error; + goto out_super; } /* You should not be able to start a local heartbeat @@ -1045,7 +1044,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) status = -EROFS; mlog(ML_ERROR, "Local heartbeat specified on readonly " "device.\n"); - goto read_super_error; + goto out_super; } status = ocfs2_check_journals_nolocks(osb); @@ -1054,9 +1053,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) mlog(ML_ERROR, "Recovery required on readonly " "file system, but write access is " "unavailable.\n"); - else - mlog_errno(status); - goto read_super_error; + goto out_super; } ocfs2_set_ro_flag(osb, 1); @@ -1072,10 +1069,8 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) } status = ocfs2_verify_heartbeat(osb); - if (status < 0) { - mlog_errno(status); - goto read_super_error; - } + if (status < 0) + goto out_super; osb->osb_debug_root = debugfs_create_dir(osb->uuid_str, ocfs2_debugfs_root); @@ -1089,15 +1084,14 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) status = ocfs2_mount_volume(sb); if (status < 0) - goto read_super_error; + goto out_debugfs; if (osb->root_inode) inode = igrab(osb->root_inode); if (!inode) { status = -EIO; - mlog_errno(status); - goto read_super_error; + goto out_dismount; } osb->osb_dev_kset = kset_create_and_add(sb->s_id, NULL, @@ -1105,7 +1099,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) if (!osb->osb_dev_kset) { status = -ENOMEM; mlog(ML_ERROR, "Unable to create device kset %s.\n", sb->s_id); - goto read_super_error; + goto out_dismount; } /* Create filecheck sysfs related directories/files at @@ -1114,14 +1108,13 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) status = -ENOMEM; mlog(ML_ERROR, "Unable to create filecheck sysfs directory at " "/sys/fs/ocfs2/%s/filecheck.\n", sb->s_id); - goto read_super_error; + goto out_dismount; } root = d_make_root(inode); if (!root) { status = -ENOMEM; - mlog_errno(status); - goto read_super_error; + goto out_dismount; } sb->s_root = root; @@ -1168,17 +1161,21 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) return status; -read_super_error: - brelse(bh); +out_dismount: + atomic_set(&osb->vol_state, VOLUME_DISABLED); + wake_up(&osb->osb_mount_event); + ocfs2_dismount_volume(sb, 1); + goto out; - if (status) - mlog_errno(status); - - if (osb) { - atomic_set(&osb->vol_state, VOLUME_DISABLED); - wake_up(&osb->osb_mount_event); - ocfs2_dismount_volume(sb, 1); - } +out_debugfs: + debugfs_remove_recursive(osb->osb_debug_root); +out_super: + ocfs2_release_system_inodes(osb); + kfree(osb->recovery_map); + ocfs2_delete_osb(osb); + kfree(osb); +out: + mlog_errno(status); return status; } From 2b7e59ed2e77136e9360274f8f0fc208a003e95c Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Wed, 9 Nov 2022 15:46:27 +0800 Subject: [PATCH 0159/4345] ocfs2: fix memory leak in ocfs2_mount_volume() [ Upstream commit ce2fcf1516d674a174d9b34d1e1024d64de9fba3 ] There is a memory leak reported by kmemleak: unreferenced object 0xffff88810cc65e60 (size 32): comm "mount.ocfs2", pid 23753, jiffies 4302528942 (age 34735.105s) hex dump (first 32 bytes): 10 00 00 00 00 00 00 00 00 01 01 01 01 01 01 01 ................ 01 01 01 01 01 01 01 01 00 00 00 00 00 00 00 00 ................ backtrace: [] __kmalloc+0x4d/0x150 [] ocfs2_compute_replay_slots+0x121/0x330 [ocfs2] [] ocfs2_check_volume+0x485/0x900 [ocfs2] [] ocfs2_mount_volume.isra.0+0x1e9/0x650 [ocfs2] [] ocfs2_fill_super+0xe0b/0x1740 [ocfs2] [] mount_bdev+0x312/0x400 [] legacy_get_tree+0xed/0x1d0 [] vfs_get_tree+0x7d/0x230 [] path_mount+0xd62/0x1760 [] do_mount+0xca/0xe0 [] __x64_sys_mount+0x12c/0x1a0 [] do_syscall_64+0x35/0x80 [] entry_SYSCALL_64_after_hwframe+0x46/0xb0 This call stack is related to two problems. Firstly, the ocfs2 super uses "replay_map" to trace online/offline slots, in order to recover offline slots during recovery and mount. But when ocfs2_truncate_log_init() returns an error in ocfs2_mount_volume(), the memory of "replay_map" will not be freed in error handling path. Secondly, the memory of "replay_map" will not be freed if d_make_root() returns an error in ocfs2_fill_super(). But the memory of "replay_map" will be freed normally when completing recovery and mount in ocfs2_complete_mount_recovery(). Fix the first problem by adding error handling path to free "replay_map" when ocfs2_truncate_log_init() fails. And fix the second problem by calling ocfs2_free_replay_slots(osb) in the error handling path "out_dismount". In addition, since ocfs2_free_replay_slots() is static, it is necessary to remove its static attribute and declare it in header file. Link: https://lkml.kernel.org/r/20221109074627.2303950-1-lizetao1@huawei.com Fixes: 9140db04ef18 ("ocfs2: recover orphans in offline slots during recovery and mount") Signed-off-by: Li Zetao Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/ocfs2/journal.c | 2 +- fs/ocfs2/journal.h | 1 + fs/ocfs2/super.c | 5 ++++- 3 files changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index db52e843002a..0534800a472a 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -159,7 +159,7 @@ static void ocfs2_queue_replay_slots(struct ocfs2_super *osb, replay_map->rm_state = REPLAY_DONE; } -static void ocfs2_free_replay_slots(struct ocfs2_super *osb) +void ocfs2_free_replay_slots(struct ocfs2_super *osb) { struct ocfs2_replay_map *replay_map = osb->replay_map; diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index bfe611ed1b1d..eb7a21bac71e 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -152,6 +152,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb); void ocfs2_recovery_exit(struct ocfs2_super *osb); int ocfs2_compute_replay_slots(struct ocfs2_super *osb); +void ocfs2_free_replay_slots(struct ocfs2_super *osb); /* * Journal Control: * Initialize, Load, Shutdown, Wipe a journal. diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 72c44f7d7bd4..3e0b2e3e00ad 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1164,6 +1164,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) out_dismount: atomic_set(&osb->vol_state, VOLUME_DISABLED); wake_up(&osb->osb_mount_event); + ocfs2_free_replay_slots(osb); ocfs2_dismount_volume(sb, 1); goto out; @@ -1829,12 +1830,14 @@ static int ocfs2_mount_volume(struct super_block *sb) status = ocfs2_truncate_log_init(osb); if (status < 0) { mlog_errno(status); - goto out_system_inodes; + goto out_check_volume; } ocfs2_super_unlock(osb, 1); return 0; +out_check_volume: + ocfs2_free_replay_slots(osb); out_system_inodes: if (osb->local_alloc_state == OCFS2_LA_ENABLED) ocfs2_shutdown_local_alloc(osb); From 88fa351b20ca300693a206ccd3c4b0e0647944d8 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 14 Nov 2022 23:26:35 +0800 Subject: [PATCH 0160/4345] rapidio: fix possible name leaks when rio_add_device() fails [ Upstream commit f9574cd48679926e2a569e1957a5a1bcc8a719ac ] Patch series "rapidio: fix three possible memory leaks". This patchset fixes three name leaks in error handling. - patch #1 fixes two name leaks while rio_add_device() fails. - patch #2 fixes a name leak while rio_register_mport() fails. This patch (of 2): If rio_add_device() returns error, the name allocated by dev_set_name() need be freed. It should use put_device() to give up the reference in the error path, so that the name can be freed in kobject_cleanup(), and the 'rdev' can be freed in rio_release_dev(). Link: https://lkml.kernel.org/r/20221114152636.2939035-1-yangyingliang@huawei.com Link: https://lkml.kernel.org/r/20221114152636.2939035-2-yangyingliang@huawei.com Fixes: e8de370188d0 ("rapidio: add mport char device driver") Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array") Signed-off-by: Yang Yingliang Cc: Alexandre Bounine Cc: Matt Porter Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- drivers/rapidio/devices/rio_mport_cdev.c | 7 +++++-- drivers/rapidio/rio-scan.c | 8 ++++++-- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 94331d999d27..48cd9b7f3b89 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -1803,8 +1803,11 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv, rio_init_dbell_res(&rdev->riores[RIO_DOORBELL_RESOURCE], 0, 0xffff); err = rio_add_device(rdev); - if (err) - goto cleanup; + if (err) { + put_device(&rdev->dev); + return err; + } + rio_dev_get(rdev); return 0; diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c index 19b0c33f4a62..fdcf742b2adb 100644 --- a/drivers/rapidio/rio-scan.c +++ b/drivers/rapidio/rio-scan.c @@ -454,8 +454,12 @@ static struct rio_dev *rio_setup_device(struct rio_net *net, 0, 0xffff); ret = rio_add_device(rdev); - if (ret) - goto cleanup; + if (ret) { + if (rswitch) + kfree(rswitch->route_table); + put_device(&rdev->dev); + return NULL; + } rio_dev_get(rdev); From 97d9eb45ffa67ffa112a6659953321b8f7db0065 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 14 Nov 2022 23:26:36 +0800 Subject: [PATCH 0161/4345] rapidio: rio: fix possible name leak in rio_register_mport() [ Upstream commit e92a216d16bde65d21a3227e0fb2aa0794576525 ] If device_register() returns error, the name allocated by dev_set_name() need be freed. It should use put_device() to give up the reference in the error path, so that the name can be freed in kobject_cleanup(), and list_del() is called to delete the port from rio_mports. Link: https://lkml.kernel.org/r/20221114152636.2939035-3-yangyingliang@huawei.com Fixes: 2aaf308b95b2 ("rapidio: rework device hierarchy and introduce mport class of devices") Signed-off-by: Yang Yingliang Cc: Alexandre Bounine Cc: Matt Porter Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- drivers/rapidio/rio.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c index 606986c5ba2c..fcab174e5888 100644 --- a/drivers/rapidio/rio.c +++ b/drivers/rapidio/rio.c @@ -2267,11 +2267,16 @@ int rio_register_mport(struct rio_mport *port) atomic_set(&port->state, RIO_DEVICE_RUNNING); res = device_register(&port->dev); - if (res) + if (res) { dev_err(&port->dev, "RIO: mport%d registration failed ERR=%d\n", port->id, res); - else + mutex_lock(&rio_mport_list_lock); + list_del(&port->node); + mutex_unlock(&rio_mport_list_lock); + put_device(&port->dev); + } else { dev_dbg(&port->dev, "RIO: registered mport%d\n", port->id); + } return res; } From 0853787db28e99dc6d014761479ace7b8b4704d9 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 10 Dec 2020 20:46:48 +0100 Subject: [PATCH 0162/4345] clocksource/drivers/sh_cmt: Make sure channel clock supply is enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2a97d55333e4299f32c98cca6dc5c4db1c5855fc ] The Renesas Compare Match Timer 0 and 1 (CMT0/1) variants have a register to control the clock supply to the individual channels. Currently the driver does not touch this register, and relies on the documented initial value, which has the clock supply enabled for all channels present. However, when Linux starts on the APE6-EVM development board, only the clock supply to the first CMT1 channel is enabled. Hence the first channel (used as a clockevent) works, while the second channel (used as a clocksource) does not. Note that the default system clocksource is the Cortex-A15 architectured timer, and the user needs to manually switch to the CMT1 clocksource to trigger the broken behavior. Fix this by removing the fragile dependency on implicit reset and/or boot loader state, and by enabling the clock supply explicitly for all channels used instead. This requires postponing the clk_disable() call, else the timer's registers cannot be accessed in sh_cmt_setup_channel(). Signed-off-by: Geert Uytterhoeven Reviewed-by: Niklas Söderlund Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20201210194648.2901899-1-geert+renesas@glider.be Stable-dep-of: 3f44f7156f59 ("clocksource/drivers/sh_cmt: Access registers according to spec") Signed-off-by: Sasha Levin --- drivers/clocksource/sh_cmt.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 2acfcc966bb5..65a1e2416402 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -235,6 +235,8 @@ static const struct sh_cmt_info sh_cmt_info[] = { #define CMCNT 1 /* channel register */ #define CMCOR 2 /* channel register */ +#define CMCLKE 0x1000 /* CLK Enable Register (R-Car Gen2) */ + static inline u32 sh_cmt_read_cmstr(struct sh_cmt_channel *ch) { if (ch->iostart) @@ -849,6 +851,7 @@ static int sh_cmt_setup_channel(struct sh_cmt_channel *ch, unsigned int index, unsigned int hwidx, bool clockevent, bool clocksource, struct sh_cmt_device *cmt) { + u32 value; int ret; /* Skip unused channels. */ @@ -878,6 +881,11 @@ static int sh_cmt_setup_channel(struct sh_cmt_channel *ch, unsigned int index, ch->iostart = cmt->mapbase + ch->hwidx * 0x100; ch->ioctrl = ch->iostart + 0x10; ch->timer_bit = 0; + + /* Enable the clock supply to the channel */ + value = ioread32(cmt->mapbase + CMCLKE); + value |= BIT(hwidx); + iowrite32(value, cmt->mapbase + CMCLKE); break; } @@ -1010,12 +1018,10 @@ static int sh_cmt_setup(struct sh_cmt_device *cmt, struct platform_device *pdev) else cmt->rate = clk_get_rate(cmt->clk) / 8; - clk_disable(cmt->clk); - /* Map the memory resource(s). */ ret = sh_cmt_map_memory(cmt); if (ret < 0) - goto err_clk_unprepare; + goto err_clk_disable; /* Allocate and setup the channels. */ cmt->num_channels = hweight8(cmt->hw_channels); @@ -1043,6 +1049,8 @@ static int sh_cmt_setup(struct sh_cmt_device *cmt, struct platform_device *pdev) mask &= ~(1 << hwidx); } + clk_disable(cmt->clk); + platform_set_drvdata(pdev, cmt); return 0; @@ -1050,6 +1058,8 @@ static int sh_cmt_setup(struct sh_cmt_device *cmt, struct platform_device *pdev) err_unmap: kfree(cmt->channels); iounmap(cmt->mapbase); +err_clk_disable: + clk_disable(cmt->clk); err_clk_unprepare: clk_unprepare(cmt->clk); err_clk_put: From d8e7a44f488c1190ebadde6e038bf7940f50664a Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 30 Nov 2022 22:06:09 +0100 Subject: [PATCH 0163/4345] clocksource/drivers/sh_cmt: Access registers according to spec [ Upstream commit 3f44f7156f59cae06e9160eafb5d8b2dfd09e639 ] Documentation for most CMTs say that it takes two input clocks before changes propagate to the timer. This is especially relevant when the timer is stopped to change further settings. Implement the delays according to the spec. To avoid unnecessary delays in atomic mode, also check if the to-be-written value actually differs. CMCNT is a bit special because testing showed that it requires 3 cycles to propagate, which affects all CMTs. Also, the WRFLAG needs to be checked before writing. This fixes "cannot clear CMCNT" messages which occur often on R-Car Gen4 SoCs, but only very rarely on older SoCs for some reason. Fixes: 81b3b2711072 ("clocksource: sh_cmt: Add support for multiple channels per device") Signed-off-by: Wolfram Sang Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20221130210609.7718-1-wsa+renesas@sang-engineering.com Signed-off-by: Sasha Levin --- drivers/clocksource/sh_cmt.c | 88 ++++++++++++++++++++++-------------- 1 file changed, 55 insertions(+), 33 deletions(-) diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 65a1e2416402..66e4872ab34f 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -116,6 +117,7 @@ struct sh_cmt_device { void __iomem *mapbase; struct clk *clk; unsigned long rate; + unsigned int reg_delay; raw_spinlock_t lock; /* Protect the shared start/stop register */ @@ -247,10 +249,17 @@ static inline u32 sh_cmt_read_cmstr(struct sh_cmt_channel *ch) static inline void sh_cmt_write_cmstr(struct sh_cmt_channel *ch, u32 value) { - if (ch->iostart) - ch->cmt->info->write_control(ch->iostart, 0, value); - else - ch->cmt->info->write_control(ch->cmt->mapbase, 0, value); + u32 old_value = sh_cmt_read_cmstr(ch); + + if (value != old_value) { + if (ch->iostart) { + ch->cmt->info->write_control(ch->iostart, 0, value); + udelay(ch->cmt->reg_delay); + } else { + ch->cmt->info->write_control(ch->cmt->mapbase, 0, value); + udelay(ch->cmt->reg_delay); + } + } } static inline u32 sh_cmt_read_cmcsr(struct sh_cmt_channel *ch) @@ -260,7 +269,12 @@ static inline u32 sh_cmt_read_cmcsr(struct sh_cmt_channel *ch) static inline void sh_cmt_write_cmcsr(struct sh_cmt_channel *ch, u32 value) { - ch->cmt->info->write_control(ch->ioctrl, CMCSR, value); + u32 old_value = sh_cmt_read_cmcsr(ch); + + if (value != old_value) { + ch->cmt->info->write_control(ch->ioctrl, CMCSR, value); + udelay(ch->cmt->reg_delay); + } } static inline u32 sh_cmt_read_cmcnt(struct sh_cmt_channel *ch) @@ -268,14 +282,33 @@ static inline u32 sh_cmt_read_cmcnt(struct sh_cmt_channel *ch) return ch->cmt->info->read_count(ch->ioctrl, CMCNT); } -static inline void sh_cmt_write_cmcnt(struct sh_cmt_channel *ch, u32 value) +static inline int sh_cmt_write_cmcnt(struct sh_cmt_channel *ch, u32 value) { + /* Tests showed that we need to wait 3 clocks here */ + unsigned int cmcnt_delay = DIV_ROUND_UP(3 * ch->cmt->reg_delay, 2); + u32 reg; + + if (ch->cmt->info->model > SH_CMT_16BIT) { + int ret = read_poll_timeout_atomic(sh_cmt_read_cmcsr, reg, + !(reg & SH_CMT32_CMCSR_WRFLG), + 1, cmcnt_delay, false, ch); + if (ret < 0) + return ret; + } + ch->cmt->info->write_count(ch->ioctrl, CMCNT, value); + udelay(cmcnt_delay); + return 0; } static inline void sh_cmt_write_cmcor(struct sh_cmt_channel *ch, u32 value) { - ch->cmt->info->write_count(ch->ioctrl, CMCOR, value); + u32 old_value = ch->cmt->info->read_count(ch->ioctrl, CMCOR); + + if (value != old_value) { + ch->cmt->info->write_count(ch->ioctrl, CMCOR, value); + udelay(ch->cmt->reg_delay); + } } static u32 sh_cmt_get_counter(struct sh_cmt_channel *ch, u32 *has_wrapped) @@ -319,7 +352,7 @@ static void sh_cmt_start_stop_ch(struct sh_cmt_channel *ch, int start) static int sh_cmt_enable(struct sh_cmt_channel *ch) { - int k, ret; + int ret; pm_runtime_get_sync(&ch->cmt->pdev->dev); dev_pm_syscore_device(&ch->cmt->pdev->dev, true); @@ -347,26 +380,9 @@ static int sh_cmt_enable(struct sh_cmt_channel *ch) } sh_cmt_write_cmcor(ch, 0xffffffff); - sh_cmt_write_cmcnt(ch, 0); + ret = sh_cmt_write_cmcnt(ch, 0); - /* - * According to the sh73a0 user's manual, as CMCNT can be operated - * only by the RCLK (Pseudo 32 kHz), there's one restriction on - * modifying CMCNT register; two RCLK cycles are necessary before - * this register is either read or any modification of the value - * it holds is reflected in the LSI's actual operation. - * - * While at it, we're supposed to clear out the CMCNT as of this - * moment, so make sure it's processed properly here. This will - * take RCLKx2 at maximum. - */ - for (k = 0; k < 100; k++) { - if (!sh_cmt_read_cmcnt(ch)) - break; - udelay(1); - } - - if (sh_cmt_read_cmcnt(ch)) { + if (ret || sh_cmt_read_cmcnt(ch)) { dev_err(&ch->cmt->pdev->dev, "ch%u: cannot clear CMCNT\n", ch->index); ret = -ETIMEDOUT; @@ -976,8 +992,8 @@ MODULE_DEVICE_TABLE(of, sh_cmt_of_table); static int sh_cmt_setup(struct sh_cmt_device *cmt, struct platform_device *pdev) { - unsigned int mask; - unsigned int i; + unsigned int mask, i; + unsigned long rate; int ret; cmt->pdev = pdev; @@ -1013,10 +1029,16 @@ static int sh_cmt_setup(struct sh_cmt_device *cmt, struct platform_device *pdev) if (ret < 0) goto err_clk_unprepare; - if (cmt->info->width == 16) - cmt->rate = clk_get_rate(cmt->clk) / 512; - else - cmt->rate = clk_get_rate(cmt->clk) / 8; + rate = clk_get_rate(cmt->clk); + if (!rate) { + ret = -EINVAL; + goto err_clk_disable; + } + + /* We shall wait 2 input clks after register writes */ + if (cmt->info->model >= SH_CMT_48BIT) + cmt->reg_delay = DIV_ROUND_UP(2UL * USEC_PER_SEC, rate); + cmt->rate = rate / (cmt->info->width == 16 ? 512 : 8); /* Map the memory resource(s). */ ret = sh_cmt_map_memory(cmt); From 4750cac4df681ae7bcfa294312f340238b3eadab Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Sep 2021 14:10:50 -0300 Subject: [PATCH 0164/4345] futex: Move to kernel/futex/ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 77e52ae35463521041906c510fe580d15663bb93 ] In preparation for splitup.. Signed-off-by: Peter Zijlstra (Intel) Suggested-by: Thomas Gleixner Signed-off-by: André Almeida Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: André Almeida Link: https://lore.kernel.org/r/20210923171111.300673-2-andrealmeid@collabora.com Stable-dep-of: 90d758896787 ("futex: Resend potentially swallowed owner death notification") Signed-off-by: Sasha Levin --- MAINTAINERS | 2 +- kernel/Makefile | 2 +- kernel/futex/Makefile | 3 +++ kernel/{futex.c => futex/core.c} | 2 +- 4 files changed, 6 insertions(+), 3 deletions(-) create mode 100644 kernel/futex/Makefile rename kernel/{futex.c => futex/core.c} (99%) diff --git a/MAINTAINERS b/MAINTAINERS index 4d10e79030a9..f6c6b403a1b7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7280,7 +7280,7 @@ F: Documentation/locking/*futex* F: include/asm-generic/futex.h F: include/linux/futex.h F: include/uapi/linux/futex.h -F: kernel/futex.c +F: kernel/futex/* F: tools/perf/bench/futex* F: tools/testing/selftests/futex/ diff --git a/kernel/Makefile b/kernel/Makefile index e7905bdf6e97..82e9c843617f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -53,7 +53,7 @@ obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ -obj-$(CONFIG_FUTEX) += futex.o +obj-$(CONFIG_FUTEX) += futex/ obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o ifneq ($(CONFIG_SMP),y) diff --git a/kernel/futex/Makefile b/kernel/futex/Makefile new file mode 100644 index 000000000000..b89ba3fba343 --- /dev/null +++ b/kernel/futex/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += core.o diff --git a/kernel/futex.c b/kernel/futex/core.c similarity index 99% rename from kernel/futex.c rename to kernel/futex/core.c index 98a6e1b80bfe..26ca79c47480 100644 --- a/kernel/futex.c +++ b/kernel/futex/core.c @@ -42,7 +42,7 @@ #include -#include "locking/rtmutex_common.h" +#include "../locking/rtmutex_common.h" /* * READ this before attempting to hack on futexes! From fc89b8853aec7ee07b31ae45e8f980369a79871d Mon Sep 17 00:00:00 2001 From: Alexey Izbyshev Date: Sat, 12 Nov 2022 00:54:39 +0300 Subject: [PATCH 0165/4345] futex: Resend potentially swallowed owner death notification [ Upstream commit 90d758896787048fa3d4209309d4800f3920e66f ] Commit ca16d5bee598 ("futex: Prevent robust futex exit race") addressed two cases when tasks waiting on a robust non-PI futex remained blocked despite the futex not being owned anymore: * if the owner died after writing zero to the futex word, but before waking up a waiter * if a task waiting on the futex was woken up, but died before updating the futex word (effectively swallowing the notification without acting on it) In the second case, the task could be woken up either by the previous owner (after the futex word was reset to zero) or by the kernel (after the OWNER_DIED bit was set and the TID part of the futex word was reset to zero) if the previous owner died without the resetting the futex. Because the referenced commit wakes up a potential waiter only if the whole futex word is zero, the latter subcase remains unaddressed. Fix this by looking only at the TID part of the futex when deciding whether a wake up is needed. Fixes: ca16d5bee598 ("futex: Prevent robust futex exit race") Signed-off-by: Alexey Izbyshev Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20221111215439.248185-1-izbyshev@ispras.ru Signed-off-by: Sasha Levin --- kernel/futex/core.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 26ca79c47480..8dd0bc50ac36 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -3405,6 +3405,7 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { u32 uval, nval, mval; + pid_t owner; int err; /* Futex address must be 32bit aligned */ @@ -3426,6 +3427,10 @@ retry: * 2. A woken up waiter is killed before it can acquire the * futex in user space. * + * In the second case, the wake up notification could be generated + * by the unlock path in user space after setting the futex value + * to zero or by the kernel after setting the OWNER_DIED bit below. + * * In both cases the TID validation below prevents a wakeup of * potential waiters which can cause these waiters to block * forever. @@ -3434,24 +3439,27 @@ retry: * * 1) task->robust_list->list_op_pending != NULL * @pending_op == true - * 2) User space futex value == 0 + * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false * * If these conditions are met, it is safe to attempt waking up a * potential waiter without touching the user space futex value and - * trying to set the OWNER_DIED bit. The user space futex value is - * uncontended and the rest of the user space mutex state is - * consistent, so a woken waiter will just take over the - * uncontended futex. Setting the OWNER_DIED bit would create - * inconsistent state and malfunction of the user space owner died - * handling. + * trying to set the OWNER_DIED bit. If the futex value is zero, + * the rest of the user space mutex state is consistent, so a woken + * waiter will just take over the uncontended futex. Setting the + * OWNER_DIED bit would create inconsistent state and malfunction + * of the user space owner died handling. Otherwise, the OWNER_DIED + * bit is already set, and the woken waiter is expected to deal with + * this. */ - if (pending_op && !pi && !uval) { + owner = uval & FUTEX_TID_MASK; + + if (pending_op && !pi && !owner) { futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); return 0; } - if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) + if (owner != task_pid_vnr(curr)) return 0; /* From 270700e7df960fa227c2106718578302bab8ce44 Mon Sep 17 00:00:00 2001 From: Phil Auld Date: Thu, 17 Nov 2022 11:23:28 -0500 Subject: [PATCH 0166/4345] cpu/hotplug: Make target_store() a nop when target == state [ Upstream commit 64ea6e44f85b9b75925ebe1ba0e6e8430cc4e06f ] Writing the current state back in hotplug/target calls cpu_down() which will set cpu dying even when it isn't and then nothing will ever clear it. A stress test that reads values and writes them back for all cpu device files in sysfs will trigger the BUG() in select_fallback_rq once all cpus are marked as dying. kernel/cpu.c::target_store() ... if (st->state < target) ret = cpu_up(dev->id, target); else ret = cpu_down(dev->id, target); cpu_down() -> cpu_set_state() bool bringup = st->state < target; ... if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); Fix this by letting state==target fall through in the target_store() conditional. Also make sure st->target == target in that case. Fixes: 757c989b9994 ("cpu/hotplug: Make target state writeable") Signed-off-by: Phil Auld Signed-off-by: Thomas Gleixner Reviewed-by: Valentin Schneider Link: https://lore.kernel.org/r/20221117162329.3164999-2-pauld@redhat.com Signed-off-by: Sasha Levin --- kernel/cpu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index 3c9ee966c56a..008b50da2224 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2231,8 +2231,10 @@ static ssize_t write_cpuhp_target(struct device *dev, if (st->state < target) ret = cpu_up(dev->id, target); - else + else if (st->state > target) ret = cpu_down(dev->id, target); + else if (WARN_ON(st->target != target)) + st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; From 7bc9c5ad522b98d9c8744bb1a5651278b6cd02c2 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Sat, 29 Oct 2022 19:44:27 +0800 Subject: [PATCH 0167/4345] clocksource/drivers/timer-ti-dm: Fix missing clk_disable_unprepare in dmtimer_systimer_init_clock() [ Upstream commit 180d35a7c05d520314a590c99ad8643d0213f28b ] If clk_get_rate() fails which is called after clk_prepare_enable(), clk_disable_unprepare() need be called in error path to disable the clock in dmtimer_systimer_init_clock(). Fixes: 52762fbd1c47 ("clocksource/drivers/timer-ti-dm: Add clockevent and clocksource support") Signed-off-by: Yang Yingliang Reviewed-by: Tony Lindgren Link: https://lore.kernel.org/r/20221029114427.946520-1-yangyingliang@huawei.com Signed-off-by: Daniel Lezcano Signed-off-by: Sasha Levin --- drivers/clocksource/timer-ti-dm-systimer.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index 2737407ff069..632523c1232f 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -345,8 +345,10 @@ static int __init dmtimer_systimer_init_clock(struct dmtimer_systimer *t, return error; r = clk_get_rate(clock); - if (!r) + if (!r) { + clk_disable_unprepare(clock); return -ENODEV; + } if (is_ick) t->ick = clock; From 02617006b5a46f2ea55ac61f5693c7afd7bf9276 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 1 Dec 2022 16:05:14 +0800 Subject: [PATCH 0168/4345] ACPICA: Fix use-after-free in acpi_ut_copy_ipackage_to_ipackage() [ Upstream commit 470188b09e92d83c5a997f25f0e8fb8cd2bc3469 ] There is an use-after-free reported by KASAN: BUG: KASAN: use-after-free in acpi_ut_remove_reference+0x3b/0x82 Read of size 1 at addr ffff888112afc460 by task modprobe/2111 CPU: 0 PID: 2111 Comm: modprobe Not tainted 6.1.0-rc7-dirty Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), Call Trace: kasan_report+0xae/0xe0 acpi_ut_remove_reference+0x3b/0x82 acpi_ut_copy_iobject_to_iobject+0x3be/0x3d5 acpi_ds_store_object_to_local+0x15d/0x3a0 acpi_ex_store+0x78d/0x7fd acpi_ex_opcode_1A_1T_1R+0xbe4/0xf9b acpi_ps_parse_aml+0x217/0x8d5 ... The root cause of the problem is that the acpi_operand_object is freed when acpi_ut_walk_package_tree() fails in acpi_ut_copy_ipackage_to_ipackage(), lead to repeated release in acpi_ut_copy_iobject_to_iobject(). The problem was introduced by "8aa5e56eeb61" commit, this commit is to fix memory leak in acpi_ut_copy_iobject_to_iobject(), repeatedly adding remove operation, lead to "acpi_operand_object" used after free. Fix it by removing acpi_ut_remove_reference() in acpi_ut_copy_ipackage_to_ipackage(). acpi_ut_copy_ipackage_to_ipackage() is called to copy an internal package object into another internal package object, when it fails, the memory of acpi_operand_object should be freed by the caller. Fixes: 8aa5e56eeb61 ("ACPICA: Utilities: Fix memory leak in acpi_ut_copy_iobject_to_iobject") Signed-off-by: Li Zetao Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/acpica/utcopy.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c index 41bdd0278dd8..9a7cc679e544 100644 --- a/drivers/acpi/acpica/utcopy.c +++ b/drivers/acpi/acpica/utcopy.c @@ -916,13 +916,6 @@ acpi_ut_copy_ipackage_to_ipackage(union acpi_operand_object *source_obj, status = acpi_ut_walk_package_tree(source_obj, dest_obj, acpi_ut_copy_ielement_to_ielement, walk_state); - if (ACPI_FAILURE(status)) { - - /* On failure, delete the destination package object */ - - acpi_ut_remove_reference(dest_obj); - } - return_ACPI_STATUS(status); } From 95dbcb7e1c34502dc9f5333abb74553e4086505a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 4 Dec 2022 18:39:33 +0100 Subject: [PATCH 0169/4345] uprobes/x86: Allow to probe a NOP instruction with 0x66 prefix [ Upstream commit cefa72129e45313655d53a065b8055aaeb01a0c9 ] Intel ICC -hotpatch inserts 2-byte "0x66 0x90" NOP at the start of each function to reserve extra space for hot-patching, and currently it is not possible to probe these functions because branch_setup_xol_ops() wrongly rejects NOP with REP prefix as it treats them like word-sized branch instructions. Fixes: 250bbd12c2fe ("uprobes/x86: Refuse to attach uprobe to "word-sized" branch insns") Reported-by: Seiji Nishikawa Suggested-by: Denys Vlasenko Signed-off-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Acked-by: Masami Hiramatsu (Google) Link: https://lore.kernel.org/r/20221204173933.GA31544@redhat.com Signed-off-by: Sasha Levin --- arch/x86/kernel/uprobes.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 138bdb1fd136..9f948b2d26f6 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -722,8 +722,9 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) switch (opc1) { case 0xeb: /* jmp 8 */ case 0xe9: /* jmp 32 */ - case 0x90: /* prefix* + nop; same as jmp with .offs = 0 */ break; + case 0x90: /* prefix* + nop; same as jmp with .offs = 0 */ + goto setup; case 0xe8: /* call relative */ branch_clear_offset(auprobe, insn); @@ -753,6 +754,7 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) return -ENOTSUPP; } +setup: auprobe->branch.opc1 = opc1; auprobe->branch.ilen = insn->length; auprobe->branch.offs = insn->immediate.value; From fc134c355b5299495b14a54dd9bb7af8a646cb7c Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Wed, 23 Nov 2022 23:58:57 +0800 Subject: [PATCH 0170/4345] x86/xen: Fix memory leak in xen_smp_intr_init{_pv}() [ Upstream commit 69143f60868b3939ddc89289b29db593b647295e ] These local variables @{resched|pmu|callfunc...}_name saves the new string allocated by kasprintf(), and when bind_{v}ipi_to_irqhandler() fails, it goes to the @fail tag, and calls xen_smp_intr_free{_pv}() to free resource, however the new string is not saved, which cause a memory leak issue. fix it. Fixes: 9702785a747a ("i386: move xen") Signed-off-by: Xiu Jianfeng Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20221123155858.11382-2-xiujianfeng@huawei.com Signed-off-by: Juergen Gross Signed-off-by: Sasha Levin --- arch/x86/xen/smp.c | 24 ++++++++++++------------ arch/x86/xen/smp_pv.c | 12 ++++++------ 2 files changed, 18 insertions(+), 18 deletions(-) diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index c1b2f764b29a..cdec892b28e2 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -32,30 +32,30 @@ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) void xen_smp_intr_free(unsigned int cpu) { + kfree(per_cpu(xen_resched_irq, cpu).name); + per_cpu(xen_resched_irq, cpu).name = NULL; if (per_cpu(xen_resched_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu).irq, NULL); per_cpu(xen_resched_irq, cpu).irq = -1; - kfree(per_cpu(xen_resched_irq, cpu).name); - per_cpu(xen_resched_irq, cpu).name = NULL; } + kfree(per_cpu(xen_callfunc_irq, cpu).name); + per_cpu(xen_callfunc_irq, cpu).name = NULL; if (per_cpu(xen_callfunc_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu).irq, NULL); per_cpu(xen_callfunc_irq, cpu).irq = -1; - kfree(per_cpu(xen_callfunc_irq, cpu).name); - per_cpu(xen_callfunc_irq, cpu).name = NULL; } + kfree(per_cpu(xen_debug_irq, cpu).name); + per_cpu(xen_debug_irq, cpu).name = NULL; if (per_cpu(xen_debug_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu).irq, NULL); per_cpu(xen_debug_irq, cpu).irq = -1; - kfree(per_cpu(xen_debug_irq, cpu).name); - per_cpu(xen_debug_irq, cpu).name = NULL; } + kfree(per_cpu(xen_callfuncsingle_irq, cpu).name); + per_cpu(xen_callfuncsingle_irq, cpu).name = NULL; if (per_cpu(xen_callfuncsingle_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu).irq, NULL); per_cpu(xen_callfuncsingle_irq, cpu).irq = -1; - kfree(per_cpu(xen_callfuncsingle_irq, cpu).name); - per_cpu(xen_callfuncsingle_irq, cpu).name = NULL; } } @@ -65,6 +65,7 @@ int xen_smp_intr_init(unsigned int cpu) char *resched_name, *callfunc_name, *debug_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); + per_cpu(xen_resched_irq, cpu).name = resched_name; rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu, xen_reschedule_interrupt, @@ -74,9 +75,9 @@ int xen_smp_intr_init(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_resched_irq, cpu).irq = rc; - per_cpu(xen_resched_irq, cpu).name = resched_name; callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu); + per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, cpu, xen_call_function_interrupt, @@ -86,10 +87,10 @@ int xen_smp_intr_init(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_callfunc_irq, cpu).irq = rc; - per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; if (!xen_fifo_events) { debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); + per_cpu(xen_debug_irq, cpu).name = debug_name; rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, IRQF_PERCPU | IRQF_NOBALANCING, @@ -97,10 +98,10 @@ int xen_smp_intr_init(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_debug_irq, cpu).irq = rc; - per_cpu(xen_debug_irq, cpu).name = debug_name; } callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); + per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, cpu, xen_call_function_single_interrupt, @@ -110,7 +111,6 @@ int xen_smp_intr_init(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_callfuncsingle_irq, cpu).irq = rc; - per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; return 0; diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 35b6d15d874d..64873937cd1d 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -98,18 +98,18 @@ asmlinkage __visible void cpu_bringup_and_idle(void) void xen_smp_intr_free_pv(unsigned int cpu) { + kfree(per_cpu(xen_irq_work, cpu).name); + per_cpu(xen_irq_work, cpu).name = NULL; if (per_cpu(xen_irq_work, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL); per_cpu(xen_irq_work, cpu).irq = -1; - kfree(per_cpu(xen_irq_work, cpu).name); - per_cpu(xen_irq_work, cpu).name = NULL; } + kfree(per_cpu(xen_pmu_irq, cpu).name); + per_cpu(xen_pmu_irq, cpu).name = NULL; if (per_cpu(xen_pmu_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL); per_cpu(xen_pmu_irq, cpu).irq = -1; - kfree(per_cpu(xen_pmu_irq, cpu).name); - per_cpu(xen_pmu_irq, cpu).name = NULL; } } @@ -119,6 +119,7 @@ int xen_smp_intr_init_pv(unsigned int cpu) char *callfunc_name, *pmu_name; callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu); + per_cpu(xen_irq_work, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR, cpu, xen_irq_work_interrupt, @@ -128,10 +129,10 @@ int xen_smp_intr_init_pv(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_irq_work, cpu).irq = rc; - per_cpu(xen_irq_work, cpu).name = callfunc_name; if (is_xen_pmu) { pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu); + per_cpu(xen_pmu_irq, cpu).name = pmu_name; rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu, xen_pmu_irq_handler, IRQF_PERCPU|IRQF_NOBALANCING, @@ -139,7 +140,6 @@ int xen_smp_intr_init_pv(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_pmu_irq, cpu).irq = rc; - per_cpu(xen_pmu_irq, cpu).name = pmu_name; } return 0; From 70e7f308d7a8e915c7fbc0f1d959968eab8000cd Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Wed, 23 Nov 2022 23:58:58 +0800 Subject: [PATCH 0171/4345] x86/xen: Fix memory leak in xen_init_lock_cpu() [ Upstream commit ca84ce153d887b1dc8b118029976cc9faf2a9b40 ] In xen_init_lock_cpu(), the @name has allocated new string by kasprintf(), if bind_ipi_to_irqhandler() fails, it should be freed, otherwise may lead to a memory leak issue, fix it. Fixes: 2d9e1e2f58b5 ("xen: implement Xen-specific spinlocks") Signed-off-by: Xiu Jianfeng Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20221123155858.11382-3-xiujianfeng@huawei.com Signed-off-by: Juergen Gross Signed-off-by: Sasha Levin --- arch/x86/xen/spinlock.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 043c73dfd2c9..5c6fc16e4b92 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -75,6 +75,7 @@ void xen_init_lock_cpu(int cpu) cpu, per_cpu(lock_kicker_irq, cpu)); name = kasprintf(GFP_KERNEL, "spinlock%d", cpu); + per_cpu(irq_name, cpu) = name; irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR, cpu, dummy_handler, @@ -85,7 +86,6 @@ void xen_init_lock_cpu(int cpu) if (irq >= 0) { disable_irq(irq); /* make sure it's never delivered */ per_cpu(lock_kicker_irq, cpu) = irq; - per_cpu(irq_name, cpu) = name; } printk("cpu %d spinlock event irq %d\n", cpu, irq); @@ -98,6 +98,8 @@ void xen_uninit_lock_cpu(int cpu) if (!xen_pvspin) return; + kfree(per_cpu(irq_name, cpu)); + per_cpu(irq_name, cpu) = NULL; /* * When booting the kernel with 'mitigations=auto,nosmt', the secondary * CPUs are not activated, and lock_kicker_irq is not initialized. @@ -108,8 +110,6 @@ void xen_uninit_lock_cpu(int cpu) unbind_from_irqhandler(irq, NULL); per_cpu(lock_kicker_irq, cpu) = -1; - kfree(per_cpu(irq_name, cpu)); - per_cpu(irq_name, cpu) = NULL; } PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen); From 46026bb057c35f5bb111bf95e00cd8366d2e34d4 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Fri, 25 Nov 2022 21:07:45 -0800 Subject: [PATCH 0172/4345] xen/privcmd: Fix a possible warning in privcmd_ioctl_mmap_resource() [ Upstream commit 8b997b2bb2c53b76a6db6c195930e9ab8e4b0c79 ] As 'kdata.num' is user-controlled data, if user tries to allocate memory larger than(>=) MAX_ORDER, then kcalloc() will fail, it creates a stack trace and messes up dmesg with a warning. Call trace: -> privcmd_ioctl --> privcmd_ioctl_mmap_resource Add __GFP_NOWARN in order to avoid too large allocation warning. This is detected by static analysis using smatch. Fixes: 3ad0876554ca ("xen/privcmd: add IOCTL_PRIVCMD_MMAP_RESOURCE") Signed-off-by: Harshit Mogalapalli Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20221126050745.778967-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Juergen Gross Signed-off-by: Sasha Levin --- drivers/xen/privcmd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index cd5f2f09468e..28537a1a0e0b 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -760,7 +760,7 @@ static long privcmd_ioctl_mmap_resource(struct file *file, goto out; } - pfns = kcalloc(kdata.num, sizeof(*pfns), GFP_KERNEL); + pfns = kcalloc(kdata.num, sizeof(*pfns), GFP_KERNEL | __GFP_NOWARN); if (!pfns) { rc = -ENOMEM; goto out; From 2cbbd78e08bc8645a2a39eba17f0bcbbf467a6f4 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 8 Jun 2021 11:02:48 +0200 Subject: [PATCH 0173/4345] PM: runtime: Improve path in rpm_idle() when no callback [ Upstream commit 5a2bd1b1c64e1ac5627db3767ac465f18606315c ] When pm_runtime_no_callbacks() has been called for a struct device to set the dev->power.no_callbacks flag for it, it enables rpm_idle() to take a slightly quicker path by assuming that a ->runtime_idle() callback would have returned 0 to indicate success. A device that does not have the dev->power.no_callbacks flag set for it, may still be missing a corresponding ->runtime_idle() callback, in which case the slower path in rpm_idle() is taken. Let's improve the behaviour for this case, by aligning code to the quicker path. Signed-off-by: Ulf Hansson Acked-by: Alan Stern Signed-off-by: Rafael J. Wysocki Stable-dep-of: bc80c2e438dc ("PM: runtime: Do not call __rpm_callback() from rpm_idle()") Signed-off-by: Sasha Levin --- drivers/base/power/runtime.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 835a39e84c1d..532d910fe1cf 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -464,7 +464,10 @@ static int rpm_idle(struct device *dev, int rpmflags) /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; - if (dev->power.no_callbacks) + callback = RPM_GET_CALLBACK(dev, runtime_idle); + + /* If no callback assume success. */ + if (!callback || dev->power.no_callbacks) goto out; /* Carry out an asynchronous or a synchronous idle notification. */ @@ -480,10 +483,7 @@ static int rpm_idle(struct device *dev, int rpmflags) dev->power.idle_notification = true; - callback = RPM_GET_CALLBACK(dev, runtime_idle); - - if (callback) - retval = __rpm_callback(callback, dev); + retval = __rpm_callback(callback, dev); dev->power.idle_notification = false; wake_up_all(&dev->power.wait_queue); From f983afc4326c91062abdab6d95312b98a9de0654 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 2 Dec 2022 15:30:28 +0100 Subject: [PATCH 0174/4345] PM: runtime: Do not call __rpm_callback() from rpm_idle() [ Upstream commit bc80c2e438dcbfcf748452ec0f7ad5b79ff3ad88 ] Calling __rpm_callback() from rpm_idle() after adding device links support to the former is a clear mistake. Not only it causes rpm_idle() to carry out unnecessary actions, but it is also against the assumption regarding the stability of PM-runtime status across __rpm_callback() invocations, because rpm_suspend() and rpm_resume() may run in parallel with __rpm_callback() when it is called by rpm_idle() and the device's PM-runtime status can be updated by any of them. Fixes: 21d5c57b3726 ("PM / runtime: Use device links") Link: https://lore.kernel.org/linux-pm/36aed941-a73e-d937-2721-4f0decd61ce0@quicinc.com Signed-off-by: Rafael J. Wysocki Reviewed-by: Adrian Hunter Signed-off-by: Sasha Levin --- drivers/base/power/runtime.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 532d910fe1cf..360094692d29 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -483,7 +483,17 @@ static int rpm_idle(struct device *dev, int rpmflags) dev->power.idle_notification = true; - retval = __rpm_callback(callback, dev); + if (dev->power.irq_safe) + spin_unlock(&dev->power.lock); + else + spin_unlock_irq(&dev->power.lock); + + retval = callback(dev); + + if (dev->power.irq_safe) + spin_lock(&dev->power.lock); + else + spin_lock_irq(&dev->power.lock); dev->power.idle_notification = false; wake_up_all(&dev->power.wait_queue); From 17cd8c46cbec4e6ad593fb9159928b8e7608c11a Mon Sep 17 00:00:00 2001 From: Yu Liao Date: Tue, 29 Nov 2022 09:11:01 +0800 Subject: [PATCH 0175/4345] platform/x86: mxm-wmi: fix memleak in mxm_wmi_call_mx[ds|mx]() [ Upstream commit 727cc0147f5066e359aca65cc6cc5e6d64cc15d8 ] The ACPI buffer memory (out.pointer) returned by wmi_evaluate_method() is not freed after the call, so it leads to memory leak. The method results in ACPI buffer is not used, so just pass NULL to wmi_evaluate_method() which fixes the memory leak. Fixes: 99b38b4acc0d ("platform/x86: add MXM WMI driver.") Signed-off-by: Yu Liao Link: https://lore.kernel.org/r/20221129011101.2042315-1-liaoyu15@huawei.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/mxm-wmi.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/platform/x86/mxm-wmi.c b/drivers/platform/x86/mxm-wmi.c index 9a19fbd2f734..9a457956025a 100644 --- a/drivers/platform/x86/mxm-wmi.c +++ b/drivers/platform/x86/mxm-wmi.c @@ -35,13 +35,11 @@ int mxm_wmi_call_mxds(int adapter) .xarg = 1, }; struct acpi_buffer input = { (acpi_size)sizeof(args), &args }; - struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; acpi_status status; printk("calling mux switch %d\n", adapter); - status = wmi_evaluate_method(MXM_WMMX_GUID, 0x0, adapter, &input, - &output); + status = wmi_evaluate_method(MXM_WMMX_GUID, 0x0, adapter, &input, NULL); if (ACPI_FAILURE(status)) return status; @@ -60,13 +58,11 @@ int mxm_wmi_call_mxmx(int adapter) .xarg = 1, }; struct acpi_buffer input = { (acpi_size)sizeof(args), &args }; - struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; acpi_status status; printk("calling mux switch %d\n", adapter); - status = wmi_evaluate_method(MXM_WMMX_GUID, 0x0, adapter, &input, - &output); + status = wmi_evaluate_method(MXM_WMMX_GUID, 0x0, adapter, &input, NULL); if (ACPI_FAILURE(status)) return status; From d4c38ee665a228663af0926c380670528d08aa63 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 23:19:16 +0800 Subject: [PATCH 0176/4345] platform/x86: intel_scu_ipc: fix possible name leak in __intel_scu_ipc_register() [ Upstream commit 0b3d0cb7c0bed2fd6454f77ed75e7a662c6efd12 ] In some error paths before device_register(), the names allocated by dev_set_name() are not freed. Move dev_set_name() front to device_register(), so the name can be freed while calling put_device(). Fixes: 54b34aa0a729 ("platform/x86: intel_scu_ipc: Split out SCU IPC functionality from the SCU driver") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221208151916.2404977-1-yangyingliang@huawei.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/intel_scu_ipc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index 69d706039cb2..bdeb888c0fea 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -583,7 +583,6 @@ __intel_scu_ipc_register(struct device *parent, scu->dev.parent = parent; scu->dev.class = &intel_scu_ipc_class; scu->dev.release = intel_scu_ipc_release; - dev_set_name(&scu->dev, "intel_scu_ipc"); if (!request_mem_region(scu_data->mem.start, resource_size(&scu_data->mem), "intel_scu_ipc")) { @@ -612,6 +611,7 @@ __intel_scu_ipc_register(struct device *parent, * After this point intel_scu_ipc_release() takes care of * releasing the SCU IPC resources once refcount drops to zero. */ + dev_set_name(&scu->dev, "intel_scu_ipc"); err = device_register(&scu->dev); if (err) { put_device(&scu->dev); From 7b88747d6d9815f9b92d48a5c68e88a741bfe806 Mon Sep 17 00:00:00 2001 From: Anastasia Belova Date: Fri, 9 Dec 2022 13:05:50 +0300 Subject: [PATCH 0177/4345] MIPS: BCM63xx: Add check for NULL for clk in clk_enable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ee9ef11bd2a59c2fefaa0959e5efcdf040d7c654 ] Check clk for NULL before calling clk_enable_unlocked where clk is dereferenced. There is such check in other implementations of clk_enable. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: e7300d04bd08 ("MIPS: BCM63xx: Add support for the Broadcom BCM63xx family of SOCs.") Signed-off-by: Anastasia Belova Reviewed-by: Philippe Mathieu-Daudé Acked-by: Florian Fainelli Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/bcm63xx/clk.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/bcm63xx/clk.c b/arch/mips/bcm63xx/clk.c index dcfa0ea912fe..f183c45503ce 100644 --- a/arch/mips/bcm63xx/clk.c +++ b/arch/mips/bcm63xx/clk.c @@ -361,6 +361,8 @@ static struct clk clk_periph = { */ int clk_enable(struct clk *clk) { + if (!clk) + return 0; mutex_lock(&clocks_mutex); clk_enable_unlocked(clk); mutex_unlock(&clocks_mutex); From 6f8ef1de8c655c5622f7d239d99a8a081a0f4f0b Mon Sep 17 00:00:00 2001 From: Ladislav Michl Date: Thu, 8 Dec 2022 12:25:57 +0100 Subject: [PATCH 0178/4345] MIPS: OCTEON: warn only once if deprecated link status is being used MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4c587a982603d7e7e751b4925809a1512099a690 ] Avoid flooding kernel log with warnings. Fixes: 2c0756d306c2 ("MIPS: OCTEON: warn if deprecated link status is being used") Signed-off-by: Ladislav Michl Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/cavium-octeon/executive/cvmx-helper-board.c | 2 +- arch/mips/cavium-octeon/executive/cvmx-helper.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c index abd11b7af22f..9b791ccf874f 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c @@ -211,7 +211,7 @@ union cvmx_helper_link_info __cvmx_helper_board_link_get(int ipd_port) { union cvmx_helper_link_info result; - WARN(!octeon_is_simulation(), + WARN_ONCE(!octeon_is_simulation(), "Using deprecated link status - please update your DT"); /* Unless we fix it later, all links are defaulted to down */ diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c index 6044ff471002..a18ad2daf005 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c @@ -1100,7 +1100,7 @@ union cvmx_helper_link_info cvmx_helper_link_get(int ipd_port) if (index == 0) result = __cvmx_helper_rgmii_link_get(ipd_port); else { - WARN(1, "Using deprecated link status - please update your DT"); + WARN_ONCE(1, "Using deprecated link status - please update your DT"); result.s.full_duplex = 1; result.s.link_up = 1; result.s.speed = 1000; From ad4842634d6819994c567073f9fb43bd5c9b1ee9 Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Fri, 9 Dec 2022 18:04:48 +0800 Subject: [PATCH 0179/4345] fs: sysv: Fix sysv_nblocks() returns wrong value [ Upstream commit e0c49bd2b4d3cd1751491eb2d940bce968ac65e9 ] sysv_nblocks() returns 'blocks' rather than 'res', which only counting the number of triple-indirect blocks and causing sysv_getattr() gets a wrong result. [AV: this is actually a sysv counterpart of minixfs fix - 0fcd426de9d0 "[PATCH] minix block usage counting fix" in historical tree; mea culpa, should've thought to check fs/sysv back then...] Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Chen Zhongjin Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- fs/sysv/itree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index bcb67b0cabe7..31f66053e239 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -438,7 +438,7 @@ static unsigned sysv_nblocks(struct super_block *s, loff_t size) res += blocks; direct = 1; } - return blocks; + return res; } int sysv_getattr(const struct path *path, struct kstat *stat, From 5ee850645e42f541ce1ea8130c2b27cc495f965c Mon Sep 17 00:00:00 2001 From: Wang Weiyang Date: Wed, 23 Nov 2022 17:51:47 +0800 Subject: [PATCH 0180/4345] rapidio: fix possible UAF when kfifo_alloc() fails [ Upstream commit 02d7d89f816951e0862147d751b1150d67aaebdd ] If kfifo_alloc() fails in mport_cdev_open(), goto err_fifo and just free priv. But priv is still in the chdev->file_list, then list traversal may cause UAF. This fixes the following smatch warning: drivers/rapidio/devices/rio_mport_cdev.c:1930 mport_cdev_open() warn: '&priv->list' not removed from list Link: https://lkml.kernel.org/r/20221123095147.52408-1-wangweiyang2@huawei.com Fixes: e8de370188d0 ("rapidio: add mport char device driver") Signed-off-by: Wang Weiyang Cc: Alexandre Bounine Cc: Dan Carpenter Cc: Jakob Koschel Cc: John Hubbard Cc: Matt Porter Cc: Yang Yingliang Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- drivers/rapidio/devices/rio_mport_cdev.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 48cd9b7f3b89..b8c09eaa23b5 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -1903,10 +1903,6 @@ static int mport_cdev_open(struct inode *inode, struct file *filp) priv->md = chdev; - mutex_lock(&chdev->file_mutex); - list_add_tail(&priv->list, &chdev->file_list); - mutex_unlock(&chdev->file_mutex); - INIT_LIST_HEAD(&priv->db_filters); INIT_LIST_HEAD(&priv->pw_filters); spin_lock_init(&priv->fifo_lock); @@ -1925,6 +1921,9 @@ static int mport_cdev_open(struct inode *inode, struct file *filp) spin_lock_init(&priv->req_lock); mutex_init(&priv->dma_lock); #endif + mutex_lock(&chdev->file_mutex); + list_add_tail(&priv->list, &chdev->file_list); + mutex_unlock(&chdev->file_mutex); filp->private_data = priv; goto out; From bbaa9ca063298dadc37715103f860332b1c42989 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Thu, 24 Nov 2022 22:01:54 +0800 Subject: [PATCH 0181/4345] eventfd: change int to __u64 in eventfd_signal() ifndef CONFIG_EVENTFD [ Upstream commit fd4e60bf0ef8eb9edcfa12dda39e8b6ee9060492 ] Commit ee62c6b2dc93 ("eventfd: change int to __u64 in eventfd_signal()") forgot to change int to __u64 in the CONFIG_EVENTFD=n stub function. Link: https://lkml.kernel.org/r/20221124140154.104680-1-zhangqilong3@huawei.com Fixes: ee62c6b2dc93 ("eventfd: change int to __u64 in eventfd_signal()") Signed-off-by: Zhang Qilong Cc: Dylan Yudaken Cc: Jens Axboe Cc: Sha Zhengju Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- include/linux/eventfd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index ce1cf42740bf..6cd2a92daf20 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -62,7 +62,7 @@ static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd) return ERR_PTR(-ENOSYS); } -static inline int eventfd_signal(struct eventfd_ctx *ctx, int n) +static inline int eventfd_signal(struct eventfd_ctx *ctx, __u64 n) { return -ENOSYS; } From 93cdd1263691df25b7ec710f3b9ba2264724f1a3 Mon Sep 17 00:00:00 2001 From: Gavrilov Ilia Date: Tue, 29 Nov 2022 09:23:38 +0000 Subject: [PATCH 0182/4345] relay: fix type mismatch when allocating memory in relay_create_buf() [ Upstream commit 4d8586e04602fe42f0a782d2005956f8b6302678 ] The 'padding' field of the 'rchan_buf' structure is an array of 'size_t' elements, but the memory is allocated for an array of 'size_t *' elements. Found by Linux Verification Center (linuxtesting.org) with SVACE. Link: https://lkml.kernel.org/r/20221129092002.3538384-1-Ilia.Gavrilov@infotecs.ru Fixes: b86ff981a825 ("[PATCH] relay: migrate from relayfs to a generic relay API") Signed-off-by: Ilia.Gavrilov Cc: Colin Ian King Cc: Jens Axboe Cc: wuchi Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- kernel/relay.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/relay.c b/kernel/relay.c index b08d936d5fa7..067769b80d4a 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -163,13 +163,13 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan) { struct rchan_buf *buf; - if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *)) + if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t)) return NULL; buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); if (!buf) return NULL; - buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t *), + buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t), GFP_KERNEL); if (!buf->padding) goto free_buf; From cff9fefdfbf5744afbb6d70bff2b49ec2065d23d Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Fri, 2 Dec 2022 03:00:38 +0000 Subject: [PATCH 0183/4345] hfs: Fix OOB Write in hfs_asc2mac [ Upstream commit c53ed55cb275344086e32a7080a6b19cb183650b ] Syzbot reported a OOB Write bug: loop0: detected capacity change from 0 to 64 ================================================================== BUG: KASAN: slab-out-of-bounds in hfs_asc2mac+0x467/0x9a0 fs/hfs/trans.c:133 Write of size 1 at addr ffff88801848314e by task syz-executor391/3632 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x28e lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:284 print_report+0x107/0x1f0 mm/kasan/report.c:395 kasan_report+0xcd/0x100 mm/kasan/report.c:495 hfs_asc2mac+0x467/0x9a0 fs/hfs/trans.c:133 hfs_cat_build_key+0x92/0x170 fs/hfs/catalog.c:28 hfs_lookup+0x1ab/0x2c0 fs/hfs/dir.c:31 lookup_open fs/namei.c:3391 [inline] open_last_lookups fs/namei.c:3481 [inline] path_openat+0x10e6/0x2df0 fs/namei.c:3710 do_filp_open+0x264/0x4f0 fs/namei.c:3740 If in->len is much larger than HFS_NAMELEN(31) which is the maximum length of an HFS filename, a OOB write could occur in hfs_asc2mac(). In that case, when the dst reaches the boundary, the srclen is still greater than 0, which causes a OOB write. Fix this by adding a check on dstlen in while() before writing to dst address. Link: https://lkml.kernel.org/r/20221202030038.1391945-1-zhangpeng362@huawei.com Fixes: 328b92278650 ("[PATCH] hfs: NLS support") Signed-off-by: ZhangPeng Reviewed-by: Viacheslav Dubeyko Reported-by: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/hfs/trans.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/hfs/trans.c b/fs/hfs/trans.c index 39f5e343bf4d..fdb0edb8a607 100644 --- a/fs/hfs/trans.c +++ b/fs/hfs/trans.c @@ -109,7 +109,7 @@ void hfs_asc2mac(struct super_block *sb, struct hfs_name *out, const struct qstr if (nls_io) { wchar_t ch; - while (srclen > 0) { + while (srclen > 0 && dstlen > 0) { size = nls_io->char2uni(src, srclen, &ch); if (size < 0) { ch = '?'; From 53915ecc43c5139d6cdd1caa4fdc9290b9597008 Mon Sep 17 00:00:00 2001 From: Cai Xinchen Date: Sat, 3 Dec 2022 08:57:21 +0000 Subject: [PATCH 0184/4345] rapidio: devices: fix missing put_device in mport_cdev_open [ Upstream commit d5b6e6eba3af11cb2a2791fa36a2524990fcde1a ] When kfifo_alloc fails, the refcount of chdev->dev is left incremental. We should use put_device(&chdev->dev) to decrease the ref count of chdev->dev to avoid refcount leak. Link: https://lkml.kernel.org/r/20221203085721.13146-1-caixinchen1@huawei.com Fixes: e8de370188d0 ("rapidio: add mport char device driver") Signed-off-by: Cai Xinchen Cc: Alexandre Bounine Cc: Dan Carpenter Cc: Jakob Koschel Cc: John Hubbard Cc: Matt Porter Cc: Wang Weiyang Cc: Yang Yingliang Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- drivers/rapidio/devices/rio_mport_cdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index b8c09eaa23b5..5ac2dc1e2abd 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -1911,6 +1911,7 @@ static int mport_cdev_open(struct inode *inode, struct file *filp) sizeof(struct rio_event) * MPORT_EVENT_DEPTH, GFP_KERNEL); if (ret < 0) { + put_device(&chdev->dev); dev_err(&chdev->dev, DRV_NAME ": kfifo_alloc failed\n"); ret = -ENOMEM; goto err_fifo; From c3fb3e9a2c0c1a0fa492d90eb19bcfa92a5f884d Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Mon, 25 Jul 2022 18:13:59 +0300 Subject: [PATCH 0185/4345] wifi: ath9k: hif_usb: fix memory leak of urbs in ath9k_hif_usb_dealloc_tx_urbs() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c2a94de38c74e86f49124ac14f093d6a5c377a90 ] Syzkaller reports a long-known leak of urbs in ath9k_hif_usb_dealloc_tx_urbs(). The cause of the leak is that usb_get_urb() is called but usb_free_urb() (or usb_put_urb()) is not called inside usb_kill_urb() as urb->dev or urb->ep fields have not been initialized and usb_kill_urb() returns immediately. The patch removes trying to kill urbs located in hif_dev->tx.tx_buf because hif_dev->tx.tx_buf is not supposed to contain urbs which are in pending state (the pending urbs are stored in hif_dev->tx.tx_pending). The tx.tx_lock is acquired so there should not be any changes in the list. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: 03fb92a432ea ("ath9k: hif_usb: fix race condition between usb_get_urb() and usb_kill_anchored_urbs()") Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220725151359.283704-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/hif_usb.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index f06eec99de68..e66518d86882 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -781,14 +781,10 @@ static void ath9k_hif_usb_dealloc_tx_urbs(struct hif_device_usb *hif_dev) spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); list_for_each_entry_safe(tx_buf, tx_buf_tmp, &hif_dev->tx.tx_buf, list) { - usb_get_urb(tx_buf->urb); - spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); - usb_kill_urb(tx_buf->urb); list_del(&tx_buf->list); usb_free_urb(tx_buf->urb); kfree(tx_buf->buf); kfree(tx_buf); - spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); } spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); From 98d9172822dc6f38138333941984bd759a89d419 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Sat, 8 Oct 2022 14:49:17 +0300 Subject: [PATCH 0186/4345] wifi: ath9k: hif_usb: Fix use-after-free in ath9k_hif_usb_reg_in_cb() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit dd95f2239fc846795fc926787c3ae0ca701c9840 ] It is possible that skb is freed in ath9k_htc_rx_msg(), then usb_submit_urb() fails and we try to free skb again. It causes use-after-free bug. Moreover, if alloc_skb() fails, urb->context becomes NULL but rx_buf is not freed and there can be a memory leak. The patch removes unnecessary nskb and makes skb processing more clear: it is supposed that ath9k_htc_rx_msg() either frees old skb or passes its managing to another callback function. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: 3deff76095c4 ("ath9k_htc: Increase URB count for REG_IN pipe") Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221008114917.21404-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/hif_usb.c | 28 +++++++++++++----------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index e66518d86882..e5d5b0761881 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -709,14 +709,13 @@ static void ath9k_hif_usb_reg_in_cb(struct urb *urb) struct rx_buf *rx_buf = (struct rx_buf *)urb->context; struct hif_device_usb *hif_dev = rx_buf->hif_dev; struct sk_buff *skb = rx_buf->skb; - struct sk_buff *nskb; int ret; if (!skb) return; if (!hif_dev) - goto free; + goto free_skb; switch (urb->status) { case 0: @@ -725,7 +724,7 @@ static void ath9k_hif_usb_reg_in_cb(struct urb *urb) case -ECONNRESET: case -ENODEV: case -ESHUTDOWN: - goto free; + goto free_skb; default: skb_reset_tail_pointer(skb); skb_trim(skb, 0); @@ -736,25 +735,27 @@ static void ath9k_hif_usb_reg_in_cb(struct urb *urb) if (likely(urb->actual_length != 0)) { skb_put(skb, urb->actual_length); - /* Process the command first */ + /* + * Process the command first. + * skb is either freed here or passed to be + * managed to another callback function. + */ ath9k_htc_rx_msg(hif_dev->htc_handle, skb, skb->len, USB_REG_IN_PIPE); - - nskb = alloc_skb(MAX_REG_IN_BUF_SIZE, GFP_ATOMIC); - if (!nskb) { + skb = alloc_skb(MAX_REG_IN_BUF_SIZE, GFP_ATOMIC); + if (!skb) { dev_err(&hif_dev->udev->dev, "ath9k_htc: REG_IN memory allocation failure\n"); - urb->context = NULL; - return; + goto free_rx_buf; } - rx_buf->skb = nskb; + rx_buf->skb = skb; usb_fill_int_urb(urb, hif_dev->udev, usb_rcvintpipe(hif_dev->udev, USB_REG_IN_PIPE), - nskb->data, MAX_REG_IN_BUF_SIZE, + skb->data, MAX_REG_IN_BUF_SIZE, ath9k_hif_usb_reg_in_cb, rx_buf, 1); } @@ -763,12 +764,13 @@ resubmit: ret = usb_submit_urb(urb, GFP_ATOMIC); if (ret) { usb_unanchor_urb(urb); - goto free; + goto free_skb; } return; -free: +free_skb: kfree_skb(skb); +free_rx_buf: kfree(rx_buf); urb->context = NULL; } From 9b6851c1826356c573391230e7629ba6ec53a3de Mon Sep 17 00:00:00 2001 From: Bitterblue Smith Date: Sat, 8 Oct 2022 13:56:09 +0300 Subject: [PATCH 0187/4345] wifi: rtl8xxxu: Fix reading the vendor of combo chips [ Upstream commit 6f103aeb5e985ac08f3a4a049a2c17294f40cff9 ] The wifi + bluetooth combo chips (RTL8723AU and RTL8723BU) read the chip vendor from the wrong register because the val32 variable gets overwritten. Add one more variable to avoid this. This had no real effect on RTL8723BU. It may have had an effect on RTL8723AU. Fixes: 26f1fad29ad9 ("New driver: rtl8xxxu (mac80211)") Signed-off-by: Bitterblue Smith Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/24af8024-2f07-552b-93d8-38823d8e3cb0@gmail.com Signed-off-by: Sasha Levin --- .../wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index e34cd6fed7e8..43898f105bb7 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -1607,18 +1607,18 @@ static void rtl8xxxu_print_chipinfo(struct rtl8xxxu_priv *priv) static int rtl8xxxu_identify_chip(struct rtl8xxxu_priv *priv) { struct device *dev = &priv->udev->dev; - u32 val32, bonding; + u32 val32, bonding, sys_cfg; u16 val16; - val32 = rtl8xxxu_read32(priv, REG_SYS_CFG); - priv->chip_cut = (val32 & SYS_CFG_CHIP_VERSION_MASK) >> + sys_cfg = rtl8xxxu_read32(priv, REG_SYS_CFG); + priv->chip_cut = (sys_cfg & SYS_CFG_CHIP_VERSION_MASK) >> SYS_CFG_CHIP_VERSION_SHIFT; - if (val32 & SYS_CFG_TRP_VAUX_EN) { + if (sys_cfg & SYS_CFG_TRP_VAUX_EN) { dev_info(dev, "Unsupported test chip\n"); return -ENOTSUPP; } - if (val32 & SYS_CFG_BT_FUNC) { + if (sys_cfg & SYS_CFG_BT_FUNC) { if (priv->chip_cut >= 3) { sprintf(priv->chip_name, "8723BU"); priv->rtl_chip = RTL8723B; @@ -1640,7 +1640,7 @@ static int rtl8xxxu_identify_chip(struct rtl8xxxu_priv *priv) if (val32 & MULTI_GPS_FUNC_EN) priv->has_gps = 1; priv->is_multi_func = 1; - } else if (val32 & SYS_CFG_TYPE_ID) { + } else if (sys_cfg & SYS_CFG_TYPE_ID) { bonding = rtl8xxxu_read32(priv, REG_HPON_FSM); bonding &= HPON_FSM_BONDING_MASK; if (priv->fops->tx_desc_size == @@ -1688,7 +1688,7 @@ static int rtl8xxxu_identify_chip(struct rtl8xxxu_priv *priv) case RTL8188E: case RTL8192E: case RTL8723B: - switch (val32 & SYS_CFG_VENDOR_EXT_MASK) { + switch (sys_cfg & SYS_CFG_VENDOR_EXT_MASK) { case SYS_CFG_VENDOR_ID_TSMC: sprintf(priv->chip_vendor, "TSMC"); break; @@ -1705,7 +1705,7 @@ static int rtl8xxxu_identify_chip(struct rtl8xxxu_priv *priv) } break; default: - if (val32 & SYS_CFG_VENDOR_ID) { + if (sys_cfg & SYS_CFG_VENDOR_ID) { sprintf(priv->chip_vendor, "UMC"); priv->vendor_umc = 1; } else { From 26ce3f0c8f61d578786d1e1e6bed8cefc1e4844a Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Tue, 11 Oct 2022 14:10:49 -0700 Subject: [PATCH 0188/4345] drm/bridge: adv7533: remove dynamic lane switching from adv7533 bridge [ Upstream commit 9a0cdcd6649b76f0b7ceec0e55b0a718321e34d3 ] adv7533 bridge tries to dynamically switch lanes based on the mode by detaching and attaching the mipi dsi device. This approach is incorrect because this method of dynamic switch of detaching and attaching the mipi dsi device also results in removing and adding the component which is not necessary. This approach is also prone to deadlocks. So for example, on the db410c whenever this path is executed with lockdep enabled, this results in a deadlock due to below ordering of locks. -> #1 (crtc_ww_class_acquire){+.+.}-{0:0}: lock_acquire+0x6c/0x90 drm_modeset_acquire_init+0xf4/0x150 drmm_mode_config_init+0x220/0x770 msm_drm_bind+0x13c/0x654 try_to_bring_up_aggregate_device+0x164/0x1d0 __component_add+0xa8/0x174 component_add+0x18/0x2c dsi_dev_attach+0x24/0x30 dsi_host_attach+0x98/0x14c devm_mipi_dsi_attach+0x38/0xb0 adv7533_attach_dsi+0x8c/0x110 adv7511_probe+0x5a0/0x930 i2c_device_probe+0x30c/0x350 really_probe.part.0+0x9c/0x2b0 __driver_probe_device+0x98/0x144 driver_probe_device+0xac/0x14c __device_attach_driver+0xbc/0x124 bus_for_each_drv+0x78/0xd0 __device_attach+0xa8/0x1c0 device_initial_probe+0x18/0x24 bus_probe_device+0xa0/0xac deferred_probe_work_func+0x90/0xd0 process_one_work+0x28c/0x6b0 worker_thread+0x240/0x444 kthread+0x110/0x114 ret_from_fork+0x10/0x20 -> #0 (component_mutex){+.+.}-{3:3}: __lock_acquire+0x1280/0x20ac lock_acquire.part.0+0xe0/0x230 lock_acquire+0x6c/0x90 __mutex_lock+0x84/0x400 mutex_lock_nested+0x3c/0x70 component_del+0x34/0x170 dsi_dev_detach+0x24/0x30 dsi_host_detach+0x20/0x64 mipi_dsi_detach+0x2c/0x40 adv7533_mode_set+0x64/0x90 adv7511_bridge_mode_set+0x210/0x214 drm_bridge_chain_mode_set+0x5c/0x84 crtc_set_mode+0x18c/0x1dc drm_atomic_helper_commit_modeset_disables+0x40/0x50 msm_atomic_commit_tail+0x1d0/0x6e0 commit_tail+0xa4/0x180 drm_atomic_helper_commit+0x178/0x3b0 drm_atomic_commit+0xa4/0xe0 drm_client_modeset_commit_atomic+0x228/0x284 drm_client_modeset_commit_locked+0x64/0x1d0 drm_client_modeset_commit+0x34/0x60 drm_fb_helper_lastclose+0x74/0xcc drm_lastclose+0x3c/0x80 drm_release+0xfc/0x114 __fput+0x70/0x224 ____fput+0x14/0x20 task_work_run+0x88/0x1a0 do_exit+0x350/0xa50 do_group_exit+0x38/0xa4 __wake_up_parent+0x0/0x34 invoke_syscall+0x48/0x114 el0_svc_common.constprop.0+0x60/0x11c do_el0_svc+0x30/0xc0 el0_svc+0x58/0x100 el0t_64_sync_handler+0x1b0/0x1bc el0t_64_sync+0x18c/0x190 Due to above reasons, remove the dynamic lane switching code from adv7533 bridge chip and filter out the modes which would need different number of lanes as compared to the initialization time using the mode_valid callback. This can be potentially re-introduced by using the pre_enable() callback but this needs to be evaluated first whether such an approach will work so this will be done with a separate change. changes since RFC: - Fix commit text and add TODO comment changes in v2: - Fix checkpatch formatting errors Fixes: 62b2f026cd8e ("drm/bridge: adv7533: Change number of DSI lanes dynamically") Closes: https://gitlab.freedesktop.org/drm/msm/-/issues/16 Suggested-by: Dmitry Baryshkov Signed-off-by: Abhinav Kumar Reviewed-by: Robert Foss Link: https://lore.kernel.org/r/1661797363-7564-1-git-send-email-quic_abhinavk@quicinc.com Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/1665522649-3423-1-git-send-email-quic_abhinavk@quicinc.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/adv7511/adv7511.h | 3 ++- drivers/gpu/drm/bridge/adv7511/adv7511_drv.c | 18 ++++++++++---- drivers/gpu/drm/bridge/adv7511/adv7533.c | 25 ++++++++++---------- 3 files changed, 29 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511.h b/drivers/gpu/drm/bridge/adv7511/adv7511.h index 711061bf3eb7..e95abeb64b93 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511.h +++ b/drivers/gpu/drm/bridge/adv7511/adv7511.h @@ -394,7 +394,8 @@ static inline int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511) void adv7533_dsi_power_on(struct adv7511 *adv); void adv7533_dsi_power_off(struct adv7511 *adv); -void adv7533_mode_set(struct adv7511 *adv, const struct drm_display_mode *mode); +enum drm_mode_status adv7533_mode_valid(struct adv7511 *adv, + const struct drm_display_mode *mode); int adv7533_patch_registers(struct adv7511 *adv); int adv7533_patch_cec_registers(struct adv7511 *adv); int adv7533_attach_dsi(struct adv7511 *adv); diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 430c5e8f0388..6ba860a16e96 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -697,7 +697,7 @@ adv7511_detect(struct adv7511 *adv7511, struct drm_connector *connector) } static enum drm_mode_status adv7511_mode_valid(struct adv7511 *adv7511, - struct drm_display_mode *mode) + const struct drm_display_mode *mode) { if (mode->clock > 165000) return MODE_CLOCK_HIGH; @@ -791,9 +791,6 @@ static void adv7511_mode_set(struct adv7511 *adv7511, regmap_update_bits(adv7511->regmap, 0x17, 0x60, (vsync_polarity << 6) | (hsync_polarity << 5)); - if (adv7511->type == ADV7533 || adv7511->type == ADV7535) - adv7533_mode_set(adv7511, adj_mode); - drm_mode_copy(&adv7511->curr_mode, adj_mode); /* @@ -913,6 +910,18 @@ static void adv7511_bridge_mode_set(struct drm_bridge *bridge, adv7511_mode_set(adv, mode, adj_mode); } +static enum drm_mode_status adv7511_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + struct adv7511 *adv = bridge_to_adv7511(bridge); + + if (adv->type == ADV7533 || adv->type == ADV7535) + return adv7533_mode_valid(adv, mode); + else + return adv7511_mode_valid(adv, mode); +} + static int adv7511_bridge_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flags flags) { @@ -963,6 +972,7 @@ static const struct drm_bridge_funcs adv7511_bridge_funcs = { .enable = adv7511_bridge_enable, .disable = adv7511_bridge_disable, .mode_set = adv7511_bridge_mode_set, + .mode_valid = adv7511_bridge_mode_valid, .attach = adv7511_bridge_attach, .detect = adv7511_bridge_detect, .get_edid = adv7511_bridge_get_edid, diff --git a/drivers/gpu/drm/bridge/adv7511/adv7533.c b/drivers/gpu/drm/bridge/adv7511/adv7533.c index aa19d5a40e31..f304a5ff8e59 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7533.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7533.c @@ -100,26 +100,27 @@ void adv7533_dsi_power_off(struct adv7511 *adv) regmap_write(adv->regmap_cec, 0x27, 0x0b); } -void adv7533_mode_set(struct adv7511 *adv, const struct drm_display_mode *mode) +enum drm_mode_status adv7533_mode_valid(struct adv7511 *adv, + const struct drm_display_mode *mode) { + int lanes; struct mipi_dsi_device *dsi = adv->dsi; - int lanes, ret; - - if (adv->num_dsi_lanes != 4) - return; if (mode->clock > 80000) lanes = 4; else lanes = 3; - if (lanes != dsi->lanes) { - mipi_dsi_detach(dsi); - dsi->lanes = lanes; - ret = mipi_dsi_attach(dsi); - if (ret) - dev_err(&dsi->dev, "failed to change host lanes\n"); - } + /* + * TODO: add support for dynamic switching of lanes + * by using the bridge pre_enable() op . Till then filter + * out the modes which shall need different number of lanes + * than what was configured in the device tree. + */ + if (lanes != dsi->lanes) + return MODE_BAD; + + return MODE_OK; } int adv7533_patch_registers(struct adv7511 *adv) From c61650b869e0b6fb0c0a28ed42d928eea969afc8 Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Tue, 11 Oct 2022 08:01:03 -0400 Subject: [PATCH 0189/4345] libbpf: Fix use-after-free in btf_dump_name_dups [ Upstream commit 93c660ca40b5d2f7c1b1626e955a8e9fa30e0749 ] ASAN reports an use-after-free in btf_dump_name_dups: ERROR: AddressSanitizer: heap-use-after-free on address 0xffff927006db at pc 0xaaaab5dfb618 bp 0xffffdd89b890 sp 0xffffdd89b928 READ of size 2 at 0xffff927006db thread T0 #0 0xaaaab5dfb614 in __interceptor_strcmp.part.0 (test_progs+0x21b614) #1 0xaaaab635f144 in str_equal_fn tools/lib/bpf/btf_dump.c:127 #2 0xaaaab635e3e0 in hashmap_find_entry tools/lib/bpf/hashmap.c:143 #3 0xaaaab635e72c in hashmap__find tools/lib/bpf/hashmap.c:212 #4 0xaaaab6362258 in btf_dump_name_dups tools/lib/bpf/btf_dump.c:1525 #5 0xaaaab636240c in btf_dump_resolve_name tools/lib/bpf/btf_dump.c:1552 #6 0xaaaab6362598 in btf_dump_type_name tools/lib/bpf/btf_dump.c:1567 #7 0xaaaab6360b48 in btf_dump_emit_struct_def tools/lib/bpf/btf_dump.c:912 #8 0xaaaab6360630 in btf_dump_emit_type tools/lib/bpf/btf_dump.c:798 #9 0xaaaab635f720 in btf_dump__dump_type tools/lib/bpf/btf_dump.c:282 #10 0xaaaab608523c in test_btf_dump_incremental tools/testing/selftests/bpf/prog_tests/btf_dump.c:236 #11 0xaaaab6097530 in test_btf_dump tools/testing/selftests/bpf/prog_tests/btf_dump.c:875 #12 0xaaaab6314ed0 in run_one_test tools/testing/selftests/bpf/test_progs.c:1062 #13 0xaaaab631a0a8 in main tools/testing/selftests/bpf/test_progs.c:1697 #14 0xffff9676d214 in __libc_start_main ../csu/libc-start.c:308 #15 0xaaaab5d65990 (test_progs+0x185990) 0xffff927006db is located 11 bytes inside of 16-byte region [0xffff927006d0,0xffff927006e0) freed by thread T0 here: #0 0xaaaab5e2c7c4 in realloc (test_progs+0x24c7c4) #1 0xaaaab634f4a0 in libbpf_reallocarray tools/lib/bpf/libbpf_internal.h:191 #2 0xaaaab634f840 in libbpf_add_mem tools/lib/bpf/btf.c:163 #3 0xaaaab636643c in strset_add_str_mem tools/lib/bpf/strset.c:106 #4 0xaaaab6366560 in strset__add_str tools/lib/bpf/strset.c:157 #5 0xaaaab6352d70 in btf__add_str tools/lib/bpf/btf.c:1519 #6 0xaaaab6353e10 in btf__add_field tools/lib/bpf/btf.c:2032 #7 0xaaaab6084fcc in test_btf_dump_incremental tools/testing/selftests/bpf/prog_tests/btf_dump.c:232 #8 0xaaaab6097530 in test_btf_dump tools/testing/selftests/bpf/prog_tests/btf_dump.c:875 #9 0xaaaab6314ed0 in run_one_test tools/testing/selftests/bpf/test_progs.c:1062 #10 0xaaaab631a0a8 in main tools/testing/selftests/bpf/test_progs.c:1697 #11 0xffff9676d214 in __libc_start_main ../csu/libc-start.c:308 #12 0xaaaab5d65990 (test_progs+0x185990) previously allocated by thread T0 here: #0 0xaaaab5e2c7c4 in realloc (test_progs+0x24c7c4) #1 0xaaaab634f4a0 in libbpf_reallocarray tools/lib/bpf/libbpf_internal.h:191 #2 0xaaaab634f840 in libbpf_add_mem tools/lib/bpf/btf.c:163 #3 0xaaaab636643c in strset_add_str_mem tools/lib/bpf/strset.c:106 #4 0xaaaab6366560 in strset__add_str tools/lib/bpf/strset.c:157 #5 0xaaaab6352d70 in btf__add_str tools/lib/bpf/btf.c:1519 #6 0xaaaab6353ff0 in btf_add_enum_common tools/lib/bpf/btf.c:2070 #7 0xaaaab6354080 in btf__add_enum tools/lib/bpf/btf.c:2102 #8 0xaaaab6082f50 in test_btf_dump_incremental tools/testing/selftests/bpf/prog_tests/btf_dump.c:162 #9 0xaaaab6097530 in test_btf_dump tools/testing/selftests/bpf/prog_tests/btf_dump.c:875 #10 0xaaaab6314ed0 in run_one_test tools/testing/selftests/bpf/test_progs.c:1062 #11 0xaaaab631a0a8 in main tools/testing/selftests/bpf/test_progs.c:1697 #12 0xffff9676d214 in __libc_start_main ../csu/libc-start.c:308 #13 0xaaaab5d65990 (test_progs+0x185990) The reason is that the key stored in hash table name_map is a string address, and the string memory is allocated by realloc() function, when the memory is resized by realloc() later, the old memory may be freed, so the address stored in name_map references to a freed memory, causing use-after-free. Fix it by storing duplicated string address in name_map. Fixes: 919d2b1dbb07 ("libbpf: Allow modification of BTF and add btf__add_str API") Signed-off-by: Xu Kuohai Signed-off-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20221011120108.782373-2-xukuohai@huaweicloud.com Signed-off-by: Sasha Levin --- tools/lib/bpf/btf_dump.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index bd22853be4a6..0e2d63da24e9 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -188,6 +188,17 @@ static int btf_dump_resize(struct btf_dump *d) return 0; } +static void btf_dump_free_names(struct hashmap *map) +{ + size_t bkt; + struct hashmap_entry *cur; + + hashmap__for_each_entry(map, cur, bkt) + free((void *)cur->key); + + hashmap__free(map); +} + void btf_dump__free(struct btf_dump *d) { int i; @@ -206,8 +217,8 @@ void btf_dump__free(struct btf_dump *d) free(d->cached_names); free(d->emit_queue); free(d->decl_stack); - hashmap__free(d->type_names); - hashmap__free(d->ident_names); + btf_dump_free_names(d->type_names); + btf_dump_free_names(d->ident_names); free(d); } @@ -1392,11 +1403,23 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map, const char *orig_name) { + char *old_name, *new_name; size_t dup_cnt = 0; + int err; + + new_name = strdup(orig_name); + if (!new_name) + return 1; hashmap__find(name_map, orig_name, (void **)&dup_cnt); dup_cnt++; - hashmap__set(name_map, orig_name, (void *)dup_cnt, NULL, NULL); + + err = hashmap__set(name_map, new_name, (void *)dup_cnt, + (const void **)&old_name, NULL); + if (err) + free(new_name); + + free(old_name); return dup_cnt; } From 85b297d7986c64f36825020b848f09f0415f325a Mon Sep 17 00:00:00 2001 From: Shung-Hsi Yu Date: Wed, 12 Oct 2022 10:23:53 +0800 Subject: [PATCH 0190/4345] libbpf: Fix null-pointer dereference in find_prog_by_sec_insn() [ Upstream commit d0d382f95a9270dcf803539d6781d6bd67e3f5b2 ] When there are no program sections, obj->programs is left unallocated, and find_prog_by_sec_insn()'s search lands on &obj->programs[0] == NULL, and will cause null-pointer dereference in the following access to prog->sec_idx. Guard the search with obj->nr_programs similar to what's being done in __bpf_program__iter() to prevent null-pointer access from happening. Fixes: db2b8b06423c ("libbpf: Support CO-RE relocations for multi-prog sections") Signed-off-by: Shung-Hsi Yu Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20221012022353.7350-4-shung-hsi.yu@suse.com Signed-off-by: Sasha Levin --- tools/lib/bpf/libbpf.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 66d7f8d494de..015ed8253f73 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -3479,6 +3479,9 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj, int l = 0, r = obj->nr_programs - 1, m; struct bpf_program *prog; + if (!obj->nr_programs) + return NULL; + while (l < r) { m = l + (r - l + 1) / 2; prog = &obj->programs[m]; From 7e0ba56c7e5f150af14c15425d2eec1f9ee3e735 Mon Sep 17 00:00:00 2001 From: Junlin Yang Date: Fri, 9 Apr 2021 21:54:26 +0800 Subject: [PATCH 0191/4345] pata_ipx4xx_cf: Fix unsigned comparison with less than zero [ Upstream commit c38ae56ee034623c59e39c0130ca0dec086c1a39 ] The return from the call to platform_get_irq() is int, it can be a negative error code, however this is being assigned to an unsigned int variable 'irq', so making 'irq' an int, and change the position to keep the code format. ./drivers/ata/pata_ixp4xx_cf.c:168:5-8: WARNING: Unsigned expression compared with zero: irq > 0 Signed-off-by: Junlin Yang Link: https://lore.kernel.org/r/20210409135426.1773-1-angkery@163.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/ata/pata_ixp4xx_cf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c index abc0e87ca1a8..43215a4c1e54 100644 --- a/drivers/ata/pata_ixp4xx_cf.c +++ b/drivers/ata/pata_ixp4xx_cf.c @@ -135,12 +135,12 @@ static void ixp4xx_setup_port(struct ata_port *ap, static int ixp4xx_pata_probe(struct platform_device *pdev) { - unsigned int irq; struct resource *cs0, *cs1; struct ata_host *host; struct ata_port *ap; struct ixp4xx_pata_data *data = dev_get_platdata(&pdev->dev); int ret; + int irq; cs0 = platform_get_resource(pdev, IORESOURCE_MEM, 0); cs1 = platform_get_resource(pdev, IORESOURCE_MEM, 1); From 83f7e3c988710202d0f5a742c96c0817ccfee326 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Tue, 27 Sep 2022 09:28:13 +0800 Subject: [PATCH 0192/4345] media: coda: jpeg: Add check for kmalloc [ Upstream commit f30ce3d3760b22ee33c8d9c2e223764ad30bdc5f ] As kmalloc can return NULL pointer, it should be better to check the return value and return error, same as coda_jpeg_decode_header. Fixes: 96f6f62c4656 ("media: coda: jpeg: add CODA960 JPEG encoder support") Signed-off-by: Jiasheng Jiang Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/coda/coda-jpeg.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/coda/coda-jpeg.c b/drivers/media/platform/coda/coda-jpeg.c index a72f4655e5ad..b7bf529f18f7 100644 --- a/drivers/media/platform/coda/coda-jpeg.c +++ b/drivers/media/platform/coda/coda-jpeg.c @@ -1052,10 +1052,16 @@ static int coda9_jpeg_start_encoding(struct coda_ctx *ctx) v4l2_err(&dev->v4l2_dev, "error loading Huffman tables\n"); return ret; } - if (!ctx->params.jpeg_qmat_tab[0]) + if (!ctx->params.jpeg_qmat_tab[0]) { ctx->params.jpeg_qmat_tab[0] = kmalloc(64, GFP_KERNEL); - if (!ctx->params.jpeg_qmat_tab[1]) + if (!ctx->params.jpeg_qmat_tab[0]) + return -ENOMEM; + } + if (!ctx->params.jpeg_qmat_tab[1]) { ctx->params.jpeg_qmat_tab[1] = kmalloc(64, GFP_KERNEL); + if (!ctx->params.jpeg_qmat_tab[1]) + return -ENOMEM; + } coda_set_jpeg_compression_quality(ctx, ctx->params.jpeg_quality); return 0; From 86d531c1d7947d5cd845d8b280262ad53fd10cc2 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Wed, 21 Sep 2022 13:38:00 +0200 Subject: [PATCH 0193/4345] media: i2c: ad5820: Fix error path [ Upstream commit 9fce241660f37d9e95e93c0ae6fba8cfefa5797b ] Error path seems to be swaped. Fix the order and provide some meaningful names. Fixes: bee3d5115611 ("[media] ad5820: Add driver for auto-focus coil") Signed-off-by: Ricardo Ribalda Signed-off-by: Sakari Ailus Signed-off-by: Sasha Levin --- drivers/media/i2c/ad5820.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/media/i2c/ad5820.c b/drivers/media/i2c/ad5820.c index 19c74db0649f..f55322eebf6d 100644 --- a/drivers/media/i2c/ad5820.c +++ b/drivers/media/i2c/ad5820.c @@ -329,18 +329,18 @@ static int ad5820_probe(struct i2c_client *client, ret = media_entity_pads_init(&coil->subdev.entity, 0, NULL); if (ret < 0) - goto cleanup2; + goto clean_mutex; ret = v4l2_async_register_subdev(&coil->subdev); if (ret < 0) - goto cleanup; + goto clean_entity; return ret; -cleanup2: - mutex_destroy(&coil->power_lock); -cleanup: +clean_entity: media_entity_cleanup(&coil->subdev.entity); +clean_mutex: + mutex_destroy(&coil->power_lock); return ret; } From 4882492ad3f08a35fbc4a02a40b416583f0d5056 Mon Sep 17 00:00:00 2001 From: Tang Bin Date: Tue, 13 Sep 2022 14:37:00 +0800 Subject: [PATCH 0194/4345] venus: pm_helpers: Fix error check in vcodec_domains_get() [ Upstream commit 0f6e8d8c94a82e85e1b9b62a7671990740dc6f70 ] In the function vcodec_domains_get(), dev_pm_domain_attach_by_name() may return NULL in some cases, so IS_ERR() doesn't meet the requirements. Thus fix it. Fixes: 7482a983dea3 ("media: venus: redesign clocks and pm domains control") Signed-off-by: Tang Bin Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/venus/pm_helpers.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/qcom/venus/pm_helpers.c b/drivers/media/platform/qcom/venus/pm_helpers.c index 710f9a2b132b..f7de02352f1b 100644 --- a/drivers/media/platform/qcom/venus/pm_helpers.c +++ b/drivers/media/platform/qcom/venus/pm_helpers.c @@ -764,8 +764,8 @@ static int vcodec_domains_get(struct venus_core *core) for (i = 0; i < res->vcodec_pmdomains_num; i++) { pd = dev_pm_domain_attach_by_name(dev, res->vcodec_pmdomains[i]); - if (IS_ERR(pd)) - return PTR_ERR(pd); + if (IS_ERR_OR_NULL(pd)) + return PTR_ERR(pd) ? : -ENODATA; core->pmdomains[i] = pd; } From c93cac58a7e502f09bbe3f3dc695c6d4657cd616 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Mon, 18 Jan 2021 02:52:48 +0100 Subject: [PATCH 0195/4345] media: exynos4-is: Use v4l2_async_notifier_add_fwnode_remote_subdev [ Upstream commit 3a2822bfe45c50abd9f76a8547a77a1f6a0e8c8d ] The use of v4l2_async_notifier_add_subdev will be discouraged. Drivers are instead encouraged to use a helper such as v4l2_async_notifier_add_fwnode_remote_subdev. This fixes a misuse of the API, as v4l2_async_notifier_add_subdev should get a kmalloc'ed struct v4l2_async_subdev, removing some boilerplate code while at it. Use the appropriate helper v4l2_async_notifier_add_fwnode_remote_subdev, which handles the needed setup, instead of open-coding it. Signed-off-by: Ezequiel Garcia Reviewed-by: Jacopo Mondi Reviewed-by: Helen Koike Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: f98a5c2e1c43 ("media: exynos4-is: don't rely on the v4l2_async_subdev internals") Signed-off-by: Sasha Levin --- drivers/media/platform/exynos4-is/media-dev.c | 24 ++++++++++--------- drivers/media/platform/exynos4-is/media-dev.h | 2 +- 2 files changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c index a9a8f0433fb2..3d877c5ae290 100644 --- a/drivers/media/platform/exynos4-is/media-dev.c +++ b/drivers/media/platform/exynos4-is/media-dev.c @@ -401,6 +401,7 @@ static int fimc_md_parse_one_endpoint(struct fimc_md *fmd, int index = fmd->num_sensors; struct fimc_source_info *pd = &fmd->sensor[index].pdata; struct device_node *rem, *np; + struct v4l2_async_subdev *asd; struct v4l2_fwnode_endpoint endpoint = { .bus_type = 0 }; int ret; @@ -418,10 +419,10 @@ static int fimc_md_parse_one_endpoint(struct fimc_md *fmd, pd->mux_id = (endpoint.base.port - 1) & 0x1; rem = of_graph_get_remote_port_parent(ep); - of_node_put(ep); if (rem == NULL) { v4l2_info(&fmd->v4l2_dev, "Remote device at %pOF not found\n", ep); + of_node_put(ep); return 0; } @@ -450,6 +451,7 @@ static int fimc_md_parse_one_endpoint(struct fimc_md *fmd, * checking parent's node name. */ np = of_get_parent(rem); + of_node_put(rem); if (of_node_name_eq(np, "i2c-isp")) pd->fimc_bus_type = FIMC_BUS_TYPE_ISP_WRITEBACK; @@ -458,20 +460,19 @@ static int fimc_md_parse_one_endpoint(struct fimc_md *fmd, of_node_put(np); if (WARN_ON(index >= ARRAY_SIZE(fmd->sensor))) { - of_node_put(rem); + of_node_put(ep); return -EINVAL; } - fmd->sensor[index].asd.match_type = V4L2_ASYNC_MATCH_FWNODE; - fmd->sensor[index].asd.match.fwnode = of_fwnode_handle(rem); + asd = v4l2_async_notifier_add_fwnode_remote_subdev( + &fmd->subdev_notifier, of_fwnode_handle(ep), sizeof(*asd)); - ret = v4l2_async_notifier_add_subdev(&fmd->subdev_notifier, - &fmd->sensor[index].asd); - if (ret) { - of_node_put(rem); - return ret; - } + of_node_put(ep); + if (IS_ERR(asd)) + return PTR_ERR(asd); + + fmd->sensor[index].asd = asd; fmd->num_sensors++; return 0; @@ -1377,7 +1378,8 @@ static int subdev_notifier_bound(struct v4l2_async_notifier *notifier, /* Find platform data for this sensor subdev */ for (i = 0; i < ARRAY_SIZE(fmd->sensor); i++) - if (fmd->sensor[i].asd.match.fwnode == + if (fmd->sensor[i].asd && + fmd->sensor[i].asd->match.fwnode == of_fwnode_handle(subdev->dev->of_node)) si = &fmd->sensor[i]; diff --git a/drivers/media/platform/exynos4-is/media-dev.h b/drivers/media/platform/exynos4-is/media-dev.h index 9447fafe23c6..a3876d668ea6 100644 --- a/drivers/media/platform/exynos4-is/media-dev.h +++ b/drivers/media/platform/exynos4-is/media-dev.h @@ -83,7 +83,7 @@ struct fimc_camclk_info { */ struct fimc_sensor_info { struct fimc_source_info pdata; - struct v4l2_async_subdev asd; + struct v4l2_async_subdev *asd; struct v4l2_subdev *subdev; struct fimc_dev *host; }; From 580c79fd57f38823d3864d76b746ee9ae06b42a8 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 23 Sep 2022 11:42:01 +0200 Subject: [PATCH 0196/4345] media: exynos4-is: don't rely on the v4l2_async_subdev internals [ Upstream commit f98a5c2e1c4396488c27274ba82afc11725a4bcc ] Commit 1f391df44607 ("media: v4l2-async: Use endpoints in __v4l2_async_nf_add_fwnode_remote()") changed the data that is stored in the v4l2_async_subdev internals from the fwnode pointer to the parent device to the fwnode pointer to the matched endpoint. This broke the sensor matching code, which relied on the particular fwnode data in the v4l2_async_subdev internals. Fix this by simply matching the v4l2_async_subdev pointer, which is already available there. Reported-by: Daniel Scally Fixes: fa91f1056f17 ("[media] exynos4-is: Add support for asynchronous subdevices registration") Signed-off-by: Marek Szyprowski Reviewed-by: Daniel Scally Signed-off-by: Sakari Ailus Signed-off-by: Sasha Levin --- drivers/media/platform/exynos4-is/media-dev.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c index 3d877c5ae290..8603c578f55f 100644 --- a/drivers/media/platform/exynos4-is/media-dev.c +++ b/drivers/media/platform/exynos4-is/media-dev.c @@ -1378,9 +1378,7 @@ static int subdev_notifier_bound(struct v4l2_async_notifier *notifier, /* Find platform data for this sensor subdev */ for (i = 0; i < ARRAY_SIZE(fmd->sensor); i++) - if (fmd->sensor[i].asd && - fmd->sensor[i].asd->match.fwnode == - of_fwnode_handle(subdev->dev->of_node)) + if (fmd->sensor[i].asd == asd) si = &fmd->sensor[i]; if (si == NULL) From cd50258e9c28e20473abe95ae17fb6848c6d0095 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 7 Dec 2021 21:15:28 +0900 Subject: [PATCH 0197/4345] can: kvaser_usb: do not increase tx statistics when sending error message frames [ Upstream commit 0b0ce2c67795672115ac6ca28351a78799cd114b ] The CAN error message frames (i.e. error skb) are an interface specific to socket CAN. The payload of the CAN error message frames does not correspond to any actual data sent on the wire. Only an error flag and a delimiter are transmitted when an error occurs (c.f. ISO 11898-1 section 10.4.4.2 "Error flag"). For this reason, it makes no sense to increment the tx_packets and tx_bytes fields of struct net_device_stats when sending an error message frame because no actual payload will be transmitted on the wire. N.B. Sending error message frames is a very specific feature which, at the moment, is only supported by the Kvaser Hydra hardware. Please refer to [1] for more details on the topic. [1] https://lore.kernel.org/linux-can/CAMZ6RqK0rTNg3u3mBpZOoY51jLZ-et-J01tY6-+mWsM4meVw-A@mail.gmail.com/t/#u Link: https://lore.kernel.org/all/20211207121531.42941-3-mailhol.vincent@wanadoo.fr Co-developed-by: Jimmy Assarsson Signed-off-by: Jimmy Assarsson Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde Stable-dep-of: 35364f5b41a4 ("can: kvaser_usb: kvaser_usb_leaf: Get capabilities from device") Signed-off-by: Sasha Levin --- drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 45d278724883..9588efbfae71 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -293,6 +293,7 @@ struct kvaser_cmd { #define KVASER_USB_HYDRA_CF_FLAG_OVERRUN BIT(1) #define KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME BIT(4) #define KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID BIT(5) +#define KVASER_USB_HYDRA_CF_FLAG_TX_ACK BIT(6) /* CAN frame flags. Used in ext_rx_can and ext_tx_can */ #define KVASER_USB_HYDRA_CF_FLAG_OSM_NACK BIT(12) #define KVASER_USB_HYDRA_CF_FLAG_ABL BIT(13) @@ -1099,6 +1100,7 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev, struct kvaser_usb_net_priv *priv; unsigned long irq_flags; bool one_shot_fail = false; + bool is_err_frame = false; u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd); priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); @@ -1117,10 +1119,13 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev, kvaser_usb_hydra_one_shot_fail(priv, cmd_ext); one_shot_fail = true; } + + is_err_frame = flags & KVASER_USB_HYDRA_CF_FLAG_TX_ACK && + flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME; } context = &priv->tx_contexts[transid % dev->max_tx_urbs]; - if (!one_shot_fail) { + if (!one_shot_fail && !is_err_frame) { struct net_device_stats *stats = &priv->netdev->stats; stats->tx_packets++; From eafcf1b5997ece092e6edc168686538e99303959 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Mon, 10 Oct 2022 20:52:28 +0200 Subject: [PATCH 0198/4345] can: kvaser_usb: kvaser_usb_leaf: Get capabilities from device [ Upstream commit 35364f5b41a4917fe94a3f393d149b63ec583297 ] Use the CMD_GET_CAPABILITIES_REQ command to query the device for certain capabilities. We are only interested in LISTENONLY mode and wither the device reports CAN error counters. Fixes: 080f40a6fa28 ("can: kvaser_usb: Add support for Kvaser CAN/USB devices") Reported-by: Anssi Hannula Tested-by: Anssi Hannula Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/all/20221010185237.319219-3-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- .../net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 144 +++++++++++++++++- 1 file changed, 143 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 15380cc08ee6..26f32828f905 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -73,6 +73,8 @@ #define CMD_TX_ACKNOWLEDGE 50 #define CMD_CAN_ERROR_EVENT 51 #define CMD_FLUSH_QUEUE_REPLY 68 +#define CMD_GET_CAPABILITIES_REQ 95 +#define CMD_GET_CAPABILITIES_RESP 96 #define CMD_LEAF_LOG_MESSAGE 106 @@ -82,6 +84,8 @@ #define KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK BIT(5) #define KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK BIT(6) +#define KVASER_USB_LEAF_SWOPTION_EXT_CAP BIT(12) + /* error factors */ #define M16C_EF_ACKE BIT(0) #define M16C_EF_CRCE BIT(1) @@ -277,6 +281,28 @@ struct leaf_cmd_log_message { u8 data[8]; } __packed; +/* Sub commands for cap_req and cap_res */ +#define KVASER_USB_LEAF_CAP_CMD_LISTEN_MODE 0x02 +#define KVASER_USB_LEAF_CAP_CMD_ERR_REPORT 0x05 +struct kvaser_cmd_cap_req { + __le16 padding0; + __le16 cap_cmd; + __le16 padding1; + __le16 channel; +} __packed; + +/* Status codes for cap_res */ +#define KVASER_USB_LEAF_CAP_STAT_OK 0x00 +#define KVASER_USB_LEAF_CAP_STAT_NOT_IMPL 0x01 +#define KVASER_USB_LEAF_CAP_STAT_UNAVAIL 0x02 +struct kvaser_cmd_cap_res { + __le16 padding; + __le16 cap_cmd; + __le16 status; + __le32 mask; + __le32 value; +} __packed; + struct kvaser_cmd { u8 len; u8 id; @@ -294,6 +320,8 @@ struct kvaser_cmd { struct leaf_cmd_chip_state_event chip_state_event; struct leaf_cmd_error_event error_event; struct leaf_cmd_log_message log_message; + struct kvaser_cmd_cap_req cap_req; + struct kvaser_cmd_cap_res cap_res; } __packed leaf; union { @@ -323,6 +351,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_leaf[] = { [CMD_LEAF_LOG_MESSAGE] = kvaser_fsize(u.leaf.log_message), [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.leaf.chip_state_event), [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.leaf.error_event), + [CMD_GET_CAPABILITIES_RESP] = kvaser_fsize(u.leaf.cap_res), /* ignored events: */ [CMD_FLUSH_QUEUE_REPLY] = CMD_SIZE_ANY, }; @@ -607,6 +636,9 @@ static void kvaser_usb_leaf_get_software_info_leaf(struct kvaser_usb *dev, dev->fw_version = le32_to_cpu(softinfo->fw_version); dev->max_tx_urbs = le16_to_cpu(softinfo->max_outstanding_tx); + if (sw_options & KVASER_USB_LEAF_SWOPTION_EXT_CAP) + dev->card_data.capabilities |= KVASER_USB_CAP_EXT_CAP; + if (dev->driver_info->quirks & KVASER_USB_QUIRK_IGNORE_CLK_FREQ) { /* Firmware expects bittiming parameters calculated for 16MHz * clock, regardless of the actual clock @@ -694,6 +726,116 @@ static int kvaser_usb_leaf_get_card_info(struct kvaser_usb *dev) return 0; } +static int kvaser_usb_leaf_get_single_capability(struct kvaser_usb *dev, + u16 cap_cmd_req, u16 *status) +{ + struct kvaser_usb_dev_card_data *card_data = &dev->card_data; + struct kvaser_cmd *cmd; + u32 value = 0; + u32 mask = 0; + u16 cap_cmd_res; + int err; + int i; + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->id = CMD_GET_CAPABILITIES_REQ; + cmd->u.leaf.cap_req.cap_cmd = cpu_to_le16(cap_cmd_req); + cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_cap_req); + + err = kvaser_usb_send_cmd(dev, cmd, cmd->len); + if (err) + goto end; + + err = kvaser_usb_leaf_wait_cmd(dev, CMD_GET_CAPABILITIES_RESP, cmd); + if (err) + goto end; + + *status = le16_to_cpu(cmd->u.leaf.cap_res.status); + + if (*status != KVASER_USB_LEAF_CAP_STAT_OK) + goto end; + + cap_cmd_res = le16_to_cpu(cmd->u.leaf.cap_res.cap_cmd); + switch (cap_cmd_res) { + case KVASER_USB_LEAF_CAP_CMD_LISTEN_MODE: + case KVASER_USB_LEAF_CAP_CMD_ERR_REPORT: + value = le32_to_cpu(cmd->u.leaf.cap_res.value); + mask = le32_to_cpu(cmd->u.leaf.cap_res.mask); + break; + default: + dev_warn(&dev->intf->dev, "Unknown capability command %u\n", + cap_cmd_res); + break; + } + + for (i = 0; i < dev->nchannels; i++) { + if (BIT(i) & (value & mask)) { + switch (cap_cmd_res) { + case KVASER_USB_LEAF_CAP_CMD_LISTEN_MODE: + card_data->ctrlmode_supported |= + CAN_CTRLMODE_LISTENONLY; + break; + case KVASER_USB_LEAF_CAP_CMD_ERR_REPORT: + card_data->capabilities |= + KVASER_USB_CAP_BERR_CAP; + break; + } + } + } + +end: + kfree(cmd); + + return err; +} + +static int kvaser_usb_leaf_get_capabilities_leaf(struct kvaser_usb *dev) +{ + int err; + u16 status; + + if (!(dev->card_data.capabilities & KVASER_USB_CAP_EXT_CAP)) { + dev_info(&dev->intf->dev, + "No extended capability support. Upgrade device firmware.\n"); + return 0; + } + + err = kvaser_usb_leaf_get_single_capability(dev, + KVASER_USB_LEAF_CAP_CMD_LISTEN_MODE, + &status); + if (err) + return err; + if (status) + dev_info(&dev->intf->dev, + "KVASER_USB_LEAF_CAP_CMD_LISTEN_MODE failed %u\n", + status); + + err = kvaser_usb_leaf_get_single_capability(dev, + KVASER_USB_LEAF_CAP_CMD_ERR_REPORT, + &status); + if (err) + return err; + if (status) + dev_info(&dev->intf->dev, + "KVASER_USB_LEAF_CAP_CMD_ERR_REPORT failed %u\n", + status); + + return 0; +} + +static int kvaser_usb_leaf_get_capabilities(struct kvaser_usb *dev) +{ + int err = 0; + + if (dev->driver_info->family == KVASER_LEAF) + err = kvaser_usb_leaf_get_capabilities_leaf(dev); + + return err; +} + static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, const struct kvaser_cmd *cmd) { @@ -1490,7 +1632,7 @@ const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = { .dev_get_software_info = kvaser_usb_leaf_get_software_info, .dev_get_software_details = NULL, .dev_get_card_info = kvaser_usb_leaf_get_card_info, - .dev_get_capabilities = NULL, + .dev_get_capabilities = kvaser_usb_leaf_get_capabilities, .dev_set_opt_mode = kvaser_usb_leaf_set_opt_mode, .dev_start_chip = kvaser_usb_leaf_start_chip, .dev_stop_chip = kvaser_usb_leaf_stop_chip, From caea629409dc4d2676d345fb460021a5c8127538 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Mon, 10 Oct 2022 20:52:29 +0200 Subject: [PATCH 0199/4345] can: kvaser_usb: kvaser_usb_leaf: Rename {leaf,usbcan}_cmd_error_event to {leaf,usbcan}_cmd_can_error_event [ Upstream commit 7ea56128dbf904a3359bcf9289cccdfa3c85c7e8 ] Prepare for handling CMD_ERROR_EVENT. Rename struct {leaf,usbcan}_cmd_error_event to {leaf,usbcan}_cmd_can_error_event. Fixes: 080f40a6fa28 ("can: kvaser_usb: Add support for Kvaser CAN/USB devices") Reported-by: Anssi Hannula Tested-by: Anssi Hannula Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/all/20221010185237.319219-4-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- .../net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 38 +++++++++---------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 26f32828f905..4f3d1150b2b2 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -233,7 +233,7 @@ struct kvaser_cmd_tx_acknowledge_header { u8 tid; } __packed; -struct leaf_cmd_error_event { +struct leaf_cmd_can_error_event { u8 tid; u8 flags; __le16 time[3]; @@ -245,7 +245,7 @@ struct leaf_cmd_error_event { u8 error_factor; } __packed; -struct usbcan_cmd_error_event { +struct usbcan_cmd_can_error_event { u8 tid; u8 padding; u8 tx_errors_count_ch0; @@ -318,7 +318,7 @@ struct kvaser_cmd { struct leaf_cmd_softinfo softinfo; struct leaf_cmd_rx_can rx_can; struct leaf_cmd_chip_state_event chip_state_event; - struct leaf_cmd_error_event error_event; + struct leaf_cmd_can_error_event can_error_event; struct leaf_cmd_log_message log_message; struct kvaser_cmd_cap_req cap_req; struct kvaser_cmd_cap_res cap_res; @@ -328,7 +328,7 @@ struct kvaser_cmd { struct usbcan_cmd_softinfo softinfo; struct usbcan_cmd_rx_can rx_can; struct usbcan_cmd_chip_state_event chip_state_event; - struct usbcan_cmd_error_event error_event; + struct usbcan_cmd_can_error_event can_error_event; } __packed usbcan; struct kvaser_cmd_tx_can tx_can; @@ -350,7 +350,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_leaf[] = { [CMD_RX_EXT_MESSAGE] = kvaser_fsize(u.leaf.rx_can), [CMD_LEAF_LOG_MESSAGE] = kvaser_fsize(u.leaf.log_message), [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.leaf.chip_state_event), - [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.leaf.error_event), + [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.leaf.can_error_event), [CMD_GET_CAPABILITIES_RESP] = kvaser_fsize(u.leaf.cap_res), /* ignored events: */ [CMD_FLUSH_QUEUE_REPLY] = CMD_SIZE_ANY, @@ -365,7 +365,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = { [CMD_RX_STD_MESSAGE] = kvaser_fsize(u.usbcan.rx_can), [CMD_RX_EXT_MESSAGE] = kvaser_fsize(u.usbcan.rx_can), [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.usbcan.chip_state_event), - [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.usbcan.error_event), + [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.usbcan.can_error_event), /* ignored events: */ [CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = CMD_SIZE_ANY, }; @@ -1137,11 +1137,11 @@ static void kvaser_usb_leaf_usbcan_rx_error(const struct kvaser_usb *dev, case CMD_CAN_ERROR_EVENT: es.channel = 0; - es.status = cmd->u.usbcan.error_event.status_ch0; - es.txerr = cmd->u.usbcan.error_event.tx_errors_count_ch0; - es.rxerr = cmd->u.usbcan.error_event.rx_errors_count_ch0; + es.status = cmd->u.usbcan.can_error_event.status_ch0; + es.txerr = cmd->u.usbcan.can_error_event.tx_errors_count_ch0; + es.rxerr = cmd->u.usbcan.can_error_event.rx_errors_count_ch0; es.usbcan.other_ch_status = - cmd->u.usbcan.error_event.status_ch1; + cmd->u.usbcan.can_error_event.status_ch1; kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es); /* The USBCAN firmware supports up to 2 channels. @@ -1149,13 +1149,13 @@ static void kvaser_usb_leaf_usbcan_rx_error(const struct kvaser_usb *dev, */ if (dev->nchannels == MAX_USBCAN_NET_DEVICES) { es.channel = 1; - es.status = cmd->u.usbcan.error_event.status_ch1; + es.status = cmd->u.usbcan.can_error_event.status_ch1; es.txerr = - cmd->u.usbcan.error_event.tx_errors_count_ch1; + cmd->u.usbcan.can_error_event.tx_errors_count_ch1; es.rxerr = - cmd->u.usbcan.error_event.rx_errors_count_ch1; + cmd->u.usbcan.can_error_event.rx_errors_count_ch1; es.usbcan.other_ch_status = - cmd->u.usbcan.error_event.status_ch0; + cmd->u.usbcan.can_error_event.status_ch0; kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es); } break; @@ -1172,11 +1172,11 @@ static void kvaser_usb_leaf_leaf_rx_error(const struct kvaser_usb *dev, switch (cmd->id) { case CMD_CAN_ERROR_EVENT: - es.channel = cmd->u.leaf.error_event.channel; - es.status = cmd->u.leaf.error_event.status; - es.txerr = cmd->u.leaf.error_event.tx_errors_count; - es.rxerr = cmd->u.leaf.error_event.rx_errors_count; - es.leaf.error_factor = cmd->u.leaf.error_event.error_factor; + es.channel = cmd->u.leaf.can_error_event.channel; + es.status = cmd->u.leaf.can_error_event.status; + es.txerr = cmd->u.leaf.can_error_event.tx_errors_count; + es.rxerr = cmd->u.leaf.can_error_event.rx_errors_count; + es.leaf.error_factor = cmd->u.leaf.can_error_event.error_factor; break; case CMD_LEAF_LOG_MESSAGE: es.channel = cmd->u.leaf.log_message.channel; From 96af45b1b46ea57c4781f7788128e31f8be72fcd Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Mon, 10 Oct 2022 20:52:30 +0200 Subject: [PATCH 0200/4345] can: kvaser_usb: kvaser_usb_leaf: Handle CMD_ERROR_EVENT [ Upstream commit b24cb2d169e0c9dce664a959e1f2aa9781285dc9 ] The device will send an error event command, to indicate certain errors. This indicates a misbehaving driver, and should never occur. Fixes: 080f40a6fa28 ("can: kvaser_usb: Add support for Kvaser CAN/USB devices") Tested-by: Anssi Hannula Co-developed-by: Anssi Hannula Signed-off-by: Anssi Hannula Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/all/20221010185237.319219-5-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- .../net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 99 +++++++++++++++++++ 1 file changed, 99 insertions(+) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 4f3d1150b2b2..3c3e78992b55 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -69,6 +69,7 @@ #define CMD_GET_CARD_INFO_REPLY 35 #define CMD_GET_SOFTWARE_INFO 38 #define CMD_GET_SOFTWARE_INFO_REPLY 39 +#define CMD_ERROR_EVENT 45 #define CMD_FLUSH_QUEUE 48 #define CMD_TX_ACKNOWLEDGE 50 #define CMD_CAN_ERROR_EVENT 51 @@ -257,6 +258,28 @@ struct usbcan_cmd_can_error_event { __le16 time; } __packed; +/* CMD_ERROR_EVENT error codes */ +#define KVASER_USB_LEAF_ERROR_EVENT_TX_QUEUE_FULL 0x8 +#define KVASER_USB_LEAF_ERROR_EVENT_PARAM 0x9 + +struct leaf_cmd_error_event { + u8 tid; + u8 error_code; + __le16 timestamp[3]; + __le16 padding; + __le16 info1; + __le16 info2; +} __packed; + +struct usbcan_cmd_error_event { + u8 tid; + u8 error_code; + __le16 info1; + __le16 info2; + __le16 timestamp; + __le16 padding; +} __packed; + struct kvaser_cmd_ctrl_mode { u8 tid; u8 channel; @@ -320,6 +343,7 @@ struct kvaser_cmd { struct leaf_cmd_chip_state_event chip_state_event; struct leaf_cmd_can_error_event can_error_event; struct leaf_cmd_log_message log_message; + struct leaf_cmd_error_event error_event; struct kvaser_cmd_cap_req cap_req; struct kvaser_cmd_cap_res cap_res; } __packed leaf; @@ -329,6 +353,7 @@ struct kvaser_cmd { struct usbcan_cmd_rx_can rx_can; struct usbcan_cmd_chip_state_event chip_state_event; struct usbcan_cmd_can_error_event can_error_event; + struct usbcan_cmd_error_event error_event; } __packed usbcan; struct kvaser_cmd_tx_can tx_can; @@ -352,6 +377,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_leaf[] = { [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.leaf.chip_state_event), [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.leaf.can_error_event), [CMD_GET_CAPABILITIES_RESP] = kvaser_fsize(u.leaf.cap_res), + [CMD_ERROR_EVENT] = kvaser_fsize(u.leaf.error_event), /* ignored events: */ [CMD_FLUSH_QUEUE_REPLY] = CMD_SIZE_ANY, }; @@ -366,6 +392,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = { [CMD_RX_EXT_MESSAGE] = kvaser_fsize(u.usbcan.rx_can), [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.usbcan.chip_state_event), [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.usbcan.can_error_event), + [CMD_ERROR_EVENT] = kvaser_fsize(u.usbcan.error_event), /* ignored events: */ [CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = CMD_SIZE_ANY, }; @@ -1308,6 +1335,74 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev, netif_rx(skb); } +static void kvaser_usb_leaf_error_event_parameter(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + u16 info1 = 0; + + switch (dev->driver_info->family) { + case KVASER_LEAF: + info1 = le16_to_cpu(cmd->u.leaf.error_event.info1); + break; + case KVASER_USBCAN: + info1 = le16_to_cpu(cmd->u.usbcan.error_event.info1); + break; + } + + /* info1 will contain the offending cmd_no */ + switch (info1) { + case CMD_SET_CTRL_MODE: + dev_warn(&dev->intf->dev, + "CMD_SET_CTRL_MODE error in parameter\n"); + break; + + case CMD_SET_BUS_PARAMS: + dev_warn(&dev->intf->dev, + "CMD_SET_BUS_PARAMS error in parameter\n"); + break; + + default: + dev_warn(&dev->intf->dev, + "Unhandled parameter error event cmd_no (%u)\n", + info1); + break; + } +} + +static void kvaser_usb_leaf_error_event(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + u8 error_code = 0; + + switch (dev->driver_info->family) { + case KVASER_LEAF: + error_code = cmd->u.leaf.error_event.error_code; + break; + case KVASER_USBCAN: + error_code = cmd->u.usbcan.error_event.error_code; + break; + } + + switch (error_code) { + case KVASER_USB_LEAF_ERROR_EVENT_TX_QUEUE_FULL: + /* Received additional CAN message, when firmware TX queue is + * already full. Something is wrong with the driver. + * This should never happen! + */ + dev_err(&dev->intf->dev, + "Received error event TX_QUEUE_FULL\n"); + break; + case KVASER_USB_LEAF_ERROR_EVENT_PARAM: + kvaser_usb_leaf_error_event_parameter(dev, cmd); + break; + + default: + dev_warn(&dev->intf->dev, + "Unhandled error event (%d)\n", error_code); + break; + } +} + static void kvaser_usb_leaf_start_chip_reply(const struct kvaser_usb *dev, const struct kvaser_cmd *cmd) { @@ -1386,6 +1481,10 @@ static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev, kvaser_usb_leaf_tx_acknowledge(dev, cmd); break; + case CMD_ERROR_EVENT: + kvaser_usb_leaf_error_event(dev, cmd); + break; + /* Ignored commands */ case CMD_USBCAN_CLOCK_OVERFLOW_EVENT: if (dev->driver_info->family != KVASER_USBCAN) From fbd155fe14c83f489c2ca33607ead0474530805a Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 10 Oct 2022 20:52:31 +0200 Subject: [PATCH 0201/4345] can: kvaser_usb_leaf: Set Warning state even without bus errors [ Upstream commit df1b7af2761b935f63b4a53e789d41ed859edf61 ] kvaser_usb_leaf_rx_error_update_can_state() sets error state according to error counters when the hardware does not indicate a specific state directly. However, this is currently gated behind a check for M16C_STATE_BUS_ERROR which does not always seem to be set when error counters are increasing, and may not be set when error counters are decreasing. This causes the CAN_STATE_ERROR_WARNING state to not be set in some cases even when appropriate. Change the code to set error state from counters even without M16C_STATE_BUS_ERROR. The Error-Passive case seems superfluous as it is already set via M16C_STATE_BUS_PASSIVE flag above, but it is kept for now. Tested with 0bfd:0124 Kvaser Mini PCI Express 2xHS FW 4.18.778. Fixes: 080f40a6fa28 ("can: kvaser_usb: Add support for Kvaser CAN/USB devices") Tested-by: Jimmy Assarsson Signed-off-by: Anssi Hannula Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/all/20221010185237.319219-6-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- .../net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 20 ++++++++----------- 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 3c3e78992b55..b43631eaccf1 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -965,20 +965,16 @@ kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv, new_state = CAN_STATE_BUS_OFF; } else if (es->status & M16C_STATE_BUS_PASSIVE) { new_state = CAN_STATE_ERROR_PASSIVE; - } else if (es->status & M16C_STATE_BUS_ERROR) { + } else if ((es->status & M16C_STATE_BUS_ERROR) && + cur_state >= CAN_STATE_BUS_OFF) { /* Guard against spurious error events after a busoff */ - if (cur_state < CAN_STATE_BUS_OFF) { - if (es->txerr >= 128 || es->rxerr >= 128) - new_state = CAN_STATE_ERROR_PASSIVE; - else if (es->txerr >= 96 || es->rxerr >= 96) - new_state = CAN_STATE_ERROR_WARNING; - else if (cur_state > CAN_STATE_ERROR_ACTIVE) - new_state = CAN_STATE_ERROR_ACTIVE; - } - } - - if (!es->status) + } else if (es->txerr >= 128 || es->rxerr >= 128) { + new_state = CAN_STATE_ERROR_PASSIVE; + } else if (es->txerr >= 96 || es->rxerr >= 96) { + new_state = CAN_STATE_ERROR_WARNING; + } else { new_state = CAN_STATE_ERROR_ACTIVE; + } if (new_state != cur_state) { tx_state = (es->txerr >= es->rxerr) ? new_state : 0; From f83742285f779806e095dac23b6942dfb4a7ed49 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 10 Oct 2022 20:52:32 +0200 Subject: [PATCH 0202/4345] can: kvaser_usb_leaf: Fix improved state not being reported [ Upstream commit 8d21f5927ae604881f98587fabf6753f88730968 ] The tested 0bfd:0017 Kvaser Memorator Professional HS/HS FW 2.0.50 and 0bfd:0124 Kvaser Mini PCI Express 2xHS FW 4.18.778 do not seem to send any unsolicited events when error counters decrease or when the device transitions from ERROR_PASSIVE to ERROR_ACTIVE (or WARNING). This causes the interface to e.g. indefinitely stay in the ERROR_PASSIVE state. Fix that by asking for chip state (inc. counters) event every 0.5 secs when error counters are non-zero. Since there are non-error-counter devices, also always poll in ERROR_PASSIVE even if the counters show zero. Fixes: 080f40a6fa28 ("can: kvaser_usb: Add support for Kvaser CAN/USB devices") Tested-by: Jimmy Assarsson Signed-off-by: Anssi Hannula Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/all/20221010185237.319219-7-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/usb/kvaser_usb/kvaser_usb.h | 7 +++ .../net/can/usb/kvaser_usb/kvaser_usb_core.c | 19 +++++- .../net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 58 +++++++++++++++++++ 3 files changed, 81 insertions(+), 3 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h index 62958f04a2f2..1f4583f1dae2 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h @@ -104,6 +104,9 @@ struct kvaser_usb_net_priv { struct can_priv can; struct can_berr_counter bec; + /* subdriver-specific data */ + void *sub_priv; + struct kvaser_usb *dev; struct net_device *netdev; int channel; @@ -125,6 +128,8 @@ struct kvaser_usb_net_priv { * * @dev_setup_endpoints: setup USB in and out endpoints * @dev_init_card: initialize card + * @dev_init_channel: initialize channel + * @dev_remove_channel: uninitialize channel * @dev_get_software_info: get software info * @dev_get_software_details: get software details * @dev_get_card_info: get card info @@ -146,6 +151,8 @@ struct kvaser_usb_dev_ops { struct can_berr_counter *bec); int (*dev_setup_endpoints)(struct kvaser_usb *dev); int (*dev_init_card)(struct kvaser_usb *dev); + int (*dev_init_channel)(struct kvaser_usb_net_priv *priv); + void (*dev_remove_channel)(struct kvaser_usb_net_priv *priv); int (*dev_get_software_info)(struct kvaser_usb *dev); int (*dev_get_software_details)(struct kvaser_usb *dev); int (*dev_get_card_info)(struct kvaser_usb *dev); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 7491f85e85b3..2c816d8929da 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -645,6 +645,7 @@ static const struct net_device_ops kvaser_usb_netdev_ops = { static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev) { + const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops; int i; for (i = 0; i < dev->nchannels; i++) { @@ -660,6 +661,9 @@ static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev) if (!dev->nets[i]) continue; + if (ops->dev_remove_channel) + ops->dev_remove_channel(dev->nets[i]); + free_candev(dev->nets[i]->netdev); } } @@ -727,17 +731,26 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel) dev->nets[channel] = priv; + if (ops->dev_init_channel) { + err = ops->dev_init_channel(priv); + if (err) + goto err; + } + err = register_candev(netdev); if (err) { dev_err(&dev->intf->dev, "Failed to register CAN device\n"); - free_candev(netdev); - dev->nets[channel] = NULL; - return err; + goto err; } netdev_dbg(netdev, "device registered\n"); return 0; + +err: + free_candev(netdev); + dev->nets[channel] = NULL; + return err; } static int kvaser_usb_probe(struct usb_interface *intf, diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index b43631eaccf1..6d45ae6f2a08 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -55,6 +56,7 @@ #define CMD_RX_EXT_MESSAGE 14 #define CMD_TX_EXT_MESSAGE 15 #define CMD_SET_BUS_PARAMS 16 +#define CMD_GET_CHIP_STATE 19 #define CMD_CHIP_STATE_EVENT 20 #define CMD_SET_CTRL_MODE 21 #define CMD_RESET_CHIP 24 @@ -420,6 +422,12 @@ struct kvaser_usb_err_summary { }; }; +struct kvaser_usb_net_leaf_priv { + struct kvaser_usb_net_priv *net; + + struct delayed_work chip_state_req_work; +}; + static const struct can_bittiming_const kvaser_usb_leaf_m16c_bittiming_const = { .name = "kvaser_usb_ucii", .tseg1_min = 4, @@ -947,6 +955,16 @@ static int kvaser_usb_leaf_simple_cmd_async(struct kvaser_usb_net_priv *priv, return err; } +static void kvaser_usb_leaf_chip_state_req_work(struct work_struct *work) +{ + struct kvaser_usb_net_leaf_priv *leaf = + container_of(work, struct kvaser_usb_net_leaf_priv, + chip_state_req_work.work); + struct kvaser_usb_net_priv *priv = leaf->net; + + kvaser_usb_leaf_simple_cmd_async(priv, CMD_GET_CHIP_STATE); +} + static void kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv, const struct kvaser_usb_err_summary *es, @@ -1018,6 +1036,7 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, struct sk_buff *skb; struct net_device_stats *stats; struct kvaser_usb_net_priv *priv; + struct kvaser_usb_net_leaf_priv *leaf; enum can_state old_state, new_state; if (es->channel >= dev->nchannels) { @@ -1027,6 +1046,7 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, } priv = dev->nets[es->channel]; + leaf = priv->sub_priv; stats = &priv->netdev->stats; /* Update all of the CAN interface's state and error counters before @@ -1043,6 +1063,14 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, kvaser_usb_leaf_rx_error_update_can_state(priv, es, &tmp_cf); new_state = priv->can.state; + /* If there are errors, request status updates periodically as we do + * not get automatic notifications of improved state. + */ + if (new_state < CAN_STATE_BUS_OFF && + (es->rxerr || es->txerr || new_state == CAN_STATE_ERROR_PASSIVE)) + schedule_delayed_work(&leaf->chip_state_req_work, + msecs_to_jiffies(500)); + skb = alloc_can_err_skb(priv->netdev, &cf); if (!skb) { stats->rx_dropped++; @@ -1577,10 +1605,13 @@ static int kvaser_usb_leaf_start_chip(struct kvaser_usb_net_priv *priv) static int kvaser_usb_leaf_stop_chip(struct kvaser_usb_net_priv *priv) { + struct kvaser_usb_net_leaf_priv *leaf = priv->sub_priv; int err; reinit_completion(&priv->stop_comp); + cancel_delayed_work(&leaf->chip_state_req_work); + err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_STOP_CHIP, priv->channel); if (err) @@ -1627,6 +1658,31 @@ static int kvaser_usb_leaf_init_card(struct kvaser_usb *dev) return 0; } +static int kvaser_usb_leaf_init_channel(struct kvaser_usb_net_priv *priv) +{ + struct kvaser_usb_net_leaf_priv *leaf; + + leaf = devm_kzalloc(&priv->dev->intf->dev, sizeof(*leaf), GFP_KERNEL); + if (!leaf) + return -ENOMEM; + + leaf->net = priv; + INIT_DELAYED_WORK(&leaf->chip_state_req_work, + kvaser_usb_leaf_chip_state_req_work); + + priv->sub_priv = leaf; + + return 0; +} + +static void kvaser_usb_leaf_remove_channel(struct kvaser_usb_net_priv *priv) +{ + struct kvaser_usb_net_leaf_priv *leaf = priv->sub_priv; + + if (leaf) + cancel_delayed_work_sync(&leaf->chip_state_req_work); +} + static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev) { struct kvaser_usb_net_priv *priv = netdev_priv(netdev); @@ -1724,6 +1780,8 @@ const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = { .dev_get_berr_counter = kvaser_usb_leaf_get_berr_counter, .dev_setup_endpoints = kvaser_usb_leaf_setup_endpoints, .dev_init_card = kvaser_usb_leaf_init_card, + .dev_init_channel = kvaser_usb_leaf_init_channel, + .dev_remove_channel = kvaser_usb_leaf_remove_channel, .dev_get_software_info = kvaser_usb_leaf_get_software_info, .dev_get_software_details = NULL, .dev_get_card_info = kvaser_usb_leaf_get_card_info, From cd56718e7cb605754f3249a066cb6f3ea465cfa3 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 10 Oct 2022 20:52:33 +0200 Subject: [PATCH 0203/4345] can: kvaser_usb_leaf: Fix wrong CAN state after stopping [ Upstream commit a11249acf802341294557895d8e5f6aef080253f ] 0bfd:0124 Kvaser Mini PCI Express 2xHS FW 4.18.778 sends a CMD_CHIP_STATE_EVENT indicating bus-off after stopping the device, causing a stopped device to appear as CAN_STATE_BUS_OFF instead of CAN_STATE_STOPPED. Fix that by not handling error events on stopped devices. Fixes: 080f40a6fa28 ("can: kvaser_usb: Add support for Kvaser CAN/USB devices") Tested-by: Jimmy Assarsson Signed-off-by: Anssi Hannula Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/all/20221010185237.319219-8-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 6d45ae6f2a08..52ac6446634d 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -1049,6 +1049,10 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, leaf = priv->sub_priv; stats = &priv->netdev->stats; + /* Ignore e.g. state change to bus-off reported just after stopping */ + if (!netif_running(priv->netdev)) + return; + /* Update all of the CAN interface's state and error counters before * trying any memory allocation that can actually fail with -ENOMEM. * From a50ad6772f6f9255549112e3a463336cc4fa4f99 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 10 Oct 2022 20:52:35 +0200 Subject: [PATCH 0204/4345] can: kvaser_usb_leaf: Fix bogus restart events [ Upstream commit 90904d326269a38fe5dd895fb2db7c03199654c4 ] When auto-restart is enabled, the kvaser_usb_leaf driver considers transition from any state >= CAN_STATE_BUS_OFF as a bus-off recovery event (restart). However, these events may occur at interface startup time before kvaser_usb_open() has set the state to CAN_STATE_ERROR_ACTIVE, causing restarts counter to increase and CAN_ERR_RESTARTED to be sent despite no actual restart having occurred. Fix that by making the auto-restart condition checks more strict so that they only trigger when the interface was actually in the BUS_OFF state. Fixes: 080f40a6fa28 ("can: kvaser_usb: Add support for Kvaser CAN/USB devices") Tested-by: Jimmy Assarsson Signed-off-by: Anssi Hannula Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/all/20221010185237.319219-10-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 52ac6446634d..d1877ff2ff71 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -899,7 +899,7 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, context = &priv->tx_contexts[tid % dev->max_tx_urbs]; /* Sometimes the state change doesn't come after a bus-off event */ - if (priv->can.restart_ms && priv->can.state >= CAN_STATE_BUS_OFF) { + if (priv->can.restart_ms && priv->can.state == CAN_STATE_BUS_OFF) { struct sk_buff *skb; struct can_frame *cf; @@ -1002,7 +1002,7 @@ kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv, } if (priv->can.restart_ms && - cur_state >= CAN_STATE_BUS_OFF && + cur_state == CAN_STATE_BUS_OFF && new_state < CAN_STATE_BUS_OFF) priv->can.can_stats.restarts++; @@ -1092,7 +1092,7 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, } if (priv->can.restart_ms && - old_state >= CAN_STATE_BUS_OFF && + old_state == CAN_STATE_BUS_OFF && new_state < CAN_STATE_BUS_OFF) { cf->can_id |= CAN_ERR_RESTARTED; netif_carrier_on(priv->netdev); From 669bdf121fa47832866434e47c7673bba66fe82e Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Mon, 10 Oct 2022 20:52:36 +0200 Subject: [PATCH 0205/4345] can: kvaser_usb: Add struct kvaser_usb_busparams [ Upstream commit 00e5786177649c1e3110f9454fdd34e336597265 ] Add struct kvaser_usb_busparams containing the busparameters used in CMD_{SET,GET}_BUSPARAMS* commands. Tested-by: Anssi Hannula Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/all/20221010185237.319219-11-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Stable-dep-of: 39d3df6b0ea8 ("can: kvaser_usb: Compare requested bittiming parameters with actual parameters in do_set_{,data}_bittiming") Signed-off-by: Sasha Levin --- drivers/net/can/usb/kvaser_usb/kvaser_usb.h | 8 +++++ .../net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 32 +++++++------------ .../net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 18 ++++------- 3 files changed, 27 insertions(+), 31 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h index 1f4583f1dae2..cb8018723748 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h @@ -76,6 +76,14 @@ struct kvaser_usb_tx_urb_context { int dlc; }; +struct kvaser_usb_busparams { + __le32 bitrate; + u8 tseg1; + u8 tseg2; + u8 sjw; + u8 nsamples; +} __packed; + struct kvaser_usb { struct usb_device *udev; struct usb_interface *intf; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 9588efbfae71..72c37dc50b6b 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -193,17 +193,9 @@ struct kvaser_cmd_chip_state_event { #define KVASER_USB_HYDRA_BUS_MODE_CANFD_ISO 0x01 #define KVASER_USB_HYDRA_BUS_MODE_NONISO 0x02 struct kvaser_cmd_set_busparams { - __le32 bitrate; - u8 tseg1; - u8 tseg2; - u8 sjw; - u8 nsamples; + struct kvaser_usb_busparams busparams_arb; u8 reserved0[4]; - __le32 bitrate_d; - u8 tseg1_d; - u8 tseg2_d; - u8 sjw_d; - u8 nsamples_d; + struct kvaser_usb_busparams busparams_data; u8 canfd_mode; u8 reserved1[7]; } __packed; @@ -1515,11 +1507,11 @@ static int kvaser_usb_hydra_set_bittiming(struct net_device *netdev) return -ENOMEM; cmd->header.cmd_no = CMD_SET_BUSPARAMS_REQ; - cmd->set_busparams_req.bitrate = cpu_to_le32(bt->bitrate); - cmd->set_busparams_req.sjw = (u8)sjw; - cmd->set_busparams_req.tseg1 = (u8)tseg1; - cmd->set_busparams_req.tseg2 = (u8)tseg2; - cmd->set_busparams_req.nsamples = 1; + cmd->set_busparams_req.busparams_arb.bitrate = cpu_to_le32(bt->bitrate); + cmd->set_busparams_req.busparams_arb.sjw = (u8)sjw; + cmd->set_busparams_req.busparams_arb.tseg1 = (u8)tseg1; + cmd->set_busparams_req.busparams_arb.tseg2 = (u8)tseg2; + cmd->set_busparams_req.busparams_arb.nsamples = 1; kvaser_usb_hydra_set_cmd_dest_he (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); @@ -1549,11 +1541,11 @@ static int kvaser_usb_hydra_set_data_bittiming(struct net_device *netdev) return -ENOMEM; cmd->header.cmd_no = CMD_SET_BUSPARAMS_FD_REQ; - cmd->set_busparams_req.bitrate_d = cpu_to_le32(dbt->bitrate); - cmd->set_busparams_req.sjw_d = (u8)sjw; - cmd->set_busparams_req.tseg1_d = (u8)tseg1; - cmd->set_busparams_req.tseg2_d = (u8)tseg2; - cmd->set_busparams_req.nsamples_d = 1; + cmd->set_busparams_req.busparams_data.bitrate = cpu_to_le32(dbt->bitrate); + cmd->set_busparams_req.busparams_data.sjw = (u8)sjw; + cmd->set_busparams_req.busparams_data.tseg1 = (u8)tseg1; + cmd->set_busparams_req.busparams_data.tseg2 = (u8)tseg2; + cmd->set_busparams_req.busparams_data.nsamples = 1; if (priv->can.ctrlmode & CAN_CTRLMODE_FD) { if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index d1877ff2ff71..1e2f727a1efb 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -163,11 +163,7 @@ struct usbcan_cmd_softinfo { struct kvaser_cmd_busparams { u8 tid; u8 channel; - __le32 bitrate; - u8 tseg1; - u8 tseg2; - u8 sjw; - u8 no_samp; + struct kvaser_usb_busparams busparams; } __packed; struct kvaser_cmd_tx_can { @@ -1703,15 +1699,15 @@ static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev) cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_busparams); cmd->u.busparams.channel = priv->channel; cmd->u.busparams.tid = 0xff; - cmd->u.busparams.bitrate = cpu_to_le32(bt->bitrate); - cmd->u.busparams.sjw = bt->sjw; - cmd->u.busparams.tseg1 = bt->prop_seg + bt->phase_seg1; - cmd->u.busparams.tseg2 = bt->phase_seg2; + cmd->u.busparams.busparams.bitrate = cpu_to_le32(bt->bitrate); + cmd->u.busparams.busparams.sjw = bt->sjw; + cmd->u.busparams.busparams.tseg1 = bt->prop_seg + bt->phase_seg1; + cmd->u.busparams.busparams.tseg2 = bt->phase_seg2; if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) - cmd->u.busparams.no_samp = 3; + cmd->u.busparams.busparams.nsamples = 3; else - cmd->u.busparams.no_samp = 1; + cmd->u.busparams.busparams.nsamples = 1; rc = kvaser_usb_send_cmd(dev, cmd, cmd->len); From 1874f9143fbaccd10214b5a500e0c1e8717527e7 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Mon, 10 Oct 2022 20:52:37 +0200 Subject: [PATCH 0206/4345] can: kvaser_usb: Compare requested bittiming parameters with actual parameters in do_set_{,data}_bittiming [ Upstream commit 39d3df6b0ea80f9b515c632ca07b39b1c156edee ] The device will respond with a CMD_ERROR_EVENT command, with error_code KVASER_USB_{LEAF,HYDRA}_ERROR_EVENT_PARAM, if the CMD_SET_BUSPARAMS_REQ contains invalid bittiming parameters. However, this command does not contain any channel reference. To check if the CMD_SET_BUSPARAMS_REQ was successful, redback and compare the requested bittiming parameters with the device reported parameters. Fixes: 080f40a6fa28 ("can: kvaser_usb: Add support for Kvaser CAN/USB devices") Fixes: aec5fb2268b7 ("can: kvaser_usb: Add support for Kvaser USB hydra family") Tested-by: Anssi Hannula Co-developed-by: Anssi Hannula Signed-off-by: Anssi Hannula Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/all/20221010185237.319219-12-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/usb/kvaser_usb/kvaser_usb.h | 15 +- .../net/can/usb/kvaser_usb/kvaser_usb_core.c | 96 ++++++++++- .../net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 150 +++++++++++++++--- .../net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 64 ++++++-- 4 files changed, 284 insertions(+), 41 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h index cb8018723748..5699531f8787 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h @@ -119,9 +119,12 @@ struct kvaser_usb_net_priv { struct net_device *netdev; int channel; - struct completion start_comp, stop_comp, flush_comp; + struct completion start_comp, stop_comp, flush_comp, + get_busparams_comp; struct usb_anchor tx_submitted; + struct kvaser_usb_busparams busparams_nominal, busparams_data; + spinlock_t tx_contexts_lock; /* lock for active_tx_contexts */ int active_tx_contexts; struct kvaser_usb_tx_urb_context tx_contexts[]; @@ -131,7 +134,9 @@ struct kvaser_usb_net_priv { * struct kvaser_usb_dev_ops - Device specific functions * @dev_set_mode: used for can.do_set_mode * @dev_set_bittiming: used for can.do_set_bittiming + * @dev_get_busparams: readback arbitration busparams * @dev_set_data_bittiming: used for can.do_set_data_bittiming + * @dev_get_data_busparams: readback data busparams * @dev_get_berr_counter: used for can.do_get_berr_counter * * @dev_setup_endpoints: setup USB in and out endpoints @@ -153,8 +158,12 @@ struct kvaser_usb_net_priv { */ struct kvaser_usb_dev_ops { int (*dev_set_mode)(struct net_device *netdev, enum can_mode mode); - int (*dev_set_bittiming)(struct net_device *netdev); - int (*dev_set_data_bittiming)(struct net_device *netdev); + int (*dev_set_bittiming)(const struct net_device *netdev, + const struct kvaser_usb_busparams *busparams); + int (*dev_get_busparams)(struct kvaser_usb_net_priv *priv); + int (*dev_set_data_bittiming)(const struct net_device *netdev, + const struct kvaser_usb_busparams *busparams); + int (*dev_get_data_busparams)(struct kvaser_usb_net_priv *priv); int (*dev_get_berr_counter)(const struct net_device *netdev, struct can_berr_counter *bec); int (*dev_setup_endpoints)(struct kvaser_usb *dev); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 2c816d8929da..1f015b496a47 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -416,10 +416,6 @@ static int kvaser_usb_open(struct net_device *netdev) if (err) return err; - err = kvaser_usb_setup_rx_urbs(dev); - if (err) - goto error; - err = ops->dev_set_opt_mode(priv); if (err) goto error; @@ -510,6 +506,93 @@ static int kvaser_usb_close(struct net_device *netdev) return 0; } +static int kvaser_usb_set_bittiming(struct net_device *netdev) +{ + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + struct kvaser_usb *dev = priv->dev; + const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops; + struct can_bittiming *bt = &priv->can.bittiming; + + struct kvaser_usb_busparams busparams; + int tseg1 = bt->prop_seg + bt->phase_seg1; + int tseg2 = bt->phase_seg2; + int sjw = bt->sjw; + int err = -EOPNOTSUPP; + + busparams.bitrate = cpu_to_le32(bt->bitrate); + busparams.sjw = (u8)sjw; + busparams.tseg1 = (u8)tseg1; + busparams.tseg2 = (u8)tseg2; + if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) + busparams.nsamples = 3; + else + busparams.nsamples = 1; + + err = ops->dev_set_bittiming(netdev, &busparams); + if (err) + return err; + + err = kvaser_usb_setup_rx_urbs(priv->dev); + if (err) + return err; + + err = ops->dev_get_busparams(priv); + if (err) { + /* Treat EOPNOTSUPP as success */ + if (err == -EOPNOTSUPP) + err = 0; + return err; + } + + if (memcmp(&busparams, &priv->busparams_nominal, + sizeof(priv->busparams_nominal)) != 0) + err = -EINVAL; + + return err; +} + +static int kvaser_usb_set_data_bittiming(struct net_device *netdev) +{ + struct kvaser_usb_net_priv *priv = netdev_priv(netdev); + struct kvaser_usb *dev = priv->dev; + const struct kvaser_usb_dev_ops *ops = dev->driver_info->ops; + struct can_bittiming *dbt = &priv->can.data_bittiming; + + struct kvaser_usb_busparams busparams; + int tseg1 = dbt->prop_seg + dbt->phase_seg1; + int tseg2 = dbt->phase_seg2; + int sjw = dbt->sjw; + int err; + + if (!ops->dev_set_data_bittiming || + !ops->dev_get_data_busparams) + return -EOPNOTSUPP; + + busparams.bitrate = cpu_to_le32(dbt->bitrate); + busparams.sjw = (u8)sjw; + busparams.tseg1 = (u8)tseg1; + busparams.tseg2 = (u8)tseg2; + busparams.nsamples = 1; + + err = ops->dev_set_data_bittiming(netdev, &busparams); + if (err) + return err; + + err = kvaser_usb_setup_rx_urbs(priv->dev); + if (err) + return err; + + err = ops->dev_get_data_busparams(priv); + if (err) + return err; + + if (memcmp(&busparams, &priv->busparams_data, + sizeof(priv->busparams_data)) != 0) + err = -EINVAL; + + return err; +} + static void kvaser_usb_write_bulk_callback(struct urb *urb) { struct kvaser_usb_tx_urb_context *context = urb->context; @@ -695,6 +778,7 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel) init_completion(&priv->start_comp); init_completion(&priv->stop_comp); init_completion(&priv->flush_comp); + init_completion(&priv->get_busparams_comp); priv->can.ctrlmode_supported = 0; priv->dev = dev; @@ -707,7 +791,7 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel) priv->can.state = CAN_STATE_STOPPED; priv->can.clock.freq = dev->cfg->clock.freq; priv->can.bittiming_const = dev->cfg->bittiming_const; - priv->can.do_set_bittiming = ops->dev_set_bittiming; + priv->can.do_set_bittiming = kvaser_usb_set_bittiming; priv->can.do_set_mode = ops->dev_set_mode; if ((driver_info->quirks & KVASER_USB_QUIRK_HAS_TXRX_ERRORS) || (priv->dev->card_data.capabilities & KVASER_USB_CAP_BERR_CAP)) @@ -719,7 +803,7 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel) if (priv->can.ctrlmode_supported & CAN_CTRLMODE_FD) { priv->can.data_bittiming_const = dev->cfg->data_bittiming_const; - priv->can.do_set_data_bittiming = ops->dev_set_data_bittiming; + priv->can.do_set_data_bittiming = kvaser_usb_set_data_bittiming; } netdev->flags |= IFF_ECHO; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 72c37dc50b6b..2764fdd7e84b 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -43,6 +43,8 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_flexc; /* Minihydra command IDs */ #define CMD_SET_BUSPARAMS_REQ 16 +#define CMD_GET_BUSPARAMS_REQ 17 +#define CMD_GET_BUSPARAMS_RESP 18 #define CMD_GET_CHIP_STATE_REQ 19 #define CMD_CHIP_STATE_EVENT 20 #define CMD_SET_DRIVERMODE_REQ 21 @@ -193,13 +195,26 @@ struct kvaser_cmd_chip_state_event { #define KVASER_USB_HYDRA_BUS_MODE_CANFD_ISO 0x01 #define KVASER_USB_HYDRA_BUS_MODE_NONISO 0x02 struct kvaser_cmd_set_busparams { - struct kvaser_usb_busparams busparams_arb; + struct kvaser_usb_busparams busparams_nominal; u8 reserved0[4]; struct kvaser_usb_busparams busparams_data; u8 canfd_mode; u8 reserved1[7]; } __packed; +/* Busparam type */ +#define KVASER_USB_HYDRA_BUSPARAM_TYPE_CAN 0x00 +#define KVASER_USB_HYDRA_BUSPARAM_TYPE_CANFD 0x01 +struct kvaser_cmd_get_busparams_req { + u8 type; + u8 reserved[27]; +} __packed; + +struct kvaser_cmd_get_busparams_res { + struct kvaser_usb_busparams busparams; + u8 reserved[20]; +} __packed; + /* Ctrl modes */ #define KVASER_USB_HYDRA_CTRLMODE_NORMAL 0x01 #define KVASER_USB_HYDRA_CTRLMODE_LISTEN 0x02 @@ -270,6 +285,8 @@ struct kvaser_cmd { struct kvaser_cmd_error_event error_event; struct kvaser_cmd_set_busparams set_busparams_req; + struct kvaser_cmd_get_busparams_req get_busparams_req; + struct kvaser_cmd_get_busparams_res get_busparams_res; struct kvaser_cmd_chip_state_event chip_state_event; @@ -352,6 +369,10 @@ struct kvaser_cmd_ext { } __packed; } __packed; +struct kvaser_usb_net_hydra_priv { + int pending_get_busparams_type; +}; + static const struct can_bittiming_const kvaser_usb_hydra_kcan_bittiming_c = { .name = "kvaser_usb_kcan", .tseg1_min = 1, @@ -805,6 +826,39 @@ static void kvaser_usb_hydra_flush_queue_reply(const struct kvaser_usb *dev, complete(&priv->flush_comp); } +static void kvaser_usb_hydra_get_busparams_reply(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv; + struct kvaser_usb_net_hydra_priv *hydra; + + priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); + if (!priv) + return; + + hydra = priv->sub_priv; + if (!hydra) + return; + + switch (hydra->pending_get_busparams_type) { + case KVASER_USB_HYDRA_BUSPARAM_TYPE_CAN: + memcpy(&priv->busparams_nominal, &cmd->get_busparams_res.busparams, + sizeof(priv->busparams_nominal)); + break; + case KVASER_USB_HYDRA_BUSPARAM_TYPE_CANFD: + memcpy(&priv->busparams_data, &cmd->get_busparams_res.busparams, + sizeof(priv->busparams_nominal)); + break; + default: + dev_warn(&dev->intf->dev, "Unknown get_busparams_type %d\n", + hydra->pending_get_busparams_type); + break; + } + hydra->pending_get_busparams_type = -1; + + complete(&priv->get_busparams_comp); +} + static void kvaser_usb_hydra_bus_status_to_can_state(const struct kvaser_usb_net_priv *priv, u8 bus_status, @@ -1291,6 +1345,10 @@ static void kvaser_usb_hydra_handle_cmd_std(const struct kvaser_usb *dev, kvaser_usb_hydra_state_event(dev, cmd); break; + case CMD_GET_BUSPARAMS_RESP: + kvaser_usb_hydra_get_busparams_reply(dev, cmd); + break; + case CMD_ERROR_EVENT: kvaser_usb_hydra_error_event(dev, cmd); break; @@ -1491,15 +1549,58 @@ static int kvaser_usb_hydra_set_mode(struct net_device *netdev, return err; } -static int kvaser_usb_hydra_set_bittiming(struct net_device *netdev) +static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv, + int busparams_type) +{ + struct kvaser_usb *dev = priv->dev; + struct kvaser_usb_net_hydra_priv *hydra = priv->sub_priv; + struct kvaser_cmd *cmd; + int err; + + if (!hydra) + return -EINVAL; + + cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + cmd->header.cmd_no = CMD_GET_BUSPARAMS_REQ; + kvaser_usb_hydra_set_cmd_dest_he + (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); + kvaser_usb_hydra_set_cmd_transid + (cmd, kvaser_usb_hydra_get_next_transid(dev)); + cmd->get_busparams_req.type = busparams_type; + hydra->pending_get_busparams_type = busparams_type; + + reinit_completion(&priv->get_busparams_comp); + + err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + if (err) + return err; + + if (!wait_for_completion_timeout(&priv->get_busparams_comp, + msecs_to_jiffies(KVASER_USB_TIMEOUT))) + return -ETIMEDOUT; + + return err; +} + +static int kvaser_usb_hydra_get_nominal_busparams(struct kvaser_usb_net_priv *priv) +{ + return kvaser_usb_hydra_get_busparams(priv, KVASER_USB_HYDRA_BUSPARAM_TYPE_CAN); +} + +static int kvaser_usb_hydra_get_data_busparams(struct kvaser_usb_net_priv *priv) +{ + return kvaser_usb_hydra_get_busparams(priv, KVASER_USB_HYDRA_BUSPARAM_TYPE_CANFD); +} + +static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev, + const struct kvaser_usb_busparams *busparams) { struct kvaser_cmd *cmd; struct kvaser_usb_net_priv *priv = netdev_priv(netdev); - struct can_bittiming *bt = &priv->can.bittiming; struct kvaser_usb *dev = priv->dev; - int tseg1 = bt->prop_seg + bt->phase_seg1; - int tseg2 = bt->phase_seg2; - int sjw = bt->sjw; int err; cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); @@ -1507,11 +1608,8 @@ static int kvaser_usb_hydra_set_bittiming(struct net_device *netdev) return -ENOMEM; cmd->header.cmd_no = CMD_SET_BUSPARAMS_REQ; - cmd->set_busparams_req.busparams_arb.bitrate = cpu_to_le32(bt->bitrate); - cmd->set_busparams_req.busparams_arb.sjw = (u8)sjw; - cmd->set_busparams_req.busparams_arb.tseg1 = (u8)tseg1; - cmd->set_busparams_req.busparams_arb.tseg2 = (u8)tseg2; - cmd->set_busparams_req.busparams_arb.nsamples = 1; + memcpy(&cmd->set_busparams_req.busparams_nominal, busparams, + sizeof(cmd->set_busparams_req.busparams_nominal)); kvaser_usb_hydra_set_cmd_dest_he (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); @@ -1525,15 +1623,12 @@ static int kvaser_usb_hydra_set_bittiming(struct net_device *netdev) return err; } -static int kvaser_usb_hydra_set_data_bittiming(struct net_device *netdev) +static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev, + const struct kvaser_usb_busparams *busparams) { struct kvaser_cmd *cmd; struct kvaser_usb_net_priv *priv = netdev_priv(netdev); - struct can_bittiming *dbt = &priv->can.data_bittiming; struct kvaser_usb *dev = priv->dev; - int tseg1 = dbt->prop_seg + dbt->phase_seg1; - int tseg2 = dbt->phase_seg2; - int sjw = dbt->sjw; int err; cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); @@ -1541,11 +1636,8 @@ static int kvaser_usb_hydra_set_data_bittiming(struct net_device *netdev) return -ENOMEM; cmd->header.cmd_no = CMD_SET_BUSPARAMS_FD_REQ; - cmd->set_busparams_req.busparams_data.bitrate = cpu_to_le32(dbt->bitrate); - cmd->set_busparams_req.busparams_data.sjw = (u8)sjw; - cmd->set_busparams_req.busparams_data.tseg1 = (u8)tseg1; - cmd->set_busparams_req.busparams_data.tseg2 = (u8)tseg2; - cmd->set_busparams_req.busparams_data.nsamples = 1; + memcpy(&cmd->set_busparams_req.busparams_data, busparams, + sizeof(cmd->set_busparams_req.busparams_data)); if (priv->can.ctrlmode & CAN_CTRLMODE_FD) { if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) @@ -1652,6 +1744,19 @@ static int kvaser_usb_hydra_init_card(struct kvaser_usb *dev) return 0; } +static int kvaser_usb_hydra_init_channel(struct kvaser_usb_net_priv *priv) +{ + struct kvaser_usb_net_hydra_priv *hydra; + + hydra = devm_kzalloc(&priv->dev->intf->dev, sizeof(*hydra), GFP_KERNEL); + if (!hydra) + return -ENOMEM; + + priv->sub_priv = hydra; + + return 0; +} + static int kvaser_usb_hydra_get_software_info(struct kvaser_usb *dev) { struct kvaser_cmd cmd; @@ -1994,10 +2099,13 @@ kvaser_usb_hydra_frame_to_cmd(const struct kvaser_usb_net_priv *priv, const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops = { .dev_set_mode = kvaser_usb_hydra_set_mode, .dev_set_bittiming = kvaser_usb_hydra_set_bittiming, + .dev_get_busparams = kvaser_usb_hydra_get_nominal_busparams, .dev_set_data_bittiming = kvaser_usb_hydra_set_data_bittiming, + .dev_get_data_busparams = kvaser_usb_hydra_get_data_busparams, .dev_get_berr_counter = kvaser_usb_hydra_get_berr_counter, .dev_setup_endpoints = kvaser_usb_hydra_setup_endpoints, .dev_init_card = kvaser_usb_hydra_init_card, + .dev_init_channel = kvaser_usb_hydra_init_channel, .dev_get_software_info = kvaser_usb_hydra_get_software_info, .dev_get_software_details = kvaser_usb_hydra_get_software_details, .dev_get_card_info = kvaser_usb_hydra_get_card_info, diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 1e2f727a1efb..f06d63db9077 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -56,6 +56,8 @@ #define CMD_RX_EXT_MESSAGE 14 #define CMD_TX_EXT_MESSAGE 15 #define CMD_SET_BUS_PARAMS 16 +#define CMD_GET_BUS_PARAMS 17 +#define CMD_GET_BUS_PARAMS_REPLY 18 #define CMD_GET_CHIP_STATE 19 #define CMD_CHIP_STATE_EVENT 20 #define CMD_SET_CTRL_MODE 21 @@ -375,6 +377,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_leaf[] = { [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.leaf.chip_state_event), [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.leaf.can_error_event), [CMD_GET_CAPABILITIES_RESP] = kvaser_fsize(u.leaf.cap_res), + [CMD_GET_BUS_PARAMS_REPLY] = kvaser_fsize(u.busparams), [CMD_ERROR_EVENT] = kvaser_fsize(u.leaf.error_event), /* ignored events: */ [CMD_FLUSH_QUEUE_REPLY] = CMD_SIZE_ANY, @@ -1467,6 +1470,25 @@ static void kvaser_usb_leaf_stop_chip_reply(const struct kvaser_usb *dev, complete(&priv->stop_comp); } +static void kvaser_usb_leaf_get_busparams_reply(const struct kvaser_usb *dev, + const struct kvaser_cmd *cmd) +{ + struct kvaser_usb_net_priv *priv; + u8 channel = cmd->u.busparams.channel; + + if (channel >= dev->nchannels) { + dev_err(&dev->intf->dev, + "Invalid channel number (%d)\n", channel); + return; + } + + priv = dev->nets[channel]; + memcpy(&priv->busparams_nominal, &cmd->u.busparams.busparams, + sizeof(priv->busparams_nominal)); + + complete(&priv->get_busparams_comp); +} + static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev, const struct kvaser_cmd *cmd) { @@ -1509,6 +1531,10 @@ static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev, kvaser_usb_leaf_error_event(dev, cmd); break; + case CMD_GET_BUS_PARAMS_REPLY: + kvaser_usb_leaf_get_busparams_reply(dev, cmd); + break; + /* Ignored commands */ case CMD_USBCAN_CLOCK_OVERFLOW_EVENT: if (dev->driver_info->family != KVASER_USBCAN) @@ -1683,10 +1709,10 @@ static void kvaser_usb_leaf_remove_channel(struct kvaser_usb_net_priv *priv) cancel_delayed_work_sync(&leaf->chip_state_req_work); } -static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev) +static int kvaser_usb_leaf_set_bittiming(const struct net_device *netdev, + const struct kvaser_usb_busparams *busparams) { struct kvaser_usb_net_priv *priv = netdev_priv(netdev); - struct can_bittiming *bt = &priv->can.bittiming; struct kvaser_usb *dev = priv->dev; struct kvaser_cmd *cmd; int rc; @@ -1699,15 +1725,8 @@ static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev) cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_busparams); cmd->u.busparams.channel = priv->channel; cmd->u.busparams.tid = 0xff; - cmd->u.busparams.busparams.bitrate = cpu_to_le32(bt->bitrate); - cmd->u.busparams.busparams.sjw = bt->sjw; - cmd->u.busparams.busparams.tseg1 = bt->prop_seg + bt->phase_seg1; - cmd->u.busparams.busparams.tseg2 = bt->phase_seg2; - - if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) - cmd->u.busparams.busparams.nsamples = 3; - else - cmd->u.busparams.busparams.nsamples = 1; + memcpy(&cmd->u.busparams.busparams, busparams, + sizeof(cmd->u.busparams.busparams)); rc = kvaser_usb_send_cmd(dev, cmd, cmd->len); @@ -1715,6 +1734,27 @@ static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev) return rc; } +static int kvaser_usb_leaf_get_busparams(struct kvaser_usb_net_priv *priv) +{ + int err; + + if (priv->dev->driver_info->family == KVASER_USBCAN) + return -EOPNOTSUPP; + + reinit_completion(&priv->get_busparams_comp); + + err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_GET_BUS_PARAMS, + priv->channel); + if (err) + return err; + + if (!wait_for_completion_timeout(&priv->get_busparams_comp, + msecs_to_jiffies(KVASER_USB_TIMEOUT))) + return -ETIMEDOUT; + + return 0; +} + static int kvaser_usb_leaf_set_mode(struct net_device *netdev, enum can_mode mode) { @@ -1776,7 +1816,9 @@ static int kvaser_usb_leaf_setup_endpoints(struct kvaser_usb *dev) const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = { .dev_set_mode = kvaser_usb_leaf_set_mode, .dev_set_bittiming = kvaser_usb_leaf_set_bittiming, + .dev_get_busparams = kvaser_usb_leaf_get_busparams, .dev_set_data_bittiming = NULL, + .dev_get_data_busparams = NULL, .dev_get_berr_counter = kvaser_usb_leaf_get_berr_counter, .dev_setup_endpoints = kvaser_usb_leaf_setup_endpoints, .dev_init_card = kvaser_usb_leaf_init_card, From 110bf15825edf4f20bc4e56aba624297861b06ab Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Thu, 22 Sep 2022 21:21:07 +0800 Subject: [PATCH 0207/4345] drm/rockchip: lvds: fix PM usage counter unbalance in poweron [ Upstream commit 4dba27f1a14592ac4cf71c3bc1cc1fd05dea8015 ] pm_runtime_get_sync will increment pm usage counter even it failed. Forgetting to putting operation will result in reference leak here. We fix it by replacing it with the newest pm_runtime_resume_and_get to keep usage counter balanced. Fixes: 34cc0aa25456 ("drm/rockchip: Add support for Rockchip Soc LVDS") Fixes: cca1705c3d89 ("drm/rockchip: lvds: Add PX30 support") Signed-off-by: Zhang Qilong Signed-off-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/20220922132107.105419-3-zhangqilong3@huawei.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/rockchip/rockchip_lvds.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c index 7c20b4a24a7e..e2487937c4e3 100644 --- a/drivers/gpu/drm/rockchip/rockchip_lvds.c +++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c @@ -145,7 +145,7 @@ static int rk3288_lvds_poweron(struct rockchip_lvds *lvds) DRM_DEV_ERROR(lvds->dev, "failed to enable lvds pclk %d\n", ret); return ret; } - ret = pm_runtime_get_sync(lvds->dev); + ret = pm_runtime_resume_and_get(lvds->dev); if (ret < 0) { DRM_DEV_ERROR(lvds->dev, "failed to get pm runtime: %d\n", ret); clk_disable(lvds->pclk); @@ -329,16 +329,20 @@ static int px30_lvds_poweron(struct rockchip_lvds *lvds) { int ret; - ret = pm_runtime_get_sync(lvds->dev); + ret = pm_runtime_resume_and_get(lvds->dev); if (ret < 0) { DRM_DEV_ERROR(lvds->dev, "failed to get pm runtime: %d\n", ret); return ret; } /* Enable LVDS mode */ - return regmap_update_bits(lvds->grf, PX30_LVDS_GRF_PD_VO_CON1, + ret = regmap_update_bits(lvds->grf, PX30_LVDS_GRF_PD_VO_CON1, PX30_LVDS_MODE_EN(1) | PX30_LVDS_P2S_EN(1), PX30_LVDS_MODE_EN(1) | PX30_LVDS_P2S_EN(1)); + if (ret) + pm_runtime_put(lvds->dev); + + return ret; } static void px30_lvds_poweroff(struct rockchip_lvds *lvds) From dd958c7f3e77bcdafaa43c2d9ed16fa62fc11c82 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 28 Oct 2022 13:38:34 +0200 Subject: [PATCH 0208/4345] clk: renesas: r9a06g032: Repair grave increment error [ Upstream commit 02693e11611e082e3c4d8653e8af028e43d31164 ] If condition (clkspec.np != pd->dev.of_node) is true, then the driver ends up in an endless loop, forever, locking up the machine. Fixes: aad03a66f902 ("clk: renesas: r9a06g032: Add clock domain support") Reviewed-by: Ralph Siemsen Signed-off-by: Marek Vasut Reviewed-by: Gareth Williams Link: https://lore.kernel.org/r/20221028113834.7496-1-marex@denx.de Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- drivers/clk/renesas/r9a06g032-clocks.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c index 245150a5484a..285f6ac25372 100644 --- a/drivers/clk/renesas/r9a06g032-clocks.c +++ b/drivers/clk/renesas/r9a06g032-clocks.c @@ -386,7 +386,7 @@ static int r9a06g032_attach_dev(struct generic_pm_domain *pd, int error; int index; - while (!of_parse_phandle_with_args(np, "clocks", "#clock-cells", i, + while (!of_parse_phandle_with_args(np, "clocks", "#clock-cells", i++, &clkspec)) { if (clkspec.np != pd->dev.of_node) continue; @@ -399,7 +399,6 @@ static int r9a06g032_attach_dev(struct generic_pm_domain *pd, if (error) return error; } - i++; } return 0; From f1aa976857a310f38a420f4a65e9b007ae9272fd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Tue, 1 Nov 2022 18:32:51 +0100 Subject: [PATCH 0209/4345] spi: Update reference to struct spi_controller MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit bf585ccee22faf469d82727cf375868105b362f7 ] struct spi_master has been renamed to struct spi_controller. Update the reference in spi.rst to make it clickable again. Fixes: 8caab75fd2c2 ("spi: Generalize SPI "master" to "controller"") Signed-off-by: Jonathan Neuschäfer Link: https://lore.kernel.org/r/20221101173252.1069294-1-j.neuschaefer@gmx.net Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- Documentation/driver-api/spi.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/driver-api/spi.rst b/Documentation/driver-api/spi.rst index f64cb666498a..f28887045049 100644 --- a/Documentation/driver-api/spi.rst +++ b/Documentation/driver-api/spi.rst @@ -25,8 +25,8 @@ hardware, which may be as simple as a set of GPIO pins or as complex as a pair of FIFOs connected to dual DMA engines on the other side of the SPI shift register (maximizing throughput). Such drivers bridge between whatever bus they sit on (often the platform bus) and SPI, and expose -the SPI side of their device as a :c:type:`struct spi_master -`. SPI devices are children of that master, +the SPI side of their device as a :c:type:`struct spi_controller +`. SPI devices are children of that master, represented as a :c:type:`struct spi_device ` and manufactured from :c:type:`struct spi_board_info ` descriptors which are usually provided by From 576828e59a0e03bbc763872912b04f3e3a1b3311 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 15 Oct 2022 01:11:06 +0200 Subject: [PATCH 0210/4345] drm/panel/panel-sitronix-st7701: Remove panel on DSI attach failure [ Upstream commit c62102165dd79284d42383d2f7ed17301bd8e629 ] In case mipi_dsi_attach() fails, call drm_panel_remove() to avoid memory leak. Fixes: 849b2e3ff969 ("drm/panel: Add Sitronix ST7701 panel driver") Signed-off-by: Marek Vasut Signed-off-by: Linus Walleij Link: https://patchwork.freedesktop.org/patch/msgid/20221014231106.468063-1-marex@denx.de Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-sitronix-st7701.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c index 4d2a149b202c..cd9f01940b17 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c @@ -384,7 +384,15 @@ static int st7701_dsi_probe(struct mipi_dsi_device *dsi) st7701->dsi = dsi; st7701->desc = desc; - return mipi_dsi_attach(dsi); + ret = mipi_dsi_attach(dsi); + if (ret) + goto err_attach; + + return 0; + +err_attach: + drm_panel_remove(&st7701->panel); + return ret; } static int st7701_dsi_remove(struct mipi_dsi_device *dsi) From d5b227f0d28d629f6782b0dda091fd78fbcfbb1f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 20 Nov 2020 12:25:46 -0600 Subject: [PATCH 0211/4345] ima: Fix fall-through warnings for Clang [ Upstream commit 28073eb09c5aa29e879490edb88cfd3e7073821e ] In preparation to enable -Wimplicit-fallthrough for Clang, fix multiple warnings by explicitly adding multiple break statements instead of just letting the code fall through to the next case. Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva Signed-off-by: Mimi Zohar Stable-dep-of: c7423dbdbc9e ("ima: Handle -ESTALE returned by ima_filter_rule_match()") Signed-off-by: Sasha Levin --- security/integrity/ima/ima_main.c | 1 + security/integrity/ima/ima_policy.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 2d1af8899cab..600b97677085 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -743,6 +743,7 @@ int ima_load_data(enum kernel_load_data_id id, bool contents) pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } + break; default: break; } diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 18569adcb4fe..4c937ff2e4dd 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -566,6 +566,7 @@ static bool ima_match_rules(struct ima_rule_entry *rule, struct inode *inode, rc = ima_filter_rule_match(secid, rule->lsm[i].type, Audit_equal, rule->lsm[i].rule); + break; default: break; } @@ -802,6 +803,7 @@ void __init ima_init_policy(void) add_rules(default_measurement_rules, ARRAY_SIZE(default_measurement_rules), IMA_DEFAULT_POLICY); + break; default: break; } From c4b035b1f036ddd53fbfced49046e586c5ad8a3e Mon Sep 17 00:00:00 2001 From: GUO Zihua Date: Wed, 21 Sep 2022 20:58:04 +0800 Subject: [PATCH 0212/4345] ima: Handle -ESTALE returned by ima_filter_rule_match() [ Upstream commit c7423dbdbc9ecef7fff5239d144cad4b9887f4de ] IMA relies on the blocking LSM policy notifier callback to update the LSM based IMA policy rules. When SELinux update its policies, IMA would be notified and starts updating all its lsm rules one-by-one. During this time, -ESTALE would be returned by ima_filter_rule_match() if it is called with a LSM rule that has not yet been updated. In ima_match_rules(), -ESTALE is not handled, and the LSM rule is considered a match, causing extra files to be measured by IMA. Fix it by re-initializing a temporary rule if -ESTALE is returned by ima_filter_rule_match(). The origin rule in the rule list would be updated by the LSM policy notifier callback. Fixes: b16942455193 ("ima: use the lsm policy update notifier") Signed-off-by: GUO Zihua Reviewed-by: Roberto Sassu Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/ima/ima_policy.c | 41 ++++++++++++++++++++++------- 1 file changed, 32 insertions(+), 9 deletions(-) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 4c937ff2e4dd..a83ce111cf50 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -503,6 +503,9 @@ static bool ima_match_rules(struct ima_rule_entry *rule, struct inode *inode, const char *keyring) { int i; + bool result = false; + struct ima_rule_entry *lsm_rule = rule; + bool rule_reinitialized = false; if (func == KEY_CHECK) { return (rule->flags & IMA_FUNC) && (rule->func == func) && @@ -545,35 +548,55 @@ static bool ima_match_rules(struct ima_rule_entry *rule, struct inode *inode, int rc = 0; u32 osid; - if (!rule->lsm[i].rule) { - if (!rule->lsm[i].args_p) + if (!lsm_rule->lsm[i].rule) { + if (!lsm_rule->lsm[i].args_p) continue; else return false; } + +retry: switch (i) { case LSM_OBJ_USER: case LSM_OBJ_ROLE: case LSM_OBJ_TYPE: security_inode_getsecid(inode, &osid); - rc = ima_filter_rule_match(osid, rule->lsm[i].type, + rc = ima_filter_rule_match(osid, lsm_rule->lsm[i].type, Audit_equal, - rule->lsm[i].rule); + lsm_rule->lsm[i].rule); break; case LSM_SUBJ_USER: case LSM_SUBJ_ROLE: case LSM_SUBJ_TYPE: - rc = ima_filter_rule_match(secid, rule->lsm[i].type, + rc = ima_filter_rule_match(secid, lsm_rule->lsm[i].type, Audit_equal, - rule->lsm[i].rule); + lsm_rule->lsm[i].rule); break; default: break; } - if (!rc) - return false; + + if (rc == -ESTALE && !rule_reinitialized) { + lsm_rule = ima_lsm_copy_rule(rule); + if (lsm_rule) { + rule_reinitialized = true; + goto retry; + } + } + if (!rc) { + result = false; + goto out; + } } - return true; + result = true; + +out: + if (rule_reinitialized) { + for (i = 0; i < MAX_LSM_RULES; i++) + ima_filter_rule_free(lsm_rule->lsm[i].rule); + kfree(lsm_rule); + } + return result; } /* From b12f354fe61f8c2bf677ea82e1f366cc0ed47da8 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 15 Oct 2021 03:11:00 +0300 Subject: [PATCH 0213/4345] drm/msm/hdmi: switch to drm_bridge_connector [ Upstream commit caa24223463dfd75702a24daac13c93edb4aafac ] Merge old hdmi_bridge and hdmi_connector implementations. Use drm_bridge_connector instead. Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Link: https://lore.kernel.org/r/20211015001100.4193241-2-dmitry.baryshkov@linaro.org Signed-off-by: Dmitry Baryshkov Signed-off-by: Rob Clark Stable-dep-of: b964444b2b64 ("drm/msm/hdmi: use devres helper for runtime PM management") Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/Makefile | 2 +- drivers/gpu/drm/msm/hdmi/hdmi.c | 12 +- drivers/gpu/drm/msm/hdmi/hdmi.h | 19 ++- drivers/gpu/drm/msm/hdmi/hdmi_bridge.c | 81 ++++++++- .../msm/hdmi/{hdmi_connector.c => hdmi_hpd.c} | 154 ++---------------- 5 files changed, 109 insertions(+), 159 deletions(-) rename drivers/gpu/drm/msm/hdmi/{hdmi_connector.c => hdmi_hpd.c} (63%) diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 340682cd0f32..2457ef9851bb 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -19,7 +19,7 @@ msm-y := \ hdmi/hdmi.o \ hdmi/hdmi_audio.o \ hdmi/hdmi_bridge.o \ - hdmi/hdmi_connector.o \ + hdmi/hdmi_hpd.o \ hdmi/hdmi_i2c.o \ hdmi/hdmi_phy.o \ hdmi/hdmi_phy_8960.o \ diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index bd65dc9b8892..f6b09e8eca67 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -8,6 +8,8 @@ #include #include +#include + #include #include "hdmi.h" @@ -41,7 +43,7 @@ static irqreturn_t msm_hdmi_irq(int irq, void *dev_id) struct hdmi *hdmi = dev_id; /* Process HPD: */ - msm_hdmi_connector_irq(hdmi->connector); + msm_hdmi_hpd_irq(hdmi->bridge); /* Process DDC: */ msm_hdmi_i2c_irq(hdmi->i2c); @@ -311,7 +313,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, goto fail; } - hdmi->connector = msm_hdmi_connector_init(hdmi); + hdmi->connector = drm_bridge_connector_init(hdmi->dev, encoder); if (IS_ERR(hdmi->connector)) { ret = PTR_ERR(hdmi->connector); DRM_DEV_ERROR(dev->dev, "failed to create HDMI connector: %d\n", ret); @@ -319,6 +321,8 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, goto fail; } + drm_connector_attach_encoder(hdmi->connector, hdmi->encoder); + hdmi->irq = irq_of_parse_and_map(pdev->dev.of_node, 0); if (!hdmi->irq) { ret = -EINVAL; @@ -335,7 +339,9 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, goto fail; } - ret = msm_hdmi_hpd_enable(hdmi->connector); + drm_bridge_connector_enable_hpd(hdmi->connector); + + ret = msm_hdmi_hpd_enable(hdmi->bridge); if (ret < 0) { DRM_DEV_ERROR(&hdmi->pdev->dev, "failed to enable HPD: %d\n", ret); goto fail; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h index d0b84f0abee1..8d2706bec3b9 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.h @@ -114,6 +114,13 @@ struct hdmi_platform_config { struct hdmi_gpio_data gpios[HDMI_MAX_NUM_GPIO]; }; +struct hdmi_bridge { + struct drm_bridge base; + struct hdmi *hdmi; + struct work_struct hpd_work; +}; +#define to_hdmi_bridge(x) container_of(x, struct hdmi_bridge, base) + void msm_hdmi_set_mode(struct hdmi *hdmi, bool power_on); static inline void hdmi_write(struct hdmi *hdmi, u32 reg, u32 data) @@ -230,13 +237,11 @@ void msm_hdmi_audio_set_sample_rate(struct hdmi *hdmi, int rate); struct drm_bridge *msm_hdmi_bridge_init(struct hdmi *hdmi); void msm_hdmi_bridge_destroy(struct drm_bridge *bridge); -/* - * hdmi connector: - */ - -void msm_hdmi_connector_irq(struct drm_connector *connector); -struct drm_connector *msm_hdmi_connector_init(struct hdmi *hdmi); -int msm_hdmi_hpd_enable(struct drm_connector *connector); +void msm_hdmi_hpd_irq(struct drm_bridge *bridge); +enum drm_connector_status msm_hdmi_bridge_detect( + struct drm_bridge *bridge); +int msm_hdmi_hpd_enable(struct drm_bridge *bridge); +void msm_hdmi_hpd_disable(struct hdmi_bridge *hdmi_bridge); /* * i2c adapter for ddc: diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c index 6e380db9287b..efcfdd70a02e 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c @@ -5,17 +5,16 @@ */ #include +#include +#include "msm_kms.h" #include "hdmi.h" -struct hdmi_bridge { - struct drm_bridge base; - struct hdmi *hdmi; -}; -#define to_hdmi_bridge(x) container_of(x, struct hdmi_bridge, base) - void msm_hdmi_bridge_destroy(struct drm_bridge *bridge) { + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + + msm_hdmi_hpd_disable(hdmi_bridge); } static void msm_hdmi_power_on(struct drm_bridge *bridge) @@ -259,14 +258,76 @@ static void msm_hdmi_bridge_mode_set(struct drm_bridge *bridge, msm_hdmi_audio_update(hdmi); } +static struct edid *msm_hdmi_bridge_get_edid(struct drm_bridge *bridge, + struct drm_connector *connector) +{ + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + struct edid *edid; + uint32_t hdmi_ctrl; + + hdmi_ctrl = hdmi_read(hdmi, REG_HDMI_CTRL); + hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl | HDMI_CTRL_ENABLE); + + edid = drm_get_edid(connector, hdmi->i2c); + + hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl); + + hdmi->hdmi_mode = drm_detect_hdmi_monitor(edid); + + return edid; +} + +static enum drm_mode_status msm_hdmi_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + const struct hdmi_platform_config *config = hdmi->config; + struct msm_drm_private *priv = bridge->dev->dev_private; + struct msm_kms *kms = priv->kms; + long actual, requested; + + requested = 1000 * mode->clock; + actual = kms->funcs->round_pixclk(kms, + requested, hdmi_bridge->hdmi->encoder); + + /* for mdp5/apq8074, we manage our own pixel clk (as opposed to + * mdp4/dtv stuff where pixel clk is assigned to mdp/encoder + * instead): + */ + if (config->pwr_clk_cnt > 0) + actual = clk_round_rate(hdmi->pwr_clks[0], actual); + + DBG("requested=%ld, actual=%ld", requested, actual); + + if (actual != requested) + return MODE_CLOCK_RANGE; + + return 0; +} + static const struct drm_bridge_funcs msm_hdmi_bridge_funcs = { .pre_enable = msm_hdmi_bridge_pre_enable, .enable = msm_hdmi_bridge_enable, .disable = msm_hdmi_bridge_disable, .post_disable = msm_hdmi_bridge_post_disable, .mode_set = msm_hdmi_bridge_mode_set, + .mode_valid = msm_hdmi_bridge_mode_valid, + .get_edid = msm_hdmi_bridge_get_edid, + .detect = msm_hdmi_bridge_detect, }; +static void +msm_hdmi_hotplug_work(struct work_struct *work) +{ + struct hdmi_bridge *hdmi_bridge = + container_of(work, struct hdmi_bridge, hpd_work); + struct drm_bridge *bridge = &hdmi_bridge->base; + + drm_bridge_hpd_notify(bridge, drm_bridge_detect(bridge)); +} /* initialize bridge */ struct drm_bridge *msm_hdmi_bridge_init(struct hdmi *hdmi) @@ -283,11 +344,17 @@ struct drm_bridge *msm_hdmi_bridge_init(struct hdmi *hdmi) } hdmi_bridge->hdmi = hdmi; + INIT_WORK(&hdmi_bridge->hpd_work, msm_hdmi_hotplug_work); bridge = &hdmi_bridge->base; bridge->funcs = &msm_hdmi_bridge_funcs; + bridge->ddc = hdmi->i2c; + bridge->type = DRM_MODE_CONNECTOR_HDMIA; + bridge->ops = DRM_BRIDGE_OP_HPD | + DRM_BRIDGE_OP_DETECT | + DRM_BRIDGE_OP_EDID; - ret = drm_bridge_attach(hdmi->encoder, bridge, NULL, 0); + ret = drm_bridge_attach(hdmi->encoder, bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); if (ret) goto fail; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c similarity index 63% rename from drivers/gpu/drm/msm/hdmi/hdmi_connector.c rename to drivers/gpu/drm/msm/hdmi/hdmi_hpd.c index 58707a1f3878..c3a236bb952c 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c @@ -11,13 +11,6 @@ #include "msm_kms.h" #include "hdmi.h" -struct hdmi_connector { - struct drm_connector base; - struct hdmi *hdmi; - struct work_struct hpd_work; -}; -#define to_hdmi_connector(x) container_of(x, struct hdmi_connector, base) - static void msm_hdmi_phy_reset(struct hdmi *hdmi) { unsigned int val; @@ -139,10 +132,10 @@ static void enable_hpd_clocks(struct hdmi *hdmi, bool enable) } } -int msm_hdmi_hpd_enable(struct drm_connector *connector) +int msm_hdmi_hpd_enable(struct drm_bridge *bridge) { - struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector); - struct hdmi *hdmi = hdmi_connector->hdmi; + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; const struct hdmi_platform_config *config = hdmi->config; struct device *dev = &hdmi->pdev->dev; uint32_t hpd_ctrl; @@ -202,9 +195,9 @@ fail: return ret; } -static void hdp_disable(struct hdmi_connector *hdmi_connector) +void msm_hdmi_hpd_disable(struct hdmi_bridge *hdmi_bridge) { - struct hdmi *hdmi = hdmi_connector->hdmi; + struct hdmi *hdmi = hdmi_bridge->hdmi; const struct hdmi_platform_config *config = hdmi->config; struct device *dev = &hdmi->pdev->dev; int i, ret = 0; @@ -233,19 +226,10 @@ static void hdp_disable(struct hdmi_connector *hdmi_connector) } } -static void -msm_hdmi_hotplug_work(struct work_struct *work) +void msm_hdmi_hpd_irq(struct drm_bridge *bridge) { - struct hdmi_connector *hdmi_connector = - container_of(work, struct hdmi_connector, hpd_work); - struct drm_connector *connector = &hdmi_connector->base; - drm_helper_hpd_irq_event(connector->dev); -} - -void msm_hdmi_connector_irq(struct drm_connector *connector) -{ - struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector); - struct hdmi *hdmi = hdmi_connector->hdmi; + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; uint32_t hpd_int_status, hpd_int_ctrl; /* Process HPD: */ @@ -268,7 +252,7 @@ void msm_hdmi_connector_irq(struct drm_connector *connector) hpd_int_ctrl |= HDMI_HPD_INT_CTRL_INT_CONNECT; hdmi_write(hdmi, REG_HDMI_HPD_INT_CTRL, hpd_int_ctrl); - queue_work(hdmi->workq, &hdmi_connector->hpd_work); + queue_work(hdmi->workq, &hdmi_bridge->hpd_work); } } @@ -299,11 +283,11 @@ static enum drm_connector_status detect_gpio(struct hdmi *hdmi) connector_status_disconnected; } -static enum drm_connector_status hdmi_connector_detect( - struct drm_connector *connector, bool force) +enum drm_connector_status msm_hdmi_bridge_detect( + struct drm_bridge *bridge) { - struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector); - struct hdmi *hdmi = hdmi_connector->hdmi; + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; const struct hdmi_platform_config *config = hdmi->config; struct hdmi_gpio_data hpd_gpio = config->gpios[HPD_GPIO_INDEX]; enum drm_connector_status stat_gpio, stat_reg; @@ -337,115 +321,3 @@ static enum drm_connector_status hdmi_connector_detect( return stat_gpio; } - -static void hdmi_connector_destroy(struct drm_connector *connector) -{ - struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector); - - hdp_disable(hdmi_connector); - - drm_connector_cleanup(connector); - - kfree(hdmi_connector); -} - -static int msm_hdmi_connector_get_modes(struct drm_connector *connector) -{ - struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector); - struct hdmi *hdmi = hdmi_connector->hdmi; - struct edid *edid; - uint32_t hdmi_ctrl; - int ret = 0; - - hdmi_ctrl = hdmi_read(hdmi, REG_HDMI_CTRL); - hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl | HDMI_CTRL_ENABLE); - - edid = drm_get_edid(connector, hdmi->i2c); - - hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl); - - hdmi->hdmi_mode = drm_detect_hdmi_monitor(edid); - drm_connector_update_edid_property(connector, edid); - - if (edid) { - ret = drm_add_edid_modes(connector, edid); - kfree(edid); - } - - return ret; -} - -static int msm_hdmi_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector); - struct hdmi *hdmi = hdmi_connector->hdmi; - const struct hdmi_platform_config *config = hdmi->config; - struct msm_drm_private *priv = connector->dev->dev_private; - struct msm_kms *kms = priv->kms; - long actual, requested; - - requested = 1000 * mode->clock; - actual = kms->funcs->round_pixclk(kms, - requested, hdmi_connector->hdmi->encoder); - - /* for mdp5/apq8074, we manage our own pixel clk (as opposed to - * mdp4/dtv stuff where pixel clk is assigned to mdp/encoder - * instead): - */ - if (config->pwr_clk_cnt > 0) - actual = clk_round_rate(hdmi->pwr_clks[0], actual); - - DBG("requested=%ld, actual=%ld", requested, actual); - - if (actual != requested) - return MODE_CLOCK_RANGE; - - return 0; -} - -static const struct drm_connector_funcs hdmi_connector_funcs = { - .detect = hdmi_connector_detect, - .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = hdmi_connector_destroy, - .reset = drm_atomic_helper_connector_reset, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, - .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, -}; - -static const struct drm_connector_helper_funcs msm_hdmi_connector_helper_funcs = { - .get_modes = msm_hdmi_connector_get_modes, - .mode_valid = msm_hdmi_connector_mode_valid, -}; - -/* initialize connector */ -struct drm_connector *msm_hdmi_connector_init(struct hdmi *hdmi) -{ - struct drm_connector *connector = NULL; - struct hdmi_connector *hdmi_connector; - - hdmi_connector = kzalloc(sizeof(*hdmi_connector), GFP_KERNEL); - if (!hdmi_connector) - return ERR_PTR(-ENOMEM); - - hdmi_connector->hdmi = hdmi; - INIT_WORK(&hdmi_connector->hpd_work, msm_hdmi_hotplug_work); - - connector = &hdmi_connector->base; - - drm_connector_init_with_ddc(hdmi->dev, connector, - &hdmi_connector_funcs, - DRM_MODE_CONNECTOR_HDMIA, - hdmi->i2c); - drm_connector_helper_add(connector, &msm_hdmi_connector_helper_funcs); - - connector->polled = DRM_CONNECTOR_POLL_CONNECT | - DRM_CONNECTOR_POLL_DISCONNECT; - - connector->interlace_allowed = 0; - connector->doublescan_allowed = 0; - - drm_connector_attach_encoder(connector, hdmi->encoder); - - return connector; -} From d959ff7fa9e512c54522bcc8127223c56a586558 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Thu, 9 Jun 2022 15:23:42 +0300 Subject: [PATCH 0214/4345] drm/msm/hdmi: drop unused GPIO support [ Upstream commit 68e674b13b17ed41aac2763d12ece6deaae8df58 ] The HDMI driver has code to configure extra GPIOs, which predates pinctrl support. Nowadays all platforms should use pinctrl instead. Neither of upstreamed Qualcomm platforms uses these properties, so it's safe to drop them. Reported-by: kernel test robot Signed-off-by: Dmitry Baryshkov Reviewed-by: Stephen Boyd Patchwork: https://patchwork.freedesktop.org/patch/488858/ Link: https://lore.kernel.org/r/20220609122350.3157529-7-dmitry.baryshkov@linaro.org Signed-off-by: Dmitry Baryshkov Stable-dep-of: b964444b2b64 ("drm/msm/hdmi: use devres helper for runtime PM management") Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/hdmi/hdmi.c | 66 +++++++---------------------- drivers/gpu/drm/msm/hdmi/hdmi.h | 13 +----- drivers/gpu/drm/msm/hdmi/hdmi_hpd.c | 62 ++------------------------- 3 files changed, 21 insertions(+), 120 deletions(-) diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index f6b09e8eca67..efb14043a6ec 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -247,6 +247,20 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev) hdmi->pwr_clks[i] = clk; } + hdmi->hpd_gpiod = devm_gpiod_get_optional(&pdev->dev, "hpd", GPIOD_IN); + /* This will catch e.g. -EPROBE_DEFER */ + if (IS_ERR(hdmi->hpd_gpiod)) { + ret = PTR_ERR(hdmi->hpd_gpiod); + DRM_DEV_ERROR(&pdev->dev, "failed to get hpd gpio: (%d)\n", ret); + goto fail; + } + + if (!hdmi->hpd_gpiod) + DBG("failed to get HPD gpio"); + + if (hdmi->hpd_gpiod) + gpiod_set_consumer_name(hdmi->hpd_gpiod, "HDMI_HPD"); + pm_runtime_enable(&pdev->dev); hdmi->workq = alloc_ordered_workqueue("msm_hdmi", 0); @@ -429,20 +443,6 @@ static struct hdmi_platform_config hdmi_tx_8996_config = { .hpd_freq = hpd_clk_freq_8x74, }; -static const struct { - const char *name; - const bool output; - const int value; - const char *label; -} msm_hdmi_gpio_pdata[] = { - { "qcom,hdmi-tx-ddc-clk", true, 1, "HDMI_DDC_CLK" }, - { "qcom,hdmi-tx-ddc-data", true, 1, "HDMI_DDC_DATA" }, - { "qcom,hdmi-tx-hpd", false, 1, "HDMI_HPD" }, - { "qcom,hdmi-tx-mux-en", true, 1, "HDMI_MUX_EN" }, - { "qcom,hdmi-tx-mux-sel", true, 0, "HDMI_MUX_SEL" }, - { "qcom,hdmi-tx-mux-lpm", true, 1, "HDMI_MUX_LPM" }, -}; - /* * HDMI audio codec callbacks */ @@ -555,7 +555,7 @@ static int msm_hdmi_bind(struct device *dev, struct device *master, void *data) struct hdmi_platform_config *hdmi_cfg; struct hdmi *hdmi; struct device_node *of_node = dev->of_node; - int i, err; + int err; hdmi_cfg = (struct hdmi_platform_config *) of_device_get_match_data(dev); @@ -567,42 +567,6 @@ static int msm_hdmi_bind(struct device *dev, struct device *master, void *data) hdmi_cfg->mmio_name = "core_physical"; hdmi_cfg->qfprom_mmio_name = "qfprom_physical"; - for (i = 0; i < HDMI_MAX_NUM_GPIO; i++) { - const char *name = msm_hdmi_gpio_pdata[i].name; - struct gpio_desc *gpiod; - - /* - * We are fetching the GPIO lines "as is" since the connector - * code is enabling and disabling the lines. Until that point - * the power-on default value will be kept. - */ - gpiod = devm_gpiod_get_optional(dev, name, GPIOD_ASIS); - /* This will catch e.g. -PROBE_DEFER */ - if (IS_ERR(gpiod)) - return PTR_ERR(gpiod); - if (!gpiod) { - /* Try a second time, stripping down the name */ - char name3[32]; - - /* - * Try again after stripping out the "qcom,hdmi-tx" - * prefix. This is mainly to match "hpd-gpios" used - * in the upstream bindings. - */ - if (sscanf(name, "qcom,hdmi-tx-%s", name3)) - gpiod = devm_gpiod_get_optional(dev, name3, GPIOD_ASIS); - if (IS_ERR(gpiod)) - return PTR_ERR(gpiod); - if (!gpiod) - DBG("failed to get gpio: %s", name); - } - hdmi_cfg->gpios[i].gpiod = gpiod; - if (gpiod) - gpiod_set_consumer_name(gpiod, msm_hdmi_gpio_pdata[i].label); - hdmi_cfg->gpios[i].output = msm_hdmi_gpio_pdata[i].output; - hdmi_cfg->gpios[i].value = msm_hdmi_gpio_pdata[i].value; - } - dev->platform_data = hdmi_cfg; hdmi = msm_hdmi_init(to_platform_device(dev)); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h index 8d2706bec3b9..20f554312b17 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.h @@ -19,17 +19,9 @@ #include "msm_drv.h" #include "hdmi.xml.h" -#define HDMI_MAX_NUM_GPIO 6 - struct hdmi_phy; struct hdmi_platform_config; -struct hdmi_gpio_data { - struct gpio_desc *gpiod; - bool output; - int value; -}; - struct hdmi_audio { bool enabled; struct hdmi_audio_infoframe infoframe; @@ -61,6 +53,8 @@ struct hdmi { struct clk **hpd_clks; struct clk **pwr_clks; + struct gpio_desc *hpd_gpiod; + struct hdmi_phy *phy; struct device *phy_dev; @@ -109,9 +103,6 @@ struct hdmi_platform_config { /* clks that need to be on for screen pwr (ie pixel clk): */ const char **pwr_clk_names; int pwr_clk_cnt; - - /* gpio's: */ - struct hdmi_gpio_data gpios[HDMI_MAX_NUM_GPIO]; }; struct hdmi_bridge { diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c b/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c index c3a236bb952c..52ebe562ca9b 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c @@ -60,48 +60,6 @@ static void msm_hdmi_phy_reset(struct hdmi *hdmi) } } -static int gpio_config(struct hdmi *hdmi, bool on) -{ - const struct hdmi_platform_config *config = hdmi->config; - int i; - - if (on) { - for (i = 0; i < HDMI_MAX_NUM_GPIO; i++) { - struct hdmi_gpio_data gpio = config->gpios[i]; - - if (gpio.gpiod) { - if (gpio.output) { - gpiod_direction_output(gpio.gpiod, - gpio.value); - } else { - gpiod_direction_input(gpio.gpiod); - gpiod_set_value_cansleep(gpio.gpiod, - gpio.value); - } - } - } - - DBG("gpio on"); - } else { - for (i = 0; i < HDMI_MAX_NUM_GPIO; i++) { - struct hdmi_gpio_data gpio = config->gpios[i]; - - if (!gpio.gpiod) - continue; - - if (gpio.output) { - int value = gpio.value ? 0 : 1; - - gpiod_set_value_cansleep(gpio.gpiod, value); - } - } - - DBG("gpio off"); - } - - return 0; -} - static void enable_hpd_clocks(struct hdmi *hdmi, bool enable) { const struct hdmi_platform_config *config = hdmi->config; @@ -157,11 +115,8 @@ int msm_hdmi_hpd_enable(struct drm_bridge *bridge) goto fail; } - ret = gpio_config(hdmi, true); - if (ret) { - DRM_DEV_ERROR(dev, "failed to configure GPIOs: %d\n", ret); - goto fail; - } + if (hdmi->hpd_gpiod) + gpiod_set_value_cansleep(hdmi->hpd_gpiod, 1); pm_runtime_get_sync(dev); enable_hpd_clocks(hdmi, true); @@ -210,10 +165,6 @@ void msm_hdmi_hpd_disable(struct hdmi_bridge *hdmi_bridge) enable_hpd_clocks(hdmi, false); pm_runtime_put_autosuspend(dev); - ret = gpio_config(hdmi, false); - if (ret) - dev_warn(dev, "failed to unconfigure GPIOs: %d\n", ret); - ret = pinctrl_pm_select_sleep_state(dev); if (ret) dev_warn(dev, "pinctrl state chg failed: %d\n", ret); @@ -275,10 +226,7 @@ static enum drm_connector_status detect_reg(struct hdmi *hdmi) #define HPD_GPIO_INDEX 2 static enum drm_connector_status detect_gpio(struct hdmi *hdmi) { - const struct hdmi_platform_config *config = hdmi->config; - struct hdmi_gpio_data hpd_gpio = config->gpios[HPD_GPIO_INDEX]; - - return gpiod_get_value(hpd_gpio.gpiod) ? + return gpiod_get_value(hdmi->hpd_gpiod) ? connector_status_connected : connector_status_disconnected; } @@ -288,8 +236,6 @@ enum drm_connector_status msm_hdmi_bridge_detect( { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; - const struct hdmi_platform_config *config = hdmi->config; - struct hdmi_gpio_data hpd_gpio = config->gpios[HPD_GPIO_INDEX]; enum drm_connector_status stat_gpio, stat_reg; int retry = 20; @@ -297,7 +243,7 @@ enum drm_connector_status msm_hdmi_bridge_detect( * some platforms may not have hpd gpio. Rely only on the status * provided by REG_HDMI_HPD_INT_STATUS in this case. */ - if (!hpd_gpio.gpiod) + if (!hdmi->hpd_gpiod) return detect_reg(hdmi); do { From 72e8d9c731a78a30d7347fa8104ca0547a295e09 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:53 +0530 Subject: [PATCH 0215/4345] bpf: Fix slot type check in check_stack_write_var_off [ Upstream commit f5e477a861e4a20d8a1c5f7a245f3a3c3c376b03 ] For the case where allow_ptr_leaks is false, code is checking whether slot type is STACK_INVALID and STACK_SPILL and rejecting other cases. This is a consequence of incorrectly checking for register type instead of the slot type (NOT_INIT and SCALAR_VALUE respectively). Fix the check. Fixes: 01f810ace9ed ("bpf: Allow variable-offset stack access") Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221103191013.1236066-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 50364031eb4d..4d62822f5502 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2439,14 +2439,17 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, spi = slot / BPF_REG_SIZE; stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; - if (!env->allow_ptr_leaks - && *stype != NOT_INIT - && *stype != SCALAR_VALUE) { - /* Reject the write if there's are spilled pointers in - * range. If we didn't reject here, the ptr status - * would be erased below (even though not all slots are - * actually overwritten), possibly opening the door to - * leaks. + if (!env->allow_ptr_leaks && *stype != STACK_MISC && *stype != STACK_ZERO) { + /* Reject the write if range we may write to has not + * been initialized beforehand. If we didn't reject + * here, the ptr status would be erased below (even + * though not all slots are actually overwritten), + * possibly opening the door to leaks. + * + * We do however catch STACK_INVALID case below, and + * only allow reading possibly uninitialized memory + * later for CAP_PERFMON, as the write may not happen to + * that slot. */ verbose(env, "spilled ptr in range of var-offset stack write; insn %d, ptr off: %d", insn_idx, i); From f9d19f3a044ca651b0be52a4bf951ffe74259b9f Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Thu, 27 Oct 2022 20:38:55 +0800 Subject: [PATCH 0216/4345] media: vivid: fix compose size exceed boundary [ Upstream commit 94a7ad9283464b75b12516c5512541d467cefcf8 ] syzkaller found a bug: BUG: unable to handle page fault for address: ffffc9000a3b1000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 100000067 P4D 100000067 PUD 10015f067 PMD 1121ca067 PTE 0 Oops: 0002 [#1] PREEMPT SMP CPU: 0 PID: 23489 Comm: vivid-000-vid-c Not tainted 6.1.0-rc1+ #512 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:memcpy_erms+0x6/0x10 [...] Call Trace: ? tpg_fill_plane_buffer+0x856/0x15b0 vivid_fillbuff+0x8ac/0x1110 vivid_thread_vid_cap_tick+0x361/0xc90 vivid_thread_vid_cap+0x21a/0x3a0 kthread+0x143/0x180 ret_from_fork+0x1f/0x30 This is because we forget to check boundary after adjust compose->height int V4L2_SEL_TGT_CROP case. Add v4l2_rect_map_inside() to fix this problem for this case. Fixes: ef834f7836ec ("[media] vivid: add the video capture and output parts") Signed-off-by: Liu Shixin Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/test-drivers/vivid/vivid-vid-cap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c index d493bd17481b..437889e51ca0 100644 --- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c @@ -961,6 +961,7 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection if (dev->has_compose_cap) { v4l2_rect_set_min_size(compose, &min_rect); v4l2_rect_set_max_size(compose, &max_rect); + v4l2_rect_map_inside(compose, &fmt); } dev->fmt_cap_rect = fmt; tpg_s_buf_height(&dev->tpg, fmt.height); From 7fc38327fd648876368b983d2f29cc17ddea73e9 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 24 Oct 2022 21:46:50 +0800 Subject: [PATCH 0217/4345] media: platform: exynos4-is: fix return value check in fimc_md_probe() [ Upstream commit e38e42c078da4af962d322b97e726dcb2f184e3f ] devm_pinctrl_get() may return ERR_PTR(-EPROBE_DEFER), add a minus sign to fix it. Fixes: 4163851f7b99 ("[media] s5p-fimc: Use pinctrl API for camera ports configuration") Signed-off-by: Yang Yingliang Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/exynos4-is/media-dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c index 8603c578f55f..a9ab2a28fc26 100644 --- a/drivers/media/platform/exynos4-is/media-dev.c +++ b/drivers/media/platform/exynos4-is/media-dev.c @@ -1470,7 +1470,7 @@ static int fimc_md_probe(struct platform_device *pdev) pinctrl = devm_pinctrl_get(dev); if (IS_ERR(pinctrl)) { ret = PTR_ERR(pinctrl); - if (ret != EPROBE_DEFER) + if (ret != -EPROBE_DEFER) dev_err(dev, "Failed to get pinctrl: %d\n", ret); goto err_clk; } From 42b2b7382aaba04b7cf6c9868da00d9c914fa500 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 4 Nov 2022 09:36:44 -0700 Subject: [PATCH 0218/4345] bpf: propagate precision in ALU/ALU64 operations [ Upstream commit a3b666bfa9c9edc05bca62a87abafe0936bd7f97 ] When processing ALU/ALU64 operations (apart from BPF_MOV, which is handled correctly already; and BPF_NEG and BPF_END are special and don't have source register), if destination register is already marked precise, this causes problem with potentially missing precision tracking for the source register. E.g., when we have r1 >>= r5 and r1 is marked precise, but r5 isn't, this will lead to r5 staying as imprecise. This is due to the precision backtracking logic stopping early when it sees r1 is already marked precise. If r1 wasn't precise, we'd keep backtracking and would add r5 to the set of registers that need to be marked precise. So there is a discrepancy here which can lead to invalid and incompatible states matched due to lack of precision marking on r5. If r1 wasn't precise, precision backtracking would correctly mark both r1 and r5 as precise. This is simple to fix, though. During the forward instruction simulation pass, for arithmetic operations of `scalar = scalar` form (where is ALU or ALU64 operations), if destination register is already precise, mark source register as precise. This applies only when both involved registers are SCALARs. `ptr += scalar` and `scalar += ptr` cases are already handled correctly. This does have (negative) effect on some selftest programs and few Cilium programs. ~/baseline-tmp-results.csv are veristat results with this patch, while ~/baseline-results.csv is without it. See post scriptum for instructions on how to make Cilium programs testable with veristat. Correctness has a price. $ ./veristat -C -e file,prog,insns,states ~/baseline-results.csv ~/baseline-tmp-results.csv | grep -v '+0' File Program Total insns (A) Total insns (B) Total insns (DIFF) Total states (A) Total states (B) Total states (DIFF) ----------------------- -------------------- --------------- --------------- ------------------ ---------------- ---------------- ------------------- bpf_cubic.bpf.linked1.o bpf_cubic_cong_avoid 997 1700 +703 (+70.51%) 62 90 +28 (+45.16%) test_l4lb.bpf.linked1.o balancer_ingress 4559 5469 +910 (+19.96%) 118 126 +8 (+6.78%) ----------------------- -------------------- --------------- --------------- ------------------ ---------------- ---------------- ------------------- $ ./veristat -C -e file,prog,verdict,insns,states ~/baseline-results-cilium.csv ~/baseline-tmp-results-cilium.csv | grep -v '+0' File Program Total insns (A) Total insns (B) Total insns (DIFF) Total states (A) Total states (B) Total states (DIFF) ------------- ------------------------------ --------------- --------------- ------------------ ---------------- ---------------- ------------------- bpf_host.o tail_nodeport_nat_ingress_ipv6 4448 5261 +813 (+18.28%) 234 247 +13 (+5.56%) bpf_host.o tail_nodeport_nat_ipv6_egress 3396 3446 +50 (+1.47%) 201 203 +2 (+1.00%) bpf_lxc.o tail_nodeport_nat_ingress_ipv6 4448 5261 +813 (+18.28%) 234 247 +13 (+5.56%) bpf_overlay.o tail_nodeport_nat_ingress_ipv6 4448 5261 +813 (+18.28%) 234 247 +13 (+5.56%) bpf_xdp.o tail_lb_ipv4 71736 73442 +1706 (+2.38%) 4295 4370 +75 (+1.75%) ------------- ------------------------------ --------------- --------------- ------------------ ---------------- ---------------- ------------------- P.S. To make Cilium ([0]) programs libbpf-compatible and thus veristat-loadable, apply changes from topmost commit in [1], which does minimal changes to Cilium source code, mostly around SEC() annotations and BPF map definitions. [0] https://github.com/cilium/cilium/ [1] https://github.com/anakryiko/cilium/commits/libbpf-friendliness Fixes: b5dc0163d8fd ("bpf: precise scalar_value tracking") Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20221104163649.121784-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4d62822f5502..30e0fa1bd83c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6992,6 +6992,11 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, return err; return adjust_ptr_min_max_vals(env, insn, dst_reg, src_reg); + } else if (dst_reg->precise) { + /* if dst_reg is precise, src_reg should be precise as well */ + err = mark_chain_precision(env, insn->src_reg); + if (err) + return err; } } else { /* Pretend the src is a reg with a known value, since we only From cdd73a5ed0840da88a3b9ad353f568e6f156d417 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 21 Sep 2021 17:49:34 -0700 Subject: [PATCH 0219/4345] bpf: Check the other end of slot_type for STACK_SPILL [ Upstream commit 27113c59b6d0a587b29ae72d4ff3f832f58b0651 ] Every 8 bytes of the stack is tracked by a bpf_stack_state. Within each bpf_stack_state, there is a 'u8 slot_type[8]' to track the type of each byte. Verifier tests slot_type[0] == STACK_SPILL to decide if the spilled reg state is saved. Verifier currently only saves the reg state if the whole 8 bytes are spilled to the stack, so checking the slot_type[7] is the same as checking slot_type[0]. The later patch will allow verifier to save the bounded scalar reg also for <8 bytes spill. There is a llvm patch [1] to ensure the <8 bytes spill will be 8-byte aligned, so checking slot_type[7] instead of slot_type[0] is required. While at it, this patch refactors the slot_type[0] == STACK_SPILL test into a new function is_spilled_reg() and change the slot_type[0] check to slot_type[7] check in there also. [1] https://reviews.llvm.org/D109073 Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210922004934.624194-1-kafai@fb.com Stable-dep-of: 529409ea92d5 ("bpf: propagate precision across all frames, not just the last one") Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 30e0fa1bd83c..034eb3030ce9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -562,6 +562,14 @@ const char *kernel_type_name(u32 id) btf_type_by_id(btf_vmlinux, id)->name_off); } +/* The reg state of a pointer or a bounded scalar was saved when + * it was spilled to the stack. + */ +static bool is_spilled_reg(const struct bpf_stack_state *stack) +{ + return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { @@ -666,7 +674,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, continue; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, state->stack[i].spilled_ptr.live); - if (state->stack[i].slot_type[0] == STACK_SPILL) { + if (is_spilled_reg(&state->stack[i])) { reg = &state->stack[i].spilled_ptr; t = reg->type; verbose(env, "=%s", reg_type_str[t]); @@ -2009,7 +2017,7 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, reg->precise = true; } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { - if (func->stack[j].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE) @@ -2051,7 +2059,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, } while (spi >= 0) { - if (func->stack[spi].slot_type[0] != STACK_SPILL) { + if (!is_spilled_reg(&func->stack[spi])) { stack_mask = 0; break; } @@ -2150,7 +2158,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, return 0; } - if (func->stack[i].slot_type[0] != STACK_SPILL) { + if (!is_spilled_reg(&func->stack[i])) { stack_mask &= ~(1ull << i); continue; } @@ -2348,7 +2356,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ - if (state->stack[spi].slot_type[0] == STACK_SPILL) + if (is_spilled_reg(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) state->stack[spi].slot_type[i] = STACK_MISC; @@ -2562,7 +2570,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; - if (stype[0] == STACK_SPILL) { + if (is_spilled_reg(®_state->stack[spi])) { if (size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); @@ -4081,11 +4089,11 @@ static int check_stack_range_initialized( goto mark; } - if (state->stack[spi].slot_type[0] == STACK_SPILL && + if (is_spilled_reg(&state->stack[spi]) && state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID) goto mark; - if (state->stack[spi].slot_type[0] == STACK_SPILL && + if (is_spilled_reg(&state->stack[spi]) && (state->stack[spi].spilled_ptr.type == SCALAR_VALUE || env->allow_ptr_leaks)) { if (clobber) { @@ -9282,9 +9290,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, * return false to continue verification of this path */ return false; - if (i % BPF_REG_SIZE) + if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; - if (old->stack[spi].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&old->stack[spi])) continue; if (!regsafe(env, &old->stack[spi].spilled_ptr, &cur->stack[spi].spilled_ptr, idmap)) @@ -9491,7 +9499,7 @@ static int propagate_precision(struct bpf_verifier_env *env, } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&state->stack[i])) continue; state_reg = &state->stack[i].spilled_ptr; if (state_reg->type != SCALAR_VALUE || From e1989d808b86f1c690a060f75b928f3db81cd977 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 4 Nov 2022 09:36:45 -0700 Subject: [PATCH 0220/4345] bpf: propagate precision across all frames, not just the last one [ Upstream commit 529409ea92d590659be487ba0839710329bd8074 ] When equivalent completed state is found and it has additional precision restrictions, BPF verifier propagates precision to currently-being-verified state chain (i.e., including parent states) so that if some of the states in the chain are not yet completed, necessary precision restrictions are enforced. Unfortunately, right now this happens only for the last frame (deepest active subprogram's frame), not all the frames. This can lead to incorrect matching of states due to missing precision marker. Currently this doesn't seem possible as BPF verifier forces everything to precise when validated BPF program has any subprograms. But with the next patch lifting this restriction, this becomes problematic. In fact, without this fix, we'll start getting failure in one of the existing test_verifier test cases: #906/p precise: cross frame pruning FAIL Unexpected success to load! verification time 48 usec stack depth 0+0 processed 26 insns (limit 1000000) max_states_per_insn 3 total_states 17 peak_states 17 mark_read 8 This patch adds precision propagation across all frames. Fixes: a3ce685dd01a ("bpf: fix precision tracking") Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20221104163649.121784-3-andrii@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 71 ++++++++++++++++++++++++------------------- 1 file changed, 39 insertions(+), 32 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 034eb3030ce9..232c93357b90 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2027,7 +2027,7 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, } } -static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, +static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno, int spi) { struct bpf_verifier_state *st = env->cur_state; @@ -2044,7 +2044,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, if (!env->bpf_capable) return 0; - func = st->frame[st->curframe]; + func = st->frame[frame]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { @@ -2125,7 +2125,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, break; new_marks = false; - func = st->frame[st->curframe]; + func = st->frame[frame]; bitmap_from_u64(mask, reg_mask); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; @@ -2191,12 +2191,17 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, static int mark_chain_precision(struct bpf_verifier_env *env, int regno) { - return __mark_chain_precision(env, regno, -1); + return __mark_chain_precision(env, env->cur_state->curframe, regno, -1); } -static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi) +static int mark_chain_precision_frame(struct bpf_verifier_env *env, int frame, int regno) { - return __mark_chain_precision(env, -1, spi); + return __mark_chain_precision(env, frame, regno, -1); +} + +static int mark_chain_precision_stack_frame(struct bpf_verifier_env *env, int frame, int spi) +{ + return __mark_chain_precision(env, frame, -1, spi); } static bool is_spillable_regtype(enum bpf_reg_type type) @@ -9483,34 +9488,36 @@ static int propagate_precision(struct bpf_verifier_env *env, { struct bpf_reg_state *state_reg; struct bpf_func_state *state; - int i, err = 0; + int i, err = 0, fr; - state = old->frame[old->curframe]; - state_reg = state->regs; - for (i = 0; i < BPF_REG_FP; i++, state_reg++) { - if (state_reg->type != SCALAR_VALUE || - !state_reg->precise) - continue; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "propagating r%d\n", i); - err = mark_chain_precision(env, i); - if (err < 0) - return err; - } + for (fr = old->curframe; fr >= 0; fr--) { + state = old->frame[fr]; + state_reg = state->regs; + for (i = 0; i < BPF_REG_FP; i++, state_reg++) { + if (state_reg->type != SCALAR_VALUE || + !state_reg->precise) + continue; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "frame %d: propagating r%d\n", i, fr); + err = mark_chain_precision_frame(env, fr, i); + if (err < 0) + return err; + } - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (!is_spilled_reg(&state->stack[i])) - continue; - state_reg = &state->stack[i].spilled_ptr; - if (state_reg->type != SCALAR_VALUE || - !state_reg->precise) - continue; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "propagating fp%d\n", - (-i - 1) * BPF_REG_SIZE); - err = mark_chain_precision_stack(env, i); - if (err < 0) - return err; + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (!is_spilled_reg(&state->stack[i])) + continue; + state_reg = &state->stack[i].spilled_ptr; + if (state_reg->type != SCALAR_VALUE || + !state_reg->precise) + continue; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "frame %d: propagating fp%d\n", + (-i - 1) * BPF_REG_SIZE, fr); + err = mark_chain_precision_stack_frame(env, fr, i); + if (err < 0) + return err; + } } return 0; } From 1a79539f4e8b24e234c2e7fc2050e416e9ce212d Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Wed, 2 Nov 2022 14:43:20 +0530 Subject: [PATCH 0221/4345] clk: qcom: gcc-sm8250: Use retention mode for USB GDSCs [ Upstream commit ac1c5a03d3772b1db25e8092f771aa33f6ae2f7e ] USB controllers on SM8250 doesn't work after coming back from suspend. This can be fixed by keeping the USB GDSCs in retention mode so that hardware can keep them ON and put into rentention mode once the parent domain goes to a low power state. Fixes: 3e5770921a88 ("clk: qcom: gcc: Add global clock controller driver for SM8250") Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221102091320.66007-1-manivannan.sadhasivam@linaro.org Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-sm8250.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/gcc-sm8250.c b/drivers/clk/qcom/gcc-sm8250.c index ab594a0f0c40..7ec11acc8298 100644 --- a/drivers/clk/qcom/gcc-sm8250.c +++ b/drivers/clk/qcom/gcc-sm8250.c @@ -3268,7 +3268,7 @@ static struct gdsc usb30_prim_gdsc = { .pd = { .name = "usb30_prim_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc usb30_sec_gdsc = { @@ -3276,7 +3276,7 @@ static struct gdsc usb30_sec_gdsc = { .pd = { .name = "usb30_sec_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = { From 330bc5533e8a8ed69cb951d5a8edce9bddb9db21 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Sat, 22 Oct 2022 20:13:52 +0800 Subject: [PATCH 0222/4345] mtd: Fix device name leak when register device failed in add_mtd_device() [ Upstream commit 895d68a39481a75c680aa421546931fb11942fa6 ] There is a kmemleak when register device failed: unreferenced object 0xffff888101aab550 (size 8): comm "insmod", pid 3922, jiffies 4295277753 (age 925.408s) hex dump (first 8 bytes): 6d 74 64 30 00 88 ff ff mtd0.... backtrace: [<00000000bde26724>] __kmalloc_node_track_caller+0x4e/0x150 [<000000003c32b416>] kvasprintf+0xb0/0x130 [<000000001f7a8f15>] kobject_set_name_vargs+0x2f/0xb0 [<000000006e781163>] dev_set_name+0xab/0xe0 [<00000000e30d0c78>] add_mtd_device+0x4bb/0x700 [<00000000f3d34de7>] mtd_device_parse_register+0x2ac/0x3f0 [<00000000c0d88488>] 0xffffffffa0238457 [<00000000b40d0922>] 0xffffffffa02a008f [<0000000023d17b9d>] do_one_initcall+0x87/0x2a0 [<00000000770f6ca6>] do_init_module+0xdf/0x320 [<000000007b6768fe>] load_module+0x2f98/0x3330 [<00000000346bed5a>] __do_sys_finit_module+0x113/0x1b0 [<00000000674c2290>] do_syscall_64+0x35/0x80 [<000000004c6a8d97>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 If register device failed, should call put_device() to give up the reference. Fixes: 1f24b5a8ecbb ("[MTD] driver model updates") Signed-off-by: Zhang Xiaoxu Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20221022121352.2534682-1-zhangxiaoxu5@huawei.com Signed-off-by: Sasha Levin --- drivers/mtd/mtdcore.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index a5197a481902..b2d88ff90e93 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -667,8 +667,10 @@ int add_mtd_device(struct mtd_info *mtd) dev_set_drvdata(&mtd->dev, mtd); of_node_get(mtd_get_of_node(mtd)); error = device_register(&mtd->dev); - if (error) + if (error) { + put_device(&mtd->dev); goto fail_added; + } /* Add the nvmem provider */ error = mtd_nvmem_add(mtd); From 624438195c324a47b797b302e6643448f9498717 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 4 Nov 2022 13:12:38 -0700 Subject: [PATCH 0223/4345] Input: joystick - fix Kconfig warning for JOYSTICK_ADC [ Upstream commit 6100a19c4fcfe154dd32f8a8ef4e8c0b1f607c75 ] Fix a Kconfig warning for JOYSTICK_ADC by also selecting IIO_BUFFER. WARNING: unmet direct dependencies detected for IIO_BUFFER_CB Depends on [n]: IIO [=y] && IIO_BUFFER [=n] Selected by [y]: - JOYSTICK_ADC [=y] && INPUT [=y] && INPUT_JOYSTICK [=y] && IIO [=y] Fixes: 2c2b364fddd5 ("Input: joystick - add ADC attached joystick driver.") Reported-by: kernel test robot Signed-off-by: Randy Dunlap Link: https://lore.kernel.org/r/20221104201238.31628-1-rdunlap@infradead.org Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/joystick/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/joystick/Kconfig b/drivers/input/joystick/Kconfig index b080f0cfb068..d8ec5193a941 100644 --- a/drivers/input/joystick/Kconfig +++ b/drivers/input/joystick/Kconfig @@ -45,6 +45,7 @@ config JOYSTICK_A3D config JOYSTICK_ADC tristate "Simple joystick connected over ADC" depends on IIO + select IIO_BUFFER select IIO_BUFFER_CB help Say Y here if you have a simple joystick connected over ADC. From 61c96d99d42cfb71cd1cfc6e4d60f8e3765db883 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 4 Nov 2022 17:33:39 +0100 Subject: [PATCH 0224/4345] wifi: rsi: Fix handling of 802.3 EAPOL frames sent via control port [ Upstream commit b8f6efccbb9dc0ff5dee7e20d69a4747298ee603 ] When using wpa_supplicant v2.10, this driver is no longer able to associate with any AP and fails in the EAPOL 4-way handshake while sending the 2/4 message to the AP. The problem is not present in wpa_supplicant v2.9 or older. The problem stems from HostAP commit 144314eaa ("wpa_supplicant: Send EAPOL frames over nl80211 where available") which changes the way EAPOL frames are sent, from them being send at L2 frames to them being sent via nl80211 control port. An EAPOL frame sent as L2 frame is passed to the WiFi driver with skb->protocol ETH_P_PAE, while EAPOL frame sent via nl80211 control port has skb->protocol set to ETH_P_802_3 . The later happens in ieee80211_tx_control_port(), where the EAPOL frame is encapsulated into 802.3 frame. The rsi_91x driver handles ETH_P_PAE EAPOL frames as high-priority frames and sends them via highest-priority transmit queue, while the ETH_P_802_3 frames are sent as regular frames. The EAPOL 4-way handshake frames must be sent as highest-priority, otherwise the 4-way handshake times out. Therefore, to fix this problem, inspect the skb control flags and if flag IEEE80211_TX_CTRL_PORT_CTRL_PROTO is set, assume this is an EAPOL frame and transmit the frame via high-priority queue just like other ETH_P_PAE frames. Fixes: 0eb42586cf87 ("rsi: data packet descriptor enhancements") Signed-off-by: Marek Vasut Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221104163339.227432-1-marex@denx.de Signed-off-by: Sasha Levin --- drivers/net/wireless/rsi/rsi_91x_core.c | 4 +++- drivers/net/wireless/rsi/rsi_91x_hal.c | 6 +++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/rsi/rsi_91x_core.c b/drivers/net/wireless/rsi/rsi_91x_core.c index 9c4c58557248..b7fa03813da1 100644 --- a/drivers/net/wireless/rsi/rsi_91x_core.c +++ b/drivers/net/wireless/rsi/rsi_91x_core.c @@ -466,7 +466,9 @@ void rsi_core_xmit(struct rsi_common *common, struct sk_buff *skb) tid, 0); } } - if (skb->protocol == cpu_to_be16(ETH_P_PAE)) { + + if (IEEE80211_SKB_CB(skb)->control.flags & + IEEE80211_TX_CTRL_PORT_CTRL_PROTO) { q_num = MGMT_SOFT_Q; skb->priority = q_num; } diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c index dca81a4bbdd7..30d2eccbcadd 100644 --- a/drivers/net/wireless/rsi/rsi_91x_hal.c +++ b/drivers/net/wireless/rsi/rsi_91x_hal.c @@ -162,12 +162,16 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb) u8 header_size; u8 vap_id = 0; u8 dword_align_bytes; + bool tx_eapol; u16 seq_num; info = IEEE80211_SKB_CB(skb); vif = info->control.vif; tx_params = (struct skb_info *)info->driver_data; + tx_eapol = IEEE80211_SKB_CB(skb)->control.flags & + IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + header_size = FRAME_DESC_SZ + sizeof(struct rsi_xtended_desc); if (header_size > skb_headroom(skb)) { rsi_dbg(ERR_ZONE, "%s: Unable to send pkt\n", __func__); @@ -231,7 +235,7 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb) } } - if (skb->protocol == cpu_to_be16(ETH_P_PAE)) { + if (tx_eapol) { rsi_dbg(INFO_ZONE, "*** Tx EAPOL ***\n"); data_desc->frame_info = cpu_to_le16(RATE_INFO_ENABLE); From 3d5cab726e3b370fea1b6e67183f0e13c409ce5c Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Mon, 4 Jul 2022 10:44:37 +0100 Subject: [PATCH 0225/4345] media: camss: Clean up received buffers on failed start of streaming [ Upstream commit c8f3582345e6a69da65ab588f7c4c2d1685b0e80 ] It is required to return the received buffers, if streaming can not be started. For instance media_pipeline_start() may fail with EPIPE, if a link validation between entities is not passed, and in such a case a user gets a kernel warning: WARNING: CPU: 1 PID: 520 at drivers/media/common/videobuf2/videobuf2-core.c:1592 vb2_start_streaming+0xec/0x160 Call trace: vb2_start_streaming+0xec/0x160 vb2_core_streamon+0x9c/0x1a0 vb2_ioctl_streamon+0x68/0xbc v4l_streamon+0x30/0x3c __video_do_ioctl+0x184/0x3e0 video_usercopy+0x37c/0x7b0 video_ioctl2+0x24/0x40 v4l2_ioctl+0x4c/0x70 The fix is to correct the error path in video_start_streaming() of camss. Fixes: 0ac2586c410f ("media: camss: Add files which handle the video device nodes") Signed-off-by: Vladimir Zapolskiy Reviewed-by: Robert Foss Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/camss/camss-video.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c index 15965e63cb61..9333a7a33d4d 100644 --- a/drivers/media/platform/qcom/camss/camss-video.c +++ b/drivers/media/platform/qcom/camss/camss-video.c @@ -444,7 +444,7 @@ static int video_start_streaming(struct vb2_queue *q, unsigned int count) ret = media_pipeline_start(&vdev->entity, &video->pipe); if (ret < 0) - return ret; + goto flush_buffers; ret = video_check_format(video); if (ret < 0) @@ -473,6 +473,7 @@ static int video_start_streaming(struct vb2_queue *q, unsigned int count) error: media_pipeline_stop(&vdev->entity); +flush_buffers: video->ops->flush_buffers(video, VB2_BUF_STATE_QUEUED); return ret; From 00fce49d142d9a952381fc5c8c28f4c0965163dd Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 3 Oct 2022 07:34:21 +0100 Subject: [PATCH 0226/4345] net, proc: Provide PROC_FS=n fallback for proc_create_net_single_write() [ Upstream commit c3d96f690a790074b508fe183a41e36a00cd7ddd ] Provide a CONFIG_PROC_FS=n fallback for proc_create_net_single_write(). Also provide a fallback for proc_create_net_data_write(). Fixes: 564def71765c ("proc: Add a way to make network proc files writable") Reported-by: kernel test robot Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org Signed-off-by: Sasha Levin --- include/linux/proc_fs.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 000cc0533c33..8c892730a1f1 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -190,8 +190,10 @@ static inline void proc_remove(struct proc_dir_entry *de) {} static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; } #define proc_create_net_data(name, mode, parent, ops, state_size, data) ({NULL;}) +#define proc_create_net_data_write(name, mode, parent, ops, write, state_size, data) ({NULL;}) #define proc_create_net(name, mode, parent, state_size, ops) ({NULL;}) #define proc_create_net_single(name, mode, parent, show, data) ({NULL;}) +#define proc_create_net_single_write(name, mode, parent, show, write, data) ({NULL;}) static inline struct pid *tgid_pidfd_to_pid(const struct file *file) { From cea79ae89b6b3f22722da2bbf936097afdaa944b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Sep 2022 19:17:29 +0100 Subject: [PATCH 0227/4345] rxrpc: Fix ack.bufferSize to be 0 when generating an ack [ Upstream commit 8889a711f9b4dcf4dd1330fa493081beebd118c9 ] ack.bufferSize should be set to 0 when generating an ack. Fixes: 8d94aa381dab ("rxrpc: Calls shouldn't hold socket refs") Reported-by: Jeffrey Altman Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: Sasha Levin --- net/rxrpc/output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 9683617db704..08c117bc083e 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -93,7 +93,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, *_hard_ack = hard_ack; *_top = top; - pkt->ack.bufferSpace = htons(8); + pkt->ack.bufferSpace = htons(0); pkt->ack.maxSkew = htons(0); pkt->ack.firstPacket = htonl(hard_ack + 1); pkt->ack.previousPacket = htonl(call->ackr_highest_seq); From b4b30f56ec512e2c35fc0761bc90b0e519d8fa6e Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Fri, 4 Nov 2022 17:50:02 +0800 Subject: [PATCH 0228/4345] drm/radeon: Add the missed acpi_put_table() to fix memory leak [ Upstream commit 10276a20be1115e1f76c189330da2992df980eee ] When the radeon driver reads the bios information from ACPI table in radeon_acpi_vfct_bios(), it misses to call acpi_put_table() to release the ACPI memory after the init, so add acpi_put_table() properly to fix the memory leak. v2: fix text formatting (Alex) Fixes: 268ba0a99f89 ("drm/radeon: implement ACPI VFCT vbios fetch (v3)") Signed-off-by: Hanjun Guo Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/radeon/radeon_bios.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index bb29cf02974d..34d2cb929c06 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -612,13 +612,14 @@ static bool radeon_acpi_vfct_bios(struct radeon_device *rdev) acpi_size tbl_size; UEFI_ACPI_VFCT *vfct; unsigned offset; + bool r = false; if (!ACPI_SUCCESS(acpi_get_table("VFCT", 1, &hdr))) return false; tbl_size = hdr->length; if (tbl_size < sizeof(UEFI_ACPI_VFCT)) { DRM_ERROR("ACPI VFCT table present but broken (too short #1)\n"); - return false; + goto out; } vfct = (UEFI_ACPI_VFCT *)hdr; @@ -631,13 +632,13 @@ static bool radeon_acpi_vfct_bios(struct radeon_device *rdev) offset += sizeof(VFCT_IMAGE_HEADER); if (offset > tbl_size) { DRM_ERROR("ACPI VFCT image header truncated\n"); - return false; + goto out; } offset += vhdr->ImageLength; if (offset > tbl_size) { DRM_ERROR("ACPI VFCT image truncated\n"); - return false; + goto out; } if (vhdr->ImageLength && @@ -649,15 +650,18 @@ static bool radeon_acpi_vfct_bios(struct radeon_device *rdev) rdev->bios = kmemdup(&vbios->VbiosContent, vhdr->ImageLength, GFP_KERNEL); + if (rdev->bios) + r = true; - if (!rdev->bios) - return false; - return true; + goto out; } } DRM_ERROR("ACPI VFCT table present but broken (too short #2)\n"); - return false; + +out: + acpi_put_table(hdr); + return r; } #else static inline bool radeon_acpi_vfct_bios(struct radeon_device *rdev) From 698bbaf0b4ed93321c205a026fc8262b8b3264d5 Mon Sep 17 00:00:00 2001 From: Xinlei Lee Date: Wed, 9 Nov 2022 18:00:59 +0800 Subject: [PATCH 0229/4345] drm/mediatek: Modify dpi power on/off sequence. [ Upstream commit ff446c0f6290185cefafe3b376bb86063a3a9f6a ] Modify dpi power on/off sequence so that the first gpio operation will take effect. Fixes: 6bd4763fd532 ("drm/mediatek: set dpi pin mode to gpio low to avoid leakage current") Signed-off-by: Xinlei Lee Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_dpi.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index c1ae336df683..aa3d472c79d7 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -367,9 +367,6 @@ static void mtk_dpi_power_off(struct mtk_dpi *dpi) if (--dpi->refcount != 0) return; - if (dpi->pinctrl && dpi->pins_gpio) - pinctrl_select_state(dpi->pinctrl, dpi->pins_gpio); - mtk_dpi_disable(dpi); clk_disable_unprepare(dpi->pixel_clk); clk_disable_unprepare(dpi->engine_clk); @@ -394,9 +391,6 @@ static int mtk_dpi_power_on(struct mtk_dpi *dpi) goto err_pixel; } - if (dpi->pinctrl && dpi->pins_dpi) - pinctrl_select_state(dpi->pinctrl, dpi->pins_dpi); - return 0; err_pixel: @@ -525,12 +519,18 @@ static void mtk_dpi_bridge_disable(struct drm_bridge *bridge) struct mtk_dpi *dpi = bridge_to_dpi(bridge); mtk_dpi_power_off(dpi); + + if (dpi->pinctrl && dpi->pins_gpio) + pinctrl_select_state(dpi->pinctrl, dpi->pins_gpio); } static void mtk_dpi_bridge_enable(struct drm_bridge *bridge) { struct mtk_dpi *dpi = bridge_to_dpi(bridge); + if (dpi->pinctrl && dpi->pins_dpi) + pinctrl_select_state(dpi->pinctrl, dpi->pins_dpi); + mtk_dpi_power_on(dpi); mtk_dpi_set_display_mode(dpi, &dpi->mode); mtk_dpi_enable(dpi); From 21a1409e8cf73053b54f7860548e3043dfa351a9 Mon Sep 17 00:00:00 2001 From: Zeng Heng Date: Mon, 14 Nov 2022 16:56:29 +0800 Subject: [PATCH 0230/4345] ASoC: pxa: fix null-pointer dereference in filter() [ Upstream commit ec7bf231aaa1bdbcb69d23bc50c753c80fb22429 ] kasprintf() would return NULL pointer when kmalloc() fail to allocate. Need to check the return pointer before calling strcmp(). Fixes: 7a824e214e25 ("ASoC: mmp: add audio dma support") Signed-off-by: Zeng Heng Link: https://lore.kernel.org/r/20221114085629.1910435-1-zengheng4@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/pxa/mmp-pcm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/pxa/mmp-pcm.c b/sound/soc/pxa/mmp-pcm.c index 53fc49e32fbc..0791737c3bf3 100644 --- a/sound/soc/pxa/mmp-pcm.c +++ b/sound/soc/pxa/mmp-pcm.c @@ -98,7 +98,7 @@ static bool filter(struct dma_chan *chan, void *param) devname = kasprintf(GFP_KERNEL, "%s.%d", dma_data->dma_res->name, dma_data->ssp_id); - if ((strcmp(dev_name(chan->device->dev), devname) == 0) && + if (devname && (strcmp(dev_name(chan->device->dev), devname) == 0) && (chan->chan_id == dma_data->dma_res->start)) { found = true; } From f48c474efe05cf9ce5e535b5e0ddd710e963936c Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 15 Nov 2022 17:15:08 +0800 Subject: [PATCH 0231/4345] regulator: core: fix unbalanced of node refcount in regulator_dev_lookup() [ Upstream commit f2b41b748c19962b82709d9f23c6b2b0ce9d2f91 ] I got the the following report: OF: ERROR: memory leak, expected refcount 1 instead of 2, of_node_get()/of_node_put() unbalanced - destroy cset entry: attach overlay node /i2c/pmic@62/regulators/exten In of_get_regulator(), the node is returned from of_parse_phandle() with refcount incremented, after using it, of_node_put() need be called. Fixes: 69511a452e6d ("regulator: map consumer regulator based on device tree") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221115091508.900752-1-yangyingliang@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index eb083b26ab4f..876afa3919c1 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1775,6 +1775,7 @@ static struct regulator_dev *regulator_dev_lookup(struct device *dev, node = of_get_regulator(dev, supply); if (node) { r = of_find_regulator_by_node(node); + of_node_put(node); if (r) return r; From 85273b4a7076ed5328c8ace02234e4e7e10972d5 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 15 Nov 2022 15:56:57 +0300 Subject: [PATCH 0232/4345] amdgpu/pm: prevent array underflow in vega20_odn_edit_dpm_table() [ Upstream commit d27252b5706e51188aed7647126e44dcf9e940c1 ] In the PP_OD_EDIT_VDDC_CURVE case the "input_index" variable is capped at 2 but not checked for negative values so it results in an out of bounds read. This value comes from the user via sysfs. Fixes: d5bf26539494 ("drm/amd/powerplay: added vega20 overdrive support V3") Signed-off-by: Dan Carpenter Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 60cde0c52825..57a354a03e8a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -2962,7 +2962,8 @@ static int vega20_odn_edit_dpm_table(struct pp_hwmgr *hwmgr, data->od8_settings.od8_settings_array; OverDriveTable_t *od_table = &(data->smc_state_table.overdrive_table); - int32_t input_index, input_clk, input_vol, i; + int32_t input_clk, input_vol, i; + uint32_t input_index; int od8_id; int ret; From 6f6a99fb620dc09e424986aa9c3492bb74a138bf Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Wed, 15 Dec 2021 10:17:37 +0100 Subject: [PATCH 0233/4345] drm/fourcc: Add packed 10bit YUV 4:2:0 format [ Upstream commit 006ea1b5822f9019bd722ffc6242bc0880879e3d ] Adds a format that is 3 10bit YUV 4:2:0 samples packed into a 32bit word (with 2 spare bits). Supported on Broadcom BCM2711 chips. Signed-off-by: Dave Stevenson Signed-off-by: Maxime Ripard Acked-by: Thomas Zimmermann Link: https://lore.kernel.org/r/20211215091739.135042-2-maxime@cerno.tech Stable-dep-of: b230555f3257 ("drm/fourcc: Fix vsub/hsub for Q410 and Q401") Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_fourcc.c | 3 +++ include/uapi/drm/drm_fourcc.h | 11 +++++++++++ 2 files changed, 14 insertions(+) diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index 722c7ebe4e88..4d4b65a88bd1 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -286,6 +286,9 @@ const struct drm_format_info *__drm_format_info(u32 format) .num_planes = 3, .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 0, .vsub = 0, .is_yuv = true }, + { .format = DRM_FORMAT_P030, .depth = 0, .num_planes = 2, + .char_per_block = { 4, 8, 0 }, .block_w = { 3, 3, 0 }, .block_h = { 1, 1, 0 }, + .hsub = 2, .vsub = 2, .is_yuv = true}, }; unsigned int i; diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 5498d7a6556a..dad9d3b4a97a 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -271,6 +271,13 @@ extern "C" { */ #define DRM_FORMAT_P016 fourcc_code('P', '0', '1', '6') /* 2x2 subsampled Cr:Cb plane 16 bits per channel */ +/* 2 plane YCbCr420. + * 3 10 bit components and 2 padding bits packed into 4 bytes. + * index 0 = Y plane, [31:0] x:Y2:Y1:Y0 2:10:10:10 little endian + * index 1 = Cr:Cb plane, [63:0] x:Cr2:Cb2:Cr1:x:Cb1:Cr0:Cb0 [2:10:10:10:2:10:10:10] little endian + */ +#define DRM_FORMAT_P030 fourcc_code('P', '0', '3', '0') /* 2x2 subsampled Cr:Cb plane 10 bits per channel packed */ + /* 3 plane non-subsampled (444) YCbCr * 16 bits per component, but only 10 bits are used and 6 bits are padded * index 0: Y plane, [15:0] Y:x [10:6] little endian @@ -777,6 +784,10 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) * and UV. Some SAND-using hardware stores UV in a separate tiled * image from Y to reduce the column height, which is not supported * with these modifiers. + * + * The DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT modifier is also + * supported for DRM_FORMAT_P030 where the columns remain as 128 bytes + * wide, but as this is a 10 bpp format that translates to 96 pixels. */ #define DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(v) \ From 102df01caf5ebf8948d00de1ae53fd730a454905 Mon Sep 17 00:00:00 2001 From: Brian Starkey Date: Tue, 13 Sep 2022 15:43:06 +0100 Subject: [PATCH 0234/4345] drm/fourcc: Fix vsub/hsub for Q410 and Q401 [ Upstream commit b230555f3257f197dd98641ef6ebaf778b52dd51 ] These formats are not subsampled, but that means hsub and vsub should be 1, not 0. Fixes: 94b292b27734 ("drm: drm_fourcc: add NV15, Q410, Q401 YUV formats") Reported-by: George Kennedy Reported-by: butt3rflyh4ck Signed-off-by: Brian Starkey Reviewed-by: Liviu Dudau Signed-off-by: Liviu Dudau Link: https://patchwork.freedesktop.org/patch/msgid/20220913144306.17279-1-brian.starkey@arm.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_fourcc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index 4d4b65a88bd1..92152c06b75b 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -280,12 +280,12 @@ const struct drm_format_info *__drm_format_info(u32 format) .vsub = 2, .is_yuv = true }, { .format = DRM_FORMAT_Q410, .depth = 0, .num_planes = 3, .char_per_block = { 2, 2, 2 }, - .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 0, - .vsub = 0, .is_yuv = true }, + .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 1, + .vsub = 1, .is_yuv = true }, { .format = DRM_FORMAT_Q401, .depth = 0, .num_planes = 3, .char_per_block = { 2, 2, 2 }, - .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 0, - .vsub = 0, .is_yuv = true }, + .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 1, + .vsub = 1, .is_yuv = true }, { .format = DRM_FORMAT_P030, .depth = 0, .num_planes = 2, .char_per_block = { 4, 8, 0 }, .block_w = { 3, 3, 0 }, .block_h = { 1, 1, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true}, From 3bd737289c26be3cee4b9afaf61ef784a2af9d6e Mon Sep 17 00:00:00 2001 From: GUO Zihua Date: Fri, 11 Nov 2022 18:13:17 +0800 Subject: [PATCH 0235/4345] integrity: Fix memory leakage in keyring allocation error path [ Upstream commit 39419ef7af0916cc3620ecf1ed42d29659109bf3 ] Key restriction is allocated in integrity_init_keyring(). However, if keyring allocation failed, it is not freed, causing memory leaks. Fixes: 2b6aa412ff23 ("KEYS: Use structure to capture key restriction function and data") Signed-off-by: GUO Zihua Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/digsig.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index 0f518dcfde05..de442af7b336 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -120,6 +120,7 @@ int __init integrity_init_keyring(const unsigned int id) { struct key_restriction *restriction; key_perm_t perm; + int ret; perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH; @@ -140,7 +141,10 @@ int __init integrity_init_keyring(const unsigned int id) perm |= KEY_USR_WRITE; out: - return __integrity_init_keyring(id, perm, restriction); + ret = __integrity_init_keyring(id, perm, restriction); + if (ret) + kfree(restriction); + return ret; } int __init integrity_add_key(const unsigned int id, const void *data, From adf03c30996881a9292a8b9d175f5ad5c410110a Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Sat, 12 Nov 2022 17:27:19 +0800 Subject: [PATCH 0236/4345] ima: Fix misuse of dereference of pointer in template_desc_init_fields() [ Upstream commit 25369175ce84813dd99d6604e710dc2491f68523 ] The input parameter @fields is type of struct ima_template_field ***, so when allocates array memory for @fields, the size of element should be sizeof(**field) instead of sizeof(*field). Actually the original code would not cause any runtime error, but it's better to make it logically right. Fixes: adf53a778a0a ("ima: new templates management mechanism") Signed-off-by: Xiu Jianfeng Reviewed-by: Roberto Sassu Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/ima/ima_template.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c index f64c01d53e96..e053c741997b 100644 --- a/security/integrity/ima/ima_template.c +++ b/security/integrity/ima/ima_template.c @@ -220,11 +220,11 @@ int template_desc_init_fields(const char *template_fmt, } if (fields && num_fields) { - *fields = kmalloc_array(i, sizeof(*fields), GFP_KERNEL); + *fields = kmalloc_array(i, sizeof(**fields), GFP_KERNEL); if (*fields == NULL) return -ENOMEM; - memcpy(*fields, found_fields, i * sizeof(*fields)); + memcpy(*fields, found_fields, i * sizeof(**fields)); *num_fields = i; } From effbf636162bddcbcb38b78e11995c759a76bae1 Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Thu, 10 Nov 2022 14:19:26 +0800 Subject: [PATCH 0237/4345] wifi: ath10k: Fix return value in ath10k_pci_init() [ Upstream commit 2af7749047d8d6ad43feff69f555a13a6a6c2831 ] This driver is attempting to register to support two different buses. if either of these is successful then ath10k_pci_init() should return 0 so that hardware attached to the successful bus can be probed and supported. only if both of these are unsuccessful should ath10k_pci_init() return an errno. Fixes: 0b523ced9a3c ("ath10k: add basic skeleton to support ahb") Signed-off-by: Xiu Jianfeng Reviewed-by: Jeff Johnson Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221110061926.18163-1-xiujianfeng@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath10k/pci.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index 86f52bcb3e4d..67e240327fb3 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -3799,18 +3799,22 @@ static struct pci_driver ath10k_pci_driver = { static int __init ath10k_pci_init(void) { - int ret; + int ret1, ret2; - ret = pci_register_driver(&ath10k_pci_driver); - if (ret) + ret1 = pci_register_driver(&ath10k_pci_driver); + if (ret1) printk(KERN_ERR "failed to register ath10k pci driver: %d\n", - ret); + ret1); - ret = ath10k_ahb_init(); - if (ret) - printk(KERN_ERR "ahb init failed: %d\n", ret); + ret2 = ath10k_ahb_init(); + if (ret2) + printk(KERN_ERR "ahb init failed: %d\n", ret2); - return ret; + if (ret1 && ret2) + return ret1; + + /* registered to at least one bus */ + return 0; } module_init(ath10k_pci_init); From 0919982a1744346269320615615c7deb14106661 Mon Sep 17 00:00:00 2001 From: Hui Tang Date: Mon, 14 Nov 2022 17:02:40 +0800 Subject: [PATCH 0238/4345] mtd: lpddr2_nvm: Fix possible null-ptr-deref MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6bdd45d795adf9e73b38ced5e7f750cd199499ff ] It will cause null-ptr-deref when resource_size(add_range) invoked, if platform_get_resource() returns NULL. Fixes: 96ba9dd65788 ("mtd: lpddr: add driver for LPDDR2-NVM PCM memories") Signed-off-by: Hui Tang Acked-by: Uwe Kleine-König Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20221114090240.244172-1-tanghui20@huawei.com Signed-off-by: Sasha Levin --- drivers/mtd/lpddr/lpddr2_nvm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mtd/lpddr/lpddr2_nvm.c b/drivers/mtd/lpddr/lpddr2_nvm.c index 72f5c7b30079..add4386f99f0 100644 --- a/drivers/mtd/lpddr/lpddr2_nvm.c +++ b/drivers/mtd/lpddr/lpddr2_nvm.c @@ -433,6 +433,8 @@ static int lpddr2_nvm_probe(struct platform_device *pdev) /* lpddr2_nvm address range */ add_range = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!add_range) + return -ENODEV; /* Populate map_info data structure */ *map = (struct map_info) { From 3afd738e7712473bf0d9a8ccb4b1092d59345f01 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Thu, 17 Nov 2022 21:49:19 -0800 Subject: [PATCH 0239/4345] Input: elants_i2c - properly handle the reset GPIO when power is off [ Upstream commit a85fbd6498441694475716a4d5c65f9d3e073faf ] As can be seen in elants_i2c_power_off(), we want the reset GPIO asserted when power is off. The reset GPIO is active low so we need the reset line logic low when power is off to avoid leakage. We have a problem, though, at probe time. At probe time we haven't powered the regulators on yet but we have: devm_gpiod_get(&client->dev, "reset", GPIOD_OUT_LOW); While that _looks_ right, it turns out that it's not. The GPIOD_OUT_LOW doesn't mean to init the GPIO to low. It means init the GPIO to "not asserted". Since this is an active low GPIO that inits it to be high. Let's fix this to properly init the GPIO. Now after both probe and power off the state of the GPIO is consistent (it's "asserted" or level low). Once we fix this, we can see that at power on time we no longer to assert the reset GPIO as the first thing. The reset GPIO is _always_ asserted before powering on. Let's fix powering on to account for this. Fixes: afe10358e47a ("Input: elants_i2c - wire up regulator support") Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20221117123805.1.I9959ac561dd6e1e8e1ce7085e4de6167b27c574f@changeid Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/touchscreen/elants_i2c.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c index c09aefa2661d..ca9cee5851a0 100644 --- a/drivers/input/touchscreen/elants_i2c.c +++ b/drivers/input/touchscreen/elants_i2c.c @@ -1219,14 +1219,12 @@ static int elants_i2c_power_on(struct elants_data *ts) if (IS_ERR_OR_NULL(ts->reset_gpio)) return 0; - gpiod_set_value_cansleep(ts->reset_gpio, 1); - error = regulator_enable(ts->vcc33); if (error) { dev_err(&ts->client->dev, "failed to enable vcc33 regulator: %d\n", error); - goto release_reset_gpio; + return error; } error = regulator_enable(ts->vccio); @@ -1235,7 +1233,7 @@ static int elants_i2c_power_on(struct elants_data *ts) "failed to enable vccio regulator: %d\n", error); regulator_disable(ts->vcc33); - goto release_reset_gpio; + return error; } /* @@ -1244,7 +1242,6 @@ static int elants_i2c_power_on(struct elants_data *ts) */ udelay(ELAN_POWERON_DELAY_USEC); -release_reset_gpio: gpiod_set_value_cansleep(ts->reset_gpio, 0); if (error) return error; @@ -1352,7 +1349,7 @@ static int elants_i2c_probe(struct i2c_client *client, return error; } - ts->reset_gpio = devm_gpiod_get(&client->dev, "reset", GPIOD_OUT_LOW); + ts->reset_gpio = devm_gpiod_get(&client->dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(ts->reset_gpio)) { error = PTR_ERR(ts->reset_gpio); From 0369af6fe33d4053899b121b32e91f870b2cf0ae Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Tue, 8 Nov 2022 15:06:30 +0800 Subject: [PATCH 0240/4345] media: vidtv: Fix use-after-free in vidtv_bridge_dvb_init() [ Upstream commit ba8d9405935097e296bcf7a942c3a01df0edb865 ] KASAN reports a use-after-free: BUG: KASAN: use-after-free in dvb_dmxdev_release+0x4d5/0x5d0 [dvb_core] Call Trace: ... dvb_dmxdev_release+0x4d5/0x5d0 [dvb_core] vidtv_bridge_probe+0x7bf/0xa40 [dvb_vidtv_bridge] platform_probe+0xb6/0x170 ... Allocated by task 1238: ... dvb_register_device+0x1a7/0xa70 [dvb_core] dvb_dmxdev_init+0x2af/0x4a0 [dvb_core] vidtv_bridge_probe+0x766/0xa40 [dvb_vidtv_bridge] ... Freed by task 1238: dvb_register_device+0x6d2/0xa70 [dvb_core] dvb_dmxdev_init+0x2af/0x4a0 [dvb_core] vidtv_bridge_probe+0x766/0xa40 [dvb_vidtv_bridge] ... It is because the error handling in vidtv_bridge_dvb_init() is wrong. First, vidtv_bridge_dmx(dev)_init() will clean themselves when fail, but goto fail_dmx(_dev): calls release functions again, which causes use-after-free. Also, in fail_fe, fail_tuner_probe and fail_demod_probe, j = i will cause out-of-bound when i finished its loop (i == NUM_FE). And the loop releasing is wrong, although now NUM_FE is 1 so it won't cause problem. Fix this by correctly releasing everything. Fixes: f90cf6079bf6 ("media: vidtv: add a bridge driver") Signed-off-by: Chen Zhongjin Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- .../media/test-drivers/vidtv/vidtv_bridge.c | 24 +++++++------------ 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/drivers/media/test-drivers/vidtv/vidtv_bridge.c b/drivers/media/test-drivers/vidtv/vidtv_bridge.c index fc64d0c8492a..3c281265a9ec 100644 --- a/drivers/media/test-drivers/vidtv/vidtv_bridge.c +++ b/drivers/media/test-drivers/vidtv/vidtv_bridge.c @@ -456,26 +456,20 @@ fail_dmx_conn: for (j = j - 1; j >= 0; --j) dvb->demux.dmx.remove_frontend(&dvb->demux.dmx, &dvb->dmx_fe[j]); -fail_dmx_dev: dvb_dmxdev_release(&dvb->dmx_dev); -fail_dmx: +fail_dmx_dev: dvb_dmx_release(&dvb->demux); -fail_fe: - for (j = i; j >= 0; --j) - dvb_unregister_frontend(dvb->fe[j]); -fail_tuner_probe: - for (j = i; j >= 0; --j) - if (dvb->i2c_client_tuner[j]) - dvb_module_release(dvb->i2c_client_tuner[j]); - +fail_dmx: fail_demod_probe: - for (j = i; j >= 0; --j) - if (dvb->i2c_client_demod[j]) - dvb_module_release(dvb->i2c_client_demod[j]); - + for (i = i - 1; i >= 0; --i) { + dvb_unregister_frontend(dvb->fe[i]); +fail_fe: + dvb_module_release(dvb->i2c_client_tuner[i]); +fail_tuner_probe: + dvb_module_release(dvb->i2c_client_demod[i]); + } fail_adapter: dvb_unregister_adapter(&dvb->adapter); - fail_i2c: i2c_del_adapter(&dvb->i2c_adapter); From 49060c0da57a381563e482e331dc9d4c3725b41b Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 10 Nov 2022 16:24:23 +0800 Subject: [PATCH 0241/4345] media: solo6x10: fix possible memory leak in solo_sysfs_init() [ Upstream commit 7f5866dd96d95b74e439f6ee17b8abd8195179fb ] If device_register() returns error in solo_sysfs_init(), the name allocated by dev_set_name() need be freed. As comment of device_register() says, it should use put_device() to give up the reference in the error path. So fix this by calling put_device(), then the name can be freed in kobject_cleanup(). Fixes: dcae5dacbce5 ("[media] solo6x10: sync to latest code from Bluecherry's git repo") Signed-off-by: Yang Yingliang Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/pci/solo6x10/solo6x10-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/pci/solo6x10/solo6x10-core.c b/drivers/media/pci/solo6x10/solo6x10-core.c index d497afc7e7b7..4ebb1e020fad 100644 --- a/drivers/media/pci/solo6x10/solo6x10-core.c +++ b/drivers/media/pci/solo6x10/solo6x10-core.c @@ -420,6 +420,7 @@ static int solo_sysfs_init(struct solo_dev *solo_dev) solo_dev->nr_chans); if (device_register(dev)) { + put_device(dev); dev->parent = NULL; return -ENOMEM; } From 8470060019538dfe2801f613d94d00cce7eddf7e Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Fri, 11 Nov 2022 06:08:53 +0000 Subject: [PATCH 0242/4345] media: platform: exynos4-is: Fix error handling in fimc_md_init() [ Upstream commit b434422c45282a0573d8123239abc41fa72665d4 ] A problem about modprobe s5p_fimc failed is triggered with the following log given: [ 272.075275] Error: Driver 'exynos4-fimc' is already registered, aborting... modprobe: ERROR: could not insert 's5p_fimc': Device or resource busy The reason is that fimc_md_init() returns platform_driver_register() directly without checking its return value, if platform_driver_register() failed, it returns without unregister fimc_driver, resulting the s5p_fimc can never be installed later. A simple call graph is shown as below: fimc_md_init() fimc_register_driver() # register fimc_driver platform_driver_register() platform_driver_register() driver_register() bus_add_driver() dev = kzalloc(...) # OOM happened # return without unregister fimc_driver Fix by unregister fimc_driver when platform_driver_register() returns error. Fixes: d3953223b090 ("[media] s5p-fimc: Add the media device driver") Signed-off-by: Yuan Can Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/exynos4-is/fimc-core.c | 2 +- drivers/media/platform/exynos4-is/media-dev.c | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/exynos4-is/fimc-core.c b/drivers/media/platform/exynos4-is/fimc-core.c index 08d1f39a914c..60b28e6f739e 100644 --- a/drivers/media/platform/exynos4-is/fimc-core.c +++ b/drivers/media/platform/exynos4-is/fimc-core.c @@ -1174,7 +1174,7 @@ int __init fimc_register_driver(void) return platform_driver_register(&fimc_driver); } -void __exit fimc_unregister_driver(void) +void fimc_unregister_driver(void) { platform_driver_unregister(&fimc_driver); } diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c index a9ab2a28fc26..bd37011fb671 100644 --- a/drivers/media/platform/exynos4-is/media-dev.c +++ b/drivers/media/platform/exynos4-is/media-dev.c @@ -1582,7 +1582,11 @@ static int __init fimc_md_init(void) if (ret) return ret; - return platform_driver_register(&fimc_md_driver); + ret = platform_driver_register(&fimc_md_driver); + if (ret) + fimc_unregister_driver(); + + return ret; } static void __exit fimc_md_exit(void) From 49aa080951aa26974fac6e38bb1a023adc18c00d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 18 Dec 2019 11:39:07 +0100 Subject: [PATCH 0243/4345] media: videobuf-dma-contig: use dma_mmap_coherent [ Upstream commit b3dc3f8e49577840dc8ac8a365c5b3da4edb10b8 ] dma_alloc_coherent does not return a physical address, but a DMA address, which might be remapped or have an offset. Passing the DMA address to vm_iomap_memory is thus broken. Use the proper dma_mmap_coherent helper instead, and stop passing __GFP_COMP to dma_alloc_coherent, as the memory management inside the DMA allocator is hidden from the callers and does not require it. With this the gfp_t argument to __videobuf_dc_alloc can be removed and hard coded to GFP_KERNEL. Fixes: a8f3c203e19b ("[media] videobuf-dma-contig: add cache support") Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/media/v4l2-core/videobuf-dma-contig.c | 22 +++++++------------ 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c index 52312ce2ba05..f2c439359557 100644 --- a/drivers/media/v4l2-core/videobuf-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf-dma-contig.c @@ -36,12 +36,11 @@ struct videobuf_dma_contig_memory { static int __videobuf_dc_alloc(struct device *dev, struct videobuf_dma_contig_memory *mem, - unsigned long size, gfp_t flags) + unsigned long size) { mem->size = size; - mem->vaddr = dma_alloc_coherent(dev, mem->size, - &mem->dma_handle, flags); - + mem->vaddr = dma_alloc_coherent(dev, mem->size, &mem->dma_handle, + GFP_KERNEL); if (!mem->vaddr) { dev_err(dev, "memory alloc size %ld failed\n", mem->size); return -ENOMEM; @@ -258,8 +257,7 @@ static int __videobuf_iolock(struct videobuf_queue *q, return videobuf_dma_contig_user_get(mem, vb); /* allocate memory for the read() method */ - if (__videobuf_dc_alloc(q->dev, mem, PAGE_ALIGN(vb->size), - GFP_KERNEL)) + if (__videobuf_dc_alloc(q->dev, mem, PAGE_ALIGN(vb->size))) return -ENOMEM; break; case V4L2_MEMORY_OVERLAY: @@ -295,22 +293,18 @@ static int __videobuf_mmap_mapper(struct videobuf_queue *q, BUG_ON(!mem); MAGIC_CHECK(mem->magic, MAGIC_DC_MEM); - if (__videobuf_dc_alloc(q->dev, mem, PAGE_ALIGN(buf->bsize), - GFP_KERNEL | __GFP_COMP)) + if (__videobuf_dc_alloc(q->dev, mem, PAGE_ALIGN(buf->bsize))) goto error; - /* Try to remap memory */ - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - /* the "vm_pgoff" is just used in v4l2 to find the * corresponding buffer data structure which is allocated * earlier and it does not mean the offset from the physical * buffer start address as usual. So set it to 0 to pass - * the sanity check in vm_iomap_memory(). + * the sanity check in dma_mmap_coherent(). */ vma->vm_pgoff = 0; - - retval = vm_iomap_memory(vma, mem->dma_handle, mem->size); + retval = dma_mmap_coherent(q->dev, vma, mem->vaddr, mem->dma_handle, + mem->size); if (retval) { dev_err(q->dev, "mmap: remap failed with error %d. ", retval); From 9920e87a84ec491f0791c76eb42d2524301989bd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:55:46 -0700 Subject: [PATCH 0244/4345] inet: add READ_ONCE(sk->sk_bound_dev_if) in inet_csk_bind_conflict() [ Upstream commit d2c135619cb89d1d5693df81ab408c5e8e97e898 ] inet_csk_bind_conflict() can access sk->sk_bound_dev_if for unlocked sockets. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/inet_connection_sock.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4d9713324003..e54abccdffd0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -147,10 +147,14 @@ static int inet_csk_bind_conflict(const struct sock *sk, */ sk_for_each_bound(sk2, &tb->owners) { - if (sk != sk2 && - (!sk->sk_bound_dev_if || - !sk2->sk_bound_dev_if || - sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { + int bound_dev_if2; + + if (sk == sk2) + continue; + bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); + if ((!sk->sk_bound_dev_if || + !bound_dev_if2 || + sk->sk_bound_dev_if == bound_dev_if2)) { if (reuse && sk2->sk_reuse && sk2->sk_state != TCP_LISTEN) { if ((!relax || From 0d6ae25da5cbe08109c6dd0b265a5ddc71bce25e Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 21 Nov 2022 10:03:39 -0800 Subject: [PATCH 0245/4345] bpf: Move skb->len == 0 checks into __bpf_redirect [ Upstream commit 114039b342014680911c35bd6b72624180fd669a ] To avoid potentially breaking existing users. Both mac/no-mac cases have to be amended; mac_header >= network_header is not enough (verified with a new test, see next patch). Fixes: fd1894224407 ("bpf: Don't redirect packets with invalid pkt_len") Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20221121180340.1983627-1-sdf@google.com Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- net/bpf/test_run.c | 3 --- net/core/filter.c | 7 ++++++- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 717b01ff9b2b..7df14a0e380c 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -442,9 +442,6 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) { struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb; - if (!skb->len) - return -EINVAL; - if (!__skb) return 0; diff --git a/net/core/filter.c b/net/core/filter.c index 4c22e6d1da74..ef7e74260afc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2125,6 +2125,11 @@ static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, { unsigned int mlen = skb_network_offset(skb); + if (unlikely(skb->len <= mlen)) { + kfree_skb(skb); + return -ERANGE; + } + if (mlen) { __skb_pull(skb, mlen); @@ -2146,7 +2151,7 @@ static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, u32 flags) { /* Verify that a link layer header is carried */ - if (unlikely(skb->mac_header >= skb->network_header)) { + if (unlikely(skb->mac_header >= skb->network_header || skb->len == 0)) { kfree_skb(skb); return -ERANGE; } From ad2d0a3dc224657002ce65aa8a50ce3e86e7cd9f Mon Sep 17 00:00:00 2001 From: Marcus Folkesson Date: Thu, 17 Nov 2022 13:13:26 +0100 Subject: [PATCH 0246/4345] HID: hid-sensor-custom: set fixed size for custom attributes [ Upstream commit 9d013910df22de91333a0acc81d1dbb115bd76f6 ] This is no bugfix (so no Fixes: tag is necessary) as it is taken care of in hid_sensor_custom_add_attributes(). The motivation for this patch is that: hid_sensor_custom_field.attr_name and hid_sensor_custom_field.attrs has the size of HID_CUSTOM_TOTAL_ATTRS and used in same context. We compare against HID_CUSTOM_TOTAL_ATTRS when looping through hid_custom_attrs. We will silent the smatch error: hid_sensor_custom_add_attributes() error: buffer overflow 'hid_custom_attrs' 8 <= 10 Signed-off-by: Marcus Folkesson Acked-by: Jonathan Cameron Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-sensor-custom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index 4d25577a8573..971600a6397a 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -59,7 +59,7 @@ struct hid_sensor_sample { u32 raw_len; } __packed; -static struct attribute hid_custom_attrs[] = { +static struct attribute hid_custom_attrs[HID_CUSTOM_TOTAL_ATTRS] = { {.name = "name", .mode = S_IRUGO}, {.name = "units", .mode = S_IRUGO}, {.name = "unit-expo", .mode = S_IRUGO}, From 88550b4446478eb7e3c8337e8a641291e5b7e5a1 Mon Sep 17 00:00:00 2001 From: Baisong Zhong Date: Mon, 21 Nov 2022 19:00:44 +0800 Subject: [PATCH 0247/4345] ALSA: pcm: fix undefined behavior in bit shift for SNDRV_PCM_RATE_KNOT [ Upstream commit b5172e62458f8e6ff359e5f096044a488db90ac5 ] Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. The UBSAN warning calltrace like below: UBSAN: shift-out-of-bounds in sound/core/pcm_native.c:2676:21 left shift of 1 by 31 places cannot be represented in type 'int' ... Call Trace: dump_stack_lvl+0x8d/0xcf ubsan_epilogue+0xa/0x44 __ubsan_handle_shift_out_of_bounds+0x1e7/0x208 snd_pcm_open_substream+0x9f0/0xa90 snd_pcm_oss_open.part.26+0x313/0x670 snd_pcm_oss_open+0x30/0x40 soundcore_open+0x18b/0x2e0 chrdev_open+0xe2/0x270 do_dentry_open+0x2f7/0x620 path_openat+0xd66/0xe70 do_filp_open+0xe3/0x170 do_sys_openat2+0x357/0x4a0 do_sys_open+0x87/0xd0 do_syscall_64+0x34/0x80 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Baisong Zhong Link: https://lore.kernel.org/r/20221121110044.3115686-1-zhongbaisong@huawei.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- include/sound/pcm.h | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 5ffc2efedd9f..6554a9f71c62 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -106,24 +106,24 @@ struct snd_pcm_ops { #define SNDRV_PCM_POS_XRUN ((snd_pcm_uframes_t)-1) /* If you change this don't forget to change rates[] table in pcm_native.c */ -#define SNDRV_PCM_RATE_5512 (1<<0) /* 5512Hz */ -#define SNDRV_PCM_RATE_8000 (1<<1) /* 8000Hz */ -#define SNDRV_PCM_RATE_11025 (1<<2) /* 11025Hz */ -#define SNDRV_PCM_RATE_16000 (1<<3) /* 16000Hz */ -#define SNDRV_PCM_RATE_22050 (1<<4) /* 22050Hz */ -#define SNDRV_PCM_RATE_32000 (1<<5) /* 32000Hz */ -#define SNDRV_PCM_RATE_44100 (1<<6) /* 44100Hz */ -#define SNDRV_PCM_RATE_48000 (1<<7) /* 48000Hz */ -#define SNDRV_PCM_RATE_64000 (1<<8) /* 64000Hz */ -#define SNDRV_PCM_RATE_88200 (1<<9) /* 88200Hz */ -#define SNDRV_PCM_RATE_96000 (1<<10) /* 96000Hz */ -#define SNDRV_PCM_RATE_176400 (1<<11) /* 176400Hz */ -#define SNDRV_PCM_RATE_192000 (1<<12) /* 192000Hz */ -#define SNDRV_PCM_RATE_352800 (1<<13) /* 352800Hz */ -#define SNDRV_PCM_RATE_384000 (1<<14) /* 384000Hz */ +#define SNDRV_PCM_RATE_5512 (1U<<0) /* 5512Hz */ +#define SNDRV_PCM_RATE_8000 (1U<<1) /* 8000Hz */ +#define SNDRV_PCM_RATE_11025 (1U<<2) /* 11025Hz */ +#define SNDRV_PCM_RATE_16000 (1U<<3) /* 16000Hz */ +#define SNDRV_PCM_RATE_22050 (1U<<4) /* 22050Hz */ +#define SNDRV_PCM_RATE_32000 (1U<<5) /* 32000Hz */ +#define SNDRV_PCM_RATE_44100 (1U<<6) /* 44100Hz */ +#define SNDRV_PCM_RATE_48000 (1U<<7) /* 48000Hz */ +#define SNDRV_PCM_RATE_64000 (1U<<8) /* 64000Hz */ +#define SNDRV_PCM_RATE_88200 (1U<<9) /* 88200Hz */ +#define SNDRV_PCM_RATE_96000 (1U<<10) /* 96000Hz */ +#define SNDRV_PCM_RATE_176400 (1U<<11) /* 176400Hz */ +#define SNDRV_PCM_RATE_192000 (1U<<12) /* 192000Hz */ +#define SNDRV_PCM_RATE_352800 (1U<<13) /* 352800Hz */ +#define SNDRV_PCM_RATE_384000 (1U<<14) /* 384000Hz */ -#define SNDRV_PCM_RATE_CONTINUOUS (1<<30) /* continuous range */ -#define SNDRV_PCM_RATE_KNOT (1<<31) /* supports more non-continuos rates */ +#define SNDRV_PCM_RATE_CONTINUOUS (1U<<30) /* continuous range */ +#define SNDRV_PCM_RATE_KNOT (1U<<31) /* supports more non-continuos rates */ #define SNDRV_PCM_RATE_8000_44100 (SNDRV_PCM_RATE_8000|SNDRV_PCM_RATE_11025|\ SNDRV_PCM_RATE_16000|SNDRV_PCM_RATE_22050|\ From d7198b63cbeeb8b4b9fa6dfe0a39074d49513f4f Mon Sep 17 00:00:00 2001 From: Baisong Zhong Date: Mon, 21 Nov 2022 19:16:30 +0800 Subject: [PATCH 0248/4345] ALSA: seq: fix undefined behavior in bit shift for SNDRV_SEQ_FILTER_USE_EVENT [ Upstream commit cf59e1e4c79bf741905484cdb13c130b53576a16 ] Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. The UBSAN warning calltrace like below: UBSAN: shift-out-of-bounds in sound/core/seq/seq_clientmgr.c:509:22 left shift of 1 by 31 places cannot be represented in type 'int' ... Call Trace: dump_stack_lvl+0x8d/0xcf ubsan_epilogue+0xa/0x44 __ubsan_handle_shift_out_of_bounds+0x1e7/0x208 snd_seq_deliver_single_event.constprop.21+0x191/0x2f0 snd_seq_deliver_event+0x1a2/0x350 snd_seq_kernel_client_dispatch+0x8b/0xb0 snd_seq_client_notify_subscription+0x72/0xa0 snd_seq_ioctl_subscribe_port+0x128/0x160 snd_seq_kernel_client_ctl+0xce/0xf0 snd_seq_oss_create_client+0x109/0x15b alsa_seq_oss_init+0x11c/0x1aa do_one_initcall+0x80/0x440 kernel_init_freeable+0x370/0x3c3 kernel_init+0x1b/0x190 ret_from_fork+0x1f/0x30 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Baisong Zhong Link: https://lore.kernel.org/r/20221121111630.3119259-1-zhongbaisong@huawei.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- include/uapi/sound/asequencer.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index a75e14edc957..dbd60f48b4b0 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -344,10 +344,10 @@ typedef int __bitwise snd_seq_client_type_t; #define KERNEL_CLIENT ((__force snd_seq_client_type_t) 2) /* event filter flags */ -#define SNDRV_SEQ_FILTER_BROADCAST (1<<0) /* accept broadcast messages */ -#define SNDRV_SEQ_FILTER_MULTICAST (1<<1) /* accept multicast messages */ -#define SNDRV_SEQ_FILTER_BOUNCE (1<<2) /* accept bounce event in error */ -#define SNDRV_SEQ_FILTER_USE_EVENT (1<<31) /* use event filter */ +#define SNDRV_SEQ_FILTER_BROADCAST (1U<<0) /* accept broadcast messages */ +#define SNDRV_SEQ_FILTER_MULTICAST (1U<<1) /* accept multicast messages */ +#define SNDRV_SEQ_FILTER_BOUNCE (1U<<2) /* accept bounce event in error */ +#define SNDRV_SEQ_FILTER_USE_EVENT (1U<<31) /* use event filter */ struct snd_seq_client_info { int client; /* client number to inquire */ From a065be02433e0bfb053789be23df028b317f9b56 Mon Sep 17 00:00:00 2001 From: Wang ShaoBo Date: Wed, 23 Nov 2022 11:46:16 +0800 Subject: [PATCH 0249/4345] regulator: core: use kfree_const() to free space conditionally [ Upstream commit dc8d006d15b623c1d80b90b45d6dcb6e890dad09 ] Use kfree_const() to free supply_name conditionally in create_regulator() as supply_name may be allocated from kmalloc() or directly from .rodata section. Fixes: 87fe29b61f95 ("regulator: push allocations in create_regulator() outside of lock") Signed-off-by: Wang ShaoBo Link: https://lore.kernel.org/r/20221123034616.3609537-1-bobo.shaobowang@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 876afa3919c1..60c0be2ea5c5 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1645,7 +1645,7 @@ static struct regulator *create_regulator(struct regulator_dev *rdev, regulator = kzalloc(sizeof(*regulator), GFP_KERNEL); if (regulator == NULL) { - kfree(supply_name); + kfree_const(supply_name); return NULL; } From f4d70c139d313948e02360304a6cbcd3a4f5deb5 Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Wed, 23 Nov 2022 17:12:01 +0800 Subject: [PATCH 0250/4345] clk: rockchip: Fix memory leak in rockchip_clk_register_pll() [ Upstream commit 739a6a6bbdb793bd57938cb24aa5a6df89983546 ] If clk_register() fails, @pll->rate_table may have allocated memory by kmemdup(), so it needs to be freed, otherwise will cause memory leak issue, this patch fixes it. Fixes: 90c590254051 ("clk: rockchip: add clock type for pll clocks and pll used on rk3066") Signed-off-by: Xiu Jianfeng Link: https://lore.kernel.org/r/20221123091201.199819-1-xiujianfeng@huawei.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- drivers/clk/rockchip/clk-pll.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/rockchip/clk-pll.c b/drivers/clk/rockchip/clk-pll.c index bbbf9ce42867..d0bd513ff3c3 100644 --- a/drivers/clk/rockchip/clk-pll.c +++ b/drivers/clk/rockchip/clk-pll.c @@ -981,6 +981,7 @@ struct clk *rockchip_clk_register_pll(struct rockchip_clk_provider *ctx, return mux_clk; err_pll: + kfree(pll->rate_table); clk_unregister(mux_clk); mux_clk = pll_clk; err_mux: From 3725a8f26bdbc38dfdf545836117f1e069277c91 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 17 Nov 2022 23:00:03 +0800 Subject: [PATCH 0251/4345] drm/amdgpu: fix pci device refcount leak [ Upstream commit b85e285e3d6352b02947fc1b72303673dfacb0aa ] As comment of pci_get_domain_bus_and_slot() says, it returns a pci device with refcount increment, when finish using it, the caller must decrement the reference count by calling pci_dev_put(). So before returning from amdgpu_device_resume|suspend_display_audio(), pci_dev_put() is called to avoid refcount leak. Fixes: 3f12acc8d6d4 ("drm/amdgpu: put the audio codec into suspend state before gpu reset V3") Reviewed-by: Evan Quan Signed-off-by: Yang Yingliang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index bde0496d2f15..8bd887fb6e63 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4443,6 +4443,8 @@ static void amdgpu_device_resume_display_audio(struct amdgpu_device *adev) pm_runtime_enable(&(p->dev)); pm_runtime_resume(&(p->dev)); } + + pci_dev_put(p); } static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev) @@ -4481,6 +4483,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev) if (expires < ktime_get_mono_fast_ns()) { dev_warn(adev->dev, "failed to suspend display audio\n"); + pci_dev_put(p); /* TODO: abort the succeeding gpu reset? */ return -ETIMEDOUT; } @@ -4488,6 +4491,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev) pm_runtime_disable(&(p->dev)); + pci_dev_put(p); return 0; } From 7d1e0d237c4cb59eb209063f958d2bf911c6904d Mon Sep 17 00:00:00 2001 From: Jonathan Toppins Date: Tue, 22 Nov 2022 16:24:29 -0500 Subject: [PATCH 0252/4345] bonding: fix link recovery in mode 2 when updelay is nonzero [ Upstream commit f8a65ab2f3ff7410921ebbf0dc55453102c33c56 ] Before this change when a bond in mode 2 lost link, all of its slaves lost link, the bonding device would never recover even after the expiration of updelay. This change removes the updelay when the bond currently has no usable links. Conforming to bonding.txt section 13.1 paragraph 4. Fixes: 41f891004063 ("bonding: ignore updelay param when there is no active slave") Signed-off-by: Jonathan Toppins Acked-by: Jay Vosburgh Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/bonding/bond_main.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index f38a6ce5749b..e66092518fdd 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2398,7 +2398,16 @@ static int bond_miimon_inspect(struct bonding *bond) struct slave *slave; bool ignore_updelay; - ignore_updelay = !rcu_dereference(bond->curr_active_slave); + if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { + ignore_updelay = !rcu_dereference(bond->curr_active_slave); + } else { + struct bond_up_slave *usable_slaves; + + usable_slaves = rcu_dereference(bond->usable_slaves); + + if (usable_slaves && usable_slaves->count == 0) + ignore_updelay = true; + } bond_for_each_slave_rcu(bond, slave, iter) { bond_propose_link_state(slave, BOND_LINK_NOCHANGE); From 1d0c2b762dad2b8dd166e17c0e90b88b86a3284f Mon Sep 17 00:00:00 2001 From: Zheng Yongjun Date: Sat, 19 Nov 2022 07:33:07 +0000 Subject: [PATCH 0253/4345] mtd: maps: pxa2xx-flash: fix memory leak in probe [ Upstream commit 2399401feee27c639addc5b7e6ba519d3ca341bf ] Free 'info' upon remapping error to avoid a memory leak. Fixes: e644f7d62894 ("[MTD] MAPS: Merge Lubbock and Mainstone drivers into common PXA2xx driver") Signed-off-by: Zheng Yongjun [: Reword the commit log] Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20221119073307.22929-1-zhengyongjun3@huawei.com Signed-off-by: Sasha Levin --- drivers/mtd/maps/pxa2xx-flash.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c index 7d96758a8f04..6e5e55755970 100644 --- a/drivers/mtd/maps/pxa2xx-flash.c +++ b/drivers/mtd/maps/pxa2xx-flash.c @@ -66,6 +66,7 @@ static int pxa2xx_flash_probe(struct platform_device *pdev) if (!info->map.virt) { printk(KERN_WARNING "Failed to ioremap %s\n", info->map.name); + kfree(info); return -ENOMEM; } info->map.cached = ioremap_cache(info->map.phys, info->map.size); @@ -87,6 +88,7 @@ static int pxa2xx_flash_probe(struct platform_device *pdev) iounmap((void *)info->map.virt); if (info->map.cached) iounmap(info->map.cached); + kfree(info); return -EIO; } info->mtd->dev.parent = &pdev->dev; From b73fac67f3559bd0f5d093b06cef3747569f9c07 Mon Sep 17 00:00:00 2001 From: Xiaomeng Tong Date: Wed, 6 Apr 2022 21:04:44 +0200 Subject: [PATCH 0254/4345] drbd: fix an invalid memory access caused by incorrect use of list iterator MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ae4d37b5df749926891583d42a6801b5da11e3c1 ] The bug is here: idr_remove(&connection->peer_devices, vnr); If the previous for_each_connection() don't exit early (no goto hit inside the loop), the iterator 'connection' after the loop will be a bogus pointer to an invalid structure object containing the HEAD (&resource->connections). As a result, the use of 'connection' above will lead to a invalid memory access (including a possible invalid free as idr_remove could call free_layer). The original intention should have been to remove all peer_devices, but the following lines have already done the work. So just remove this line and the unneeded label, to fix this bug. Cc: stable@vger.kernel.org Fixes: c06ece6ba6f1b ("drbd: Turn connection->volumes into connection->peer_devices") Signed-off-by: Xiaomeng Tong Reviewed-by: Christoph Böhmwalder Reviewed-by: Lars Ellenberg Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/drbd/drbd_main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 51450f7c81af..420bdaf8c356 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2819,7 +2819,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig if (init_submitter(device)) { err = ERR_NOMEM; - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; } add_disk(disk); @@ -2836,8 +2836,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_debugfs_device_add(device); return NO_ERROR; -out_idr_remove_vol: - idr_remove(&connection->peer_devices, vnr); out_idr_remove_from_resource: for_each_connection_safe(connection, n, resource) { peer_device = idr_remove(&connection->peer_devices, vnr); From 4518d7cc38b7d1a7ce5a7878ca601c91e19fe47d Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Thu, 24 Nov 2022 14:05:10 +0000 Subject: [PATCH 0255/4345] ASoC: qcom: Add checks for devm_kcalloc [ Upstream commit 1bf5ee979076ceb121ee51c95197d890b1cee7f4 ] As the devm_kcalloc may return NULL, the return value needs to be checked to avoid NULL poineter dereference. Fixes: 24caf8d9eb10 ("ASoC: qcom: lpass-sc7180: Add platform driver for lpass audio") Signed-off-by: Yuan Can Link: https://lore.kernel.org/r/20221124140510.63468-1-yuancan@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/qcom/lpass-sc7180.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/qcom/lpass-sc7180.c b/sound/soc/qcom/lpass-sc7180.c index c647e627897a..cb4e9017cd77 100644 --- a/sound/soc/qcom/lpass-sc7180.c +++ b/sound/soc/qcom/lpass-sc7180.c @@ -129,6 +129,9 @@ static int sc7180_lpass_init(struct platform_device *pdev) drvdata->clks = devm_kcalloc(dev, variant->num_clks, sizeof(*drvdata->clks), GFP_KERNEL); + if (!drvdata->clks) + return -ENOMEM; + drvdata->num_clks = variant->num_clks; for (i = 0; i < drvdata->num_clks; i++) From 14d85b600bb1f6f8ef61fa8fc1907e2e623d8350 Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Thu, 10 Nov 2022 07:26:33 +0000 Subject: [PATCH 0256/4345] media: vimc: Fix wrong function called when vimc_init() fails [ Upstream commit f74d3f326d1d5b8951ce263c59a121ecfa65e7c0 ] In vimc_init(), when platform_driver_register(&vimc_pdrv) fails, platform_driver_unregister(&vimc_pdrv) is wrongly called rather than platform_device_unregister(&vimc_pdev), which causes kernel warning: Unexpected driver unregister! WARNING: CPU: 1 PID: 14517 at drivers/base/driver.c:270 driver_unregister+0x8f/0xb0 RIP: 0010:driver_unregister+0x8f/0xb0 Call Trace: vimc_init+0x7d/0x1000 [vimc] do_one_initcall+0xd0/0x4e0 do_init_module+0x1cf/0x6b0 load_module+0x65c2/0x7820 Fixes: 4a29b7090749 ("[media] vimc: Subdevices as modules") Signed-off-by: Chen Zhongjin Signed-off-by: Shuah Khan Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/test-drivers/vimc/vimc-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/test-drivers/vimc/vimc-core.c b/drivers/media/test-drivers/vimc/vimc-core.c index 4b0ae6f51d76..857529ce3638 100644 --- a/drivers/media/test-drivers/vimc/vimc-core.c +++ b/drivers/media/test-drivers/vimc/vimc-core.c @@ -357,7 +357,7 @@ static int __init vimc_init(void) if (ret) { dev_err(&vimc_pdev.dev, "platform driver registration failed (err=%d)\n", ret); - platform_driver_unregister(&vimc_pdrv); + platform_device_unregister(&vimc_pdev); return ret; } From dabf7b675c1672a4b564e603f4cdd06649fbc372 Mon Sep 17 00:00:00 2001 From: Gautam Menghani Date: Wed, 19 Oct 2022 06:02:14 +0100 Subject: [PATCH 0257/4345] media: imon: fix a race condition in send_packet() [ Upstream commit 813ceef062b53d68f296aa3cb944b21a091fabdb ] The function send_packet() has a race condition as follows: func send_packet() { // do work call usb_submit_urb() mutex_unlock() wait_for_event_interruptible() <-- lock gone mutex_lock() } func vfd_write() { mutex_lock() call send_packet() <- prev call is not completed mutex_unlock() } When the mutex is unlocked and the function send_packet() waits for the call to complete, vfd_write() can start another call, which leads to the "URB submitted while active" warning in usb_submit_urb(). Fix this by removing the mutex_unlock() call in send_packet() and using mutex_lock_interruptible(). Link: https://syzkaller.appspot.com/bug?id=e378e6a51fbe6c5cc43e34f131cc9a315ef0337e Fixes: 21677cfc562a ("V4L/DVB: ir-core: add imon driver") Reported-by: syzbot+0c3cb6dc05fbbdc3ad66@syzkaller.appspotmail.com Signed-off-by: Gautam Menghani Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/rc/imon.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c index bc9ac6002e25..98a38755c694 100644 --- a/drivers/media/rc/imon.c +++ b/drivers/media/rc/imon.c @@ -646,15 +646,14 @@ static int send_packet(struct imon_context *ictx) pr_err_ratelimited("error submitting urb(%d)\n", retval); } else { /* Wait for transmission to complete (or abort) */ - mutex_unlock(&ictx->lock); retval = wait_for_completion_interruptible( &ictx->tx.finished); if (retval) { usb_kill_urb(ictx->tx_urb); pr_err_ratelimited("task interrupted\n"); } - mutex_lock(&ictx->lock); + ictx->tx.busy = false; retval = ictx->tx.status; if (retval) pr_err_ratelimited("packet tx failed (%d)\n", retval); @@ -958,7 +957,8 @@ static ssize_t vfd_write(struct file *file, const char __user *buf, if (ictx->disconnected) return -ENODEV; - mutex_lock(&ictx->lock); + if (mutex_lock_interruptible(&ictx->lock)) + return -ERESTARTSYS; if (!ictx->dev_present_intf0) { pr_err_ratelimited("no iMON device present\n"); From 9916497a12397ef59b30e1b02601a31ec07e157c Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 17 Nov 2022 12:36:34 +0100 Subject: [PATCH 0258/4345] clk: imx: replace osc_hdmi with dummy [ Upstream commit e7fa365ff66f16772dc06b480cd78f858d10856b ] There is no occurrence of the hdmi oscillator in the reference manual (document IMX8MNRM Rev 2, 07/2022). Further, if we consider the indexes 76-81 and 134 of the "Clock Root" table of chapter 5 of the RM, there is no entry for the source select bits 101b, which is the setting referenced by "osc_hdmi". Fix by renaming "osc_hdmi" with "dummy", a clock which has already been used for missing source select bits. Tested on the BSH SystemMaster (SMM) S2 board. Fixes: 96d6392b54dbb ("clk: imx: Add support for i.MX8MN clock driver") Signed-off-by: Dario Binacchi Acked-by: Marco Felsch Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20221117113637.1978703-3-dario.binacchi@amarulasolutions.com Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx8mn.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c index db122d94db58..8a49e072d6e8 100644 --- a/drivers/clk/imx/clk-imx8mn.c +++ b/drivers/clk/imx/clk-imx8mn.c @@ -105,27 +105,27 @@ static const char * const imx8mn_disp_pixel_sels[] = {"osc_24m", "video_pll1_out "sys_pll3_out", "clk_ext4", }; static const char * const imx8mn_sai2_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out", - "video_pll1_out", "sys_pll1_133m", "osc_hdmi", + "video_pll1_out", "sys_pll1_133m", "dummy", "clk_ext3", "clk_ext4", }; static const char * const imx8mn_sai3_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out", - "video_pll1_out", "sys_pll1_133m", "osc_hdmi", + "video_pll1_out", "sys_pll1_133m", "dummy", "clk_ext3", "clk_ext4", }; static const char * const imx8mn_sai5_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out", - "video_pll1_out", "sys_pll1_133m", "osc_hdmi", + "video_pll1_out", "sys_pll1_133m", "dummy", "clk_ext2", "clk_ext3", }; static const char * const imx8mn_sai6_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out", - "video_pll1_out", "sys_pll1_133m", "osc_hdmi", + "video_pll1_out", "sys_pll1_133m", "dummy", "clk_ext3", "clk_ext4", }; static const char * const imx8mn_sai7_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out", - "video_pll1_out", "sys_pll1_133m", "osc_hdmi", + "video_pll1_out", "sys_pll1_133m", "dummy", "clk_ext3", "clk_ext4", }; static const char * const imx8mn_spdif1_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out", - "video_pll1_out", "sys_pll1_133m", "osc_hdmi", + "video_pll1_out", "sys_pll1_133m", "dummy", "clk_ext2", "clk_ext3", }; static const char * const imx8mn_enet_ref_sels[] = {"osc_24m", "sys_pll2_125m", "sys_pll2_50m", From 05be5d56f7adfbd89dae445ab4f9d15868c53a7f Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Fri, 25 Nov 2022 07:01:56 +0000 Subject: [PATCH 0259/4345] pinctrl: pinconf-generic: add missing of_node_put() [ Upstream commit 5ead93289815a075d43c415e35c8beafafb801c9 ] of_node_put() needs to be called when jumping out of the loop, since for_each_available_child_of_node() will increase the refcount of node. Fixes: c7289500e29d ("pinctrl: pinconf-generic: scan also referenced phandle node") Signed-off-by: ZhangPeng Link: https://lore.kernel.org/r/20221125070156.3535855-1-zhangpeng362@huawei.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinconf-generic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index 42e27dba62e2..762abb0dfebb 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -393,8 +393,10 @@ int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev, for_each_available_child_of_node(np_config, np) { ret = pinconf_generic_dt_subnode_to_map(pctldev, np, map, &reserved_maps, num_maps, type); - if (ret < 0) + if (ret < 0) { + of_node_put(np); goto exit; + } } return 0; From e34cf6caccf5bbb3698ed7d49f2f4a3b8d9ebd91 Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Tue, 8 Nov 2022 03:30:05 +0000 Subject: [PATCH 0260/4345] media: dvb-core: Fix ignored return value in dvb_register_frontend() [ Upstream commit a574359e2e71ce16be212df3a082ed60a4bd2c5f ] In dvb_register_frontend(), dvb_register_device() is possible to fail but its return value is ignored. It will cause use-after-free when module is removed, because in dvb_unregister_frontend() it tries to unregister a not registered device. BUG: KASAN: use-after-free in dvb_remove_device+0x18b/0x1f0 [dvb_core] Read of size 4 at addr ffff88800dff4824 by task rmmod/428 CPU: 3 PID: 428 Comm: rmmod Call Trace: ... dvb_remove_device+0x18b/0x1f0 [dvb_core] dvb_unregister_frontend+0x7b/0x130 [dvb_core] vidtv_bridge_remove+0x6e/0x160 [dvb_vidtv_bridge] ... Fix this by catching return value of dvb_register_device(). However the fe->refcount can't be put to zero immediately, because there are still modules calling dvb_frontend_detach() when dvb_register_frontend() fails. Link: https://lore.kernel.org/linux-media/20221108033005.169095-1-chenzhongjin@huawei.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Chen Zhongjin Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/dvb-core/dvb_frontend.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index 06ea30a689d7..b28ea7204f23 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -2961,6 +2961,7 @@ int dvb_register_frontend(struct dvb_adapter *dvb, .name = fe->ops.info.name, #endif }; + int ret; dev_dbg(dvb->device, "%s:\n", __func__); @@ -2994,8 +2995,13 @@ int dvb_register_frontend(struct dvb_adapter *dvb, "DVB: registering adapter %i frontend %i (%s)...\n", fe->dvb->num, fe->id, fe->ops.info.name); - dvb_register_device(fe->dvb, &fepriv->dvbdev, &dvbdev_template, + ret = dvb_register_device(fe->dvb, &fepriv->dvbdev, &dvbdev_template, fe, DVB_DEVICE_FRONTEND, 0); + if (ret) { + dvb_frontend_put(fe); + mutex_unlock(&frontend_mutex); + return ret; + } /* * Initialize the cache to the proper values according with the From 559891d430e3f3a178040c4371ed419edbfa7d65 Mon Sep 17 00:00:00 2001 From: Baisong Zhong Date: Sun, 20 Nov 2022 06:59:18 +0000 Subject: [PATCH 0261/4345] media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer() [ Upstream commit 0ed554fd769a19ea8464bb83e9ac201002ef74ad ] Wei Chen reports a kernel bug as blew: general protection fault, probably for non-canonical address KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] ... Call Trace: __i2c_transfer+0x77e/0x1930 drivers/i2c/i2c-core-base.c:2109 i2c_transfer+0x1d5/0x3d0 drivers/i2c/i2c-core-base.c:2170 i2cdev_ioctl_rdwr+0x393/0x660 drivers/i2c/i2c-dev.c:297 i2cdev_ioctl+0x75d/0x9f0 drivers/i2c/i2c-dev.c:458 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xfb/0x170 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fd834a8bded In az6027_i2c_xfer(), if msg[i].addr is 0x99, a null-ptr-deref will caused when accessing msg[i].buf. For msg[i].len is 0 and msg[i].buf is null. Fix this by checking msg[i].len in az6027_i2c_xfer(). Link: https://lore.kernel.org/lkml/CAO4mrfcPHB5aQJO=mpqV+p8mPLNg-Fok0gw8gZ=zemAfMGTzMg@mail.gmail.com/ Link: https://lore.kernel.org/linux-media/20221120065918.2160782-1-zhongbaisong@huawei.com Fixes: 76f9a820c867 ("V4L/DVB: AZ6027: Initial import of the driver") Reported-by: Wei Chen Signed-off-by: Baisong Zhong Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb/az6027.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/media/usb/dvb-usb/az6027.c b/drivers/media/usb/dvb-usb/az6027.c index 86788771175b..32b4ee65c280 100644 --- a/drivers/media/usb/dvb-usb/az6027.c +++ b/drivers/media/usb/dvb-usb/az6027.c @@ -975,6 +975,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n if (msg[i].addr == 0x99) { req = 0xBE; index = 0; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } value = msg[i].buf[0] & 0x00ff; length = 1; az6027_usb_out_op(d, req, value, index, data, length); From 54ab1276001b11312dc144e84a7805be420b70db Mon Sep 17 00:00:00 2001 From: Aakarsh Jain Date: Mon, 14 Nov 2022 11:50:23 +0000 Subject: [PATCH 0262/4345] media: s5p-mfc: Add variant data for MFC v7 hardware for Exynos 3250 SoC [ Upstream commit f50ebe10f5d8092c37e2bd430c78e03bf38b1e20 ] Commit 5441e9dafdfc6dc40 ("[media] s5p-mfc: Core support for MFC v7") which adds mfc v7 support for Exynos3250 and use the same compatible string as used by Exynos5240 but both the IPs are a bit different in terms of IP clock. Add variant driver data based on the new compatible string "samsung,exynos3250-mfc" for Exynos3250 SoC. Suggested-by: Alim Akhtar Fixes: 5441e9dafdfc ("[media] s5p-mfc: Core support for MFC v7") Signed-off-by: Aakarsh Jain Reviewed-by: Alim Akhtar Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/platform/s5p-mfc/s5p_mfc.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c index f336a9543273..6cbec3bbfce6 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c @@ -1584,8 +1584,18 @@ static struct s5p_mfc_variant mfc_drvdata_v7 = { .port_num = MFC_NUM_PORTS_V7, .buf_size = &buf_size_v7, .fw_name[0] = "s5p-mfc-v7.fw", - .clk_names = {"mfc", "sclk_mfc"}, - .num_clocks = 2, + .clk_names = {"mfc"}, + .num_clocks = 1, +}; + +static struct s5p_mfc_variant mfc_drvdata_v7_3250 = { + .version = MFC_VERSION_V7, + .version_bit = MFC_V7_BIT, + .port_num = MFC_NUM_PORTS_V7, + .buf_size = &buf_size_v7, + .fw_name[0] = "s5p-mfc-v7.fw", + .clk_names = {"mfc", "sclk_mfc"}, + .num_clocks = 2, }; static struct s5p_mfc_buf_size_v6 mfc_buf_size_v8 = { @@ -1655,6 +1665,9 @@ static const struct of_device_id exynos_mfc_match[] = { }, { .compatible = "samsung,mfc-v7", .data = &mfc_drvdata_v7, + }, { + .compatible = "samsung,exynos3250-mfc", + .data = &mfc_drvdata_v7_3250, }, { .compatible = "samsung,mfc-v8", .data = &mfc_drvdata_v8, From cf2cbca714725d2a7698e777a4263b4f33483ac6 Mon Sep 17 00:00:00 2001 From: Zhang Zekun Date: Tue, 2 Aug 2022 08:50:50 +0000 Subject: [PATCH 0263/4345] drm/tegra: Add missing clk_disable_unprepare() in tegra_dc_probe() [ Upstream commit 7ad4384d53c67672a8720cdc2ef638d7d1710ab8 ] Add the missing clk_disable_unprepare() before return from tegra_dc_probe() in the error handling path. Fixes: f68ba6912bd2 ("drm/tegra: dc: Link DC1 to DC0 on Tegra20") Signed-off-by: Zhang Zekun Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/gpu/drm/tegra/dc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index ceb86338c003..958d12da902d 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -2564,8 +2564,10 @@ static int tegra_dc_probe(struct platform_device *pdev) usleep_range(2000, 4000); err = reset_control_assert(dc->rst); - if (err < 0) + if (err < 0) { + clk_disable_unprepare(dc->clk); return err; + } usleep_range(2000, 4000); From 6013c3de955711ae977b4ca62247aa21fb961676 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 27 Oct 2022 00:46:48 -0700 Subject: [PATCH 0264/4345] ASoC: dt-bindings: wcd9335: fix reset line polarity in example [ Upstream commit 34cb111f8a7b98b5fec809dd194003bca20ef1b2 ] When resetting the block, the reset line is being driven low and then high, which means that the line in DTS should be annotated as "active low". Fixes: 1877c9fda1b7 ("ASoC: dt-bindings: add dt bindings for wcd9335 audio codec") Signed-off-by: Dmitry Torokhov Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20221027074652.1044235-2-dmitry.torokhov@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- Documentation/devicetree/bindings/sound/qcom,wcd9335.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt b/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt index 5d6ea66a863f..1f75feec3dec 100644 --- a/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt +++ b/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt @@ -109,7 +109,7 @@ audio-codec@1{ reg = <1 0>; interrupts = <&msmgpio 54 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "intr2" - reset-gpios = <&msmgpio 64 0>; + reset-gpios = <&msmgpio 64 GPIO_ACTIVE_LOW>; slim-ifc-dev = <&wc9335_ifd>; clock-names = "mclk", "native"; clocks = <&rpmcc RPM_SMD_DIV_CLK1>, From 193691ff5b7619308433ce4cdfb3e1eda5ec3d41 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 16 Nov 2022 11:07:50 +0800 Subject: [PATCH 0265/4345] ASoC: mediatek: mtk-btcvsd: Add checks for write and read of mtk_btcvsd_snd [ Upstream commit d067b3378a78c9c3048ac535e31c171b6f5b5846 ] As the mtk_btcvsd_snd_write and mtk_btcvsd_snd_read may return error, it should be better to catch the exception. Fixes: 4bd8597dc36c ("ASoC: mediatek: add btcvsd driver") Signed-off-by: Jiasheng Jiang Link: https://lore.kernel.org/r/20221116030750.40500-1-jiasheng@iscas.ac.cn Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/mediatek/common/mtk-btcvsd.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/sound/soc/mediatek/common/mtk-btcvsd.c b/sound/soc/mediatek/common/mtk-btcvsd.c index 86e982e3209e..e1f57b0dedd0 100644 --- a/sound/soc/mediatek/common/mtk-btcvsd.c +++ b/sound/soc/mediatek/common/mtk-btcvsd.c @@ -1038,11 +1038,9 @@ static int mtk_pcm_btcvsd_copy(struct snd_soc_component *component, struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(component); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - mtk_btcvsd_snd_write(bt, buf, count); + return mtk_btcvsd_snd_write(bt, buf, count); else - mtk_btcvsd_snd_read(bt, buf, count); - - return 0; + return mtk_btcvsd_snd_read(bt, buf, count); } /* kcontrol */ From 58a1023eb5f71a7560b7dd502696d3dee380444b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2022 16:44:47 -0400 Subject: [PATCH 0266/4345] NFSv4.2: Clear FATTR4_WORD2_SECURITY_LABEL when done decoding [ Upstream commit eef7314caf2d73a94b68ba293cd105154d3a664e ] We need to clear the FATTR4_WORD2_SECURITY_LABEL bitmap flag irrespective of whether or not the label is too long. Fixes: aa9c2669626c ("NFS: Client implementation of Labeled-NFS") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs4xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index e2f0e3446e22..f8c89f9f4d52 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4166,6 +4166,7 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, p = xdr_inline_decode(xdr, len); if (unlikely(!p)) return -EIO; + bitmap[2] &= ~FATTR4_WORD2_SECURITY_LABEL; if (len < NFS4_MAXLABELLEN) { if (label) { if (label->len) { @@ -4178,7 +4179,6 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, label->lfs = lfs; status = NFS_ATTR_FATTR_V4_SECURITY_LABEL; } - bitmap[2] &= ~FATTR4_WORD2_SECURITY_LABEL; } else printk(KERN_WARNING "%s: label too long (%u)!\n", __func__, len); From 15feece7afcff25766a66aacc380652eebc0a114 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2022 18:21:14 -0400 Subject: [PATCH 0267/4345] NFSv4.2: Fix a memory stomp in decode_attr_security_label [ Upstream commit 43c1031f7110967c240cb6e922adcfc4b8899183 ] We must not change the value of label->len if it is zero, since that indicates we stored a label. Fixes: b4487b935452 ("nfs: Fix getxattr kernel panic and memory overflow") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs4xdr.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index f8c89f9f4d52..f1e599553f2b 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4168,12 +4168,10 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, return -EIO; bitmap[2] &= ~FATTR4_WORD2_SECURITY_LABEL; if (len < NFS4_MAXLABELLEN) { - if (label) { - if (label->len) { - if (label->len < len) - return -ERANGE; - memcpy(label->label, p, len); - } + if (label && label->len) { + if (label->len < len) + return -ERANGE; + memcpy(label->label, p, len); label->len = len; label->pi = pi; label->lfs = lfs; From d16d7870fd8f48dabbe35ce4092d5101bca30e7c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 19 Oct 2022 13:12:11 -0400 Subject: [PATCH 0268/4345] NFSv4.2: Fix initialisation of struct nfs4_label [ Upstream commit c528f70f504434eaff993a5ddd52203a2010d51f ] The call to nfs4_label_init_security() should return a fully initialised label. Fixes: aa9c2669626c ("NFS: Client implementation of Labeled-NFS") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs4proc.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 36af3734ac87..15550d673e61 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -130,6 +130,11 @@ nfs4_label_init_security(struct inode *dir, struct dentry *dentry, if (nfs_server_capable(dir, NFS_CAP_SECURITY_LABEL) == 0) return NULL; + label->lfs = 0; + label->pi = 0; + label->len = 0; + label->label = NULL; + err = security_dentry_init_security(dentry, sattr->ia_mode, &dentry->d_name, (void **)&label->label, &label->len); if (err == 0) @@ -3793,7 +3798,7 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags, struct iattr *attr, int *opened) { struct nfs4_state *state; - struct nfs4_label l = {0, 0, 0, NULL}, *label = NULL; + struct nfs4_label l, *label; label = nfs4_label_init_security(dir, ctx->dentry, attr, &l); @@ -4557,7 +4562,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, int flags) { struct nfs_server *server = NFS_SERVER(dir); - struct nfs4_label l, *ilabel = NULL; + struct nfs4_label l, *ilabel; struct nfs_open_context *ctx; struct nfs4_state *state; int status = 0; @@ -4916,7 +4921,7 @@ static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry, struct nfs4_exception exception = { .interruptible = true, }; - struct nfs4_label l, *label = NULL; + struct nfs4_label l, *label; int err; label = nfs4_label_init_security(dir, dentry, sattr, &l); @@ -4957,7 +4962,7 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, struct nfs4_exception exception = { .interruptible = true, }; - struct nfs4_label l, *label = NULL; + struct nfs4_label l, *label; int err; label = nfs4_label_init_security(dir, dentry, sattr, &l); @@ -5078,7 +5083,7 @@ static int nfs4_proc_mknod(struct inode *dir, struct dentry *dentry, struct nfs4_exception exception = { .interruptible = true, }; - struct nfs4_label l, *label = NULL; + struct nfs4_label l, *label; int err; label = nfs4_label_init_security(dir, dentry, sattr, &l); From bc60485b9347e6dd3e0e6511ba9491d09e5608f8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 4 Nov 2022 13:20:01 -0400 Subject: [PATCH 0269/4345] NFSv4: Fix a deadlock between nfs4_open_recover_helper() and delegreturn [ Upstream commit 51069e4aef6257b0454057359faed0ab0c9af083 ] If we're asked to recover open state while a delegation return is outstanding, then the state manager thread cannot use a cached open, so if the server returns a delegation, we can end up deadlocked behind the pending delegreturn. To avoid this problem, let's just ask the server not to give us a delegation unless we're explicitly reclaiming one. Fixes: be36e185bd26 ("NFSv4: nfs4_open_recover_helper() must set share access") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs4proc.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 15550d673e61..ee46ab09e330 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2126,18 +2126,18 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context } static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, - fmode_t fmode) + fmode_t fmode) { struct nfs4_state *newstate; + struct nfs_server *server = NFS_SB(opendata->dentry->d_sb); + int openflags = opendata->o_arg.open_flags; int ret; if (!nfs4_mode_match_open_stateid(opendata->state, fmode)) return 0; - opendata->o_arg.open_flags = 0; opendata->o_arg.fmode = fmode; - opendata->o_arg.share_access = nfs4_map_atomic_open_share( - NFS_SB(opendata->dentry->d_sb), - fmode, 0); + opendata->o_arg.share_access = + nfs4_map_atomic_open_share(server, fmode, openflags); memset(&opendata->o_res, 0, sizeof(opendata->o_res)); memset(&opendata->c_res, 0, sizeof(opendata->c_res)); nfs4_init_opendata_res(opendata); @@ -2713,10 +2713,15 @@ static int _nfs4_open_expired(struct nfs_open_context *ctx, struct nfs4_state *s struct nfs4_opendata *opendata; int ret; - opendata = nfs4_open_recoverdata_alloc(ctx, state, - NFS4_OPEN_CLAIM_FH); + opendata = nfs4_open_recoverdata_alloc(ctx, state, NFS4_OPEN_CLAIM_FH); if (IS_ERR(opendata)) return PTR_ERR(opendata); + /* + * We're not recovering a delegation, so ask for no delegation. + * Otherwise the recovery thread could deadlock with an outstanding + * delegation return. + */ + opendata->o_arg.open_flags = O_DIRECT; ret = nfs4_open_recover(opendata, state); if (ret == -ESTALE) d_drop(ctx->dentry); From 5458bc0f9df639d83471ca384152cc62dbee0aeb Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 14 Nov 2022 17:30:39 -0500 Subject: [PATCH 0270/4345] NFS: Fix an Oops in nfs_d_automount() [ Upstream commit 35e3b6ae84935d0d7ff76cbdaa83411b0ad5e471 ] When mounting from a NFSv4 referral, path->dentry can end up being a negative dentry, so derive the struct nfs_server from the dentry itself instead. Fixes: 2b0143b5c986 ("VFS: normal filesystems (and lustre): d_inode() annotations") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/namespace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 2bcbe38afe2e..1f03445b5cb4 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -147,7 +147,7 @@ struct vfsmount *nfs_d_automount(struct path *path) struct nfs_fs_context *ctx; struct fs_context *fc; struct vfsmount *mnt = ERR_PTR(-ENOMEM); - struct nfs_server *server = NFS_SERVER(d_inode(path->dentry)); + struct nfs_server *server = NFS_SB(path->dentry->d_sb); struct nfs_client *client = server->nfs_client; int timeout = READ_ONCE(nfs_mountpoint_expiry_timeout); int ret; From ae66695aa1eb38734c84939ddfad72413c1b6509 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Sat, 26 Nov 2022 10:14:29 +0800 Subject: [PATCH 0271/4345] ALSA: asihpi: fix missing pci_disable_device() [ Upstream commit 9d86515c3d4c0564a0c31a2df87d735353a1971e ] pci_disable_device() need be called while module exiting, switch to use pcim_enable(), pci_disable_device() will be called in pcim_release(). Fixes: 3285ea10e9b0 ("ALSA: asihpi - Interrelated HPI tidy up.") Signed-off-by: Liu Shixin Link: https://lore.kernel.org/r/20221126021429.3029562-1-liushixin2@huawei.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/asihpi/hpioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c index bb31b7fe867d..477a5b4b50bc 100644 --- a/sound/pci/asihpi/hpioctl.c +++ b/sound/pci/asihpi/hpioctl.c @@ -361,7 +361,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev, pci_dev->device, pci_dev->subsystem_vendor, pci_dev->subsystem_device, pci_dev->devfn); - if (pci_enable_device(pci_dev) < 0) { + if (pcim_enable_device(pci_dev) < 0) { dev_err(&pci_dev->dev, "pci_enable_device failed, disabling device\n"); return -EIO; From ae966649f665bc3868b935157dd4a3c31810dcc0 Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Wed, 23 Nov 2022 23:02:06 +0200 Subject: [PATCH 0272/4345] wifi: iwlwifi: mvm: fix double free on tx path. [ Upstream commit 0473cbae2137b963bd0eaa74336131cb1d3bc6c3 ] We see kernel crashes and lockups and KASAN errors related to ax210 firmware crashes. One of the KASAN dumps pointed at the tx path, and it appears there is indeed a way to double-free an skb. If iwl_mvm_tx_skb_sta returns non-zero, then the 'skb' sent into the method will be freed. But, in case where we build TSO skb buffer, the skb may also be freed in error case. So, return 0 in that particular error case and do cleanup manually. BUG: KASAN: use-after-free in __list_del_entry_valid+0x12/0x90 iwlwifi 0000:06:00.0: 0x00000000 | tsf hi Read of size 8 at addr ffff88813cfa4ba0 by task btserver/9650 CPU: 4 PID: 9650 Comm: btserver Tainted: G W 5.19.8+ #5 iwlwifi 0000:06:00.0: 0x00000000 | time gp1 Hardware name: Default string Default string/SKYBAY, BIOS 5.12 02/19/2019 Call Trace: dump_stack_lvl+0x55/0x6d print_report.cold.12+0xf2/0x684 iwlwifi 0000:06:00.0: 0x1D0915A8 | time gp2 ? __list_del_entry_valid+0x12/0x90 kasan_report+0x8b/0x180 iwlwifi 0000:06:00.0: 0x00000001 | uCode revision type ? __list_del_entry_valid+0x12/0x90 __list_del_entry_valid+0x12/0x90 iwlwifi 0000:06:00.0: 0x00000048 | uCode version major tcp_update_skb_after_send+0x5d/0x170 __tcp_transmit_skb+0xb61/0x15c0 iwlwifi 0000:06:00.0: 0xDAA05125 | uCode version minor ? __tcp_select_window+0x490/0x490 iwlwifi 0000:06:00.0: 0x00000420 | hw version ? trace_kmalloc_node+0x29/0xd0 ? __kmalloc_node_track_caller+0x12a/0x260 ? memset+0x1f/0x40 ? __build_skb_around+0x125/0x150 ? __alloc_skb+0x1d4/0x220 ? skb_zerocopy_clone+0x55/0x230 iwlwifi 0000:06:00.0: 0x00489002 | board version ? kmalloc_reserve+0x80/0x80 ? rcu_read_lock_bh_held+0x60/0xb0 tcp_write_xmit+0x3f1/0x24d0 iwlwifi 0000:06:00.0: 0x034E001C | hcmd ? __check_object_size+0x180/0x350 iwlwifi 0000:06:00.0: 0x24020000 | isr0 tcp_sendmsg_locked+0x8a9/0x1520 iwlwifi 0000:06:00.0: 0x01400000 | isr1 ? tcp_sendpage+0x50/0x50 iwlwifi 0000:06:00.0: 0x48F0000A | isr2 ? lock_release+0xb9/0x400 ? tcp_sendmsg+0x14/0x40 iwlwifi 0000:06:00.0: 0x00C3080C | isr3 ? lock_downgrade+0x390/0x390 ? do_raw_spin_lock+0x114/0x1d0 iwlwifi 0000:06:00.0: 0x00200000 | isr4 ? rwlock_bug.part.2+0x50/0x50 iwlwifi 0000:06:00.0: 0x034A001C | last cmd Id ? rwlock_bug.part.2+0x50/0x50 ? lockdep_hardirqs_on_prepare+0xe/0x200 iwlwifi 0000:06:00.0: 0x0000C2F0 | wait_event ? __local_bh_enable_ip+0x87/0xe0 ? inet_send_prepare+0x220/0x220 iwlwifi 0000:06:00.0: 0x000000C4 | l2p_control tcp_sendmsg+0x22/0x40 sock_sendmsg+0x5f/0x70 iwlwifi 0000:06:00.0: 0x00010034 | l2p_duration __sys_sendto+0x19d/0x250 iwlwifi 0000:06:00.0: 0x00000007 | l2p_mhvalid ? __ia32_sys_getpeername+0x40/0x40 iwlwifi 0000:06:00.0: 0x00000000 | l2p_addr_match ? rcu_read_lock_held_common+0x12/0x50 ? rcu_read_lock_sched_held+0x5a/0xd0 ? rcu_read_lock_bh_held+0xb0/0xb0 ? rcu_read_lock_sched_held+0x5a/0xd0 ? rcu_read_lock_sched_held+0x5a/0xd0 ? lock_release+0xb9/0x400 ? lock_downgrade+0x390/0x390 ? ktime_get+0x64/0x130 ? ktime_get+0x8d/0x130 ? rcu_read_lock_held_common+0x12/0x50 ? rcu_read_lock_sched_held+0x5a/0xd0 ? rcu_read_lock_held_common+0x12/0x50 ? rcu_read_lock_sched_held+0x5a/0xd0 ? rcu_read_lock_bh_held+0xb0/0xb0 ? rcu_read_lock_bh_held+0xb0/0xb0 __x64_sys_sendto+0x6f/0x80 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f1d126e4531 Code: 00 00 00 00 0f 1f 44 00 00 f3 0f 1e fa 48 8d 05 35 80 0c 00 41 89 ca 8b 00 85 c0 75 1c 45 31 c9 45 31 c0 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 67 c3 66 0f 1f 44 00 00 55 48 83 ec 20 48 89 RSP: 002b:00007ffe21a679d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 000000000000ffdc RCX: 00007f1d126e4531 RDX: 0000000000010000 RSI: 000000000374acf0 RDI: 0000000000000014 RBP: 00007ffe21a67ac0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000010 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000000 Allocated by task 9650: kasan_save_stack+0x1c/0x40 __kasan_slab_alloc+0x6d/0x90 kmem_cache_alloc_node+0xf3/0x2b0 __alloc_skb+0x191/0x220 tcp_stream_alloc_skb+0x3f/0x330 tcp_sendmsg_locked+0x67c/0x1520 tcp_sendmsg+0x22/0x40 sock_sendmsg+0x5f/0x70 __sys_sendto+0x19d/0x250 __x64_sys_sendto+0x6f/0x80 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Freed by task 9650: kasan_save_stack+0x1c/0x40 kasan_set_track+0x21/0x30 kasan_set_free_info+0x20/0x30 __kasan_slab_free+0x102/0x170 kmem_cache_free+0xc8/0x3e0 iwl_mvm_mac_itxq_xmit+0x124/0x270 [iwlmvm] ieee80211_queue_skb+0x874/0xd10 [mac80211] ieee80211_xmit_fast+0xf80/0x1180 [mac80211] __ieee80211_subif_start_xmit+0x287/0x680 [mac80211] ieee80211_subif_start_xmit+0xcd/0x730 [mac80211] dev_hard_start_xmit+0xf6/0x420 __dev_queue_xmit+0x165b/0x1b50 ip_finish_output2+0x66e/0xfb0 __ip_finish_output+0x487/0x6d0 ip_output+0x11c/0x350 __ip_queue_xmit+0x36b/0x9d0 __tcp_transmit_skb+0xb35/0x15c0 tcp_write_xmit+0x3f1/0x24d0 tcp_sendmsg_locked+0x8a9/0x1520 tcp_sendmsg+0x22/0x40 sock_sendmsg+0x5f/0x70 __sys_sendto+0x19d/0x250 __x64_sys_sendto+0x6f/0x80 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x46/0xb0 The buggy address belongs to the object at ffff88813cfa4b40 which belongs to the cache skbuff_fclone_cache of size 472 The buggy address is located 96 bytes inside of 472-byte region [ffff88813cfa4b40, ffff88813cfa4d18) The buggy address belongs to the physical page: page:ffffea0004f3e900 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88813cfa6c40 pfn:0x13cfa4 head:ffffea0004f3e900 order:2 compound_mapcount:0 compound_pincount:0 flags: 0x5fff8000010200(slab|head|node=0|zone=2|lastcpupid=0x3fff) raw: 005fff8000010200 ffffea0004656b08 ffffea0008e8cf08 ffff8881081a5240 raw: ffff88813cfa6c40 0000000000170015 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88813cfa4a80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88813cfa4b00: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb >ffff88813cfa4b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88813cfa4c00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88813cfa4c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Fixes: 08f7d8b69aaf ("iwlwifi: mvm: bring back mvm GSO code") Link: https://lore.kernel.org/linux-wireless/20220928193057.16132-1-greearb@candelatech.com/ Tested-by: Amol Jawale Signed-off-by: Ben Greear Link: https://lore.kernel.org/r/20221123225313.21b1ee31d666.I3b3ba184433dd2a544d91eeeda29b467021824ae@changeid Signed-off-by: Gregory Greenman Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 7186e1dbbd6b..d310337b1625 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1203,6 +1203,7 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb, struct sk_buff_head mpdus_skbs; unsigned int payload_len; int ret; + struct sk_buff *orig_skb = skb; if (WARN_ON_ONCE(!mvmsta)) return -1; @@ -1235,8 +1236,17 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb, ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta); if (ret) { + /* Free skbs created as part of TSO logic that have not yet been dequeued */ __skb_queue_purge(&mpdus_skbs); - return ret; + /* skb here is not necessarily same as skb that entered this method, + * so free it explicitly. + */ + if (skb == orig_skb) + ieee80211_free_txskb(mvm->hw, skb); + else + kfree_skb(skb); + /* there was error, but we consumed skb one way or another, so return 0 */ + return 0; } } From 52c9ad56c19d45ac03cfd6e8258166deb70802e7 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 11 Nov 2021 17:11:08 +0100 Subject: [PATCH 0273/4345] ASoC: mediatek: mt8173: Fix debugfs registration for components [ Upstream commit 8c32984bc7da29828260ac514d5d4967f7e8f62d ] When registering the mt8173-afe-pcm driver, we are also adding two components: one is for the PCM DAIs and one is for the HDMI DAIs, but when debugfs is enabled, we're getting the following issue: [ 17.279176] debugfs: Directory '11220000.audio-controller' with parent 'mtk-rt5650' already present! [ 17.288345] debugfs: Directory '11220000.audio-controller' with parent 'mtk-rt5650' already present! To overcome to that without any potentially big rewrite of this driver, similarly to what was done in mt8195-afe-pcm, add a debugfs_prefix to the components before actually adding them. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20211111161108.502344-1-angelogioacchino.delregno@collabora.com Signed-off-by: Mark Brown Stable-dep-of: 4cbb264d4e91 ("ASoC: mediatek: mt8173: Enable IRQ when pdata is ready") Signed-off-by: Sasha Levin --- sound/soc/mediatek/mt8173/mt8173-afe-pcm.c | 51 ++++++++++++++++++---- 1 file changed, 43 insertions(+), 8 deletions(-) diff --git a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c index 7e7bda70d12e..a8c7617978a6 100644 --- a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c +++ b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c @@ -1054,6 +1054,7 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) int irq_id; struct mtk_base_afe *afe; struct mt8173_afe_private *afe_priv; + struct snd_soc_component *comp_pcm, *comp_hdmi; ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(33)); if (ret) @@ -1142,23 +1143,55 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) if (ret) goto err_pm_disable; - ret = devm_snd_soc_register_component(&pdev->dev, - &mt8173_afe_pcm_dai_component, - mt8173_afe_pcm_dais, - ARRAY_SIZE(mt8173_afe_pcm_dais)); + comp_pcm = devm_kzalloc(&pdev->dev, sizeof(*comp_pcm), GFP_KERNEL); + if (!comp_pcm) { + ret = -ENOMEM; + goto err_pm_disable; + } + + ret = snd_soc_component_initialize(comp_pcm, + &mt8173_afe_pcm_dai_component, + &pdev->dev); if (ret) goto err_pm_disable; - ret = devm_snd_soc_register_component(&pdev->dev, - &mt8173_afe_hdmi_dai_component, - mt8173_afe_hdmi_dais, - ARRAY_SIZE(mt8173_afe_hdmi_dais)); +#ifdef CONFIG_DEBUG_FS + comp_pcm->debugfs_prefix = "pcm"; +#endif + + ret = snd_soc_add_component(comp_pcm, + mt8173_afe_pcm_dais, + ARRAY_SIZE(mt8173_afe_pcm_dais)); if (ret) goto err_pm_disable; + comp_hdmi = devm_kzalloc(&pdev->dev, sizeof(*comp_hdmi), GFP_KERNEL); + if (!comp_hdmi) { + ret = -ENOMEM; + goto err_pm_disable; + } + + ret = snd_soc_component_initialize(comp_hdmi, + &mt8173_afe_hdmi_dai_component, + &pdev->dev); + if (ret) + goto err_pm_disable; + +#ifdef CONFIG_DEBUG_FS + comp_hdmi->debugfs_prefix = "hdmi"; +#endif + + ret = snd_soc_add_component(comp_hdmi, + mt8173_afe_hdmi_dais, + ARRAY_SIZE(mt8173_afe_hdmi_dais)); + if (ret) + goto err_cleanup_components; + dev_info(&pdev->dev, "MT8173 AFE driver initialized.\n"); return 0; +err_cleanup_components: + snd_soc_unregister_component(&pdev->dev); err_pm_disable: pm_runtime_disable(&pdev->dev); return ret; @@ -1166,6 +1199,8 @@ err_pm_disable: static int mt8173_afe_pcm_dev_remove(struct platform_device *pdev) { + snd_soc_unregister_component(&pdev->dev); + pm_runtime_disable(&pdev->dev); if (!pm_runtime_status_suspended(&pdev->dev)) mt8173_afe_runtime_suspend(&pdev->dev); From 57491967ad8f865a9a81d08c36b26facd14d84e5 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Mon, 28 Nov 2022 11:49:16 +0100 Subject: [PATCH 0274/4345] ASoC: mediatek: mt8173: Enable IRQ when pdata is ready [ Upstream commit 4cbb264d4e9136acab2c8fd39e39ab1b1402b84b ] If the device does not come straight from reset, we might receive an IRQ before we are ready to handle it. Fixes: [ 2.334737] Unable to handle kernel read from unreadable memory at virtual address 00000000000001e4 [ 2.522601] Call trace: [ 2.525040] regmap_read+0x1c/0x80 [ 2.528434] mt8173_afe_irq_handler+0x40/0xf0 ... [ 2.598921] start_kernel+0x338/0x42c Signed-off-by: Ricardo Ribalda Fixes: ee0bcaff109f ("ASoC: mediatek: Add AFE platform driver") Link: https://lore.kernel.org/r/20221128-mt8173-afe-v1-0-70728221628f@chromium.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/mediatek/mt8173/mt8173-afe-pcm.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c index a8c7617978a6..619d6733091c 100644 --- a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c +++ b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c @@ -1072,16 +1072,6 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) afe->dev = &pdev->dev; - irq_id = platform_get_irq(pdev, 0); - if (irq_id <= 0) - return irq_id < 0 ? irq_id : -ENXIO; - ret = devm_request_irq(afe->dev, irq_id, mt8173_afe_irq_handler, - 0, "Afe_ISR_Handle", (void *)afe); - if (ret) { - dev_err(afe->dev, "could not request_irq\n"); - return ret; - } - afe->base_addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(afe->base_addr)) return PTR_ERR(afe->base_addr); @@ -1187,6 +1177,16 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) if (ret) goto err_cleanup_components; + irq_id = platform_get_irq(pdev, 0); + if (irq_id <= 0) + return irq_id < 0 ? irq_id : -ENXIO; + ret = devm_request_irq(afe->dev, irq_id, mt8173_afe_irq_handler, + 0, "Afe_ISR_Handle", (void *)afe); + if (ret) { + dev_err(afe->dev, "could not request_irq\n"); + goto err_pm_disable; + } + dev_info(&pdev->dev, "MT8173 AFE driver initialized.\n"); return 0; From a012cdd4fd62b947bea6d746f3ee99c752c3dbdf Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Tue, 22 Nov 2022 17:33:24 +0800 Subject: [PATCH 0275/4345] drm/amd/pm/smu11: BACO is supported when it's in BACO state [ Upstream commit 6dca7efe6e522bf213c7dab691fa580d82f48f74 ] Return true early if ASIC is in BACO state already, no need to talk to SMU. It can fix the issue that driver was not calling BACO exit at all in runtime pm resume, and a timing issue leading to a PCI AER error happened eventually. Fixes: 8795e182b02d ("PCI/portdrv: Don't disable AER reporting in get_port_device_capability()") Suggested-by: Lijo Lazar Signed-off-by: Guchun Chen Reviewed-by: Lijo Lazar Reviewed-by: Evan Quan Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index e646f5931d79..89f20497c14f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1476,6 +1476,10 @@ bool smu_v11_0_baco_is_support(struct smu_context *smu) if (!smu_baco->platform_support) return false; + /* return true if ASIC is in BACO state already */ + if (smu_v11_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER) + return true; + /* Arcturus does not support this bit mask */ if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) && !smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT)) From 3991d98a8a07b71c02f3a39f77d6d9a7f575a5c4 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Tue, 22 Nov 2022 19:30:42 +0800 Subject: [PATCH 0276/4345] drm/radeon: Fix PCI device refcount leak in radeon_atrm_get_bios() [ Upstream commit 725a521a18734f65de05b8d353b5bd0d3ca4c37a ] As comment of pci_get_class() says, it returns a pci_device with its refcount increased and decreased the refcount for the input parameter @from if it is not NULL. If we break the loop in radeon_atrm_get_bios() with 'pdev' not NULL, we need to call pci_dev_put() to decrease the refcount. Add the missing pci_dev_put() to avoid refcount leak. Fixes: d8ade3526b2a ("drm/radeon: handle non-VGA class pci devices with ATRM") Fixes: c61e2775873f ("drm/radeon: split ATRM support out from the ATPX handler (v3)") Signed-off-by: Xiongfeng Wang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/radeon/radeon_bios.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index 34d2cb929c06..0c94147f7625 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -227,6 +227,7 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev) if (!found) return false; + pci_dev_put(pdev); rdev->bios = kmalloc(size, GFP_KERNEL); if (!rdev->bios) { From 7c1ddf7c664b5bc91f14b1bdeaa45520ef1760e4 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Tue, 22 Nov 2022 19:30:43 +0800 Subject: [PATCH 0277/4345] drm/amdgpu: Fix PCI device refcount leak in amdgpu_atrm_get_bios() [ Upstream commit ca54639c7752edf1304d92ff4d0c049d4efc9ba0 ] As comment of pci_get_class() says, it returns a pci_device with its refcount increased and decreased the refcount for the input parameter @from if it is not NULL. If we break the loop in amdgpu_atrm_get_bios() with 'pdev' not NULL, we need to call pci_dev_put() to decrease the refcount. Add the missing pci_dev_put() to avoid refcount leak. Fixes: d38ceaf99ed0 ("drm/amdgpu: add core driver (v4)") Signed-off-by: Xiongfeng Wang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 6333cada1e09..4b568ee93243 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -313,6 +313,7 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) if (!found) return false; + pci_dev_put(pdev); adev->bios = kmalloc(size, GFP_KERNEL); if (!adev->bios) { From cd0e9ee50cb59926f9056cb3cd08f818bc039876 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Thu, 29 Sep 2022 00:04:02 +0800 Subject: [PATCH 0278/4345] ASoC: pcm512x: Fix PM disable depth imbalance in pcm512x_probe [ Upstream commit 97b801be6f8e53676b9f2b105f54e35c745c1b22 ] The pm_runtime_enable will increase power disable depth. Thus a pairing decrement is needed on the error handling path to keep it balanced according to context. We fix it by going to err_pm instead of err_clk. Fixes:f086ba9d5389c ("ASoC: pcm512x: Support mastering BCLK/LRCLK using the PLL") Signed-off-by: Zhang Qilong Link: https://lore.kernel.org/r/20220928160402.126140-1-zhangqilong3@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/pcm512x.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c index 8153d3d01654..3677e9029f91 100644 --- a/sound/soc/codecs/pcm512x.c +++ b/sound/soc/codecs/pcm512x.c @@ -1599,7 +1599,7 @@ int pcm512x_probe(struct device *dev, struct regmap *regmap) if (val > 6) { dev_err(dev, "Invalid pll-in\n"); ret = -EINVAL; - goto err_clk; + goto err_pm; } pcm512x->pll_in = val; } @@ -1608,7 +1608,7 @@ int pcm512x_probe(struct device *dev, struct regmap *regmap) if (val > 6) { dev_err(dev, "Invalid pll-out\n"); ret = -EINVAL; - goto err_clk; + goto err_pm; } pcm512x->pll_out = val; } @@ -1617,12 +1617,12 @@ int pcm512x_probe(struct device *dev, struct regmap *regmap) dev_err(dev, "Error: both pll-in and pll-out, or none\n"); ret = -EINVAL; - goto err_clk; + goto err_pm; } if (pcm512x->pll_in && pcm512x->pll_in == pcm512x->pll_out) { dev_err(dev, "Error: pll-in == pll-out\n"); ret = -EINVAL; - goto err_clk; + goto err_pm; } } #endif From 429a2a4258d524b2144dd9c9d87ba93f7492c7f6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 22 Nov 2022 16:00:09 +0100 Subject: [PATCH 0279/4345] netfilter: conntrack: set icmpv6 redirects as RELATED [ Upstream commit 7d7cfb48d81353e826493d24c7cec7360950968f ] icmp conntrack will set icmp redirects as RELATED, but icmpv6 will not do this. For icmpv6, only icmp errors (code <= 128) are examined for RELATED state. ICMPV6 Redirects are part of neighbour discovery mechanism, those are handled by marking a selected subset (e.g. neighbour solicitations) as UNTRACKED, but not REDIRECT -- they will thus be flagged as INVALID. Add minimal support for REDIRECTs. No parsing of neighbour options is added for simplicity, so this will only check that we have the embeeded original header (ND_OPT_REDIRECT_HDR), and then attempt to do a flow lookup for this tuple. Also extend the existing test case to cover redirects. Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Reported-by: Eric Garver Link: https://github.com/firewalld/firewalld/issues/1046 Signed-off-by: Florian Westphal Acked-by: Eric Garver Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_proto_icmpv6.c | 53 +++++++++++++++++++ .../netfilter/conntrack_icmp_related.sh | 36 ++++++++++++- 2 files changed, 87 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index facd8c64ec4e..f1a87de1c60e 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -130,6 +130,56 @@ static void icmpv6_error_log(const struct sk_buff *skb, IPPROTO_ICMPV6, "%s", msg); } +static noinline_for_stack int +nf_conntrack_icmpv6_redirect(struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state) +{ + u8 hl = ipv6_hdr(skb)->hop_limit; + union nf_inet_addr outer_daddr; + union { + struct nd_opt_hdr nd_opt; + struct rd_msg rd_msg; + } tmp; + const struct nd_opt_hdr *nd_opt; + const struct rd_msg *rd_msg; + + rd_msg = skb_header_pointer(skb, dataoff, sizeof(*rd_msg), &tmp.rd_msg); + if (!rd_msg) { + icmpv6_error_log(skb, state, "short redirect"); + return -NF_ACCEPT; + } + + if (rd_msg->icmph.icmp6_code != 0) + return NF_ACCEPT; + + if (hl != 255 || !(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { + icmpv6_error_log(skb, state, "invalid saddr or hoplimit for redirect"); + return -NF_ACCEPT; + } + + dataoff += sizeof(*rd_msg); + + /* warning: rd_msg no longer usable after this call */ + nd_opt = skb_header_pointer(skb, dataoff, sizeof(*nd_opt), &tmp.nd_opt); + if (!nd_opt || nd_opt->nd_opt_len == 0) { + icmpv6_error_log(skb, state, "redirect without options"); + return -NF_ACCEPT; + } + + /* We could call ndisc_parse_options(), but it would need + * skb_linearize() and a bit more work. + */ + if (nd_opt->nd_opt_type != ND_OPT_REDIRECT_HDR) + return NF_ACCEPT; + + memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr, + sizeof(outer_daddr.ip6)); + dataoff += 8; + return nf_conntrack_inet_error(tmpl, skb, dataoff, state, + IPPROTO_ICMPV6, &outer_daddr); +} + int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, @@ -160,6 +210,9 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, return NF_ACCEPT; } + if (icmp6h->icmp6_type == NDISC_REDIRECT) + return nf_conntrack_icmpv6_redirect(tmpl, skb, dataoff, state); + /* is not error message ? */ if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; diff --git a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh index b48e1833bc89..76645aaf2b58 100755 --- a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh +++ b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh @@ -35,6 +35,8 @@ cleanup() { for i in 1 2;do ip netns del nsrouter$i;done } +trap cleanup EXIT + ipv4() { echo -n 192.168.$1.2 } @@ -146,11 +148,17 @@ ip netns exec nsclient1 nft -f - < /dev/null + +expect="packets 1 bytes 112" +check_counter nsclient1 "redir4" "$expect" +if [ $? -ne 0 ];then + ret=1 +fi + +ip netns exec "nsclient1" ping -c 1 dead:1::42 > /dev/null +expect="packets 1 bytes 192" +check_counter nsclient1 "redir6" "$expect" +if [ $? -ne 0 ];then + ret=1 +fi + +if [ $ret -eq 0 ];then + echo "PASS: icmp redirects had RELATED state" +else + echo "ERROR: icmp redirect RELATED state test has failed" +fi + exit $ret From 28e4a763cd4a2b1a78852216ef4bd7df3a05cec6 Mon Sep 17 00:00:00 2001 From: Pengcheng Yang Date: Tue, 29 Nov 2022 18:40:38 +0800 Subject: [PATCH 0280/4345] bpf, sockmap: Fix repeated calls to sock_put() when msg has more_data [ Upstream commit 7a9841ca025275b5b0edfb0b618934abb6ceec15 ] In tcp_bpf_send_verdict() redirection, the eval variable is assigned to __SK_REDIRECT after the apply_bytes data is sent, if msg has more_data, sock_put() will be called multiple times. We should reset the eval variable to __SK_NONE every time more_data starts. This causes: IPv4: Attempt to release TCP socket in state 1 00000000b4c925d7 ------------[ cut here ]------------ refcount_t: addition on 0; use-after-free. WARNING: CPU: 5 PID: 4482 at lib/refcount.c:25 refcount_warn_saturate+0x7d/0x110 Modules linked in: CPU: 5 PID: 4482 Comm: sockhash_bypass Kdump: loaded Not tainted 6.0.0 #1 Hardware name: Red Hat KVM, BIOS 1.11.0-2.el7 04/01/2014 Call Trace: __tcp_transmit_skb+0xa1b/0xb90 ? __alloc_skb+0x8c/0x1a0 ? __kmalloc_node_track_caller+0x184/0x320 tcp_write_xmit+0x22a/0x1110 __tcp_push_pending_frames+0x32/0xf0 do_tcp_sendpages+0x62d/0x640 tcp_bpf_push+0xae/0x2c0 tcp_bpf_sendmsg_redir+0x260/0x410 ? preempt_count_add+0x70/0xa0 tcp_bpf_send_verdict+0x386/0x4b0 tcp_bpf_sendmsg+0x21b/0x3b0 sock_sendmsg+0x58/0x70 __sys_sendto+0xfa/0x170 ? xfd_validate_state+0x1d/0x80 ? switch_fpu_return+0x59/0xe0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x37/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: cd9733f5d75c ("tcp_bpf: Fix one concurrency problem in the tcp_bpf_send_verdict function") Signed-off-by: Pengcheng Yang Signed-off-by: Daniel Borkmann Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/1669718441-2654-2-git-send-email-yangpc@wangsu.com Signed-off-by: Sasha Levin --- net/ipv4/tcp_bpf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 809ee0f32d59..027f7f9256e1 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -316,7 +316,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; u32 tosend, origsize, sent, delta = 0; - u32 eval = __SK_NONE; + u32 eval; int ret; more_data: @@ -347,6 +347,7 @@ more_data: tosend = msg->sg.size; if (psock->apply_bytes && psock->apply_bytes < tosend) tosend = psock->apply_bytes; + eval = __SK_NONE; switch (psock->eval) { case __SK_PASS: From c58df40e3e67fd7603290b5dd24c47cdc1f9ef74 Mon Sep 17 00:00:00 2001 From: Pengcheng Yang Date: Tue, 29 Nov 2022 18:40:40 +0800 Subject: [PATCH 0281/4345] bpf, sockmap: Fix data loss caused by using apply_bytes on ingress redirect [ Upstream commit 9072931f020bfd907d6d89ee21ff1481cd78b407 ] Use apply_bytes on ingress redirect, when apply_bytes is less than the length of msg data, some data may be skipped and lost in bpf_tcp_ingress(). If there is still data in the scatterlist that has not been consumed, we cannot move the msg iter. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Pengcheng Yang Signed-off-by: Daniel Borkmann Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/1669718441-2654-4-git-send-email-yangpc@wangsu.com Signed-off-by: Sasha Levin --- net/ipv4/tcp_bpf.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 027f7f9256e1..6a1685461f89 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -125,8 +125,11 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, tmp->sg.end = i; if (apply) { apply_bytes -= size; - if (!apply_bytes) + if (!apply_bytes) { + if (sge->length) + sk_msg_iter_var_prev(i); break; + } } } while (i != msg->sg.end); From ab19f402a12d61969642ea6889b63e7441504fe9 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 28 Nov 2022 14:06:14 +0300 Subject: [PATCH 0282/4345] bonding: uninitialized variable in bond_miimon_inspect() [ Upstream commit e5214f363dabca240446272dac54d404501ad5e5 ] The "ignore_updelay" variable needs to be initialized to false. Fixes: f8a65ab2f3ff ("bonding: fix link recovery in mode 2 when updelay is nonzero") Signed-off-by: Dan Carpenter Reviewed-by: Pavan Chebbi Acked-by: Jay Vosburgh Link: https://lore.kernel.org/r/Y4SWJlh3ohJ6EPTL@kili Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/bonding/bond_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e66092518fdd..c40b92f8d16b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2393,10 +2393,10 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in /* called with rcu_read_lock() */ static int bond_miimon_inspect(struct bonding *bond) { + bool ignore_updelay = false; int link_state, commit = 0; struct list_head *iter; struct slave *slave; - bool ignore_updelay; if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { ignore_updelay = !rcu_dereference(bond->curr_active_slave); From b0163248dbafcd7a108b4a2b66f64d668f6e35bb Mon Sep 17 00:00:00 2001 From: Alexander Sverdlin Date: Wed, 30 Nov 2022 17:29:27 +0100 Subject: [PATCH 0283/4345] spi: spidev: mask SPI_CS_HIGH in SPI_IOC_RD_MODE [ Upstream commit 7dbfa445ff7393d1c4c066c1727c9e0af1251958 ] Commit f3186dd87669 ("spi: Optionally use GPIO descriptors for CS GPIOs") has changed the user-space interface so that bogus SPI_CS_HIGH started to appear in the mask returned by SPI_IOC_RD_MODE even for active-low CS pins. Commit 138c9c32f090 ("spi: spidev: Fix CS polarity if GPIO descriptors are used") fixed only SPI_IOC_WR_MODE part of the problem. Let's fix SPI_IOC_RD_MODE symmetrically. Test case: #include #include #include int main(int argc, char **argv) { char modew = SPI_CPHA; char moder; int f = open("/dev/spidev0.0", O_RDWR); if (f < 0) return 1; ioctl(f, SPI_IOC_WR_MODE, &modew); ioctl(f, SPI_IOC_RD_MODE, &moder); return moder == modew ? 0 : 2; } Fixes: f3186dd87669 ("spi: Optionally use GPIO descriptors for CS GPIOs") Signed-off-by: Alexander Sverdlin Link: https://lore.kernel.org/r/20221130162927.539512-1-alexander.sverdlin@siemens.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spidev.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 859910ec8d9f..9c5ec99431d2 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -376,12 +376,23 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) switch (cmd) { /* read requests */ case SPI_IOC_RD_MODE: - retval = put_user(spi->mode & SPI_MODE_MASK, - (__u8 __user *)arg); - break; case SPI_IOC_RD_MODE32: - retval = put_user(spi->mode & SPI_MODE_MASK, - (__u32 __user *)arg); + tmp = spi->mode; + + { + struct spi_controller *ctlr = spi->controller; + + if (ctlr->use_gpio_descriptors && ctlr->cs_gpiods && + ctlr->cs_gpiods[spi->chip_select]) + tmp &= ~SPI_CS_HIGH; + } + + if (cmd == SPI_IOC_RD_MODE) + retval = put_user(tmp & SPI_MODE_MASK, + (__u8 __user *)arg); + else + retval = put_user(tmp & SPI_MODE_MASK, + (__u32 __user *)arg); break; case SPI_IOC_RD_LSB_FIRST: retval = put_user((spi->mode & SPI_LSB_FIRST) ? 1 : 0, From b2c0b94f48373ee743a4d63825a9d52364418837 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Thu, 17 Nov 2022 14:45:00 +0800 Subject: [PATCH 0284/4345] wifi: mac80211: fix memory leak in ieee80211_if_add() [ Upstream commit 13e5afd3d773c6fc6ca2b89027befaaaa1ea7293 ] When register_netdevice() failed in ieee80211_if_add(), ndev->tstats isn't released. Fix it. Fixes: 5a490510ba5f ("mac80211: use per-CPU TX/RX statistics") Signed-off-by: Zhengchao Shao Link: https://lore.kernel.org/r/20221117064500.319983-1-shaozhengchao@huawei.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/iface.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 3a15ef8dd322..d04e5a1a7e0e 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -2013,6 +2013,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = register_netdevice(ndev); if (ret) { + ieee80211_if_free(ndev); free_netdev(ndev); return ret; } From 4ecb7a6e61b1e1605f49bb8a195e599e777baa4a Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Wed, 9 Nov 2022 17:02:37 +0800 Subject: [PATCH 0285/4345] wifi: cfg80211: Fix not unregister reg_pdev when load_builtin_regdb_keys() fails [ Upstream commit 833a9fd28c9b7ccb39a334721379e992dc1c0c89 ] In regulatory_init_db(), when it's going to return a error, reg_pdev should be unregistered. When load_builtin_regdb_keys() fails it doesn't do it and makes cfg80211 can't be reload with report: sysfs: cannot create duplicate filename '/devices/platform/regulatory.0' ... dump_stack_lvl+0x79/0x9b sysfs_warn_dup.cold+0x1c/0x29 sysfs_create_dir_ns+0x22d/0x290 kobject_add_internal+0x247/0x800 kobject_add+0x135/0x1b0 device_add+0x389/0x1be0 platform_device_add+0x28f/0x790 platform_device_register_full+0x376/0x4b0 regulatory_init+0x9a/0x4b2 [cfg80211] cfg80211_init+0x84/0x113 [cfg80211] ... Fixes: 90a53e4432b1 ("cfg80211: implement regdb signature checking") Signed-off-by: Chen Zhongjin Link: https://lore.kernel.org/r/20221109090237.214127-1-chenzhongjin@huawei.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/reg.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/wireless/reg.c b/net/wireless/reg.c index a1e64d967bd3..90297264d8ae 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -4185,8 +4185,10 @@ static int __init regulatory_init_db(void) return -EINVAL; err = load_builtin_regdb_keys(); - if (err) + if (err) { + platform_device_unregister(reg_pdev); return err; + } /* We always try to get an update for the static regdomain */ err = regulatory_hint_core(cfg80211_world_regdom->alpha2); From f532db69ab1342b16a8ba90ace9a55b79bbb8011 Mon Sep 17 00:00:00 2001 From: Deren Wu Date: Sun, 27 Nov 2022 10:35:37 +0800 Subject: [PATCH 0286/4345] wifi: mt76: fix coverity overrun-call in mt76_get_txpower() [ Upstream commit 03dd0d49de7db680a856fa566963bb8421f46368 ] Make sure the nss is valid for nss_delta array. Return zero if the index is invalid. Coverity message: Event overrun-call: Overrunning callee's array of size 4 by passing argument "n_chains" (which evaluates to 15) in call to "mt76_tx_power_nss_delta". int delta = mt76_tx_power_nss_delta(n_chains); Fixes: 07cda406308b ("mt76: fix rounding issues on converting per-chain and combined txpower") Signed-off-by: Deren Wu Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt76.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index a5be66de1cff..5a8060790a61 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -884,8 +884,9 @@ static inline bool mt76_is_skb_pktid(u8 pktid) static inline u8 mt76_tx_power_nss_delta(u8 nss) { static const u8 nss_delta[4] = { 0, 6, 9, 12 }; + u8 idx = nss - 1; - return nss_delta[nss - 1]; + return (idx < ARRAY_SIZE(nss_delta)) ? nss_delta[idx] : 0; } static inline bool mt76_testmode_enabled(struct mt76_dev *dev) From 6f25402d8a00a6b12ead75b96c03c5b7813f2aa8 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 1 Dec 2022 20:27:05 +0800 Subject: [PATCH 0287/4345] regulator: core: fix module refcount leak in set_supply() [ Upstream commit da46ee19cbd8344d6860816b4827a7ce95764867 ] If create_regulator() fails in set_supply(), the module refcount needs be put to keep refcount balanced. Fixes: e2c09ae7a74d ("regulator: core: Increase refcount for regulator supply's module") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221201122706.4055992-2-yangyingliang@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 60c0be2ea5c5..830a9be4432e 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1472,6 +1472,7 @@ static int set_supply(struct regulator_dev *rdev, rdev->supply = create_regulator(supply_rdev, &rdev->dev, "SUPPLY"); if (rdev->supply == NULL) { + module_put(supply_rdev->owner); err = -ENOMEM; return err; } From ee4425e81d9b5bc7cd9c650acf07b586338815c0 Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Tue, 8 Nov 2022 22:56:25 +0100 Subject: [PATCH 0288/4345] clk: qcom: clk-krait: fix wrong div2 functions [ Upstream commit d676d3a3717cf726d3affedbe5ba98fc4ccad7b3 ] Currently div2 value is applied to the wrong bits. This is caused by a bug in the code where the shift is done only for lpl, for anything else the mask is not shifted to the correct bits. Fix this by correctly shift if lpl is not supported. Fixes: 4d7dc77babfe ("clk: qcom: Add support for Krait clocks") Signed-off-by: Christian Marangi Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221108215625.30186-1-ansuelsmth@gmail.com Signed-off-by: Sasha Levin --- drivers/clk/qcom/clk-krait.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/qcom/clk-krait.c b/drivers/clk/qcom/clk-krait.c index 90046428693c..e74fc81a14d0 100644 --- a/drivers/clk/qcom/clk-krait.c +++ b/drivers/clk/qcom/clk-krait.c @@ -98,6 +98,8 @@ static int krait_div2_set_rate(struct clk_hw *hw, unsigned long rate, if (d->lpl) mask = mask << (d->shift + LPL_SHIFT) | mask << d->shift; + else + mask <<= d->shift; spin_lock_irqsave(&krait_clock_reg_lock, flags); val = krait_get_l2_indirect_reg(d->offset); From 38d13a2a9e522582cf872b9453477940a0fa9a7e Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 29 Nov 2022 17:48:09 +0100 Subject: [PATCH 0289/4345] hsr: Add a rcu-read lock to hsr_forward_skb(). [ Upstream commit 5aa2820177af650293b2f9f1873c1f6f8e4ad7a4 ] hsr_forward_skb() a skb and keeps information in an on-stack hsr_frame_info. hsr_get_node() assigns hsr_frame_info::node_src which is from a RCU list. This pointer is used later in hsr_forward_do(). I don't see a reason why this pointer can't vanish midway since there is no guarantee that hsr_forward_skb() is invoked from an RCU read section. Use rcu_read_lock() to protect hsr_frame_info::node_src from its assignment until it is no longer used. Fixes: f266a683a4804 ("net/hsr: Better frame dispatch") Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/hsr/hsr_forward.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index cb9b54a7abd2..90b0ed16552b 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -545,11 +545,13 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port) { struct hsr_frame_info frame; + rcu_read_lock(); if (fill_frame_info(&frame, skb, port) < 0) goto out_drop; hsr_register_frame_in(frame.node_src, port, frame.sequence_nr); hsr_forward_do(&frame); + rcu_read_unlock(); /* Gets called for ingress frames as well as egress from master port. * So check and increment stats for master port only here. */ @@ -564,6 +566,7 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port) return; out_drop: + rcu_read_unlock(); port->dev->stats.tx_dropped++; kfree_skb(skb); } From 8cee8543f002174f7501eb4d024da2b12121971d Mon Sep 17 00:00:00 2001 From: George McCollister Date: Tue, 9 Feb 2021 19:02:10 -0600 Subject: [PATCH 0290/4345] net: hsr: generate supervision frame without HSR/PRP tag [ Upstream commit 78be9217c4014cebac4d549cc2db1f2886d5a8fb ] For a switch to offload insertion of HSR/PRP tags, frames must not be sent to the CPU facing switch port with a tag. Generate supervision frames (eth type ETH_P_PRP) without HSR v1 (ETH_P_HSR)/PRP tag and rely on create_tagged_frame which inserts it later. This will allow skipping the tag insertion for all outgoing frames in the future which is required for HSR v1/PRP tag insertions to be offloaded. HSR v0 supervision frames always contain tag information so insertion of the tag can't be offloaded. IEC 62439-3 Ed.2.0 (HSR v1) specifically notes that this was changed since v0 to allow offloading. Signed-off-by: George McCollister Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: David S. Miller Stable-dep-of: d5c7652eb16f ("hsr: Disable netpoll.") Signed-off-by: Sasha Levin --- net/hsr/hsr_device.c | 39 +++++++-------------------------------- net/hsr/hsr_forward.c | 8 +++++++- 2 files changed, 14 insertions(+), 33 deletions(-) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index fec1b014c0a2..7449c3c95317 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -232,7 +232,7 @@ static const struct header_ops hsr_header_ops = { .parse = eth_header_parse, }; -static struct sk_buff *hsr_init_skb(struct hsr_port *master, u16 proto) +static struct sk_buff *hsr_init_skb(struct hsr_port *master) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; @@ -244,8 +244,7 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master, u16 proto) * being, for PRP it is a trailer and for HSR it is a * header */ - skb = dev_alloc_skb(sizeof(struct hsr_tag) + - sizeof(struct hsr_sup_tag) + + skb = dev_alloc_skb(sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload) + hlen + tlen); if (!skb) @@ -253,10 +252,9 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master, u16 proto) skb_reserve(skb, hlen); skb->dev = master->dev; - skb->protocol = htons(proto); skb->priority = TC_PRIO_CONTROL; - if (dev_hard_header(skb, skb->dev, proto, + if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; @@ -278,12 +276,10 @@ static void send_hsr_supervision_frame(struct hsr_port *master, { struct hsr_priv *hsr = master->hsr; __u8 type = HSR_TLV_LIFE_CHECK; - struct hsr_tag *hsr_tag = NULL; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; unsigned long irqflags; struct sk_buff *skb; - u16 proto; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { @@ -292,23 +288,12 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr->announce_count++; } - if (!hsr->prot_version) - proto = ETH_P_PRP; - else - proto = ETH_P_HSR; - - skb = hsr_init_skb(master, proto); + skb = hsr_init_skb(master); if (!skb) { WARN_ONCE(1, "HSR: Could not send supervision frame\n"); return; } - if (hsr->prot_version > 0) { - hsr_tag = skb_put(skb, sizeof(struct hsr_tag)); - hsr_tag->encap_proto = htons(ETH_P_PRP); - set_hsr_tag_LSDU_size(hsr_tag, HSR_V1_SUP_LSDUSIZE); - } - hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); @@ -318,8 +303,6 @@ static void send_hsr_supervision_frame(struct hsr_port *master, if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; - hsr_tag->sequence_nr = htons(hsr->sequence_nr); - hsr->sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; @@ -335,7 +318,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); - if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN)) + if (skb_put_padto(skb, ETH_ZLEN)) return; hsr_forward_skb(skb, master); @@ -351,10 +334,8 @@ static void send_prp_supervision_frame(struct hsr_port *master, struct hsr_sup_tag *hsr_stag; unsigned long irqflags; struct sk_buff *skb; - struct prp_rct *rct; - u8 *tail; - skb = hsr_init_skb(master, ETH_P_PRP); + skb = hsr_init_skb(master); if (!skb) { WARN_ONCE(1, "PRP: Could not send supervision frame\n"); return; @@ -376,17 +357,11 @@ static void send_prp_supervision_frame(struct hsr_port *master, hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); - if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN)) { + if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); return; } - tail = skb_tail_pointer(skb) - HSR_HLEN; - rct = (struct prp_rct *)tail; - rct->PRP_suffix = htons(ETH_P_PRP); - set_prp_LSDU_size(rct, HSR_V1_SUP_LSDUSIZE); - rct->sequence_nr = htons(hsr->sequence_nr); - hsr->sequence_nr++; spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); hsr_forward_skb(skb, master); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 90b0ed16552b..15653d3bb6ac 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -186,6 +186,7 @@ static struct sk_buff *prp_fill_rct(struct sk_buff *skb, set_prp_LSDU_size(trailer, lsdu_size); trailer->sequence_nr = htons(frame->sequence_nr); trailer->PRP_suffix = htons(ETH_P_PRP); + skb->protocol = eth_hdr(skb)->h_proto; return skb; } @@ -226,6 +227,7 @@ static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto; hsr_ethhdr->ethhdr.h_proto = htons(proto_version ? ETH_P_HSR : ETH_P_PRP); + skb->protocol = hsr_ethhdr->ethhdr.h_proto; return skb; } @@ -455,7 +457,11 @@ static void handle_std_frame(struct sk_buff *skb, int hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, struct hsr_frame_info *frame) { - if (proto == htons(ETH_P_PRP) || + struct hsr_port *port = frame->port_rcv; + struct hsr_priv *hsr = port->hsr; + + /* HSRv0 supervisory frames double as a tag so treat them as tagged. */ + if ((!hsr->prot_version && proto == htons(ETH_P_PRP)) || proto == htons(ETH_P_HSR)) { /* Check if skb contains hsr_ethhdr */ if (skb->mac_len < sizeof(struct hsr_ethhdr)) From 28921ec555d526f42bd305458f51e2f827765844 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 29 Nov 2022 17:48:11 +0100 Subject: [PATCH 0291/4345] hsr: Disable netpoll. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d5c7652eb16fa203d82546e0285136d7b321ffa9 ] The hsr device is a software device. Its net_device_ops::ndo_start_xmit() routine will process the packet and then pass the resulting skb to dev_queue_xmit(). During processing, hsr acquires a lock with spin_lock_bh() (hsr_add_node()) which needs to be promoted to the _irq() suffix in order to avoid a potential deadlock. Then there are the warnings in dev_queue_xmit() (due to local_bh_disable() with disabled interrupts) left. Instead trying to address those (there is qdisc and…) for netpoll sake, just disable netpoll on hsr. Disable netpoll on hsr and replace the _irqsave() locking with _bh(). Fixes: f421436a591d3 ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)") Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/hsr/hsr_device.c | 14 ++++++-------- net/hsr/hsr_forward.c | 5 ++--- 2 files changed, 8 insertions(+), 11 deletions(-) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 7449c3c95317..037ad39564a4 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -278,7 +278,6 @@ static void send_hsr_supervision_frame(struct hsr_port *master, __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; - unsigned long irqflags; struct sk_buff *skb; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); @@ -299,7 +298,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ - spin_lock_irqsave(&master->hsr->seqnr_lock, irqflags); + spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; @@ -307,7 +306,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } - spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); + spin_unlock_bh(&hsr->seqnr_lock); hsr_stag->HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ @@ -332,7 +331,6 @@ static void send_prp_supervision_frame(struct hsr_port *master, struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; - unsigned long irqflags; struct sk_buff *skb; skb = hsr_init_skb(master); @@ -347,7 +345,7 @@ static void send_prp_supervision_frame(struct hsr_port *master, set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ - spin_lock_irqsave(&master->hsr->seqnr_lock, irqflags); + spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; @@ -358,11 +356,11 @@ static void send_prp_supervision_frame(struct hsr_port *master, ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { - spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); + spin_unlock_bh(&hsr->seqnr_lock); return; } - spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); + spin_unlock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); } @@ -443,7 +441,7 @@ void hsr_dev_setup(struct net_device *dev) dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); - dev->priv_flags |= IFF_NO_QUEUE; + dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; dev->needs_free_netdev = true; diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 15653d3bb6ac..142bed7f1fea 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -437,7 +437,6 @@ static void handle_std_frame(struct sk_buff *skb, { struct hsr_port *port = frame->port_rcv; struct hsr_priv *hsr = port->hsr; - unsigned long irqflags; frame->skb_hsr = NULL; frame->skb_prp = NULL; @@ -447,10 +446,10 @@ static void handle_std_frame(struct sk_buff *skb, frame->is_from_san = true; } else { /* Sequence nr for the master node */ - spin_lock_irqsave(&hsr->seqnr_lock, irqflags); + spin_lock_bh(&hsr->seqnr_lock); frame->sequence_nr = hsr->sequence_nr; hsr->sequence_nr++; - spin_unlock_irqrestore(&hsr->seqnr_lock, irqflags); + spin_unlock_bh(&hsr->seqnr_lock); } } From c671f2d10d83cd685123af485f8d1663a725a785 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 29 Nov 2022 17:48:12 +0100 Subject: [PATCH 0292/4345] hsr: Synchronize sending frames to have always incremented outgoing seq nr. [ Upstream commit 06afd2c31d338fa762548580c1bf088703dd1e03 ] Sending frames via the hsr (master) device requires a sequence number which is tracked in hsr_priv::sequence_nr and protected by hsr_priv::seqnr_lock. Each time a new frame is sent, it will obtain a new id and then send it via the slave devices. Each time a packet is sent (via hsr_forward_do()) the sequence number is checked via hsr_register_frame_out() to ensure that a frame is not handled twice. This make sense for the receiving side to ensure that the frame is not injected into the stack twice after it has been received from both slave ports. There is no locking to cover the sending path which means the following scenario is possible: CPU0 CPU1 hsr_dev_xmit(skb1) hsr_dev_xmit(skb2) fill_frame_info() fill_frame_info() hsr_fill_frame_info() hsr_fill_frame_info() handle_std_frame() handle_std_frame() skb1's sequence_nr = 1 skb2's sequence_nr = 2 hsr_forward_do() hsr_forward_do() hsr_register_frame_out(, 2) // okay, send) hsr_register_frame_out(, 1) // stop, lower seq duplicate Both skbs (or their struct hsr_frame_info) received an unique id. However since skb2 was sent before skb1, the higher sequence number was recorded in hsr_register_frame_out() and the late arriving skb1 was dropped and never sent. This scenario has been observed in a three node HSR setup, with node1 + node2 having ping and iperf running in parallel. From time to time ping reported a missing packet. Based on tracing that missing ping packet did not leave the system. It might be possible (didn't check) to drop the sequence number check on the sending side. But if the higher sequence number leaves on wire before the lower does and the destination receives them in that order and it will drop the packet with the lower sequence number and never inject into the stack. Therefore it seems the only way is to lock the whole path from obtaining the sequence number and sending via dev_queue_xmit() and assuming the packets leave on wire in the same order (and don't get reordered by the NIC). Cover the whole path for the master interface from obtaining the ID until after it has been forwarded via hsr_forward_skb() to ensure the skbs are sent to the NIC in the order of the assigned sequence numbers. Fixes: f421436a591d3 ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)") Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/hsr/hsr_device.c | 12 +++++++----- net/hsr/hsr_forward.c | 3 +-- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 037ad39564a4..84e6ef4f3525 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -219,7 +219,9 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); + spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); + spin_unlock_bh(&hsr->seqnr_lock); } else { atomic_long_inc(&dev->tx_dropped); dev_kfree_skb_any(skb); @@ -306,7 +308,6 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } - spin_unlock_bh(&hsr->seqnr_lock); hsr_stag->HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ @@ -317,11 +318,13 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); - if (skb_put_padto(skb, ETH_ZLEN)) + if (skb_put_padto(skb, ETH_ZLEN)) { + spin_unlock_bh(&hsr->seqnr_lock); return; + } hsr_forward_skb(skb, master); - + spin_unlock_bh(&hsr->seqnr_lock); return; } @@ -360,9 +363,8 @@ static void send_prp_supervision_frame(struct hsr_port *master, return; } - spin_unlock_bh(&hsr->seqnr_lock); - hsr_forward_skb(skb, master); + spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 142bed7f1fea..aec48e670fb6 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -446,10 +446,9 @@ static void handle_std_frame(struct sk_buff *skb, frame->is_from_san = true; } else { /* Sequence nr for the master node */ - spin_lock_bh(&hsr->seqnr_lock); + lockdep_assert_held(&hsr->seqnr_lock); frame->sequence_nr = hsr->sequence_nr; hsr->sequence_nr++; - spin_unlock_bh(&hsr->seqnr_lock); } } From 0cf92d23569223f00a108327a03584a754924895 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 29 Nov 2022 17:48:13 +0100 Subject: [PATCH 0293/4345] hsr: Synchronize sequence number updates. [ Upstream commit 5c7aa13210c3abdd34fd421f62347665ec6eb551 ] hsr_register_frame_out() compares new sequence_nr vs the old one recorded in hsr_node::seq_out and if the new sequence_nr is higher then it will be written to hsr_node::seq_out as the new value. This operation isn't locked so it is possible that two frames with the same sequence number arrive (via the two slave devices) and are fed to hsr_register_frame_out() at the same time. Both will pass the check and update the sequence counter later to the same value. As a result the content of the same packet is fed into the stack twice. This was noticed by running ping and observing DUP being reported from time to time. Instead of using the hsr_priv::seqnr_lock for the whole receive path (as it is for sending in the master node) add an additional lock that is only used for sequence number checks and updates. Add a per-node lock that is used during sequence number reads and updates. Fixes: f421436a591d3 ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)") Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/hsr/hsr_framereg.c | 9 ++++++++- net/hsr/hsr_framereg.h | 2 ++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 805f974923b9..20cb6b7dbc69 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -159,6 +159,7 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, return NULL; ether_addr_copy(new_node->macaddress_A, addr); + spin_lock_init(&new_node->seq_out_lock); /* We are only interested in time diffs here, so use current jiffies * as initialization. (0 could trigger an spurious ring error warning). @@ -311,6 +312,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) goto done; ether_addr_copy(node_real->macaddress_B, ethhdr->h_source); + spin_lock_bh(&node_real->seq_out_lock); for (i = 0; i < HSR_PT_PORTS; i++) { if (!node_curr->time_in_stale[i] && time_after(node_curr->time_in[i], node_real->time_in[i])) { @@ -321,6 +323,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) if (seq_nr_after(node_curr->seq_out[i], node_real->seq_out[i])) node_real->seq_out[i] = node_curr->seq_out[i]; } + spin_unlock_bh(&node_real->seq_out_lock); node_real->addr_B_port = port_rcv->type; spin_lock_bh(&hsr->list_lock); @@ -413,13 +416,17 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, u16 sequence_nr) { + spin_lock_bh(&node->seq_out_lock); if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type]) && time_is_after_jiffies(node->time_out[port->type] + - msecs_to_jiffies(HSR_ENTRY_FORGET_TIME))) + msecs_to_jiffies(HSR_ENTRY_FORGET_TIME))) { + spin_unlock_bh(&node->seq_out_lock); return 1; + } node->time_out[port->type] = jiffies; node->seq_out[port->type] = sequence_nr; + spin_unlock_bh(&node->seq_out_lock); return 0; } diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index d9628e7a5f05..5a771cb3f032 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -69,6 +69,8 @@ void prp_update_san_info(struct hsr_node *node, bool is_sup); struct hsr_node { struct list_head mac_list; + /* Protect R/W access to seq_out */ + spinlock_t seq_out_lock; unsigned char macaddress_A[ETH_ALEN]; unsigned char macaddress_B[ETH_ALEN]; /* Local slave through which AddrB frames are received from this node */ From 74ac7c9ee2d486c501e7864c903f5098fc477acd Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Mon, 17 Oct 2022 09:42:30 +0800 Subject: [PATCH 0294/4345] configfs: fix possible memory leak in configfs_create_dir() [ Upstream commit c65234b283a65cfbfc94619655e820a5e55199eb ] kmemleak reported memory leaks in configfs_create_dir(): unreferenced object 0xffff888009f6af00 (size 192): comm "modprobe", pid 3777, jiffies 4295537735 (age 233.784s) backtrace: kmem_cache_alloc (mm/slub.c:3250 mm/slub.c:3256 mm/slub.c:3263 mm/slub.c:3273) new_fragment (./include/linux/slab.h:600 fs/configfs/dir.c:163) configfs_register_subsystem (fs/configfs/dir.c:1857) basic_write (drivers/hwtracing/stm/p_basic.c:14) stm_p_basic do_one_initcall (init/main.c:1296) do_init_module (kernel/module/main.c:2455) ... unreferenced object 0xffff888003ba7180 (size 96): comm "modprobe", pid 3777, jiffies 4295537735 (age 233.784s) backtrace: kmem_cache_alloc (mm/slub.c:3250 mm/slub.c:3256 mm/slub.c:3263 mm/slub.c:3273) configfs_new_dirent (./include/linux/slab.h:723 fs/configfs/dir.c:194) configfs_make_dirent (fs/configfs/dir.c:248) configfs_create_dir (fs/configfs/dir.c:296) configfs_attach_group.isra.28 (fs/configfs/dir.c:816 fs/configfs/dir.c:852) configfs_register_subsystem (fs/configfs/dir.c:1881) basic_write (drivers/hwtracing/stm/p_basic.c:14) stm_p_basic do_one_initcall (init/main.c:1296) do_init_module (kernel/module/main.c:2455) ... This is because the refcount is not correct in configfs_make_dirent(). For normal stage, the refcount is changing as: configfs_register_subsystem() configfs_create_dir() configfs_make_dirent() configfs_new_dirent() # set s_count = 1 dentry->d_fsdata = configfs_get(sd); # s_count = 2 ... configfs_unregister_subsystem() configfs_remove_dir() remove_dir() configfs_remove_dirent() # s_count = 1 dput() ... *dentry_unlink_inode()* configfs_d_iput() # s_count = 0, release However, if we failed in configfs_create(): configfs_register_subsystem() configfs_create_dir() configfs_make_dirent() # s_count = 2 ... configfs_create() # fail ->out_remove: configfs_remove_dirent(dentry) configfs_put(sd) # s_count = 1 return PTR_ERR(inode); There is no inode in the error path, so the configfs_d_iput() is lost and makes sd and fragment memory leaked. To fix this, when we failed in configfs_create(), manually call configfs_put(sd) to keep the refcount correct. Fixes: 7063fbf22611 ("[PATCH] configfs: User-driven configuration filesystem") Signed-off-by: Chen Zhongjin Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- fs/configfs/dir.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 5ad27e484014..12388ed4faa5 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -317,6 +317,7 @@ static int configfs_create_dir(struct config_item *item, struct dentry *dentry, return 0; out_remove: + configfs_put(dentry->d_fsdata); configfs_remove_dirent(dentry); return PTR_ERR(inode); } @@ -383,6 +384,7 @@ int configfs_create_link(struct configfs_dirent *target, struct dentry *parent, return 0; out_remove: + configfs_put(dentry->d_fsdata); configfs_remove_dirent(dentry); return PTR_ERR(inode); } From 6a03c31d08f95dca9633a552de167b9e625833a8 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 2 Dec 2022 10:51:11 +0800 Subject: [PATCH 0295/4345] regulator: core: fix resource leak in regulator_register() [ Upstream commit ba62319a42c50e6254e98b3f316464fac8e77968 ] I got some resource leak reports while doing fault injection test: OF: ERROR: memory leak, expected refcount 1 instead of 100, of_node_get()/of_node_put() unbalanced - destroy cset entry: attach overlay node /i2c/pmic@64/regulators/buck1 unreferenced object 0xffff88810deea000 (size 512): comm "490-i2c-rt5190a", pid 253, jiffies 4294859840 (age 5061.046s) hex dump (first 32 bytes): 00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00 .....N.......... ff ff ff ff ff ff ff ff a0 1e 00 a1 ff ff ff ff ................ backtrace: [<00000000d78541e2>] kmalloc_trace+0x21/0x110 [<00000000b343d153>] device_private_init+0x32/0xd0 [<00000000be1f0c70>] device_add+0xb2d/0x1030 [<00000000e3e6344d>] regulator_register+0xaf2/0x12a0 [<00000000e2f5e754>] devm_regulator_register+0x57/0xb0 [<000000008b898197>] rt5190a_probe+0x52a/0x861 [rt5190a_regulator] unreferenced object 0xffff88810b617b80 (size 32): comm "490-i2c-rt5190a", pid 253, jiffies 4294859904 (age 5060.983s) hex dump (first 32 bytes): 72 65 67 75 6c 61 74 6f 72 2e 32 38 36 38 2d 53 regulator.2868-S 55 50 50 4c 59 00 ff ff 29 00 00 00 2b 00 00 00 UPPLY...)...+... backtrace: [<000000009da9280d>] __kmalloc_node_track_caller+0x44/0x1b0 [<0000000025c6a4e5>] kstrdup+0x3a/0x70 [<00000000790efb69>] create_regulator+0xc0/0x4e0 [<0000000005ed203a>] regulator_resolve_supply+0x2d4/0x440 [<0000000045796214>] regulator_register+0x10b3/0x12a0 [<00000000e2f5e754>] devm_regulator_register+0x57/0xb0 [<000000008b898197>] rt5190a_probe+0x52a/0x861 [rt5190a_regulator] After calling regulator_resolve_supply(), the 'rdev->supply' is set by set_supply(), after this set, in the error path, the resources need be released, so call regulator_put() to avoid the leaks. Fixes: aea6cb99703e ("regulator: resolve supply after creating regulator") Fixes: 8a866d527ac0 ("regulator: core: Resolve supply name earlier to prevent double-init") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221202025111.496402-1-yangyingliang@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 830a9be4432e..4472c31b9b00 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5400,6 +5400,7 @@ unset_supplies: regulator_remove_coupling(rdev); mutex_unlock(®ulator_list_mutex); wash: + regulator_put(rdev->supply); kfree(rdev->coupling_desc.coupled_rdevs); mutex_lock(®ulator_list_mutex); regulator_ena_gpio_free(rdev); From e7720ef53b23b965717ccdbf9038294f54dfa506 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sun, 23 Oct 2022 23:31:56 +0200 Subject: [PATCH 0296/4345] hwmon: (jc42) Convert register access and caching to regmap/regcache [ Upstream commit 8f2fa4726faf01094d7a5be7bd0c120c565f54d9 ] Switch the jc42 driver to use an I2C regmap to access the registers. Also move over to regmap's built-in caching instead of adding a custom caching implementation. This works for JC42_REG_TEMP_UPPER, JC42_REG_TEMP_LOWER and JC42_REG_TEMP_CRITICAL as these values never change except when explicitly written. The cache For JC42_REG_TEMP is dropped (regmap can't cache it because it's volatile, meaning it can change at any time) as well for simplicity and consistency with other drivers. Signed-off-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20221023213157.11078-2-martin.blumenstingl@googlemail.com Signed-off-by: Guenter Roeck Stable-dep-of: 084ed144c448 ("hwmon: (jc42) Restore the min/max/critical temperatures on resume") Signed-off-by: Sasha Levin --- drivers/hwmon/Kconfig | 1 + drivers/hwmon/jc42.c | 233 ++++++++++++++++++++++++------------------ 2 files changed, 132 insertions(+), 102 deletions(-) diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index f741c7492ee4..8a427467a842 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -766,6 +766,7 @@ config SENSORS_IT87 config SENSORS_JC42 tristate "JEDEC JC42.4 compliant memory module temperature sensors" depends on I2C + select REGMAP_I2C help If you say yes here, you get support for JEDEC JC42.4 compliant temperature sensors, which are used on many DDR3 memory modules for diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c index 4a03d010ec5a..9a2a062eb7b8 100644 --- a/drivers/hwmon/jc42.c +++ b/drivers/hwmon/jc42.c @@ -19,6 +19,7 @@ #include #include #include +#include /* Addresses to scan */ static const unsigned short normal_i2c[] = { @@ -189,31 +190,14 @@ static struct jc42_chips jc42_chips[] = { { STM_MANID, STTS3000_DEVID, STTS3000_DEVID_MASK }, }; -enum temp_index { - t_input = 0, - t_crit, - t_min, - t_max, - t_num_temp -}; - -static const u8 temp_regs[t_num_temp] = { - [t_input] = JC42_REG_TEMP, - [t_crit] = JC42_REG_TEMP_CRITICAL, - [t_min] = JC42_REG_TEMP_LOWER, - [t_max] = JC42_REG_TEMP_UPPER, -}; - /* Each client has this additional data */ struct jc42_data { - struct i2c_client *client; struct mutex update_lock; /* protect register access */ + struct regmap *regmap; bool extended; /* true if extended range supported */ bool valid; - unsigned long last_updated; /* In jiffies */ u16 orig_config; /* original configuration */ u16 config; /* current configuration */ - u16 temp[t_num_temp];/* Temperatures */ }; #define JC42_TEMP_MIN_EXTENDED (-40000) @@ -238,85 +222,102 @@ static int jc42_temp_from_reg(s16 reg) return reg * 125 / 2; } -static struct jc42_data *jc42_update_device(struct device *dev) -{ - struct jc42_data *data = dev_get_drvdata(dev); - struct i2c_client *client = data->client; - struct jc42_data *ret = data; - int i, val; - - mutex_lock(&data->update_lock); - - if (time_after(jiffies, data->last_updated + HZ) || !data->valid) { - for (i = 0; i < t_num_temp; i++) { - val = i2c_smbus_read_word_swapped(client, temp_regs[i]); - if (val < 0) { - ret = ERR_PTR(val); - goto abort; - } - data->temp[i] = val; - } - data->last_updated = jiffies; - data->valid = true; - } -abort: - mutex_unlock(&data->update_lock); - return ret; -} - static int jc42_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { - struct jc42_data *data = jc42_update_device(dev); - int temp, hyst; + struct jc42_data *data = dev_get_drvdata(dev); + unsigned int regval; + int ret, temp, hyst; - if (IS_ERR(data)) - return PTR_ERR(data); + mutex_lock(&data->update_lock); switch (attr) { case hwmon_temp_input: - *val = jc42_temp_from_reg(data->temp[t_input]); - return 0; + ret = regmap_read(data->regmap, JC42_REG_TEMP, ®val); + if (ret) + break; + + *val = jc42_temp_from_reg(regval); + break; case hwmon_temp_min: - *val = jc42_temp_from_reg(data->temp[t_min]); - return 0; + ret = regmap_read(data->regmap, JC42_REG_TEMP_LOWER, ®val); + if (ret) + break; + + *val = jc42_temp_from_reg(regval); + break; case hwmon_temp_max: - *val = jc42_temp_from_reg(data->temp[t_max]); - return 0; + ret = regmap_read(data->regmap, JC42_REG_TEMP_UPPER, ®val); + if (ret) + break; + + *val = jc42_temp_from_reg(regval); + break; case hwmon_temp_crit: - *val = jc42_temp_from_reg(data->temp[t_crit]); - return 0; + ret = regmap_read(data->regmap, JC42_REG_TEMP_CRITICAL, + ®val); + if (ret) + break; + + *val = jc42_temp_from_reg(regval); + break; case hwmon_temp_max_hyst: - temp = jc42_temp_from_reg(data->temp[t_max]); + ret = regmap_read(data->regmap, JC42_REG_TEMP_UPPER, ®val); + if (ret) + break; + + temp = jc42_temp_from_reg(regval); hyst = jc42_hysteresis[(data->config & JC42_CFG_HYST_MASK) >> JC42_CFG_HYST_SHIFT]; *val = temp - hyst; - return 0; + break; case hwmon_temp_crit_hyst: - temp = jc42_temp_from_reg(data->temp[t_crit]); + ret = regmap_read(data->regmap, JC42_REG_TEMP_CRITICAL, + ®val); + if (ret) + break; + + temp = jc42_temp_from_reg(regval); hyst = jc42_hysteresis[(data->config & JC42_CFG_HYST_MASK) >> JC42_CFG_HYST_SHIFT]; *val = temp - hyst; - return 0; + break; case hwmon_temp_min_alarm: - *val = (data->temp[t_input] >> JC42_ALARM_MIN_BIT) & 1; - return 0; + ret = regmap_read(data->regmap, JC42_REG_TEMP, ®val); + if (ret) + break; + + *val = (regval >> JC42_ALARM_MIN_BIT) & 1; + break; case hwmon_temp_max_alarm: - *val = (data->temp[t_input] >> JC42_ALARM_MAX_BIT) & 1; - return 0; + ret = regmap_read(data->regmap, JC42_REG_TEMP, ®val); + if (ret) + break; + + *val = (regval >> JC42_ALARM_MAX_BIT) & 1; + break; case hwmon_temp_crit_alarm: - *val = (data->temp[t_input] >> JC42_ALARM_CRIT_BIT) & 1; - return 0; + ret = regmap_read(data->regmap, JC42_REG_TEMP, ®val); + if (ret) + break; + + *val = (regval >> JC42_ALARM_CRIT_BIT) & 1; + break; default: - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + break; } + + mutex_unlock(&data->update_lock); + + return ret; } static int jc42_write(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long val) { struct jc42_data *data = dev_get_drvdata(dev); - struct i2c_client *client = data->client; + unsigned int regval; int diff, hyst; int ret; @@ -324,21 +325,23 @@ static int jc42_write(struct device *dev, enum hwmon_sensor_types type, switch (attr) { case hwmon_temp_min: - data->temp[t_min] = jc42_temp_to_reg(val, data->extended); - ret = i2c_smbus_write_word_swapped(client, temp_regs[t_min], - data->temp[t_min]); + ret = regmap_write(data->regmap, JC42_REG_TEMP_LOWER, + jc42_temp_to_reg(val, data->extended)); break; case hwmon_temp_max: - data->temp[t_max] = jc42_temp_to_reg(val, data->extended); - ret = i2c_smbus_write_word_swapped(client, temp_regs[t_max], - data->temp[t_max]); + ret = regmap_write(data->regmap, JC42_REG_TEMP_UPPER, + jc42_temp_to_reg(val, data->extended)); break; case hwmon_temp_crit: - data->temp[t_crit] = jc42_temp_to_reg(val, data->extended); - ret = i2c_smbus_write_word_swapped(client, temp_regs[t_crit], - data->temp[t_crit]); + ret = regmap_write(data->regmap, JC42_REG_TEMP_CRITICAL, + jc42_temp_to_reg(val, data->extended)); break; case hwmon_temp_crit_hyst: + ret = regmap_read(data->regmap, JC42_REG_TEMP_CRITICAL, + ®val); + if (ret) + return ret; + /* * JC42.4 compliant chips only support four hysteresis values. * Pick best choice and go from there. @@ -346,7 +349,7 @@ static int jc42_write(struct device *dev, enum hwmon_sensor_types type, val = clamp_val(val, (data->extended ? JC42_TEMP_MIN_EXTENDED : JC42_TEMP_MIN) - 6000, JC42_TEMP_MAX); - diff = jc42_temp_from_reg(data->temp[t_crit]) - val; + diff = jc42_temp_from_reg(regval) - val; hyst = 0; if (diff > 0) { if (diff < 2250) @@ -358,9 +361,8 @@ static int jc42_write(struct device *dev, enum hwmon_sensor_types type, } data->config = (data->config & ~JC42_CFG_HYST_MASK) | (hyst << JC42_CFG_HYST_SHIFT); - ret = i2c_smbus_write_word_swapped(data->client, - JC42_REG_CONFIG, - data->config); + ret = regmap_write(data->regmap, JC42_REG_CONFIG, + data->config); break; default: ret = -EOPNOTSUPP; @@ -458,51 +460,80 @@ static const struct hwmon_chip_info jc42_chip_info = { .info = jc42_info, }; +static bool jc42_readable_reg(struct device *dev, unsigned int reg) +{ + return (reg >= JC42_REG_CAP && reg <= JC42_REG_DEVICEID) || + reg == JC42_REG_SMBUS; +} + +static bool jc42_writable_reg(struct device *dev, unsigned int reg) +{ + return (reg >= JC42_REG_CONFIG && reg <= JC42_REG_TEMP_CRITICAL) || + reg == JC42_REG_SMBUS; +} + +static bool jc42_volatile_reg(struct device *dev, unsigned int reg) +{ + return reg == JC42_REG_CONFIG || reg == JC42_REG_TEMP; +} + +static const struct regmap_config jc42_regmap_config = { + .reg_bits = 8, + .val_bits = 16, + .val_format_endian = REGMAP_ENDIAN_BIG, + .max_register = JC42_REG_SMBUS, + .writeable_reg = jc42_writable_reg, + .readable_reg = jc42_readable_reg, + .volatile_reg = jc42_volatile_reg, + .cache_type = REGCACHE_RBTREE, +}; + static int jc42_probe(struct i2c_client *client) { struct device *dev = &client->dev; struct device *hwmon_dev; + unsigned int config, cap; struct jc42_data *data; - int config, cap; + int ret; data = devm_kzalloc(dev, sizeof(struct jc42_data), GFP_KERNEL); if (!data) return -ENOMEM; - data->client = client; + data->regmap = devm_regmap_init_i2c(client, &jc42_regmap_config); + if (IS_ERR(data->regmap)) + return PTR_ERR(data->regmap); + i2c_set_clientdata(client, data); mutex_init(&data->update_lock); - cap = i2c_smbus_read_word_swapped(client, JC42_REG_CAP); - if (cap < 0) - return cap; + ret = regmap_read(data->regmap, JC42_REG_CAP, &cap); + if (ret) + return ret; data->extended = !!(cap & JC42_CAP_RANGE); if (device_property_read_bool(dev, "smbus-timeout-disable")) { - int smbus; - /* * Not all chips support this register, but from a * quick read of various datasheets no chip appears * incompatible with the below attempt to disable * the timeout. And the whole thing is opt-in... */ - smbus = i2c_smbus_read_word_swapped(client, JC42_REG_SMBUS); - if (smbus < 0) - return smbus; - i2c_smbus_write_word_swapped(client, JC42_REG_SMBUS, - smbus | SMBUS_STMOUT); + ret = regmap_set_bits(data->regmap, JC42_REG_SMBUS, + SMBUS_STMOUT); + if (ret) + return ret; } - config = i2c_smbus_read_word_swapped(client, JC42_REG_CONFIG); - if (config < 0) - return config; + ret = regmap_read(data->regmap, JC42_REG_CONFIG, &config); + if (ret) + return ret; data->orig_config = config; if (config & JC42_CFG_SHUTDOWN) { config &= ~JC42_CFG_SHUTDOWN; - i2c_smbus_write_word_swapped(client, JC42_REG_CONFIG, config); + regmap_write(data->regmap, JC42_REG_CONFIG, config); } data->config = config; @@ -523,7 +554,7 @@ static int jc42_remove(struct i2c_client *client) config = (data->orig_config & ~JC42_CFG_HYST_MASK) | (data->config & JC42_CFG_HYST_MASK); - i2c_smbus_write_word_swapped(client, JC42_REG_CONFIG, config); + regmap_write(data->regmap, JC42_REG_CONFIG, config); } return 0; } @@ -535,8 +566,7 @@ static int jc42_suspend(struct device *dev) struct jc42_data *data = dev_get_drvdata(dev); data->config |= JC42_CFG_SHUTDOWN; - i2c_smbus_write_word_swapped(data->client, JC42_REG_CONFIG, - data->config); + regmap_write(data->regmap, JC42_REG_CONFIG, data->config); return 0; } @@ -545,8 +575,7 @@ static int jc42_resume(struct device *dev) struct jc42_data *data = dev_get_drvdata(dev); data->config &= ~JC42_CFG_SHUTDOWN; - i2c_smbus_write_word_swapped(data->client, JC42_REG_CONFIG, - data->config); + regmap_write(data->regmap, JC42_REG_CONFIG, data->config); return 0; } From 8c3ef38a0d58d2aa9b597a1d7ae485f765ce7b86 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sun, 23 Oct 2022 23:31:57 +0200 Subject: [PATCH 0297/4345] hwmon: (jc42) Restore the min/max/critical temperatures on resume MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 084ed144c448fd5bc8ed5a58247153fbbfd115c3 ] The JC42 compatible thermal sensor on Kingston KSM32ES8/16ME DIMMs (using Micron E-Die) is an ST Microelectronics STTS2004 (manufacturer 0x104a, device 0x2201). It does not keep the previously programmed minimum, maximum and critical temperatures after system suspend and resume (which is a shutdown / startup cycle for the JC42 temperature sensor). This results in an alarm on system resume because the hardware default for these values is 0°C (so any environment temperature greater than 0°C will trigger the alarm). Example before system suspend: jc42-i2c-0-1a Adapter: SMBus PIIX4 adapter port 0 at 0b00 temp1: +34.8°C (low = +0.0°C) (high = +85.0°C, hyst = +85.0°C) (crit = +95.0°C, hyst = +95.0°C) Example after system resume (without this change): jc42-i2c-0-1a Adapter: SMBus PIIX4 adapter port 0 at 0b00 temp1: +34.8°C (low = +0.0°C) ALARM (HIGH, CRIT) (high = +0.0°C, hyst = +0.0°C) (crit = +0.0°C, hyst = +0.0°C) Apply the cached values from the JC42_REG_TEMP_UPPER, JC42_REG_TEMP_LOWER, JC42_REG_TEMP_CRITICAL and JC42_REG_SMBUS (where the SMBUS register is not related to this issue but a side-effect of using regcache_sync() during system resume with the previously cached/programmed values. This fixes the alarm due to the hardware defaults of 0°C because the previously applied limits (set by userspace) are re-applied on system resume. Fixes: 175c490c9e7f ("hwmon: (jc42) Add support for STTS2004 and AT30TSE004") Reviewed-by: Guenter Roeck Signed-off-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20221023213157.11078-3-martin.blumenstingl@googlemail.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/jc42.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c index 9a2a062eb7b8..5240bfdfcf2e 100644 --- a/drivers/hwmon/jc42.c +++ b/drivers/hwmon/jc42.c @@ -567,6 +567,10 @@ static int jc42_suspend(struct device *dev) data->config |= JC42_CFG_SHUTDOWN; regmap_write(data->regmap, JC42_REG_CONFIG, data->config); + + regcache_cache_only(data->regmap, true); + regcache_mark_dirty(data->regmap); + return 0; } @@ -574,9 +578,13 @@ static int jc42_resume(struct device *dev) { struct jc42_data *data = dev_get_drvdata(dev); + regcache_cache_only(data->regmap, false); + data->config &= ~JC42_CFG_SHUTDOWN; regmap_write(data->regmap, JC42_REG_CONFIG, data->config); - return 0; + + /* Restore cached register values to hardware */ + return regcache_sync(data->regmap); } static const struct dev_pm_ops jc42_dev_pm_ops = { From be719496ae6a7fc325e9e5056a52f63ebc84cc0c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Dec 2022 11:16:40 +0000 Subject: [PATCH 0298/4345] bpf, sockmap: fix race in sock_map_free() [ Upstream commit 0a182f8d607464911756b4dbef5d6cad8de22469 ] sock_map_free() calls release_sock(sk) without owning a reference on the socket. This can cause use-after-free as syzbot found [1] Jakub Sitnicki already took care of a similar issue in sock_hash_free() in commit 75e68e5bf2c7 ("bpf, sockhash: Synchronize delete from bucket list on map free") [1] refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 0 PID: 3785 at lib/refcount.c:31 refcount_warn_saturate+0x17c/0x1a0 lib/refcount.c:31 Modules linked in: CPU: 0 PID: 3785 Comm: kworker/u4:6 Not tainted 6.1.0-rc7-syzkaller-00103-gef4d3ea40565 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Workqueue: events_unbound bpf_map_free_deferred RIP: 0010:refcount_warn_saturate+0x17c/0x1a0 lib/refcount.c:31 Code: 68 8b 31 c0 e8 75 71 15 fd 0f 0b e9 64 ff ff ff e8 d9 6e 4e fd c6 05 62 9c 3d 0a 01 48 c7 c7 80 bb 68 8b 31 c0 e8 54 71 15 fd <0f> 0b e9 43 ff ff ff 89 d9 80 e1 07 80 c1 03 38 c1 0f 8c a2 fe ff RSP: 0018:ffffc9000456fb60 EFLAGS: 00010246 RAX: eae59bab72dcd700 RBX: 0000000000000004 RCX: ffff8880207057c0 RDX: 0000000000000000 RSI: 0000000000000201 RDI: 0000000000000000 RBP: 0000000000000004 R08: ffffffff816fdabd R09: fffff520008adee5 R10: fffff520008adee5 R11: 1ffff920008adee4 R12: 0000000000000004 R13: dffffc0000000000 R14: ffff88807b1c6c00 R15: 1ffff1100f638dcf FS: 0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b30c30000 CR3: 000000000d08e000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __refcount_dec include/linux/refcount.h:344 [inline] refcount_dec include/linux/refcount.h:359 [inline] __sock_put include/net/sock.h:779 [inline] tcp_release_cb+0x2d0/0x360 net/ipv4/tcp_output.c:1092 release_sock+0xaf/0x1c0 net/core/sock.c:3468 sock_map_free+0x219/0x2c0 net/core/sock_map.c:356 process_one_work+0x81c/0xd10 kernel/workqueue.c:2289 worker_thread+0xb14/0x1330 kernel/workqueue.c:2436 kthread+0x266/0x300 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 Fixes: 7e81a3530206 ("bpf: Sockmap, ensure sock lock held during tear down") Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Jakub Sitnicki Cc: John Fastabend Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Song Liu Acked-by: John Fastabend Link: https://lore.kernel.org/r/20221202111640.2745533-1-edumazet@google.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- net/core/sock_map.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index cbf4184fabc9..ee5d3f49b0b5 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -358,11 +358,13 @@ static void sock_map_free(struct bpf_map *map) sk = xchg(psk, NULL); if (sk) { + sock_hold(sk); lock_sock(sk); rcu_read_lock(); sock_map_unref(sk, psk); rcu_read_unlock(); release_sock(sk); + sock_put(sk); } } From 46a9b31369d76ba0f01950a0331e924be05fff58 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 5 Dec 2022 14:21:22 +0100 Subject: [PATCH 0299/4345] ALSA: pcm: Set missing stop_operating flag at undoing trigger start [ Upstream commit 5c8cc93b06d1ff860327a273abf3ac006290d242 ] When a PCM trigger-start fails at snd_pcm_do_start(), PCM core tries to undo the action at snd_pcm_undo_start() by issuing the trigger STOP manually. At that point, we forgot to set the stop_operating flag, hence the sync-stop won't be issued at the next prepare or other calls. This patch adds the missing stop_operating flag at snd_pcm_undo_start(). Fixes: 1e850beea278 ("ALSA: pcm: Add the support for sync-stop operation") Link: https://lore.kernel.org/r/b4e71631-4a94-613-27b2-fb595792630@carlh.net Link: https://lore.kernel.org/r/20221205132124.11585-2-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/core/pcm_native.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 6cc7c2a9fe73..9425fcd30c4c 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1413,8 +1413,10 @@ static int snd_pcm_do_start(struct snd_pcm_substream *substream, static void snd_pcm_undo_start(struct snd_pcm_substream *substream, snd_pcm_state_t state) { - if (substream->runtime->trigger_master == substream) + if (substream->runtime->trigger_master == substream) { substream->ops->trigger(substream, SNDRV_PCM_TRIGGER_STOP); + substream->runtime->stop_operating = true; + } } static void snd_pcm_post_start(struct snd_pcm_substream *substream, From 7df1fbe49bd2963e0478dfb7fa4c1062ab1e996a Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Sat, 26 Nov 2022 11:31:26 +0000 Subject: [PATCH 0300/4345] media: saa7164: fix missing pci_disable_device() [ Upstream commit 57fb35d7542384cac8f198cd1c927540ad38b61a ] Add missing pci_disable_device() in the error path in saa7164_initdev(). Fixes: 443c1228d505 ("V4L/DVB (12923): SAA7164: Add support for the NXP SAA7164 silicon") Signed-off-by: Liu Shixin Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/pci/saa7164/saa7164-core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c index 6c08b77bfd47..3cadfbe60fe6 100644 --- a/drivers/media/pci/saa7164/saa7164-core.c +++ b/drivers/media/pci/saa7164/saa7164-core.c @@ -1270,7 +1270,7 @@ static int saa7164_initdev(struct pci_dev *pci_dev, if (saa7164_dev_setup(dev) < 0) { err = -EINVAL; - goto fail_free; + goto fail_dev; } /* print pci info */ @@ -1438,6 +1438,8 @@ fail_fw: fail_irq: saa7164_dev_unregister(dev); +fail_dev: + pci_disable_device(pci_dev); fail_free: v4l2_device_unregister(&dev->v4l2_dev); kfree(dev); From 0649129359219ce6ff380ec401f87308485c6ae3 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 6 Dec 2022 14:10:04 +0800 Subject: [PATCH 0301/4345] ALSA: mts64: fix possible null-ptr-defer in snd_mts64_interrupt [ Upstream commit cf2ea3c86ad90d63d1c572b43e1ca9276b0357ad ] I got a null-ptr-defer error report when I do the following tests on the qemu platform: make defconfig and CONFIG_PARPORT=m, CONFIG_PARPORT_PC=m, CONFIG_SND_MTS64=m Then making test scripts: cat>test_mod1.sh< snd_mts64_interrupt+0x24/0xa0 [snd_mts64] parport_irq_handler+0x37/0x50 [parport] __handle_irq_event_percpu+0x39/0x190 handle_irq_event_percpu+0xa/0x30 handle_irq_event+0x2f/0x50 handle_edge_irq+0x99/0x1b0 __common_interrupt+0x5d/0x100 common_interrupt+0xa0/0xc0 asm_common_interrupt+0x22/0x40 RIP: 0010:_raw_write_unlock_irqrestore+0x11/0x30 parport_claim+0xbd/0x230 [parport] snd_mts64_probe+0x14a/0x465 [snd_mts64] platform_probe+0x3f/0xa0 really_probe+0x129/0x2c0 __driver_probe_device+0x6d/0xc0 driver_probe_device+0x1a/0xa0 __device_attach_driver+0x7a/0xb0 bus_for_each_drv+0x62/0xb0 __device_attach+0xe4/0x180 bus_probe_device+0x82/0xa0 device_add+0x550/0x920 platform_device_add+0x106/0x220 snd_mts64_attach+0x2e/0x80 [snd_mts64] port_check+0x14/0x20 [parport] bus_for_each_dev+0x6e/0xc0 __parport_register_driver+0x7c/0xb0 [parport] snd_mts64_module_init+0x31/0x1000 [snd_mts64] do_one_initcall+0x3c/0x1f0 do_init_module+0x46/0x1c6 load_module+0x1d8d/0x1e10 __do_sys_finit_module+0xa2/0xf0 do_syscall_64+0x37/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Kernel panic - not syncing: Fatal exception in interrupt Rebooting in 1 seconds.. The mts wa not initialized during interrupt, we add check for mts to fix this bug. Fixes: 68ab801e32bb ("[ALSA] Add snd-mts64 driver for ESI Miditerminal 4140") Signed-off-by: Gaosheng Cui Link: https://lore.kernel.org/r/20221206061004.1222966-1-cuigaosheng1@huawei.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/drivers/mts64.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/drivers/mts64.c b/sound/drivers/mts64.c index 9c708b693cb3..257314920e4d 100644 --- a/sound/drivers/mts64.c +++ b/sound/drivers/mts64.c @@ -816,6 +816,9 @@ static void snd_mts64_interrupt(void *private) u8 status, data; struct snd_rawmidi_substream *substream; + if (!mts) + return; + spin_lock(&mts->lock); ret = mts64_read(mts->pardev->port); data = ret & 0x00ff; From be7d90fc3a8f59adf7f9440ec4451fe8c1f13d7c Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Sun, 20 Nov 2022 15:34:29 +0800 Subject: [PATCH 0302/4345] xprtrdma: Fix regbuf data not freed in rpcrdma_req_create() [ Upstream commit 9181f40fb2952fd59ecb75e7158620c9c669eee3 ] If rdma receive buffer allocate failed, should call rpcrdma_regbuf_free() to free the send buffer, otherwise, the buffer data will be leaked. Fixes: bb93a1ae2bf4 ("xprtrdma: Allocate req's regbufs at xprt create time") Signed-off-by: Zhang Xiaoxu Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- net/sunrpc/xprtrdma/verbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index dcc1992b14d7..338b06de86d1 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -866,7 +866,7 @@ struct rpcrdma_req *rpcrdma_req_create(struct rpcrdma_xprt *r_xprt, size_t size, return req; out3: - kfree(req->rl_sendbuf); + rpcrdma_regbuf_free(req->rl_sendbuf); out2: kfree(req); out1: From 3fbc3c78fa32d2e7b713a9031ba44a231a9f55b5 Mon Sep 17 00:00:00 2001 From: Wang ShaoBo Date: Thu, 24 Nov 2022 17:23:42 +0800 Subject: [PATCH 0303/4345] SUNRPC: Fix missing release socket in rpc_sockname() [ Upstream commit 50fa355bc0d75911fe9d5072a5ba52cdb803aff7 ] socket dynamically created is not released when getting an unintended address family type in rpc_sockname(), direct to out_release for calling sock_release(). Fixes: 2e738fdce22f ("SUNRPC: Add API to acquire source address") Signed-off-by: Wang ShaoBo Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- net/sunrpc/clnt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 78c6648af782..c478108ca6a6 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1361,7 +1361,7 @@ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen, break; default: err = -EAFNOSUPPORT; - goto out; + goto out_release; } if (err < 0) { dprintk("RPC: can't bind UDP socket (%d)\n", err); From 81ea3d964f2b1ab7f64197375bca1fbc10a8c92d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 6 Dec 2022 12:42:59 -0500 Subject: [PATCH 0304/4345] NFSv4.x: Fail client initialisation if state manager thread can't run [ Upstream commit b4e4f66901658fae0614dea5bf91062a5387eda7 ] If the state manager thread fails to start, then we should just mark the client initialisation as failed so that other processes or threads don't get stuck in nfs_wait_client_init_complete(). Reported-by: ChenXiaoSong Fixes: 4697bd5e9419 ("NFSv4: Fix a race in the net namespace mount notification") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs4state.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index a77a3d8c0b3f..175b2e064003 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1226,6 +1226,8 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) if (IS_ERR(task)) { printk(KERN_ERR "%s: kthread_run: %ld\n", __func__, PTR_ERR(task)); + if (!nfs_client_init_is_complete(clp)) + nfs_mark_client_ready(clp, PTR_ERR(task)); nfs4_clear_state_manager_bit(clp); nfs_put_client(clp); module_put(THIS_MODULE); From 4a6e5d0222804a3eaf2ea4cf893f412e7cf98cb2 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 1 Nov 2022 14:30:15 +0800 Subject: [PATCH 0305/4345] mmc: alcor: fix return value check of mmc_add_host() [ Upstream commit e93d1468f429475a753d6baa79b853b7ee5ef8c0 ] mmc_add_host() may return error, if we ignore its return value, the memory that allocated in mmc_alloc_host() will be leaked and it will lead a kernel crash because of deleting not added device in the remove path. So fix this by checking the return value and calling mmc_free_host() in the error path. Fixes: c5413ad815a6 ("mmc: add new Alcor Micro Cardreader SD/MMC driver") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221101063023.1664968-2-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/alcor.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c index bfb8efeb7eb8..d01df01d4b4d 100644 --- a/drivers/mmc/host/alcor.c +++ b/drivers/mmc/host/alcor.c @@ -1114,7 +1114,10 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev) alcor_hw_init(host); dev_set_drvdata(&pdev->dev, host); - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) + goto free_host; + return 0; free_host: From 7c3b301ca8b0cab392c71da8fcdfa499074f8e97 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 1 Nov 2022 14:30:16 +0800 Subject: [PATCH 0306/4345] mmc: moxart: fix return value check of mmc_add_host() [ Upstream commit 0ca18d09c744fb030ae9bc5836c3e357e0237dea ] mmc_add_host() may return error, if we ignore its return value, the memory that allocated in mmc_alloc_host() will be leaked and it will lead a kernel crash because of deleting not added device in the remove path. So fix this by checking the return value and goto error path which will call mmc_free_host(). Fixes: 1b66e94e6b99 ("mmc: moxart: Add MOXA ART SD/MMC driver") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221101063023.1664968-3-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/moxart-mmc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c index c16300b92139..fb96bb76eefb 100644 --- a/drivers/mmc/host/moxart-mmc.c +++ b/drivers/mmc/host/moxart-mmc.c @@ -668,7 +668,9 @@ static int moxart_probe(struct platform_device *pdev) goto out; dev_set_drvdata(dev, mmc); - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) + goto out; dev_dbg(dev, "IRQ=%d, FIFO is %d bytes\n", irq, host->fifo_width); From 3904eb97bb78fdca3e16d30a38ce5697b9686110 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 1 Nov 2022 14:30:17 +0800 Subject: [PATCH 0307/4345] mmc: mxcmmc: fix return value check of mmc_add_host() [ Upstream commit cde600af7b413c9fe03e85c58c4279df90e91d13 ] mmc_add_host() may return error, if we ignore its return value, the memory that allocated in mmc_alloc_host() will be leaked and it will lead a kernel crash because of deleting not added device in the remove path. So fix this by checking the return value and goto error path which will call mmc_free_host(). Fixes: d96be879ff46 ("mmc: Add a MX2/MX3 specific SDHC driver") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221101063023.1664968-4-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/mxcmmc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c index 12ee07285980..93a105b07564 100644 --- a/drivers/mmc/host/mxcmmc.c +++ b/drivers/mmc/host/mxcmmc.c @@ -1167,7 +1167,9 @@ static int mxcmci_probe(struct platform_device *pdev) timer_setup(&host->watchdog, mxcmci_watchdog, 0); - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) + goto out_free_dma; return 0; From b896a9b7a0c37e9201fe4bc4d519a2ec193bd489 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 1 Nov 2022 14:30:18 +0800 Subject: [PATCH 0308/4345] mmc: pxamci: fix return value check of mmc_add_host() [ Upstream commit 80e1ef3afb8bfbe768380b70ffe1b6cab87d1a3b ] mmc_add_host() may return error, if we ignore its return value, the memory that allocated in mmc_alloc_host() will be leaked and it will lead a kernel crash because of deleting not added device in the remove path. So fix this by checking the return value and goto error path which will call mmc_free_host(), besides, ->exit() need be called to uninit the pdata. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221101063023.1664968-5-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/pxamci.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 55868b6b8658..e25e9bb34eb3 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -763,7 +763,12 @@ static int pxamci_probe(struct platform_device *pdev) dev_warn(dev, "gpio_ro and get_ro() both defined\n"); } - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) { + if (host->pdata && host->pdata->exit) + host->pdata->exit(dev, mmc); + goto out; + } return 0; From 7fa922c7a3dd623fd59f1af50e8896fd9ca7f654 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 1 Nov 2022 14:30:20 +0800 Subject: [PATCH 0309/4345] mmc: rtsx_usb_sdmmc: fix return value check of mmc_add_host() [ Upstream commit fc38a5a10e9e5a75eb9189854abeb8405b214cc9 ] mmc_add_host() may return error, if we ignore its return value, the memory that allocated in mmc_alloc_host() will be leaked and it will lead a kernel crash because of deleting not added device in the remove path. So fix this by checking the return value and calling mmc_free_host() in the error path, besides, led_classdev_unregister() and pm_runtime_disable() also need be called. Fixes: c7f6558d84af ("mmc: Add realtek USB sdmmc host driver") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221101063023.1664968-7-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/rtsx_usb_sdmmc.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c index 5fe4528e296e..1be3a355f10d 100644 --- a/drivers/mmc/host/rtsx_usb_sdmmc.c +++ b/drivers/mmc/host/rtsx_usb_sdmmc.c @@ -1332,6 +1332,7 @@ static int rtsx_usb_sdmmc_drv_probe(struct platform_device *pdev) #ifdef RTSX_USB_USE_LEDS_CLASS int err; #endif + int ret; ucr = usb_get_intfdata(to_usb_interface(pdev->dev.parent)); if (!ucr) @@ -1368,7 +1369,15 @@ static int rtsx_usb_sdmmc_drv_probe(struct platform_device *pdev) INIT_WORK(&host->led_work, rtsx_usb_update_led); #endif - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) { +#ifdef RTSX_USB_USE_LEDS_CLASS + led_classdev_unregister(&host->led); +#endif + mmc_free_host(mmc); + pm_runtime_disable(&pdev->dev); + return ret; + } return 0; } From aabbedcb6c9a72d12d35dc672e83f0c8064d8a61 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 1 Nov 2022 14:30:21 +0800 Subject: [PATCH 0310/4345] mmc: toshsd: fix return value check of mmc_add_host() [ Upstream commit f670744a316ea983113a65313dcd387b5a992444 ] mmc_add_host() may return error, if we ignore its return value, the memory that allocated in mmc_alloc_host() will be leaked and it will lead a kernel crash because of deleting not added device in the remove path. So fix this by checking the return value and goto error path which will call mmc_free_host(), besides, free_irq() also needs be called. Fixes: a5eb8bbd66cc ("mmc: add Toshiba PCI SD controller driver") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221101063023.1664968-8-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/toshsd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/toshsd.c b/drivers/mmc/host/toshsd.c index 8d037c2071ab..497791ffada6 100644 --- a/drivers/mmc/host/toshsd.c +++ b/drivers/mmc/host/toshsd.c @@ -651,7 +651,9 @@ static int toshsd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) goto unmap; - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) + goto free_irq; base = pci_resource_start(pdev, 0); dev_dbg(&pdev->dev, "MMIO %pa, IRQ %d\n", &base, pdev->irq); @@ -660,6 +662,8 @@ static int toshsd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; +free_irq: + free_irq(pdev->irq, host); unmap: pci_iounmap(pdev, host->ioaddr); release: From 3049a3b927a40d89d4582ff1033cd7953be773c7 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 1 Nov 2022 14:30:22 +0800 Subject: [PATCH 0311/4345] mmc: vub300: fix return value check of mmc_add_host() [ Upstream commit 0613ad2401f88bdeae5594c30afe318e93b14676 ] mmc_add_host() may return error, if we ignore its return value, the memory that allocated in mmc_alloc_host() will be leaked and it will lead a kernel crash because of deleting not added device in the remove path. So fix this by checking the return value and goto error path which will call mmc_free_host(), besides, the timer added before mmc_add_host() needs be del. And this patch fixes another missing call mmc_free_host() if usb_control_msg() fails. Fixes: 88095e7b473a ("mmc: Add new VUB300 USB-to-SD/SDIO/MMC driver") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221101063023.1664968-9-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/vub300.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index 97beece62fec..ab36ec479747 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -2299,14 +2299,14 @@ static int vub300_probe(struct usb_interface *interface, 0x0000, 0x0000, &vub300->system_port_status, sizeof(vub300->system_port_status), 1000); if (retval < 0) { - goto error4; + goto error5; } else if (sizeof(vub300->system_port_status) == retval) { vub300->card_present = (0x0001 & vub300->system_port_status.port_flags) ? 1 : 0; vub300->read_only = (0x0010 & vub300->system_port_status.port_flags) ? 1 : 0; } else { - goto error4; + goto error5; } usb_set_intfdata(interface, vub300); INIT_DELAYED_WORK(&vub300->pollwork, vub300_pollwork_thread); @@ -2329,8 +2329,13 @@ static int vub300_probe(struct usb_interface *interface, "USB vub300 remote SDIO host controller[%d]" "connected with no SD/SDIO card inserted\n", interface_to_InterfaceNumber(interface)); - mmc_add_host(mmc); + retval = mmc_add_host(mmc); + if (retval) + goto error6; + return 0; +error6: + del_timer_sync(&vub300->inactivity_timer); error5: mmc_free_host(mmc); /* From 9bedf64dda84b29151e41591d8ded9ff0e6d336a Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 1 Nov 2022 14:30:23 +0800 Subject: [PATCH 0312/4345] mmc: wmt-sdmmc: fix return value check of mmc_add_host() [ Upstream commit 29276d56f6ed138db0f38cd31aedc0b725c8c76c ] mmc_add_host() may return error, if we ignore its return value, the memory that allocated in mmc_alloc_host() will be leaked and it will lead a kernel crash because of deleting not added device in the remove path. So fix this by checking the return value and goto error path which will call mmc_free_host(), besides, clk_disable_unprepare() also needs be called. Fixes: 3a96dff0f828 ("mmc: SD/MMC Host Controller for Wondermedia WM8505/WM8650") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221101063023.1664968-10-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/wmt-sdmmc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/wmt-sdmmc.c b/drivers/mmc/host/wmt-sdmmc.c index 8df722ec57ed..393319548857 100644 --- a/drivers/mmc/host/wmt-sdmmc.c +++ b/drivers/mmc/host/wmt-sdmmc.c @@ -859,11 +859,15 @@ static int wmt_mci_probe(struct platform_device *pdev) /* configure the controller to a known 'ready' state */ wmt_reset_hardware(mmc); - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) + goto fail7; dev_info(&pdev->dev, "WMT SDHC Controller initialized\n"); return 0; +fail7: + clk_disable_unprepare(priv->clk_sdmmc); fail6: clk_put(priv->clk_sdmmc); fail5_and_a_half: From 00ac0f5f95920f003cd6ece53cdc759549b69118 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 8 Nov 2022 20:28:19 +0800 Subject: [PATCH 0313/4345] mmc: atmel-mci: fix return value check of mmc_add_host() [ Upstream commit 9e6e8c43726673ca2abcaac87640b9215fd72f4c ] mmc_add_host() may return error, if we ignore its return value, it will lead two issues: 1. The memory that allocated in mmc_alloc_host() is leaked. 2. In the remove() path, mmc_remove_host() will be called to delete device, but it's not added yet, it will lead a kernel crash because of null-ptr-deref in device_del(). So fix this by checking the return value and calling mmc_free_host() in the error path. Fixes: 7d2be0749a59 ("atmel-mci: Driver for Atmel on-chip MMC controllers") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221108122819.429975-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/atmel-mci.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index 444bd3a0a922..af85b32c6c1c 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -2223,6 +2223,7 @@ static int atmci_init_slot(struct atmel_mci *host, { struct mmc_host *mmc; struct atmel_mci_slot *slot; + int ret; mmc = mmc_alloc_host(sizeof(struct atmel_mci_slot), &host->pdev->dev); if (!mmc) @@ -2306,11 +2307,13 @@ static int atmci_init_slot(struct atmel_mci *host, host->slot[id] = slot; mmc_regulator_get_supply(mmc); - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) { + mmc_free_host(mmc); + return ret; + } if (gpio_is_valid(slot->detect_pin)) { - int ret; - timer_setup(&slot->detect_timer, atmci_detect_change, 0); ret = request_irq(gpio_to_irq(slot->detect_pin), From fb3d596267a98813a7a8206097d8d46c98505a0d Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 8 Nov 2022 20:13:16 +0800 Subject: [PATCH 0314/4345] mmc: omap_hsmmc: fix return value check of mmc_add_host() [ Upstream commit a525cad241c339ca00bf7ebf03c5180f2a9b767c ] mmc_add_host() may return error, if we ignore its return value, it will lead two issues: 1. The memory that allocated in mmc_alloc_host() is leaked. 2. In the remove() path, mmc_remove_host() will be called to delete device, but it's not added yet, it will lead a kernel crash because of null-ptr-deref in device_del(). Fix this by checking the return value and goto error path wihch will call mmc_free_host(). Fixes: a45c6cb81647 ("[ARM] 5369/1: omap mmc: Add new omap hsmmc controller for 2430 and 34xx, v3") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221108121316.340354-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/omap_hsmmc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index aa9cc49206d1..5b6ede81fc9f 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1987,7 +1987,9 @@ static int omap_hsmmc_probe(struct platform_device *pdev) if (!ret) mmc->caps |= MMC_CAP_SDIO_IRQ; - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) + goto err_irq; if (mmc_pdata(host)->name != NULL) { ret = device_create_file(&mmc->class_dev, &dev_attr_slot_name); From 64b2c441171febf075bd9632aca579afda8ab9fb Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 8 Nov 2022 20:34:17 +0800 Subject: [PATCH 0315/4345] mmc: meson-gx: fix return value check of mmc_add_host() [ Upstream commit 90935f16f2650ab7416fa2ffbe5c28cb39cf3f1e ] mmc_add_host() may return error, if we ignore its return value, it will lead two issues: 1. The memory that allocated in mmc_alloc_host() is leaked. 2. In the remove() path, mmc_remove_host() will be called to delete device, but it's not added yet, it will lead a kernel crash because of null-ptr-deref in device_del(). Fix this by checking the return value and goto error path which will call mmc_free_host(). Fixes: 51c5d8447bd7 ("MMC: meson: initial support for GX platforms") Signed-off-by: Yang Yingliang Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20221108123417.479045-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/meson-gx-mmc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index bccc85b3fc50..19a6b55e344f 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -1280,7 +1280,9 @@ static int meson_mmc_probe(struct platform_device *pdev) } mmc->ops = &meson_mmc_ops; - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) + goto err_free_irq; return 0; From 63400da6cd37a9793c19bb6aed7131b58b975a04 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 8 Nov 2022 21:09:49 +0800 Subject: [PATCH 0316/4345] mmc: via-sdmmc: fix return value check of mmc_add_host() [ Upstream commit e4e46fb61e3bb4628170810d3f2b996b709b90d9 ] mmc_add_host() may return error, if we ignore its return value, it will lead two issues: 1. The memory that allocated in mmc_alloc_host() is leaked. 2. In the remove() path, mmc_remove_host() will be called to delete device, but it's not added yet, it will lead a kernel crash because of null-ptr-deref in device_del(). Fix this by checking the return value and goto error path which will call mmc_free_host(). Fixes: f0bf7f61b840 ("mmc: Add new via-sdmmc host controller driver") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221108130949.1067699-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/via-sdmmc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c index f07c71db3caf..f6b525fb5c0e 100644 --- a/drivers/mmc/host/via-sdmmc.c +++ b/drivers/mmc/host/via-sdmmc.c @@ -1154,7 +1154,9 @@ static int via_sd_probe(struct pci_dev *pcidev, pcidev->subsystem_device == 0x3891) sdhost->quirks = VIA_CRDR_QUIRK_300MS_PWRDELAY; - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) + goto unmap; return 0; From 1922def5cb13528e23c9ddc13cf334e31499feb6 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 9 Nov 2022 21:32:37 +0800 Subject: [PATCH 0317/4345] mmc: wbsd: fix return value check of mmc_add_host() [ Upstream commit dc5b9b50fc9d1334407e316e6e29a5097ef833bd ] mmc_add_host() may return error, if we ignore its return value, it will lead two issues: 1. The memory that allocated in mmc_alloc_host() is leaked. 2. In the remove() path, mmc_remove_host() will be called to delete device, but it's not added yet, it will lead a kernel crash because of null-ptr-deref in device_del(). So fix this by checking the return value and goto error path which will call mmc_free_host(), besides, other resources also need be released. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221109133237.3273558-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/wbsd.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c index cd63ea865b77..f3090216e0dc 100644 --- a/drivers/mmc/host/wbsd.c +++ b/drivers/mmc/host/wbsd.c @@ -1703,7 +1703,17 @@ static int wbsd_init(struct device *dev, int base, int irq, int dma, */ wbsd_init_device(host); - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) { + if (!pnp) + wbsd_chip_poweroff(host); + + wbsd_release_resources(host); + wbsd_free_mmc(dev); + + mmc_free_host(mmc); + return ret; + } pr_info("%s: W83L51xD", mmc_hostname(mmc)); if (host->chip_id != 0) From 0b1e96d3fd6a4d5dfe77cdbbf975868890312f96 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 9 Nov 2022 21:35:39 +0800 Subject: [PATCH 0318/4345] mmc: mmci: fix return value check of mmc_add_host() [ Upstream commit b38a20f29a49ae04d23750d104b25400b792b98c ] mmc_add_host() may return error, if we ignore its return value, it will lead two issues: 1. The memory that allocated in mmc_alloc_host() is leaked. 2. In the remove() path, mmc_remove_host() will be called to delete device, but it's not added yet, it will lead a kernel crash because of null-ptr-deref in device_del(). So fix this by checking the return value and goto error path which will call mmc_free_host(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221109133539.3275664-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/mmci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index b5684e5d79e6..5d83c8e7bf5c 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -2191,7 +2191,9 @@ static int mmci_probe(struct amba_device *dev, pm_runtime_set_autosuspend_delay(&dev->dev, 50); pm_runtime_use_autosuspend(&dev->dev); - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (ret) + goto clk_disable; pm_runtime_put(&dev->dev); return 0; From 6fdb8661b964667454346ad6e7937b4e98990e35 Mon Sep 17 00:00:00 2001 From: Liang He Date: Tue, 19 Jul 2022 22:10:23 +0800 Subject: [PATCH 0319/4345] media: c8sectpfe: Add of_node_put() when breaking out of loop [ Upstream commit 63ff05a1ad242a5a0f897921c87b70d601bda59c ] In configure_channels(), we should call of_node_put() when breaking out of for_each_child_of_node() which will automatically increase and decrease the refcount. Fixes: c5f5d0f99794 ("[media] c8sectpfe: STiH407/10 Linux DVB demux support") Signed-off-by: Liang He Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c index dbe7788083a4..b7e0ec265b70 100644 --- a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c +++ b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-core.c @@ -937,6 +937,7 @@ static int configure_channels(struct c8sectpfei *fei) if (ret) { dev_err(fei->dev, "configure_memdma_and_inputblock failed\n"); + of_node_put(child); goto err_unmap; } index++; From 35ddd00b36589cf948875b825eedaab1aefd5ad5 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Thu, 17 Nov 2022 14:56:52 +0800 Subject: [PATCH 0320/4345] media: coda: Add check for dcoda_iram_alloc [ Upstream commit 6b8082238fb8bb20f67e46388123e67a5bbc558d ] As the coda_iram_alloc may return NULL pointer, it should be better to check the return value in order to avoid NULL poineter dereference, same as the others. Fixes: b313bcc9a467 ("[media] coda: simplify IRAM setup") Signed-off-by: Jiasheng Jiang Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/coda/coda-bit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c index 159c9de85788..b8a70ef8e8ec 100644 --- a/drivers/media/platform/coda/coda-bit.c +++ b/drivers/media/platform/coda/coda-bit.c @@ -852,7 +852,7 @@ static void coda_setup_iram(struct coda_ctx *ctx) /* Only H.264BP and H.263P3 are considered */ iram_info->buf_dbk_y_use = coda_iram_alloc(iram_info, w64); iram_info->buf_dbk_c_use = coda_iram_alloc(iram_info, w64); - if (!iram_info->buf_dbk_c_use) + if (!iram_info->buf_dbk_y_use || !iram_info->buf_dbk_c_use) goto out; iram_info->axi_sram_use |= dbk_bits; @@ -876,7 +876,7 @@ static void coda_setup_iram(struct coda_ctx *ctx) iram_info->buf_dbk_y_use = coda_iram_alloc(iram_info, w128); iram_info->buf_dbk_c_use = coda_iram_alloc(iram_info, w128); - if (!iram_info->buf_dbk_c_use) + if (!iram_info->buf_dbk_y_use || !iram_info->buf_dbk_c_use) goto out; iram_info->axi_sram_use |= dbk_bits; From d9b37ea8869e4e6da90c07a310d819a78cbd23d2 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Thu, 17 Nov 2022 15:02:36 +0800 Subject: [PATCH 0321/4345] media: coda: Add check for kmalloc [ Upstream commit 6e5e5defdb8b0186312c2f855ace175aee6daf9b ] As the kmalloc may return NULL pointer, it should be better to check the return value in order to avoid NULL poineter dereference, same as the others. Fixes: cb1d3a336371 ("[media] coda: add CODA7541 JPEG support") Signed-off-by: Jiasheng Jiang Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/coda/coda-bit.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c index b8a70ef8e8ec..6ffa12e83e42 100644 --- a/drivers/media/platform/coda/coda-bit.c +++ b/drivers/media/platform/coda/coda-bit.c @@ -1082,10 +1082,16 @@ static int coda_start_encoding(struct coda_ctx *ctx) } if (dst_fourcc == V4L2_PIX_FMT_JPEG) { - if (!ctx->params.jpeg_qmat_tab[0]) + if (!ctx->params.jpeg_qmat_tab[0]) { ctx->params.jpeg_qmat_tab[0] = kmalloc(64, GFP_KERNEL); - if (!ctx->params.jpeg_qmat_tab[1]) + if (!ctx->params.jpeg_qmat_tab[0]) + return -ENOMEM; + } + if (!ctx->params.jpeg_qmat_tab[1]) { ctx->params.jpeg_qmat_tab[1] = kmalloc(64, GFP_KERNEL); + if (!ctx->params.jpeg_qmat_tab[1]) + return -ENOMEM; + } coda_set_jpeg_compression_quality(ctx, ctx->params.jpeg_quality); } From da13355bb9961316d124f94dfc7a1385d0fb035a Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Wed, 23 Nov 2022 11:20:15 +0800 Subject: [PATCH 0322/4345] clk: samsung: Fix memory leak in _samsung_clk_register_pll() [ Upstream commit 5174e5b0d1b669a489524192b6adcbb3c54ebc72 ] If clk_register() fails, @pll->rate_table may have allocated memory by kmemdup(), so it needs to be freed, otherwise will cause memory leak issue, this patch fixes it. Fixes: 3ff6e0d8d64d ("clk: samsung: Add support to register rate_table for samsung plls") Signed-off-by: Xiu Jianfeng Link: https://lore.kernel.org/r/20221123032015.63980-1-xiujianfeng@huawei.com Reviewed-by: Alim Akhtar Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/samsung/clk-pll.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c index ac70ad785d8e..33df20f813d5 100644 --- a/drivers/clk/samsung/clk-pll.c +++ b/drivers/clk/samsung/clk-pll.c @@ -1390,6 +1390,7 @@ static void __init _samsung_clk_register_pll(struct samsung_clk_provider *ctx, if (ret) { pr_err("%s: failed to register pll clock %s : %d\n", __func__, pll_clk->name, ret); + kfree(pll->rate_table); kfree(pll); return; } From 7f3b4fa482220c539a0f2a73be3275482dd85def Mon Sep 17 00:00:00 2001 From: Kris Bahnsen Date: Wed, 7 Dec 2022 15:08:53 -0800 Subject: [PATCH 0323/4345] spi: spi-gpio: Don't set MOSI as an input if not 3WIRE mode [ Upstream commit 3a6f994f848a69deb2bf3cd9d130dd0c09730e55 ] The addition of 3WIRE support would affect MOSI direction even when still in standard (4 wire) mode. This can lead to MOSI being at an invalid logic level when a device driver sets an SPI message with a NULL tx_buf. spi.h states that if tx_buf is NULL then "zeros will be shifted out ... " If MOSI is tristated then the data shifted out is subject to pull resistors, keepers, or in the absence of those, noise. This issue came to light when using spi-gpio connected to an ADS7843 touchscreen controller. MOSI pulled high when clocking MISO data in caused the SPI device to interpret this as a command which would put the device in an unexpected and non-functional state. Fixes: 4b859db2c606 ("spi: spi-gpio: add SPI_3WIRE support") Fixes: 5132b3d28371 ("spi: gpio: Support 3WIRE high-impedance turn-around") Signed-off-by: Kris Bahnsen Link: https://lore.kernel.org/r/20221207230853.6174-1-kris@embeddedTS.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-gpio.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c index 0584f4d2fde2..3ffdab6caac2 100644 --- a/drivers/spi/spi-gpio.c +++ b/drivers/spi/spi-gpio.c @@ -244,9 +244,19 @@ static int spi_gpio_set_direction(struct spi_device *spi, bool output) if (output) return gpiod_direction_output(spi_gpio->mosi, 1); - ret = gpiod_direction_input(spi_gpio->mosi); - if (ret) - return ret; + /* + * Only change MOSI to an input if using 3WIRE mode. + * Otherwise, MOSI could be left floating if there is + * no pull resistor connected to the I/O pin, or could + * be left logic high if there is a pull-up. Transmitting + * logic high when only clocking MISO data in can put some + * SPI devices in to a bad state. + */ + if (spi->mode & SPI_3WIRE) { + ret = gpiod_direction_input(spi_gpio->mosi); + if (ret) + return ret; + } /* * Send a turnaround high impedance cycle when switching * from output to input. Theoretically there should be From d43003724879139e5e7140bae85bd6f670813d2f Mon Sep 17 00:00:00 2001 From: Bitterblue Smith Date: Thu, 1 Dec 2022 16:13:57 +0200 Subject: [PATCH 0324/4345] wifi: rtl8xxxu: Add __packed to struct rtl8723bu_c2h [ Upstream commit dd469a754afdb782ba3033cee102147493dc39f4 ] This struct is used to access a sequence of bytes received from the wifi chip. It must not have any padding bytes between the members. This doesn't change anything on my system, possibly because currently none of the members need more than byte alignment. Fixes: b2b43b7837ba ("rtl8xxxu: Initial functionality to handle C2H events for 8723bu") Signed-off-by: Bitterblue Smith Reviewed-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1a270918-da22-ff5f-29fc-7855f740c5ba@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h index b28fa0c4d180..0ed4d67308d7 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h @@ -1190,7 +1190,7 @@ struct rtl8723bu_c2h { u8 bw; } __packed ra_report; }; -}; +} __packed; struct rtl8xxxu_fileops; From f89c0fbb8bdb8cf8139520a9631210dfbd5902bb Mon Sep 17 00:00:00 2001 From: Bitterblue Smith Date: Thu, 1 Dec 2022 16:15:08 +0200 Subject: [PATCH 0325/4345] wifi: rtl8xxxu: Fix the channel width reporting [ Upstream commit 76c16af2cb10282274596e21add2c9f0b95c941b ] The gen 2 chips RTL8192EU and RTL8188FU periodically send the driver reports about the TX rate, and the driver passes these reports to sta_statistics. The reports from RTL8192EU may or may not include the channel width. The reports from RTL8188FU do not include it. Only access the c2h->ra_report.bw field if the report (skb) is big enough. The other problem fixed here is that the code was actually never changing the channel width initially reported by rtl8xxxu_bss_info_changed because the value of RATE_INFO_BW_20 is 0. Fixes: 0985d3a410ac ("rtl8xxxu: Feed current txrate information for mac80211") Signed-off-by: Bitterblue Smith Reviewed-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/5b41f1ae-72e7-6b7a-2459-b736399a1c40@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 43898f105bb7..9a12f1d38007 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -5520,7 +5520,6 @@ static void rtl8xxxu_c2hcmd_callback(struct work_struct *work) rarpt->txrate.flags = 0; rate = c2h->ra_report.rate; sgi = c2h->ra_report.sgi; - bw = c2h->ra_report.bw; if (rate < DESC_RATE_MCS0) { rarpt->txrate.legacy = @@ -5537,8 +5536,13 @@ static void rtl8xxxu_c2hcmd_callback(struct work_struct *work) RATE_INFO_FLAGS_SHORT_GI; } - if (bw == RATE_INFO_BW_20) - rarpt->txrate.bw |= RATE_INFO_BW_20; + if (skb->len >= offsetofend(typeof(*c2h), ra_report.bw)) { + if (c2h->ra_report.bw == RTL8XXXU_CHANNEL_WIDTH_40) + bw = RATE_INFO_BW_40; + else + bw = RATE_INFO_BW_20; + rarpt->txrate.bw = bw; + } } bit_rate = cfg80211_calculate_bitrate(&rarpt->txrate); rarpt->bit_rate = bit_rate; From 2484f159648031989a69e3950f79b938697152fa Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Fri, 2 Dec 2022 13:35:42 +0800 Subject: [PATCH 0326/4345] wifi: brcmfmac: Fix error return code in brcmf_sdio_download_firmware() [ Upstream commit c2f2924bc7f9ea75ef8d95863e710168f8196256 ] Fix to return a negative error code instead of 0 when brcmf_chip_set_active() fails. In addition, change the return value for brcmf_pcie_exit_download_state() to keep consistent. Fixes: d380ebc9b6fb ("brcmfmac: rename chip download functions") Signed-off-by: Wang Yufen Reviewed-by: Arend van Spriel Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1669959342-27144-1-git-send-email-wangyufen@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c | 2 +- drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 61febc9bfa14..4e9d2b3659f0 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -618,7 +618,7 @@ static int brcmf_pcie_exit_download_state(struct brcmf_pciedev_info *devinfo, } if (!brcmf_chip_set_active(devinfo->ci, resetintr)) - return -EINVAL; + return -EIO; return 0; } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 9929e90866f0..3c0d5c68eaca 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -3401,6 +3401,7 @@ static int brcmf_sdio_download_firmware(struct brcmf_sdio *bus, /* Take arm out of reset */ if (!brcmf_chip_set_active(bus->ci, rstvec)) { brcmf_err("error getting out of ARM core reset\n"); + bcmerror = -EIO; goto err; } From 782d0444eac986a4536cca2fb0f7e23de9e9e643 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 22 Nov 2022 12:04:10 +0800 Subject: [PATCH 0327/4345] blktrace: Fix output non-blktrace event when blk_classic option enabled [ Upstream commit f596da3efaf4130ff61cd029558845808df9bf99 ] When the blk_classic option is enabled, non-blktrace events must be filtered out. Otherwise, events of other types are output in the blktrace classic format, which is unexpected. The problem can be triggered in the following ways: # echo 1 > /sys/kernel/debug/tracing/options/blk_classic # echo 1 > /sys/kernel/debug/tracing/events/enable # echo blk > /sys/kernel/debug/tracing/current_tracer # cat /sys/kernel/debug/tracing/trace_pipe Fixes: c71a89615411 ("blktrace: add ftrace plugin") Signed-off-by: Yang Jihong Link: https://lore.kernel.org/r/20221122040410.85113-1-yangjihong1@huawei.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- kernel/trace/blktrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 15a376f85e09..ab912cc60760 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1592,7 +1592,8 @@ blk_trace_event_print_binary(struct trace_iterator *iter, int flags, static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) { - if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) + if ((iter->ent->type != TRACE_BLK) || + !(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) return TRACE_TYPE_UNHANDLED; return print_one_line(iter, true); From ae8190f19f964ee1d2ad02044152fce4e505e00a Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 20 Jan 2021 09:30:27 +0000 Subject: [PATCH 0328/4345] clk: socfpga: clk-pll: Remove unused variable 'rc' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 75fddccbca32349570b2d53955982b4117fa5515 ] Fixes the following W=1 kernel build warning(s): drivers/clk/socfpga/clk-pll.c: In function ‘__socfpga_pll_init’: drivers/clk/socfpga/clk-pll.c:83:6: warning: variable ‘rc’ set but not used [-Wunused-but-set-variable] Cc: Dinh Nguyen Cc: Michael Turquette Cc: Stephen Boyd Cc: linux-clk@vger.kernel.org Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20210120093040.1719407-8-lee.jones@linaro.org Acked-by: Dinh Nguyen Signed-off-by: Stephen Boyd Stable-dep-of: 0b8ba891ad4d ("clk: socfpga: Fix memory leak in socfpga_gate_init()") Signed-off-by: Sasha Levin --- drivers/clk/socfpga/clk-pll.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/clk/socfpga/clk-pll.c b/drivers/clk/socfpga/clk-pll.c index e5fb786843f3..3cf99df7d005 100644 --- a/drivers/clk/socfpga/clk-pll.c +++ b/drivers/clk/socfpga/clk-pll.c @@ -80,7 +80,6 @@ static __init struct clk *__socfpga_pll_init(struct device_node *node, const char *parent_name[SOCFPGA_MAX_PARENTS]; struct clk_init_data init; struct device_node *clkmgr_np; - int rc; of_property_read_u32(node, "reg", ®); @@ -111,7 +110,7 @@ static __init struct clk *__socfpga_pll_init(struct device_node *node, kfree(pll_clk); return NULL; } - rc = of_clk_add_provider(node, of_clk_src_simple_get, clk); + of_clk_add_provider(node, of_clk_src_simple_get, clk); return clk; } From 4b672ee71c1c32725b71a49be52ac974ea519c4a Mon Sep 17 00:00:00 2001 From: Dinh Nguyen Date: Tue, 2 Mar 2021 15:41:49 -0600 Subject: [PATCH 0329/4345] clk: socfpga: use clk_hw_register for a5/c5 [ Upstream commit 2c2b9c6067170de2a63e7e3d9f5bb205b870de7c ] As recommended by Stephen Boyd, convert the cyclone5/arria5 clock driver to use the clk_hw registration method. Suggested-by: Stephen Boyd Signed-off-by: Dinh Nguyen Link: https://lore.kernel.org/r/20210302214151.1333447-1-dinguyen@kernel.org Signed-off-by: Stephen Boyd Stable-dep-of: 0b8ba891ad4d ("clk: socfpga: Fix memory leak in socfpga_gate_init()") Signed-off-by: Sasha Levin --- drivers/clk/socfpga/clk-gate.c | 11 +++++++---- drivers/clk/socfpga/clk-periph.c | 8 ++++---- drivers/clk/socfpga/clk-pll.c | 18 +++++++++++------- 3 files changed, 22 insertions(+), 15 deletions(-) diff --git a/drivers/clk/socfpga/clk-gate.c b/drivers/clk/socfpga/clk-gate.c index cf94a12459ea..1ec9678d8cd3 100644 --- a/drivers/clk/socfpga/clk-gate.c +++ b/drivers/clk/socfpga/clk-gate.c @@ -174,13 +174,14 @@ void __init socfpga_gate_init(struct device_node *node) u32 div_reg[3]; u32 clk_phase[2]; u32 fixed_div; - struct clk *clk; + struct clk_hw *hw_clk; struct socfpga_gate_clk *socfpga_clk; const char *clk_name = node->name; const char *parent_name[SOCFPGA_MAX_PARENTS]; struct clk_init_data init; struct clk_ops *ops; int rc; + int err; socfpga_clk = kzalloc(sizeof(*socfpga_clk), GFP_KERNEL); if (WARN_ON(!socfpga_clk)) @@ -238,12 +239,14 @@ void __init socfpga_gate_init(struct device_node *node) init.parent_names = parent_name; socfpga_clk->hw.hw.init = &init; - clk = clk_register(NULL, &socfpga_clk->hw.hw); - if (WARN_ON(IS_ERR(clk))) { + hw_clk = &socfpga_clk->hw.hw; + + err = clk_hw_register(NULL, hw_clk); + if (err) { kfree(socfpga_clk); return; } - rc = of_clk_add_provider(node, of_clk_src_simple_get, clk); + rc = of_clk_add_provider(node, of_clk_src_simple_get, hw_clk); if (WARN_ON(rc)) return; } diff --git a/drivers/clk/socfpga/clk-periph.c b/drivers/clk/socfpga/clk-periph.c index 5e0c4b45f77f..43707e2d7248 100644 --- a/drivers/clk/socfpga/clk-periph.c +++ b/drivers/clk/socfpga/clk-periph.c @@ -51,7 +51,7 @@ static __init void __socfpga_periph_init(struct device_node *node, const struct clk_ops *ops) { u32 reg; - struct clk *clk; + struct clk_hw *hw_clk; struct socfpga_periph_clk *periph_clk; const char *clk_name = node->name; const char *parent_name[SOCFPGA_MAX_PARENTS]; @@ -94,13 +94,13 @@ static __init void __socfpga_periph_init(struct device_node *node, init.parent_names = parent_name; periph_clk->hw.hw.init = &init; + hw_clk = &periph_clk->hw.hw; - clk = clk_register(NULL, &periph_clk->hw.hw); - if (WARN_ON(IS_ERR(clk))) { + if (clk_hw_register(NULL, hw_clk)) { kfree(periph_clk); return; } - rc = of_clk_add_provider(node, of_clk_src_simple_get, clk); + rc = of_clk_add_provider(node, of_clk_src_simple_get, hw_clk); } void __init socfpga_periph_init(struct device_node *node) diff --git a/drivers/clk/socfpga/clk-pll.c b/drivers/clk/socfpga/clk-pll.c index 3cf99df7d005..dcb573d44034 100644 --- a/drivers/clk/socfpga/clk-pll.c +++ b/drivers/clk/socfpga/clk-pll.c @@ -70,16 +70,18 @@ static const struct clk_ops clk_pll_ops = { .get_parent = clk_pll_get_parent, }; -static __init struct clk *__socfpga_pll_init(struct device_node *node, +static __init struct clk_hw *__socfpga_pll_init(struct device_node *node, const struct clk_ops *ops) { u32 reg; - struct clk *clk; + struct clk_hw *hw_clk; struct socfpga_pll *pll_clk; const char *clk_name = node->name; const char *parent_name[SOCFPGA_MAX_PARENTS]; struct clk_init_data init; struct device_node *clkmgr_np; + int rc; + int err; of_property_read_u32(node, "reg", ®); @@ -105,13 +107,15 @@ static __init struct clk *__socfpga_pll_init(struct device_node *node, pll_clk->hw.bit_idx = SOCFPGA_PLL_EXT_ENA; - clk = clk_register(NULL, &pll_clk->hw.hw); - if (WARN_ON(IS_ERR(clk))) { + hw_clk = &pll_clk->hw.hw; + + err = clk_hw_register(NULL, hw_clk); + if (err) { kfree(pll_clk); - return NULL; + return ERR_PTR(err); } - of_clk_add_provider(node, of_clk_src_simple_get, clk); - return clk; + rc = of_clk_add_provider(node, of_clk_src_simple_get, hw_clk); + return hw_clk; } void __init socfpga_pll_init(struct device_node *node) From 3e8fd1d0fab4d5c9a50d225dddc207deac12f13a Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Wed, 23 Nov 2022 11:16:22 +0800 Subject: [PATCH 0330/4345] clk: socfpga: Fix memory leak in socfpga_gate_init() [ Upstream commit 0b8ba891ad4d1ef6bfa4c72efc83f9f9f855f68b ] Free @socfpga_clk and @ops on the error path to avoid memory leak issue. Fixes: a30a67be7b6e ("clk: socfpga: Don't have get_parent for single parent ops") Signed-off-by: Xiu Jianfeng Link: https://lore.kernel.org/r/20221123031622.63171-1-xiujianfeng@huawei.com Acked-by: Dinh Nguyen Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/socfpga/clk-gate.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/clk/socfpga/clk-gate.c b/drivers/clk/socfpga/clk-gate.c index 1ec9678d8cd3..ee2a2d284113 100644 --- a/drivers/clk/socfpga/clk-gate.c +++ b/drivers/clk/socfpga/clk-gate.c @@ -188,8 +188,10 @@ void __init socfpga_gate_init(struct device_node *node) return; ops = kmemdup(&gateclk_ops, sizeof(gateclk_ops), GFP_KERNEL); - if (WARN_ON(!ops)) + if (WARN_ON(!ops)) { + kfree(socfpga_clk); return; + } rc = of_property_read_u32_array(node, "clk-gate", clk_gate, 2); if (rc) @@ -243,6 +245,7 @@ void __init socfpga_gate_init(struct device_node *node) err = clk_hw_register(NULL, hw_clk); if (err) { + kfree(ops); kfree(socfpga_clk); return; } From e2227eee7ae1c57daeae350b47cfe050bfe9cdda Mon Sep 17 00:00:00 2001 From: Artem Chernyshev Date: Tue, 6 Dec 2022 09:58:34 +0300 Subject: [PATCH 0331/4345] net: vmw_vsock: vmci: Check memcpy_from_msg() [ Upstream commit 44aa5a6dba8283bfda28b1517af4de711c5652a4 ] vmci_transport_dgram_enqueue() does not check the return value of memcpy_from_msg(). If memcpy_from_msg() fails, it is possible that uninitialized memory contents are sent unintentionally instead of user's message in the datagram to the destination. Return with an error if memcpy_from_msg() fails. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 0f7db23a07af ("vmci_transport: switch ->enqeue_dgram, ->enqueue_stream and ->dequeue_stream to msghdr") Signed-off-by: Artem Chernyshev Reviewed-by: Stefano Garzarella Reviewed-by: Vishnu Dasa Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/vmw_vsock/vmci_transport.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index a9ca95a0fcdd..8c2856cbfecc 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1713,7 +1713,11 @@ static int vmci_transport_dgram_enqueue( if (!dg) return -ENOMEM; - memcpy_from_msg(VMCI_DG_PAYLOAD(dg), msg, len); + err = memcpy_from_msg(VMCI_DG_PAYLOAD(dg), msg, len); + if (err) { + kfree(dg); + return err; + } dg->dst = vmci_make_handle(remote_addr->svm_cid, remote_addr->svm_port); From 8ed99944572b118770253c81493a620673a0f96b Mon Sep 17 00:00:00 2001 From: Yongqiang Liu Date: Wed, 7 Dec 2022 07:20:45 +0000 Subject: [PATCH 0332/4345] net: defxx: Fix missing err handling in dfx_init() [ Upstream commit ae18dcdff0f8d7e84cd3fd9f496518b5e72d185d ] When eisa_driver_register() or tc_register_driver() failed, the modprobe defxx would fail with some err log as follows: Error: Driver 'defxx' is already registered, aborting... Fix this issue by adding err hanling in dfx_init(). Fixes: e89a2cfb7d7b5 ("[TC] defxx: TURBOchannel support") Signed-off-by: Yongqiang Liu Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/fddi/defxx.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c index c7ce6d5491af..442bdc6e8dc4 100644 --- a/drivers/net/fddi/defxx.c +++ b/drivers/net/fddi/defxx.c @@ -3844,10 +3844,24 @@ static int dfx_init(void) int status; status = pci_register_driver(&dfx_pci_driver); - if (!status) - status = eisa_driver_register(&dfx_eisa_driver); - if (!status) - status = tc_register_driver(&dfx_tc_driver); + if (status) + goto err_pci_register; + + status = eisa_driver_register(&dfx_eisa_driver); + if (status) + goto err_eisa_register; + + status = tc_register_driver(&dfx_tc_driver); + if (status) + goto err_tc_register; + + return 0; + +err_tc_register: + eisa_driver_unregister(&dfx_eisa_driver); +err_eisa_register: + pci_unregister_driver(&dfx_pci_driver); +err_pci_register: return status; } From 787d1bae7f1101d161a3ced9fb2b9fe800da1322 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Wed, 7 Dec 2022 16:31:59 +0800 Subject: [PATCH 0333/4345] net: stmmac: selftests: fix potential memleak in stmmac_test_arpoffload() [ Upstream commit f150b63f3fa5fdd81e0dd6151e8850268e29438c ] The skb allocated by stmmac_test_get_arp_skb() hasn't been released in some error handling case, which will lead to a memory leak. Fix this up by adding kfree_skb() to release skb. Compile tested only. Fixes: 5e3fb0a6e2b3 ("net: stmmac: selftests: Implement the ARP Offload test") Signed-off-by: Zhang Changzhong Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index dd5c4ef92ef3..ea7200b7b647 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -1654,12 +1654,16 @@ static int stmmac_test_arpoffload(struct stmmac_priv *priv) } ret = stmmac_set_arp_offload(priv, priv->hw, true, ip_addr); - if (ret) + if (ret) { + kfree_skb(skb); goto cleanup; + } ret = dev_set_promiscuity(priv->dev, 1); - if (ret) + if (ret) { + kfree_skb(skb); goto cleanup; + } ret = dev_direct_xmit(skb, 0); if (ret) From 14b349a15c297cf3e01b5deb4116f7cf297b6184 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Wed, 7 Dec 2022 08:54:10 +0000 Subject: [PATCH 0334/4345] drivers: net: qlcnic: Fix potential memory leak in qlcnic_sriov_init() [ Upstream commit 01de1123322e4fe1bbd0fcdf0982511b55519c03 ] If vp alloc failed in qlcnic_sriov_init(), all previously allocated vp needs to be freed. Fixes: f197a7aa6288 ("qlcnic: VF-PF communication channel implementation") Signed-off-by: Yuan Can Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 8367891bfb13..e864c453c5e6 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -221,6 +221,8 @@ int qlcnic_sriov_init(struct qlcnic_adapter *adapter, int num_vfs) return 0; qlcnic_destroy_async_wq: + while (i--) + kfree(sriov->vf_info[i].vp); destroy_workqueue(bc->bc_async_wq); qlcnic_destroy_trans_wq: From 2b4af99b44861646013821019dd13a4ac48c0219 Mon Sep 17 00:00:00 2001 From: ruanjinjie Date: Sun, 11 Dec 2022 10:33:37 +0800 Subject: [PATCH 0335/4345] of: overlay: fix null pointer dereferencing in find_dup_cset_node_entry() and find_dup_cset_prop() [ Upstream commit ee9d7a0e754568180a2f8ebc4aad226278a9116f ] When kmalloc() fail to allocate memory in kasprintf(), fn_1 or fn_2 will be NULL, and strcmp() will cause null pointer dereference. Fixes: 2fe0e8769df9 ("of: overlay: check prevents multiple fragments touching same property") Signed-off-by: ruanjinjie Link: https://lore.kernel.org/r/20221211023337.592266-1-ruanjinjie@huawei.com Signed-off-by: Rob Herring Signed-off-by: Sasha Levin --- drivers/of/overlay.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index c8a0c0e9dec1..67b404f36e79 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -547,7 +547,7 @@ static int find_dup_cset_node_entry(struct overlay_changeset *ovcs, fn_1 = kasprintf(GFP_KERNEL, "%pOF", ce_1->np); fn_2 = kasprintf(GFP_KERNEL, "%pOF", ce_2->np); - node_path_match = !strcmp(fn_1, fn_2); + node_path_match = !fn_1 || !fn_2 || !strcmp(fn_1, fn_2); kfree(fn_1); kfree(fn_2); if (node_path_match) { @@ -582,7 +582,7 @@ static int find_dup_cset_prop(struct overlay_changeset *ovcs, fn_1 = kasprintf(GFP_KERNEL, "%pOF", ce_1->np); fn_2 = kasprintf(GFP_KERNEL, "%pOF", ce_2->np); - node_path_match = !strcmp(fn_1, fn_2); + node_path_match = !fn_1 || !fn_2 || !strcmp(fn_1, fn_2); kfree(fn_1); kfree(fn_2); if (node_path_match && From 0b3f452d0cf7d8c10329bad52bf22aef2103c62b Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 20:01:21 +0800 Subject: [PATCH 0336/4345] ethernet: s2io: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit 6cee96e09df54ae17784c0f38a49e0ed8229b825 ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. It should use dev_kfree_skb_irq() or dev_consume_skb_irq() instead. The difference between them is free reason, dev_kfree_skb_irq() means the SKB is dropped in error and dev_consume_skb_irq() means the SKB is consumed in normal. In this case, dev_kfree_skb() is called in free_tx_buffers() to drop the SKBs in tx buffers, when the card is down, so replace it with dev_kfree_skb_irq() here. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/neterion/s2io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 8a30be698f99..ff46b08ac1f4 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -2384,7 +2384,7 @@ static void free_tx_buffers(struct s2io_nic *nic) skb = s2io_txdl_getskb(&mac_control->fifos[i], txdp, j); if (skb) { swstats->mem_freed += skb->truesize; - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); cnt++; } } From 51e2d1b84acac39f79cacb60e6e154ce00a9d308 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 8 Dec 2022 20:05:40 +0800 Subject: [PATCH 0337/4345] net: farsync: Fix kmemleak when rmmods farsync [ Upstream commit 2f623aaf9f31de968dea6169849706a2f9be444c ] There are two memory leaks reported by kmemleak: unreferenced object 0xffff888114b20200 (size 128): comm "modprobe", pid 4846, jiffies 4295146524 (age 401.345s) hex dump (first 32 bytes): e0 62 57 09 81 88 ff ff e0 62 57 09 81 88 ff ff .bW......bW..... 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmalloc_trace+0x22/0x60 [] __hw_addr_add_ex+0x198/0x6c0 [] dev_addr_init+0x13d/0x230 [] alloc_netdev_mqs+0x10d/0xe50 [] alloc_hdlcdev+0x2e/0x80 [] fst_add_one+0x601/0x10e0 [farsync] ... unreferenced object 0xffff88810b85b000 (size 1024): comm "modprobe", pid 4846, jiffies 4295146523 (age 401.346s) hex dump (first 32 bytes): 00 00 b0 02 00 c9 ff ff 00 70 0a 00 00 c9 ff ff .........p...... 00 00 00 f2 00 00 00 f3 0a 00 00 00 02 00 00 00 ................ backtrace: [] kmalloc_trace+0x22/0x60 [] fst_add_one+0x154/0x10e0 [farsync] [] local_pci_probe+0xd3/0x170 ... The root cause is traced to the netdev and fst_card_info are not freed when removes one fst in fst_remove_one(), which may trigger oom if repeated insmod and rmmod module. Fix it by adding free_netdev() and kfree() in fst_remove_one(), just as the operations on the error handling path in fst_add_one(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Li Zetao Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/wan/farsync.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index b50cf11d197d..36a6958b6a0b 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -2612,6 +2612,7 @@ fst_remove_one(struct pci_dev *pdev) for (i = 0; i < card->nports; i++) { struct net_device *dev = port_to_dev(&card->ports[i]); unregister_hdlc_device(dev); + free_netdev(dev); } fst_disable_intr(card); @@ -2632,6 +2633,7 @@ fst_remove_one(struct pci_dev *pdev) card->tx_dma_handle_card); } fst_card_array[card->card_no] = NULL; + kfree(card); } static struct pci_driver fst_driver = { From 91f09a776ae335ca836ed864b8f2a9461882a280 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 8 Dec 2022 20:04:52 +0800 Subject: [PATCH 0338/4345] net/tunnel: wait until all sk_user_data reader finish before releasing the sock [ Upstream commit 3cf7203ca620682165706f70a1b12b5194607dce ] There is a race condition in vxlan that when deleting a vxlan device during receiving packets, there is a possibility that the sock is released after getting vxlan_sock vs from sk_user_data. Then in later vxlan_ecn_decapsulate(), vxlan_get_sk_family() we will got NULL pointer dereference. e.g. #0 [ffffa25ec6978a38] machine_kexec at ffffffff8c669757 #1 [ffffa25ec6978a90] __crash_kexec at ffffffff8c7c0a4d #2 [ffffa25ec6978b58] crash_kexec at ffffffff8c7c1c48 #3 [ffffa25ec6978b60] oops_end at ffffffff8c627f2b #4 [ffffa25ec6978b80] page_fault_oops at ffffffff8c678fcb #5 [ffffa25ec6978bd8] exc_page_fault at ffffffff8d109542 #6 [ffffa25ec6978c00] asm_exc_page_fault at ffffffff8d200b62 [exception RIP: vxlan_ecn_decapsulate+0x3b] RIP: ffffffffc1014e7b RSP: ffffa25ec6978cb0 RFLAGS: 00010246 RAX: 0000000000000008 RBX: ffff8aa000888000 RCX: 0000000000000000 RDX: 000000000000000e RSI: ffff8a9fc7ab803e RDI: ffff8a9fd1168700 RBP: ffff8a9fc7ab803e R8: 0000000000700000 R9: 00000000000010ae R10: ffff8a9fcb748980 R11: 0000000000000000 R12: ffff8a9fd1168700 R13: ffff8aa000888000 R14: 00000000002a0000 R15: 00000000000010ae ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ffffa25ec6978ce8] vxlan_rcv at ffffffffc10189cd [vxlan] #8 [ffffa25ec6978d90] udp_queue_rcv_one_skb at ffffffff8cfb6507 #9 [ffffa25ec6978dc0] udp_unicast_rcv_skb at ffffffff8cfb6e45 #10 [ffffa25ec6978dc8] __udp4_lib_rcv at ffffffff8cfb8807 #11 [ffffa25ec6978e20] ip_protocol_deliver_rcu at ffffffff8cf76951 #12 [ffffa25ec6978e48] ip_local_deliver at ffffffff8cf76bde #13 [ffffa25ec6978ea0] __netif_receive_skb_one_core at ffffffff8cecde9b #14 [ffffa25ec6978ec8] process_backlog at ffffffff8cece139 #15 [ffffa25ec6978f00] __napi_poll at ffffffff8ceced1a #16 [ffffa25ec6978f28] net_rx_action at ffffffff8cecf1f3 #17 [ffffa25ec6978fa0] __softirqentry_text_start at ffffffff8d4000ca #18 [ffffa25ec6978ff0] do_softirq at ffffffff8c6fbdc3 Reproducer: https://github.com/Mellanox/ovs-tests/blob/master/test-ovs-vxlan-remove-tunnel-during-traffic.sh Fix this by waiting for all sk_user_data reader to finish before releasing the sock. Reported-by: Jianlin Shi Suggested-by: Jakub Sitnicki Fixes: 6a93cc905274 ("udp-tunnel: Add a few more UDP tunnel APIs") Signed-off-by: Hangbin Liu Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/udp_tunnel_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 3eecba0874aa..d70f683d3c49 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -194,6 +194,7 @@ EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); void udp_tunnel_sock_release(struct socket *sock) { rcu_assign_sk_user_data(sock->sk, NULL); + synchronize_rcu(); kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } From 0e23250149f498044cbb4d8747a2f233858e36ff Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 21:37:34 +0800 Subject: [PATCH 0339/4345] net: apple: mace: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit 3dfe3486c1cd4f82b466b7d307f23777137b8acc ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. It should use dev_kfree_skb_irq() or dev_consume_skb_irq() instead. The difference between them is free reason, dev_kfree_skb_irq() means the SKB is dropped in error and dev_consume_skb_irq() means the SKB is consumed in normal. In this case, dev_kfree_skb() is called in mace_tx_timeout() to drop the SKB, when tx timeout, so replace it with dev_kfree_skb_irq(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/apple/mace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index 9e5006e59215..6f6530c29166 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -841,7 +841,7 @@ static void mace_tx_timeout(struct timer_list *t) if (mp->tx_bad_runt) { mp->tx_bad_runt = 0; } else if (i != mp->tx_fill) { - dev_kfree_skb(mp->tx_bufs[i]); + dev_kfree_skb_irq(mp->tx_bufs[i]); if (++i >= N_TX_RING) i = 0; mp->tx_empty = i; From c43def060cae288a9684861b495e7784d41ea084 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 21:37:35 +0800 Subject: [PATCH 0340/4345] net: apple: bmac: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit 5fe02e046e6422c4adfdbc50206ec7186077da24 ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. It should use dev_kfree_skb_irq() or dev_consume_skb_irq() instead. The difference between them is free reason, dev_kfree_skb_irq() means the SKB is dropped in error and dev_consume_skb_irq() means the SKB is consumed in normal. In this case, dev_kfree_skb() is called in bmac_tx_timeout() to drop the SKB, when tx timeout, so replace it with dev_kfree_skb_irq(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/apple/bmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index 1e4e402f07d7..dd6c44f5f925 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -1511,7 +1511,7 @@ static void bmac_tx_timeout(struct timer_list *t) i = bp->tx_empty; ++dev->stats.tx_errors; if (i != bp->tx_fill) { - dev_kfree_skb(bp->tx_bufs[i]); + dev_kfree_skb_irq(bp->tx_bufs[i]); bp->tx_bufs[i] = NULL; if (++i >= N_TX_RING) i = 0; bp->tx_empty = i; From decede59ea06358416c855ae56b543cf0dbc35df Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 22:21:44 +0800 Subject: [PATCH 0341/4345] net: emaclite: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit d1678bf45f21fa5ae4a456f821858679556ea5f8 ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. It should use dev_kfree_skb_irq() or dev_consume_skb_irq() instead. The difference between them is free reason, dev_kfree_skb_irq() means the SKB is dropped in error and dev_consume_skb_irq() means the SKB is consumed in normal. In this case, dev_kfree_skb() is called in xemaclite_tx_timeout() to drop the SKB, when tx timeout, so replace it with dev_kfree_skb_irq(). Fixes: bb81b2ddfa19 ("net: add Xilinx emac lite device driver") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/xilinx/xilinx_emaclite.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index f6ea4a0ad5df..02b95afe2506 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -541,7 +541,7 @@ static void xemaclite_tx_timeout(struct net_device *dev, unsigned int txqueue) xemaclite_enable_interrupts(lp); if (lp->deferred_skb) { - dev_kfree_skb(lp->deferred_skb); + dev_kfree_skb_irq(lp->deferred_skb); lp->deferred_skb = NULL; dev->stats.tx_errors++; } From b242358a27a768f56814c4d9136d4662f5405e16 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 22:21:45 +0800 Subject: [PATCH 0342/4345] net: ethernet: dnet: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit f07fadcbee2a5e84caa67c7c445424200bffb60b ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. In this case, the lock is used to protected 'bp', so we can move dev_kfree_skb() after the spin_unlock_irqrestore(). Fixes: 4796417417a6 ("dnet: Dave DNET ethernet controller driver (updated)") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/dnet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index 48c6eb142dcc..05a0cc583f8a 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -550,11 +550,11 @@ static netdev_tx_t dnet_start_xmit(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); + spin_unlock_irqrestore(&bp->lock, flags); + /* free the buffer */ dev_kfree_skb(skb); - spin_unlock_irqrestore(&bp->lock, flags); - return NETDEV_TX_OK; } From ee3b1364af268e6ed0487165f301a69dd82000a4 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 22:21:46 +0800 Subject: [PATCH 0343/4345] hamradio: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit 3727f742915f04f6fc550b80cf406999bd4e90d0 ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. It should use dev_kfree_skb_irq() or dev_consume_skb_irq() instead. The difference between them is free reason, dev_kfree_skb_irq() means the SKB is dropped in error and dev_consume_skb_irq() means the SKB is consumed in normal. In scc_discard_buffers(), dev_kfree_skb() is called to discard the SKBs, so replace it with dev_kfree_skb_irq(). In scc_net_tx(), dev_kfree_skb() is called to drop the SKB that exceed queue length, so replace it with dev_kfree_skb_irq(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/hamradio/scc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index 36eeb80406f2..eeb6c47d8167 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -300,12 +300,12 @@ static inline void scc_discard_buffers(struct scc_channel *scc) spin_lock_irqsave(&scc->lock, flags); if (scc->tx_buff != NULL) { - dev_kfree_skb(scc->tx_buff); + dev_kfree_skb_irq(scc->tx_buff); scc->tx_buff = NULL; } while (!skb_queue_empty(&scc->tx_queue)) - dev_kfree_skb(skb_dequeue(&scc->tx_queue)); + dev_kfree_skb_irq(skb_dequeue(&scc->tx_queue)); spin_unlock_irqrestore(&scc->lock, flags); } @@ -1667,7 +1667,7 @@ static netdev_tx_t scc_net_tx(struct sk_buff *skb, struct net_device *dev) if (skb_queue_len(&scc->tx_queue) > scc->dev->tx_queue_len) { struct sk_buff *skb_del; skb_del = skb_dequeue(&scc->tx_queue); - dev_kfree_skb(skb_del); + dev_kfree_skb_irq(skb_del); } skb_queue_tail(&scc->tx_queue, skb); netif_trans_update(dev); From 8eb5f8ae51323d892fb143a19094159d3e2412c7 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 22:21:47 +0800 Subject: [PATCH 0344/4345] net: amd: lance: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit 6151d105dfce8c23edf30eed35e97f3d9b96a35c ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. It should use dev_kfree_skb_irq() or dev_consume_skb_irq() instead. The difference between them is free reason, dev_kfree_skb_irq() means the SKB is dropped in error and dev_consume_skb_irq() means the SKB is consumed in normal. In these two cases, dev_kfree_skb() is called consume the xmited SKB, so replace it with dev_consume_skb_irq(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/atarilance.c | 2 +- drivers/net/ethernet/amd/lance.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c index 961796abab35..5e8b72db8873 100644 --- a/drivers/net/ethernet/amd/atarilance.c +++ b/drivers/net/ethernet/amd/atarilance.c @@ -825,7 +825,7 @@ lance_start_xmit(struct sk_buff *skb, struct net_device *dev) lp->memcpy_f( PKTBUF_ADDR(head), (void *)skb->data, skb->len ); head->flag = TMD1_OWN_CHIP | TMD1_ENP | TMD1_STP; dev->stats.tx_bytes += skb->len; - dev_kfree_skb( skb ); + dev_consume_skb_irq(skb); lp->cur_tx++; while( lp->cur_tx >= TX_RING_SIZE && lp->dirty_tx >= TX_RING_SIZE ) { lp->cur_tx -= TX_RING_SIZE; diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index aff44241988c..9dae225b7fd5 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -997,7 +997,7 @@ static netdev_tx_t lance_start_xmit(struct sk_buff *skb, skb_copy_from_linear_data(skb, &lp->tx_bounce_buffs[entry], skb->len); lp->tx_ring[entry].base = ((u32)isa_virt_to_bus((lp->tx_bounce_buffs + entry)) & 0xffffff) | 0x83000000; - dev_kfree_skb(skb); + dev_consume_skb_irq(skb); } else { lp->tx_skbuff[entry] = skb; lp->tx_ring[entry].base = ((u32)isa_virt_to_bus(skb->data) & 0xffffff) | 0x83000000; From 03ea9ba5fd239fbb61dc5865cb52bc27c243c125 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Thu, 8 Dec 2022 10:22:24 -0600 Subject: [PATCH 0345/4345] net: amd-xgbe: Fix logic around active and passive cables [ Upstream commit 4998006c73afe44e2f639d55bd331c6c26eb039f ] SFP+ active and passive cables are copper cables with fixed SFP+ end connectors. Due to a misinterpretation of this, SFP+ active cables could end up not being recognized, causing the driver to fail to establish a connection. Introduce a new enum in SFP+ cable types, XGBE_SFP_CABLE_FIBER, that is the default cable type, and handle active and passive cables when they are specifically detected. Fixes: abf0a1c2b26a ("amd-xgbe: Add support for SFP+ modules") Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index a7166cd1179f..a9a734454973 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -189,6 +189,7 @@ enum xgbe_sfp_cable { XGBE_SFP_CABLE_UNKNOWN = 0, XGBE_SFP_CABLE_ACTIVE, XGBE_SFP_CABLE_PASSIVE, + XGBE_SFP_CABLE_FIBER, }; enum xgbe_sfp_base { @@ -1149,16 +1150,18 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata) phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data); phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data); - /* Assume ACTIVE cable unless told it is PASSIVE */ + /* Assume FIBER cable unless told otherwise */ if (sfp_base[XGBE_SFP_BASE_CABLE] & XGBE_SFP_BASE_CABLE_PASSIVE) { phy_data->sfp_cable = XGBE_SFP_CABLE_PASSIVE; phy_data->sfp_cable_len = sfp_base[XGBE_SFP_BASE_CU_CABLE_LEN]; - } else { + } else if (sfp_base[XGBE_SFP_BASE_CABLE] & XGBE_SFP_BASE_CABLE_ACTIVE) { phy_data->sfp_cable = XGBE_SFP_CABLE_ACTIVE; + } else { + phy_data->sfp_cable = XGBE_SFP_CABLE_FIBER; } /* Determine the type of SFP */ - if (phy_data->sfp_cable == XGBE_SFP_CABLE_PASSIVE && + if (phy_data->sfp_cable != XGBE_SFP_CABLE_FIBER && xgbe_phy_sfp_bit_rate(sfp_eeprom, XGBE_SFP_SPEED_10000)) phy_data->sfp_base = XGBE_SFP_BASE_10000_CR; else if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_SR) From 334c9fb892323690add0e6d53e664a67830c6fa1 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Thu, 8 Dec 2022 10:22:25 -0600 Subject: [PATCH 0346/4345] net: amd-xgbe: Check only the minimum speed for active/passive cables [ Upstream commit f8ab263d4d48e6dab752029bf562f20a2ee630ed ] There are cables that exist that can support speeds in excess of 10GbE. The driver, however, restricts the EEPROM advertised nominal bitrate to a specific range, which can prevent usage of cables that can support, for example, up to 25GbE. Rather than checking that an active or passive cable supports a specific range, only check for a minimum supported speed. Fixes: abf0a1c2b26a ("amd-xgbe: Add support for SFP+ modules") Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index a9a734454973..97e32c0490f8 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -237,10 +237,7 @@ enum xgbe_sfp_speed { #define XGBE_SFP_BASE_BR 12 #define XGBE_SFP_BASE_BR_1GBE_MIN 0x0a -#define XGBE_SFP_BASE_BR_1GBE_MAX 0x0d #define XGBE_SFP_BASE_BR_10GBE_MIN 0x64 -#define XGBE_SFP_BASE_BR_10GBE_MAX 0x68 -#define XGBE_MOLEX_SFP_BASE_BR_10GBE_MAX 0x78 #define XGBE_SFP_BASE_CU_CABLE_LEN 18 @@ -827,29 +824,22 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata) static bool xgbe_phy_sfp_bit_rate(struct xgbe_sfp_eeprom *sfp_eeprom, enum xgbe_sfp_speed sfp_speed) { - u8 *sfp_base, min, max; + u8 *sfp_base, min; sfp_base = sfp_eeprom->base; switch (sfp_speed) { case XGBE_SFP_SPEED_1000: min = XGBE_SFP_BASE_BR_1GBE_MIN; - max = XGBE_SFP_BASE_BR_1GBE_MAX; break; case XGBE_SFP_SPEED_10000: min = XGBE_SFP_BASE_BR_10GBE_MIN; - if (memcmp(&sfp_eeprom->base[XGBE_SFP_BASE_VENDOR_NAME], - XGBE_MOLEX_VENDOR, XGBE_SFP_BASE_VENDOR_NAME_LEN) == 0) - max = XGBE_MOLEX_SFP_BASE_BR_10GBE_MAX; - else - max = XGBE_SFP_BASE_BR_10GBE_MAX; break; default: return false; } - return ((sfp_base[XGBE_SFP_BASE_BR] >= min) && - (sfp_base[XGBE_SFP_BASE_BR] <= max)); + return sfp_base[XGBE_SFP_BASE_BR] >= min; } static void xgbe_phy_free_phy_device(struct xgbe_prv_data *pdata) From 39b48a92edaf66292a16106194e51a198ba1ada9 Mon Sep 17 00:00:00 2001 From: Markus Schneider-Pargmann Date: Tue, 6 Dec 2022 12:57:25 +0100 Subject: [PATCH 0347/4345] can: tcan4x5x: Remove invalid write in clear_interrupts [ Upstream commit 40c9e4f676abbe194541d88e796341c92d5a13c0 ] Register 0x824 TCAN4X5X_MCAN_INT_REG is a read-only register. Any writes to this register do not have any effect. Remove this write. The m_can driver aldready clears the interrupts in m_can_isr() by writing to M_CAN_IR which is translated to register 0x1050 which is a writable version of this register. Fixes: 5443c226ba91 ("can: tcan4x5x: Add tcan4x5x driver to the kernel") Signed-off-by: Markus Schneider-Pargmann Link: https://lore.kernel.org/all/20221206115728.1056014-9-msp@baylibre.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/m_can/tcan4x5x.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c index f169d9090e52..f903f78af087 100644 --- a/drivers/net/can/m_can/tcan4x5x.c +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -294,11 +294,6 @@ static int tcan4x5x_clear_interrupts(struct m_can_classdev *cdev) if (ret) return ret; - ret = tcan4x5x_write_tcan_reg(cdev, TCAN4X5X_MCAN_INT_REG, - TCAN4X5X_ENABLE_MCAN_INT); - if (ret) - return ret; - ret = tcan4x5x_write_tcan_reg(cdev, TCAN4X5X_INT_FLAGS, TCAN4X5X_CLEAR_ALL_INT); if (ret) From 4df544f592adbf6f65be0303af5d28da29ed78ee Mon Sep 17 00:00:00 2001 From: Jerry Ray Date: Fri, 9 Dec 2022 09:35:02 -0600 Subject: [PATCH 0348/4345] net: lan9303: Fix read error execution path [ Upstream commit 8964916d206071b058c6351f88b1966bd58cbde0 ] This patch fixes an issue where a read failure of a port statistic counter will return unknown results. While it is highly unlikely the read will ever fail, it is much cleaner to return a zero for the stat count. Fixes: a1292595e006 ("net: dsa: add new DSA switch driver for the SMSC-LAN9303") Signed-off-by: Jerry Ray Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20221209153502.7429-1-jerry.ray@microchip.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/lan9303-core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index c79bb8cf962c..deeed50a42c0 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1002,9 +1002,11 @@ static void lan9303_get_ethtool_stats(struct dsa_switch *ds, int port, ret = lan9303_read_switch_port( chip, port, lan9303_mib[u].offset, ®); - if (ret) + if (ret) { dev_warn(chip->dev, "Reading status port %d reg %u failed\n", port, lan9303_mib[u].offset); + reg = 0; + } data[u] = reg; } } From 13286ad1c7c49c606fdcba4cf66f953a1a16c1ca Mon Sep 17 00:00:00 2001 From: Eric Pilmore Date: Thu, 8 Dec 2022 16:06:59 -0800 Subject: [PATCH 0349/4345] ntb_netdev: Use dev_kfree_skb_any() in interrupt context [ Upstream commit 5f7d78b2b12a9d561f48fa00bab29b40f4616dad ] TX/RX callback handlers (ntb_netdev_tx_handler(), ntb_netdev_rx_handler()) can be called in interrupt context via the DMA framework when the respective DMA operations have completed. As such, any calls by these routines to free skb's, should use the interrupt context safe dev_kfree_skb_any() function. Previously, these callback handlers would call the interrupt unsafe version of dev_kfree_skb(). This has not presented an issue on Intel IOAT DMA engines as that driver utilizes tasklets rather than a hard interrupt handler, like the AMD PTDMA DMA driver. On AMD systems, a kernel WARNING message is encountered, which is being issued from skb_release_head_state() due to in_hardirq() being true. Besides the user visible WARNING from the kernel, the other symptom of this bug was that TCP/IP performance across the ntb_netdev interface was very poor, i.e. approximately an order of magnitude below what was expected. With the repair to use dev_kfree_skb_any(), kernel WARNINGs from skb_release_head_state() ceased and TCP/IP performance, as measured by iperf, was on par with expected results, approximately 20 Gb/s on AMD Milan based server. Note that this performance is comparable with Intel based servers. Fixes: 765ccc7bc3d91 ("ntb_netdev: correct skb leak") Fixes: 548c237c0a997 ("net: Add support for NTB virtual ethernet device") Signed-off-by: Eric Pilmore Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20221209000659.8318-1-epilmore@gigaio.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ntb_netdev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 1b7d588ff3c5..b701ee83e64a 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -137,7 +137,7 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, enqueue_again: rc = ntb_transport_rx_enqueue(qp, skb, skb->data, ndev->mtu + ETH_HLEN); if (rc) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); ndev->stats.rx_errors++; ndev->stats.rx_fifo_errors++; } @@ -192,7 +192,7 @@ static void ntb_netdev_tx_handler(struct ntb_transport_qp *qp, void *qp_data, ndev->stats.tx_aborted_errors++; } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); if (ntb_transport_tx_free_entry(dev->qp) >= tx_start) { /* Make sure anybody stopping the queue after this sees the new From 214346a517241af1272171126b1f79cf16dcaf99 Mon Sep 17 00:00:00 2001 From: Firo Yang Date: Fri, 9 Dec 2022 13:48:54 +0800 Subject: [PATCH 0350/4345] sctp: sysctl: make extra pointers netns aware [ Upstream commit da05cecc4939c0410d56c29e252998b192756318 ] Recently, a customer reported that from their container whose net namespace is different to the host's init_net, they can't set the container's net.sctp.rto_max to any value smaller than init_net.sctp.rto_min. For instance, Host: sudo sysctl net.sctp.rto_min net.sctp.rto_min = 1000 Container: echo 100 > /mnt/proc-net/sctp/rto_min echo 400 > /mnt/proc-net/sctp/rto_max echo: write error: Invalid argument This is caused by the check made from this'commit 4f3fdf3bc59c ("sctp: add check rto_min and rto_max in sysctl")' When validating the input value, it's always referring the boundary value set for the init_net namespace. Having container's rto_max smaller than host's init_net.sctp.rto_min does make sense. Consider that the rto between two containers on the same host is very likely smaller than it for two hosts. So to fix this problem, as suggested by Marcelo, this patch makes the extra pointers of rto_min, rto_max, pf_retrans, and ps_retrans point to the corresponding variables from the newly created net namespace while the new net namespace is being registered in sctp_sysctl_net_register. Fixes: 4f3fdf3bc59c ("sctp: add check rto_min and rto_max in sysctl") Reviewed-by: Marcelo Ricardo Leitner Reviewed-by: Jakub Kicinski Acked-by: Marcelo Ricardo Leitner Signed-off-by: Firo Yang Link: https://lore.kernel.org/r/20221209054854.23889-1-firo.yang@suse.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sctp/sysctl.c | 73 ++++++++++++++++++++++++++++------------------- 1 file changed, 44 insertions(+), 29 deletions(-) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index c16c80963e55..e4af050aec1b 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -79,17 +79,18 @@ static struct ctl_table sctp_table[] = { { /* sentinel */ } }; +/* The following index defines are used in sctp_sysctl_net_register(). + * If you add new items to the sctp_net_table, please ensure that + * the index values of these defines hold the same meaning indicated by + * their macro names when they appear in sctp_net_table. + */ +#define SCTP_RTO_MIN_IDX 0 +#define SCTP_RTO_MAX_IDX 1 +#define SCTP_PF_RETRANS_IDX 2 +#define SCTP_PS_RETRANS_IDX 3 + static struct ctl_table sctp_net_table[] = { - { - .procname = "rto_initial", - .data = &init_net.sctp.rto_initial, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - .extra2 = &timer_max - }, - { + [SCTP_RTO_MIN_IDX] = { .procname = "rto_min", .data = &init_net.sctp.rto_min, .maxlen = sizeof(unsigned int), @@ -98,7 +99,7 @@ static struct ctl_table sctp_net_table[] = { .extra1 = SYSCTL_ONE, .extra2 = &init_net.sctp.rto_max }, - { + [SCTP_RTO_MAX_IDX] = { .procname = "rto_max", .data = &init_net.sctp.rto_max, .maxlen = sizeof(unsigned int), @@ -107,6 +108,33 @@ static struct ctl_table sctp_net_table[] = { .extra1 = &init_net.sctp.rto_min, .extra2 = &timer_max }, + [SCTP_PF_RETRANS_IDX] = { + .procname = "pf_retrans", + .data = &init_net.sctp.pf_retrans, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &init_net.sctp.ps_retrans, + }, + [SCTP_PS_RETRANS_IDX] = { + .procname = "ps_retrans", + .data = &init_net.sctp.ps_retrans, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &init_net.sctp.pf_retrans, + .extra2 = &ps_retrans_max, + }, + { + .procname = "rto_initial", + .data = &init_net.sctp.rto_initial, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = &timer_max + }, { .procname = "rto_alpha_exp_divisor", .data = &init_net.sctp.rto_alpha, @@ -202,24 +230,6 @@ static struct ctl_table sctp_net_table[] = { .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, - { - .procname = "pf_retrans", - .data = &init_net.sctp.pf_retrans, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = &init_net.sctp.ps_retrans, - }, - { - .procname = "ps_retrans", - .data = &init_net.sctp.ps_retrans, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &init_net.sctp.pf_retrans, - .extra2 = &ps_retrans_max, - }, { .procname = "sndbuf_policy", .data = &init_net.sctp.sndbuf_policy, @@ -489,6 +499,11 @@ int sctp_sysctl_net_register(struct net *net) for (i = 0; table[i].data; i++) table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + table[SCTP_RTO_MIN_IDX].extra2 = &net->sctp.rto_max; + table[SCTP_RTO_MAX_IDX].extra1 = &net->sctp.rto_min; + table[SCTP_PF_RETRANS_IDX].extra2 = &net->sctp.ps_retrans; + table[SCTP_PS_RETRANS_IDX].extra1 = &net->sctp.pf_retrans; + net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table); if (net->sctp.sysctl_header == NULL) { kfree(table); From f7dc27702b598452141868ec108f40e1151f5171 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 6 Dec 2022 20:59:10 +0800 Subject: [PATCH 0351/4345] Bluetooth: btusb: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit b15a6bd3c80c77faec8317319b97f976b1a08332 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Fixes: 803b58367ffb ("Bluetooth: btusb: Implement driver internal packet reassembly") Signed-off-by: Yang Yingliang Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/btusb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 54001ad5de9f..3d905fda9b29 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -661,13 +661,13 @@ static inline void btusb_free_frags(struct btusb_data *data) spin_lock_irqsave(&data->rxlock, flags); - kfree_skb(data->evt_skb); + dev_kfree_skb_irq(data->evt_skb); data->evt_skb = NULL; - kfree_skb(data->acl_skb); + dev_kfree_skb_irq(data->acl_skb); data->acl_skb = NULL; - kfree_skb(data->sco_skb); + dev_kfree_skb_irq(data->sco_skb); data->sco_skb = NULL; spin_unlock_irqrestore(&data->rxlock, flags); From 0169acb41bc8634c50d3428edb2cae7ca304f673 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 10:18:30 +0800 Subject: [PATCH 0352/4345] Bluetooth: hci_qca: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit df4cfc91208e0a98f078223793f5871b1a82cc54 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Fixes: 0ff252c1976d ("Bluetooth: hciuart: Add support QCA chipset for UART") Signed-off-by: Yang Yingliang Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/hci_qca.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index eea18aed17f8..60b0e13bb9fc 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -905,7 +905,7 @@ static int qca_enqueue(struct hci_uart *hu, struct sk_buff *skb) default: BT_ERR("Illegal tx state: %d (losing packet)", qca->tx_ibs_state); - kfree_skb(skb); + dev_kfree_skb_irq(skb); break; } From 5991402fe091c33ee0702d92026a3520ee6440fc Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 10:18:31 +0800 Subject: [PATCH 0353/4345] Bluetooth: hci_ll: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 8f458f783dfbb19c1f1cb58ed06eeb701f52091b ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Fixes: 166d2f6a4332 ("[Bluetooth] Add UART driver for Texas Instruments' BRF63xx chips") Signed-off-by: Yang Yingliang Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/hci_ll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index 8bfe024d1fcd..7495ca34c9e7 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -345,7 +345,7 @@ static int ll_enqueue(struct hci_uart *hu, struct sk_buff *skb) default: BT_ERR("illegal hcill state: %ld (losing packet)", ll->hcill_state); - kfree_skb(skb); + dev_kfree_skb_irq(skb); break; } From 33af776a8d988ddd0942923ef09ff7fb8ecaf279 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 10:18:32 +0800 Subject: [PATCH 0354/4345] Bluetooth: hci_h5: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 383630cc6758d619874c2e8bb2f68a61f3f9ef6e ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Fixes: 43eb12d78960 ("Bluetooth: Fix/implement Three-wire reliable packet sending") Signed-off-by: Yang Yingliang Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/hci_h5.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index 996729e78105..7f70a677b92b 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -299,7 +299,7 @@ static void h5_pkt_cull(struct h5 *h5) break; __skb_unlink(skb, &h5->unack); - kfree_skb(skb); + dev_kfree_skb_irq(skb); } if (skb_queue_empty(&h5->unack)) From 82256faaeb3abe4f9cf27e668f3d9f9ff20491d3 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 10:18:33 +0800 Subject: [PATCH 0355/4345] Bluetooth: hci_bcsp: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 7b503e339c1a80bf0051ec2d19c3bc777014ac61 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/hci_bcsp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index cf4a56095817..8055f63603f4 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -378,7 +378,7 @@ static void bcsp_pkt_cull(struct bcsp_struct *bcsp) i++; __skb_unlink(skb, &bcsp->unack); - kfree_skb(skb); + dev_kfree_skb_irq(skb); } if (skb_queue_empty(&bcsp->unack)) From 4002180e0761a2bfa7fd6d44ce858713bbf93080 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 10:18:34 +0800 Subject: [PATCH 0356/4345] Bluetooth: hci_core: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 39c1eb6fcbae8ce9bb71b2ac5cb609355a2b181b ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Fixes: 9238f36a5a50 ("Bluetooth: Add request cmd_complete and cmd_status functions") Signed-off-by: Yang Yingliang Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/hci_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index f8aab38ab595..2af1477a05ca 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -4910,7 +4910,7 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; else *req_complete = bt_cb(skb)->hci.req_complete; - kfree_skb(skb); + dev_kfree_skb_irq(skb); } spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); } From 815b961c71af3136c686467fef47b91456046761 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 10:18:35 +0800 Subject: [PATCH 0357/4345] Bluetooth: RFCOMM: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 0ba18967d4544955b2eff2fbc4f2a8750c4df90a ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Fixes: 81be03e026dc ("Bluetooth: RFCOMM: Replace use of memcpy_from_msg with bt_skb_sendmmsg") Signed-off-by: Yang Yingliang Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/rfcomm/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 7324764384b6..8d6fce9005bd 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -590,7 +590,7 @@ int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb) ret = rfcomm_dlc_send_frag(d, frag); if (ret < 0) { - kfree_skb(frag); + dev_kfree_skb_irq(frag); goto unlock; } From f694e627c603cf46481a3f53febb8a4eb33f4917 Mon Sep 17 00:00:00 2001 From: Piergiorgio Beruto Date: Sat, 10 Dec 2022 23:37:22 +0100 Subject: [PATCH 0358/4345] stmmac: fix potential division by 0 [ Upstream commit ede5a389852d3640a28e7187fb32b7f204380901 ] When the MAC is connected to a 10 Mb/s PHY and the PTP clock is derived from the MAC reference clock (default), the clk_ptp_rate becomes too small and the calculated sub second increment becomes 0 when computed by the stmmac_config_sub_second_increment() function within stmmac_init_tstamp_counter(). Therefore, the subsequent div_u64 in stmmac_init_tstamp_counter() operation triggers a divide by 0 exception as shown below. [ 95.062067] socfpga-dwmac ff700000.ethernet eth0: Register MEM_TYPE_PAGE_POOL RxQ-0 [ 95.076440] socfpga-dwmac ff700000.ethernet eth0: PHY [stmmac-0:08] driver [NCN26000] (irq=49) [ 95.095964] dwmac1000: Master AXI performs any burst length [ 95.101588] socfpga-dwmac ff700000.ethernet eth0: No Safety Features support found [ 95.109428] Division by zero in kernel. [ 95.113447] CPU: 0 PID: 239 Comm: ifconfig Not tainted 6.1.0-rc7-centurion3-1.0.3.0-01574-gb624218205b7-dirty #77 [ 95.123686] Hardware name: Altera SOCFPGA [ 95.127695] unwind_backtrace from show_stack+0x10/0x14 [ 95.132938] show_stack from dump_stack_lvl+0x40/0x4c [ 95.137992] dump_stack_lvl from Ldiv0+0x8/0x10 [ 95.142527] Ldiv0 from __aeabi_uidivmod+0x8/0x18 [ 95.147232] __aeabi_uidivmod from div_u64_rem+0x1c/0x40 [ 95.152552] div_u64_rem from stmmac_init_tstamp_counter+0xd0/0x164 [ 95.158826] stmmac_init_tstamp_counter from stmmac_hw_setup+0x430/0xf00 [ 95.165533] stmmac_hw_setup from __stmmac_open+0x214/0x2d4 [ 95.171117] __stmmac_open from stmmac_open+0x30/0x44 [ 95.176182] stmmac_open from __dev_open+0x11c/0x134 [ 95.181172] __dev_open from __dev_change_flags+0x168/0x17c [ 95.186750] __dev_change_flags from dev_change_flags+0x14/0x50 [ 95.192662] dev_change_flags from devinet_ioctl+0x2b4/0x604 [ 95.198321] devinet_ioctl from inet_ioctl+0x1ec/0x214 [ 95.203462] inet_ioctl from sock_ioctl+0x14c/0x3c4 [ 95.208354] sock_ioctl from vfs_ioctl+0x20/0x38 [ 95.212984] vfs_ioctl from sys_ioctl+0x250/0x844 [ 95.217691] sys_ioctl from ret_fast_syscall+0x0/0x4c [ 95.222743] Exception stack(0xd0ee1fa8 to 0xd0ee1ff0) [ 95.227790] 1fa0: 00574c4f be9aeca4 00000003 00008914 be9aeca4 be9aec50 [ 95.235945] 1fc0: 00574c4f be9aeca4 0059f078 00000036 be9aee8c be9aef7a 00000015 00000000 [ 95.244096] 1fe0: 005a01f0 be9aec38 004d7484 b6e67d74 Signed-off-by: Piergiorgio Beruto Fixes: 91a2559c1dc5 ("net: stmmac: Fix sub-second increment") Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/de4c64ccac9084952c56a06a8171d738604c4770.1670678513.git.piergiorgio.beruto@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 53efcc9c40e2..0ad5ce874557 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -44,7 +44,8 @@ static void config_sub_second_increment(void __iomem *ioaddr, if (!(value & PTP_TCR_TSCTRLSSR)) data = (data * 1000) / 465; - data &= PTP_SSIR_SSINC_MASK; + if (data > PTP_SSIR_SSINC_MAX) + data = PTP_SSIR_SSINC_MAX; reg_value = data; if (gmac4) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h index 7abb1d47e7da..60e6b085e2f6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h @@ -61,7 +61,7 @@ #define PTP_TCR_TSENMACADDR BIT(18) /* SSIR defines */ -#define PTP_SSIR_SSINC_MASK 0xff +#define PTP_SSIR_SSINC_MAX 0xff #define GMAC4_PTP_SSIR_SSINC_SHIFT 16 #endif /* __STMMAC_PTP_H__ */ From 935d86b29093e75b6c547d90b3979c2c2d23f1c4 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 23 Aug 2022 09:15:03 +0800 Subject: [PATCH 0359/4345] apparmor: fix a memleak in multi_transaction_new() [ Upstream commit c73275cf6834787ca090317f1d20dbfa3b7f05aa ] In multi_transaction_new(), the variable t is not freed or passed out on the failure of copy_from_user(t->data, buf, size), which could lead to a memleak. Fix this bug by adding a put_multi_transaction(t) in the error path. Fixes: 1dea3b41e84c5 ("apparmor: speed up transactional queries") Signed-off-by: Gaosheng Cui Signed-off-by: John Johansen Signed-off-by: Sasha Levin --- security/apparmor/apparmorfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index c173f6fd7aee..49d97b331abc 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -867,8 +867,10 @@ static struct multi_transaction *multi_transaction_new(struct file *file, if (!t) return ERR_PTR(-ENOMEM); kref_init(&t->count); - if (copy_from_user(t->data, buf, size)) + if (copy_from_user(t->data, buf, size)) { + put_multi_transaction(t); return ERR_PTR(-EFAULT); + } return t; } From 78629ca972ac3d98e105a3b89581ab618bd959d3 Mon Sep 17 00:00:00 2001 From: John Johansen Date: Tue, 6 Sep 2022 03:39:55 -0700 Subject: [PATCH 0360/4345] apparmor: fix lockdep warning when removing a namespace [ Upstream commit 9c4557efc558a68e4cd973490fd936d6e3414db8 ] Fix the following lockdep warning [ 1119.158984] ============================================ [ 1119.158988] WARNING: possible recursive locking detected [ 1119.158996] 6.0.0-rc1+ #257 Tainted: G E N [ 1119.158999] -------------------------------------------- [ 1119.159001] bash/80100 is trying to acquire lock: [ 1119.159007] ffff88803e79b4a0 (&ns->lock/1){+.+.}-{4:4}, at: destroy_ns.part.0+0x43/0x140 [ 1119.159028] but task is already holding lock: [ 1119.159030] ffff8881009764a0 (&ns->lock/1){+.+.}-{4:4}, at: aa_remove_profiles+0x3f0/0x640 [ 1119.159040] other info that might help us debug this: [ 1119.159042] Possible unsafe locking scenario: [ 1119.159043] CPU0 [ 1119.159045] ---- [ 1119.159047] lock(&ns->lock/1); [ 1119.159051] lock(&ns->lock/1); [ 1119.159055] *** DEADLOCK *** Which is caused by an incorrect lockdep nesting notation Fixes: feb3c766a3ab ("apparmor: fix possible recursive lock warning in __aa_create_ns") Signed-off-by: John Johansen Signed-off-by: Sasha Levin --- security/apparmor/policy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 4c010c9a6af1..fcf22577f606 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -1125,7 +1125,7 @@ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj, if (!name) { /* remove namespace - can only happen if fqname[0] == ':' */ - mutex_lock_nested(&ns->parent->lock, ns->level); + mutex_lock_nested(&ns->parent->lock, ns->parent->level); __aa_bump_ns_revision(ns); __aa_remove_ns(ns); mutex_unlock(&ns->parent->lock); From bf4d7c66a18abb726455cd41502af0403d6d4378 Mon Sep 17 00:00:00 2001 From: John Johansen Date: Fri, 6 May 2022 18:57:12 -0700 Subject: [PATCH 0361/4345] apparmor: Fix abi check to include v8 abi [ Upstream commit 1b5a6198f5a9d0aa5497da0dc4bcd4fc166ee516 ] The v8 abi is supported by the kernel but the userspace supported version check does not allow for it. This was missed when v8 was added due to a bug in the userspace compiler which was setting an older abi version for v8 encoding (which is forward compatible except on the network encoding). However it is possible to detect the network encoding by checking the policydb network support which the code does. The end result was that missing the abi flag worked until userspace was fixed and began correctly checking for the v8 abi version. Fixes: 56974a6fcfef ("apparmor: add base infastructure for socket mediation") Signed-off-by: John Johansen Signed-off-by: Sasha Levin --- security/apparmor/policy_unpack.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 556ef65ab6ee..519656e68582 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -964,7 +964,7 @@ static int verify_header(struct aa_ext *e, int required, const char **ns) * if not specified use previous version * Mask off everything that is not kernel abi version */ - if (VERSION_LT(e->version, v5) || VERSION_GT(e->version, v7)) { + if (VERSION_LT(e->version, v5) || VERSION_GT(e->version, v8)) { audit_iface(NULL, NULL, NULL, "unsupported interface version", e, error); return error; From ee3cffc38efe1609723888dfb3c8640f84226d31 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Tue, 27 Sep 2022 08:55:55 +0000 Subject: [PATCH 0362/4345] crypto: sun8i-ss - use dma_addr instead u32 [ Upstream commit 839b8ae2fc10f205317bcc32c9de18456756e1f5 ] The DMA address need to be stored in a dma_addr_t Fixes: 359e893e8af4 ("crypto: sun8i-ss - rework handling of IV") Reported-by: Dan Carpenter Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c index d0954993e2e3..49c7a8b464dd 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c @@ -105,7 +105,7 @@ static int sun8i_ss_setup_ivs(struct skcipher_request *areq) unsigned int ivsize = crypto_skcipher_ivsize(tfm); struct sun8i_ss_flow *sf = &ss->flows[rctx->flow]; int i = 0; - u32 a; + dma_addr_t a; int err; rctx->ivlen = ivsize; From 3bebfa5f93456656f0525022debdc729ec457fbd Mon Sep 17 00:00:00 2001 From: Natalia Petrova Date: Wed, 28 Sep 2022 13:25:05 +0300 Subject: [PATCH 0363/4345] crypto: nitrox - avoid double free on error path in nitrox_sriov_init() [ Upstream commit 094528b6a5a755b1195a01e10b13597d67d1a0e6 ] If alloc_workqueue() fails in nitrox_mbox_init() it deallocates ndev->iov.vfdev and returns error code, but then nitrox_sriov_init() calls nitrox_sriov_cleanup() where ndev->iov.vfdev is deallocated again. Fix this by nulling ndev->iov.vfdev after the first deallocation. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 9e5de3e06e54 ("crypto: cavium/nitrox - Add mailbox...") Signed-off-by: Natalia Petrova Signed-off-by: Alexey Khoroshilov Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/cavium/nitrox/nitrox_mbx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/crypto/cavium/nitrox/nitrox_mbx.c b/drivers/crypto/cavium/nitrox/nitrox_mbx.c index b51b0449b478..a131dbbbcb86 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_mbx.c +++ b/drivers/crypto/cavium/nitrox/nitrox_mbx.c @@ -190,6 +190,7 @@ int nitrox_mbox_init(struct nitrox_device *ndev) ndev->iov.pf2vf_wq = alloc_workqueue("nitrox_pf2vf", 0, 0); if (!ndev->iov.pf2vf_wq) { kfree(ndev->iov.vfdev); + ndev->iov.vfdev = NULL; return -ENOMEM; } /* enable pf2vf mailbox interrupts */ From f4c917a4b0304d7565ff1a13c716aa2ebac53022 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 18 Oct 2022 13:29:49 -0700 Subject: [PATCH 0364/4345] scsi: core: Fix a race between scsi_done() and scsi_timeout() [ Upstream commit 978b7922d3dca672b41bb4b8ce6c06ab77112741 ] If there is a race between scsi_done() and scsi_timeout() and if scsi_timeout() loses the race, scsi_timeout() should not reset the request timer. Hence change the return value for this case from BLK_EH_RESET_TIMER into BLK_EH_DONE. Although the block layer holds a reference on a request (req->ref) while calling a timeout handler, restarting the timer (blk_add_timer()) while a request is being completed is racy. Reviewed-by: Mike Christie Cc: Keith Busch Cc: Christoph Hellwig Cc: Ming Lei Cc: John Garry Cc: Hannes Reinecke Reported-by: Adrian Hunter Fixes: 15f73f5b3e59 ("blk-mq: move failure injection out of blk_mq_complete_request") Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20221018202958.1902564-2-bvanassche@acm.org Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_error.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index f11f51e2465f..0c4bc42b55c2 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -306,19 +306,11 @@ enum blk_eh_timer_return scsi_times_out(struct request *req) if (rtn == BLK_EH_DONE) { /* - * Set the command to complete first in order to prevent a real - * completion from releasing the command while error handling - * is using it. If the command was already completed, then the - * lower level driver beat the timeout handler, and it is safe - * to return without escalating error recovery. - * - * If timeout handling lost the race to a real completion, the - * block layer may ignore that due to a fake timeout injection, - * so return RESET_TIMER to allow error handling another shot - * at this command. + * If scsi_done() has already set SCMD_STATE_COMPLETE, do not + * modify *scmd. */ if (test_and_set_bit(SCMD_STATE_COMPLETE, &scmd->state)) - return BLK_EH_RESET_TIMER; + return BLK_EH_DONE; if (scsi_abort_command(scmd) != SUCCESS) { set_host_byte(scmd, DID_TIME_OUT); scsi_eh_scmd_add(scmd); From 6962f682d0c370cd4668390ff6c81154026b5e49 Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Fri, 21 Oct 2022 08:46:04 +0800 Subject: [PATCH 0365/4345] apparmor: Use pointer to struct aa_label for lbs_cred [ Upstream commit 37923d4321b1e38170086da2c117f78f2b0f49c6 ] According to the implementations of cred_label() and set_cred_label(), we should use pointer to struct aa_label for lbs_cred instead of struct aa_task_ctx, this patch fixes it. Fixes: bbd3662a8348 ("Infrastructure management of the cred security blob") Signed-off-by: Xiu Jianfeng Signed-off-by: John Johansen Signed-off-by: Sasha Levin --- security/apparmor/lsm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index ffeaee5ed968..585edcc6814d 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1161,10 +1161,10 @@ static int apparmor_inet_conn_request(struct sock *sk, struct sk_buff *skb, #endif /* - * The cred blob is a pointer to, not an instance of, an aa_task_ctx. + * The cred blob is a pointer to, not an instance of, an aa_label. */ struct lsm_blob_sizes apparmor_blob_sizes __lsm_ro_after_init = { - .lbs_cred = sizeof(struct aa_task_ctx *), + .lbs_cred = sizeof(struct aa_label *), .lbs_file = sizeof(struct aa_file_ctx), .lbs_task = sizeof(struct aa_task_ctx), }; From 9784b01eb46c6ca1342a50d0f76cb4c664fff3f4 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Mon, 26 Sep 2022 16:49:23 +0530 Subject: [PATCH 0366/4345] PCI: dwc: Fix n_fts[] array overrun [ Upstream commit 66110361281b2f7da0c8bd51eaf1f152f4236035 ] commit aeaa0bfe89654 ("PCI: dwc: Move N_FTS setup to common setup") incorrectly uses pci->link_gen in deriving the index to the n_fts[] array also introducing the issue of accessing beyond the boundaries of array for greater than Gen-2 speeds. This change fixes that issue. Link: https://lore.kernel.org/r/20220926111923.22487-1-vidyas@nvidia.com Fixes: aeaa0bfe8965 ("PCI: dwc: Move N_FTS setup to common setup") Signed-off-by: Vidya Sagar Signed-off-by: Lorenzo Pieralisi Reviewed-by: Rob Herring Acked-by: Jingoo Han Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pcie-designware.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index 2b74ff88c5c5..28945351da14 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -589,7 +589,7 @@ void dw_pcie_setup(struct dw_pcie *pci) if (pci->n_fts[1]) { val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); val &= ~PORT_LOGIC_N_FTS_MASK; - val |= pci->n_fts[pci->link_gen - 1]; + val |= pci->n_fts[1]; dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); } From 16db9aaa41510fdee765107a8589a31e0c905f33 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 25 Oct 2022 10:37:13 +0300 Subject: [PATCH 0367/4345] RDMA/core: Fix order of nldev_exit call [ Upstream commit 4508d32ccced24c972bc4592104513e1ff8439b5 ] Create symmetrical exit flow by calling to nldev_exit() after call to rdma_nl_unregister(RDMA_NL_LS). Fixes: 6c80b41abe22 ("RDMA/netlink: Add nldev initialization flows") Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/64e676774a53a406f4cde265d5a4cfd6b8e97df9.1666683334.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index d91892ffe243..5b7abcf102fe 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2793,8 +2793,8 @@ err: static void __exit ib_core_cleanup(void) { roce_gid_mgmt_cleanup(); - nldev_exit(); rdma_nl_unregister(RDMA_NL_LS); + nldev_exit(); unregister_pernet_device(&rdma_dev_net_ops); unregister_blocking_lsm_notifier(&ibdev_lsm_nb); ib_sa_cleanup(); From c42d8120bf4728561101142a1568e6660f416cae Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Thu, 25 Aug 2022 18:01:01 +0900 Subject: [PATCH 0368/4345] PCI: pci-epf-test: Register notifier if only core_init_notifier is enabled [ Upstream commit 6acd25cc98ce0c9ee4fefdaf44fc8bca534b26e5 ] The pci_epf_test_notifier function should be installed also if only core_init_notifier is enabled. Fix the current logic. Link: https://lore.kernel.org/r/20220825090101.20474-1-hayashi.kunihiko@socionext.com Fixes: 5e50ee27d4a5 ("PCI: pci-epf-test: Add support to defer core initialization") Signed-off-by: Kunihiko Hayashi Signed-off-by: Lorenzo Pieralisi Acked-by: Om Prakash Singh Acked-by: Kishon Vijay Abraham I Signed-off-by: Sasha Levin --- drivers/pci/endpoint/functions/pci-epf-test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index ddfeca9016a0..ef52f5097eb3 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -870,7 +870,7 @@ static int pci_epf_test_bind(struct pci_epf *epf) if (ret) epf_test->dma_supported = false; - if (linkup_notifier) { + if (linkup_notifier || core_init_notifier) { epf->nb.notifier_call = pci_epf_test_notifier; pci_epc_register_notifier(epc, &epf->nb); } else { From f1acf7e69355751bc09a70d9e5fefe3b4d1e02d2 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Tue, 18 Oct 2022 10:45:32 +0800 Subject: [PATCH 0369/4345] f2fs: Fix the race condition of resize flag between resizefs [ Upstream commit 28fc4e9077ce59ab28c89c20dc6be5154473218f ] Because the set/clear SBI_IS_RESIZEFS flag not between any locks, In the following case: thread1 thread2 ->ioctl(resizefs) ->set RESIZEFS flag ->ioctl(resizefs) ... ->set RESIZEFS flag ->clear RESIZEFS flag ->resizefs stream # No RESIZEFS flag in the stream Also before freeze_super, the resizefs not started, we should not set the SBI_IS_RESIZEFS flag. So move the set/clear SBI_IS_RESIZEFS flag between the cp_mutex and gc_lock. Fixes: b4b10061ef98 ("f2fs: refactor resize_fs to avoid meta updates in progress") Signed-off-by: Zhang Xiaoxu Signed-off-by: Zhang Qilong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/gc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 3baa62ef6e3a..5ac0b605335f 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -2035,8 +2035,6 @@ out_unlock: if (err) return err; - set_sbi_flag(sbi, SBI_IS_RESIZEFS); - freeze_super(sbi->sb); down_write(&sbi->gc_lock); mutex_lock(&sbi->cp_mutex); @@ -2052,6 +2050,7 @@ out_unlock: if (err) goto out_err; + set_sbi_flag(sbi, SBI_IS_RESIZEFS); err = free_segment_range(sbi, secs, false); if (err) goto recover_out; @@ -2075,6 +2074,7 @@ out_unlock: f2fs_commit_super(sbi, false); } recover_out: + clear_sbi_flag(sbi, SBI_IS_RESIZEFS); if (err) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_err(sbi, "resize_fs failed, should run fsck to repair!"); @@ -2087,6 +2087,5 @@ out_err: mutex_unlock(&sbi->cp_mutex); up_write(&sbi->gc_lock); thaw_super(sbi->sb); - clear_sbi_flag(sbi, SBI_IS_RESIZEFS); return err; } From a13c0ff862afcd659868599870eba00d680badce Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Tue, 27 Sep 2022 07:54:41 +0000 Subject: [PATCH 0370/4345] crypto: rockchip - do not do custom power management [ Upstream commit c50ef1411c8cbad0c7db100c477126076b6e3348 ] The clock enable/disable at tfm init/exit is fragile, if 2 tfm are init in the same time and one is removed just after, it will leave the hardware uncloked even if a user remains. Instead simply enable clocks at probe time. We will do PM later. Fixes: ce0183cb6464b ("crypto: rockchip - switch to skcipher API") Reviewed-by: John Keeping Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/rockchip/rk3288_crypto.c | 4 ++-- drivers/crypto/rockchip/rk3288_crypto.h | 2 -- drivers/crypto/rockchip/rk3288_crypto_ahash.c | 3 +-- drivers/crypto/rockchip/rk3288_crypto_skcipher.c | 5 +++-- 4 files changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/crypto/rockchip/rk3288_crypto.c b/drivers/crypto/rockchip/rk3288_crypto.c index 35d73061d156..5f8444b9633a 100644 --- a/drivers/crypto/rockchip/rk3288_crypto.c +++ b/drivers/crypto/rockchip/rk3288_crypto.c @@ -395,8 +395,7 @@ static int rk_crypto_probe(struct platform_device *pdev) rk_crypto_done_task_cb, (unsigned long)crypto_info); crypto_init_queue(&crypto_info->queue, 50); - crypto_info->enable_clk = rk_crypto_enable_clk; - crypto_info->disable_clk = rk_crypto_disable_clk; + rk_crypto_enable_clk(crypto_info); crypto_info->load_data = rk_load_data; crypto_info->unload_data = rk_unload_data; crypto_info->enqueue = rk_crypto_enqueue; @@ -423,6 +422,7 @@ static int rk_crypto_remove(struct platform_device *pdev) struct rk_crypto_info *crypto_tmp = platform_get_drvdata(pdev); rk_crypto_unregister(); + rk_crypto_disable_clk(crypto_tmp); tasklet_kill(&crypto_tmp->done_task); tasklet_kill(&crypto_tmp->queue_task); return 0; diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h index 3db595570c9c..39ffcd630760 100644 --- a/drivers/crypto/rockchip/rk3288_crypto.h +++ b/drivers/crypto/rockchip/rk3288_crypto.h @@ -219,8 +219,6 @@ struct rk_crypto_info { int (*start)(struct rk_crypto_info *dev); int (*update)(struct rk_crypto_info *dev); void (*complete)(struct crypto_async_request *base, int err); - int (*enable_clk)(struct rk_crypto_info *dev); - void (*disable_clk)(struct rk_crypto_info *dev); int (*load_data)(struct rk_crypto_info *dev, struct scatterlist *sg_src, struct scatterlist *sg_dst); diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index 81befe7febaa..9583310a69d5 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -301,7 +301,7 @@ static int rk_cra_hash_init(struct crypto_tfm *tfm) sizeof(struct rk_ahash_rctx) + crypto_ahash_reqsize(tctx->fallback_tfm)); - return tctx->dev->enable_clk(tctx->dev); + return 0; } static void rk_cra_hash_exit(struct crypto_tfm *tfm) @@ -309,7 +309,6 @@ static void rk_cra_hash_exit(struct crypto_tfm *tfm) struct rk_ahash_ctx *tctx = crypto_tfm_ctx(tfm); free_page((unsigned long)tctx->dev->addr_vir); - return tctx->dev->disable_clk(tctx->dev); } struct rk_crypto_tmp rk_ahash_sha1 = { diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c index 5bbf0d2722e1..8c44a19eab75 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c +++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c @@ -388,8 +388,10 @@ static int rk_ablk_init_tfm(struct crypto_skcipher *tfm) ctx->dev->update = rk_ablk_rx; ctx->dev->complete = rk_crypto_complete; ctx->dev->addr_vir = (char *)__get_free_page(GFP_KERNEL); + if (!ctx->dev->addr_vir) + return -ENOMEM; - return ctx->dev->addr_vir ? ctx->dev->enable_clk(ctx->dev) : -ENOMEM; + return 0; } static void rk_ablk_exit_tfm(struct crypto_skcipher *tfm) @@ -397,7 +399,6 @@ static void rk_ablk_exit_tfm(struct crypto_skcipher *tfm) struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); free_page((unsigned long)ctx->dev->addr_vir); - ctx->dev->disable_clk(ctx->dev); } struct rk_crypto_tmp rk_ecb_aes_alg = { From 86f1e7f46ba9a68ff8438935fb76d7ab6c9180d7 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Tue, 27 Sep 2022 07:54:43 +0000 Subject: [PATCH 0371/4345] crypto: rockchip - do not store mode globally [ Upstream commit 87e356c4966444866186f68f05832fdcc0f351a3 ] Storing the mode globally does not work if 2 requests are handled in the same time. We should store it in a request context. Fixes: ce0183cb6464b ("crypto: rockchip - switch to skcipher API") Reviewed-by: John Keeping Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/rockchip/rk3288_crypto.h | 5 +- .../crypto/rockchip/rk3288_crypto_skcipher.c | 58 ++++++++++++------- 2 files changed, 41 insertions(+), 22 deletions(-) diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h index 39ffcd630760..65b9b58bb304 100644 --- a/drivers/crypto/rockchip/rk3288_crypto.h +++ b/drivers/crypto/rockchip/rk3288_crypto.h @@ -244,10 +244,13 @@ struct rk_ahash_rctx { struct rk_cipher_ctx { struct rk_crypto_info *dev; unsigned int keylen; - u32 mode; u8 iv[AES_BLOCK_SIZE]; }; +struct rk_cipher_rctx { + u32 mode; +}; + enum alg_type { ALG_TYPE_HASH, ALG_TYPE_CIPHER, diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c index 8c44a19eab75..bbd0bf52bf07 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c +++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c @@ -76,9 +76,10 @@ static int rk_aes_ecb_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_AES_ECB_MODE; + rctx->mode = RK_CRYPTO_AES_ECB_MODE; return rk_handle_req(dev, req); } @@ -86,9 +87,10 @@ static int rk_aes_ecb_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_AES_ECB_MODE | RK_CRYPTO_DEC; + rctx->mode = RK_CRYPTO_AES_ECB_MODE | RK_CRYPTO_DEC; return rk_handle_req(dev, req); } @@ -96,9 +98,10 @@ static int rk_aes_cbc_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_AES_CBC_MODE; + rctx->mode = RK_CRYPTO_AES_CBC_MODE; return rk_handle_req(dev, req); } @@ -106,9 +109,10 @@ static int rk_aes_cbc_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_AES_CBC_MODE | RK_CRYPTO_DEC; + rctx->mode = RK_CRYPTO_AES_CBC_MODE | RK_CRYPTO_DEC; return rk_handle_req(dev, req); } @@ -116,9 +120,10 @@ static int rk_des_ecb_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = 0; + rctx->mode = 0; return rk_handle_req(dev, req); } @@ -126,9 +131,10 @@ static int rk_des_ecb_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_DEC; + rctx->mode = RK_CRYPTO_DEC; return rk_handle_req(dev, req); } @@ -136,9 +142,10 @@ static int rk_des_cbc_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_TDES_CHAINMODE_CBC; + rctx->mode = RK_CRYPTO_TDES_CHAINMODE_CBC; return rk_handle_req(dev, req); } @@ -146,9 +153,10 @@ static int rk_des_cbc_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_TDES_CHAINMODE_CBC | RK_CRYPTO_DEC; + rctx->mode = RK_CRYPTO_TDES_CHAINMODE_CBC | RK_CRYPTO_DEC; return rk_handle_req(dev, req); } @@ -156,9 +164,10 @@ static int rk_des3_ede_ecb_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_TDES_SELECT; + rctx->mode = RK_CRYPTO_TDES_SELECT; return rk_handle_req(dev, req); } @@ -166,9 +175,10 @@ static int rk_des3_ede_ecb_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_DEC; + rctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_DEC; return rk_handle_req(dev, req); } @@ -176,9 +186,10 @@ static int rk_des3_ede_cbc_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC; + rctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC; return rk_handle_req(dev, req); } @@ -186,9 +197,10 @@ static int rk_des3_ede_cbc_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_crypto_info *dev = ctx->dev; - ctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC | + rctx->mode = RK_CRYPTO_TDES_SELECT | RK_CRYPTO_TDES_CHAINMODE_CBC | RK_CRYPTO_DEC; return rk_handle_req(dev, req); } @@ -199,6 +211,7 @@ static void rk_ablk_hw_init(struct rk_crypto_info *dev) skcipher_request_cast(dev->async_req); struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req); struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(cipher); u32 ivsize, block, conf_reg = 0; @@ -206,22 +219,22 @@ static void rk_ablk_hw_init(struct rk_crypto_info *dev) ivsize = crypto_skcipher_ivsize(cipher); if (block == DES_BLOCK_SIZE) { - ctx->mode |= RK_CRYPTO_TDES_FIFO_MODE | + rctx->mode |= RK_CRYPTO_TDES_FIFO_MODE | RK_CRYPTO_TDES_BYTESWAP_KEY | RK_CRYPTO_TDES_BYTESWAP_IV; - CRYPTO_WRITE(dev, RK_CRYPTO_TDES_CTRL, ctx->mode); + CRYPTO_WRITE(dev, RK_CRYPTO_TDES_CTRL, rctx->mode); memcpy_toio(dev->reg + RK_CRYPTO_TDES_IV_0, req->iv, ivsize); conf_reg = RK_CRYPTO_DESSEL; } else { - ctx->mode |= RK_CRYPTO_AES_FIFO_MODE | + rctx->mode |= RK_CRYPTO_AES_FIFO_MODE | RK_CRYPTO_AES_KEY_CHANGE | RK_CRYPTO_AES_BYTESWAP_KEY | RK_CRYPTO_AES_BYTESWAP_IV; if (ctx->keylen == AES_KEYSIZE_192) - ctx->mode |= RK_CRYPTO_AES_192BIT_key; + rctx->mode |= RK_CRYPTO_AES_192BIT_key; else if (ctx->keylen == AES_KEYSIZE_256) - ctx->mode |= RK_CRYPTO_AES_256BIT_key; - CRYPTO_WRITE(dev, RK_CRYPTO_AES_CTRL, ctx->mode); + rctx->mode |= RK_CRYPTO_AES_256BIT_key; + CRYPTO_WRITE(dev, RK_CRYPTO_AES_CTRL, rctx->mode); memcpy_toio(dev->reg + RK_CRYPTO_AES_IV_0, req->iv, ivsize); } conf_reg |= RK_CRYPTO_BYTESWAP_BTFIFO | @@ -246,6 +259,7 @@ static int rk_set_data_start(struct rk_crypto_info *dev) struct skcipher_request *req = skcipher_request_cast(dev->async_req); struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); u32 ivsize = crypto_skcipher_ivsize(tfm); u8 *src_last_blk = page_address(sg_page(dev->sg_src)) + @@ -254,7 +268,7 @@ static int rk_set_data_start(struct rk_crypto_info *dev) /* Store the iv that need to be updated in chain mode. * And update the IV buffer to contain the next IV for decryption mode. */ - if (ctx->mode & RK_CRYPTO_DEC) { + if (rctx->mode & RK_CRYPTO_DEC) { memcpy(ctx->iv, src_last_blk, ivsize); sg_pcopy_to_buffer(dev->first, dev->src_nents, req->iv, ivsize, dev->total - ivsize); @@ -294,11 +308,12 @@ static void rk_iv_copyback(struct rk_crypto_info *dev) struct skcipher_request *req = skcipher_request_cast(dev->async_req); struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); u32 ivsize = crypto_skcipher_ivsize(tfm); /* Update the IV buffer to contain the next IV for encryption mode. */ - if (!(ctx->mode & RK_CRYPTO_DEC)) { + if (!(rctx->mode & RK_CRYPTO_DEC)) { if (dev->aligned) { memcpy(req->iv, sg_virt(dev->sg_dst) + dev->sg_dst->length - ivsize, ivsize); @@ -314,11 +329,12 @@ static void rk_update_iv(struct rk_crypto_info *dev) struct skcipher_request *req = skcipher_request_cast(dev->async_req); struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); u32 ivsize = crypto_skcipher_ivsize(tfm); u8 *new_iv = NULL; - if (ctx->mode & RK_CRYPTO_DEC) { + if (rctx->mode & RK_CRYPTO_DEC) { new_iv = ctx->iv; } else { new_iv = page_address(sg_page(dev->sg_dst)) + From fbd5f112dc9d7f61c9cdf21efcac2d58b3c23cbe Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Tue, 27 Sep 2022 07:54:44 +0000 Subject: [PATCH 0372/4345] crypto: rockchip - add fallback for cipher [ Upstream commit 68ef8af09a1a912a5ed2cfaa4cca7606f52cef90 ] The hardware does not handle 0 size length request, let's add a fallback. Furthermore fallback will be used for all unaligned case the hardware cannot handle. Fixes: ce0183cb6464b ("crypto: rockchip - switch to skcipher API") Reviewed-by: John Keeping Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/Kconfig | 4 + drivers/crypto/rockchip/rk3288_crypto.h | 2 + .../crypto/rockchip/rk3288_crypto_skcipher.c | 97 ++++++++++++++++--- 3 files changed, 90 insertions(+), 13 deletions(-) diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index ff5e85eefbf6..8aa8b330df70 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -749,6 +749,10 @@ config CRYPTO_DEV_IMGTEC_HASH config CRYPTO_DEV_ROCKCHIP tristate "Rockchip's Cryptographic Engine driver" depends on OF && ARCH_ROCKCHIP + depends on PM + select CRYPTO_ECB + select CRYPTO_CBC + select CRYPTO_DES select CRYPTO_AES select CRYPTO_LIB_DES select CRYPTO_MD5 diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h index 65b9b58bb304..027e28f60843 100644 --- a/drivers/crypto/rockchip/rk3288_crypto.h +++ b/drivers/crypto/rockchip/rk3288_crypto.h @@ -245,10 +245,12 @@ struct rk_cipher_ctx { struct rk_crypto_info *dev; unsigned int keylen; u8 iv[AES_BLOCK_SIZE]; + struct crypto_skcipher *fallback_tfm; }; struct rk_cipher_rctx { u32 mode; + struct skcipher_request fallback_req; // keep at the end }; enum alg_type { diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c index bbd0bf52bf07..eac5bba66e25 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c +++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c @@ -13,6 +13,63 @@ #define RK_CRYPTO_DEC BIT(0) +static int rk_cipher_need_fallback(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + unsigned int bs = crypto_skcipher_blocksize(tfm); + struct scatterlist *sgs, *sgd; + unsigned int stodo, dtodo, len; + + if (!req->cryptlen) + return true; + + len = req->cryptlen; + sgs = req->src; + sgd = req->dst; + while (sgs && sgd) { + if (!IS_ALIGNED(sgs->offset, sizeof(u32))) { + return true; + } + if (!IS_ALIGNED(sgd->offset, sizeof(u32))) { + return true; + } + stodo = min(len, sgs->length); + if (stodo % bs) { + return true; + } + dtodo = min(len, sgd->length); + if (dtodo % bs) { + return true; + } + if (stodo != dtodo) { + return true; + } + len -= stodo; + sgs = sg_next(sgs); + sgd = sg_next(sgd); + } + return false; +} + +static int rk_cipher_fallback(struct skcipher_request *areq) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq); + struct rk_cipher_ctx *op = crypto_skcipher_ctx(tfm); + struct rk_cipher_rctx *rctx = skcipher_request_ctx(areq); + int err; + + skcipher_request_set_tfm(&rctx->fallback_req, op->fallback_tfm); + skcipher_request_set_callback(&rctx->fallback_req, areq->base.flags, + areq->base.complete, areq->base.data); + skcipher_request_set_crypt(&rctx->fallback_req, areq->src, areq->dst, + areq->cryptlen, areq->iv); + if (rctx->mode & RK_CRYPTO_DEC) + err = crypto_skcipher_decrypt(&rctx->fallback_req); + else + err = crypto_skcipher_encrypt(&rctx->fallback_req); + return err; +} + static void rk_crypto_complete(struct crypto_async_request *base, int err) { if (base->complete) @@ -22,10 +79,10 @@ static void rk_crypto_complete(struct crypto_async_request *base, int err) static int rk_handle_req(struct rk_crypto_info *dev, struct skcipher_request *req) { - if (!IS_ALIGNED(req->cryptlen, dev->align_size)) - return -EINVAL; - else - return dev->enqueue(dev, &req->base); + if (rk_cipher_need_fallback(req)) + return rk_cipher_fallback(req); + + return dev->enqueue(dev, &req->base); } static int rk_aes_setkey(struct crypto_skcipher *cipher, @@ -39,7 +96,8 @@ static int rk_aes_setkey(struct crypto_skcipher *cipher, return -EINVAL; ctx->keylen = keylen; memcpy_toio(ctx->dev->reg + RK_CRYPTO_AES_KEY_0, key, keylen); - return 0; + + return crypto_skcipher_setkey(ctx->fallback_tfm, key, keylen); } static int rk_des_setkey(struct crypto_skcipher *cipher, @@ -54,7 +112,8 @@ static int rk_des_setkey(struct crypto_skcipher *cipher, ctx->keylen = keylen; memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen); - return 0; + + return crypto_skcipher_setkey(ctx->fallback_tfm, key, keylen); } static int rk_tdes_setkey(struct crypto_skcipher *cipher, @@ -69,7 +128,7 @@ static int rk_tdes_setkey(struct crypto_skcipher *cipher, ctx->keylen = keylen; memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen); - return 0; + return crypto_skcipher_setkey(ctx->fallback_tfm, key, keylen); } static int rk_aes_ecb_encrypt(struct skcipher_request *req) @@ -394,6 +453,7 @@ static int rk_ablk_init_tfm(struct crypto_skcipher *tfm) { struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_alg *alg = crypto_skcipher_alg(tfm); + const char *name = crypto_tfm_alg_name(&tfm->base); struct rk_crypto_tmp *algt; algt = container_of(alg, struct rk_crypto_tmp, alg.skcipher); @@ -407,6 +467,16 @@ static int rk_ablk_init_tfm(struct crypto_skcipher *tfm) if (!ctx->dev->addr_vir) return -ENOMEM; + ctx->fallback_tfm = crypto_alloc_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(ctx->fallback_tfm)) { + dev_err(ctx->dev->dev, "ERROR: Cannot allocate fallback for %s %ld\n", + name, PTR_ERR(ctx->fallback_tfm)); + return PTR_ERR(ctx->fallback_tfm); + } + + tfm->reqsize = sizeof(struct rk_cipher_rctx) + + crypto_skcipher_reqsize(ctx->fallback_tfm); + return 0; } @@ -415,6 +485,7 @@ static void rk_ablk_exit_tfm(struct crypto_skcipher *tfm) struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); free_page((unsigned long)ctx->dev->addr_vir); + crypto_free_skcipher(ctx->fallback_tfm); } struct rk_crypto_tmp rk_ecb_aes_alg = { @@ -423,7 +494,7 @@ struct rk_crypto_tmp rk_ecb_aes_alg = { .base.cra_name = "ecb(aes)", .base.cra_driver_name = "ecb-aes-rk", .base.cra_priority = 300, - .base.cra_flags = CRYPTO_ALG_ASYNC, + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct rk_cipher_ctx), .base.cra_alignmask = 0x0f, @@ -445,7 +516,7 @@ struct rk_crypto_tmp rk_cbc_aes_alg = { .base.cra_name = "cbc(aes)", .base.cra_driver_name = "cbc-aes-rk", .base.cra_priority = 300, - .base.cra_flags = CRYPTO_ALG_ASYNC, + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .base.cra_blocksize = AES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct rk_cipher_ctx), .base.cra_alignmask = 0x0f, @@ -468,7 +539,7 @@ struct rk_crypto_tmp rk_ecb_des_alg = { .base.cra_name = "ecb(des)", .base.cra_driver_name = "ecb-des-rk", .base.cra_priority = 300, - .base.cra_flags = CRYPTO_ALG_ASYNC, + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .base.cra_blocksize = DES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct rk_cipher_ctx), .base.cra_alignmask = 0x07, @@ -490,7 +561,7 @@ struct rk_crypto_tmp rk_cbc_des_alg = { .base.cra_name = "cbc(des)", .base.cra_driver_name = "cbc-des-rk", .base.cra_priority = 300, - .base.cra_flags = CRYPTO_ALG_ASYNC, + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .base.cra_blocksize = DES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct rk_cipher_ctx), .base.cra_alignmask = 0x07, @@ -513,7 +584,7 @@ struct rk_crypto_tmp rk_ecb_des3_ede_alg = { .base.cra_name = "ecb(des3_ede)", .base.cra_driver_name = "ecb-des3-ede-rk", .base.cra_priority = 300, - .base.cra_flags = CRYPTO_ALG_ASYNC, + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .base.cra_blocksize = DES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct rk_cipher_ctx), .base.cra_alignmask = 0x07, @@ -535,7 +606,7 @@ struct rk_crypto_tmp rk_cbc_des3_ede_alg = { .base.cra_name = "cbc(des3_ede)", .base.cra_driver_name = "cbc-des3-ede-rk", .base.cra_priority = 300, - .base.cra_flags = CRYPTO_ALG_ASYNC, + .base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK, .base.cra_blocksize = DES_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct rk_cipher_ctx), .base.cra_alignmask = 0x07, From b0b9635f09e0229960b660736351b89d03bb4858 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Tue, 27 Sep 2022 07:54:45 +0000 Subject: [PATCH 0373/4345] crypto: rockchip - add fallback for ahash [ Upstream commit 816600485cb597b3ff7d6806a95a78512839f775 ] Adds a fallback for all case hardware cannot handle. Fixes: ce0183cb6464b ("crypto: rockchip - switch to skcipher API") Reviewed-by: John Keeping Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/rockchip/rk3288_crypto_ahash.c | 38 +++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index 9583310a69d5..f917adc4a608 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -16,6 +16,40 @@ * so we put the fixed hash out when met zero message. */ +static bool rk_ahash_need_fallback(struct ahash_request *req) +{ + struct scatterlist *sg; + + sg = req->src; + while (sg) { + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { + return true; + } + if (sg->length % 4) { + return true; + } + sg = sg_next(sg); + } + return false; +} + +static int rk_ahash_digest_fb(struct ahash_request *areq) +{ + struct rk_ahash_rctx *rctx = ahash_request_ctx(areq); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct rk_ahash_ctx *tfmctx = crypto_ahash_ctx(tfm); + + ahash_request_set_tfm(&rctx->fallback_req, tfmctx->fallback_tfm); + rctx->fallback_req.base.flags = areq->base.flags & + CRYPTO_TFM_REQ_MAY_SLEEP; + + rctx->fallback_req.nbytes = areq->nbytes; + rctx->fallback_req.src = areq->src; + rctx->fallback_req.result = areq->result; + + return crypto_ahash_digest(&rctx->fallback_req); +} + static int zero_message_process(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); @@ -167,6 +201,9 @@ static int rk_ahash_digest(struct ahash_request *req) struct rk_ahash_ctx *tctx = crypto_tfm_ctx(req->base.tfm); struct rk_crypto_info *dev = tctx->dev; + if (rk_ahash_need_fallback(req)) + return rk_ahash_digest_fb(req); + if (!req->nbytes) return zero_message_process(req); else @@ -309,6 +346,7 @@ static void rk_cra_hash_exit(struct crypto_tfm *tfm) struct rk_ahash_ctx *tctx = crypto_tfm_ctx(tfm); free_page((unsigned long)tctx->dev->addr_vir); + crypto_free_ahash(tctx->fallback_tfm); } struct rk_crypto_tmp rk_ahash_sha1 = { From 0971bc99d124d78aa6779630753ef5a313eabd76 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Tue, 27 Sep 2022 07:54:46 +0000 Subject: [PATCH 0374/4345] crypto: rockchip - better handle cipher key [ Upstream commit d6b23ccef82816050c2fd458c9dabfa0e0af09b9 ] The key should not be set in hardware too much in advance, this will fail it 2 TFM with different keys generate alternative requests. The key should be stored and used just before doing cipher operations. Fixes: ce0183cb6464b ("crypto: rockchip - switch to skcipher API") Reviewed-by: John Keeping Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/rockchip/rk3288_crypto.h | 1 + drivers/crypto/rockchip/rk3288_crypto_skcipher.c | 10 +++++++--- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h index 027e28f60843..1eabf3952a03 100644 --- a/drivers/crypto/rockchip/rk3288_crypto.h +++ b/drivers/crypto/rockchip/rk3288_crypto.h @@ -244,6 +244,7 @@ struct rk_ahash_rctx { struct rk_cipher_ctx { struct rk_crypto_info *dev; unsigned int keylen; + u8 key[AES_MAX_KEY_SIZE]; u8 iv[AES_BLOCK_SIZE]; struct crypto_skcipher *fallback_tfm; }; diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c index eac5bba66e25..1ef94f8db2c5 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c +++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c @@ -95,7 +95,7 @@ static int rk_aes_setkey(struct crypto_skcipher *cipher, keylen != AES_KEYSIZE_256) return -EINVAL; ctx->keylen = keylen; - memcpy_toio(ctx->dev->reg + RK_CRYPTO_AES_KEY_0, key, keylen); + memcpy(ctx->key, key, keylen); return crypto_skcipher_setkey(ctx->fallback_tfm, key, keylen); } @@ -111,7 +111,7 @@ static int rk_des_setkey(struct crypto_skcipher *cipher, return err; ctx->keylen = keylen; - memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen); + memcpy(ctx->key, key, keylen); return crypto_skcipher_setkey(ctx->fallback_tfm, key, keylen); } @@ -127,7 +127,8 @@ static int rk_tdes_setkey(struct crypto_skcipher *cipher, return err; ctx->keylen = keylen; - memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen); + memcpy(ctx->key, key, keylen); + return crypto_skcipher_setkey(ctx->fallback_tfm, key, keylen); } @@ -283,6 +284,7 @@ static void rk_ablk_hw_init(struct rk_crypto_info *dev) RK_CRYPTO_TDES_BYTESWAP_IV; CRYPTO_WRITE(dev, RK_CRYPTO_TDES_CTRL, rctx->mode); memcpy_toio(dev->reg + RK_CRYPTO_TDES_IV_0, req->iv, ivsize); + memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, ctx->key, ctx->keylen); conf_reg = RK_CRYPTO_DESSEL; } else { rctx->mode |= RK_CRYPTO_AES_FIFO_MODE | @@ -295,6 +297,7 @@ static void rk_ablk_hw_init(struct rk_crypto_info *dev) rctx->mode |= RK_CRYPTO_AES_256BIT_key; CRYPTO_WRITE(dev, RK_CRYPTO_AES_CTRL, rctx->mode); memcpy_toio(dev->reg + RK_CRYPTO_AES_IV_0, req->iv, ivsize); + memcpy_toio(ctx->dev->reg + RK_CRYPTO_AES_KEY_0, ctx->key, ctx->keylen); } conf_reg |= RK_CRYPTO_BYTESWAP_BTFIFO | RK_CRYPTO_BYTESWAP_BRFIFO; @@ -484,6 +487,7 @@ static void rk_ablk_exit_tfm(struct crypto_skcipher *tfm) { struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); + memzero_explicit(ctx->key, ctx->keylen); free_page((unsigned long)ctx->dev->addr_vir); crypto_free_skcipher(ctx->fallback_tfm); } From de041a2e7091247b8bcf1808af16b32c37360974 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Tue, 27 Sep 2022 07:54:47 +0000 Subject: [PATCH 0375/4345] crypto: rockchip - remove non-aligned handling [ Upstream commit bb3c7b73363c9a149b12b74c44ae94b73a8fddf8 ] Now driver have fallback for un-aligned cases, remove all code handling those cases. Fixes: ce0183cb6464b ("crypto: rockchip - switch to skcipher API") Reviewed-by: John Keeping Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/rockchip/rk3288_crypto.c | 67 +++++-------------- drivers/crypto/rockchip/rk3288_crypto.h | 4 -- drivers/crypto/rockchip/rk3288_crypto_ahash.c | 22 ++---- .../crypto/rockchip/rk3288_crypto_skcipher.c | 39 +++-------- 4 files changed, 30 insertions(+), 102 deletions(-) diff --git a/drivers/crypto/rockchip/rk3288_crypto.c b/drivers/crypto/rockchip/rk3288_crypto.c index 5f8444b9633a..31453257ab11 100644 --- a/drivers/crypto/rockchip/rk3288_crypto.c +++ b/drivers/crypto/rockchip/rk3288_crypto.c @@ -88,63 +88,26 @@ static int rk_load_data(struct rk_crypto_info *dev, { unsigned int count; - dev->aligned = dev->aligned ? - check_alignment(sg_src, sg_dst, dev->align_size) : - dev->aligned; - if (dev->aligned) { - count = min(dev->left_bytes, sg_src->length); - dev->left_bytes -= count; + count = min(dev->left_bytes, sg_src->length); + dev->left_bytes -= count; - if (!dma_map_sg(dev->dev, sg_src, 1, DMA_TO_DEVICE)) { - dev_err(dev->dev, "[%s:%d] dma_map_sg(src) error\n", + if (!dma_map_sg(dev->dev, sg_src, 1, DMA_TO_DEVICE)) { + dev_err(dev->dev, "[%s:%d] dma_map_sg(src) error\n", __func__, __LINE__); - return -EINVAL; - } - dev->addr_in = sg_dma_address(sg_src); + return -EINVAL; + } + dev->addr_in = sg_dma_address(sg_src); - if (sg_dst) { - if (!dma_map_sg(dev->dev, sg_dst, 1, DMA_FROM_DEVICE)) { - dev_err(dev->dev, + if (sg_dst) { + if (!dma_map_sg(dev->dev, sg_dst, 1, DMA_FROM_DEVICE)) { + dev_err(dev->dev, "[%s:%d] dma_map_sg(dst) error\n", __func__, __LINE__); - dma_unmap_sg(dev->dev, sg_src, 1, - DMA_TO_DEVICE); - return -EINVAL; - } - dev->addr_out = sg_dma_address(sg_dst); - } - } else { - count = (dev->left_bytes > PAGE_SIZE) ? - PAGE_SIZE : dev->left_bytes; - - if (!sg_pcopy_to_buffer(dev->first, dev->src_nents, - dev->addr_vir, count, - dev->total - dev->left_bytes)) { - dev_err(dev->dev, "[%s:%d] pcopy err\n", - __func__, __LINE__); + dma_unmap_sg(dev->dev, sg_src, 1, + DMA_TO_DEVICE); return -EINVAL; } - dev->left_bytes -= count; - sg_init_one(&dev->sg_tmp, dev->addr_vir, count); - if (!dma_map_sg(dev->dev, &dev->sg_tmp, 1, DMA_TO_DEVICE)) { - dev_err(dev->dev, "[%s:%d] dma_map_sg(sg_tmp) error\n", - __func__, __LINE__); - return -ENOMEM; - } - dev->addr_in = sg_dma_address(&dev->sg_tmp); - - if (sg_dst) { - if (!dma_map_sg(dev->dev, &dev->sg_tmp, 1, - DMA_FROM_DEVICE)) { - dev_err(dev->dev, - "[%s:%d] dma_map_sg(sg_tmp) error\n", - __func__, __LINE__); - dma_unmap_sg(dev->dev, &dev->sg_tmp, 1, - DMA_TO_DEVICE); - return -ENOMEM; - } - dev->addr_out = sg_dma_address(&dev->sg_tmp); - } + dev->addr_out = sg_dma_address(sg_dst); } dev->count = count; return 0; @@ -154,11 +117,11 @@ static void rk_unload_data(struct rk_crypto_info *dev) { struct scatterlist *sg_in, *sg_out; - sg_in = dev->aligned ? dev->sg_src : &dev->sg_tmp; + sg_in = dev->sg_src; dma_unmap_sg(dev->dev, sg_in, 1, DMA_TO_DEVICE); if (dev->sg_dst) { - sg_out = dev->aligned ? dev->sg_dst : &dev->sg_tmp; + sg_out = dev->sg_dst; dma_unmap_sg(dev->dev, sg_out, 1, DMA_FROM_DEVICE); } } diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h index 1eabf3952a03..acaf6f875d0b 100644 --- a/drivers/crypto/rockchip/rk3288_crypto.h +++ b/drivers/crypto/rockchip/rk3288_crypto.h @@ -203,12 +203,8 @@ struct rk_crypto_info { /* the public variable */ struct scatterlist *sg_src; struct scatterlist *sg_dst; - struct scatterlist sg_tmp; struct scatterlist *first; unsigned int left_bytes; - void *addr_vir; - int aligned; - int align_size; size_t src_nents; size_t dst_nents; unsigned int total; diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index f917adc4a608..f1d482ecc195 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -236,8 +236,6 @@ static int rk_ahash_start(struct rk_crypto_info *dev) dev->total = req->nbytes; dev->left_bytes = req->nbytes; - dev->aligned = 0; - dev->align_size = 4; dev->sg_dst = NULL; dev->sg_src = req->src; dev->first = req->src; @@ -272,15 +270,13 @@ static int rk_ahash_crypto_rx(struct rk_crypto_info *dev) dev->unload_data(dev); if (dev->left_bytes) { - if (dev->aligned) { - if (sg_is_last(dev->sg_src)) { - dev_warn(dev->dev, "[%s:%d], Lack of data\n", - __func__, __LINE__); - err = -ENOMEM; - goto out_rx; - } - dev->sg_src = sg_next(dev->sg_src); + if (sg_is_last(dev->sg_src)) { + dev_warn(dev->dev, "[%s:%d], Lack of data\n", + __func__, __LINE__); + err = -ENOMEM; + goto out_rx; } + dev->sg_src = sg_next(dev->sg_src); err = rk_ahash_set_data_start(dev); } else { /* @@ -318,11 +314,6 @@ static int rk_cra_hash_init(struct crypto_tfm *tfm) algt = container_of(alg, struct rk_crypto_tmp, alg.hash); tctx->dev = algt->dev; - tctx->dev->addr_vir = (void *)__get_free_page(GFP_KERNEL); - if (!tctx->dev->addr_vir) { - dev_err(tctx->dev->dev, "failed to kmalloc for addr_vir\n"); - return -ENOMEM; - } tctx->dev->start = rk_ahash_start; tctx->dev->update = rk_ahash_crypto_rx; tctx->dev->complete = rk_ahash_crypto_complete; @@ -345,7 +336,6 @@ static void rk_cra_hash_exit(struct crypto_tfm *tfm) { struct rk_ahash_ctx *tctx = crypto_tfm_ctx(tfm); - free_page((unsigned long)tctx->dev->addr_vir); crypto_free_ahash(tctx->fallback_tfm); } diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c index 1ef94f8db2c5..d067b7f09165 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c +++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c @@ -356,7 +356,6 @@ static int rk_ablk_start(struct rk_crypto_info *dev) dev->src_nents = sg_nents(req->src); dev->sg_dst = req->dst; dev->dst_nents = sg_nents(req->dst); - dev->aligned = 1; spin_lock_irqsave(&dev->lock, flags); rk_ablk_hw_init(dev); @@ -376,13 +375,9 @@ static void rk_iv_copyback(struct rk_crypto_info *dev) /* Update the IV buffer to contain the next IV for encryption mode. */ if (!(rctx->mode & RK_CRYPTO_DEC)) { - if (dev->aligned) { - memcpy(req->iv, sg_virt(dev->sg_dst) + - dev->sg_dst->length - ivsize, ivsize); - } else { - memcpy(req->iv, dev->addr_vir + - dev->count - ivsize, ivsize); - } + memcpy(req->iv, + sg_virt(dev->sg_dst) + dev->sg_dst->length - ivsize, + ivsize); } } @@ -420,27 +415,16 @@ static int rk_ablk_rx(struct rk_crypto_info *dev) skcipher_request_cast(dev->async_req); dev->unload_data(dev); - if (!dev->aligned) { - if (!sg_pcopy_from_buffer(req->dst, dev->dst_nents, - dev->addr_vir, dev->count, - dev->total - dev->left_bytes - - dev->count)) { - err = -EINVAL; - goto out_rx; - } - } if (dev->left_bytes) { rk_update_iv(dev); - if (dev->aligned) { - if (sg_is_last(dev->sg_src)) { - dev_err(dev->dev, "[%s:%d] Lack of data\n", + if (sg_is_last(dev->sg_src)) { + dev_err(dev->dev, "[%s:%d] Lack of data\n", __func__, __LINE__); - err = -ENOMEM; - goto out_rx; - } - dev->sg_src = sg_next(dev->sg_src); - dev->sg_dst = sg_next(dev->sg_dst); + err = -ENOMEM; + goto out_rx; } + dev->sg_src = sg_next(dev->sg_src); + dev->sg_dst = sg_next(dev->sg_dst); err = rk_set_data_start(dev); } else { rk_iv_copyback(dev); @@ -462,13 +446,9 @@ static int rk_ablk_init_tfm(struct crypto_skcipher *tfm) algt = container_of(alg, struct rk_crypto_tmp, alg.skcipher); ctx->dev = algt->dev; - ctx->dev->align_size = crypto_tfm_alg_alignmask(crypto_skcipher_tfm(tfm)) + 1; ctx->dev->start = rk_ablk_start; ctx->dev->update = rk_ablk_rx; ctx->dev->complete = rk_crypto_complete; - ctx->dev->addr_vir = (char *)__get_free_page(GFP_KERNEL); - if (!ctx->dev->addr_vir) - return -ENOMEM; ctx->fallback_tfm = crypto_alloc_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK); if (IS_ERR(ctx->fallback_tfm)) { @@ -488,7 +468,6 @@ static void rk_ablk_exit_tfm(struct crypto_skcipher *tfm) struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); memzero_explicit(ctx->key, ctx->keylen); - free_page((unsigned long)ctx->dev->addr_vir); crypto_free_skcipher(ctx->fallback_tfm); } From 6cd8bbb089be07b0e6c2a4ab70f8549b6c6e2273 Mon Sep 17 00:00:00 2001 From: Kai Ye Date: Thu, 1 Apr 2021 11:01:39 +0800 Subject: [PATCH 0376/4345] crypto: rockchip - delete unneeded variable initialization [ Upstream commit 3d8c5f5a08c39835a365c69d1a6d9518722ed19e ] Delete unneeded variable initialization Signed-off-by: Kai Ye Signed-off-by: Herbert Xu Stable-dep-of: 57d67c6e8219 ("crypto: rockchip - rework by using crypto_engine") Signed-off-by: Sasha Levin --- drivers/crypto/rockchip/rk3288_crypto_ahash.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index f1d482ecc195..c762e462eb57 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -82,7 +82,7 @@ static void rk_ahash_reg_init(struct rk_crypto_info *dev) { struct ahash_request *req = ahash_request_cast(dev->async_req); struct rk_ahash_rctx *rctx = ahash_request_ctx(req); - int reg_status = 0; + int reg_status; reg_status = CRYPTO_READ(dev, RK_CRYPTO_CTRL) | RK_CRYPTO_HASH_FLUSH | _SBF(0xffff, 16); From 417ef568a72527d61b17c240fed680f1fc851d4b Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Tue, 27 Sep 2022 07:54:48 +0000 Subject: [PATCH 0377/4345] crypto: rockchip - rework by using crypto_engine [ Upstream commit 57d67c6e8219b2a034c16d6149e30fb40fd39935 ] Instead of doing manual queue management, let's use the crypto/engine for that. In the same time, rework the requests handling to be easier to understand (and fix all bugs related to them). Fixes: ce0183cb6464b ("crypto: rockchip - switch to skcipher API") Reviewed-by: John Keeping Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/Kconfig | 1 + drivers/crypto/rockchip/rk3288_crypto.c | 152 +--------- drivers/crypto/rockchip/rk3288_crypto.h | 37 +-- drivers/crypto/rockchip/rk3288_crypto_ahash.c | 140 +++++----- .../crypto/rockchip/rk3288_crypto_skcipher.c | 262 +++++++++--------- 5 files changed, 224 insertions(+), 368 deletions(-) diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 8aa8b330df70..0a3dd0793f30 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -754,6 +754,7 @@ config CRYPTO_DEV_ROCKCHIP select CRYPTO_CBC select CRYPTO_DES select CRYPTO_AES + select CRYPTO_ENGINE select CRYPTO_LIB_DES select CRYPTO_MD5 select CRYPTO_SHA1 diff --git a/drivers/crypto/rockchip/rk3288_crypto.c b/drivers/crypto/rockchip/rk3288_crypto.c index 31453257ab11..14a0aef18ab1 100644 --- a/drivers/crypto/rockchip/rk3288_crypto.c +++ b/drivers/crypto/rockchip/rk3288_crypto.c @@ -65,149 +65,24 @@ static void rk_crypto_disable_clk(struct rk_crypto_info *dev) clk_disable_unprepare(dev->sclk); } -static int check_alignment(struct scatterlist *sg_src, - struct scatterlist *sg_dst, - int align_mask) -{ - int in, out, align; - - in = IS_ALIGNED((uint32_t)sg_src->offset, 4) && - IS_ALIGNED((uint32_t)sg_src->length, align_mask); - if (!sg_dst) - return in; - out = IS_ALIGNED((uint32_t)sg_dst->offset, 4) && - IS_ALIGNED((uint32_t)sg_dst->length, align_mask); - align = in && out; - - return (align && (sg_src->length == sg_dst->length)); -} - -static int rk_load_data(struct rk_crypto_info *dev, - struct scatterlist *sg_src, - struct scatterlist *sg_dst) -{ - unsigned int count; - - count = min(dev->left_bytes, sg_src->length); - dev->left_bytes -= count; - - if (!dma_map_sg(dev->dev, sg_src, 1, DMA_TO_DEVICE)) { - dev_err(dev->dev, "[%s:%d] dma_map_sg(src) error\n", - __func__, __LINE__); - return -EINVAL; - } - dev->addr_in = sg_dma_address(sg_src); - - if (sg_dst) { - if (!dma_map_sg(dev->dev, sg_dst, 1, DMA_FROM_DEVICE)) { - dev_err(dev->dev, - "[%s:%d] dma_map_sg(dst) error\n", - __func__, __LINE__); - dma_unmap_sg(dev->dev, sg_src, 1, - DMA_TO_DEVICE); - return -EINVAL; - } - dev->addr_out = sg_dma_address(sg_dst); - } - dev->count = count; - return 0; -} - -static void rk_unload_data(struct rk_crypto_info *dev) -{ - struct scatterlist *sg_in, *sg_out; - - sg_in = dev->sg_src; - dma_unmap_sg(dev->dev, sg_in, 1, DMA_TO_DEVICE); - - if (dev->sg_dst) { - sg_out = dev->sg_dst; - dma_unmap_sg(dev->dev, sg_out, 1, DMA_FROM_DEVICE); - } -} - static irqreturn_t rk_crypto_irq_handle(int irq, void *dev_id) { struct rk_crypto_info *dev = platform_get_drvdata(dev_id); u32 interrupt_status; - spin_lock(&dev->lock); interrupt_status = CRYPTO_READ(dev, RK_CRYPTO_INTSTS); CRYPTO_WRITE(dev, RK_CRYPTO_INTSTS, interrupt_status); + dev->status = 1; if (interrupt_status & 0x0a) { dev_warn(dev->dev, "DMA Error\n"); - dev->err = -EFAULT; + dev->status = 0; } - tasklet_schedule(&dev->done_task); + complete(&dev->complete); - spin_unlock(&dev->lock); return IRQ_HANDLED; } -static int rk_crypto_enqueue(struct rk_crypto_info *dev, - struct crypto_async_request *async_req) -{ - unsigned long flags; - int ret; - - spin_lock_irqsave(&dev->lock, flags); - ret = crypto_enqueue_request(&dev->queue, async_req); - if (dev->busy) { - spin_unlock_irqrestore(&dev->lock, flags); - return ret; - } - dev->busy = true; - spin_unlock_irqrestore(&dev->lock, flags); - tasklet_schedule(&dev->queue_task); - - return ret; -} - -static void rk_crypto_queue_task_cb(unsigned long data) -{ - struct rk_crypto_info *dev = (struct rk_crypto_info *)data; - struct crypto_async_request *async_req, *backlog; - unsigned long flags; - int err = 0; - - dev->err = 0; - spin_lock_irqsave(&dev->lock, flags); - backlog = crypto_get_backlog(&dev->queue); - async_req = crypto_dequeue_request(&dev->queue); - - if (!async_req) { - dev->busy = false; - spin_unlock_irqrestore(&dev->lock, flags); - return; - } - spin_unlock_irqrestore(&dev->lock, flags); - - if (backlog) { - backlog->complete(backlog, -EINPROGRESS); - backlog = NULL; - } - - dev->async_req = async_req; - err = dev->start(dev); - if (err) - dev->complete(dev->async_req, err); -} - -static void rk_crypto_done_task_cb(unsigned long data) -{ - struct rk_crypto_info *dev = (struct rk_crypto_info *)data; - - if (dev->err) { - dev->complete(dev->async_req, dev->err); - return; - } - - dev->err = dev->update(dev); - if (dev->err) - dev->complete(dev->async_req, dev->err); -} - static struct rk_crypto_tmp *rk_cipher_algs[] = { &rk_ecb_aes_alg, &rk_cbc_aes_alg, @@ -300,8 +175,6 @@ static int rk_crypto_probe(struct platform_device *pdev) if (err) goto err_crypto; - spin_lock_init(&crypto_info->lock); - crypto_info->reg = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(crypto_info->reg)) { err = PTR_ERR(crypto_info->reg); @@ -352,17 +225,11 @@ static int rk_crypto_probe(struct platform_device *pdev) crypto_info->dev = &pdev->dev; platform_set_drvdata(pdev, crypto_info); - tasklet_init(&crypto_info->queue_task, - rk_crypto_queue_task_cb, (unsigned long)crypto_info); - tasklet_init(&crypto_info->done_task, - rk_crypto_done_task_cb, (unsigned long)crypto_info); - crypto_init_queue(&crypto_info->queue, 50); + crypto_info->engine = crypto_engine_alloc_init(&pdev->dev, true); + crypto_engine_start(crypto_info->engine); + init_completion(&crypto_info->complete); rk_crypto_enable_clk(crypto_info); - crypto_info->load_data = rk_load_data; - crypto_info->unload_data = rk_unload_data; - crypto_info->enqueue = rk_crypto_enqueue; - crypto_info->busy = false; err = rk_crypto_register(crypto_info); if (err) { @@ -374,9 +241,9 @@ static int rk_crypto_probe(struct platform_device *pdev) return 0; err_register_alg: - tasklet_kill(&crypto_info->queue_task); - tasklet_kill(&crypto_info->done_task); + crypto_engine_exit(crypto_info->engine); err_crypto: + dev_err(dev, "Crypto Accelerator not successfully registered\n"); return err; } @@ -386,8 +253,7 @@ static int rk_crypto_remove(struct platform_device *pdev) rk_crypto_unregister(); rk_crypto_disable_clk(crypto_tmp); - tasklet_kill(&crypto_tmp->done_task); - tasklet_kill(&crypto_tmp->queue_task); + crypto_engine_exit(crypto_tmp->engine); return 0; } diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h index acaf6f875d0b..6b1413c0359b 100644 --- a/drivers/crypto/rockchip/rk3288_crypto.h +++ b/drivers/crypto/rockchip/rk3288_crypto.h @@ -5,9 +5,11 @@ #include #include #include +#include #include #include #include +#include #include #include @@ -192,39 +194,15 @@ struct rk_crypto_info { struct reset_control *rst; void __iomem *reg; int irq; - struct crypto_queue queue; - struct tasklet_struct queue_task; - struct tasklet_struct done_task; - struct crypto_async_request *async_req; - int err; - /* device lock */ - spinlock_t lock; - /* the public variable */ - struct scatterlist *sg_src; - struct scatterlist *sg_dst; - struct scatterlist *first; - unsigned int left_bytes; - size_t src_nents; - size_t dst_nents; - unsigned int total; - unsigned int count; - dma_addr_t addr_in; - dma_addr_t addr_out; - bool busy; - int (*start)(struct rk_crypto_info *dev); - int (*update)(struct rk_crypto_info *dev); - void (*complete)(struct crypto_async_request *base, int err); - int (*load_data)(struct rk_crypto_info *dev, - struct scatterlist *sg_src, - struct scatterlist *sg_dst); - void (*unload_data)(struct rk_crypto_info *dev); - int (*enqueue)(struct rk_crypto_info *dev, - struct crypto_async_request *async_req); + struct crypto_engine *engine; + struct completion complete; + int status; }; /* the private variable of hash */ struct rk_ahash_ctx { + struct crypto_engine_ctx enginectx; struct rk_crypto_info *dev; /* for fallback */ struct crypto_ahash *fallback_tfm; @@ -234,10 +212,12 @@ struct rk_ahash_ctx { struct rk_ahash_rctx { struct ahash_request fallback_req; u32 mode; + int nrsg; }; /* the private variable of cipher */ struct rk_cipher_ctx { + struct crypto_engine_ctx enginectx; struct rk_crypto_info *dev; unsigned int keylen; u8 key[AES_MAX_KEY_SIZE]; @@ -246,6 +226,7 @@ struct rk_cipher_ctx { }; struct rk_cipher_rctx { + u8 backup_iv[AES_BLOCK_SIZE]; u32 mode; struct skcipher_request fallback_req; // keep at the end }; diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index c762e462eb57..edd40e16a3f0 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -9,6 +9,7 @@ * Some ideas are from marvell/cesa.c and s5p-sss.c driver. */ #include +#include #include "rk3288_crypto.h" /* @@ -72,16 +73,12 @@ static int zero_message_process(struct ahash_request *req) return 0; } -static void rk_ahash_crypto_complete(struct crypto_async_request *base, int err) +static void rk_ahash_reg_init(struct ahash_request *req) { - if (base->complete) - base->complete(base, err); -} - -static void rk_ahash_reg_init(struct rk_crypto_info *dev) -{ - struct ahash_request *req = ahash_request_cast(dev->async_req); struct rk_ahash_rctx *rctx = ahash_request_ctx(req); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct rk_ahash_ctx *tctx = crypto_ahash_ctx(tfm); + struct rk_crypto_info *dev = tctx->dev; int reg_status; reg_status = CRYPTO_READ(dev, RK_CRYPTO_CTRL) | @@ -108,7 +105,7 @@ static void rk_ahash_reg_init(struct rk_crypto_info *dev) RK_CRYPTO_BYTESWAP_BRFIFO | RK_CRYPTO_BYTESWAP_BTFIFO); - CRYPTO_WRITE(dev, RK_CRYPTO_HASH_MSG_LEN, dev->total); + CRYPTO_WRITE(dev, RK_CRYPTO_HASH_MSG_LEN, req->nbytes); } static int rk_ahash_init(struct ahash_request *req) @@ -206,44 +203,59 @@ static int rk_ahash_digest(struct ahash_request *req) if (!req->nbytes) return zero_message_process(req); - else - return dev->enqueue(dev, &req->base); + + return crypto_transfer_hash_request_to_engine(dev->engine, req); } -static void crypto_ahash_dma_start(struct rk_crypto_info *dev) +static void crypto_ahash_dma_start(struct rk_crypto_info *dev, struct scatterlist *sg) { - CRYPTO_WRITE(dev, RK_CRYPTO_HRDMAS, dev->addr_in); - CRYPTO_WRITE(dev, RK_CRYPTO_HRDMAL, (dev->count + 3) / 4); + CRYPTO_WRITE(dev, RK_CRYPTO_HRDMAS, sg_dma_address(sg)); + CRYPTO_WRITE(dev, RK_CRYPTO_HRDMAL, sg_dma_len(sg) / 4); CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, RK_CRYPTO_HASH_START | (RK_CRYPTO_HASH_START << 16)); } -static int rk_ahash_set_data_start(struct rk_crypto_info *dev) +static int rk_hash_prepare(struct crypto_engine *engine, void *breq) { - int err; + struct ahash_request *areq = container_of(breq, struct ahash_request, base); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct rk_ahash_rctx *rctx = ahash_request_ctx(areq); + struct rk_ahash_ctx *tctx = crypto_ahash_ctx(tfm); + int ret; - err = dev->load_data(dev, dev->sg_src, NULL); - if (!err) - crypto_ahash_dma_start(dev); - return err; + ret = dma_map_sg(tctx->dev->dev, areq->src, sg_nents(areq->src), DMA_TO_DEVICE); + if (ret <= 0) + return -EINVAL; + + rctx->nrsg = ret; + + return 0; } -static int rk_ahash_start(struct rk_crypto_info *dev) +static int rk_hash_unprepare(struct crypto_engine *engine, void *breq) { - struct ahash_request *req = ahash_request_cast(dev->async_req); - struct crypto_ahash *tfm; - struct rk_ahash_rctx *rctx; + struct ahash_request *areq = container_of(breq, struct ahash_request, base); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct rk_ahash_rctx *rctx = ahash_request_ctx(areq); + struct rk_ahash_ctx *tctx = crypto_ahash_ctx(tfm); + + dma_unmap_sg(tctx->dev->dev, areq->src, rctx->nrsg, DMA_TO_DEVICE); + return 0; +} + +static int rk_hash_run(struct crypto_engine *engine, void *breq) +{ + struct ahash_request *areq = container_of(breq, struct ahash_request, base); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + struct rk_ahash_rctx *rctx = ahash_request_ctx(areq); + struct rk_ahash_ctx *tctx = crypto_ahash_ctx(tfm); + struct scatterlist *sg = areq->src; + int err = 0; + int i; + u32 v; - dev->total = req->nbytes; - dev->left_bytes = req->nbytes; - dev->sg_dst = NULL; - dev->sg_src = req->src; - dev->first = req->src; - dev->src_nents = sg_nents(req->src); - rctx = ahash_request_ctx(req); rctx->mode = 0; - tfm = crypto_ahash_reqtfm(req); switch (crypto_ahash_digestsize(tfm)) { case SHA1_DIGEST_SIZE: rctx->mode = RK_CRYPTO_HASH_SHA1; @@ -255,30 +267,26 @@ static int rk_ahash_start(struct rk_crypto_info *dev) rctx->mode = RK_CRYPTO_HASH_MD5; break; default: - return -EINVAL; + err = -EINVAL; + goto theend; } - rk_ahash_reg_init(dev); - return rk_ahash_set_data_start(dev); -} + rk_ahash_reg_init(areq); -static int rk_ahash_crypto_rx(struct rk_crypto_info *dev) -{ - int err = 0; - struct ahash_request *req = ahash_request_cast(dev->async_req); - struct crypto_ahash *tfm; - - dev->unload_data(dev); - if (dev->left_bytes) { - if (sg_is_last(dev->sg_src)) { - dev_warn(dev->dev, "[%s:%d], Lack of data\n", - __func__, __LINE__); - err = -ENOMEM; - goto out_rx; + while (sg) { + reinit_completion(&tctx->dev->complete); + tctx->dev->status = 0; + crypto_ahash_dma_start(tctx->dev, sg); + wait_for_completion_interruptible_timeout(&tctx->dev->complete, + msecs_to_jiffies(2000)); + if (!tctx->dev->status) { + dev_err(tctx->dev->dev, "DMA timeout\n"); + err = -EFAULT; + goto theend; } - dev->sg_src = sg_next(dev->sg_src); - err = rk_ahash_set_data_start(dev); - } else { + sg = sg_next(sg); + } + /* * it will take some time to process date after last dma * transmission. @@ -289,18 +297,20 @@ static int rk_ahash_crypto_rx(struct rk_crypto_info *dev) * efficiency, and make it response quickly when dma * complete. */ - while (!CRYPTO_READ(dev, RK_CRYPTO_HASH_STS)) - udelay(10); + while (!CRYPTO_READ(tctx->dev, RK_CRYPTO_HASH_STS)) + udelay(10); - tfm = crypto_ahash_reqtfm(req); - memcpy_fromio(req->result, dev->reg + RK_CRYPTO_HASH_DOUT_0, - crypto_ahash_digestsize(tfm)); - dev->complete(dev->async_req, 0); - tasklet_schedule(&dev->queue_task); + for (i = 0; i < crypto_ahash_digestsize(tfm) / 4; i++) { + v = readl(tctx->dev->reg + RK_CRYPTO_HASH_DOUT_0 + i * 4); + put_unaligned_le32(v, areq->result + i * 4); } -out_rx: - return err; +theend: + local_bh_disable(); + crypto_finalize_hash_request(engine, breq, err); + local_bh_enable(); + + return 0; } static int rk_cra_hash_init(struct crypto_tfm *tfm) @@ -314,9 +324,6 @@ static int rk_cra_hash_init(struct crypto_tfm *tfm) algt = container_of(alg, struct rk_crypto_tmp, alg.hash); tctx->dev = algt->dev; - tctx->dev->start = rk_ahash_start; - tctx->dev->update = rk_ahash_crypto_rx; - tctx->dev->complete = rk_ahash_crypto_complete; /* for fallback */ tctx->fallback_tfm = crypto_alloc_ahash(alg_name, 0, @@ -325,10 +332,15 @@ static int rk_cra_hash_init(struct crypto_tfm *tfm) dev_err(tctx->dev->dev, "Could not load fallback driver.\n"); return PTR_ERR(tctx->fallback_tfm); } + crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), sizeof(struct rk_ahash_rctx) + crypto_ahash_reqsize(tctx->fallback_tfm)); + tctx->enginectx.op.do_one_request = rk_hash_run; + tctx->enginectx.op.prepare_request = rk_hash_prepare; + tctx->enginectx.op.unprepare_request = rk_hash_unprepare; + return 0; } diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c index d067b7f09165..67a7e05d5ae3 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c +++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c @@ -9,6 +9,7 @@ * Some ideas are from marvell-cesa.c and s5p-sss.c driver. */ #include +#include #include "rk3288_crypto.h" #define RK_CRYPTO_DEC BIT(0) @@ -70,19 +71,15 @@ static int rk_cipher_fallback(struct skcipher_request *areq) return err; } -static void rk_crypto_complete(struct crypto_async_request *base, int err) -{ - if (base->complete) - base->complete(base, err); -} - static int rk_handle_req(struct rk_crypto_info *dev, struct skcipher_request *req) { + struct crypto_engine *engine = dev->engine; + if (rk_cipher_need_fallback(req)) return rk_cipher_fallback(req); - return dev->enqueue(dev, &req->base); + return crypto_transfer_skcipher_request_to_engine(engine, req); } static int rk_aes_setkey(struct crypto_skcipher *cipher, @@ -265,25 +262,21 @@ static int rk_des3_ede_cbc_decrypt(struct skcipher_request *req) return rk_handle_req(dev, req); } -static void rk_ablk_hw_init(struct rk_crypto_info *dev) +static void rk_ablk_hw_init(struct rk_crypto_info *dev, struct skcipher_request *req) { - struct skcipher_request *req = - skcipher_request_cast(dev->async_req); struct crypto_skcipher *cipher = crypto_skcipher_reqtfm(req); struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher); struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(cipher); - u32 ivsize, block, conf_reg = 0; + u32 block, conf_reg = 0; block = crypto_tfm_alg_blocksize(tfm); - ivsize = crypto_skcipher_ivsize(cipher); if (block == DES_BLOCK_SIZE) { rctx->mode |= RK_CRYPTO_TDES_FIFO_MODE | RK_CRYPTO_TDES_BYTESWAP_KEY | RK_CRYPTO_TDES_BYTESWAP_IV; CRYPTO_WRITE(dev, RK_CRYPTO_TDES_CTRL, rctx->mode); - memcpy_toio(dev->reg + RK_CRYPTO_TDES_IV_0, req->iv, ivsize); memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, ctx->key, ctx->keylen); conf_reg = RK_CRYPTO_DESSEL; } else { @@ -296,7 +289,6 @@ static void rk_ablk_hw_init(struct rk_crypto_info *dev) else if (ctx->keylen == AES_KEYSIZE_256) rctx->mode |= RK_CRYPTO_AES_256BIT_key; CRYPTO_WRITE(dev, RK_CRYPTO_AES_CTRL, rctx->mode); - memcpy_toio(dev->reg + RK_CRYPTO_AES_IV_0, req->iv, ivsize); memcpy_toio(ctx->dev->reg + RK_CRYPTO_AES_KEY_0, ctx->key, ctx->keylen); } conf_reg |= RK_CRYPTO_BYTESWAP_BTFIFO | @@ -306,133 +298,138 @@ static void rk_ablk_hw_init(struct rk_crypto_info *dev) RK_CRYPTO_BCDMA_ERR_ENA | RK_CRYPTO_BCDMA_DONE_ENA); } -static void crypto_dma_start(struct rk_crypto_info *dev) +static void crypto_dma_start(struct rk_crypto_info *dev, + struct scatterlist *sgs, + struct scatterlist *sgd, unsigned int todo) { - CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAS, dev->addr_in); - CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAL, dev->count / 4); - CRYPTO_WRITE(dev, RK_CRYPTO_BTDMAS, dev->addr_out); + CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAS, sg_dma_address(sgs)); + CRYPTO_WRITE(dev, RK_CRYPTO_BRDMAL, todo); + CRYPTO_WRITE(dev, RK_CRYPTO_BTDMAS, sg_dma_address(sgd)); CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, RK_CRYPTO_BLOCK_START | _SBF(RK_CRYPTO_BLOCK_START, 16)); } -static int rk_set_data_start(struct rk_crypto_info *dev) +static int rk_cipher_run(struct crypto_engine *engine, void *async_req) { - int err; - struct skcipher_request *req = - skcipher_request_cast(dev->async_req); - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); + struct skcipher_request *areq = container_of(async_req, struct skcipher_request, base); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(areq); struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); - u32 ivsize = crypto_skcipher_ivsize(tfm); - u8 *src_last_blk = page_address(sg_page(dev->sg_src)) + - dev->sg_src->offset + dev->sg_src->length - ivsize; - - /* Store the iv that need to be updated in chain mode. - * And update the IV buffer to contain the next IV for decryption mode. - */ - if (rctx->mode & RK_CRYPTO_DEC) { - memcpy(ctx->iv, src_last_blk, ivsize); - sg_pcopy_to_buffer(dev->first, dev->src_nents, req->iv, - ivsize, dev->total - ivsize); - } - - err = dev->load_data(dev, dev->sg_src, dev->sg_dst); - if (!err) - crypto_dma_start(dev); - return err; -} - -static int rk_ablk_start(struct rk_crypto_info *dev) -{ - struct skcipher_request *req = - skcipher_request_cast(dev->async_req); - unsigned long flags; + struct rk_cipher_rctx *rctx = skcipher_request_ctx(areq); + struct scatterlist *sgs, *sgd; int err = 0; + int ivsize = crypto_skcipher_ivsize(tfm); + int offset; + u8 iv[AES_BLOCK_SIZE]; + u8 biv[AES_BLOCK_SIZE]; + u8 *ivtouse = areq->iv; + unsigned int len = areq->cryptlen; + unsigned int todo; - dev->left_bytes = req->cryptlen; - dev->total = req->cryptlen; - dev->sg_src = req->src; - dev->first = req->src; - dev->src_nents = sg_nents(req->src); - dev->sg_dst = req->dst; - dev->dst_nents = sg_nents(req->dst); - - spin_lock_irqsave(&dev->lock, flags); - rk_ablk_hw_init(dev); - err = rk_set_data_start(dev); - spin_unlock_irqrestore(&dev->lock, flags); - return err; -} - -static void rk_iv_copyback(struct rk_crypto_info *dev) -{ - struct skcipher_request *req = - skcipher_request_cast(dev->async_req); - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); - struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); - u32 ivsize = crypto_skcipher_ivsize(tfm); - - /* Update the IV buffer to contain the next IV for encryption mode. */ - if (!(rctx->mode & RK_CRYPTO_DEC)) { - memcpy(req->iv, - sg_virt(dev->sg_dst) + dev->sg_dst->length - ivsize, - ivsize); - } -} - -static void rk_update_iv(struct rk_crypto_info *dev) -{ - struct skcipher_request *req = - skcipher_request_cast(dev->async_req); - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct rk_cipher_rctx *rctx = skcipher_request_ctx(req); - struct rk_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); - u32 ivsize = crypto_skcipher_ivsize(tfm); - u8 *new_iv = NULL; - - if (rctx->mode & RK_CRYPTO_DEC) { - new_iv = ctx->iv; - } else { - new_iv = page_address(sg_page(dev->sg_dst)) + - dev->sg_dst->offset + dev->sg_dst->length - ivsize; - } - - if (ivsize == DES_BLOCK_SIZE) - memcpy_toio(dev->reg + RK_CRYPTO_TDES_IV_0, new_iv, ivsize); - else if (ivsize == AES_BLOCK_SIZE) - memcpy_toio(dev->reg + RK_CRYPTO_AES_IV_0, new_iv, ivsize); -} - -/* return: - * true some err was occurred - * fault no err, continue - */ -static int rk_ablk_rx(struct rk_crypto_info *dev) -{ - int err = 0; - struct skcipher_request *req = - skcipher_request_cast(dev->async_req); - - dev->unload_data(dev); - if (dev->left_bytes) { - rk_update_iv(dev); - if (sg_is_last(dev->sg_src)) { - dev_err(dev->dev, "[%s:%d] Lack of data\n", - __func__, __LINE__); - err = -ENOMEM; - goto out_rx; + ivsize = crypto_skcipher_ivsize(tfm); + if (areq->iv && crypto_skcipher_ivsize(tfm) > 0) { + if (rctx->mode & RK_CRYPTO_DEC) { + offset = areq->cryptlen - ivsize; + scatterwalk_map_and_copy(rctx->backup_iv, areq->src, + offset, ivsize, 0); } - dev->sg_src = sg_next(dev->sg_src); - dev->sg_dst = sg_next(dev->sg_dst); - err = rk_set_data_start(dev); - } else { - rk_iv_copyback(dev); - /* here show the calculation is over without any err */ - dev->complete(dev->async_req, 0); - tasklet_schedule(&dev->queue_task); } -out_rx: + + sgs = areq->src; + sgd = areq->dst; + + while (sgs && sgd && len) { + if (!sgs->length) { + sgs = sg_next(sgs); + sgd = sg_next(sgd); + continue; + } + if (rctx->mode & RK_CRYPTO_DEC) { + /* we backup last block of source to be used as IV at next step */ + offset = sgs->length - ivsize; + scatterwalk_map_and_copy(biv, sgs, offset, ivsize, 0); + } + if (sgs == sgd) { + err = dma_map_sg(ctx->dev->dev, sgs, 1, DMA_BIDIRECTIONAL); + if (err <= 0) { + err = -EINVAL; + goto theend_iv; + } + } else { + err = dma_map_sg(ctx->dev->dev, sgs, 1, DMA_TO_DEVICE); + if (err <= 0) { + err = -EINVAL; + goto theend_iv; + } + err = dma_map_sg(ctx->dev->dev, sgd, 1, DMA_FROM_DEVICE); + if (err <= 0) { + err = -EINVAL; + goto theend_sgs; + } + } + err = 0; + rk_ablk_hw_init(ctx->dev, areq); + if (ivsize) { + if (ivsize == DES_BLOCK_SIZE) + memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_IV_0, ivtouse, ivsize); + else + memcpy_toio(ctx->dev->reg + RK_CRYPTO_AES_IV_0, ivtouse, ivsize); + } + reinit_completion(&ctx->dev->complete); + ctx->dev->status = 0; + + todo = min(sg_dma_len(sgs), len); + len -= todo; + crypto_dma_start(ctx->dev, sgs, sgd, todo / 4); + wait_for_completion_interruptible_timeout(&ctx->dev->complete, + msecs_to_jiffies(2000)); + if (!ctx->dev->status) { + dev_err(ctx->dev->dev, "DMA timeout\n"); + err = -EFAULT; + goto theend; + } + if (sgs == sgd) { + dma_unmap_sg(ctx->dev->dev, sgs, 1, DMA_BIDIRECTIONAL); + } else { + dma_unmap_sg(ctx->dev->dev, sgs, 1, DMA_TO_DEVICE); + dma_unmap_sg(ctx->dev->dev, sgd, 1, DMA_FROM_DEVICE); + } + if (rctx->mode & RK_CRYPTO_DEC) { + memcpy(iv, biv, ivsize); + ivtouse = iv; + } else { + offset = sgd->length - ivsize; + scatterwalk_map_and_copy(iv, sgd, offset, ivsize, 0); + ivtouse = iv; + } + sgs = sg_next(sgs); + sgd = sg_next(sgd); + } + + if (areq->iv && ivsize > 0) { + offset = areq->cryptlen - ivsize; + if (rctx->mode & RK_CRYPTO_DEC) { + memcpy(areq->iv, rctx->backup_iv, ivsize); + memzero_explicit(rctx->backup_iv, ivsize); + } else { + scatterwalk_map_and_copy(areq->iv, areq->dst, offset, + ivsize, 0); + } + } + +theend: + local_bh_disable(); + crypto_finalize_skcipher_request(engine, areq, err); + local_bh_enable(); + return 0; + +theend_sgs: + if (sgs == sgd) { + dma_unmap_sg(ctx->dev->dev, sgs, 1, DMA_BIDIRECTIONAL); + } else { + dma_unmap_sg(ctx->dev->dev, sgs, 1, DMA_TO_DEVICE); + dma_unmap_sg(ctx->dev->dev, sgd, 1, DMA_FROM_DEVICE); + } +theend_iv: return err; } @@ -446,9 +443,6 @@ static int rk_ablk_init_tfm(struct crypto_skcipher *tfm) algt = container_of(alg, struct rk_crypto_tmp, alg.skcipher); ctx->dev = algt->dev; - ctx->dev->start = rk_ablk_start; - ctx->dev->update = rk_ablk_rx; - ctx->dev->complete = rk_crypto_complete; ctx->fallback_tfm = crypto_alloc_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK); if (IS_ERR(ctx->fallback_tfm)) { @@ -460,6 +454,8 @@ static int rk_ablk_init_tfm(struct crypto_skcipher *tfm) tfm->reqsize = sizeof(struct rk_cipher_rctx) + crypto_skcipher_reqsize(ctx->fallback_tfm); + ctx->enginectx.op.do_one_request = rk_cipher_run; + return 0; } From 9a32aa87a25d800b2c6f47bc2749a7bfd9a486f3 Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Fri, 28 Oct 2022 20:33:20 +0800 Subject: [PATCH 0378/4345] apparmor: Fix memleak in alloc_ns() [ Upstream commit e9e6fa49dbab6d84c676666f3fe7d360497fd65b ] After changes in commit a1bd627b46d1 ("apparmor: share profile name on replacement"), the hname member of struct aa_policy is not valid slab object, but a subset of that, it can not be freed by kfree_sensitive(), use aa_policy_destroy() to fix it. Fixes: a1bd627b46d1 ("apparmor: share profile name on replacement") Signed-off-by: Xiu Jianfeng Signed-off-by: John Johansen Signed-off-by: Sasha Levin --- security/apparmor/policy_ns.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c index 70921d95fb40..53d24cf63893 100644 --- a/security/apparmor/policy_ns.c +++ b/security/apparmor/policy_ns.c @@ -121,7 +121,7 @@ static struct aa_ns *alloc_ns(const char *prefix, const char *name) return ns; fail_unconfined: - kfree_sensitive(ns->base.hname); + aa_policy_destroy(&ns->base); fail_ns: kfree_sensitive(ns); return NULL; From ef8e236832fbd86a9314e13f6f13102da936de85 Mon Sep 17 00:00:00 2001 From: Dongdong Zhang Date: Tue, 25 Oct 2022 17:40:36 +0800 Subject: [PATCH 0379/4345] f2fs: fix normal discard process [ Upstream commit b5f1a218ae5e4339130d6e733f0e63d623e09a2c ] In the DPOLICY_BG mode, there is a conflict between the two conditions "i + 1 < dpolicy->granularity" and "i < DEFAULT_DISCARD_GRANULARITY". If i = 15, the first condition is false, it will enter the second condition and dispatch all small granularity discards in function __issue_discard_cmd_orderly. The restrictive effect of the first condition to small discards will be invalidated. These two conditions should align. Fixes: 20ee4382322c ("f2fs: issue small discard by LBA order") Signed-off-by: Dongdong Zhang Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/segment.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 68774d6198a5..7c90d93f4e43 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1532,7 +1532,7 @@ retry: if (i + 1 < dpolicy->granularity) break; - if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered) + if (i + 1 < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered) return __issue_discard_cmd_orderly(sbi, dpolicy); pend_list = &dcc->pend_list[i]; From 75af03fdf35acf15a3977f7115f6b8d10dff4bc7 Mon Sep 17 00:00:00 2001 From: Bernard Metzler Date: Mon, 7 Nov 2022 15:50:57 +0100 Subject: [PATCH 0380/4345] RDMA/siw: Fix immediate work request flush to completion queue [ Upstream commit bdf1da5df9da680589a7f74448dd0a94dd3e1446 ] Correctly set send queue element opcode during immediate work request flushing in post sendqueue operation, if the QP is in ERROR state. An undefined ocode value results in out-of-bounds access to an array for mapping the opcode between siw internal and RDMA core representation in work completion generation. It resulted in a KASAN BUG report of type 'global-out-of-bounds' during NFSoRDMA testing. This patch further fixes a potential case of a malicious user which may write undefined values for completion queue elements status or opcode, if the CQ is memory mapped to user land. It avoids the same out-of-bounds access to arrays for status and opcode mapping as described above. Fixes: 303ae1cdfdf7 ("rdma/siw: application interface") Fixes: b0fff7317bb4 ("rdma/siw: completion queue methods") Reported-by: Olga Kornievskaia Reviewed-by: Tom Talpey Signed-off-by: Bernard Metzler Link: https://lore.kernel.org/r/20221107145057.895747-1-bmt@zurich.ibm.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/sw/siw/siw_cq.c | 24 ++++++++++++++-- drivers/infiniband/sw/siw/siw_verbs.c | 40 ++++++++++++++++++++++++--- 2 files changed, 58 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_cq.c b/drivers/infiniband/sw/siw/siw_cq.c index d68e37859e73..acc7bcd538b5 100644 --- a/drivers/infiniband/sw/siw/siw_cq.c +++ b/drivers/infiniband/sw/siw/siw_cq.c @@ -56,8 +56,6 @@ int siw_reap_cqe(struct siw_cq *cq, struct ib_wc *wc) if (READ_ONCE(cqe->flags) & SIW_WQE_VALID) { memset(wc, 0, sizeof(*wc)); wc->wr_id = cqe->id; - wc->status = map_cqe_status[cqe->status].ib; - wc->opcode = map_wc_opcode[cqe->opcode]; wc->byte_len = cqe->bytes; /* @@ -71,10 +69,32 @@ int siw_reap_cqe(struct siw_cq *cq, struct ib_wc *wc) wc->wc_flags = IB_WC_WITH_INVALIDATE; } wc->qp = cqe->base_qp; + wc->opcode = map_wc_opcode[cqe->opcode]; + wc->status = map_cqe_status[cqe->status].ib; siw_dbg_cq(cq, "idx %u, type %d, flags %2x, id 0x%pK\n", cq->cq_get % cq->num_cqe, cqe->opcode, cqe->flags, (void *)(uintptr_t)cqe->id); + } else { + /* + * A malicious user may set invalid opcode or + * status in the user mmapped CQE array. + * Sanity check and correct values in that case + * to avoid out-of-bounds access to global arrays + * for opcode and status mapping. + */ + u8 opcode = cqe->opcode; + u16 status = cqe->status; + + if (opcode >= SIW_NUM_OPCODES) { + opcode = 0; + status = IB_WC_GENERAL_ERR; + } else if (status >= SIW_NUM_WC_STATUS) { + status = IB_WC_GENERAL_ERR; + } + wc->opcode = map_wc_opcode[opcode]; + wc->status = map_cqe_status[status].ib; + } WRITE_ONCE(cqe->flags, 0); cq->cq_get++; diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 34e847a91eb8..d043793ff0f5 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -672,13 +672,45 @@ static int siw_copy_inline_sgl(const struct ib_send_wr *core_wr, static int siw_sq_flush_wr(struct siw_qp *qp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { - struct siw_sqe sqe = {}; int rv = 0; while (wr) { - sqe.id = wr->wr_id; - sqe.opcode = wr->opcode; - rv = siw_sqe_complete(qp, &sqe, 0, SIW_WC_WR_FLUSH_ERR); + struct siw_sqe sqe = {}; + + switch (wr->opcode) { + case IB_WR_RDMA_WRITE: + sqe.opcode = SIW_OP_WRITE; + break; + case IB_WR_RDMA_READ: + sqe.opcode = SIW_OP_READ; + break; + case IB_WR_RDMA_READ_WITH_INV: + sqe.opcode = SIW_OP_READ_LOCAL_INV; + break; + case IB_WR_SEND: + sqe.opcode = SIW_OP_SEND; + break; + case IB_WR_SEND_WITH_IMM: + sqe.opcode = SIW_OP_SEND_WITH_IMM; + break; + case IB_WR_SEND_WITH_INV: + sqe.opcode = SIW_OP_SEND_REMOTE_INV; + break; + case IB_WR_LOCAL_INV: + sqe.opcode = SIW_OP_INVAL_STAG; + break; + case IB_WR_REG_MR: + sqe.opcode = SIW_OP_REG_MR; + break; + default: + rv = -EINVAL; + break; + } + if (!rv) { + sqe.id = wr->wr_id; + rv = siw_sqe_complete(qp, &sqe, 0, + SIW_WC_WR_FLUSH_ERR); + } if (rv) { if (bad_wr) *bad_wr = wr; From 237a8936d6213c8af75165aa92394dc902abc368 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Mon, 7 Nov 2022 10:51:36 +0200 Subject: [PATCH 0381/4345] RDMA/nldev: Return "-EAGAIN" if the cm_id isn't from expected port [ Upstream commit ecacb3751f254572af0009b9501e2cdc83a30b6a ] When filling a cm_id entry, return "-EAGAIN" instead of 0 if the cm_id doesn'the have the same port as requested, otherwise an incomplete entry may be returned, which causes "rdam res show cm_id" to return an error. For example on a machine with two rdma devices with "rping -C 1 -v -s" running background, the "rdma" command fails: $ rdma -V rdma utility, iproute2-5.19.0 $ rdma res show cm_id link mlx5_0/- cm-idn 0 state LISTEN ps TCP pid 28056 comm rping src-addr 0.0.0.0:7174 error: Protocol not available While with this fix it succeeds: $ rdma res show cm_id link mlx5_0/- cm-idn 0 state LISTEN ps TCP pid 26395 comm rping src-addr 0.0.0.0:7174 link mlx5_1/- cm-idn 0 state LISTEN ps TCP pid 26395 comm rping src-addr 0.0.0.0:7174 Fixes: 00313983cda6 ("RDMA/nldev: provide detailed CM_ID information") Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/a08e898cdac5e28428eb749a99d9d981571b8ea7.1667810736.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/nldev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index c90f6378d839..f7689bc10d14 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -541,7 +541,7 @@ static int fill_res_cm_id_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_cm_id *cm_id = &id_priv->id; if (port && port != cm_id->port_num) - return 0; + return -EAGAIN; if (cm_id->port_num && nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, cm_id->port_num)) From 917bf4c0a76df2f9b58832a09fc833d27e484469 Mon Sep 17 00:00:00 2001 From: Bernard Metzler Date: Tue, 15 Nov 2022 18:07:47 +0100 Subject: [PATCH 0382/4345] RDMA/siw: Set defined status for work completion with undefined status [ Upstream commit 60da2d11fcbc043304910e4d2ca82f9bab953e63 ] A malicious user may write undefined values into memory mapped completion queue elements status or opcode. Undefined status or opcode values will result in out-of-bounds access to an array mapping siw internal representation of opcode and status to RDMA core representation when reaping CQ elements. While siw detects those undefined values, it did not correctly set completion status to a defined value, thus defeating the whole purpose of the check. This bug leads to the following Smatch static checker warning: drivers/infiniband/sw/siw/siw_cq.c:96 siw_reap_cqe() error: buffer overflow 'map_cqe_status' 10 <= 21 Fixes: bdf1da5df9da ("RDMA/siw: Fix immediate work request flush to completion queue") Link: https://lore.kernel.org/r/20221115170747.1263298-1-bmt@zurich.ibm.com Reported-by: Dan Carpenter Signed-off-by: Bernard Metzler Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/sw/siw/siw_cq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_cq.c b/drivers/infiniband/sw/siw/siw_cq.c index acc7bcd538b5..403029de6b92 100644 --- a/drivers/infiniband/sw/siw/siw_cq.c +++ b/drivers/infiniband/sw/siw/siw_cq.c @@ -88,9 +88,9 @@ int siw_reap_cqe(struct siw_cq *cq, struct ib_wc *wc) if (opcode >= SIW_NUM_OPCODES) { opcode = 0; - status = IB_WC_GENERAL_ERR; + status = SIW_WC_GENERAL_ERR; } else if (status >= SIW_NUM_WC_STATUS) { - status = IB_WC_GENERAL_ERR; + status = SIW_WC_GENERAL_ERR; } wc->opcode = map_wc_opcode[opcode]; wc->status = map_cqe_status[status].ib; From 33260f4c3ed35f0ccf7b995f9b6aa38132186157 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Fri, 11 Nov 2022 02:05:25 -0800 Subject: [PATCH 0383/4345] scsi: scsi_debug: Fix a warning in resp_write_scat() [ Upstream commit 216e179724c1d9f57a8ababf8bd7aaabef67f01b ] As 'lbdof_blen' is coming from user, if the size in kzalloc() is >= MAX_ORDER then we hit a warning. Call trace: sg_ioctl sg_ioctl_common scsi_ioctl sg_scsi_ioctl blk_execute_rq blk_mq_sched_insert_request blk_mq_run_hw_queue __blk_mq_delay_run_hw_queue __blk_mq_run_hw_queue blk_mq_sched_dispatch_requests __blk_mq_sched_dispatch_requests blk_mq_dispatch_rq_list scsi_queue_rq scsi_dispatch_cmd scsi_debug_queuecommand schedule_resp resp_write_scat If you try to allocate a memory larger than(>=) MAX_ORDER, then kmalloc() will definitely fail. It creates a stack trace and messes up dmesg. The user controls the size here so if they specify a too large size it will fail. Add __GFP_NOWARN in order to avoid too large allocation warning. This is detected by static analysis using smatch. Fixes: 481b5e5c7949 ("scsi: scsi_debug: add resp_write_scat function") Signed-off-by: Harshit Mogalapalli Link: https://lore.kernel.org/r/20221111100526.1790533-1-harshit.m.mogalapalli@oracle.com Acked-by: Douglas Gilbert Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index cc20621bb49d..110d0e7f9413 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -3619,7 +3619,7 @@ static int resp_write_scat(struct scsi_cmnd *scp, mk_sense_buffer(scp, ILLEGAL_REQUEST, INVALID_FIELD_IN_CDB, 0); return illegal_condition_result; } - lrdp = kzalloc(lbdof_blen, GFP_ATOMIC); + lrdp = kzalloc(lbdof_blen, GFP_ATOMIC | __GFP_NOWARN); if (lrdp == NULL) return SCSI_MLQUEUE_HOST_BUSY; if (sdebug_verbose) From 1ab9e15b14414670c9dcad5f466de16ea953bfb6 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 8 Nov 2022 16:29:12 +0800 Subject: [PATCH 0384/4345] crypto: ccree - Remove debugfs when platform_driver_register failed [ Upstream commit 4f1c596df706c9aca662b6c214fad84047ae2a97 ] When platform_driver_register failed, we need to remove debugfs, which will caused a resource leak, fix it. Failed logs as follows: [ 32.606488] debugfs: Directory 'ccree' with parent '/' already present! Fixes: 4c3f97276e15 ("crypto: ccree - introduce CryptoCell driver") Signed-off-by: Gaosheng Cui Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/ccree/cc_driver.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c index 6f519d3e896c..7924693f58e0 100644 --- a/drivers/crypto/ccree/cc_driver.c +++ b/drivers/crypto/ccree/cc_driver.c @@ -614,9 +614,17 @@ static struct platform_driver ccree_driver = { static int __init ccree_init(void) { + int rc; + cc_debugfs_global_init(); - return platform_driver_register(&ccree_driver); + rc = platform_driver_register(&ccree_driver); + if (rc) { + cc_debugfs_global_fini(); + return rc; + } + + return 0; } module_init(ccree_init); From 2dfe1d221e1ab6e568b1026c38735d061c2c3cae Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 11 Nov 2022 17:59:17 +0800 Subject: [PATCH 0385/4345] crypto: cryptd - Use request context instead of stack for sub-request [ Upstream commit 3a58c231172537f7b0e19d93ed33decd04f80eab ] cryptd is buggy as it tries to use sync_skcipher without going through the proper sync_skcipher interface. In fact it doesn't even need sync_skcipher since it's already a proper skcipher and can easily access the request context instead of using something off the stack. Fixes: 36b3875a97b8 ("crypto: cryptd - Remove VLA usage of skcipher") Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/cryptd.c | 36 +++++++++++++++++++----------------- 1 file changed, 19 insertions(+), 17 deletions(-) diff --git a/crypto/cryptd.c b/crypto/cryptd.c index 668095eca0fa..ca3a40fc7da9 100644 --- a/crypto/cryptd.c +++ b/crypto/cryptd.c @@ -68,11 +68,12 @@ struct aead_instance_ctx { struct cryptd_skcipher_ctx { refcount_t refcnt; - struct crypto_sync_skcipher *child; + struct crypto_skcipher *child; }; struct cryptd_skcipher_request_ctx { crypto_completion_t complete; + struct skcipher_request req; }; struct cryptd_hash_ctx { @@ -227,13 +228,13 @@ static int cryptd_skcipher_setkey(struct crypto_skcipher *parent, const u8 *key, unsigned int keylen) { struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(parent); - struct crypto_sync_skcipher *child = ctx->child; + struct crypto_skcipher *child = ctx->child; - crypto_sync_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK); - crypto_sync_skcipher_set_flags(child, - crypto_skcipher_get_flags(parent) & - CRYPTO_TFM_REQ_MASK); - return crypto_sync_skcipher_setkey(child, key, keylen); + crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK); + crypto_skcipher_set_flags(child, + crypto_skcipher_get_flags(parent) & + CRYPTO_TFM_REQ_MASK); + return crypto_skcipher_setkey(child, key, keylen); } static void cryptd_skcipher_complete(struct skcipher_request *req, int err) @@ -258,13 +259,13 @@ static void cryptd_skcipher_encrypt(struct crypto_async_request *base, struct cryptd_skcipher_request_ctx *rctx = skcipher_request_ctx(req); struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); - struct crypto_sync_skcipher *child = ctx->child; - SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, child); + struct skcipher_request *subreq = &rctx->req; + struct crypto_skcipher *child = ctx->child; if (unlikely(err == -EINPROGRESS)) goto out; - skcipher_request_set_sync_tfm(subreq, child); + skcipher_request_set_tfm(subreq, child); skcipher_request_set_callback(subreq, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); skcipher_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, @@ -286,13 +287,13 @@ static void cryptd_skcipher_decrypt(struct crypto_async_request *base, struct cryptd_skcipher_request_ctx *rctx = skcipher_request_ctx(req); struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); - struct crypto_sync_skcipher *child = ctx->child; - SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, child); + struct skcipher_request *subreq = &rctx->req; + struct crypto_skcipher *child = ctx->child; if (unlikely(err == -EINPROGRESS)) goto out; - skcipher_request_set_sync_tfm(subreq, child); + skcipher_request_set_tfm(subreq, child); skcipher_request_set_callback(subreq, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); skcipher_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, @@ -343,9 +344,10 @@ static int cryptd_skcipher_init_tfm(struct crypto_skcipher *tfm) if (IS_ERR(cipher)) return PTR_ERR(cipher); - ctx->child = (struct crypto_sync_skcipher *)cipher; + ctx->child = cipher; crypto_skcipher_set_reqsize( - tfm, sizeof(struct cryptd_skcipher_request_ctx)); + tfm, sizeof(struct cryptd_skcipher_request_ctx) + + crypto_skcipher_reqsize(cipher)); return 0; } @@ -353,7 +355,7 @@ static void cryptd_skcipher_exit_tfm(struct crypto_skcipher *tfm) { struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); - crypto_free_sync_skcipher(ctx->child); + crypto_free_skcipher(ctx->child); } static void cryptd_skcipher_free(struct skcipher_instance *inst) @@ -931,7 +933,7 @@ struct crypto_skcipher *cryptd_skcipher_child(struct cryptd_skcipher *tfm) { struct cryptd_skcipher_ctx *ctx = crypto_skcipher_ctx(&tfm->base); - return &ctx->child->base; + return ctx->child; } EXPORT_SYMBOL_GPL(cryptd_skcipher_child); From ed97ade655ea8965dce65c3e2055574cd98b5487 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Fri, 11 Nov 2022 18:00:36 +0800 Subject: [PATCH 0386/4345] crypto: hisilicon/qm - add missing pci_dev_put() in q_num_set() [ Upstream commit cc7710d0d4ebc6998f04035cde4f32c5ddbe9d7f ] pci_get_device() will increase the reference count for the returned pci_dev. We need to use pci_dev_put() to decrease the reference count before q_num_set() returns. Fixes: c8b4b477079d ("crypto: hisilicon - add HiSilicon HPRE accelerator") Signed-off-by: Xiongfeng Wang Reviewed-by: Weili Qian Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/hisilicon/qm.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h index 0420f4ce7197..aaad3d76dc04 100644 --- a/drivers/crypto/hisilicon/qm.h +++ b/drivers/crypto/hisilicon/qm.h @@ -289,14 +289,14 @@ struct hisi_qp { static inline int q_num_set(const char *val, const struct kernel_param *kp, unsigned int device) { - struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, - device, NULL); + struct pci_dev *pdev; u32 n, q_num; int ret; if (!val) return -EINVAL; + pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, device, NULL); if (!pdev) { q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2); pr_info("No device found currently, suppose queue number is %d\n", @@ -306,6 +306,8 @@ static inline int q_num_set(const char *val, const struct kernel_param *kp, q_num = QM_QNUM_V1; else q_num = QM_QNUM_V2; + + pci_dev_put(pdev); } ret = kstrtou32(val, 10, &n); From cc5e9153586ac5d16ca2426da785ffd7641f9de7 Mon Sep 17 00:00:00 2001 From: Luoyouming Date: Thu, 22 Sep 2022 20:33:13 +0800 Subject: [PATCH 0387/4345] RDMA/hns: Repacing 'dseg_len' by macros in fill_ext_sge_inl_data() [ Upstream commit 3b1f864c904915b3baebffb31ea05ee704b0df3c ] The sge size is known to be constant, so it's unnecessary to use sizeof to calculate. Link: https://lore.kernel.org/r/20220922123315.3732205-11-xuhaoyue1@hisilicon.com Signed-off-by: Luoyouming Signed-off-by: Haoyue Xu Signed-off-by: Jason Gunthorpe Stable-dep-of: 8eaa6f7d569b ("RDMA/hns: Fix ext_sge num error when post send") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 6dab03b7aca8..4836090ec817 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -159,8 +159,7 @@ static int fill_ext_sge_inl_data(struct hns_roce_qp *qp, unsigned int *sge_idx, u32 msg_len) { struct ib_device *ibdev = &(to_hr_dev(qp->ibqp.device))->ib_dev; - unsigned int dseg_len = sizeof(struct hns_roce_v2_wqe_data_seg); - unsigned int ext_sge_sz = qp->sq.max_gs * dseg_len; + unsigned int ext_sge_sz = qp->sq.max_gs * HNS_ROCE_SGE_SIZE; unsigned int left_len_in_pg; unsigned int idx = *sge_idx; unsigned int i = 0; @@ -188,7 +187,7 @@ static int fill_ext_sge_inl_data(struct hns_roce_qp *qp, if (len <= left_len_in_pg) { memcpy(dseg, addr, len); - idx += len / dseg_len; + idx += len / HNS_ROCE_SGE_SIZE; i++; if (i >= wr->num_sge) @@ -203,7 +202,7 @@ static int fill_ext_sge_inl_data(struct hns_roce_qp *qp, len -= left_len_in_pg; addr += left_len_in_pg; - idx += left_len_in_pg / dseg_len; + idx += left_len_in_pg / HNS_ROCE_SGE_SIZE; dseg = hns_roce_get_extend_sge(qp, idx & (qp->sge.sge_cnt - 1)); left_len_in_pg = 1 << HNS_HW_PAGE_SHIFT; From 8b5f1af3352aed7a8680506ded4c2b2cf7d8726d Mon Sep 17 00:00:00 2001 From: Luoyouming Date: Tue, 8 Nov 2022 21:38:46 +0800 Subject: [PATCH 0388/4345] RDMA/hns: Fix ext_sge num error when post send [ Upstream commit 8eaa6f7d569b4a22bfc1b0a3fdfeeb401feb65a4 ] In the HNS ROCE driver, The sge is divided into standard sge and extended sge. There are 2 standard sge in RC/XRC, and the UD standard sge is 0. In the scenario of RC SQ inline, if the data does not exceed 32bytes, the standard sge will be used. If it exceeds, only the extended sge will be used to fill the data. Currently, when filling the extended sge, max_gs is directly used as the number of the extended sge, which did not subtract the number of standard sge. There is a logical error. The new algorithm subtracts the number of standard sge from max_gs to get the actual number of extended sge. Fixes: 30b707886aeb ("RDMA/hns: Support inline data in extented sge space for RC") Link: https://lore.kernel.org/r/20221108133847.2304539-2-xuhaoyue1@hisilicon.com Signed-off-by: Luoyouming Signed-off-by: Haoyue Xu Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 4836090ec817..e1395590edfd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -154,20 +154,29 @@ static void set_atomic_seg(const struct ib_send_wr *wr, V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge); } +static unsigned int get_std_sge_num(struct hns_roce_qp *qp) +{ + if (qp->ibqp.qp_type == IB_QPT_GSI || qp->ibqp.qp_type == IB_QPT_UD) + return 0; + + return HNS_ROCE_SGE_IN_WQE; +} + static int fill_ext_sge_inl_data(struct hns_roce_qp *qp, const struct ib_send_wr *wr, unsigned int *sge_idx, u32 msg_len) { struct ib_device *ibdev = &(to_hr_dev(qp->ibqp.device))->ib_dev; - unsigned int ext_sge_sz = qp->sq.max_gs * HNS_ROCE_SGE_SIZE; unsigned int left_len_in_pg; unsigned int idx = *sge_idx; + unsigned int std_sge_num; unsigned int i = 0; unsigned int len; void *addr; void *dseg; - if (msg_len > ext_sge_sz) { + std_sge_num = get_std_sge_num(qp); + if (msg_len > (qp->sq.max_gs - std_sge_num) * HNS_ROCE_SGE_SIZE) { ibdev_err(ibdev, "no enough extended sge space for inline data.\n"); return -EINVAL; From d8f2a0bc52a8cef83cbb74bf26e0ca4d94382154 Mon Sep 17 00:00:00 2001 From: Zeng Heng Date: Mon, 21 Nov 2022 10:00:29 +0800 Subject: [PATCH 0389/4345] PCI: Check for alloc failure in pci_request_irq() [ Upstream commit 2d9cd957d40c3ac491b358e7cff0515bb07a3a9c ] When kvasprintf() fails to allocate memory, it returns a NULL pointer. Return error from pci_request_irq() so we don't dereference it. [bhelgaas: commit log] Fixes: 704e8953d3e9 ("PCI/irq: Add pci_request_irq() and pci_free_irq() helpers") Link: https://lore.kernel.org/r/20221121020029.3759444-1-zengheng4@huawei.com Signed-off-by: Zeng Heng Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/pci/irq.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c index 12ecd0aaa28d..0050e8f6814e 100644 --- a/drivers/pci/irq.c +++ b/drivers/pci/irq.c @@ -44,6 +44,8 @@ int pci_request_irq(struct pci_dev *dev, unsigned int nr, irq_handler_t handler, va_start(ap, fmt); devname = kvasprintf(GFP_KERNEL, fmt, ap); va_end(ap); + if (!devname) + return -ENOMEM; ret = request_threaded_irq(pci_irq_vector(dev, nr), handler, thread_fn, irqflags, devname, dev_id); From 34bab85c2e1f1d8f71443c45b37de5067342767f Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Thu, 17 Nov 2022 21:15:46 +0800 Subject: [PATCH 0390/4345] RDMA/hfi: Decrease PCI device reference count in error path [ Upstream commit 9b51d072da1d27e1193e84708201c48e385ad912 ] pci_get_device() will increase the reference count for the returned pci_dev, and also decrease the reference count for the input parameter *from* if it is not NULL. If we break out the loop in node_affinity_init() with 'dev' not NULL, we need to call pci_dev_put() to decrease the reference count. Add missing pci_dev_put() in error path. Fixes: c513de490f80 ("IB/hfi1: Invalid NUMA node information can cause a divide by zero") Signed-off-by: Xiongfeng Wang Link: https://lore.kernel.org/r/20221117131546.113280-1-wangxiongfeng2@huawei.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/affinity.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 04b1e8f021f6..d5a8d0173709 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -219,6 +219,8 @@ out: for (node = 0; node < node_affinity.num_possible_nodes; node++) hfi1_per_node_cntr[node] = 1; + pci_dev_put(dev); + return 0; } From 3d47544ba0c723f3844e41d286b30040b4c84651 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 21 Nov 2022 18:22:36 +0100 Subject: [PATCH 0391/4345] crypto: ccree - Make cc_debugfs_global_fini() available for module init function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8e96729fc26c8967db45a3fb7a60387619f77a22 ] ccree_init() calls cc_debugfs_global_fini(), the former is an init function and the latter an exit function though. A modular build emits: WARNING: modpost: drivers/crypto/ccree/ccree.o: section mismatch in reference: init_module (section: .init.text) -> cc_debugfs_global_fini (section: .exit.text) (with CONFIG_DEBUG_SECTION_MISMATCH=y). Fixes: 4f1c596df706 ("crypto: ccree - Remove debugfs when platform_driver_register failed") Signed-off-by: Uwe Kleine-König Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/ccree/cc_debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/ccree/cc_debugfs.c b/drivers/crypto/ccree/cc_debugfs.c index 7083767602fc..8f008f024f8f 100644 --- a/drivers/crypto/ccree/cc_debugfs.c +++ b/drivers/crypto/ccree/cc_debugfs.c @@ -55,7 +55,7 @@ void __init cc_debugfs_global_init(void) cc_debugfs_dir = debugfs_create_dir("ccree", NULL); } -void __exit cc_debugfs_global_fini(void) +void cc_debugfs_global_fini(void) { debugfs_remove(cc_debugfs_dir); } From 164fa80330a81db67c26d10d071083941d29a510 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Sat, 19 Nov 2022 15:08:34 +0800 Subject: [PATCH 0392/4345] RDMA/hns: fix memory leak in hns_roce_alloc_mr() [ Upstream commit a115aa00b18f7b8982b8f458149632caf64a862a ] When hns_roce_mr_enable() failed in hns_roce_alloc_mr(), mr_key is not released. Compiled test only. Fixes: 9b2cf76c9f05 ("RDMA/hns: Optimize PBL buffer allocation process") Signed-off-by: Zhengchao Shao Link: https://lore.kernel.org/r/20221119070834.48502-1-shaozhengchao@huawei.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_mr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 6d7cc724862f..1c342a7bd7df 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -456,10 +456,10 @@ struct ib_mr *hns_roce_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, return &mr->ibmr; -err_key: - free_mr_key(hr_dev, mr); err_pbl: free_mr_pbl(hr_dev, mr); +err_key: + free_mr_key(hr_dev, mr); err_free: kfree(mr); return ERR_PTR(ret); From 6bb5a62bfd624039b05157745c234068508393a9 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Tue, 22 Nov 2022 23:14:37 +0800 Subject: [PATCH 0393/4345] RDMA/rxe: Fix NULL-ptr-deref in rxe_qp_do_cleanup() when socket create failed [ Upstream commit f67376d801499f4fa0838c18c1efcad8840e550d ] There is a null-ptr-deref when mount.cifs over rdma: BUG: KASAN: null-ptr-deref in rxe_qp_do_cleanup+0x2f3/0x360 [rdma_rxe] Read of size 8 at addr 0000000000000018 by task mount.cifs/3046 CPU: 2 PID: 3046 Comm: mount.cifs Not tainted 6.1.0-rc5+ #62 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc3 Call Trace: dump_stack_lvl+0x34/0x44 kasan_report+0xad/0x130 rxe_qp_do_cleanup+0x2f3/0x360 [rdma_rxe] execute_in_process_context+0x25/0x90 __rxe_cleanup+0x101/0x1d0 [rdma_rxe] rxe_create_qp+0x16a/0x180 [rdma_rxe] create_qp.part.0+0x27d/0x340 ib_create_qp_kernel+0x73/0x160 rdma_create_qp+0x100/0x230 _smbd_get_connection+0x752/0x20f0 smbd_get_connection+0x21/0x40 cifs_get_tcp_session+0x8ef/0xda0 mount_get_conns+0x60/0x750 cifs_mount+0x103/0xd00 cifs_smb3_do_mount+0x1dd/0xcb0 smb3_get_tree+0x1d5/0x300 vfs_get_tree+0x41/0xf0 path_mount+0x9b3/0xdd0 __x64_sys_mount+0x190/0x1d0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 The root cause of the issue is the socket create failed in rxe_qp_init_req(). So move the reset rxe_qp_do_cleanup() after the NULL ptr check. Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://lore.kernel.org/r/20221122151437.1057671-1-zhangxiaoxu5@huawei.com Signed-off-by: Zhang Xiaoxu Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/sw/rxe/rxe_qp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 2e4b008f0387..99c1b3553e6e 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -812,12 +812,12 @@ static void rxe_qp_do_cleanup(struct work_struct *work) qp->resp.mr = NULL; } - if (qp_type(qp) == IB_QPT_RC) - sk_dst_reset(qp->sk->sk); - free_rd_atomic_resources(qp); if (qp->sk) { + if (qp_type(qp) == IB_QPT_RC) + sk_dst_reset(qp->sk->sk); + kernel_sock_shutdown(qp->sk, SHUT_RDWR); sock_release(qp->sk); } From c808edbf580bfc454671cbe66e9d7c2e938e7601 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Tue, 22 Nov 2022 01:57:51 +0000 Subject: [PATCH 0394/4345] scsi: hpsa: Fix possible memory leak in hpsa_init_one() [ Upstream commit 9c9ff300e0de07475796495d86f449340d454a0c ] The hpda_alloc_ctlr_info() allocates h and its field reply_map. However, in hpsa_init_one(), if alloc_percpu() failed, the hpsa_init_one() jumps to clean1 directly, which frees h and leaks the h->reply_map. Fix by calling hpda_free_ctlr_info() to release h->replay_map and h instead free h directly. Fixes: 8b834bff1b73 ("scsi: hpsa: fix selection of reply queue") Signed-off-by: Yuan Can Link: https://lore.kernel.org/r/20221122015751.87284-1-yuancan@huawei.com Reviewed-by: Ming Lei Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hpsa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 8df70c92911d..cd78d77911cd 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -8904,7 +8904,7 @@ clean1: /* wq/aer/h */ destroy_workqueue(h->monitor_ctlr_wq); h->monitor_ctlr_wq = NULL; } - kfree(h); + hpda_free_ctlr_info(h); return rc; } From 4a99e6a1049cad270a9c7a8608d063f9f1df1abf Mon Sep 17 00:00:00 2001 From: Zhang Yiqun Date: Wed, 16 Nov 2022 17:24:11 +0800 Subject: [PATCH 0395/4345] crypto: tcrypt - Fix multibuffer skcipher speed test mem leak [ Upstream commit 1aa33fc8d4032227253ceb736f47c52b859d9683 ] In the past, the data for mb-skcipher test has been allocated twice, that means the first allcated memory area is without free, which may cause a potential memory leakage. So this patch is to remove one allocation to fix this error. Fixes: e161c5930c15 ("crypto: tcrypt - add multibuf skcipher...") Signed-off-by: Zhang Yiqun Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/tcrypt.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index 8609174e036e..7972d2784b3b 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -1282,15 +1282,6 @@ static void test_mb_skcipher_speed(const char *algo, int enc, int secs, goto out_free_tfm; } - - for (i = 0; i < num_mb; ++i) - if (testmgr_alloc_buf(data[i].xbuf)) { - while (i--) - testmgr_free_buf(data[i].xbuf); - goto out_free_tfm; - } - - for (i = 0; i < num_mb; ++i) { data[i].req = skcipher_request_alloc(tfm, GFP_KERNEL); if (!data[i].req) { From 8e0681dd4eee029eb1d533d06993f7cb091efb73 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 16 Nov 2022 20:28:02 -0500 Subject: [PATCH 0396/4345] padata: Always leave BHs disabled when running ->parallel() [ Upstream commit 34c3a47d20ae55b3600fed733bf96eafe9c500d5 ] A deadlock can happen when an overloaded system runs ->parallel() in the context of the current task: padata_do_parallel ->parallel() pcrypt_aead_enc/dec padata_do_serial spin_lock(&reorder->lock) // BHs still enabled ... __do_softirq ... padata_do_serial spin_lock(&reorder->lock) It's a bug for BHs to be on in _do_serial as Steffen points out, so ensure they're off in the "current task" case like they are in padata_parallel_worker to avoid this situation. Reported-by: syzbot+bc05445bc14148d51915@syzkaller.appspotmail.com Fixes: 4611ce224688 ("padata: allocate work structures for parallel jobs from a pool") Signed-off-by: Daniel Jordan Acked-by: Steffen Klassert Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- kernel/padata.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/kernel/padata.c b/kernel/padata.c index d4d3ba6e1728..4d31a69a9b38 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -220,14 +220,16 @@ int padata_do_parallel(struct padata_shell *ps, pw = padata_work_alloc(); spin_unlock(&padata_works_lock); + if (!pw) { + /* Maximum works limit exceeded, run in the current task. */ + padata->parallel(padata); + } + rcu_read_unlock_bh(); if (pw) { padata_work_init(pw, padata_parallel_worker, padata, 0); queue_work(pinst->parallel_wq, &pw->pw_work); - } else { - /* Maximum works limit exceeded, run in the current task. */ - padata->parallel(padata); } return 0; From 7ccfc2bb587941dd569122913daa1252e2612631 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Wed, 16 Nov 2022 20:28:04 -0500 Subject: [PATCH 0397/4345] padata: Fix list iterator in padata_do_serial() [ Upstream commit 57ddfecc72a6c9941d159543e1c0c0a74fe9afdd ] list_for_each_entry_reverse() assumes that the iterated list is nonempty and that every list_head is embedded in the same type, but its use in padata_do_serial() breaks both rules. This doesn't cause any issues now because padata_priv and padata_list happen to have their list fields at the same offset, but we really shouldn't be relying on that. Fixes: bfde23ce200e ("padata: unbind parallel jobs from specific CPUs") Signed-off-by: Daniel Jordan Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- kernel/padata.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/kernel/padata.c b/kernel/padata.c index 4d31a69a9b38..11ca3ebd8b12 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -403,13 +403,16 @@ void padata_do_serial(struct padata_priv *padata) int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr); struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu); struct padata_priv *cur; + struct list_head *pos; spin_lock(&reorder->lock); /* Sort in ascending order of sequence number. */ - list_for_each_entry_reverse(cur, &reorder->list, list) + list_for_each_prev(pos, &reorder->list) { + cur = list_entry(pos, struct padata_priv, list); if (cur->seq_nr < padata->seq_nr) break; - list_add(&padata->list, &cur->list); + } + list_add(&padata->list, pos); spin_unlock(&reorder->lock); /* From ce1a69cc85006b494353911b35171da195d79e25 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 9 Nov 2022 11:24:03 +0800 Subject: [PATCH 0398/4345] scsi: mpt3sas: Fix possible resource leaks in mpt3sas_transport_port_add() [ Upstream commit 78316e9dfc24906dd474630928ed1d3c562b568e ] In mpt3sas_transport_port_add(), if sas_rphy_add() returns error, sas_rphy_free() needs be called to free the resource allocated in sas_end_device_alloc(). Otherwise a kernel crash will happen: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000108 CPU: 45 PID: 37020 Comm: bash Kdump: loaded Tainted: G W 6.1.0-rc1+ #189 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : device_del+0x54/0x3d0 lr : device_del+0x37c/0x3d0 Call trace: device_del+0x54/0x3d0 attribute_container_class_device_del+0x28/0x38 transport_remove_classdev+0x6c/0x80 attribute_container_device_trigger+0x108/0x110 transport_remove_device+0x28/0x38 sas_rphy_remove+0x50/0x78 [scsi_transport_sas] sas_port_delete+0x30/0x148 [scsi_transport_sas] do_sas_phy_delete+0x78/0x80 [scsi_transport_sas] device_for_each_child+0x68/0xb0 sas_remove_children+0x30/0x50 [scsi_transport_sas] sas_rphy_remove+0x38/0x78 [scsi_transport_sas] sas_port_delete+0x30/0x148 [scsi_transport_sas] do_sas_phy_delete+0x78/0x80 [scsi_transport_sas] device_for_each_child+0x68/0xb0 sas_remove_children+0x30/0x50 [scsi_transport_sas] sas_remove_host+0x20/0x38 [scsi_transport_sas] scsih_remove+0xd8/0x420 [mpt3sas] Because transport_add_device() is not called when sas_rphy_add() fails, the device is not added. When sas_rphy_remove() is subsequently called to remove the device in the remove() path, a NULL pointer dereference happens. Fixes: f92363d12359 ("[SCSI] mpt3sas: add new driver supporting 12GB SAS") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221109032403.1636422-1-yangyingliang@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_transport.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c index 6ec5b7f33dfd..b58f4d9c296a 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_transport.c +++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c @@ -712,6 +712,8 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle, if ((sas_rphy_add(rphy))) { ioc_err(ioc, "failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); + sas_rphy_free(rphy); + rphy = NULL; } if (mpt3sas_port->remote_identify.device_type == SAS_END_DEVICE) { From f671a3f2869d31ec81912f1d1d9f628d4d46e011 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 10 Nov 2022 23:11:29 +0800 Subject: [PATCH 0399/4345] scsi: hpsa: Fix error handling in hpsa_add_sas_host() [ Upstream commit 4ef174a3ad9b5d73c1b6573e244ebba2b0d86eac ] hpsa_sas_port_add_phy() does: ... sas_phy_add() -> may return error here sas_port_add_phy() ... Whereas hpsa_free_sas_phy() does: ... sas_port_delete_phy() sas_phy_delete() ... If hpsa_sas_port_add_phy() returns an error, hpsa_free_sas_phy() can not be called to free the memory because the port and the phy have not been added yet. Replace hpsa_free_sas_phy() with sas_phy_free() and kfree() to avoid kernel crash in this case. Fixes: d04e62b9d63a ("hpsa: add in sas transport class") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221110151129.394389-1-yangyingliang@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hpsa.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index cd78d77911cd..48be84b4e95c 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -9764,7 +9764,8 @@ static int hpsa_add_sas_host(struct ctlr_info *h) return 0; free_sas_phy: - hpsa_free_sas_phy(hpsa_sas_phy); + sas_phy_free(hpsa_sas_phy->phy); + kfree(hpsa_sas_phy); free_sas_port: hpsa_free_sas_port(hpsa_sas_port); free_sas_node: From ac5cfe8bbbf91b99838e1996faa661295e59830d Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 11 Nov 2022 12:30:12 +0800 Subject: [PATCH 0400/4345] scsi: hpsa: Fix possible memory leak in hpsa_add_sas_device() [ Upstream commit fda34a5d304d0b98cc967e8763b52221b66dc202 ] If hpsa_sas_port_add_rphy() returns an error, the 'rphy' allocated in sas_end_device_alloc() needs to be freed. Address this by calling sas_rphy_free() in the error path. Fixes: d04e62b9d63a ("hpsa: add in sas transport class") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221111043012.1074466-1-yangyingliang@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hpsa.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 48be84b4e95c..b2d4b6c78b5c 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -9801,10 +9801,12 @@ static int hpsa_add_sas_device(struct hpsa_sas_node *hpsa_sas_node, rc = hpsa_sas_port_add_rphy(hpsa_sas_port, rphy); if (rc) - goto free_sas_port; + goto free_sas_rphy; return 0; +free_sas_rphy: + sas_rphy_free(rphy); free_sas_port: hpsa_free_sas_port(hpsa_sas_port); device->sas_port = NULL; From eaa71cdae88abc75281f6116bf6ff69e432713cb Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Fri, 11 Nov 2022 23:00:31 -0800 Subject: [PATCH 0401/4345] scsi: scsi_debug: Fix a warning in resp_verify() [ Upstream commit ed0f17b748b20271cb568c7ca0b23b120316a47d ] As 'vnum' is controlled by user, so if user tries to allocate memory larger than(>=) MAX_ORDER, then kcalloc() will fail, it creates a stack trace and messes up dmesg with a warning. Add __GFP_NOWARN in order to avoid too large allocation warning. This is detected by static analysis using smatch. Fixes: c3e2fe9222d4 ("scsi: scsi_debug: Implement VERIFY(10), add VERIFY(16)") Signed-off-by: Harshit Mogalapalli Link: https://lore.kernel.org/r/20221112070031.2121068-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 110d0e7f9413..cdbcb5eaf279 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -4275,7 +4275,7 @@ static int resp_verify(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) if (ret) return ret; - arr = kcalloc(lb_size, vnum, GFP_ATOMIC); + arr = kcalloc(lb_size, vnum, GFP_ATOMIC | __GFP_NOWARN); if (!arr) { mk_sense_buffer(scp, ILLEGAL_REQUEST, INSUFF_RES_ASC, INSUFF_RES_ASCQ); From 2b142f6046ceb19e35ea77b9ad4578f19d751eb9 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Fri, 11 Nov 2022 23:06:12 -0800 Subject: [PATCH 0402/4345] scsi: scsi_debug: Fix a warning in resp_report_zones() [ Upstream commit 07f2ca139d9a7a1ba71c4c03997c8de161db2346 ] As 'alloc_len' is user controlled data, if user tries to allocate memory larger than(>=) MAX_ORDER, then kcalloc() will fail, it creates a stack trace and messes up dmesg with a warning. Add __GFP_NOWARN in order to avoid too large allocation warning. This is detected by static analysis using smatch. Fixes: 7db0e0c8190a ("scsi: scsi_debug: Fix buffer size of REPORT ZONES command") Signed-off-by: Harshit Mogalapalli Link: https://lore.kernel.org/r/20221112070612.2121535-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index cdbcb5eaf279..bd63357f439d 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -4346,7 +4346,7 @@ static int resp_report_zones(struct scsi_cmnd *scp, rep_max_zones = min((alloc_len - 64) >> ilog2(RZONES_DESC_HD), max_zones); - arr = kzalloc(alloc_len, GFP_ATOMIC); + arr = kzalloc(alloc_len, GFP_ATOMIC | __GFP_NOWARN); if (!arr) { mk_sense_buffer(scp, ILLEGAL_REQUEST, INSUFF_RES_ASC, INSUFF_RES_ASCQ); From 9d0ad1e2bae72ae7f97d5374bb2d7b46c5ca7bd6 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Sat, 12 Nov 2022 17:43:10 +0800 Subject: [PATCH 0403/4345] scsi: fcoe: Fix possible name leak when device_register() fails [ Upstream commit 47b6a122c7b69a876c7ee2fc064a26b09627de9d ] If device_register() returns an error, the name allocated by dev_set_name() needs to be freed. As the comment of device_register() says, one should use put_device() to give up the reference in the error path. Fix this by calling put_device(), then the name can be freed in kobject_cleanup(). The 'fcf' is freed in fcoe_fcf_device_release(), so the kfree() in the error path can be removed. The 'ctlr' is freed in fcoe_ctlr_device_release(), so don't use the error label, just return NULL after calling put_device(). Fixes: 9a74e884ee71 ("[SCSI] libfcoe: Add fcoe_sysfs") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221112094310.3633291-1-yangyingliang@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/fcoe/fcoe_sysfs.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/fcoe/fcoe_sysfs.c b/drivers/scsi/fcoe/fcoe_sysfs.c index ffef2c8eddc6..68d8027d5108 100644 --- a/drivers/scsi/fcoe/fcoe_sysfs.c +++ b/drivers/scsi/fcoe/fcoe_sysfs.c @@ -830,14 +830,15 @@ struct fcoe_ctlr_device *fcoe_ctlr_device_add(struct device *parent, dev_set_name(&ctlr->dev, "ctlr_%d", ctlr->id); error = device_register(&ctlr->dev); - if (error) - goto out_del_q2; + if (error) { + destroy_workqueue(ctlr->devloss_work_q); + destroy_workqueue(ctlr->work_q); + put_device(&ctlr->dev); + return NULL; + } return ctlr; -out_del_q2: - destroy_workqueue(ctlr->devloss_work_q); - ctlr->devloss_work_q = NULL; out_del_q: destroy_workqueue(ctlr->work_q); ctlr->work_q = NULL; @@ -1036,16 +1037,16 @@ struct fcoe_fcf_device *fcoe_fcf_device_add(struct fcoe_ctlr_device *ctlr, fcf->selected = new_fcf->selected; error = device_register(&fcf->dev); - if (error) - goto out_del; + if (error) { + put_device(&fcf->dev); + goto out; + } fcf->state = FCOE_FCF_STATE_CONNECTED; list_add_tail(&fcf->peers, &ctlr->fcfs); return fcf; -out_del: - kfree(fcf); out: return NULL; } From b520a32796812a7fa343931f4f015b47620a8e71 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Sat, 12 Nov 2022 21:10:10 +0800 Subject: [PATCH 0404/4345] scsi: scsi_debug: Fix possible name leak in sdebug_add_host_helper() [ Upstream commit e6d773f93a49e0eda88a903a2a6542ca83380eb1 ] Afer commit 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array"), the name of device is allocated dynamically, it needs be freed when device_register() returns error. As comment of device_register() says, one should use put_device() to give up the reference in the error path. Fix this by calling put_device(), then the name can be freed in kobject_cleanup(), and sdbg_host is freed in sdebug_release_adapter(). When the device release is not set, it means the device is not initialized. We can not call put_device() in this case. Use kfree() to free memory. Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221112131010.3757845-1-yangyingliang@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_debug.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index bd63357f439d..7cfc6db81763 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -7103,7 +7103,10 @@ clean: kfree(sdbg_devinfo->zstate); kfree(sdbg_devinfo); } - kfree(sdbg_host); + if (sdbg_host->dev.release) + put_device(&sdbg_host->dev); + else + kfree(sdbg_host); pr_warn("%s: failed, errno=%d\n", __func__, -error); return error; } From f4ba143b04a17559f2c85e18b47db117f40d8cf3 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Sun, 13 Nov 2022 14:45:13 +0800 Subject: [PATCH 0405/4345] scsi: ipr: Fix WARNING in ipr_init() [ Upstream commit e6f108bffc3708ddcff72324f7d40dfcd0204894 ] ipr_init() will not call unregister_reboot_notifier() when pci_register_driver() fails, which causes a WARNING. Call unregister_reboot_notifier() when pci_register_driver() fails. notifier callback ipr_halt [ipr] already registered WARNING: CPU: 3 PID: 299 at kernel/notifier.c:29 notifier_chain_register+0x16d/0x230 Modules linked in: ipr(+) xhci_pci_renesas xhci_hcd ehci_hcd usbcore led_class gpu_sched drm_buddy video wmi drm_ttm_helper ttm drm_display_helper drm_kms_helper drm drm_panel_orientation_quirks agpgart cfbft CPU: 3 PID: 299 Comm: modprobe Tainted: G W 6.1.0-rc1-00190-g39508d23b672-dirty #332 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 RIP: 0010:notifier_chain_register+0x16d/0x230 Call Trace: __blocking_notifier_chain_register+0x73/0xb0 ipr_init+0x30/0x1000 [ipr] do_one_initcall+0xdb/0x480 do_init_module+0x1cf/0x680 load_module+0x6a50/0x70a0 __do_sys_finit_module+0x12f/0x1c0 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: f72919ec2bbb ("[SCSI] ipr: implement shutdown changes and remove obsolete write cache parameter") Signed-off-by: Shang XiaoJing Link: https://lore.kernel.org/r/20221113064513.14028-1-shangxiaojing@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/ipr.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 90e8a538b078..a5e6fbd86ad4 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -10870,11 +10870,19 @@ static struct notifier_block ipr_notifier = { **/ static int __init ipr_init(void) { + int rc; + ipr_info("IBM Power RAID SCSI Device Driver version: %s %s\n", IPR_DRIVER_VERSION, IPR_DRIVER_DATE); register_reboot_notifier(&ipr_notifier); - return pci_register_driver(&ipr_driver); + rc = pci_register_driver(&ipr_driver); + if (rc) { + unregister_reboot_notifier(&ipr_notifier); + return rc; + } + + return 0; } /** From 22e8c7a56bb1cd2ed0beaaccb34282ac9cbbe27e Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Tue, 15 Nov 2022 17:24:42 +0800 Subject: [PATCH 0406/4345] scsi: fcoe: Fix transport not deattached when fcoe_if_init() fails [ Upstream commit 4155658cee394b22b24c6d64e49247bf26d95b92 ] fcoe_init() calls fcoe_transport_attach(&fcoe_sw_transport), but when fcoe_if_init() fails, &fcoe_sw_transport is not detached and leaves freed &fcoe_sw_transport on fcoe_transports list. This causes panic when reinserting module. BUG: unable to handle page fault for address: fffffbfff82e2213 RIP: 0010:fcoe_transport_attach+0xe1/0x230 [libfcoe] Call Trace: do_one_initcall+0xd0/0x4e0 load_module+0x5eee/0x7210 ... Fixes: 78a582463c1e ("[SCSI] fcoe: convert fcoe.ko to become an fcoe transport provider driver") Signed-off-by: Chen Zhongjin Link: https://lore.kernel.org/r/20221115092442.133088-1-chenzhongjin@huawei.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/fcoe/fcoe.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 0f9274960dc6..30afcbbe1f86 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -2504,6 +2504,7 @@ static int __init fcoe_init(void) out_free: mutex_unlock(&fcoe_config_mutex); + fcoe_transport_detach(&fcoe_sw_transport); out_destroy: destroy_workqueue(fcoe_wq); return rc; From ad27f74e901fc48729733c88818e6b96c813057d Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 17 Nov 2022 11:51:00 +0800 Subject: [PATCH 0407/4345] scsi: snic: Fix possible UAF in snic_tgt_create() [ Upstream commit e118df492320176af94deec000ae034cc92be754 ] Smatch reports a warning as follows: drivers/scsi/snic/snic_disc.c:307 snic_tgt_create() warn: '&tgt->list' not removed from list If device_add() fails in snic_tgt_create(), tgt will be freed, but tgt->list will not be removed from snic->disc.tgt_list, then list traversal may cause UAF. Remove from snic->disc.tgt_list before free(). Fixes: c8806b6c9e82 ("snic: driver for Cisco SCSI HBA") Signed-off-by: Gaosheng Cui Link: https://lore.kernel.org/r/20221117035100.2944812-1-cuigaosheng1@huawei.com Acked-by: Narsimhulu Musini Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/snic/snic_disc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/snic/snic_disc.c b/drivers/scsi/snic/snic_disc.c index e9ccfb97773f..7cf871323b2c 100644 --- a/drivers/scsi/snic/snic_disc.c +++ b/drivers/scsi/snic/snic_disc.c @@ -318,6 +318,9 @@ snic_tgt_create(struct snic *snic, struct snic_tgt_id *tgtid) ret); put_device(&snic->shost->shost_gendev); + spin_lock_irqsave(snic->shost->host_lock, flags); + list_del(&tgt->list); + spin_unlock_irqrestore(snic->shost->host_lock, flags); kfree(tgt); tgt = NULL; From d1b85d28834573681dd60cdcdf5dfdcb4f022b67 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Sat, 26 Nov 2022 04:34:10 +0000 Subject: [PATCH 0408/4345] RDMA/nldev: Add checks for nla_nest_start() in fill_stat_counter_qps() [ Upstream commit ea5ef136e215fdef35f14010bc51fcd6686e6922 ] As the nla_nest_start() may fail with NULL returned, the return value needs to be checked. Fixes: c4ffee7c9bdb ("RDMA/netlink: Implement counter dumpit calback") Signed-off-by: Yuan Can Link: https://lore.kernel.org/r/20221126043410.85632-1-yuancan@huawei.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/nldev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index f7689bc10d14..78534340d282 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -754,6 +754,8 @@ static int fill_stat_counter_qps(struct sk_buff *msg, int ret = 0; table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP); + if (!table_attr) + return -EMSGSIZE; rt = &counter->device->res[RDMA_RESTRACK_QP]; xa_lock(&rt->xa); From 25a8dabaabf6d2937ed43460d76c6cc2cd83cd55 Mon Sep 17 00:00:00 2001 From: Yonggil Song Date: Tue, 22 Nov 2022 18:03:20 +0900 Subject: [PATCH 0409/4345] f2fs: avoid victim selection from previous victim section [ Upstream commit e219aecfd4b766c4e878a3769057e9809f7fcadc ] When f2fs chooses GC victim in large section & LFS mode, next_victim_seg[gc_type] is referenced first. After segment is freed, next_victim_seg[gc_type] has the next segment number. However, next_victim_seg[gc_type] still has the last segment number even after the last segment of section is freed. In this case, when f2fs chooses a victim for the next GC round, the last segment of previous victim section is chosen as a victim. Initialize next_victim_seg[gc_type] to NULL_SEGNO for the last segment in large section. Fixes: e3080b0120a1 ("f2fs: support subsectional garbage collection") Signed-off-by: Yonggil Song Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/gc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 5ac0b605335f..89156568a4fb 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1649,8 +1649,9 @@ freed: get_valid_blocks(sbi, segno, false) == 0) seg_freed++; - if (__is_large_section(sbi) && segno + 1 < end_segno) - sbi->next_victim_seg[gc_type] = segno + 1; + if (__is_large_section(sbi)) + sbi->next_victim_seg[gc_type] = + (segno + 1 < end_segno) ? segno + 1 : NULL_SEGNO; skip: f2fs_put_page(sum_page, 0); } From 357f3e1756309a7fd43999cd51691d4275b98064 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Mon, 28 Nov 2022 13:52:46 +0200 Subject: [PATCH 0410/4345] RDMA/nldev: Fix failure to send large messages [ Upstream commit fc8f93ad3e5485d45c992233c96acd902992dfc4 ] Return "-EMSGSIZE" instead of "-EINVAL" when filling a QP entry, so that new SKBs will be allocated if there's not enough room in current SKB. Fixes: 65959522f806 ("RDMA: Add support to dump resource tracker in RAW format") Signed-off-by: Mark Zhang Reviewed-by: Patrisious Haddad Link: https://lore.kernel.org/r/b5e9c62f6b8369acab5648b661bf539cbceeffdc.1669636336.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/nldev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 78534340d282..f7f80707af4b 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -502,7 +502,7 @@ static int fill_res_qp_entry(struct sk_buff *msg, bool has_cap_net_admin, /* In create_qp() port is not set yet */ if (qp->port && nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, qp->port)) - return -EINVAL; + return -EMSGSIZE; ret = nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qp->qp_num); if (ret) From 75c7b5d6b53497e6dc0e1158f9c96f43f1654f72 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 22 Nov 2022 22:56:19 +0100 Subject: [PATCH 0411/4345] crypto: amlogic - Remove kcalloc without check [ Upstream commit 3d780c8a9850ad60dee47a8d971ba7888f3d1bd3 ] There is no real point in allocating dedicated memory for the irqs array. MAXFLOW is only 2, so it is easier to allocated the needed space directly within the 'meson_dev' structure. This saves some memory allocation and avoids an indirection when using the irqs array. Fixes: 48fe583fe541 ("crypto: amlogic - Add crypto accelerator...") Signed-off-by: Christophe JAILLET Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/amlogic/amlogic-gxl-core.c | 1 - drivers/crypto/amlogic/amlogic-gxl.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/crypto/amlogic/amlogic-gxl-core.c b/drivers/crypto/amlogic/amlogic-gxl-core.c index 5bbeff433c8c..7a5cf1122af9 100644 --- a/drivers/crypto/amlogic/amlogic-gxl-core.c +++ b/drivers/crypto/amlogic/amlogic-gxl-core.c @@ -240,7 +240,6 @@ static int meson_crypto_probe(struct platform_device *pdev) return err; } - mc->irqs = devm_kcalloc(mc->dev, MAXFLOW, sizeof(int), GFP_KERNEL); for (i = 0; i < MAXFLOW; i++) { mc->irqs[i] = platform_get_irq(pdev, i); if (mc->irqs[i] < 0) diff --git a/drivers/crypto/amlogic/amlogic-gxl.h b/drivers/crypto/amlogic/amlogic-gxl.h index dc0f142324a3..8c0746a1d6d4 100644 --- a/drivers/crypto/amlogic/amlogic-gxl.h +++ b/drivers/crypto/amlogic/amlogic-gxl.h @@ -95,7 +95,7 @@ struct meson_dev { struct device *dev; struct meson_flow *chanlist; atomic_t flow; - int *irqs; + int irqs[MAXFLOW]; #ifdef CONFIG_CRYPTO_DEV_AMLOGIC_GXL_DEBUG struct dentry *dbgfs_dir; #endif From 09814c669d18d0478ea00aaab71bd3d12006543e Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Thu, 24 Nov 2022 14:49:40 +0800 Subject: [PATCH 0412/4345] crypto: omap-sham - Use pm_runtime_resume_and_get() in omap_sham_probe() [ Upstream commit 7bcceb4c9896b1b672b636ae70fe75110d6bf1ad ] omap_sham_probe() calls pm_runtime_get_sync() and calls pm_runtime_put_sync() latter to put usage_counter. However, pm_runtime_get_sync() will increment usage_counter even it failed. Fix it by replacing it with pm_runtime_resume_and_get() to keep usage counter balanced. Fixes: b359f034c8bf ("crypto: omap-sham - Convert to use pm_runtime API") Signed-off-by: Shang XiaoJing Acked-by: Mark Greer Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/omap-sham.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c index 48f78e34cf8d..5a57617441b8 100644 --- a/drivers/crypto/omap-sham.c +++ b/drivers/crypto/omap-sham.c @@ -2130,7 +2130,7 @@ static int omap_sham_probe(struct platform_device *pdev) pm_runtime_enable(dev); pm_runtime_irq_safe(dev); - err = pm_runtime_get_sync(dev); + err = pm_runtime_resume_and_get(dev); if (err < 0) { dev_err(dev, "failed to get sync: %d\n", err); goto err_pm; From 61c5b47c5b2826f46abc3a06ad03ab274c0a6dcc Mon Sep 17 00:00:00 2001 From: Tong Tiangen Date: Mon, 24 Oct 2022 09:47:25 +0000 Subject: [PATCH 0413/4345] riscv/mm: add arch hook arch_clear_hugepage_flags [ Upstream commit d8bf77a1dc3079692f54be3087a5fd16d90027b0 ] With the PG_arch_1 we keep track if the page's data cache is clean, architecture rely on this property to treat new pages as dirty with respect to the data cache and perform the flushing before mapping the pages into userspace. This patch adds a new architecture hook, arch_clear_hugepage_flags,so that architectures which rely on the page flags being in a particular state for fresh allocations can adjust the flags accordingly when a page is freed into the pool. Fixes: 9e953cda5cdf ("riscv: Introduce huge page support for 32/64bit kernel") Signed-off-by: Tong Tiangen Link: https://lore.kernel.org/r/20221024094725.3054311-3-tongtiangen@huawei.com Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/include/asm/hugetlb.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index a5c2ca1d1cd8..ec19d6afc896 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -5,4 +5,10 @@ #include #include +static inline void arch_clear_hugepage_flags(struct page *page) +{ + clear_bit(PG_dcache_clean, &page->flags); +} +#define arch_clear_hugepage_flags arch_clear_hugepage_flags + #endif /* _ASM_RISCV_HUGETLB_H */ From 7cbf2fc276f7a467db7ec051f17fddfd8abd9e54 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Fri, 2 Dec 2022 12:00:37 +0800 Subject: [PATCH 0414/4345] RDMA/hfi1: Fix error return code in parse_platform_config() [ Upstream commit 725349f8ba1e78a146c6ff8f3ee5e2712e517106 ] In the previous iteration of the while loop, the "ret" may have been assigned a value of 0, so the error return code -EINVAL may have been incorrectly set to 0. To fix set valid return code before calling to goto. Fixes: 97167e813415 ("staging/rdma/hfi1: Tune for unknown channel if configuration file is absent") Signed-off-by: Wang Yufen Link: https://lore.kernel.org/r/1669953638-11747-1-git-send-email-wangyufen@huawei.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/firmware.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c index 2cf102b5abd4..f3e64c850aa5 100644 --- a/drivers/infiniband/hw/hfi1/firmware.c +++ b/drivers/infiniband/hw/hfi1/firmware.c @@ -1786,6 +1786,7 @@ int parse_platform_config(struct hfi1_devdata *dd) if (!dd->platform_config.data) { dd_dev_err(dd, "%s: Missing config file\n", __func__); + ret = -EINVAL; goto bail; } ptr = (u32 *)dd->platform_config.data; @@ -1794,6 +1795,7 @@ int parse_platform_config(struct hfi1_devdata *dd) ptr++; if (magic_num != PLATFORM_CONFIG_MAGIC_NUM) { dd_dev_err(dd, "%s: Bad config file\n", __func__); + ret = -EINVAL; goto bail; } @@ -1817,6 +1819,7 @@ int parse_platform_config(struct hfi1_devdata *dd) if (file_length > dd->platform_config.size) { dd_dev_info(dd, "%s:File claims to be larger than read size\n", __func__); + ret = -EINVAL; goto bail; } else if (file_length < dd->platform_config.size) { dd_dev_info(dd, @@ -1837,6 +1840,7 @@ int parse_platform_config(struct hfi1_devdata *dd) dd_dev_err(dd, "%s: Failed validation at offset %ld\n", __func__, (ptr - (u32 *) dd->platform_config.data)); + ret = -EINVAL; goto bail; } @@ -1880,6 +1884,7 @@ int parse_platform_config(struct hfi1_devdata *dd) __func__, table_type, (ptr - (u32 *) dd->platform_config.data)); + ret = -EINVAL; goto bail; /* We don't trust this file now */ } pcfgcache->config_tables[table_type].table = ptr; @@ -1899,6 +1904,7 @@ int parse_platform_config(struct hfi1_devdata *dd) __func__, table_type, (ptr - (u32 *)dd->platform_config.data)); + ret = -EINVAL; goto bail; /* We don't trust this file now */ } pcfgcache->config_tables[table_type].table_metadata = From 0c53bb661f0a8e8f4cc60aac0515c50c7b375490 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Fri, 2 Dec 2022 12:00:38 +0800 Subject: [PATCH 0415/4345] RDMA/srp: Fix error return code in srp_parse_options() [ Upstream commit ed461b30b22c8fa85c25189c14cb89f29595cd14 ] In the previous iteration of the while loop, the "ret" may have been assigned a value of 0, so the error return code -EINVAL may have been incorrectly set to 0. To fix set valid return code before calling to goto. Also investigate each case separately as Andy suggessted. Fixes: e711f968c49c ("IB/srp: replace custom implementation of hex2bin()") Fixes: 2a174df0c602 ("IB/srp: Use kstrtoull() instead of simple_strtoull()") Fixes: 19f313438c77 ("IB/srp: Add RDMA/CM support") Signed-off-by: Wang Yufen Link: https://lore.kernel.org/r/1669953638-11747-2-git-send-email-wangyufen@huawei.com Reviewed-by: Bart Van Assche Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/srp/ib_srp.c | 96 ++++++++++++++++++++++++----- 1 file changed, 82 insertions(+), 14 deletions(-) diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index b4ccb333a834..adbd56af379f 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -3397,7 +3397,8 @@ static int srp_parse_options(struct net *net, const char *buf, break; case SRP_OPT_PKEY: - if (match_hex(args, &token)) { + ret = match_hex(args, &token); + if (ret) { pr_warn("bad P_Key parameter '%s'\n", p); goto out; } @@ -3457,7 +3458,8 @@ static int srp_parse_options(struct net *net, const char *buf, break; case SRP_OPT_MAX_SECT: - if (match_int(args, &token)) { + ret = match_int(args, &token); + if (ret) { pr_warn("bad max sect parameter '%s'\n", p); goto out; } @@ -3465,8 +3467,15 @@ static int srp_parse_options(struct net *net, const char *buf, break; case SRP_OPT_QUEUE_SIZE: - if (match_int(args, &token) || token < 1) { + ret = match_int(args, &token); + if (ret) { + pr_warn("match_int() failed for queue_size parameter '%s', Error %d\n", + p, ret); + goto out; + } + if (token < 1) { pr_warn("bad queue_size parameter '%s'\n", p); + ret = -EINVAL; goto out; } target->scsi_host->can_queue = token; @@ -3477,25 +3486,40 @@ static int srp_parse_options(struct net *net, const char *buf, break; case SRP_OPT_MAX_CMD_PER_LUN: - if (match_int(args, &token) || token < 1) { + ret = match_int(args, &token); + if (ret) { + pr_warn("match_int() failed for max cmd_per_lun parameter '%s', Error %d\n", + p, ret); + goto out; + } + if (token < 1) { pr_warn("bad max cmd_per_lun parameter '%s'\n", p); + ret = -EINVAL; goto out; } target->scsi_host->cmd_per_lun = token; break; case SRP_OPT_TARGET_CAN_QUEUE: - if (match_int(args, &token) || token < 1) { + ret = match_int(args, &token); + if (ret) { + pr_warn("match_int() failed for max target_can_queue parameter '%s', Error %d\n", + p, ret); + goto out; + } + if (token < 1) { pr_warn("bad max target_can_queue parameter '%s'\n", p); + ret = -EINVAL; goto out; } target->target_can_queue = token; break; case SRP_OPT_IO_CLASS: - if (match_hex(args, &token)) { + ret = match_hex(args, &token); + if (ret) { pr_warn("bad IO class parameter '%s'\n", p); goto out; } @@ -3504,6 +3528,7 @@ static int srp_parse_options(struct net *net, const char *buf, pr_warn("unknown IO class parameter value %x specified (use %x or %x).\n", token, SRP_REV10_IB_IO_CLASS, SRP_REV16A_IB_IO_CLASS); + ret = -EINVAL; goto out; } target->io_class = token; @@ -3526,16 +3551,24 @@ static int srp_parse_options(struct net *net, const char *buf, break; case SRP_OPT_CMD_SG_ENTRIES: - if (match_int(args, &token) || token < 1 || token > 255) { + ret = match_int(args, &token); + if (ret) { + pr_warn("match_int() failed for max cmd_sg_entries parameter '%s', Error %d\n", + p, ret); + goto out; + } + if (token < 1 || token > 255) { pr_warn("bad max cmd_sg_entries parameter '%s'\n", p); + ret = -EINVAL; goto out; } target->cmd_sg_cnt = token; break; case SRP_OPT_ALLOW_EXT_SG: - if (match_int(args, &token)) { + ret = match_int(args, &token); + if (ret) { pr_warn("bad allow_ext_sg parameter '%s'\n", p); goto out; } @@ -3543,43 +3576,77 @@ static int srp_parse_options(struct net *net, const char *buf, break; case SRP_OPT_SG_TABLESIZE: - if (match_int(args, &token) || token < 1 || - token > SG_MAX_SEGMENTS) { + ret = match_int(args, &token); + if (ret) { + pr_warn("match_int() failed for max sg_tablesize parameter '%s', Error %d\n", + p, ret); + goto out; + } + if (token < 1 || token > SG_MAX_SEGMENTS) { pr_warn("bad max sg_tablesize parameter '%s'\n", p); + ret = -EINVAL; goto out; } target->sg_tablesize = token; break; case SRP_OPT_COMP_VECTOR: - if (match_int(args, &token) || token < 0) { + ret = match_int(args, &token); + if (ret) { + pr_warn("match_int() failed for comp_vector parameter '%s', Error %d\n", + p, ret); + goto out; + } + if (token < 0) { pr_warn("bad comp_vector parameter '%s'\n", p); + ret = -EINVAL; goto out; } target->comp_vector = token; break; case SRP_OPT_TL_RETRY_COUNT: - if (match_int(args, &token) || token < 2 || token > 7) { + ret = match_int(args, &token); + if (ret) { + pr_warn("match_int() failed for tl_retry_count parameter '%s', Error %d\n", + p, ret); + goto out; + } + if (token < 2 || token > 7) { pr_warn("bad tl_retry_count parameter '%s' (must be a number between 2 and 7)\n", p); + ret = -EINVAL; goto out; } target->tl_retry_count = token; break; case SRP_OPT_MAX_IT_IU_SIZE: - if (match_int(args, &token) || token < 0) { + ret = match_int(args, &token); + if (ret) { + pr_warn("match_int() failed for max it_iu_size parameter '%s', Error %d\n", + p, ret); + goto out; + } + if (token < 0) { pr_warn("bad maximum initiator to target IU size '%s'\n", p); + ret = -EINVAL; goto out; } target->max_it_iu_size = token; break; case SRP_OPT_CH_COUNT: - if (match_int(args, &token) || token < 1) { + ret = match_int(args, &token); + if (ret) { + pr_warn("match_int() failed for channel count parameter '%s', Error %d\n", + p, ret); + goto out; + } + if (token < 1) { pr_warn("bad channel count %s\n", p); + ret = -EINVAL; goto out; } target->ch_count = token; @@ -3588,6 +3655,7 @@ static int srp_parse_options(struct net *net, const char *buf, default: pr_warn("unknown parameter or missing value '%s' in target creation request\n", p); + ret = -EINVAL; goto out; } } From 73ab1c956a32a97e231327bc9f80ebf313a45082 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Tue, 18 Oct 2022 12:40:04 +0800 Subject: [PATCH 0416/4345] orangefs: Fix sysfs not cleanup when dev init failed [ Upstream commit ea60a4ad0cf88b411cde6888b8c890935686ecd7 ] When the dev init failed, should cleanup the sysfs, otherwise, the module will never be loaded since can not create duplicate sysfs directory: sysfs: cannot create duplicate filename '/fs/orangefs' CPU: 1 PID: 6549 Comm: insmod Tainted: G W 6.0.0+ #44 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc33 04/01/2014 Call Trace: dump_stack_lvl+0x34/0x44 sysfs_warn_dup.cold+0x17/0x24 sysfs_create_dir_ns+0x16d/0x180 kobject_add_internal+0x156/0x3a0 kobject_init_and_add+0xcf/0x120 orangefs_sysfs_init+0x7e/0x3a0 [orangefs] orangefs_init+0xfe/0x1000 [orangefs] do_one_initcall+0x87/0x2a0 do_init_module+0xdf/0x320 load_module+0x2f98/0x3330 __do_sys_finit_module+0x113/0x1b0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 kobject_add_internal failed for orangefs with -EEXIST, don't try to register things with the same name in the same directory. Fixes: 2f83ace37181 ("orangefs: put register_chrdev immediately before register_filesystem") Signed-off-by: Zhang Xiaoxu Signed-off-by: Mike Marshall Signed-off-by: Sasha Levin --- fs/orangefs/orangefs-mod.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index 74a3d6337ef4..ac9c91b83868 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -141,7 +141,7 @@ static int __init orangefs_init(void) gossip_err("%s: could not initialize device subsystem %d!\n", __func__, ret); - goto cleanup_device; + goto cleanup_sysfs; } ret = register_filesystem(&orangefs_fs_type); @@ -152,11 +152,11 @@ static int __init orangefs_init(void) goto out; } - orangefs_sysfs_exit(); - -cleanup_device: orangefs_dev_cleanup(); +cleanup_sysfs: + orangefs_sysfs_exit(); + sysfs_init_failed: orangefs_debugfs_cleanup(); From 83b2c33b53b2292e624ef8823d0608163c486790 Mon Sep 17 00:00:00 2001 From: Chengchang Tang Date: Sat, 26 Nov 2022 18:29:08 +0800 Subject: [PATCH 0417/4345] RDMA/hns: Fix PBL page MTR find [ Upstream commit 9fb39ef2ff3e18f1740625ba04093dfbef086d2b ] Now, The address of the first two pages in the MR will be searched, which use to speed up the lookup of the pbl table for hardware. An exception will occur when there is only one page in this MR. This patch fix the number of page to search. Fixes: 9b2cf76c9f05 ("RDMA/hns: Optimize PBL buffer allocation process") Link: https://lore.kernel.org/r/20221126102911.2921820-4-xuhaoyue1@hisilicon.com Signed-off-by: Chengchang Tang Signed-off-by: Haoyue Xu Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index e1395590edfd..0f4ef4516868 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2738,7 +2738,8 @@ static int set_mtpt_pbl(struct hns_roce_dev *hr_dev, int i, count; count = hns_roce_mtr_find(hr_dev, &mr->pbl_mtr, 0, pages, - ARRAY_SIZE(pages), &pbl_ba); + min_t(int, ARRAY_SIZE(pages), mr->npages), + &pbl_ba); if (count < 1) { ibdev_err(ibdev, "failed to find PBL mtr, count = %d.\n", count); From 15ca148940187d04d506c3e66ab43df06f2f56c4 Mon Sep 17 00:00:00 2001 From: Chengchang Tang Date: Sat, 26 Nov 2022 18:29:09 +0800 Subject: [PATCH 0418/4345] RDMA/hns: Fix page size cap from firmware [ Upstream commit 99dc5a0712883d5d13b620d25b3759d429577bc8 ] Add verification to make sure the roce page size cap is supported by the system page size. Fixes: ba6bb7e97421 ("RDMA/hns: Add interfaces to get pf capabilities from firmware") Link: https://lore.kernel.org/r/20221126102911.2921820-5-xuhaoyue1@hisilicon.com Signed-off-by: Chengchang Tang Signed-off-by: Haoyue Xu Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 0f4ef4516868..76ed547b76ea 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2166,6 +2166,9 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) calc_pg_sz(caps->num_idx_segs, caps->idx_entry_sz, caps->idx_hop_num, 1, &caps->idx_buf_pg_sz, &caps->idx_ba_pg_sz, HEM_TYPE_IDX); + if (!(caps->page_size_cap & PAGE_SIZE)) + caps->page_size_cap = HNS_ROCE_V2_PAGE_SIZE_SUPPORTED; + return 0; } From 38da26c8552ee431c8276bb2afc41194e93a5eb0 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 1 Dec 2022 14:25:26 +0800 Subject: [PATCH 0419/4345] crypto: img-hash - Fix variable dereferenced before check 'hdev->req' [ Upstream commit 04ba54e5af8f8f0137b08cb51a0b3a2e1ea46c94 ] Smatch report warning as follows: drivers/crypto/img-hash.c:366 img_hash_dma_task() warn: variable dereferenced before check 'hdev->req' Variable dereferenced should be done after check 'hdev->req', fix it. Fixes: d358f1abbf71 ("crypto: img-hash - Add Imagination Technologies hw hash accelerator") Fixes: 10badea259fa ("crypto: img-hash - Fix null pointer exception") Signed-off-by: Gaosheng Cui Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/img-hash.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/img-hash.c b/drivers/crypto/img-hash.c index 91f555ccbb31..cecae50d0f58 100644 --- a/drivers/crypto/img-hash.c +++ b/drivers/crypto/img-hash.c @@ -357,12 +357,16 @@ static int img_hash_dma_init(struct img_hash_dev *hdev) static void img_hash_dma_task(unsigned long d) { struct img_hash_dev *hdev = (struct img_hash_dev *)d; - struct img_hash_request_ctx *ctx = ahash_request_ctx(hdev->req); + struct img_hash_request_ctx *ctx; u8 *addr; size_t nbytes, bleft, wsend, len, tbc; struct scatterlist tsg; - if (!hdev->req || !ctx->sg) + if (!hdev->req) + return; + + ctx = ahash_request_ctx(hdev->req); + if (!ctx->sg) return; addr = sg_virt(ctx->sg); From 5998e5c30e839f73e62cb29e0d9617b0d16ccba3 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Fri, 2 Dec 2022 21:22:33 +0800 Subject: [PATCH 0420/4345] hwrng: amd - Fix PCI device refcount leak [ Upstream commit ecadb5b0111ea19fc7c240bb25d424a94471eb7d ] for_each_pci_dev() is implemented by pci_get_device(). The comment of pci_get_device() says that it will increase the reference count for the returned pci_dev and also decrease the reference count for the input pci_dev @from if it is not NULL. If we break for_each_pci_dev() loop with pdev not NULL, we need to call pci_dev_put() to decrease the reference count. Add the missing pci_dev_put() for the normal and error path. Fixes: 96d63c0297cc ("[PATCH] Add AMD HW RNG driver") Signed-off-by: Xiongfeng Wang Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/char/hw_random/amd-rng.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/char/hw_random/amd-rng.c b/drivers/char/hw_random/amd-rng.c index 9959c762da2f..db3dd467194c 100644 --- a/drivers/char/hw_random/amd-rng.c +++ b/drivers/char/hw_random/amd-rng.c @@ -143,15 +143,19 @@ static int __init mod_init(void) found: err = pci_read_config_dword(pdev, 0x58, &pmbase); if (err) - return err; + goto put_dev; pmbase &= 0x0000FF00; - if (pmbase == 0) - return -EIO; + if (pmbase == 0) { + err = -EIO; + goto put_dev; + } priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + if (!priv) { + err = -ENOMEM; + goto put_dev; + } if (!request_region(pmbase + PMBASE_OFFSET, PMBASE_SIZE, DRV_NAME)) { dev_err(&pdev->dev, DRV_NAME " region 0x%x already in use!\n", @@ -185,6 +189,8 @@ err_iomap: release_region(pmbase + PMBASE_OFFSET, PMBASE_SIZE); out: kfree(priv); +put_dev: + pci_dev_put(pdev); return err; } @@ -200,6 +206,8 @@ static void __exit mod_exit(void) release_region(priv->pmbase + PMBASE_OFFSET, PMBASE_SIZE); + pci_dev_put(priv->pcidev); + kfree(priv); } From aa96aff394a511cc7bb7df08d1b8504d4d97671e Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Fri, 2 Dec 2022 21:22:34 +0800 Subject: [PATCH 0421/4345] hwrng: geode - Fix PCI device refcount leak [ Upstream commit 9f6ec8dc574efb7f4f3d7ee9cd59ae307e78f445 ] for_each_pci_dev() is implemented by pci_get_device(). The comment of pci_get_device() says that it will increase the reference count for the returned pci_dev and also decrease the reference count for the input pci_dev @from if it is not NULL. If we break for_each_pci_dev() loop with pdev not NULL, we need to call pci_dev_put() to decrease the reference count. We add a new struct 'amd_geode_priv' to record pointer of the pci_dev and membase, and then add missing pci_dev_put() for the normal and error path. Fixes: ef5d862734b8 ("[PATCH] Add Geode HW RNG driver") Signed-off-by: Xiongfeng Wang Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/char/hw_random/geode-rng.c | 36 +++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 8 deletions(-) diff --git a/drivers/char/hw_random/geode-rng.c b/drivers/char/hw_random/geode-rng.c index e1d421a36a13..207272979f23 100644 --- a/drivers/char/hw_random/geode-rng.c +++ b/drivers/char/hw_random/geode-rng.c @@ -51,6 +51,10 @@ static const struct pci_device_id pci_tbl[] = { }; MODULE_DEVICE_TABLE(pci, pci_tbl); +struct amd_geode_priv { + struct pci_dev *pcidev; + void __iomem *membase; +}; static int geode_rng_data_read(struct hwrng *rng, u32 *data) { @@ -90,6 +94,7 @@ static int __init mod_init(void) const struct pci_device_id *ent; void __iomem *mem; unsigned long rng_base; + struct amd_geode_priv *priv; for_each_pci_dev(pdev) { ent = pci_match_id(pci_tbl, pdev); @@ -97,17 +102,26 @@ static int __init mod_init(void) goto found; } /* Device not found. */ - goto out; + return err; found: + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + err = -ENOMEM; + goto put_dev; + } + rng_base = pci_resource_start(pdev, 0); if (rng_base == 0) - goto out; + goto free_priv; err = -ENOMEM; mem = ioremap(rng_base, 0x58); if (!mem) - goto out; - geode_rng.priv = (unsigned long)mem; + goto free_priv; + + geode_rng.priv = (unsigned long)priv; + priv->membase = mem; + priv->pcidev = pdev; pr_info("AMD Geode RNG detected\n"); err = hwrng_register(&geode_rng); @@ -116,20 +130,26 @@ found: err); goto err_unmap; } -out: return err; err_unmap: iounmap(mem); - goto out; +free_priv: + kfree(priv); +put_dev: + pci_dev_put(pdev); + return err; } static void __exit mod_exit(void) { - void __iomem *mem = (void __iomem *)geode_rng.priv; + struct amd_geode_priv *priv; + priv = (struct amd_geode_priv *)geode_rng.priv; hwrng_unregister(&geode_rng); - iounmap(mem); + iounmap(priv->membase); + pci_dev_put(priv->pcidev); + kfree(priv); } module_init(mod_init); From d21714134505bc23daa0455b295f3b63730b3b42 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 8 Dec 2022 09:52:54 +0200 Subject: [PATCH 0422/4345] IB/IPoIB: Fix queue count inconsistency for PKEY child interfaces [ Upstream commit dbc94a0fb81771a38733c0e8f2ea8c4fa6934dc1 ] There are 2 ways to create IPoIB PKEY child interfaces: 1) Writing a PKEY to /sys/class/net//create_child. 2) Using netlink with iproute. While with sysfs the child interface has the same number of tx and rx queues as the parent, with netlink there will always be 1 tx and 1 rx queue for the child interface. That's because the get_num_tx/rx_queues() netlink ops are missing and the default value of 1 is taken for the number of queues (in rtnl_create_link()). This change adds the get_num_tx/rx_queues() ops which allows for interfaces with multiple queues to be created over netlink. This constant only represents the max number of tx and rx queues on that net device. Fixes: 9baa0b036410 ("IB/ipoib: Add rtnl_link_ops support") Signed-off-by: Dragos Tatulea Link: https://lore.kernel.org/r/f4a42c8aa43c02d5ae5559a60c3e5e0f18c82531.1670485816.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c index 5b05cf3837da..28e9b70844e4 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c @@ -42,6 +42,11 @@ static const struct nla_policy ipoib_policy[IFLA_IPOIB_MAX + 1] = { [IFLA_IPOIB_UMCAST] = { .type = NLA_U16 }, }; +static unsigned int ipoib_get_max_num_queues(void) +{ + return min_t(unsigned int, num_possible_cpus(), 128); +} + static int ipoib_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -173,6 +178,8 @@ static struct rtnl_link_ops ipoib_link_ops __read_mostly = { .changelink = ipoib_changelink, .get_size = ipoib_get_size, .fill_info = ipoib_fill_info, + .get_num_rx_queues = ipoib_get_max_num_queues, + .get_num_tx_queues = ipoib_get_max_num_queues, }; struct rtnl_link_ops *ipoib_get_link_ops(void) From fce9890e1be4c0460dad850cc8c00414a9d25f0f Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 9 Nov 2022 14:40:36 +0800 Subject: [PATCH 0423/4345] drivers: dio: fix possible memory leak in dio_init() [ Upstream commit e63e99397b2613d50a5f4f02ed07307e67a190f1 ] If device_register() returns error, the 'dev' and name needs be freed. Add a release function, and then call put_device() in the error path, so the name is freed in kobject_cleanup() and to the 'dev' is freed in release function. Fixes: 2e4c77bea3d8 ("m68k: dio - Kill warn_unused_result warnings") Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221109064036.1835346-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/dio/dio.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/dio/dio.c b/drivers/dio/dio.c index 193b40e7aec0..1414a1c81834 100644 --- a/drivers/dio/dio.c +++ b/drivers/dio/dio.c @@ -110,6 +110,12 @@ static char dio_no_name[] = { 0 }; #endif /* CONFIG_DIO_CONSTANTS */ +static void dio_dev_release(struct device *dev) +{ + struct dio_dev *ddev = container_of(dev, typeof(struct dio_dev), dev); + kfree(ddev); +} + int __init dio_find(int deviceid) { /* Called to find a DIO device before the full bus scan has run. @@ -224,6 +230,7 @@ static int __init dio_init(void) dev->bus = &dio_bus; dev->dev.parent = &dio_bus.dev; dev->dev.bus = &dio_bus_type; + dev->dev.release = dio_dev_release; dev->scode = scode; dev->resource.start = pa; dev->resource.end = pa + DIO_SIZE(scode, va); @@ -251,6 +258,7 @@ static int __init dio_init(void) if (error) { pr_err("DIO: Error registering device %s\n", dev->name); + put_device(&dev->dev); continue; } error = dio_create_sysfs_dev_files(dev); From 7e74868a38b4e0994c58a1d8352e6fbaaa785f6c Mon Sep 17 00:00:00 2001 From: Kartik Date: Tue, 18 Oct 2022 20:28:06 +0530 Subject: [PATCH 0424/4345] serial: tegra: Read DMA status before terminating MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 109a951a9f1fd8a34ebd1896cbbd5d5cede880a7 ] Read the DMA status before terminating the DMA, as doing so deletes the DMA desc. Also, to get the correct transfer status information, pause the DMA using dmaengine_pause() before reading the DMA status. Fixes: e9ea096dd225 ("serial: tegra: add serial driver") Reviewed-by: Jon Hunter Reviewed-by: Ilpo Järvinen Acked-by: Thierry Reding Signed-off-by: Akhil R Signed-off-by: Kartik Link: https://lore.kernel.org/r/1666105086-17326-1-git-send-email-kkartik@nvidia.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/serial-tegra.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index cda71802b698..62377c831894 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -614,8 +614,9 @@ static void tegra_uart_stop_tx(struct uart_port *u) if (tup->tx_in_progress != TEGRA_UART_TX_DMA) return; - dmaengine_terminate_all(tup->tx_dma_chan); + dmaengine_pause(tup->tx_dma_chan); dmaengine_tx_status(tup->tx_dma_chan, tup->tx_cookie, &state); + dmaengine_terminate_all(tup->tx_dma_chan); count = tup->tx_bytes_requested - state.residue; async_tx_ack(tup->tx_dma_desc); uart_xmit_advance(&tup->uport, count); @@ -758,8 +759,9 @@ static void tegra_uart_terminate_rx_dma(struct tegra_uart_port *tup) return; } - dmaengine_terminate_all(tup->rx_dma_chan); + dmaengine_pause(tup->rx_dma_chan); dmaengine_tx_status(tup->rx_dma_chan, tup->rx_cookie, &state); + dmaengine_terminate_all(tup->rx_dma_chan); tegra_uart_rx_buffer_push(tup, state.residue); tup->rx_dma_active = false; From 18a7200646958cf8e1b8a933de08122fc50676cd Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 26 Oct 2022 16:28:03 +0800 Subject: [PATCH 0425/4345] class: fix possible memory leak in __class_register() [ Upstream commit 8c3e8a6bdb5253b97ad532570f8b5db5f7a06407 ] If class_add_groups() returns error, the 'cp->subsys' need be unregister, and the 'cp' need be freed. We can not call kset_unregister() here, because the 'cls' will be freed in callback function class_release() and it's also freed in caller's error path, it will cause double free. So fix this by calling kobject_del() and kfree_const(name) to cleanup kobject. Besides, call kfree() to free the 'cp'. Fault injection test can trigger this: unreferenced object 0xffff888102fa8190 (size 8): comm "modprobe", pid 502, jiffies 4294906074 (age 49.296s) hex dump (first 8 bytes): 70 6b 74 63 64 76 64 00 pktcdvd. backtrace: [<00000000e7c7703d>] __kmalloc_track_caller+0x1ae/0x320 [<000000005e4d70bc>] kstrdup+0x3a/0x70 [<00000000c2e5e85a>] kstrdup_const+0x68/0x80 [<000000000049a8c7>] kvasprintf_const+0x10b/0x190 [<0000000029123163>] kobject_set_name_vargs+0x56/0x150 [<00000000747219c9>] kobject_set_name+0xab/0xe0 [<0000000005f1ea4e>] __class_register+0x15c/0x49a unreferenced object 0xffff888037274000 (size 1024): comm "modprobe", pid 502, jiffies 4294906074 (age 49.296s) hex dump (first 32 bytes): 00 40 27 37 80 88 ff ff 00 40 27 37 80 88 ff ff .@'7.....@'7.... 00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00 .....N.......... backtrace: [<00000000151f9600>] kmem_cache_alloc_trace+0x17c/0x2f0 [<00000000ecf3dd95>] __class_register+0x86/0x49a Fixes: ced6473e7486 ("driver core: class: add class_groups support") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221026082803.3458760-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/base/class.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/base/class.c b/drivers/base/class.c index c3451481194e..ef7ff822bc08 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -192,6 +192,11 @@ int __class_register(struct class *cls, struct lock_class_key *key) } error = class_add_groups(class_get(cls), cls->class_groups); class_put(cls); + if (error) { + kobject_del(&cp->subsys.kobj); + kfree_const(cp->subsys.kobj.name); + kfree(cp); + } return error; } EXPORT_SYMBOL_GPL(__class_register); From 27b612bd09bd74c21eabd81a6bad5ba1d2dd11d0 Mon Sep 17 00:00:00 2001 From: Rafael Mendonca Date: Tue, 18 Oct 2022 12:28:25 -0300 Subject: [PATCH 0426/4345] vfio: platform: Do not pass return buffer to ACPI _RST method [ Upstream commit e67e070632a665c932d534b8b800477bb3111449 ] The ACPI _RST method has no return value, there's no need to pass a return buffer to acpi_evaluate_object(). Fixes: d30daa33ec1d ("vfio: platform: call _RST method when using ACPI") Signed-off-by: Rafael Mendonca Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20221018152825.891032-1-rafaelmendsr@gmail.com Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- drivers/vfio/platform/vfio_platform_common.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index e83a7cd15c95..e15ef1a949e0 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -72,12 +72,11 @@ static int vfio_platform_acpi_call_reset(struct vfio_platform_device *vdev, const char **extra_dbg) { #ifdef CONFIG_ACPI - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; struct device *dev = vdev->device; acpi_handle handle = ACPI_HANDLE(dev); acpi_status acpi_ret; - acpi_ret = acpi_evaluate_object(handle, "_RST", NULL, &buffer); + acpi_ret = acpi_evaluate_object(handle, "_RST", NULL, NULL); if (ACPI_FAILURE(acpi_ret)) { if (extra_dbg) *extra_dbg = acpi_format_exception(acpi_ret); From 9bf7a0b2b15cd12e15f7858072bd89933746de67 Mon Sep 17 00:00:00 2001 From: Rafael Mendonca Date: Fri, 30 Sep 2022 19:40:57 -0300 Subject: [PATCH 0427/4345] uio: uio_dmem_genirq: Fix missing unlock in irq configuration [ Upstream commit 9de255c461d1b3f0242b3ad1450c3323a3e00b34 ] Commit b74351287d4b ("uio: fix a sleep-in-atomic-context bug in uio_dmem_genirq_irqcontrol()") started calling disable_irq() without holding the spinlock because it can sleep. However, that fix introduced another bug: if interrupt is already disabled and a new disable request comes in, then the spinlock is not unlocked: root@localhost:~# printf '\x00\x00\x00\x00' > /dev/uio0 root@localhost:~# printf '\x00\x00\x00\x00' > /dev/uio0 root@localhost:~# [ 14.851538] BUG: scheduling while atomic: bash/223/0x00000002 [ 14.851991] Modules linked in: uio_dmem_genirq uio myfpga(OE) bochs drm_vram_helper drm_ttm_helper ttm drm_kms_helper drm snd_pcm ppdev joydev psmouse snd_timer snd e1000fb_sys_fops syscopyarea parport sysfillrect soundcore sysimgblt input_leds pcspkr i2c_piix4 serio_raw floppy evbug qemu_fw_cfg mac_hid pata_acpi ip_tables x_tables autofs4 [last unloaded: parport_pc] [ 14.854206] CPU: 0 PID: 223 Comm: bash Tainted: G OE 6.0.0-rc7 #21 [ 14.854786] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 [ 14.855664] Call Trace: [ 14.855861] [ 14.856025] dump_stack_lvl+0x4d/0x67 [ 14.856325] dump_stack+0x14/0x1a [ 14.856583] __schedule_bug.cold+0x4b/0x5c [ 14.856915] __schedule+0xe81/0x13d0 [ 14.857199] ? idr_find+0x13/0x20 [ 14.857456] ? get_work_pool+0x2d/0x50 [ 14.857756] ? __flush_work+0x233/0x280 [ 14.858068] ? __schedule+0xa95/0x13d0 [ 14.858307] ? idr_find+0x13/0x20 [ 14.858519] ? get_work_pool+0x2d/0x50 [ 14.858798] schedule+0x6c/0x100 [ 14.859009] schedule_hrtimeout_range_clock+0xff/0x110 [ 14.859335] ? tty_write_room+0x1f/0x30 [ 14.859598] ? n_tty_poll+0x1ec/0x220 [ 14.859830] ? tty_ldisc_deref+0x1a/0x20 [ 14.860090] schedule_hrtimeout_range+0x17/0x20 [ 14.860373] do_select+0x596/0x840 [ 14.860627] ? __kernel_text_address+0x16/0x50 [ 14.860954] ? poll_freewait+0xb0/0xb0 [ 14.861235] ? poll_freewait+0xb0/0xb0 [ 14.861517] ? rpm_resume+0x49d/0x780 [ 14.861798] ? common_interrupt+0x59/0xa0 [ 14.862127] ? asm_common_interrupt+0x2b/0x40 [ 14.862511] ? __uart_start.isra.0+0x61/0x70 [ 14.862902] ? __check_object_size+0x61/0x280 [ 14.863255] core_sys_select+0x1c6/0x400 [ 14.863575] ? vfs_write+0x1c9/0x3d0 [ 14.863853] ? vfs_write+0x1c9/0x3d0 [ 14.864121] ? _copy_from_user+0x45/0x70 [ 14.864526] do_pselect.constprop.0+0xb3/0xf0 [ 14.864893] ? do_syscall_64+0x6d/0x90 [ 14.865228] ? do_syscall_64+0x6d/0x90 [ 14.865556] __x64_sys_pselect6+0x76/0xa0 [ 14.865906] do_syscall_64+0x60/0x90 [ 14.866214] ? syscall_exit_to_user_mode+0x2a/0x50 [ 14.866640] ? do_syscall_64+0x6d/0x90 [ 14.866972] ? do_syscall_64+0x6d/0x90 [ 14.867286] ? do_syscall_64+0x6d/0x90 [ 14.867626] entry_SYSCALL_64_after_hwframe+0x63/0xcd [...] stripped [ 14.872959] ('myfpga' is a simple 'uio_dmem_genirq' driver I wrote to test this) The implementation of "uio_dmem_genirq" was based on "uio_pdrv_genirq" and it is used in a similar manner to the "uio_pdrv_genirq" driver with respect to interrupt configuration and handling. At the time "uio_dmem_genirq" was introduced, both had the same implementation of the 'uio_info' handlers irqcontrol() and handler(). Then commit 34cb27528398 ("UIO: Fix concurrency issue"), which was only applied to "uio_pdrv_genirq", ended up making them a little different. That commit, among other things, changed disable_irq() to disable_irq_nosync() in the implementation of irqcontrol(). The motivation there was to avoid a deadlock between irqcontrol() and handler(), since it added a spinlock in the irq handler, and disable_irq() waits for the completion of the irq handler. By changing disable_irq() to disable_irq_nosync() in irqcontrol(), we also avoid the sleeping-while-atomic bug that commit b74351287d4b ("uio: fix a sleep-in-atomic-context bug in uio_dmem_genirq_irqcontrol()") was trying to fix. Thus, this fixes the missing unlock in irqcontrol() by importing the implementation of irqcontrol() handler from the "uio_pdrv_genirq" driver. In the end, it reverts commit b74351287d4b ("uio: fix a sleep-in-atomic-context bug in uio_dmem_genirq_irqcontrol()") and change disable_irq() to disable_irq_nosync(). It is worth noting that this still does not address the concurrency issue fixed by commit 34cb27528398 ("UIO: Fix concurrency issue"). It will be addressed separately in the next commits. Split out from commit 34cb27528398 ("UIO: Fix concurrency issue"). Fixes: b74351287d4b ("uio: fix a sleep-in-atomic-context bug in uio_dmem_genirq_irqcontrol()") Signed-off-by: Rafael Mendonca Link: https://lore.kernel.org/r/20220930224100.816175-2-rafaelmendsr@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/uio/uio_dmem_genirq.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c index ec7f66f4555a..796946bab508 100644 --- a/drivers/uio/uio_dmem_genirq.c +++ b/drivers/uio/uio_dmem_genirq.c @@ -132,13 +132,11 @@ static int uio_dmem_genirq_irqcontrol(struct uio_info *dev_info, s32 irq_on) if (irq_on) { if (test_and_clear_bit(0, &priv->flags)) enable_irq(dev_info->irq); - spin_unlock_irqrestore(&priv->lock, flags); } else { - if (!test_and_set_bit(0, &priv->flags)) { - spin_unlock_irqrestore(&priv->lock, flags); - disable_irq(dev_info->irq); - } + if (!test_and_set_bit(0, &priv->flags)) + disable_irq_nosync(dev_info->irq); } + spin_unlock_irqrestore(&priv->lock, flags); return 0; } From 2fcb7c7d52194c0f0c412c1d960899b8e922bab5 Mon Sep 17 00:00:00 2001 From: Rafael Mendonca Date: Fri, 30 Sep 2022 19:40:58 -0300 Subject: [PATCH 0428/4345] uio: uio_dmem_genirq: Fix deadlock between irq config and handling [ Upstream commit 118b918018175d9fcd8db667f905012e986cc2c9 ] This fixes a concurrency issue addressed in commit 34cb27528398 ("UIO: Fix concurrency issue"): "In a SMP case there was a race condition issue between Uio_pdrv_genirq_irqcontrol() running on one CPU and irq handler on another CPU. Fix it by spin_locking shared resources access inside irq handler." The implementation of "uio_dmem_genirq" was based on "uio_pdrv_genirq" and it is used in a similar manner to the "uio_pdrv_genirq" driver with respect to interrupt configuration and handling. At the time "uio_dmem_genirq" was merged, both had the same implementation of the 'uio_info' handlers irqcontrol() and handler(), thus, both had the same concurrency issue mentioned by the above commit. However, the above patch was only applied to the "uio_pdrv_genirq" driver. Split out from commit 34cb27528398 ("UIO: Fix concurrency issue"). Fixes: 0a0c3b5a24bd ("Add new uio device for dynamic memory allocation") Signed-off-by: Rafael Mendonca Link: https://lore.kernel.org/r/20220930224100.816175-3-rafaelmendsr@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/uio/uio_dmem_genirq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c index 796946bab508..92751737bbea 100644 --- a/drivers/uio/uio_dmem_genirq.c +++ b/drivers/uio/uio_dmem_genirq.c @@ -110,8 +110,10 @@ static irqreturn_t uio_dmem_genirq_handler(int irq, struct uio_info *dev_info) * remember the state so we can allow user space to enable it later. */ + spin_lock(&priv->lock); if (!test_and_set_bit(0, &priv->flags)) disable_irq_nosync(irq); + spin_unlock(&priv->lock); return IRQ_HANDLED; } @@ -125,7 +127,8 @@ static int uio_dmem_genirq_irqcontrol(struct uio_info *dev_info, s32 irq_on) * in the interrupt controller, but keep track of the * state to prevent per-irq depth damage. * - * Serialize this operation to support multiple tasks. + * Serialize this operation to support multiple tasks and concurrency + * with irq handler on SMP systems. */ spin_lock_irqsave(&priv->lock, flags); From 775a6f8bed8725f3189b85bec3e1179dd03fc253 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 11 Nov 2022 10:03:17 +0100 Subject: [PATCH 0429/4345] usb: fotg210-udc: Fix ages old endianness issues [ Upstream commit 46ed6026ca2181c917c8334a82e3eaf40a6234dd ] The code in the FOTG210 driver isn't entirely endianness-agnostic as reported by the kernel robot sparse testing. This came to the surface while moving the files around. The driver is only used on little-endian systems, so this causes no real-world regression, but it is nice to be strict and have some compile coverage also on big endian machines, so fix it up with the right LE accessors. Fixes: b84a8dee23fd ("usb: gadget: add Faraday fotg210_udc driver") Reported-by: kernel test robot Link: https://lore.kernel.org/linux-usb/202211110910.0dJ7nZCn-lkp@intel.com/ Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20221111090317.94228-1-linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/fotg210-udc.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/usb/gadget/udc/fotg210-udc.c b/drivers/usb/gadget/udc/fotg210-udc.c index 75bf446f4a66..11712bc89635 100644 --- a/drivers/usb/gadget/udc/fotg210-udc.c +++ b/drivers/usb/gadget/udc/fotg210-udc.c @@ -629,10 +629,10 @@ static void fotg210_request_error(struct fotg210_udc *fotg210) static void fotg210_set_address(struct fotg210_udc *fotg210, struct usb_ctrlrequest *ctrl) { - if (ctrl->wValue >= 0x0100) { + if (le16_to_cpu(ctrl->wValue) >= 0x0100) { fotg210_request_error(fotg210); } else { - fotg210_set_dev_addr(fotg210, ctrl->wValue); + fotg210_set_dev_addr(fotg210, le16_to_cpu(ctrl->wValue)); fotg210_set_cxdone(fotg210); } } @@ -713,17 +713,17 @@ static void fotg210_get_status(struct fotg210_udc *fotg210, switch (ctrl->bRequestType & USB_RECIP_MASK) { case USB_RECIP_DEVICE: - fotg210->ep0_data = 1 << USB_DEVICE_SELF_POWERED; + fotg210->ep0_data = cpu_to_le16(1 << USB_DEVICE_SELF_POWERED); break; case USB_RECIP_INTERFACE: - fotg210->ep0_data = 0; + fotg210->ep0_data = cpu_to_le16(0); break; case USB_RECIP_ENDPOINT: epnum = ctrl->wIndex & USB_ENDPOINT_NUMBER_MASK; if (epnum) fotg210->ep0_data = - fotg210_is_epnstall(fotg210->ep[epnum]) - << USB_ENDPOINT_HALT; + cpu_to_le16(fotg210_is_epnstall(fotg210->ep[epnum]) + << USB_ENDPOINT_HALT); else fotg210_request_error(fotg210); break; From 5d2b286eb034af114f67d9967fc3fbc1829bb712 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 17 Nov 2022 11:59:14 +0800 Subject: [PATCH 0430/4345] staging: vme_user: Fix possible UAF in tsi148_dma_list_add [ Upstream commit 357057ee55d3c99a5de5abe8150f7bca04f8e53b ] Smatch report warning as follows: drivers/staging/vme_user/vme_tsi148.c:1757 tsi148_dma_list_add() warn: '&entry->list' not removed from list In tsi148_dma_list_add(), the error path "goto err_dma" will not remove entry->list from list->entries, but entry will be freed, then list traversal may cause UAF. Fix by removeing it from list->entries before free(). Fixes: b2383c90a9d6 ("vme: tsi148: fix first DMA item mapping") Signed-off-by: Gaosheng Cui Link: https://lore.kernel.org/r/20221117035914.2954454-1-cuigaosheng1@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/vme/bridges/vme_tsi148.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/vme/bridges/vme_tsi148.c b/drivers/vme/bridges/vme_tsi148.c index 50ae26977a02..5ccda1a363ec 100644 --- a/drivers/vme/bridges/vme_tsi148.c +++ b/drivers/vme/bridges/vme_tsi148.c @@ -1771,6 +1771,7 @@ static int tsi148_dma_list_add(struct vme_dma_list *list, return 0; err_dma: + list_del(&entry->list); err_dest: err_source: err_align: From 1ca02df871adf04e26134863065521e504e03cd5 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Mon, 14 Nov 2022 17:59:24 +0100 Subject: [PATCH 0431/4345] usb: typec: Check for ops->exit instead of ops->enter in altmode_exit [ Upstream commit b6ddd180e3d9f92c1e482b3cdeec7dda086b1341 ] typec_altmode_exit checks if ops->enter is not NULL but then calls ops->exit a few lines below. Fix that and check for the function pointer it's about to call instead. Fixes: 8a37d87d72f0 ("usb: typec: Bus type for alternate modes") Signed-off-by: Sven Peter Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20221114165924.33487-1-sven@svenpeter.dev Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/typec/bus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index e8ddb81cb6df..f4e7f4d78b56 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -132,7 +132,7 @@ int typec_altmode_exit(struct typec_altmode *adev) if (!adev || !adev->active) return 0; - if (!pdev->ops || !pdev->ops->enter) + if (!pdev->ops || !pdev->ops->exit) return -EOPNOTSUPP; /* Moving to USB Safe State */ From d3b6c28a71f111a6c67ddc3238aab95910fd86cf Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 21 Nov 2022 14:24:16 +0800 Subject: [PATCH 0432/4345] usb: typec: tcpci: fix of node refcount leak in tcpci_register_port() [ Upstream commit 0384e87e3fec735e47f1c133c796f32ef7a72a9b ] I got the following report while doing device(mt6370-tcpc) load test with CONFIG_OF_UNITTEST and CONFIG_OF_DYNAMIC enabled: OF: ERROR: memory leak, expected refcount 1 instead of 2, of_node_get()/of_node_put() unbalanced - destroy cset entry: attach overlay node /i2c/pmic@34/tcpc/connector The 'fwnode' set in tcpci_parse_config() which is called in tcpci_register_port(), its node refcount is increased in device_get_named_child_node(). It needs be put while exiting, so call fwnode_handle_put() in the error path of tcpci_register_port() and in tcpci_unregister_port() to avoid leak. Fixes: 5e85a04c8c0d ("usb: typec: add fwnode to tcpc") Signed-off-by: Yang Yingliang Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20221121062416.1026192-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/typec/tcpm/tcpci.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 49420e28a1f7..069affa5cb1e 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -649,8 +649,10 @@ struct tcpci *tcpci_register_port(struct device *dev, struct tcpci_data *data) return ERR_PTR(err); tcpci->port = tcpm_register_port(tcpci->dev, &tcpci->tcpc); - if (IS_ERR(tcpci->port)) + if (IS_ERR(tcpci->port)) { + fwnode_handle_put(tcpci->tcpc.fwnode); return ERR_CAST(tcpci->port); + } return tcpci; } @@ -659,6 +661,7 @@ EXPORT_SYMBOL_GPL(tcpci_register_port); void tcpci_unregister_port(struct tcpci *tcpci) { tcpm_unregister_port(tcpci->port); + fwnode_handle_put(tcpci->tcpc.fwnode); } EXPORT_SYMBOL_GPL(tcpci_unregister_port); From fab27438abe2930bc345b90ed63b9f9939bb285d Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Mon, 14 Nov 2022 18:44:47 +0100 Subject: [PATCH 0433/4345] usb: typec: tipd: Fix spurious fwnode_handle_put in error path [ Upstream commit 782c70edc4852a5d39be12377a85501546236212 ] The err_role_put error path always calls fwnode_handle_put to release the fwnode. This path can be reached after probe itself has already released that fwnode though. Fix that by moving fwnode_handle_put in the happy path to the very end. Fixes: 18a6c866bb19 ("usb: typec: tps6598x: Add USB role switching logic") Signed-off-by: Sven Peter Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20221114174449.34634-2-sven@svenpeter.dev Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/typec/tps6598x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/tps6598x.c b/drivers/usb/typec/tps6598x.c index 6cb5c8e2c853..4722b7f7a4a2 100644 --- a/drivers/usb/typec/tps6598x.c +++ b/drivers/usb/typec/tps6598x.c @@ -564,7 +564,6 @@ static int tps6598x_probe(struct i2c_client *client) ret = PTR_ERR(tps->port); goto err_role_put; } - fwnode_handle_put(fwnode); if (status & TPS_STATUS_PLUG_PRESENT) { ret = tps6598x_connect(tps, status); @@ -583,6 +582,7 @@ static int tps6598x_probe(struct i2c_client *client) } i2c_set_clientdata(client, tps); + fwnode_handle_put(fwnode); return 0; From d5b16eb076f46c88d02d41ece5bec4e0d89158bb Mon Sep 17 00:00:00 2001 From: Jiamei Xie Date: Thu, 17 Nov 2022 18:32:37 +0800 Subject: [PATCH 0434/4345] serial: amba-pl011: avoid SBSA UART accessing DMACR register [ Upstream commit 94cdb9f33698478b0e7062586633c42c6158a786 ] Chapter "B Generic UART" in "ARM Server Base System Architecture" [1] documentation describes a generic UART interface. Such generic UART does not support DMA. In current code, sbsa_uart_pops and amba_pl011_pops share the same stop_rx operation, which will invoke pl011_dma_rx_stop, leading to an access of the DMACR register. This commit adds a using_rx_dma check in pl011_dma_rx_stop to avoid the access to DMACR register for SBSA UARTs which does not support DMA. When the kernel enables DMA engine with "CONFIG_DMA_ENGINE=y", Linux SBSA PL011 driver will access PL011 DMACR register in some functions. For most real SBSA Pl011 hardware implementations, the DMACR write behaviour will be ignored. So these DMACR operations will not cause obvious problems. But for some virtual SBSA PL011 hardware, like Xen virtual SBSA PL011 (vpl011) device, the behaviour might be different. Xen vpl011 emulation will inject a data abort to guest, when guest is accessing an unimplemented UART register. As Xen VPL011 is SBSA compatible, it will not implement DMACR register. So when Linux SBSA PL011 driver access DMACR register, it will get an unhandled data abort fault and the application will get a segmentation fault: Unhandled fault at 0xffffffc00944d048 Mem abort info: ESR = 0x96000000 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x00: ttbr address size fault Data abort info: ISV = 0, ISS = 0x00000000 CM = 0, WnR = 0 swapper pgtable: 4k pages, 39-bit VAs, pgdp=0000000020e2e000 [ffffffc00944d048] pgd=100000003ffff803, p4d=100000003ffff803, pud=100000003ffff803, pmd=100000003fffa803, pte=006800009c090f13 Internal error: ttbr address size fault: 96000000 [#1] PREEMPT SMP ... Call trace: pl011_stop_rx+0x70/0x80 tty_port_shutdown+0x7c/0xb4 tty_port_close+0x60/0xcc uart_close+0x34/0x8c tty_release+0x144/0x4c0 __fput+0x78/0x220 ____fput+0x1c/0x30 task_work_run+0x88/0xc0 do_notify_resume+0x8d0/0x123c el0_svc+0xa8/0xc0 el0t_64_sync_handler+0xa4/0x130 el0t_64_sync+0x1a0/0x1a4 Code: b9000083 b901f001 794038a0 8b000042 (b9000041) ---[ end trace 83dd93df15c3216f ]--- note: bootlogd[132] exited with preempt_count 1 /etc/rcS.d/S07bootlogd: line 47: 132 Segmentation fault start-stop-daemon This has been discussed in the Xen community, and we think it should fix this in Linux. See [2] for more information. [1] https://developer.arm.com/documentation/den0094/c/?lang=en [2] https://lists.xenproject.org/archives/html/xen-devel/2022-11/msg00543.html Fixes: 0dd1e247fd39 (drivers: PL011: add support for the ARM SBSA generic UART) Signed-off-by: Jiamei Xie Reviewed-by: Andre Przywara Link: https://lore.kernel.org/r/20221117103237.86856-1-jiamei.xie@arm.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/amba-pl011.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 9900ee3f9068..2f7373fc7bb7 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1048,6 +1048,9 @@ static void pl011_dma_rx_callback(void *data) */ static inline void pl011_dma_rx_stop(struct uart_amba_port *uap) { + if (!uap->using_rx_dma) + return; + /* FIXME. Just disable the DMA enable */ uap->dmacr &= ~UART011_RXDMAE; pl011_write(uap->dmacr, uap, REG_DMACR); From 46d08b0e0be590377c0e1b79b65d8f860abdb883 Mon Sep 17 00:00:00 2001 From: delisun Date: Thu, 10 Nov 2022 10:01:08 +0800 Subject: [PATCH 0435/4345] serial: pl011: Do not clear RX FIFO & RX interrupt in unthrottle. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 032d5a71ed378ffc6a2d41a187d8488a4f9fe415 ] Clearing the RX FIFO will cause data loss. Copy the pl011_enabl_interrupts implementation, and remove the clear interrupt and FIFO part of the code. Fixes: 211565b10099 ("serial: pl011: UPSTAT_AUTORTS requires .throttle/unthrottle") Signed-off-by: delisun Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20221110020108.7700-1-delisun@pateo.com.cn Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/amba-pl011.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 2f7373fc7bb7..348d4b2a391a 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1760,8 +1760,17 @@ static void pl011_enable_interrupts(struct uart_amba_port *uap) static void pl011_unthrottle_rx(struct uart_port *port) { struct uart_amba_port *uap = container_of(port, struct uart_amba_port, port); + unsigned long flags; - pl011_enable_interrupts(uap); + spin_lock_irqsave(&uap->port.lock, flags); + + uap->im = UART011_RTIM; + if (!pl011_dma_rx_running(uap)) + uap->im |= UART011_RXIM; + + pl011_write(uap->im, uap, REG_IMSC); + + spin_unlock_irqrestore(&uap->port.lock, flags); } static int pl011_startup(struct uart_port *port) From 07f4ca68b0f6bf84b6b391c14b59fd179fcde9c5 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Tue, 22 Nov 2022 19:45:59 +0800 Subject: [PATCH 0436/4345] serial: pch: Fix PCI device refcount leak in pch_request_dma() [ Upstream commit 8be3a7bf773700534a6e8f87f6ed2ed111254be5 ] As comment of pci_get_slot() says, it returns a pci_device with its refcount increased. The caller must decrement the reference count by calling pci_dev_put(). Since 'dma_dev' is only used to filter the channel in filter(), we can call pci_dev_put() before exiting from pch_request_dma(). Add the missing pci_dev_put() for the normal and error path. Fixes: 3c6a483275f4 ("Serial: EG20T: add PCH_UART driver") Signed-off-by: Xiongfeng Wang Link: https://lore.kernel.org/r/20221122114559.27692-1-wangxiongfeng2@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/pch_uart.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 351ad0b02029..fa2061f1cf3d 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -711,6 +711,7 @@ static void pch_request_dma(struct uart_port *port) if (!chan) { dev_err(priv->port.dev, "%s:dma_request_channel FAILS(Tx)\n", __func__); + pci_dev_put(dma_dev); return; } priv->chan_tx = chan; @@ -727,6 +728,7 @@ static void pch_request_dma(struct uart_port *port) __func__); dma_release_channel(priv->chan_tx); priv->chan_tx = NULL; + pci_dev_put(dma_dev); return; } @@ -734,6 +736,8 @@ static void pch_request_dma(struct uart_port *port) priv->rx_buf_virt = dma_alloc_coherent(port->dev, port->fifosize, &priv->rx_buf_dma, GFP_KERNEL); priv->chan_rx = chan; + + pci_dev_put(dma_dev); } static void pch_dma_rx_complete(void *arg) From af320d1a3cefec9c08a6682eab471e27528dbbcb Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 20 Sep 2022 07:20:42 +0200 Subject: [PATCH 0437/4345] tty: serial: clean up stop-tx part in altera_uart_tx_chars() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d9c128117da41cf4cb0e80ae565b5d3ac79dffac ] The "stop TX" path in altera_uart_tx_chars() is open-coded, so: * use uart_circ_empty() to check if the buffer is empty, and * when true, call altera_uart_stop_tx(). Cc: Tobias Klauser Reviewed-by: Ilpo Järvinen Acked-by: Tobias Klauser Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20220920052049.20507-3-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 1307c5d33cce ("serial: altera_uart: fix locking in polling mode") Signed-off-by: Sasha Levin --- drivers/tty/serial/altera_uart.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c index 0e487ce091ac..508a3c2b7781 100644 --- a/drivers/tty/serial/altera_uart.c +++ b/drivers/tty/serial/altera_uart.c @@ -274,10 +274,8 @@ static void altera_uart_tx_chars(struct altera_uart *pp) if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) uart_write_wakeup(port); - if (xmit->head == xmit->tail) { - pp->imr &= ~ALTERA_UART_CONTROL_TRDY_MSK; - altera_uart_update_ctrl_reg(pp); - } + if (uart_circ_empty(xmit)) + altera_uart_stop_tx(port); } static irqreturn_t altera_uart_interrupt(int irq, void *data) From 8ff88d007f1b4d296b01925a7f237e829c207a75 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 20 Sep 2022 07:20:43 +0200 Subject: [PATCH 0438/4345] tty: serial: altera_uart_{r,t}x_chars() need only uart_port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3af44d9bb0539d5fa27d6159d696fda5f3747bff ] Both altera_uart_{r,t}x_chars() need only uart_port, not altera_uart. So pass the former from altera_uart_interrupt() directly. Apart it maybe saves a dereference, this makes the transition of altera_uart_tx_chars() easier to follow in the next patch. Cc: Tobias Klauser Reviewed-by: Ilpo Järvinen Acked-by: Tobias Klauser Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20220920052049.20507-4-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 1307c5d33cce ("serial: altera_uart: fix locking in polling mode") Signed-off-by: Sasha Levin --- drivers/tty/serial/altera_uart.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c index 508a3c2b7781..20c610440133 100644 --- a/drivers/tty/serial/altera_uart.c +++ b/drivers/tty/serial/altera_uart.c @@ -199,9 +199,8 @@ static void altera_uart_set_termios(struct uart_port *port, */ } -static void altera_uart_rx_chars(struct altera_uart *pp) +static void altera_uart_rx_chars(struct uart_port *port) { - struct uart_port *port = &pp->port; unsigned char ch, flag; unsigned short status; @@ -248,9 +247,8 @@ static void altera_uart_rx_chars(struct altera_uart *pp) spin_lock(&port->lock); } -static void altera_uart_tx_chars(struct altera_uart *pp) +static void altera_uart_tx_chars(struct uart_port *port) { - struct uart_port *port = &pp->port; struct circ_buf *xmit = &port->state->xmit; if (port->x_char) { @@ -288,9 +286,9 @@ static irqreturn_t altera_uart_interrupt(int irq, void *data) spin_lock(&port->lock); if (isr & ALTERA_UART_STATUS_RRDY_MSK) - altera_uart_rx_chars(pp); + altera_uart_rx_chars(port); if (isr & ALTERA_UART_STATUS_TRDY_MSK) - altera_uart_tx_chars(pp); + altera_uart_tx_chars(port); spin_unlock(&port->lock); return IRQ_RETVAL(isr); From a26b13d158ae39c40e080e5a827a73261095d74a Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 22 Nov 2022 15:04:26 -0500 Subject: [PATCH 0439/4345] serial: altera_uart: fix locking in polling mode [ Upstream commit 1307c5d33cce8a41dd77c2571e4df65a5b627feb ] Since altera_uart_interrupt() may also be called from a poll timer in "serving_softirq" context, use spin_[lock_irqsave|unlock_irqrestore] variants, which are appropriate for both softirq and hardware interrupt contexts. Fixes: 2f8b9c15cd88 ("altera_uart: Add support for polling mode (IRQ-less)") Signed-off-by: Gabriel Somlo Link: https://lore.kernel.org/r/20221122200426.888349-1-gsomlo@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/altera_uart.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c index 20c610440133..d91f76b1d353 100644 --- a/drivers/tty/serial/altera_uart.c +++ b/drivers/tty/serial/altera_uart.c @@ -280,16 +280,17 @@ static irqreturn_t altera_uart_interrupt(int irq, void *data) { struct uart_port *port = data; struct altera_uart *pp = container_of(port, struct altera_uart, port); + unsigned long flags; unsigned int isr; isr = altera_uart_readl(port, ALTERA_UART_STATUS_REG) & pp->imr; - spin_lock(&port->lock); + spin_lock_irqsave(&port->lock, flags); if (isr & ALTERA_UART_STATUS_RRDY_MSK) altera_uart_rx_chars(port); if (isr & ALTERA_UART_STATUS_TRDY_MSK) altera_uart_tx_chars(port); - spin_unlock(&port->lock); + spin_unlock_irqrestore(&port->lock, flags); return IRQ_RETVAL(isr); } From d7c4331c073aa4fa9e721c8d5d9842f91f25fcd2 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Wed, 23 Nov 2022 06:12:12 +0000 Subject: [PATCH 0440/4345] serial: sunsab: Fix error handling in sunsab_init() [ Upstream commit 1a6ec673fb627c26e2267ca0a03849f91dbd9b40 ] The sunsab_init() returns the platform_driver_register() directly without checking its return value, if platform_driver_register() failed, the allocated sunsab_ports is leaked. Fix by free sunsab_ports and set it to NULL when platform_driver_register() failed. Fixes: c4d37215a824 ("[SERIAL] sunsab: Convert to of_driver framework.") Signed-off-by: Yuan Can Link: https://lore.kernel.org/r/20221123061212.52593-1-yuancan@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/sunsab.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c index bab551f46963..451c7233623f 100644 --- a/drivers/tty/serial/sunsab.c +++ b/drivers/tty/serial/sunsab.c @@ -1137,7 +1137,13 @@ static int __init sunsab_init(void) } } - return platform_driver_register(&sab_driver); + err = platform_driver_register(&sab_driver); + if (err) { + kfree(sunsab_ports); + sunsab_ports = NULL; + } + + return err; } static void __exit sunsab_exit(void) From 0b5a89e8bce1ea43687742b4de8e216189ff94ac Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Sat, 19 Nov 2022 11:57:21 +0800 Subject: [PATCH 0441/4345] test_firmware: fix memory leak in test_firmware_init() [ Upstream commit 7610615e8cdb3f6f5bbd9d8e7a5d8a63e3cabf2e ] When misc_register() failed in test_firmware_init(), the memory pointed by test_fw_config->name is not released. The memory leak information is as follows: unreferenced object 0xffff88810a34cb00 (size 32): comm "insmod", pid 7952, jiffies 4294948236 (age 49.060s) hex dump (first 32 bytes): 74 65 73 74 2d 66 69 72 6d 77 61 72 65 2e 62 69 test-firmware.bi 6e 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 n............... backtrace: [] __kmalloc_node_track_caller+0x4b/0xc0 [] kstrndup+0x46/0xc0 [] __test_firmware_config_init+0x29/0x380 [test_firmware] [] 0xffffffffa040f068 [] do_one_initcall+0x141/0x780 [] do_init_module+0x1c3/0x630 [] load_module+0x623e/0x76a0 [] __do_sys_finit_module+0x181/0x240 [] do_syscall_64+0x39/0xb0 [] entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: c92316bf8e94 ("test_firmware: add batched firmware tests") Signed-off-by: Zhengchao Shao Acked-by: Luis Chamberlain Link: https://lore.kernel.org/r/20221119035721.18268-1-shaozhengchao@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- lib/test_firmware.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 2baa275a6ddf..76550d2e2edc 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -1114,6 +1114,7 @@ static int __init test_firmware_init(void) rc = misc_register(&test_fw_misc_device); if (rc) { + __test_firmware_config_free(); kfree(test_fw_config); pr_err("could not register misc device: %d\n", rc); return rc; From 7525741cb302a1672b8c3a5edb2a08e4229b5c7c Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 11 Nov 2022 22:59:29 +0800 Subject: [PATCH 0442/4345] misc: ocxl: fix possible name leak in ocxl_file_register_afu() [ Upstream commit a4cb1004aeed2ab893a058fad00a5b41a12c4691 ] If device_register() returns error in ocxl_file_register_afu(), the name allocated by dev_set_name() need be freed. As comment of device_register() says, it should use put_device() to give up the reference in the error path. So fix this by calling put_device(), then the name can be freed in kobject_cleanup(), and info is freed in info_release(). Fixes: 75ca758adbaf ("ocxl: Create a clear delineation between ocxl backend & frontend") Signed-off-by: Yang Yingliang Acked-by: Andrew Donnellan Acked-by: Frederic Barrat Link: https://lore.kernel.org/r/20221111145929.2429271-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/ocxl/file.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index e094809b54ff..524ded87964d 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -543,8 +543,11 @@ int ocxl_file_register_afu(struct ocxl_afu *afu) goto err_put; rc = device_register(&info->dev); - if (rc) - goto err_put; + if (rc) { + free_minor(info); + put_device(&info->dev); + return rc; + } rc = ocxl_sysfs_register_afu(info); if (rc) From a40e1b0a922a53fa925ea8b296e3de30a31ed028 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 21 Nov 2022 23:43:39 +0800 Subject: [PATCH 0443/4345] ocxl: fix pci device refcount leak when calling get_function_0() [ Upstream commit 27158c72678b39ee01cc01de1aba6b51c71abe2f ] get_function_0() calls pci_get_domain_bus_and_slot(), as comment says, it returns a pci device with refcount increment, so after using it, pci_dev_put() needs be called. Get the device reference when get_function_0() is not called, so pci_dev_put() can be called in the error path and callers unconditionally. And add comment above get_dvsec_vendor0() to tell callers to call pci_dev_put(). Fixes: 87db7579ebd5 ("ocxl: control via sysfs whether the FPGA is reloaded on a link reset") Suggested-by: Andrew Donnellan Signed-off-by: Yang Yingliang Acked-by: Andrew Donnellan Link: https://lore.kernel.org/r/20221121154339.4088935-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/ocxl/config.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c index 4d490b92d951..3ced98b506f4 100644 --- a/drivers/misc/ocxl/config.c +++ b/drivers/misc/ocxl/config.c @@ -204,6 +204,18 @@ static int read_dvsec_vendor(struct pci_dev *dev) return 0; } +/** + * get_dvsec_vendor0() - Find a related PCI device (function 0) + * @dev: PCI device to match + * @dev0: The PCI device (function 0) found + * @out_pos: The position of PCI device (function 0) + * + * Returns 0 on success, negative on failure. + * + * NOTE: If it's successful, the reference of dev0 is increased, + * so after using it, the callers must call pci_dev_put() to give + * up the reference. + */ static int get_dvsec_vendor0(struct pci_dev *dev, struct pci_dev **dev0, int *out_pos) { @@ -213,10 +225,14 @@ static int get_dvsec_vendor0(struct pci_dev *dev, struct pci_dev **dev0, dev = get_function_0(dev); if (!dev) return -1; + } else { + dev = pci_dev_get(dev); } pos = find_dvsec(dev, OCXL_DVSEC_VENDOR_ID); - if (!pos) + if (!pos) { + pci_dev_put(dev); return -1; + } *dev0 = dev; *out_pos = pos; return 0; @@ -233,6 +249,7 @@ int ocxl_config_get_reset_reload(struct pci_dev *dev, int *val) pci_read_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD, &reset_reload); + pci_dev_put(dev0); *val = !!(reset_reload & BIT(0)); return 0; } @@ -254,6 +271,7 @@ int ocxl_config_set_reset_reload(struct pci_dev *dev, int val) reset_reload &= ~BIT(0); pci_write_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD, reset_reload); + pci_dev_put(dev0); return 0; } From 57c857353d5020bdec8284d9c0fee447484fe5e0 Mon Sep 17 00:00:00 2001 From: ruanjinjie Date: Thu, 17 Nov 2022 14:47:25 +0800 Subject: [PATCH 0444/4345] misc: tifm: fix possible memory leak in tifm_7xx1_switch_media() [ Upstream commit fd2c930cf6a5b9176382c15f9acb1996e76e25ad ] If device_register() returns error in tifm_7xx1_switch_media(), name of kobject which is allocated in dev_set_name() called in device_add() is leaked. Never directly free @dev after calling device_register(), even if it returned an error! Always use put_device() to give up the reference initialized. Fixes: 2428a8fe2261 ("tifm: move common device management tasks from tifm_7xx1 to tifm_core") Signed-off-by: ruanjinjie Link: https://lore.kernel.org/r/20221117064725.3478402-1-ruanjinjie@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/tifm_7xx1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/tifm_7xx1.c b/drivers/misc/tifm_7xx1.c index 228f2eb1d476..2aebbfda104d 100644 --- a/drivers/misc/tifm_7xx1.c +++ b/drivers/misc/tifm_7xx1.c @@ -190,7 +190,7 @@ static void tifm_7xx1_switch_media(struct work_struct *work) spin_unlock_irqrestore(&fm->lock, flags); } if (sock) - tifm_free_device(&sock->dev); + put_device(&sock->dev); } spin_lock_irqsave(&fm->lock, flags); } From 0f67ed565f20ea2fdd98e3b0b0169d9e580bb83c Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Thu, 10 Nov 2022 11:50:33 +0800 Subject: [PATCH 0445/4345] misc: sgi-gru: fix use-after-free error in gru_set_context_option, gru_fault and gru_handle_user_call_os [ Upstream commit 643a16a0eb1d6ac23744bb6e90a00fc21148a9dc ] In some bad situation, the gts may be freed gru_check_chiplet_assignment. The call chain can be gru_unload_context->gru_free_gru_context->gts_drop and kfree finally. However, the caller didn't know if the gts is freed or not and use it afterwards. This will trigger a Use after Free bug. Fix it by introducing a return value to see if it's in error path or not. Free the gts in caller if gru_check_chiplet_assignment check failed. Fixes: 55484c45dbec ("gru: allow users to specify gru chiplet 2") Signed-off-by: Zheng Wang Acked-by: Dimitri Sivanich Link: https://lore.kernel.org/r/20221110035033.19498-1-zyytlz.wz@163.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/sgi-gru/grufault.c | 13 +++++++++++-- drivers/misc/sgi-gru/grumain.c | 22 ++++++++++++++++++---- drivers/misc/sgi-gru/grutables.h | 2 +- 3 files changed, 30 insertions(+), 7 deletions(-) diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c index 723825524ea0..9c7d475d1890 100644 --- a/drivers/misc/sgi-gru/grufault.c +++ b/drivers/misc/sgi-gru/grufault.c @@ -648,6 +648,7 @@ int gru_handle_user_call_os(unsigned long cb) if ((cb & (GRU_HANDLE_STRIDE - 1)) || ucbnum >= GRU_NUM_CB) return -EINVAL; +again: gts = gru_find_lock_gts(cb); if (!gts) return -EINVAL; @@ -656,7 +657,11 @@ int gru_handle_user_call_os(unsigned long cb) if (ucbnum >= gts->ts_cbr_au_count * GRU_CBR_AU_SIZE) goto exit; - gru_check_context_placement(gts); + if (gru_check_context_placement(gts)) { + gru_unlock_gts(gts); + gru_unload_context(gts, 1); + goto again; + } /* * CCH may contain stale data if ts_force_cch_reload is set. @@ -874,7 +879,11 @@ int gru_set_context_option(unsigned long arg) } else { gts->ts_user_blade_id = req.val1; gts->ts_user_chiplet_id = req.val0; - gru_check_context_placement(gts); + if (gru_check_context_placement(gts)) { + gru_unlock_gts(gts); + gru_unload_context(gts, 1); + return ret; + } } break; case sco_gseg_owner: diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c index 40ac59dd018c..e2325e3d077e 100644 --- a/drivers/misc/sgi-gru/grumain.c +++ b/drivers/misc/sgi-gru/grumain.c @@ -716,9 +716,10 @@ static int gru_check_chiplet_assignment(struct gru_state *gru, * chiplet. Misassignment can occur if the process migrates to a different * blade or if the user changes the selected blade/chiplet. */ -void gru_check_context_placement(struct gru_thread_state *gts) +int gru_check_context_placement(struct gru_thread_state *gts) { struct gru_state *gru; + int ret = 0; /* * If the current task is the context owner, verify that the @@ -726,15 +727,23 @@ void gru_check_context_placement(struct gru_thread_state *gts) * references. Pthread apps use non-owner references to the CBRs. */ gru = gts->ts_gru; + /* + * If gru or gts->ts_tgid_owner isn't initialized properly, return + * success to indicate that the caller does not need to unload the + * gru context.The caller is responsible for their inspection and + * reinitialization if needed. + */ if (!gru || gts->ts_tgid_owner != current->tgid) - return; + return ret; if (!gru_check_chiplet_assignment(gru, gts)) { STAT(check_context_unload); - gru_unload_context(gts, 1); + ret = -EINVAL; } else if (gru_retarget_intr(gts)) { STAT(check_context_retarget_intr); } + + return ret; } @@ -934,7 +943,12 @@ again: mutex_lock(>s->ts_ctxlock); preempt_disable(); - gru_check_context_placement(gts); + if (gru_check_context_placement(gts)) { + preempt_enable(); + mutex_unlock(>s->ts_ctxlock); + gru_unload_context(gts, 1); + return VM_FAULT_NOPAGE; + } if (!gts->ts_gru) { STAT(load_user_context); diff --git a/drivers/misc/sgi-gru/grutables.h b/drivers/misc/sgi-gru/grutables.h index 5ce8f3081e96..10f0a083b1fa 100644 --- a/drivers/misc/sgi-gru/grutables.h +++ b/drivers/misc/sgi-gru/grutables.h @@ -637,7 +637,7 @@ extern int gru_user_flush_tlb(unsigned long arg); extern int gru_user_unload_context(unsigned long arg); extern int gru_get_exception_detail(unsigned long arg); extern int gru_set_context_option(unsigned long address); -extern void gru_check_context_placement(struct gru_thread_state *gts); +extern int gru_check_context_placement(struct gru_thread_state *gts); extern int gru_cpu_fault_map_id(void); extern struct vm_area_struct *gru_find_vma(unsigned long vaddr); extern void gru_flush_all_tlb(struct gru_state *gru); From d34742245e4366579f9a80f8cfe4a63248e838e0 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 17 Nov 2022 15:06:36 +0800 Subject: [PATCH 0446/4345] firmware: raspberrypi: fix possible memory leak in rpi_firmware_probe() [ Upstream commit 7b51161696e803fd5f9ad55b20a64c2df313f95c ] In rpi_firmware_probe(), if mbox_request_channel() fails, the 'fw' will not be freed through rpi_firmware_delete(), fix this leak by calling kfree() in the error path. Fixes: 1e7c57355a3b ("firmware: raspberrypi: Keep count of all consumers") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221117070636.3849773-1-yangyingliang@huawei.com Acked-by: Joel Savitz Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/firmware/raspberrypi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c index 1d965c1252ca..9eef49da47e0 100644 --- a/drivers/firmware/raspberrypi.c +++ b/drivers/firmware/raspberrypi.c @@ -265,6 +265,7 @@ static int rpi_firmware_probe(struct platform_device *pdev) int ret = PTR_ERR(fw->chan); if (ret != -EPROBE_DEFER) dev_err(dev, "Failed to get mbox channel: %d\n", ret); + kfree(fw); return ret; } From 170e8c2d2b61e15e7f7cfeded81bc1e959a15ed8 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 11 Nov 2022 22:54:39 +0800 Subject: [PATCH 0447/4345] cxl: fix possible null-ptr-deref in cxl_guest_init_afu|adapter() [ Upstream commit 61c80d1c3833e196256fb060382db94f24d3d9a7 ] If device_register() fails in cxl_register_afu|adapter(), the device is not added, device_unregister() can not be called in the error path, otherwise it will cause a null-ptr-deref because of removing not added device. As comment of device_register() says, it should use put_device() to give up the reference in the error path. So split device_unregister() into device_del() and put_device(), then goes to put dev when register fails. Fixes: 14baf4d9c739 ("cxl: Add guest-specific code") Signed-off-by: Yang Yingliang Acked-by: Andrew Donnellan Acked-by: Frederic Barrat Link: https://lore.kernel.org/r/20221111145440.2426970-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/cxl/guest.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/misc/cxl/guest.c b/drivers/misc/cxl/guest.c index 186308f1f8eb..6334376826a9 100644 --- a/drivers/misc/cxl/guest.c +++ b/drivers/misc/cxl/guest.c @@ -959,10 +959,10 @@ int cxl_guest_init_afu(struct cxl *adapter, int slice, struct device_node *afu_n * if it returns an error! */ if ((rc = cxl_register_afu(afu))) - goto err_put1; + goto err_put_dev; if ((rc = cxl_sysfs_afu_add(afu))) - goto err_put1; + goto err_del_dev; /* * pHyp doesn't expose the programming models supported by the @@ -978,7 +978,7 @@ int cxl_guest_init_afu(struct cxl *adapter, int slice, struct device_node *afu_n afu->modes_supported = CXL_MODE_DIRECTED; if ((rc = cxl_afu_select_best_mode(afu))) - goto err_put2; + goto err_remove_sysfs; adapter->afu[afu->slice] = afu; @@ -998,10 +998,12 @@ int cxl_guest_init_afu(struct cxl *adapter, int slice, struct device_node *afu_n return 0; -err_put2: +err_remove_sysfs: cxl_sysfs_afu_remove(afu); -err_put1: - device_unregister(&afu->dev); +err_del_dev: + device_del(&afu->dev); +err_put_dev: + put_device(&afu->dev); free = false; guest_release_serr_irq(afu); err2: @@ -1135,18 +1137,20 @@ struct cxl *cxl_guest_init_adapter(struct device_node *np, struct platform_devic * even if it returns an error! */ if ((rc = cxl_register_adapter(adapter))) - goto err_put1; + goto err_put_dev; if ((rc = cxl_sysfs_adapter_add(adapter))) - goto err_put1; + goto err_del_dev; /* release the context lock as the adapter is configured */ cxl_adapter_context_unlock(adapter); return adapter; -err_put1: - device_unregister(&adapter->dev); +err_del_dev: + device_del(&adapter->dev); +err_put_dev: + put_device(&adapter->dev); free = false; cxl_guest_remove_chardev(adapter); err1: From 0f63c0ddc2ea20d783d29243f4dbe0f9e95dfdec Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 11 Nov 2022 22:54:40 +0800 Subject: [PATCH 0448/4345] cxl: fix possible null-ptr-deref in cxl_pci_init_afu|adapter() [ Upstream commit 02cd3032b154fa02fdf90e7467abaeed889330b2 ] If device_register() fails in cxl_pci_afu|adapter(), the device is not added, device_unregister() can not be called in the error path, otherwise it will cause a null-ptr-deref because of removing not added device. As comment of device_register() says, it should use put_device() to give up the reference in the error path. So split device_unregister() into device_del() and put_device(), then goes to put dev when register fails. Fixes: f204e0b8cedd ("cxl: Driver code for powernv PCIe based cards for userspace access") Signed-off-by: Yang Yingliang Acked-by: Frederic Barrat Acked-by: Andrew Donnellan Link: https://lore.kernel.org/r/20221111145440.2426970-2-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/cxl/pci.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 2ba899f5659f..0ac3f4cb88ac 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -1164,10 +1164,10 @@ static int pci_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev) * if it returns an error! */ if ((rc = cxl_register_afu(afu))) - goto err_put1; + goto err_put_dev; if ((rc = cxl_sysfs_afu_add(afu))) - goto err_put1; + goto err_del_dev; adapter->afu[afu->slice] = afu; @@ -1176,10 +1176,12 @@ static int pci_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev) return 0; -err_put1: +err_del_dev: + device_del(&afu->dev); +err_put_dev: pci_deconfigure_afu(afu); cxl_debugfs_afu_remove(afu); - device_unregister(&afu->dev); + put_device(&afu->dev); return rc; err_free_native: @@ -1667,23 +1669,25 @@ static struct cxl *cxl_pci_init_adapter(struct pci_dev *dev) * even if it returns an error! */ if ((rc = cxl_register_adapter(adapter))) - goto err_put1; + goto err_put_dev; if ((rc = cxl_sysfs_adapter_add(adapter))) - goto err_put1; + goto err_del_dev; /* Release the context lock as adapter is configured */ cxl_adapter_context_unlock(adapter); return adapter; -err_put1: +err_del_dev: + device_del(&adapter->dev); +err_put_dev: /* This should mirror cxl_remove_adapter, except without the * sysfs parts */ cxl_debugfs_adapter_remove(adapter); cxl_deconfigure_adapter(adapter); - device_unregister(&adapter->dev); + put_device(&adapter->dev); return ERR_PTR(rc); err_release: From 6b22e715bb5bba3ec5844cf5b58a9f6021939698 Mon Sep 17 00:00:00 2001 From: Cosmin Tanislav Date: Thu, 3 Nov 2022 15:00:29 +0200 Subject: [PATCH 0449/4345] iio: temperature: ltc2983: make bulk write buffer DMA-safe [ Upstream commit 5e0176213949724fbe9a8e4a39817edce337b8a0 ] regmap_bulk_write() does not guarantee implicit DMA-safety, even though the current implementation duplicates the given buffer. Do not rely on it. Fixes: f110f3188e56 ("iio: temperature: Add support for LTC2983") Signed-off-by: Cosmin Tanislav Link: https://lore.kernel.org/r/20221103130041.2153295-2-demonsingur@gmail.com Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/temperature/ltc2983.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/iio/temperature/ltc2983.c b/drivers/iio/temperature/ltc2983.c index 8306daa77908..b2ae2d2c7eef 100644 --- a/drivers/iio/temperature/ltc2983.c +++ b/drivers/iio/temperature/ltc2983.c @@ -205,6 +205,7 @@ struct ltc2983_data { * Holds the converted temperature */ __be32 temp ____cacheline_aligned; + __be32 chan_val; }; struct ltc2983_sensor { @@ -309,19 +310,18 @@ static int __ltc2983_fault_handler(const struct ltc2983_data *st, return 0; } -static int __ltc2983_chan_assign_common(const struct ltc2983_data *st, +static int __ltc2983_chan_assign_common(struct ltc2983_data *st, const struct ltc2983_sensor *sensor, u32 chan_val) { u32 reg = LTC2983_CHAN_START_ADDR(sensor->chan); - __be32 __chan_val; chan_val |= LTC2983_CHAN_TYPE(sensor->type); dev_dbg(&st->spi->dev, "Assign reg:0x%04X, val:0x%08X\n", reg, chan_val); - __chan_val = cpu_to_be32(chan_val); - return regmap_bulk_write(st->regmap, reg, &__chan_val, - sizeof(__chan_val)); + st->chan_val = cpu_to_be32(chan_val); + return regmap_bulk_write(st->regmap, reg, &st->chan_val, + sizeof(st->chan_val)); } static int __ltc2983_chan_custom_sensor_assign(struct ltc2983_data *st, From 50aaa6b1742cb26f718bc72f4196aaf6a4efa7a7 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Wed, 3 Mar 2021 11:49:15 +1300 Subject: [PATCH 0450/4345] genirq: Add IRQF_NO_AUTOEN for request_irq/nmi() [ Upstream commit cbe16f35bee6880becca6f20d2ebf6b457148552 ] Many drivers don't want interrupts enabled automatically via request_irq(). So they are handling this issue by either way of the below two: (1) irq_set_status_flags(irq, IRQ_NOAUTOEN); request_irq(dev, irq...); (2) request_irq(dev, irq...); disable_irq(irq); The code in the second way is silly and unsafe. In the small time gap between request_irq() and disable_irq(), interrupts can still come. The code in the first way is safe though it's subobtimal. Add a new IRQF_NO_AUTOEN flag which can be handed in by drivers to request_irq() and request_nmi(). It prevents the automatic enabling of the requested interrupt/nmi in the same safe way as #1 above. With that the various usage sites of #1 and #2 above can be simplified and corrected. Signed-off-by: Barry Song Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Cc: dmitry.torokhov@gmail.com Link: https://lore.kernel.org/r/20210302224916.13980-2-song.bao.hua@hisilicon.com Stable-dep-of: 99c05e4283a1 ("iio: adis: add '__adis_enable_irq()' implementation") Signed-off-by: Sasha Levin --- include/linux/interrupt.h | 4 ++++ kernel/irq/manage.c | 11 +++++++++-- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index ee8299eb1f52..0652b4858ba6 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -61,6 +61,9 @@ * interrupt handler after suspending interrupts. For system * wakeup devices users need to implement wakeup detection in * their interrupt handlers. + * IRQF_NO_AUTOEN - Don't enable IRQ or NMI automatically when users request it. + * Users will enable it explicitly by enable_irq() or enable_nmi() + * later. */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 @@ -74,6 +77,7 @@ #define IRQF_NO_THREAD 0x00010000 #define IRQF_EARLY_RESUME 0x00020000 #define IRQF_COND_SUSPEND 0x00040000 +#define IRQF_NO_AUTOEN 0x00080000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3cb29835632f..437b073dc487 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1667,7 +1667,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irqd_set(&desc->irq_data, IRQD_NO_BALANCING); } - if (irq_settings_can_autoenable(desc)) { + if (!(new->flags & IRQF_NO_AUTOEN) && + irq_settings_can_autoenable(desc)) { irq_startup(desc, IRQ_RESEND, IRQ_START_COND); } else { /* @@ -2054,10 +2055,15 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, * which interrupt is which (messes up the interrupt freeing * logic etc). * + * Also shared interrupts do not go well with disabling auto enable. + * The sharing interrupt might request it while it's still disabled + * and then wait for interrupts forever. + * * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and * it cannot be set along with IRQF_NO_SUSPEND. */ if (((irqflags & IRQF_SHARED) && !dev_id) || + ((irqflags & IRQF_SHARED) && (irqflags & IRQF_NO_AUTOEN)) || (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) || ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND))) return -EINVAL; @@ -2213,7 +2219,8 @@ int request_nmi(unsigned int irq, irq_handler_t handler, desc = irq_to_desc(irq); - if (!desc || irq_settings_can_autoenable(desc) || + if (!desc || (irq_settings_can_autoenable(desc) && + !(irqflags & IRQF_NO_AUTOEN)) || !irq_settings_can_request(desc) || WARN_ON(irq_settings_is_per_cpu_devid(desc)) || !irq_supports_nmi(desc)) From 8eb2a679c603a59c7caa3611906597a090001622 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Fri, 2 Apr 2021 19:45:43 +0100 Subject: [PATCH 0451/4345] iio:imu:adis: Use IRQF_NO_AUTOEN instead of irq request then disable [ Upstream commit 30f6a542b7d39b1ba990a28a3891bc03691d8d41 ] This is a bit involved as the adis library code already has some sanity checking of the flags of the requested irq that we need to ensure is happy to pass through the IRQF_NO_AUTOEN flag untouched. Using this flag avoids us autoenabling the irq in the adis16460 and adis16475 drivers which cover parts that don't have any means of masking the interrupt on the device end. Note, compile tested only! Signed-off-by: Jonathan Cameron Cc: Alexandru Ardelean Reviewed-by: Nuno Sa Reviewed-by: Barry Song Reviewed-by: Andy Shevchenko Reviewed-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20210402184544.488862-7-jic23@kernel.org Stable-dep-of: 99c05e4283a1 ("iio: adis: add '__adis_enable_irq()' implementation") Signed-off-by: Sasha Levin --- drivers/iio/imu/adis16460.c | 4 ++-- drivers/iio/imu/adis16475.c | 5 +++-- drivers/iio/imu/adis_trigger.c | 11 ++++++----- 3 files changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/iio/imu/adis16460.c b/drivers/iio/imu/adis16460.c index 74a161e39733..73bf45e859b8 100644 --- a/drivers/iio/imu/adis16460.c +++ b/drivers/iio/imu/adis16460.c @@ -403,12 +403,12 @@ static int adis16460_probe(struct spi_device *spi) if (ret) return ret; + /* We cannot mask the interrupt, so ensure it isn't auto enabled */ + st->adis.irq_flag |= IRQF_NO_AUTOEN; ret = devm_adis_setup_buffer_and_trigger(&st->adis, indio_dev, NULL); if (ret) return ret; - adis16460_enable_irq(&st->adis, 0); - ret = __adis_initial_startup(&st->adis); if (ret) return ret; diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c index 3c4e4deb8760..8ab88ba4892c 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -1196,6 +1196,9 @@ static int adis16475_config_irq_pin(struct adis16475 *st) return -EINVAL; } + /* We cannot mask the interrupt so ensure it's not enabled at request */ + st->adis.irq_flag |= IRQF_NO_AUTOEN; + val = ADIS16475_MSG_CTRL_DR_POL(polarity); ret = __adis_update_bits(&st->adis, ADIS16475_REG_MSG_CTRL, ADIS16475_MSG_CTRL_DR_POL_MASK, val); @@ -1300,8 +1303,6 @@ static int adis16475_probe(struct spi_device *spi) if (ret) return ret; - adis16475_enable_irq(&st->adis, false); - ret = devm_iio_device_register(&spi->dev, indio_dev); if (ret) return ret; diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index 64e0ba51cb18..17058ac7aa9f 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -36,18 +36,19 @@ static void adis_trigger_setup(struct adis *adis) static int adis_validate_irq_flag(struct adis *adis) { + unsigned long direction = adis->irq_flag & IRQF_TRIGGER_MASK; /* * Typically this devices have data ready either on the rising edge or * on the falling edge of the data ready pin. This checks enforces that * one of those is set in the drivers... It defaults to - * IRQF_TRIGGER_RISING for backward compatibility wiht devices that + * IRQF_TRIGGER_RISING for backward compatibility with devices that * don't support changing the pin polarity. */ - if (!adis->irq_flag) { - adis->irq_flag = IRQF_TRIGGER_RISING; + if (direction == IRQF_TRIGGER_NONE) { + adis->irq_flag |= IRQF_TRIGGER_RISING; return 0; - } else if (adis->irq_flag != IRQF_TRIGGER_RISING && - adis->irq_flag != IRQF_TRIGGER_FALLING) { + } else if (direction != IRQF_TRIGGER_RISING && + direction != IRQF_TRIGGER_FALLING) { dev_err(&adis->spi->dev, "Invalid IRQ mask: %08lx\n", adis->irq_flag); return -EINVAL; From d1b73eebc70defee59236a4ae37477d668c7b67b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Fri, 3 Sep 2021 16:14:20 +0200 Subject: [PATCH 0452/4345] iio: adis: handle devices that cannot unmask the drdy pin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 31fa357ac809affd9f9a7d0b5d1991951e16beec ] Some devices can't mask/unmask the data ready pin and in those cases each driver was just calling '{dis}enable_irq()' to control the trigger state. This change, moves that handling into the library by introducing a new boolean in the data structure that tells the library that the device cannot unmask the pin. On top of controlling the trigger state, we can also use this flag to automatically request the IRQ with 'IRQF_NO_AUTOEN' in case it is set. So far, all users of the library want to start operation with IRQs/DRDY pin disabled so it should be fairly safe to do this inside the library. Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20210903141423.517028-3-nuno.sa@analog.com Signed-off-by: Jonathan Cameron Stable-dep-of: 99c05e4283a1 ("iio: adis: add '__adis_enable_irq()' implementation") Signed-off-by: Sasha Levin --- drivers/iio/imu/adis.c | 15 ++++++++++++++- drivers/iio/imu/adis_trigger.c | 4 ++++ include/linux/iio/imu/adis.h | 2 ++ 3 files changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index 715eef81bc24..5fcf269e98a6 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -290,6 +290,13 @@ int adis_enable_irq(struct adis *adis, bool enable) if (adis->data->enable_irq) { ret = adis->data->enable_irq(adis, enable); goto out_unlock; + } else if (adis->data->unmasked_drdy) { + if (enable) + enable_irq(adis->spi->irq); + else + disable_irq(adis->spi->irq); + + goto out_unlock; } ret = __adis_read_reg_16(adis, adis->data->msc_ctrl_reg, &msc); @@ -434,7 +441,13 @@ int __adis_initial_startup(struct adis *adis) if (ret) return ret; - adis_enable_irq(adis, false); + /* + * don't bother calling this if we can't unmask the IRQ as in this case + * the IRQ is most likely not yet requested and we will request it + * with 'IRQF_NO_AUTOEN' anyways. + */ + if (!adis->data->unmasked_drdy) + adis_enable_irq(adis, false); if (!adis->data->prod_id_reg) return 0; diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index 17058ac7aa9f..76b0488ef41b 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -37,6 +37,10 @@ static void adis_trigger_setup(struct adis *adis) static int adis_validate_irq_flag(struct adis *adis) { unsigned long direction = adis->irq_flag & IRQF_TRIGGER_MASK; + + /* We cannot mask the interrupt so ensure it's not enabled at request */ + if (adis->data->unmasked_drdy) + adis->irq_flag |= IRQF_NO_AUTOEN; /* * Typically this devices have data ready either on the rising edge or * on the falling edge of the data ready pin. This checks enforces that diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 04e96d688ba9..2ced0c88f481 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -49,6 +49,7 @@ struct adis_timeout { * @status_error_mask: Bitmask of errors supported by the device * @timeouts: Chip specific delays * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable + * @unmasked_drdy: True for devices that cannot mask/unmask the data ready pin * @has_paging: True if ADIS device has paged registers * @burst_reg_cmd: Register command that triggers burst * @burst_len: Burst size in the SPI RX buffer. If @burst_max_len is defined, @@ -77,6 +78,7 @@ struct adis_data { unsigned int status_error_mask; int (*enable_irq)(struct adis *adis, bool enable); + bool unmasked_drdy; bool has_paging; From 83e321a2ec4d7e81e6b043a37607095f12b53079 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Sat, 22 Jan 2022 14:09:05 +0100 Subject: [PATCH 0453/4345] iio: adis: stylistic changes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c39010ea6ba13bdf0003bd353e1d4c663aaac0a8 ] Minor stylistic changes to address checkptach complains when called with '--strict'. Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20220122130905.99-3-nuno.sa@analog.com Signed-off-by: Jonathan Cameron Stable-dep-of: 99c05e4283a1 ("iio: adis: add '__adis_enable_irq()' implementation") Signed-off-by: Sasha Levin --- drivers/iio/imu/adis.c | 47 +++++++++++++++++---------------- drivers/iio/imu/adis_buffer.c | 6 ++--- drivers/iio/imu/adis_trigger.c | 3 +-- include/linux/iio/imu/adis.h | 48 ++++++++++++++++++---------------- 4 files changed, 54 insertions(+), 50 deletions(-) diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index 5fcf269e98a6..54d1084f13d0 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -34,8 +34,8 @@ * @value: The value to write to device (up to 4 bytes) * @size: The size of the @value (in bytes) */ -int __adis_write_reg(struct adis *adis, unsigned int reg, - unsigned int value, unsigned int size) +int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int value, + unsigned int size) { unsigned int page = reg / ADIS_PAGE_SIZE; int ret, i; @@ -118,7 +118,7 @@ int __adis_write_reg(struct adis *adis, unsigned int reg, ret = spi_sync(adis->spi, &msg); if (ret) { dev_err(&adis->spi->dev, "Failed to write register 0x%02X: %d\n", - reg, ret); + reg, ret); } else { adis->current_page = page; } @@ -134,8 +134,8 @@ EXPORT_SYMBOL_GPL(__adis_write_reg); * @val: The value read back from the device * @size: The size of the @val buffer */ -int __adis_read_reg(struct adis *adis, unsigned int reg, - unsigned int *val, unsigned int size) +int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val, + unsigned int size) { unsigned int page = reg / ADIS_PAGE_SIZE; struct spi_message msg; @@ -205,12 +205,12 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, ret = spi_sync(adis->spi, &msg); if (ret) { dev_err(&adis->spi->dev, "Failed to read register 0x%02X: %d\n", - reg, ret); + reg, ret); return ret; - } else { - adis->current_page = page; } + adis->current_page = page; + switch (size) { case 4: *val = get_unaligned_be32(adis->rx); @@ -251,13 +251,13 @@ EXPORT_SYMBOL_GPL(__adis_update_bits_base); #ifdef CONFIG_DEBUG_FS -int adis_debugfs_reg_access(struct iio_dev *indio_dev, - unsigned int reg, unsigned int writeval, unsigned int *readval) +int adis_debugfs_reg_access(struct iio_dev *indio_dev, unsigned int reg, + unsigned int writeval, unsigned int *readval) { struct adis *adis = iio_device_get_drvdata(indio_dev); if (readval) { - uint16_t val16; + u16 val16; int ret; ret = adis_read_reg_16(adis, reg, &val16); @@ -265,9 +265,9 @@ int adis_debugfs_reg_access(struct iio_dev *indio_dev, *readval = val16; return ret; - } else { - return adis_write_reg_16(adis, reg, writeval); } + + return adis_write_reg_16(adis, reg, writeval); } EXPORT_SYMBOL(adis_debugfs_reg_access); @@ -283,14 +283,16 @@ EXPORT_SYMBOL(adis_debugfs_reg_access); int adis_enable_irq(struct adis *adis, bool enable) { int ret = 0; - uint16_t msc; + u16 msc; mutex_lock(&adis->state_lock); if (adis->data->enable_irq) { ret = adis->data->enable_irq(adis, enable); goto out_unlock; - } else if (adis->data->unmasked_drdy) { + } + + if (adis->data->unmasked_drdy) { if (enable) enable_irq(adis->spi->irq); else @@ -326,7 +328,7 @@ EXPORT_SYMBOL(adis_enable_irq); */ int __adis_check_status(struct adis *adis) { - uint16_t status; + u16 status; int ret; int i; @@ -362,7 +364,7 @@ int __adis_reset(struct adis *adis) const struct adis_timeout *timeouts = adis->data->timeouts; ret = __adis_write_reg_8(adis, adis->data->glob_cmd_reg, - ADIS_GLOB_CMD_SW_RESET); + ADIS_GLOB_CMD_SW_RESET); if (ret) { dev_err(&adis->spi->dev, "Failed to reset device: %d\n", ret); return ret; @@ -418,7 +420,7 @@ int __adis_initial_startup(struct adis *adis) { const struct adis_timeout *timeouts = adis->data->timeouts; struct gpio_desc *gpio; - uint16_t prod_id; + u16 prod_id; int ret; /* check if the device has rst pin low */ @@ -427,7 +429,7 @@ int __adis_initial_startup(struct adis *adis) return PTR_ERR(gpio); if (gpio) { - msleep(10); + usleep_range(10, 12); /* bring device out of reset */ gpiod_set_value_cansleep(gpio, 0); msleep(timeouts->reset_ms); @@ -481,7 +483,8 @@ EXPORT_SYMBOL_GPL(__adis_initial_startup); * a error bit in the channels raw value set error_mask to 0. */ int adis_single_conversion(struct iio_dev *indio_dev, - const struct iio_chan_spec *chan, unsigned int error_mask, int *val) + const struct iio_chan_spec *chan, + unsigned int error_mask, int *val) { struct adis *adis = iio_device_get_drvdata(indio_dev); unsigned int uval; @@ -490,7 +493,7 @@ int adis_single_conversion(struct iio_dev *indio_dev, mutex_lock(&adis->state_lock); ret = __adis_read_reg(adis, chan->address, &uval, - chan->scan_type.storagebits / 8); + chan->scan_type.storagebits / 8); if (ret) goto err_unlock; @@ -525,7 +528,7 @@ EXPORT_SYMBOL_GPL(adis_single_conversion); * called. */ int adis_init(struct adis *adis, struct iio_dev *indio_dev, - struct spi_device *spi, const struct adis_data *data) + struct spi_device *spi, const struct adis_data *data) { if (!data || !data->timeouts) { dev_err(&spi->dev, "No config data or timeouts not defined!\n"); diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c index 175af154e443..7a7747617fca 100644 --- a/drivers/iio/imu/adis_buffer.c +++ b/drivers/iio/imu/adis_buffer.c @@ -20,7 +20,7 @@ #include static int adis_update_scan_mode_burst(struct iio_dev *indio_dev, - const unsigned long *scan_mask) + const unsigned long *scan_mask) { struct adis *adis = iio_device_get_drvdata(indio_dev); unsigned int burst_length, burst_max_length; @@ -63,7 +63,7 @@ static int adis_update_scan_mode_burst(struct iio_dev *indio_dev, } int adis_update_scan_mode(struct iio_dev *indio_dev, - const unsigned long *scan_mask) + const unsigned long *scan_mask) { struct adis *adis = iio_device_get_drvdata(indio_dev); const struct iio_chan_spec *chan; @@ -149,7 +149,7 @@ static irqreturn_t adis_trigger_handler(int irq, void *p) } iio_push_to_buffers_with_timestamp(indio_dev, adis->buffer, - pf->timestamp); + pf->timestamp); iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index 76b0488ef41b..e7f0ee3e7a07 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -15,8 +15,7 @@ #include #include -static int adis_data_rdy_trigger_set_state(struct iio_trigger *trig, - bool state) +static int adis_data_rdy_trigger_set_state(struct iio_trigger *trig, bool state) { struct adis *adis = iio_trigger_get_drvdata(trig); diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 2ced0c88f481..1b66953573ee 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -32,6 +32,7 @@ struct adis_timeout { u16 sw_reset_ms; u16 self_test_ms; }; + /** * struct adis_data - ADIS chip variant specific data * @read_delay: SPI delay for read operations in us @@ -45,7 +46,7 @@ struct adis_timeout { * @self_test_mask: Bitmask of supported self-test operations * @self_test_reg: Register address to request self test command * @self_test_no_autoclear: True if device's self-test needs clear of ctrl reg - * @status_error_msgs: Array of error messgaes + * @status_error_msgs: Array of error messages * @status_error_mask: Bitmask of errors supported by the device * @timeouts: Chip specific delays * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable @@ -128,12 +129,12 @@ struct adis { unsigned long irq_flag; void *buffer; - uint8_t tx[10] ____cacheline_aligned; - uint8_t rx[4]; + u8 tx[10] ____cacheline_aligned; + u8 rx[4]; }; int adis_init(struct adis *adis, struct iio_dev *indio_dev, - struct spi_device *spi, const struct adis_data *data); + struct spi_device *spi, const struct adis_data *data); int __adis_reset(struct adis *adis); /** @@ -154,9 +155,9 @@ static inline int adis_reset(struct adis *adis) } int __adis_write_reg(struct adis *adis, unsigned int reg, - unsigned int val, unsigned int size); + unsigned int val, unsigned int size); int __adis_read_reg(struct adis *adis, unsigned int reg, - unsigned int *val, unsigned int size); + unsigned int *val, unsigned int size); /** * __adis_write_reg_8() - Write single byte to a register (unlocked) @@ -165,7 +166,7 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, * @value: The value to write */ static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, - uint8_t val) + u8 val) { return __adis_write_reg(adis, reg, val, 1); } @@ -177,7 +178,7 @@ static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, - uint16_t val) + u16 val) { return __adis_write_reg(adis, reg, val, 2); } @@ -189,7 +190,7 @@ static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, - uint32_t val) + u32 val) { return __adis_write_reg(adis, reg, val, 4); } @@ -201,7 +202,7 @@ static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, - uint16_t *val) + u16 *val) { unsigned int tmp; int ret; @@ -220,7 +221,7 @@ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, - uint32_t *val) + u32 *val) { unsigned int tmp; int ret; @@ -240,7 +241,7 @@ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, * @size: The size of the @value (in bytes) */ static inline int adis_write_reg(struct adis *adis, unsigned int reg, - unsigned int val, unsigned int size) + unsigned int val, unsigned int size) { int ret; @@ -259,7 +260,7 @@ static inline int adis_write_reg(struct adis *adis, unsigned int reg, * @size: The size of the @val buffer */ static int adis_read_reg(struct adis *adis, unsigned int reg, - unsigned int *val, unsigned int size) + unsigned int *val, unsigned int size) { int ret; @@ -277,7 +278,7 @@ static int adis_read_reg(struct adis *adis, unsigned int reg, * @value: The value to write */ static inline int adis_write_reg_8(struct adis *adis, unsigned int reg, - uint8_t val) + u8 val) { return adis_write_reg(adis, reg, val, 1); } @@ -289,7 +290,7 @@ static inline int adis_write_reg_8(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int adis_write_reg_16(struct adis *adis, unsigned int reg, - uint16_t val) + u16 val) { return adis_write_reg(adis, reg, val, 2); } @@ -301,7 +302,7 @@ static inline int adis_write_reg_16(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int adis_write_reg_32(struct adis *adis, unsigned int reg, - uint32_t val) + u32 val) { return adis_write_reg(adis, reg, val, 4); } @@ -313,7 +314,7 @@ static inline int adis_write_reg_32(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg, - uint16_t *val) + u16 *val) { unsigned int tmp; int ret; @@ -332,7 +333,7 @@ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int adis_read_reg_32(struct adis *adis, unsigned int reg, - uint32_t *val) + u32 *val) { unsigned int tmp; int ret; @@ -431,8 +432,8 @@ static inline int adis_initial_startup(struct adis *adis) } int adis_single_conversion(struct iio_dev *indio_dev, - const struct iio_chan_spec *chan, unsigned int error_mask, - int *val); + const struct iio_chan_spec *chan, + unsigned int error_mask, int *val); #define ADIS_VOLTAGE_CHAN(addr, si, chan, name, info_all, bits) { \ .type = IIO_VOLTAGE, \ @@ -481,7 +482,7 @@ int adis_single_conversion(struct iio_dev *indio_dev, .modified = 1, \ .channel2 = IIO_MOD_ ## mod, \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ - info_sep, \ + (info_sep), \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ .info_mask_shared_by_all = info_all, \ .address = (addr), \ @@ -515,7 +516,7 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); int adis_update_scan_mode(struct iio_dev *indio_dev, - const unsigned long *scan_mask); + const unsigned long *scan_mask); #else /* CONFIG_IIO_BUFFER */ @@ -539,7 +540,8 @@ static inline int devm_adis_probe_trigger(struct adis *adis, #ifdef CONFIG_DEBUG_FS int adis_debugfs_reg_access(struct iio_dev *indio_dev, - unsigned int reg, unsigned int writeval, unsigned int *readval); + unsigned int reg, unsigned int writeval, + unsigned int *readval); #else From 3feb8fd8bf936756990047563833cde6d59117fe Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sun, 30 Jan 2022 20:56:53 +0000 Subject: [PATCH 0454/4345] iio:imu:adis: Move exports into IIO_ADISLIB namespace [ Upstream commit 6c9304d6af122f9afea41885ad82ed627e9442a8 ] In order to avoid unneessary pollution of the global symbol namespace move the common/library functions into a specific namespace and import that into the various specific device drivers that use them. Signed-off-by: Jonathan Cameron Cc: Lars-Peter Clausen Cc: Song Bao Hua (Barry Song) Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220130205701.334592-9-jic23@kernel.org Stable-dep-of: 99c05e4283a1 ("iio: adis: add '__adis_enable_irq()' implementation") Signed-off-by: Sasha Levin --- drivers/iio/accel/adis16201.c | 1 + drivers/iio/accel/adis16209.c | 1 + drivers/iio/gyro/adis16136.c | 1 + drivers/iio/gyro/adis16260.c | 1 + drivers/iio/imu/adis.c | 20 ++++++++++---------- drivers/iio/imu/adis16400.c | 1 + drivers/iio/imu/adis16460.c | 1 + drivers/iio/imu/adis16475.c | 1 + drivers/iio/imu/adis16480.c | 1 + drivers/iio/imu/adis_buffer.c | 4 ++-- drivers/iio/imu/adis_trigger.c | 2 +- drivers/staging/iio/accel/adis16203.c | 1 + drivers/staging/iio/accel/adis16240.c | 1 + 13 files changed, 23 insertions(+), 13 deletions(-) diff --git a/drivers/iio/accel/adis16201.c b/drivers/iio/accel/adis16201.c index 84bbdfd2f2ba..b4ae4f86da3e 100644 --- a/drivers/iio/accel/adis16201.c +++ b/drivers/iio/accel/adis16201.c @@ -304,3 +304,4 @@ MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>"); MODULE_DESCRIPTION("Analog Devices ADIS16201 Dual-Axis Digital Inclinometer and Accelerometer"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("spi:adis16201"); +MODULE_IMPORT_NS(IIO_ADISLIB); diff --git a/drivers/iio/accel/adis16209.c b/drivers/iio/accel/adis16209.c index 4a841aec6268..e6e465f397d9 100644 --- a/drivers/iio/accel/adis16209.c +++ b/drivers/iio/accel/adis16209.c @@ -314,3 +314,4 @@ MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>"); MODULE_DESCRIPTION("Analog Devices ADIS16209 Dual-Axis Digital Inclinometer and Accelerometer"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("spi:adis16209"); +MODULE_IMPORT_NS(IIO_ADISLIB); diff --git a/drivers/iio/gyro/adis16136.c b/drivers/iio/gyro/adis16136.c index a11ae9db0d11..74db8edb4283 100644 --- a/drivers/iio/gyro/adis16136.c +++ b/drivers/iio/gyro/adis16136.c @@ -599,3 +599,4 @@ module_spi_driver(adis16136_driver); MODULE_AUTHOR("Lars-Peter Clausen "); MODULE_DESCRIPTION("Analog Devices ADIS16133/ADIS16135/ADIS16136 gyroscope driver"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(IIO_ADISLIB); diff --git a/drivers/iio/gyro/adis16260.c b/drivers/iio/gyro/adis16260.c index e7c9a3e31c45..1e45d93de5b7 100644 --- a/drivers/iio/gyro/adis16260.c +++ b/drivers/iio/gyro/adis16260.c @@ -438,3 +438,4 @@ module_spi_driver(adis16260_driver); MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>"); MODULE_DESCRIPTION("Analog Devices ADIS16260/5 Digital Gyroscope Sensor"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(IIO_ADISLIB); diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index 54d1084f13d0..b0a426053c20 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -125,7 +125,7 @@ int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int value, return ret; } -EXPORT_SYMBOL_GPL(__adis_write_reg); +EXPORT_SYMBOL_NS_GPL(__adis_write_reg, IIO_ADISLIB); /** * __adis_read_reg() - read N bytes from register (unlocked version) @@ -222,7 +222,7 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val, return ret; } -EXPORT_SYMBOL_GPL(__adis_read_reg); +EXPORT_SYMBOL_NS_GPL(__adis_read_reg, IIO_ADISLIB); /** * __adis_update_bits_base() - ADIS Update bits function - Unlocked version * @adis: The adis device @@ -247,7 +247,7 @@ int __adis_update_bits_base(struct adis *adis, unsigned int reg, const u32 mask, return __adis_write_reg(adis, reg, __val, size); } -EXPORT_SYMBOL_GPL(__adis_update_bits_base); +EXPORT_SYMBOL_NS_GPL(__adis_update_bits_base, IIO_ADISLIB); #ifdef CONFIG_DEBUG_FS @@ -269,7 +269,7 @@ int adis_debugfs_reg_access(struct iio_dev *indio_dev, unsigned int reg, return adis_write_reg_16(adis, reg, writeval); } -EXPORT_SYMBOL(adis_debugfs_reg_access); +EXPORT_SYMBOL_NS(adis_debugfs_reg_access, IIO_ADISLIB); #endif @@ -318,7 +318,7 @@ out_unlock: mutex_unlock(&adis->state_lock); return ret; } -EXPORT_SYMBOL(adis_enable_irq); +EXPORT_SYMBOL_NS(adis_enable_irq, IIO_ADISLIB); /** * __adis_check_status() - Check the device for error conditions (unlocked) @@ -350,7 +350,7 @@ int __adis_check_status(struct adis *adis) return -EIO; } -EXPORT_SYMBOL_GPL(__adis_check_status); +EXPORT_SYMBOL_NS_GPL(__adis_check_status, IIO_ADISLIB); /** * __adis_reset() - Reset the device (unlocked version) @@ -374,7 +374,7 @@ int __adis_reset(struct adis *adis) return 0; } -EXPORT_SYMBOL_GPL(__adis_reset); +EXPORT_SYMBOL_NS_GPL(__adis_reset, IIO_ADIS_LIB); static int adis_self_test(struct adis *adis) { @@ -465,7 +465,7 @@ int __adis_initial_startup(struct adis *adis) return 0; } -EXPORT_SYMBOL_GPL(__adis_initial_startup); +EXPORT_SYMBOL_NS_GPL(__adis_initial_startup, IIO_ADISLIB); /** * adis_single_conversion() - Performs a single sample conversion @@ -513,7 +513,7 @@ err_unlock: mutex_unlock(&adis->state_lock); return ret; } -EXPORT_SYMBOL_GPL(adis_single_conversion); +EXPORT_SYMBOL_NS_GPL(adis_single_conversion, IIO_ADISLIB); /** * adis_init() - Initialize adis device structure @@ -550,7 +550,7 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev, return 0; } -EXPORT_SYMBOL_GPL(adis_init); +EXPORT_SYMBOL_NS_GPL(adis_init, IIO_ADISLIB); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Lars-Peter Clausen "); diff --git a/drivers/iio/imu/adis16400.c b/drivers/iio/imu/adis16400.c index 4aff16466da0..c5255116954a 100644 --- a/drivers/iio/imu/adis16400.c +++ b/drivers/iio/imu/adis16400.c @@ -1252,3 +1252,4 @@ module_spi_driver(adis16400_driver); MODULE_AUTHOR("Manuel Stahl "); MODULE_DESCRIPTION("Analog Devices ADIS16400/5 IMU SPI driver"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(IIO_ADISLIB); diff --git a/drivers/iio/imu/adis16460.c b/drivers/iio/imu/adis16460.c index 73bf45e859b8..a28143a19d3a 100644 --- a/drivers/iio/imu/adis16460.c +++ b/drivers/iio/imu/adis16460.c @@ -447,3 +447,4 @@ module_spi_driver(adis16460_driver); MODULE_AUTHOR("Dragos Bogdan "); MODULE_DESCRIPTION("Analog Devices ADIS16460 IMU driver"); MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(IIO_ADISLIB); diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c index 8ab88ba4892c..aed1cf3bfa13 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -1324,3 +1324,4 @@ module_spi_driver(adis16475_driver); MODULE_AUTHOR("Nuno Sa "); MODULE_DESCRIPTION("Analog Devices ADIS16475 IMU driver"); MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(IIO_ADISLIB); diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c index dfe86c589325..c6a3d9a04fce 100644 --- a/drivers/iio/imu/adis16480.c +++ b/drivers/iio/imu/adis16480.c @@ -1340,3 +1340,4 @@ module_spi_driver(adis16480_driver); MODULE_AUTHOR("Lars-Peter Clausen "); MODULE_DESCRIPTION("Analog Devices ADIS16480 IMU driver"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(IIO_ADISLIB); diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c index 7a7747617fca..7cc1145910f6 100644 --- a/drivers/iio/imu/adis_buffer.c +++ b/drivers/iio/imu/adis_buffer.c @@ -120,7 +120,7 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, return 0; } -EXPORT_SYMBOL_GPL(adis_update_scan_mode); +EXPORT_SYMBOL_NS_GPL(adis_update_scan_mode, IIO_ADISLIB); static irqreturn_t adis_trigger_handler(int irq, void *p) { @@ -202,5 +202,5 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, return devm_add_action_or_reset(&adis->spi->dev, adis_buffer_cleanup, adis); } -EXPORT_SYMBOL_GPL(devm_adis_setup_buffer_and_trigger); +EXPORT_SYMBOL_NS_GPL(devm_adis_setup_buffer_and_trigger, IIO_ADISLIB); diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index e7f0ee3e7a07..80adfa58e50c 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -92,5 +92,5 @@ int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) return devm_iio_trigger_register(&adis->spi->dev, adis->trig); } -EXPORT_SYMBOL_GPL(devm_adis_probe_trigger); +EXPORT_SYMBOL_NS_GPL(devm_adis_probe_trigger, IIO_ADISLIB); diff --git a/drivers/staging/iio/accel/adis16203.c b/drivers/staging/iio/accel/adis16203.c index b68304da288b..7be44ff2c943 100644 --- a/drivers/staging/iio/accel/adis16203.c +++ b/drivers/staging/iio/accel/adis16203.c @@ -318,3 +318,4 @@ MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>"); MODULE_DESCRIPTION("Analog Devices ADIS16203 Programmable 360 Degrees Inclinometer"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("spi:adis16203"); +MODULE_IMPORT_NS(IIO_ADISLIB); diff --git a/drivers/staging/iio/accel/adis16240.c b/drivers/staging/iio/accel/adis16240.c index 5064adce5f58..dbbbf81207f9 100644 --- a/drivers/staging/iio/accel/adis16240.c +++ b/drivers/staging/iio/accel/adis16240.c @@ -445,3 +445,4 @@ MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>"); MODULE_DESCRIPTION("Analog Devices Programmable Impact Sensor and Recorder"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("spi:adis16240"); +MODULE_IMPORT_NS(IIO_ADISLIB); From bb5e9402b24e24421ac34af4e267ef855a292102 Mon Sep 17 00:00:00 2001 From: Ramona Bolboaca Date: Tue, 22 Nov 2022 10:27:49 +0200 Subject: [PATCH 0455/4345] iio: adis: add '__adis_enable_irq()' implementation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 99c05e4283a19a02a256f14100ca4ec3b2da3f62 ] Add '__adis_enable_irq()' implementation which is the unlocked version of 'adis_enable_irq()'. Call '__adis_enable_irq()' instead of 'adis_enable_irq()' from '__adis_intial_startup()' to keep the expected unlocked functionality. This fix is needed to remove a deadlock for all devices which are using 'adis_initial_startup()'. The deadlock occurs because the same mutex is acquired twice, without releasing it. The mutex is acquired once inside 'adis_initial_startup()', before calling '__adis_initial_startup()', and once inside 'adis_enable_irq()', which is called by '__adis_initial_startup()'. The deadlock is removed by calling '__adis_enable_irq()', instead of 'adis_enable_irq()' from within '__adis_initial_startup()'. Fixes: b600bd7eb3335 ("iio: adis: do not disabe IRQs in 'adis_init()'") Signed-off-by: Ramona Bolboaca Reviewed-by: Nuno Sá Link: https://lore.kernel.org/r/20221122082757.449452-2-ramona.bolboaca@analog.com Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/imu/adis.c | 28 ++++++++++------------------ include/linux/iio/imu/adis.h | 13 ++++++++++++- 2 files changed, 22 insertions(+), 19 deletions(-) diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index b0a426053c20..e9821814afec 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -274,23 +274,19 @@ EXPORT_SYMBOL_NS(adis_debugfs_reg_access, IIO_ADISLIB); #endif /** - * adis_enable_irq() - Enable or disable data ready IRQ + * __adis_enable_irq() - Enable or disable data ready IRQ (unlocked) * @adis: The adis device * @enable: Whether to enable the IRQ * * Returns 0 on success, negative error code otherwise */ -int adis_enable_irq(struct adis *adis, bool enable) +int __adis_enable_irq(struct adis *adis, bool enable) { - int ret = 0; + int ret; u16 msc; - mutex_lock(&adis->state_lock); - - if (adis->data->enable_irq) { - ret = adis->data->enable_irq(adis, enable); - goto out_unlock; - } + if (adis->data->enable_irq) + return adis->data->enable_irq(adis, enable); if (adis->data->unmasked_drdy) { if (enable) @@ -298,12 +294,12 @@ int adis_enable_irq(struct adis *adis, bool enable) else disable_irq(adis->spi->irq); - goto out_unlock; + return 0; } ret = __adis_read_reg_16(adis, adis->data->msc_ctrl_reg, &msc); if (ret) - goto out_unlock; + return ret; msc |= ADIS_MSC_CTRL_DATA_RDY_POL_HIGH; msc &= ~ADIS_MSC_CTRL_DATA_RDY_DIO2; @@ -312,13 +308,9 @@ int adis_enable_irq(struct adis *adis, bool enable) else msc &= ~ADIS_MSC_CTRL_DATA_RDY_EN; - ret = __adis_write_reg_16(adis, adis->data->msc_ctrl_reg, msc); - -out_unlock: - mutex_unlock(&adis->state_lock); - return ret; + return __adis_write_reg_16(adis, adis->data->msc_ctrl_reg, msc); } -EXPORT_SYMBOL_NS(adis_enable_irq, IIO_ADISLIB); +EXPORT_SYMBOL_NS(__adis_enable_irq, IIO_ADISLIB); /** * __adis_check_status() - Check the device for error conditions (unlocked) @@ -449,7 +441,7 @@ int __adis_initial_startup(struct adis *adis) * with 'IRQF_NO_AUTOEN' anyways. */ if (!adis->data->unmasked_drdy) - adis_enable_irq(adis, false); + __adis_enable_irq(adis, false); if (!adis->data->prod_id_reg) return 0; diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 1b66953573ee..5f45b785e794 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -404,9 +404,20 @@ static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, __adis_update_bits_base(adis, reg, mask, val, 2)); \ }) -int adis_enable_irq(struct adis *adis, bool enable); int __adis_check_status(struct adis *adis); int __adis_initial_startup(struct adis *adis); +int __adis_enable_irq(struct adis *adis, bool enable); + +static inline int adis_enable_irq(struct adis *adis, bool enable) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_enable_irq(adis, enable); + mutex_unlock(&adis->state_lock); + + return ret; +} static inline int adis_check_status(struct adis *adis) { From 07905a92497ca95cc419db7759d4264bfd89efcf Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Wed, 23 Nov 2022 14:36:09 +0100 Subject: [PATCH 0456/4345] counter: stm32-lptimer-cnt: fix the check on arr and cmp registers update [ Upstream commit fd5ac974fc25feed084c2d1599d0dddb4e0556bc ] The ARR (auto reload register) and CMP (compare) registers are successively written. The status bits to check the update of these registers are polled together with regmap_read_poll_timeout(). The condition to end the loop may become true, even if one of the register isn't correctly updated. So ensure both status bits are set before clearing them. Fixes: d8958824cf07 ("iio: counter: Add support for STM32 LPTimer") Signed-off-by: Fabrice Gasnier Link: https://lore.kernel.org/r/20221123133609.465614-1-fabrice.gasnier@foss.st.com/ Signed-off-by: William Breathitt Gray Signed-off-by: Sasha Levin --- drivers/counter/stm32-lptimer-cnt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/counter/stm32-lptimer-cnt.c b/drivers/counter/stm32-lptimer-cnt.c index 937439635d53..b084e971a493 100644 --- a/drivers/counter/stm32-lptimer-cnt.c +++ b/drivers/counter/stm32-lptimer-cnt.c @@ -69,7 +69,7 @@ static int stm32_lptim_set_enable_state(struct stm32_lptim_cnt *priv, /* ensure CMP & ARR registers are properly written */ ret = regmap_read_poll_timeout(priv->regmap, STM32_LPTIM_ISR, val, - (val & STM32_LPTIM_CMPOK_ARROK), + (val & STM32_LPTIM_CMPOK_ARROK) == STM32_LPTIM_CMPOK_ARROK, 100, 1000); if (ret) return ret; From c3767f81056bc2ccb41f0de49b0716d24167edd2 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 22 Nov 2022 19:12:26 +0800 Subject: [PATCH 0457/4345] usb: roles: fix of node refcount leak in usb_role_switch_is_parent() [ Upstream commit 1ab30c610630da5391a373cddb8a065bf4c4bc01 ] I got the following report while doing device(mt6370-tcpc) load test with CONFIG_OF_UNITTEST and CONFIG_OF_DYNAMIC enabled: OF: ERROR: memory leak, expected refcount 1 instead of 2, of_node_get()/of_node_put() unbalanced - destroy cset entry: attach overlay node /i2c/pmic@34 The 'parent' returned by fwnode_get_parent() with refcount incremented. it needs be put after using. Fixes: 6fadd72943b8 ("usb: roles: get usb-role-switch from parent") Reviewed-by: Heikki Krogerus Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221122111226.251588-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/roles/class.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index 33b637d0d8d9..5cc20275335d 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -106,10 +106,13 @@ usb_role_switch_is_parent(struct fwnode_handle *fwnode) struct fwnode_handle *parent = fwnode_get_parent(fwnode); struct device *dev; - if (!parent || !fwnode_property_present(parent, "usb-role-switch")) + if (!fwnode_property_present(parent, "usb-role-switch")) { + fwnode_handle_put(parent); return NULL; + } dev = class_find_device_by_fwnode(role_class, parent); + fwnode_handle_put(parent); return dev ? to_role_switch(dev) : ERR_PTR(-EPROBE_DEFER); } From 52302c30b2186b37158e251560338074a44210cc Mon Sep 17 00:00:00 2001 From: Maxim Devaev Date: Sat, 21 Aug 2021 16:40:04 +0300 Subject: [PATCH 0458/4345] usb: gadget: f_hid: optional SETUP/SET_REPORT mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d7428bc26fc767942c38d74b80299bcd4f01e7cb ] f_hid provides the OUT Endpoint as only way for receiving reports from the host. SETUP/SET_REPORT method is not supported, and this causes a number of compatibility problems with various host drivers, especially in the case of keyboard emulation using f_hid. - Some hosts do not support the OUT Endpoint and ignore it, so it becomes impossible for the gadget to receive a report from the host. In the case of a keyboard, the gadget loses the ability to receive the status of the LEDs. - Some BIOSes/UEFIs can't work with HID devices with the OUT Endpoint at all. This may be due to their bugs or incomplete implementation of the HID standard. For example, absolutely all Apple UEFIs can't handle the OUT Endpoint if it goes after IN Endpoint in the descriptor and require the reverse order (OUT, IN) which is a violation of the standard. Other hosts either do not initialize gadgets with a descriptor containing the OUT Endpoint completely (like some HP and DELL BIOSes and embedded firmwares like on KVM switches), or initialize them, but will not poll the IN Endpoint. This patch adds configfs option no_out_endpoint=1 to disable the OUT Endpoint and allows f_hid to receive reports from the host via SETUP/SET_REPORT. Previously, there was such a feature in f_hid, but it was replaced by the OUT Endpoint [1] in the commit 99c515005857 ("usb: gadget: hidg: register OUT INT endpoint for SET_REPORT"). So this patch actually returns the removed functionality while making it optional. For backward compatibility reasons, the OUT Endpoint mode remains the default behaviour. - The OUT Endpoint mode provides the report queue and reduces USB overhead (eliminating SETUP routine) on transmitting a report from the host. - If the SETUP/SET_REPORT mode is used, there is no report queue, so the userspace will only read last report. For classic HID devices like keyboards this is not a problem, since it's intended to transmit the status of the LEDs and only the last report is important. This mode provides better compatibility with strange and buggy host drivers. Both modes passed USBCV tests. Checking with the USB protocol analyzer also confirmed that everything is working as it should and the new mode ensures operability in all of the described cases. Link: https://www.spinics.net/lists/linux-usb/msg65494.html [1] Reviewed-by: Maciej Żenczykowski Acked-by: Felipe Balbi Signed-off-by: Maxim Devaev Link: https://lore.kernel.org/r/20210821134004.363217-1-mdevaev@gmail.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 89ff3dfac604 ("usb: gadget: f_hid: fix f_hidg lifetime vs cdev") Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/f_hid.c | 220 +++++++++++++++++++++++----- drivers/usb/gadget/function/u_hid.h | 1 + 2 files changed, 188 insertions(+), 33 deletions(-) diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 6742271cd6e6..8cb199f52b52 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -45,12 +45,25 @@ struct f_hidg { unsigned short report_desc_length; char *report_desc; unsigned short report_length; + /* + * use_out_ep - if true, the OUT Endpoint (interrupt out method) + * will be used to receive reports from the host + * using functions with the "intout" suffix. + * Otherwise, the OUT Endpoint will not be configured + * and the SETUP/SET_REPORT method ("ssreport" suffix) + * will be used to receive reports. + */ + bool use_out_ep; /* recv report */ - struct list_head completed_out_req; spinlock_t read_spinlock; wait_queue_head_t read_queue; + /* recv report - interrupt out only (use_out_ep == 1) */ + struct list_head completed_out_req; unsigned int qlen; + /* recv report - setup set_report only (use_out_ep == 0) */ + char *set_report_buf; + unsigned int set_report_length; /* send report */ spinlock_t write_spinlock; @@ -79,7 +92,7 @@ static struct usb_interface_descriptor hidg_interface_desc = { .bDescriptorType = USB_DT_INTERFACE, /* .bInterfaceNumber = DYNAMIC */ .bAlternateSetting = 0, - .bNumEndpoints = 2, + /* .bNumEndpoints = DYNAMIC (depends on use_out_ep) */ .bInterfaceClass = USB_CLASS_HID, /* .bInterfaceSubClass = DYNAMIC */ /* .bInterfaceProtocol = DYNAMIC */ @@ -140,7 +153,7 @@ static struct usb_ss_ep_comp_descriptor hidg_ss_out_comp_desc = { /* .wBytesPerInterval = DYNAMIC */ }; -static struct usb_descriptor_header *hidg_ss_descriptors[] = { +static struct usb_descriptor_header *hidg_ss_descriptors_intout[] = { (struct usb_descriptor_header *)&hidg_interface_desc, (struct usb_descriptor_header *)&hidg_desc, (struct usb_descriptor_header *)&hidg_ss_in_ep_desc, @@ -150,6 +163,14 @@ static struct usb_descriptor_header *hidg_ss_descriptors[] = { NULL, }; +static struct usb_descriptor_header *hidg_ss_descriptors_ssreport[] = { + (struct usb_descriptor_header *)&hidg_interface_desc, + (struct usb_descriptor_header *)&hidg_desc, + (struct usb_descriptor_header *)&hidg_ss_in_ep_desc, + (struct usb_descriptor_header *)&hidg_ss_in_comp_desc, + NULL, +}; + /* High-Speed Support */ static struct usb_endpoint_descriptor hidg_hs_in_ep_desc = { @@ -176,7 +197,7 @@ static struct usb_endpoint_descriptor hidg_hs_out_ep_desc = { */ }; -static struct usb_descriptor_header *hidg_hs_descriptors[] = { +static struct usb_descriptor_header *hidg_hs_descriptors_intout[] = { (struct usb_descriptor_header *)&hidg_interface_desc, (struct usb_descriptor_header *)&hidg_desc, (struct usb_descriptor_header *)&hidg_hs_in_ep_desc, @@ -184,6 +205,13 @@ static struct usb_descriptor_header *hidg_hs_descriptors[] = { NULL, }; +static struct usb_descriptor_header *hidg_hs_descriptors_ssreport[] = { + (struct usb_descriptor_header *)&hidg_interface_desc, + (struct usb_descriptor_header *)&hidg_desc, + (struct usb_descriptor_header *)&hidg_hs_in_ep_desc, + NULL, +}; + /* Full-Speed Support */ static struct usb_endpoint_descriptor hidg_fs_in_ep_desc = { @@ -210,7 +238,7 @@ static struct usb_endpoint_descriptor hidg_fs_out_ep_desc = { */ }; -static struct usb_descriptor_header *hidg_fs_descriptors[] = { +static struct usb_descriptor_header *hidg_fs_descriptors_intout[] = { (struct usb_descriptor_header *)&hidg_interface_desc, (struct usb_descriptor_header *)&hidg_desc, (struct usb_descriptor_header *)&hidg_fs_in_ep_desc, @@ -218,6 +246,13 @@ static struct usb_descriptor_header *hidg_fs_descriptors[] = { NULL, }; +static struct usb_descriptor_header *hidg_fs_descriptors_ssreport[] = { + (struct usb_descriptor_header *)&hidg_interface_desc, + (struct usb_descriptor_header *)&hidg_desc, + (struct usb_descriptor_header *)&hidg_fs_in_ep_desc, + NULL, +}; + /*-------------------------------------------------------------------------*/ /* Strings */ @@ -241,8 +276,8 @@ static struct usb_gadget_strings *ct_func_strings[] = { /*-------------------------------------------------------------------------*/ /* Char Device */ -static ssize_t f_hidg_read(struct file *file, char __user *buffer, - size_t count, loff_t *ptr) +static ssize_t f_hidg_intout_read(struct file *file, char __user *buffer, + size_t count, loff_t *ptr) { struct f_hidg *hidg = file->private_data; struct f_hidg_req_list *list; @@ -255,15 +290,15 @@ static ssize_t f_hidg_read(struct file *file, char __user *buffer, spin_lock_irqsave(&hidg->read_spinlock, flags); -#define READ_COND (!list_empty(&hidg->completed_out_req)) +#define READ_COND_INTOUT (!list_empty(&hidg->completed_out_req)) /* wait for at least one buffer to complete */ - while (!READ_COND) { + while (!READ_COND_INTOUT) { spin_unlock_irqrestore(&hidg->read_spinlock, flags); if (file->f_flags & O_NONBLOCK) return -EAGAIN; - if (wait_event_interruptible(hidg->read_queue, READ_COND)) + if (wait_event_interruptible(hidg->read_queue, READ_COND_INTOUT)) return -ERESTARTSYS; spin_lock_irqsave(&hidg->read_spinlock, flags); @@ -313,6 +348,60 @@ static ssize_t f_hidg_read(struct file *file, char __user *buffer, return count; } +#define READ_COND_SSREPORT (hidg->set_report_buf != NULL) + +static ssize_t f_hidg_ssreport_read(struct file *file, char __user *buffer, + size_t count, loff_t *ptr) +{ + struct f_hidg *hidg = file->private_data; + char *tmp_buf = NULL; + unsigned long flags; + + if (!count) + return 0; + + spin_lock_irqsave(&hidg->read_spinlock, flags); + + while (!READ_COND_SSREPORT) { + spin_unlock_irqrestore(&hidg->read_spinlock, flags); + if (file->f_flags & O_NONBLOCK) + return -EAGAIN; + + if (wait_event_interruptible(hidg->read_queue, READ_COND_SSREPORT)) + return -ERESTARTSYS; + + spin_lock_irqsave(&hidg->read_spinlock, flags); + } + + count = min_t(unsigned int, count, hidg->set_report_length); + tmp_buf = hidg->set_report_buf; + hidg->set_report_buf = NULL; + + spin_unlock_irqrestore(&hidg->read_spinlock, flags); + + if (tmp_buf != NULL) { + count -= copy_to_user(buffer, tmp_buf, count); + kfree(tmp_buf); + } else { + count = -ENOMEM; + } + + wake_up(&hidg->read_queue); + + return count; +} + +static ssize_t f_hidg_read(struct file *file, char __user *buffer, + size_t count, loff_t *ptr) +{ + struct f_hidg *hidg = file->private_data; + + if (hidg->use_out_ep) + return f_hidg_intout_read(file, buffer, count, ptr); + else + return f_hidg_ssreport_read(file, buffer, count, ptr); +} + static void f_hidg_req_complete(struct usb_ep *ep, struct usb_request *req) { struct f_hidg *hidg = (struct f_hidg *)ep->driver_data; @@ -433,14 +522,20 @@ static __poll_t f_hidg_poll(struct file *file, poll_table *wait) if (WRITE_COND) ret |= EPOLLOUT | EPOLLWRNORM; - if (READ_COND) - ret |= EPOLLIN | EPOLLRDNORM; + if (hidg->use_out_ep) { + if (READ_COND_INTOUT) + ret |= EPOLLIN | EPOLLRDNORM; + } else { + if (READ_COND_SSREPORT) + ret |= EPOLLIN | EPOLLRDNORM; + } return ret; } #undef WRITE_COND -#undef READ_COND +#undef READ_COND_SSREPORT +#undef READ_COND_INTOUT static int f_hidg_release(struct inode *inode, struct file *fd) { @@ -467,7 +562,7 @@ static inline struct usb_request *hidg_alloc_ep_req(struct usb_ep *ep, return alloc_ep_req(ep, length); } -static void hidg_set_report_complete(struct usb_ep *ep, struct usb_request *req) +static void hidg_intout_complete(struct usb_ep *ep, struct usb_request *req) { struct f_hidg *hidg = (struct f_hidg *) req->context; struct usb_composite_dev *cdev = hidg->func.config->cdev; @@ -502,6 +597,37 @@ free_req: } } +static void hidg_ssreport_complete(struct usb_ep *ep, struct usb_request *req) +{ + struct f_hidg *hidg = (struct f_hidg *)req->context; + struct usb_composite_dev *cdev = hidg->func.config->cdev; + char *new_buf = NULL; + unsigned long flags; + + if (req->status != 0 || req->buf == NULL || req->actual == 0) { + ERROR(cdev, + "%s FAILED: status=%d, buf=%p, actual=%d\n", + __func__, req->status, req->buf, req->actual); + return; + } + + spin_lock_irqsave(&hidg->read_spinlock, flags); + + new_buf = krealloc(hidg->set_report_buf, req->actual, GFP_ATOMIC); + if (new_buf == NULL) { + spin_unlock_irqrestore(&hidg->read_spinlock, flags); + return; + } + hidg->set_report_buf = new_buf; + + hidg->set_report_length = req->actual; + memcpy(hidg->set_report_buf, req->buf, req->actual); + + spin_unlock_irqrestore(&hidg->read_spinlock, flags); + + wake_up(&hidg->read_queue); +} + static int hidg_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl) { @@ -549,7 +675,11 @@ static int hidg_setup(struct usb_function *f, case ((USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE) << 8 | HID_REQ_SET_REPORT): VDBG(cdev, "set_report | wLength=%d\n", ctrl->wLength); - goto stall; + if (hidg->use_out_ep) + goto stall; + req->complete = hidg_ssreport_complete; + req->context = hidg; + goto respond; break; case ((USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE) << 8 @@ -637,15 +767,18 @@ static void hidg_disable(struct usb_function *f) unsigned long flags; usb_ep_disable(hidg->in_ep); - usb_ep_disable(hidg->out_ep); - spin_lock_irqsave(&hidg->read_spinlock, flags); - list_for_each_entry_safe(list, next, &hidg->completed_out_req, list) { - free_ep_req(hidg->out_ep, list->req); - list_del(&list->list); - kfree(list); + if (hidg->out_ep) { + usb_ep_disable(hidg->out_ep); + + spin_lock_irqsave(&hidg->read_spinlock, flags); + list_for_each_entry_safe(list, next, &hidg->completed_out_req, list) { + free_ep_req(hidg->out_ep, list->req); + list_del(&list->list); + kfree(list); + } + spin_unlock_irqrestore(&hidg->read_spinlock, flags); } - spin_unlock_irqrestore(&hidg->read_spinlock, flags); spin_lock_irqsave(&hidg->write_spinlock, flags); if (!hidg->write_pending) { @@ -691,8 +824,7 @@ static int hidg_set_alt(struct usb_function *f, unsigned intf, unsigned alt) } } - - if (hidg->out_ep != NULL) { + if (hidg->use_out_ep && hidg->out_ep != NULL) { /* restart endpoint */ usb_ep_disable(hidg->out_ep); @@ -717,7 +849,7 @@ static int hidg_set_alt(struct usb_function *f, unsigned intf, unsigned alt) hidg_alloc_ep_req(hidg->out_ep, hidg->report_length); if (req) { - req->complete = hidg_set_report_complete; + req->complete = hidg_intout_complete; req->context = hidg; status = usb_ep_queue(hidg->out_ep, req, GFP_ATOMIC); @@ -743,7 +875,8 @@ static int hidg_set_alt(struct usb_function *f, unsigned intf, unsigned alt) } return 0; disable_out_ep: - usb_ep_disable(hidg->out_ep); + if (hidg->out_ep) + usb_ep_disable(hidg->out_ep); free_req_in: if (req_in) free_ep_req(hidg->in_ep, req_in); @@ -795,14 +928,21 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) goto fail; hidg->in_ep = ep; - ep = usb_ep_autoconfig(c->cdev->gadget, &hidg_fs_out_ep_desc); - if (!ep) - goto fail; - hidg->out_ep = ep; + hidg->out_ep = NULL; + if (hidg->use_out_ep) { + ep = usb_ep_autoconfig(c->cdev->gadget, &hidg_fs_out_ep_desc); + if (!ep) + goto fail; + hidg->out_ep = ep; + } + + /* used only if use_out_ep == 1 */ + hidg->set_report_buf = NULL; /* set descriptor dynamic values */ hidg_interface_desc.bInterfaceSubClass = hidg->bInterfaceSubClass; hidg_interface_desc.bInterfaceProtocol = hidg->bInterfaceProtocol; + hidg_interface_desc.bNumEndpoints = hidg->use_out_ep ? 2 : 1; hidg->protocol = HID_REPORT_PROTOCOL; hidg->idle = 1; hidg_ss_in_ep_desc.wMaxPacketSize = cpu_to_le16(hidg->report_length); @@ -833,9 +973,19 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) hidg_ss_out_ep_desc.bEndpointAddress = hidg_fs_out_ep_desc.bEndpointAddress; - status = usb_assign_descriptors(f, hidg_fs_descriptors, - hidg_hs_descriptors, hidg_ss_descriptors, - hidg_ss_descriptors); + if (hidg->use_out_ep) + status = usb_assign_descriptors(f, + hidg_fs_descriptors_intout, + hidg_hs_descriptors_intout, + hidg_ss_descriptors_intout, + hidg_ss_descriptors_intout); + else + status = usb_assign_descriptors(f, + hidg_fs_descriptors_ssreport, + hidg_hs_descriptors_ssreport, + hidg_ss_descriptors_ssreport, + hidg_ss_descriptors_ssreport); + if (status) goto fail; @@ -950,6 +1100,7 @@ CONFIGFS_ATTR(f_hid_opts_, name) F_HID_OPT(subclass, 8, 255); F_HID_OPT(protocol, 8, 255); +F_HID_OPT(no_out_endpoint, 8, 1); F_HID_OPT(report_length, 16, 65535); static ssize_t f_hid_opts_report_desc_show(struct config_item *item, char *page) @@ -1009,6 +1160,7 @@ CONFIGFS_ATTR_RO(f_hid_opts_, dev); static struct configfs_attribute *hid_attrs[] = { &f_hid_opts_attr_subclass, &f_hid_opts_attr_protocol, + &f_hid_opts_attr_no_out_endpoint, &f_hid_opts_attr_report_length, &f_hid_opts_attr_report_desc, &f_hid_opts_attr_dev, @@ -1093,6 +1245,7 @@ static void hidg_free(struct usb_function *f) hidg = func_to_hidg(f); opts = container_of(f->fi, struct f_hid_opts, func_inst); kfree(hidg->report_desc); + kfree(hidg->set_report_buf); kfree(hidg); mutex_lock(&opts->lock); --opts->refcnt; @@ -1139,6 +1292,7 @@ static struct usb_function *hidg_alloc(struct usb_function_instance *fi) return ERR_PTR(-ENOMEM); } } + hidg->use_out_ep = !opts->no_out_endpoint; mutex_unlock(&opts->lock); diff --git a/drivers/usb/gadget/function/u_hid.h b/drivers/usb/gadget/function/u_hid.h index 84e6da302499..fa631f34bb3d 100644 --- a/drivers/usb/gadget/function/u_hid.h +++ b/drivers/usb/gadget/function/u_hid.h @@ -20,6 +20,7 @@ struct f_hid_opts { int minor; unsigned char subclass; unsigned char protocol; + unsigned char no_out_endpoint; unsigned short report_length; unsigned short report_desc_length; unsigned char *report_desc; From 1b6a53e447ec3d81623610c8c7ec5082b47dfdce Mon Sep 17 00:00:00 2001 From: John Keeping Date: Tue, 22 Nov 2022 12:35:21 +0000 Subject: [PATCH 0459/4345] usb: gadget: f_hid: fix f_hidg lifetime vs cdev [ Upstream commit 89ff3dfac604614287ad5aad9370c3f984ea3f4b ] The embedded struct cdev does not have its lifetime correctly tied to the enclosing struct f_hidg, so there is a use-after-free if /dev/hidgN is held open while the gadget is deleted. This can readily be replicated with libusbgx's example programs (for conciseness - operating directly via configfs is equivalent): gadget-hid exec 3<> /dev/hidg0 gadget-vid-pid-remove exec 3<&- Pull the existing device up in to struct f_hidg and make use of the cdev_device_{add,del}() helpers. This changes the lifetime of the device object to match struct f_hidg, but note that it is still added and deleted at the same time. Fixes: 71adf1189469 ("USB: gadget: add HID gadget driver") Tested-by: Lee Jones Reviewed-by: Andrzej Pietrasiewicz Reviewed-by: Lee Jones Signed-off-by: John Keeping Link: https://lore.kernel.org/r/20221122123523.3068034-2-john@metanate.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/f_hid.c | 52 ++++++++++++++++------------- 1 file changed, 28 insertions(+), 24 deletions(-) diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 8cb199f52b52..97e927eacc62 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -71,7 +71,7 @@ struct f_hidg { wait_queue_head_t write_queue; struct usb_request *req; - int minor; + struct device dev; struct cdev cdev; struct usb_function func; @@ -84,6 +84,14 @@ static inline struct f_hidg *func_to_hidg(struct usb_function *f) return container_of(f, struct f_hidg, func); } +static void hidg_release(struct device *dev) +{ + struct f_hidg *hidg = container_of(dev, struct f_hidg, dev); + + kfree(hidg->set_report_buf); + kfree(hidg); +} + /*-------------------------------------------------------------------------*/ /* Static descriptors */ @@ -904,9 +912,7 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) struct usb_ep *ep; struct f_hidg *hidg = func_to_hidg(f); struct usb_string *us; - struct device *device; int status; - dev_t dev; /* maybe allocate device-global string IDs, and patch descriptors */ us = usb_gstrings_attach(c->cdev, ct_func_strings, @@ -999,21 +1005,11 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) /* create char device */ cdev_init(&hidg->cdev, &f_hidg_fops); - dev = MKDEV(major, hidg->minor); - status = cdev_add(&hidg->cdev, dev, 1); + status = cdev_device_add(&hidg->cdev, &hidg->dev); if (status) goto fail_free_descs; - device = device_create(hidg_class, NULL, dev, NULL, - "%s%d", "hidg", hidg->minor); - if (IS_ERR(device)) { - status = PTR_ERR(device); - goto del; - } - return 0; -del: - cdev_del(&hidg->cdev); fail_free_descs: usb_free_all_descriptors(f); fail: @@ -1244,9 +1240,7 @@ static void hidg_free(struct usb_function *f) hidg = func_to_hidg(f); opts = container_of(f->fi, struct f_hid_opts, func_inst); - kfree(hidg->report_desc); - kfree(hidg->set_report_buf); - kfree(hidg); + put_device(&hidg->dev); mutex_lock(&opts->lock); --opts->refcnt; mutex_unlock(&opts->lock); @@ -1256,8 +1250,7 @@ static void hidg_unbind(struct usb_configuration *c, struct usb_function *f) { struct f_hidg *hidg = func_to_hidg(f); - device_destroy(hidg_class, MKDEV(major, hidg->minor)); - cdev_del(&hidg->cdev); + cdev_device_del(&hidg->cdev, &hidg->dev); usb_free_all_descriptors(f); } @@ -1266,6 +1259,7 @@ static struct usb_function *hidg_alloc(struct usb_function_instance *fi) { struct f_hidg *hidg; struct f_hid_opts *opts; + int ret; /* allocate and initialize one new instance */ hidg = kzalloc(sizeof(*hidg), GFP_KERNEL); @@ -1277,17 +1271,27 @@ static struct usb_function *hidg_alloc(struct usb_function_instance *fi) mutex_lock(&opts->lock); ++opts->refcnt; - hidg->minor = opts->minor; + device_initialize(&hidg->dev); + hidg->dev.release = hidg_release; + hidg->dev.class = hidg_class; + hidg->dev.devt = MKDEV(major, opts->minor); + ret = dev_set_name(&hidg->dev, "hidg%d", opts->minor); + if (ret) { + --opts->refcnt; + mutex_unlock(&opts->lock); + return ERR_PTR(ret); + } + hidg->bInterfaceSubClass = opts->subclass; hidg->bInterfaceProtocol = opts->protocol; hidg->report_length = opts->report_length; hidg->report_desc_length = opts->report_desc_length; if (opts->report_desc) { - hidg->report_desc = kmemdup(opts->report_desc, - opts->report_desc_length, - GFP_KERNEL); + hidg->report_desc = devm_kmemdup(&hidg->dev, opts->report_desc, + opts->report_desc_length, + GFP_KERNEL); if (!hidg->report_desc) { - kfree(hidg); + put_device(&hidg->dev); mutex_unlock(&opts->lock); return ERR_PTR(-ENOMEM); } From e88b89a096af0001bcff6bf7ad2feb1486487173 Mon Sep 17 00:00:00 2001 From: John Keeping Date: Tue, 22 Nov 2022 12:35:22 +0000 Subject: [PATCH 0460/4345] usb: gadget: f_hid: fix refcount leak on error path [ Upstream commit 70a3288a7586526315105c699b687d78cd32559a ] When failing to allocate report_desc, opts->refcnt has already been incremented so it needs to be decremented to avoid leaving the options structure permanently locked. Fixes: 21a9476a7ba8 ("usb: gadget: hid: add configfs support") Tested-by: Lee Jones Reviewed-by: Andrzej Pietrasiewicz Reviewed-by: Lee Jones Signed-off-by: John Keeping Link: https://lore.kernel.org/r/20221122123523.3068034-3-john@metanate.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/f_hid.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 97e927eacc62..e7cf56b13c64 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -1292,6 +1292,7 @@ static struct usb_function *hidg_alloc(struct usb_function_instance *fi) GFP_KERNEL); if (!hidg->report_desc) { put_device(&hidg->dev); + --opts->refcnt; mutex_unlock(&opts->lock); return ERR_PTR(-ENOMEM); } From 0d1c2c8db28919c4351000d7c1692f1767bdc4f7 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Fri, 2 Dec 2022 01:38:49 -0800 Subject: [PATCH 0461/4345] drivers: mcb: fix resource leak in mcb_probe() [ Upstream commit d7237462561fcd224fa687c56ccb68629f50fc0d ] When probe hook function failed in mcb_probe(), it doesn't put the device. Compiled test only. Fixes: 7bc364097a89 ("mcb: Acquire reference to device in probe") Signed-off-by: Zhengchao Shao Signed-off-by: Johannes Thumshirn Link: https://lore.kernel.org/r/9f87de36bfb85158b506cb78c6fc9db3f6a3bad1.1669624063.git.johannes.thumshirn@wdc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/mcb/mcb-core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c index 38cc8340e817..8b8cd751fe9a 100644 --- a/drivers/mcb/mcb-core.c +++ b/drivers/mcb/mcb-core.c @@ -71,8 +71,10 @@ static int mcb_probe(struct device *dev) get_device(dev); ret = mdrv->probe(mdev, found_id); - if (ret) + if (ret) { module_put(carrier_mod); + put_device(dev); + } return ret; } From 7b289b791a59386dc23a00d3cf17a0db984b40d3 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 2 Dec 2022 01:38:50 -0800 Subject: [PATCH 0462/4345] mcb: mcb-parse: fix error handing in chameleon_parse_gdd() [ Upstream commit 728ac3389296caf68638628c987aeae6c8851e2d ] If mcb_device_register() returns error in chameleon_parse_gdd(), the refcount of bus and device name are leaked. Fix this by calling put_device() to give up the reference, so they can be released in mcb_release_dev() and kobject_cleanup(). Fixes: 3764e82e5150 ("drivers: Introduce MEN Chameleon Bus") Reviewed-by: Johannes Thumshirn Signed-off-by: Yang Yingliang Signed-off-by: Johannes Thumshirn Link: https://lore.kernel.org/r/ebfb06e39b19272f0197fa9136b5e4b6f34ad732.1669624063.git.johannes.thumshirn@wdc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/mcb/mcb-parse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c index 0266bfddfbe2..aa6938da0db8 100644 --- a/drivers/mcb/mcb-parse.c +++ b/drivers/mcb/mcb-parse.c @@ -108,7 +108,7 @@ static int chameleon_parse_gdd(struct mcb_bus *bus, return 0; err: - mcb_free_dev(mdev); + put_device(&mdev->dev); return ret; } From c46db6088bccff5115674d583fef46ede80077a2 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 2 Dec 2022 11:02:37 +0800 Subject: [PATCH 0463/4345] chardev: fix error handling in cdev_device_add() [ Upstream commit 11fa7fefe3d8fac7da56bc9aa3dd5fb3081ca797 ] While doing fault injection test, I got the following report: ------------[ cut here ]------------ kobject: '(null)' (0000000039956980): is not initialized, yet kobject_put() is being called. WARNING: CPU: 3 PID: 6306 at kobject_put+0x23d/0x4e0 CPU: 3 PID: 6306 Comm: 283 Tainted: G W 6.1.0-rc2-00005-g307c1086d7c9 #1253 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:kobject_put+0x23d/0x4e0 Call Trace: cdev_device_add+0x15e/0x1b0 __iio_device_register+0x13b4/0x1af0 [industrialio] __devm_iio_device_register+0x22/0x90 [industrialio] max517_probe+0x3d8/0x6b4 [max517] i2c_device_probe+0xa81/0xc00 When device_add() is injected fault and returns error, if dev->devt is not set, cdev_add() is not called, cdev_del() is not needed. Fix this by checking dev->devt in error path. Fixes: 233ed09d7fda ("chardev: add helper function to register char devs with a struct device") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221202030237.520280-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- fs/char_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/char_dev.c b/fs/char_dev.c index ba0ded7842a7..3f667292608c 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -547,7 +547,7 @@ int cdev_device_add(struct cdev *cdev, struct device *dev) } rc = device_add(dev); - if (rc) + if (rc && dev->devt) cdev_del(cdev); return rc; From 46b3885c8cb4e5c9dd0d01ef2b22468a2a962cf1 Mon Sep 17 00:00:00 2001 From: Hui Tang Date: Mon, 14 Nov 2022 17:25:40 +0800 Subject: [PATCH 0464/4345] i2c: pxa-pci: fix missing pci_disable_device() on error in ce4100_i2c_probe [ Upstream commit d78a167332e1ca8113268ed922c1212fd71b73ad ] Using pcim_enable_device() to avoid missing pci_disable_device(). Fixes: 7e94dd154e93 ("i2c-pxa2xx: Add PCI support for PXA I2C controller") Signed-off-by: Hui Tang Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-pxa-pci.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/i2c/busses/i2c-pxa-pci.c b/drivers/i2c/busses/i2c-pxa-pci.c index f614cade432b..30e38bc8b6db 100644 --- a/drivers/i2c/busses/i2c-pxa-pci.c +++ b/drivers/i2c/busses/i2c-pxa-pci.c @@ -105,7 +105,7 @@ static int ce4100_i2c_probe(struct pci_dev *dev, int i; struct ce4100_devices *sds; - ret = pci_enable_device_mem(dev); + ret = pcim_enable_device(dev); if (ret) return ret; @@ -114,10 +114,8 @@ static int ce4100_i2c_probe(struct pci_dev *dev, return -EINVAL; } sds = kzalloc(sizeof(*sds), GFP_KERNEL); - if (!sds) { - ret = -ENOMEM; - goto err_mem; - } + if (!sds) + return -ENOMEM; for (i = 0; i < ARRAY_SIZE(sds->pdev); i++) { sds->pdev[i] = add_i2c_device(dev, i); @@ -133,8 +131,6 @@ static int ce4100_i2c_probe(struct pci_dev *dev, err_dev_add: kfree(sds); -err_mem: - pci_disable_device(dev); return ret; } From daa8045a991363ccdae5615d170f35aa1135e7a7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 23 Nov 2022 09:43:14 +0300 Subject: [PATCH 0465/4345] staging: rtl8192u: Fix use after free in ieee80211_rx() [ Upstream commit bcc5e2dcf09089b337b76fc1a589f6ff95ca19ac ] We cannot dereference the "skb" pointer after calling ieee80211_monitor_rx(), because it is a use after free. Fixes: 8fc8598e61f6 ("Staging: Added Realtek rtl8192u driver to staging") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/Y33BArx3k/aw6yv/@kili Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c index b6fee7230ce0..3871437f4708 100644 --- a/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c +++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c @@ -954,9 +954,11 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, #endif if (ieee->iw_mode == IW_MODE_MONITOR) { + unsigned int len = skb->len; + ieee80211_monitor_rx(ieee, skb, rx_stats); stats->rx_packets++; - stats->rx_bytes += skb->len; + stats->rx_bytes += len; return 1; } From b9fa01fb3140f1e2a7989a4b4ab86296f8b9c064 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 23 Nov 2022 16:12:53 +0800 Subject: [PATCH 0466/4345] staging: rtl8192e: Fix potential use-after-free in rtllib_rx_Monitor() [ Upstream commit d30f4436f364b4ad915ca2c09be07cd0f93ceb44 ] The skb is delivered to netif_rx() in rtllib_monitor_rx(), which may free it, after calling this, dereferencing skb may trigger use-after-free. Found by Smatch. Fixes: 94a799425eee ("From: wlanfae [PATCH 1/8] rtl8192e: Import new version of driver from realtek") Signed-off-by: YueHaibing Link: https://lore.kernel.org/r/20221123081253.22296-1-yuehaibing@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/staging/rtl8192e/rtllib_rx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c index 63752233e551..404794503fb6 100644 --- a/drivers/staging/rtl8192e/rtllib_rx.c +++ b/drivers/staging/rtl8192e/rtllib_rx.c @@ -1490,9 +1490,9 @@ static int rtllib_rx_Monitor(struct rtllib_device *ieee, struct sk_buff *skb, hdrlen += 4; } - rtllib_monitor_rx(ieee, skb, rx_stats, hdrlen); ieee->stats.rx_packets++; ieee->stats.rx_bytes += skb->len; + rtllib_monitor_rx(ieee, skb, rx_stats, hdrlen); return 1; } From 37d3de40c1ffb6a5e626bf46ff5ef5766c824e2c Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Mon, 5 Dec 2022 16:48:05 +0800 Subject: [PATCH 0467/4345] vme: Fix error not catched in fake_init() [ Upstream commit 7bef797d707f1744f71156b21d41e3b8c946631f ] In fake_init(), __root_device_register() is possible to fail but it's ignored, which can cause unregistering vme_root fail when exit. general protection fault, probably for non-canonical address 0xdffffc000000008c KASAN: null-ptr-deref in range [0x0000000000000460-0x0000000000000467] RIP: 0010:root_device_unregister+0x26/0x60 Call Trace: __x64_sys_delete_module+0x34f/0x540 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Return error when __root_device_register() fails. Fixes: 658bcdae9c67 ("vme: Adding Fake VME driver") Signed-off-by: Chen Zhongjin Link: https://lore.kernel.org/r/20221205084805.147436-1-chenzhongjin@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/vme/bridges/vme_fake.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/vme/bridges/vme_fake.c b/drivers/vme/bridges/vme_fake.c index 6a1bc284f297..eae78366eb02 100644 --- a/drivers/vme/bridges/vme_fake.c +++ b/drivers/vme/bridges/vme_fake.c @@ -1073,6 +1073,8 @@ static int __init fake_init(void) /* We need a fake parent device */ vme_root = __root_device_register("vme", THIS_MODULE); + if (IS_ERR(vme_root)) + return PTR_ERR(vme_root); /* If we want to support more than one bridge at some point, we need to * dynamically allocate this so we get one per device. From aeee7ad0897f83721a8213df85010c77927c705b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Mar 2022 18:06:20 +0300 Subject: [PATCH 0468/4345] gpiolib: Get rid of redundant 'else' [ Upstream commit 1cef8b5019769d46725932eeace7a383bca97905 ] In the snippets like the following if (...) return / goto / break / continue ...; else ... the 'else' is redundant. Get rid of it. In case of IOCTLs use switch-case pattern that seems the usual in such cases. While at it, clarify necessity of else in gpiod_direction_output() by attaching else if to the closing curly brace on a previous line. Signed-off-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski Stable-dep-of: 533aae7c94db ("gpiolib: cdev: fix NULL-pointer dereferences") Signed-off-by: Sasha Levin --- drivers/gpio/gpiolib-cdev.c | 66 ++++++++++++++++++++----------------- drivers/gpio/gpiolib.c | 12 +++---- 2 files changed, 40 insertions(+), 38 deletions(-) diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 381cfa26a4a1..b51b4d7a611e 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -197,16 +197,15 @@ static long linehandle_ioctl(struct file *file, unsigned int cmd, void __user *ip = (void __user *)arg; struct gpiohandle_data ghd; DECLARE_BITMAP(vals, GPIOHANDLES_MAX); - int i; + unsigned int i; + int ret; - if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) { - /* NOTE: It's ok to read values of output lines. */ - int ret = gpiod_get_array_value_complex(false, - true, - lh->num_descs, - lh->descs, - NULL, - vals); + switch (cmd) { + case GPIOHANDLE_GET_LINE_VALUES_IOCTL: + /* NOTE: It's okay to read values of output lines */ + ret = gpiod_get_array_value_complex(false, true, + lh->num_descs, lh->descs, + NULL, vals); if (ret) return ret; @@ -218,7 +217,7 @@ static long linehandle_ioctl(struct file *file, unsigned int cmd, return -EFAULT; return 0; - } else if (cmd == GPIOHANDLE_SET_LINE_VALUES_IOCTL) { + case GPIOHANDLE_SET_LINE_VALUES_IOCTL: /* * All line descriptors were created at once with the same * flags so just check if the first one is really output. @@ -240,10 +239,11 @@ static long linehandle_ioctl(struct file *file, unsigned int cmd, lh->descs, NULL, vals); - } else if (cmd == GPIOHANDLE_SET_CONFIG_IOCTL) { + case GPIOHANDLE_SET_CONFIG_IOCTL: return linehandle_set_config(lh, ip); + default: + return -EINVAL; } - return -EINVAL; } #ifdef CONFIG_COMPAT @@ -1165,14 +1165,16 @@ static long linereq_ioctl(struct file *file, unsigned int cmd, struct linereq *lr = file->private_data; void __user *ip = (void __user *)arg; - if (cmd == GPIO_V2_LINE_GET_VALUES_IOCTL) + switch (cmd) { + case GPIO_V2_LINE_GET_VALUES_IOCTL: return linereq_get_values(lr, ip); - else if (cmd == GPIO_V2_LINE_SET_VALUES_IOCTL) + case GPIO_V2_LINE_SET_VALUES_IOCTL: return linereq_set_values(lr, ip); - else if (cmd == GPIO_V2_LINE_SET_CONFIG_IOCTL) + case GPIO_V2_LINE_SET_CONFIG_IOCTL: return linereq_set_config(lr, ip); - - return -EINVAL; + default: + return -EINVAL; + } } #ifdef CONFIG_COMPAT @@ -2095,28 +2097,30 @@ static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return -ENODEV; /* Fill in the struct and pass to userspace */ - if (cmd == GPIO_GET_CHIPINFO_IOCTL) { + switch (cmd) { + case GPIO_GET_CHIPINFO_IOCTL: return chipinfo_get(cdev, ip); #ifdef CONFIG_GPIO_CDEV_V1 - } else if (cmd == GPIO_GET_LINEHANDLE_IOCTL) { + case GPIO_GET_LINEHANDLE_IOCTL: return linehandle_create(gdev, ip); - } else if (cmd == GPIO_GET_LINEEVENT_IOCTL) { + case GPIO_GET_LINEEVENT_IOCTL: return lineevent_create(gdev, ip); - } else if (cmd == GPIO_GET_LINEINFO_IOCTL || - cmd == GPIO_GET_LINEINFO_WATCH_IOCTL) { - return lineinfo_get_v1(cdev, ip, - cmd == GPIO_GET_LINEINFO_WATCH_IOCTL); + case GPIO_GET_LINEINFO_IOCTL: + return lineinfo_get_v1(cdev, ip, false); + case GPIO_GET_LINEINFO_WATCH_IOCTL: + return lineinfo_get_v1(cdev, ip, true); #endif /* CONFIG_GPIO_CDEV_V1 */ - } else if (cmd == GPIO_V2_GET_LINEINFO_IOCTL || - cmd == GPIO_V2_GET_LINEINFO_WATCH_IOCTL) { - return lineinfo_get(cdev, ip, - cmd == GPIO_V2_GET_LINEINFO_WATCH_IOCTL); - } else if (cmd == GPIO_V2_GET_LINE_IOCTL) { + case GPIO_V2_GET_LINEINFO_IOCTL: + return lineinfo_get(cdev, ip, false); + case GPIO_V2_GET_LINEINFO_WATCH_IOCTL: + return lineinfo_get(cdev, ip, true); + case GPIO_V2_GET_LINE_IOCTL: return linereq_create(gdev, ip); - } else if (cmd == GPIO_GET_LINEINFO_UNWATCH_IOCTL) { + case GPIO_GET_LINEINFO_UNWATCH_IOCTL: return lineinfo_unwatch(cdev, ip); + default: + return -EINVAL; } - return -EINVAL; } #ifdef CONFIG_COMPAT diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 59d8affad343..3e01a3ac652d 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -186,9 +186,8 @@ static int gpiochip_find_base(int ngpio) /* found a free space? */ if (gdev->base + gdev->ngpio <= base) break; - else - /* nope, check the space right before the chip */ - base = gdev->base - ngpio; + /* nope, check the space right before the chip */ + base = gdev->base - ngpio; } if (gpio_is_valid(base)) { @@ -2481,8 +2480,7 @@ int gpiod_direction_output(struct gpio_desc *desc, int value) ret = gpiod_direction_input(desc); goto set_output_flag; } - } - else if (test_bit(FLAG_OPEN_SOURCE, &desc->flags)) { + } else if (test_bit(FLAG_OPEN_SOURCE, &desc->flags)) { ret = gpio_set_config(desc, PIN_CONFIG_DRIVE_OPEN_SOURCE); if (!ret) goto set_output_value; @@ -2656,9 +2654,9 @@ static int gpiod_get_raw_value_commit(const struct gpio_desc *desc) static int gpio_chip_get_multiple(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits) { - if (gc->get_multiple) { + if (gc->get_multiple) return gc->get_multiple(gc, mask, bits); - } else if (gc->get) { + if (gc->get) { int i, value; for_each_set_bit(i, mask, gc->ngpio) { From 6d79546622baab843172b52c3af035f83c1b21df Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 5 Dec 2022 13:39:02 +0100 Subject: [PATCH 0469/4345] gpiolib: cdev: fix NULL-pointer dereferences [ Upstream commit 533aae7c94dbc2b14301cfd68ae7e0e90f0c8438 ] There are several places where we can crash the kernel by requesting lines, unbinding the GPIO device, then calling any of the system calls relevant to the GPIO character device's annonymous file descriptors: ioctl(), read(), poll(). While I observed it with the GPIO simulator, it will also happen for any of the GPIO devices that can be hot-unplugged - for instance any HID GPIO expander (e.g. CP2112). This affects both v1 and v2 uAPI. This fixes it partially by checking if gdev->chip is not NULL but it doesn't entirely remedy the situation as we still have a race condition in which another thread can remove the device after the check. Fixes: d7c51b47ac11 ("gpio: userspace ABI for reading/writing GPIO lines") Fixes: 3c0d9c635ae2 ("gpiolib: cdev: support GPIO_V2_GET_LINE_IOCTL and GPIO_V2_LINE_GET_VALUES_IOCTL") Fixes: aad955842d1c ("gpiolib: cdev: support GPIO_V2_GET_LINEINFO_IOCTL and GPIO_V2_GET_LINEINFO_WATCH_IOCTL") Fixes: a54756cb24ea ("gpiolib: cdev: support GPIO_V2_LINE_SET_CONFIG_IOCTL") Fixes: 7b8e00d98168 ("gpiolib: cdev: support GPIO_V2_LINE_SET_VALUES_IOCTL") Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/gpio/gpiolib-cdev.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index b51b4d7a611e..40d0196d8bdc 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -200,6 +200,9 @@ static long linehandle_ioctl(struct file *file, unsigned int cmd, unsigned int i; int ret; + if (!lh->gdev->chip) + return -ENODEV; + switch (cmd) { case GPIOHANDLE_GET_LINE_VALUES_IOCTL: /* NOTE: It's okay to read values of output lines */ @@ -1165,6 +1168,9 @@ static long linereq_ioctl(struct file *file, unsigned int cmd, struct linereq *lr = file->private_data; void __user *ip = (void __user *)arg; + if (!lr->gdev->chip) + return -ENODEV; + switch (cmd) { case GPIO_V2_LINE_GET_VALUES_IOCTL: return linereq_get_values(lr, ip); @@ -1191,6 +1197,9 @@ static __poll_t linereq_poll(struct file *file, struct linereq *lr = file->private_data; __poll_t events = 0; + if (!lr->gdev->chip) + return EPOLLHUP | EPOLLERR; + poll_wait(file, &lr->wait, wait); if (!kfifo_is_empty_spinlocked_noirqsave(&lr->events, @@ -1210,6 +1219,9 @@ static ssize_t linereq_read(struct file *file, ssize_t bytes_read = 0; int ret; + if (!lr->gdev->chip) + return -ENODEV; + if (count < sizeof(le)) return -EINVAL; @@ -1475,6 +1487,9 @@ static __poll_t lineevent_poll(struct file *file, struct lineevent_state *le = file->private_data; __poll_t events = 0; + if (!le->gdev->chip) + return EPOLLHUP | EPOLLERR; + poll_wait(file, &le->wait, wait); if (!kfifo_is_empty_spinlocked_noirqsave(&le->events, &le->wait.lock)) @@ -1510,6 +1525,9 @@ static ssize_t lineevent_read(struct file *file, ssize_t ge_size; int ret; + if (!le->gdev->chip) + return -ENODEV; + /* * When compatible system call is being used the struct gpioevent_data, * in case of at least ia32, has different size due to the alignment @@ -1588,6 +1606,9 @@ static long lineevent_ioctl(struct file *file, unsigned int cmd, void __user *ip = (void __user *)arg; struct gpiohandle_data ghd; + if (!le->gdev->chip) + return -ENODEV; + /* * We can get the value for an event line but not set it, * because it is input by definition. @@ -2168,6 +2189,9 @@ static __poll_t lineinfo_watch_poll(struct file *file, struct gpio_chardev_data *cdev = file->private_data; __poll_t events = 0; + if (!cdev->gdev->chip) + return EPOLLHUP | EPOLLERR; + poll_wait(file, &cdev->wait, pollt); if (!kfifo_is_empty_spinlocked_noirqsave(&cdev->events, @@ -2186,6 +2210,9 @@ static ssize_t lineinfo_watch_read(struct file *file, char __user *buf, int ret; size_t event_size; + if (!cdev->gdev->chip) + return -ENODEV; + #ifndef CONFIG_GPIO_CDEV_V1 event_size = sizeof(struct gpio_v2_line_info_changed); if (count < event_size) From 61df25c41b8e0d2c988ccf17139f70075a2e1ba4 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Sat, 29 Oct 2022 17:38:25 +0800 Subject: [PATCH 0470/4345] i2c: mux: reg: check return value after calling platform_get_resource() [ Upstream commit 2d47b79d2bd39cc6369eccf94a06568d84c906ae ] It will cause null-ptr-deref in resource_size(), if platform_get_resource() returns NULL, move calling resource_size() after devm_ioremap_resource() that will check 'res' to avoid null-ptr-deref. And use devm_platform_get_and_ioremap_resource() to simplify code. Fixes: b3fdd32799d8 ("i2c: mux: Add register-based mux i2c-mux-reg") Signed-off-by: Yang Yingliang Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/muxes/i2c-mux-reg.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c index 0e0679f65cf7..30a6de1694e0 100644 --- a/drivers/i2c/muxes/i2c-mux-reg.c +++ b/drivers/i2c/muxes/i2c-mux-reg.c @@ -183,13 +183,12 @@ static int i2c_mux_reg_probe(struct platform_device *pdev) if (!mux->data.reg) { dev_info(&pdev->dev, "Register not set, using platform resource\n"); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - mux->data.reg_size = resource_size(res); - mux->data.reg = devm_ioremap_resource(&pdev->dev, res); + mux->data.reg = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(mux->data.reg)) { ret = PTR_ERR(mux->data.reg); goto err_put_parent; } + mux->data.reg_size = resource_size(res); } if (mux->data.reg_size != 4 && mux->data.reg_size != 2 && From 9ac541a0898e8ec187a3fa7024b9701cffae6bf2 Mon Sep 17 00:00:00 2001 From: Zheyu Ma Date: Fri, 29 Jul 2022 19:02:16 +0800 Subject: [PATCH 0471/4345] i2c: ismt: Fix an out-of-bounds bug in ismt_access() [ Upstream commit 39244cc754829bf707dccd12e2ce37510f5b1f8d ] When the driver does not check the data from the user, the variable 'data->block[0]' may be very large to cause an out-of-bounds bug. The following log can reveal it: [ 33.995542] i2c i2c-1: ioctl, cmd=0x720, arg=0x7ffcb3dc3a20 [ 33.995978] ismt_smbus 0000:00:05.0: I2C_SMBUS_BLOCK_DATA: WRITE [ 33.996475] ================================================================== [ 33.996995] BUG: KASAN: out-of-bounds in ismt_access.cold+0x374/0x214b [ 33.997473] Read of size 18446744073709551615 at addr ffff88810efcfdb1 by task ismt_poc/485 [ 33.999450] Call Trace: [ 34.001849] memcpy+0x20/0x60 [ 34.002077] ismt_access.cold+0x374/0x214b [ 34.003382] __i2c_smbus_xfer+0x44f/0xfb0 [ 34.004007] i2c_smbus_xfer+0x10a/0x390 [ 34.004291] i2cdev_ioctl_smbus+0x2c8/0x710 [ 34.005196] i2cdev_ioctl+0x5ec/0x74c Fix this bug by checking the size of 'data->block[0]' first. Fixes: 13f35ac14cd0 ("i2c: Adding support for Intel iSMT SMBus 2.0 host controller") Signed-off-by: Zheyu Ma Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-ismt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index 3d2d92640651..cec2b2ae7684 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -507,6 +507,9 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, if (read_write == I2C_SMBUS_WRITE) { /* Block Write */ dev_dbg(dev, "I2C_SMBUS_BLOCK_DATA: WRITE\n"); + if (data->block[0] < 1 || data->block[0] > I2C_SMBUS_BLOCK_MAX) + return -EINVAL; + dma_size = data->block[0] + 1; dma_direction = DMA_TO_DEVICE; desc->wr_len_cmd = dma_size; From b7bf15aa197314c1adfcef5894385c0f2557bb8c Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Thu, 8 Dec 2022 19:00:58 +0800 Subject: [PATCH 0472/4345] usb: storage: Add check for kcalloc [ Upstream commit c35ca10f53c51eeb610d3f8fbc6dd6d511b58a58 ] As kcalloc may return NULL pointer, the return value should be checked and return error if fails as same as the ones in alauda_read_map. Fixes: e80b0fade09e ("[PATCH] USB Storage: add alauda support") Acked-by: Alan Stern Signed-off-by: Jiasheng Jiang Link: https://lore.kernel.org/r/20221208110058.12983-1-jiasheng@iscas.ac.cn Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/storage/alauda.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/storage/alauda.c b/drivers/usb/storage/alauda.c index 20b857e97e60..7e4ce0e7e05a 100644 --- a/drivers/usb/storage/alauda.c +++ b/drivers/usb/storage/alauda.c @@ -438,6 +438,8 @@ static int alauda_init_media(struct us_data *us) + MEDIA_INFO(us).blockshift + MEDIA_INFO(us).pageshift); MEDIA_INFO(us).pba_to_lba = kcalloc(num_zones, sizeof(u16*), GFP_NOIO); MEDIA_INFO(us).lba_to_pba = kcalloc(num_zones, sizeof(u16*), GFP_NOIO); + if (MEDIA_INFO(us).pba_to_lba == NULL || MEDIA_INFO(us).lba_to_pba == NULL) + return USB_STOR_TRANSPORT_ERROR; if (alauda_reset_media(us) != USB_STOR_XFER_GOOD) return USB_STOR_TRANSPORT_ERROR; From 962f869b36789591c4c71a8bb5e8f971d623d808 Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Wed, 7 Dec 2022 21:53:26 +0800 Subject: [PATCH 0473/4345] tracing/hist: Fix issue of losting command info in error_log [ Upstream commit 608c6ed3337850c767ab0dd6c583477922233e29 ] When input some constructed invalid 'trigger' command, command info in 'error_log' are lost [1]. The root cause is that there is a path that event_hist_trigger_parse() is recursely called once and 'last_cmd' which save origin command is cleared, then later calling of hist_err() will no longer record origin command info: event_hist_trigger_parse() { last_cmd_set() // <1> 'last_cmd' save origin command here at first create_actions() { onmatch_create() { action_create() { trace_action_create() { trace_action_create_field_var() { create_field_var_hist() { event_hist_trigger_parse() { // <2> recursely called once hist_err_clear() // <3> 'last_cmd' is cleared here } hist_err() // <4> No longer find origin command!!! Since 'glob' is empty string while running into the recurse call, we can trickly check it and bypass the call of hist_err_clear() to solve it. [1] # cd /sys/kernel/tracing # echo "my_synth_event int v1; int v2; int v3;" >> synthetic_events # echo 'hist:keys=pid' >> events/sched/sched_waking/trigger # echo "hist:keys=next_pid:onmatch(sched.sched_waking).my_synth_event(\ pid,pid1)" >> events/sched/sched_switch/trigger # cat error_log [ 8.405018] hist:sched:sched_switch: error: Couldn't find synthetic event Command: hist:keys=next_pid:onmatch(sched.sched_waking).my_synth_event(pid,pid1) ^ [ 8.816902] hist:sched:sched_switch: error: Couldn't find field Command: hist:keys=next_pid:onmatch(sched.sched_waking).my_synth_event(pid,pid1) ^ [ 8.816902] hist:sched:sched_switch: error: Couldn't parse field variable Command: hist:keys=next_pid:onmatch(sched.sched_waking).my_synth_event(pid,pid1) ^ [ 8.999880] : error: Couldn't find field Command: ^ [ 8.999880] : error: Couldn't parse field variable Command: ^ [ 8.999880] : error: Couldn't find field Command: ^ [ 8.999880] : error: Couldn't create histogram for field Command: ^ Link: https://lore.kernel.org/linux-trace-kernel/20221207135326.3483216-1-zhengyejian1@huawei.com Cc: Cc: Fixes: f404da6e1d46 ("tracing: Add 'last error' error facility for hist triggers") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/trace_events_hist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index fd5416829445..8e01ab49118d 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5827,7 +5827,7 @@ enable: /* Just return zero, not the number of registered triggers */ ret = 0; out: - if (ret == 0) + if (ret == 0 && glob[0]) hist_err_clear(); return ret; From 86fa7bb4e2d562714555eb48f7129e92fc4bb975 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Thu, 8 Dec 2022 09:33:41 +0800 Subject: [PATCH 0474/4345] samples: vfio-mdev: Fix missing pci_disable_device() in mdpy_fb_probe() [ Upstream commit d1f0f50fbbbbca1e3e8157e51934613bf88f6d44 ] Add missing pci_disable_device() in fail path of mdpy_fb_probe(). Besides, fix missing release functions in mdpy_fb_remove(). Fixes: cacade1946a4 ("sample: vfio mdev display - guest driver") Signed-off-by: Shang XiaoJing Link: https://lore.kernel.org/r/20221208013341.3999-1-shangxiaojing@huawei.com Signed-off-by: Alex Williamson Signed-off-by: Sasha Levin --- samples/vfio-mdev/mdpy-fb.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/samples/vfio-mdev/mdpy-fb.c b/samples/vfio-mdev/mdpy-fb.c index 9ec93d90e8a5..4eb7aa11cfbb 100644 --- a/samples/vfio-mdev/mdpy-fb.c +++ b/samples/vfio-mdev/mdpy-fb.c @@ -109,7 +109,7 @@ static int mdpy_fb_probe(struct pci_dev *pdev, ret = pci_request_regions(pdev, "mdpy-fb"); if (ret < 0) - return ret; + goto err_disable_dev; pci_read_config_dword(pdev, MDPY_FORMAT_OFFSET, &format); pci_read_config_dword(pdev, MDPY_WIDTH_OFFSET, &width); @@ -191,6 +191,9 @@ err_release_fb: err_release_regions: pci_release_regions(pdev); +err_disable_dev: + pci_disable_device(pdev); + return ret; } @@ -199,7 +202,10 @@ static void mdpy_fb_remove(struct pci_dev *pdev) struct fb_info *info = pci_get_drvdata(pdev); unregister_framebuffer(info); + iounmap(info->screen_base); framebuffer_release(info); + pci_release_regions(pdev); + pci_disable_device(pdev); } static struct pci_device_id mdpy_fb_pci_table[] = { From c56c1449ccc3e40614e5941e96caf405da224362 Mon Sep 17 00:00:00 2001 From: Marcus Folkesson Date: Fri, 14 Oct 2022 09:35:07 +0200 Subject: [PATCH 0475/4345] thermal/drivers/imx8mm_thermal: Validate temperature range [ Upstream commit d37edc7370273306d8747097fafa62436c1cfe16 ] Check against the upper temperature limit (125 degrees C) before consider the temperature valid. Fixes: 5eed800a6811 ("thermal: imx8mm: Add support for i.MX8MM thermal monitoring unit") Signed-off-by: Marcus Folkesson Reviewed-by: Jacky Bai Link: https://lore.kernel.org/r/20221014073507.1594844-1-marcus.folkesson@gmail.com Signed-off-by: Daniel Lezcano Signed-off-by: Sasha Levin --- drivers/thermal/imx8mm_thermal.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/imx8mm_thermal.c b/drivers/thermal/imx8mm_thermal.c index 0f4cabd2a8c6..6be16e0598b6 100644 --- a/drivers/thermal/imx8mm_thermal.c +++ b/drivers/thermal/imx8mm_thermal.c @@ -65,8 +65,14 @@ static int imx8mm_tmu_get_temp(void *data, int *temp) u32 val; val = readl_relaxed(tmu->base + TRITSR) & TRITSR_TEMP0_VAL_MASK; + + /* + * Do not validate against the V bit (bit 31) due to errata + * ERR051272: TMU: Bit 31 of registers TMU_TSCR/TMU_TRITSR/TMU_TRATSR invalid + */ + *temp = val * 1000; - if (*temp < VER1_TEMP_LOW_LIMIT) + if (*temp < VER1_TEMP_LOW_LIMIT || *temp > VER2_TEMP_HIGH_LIMIT) return -EAGAIN; return 0; From f279a7af799d2e783ac8b48c059ff5e95f21561a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 1 Nov 2022 17:09:46 +0200 Subject: [PATCH 0476/4345] fbdev: ssd1307fb: Drop optional dependency [ Upstream commit 025e3b507a3a8e1ee96a3112bb67495c77d6cdb6 ] Only a single out of three devices need a PWM, so from driver it's optional. Moreover it's a single driver in the entire kernel that currently selects PWM. Unfortunately this selection is a root cause of the circular dependencies when we want to enable optional PWM for some other drivers that select GPIOLIB. Fixes: a2ed00da5047 ("drivers/video: add support for the Solomon SSD1307 OLED Controller") Signed-off-by: Andy Shevchenko Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 4f02db65dede..3ac78db17e46 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -2216,7 +2216,6 @@ config FB_SSD1307 select FB_SYS_COPYAREA select FB_SYS_IMAGEBLIT select FB_DEFERRED_IO - select PWM select FB_BACKLIGHT help This driver implements support for the Solomon SSD1307 From 3922415e4c3f03baddfc756e66aabaa9e2f4d798 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Sat, 12 Nov 2022 17:55:10 +0800 Subject: [PATCH 0477/4345] fbdev: pm2fb: fix missing pci_disable_device() [ Upstream commit ed359a464846b48f76ea6cc5cd8257e545ac97f4 ] Add missing pci_disable_device() in error path of probe() and remove() path. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/pm2fb.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c index c12d46e28359..87b6a929a6b3 100644 --- a/drivers/video/fbdev/pm2fb.c +++ b/drivers/video/fbdev/pm2fb.c @@ -1529,8 +1529,10 @@ static int pm2fb_probe(struct pci_dev *pdev, const struct pci_device_id *id) } info = framebuffer_alloc(sizeof(struct pm2fb_par), &pdev->dev); - if (!info) - return -ENOMEM; + if (!info) { + err = -ENOMEM; + goto err_exit_disable; + } default_par = info->par; switch (pdev->device) { @@ -1711,6 +1713,8 @@ static int pm2fb_probe(struct pci_dev *pdev, const struct pci_device_id *id) release_mem_region(pm2fb_fix.mmio_start, pm2fb_fix.mmio_len); err_exit_neither: framebuffer_release(info); + err_exit_disable: + pci_disable_device(pdev); return retval; } @@ -1737,6 +1741,7 @@ static void pm2fb_remove(struct pci_dev *pdev) fb_dealloc_cmap(&info->cmap); kfree(info->pixmap.addr); framebuffer_release(info); + pci_disable_device(pdev); } static const struct pci_device_id pm2fb_id_table[] = { From 71bca42bc44f7141f39d4f3f240e6d2aeb245e3c Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Mon, 14 Nov 2022 09:08:52 +0800 Subject: [PATCH 0478/4345] fbdev: via: Fix error in via_core_init() [ Upstream commit 5886b130de953cfb8826f7771ec8640a79934a7f ] via_core_init() won't exit the driver when pci_register_driver() failed. Exit the viafb-i2c and the viafb-gpio in failed path to prevent error. VIA Graphics Integration Chipset framebuffer 2.4 initializing Error: Driver 'viafb-i2c' is already registered, aborting... Error: Driver 'viafb-gpio' is already registered, aborting... Fixes: 7582eb9be85f ("viafb: Turn GPIO and i2c into proper platform devices") Signed-off-by: Shang XiaoJing Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/via/via-core.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/via/via-core.c b/drivers/video/fbdev/via/via-core.c index 89d75079b730..0363b478fa3e 100644 --- a/drivers/video/fbdev/via/via-core.c +++ b/drivers/video/fbdev/via/via-core.c @@ -725,7 +725,14 @@ static int __init via_core_init(void) return ret; viafb_i2c_init(); viafb_gpio_init(); - return pci_register_driver(&via_driver); + ret = pci_register_driver(&via_driver); + if (ret) { + viafb_gpio_exit(); + viafb_i2c_exit(); + return ret; + } + + return 0; } static void __exit via_core_exit(void) From 164857bc0223e287d6332a47d90f5c44daa0f5c3 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Mon, 14 Nov 2022 16:56:54 +0800 Subject: [PATCH 0479/4345] fbdev: vermilion: decrease reference count in error path [ Upstream commit 001f2cdb952a9566c77fb4b5470cc361db5601bb ] pci_get_device() will increase the reference count for the returned pci_dev. For the error path, we need to use pci_dev_put() to decrease the reference count. Fixes: dbe7e429fedb ("vmlfb: framebuffer driver for Intel Vermilion Range") Signed-off-by: Xiongfeng Wang Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/vermilion/vermilion.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c index ff61605b8764..a543643ce014 100644 --- a/drivers/video/fbdev/vermilion/vermilion.c +++ b/drivers/video/fbdev/vermilion/vermilion.c @@ -277,8 +277,10 @@ static int vmlfb_get_gpu(struct vml_par *par) mutex_unlock(&vml_mutex); - if (pci_enable_device(par->gpu) < 0) + if (pci_enable_device(par->gpu) < 0) { + pci_dev_put(par->gpu); return -ENODEV; + } return 0; } From ee13e2aec330f47262692a9f0bed5924c0bb3394 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 10 Dec 2022 12:35:22 +0100 Subject: [PATCH 0480/4345] fbdev: uvesafb: Fixes an error handling path in uvesafb_probe() [ Upstream commit a94371040712031ba129c7e9d8ff04a06a2f8207 ] If an error occurs after a successful uvesafb_init_mtrr() call, it must be undone by a corresponding arch_phys_wc_del() call, as already done in the remove function. This has been added in the remove function in commit 63e28a7a5ffc ("uvesafb: Clean up MTRR code") Fixes: 8bdb3a2d7df4 ("uvesafb: the driver core") Signed-off-by: Christophe JAILLET Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/uvesafb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index def14ac0ebe1..661f12742e4f 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -1756,6 +1756,7 @@ static int uvesafb_probe(struct platform_device *dev) out_unmap: iounmap(info->screen_base); out_mem: + arch_phys_wc_del(par->mtrr_handle); release_mem_region(info->fix.smem_start, info->fix.smem_len); out_reg: release_region(0x3c0, 32); From 6ba4b00f8837f8c10407119ea887d7ecf9864938 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 1 Nov 2022 11:41:18 +0800 Subject: [PATCH 0481/4345] HSI: omap_ssi_core: fix unbalanced pm_runtime_disable() [ Upstream commit f5181c35ed7ba0ceb6e42872aad1334d994b0175 ] In error label 'out1' path in ssi_probe(), the pm_runtime_enable() has not been called yet, so pm_runtime_disable() is not needed. Fixes: b209e047bc74 ("HSI: Introduce OMAP SSI driver") Signed-off-by: Yang Yingliang Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/hsi/controllers/omap_ssi_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hsi/controllers/omap_ssi_core.c b/drivers/hsi/controllers/omap_ssi_core.c index eb9820158318..b23a576ed88a 100644 --- a/drivers/hsi/controllers/omap_ssi_core.c +++ b/drivers/hsi/controllers/omap_ssi_core.c @@ -536,9 +536,9 @@ out3: device_for_each_child(&pd->dev, NULL, ssi_remove_ports); out2: ssi_remove_controller(ssi); + pm_runtime_disable(&pd->dev); out1: platform_set_drvdata(pd, NULL); - pm_runtime_disable(&pd->dev); return err; } From ae2eb995abb90d07a43e9d5cdc22fd0a41ccf174 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 31 Oct 2022 15:43:37 +0800 Subject: [PATCH 0482/4345] HSI: omap_ssi_core: fix possible memory leak in ssi_probe() [ Upstream commit 1aff514e1d2bd47854dbbdf867970b9d463d4c57 ] If ssi_add_controller() returns error, it should call hsi_put_controller() to give up the reference that was set in hsi_alloc_controller(), so that it can call hsi_controller_release() to free controller and ports that allocated in hsi_alloc_controller(). Fixes: b209e047bc74 ("HSI: Introduce OMAP SSI driver") Signed-off-by: Yang Yingliang Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/hsi/controllers/omap_ssi_core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hsi/controllers/omap_ssi_core.c b/drivers/hsi/controllers/omap_ssi_core.c index b23a576ed88a..052cf3e92dd6 100644 --- a/drivers/hsi/controllers/omap_ssi_core.c +++ b/drivers/hsi/controllers/omap_ssi_core.c @@ -502,8 +502,10 @@ static int ssi_probe(struct platform_device *pd) platform_set_drvdata(pd, ssi); err = ssi_add_controller(ssi, pd); - if (err < 0) + if (err < 0) { + hsi_put_controller(ssi); goto out1; + } pm_runtime_enable(&pd->dev); From 1d6d90994a8d32e44b89b5e62a78d9fd50686772 Mon Sep 17 00:00:00 2001 From: Zeng Heng Date: Thu, 17 Nov 2022 16:32:19 +0800 Subject: [PATCH 0483/4345] power: supply: fix residue sysfs file in error handle route of __power_supply_register() [ Upstream commit 5b79480ce1978864ac3f06f2134dfa3b6691fe74 ] If device_add() succeeds, we should call device_del() when want to get rid of it, so move it into proper jump symbol. Otherwise, when __power_supply_register() returns fail and goto wakeup_init_failed to exit, there is still residue device file in sysfs. When attempt to probe device again, sysfs would complain as below: sysfs: cannot create duplicate filename '/devices/platform/i2c/i2c-0/0-001c/power_supply/adp5061' Call Trace: dump_stack_lvl+0x68/0x85 sysfs_warn_dup.cold+0x1c/0x29 sysfs_create_dir_ns+0x1b1/0x1d0 kobject_add_internal+0x143/0x390 kobject_add+0x108/0x170 Fixes: 80c6463e2fa3 ("power_supply: Fix Oops from NULL pointer dereference from wakeup_source_activate") Signed-off-by: Zeng Heng Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/power_supply_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 280c54c23e37..be2cb925c115 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -1201,8 +1201,8 @@ create_triggers_failed: register_cooler_failed: psy_unregister_thermal(psy); register_thermal_failed: - device_del(dev); wakeup_init_failed: + device_del(dev); device_add_failed: check_supplies_failed: dev_set_name_failed: From 6364577ae225ddec98e36f5db6d40b2dedb84ea7 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Mon, 21 Nov 2022 07:52:34 +0000 Subject: [PATCH 0484/4345] perf trace: Return error if a system call doesn't exist [ Upstream commit d4223e1776c30b2ce8d0e6eaadcbf696e60fca3c ] When a system call is not detected, the reason is either because the system call ID is out of scope or failure to find the corresponding path in the sysfs, trace__read_syscall_info() returns zero. Finally, without returning an error value it introduces confusion for the caller. This patch lets the function trace__read_syscall_info() to return -EEXIST when a system call doesn't exist. Fixes: b8b1033fcaa091d8 ("perf trace: Mark syscall ids that are not allocated to avoid unnecessary error messages") Signed-off-by: Leo Yan Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: bpf@vger.kernel.org Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20221121075237.127706-3-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/builtin-trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index de80534473af..555e16d8d55b 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1774,11 +1774,11 @@ static int trace__read_syscall_info(struct trace *trace, int id) #endif sc = trace->syscalls.table + id; if (sc->nonexistent) - return 0; + return -EEXIST; if (name == NULL) { sc->nonexistent = true; - return 0; + return -EEXIST; } sc->name = name; From bd29da58046aa772c775548ee6f502cc5f3aa489 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Mon, 21 Nov 2022 07:52:33 +0000 Subject: [PATCH 0485/4345] perf trace: Use macro RAW_SYSCALL_ARGS_NUM to replace number [ Upstream commit eadcab4c7a66e1df03d32da0db55d89fd9343fcc ] This patch defines a macro RAW_SYSCALL_ARGS_NUM to replace the open coded number '6'. Signed-off-by: Leo Yan Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20221121075237.127706-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Stable-dep-of: 03e9a5d8eb55 ("perf trace: Handle failure when trace point folder is missed") Signed-off-by: Sasha Levin --- tools/perf/builtin-trace.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 555e16d8d55b..1a7279687f25 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -87,6 +87,8 @@ # define F_LINUX_SPECIFIC_BASE 1024 #endif +#define RAW_SYSCALL_ARGS_NUM 6 + /* * strtoul: Go from a string to a value, i.e. for msr: MSR_FS_BASE to 0xc0000100 */ @@ -107,7 +109,7 @@ struct syscall_fmt { const char *sys_enter, *sys_exit; } bpf_prog_name; - struct syscall_arg_fmt arg[6]; + struct syscall_arg_fmt arg[RAW_SYSCALL_ARGS_NUM]; u8 nr_args; bool errpid; bool timeout; @@ -1216,7 +1218,7 @@ struct syscall { */ struct bpf_map_syscall_entry { bool enabled; - u16 string_args_len[6]; + u16 string_args_len[RAW_SYSCALL_ARGS_NUM]; }; /* @@ -1641,7 +1643,7 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args) { int idx; - if (nr_args == 6 && sc->fmt && sc->fmt->nr_args != 0) + if (nr_args == RAW_SYSCALL_ARGS_NUM && sc->fmt && sc->fmt->nr_args != 0) nr_args = sc->fmt->nr_args; sc->arg_fmt = calloc(nr_args, sizeof(*sc->arg_fmt)); @@ -1792,7 +1794,8 @@ static int trace__read_syscall_info(struct trace *trace, int id) sc->tp_format = trace_event__tp_format("syscalls", tp_name); } - if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields)) + if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? + RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields)) return -ENOMEM; if (IS_ERR(sc->tp_format)) From c8e77bd7499f51b7378bc36fe43dc1c9d5fa4e16 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Mon, 21 Nov 2022 07:52:35 +0000 Subject: [PATCH 0486/4345] perf trace: Handle failure when trace point folder is missed [ Upstream commit 03e9a5d8eb552a1bf692a9c8a5ecd50f4e428006 ] On Arm64 a case is perf tools fails to find the corresponding trace point folder for system calls listed in the table 'syscalltbl_arm64', e.g. the generated system call table contains "lookup_dcookie" but we cannot find out the matched trace point folder for it. We need to figure out if there have any issue for the generated system call table, on the other hand, we need to handle the case when trace point folder is missed under sysfs, this patch sets the flag syscall::nonexistent as true and returns the error from trace__read_syscall_info(). Another problem is for trace__syscall_info(), it returns two different values if a system call doesn't exist: at the first time calling trace__syscall_info() it returns NULL when the system call doesn't exist, later if call trace__syscall_info() again for the same missed system call, it returns pointer of syscall. trace__syscall_info() checks the condition 'syscalls.table[id].name == NULL', but the name will be assigned in the first invoking even the system call is not found. So checking system call's name in trace__syscall_info() is not the right thing to do, this patch simply checks flag syscall::nonexistent to make decision if a system call exists or not, finally trace__syscall_info() returns the consistent result (NULL) if a system call doesn't existed. Fixes: b8b1033fcaa091d8 ("perf trace: Mark syscall ids that are not allocated to avoid unnecessary error messages") Signed-off-by: Leo Yan Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: bpf@vger.kernel.org Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20221121075237.127706-4-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/builtin-trace.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 1a7279687f25..8de0d0a740de 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1794,13 +1794,19 @@ static int trace__read_syscall_info(struct trace *trace, int id) sc->tp_format = trace_event__tp_format("syscalls", tp_name); } + /* + * Fails to read trace point format via sysfs node, so the trace point + * doesn't exist. Set the 'nonexistent' flag as true. + */ + if (IS_ERR(sc->tp_format)) { + sc->nonexistent = true; + return PTR_ERR(sc->tp_format); + } + if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields)) return -ENOMEM; - if (IS_ERR(sc->tp_format)) - return PTR_ERR(sc->tp_format); - sc->args = sc->tp_format->format.fields; /* * We need to check and discard the first variable '__syscall_nr' @@ -2117,11 +2123,8 @@ static struct syscall *trace__syscall_info(struct trace *trace, (err = trace__read_syscall_info(trace, id)) != 0) goto out_cant_read; - if (trace->syscalls.table[id].name == NULL) { - if (trace->syscalls.table[id].nonexistent) - return NULL; + if (trace->syscalls.table && trace->syscalls.table[id].nonexistent) goto out_cant_read; - } return &trace->syscalls.table[id]; From 73ca3b19d902492a7aef7cabae58507984e0f963 Mon Sep 17 00:00:00 2001 From: Ajay Kaher Date: Wed, 23 Nov 2022 15:48:16 +0530 Subject: [PATCH 0487/4345] perf symbol: correction while adjusting symbol [ Upstream commit 6f520ce17920b3cdfbd2479b3ccf27f9706219d0 ] perf doesn't provide proper symbol information for specially crafted .debug files. Sometimes .debug file may not have similar program header as runtime ELF file. For example if we generate .debug file using objcopy --only-keep-debug resulting file will not contain .text, .data and other runtime sections. That means corresponding program headers will have zero FileSiz and modified Offset. Example: program header of text section of libxxx.so: Type Offset VirtAddr PhysAddr FileSiz MemSiz Flags Align LOAD 0x00000000003d3000 0x00000000003d3000 0x00000000003d3000 0x000000000055ae80 0x000000000055ae80 R E 0x1000 Same program header after executing: objcopy --only-keep-debug libxxx.so libxxx.so.debug LOAD 0x0000000000001000 0x00000000003d3000 0x00000000003d3000 0x0000000000000000 0x000000000055ae80 R E 0x1000 Offset and FileSiz have been changed. Following formula will not provide correct value, if program header taken from .debug file (syms_ss): sym.st_value -= phdr.p_vaddr - phdr.p_offset; Correct program header information is located inside runtime ELF file (runtime_ss). Fixes: 2d86612aacb7805f ("perf symbol: Correct address for bss symbols") Signed-off-by: Ajay Kaher Cc: Alexander Shishkin Cc: Alexey Makhalov Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Srivatsa S. Bhat Cc: Steven Rostedt (VMware) Cc: Vasavi Sirnapalli Link: http://lore.kernel.org/lkml/1669198696-50547-1-git-send-email-akaher@vmware.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/symbol-elf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 3e423a920015..5221f272f85c 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1247,7 +1247,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, (!used_opd && syms_ss->adjust_symbols)) { GElf_Phdr phdr; - if (elf_read_program_header(syms_ss->elf, + if (elf_read_program_header(runtime_ss->elf, (u64)sym.st_value, &phdr)) { pr_debug4("%s: failed to find program header for " "symbol: %s st_value: %#" PRIx64 "\n", From 72283ecfdc84cabe544cb5b007afd8db9fbe6623 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Thu, 24 Nov 2022 11:33:32 +0000 Subject: [PATCH 0488/4345] HSI: omap_ssi_core: Fix error handling in ssi_init() [ Upstream commit 3ffa9f713c39a213a08d9ff13ab983a8aa5d8b5d ] The ssi_init() returns the platform_driver_register() directly without checking its return value, if platform_driver_register() failed, the ssi_pdriver is not unregistered. Fix by unregister ssi_pdriver when the last platform_driver_register() failed. Fixes: 0fae198988b8 ("HSI: omap_ssi: built omap_ssi and omap_ssi_port into one module") Signed-off-by: Yuan Can Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/hsi/controllers/omap_ssi_core.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/hsi/controllers/omap_ssi_core.c b/drivers/hsi/controllers/omap_ssi_core.c index 052cf3e92dd6..26f2c3c01297 100644 --- a/drivers/hsi/controllers/omap_ssi_core.c +++ b/drivers/hsi/controllers/omap_ssi_core.c @@ -631,7 +631,13 @@ static int __init ssi_init(void) { if (ret) return ret; - return platform_driver_register(&ssi_port_pdriver); + ret = platform_driver_register(&ssi_port_pdriver); + if (ret) { + platform_driver_unregister(&ssi_pdriver); + return ret; + } + + return 0; } module_init(ssi_init); From 5beadb55f4e36fafe5d6df5dcd5f85d803f3f134 Mon Sep 17 00:00:00 2001 From: ruanjinjie Date: Mon, 5 Dec 2022 15:51:53 +0800 Subject: [PATCH 0489/4345] power: supply: fix null pointer dereferencing in power_supply_get_battery_info [ Upstream commit 104bb8a663451404a26331263ce5b96c34504049 ] when kmalloc() fail to allocate memory in kasprintf(), propname will be NULL, strcmp() called by of_get_property() will cause null pointer dereference. So return ENOMEM if kasprintf() return NULL pointer. Fixes: 3afb50d7125b ("power: supply: core: Add some helpers to use the battery OCV capacity table") Signed-off-by: ruanjinjie Reviewed-by: Baolin Wang Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/power_supply_core.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index be2cb925c115..2b644590fa8e 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -677,6 +677,11 @@ int power_supply_get_battery_info(struct power_supply *psy, int i, tab_len, size; propname = kasprintf(GFP_KERNEL, "ocv-capacity-table-%d", index); + if (!propname) { + power_supply_put_battery_info(psy, info); + err = -ENOMEM; + goto out_put_node; + } list = of_get_property(battery_np, propname, &size); if (!list || !size) { dev_err(&psy->dev, "failed to get %s\n", propname); From aeef93416c0954fd8c057342bd6a1a0303ccc4c0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 15 Dec 2022 18:03:43 +0100 Subject: [PATCH 0490/4345] RDMA/siw: Fix pointer cast warning [ Upstream commit 5244ca88671a1981ceec09c5c8809f003e6a62aa ] The previous build fix left a remaining issue in configurations with 64-bit dma_addr_t on 32-bit architectures: drivers/infiniband/sw/siw/siw_qp_tx.c: In function 'siw_get_pblpage': drivers/infiniband/sw/siw/siw_qp_tx.c:32:37: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] 32 | return virt_to_page((void *)paddr); | ^ Use the same double cast here that the driver uses elsewhere to convert between dma_addr_t and void*. Fixes: 0d1b756acf60 ("RDMA/siw: Pass a pointer to virt_to_page()") Link: https://lore.kernel.org/r/20221215170347.2612403-1-arnd@kernel.org Signed-off-by: Arnd Bergmann Acked-by: Bernard Metzler Reviewed-by: Linus Walleij Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/sw/siw/siw_qp_tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index 3c3ae5ef2942..df8802b4981c 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -29,7 +29,7 @@ static struct page *siw_get_pblpage(struct siw_mem *mem, u64 addr, int *idx) dma_addr_t paddr = siw_pbl_get_buffer(pbl, offset, NULL, idx); if (paddr) - return virt_to_page((void *)paddr); + return virt_to_page((void *)(uintptr_t)paddr); return NULL; } From 160b92ab4a253dfb0f7cc03b9c33617e9c530104 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Tue, 25 Oct 2022 18:54:11 +0200 Subject: [PATCH 0491/4345] iommu/sun50i: Fix reset release [ Upstream commit 9ad0c1252e84dbc664f0462707182245ed603237 ] Reset signal is asserted by writing 0 to the corresponding locations of masters we want to reset. So in order to deassert all reset signals, we should write 1's to all locations. Current code writes 1's to locations of masters which were just reset which is good. However, at the same time it also writes 0's to other locations and thus asserts reset signals of remaining masters. Fix code by writing all 1's when we want to deassert all reset signals. This bug was discovered when working with Cedrus (video decoder). When it faulted, display went blank due to reset signal assertion. Fixes: 4100b8c229b3 ("iommu: Add Allwinner H6 IOMMU driver") Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20221025165415.307591-2-jernej.skrabec@gmail.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/sun50i-iommu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index ea6db1341916..3dead4f91420 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -28,6 +28,7 @@ #include #define IOMMU_RESET_REG 0x010 +#define IOMMU_RESET_RELEASE_ALL 0xffffffff #define IOMMU_ENABLE_REG 0x020 #define IOMMU_ENABLE_ENABLE BIT(0) @@ -905,7 +906,7 @@ static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id) iommu_write(iommu, IOMMU_INT_CLR_REG, status); iommu_write(iommu, IOMMU_RESET_REG, ~status); - iommu_write(iommu, IOMMU_RESET_REG, status); + iommu_write(iommu, IOMMU_RESET_REG, IOMMU_RESET_RELEASE_ALL); spin_unlock(&iommu->iommu_lock); From 3a63c4ff57bf0c7b7c1ac1c86b1b546bf95604d6 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Tue, 25 Oct 2022 18:54:12 +0200 Subject: [PATCH 0492/4345] iommu/sun50i: Consider all fault sources for reset [ Upstream commit cef20703e2b2276aaa402ec5a65ec9a09963b83e ] We have to reset masters for all faults - permissions, L1 fault or L2 fault. Currently it's done only for permissions. If other type of fault happens, master is in locked up state. Fix that by really considering all fault sources. Fixes: 4100b8c229b3 ("iommu: Add Allwinner H6 IOMMU driver") Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20221025165415.307591-3-jernej.skrabec@gmail.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/sun50i-iommu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index 3dead4f91420..2512eabbf4ac 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -881,8 +881,8 @@ static phys_addr_t sun50i_iommu_handle_perm_irq(struct sun50i_iommu *iommu) static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id) { + u32 status, l1_status, l2_status, resets; struct sun50i_iommu *iommu = dev_id; - u32 status; spin_lock(&iommu->iommu_lock); @@ -892,6 +892,9 @@ static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id) return IRQ_NONE; } + l1_status = iommu_read(iommu, IOMMU_L1PG_INT_REG); + l2_status = iommu_read(iommu, IOMMU_L2PG_INT_REG); + if (status & IOMMU_INT_INVALID_L2PG) sun50i_iommu_handle_pt_irq(iommu, IOMMU_INT_ERR_ADDR_L2_REG, @@ -905,7 +908,8 @@ static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id) iommu_write(iommu, IOMMU_INT_CLR_REG, status); - iommu_write(iommu, IOMMU_RESET_REG, ~status); + resets = (status | l1_status | l2_status) & IOMMU_INT_MASTER_MASK; + iommu_write(iommu, IOMMU_RESET_REG, ~resets); iommu_write(iommu, IOMMU_RESET_REG, IOMMU_RESET_RELEASE_ALL); spin_unlock(&iommu->iommu_lock); From 147af0c1e7fd5db272256107bd2eb2647d966e9e Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Tue, 25 Oct 2022 18:54:13 +0200 Subject: [PATCH 0493/4345] iommu/sun50i: Fix R/W permission check [ Upstream commit eac0104dc69be50bed86926d6f32e82b44f8c921 ] Because driver has enum type permissions and iommu subsystem has bitmap type, we have to be careful how check for combined read and write permissions is done. In such case, we have to mask both permissions and check that both are set at the same time. Current code just masks both flags but doesn't check that both are set. In short, it always sets R/W permission, regardles if requested permissions were RO, WO or RW. Fix that. Fixes: 4100b8c229b3 ("iommu: Add Allwinner H6 IOMMU driver") Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20221025165415.307591-4-jernej.skrabec@gmail.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/sun50i-iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index 2512eabbf4ac..68aee56e2231 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -272,7 +272,7 @@ static u32 sun50i_mk_pte(phys_addr_t page, int prot) enum sun50i_iommu_aci aci; u32 flags = 0; - if (prot & (IOMMU_READ | IOMMU_WRITE)) + if ((prot & (IOMMU_READ | IOMMU_WRITE)) == (IOMMU_READ | IOMMU_WRITE)) aci = SUN50I_IOMMU_ACI_RD_WR; else if (prot & IOMMU_READ) aci = SUN50I_IOMMU_ACI_RD; From ca31ad0932af7e77719c16ca8334c821421ba618 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Tue, 25 Oct 2022 18:54:14 +0200 Subject: [PATCH 0494/4345] iommu/sun50i: Fix flush size [ Upstream commit 67a8a67f9eceb72e4c73d1d09ed9ab04f4b8e12d ] Function sun50i_table_flush() takes number of entries as an argument, not number of bytes. Fix that mistake in sun50i_dte_get_page_table(). Fixes: 4100b8c229b3 ("iommu: Add Allwinner H6 IOMMU driver") Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20221025165415.307591-5-jernej.skrabec@gmail.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/sun50i-iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index 68aee56e2231..dc8ad35cbc4e 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -513,7 +513,7 @@ static u32 *sun50i_dte_get_page_table(struct sun50i_iommu_domain *sun50i_domain, sun50i_iommu_free_page_table(iommu, drop_pt); } - sun50i_table_flush(sun50i_domain, page_table, PT_SIZE); + sun50i_table_flush(sun50i_domain, page_table, NUM_PT_ENTRIES); sun50i_table_flush(sun50i_domain, dte_addr, 1); return page_table; From c2a98433421ea23872ffb6d404c49552b391137a Mon Sep 17 00:00:00 2001 From: Al Cooper Date: Wed, 5 Oct 2022 14:30:14 -0700 Subject: [PATCH 0495/4345] phy: usb: s2 WoL wakeup_count not incremented for USB->Eth devices [ Upstream commit f7fc5b7090372fc4dd7798c874635ca41b8ba733 ] The PHY's "wakeup_count" is not incrementing when waking from WoL. The wakeup count can be found in sysfs at: /sys/bus/platform/devices/rdb/*.usb-phy/power/wakeup_count. The problem is that the system wakup event handler was being passed the wrong "device" by the PHY driver. Fixes: f1c0db40a3ad ("phy: usb: Add "wake on" functionality") Signed-off-by: Al Cooper Signed-off-by: Justin Chen Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/1665005418-15807-3-git-send-email-justinpopo6@gmail.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/broadcom/phy-brcm-usb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/phy/broadcom/phy-brcm-usb.c b/drivers/phy/broadcom/phy-brcm-usb.c index b901a0d4e2a8..cd2240ea2c9a 100644 --- a/drivers/phy/broadcom/phy-brcm-usb.c +++ b/drivers/phy/broadcom/phy-brcm-usb.c @@ -101,9 +101,9 @@ static int brcm_pm_notifier(struct notifier_block *notifier, static irqreturn_t brcm_usb_phy_wake_isr(int irq, void *dev_id) { - struct phy *gphy = dev_id; + struct device *dev = dev_id; - pm_wakeup_event(&gphy->dev, 0); + pm_wakeup_event(dev, 0); return IRQ_HANDLED; } @@ -437,7 +437,7 @@ static int brcm_usb_phy_dvr_init(struct platform_device *pdev, if (priv->wake_irq >= 0) { err = devm_request_irq(dev, priv->wake_irq, brcm_usb_phy_wake_isr, 0, - dev_name(dev), gphy); + dev_name(dev), dev); if (err < 0) return err; device_set_wakeup_capable(dev, 1); From ddd2bb08bd99b7ee4442fbbe0f9b80236fdd71d2 Mon Sep 17 00:00:00 2001 From: Matt Redfearn Date: Tue, 27 Sep 2022 14:52:56 -0700 Subject: [PATCH 0496/4345] include/uapi/linux/swab: Fix potentially missing __always_inline MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit defbab270d45e32b068e7e73c3567232d745c60f ] Commit bc27fb68aaad ("include/uapi/linux/byteorder, swab: force inlining of some byteswap operations") added __always_inline to swab functions and commit 283d75737837 ("uapi/linux/stddef.h: Provide __always_inline to userspace headers") added a definition of __always_inline for use in exported headers when the kernel's compiler.h is not available. However, since swab.h does not include stddef.h, if the header soup does not indirectly include it, the definition of __always_inline is missing, resulting in a compilation failure, which was observed compiling the perf tool using exported headers containing this commit: In file included from /usr/include/linux/byteorder/little_endian.h:12:0, from /usr/include/asm/byteorder.h:14, from tools/include/uapi/linux/perf_event.h:20, from perf.h:8, from builtin-bench.c:18: /usr/include/linux/swab.h:160:8: error: unknown type name `__always_inline' static __always_inline __u16 __swab16p(const __u16 *p) Fix this by replacing the inclusion of linux/compiler.h with linux/stddef.h to ensure that we pick up that definition if required, without relying on it's indirect inclusion. compiler.h is then included indirectly, via stddef.h. Fixes: 283d75737837 ("uapi/linux/stddef.h: Provide __always_inline to userspace headers") Signed-off-by: Matt Redfearn Signed-off-by: Florian Fainelli Signed-off-by: Arnd Bergmann Tested-by: Nathan Chancellor Reviewed-by: Petr Vaněk Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- include/uapi/linux/swab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index 7272f85d6d6a..3736f2fe1541 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -3,7 +3,7 @@ #define _UAPI_LINUX_SWAB_H #include -#include +#include #include #include From a42e95547522fc7714ffb63c440322a2548f0baf Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 28 Oct 2022 13:33:55 +0100 Subject: [PATCH 0497/4345] pwm: tegra: Improve required rate calculation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f271946117dde2ca8741b8138b347b2d68e6ad56 ] For the case where dev_pm_opp_set_rate() is called to set the PWM clock rate, the requested rate is calculated as ... required_clk_rate = (NSEC_PER_SEC / period_ns) << PWM_DUTY_WIDTH; The above calculation may lead to rounding errors because the NSEC_PER_SEC is divided by 'period_ns' before applying the PWM_DUTY_WIDTH multiplication factor. For example, if the period is 45334ns, the above calculation yields a rate of 5646848Hz instead of 5646976Hz. Fix this by applying the multiplication factor before dividing and using the DIV_ROUND_UP macro which yields the expected result of 5646976Hz. Fixes: 1d7796bdb63a ("pwm: tegra: Support dynamic clock frequency configuration") Signed-off-by: Jon Hunter Reviewed-by: Uwe Kleine-König Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-tegra.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pwm/pwm-tegra.c b/drivers/pwm/pwm-tegra.c index 8c4e6657b61e..36cc1452cb7a 100644 --- a/drivers/pwm/pwm-tegra.c +++ b/drivers/pwm/pwm-tegra.c @@ -142,8 +142,8 @@ static int tegra_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, * source clock rate as required_clk_rate, PWM controller will * be able to configure the requested period. */ - required_clk_rate = - (NSEC_PER_SEC / period_ns) << PWM_DUTY_WIDTH; + required_clk_rate = DIV_ROUND_UP_ULL(NSEC_PER_SEC << PWM_DUTY_WIDTH, + period_ns); err = clk_set_rate(pc->clk, required_clk_rate); if (err < 0) From 490b233677de945349c700a552fac23be8b754eb Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 10 Nov 2022 17:27:15 -0800 Subject: [PATCH 0498/4345] dmaengine: idxd: Fix crc_val field for completion record [ Upstream commit dc901d98b1fe6e52ab81cd3e0879379168e06daa ] The crc_val in the completion record should be 64 bits and not 32 bits. Fixes: 4ac823e9cd85 ("dmaengine: idxd: fix delta_rec and crc size field for completion record") Reported-by: Nirav N Shah Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20221111012715.2031481-1-fenghua.yu@intel.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- include/uapi/linux/idxd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 9d9ecc0f4c38..f086c5579006 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -188,7 +188,7 @@ struct dsa_completion_record { }; uint32_t delta_rec_size; - uint32_t crc_val; + uint64_t crc_val; /* DIF check & strip */ struct { From 5814d77e2f72fb1eec7c8e7bcf7c26b294516e37 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 8 Aug 2022 20:23:59 +0200 Subject: [PATCH 0499/4345] rtc: rtc-cmos: Do not check ACPI_FADT_LOW_POWER_S0 [ Upstream commit 6492fed7d8c95f53b0b804ef541324d924d95d41 ] The ACPI_FADT_LOW_POWER_S0 flag merely means that it is better to use low-power S0 idle on the given platform than S3 (provided that the latter is supported) and it doesn't preclude using either of them (which of them will be used depends on the choices made by user space). For this reason, there is no benefit from checking that flag in use_acpi_alarm_quirks(). First off, it cannot be a bug to do S3 with use_acpi_alarm set, because S3 can be used on systems with ACPI_FADT_LOW_POWER_S0 and it must work if really supported, so the ACPI_FADT_LOW_POWER_S0 check is not needed to protect the S3-capable systems from failing. Second, suspend-to-idle can be carried out on a system with ACPI_FADT_LOW_POWER_S0 unset and it is expected to work, so if setting use_acpi_alarm is needed to handle that case correctly, it should be set regardless of the ACPI_FADT_LOW_POWER_S0 value. Accordingly, drop the ACPI_FADT_LOW_POWER_S0 check from use_acpi_alarm_quirks(). Signed-off-by: Rafael J. Wysocki Reviewed-by: Mario Limonciello Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/12054246.O9o76ZdvQC@kreacher Stable-dep-of: 83ebb7b3036d ("rtc: cmos: Disable ACPI RTC event on removal") Signed-off-by: Sasha Levin --- drivers/rtc/rtc-cmos.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index d4f6c4dd42c4..19bc1d8a5de5 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -1265,9 +1265,6 @@ static void use_acpi_alarm_quirks(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return; - if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0)) - return; - if (!is_hpet_enabled()) return; From 0bcfccb48696aba475f046c2021f0733659ce0ef Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 12 Oct 2022 20:07:01 +0200 Subject: [PATCH 0500/4345] rtc: cmos: Fix event handler registration ordering issue [ Upstream commit 4919d3eb2ec0ee364f7e3cf2d99646c1b224fae8 ] Because acpi_install_fixed_event_handler() enables the event automatically on success, it is incorrect to call it before the handler routine passed to it is ready to handle events. Unfortunately, the rtc-cmos driver does exactly the incorrect thing by calling cmos_wake_setup(), which passes rtc_handler() to acpi_install_fixed_event_handler(), before cmos_do_probe(), because rtc_handler() uses dev_get_drvdata() to get to the cmos object pointer and the driver data pointer is only populated in cmos_do_probe(). This leads to a NULL pointer dereference in rtc_handler() on boot if the RTC fixed event happens to be active at the init time. To address this issue, change the initialization ordering of the driver so that cmos_wake_setup() is always called after a successful cmos_do_probe() call. While at it, change cmos_pnp_probe() to call cmos_do_probe() after the initial if () statement used for computing the IRQ argument to be passed to cmos_do_probe() which is cleaner than calling it in each branch of that if () (local variable "irq" can be of type int, because it is passed to that function as an argument of type int). Note that commit 6492fed7d8c9 ("rtc: rtc-cmos: Do not check ACPI_FADT_LOW_POWER_S0") caused this issue to affect a larger number of systems, because previously it only affected systems with ACPI_FADT_LOW_POWER_S0 set, but it is present regardless of that commit. Fixes: 6492fed7d8c9 ("rtc: rtc-cmos: Do not check ACPI_FADT_LOW_POWER_S0") Fixes: a474aaedac99 ("rtc-cmos: move wake setup from ACPI glue into RTC driver") Link: https://lore.kernel.org/linux-acpi/20221010141630.zfzi7mk7zvnmclzy@techsingularity.net/ Reported-by: Mel Gorman Signed-off-by: Rafael J. Wysocki Reviewed-by: Bjorn Helgaas Tested-by: Mel Gorman Link: https://lore.kernel.org/r/5629262.DvuYhMxLoT@kreacher Signed-off-by: Alexandre Belloni Stable-dep-of: 83ebb7b3036d ("rtc: cmos: Disable ACPI RTC event on removal") Signed-off-by: Sasha Levin --- drivers/rtc/rtc-cmos.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 19bc1d8a5de5..449818732acf 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -1357,10 +1357,10 @@ static void cmos_check_acpi_rtc_status(struct device *dev, static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) { - cmos_wake_setup(&pnp->dev); + int irq, ret; if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0)) { - unsigned int irq = 0; + irq = 0; #ifdef CONFIG_X86 /* Some machines contain a PNP entry for the RTC, but * don't define the IRQ. It should always be safe to @@ -1369,13 +1369,17 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) if (nr_legacy_irqs()) irq = RTC_IRQ; #endif - return cmos_do_probe(&pnp->dev, - pnp_get_resource(pnp, IORESOURCE_IO, 0), irq); } else { - return cmos_do_probe(&pnp->dev, - pnp_get_resource(pnp, IORESOURCE_IO, 0), - pnp_irq(pnp, 0)); + irq = pnp_irq(pnp, 0); } + + ret = cmos_do_probe(&pnp->dev, pnp_get_resource(pnp, IORESOURCE_IO, 0), irq); + if (ret) + return ret; + + cmos_wake_setup(&pnp->dev); + + return 0; } static void cmos_pnp_remove(struct pnp_dev *pnp) @@ -1459,10 +1463,9 @@ static inline void cmos_of_init(struct platform_device *pdev) {} static int __init cmos_platform_probe(struct platform_device *pdev) { struct resource *resource; - int irq; + int irq, ret; cmos_of_init(pdev); - cmos_wake_setup(&pdev->dev); if (RTC_IOMAPPED) resource = platform_get_resource(pdev, IORESOURCE_IO, 0); @@ -1472,7 +1475,13 @@ static int __init cmos_platform_probe(struct platform_device *pdev) if (irq < 0) irq = -1; - return cmos_do_probe(&pdev->dev, resource, irq); + ret = cmos_do_probe(&pdev->dev, resource, irq); + if (ret) + return ret; + + cmos_wake_setup(&pdev->dev); + + return 0; } static int cmos_platform_remove(struct platform_device *pdev) From f2ece2c722be915337e733a5533d09c6f0ec02e0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 18 Oct 2022 18:09:31 +0200 Subject: [PATCH 0501/4345] rtc: cmos: Fix wake alarm breakage [ Upstream commit 0782b66ed2fbb035dda76111df0954515e417b24 ] Commit 4919d3eb2ec0 ("rtc: cmos: Fix event handler registration ordering issue") overlooked the fact that cmos_do_probe() depended on the preparations carried out by cmos_wake_setup() and the wake alarm stopped working after the ordering of them had been changed. Address this by partially reverting commit 4919d3eb2ec0 so that cmos_wake_setup() is called before cmos_do_probe() again and moving the rtc_wake_setup() invocation from cmos_wake_setup() directly to the callers of cmos_do_probe() where it will happen after a successful completion of the latter. Fixes: 4919d3eb2ec0 ("rtc: cmos: Fix event handler registration ordering issue") Reported-by: Zhang Rui Reported-by: Todd Brandt Signed-off-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/5887691.lOV4Wx5bFT@kreacher Signed-off-by: Alexandre Belloni Stable-dep-of: 83ebb7b3036d ("rtc: cmos: Disable ACPI RTC event on removal") Signed-off-by: Sasha Levin --- drivers/rtc/rtc-cmos.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 449818732acf..426e6a67cc38 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -1238,6 +1238,9 @@ static u32 rtc_handler(void *context) static inline void rtc_wake_setup(struct device *dev) { + if (acpi_disabled) + return; + acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, dev); /* * After the RTC handler is installed, the Fixed_RTC event should @@ -1291,7 +1294,6 @@ static void cmos_wake_setup(struct device *dev) use_acpi_alarm_quirks(); - rtc_wake_setup(dev); acpi_rtc_info.wake_on = rtc_wake_on; acpi_rtc_info.wake_off = rtc_wake_off; @@ -1359,6 +1361,8 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) { int irq, ret; + cmos_wake_setup(&pnp->dev); + if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0)) { irq = 0; #ifdef CONFIG_X86 @@ -1377,7 +1381,7 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) if (ret) return ret; - cmos_wake_setup(&pnp->dev); + rtc_wake_setup(&pnp->dev); return 0; } @@ -1466,6 +1470,7 @@ static int __init cmos_platform_probe(struct platform_device *pdev) int irq, ret; cmos_of_init(pdev); + cmos_wake_setup(&pdev->dev); if (RTC_IOMAPPED) resource = platform_get_resource(pdev, IORESOURCE_IO, 0); @@ -1479,7 +1484,7 @@ static int __init cmos_platform_probe(struct platform_device *pdev) if (ret) return ret; - cmos_wake_setup(&pdev->dev); + rtc_wake_setup(&pdev->dev); return 0; } From 45b96601a6ece7e232e005b715c2ef894fa34e64 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Tue, 18 Oct 2022 22:35:11 +0200 Subject: [PATCH 0502/4345] rtc: cmos: fix build on non-ACPI platforms [ Upstream commit db4e955ae333567dea02822624106c0b96a2f84f ] Now that rtc_wake_setup is called outside of cmos_wake_setup, it also need to be defined on non-ACPI platforms. Reported-by: kernel test robot Link: https://lore.kernel.org/r/20221018203512.2532407-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni Stable-dep-of: 83ebb7b3036d ("rtc: cmos: Disable ACPI RTC event on removal") Signed-off-by: Sasha Levin --- drivers/rtc/rtc-cmos.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 426e6a67cc38..ff556a93a397 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -1351,6 +1351,9 @@ static void cmos_check_acpi_rtc_status(struct device *dev, { } +static void rtc_wake_setup(struct device *dev) +{ +} #endif #ifdef CONFIG_PNP From 14ad1353c5154dc5d489a86af10d4e92340a1f47 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 9 Nov 2022 13:07:08 +0100 Subject: [PATCH 0503/4345] rtc: cmos: Call cmos_wake_setup() from cmos_do_probe() [ Upstream commit 508ccdfb86b21da37ad091003a4d4567709d5dfb ] Notice that cmos_wake_setup() is the only user of acpi_rtc_info and it can operate on the cmos_rtc variable directly, so it need not set the platform_data pointer before cmos_do_probe() is called. Instead, it can be called by cmos_do_probe() in the case when the platform_data pointer is not set to implement the default behavior (which is to use the FADT information as long as ACPI support is enabled). Modify the code accordingly. While at it, drop a comment that doesn't really match the code it is supposed to be describing. Signed-off-by: Rafael J. Wysocki Reviewed-by: Zhang Rui Tested-by: Zhang Rui Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/4803444.31r3eYUQgx@kreacher Signed-off-by: Alexandre Belloni Stable-dep-of: 83ebb7b3036d ("rtc: cmos: Disable ACPI RTC event on removal") Signed-off-by: Sasha Levin --- drivers/rtc/rtc-cmos.c | 47 ++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 25 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index ff556a93a397..c292af30d4fd 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -750,6 +750,8 @@ static irqreturn_t cmos_interrupt(int irq, void *p) return IRQ_NONE; } +static void cmos_wake_setup(struct device *dev); + #ifdef CONFIG_PNP #define INITSECTION @@ -833,19 +835,27 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) if (info->address_space) address_space = info->address_space; - if (info->rtc_day_alarm && info->rtc_day_alarm < 128) - cmos_rtc.day_alrm = info->rtc_day_alarm; - if (info->rtc_mon_alarm && info->rtc_mon_alarm < 128) - cmos_rtc.mon_alrm = info->rtc_mon_alarm; - if (info->rtc_century && info->rtc_century < 128) - cmos_rtc.century = info->rtc_century; + cmos_rtc.day_alrm = info->rtc_day_alarm; + cmos_rtc.mon_alrm = info->rtc_mon_alarm; + cmos_rtc.century = info->rtc_century; if (info->wake_on && info->wake_off) { cmos_rtc.wake_on = info->wake_on; cmos_rtc.wake_off = info->wake_off; } + } else { + cmos_wake_setup(dev); } + if (cmos_rtc.day_alrm >= 128) + cmos_rtc.day_alrm = 0; + + if (cmos_rtc.mon_alrm >= 128) + cmos_rtc.mon_alrm = 0; + + if (cmos_rtc.century >= 128) + cmos_rtc.century = 0; + cmos_rtc.dev = dev; dev_set_drvdata(dev, &cmos_rtc); @@ -1280,13 +1290,6 @@ static void use_acpi_alarm_quirks(void) static inline void use_acpi_alarm_quirks(void) { } #endif -/* Every ACPI platform has a mc146818 compatible "cmos rtc". Here we find - * its device node and pass extra config data. This helps its driver use - * capabilities that the now-obsolete mc146818 didn't have, and informs it - * that this board's RTC is wakeup-capable (per ACPI spec). - */ -static struct cmos_rtc_board_info acpi_rtc_info; - static void cmos_wake_setup(struct device *dev) { if (acpi_disabled) @@ -1294,26 +1297,23 @@ static void cmos_wake_setup(struct device *dev) use_acpi_alarm_quirks(); - acpi_rtc_info.wake_on = rtc_wake_on; - acpi_rtc_info.wake_off = rtc_wake_off; + cmos_rtc.wake_on = rtc_wake_on; + cmos_rtc.wake_off = rtc_wake_off; - /* workaround bug in some ACPI tables */ + /* ACPI tables bug workaround. */ if (acpi_gbl_FADT.month_alarm && !acpi_gbl_FADT.day_alarm) { dev_dbg(dev, "bogus FADT month_alarm (%d)\n", acpi_gbl_FADT.month_alarm); acpi_gbl_FADT.month_alarm = 0; } - acpi_rtc_info.rtc_day_alarm = acpi_gbl_FADT.day_alarm; - acpi_rtc_info.rtc_mon_alarm = acpi_gbl_FADT.month_alarm; - acpi_rtc_info.rtc_century = acpi_gbl_FADT.century; + cmos_rtc.day_alrm = acpi_gbl_FADT.day_alarm; + cmos_rtc.mon_alrm = acpi_gbl_FADT.month_alarm; + cmos_rtc.century = acpi_gbl_FADT.century; - /* NOTE: S4_RTC_WAKE is NOT currently useful to Linux */ if (acpi_gbl_FADT.flags & ACPI_FADT_S4_RTC_WAKE) dev_info(dev, "RTC can wake from S4\n"); - dev->platform_data = &acpi_rtc_info; - /* RTC always wakes from S1/S2/S3, and often S4/STD */ device_init_wakeup(dev, 1); } @@ -1364,8 +1364,6 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) { int irq, ret; - cmos_wake_setup(&pnp->dev); - if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0)) { irq = 0; #ifdef CONFIG_X86 @@ -1473,7 +1471,6 @@ static int __init cmos_platform_probe(struct platform_device *pdev) int irq, ret; cmos_of_init(pdev); - cmos_wake_setup(&pdev->dev); if (RTC_IOMAPPED) resource = platform_get_resource(pdev, IORESOURCE_IO, 0); From 462db582e8eb53c4925f45015e38637e2436e23e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 9 Nov 2022 13:09:07 +0100 Subject: [PATCH 0504/4345] rtc: cmos: Call rtc_wake_setup() from cmos_do_probe() [ Upstream commit 375bbba09692fe4c5218eddee8e312dd733fa846 ] To reduce code duplication, move the invocation of rtc_wake_setup() into cmos_do_probe() and simplify the callers of the latter. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Zhang Rui Tested-by: Zhang Rui Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/2143522.irdbgypaU6@kreacher Signed-off-by: Alexandre Belloni Stable-dep-of: 83ebb7b3036d ("rtc: cmos: Disable ACPI RTC event on removal") Signed-off-by: Sasha Levin --- drivers/rtc/rtc-cmos.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index c292af30d4fd..445089cad471 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -750,6 +750,7 @@ static irqreturn_t cmos_interrupt(int irq, void *p) return IRQ_NONE; } +static inline void rtc_wake_setup(struct device *dev); static void cmos_wake_setup(struct device *dev); #ifdef CONFIG_PNP @@ -943,6 +944,13 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) if (rtc_nvmem_register(cmos_rtc.rtc, &nvmem_cfg)) dev_err(dev, "nvmem registration failed\n"); + /* + * Everything has gone well so far, so by default register a handler for + * the ACPI RTC fixed event. + */ + if (!info) + rtc_wake_setup(dev); + dev_info(dev, "%s%s, %d bytes nvram%s\n", !is_valid_irq(rtc_irq) ? "no alarms" : cmos_rtc.mon_alrm ? "alarms up to one year" : @@ -1362,7 +1370,7 @@ static void rtc_wake_setup(struct device *dev) static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) { - int irq, ret; + int irq; if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0)) { irq = 0; @@ -1378,13 +1386,7 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) irq = pnp_irq(pnp, 0); } - ret = cmos_do_probe(&pnp->dev, pnp_get_resource(pnp, IORESOURCE_IO, 0), irq); - if (ret) - return ret; - - rtc_wake_setup(&pnp->dev); - - return 0; + return cmos_do_probe(&pnp->dev, pnp_get_resource(pnp, IORESOURCE_IO, 0), irq); } static void cmos_pnp_remove(struct pnp_dev *pnp) @@ -1468,7 +1470,7 @@ static inline void cmos_of_init(struct platform_device *pdev) {} static int __init cmos_platform_probe(struct platform_device *pdev) { struct resource *resource; - int irq, ret; + int irq; cmos_of_init(pdev); @@ -1480,13 +1482,7 @@ static int __init cmos_platform_probe(struct platform_device *pdev) if (irq < 0) irq = -1; - ret = cmos_do_probe(&pdev->dev, resource, irq); - if (ret) - return ret; - - rtc_wake_setup(&pdev->dev); - - return 0; + return cmos_do_probe(&pdev->dev, resource, irq); } static int cmos_platform_remove(struct platform_device *pdev) From 9f9923baa2916732939cb66c6317769cc2a91b8f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 9 Nov 2022 13:09:32 +0100 Subject: [PATCH 0505/4345] rtc: cmos: Eliminate forward declarations of some functions [ Upstream commit dca4d3b71c8a09a16951add656711fbd6f5bfbb0 ] Reorder the ACPI-related code before cmos_do_probe() so as to eliminate excessive forward declarations of some functions. While at it, for consistency, add the inline modifier to the definitions of empty stub static funtions and remove it from the corresponding definitions of functions with non-empty bodies. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Zhang Rui Tested-by: Zhang Rui Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/13157911.uLZWGnKmhe@kreacher Signed-off-by: Alexandre Belloni Stable-dep-of: 83ebb7b3036d ("rtc: cmos: Disable ACPI RTC event on removal") Signed-off-by: Sasha Levin --- drivers/rtc/rtc-cmos.c | 304 ++++++++++++++++++++--------------------- 1 file changed, 149 insertions(+), 155 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 445089cad471..541cdae587eb 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -750,8 +750,155 @@ static irqreturn_t cmos_interrupt(int irq, void *p) return IRQ_NONE; } -static inline void rtc_wake_setup(struct device *dev); -static void cmos_wake_setup(struct device *dev); +#ifdef CONFIG_ACPI + +#include + +static u32 rtc_handler(void *context) +{ + struct device *dev = context; + struct cmos_rtc *cmos = dev_get_drvdata(dev); + unsigned char rtc_control = 0; + unsigned char rtc_intr; + unsigned long flags; + + + /* + * Always update rtc irq when ACPI is used as RTC Alarm. + * Or else, ACPI SCI is enabled during suspend/resume only, + * update rtc irq in that case. + */ + if (cmos_use_acpi_alarm()) + cmos_interrupt(0, (void *)cmos->rtc); + else { + /* Fix me: can we use cmos_interrupt() here as well? */ + spin_lock_irqsave(&rtc_lock, flags); + if (cmos_rtc.suspend_ctrl) + rtc_control = CMOS_READ(RTC_CONTROL); + if (rtc_control & RTC_AIE) { + cmos_rtc.suspend_ctrl &= ~RTC_AIE; + CMOS_WRITE(rtc_control, RTC_CONTROL); + rtc_intr = CMOS_READ(RTC_INTR_FLAGS); + rtc_update_irq(cmos->rtc, 1, rtc_intr); + } + spin_unlock_irqrestore(&rtc_lock, flags); + } + + pm_wakeup_hard_event(dev); + acpi_clear_event(ACPI_EVENT_RTC); + acpi_disable_event(ACPI_EVENT_RTC, 0); + return ACPI_INTERRUPT_HANDLED; +} + +static void rtc_wake_setup(struct device *dev) +{ + if (acpi_disabled) + return; + + acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, dev); + /* + * After the RTC handler is installed, the Fixed_RTC event should + * be disabled. Only when the RTC alarm is set will it be enabled. + */ + acpi_clear_event(ACPI_EVENT_RTC); + acpi_disable_event(ACPI_EVENT_RTC, 0); +} + +static void rtc_wake_on(struct device *dev) +{ + acpi_clear_event(ACPI_EVENT_RTC); + acpi_enable_event(ACPI_EVENT_RTC, 0); +} + +static void rtc_wake_off(struct device *dev) +{ + acpi_disable_event(ACPI_EVENT_RTC, 0); +} + +#ifdef CONFIG_X86 +/* Enable use_acpi_alarm mode for Intel platforms no earlier than 2015 */ +static void use_acpi_alarm_quirks(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; + + if (!is_hpet_enabled()) + return; + + if (dmi_get_bios_year() < 2015) + return; + + use_acpi_alarm = true; +} +#else +static inline void use_acpi_alarm_quirks(void) { } +#endif + +static void cmos_wake_setup(struct device *dev) +{ + if (acpi_disabled) + return; + + use_acpi_alarm_quirks(); + + cmos_rtc.wake_on = rtc_wake_on; + cmos_rtc.wake_off = rtc_wake_off; + + /* ACPI tables bug workaround. */ + if (acpi_gbl_FADT.month_alarm && !acpi_gbl_FADT.day_alarm) { + dev_dbg(dev, "bogus FADT month_alarm (%d)\n", + acpi_gbl_FADT.month_alarm); + acpi_gbl_FADT.month_alarm = 0; + } + + cmos_rtc.day_alrm = acpi_gbl_FADT.day_alarm; + cmos_rtc.mon_alrm = acpi_gbl_FADT.month_alarm; + cmos_rtc.century = acpi_gbl_FADT.century; + + if (acpi_gbl_FADT.flags & ACPI_FADT_S4_RTC_WAKE) + dev_info(dev, "RTC can wake from S4\n"); + + /* RTC always wakes from S1/S2/S3, and often S4/STD */ + device_init_wakeup(dev, 1); +} + +static void cmos_check_acpi_rtc_status(struct device *dev, + unsigned char *rtc_control) +{ + struct cmos_rtc *cmos = dev_get_drvdata(dev); + acpi_event_status rtc_status; + acpi_status status; + + if (acpi_gbl_FADT.flags & ACPI_FADT_FIXED_RTC) + return; + + status = acpi_get_event_status(ACPI_EVENT_RTC, &rtc_status); + if (ACPI_FAILURE(status)) { + dev_err(dev, "Could not get RTC status\n"); + } else if (rtc_status & ACPI_EVENT_FLAG_SET) { + unsigned char mask; + *rtc_control &= ~RTC_AIE; + CMOS_WRITE(*rtc_control, RTC_CONTROL); + mask = CMOS_READ(RTC_INTR_FLAGS); + rtc_update_irq(cmos->rtc, 1, mask); + } +} + +#else /* !CONFIG_ACPI */ + +static inline void rtc_wake_setup(struct device *dev) +{ +} + +static inline void cmos_wake_setup(struct device *dev) +{ +} + +static inline void cmos_check_acpi_rtc_status(struct device *dev, + unsigned char *rtc_control) +{ +} +#endif /* CONFIG_ACPI */ #ifdef CONFIG_PNP #define INITSECTION @@ -1145,9 +1292,6 @@ static void cmos_check_wkalrm(struct device *dev) } } -static void cmos_check_acpi_rtc_status(struct device *dev, - unsigned char *rtc_control); - static int __maybe_unused cmos_resume(struct device *dev) { struct cmos_rtc *cmos = dev_get_drvdata(dev); @@ -1214,156 +1358,6 @@ static SIMPLE_DEV_PM_OPS(cmos_pm_ops, cmos_suspend, cmos_resume); * predate even PNPBIOS should set up platform_bus devices. */ -#ifdef CONFIG_ACPI - -#include - -static u32 rtc_handler(void *context) -{ - struct device *dev = context; - struct cmos_rtc *cmos = dev_get_drvdata(dev); - unsigned char rtc_control = 0; - unsigned char rtc_intr; - unsigned long flags; - - - /* - * Always update rtc irq when ACPI is used as RTC Alarm. - * Or else, ACPI SCI is enabled during suspend/resume only, - * update rtc irq in that case. - */ - if (cmos_use_acpi_alarm()) - cmos_interrupt(0, (void *)cmos->rtc); - else { - /* Fix me: can we use cmos_interrupt() here as well? */ - spin_lock_irqsave(&rtc_lock, flags); - if (cmos_rtc.suspend_ctrl) - rtc_control = CMOS_READ(RTC_CONTROL); - if (rtc_control & RTC_AIE) { - cmos_rtc.suspend_ctrl &= ~RTC_AIE; - CMOS_WRITE(rtc_control, RTC_CONTROL); - rtc_intr = CMOS_READ(RTC_INTR_FLAGS); - rtc_update_irq(cmos->rtc, 1, rtc_intr); - } - spin_unlock_irqrestore(&rtc_lock, flags); - } - - pm_wakeup_hard_event(dev); - acpi_clear_event(ACPI_EVENT_RTC); - acpi_disable_event(ACPI_EVENT_RTC, 0); - return ACPI_INTERRUPT_HANDLED; -} - -static inline void rtc_wake_setup(struct device *dev) -{ - if (acpi_disabled) - return; - - acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, dev); - /* - * After the RTC handler is installed, the Fixed_RTC event should - * be disabled. Only when the RTC alarm is set will it be enabled. - */ - acpi_clear_event(ACPI_EVENT_RTC); - acpi_disable_event(ACPI_EVENT_RTC, 0); -} - -static void rtc_wake_on(struct device *dev) -{ - acpi_clear_event(ACPI_EVENT_RTC); - acpi_enable_event(ACPI_EVENT_RTC, 0); -} - -static void rtc_wake_off(struct device *dev) -{ - acpi_disable_event(ACPI_EVENT_RTC, 0); -} - -#ifdef CONFIG_X86 -/* Enable use_acpi_alarm mode for Intel platforms no earlier than 2015 */ -static void use_acpi_alarm_quirks(void) -{ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) - return; - - if (!is_hpet_enabled()) - return; - - if (dmi_get_bios_year() < 2015) - return; - - use_acpi_alarm = true; -} -#else -static inline void use_acpi_alarm_quirks(void) { } -#endif - -static void cmos_wake_setup(struct device *dev) -{ - if (acpi_disabled) - return; - - use_acpi_alarm_quirks(); - - cmos_rtc.wake_on = rtc_wake_on; - cmos_rtc.wake_off = rtc_wake_off; - - /* ACPI tables bug workaround. */ - if (acpi_gbl_FADT.month_alarm && !acpi_gbl_FADT.day_alarm) { - dev_dbg(dev, "bogus FADT month_alarm (%d)\n", - acpi_gbl_FADT.month_alarm); - acpi_gbl_FADT.month_alarm = 0; - } - - cmos_rtc.day_alrm = acpi_gbl_FADT.day_alarm; - cmos_rtc.mon_alrm = acpi_gbl_FADT.month_alarm; - cmos_rtc.century = acpi_gbl_FADT.century; - - if (acpi_gbl_FADT.flags & ACPI_FADT_S4_RTC_WAKE) - dev_info(dev, "RTC can wake from S4\n"); - - /* RTC always wakes from S1/S2/S3, and often S4/STD */ - device_init_wakeup(dev, 1); -} - -static void cmos_check_acpi_rtc_status(struct device *dev, - unsigned char *rtc_control) -{ - struct cmos_rtc *cmos = dev_get_drvdata(dev); - acpi_event_status rtc_status; - acpi_status status; - - if (acpi_gbl_FADT.flags & ACPI_FADT_FIXED_RTC) - return; - - status = acpi_get_event_status(ACPI_EVENT_RTC, &rtc_status); - if (ACPI_FAILURE(status)) { - dev_err(dev, "Could not get RTC status\n"); - } else if (rtc_status & ACPI_EVENT_FLAG_SET) { - unsigned char mask; - *rtc_control &= ~RTC_AIE; - CMOS_WRITE(*rtc_control, RTC_CONTROL); - mask = CMOS_READ(RTC_INTR_FLAGS); - rtc_update_irq(cmos->rtc, 1, mask); - } -} - -#else - -static void cmos_wake_setup(struct device *dev) -{ -} - -static void cmos_check_acpi_rtc_status(struct device *dev, - unsigned char *rtc_control) -{ -} - -static void rtc_wake_setup(struct device *dev) -{ -} -#endif - #ifdef CONFIG_PNP #include From ca8cb20c2254a3f56fad3635cb6e51e671df3327 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 9 Nov 2022 13:12:00 +0100 Subject: [PATCH 0506/4345] rtc: cmos: Rename ACPI-related functions [ Upstream commit d13e9ad9f5146f066a5c5a1cc993d09e4fb21ead ] The names of rtc_wake_setup() and cmos_wake_setup() don't indicate that these functions are ACPI-related, which is the case, and the former doesn't really reflect the role of the function. Rename them to acpi_rtc_event_setup() and acpi_cmos_wake_setup(), respectively, to address this shortcoming. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Zhang Rui Tested-by: Zhang Rui Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/3225614.44csPzL39Z@kreacher Signed-off-by: Alexandre Belloni Stable-dep-of: 83ebb7b3036d ("rtc: cmos: Disable ACPI RTC event on removal") Signed-off-by: Sasha Levin --- drivers/rtc/rtc-cmos.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 541cdae587eb..dd05c12dada8 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -790,7 +790,7 @@ static u32 rtc_handler(void *context) return ACPI_INTERRUPT_HANDLED; } -static void rtc_wake_setup(struct device *dev) +static void acpi_rtc_event_setup(struct device *dev) { if (acpi_disabled) return; @@ -834,7 +834,7 @@ static void use_acpi_alarm_quirks(void) static inline void use_acpi_alarm_quirks(void) { } #endif -static void cmos_wake_setup(struct device *dev) +static void acpi_cmos_wake_setup(struct device *dev) { if (acpi_disabled) return; @@ -886,11 +886,11 @@ static void cmos_check_acpi_rtc_status(struct device *dev, #else /* !CONFIG_ACPI */ -static inline void rtc_wake_setup(struct device *dev) +static inline void acpi_rtc_event_setup(struct device *dev) { } -static inline void cmos_wake_setup(struct device *dev) +static inline void acpi_cmos_wake_setup(struct device *dev) { } @@ -992,7 +992,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) cmos_rtc.wake_off = info->wake_off; } } else { - cmos_wake_setup(dev); + acpi_cmos_wake_setup(dev); } if (cmos_rtc.day_alrm >= 128) @@ -1096,7 +1096,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) * the ACPI RTC fixed event. */ if (!info) - rtc_wake_setup(dev); + acpi_rtc_event_setup(dev); dev_info(dev, "%s%s, %d bytes nvram%s\n", !is_valid_irq(rtc_irq) ? "no alarms" : From f0c36ea4248a0133451dec8b5ad571cf0972ff98 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 9 Nov 2022 13:15:36 +0100 Subject: [PATCH 0507/4345] rtc: cmos: Disable ACPI RTC event on removal [ Upstream commit 83ebb7b3036d151ee39a4a752018665648fc3bd4 ] Make cmos_do_remove() drop the ACPI RTC fixed event handler so as to prevent it from operating on stale data in case the event triggers after driver removal. Fixes: 311ee9c151ad ("rtc: cmos: allow using ACPI for RTC alarm instead of HPET") Signed-off-by: Rafael J. Wysocki Reviewed-by: Zhang Rui Tested-by: Zhang Rui Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/2224609.iZASKD2KPV@kreacher Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-cmos.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index dd05c12dada8..7f560937bf7c 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -804,6 +804,14 @@ static void acpi_rtc_event_setup(struct device *dev) acpi_disable_event(ACPI_EVENT_RTC, 0); } +static void acpi_rtc_event_cleanup(void) +{ + if (acpi_disabled) + return; + + acpi_remove_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler); +} + static void rtc_wake_on(struct device *dev) { acpi_clear_event(ACPI_EVENT_RTC); @@ -890,6 +898,10 @@ static inline void acpi_rtc_event_setup(struct device *dev) { } +static inline void acpi_rtc_event_cleanup(void) +{ +} + static inline void acpi_cmos_wake_setup(struct device *dev) { } @@ -1143,6 +1155,9 @@ static void cmos_do_remove(struct device *dev) hpet_unregister_irq_handler(cmos_interrupt); } + if (!dev_get_platdata(dev)) + acpi_rtc_event_cleanup(); + cmos->rtc = NULL; ports = cmos->iomem; From aaed333e2237da8a391cdc0e675da1993347c4e4 Mon Sep 17 00:00:00 2001 From: Stefan Eichenberger Date: Sun, 6 Nov 2022 12:59:15 +0100 Subject: [PATCH 0508/4345] rtc: snvs: Allow a time difference on clock register read [ Upstream commit 0462681e207ccc44778a77b3297af728b1cf5b9f ] On an iMX6ULL the following message appears when a wakealarm is set: echo 0 > /sys/class/rtc/rtc1/wakealarm rtc rtc1: Timeout trying to get valid LPSRT Counter read This does not always happen but is reproducible quite often (7 out of 10 times). The problem appears because the iMX6ULL is not able to read the registers within one 32kHz clock cycle which is the base clock of the RTC. Therefore, this patch allows a difference of up to 320 cycles (10ms). 10ms was chosen to be big enough even on systems with less cpu power (e.g. iMX6ULL). According to the reference manual a difference is fine: - If the two consecutive reads are similar, the value is correct. The values have to be similar, not equal. Fixes: cd7f3a249dbe ("rtc: snvs: Add timeouts to avoid kernel lockups") Reviewed-by: Francesco Dolcini Signed-off-by: Stefan Eichenberger Signed-off-by: Francesco Dolcini Link: https://lore.kernel.org/r/20221106115915.7930-1-francesco@dolcini.it Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-snvs.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-snvs.c b/drivers/rtc/rtc-snvs.c index 0263d996b8a8..cc7f6c4216bc 100644 --- a/drivers/rtc/rtc-snvs.c +++ b/drivers/rtc/rtc-snvs.c @@ -32,6 +32,14 @@ #define SNVS_LPPGDR_INIT 0x41736166 #define CNTR_TO_SECS_SH 15 +/* The maximum RTC clock cycles that are allowed to pass between two + * consecutive clock counter register reads. If the values are corrupted a + * bigger difference is expected. The RTC frequency is 32kHz. With 320 cycles + * we end at 10ms which should be enough for most cases. If it once takes + * longer than expected we do a retry. + */ +#define MAX_RTC_READ_DIFF_CYCLES 320 + struct snvs_rtc_data { struct rtc_device *rtc; struct regmap *regmap; @@ -56,6 +64,7 @@ static u64 rtc_read_lpsrt(struct snvs_rtc_data *data) static u32 rtc_read_lp_counter(struct snvs_rtc_data *data) { u64 read1, read2; + s64 diff; unsigned int timeout = 100; /* As expected, the registers might update between the read of the LSB @@ -66,7 +75,8 @@ static u32 rtc_read_lp_counter(struct snvs_rtc_data *data) do { read2 = read1; read1 = rtc_read_lpsrt(data); - } while (read1 != read2 && --timeout); + diff = read1 - read2; + } while (((diff < 0) || (diff > MAX_RTC_READ_DIFF_CYCLES)) && --timeout); if (!timeout) dev_err(&data->rtc->dev, "Timeout trying to get valid LPSRT Counter read\n"); @@ -78,13 +88,15 @@ static u32 rtc_read_lp_counter(struct snvs_rtc_data *data) static int rtc_read_lp_counter_lsb(struct snvs_rtc_data *data, u32 *lsb) { u32 count1, count2; + s32 diff; unsigned int timeout = 100; regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &count1); do { count2 = count1; regmap_read(data->regmap, data->offset + SNVS_LPSRTCLR, &count1); - } while (count1 != count2 && --timeout); + diff = count1 - count2; + } while (((diff < 0) || (diff > MAX_RTC_READ_DIFF_CYCLES)) && --timeout); if (!timeout) { dev_err(&data->rtc->dev, "Timeout trying to get valid LPSRT Counter read\n"); return -ETIMEDOUT; From 3929576f10ea67743bd2a44ed628c2a25bdbb559 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Wed, 21 Sep 2022 09:41:41 +0200 Subject: [PATCH 0509/4345] rtc: pcf85063: Fix reading alarm [ Upstream commit a6ceee26fd5ed9b5bd37322b1ca88e4548cee4a3 ] If the alarms are disabled the topmost bit (AEN_*) is set in the alarm registers. This is also interpreted in BCD number leading to this warning: rtc rtc0: invalid alarm value: 2022-09-21T80:80:80 Fix this by masking alarm enabling and reserved bits. Fixes: 05cb3a56ee8c ("rtc: pcf85063: add alarm support") Signed-off-by: Alexander Stein Link: https://lore.kernel.org/r/20220921074141.3903104-1-alexander.stein@ew.tq-group.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-pcf85063.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c index 62684ca3a665..d739b0c965aa 100644 --- a/drivers/rtc/rtc-pcf85063.c +++ b/drivers/rtc/rtc-pcf85063.c @@ -167,10 +167,10 @@ static int pcf85063_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) if (ret) return ret; - alrm->time.tm_sec = bcd2bin(buf[0]); - alrm->time.tm_min = bcd2bin(buf[1]); - alrm->time.tm_hour = bcd2bin(buf[2]); - alrm->time.tm_mday = bcd2bin(buf[3]); + alrm->time.tm_sec = bcd2bin(buf[0] & 0x7f); + alrm->time.tm_min = bcd2bin(buf[1] & 0x7f); + alrm->time.tm_hour = bcd2bin(buf[2] & 0x3f); + alrm->time.tm_mday = bcd2bin(buf[3] & 0x3f); ret = regmap_read(pcf85063->regmap, PCF85063_REG_CTRL2, &val); if (ret) From 03f51c72997559e73b327608f0cccfded715c9a0 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 18 Nov 2022 17:36:04 +0800 Subject: [PATCH 0510/4345] iommu/amd: Fix pci device refcount leak in ppr_notifier() [ Upstream commit 6cf0981c2233f97d56938d9d61845383d6eb227c ] As comment of pci_get_domain_bus_and_slot() says, it returns a pci device with refcount increment, when finish using it, the caller must decrement the reference count by calling pci_dev_put(). So call it before returning from ppr_notifier() to avoid refcount leak. Fixes: daae2d25a477 ("iommu/amd: Don't copy GCR3 table root pointer") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221118093604.216371-1-yangyingliang@huawei.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/amd/iommu_v2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c index fb61bdca4c2c..16776e3c6eab 100644 --- a/drivers/iommu/amd/iommu_v2.c +++ b/drivers/iommu/amd/iommu_v2.c @@ -587,6 +587,7 @@ out_drop_state: put_device_state(dev_state); out: + pci_dev_put(pdev); return ret; } From 0d240ac0e4c35d3f64fc782c11433138c1bd016e Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Mon, 21 Nov 2022 08:20:22 +0000 Subject: [PATCH 0511/4345] iommu/fsl_pamu: Fix resource leak in fsl_pamu_probe() [ Upstream commit 73f5fc5f884ad0c5f7d57f66303af64f9f002526 ] The fsl_pamu_probe() returns directly when create_csd() failed, leaving irq and memories unreleased. Fix by jumping to error if create_csd() returns error. Fixes: 695093e38c3e ("iommu/fsl: Freescale PAMU driver and iommu implementation.") Signed-off-by: Yuan Can Link: https://lore.kernel.org/r/20221121082022.19091-1-yuancan@huawei.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/fsl_pamu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c index b9a974d97831..25689bdf812e 100644 --- a/drivers/iommu/fsl_pamu.c +++ b/drivers/iommu/fsl_pamu.c @@ -1122,7 +1122,7 @@ static int fsl_pamu_probe(struct platform_device *pdev) ret = create_csd(ppaact_phys, mem_size, csd_port_id); if (ret) { dev_err(dev, "could not create coherence subdomain\n"); - return ret; + goto error; } } From 2ac0a7059b7bcbed35bfffa34a82c9a9e99638ef Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 4 Nov 2022 11:25:51 +0800 Subject: [PATCH 0512/4345] macintosh: fix possible memory leak in macio_add_one_device() [ Upstream commit 5ca86eae55a2f006e6c1edd2029b2cacb6979515 ] Afer commit 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array"), the name of device is allocated dynamically. It needs to be freed when of_device_register() fails. Call put_device() to give up the reference that's taken in device_initialize(), so that it can be freed in kobject_cleanup() when the refcount hits 0. macio device is freed in macio_release_dev(), so the kfree() can be removed. Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array") Signed-off-by: Yang Yingliang Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221104032551.1075335-1-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/macintosh/macio_asic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 49af60bdac92..7db2e23a5ac8 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -425,7 +425,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, if (of_device_register(&dev->ofdev) != 0) { printk(KERN_DEBUG"macio: device registration error for %s!\n", dev_name(&dev->ofdev.dev)); - kfree(dev); + put_device(&dev->ofdev.dev); return NULL; } From 7fded04fbbb8fd6d2cad45c079909c6625969d6a Mon Sep 17 00:00:00 2001 From: Xie Shaowen Date: Tue, 2 Aug 2022 15:41:48 +0800 Subject: [PATCH 0513/4345] macintosh/macio-adb: check the return value of ioremap() [ Upstream commit dbaa3105736d4d73063ea0a3b01cd7fafce924e6 ] The function ioremap() in macio_init() can fail, so its return value should be checked. Fixes: 36874579dbf4c ("[PATCH] powerpc: macio-adb build fix") Reported-by: Hacash Robot Signed-off-by: Xie Shaowen Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220802074148.3213659-1-studentxswpy@163.com Signed-off-by: Sasha Levin --- drivers/macintosh/macio-adb.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/macintosh/macio-adb.c b/drivers/macintosh/macio-adb.c index d4759db002c6..defe65f51fa2 100644 --- a/drivers/macintosh/macio-adb.c +++ b/drivers/macintosh/macio-adb.c @@ -106,6 +106,10 @@ int macio_init(void) return -ENXIO; } adb = ioremap(r.start, sizeof(struct adb_regs)); + if (!adb) { + of_node_put(adbs); + return -ENOMEM; + } out_8(&adb->ctrl.r, 0); out_8(&adb->intr.r, 0); From 40b4be399e0db7073dec5a0de5ca9994f7e31e58 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 29 Jan 2022 08:16:04 +0100 Subject: [PATCH 0514/4345] powerpc/52xx: Fix a resource leak in an error handling path [ Upstream commit 5836947613ef33d311b4eff6a32d019580a214f5 ] The error handling path of mpc52xx_lpbfifo_probe() has a request_irq() that is not balanced by a corresponding free_irq(). Add the missing call, as already done in the remove function. Fixes: 3c9059d79f5e ("powerpc/5200: add LocalPlus bus FIFO device driver") Signed-off-by: Christophe JAILLET Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/dec1496d46ccd5311d0f6e9f9ca4238be11bf6a6.1643440531.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c index 05e19470d523..22e264bd3ed2 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c @@ -530,6 +530,7 @@ static int mpc52xx_lpbfifo_probe(struct platform_device *op) err_bcom_rx_irq: bcom_gen_bd_rx_release(lpbfifo.bcom_rx_task); err_bcom_rx: + free_irq(lpbfifo.irq, &lpbfifo); err_irq: iounmap(lpbfifo.regs); lpbfifo.regs = NULL; From 81c8bbf5b2b5f0c8030fff1716c00849cda8571a Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Sun, 5 Jun 2022 10:00:38 +0400 Subject: [PATCH 0515/4345] cxl: Fix refcount leak in cxl_calc_capp_routing [ Upstream commit 1d09697ff22908ae487fc8c4fbde1811732be523 ] of_get_next_parent() returns a node pointer with refcount incremented, we should use of_node_put() on it when not need anymore. This function only calls of_node_put() in normal path, missing it in the error path. Add missing of_node_put() to avoid refcount leak. Fixes: f24be42aab37 ("cxl: Add psl9 specific code") Signed-off-by: Miaoqian Lin Acked-by: Andrew Donnellan Acked-by: Frederic Barrat Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220605060038.62217-1-linmq006@gmail.com Signed-off-by: Sasha Levin --- drivers/misc/cxl/pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 0ac3f4cb88ac..d183836d80e3 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -387,6 +387,7 @@ int cxl_calc_capp_routing(struct pci_dev *dev, u64 *chipid, rc = get_phb_index(np, phb_index); if (rc) { pr_err("cxl: invalid phb index\n"); + of_node_put(np); return rc; } From 76957b6aed995ab411aa1b05802c23d785fb803b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 23 Dec 2020 09:38:48 +0000 Subject: [PATCH 0516/4345] powerpc/xmon: Enable breakpoints on 8xx [ Upstream commit 30662217885d7341161924acf1665924d7d37d64 ] Since commit 4ad8622dc548 ("powerpc/8xx: Implement hw_breakpoint"), 8xx has breakpoints so there is no reason to opt breakpoint logic out of xmon for the 8xx. Fixes: 4ad8622dc548 ("powerpc/8xx: Implement hw_breakpoint") Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/b0607f1113d1558e73476bb06db0ee16d31a6e5b.1608716197.git.christophe.leroy@csgroup.eu Stable-dep-of: 1c4a4a4c8410 ("powerpc/xmon: Fix -Wswitch-unreachable warning in bpt_cmds") Signed-off-by: Sasha Levin --- arch/powerpc/xmon/xmon.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 5559edf36756..c6a36b4045e8 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1383,7 +1383,6 @@ static long check_bp_loc(unsigned long addr) return 1; } -#ifndef CONFIG_PPC_8xx static int find_free_data_bpt(void) { int i; @@ -1395,7 +1394,6 @@ static int find_free_data_bpt(void) printf("Couldn't find free breakpoint register\n"); return -1; } -#endif static void print_data_bpts(void) { @@ -1435,7 +1433,6 @@ bpt_cmds(void) cmd = inchar(); switch (cmd) { -#ifndef CONFIG_PPC_8xx static const char badaddr[] = "Only kernel addresses are permitted for breakpoints\n"; int mode; case 'd': /* bd - hardware data breakpoint */ @@ -1497,7 +1494,6 @@ bpt_cmds(void) force_enable_xmon(); } break; -#endif case 'c': if (!scanhex(&a)) { From f0bd6504e580644d65fb8075c901e700962f16de Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 16 Sep 2022 15:15:04 +0100 Subject: [PATCH 0517/4345] powerpc/xmon: Fix -Wswitch-unreachable warning in bpt_cmds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1c4a4a4c8410be4a231a58b23e7a30923ff954ac ] When building with automatic stack variable initialization, GCC 12 complains about variables defined outside of switch case statements. Move the variable into the case that uses it, which silences the warning: arch/powerpc/xmon/xmon.c: In function ‘bpt_cmds’: arch/powerpc/xmon/xmon.c:1529:13: warning: statement will never be executed [-Wswitch-unreachable] 1529 | int mode; | ^~~~ Fixes: 09b6c1129f89 ("powerpc/xmon: Fix compile error with PPC_8xx=y") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/YySE6FHiOcbWWR+9@work Signed-off-by: Sasha Levin --- arch/powerpc/xmon/xmon.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index c6a36b4045e8..2872b66d9fec 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1433,9 +1433,9 @@ bpt_cmds(void) cmd = inchar(); switch (cmd) { - static const char badaddr[] = "Only kernel addresses are permitted for breakpoints\n"; - int mode; - case 'd': /* bd - hardware data breakpoint */ + case 'd': { /* bd - hardware data breakpoint */ + static const char badaddr[] = "Only kernel addresses are permitted for breakpoints\n"; + int mode; if (xmon_is_ro) { printf(xmon_ro_msg); break; @@ -1468,6 +1468,7 @@ bpt_cmds(void) force_enable_xmon(); break; + } case 'i': /* bi - hardware instr breakpoint */ if (xmon_is_ro) { From 195cb98861dc7716060def6b42a2f2b34232aad1 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 17 Oct 2022 11:23:33 +0800 Subject: [PATCH 0518/4345] powerpc/xive: add missing iounmap() in error path in xive_spapr_populate_irq_data() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8b49670f3bb3f10cd4d5a6dca17f5a31b173ecdc ] If remapping 'data->trig_page' fails, the 'data->eoi_mmio' need be unmapped before returning from xive_spapr_populate_irq_data(). Fixes: eac1e731b59e ("powerpc/xive: guest exploitation of the XIVE interrupt controller") Signed-off-by: Yang Yingliang Reviewed-by: Cédric Le Goater Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221017032333.1852406-1-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- arch/powerpc/sysdev/xive/spapr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index 38e8b9896174..53cf14349d5e 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -425,6 +425,7 @@ static int xive_spapr_populate_irq_data(u32 hw_irq, struct xive_irq_data *data) data->trig_mmio = ioremap(data->trig_page, 1u << data->esb_shift); if (!data->trig_mmio) { + iounmap(data->eoi_mmio); pr_err("Failed to map trigger page for irq 0x%x\n", hw_irq); return -ENOMEM; } From e2155129599f96d29005721803ecb35bbf6d1ceb Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 31 Mar 2021 22:38:02 +0900 Subject: [PATCH 0519/4345] kbuild: remove unneeded mkdir for external modules_install [ Upstream commit 4b97ec0e9cfd5995f41b9726c88566a31f4625cc ] scripts/Makefile.modinst creates directories as needed. Signed-off-by: Masahiro Yamada Stable-dep-of: c7b98de745cf ("phy: qcom-qmp-combo: fix runtime suspend") Signed-off-by: Sasha Levin --- Makefile | 2 -- 1 file changed, 2 deletions(-) diff --git a/Makefile b/Makefile index 33422c7d149e..e1279904ca0e 100644 --- a/Makefile +++ b/Makefile @@ -1746,10 +1746,8 @@ $(MODORDER): descend PHONY += modules_install modules_install: _emodinst_ _emodinst_post -install-dir := $(if $(INSTALL_MOD_DIR),$(INSTALL_MOD_DIR),extra) PHONY += _emodinst_ _emodinst_: - $(Q)mkdir -p $(MODLIB)/$(install-dir) $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modinst PHONY += _emodinst_post From e3bdda22b49e7a3cba2faa59377f5d39398c0b66 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 31 Mar 2021 22:38:03 +0900 Subject: [PATCH 0520/4345] kbuild: unify modules(_install) for in-tree and external modules [ Upstream commit 3e3005df73b535cb849cf4ec8075d6aa3c460f68 ] If you attempt to build or install modules ('make modules(_install)' with CONFIG_MODULES disabled, you will get a clear error message, but nothing for external module builds. Factor out the modules and modules_install rules into the common part, so you will get the same error message when you try to build external modules with CONFIG_MODULES=n. Signed-off-by: Masahiro Yamada Stable-dep-of: c7b98de745cf ("phy: qcom-qmp-combo: fix runtime suspend") Signed-off-by: Sasha Levin --- Makefile | 85 ++++++++++++++++++++++++-------------------------------- 1 file changed, 36 insertions(+), 49 deletions(-) diff --git a/Makefile b/Makefile index e1279904ca0e..69c9123bc96d 100644 --- a/Makefile +++ b/Makefile @@ -1425,7 +1425,6 @@ endif PHONY += modules modules: $(if $(KBUILD_BUILTIN),vmlinux) modules_check modules_prepare - $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost PHONY += modules_check modules_check: modules.order @@ -1443,12 +1442,9 @@ PHONY += modules_prepare modules_prepare: prepare $(Q)$(MAKE) $(build)=scripts scripts/module.lds -# Target to install modules -PHONY += modules_install -modules_install: _modinst_ _modinst_post - -PHONY += _modinst_ -_modinst_: +modules_install: __modinst_pre +PHONY += __modinst_pre +__modinst_pre: @rm -rf $(MODLIB)/kernel @rm -f $(MODLIB)/source @mkdir -p $(MODLIB)/kernel @@ -1460,14 +1456,6 @@ _modinst_: @sed 's:^:kernel/:' modules.order > $(MODLIB)/modules.order @cp -f modules.builtin $(MODLIB)/ @cp -f $(objtree)/modules.builtin.modinfo $(MODLIB)/ - $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modinst - -# This depmod is only for convenience to give the initial -# boot a modules.dep even before / is mounted read-write. However the -# boot script depmod is the master version. -PHONY += _modinst_post -_modinst_post: _modinst_ - $(call cmd,depmod) ifeq ($(CONFIG_MODULE_SIG), y) PHONY += modules_sign @@ -1475,20 +1463,6 @@ modules_sign: $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modsign endif -else # CONFIG_MODULES - -# Modules not configured -# --------------------------------------------------------------------------- - -PHONY += modules modules_install -modules modules_install: - @echo >&2 - @echo >&2 "The present kernel configuration has modules disabled." - @echo >&2 "Type 'make config' and enable loadable module support." - @echo >&2 "Then build a kernel with module support enabled." - @echo >&2 - @exit 1 - endif # CONFIG_MODULES ### @@ -1736,24 +1710,9 @@ KBUILD_BUILTIN := KBUILD_MODULES := 1 build-dirs := $(KBUILD_EXTMOD) -PHONY += modules -modules: $(MODORDER) - $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost - $(MODORDER): descend @: -PHONY += modules_install -modules_install: _emodinst_ _emodinst_post - -PHONY += _emodinst_ -_emodinst_: - $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modinst - -PHONY += _emodinst_post -_emodinst_post: _emodinst_ - $(call cmd,depmod) - compile_commands.json: $(extmod-prefix)compile_commands.json PHONY += compile_commands.json @@ -1776,6 +1735,39 @@ PHONY += prepare modules_prepare endif # KBUILD_EXTMOD +# --------------------------------------------------------------------------- +# Modules + +PHONY += modules modules_install + +ifdef CONFIG_MODULES + +modules: $(MODORDER) + $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost + +quiet_cmd_depmod = DEPMOD $(KERNELRELEASE) + cmd_depmod = $(CONFIG_SHELL) $(srctree)/scripts/depmod.sh $(DEPMOD) \ + $(KERNELRELEASE) + +modules_install: + $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modinst + $(call cmd,depmod) + +else # CONFIG_MODULES + +# Modules not configured +# --------------------------------------------------------------------------- + +modules modules_install: + @echo >&2 '***' + @echo >&2 '*** The present kernel configuration has modules disabled.' + @echo >&2 '*** To use the module feature, please run "make menuconfig" etc.' + @echo >&2 '*** to enable CONFIG_MODULES.' + @echo >&2 '***' + @exit 1 + +endif # CONFIG_MODULES + # Single targets # --------------------------------------------------------------------------- # To build individual files in subdirectories, you can do like this: @@ -1963,11 +1955,6 @@ tools/%: FORCE quiet_cmd_rmfiles = $(if $(wildcard $(rm-files)),CLEAN $(wildcard $(rm-files))) cmd_rmfiles = rm -rf $(rm-files) -# Run depmod only if we have System.map and depmod is executable -quiet_cmd_depmod = DEPMOD $(KERNELRELEASE) - cmd_depmod = $(CONFIG_SHELL) $(srctree)/scripts/depmod.sh $(DEPMOD) \ - $(KERNELRELEASE) - # read saved command lines for existing targets existing-targets := $(wildcard $(sort $(targets))) From 8d2ff5b3e28d81fb925647295f54759989f3f31a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 28 Aug 2022 11:39:50 +0900 Subject: [PATCH 0521/4345] kbuild: refactor single builds of *.ko [ Upstream commit f110e5a250e3c5db417e094b3dd86f1c135291ca ] Remove the potentially invalid modules.order instead of using the temporary file. Also, KBUILD_MODULES is don't care for single builds. No need to cancel it. Signed-off-by: Masahiro Yamada Stable-dep-of: c7b98de745cf ("phy: qcom-qmp-combo: fix runtime suspend") Signed-off-by: Sasha Levin --- Makefile | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/Makefile b/Makefile index 69c9123bc96d..704709f34da3 100644 --- a/Makefile +++ b/Makefile @@ -1766,6 +1766,8 @@ modules modules_install: @echo >&2 '***' @exit 1 +KBUILD_MODULES := + endif # CONFIG_MODULES # Single targets @@ -1791,18 +1793,12 @@ $(single-ko): single_modpost $(single-no-ko): descend @: -ifeq ($(KBUILD_EXTMOD),) -# For the single build of in-tree modules, use a temporary file to avoid -# the situation of modules_install installing an invalid modules.order. -MODORDER := .modules.tmp -endif - +# Remove MODORDER when done because it is not the real one. PHONY += single_modpost single_modpost: $(single-no-ko) modules_prepare $(Q){ $(foreach m, $(single-ko), echo $(extmod-prefix)$m;) } > $(MODORDER) $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost - -KBUILD_MODULES := 1 + $(Q)rm -f $(MODORDER) export KBUILD_SINGLE_TARGETS := $(addprefix $(extmod-prefix), $(single-no-ko)) @@ -1812,10 +1808,6 @@ build-dirs := $(foreach d, $(build-dirs), \ endif -ifndef CONFIG_MODULES -KBUILD_MODULES := -endif - # Handle descending into subdirectories listed in $(build-dirs) # Preset locale variables to speed up the build process. Limit locale # tweaks to this spot to avoid wrong language settings when running From da1a33795dfda0c52b484351647ba2981dbfaf7b Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sun, 27 Nov 2022 22:49:28 +1000 Subject: [PATCH 0522/4345] powerpc/perf: callchain validate kernel stack pointer bounds [ Upstream commit 32c5209214bd8d4f8c4e9d9b630ef4c671f58e79 ] The interrupt frame detection and loads from the hypothetical pt_regs are not bounds-checked. The next-frame validation only bounds-checks STACK_FRAME_OVERHEAD, which does not include the pt_regs. Add another test for this. The user could set r1 to be equal to the address matching the first interrupt frame - STACK_INT_FRAME_SIZE, which is in the previous page due to the kernel redzone, and induce the kernel to load the marker from there. Possibly this could cause a crash at least. If the user could induce the previous page to contain a valid marker, then it might be able to direct perf to read specific memory addresses in a way that could be transmitted back to the user in the perf data. Fixes: 20002ded4d93 ("perf_counter: powerpc: Add callchain support") Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221127124942.1665522-4-npiggin@gmail.com Signed-off-by: Sasha Levin --- arch/powerpc/perf/callchain.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 6c028ee513c0..99f3c4fc21cb 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -61,6 +61,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re next_sp = fp[0]; if (next_sp == sp + STACK_INT_FRAME_SIZE && + validate_sp(sp, current, STACK_INT_FRAME_SIZE) && fp[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) { /* * This looks like an interrupt frame for an From 0abfe735be5487cbeec3a41a881326fd6278e512 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Sat, 29 Oct 2022 19:16:26 +0800 Subject: [PATCH 0523/4345] powerpc/83xx/mpc832x_rdb: call platform_device_put() in error case in of_fsl_spi_probe() [ Upstream commit 4d0eea415216fe3791da2f65eb41399e70c7bedf ] If platform_device_add() is not called or failed, it can not call platform_device_del() to clean up memory, it should call platform_device_put() in error case. Fixes: 26f6cb999366 ("[POWERPC] fsl_soc: add support for fsl_spi") Signed-off-by: Yang Yingliang Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221029111626.429971-1-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/83xx/mpc832x_rdb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index 622c625d5ce4..1114b6a11b3f 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -106,7 +106,7 @@ static int __init of_fsl_spi_probe(char *type, char *compatible, u32 sysclk, goto next; unreg: - platform_device_del(pdev); + platform_device_put(pdev); err: pr_err("%pOF: registration failed\n", np); next: From 464506de9bb3cb15e92ce2dc127e963614af7d27 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 30 Nov 2022 23:15:13 +0530 Subject: [PATCH 0524/4345] powerpc/hv-gpci: Fix hv_gpci event list [ Upstream commit 03f7c1d2a49acd30e38789cd809d3300721e9b0e ] Based on getPerfCountInfo v1.018 documentation, some of the hv_gpci events were deprecated for platform firmware that supports counter_info_version 0x8 or above. Fix the hv_gpci event list by adding a new attribute group called "hv_gpci_event_attrs_v6" and a "ENABLE_EVENTS_COUNTERINFO_V6" macro to enable these events for platform firmware that supports counter_info_version 0x6 or below. And assigning the hv_gpci event list based on output counter info version of underlying plaform. Fixes: 97bf2640184f ("powerpc/perf/hv-gpci: add the remaining gpci requests") Signed-off-by: Kajol Jain Reviewed-by: Madhavan Srinivasan Reviewed-by: Athira Rajeev Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221130174513.87501-1-kjain@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/perf/hv-gpci-requests.h | 4 ++++ arch/powerpc/perf/hv-gpci.c | 33 +++++++++++++++++++++++++++- arch/powerpc/perf/hv-gpci.h | 1 + arch/powerpc/perf/req-gen/perf.h | 20 +++++++++++++++++ 4 files changed, 57 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h index 8965b4463d43..5e86371a20c7 100644 --- a/arch/powerpc/perf/hv-gpci-requests.h +++ b/arch/powerpc/perf/hv-gpci-requests.h @@ -79,6 +79,7 @@ REQUEST(__field(0, 8, partition_id) ) #include I(REQUEST_END) +#ifdef ENABLE_EVENTS_COUNTERINFO_V6 /* * Not available for counter_info_version >= 0x8, use * run_instruction_cycles_by_partition(0x100) instead. @@ -92,6 +93,7 @@ REQUEST(__field(0, 8, partition_id) __count(0x10, 8, cycles) ) #include I(REQUEST_END) +#endif #define REQUEST_NAME system_performance_capabilities #define REQUEST_NUM 0x40 @@ -103,6 +105,7 @@ REQUEST(__field(0, 1, perf_collect_privileged) ) #include I(REQUEST_END) +#ifdef ENABLE_EVENTS_COUNTERINFO_V6 #define REQUEST_NAME processor_bus_utilization_abc_links #define REQUEST_NUM 0x50 #define REQUEST_IDX_KIND "hw_chip_id=?" @@ -194,6 +197,7 @@ REQUEST(__field(0, 4, phys_processor_idx) __count(0x28, 8, instructions_completed) ) #include I(REQUEST_END) +#endif /* Processor_core_power_mode (0x95) skipped, no counters */ /* Affinity_domain_information_by_virtual_processor (0xA0) skipped, diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index c756228a081f..28b770bbc10b 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -72,7 +72,7 @@ static struct attribute_group format_group = { static struct attribute_group event_group = { .name = "events", - .attrs = hv_gpci_event_attrs, + /* .attrs is set in init */ }; #define HV_CAPS_ATTR(_name, _format) \ @@ -330,6 +330,7 @@ static int hv_gpci_init(void) int r; unsigned long hret; struct hv_perf_caps caps; + struct hv_gpci_request_buffer *arg; hv_gpci_assert_offsets_correct(); @@ -353,6 +354,36 @@ static int hv_gpci_init(void) /* sampling not supported */ h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + arg = (void *)get_cpu_var(hv_gpci_reqb); + memset(arg, 0, HGPCI_REQ_BUFFER_SIZE); + + /* + * hcall H_GET_PERF_COUNTER_INFO populates the output + * counter_info_version value based on the system hypervisor. + * Pass the counter request 0x10 corresponds to request type + * 'Dispatch_timebase_by_processor', to get the supported + * counter_info_version. + */ + arg->params.counter_request = cpu_to_be32(0x10); + + r = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, + virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + if (r) { + pr_devel("hcall failed, can't get supported counter_info_version: 0x%x\n", r); + arg->params.counter_info_version_out = 0x8; + } + + /* + * Use counter_info_version_out value to assign + * required hv-gpci event list. + */ + if (arg->params.counter_info_version_out >= 0x8) + event_group.attrs = hv_gpci_event_attrs; + else + event_group.attrs = hv_gpci_event_attrs_v6; + + put_cpu_var(hv_gpci_reqb); + r = perf_pmu_register(&h_gpci_pmu, h_gpci_pmu.name, -1); if (r) return r; diff --git a/arch/powerpc/perf/hv-gpci.h b/arch/powerpc/perf/hv-gpci.h index 4d108262bed7..c72020912dea 100644 --- a/arch/powerpc/perf/hv-gpci.h +++ b/arch/powerpc/perf/hv-gpci.h @@ -26,6 +26,7 @@ enum { #define REQUEST_FILE "../hv-gpci-requests.h" #define NAME_LOWER hv_gpci #define NAME_UPPER HV_GPCI +#define ENABLE_EVENTS_COUNTERINFO_V6 #include "req-gen/perf.h" #undef REQUEST_FILE #undef NAME_LOWER diff --git a/arch/powerpc/perf/req-gen/perf.h b/arch/powerpc/perf/req-gen/perf.h index fa9bc804e67a..6b2a59fefffa 100644 --- a/arch/powerpc/perf/req-gen/perf.h +++ b/arch/powerpc/perf/req-gen/perf.h @@ -139,6 +139,26 @@ PMU_EVENT_ATTR_STRING( \ #define REQUEST_(r_name, r_value, r_idx_1, r_fields) \ r_fields +/* Generate event list for platforms with counter_info_version 0x6 or below */ +static __maybe_unused struct attribute *hv_gpci_event_attrs_v6[] = { +#include REQUEST_FILE + NULL +}; + +/* + * Based on getPerfCountInfo v1.018 documentation, some of the hv-gpci + * events were deprecated for platform firmware that supports + * counter_info_version 0x8 or above. + * Those deprecated events are still part of platform firmware that + * support counter_info_version 0x6 and below. As per the getPerfCountInfo + * v1.018 documentation there is no counter_info_version 0x7. + * Undefining macro ENABLE_EVENTS_COUNTERINFO_V6, to disable the addition of + * deprecated events in "hv_gpci_event_attrs" attribute group, for platforms + * that supports counter_info_version 0x8 or above. + */ +#undef ENABLE_EVENTS_COUNTERINFO_V6 + +/* Generate event list for platforms with counter_info_version 0x8 or above*/ static __maybe_unused struct attribute *hv_gpci_event_attrs[] = { #include REQUEST_FILE NULL From dc02d8e59d36080dddaba22f19fe813f8b473918 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 5 Dec 2022 12:44:27 +0400 Subject: [PATCH 0525/4345] selftests/powerpc: Fix resource leaks [ Upstream commit 8f4ab7da904ab7027ccd43ddb4f0094e932a5877 ] In check_all_cpu_dscr_defaults, opendir() opens the directory stream. Add missing closedir() in the error path to release it. In check_cpu_dscr_default, open() creates an open file descriptor. Add missing close() in the error path to release it. Fixes: ebd5858c904b ("selftests/powerpc: Add test for all DSCR sysfs interfaces") Signed-off-by: Miaoqian Lin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221205084429.570654-1-linmq006@gmail.com Signed-off-by: Sasha Levin --- tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c index fbbdffdb2e5d..f20d1c166d1e 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c @@ -24,6 +24,7 @@ static int check_cpu_dscr_default(char *file, unsigned long val) rc = read(fd, buf, sizeof(buf)); if (rc == -1) { perror("read() failed"); + close(fd); return 1; } close(fd); @@ -65,8 +66,10 @@ static int check_all_cpu_dscr_defaults(unsigned long val) if (access(file, F_OK)) continue; - if (check_cpu_dscr_default(file, val)) + if (check_cpu_dscr_default(file, val)) { + closedir(sysfs); return 1; + } } closedir(sysfs); return 0; From 57f215a231673eba851fb3db9d30379296cacd97 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 28 Nov 2022 10:06:28 -0400 Subject: [PATCH 0526/4345] iommu/sun50i: Remove IOMMU_DOMAIN_IDENTITY [ Upstream commit ef5bb8e7a7127218f826b9ccdf7508e7a339f4c2 ] This driver treats IOMMU_DOMAIN_IDENTITY the same as UNMANAGED, which cannot possibly be correct. UNMANAGED domains are required to start out blocking all DMAs. This seems to be what this driver does as it allocates a first level 'dt' for the IO page table that is 0 filled. Thus UNMANAGED looks like a working IO page table, and so IDENTITY must be a mistake. Remove it. Fixes: 4100b8c229b3 ("iommu: Add Allwinner H6 IOMMU driver") Signed-off-by: Jason Gunthorpe Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/0-v1-97f0adf27b5e+1f0-s50_identity_jgg@nvidia.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/sun50i-iommu.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index dc8ad35cbc4e..65aa30d55d3a 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -603,7 +603,6 @@ static struct iommu_domain *sun50i_iommu_domain_alloc(unsigned type) struct sun50i_iommu_domain *sun50i_domain; if (type != IOMMU_DOMAIN_DMA && - type != IOMMU_DOMAIN_IDENTITY && type != IOMMU_DOMAIN_UNMANAGED) return NULL; From 6a65f4644b65a1c1858a30661b46a30af6cc5f48 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 2 Dec 2022 19:35:05 +0100 Subject: [PATCH 0527/4345] pwm: sifive: Call pwm_sifive_update_clock() while mutex is held MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 45558b3abb87eeb2cedb8a59cb2699c120b5102a ] As was documented in commit 0f02f491b786 ("pwm: sifive: Reduce time the controller lock is held") a caller of pwm_sifive_update_clock() must hold the mutex. So fix pwm_sifive_clock_notifier() to grab the lock. While this necessity was only documented later, the race exists since the driver was introduced. Fixes: 9e37a53eb051 ("pwm: sifive: Add a driver for SiFive SoC PWM") Reported-by: Emil Renner Berthing Reviewed-by: Emil Renner Berthing Link: https://lore.kernel.org/r/20221018061656.1428111-1-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-sifive.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-sifive.c b/drivers/pwm/pwm-sifive.c index 9cc0612f0849..12e9e23272ab 100644 --- a/drivers/pwm/pwm-sifive.c +++ b/drivers/pwm/pwm-sifive.c @@ -217,8 +217,11 @@ static int pwm_sifive_clock_notifier(struct notifier_block *nb, struct pwm_sifive_ddata *ddata = container_of(nb, struct pwm_sifive_ddata, notifier); - if (event == POST_RATE_CHANGE) + if (event == POST_RATE_CHANGE) { + mutex_lock(&ddata->lock); pwm_sifive_update_clock(ddata, ndata->new_rate); + mutex_unlock(&ddata->lock); + } return NOTIFY_OK; } From e4539eb5c0c342567183fe386d0699c8dab49490 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 29 Nov 2022 18:56:50 +0800 Subject: [PATCH 0528/4345] remoteproc: sysmon: fix memory leak in qcom_add_sysmon_subdev() [ Upstream commit e01ce676aaef3b13d02343d7e70f9637d93a3367 ] The kfree() should be called when of_irq_get_byname() fails or devm_request_threaded_irq() fails in qcom_add_sysmon_subdev(), otherwise there will be a memory leak, so add kfree() to fix it. Fixes: 027045a6e2b7 ("remoteproc: qcom: Add shutdown-ack irq") Signed-off-by: Gaosheng Cui Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221129105650.1539187-1-cuigaosheng1@huawei.com Signed-off-by: Sasha Levin --- drivers/remoteproc/qcom_sysmon.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/qcom_sysmon.c b/drivers/remoteproc/qcom_sysmon.c index a26221a6f6c2..c348ea35e47c 100644 --- a/drivers/remoteproc/qcom_sysmon.c +++ b/drivers/remoteproc/qcom_sysmon.c @@ -625,7 +625,9 @@ struct qcom_sysmon *qcom_add_sysmon_subdev(struct rproc *rproc, if (sysmon->shutdown_irq != -ENODATA) { dev_err(sysmon->dev, "failed to retrieve shutdown-ack IRQ\n"); - return ERR_PTR(sysmon->shutdown_irq); + ret = sysmon->shutdown_irq; + kfree(sysmon); + return ERR_PTR(ret); } } else { ret = devm_request_threaded_irq(sysmon->dev, @@ -636,6 +638,7 @@ struct qcom_sysmon *qcom_add_sysmon_subdev(struct rproc *rproc, if (ret) { dev_err(sysmon->dev, "failed to acquire shutdown-ack IRQ\n"); + kfree(sysmon); return ERR_PTR(ret); } } From 582dd58a186cc7f3b3b7ca1a6f8bdd98256f43f4 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Fri, 18 Nov 2022 10:08:15 +0100 Subject: [PATCH 0529/4345] remoteproc: qcom_q6v5_pas: disable wakeup on probe fail or remove [ Upstream commit 9a70551996e699fda262e8d54bbd41739d7aad6d ] Leaving wakeup enabled during probe fail (-EPROBE_DEFER) or remove makes the subsequent probe fail. [ 3.749454] remoteproc remoteproc0: releasing 3000000.remoteproc [ 3.752949] qcom_q6v5_pas: probe of 3000000.remoteproc failed with error -17 [ 3.878935] remoteproc remoteproc0: releasing 4080000.remoteproc [ 3.887602] qcom_q6v5_pas: probe of 4080000.remoteproc failed with error -17 [ 4.319552] remoteproc remoteproc0: releasing 8300000.remoteproc [ 4.332716] qcom_q6v5_pas: probe of 8300000.remoteproc failed with error -17 Fix this by disabling wakeup in both cases so the driver can properly probe on the next try. Fixes: a781e5aa5911 ("remoteproc: core: Prevent system suspend during remoteproc recovery") Fixes: dc86c129b4fb ("remoteproc: qcom: pas: Mark devices as wakeup capable") Reviewed-by: Mukesh Ojha Signed-off-by: Luca Weiss Reviewed-by: Caleb Connolly Reviewed-by: Sibi Sankar Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221118090816.100012-1-luca.weiss@fairphone.com Signed-off-by: Sasha Levin --- drivers/remoteproc/qcom_q6v5_pas.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c index 0678b417707e..99b206b00456 100644 --- a/drivers/remoteproc/qcom_q6v5_pas.c +++ b/drivers/remoteproc/qcom_q6v5_pas.c @@ -472,6 +472,7 @@ detach_proxy_pds: detach_active_pds: adsp_pds_detach(adsp, adsp->active_pds, adsp->active_pd_count); free_rproc: + device_init_wakeup(adsp->dev, false); rproc_free(rproc); return ret; @@ -487,6 +488,7 @@ static int adsp_remove(struct platform_device *pdev) qcom_remove_sysmon_subdev(adsp->sysmon); qcom_remove_smd_subdev(adsp->rproc, &adsp->smd_subdev); qcom_remove_ssr_subdev(adsp->rproc, &adsp->ssr_subdev); + device_init_wakeup(adsp->dev, false); rproc_free(adsp->rproc); return 0; From be5816b27bff4438c7da487b6c873409d2d565c5 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Fri, 18 Nov 2022 10:08:16 +0100 Subject: [PATCH 0530/4345] remoteproc: qcom_q6v5_pas: detach power domains on remove [ Upstream commit 34d01df00b84127be04c914fc9f8e8be1fcdf851 ] We need to detach from the power domains also on remove, not just on probe fail so a subsequent probe works as expected. Otherwise the following error appears on re-probe: [ 29.452005] sysfs: cannot create duplicate filename '/devices/genpd:0:3000000.remoteproc' [ 29.477121] CPU: 1 PID: 483 Comm: sh Tainted: G W 6.1.0-rc4-00075-g71a113770bda #78 [ 29.510319] Hardware name: Fairphone 4 (DT) [ 29.538335] Call trace: [ 29.564470] dump_backtrace.part.0+0xe0/0xf0 [ 29.592602] show_stack+0x18/0x30 [ 29.619616] dump_stack_lvl+0x64/0x80 [ 29.646834] dump_stack+0x18/0x34 [ 29.673541] sysfs_warn_dup+0x60/0x7c [ 29.700592] sysfs_create_dir_ns+0xec/0x110 [ 29.728057] kobject_add_internal+0xb8/0x374 [ 29.755530] kobject_add+0x9c/0x104 [ 29.782072] device_add+0xbc/0x8a0 [ 29.808445] device_register+0x20/0x30 [ 29.835175] genpd_dev_pm_attach_by_id+0xa4/0x190 [ 29.862851] genpd_dev_pm_attach_by_name+0x3c/0xb0 [ 29.890472] dev_pm_domain_attach_by_name+0x20/0x30 [ 29.918212] adsp_probe+0x278/0x580 [ 29.944384] platform_probe+0x68/0xc0 [ 29.970603] really_probe+0xbc/0x2dc [ 29.996662] __driver_probe_device+0x78/0xe0 [ 30.023491] device_driver_attach+0x48/0xac [ 30.050215] bind_store+0xb8/0x114 [ 30.075957] drv_attr_store+0x24/0x3c [ 30.101874] sysfs_kf_write+0x44/0x54 [ 30.127751] kernfs_fop_write_iter+0x120/0x1f0 [ 30.154448] vfs_write+0x1ac/0x380 [ 30.179937] ksys_write+0x70/0x104 [ 30.205274] __arm64_sys_write+0x1c/0x2c [ 30.231060] invoke_syscall+0x48/0x114 [ 30.256594] el0_svc_common.constprop.0+0x44/0xec [ 30.283183] do_el0_svc+0x2c/0xd0 [ 30.308320] el0_svc+0x2c/0x84 [ 30.333059] el0t_64_sync_handler+0xf4/0x120 [ 30.359001] el0t_64_sync+0x18c/0x190 [ 30.384385] kobject_add_internal failed for genpd:0:3000000.remoteproc with -EEXIST, don't try to register things with the same name in the same directory. [ 30.406029] remoteproc remoteproc0: releasing 3000000.remoteproc [ 30.416064] qcom_q6v5_pas: probe of 3000000.remoteproc failed with error -17 Fixes: 17ee2fb4e856 ("remoteproc: qcom: pas: Vote for active/proxy power domains") Reviewed-by: Sibi Sankar Reviewed-by: Mukesh Ojha Signed-off-by: Luca Weiss Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221118090816.100012-2-luca.weiss@fairphone.com Signed-off-by: Sasha Levin --- drivers/remoteproc/qcom_q6v5_pas.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c index 99b206b00456..d8ef10fba8e8 100644 --- a/drivers/remoteproc/qcom_q6v5_pas.c +++ b/drivers/remoteproc/qcom_q6v5_pas.c @@ -488,6 +488,7 @@ static int adsp_remove(struct platform_device *pdev) qcom_remove_sysmon_subdev(adsp->sysmon); qcom_remove_smd_subdev(adsp->rproc, &adsp->smd_subdev); qcom_remove_ssr_subdev(adsp->rproc, &adsp->ssr_subdev); + adsp_pds_detach(adsp, adsp->proxy_pds, adsp->proxy_pd_count); device_init_wakeup(adsp->dev, false); rproc_free(adsp->rproc); From 12654b7d8deb777b5f04a3a5c1c9dd8375383bcc Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Sat, 3 Dec 2022 07:06:39 +0000 Subject: [PATCH 0531/4345] remoteproc: qcom_q6v5_pas: Fix missing of_node_put() in adsp_alloc_memory_region() [ Upstream commit 38e7d9c19276832ebb0277f415b9214bf7baeb37 ] The pointer node is returned by of_parse_phandle() with refcount incremented. We should use of_node_put() on it when done. Fixes: b9e718e950c3 ("remoteproc: Introduce Qualcomm ADSP PIL") Signed-off-by: Yuan Can Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221203070639.15128-1-yuancan@huawei.com Signed-off-by: Sasha Levin --- drivers/remoteproc/qcom_q6v5_pas.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c index d8ef10fba8e8..1a0d6eb9425b 100644 --- a/drivers/remoteproc/qcom_q6v5_pas.c +++ b/drivers/remoteproc/qcom_q6v5_pas.c @@ -365,6 +365,7 @@ static int adsp_alloc_memory_region(struct qcom_adsp *adsp) } ret = of_address_to_resource(node, 0, &r); + of_node_put(node); if (ret) return ret; From 9dc96fee2648252c56ccebd4be258634ce48769a Mon Sep 17 00:00:00 2001 From: Haowen Bai Date: Wed, 11 May 2022 09:27:56 +0800 Subject: [PATCH 0532/4345] powerpc/eeh: Drop redundant spinlock initialization [ Upstream commit 3def164a5cedad9117859dd4610cae2cc59cb6d2 ] slot_errbuf_lock has declared and initialized by DEFINE_SPINLOCK, so we don't need to spin_lock_init again, drop it. Signed-off-by: Haowen Bai Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1652232476-9696-1-git-send-email-baihaowen@meizu.com Stable-dep-of: 9aafbfa5f57a ("powerpc/pseries/eeh: use correct API for error log size") Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/eeh_pseries.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 7ed38ebd0c7b..6ad8bda06345 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -846,8 +846,7 @@ static int __init eeh_pseries_init(void) return -EINVAL; } - /* Initialize error log lock and size */ - spin_lock_init(&slot_errbuf_lock); + /* Initialize error log size */ eeh_error_buf_size = rtas_token("rtas-error-log-max"); if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) { pr_info("%s: unknown EEH error log size\n", From 1f5571cb1d7be29df8d4cc4cb6ab1c6a5039ee54 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Fri, 18 Nov 2022 09:07:43 -0600 Subject: [PATCH 0533/4345] powerpc/pseries/eeh: use correct API for error log size [ Upstream commit 9aafbfa5f57a4b75bafd3bed0191e8429c5fa618 ] rtas-error-log-max is not the name of an RTAS function, so rtas_token() is not the appropriate API for retrieving its value. We already have rtas_get_error_log_max() which returns a sensible value if the property is absent for any reason, so use that instead. Fixes: 8d633291b4fc ("powerpc/eeh: pseries platform EEH error log retrieval") Signed-off-by: Nathan Lynch [mpe: Drop no-longer possible error handling as noticed by ajd] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221118150751.469393-6-nathanl@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/eeh_pseries.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 6ad8bda06345..4601ad10ca7b 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -847,16 +847,7 @@ static int __init eeh_pseries_init(void) } /* Initialize error log size */ - eeh_error_buf_size = rtas_token("rtas-error-log-max"); - if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) { - pr_info("%s: unknown EEH error log size\n", - __func__); - eeh_error_buf_size = 1024; - } else if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) { - pr_info("%s: EEH error log size %d exceeds the maximal %d\n", - __func__, eeh_error_buf_size, RTAS_ERROR_LOG_MAX); - eeh_error_buf_size = RTAS_ERROR_LOG_MAX; - } + eeh_error_buf_size = rtas_get_error_log_max(); /* Set EEH probe mode */ eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG); From 8e65e707640b762de21aa50aa6e8948071fcaab4 Mon Sep 17 00:00:00 2001 From: Qingfang DENG Date: Thu, 8 Dec 2022 20:35:29 +0800 Subject: [PATCH 0534/4345] netfilter: flowtable: really fix NAT IPv6 offload [ Upstream commit 5fb45f95eec682621748b7cb012c6a8f0f981e6a ] The for-loop was broken from the start. It translates to: for (i = 0; i < 4; i += 4) which means the loop statement is run only once, so only the highest 32-bit of the IPv6 address gets mangled. Fix the loop increment. Fixes: 0e07e25b481a ("netfilter: flowtable: fix NAT IPv6 offload mangling") Fixes: 5c27d8d76ce8 ("netfilter: nf_flow_table_offload: add IPv6 support") Signed-off-by: Qingfang DENG Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_flow_table_offload.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 28306cb66719..746ca77d0aad 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -305,12 +305,12 @@ static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, const __be32 *addr, const __be32 *mask) { struct flow_action_entry *entry; - int i, j; + int i; - for (i = 0, j = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32), j++) { + for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++) { entry = flow_action_entry_next(flow_rule); flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6, - offset + i, &addr[j], mask); + offset + i * sizeof(u32), &addr[i], mask); } } From 34836c592345f087eff0b6cc2c48ee3153997cb4 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Wed, 23 Nov 2022 09:48:05 +0800 Subject: [PATCH 0535/4345] rtc: st-lpc: Add missing clk_disable_unprepare in st_rtc_probe() [ Upstream commit 5fb733d7bd6949e90028efdce8bd528c6ab7cf1e ] The clk_disable_unprepare() should be called in the error handling of clk_get_rate(), fix it. Fixes: b5b2bdfc2893 ("rtc: st: Add new driver for ST's LPC RTC") Signed-off-by: Gaosheng Cui Link: https://lore.kernel.org/r/20221123014805.1993052-1-cuigaosheng1@huawei.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-st-lpc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/rtc/rtc-st-lpc.c b/drivers/rtc/rtc-st-lpc.c index 0c65448b85ee..7d53f7e2febc 100644 --- a/drivers/rtc/rtc-st-lpc.c +++ b/drivers/rtc/rtc-st-lpc.c @@ -238,6 +238,7 @@ static int st_rtc_probe(struct platform_device *pdev) rtc->clkrate = clk_get_rate(rtc->clk); if (!rtc->clkrate) { + clk_disable_unprepare(rtc->clk); dev_err(&pdev->dev, "Unable to fetch clock rate\n"); return -EINVAL; } From e9453c13ae9ce19ff8109171b5736ad46bd64a4f Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Wed, 23 Nov 2022 09:59:53 +0800 Subject: [PATCH 0536/4345] rtc: pic32: Move devm_rtc_allocate_device earlier in pic32_rtc_probe() [ Upstream commit 90cd5c88830140c9fade92a8027e0fb2c6e4cc49 ] The pic32_rtc_enable(pdata, 0) and clk_disable_unprepare(pdata->clk) should be called in the error handling of devm_rtc_allocate_device(), so we should move devm_rtc_allocate_device earlier in pic32_rtc_probe() to fix it. Fixes: 6515e23b9fde ("rtc: pic32: convert to devm_rtc_allocate_device") Signed-off-by: Gaosheng Cui Link: https://lore.kernel.org/r/20221123015953.1998521-1-cuigaosheng1@huawei.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-pic32.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-pic32.c b/drivers/rtc/rtc-pic32.c index 2b6946744654..7be1ca1633fc 100644 --- a/drivers/rtc/rtc-pic32.c +++ b/drivers/rtc/rtc-pic32.c @@ -324,16 +324,16 @@ static int pic32_rtc_probe(struct platform_device *pdev) spin_lock_init(&pdata->alarm_lock); + pdata->rtc = devm_rtc_allocate_device(&pdev->dev); + if (IS_ERR(pdata->rtc)) + return PTR_ERR(pdata->rtc); + clk_prepare_enable(pdata->clk); pic32_rtc_enable(pdata, 1); device_init_wakeup(&pdev->dev, 1); - pdata->rtc = devm_rtc_allocate_device(&pdev->dev); - if (IS_ERR(pdata->rtc)) - return PTR_ERR(pdata->rtc); - pdata->rtc->ops = &pic32_rtcops; pdata->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; pdata->rtc->range_max = RTC_TIMESTAMP_END_2099; From 09c007e2392321e74483cea3ab1e99c0b629700a Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sun, 11 Dec 2022 23:35:53 +0100 Subject: [PATCH 0537/4345] rtc: pcf85063: fix pcf85063_clkout_control [ Upstream commit c2d12e85336f6d4172fb2bab5935027c446d7343 ] pcf85063_clkout_control reads the wrong register but then update the correct one. Reported-by: Janne Terho Fixes: 8c229ab6048b ("rtc: pcf85063: Add pcf85063 clkout control to common clock framework") Link: https://lore.kernel.org/r/20221211223553.59955-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-pcf85063.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c index d739b0c965aa..449204d84c61 100644 --- a/drivers/rtc/rtc-pcf85063.c +++ b/drivers/rtc/rtc-pcf85063.c @@ -430,7 +430,7 @@ static int pcf85063_clkout_control(struct clk_hw *hw, bool enable) unsigned int buf; int ret; - ret = regmap_read(pcf85063->regmap, PCF85063_REG_OFFSET, &buf); + ret = regmap_read(pcf85063->regmap, PCF85063_REG_CTRL2, &buf); if (ret < 0) return ret; buf &= PCF85063_REG_CLKO_F_MASK; From 452e85cc3edf1eb03e6861b258c3eea0c2e8cb08 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 14 May 2021 15:56:56 -0400 Subject: [PATCH 0538/4345] NFSD: Remove spurious cb_setup_err tracepoint [ Upstream commit 9f57c6062bf3ce2c6ab9ba60040b34e8134ef259 ] This path is not really an error path, so the tracepoint I added there is just noise. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields Stable-dep-of: 3bc8edc98bd4 ("nfsd: under NFSv4.1, fix double svc_xprt_put on rpc_create failure") Signed-off-by: Sasha Levin --- fs/nfsd/nfs4callback.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 7325592b456e..4eceff561e5a 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -915,10 +915,8 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) { - trace_nfsd_cb_setup_err(clp, -EINVAL); + if (!conn->cb_xprt) return -EINVAL; - } clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; From c1207219a4bfa50121c9345d5d165470d0a82531 Mon Sep 17 00:00:00 2001 From: Dan Aloni Date: Mon, 12 Dec 2022 13:11:06 +0200 Subject: [PATCH 0539/4345] nfsd: under NFSv4.1, fix double svc_xprt_put on rpc_create failure [ Upstream commit 3bc8edc98bd43540dbe648e4ef91f443d6d20a24 ] On error situation `clp->cl_cb_conn.cb_xprt` should not be given a reference to the xprt otherwise both client cleanup and the error handling path of the caller call to put it. Better to delay handing over the reference to a later branch. [ 72.530665] refcount_t: underflow; use-after-free. [ 72.531933] WARNING: CPU: 0 PID: 173 at lib/refcount.c:28 refcount_warn_saturate+0xcf/0x120 [ 72.533075] Modules linked in: nfsd(OE) nfsv4(OE) nfsv3(OE) nfs(OE) lockd(OE) compat_nfs_ssc(OE) nfs_acl(OE) rpcsec_gss_krb5(OE) auth_rpcgss(OE) rpcrdma(OE) dns_resolver fscache netfs grace rdma_cm iw_cm ib_cm sunrpc(OE) mlx5_ib mlx5_core mlxfw pci_hyperv_intf ib_uverbs ib_core xt_MASQUERADE nf_conntrack_netlink nft_counter xt_addrtype nft_compat br_netfilter bridge stp llc nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set overlay nf_tables nfnetlink crct10dif_pclmul crc32_pclmul ghash_clmulni_intel xfs serio_raw virtio_net virtio_blk net_failover failover fuse [last unloaded: sunrpc] [ 72.540389] CPU: 0 PID: 173 Comm: kworker/u16:5 Tainted: G OE 5.15.82-dan #1 [ 72.541511] Hardware name: Red Hat KVM/RHEL-AV, BIOS 1.16.0-3.module+el8.7.0+1084+97b81f61 04/01/2014 [ 72.542717] Workqueue: nfsd4_callbacks nfsd4_run_cb_work [nfsd] [ 72.543575] RIP: 0010:refcount_warn_saturate+0xcf/0x120 [ 72.544299] Code: 55 00 0f 0b 5d e9 01 50 98 00 80 3d 75 9e 39 08 00 0f 85 74 ff ff ff 48 c7 c7 e8 d1 60 8e c6 05 61 9e 39 08 01 e8 f6 51 55 00 <0f> 0b 5d e9 d9 4f 98 00 80 3d 4b 9e 39 08 00 0f 85 4c ff ff ff 48 [ 72.546666] RSP: 0018:ffffb3f841157cf0 EFLAGS: 00010286 [ 72.547393] RAX: 0000000000000026 RBX: ffff89ac6231d478 RCX: 0000000000000000 [ 72.548324] RDX: ffff89adb7c2c2c0 RSI: ffff89adb7c205c0 RDI: ffff89adb7c205c0 [ 72.549271] RBP: ffffb3f841157cf0 R08: 0000000000000000 R09: c0000000ffefffff [ 72.550209] R10: 0000000000000001 R11: ffffb3f841157ad0 R12: ffff89ac6231d180 [ 72.551142] R13: ffff89ac6231d478 R14: ffff89ac40c06180 R15: ffff89ac6231d4b0 [ 72.552089] FS: 0000000000000000(0000) GS:ffff89adb7c00000(0000) knlGS:0000000000000000 [ 72.553175] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 72.553934] CR2: 0000563a310506a8 CR3: 0000000109a66000 CR4: 0000000000350ef0 [ 72.554874] Call Trace: [ 72.555278] [ 72.555614] svc_xprt_put+0xaf/0xe0 [sunrpc] [ 72.556276] nfsd4_process_cb_update.isra.11+0xb7/0x410 [nfsd] [ 72.557087] ? update_load_avg+0x82/0x610 [ 72.557652] ? cpuacct_charge+0x60/0x70 [ 72.558212] ? dequeue_entity+0xdb/0x3e0 [ 72.558765] ? queued_spin_unlock+0x9/0x20 [ 72.559358] nfsd4_run_cb_work+0xfc/0x270 [nfsd] [ 72.560031] process_one_work+0x1df/0x390 [ 72.560600] worker_thread+0x37/0x3b0 [ 72.561644] ? process_one_work+0x390/0x390 [ 72.562247] kthread+0x12f/0x150 [ 72.562710] ? set_kthread_struct+0x50/0x50 [ 72.563309] ret_from_fork+0x22/0x30 [ 72.563818] [ 72.564189] ---[ end trace 031117b1c72ec616 ]--- [ 72.566019] list_add corruption. next->prev should be prev (ffff89ac4977e538), but was ffff89ac4763e018. (next=ffff89ac4763e018). [ 72.567647] ------------[ cut here ]------------ Fixes: a4abc6b12eb1 ("nfsd: Fix svc_xprt refcnt leak when setup callback client failed") Cc: Xiyu Yang Cc: J. Bruce Fields Signed-off-by: Dan Aloni Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/nfs4callback.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 4eceff561e5a..af2064e36ac6 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -917,7 +917,6 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c } else { if (!conn->cb_xprt) return -EINVAL; - clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; args.prognumber = clp->cl_cb_session->se_cb_prog; @@ -937,6 +936,9 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c rpc_shutdown_client(client); return -ENOMEM; } + + if (clp->cl_minorversion != 0) + clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_client = client; clp->cl_cb_cred = cred; trace_nfsd_cb_setup(clp); From 2a930b75bf93d7d844d778a207e990dd02526c5c Mon Sep 17 00:00:00 2001 From: Emeel Hakim Date: Sun, 11 Dec 2022 09:55:32 +0200 Subject: [PATCH 0540/4345] net: macsec: fix net device access prior to holding a lock [ Upstream commit f3b4a00f0f62da252c598310698dfc82ef2f2e2e ] Currently macsec offload selection update routine accesses the net device prior to holding the relevant lock. Fix by holding the lock prior to the device access. Fixes: dcb780fb2795 ("net: macsec: add nla support for changing the offloading selection") Reviewed-by: Raed Salem Signed-off-by: Emeel Hakim Link: https://lore.kernel.org/r/20221211075532.28099-1-ehakim@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/macsec.c | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index eb029456b594..4fdb970e3482 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2584,7 +2584,7 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) const struct macsec_ops *ops; struct macsec_context ctx; struct macsec_dev *macsec; - int ret; + int ret = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; @@ -2597,28 +2597,36 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) macsec_genl_offload_policy, NULL)) return -EINVAL; + rtnl_lock(); + dev = get_dev_from_nl(genl_info_net(info), attrs); - if (IS_ERR(dev)) - return PTR_ERR(dev); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } macsec = macsec_priv(dev); - if (!tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]) - return -EINVAL; + if (!tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]) { + ret = -EINVAL; + goto out; + } offload = nla_get_u8(tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]); if (macsec->offload == offload) - return 0; + goto out; /* Check if the offloading mode is supported by the underlying layers */ if (offload != MACSEC_OFFLOAD_OFF && - !macsec_check_offload(offload, macsec)) - return -EOPNOTSUPP; + !macsec_check_offload(offload, macsec)) { + ret = -EOPNOTSUPP; + goto out; + } /* Check if the net device is busy. */ - if (netif_running(dev)) - return -EBUSY; - - rtnl_lock(); + if (netif_running(dev)) { + ret = -EBUSY; + goto out; + } prev_offload = macsec->offload; macsec->offload = offload; @@ -2653,7 +2661,7 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) rollback: macsec->offload = prev_offload; - +out: rtnl_unlock(); return ret; } From 30e0a066b611f0e16581ac6ec8d4e54b92c99a56 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 12 Dec 2022 16:41:37 +0800 Subject: [PATCH 0541/4345] mISDN: hfcsusb: don't call dev_kfree_skb/kfree_skb() under spin_lock_irqsave() [ Upstream commit ddc9648db162eee556edd5222d2808fe33730203 ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. It should use dev_kfree_skb_irq() or dev_consume_skb_irq() instead. The difference between them is free reason, dev_kfree_skb_irq() means the SKB is dropped in error and dev_consume_skb_irq() means the SKB is consumed in normal. skb_queue_purge() is called under spin_lock_irqsave() in hfcusb_l2l1D(), kfree_skb() is called in it, to fix this, use skb_queue_splice_init() to move the dch->squeue to a free queue, also enqueue the tx_skb and rx_skb, at last calling __skb_queue_purge() to free the SKBs afer unlock. In tx_iso_complete(), dev_kfree_skb() is called to consume the transmitted SKB, so replace it with dev_consume_skb_irq(). Fixes: 69f52adb2d53 ("mISDN: Add HFC USB driver") Signed-off-by: Yang Yingliang Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/isdn/hardware/mISDN/hfcsusb.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index cd5642cef01f..e8b37bd5e34a 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -326,20 +326,24 @@ hfcusb_l2l1D(struct mISDNchannel *ch, struct sk_buff *skb) test_and_clear_bit(FLG_L2_ACTIVATED, &dch->Flags); if (hw->protocol == ISDN_P_NT_S0) { + struct sk_buff_head free_queue; + + __skb_queue_head_init(&free_queue); hfcsusb_ph_command(hw, HFC_L1_DEACTIVATE_NT); spin_lock_irqsave(&hw->lock, flags); - skb_queue_purge(&dch->squeue); + skb_queue_splice_init(&dch->squeue, &free_queue); if (dch->tx_skb) { - dev_kfree_skb(dch->tx_skb); + __skb_queue_tail(&free_queue, dch->tx_skb); dch->tx_skb = NULL; } dch->tx_idx = 0; if (dch->rx_skb) { - dev_kfree_skb(dch->rx_skb); + __skb_queue_tail(&free_queue, dch->rx_skb); dch->rx_skb = NULL; } test_and_clear_bit(FLG_TX_BUSY, &dch->Flags); spin_unlock_irqrestore(&hw->lock, flags); + __skb_queue_purge(&free_queue); #ifdef FIXME if (test_and_clear_bit(FLG_L1_BUSY, &dch->Flags)) dchannel_sched_event(&hc->dch, D_CLEARBUSY); @@ -1330,7 +1334,7 @@ tx_iso_complete(struct urb *urb) printk("\n"); } - dev_kfree_skb(tx_skb); + dev_consume_skb_irq(tx_skb); tx_skb = NULL; if (fifo->dch && get_next_dframe(fifo->dch)) tx_skb = fifo->dch->tx_skb; From b58c8719666d6096b40f6780da4ea0c50bd34450 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 12 Dec 2022 16:41:38 +0800 Subject: [PATCH 0542/4345] mISDN: hfcpci: don't call dev_kfree_skb/kfree_skb() under spin_lock_irqsave() [ Upstream commit f0f596bd75a9d573ca9b587abb39cee0b916bb82 ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. skb_queue_purge() is called under spin_lock_irqsave() in hfcpci_l2l1D(), kfree_skb() is called in it, to fix this, use skb_queue_splice_init() to move the dch->squeue to a free queue, also enqueue the tx_skb and rx_skb, at last calling __skb_queue_purge() to free the SKBs afer unlock. Fixes: 1700fe1a10dc ("Add mISDN HFC PCI driver") Signed-off-by: Yang Yingliang Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/isdn/hardware/mISDN/hfcpci.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index af17459c1a5c..eba58b99cd29 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -1617,16 +1617,19 @@ hfcpci_l2l1D(struct mISDNchannel *ch, struct sk_buff *skb) test_and_clear_bit(FLG_L2_ACTIVATED, &dch->Flags); spin_lock_irqsave(&hc->lock, flags); if (hc->hw.protocol == ISDN_P_NT_S0) { + struct sk_buff_head free_queue; + + __skb_queue_head_init(&free_queue); /* prepare deactivation */ Write_hfc(hc, HFCPCI_STATES, 0x40); - skb_queue_purge(&dch->squeue); + skb_queue_splice_init(&dch->squeue, &free_queue); if (dch->tx_skb) { - dev_kfree_skb(dch->tx_skb); + __skb_queue_tail(&free_queue, dch->tx_skb); dch->tx_skb = NULL; } dch->tx_idx = 0; if (dch->rx_skb) { - dev_kfree_skb(dch->rx_skb); + __skb_queue_tail(&free_queue, dch->rx_skb); dch->rx_skb = NULL; } test_and_clear_bit(FLG_TX_BUSY, &dch->Flags); @@ -1639,10 +1642,12 @@ hfcpci_l2l1D(struct mISDNchannel *ch, struct sk_buff *skb) hc->hw.mst_m &= ~HFCPCI_MASTER; Write_hfc(hc, HFCPCI_MST_MODE, hc->hw.mst_m); ret = 0; + spin_unlock_irqrestore(&hc->lock, flags); + __skb_queue_purge(&free_queue); } else { ret = l1_event(dch->l1, hh->prim); + spin_unlock_irqrestore(&hc->lock, flags); } - spin_unlock_irqrestore(&hc->lock, flags); break; } if (!ret) From 6939f84e5369a5597ae5c57634aa7e5c8207bbfc Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 12 Dec 2022 16:41:39 +0800 Subject: [PATCH 0543/4345] mISDN: hfcmulti: don't call dev_kfree_skb/kfree_skb() under spin_lock_irqsave() [ Upstream commit 1232946cf522b8de9e398828bde325d7c41f29dd ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. skb_queue_purge() is called under spin_lock_irqsave() in handle_dmsg() and hfcm_l1callback(), kfree_skb() is called in them, to fix this, use skb_queue_splice_init() to move the dch->squeue to a free queue, also enqueue the tx_skb and rx_skb, at last calling __skb_queue_purge() to free the SKBs afer unlock. Fixes: af69fb3a8ffa ("Add mISDN HFC multiport driver") Signed-off-by: Yang Yingliang Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/isdn/hardware/mISDN/hfcmulti.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index 7013a3f08429..4c5b6772562d 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -3219,6 +3219,7 @@ static int hfcm_l1callback(struct dchannel *dch, u_int cmd) { struct hfc_multi *hc = dch->hw; + struct sk_buff_head free_queue; u_long flags; switch (cmd) { @@ -3247,6 +3248,7 @@ hfcm_l1callback(struct dchannel *dch, u_int cmd) l1_event(dch->l1, HW_POWERUP_IND); break; case HW_DEACT_REQ: + __skb_queue_head_init(&free_queue); /* start deactivation */ spin_lock_irqsave(&hc->lock, flags); if (hc->ctype == HFC_TYPE_E1) { @@ -3266,20 +3268,21 @@ hfcm_l1callback(struct dchannel *dch, u_int cmd) plxsd_checksync(hc, 0); } } - skb_queue_purge(&dch->squeue); + skb_queue_splice_init(&dch->squeue, &free_queue); if (dch->tx_skb) { - dev_kfree_skb(dch->tx_skb); + __skb_queue_tail(&free_queue, dch->tx_skb); dch->tx_skb = NULL; } dch->tx_idx = 0; if (dch->rx_skb) { - dev_kfree_skb(dch->rx_skb); + __skb_queue_tail(&free_queue, dch->rx_skb); dch->rx_skb = NULL; } test_and_clear_bit(FLG_TX_BUSY, &dch->Flags); if (test_and_clear_bit(FLG_BUSY_TIMER, &dch->Flags)) del_timer(&dch->timer); spin_unlock_irqrestore(&hc->lock, flags); + __skb_queue_purge(&free_queue); break; case HW_POWERUP_REQ: spin_lock_irqsave(&hc->lock, flags); @@ -3386,6 +3389,9 @@ handle_dmsg(struct mISDNchannel *ch, struct sk_buff *skb) case PH_DEACTIVATE_REQ: test_and_clear_bit(FLG_L2_ACTIVATED, &dch->Flags); if (dch->dev.D.protocol != ISDN_P_TE_S0) { + struct sk_buff_head free_queue; + + __skb_queue_head_init(&free_queue); spin_lock_irqsave(&hc->lock, flags); if (debug & DEBUG_HFCMULTI_MSG) printk(KERN_DEBUG @@ -3407,14 +3413,14 @@ handle_dmsg(struct mISDNchannel *ch, struct sk_buff *skb) /* deactivate */ dch->state = 1; } - skb_queue_purge(&dch->squeue); + skb_queue_splice_init(&dch->squeue, &free_queue); if (dch->tx_skb) { - dev_kfree_skb(dch->tx_skb); + __skb_queue_tail(&free_queue, dch->tx_skb); dch->tx_skb = NULL; } dch->tx_idx = 0; if (dch->rx_skb) { - dev_kfree_skb(dch->rx_skb); + __skb_queue_tail(&free_queue, dch->rx_skb); dch->rx_skb = NULL; } test_and_clear_bit(FLG_TX_BUSY, &dch->Flags); @@ -3426,6 +3432,7 @@ handle_dmsg(struct mISDNchannel *ch, struct sk_buff *skb) #endif ret = 0; spin_unlock_irqrestore(&hc->lock, flags); + __skb_queue_purge(&free_queue); } else ret = l1_event(dch->l1, hh->prim); break; From aea9e64dec2cc6cd742e07ecd4e6236fc76b389b Mon Sep 17 00:00:00 2001 From: Minsuk Kang Date: Wed, 14 Dec 2022 10:51:39 +0900 Subject: [PATCH 0544/4345] nfc: pn533: Clear nfc_target before being used [ Upstream commit 9f28157778ede0d4f183f7ab3b46995bb400abbe ] Fix a slab-out-of-bounds read that occurs in nla_put() called from nfc_genl_send_target() when target->sensb_res_len, which is duplicated from an nfc_target in pn533, is too large as the nfc_target is not properly initialized and retains garbage values. Clear nfc_targets with memset() before they are used. Found by a modified version of syzkaller. BUG: KASAN: slab-out-of-bounds in nla_put Call Trace: memcpy nla_put nfc_genl_dump_targets genl_lock_dumpit netlink_dump __netlink_dump_start genl_family_rcv_msg_dumpit genl_rcv_msg netlink_rcv_skb genl_rcv netlink_unicast netlink_sendmsg sock_sendmsg ____sys_sendmsg ___sys_sendmsg __sys_sendmsg do_syscall_64 Fixes: 673088fb42d0 ("NFC: pn533: Send ATR_REQ directly for active device detection") Fixes: 361f3cb7f9cf ("NFC: DEP link hook implementation for pn533") Signed-off-by: Minsuk Kang Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20221214015139.119673-1-linuxlovemin@yonsei.ac.kr Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/nfc/pn533/pn533.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c index 8d7e29d953b7..87e1296c6838 100644 --- a/drivers/nfc/pn533/pn533.c +++ b/drivers/nfc/pn533/pn533.c @@ -1319,6 +1319,8 @@ static int pn533_poll_dep_complete(struct pn533 *dev, void *arg, if (IS_ERR(resp)) return PTR_ERR(resp); + memset(&nfc_target, 0, sizeof(struct nfc_target)); + rsp = (struct pn533_cmd_jump_dep_response *)resp->data; rc = rsp->status & PN533_CMD_RET_MASK; @@ -1960,6 +1962,8 @@ static int pn533_in_dep_link_up_complete(struct pn533 *dev, void *arg, dev_dbg(dev->dev, "Creating new target\n"); + memset(&nfc_target, 0, sizeof(struct nfc_target)); + nfc_target.supported_protocols = NFC_PROTO_NFC_DEP_MASK; nfc_target.nfcid1_len = 10; memcpy(nfc_target.nfcid1, rsp->nfcid3t, nfc_target.nfcid1_len); From 3d5f83a62e8235d235534b3dc6f197d8a822c269 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Tue, 13 Dec 2022 20:56:14 +0800 Subject: [PATCH 0545/4345] r6040: Fix kmemleak in probe and remove [ Upstream commit 7e43039a49c2da45edc1d9d7c9ede4003ab45a5f ] There is a memory leaks reported by kmemleak: unreferenced object 0xffff888116111000 (size 2048): comm "modprobe", pid 817, jiffies 4294759745 (age 76.502s) hex dump (first 32 bytes): 00 c4 0a 04 81 88 ff ff 08 10 11 16 81 88 ff ff ................ 08 10 11 16 81 88 ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [] kmalloc_trace+0x22/0x60 [] phy_device_create+0x4e/0x90 [] get_phy_device+0xd2/0x220 [] mdiobus_scan+0xa4/0x2e0 [] __mdiobus_register+0x482/0x8b0 [] r6040_init_one+0x714/0xd2c [r6040] ... The problem occurs in probe process as follows: r6040_init_one: mdiobus_register mdiobus_scan <- alloc and register phy_device, the reference count of phy_device is 3 r6040_mii_probe phy_connect <- connect to the first phy_device, so the reference count of the first phy_device is 4, others are 3 register_netdev <- fault inject succeeded, goto error handling path // error handling path err_out_mdio_unregister: mdiobus_unregister(lp->mii_bus); err_out_mdio: mdiobus_free(lp->mii_bus); <- the reference count of the first phy_device is 1, it is not released and other phy_devices are released // similarly, the remove process also has the same problem The root cause is traced to the phy_device is not disconnected when removes one r6040 device in r6040_remove_one() or on error handling path after r6040_mii probed successfully. In r6040_mii_probe(), a net ethernet device is connected to the first PHY device of mii_bus, in order to notify the connected driver when the link status changes, which is the default behavior of the PHY infrastructure to handle everything. Therefore the phy_device should be disconnected when removes one r6040 device or on error handling path. Fix it by adding phy_disconnect() when removes one r6040 device or on error handling path after r6040_mii probed successfully. Fixes: 3831861b4ad8 ("r6040: implement phylib") Signed-off-by: Li Zetao Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20221213125614.927754-1-lizetao1@huawei.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/rdc/r6040.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index ccdfa930130b..4cff544f04c2 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -1158,10 +1158,12 @@ static int r6040_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) err = register_netdev(dev); if (err) { dev_err(&pdev->dev, "Failed to register net device\n"); - goto err_out_mdio_unregister; + goto err_out_phy_disconnect; } return 0; +err_out_phy_disconnect: + phy_disconnect(dev->phydev); err_out_mdio_unregister: mdiobus_unregister(lp->mii_bus); err_out_mdio: @@ -1185,6 +1187,7 @@ static void r6040_remove_one(struct pci_dev *pdev) struct r6040_private *lp = netdev_priv(dev); unregister_netdev(dev); + phy_disconnect(dev->phydev); mdiobus_unregister(lp->mii_bus); mdiobus_free(lp->mii_bus); netif_napi_del(&lp->napi); From 67349025f00d0749e36386cfcfc32c2887f47fdb Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 25 Nov 2020 23:48:40 +0100 Subject: [PATCH 0546/4345] net: switch to storing KCOV handle directly in sk_buff [ Upstream commit fa69ee5aa48b5b52e8028c2eb486906e9998d081 ] It turns out that usage of skb extensions can cause memory leaks. Ido Schimmel reported: "[...] there are instances that blindly overwrite 'skb->extensions' by invoking skb_copy_header() after __alloc_skb()." Therefore, give up on using skb extensions for KCOV handle, and instead directly store kcov_handle in sk_buff. Fixes: 6370cc3bbd8a ("net: add kcov handle to skb extensions") Fixes: 85ce50d337d1 ("net: kcov: don't select SKB_EXTENSIONS when there is no NET") Fixes: 97f53a08cba1 ("net: linux/skbuff.h: combine SKB_EXTENSIONS + KCOV handling") Link: https://lore.kernel.org/linux-wireless/20201121160941.GA485907@shredder.lan/ Reported-by: Ido Schimmel Signed-off-by: Marco Elver Link: https://lore.kernel.org/r/20201125224840.2014773-1-elver@google.com Signed-off-by: Jakub Kicinski Stable-dep-of: db0b124f02ba ("igc: Enhance Qbv scheduling by using first flag bit") Signed-off-by: Sasha Levin --- include/linux/skbuff.h | 37 +++++++++++++------------------------ lib/Kconfig.debug | 1 - net/core/skbuff.c | 6 ------ 3 files changed, 13 insertions(+), 31 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 462b0e3ef2b2..521d66ec8d80 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -702,6 +702,7 @@ typedef unsigned char *sk_buff_data_t; * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header + * @kcov_handle: KCOV remote handle for remote coverage collection * @tail: Tail pointer * @end: End pointer * @head: Head of buffer @@ -906,6 +907,10 @@ struct sk_buff { __u16 network_header; __u16 mac_header; +#ifdef CONFIG_KCOV + u64 kcov_handle; +#endif + /* private: */ __u32 headers_end[0]; /* public: */ @@ -4160,9 +4165,6 @@ enum skb_ext_id { #endif #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, -#endif -#if IS_ENABLED(CONFIG_KCOV) - SKB_EXT_KCOV_HANDLE, #endif SKB_EXT_NUM, /* must be last */ }; @@ -4618,35 +4620,22 @@ static inline void skb_reset_redirect(struct sk_buff *skb) #endif } -#if IS_ENABLED(CONFIG_KCOV) && IS_ENABLED(CONFIG_SKB_EXTENSIONS) static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { - /* Do not allocate skb extensions only to set kcov_handle to zero - * (as it is zero by default). However, if the extensions are - * already allocated, update kcov_handle anyway since - * skb_set_kcov_handle can be called to zero a previously set - * value. - */ - if (skb_has_extensions(skb) || kcov_handle) { - u64 *kcov_handle_ptr = skb_ext_add(skb, SKB_EXT_KCOV_HANDLE); - - if (kcov_handle_ptr) - *kcov_handle_ptr = kcov_handle; - } +#ifdef CONFIG_KCOV + skb->kcov_handle = kcov_handle; +#endif } static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { - u64 *kcov_handle = skb_ext_find(skb, SKB_EXT_KCOV_HANDLE); - - return kcov_handle ? *kcov_handle : 0; -} +#ifdef CONFIG_KCOV + return skb->kcov_handle; #else -static inline void skb_set_kcov_handle(struct sk_buff *skb, - const u64 kcov_handle) { } -static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { return 0; } -#endif /* CONFIG_KCOV && CONFIG_SKB_EXTENSIONS */ + return 0; +#endif +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 4aed8abb2022..19c28a34c5f1 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1915,7 +1915,6 @@ config KCOV depends on CC_HAS_SANCOV_TRACE_PC || GCC_PLUGINS select DEBUG_FS select GCC_PLUGIN_SANCOV if !CC_HAS_SANCOV_TRACE_PC - select SKB_EXTENSIONS if NET help KCOV exposes kernel code coverage information in a form suitable for coverage-guided fuzzing (randomized testing). diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 06169889b0ca..176bcbb07aab 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4258,9 +4258,6 @@ static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_MPTCP) [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), #endif -#if IS_ENABLED(CONFIG_KCOV) - [SKB_EXT_KCOV_HANDLE] = SKB_EXT_CHUNKSIZEOF(u64), -#endif }; static __always_inline unsigned int skb_ext_total_length(void) @@ -4277,9 +4274,6 @@ static __always_inline unsigned int skb_ext_total_length(void) #endif #if IS_ENABLED(CONFIG_MPTCP) skb_ext_type_len[SKB_EXT_MPTCP] + -#endif -#if IS_ENABLED(CONFIG_KCOV) - skb_ext_type_len[SKB_EXT_KCOV_HANDLE] + #endif 0; } From 4794d07fe635a87b959db3383fd01d081a65c937 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 16 Jan 2021 14:13:37 +0800 Subject: [PATCH 0547/4345] net: add inline function skb_csum_is_sctp [ Upstream commit fa82117010430aff2ce86400f7328f55a31b48a6 ] This patch is to define a inline function skb_csum_is_sctp(), and also replace all places where it checks if it's a SCTP CSUM skb. This function would be used later in many networking drivers in the following patches. Suggested-by: Alexander Duyck Signed-off-by: Xin Long Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski Stable-dep-of: db0b124f02ba ("igc: Enhance Qbv scheduling by using first flag bit") Signed-off-by: Sasha Levin --- drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 2 +- include/linux/skbuff.h | 5 +++++ net/core/dev.c | 2 +- 3 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 46dbb49f837c..5463c8b8e43c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -986,7 +986,7 @@ static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb) stats->vlan_inserted++; } - if (skb->csum_not_inet) + if (skb_csum_is_sctp(skb)) stats->crc32_csum++; else stats->csum++; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 521d66ec8d80..39636fe7e8f0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4620,6 +4620,11 @@ static inline void skb_reset_redirect(struct sk_buff *skb) #endif } +static inline bool skb_csum_is_sctp(struct sk_buff *skb) +{ + return skb->csum_not_inet; +} + static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { diff --git a/net/core/dev.c b/net/core/dev.c index 34b5aab42b91..a421c54331ea 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3631,7 +3631,7 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features) { - if (unlikely(skb->csum_not_inet)) + if (unlikely(skb_csum_is_sctp(skb))) return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); From ae5d96bae3cce68aca11571963ee509586c949f8 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 16 Jan 2021 14:13:40 +0800 Subject: [PATCH 0548/4345] net: igc: use skb_csum_is_sctp instead of protocol check [ Upstream commit 609d29a9d2429a840a2f1f44e77b71d58e3e9a33 ] Using skb_csum_is_sctp is a easier way to validate it's a SCTP CRC checksum offload packet, and yet it also makes igc support SCTP CRC checksum offload for UDP and GRE encapped packets, just as it does in igb driver. Signed-off-by: Xin Long Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski Stable-dep-of: db0b124f02ba ("igc: Enhance Qbv scheduling by using first flag bit") Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index e7ffe63925fd..f438cdf83e55 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -954,15 +954,6 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, } } -static inline bool igc_ipv6_csum_is_sctp(struct sk_buff *skb) -{ - unsigned int offset = 0; - - ipv6_find_hdr(skb, &offset, IPPROTO_SCTP, NULL, NULL); - - return offset == skb_checksum_start_offset(skb); -} - static void igc_tx_csum(struct igc_ring *tx_ring, struct igc_tx_buffer *first) { struct sk_buff *skb = first->skb; @@ -985,10 +976,7 @@ csum_failed: break; case offsetof(struct sctphdr, checksum): /* validate that this is actually an SCTP request */ - if ((first->protocol == htons(ETH_P_IP) && - (ip_hdr(skb)->protocol == IPPROTO_SCTP)) || - (first->protocol == htons(ETH_P_IPV6) && - igc_ipv6_csum_is_sctp(skb))) { + if (skb_csum_is_sctp(skb)) { type_tucmd = IGC_ADVTXD_TUCMD_L4T_SCTP; break; } From a8f9698a05b5fb17d517d0777b8a14ffe88c6ecb Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 10 Mar 2021 16:50:44 +0200 Subject: [PATCH 0549/4345] net: add a helper to avoid issues with HW TX timestamping and SO_TXTIME [ Upstream commit 847cbfc014adafeac401e19e349b0fd524f201c3 ] As explained in commit 29d98f54a4fe ("net: enetc: allow hardware timestamping on TX queues with tc-etf enabled"), hardware TX timestamping requires an skb with skb->tstamp = 0. When a packet is sent with SO_TXTIME, the skb->skb_mstamp_ns corrupts the value of skb->tstamp, so the drivers need to explicitly reset skb->tstamp to zero after consuming the TX time. Create a helper named skb_txtime_consumed() which does just that. All drivers which offload TC_SETUP_QDISC_ETF should implement it, and it would make it easier to assess during review whether they do the right thing in order to be compatible with hardware timestamping or not. Suggested-by: Vinicius Costa Gomes Signed-off-by: Vladimir Oltean Acked-by: Vinicius Costa Gomes Signed-off-by: David S. Miller Stable-dep-of: db0b124f02ba ("igc: Enhance Qbv scheduling by using first flag bit") Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/enetc/enetc.c | 8 ++------ drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- include/net/pkt_sched.h | 9 +++++++++ 4 files changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 975762ccb66f..5f9603d4c049 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -5,6 +5,7 @@ #include #include #include +#include /* ENETC overhead: optional extension BD + 1 BD gap */ #define ENETC_TXBDS_NEEDED(val) ((val) + 2) @@ -384,12 +385,7 @@ static void enetc_tstamp_tx(struct sk_buff *skb, u64 tstamp) if (skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) { memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ns_to_ktime(tstamp); - /* Ensure skb_mstamp_ns, which might have been populated with - * the txtime, is not mistaken for a software timestamp, - * because this will prevent the dispatch of our hardware - * timestamp to the socket. - */ - skb->tstamp = ktime_set(0, 0); + skb_txtime_consumed(skb); skb_tstamp_tx(skb, &shhwtstamps); } } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index f24f1a8ec2fb..2646601c3487 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -5879,7 +5879,7 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, */ if (tx_ring->launchtime_enable) { ts = ktime_to_timespec64(first->skb->tstamp); - first->skb->tstamp = ktime_set(0, 0); + skb_txtime_consumed(first->skb); context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32); } else { context_desc->seqnum_seed = 0; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index f438cdf83e55..48192594d3d7 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -946,7 +946,7 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, struct igc_adapter *adapter = netdev_priv(tx_ring->netdev); ktime_t txtime = first->skb->tstamp; - first->skb->tstamp = ktime_set(0, 0); + skb_txtime_consumed(first->skb); context_desc->launch_time = igc_tx_launchtime(adapter, txtime); } else { diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 7e58b4470570..50d5ffbad473 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -179,4 +179,13 @@ struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload *offload); void taprio_offload_free(struct tc_taprio_qopt_offload *offload); +/* Ensure skb_mstamp_ns, which might have been populated with the txtime, is + * not mistaken for a software timestamp, because this will otherwise prevent + * the dispatch of hardware timestamps to the socket. + */ +static inline void skb_txtime_consumed(struct sk_buff *skb) +{ + skb->tstamp = ktime_set(0, 0); +} + #endif From 413fe82420aa6b5b89fbf3aac006ce191619450c Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Fri, 9 Dec 2022 12:15:17 +0800 Subject: [PATCH 0550/4345] igc: Enhance Qbv scheduling by using first flag bit [ Upstream commit db0b124f02ba68de6517ac303d431af220ccfe9f ] The I225 hardware has a limitation that packets can only be scheduled in the [0, cycle-time] interval. So, scheduling a packet to the start of the next cycle doesn't usually work. To overcome this, we use the Transmit Descriptor first flag to indicates that a packet should be the first packet (from a queue) in a cycle according to the section 7.5.2.9.3.4 The First Packet on Each QBV Cycle in Intel Discrete I225/6 User Manual. But this only works if there was any packet from that queue during the current cycle, to avoid this issue, we issue an empty packet if that's not the case. Also require one more descriptor to be available, to take into account the empty packet that might be issued. Test Setup: Talker: Use l2_tai to generate the launchtime into packet load. Listener: Use timedump.c to compute the delta between packet arrival and LaunchTime packet payload. Test Result: Before: 1666000610127300000,1666000610127300096,96,621273 1666000610127400000,1666000610127400192,192,621274 1666000610127500000,1666000610127500032,32,621275 1666000610127600000,1666000610127600128,128,621276 1666000610127700000,1666000610127700224,224,621277 1666000610127800000,1666000610127800064,64,621278 1666000610127900000,1666000610127900160,160,621279 1666000610128000000,1666000610128000000,0,621280 1666000610128100000,1666000610128100096,96,621281 1666000610128200000,1666000610128200192,192,621282 1666000610128300000,1666000610128300032,32,621283 1666000610128400000,1666000610128301056,-98944,621284 1666000610128500000,1666000610128302080,-197920,621285 1666000610128600000,1666000610128302848,-297152,621286 1666000610128700000,1666000610128303872,-396128,621287 1666000610128800000,1666000610128304896,-495104,621288 1666000610128900000,1666000610128305664,-594336,621289 1666000610129000000,1666000610128306688,-693312,621290 1666000610129100000,1666000610128307712,-792288,621291 1666000610129200000,1666000610128308480,-891520,621292 1666000610129300000,1666000610128309504,-990496,621293 1666000610129400000,1666000610128310528,-1089472,621294 1666000610129500000,1666000610128311296,-1188704,621295 1666000610129600000,1666000610128312320,-1287680,621296 1666000610129700000,1666000610128313344,-1386656,621297 1666000610129800000,1666000610128314112,-1485888,621298 1666000610129900000,1666000610128315136,-1584864,621299 1666000610130000000,1666000610128316160,-1683840,621300 1666000610130100000,1666000610128316928,-1783072,621301 1666000610130200000,1666000610128317952,-1882048,621302 1666000610130300000,1666000610128318976,-1981024,621303 1666000610130400000,1666000610128319744,-2080256,621304 1666000610130500000,1666000610128320768,-2179232,621305 1666000610130600000,1666000610128321792,-2278208,621306 1666000610130700000,1666000610128322816,-2377184,621307 1666000610130800000,1666000610128323584,-2476416,621308 1666000610130900000,1666000610128324608,-2575392,621309 1666000610131000000,1666000610128325632,-2674368,621310 1666000610131100000,1666000610128326400,-2773600,621311 1666000610131200000,1666000610128327424,-2872576,621312 1666000610131300000,1666000610128328448,-2971552,621313 1666000610131400000,1666000610128329216,-3070784,621314 1666000610131500000,1666000610131500032,32,621315 1666000610131600000,1666000610131600128,128,621316 1666000610131700000,1666000610131700224,224,621317 After: 1666073510646200000,1666073510646200064,64,2676462 1666073510646300000,1666073510646300160,160,2676463 1666073510646400000,1666073510646400256,256,2676464 1666073510646500000,1666073510646500096,96,2676465 1666073510646600000,1666073510646600192,192,2676466 1666073510646700000,1666073510646700032,32,2676467 1666073510646800000,1666073510646800128,128,2676468 1666073510646900000,1666073510646900224,224,2676469 1666073510647000000,1666073510647000064,64,2676470 1666073510647100000,1666073510647100160,160,2676471 1666073510647200000,1666073510647200256,256,2676472 1666073510647300000,1666073510647300096,96,2676473 1666073510647400000,1666073510647400192,192,2676474 1666073510647500000,1666073510647500032,32,2676475 1666073510647600000,1666073510647600128,128,2676476 1666073510647700000,1666073510647700224,224,2676477 1666073510647800000,1666073510647800064,64,2676478 1666073510647900000,1666073510647900160,160,2676479 1666073510648000000,1666073510648000000,0,2676480 1666073510648100000,1666073510648100096,96,2676481 1666073510648200000,1666073510648200192,192,2676482 1666073510648300000,1666073510648300032,32,2676483 1666073510648400000,1666073510648400128,128,2676484 1666073510648500000,1666073510648500224,224,2676485 1666073510648600000,1666073510648600064,64,2676486 1666073510648700000,1666073510648700160,160,2676487 1666073510648800000,1666073510648800000,0,2676488 1666073510648900000,1666073510648900096,96,2676489 1666073510649000000,1666073510649000192,192,2676490 1666073510649100000,1666073510649100032,32,2676491 1666073510649200000,1666073510649200128,128,2676492 1666073510649300000,1666073510649300224,224,2676493 1666073510649400000,1666073510649400064,64,2676494 1666073510649500000,1666073510649500160,160,2676495 1666073510649600000,1666073510649600000,0,2676496 1666073510649700000,1666073510649700096,96,2676497 1666073510649800000,1666073510649800192,192,2676498 1666073510649900000,1666073510649900032,32,2676499 1666073510650000000,1666073510650000128,128,2676500 Fixes: 82faa9b79950 ("igc: Add support for ETF offloading") Signed-off-by: Vinicius Costa Gomes Co-developed-by: Aravindhan Gunasekaran Signed-off-by: Aravindhan Gunasekaran Co-developed-by: Muhammad Husaini Zulkifli Signed-off-by: Muhammad Husaini Zulkifli Signed-off-by: Malli C Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc.h | 2 + drivers/net/ethernet/intel/igc/igc_defines.h | 2 + drivers/net/ethernet/intel/igc/igc_main.c | 176 ++++++++++++++++--- 3 files changed, 151 insertions(+), 29 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index a97bf7a5f1d6..970dd878d8a7 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -87,6 +87,8 @@ struct igc_ring { u8 queue_index; /* logical index of the ring*/ u8 reg_idx; /* physical index of the ring */ bool launchtime_enable; /* true if LaunchTime is enabled */ + ktime_t last_tx_cycle; /* end of the cycle with a launchtime transmission */ + ktime_t last_ff_cycle; /* Last cycle with an active first flag */ u32 start_time; u32 end_time; diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 32f5fd684139..352b50d3881d 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -278,6 +278,8 @@ #define IGC_ADVTXD_L4LEN_SHIFT 8 /* Adv ctxt L4LEN shift */ #define IGC_ADVTXD_MSS_SHIFT 16 /* Adv ctxt MSS shift */ +#define IGC_ADVTXD_TSN_CNTX_FIRST 0x00000080 + /* Transmit Control */ #define IGC_TCTL_EN 0x00000002 /* enable Tx */ #define IGC_TCTL_PSP 0x00000008 /* pad short packets */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 48192594d3d7..f4082ea7beaa 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -898,25 +898,118 @@ static int igc_write_mc_addr_list(struct net_device *netdev) return netdev_mc_count(netdev); } -static __le32 igc_tx_launchtime(struct igc_adapter *adapter, ktime_t txtime) +static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime, + bool *first_flag, bool *insert_empty) { + struct igc_adapter *adapter = netdev_priv(ring->netdev); ktime_t cycle_time = adapter->cycle_time; ktime_t base_time = adapter->base_time; + ktime_t now = ktime_get_clocktai(); + ktime_t baset_est, end_of_cycle; u32 launchtime; + s64 n; - /* FIXME: when using ETF together with taprio, we may have a - * case where 'delta' is larger than the cycle_time, this may - * cause problems if we don't read the current value of - * IGC_BASET, as the value writen into the launchtime - * descriptor field may be misinterpreted. + n = div64_s64(ktime_sub_ns(now, base_time), cycle_time); + + baset_est = ktime_add_ns(base_time, cycle_time * (n)); + end_of_cycle = ktime_add_ns(baset_est, cycle_time); + + if (ktime_compare(txtime, end_of_cycle) >= 0) { + if (baset_est != ring->last_ff_cycle) { + *first_flag = true; + ring->last_ff_cycle = baset_est; + + if (ktime_compare(txtime, ring->last_tx_cycle) > 0) + *insert_empty = true; + } + } + + /* Introducing a window at end of cycle on which packets + * potentially not honor launchtime. Window of 5us chosen + * considering software update the tail pointer and packets + * are dma'ed to packet buffer. */ - div_s64_rem(ktime_sub_ns(txtime, base_time), cycle_time, &launchtime); + if ((ktime_sub_ns(end_of_cycle, now) < 5 * NSEC_PER_USEC)) + netdev_warn(ring->netdev, "Packet with txtime=%llu may not be honoured\n", + txtime); + + ring->last_tx_cycle = end_of_cycle; + + launchtime = ktime_sub_ns(txtime, baset_est); + if (launchtime > 0) + div_s64_rem(launchtime, cycle_time, &launchtime); + else + launchtime = 0; return cpu_to_le32(launchtime); } +static int igc_init_empty_frame(struct igc_ring *ring, + struct igc_tx_buffer *buffer, + struct sk_buff *skb) +{ + unsigned int size; + dma_addr_t dma; + + size = skb_headlen(skb); + + dma = dma_map_single(ring->dev, skb->data, size, DMA_TO_DEVICE); + if (dma_mapping_error(ring->dev, dma)) { + netdev_err_once(ring->netdev, "Failed to map DMA for TX\n"); + return -ENOMEM; + } + + buffer->skb = skb; + buffer->protocol = 0; + buffer->bytecount = skb->len; + buffer->gso_segs = 1; + buffer->time_stamp = jiffies; + dma_unmap_len_set(buffer, len, skb->len); + dma_unmap_addr_set(buffer, dma, dma); + + return 0; +} + +static int igc_init_tx_empty_descriptor(struct igc_ring *ring, + struct sk_buff *skb, + struct igc_tx_buffer *first) +{ + union igc_adv_tx_desc *desc; + u32 cmd_type, olinfo_status; + int err; + + if (!igc_desc_unused(ring)) + return -EBUSY; + + err = igc_init_empty_frame(ring, first, skb); + if (err) + return err; + + cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | + IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | + first->bytecount; + olinfo_status = first->bytecount << IGC_ADVTXD_PAYLEN_SHIFT; + + desc = IGC_TX_DESC(ring, ring->next_to_use); + desc->read.cmd_type_len = cpu_to_le32(cmd_type); + desc->read.olinfo_status = cpu_to_le32(olinfo_status); + desc->read.buffer_addr = cpu_to_le64(dma_unmap_addr(first, dma)); + + netdev_tx_sent_queue(txring_txq(ring), skb->len); + + first->next_to_watch = desc; + + ring->next_to_use++; + if (ring->next_to_use == ring->count) + ring->next_to_use = 0; + + return 0; +} + +#define IGC_EMPTY_FRAME_SIZE 60 + static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, - struct igc_tx_buffer *first, + __le32 launch_time, bool first_flag, u32 vlan_macip_lens, u32 type_tucmd, u32 mss_l4len_idx) { @@ -935,26 +1028,17 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, if (test_bit(IGC_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) mss_l4len_idx |= tx_ring->reg_idx << 4; + if (first_flag) + mss_l4len_idx |= IGC_ADVTXD_TSN_CNTX_FIRST; + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); - - /* We assume there is always a valid Tx time available. Invalid times - * should have been handled by the upper layers. - */ - if (tx_ring->launchtime_enable) { - struct igc_adapter *adapter = netdev_priv(tx_ring->netdev); - ktime_t txtime = first->skb->tstamp; - - skb_txtime_consumed(first->skb); - context_desc->launch_time = igc_tx_launchtime(adapter, - txtime); - } else { - context_desc->launch_time = 0; - } + context_desc->launch_time = launch_time; } -static void igc_tx_csum(struct igc_ring *tx_ring, struct igc_tx_buffer *first) +static void igc_tx_csum(struct igc_ring *tx_ring, struct igc_tx_buffer *first, + __le32 launch_time, bool first_flag) { struct sk_buff *skb = first->skb; u32 vlan_macip_lens = 0; @@ -994,7 +1078,8 @@ no_csum: vlan_macip_lens |= skb_network_offset(skb) << IGC_ADVTXD_MACLEN_SHIFT; vlan_macip_lens |= first->tx_flags & IGC_TX_FLAGS_VLAN_MASK; - igc_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, type_tucmd, 0); + igc_tx_ctxtdesc(tx_ring, launch_time, first_flag, + vlan_macip_lens, type_tucmd, 0); } static int __igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size) @@ -1218,6 +1303,7 @@ dma_error: static int igc_tso(struct igc_ring *tx_ring, struct igc_tx_buffer *first, + __le32 launch_time, bool first_flag, u8 *hdr_len) { u32 vlan_macip_lens, type_tucmd, mss_l4len_idx; @@ -1304,8 +1390,8 @@ static int igc_tso(struct igc_ring *tx_ring, vlan_macip_lens |= (ip.hdr - skb->data) << IGC_ADVTXD_MACLEN_SHIFT; vlan_macip_lens |= first->tx_flags & IGC_TX_FLAGS_VLAN_MASK; - igc_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, - type_tucmd, mss_l4len_idx); + igc_tx_ctxtdesc(tx_ring, launch_time, first_flag, + vlan_macip_lens, type_tucmd, mss_l4len_idx); return 1; } @@ -1313,11 +1399,14 @@ static int igc_tso(struct igc_ring *tx_ring, static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, struct igc_ring *tx_ring) { + bool first_flag = false, insert_empty = false; u16 count = TXD_USE_COUNT(skb_headlen(skb)); __be16 protocol = vlan_get_protocol(skb); struct igc_tx_buffer *first; + __le32 launch_time = 0; u32 tx_flags = 0; unsigned short f; + ktime_t txtime; u8 hdr_len = 0; int tso = 0; @@ -1331,11 +1420,40 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, count += TXD_USE_COUNT(skb_frag_size( &skb_shinfo(skb)->frags[f])); - if (igc_maybe_stop_tx(tx_ring, count + 3)) { + if (igc_maybe_stop_tx(tx_ring, count + 5)) { /* this is a hard error */ return NETDEV_TX_BUSY; } + if (!tx_ring->launchtime_enable) + goto done; + + txtime = skb->tstamp; + skb->tstamp = ktime_set(0, 0); + launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty); + + if (insert_empty) { + struct igc_tx_buffer *empty_info; + struct sk_buff *empty; + void *data; + + empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); + if (!empty) + goto done; + + data = skb_put(empty, IGC_EMPTY_FRAME_SIZE); + memset(data, 0, IGC_EMPTY_FRAME_SIZE); + + igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); + + if (igc_init_tx_empty_descriptor(tx_ring, + empty, + empty_info) < 0) + dev_kfree_skb_any(empty); + } + +done: /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; first->skb = skb; @@ -1366,11 +1484,11 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, first->tx_flags = tx_flags; first->protocol = protocol; - tso = igc_tso(tx_ring, first, &hdr_len); + tso = igc_tso(tx_ring, first, launch_time, first_flag, &hdr_len); if (tso < 0) goto out_drop; else if (!tso) - igc_tx_csum(tx_ring, first); + igc_tx_csum(tx_ring, first, launch_time, first_flag); igc_tx_map(tx_ring, first, hdr_len); From a0e2295c2aed508365a2343dafe392fd0d3d57ae Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Fri, 9 Dec 2022 12:15:18 +0800 Subject: [PATCH 0551/4345] igc: Use strict cycles for Qbv scheduling [ Upstream commit d8f45be01dd9381065a3778a579385249ed011dc ] Configuring strict cycle mode in the controller forces more well behaved transmissions when taprio is offloaded. When set this strict_cycle and strict_end, transmission is not enabled if the whole packet cannot be completed before end of the Qbv cycle. Fixes: 82faa9b79950 ("igc: Add support for ETF offloading") Signed-off-by: Vinicius Costa Gomes Signed-off-by: Aravindhan Gunasekaran Signed-off-by: Muhammad Husaini Zulkifli Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_tsn.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 174103c4bea6..2d4db2a547b2 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -92,15 +92,8 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_STQT(i), ring->start_time); wr32(IGC_ENDQT(i), ring->end_time); - if (adapter->base_time) { - /* If we have a base_time we are in "taprio" - * mode and we need to be strict about the - * cycles: only transmit a packet if it can be - * completed during that cycle. - */ - txqctl |= IGC_TXQCTL_STRICT_CYCLE | - IGC_TXQCTL_STRICT_END; - } + txqctl |= IGC_TXQCTL_STRICT_CYCLE | + IGC_TXQCTL_STRICT_END; if (ring->launchtime_enable) txqctl |= IGC_TXQCTL_QUEUE_MODE_LAUNCHT; From 3f2a944c23e869017216355d01ea8940ac7dd4a2 Mon Sep 17 00:00:00 2001 From: Muhammad Husaini Zulkifli Date: Fri, 9 Dec 2022 12:15:19 +0800 Subject: [PATCH 0552/4345] igc: Add checking for basetime less than zero [ Upstream commit 3b61764fb49a6e147ac90d71dccdddc9d5508ba1 ] Using the tc qdisc command, the user can set basetime to any value. Checking should be done on the driver's side to prevent registering basetime values that are less than zero. Fixes: ec50a9d437f0 ("igc: Add support for taprio offloading") Signed-off-by: Muhammad Husaini Zulkifli Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index f4082ea7beaa..45069dc0ccc6 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4912,6 +4912,9 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, return 0; } + if (qopt->base_time < 0) + return -ERANGE; + if (adapter->base_time) return -EALREADY; From b48d3db89161ac20ff4f002bb9e8837b2acd6001 Mon Sep 17 00:00:00 2001 From: Tan Tee Min Date: Fri, 9 Dec 2022 12:15:21 +0800 Subject: [PATCH 0553/4345] igc: recalculate Qbv end_time by considering cycle time [ Upstream commit 6d05251d537a4d3835959a8cdd8cbbbdcdc0c904 ] Qbv users can specify a cycle time that is not equal to the total GCL intervals. Hence, recalculation is necessary here to exclude the time interval that exceeds the cycle time. As those GCL which exceeds the cycle time will be truncated. According to IEEE Std. 802.1Q-2018 section 8.6.9.2, once the end of the list is reached, it will switch to the END_OF_CYCLE state and leave the gates in the same state until the next cycle is started. Fixes: ec50a9d437f0 ("igc: Add support for taprio offloading") Signed-off-by: Tan Tee Min Signed-off-by: Muhammad Husaini Zulkifli Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 45069dc0ccc6..94a608585f71 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4933,6 +4933,21 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, end_time += e->interval; + /* If any of the conditions below are true, we need to manually + * control the end time of the cycle. + * 1. Qbv users can specify a cycle time that is not equal + * to the total GCL intervals. Hence, recalculation is + * necessary here to exclude the time interval that + * exceeds the cycle time. + * 2. According to IEEE Std. 802.1Q-2018 section 8.6.9.2, + * once the end of the list is reached, it will switch + * to the END_OF_CYCLE state and leave the gates in the + * same state until the next cycle is started. + */ + if (end_time > adapter->cycle_time || + n + 1 == qopt->num_entries) + end_time = adapter->cycle_time; + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; From edb995b5ec32a1dfcd5ce44aa92644c07fc80afb Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Mon, 6 Jun 2022 11:27:47 +0200 Subject: [PATCH 0554/4345] igc: Lift TAPRIO schedule restriction [ Upstream commit a5fd39464a4081ce11c801d7e20c4551ba7cb983 ] Add support for Qbv schedules where one queue stays open in consecutive entries. Currently that's not supported. Example schedule: |tc qdisc replace dev ${INTERFACE} handle 100 parent root taprio num_tc 3 \ | map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 \ | queues 1@0 1@1 2@2 \ | base-time ${BASETIME} \ | sched-entry S 0x01 300000 \ # Stream High/Low | sched-entry S 0x06 500000 \ # Management and Best Effort | sched-entry S 0x04 200000 \ # Best Effort | flags 0x02 Signed-off-by: Kurt Kanzenbach Reviewed-by: Vinicius Costa Gomes Tested-by: Naama Meir Signed-off-by: Tony Nguyen Stable-dep-of: 72abeedd8398 ("igc: Set Qbv start_time and end_time to end_time if not being configured in GCL") Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 94a608585f71..9420a169780c 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4862,9 +4862,10 @@ static bool validate_schedule(struct igc_adapter *adapter, return false; for (n = 0; n < qopt->num_entries; n++) { - const struct tc_taprio_sched_entry *e; + const struct tc_taprio_sched_entry *e, *prev; int i; + prev = n ? &qopt->entries[n - 1] : NULL; e = &qopt->entries[n]; /* i225 only supports "global" frame preemption @@ -4877,7 +4878,12 @@ static bool validate_schedule(struct igc_adapter *adapter, if (e->gate_mask & BIT(i)) queue_uses[i]++; - if (queue_uses[i] > 1) + /* There are limitations: A single queue cannot be + * opened and closed multiple times per cycle unless the + * gate stays open. Check for it. + */ + if (queue_uses[i] > 1 && + !(prev->gate_mask & BIT(i))) return false; } } @@ -4904,6 +4910,7 @@ static int igc_tsn_enable_launchtime(struct igc_adapter *adapter, static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct tc_taprio_qopt_offload *qopt) { + bool queue_configured[IGC_MAX_TX_QUEUES] = { }; u32 start_time = 0, end_time = 0; size_t n; @@ -4924,9 +4931,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; - /* FIXME: be a little smarter about cases when the gate for a - * queue stays open for more than one entry. - */ for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; int i; @@ -4954,8 +4958,15 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!(e->gate_mask & BIT(i))) continue; - ring->start_time = start_time; + /* Check whether a queue stays open for more than one + * entry. If so, keep the start and advance the end + * time. + */ + if (!queue_configured[i]) + ring->start_time = start_time; ring->end_time = end_time; + + queue_configured[i] = true; } start_time += e->interval; From 1e2a27dab1e5aefeeff963ace5ffb066ebf82a20 Mon Sep 17 00:00:00 2001 From: Tan Tee Min Date: Fri, 9 Dec 2022 12:15:22 +0800 Subject: [PATCH 0555/4345] igc: Set Qbv start_time and end_time to end_time if not being configured in GCL [ Upstream commit 72abeedd83982c1bc6023f631e412db78374d9b4 ] The default setting of end_time minus start_time is whole 1 second. Thus, if it's not being configured in any GCL entry then it will be staying at original 1 second. This patch is changing the start_time and end_time to be end_time as if setting zero will be having weird HW behavior where the gate will not be fully closed. Fixes: ec50a9d437f0 ("igc: Add support for taprio offloading") Signed-off-by: Tan Tee Min Signed-off-by: Muhammad Husaini Zulkifli Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9420a169780c..1a0aae7b128d 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4913,6 +4913,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, bool queue_configured[IGC_MAX_TX_QUEUES] = { }; u32 start_time = 0, end_time = 0; size_t n; + int i; if (!qopt->enable) { adapter->base_time = 0; @@ -4933,7 +4934,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; - int i; end_time += e->interval; @@ -4972,6 +4972,18 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, start_time += e->interval; } + /* Check whether a queue gets configured. + * If not, set the start and end time to be end time. + */ + for (i = 0; i < adapter->num_tx_queues; i++) { + if (!queue_configured[i]) { + struct igc_ring *ring = adapter->tx_ring[i]; + + ring->start_time = end_time; + ring->end_time = end_time; + } + } + return 0; } From 57ce1a36c060e480e1b2be82c4e27fb56619326c Mon Sep 17 00:00:00 2001 From: GUO Zihua Date: Tue, 22 Nov 2022 16:50:46 +0800 Subject: [PATCH 0556/4345] rtc: mxc_v2: Add missing clk_disable_unprepare() [ Upstream commit 55d5a86618d3b1a768bce01882b74cbbd2651975 ] The call to clk_disable_unprepare() is left out in the error handling of devm_rtc_allocate_device. Add it back. Fixes: 5490a1e018a4 ("rtc: mxc_v2: fix possible race condition") Signed-off-by: GUO Zihua Link: https://lore.kernel.org/r/20221122085046.21689-1-guozihua@huawei.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-mxc_v2.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-mxc_v2.c b/drivers/rtc/rtc-mxc_v2.c index d349cef09cb7..48595b00ebb3 100644 --- a/drivers/rtc/rtc-mxc_v2.c +++ b/drivers/rtc/rtc-mxc_v2.c @@ -337,8 +337,10 @@ static int mxc_rtc_probe(struct platform_device *pdev) } pdata->rtc = devm_rtc_allocate_device(&pdev->dev); - if (IS_ERR(pdata->rtc)) + if (IS_ERR(pdata->rtc)) { + clk_disable_unprepare(pdata->clk); return PTR_ERR(pdata->rtc); + } pdata->rtc->ops = &mxc_rtc_ops; pdata->rtc->range_max = U32_MAX; From ea14220031b333d3c620f7e401a308b3a6896081 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 14 Dec 2022 18:01:01 -0800 Subject: [PATCH 0557/4345] selftests: devlink: fix the fd redirect in dummy_reporter_test [ Upstream commit 2fc60e2ff972d3dca836bff0b08cbe503c4ca1ce ] $number + > bash means redirect FD $number, e.g. commonly used 2> redirects stderr (fd 2). The test uses 8192> to write the number 8192 to a file, this results in: ./devlink.sh: line 499: 8192: Bad file descriptor Oddly the test also papers over this issue by checking for failure (expecting an error rather than success) so it passes, anyway. Fixes: ff18176ad806 ("selftests: Add a test of large binary to devlink health test") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- tools/testing/selftests/drivers/net/netdevsim/devlink.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index 40909c254365..16d2de18591d 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -495,8 +495,8 @@ dummy_reporter_test() check_reporter_info dummy healthy 3 3 10 true - echo 8192> $DEBUGFS_DIR/health/binary_len - check_fail $? "Failed set dummy reporter binary len to 8192" + echo 8192 > $DEBUGFS_DIR/health/binary_len + check_err $? "Failed set dummy reporter binary len to 8192" local dump=$(devlink health dump show $DL_HANDLE reporter dummy -j) check_err $? "Failed show dump of dummy reporter" From 6736b61ecf230dd656464de0f514bdeadb384f20 Mon Sep 17 00:00:00 2001 From: Eelco Chaudron Date: Thu, 15 Dec 2022 15:46:33 +0100 Subject: [PATCH 0558/4345] openvswitch: Fix flow lookup to use unmasked key [ Upstream commit 68bb10101e6b0a6bb44e9c908ef795fc4af99eae ] The commit mentioned below causes the ovs_flow_tbl_lookup() function to be called with the masked key. However, it's supposed to be called with the unmasked key. This due to the fact that the datapath supports installing wider flows, and OVS relies on this behavior. For example if ipv4(src=1.1.1.1/192.0.0.0, dst=1.1.1.2/192.0.0.0) exists, a wider flow (smaller mask) of ipv4(src=192.1.1.1/128.0.0.0,dst=192.1.1.2/ 128.0.0.0) is allowed to be added. However, if we try to add a wildcard rule, the installation fails: $ ovs-appctl dpctl/add-flow system@myDP "in_port(1),eth_type(0x0800), \ ipv4(src=1.1.1.1/192.0.0.0,dst=1.1.1.2/192.0.0.0,frag=no)" 2 $ ovs-appctl dpctl/add-flow system@myDP "in_port(1),eth_type(0x0800), \ ipv4(src=192.1.1.1/0.0.0.0,dst=49.1.1.2/0.0.0.0,frag=no)" 2 ovs-vswitchd: updating flow table (File exists) The reason is that the key used to determine if the flow is already present in the system uses the original key ANDed with the mask. This results in the IP address not being part of the (miniflow) key, i.e., being substituted with an all-zero value. When doing the actual lookup, this results in the key wrongfully matching the first flow, and therefore the flow does not get installed. This change reverses the commit below, but rather than having the key on the stack, it's allocated. Fixes: 190aa3e77880 ("openvswitch: Fix Frame-size larger than 1024 bytes warning.") Signed-off-by: Eelco Chaudron Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/openvswitch/datapath.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 7ed97dc0b561..435f7f1be614 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -933,6 +933,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) struct sw_flow_mask mask; struct sk_buff *reply; struct datapath *dp; + struct sw_flow_key *key; struct sw_flow_actions *acts; struct sw_flow_match match; u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); @@ -960,24 +961,26 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) } /* Extract key. */ - ovs_match_init(&match, &new_flow->key, false, &mask); + key = kzalloc(sizeof(*key), GFP_KERNEL); + if (!key) { + error = -ENOMEM; + goto err_kfree_key; + } + + ovs_match_init(&match, key, false, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) goto err_kfree_flow; + ovs_flow_mask_key(&new_flow->key, key, true, &mask); + /* Extract flow identifier. */ error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], - &new_flow->key, log); + key, log); if (error) goto err_kfree_flow; - /* unmasked key is needed to match when ufid is not used. */ - if (ovs_identifier_is_key(&new_flow->id)) - match.key = new_flow->id.unmasked_key; - - ovs_flow_mask_key(&new_flow->key, &new_flow->key, true, &mask); - /* Validate actions. */ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, &acts, log); @@ -1004,7 +1007,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) if (ovs_identifier_is_ufid(&new_flow->id)) flow = ovs_flow_tbl_lookup_ufid(&dp->table, &new_flow->id); if (!flow) - flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->key); + flow = ovs_flow_tbl_lookup(&dp->table, key); if (likely(!flow)) { rcu_assign_pointer(new_flow->sf_acts, acts); @@ -1074,6 +1077,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) if (reply) ovs_notify(&dp_flow_genl_family, reply, info); + + kfree(key); return 0; err_unlock_ovs: @@ -1083,6 +1088,8 @@ err_kfree_acts: ovs_nla_free_flow_actions(acts); err_kfree_flow: ovs_flow_free(new_flow, false); +err_kfree_key: + kfree(key); error: return error; } From 821be5a5ab09a40ba09cb5ba354f18cf7996fea0 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 14 Dec 2022 23:11:58 -0700 Subject: [PATCH 0559/4345] skbuff: Account for tail adjustment during pull operations [ Upstream commit 2d7afdcbc9d32423f177ee12b7c93783aea338fb ] Extending the tail can have some unexpected side effects if a program uses a helper like BPF_FUNC_skb_pull_data to read partial content beyond the head skb headlen when all the skbs in the gso frag_list are linear with no head_frag - kernel BUG at net/core/skbuff.c:4219! pc : skb_segment+0xcf4/0xd2c lr : skb_segment+0x63c/0xd2c Call trace: skb_segment+0xcf4/0xd2c __udp_gso_segment+0xa4/0x544 udp4_ufo_fragment+0x184/0x1c0 inet_gso_segment+0x16c/0x3a4 skb_mac_gso_segment+0xd4/0x1b0 __skb_gso_segment+0xcc/0x12c udp_rcv_segment+0x54/0x16c udp_queue_rcv_skb+0x78/0x144 udp_unicast_rcv_skb+0x8c/0xa4 __udp4_lib_rcv+0x490/0x68c udp_rcv+0x20/0x30 ip_protocol_deliver_rcu+0x1b0/0x33c ip_local_deliver+0xd8/0x1f0 ip_rcv+0x98/0x1a4 deliver_ptype_list_skb+0x98/0x1ec __netif_receive_skb_core+0x978/0xc60 Fix this by marking these skbs as GSO_DODGY so segmentation can handle the tail updates accordingly. Fixes: 3dcbdb134f32 ("net: gso: Fix skb_segment splat when splitting gso_size mangled skb having linear-headed frag_list") Signed-off-by: Sean Tranchetti Signed-off-by: Subash Abhinov Kasiviswanathan Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/1671084718-24796-1-git-send-email-quic_subashab@quicinc.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/skbuff.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 176bcbb07aab..2b12e0730b85 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2115,6 +2115,9 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) insp = list; } else { /* Eaten partially. */ + if (skb_is_gso(skb) && !list->head_frag && + skb_headlen(list)) + skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; if (skb_shared(list)) { /* Sucks! We need to fork list. :-( */ From a39b4de0804f9fe0ae911b359ffd4afe7d9d933b Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 10 Nov 2022 23:08:22 +0800 Subject: [PATCH 0560/4345] mailbox: zynq-ipi: fix error handling while device_register() fails [ Upstream commit a6792a0cdef0b1c2d77920246283a72537e60e94 ] If device_register() fails, it has two issues: 1. The name allocated by dev_set_name() is leaked. 2. The parent of device is not NULL, device_unregister() is called in zynqmp_ipi_free_mboxes(), it will lead a kernel crash because of removing not added device. Call put_device() to give up the reference, so the name is freed in kobject_cleanup(). Add device registered check in zynqmp_ipi_free_mboxes() to avoid null-ptr-deref. Fixes: 4981b82ba2ff ("mailbox: ZynqMP IPI mailbox controller") Signed-off-by: Yang Yingliang Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/zynqmp-ipi-mailbox.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c index f44079d62b1a..527204c6d5cd 100644 --- a/drivers/mailbox/zynqmp-ipi-mailbox.c +++ b/drivers/mailbox/zynqmp-ipi-mailbox.c @@ -493,6 +493,7 @@ static int zynqmp_ipi_mbox_probe(struct zynqmp_ipi_mbox *ipi_mbox, ret = device_register(&ipi_mbox->dev); if (ret) { dev_err(dev, "Failed to register ipi mbox dev.\n"); + put_device(&ipi_mbox->dev); return ret; } mdev = &ipi_mbox->dev; @@ -619,7 +620,8 @@ static void zynqmp_ipi_free_mboxes(struct zynqmp_ipi_pdata *pdata) ipi_mbox = &pdata->ipi_mboxes[i]; if (ipi_mbox->dev.parent) { mbox_controller_unregister(&ipi_mbox->mbox); - device_unregister(&ipi_mbox->dev); + if (device_is_registered(&ipi_mbox->dev)) + device_unregister(&ipi_mbox->dev); } } } From 5c544c7c6afab7ac7eb9aa8eefe49bbc45e95bd7 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 17 Dec 2022 14:17:07 -0800 Subject: [PATCH 0561/4345] net_sched: reject TCF_EM_SIMPLE case for complex ematch module [ Upstream commit 9cd3fd2054c3b3055163accbf2f31a4426f10317 ] When TCF_EM_SIMPLE was introduced, it is supposed to be convenient for ematch implementation: https://lore.kernel.org/all/20050105110048.GO26856@postel.suug.ch/ "You don't have to, providing a 32bit data chunk without TCF_EM_SIMPLE set will simply result in allocating & copy. It's an optimization, nothing more." So if an ematch module provides ops->datalen that means it wants a complex data structure (saved in its em->data) instead of a simple u32 value. We should simply reject such a combination, otherwise this u32 could be misinterpreted as a pointer. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-and-tested-by: syzbot+4caeae4c7103813598ae@syzkaller.appspotmail.com Reported-by: Jun Nie Cc: Jamal Hadi Salim Cc: Paolo Abeni Signed-off-by: Cong Wang Acked-by: Paolo Abeni Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/ematch.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sched/ematch.c b/net/sched/ematch.c index f885bea5b452..b7154103e9cd 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -255,6 +255,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * the value carried. */ if (em_hdr->flags & TCF_EM_SIMPLE) { + if (em->ops->datalen > 0) + goto errout; if (data_len < sizeof(u32)) goto errout; em->data = *(u32 *) data; From 3c973736909fd95548cea68616321c2e522fdeeb Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 15 Dec 2022 16:19:47 +0000 Subject: [PATCH 0562/4345] rxrpc: Fix missing unlock in rxrpc_do_sendmsg() [ Upstream commit 4feb2c44629e6f9b459b41a5a60491069d346a95 ] One of the error paths in rxrpc_do_sendmsg() doesn't unlock the call mutex before returning. Fix it to do this. Note that this still doesn't get rid of the checker warning: ../net/rxrpc/sendmsg.c:617:5: warning: context imbalance in 'rxrpc_do_sendmsg' - wrong count at exit I think the interplay between the socket lock and the call's user_mutex may be too complicated for checker to analyse, especially as rxrpc_new_client_call_for_sendmsg(), which it calls, returns with the call's user_mutex if successful but unconditionally drops the socket lock. Fixes: e754eba685aa ("rxrpc: Provide a cmsg to specify the amount of Tx data for a call") Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/rxrpc/sendmsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index eef3c14fd1c1..a670553159ab 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -733,7 +733,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (call->tx_total_len != -1 || call->tx_pending || call->tx_top != 0) - goto error_put; + goto out_put_unlock; call->tx_total_len = p.call.tx_total_len; } } From 7c3a20bfd23bdb0d92e8b9ac00feafd438adce61 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 18 Dec 2022 19:08:40 +0100 Subject: [PATCH 0563/4345] myri10ge: Fix an error handling path in myri10ge_probe() [ Upstream commit d83b950d44d2982c0e62e3d81b0f35ab09431008 ] Some memory allocated in myri10ge_probe_slices() is not released in the error handling path of myri10ge_probe(). Add the corresponding kfree(), as already done in the remove function. Fixes: 0dcffac1a329 ("myri10ge: add multislices support") Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 1664e9184c9c..5a1ed4818baa 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -3920,6 +3920,7 @@ abort_with_slices: myri10ge_free_slices(mgp); abort_with_firmware: + kfree(mgp->msix_vectors); myri10ge_dummy_rdma(mgp, 0); abort_with_ioremap: From 9062493811676ee0efe6c74d98f00ca38c4e17d4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 16 Dec 2022 16:29:17 +0000 Subject: [PATCH 0564/4345] net: stream: purge sk_error_queue in sk_stream_kill_queues() [ Upstream commit e0c8bccd40fc1c19e1d246c39bcf79e357e1ada3 ] Changheon Lee reported TCP socket leaks, with a nice repro. It seems we leak TCP sockets with the following sequence: 1) SOF_TIMESTAMPING_TX_ACK is enabled on the socket. Each ACK will cook an skb put in error queue, from __skb_tstamp_tx(). __skb_tstamp_tx() is using skb_clone(), unless SOF_TIMESTAMPING_OPT_TSONLY was also requested. 2) If the application is also using MSG_ZEROCOPY, then we put in the error queue cloned skbs that had a struct ubuf_info attached to them. Whenever an struct ubuf_info is allocated, sock_zerocopy_alloc() does a sock_hold(). As long as the cloned skbs are still in sk_error_queue, socket refcount is kept elevated. 3) Application closes the socket, while error queue is not empty. Since tcp_close() no longer purges the socket error queue, we might end up with a TCP socket with at least one skb in error queue keeping the socket alive forever. This bug can be (ab)used to consume all kernel memory and freeze the host. We need to purge the error queue, with proper synchronization against concurrent writers. Fixes: 24bcbe1cc69f ("net: stream: don't purge sk_error_queue in sk_stream_kill_queues()") Reported-by: Changheon Lee Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/stream.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/core/stream.c b/net/core/stream.c index a61130504827..d7c5413d16d5 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -196,6 +196,12 @@ void sk_stream_kill_queues(struct sock *sk) /* First the read buffer. */ __skb_queue_purge(&sk->sk_receive_queue); + /* Next, the error queue. + * We need to use queue lock, because other threads might + * add packets to the queue without socket lock being held. + */ + skb_queue_purge(&sk->sk_error_queue); + /* Next, the write queue. */ WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); From 5a52380b8193cf8be6c4a6b94b86ef64ed80c0dc Mon Sep 17 00:00:00 2001 From: Zqiang Date: Thu, 13 Oct 2022 12:41:48 +0800 Subject: [PATCH 0565/4345] rcu: Fix __this_cpu_read() lockdep warning in rcu_force_quiescent_state() [ Upstream commit ceb1c8c9b8aa9199da46a0f29d2d5f08d9b44c15 ] Running rcutorture with non-zero fqs_duration module parameter in a kernel built with CONFIG_PREEMPTION=y results in the following splat: BUG: using __this_cpu_read() in preemptible [00000000] code: rcu_torture_fqs/398 caller is __this_cpu_preempt_check+0x13/0x20 CPU: 3 PID: 398 Comm: rcu_torture_fqs Not tainted 6.0.0-rc1-yoctodev-standard+ Call Trace: dump_stack_lvl+0x5b/0x86 dump_stack+0x10/0x16 check_preemption_disabled+0xe5/0xf0 __this_cpu_preempt_check+0x13/0x20 rcu_force_quiescent_state.part.0+0x1c/0x170 rcu_force_quiescent_state+0x1e/0x30 rcu_torture_fqs+0xca/0x160 ? rcu_torture_boost+0x430/0x430 kthread+0x192/0x1d0 ? kthread_complete_and_exit+0x30/0x30 ret_from_fork+0x22/0x30 The problem is that rcu_force_quiescent_state() uses __this_cpu_read() in preemptible code instead of the proper raw_cpu_read(). This commit therefore changes __this_cpu_read() to raw_cpu_read(). Signed-off-by: Zqiang Reviewed-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- kernel/rcu/tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b10d6bcea77d..3fe7c75c371b 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2650,7 +2650,7 @@ void rcu_force_quiescent_state(void) struct rcu_node *rnp_old = NULL; /* Funnel through hierarchy to reduce memory contention. */ - rnp = __this_cpu_read(rcu_data.mynode); + rnp = raw_cpu_read(rcu_data.mynode); for (; rnp != NULL; rnp = rnp->parent) { ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) || !raw_spin_trylock(&rnp->fqslock); From 0461a8c278b8fe74d19e58bc224327bef645e295 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 14 Nov 2022 14:40:42 +0000 Subject: [PATCH 0566/4345] arm64: make is_ttbrX_addr() noinstr-safe [ Upstream commit d8c1d798a2e5091128c391c6dadcc9be334af3f5 ] We use is_ttbr0_addr() in noinstr code, but as it's only marked as inline, it's theoretically possible for the compiler to place it out-of-line and instrument it, which would be problematic. Mark is_ttbr0_addr() as __always_inline such that that can safely be used from noinstr code. For consistency, do the same to is_ttbr1_addr(). Note that while is_ttbr1_addr() calls arch_kasan_reset_tag(), this is a macro (and its callees are either macros or __always_inline), so there is not a risk of transient instrumentation. Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: Will Deacon Link: https://lore.kernel.org/r/20221114144042.3001140-1-mark.rutland@arm.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/include/asm/processor.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 7c546c3487c9..c628d8e3a403 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -230,13 +230,13 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, } #endif -static inline bool is_ttbr0_addr(unsigned long addr) +static __always_inline bool is_ttbr0_addr(unsigned long addr) { /* entry assembly clears tags for TTBR0 addrs */ return addr < TASK_SIZE; } -static inline bool is_ttbr1_addr(unsigned long addr) +static __always_inline bool is_ttbr1_addr(unsigned long addr) { /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; From 9b267051c82a6f7be6638b6834c10ede312f8335 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Fri, 19 Aug 2022 19:17:29 -0300 Subject: [PATCH 0567/4345] video: hyperv_fb: Avoid taking busy spinlock on panic path [ Upstream commit 1d044ca035dc22df0d3b39e56f2881071d9118bd ] The Hyper-V framebuffer code registers a panic notifier in order to try updating its fbdev if the kernel crashed. The notifier callback is straightforward, but it calls the vmbus_sendpacket() routine eventually, and such function takes a spinlock for the ring buffer operations. Panic path runs in atomic context, with local interrupts and preemption disabled, and all secondary CPUs shutdown. That said, taking a spinlock might cause a lockup if a secondary CPU was disabled with such lock taken. Fix it here by checking if the ring buffer spinlock is busy on Hyper-V framebuffer panic notifier; if so, bail-out avoiding the potential lockup scenario. Cc: Andrea Parri (Microsoft) Cc: Dexuan Cui Cc: Haiyang Zhang Cc: "K. Y. Srinivasan" Cc: Michael Kelley Cc: Stephen Hemminger Cc: Tianyu Lan Cc: Wei Liu Tested-by: Fabio A M Martins Signed-off-by: Guilherme G. Piccoli Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220819221731.480795-10-gpiccoli@igalia.com Signed-off-by: Wei Liu Signed-off-by: Sasha Levin --- drivers/hv/ring_buffer.c | 13 +++++++++++++ drivers/video/fbdev/hyperv_fb.c | 8 +++++++- include/linux/hyperv.h | 2 ++ 3 files changed, 22 insertions(+), 1 deletion(-) diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 769851b6e74c..7ed6fad3fa8f 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -246,6 +246,19 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) mutex_unlock(&ring_info->ring_buffer_mutex); } +/* + * Check if the ring buffer spinlock is available to take or not; used on + * atomic contexts, like panic path (see the Hyper-V framebuffer driver). + */ + +bool hv_ringbuffer_spinlock_busy(struct vmbus_channel *channel) +{ + struct hv_ring_buffer_info *rinfo = &channel->outbound; + + return spin_is_locked(&rinfo->ring_lock); +} +EXPORT_SYMBOL_GPL(hv_ringbuffer_spinlock_busy); + /* Write to the ring buffer. */ int hv_ringbuffer_write(struct vmbus_channel *channel, const struct kvec *kv_list, u32 kv_count) diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index 40baa79f8046..f0a66a344d87 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -798,12 +798,18 @@ static void hvfb_ondemand_refresh_throttle(struct hvfb_par *par, static int hvfb_on_panic(struct notifier_block *nb, unsigned long e, void *p) { + struct hv_device *hdev; struct hvfb_par *par; struct fb_info *info; par = container_of(nb, struct hvfb_par, hvfb_panic_nb); - par->synchronous_fb = true; info = par->info; + hdev = device_to_hv_device(info->device); + + if (hv_ringbuffer_spinlock_busy(hdev->channel)) + return NOTIFY_DONE; + + par->synchronous_fb = true; if (par->need_docopy) hvfb_docopy(par, 0, dio_fb_size); synthvid_update(info, 0, 0, INT_MAX, INT_MAX); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 1ce131f29f3b..eada4d8d6587 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1269,6 +1269,8 @@ struct hv_ring_buffer_debug_info { int hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info, struct hv_ring_buffer_debug_info *debug_info); +bool hv_ringbuffer_spinlock_busy(struct vmbus_channel *channel); + /* Vmbus interface */ #define vmbus_driver_register(driver) \ __vmbus_driver_register(driver, THIS_MODULE, KBUILD_MODNAME) From 22c1d8f24cdb2022f59aa9a88f6d8fa9938eff1e Mon Sep 17 00:00:00 2001 From: Gaurav Kohli Date: Fri, 25 Nov 2022 22:14:51 -0800 Subject: [PATCH 0568/4345] x86/hyperv: Remove unregister syscore call from Hyper-V cleanup [ Upstream commit 32c97d980e2eef25465d453f2956a9ca68926a3c ] Hyper-V cleanup code comes under panic path where preemption and irq is already disabled. So calling of unregister_syscore_ops might schedule out the thread even for the case where mutex lock is free. hyperv_cleanup unregister_syscore_ops mutex_lock(&syscore_ops_lock) might_sleep Here might_sleep might schedule out this thread, where voluntary preemption config is on and this thread will never comes back. And also this was added earlier to maintain the symmetry which is not required as this can comes during crash shutdown path only. To prevent the same, removing unregister_syscore_ops function call. Signed-off-by: Gaurav Kohli Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1669443291-2575-1-git-send-email-gauravkohli@linux.microsoft.com Signed-off-by: Wei Liu Signed-off-by: Sasha Levin --- arch/x86/hyperv/hv_init.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 01860c0d324d..70fd21ebb9d5 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -453,8 +453,6 @@ void hyperv_cleanup(void) { union hv_x64_msr_hypercall_contents hypercall_msr; - unregister_syscore_ops(&hv_syscore_ops); - /* Reset our OS id */ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); From dcbc51d31d0afbd45e830e3cf565a7b3ca7bf0d8 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Wed, 2 Nov 2022 10:51:23 +0800 Subject: [PATCH 0569/4345] binfmt_misc: fix shift-out-of-bounds in check_special_flags [ Upstream commit 6a46bf558803dd2b959ca7435a5c143efe837217 ] UBSAN reported a shift-out-of-bounds warning: left shift of 1 by 31 places cannot be represented in type 'int' Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x8d/0xcf lib/dump_stack.c:106 ubsan_epilogue+0xa/0x44 lib/ubsan.c:151 __ubsan_handle_shift_out_of_bounds+0x1e7/0x208 lib/ubsan.c:322 check_special_flags fs/binfmt_misc.c:241 [inline] create_entry fs/binfmt_misc.c:456 [inline] bm_register_write+0x9d3/0xa20 fs/binfmt_misc.c:654 vfs_write+0x11e/0x580 fs/read_write.c:582 ksys_write+0xcf/0x120 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x34/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x4194e1 Since the type of Node's flags is unsigned long, we should define these macros with same type too. Signed-off-by: Liu Shixin Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221102025123.1117184-1-liushixin2@huawei.com Signed-off-by: Sasha Levin --- fs/binfmt_misc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 11b5bf241955..ce0047feea72 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -44,10 +44,10 @@ static LIST_HEAD(entries); static int enabled = 1; enum {Enabled, Magic}; -#define MISC_FMT_PRESERVE_ARGV0 (1 << 31) -#define MISC_FMT_OPEN_BINARY (1 << 30) -#define MISC_FMT_CREDENTIALS (1 << 29) -#define MISC_FMT_OPEN_FILE (1 << 28) +#define MISC_FMT_PRESERVE_ARGV0 (1UL << 31) +#define MISC_FMT_OPEN_BINARY (1UL << 30) +#define MISC_FMT_CREDENTIALS (1UL << 29) +#define MISC_FMT_OPEN_FILE (1UL << 28) typedef struct { struct list_head list; From 3e997e4ce8ae7ab89d72334120f6aee49c5bbdbd Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Tue, 18 Oct 2022 08:48:07 -0500 Subject: [PATCH 0570/4345] fs: jfs: fix shift-out-of-bounds in dbAllocAG [ Upstream commit 898f706695682b9954f280d95e49fa86ffa55d08 ] Syzbot found a crash : UBSAN: shift-out-of-bounds in dbAllocAG. The underlying bug is the missing check of bmp->db_agl2size. The field can be greater than 64 and trigger the shift-out-of-bounds. Fix this bug by adding a check of bmp->db_agl2size in dbMount since this field is used in many following functions. The upper bound for this field is L2MAXL2SIZE - L2MAXAG, thanks for the help of Dave Kleikamp. Note that, for maintenance, I reorganized error handling code of dbMount. Reported-by: syzbot+15342c1aa6a00fb7a438@syzkaller.appspotmail.com Signed-off-by: Dongliang Mu Signed-off-by: Dave Kleikamp Signed-off-by: Sasha Levin --- fs/jfs/jfs_dmap.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 0ce17ea8fa8a..b0a65aaed43e 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -155,7 +155,7 @@ int dbMount(struct inode *ipbmap) struct bmap *bmp; struct dbmap_disk *dbmp_le; struct metapage *mp; - int i; + int i, err; /* * allocate/initialize the in-memory bmap descriptor @@ -170,8 +170,8 @@ int dbMount(struct inode *ipbmap) BMAPBLKNO << JFS_SBI(ipbmap->i_sb)->l2nbperpage, PSIZE, 0); if (mp == NULL) { - kfree(bmp); - return -EIO; + err = -EIO; + goto err_kfree_bmp; } /* copy the on-disk bmap descriptor to its in-memory version. */ @@ -181,9 +181,8 @@ int dbMount(struct inode *ipbmap) bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag); if (!bmp->db_numag) { - release_metapage(mp); - kfree(bmp); - return -EINVAL; + err = -EINVAL; + goto err_release_metapage; } bmp->db_maxlevel = le32_to_cpu(dbmp_le->dn_maxlevel); @@ -194,6 +193,11 @@ int dbMount(struct inode *ipbmap) bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth); bmp->db_agstart = le32_to_cpu(dbmp_le->dn_agstart); bmp->db_agl2size = le32_to_cpu(dbmp_le->dn_agl2size); + if (bmp->db_agl2size > L2MAXL2SIZE - L2MAXAG) { + err = -EINVAL; + goto err_release_metapage; + } + for (i = 0; i < MAXAG; i++) bmp->db_agfree[i] = le64_to_cpu(dbmp_le->dn_agfree[i]); bmp->db_agsize = le64_to_cpu(dbmp_le->dn_agsize); @@ -214,6 +218,12 @@ int dbMount(struct inode *ipbmap) BMAP_LOCK_INIT(bmp); return (0); + +err_release_metapage: + release_metapage(mp); +err_kfree_bmp: + kfree(bmp); + return err; } From 40dba68d418237b1ae2beaa06d46a94dd946278e Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Sun, 23 Oct 2022 18:57:41 +0900 Subject: [PATCH 0571/4345] udf: Avoid double brelse() in udf_rename() [ Upstream commit c791730f2554a9ebb8f18df9368dc27d4ebc38c2 ] syzbot reported a warning like below [1]: VFS: brelse: Trying to free free buffer WARNING: CPU: 2 PID: 7301 at fs/buffer.c:1145 __brelse+0x67/0xa0 ... Call Trace: invalidate_bh_lru+0x99/0x150 smp_call_function_many_cond+0xe2a/0x10c0 ? generic_remap_file_range_prep+0x50/0x50 ? __brelse+0xa0/0xa0 ? __mutex_lock+0x21c/0x12d0 ? smp_call_on_cpu+0x250/0x250 ? rcu_read_lock_sched_held+0xb/0x60 ? lock_release+0x587/0x810 ? __brelse+0xa0/0xa0 ? generic_remap_file_range_prep+0x50/0x50 on_each_cpu_cond_mask+0x3c/0x80 blkdev_flush_mapping+0x13a/0x2f0 blkdev_put_whole+0xd3/0xf0 blkdev_put+0x222/0x760 deactivate_locked_super+0x96/0x160 deactivate_super+0xda/0x100 cleanup_mnt+0x222/0x3d0 task_work_run+0x149/0x240 ? task_work_cancel+0x30/0x30 do_exit+0xb29/0x2a40 ? reacquire_held_locks+0x4a0/0x4a0 ? do_raw_spin_lock+0x12a/0x2b0 ? mm_update_next_owner+0x7c0/0x7c0 ? rwlock_bug.part.0+0x90/0x90 ? zap_other_threads+0x234/0x2d0 do_group_exit+0xd0/0x2a0 __x64_sys_exit_group+0x3a/0x50 do_syscall_64+0x34/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd The cause of the issue is that brelse() is called on both ofibh.sbh and ofibh.ebh by udf_find_entry() when it returns NULL. However, brelse() is called by udf_rename(), too. So, b_count on buffer_head becomes unbalanced. This patch fixes the issue by not calling brelse() by udf_rename() when udf_find_entry() returns NULL. Link: https://syzkaller.appspot.com/bug?id=8297f45698159c6bca8a1f87dc983667c1a1c851 [1] Reported-by: syzbot+7902cd7684bc35306224@syzkaller.appspotmail.com Signed-off-by: Shigeru Yoshida Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20221023095741.271430-1-syoshida@redhat.com Signed-off-by: Sasha Levin --- fs/udf/namei.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/udf/namei.c b/fs/udf/namei.c index aff5ca32e4f6..58120d2f265f 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -1090,8 +1090,9 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, return -EINVAL; ofi = udf_find_entry(old_dir, &old_dentry->d_name, &ofibh, &ocfi); - if (IS_ERR(ofi)) { - retval = PTR_ERR(ofi); + if (!ofi || IS_ERR(ofi)) { + if (IS_ERR(ofi)) + retval = PTR_ERR(ofi); goto end_rename; } @@ -1100,8 +1101,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, brelse(ofibh.sbh); tloc = lelb_to_cpu(ocfi.icb.extLocation); - if (!ofi || udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) - != old_inode->i_ino) + if (udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) != old_inode->i_ino) goto end_rename; nfi = udf_find_entry(new_dir, &new_dentry->d_name, &nfibh, &ncfi); From 911999b193735cd378517b6cd5fe585ee345d49c Mon Sep 17 00:00:00 2001 From: Hoi Pok Wu Date: Tue, 25 Oct 2022 23:20:45 +0800 Subject: [PATCH 0572/4345] fs: jfs: fix shift-out-of-bounds in dbDiscardAG [ Upstream commit 25e70c6162f207828dd405b432d8f2a98dbf7082 ] This should be applied to most URSAN bugs found recently by syzbot, by guarding the dbMount. As syzbot feeding rubbish into the bmap descriptor. Signed-off-by: Hoi Pok Wu Signed-off-by: Dave Kleikamp Signed-off-by: Sasha Levin --- fs/jfs/jfs_dmap.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index b0a65aaed43e..2c9493011aec 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -198,6 +198,11 @@ int dbMount(struct inode *ipbmap) goto err_release_metapage; } + if (((bmp->db_mapsize - 1) >> bmp->db_agl2size) > MAXAG) { + err = -EINVAL; + goto err_release_metapage; + } + for (i = 0; i < MAXAG; i++) bmp->db_agfree[i] = le64_to_cpu(dbmp_le->dn_agfree[i]); bmp->db_agsize = le64_to_cpu(dbmp_le->dn_agsize); From b0b83d3f3ffa96e8395c56b83d6197e184902a34 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 7 Nov 2022 18:42:36 +0100 Subject: [PATCH 0573/4345] ACPICA: Fix error code path in acpi_ds_call_control_method() [ Upstream commit 404ec60438add1afadaffaed34bb5fe4ddcadd40 ] A use-after-free in acpi_ps_parse_aml() after a failing invocaion of acpi_ds_call_control_method() is reported by KASAN [1] and code inspection reveals that next_walk_state pushed to the thread by acpi_ds_create_walk_state() is freed on errors, but it is not popped from the thread beforehand. Thus acpi_ds_get_current_walk_state() called by acpi_ps_parse_aml() subsequently returns it as the new walk state which is incorrect. To address this, make acpi_ds_call_control_method() call acpi_ds_pop_walk_state() to pop next_walk_state from the thread before returning an error. Link: https://lore.kernel.org/linux-acpi/20221019073443.248215-1-chenzhongjin@huawei.com/ # [1] Reported-by: Chen Zhongjin Signed-off-by: Rafael J. Wysocki Reviewed-by: Chen Zhongjin Signed-off-by: Sasha Levin --- drivers/acpi/acpica/dsmethod.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index cf67caff878a..97971c79c5f5 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -517,7 +517,7 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread, info = ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_evaluate_info)); if (!info) { status = AE_NO_MEMORY; - goto cleanup; + goto pop_walk_state; } info->parameters = &this_walk_state->operands[0]; @@ -529,7 +529,7 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread, ACPI_FREE(info); if (ACPI_FAILURE(status)) { - goto cleanup; + goto pop_walk_state; } next_walk_state->method_nesting_depth = @@ -575,6 +575,12 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread, return_ACPI_STATUS(status); +pop_walk_state: + + /* On error, pop the walk state to be deleted from thread */ + + acpi_ds_pop_walk_state(thread); + cleanup: /* On error, we must terminate the method properly */ From d464b035c0613856d012cf1704879d3ff3f057fb Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 27 Oct 2022 13:43:05 +0900 Subject: [PATCH 0574/4345] nilfs2: fix shift-out-of-bounds/overflow in nilfs_sb2_bad_offset() [ Upstream commit 610a2a3d7d8be3537458a378ec69396a76c385b6 ] Patch series "nilfs2: fix UBSAN shift-out-of-bounds warnings on mount time". The first patch fixes a bug reported by syzbot, and the second one fixes the remaining bug of the same kind. Although they are triggered by the same super block data anomaly, I divided it into the above two because the details of the issues and how to fix it are different. Both are required to eliminate the shift-out-of-bounds issues at mount time. This patch (of 2): If the block size exponent information written in an on-disk superblock is corrupted, nilfs_sb2_bad_offset helper function can trigger shift-out-of-bounds warning followed by a kernel panic (if panic_on_warn is set): shift exponent 38983 is too large for 64-bit type 'unsigned long long' Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x28e lib/dump_stack.c:106 ubsan_epilogue lib/ubsan.c:151 [inline] __ubsan_handle_shift_out_of_bounds+0x33d/0x3b0 lib/ubsan.c:322 nilfs_sb2_bad_offset fs/nilfs2/the_nilfs.c:449 [inline] nilfs_load_super_block+0xdf5/0xe00 fs/nilfs2/the_nilfs.c:523 init_nilfs+0xb7/0x7d0 fs/nilfs2/the_nilfs.c:577 nilfs_fill_super+0xb1/0x5d0 fs/nilfs2/super.c:1047 nilfs_mount+0x613/0x9b0 fs/nilfs2/super.c:1317 ... In addition, since nilfs_sb2_bad_offset() performs multiplication without considering the upper bound, the computation may overflow if the disk layout parameters are not normal. This fixes these issues by inserting preliminary sanity checks for those parameters and by converting the comparison from one involving multiplication and left bit-shifting to one using division and right bit-shifting. Link: https://lkml.kernel.org/r/20221027044306.42774-1-konishi.ryusuke@gmail.com Link: https://lkml.kernel.org/r/20221027044306.42774-2-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+e91619dd4c11c4960706@syzkaller.appspotmail.com Tested-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/nilfs2/the_nilfs.c | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index ce103dd39b89..6e2ccdd79c89 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "nilfs.h" #include "segment.h" @@ -443,11 +444,33 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp) return crc == le32_to_cpu(sbp->s_sum); } -static int nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset) +/** + * nilfs_sb2_bad_offset - check the location of the second superblock + * @sbp: superblock raw data buffer + * @offset: byte offset of second superblock calculated from device size + * + * nilfs_sb2_bad_offset() checks if the position on the second + * superblock is valid or not based on the filesystem parameters + * stored in @sbp. If @offset points to a location within the segment + * area, or if the parameters themselves are not normal, it is + * determined to be invalid. + * + * Return Value: true if invalid, false if valid. + */ +static bool nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset) { - return offset < ((le64_to_cpu(sbp->s_nsegments) * - le32_to_cpu(sbp->s_blocks_per_segment)) << - (le32_to_cpu(sbp->s_log_block_size) + 10)); + unsigned int shift_bits = le32_to_cpu(sbp->s_log_block_size); + u32 blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment); + u64 nsegments = le64_to_cpu(sbp->s_nsegments); + u64 index; + + if (blocks_per_segment < NILFS_SEG_MIN_BLOCKS || + shift_bits > ilog2(NILFS_MAX_BLOCK_SIZE) - BLOCK_SIZE_BITS) + return true; + + index = offset >> (shift_bits + BLOCK_SIZE_BITS); + do_div(index, blocks_per_segment); + return index < nsegments; } static void nilfs_release_super_block(struct the_nilfs *nilfs) From ec93b5430ec0f60877a5388bb023d60624f9ab9f Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 27 Oct 2022 13:43:06 +0900 Subject: [PATCH 0575/4345] nilfs2: fix shift-out-of-bounds due to too large exponent of block size [ Upstream commit ebeccaaef67a4895d2496ab8d9c2fb8d89201211 ] If field s_log_block_size of superblock data is corrupted and too large, init_nilfs() and load_nilfs() still can trigger a shift-out-of-bounds warning followed by a kernel panic (if panic_on_warn is set): shift exponent 38973 is too large for 32-bit type 'int' Call Trace: dump_stack_lvl+0xcd/0x134 ubsan_epilogue+0xb/0x50 __ubsan_handle_shift_out_of_bounds.cold.12+0x17b/0x1f5 init_nilfs.cold.11+0x18/0x1d [nilfs2] nilfs_mount+0x9b5/0x12b0 [nilfs2] ... This fixes the issue by adding and using a new helper function for getting block size with sanity check. Link: https://lkml.kernel.org/r/20221027044306.42774-3-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/nilfs2/the_nilfs.c | 42 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 38 insertions(+), 4 deletions(-) diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 6e2ccdd79c89..211937054c31 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -193,6 +193,34 @@ static int nilfs_store_log_cursor(struct the_nilfs *nilfs, return ret; } +/** + * nilfs_get_blocksize - get block size from raw superblock data + * @sb: super block instance + * @sbp: superblock raw data buffer + * @blocksize: place to store block size + * + * nilfs_get_blocksize() calculates the block size from the block size + * exponent information written in @sbp and stores it in @blocksize, + * or aborts with an error message if it's too large. + * + * Return Value: On success, 0 is returned. If the block size is too + * large, -EINVAL is returned. + */ +static int nilfs_get_blocksize(struct super_block *sb, + struct nilfs_super_block *sbp, int *blocksize) +{ + unsigned int shift_bits = le32_to_cpu(sbp->s_log_block_size); + + if (unlikely(shift_bits > + ilog2(NILFS_MAX_BLOCK_SIZE) - BLOCK_SIZE_BITS)) { + nilfs_err(sb, "too large filesystem blocksize: 2 ^ %u KiB", + shift_bits); + return -EINVAL; + } + *blocksize = BLOCK_SIZE << shift_bits; + return 0; +} + /** * load_nilfs - load and recover the nilfs * @nilfs: the_nilfs structure to be released @@ -246,11 +274,15 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) nilfs->ns_sbwtime = le64_to_cpu(sbp[0]->s_wtime); /* verify consistency between two super blocks */ - blocksize = BLOCK_SIZE << le32_to_cpu(sbp[0]->s_log_block_size); + err = nilfs_get_blocksize(sb, sbp[0], &blocksize); + if (err) + goto scan_error; + if (blocksize != nilfs->ns_blocksize) { nilfs_warn(sb, "blocksize differs between two super blocks (%d != %d)", blocksize, nilfs->ns_blocksize); + err = -EINVAL; goto scan_error; } @@ -609,9 +641,11 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) if (err) goto failed_sbh; - blocksize = BLOCK_SIZE << le32_to_cpu(sbp->s_log_block_size); - if (blocksize < NILFS_MIN_BLOCK_SIZE || - blocksize > NILFS_MAX_BLOCK_SIZE) { + err = nilfs_get_blocksize(sb, sbp, &blocksize); + if (err) + goto failed_sbh; + + if (blocksize < NILFS_MIN_BLOCK_SIZE) { nilfs_err(sb, "couldn't mount because of unsupported filesystem blocksize %d", blocksize); From 6edd0cdee5780fd5f43356b72b29a2a6d48ef6da Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Sat, 15 May 2021 22:06:31 +0800 Subject: [PATCH 0576/4345] acct: fix potential integer overflow in encode_comp_t() [ Upstream commit c5f31c655bcc01b6da53b836ac951c1556245305 ] The integer overflow is descripted with following codes: > 317 static comp_t encode_comp_t(u64 value) > 318 { > 319 int exp, rnd; ...... > 341 exp <<= MANTSIZE; > 342 exp += value; > 343 return exp; > 344 } Currently comp_t is defined as type of '__u16', but the variable 'exp' is type of 'int', so overflow would happen when variable 'exp' in line 343 is greater than 65535. Link: https://lkml.kernel.org/r/20210515140631.369106-3-zhengyejian1@huawei.com Signed-off-by: Zheng Yejian Cc: Hanjun Guo Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Zhang Jinhao Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- kernel/acct.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/acct.c b/kernel/acct.c index f175df8f6aa4..12f7dacf560e 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -331,6 +331,8 @@ static comp_t encode_comp_t(unsigned long value) exp++; } + if (exp > (((comp_t) ~0U) >> MANTSIZE)) + return (comp_t) ~0U; /* * Clean it up and polish it off. */ From 4fd3a11804c8877ff11fec59c5c53f1635331e3e Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Wed, 30 Nov 2022 06:59:59 +0000 Subject: [PATCH 0577/4345] hfs: fix OOB Read in __hfs_brec_find [ Upstream commit 8d824e69d9f3fa3121b2dda25053bae71e2460d2 ] Syzbot reported a OOB read bug: ================================================================== BUG: KASAN: slab-out-of-bounds in hfs_strcmp+0x117/0x190 fs/hfs/string.c:84 Read of size 1 at addr ffff88807eb62c4e by task kworker/u4:1/11 CPU: 1 PID: 11 Comm: kworker/u4:1 Not tainted 6.1.0-rc6-syzkaller-00308-g644e9524388a #0 Workqueue: writeback wb_workfn (flush-7:0) Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x28e lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:284 print_report+0x107/0x1f0 mm/kasan/report.c:395 kasan_report+0xcd/0x100 mm/kasan/report.c:495 hfs_strcmp+0x117/0x190 fs/hfs/string.c:84 __hfs_brec_find+0x213/0x5c0 fs/hfs/bfind.c:75 hfs_brec_find+0x276/0x520 fs/hfs/bfind.c:138 hfs_write_inode+0x34c/0xb40 fs/hfs/inode.c:462 write_inode fs/fs-writeback.c:1440 [inline] If the input inode of hfs_write_inode() is incorrect: struct inode struct hfs_inode_info struct hfs_cat_key struct hfs_name u8 len # len is greater than HFS_NAMELEN(31) which is the maximum length of an HFS filename OOB read occurred: hfs_write_inode() hfs_brec_find() __hfs_brec_find() hfs_cat_keycmp() hfs_strcmp() # OOB read occurred due to len is too large Fix this by adding a Check on len in hfs_write_inode() before calling hfs_brec_find(). Link: https://lkml.kernel.org/r/20221130065959.2168236-1-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reported-by: Cc: Damien Le Moal Cc: Ira Weiny Cc: Jeff Layton Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Nanyong Sun Cc: Viacheslav Dubeyko Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/hfs/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index f35a37c65e5f..e9b4249a4b01 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -454,6 +454,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) /* panic? */ return -EIO; + if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN) + return -EIO; fd.search_key->cat = HFS_I(main_inode)->cat_key; if (hfs_brec_find(&fd)) /* panic? */ From 6cd4865bb4bef8fbbb4aac7bc9db6d6a6d256887 Mon Sep 17 00:00:00 2001 From: Doug Brown Date: Sat, 10 Sep 2022 13:29:38 -0700 Subject: [PATCH 0578/4345] drm/etnaviv: add missing quirks for GC300 [ Upstream commit cc7d3fb446a91f24978a6aa59cbb578f92e22242 ] The GC300's features register doesn't specify that a 2D pipe is available, and like the GC600, its idle register reports zero bits where modules aren't present. Signed-off-by: Doug Brown Reviewed-by: Christian Gmeiner Signed-off-by: Lucas Stach Signed-off-by: Sasha Levin --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 2520b7dad6ce..f3281d56b1d8 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -408,6 +408,12 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) if (gpu->identity.model == chipModel_GC700) gpu->identity.features &= ~chipFeatures_FAST_CLEAR; + /* These models/revisions don't have the 2D pipe bit */ + if ((gpu->identity.model == chipModel_GC500 && + gpu->identity.revision <= 2) || + gpu->identity.model == chipModel_GC300) + gpu->identity.features |= chipFeatures_PIPE_2D; + if ((gpu->identity.model == chipModel_GC500 && gpu->identity.revision < 2) || (gpu->identity.model == chipModel_GC300 && @@ -441,8 +447,9 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_5); } - /* GC600 idle register reports zero bits where modules aren't present */ - if (gpu->identity.model == chipModel_GC600) + /* GC600/300 idle register reports zero bits where modules aren't present */ + if (gpu->identity.model == chipModel_GC600 || + gpu->identity.model == chipModel_GC300) gpu->idle_mask = VIVS_HI_IDLE_STATE_TX | VIVS_HI_IDLE_STATE_RA | VIVS_HI_IDLE_STATE_SE | From 2e8bb402b060a6c22160de3d72cee057698177c8 Mon Sep 17 00:00:00 2001 From: Wright Feng Date: Wed, 28 Sep 2022 22:10:00 -0500 Subject: [PATCH 0579/4345] brcmfmac: return error when getting invalid max_flowrings from dongle [ Upstream commit 2aca4f3734bd717e04943ddf340d49ab62299a00 ] When firmware hit trap at initialization, host will read abnormal max_flowrings number from dongle, and it will cause kernel panic when doing iowrite to initialize dongle ring. To detect this error at early stage, we directly return error when getting invalid max_flowrings(>256). Signed-off-by: Wright Feng Signed-off-by: Chi-hsien Lin Signed-off-by: Ian Lin Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220929031001.9962-3-ian.lin@infineon.com Signed-off-by: Sasha Levin --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 4e9d2b3659f0..6a5621f17bf5 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1109,6 +1109,10 @@ static int brcmf_pcie_init_ringbuffers(struct brcmf_pciedev_info *devinfo) BRCMF_NROF_H2D_COMMON_MSGRINGS; max_completionrings = BRCMF_NROF_D2H_COMMON_MSGRINGS; } + if (max_flowrings > 256) { + brcmf_err(bus, "invalid max_flowrings(%d)\n", max_flowrings); + return -EIO; + } if (devinfo->dma_idx_sz != 0) { bufsz = (max_submissionrings + max_completionrings) * From 1824ccabee5445347b83642e4087cc2eca070343 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Sun, 9 Oct 2022 00:15:32 +0300 Subject: [PATCH 0580/4345] wifi: ath9k: verify the expected usb_endpoints are present MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 16ef02bad239f11f322df8425d302be62f0443ce ] The bug arises when a USB device claims to be an ATH9K but doesn't have the expected endpoints. (In this case there was an interrupt endpoint where the driver expected a bulk endpoint.) The kernel needs to be able to handle such devices without getting an internal error. usb 1-1: BOGUS urb xfer, pipe 3 != type 1 WARNING: CPU: 3 PID: 500 at drivers/usb/core/urb.c:493 usb_submit_urb+0xce2/0x1430 drivers/usb/core/urb.c:493 Modules linked in: CPU: 3 PID: 500 Comm: kworker/3:2 Not tainted 5.10.135-syzkaller #0 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 Workqueue: events request_firmware_work_func RIP: 0010:usb_submit_urb+0xce2/0x1430 drivers/usb/core/urb.c:493 Call Trace: ath9k_hif_usb_alloc_rx_urbs drivers/net/wireless/ath/ath9k/hif_usb.c:908 [inline] ath9k_hif_usb_alloc_urbs+0x75e/0x1010 drivers/net/wireless/ath/ath9k/hif_usb.c:1019 ath9k_hif_usb_dev_init drivers/net/wireless/ath/ath9k/hif_usb.c:1109 [inline] ath9k_hif_usb_firmware_cb+0x142/0x530 drivers/net/wireless/ath/ath9k/hif_usb.c:1242 request_firmware_work_func+0x12e/0x240 drivers/base/firmware_loader/main.c:1097 process_one_work+0x9af/0x1600 kernel/workqueue.c:2279 worker_thread+0x61d/0x12f0 kernel/workqueue.c:2425 kthread+0x3b4/0x4a0 kernel/kthread.c:313 ret_from_fork+0x22/0x30 arch/x86/entry/entry_64.S:299 Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Suggested-by: Alan Stern Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221008211532.74583-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/hif_usb.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index e5d5b0761881..f938ac1a4abd 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -1328,10 +1328,24 @@ static int send_eject_command(struct usb_interface *interface) static int ath9k_hif_usb_probe(struct usb_interface *interface, const struct usb_device_id *id) { + struct usb_endpoint_descriptor *bulk_in, *bulk_out, *int_in, *int_out; struct usb_device *udev = interface_to_usbdev(interface); + struct usb_host_interface *alt; struct hif_device_usb *hif_dev; int ret = 0; + /* Verify the expected endpoints are present */ + alt = interface->cur_altsetting; + if (usb_find_common_endpoints(alt, &bulk_in, &bulk_out, &int_in, &int_out) < 0 || + usb_endpoint_num(bulk_in) != USB_WLAN_RX_PIPE || + usb_endpoint_num(bulk_out) != USB_WLAN_TX_PIPE || + usb_endpoint_num(int_in) != USB_REG_IN_PIPE || + usb_endpoint_num(int_out) != USB_REG_OUT_PIPE) { + dev_err(&udev->dev, + "ath9k_htc: Device endpoint numbers are not the expected ones\n"); + return -ENODEV; + } + if (id->driver_info == STORAGE_DEVICE) return send_eject_command(interface); From 8af52492717e3538eba3f81d012b1476af8a89a6 Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Mon, 10 Oct 2022 03:32:23 +0900 Subject: [PATCH 0581/4345] wifi: ar5523: Fix use-after-free on ar5523_cmd() timed out [ Upstream commit b6702a942a069c2a975478d719e98d83cdae1797 ] syzkaller reported use-after-free with the stack trace like below [1]: [ 38.960489][ C3] ================================================================== [ 38.963216][ C3] BUG: KASAN: use-after-free in ar5523_cmd_tx_cb+0x220/0x240 [ 38.964950][ C3] Read of size 8 at addr ffff888048e03450 by task swapper/3/0 [ 38.966363][ C3] [ 38.967053][ C3] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 6.0.0-09039-ga6afa4199d3d-dirty #18 [ 38.968464][ C3] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.fc36 04/01/2014 [ 38.969959][ C3] Call Trace: [ 38.970841][ C3] [ 38.971663][ C3] dump_stack_lvl+0xfc/0x174 [ 38.972620][ C3] print_report.cold+0x2c3/0x752 [ 38.973626][ C3] ? ar5523_cmd_tx_cb+0x220/0x240 [ 38.974644][ C3] kasan_report+0xb1/0x1d0 [ 38.975720][ C3] ? ar5523_cmd_tx_cb+0x220/0x240 [ 38.976831][ C3] ar5523_cmd_tx_cb+0x220/0x240 [ 38.978412][ C3] __usb_hcd_giveback_urb+0x353/0x5b0 [ 38.979755][ C3] usb_hcd_giveback_urb+0x385/0x430 [ 38.981266][ C3] dummy_timer+0x140c/0x34e0 [ 38.982925][ C3] ? notifier_call_chain+0xb5/0x1e0 [ 38.984761][ C3] ? rcu_read_lock_sched_held+0xb/0x60 [ 38.986242][ C3] ? lock_release+0x51c/0x790 [ 38.987323][ C3] ? _raw_read_unlock_irqrestore+0x37/0x70 [ 38.988483][ C3] ? __wake_up_common_lock+0xde/0x130 [ 38.989621][ C3] ? reacquire_held_locks+0x4a0/0x4a0 [ 38.990777][ C3] ? lock_acquire+0x472/0x550 [ 38.991919][ C3] ? rcu_read_lock_sched_held+0xb/0x60 [ 38.993138][ C3] ? lock_acquire+0x472/0x550 [ 38.994890][ C3] ? dummy_urb_enqueue+0x860/0x860 [ 38.996266][ C3] ? do_raw_spin_unlock+0x16f/0x230 [ 38.997670][ C3] ? dummy_urb_enqueue+0x860/0x860 [ 38.999116][ C3] call_timer_fn+0x1a0/0x6a0 [ 39.000668][ C3] ? add_timer_on+0x4a0/0x4a0 [ 39.002137][ C3] ? reacquire_held_locks+0x4a0/0x4a0 [ 39.003809][ C3] ? __next_timer_interrupt+0x226/0x2a0 [ 39.005509][ C3] __run_timers.part.0+0x69a/0xac0 [ 39.007025][ C3] ? dummy_urb_enqueue+0x860/0x860 [ 39.008716][ C3] ? call_timer_fn+0x6a0/0x6a0 [ 39.010254][ C3] ? cpuacct_percpu_seq_show+0x10/0x10 [ 39.011795][ C3] ? kvm_sched_clock_read+0x14/0x40 [ 39.013277][ C3] ? sched_clock_cpu+0x69/0x2b0 [ 39.014724][ C3] run_timer_softirq+0xb6/0x1d0 [ 39.016196][ C3] __do_softirq+0x1d2/0x9be [ 39.017616][ C3] __irq_exit_rcu+0xeb/0x190 [ 39.019004][ C3] irq_exit_rcu+0x5/0x20 [ 39.020361][ C3] sysvec_apic_timer_interrupt+0x8f/0xb0 [ 39.021965][ C3] [ 39.023237][ C3] In ar5523_probe(), ar5523_host_available() calls ar5523_cmd() as below (there are other functions which finally call ar5523_cmd()): ar5523_probe() -> ar5523_host_available() -> ar5523_cmd_read() -> ar5523_cmd() If ar5523_cmd() timed out, then ar5523_host_available() failed and ar5523_probe() freed the device structure. So, ar5523_cmd_tx_cb() might touch the freed structure. This patch fixes this issue by canceling in-flight tx cmd if submitted urb timed out. Link: https://syzkaller.appspot.com/bug?id=9e12b2d54300842b71bdd18b54971385ff0d0d3a [1] Reported-by: syzbot+95001b1fd6dfcc716c29@syzkaller.appspotmail.com Signed-off-by: Shigeru Yoshida Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221009183223.420015-1-syoshida@redhat.com Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ar5523/ar5523.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c index 1baec4b412c8..efe38b2c1df7 100644 --- a/drivers/net/wireless/ath/ar5523/ar5523.c +++ b/drivers/net/wireless/ath/ar5523/ar5523.c @@ -241,6 +241,11 @@ static void ar5523_cmd_tx_cb(struct urb *urb) } } +static void ar5523_cancel_tx_cmd(struct ar5523 *ar) +{ + usb_kill_urb(ar->tx_cmd.urb_tx); +} + static int ar5523_cmd(struct ar5523 *ar, u32 code, const void *idata, int ilen, void *odata, int olen, int flags) { @@ -280,6 +285,7 @@ static int ar5523_cmd(struct ar5523 *ar, u32 code, const void *idata, } if (!wait_for_completion_timeout(&cmd->done, 2 * HZ)) { + ar5523_cancel_tx_cmd(ar); cmd->odata = NULL; ar5523_err(ar, "timeout waiting for command %02x reply\n", code); From be4cd23cd36bc1ecfdefd2cd01a83cf5c3423b98 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Amadeusz=20S=C5=82awi=C5=84ski?= Date: Mon, 10 Oct 2022 14:19:43 +0200 Subject: [PATCH 0582/4345] ASoC: codecs: rt298: Add quirk for KBL-R RVP platform MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 953dbd1cef18ce9ac0d69c1bd735b929fe52a17e ] KBL-R RVP platforms also use combojack, so we need to enable that configuration for them. Signed-off-by: Amadeusz Sławiński Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20221010121955.718168-4-cezary.rojewski@intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/rt298.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/sound/soc/codecs/rt298.c b/sound/soc/codecs/rt298.c index dc0273a5a11f..1ca06213e3a3 100644 --- a/sound/soc/codecs/rt298.c +++ b/sound/soc/codecs/rt298.c @@ -1168,6 +1168,13 @@ static const struct dmi_system_id force_combo_jack_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Geminilake") } }, + { + .ident = "Intel Kabylake R RVP", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Kabylake Client platform") + } + }, { } }; From c69bc8e34df4fc5db06e0b4a9a9ffffb1b241436 Mon Sep 17 00:00:00 2001 From: Zhang Yuchen Date: Fri, 7 Oct 2022 17:26:17 +0800 Subject: [PATCH 0583/4345] ipmi: fix memleak when unload ipmi driver [ Upstream commit 36992eb6b9b83f7f9cdc8e74fb5799d7b52e83e9 ] After the IPMI disconnect problem, the memory kept rising and we tried to unload the driver to free the memory. However, only part of the free memory is recovered after the driver is uninstalled. Using ebpf to hook free functions, we find that neither ipmi_user nor ipmi_smi_msg is free, only ipmi_recv_msg is free. We find that the deliver_smi_err_response call in clean_smi_msgs does the destroy processing on each message from the xmit_msg queue without checking the return value and free ipmi_smi_msg. deliver_smi_err_response is called only at this location. Adding the free handling has no effect. To verify, try using ebpf to trace the free function. $ bpftrace -e 'kretprobe:ipmi_alloc_recv_msg {printf("alloc rcv %p\n",retval);} kprobe:free_recv_msg {printf("free recv %p\n", arg0)} kretprobe:ipmi_alloc_smi_msg {printf("alloc smi %p\n", retval);} kprobe:free_smi_msg {printf("free smi %p\n",arg0)}' Signed-off-by: Zhang Yuchen Message-Id: <20221007092617.87597-4-zhangyuchen.lcr@bytedance.com> [Fixed the comment above handle_one_recv_msg().] Signed-off-by: Corey Minyard Signed-off-by: Sasha Levin --- drivers/char/ipmi/ipmi_msghandler.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 05e7339752ac..223b90247648 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -3540,12 +3540,16 @@ static void deliver_smi_err_response(struct ipmi_smi *intf, struct ipmi_smi_msg *msg, unsigned char err) { + int rv; msg->rsp[0] = msg->data[0] | 4; msg->rsp[1] = msg->data[1]; msg->rsp[2] = err; msg->rsp_size = 3; - /* It's an error, so it will never requeue, no need to check return. */ - handle_one_recv_msg(intf, msg); + + /* This will never requeue, but it may ask us to free the message. */ + rv = handle_one_recv_msg(intf, msg); + if (rv == 0) + ipmi_free_smi_msg(msg); } static void cleanup_smi_msgs(struct ipmi_smi *intf) From 648cdb8bf376e722169a681489820b747eda8415 Mon Sep 17 00:00:00 2001 From: gehao Date: Wed, 26 Oct 2022 17:54:05 +0800 Subject: [PATCH 0584/4345] drm/amd/display: prevent memory leak [ Upstream commit d232afb1f3417ae8194ccf19ad3a8360e70e104e ] In dce6(0,1,4)_create_resource_pool and dce80_create_resource_pool the allocated memory should be released if construct pool fails. Reviewed-by: Rodrigo Siqueira Signed-off-by: gehao Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.c | 3 +++ drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c | 2 ++ 2 files changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.c index 5a5a9cb77acb..bcdd8a958fc0 100644 --- a/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_resource.c @@ -1132,6 +1132,7 @@ struct resource_pool *dce60_create_resource_pool( if (dce60_construct(num_virtual_links, dc, pool)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } @@ -1329,6 +1330,7 @@ struct resource_pool *dce61_create_resource_pool( if (dce61_construct(num_virtual_links, dc, pool)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } @@ -1522,6 +1524,7 @@ struct resource_pool *dce64_create_resource_pool( if (dce64_construct(num_virtual_links, dc, pool)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c index a19be9de2df7..2eefa07762ae 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c @@ -1141,6 +1141,7 @@ struct resource_pool *dce80_create_resource_pool( if (dce80_construct(num_virtual_links, dc, pool)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } @@ -1338,6 +1339,7 @@ struct resource_pool *dce81_create_resource_pool( if (dce81_construct(num_virtual_links, dc, pool)) return &pool->base; + kfree(pool); BREAK_TO_DEBUGGER(); return NULL; } From ebc2fb6afc9856188ce0bbb64185a7115c80a1a6 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 31 Oct 2022 12:43:54 +0100 Subject: [PATCH 0585/4345] qed (gcc13): use u16 for fid to be big enough [ Upstream commit 7d84118229bf7f7290438c85caa8e49de52d50c1 ] gcc 13 correctly reports overflow in qed_grc_dump_addr_range(): In file included from drivers/net/ethernet/qlogic/qed/qed.h:23, from drivers/net/ethernet/qlogic/qed/qed_debug.c:10: drivers/net/ethernet/qlogic/qed/qed_debug.c: In function 'qed_grc_dump_addr_range': include/linux/qed/qed_if.h:1217:9: error: overflow in conversion from 'int' to 'u8' {aka 'unsigned char'} changes value from '(int)vf_id << 8 | 128' to '128' [-Werror=overflow] We do: u8 fid; ... fid = vf_id << 8 | 128; Since fid is 16bit (and the stored value above too), fid should be u16, not u8. Fix that. Cc: Martin Liska Cc: Ariel Elior Cc: Manish Chopra Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20221031114354.10398-1-jirislaby@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_debug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 6ab3e60d4928..4b4077cf2d26 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -1796,9 +1796,10 @@ static u32 qed_grc_dump_addr_range(struct qed_hwfn *p_hwfn, u8 split_id) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - u8 port_id = 0, pf_id = 0, vf_id = 0, fid = 0; + u8 port_id = 0, pf_id = 0, vf_id = 0; bool read_using_dmae = false; u32 thresh; + u16 fid; if (!dump) return len; From 6d935a02658be82585ecb39aab339faa84496650 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 27 Oct 2022 15:55:37 -0700 Subject: [PATCH 0586/4345] bpf: make sure skb->len != 0 when redirecting to a tunneling device [ Upstream commit 07ec7b502800ba9f7b8b15cb01dd6556bb41aaca ] syzkaller managed to trigger another case where skb->len == 0 when we enter __dev_queue_xmit: WARNING: CPU: 0 PID: 2470 at include/linux/skbuff.h:2576 skb_assert_len include/linux/skbuff.h:2576 [inline] WARNING: CPU: 0 PID: 2470 at include/linux/skbuff.h:2576 __dev_queue_xmit+0x2069/0x35e0 net/core/dev.c:4295 Call Trace: dev_queue_xmit+0x17/0x20 net/core/dev.c:4406 __bpf_tx_skb net/core/filter.c:2115 [inline] __bpf_redirect_no_mac net/core/filter.c:2140 [inline] __bpf_redirect+0x5fb/0xda0 net/core/filter.c:2163 ____bpf_clone_redirect net/core/filter.c:2447 [inline] bpf_clone_redirect+0x247/0x390 net/core/filter.c:2419 bpf_prog_48159a89cb4a9a16+0x59/0x5e bpf_dispatcher_nop_func include/linux/bpf.h:897 [inline] __bpf_prog_run include/linux/filter.h:596 [inline] bpf_prog_run include/linux/filter.h:603 [inline] bpf_test_run+0x46c/0x890 net/bpf/test_run.c:402 bpf_prog_test_run_skb+0xbdc/0x14c0 net/bpf/test_run.c:1170 bpf_prog_test_run+0x345/0x3c0 kernel/bpf/syscall.c:3648 __sys_bpf+0x43a/0x6c0 kernel/bpf/syscall.c:5005 __do_sys_bpf kernel/bpf/syscall.c:5091 [inline] __se_sys_bpf kernel/bpf/syscall.c:5089 [inline] __x64_sys_bpf+0x7c/0x90 kernel/bpf/syscall.c:5089 do_syscall_64+0x54/0x70 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x61/0xc6 The reproducer doesn't really reproduce outside of syzkaller environment, so I'm taking a guess here. It looks like we do generate correct ETH_HLEN-sized packet, but we redirect the packet to the tunneling device. Before we do so, we __skb_pull l2 header and arrive again at skb->len == 0. Doesn't seem like we can do anything better than having an explicit check after __skb_pull? Cc: Eric Dumazet Reported-by: syzbot+f635e86ec3fa0a37e019@syzkaller.appspotmail.com Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20221027225537.353077-1-sdf@google.com Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- net/core/filter.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/core/filter.c b/net/core/filter.c index ef7e74260afc..e3cdbd4996e0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2132,6 +2132,10 @@ static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, if (mlen) { __skb_pull(skb, mlen); + if (unlikely(!skb->len)) { + kfree_skb(skb); + return -ERANGE; + } /* At ingress, the mac header has already been pulled once. * At egress, skb_pospull_rcsum has to be done in case that From 5b0b6553bf4ad3a435a57e02c68d6075f384e1be Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 2 Nov 2022 09:09:33 -0700 Subject: [PATCH 0587/4345] net: ethernet: ti: Fix return type of netcp_ndo_start_xmit() [ Upstream commit 63fe6ff674a96cfcfc0fa8df1051a27aa31c70b4 ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A proposed warning in clang aims to catch these at compile time, which reveals: drivers/net/ethernet/ti/netcp_core.c:1944:21: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict] .ndo_start_xmit = netcp_ndo_start_xmit, ^~~~~~~~~~~~~~~~~~~~ 1 error generated. ->ndo_start_xmit() in 'struct net_device_ops' expects a return type of 'netdev_tx_t', not 'int'. Adjust the return type of netcp_ndo_start_xmit() to match the prototype's to resolve the warning and CFI failure. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Signed-off-by: Nathan Chancellor Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20221102160933.1601260-1-nathan@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/netcp_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index dc50e948195d..f145abb77a49 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1262,7 +1262,7 @@ out: } /* Submit the packet */ -static int netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct netcp_intf *netcp = netdev_priv(ndev); struct netcp_stats *tx_stats = &netcp->stats; From e7aa8a4709d4b028c72f56cc146499d82d1d97a9 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 2 Nov 2022 09:06:10 -0700 Subject: [PATCH 0588/4345] hamradio: baycom_epp: Fix return type of baycom_send_packet() [ Upstream commit c5733e5b15d91ab679646ec3149e192996a27d5d ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A proposed warning in clang aims to catch these at compile time, which reveals: drivers/net/hamradio/baycom_epp.c:1119:25: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict] .ndo_start_xmit = baycom_send_packet, ^~~~~~~~~~~~~~~~~~ 1 error generated. ->ndo_start_xmit() in 'struct net_device_ops' expects a return type of 'netdev_tx_t', not 'int'. Adjust the return type of baycom_send_packet() to match the prototype's to resolve the warning and CFI failure. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Signed-off-by: Nathan Chancellor Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20221102160610.1186145-1-nathan@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/hamradio/baycom_epp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index e4e4981ac1d2..eea9d47157cf 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -758,7 +758,7 @@ static void epp_bh(struct work_struct *work) * ===================== network driver interface ========================= */ -static int baycom_send_packet(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t baycom_send_packet(struct sk_buff *skb, struct net_device *dev) { struct baycom_state *bc = netdev_priv(dev); From 87792567d9ed93fd336d2c3b8d7870f44e141e6d Mon Sep 17 00:00:00 2001 From: Minsuk Kang Date: Mon, 24 Oct 2022 16:13:29 +0900 Subject: [PATCH 0589/4345] wifi: brcmfmac: Fix potential shift-out-of-bounds in brcmf_fw_alloc_request() [ Upstream commit 81d17f6f3331f03c8eafdacea68ab773426c1e3c ] This patch fixes a shift-out-of-bounds in brcmfmac that occurs in BIT(chiprev) when a 'chiprev' provided by the device is too large. It should also not be equal to or greater than BITS_PER_TYPE(u32) as we do bitwise AND with a u32 variable and BIT(chiprev). The patch adds a check that makes the function return NULL if that is the case. Note that the NULL case is later handled by the bus-specific caller, brcmf_usb_probe_cb() or brcmf_usb_reset_resume(), for example. Found by a modified version of syzkaller. UBSAN: shift-out-of-bounds in drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c shift exponent 151055786 is too large for 64-bit type 'long unsigned int' CPU: 0 PID: 1885 Comm: kworker/0:2 Tainted: G O 5.14.0+ #132 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 Workqueue: usb_hub_wq hub_event Call Trace: dump_stack_lvl+0x57/0x7d ubsan_epilogue+0x5/0x40 __ubsan_handle_shift_out_of_bounds.cold+0x53/0xdb ? lock_chain_count+0x20/0x20 brcmf_fw_alloc_request.cold+0x19/0x3ea ? brcmf_fw_get_firmwares+0x250/0x250 ? brcmf_usb_ioctl_resp_wait+0x1a7/0x1f0 brcmf_usb_get_fwname+0x114/0x1a0 ? brcmf_usb_reset_resume+0x120/0x120 ? number+0x6c4/0x9a0 brcmf_c_process_clm_blob+0x168/0x590 ? put_dec+0x90/0x90 ? enable_ptr_key_workfn+0x20/0x20 ? brcmf_common_pd_remove+0x50/0x50 ? rcu_read_lock_sched_held+0xa1/0xd0 brcmf_c_preinit_dcmds+0x673/0xc40 ? brcmf_c_set_joinpref_default+0x100/0x100 ? rcu_read_lock_sched_held+0xa1/0xd0 ? rcu_read_lock_bh_held+0xb0/0xb0 ? lock_acquire+0x19d/0x4e0 ? find_held_lock+0x2d/0x110 ? brcmf_usb_deq+0x1cc/0x260 ? mark_held_locks+0x9f/0xe0 ? lockdep_hardirqs_on_prepare+0x273/0x3e0 ? _raw_spin_unlock_irqrestore+0x47/0x50 ? trace_hardirqs_on+0x1c/0x120 ? brcmf_usb_deq+0x1a7/0x260 ? brcmf_usb_rx_fill_all+0x5a/0xf0 brcmf_attach+0x246/0xd40 ? wiphy_new_nm+0x1476/0x1d50 ? kmemdup+0x30/0x40 brcmf_usb_probe+0x12de/0x1690 ? brcmf_usbdev_qinit.constprop.0+0x470/0x470 usb_probe_interface+0x25f/0x710 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 ? usb_match_id.part.0+0x88/0xc0 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 ? driver_allows_async_probing+0x120/0x120 bus_for_each_drv+0x123/0x1a0 ? bus_rescan_devices+0x20/0x20 ? lockdep_hardirqs_on_prepare+0x273/0x3e0 ? trace_hardirqs_on+0x1c/0x120 __device_attach+0x207/0x330 ? device_bind_driver+0xb0/0xb0 ? kobject_uevent_env+0x230/0x12c0 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 ? __mutex_unlock_slowpath+0xe7/0x660 ? __fw_devlink_link_to_suppliers+0x550/0x550 usb_set_configuration+0x984/0x1770 ? kernfs_create_link+0x175/0x230 usb_generic_driver_probe+0x69/0x90 usb_probe_device+0x9c/0x220 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 ? driver_allows_async_probing+0x120/0x120 bus_for_each_drv+0x123/0x1a0 ? bus_rescan_devices+0x20/0x20 ? lockdep_hardirqs_on_prepare+0x273/0x3e0 ? trace_hardirqs_on+0x1c/0x120 __device_attach+0x207/0x330 ? device_bind_driver+0xb0/0xb0 ? kobject_uevent_env+0x230/0x12c0 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 ? __fw_devlink_link_to_suppliers+0x550/0x550 usb_new_device.cold+0x463/0xf66 ? hub_disconnect+0x400/0x400 ? _raw_spin_unlock_irq+0x24/0x30 hub_event+0x10d5/0x3330 ? hub_port_debounce+0x280/0x280 ? __lock_acquire+0x1671/0x5790 ? wq_calc_node_cpumask+0x170/0x2a0 ? lock_release+0x640/0x640 ? rcu_read_lock_sched_held+0xa1/0xd0 ? rcu_read_lock_bh_held+0xb0/0xb0 ? lockdep_hardirqs_on_prepare+0x273/0x3e0 process_one_work+0x873/0x13e0 ? lock_release+0x640/0x640 ? pwq_dec_nr_in_flight+0x320/0x320 ? rwlock_bug.part.0+0x90/0x90 worker_thread+0x8b/0xd10 ? __kthread_parkme+0xd9/0x1d0 ? process_one_work+0x13e0/0x13e0 kthread+0x379/0x450 ? _raw_spin_unlock_irq+0x24/0x30 ? set_kthread_struct+0x100/0x100 ret_from_fork+0x1f/0x30 Reported-by: Dokyung Song Reported-by: Jisoo Jang Reported-by: Minsuk Kang Signed-off-by: Minsuk Kang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221024071329.504277-1-linuxlovemin@yonsei.ac.kr Signed-off-by: Sasha Levin --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c index a2b8d9171af2..060889bf6d05 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c @@ -703,6 +703,11 @@ brcmf_fw_alloc_request(u32 chip, u32 chiprev, u32 i, j; char end = '\0'; + if (chiprev >= BITS_PER_TYPE(u32)) { + brcmf_err("Invalid chip revision %u\n", chiprev); + return NULL; + } + for (i = 0; i < table_size; i++) { if (mapping_table[i].chipid == chip && mapping_table[i].revmask & BIT(chiprev)) From 3cb18dea11196fb4a06f78294cec5e61985e1aff Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Oct 2022 02:25:24 -0700 Subject: [PATCH 0590/4345] igb: Do not free q_vector unless new one was allocated [ Upstream commit 0668716506ca66f90d395f36ccdaebc3e0e84801 ] Avoid potential use-after-free condition under memory pressure. If the kzalloc() fails, q_vector will be freed but left in the original adapter->q_vector[v_idx] array position. Cc: Jesse Brandeburg Cc: Tony Nguyen Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: intel-wired-lan@lists.osuosl.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Michael J. Ruhl Reviewed-by: Jacob Keller Tested-by: Gurucharan (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igb/igb_main.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 2646601c3487..0ea8e4024d63 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1204,8 +1204,12 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, if (!q_vector) { q_vector = kzalloc(size, GFP_KERNEL); } else if (size > ksize(q_vector)) { - kfree_rcu(q_vector, rcu); - q_vector = kzalloc(size, GFP_KERNEL); + struct igb_q_vector *new_q_vector; + + new_q_vector = kzalloc(size, GFP_KERNEL); + if (new_q_vector) + kfree_rcu(q_vector, rcu); + q_vector = new_q_vector; } else { memset(q_vector, 0, size); } From a42a23bdae61a3aa789d1ad2da6d5583508262ca Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 2 Nov 2022 08:25:39 -0700 Subject: [PATCH 0591/4345] drm/amdgpu: Fix type of second parameter in trans_msg() callback [ Upstream commit f0d0f1087333714ee683cc134a95afe331d7ddd9 ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A proposed warning in clang aims to catch these at compile time, which reveals: drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c:412:15: error: incompatible function pointer types initializing 'void (*)(struct amdgpu_device *, u32, u32, u32, u32)' (aka 'void (*)(struct amdgpu_device *, unsigned int, unsigned int, unsigned int, unsigned int)') with an expression of type 'void (struct amdgpu_device *, enum idh_request, u32, u32, u32)' (aka 'void (struct amdgpu_device *, enum idh_request, unsigned int, unsigned int, unsigned int)') [-Werror,-Wincompatible-function-pointer-types-strict] .trans_msg = xgpu_ai_mailbox_trans_msg, ^~~~~~~~~~~~~~~~~~~~~~~~~ 1 error generated. drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c:435:15: error: incompatible function pointer types initializing 'void (*)(struct amdgpu_device *, u32, u32, u32, u32)' (aka 'void (*)(struct amdgpu_device *, unsigned int, unsigned int, unsigned int, unsigned int)') with an expression of type 'void (struct amdgpu_device *, enum idh_request, u32, u32, u32)' (aka 'void (struct amdgpu_device *, enum idh_request, unsigned int, unsigned int, unsigned int)') [-Werror,-Wincompatible-function-pointer-types-strict] .trans_msg = xgpu_nv_mailbox_trans_msg, ^~~~~~~~~~~~~~~~~~~~~~~~~ 1 error generated. The type of the second parameter in the prototype should be 'enum idh_request' instead of 'u32'. Update it to clear up the warnings. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Reported-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Nathan Chancellor Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index aea49bad914f..fbd92fff8b06 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -62,6 +62,8 @@ struct amdgpu_vf_error_buffer { uint64_t data[AMDGPU_VF_ERROR_ENTRY_SIZE]; }; +enum idh_request; + /** * struct amdgpu_virt_ops - amdgpu device virt operations */ @@ -71,7 +73,8 @@ struct amdgpu_virt_ops { int (*req_init_data)(struct amdgpu_device *adev); int (*reset_gpu)(struct amdgpu_device *adev); int (*wait_reset)(struct amdgpu_device *adev); - void (*trans_msg)(struct amdgpu_device *adev, u32 req, u32 data1, u32 data2, u32 data3); + void (*trans_msg)(struct amdgpu_device *adev, enum idh_request req, + u32 data1, u32 data2, u32 data3); }; /* From 9606bbc271ac86c266d1f4a0285dd69b3fda2d0f Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 2 Nov 2022 08:25:40 -0700 Subject: [PATCH 0592/4345] drm/amdgpu: Fix type of second parameter in odn_edit_dpm_table() callback [ Upstream commit e4d0ef752081e7aa6ffb7ccac11c499c732a2e05 ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A proposed warning in clang aims to catch these at compile time, which reveals: drivers/gpu/drm/amd/amdgpu/../pm/swsmu/amdgpu_smu.c:3008:29: error: incompatible function pointer types initializing 'int (*)(void *, uint32_t, long *, uint32_t)' (aka 'int (*)(void *, unsigned int, long *, unsigned int)') with an expression of type 'int (void *, enum PP_OD_DPM_TABLE_COMMAND, long *, uint32_t)' (aka 'int (void *, enum PP_OD_DPM_TABLE_COMMAND, long *, unsigned int)') [-Werror,-Wincompatible-function-pointer-types-strict] .odn_edit_dpm_table = smu_od_edit_dpm_table, ^~~~~~~~~~~~~~~~~~~~~ 1 error generated. There are only two implementations of ->odn_edit_dpm_table() in 'struct amd_pm_funcs': smu_od_edit_dpm_table() and pp_odn_edit_dpm_table(). One has a second parameter type of 'enum PP_OD_DPM_TABLE_COMMAND' and the other uses 'u32'. Ultimately, smu_od_edit_dpm_table() calls ->od_edit_dpm_table() from 'struct pptable_funcs' and pp_odn_edit_dpm_table() calls ->odn_edit_dpm_table() from 'struct pp_hwmgr_func', which both have a second parameter type of 'enum PP_OD_DPM_TABLE_COMMAND'. Update the type parameter in both the prototype in 'struct amd_pm_funcs' and pp_odn_edit_dpm_table() to 'enum PP_OD_DPM_TABLE_COMMAND', which cleans up the warning. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Reported-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Nathan Chancellor Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/include/kgd_pp_interface.h | 3 ++- drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 94132c70d7af..5e8876ad1a1b 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -282,7 +282,8 @@ struct amd_pm_funcs { int (*get_power_profile_mode)(void *handle, char *buf); int (*set_power_profile_mode)(void *handle, long *input, uint32_t size); int (*set_fine_grain_clk_vol)(void *handle, uint32_t type, long *input, uint32_t size); - int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size); + int (*odn_edit_dpm_table)(void *handle, enum PP_OD_DPM_TABLE_COMMAND type, + long *input, uint32_t size); int (*set_mp1_state)(void *handle, enum pp_mp1_state mp1_state); int (*smu_i2c_bus_access)(void *handle, bool acquire); /* export to DC */ diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index eab9768029c1..a98ea29b2fd5 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -924,7 +924,8 @@ static int pp_set_fine_grain_clk_vol(void *handle, uint32_t type, long *input, u return hwmgr->hwmgr_func->set_fine_grain_clk_vol(hwmgr, type, input, size); } -static int pp_odn_edit_dpm_table(void *handle, uint32_t type, long *input, uint32_t size) +static int pp_odn_edit_dpm_table(void *handle, enum PP_OD_DPM_TABLE_COMMAND type, + long *input, uint32_t size) { struct pp_hwmgr *hwmgr = handle; From eeb75f80bceb88091722611b694042879aea1231 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 3 Nov 2022 10:01:28 -0700 Subject: [PATCH 0593/4345] s390/ctcm: Fix return type of ctc{mp,}m_tx() [ Upstream commit aa5bf80c3c067b82b4362cd6e8e2194623bcaca6 ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A proposed warning in clang aims to catch these at compile time, which reveals: drivers/s390/net/ctcm_main.c:1064:21: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict] .ndo_start_xmit = ctcm_tx, ^~~~~~~ drivers/s390/net/ctcm_main.c:1072:21: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict] .ndo_start_xmit = ctcmpc_tx, ^~~~~~~~~ ->ndo_start_xmit() in 'struct net_device_ops' expects a return type of 'netdev_tx_t', not 'int'. Adjust the return type of ctc{mp,}m_tx() to match the prototype's to resolve the warning and potential CFI failure, should s390 select ARCH_SUPPORTS_CFI_CLANG in the future. Additionally, while in the area, remove a comment block that is no longer relevant. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Reviewed-by: Alexandra Winter Reviewed-by: Kees Cook Signed-off-by: Nathan Chancellor Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/s390/net/ctcm_main.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index d06809eac16d..fb0e8f1cabdc 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -865,16 +865,9 @@ done: /** * Start transmission of a packet. * Called from generic network device layer. - * - * skb Pointer to buffer containing the packet. - * dev Pointer to interface struct. - * - * returns 0 if packet consumed, !0 if packet rejected. - * Note: If we return !0, then the packet is free'd by - * the generic network layer. */ /* first merge version - leaving both functions separated */ -static int ctcm_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ctcm_tx(struct sk_buff *skb, struct net_device *dev) { struct ctcm_priv *priv = dev->ml_priv; @@ -917,7 +910,7 @@ static int ctcm_tx(struct sk_buff *skb, struct net_device *dev) } /* unmerged MPC variant of ctcm_tx */ -static int ctcmpc_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ctcmpc_tx(struct sk_buff *skb, struct net_device *dev) { int len = 0; struct ctcm_priv *priv = dev->ml_priv; From 3ac0217ca9186c2f9af9a0113a331a42aa847894 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 3 Nov 2022 10:01:29 -0700 Subject: [PATCH 0594/4345] s390/netiucv: Fix return type of netiucv_tx() [ Upstream commit 88d86d18d7cf7e9137c95f9d212bb9fff8a1b4be ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A proposed warning in clang aims to catch these at compile time, which reveals: drivers/s390/net/netiucv.c:1854:21: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict] .ndo_start_xmit = netiucv_tx, ^~~~~~~~~~ ->ndo_start_xmit() in 'struct net_device_ops' expects a return type of 'netdev_tx_t', not 'int'. Adjust the return type of netiucv_tx() to match the prototype's to resolve the warning and potential CFI failure, should s390 select ARCH_SUPPORTS_CFI_CLANG in the future. Additionally, while in the area, remove a comment block that is no longer relevant. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Reviewed-by: Alexandra Winter Reviewed-by: Kees Cook Signed-off-by: Nathan Chancellor Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/s390/net/netiucv.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c index 260860cf3aa1..a2f403c4ec38 100644 --- a/drivers/s390/net/netiucv.c +++ b/drivers/s390/net/netiucv.c @@ -1260,15 +1260,8 @@ static int netiucv_close(struct net_device *dev) /** * Start transmission of a packet. * Called from generic network device layer. - * - * @param skb Pointer to buffer containing the packet. - * @param dev Pointer to interface struct. - * - * @return 0 if packet consumed, !0 if packet rejected. - * Note: If we return !0, then the packet is free'd by - * the generic network layer. */ -static int netiucv_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t netiucv_tx(struct sk_buff *skb, struct net_device *dev) { struct netiucv_priv *privptr = netdev_priv(dev); int rc; From ebc3c77785dc8b5b626309c0032a38fbb139287a Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 3 Nov 2022 10:01:30 -0700 Subject: [PATCH 0595/4345] s390/lcs: Fix return type of lcs_start_xmit() [ Upstream commit bb16db8393658e0978c3f0d30ae069e878264fa3 ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A proposed warning in clang aims to catch these at compile time, which reveals: drivers/s390/net/lcs.c:2090:21: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict] .ndo_start_xmit = lcs_start_xmit, ^~~~~~~~~~~~~~ drivers/s390/net/lcs.c:2097:21: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict] .ndo_start_xmit = lcs_start_xmit, ^~~~~~~~~~~~~~ ->ndo_start_xmit() in 'struct net_device_ops' expects a return type of 'netdev_tx_t', not 'int'. Adjust the return type of lcs_start_xmit() to match the prototype's to resolve the warning and potential CFI failure, should s390 select ARCH_SUPPORTS_CFI_CLANG in the future. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Reviewed-by: Alexandra Winter Reviewed-by: Kees Cook Signed-off-by: Nathan Chancellor Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/s390/net/lcs.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c index 06a322bdced6..7e743f4717a9 100644 --- a/drivers/s390/net/lcs.c +++ b/drivers/s390/net/lcs.c @@ -1518,9 +1518,8 @@ lcs_txbuffer_cb(struct lcs_channel *channel, struct lcs_buffer *buffer) /** * Packet transmit function called by network stack */ -static int -__lcs_start_xmit(struct lcs_card *card, struct sk_buff *skb, - struct net_device *dev) +static netdev_tx_t __lcs_start_xmit(struct lcs_card *card, struct sk_buff *skb, + struct net_device *dev) { struct lcs_header *header; int rc = NETDEV_TX_OK; @@ -1581,8 +1580,7 @@ out: return rc; } -static int -lcs_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t lcs_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct lcs_card *card; int rc; From 4f238212c7c06fd07b16d5db5af8ab9cc10086dc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 7 Nov 2022 21:25:42 +0200 Subject: [PATCH 0596/4345] drm/msm: Use drm_mode_copy() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b2a1c5ca50db22b3677676dd5bad5f6092429acf ] struct drm_display_mode embeds a list head, so overwriting the full struct with another one will corrupt the list (if the destination mode is on a list). Use drm_mode_copy() instead which explicitly preserves the list head of the destination mode. Even if we know the destination mode is not on any list using drm_mode_copy() seems decent as it sets a good example. Bad examples of not using it might eventually get copied into code where preserving the list head actually matters. Obviously one case not covered here is when the mode itself is embedded in a larger structure and the whole structure is copied. But if we are careful when copying into modes embedded in structures I think we can be a little more reassured that bogus list heads haven't been propagated in. @is_mode_copy@ @@ drm_mode_copy(...) { ... } @depends on !is_mode_copy@ struct drm_display_mode *mode; expression E, S; @@ ( - *mode = E + drm_mode_copy(mode, &E) | - memcpy(mode, E, S) + drm_mode_copy(mode, E) ) @depends on !is_mode_copy@ struct drm_display_mode mode; expression E; @@ ( - mode = E + drm_mode_copy(&mode, &E) | - memcpy(&mode, E, S) + drm_mode_copy(&mode, E) ) @@ struct drm_display_mode *mode; @@ - &*mode + mode Cc: Rob Clark Cc: Sean Paul Cc: Abhinav Kumar Cc: linux-arm-msm@vger.kernel.org Cc: freedreno@lists.freedesktop.org Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Reviewed-by: Daniel Vetter Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20221107192545.9896-5-ville.syrjala@linux.intel.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dp/dp_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 5a152d505dfb..1c3dcbc6cce8 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -848,7 +848,7 @@ static int dp_display_set_mode(struct msm_dp *dp_display, dp = container_of(dp_display, struct dp_display_private, dp_display); - dp->panel->dp_mode.drm_mode = mode->drm_mode; + drm_mode_copy(&dp->panel->dp_mode.drm_mode, &mode->drm_mode); dp->panel->dp_mode.bpp = mode->bpp; dp->panel->dp_mode.capabilities = mode->capabilities; dp_panel_init_panel_info(dp->panel); From dd31d73040182cf5b8e6c3bc40e29e9d8c892a83 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 7 Nov 2022 21:25:44 +0200 Subject: [PATCH 0597/4345] drm/rockchip: Use drm_mode_copy() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2bfaa28000d2830d3209161a4541cce0660e1b84 ] struct drm_display_mode embeds a list head, so overwriting the full struct with another one will corrupt the list (if the destination mode is on a list). Use drm_mode_copy() instead which explicitly preserves the list head of the destination mode. Even if we know the destination mode is not on any list using drm_mode_copy() seems decent as it sets a good example. Bad examples of not using it might eventually get copied into code where preserving the list head actually matters. Obviously one case not covered here is when the mode itself is embedded in a larger structure and the whole structure is copied. But if we are careful when copying into modes embedded in structures I think we can be a little more reassured that bogus list heads haven't been propagated in. @is_mode_copy@ @@ drm_mode_copy(...) { ... } @depends on !is_mode_copy@ struct drm_display_mode *mode; expression E, S; @@ ( - *mode = E + drm_mode_copy(mode, &E) | - memcpy(mode, E, S) + drm_mode_copy(mode, E) ) @depends on !is_mode_copy@ struct drm_display_mode mode; expression E; @@ ( - mode = E + drm_mode_copy(&mode, &E) | - memcpy(&mode, E, S) + drm_mode_copy(&mode, E) ) @@ struct drm_display_mode *mode; @@ - &*mode + mode Signed-off-by: Ville Syrjälä Cc: Sandy Huang Cc: "Heiko Stübner" Cc: linux-arm-kernel@lists.infradead.org Cc: linux-rockchip@lists.infradead.org Link: https://patchwork.freedesktop.org/patch/msgid/20221107192545.9896-7-ville.syrjala@linux.intel.com Reviewed-by: Daniel Vetter Signed-off-by: Sasha Levin --- drivers/gpu/drm/rockchip/cdn-dp-core.c | 2 +- drivers/gpu/drm/rockchip/inno_hdmi.c | 2 +- drivers/gpu/drm/rockchip/rk3066_hdmi.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index 857c47c69ef1..adeaa0140f0f 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -564,7 +564,7 @@ static void cdn_dp_encoder_mode_set(struct drm_encoder *encoder, video->v_sync_polarity = !!(mode->flags & DRM_MODE_FLAG_NVSYNC); video->h_sync_polarity = !!(mode->flags & DRM_MODE_FLAG_NHSYNC); - memcpy(&dp->mode, adjusted, sizeof(*mode)); + drm_mode_copy(&dp->mode, adjusted); } static bool cdn_dp_check_link_status(struct cdn_dp_device *dp) diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index 7afdc54eb3ec..78120da5e63a 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -488,7 +488,7 @@ static void inno_hdmi_encoder_mode_set(struct drm_encoder *encoder, inno_hdmi_setup(hdmi, adj_mode); /* Store the display mode for plugin/DPMS poweron events */ - memcpy(&hdmi->previous_mode, adj_mode, sizeof(hdmi->previous_mode)); + drm_mode_copy(&hdmi->previous_mode, adj_mode); } static void inno_hdmi_encoder_enable(struct drm_encoder *encoder) diff --git a/drivers/gpu/drm/rockchip/rk3066_hdmi.c b/drivers/gpu/drm/rockchip/rk3066_hdmi.c index 1c546c3a8998..17e7c40a9e7b 100644 --- a/drivers/gpu/drm/rockchip/rk3066_hdmi.c +++ b/drivers/gpu/drm/rockchip/rk3066_hdmi.c @@ -383,7 +383,7 @@ rk3066_hdmi_encoder_mode_set(struct drm_encoder *encoder, struct rk3066_hdmi *hdmi = to_rk3066_hdmi(encoder); /* Store the display mode for plugin/DPMS poweron events. */ - memcpy(&hdmi->previous_mode, adj_mode, sizeof(hdmi->previous_mode)); + drm_mode_copy(&hdmi->previous_mode, adj_mode); } static void rk3066_hdmi_encoder_enable(struct drm_encoder *encoder) From 7d86851c304aa75835cb82675230eb3a302f6afb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 7 Nov 2022 21:25:45 +0200 Subject: [PATCH 0598/4345] drm/sti: Use drm_mode_copy() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 442cf8e22ba25a77cb9092d78733fdbac9844e50 ] struct drm_display_mode embeds a list head, so overwriting the full struct with another one will corrupt the list (if the destination mode is on a list). Use drm_mode_copy() instead which explicitly preserves the list head of the destination mode. Even if we know the destination mode is not on any list using drm_mode_copy() seems decent as it sets a good example. Bad examples of not using it might eventually get copied into code where preserving the list head actually matters. Obviously one case not covered here is when the mode itself is embedded in a larger structure and the whole structure is copied. But if we are careful when copying into modes embedded in structures I think we can be a little more reassured that bogus list heads haven't been propagated in. @is_mode_copy@ @@ drm_mode_copy(...) { ... } @depends on !is_mode_copy@ struct drm_display_mode *mode; expression E, S; @@ ( - *mode = E + drm_mode_copy(mode, &E) | - memcpy(mode, E, S) + drm_mode_copy(mode, E) ) @depends on !is_mode_copy@ struct drm_display_mode mode; expression E; @@ ( - mode = E + drm_mode_copy(&mode, &E) | - memcpy(&mode, E, S) + drm_mode_copy(&mode, E) ) @@ struct drm_display_mode *mode; @@ - &*mode + mode Cc: Alain Volmat Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20221107192545.9896-8-ville.syrjala@linux.intel.com Reviewed-by: Daniel Vetter Signed-off-by: Sasha Levin --- drivers/gpu/drm/sti/sti_dvo.c | 2 +- drivers/gpu/drm/sti/sti_hda.c | 2 +- drivers/gpu/drm/sti/sti_hdmi.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c index ddb4184f0726..b0676a73a1d7 100644 --- a/drivers/gpu/drm/sti/sti_dvo.c +++ b/drivers/gpu/drm/sti/sti_dvo.c @@ -288,7 +288,7 @@ static void sti_dvo_set_mode(struct drm_bridge *bridge, DRM_DEBUG_DRIVER("\n"); - memcpy(&dvo->mode, mode, sizeof(struct drm_display_mode)); + drm_mode_copy(&dvo->mode, mode); /* According to the path used (main or aux), the dvo clocks should * have a different parent clock. */ diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index 5c2b650b561d..84109800143a 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -523,7 +523,7 @@ static void sti_hda_set_mode(struct drm_bridge *bridge, DRM_DEBUG_DRIVER("\n"); - memcpy(&hda->mode, mode, sizeof(struct drm_display_mode)); + drm_mode_copy(&hda->mode, mode); if (!hda_get_mode_idx(hda->mode, &mode_idx)) { DRM_ERROR("Undefined mode\n"); diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index 38a558768e53..412664dfb0b0 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -934,7 +934,7 @@ static void sti_hdmi_set_mode(struct drm_bridge *bridge, DRM_DEBUG_DRIVER("\n"); /* Copy the drm display mode in the connector local structure */ - memcpy(&hdmi->mode, mode, sizeof(struct drm_display_mode)); + drm_mode_copy(&hdmi->mode, mode); /* Update clock framerate according to the selected mode */ ret = clk_set_rate(hdmi->clk_pix, mode->clock * 1000); From 100caacfa0ed26e061954c90cdc835d42f709536 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Fri, 16 Sep 2022 16:33:05 -0700 Subject: [PATCH 0599/4345] drivers/md/md-bitmap: check the return value of md_bitmap_get_counter() [ Upstream commit 3bd548e5b819b8c0f2c9085de775c5c7bff9052f ] Check the return value of md_bitmap_get_counter() in case it returns NULL pointer, which will result in a null pointer dereference. v2: update the check to include other dereference Signed-off-by: Li Zhong Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/md-bitmap.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index d377ea060925..4e52fcf98d59 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2196,20 +2196,23 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, if (set) { bmc_new = md_bitmap_get_counter(&bitmap->counts, block, &new_blocks, 1); - if (*bmc_new == 0) { - /* need to set on-disk bits too. */ - sector_t end = block + new_blocks; - sector_t start = block >> chunkshift; - start <<= chunkshift; - while (start < end) { - md_bitmap_file_set_bit(bitmap, block); - start += 1 << chunkshift; + if (bmc_new) { + if (*bmc_new == 0) { + /* need to set on-disk bits too. */ + sector_t end = block + new_blocks; + sector_t start = block >> chunkshift; + + start <<= chunkshift; + while (start < end) { + md_bitmap_file_set_bit(bitmap, block); + start += 1 << chunkshift; + } + *bmc_new = 2; + md_bitmap_count_page(&bitmap->counts, block, 1); + md_bitmap_set_pending(&bitmap->counts, block); } - *bmc_new = 2; - md_bitmap_count_page(&bitmap->counts, block, 1); - md_bitmap_set_pending(&bitmap->counts, block); + *bmc_new |= NEEDED_MASK; } - *bmc_new |= NEEDED_MASK; if (new_blocks < old_blocks) old_blocks = new_blocks; } From 10d713532ffc67b13df61ed9c138a8ce0a186236 Mon Sep 17 00:00:00 2001 From: Jiang Li Date: Mon, 7 Nov 2022 22:16:59 +0800 Subject: [PATCH 0600/4345] md/raid1: stop mdx_raid1 thread when raid1 array run failed [ Upstream commit b611ad14006e5be2170d9e8e611bf49dff288911 ] fail run raid1 array when we assemble array with the inactive disk only, but the mdx_raid1 thread were not stop, Even if the associated resources have been released. it will caused a NULL dereference when we do poweroff. This causes the following Oops: [ 287.587787] BUG: kernel NULL pointer dereference, address: 0000000000000070 [ 287.594762] #PF: supervisor read access in kernel mode [ 287.599912] #PF: error_code(0x0000) - not-present page [ 287.605061] PGD 0 P4D 0 [ 287.607612] Oops: 0000 [#1] SMP NOPTI [ 287.611287] CPU: 3 PID: 5265 Comm: md0_raid1 Tainted: G U 5.10.146 #0 [ 287.619029] Hardware name: xxxxxxx/To be filled by O.E.M, BIOS 5.19 06/16/2022 [ 287.626775] RIP: 0010:md_check_recovery+0x57/0x500 [md_mod] [ 287.632357] Code: fe 01 00 00 48 83 bb 10 03 00 00 00 74 08 48 89 ...... [ 287.651118] RSP: 0018:ffffc90000433d78 EFLAGS: 00010202 [ 287.656347] RAX: 0000000000000000 RBX: ffff888105986800 RCX: 0000000000000000 [ 287.663491] RDX: ffffc90000433bb0 RSI: 00000000ffffefff RDI: ffff888105986800 [ 287.670634] RBP: ffffc90000433da0 R08: 0000000000000000 R09: c0000000ffffefff [ 287.677771] R10: 0000000000000001 R11: ffffc90000433ba8 R12: ffff888105986800 [ 287.684907] R13: 0000000000000000 R14: fffffffffffffe00 R15: ffff888100b6b500 [ 287.692052] FS: 0000000000000000(0000) GS:ffff888277f80000(0000) knlGS:0000000000000000 [ 287.700149] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 287.705897] CR2: 0000000000000070 CR3: 000000000320a000 CR4: 0000000000350ee0 [ 287.713033] Call Trace: [ 287.715498] raid1d+0x6c/0xbbb [raid1] [ 287.719256] ? __schedule+0x1ff/0x760 [ 287.722930] ? schedule+0x3b/0xb0 [ 287.726260] ? schedule_timeout+0x1ed/0x290 [ 287.730456] ? __switch_to+0x11f/0x400 [ 287.734219] md_thread+0xe9/0x140 [md_mod] [ 287.738328] ? md_thread+0xe9/0x140 [md_mod] [ 287.742601] ? wait_woken+0x80/0x80 [ 287.746097] ? md_register_thread+0xe0/0xe0 [md_mod] [ 287.751064] kthread+0x11a/0x140 [ 287.754300] ? kthread_park+0x90/0x90 [ 287.757974] ret_from_fork+0x1f/0x30 In fact, when raid1 array run fail, we need to do md_unregister_thread() before raid1_free(). Signed-off-by: Jiang Li Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/raid1.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index fb31e5dd54a6..6b5cc3f59fb3 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -3115,6 +3115,7 @@ static int raid1_run(struct mddev *mddev) * RAID1 needs at least one disk in active */ if (conf->raid_disks - mddev->degraded < 1) { + md_unregister_thread(&conf->thread); ret = -EINVAL; goto abort; } From e2d60023aff444152c996093c0dc4ffd229e5143 Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Wed, 2 Nov 2022 15:35:53 -0400 Subject: [PATCH 0601/4345] drm/amd/display: fix array index out of bound error in bios parser [ Upstream commit 4fc1ba4aa589ca267468ad23fedef37562227d32 ] [Why&How] Firmware headers dictate that gpio_pin array only has a size of 8. The count returned from vbios however is greater than 8. Fix this by not using array indexing but incrementing the pointer since gpio_pin definition in atomfirmware.h is hardcoded to size 8 Reviewed-by: Martin Leung Acked-by: Tom Chung Signed-off-by: Aurabindo Pillai Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../gpu/drm/amd/display/dc/bios/bios_parser2.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 29d64e7e304f..930d2b7d3448 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -352,6 +352,7 @@ static enum bp_result get_gpio_i2c_info( uint32_t count = 0; unsigned int table_index = 0; bool find_valid = false; + struct atom_gpio_pin_assignment *pin; if (!info) return BP_RESULT_BADINPUT; @@ -379,20 +380,17 @@ static enum bp_result get_gpio_i2c_info( - sizeof(struct atom_common_table_header)) / sizeof(struct atom_gpio_pin_assignment); + pin = (struct atom_gpio_pin_assignment *) header->gpio_pin; + for (table_index = 0; table_index < count; table_index++) { - if (((record->i2c_id & I2C_HW_CAP) == ( - header->gpio_pin[table_index].gpio_id & - I2C_HW_CAP)) && - ((record->i2c_id & I2C_HW_ENGINE_ID_MASK) == - (header->gpio_pin[table_index].gpio_id & - I2C_HW_ENGINE_ID_MASK)) && - ((record->i2c_id & I2C_HW_LANE_MUX) == - (header->gpio_pin[table_index].gpio_id & - I2C_HW_LANE_MUX))) { + if (((record->i2c_id & I2C_HW_CAP) == (pin->gpio_id & I2C_HW_CAP)) && + ((record->i2c_id & I2C_HW_ENGINE_ID_MASK) == (pin->gpio_id & I2C_HW_ENGINE_ID_MASK)) && + ((record->i2c_id & I2C_HW_LANE_MUX) == (pin->gpio_id & I2C_HW_LANE_MUX))) { /* still valid */ find_valid = true; break; } + pin = (struct atom_gpio_pin_assignment *)((uint8_t *)pin + sizeof(struct atom_gpio_pin_assignment)); } /* If we don't find the entry that we are looking for then From 037db10e3f93f0d51ab3f52fbdaa7e67a7edd0b8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 15 Nov 2022 08:53:55 +0000 Subject: [PATCH 0602/4345] net: add atomic_long_t to net_device_stats fields [ Upstream commit 6c1c5097781f563b70a81683ea6fdac21637573b ] Long standing KCSAN issues are caused by data-race around some dev->stats changes. Most performance critical paths already use per-cpu variables, or per-queue ones. It is reasonable (and more correct) to use atomic operations for the slow paths. This patch adds an union for each field of net_device_stats, so that we can convert paths that are not yet protected by a spinlock or a mutex. netdev_stats_to_stats64() no longer has an #if BITS_PER_LONG==64 Note that the memcpy() we were using on 64bit arches had no provision to avoid load-tearing, while atomic_long_read() is providing the needed protection at no cost. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/netdevice.h | 58 +++++++++++++++++++++++---------------- include/net/dst.h | 5 ++-- net/core/dev.c | 14 ++-------- 3 files changed, 40 insertions(+), 37 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ef75567efd27..b478a16ef284 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -166,31 +166,38 @@ static inline bool dev_xmit_complete(int rc) * (unsigned long) so they can be read and written atomically. */ +#define NET_DEV_STAT(FIELD) \ + union { \ + unsigned long FIELD; \ + atomic_long_t __##FIELD; \ + } + struct net_device_stats { - unsigned long rx_packets; - unsigned long tx_packets; - unsigned long rx_bytes; - unsigned long tx_bytes; - unsigned long rx_errors; - unsigned long tx_errors; - unsigned long rx_dropped; - unsigned long tx_dropped; - unsigned long multicast; - unsigned long collisions; - unsigned long rx_length_errors; - unsigned long rx_over_errors; - unsigned long rx_crc_errors; - unsigned long rx_frame_errors; - unsigned long rx_fifo_errors; - unsigned long rx_missed_errors; - unsigned long tx_aborted_errors; - unsigned long tx_carrier_errors; - unsigned long tx_fifo_errors; - unsigned long tx_heartbeat_errors; - unsigned long tx_window_errors; - unsigned long rx_compressed; - unsigned long tx_compressed; + NET_DEV_STAT(rx_packets); + NET_DEV_STAT(tx_packets); + NET_DEV_STAT(rx_bytes); + NET_DEV_STAT(tx_bytes); + NET_DEV_STAT(rx_errors); + NET_DEV_STAT(tx_errors); + NET_DEV_STAT(rx_dropped); + NET_DEV_STAT(tx_dropped); + NET_DEV_STAT(multicast); + NET_DEV_STAT(collisions); + NET_DEV_STAT(rx_length_errors); + NET_DEV_STAT(rx_over_errors); + NET_DEV_STAT(rx_crc_errors); + NET_DEV_STAT(rx_frame_errors); + NET_DEV_STAT(rx_fifo_errors); + NET_DEV_STAT(rx_missed_errors); + NET_DEV_STAT(tx_aborted_errors); + NET_DEV_STAT(tx_carrier_errors); + NET_DEV_STAT(tx_fifo_errors); + NET_DEV_STAT(tx_heartbeat_errors); + NET_DEV_STAT(tx_window_errors); + NET_DEV_STAT(rx_compressed); + NET_DEV_STAT(tx_compressed); }; +#undef NET_DEV_STAT #include @@ -5256,4 +5263,9 @@ do { \ extern struct net_device *blackhole_netdev; +/* Note: Avoid these macros in fast path, prefer per-cpu or per-queue counters. */ +#define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD) +#define DEV_STATS_ADD(DEV, FIELD, VAL) \ + atomic_long_add((VAL), &(DEV)->stats.__##FIELD) + #endif /* _LINUX_NETDEVICE_H */ diff --git a/include/net/dst.h b/include/net/dst.h index acd15c544cf3..ae2cf57d796b 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -356,9 +356,8 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { - /* TODO : stats should be SMP safe */ - dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + DEV_STATS_INC(dev, rx_packets); + DEV_STATS_ADD(dev, rx_bytes, skb->len); __skb_tunnel_rx(skb, dev, net); } diff --git a/net/core/dev.c b/net/core/dev.c index a421c54331ea..37bb60a7e97e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10320,24 +10320,16 @@ void netdev_run_todo(void) void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { -#if BITS_PER_LONG == 64 - BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats)); - memcpy(stats64, netdev_stats, sizeof(*netdev_stats)); - /* zero out counters that only exist in rtnl_link_stats64 */ - memset((char *)stats64 + sizeof(*netdev_stats), 0, - sizeof(*stats64) - sizeof(*netdev_stats)); -#else - size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long); - const unsigned long *src = (const unsigned long *)netdev_stats; + size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); + const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) - dst[i] = src[i]; + dst[i] = atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); -#endif } EXPORT_SYMBOL(netdev_stats_to_stats64); From 755eb0879224ffc2a43de724554aeaf0e51e5a64 Mon Sep 17 00:00:00 2001 From: Schspa Shi Date: Wed, 16 Nov 2022 19:45:11 +0800 Subject: [PATCH 0603/4345] mrp: introduce active flags to prevent UAF when applicant uninit [ Upstream commit ab0377803dafc58f1e22296708c1c28e309414d6 ] The caller of del_timer_sync must prevent restarting of the timer, If we have no this synchronization, there is a small probability that the cancellation will not be successful. And syzbot report the fellowing crash: ================================================================== BUG: KASAN: use-after-free in hlist_add_head include/linux/list.h:929 [inline] BUG: KASAN: use-after-free in enqueue_timer+0x18/0xa4 kernel/time/timer.c:605 Write at addr f9ff000024df6058 by task syz-fuzzer/2256 Pointer tag: [f9], memory tag: [fe] CPU: 1 PID: 2256 Comm: syz-fuzzer Not tainted 6.1.0-rc5-syzkaller-00008- ge01d50cbd6ee #0 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace.part.0+0xe0/0xf0 arch/arm64/kernel/stacktrace.c:156 dump_backtrace arch/arm64/kernel/stacktrace.c:162 [inline] show_stack+0x18/0x40 arch/arm64/kernel/stacktrace.c:163 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x68/0x84 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:284 [inline] print_report+0x1a8/0x4a0 mm/kasan/report.c:395 kasan_report+0x94/0xb4 mm/kasan/report.c:495 __do_kernel_fault+0x164/0x1e0 arch/arm64/mm/fault.c:320 do_bad_area arch/arm64/mm/fault.c:473 [inline] do_tag_check_fault+0x78/0x8c arch/arm64/mm/fault.c:749 do_mem_abort+0x44/0x94 arch/arm64/mm/fault.c:825 el1_abort+0x40/0x60 arch/arm64/kernel/entry-common.c:367 el1h_64_sync_handler+0xd8/0xe4 arch/arm64/kernel/entry-common.c:427 el1h_64_sync+0x64/0x68 arch/arm64/kernel/entry.S:576 hlist_add_head include/linux/list.h:929 [inline] enqueue_timer+0x18/0xa4 kernel/time/timer.c:605 mod_timer+0x14/0x20 kernel/time/timer.c:1161 mrp_periodic_timer_arm net/802/mrp.c:614 [inline] mrp_periodic_timer+0xa0/0xc0 net/802/mrp.c:627 call_timer_fn.constprop.0+0x24/0x80 kernel/time/timer.c:1474 expire_timers+0x98/0xc4 kernel/time/timer.c:1519 To fix it, we can introduce a new active flags to make sure the timer will not restart. Reported-by: syzbot+6fd64001c20aa99e34a4@syzkaller.appspotmail.com Signed-off-by: Schspa Shi Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/mrp.h | 1 + net/802/mrp.c | 18 +++++++++++++----- 2 files changed, 14 insertions(+), 5 deletions(-) diff --git a/include/net/mrp.h b/include/net/mrp.h index 1c308c034e1a..a8102661fd61 100644 --- a/include/net/mrp.h +++ b/include/net/mrp.h @@ -120,6 +120,7 @@ struct mrp_applicant { struct sk_buff *pdu; struct rb_root mad; struct rcu_head rcu; + bool active; }; struct mrp_port { diff --git a/net/802/mrp.c b/net/802/mrp.c index 35e04cc5390c..c10a432a5b43 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -606,7 +606,10 @@ static void mrp_join_timer(struct timer_list *t) spin_unlock(&app->lock); mrp_queue_xmit(app); - mrp_join_timer_arm(app); + spin_lock(&app->lock); + if (likely(app->active)) + mrp_join_timer_arm(app); + spin_unlock(&app->lock); } static void mrp_periodic_timer_arm(struct mrp_applicant *app) @@ -620,11 +623,12 @@ static void mrp_periodic_timer(struct timer_list *t) struct mrp_applicant *app = from_timer(app, t, periodic_timer); spin_lock(&app->lock); - mrp_mad_event(app, MRP_EVENT_PERIODIC); - mrp_pdu_queue(app); + if (likely(app->active)) { + mrp_mad_event(app, MRP_EVENT_PERIODIC); + mrp_pdu_queue(app); + mrp_periodic_timer_arm(app); + } spin_unlock(&app->lock); - - mrp_periodic_timer_arm(app); } static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset) @@ -872,6 +876,7 @@ int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl) app->dev = dev; app->app = appl; app->mad = RB_ROOT; + app->active = true; spin_lock_init(&app->lock); skb_queue_head_init(&app->queue); rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app); @@ -900,6 +905,9 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) RCU_INIT_POINTER(port->applicants[appl->type], NULL); + spin_lock_bh(&app->lock); + app->active = false; + spin_unlock_bh(&app->lock); /* Delete timer and generate a final TX event to flush out * all pending messages before the applicant is gone. */ From 148dcbd3af039ae39c3af697a3183008c7995805 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 21 Nov 2022 10:29:13 -0800 Subject: [PATCH 0604/4345] ppp: associate skb with a device at tx [ Upstream commit 9f225444467b98579cf28d94f4ad053460dfdb84 ] Syzkaller triggered flow dissector warning with the following: r0 = openat$ppp(0xffffffffffffff9c, &(0x7f0000000000), 0xc0802, 0x0) ioctl$PPPIOCNEWUNIT(r0, 0xc004743e, &(0x7f00000000c0)) ioctl$PPPIOCSACTIVE(r0, 0x40107446, &(0x7f0000000240)={0x2, &(0x7f0000000180)=[{0x20, 0x0, 0x0, 0xfffff034}, {0x6}]}) pwritev(r0, &(0x7f0000000040)=[{&(0x7f0000000140)='\x00!', 0x2}], 0x1, 0x0, 0x0) [ 9.485814] WARNING: CPU: 3 PID: 329 at net/core/flow_dissector.c:1016 __skb_flow_dissect+0x1ee0/0x1fa0 [ 9.485929] skb_get_poff+0x53/0xa0 [ 9.485937] bpf_skb_get_pay_offset+0xe/0x20 [ 9.485944] ? ppp_send_frame+0xc2/0x5b0 [ 9.485949] ? _raw_spin_unlock_irqrestore+0x40/0x60 [ 9.485958] ? __ppp_xmit_process+0x7a/0xe0 [ 9.485968] ? ppp_xmit_process+0x5b/0xb0 [ 9.485974] ? ppp_write+0x12a/0x190 [ 9.485981] ? do_iter_write+0x18e/0x2d0 [ 9.485987] ? __import_iovec+0x30/0x130 [ 9.485997] ? do_pwritev+0x1b6/0x240 [ 9.486016] ? trace_hardirqs_on+0x47/0x50 [ 9.486023] ? __x64_sys_pwritev+0x24/0x30 [ 9.486026] ? do_syscall_64+0x3d/0x80 [ 9.486031] ? entry_SYSCALL_64_after_hwframe+0x63/0xcd Flow dissector tries to find skb net namespace either via device or via socket. Neigher is set in ppp_send_frame, so let's manually use ppp->dev. Cc: Paul Mackerras Cc: linux-ppp@vger.kernel.org Reported-by: syzbot+41cab52ab62ee99ed24a@syzkaller.appspotmail.com Signed-off-by: Stanislav Fomichev Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ppp/ppp_generic.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 2b9815ec4a62..b825c6a9b6dd 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1610,6 +1610,8 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) int len; unsigned char *cp; + skb->dev = ppp->dev; + if (proto < 0x8000) { #ifdef CONFIG_PPP_FILTER /* check if we should pass this packet */ From 329a76635548ee8fceb3b78c7d54d96524e80925 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 22 Nov 2022 19:54:22 -0800 Subject: [PATCH 0605/4345] bpf: Prevent decl_tag from being referenced in func_proto arg [ Upstream commit f17472d4599697d701aa239b4c475a506bccfd19 ] Syzkaller managed to hit another decl_tag issue: btf_func_proto_check kernel/bpf/btf.c:4506 [inline] btf_check_all_types kernel/bpf/btf.c:4734 [inline] btf_parse_type_sec+0x1175/0x1980 kernel/bpf/btf.c:4763 btf_parse kernel/bpf/btf.c:5042 [inline] btf_new_fd+0x65a/0xb00 kernel/bpf/btf.c:6709 bpf_btf_load+0x6f/0x90 kernel/bpf/syscall.c:4342 __sys_bpf+0x50a/0x6c0 kernel/bpf/syscall.c:5034 __do_sys_bpf kernel/bpf/syscall.c:5093 [inline] __se_sys_bpf kernel/bpf/syscall.c:5091 [inline] __x64_sys_bpf+0x7c/0x90 kernel/bpf/syscall.c:5091 do_syscall_64+0x54/0x70 arch/x86/entry/common.c:48 This seems similar to commit ea68376c8bed ("bpf: prevent decl_tag from being referenced in func_proto") but for the argument. Reported-by: syzbot+8dd0551dda6020944c5d@syzkaller.appspotmail.com Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20221123035422.872531-2-sdf@google.com Signed-off-by: Sasha Levin --- kernel/bpf/btf.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9232938e3f96..52e704860739 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3675,6 +3675,11 @@ static int btf_func_proto_check(struct btf_verifier_env *env, break; } + if (btf_type_is_resolve_source_only(arg_type)) { + btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); + return -EINVAL; + } + if (args[i].name_off && (!btf_name_offset_valid(btf, args[i].name_off) || !btf_name_valid_identifier(btf, args[i].name_off))) { From dd1e1bf916da66ab23ae476a90bd3b943ccc3248 Mon Sep 17 00:00:00 2001 From: Maxim Korotkov Date: Tue, 22 Nov 2022 15:29:01 +0300 Subject: [PATCH 0606/4345] ethtool: avoiding integer overflow in ethtool_phys_id() [ Upstream commit 64a8f8f7127da228d59a39e2c5e75f86590f90b4 ] The value of an arithmetic expression "n * id.data" is subject to possible overflow due to a failure to cast operands to a larger data type before performing arithmetic. Used macro for multiplication instead operator for avoiding overflow. Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Maxim Korotkov Reviewed-by: Alexander Lobakin Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20221122122901.22294-1-korotkov.maxim.s@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ethtool/ioctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 80d2a00d3097..47c2dd4a9b9f 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1966,7 +1966,8 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) } else { /* Driver expects to be called at twice the frequency in rc */ int n = rc * 2, interval = HZ / n; - u64 count = n * id.data, i = 0; + u64 count = mul_u32_u32(n, id.data); + u64 i = 0; do { rtnl_lock(); From b42580c8d8aac11a66046897979cc13cfd04c541 Mon Sep 17 00:00:00 2001 From: Yan Lei Date: Sun, 10 Apr 2022 07:19:25 +0100 Subject: [PATCH 0607/4345] media: dvb-frontends: fix leak of memory fw [ Upstream commit a15fe8d9f1bf460a804bcf18a890bfd2cf0d5caa ] Link: https://lore.kernel.org/linux-media/20220410061925.4107-1-chinayanlei2002@163.com Signed-off-by: Yan Lei Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/dvb-frontends/bcm3510.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c index da0ff7b44da4..68b92b4419cf 100644 --- a/drivers/media/dvb-frontends/bcm3510.c +++ b/drivers/media/dvb-frontends/bcm3510.c @@ -649,6 +649,7 @@ static int bcm3510_download_firmware(struct dvb_frontend* fe) deb_info("firmware chunk, addr: 0x%04x, len: 0x%04x, total length: 0x%04zx\n",addr,len,fw->size); if ((ret = bcm3510_write_ram(st,addr,&b[i+4],len)) < 0) { err("firmware download failed: %d\n",ret); + release_firmware(fw); return ret; } i += 4 + len; From 2abd73433872194bccdf1432a0980e4ec5273c2a Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 7 Aug 2022 15:59:52 +0100 Subject: [PATCH 0608/4345] media: dvbdev: adopts refcnt to avoid UAF [ Upstream commit 0fc044b2b5e2d05a1fa1fb0d7f270367a7855d79 ] dvb_unregister_device() is known that prone to use-after-free. That is, the cleanup from dvb_unregister_device() releases the dvb_device even if there are pointers stored in file->private_data still refer to it. This patch adds a reference counter into struct dvb_device and delays its deallocation until no pointer refers to the object. Link: https://lore.kernel.org/linux-media/20220807145952.10368-1-linma@zju.edu.cn Signed-off-by: Lin Ma Reported-by: kernel test robot Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/dvb-core/dvb_ca_en50221.c | 2 +- drivers/media/dvb-core/dvb_frontend.c | 2 +- drivers/media/dvb-core/dvbdev.c | 32 +++++++++++++++++++------ include/media/dvbdev.h | 31 +++++++++++++----------- 4 files changed, 44 insertions(+), 23 deletions(-) diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index cfc27629444f..fd476536d32e 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -157,7 +157,7 @@ static void dvb_ca_private_free(struct dvb_ca_private *ca) { unsigned int i; - dvb_free_device(ca->dvbdev); + dvb_device_put(ca->dvbdev); for (i = 0; i < ca->slot_count; i++) vfree(ca->slot_info[i].rx_buffer.data); diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index b28ea7204f23..b04638321b75 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -135,7 +135,7 @@ static void __dvb_frontend_free(struct dvb_frontend *fe) struct dvb_frontend_private *fepriv = fe->frontend_priv; if (fepriv) - dvb_free_device(fepriv->dvbdev); + dvb_device_put(fepriv->dvbdev); dvb_frontend_invoke_release(fe, fe->ops.release); diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index ec9ebff28552..7b28b483e4b2 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -107,7 +107,7 @@ static int dvb_device_open(struct inode *inode, struct file *file) new_fops = fops_get(dvbdev->fops); if (!new_fops) goto fail; - file->private_data = dvbdev; + file->private_data = dvb_device_get(dvbdev); replace_fops(file, new_fops); if (file->f_op->open) err = file->f_op->open(inode, file); @@ -171,6 +171,9 @@ int dvb_generic_release(struct inode *inode, struct file *file) } dvbdev->users++; + + dvb_device_put(dvbdev); + return 0; } EXPORT_SYMBOL(dvb_generic_release); @@ -487,6 +490,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, return -ENOMEM; } + kref_init(&dvbdev->ref); memcpy(dvbdev, template, sizeof(struct dvb_device)); dvbdev->type = type; dvbdev->id = id; @@ -517,7 +521,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, #endif dvbdev->minor = minor; - dvb_minors[minor] = dvbdev; + dvb_minors[minor] = dvb_device_get(dvbdev); up_write(&minor_rwsem); ret = dvb_register_media_device(dvbdev, type, minor, demux_sink_pads); @@ -557,6 +561,7 @@ void dvb_remove_device(struct dvb_device *dvbdev) down_write(&minor_rwsem); dvb_minors[dvbdev->minor] = NULL; + dvb_device_put(dvbdev); up_write(&minor_rwsem); dvb_media_device_free(dvbdev); @@ -568,21 +573,34 @@ void dvb_remove_device(struct dvb_device *dvbdev) EXPORT_SYMBOL(dvb_remove_device); -void dvb_free_device(struct dvb_device *dvbdev) +static void dvb_free_device(struct kref *ref) { - if (!dvbdev) - return; + struct dvb_device *dvbdev = container_of(ref, struct dvb_device, ref); kfree (dvbdev->fops); kfree (dvbdev); } -EXPORT_SYMBOL(dvb_free_device); + + +struct dvb_device *dvb_device_get(struct dvb_device *dvbdev) +{ + kref_get(&dvbdev->ref); + return dvbdev; +} +EXPORT_SYMBOL(dvb_device_get); + + +void dvb_device_put(struct dvb_device *dvbdev) +{ + if (dvbdev) + kref_put(&dvbdev->ref, dvb_free_device); +} void dvb_unregister_device(struct dvb_device *dvbdev) { dvb_remove_device(dvbdev); - dvb_free_device(dvbdev); + dvb_device_put(dvbdev); } EXPORT_SYMBOL(dvb_unregister_device); diff --git a/include/media/dvbdev.h b/include/media/dvbdev.h index e547cbeee431..6e736587aa1f 100644 --- a/include/media/dvbdev.h +++ b/include/media/dvbdev.h @@ -156,6 +156,7 @@ struct dvb_adapter { */ struct dvb_device { struct list_head list_head; + struct kref ref; const struct file_operations *fops; struct dvb_adapter *adapter; enum dvb_device_type type; @@ -187,6 +188,20 @@ struct dvb_device { void *priv; }; +/** + * dvb_device_get - Increase dvb_device reference + * + * @dvbdev: pointer to struct dvb_device + */ +struct dvb_device *dvb_device_get(struct dvb_device *dvbdev); + +/** + * dvb_device_get - Decrease dvb_device reference + * + * @dvbdev: pointer to struct dvb_device + */ +void dvb_device_put(struct dvb_device *dvbdev); + /** * dvb_register_adapter - Registers a new DVB adapter * @@ -231,29 +246,17 @@ int dvb_register_device(struct dvb_adapter *adap, /** * dvb_remove_device - Remove a registered DVB device * - * This does not free memory. To do that, call dvb_free_device(). + * This does not free memory. dvb_free_device() will do that when + * reference counter is empty * * @dvbdev: pointer to struct dvb_device */ void dvb_remove_device(struct dvb_device *dvbdev); -/** - * dvb_free_device - Free memory occupied by a DVB device. - * - * Call dvb_unregister_device() before calling this function. - * - * @dvbdev: pointer to struct dvb_device - */ -void dvb_free_device(struct dvb_device *dvbdev); /** * dvb_unregister_device - Unregisters a DVB device * - * This is a combination of dvb_remove_device() and dvb_free_device(). - * Using this function is usually a mistake, and is often an indicator - * for a use-after-free bug (when a userspace process keeps a file - * handle to a detached device). - * * @dvbdev: pointer to struct dvb_device */ void dvb_unregister_device(struct dvb_device *dvbdev); From 7d7ab25ead969594df05fb09ee46ca931d46c5c8 Mon Sep 17 00:00:00 2001 From: Mazin Al Haddad Date: Wed, 24 Aug 2022 02:21:52 +0100 Subject: [PATCH 0609/4345] media: dvb-usb: fix memory leak in dvb_usb_adapter_init() [ Upstream commit 94d90fb06b94a90c176270d38861bcba34ce377d ] Syzbot reports a memory leak in "dvb_usb_adapter_init()". The leak is due to not accounting for and freeing current iteration's adapter->priv in case of an error. Currently if an error occurs, it will exit before incrementing "num_adapters_initalized", which is used as a reference counter to free all adap->priv in "dvb_usb_adapter_exit()". There are multiple error paths that can exit from before incrementing the counter. Including the error handling paths for "dvb_usb_adapter_stream_init()", "dvb_usb_adapter_dvb_init()" and "dvb_usb_adapter_frontend_init()" within "dvb_usb_adapter_init()". This means that in case of an error in any of these functions the current iteration is not accounted for and the current iteration's adap->priv is not freed. Fix this by freeing the current iteration's adap->priv in the "stream_init_err:" label in the error path. The rest of the (accounted for) adap->priv objects are freed in dvb_usb_adapter_exit() as expected using the num_adapters_initalized variable. Syzbot report: BUG: memory leak unreferenced object 0xffff8881172f1a00 (size 512): comm "kworker/0:2", pid 139, jiffies 4294994873 (age 10.960s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] dvb_usb_adapter_init drivers/media/usb/dvb-usb/dvb-usb-init.c:75 [inline] [] dvb_usb_init drivers/media/usb/dvb-usb/dvb-usb-init.c:184 [inline] [] dvb_usb_device_init.cold+0x4e5/0x79e drivers/media/usb/dvb-usb/dvb-usb-init.c:308 [] dib0700_probe+0x8d/0x1b0 drivers/media/usb/dvb-usb/dib0700_core.c:883 [] usb_probe_interface+0x177/0x370 drivers/usb/core/driver.c:396 [] call_driver_probe drivers/base/dd.c:542 [inline] [] really_probe.part.0+0xe7/0x310 drivers/base/dd.c:621 [] really_probe drivers/base/dd.c:583 [inline] [] __driver_probe_device+0x10c/0x1e0 drivers/base/dd.c:752 [] driver_probe_device+0x2a/0x120 drivers/base/dd.c:782 [] __device_attach_driver+0xf6/0x140 drivers/base/dd.c:899 [] bus_for_each_drv+0xb7/0x100 drivers/base/bus.c:427 [] __device_attach+0x122/0x260 drivers/base/dd.c:970 [] bus_probe_device+0xc6/0xe0 drivers/base/bus.c:487 [] device_add+0x5fb/0xdf0 drivers/base/core.c:3405 [] usb_set_configuration+0x8f2/0xb80 drivers/usb/core/message.c:2170 [] usb_generic_driver_probe+0x8c/0xc0 drivers/usb/core/generic.c:238 [] usb_probe_device+0x5c/0x140 drivers/usb/core/driver.c:293 [] call_driver_probe drivers/base/dd.c:542 [inline] [] really_probe.part.0+0xe7/0x310 drivers/base/dd.c:621 [] really_probe drivers/base/dd.c:583 [inline] [] __driver_probe_device+0x10c/0x1e0 drivers/base/dd.c:752 Link: https://syzkaller.appspot.com/bug?extid=f66dd31987e6740657be Reported-and-tested-by: syzbot+f66dd31987e6740657be@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-media/20220824012152.539788-1-mazinalhaddad05@gmail.com Signed-off-by: Mazin Al Haddad Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb/dvb-usb-init.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c index 61439c8f33ca..58eea8ab5477 100644 --- a/drivers/media/usb/dvb-usb/dvb-usb-init.c +++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c @@ -81,7 +81,7 @@ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) ret = dvb_usb_adapter_stream_init(adap); if (ret) - return ret; + goto stream_init_err; ret = dvb_usb_adapter_dvb_init(adap, adapter_nrs); if (ret) @@ -114,6 +114,8 @@ frontend_init_err: dvb_usb_adapter_dvb_exit(adap); dvb_init_err: dvb_usb_adapter_stream_exit(adap); +stream_init_err: + kfree(adap->priv); return ret; } From e8022da1fa2fdf2fa204b445dd3354e7a66d085a Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 17 Nov 2022 10:29:40 +0800 Subject: [PATCH 0610/4345] blk-mq: fix possible memleak when register 'hctx' failed [ Upstream commit 4b7a21c57b14fbcd0e1729150189e5933f5088e9 ] There's issue as follows when do fault injection test: unreferenced object 0xffff888132a9f400 (size 512): comm "insmod", pid 308021, jiffies 4324277909 (age 509.733s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 08 f4 a9 32 81 88 ff ff ...........2.... 08 f4 a9 32 81 88 ff ff 00 00 00 00 00 00 00 00 ...2............ backtrace: [<00000000e8952bb4>] kmalloc_node_trace+0x22/0xa0 [<00000000f9980e0f>] blk_mq_alloc_and_init_hctx+0x3f1/0x7e0 [<000000002e719efa>] blk_mq_realloc_hw_ctxs+0x1e6/0x230 [<000000004f1fda40>] blk_mq_init_allocated_queue+0x27e/0x910 [<00000000287123ec>] __blk_mq_alloc_disk+0x67/0xf0 [<00000000a2a34657>] 0xffffffffa2ad310f [<00000000b173f718>] 0xffffffffa2af824a [<0000000095a1dabb>] do_one_initcall+0x87/0x2a0 [<00000000f32fdf93>] do_init_module+0xdf/0x320 [<00000000cbe8541e>] load_module+0x3006/0x3390 [<0000000069ed1bdb>] __do_sys_finit_module+0x113/0x1b0 [<00000000a1a29ae8>] do_syscall_64+0x35/0x80 [<000000009cd878b0>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 Fault injection context as follows: kobject_add blk_mq_register_hctx blk_mq_sysfs_register blk_register_queue device_add_disk null_add_dev.part.0 [null_blk] As 'blk_mq_register_hctx' may already add some objects when failed halfway, but there isn't do fallback, caller don't know which objects add failed. To solve above issue just do fallback when add objects failed halfway in 'blk_mq_register_hctx'. Signed-off-by: Ye Bin Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20221117022940.873959-1-yebin@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-mq-sysfs.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 7b52e7657b2d..f0bc3398f3ed 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -242,7 +242,7 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct blk_mq_ctx *ctx; - int i, ret; + int i, j, ret; if (!hctx->nr_ctx) return 0; @@ -254,9 +254,16 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) hctx_for_each_ctx(hctx, ctx, i) { ret = kobject_add(&ctx->kobj, &hctx->kobj, "cpu%u", ctx->cpu); if (ret) - break; + goto out; } + return 0; +out: + hctx_for_each_ctx(hctx, ctx, j) { + if (j < i) + kobject_del(&ctx->kobj); + } + kobject_del(&hctx->kobj); return ret; } From 17c2eb9ce8c16439b1ead765f565a38238cd94e0 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 30 Nov 2022 12:00:12 -0800 Subject: [PATCH 0611/4345] libbpf: Avoid enum forward-declarations in public API in C++ mode [ Upstream commit b42693415b86f608049cf1b4870adc1dc65e58b0 ] C++ enum forward declarations are fundamentally not compatible with pure C enum definitions, and so libbpf's use of `enum bpf_stats_type;` forward declaration in libbpf/bpf.h public API header is causing C++ compilation issues. More details can be found in [0], but it comes down to C++ supporting enum forward declaration only with explicitly specified backing type: enum bpf_stats_type: int; In C (and I believe it's a GCC extension also), such forward declaration is simply: enum bpf_stats_type; Further, in Linux UAPI this enum is defined in pure C way: enum bpf_stats_type { BPF_STATS_RUN_TIME = 0; } And even though in both cases backing type is int, which can be confirmed by looking at DWARF information, for C++ compiler actual enum definition and forward declaration are incompatible. To eliminate this problem, for C++ mode define input argument as int, which makes enum unnecessary in libbpf public header. This solves the issue and as demonstrated by next patch doesn't cause any unwanted compiler warnings, at least with default warnings setting. [0] https://stackoverflow.com/questions/42766839/c11-enum-forward-causes-underlying-type-mismatch [1] Closes: https://github.com/libbpf/libbpf/issues/249 Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20221130200013.2997831-1-andrii@kernel.org Signed-off-by: Sasha Levin --- tools/lib/bpf/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 875dde20d56e..92a3eaa154dd 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -241,8 +241,15 @@ LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); +#ifdef __cplusplus +/* forward-declaring enums in C++ isn't compatible with pure C enums, so + * instead define bpf_enable_stats() as accepting int as an input + */ +LIBBPF_API int bpf_enable_stats(int type); +#else enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */ LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type); +#endif struct bpf_prog_bind_opts { size_t sz; /* size of this struct for forward/backward compatibility */ From 4b737246ff50f810d6ab4be13c1388a07f0c14b1 Mon Sep 17 00:00:00 2001 From: Rui Zhang Date: Thu, 1 Dec 2022 11:38:06 +0800 Subject: [PATCH 0612/4345] regulator: core: fix use_count leakage when handling boot-on MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0591b14ce0398125439c759f889647369aa616a0 ] I found a use_count leakage towards supply regulator of rdev with boot-on option. ┌───────────────────┐ ┌───────────────────┐ │ regulator_dev A │ │ regulator_dev B │ │ (boot-on) │ │ (boot-on) │ │ use_count=0 │◀──supply──│ use_count=1 │ │ │ │ │ └───────────────────┘ └───────────────────┘ In case of rdev(A) configured with `regulator-boot-on', the use_count of supplying regulator(B) will increment inside regulator_enable(rdev->supply). Thus, B will acts like always-on, and further balanced regulator_enable/disable cannot actually disable it anymore. However, B was also configured with `regulator-boot-on', we wish it could be disabled afterwards. Signed-off-by: Rui Zhang Link: https://lore.kernel.org/r/20221201033806.2567812-1-zr.zhang@vivo.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 4472c31b9b00..df746ba5c1bc 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1428,7 +1428,13 @@ static int set_machine_constraints(struct regulator_dev *rdev) if (rdev->supply_name && !rdev->supply) return -EPROBE_DEFER; - if (rdev->supply) { + /* If supplying regulator has already been enabled, + * it's not intended to have use_count increment + * when rdev is only boot-on. + */ + if (rdev->supply && + (rdev->constraints->always_on || + !regulator_is_enabled(rdev->supply))) { ret = regulator_enable(rdev->supply); if (ret < 0) { _regulator_put(rdev->supply); From 58e21146c0f99958a5ad89fdc16ce0f387351899 Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Fri, 11 Nov 2022 17:10:33 +0900 Subject: [PATCH 0613/4345] mmc: f-sdh30: Add quirks for broken timeout clock capability [ Upstream commit aae9d3a440736691b3c1cb09ae2c32c4f1ee2e67 ] There is a case where the timeout clock is not supplied to the capability. Add a quirk for that. Signed-off-by: Kunihiko Hayashi Acked-by: Jassi Brar Link: https://lore.kernel.org/r/20221111081033.3813-7-hayashi.kunihiko@socionext.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/sdhci_f_sdh30.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mmc/host/sdhci_f_sdh30.c b/drivers/mmc/host/sdhci_f_sdh30.c index 3f5977979cf2..6c4f43e11282 100644 --- a/drivers/mmc/host/sdhci_f_sdh30.c +++ b/drivers/mmc/host/sdhci_f_sdh30.c @@ -168,6 +168,9 @@ static int sdhci_f_sdh30_probe(struct platform_device *pdev) if (reg & SDHCI_CAN_DO_8BIT) priv->vendor_hs200 = F_SDH30_EMMC_HS200; + if (!(reg & SDHCI_TIMEOUT_CLK_MASK)) + host->quirks |= SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK; + ret = sdhci_add_host(host); if (ret) goto err_add_host; From a63a1ae13469079994af1a24167f6f42b49eab34 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sun, 20 Nov 2022 12:34:55 +0100 Subject: [PATCH 0614/4345] mmc: renesas_sdhi: better reset from HS400 mode [ Upstream commit 0da69dd2155019ed4c444ede0e79ce7a4a6af627 ] Up to now, HS400 adjustment mode was only disabled on soft reset when a calibration table was in use. It is safer, though, to disable it as soon as the instance has an adjustment related quirk set, i.e. bad taps or a calibration table. Signed-off-by: Wolfram Sang Reviewed-by: Yoshihiro Shimoda Tested-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20221120113457.42010-3-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/renesas_sdhi_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index ac01fb518386..a49b8fe2a098 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -537,7 +537,7 @@ static void renesas_sdhi_reset_hs400_mode(struct tmio_mmc_host *host, SH_MOBILE_SDHI_SCC_TMPPORT2_HS400OSEL) & sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_TMPPORT2)); - if (priv->adjust_hs400_calib_table) + if (priv->quirks && (priv->quirks->hs400_calib_table || priv->quirks->hs400_bad_taps)) renesas_sdhi_adjust_hs400_mode_disable(host); sd_ctrl_write16(host, CTL_SD_CARD_CLK_CTL, CLK_CTL_SCLKEN | From 1c6447d0fc68650e51586dde79b5090d9d77f13a Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Wed, 23 Nov 2022 03:51:59 +0900 Subject: [PATCH 0615/4345] media: si470x: Fix use-after-free in si470x_int_in_callback() [ Upstream commit 7d21e0b1b41b21d628bf2afce777727bd4479aa5 ] syzbot reported use-after-free in si470x_int_in_callback() [1]. This indicates that urb->context, which contains struct si470x_device object, is freed when si470x_int_in_callback() is called. The cause of this issue is that si470x_int_in_callback() is called for freed urb. si470x_usb_driver_probe() calls si470x_start_usb(), which then calls usb_submit_urb() and si470x_start(). If si470x_start_usb() fails, si470x_usb_driver_probe() doesn't kill urb, but it just frees struct si470x_device object, as depicted below: si470x_usb_driver_probe() ... si470x_start_usb() ... usb_submit_urb() retval = si470x_start() return retval if (retval < 0) free struct si470x_device object, but don't kill urb This patch fixes this issue by killing urb when si470x_start_usb() fails and urb is submitted. If si470x_start_usb() fails and urb is not submitted, i.e. submitting usb fails, it just frees struct si470x_device object. Reported-by: syzbot+9ca7a12fd736d93e0232@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=94ed6dddd5a55e90fd4bab942aa4bb297741d977 [1] Signed-off-by: Shigeru Yoshida Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/radio/si470x/radio-si470x-usb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/radio/si470x/radio-si470x-usb.c b/drivers/media/radio/si470x/radio-si470x-usb.c index 3f8634a46573..1365ae732b79 100644 --- a/drivers/media/radio/si470x/radio-si470x-usb.c +++ b/drivers/media/radio/si470x/radio-si470x-usb.c @@ -733,8 +733,10 @@ static int si470x_usb_driver_probe(struct usb_interface *intf, /* start radio */ retval = si470x_start_usb(radio); - if (retval < 0) + if (retval < 0 && !radio->int_in_running) goto err_buf; + else if (retval < 0) /* in case of radio->int_in_running == 1 */ + goto err_all; /* set initial frequency */ si470x_set_freq(radio, 87.5 * FREQ_MUL); /* available in all regions */ From efd025f32fce27a8ada9bcb4731e8a84476e5b3d Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Tue, 22 Nov 2022 21:36:14 +0800 Subject: [PATCH 0616/4345] clk: st: Fix memory leak in st_of_quadfs_setup() [ Upstream commit cfd3ffb36f0d566846163118651d868e607300ba ] If st_clk_register_quadfs_pll() fails, @lock should be freed before goto @err_exit, otherwise will cause meory leak issue, fix it. Signed-off-by: Xiu Jianfeng Link: https://lore.kernel.org/r/20221122133614.184910-1-xiujianfeng@huawei.com Reviewed-by: Patrice Chotard Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/st/clkgen-fsyn.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/clk/st/clkgen-fsyn.c b/drivers/clk/st/clkgen-fsyn.c index f1adc858b590..0e58a7cda427 100644 --- a/drivers/clk/st/clkgen-fsyn.c +++ b/drivers/clk/st/clkgen-fsyn.c @@ -942,9 +942,10 @@ static void __init st_of_quadfs_setup(struct device_node *np, clk = st_clk_register_quadfs_pll(pll_name, clk_parent_name, data, reg, lock); - if (IS_ERR(clk)) + if (IS_ERR(clk)) { + kfree(lock); goto err_exit; - else + } else pr_debug("%s: parent %s rate %u\n", __clk_get_name(clk), __clk_get_name(clk_get_parent(clk)), From dcd28191be9bbf307ba51a5b485773a55b0037c4 Mon Sep 17 00:00:00 2001 From: Hawkins Jiawei Date: Fri, 21 Oct 2022 07:16:08 +0800 Subject: [PATCH 0617/4345] hugetlbfs: fix null-ptr-deref in hugetlbfs_parse_param() [ Upstream commit 26215b7ee923b9251f7bb12c4e5f09dc465d35f2 ] Syzkaller reports a null-ptr-deref bug as follows: ====================================================== KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:hugetlbfs_parse_param+0x1dd/0x8e0 fs/hugetlbfs/inode.c:1380 [...] Call Trace: vfs_parse_fs_param fs/fs_context.c:148 [inline] vfs_parse_fs_param+0x1f9/0x3c0 fs/fs_context.c:129 vfs_parse_fs_string+0xdb/0x170 fs/fs_context.c:191 generic_parse_monolithic+0x16f/0x1f0 fs/fs_context.c:231 do_new_mount fs/namespace.c:3036 [inline] path_mount+0x12de/0x1e20 fs/namespace.c:3370 do_mount fs/namespace.c:3383 [inline] __do_sys_mount fs/namespace.c:3591 [inline] __se_sys_mount fs/namespace.c:3568 [inline] __x64_sys_mount+0x27f/0x300 fs/namespace.c:3568 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd [...] ====================================================== According to commit "vfs: parse: deal with zero length string value", kernel will set the param->string to null pointer in vfs_parse_fs_string() if fs string has zero length. Yet the problem is that, hugetlbfs_parse_param() will dereference the param->string, without checking whether it is a null pointer. To be more specific, if hugetlbfs_parse_param() parses an illegal mount parameter, such as "size=,", kernel will constructs struct fs_parameter with null pointer in vfs_parse_fs_string(), then passes this struct fs_parameter to hugetlbfs_parse_param(), which triggers the above null-ptr-deref bug. This patch solves it by adding sanity check on param->string in hugetlbfs_parse_param(). Link: https://lkml.kernel.org/r/20221020231609.4810-1-yin31149@gmail.com Reported-by: syzbot+a3e6acd85ded5c16a709@syzkaller.appspotmail.com Tested-by: syzbot+a3e6acd85ded5c16a709@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/0000000000005ad00405eb7148c6@google.com/ Signed-off-by: Hawkins Jiawei Reviewed-by: Mike Kravetz Cc: Hawkins Jiawei Cc: Muchun Song Cc: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/hugetlbfs/inode.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a2f43f1a85f8..5181e6d4e18c 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1261,7 +1261,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_size: /* memparse() will accept a K/M/G without a digit */ - if (!isdigit(param->string[0])) + if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->max_size_opt = memparse(param->string, &rest); ctx->max_val_type = SIZE_STD; @@ -1271,7 +1271,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_nr_inodes: /* memparse() will accept a K/M/G without a digit */ - if (!isdigit(param->string[0])) + if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->nr_inodes = memparse(param->string, &rest); return 0; @@ -1287,7 +1287,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_min_size: /* memparse() will accept a K/M/G without a digit */ - if (!isdigit(param->string[0])) + if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->min_size_opt = memparse(param->string, &rest); ctx->min_val_type = SIZE_STD; From f3d3f3564e8b28d39c540d30262dc34ab9e959d3 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 2 Nov 2022 08:42:15 -0700 Subject: [PATCH 0618/4345] drm/fsl-dcu: Fix return type of fsl_dcu_drm_connector_mode_valid() [ Upstream commit 96d845a67b7e406cfed7880a724c8ca6121e022e ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A proposed warning in clang aims to catch these at compile time, which reveals: drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c:74:16: error: incompatible function pointer types initializing 'enum drm_mode_status (*)(struct drm_connector *, struct drm_display_mode *)' with an expression of type 'int (struct drm_connector *, struct drm_display_mode *)' [-Werror,-Wincompatible-function-pointer-types-strict] .mode_valid = fsl_dcu_drm_connector_mode_valid, ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1 error generated. ->mode_valid() in 'struct drm_connector_helper_funcs' expects a return type of 'enum drm_mode_status', not 'int'. Adjust the return type of fsl_dcu_drm_connector_mode_valid() to match the prototype's to resolve the warning and CFI failure. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Reported-by: Sami Tolvanen Signed-off-by: Nathan Chancellor Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221102154215.78059-1-nathan@kernel.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c index 4d4a715b429d..2c2b92324a2e 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c @@ -60,8 +60,9 @@ static int fsl_dcu_drm_connector_get_modes(struct drm_connector *connector) return drm_panel_get_modes(fsl_connector->panel, connector); } -static int fsl_dcu_drm_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +fsl_dcu_drm_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { if (mode->hdisplay & 0xf) return MODE_ERROR; From 6e3c4d3fa5d458d685561ecbaf8daa9dba14979e Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 2 Nov 2022 08:56:23 -0700 Subject: [PATCH 0619/4345] drm/sti: Fix return type of sti_{dvo,hda,hdmi}_connector_mode_valid() [ Upstream commit 0ad811cc08a937d875cbad0149c1bab17f84ba05 ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A proposed warning in clang aims to catch these at compile time, which reveals: drivers/gpu/drm/sti/sti_hda.c:637:16: error: incompatible function pointer types initializing 'enum drm_mode_status (*)(struct drm_connector *, struct drm_display_mode *)' with an expression of type 'int (struct drm_connector *, struct drm_display_mode *)' [-Werror,-Wincompatible-function-pointer-types-strict] .mode_valid = sti_hda_connector_mode_valid, ^~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/sti/sti_dvo.c:376:16: error: incompatible function pointer types initializing 'enum drm_mode_status (*)(struct drm_connector *, struct drm_display_mode *)' with an expression of type 'int (struct drm_connector *, struct drm_display_mode *)' [-Werror,-Wincompatible-function-pointer-types-strict] .mode_valid = sti_dvo_connector_mode_valid, ^~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/sti/sti_hdmi.c:1035:16: error: incompatible function pointer types initializing 'enum drm_mode_status (*)(struct drm_connector *, struct drm_display_mode *)' with an expression of type 'int (struct drm_connector *, struct drm_display_mode *)' [-Werror,-Wincompatible-function-pointer-types-strict] .mode_valid = sti_hdmi_connector_mode_valid, ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ->mode_valid() in 'struct drm_connector_helper_funcs' expects a return type of 'enum drm_mode_status', not 'int'. Adjust the return type of sti_{dvo,hda,hdmi}_connector_mode_valid() to match the prototype's to resolve the warning and CFI failure. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Signed-off-by: Nathan Chancellor Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221102155623.3042869-1-nathan@kernel.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/sti/sti_dvo.c | 5 +++-- drivers/gpu/drm/sti/sti_hda.c | 5 +++-- drivers/gpu/drm/sti/sti_hdmi.c | 5 +++-- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c index b0676a73a1d7..11225ac213e1 100644 --- a/drivers/gpu/drm/sti/sti_dvo.c +++ b/drivers/gpu/drm/sti/sti_dvo.c @@ -346,8 +346,9 @@ static int sti_dvo_connector_get_modes(struct drm_connector *connector) #define CLK_TOLERANCE_HZ 50 -static int sti_dvo_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +sti_dvo_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { int target = mode->clock * 1000; int target_min = target - CLK_TOLERANCE_HZ; diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index 84109800143a..418dfccc2faf 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -600,8 +600,9 @@ static int sti_hda_connector_get_modes(struct drm_connector *connector) #define CLK_TOLERANCE_HZ 50 -static int sti_hda_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +sti_hda_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { int target = mode->clock * 1000; int target_min = target - CLK_TOLERANCE_HZ; diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index 412664dfb0b0..1bcee73f5114 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -997,8 +997,9 @@ fail: #define CLK_TOLERANCE_HZ 50 -static int sti_hdmi_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +sti_hdmi_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { int target = mode->clock * 1000; int target_min = target - CLK_TOLERANCE_HZ; From b8affa0c6405ee968dcb6030bee2cf719a464752 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Tue, 18 Oct 2022 12:40:05 +0800 Subject: [PATCH 0620/4345] orangefs: Fix kmemleak in orangefs_prepare_debugfs_help_string() [ Upstream commit d23417a5bf3a3afc55de5442eb46e1e60458b0a1 ] When insert and remove the orangefs module, then debug_help_string will be leaked: unreferenced object 0xffff8881652ba000 (size 4096): comm "insmod", pid 1701, jiffies 4294893639 (age 13218.530s) hex dump (first 32 bytes): 43 6c 69 65 6e 74 20 44 65 62 75 67 20 4b 65 79 Client Debug Key 77 6f 72 64 73 20 61 72 65 20 75 6e 6b 6e 6f 77 words are unknow backtrace: [<0000000004e6f8e3>] kmalloc_trace+0x27/0xa0 [<0000000006f75d85>] orangefs_prepare_debugfs_help_string+0x5e/0x480 [orangefs] [<0000000091270a2a>] _sub_I_65535_1+0x57/0xf70 [crc_itu_t] [<000000004b1ee1a3>] do_one_initcall+0x87/0x2a0 [<000000001d0614ae>] do_init_module+0xdf/0x320 [<00000000efef068c>] load_module+0x2f98/0x3330 [<000000006533b44d>] __do_sys_finit_module+0x113/0x1b0 [<00000000a0da6f99>] do_syscall_64+0x35/0x80 [<000000007790b19b>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 When remove the module, should always free debug_help_string. Should always free the allocated buffer when change the free_debug_help_string. Signed-off-by: Zhang Xiaoxu Signed-off-by: Mike Marshall Signed-off-by: Sasha Levin --- fs/orangefs/orangefs-debugfs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 29eaa4544372..a848b6ef9599 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -222,6 +222,8 @@ out: void orangefs_debugfs_cleanup(void) { debugfs_remove_recursive(debug_dir); + kfree(debug_help_string); + debug_help_string = NULL; } /* open ORANGEFS_KMOD_DEBUG_HELP_FILE */ @@ -671,6 +673,7 @@ int orangefs_prepare_debugfs_help_string(int at_boot) memset(debug_help_string, 0, DEBUG_HELP_STRING_SIZE); strlcat(debug_help_string, new, string_size); mutex_unlock(&orangefs_help_file_lock); + kfree(new); } rc = 0; From a076490b0211990ec6764328c22cb744dd782bd9 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Tue, 18 Oct 2022 12:40:07 +0800 Subject: [PATCH 0621/4345] orangefs: Fix kmemleak in orangefs_{kernel,client}_debug_init() [ Upstream commit 31720a2b109b3080eb77e97b8f6f50a27b4ae599 ] When insert and remove the orangefs module, there are memory leaked as below: unreferenced object 0xffff88816b0cc000 (size 2048): comm "insmod", pid 783, jiffies 4294813439 (age 65.512s) hex dump (first 32 bytes): 6e 6f 6e 65 0a 00 00 00 00 00 00 00 00 00 00 00 none............ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000031ab7788>] kmalloc_trace+0x27/0xa0 [<000000005b405fee>] orangefs_debugfs_init.cold+0xaf/0x17f [<00000000e5a0085b>] 0xffffffffa02780f9 [<000000004232d9f7>] do_one_initcall+0x87/0x2a0 [<0000000054f22384>] do_init_module+0xdf/0x320 [<000000003263bdea>] load_module+0x2f98/0x3330 [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0 [<00000000250ae02b>] do_syscall_64+0x35/0x80 [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 Use the golbal variable as the buffer rather than dynamic allocate to slove the problem. Signed-off-by: Zhang Xiaoxu Signed-off-by: Mike Marshall Signed-off-by: Sasha Levin --- fs/orangefs/orangefs-debugfs.c | 26 +++----------------------- 1 file changed, 3 insertions(+), 23 deletions(-) diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index a848b6ef9599..1b508f543384 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -194,15 +194,10 @@ void orangefs_debugfs_init(int debug_mask) */ static void orangefs_kernel_debug_init(void) { - int rc = -ENOMEM; - char *k_buffer = NULL; + static char k_buffer[ORANGEFS_MAX_DEBUG_STRING_LEN] = { }; gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__); - k_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL); - if (!k_buffer) - goto out; - if (strlen(kernel_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) { strcpy(k_buffer, kernel_debug_string); strcat(k_buffer, "\n"); @@ -213,9 +208,6 @@ static void orangefs_kernel_debug_init(void) debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE, 0444, debug_dir, k_buffer, &kernel_debug_fops); - -out: - gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc); } @@ -299,18 +291,13 @@ static int help_show(struct seq_file *m, void *v) /* * initialize the client-debug file. */ -static int orangefs_client_debug_init(void) +static void orangefs_client_debug_init(void) { - int rc = -ENOMEM; - char *c_buffer = NULL; + static char c_buffer[ORANGEFS_MAX_DEBUG_STRING_LEN] = { }; gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__); - c_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL); - if (!c_buffer) - goto out; - if (strlen(client_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) { strcpy(c_buffer, client_debug_string); strcat(c_buffer, "\n"); @@ -324,13 +311,6 @@ static int orangefs_client_debug_init(void) debug_dir, c_buffer, &kernel_debug_fops); - - rc = 0; - -out: - - gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc); - return rc; } /* open ORANGEFS_KMOD_DEBUG_FILE or ORANGEFS_CLIENT_DEBUG_FILE.*/ From 2727dbfe8d06ca094f7977f43d76d458ae4c158d Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 27 Oct 2022 14:29:31 +0800 Subject: [PATCH 0622/4345] hwmon: (jc42) Fix missing unlock on error in jc42_write() [ Upstream commit b744db17abf6a2efc2bfa80870cc88e9799a8ccc ] Add the missing unlock before return from function jc42_write() in the error handling case. Fixes: 37dedaee8bc6 ("hwmon: (jc42) Convert register access and caching to regmap/regcache") Signed-off-by: Yang Yingliang Reviewed-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20221027062931.598247-1-yangyingliang@huawei.com Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/jc42.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c index 5240bfdfcf2e..52f341d46029 100644 --- a/drivers/hwmon/jc42.c +++ b/drivers/hwmon/jc42.c @@ -340,7 +340,7 @@ static int jc42_write(struct device *dev, enum hwmon_sensor_types type, ret = regmap_read(data->regmap, JC42_REG_TEMP_CRITICAL, ®val); if (ret) - return ret; + break; /* * JC42.4 compliant chips only support four hysteresis values. From d3a8925d6c1de1ba97ed47f30347491da26a844b Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 16 Dec 2021 17:11:27 -0600 Subject: [PATCH 0623/4345] ALSA/ASoC: hda: move/rename snd_hdac_ext_stop_streams to hdac_stream.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 12054f0ce8be7d2003ec068ab27c9eb608397b98 ] snd_hdac_ext_stop_streams() has really nothing to do with the extension, it just loops over the bus streams. Move it to the hdac_stream layer and rename to remove the 'ext' prefix and add the precision that the chip will also be stopped. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Kai Vehmanen Reviewed-by: Péter Ujfalusi Reviewed-by: Ranjani Sridharan Reviewed-by: Cezary Rojewski Link: https://lore.kernel.org/r/20211216231128.344321-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Takashi Iwai Stable-dep-of: 171107237246 ("ASoC: Intel: Skylake: Fix driver hang during shutdown") Signed-off-by: Sasha Levin --- include/sound/hdaudio.h | 1 + include/sound/hdaudio_ext.h | 1 - sound/hda/ext/hdac_ext_stream.c | 17 ----------------- sound/hda/hdac_stream.c | 16 ++++++++++++++++ sound/soc/intel/skylake/skl.c | 4 ++-- 5 files changed, 19 insertions(+), 20 deletions(-) diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index 6eed61e6cf8a..63edae565573 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -562,6 +562,7 @@ int snd_hdac_stream_set_params(struct hdac_stream *azx_dev, void snd_hdac_stream_start(struct hdac_stream *azx_dev, bool fresh_start); void snd_hdac_stream_clear(struct hdac_stream *azx_dev); void snd_hdac_stream_stop(struct hdac_stream *azx_dev); +void snd_hdac_stop_streams_and_chip(struct hdac_bus *bus); void snd_hdac_stream_reset(struct hdac_stream *azx_dev); void snd_hdac_stream_sync_trigger(struct hdac_stream *azx_dev, bool set, unsigned int streams, unsigned int reg); diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index 75048ea178f6..ddcb5b2f0a8e 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -92,7 +92,6 @@ void snd_hdac_ext_stream_decouple_locked(struct hdac_bus *bus, struct hdac_ext_stream *azx_dev, bool decouple); void snd_hdac_ext_stream_decouple(struct hdac_bus *bus, struct hdac_ext_stream *azx_dev, bool decouple); -void snd_hdac_ext_stop_streams(struct hdac_bus *bus); int snd_hdac_ext_stream_set_spib(struct hdac_bus *bus, struct hdac_ext_stream *stream, u32 value); diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c index 1e6e4cf428cd..4276dae2e00a 100644 --- a/sound/hda/ext/hdac_ext_stream.c +++ b/sound/hda/ext/hdac_ext_stream.c @@ -475,23 +475,6 @@ int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_bus *bus, } EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_get_spbmaxfifo); - -/** - * snd_hdac_ext_stop_streams - stop all stream if running - * @bus: HD-audio core bus - */ -void snd_hdac_ext_stop_streams(struct hdac_bus *bus) -{ - struct hdac_stream *stream; - - if (bus->chip_init) { - list_for_each_entry(stream, &bus->stream_list, list) - snd_hdac_stream_stop(stream); - snd_hdac_bus_stop_chip(bus); - } -} -EXPORT_SYMBOL_GPL(snd_hdac_ext_stop_streams); - /** * snd_hdac_ext_stream_drsm_enable - enable DMA resume for a stream * @bus: HD-audio core bus diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index ce77a5320163..f9f0ed3042a2 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -142,6 +142,22 @@ void snd_hdac_stream_stop(struct hdac_stream *azx_dev) } EXPORT_SYMBOL_GPL(snd_hdac_stream_stop); +/** + * snd_hdac_stop_streams_and_chip - stop all streams and chip if running + * @bus: HD-audio core bus + */ +void snd_hdac_stop_streams_and_chip(struct hdac_bus *bus) +{ + struct hdac_stream *stream; + + if (bus->chip_init) { + list_for_each_entry(stream, &bus->stream_list, list) + snd_hdac_stream_stop(stream); + snd_hdac_bus_stop_chip(bus); + } +} +EXPORT_SYMBOL_GPL(snd_hdac_stop_streams_and_chip); + /** * snd_hdac_stream_reset - reset a stream * @azx_dev: HD-audio core stream to reset diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 8b993722f74e..83b1eb70b40a 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -439,7 +439,7 @@ static int skl_free(struct hdac_bus *bus) skl->init_done = 0; /* to be sure */ - snd_hdac_ext_stop_streams(bus); + snd_hdac_stop_streams_and_chip(bus); if (bus->irq >= 0) free_irq(bus->irq, (void *)bus); @@ -1100,7 +1100,7 @@ static void skl_shutdown(struct pci_dev *pci) if (!skl->init_done) return; - snd_hdac_ext_stop_streams(bus); + snd_hdac_stop_streams_and_chip(bus); list_for_each_entry(s, &bus->stream_list, list) { stream = stream_to_hdac_ext_stream(s); snd_hdac_ext_stream_decouple(bus, stream, false); From 72c0e552bc863860dac56bb8525f54565a569c79 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 19 Sep 2022 14:10:38 +0200 Subject: [PATCH 0624/4345] ALSA: hda: add snd_hdac_stop_streams() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 24ad3835a6db4f8857975effa6bf47730371a5ff ] Minor code reuse, no functionality change. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Reviewed-by: Kai Vehmanen Link: https://lore.kernel.org/r/20220919121041.43463-6-pierre-louis.bossart@linux.intel.com Signed-off-by: Takashi Iwai Stable-dep-of: 171107237246 ("ASoC: Intel: Skylake: Fix driver hang during shutdown") Signed-off-by: Sasha Levin --- include/sound/hdaudio.h | 1 + sound/hda/hdac_stream.c | 17 ++++++++++++++--- sound/pci/hda/hda_controller.c | 4 +--- 3 files changed, 16 insertions(+), 6 deletions(-) diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index 63edae565573..496decb63f80 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -562,6 +562,7 @@ int snd_hdac_stream_set_params(struct hdac_stream *azx_dev, void snd_hdac_stream_start(struct hdac_stream *azx_dev, bool fresh_start); void snd_hdac_stream_clear(struct hdac_stream *azx_dev); void snd_hdac_stream_stop(struct hdac_stream *azx_dev); +void snd_hdac_stop_streams(struct hdac_bus *bus); void snd_hdac_stop_streams_and_chip(struct hdac_bus *bus); void snd_hdac_stream_reset(struct hdac_stream *azx_dev); void snd_hdac_stream_sync_trigger(struct hdac_stream *azx_dev, bool set, diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index f9f0ed3042a2..1e0f61affd97 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -142,17 +142,28 @@ void snd_hdac_stream_stop(struct hdac_stream *azx_dev) } EXPORT_SYMBOL_GPL(snd_hdac_stream_stop); +/** + * snd_hdac_stop_streams - stop all streams + * @bus: HD-audio core bus + */ +void snd_hdac_stop_streams(struct hdac_bus *bus) +{ + struct hdac_stream *stream; + + list_for_each_entry(stream, &bus->stream_list, list) + snd_hdac_stream_stop(stream); +} +EXPORT_SYMBOL_GPL(snd_hdac_stop_streams); + /** * snd_hdac_stop_streams_and_chip - stop all streams and chip if running * @bus: HD-audio core bus */ void snd_hdac_stop_streams_and_chip(struct hdac_bus *bus) { - struct hdac_stream *stream; if (bus->chip_init) { - list_for_each_entry(stream, &bus->stream_list, list) - snd_hdac_stream_stop(stream); + snd_hdac_stop_streams(bus); snd_hdac_bus_stop_chip(bus); } } diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 3de7dc34def2..ea76395d71d3 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -1045,10 +1045,8 @@ EXPORT_SYMBOL_GPL(azx_init_chip); void azx_stop_all_streams(struct azx *chip) { struct hdac_bus *bus = azx_bus(chip); - struct hdac_stream *s; - list_for_each_entry(s, &bus->stream_list, list) - snd_hdac_stream_stop(s); + snd_hdac_stop_streams(bus); } EXPORT_SYMBOL_GPL(azx_stop_all_streams); From c2eb1a3877f593cb022b9e32564037536f0fe763 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 5 Dec 2022 09:53:29 +0100 Subject: [PATCH 0625/4345] ASoC: Intel: Skylake: Fix driver hang during shutdown [ Upstream commit 171107237246d66bce04f3769d33648f896b4ce3 ] AudioDSP cores and HDAudio links need to be turned off on shutdown to ensure no communication or data transfer occurs during the procedure. Fixes: c5a76a246989 ("ASoC: Intel: Skylake: Add shutdown callback") Signed-off-by: Cezary Rojewski Tested-by: Lukasz Majczak Link: https://lore.kernel.org/r/20221205085330.857665-6-cezary.rojewski@intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/intel/skylake/skl.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 83b1eb70b40a..2085e12dc611 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -1100,7 +1100,10 @@ static void skl_shutdown(struct pci_dev *pci) if (!skl->init_done) return; - snd_hdac_stop_streams_and_chip(bus); + snd_hdac_stop_streams(bus); + snd_hdac_ext_bus_link_power_down_all(bus); + skl_dsp_sleep(skl->dsp); + list_for_each_entry(s, &bus->stream_list, list) { stream = stream_to_hdac_ext_stream(s); snd_hdac_ext_stream_decouple(bus, stream, false); From 812a18e48efb239c4417541ca25707c8888fdd11 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Mon, 5 Dec 2022 18:04:24 +0800 Subject: [PATCH 0626/4345] ASoC: mediatek: mt8173-rt5650-rt5514: fix refcount leak in mt8173_rt5650_rt5514_dev_probe() [ Upstream commit 3327d721114c109ba0575f86f8fda3b525404054 ] The node returned by of_parse_phandle() with refcount incremented, of_node_put() needs be called when finish using it. So add it in the error path in mt8173_rt5650_rt5514_dev_probe(). Fixes: 0d1d7a664288 ("ASoC: mediatek: Refine mt8173 driver and change config option") Signed-off-by: Wang Yufen Link: https://lore.kernel.org/r/1670234664-24246-1-git-send-email-wangyufen@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c index 390da5bf727e..9421b919d462 100644 --- a/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c +++ b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c @@ -200,14 +200,16 @@ static int mt8173_rt5650_rt5514_dev_probe(struct platform_device *pdev) if (!mt8173_rt5650_rt5514_dais[DAI_LINK_CODEC_I2S].codecs[0].of_node) { dev_err(&pdev->dev, "Property 'audio-codec' missing or invalid\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } mt8173_rt5650_rt5514_dais[DAI_LINK_CODEC_I2S].codecs[1].of_node = of_parse_phandle(pdev->dev.of_node, "mediatek,audio-codec", 1); if (!mt8173_rt5650_rt5514_dais[DAI_LINK_CODEC_I2S].codecs[1].of_node) { dev_err(&pdev->dev, "Property 'audio-codec' missing or invalid\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } mt8173_rt5650_rt5514_codec_conf[0].dlc.of_node = mt8173_rt5650_rt5514_dais[DAI_LINK_CODEC_I2S].codecs[1].of_node; @@ -219,6 +221,7 @@ static int mt8173_rt5650_rt5514_dev_probe(struct platform_device *pdev) dev_err(&pdev->dev, "%s snd_soc_register_card fail %d\n", __func__, ret); +out: of_node_put(platform_node); return ret; } From 06c9d468c06806dab752eb8e72addbf3792c1023 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Mon, 5 Dec 2022 16:15:27 +0800 Subject: [PATCH 0627/4345] ASoC: audio-graph-card: fix refcount leak of cpu_ep in __graph_for_each_link() [ Upstream commit 8ab2d12c726f0fde0692fa5d81d8019b3dcd62d0 ] The of_get_next_child() returns a node with refcount incremented, and decrements the refcount of prev. So in the error path of the while loop, of_node_put() needs be called for cpu_ep. Fixes: fce9b90c1ab7 ("ASoC: audio-graph-card: cleanup DAI link loop method - step2") Signed-off-by: Wang Yufen Acked-by: Kuninori Morimoto Link: https://lore.kernel.org/r/1670228127-13835-1-git-send-email-wangyufen@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/generic/audio-graph-card.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c index bfbee2d716f3..84510ca0b8fd 100644 --- a/sound/soc/generic/audio-graph-card.c +++ b/sound/soc/generic/audio-graph-card.c @@ -466,8 +466,10 @@ static int graph_for_each_link(struct asoc_simple_priv *priv, of_node_put(codec_ep); of_node_put(codec_port); - if (ret < 0) + if (ret < 0) { + of_node_put(cpu_ep); return ret; + } codec_port_old = codec_port; } From e4a8573b046087c869406ed9f54ef153b8043939 Mon Sep 17 00:00:00 2001 From: Wang Jingjin Date: Mon, 5 Dec 2022 11:28:02 +0800 Subject: [PATCH 0628/4345] ASoC: rockchip: pdm: Add missing clk_disable_unprepare() in rockchip_pdm_runtime_resume() [ Upstream commit ef0a098efb36660326c133af9b5a04a96a00e3ca ] The clk_disable_unprepare() should be called in the error handling of rockchip_pdm_runtime_resume(). Fixes: fc05a5b22253 ("ASoC: rockchip: add support for pdm controller") Signed-off-by: Wang Jingjin Link: https://lore.kernel.org/r/20221205032802.2422983-1-wangjingjin1@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/rockchip/rockchip_pdm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c index 5adb293d0435..94cfbc90390b 100644 --- a/sound/soc/rockchip/rockchip_pdm.c +++ b/sound/soc/rockchip/rockchip_pdm.c @@ -368,6 +368,7 @@ static int rockchip_pdm_runtime_resume(struct device *dev) ret = clk_prepare_enable(pdm->hclk); if (ret) { + clk_disable_unprepare(pdm->clk); dev_err(pdm->dev, "hclock enable failed %d\n", ret); return ret; } From c0ae46693b8563efa56131b95f4d015d14e1c6ba Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 9 Dec 2022 10:16:57 +0100 Subject: [PATCH 0629/4345] ASoC: wm8994: Fix potential deadlock [ Upstream commit 9529dc167ffcdfd201b9f0eda71015f174095f7e ] Fix this by dropping wm8994->accdet_lock while calling cancel_delayed_work_sync(&wm8994->mic_work) in wm1811_jackdet_irq(). Fixes: c0cc3f166525 ("ASoC: wm8994: Allow a delay between jack insertion and microphone detect") Signed-off-by: Marek Szyprowski Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20221209091657.1183-1-m.szyprowski@samsung.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/wm8994.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index f57884113406..d3a7480fda43 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -3853,7 +3853,12 @@ static irqreturn_t wm1811_jackdet_irq(int irq, void *data) } else { dev_dbg(component->dev, "Jack not detected\n"); + /* Release wm8994->accdet_lock to avoid deadlock: + * cancel_delayed_work_sync() takes wm8994->mic_work internal + * lock and wm1811_mic_work takes wm8994->accdet_lock */ + mutex_unlock(&wm8994->accdet_lock); cancel_delayed_work_sync(&wm8994->mic_work); + mutex_lock(&wm8994->accdet_lock); snd_soc_component_update_bits(component, WM8958_MICBIAS2, WM8958_MICB2_DISCH, WM8958_MICB2_DISCH); From fd49dc17c3d71a4d402b85c38171e9d0342ec9c9 Mon Sep 17 00:00:00 2001 From: Wang Jingjin Date: Thu, 8 Dec 2022 14:39:00 +0800 Subject: [PATCH 0630/4345] ASoC: rockchip: spdif: Add missing clk_disable_unprepare() in rk_spdif_runtime_resume() [ Upstream commit 6d94d0090527b1763872275a7ccd44df7219b31e ] rk_spdif_runtime_resume() may have called clk_prepare_enable() before return from failed branches, add missing clk_disable_unprepare() in this case. Fixes: f874b80e1571 ("ASoC: rockchip: Add rockchip SPDIF transceiver driver") Signed-off-by: Wang Jingjin Link: https://lore.kernel.org/r/20221208063900.4180790-1-wangjingjin1@huawei.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/rockchip/rockchip_spdif.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/rockchip/rockchip_spdif.c b/sound/soc/rockchip/rockchip_spdif.c index 674810851fbc..ccddcd9926af 100644 --- a/sound/soc/rockchip/rockchip_spdif.c +++ b/sound/soc/rockchip/rockchip_spdif.c @@ -86,6 +86,7 @@ static int __maybe_unused rk_spdif_runtime_resume(struct device *dev) ret = clk_prepare_enable(spdif->hclk); if (ret) { + clk_disable_unprepare(spdif->mclk); dev_err(spdif->dev, "hclk clock enable failed %d\n", ret); return ret; } From 4138e1b7751c5b14d6e10eb2b3b063c45b0eb9f6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 13 Dec 2022 13:33:19 +0100 Subject: [PATCH 0631/4345] ASoC: rt5670: Remove unbalanced pm_runtime_put() [ Upstream commit 6c900dcc3f7331a67ed29739d74524e428d137fb ] For some reason rt5670_i2c_probe() does a pm_runtime_put() at the end of a successful probe. But it has never done a pm_runtime_get() leading to the following error being logged into dmesg: rt5670 i2c-10EC5640:00: Runtime PM usage count underflow! Fix this by removing the unnecessary pm_runtime_put(). Fixes: 64e89e5f5548 ("ASoC: rt5670: Add runtime PM support") Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20221213123319.11285-1-hdegoede@redhat.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/rt5670.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c index 47ce074289ca..58227602053f 100644 --- a/sound/soc/codecs/rt5670.c +++ b/sound/soc/codecs/rt5670.c @@ -3192,8 +3192,6 @@ static int rt5670_i2c_probe(struct i2c_client *i2c, if (ret < 0) goto err; - pm_runtime_put(&i2c->dev); - return 0; err: pm_runtime_disable(&i2c->dev); From c3607ed7edfb73f194abfe8d5bbdb8a857266a1f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 9 Dec 2022 11:54:57 -0800 Subject: [PATCH 0632/4345] LoadPin: Ignore the "contents" argument of the LSM hooks [ Upstream commit 1a17e5b513ceebf21100027745b8731b4728edf7 ] LoadPin only enforces the read-only origin of kernel file reads. Whether or not it was a partial read isn't important. Remove the overly conservative checks so that things like partial firmware reads will succeed (i.e. reading a firmware header). Fixes: 2039bda1fa8d ("LSM: Add "contents" flag to kernel_read_file hook") Cc: Paul Moore Cc: James Morris Cc: "Serge E. Hallyn" Cc: linux-security-module@vger.kernel.org Signed-off-by: Kees Cook Acked-by: Serge Hallyn Tested-by: Ping-Ke Shih Link: https://lore.kernel.org/r/20221209195453.never.494-kees@kernel.org Signed-off-by: Sasha Levin --- security/loadpin/loadpin.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index b12f7d986b1e..5fce105a372d 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -118,21 +118,11 @@ static void loadpin_sb_free_security(struct super_block *mnt_sb) } } -static int loadpin_read_file(struct file *file, enum kernel_read_file_id id, - bool contents) +static int loadpin_check(struct file *file, enum kernel_read_file_id id) { struct super_block *load_root; const char *origin = kernel_read_file_id_str(id); - /* - * If we will not know that we'll be seeing the full contents - * then we cannot trust a load will be complete and unchanged - * off disk. Treat all contents=false hooks as if there were - * no associated file struct. - */ - if (!contents) - file = NULL; - /* If the file id is excluded, ignore the pinning. */ if ((unsigned int)id < ARRAY_SIZE(ignore_read_file_id) && ignore_read_file_id[id]) { @@ -187,9 +177,25 @@ static int loadpin_read_file(struct file *file, enum kernel_read_file_id id, return 0; } +static int loadpin_read_file(struct file *file, enum kernel_read_file_id id, + bool contents) +{ + /* + * LoadPin only cares about the _origin_ of a file, not its + * contents, so we can ignore the "are full contents available" + * argument here. + */ + return loadpin_check(file, id); +} + static int loadpin_load_data(enum kernel_load_data_id id, bool contents) { - return loadpin_read_file(NULL, (enum kernel_read_file_id) id, contents); + /* + * LoadPin only cares about the _origin_ of a file, not its + * contents, so a NULL file is passed, and we can ignore the + * state of "contents". + */ + return loadpin_check(NULL, (enum kernel_read_file_id) id); } static struct security_hook_list loadpin_hooks[] __lsm_ro_after_init = { From 1c7b03d00c070dba9b9998bbd474c7346efb1f43 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 14 Dec 2022 23:18:34 +0000 Subject: [PATCH 0633/4345] pstore: Switch pmsg_lock to an rt_mutex to avoid priority inversion [ Upstream commit 76d62f24db07f22ccf9bc18ca793c27d4ebef721 ] Wei Wang reported seeing priority inversion caused latencies caused by contention on pmsg_lock, and suggested it be switched to a rt_mutex. I was initially hesitant this would help, as the tasks in that trace all seemed to be SCHED_NORMAL, so the benefit would be limited to only nice boosting. However, another similar issue was raised where the priority inversion was seen did involve a blocked RT task so it is clear this would be helpful in that case. Cc: Wei Wang Cc: Midas Chien Cc: Connor O'Brien Cc: Kees Cook Cc: Anton Vorontsov Cc: Colin Cross Cc: Tony Luck Cc: kernel-team@android.com Fixes: 9d5438f462ab ("pstore: Add pmsg - user-space accessible pstore object") Reported-by: Wei Wang Signed-off-by: John Stultz Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221214231834.3711880-1-jstultz@google.com Signed-off-by: Sasha Levin --- fs/pstore/pmsg.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index d8542ec2f38c..18cf94b597e0 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -7,9 +7,10 @@ #include #include #include +#include #include "internal.h" -static DEFINE_MUTEX(pmsg_lock); +static DEFINE_RT_MUTEX(pmsg_lock); static ssize_t write_pmsg(struct file *file, const char __user *buf, size_t count, loff_t *ppos) @@ -28,9 +29,9 @@ static ssize_t write_pmsg(struct file *file, const char __user *buf, if (!access_ok(buf, count)) return -EFAULT; - mutex_lock(&pmsg_lock); + rt_mutex_lock(&pmsg_lock); ret = psinfo->write_user(&record, buf); - mutex_unlock(&pmsg_lock); + rt_mutex_unlock(&pmsg_lock); return ret ? ret : count; } From 1080729b9a565b386a808c42b628494f294daeb2 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 20 Dec 2022 11:57:00 +0800 Subject: [PATCH 0634/4345] perf debug: Set debug_peo_args and redirect_to_stderr variable to correct values in perf_quiet_option() [ Upstream commit 188ac720d364035008a54d249cf47b4cc100f819 ] When perf uses quiet mode, perf_quiet_option() sets the 'debug_peo_args' variable to -1, and display_attr() incorrectly determines the value of 'debug_peo_args'. As a result, unexpected information is displayed. Before: # perf record --quiet -- ls > /dev/null ------------------------------------------------------------ perf_event_attr: size 128 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID|LOST disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 bpf_event 1 ------------------------------------------------------------ ... After: # perf record --quiet -- ls > /dev/null # redirect_to_stderr is a similar problem. Fixes: f78eaef0e0493f60 ("perf tools: Allow to force redirect pr_debug to stderr.") Fixes: ccd26741f5e6bdf2 ("perf tool: Provide an option to print perf_event_open args and return value") Suggested-by: Adrian Hunter Reviewed-by: Adrian Hunter Signed-off-by: Yang Jihong Cc: Alexander Shishkin Cc: Andi Kleen Cc: Carsten Haitzler Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: martin.lau@kernel.org Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Ravi Bangoria Link: https://lore.kernel.org/r/20221220035702.188413-2-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/debug.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 0af163abaa62..854dd3d2d8de 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -207,6 +207,10 @@ int perf_quiet_option(void) opt++; } + /* For debug variables that are used as bool types, set to 0. */ + redirect_to_stderr = 0; + debug_peo_args = 0; + return 0; } From 07b0ce902e2810ef4a3070015cb12ed289a1628f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 21 Dec 2022 14:30:48 +0000 Subject: [PATCH 0635/4345] afs: Fix lost servers_outstanding count [ Upstream commit 36f82c93ee0bd88f1c95a52537906b8178b537f1 ] The afs_fs_probe_dispatcher() work function is passed a count on net->servers_outstanding when it is scheduled (which may come via its timer). This is passed back to the work_item, passed to the timer or dropped at the end of the dispatcher function. But, at the top of the dispatcher function, there are two checks which skip the rest of the function: if the network namespace is being destroyed or if there are no fileservers to probe. These two return paths, however, do not drop the count passed to the dispatcher, and so, sometimes, the destruction of a network namespace, such as induced by rmmod of the kafs module, may get stuck in afs_purge_servers(), waiting for net->servers_outstanding to become zero. Fix this by adding the missing decrements in afs_fs_probe_dispatcher(). Fixes: f6cbb368bcb0 ("afs: Actively poll fileservers to maintain NAT or firewall openings") Reported-by: Marc Dionne Signed-off-by: David Howells Tested-by: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/167164544917.2072364.3759519569649459359.stgit@warthog.procyon.org.uk/ Signed-off-by: Sasha Levin --- fs/afs/fs_probe.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 04d42e49fc59..def80365fe79 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -360,12 +360,15 @@ void afs_fs_probe_dispatcher(struct work_struct *work) unsigned long nowj, timer_at, poll_at; bool first_pass = true, set_timer = false; - if (!net->live) + if (!net->live) { + afs_dec_servers_outstanding(net); return; + } _enter(""); if (list_empty(&net->fs_probe_fast) && list_empty(&net->fs_probe_slow)) { + afs_dec_servers_outstanding(net); _leave(" [none]"); return; } From 1d8dcc3dadf95d92d078dfedfc9efaad772090b6 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 21 Dec 2022 05:18:55 +0000 Subject: [PATCH 0636/4345] pstore: Make sure CONFIG_PSTORE_PMSG selects CONFIG_RT_MUTEXES [ Upstream commit 2f4fec5943407318b9523f01ce1f5d668c028332 ] In commit 76d62f24db07 ("pstore: Switch pmsg_lock to an rt_mutex to avoid priority inversion") I changed a lock to an rt_mutex. However, its possible that CONFIG_RT_MUTEXES is not enabled, which then results in a build failure, as the 0day bot detected: https://lore.kernel.org/linux-mm/202212211244.TwzWZD3H-lkp@intel.com/ Thus this patch changes CONFIG_PSTORE_PMSG to select CONFIG_RT_MUTEXES, which ensures the build will not fail. Cc: Wei Wang Cc: Midas Chien Cc: Connor O'Brien Cc: Kees Cook Cc: Anton Vorontsov Cc: Colin Cross Cc: Tony Luck Cc: kernel test robot Cc: kernel-team@android.com Fixes: 76d62f24db07 ("pstore: Switch pmsg_lock to an rt_mutex to avoid priority inversion") Reported-by: kernel test robot Signed-off-by: John Stultz Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221221051855.15761-1-jstultz@google.com Signed-off-by: Sasha Levin --- fs/pstore/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 8efe60487b48..71dbe9a2533f 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -118,6 +118,7 @@ config PSTORE_CONSOLE config PSTORE_PMSG bool "Log user space messages" depends on PSTORE + select RT_MUTEXES help When the option is enabled, pstore will export a character interface /dev/pmsg0 to log user space messages. On reboot From 7691fa41024eed0a87d45f50a3bb0bcbae5dda41 Mon Sep 17 00:00:00 2001 From: GUO Zihua Date: Wed, 21 Sep 2022 20:58:03 +0800 Subject: [PATCH 0637/4345] ima: Simplify ima_lsm_copy_rule [ Upstream commit d57378d3aa4d864d9e590482602068af1b20c0c5 ] Currently ima_lsm_copy_rule() set the arg_p field of the source rule to NULL, so that the source rule could be freed afterward. It does not make sense for this behavior to be inside a "copy" function. So move it outside and let the caller handle this field. ima_lsm_copy_rule() now produce a shallow copy of the original entry including args_p field. Meaning only the lsm.rule and the rule itself should be freed for the original rule. Thus, instead of calling ima_lsm_free_rule() which frees lsm.rule as well as args_p field, free the lsm.rule directly. Signed-off-by: GUO Zihua Reviewed-by: Roberto Sassu Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/ima/ima_policy.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index a83ce111cf50..96ecb7d25403 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -370,12 +370,6 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) nentry->lsm[i].type = entry->lsm[i].type; nentry->lsm[i].args_p = entry->lsm[i].args_p; - /* - * Remove the reference from entry so that the associated - * memory will not be freed during a later call to - * ima_lsm_free_rule(entry). - */ - entry->lsm[i].args_p = NULL; ima_filter_rule_init(nentry->lsm[i].type, Audit_equal, nentry->lsm[i].args_p, @@ -389,6 +383,7 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) static int ima_lsm_update_rule(struct ima_rule_entry *entry) { + int i; struct ima_rule_entry *nentry; nentry = ima_lsm_copy_rule(entry); @@ -403,7 +398,8 @@ static int ima_lsm_update_rule(struct ima_rule_entry *entry) * references and the entry itself. All other memory refrences will now * be owned by nentry. */ - ima_lsm_free_rule(entry); + for (i = 0; i < MAX_LSM_RULES; i++) + ima_filter_rule_free(entry->lsm[i].rule); kfree(entry); return 0; From d3767082ebfa8390f8bc11a55303ee072626b00c Mon Sep 17 00:00:00 2001 From: wangdicheng Date: Wed, 7 Dec 2022 16:20:36 +0800 Subject: [PATCH 0638/4345] ALSA: usb-audio: add the quirk for KT0206 device commit 696b66ac26ef953aed5783ef26a252ec8f207013 upstream. Add relevant information to the quirks-table.h file. The test passes and the sound source file plays normally. Signed-off-by: wangdicheng Cc: Link: https://lore.kernel.org/r/SG2PR02MB587849631CB96809CF90DBED8A1A9@SG2PR02MB5878.apcprd02.prod.outlook.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/quirks-table.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 6a78813b63f5..ec74aead0844 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -76,6 +76,8 @@ { USB_DEVICE_VENDOR_SPEC(0x041e, 0x3f0a) }, /* E-Mu 0204 USB */ { USB_DEVICE_VENDOR_SPEC(0x041e, 0x3f19) }, +/* Ktmicro Usb_audio device */ +{ USB_DEVICE_VENDOR_SPEC(0x31b2, 0x0011) }, /* * Creative Technology, Ltd Live! Cam Sync HD [VF0770] From c863b673503eb64188d25c4a3cfa863ce4d68fef Mon Sep 17 00:00:00 2001 From: Edward Pacman Date: Wed, 7 Dec 2022 21:32:18 +0800 Subject: [PATCH 0639/4345] ALSA: hda/realtek: Add quirk for Lenovo TianYi510Pro-14IOB commit 4bf5bf54476dffe60e6b6d8d539f67309ff599e2 upstream. Lenovo TianYi510Pro-14IOB (17aa:3742) require quirk for enabling headset-mic Signed-off-by: Edward Pacman Cc: Link: https://bugzilla.kernel.org/show_bug.cgi?id=216756 Link: https://lore.kernel.org/r/20221207133218.18989-1-edward@edward-p.xyz Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8011b451902a..e0bca0b029ed 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -10514,6 +10514,17 @@ static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec, } } +static void alc897_fixup_lenovo_headset_mode(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->parse_flags |= HDA_PINCFG_HEADSET_MIC; + spec->gen.hp_automute_hook = alc897_hp_automute_hook; + } +} + static const struct coef_fw alc668_coefs[] = { WRITE_COEF(0x01, 0xbebe), WRITE_COEF(0x02, 0xaaaa), WRITE_COEF(0x03, 0x0), WRITE_COEF(0x04, 0x0180), WRITE_COEF(0x06, 0x0), WRITE_COEF(0x07, 0x0f80), @@ -10597,6 +10608,8 @@ enum { ALC897_FIXUP_LENOVO_HEADSET_MIC, ALC897_FIXUP_HEADSET_MIC_PIN, ALC897_FIXUP_HP_HSMIC_VERB, + ALC897_FIXUP_LENOVO_HEADSET_MODE, + ALC897_FIXUP_HEADSET_MIC_PIN2, }; static const struct hda_fixup alc662_fixups[] = { @@ -11023,6 +11036,19 @@ static const struct hda_fixup alc662_fixups[] = { { } }, }, + [ALC897_FIXUP_LENOVO_HEADSET_MODE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc897_fixup_lenovo_headset_mode, + }, + [ALC897_FIXUP_HEADSET_MIC_PIN2] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1a, 0x01a11140 }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC897_FIXUP_LENOVO_HEADSET_MODE + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { @@ -11075,6 +11101,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x3742, "Lenovo TianYi510Pro-14IOB", ALC897_FIXUP_HEADSET_MIC_PIN2), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x1849, 0x5892, "ASRock B150M", ALC892_FIXUP_ASROCK_MOBO), From 2b725b6fbbe6577dbe5aa931522cec6475da9140 Mon Sep 17 00:00:00 2001 From: Jiao Zhou Date: Tue, 6 Dec 2022 13:53:11 -0500 Subject: [PATCH 0640/4345] ALSA: hda/hdmi: Add HP Device 0x8711 to force connect list commit 31b573946ea55e1ea0e08ae8e83bcf879b30f83a upstream. HDMI audio is not working on the HP EliteDesk 800 G6 because the pin is unconnected. This issue can be resolved by using the 'hdajackretask' tool to override the unconnected pin to force it to connect. Signed-off-by: Jiao Zhou Cc: Link: https://lore.kernel.org/r/20221206185311.3669950-1-jiaozhou@google.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_hdmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index b1c57c65f6cd..19566b75753e 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1965,6 +1965,7 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid) static const struct snd_pci_quirk force_connect_list[] = { SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1), SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), + SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1), SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1), {} }; From d17c82aad67ab0be12edd551f0b8654d35804b69 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Mon, 28 Nov 2022 17:15:26 +0100 Subject: [PATCH 0641/4345] usb: dwc3: Fix race between dwc3_set_mode and __dwc3_set_mode commit 62c73bfea048e66168df09da6d3e4510ecda40bb upstream. dwc->desired_dr_role is changed by dwc3_set_mode inside a spinlock but then read by __dwc3_set_mode outside of that lock. This can lead to a race condition when very quick successive role switch events happen: CPU A dwc3_set_mode(DWC3_GCTL_PRTCAP_HOST) // first role switch event spin_lock_irqsave(&dwc->lock, flags); dwc->desired_dr_role = mode; // DWC3_GCTL_PRTCAP_HOST spin_unlock_irqrestore(&dwc->lock, flags); queue_work(system_freezable_wq, &dwc->drd_work); CPU B __dwc3_set_mode // .... spin_lock_irqsave(&dwc->lock, flags); // desired_dr_role is DWC3_GCTL_PRTCAP_HOST dwc3_set_prtcap(dwc, dwc->desired_dr_role); spin_unlock_irqrestore(&dwc->lock, flags); CPU A dwc3_set_mode(DWC3_GCTL_PRTCAP_DEVICE) // second event spin_lock_irqsave(&dwc->lock, flags); dwc->desired_dr_role = mode; // DWC3_GCTL_PRTCAP_DEVICE spin_unlock_irqrestore(&dwc->lock, flags); CPU B (continues running __dwc3_set_mode) switch (dwc->desired_dr_role) { // DWC3_GCTL_PRTCAP_DEVICE // .... case DWC3_GCTL_PRTCAP_DEVICE: // .... ret = dwc3_gadget_init(dwc); We then have DWC3_GCTL.DWC3_GCTL_PRTCAPDIR = DWC3_GCTL_PRTCAP_HOST and dwc->current_dr_role = DWC3_GCTL_PRTCAP_HOST but initialized the controller in device mode. It's also possible to get into a state where both host and device are intialized at the same time. Fix this race by creating a local copy of desired_dr_role inside __dwc3_set_mode while holding dwc->lock. Fixes: 41ce1456e1db ("usb: dwc3: core: make dwc3_set_mode() work properly") Cc: stable Acked-by: Thinh Nguyen Signed-off-by: Sven Peter Link: https://lore.kernel.org/r/20221128161526.79730-1-sven@svenpeter.dev Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 4a0eec176511..9d6df4c67894 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -120,21 +120,25 @@ static void __dwc3_set_mode(struct work_struct *work) unsigned long flags; int ret; u32 reg; + u32 desired_dr_role; mutex_lock(&dwc->mutex); + spin_lock_irqsave(&dwc->lock, flags); + desired_dr_role = dwc->desired_dr_role; + spin_unlock_irqrestore(&dwc->lock, flags); pm_runtime_get_sync(dwc->dev); if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_OTG) dwc3_otg_update(dwc, 0); - if (!dwc->desired_dr_role) + if (!desired_dr_role) goto out; - if (dwc->desired_dr_role == dwc->current_dr_role) + if (desired_dr_role == dwc->current_dr_role) goto out; - if (dwc->desired_dr_role == DWC3_GCTL_PRTCAP_OTG && dwc->edev) + if (desired_dr_role == DWC3_GCTL_PRTCAP_OTG && dwc->edev) goto out; switch (dwc->current_dr_role) { @@ -162,7 +166,7 @@ static void __dwc3_set_mode(struct work_struct *work) */ if (dwc->current_dr_role && ((DWC3_IP_IS(DWC3) || DWC3_VER_IS_PRIOR(DWC31, 190A)) && - dwc->desired_dr_role != DWC3_GCTL_PRTCAP_OTG)) { + desired_dr_role != DWC3_GCTL_PRTCAP_OTG)) { reg = dwc3_readl(dwc->regs, DWC3_GCTL); reg |= DWC3_GCTL_CORESOFTRESET; dwc3_writel(dwc->regs, DWC3_GCTL, reg); @@ -182,11 +186,11 @@ static void __dwc3_set_mode(struct work_struct *work) spin_lock_irqsave(&dwc->lock, flags); - dwc3_set_prtcap(dwc, dwc->desired_dr_role); + dwc3_set_prtcap(dwc, desired_dr_role); spin_unlock_irqrestore(&dwc->lock, flags); - switch (dwc->desired_dr_role) { + switch (desired_dr_role) { case DWC3_GCTL_PRTCAP_HOST: ret = dwc3_host_init(dwc); if (ret) { From 723ffde78af50c5e707641e0855a8d56ffd16526 Mon Sep 17 00:00:00 2001 From: Ferry Toth Date: Mon, 5 Dec 2022 21:15:27 +0100 Subject: [PATCH 0642/4345] usb: dwc3: core: defer probe on ulpi_read_id timeout commit 63130462c919ece0ad0d9bb5a1f795ef8d79687e upstream. Since commit 0f0101719138 ("usb: dwc3: Don't switch OTG -> peripheral if extcon is present"), Dual Role support on Intel Merrifield platform broke due to rearranging the call to dwc3_get_extcon(). It appears to be caused by ulpi_read_id() masking the timeout on the first test write. In the past dwc3 probe continued by calling dwc3_core_soft_reset() followed by dwc3_get_extcon() which happend to return -EPROBE_DEFER. On deferred probe ulpi_read_id() finally succeeded. Due to above mentioned rearranging -EPROBE_DEFER is not returned and probe completes without phy. On Intel Merrifield the timeout on the first test write issue is reproducible but it is difficult to find the root cause. Using a mainline kernel and rootfs with buildroot ulpi_read_id() succeeds. As soon as adding ftrace / bootconfig to find out why, ulpi_read_id() fails and we can't analyze the flow. Using another rootfs ulpi_read_id() fails even without adding ftrace. We suspect the issue is some kind of timing / race, but merely retrying ulpi_read_id() does not resolve the issue. As we now changed ulpi_read_id() to return -ETIMEDOUT in this case, we need to handle the error by calling dwc3_core_soft_reset() and request -EPROBE_DEFER. On deferred probe ulpi_read_id() is retried and succeeds. Fixes: ef6a7bcfb01c ("usb: ulpi: Support device discovery via DT") Cc: stable@vger.kernel.org Acked-by: Thinh Nguyen Signed-off-by: Ferry Toth Link: https://lore.kernel.org/r/20221205201527.13525-3-ftoth@exalondelft.nl Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 9d6df4c67894..d73f624ed42a 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -960,8 +960,13 @@ static int dwc3_core_init(struct dwc3 *dwc) if (!dwc->ulpi_ready) { ret = dwc3_core_ulpi_init(dwc); - if (ret) + if (ret) { + if (ret == -ETIMEDOUT) { + dwc3_core_soft_reset(dwc); + ret = -EPROBE_DEFER; + } goto err0; + } dwc->ulpi_ready = true; } From 7a203471b9800f2eecbeab67664294c7ef49f8ca Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Thu, 1 Dec 2022 15:11:41 -0800 Subject: [PATCH 0643/4345] HID: wacom: Ensure bootloader PID is usable in hidraw mode commit 1db1f392591aff13fd643f0ec7c1d5e27391d700 upstream. Some Wacom devices have a special "bootloader" mode that is used for firmware flashing. When operating in this mode, the device cannot be used for input, and the HID descriptor is not able to be processed by the driver. The driver generates an "Unknown device_type" warning and then returns an error code from wacom_probe(). This is a problem because userspace still needs to be able to interact with the device via hidraw to perform the firmware flash. This commit adds a non-generic device definition for 056a:0094 which is used when devices are in "bootloader" mode. It marks the devices with a special BOOTLOADER type that is recognized by wacom_probe() and wacom_raw_event(). When we see this type we ensure a hidraw device is created and otherwise keep our hands off so that userspace is in full control. Signed-off-by: Jason Gerecke Tested-by: Tatsunosuke Tobita Cc: Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom_sys.c | 8 ++++++++ drivers/hid/wacom_wac.c | 4 ++++ drivers/hid/wacom_wac.h | 1 + 3 files changed, 13 insertions(+) diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 4dbf69078387..b42785fdf7ed 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -160,6 +160,9 @@ static int wacom_raw_event(struct hid_device *hdev, struct hid_report *report, { struct wacom *wacom = hid_get_drvdata(hdev); + if (wacom->wacom_wac.features.type == BOOTLOADER) + return 0; + if (size > WACOM_PKGLEN_MAX) return 1; @@ -2786,6 +2789,11 @@ static int wacom_probe(struct hid_device *hdev, return error; } + if (features->type == BOOTLOADER) { + hid_warn(hdev, "Using device in hidraw-only mode"); + return hid_hw_start(hdev, HID_CONNECT_HIDRAW); + } + error = wacom_parse_and_register(wacom, false); if (error) return error; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index d8d127fcc82a..afb94b89fc4d 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -4782,6 +4782,9 @@ static const struct wacom_features wacom_features_0x3c8 = static const struct wacom_features wacom_features_HID_ANY_ID = { "Wacom HID", .type = HID_GENERIC, .oVid = HID_ANY_ID, .oPid = HID_ANY_ID }; +static const struct wacom_features wacom_features_0x94 = + { "Wacom Bootloader", .type = BOOTLOADER }; + #define USB_DEVICE_WACOM(prod) \ HID_DEVICE(BUS_USB, HID_GROUP_WACOM, USB_VENDOR_ID_WACOM, prod),\ .driver_data = (kernel_ulong_t)&wacom_features_##prod @@ -4855,6 +4858,7 @@ const struct hid_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0x84) }, { USB_DEVICE_WACOM(0x90) }, { USB_DEVICE_WACOM(0x93) }, + { USB_DEVICE_WACOM(0x94) }, { USB_DEVICE_WACOM(0x97) }, { USB_DEVICE_WACOM(0x9A) }, { USB_DEVICE_WACOM(0x9F) }, diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index 8dea7cb298e6..ca172efcf072 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -242,6 +242,7 @@ enum { MTTPC, MTTPC_B, HID_GENERIC, + BOOTLOADER, MAX_TYPE }; From 08371068fff82fae6d4d22b4843683812742f2d8 Mon Sep 17 00:00:00 2001 From: Enrik Berkhan Date: Thu, 3 Nov 2022 23:27:12 +0100 Subject: [PATCH 0644/4345] HID: mcp2221: don't connect hidraw MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 67c90d14018775556d5420382ace86521421f9ff upstream. The MCP2221 driver should not connect to the hidraw userspace interface, as it needs exclusive access to the chip. If you want to use /dev/hidrawX with the MCP2221, you need to avoid binding this driver to the device and use the hid generic driver instead (e.g. using udev rules). Cc: stable@vger.kernel.org Reported-by: Sven Zühlsdorf Signed-off-by: Enrik Berkhan Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20221103222714.21566-2-Enrik.Berkhan@inka.de Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-mcp2221.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index de52e9f7bb8c..560eeec4035a 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -840,12 +840,19 @@ static int mcp2221_probe(struct hid_device *hdev, return ret; } - ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW); + /* + * This driver uses the .raw_event callback and therefore does not need any + * HID_CONNECT_xxx flags. + */ + ret = hid_hw_start(hdev, 0); if (ret) { hid_err(hdev, "can't start hardware\n"); return ret; } + hid_info(hdev, "USB HID v%x.%02x Device [%s] on %s\n", hdev->version >> 8, + hdev->version & 0xff, hdev->name, hdev->phys); + ret = hid_hw_open(hdev); if (ret) { hid_err(hdev, "can't open device\n"); @@ -870,8 +877,7 @@ static int mcp2221_probe(struct hid_device *hdev, mcp->adapter.retries = 1; mcp->adapter.dev.parent = &hdev->dev; snprintf(mcp->adapter.name, sizeof(mcp->adapter.name), - "MCP2221 usb-i2c bridge on hidraw%d", - ((struct hidraw *)hdev->hidraw)->minor); + "MCP2221 usb-i2c bridge"); ret = i2c_add_adapter(&mcp->adapter); if (ret) { From 582f5fc2c5863b595df7b6255797cf92f9e9ab3f Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Thu, 10 Nov 2022 10:46:35 +0100 Subject: [PATCH 0645/4345] reiserfs: Add missing calls to reiserfs_security_free() commit 572302af1258459e124437b8f3369357447afac7 upstream. Commit 57fe60df6241 ("reiserfs: add atomic addition of selinux attributes during inode creation") defined reiserfs_security_free() to free the name and value of a security xattr allocated by the active LSM through security_old_inode_init_security(). However, this function is not called in the reiserfs code. Thus, add a call to reiserfs_security_free() whenever reiserfs_security_init() is called, and initialize value to NULL, to avoid to call kfree() on an uninitialized pointer. Finally, remove the kfree() for the xattr name, as it is not allocated anymore. Fixes: 57fe60df6241 ("reiserfs: add atomic addition of selinux attributes during inode creation") Cc: stable@vger.kernel.org Cc: Jeff Mahoney Cc: Tetsuo Handa Reported-by: Mimi Zohar Reported-by: Tetsuo Handa Signed-off-by: Roberto Sassu Reviewed-by: Mimi Zohar Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- fs/reiserfs/namei.c | 4 ++++ fs/reiserfs/xattr_security.c | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 1594687582f0..84cc136d41dd 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -695,6 +695,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod out_failed: reiserfs_write_unlock(dir->i_sb); + reiserfs_security_free(&security); return retval; } @@ -778,6 +779,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode out_failed: reiserfs_write_unlock(dir->i_sb); + reiserfs_security_free(&security); return retval; } @@ -876,6 +878,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode retval = journal_end(&th); out_failed: reiserfs_write_unlock(dir->i_sb); + reiserfs_security_free(&security); return retval; } @@ -1191,6 +1194,7 @@ static int reiserfs_symlink(struct inode *parent_dir, retval = journal_end(&th); out_failed: reiserfs_write_unlock(parent_dir->i_sb); + reiserfs_security_free(&security); return retval; } diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index 20be9a0e5870..59d87f9f72fb 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -49,6 +49,7 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode, int error; sec->name = NULL; + sec->value = NULL; /* Don't add selinux attributes on xattrs - they'll never get used */ if (IS_PRIVATE(dir)) @@ -94,7 +95,6 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, void reiserfs_security_free(struct reiserfs_security_handle *sec) { - kfree(sec->name); kfree(sec->value); sec->name = NULL; sec->value = NULL; From 9f604702b765ee6a594a952b024dfaf916518e46 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Tue, 20 Sep 2022 13:28:07 +0200 Subject: [PATCH 0646/4345] iio: adc: ad_sigma_delta: do not use internal iio_dev lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 20228a1d5a55e7db0c6720840f2c7d2b48c55f69 upstream. Drop 'mlock' usage by making use of iio_device_claim_direct_mode(). This change actually makes sure we cannot do a single conversion while buffering is enable. Note there was a potential race in the previous code since we were only acquiring the lock after checking if the bus is enabled. Fixes: af3008485ea0 ("iio:adc: Add common code for ADI Sigma Delta devices") Signed-off-by: Nuno Sá Reviewed-by: Miquel Raynal Cc: #No rush as race is very old. Link: https://lore.kernel.org/r/20220920112821.975359-2-nuno.sa@analog.com Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/ad_sigma_delta.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index 3a6f239d4acc..496cb2b26bfd 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -280,10 +280,10 @@ int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, unsigned int data_reg; int ret = 0; - if (iio_buffer_enabled(indio_dev)) - return -EBUSY; + ret = iio_device_claim_direct_mode(indio_dev); + if (ret) + return ret; - mutex_lock(&indio_dev->mlock); ad_sigma_delta_set_channel(sigma_delta, chan->address); spi_bus_lock(sigma_delta->spi->master); @@ -322,7 +322,7 @@ out: ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_IDLE); sigma_delta->bus_locked = false; spi_bus_unlock(sigma_delta->spi->master); - mutex_unlock(&indio_dev->mlock); + iio_device_release_direct_mode(indio_dev); if (ret) return ret; From e12f4c321247bd420664a4771f3d6faa9b45ce96 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 15 Nov 2022 14:23:23 +0100 Subject: [PATCH 0647/4345] iio: adc128s052: add proper .data members in adc128_of_match table commit e2af60f5900c6ade53477b494ffb54690eee11f5 upstream. Prior to commit bd5d54e4d49d ("iio: adc128s052: add ACPI _HID AANT1280"), the driver unconditionally used spi_get_device_id() to get the index into the adc128_config array. However, with that commit, OF-based boards now incorrectly treat all supported sensors as if they are an adc128s052, because all the .data members of the adc128_of_match table are implicitly 0. Our board, which has an adc122s021, thus exposes 8 channels whereas it really only has two. Fixes: bd5d54e4d49d ("iio: adc128s052: add ACPI _HID AANT1280") Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20221115132324.1078169-1-linux@rasmusvillemoes.dk Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/ti-adc128s052.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/iio/adc/ti-adc128s052.c b/drivers/iio/adc/ti-adc128s052.c index 83c1ae07b3e9..8618ae7bc067 100644 --- a/drivers/iio/adc/ti-adc128s052.c +++ b/drivers/iio/adc/ti-adc128s052.c @@ -193,13 +193,13 @@ static int adc128_remove(struct spi_device *spi) } static const struct of_device_id adc128_of_match[] = { - { .compatible = "ti,adc128s052", }, - { .compatible = "ti,adc122s021", }, - { .compatible = "ti,adc122s051", }, - { .compatible = "ti,adc122s101", }, - { .compatible = "ti,adc124s021", }, - { .compatible = "ti,adc124s051", }, - { .compatible = "ti,adc124s101", }, + { .compatible = "ti,adc128s052", .data = (void*)0L, }, + { .compatible = "ti,adc122s021", .data = (void*)1L, }, + { .compatible = "ti,adc122s051", .data = (void*)1L, }, + { .compatible = "ti,adc122s101", .data = (void*)1L, }, + { .compatible = "ti,adc124s021", .data = (void*)2L, }, + { .compatible = "ti,adc124s051", .data = (void*)2L, }, + { .compatible = "ti,adc124s101", .data = (void*)2L, }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, adc128_of_match); From 36be7afca1031d0c50b9dda31393123e42acc9f5 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 15 Dec 2022 11:46:46 +0100 Subject: [PATCH 0648/4345] regulator: core: fix deadlock on regulator enable commit cb3543cff90a4448ed560ac86c98033ad5fecda9 upstream. When updating the operating mode as part of regulator enable, the caller has already locked the regulator tree and drms_uA_update() must not try to do the same in order not to trigger a deadlock. The lock inversion is reported by lockdep as: ====================================================== WARNING: possible circular locking dependency detected 6.1.0-next-20221215 #142 Not tainted ------------------------------------------------------ udevd/154 is trying to acquire lock: ffffc11f123d7e50 (regulator_list_mutex){+.+.}-{3:3}, at: regulator_lock_dependent+0x54/0x280 but task is already holding lock: ffff80000e4c36e8 (regulator_ww_class_acquire){+.+.}-{0:0}, at: regulator_enable+0x34/0x80 which lock already depends on the new lock. ... Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(regulator_ww_class_acquire); lock(regulator_list_mutex); lock(regulator_ww_class_acquire); lock(regulator_list_mutex); *** DEADLOCK *** just before probe of a Qualcomm UFS controller (occasionally) deadlocks when enabling one of its regulators. Fixes: 9243a195be7a ("regulator: core: Change voltage setting path") Fixes: f8702f9e4aa7 ("regulator: core: Use ww_mutex for regulators locking") Cc: stable@vger.kernel.org # 5.0 Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20221215104646.19818-1-johan+linaro@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index df746ba5c1bc..6dd698b2d0af 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -980,7 +980,7 @@ static int drms_uA_update(struct regulator_dev *rdev) /* get input voltage */ input_uV = 0; if (rdev->supply) - input_uV = regulator_get_voltage(rdev->supply); + input_uV = regulator_get_voltage_rdev(rdev->supply->rdev); if (input_uV <= 0) input_uV = rdev->constraints->input_uV; if (input_uV <= 0) { From f24474d12e68dfb3fa051ece57ff6bb11361d7f8 Mon Sep 17 00:00:00 2001 From: Rickard x Andersson Date: Tue, 20 Dec 2022 11:23:18 +0100 Subject: [PATCH 0649/4345] gcov: add support for checksum field commit e96b95c2b7a63a454b6498e2df67aac14d046d13 upstream. In GCC version 12.1 a checksum field was added. This patch fixes a kernel crash occurring during boot when using gcov-kernel with GCC version 12.2. The crash occurred on a system running on i.MX6SX. Link: https://lkml.kernel.org/r/20221220102318.3418501-1-rickaran@axis.com Fixes: 977ef30a7d88 ("gcov: support GCC 12.1 and newer compilers") Signed-off-by: Rickard x Andersson Reviewed-by: Peter Oberparleiter Tested-by: Peter Oberparleiter Reviewed-by: Martin Liska Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- kernel/gcov/gcc_4_7.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index c699feda21ac..04880d8fba25 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -85,6 +85,7 @@ struct gcov_fn_info { * @version: gcov version magic indicating the gcc version used for compilation * @next: list head for a singly-linked list * @stamp: uniquifying time stamp + * @checksum: unique object checksum * @filename: name of the associated gcov data file * @merge: merge functions (null for unused counter type) * @n_functions: number of instrumented functions @@ -97,6 +98,10 @@ struct gcov_info { unsigned int version; struct gcov_info *next; unsigned int stamp; + /* Since GCC 12.1 a checksum field is added. */ +#if (__GNUC__ >= 12) + unsigned int checksum; +#endif const char *filename; void (*merge[GCOV_COUNTERS])(gcov_type *, unsigned int); unsigned int n_functions; From 740c537f52c1f54aff9094744483d1515c7c8b7b Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Mon, 28 Nov 2022 11:33:05 +0100 Subject: [PATCH 0650/4345] ovl: fix use inode directly in rcu-walk mode commit 672e4268b2863d7e4978dfed29552b31c2f9bd4e upstream. ovl_dentry_revalidate_common() can be called in rcu-walk mode. As document said, "in rcu-walk mode, d_parent and d_inode should not be used without care". Check inode here to protect access under rcu-walk mode. Fixes: bccece1ead36 ("ovl: allow remote upper") Reported-and-tested-by: syzbot+a4055c78774bbf3498bb@syzkaller.appspotmail.com Signed-off-by: Chen Zhongjin Cc: # v5.7 Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/super.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 45c596dfe3a3..e3cd5a00f880 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -138,11 +138,16 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry, unsigned int flags, bool weak) { struct ovl_entry *oe = dentry->d_fsdata; + struct inode *inode = d_inode_rcu(dentry); struct dentry *upper; unsigned int i; int ret = 1; - upper = ovl_dentry_upper(dentry); + /* Careful in RCU mode */ + if (!inode) + return -ECHILD; + + upper = ovl_i_dentry_upper(inode); if (upper) ret = ovl_revalidate_real(upper, flags, weak); From 153319671a08bab75399a9ff6a2eaf54bd0cc4cb Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Mon, 28 Nov 2022 08:39:03 +0000 Subject: [PATCH 0651/4345] media: dvbdev: fix build warning due to comments commit 3edfd14bb50fa6f94ed1a37bbb17d9f1c2793b57 upstream. Previous commit that introduces reference counter does not add proper comments, which will lead to warning when building htmldocs. Fix them. Reported-by: "Stephen Rothwell" Fixes: 0fc044b2b5e2 ("media: dvbdev: adopts refcnt to avoid UAF") Signed-off-by: Lin Ma Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- include/media/dvbdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/media/dvbdev.h b/include/media/dvbdev.h index 6e736587aa1f..c493a3ffe45c 100644 --- a/include/media/dvbdev.h +++ b/include/media/dvbdev.h @@ -126,6 +126,7 @@ struct dvb_adapter { * struct dvb_device - represents a DVB device node * * @list_head: List head with all DVB devices + * @ref: reference counter * @fops: pointer to struct file_operations * @adapter: pointer to the adapter that holds this device node * @type: type of the device, as defined by &enum dvb_device_type. @@ -196,7 +197,7 @@ struct dvb_device { struct dvb_device *dvb_device_get(struct dvb_device *dvbdev); /** - * dvb_device_get - Decrease dvb_device reference + * dvb_device_put - Decrease dvb_device reference * * @dvbdev: pointer to struct dvb_device */ From a8be7c2787b98cf43b5c308094d2e2b1c8ce19b6 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Mon, 28 Nov 2022 16:21:59 +0000 Subject: [PATCH 0652/4345] media: dvbdev: fix refcnt bug commit 3a664569b71b0a52be5ffb9fb87cc4f83d29bd71 upstream. Previous commit initialize the dvbdev->ref before the template copy, which will overwrite the reference and cause refcnt bug. refcount_t: addition on 0; use-after-free. WARNING: CPU: 0 PID: 1 at lib/refcount.c:25 refcount_warn_saturate+0x17c/0x1f0 lib/refcount.c:25 Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.1.0-rc6-next-20221128-syzkaller #0 ... RIP: 0010:refcount_warn_saturate+0x17c/0x1f0 lib/refcount.c:25 RSP: 0000:ffffc900000678d0 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: ffff88813ff58000 RSI: ffffffff81660e7c RDI: fffff5200000cf0c RBP: ffff888022a45010 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000080000000 R11: 0000000000000000 R12: 0000000000000001 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff88823ffff000 CR3: 000000000c48e000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __refcount_add include/linux/refcount.h:199 [inline] __refcount_inc include/linux/refcount.h:250 [inline] refcount_inc include/linux/refcount.h:267 [inline] kref_get include/linux/kref.h:45 [inline] dvb_device_get drivers/media/dvb-core/dvbdev.c:585 [inline] dvb_register_device+0xe83/0x16e0 drivers/media/dvb-core/dvbdev.c:517 ... Just place the kref_init at correct position. Reported-by: syzbot+fce48a3dd3368645bd6c@syzkaller.appspotmail.com Fixes: 0fc044b2b5e2 ("media: dvbdev: adopts refcnt to avoid UAF") Signed-off-by: Lin Ma Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/dvb-core/dvbdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index 7b28b483e4b2..4031905f0b07 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -490,8 +490,8 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, return -ENOMEM; } - kref_init(&dvbdev->ref); memcpy(dvbdev, template, sizeof(struct dvb_device)); + kref_init(&dvbdev->ref); dvbdev->type = type; dvbdev->id = id; dvbdev->adapter = adap; From ce2462bcf3ff0e3d8886220f6571474985ca2458 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Thu, 10 Nov 2022 11:45:48 +0000 Subject: [PATCH 0653/4345] pwm: tegra: Fix 32 bit build MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit dd1f1da4ada5d8ac774c2ebe97230637820b3323 ] The value of NSEC_PER_SEC << PWM_DUTY_WIDTH doesn't fix within a 32 bit integer causing a build warning/error (and the value truncated): drivers/pwm/pwm-tegra.c: In function ‘tegra_pwm_config’: drivers/pwm/pwm-tegra.c:148:53: error: result of ‘1000000000 << 8’ requires 39 bits to represent, but ‘long int’ only has 32 bits [-Werror=shift-overflow=] 148 | required_clk_rate = DIV_ROUND_UP_ULL(NSEC_PER_SEC << PWM_DUTY_WIDTH, | ^~ Explicitly cast to a u64 to ensure the correct result. Fixes: cfcb68817fb3 ("pwm: tegra: Improve required rate calculation") Signed-off-by: Steven Price Reviewed-by: Uwe Kleine-König Reviewed-by: Jon Hunter Signed-off-by: Sasha Levin --- drivers/pwm/pwm-tegra.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-tegra.c b/drivers/pwm/pwm-tegra.c index 36cc1452cb7a..f3528c56e894 100644 --- a/drivers/pwm/pwm-tegra.c +++ b/drivers/pwm/pwm-tegra.c @@ -142,7 +142,7 @@ static int tegra_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, * source clock rate as required_clk_rate, PWM controller will * be able to configure the requested period. */ - required_clk_rate = DIV_ROUND_UP_ULL(NSEC_PER_SEC << PWM_DUTY_WIDTH, + required_clk_rate = DIV_ROUND_UP_ULL((u64)NSEC_PER_SEC << PWM_DUTY_WIDTH, period_ns); err = clk_set_rate(pc->clk, required_clk_rate); From f9089b95548f0272e02a89989c511e235561d051 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Tue, 6 Dec 2022 12:17:31 +0400 Subject: [PATCH 0654/4345] usb: dwc3: qcom: Fix memory leak in dwc3_qcom_interconnect_init [ Upstream commit 97a48da1619ba6bd42a0e5da0a03aa490a9496b1 ] of_icc_get() alloc resources for path handle, we should release it when not need anymore. Like the release in dwc3_qcom_interconnect_exit() function. Add icc_put() in error handling to fix this. Fixes: bea46b981515 ("usb: dwc3: qcom: Add interconnect support in dwc3 driver") Cc: stable Acked-by: Thinh Nguyen Signed-off-by: Miaoqian Lin Link: https://lore.kernel.org/r/20221206081731.818107-1-linmq006@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/dwc3/dwc3-qcom.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index ca3a35fd8f74..528e36cc58ea 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -258,7 +258,8 @@ static int dwc3_qcom_interconnect_init(struct dwc3_qcom *qcom) if (IS_ERR(qcom->icc_path_apps)) { dev_err(dev, "failed to get apps-usb path: %ld\n", PTR_ERR(qcom->icc_path_apps)); - return PTR_ERR(qcom->icc_path_apps); + ret = PTR_ERR(qcom->icc_path_apps); + goto put_path_ddr; } if (usb_get_maximum_speed(&qcom->dwc3->dev) >= USB_SPEED_SUPER || @@ -271,17 +272,23 @@ static int dwc3_qcom_interconnect_init(struct dwc3_qcom *qcom) if (ret) { dev_err(dev, "failed to set bandwidth for usb-ddr path: %d\n", ret); - return ret; + goto put_path_apps; } ret = icc_set_bw(qcom->icc_path_apps, APPS_USB_AVG_BW, APPS_USB_PEAK_BW); if (ret) { dev_err(dev, "failed to set bandwidth for apps-usb path: %d\n", ret); - return ret; + goto put_path_apps; } return 0; + +put_path_apps: + icc_put(qcom->icc_path_apps); +put_path_ddr: + icc_put(qcom->icc_path_ddr); + return ret; } /** From fe6ea044c4f05706cb71040055b1c70c6c8275e0 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sun, 11 Dec 2022 18:18:55 -0300 Subject: [PATCH 0655/4345] cifs: fix oops during encryption [ Upstream commit f7f291e14dde32a07b1f0aa06921d28f875a7b54 ] When running xfstests against Azure the following oops occurred on an arm64 system Unable to handle kernel write to read-only memory at virtual address ffff0001221cf000 Mem abort info: ESR = 0x9600004f EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x0f: level 3 permission fault Data abort info: ISV = 0, ISS = 0x0000004f CM = 0, WnR = 1 swapper pgtable: 4k pages, 48-bit VAs, pgdp=00000000294f3000 [ffff0001221cf000] pgd=18000001ffff8003, p4d=18000001ffff8003, pud=18000001ff82e003, pmd=18000001ff71d003, pte=00600001221cf787 Internal error: Oops: 9600004f [#1] PREEMPT SMP ... pstate: 80000005 (Nzcv daif -PAN -UAO -TCO BTYPE=--) pc : __memcpy+0x40/0x230 lr : scatterwalk_copychunks+0xe0/0x200 sp : ffff800014e92de0 x29: ffff800014e92de0 x28: ffff000114f9de80 x27: 0000000000000008 x26: 0000000000000008 x25: ffff800014e92e78 x24: 0000000000000008 x23: 0000000000000001 x22: 0000040000000000 x21: ffff000000000000 x20: 0000000000000001 x19: ffff0001037c4488 x18: 0000000000000014 x17: 235e1c0d6efa9661 x16: a435f9576b6edd6c x15: 0000000000000058 x14: 0000000000000001 x13: 0000000000000008 x12: ffff000114f2e590 x11: ffffffffffffffff x10: 0000040000000000 x9 : ffff8000105c3580 x8 : 2e9413b10000001a x7 : 534b4410fb86b005 x6 : 534b4410fb86b005 x5 : ffff0001221cf008 x4 : ffff0001037c4490 x3 : 0000000000000001 x2 : 0000000000000008 x1 : ffff0001037c4488 x0 : ffff0001221cf000 Call trace: __memcpy+0x40/0x230 scatterwalk_map_and_copy+0x98/0x100 crypto_ccm_encrypt+0x150/0x180 crypto_aead_encrypt+0x2c/0x40 crypt_message+0x750/0x880 smb3_init_transform_rq+0x298/0x340 smb_send_rqst.part.11+0xd8/0x180 smb_send_rqst+0x3c/0x100 compound_send_recv+0x534/0xbc0 smb2_query_info_compound+0x32c/0x440 smb2_set_ea+0x438/0x4c0 cifs_xattr_set+0x5d4/0x7c0 This is because in scatterwalk_copychunks(), we attempted to write to a buffer (@sign) that was allocated in the stack (vmalloc area) by crypt_message() and thus accessing its remaining 8 (x2) bytes ended up crossing a page boundary. To simply fix it, we could just pass @sign kmalloc'd from crypt_message() and then we're done. Luckily, we don't seem to pass any other vmalloc'd buffers in smb_rqst::rq_iov... Instead, let's map the correct pages and offsets from vmalloc buffers as well in cifs_sg_set_buf() and then avoiding such oopses. Signed-off-by: Paulo Alcantara (SUSE) Cc: stable@vger.kernel.org Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/cifs/cifsglob.h | 69 +++++++++++++++++++++ fs/cifs/cifsproto.h | 4 +- fs/cifs/misc.c | 4 +- fs/cifs/smb2ops.c | 147 +++++++++++++++++++++----------------------- 4 files changed, 143 insertions(+), 81 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 196285b0fe46..92a7628560cc 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -22,6 +22,8 @@ #include #include #include +#include +#include #include #include #include "cifs_fs_sb.h" @@ -30,6 +32,7 @@ #include #include #include "smb2pdu.h" +#include "smb2glob.h" #define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */ @@ -2046,4 +2049,70 @@ static inline bool is_tcon_dfs(struct cifs_tcon *tcon) tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT); } +static inline unsigned int cifs_get_num_sgs(const struct smb_rqst *rqst, + int num_rqst, + const u8 *sig) +{ + unsigned int len, skip; + unsigned int nents = 0; + unsigned long addr; + int i, j; + + /* Assumes the first rqst has a transform header as the first iov. + * I.e. + * rqst[0].rq_iov[0] is transform header + * rqst[0].rq_iov[1+] data to be encrypted/decrypted + * rqst[1+].rq_iov[0+] data to be encrypted/decrypted + */ + for (i = 0; i < num_rqst; i++) { + /* + * The first rqst has a transform header where the + * first 20 bytes are not part of the encrypted blob. + */ + for (j = 0; j < rqst[i].rq_nvec; j++) { + struct kvec *iov = &rqst[i].rq_iov[j]; + + skip = (i == 0) && (j == 0) ? 20 : 0; + addr = (unsigned long)iov->iov_base + skip; + if (unlikely(is_vmalloc_addr((void *)addr))) { + len = iov->iov_len - skip; + nents += DIV_ROUND_UP(offset_in_page(addr) + len, + PAGE_SIZE); + } else { + nents++; + } + } + nents += rqst[i].rq_npages; + } + nents += DIV_ROUND_UP(offset_in_page(sig) + SMB2_SIGNATURE_SIZE, PAGE_SIZE); + return nents; +} + +/* We can not use the normal sg_set_buf() as we will sometimes pass a + * stack object as buf. + */ +static inline struct scatterlist *cifs_sg_set_buf(struct scatterlist *sg, + const void *buf, + unsigned int buflen) +{ + unsigned long addr = (unsigned long)buf; + unsigned int off = offset_in_page(addr); + + addr &= PAGE_MASK; + if (unlikely(is_vmalloc_addr((void *)addr))) { + do { + unsigned int len = min_t(unsigned int, buflen, PAGE_SIZE - off); + + sg_set_page(sg++, vmalloc_to_page((void *)addr), len, off); + + off = 0; + addr += PAGE_SIZE; + buflen -= len; + } while (buflen); + } else { + sg_set_page(sg++, virt_to_page(addr), buflen, off); + } + return sg; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index a6ca4eda9a5a..ca34cc1e1931 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -602,8 +602,8 @@ int cifs_alloc_hash(const char *name, struct crypto_shash **shash, struct sdesc **sdesc); void cifs_free_hash(struct crypto_shash **shash, struct sdesc **sdesc); -extern void rqst_page_get_length(struct smb_rqst *rqst, unsigned int page, - unsigned int *len, unsigned int *offset); +void rqst_page_get_length(const struct smb_rqst *rqst, unsigned int page, + unsigned int *len, unsigned int *offset); struct cifs_chan * cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server); int cifs_try_adding_channels(struct cifs_ses *ses); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 9d740916a8ee..9044b0fca9a3 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -974,8 +974,8 @@ cifs_free_hash(struct crypto_shash **shash, struct sdesc **sdesc) * Input: rqst - a smb_rqst, page - a page index for rqst * Output: *len - the length for this page, *offset - the offset for this page */ -void rqst_page_get_length(struct smb_rqst *rqst, unsigned int page, - unsigned int *len, unsigned int *offset) +void rqst_page_get_length(const struct smb_rqst *rqst, unsigned int page, + unsigned int *len, unsigned int *offset) { *len = rqst->rq_pagesz; *offset = (page == 0) ? rqst->rq_offset : 0; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 72368b656b33..844db4652dd1 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -4164,69 +4164,82 @@ fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, unsigned int orig_len, memcpy(&tr_hdr->SessionId, &shdr->SessionId, 8); } -/* We can not use the normal sg_set_buf() as we will sometimes pass a - * stack object as buf. - */ -static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf, - unsigned int buflen) +static void *smb2_aead_req_alloc(struct crypto_aead *tfm, const struct smb_rqst *rqst, + int num_rqst, const u8 *sig, u8 **iv, + struct aead_request **req, struct scatterlist **sgl, + unsigned int *num_sgs) { - void *addr; - /* - * VMAP_STACK (at least) puts stack into the vmalloc address space - */ - if (is_vmalloc_addr(buf)) - addr = vmalloc_to_page(buf); - else - addr = virt_to_page(buf); - sg_set_page(sg, addr, buflen, offset_in_page(buf)); -} + unsigned int req_size = sizeof(**req) + crypto_aead_reqsize(tfm); + unsigned int iv_size = crypto_aead_ivsize(tfm); + unsigned int len; + u8 *p; -/* Assumes the first rqst has a transform header as the first iov. - * I.e. - * rqst[0].rq_iov[0] is transform header - * rqst[0].rq_iov[1+] data to be encrypted/decrypted - * rqst[1+].rq_iov[0+] data to be encrypted/decrypted - */ -static struct scatterlist * -init_sg(int num_rqst, struct smb_rqst *rqst, u8 *sign) -{ - unsigned int sg_len; - struct scatterlist *sg; - unsigned int i; - unsigned int j; - unsigned int idx = 0; - int skip; + *num_sgs = cifs_get_num_sgs(rqst, num_rqst, sig); - sg_len = 1; - for (i = 0; i < num_rqst; i++) - sg_len += rqst[i].rq_nvec + rqst[i].rq_npages; + len = iv_size; + len += crypto_aead_alignmask(tfm) & ~(crypto_tfm_ctx_alignment() - 1); + len = ALIGN(len, crypto_tfm_ctx_alignment()); + len += req_size; + len = ALIGN(len, __alignof__(struct scatterlist)); + len += *num_sgs * sizeof(**sgl); - sg = kmalloc_array(sg_len, sizeof(struct scatterlist), GFP_KERNEL); - if (!sg) + p = kmalloc(len, GFP_ATOMIC); + if (!p) return NULL; - sg_init_table(sg, sg_len); + *iv = (u8 *)PTR_ALIGN(p, crypto_aead_alignmask(tfm) + 1); + *req = (struct aead_request *)PTR_ALIGN(*iv + iv_size, + crypto_tfm_ctx_alignment()); + *sgl = (struct scatterlist *)PTR_ALIGN((u8 *)*req + req_size, + __alignof__(struct scatterlist)); + return p; +} + +static void *smb2_get_aead_req(struct crypto_aead *tfm, const struct smb_rqst *rqst, + int num_rqst, const u8 *sig, u8 **iv, + struct aead_request **req, struct scatterlist **sgl) +{ + unsigned int off, len, skip; + struct scatterlist *sg; + unsigned int num_sgs; + unsigned long addr; + int i, j; + void *p; + + p = smb2_aead_req_alloc(tfm, rqst, num_rqst, sig, iv, req, sgl, &num_sgs); + if (!p) + return NULL; + + sg_init_table(*sgl, num_sgs); + sg = *sgl; + + /* Assumes the first rqst has a transform header as the first iov. + * I.e. + * rqst[0].rq_iov[0] is transform header + * rqst[0].rq_iov[1+] data to be encrypted/decrypted + * rqst[1+].rq_iov[0+] data to be encrypted/decrypted + */ for (i = 0; i < num_rqst; i++) { + /* + * The first rqst has a transform header where the + * first 20 bytes are not part of the encrypted blob. + */ for (j = 0; j < rqst[i].rq_nvec; j++) { - /* - * The first rqst has a transform header where the - * first 20 bytes are not part of the encrypted blob - */ + struct kvec *iov = &rqst[i].rq_iov[j]; + skip = (i == 0) && (j == 0) ? 20 : 0; - smb2_sg_set_buf(&sg[idx++], - rqst[i].rq_iov[j].iov_base + skip, - rqst[i].rq_iov[j].iov_len - skip); - } - + addr = (unsigned long)iov->iov_base + skip; + len = iov->iov_len - skip; + sg = cifs_sg_set_buf(sg, (void *)addr, len); + } for (j = 0; j < rqst[i].rq_npages; j++) { - unsigned int len, offset; - - rqst_page_get_length(&rqst[i], j, &len, &offset); - sg_set_page(&sg[idx++], rqst[i].rq_pages[j], len, offset); + rqst_page_get_length(&rqst[i], j, &len, &off); + sg_set_page(sg++, rqst[i].rq_pages[j], len, off); } } - smb2_sg_set_buf(&sg[idx], sign, SMB2_SIGNATURE_SIZE); - return sg; + cifs_sg_set_buf(sg, sig, SMB2_SIGNATURE_SIZE); + + return p; } static int @@ -4270,11 +4283,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, u8 sign[SMB2_SIGNATURE_SIZE] = {}; u8 key[SMB3_ENC_DEC_KEY_SIZE]; struct aead_request *req; - char *iv; - unsigned int iv_len; + u8 *iv; DECLARE_CRYPTO_WAIT(wait); struct crypto_aead *tfm; unsigned int crypt_len = le32_to_cpu(tr_hdr->OriginalMessageSize); + void *creq; rc = smb2_get_enc_key(server, tr_hdr->SessionId, enc, key); if (rc) { @@ -4309,32 +4322,15 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, return rc; } - req = aead_request_alloc(tfm, GFP_KERNEL); - if (!req) { - cifs_server_dbg(VFS, "%s: Failed to alloc aead request\n", __func__); + creq = smb2_get_aead_req(tfm, rqst, num_rqst, sign, &iv, &req, &sg); + if (unlikely(!creq)) return -ENOMEM; - } if (!enc) { memcpy(sign, &tr_hdr->Signature, SMB2_SIGNATURE_SIZE); crypt_len += SMB2_SIGNATURE_SIZE; } - sg = init_sg(num_rqst, rqst, sign); - if (!sg) { - cifs_server_dbg(VFS, "%s: Failed to init sg\n", __func__); - rc = -ENOMEM; - goto free_req; - } - - iv_len = crypto_aead_ivsize(tfm); - iv = kzalloc(iv_len, GFP_KERNEL); - if (!iv) { - cifs_server_dbg(VFS, "%s: Failed to alloc iv\n", __func__); - rc = -ENOMEM; - goto free_sg; - } - if ((server->cipher_type == SMB2_ENCRYPTION_AES128_GCM) || (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) memcpy(iv, (char *)tr_hdr->Nonce, SMB3_AES_GCM_NONCE); @@ -4343,6 +4339,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, memcpy(iv + 1, (char *)tr_hdr->Nonce, SMB3_AES_CCM_NONCE); } + aead_request_set_tfm(req, tfm); aead_request_set_crypt(req, sg, sg, crypt_len, iv); aead_request_set_ad(req, assoc_data_len); @@ -4355,11 +4352,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, if (!rc && enc) memcpy(&tr_hdr->Signature, sign, SMB2_SIGNATURE_SIZE); - kfree(iv); -free_sg: - kfree(sg); -free_req: - kfree(req); + kfree_sensitive(creq); return rc; } From f5d8738fbe33e71959b5a69221ecf515032d3fc7 Mon Sep 17 00:00:00 2001 From: Klaus Jensen Date: Tue, 13 Dec 2022 09:58:07 +0100 Subject: [PATCH 0656/4345] nvme-pci: fix doorbell buffer value endianness [ Upstream commit b5f96cb719d8ba220b565ddd3ba4ac0d8bcfb130 ] When using shadow doorbells, the event index and the doorbell values are written to host memory. Prior to this patch, the values written would erroneously be written in host endianness. This causes trouble on big-endian platforms. Fix this by adding missing endian conversions. This issue was noticed by Guenter while testing various big-endian platforms under QEMU[1]. A similar fix required for hw/nvme in QEMU is up for review as well[2]. [1]: https://lore.kernel.org/qemu-devel/20221209110022.GA3396194@roeck-us.net/ [2]: https://lore.kernel.org/qemu-devel/20221212114409.34972-4-its@irrelevant.dk/ Fixes: f9f38e33389c ("nvme: improve performance for virtual NVMe devices") Reported-by: Guenter Roeck Signed-off-by: Klaus Jensen Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c222d7bf6ce1..948b027a75d3 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -139,9 +139,9 @@ struct nvme_dev { mempool_t *iod_mempool; /* shadow doorbell buffer support: */ - u32 *dbbuf_dbs; + __le32 *dbbuf_dbs; dma_addr_t dbbuf_dbs_dma_addr; - u32 *dbbuf_eis; + __le32 *dbbuf_eis; dma_addr_t dbbuf_eis_dma_addr; /* host memory buffer support: */ @@ -209,10 +209,10 @@ struct nvme_queue { #define NVMEQ_SQ_CMB 1 #define NVMEQ_DELETE_ERROR 2 #define NVMEQ_POLLED 3 - u32 *dbbuf_sq_db; - u32 *dbbuf_cq_db; - u32 *dbbuf_sq_ei; - u32 *dbbuf_cq_ei; + __le32 *dbbuf_sq_db; + __le32 *dbbuf_cq_db; + __le32 *dbbuf_sq_ei; + __le32 *dbbuf_cq_ei; struct completion delete_done; }; @@ -334,11 +334,11 @@ static inline int nvme_dbbuf_need_event(u16 event_idx, u16 new_idx, u16 old) } /* Update dbbuf and return true if an MMIO is required */ -static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, - volatile u32 *dbbuf_ei) +static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db, + volatile __le32 *dbbuf_ei) { if (dbbuf_db) { - u16 old_value; + u16 old_value, event_idx; /* * Ensure that the queue is written before updating @@ -346,8 +346,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, */ wmb(); - old_value = *dbbuf_db; - *dbbuf_db = value; + old_value = le32_to_cpu(*dbbuf_db); + *dbbuf_db = cpu_to_le32(value); /* * Ensure that the doorbell is updated before reading the event @@ -357,7 +357,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, */ mb(); - if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value)) + event_idx = le32_to_cpu(*dbbuf_ei); + if (!nvme_dbbuf_need_event(event_idx, value, old_value)) return false; } From dfb6d54893d544151e7f480bc44cfe7823f5ad23 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 19 Dec 2022 10:59:06 -0800 Subject: [PATCH 0657/4345] nvme-pci: fix mempool alloc size [ Upstream commit c89a529e823d51dd23c7ec0c047c7a454a428541 ] Convert the max size to bytes to match the units of the divisor that calculates the worst-case number of PRP entries. The result is used to determine how many PRP Lists are required. The code was previously rounding this to 1 list, but we can require 2 in the worst case. In that scenario, the driver would corrupt memory beyond the size provided by the mempool. While unlikely to occur (you'd need a 4MB in exactly 127 phys segments on a queue that doesn't support SGLs), this memory corruption has been observed by kfence. Cc: Jens Axboe Fixes: 943e942e6266f ("nvme-pci: limit max IO size and segments to avoid high order allocations") Signed-off-by: Keith Busch Reviewed-by: Jens Axboe Reviewed-by: Kanchan Joshi Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 948b027a75d3..0452fb96df69 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -372,8 +372,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db, */ static int nvme_pci_npages_prp(void) { - unsigned nprps = DIV_ROUND_UP(NVME_MAX_KB_SZ + NVME_CTRL_PAGE_SIZE, - NVME_CTRL_PAGE_SIZE); + unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE; + unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE); return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8); } From cc512539c44f173c2a5fc967e4feb0043bc5773d Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 19 Dec 2022 13:54:55 -0800 Subject: [PATCH 0658/4345] nvme-pci: fix page size checks [ Upstream commit 841734234a28fd5cd0889b84bd4d93a0988fa11e ] The size allocated out of the dma pool is at most NVME_CTRL_PAGE_SIZE, which may be smaller than the PAGE_SIZE. Fixes: c61b82c7b7134 ("nvme-pci: fix PRP pool size") Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 0452fb96df69..67dd68462b81 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -33,7 +33,7 @@ #define SQ_SIZE(q) ((q)->q_depth << (q)->sqes) #define CQ_SIZE(q) ((q)->q_depth * sizeof(struct nvme_completion)) -#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc)) +#define SGES_PER_PAGE (NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc)) /* * These can be higher, but we need to ensure that any command doesn't @@ -374,7 +374,7 @@ static int nvme_pci_npages_prp(void) { unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE; unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE); - return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8); + return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8); } /* @@ -384,7 +384,7 @@ static int nvme_pci_npages_prp(void) static int nvme_pci_npages_sgl(void) { return DIV_ROUND_UP(NVME_MAX_SEGS * sizeof(struct nvme_sgl_desc), - PAGE_SIZE); + NVME_CTRL_PAGE_SIZE); } static size_t nvme_pci_iod_alloc_size(void) @@ -735,7 +735,7 @@ static void nvme_pci_sgl_set_seg(struct nvme_sgl_desc *sge, sge->length = cpu_to_le32(entries * sizeof(*sge)); sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4; } else { - sge->length = cpu_to_le32(PAGE_SIZE); + sge->length = cpu_to_le32(NVME_CTRL_PAGE_SIZE); sge->type = NVME_SGL_FMT_SEG_DESC << 4; } } From ab711f3eda7a62c800b41997e818b675812f53a9 Mon Sep 17 00:00:00 2001 From: Adam Vodopjan Date: Fri, 9 Dec 2022 09:26:34 +0000 Subject: [PATCH 0659/4345] ata: ahci: Fix PCS quirk application for suspend [ Upstream commit 37e14e4f3715428b809e4df9a9958baa64c77d51 ] Since kernel 5.3.4 my laptop (ICH8M controller) does not see Kingston SV300S37A60G SSD disk connected into a SATA connector on wake from suspend. The problem was introduced in c312ef176399 ("libata/ahci: Drop PCS quirk for Denverton and beyond"): the quirk is not applied on wake from suspend as it originally was. It is worth to mention the commit contained another bug: the quirk is not applied at all to controllers which require it. The fix commit 09d6ac8dc51a ("libata/ahci: Fix PCS quirk application") landed in 5.3.8. So testing my patch anywhere between commits c312ef176399 and 09d6ac8dc51a is pointless. Not all disks trigger the problem. For example nothing bad happens with Western Digital WD5000LPCX HDD. Test hardware: - Acer 5920G with ICH8M SATA controller - sda: some SATA HDD connnected into the DVD drive IDE port with a SATA-IDE caddy. It is a boot disk - sdb: Kingston SV300S37A60G SSD connected into the only SATA port Sample "dmesg --notime | grep -E '^(sd |ata)'" output on wake: sd 0:0:0:0: [sda] Starting disk sd 2:0:0:0: [sdb] Starting disk ata4: SATA link down (SStatus 4 SControl 300) ata3: SATA link down (SStatus 4 SControl 300) ata1.00: ACPI cmd ef/03:0c:00:00:00:a0 (SET FEATURES) filtered out ata1.00: ACPI cmd ef/03:42:00:00:00:a0 (SET FEATURES) filtered out ata1: FORCE: cable set to 80c ata5: SATA link down (SStatus 0 SControl 300) ata3: SATA link down (SStatus 4 SControl 300) ata3: SATA link down (SStatus 4 SControl 300) ata3.00: disabled sd 2:0:0:0: rejecting I/O to offline device ata3.00: detaching (SCSI 2:0:0:0) sd 2:0:0:0: [sdb] Start/Stop Unit failed: Result: hostbyte=DID_NO_CONNECT driverbyte=DRIVER_OK sd 2:0:0:0: [sdb] Synchronizing SCSI cache sd 2:0:0:0: [sdb] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK sd 2:0:0:0: [sdb] Stopping disk sd 2:0:0:0: [sdb] Start/Stop Unit failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK Commit c312ef176399 dropped ahci_pci_reset_controller() which internally calls ahci_reset_controller() and applies the PCS quirk if needed after that. It was called each time a reset was required instead of just ahci_reset_controller(). This patch puts the function back in place. Fixes: c312ef176399 ("libata/ahci: Drop PCS quirk for Denverton and beyond") Signed-off-by: Adam Vodopjan Signed-off-by: Damien Le Moal Signed-off-by: Sasha Levin --- drivers/ata/ahci.c | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index ff2add0101fe..7ca9fa9a75e2 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -83,6 +83,7 @@ enum board_ids { static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static void ahci_remove_one(struct pci_dev *dev); static void ahci_shutdown_one(struct pci_dev *dev); +static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hpriv); static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline); static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class, @@ -664,6 +665,25 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev, ahci_save_initial_config(&pdev->dev, hpriv); } +static int ahci_pci_reset_controller(struct ata_host *host) +{ + struct pci_dev *pdev = to_pci_dev(host->dev); + struct ahci_host_priv *hpriv = host->private_data; + int rc; + + rc = ahci_reset_controller(host); + if (rc) + return rc; + + /* + * If platform firmware failed to enable ports, try to enable + * them here. + */ + ahci_intel_pcs_quirk(pdev, hpriv); + + return 0; +} + static void ahci_pci_init_controller(struct ata_host *host) { struct ahci_host_priv *hpriv = host->private_data; @@ -865,7 +885,7 @@ static int ahci_pci_device_runtime_resume(struct device *dev) struct ata_host *host = pci_get_drvdata(pdev); int rc; - rc = ahci_reset_controller(host); + rc = ahci_pci_reset_controller(host); if (rc) return rc; ahci_pci_init_controller(host); @@ -900,7 +920,7 @@ static int ahci_pci_device_resume(struct device *dev) ahci_mcp89_apple_enable(pdev); if (pdev->dev.power.power_state.event == PM_EVENT_SUSPEND) { - rc = ahci_reset_controller(host); + rc = ahci_pci_reset_controller(host); if (rc) return rc; @@ -1785,12 +1805,6 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* save initial config */ ahci_pci_save_initial_config(pdev, hpriv); - /* - * If platform firmware failed to enable ports, try to enable - * them here. - */ - ahci_intel_pcs_quirk(pdev, hpriv); - /* prepare host */ if (hpriv->cap & HOST_CAP_NCQ) { pi.flags |= ATA_FLAG_NCQ; @@ -1900,7 +1914,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) return rc; - rc = ahci_reset_controller(host); + rc = ahci_pci_reset_controller(host); if (rc) return rc; From 4b3282a9779c079c4fa5a911ccae4cf7c30a580f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Dec 2022 10:30:45 +0100 Subject: [PATCH 0660/4345] nvme: fix the NVME_CMD_EFFECTS_CSE_MASK definition [ Upstream commit 685e6311637e46f3212439ce2789f8a300e5050f ] 3 << 16 does not generate the correct mask for bits 16, 17 and 18. Use the GENMASK macro to generate the correct mask instead. Fixes: 84fef62d135b ("nvme: check admin passthru command effects") Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Kanchan Joshi Signed-off-by: Sasha Levin --- include/linux/nvme.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/linux/nvme.h b/include/linux/nvme.h index bfed36e342cc..fe39ed9e9303 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -7,6 +7,7 @@ #ifndef _LINUX_NVME_H #define _LINUX_NVME_H +#include #include #include @@ -528,7 +529,7 @@ enum { NVME_CMD_EFFECTS_NCC = 1 << 2, NVME_CMD_EFFECTS_NIC = 1 << 3, NVME_CMD_EFFECTS_CCC = 1 << 4, - NVME_CMD_EFFECTS_CSE_MASK = 3 << 16, + NVME_CMD_EFFECTS_CSE_MASK = GENMASK(18, 16), NVME_CMD_EFFECTS_UUID_SEL = 1 << 19, }; From 57ae492f620ceaaad0188bd39ce3a3dc4bdac64c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Dec 2022 09:51:19 +0100 Subject: [PATCH 0661/4345] nvmet: don't defer passthrough commands with trivial effects to the workqueue [ Upstream commit 2a459f6933e1c459bffb7cc73fd6c900edc714bd ] Mask out the "Command Supported" and "Logical Block Content Change" bits and only defer execution of commands that have non-trivial effects to the workqueue for synchronous execution. This allows to execute admin commands asynchronously on controllers that provide a Command Supported and Effects log page, and will keep allowing to execute Write commands asynchronously once command effects on I/O commands are taken into account. Fixes: c1fef73f793b ("nvmet: add passthru code to process commands") Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Kanchan Joshi Signed-off-by: Sasha Levin --- drivers/nvme/target/passthru.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index d24251ece502..f76d01028df0 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -259,14 +259,13 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) } /* - * If there are effects for the command we are about to execute, or - * an end_req function we need to use nvme_execute_passthru_rq() - * synchronously in a work item seeing the end_req function and - * nvme_passthru_end() can't be called in the request done callback - * which is typically in interrupt context. + * If a command needs post-execution fixups, or there are any + * non-trivial effects, make sure to execute the command synchronously + * in a workqueue so that nvme_passthru_end gets called. */ effects = nvme_command_effects(ctrl, ns, req->cmd->common.opcode); - if (req->p.use_workqueue || effects) { + if (req->p.use_workqueue || + (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))) { INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work); req->p.rq = rq; schedule_work(&req->p.work); From 0af0e115ff59d638f45416a004cdd8edb38db40c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 14 Nov 2022 23:27:46 +0530 Subject: [PATCH 0662/4345] objtool: Fix SEGFAULT [ Upstream commit efb11fdb3e1a9f694fa12b70b21e69e55ec59c36 ] find_insn() will return NULL in case of failure. Check insn in order to avoid a kernel Oops for NULL pointer dereference. Tested-by: Naveen N. Rao Reviewed-by: Naveen N. Rao Acked-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221114175754.1131267-9-sv@linux.ibm.com Signed-off-by: Sasha Levin --- tools/objtool/check.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5d64b673da2d..700984e7f5ba 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -196,7 +196,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, return false; insn = find_insn(file, func->sec, func->offset); - if (!insn->func) + if (!insn || !insn->func) return false; func_for_each_insn(file, func, insn) { From f2167f10fcca68ab9ae3f8d94d2c704c5541ac69 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Fri, 18 Nov 2022 09:07:41 -0600 Subject: [PATCH 0663/4345] powerpc/rtas: avoid device tree lookups in rtas_os_term() [ Upstream commit ed2213bfb192ab51f09f12e9b49b5d482c6493f3 ] rtas_os_term() is called during panic. Its behavior depends on a couple of conditions in the /rtas node of the device tree, the traversal of which entails locking and local IRQ state changes. If the kernel panics while devtree_lock is held, rtas_os_term() as currently written could hang. Instead of discovering the relevant characteristics at panic time, cache them in file-static variables at boot. Note the lookup for "ibm,extended-os-term" is converted to of_property_read_bool() since it is a boolean property, not an RTAS function token. Signed-off-by: Nathan Lynch Reviewed-by: Nicholas Piggin Reviewed-by: Andrew Donnellan [mpe: Incorporate suggested change from Nick] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221118150751.469393-4-nathanl@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/rtas.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index bf962051af0a..aa66317a9a49 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -715,6 +715,7 @@ void __noreturn rtas_halt(void) /* Must be in the RMO region, so we place it here */ static char rtas_os_term_buf[2048]; +static s32 ibm_os_term_token = RTAS_UNKNOWN_SERVICE; void rtas_os_term(char *str) { @@ -726,14 +727,13 @@ void rtas_os_term(char *str) * this property may terminate the partition which we want to avoid * since it interferes with panic_timeout. */ - if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term") || - RTAS_UNKNOWN_SERVICE == rtas_token("ibm,extended-os-term")) + if (ibm_os_term_token == RTAS_UNKNOWN_SERVICE) return; snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str); do { - status = rtas_call(rtas_token("ibm,os-term"), 1, 1, NULL, + status = rtas_call(ibm_os_term_token, 1, 1, NULL, __pa(rtas_os_term_buf)); } while (rtas_busy_delay(status)); @@ -1267,6 +1267,13 @@ void __init rtas_initialize(void) no_entry = of_property_read_u32(rtas.dev, "linux,rtas-entry", &entry); rtas.entry = no_entry ? rtas.base : entry; + /* + * Discover these now to avoid device tree lookups in the + * panic path. + */ + if (of_property_read_bool(rtas.dev, "ibm,extended-os-term")) + ibm_os_term_token = rtas_token("ibm,os-term"); + /* If RTAS was found, allocate the RMO buffer for it and look for * the stop-self token if any */ From 6f7e2fcab73372a371ab4017cbedf7a71f4f9b40 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Fri, 18 Nov 2022 09:07:42 -0600 Subject: [PATCH 0664/4345] powerpc/rtas: avoid scheduling in rtas_os_term() [ Upstream commit 6c606e57eecc37d6b36d732b1ff7e55b7dc32dd4 ] It's unsafe to use rtas_busy_delay() to handle a busy status from the ibm,os-term RTAS function in rtas_os_term(): Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b BUG: sleeping function called from invalid context at arch/powerpc/kernel/rtas.c:618 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 1, name: swapper/0 preempt_count: 2, expected: 0 CPU: 7 PID: 1 Comm: swapper/0 Tainted: G D 6.0.0-rc5-02182-gf8553a572277-dirty #9 Call Trace: [c000000007b8f000] [c000000001337110] dump_stack_lvl+0xb4/0x110 (unreliable) [c000000007b8f040] [c0000000002440e4] __might_resched+0x394/0x3c0 [c000000007b8f0e0] [c00000000004f680] rtas_busy_delay+0x120/0x1b0 [c000000007b8f100] [c000000000052d04] rtas_os_term+0xb8/0xf4 [c000000007b8f180] [c0000000001150fc] pseries_panic+0x50/0x68 [c000000007b8f1f0] [c000000000036354] ppc_panic_platform_handler+0x34/0x50 [c000000007b8f210] [c0000000002303c4] notifier_call_chain+0xd4/0x1c0 [c000000007b8f2b0] [c0000000002306cc] atomic_notifier_call_chain+0xac/0x1c0 [c000000007b8f2f0] [c0000000001d62b8] panic+0x228/0x4d0 [c000000007b8f390] [c0000000001e573c] do_exit+0x140c/0x1420 [c000000007b8f480] [c0000000001e586c] make_task_dead+0xdc/0x200 Use rtas_busy_delay_time() instead, which signals without side effects whether to attempt the ibm,os-term RTAS call again. Signed-off-by: Nathan Lynch Reviewed-by: Nicholas Piggin Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221118150751.469393-5-nathanl@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/rtas.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index aa66317a9a49..014229c40435 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -732,10 +732,15 @@ void rtas_os_term(char *str) snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str); + /* + * Keep calling as long as RTAS returns a "try again" status, + * but don't use rtas_busy_delay(), which potentially + * schedules. + */ do { status = rtas_call(ibm_os_term_token, 1, 1, NULL, __pa(rtas_os_term_buf)); - } while (rtas_busy_delay(status)); + } while (rtas_busy_delay_time(status)); if (status != 0) printk(KERN_EMERG "ibm,os-term call failed %d\n", status); From eaf0b782269f38642bc6fad72c9ace022fdeef78 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= Date: Mon, 28 Nov 2022 17:57:05 +0100 Subject: [PATCH 0665/4345] HID: multitouch: fix Asus ExpertBook P2 P2451FA trackpoint MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4eab1c2fe06c98a4dff258dd64800b6986c101e9 ] The HID descriptor of this device contains two mouse collections, one for mouse emulation and the other for the trackpoint. Both collections get merged and, because the first one defines X and Y, the movemenent events reported by the trackpoint collection are ignored. Set the MT_CLS_WIN_8_FORCE_MULTI_INPUT class for this device to be able to receive its reports. This fix is similar to/based on commit 40d5bb87377a ("HID: multitouch: enable multi-input as a quirk for some devices"). Link: https://gitlab.freedesktop.org/libinput/libinput/-/issues/825 Reported-by: Akito Tested-by: Akito Signed-off-by: José Expósito Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-multitouch.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index a78ce16d4782..ea8c52f0aa78 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1912,6 +1912,10 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_ELAN, 0x313a) }, + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_ELAN, 0x3148) }, + /* Elitegroup panel */ { .driver_data = MT_CLS_SERIAL, MT_USB_DEVICE(USB_VENDOR_ID_ELITEGROUP, From 0d992c044cfb2c552f03ee7e5fb99c034391f61b Mon Sep 17 00:00:00 2001 From: Terry Junge Date: Thu, 8 Dec 2022 15:05:06 -0800 Subject: [PATCH 0666/4345] HID: plantronics: Additional PIDs for double volume key presses quirk [ Upstream commit 3d57f36c89d8ba32b2c312f397a37fd1a2dc7cfc ] I no longer work for Plantronics (aka Poly, aka HP) and do not have access to the headsets in order to test. However, as noted by Maxim, the other 32xx models that share the same base code set as the 3220 would need the same quirk. This patch adds the PIDs for the rest of the Blackwire 32XX product family that require the quirk. Plantronics Blackwire 3210 Series (047f:c055) Plantronics Blackwire 3215 Series (047f:c057) Plantronics Blackwire 3225 Series (047f:c058) Quote from previous patch by Maxim Mikityanskiy Plantronics Blackwire 3220 Series (047f:c056) sends HID reports twice for each volume key press. This patch adds a quirk to hid-plantronics for this product ID, which will ignore the second volume key press if it happens within 5 ms from the last one that was handled. The patch was tested on the mentioned model only, it shouldn't affect other models, however, this quirk might be needed for them too. Auto-repeat (when a key is held pressed) is not affected, because the rate is about 3 times per second, which is far less frequent than once in 5 ms. End quote Signed-off-by: Terry Junge Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-ids.h | 3 +++ drivers/hid/hid-plantronics.c | 9 +++++++++ 2 files changed, 12 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 2001566be3f5..09c3f30f10d3 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -948,7 +948,10 @@ #define USB_DEVICE_ID_ORTEK_IHOME_IMAC_A210S 0x8003 #define USB_VENDOR_ID_PLANTRONICS 0x047f +#define USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3210_SERIES 0xc055 #define USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3220_SERIES 0xc056 +#define USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3215_SERIES 0xc057 +#define USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3225_SERIES 0xc058 #define USB_VENDOR_ID_PANASONIC 0x04da #define USB_DEVICE_ID_PANABOARD_UBT780 0x1044 diff --git a/drivers/hid/hid-plantronics.c b/drivers/hid/hid-plantronics.c index e81b7cec2d12..3d414ae194ac 100644 --- a/drivers/hid/hid-plantronics.c +++ b/drivers/hid/hid-plantronics.c @@ -198,9 +198,18 @@ err: } static const struct hid_device_id plantronics_devices[] = { + { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, + USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3210_SERIES), + .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3220_SERIES), .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, + { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, + USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3215_SERIES), + .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, + { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, + USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3225_SERIES), + .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, HID_ANY_ID) }, { } }; From 44cf50587e822714f52ceeadd16b6c38d1b29d0f Mon Sep 17 00:00:00 2001 From: Qiujun Huang Date: Sun, 4 Sep 2022 23:17:13 +0800 Subject: [PATCH 0667/4345] pstore/zone: Use GFP_ATOMIC to allocate zone buffer commit 99b3b837855b987563bcfb397cf9ddd88262814b upstream. There is a case found when triggering a panic_on_oom, pstore fails to dump kmsg. Because psz_kmsg_write_record can't get the new buffer. Handle this by using GFP_ATOMIC to allocate a buffer at lower watermark. Signed-off-by: Qiujun Huang Fixes: 335426c6dcdd ("pstore/zone: Provide way to skip "broken" zone for MTD devices") Cc: WeiXiong Liao Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/CAJRQjofRCF7wjrYmw3D7zd5QZnwHQq+F8U-mJDJ6NZ4bddYdLA@mail.gmail.com Signed-off-by: Greg Kroah-Hartman --- fs/pstore/zone.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c index 3ce89216670c..b50fc33f2ab2 100644 --- a/fs/pstore/zone.c +++ b/fs/pstore/zone.c @@ -761,7 +761,7 @@ static inline int notrace psz_kmsg_write_record(struct psz_context *cxt, /* avoid destroying old data, allocate a new one */ len = zone->buffer_size + sizeof(*zone->buffer); zone->oldbuf = zone->buffer; - zone->buffer = kzalloc(len, GFP_KERNEL); + zone->buffer = kzalloc(len, GFP_ATOMIC); if (!zone->buffer) { zone->buffer = zone->oldbuf; return -ENOMEM; From 12407462d3fccd865b0db8123d9d3972fd3c2aa5 Mon Sep 17 00:00:00 2001 From: Aditya Garg Date: Wed, 7 Dec 2022 03:05:40 +0000 Subject: [PATCH 0668/4345] hfsplus: fix bug causing custom uid and gid being unable to be assigned with mount commit 9f2b5debc07073e6dfdd774e3594d0224b991927 upstream. Despite specifying UID and GID in mount command, the specified UID and GID were not being assigned. This patch fixes this issue. Link: https://lkml.kernel.org/r/C0264BF5-059C-45CF-B8DA-3A3BD2C803A2@live.com Signed-off-by: Aditya Garg Reviewed-by: Viacheslav Dubeyko Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/hfsplus/hfsplus_fs.h | 2 ++ fs/hfsplus/inode.c | 4 ++-- fs/hfsplus/options.c | 4 ++++ 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index a92de5199ec3..c438680ef9f7 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -198,6 +198,8 @@ struct hfsplus_sb_info { #define HFSPLUS_SB_HFSX 3 #define HFSPLUS_SB_CASEFOLD 4 #define HFSPLUS_SB_NOBARRIER 5 +#define HFSPLUS_SB_UID 6 +#define HFSPLUS_SB_GID 7 static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb) { diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index e3da9e96b835..fe825c41a2a0 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -187,11 +187,11 @@ static void hfsplus_get_perms(struct inode *inode, mode = be16_to_cpu(perms->mode); i_uid_write(inode, be32_to_cpu(perms->owner)); - if (!i_uid_read(inode) && !mode) + if ((test_bit(HFSPLUS_SB_UID, &sbi->flags)) || (!i_uid_read(inode) && !mode)) inode->i_uid = sbi->uid; i_gid_write(inode, be32_to_cpu(perms->group)); - if (!i_gid_read(inode) && !mode) + if ((test_bit(HFSPLUS_SB_GID, &sbi->flags)) || (!i_gid_read(inode) && !mode)) inode->i_gid = sbi->gid; if (dir) { diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index 047e05c57560..c94a58762ad6 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -140,6 +140,8 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi) if (!uid_valid(sbi->uid)) { pr_err("invalid uid specified\n"); return 0; + } else { + set_bit(HFSPLUS_SB_UID, &sbi->flags); } break; case opt_gid: @@ -151,6 +153,8 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi) if (!gid_valid(sbi->gid)) { pr_err("invalid gid specified\n"); return 0; + } else { + set_bit(HFSPLUS_SB_GID, &sbi->flags); } break; case opt_part: From c3e8bbcbaa87d15ffc179abc0dcabb1e94f4757e Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Fri, 2 Dec 2022 09:41:01 +0800 Subject: [PATCH 0669/4345] binfmt: Fix error return code in load_elf_fdpic_binary() commit e7f703ff2507f4e9f496da96cd4b78fd3026120c upstream. Fix to return a negative error code from create_elf_fdpic_tables() instead of 0. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Wang Yufen Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/1669945261-30271-1-git-send-email-wangyufen@huawei.com Signed-off-by: Greg Kroah-Hartman --- fs/binfmt_elf_fdpic.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 5764295a3f0f..8c3b7cc8e2a1 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -434,8 +434,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->mm->start_stack = current->mm->start_brk + stack_size; #endif - if (create_elf_fdpic_tables(bprm, current->mm, - &exec_params, &interp_params) < 0) + retval = create_elf_fdpic_tables(bprm, current->mm, &exec_params, + &interp_params); + if (retval < 0) goto error; kdebug("- start_code %lx", current->mm->start_code); From 56abf8046bc1e12b3c21335dd50386be773a1522 Mon Sep 17 00:00:00 2001 From: Zhang Tianci Date: Thu, 1 Sep 2022 16:29:29 +0800 Subject: [PATCH 0670/4345] ovl: Use ovl mounter's fsuid and fsgid in ovl_link() commit 5b0db51215e895a361bc63132caa7cca36a53d6a upstream. There is a wrong case of link() on overlay: $ mkdir /lower /fuse /merge $ mount -t fuse /fuse $ mkdir /fuse/upper /fuse/work $ mount -t overlay /merge -o lowerdir=/lower,upperdir=/fuse/upper,\ workdir=work $ touch /merge/file $ chown bin.bin /merge/file // the file's caller becomes "bin" $ ln /merge/file /merge/lnkfile Then we will get an error(EACCES) because fuse daemon checks the link()'s caller is "bin", it denied this request. In the changing history of ovl_link(), there are two key commits: The first is commit bb0d2b8ad296 ("ovl: fix sgid on directory") which overrides the cred's fsuid/fsgid using the new inode. The new inode's owner is initialized by inode_init_owner(), and inode->fsuid is assigned to the current user. So the override fsuid becomes the current user. We know link() is actually modifying the directory, so the caller must have the MAY_WRITE permission on the directory. The current caller may should have this permission. This is acceptable to use the caller's fsuid. The second is commit 51f7e52dc943 ("ovl: share inode for hard link") which removed the inode creation in ovl_link(). This commit move inode_init_owner() into ovl_create_object(), so the ovl_link() just give the old inode to ovl_create_or_link(). Then the override fsuid becomes the old inode's fsuid, neither the caller nor the overlay's mounter! So this is incorrect. Fix this bug by using ovl mounter's fsuid/fsgid to do underlying fs's link(). Link: https://lore.kernel.org/all/20220817102952.xnvesg3a7rbv576x@wittgenstein/T Link: https://lore.kernel.org/lkml/20220825130552.29587-1-zhangtianci.1997@bytedance.com/t Signed-off-by: Zhang Tianci Signed-off-by: Jiachen Zhang Reviewed-by: Christian Brauner (Microsoft) Fixes: 51f7e52dc943 ("ovl: share inode for hard link") Cc: # v4.8 Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/dir.c | 46 ++++++++++++++++++++++++++++++---------------- 1 file changed, 30 insertions(+), 16 deletions(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index d0e5cde27702..8ebd9f2b1c95 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -586,28 +586,42 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, goto out_revert_creds; } - err = -ENOMEM; - override_cred = prepare_creds(); - if (override_cred) { + if (!attr->hardlink) { + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_revert_creds; + /* + * In the creation cases(create, mkdir, mknod, symlink), + * ovl should transfer current's fs{u,g}id to underlying + * fs. Because underlying fs want to initialize its new + * inode owner using current's fs{u,g}id. And in this + * case, the @inode is a new inode that is initialized + * in inode_init_owner() to current's fs{u,g}id. So use + * the inode's i_{u,g}id to override the cred's fs{u,g}id. + * + * But in the other hardlink case, ovl_link() does not + * create a new inode, so just use the ovl mounter's + * fs{u,g}id. + */ override_cred->fsuid = inode->i_uid; override_cred->fsgid = inode->i_gid; - if (!attr->hardlink) { - err = security_dentry_create_files_as(dentry, - attr->mode, &dentry->d_name, old_cred, - override_cred); - if (err) { - put_cred(override_cred); - goto out_revert_creds; - } + err = security_dentry_create_files_as(dentry, + attr->mode, &dentry->d_name, old_cred, + override_cred); + if (err) { + put_cred(override_cred); + goto out_revert_creds; } put_cred(override_creds(override_cred)); put_cred(override_cred); - - if (!ovl_dentry_is_whiteout(dentry)) - err = ovl_create_upper(dentry, inode, attr); - else - err = ovl_create_over_whiteout(dentry, inode, attr); } + + if (!ovl_dentry_is_whiteout(dentry)) + err = ovl_create_upper(dentry, inode, attr); + else + err = ovl_create_over_whiteout(dentry, inode, attr); + out_revert_creds: revert_creds(old_cred); return err; From 5e79f77ea42fdc7dc147f640cbc2c925b318954e Mon Sep 17 00:00:00 2001 From: Artem Egorkine Date: Sun, 25 Dec 2022 12:57:27 +0200 Subject: [PATCH 0671/4345] ALSA: line6: correct midi status byte when receiving data from podxt commit 8508fa2e7472f673edbeedf1b1d2b7a6bb898ecc upstream. A PODxt device sends 0xb2, 0xc2 or 0xf2 as a status byte for MIDI messages over USB that should otherwise have a 0xb0, 0xc0 or 0xf0 status byte. This is usually corrected by the driver on other OSes. This fixes MIDI sysex messages sent by PODxt. [ tiwai: fixed white spaces ] Signed-off-by: Artem Egorkine Cc: Link: https://lore.kernel.org/r/20221225105728.1153989-1-arteme@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/line6/driver.c | 3 ++- sound/usb/line6/midi.c | 3 ++- sound/usb/line6/midibuf.c | 25 +++++++++++++++++-------- sound/usb/line6/midibuf.h | 5 ++++- sound/usb/line6/pod.c | 3 ++- 5 files changed, 27 insertions(+), 12 deletions(-) diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index 59faa5a9a714..b67617b68e50 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -304,7 +304,8 @@ static void line6_data_received(struct urb *urb) for (;;) { done = line6_midibuf_read(mb, line6->buffer_message, - LINE6_MIDI_MESSAGE_MAXLEN); + LINE6_MIDI_MESSAGE_MAXLEN, + LINE6_MIDIBUF_READ_RX); if (done <= 0) break; diff --git a/sound/usb/line6/midi.c b/sound/usb/line6/midi.c index ba0e2b7e8fe1..d52355de2bbc 100644 --- a/sound/usb/line6/midi.c +++ b/sound/usb/line6/midi.c @@ -56,7 +56,8 @@ static void line6_midi_transmit(struct snd_rawmidi_substream *substream) for (;;) { done = line6_midibuf_read(mb, chunk, - LINE6_FALLBACK_MAXPACKETSIZE); + LINE6_FALLBACK_MAXPACKETSIZE, + LINE6_MIDIBUF_READ_TX); if (done == 0) break; diff --git a/sound/usb/line6/midibuf.c b/sound/usb/line6/midibuf.c index 6a70463f82c4..e7f830f7526c 100644 --- a/sound/usb/line6/midibuf.c +++ b/sound/usb/line6/midibuf.c @@ -9,6 +9,7 @@ #include "midibuf.h" + static int midibuf_message_length(unsigned char code) { int message_length; @@ -20,12 +21,7 @@ static int midibuf_message_length(unsigned char code) message_length = length[(code >> 4) - 8]; } else { - /* - Note that according to the MIDI specification 0xf2 is - the "Song Position Pointer", but this is used by Line 6 - to send sysex messages to the host. - */ - static const int length[] = { -1, 2, -1, 2, -1, -1, 1, 1, 1, 1, + static const int length[] = { -1, 2, 2, 2, -1, -1, 1, 1, 1, -1, 1, 1, 1, -1, 1, 1 }; message_length = length[code & 0x0f]; @@ -125,7 +121,7 @@ int line6_midibuf_write(struct midi_buffer *this, unsigned char *data, } int line6_midibuf_read(struct midi_buffer *this, unsigned char *data, - int length) + int length, int read_type) { int bytes_used; int length1, length2; @@ -148,9 +144,22 @@ int line6_midibuf_read(struct midi_buffer *this, unsigned char *data, length1 = this->size - this->pos_read; - /* check MIDI command length */ command = this->buf[this->pos_read]; + /* + PODxt always has status byte lower nibble set to 0010, + when it means to send 0000, so we correct if here so + that control/program changes come on channel 1 and + sysex message status byte is correct + */ + if (read_type == LINE6_MIDIBUF_READ_RX) { + if (command == 0xb2 || command == 0xc2 || command == 0xf2) { + unsigned char fixed = command & 0xf0; + this->buf[this->pos_read] = fixed; + command = fixed; + } + } + /* check MIDI command length */ if (command & 0x80) { midi_length = midibuf_message_length(command); this->command_prev = command; diff --git a/sound/usb/line6/midibuf.h b/sound/usb/line6/midibuf.h index 124a8f9f7e96..542e8d836f87 100644 --- a/sound/usb/line6/midibuf.h +++ b/sound/usb/line6/midibuf.h @@ -8,6 +8,9 @@ #ifndef MIDIBUF_H #define MIDIBUF_H +#define LINE6_MIDIBUF_READ_TX 0 +#define LINE6_MIDIBUF_READ_RX 1 + struct midi_buffer { unsigned char *buf; int size; @@ -23,7 +26,7 @@ extern void line6_midibuf_destroy(struct midi_buffer *mb); extern int line6_midibuf_ignore(struct midi_buffer *mb, int length); extern int line6_midibuf_init(struct midi_buffer *mb, int size, int split); extern int line6_midibuf_read(struct midi_buffer *mb, unsigned char *data, - int length); + int length, int read_type); extern void line6_midibuf_reset(struct midi_buffer *mb); extern int line6_midibuf_write(struct midi_buffer *mb, unsigned char *data, int length); diff --git a/sound/usb/line6/pod.c b/sound/usb/line6/pod.c index 16e644330c4d..54be5ac919bf 100644 --- a/sound/usb/line6/pod.c +++ b/sound/usb/line6/pod.c @@ -159,8 +159,9 @@ static struct line6_pcm_properties pod_pcm_properties = { .bytes_per_channel = 3 /* SNDRV_PCM_FMTBIT_S24_3LE */ }; + static const char pod_version_header[] = { - 0xf2, 0x7e, 0x7f, 0x06, 0x02 + 0xf0, 0x7e, 0x7f, 0x06, 0x02 }; static char *pod_alloc_sysex_buffer(struct usb_line6_pod *pod, int code, From 66f359ad66d49f75d39ac729f9114dabf90b81bb Mon Sep 17 00:00:00 2001 From: Artem Egorkine Date: Sun, 25 Dec 2022 12:57:28 +0200 Subject: [PATCH 0672/4345] ALSA: line6: fix stack overflow in line6_midi_transmit commit b8800d324abb50160560c636bfafe2c81001b66c upstream. Correctly calculate available space including the size of the chunk buffer. This fixes a buffer overflow when multiple MIDI sysex messages are sent to a PODxt device. Signed-off-by: Artem Egorkine Cc: Link: https://lore.kernel.org/r/20221225105728.1153989-2-arteme@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/line6/midi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/usb/line6/midi.c b/sound/usb/line6/midi.c index d52355de2bbc..0838632c788e 100644 --- a/sound/usb/line6/midi.c +++ b/sound/usb/line6/midi.c @@ -44,7 +44,8 @@ static void line6_midi_transmit(struct snd_rawmidi_substream *substream) int req, done; for (;;) { - req = min(line6_midibuf_bytes_free(mb), line6->max_packet_size); + req = min3(line6_midibuf_bytes_free(mb), line6->max_packet_size, + LINE6_FALLBACK_MAXPACKETSIZE); done = snd_rawmidi_transmit_peek(substream, chunk, req); if (done == 0) From b591b2919d018ef91b4a9571edca94105bcad3df Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sat, 17 Dec 2022 22:28:40 +0100 Subject: [PATCH 0673/4345] pnode: terminate at peers of source commit 11933cf1d91d57da9e5c53822a540bbdc2656c16 upstream. The propagate_mnt() function handles mount propagation when creating mounts and propagates the source mount tree @source_mnt to all applicable nodes of the destination propagation mount tree headed by @dest_mnt. Unfortunately it contains a bug where it fails to terminate at peers of @source_mnt when looking up copies of the source mount that become masters for copies of the source mount tree mounted on top of slaves in the destination propagation tree causing a NULL dereference. Once the mechanics of the bug are understood it's easy to trigger. Because of unprivileged user namespaces it is available to unprivileged users. While fixing this bug we've gotten confused multiple times due to unclear terminology or missing concepts. So let's start this with some clarifications: * The terms "master" or "peer" denote a shared mount. A shared mount belongs to a peer group. * A peer group is a set of shared mounts that propagate to each other. They are identified by a peer group id. The peer group id is available in @shared_mnt->mnt_group_id. Shared mounts within the same peer group have the same peer group id. The peers in a peer group can be reached via @shared_mnt->mnt_share. * The terms "slave mount" or "dependent mount" denote a mount that receives propagation from a peer in a peer group. IOW, shared mounts may have slave mounts and slave mounts have shared mounts as their master. Slave mounts of a given peer in a peer group are listed on that peers slave list available at @shared_mnt->mnt_slave_list. * The term "master mount" denotes a mount in a peer group. IOW, it denotes a shared mount or a peer mount in a peer group. The term "master mount" - or "master" for short - is mostly used when talking in the context of slave mounts that receive propagation from a master mount. A master mount of a slave identifies the closest peer group a slave mount receives propagation from. The master mount of a slave can be identified via @slave_mount->mnt_master. Different slaves may point to different masters in the same peer group. * Multiple peers in a peer group can have non-empty ->mnt_slave_lists. Non-empty ->mnt_slave_lists of peers don't intersect. Consequently, to ensure all slave mounts of a peer group are visited the ->mnt_slave_lists of all peers in a peer group have to be walked. * Slave mounts point to a peer in the closest peer group they receive propagation from via @slave_mnt->mnt_master (see above). Together with these peers they form a propagation group (see below). The closest peer group can thus be identified through the peer group id @slave_mnt->mnt_master->mnt_group_id of the peer/master that a slave mount receives propagation from. * A shared-slave mount is a slave mount to a peer group pg1 while also a peer in another peer group pg2. IOW, a peer group may receive propagation from another peer group. If a peer group pg1 is a slave to another peer group pg2 then all peers in peer group pg1 point to the same peer in peer group pg2 via ->mnt_master. IOW, all peers in peer group pg1 appear on the same ->mnt_slave_list. IOW, they cannot be slaves to different peer groups. * A pure slave mount is a slave mount that is a slave to a peer group but is not a peer in another peer group. * A propagation group denotes the set of mounts consisting of a single peer group pg1 and all slave mounts and shared-slave mounts that point to a peer in that peer group via ->mnt_master. IOW, all slave mounts such that @slave_mnt->mnt_master->mnt_group_id is equal to @shared_mnt->mnt_group_id. The concept of a propagation group makes it easier to talk about a single propagation level in a propagation tree. For example, in propagate_mnt() the immediate peers of @dest_mnt and all slaves of @dest_mnt's peer group form a propagation group propg1. So a shared-slave mount that is a slave in propg1 and that is a peer in another peer group pg2 forms another propagation group propg2 together with all slaves that point to that shared-slave mount in their ->mnt_master. * A propagation tree refers to all mounts that receive propagation starting from a specific shared mount. For example, for propagate_mnt() @dest_mnt is the start of a propagation tree. The propagation tree ecompasses all mounts that receive propagation from @dest_mnt's peer group down to the leafs. With that out of the way let's get to the actual algorithm. We know that @dest_mnt is guaranteed to be a pure shared mount or a shared-slave mount. This is guaranteed by a check in attach_recursive_mnt(). So propagate_mnt() will first propagate the source mount tree to all peers in @dest_mnt's peer group: for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) { ret = propagate_one(n); if (ret) goto out; } Notice, that the peer propagation loop of propagate_mnt() doesn't propagate @dest_mnt itself. @dest_mnt is mounted directly in attach_recursive_mnt() after we propagated to the destination propagation tree. The mount that will be mounted on top of @dest_mnt is @source_mnt. This copy was created earlier even before we entered attach_recursive_mnt() and doesn't concern us a lot here. It's just important to notice that when propagate_mnt() is called @source_mnt will not yet have been mounted on top of @dest_mnt. Thus, @source_mnt->mnt_parent will either still point to @source_mnt or - in the case @source_mnt is moved and thus already attached - still to its former parent. For each peer @m in @dest_mnt's peer group propagate_one() will create a new copy of the source mount tree and mount that copy @child on @m such that @child->mnt_parent points to @m after propagate_one() returns. propagate_one() will stash the last destination propagation node @m in @last_dest and the last copy it created for the source mount tree in @last_source. Hence, if we call into propagate_one() again for the next destination propagation node @m, @last_dest will point to the previous destination propagation node and @last_source will point to the previous copy of the source mount tree and mounted on @last_dest. Each new copy of the source mount tree is created from the previous copy of the source mount tree. This will become important later. The peer loop in propagate_mnt() is straightforward. We iterate through the peers copying and updating @last_source and @last_dest as we go through them and mount each copy of the source mount tree @child on a peer @m in @dest_mnt's peer group. After propagate_mnt() handled the peers in @dest_mnt's peer group propagate_mnt() will propagate the source mount tree down the propagation tree that @dest_mnt's peer group propagates to: for (m = next_group(dest_mnt, dest_mnt); m; m = next_group(m, dest_mnt)) { /* everything in that slave group */ n = m; do { ret = propagate_one(n); if (ret) goto out; n = next_peer(n); } while (n != m); } The next_group() helper will recursively walk the destination propagation tree, descending into each propagation group of the propagation tree. The important part is that it takes care to propagate the source mount tree to all peers in the peer group of a propagation group before it propagates to the slaves to those peers in the propagation group. IOW, it creates and mounts copies of the source mount tree that become masters before it creates and mounts copies of the source mount tree that become slaves to these masters. It is important to remember that propagating the source mount tree to each mount @m in the destination propagation tree simply means that we create and mount new copies @child of the source mount tree on @m such that @child->mnt_parent points to @m. Since we know that each node @m in the destination propagation tree headed by @dest_mnt's peer group will be overmounted with a copy of the source mount tree and since we know that the propagation properties of each copy of the source mount tree we create and mount at @m will mostly mirror the propagation properties of @m. We can use that information to create and mount the copies of the source mount tree that become masters before their slaves. The easy case is always when @m and @last_dest are peers in a peer group of a given propagation group. In that case we know that we can simply copy @last_source without having to figure out what the master for the new copy @child of the source mount tree needs to be as we've done that in a previous call to propagate_one(). The hard case is when we're dealing with a slave mount or a shared-slave mount @m in a destination propagation group that we need to create and mount a copy of the source mount tree on. For each propagation group in the destination propagation tree we propagate the source mount tree to we want to make sure that the copies @child of the source mount tree we create and mount on slaves @m pick an ealier copy of the source mount tree that we mounted on a master @m of the destination propagation group as their master. This is a mouthful but as far as we can tell that's the core of it all. But, if we keep track of the masters in the destination propagation tree @m we can use the information to find the correct master for each copy of the source mount tree we create and mount at the slaves in the destination propagation tree @m. Let's walk through the base case as that's still fairly easy to grasp. If we're dealing with the first slave in the propagation group that @dest_mnt is in then we don't yet have marked any masters in the destination propagation tree. We know the master for the first slave to @dest_mnt's peer group is simple @dest_mnt. So we expect this algorithm to yield a copy of the source mount tree that was mounted on a peer in @dest_mnt's peer group as the master for the copy of the source mount tree we want to mount at the first slave @m: for (n = m; ; n = p) { p = n->mnt_master; if (p == dest_master || IS_MNT_MARKED(p)) break; } For the first slave we walk the destination propagation tree all the way up to a peer in @dest_mnt's peer group. IOW, the propagation hierarchy can be walked by walking up the @mnt->mnt_master hierarchy of the destination propagation tree @m. We will ultimately find a peer in @dest_mnt's peer group and thus ultimately @dest_mnt->mnt_master. Btw, here the assumption we listed at the beginning becomes important. Namely, that peers in a peer group pg1 that are slaves in another peer group pg2 appear on the same ->mnt_slave_list. IOW, all slaves who are peers in peer group pg1 point to the same peer in peer group pg2 via their ->mnt_master. Otherwise the termination condition in the code above would be wrong and next_group() would be broken too. So the first iteration sets: n = m; p = n->mnt_master; such that @p now points to a peer or @dest_mnt itself. We walk up one more level since we don't have any marked mounts. So we end up with: n = dest_mnt; p = dest_mnt->mnt_master; If @dest_mnt's peer group is not slave to another peer group then @p is now NULL. If @dest_mnt's peer group is a slave to another peer group then @p now points to @dest_mnt->mnt_master points which is a master outside the propagation tree we're dealing with. Now we need to figure out the master for the copy of the source mount tree we're about to create and mount on the first slave of @dest_mnt's peer group: do { struct mount *parent = last_source->mnt_parent; if (last_source == first_source) break; done = parent->mnt_master == p; if (done && peers(n, parent)) break; last_source = last_source->mnt_master; } while (!done); We know that @last_source->mnt_parent points to @last_dest and @last_dest is the last peer in @dest_mnt's peer group we propagated to in the peer loop in propagate_mnt(). Consequently, @last_source is the last copy we created and mount on that last peer in @dest_mnt's peer group. So @last_source is the master we want to pick. We know that @last_source->mnt_parent->mnt_master points to @last_dest->mnt_master. We also know that @last_dest->mnt_master is either NULL or points to a master outside of the destination propagation tree and so does @p. Hence: done = parent->mnt_master == p; is trivially true in the base condition. We also know that for the first slave mount of @dest_mnt's peer group that @last_dest either points @dest_mnt itself because it was initialized to: last_dest = dest_mnt; at the beginning of propagate_mnt() or it will point to a peer of @dest_mnt in its peer group. In both cases it is guaranteed that on the first iteration @n and @parent are peers (Please note the check for peers here as that's important.): if (done && peers(n, parent)) break; So, as we expected, we select @last_source, which referes to the last copy of the source mount tree we mounted on the last peer in @dest_mnt's peer group, as the master of the first slave in @dest_mnt's peer group. The rest is taken care of by clone_mnt(last_source, ...). We'll skip over that part otherwise this becomes a blogpost. At the end of propagate_mnt() we now mark @m->mnt_master as the first master in the destination propagation tree that is distinct from @dest_mnt->mnt_master. IOW, we mark @dest_mnt itself as a master. By marking @dest_mnt or one of it's peers we are able to easily find it again when we later lookup masters for other copies of the source mount tree we mount copies of the source mount tree on slaves @m to @dest_mnt's peer group. This, in turn allows us to find the master we selected for the copies of the source mount tree we mounted on master in the destination propagation tree again. The important part is to realize that the code makes use of the fact that the last copy of the source mount tree stashed in @last_source was mounted on top of the previous destination propagation node @last_dest. What this means is that @last_source allows us to walk the destination propagation hierarchy the same way each destination propagation node @m does. If we take @last_source, which is the copy of @source_mnt we have mounted on @last_dest in the previous iteration of propagate_one(), then we know @last_source->mnt_parent points to @last_dest but we also know that as we walk through the destination propagation tree that @last_source->mnt_master will point to an earlier copy of the source mount tree we mounted one an earlier destination propagation node @m. IOW, @last_source->mnt_parent will be our hook into the destination propagation tree and each consecutive @last_source->mnt_master will lead us to an earlier propagation node @m via @last_source->mnt_master->mnt_parent. Hence, by walking up @last_source->mnt_master, each of which is mounted on a node that is a master @m in the destination propagation tree we can also walk up the destination propagation hierarchy. So, for each new destination propagation node @m we use the previous copy of @last_source and the fact it's mounted on the previous propagation node @last_dest via @last_source->mnt_master->mnt_parent to determine what the master of the new copy of @last_source needs to be. The goal is to find the _closest_ master that the new copy of the source mount tree we are about to create and mount on a slave @m in the destination propagation tree needs to pick. IOW, we want to find a suitable master in the propagation group. As the propagation structure of the source mount propagation tree we create mirrors the propagation structure of the destination propagation tree we can find @m's closest master - i.e., a marked master - which is a peer in the closest peer group that @m receives propagation from. We store that closest master of @m in @p as before and record the slave to that master in @n We then search for this master @p via @last_source by walking up the master hierarchy starting from the last copy of the source mount tree stored in @last_source that we created and mounted on the previous destination propagation node @m. We will try to find the master by walking @last_source->mnt_master and by comparing @last_source->mnt_master->mnt_parent->mnt_master to @p. If we find @p then we can figure out what earlier copy of the source mount tree needs to be the master for the new copy of the source mount tree we're about to create and mount at the current destination propagation node @m. If @last_source->mnt_master->mnt_parent and @n are peers then we know that the closest master they receive propagation from is @last_source->mnt_master->mnt_parent->mnt_master. If not then the closest immediate peer group that they receive propagation from must be one level higher up. This builds on the earlier clarification at the beginning that all peers in a peer group which are slaves of other peer groups all point to the same ->mnt_master, i.e., appear on the same ->mnt_slave_list, of the closest peer group that they receive propagation from. However, terminating the walk has corner cases. If the closest marked master for a given destination node @m cannot be found by walking up the master hierarchy via @last_source->mnt_master then we need to terminate the walk when we encounter @source_mnt again. This isn't an arbitrary termination. It simply means that the new copy of the source mount tree we're about to create has a copy of the source mount tree we created and mounted on a peer in @dest_mnt's peer group as its master. IOW, @source_mnt is the peer in the closest peer group that the new copy of the source mount tree receives propagation from. We absolutely have to stop @source_mnt because @last_source->mnt_master either points outside the propagation hierarchy we're dealing with or it is NULL because @source_mnt isn't a shared-slave. So continuing the walk past @source_mnt would cause a NULL dereference via @last_source->mnt_master->mnt_parent. And so we have to stop the walk when we encounter @source_mnt again. One scenario where this can happen is when we first handled a series of slaves of @dest_mnt's peer group and then encounter peers in a new peer group that is a slave to @dest_mnt's peer group. We handle them and then we encounter another slave mount to @dest_mnt that is a pure slave to @dest_mnt's peer group. That pure slave will have a peer in @dest_mnt's peer group as its master. Consequently, the new copy of the source mount tree will need to have @source_mnt as it's master. So we walk the propagation hierarchy all the way up to @source_mnt based on @last_source->mnt_master. So terminate on @source_mnt, easy peasy. Except, that the check misses something that the rest of the algorithm already handles. If @dest_mnt has peers in it's peer group the peer loop in propagate_mnt(): for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) { ret = propagate_one(n); if (ret) goto out; } will consecutively update @last_source with each previous copy of the source mount tree we created and mounted at the previous peer in @dest_mnt's peer group. So after that loop terminates @last_source will point to whatever copy of the source mount tree was created and mounted on the last peer in @dest_mnt's peer group. Furthermore, if there is even a single additional peer in @dest_mnt's peer group then @last_source will __not__ point to @source_mnt anymore. Because, as we mentioned above, @dest_mnt isn't even handled in this loop but directly in attach_recursive_mnt(). So it can't even accidently come last in that peer loop. So the first time we handle a slave mount @m of @dest_mnt's peer group the copy of the source mount tree we create will make the __last copy of the source mount tree we created and mounted on the last peer in @dest_mnt's peer group the master of the new copy of the source mount tree we create and mount on the first slave of @dest_mnt's peer group__. But this means that the termination condition that checks for @source_mnt is wrong. The @source_mnt cannot be found anymore by propagate_one(). Instead it will find the last copy of the source mount tree we created and mounted for the last peer of @dest_mnt's peer group again. And that is a peer of @source_mnt not @source_mnt itself. IOW, we fail to terminate the loop correctly and ultimately dereference @last_source->mnt_master->mnt_parent. When @source_mnt's peer group isn't slave to another peer group then @last_source->mnt_master is NULL causing the splat below. For example, assume @dest_mnt is a pure shared mount and has three peers in its peer group: =================================================================================== mount-id mount-parent-id peer-group-id =================================================================================== (@dest_mnt) mnt_master[216] 309 297 shared:216 \ (@source_mnt) mnt_master[218]: 609 609 shared:218 (1) mnt_master[216]: 607 605 shared:216 \ (P1) mnt_master[218]: 624 607 shared:218 (2) mnt_master[216]: 576 574 shared:216 \ (P2) mnt_master[218]: 625 576 shared:218 (3) mnt_master[216]: 545 543 shared:216 \ (P3) mnt_master[218]: 626 545 shared:218 After this sequence has been processed @last_source will point to (P3), the copy generated for the third peer in @dest_mnt's peer group we handled. So the copy of the source mount tree (P4) we create and mount on the first slave of @dest_mnt's peer group: =================================================================================== mount-id mount-parent-id peer-group-id =================================================================================== mnt_master[216] 309 297 shared:216 / / (S0) mnt_slave 483 481 master:216 \ \ (P3) mnt_master[218] 626 545 shared:218 \ / \/ (P4) mnt_slave 627 483 master:218 will pick the last copy of the source mount tree (P3) as master, not (S0). When walking the propagation hierarchy via @last_source's master hierarchy we encounter (P3) but not (S0), i.e., @source_mnt. We can fix this in multiple ways: (1) By setting @last_source to @source_mnt after we processed the peers in @dest_mnt's peer group right after the peer loop in propagate_mnt(). (2) By changing the termination condition that relies on finding exactly @source_mnt to finding a peer of @source_mnt. (3) By only moving @last_source when we actually venture into a new peer group or some clever variant thereof. The first two options are minimally invasive and what we want as a fix. The third option is more intrusive but something we'd like to explore in the near future. This passes all LTP tests and specifically the mount propagation testsuite part of it. It also holds up against all known reproducers of this issues. Final words. First, this is a clever but __worringly__ underdocumented algorithm. There isn't a single detailed comment to be found in next_group(), propagate_one() or anywhere else in that file for that matter. This has been a giant pain to understand and work through and a bug like this is insanely difficult to fix without a detailed understanding of what's happening. Let's not talk about the amount of time that was sunk into fixing this. Second, all the cool kids with access to unshare --mount --user --map-root --propagation=unchanged are going to have a lot of fun. IOW, triggerable by unprivileged users while namespace_lock() lock is held. [ 115.848393] BUG: kernel NULL pointer dereference, address: 0000000000000010 [ 115.848967] #PF: supervisor read access in kernel mode [ 115.849386] #PF: error_code(0x0000) - not-present page [ 115.849803] PGD 0 P4D 0 [ 115.850012] Oops: 0000 [#1] PREEMPT SMP PTI [ 115.850354] CPU: 0 PID: 15591 Comm: mount Not tainted 6.1.0-rc7 #3 [ 115.850851] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 115.851510] RIP: 0010:propagate_one.part.0+0x7f/0x1a0 [ 115.851924] Code: 75 eb 4c 8b 05 c2 25 37 02 4c 89 ca 48 8b 4a 10 49 39 d0 74 1e 48 3b 81 e0 00 00 00 74 26 48 8b 92 e0 00 00 00 be 01 00 00 00 <48> 8b 4a 10 49 39 d0 75 e2 40 84 f6 74 38 4c 89 05 84 25 37 02 4d [ 115.853441] RSP: 0018:ffffb8d5443d7d50 EFLAGS: 00010282 [ 115.853865] RAX: ffff8e4d87c41c80 RBX: ffff8e4d88ded780 RCX: ffff8e4da4333a00 [ 115.854458] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8e4d88ded780 [ 115.855044] RBP: ffff8e4d88ded780 R08: ffff8e4da4338000 R09: ffff8e4da43388c0 [ 115.855693] R10: 0000000000000002 R11: ffffb8d540158000 R12: ffffb8d5443d7da8 [ 115.856304] R13: ffff8e4d88ded780 R14: 0000000000000000 R15: 0000000000000000 [ 115.856859] FS: 00007f92c90c9800(0000) GS:ffff8e4dfdc00000(0000) knlGS:0000000000000000 [ 115.857531] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 115.858006] CR2: 0000000000000010 CR3: 0000000022f4c002 CR4: 00000000000706f0 [ 115.858598] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 115.859393] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 115.860099] Call Trace: [ 115.860358] [ 115.860535] propagate_mnt+0x14d/0x190 [ 115.860848] attach_recursive_mnt+0x274/0x3e0 [ 115.861212] path_mount+0x8c8/0xa60 [ 115.861503] __x64_sys_mount+0xf6/0x140 [ 115.861819] do_syscall_64+0x5b/0x80 [ 115.862117] ? do_faccessat+0x123/0x250 [ 115.862435] ? syscall_exit_to_user_mode+0x17/0x40 [ 115.862826] ? do_syscall_64+0x67/0x80 [ 115.863133] ? syscall_exit_to_user_mode+0x17/0x40 [ 115.863527] ? do_syscall_64+0x67/0x80 [ 115.863835] ? do_syscall_64+0x67/0x80 [ 115.864144] ? do_syscall_64+0x67/0x80 [ 115.864452] ? exc_page_fault+0x70/0x170 [ 115.864775] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 115.865187] RIP: 0033:0x7f92c92b0ebe [ 115.865480] Code: 48 8b 0d 75 4f 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 42 4f 0c 00 f7 d8 64 89 01 48 [ 115.866984] RSP: 002b:00007fff000aa728 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 [ 115.867607] RAX: ffffffffffffffda RBX: 000055a77888d6b0 RCX: 00007f92c92b0ebe [ 115.868240] RDX: 000055a77888d8e0 RSI: 000055a77888e6e0 RDI: 000055a77888e620 [ 115.868823] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000001 [ 115.869403] R10: 0000000000001000 R11: 0000000000000246 R12: 000055a77888e620 [ 115.869994] R13: 000055a77888d8e0 R14: 00000000ffffffff R15: 00007f92c93e4076 [ 115.870581] [ 115.870763] Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set rfkill nf_tables nfnetlink qrtr snd_intel8x0 sunrpc snd_ac97_codec ac97_bus snd_pcm snd_timer intel_rapl_msr intel_rapl_common snd vboxguest intel_powerclamp video rapl joydev soundcore i2c_piix4 wmi fuse zram xfs vmwgfx crct10dif_pclmul crc32_pclmul crc32c_intel polyval_clmulni polyval_generic drm_ttm_helper ttm e1000 ghash_clmulni_intel serio_raw ata_generic pata_acpi scsi_dh_rdac scsi_dh_emc scsi_dh_alua dm_multipath [ 115.875288] CR2: 0000000000000010 [ 115.875641] ---[ end trace 0000000000000000 ]--- [ 115.876135] RIP: 0010:propagate_one.part.0+0x7f/0x1a0 [ 115.876551] Code: 75 eb 4c 8b 05 c2 25 37 02 4c 89 ca 48 8b 4a 10 49 39 d0 74 1e 48 3b 81 e0 00 00 00 74 26 48 8b 92 e0 00 00 00 be 01 00 00 00 <48> 8b 4a 10 49 39 d0 75 e2 40 84 f6 74 38 4c 89 05 84 25 37 02 4d [ 115.878086] RSP: 0018:ffffb8d5443d7d50 EFLAGS: 00010282 [ 115.878511] RAX: ffff8e4d87c41c80 RBX: ffff8e4d88ded780 RCX: ffff8e4da4333a00 [ 115.879128] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8e4d88ded780 [ 115.879715] RBP: ffff8e4d88ded780 R08: ffff8e4da4338000 R09: ffff8e4da43388c0 [ 115.880359] R10: 0000000000000002 R11: ffffb8d540158000 R12: ffffb8d5443d7da8 [ 115.880962] R13: ffff8e4d88ded780 R14: 0000000000000000 R15: 0000000000000000 [ 115.881548] FS: 00007f92c90c9800(0000) GS:ffff8e4dfdc00000(0000) knlGS:0000000000000000 [ 115.882234] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 115.882713] CR2: 0000000000000010 CR3: 0000000022f4c002 CR4: 00000000000706f0 [ 115.883314] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 115.883966] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Fixes: f2ebb3a921c1 ("smarter propagate_mnt()") Fixes: 5ec0811d3037 ("propogate_mnt: Handle the first propogated copy being a slave") Cc: Reported-by: Ditang Chen Signed-off-by: Seth Forshee (Digital Ocean) Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Greg Kroah-Hartman --- fs/pnode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/pnode.c b/fs/pnode.c index 1106137c747a..468e4e65a615 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -244,7 +244,7 @@ static int propagate_one(struct mount *m) } do { struct mount *parent = last_source->mnt_parent; - if (last_source == first_source) + if (peers(last_source, first_source)) break; done = parent->mnt_master == p; if (done && peers(n, parent)) From ae7793027766491c5f8635b12d15a5940d3b8698 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Fri, 4 Nov 2022 09:53:38 -0400 Subject: [PATCH 0674/4345] md: fix a crash in mempool_free commit 341097ee53573e06ab9fc675d96a052385b851fa upstream. There's a crash in mempool_free when running the lvm test shell/lvchange-rebuild-raid.sh. The reason for the crash is this: * super_written calls atomic_dec_and_test(&mddev->pending_writes) and wake_up(&mddev->sb_wait). Then it calls rdev_dec_pending(rdev, mddev) and bio_put(bio). * so, the process that waited on sb_wait and that is woken up is racing with bio_put(bio). * if the process wins the race, it calls bioset_exit before bio_put(bio) is executed. * bio_put(bio) attempts to free a bio into a destroyed bio set - causing a crash in mempool_free. We fix this bug by moving bio_put before atomic_dec_and_test. We also move rdev_dec_pending before atomic_dec_and_test as suggested by Neil Brown. The function md_end_flush has a similar bug - we must call bio_put before we decrement the number of in-progress bios. BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 11557f0067 P4D 11557f0067 PUD 0 Oops: 0002 [#1] PREEMPT SMP CPU: 0 PID: 73 Comm: kworker/0:1 Not tainted 6.1.0-rc3 #5 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 Workqueue: kdelayd flush_expired_bios [dm_delay] RIP: 0010:mempool_free+0x47/0x80 Code: 48 89 ef 5b 5d ff e0 f3 c3 48 89 f7 e8 32 45 3f 00 48 63 53 08 48 89 c6 3b 53 04 7d 2d 48 8b 43 10 8d 4a 01 48 89 df 89 4b 08 <48> 89 2c d0 e8 b0 45 3f 00 48 8d 7b 30 5b 5d 31 c9 ba 01 00 00 00 RSP: 0018:ffff88910036bda8 EFLAGS: 00010093 RAX: 0000000000000000 RBX: ffff8891037b65d8 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000202 RDI: ffff8891037b65d8 RBP: ffff8891447ba240 R08: 0000000000012908 R09: 00000000003d0900 R10: 0000000000000000 R11: 0000000000173544 R12: ffff889101a14000 R13: ffff8891562ac300 R14: ffff889102b41440 R15: ffffe8ffffa00d05 FS: 0000000000000000(0000) GS:ffff88942fa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000001102e99000 CR4: 00000000000006b0 Call Trace: clone_endio+0xf4/0x1c0 [dm_mod] clone_endio+0xf4/0x1c0 [dm_mod] __submit_bio+0x76/0x120 submit_bio_noacct_nocheck+0xb6/0x2a0 flush_expired_bios+0x28/0x2f [dm_delay] process_one_work+0x1b4/0x300 worker_thread+0x45/0x3e0 ? rescuer_thread+0x380/0x380 kthread+0xc2/0x100 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 Modules linked in: brd dm_delay dm_raid dm_mod af_packet uvesafb cfbfillrect cfbimgblt cn cfbcopyarea fb font fbdev tun autofs4 binfmt_misc configfs ipv6 virtio_rng virtio_balloon rng_core virtio_net pcspkr net_failover failover qemu_fw_cfg button mousedev raid10 raid456 libcrc32c async_raid6_recov async_memcpy async_pq raid6_pq async_xor xor async_tx raid1 raid0 md_mod sd_mod t10_pi crc64_rocksoft crc64 virtio_scsi scsi_mod evdev psmouse bsg scsi_common [last unloaded: brd] CR2: 0000000000000000 ---[ end trace 0000000000000000 ]--- Signed-off-by: Mikulas Patocka Cc: stable@vger.kernel.org Signed-off-by: Song Liu Signed-off-by: Greg Kroah-Hartman --- drivers/md/md.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 0043dec37a87..3038e7ecb7e1 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -555,13 +555,14 @@ static void md_end_flush(struct bio *bio) struct md_rdev *rdev = bio->bi_private; struct mddev *mddev = rdev->mddev; + bio_put(bio); + rdev_dec_pending(rdev, mddev); if (atomic_dec_and_test(&mddev->flush_pending)) { /* The pre-request flush has finished */ queue_work(md_wq, &mddev->flush_work); } - bio_put(bio); } static void md_submit_flush_data(struct work_struct *ws); @@ -966,10 +967,12 @@ static void super_written(struct bio *bio) } else clear_bit(LastDev, &rdev->flags); + bio_put(bio); + + rdev_dec_pending(rdev, mddev); + if (atomic_dec_and_test(&mddev->pending_writes)) wake_up(&mddev->sb_wait); - rdev_dec_pending(rdev, mddev); - bio_put(bio); } void md_super_write(struct mddev *mddev, struct md_rdev *rdev, From 882734bbc5873143b17292cd29504bda9142d565 Mon Sep 17 00:00:00 2001 From: NARIBAYASHI Akira Date: Wed, 26 Oct 2022 20:24:38 +0900 Subject: [PATCH 0675/4345] mm, compaction: fix fast_isolate_around() to stay within boundaries commit be21b32afe470c5ae98e27e49201158a47032942 upstream. Depending on the memory configuration, isolate_freepages_block() may scan pages out of the target range and causes panic. Panic can occur on systems with multiple zones in a single pageblock. The reason it is rare is that it only happens in special configurations. Depending on how many similar systems there are, it may be a good idea to fix this problem for older kernels as well. The problem is that pfn as argument of fast_isolate_around() could be out of the target range. Therefore we should consider the case where pfn < start_pfn, and also the case where end_pfn < pfn. This problem should have been addressd by the commit 6e2b7044c199 ("mm, compaction: make fast_isolate_freepages() stay within zone") but there was an oversight. Case1: pfn < start_pfn | node X's zone | node Y's zone +-----------------+------------------------------... pageblock ^ ^ ^ +-----------+-----------+-----------+-----------+... ^ ^ ^ ^ ^ end_pfn ^ start_pfn = cc->zone->zone_start_pfn pfn <---------> scanned range by "Scan After" Case2: end_pfn < pfn | node X's zone | node Y's zone +-----------------+------------------------------... pageblock ^ ^ ^ +-----------+-----------+-----------+-----------+... ^ ^ ^ ^ ^ pfn ^ end_pfn start_pfn <---------> scanned range by "Scan Before" It seems that there is no good reason to skip nr_isolated pages just after given pfn. So let perform simple scan from start to end instead of dividing the scan into "Before" and "After". Link: https://lkml.kernel.org/r/20221026112438.236336-1-a.naribayashi@fujitsu.com Fixes: 6e2b7044c199 ("mm, compaction: make fast_isolate_freepages() stay within zone"). Signed-off-by: NARIBAYASHI Akira Cc: David Rientjes Cc: Mel Gorman Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/compaction.c | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 8dfbe86bd74f..b58021666e1a 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1245,7 +1245,7 @@ move_freelist_tail(struct list_head *freelist, struct page *freepage) } static void -fast_isolate_around(struct compact_control *cc, unsigned long pfn, unsigned long nr_isolated) +fast_isolate_around(struct compact_control *cc, unsigned long pfn) { unsigned long start_pfn, end_pfn; struct page *page; @@ -1266,21 +1266,13 @@ fast_isolate_around(struct compact_control *cc, unsigned long pfn, unsigned long if (!page) return; - /* Scan before */ - if (start_pfn != pfn) { - isolate_freepages_block(cc, &start_pfn, pfn, &cc->freepages, 1, false); - if (cc->nr_freepages >= cc->nr_migratepages) - return; - } - - /* Scan after */ - start_pfn = pfn + nr_isolated; - if (start_pfn < end_pfn) - isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false); + isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false); /* Skip this pageblock in the future as it's full or nearly full */ if (cc->nr_freepages < cc->nr_migratepages) set_pageblock_skip(page); + + return; } /* Search orders in round-robin fashion */ @@ -1456,7 +1448,7 @@ fast_isolate_freepages(struct compact_control *cc) return cc->free_pfn; low_pfn = page_to_pfn(page); - fast_isolate_around(cc, low_pfn, nr_isolated); + fast_isolate_around(cc, low_pfn); return low_pfn; } From 252a720882807fb29c085ff286867c5c63167569 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Mon, 24 Oct 2022 19:30:12 +0200 Subject: [PATCH 0676/4345] f2fs: should put a page when checking the summary info commit c3db3c2fd9992c08f49aa93752d3c103c3a4f6aa upstream. The commit introduces another bug. Cc: stable@vger.kernel.org Fixes: c6ad7fd16657e ("f2fs: fix to do sanity check on summary info") Signed-off-by: Pavel Machek Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/gc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 89156568a4fb..ce6a2a247804 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1008,6 +1008,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, if (ofs_in_node >= max_addrs) { f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%u, nid:%u, max:%u", ofs_in_node, dni->ino, dni->nid, max_addrs); + f2fs_put_page(node_page, 1); return false; } From b51d5fed9f53e07ce9fc65efb4ff1abe021a4c16 Mon Sep 17 00:00:00 2001 From: Deren Wu Date: Sun, 4 Dec 2022 16:24:16 +0800 Subject: [PATCH 0677/4345] mmc: vub300: fix warning - do not call blocking ops when !TASK_RUNNING commit 4a44cd249604e29e7b90ae796d7692f5773dd348 upstream. vub300_enable_sdio_irq() works with mutex and need TASK_RUNNING here. Ensure that we mark current as TASK_RUNNING for sleepable context. [ 77.554641] do not call blocking ops when !TASK_RUNNING; state=1 set at [] sdio_irq_thread+0x17d/0x5b0 [ 77.554652] WARNING: CPU: 2 PID: 1983 at kernel/sched/core.c:9813 __might_sleep+0x116/0x160 [ 77.554905] CPU: 2 PID: 1983 Comm: ksdioirqd/mmc1 Tainted: G OE 6.1.0-rc5 #1 [ 77.554910] Hardware name: Intel(R) Client Systems NUC8i7BEH/NUC8BEB, BIOS BECFL357.86A.0081.2020.0504.1834 05/04/2020 [ 77.554912] RIP: 0010:__might_sleep+0x116/0x160 [ 77.554920] RSP: 0018:ffff888107b7fdb8 EFLAGS: 00010282 [ 77.554923] RAX: 0000000000000000 RBX: ffff888118c1b740 RCX: 0000000000000000 [ 77.554926] RDX: 0000000000000001 RSI: 0000000000000004 RDI: ffffed1020f6ffa9 [ 77.554928] RBP: ffff888107b7fde0 R08: 0000000000000001 R09: ffffed1043ea60ba [ 77.554930] R10: ffff88821f5305cb R11: ffffed1043ea60b9 R12: ffffffff93aa3a60 [ 77.554932] R13: 000000000000011b R14: 7fffffffffffffff R15: ffffffffc0558660 [ 77.554934] FS: 0000000000000000(0000) GS:ffff88821f500000(0000) knlGS:0000000000000000 [ 77.554937] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 77.554939] CR2: 00007f8a44010d68 CR3: 000000024421a003 CR4: 00000000003706e0 [ 77.554942] Call Trace: [ 77.554944] [ 77.554952] mutex_lock+0x78/0xf0 [ 77.554973] vub300_enable_sdio_irq+0x103/0x3c0 [vub300] [ 77.554981] sdio_irq_thread+0x25c/0x5b0 [ 77.555006] kthread+0x2b8/0x370 [ 77.555017] ret_from_fork+0x1f/0x30 [ 77.555023] [ 77.555025] ---[ end trace 0000000000000000 ]--- Fixes: 88095e7b473a ("mmc: Add new VUB300 USB-to-SD/SDIO/MMC driver") Signed-off-by: Deren Wu Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87dc45b122d26d63c80532976813c9365d7160b3.1670140888.git.deren.wu@mediatek.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/vub300.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index ab36ec479747..72f65f32abbc 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -2049,6 +2049,7 @@ static void vub300_enable_sdio_irq(struct mmc_host *mmc, int enable) return; kref_get(&vub300->kref); if (enable) { + set_current_state(TASK_RUNNING); mutex_lock(&vub300->irq_mutex); if (vub300->irqs_queued) { vub300->irqs_queued -= 1; @@ -2064,6 +2065,7 @@ static void vub300_enable_sdio_irq(struct mmc_host *mmc, int enable) vub300_queue_poll_work(vub300, 0); } mutex_unlock(&vub300->irq_mutex); + set_current_state(TASK_INTERRUPTIBLE); } else { vub300->irq_enabled = 0; } From 8ddc48068ac85740d3d5f9f3b0b323e733a35b33 Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Thu, 17 Nov 2022 19:23:40 +0800 Subject: [PATCH 0678/4345] tpm: acpi: Call acpi_put_table() to fix memory leak commit 8740a12ca2e2959531ad253bac99ada338b33d80 upstream. The start and length of the event log area are obtained from TPM2 or TCPA table, so we call acpi_get_table() to get the ACPI information, but the acpi_get_table() should be coupled with acpi_put_table() to release the ACPI memory, add the acpi_put_table() properly to fix the memory leak. While we are at it, remove the redundant empty line at the end of the tpm_read_log_acpi(). Fixes: 0bfb23746052 ("tpm: Move eventlog files to a subdirectory") Fixes: 85467f63a05c ("tpm: Add support for event log pointer found in TPM2 ACPI table") Cc: stable@vger.kernel.org Signed-off-by: Hanjun Guo Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/eventlog/acpi.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c index 1b18ce5ebab1..0913d3eb8d51 100644 --- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -90,16 +90,21 @@ int tpm_read_log_acpi(struct tpm_chip *chip) return -ENODEV; if (tbl->header.length < - sizeof(*tbl) + sizeof(struct acpi_tpm2_phy)) + sizeof(*tbl) + sizeof(struct acpi_tpm2_phy)) { + acpi_put_table((struct acpi_table_header *)tbl); return -ENODEV; + } tpm2_phy = (void *)tbl + sizeof(*tbl); len = tpm2_phy->log_area_minimum_length; start = tpm2_phy->log_area_start_address; - if (!start || !len) + if (!start || !len) { + acpi_put_table((struct acpi_table_header *)tbl); return -ENODEV; + } + acpi_put_table((struct acpi_table_header *)tbl); format = EFI_TCG2_EVENT_LOG_FORMAT_TCG_2; } else { /* Find TCPA entry in RSDT (ACPI_LOGICAL_ADDRESSING) */ @@ -120,8 +125,10 @@ int tpm_read_log_acpi(struct tpm_chip *chip) break; } + acpi_put_table((struct acpi_table_header *)buff); format = EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2; } + if (!len) { dev_warn(&chip->dev, "%s: TCPA log area empty\n", __func__); return -EIO; @@ -156,5 +163,4 @@ err: kfree(log->bios_event_log); log->bios_event_log = NULL; return ret; - } From 0bd9b4be721c776f77adcaf34105dfca3007ddb9 Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Thu, 17 Nov 2022 19:23:41 +0800 Subject: [PATCH 0679/4345] tpm: tpm_crb: Add the missed acpi_put_table() to fix memory leak commit 37e90c374dd11cf4919c51e847c6d6ced0abc555 upstream. In crb_acpi_add(), we get the TPM2 table to retrieve information like start method, and then assign them to the priv data, so the TPM2 table is not used after the init, should be freed, call acpi_put_table() to fix the memory leak. Fixes: 30fc8d138e91 ("tpm: TPM 2.0 CRB Interface") Cc: stable@vger.kernel.org Signed-off-by: Hanjun Guo Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm_crb.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 35c5227f3a88..5fe52a6839b5 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -676,12 +676,16 @@ static int crb_acpi_add(struct acpi_device *device) /* Should the FIFO driver handle this? */ sm = buf->start_method; - if (sm == ACPI_TPM2_MEMORY_MAPPED) - return -ENODEV; + if (sm == ACPI_TPM2_MEMORY_MAPPED) { + rc = -ENODEV; + goto out; + } priv = devm_kzalloc(dev, sizeof(struct crb_priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + if (!priv) { + rc = -ENOMEM; + goto out; + } if (sm == ACPI_TPM2_COMMAND_BUFFER_WITH_ARM_SMC) { if (buf->header.length < (sizeof(*buf) + sizeof(*crb_smc))) { @@ -689,7 +693,8 @@ static int crb_acpi_add(struct acpi_device *device) FW_BUG "TPM2 ACPI table has wrong size %u for start method type %d\n", buf->header.length, ACPI_TPM2_COMMAND_BUFFER_WITH_ARM_SMC); - return -EINVAL; + rc = -EINVAL; + goto out; } crb_smc = ACPI_ADD_PTR(struct tpm2_crb_smc, buf, sizeof(*buf)); priv->smc_func_id = crb_smc->smc_func_id; @@ -700,17 +705,23 @@ static int crb_acpi_add(struct acpi_device *device) rc = crb_map_io(device, priv, buf); if (rc) - return rc; + goto out; chip = tpmm_chip_alloc(dev, &tpm_crb); - if (IS_ERR(chip)) - return PTR_ERR(chip); + if (IS_ERR(chip)) { + rc = PTR_ERR(chip); + goto out; + } dev_set_drvdata(&chip->dev, priv); chip->acpi_dev_handle = device->handle; chip->flags = TPM_CHIP_FLAG_TPM2; - return tpm_chip_register(chip); + rc = tpm_chip_register(chip); + +out: + acpi_put_table((struct acpi_table_header *)buf); + return rc; } static int crb_acpi_remove(struct acpi_device *device) From 3b6c822238da9ee8984803355601bcc603d49cb5 Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Thu, 17 Nov 2022 19:23:42 +0800 Subject: [PATCH 0680/4345] tpm: tpm_tis: Add the missed acpi_put_table() to fix memory leak commit db9622f762104459ff87ecdf885cc42c18053fd9 upstream. In check_acpi_tpm2(), we get the TPM2 table just to make sure the table is there, not used after the init, so the acpi_put_table() should be added to release the ACPI memory. Fixes: 4cb586a188d4 ("tpm_tis: Consolidate the platform and acpi probe flow") Cc: stable@vger.kernel.org Signed-off-by: Hanjun Guo Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm_tis.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 4ed6e660273a..14fad16d371f 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -125,6 +125,7 @@ static int check_acpi_tpm2(struct device *dev) const struct acpi_device_id *aid = acpi_match_device(tpm_acpi_tbl, dev); struct acpi_table_tpm2 *tbl; acpi_status st; + int ret = 0; if (!aid || aid->driver_data != DEVICE_IS_TPM2) return 0; @@ -132,8 +133,7 @@ static int check_acpi_tpm2(struct device *dev) /* If the ACPI TPM2 signature is matched then a global ACPI_SIG_TPM2 * table is mandatory */ - st = - acpi_get_table(ACPI_SIG_TPM2, 1, (struct acpi_table_header **)&tbl); + st = acpi_get_table(ACPI_SIG_TPM2, 1, (struct acpi_table_header **)&tbl); if (ACPI_FAILURE(st) || tbl->header.length < sizeof(*tbl)) { dev_err(dev, FW_BUG "failed to get TPM2 ACPI table\n"); return -EINVAL; @@ -141,9 +141,10 @@ static int check_acpi_tpm2(struct device *dev) /* The tpm2_crb driver handles this device */ if (tbl->start_method != ACPI_TPM2_MEMORY_MAPPED) - return -ENODEV; + ret = -ENODEV; - return 0; + acpi_put_table((struct acpi_table_header *)tbl); + return ret; } #else static int check_acpi_tpm2(struct device *dev) From 2cd6026e257362f030c8be57abaf7fc0049df60a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 26 Nov 2022 15:55:18 -0500 Subject: [PATCH 0681/4345] SUNRPC: Don't leak netobj memory when gss_read_proxy_verf() fails commit da522b5fe1a5f8b7c20a0023e87b52a150e53bf5 upstream. Fixes: 030d794bf498 ("SUNRPC: Use gssproxy upcall for server RPCGSS authentication.") Signed-off-by: Chuck Lever Cc: Reviewed-by: Jeff Layton Signed-off-by: Greg Kroah-Hartman --- net/sunrpc/auth_gss/svcauth_gss.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index f5111d62972d..406ff7f8b156 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1156,18 +1156,23 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, return res; inlen = svc_getnl(argv); - if (inlen > (argv->iov_len + rqstp->rq_arg.page_len)) + if (inlen > (argv->iov_len + rqstp->rq_arg.page_len)) { + kfree(in_handle->data); return SVC_DENIED; + } pages = DIV_ROUND_UP(inlen, PAGE_SIZE); in_token->pages = kcalloc(pages, sizeof(struct page *), GFP_KERNEL); - if (!in_token->pages) + if (!in_token->pages) { + kfree(in_handle->data); return SVC_DENIED; + } in_token->page_base = 0; in_token->page_len = inlen; for (i = 0; i < pages; i++) { in_token->pages[i] = alloc_page(GFP_KERNEL); if (!in_token->pages[i]) { + kfree(in_handle->data); gss_free_in_token_pages(in_token); return SVC_DENIED; } From 7b3631a2e17dc7283abd684df9cfd258d909a8b3 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 12 Sep 2022 11:45:40 +0200 Subject: [PATCH 0682/4345] kcsan: Instrument memcpy/memset/memmove with newer Clang commit 7c201739beef1a586d806463f1465429cdce34c5 upstream. With Clang version 16+, -fsanitize=thread will turn memcpy/memset/memmove calls in instrumented functions into __tsan_memcpy/__tsan_memset/__tsan_memmove calls respectively. Add these functions to the core KCSAN runtime, so that we (a) catch data races with mem* functions, and (b) won't run into linker errors with such newer compilers. Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney [ elver@google.com: adjust check_access() call for v5.15 and earlier. ] Signed-off-by: Greg Kroah-Hartman --- kernel/kcsan/core.c | 50 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index 23e7acb5c667..762df6108c58 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -9,10 +9,12 @@ #include #include #include +#include #include #include #include #include +#include #include #include "atomic.h" @@ -1045,3 +1047,51 @@ EXPORT_SYMBOL(__tsan_atomic_thread_fence); void __tsan_atomic_signal_fence(int memorder); void __tsan_atomic_signal_fence(int memorder) { } EXPORT_SYMBOL(__tsan_atomic_signal_fence); + +#ifdef __HAVE_ARCH_MEMSET +void *__tsan_memset(void *s, int c, size_t count); +noinline void *__tsan_memset(void *s, int c, size_t count) +{ + /* + * Instead of not setting up watchpoints where accessed size is greater + * than MAX_ENCODABLE_SIZE, truncate checked size to MAX_ENCODABLE_SIZE. + */ + size_t check_len = min_t(size_t, count, MAX_ENCODABLE_SIZE); + + check_access(s, check_len, KCSAN_ACCESS_WRITE); + return memset(s, c, count); +} +#else +void *__tsan_memset(void *s, int c, size_t count) __alias(memset); +#endif +EXPORT_SYMBOL(__tsan_memset); + +#ifdef __HAVE_ARCH_MEMMOVE +void *__tsan_memmove(void *dst, const void *src, size_t len); +noinline void *__tsan_memmove(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE); + check_access(src, check_len, 0); + return memmove(dst, src, len); +} +#else +void *__tsan_memmove(void *dst, const void *src, size_t len) __alias(memmove); +#endif +EXPORT_SYMBOL(__tsan_memmove); + +#ifdef __HAVE_ARCH_MEMCPY +void *__tsan_memcpy(void *dst, const void *src, size_t len); +noinline void *__tsan_memcpy(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE); + check_access(src, check_len, 0); + return memcpy(dst, src, len); +} +#else +void *__tsan_memcpy(void *dst, const void *src, size_t len) __alias(memcpy); +#endif +EXPORT_SYMBOL(__tsan_memcpy); From 185c141946e0fd1921638593181311b39b51255f Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 24 Dec 2021 10:10:32 +0800 Subject: [PATCH 0683/4345] ASoC: Intel/SOF: use set_stream() instead of set_tdm_slots() for HDAudio commit 636110411ca726f19ef8e87b0be51bb9a4cdef06 upstream. Overloading the tx_mask with a linear value is asking for trouble and only works because the codec_dai hw_params() is called before the cpu_dai hw_params(). Move to the more generic set_stream() API to pass the hdac_stream information. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Ranjani Sridharan Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20211224021034.26635-6-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown Cc: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/soc/codecs/hdac_hda.c | 22 +++++++++++----------- sound/soc/intel/skylake/skl-pcm.c | 7 ++----- sound/soc/sof/intel/hda-dai.c | 7 ++----- 3 files changed, 15 insertions(+), 21 deletions(-) diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c index 390dd6c7f6a5..de5955db0a5f 100644 --- a/sound/soc/codecs/hdac_hda.c +++ b/sound/soc/codecs/hdac_hda.c @@ -46,9 +46,8 @@ static int hdac_hda_dai_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai); static int hdac_hda_dai_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai); -static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai, - unsigned int tx_mask, unsigned int rx_mask, - int slots, int slot_width); +static int hdac_hda_dai_set_stream(struct snd_soc_dai *dai, void *stream, + int direction); static struct hda_pcm *snd_soc_find_pcm_from_dai(struct hdac_hda_priv *hda_pvt, struct snd_soc_dai *dai); @@ -58,7 +57,7 @@ static const struct snd_soc_dai_ops hdac_hda_dai_ops = { .prepare = hdac_hda_dai_prepare, .hw_params = hdac_hda_dai_hw_params, .hw_free = hdac_hda_dai_hw_free, - .set_tdm_slot = hdac_hda_dai_set_tdm_slot, + .set_stream = hdac_hda_dai_set_stream, }; static struct snd_soc_dai_driver hdac_hda_dais[] = { @@ -180,21 +179,22 @@ static struct snd_soc_dai_driver hdac_hda_dais[] = { }; -static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai, - unsigned int tx_mask, unsigned int rx_mask, - int slots, int slot_width) +static int hdac_hda_dai_set_stream(struct snd_soc_dai *dai, + void *stream, int direction) { struct snd_soc_component *component = dai->component; struct hdac_hda_priv *hda_pvt; struct hdac_hda_pcm *pcm; + struct hdac_stream *hstream; + + if (!stream) + return -EINVAL; hda_pvt = snd_soc_component_get_drvdata(component); pcm = &hda_pvt->pcm[dai->id]; + hstream = (struct hdac_stream *)stream; - if (tx_mask) - pcm->stream_tag[SNDRV_PCM_STREAM_PLAYBACK] = tx_mask; - else - pcm->stream_tag[SNDRV_PCM_STREAM_CAPTURE] = rx_mask; + pcm->stream_tag[direction] = hstream->stream_tag; return 0; } diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c index b1897a057397..b531d9dfc2d6 100644 --- a/sound/soc/intel/skylake/skl-pcm.c +++ b/sound/soc/intel/skylake/skl-pcm.c @@ -563,11 +563,8 @@ static int skl_link_hw_params(struct snd_pcm_substream *substream, stream_tag = hdac_stream(link_dev)->stream_tag; - /* set the stream tag in the codec dai dma params */ - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - snd_soc_dai_set_tdm_slot(codec_dai, stream_tag, 0, 0, 0); - else - snd_soc_dai_set_tdm_slot(codec_dai, 0, stream_tag, 0, 0); + /* set the hdac_stream in the codec dai */ + snd_soc_dai_set_stream(codec_dai, hdac_stream(link_dev), substream->stream); p_params.s_fmt = snd_pcm_format_width(params_format(params)); p_params.ch = params_channels(params); diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index ef316311e959..de80f1b3d7f2 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -236,11 +236,8 @@ static int hda_link_hw_params(struct snd_pcm_substream *substream, if (!link) return -EINVAL; - /* set the stream tag in the codec dai dma params */ - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - snd_soc_dai_set_tdm_slot(codec_dai, stream_tag, 0, 0, 0); - else - snd_soc_dai_set_tdm_slot(codec_dai, 0, stream_tag, 0, 0); + /* set the hdac_stream in the codec dai */ + snd_soc_dai_set_stream(codec_dai, hdac_stream(link_dev), substream->stream); p_params.s_fmt = snd_pcm_format_width(params_format(params)); p_params.ch = params_channels(params); From 8b20aab8cfd0fe311a5388765d43d0e5febbcc81 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 24 Dec 2021 10:10:31 +0800 Subject: [PATCH 0684/4345] ASoC/SoundWire: dai: expand 'stream' concept beyond SoundWire commit e8444560b4d9302a511f0996f4cfdf85b628f4ca upstream. The HDAudio ASoC support relies on the set_tdm_slots() helper to store the HDaudio stream tag in the tx_mask. This only works because of the pre-existing order in soc-pcm.c, where the hw_params() is handled for codec_dais *before* cpu_dais. When the order is reversed, the stream_tag is used as a mask in the codec fixup functions: /* fixup params based on TDM slot masks */ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && codec_dai->tx_mask) soc_pcm_codec_params_fixup(&codec_params, codec_dai->tx_mask); As a result of this confusion, the codec_params_fixup() ends-up generating bad channel masks, depending on what stream_tag was allocated. We could add a flag to state that the tx_mask is really not a mask, but it would be quite ugly to persist in overloading concepts. Instead, this patch suggests a more generic get/set 'stream' API based on the existing model for SoundWire. We can expand the concept to store 'stream' opaque information that is specific to different DAI types. In the case of HDAudio DAIs, we only need to store a stream tag as an unsigned char pointer. The TDM rx_ and tx_masks should really only be used to store masks. Rename get_sdw_stream/set_sdw_stream callbacks and helpers as get_stream/set_stream. No functionality change beyond the rename. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Ranjani Sridharan Signed-off-by: Bard Liao Acked-By: Vinod Koul Link: https://lore.kernel.org/r/20211224021034.26635-5-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown Cc: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/intel.c | 8 ++++---- drivers/soundwire/qcom.c | 8 ++++---- drivers/soundwire/stream.c | 4 ++-- include/sound/soc-dai.h | 32 ++++++++++++++++---------------- sound/soc/codecs/max98373-sdw.c | 2 +- sound/soc/codecs/rt1308-sdw.c | 2 +- sound/soc/codecs/rt5682-sdw.c | 2 +- sound/soc/codecs/rt700.c | 2 +- sound/soc/codecs/rt711.c | 2 +- sound/soc/codecs/rt715.c | 2 +- sound/soc/codecs/wsa881x.c | 2 +- sound/soc/intel/boards/sof_sdw.c | 6 +++--- sound/soc/qcom/sdm845.c | 4 ++-- 13 files changed, 38 insertions(+), 38 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 942d2fe13218..4487fbb8f2e6 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -1140,8 +1140,8 @@ static const struct snd_soc_dai_ops intel_pcm_dai_ops = { .prepare = intel_prepare, .hw_free = intel_hw_free, .shutdown = intel_shutdown, - .set_sdw_stream = intel_pcm_set_sdw_stream, - .get_sdw_stream = intel_get_sdw_stream, + .set_stream = intel_pcm_set_sdw_stream, + .get_stream = intel_get_sdw_stream, }; static const struct snd_soc_dai_ops intel_pdm_dai_ops = { @@ -1150,8 +1150,8 @@ static const struct snd_soc_dai_ops intel_pdm_dai_ops = { .prepare = intel_prepare, .hw_free = intel_hw_free, .shutdown = intel_shutdown, - .set_sdw_stream = intel_pdm_set_sdw_stream, - .get_sdw_stream = intel_get_sdw_stream, + .set_stream = intel_pdm_set_sdw_stream, + .get_stream = intel_get_sdw_stream, }; static const struct snd_soc_component_driver dai_component = { diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 6d22df01f354..ac73258792e6 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -649,8 +649,8 @@ static int qcom_swrm_startup(struct snd_pcm_substream *substream, ctrl->sruntime[dai->id] = sruntime; for_each_rtd_codec_dais(rtd, i, codec_dai) { - ret = snd_soc_dai_set_sdw_stream(codec_dai, sruntime, - substream->stream); + ret = snd_soc_dai_set_stream(codec_dai, sruntime, + substream->stream); if (ret < 0 && ret != -ENOTSUPP) { dev_err(dai->dev, "Failed to set sdw stream on %s", codec_dai->name); @@ -676,8 +676,8 @@ static const struct snd_soc_dai_ops qcom_swrm_pdm_dai_ops = { .hw_free = qcom_swrm_hw_free, .startup = qcom_swrm_startup, .shutdown = qcom_swrm_shutdown, - .set_sdw_stream = qcom_swrm_set_sdw_stream, - .get_sdw_stream = qcom_swrm_get_sdw_stream, + .set_stream = qcom_swrm_set_sdw_stream, + .get_stream = qcom_swrm_get_sdw_stream, }; static const struct snd_soc_component_driver qcom_swrm_dai_component = { diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 304ff2ee7d75..79554d28f08a 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -1860,7 +1860,7 @@ static int set_stream(struct snd_pcm_substream *substream, /* Set stream pointer on all DAIs */ for_each_rtd_dais(rtd, i, dai) { - ret = snd_soc_dai_set_sdw_stream(dai, sdw_stream, substream->stream); + ret = snd_soc_dai_set_stream(dai, sdw_stream, substream->stream); if (ret < 0) { dev_err(rtd->dev, "failed to set stream pointer on dai %s", dai->name); break; @@ -1931,7 +1931,7 @@ void sdw_shutdown_stream(void *sdw_substream) /* Find stream from first CPU DAI */ dai = asoc_rtd_to_cpu(rtd, 0); - sdw_stream = snd_soc_dai_get_sdw_stream(dai, substream->stream); + sdw_stream = snd_soc_dai_get_stream(dai, substream->stream); if (IS_ERR(sdw_stream)) { dev_err(rtd->dev, "no stream found for DAI %s", dai->name); diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index 2150bd4c7a05..fe86172e8602 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -239,9 +239,9 @@ struct snd_soc_dai_ops { unsigned int *rx_num, unsigned int *rx_slot); int (*set_tristate)(struct snd_soc_dai *dai, int tristate); - int (*set_sdw_stream)(struct snd_soc_dai *dai, - void *stream, int direction); - void *(*get_sdw_stream)(struct snd_soc_dai *dai, int direction); + int (*set_stream)(struct snd_soc_dai *dai, + void *stream, int direction); + void *(*get_stream)(struct snd_soc_dai *dai, int direction); /* * DAI digital mute - optional. @@ -446,42 +446,42 @@ static inline void *snd_soc_dai_get_drvdata(struct snd_soc_dai *dai) } /** - * snd_soc_dai_set_sdw_stream() - Configures a DAI for SDW stream operation + * snd_soc_dai_set_stream() - Configures a DAI for stream operation * @dai: DAI - * @stream: STREAM + * @stream: STREAM (opaque structure depending on DAI type) * @direction: Stream direction(Playback/Capture) - * SoundWire subsystem doesn't have a notion of direction and we reuse + * Some subsystems, such as SoundWire, don't have a notion of direction and we reuse * the ASoC stream direction to configure sink/source ports. * Playback maps to source ports and Capture for sink ports. * * This should be invoked with NULL to clear the stream set previously. * Returns 0 on success, a negative error code otherwise. */ -static inline int snd_soc_dai_set_sdw_stream(struct snd_soc_dai *dai, - void *stream, int direction) +static inline int snd_soc_dai_set_stream(struct snd_soc_dai *dai, + void *stream, int direction) { - if (dai->driver->ops->set_sdw_stream) - return dai->driver->ops->set_sdw_stream(dai, stream, direction); + if (dai->driver->ops->set_stream) + return dai->driver->ops->set_stream(dai, stream, direction); else return -ENOTSUPP; } /** - * snd_soc_dai_get_sdw_stream() - Retrieves SDW stream from DAI + * snd_soc_dai_get_stream() - Retrieves stream from DAI * @dai: DAI * @direction: Stream direction(Playback/Capture) * * This routine only retrieves that was previously configured - * with snd_soc_dai_get_sdw_stream() + * with snd_soc_dai_get_stream() * * Returns pointer to stream or an ERR_PTR value, e.g. * ERR_PTR(-ENOTSUPP) if callback is not supported; */ -static inline void *snd_soc_dai_get_sdw_stream(struct snd_soc_dai *dai, - int direction) +static inline void *snd_soc_dai_get_stream(struct snd_soc_dai *dai, + int direction) { - if (dai->driver->ops->get_sdw_stream) - return dai->driver->ops->get_sdw_stream(dai, direction); + if (dai->driver->ops->get_stream) + return dai->driver->ops->get_stream(dai, direction); else return ERR_PTR(-ENOTSUPP); } diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c index 39afa011f0e2..a2bb93fb830b 100644 --- a/sound/soc/codecs/max98373-sdw.c +++ b/sound/soc/codecs/max98373-sdw.c @@ -728,7 +728,7 @@ static int max98373_sdw_set_tdm_slot(struct snd_soc_dai *dai, static const struct snd_soc_dai_ops max98373_dai_sdw_ops = { .hw_params = max98373_sdw_dai_hw_params, .hw_free = max98373_pcm_hw_free, - .set_sdw_stream = max98373_set_sdw_stream, + .set_stream = max98373_set_sdw_stream, .shutdown = max98373_shutdown, .set_tdm_slot = max98373_sdw_set_tdm_slot, }; diff --git a/sound/soc/codecs/rt1308-sdw.c b/sound/soc/codecs/rt1308-sdw.c index 31daa749c3db..a13296edf295 100644 --- a/sound/soc/codecs/rt1308-sdw.c +++ b/sound/soc/codecs/rt1308-sdw.c @@ -613,7 +613,7 @@ static const struct snd_soc_component_driver soc_component_sdw_rt1308 = { static const struct snd_soc_dai_ops rt1308_aif_dai_ops = { .hw_params = rt1308_sdw_hw_params, .hw_free = rt1308_sdw_pcm_hw_free, - .set_sdw_stream = rt1308_set_sdw_stream, + .set_stream = rt1308_set_sdw_stream, .shutdown = rt1308_sdw_shutdown, .set_tdm_slot = rt1308_sdw_set_tdm_slot, }; diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c index c9868dd096fc..2fb6b1edf933 100644 --- a/sound/soc/codecs/rt5682-sdw.c +++ b/sound/soc/codecs/rt5682-sdw.c @@ -272,7 +272,7 @@ static int rt5682_sdw_hw_free(struct snd_pcm_substream *substream, static struct snd_soc_dai_ops rt5682_sdw_ops = { .hw_params = rt5682_sdw_hw_params, .hw_free = rt5682_sdw_hw_free, - .set_sdw_stream = rt5682_set_sdw_stream, + .set_stream = rt5682_set_sdw_stream, .shutdown = rt5682_sdw_shutdown, }; diff --git a/sound/soc/codecs/rt700.c b/sound/soc/codecs/rt700.c index 687ac2153666..80acf0daabf8 100644 --- a/sound/soc/codecs/rt700.c +++ b/sound/soc/codecs/rt700.c @@ -1005,7 +1005,7 @@ static int rt700_pcm_hw_free(struct snd_pcm_substream *substream, static struct snd_soc_dai_ops rt700_ops = { .hw_params = rt700_pcm_hw_params, .hw_free = rt700_pcm_hw_free, - .set_sdw_stream = rt700_set_sdw_stream, + .set_stream = rt700_set_sdw_stream, .shutdown = rt700_shutdown, }; diff --git a/sound/soc/codecs/rt711.c b/sound/soc/codecs/rt711.c index 93d86f7558e0..9bdcc7872053 100644 --- a/sound/soc/codecs/rt711.c +++ b/sound/soc/codecs/rt711.c @@ -1059,7 +1059,7 @@ static int rt711_pcm_hw_free(struct snd_pcm_substream *substream, static struct snd_soc_dai_ops rt711_ops = { .hw_params = rt711_pcm_hw_params, .hw_free = rt711_pcm_hw_free, - .set_sdw_stream = rt711_set_sdw_stream, + .set_stream = rt711_set_sdw_stream, .shutdown = rt711_shutdown, }; diff --git a/sound/soc/codecs/rt715.c b/sound/soc/codecs/rt715.c index 532c5303e7ab..22bdccf66346 100644 --- a/sound/soc/codecs/rt715.c +++ b/sound/soc/codecs/rt715.c @@ -686,7 +686,7 @@ static int rt715_pcm_hw_free(struct snd_pcm_substream *substream, static struct snd_soc_dai_ops rt715_ops = { .hw_params = rt715_pcm_hw_params, .hw_free = rt715_pcm_hw_free, - .set_sdw_stream = rt715_set_sdw_stream, + .set_stream = rt715_set_sdw_stream, .shutdown = rt715_shutdown, }; diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 601525c77bba..15b3f47fbfa3 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -1026,7 +1026,7 @@ static struct snd_soc_dai_ops wsa881x_dai_ops = { .hw_params = wsa881x_hw_params, .hw_free = wsa881x_hw_free, .mute_stream = wsa881x_digital_mute, - .set_sdw_stream = wsa881x_set_sdw_stream, + .set_stream = wsa881x_set_sdw_stream, }; static struct snd_soc_dai_driver wsa881x_dais[] = { diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 25548555d8d7..f5d8f7951cfc 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -231,7 +231,7 @@ int sdw_prepare(struct snd_pcm_substream *substream) /* Find stream from first CPU DAI */ dai = asoc_rtd_to_cpu(rtd, 0); - sdw_stream = snd_soc_dai_get_sdw_stream(dai, substream->stream); + sdw_stream = snd_soc_dai_get_stream(dai, substream->stream); if (IS_ERR(sdw_stream)) { dev_err(rtd->dev, "no stream found for DAI %s", dai->name); @@ -251,7 +251,7 @@ int sdw_trigger(struct snd_pcm_substream *substream, int cmd) /* Find stream from first CPU DAI */ dai = asoc_rtd_to_cpu(rtd, 0); - sdw_stream = snd_soc_dai_get_sdw_stream(dai, substream->stream); + sdw_stream = snd_soc_dai_get_stream(dai, substream->stream); if (IS_ERR(sdw_stream)) { dev_err(rtd->dev, "no stream found for DAI %s", dai->name); @@ -290,7 +290,7 @@ int sdw_hw_free(struct snd_pcm_substream *substream) /* Find stream from first CPU DAI */ dai = asoc_rtd_to_cpu(rtd, 0); - sdw_stream = snd_soc_dai_get_sdw_stream(dai, substream->stream); + sdw_stream = snd_soc_dai_get_stream(dai, substream->stream); if (IS_ERR(sdw_stream)) { dev_err(rtd->dev, "no stream found for DAI %s", dai->name); diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c index 153e9b2de0b5..6be7a32933ad 100644 --- a/sound/soc/qcom/sdm845.c +++ b/sound/soc/qcom/sdm845.c @@ -56,8 +56,8 @@ static int sdm845_slim_snd_hw_params(struct snd_pcm_substream *substream, int ret = 0, i; for_each_rtd_codec_dais(rtd, i, codec_dai) { - sruntime = snd_soc_dai_get_sdw_stream(codec_dai, - substream->stream); + sruntime = snd_soc_dai_get_stream(codec_dai, + substream->stream); if (sruntime != ERR_PTR(-ENOTSUPP)) pdata->sruntime[cpu_dai->id] = sruntime; From 40b844796b6bd041b77c928f6373e02ff4c68f9f Mon Sep 17 00:00:00 2001 From: Dima Chumak Date: Mon, 26 Apr 2021 15:16:26 +0300 Subject: [PATCH 0685/4345] net/mlx5e: Fix nullptr in mlx5e_tc_add_fdb_flow() commit fe7738eb3ca3631a75844e790f6cb576c0fe7b00 upstream. The result of __dev_get_by_index() is not checked for NULL, which then passed to mlx5e_attach_encap() and gets dereferenced. Also, in case of a successful lookup, the net_device reference count is not incremented, which may result in net_device pointer becoming invalid at any time during mlx5e_attach_encap() execution. Fix by using dev_get_by_index(), which does proper reference counting on the net_device pointer. Also, handle nullptr return value when mirred device is not found. It's safe to call dev_put() on the mirred net_device pointer, right after mlx5e_attach_encap() call, because it's not being saved/copied down the call chain. Fixes: 3c37745ec614 ("net/mlx5e: Properly deal with encap flows add/del under neigh update") Addresses-Coverity: ("Dereference null return value") Signed-off-by: Dima Chumak Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed Signed-off-by: Nikita Zhandarovich Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index f1bf7f6758d0..16846442717d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1344,9 +1344,9 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct net_device *out_dev, *encap_dev = NULL; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; + struct net_device *encap_dev = NULL; struct mlx5_esw_flow_attr *esw_attr; struct mlx5_fc *counter = NULL; struct mlx5e_rep_priv *rpriv; @@ -1391,16 +1391,22 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr = attr->esw_attr; for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + struct net_device *out_dev; int mirred_ifindex; if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) continue; mirred_ifindex = parse_attr->mirred_ifindex[out_index]; - out_dev = __dev_get_by_index(dev_net(priv->netdev), - mirred_ifindex); + out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); + if (!out_dev) { + NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); + err = -ENODEV; + return err; + } err = mlx5e_attach_encap(priv, flow, out_dev, out_index, extack, &encap_dev, &encap_valid); + dev_put(out_dev); if (err) return err; From 0f6d6974b08e1f0b904466b2b7a0ff47b2c70140 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 20 May 2022 12:43:15 -0700 Subject: [PATCH 0686/4345] wifi: rtlwifi: remove always-true condition pointed out by GCC 12 commit ee3db469dd317e82f57b13aa3bc61be5cb60c2b4 upstream. The .value is a two-dim array, not a pointer. struct iqk_matrix_regs { bool iqk_done; long value[1][IQK_MATRIX_REG_NUM]; }; Acked-by: Kalle Valo Signed-off-by: Jakub Kicinski Signed-off-by: Semyon Verchenko Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c index e34d33e73e52..d8a57e96a92f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c @@ -2385,10 +2385,7 @@ void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel) rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD, "Just Read IQK Matrix reg for channel:%d....\n", channel); - if ((rtlphy->iqk_matrix[indexforchannel]. - value[0] != NULL) - /*&&(regea4 != 0) */) - _rtl92d_phy_patha_fill_iqk_matrix(hw, true, + _rtl92d_phy_patha_fill_iqk_matrix(hw, true, rtlphy->iqk_matrix[ indexforchannel].value, 0, (rtlphy->iqk_matrix[ From 289f512d08c4edffd3defa7b030debe22132d31b Mon Sep 17 00:00:00 2001 From: Ping-Ke Shih Date: Mon, 1 Aug 2022 19:33:45 +0800 Subject: [PATCH 0687/4345] wifi: rtlwifi: 8192de: correct checking of IQK reload commit 93fbc1ebd978cf408ef5765e9c1630fce9a8621b upstream. Since IQK could spend time, we make a cache of IQK result matrix that looks like iqk_matrix[channel_idx].val[x][y], and we can reload the matrix if we have made a cache. To determine a cache is made, we check iqk_matrix[channel_idx].val[0][0]. The initial commit 7274a8c22980 ("rtlwifi: rtl8192de: Merge phy routines") make a mistake that checks incorrect iqk_matrix[channel_idx].val[0] that is always true, and this mistake is found by commit ee3db469dd31 ("wifi: rtlwifi: remove always-true condition pointed out by GCC 12"), so I recall the vendor driver to find fix and apply the correctness. Fixes: 7274a8c22980 ("rtlwifi: rtl8192de: Merge phy routines") Signed-off-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220801113345.42016-1-pkshih@realtek.com Signed-off-by: Semyon Verchenko Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c index d8a57e96a92f..d3027f8fbd38 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c @@ -2385,11 +2385,10 @@ void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel) rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD, "Just Read IQK Matrix reg for channel:%d....\n", channel); - _rtl92d_phy_patha_fill_iqk_matrix(hw, true, - rtlphy->iqk_matrix[ - indexforchannel].value, 0, - (rtlphy->iqk_matrix[ - indexforchannel].value[0][2] == 0)); + if (rtlphy->iqk_matrix[indexforchannel].value[0][0] != 0) + _rtl92d_phy_patha_fill_iqk_matrix(hw, true, + rtlphy->iqk_matrix[indexforchannel].value, 0, + rtlphy->iqk_matrix[indexforchannel].value[0][2] == 0); if (IS_92D_SINGLEPHY(rtlhal->version)) { if ((rtlphy->iqk_matrix[ indexforchannel].value[0][4] != 0) From 4c57f612f433f667c454191a8ff078b135dfcc4d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 16 Sep 2020 10:10:10 -0700 Subject: [PATCH 0688/4345] torture: Exclude "NOHZ tick-stop error" from fatal errors commit 8d68e68a781db80606c8e8f3e4383be6974878fd upstream. The "NOHZ tick-stop error: Non-RCU local softirq work is pending" warning happens frequently and appears to be irrelevant to the various torture tests. This commit therefore filters it out. If there proves to be a need to pay attention to it a later commit will add an "advice" category to allow the user to immediately see that although something happened, it was not an indictment of the system being tortured. Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/rcutorture/bin/console-badness.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh index 0e4c0b2eb7f0..80ae7f08b363 100755 --- a/tools/testing/selftests/rcutorture/bin/console-badness.sh +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -13,4 +13,5 @@ egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | grep -v 'ODEBUG: ' | grep -v 'This means that this is a DEBUG kernel and it is' | -grep -v 'Warning: unable to open an initial console' +grep -v 'Warning: unable to open an initial console' | +grep -v 'NOHZ tick-stop error: Non-RCU local softirq work is pending, handler' From 7c15d7ecce0064fd0724422ec84d074a4b4eecef Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 13 Oct 2020 12:39:23 -0700 Subject: [PATCH 0689/4345] rcu: Prevent lockdep-RCU splats on lock acquisition/release commit 4d60b475f858ebdb06c1339f01a890f287b5e587 upstream. The rcu_cpu_starting() and rcu_report_dead() functions transition the current CPU between online and offline state from an RCU perspective. Unfortunately, this means that the rcu_cpu_starting() function's lock acquisition and the rcu_report_dead() function's lock releases happen while the CPU is offline from an RCU perspective, which can result in lockdep-RCU splats about using RCU from an offline CPU. And this situation can also result in too-short grace periods, especially in guest OSes that are subject to vCPU preemption. This commit therefore uses sequence-count-like synchronization to forgive use of RCU while RCU thinks a CPU is offline across the full extent of the rcu_cpu_starting() and rcu_report_dead() function's lock acquisitions and releases. One approach would have been to use the actual sequence-count primitives provided by the Linux kernel. Unfortunately, the resulting code looks completely broken and wrong, and is likely to result in patches that break RCU in an attempt to address this appearance of broken wrongness. Plus there is no net savings in lines of code, given the additional explicit memory barriers required. Therefore, this sequence count is instead implemented by a new ->ofl_seq field in the rcu_node structure. If this counter's value is an odd number, RCU forgives RCU read-side critical sections on other CPUs covered by the same rcu_node structure, even if those CPUs are offline from an RCU perspective. In addition, if a given leaf rcu_node structure's ->ofl_seq counter value is an odd number, rcu_gp_init() delays starting the grace period until that counter value changes. [ paulmck: Apply Peter Zijlstra feedback. ] Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/rcu/tree.c | 21 ++++++++++++++++++++- kernel/rcu/tree.h | 1 + 2 files changed, 21 insertions(+), 1 deletion(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3fe7c75c371b..9cce4e13af41 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1157,7 +1157,7 @@ bool rcu_lockdep_current_cpu_online(void) preempt_disable_notrace(); rdp = this_cpu_ptr(&rcu_data); rnp = rdp->mynode; - if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) + if (rdp->grpmask & rcu_rnp_online_cpus(rnp) || READ_ONCE(rnp->ofl_seq) & 0x1) ret = true; preempt_enable_notrace(); return ret; @@ -1724,6 +1724,7 @@ static void rcu_strict_gp_boundary(void *unused) */ static bool rcu_gp_init(void) { + unsigned long firstseq; unsigned long flags; unsigned long oldmask; unsigned long mask; @@ -1767,6 +1768,12 @@ static bool rcu_gp_init(void) */ rcu_state.gp_state = RCU_GP_ONOFF; rcu_for_each_leaf_node(rnp) { + smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values. + firstseq = READ_ONCE(rnp->ofl_seq); + if (firstseq & 0x1) + while (firstseq == READ_ONCE(rnp->ofl_seq)) + schedule_timeout_idle(1); // Can't wake unless RCU is watching. + smp_mb(); // Pair with barriers used when updating ->ofl_seq to even values. raw_spin_lock(&rcu_state.ofl_lock); raw_spin_lock_irq_rcu_node(rnp); if (rnp->qsmaskinit == rnp->qsmaskinitnext && @@ -4107,6 +4114,9 @@ void rcu_cpu_starting(unsigned int cpu) rnp = rdp->mynode; mask = rdp->grpmask; + WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); + WARN_ON_ONCE(!(rnp->ofl_seq & 0x1)); + smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). raw_spin_lock_irqsave_rcu_node(rnp, flags); WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask); newcpu = !(rnp->expmaskinitnext & mask); @@ -4124,6 +4134,9 @@ void rcu_cpu_starting(unsigned int cpu) } else { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } + smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). + WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); + WARN_ON_ONCE(rnp->ofl_seq & 0x1); smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } @@ -4150,6 +4163,9 @@ void rcu_report_dead(unsigned int cpu) /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; + WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); + WARN_ON_ONCE(!(rnp->ofl_seq & 0x1)); + smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). raw_spin_lock(&rcu_state.ofl_lock); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq); @@ -4162,6 +4178,9 @@ void rcu_report_dead(unsigned int cpu) WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); raw_spin_unlock(&rcu_state.ofl_lock); + smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). + WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); + WARN_ON_ONCE(rnp->ofl_seq & 0x1); rdp->cpu_started = false; } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index e4f66b8f7c47..6e8c77729a47 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -56,6 +56,7 @@ struct rcu_node { /* Initialized from ->qsmaskinitnext at the */ /* beginning of each grace period. */ unsigned long qsmaskinitnext; + unsigned long ofl_seq; /* CPU-hotplug operation sequence count. */ /* Online CPUs for next grace period. */ unsigned long expmask; /* CPUs or groups that need to check in */ /* to allow the current expedited GP */ From c2137d565ceb505de69593c181a0543bc4083838 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 25 Apr 2022 09:45:02 +0800 Subject: [PATCH 0690/4345] net/af_packet: add VLAN support for AF_PACKET SOCK_RAW GSO commit dfed913e8b55a0c2c4906f1242fd38fd9a116e49 upstream. Currently, the kernel drops GSO VLAN tagged packet if it's created with socket(AF_PACKET, SOCK_RAW, 0) plus virtio_net_hdr. The reason is AF_PACKET doesn't adjust the skb network header if there is a VLAN tag. Then after virtio_net_hdr_set_proto() called, the skb->protocol will be set to ETH_P_IP/IPv6. And in later inet/ipv6_gso_segment() the skb is dropped as network header position is invalid. Let's handle VLAN packets by adjusting network header position in packet_parse_headers(). The adjustment is safe and does not affect the later xmit as tap device also did that. In packet_snd(), packet_parse_headers() need to be moved before calling virtio_net_hdr_set_proto(), so we can set correct skb->protocol and network header first. There is no need to update tpacket_snd() as it calls packet_parse_headers() in tpacket_fill_skb(), which is already before calling virtio_net_hdr_* functions. skb->no_fcs setting is also moved upper to make all skb settings together and keep consistency with function packet_sendmsg_spkt(). Signed-off-by: Hangbin Liu Acked-by: Willem de Bruijn Acked-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/20220425014502.985464-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- net/packet/af_packet.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index eaa030e2ad55..22b0513f133d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1885,12 +1885,20 @@ oom: static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { + int depth; + if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } + /* Move network header to the right position for VLAN tagged packets */ + if (likely(skb->dev->type == ARPHRD_ETHER) && + eth_type_vlan(skb->protocol) && + __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + skb_set_network_header(skb, depth); + skb_probe_transport_header(skb); } @@ -3005,6 +3013,11 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; + if (unlikely(extra_len == 4)) + skb->no_fcs = 1; + + packet_parse_headers(skb, sock); + if (has_vnet_hdr) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) @@ -3013,11 +3026,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) virtio_net_hdr_set_proto(skb, &vnet_hdr); } - packet_parse_headers(skb, sock); - - if (unlikely(extra_len == 4)) - skb->no_fcs = 1; - err = po->xmit(skb); if (unlikely(err != 0)) { if (err > 0) From 25dbd87379f8e8c520197f0d632efea838519e88 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 2 Jun 2022 09:18:59 -0700 Subject: [PATCH 0691/4345] net/af_packet: make sure to pull mac header commit e9d3f80935b6607dcdc5682b00b1d4b28e0a0c5d upstream. GSO assumes skb->head contains link layer headers. tun device in some case can provide base 14 bytes, regardless of VLAN being used or not. After blamed commit, we can end up setting a network header offset of 18+, we better pull the missing bytes to avoid a posible crash in GSO. syzbot report was: kernel BUG at include/linux/skbuff.h:2699! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 3601 Comm: syz-executor210 Not tainted 5.18.0-syzkaller-11338-g2c5ca23f7414 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__skb_pull include/linux/skbuff.h:2699 [inline] RIP: 0010:skb_mac_gso_segment+0x48f/0x530 net/core/gro.c:136 Code: 00 48 c7 c7 00 96 d4 8a c6 05 cb d3 45 06 01 e8 26 bb d0 01 e9 2f fd ff ff 49 c7 c4 ea ff ff ff e9 f1 fe ff ff e8 91 84 19 fa <0f> 0b 48 89 df e8 97 44 66 fa e9 7f fd ff ff e8 ad 44 66 fa e9 48 RSP: 0018:ffffc90002e2f4b8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 0000000000000012 RCX: 0000000000000000 RDX: ffff88805bb58000 RSI: ffffffff8760ed0f RDI: 0000000000000004 RBP: 0000000000005dbc R08: 0000000000000004 R09: 0000000000000fe0 R10: 0000000000000fe4 R11: 0000000000000000 R12: 0000000000000fe0 R13: ffff88807194d780 R14: 1ffff920005c5e9b R15: 0000000000000012 FS: 000055555730f300(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000200015c0 CR3: 0000000071ff8000 CR4: 0000000000350ee0 Call Trace: __skb_gso_segment+0x327/0x6e0 net/core/dev.c:3411 skb_gso_segment include/linux/netdevice.h:4749 [inline] validate_xmit_skb+0x6bc/0xf10 net/core/dev.c:3669 validate_xmit_skb_list+0xbc/0x120 net/core/dev.c:3719 sch_direct_xmit+0x3d1/0xbe0 net/sched/sch_generic.c:327 __dev_xmit_skb net/core/dev.c:3815 [inline] __dev_queue_xmit+0x14a1/0x3a00 net/core/dev.c:4219 packet_snd net/packet/af_packet.c:3071 [inline] packet_sendmsg+0x21cb/0x5550 net/packet/af_packet.c:3102 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 ____sys_sendmsg+0x6eb/0x810 net/socket.c:2492 ___sys_sendmsg+0xf3/0x170 net/socket.c:2546 __sys_sendmsg net/socket.c:2575 [inline] __do_sys_sendmsg net/socket.c:2584 [inline] __se_sys_sendmsg net/socket.c:2582 [inline] __x64_sys_sendmsg+0x132/0x220 net/socket.c:2582 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f4b95da06c9 Code: 28 c3 e8 4a 15 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd7defc4c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007ffd7defc4f0 RCX: 00007f4b95da06c9 RDX: 0000000000000000 RSI: 0000000020000140 RDI: 0000000000000003 RBP: 0000000000000003 R08: bb1414ac00000050 R09: bb1414ac00000050 R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffd7defc4e0 R14: 00007ffd7defc4d8 R15: 00007ffd7defc4d4 Fixes: dfed913e8b55 ("net/af_packet: add VLAN support for AF_PACKET SOCK_RAW GSO") Signed-off-by: Eric Dumazet Reported-by: syzbot Acked-by: Hangbin Liu Acked-by: Willem de Bruijn Cc: Michael S. Tsirkin Signed-off-by: Jakub Kicinski Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- net/packet/af_packet.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 22b0513f133d..3716797c5564 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1896,8 +1896,10 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) - skb_set_network_header(skb, depth); + __vlan_get_protocol(skb, skb->protocol, &depth) != 0) { + if (pskb_may_pull(skb, depth)) + skb_set_network_header(skb, depth); + } skb_probe_transport_header(skb); } From d5db9aaf1b47c6acf16bc94e9703636cb9a6f5f9 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 24 Oct 2022 17:23:43 +0200 Subject: [PATCH 0692/4345] media: stv0288: use explicitly signed char commit 7392134428c92a4cb541bd5c8f4f5c8d2e88364d upstream. With char becoming unsigned by default, and with `char` alone being ambiguous and based on architecture, signed chars need to be marked explicitly as such. Use `s8` and `u8` types here, since that's what surrounding code does. This fixes: drivers/media/dvb-frontends/stv0288.c:471 stv0288_set_frontend() warn: assigning (-9) to unsigned variable 'tm' drivers/media/dvb-frontends/stv0288.c:471 stv0288_set_frontend() warn: we never enter this loop Cc: Mauro Carvalho Chehab Cc: linux-media@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Jason A. Donenfeld Signed-off-by: Greg Kroah-Hartman --- drivers/media/dvb-frontends/stv0288.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/media/dvb-frontends/stv0288.c b/drivers/media/dvb-frontends/stv0288.c index 3d54a0ec86af..3ae1f3a2f142 100644 --- a/drivers/media/dvb-frontends/stv0288.c +++ b/drivers/media/dvb-frontends/stv0288.c @@ -440,9 +440,8 @@ static int stv0288_set_frontend(struct dvb_frontend *fe) struct stv0288_state *state = fe->demodulator_priv; struct dtv_frontend_properties *c = &fe->dtv_property_cache; - char tm; - unsigned char tda[3]; - u8 reg, time_out = 0; + u8 tda[3], reg, time_out = 0; + s8 tm; dprintk("%s : FE_SET_FRONTEND\n", __func__); From 780297af3c85266d2f286e778132e9016630735f Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 29 Nov 2022 12:41:59 +0530 Subject: [PATCH 0693/4345] soc: qcom: Select REMAP_MMIO for LLCC driver commit 5d2fe2d7b616b8baa18348ead857b504fc2de336 upstream. LLCC driver uses REGMAP_MMIO for accessing the hardware registers. So select the dependency in Kconfig. Without this, there will be errors while building the driver with COMPILE_TEST only: ERROR: modpost: "__devm_regmap_init_mmio_clk" [drivers/soc/qcom/llcc-qcom.ko] undefined! make[1]: *** [scripts/Makefile.modpost:126: Module.symvers] Error 1 make: *** [Makefile:1944: modpost] Error 2 Cc: # 4.19 Fixes: a3134fb09e0b ("drivers: soc: Add LLCC driver") Reported-by: Borislav Petkov Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221129071201.30024-2-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/soc/qcom/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig index d0cf969a8fb5..479d60abbd14 100644 --- a/drivers/soc/qcom/Kconfig +++ b/drivers/soc/qcom/Kconfig @@ -63,6 +63,7 @@ config QCOM_GSBI config QCOM_LLCC tristate "Qualcomm Technologies, Inc. LLCC driver" depends on ARCH_QCOM || COMPILE_TEST + select REGMAP_MMIO help Qualcomm Technologies, Inc. platform specific Last Level Cache Controller(LLCC) driver for platforms such as, From 5148dfceab557f7137c82671fedaf13a68beca1a Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 30 Nov 2022 17:54:34 -0500 Subject: [PATCH 0694/4345] kest.pl: Fix grub2 menu handling for rebooting commit 26df05a8c1420ad3de314fdd407e7fc2058cc7aa upstream. grub2 has submenus where to use grub-reboot, it requires: grub-reboot X>Y where X is the main index and Y is the submenu. Thus if you have: menuentry 'Debian GNU/Linux' --class debian --class gnu-linux ... [...] } submenu 'Advanced options for Debian GNU/Linux' $menuentry_id_option ... menuentry 'Debian GNU/Linux, with Linux 6.0.0-4-amd64' --class debian --class gnu-linux ... [...] } menuentry 'Debian GNU/Linux, with Linux 6.0.0-4-amd64 (recovery mode)' --class debian --class gnu-linux ... [...] } menuentry 'Debian GNU/Linux, with Linux test' --class debian --class gnu-linux ... [...] } And wanted to boot to the "Linux test" kernel, you need to run: # grub-reboot 1>2 As 1 is the second top menu (the submenu) and 2 is the third of the sub menu entries. Have the grub.cfg parsing for grub2 handle such cases. Cc: stable@vger.kernel.org Fixes: a15ba91361d46 ("ktest: Add support for grub2") Reviewed-by: John 'Warthog9' Hawley (VMware) Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- tools/testing/ktest/ktest.pl | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 4e2450964517..a7a3e318a194 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1912,7 +1912,7 @@ sub run_scp_mod { sub _get_grub_index { - my ($command, $target, $skip) = @_; + my ($command, $target, $skip, $submenu) = @_; return if (defined($grub_number) && defined($last_grub_menu) && $last_grub_menu eq $grub_menu && defined($last_machine) && @@ -1929,11 +1929,16 @@ sub _get_grub_index { my $found = 0; + my $submenu_number = 0; + while () { if (/$target/) { $grub_number++; $found = 1; last; + } elsif (defined($submenu) && /$submenu/) { + $submenu_number++; + $grub_number = -1; } elsif (/$skip/) { $grub_number++; } @@ -1942,6 +1947,9 @@ sub _get_grub_index { dodie "Could not find '$grub_menu' through $command on $machine" if (!$found); + if ($submenu_number > 0) { + $grub_number = "$submenu_number>$grub_number"; + } doprint "$grub_number\n"; $last_grub_menu = $grub_menu; $last_machine = $machine; @@ -1952,6 +1960,7 @@ sub get_grub_index { my $command; my $target; my $skip; + my $submenu; my $grub_menu_qt; if ($reboot_type !~ /^grub/) { @@ -1966,8 +1975,9 @@ sub get_grub_index { $skip = '^\s*title\s'; } elsif ($reboot_type eq "grub2") { $command = "cat $grub_file"; - $target = '^menuentry.*' . $grub_menu_qt; - $skip = '^menuentry\s|^submenu\s'; + $target = '^\s*menuentry.*' . $grub_menu_qt; + $skip = '^\s*menuentry'; + $submenu = '^\s*submenu\s'; } elsif ($reboot_type eq "grub2bls") { $command = $grub_bls_get; $target = '^title=.*' . $grub_menu_qt; @@ -1976,7 +1986,7 @@ sub get_grub_index { return; } - _get_grub_index($command, $target, $skip); + _get_grub_index($command, $target, $skip, $submenu); } sub wait_for_input @@ -2040,7 +2050,7 @@ sub reboot_to { if ($reboot_type eq "grub") { run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch)'"; } elsif (($reboot_type eq "grub2") or ($reboot_type eq "grub2bls")) { - run_ssh "$grub_reboot $grub_number"; + run_ssh "$grub_reboot \"'$grub_number'\""; } elsif ($reboot_type eq "syslinux") { run_ssh "$syslinux --once \\\"$syslinux_label\\\" $syslinux_path"; } elsif (defined $reboot_script) { From 8c444b3061f05b2f97d4ca6eac1738db7d3eb037 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 2 Dec 2022 11:59:36 -0500 Subject: [PATCH 0695/4345] ktest.pl minconfig: Unset configs instead of just removing them commit ef784eebb56425eed6e9b16e7d47e5c00dcf9c38 upstream. After a full run of a make_min_config test, I noticed there were a lot of CONFIGs still enabled that really should not be. Looking at them, I noticed they were all defined as "default y". The issue is that the test simple removes the config and re-runs make oldconfig, which enables it again because it is set to default 'y'. Instead, explicitly disable the config with writing "# CONFIG_FOO is not set" to the file to keep it from being set again. With this change, one of my box's minconfigs went from 768 configs set, down to 521 configs set. Link: https://lkml.kernel.org/r/20221202115936.016fce23@gandalf.local.home Cc: stable@vger.kernel.org Fixes: 0a05c769a9de5 ("ktest: Added config_bisect test type") Reviewed-by: John 'Warthog9' Hawley (VMware) Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- tools/testing/ktest/ktest.pl | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index a7a3e318a194..8b1e3ae8fe50 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -3773,9 +3773,10 @@ sub test_this_config { # .config to make sure it is missing the config that # we had before my %configs = %min_configs; - delete $configs{$config}; + $configs{$config} = "# $config is not set"; make_new_config ((values %configs), (values %keep_configs)); make_oldconfig; + delete $configs{$config}; undef %configs; assign_configs \%configs, $output_config; From c023597baecb0fe5c10708bdc3460b59ca8a8194 Mon Sep 17 00:00:00 2001 From: Bixuan Cui Date: Tue, 11 Oct 2022 19:33:44 +0800 Subject: [PATCH 0696/4345] jbd2: use the correct print format commit d87a7b4c77a997d5388566dd511ca8e6b8e8a0a8 upstream. The print format error was found when using ftrace event: <...>-1406 [000] .... 23599442.895823: jbd2_end_commit: dev 252,8 transaction -1866216965 sync 0 head -1866217368 <...>-1406 [000] .... 23599442.896299: jbd2_start_commit: dev 252,8 transaction -1866216964 sync 0 Use the correct print format for transaction, head and tid. Fixes: 879c5e6b7cb4 ('jbd2: convert instrumentation from markers to tracepoints') Signed-off-by: Bixuan Cui Reviewed-by: Jason Yan Link: https://lore.kernel.org/r/1665488024-95172-1-git-send-email-cuibixuan@linux.alibaba.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/trace/events/jbd2.h | 44 ++++++++++++++++++------------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index d16a32867f3a..b1847e4314b8 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -40,7 +40,7 @@ DECLARE_EVENT_CLASS(jbd2_commit, TP_STRUCT__entry( __field( dev_t, dev ) __field( char, sync_commit ) - __field( int, transaction ) + __field( tid_t, transaction ) ), TP_fast_assign( @@ -49,7 +49,7 @@ DECLARE_EVENT_CLASS(jbd2_commit, __entry->transaction = commit_transaction->t_tid; ), - TP_printk("dev %d,%d transaction %d sync %d", + TP_printk("dev %d,%d transaction %u sync %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->transaction, __entry->sync_commit) ); @@ -97,8 +97,8 @@ TRACE_EVENT(jbd2_end_commit, TP_STRUCT__entry( __field( dev_t, dev ) __field( char, sync_commit ) - __field( int, transaction ) - __field( int, head ) + __field( tid_t, transaction ) + __field( tid_t, head ) ), TP_fast_assign( @@ -108,7 +108,7 @@ TRACE_EVENT(jbd2_end_commit, __entry->head = journal->j_tail_sequence; ), - TP_printk("dev %d,%d transaction %d sync %d head %d", + TP_printk("dev %d,%d transaction %u sync %d head %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->transaction, __entry->sync_commit, __entry->head) ); @@ -134,14 +134,14 @@ TRACE_EVENT(jbd2_submit_inode_data, ); DECLARE_EVENT_CLASS(jbd2_handle_start_class, - TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, + TP_PROTO(dev_t dev, tid_t tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks), TP_STRUCT__entry( __field( dev_t, dev ) - __field( unsigned long, tid ) + __field( tid_t, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, requested_blocks) @@ -155,28 +155,28 @@ DECLARE_EVENT_CLASS(jbd2_handle_start_class, __entry->requested_blocks = requested_blocks; ), - TP_printk("dev %d,%d tid %lu type %u line_no %u " + TP_printk("dev %d,%d tid %u type %u line_no %u " "requested_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->requested_blocks) ); DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_start, - TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, + TP_PROTO(dev_t dev, tid_t tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks) ); DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_restart, - TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, + TP_PROTO(dev_t dev, tid_t tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks) ); TRACE_EVENT(jbd2_handle_extend, - TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, + TP_PROTO(dev_t dev, tid_t tid, unsigned int type, unsigned int line_no, int buffer_credits, int requested_blocks), @@ -184,7 +184,7 @@ TRACE_EVENT(jbd2_handle_extend, TP_STRUCT__entry( __field( dev_t, dev ) - __field( unsigned long, tid ) + __field( tid_t, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, buffer_credits ) @@ -200,7 +200,7 @@ TRACE_EVENT(jbd2_handle_extend, __entry->requested_blocks = requested_blocks; ), - TP_printk("dev %d,%d tid %lu type %u line_no %u " + TP_printk("dev %d,%d tid %u type %u line_no %u " "buffer_credits %d requested_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->buffer_credits, @@ -208,7 +208,7 @@ TRACE_EVENT(jbd2_handle_extend, ); TRACE_EVENT(jbd2_handle_stats, - TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, + TP_PROTO(dev_t dev, tid_t tid, unsigned int type, unsigned int line_no, int interval, int sync, int requested_blocks, int dirtied_blocks), @@ -217,7 +217,7 @@ TRACE_EVENT(jbd2_handle_stats, TP_STRUCT__entry( __field( dev_t, dev ) - __field( unsigned long, tid ) + __field( tid_t, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, interval ) @@ -237,7 +237,7 @@ TRACE_EVENT(jbd2_handle_stats, __entry->dirtied_blocks = dirtied_blocks; ), - TP_printk("dev %d,%d tid %lu type %u line_no %u interval %d " + TP_printk("dev %d,%d tid %u type %u line_no %u interval %d " "sync %d requested_blocks %d dirtied_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->interval, @@ -246,14 +246,14 @@ TRACE_EVENT(jbd2_handle_stats, ); TRACE_EVENT(jbd2_run_stats, - TP_PROTO(dev_t dev, unsigned long tid, + TP_PROTO(dev_t dev, tid_t tid, struct transaction_run_stats_s *stats), TP_ARGS(dev, tid, stats), TP_STRUCT__entry( __field( dev_t, dev ) - __field( unsigned long, tid ) + __field( tid_t, tid ) __field( unsigned long, wait ) __field( unsigned long, request_delay ) __field( unsigned long, running ) @@ -279,7 +279,7 @@ TRACE_EVENT(jbd2_run_stats, __entry->blocks_logged = stats->rs_blocks_logged; ), - TP_printk("dev %d,%d tid %lu wait %u request_delay %u running %u " + TP_printk("dev %d,%d tid %u wait %u request_delay %u running %u " "locked %u flushing %u logging %u handle_count %u " "blocks %u blocks_logged %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, @@ -294,14 +294,14 @@ TRACE_EVENT(jbd2_run_stats, ); TRACE_EVENT(jbd2_checkpoint_stats, - TP_PROTO(dev_t dev, unsigned long tid, + TP_PROTO(dev_t dev, tid_t tid, struct transaction_chp_stats_s *stats), TP_ARGS(dev, tid, stats), TP_STRUCT__entry( __field( dev_t, dev ) - __field( unsigned long, tid ) + __field( tid_t, tid ) __field( unsigned long, chp_time ) __field( __u32, forced_to_close ) __field( __u32, written ) @@ -317,7 +317,7 @@ TRACE_EVENT(jbd2_checkpoint_stats, __entry->dropped = stats->cs_dropped; ), - TP_printk("dev %d,%d tid %lu chp_time %u forced_to_close %u " + TP_printk("dev %d,%d tid %u chp_time %u forced_to_close %u " "written %u dropped %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->chp_time), From e918762f8a08c0b32375afc5680b93e2bf1cbb11 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 10 Oct 2022 07:44:13 -0400 Subject: [PATCH 0697/4345] arm64: dts: qcom: sdm845-db845c: correct SPI2 pins drive strength commit 9905370560d9c29adc15f4937c5a0c0dac05f0b4 upstream. The pin configuration (done with generic pin controller helpers and as expressed by bindings) requires children nodes with either: 1. "pins" property and the actual configuration, 2. another set of nodes with above point. The qup_spi2_default pin configuration uses alreaady the second method with a "pinmux" child, so configure drive-strength similarly in "pinconf". Otherwise the PIN drive strength would not be applied. Fixes: 8d23a0040475 ("arm64: dts: qcom: db845c: add Low speed expansion i2c and spi nodes") Cc: Signed-off-by: Krzysztof Kozlowski Reviewed-by: Douglas Anderson Reviewed-by: Neil Armstrong Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221010114417.29859-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/qcom/sdm845-db845c.dts | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index 96d36b38f269..c6691bdc8100 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -1045,7 +1045,10 @@ /* PINCTRL - additions to nodes defined in sdm845.dtsi */ &qup_spi2_default { - drive-strength = <16>; + pinconf { + pins = "gpio27", "gpio28", "gpio29", "gpio30"; + drive-strength = <16>; + }; }; &qup_uart3_default{ From c0aa6e6ab08d991765f8b1c986bf654513859453 Mon Sep 17 00:00:00 2001 From: Wenchao Chen Date: Wed, 7 Dec 2022 13:19:09 +0800 Subject: [PATCH 0698/4345] mmc: sdhci-sprd: Disable CLK_AUTO when the clock is less than 400K commit ff874dbc4f868af128b412a9bd92637103cf11d7 upstream. When the clock is less than 400K, some SD cards fail to initialize because CLK_AUTO is enabled. Fixes: fb8bd90f83c4 ("mmc: sdhci-sprd: Add Spreadtrum's initial host controller") Signed-off-by: Wenchao Chen Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221207051909.32126-1-wenchao.chen@unisoc.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/sdhci-sprd.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 110ee0c804c8..540ebccaa9a3 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -224,13 +224,15 @@ static inline void _sdhci_sprd_set_clock(struct sdhci_host *host, div = ((div & 0x300) >> 2) | ((div & 0xFF) << 8); sdhci_enable_clk(host, div); - /* enable auto gate sdhc_enable_auto_gate */ - val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); - mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | - SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; - if (mask != (val & mask)) { - val |= mask; - sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); + /* Enable CLK_AUTO when the clock is greater than 400K. */ + if (clk > 400000) { + val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); + mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | + SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; + if (mask != (val & mask)) { + val |= mask; + sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); + } } } From 0061ab5153fb8bc574b44fbb773680d0ede48c9c Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Wed, 14 Dec 2022 15:05:08 -0800 Subject: [PATCH 0699/4345] btrfs: fix resolving backrefs for inline extent followed by prealloc commit 560840afc3e63bbe5d9c5ef6b2ecf8f3589adff6 upstream. If a file consists of an inline extent followed by a regular or prealloc extent, then a legitimate attempt to resolve a logical address in the non-inline region will result in add_all_parents reading the invalid offset field of the inline extent. If the inline extent item is placed in the leaf eb s.t. it is the first item, attempting to access the offset field will not only be meaningless, it will go past the end of the eb and cause this panic: [17.626048] BTRFS warning (device dm-2): bad eb member end: ptr 0x3fd4 start 30834688 member offset 16377 size 8 [17.631693] general protection fault, probably for non-canonical address 0x5088000000000: 0000 [#1] SMP PTI [17.635041] CPU: 2 PID: 1267 Comm: btrfs Not tainted 5.12.0-07246-g75175d5adc74-dirty #199 [17.637969] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [17.641995] RIP: 0010:btrfs_get_64+0xe7/0x110 [17.649890] RSP: 0018:ffffc90001f73a08 EFLAGS: 00010202 [17.651652] RAX: 0000000000000001 RBX: ffff88810c42d000 RCX: 0000000000000000 [17.653921] RDX: 0005088000000000 RSI: ffffc90001f73a0f RDI: 0000000000000001 [17.656174] RBP: 0000000000000ff9 R08: 0000000000000007 R09: c0000000fffeffff [17.658441] R10: ffffc90001f73790 R11: ffffc90001f73788 R12: ffff888106afe918 [17.661070] R13: 0000000000003fd4 R14: 0000000000003f6f R15: cdcdcdcdcdcdcdcd [17.663617] FS: 00007f64e7627d80(0000) GS:ffff888237c80000(0000) knlGS:0000000000000000 [17.666525] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [17.668664] CR2: 000055d4a39152e8 CR3: 000000010c596002 CR4: 0000000000770ee0 [17.671253] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [17.673634] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [17.676034] PKRU: 55555554 [17.677004] Call Trace: [17.677877] add_all_parents+0x276/0x480 [17.679325] find_parent_nodes+0xfae/0x1590 [17.680771] btrfs_find_all_leafs+0x5e/0xa0 [17.682217] iterate_extent_inodes+0xce/0x260 [17.683809] ? btrfs_inode_flags_to_xflags+0x50/0x50 [17.685597] ? iterate_inodes_from_logical+0xa1/0xd0 [17.687404] iterate_inodes_from_logical+0xa1/0xd0 [17.689121] ? btrfs_inode_flags_to_xflags+0x50/0x50 [17.691010] btrfs_ioctl_logical_to_ino+0x131/0x190 [17.692946] btrfs_ioctl+0x104a/0x2f60 [17.694384] ? selinux_file_ioctl+0x182/0x220 [17.695995] ? __x64_sys_ioctl+0x84/0xc0 [17.697394] __x64_sys_ioctl+0x84/0xc0 [17.698697] do_syscall_64+0x33/0x40 [17.700017] entry_SYSCALL_64_after_hwframe+0x44/0xae [17.701753] RIP: 0033:0x7f64e72761b7 [17.709355] RSP: 002b:00007ffefb067f58 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [17.712088] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f64e72761b7 [17.714667] RDX: 00007ffefb067fb0 RSI: 00000000c0389424 RDI: 0000000000000003 [17.717386] RBP: 00007ffefb06d188 R08: 000055d4a390d2b0 R09: 00007f64e7340a60 [17.719938] R10: 0000000000000231 R11: 0000000000000246 R12: 0000000000000001 [17.722383] R13: 0000000000000000 R14: 00000000c0389424 R15: 000055d4a38fd2a0 [17.724839] Modules linked in: Fix the bug by detecting the inline extent item in add_all_parents and skipping to the next extent item. CC: stable@vger.kernel.org # 4.9+ Reviewed-by: Qu Wenruo Signed-off-by: Boris Burkov Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/backref.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 7208ba22e734..d2f77b1242a1 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -432,6 +432,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, u64 wanted_disk_byte = ref->wanted_disk_byte; u64 count = 0; u64 data_offset; + u8 type; if (level != 0) { eb = path->nodes[level]; @@ -486,6 +487,9 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, continue; } fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); + type = btrfs_file_extent_type(eb, fi); + if (type == BTRFS_FILE_EXTENT_INLINE) + goto next; disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); data_offset = btrfs_file_extent_offset(eb, fi); From 8546f11c42bdf78faf2db7cfd9c6480297a0a497 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 8 Nov 2022 13:37:55 +0100 Subject: [PATCH 0700/4345] ARM: ux500: do not directly dereference __iomem commit 65b0e307a1a9193571db12910f382f84195a3d29 upstream. Sparse reports that calling add_device_randomness() on `uid` is a violation of address spaces. And indeed the next usage uses readl() properly, but that was left out when passing it toadd_device_ randomness(). So instead copy the whole thing to the stack first. Fixes: 4040d10a3d44 ("ARM: ux500: add DB serial number to entropy pool") Cc: Linus Walleij Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/202210230819.loF90KDh-lkp@intel.com/ Reported-by: kernel test robot Signed-off-by: Jason A. Donenfeld Link: https://lore.kernel.org/r/20221108123755.207438-1-Jason@zx2c4.com Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/soc/ux500/ux500-soc-id.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/soc/ux500/ux500-soc-id.c b/drivers/soc/ux500/ux500-soc-id.c index a9472e0e5d61..27d6e25a0115 100644 --- a/drivers/soc/ux500/ux500-soc-id.c +++ b/drivers/soc/ux500/ux500-soc-id.c @@ -167,20 +167,18 @@ ATTRIBUTE_GROUPS(ux500_soc); static const char *db8500_read_soc_id(struct device_node *backupram) { void __iomem *base; - void __iomem *uid; const char *retstr; + u32 uid[5]; base = of_iomap(backupram, 0); if (!base) return NULL; - uid = base + 0x1fc0; + memcpy_fromio(uid, base + 0x1fc0, sizeof(uid)); /* Throw these device-specific numbers into the entropy pool */ - add_device_randomness(uid, 0x14); + add_device_randomness(uid, sizeof(uid)); retstr = kasprintf(GFP_KERNEL, "%08x%08x%08x%08x%08x", - readl((u32 *)uid+0), - readl((u32 *)uid+1), readl((u32 *)uid+2), - readl((u32 *)uid+3), readl((u32 *)uid+4)); + uid[0], uid[1], uid[2], uid[3], uid[4]); iounmap(base); return retstr; } From 12576d2ebf655a43d57b71137ed49721a405179c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 30 Sep 2022 21:20:37 +0200 Subject: [PATCH 0701/4345] arm64: dts: qcom: sdm850-lenovo-yoga-c630: correct I2C12 pins drive strength commit fd49776d8f458bba5499384131eddc0b8bcaf50c upstream. The pin configuration (done with generic pin controller helpers and as expressed by bindings) requires children nodes with either: 1. "pins" property and the actual configuration, 2. another set of nodes with above point. The qup_i2c12_default pin configuration used second method - with a "pinmux" child. Fixes: 44acee207844 ("arm64: dts: qcom: Add Lenovo Yoga C630") Cc: Signed-off-by: Krzysztof Kozlowski Tested-by: Steev Klimaszewski Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220930192039.240486-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index e080c317b5e3..4d67f4982738 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -322,8 +322,10 @@ }; &qup_i2c12_default { - drive-strength = <2>; - bias-disable; + pinmux { + drive-strength = <2>; + bias-disable; + }; }; &qup_uart6_default { From d1d73c303458a148f8b77fca99aa71074c69eb49 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 9 Sep 2022 12:39:01 +0200 Subject: [PATCH 0702/4345] selftests: Use optional USERCFLAGS and USERLDFLAGS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit de3ee3f63400a23954e7c1ad1cb8c20f29ab6fe3 upstream. This change enables to extend CFLAGS and LDFLAGS from command line, e.g. to extend compiler checks: make USERCFLAGS=-Werror USERLDFLAGS=-static USERCFLAGS and USERLDFLAGS are documented in Documentation/kbuild/makefiles.rst and Documentation/kbuild/kbuild.rst This should be backported (down to 5.10) to improve previous kernel versions testing as well. Cc: Shuah Khan Cc: stable@vger.kernel.org Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20220909103901.1503436-1-mic@digikod.net Signed-off-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/lib.mk | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index b7217b5251f5..56e360e019ec 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -128,6 +128,11 @@ endef clean: $(CLEAN) +# Enables to extend CFLAGS and LDFLAGS from command line, e.g. +# make USERCFLAGS=-Werror USERLDFLAGS=-static +CFLAGS += $(USERCFLAGS) +LDFLAGS += $(USERLDFLAGS) + # When make O= with kselftest target from main level # the following aren't defined. # From cea018aaf7218a50bdbf17540b311e6b2982d883 Mon Sep 17 00:00:00 2001 From: Kant Fan Date: Tue, 25 Oct 2022 15:21:09 +0800 Subject: [PATCH 0703/4345] PM/devfreq: governor: Add a private governor_data for governor commit 5fdded8448924e3631d466eea499b11606c43640 upstream. The member void *data in the structure devfreq can be overwrite by governor_userspace. For example: 1. The device driver assigned the devfreq governor to simple_ondemand by the function devfreq_add_device() and init the devfreq member void *data to a pointer of a static structure devfreq_simple_ondemand_data by the function devfreq_add_device(). 2. The user changed the devfreq governor to userspace by the command "echo userspace > /sys/class/devfreq/.../governor". 3. The governor userspace alloced a dynamic memory for the struct userspace_data and assigend the member void *data of devfreq to this memory by the function userspace_init(). 4. The user changed the devfreq governor back to simple_ondemand by the command "echo simple_ondemand > /sys/class/devfreq/.../governor". 5. The governor userspace exited and assigned the member void *data in the structure devfreq to NULL by the function userspace_exit(). 6. The governor simple_ondemand fetched the static information of devfreq_simple_ondemand_data in the function devfreq_simple_ondemand_func() but the member void *data of devfreq was assigned to NULL by the function userspace_exit(). 7. The information of upthreshold and downdifferential is lost and the governor simple_ondemand can't work correctly. The member void *data in the structure devfreq is designed for a static pointer used in a governor and inited by the function devfreq_add_device(). This patch add an element named governor_data in the devfreq structure which can be used by a governor(E.g userspace) who want to assign a private data to do some private things. Fixes: ce26c5bb9569 ("PM / devfreq: Add basic governors") Cc: stable@vger.kernel.org # 5.10+ Reviewed-by: Chanwoo Choi Acked-by: MyungJoo Ham Signed-off-by: Kant Fan Signed-off-by: Chanwoo Choi Signed-off-by: Greg Kroah-Hartman --- drivers/devfreq/devfreq.c | 6 ++---- drivers/devfreq/governor_userspace.c | 12 ++++++------ include/linux/devfreq.h | 7 ++++--- 3 files changed, 12 insertions(+), 13 deletions(-) diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 829128c0cc68..c6f460550f5e 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -740,8 +740,7 @@ static void devfreq_dev_release(struct device *dev) * @dev: the device to add devfreq feature. * @profile: device-specific profile to run devfreq. * @governor_name: name of the policy to choose frequency. - * @data: private data for the governor. The devfreq framework does not - * touch this value. + * @data: devfreq driver pass to governors, governor should not change it. */ struct devfreq *devfreq_add_device(struct device *dev, struct devfreq_dev_profile *profile, @@ -953,8 +952,7 @@ static void devm_devfreq_dev_release(struct device *dev, void *res) * @dev: the device to add devfreq feature. * @profile: device-specific profile to run devfreq. * @governor_name: name of the policy to choose frequency. - * @data: private data for the governor. The devfreq framework does not - * touch this value. + * @data: devfreq driver pass to governors, governor should not change it. * * This function manages automatically the memory of devfreq device using device * resource management and simplify the free operation for memory of devfreq diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c index 0fd6c4851071..8a9cf8220808 100644 --- a/drivers/devfreq/governor_userspace.c +++ b/drivers/devfreq/governor_userspace.c @@ -21,7 +21,7 @@ struct userspace_data { static int devfreq_userspace_func(struct devfreq *df, unsigned long *freq) { - struct userspace_data *data = df->data; + struct userspace_data *data = df->governor_data; if (data->valid) *freq = data->user_frequency; @@ -40,7 +40,7 @@ static ssize_t store_freq(struct device *dev, struct device_attribute *attr, int err = 0; mutex_lock(&devfreq->lock); - data = devfreq->data; + data = devfreq->governor_data; sscanf(buf, "%lu", &wanted); data->user_frequency = wanted; @@ -60,7 +60,7 @@ static ssize_t show_freq(struct device *dev, struct device_attribute *attr, int err = 0; mutex_lock(&devfreq->lock); - data = devfreq->data; + data = devfreq->governor_data; if (data->valid) err = sprintf(buf, "%lu\n", data->user_frequency); @@ -91,7 +91,7 @@ static int userspace_init(struct devfreq *devfreq) goto out; } data->valid = false; - devfreq->data = data; + devfreq->governor_data = data; err = sysfs_create_group(&devfreq->dev.kobj, &dev_attr_group); out: @@ -107,8 +107,8 @@ static void userspace_exit(struct devfreq *devfreq) if (devfreq->dev.kobj.sd) sysfs_remove_group(&devfreq->dev.kobj, &dev_attr_group); - kfree(devfreq->data); - devfreq->data = NULL; + kfree(devfreq->governor_data); + devfreq->governor_data = NULL; } static int devfreq_userspace_handler(struct devfreq *devfreq, diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 121a2430d7f7..fc4c7ad49cee 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -146,8 +146,8 @@ struct devfreq_stats { * @work: delayed work for load monitoring. * @previous_freq: previously configured frequency value. * @last_status: devfreq user device info, performance statistics - * @data: Private data of the governor. The devfreq framework does not - * touch this. + * @data: devfreq driver pass to governors, governor should not change it. + * @governor_data: private data for governors, devfreq core doesn't touch it. * @user_min_freq_req: PM QoS minimum frequency request from user (via sysfs) * @user_max_freq_req: PM QoS maximum frequency request from user (via sysfs) * @scaling_min_freq: Limit minimum frequency requested by OPP interface @@ -183,7 +183,8 @@ struct devfreq { unsigned long previous_freq; struct devfreq_dev_status last_status; - void *data; /* private data for governors */ + void *data; + void *governor_data; struct dev_pm_qos_request user_min_freq_req; struct dev_pm_qos_request user_max_freq_req; From e379b88a8f8cffc99b318e028705ed9e3da0e1e0 Mon Sep 17 00:00:00 2001 From: Yongqiang Liu Date: Thu, 10 Nov 2022 14:23:07 +0000 Subject: [PATCH 0704/4345] cpufreq: Init completion before kobject_init_and_add() commit 5c51054896bcce1d33d39fead2af73fec24f40b6 upstream. In cpufreq_policy_alloc(), it will call uninitialed completion in cpufreq_sysfs_release() when kobject_init_and_add() fails. And that will cause a crash such as the following page fault in complete: BUG: unable to handle page fault for address: fffffffffffffff8 [..] RIP: 0010:complete+0x98/0x1f0 [..] Call Trace: kobject_put+0x1be/0x4c0 cpufreq_online.cold+0xee/0x1fd cpufreq_add_dev+0x183/0x1e0 subsys_interface_register+0x3f5/0x4e0 cpufreq_register_driver+0x3b7/0x670 acpi_cpufreq_init+0x56c/0x1000 [acpi_cpufreq] do_one_initcall+0x13d/0x780 do_init_module+0x1c3/0x630 load_module+0x6e67/0x73b0 __do_sys_finit_module+0x181/0x240 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 4ebe36c94aed ("cpufreq: Fix kobject memleak") Signed-off-by: Yongqiang Liu Acked-by: Viresh Kumar Cc: 5.2+ # 5.2+ Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/cpufreq/cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 30dafe8fc505..58342390966b 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1211,6 +1211,7 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL)) goto err_free_rcpumask; + init_completion(&policy->kobj_unregister); ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, cpufreq_global_kobject, "policy%u", cpu); if (ret) { @@ -1249,7 +1250,6 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu) init_rwsem(&policy->rwsem); spin_lock_init(&policy->transition_lock); init_waitqueue_head(&policy->transition_wait); - init_completion(&policy->kobj_unregister); INIT_WORK(&policy->update, handle_update); policy->cpu = cpu; From 2437b06223422aa8d92a9fa1f582465d388bc841 Mon Sep 17 00:00:00 2001 From: Philipp Jungkamp Date: Mon, 5 Dec 2022 17:37:13 +0100 Subject: [PATCH 0705/4345] ALSA: patch_realtek: Fix Dell Inspiron Plus 16 [ Upstream commit 2912cdda734d9136615ed05636d9fcbca2a7a3c5 ] The Dell Inspiron Plus 16, in both laptop and 2in1 form factor, has top speakers connected on NID 0x17, which the codec reports as unconnected. These speakers should be connected to the DAC on NID 0x03. Signed-off-by: Philipp Jungkamp Link: https://lore.kernel.org/r/20221205163713.7476-1-p.jungkamp@gmx.net Signed-off-by: Takashi Iwai Stable-dep-of: a4517c4f3423 ("ALSA: hda/realtek: Apply dual codec fixup for Dell Latitude laptops") Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 37 +++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index e0bca0b029ed..72d6456bd1eb 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6654,6 +6654,34 @@ static void alc256_fixup_mic_no_presence_and_resume(struct hda_codec *codec, } } +static void alc295_fixup_dell_inspiron_top_speakers(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + static const struct hda_pintbl pincfgs[] = { + { 0x14, 0x90170151 }, + { 0x17, 0x90170150 }, + { } + }; + static const hda_nid_t conn[] = { 0x02, 0x03 }; + static const hda_nid_t preferred_pairs[] = { + 0x14, 0x02, + 0x17, 0x03, + 0x21, 0x02, + 0 + }; + struct alc_spec *spec = codec->spec; + + alc_fixup_no_shutup(codec, fix, action); + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + snd_hda_apply_pincfgs(codec, pincfgs); + snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn); + spec->gen.preferred_dacs = preferred_pairs; + break; + } +} + enum { ALC269_FIXUP_GPIO2, ALC269_FIXUP_SONY_VAIO, @@ -6884,6 +6912,7 @@ enum { ALC285_FIXUP_LEGION_Y9000X_SPEAKERS, ALC285_FIXUP_LEGION_Y9000X_AUTOMUTE, ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED, + ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -8704,6 +8733,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC285_FIXUP_HP_MUTE_LED, }, + [ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc295_fixup_dell_inspiron_top_speakers, + .chained = true, + .chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8803,6 +8838,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0a9e, "Dell Latitude 5430", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0b19, "Dell XPS 15 9520", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), + SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), From d9fa243ab26ccc7c9965f79e2c8557acde2e5d10 Mon Sep 17 00:00:00 2001 From: Chris Chiu Date: Mon, 26 Dec 2022 19:43:03 +0800 Subject: [PATCH 0706/4345] ALSA: hda/realtek: Apply dual codec fixup for Dell Latitude laptops [ Upstream commit a4517c4f3423c7c448f2c359218f97c1173523a1 ] The Dell Latiture 3340/3440/3540 laptops with Realtek ALC3204 have dual codecs and need the ALC1220_FIXUP_GB_DUAL_CODECS to fix the conflicts of Master controls. The existing headset mic fixup for Dell is also required to enable the jack sense and the headset mic. Introduce a new fixup to fix the dual codec and headset mic issues for particular Dell laptops since other old Dell laptops with the same codec configuration are already well handled by the fixup in alc269_fallback_pin_fixup_tbl[]. Signed-off-by: Chris Chiu Cc: Link: https://lore.kernel.org/r/20221226114303.4027500-1-chris.chiu@canonical.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 72d6456bd1eb..99e121f66d21 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6913,6 +6913,7 @@ enum { ALC285_FIXUP_LEGION_Y9000X_AUTOMUTE, ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED, ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS, + ALC236_FIXUP_DELL_DUAL_CODECS, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -8739,6 +8740,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, }, + [ALC236_FIXUP_DELL_DUAL_CODECS] = { + .type = HDA_FIXUP_PINS, + .v.func = alc1220_fixup_gb_dual_codecs, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8840,6 +8847,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), + SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), From b45e77b79215405bd039a690f5b06cc03e8ed27d Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 30 Nov 2022 13:26:32 -0500 Subject: [PATCH 0707/4345] dm cache: Fix ABBA deadlock between shrink_slab and dm_cache_metadata_abort commit 352b837a5541690d4f843819028cf2b8be83d424 upstream. Same ABBA deadlock pattern fixed in commit 4b60f452ec51 ("dm thin: Fix ABBA deadlock between shrink_slab and dm_pool_abort_metadata") to DM-cache's metadata. Reported-by: Zhihao Cheng Cc: stable@vger.kernel.org Fixes: 028ae9f76f29 ("dm cache: add fail io mode and needs_check flag") Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-cache-metadata.c | 54 +++++++++++++++++++++++++++++----- 1 file changed, 47 insertions(+), 7 deletions(-) diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index af6d4f898e4c..2ecd0db0f294 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -551,11 +551,13 @@ static int __create_persistent_data_objects(struct dm_cache_metadata *cmd, return r; } -static void __destroy_persistent_data_objects(struct dm_cache_metadata *cmd) +static void __destroy_persistent_data_objects(struct dm_cache_metadata *cmd, + bool destroy_bm) { dm_sm_destroy(cmd->metadata_sm); dm_tm_destroy(cmd->tm); - dm_block_manager_destroy(cmd->bm); + if (destroy_bm) + dm_block_manager_destroy(cmd->bm); } typedef unsigned long (*flags_mutator)(unsigned long); @@ -826,7 +828,7 @@ static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev, cmd2 = lookup(bdev); if (cmd2) { mutex_unlock(&table_lock); - __destroy_persistent_data_objects(cmd); + __destroy_persistent_data_objects(cmd, true); kfree(cmd); return cmd2; } @@ -874,7 +876,7 @@ void dm_cache_metadata_close(struct dm_cache_metadata *cmd) mutex_unlock(&table_lock); if (!cmd->fail_io) - __destroy_persistent_data_objects(cmd); + __destroy_persistent_data_objects(cmd, true); kfree(cmd); } } @@ -1808,14 +1810,52 @@ int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result) int dm_cache_metadata_abort(struct dm_cache_metadata *cmd) { - int r; + int r = -EINVAL; + struct dm_block_manager *old_bm = NULL, *new_bm = NULL; + + /* fail_io is double-checked with cmd->root_lock held below */ + if (unlikely(cmd->fail_io)) + return r; + + /* + * Replacement block manager (new_bm) is created and old_bm destroyed outside of + * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of + * shrinker associated with the block manager's bufio client vs cmd root_lock). + * - must take shrinker_rwsem without holding cmd->root_lock + */ + new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT, + CACHE_MAX_CONCURRENT_LOCKS); WRITE_LOCK(cmd); - __destroy_persistent_data_objects(cmd); - r = __create_persistent_data_objects(cmd, false); + if (cmd->fail_io) { + WRITE_UNLOCK(cmd); + goto out; + } + + __destroy_persistent_data_objects(cmd, false); + old_bm = cmd->bm; + if (IS_ERR(new_bm)) { + DMERR("could not create block manager during abort"); + cmd->bm = NULL; + r = PTR_ERR(new_bm); + goto out_unlock; + } + + cmd->bm = new_bm; + r = __open_or_format_metadata(cmd, false); + if (r) { + cmd->bm = NULL; + goto out_unlock; + } + new_bm = NULL; +out_unlock: if (r) cmd->fail_io = true; WRITE_UNLOCK(cmd); + dm_block_manager_destroy(old_bm); +out: + if (new_bm && !IS_ERR(new_bm)) + dm_block_manager_destroy(new_bm); return r; } From 7e37578069737b04955c71dd85db8a3bc2709eff Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 30 Nov 2022 21:31:34 +0800 Subject: [PATCH 0708/4345] dm thin: Fix ABBA deadlock between shrink_slab and dm_pool_abort_metadata MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8111964f1b8524c4bb56b02cd9c7a37725ea21fd upstream. Following concurrent processes: P1(drop cache) P2(kworker) drop_caches_sysctl_handler drop_slab shrink_slab down_read(&shrinker_rwsem) - LOCK A do_shrink_slab super_cache_scan prune_icache_sb dispose_list evict ext4_evict_inode ext4_clear_inode ext4_discard_preallocations ext4_mb_load_buddy_gfp ext4_mb_init_cache ext4_read_block_bitmap_nowait ext4_read_bh_nowait submit_bh dm_submit_bio do_worker process_deferred_bios commit metadata_operation_failed dm_pool_abort_metadata down_write(&pmd->root_lock) - LOCK B __destroy_persistent_data_objects dm_block_manager_destroy dm_bufio_client_destroy unregister_shrinker down_write(&shrinker_rwsem) thin_map | dm_thin_find_block ↓ down_read(&pmd->root_lock) --> ABBA deadlock , which triggers hung task: [ 76.974820] INFO: task kworker/u4:3:63 blocked for more than 15 seconds. [ 76.976019] Not tainted 6.1.0-rc4-00011-g8f17dd350364-dirty #910 [ 76.978521] task:kworker/u4:3 state:D stack:0 pid:63 ppid:2 [ 76.978534] Workqueue: dm-thin do_worker [ 76.978552] Call Trace: [ 76.978564] __schedule+0x6ba/0x10f0 [ 76.978582] schedule+0x9d/0x1e0 [ 76.978588] rwsem_down_write_slowpath+0x587/0xdf0 [ 76.978600] down_write+0xec/0x110 [ 76.978607] unregister_shrinker+0x2c/0xf0 [ 76.978616] dm_bufio_client_destroy+0x116/0x3d0 [ 76.978625] dm_block_manager_destroy+0x19/0x40 [ 76.978629] __destroy_persistent_data_objects+0x5e/0x70 [ 76.978636] dm_pool_abort_metadata+0x8e/0x100 [ 76.978643] metadata_operation_failed+0x86/0x110 [ 76.978649] commit+0x6a/0x230 [ 76.978655] do_worker+0xc6e/0xd90 [ 76.978702] process_one_work+0x269/0x630 [ 76.978714] worker_thread+0x266/0x630 [ 76.978730] kthread+0x151/0x1b0 [ 76.978772] INFO: task test.sh:2646 blocked for more than 15 seconds. [ 76.979756] Not tainted 6.1.0-rc4-00011-g8f17dd350364-dirty #910 [ 76.982111] task:test.sh state:D stack:0 pid:2646 ppid:2459 [ 76.982128] Call Trace: [ 76.982139] __schedule+0x6ba/0x10f0 [ 76.982155] schedule+0x9d/0x1e0 [ 76.982159] rwsem_down_read_slowpath+0x4f4/0x910 [ 76.982173] down_read+0x84/0x170 [ 76.982177] dm_thin_find_block+0x4c/0xd0 [ 76.982183] thin_map+0x201/0x3d0 [ 76.982188] __map_bio+0x5b/0x350 [ 76.982195] dm_submit_bio+0x2b6/0x930 [ 76.982202] __submit_bio+0x123/0x2d0 [ 76.982209] submit_bio_noacct_nocheck+0x101/0x3e0 [ 76.982222] submit_bio_noacct+0x389/0x770 [ 76.982227] submit_bio+0x50/0xc0 [ 76.982232] submit_bh_wbc+0x15e/0x230 [ 76.982238] submit_bh+0x14/0x20 [ 76.982241] ext4_read_bh_nowait+0xc5/0x130 [ 76.982247] ext4_read_block_bitmap_nowait+0x340/0xc60 [ 76.982254] ext4_mb_init_cache+0x1ce/0xdc0 [ 76.982259] ext4_mb_load_buddy_gfp+0x987/0xfa0 [ 76.982263] ext4_discard_preallocations+0x45d/0x830 [ 76.982274] ext4_clear_inode+0x48/0xf0 [ 76.982280] ext4_evict_inode+0xcf/0xc70 [ 76.982285] evict+0x119/0x2b0 [ 76.982290] dispose_list+0x43/0xa0 [ 76.982294] prune_icache_sb+0x64/0x90 [ 76.982298] super_cache_scan+0x155/0x210 [ 76.982303] do_shrink_slab+0x19e/0x4e0 [ 76.982310] shrink_slab+0x2bd/0x450 [ 76.982317] drop_slab+0xcc/0x1a0 [ 76.982323] drop_caches_sysctl_handler+0xb7/0xe0 [ 76.982327] proc_sys_call_handler+0x1bc/0x300 [ 76.982331] proc_sys_write+0x17/0x20 [ 76.982334] vfs_write+0x3d3/0x570 [ 76.982342] ksys_write+0x73/0x160 [ 76.982347] __x64_sys_write+0x1e/0x30 [ 76.982352] do_syscall_64+0x35/0x80 [ 76.982357] entry_SYSCALL_64_after_hwframe+0x63/0xcd Function metadata_operation_failed() is called when operations failed on dm pool metadata, dm pool will destroy and recreate metadata. So, shrinker will be unregistered and registered, which could down write shrinker_rwsem under pmd_write_lock. Fix it by allocating dm_block_manager before locking pmd->root_lock and destroying old dm_block_manager after unlocking pmd->root_lock, then old dm_block_manager is replaced with new dm_block_manager under pmd->root_lock. So, shrinker register/unregister could be done without holding pmd->root_lock. Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216676 Cc: stable@vger.kernel.org #v5.2+ Fixes: e49e582965b3 ("dm thin: add read only and fail io modes") Signed-off-by: Zhihao Cheng Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-thin-metadata.c | 51 +++++++++++++++++++++++++++++------ 1 file changed, 43 insertions(+), 8 deletions(-) diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 842d79e5ea3a..d1e0ae06f04d 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -753,13 +753,15 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f return r; } -static void __destroy_persistent_data_objects(struct dm_pool_metadata *pmd) +static void __destroy_persistent_data_objects(struct dm_pool_metadata *pmd, + bool destroy_bm) { dm_sm_destroy(pmd->data_sm); dm_sm_destroy(pmd->metadata_sm); dm_tm_destroy(pmd->nb_tm); dm_tm_destroy(pmd->tm); - dm_block_manager_destroy(pmd->bm); + if (destroy_bm) + dm_block_manager_destroy(pmd->bm); } static int __begin_transaction(struct dm_pool_metadata *pmd) @@ -966,7 +968,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd) } pmd_write_unlock(pmd); if (!pmd->fail_io) - __destroy_persistent_data_objects(pmd); + __destroy_persistent_data_objects(pmd, true); kfree(pmd); return 0; @@ -1873,19 +1875,52 @@ static void __set_abort_with_changes_flags(struct dm_pool_metadata *pmd) int dm_pool_abort_metadata(struct dm_pool_metadata *pmd) { int r = -EINVAL; + struct dm_block_manager *old_bm = NULL, *new_bm = NULL; + + /* fail_io is double-checked with pmd->root_lock held below */ + if (unlikely(pmd->fail_io)) + return r; + + /* + * Replacement block manager (new_bm) is created and old_bm destroyed outside of + * pmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of + * shrinker associated with the block manager's bufio client vs pmd root_lock). + * - must take shrinker_rwsem without holding pmd->root_lock + */ + new_bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT, + THIN_MAX_CONCURRENT_LOCKS); pmd_write_lock(pmd); - if (pmd->fail_io) + if (pmd->fail_io) { + pmd_write_unlock(pmd); goto out; + } __set_abort_with_changes_flags(pmd); - __destroy_persistent_data_objects(pmd); - r = __create_persistent_data_objects(pmd, false); + __destroy_persistent_data_objects(pmd, false); + old_bm = pmd->bm; + if (IS_ERR(new_bm)) { + DMERR("could not create block manager during abort"); + pmd->bm = NULL; + r = PTR_ERR(new_bm); + goto out_unlock; + } + + pmd->bm = new_bm; + r = __open_or_format_metadata(pmd, false); + if (r) { + pmd->bm = NULL; + goto out_unlock; + } + new_bm = NULL; +out_unlock: if (r) pmd->fail_io = true; - -out: pmd_write_unlock(pmd); + dm_block_manager_destroy(old_bm); +out: + if (new_bm && !IS_ERR(new_bm)) + dm_block_manager_destroy(new_bm); return r; } From 94f01ecc2aa0be992865acc80ebb6701f731f955 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Thu, 8 Dec 2022 22:28:02 +0800 Subject: [PATCH 0709/4345] dm thin: Use last transaction's pmd->root when commit failed commit 7991dbff6849f67e823b7cc0c15e5a90b0549b9f upstream. Recently we found a softlock up problem in dm thin pool btree lookup code due to corrupted metadata: Kernel panic - not syncing: softlockup: hung tasks CPU: 7 PID: 2669225 Comm: kworker/u16:3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) Workqueue: dm-thin do_worker [dm_thin_pool] Call Trace: dump_stack+0x9c/0xd3 panic+0x35d/0x6b9 watchdog_timer_fn.cold+0x16/0x25 __run_hrtimer+0xa2/0x2d0 RIP: 0010:__relink_lru+0x102/0x220 [dm_bufio] __bufio_new+0x11f/0x4f0 [dm_bufio] new_read+0xa3/0x1e0 [dm_bufio] dm_bm_read_lock+0x33/0xd0 [dm_persistent_data] ro_step+0x63/0x100 [dm_persistent_data] btree_lookup_raw.constprop.0+0x44/0x220 [dm_persistent_data] dm_btree_lookup+0x16f/0x210 [dm_persistent_data] dm_thin_find_block+0x12c/0x210 [dm_thin_pool] __process_bio_read_only+0xc5/0x400 [dm_thin_pool] process_thin_deferred_bios+0x1a4/0x4a0 [dm_thin_pool] process_one_work+0x3c5/0x730 Following process may generate a broken btree mixed with fresh and stale btree nodes, which could get dm thin trapped in an infinite loop while looking up data block: Transaction 1: pmd->root = A, A->B->C // One path in btree pmd->root = X, X->Y->Z // Copy-up Transaction 2: X,Z is updated on disk, Y write failed. // Commit failed, dm thin becomes read-only. process_bio_read_only dm_thin_find_block __find_block dm_btree_lookup(pmd->root) The pmd->root points to a broken btree, Y may contain stale node pointing to any block, for example X, which gets dm thin trapped into a dead loop while looking up Z. Fix this by setting pmd->root in __open_metadata(), so that dm thin will use the last transaction's pmd->root if commit failed. Fetch a reproducer in [Link]. Linke: https://bugzilla.kernel.org/show_bug.cgi?id=216790 Cc: stable@vger.kernel.org Fixes: 991d9fa02da0 ("dm: add thin provisioning target") Signed-off-by: Zhihao Cheng Acked-by: Joe Thornber Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-thin-metadata.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index d1e0ae06f04d..8f4d149bb99d 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -701,6 +701,15 @@ static int __open_metadata(struct dm_pool_metadata *pmd) goto bad_cleanup_data_sm; } + /* + * For pool metadata opening process, root setting is redundant + * because it will be set again in __begin_transaction(). But dm + * pool aborting process really needs to get last transaction's + * root to avoid accessing broken btree. + */ + pmd->root = le64_to_cpu(disk_super->data_mapping_root); + pmd->details_root = le64_to_cpu(disk_super->device_details_root); + __setup_btree_details(pmd); dm_bm_unlock(sblock); From c84d1ca2285b40287fe0f70f4b60debc2ab21bef Mon Sep 17 00:00:00 2001 From: Luo Meng Date: Wed, 30 Nov 2022 10:09:45 +0800 Subject: [PATCH 0710/4345] dm thin: resume even if in FAIL mode commit 19eb1650afeb1aa86151f61900e9e5f1de5d8d02 upstream. If a thinpool set fail_io while suspending, resume will fail with: device-mapper: resume ioctl on vg-thinpool failed: Invalid argument The thin-pool also can't be removed if an in-flight bio is in the deferred list. This can be easily reproduced using: echo "offline" > /sys/block/sda/device/state dd if=/dev/zero of=/dev/mapper/thin bs=4K count=1 dmsetup suspend /dev/mapper/pool mkfs.ext4 /dev/mapper/thin dmsetup resume /dev/mapper/pool The root cause is maybe_resize_data_dev() will check fail_io and return error before called dm_resume. Fix this by adding FAIL mode check at the end of pool_preresume(). Cc: stable@vger.kernel.org Fixes: da105ed5fd7e ("dm thin metadata: introduce dm_pool_abort_metadata") Signed-off-by: Luo Meng Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-thin.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index a196d7cb51bd..137881179a3d 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3566,20 +3566,28 @@ static int pool_preresume(struct dm_target *ti) */ r = bind_control_target(pool, ti); if (r) - return r; + goto out; r = maybe_resize_data_dev(ti, &need_commit1); if (r) - return r; + goto out; r = maybe_resize_metadata_dev(ti, &need_commit2); if (r) - return r; + goto out; if (need_commit1 || need_commit2) (void) commit(pool); +out: + /* + * When a thin-pool is PM_FAIL, it cannot be rebuilt if + * bio is in deferred list. Therefore need to return 0 + * to allow pool_resume() to flush IO. + */ + if (r && get_pool_mode(pool) == PM_FAIL) + r = 0; - return 0; + return r; } static void pool_suspend_active_thins(struct pool *pool) From 34fe9c2251f19786a6689149a6212c6c0de1d63b Mon Sep 17 00:00:00 2001 From: Luo Meng Date: Tue, 29 Nov 2022 10:48:47 +0800 Subject: [PATCH 0711/4345] dm thin: Fix UAF in run_timer_softirq() commit 88430ebcbc0ec637b710b947738839848c20feff upstream. When dm_resume() and dm_destroy() are concurrent, it will lead to UAF, as follows: BUG: KASAN: use-after-free in __run_timers+0x173/0x710 Write of size 8 at addr ffff88816d9490f0 by task swapper/0/0 Call Trace: dump_stack_lvl+0x73/0x9f print_report.cold+0x132/0xaa2 _raw_spin_lock_irqsave+0xcd/0x160 __run_timers+0x173/0x710 kasan_report+0xad/0x110 __run_timers+0x173/0x710 __asan_store8+0x9c/0x140 __run_timers+0x173/0x710 call_timer_fn+0x310/0x310 pvclock_clocksource_read+0xfa/0x250 kvm_clock_read+0x2c/0x70 kvm_clock_get_cycles+0xd/0x20 ktime_get+0x5c/0x110 lapic_next_event+0x38/0x50 clockevents_program_event+0xf1/0x1e0 run_timer_softirq+0x49/0x90 __do_softirq+0x16e/0x62c __irq_exit_rcu+0x1fa/0x270 irq_exit_rcu+0x12/0x20 sysvec_apic_timer_interrupt+0x8e/0xc0 One of the concurrency UAF can be shown as below: use free do_resume | __find_device_hash_cell | dm_get | atomic_inc(&md->holders) | | dm_destroy | __dm_destroy | if (!dm_suspended_md(md)) | atomic_read(&md->holders) | msleep(1) dm_resume | __dm_resume | dm_table_resume_targets | pool_resume | do_waker #add delay work | dm_put | atomic_dec(&md->holders) | | dm_table_destroy | pool_dtr | __pool_dec | __pool_destroy | destroy_workqueue | kfree(pool) # free pool time out __do_softirq run_timer_softirq # pool has already been freed This can be easily reproduced using: 1. create thin-pool 2. dmsetup suspend pool 3. dmsetup resume pool 4. dmsetup remove_all # Concurrent with 3 The root cause of this UAF bug is that dm_resume() adds timer after dm_destroy() skips cancelling the timer because of suspend status. After timeout, it will call run_timer_softirq(), however pool has already been freed. The concurrency UAF bug will happen. Therefore, cancelling timer again in __pool_destroy(). Cc: stable@vger.kernel.org Fixes: 991d9fa02da0d ("dm: add thin provisioning target") Signed-off-by: Luo Meng Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-thin.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 137881179a3d..f3c519e18a12 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2907,6 +2907,8 @@ static void __pool_destroy(struct pool *pool) dm_bio_prison_destroy(pool->prison); dm_kcopyd_client_destroy(pool->copier); + cancel_delayed_work_sync(&pool->waker); + cancel_delayed_work_sync(&pool->no_space_timeout); if (pool->wq) destroy_workqueue(pool->wq); From a506b5c92757b034034ef683e667bffc456c600b Mon Sep 17 00:00:00 2001 From: Luo Meng Date: Tue, 29 Nov 2022 10:48:50 +0800 Subject: [PATCH 0712/4345] dm integrity: Fix UAF in dm_integrity_dtr() commit f50cb2cbabd6c4a60add93d72451728f86e4791c upstream. Dm_integrity also has the same UAF problem when dm_resume() and dm_destroy() are concurrent. Therefore, cancelling timer again in dm_integrity_dtr(). Cc: stable@vger.kernel.org Fixes: 7eada909bfd7a ("dm: add integrity target") Signed-off-by: Luo Meng Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-integrity.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 2156a2d5ac70..a1c4cc48bf03 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -4388,6 +4388,8 @@ static void dm_integrity_dtr(struct dm_target *ti) BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress)); BUG_ON(!list_empty(&ic->wait_list)); + if (ic->mode == 'B') + cancel_delayed_work_sync(&ic->bitmap_flush_work); if (ic->metadata_wq) destroy_workqueue(ic->metadata_wq); if (ic->wait_wq) From 342cfd8426dff4228e6c714bcb9fc8295a2748dd Mon Sep 17 00:00:00 2001 From: Luo Meng Date: Tue, 29 Nov 2022 10:48:48 +0800 Subject: [PATCH 0713/4345] dm clone: Fix UAF in clone_dtr() commit e4b5957c6f749a501c464f92792f1c8e26b61a94 upstream. Dm_clone also has the same UAF problem when dm_resume() and dm_destroy() are concurrent. Therefore, cancelling timer again in clone_dtr(). Cc: stable@vger.kernel.org Fixes: 7431b7835f554 ("dm: add clone target") Signed-off-by: Luo Meng Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-clone-target.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index bdb255edc200..0d38ad623534 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -1966,6 +1966,7 @@ static void clone_dtr(struct dm_target *ti) mempool_exit(&clone->hydration_pool); dm_kcopyd_client_destroy(clone->kcopyd_client); + cancel_delayed_work_sync(&clone->waker); destroy_workqueue(clone->wq); hash_table_exit(clone); dm_clone_metadata_close(clone->cmd); From 2b17026685a270b2beaf1cdd9857fcedd3505c7e Mon Sep 17 00:00:00 2001 From: Luo Meng Date: Tue, 29 Nov 2022 10:48:49 +0800 Subject: [PATCH 0714/4345] dm cache: Fix UAF in destroy() commit 6a459d8edbdbe7b24db42a5a9f21e6aa9e00c2aa upstream. Dm_cache also has the same UAF problem when dm_resume() and dm_destroy() are concurrent. Therefore, cancelling timer again in destroy(). Cc: stable@vger.kernel.org Fixes: c6b4fcbad044e ("dm: add cache target") Signed-off-by: Luo Meng Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-cache-target.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 4bc453f5bbaa..52e2896cf15b 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1965,6 +1965,7 @@ static void destroy(struct cache *cache) if (cache->prison) dm_bio_prison_destroy_v2(cache->prison); + cancel_delayed_work_sync(&cache->waker); if (cache->wq) destroy_workqueue(cache->wq); From 18a489a3fda74a0eb0e68ace8131a1fc11348358 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 30 Nov 2022 14:02:47 -0500 Subject: [PATCH 0715/4345] dm cache: set needs_check flag after aborting metadata commit 6b9973861cb2e96dcd0bb0f1baddc5c034207c5c upstream. Otherwise the commit that will be aborted will be associated with the metadata objects that will be torn down. Must write needs_check flag to metadata with a reset block manager. Found through code-inspection (and compared against dm-thin.c). Cc: stable@vger.kernel.org Fixes: 028ae9f76f29 ("dm cache: add fail io mode and needs_check flag") Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-cache-target.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 52e2896cf15b..9b2aec309801 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -985,16 +985,16 @@ static void abort_transaction(struct cache *cache) if (get_cache_mode(cache) >= CM_READ_ONLY) return; - if (dm_cache_metadata_set_needs_check(cache->cmd)) { - DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name); - set_cache_mode(cache, CM_FAIL); - } - DMERR_LIMIT("%s: aborting current metadata transaction", dev_name); if (dm_cache_metadata_abort(cache->cmd)) { DMERR("%s: failed to abort metadata transaction", dev_name); set_cache_mode(cache, CM_FAIL); } + + if (dm_cache_metadata_set_needs_check(cache->cmd)) { + DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name); + set_cache_mode(cache, CM_FAIL); + } } static void metadata_operation_failed(struct cache *cache, const char *op, int r) From 0cb31bd88361edb96cfc622648717ba348f0f4dc Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Wed, 7 Dec 2022 11:51:43 +0800 Subject: [PATCH 0716/4345] tracing/hist: Fix out-of-bound write on 'action_data.var_ref_idx' commit 82470f7d9044842618c847a7166de2b7458157a7 upstream. When generate a synthetic event with many params and then create a trace action for it [1], kernel panic happened [2]. It is because that in trace_action_create() 'data->n_params' is up to SYNTH_FIELDS_MAX (current value is 64), and array 'data->var_ref_idx' keeps indices into array 'hist_data->var_refs' for each synthetic event param, but the length of 'data->var_ref_idx' is TRACING_MAP_VARS_MAX (current value is 16), so out-of-bound write happened when 'data->n_params' more than 16. In this case, 'data->match_data.event' is overwritten and eventually cause the panic. To solve the issue, adjust the length of 'data->var_ref_idx' to be SYNTH_FIELDS_MAX and add sanity checks to avoid out-of-bound write. [1] # cd /sys/kernel/tracing/ # echo "my_synth_event int v1; int v2; int v3; int v4; int v5; int v6;\ int v7; int v8; int v9; int v10; int v11; int v12; int v13; int v14;\ int v15; int v16; int v17; int v18; int v19; int v20; int v21; int v22;\ int v23; int v24; int v25; int v26; int v27; int v28; int v29; int v30;\ int v31; int v32; int v33; int v34; int v35; int v36; int v37; int v38;\ int v39; int v40; int v41; int v42; int v43; int v44; int v45; int v46;\ int v47; int v48; int v49; int v50; int v51; int v52; int v53; int v54;\ int v55; int v56; int v57; int v58; int v59; int v60; int v61; int v62;\ int v63" >> synthetic_events # echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="bash"' >> \ events/sched/sched_waking/trigger # echo "hist:keys=next_pid:onmatch(sched.sched_waking).my_synth_event(\ pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,\ pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,\ pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,pid,\ pid,pid,pid,pid,pid,pid,pid,pid,pid)" >> events/sched/sched_switch/trigger [2] BUG: unable to handle page fault for address: ffff91c900000000 PGD 61001067 P4D 61001067 PUD 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 2 PID: 322 Comm: bash Tainted: G W 6.1.0-rc8+ #229 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 RIP: 0010:strcmp+0xc/0x30 Code: 75 f7 31 d2 44 0f b6 04 16 44 88 04 11 48 83 c2 01 45 84 c0 75 ee c3 cc cc cc cc 0f 1f 00 31 c0 eb 08 48 83 c0 01 84 d2 74 13 <0f> b6 14 07 3a 14 06 74 ef 19 c0 83 c8 01 c3 cc cc cc cc 31 c3 RSP: 0018:ffff9b3b00f53c48 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffffffffba958a68 RCX: 0000000000000000 RDX: 0000000000000010 RSI: ffff91c943d33a90 RDI: ffff91c900000000 RBP: ffff91c900000000 R08: 00000018d604b529 R09: 0000000000000000 R10: ffff91c9483eddb1 R11: ffff91ca483eddab R12: ffff91c946171580 R13: ffff91c9479f0538 R14: ffff91c9457c2848 R15: ffff91c9479f0538 FS: 00007f1d1cfbe740(0000) GS:ffff91c9bdc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff91c900000000 CR3: 0000000006316000 CR4: 00000000000006e0 Call Trace: __find_event_file+0x55/0x90 action_create+0x76c/0x1060 event_hist_trigger_parse+0x146d/0x2060 ? event_trigger_write+0x31/0xd0 trigger_process_regex+0xbb/0x110 event_trigger_write+0x6b/0xd0 vfs_write+0xc8/0x3e0 ? alloc_fd+0xc0/0x160 ? preempt_count_add+0x4d/0xa0 ? preempt_count_add+0x70/0xa0 ksys_write+0x5f/0xe0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f1d1d0cf077 Code: 64 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 RSP: 002b:00007ffcebb0e568 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000143 RCX: 00007f1d1d0cf077 RDX: 0000000000000143 RSI: 00005639265aa7e0 RDI: 0000000000000001 RBP: 00005639265aa7e0 R08: 000000000000000a R09: 0000000000000142 R10: 000056392639c017 R11: 0000000000000246 R12: 0000000000000143 R13: 00007f1d1d1ae6a0 R14: 00007f1d1d1aa4a0 R15: 00007f1d1d1a98a0 Modules linked in: CR2: ffff91c900000000 ---[ end trace 0000000000000000 ]--- RIP: 0010:strcmp+0xc/0x30 Code: 75 f7 31 d2 44 0f b6 04 16 44 88 04 11 48 83 c2 01 45 84 c0 75 ee c3 cc cc cc cc 0f 1f 00 31 c0 eb 08 48 83 c0 01 84 d2 74 13 <0f> b6 14 07 3a 14 06 74 ef 19 c0 83 c8 01 c3 cc cc cc cc 31 c3 RSP: 0018:ffff9b3b00f53c48 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffffffffba958a68 RCX: 0000000000000000 RDX: 0000000000000010 RSI: ffff91c943d33a90 RDI: ffff91c900000000 RBP: ffff91c900000000 R08: 00000018d604b529 R09: 0000000000000000 R10: ffff91c9483eddb1 R11: ffff91ca483eddab R12: ffff91c946171580 R13: ffff91c9479f0538 R14: ffff91c9457c2848 R15: ffff91c9479f0538 FS: 00007f1d1cfbe740(0000) GS:ffff91c9bdc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff91c900000000 CR3: 0000000006316000 CR4: 00000000000006e0 Link: https://lore.kernel.org/linux-trace-kernel/20221207035143.2278781-1-zhengyejian1@huawei.com Cc: Cc: Cc: stable@vger.kernel.org Fixes: d380dcde9a07 ("tracing: Fix now invalid var_ref_vals assumption in trace action") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_events_hist.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 8e01ab49118d..9bf2bea373d4 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -417,7 +417,7 @@ struct action_data { * event param, and is passed to the synthetic event * invocation. */ - unsigned int var_ref_idx[TRACING_MAP_VARS_MAX]; + unsigned int var_ref_idx[SYNTH_FIELDS_MAX]; struct synth_event *synth_event; bool use_trace_keyword; char *synth_event_name; @@ -1846,7 +1846,9 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, return ref_field; } } - + /* Sanity check to avoid out-of-bound write on 'hist_data->var_refs' */ + if (hist_data->n_var_refs >= TRACING_MAP_VARS_MAX) + return NULL; ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { if (init_var_ref(ref_field, var_field, system, event_name)) { @@ -3449,6 +3451,10 @@ static int trace_action_create(struct hist_trigger_data *hist_data, lockdep_assert_held(&event_mutex); + /* Sanity check to avoid out-of-bound write on 'data->var_ref_idx' */ + if (data->n_params > SYNTH_FIELDS_MAX) + return -EINVAL; + if (data->use_trace_keyword) synth_event_name = data->synth_event_name; else From e61eacf9936441af33062c944c37ba1d1d6704e8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 20 Dec 2022 14:31:40 -0800 Subject: [PATCH 0717/4345] perf/core: Call LSM hook after copying perf_event_attr commit 0a041ebca4956292cadfb14a63ace3a9c1dcb0a3 upstream. It passes the attr struct to the security_perf_event_open() but it's not initialized yet. Fixes: da97e18458fb ("perf_event: Add support for LSM and SELinux checks") Signed-off-by: Namhyung Kim Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Joel Fernandes (Google) Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20221220223140.4020470-1-namhyung@kernel.org Signed-off-by: Greg Kroah-Hartman --- kernel/events/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 979d7946a772..d7b61116f15b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11781,12 +11781,12 @@ SYSCALL_DEFINE5(perf_event_open, if (flags & ~PERF_FLAG_ALL) return -EINVAL; - /* Do we allow access to perf_event_open(2) ? */ - err = security_perf_event_open(&attr, PERF_SECURITY_OPEN); + err = perf_copy_attr(attr_uptr, &attr); if (err) return err; - err = perf_copy_attr(attr_uptr, &attr); + /* Do we allow access to perf_event_open(2) ? */ + err = security_perf_event_open(&attr, PERF_SECURITY_OPEN); if (err) return err; From 43dd254853aa274d356bb1d3ab01a8ca880b07b0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 6 Oct 2022 00:19:56 +0000 Subject: [PATCH 0718/4345] KVM: nVMX: Inject #GP, not #UD, if "generic" VMXON CR0/CR4 check fails commit 9cc409325ddd776f6fd6293d5ce93ce1248af6e4 upstream. Inject #GP for if VMXON is attempting with a CR0/CR4 that fails the generic "is CRx valid" check, but passes the CR4.VMXE check, and do the generic checks _after_ handling the post-VMXON VM-Fail. The CR4.VMXE check, and all other #UD cases, are special pre-conditions that are enforced prior to pivoting on the current VMX mode, i.e. occur before interception if VMXON is attempted in VMX non-root mode. All other CR0/CR4 checks generate #GP and effectively have lower priority than the post-VMXON check. Per the SDM: IF (register operand) or (CR0.PE = 0) or (CR4.VMXE = 0) or ... THEN #UD; ELSIF not in VMX operation THEN IF (CPL > 0) or (in A20M mode) or (the values of CR0 and CR4 are not supported in VMX operation) THEN #GP(0); ELSIF in VMX non-root operation THEN VMexit; ELSIF CPL > 0 THEN #GP(0); ELSE VMfail("VMXON executed in VMX root operation"); FI; which, if re-written without ELSIF, yields: IF (register operand) or (CR0.PE = 0) or (CR4.VMXE = 0) or ... THEN #UD IF in VMX non-root operation THEN VMexit; IF CPL > 0 THEN #GP(0) IF in VMX operation THEN VMfail("VMXON executed in VMX root operation"); IF (in A20M mode) or (the values of CR0 and CR4 are not supported in VMX operation) THEN #GP(0); Note, KVM unconditionally forwards VMXON VM-Exits that occur in L2 to L1, i.e. there is no need to check the vCPU is not in VMX non-root mode. Add a comment to explain why unconditionally forwarding such exits is functionally correct. Reported-by: Eric Li Fixes: c7d855c2aff2 ("KVM: nVMX: Inject #UD if VMXON is attempted with incompatible CR0/CR4") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Link: https://lore.kernel.org/r/20221006001956.329314-1-seanjc@google.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx/nested.c | 44 +++++++++++++++++++++++++++++---------- 1 file changed, 33 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 498fed0dda98..f15ddf58a5bc 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4901,24 +4901,35 @@ static int handle_vmon(struct kvm_vcpu *vcpu) | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; /* - * Note, KVM cannot rely on hardware to perform the CR0/CR4 #UD checks - * that have higher priority than VM-Exit (see Intel SDM's pseudocode - * for VMXON), as KVM must load valid CR0/CR4 values into hardware while - * running the guest, i.e. KVM needs to check the _guest_ values. + * Manually check CR4.VMXE checks, KVM must force CR4.VMXE=1 to enter + * the guest and so cannot rely on hardware to perform the check, + * which has higher priority than VM-Exit (see Intel SDM's pseudocode + * for VMXON). * - * Rely on hardware for the other two pre-VM-Exit checks, !VM86 and - * !COMPATIBILITY modes. KVM may run the guest in VM86 to emulate Real - * Mode, but KVM will never take the guest out of those modes. + * Rely on hardware for the other pre-VM-Exit checks, CR0.PE=1, !VM86 + * and !COMPATIBILITY modes. For an unrestricted guest, KVM doesn't + * force any of the relevant guest state. For a restricted guest, KVM + * does force CR0.PE=1, but only to also force VM86 in order to emulate + * Real Mode, and so there's no need to check CR0.PE manually. */ - if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || - !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { + if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } /* - * CPL=0 and all other checks that are lower priority than VM-Exit must - * be checked manually. + * The CPL is checked for "not in VMX operation" and for "in VMX root", + * and has higher priority than the VM-Fail due to being post-VMXON, + * i.e. VMXON #GPs outside of VMX non-root if CPL!=0. In VMX non-root, + * VMXON causes VM-Exit and KVM unconditionally forwards VMXON VM-Exits + * from L2 to L1, i.e. there's no need to check for the vCPU being in + * VMX non-root. + * + * Forwarding the VM-Exit unconditionally, i.e. without performing the + * #UD checks (see above), is functionally ok because KVM doesn't allow + * L1 to run L2 without CR4.VMXE=0, and because KVM never modifies L2's + * CR0 or CR4, i.e. it's L2's responsibility to emulate #UDs that are + * missed by hardware due to shadowing CR0 and/or CR4. */ if (vmx_get_cpl(vcpu)) { kvm_inject_gp(vcpu, 0); @@ -4928,6 +4939,17 @@ static int handle_vmon(struct kvm_vcpu *vcpu) if (vmx->nested.vmxon) return nested_vmx_fail(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); + /* + * Invalid CR0/CR4 generates #GP. These checks are performed if and + * only if the vCPU isn't already in VMX operation, i.e. effectively + * have lower priority than the VM-Fail above. + */ + if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || + !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES) != VMXON_NEEDED_FEATURES) { kvm_inject_gp(vcpu, 0); From b677629caebb3d3fdb5f9479550ce454a2247c0b Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Tue, 29 Nov 2022 13:08:27 -0800 Subject: [PATCH 0719/4345] x86/microcode/intel: Do not retry microcode reloading on the APs commit be1b670f61443aa5d0d01782e9b8ea0ee825d018 upstream. The retries in load_ucode_intel_ap() were in place to support systems with mixed steppings. Mixed steppings are no longer supported and there is only one microcode image at a time. Any retries will simply reattempt to apply the same image over and over without making progress. [ bp: Zap the circumstantial reasoning from the commit message. ] Fixes: 06b8534cb728 ("x86/microcode: Rework microcode loading") Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221129210832.107850-3-ashok.raj@intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/microcode/intel.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 7e8e07bddd5f..1ba590e6ef7b 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -659,7 +659,6 @@ void load_ucode_intel_ap(void) else iup = &intel_ucode_patch; -reget: if (!*iup) { patch = __load_ucode_intel(&uci); if (!patch) @@ -670,12 +669,7 @@ reget: uci.mc = *iup; - if (apply_microcode_early(&uci, true)) { - /* Mixed-silicon system? Try to refetch the proper patch: */ - *iup = NULL; - - goto reget; - } + apply_microcode_early(&uci, true); } static struct microcode_intel *find_patch(struct ucode_cpu_info *uci) From 362495bf451f772db24b95bf35374338eb342a5a Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 9 Dec 2022 10:52:47 -0500 Subject: [PATCH 0720/4345] ftrace/x86: Add back ftrace_expected for ftrace bug reports commit fd3dc56253acbe9c641a66d312d8393cd55eb04c upstream. After someone reported a bug report with a failed modification due to the expected value not matching what was found, it came to my attention that the ftrace_expected is no longer set when that happens. This makes for debugging the issue a bit more difficult. Set ftrace_expected to the expected code before calling ftrace_bug, so that it shows what was expected and why it failed. Link: https://lore.kernel.org/all/CA+wXwBQ-VhK+hpBtYtyZP-NiX4g8fqRRWithFOHQW-0coQ3vLg@mail.gmail.com/ Link: https://lore.kernel.org/linux-trace-kernel/20221209105247.01d4e51d@gandalf.local.home Cc: Masami Hiramatsu Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: "x86@kernel.org" Cc: Borislav Petkov Cc: Ingo Molnar Cc: stable@vger.kernel.org Fixes: 768ae4406a5c ("x86/ftrace: Use text_poke()") Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/ftrace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d096b5a1dbeb..6d546f4426ac 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -219,7 +219,9 @@ void ftrace_replace_code(int enable) ret = ftrace_verify_code(rec->ip, old); if (ret) { + ftrace_expected = old; ftrace_bug(ret, rec); + ftrace_expected = NULL; return; } } From ff3dd2c1befe48da9eb9d4042fa3aede31156a12 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 19 Dec 2022 23:35:10 +0900 Subject: [PATCH 0721/4345] x86/kprobes: Fix kprobes instruction boudary check with CONFIG_RETHUNK commit 1993bf97992df2d560287f3c4120eda57426843d upstream. Since the CONFIG_RETHUNK and CONFIG_SLS will use INT3 for stopping speculative execution after RET instruction, kprobes always failes to check the probed instruction boundary by decoding the function body if the probed address is after such sequence. (Note that some conditional code blocks will be placed after function return, if compiler decides it is not on the hot path.) This is because kprobes expects kgdb puts the INT3 as a software breakpoint and it will replace the original instruction. But these INT3 are not such purpose, it doesn't need to recover the original instruction. To avoid this issue, kprobes checks whether the INT3 is owned by kgdb or not, and if so, stop decoding and make it fail. The other INT3 will come from CONFIG_RETHUNK/CONFIG_SLS and those can be treated as a one-byte instruction. Fixes: e463a09af2f0 ("x86: Add straight-line-speculation mitigation") Suggested-by: Peter Zijlstra Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/167146051026.1374301.392728975473572291.stgit@devnote3 Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/kprobes/core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index ee85f1b258d0..97e1d2a9898f 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -306,12 +307,15 @@ static int can_probe(unsigned long paddr) kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE); insn_get_length(&insn); +#ifdef CONFIG_KGDB /* - * Another debugging subsystem might insert this breakpoint. - * In that case, we can't recover it. + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. */ - if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) return 0; +#endif addr += insn.length; } From b838b1b9ca700859153642a5a184c83923c56bba Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Wed, 7 Dec 2022 11:46:35 +0800 Subject: [PATCH 0722/4345] tracing/hist: Fix wrong return value in parse_action_params() commit 2cc6a528882d0e0ccbc1bca5f95b8c963cedac54 upstream. When number of synth fields is more than SYNTH_FIELDS_MAX, parse_action_params() should return -EINVAL. Link: https://lore.kernel.org/linux-trace-kernel/20221207034635.2253990-1-zhengyejian1@huawei.com Cc: Cc: Cc: stable@vger.kernel.org Fixes: c282a386a397 ("tracing: Add 'onmatch' hist trigger action support") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_events_hist.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9bf2bea373d4..0ae3e4454ff2 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3115,6 +3115,7 @@ static int parse_action_params(struct trace_array *tr, char *params, while (params) { if (data->n_params >= SYNTH_FIELDS_MAX) { hist_err(tr, HIST_ERR_TOO_MANY_PARAMS, 0); + ret = -EINVAL; goto out; } From 52c0622e53ea0566efdff22115363e9d67c18900 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 29 Nov 2022 19:30:09 +0800 Subject: [PATCH 0723/4345] tracing: Fix infinite loop in tracing_read_pipe on overflowed print_trace_line commit c1ac03af6ed45d05786c219d102f37eb44880f28 upstream. print_trace_line may overflow seq_file buffer. If the event is not consumed, the while loop keeps peeking this event, causing a infinite loop. Link: https://lkml.kernel.org/r/20221129113009.182425-1-yangjihong1@huawei.com Cc: Masami Hiramatsu Cc: stable@vger.kernel.org Fixes: 088b1e427dbba ("ftrace: pipe fixes") Signed-off-by: Yang Jihong Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 146771d6d007..c7c92b0eed04 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6371,7 +6371,20 @@ waitagain: ret = print_trace_line(iter); if (ret == TRACE_TYPE_PARTIAL_LINE) { - /* don't print partial lines */ + /* + * If one print_trace_line() fills entire trace_seq in one shot, + * trace_seq_to_user() will returns -EBUSY because save_len == 0, + * In this case, we need to consume it, otherwise, loop will peek + * this event next time, resulting in an infinite loop. + */ + if (save_len == 0) { + iter->seq.full = 0; + trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); + trace_consume(iter); + break; + } + + /* In other cases, don't print partial lines */ iter->seq.seq.len = save_len; break; } From 1306614412b8ffe319333356c376ac293a758d48 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Wed, 2 Nov 2022 12:01:01 +0100 Subject: [PATCH 0724/4345] staging: media: tegra-video: fix chan->mipi value on error commit 10b5ce6743c839fa75336042c64e2479caec9430 upstream. chan->mipi takes the return value of tegra_mipi_request() which can be a valid pointer or an error. However chan->mipi is checked in several places, including error-cleanup code in tegra_csi_channels_cleanup(), as 'if (chan->mipi)', which suggests the initial intent was that chan->mipi should be either NULL or a valid pointer, never an error. As a consequence, cleanup code in case of tegra_mipi_request() errors would dereference an invalid pointer. Fix by ensuring chan->mipi always contains either NULL or a void pointer. Also add that to the documentation. Fixes: 523c857e34ce ("media: tegra-video: Add CSI MIPI pads calibration") Cc: stable@vger.kernel.org Reported-by: Dan Carpenter Signed-off-by: Luca Ceresoli Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/staging/media/tegra-video/csi.c | 1 + drivers/staging/media/tegra-video/csi.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/staging/media/tegra-video/csi.c b/drivers/staging/media/tegra-video/csi.c index a19c85c57fca..edfdf6db457d 100644 --- a/drivers/staging/media/tegra-video/csi.c +++ b/drivers/staging/media/tegra-video/csi.c @@ -435,6 +435,7 @@ static int tegra_csi_channel_alloc(struct tegra_csi *csi, chan->mipi = tegra_mipi_request(csi->dev, node); if (IS_ERR(chan->mipi)) { ret = PTR_ERR(chan->mipi); + chan->mipi = NULL; dev_err(csi->dev, "failed to get mipi device: %d\n", ret); } diff --git a/drivers/staging/media/tegra-video/csi.h b/drivers/staging/media/tegra-video/csi.h index c65ff73b1cdc..be4ea81e0031 100644 --- a/drivers/staging/media/tegra-video/csi.h +++ b/drivers/staging/media/tegra-video/csi.h @@ -50,7 +50,7 @@ struct tegra_csi; * @framerate: active framerate for TPG * @h_blank: horizontal blanking for TPG active format * @v_blank: vertical blanking for TPG active format - * @mipi: mipi device for corresponding csi channel pads + * @mipi: mipi device for corresponding csi channel pads, or NULL if not applicable (TPG, error) * @pixel_rate: active pixel rate from the sensor on this channel */ struct tegra_csi_channel { From 1032520b2109d17980ed21135aac891d995f7206 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Tue, 11 Oct 2022 20:00:12 +0100 Subject: [PATCH 0725/4345] ARM: 9256/1: NWFPE: avoid compiler-generated __aeabi_uldivmod commit 3220022038b9a3845eea762af85f1c5694b9f861 upstream. clang-15's ability to elide loops completely became more aggressive when it can deduce how a variable is being updated in a loop. Counting down one variable by an increment of another can be replaced by a modulo operation. For 64b variables on 32b ARM EABI targets, this can result in the compiler generating calls to __aeabi_uldivmod, which it does for a do while loop in float64_rem(). For the kernel, we'd generally prefer that developers not open code 64b division via binary / operators and instead use the more explicit helpers from div64.h. On arm-linux-gnuabi targets, failure to do so can result in linkage failures due to undefined references to __aeabi_uldivmod(). While developers can avoid open coding divisions on 64b variables, the compiler doesn't know that the Linux kernel has a partial implementation of a compiler runtime (--rtlib) to enforce this convention. It's also undecidable for the compiler whether the code in question would be faster to execute the loop vs elide it and do the 64b division. While I actively avoid using the internal -mllvm command line flags, I think we get better code than using barrier() here, which will force reloads+spills in the loop for all toolchains. Link: https://github.com/ClangBuiltLinux/linux/issues/1666 Reported-by: Nathan Chancellor Reviewed-by: Arnd Bergmann Signed-off-by: Nick Desaulniers Tested-by: Nathan Chancellor Cc: stable@vger.kernel.org Signed-off-by: Russell King (Oracle) Signed-off-by: Greg Kroah-Hartman --- arch/arm/nwfpe/Makefile | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/nwfpe/Makefile b/arch/arm/nwfpe/Makefile index 303400fa2cdf..2aec85ab1e8b 100644 --- a/arch/arm/nwfpe/Makefile +++ b/arch/arm/nwfpe/Makefile @@ -11,3 +11,9 @@ nwfpe-y += fpa11.o fpa11_cpdo.o fpa11_cpdt.o \ entry.o nwfpe-$(CONFIG_FPE_NWFPE_XP) += extended_cpdo.o + +# Try really hard to avoid generating calls to __aeabi_uldivmod() from +# float64_rem() due to loop elision. +ifdef CONFIG_CC_IS_CLANG +CFLAGS_softfloat.o += -mllvm -replexitval=never +endif From 7dd5a68cdbbbe7fc67ba701cb52ba10d8ba149f8 Mon Sep 17 00:00:00 2001 From: Keita Suzuki Date: Tue, 26 Apr 2022 06:29:19 +0100 Subject: [PATCH 0726/4345] media: dvb-core: Fix double free in dvb_register_device() commit 6b0d0477fce747d4137aa65856318b55fba72198 upstream. In function dvb_register_device() -> dvb_register_media_device() -> dvb_create_media_entity(), dvb->entity is allocated and initialized. If the initialization fails, it frees the dvb->entity, and return an error code. The caller takes the error code and handles the error by calling dvb_media_device_free(), which unregisters the entity and frees the field again if it is not NULL. As dvb->entity may not NULLed in dvb_create_media_entity() when the allocation of dvbdev->pad fails, a double free may occur. This may also cause an Use After free in media_device_unregister_entity(). Fix this by storing NULL to dvb->entity when it is freed. Link: https://lore.kernel.org/linux-media/20220426052921.2088416-1-keitasuzuki.park@sslab.ics.keio.ac.jp Fixes: fcd5ce4b3936 ("media: dvb-core: fix a memory leak bug") Cc: stable@vger.kernel.org Cc: Wenwen Wang Signed-off-by: Keita Suzuki Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/dvb-core/dvbdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index 4031905f0b07..fea2d82300b0 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -345,6 +345,7 @@ static int dvb_create_media_entity(struct dvb_device *dvbdev, GFP_KERNEL); if (!dvbdev->pads) { kfree(dvbdev->entity); + dvbdev->entity = NULL; return -ENOMEM; } } From 3df07728abde249e2d3f47cf22f134cb4d4f5fb1 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 31 Oct 2022 11:02:45 +0100 Subject: [PATCH 0727/4345] media: dvb-core: Fix UAF due to refcount races at releasing commit fd3d91ab1c6ab0628fe642dd570b56302c30a792 upstream. The dvb-core tries to sync the releases of opened files at dvb_dmxdev_release() with two refcounts: dvbdev->users and dvr_dvbdev->users. A problem is present in those two syncs: when yet another dvb_demux_open() is called during those sync waits, dvb_demux_open() continues to process even if the device is being closed. This includes the increment of the former refcount, resulting in the leftover refcount after the sync of the latter refcount at dvb_dmxdev_release(). It ends up with use-after-free, since the function believes that all usages were gone and releases the resources. This patch addresses the problem by adding the check of dmxdev->exit flag at dvb_demux_open(), just like dvb_dvr_open() already does. With the exit flag check, the second call of dvb_demux_open() fails, hence the further corruption can be avoided. Also for avoiding the races of the dmxdev->exit flag reference, this patch serializes the dmxdev->exit set up and the sync waits with the dmxdev->mutex lock at dvb_dmxdev_release(). Without the mutex lock, dvb_demux_open() (or dvb_dvr_open()) may run concurrently with dvb_dmxdev_release(), which allows to skip the exit flag check and continue the open process that is being closed. CVE-2022-41218 is assigned to those bugs above. Reported-by: Hyunwoo Kim Cc: Link: https://lore.kernel.org/20220908132754.30532-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Hans Verkuil Signed-off-by: Greg Kroah-Hartman --- drivers/media/dvb-core/dmxdev.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c index e58cb8434daf..12b7f698f562 100644 --- a/drivers/media/dvb-core/dmxdev.c +++ b/drivers/media/dvb-core/dmxdev.c @@ -800,6 +800,11 @@ static int dvb_demux_open(struct inode *inode, struct file *file) if (mutex_lock_interruptible(&dmxdev->mutex)) return -ERESTARTSYS; + if (dmxdev->exit) { + mutex_unlock(&dmxdev->mutex); + return -ENODEV; + } + for (i = 0; i < dmxdev->filternum; i++) if (dmxdev->filter[i].state == DMXDEV_STATE_FREE) break; @@ -1458,7 +1463,10 @@ EXPORT_SYMBOL(dvb_dmxdev_init); void dvb_dmxdev_release(struct dmxdev *dmxdev) { + mutex_lock(&dmxdev->mutex); dmxdev->exit = 1; + mutex_unlock(&dmxdev->mutex); + if (dmxdev->dvbdev->users > 1) { wait_event(dmxdev->dvbdev->wait_queue, dmxdev->dvbdev->users == 1); From 8c82733e2408a4012d84fbfbc39698ef387ade98 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Fri, 16 Dec 2022 22:03:41 -0300 Subject: [PATCH 0728/4345] cifs: fix confusing debug message commit a85ceafd41927e41a4103d228a993df7edd8823b upstream. Since rc was initialised to -ENOMEM in cifs_get_smb_ses(), when an existing smb session was found, free_xid() would be called and then print CIFS: fs/cifs/connect.c: Existing tcp session with server found CIFS: fs/cifs/connect.c: VFS: in cifs_get_smb_ses as Xid: 44 with uid: 0 CIFS: fs/cifs/connect.c: Existing smb sess found (status=1) CIFS: fs/cifs/connect.c: VFS: leaving cifs_get_smb_ses (xid = 44) rc = -12 Fix this by initialising rc to 0 and then let free_xid() print this instead CIFS: fs/cifs/connect.c: Existing tcp session with server found CIFS: fs/cifs/connect.c: VFS: in cifs_get_smb_ses as Xid: 14 with uid: 0 CIFS: fs/cifs/connect.c: Existing smb sess found (status=1) CIFS: fs/cifs/connect.c: VFS: leaving cifs_get_smb_ses (xid = 14) rc = 0 Signed-off-by: Paulo Alcantara (SUSE) Cc: stable@vger.kernel.org Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/connect.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index d1c3086d7ddd..164b98540716 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3038,7 +3038,7 @@ cifs_set_cifscreds(struct smb_vol *vol __attribute__((unused)), struct cifs_ses * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) { - int rc = -ENOMEM; + int rc = 0; unsigned int xid; struct cifs_ses *ses; struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; @@ -3080,6 +3080,8 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) return ses; } + rc = -ENOMEM; + cifs_dbg(FYI, "Existing smb sess not found\n"); ses = sesInfoAlloc(); if (ses == NULL) From 6155aed4768ccd7b8a4d427e1b2db2accd5eff46 Mon Sep 17 00:00:00 2001 From: Steve French Date: Sun, 11 Dec 2022 13:54:21 -0600 Subject: [PATCH 0729/4345] cifs: fix missing display of three mount options commit 2bfd81043e944af0e52835ef6d9b41795af22341 upstream. Three mount options: "tcpnodelay" and "noautotune" and "noblocksend" were not displayed when passed in on cifs/smb3 mounts (e.g. displayed in /proc/mounts e.g.). No change to defaults so these are not displayed if not specified on mount. Cc: stable@vger.kernel.org Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/cifsfs.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index f442ef8b65da..0d8d7b57636f 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -619,9 +619,15 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_printf(s, ",echo_interval=%lu", tcon->ses->server->echo_interval / HZ); - /* Only display max_credits if it was overridden on mount */ + /* Only display the following if overridden on mount */ if (tcon->ses->server->max_credits != SMB2_MAX_CREDITS_AVAILABLE) seq_printf(s, ",max_credits=%u", tcon->ses->server->max_credits); + if (tcon->ses->server->tcp_nodelay) + seq_puts(s, ",tcpnodelay"); + if (tcon->ses->server->noautotune) + seq_puts(s, ",noautotune"); + if (tcon->ses->server->noblocksnd) + seq_puts(s, ",noblocksend"); if (tcon->snapshot_time) seq_printf(s, ",snapshot=%llu", tcon->snapshot_time); From e94443252b4656bbdce1de6da451437ed7f7158a Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Thu, 27 Oct 2022 17:32:49 +0100 Subject: [PATCH 0730/4345] rtc: ds1347: fix value written to century register commit 4dfe05bdc1ade79b943d4979a2e2a8b5ef68fbb5 upstream. In `ds1347_set_time()`, the wrong value is being written to the `DS1347_CENTURY_REG` register. It needs to be converted to BCD. Fix it. Fixes: 147dae76dbb9 ("rtc: ds1347: handle century register") Cc: # v5.5+ Signed-off-by: Ian Abbott Link: https://lore.kernel.org/r/20221027163249.447416-1-abbotti@mev.co.uk Signed-off-by: Alexandre Belloni Signed-off-by: Greg Kroah-Hartman --- drivers/rtc/rtc-ds1347.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ds1347.c b/drivers/rtc/rtc-ds1347.c index 7025cf3fb9f8..03267ac65747 100644 --- a/drivers/rtc/rtc-ds1347.c +++ b/drivers/rtc/rtc-ds1347.c @@ -112,7 +112,7 @@ static int ds1347_set_time(struct device *dev, struct rtc_time *dt) return err; century = (dt->tm_year / 100) + 19; - err = regmap_write(map, DS1347_CENTURY_REG, century); + err = regmap_write(map, DS1347_CENTURY_REG, bin2bcd(century)); if (err) return err; From ffcf71676d3b4f13c03b1b6cd8ac1bd06954d30a Mon Sep 17 00:00:00 2001 From: Florian-Ewald Mueller Date: Tue, 25 Oct 2022 09:37:05 +0200 Subject: [PATCH 0731/4345] md/bitmap: Fix bitmap chunk size overflow issues commit 4555211190798b6b6fa2c37667d175bf67945c78 upstream. - limit bitmap chunk size internal u64 variable to values not overflowing the u32 bitmap superblock structure variable stored on persistent media - assign bitmap chunk size internal u64 variable from unsigned values to avoid possible sign extension artifacts when assigning from a s32 value The bug has been there since at least kernel 4.0. Steps to reproduce it: 1: mdadm -C /dev/mdx -l 1 --bitmap=internal --bitmap-chunk=256M -e 1.2 -n2 /dev/rnbd1 /dev/rnbd2 2 resize member device rnbd1 and rnbd2 to 8 TB 3 mdadm --grow /dev/mdx --size=max The bitmap_chunksize will overflow without patch. Cc: stable@vger.kernel.org Signed-off-by: Florian-Ewald Mueller Signed-off-by: Jack Wang Signed-off-by: Song Liu Signed-off-by: Greg Kroah-Hartman --- drivers/md/md-bitmap.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 4e52fcf98d59..20afc0aec177 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -486,7 +486,7 @@ void md_bitmap_print_sb(struct bitmap *bitmap) sb = kmap_atomic(bitmap->storage.sb_page); pr_debug("%s: bitmap file superblock:\n", bmname(bitmap)); pr_debug(" magic: %08x\n", le32_to_cpu(sb->magic)); - pr_debug(" version: %d\n", le32_to_cpu(sb->version)); + pr_debug(" version: %u\n", le32_to_cpu(sb->version)); pr_debug(" uuid: %08x.%08x.%08x.%08x\n", le32_to_cpu(*(__le32 *)(sb->uuid+0)), le32_to_cpu(*(__le32 *)(sb->uuid+4)), @@ -497,11 +497,11 @@ void md_bitmap_print_sb(struct bitmap *bitmap) pr_debug("events cleared: %llu\n", (unsigned long long) le64_to_cpu(sb->events_cleared)); pr_debug(" state: %08x\n", le32_to_cpu(sb->state)); - pr_debug(" chunksize: %d B\n", le32_to_cpu(sb->chunksize)); - pr_debug(" daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep)); + pr_debug(" chunksize: %u B\n", le32_to_cpu(sb->chunksize)); + pr_debug(" daemon sleep: %us\n", le32_to_cpu(sb->daemon_sleep)); pr_debug(" sync size: %llu KB\n", (unsigned long long)le64_to_cpu(sb->sync_size)/2); - pr_debug("max write behind: %d\n", le32_to_cpu(sb->write_behind)); + pr_debug("max write behind: %u\n", le32_to_cpu(sb->write_behind)); kunmap_atomic(sb); } @@ -2106,7 +2106,8 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, bytes = DIV_ROUND_UP(chunks, 8); if (!bitmap->mddev->bitmap_info.external) bytes += sizeof(bitmap_super_t); - } while (bytes > (space << 9)); + } while (bytes > (space << 9) && (chunkshift + BITMAP_BLOCK_SHIFT) < + (BITS_PER_BYTE * sizeof(((bitmap_super_t *)0)->chunksize) - 1)); } else chunkshift = ffz(~chunksize) - BITMAP_BLOCK_SHIFT; @@ -2151,7 +2152,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, bitmap->counts.missing_pages = pages; bitmap->counts.chunkshift = chunkshift; bitmap->counts.chunks = chunks; - bitmap->mddev->bitmap_info.chunksize = 1 << (chunkshift + + bitmap->mddev->bitmap_info.chunksize = 1UL << (chunkshift + BITMAP_BLOCK_SHIFT); blocks = min(old_counts.chunks << old_counts.chunkshift, @@ -2177,8 +2178,8 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, bitmap->counts.missing_pages = old_counts.pages; bitmap->counts.chunkshift = old_counts.chunkshift; bitmap->counts.chunks = old_counts.chunks; - bitmap->mddev->bitmap_info.chunksize = 1 << (old_counts.chunkshift + - BITMAP_BLOCK_SHIFT); + bitmap->mddev->bitmap_info.chunksize = + 1UL << (old_counts.chunkshift + BITMAP_BLOCK_SHIFT); blocks = old_counts.chunks << old_counts.chunkshift; pr_warn("Could not pre-allocate in-memory bitmap for cluster raid\n"); break; @@ -2519,6 +2520,9 @@ chunksize_store(struct mddev *mddev, const char *buf, size_t len) if (csize < 512 || !is_power_of_2(csize)) return -EINVAL; + if (BITS_PER_LONG > 32 && csize >= (1ULL << (BITS_PER_BYTE * + sizeof(((bitmap_super_t *)0)->chunksize)))) + return -EOVERFLOW; mddev->bitmap_info.chunksize = csize; return len; } From d9f6614a732b012bc34ce3d25ddddd45e64b79a8 Mon Sep 17 00:00:00 2001 From: Aditya Garg Date: Thu, 27 Oct 2022 10:01:43 +0000 Subject: [PATCH 0732/4345] efi: Add iMac Pro 2017 to uefi skip cert quirk commit 0be56a116220f9e5731a6609e66a11accfe8d8e2 upstream. The iMac Pro 2017 is also a T2 Mac. Thus add it to the list of uefi skip cert. Cc: stable@vger.kernel.org Fixes: 155ca952c7ca ("efi: Do not import certificates from UEFI Secure Boot for T2 Macs") Link: https://lore.kernel.org/linux-integrity/9D46D92F-1381-4F10-989C-1A12CD2FFDD8@live.com/ Signed-off-by: Aditya Garg Signed-off-by: Mimi Zohar Signed-off-by: Greg Kroah-Hartman --- security/integrity/platform_certs/load_uefi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c index 185c609c6e38..d2f2c3936277 100644 --- a/security/integrity/platform_certs/load_uefi.c +++ b/security/integrity/platform_certs/load_uefi.c @@ -34,6 +34,7 @@ static const struct dmi_system_id uefi_skip_cert[] = { { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacPro7,1") }, { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMac20,1") }, { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMac20,2") }, + { UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMacPro1,1") }, { } }; From 652f1d66a8bedc1463fc525c6b3cb84f98edbb30 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Thu, 27 Oct 2022 19:12:21 +0200 Subject: [PATCH 0733/4345] wifi: wilc1000: sdio: fix module autoloading commit 57d545b5a3d6ce3a8fb6b093f02bfcbb908973f3 upstream. There are no SDIO module aliases included in the driver, therefore, module autoloading isn't working. Add the proper MODULE_DEVICE_TABLE(). Cc: stable@vger.kernel.org Signed-off-by: Michael Walle Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221027171221.491937-1-michael@walle.cc Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/microchip/wilc1000/sdio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c index e14b9fc2c67a..58d92311c782 100644 --- a/drivers/net/wireless/microchip/wilc1000/sdio.c +++ b/drivers/net/wireless/microchip/wilc1000/sdio.c @@ -20,6 +20,7 @@ static const struct sdio_device_id wilc_sdio_ids[] = { { SDIO_DEVICE(SDIO_VENDOR_ID_MICROCHIP_WILC, SDIO_DEVICE_ID_MICROCHIP_WILC1000) }, { }, }; +MODULE_DEVICE_TABLE(sdio, wilc_sdio_ids); #define WILC_SDIO_BLOCK_SIZE 512 From 24bc27ea4e71df53d98ecffd6e5f1a1f031389b8 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Sun, 23 Oct 2022 15:33:20 +0100 Subject: [PATCH 0734/4345] ASoC: jz4740-i2s: Handle independent FIFO flush bits commit 8b3a9ad86239f80ed569e23c3954a311f66481d6 upstream. On the JZ4740, there is a single bit that flushes (empties) both the transmit and receive FIFO. Later SoCs have independent flush bits for each FIFO. Independent FIFOs can be flushed before the snd_soc_dai_active() check because it won't disturb other active streams. This ensures that the FIFO we're about to use is always flushed before starting up. With shared FIFOs we can't do that because if another substream is active, flushing its FIFO would cause underrun errors. This also fixes a bug: since we were only setting the JZ4740's flush bit, which corresponds to the TX FIFO flush bit on other SoCs, other SoCs were not having their RX FIFO flushed at all. Fixes: 967beb2e8777 ("ASoC: jz4740: Add jz4780 support") Reviewed-by: Paul Cercueil Cc: stable@vger.kernel.org Signed-off-by: Aidan MacDonald Link: https://lore.kernel.org/r/20221023143328.160866-2-aidanmacdonald.0x0@gmail.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/jz4740/jz4740-i2s.c | 39 ++++++++++++++++++++++++++++++----- 1 file changed, 34 insertions(+), 5 deletions(-) diff --git a/sound/soc/jz4740/jz4740-i2s.c b/sound/soc/jz4740/jz4740-i2s.c index 0793e284d0e7..fb6476b153ed 100644 --- a/sound/soc/jz4740/jz4740-i2s.c +++ b/sound/soc/jz4740/jz4740-i2s.c @@ -59,7 +59,8 @@ #define JZ_AIC_CTRL_MONO_TO_STEREO BIT(11) #define JZ_AIC_CTRL_SWITCH_ENDIANNESS BIT(10) #define JZ_AIC_CTRL_SIGNED_TO_UNSIGNED BIT(9) -#define JZ_AIC_CTRL_FLUSH BIT(8) +#define JZ_AIC_CTRL_TFLUSH BIT(8) +#define JZ_AIC_CTRL_RFLUSH BIT(7) #define JZ_AIC_CTRL_ENABLE_ROR_INT BIT(6) #define JZ_AIC_CTRL_ENABLE_TUR_INT BIT(5) #define JZ_AIC_CTRL_ENABLE_RFS_INT BIT(4) @@ -94,6 +95,8 @@ enum jz47xx_i2s_version { struct i2s_soc_info { enum jz47xx_i2s_version version; struct snd_soc_dai_driver *dai; + + bool shared_fifo_flush; }; struct jz4740_i2s { @@ -122,19 +125,44 @@ static inline void jz4740_i2s_write(const struct jz4740_i2s *i2s, writel(value, i2s->base + reg); } +static inline void jz4740_i2s_set_bits(const struct jz4740_i2s *i2s, + unsigned int reg, uint32_t bits) +{ + uint32_t value = jz4740_i2s_read(i2s, reg); + value |= bits; + jz4740_i2s_write(i2s, reg, value); +} + static int jz4740_i2s_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct jz4740_i2s *i2s = snd_soc_dai_get_drvdata(dai); - uint32_t conf, ctrl; + uint32_t conf; int ret; + /* + * When we can flush FIFOs independently, only flush the FIFO + * that is starting up. We can do this when the DAI is active + * because it does not disturb other active substreams. + */ + if (!i2s->soc_info->shared_fifo_flush) { + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + jz4740_i2s_set_bits(i2s, JZ_REG_AIC_CTRL, JZ_AIC_CTRL_TFLUSH); + else + jz4740_i2s_set_bits(i2s, JZ_REG_AIC_CTRL, JZ_AIC_CTRL_RFLUSH); + } + if (snd_soc_dai_active(dai)) return 0; - ctrl = jz4740_i2s_read(i2s, JZ_REG_AIC_CTRL); - ctrl |= JZ_AIC_CTRL_FLUSH; - jz4740_i2s_write(i2s, JZ_REG_AIC_CTRL, ctrl); + /* + * When there is a shared flush bit for both FIFOs, the TFLUSH + * bit flushes both FIFOs. Flushing while the DAI is active would + * cause FIFO underruns in other active substreams so we have to + * guard this behind the snd_soc_dai_active() check. + */ + if (i2s->soc_info->shared_fifo_flush) + jz4740_i2s_set_bits(i2s, JZ_REG_AIC_CTRL, JZ_AIC_CTRL_TFLUSH); ret = clk_prepare_enable(i2s->clk_i2s); if (ret) @@ -467,6 +495,7 @@ static struct snd_soc_dai_driver jz4740_i2s_dai = { static const struct i2s_soc_info jz4740_i2s_soc_info = { .version = JZ_I2S_JZ4740, .dai = &jz4740_i2s_dai, + .shared_fifo_flush = true, }; static const struct i2s_soc_info jz4760_i2s_soc_info = { From 4e17819cb3023ef40dd4a1d1694d631cca69df04 Mon Sep 17 00:00:00 2001 From: Zhang Yuchen Date: Fri, 7 Oct 2022 17:26:16 +0800 Subject: [PATCH 0735/4345] ipmi: fix long wait in unload when IPMI disconnect commit f6f1234d98cce69578bfac79df147a1f6660596c upstream. When fixing the problem mentioned in PATCH1, we also found the following problem: If the IPMI is disconnected and in the sending process, the uninstallation driver will be stuck for a long time. The main problem is that uninstalling the driver waits for curr_msg to be sent or HOSED. After stopping tasklet, the only place to trigger the timeout mechanism is the circular poll in shutdown_smi. The poll function delays 10us and calls smi_event_handler(smi_info,10). Smi_event_handler deducts 10us from kcs->ibf_timeout. But the poll func is followed by schedule_timeout_uninterruptible(1). The time consumed here is not counted in kcs->ibf_timeout. So when 10us is deducted from kcs->ibf_timeout, at least 1 jiffies has actually passed. The waiting time has increased by more than a hundredfold. Now instead of calling poll(). call smi_event_handler() directly and calculate the elapsed time. For verification, you can directly use ebpf to check the kcs-> ibf_timeout for each call to kcs_event() when IPMI is disconnected. Decrement at normal rate before unloading. The decrement rate becomes very slow after unloading. $ bpftrace -e 'kprobe:kcs_event {printf("kcs->ibftimeout : %d\n", *(arg0+584));}' Signed-off-by: Zhang Yuchen Message-Id: <20221007092617.87597-3-zhangyuchen.lcr@bytedance.com> Signed-off-by: Corey Minyard Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/char/ipmi/ipmi_si_intf.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 5eac94cf4ff8..7fe68c680d3e 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -2160,6 +2160,20 @@ skip_fallback_noirq: } module_init(init_ipmi_si); +static void wait_msg_processed(struct smi_info *smi_info) +{ + unsigned long jiffies_now; + long time_diff; + + while (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL)) { + jiffies_now = jiffies; + time_diff = (((long)jiffies_now - (long)smi_info->last_timeout_jiffies) + * SI_USEC_PER_JIFFY); + smi_event_handler(smi_info, time_diff); + schedule_timeout_uninterruptible(1); + } +} + static void shutdown_smi(void *send_info) { struct smi_info *smi_info = send_info; @@ -2194,16 +2208,13 @@ static void shutdown_smi(void *send_info) * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ - while (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL)) { - poll(smi_info); - schedule_timeout_uninterruptible(1); - } + wait_msg_processed(smi_info); + if (smi_info->handlers) disable_si_irq(smi_info); - while (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL)) { - poll(smi_info); - schedule_timeout_uninterruptible(1); - } + + wait_msg_processed(smi_info); + if (smi_info->handlers) smi_info->handlers->cleanup(smi_info->si_sm); From 62307558e71eda3fea488ddf50a3b76bcbe91787 Mon Sep 17 00:00:00 2001 From: Alexander Sverdlin Date: Fri, 19 Nov 2021 09:14:12 +0100 Subject: [PATCH 0736/4345] mtd: spi-nor: Check for zero erase size in spi_nor_find_best_erase_type() commit 2ebc336be08160debfe27f87660cf550d710f3e9 upstream. Erase can be zeroed in spi_nor_parse_4bait() or spi_nor_init_non_uniform_erase_map(). In practice it happened with mt25qu256a, which supports 4K, 32K, 64K erases with 3b address commands, but only 4K and 64K erase with 4b address commands. Fixes: dc92843159a7 ("mtd: spi-nor: fix erase_type array to indicate current map conf") Signed-off-by: Alexander Sverdlin Signed-off-by: Tudor Ambarus Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211119081412.29732-1-alexander.sverdlin@nokia.com Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/spi-nor/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index e8146a47da12..2c256d455c9f 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -1220,6 +1220,8 @@ spi_nor_find_best_erase_type(const struct spi_nor_erase_map *map, continue; erase = &map->erase_type[i]; + if (!erase->size) + continue; /* Alignment is not mandatory for overlaid regions */ if (region->offset & SNOR_OVERLAID_REGION && From bfe1e039a0fdeafdf6bdfed037fd13ec4b86372b Mon Sep 17 00:00:00 2001 From: Huaxin Lu Date: Thu, 3 Nov 2022 00:09:49 +0800 Subject: [PATCH 0737/4345] ima: Fix a potential NULL pointer access in ima_restore_measurement_list commit 11220db412edae8dba58853238f53258268bdb88 upstream. In restore_template_fmt, when kstrdup fails, a non-NULL value will still be returned, which causes a NULL pointer access in template_desc_init_fields. Fixes: c7d09367702e ("ima: support restoring multiple template formats") Cc: stable@kernel.org Co-developed-by: Jiaming Li Signed-off-by: Jiaming Li Signed-off-by: Huaxin Lu Reviewed-by: Stefan Berger Signed-off-by: Mimi Zohar Signed-off-by: Greg Kroah-Hartman --- security/integrity/ima/ima_template.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c index e053c741997b..e5d941f485b1 100644 --- a/security/integrity/ima/ima_template.c +++ b/security/integrity/ima/ima_template.c @@ -290,8 +290,11 @@ static struct ima_template_desc *restore_template_fmt(char *template_name) template_desc->name = ""; template_desc->fmt = kstrdup(template_name, GFP_KERNEL); - if (!template_desc->fmt) + if (!template_desc->fmt) { + kfree(template_desc); + template_desc = NULL; goto out; + } spin_lock(&template_list); list_add_tail_rcu(&template_desc->list, &defined_templates); From f29d127b372e1b7662397d92341d9f7de198ff99 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 15 Nov 2022 16:17:43 +0300 Subject: [PATCH 0738/4345] ipmi: fix use after free in _ipmi_destroy_user() commit a92ce570c81dc0feaeb12a429b4bc65686d17967 upstream. The intf_free() function frees the "intf" pointer so we cannot dereference it again on the next line. Fixes: cbb79863fc31 ("ipmi: Don't allow device module unload when in use") Signed-off-by: Dan Carpenter Message-Id: Cc: # 5.5+ Signed-off-by: Corey Minyard Signed-off-by: Greg Kroah-Hartman --- drivers/char/ipmi/ipmi_msghandler.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 223b90247648..b89f300751b1 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -1284,6 +1284,7 @@ static void _ipmi_destroy_user(struct ipmi_user *user) unsigned long flags; struct cmd_rcvr *rcvr; struct cmd_rcvr *rcvrs = NULL; + struct module *owner; if (!acquire_ipmi_user(user, &i)) { /* @@ -1345,8 +1346,9 @@ static void _ipmi_destroy_user(struct ipmi_user *user) kfree(rcvr); } + owner = intf->owner; kref_put(&intf->refcount, intf_free); - module_put(intf->owner); + module_put(owner); } int ipmi_destroy_user(struct ipmi_user *user) From 99ef6cc791584495987dd11b14769b450dfa5820 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 26 Oct 2022 02:11:21 -0400 Subject: [PATCH 0739/4345] PCI: Fix pci_device_is_present() for VFs by checking PF commit 98b04dd0b4577894520493d96bc4623387767445 upstream. pci_device_is_present() previously didn't work for VFs because it reads the Vendor and Device ID, which are 0xffff for VFs, which looks like they aren't present. Check the PF instead. Wei Gong reported that if virtio I/O is in progress when the driver is unbound or "0" is written to /sys/.../sriov_numvfs, the virtio I/O operation hangs, which may result in output like this: task:bash state:D stack: 0 pid: 1773 ppid: 1241 flags:0x00004002 Call Trace: schedule+0x4f/0xc0 blk_mq_freeze_queue_wait+0x69/0xa0 blk_mq_freeze_queue+0x1b/0x20 blk_cleanup_queue+0x3d/0xd0 virtblk_remove+0x3c/0xb0 [virtio_blk] virtio_dev_remove+0x4b/0x80 ... device_unregister+0x1b/0x60 unregister_virtio_device+0x18/0x30 virtio_pci_remove+0x41/0x80 pci_device_remove+0x3e/0xb0 This happened because pci_device_is_present(VF) returned "false" in virtio_pci_remove(), so it called virtio_break_device(). The broken vq meant that vring_interrupt() skipped the vq.callback() that would have completed the virtio I/O operation via virtblk_done(). [bhelgaas: commit log, simplify to always use pci_physfn(), add stable tag] Link: https://lore.kernel.org/r/20221026060912.173250-1-mst@redhat.com Reported-by: Wei Gong Tested-by: Wei Gong Signed-off-by: Michael S. Tsirkin Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 116273454648..262577c81d30 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6152,6 +6152,8 @@ bool pci_device_is_present(struct pci_dev *pdev) { u32 v; + /* Check PF if pdev is a VF, since VF Vendor/Device IDs are 0xffff */ + pdev = pci_physfn(pdev); if (pci_dev_is_disconnected(pdev)) return false; return pci_bus_read_dev_vendor_id(pdev->bus, pdev->devfn, &v, 0); From 7c44205748edc229d580a6beaec1efe4a7b38ec1 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Tue, 8 Nov 2022 17:05:59 -0600 Subject: [PATCH 0740/4345] PCI/sysfs: Fix double free in error path commit aa382ffa705bea9931ec92b6f3c70e1fdb372195 upstream. When pci_create_attr() fails, pci_remove_resource_files() is called which will iterate over the res_attr[_wc] arrays and frees every non NULL entry. To avoid a double free here set the array entry only after it's clear we successfully initialized it. Fixes: b562ec8f74e4 ("PCI: Don't leak memory if sysfs_create_bin_file() fails") Link: https://lore.kernel.org/r/20221007070735.GX986@pengutronix.de/ Signed-off-by: Sascha Hauer Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci-sysfs.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index d15c881e2e7e..361de072dfdc 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -1141,11 +1141,9 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine) sysfs_bin_attr_init(res_attr); if (write_combine) { - pdev->res_attr_wc[num] = res_attr; sprintf(res_attr_name, "resource%d_wc", num); res_attr->mmap = pci_mmap_resource_wc; } else { - pdev->res_attr[num] = res_attr; sprintf(res_attr_name, "resource%d", num); if (pci_resource_flags(pdev, num) & IORESOURCE_IO) { res_attr->read = pci_read_resource_io; @@ -1161,10 +1159,17 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine) res_attr->size = pci_resource_len(pdev, num); res_attr->private = (void *)(unsigned long)num; retval = sysfs_create_bin_file(&pdev->dev.kobj, res_attr); - if (retval) + if (retval) { kfree(res_attr); + return retval; + } - return retval; + if (write_combine) + pdev->res_attr_wc[num] = res_attr; + else + pdev->res_attr[num] = res_attr; + + return 0; } /** From 772dbbfc208437a43b7dfa4bce1a30f3598e61ca Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 6 Oct 2022 04:34:19 +0000 Subject: [PATCH 0741/4345] crypto: n2 - add missing hash statesize commit 76a4e874593543a2dff91d249c95bac728df2774 upstream. Add missing statesize to hash templates. This is mandatory otherwise no algorithms can be registered as the core requires statesize to be set. CC: stable@kernel.org # 4.3+ Reported-by: Rolf Eike Beer Tested-by: Rolf Eike Beer Fixes: 0a625fd2abaa ("crypto: n2 - Add Niagara2 crypto driver") Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/n2_core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c index 3642bf83d809..8c4149c7d7be 100644 --- a/drivers/crypto/n2_core.c +++ b/drivers/crypto/n2_core.c @@ -1228,6 +1228,7 @@ struct n2_hash_tmpl { const u8 *hash_init; u8 hw_op_hashsz; u8 digest_size; + u8 statesize; u8 block_size; u8 auth_type; u8 hmac_type; @@ -1259,6 +1260,7 @@ static const struct n2_hash_tmpl hash_tmpls[] = { .hmac_type = AUTH_TYPE_HMAC_MD5, .hw_op_hashsz = MD5_DIGEST_SIZE, .digest_size = MD5_DIGEST_SIZE, + .statesize = sizeof(struct md5_state), .block_size = MD5_HMAC_BLOCK_SIZE }, { .name = "sha1", .hash_zero = sha1_zero_message_hash, @@ -1267,6 +1269,7 @@ static const struct n2_hash_tmpl hash_tmpls[] = { .hmac_type = AUTH_TYPE_HMAC_SHA1, .hw_op_hashsz = SHA1_DIGEST_SIZE, .digest_size = SHA1_DIGEST_SIZE, + .statesize = sizeof(struct sha1_state), .block_size = SHA1_BLOCK_SIZE }, { .name = "sha256", .hash_zero = sha256_zero_message_hash, @@ -1275,6 +1278,7 @@ static const struct n2_hash_tmpl hash_tmpls[] = { .hmac_type = AUTH_TYPE_HMAC_SHA256, .hw_op_hashsz = SHA256_DIGEST_SIZE, .digest_size = SHA256_DIGEST_SIZE, + .statesize = sizeof(struct sha256_state), .block_size = SHA256_BLOCK_SIZE }, { .name = "sha224", .hash_zero = sha224_zero_message_hash, @@ -1283,6 +1287,7 @@ static const struct n2_hash_tmpl hash_tmpls[] = { .hmac_type = AUTH_TYPE_RESERVED, .hw_op_hashsz = SHA256_DIGEST_SIZE, .digest_size = SHA224_DIGEST_SIZE, + .statesize = sizeof(struct sha256_state), .block_size = SHA224_BLOCK_SIZE }, }; #define NUM_HASH_TMPLS ARRAY_SIZE(hash_tmpls) @@ -1423,6 +1428,7 @@ static int __n2_register_one_ahash(const struct n2_hash_tmpl *tmpl) halg = &ahash->halg; halg->digestsize = tmpl->digest_size; + halg->statesize = tmpl->statesize; base = &halg->base; snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name); From 28e71fd8d5d9b1792f33cf86cbd9fcb53e1b7987 Mon Sep 17 00:00:00 2001 From: "Isaac J. Manjarres" Date: Tue, 20 Sep 2022 17:14:13 -0700 Subject: [PATCH 0742/4345] driver core: Fix bus_type.match() error handling in __driver_attach() commit 27c0d217340e47ec995557f61423ef415afba987 upstream. When a driver registers with a bus, it will attempt to match with every device on the bus through the __driver_attach() function. Currently, if the bus_type.match() function encounters an error that is not -EPROBE_DEFER, __driver_attach() will return a negative error code, which causes the driver registration logic to stop trying to match with the remaining devices on the bus. This behavior is not correct; a failure while matching a driver to a device does not mean that the driver won't be able to match and bind with other devices on the bus. Update the logic in __driver_attach() to reflect this. Fixes: 656b8035b0ee ("ARM: 8524/1: driver cohandle -EPROBE_DEFER from bus_type.match()") Cc: stable@vger.kernel.org Cc: Saravana Kannan Signed-off-by: Isaac J. Manjarres Link: https://lore.kernel.org/r/20220921001414.4046492-1-isaacmanjarres@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 72ef9e83a84b..497e3d4255c4 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -1088,7 +1088,11 @@ static int __driver_attach(struct device *dev, void *data) return 0; } else if (ret < 0) { dev_dbg(dev, "Bus failed to match device: %d\n", ret); - return ret; + /* + * Driver could not match with device, but may match with + * another device on the bus. + */ + return 0; } /* ret > 0 means positive match */ if (driver_allows_async_probing(drv)) { From e291dea722decb58b177451a24ae88be791db849 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Mon, 19 Sep 2022 10:56:37 -0500 Subject: [PATCH 0743/4345] iommu/amd: Fix ivrs_acpihid cmdline parsing code commit 5f18e9f8868c6d4eae71678e7ebd4977b7d8c8cf upstream. The second (UID) strcmp in acpi_dev_hid_uid_match considers "0" and "00" different, which can prevent device registration. Have the AMD IOMMU driver's ivrs_acpihid parsing code remove any leading zeroes to make the UID strcmp succeed. Now users can safely specify "AMDxxxxx:00" or "AMDxxxxx:0" and expect the same behaviour. Fixes: ca3bf5d47cec ("iommu/amd: Introduces ivrs_acpihid kernel parameter") Signed-off-by: Kim Phillips Cc: stable@vger.kernel.org Cc: Suravee Suthikulpanit Cc: Joerg Roedel Link: https://lore.kernel.org/r/20220919155638.391481-1-kim.phillips@amd.com Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/amd/init.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index e988f6f198c5..310ab24d003a 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3126,6 +3126,13 @@ static int __init parse_ivrs_acpihid(char *str) return 1; } + /* + * Ignore leading zeroes after ':', so e.g., AMDI0095:00 + * will match AMDI0095:0 in the second strcmp in acpi_dev_hid_uid_match + */ + while (*uid == '0' && *(uid + 1)) + uid++; + i = early_acpihid_map_size++; memcpy(early_acpihid_map[i].hid, hid, strlen(hid)); memcpy(early_acpihid_map[i].uid, uid, strlen(uid)); From 2c7c487cd85083d1aa1a403372e1ad576a3efeb4 Mon Sep 17 00:00:00 2001 From: Maria Yu Date: Tue, 6 Dec 2022 09:59:57 +0800 Subject: [PATCH 0744/4345] remoteproc: core: Do pm_relax when in RPROC_OFFLINE state commit 11c7f9e3131ad14b27a957496088fa488b153a48 upstream. Make sure that pm_relax() happens even when the remoteproc is stopped before the crash handler work is scheduled. Signed-off-by: Maria Yu Cc: stable Fixes: a781e5aa5911 ("remoteproc: core: Prevent system suspend during remoteproc recovery") Link: https://lore.kernel.org/r/20221206015957.2616-2-quic_aiquny@quicinc.com Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/remoteproc/remoteproc_core.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 369a97f3eca9..cc55ff0128cf 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1741,12 +1741,18 @@ static void rproc_crash_handler_work(struct work_struct *work) mutex_lock(&rproc->lock); - if (rproc->state == RPROC_CRASHED || rproc->state == RPROC_OFFLINE) { + if (rproc->state == RPROC_CRASHED) { /* handle only the first crash detected */ mutex_unlock(&rproc->lock); return; } + if (rproc->state == RPROC_OFFLINE) { + /* Don't recover if the remote processor was stopped */ + mutex_unlock(&rproc->lock); + goto out; + } + rproc->state = RPROC_CRASHED; dev_err(dev, "handling crash #%u in %s\n", ++rproc->crash_cnt, rproc->name); @@ -1756,6 +1762,7 @@ static void rproc_crash_handler_work(struct work_struct *work) if (!rproc->recovery_disabled) rproc_trigger_recovery(rproc); +out: pm_relax(rproc->dev.parent); } From 3505c187b86136250b39e62c72a3a70435277af6 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Thu, 17 Nov 2022 10:45:14 +0800 Subject: [PATCH 0745/4345] parisc: led: Fix potential null-ptr-deref in start_task() commit 41f563ab3c33698bdfc3403c7c2e6c94e73681e4 upstream. start_task() calls create_singlethread_workqueue() and not checked the ret value, which may return NULL. And a null-ptr-deref may happen: start_task() create_singlethread_workqueue() # failed, led_wq is NULL queue_delayed_work() queue_delayed_work_on() __queue_delayed_work() # warning here, but continue __queue_work() # access wq->flags, null-ptr-deref Check the ret value and return -ENOMEM if it is NULL. Fixes: 3499495205a6 ("[PARISC] Use work queue in LED/LCD driver instead of tasklet.") Signed-off-by: Shang XiaoJing Signed-off-by: Helge Deller Cc: Signed-off-by: Greg Kroah-Hartman --- drivers/parisc/led.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c index 36c6613f7a36..4854120fc095 100644 --- a/drivers/parisc/led.c +++ b/drivers/parisc/led.c @@ -137,6 +137,9 @@ static int start_task(void) /* Create the work queue and queue the LED task */ led_wq = create_singlethread_workqueue("led_wq"); + if (!led_wq) + return -ENOMEM; + queue_delayed_work(led_wq, &led_task, 0); return 0; From 21a773ec89946522690132b09e5d0bec13bb5d0f Mon Sep 17 00:00:00 2001 From: Wang Weiyang Date: Tue, 25 Oct 2022 19:31:01 +0800 Subject: [PATCH 0746/4345] device_cgroup: Roll back to original exceptions after copy failure commit e68bfbd3b3c3a0ec3cf8c230996ad8cabe90322f upstream. When add the 'a *:* rwm' entry to devcgroup A's whitelist, at first A's exceptions will be cleaned and A's behavior is changed to DEVCG_DEFAULT_ALLOW. Then parent's exceptions will be copyed to A's whitelist. If copy failure occurs, just return leaving A to grant permissions to all devices. And A may grant more permissions than parent. Backup A's whitelist and recover original exceptions after copy failure. Cc: stable@vger.kernel.org Fixes: 4cef7299b478 ("device_cgroup: add proper checking when changing default behavior") Signed-off-by: Wang Weiyang Reviewed-by: Aristeu Rozanski Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- security/device_cgroup.c | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 04375df52fc9..fe5cb7696993 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -81,6 +81,17 @@ free_and_exit: return -ENOMEM; } +static void dev_exceptions_move(struct list_head *dest, struct list_head *orig) +{ + struct dev_exception_item *ex, *tmp; + + lockdep_assert_held(&devcgroup_mutex); + + list_for_each_entry_safe(ex, tmp, orig, list) { + list_move_tail(&ex->list, dest); + } +} + /* * called under devcgroup_mutex */ @@ -603,11 +614,13 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup, int count, rc = 0; struct dev_exception_item ex; struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent); + struct dev_cgroup tmp_devcgrp; if (!capable(CAP_SYS_ADMIN)) return -EPERM; memset(&ex, 0, sizeof(ex)); + memset(&tmp_devcgrp, 0, sizeof(tmp_devcgrp)); b = buffer; switch (*b) { @@ -619,15 +632,27 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup, if (!may_allow_all(parent)) return -EPERM; - dev_exception_clean(devcgroup); - devcgroup->behavior = DEVCG_DEFAULT_ALLOW; - if (!parent) + if (!parent) { + devcgroup->behavior = DEVCG_DEFAULT_ALLOW; + dev_exception_clean(devcgroup); break; + } - rc = dev_exceptions_copy(&devcgroup->exceptions, - &parent->exceptions); + INIT_LIST_HEAD(&tmp_devcgrp.exceptions); + rc = dev_exceptions_copy(&tmp_devcgrp.exceptions, + &devcgroup->exceptions); if (rc) return rc; + dev_exception_clean(devcgroup); + rc = dev_exceptions_copy(&devcgroup->exceptions, + &parent->exceptions); + if (rc) { + dev_exceptions_move(&devcgroup->exceptions, + &tmp_devcgrp.exceptions); + return rc; + } + devcgroup->behavior = DEVCG_DEFAULT_ALLOW; + dev_exception_clean(&tmp_devcgrp); break; case DEVCG_DENY: if (css_has_online_children(&devcgroup->css)) From 0a0662d597de4e6bf120ed8c89edfad33be343b6 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Mon, 17 Oct 2022 15:32:01 +0000 Subject: [PATCH 0747/4345] drm/connector: send hotplug uevent on connector cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6fdc2d490ea1369d17afd7e6eb66fecc5b7209bc upstream. A typical DP-MST unplug removes a KMS connector. However care must be taken to properly synchronize with user-space. The expected sequence of events is the following: 1. The kernel notices that the DP-MST port is gone. 2. The kernel marks the connector as disconnected, then sends a uevent to make user-space re-scan the connector list. 3. User-space notices the connector goes from connected to disconnected, disables it. 4. Kernel handles the IOCTL disabling the connector. On success, the very last reference to the struct drm_connector is dropped and drm_connector_cleanup() is called. 5. The connector is removed from the list, and a uevent is sent to tell user-space that the connector disappeared. The very last step was missing. As a result, user-space thought the connector still existed and could try to disable it again. Since the kernel no longer knows about the connector, that would end up with EINVAL and confused user-space. Fix this by sending a hotplug uevent from drm_connector_cleanup(). Signed-off-by: Simon Ser Cc: stable@vger.kernel.org Cc: Daniel Vetter Cc: Lyude Paul Cc: Jonas Ådahl Tested-by: Jonas Ådahl Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20221017153150.60675-2-contact@emersion.fr Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_connector.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 5163433ac561..9c3bbe2c3e6f 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -484,6 +484,9 @@ void drm_connector_cleanup(struct drm_connector *connector) mutex_destroy(&connector->mutex); memset(connector, 0, sizeof(*connector)); + + if (dev->registered) + drm_sysfs_hotplug_event(dev); } EXPORT_SYMBOL(drm_connector_cleanup); From 439cbbc1519547f9a7b483f0de33b556ebfec901 Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Tue, 25 Oct 2022 23:19:35 -0400 Subject: [PATCH 0748/4345] drm/vmwgfx: Validate the box size for the snooped cursor commit 4cf949c7fafe21e085a4ee386bb2dade9067316e upstream. Invalid userspace dma surface copies could potentially overflow the memcpy from the surface to the snooped image leading to crashes. To fix it the dimensions of the copybox have to be validated against the expected size of the snooped cursor. Signed-off-by: Zack Rusin Fixes: 2ac863719e51 ("vmwgfx: Snoop DMA transfers with non-covering sizes") Cc: # v3.2+ Reviewed-by: Michael Banack Reviewed-by: Martin Krastev Link: https://patchwork.freedesktop.org/patch/msgid/20221026031936.1004280-1-zack@kde.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index e58112997c88..0e963fd7db17 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -182,7 +182,8 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf, if (cmd->dma.guest.ptr.offset % PAGE_SIZE || box->x != 0 || box->y != 0 || box->z != 0 || box->srcx != 0 || box->srcy != 0 || box->srcz != 0 || - box->d != 1 || box_count != 1) { + box->d != 1 || box_count != 1 || + box->w > 64 || box->h > 64) { /* TODO handle none page aligned offsets */ /* TODO handle more dst & src != 0 */ /* TODO handle more then one copy */ From bf83a303f2b56fc996ee9afd53a0a2cc71ffffad Mon Sep 17 00:00:00 2001 From: Mikko Kovanen Date: Sat, 26 Nov 2022 13:27:13 +0000 Subject: [PATCH 0749/4345] drm/i915/dsi: fix VBT send packet port selection for dual link DSI commit f9cdf4130671d767071607d0a7568c9bd36a68d0 upstream. intel_dsi->ports contains bitmask of enabled ports and correspondingly logic for selecting port for VBT packet sending must use port specific bitmask when deciding appropriate port. Fixes: 08c59dde71b7 ("drm/i915/dsi: fix VBT send packet port selection for ICL+") Cc: stable@vger.kernel.org Signed-off-by: Mikko Kovanen Reviewed-by: Jani Nikula Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/DBBPR09MB466592B16885D99ABBF2393A91119@DBBPR09MB4665.eurprd09.prod.outlook.com (cherry picked from commit 8d58bb7991c45f6b60710cc04c9498c6ea96db90) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/display/intel_dsi_vbt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index 8777d35ac7a7..117ea44fd8be 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -133,9 +133,9 @@ static enum port intel_dsi_seq_port_to_port(struct intel_dsi *intel_dsi, return ffs(intel_dsi->ports) - 1; if (seq_port) { - if (intel_dsi->ports & PORT_B) + if (intel_dsi->ports & BIT(PORT_B)) return PORT_B; - else if (intel_dsi->ports & PORT_C) + else if (intel_dsi->ports & BIT(PORT_C)) return PORT_C; } From 68af1a4842b4e69e1ac4a3488fad387972e98ee0 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Fri, 4 Nov 2022 06:45:12 +0000 Subject: [PATCH 0750/4345] drm/ingenic: Fix missing platform_driver_unregister() call in ingenic_drm_init() commit 47078311b8efebdefd5b3b2f87e2b02b14f49c66 upstream. A problem about modprobe ingenic-drm failed is triggered with the following log given: [ 303.561088] Error: Driver 'ingenic-ipu' is already registered, aborting... modprobe: ERROR: could not insert 'ingenic_drm': Device or resource busy The reason is that ingenic_drm_init() returns platform_driver_register() directly without checking its return value, if platform_driver_register() failed, it returns without unregistering ingenic_ipu_driver_ptr, resulting the ingenic-drm can never be installed later. A simple call graph is shown as below: ingenic_drm_init() platform_driver_register() # ingenic_ipu_driver_ptr are registered platform_driver_register() driver_register() bus_add_driver() priv = kzalloc(...) # OOM happened # return without unregister ingenic_ipu_driver_ptr Fixing this problem by checking the return value of platform_driver_register() and do platform_unregister_drivers() if error happened. Fixes: fc1acf317b01 ("drm/ingenic: Add support for the IPU") Signed-off-by: Yuan Can Cc: stable@vger.kernel.org Signed-off-by: Paul Cercueil Link: https://patchwork.freedesktop.org/patch/msgid/20221104064512.8569-1-yuancan@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/ingenic/ingenic-drm-drv.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c index e34718cf5c2e..5ec9770e401e 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c @@ -1120,7 +1120,11 @@ static int ingenic_drm_init(void) return err; } - return platform_driver_register(&ingenic_drm_driver); + err = platform_driver_register(&ingenic_drm_driver); + if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU) && err) + platform_driver_unregister(ingenic_ipu_driver_ptr); + + return err; } module_init(ingenic_drm_init); From bdc698ce91f232fd5eb11d2373e9f82f687314b8 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Wed, 29 Jun 2022 19:26:46 +0800 Subject: [PATCH 0751/4345] ext4: silence the warning when evicting inode with dioread_nolock commit bc12ac98ea2e1b70adc6478c8b473a0003b659d3 upstream. When evicting an inode with default dioread_nolock, it could be raced by the unwritten extents converting kworker after writeback some new allocated dirty blocks. It convert unwritten extents to written, the extents could be merged to upper level and free extent blocks, so it could mark the inode dirty again even this inode has been marked I_FREEING. But the inode->i_io_list check and warning in ext4_evict_inode() missing this corner case. Fortunately, ext4_evict_inode() will wait all extents converting finished before this check, so it will not lead to inode use-after-free problem, every thing is OK besides this warning. The WARN_ON_ONCE was originally designed for finding inode use-after-free issues in advance, but if we add current dioread_nolock case in, it will become not quite useful, so fix this warning by just remove this check. ====== WARNING: CPU: 7 PID: 1092 at fs/ext4/inode.c:227 ext4_evict_inode+0x875/0xc60 ... RIP: 0010:ext4_evict_inode+0x875/0xc60 ... Call Trace: evict+0x11c/0x2b0 iput+0x236/0x3a0 do_unlinkat+0x1b4/0x490 __x64_sys_unlinkat+0x4c/0xb0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fa933c1115b ====== rm kworker ext4_end_io_end() vfs_unlink() ext4_unlink() ext4_convert_unwritten_io_end_vec() ext4_convert_unwritten_extents() ext4_map_blocks() ext4_ext_map_blocks() ext4_ext_try_to_merge_up() __mark_inode_dirty() check !I_FREEING locked_inode_to_wb_and_lock_list() iput() iput_final() evict() ext4_evict_inode() truncate_inode_pages_final() //wait release io_end inode_io_list_move_locked() ext4_release_io_end() trigger WARN_ON_ONCE() Cc: stable@kernel.org Fixes: ceff86fddae8 ("ext4: Avoid freeing inodes on dirty list") Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20220629112647.4141034-1-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 45f31dc1e66f..bad1792865e9 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -223,13 +223,13 @@ void ext4_evict_inode(struct inode *inode) /* * For inodes with journalled data, transaction commit could have - * dirtied the inode. Flush worker is ignoring it because of I_FREEING - * flag but we still need to remove the inode from the writeback lists. + * dirtied the inode. And for inodes with dioread_nolock, unwritten + * extents converting worker could merge extents and also have dirtied + * the inode. Flush worker is ignoring it because of I_FREEING flag but + * we still need to remove the inode from the writeback lists. */ - if (!list_empty_careful(&inode->i_io_list)) { - WARN_ON_ONCE(!ext4_should_journal_data(inode)); + if (!list_empty_careful(&inode->i_io_list)) inode_io_list_del(inode); - } /* * Protect us against freezing - iput() caller didn't have to have any From d6d18d6e2d068e6d1e62f7d8cd1a1a2139c7b3df Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 17 Aug 2022 21:27:01 +0800 Subject: [PATCH 0752/4345] ext4: add inode table check in __ext4_get_inode_loc to aovid possible infinite loop commit eee22187b53611e173161e38f61de1c7ecbeb876 upstream. In do_writepages, if the value returned by ext4_writepages is "-ENOMEM" and "wbc->sync_mode == WB_SYNC_ALL", retry until the condition is not met. In __ext4_get_inode_loc, if the bh returned by sb_getblk is NULL, the function returns -ENOMEM. In __getblk_slow, if the return value of grow_buffers is less than 0, the function returns NULL. When the three processes are connected in series like the following stack, an infinite loop may occur: do_writepages <--- keep retrying ext4_writepages mpage_map_and_submit_extent mpage_map_one_extent ext4_map_blocks ext4_ext_map_blocks ext4_ext_handle_unwritten_extents ext4_ext_convert_to_initialized ext4_split_extent ext4_split_extent_at __ext4_ext_dirty __ext4_mark_inode_dirty ext4_reserve_inode_write ext4_get_inode_loc __ext4_get_inode_loc <--- return -ENOMEM sb_getblk __getblk_gfp __getblk_slow <--- return NULL grow_buffers grow_dev_page <--- return -ENXIO ret = (block < end_block) ? 1 : -ENXIO; In this issue, bg_inode_table_hi is overwritten as an incorrect value. As a result, `block < end_block` cannot be met in grow_dev_page. Therefore, __ext4_get_inode_loc always returns '-ENOMEM' and do_writepages keeps retrying. As a result, the writeback process is in the D state due to an infinite loop. Add a check on inode table block in the __ext4_get_inode_loc function by referring to ext4_read_inode_bitmap to avoid this infinite loop. Cc: stable@kernel.org Signed-off-by: Baokun Li Reviewed-by: Ritesh Harjani (IBM) Link: https://lore.kernel.org/r/20220817132701.3015912-3-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bad1792865e9..417b1b289ac1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4386,9 +4386,17 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; inode_offset = ((ino - 1) % EXT4_INODES_PER_GROUP(sb)); - block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block); iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb); + block = ext4_inode_table(sb, gdp); + if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) || + (block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) { + ext4_error(sb, "Invalid inode table block %llu in " + "block_group %u", block, iloc->block_group); + return -EFSCORRUPTED; + } + block += (inode_offset / inodes_per_block); + bh = sb_getblk(sb, block); if (unlikely(!bh)) return -ENOMEM; From 7223d5e75f26352354ea2c0ccf8b579821b52adf Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 2 Nov 2022 16:06:33 +0800 Subject: [PATCH 0753/4345] ext4: fix use-after-free in ext4_orphan_cleanup commit a71248b1accb2b42e4980afef4fa4a27fa0e36f5 upstream. I caught a issue as follows: ================================================================== BUG: KASAN: use-after-free in __list_add_valid+0x28/0x1a0 Read of size 8 at addr ffff88814b13f378 by task mount/710 CPU: 1 PID: 710 Comm: mount Not tainted 6.1.0-rc3-next #370 Call Trace: dump_stack_lvl+0x73/0x9f print_report+0x25d/0x759 kasan_report+0xc0/0x120 __asan_load8+0x99/0x140 __list_add_valid+0x28/0x1a0 ext4_orphan_cleanup+0x564/0x9d0 [ext4] __ext4_fill_super+0x48e2/0x5300 [ext4] ext4_fill_super+0x19f/0x3a0 [ext4] get_tree_bdev+0x27b/0x450 ext4_get_tree+0x19/0x30 [ext4] vfs_get_tree+0x49/0x150 path_mount+0xaae/0x1350 do_mount+0xe2/0x110 __x64_sys_mount+0xf0/0x190 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd [...] ================================================================== Above issue may happen as follows: ------------------------------------- ext4_fill_super ext4_orphan_cleanup --- loop1: assume last_orphan is 12 --- list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan) ext4_truncate --> return 0 ext4_inode_attach_jinode --> return -ENOMEM iput(inode) --> free inode<12> --- loop2: last_orphan is still 12 --- list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan); // use inode<12> and trigger UAF To solve this issue, we need to propagate the return value of ext4_inode_attach_jinode() appropriately. Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221102080633.1630225-1-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 417b1b289ac1..0f971bd0e7a5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4285,7 +4285,8 @@ int ext4_truncate(struct inode *inode) /* If we zero-out tail of the page, we have to create jinode for jbd2 */ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { - if (ext4_inode_attach_jinode(inode) < 0) + err = ext4_inode_attach_jinode(inode); + if (err) goto out_trace; } From f9cd6980800bbfd11bf94eb5f942049d4d4eaa52 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Mon, 31 Oct 2022 13:58:33 +0800 Subject: [PATCH 0754/4345] ext4: fix undefined behavior in bit shift for ext4_check_flag_values commit 3bf678a0f9c017c9ba7c581541dbc8453452a7ae upstream. Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. The UBSAN warning calltrace like below: UBSAN: shift-out-of-bounds in fs/ext4/ext4.h:591:2 left shift of 1 by 31 places cannot be represented in type 'int' Call Trace: dump_stack_lvl+0x7d/0xa5 dump_stack+0x15/0x1b ubsan_epilogue+0xe/0x4e __ubsan_handle_shift_out_of_bounds+0x1e7/0x20c ext4_init_fs+0x5a/0x277 do_one_initcall+0x76/0x430 kernel_init_freeable+0x3b3/0x422 kernel_init+0x24/0x1e0 ret_from_fork+0x1f/0x30 Fixes: 9a4c80194713 ("ext4: ensure Inode flags consistency are checked at build time") Signed-off-by: Gaosheng Cui Link: https://lore.kernel.org/r/20221031055833.3966222-1-cuigaosheng1@huawei.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ext4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4ad1c3ce9398..b328e5c3b801 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -553,7 +553,7 @@ enum { * * It's not paranoia if the Murphy's Law really *is* out to get you. :-) */ -#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG)) +#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1U << EXT4_INODE_##FLAG)) #define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG)) static inline void ext4_check_flag_values(void) From c0a738875c2e9c8c3366d792f8bf7fe508d5e5a5 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 26 Oct 2022 12:23:09 +0800 Subject: [PATCH 0755/4345] ext4: add EXT4_IGET_BAD flag to prevent unexpected bad inode commit 63b1e9bccb71fe7d7e3ddc9877dbdc85e5d2d023 upstream. There are many places that will get unhappy (and crash) when ext4_iget() returns a bad inode. However, if iget the boot loader inode, allows a bad inode to be returned, because the inode may not be initialized. This mechanism can be used to bypass some checks and cause panic. To solve this problem, we add a special iget flag EXT4_IGET_BAD. Only with this flag we'd be returning bad inode from ext4_iget(), otherwise we always return the error code if the inode is bad inode.(suggested by Jan Kara) Signed-off-by: Baokun Li Reviewed-by: Jason Yan Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221026042310.3839669-4-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ext4.h | 3 ++- fs/ext4/inode.c | 8 +++++++- fs/ext4/ioctl.c | 3 ++- 3 files changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b328e5c3b801..fb9c9e1813bc 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2842,7 +2842,8 @@ int do_journal_get_write_access(handle_t *handle, typedef enum { EXT4_IGET_NORMAL = 0, EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */ - EXT4_IGET_HANDLE = 0x0002 /* Inode # is from a handle */ + EXT4_IGET_HANDLE = 0x0002, /* Inode # is from a handle */ + EXT4_IGET_BAD = 0x0004 /* Allow to iget a bad inode */ } ext4_iget_flags; extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0f971bd0e7a5..0f9005cb1035 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4969,8 +4969,14 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) ext4_error_inode(inode, function, line, 0, "casefold flag without casefold feature"); - brelse(iloc.bh); + if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) { + ext4_error_inode(inode, function, line, 0, + "bad inode without EXT4_IGET_BAD flag"); + ret = -EUCLEAN; + goto bad_inode; + } + brelse(iloc.bh); unlock_new_inode(inode); return inode; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 413bf3d2f784..879e637ef3e1 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -121,7 +121,8 @@ static long swap_inode_boot_loader(struct super_block *sb, blkcnt_t blocks; unsigned short bytes; - inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL); + inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, + EXT4_IGET_SPECIAL | EXT4_IGET_BAD); if (IS_ERR(inode_bl)) return PTR_ERR(inode_bl); ei_bl = EXT4_I(inode_bl); From 20af66617eef36797340f0ef02d23e913a4c9a91 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 26 Oct 2022 12:23:08 +0800 Subject: [PATCH 0756/4345] ext4: add helper to check quota inums commit 07342ec259df2a35d6a34aebce010567a80a0e15 upstream. Before quota is enabled, a check on the preset quota inums in ext4_super_block is added to prevent wrong quota inodes from being loaded. In addition, when the quota fails to be enabled, the quota type and quota inum are printed to facilitate fault locating. Signed-off-by: Baokun Li Reviewed-by: Jason Yan Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221026042310.3839669-3-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/super.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9573d493c374..aa7bcc856de9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6385,6 +6385,20 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, return err; } +static inline bool ext4_check_quota_inum(int type, unsigned long qf_inum) +{ + switch (type) { + case USRQUOTA: + return qf_inum == EXT4_USR_QUOTA_INO; + case GRPQUOTA: + return qf_inum == EXT4_GRP_QUOTA_INO; + case PRJQUOTA: + return qf_inum >= EXT4_GOOD_OLD_FIRST_INO; + default: + BUG(); + } +} + static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags) { @@ -6401,9 +6415,16 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, if (!qf_inums[type]) return -EPERM; + if (!ext4_check_quota_inum(type, qf_inums[type])) { + ext4_error(sb, "Bad quota inum: %lu, type: %d", + qf_inums[type], type); + return -EUCLEAN; + } + qf_inode = ext4_iget(sb, qf_inums[type], EXT4_IGET_SPECIAL); if (IS_ERR(qf_inode)) { - ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]); + ext4_error(sb, "Bad quota inode: %lu, type: %d", + qf_inums[type], type); return PTR_ERR(qf_inode); } @@ -6442,8 +6463,9 @@ static int ext4_enable_quotas(struct super_block *sb) if (err) { ext4_warning(sb, "Failed to enable quota tracking " - "(type=%d, err=%d). Please run " - "e2fsck to fix.", type, err); + "(type=%d, err=%d, ino=%lu). " + "Please run e2fsck to fix.", type, + err, qf_inums[type]); for (type--; type >= 0; type--) { struct inode *inode; From 98004f926d27eaccdd2d336b7916a42e07392da1 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 26 Oct 2022 12:23:07 +0800 Subject: [PATCH 0757/4345] ext4: fix bug_on in __es_tree_search caused by bad quota inode commit d323877484765aaacbb2769b06e355c2041ed115 upstream. We got a issue as fllows: ================================================================== kernel BUG at fs/ext4/extents_status.c:202! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 1 PID: 810 Comm: mount Not tainted 6.1.0-rc1-next-g9631525255e3 #352 RIP: 0010:__es_tree_search.isra.0+0xb8/0xe0 RSP: 0018:ffffc90001227900 EFLAGS: 00010202 RAX: 0000000000000000 RBX: 0000000077512a0f RCX: 0000000000000000 RDX: 0000000000000002 RSI: 0000000000002a10 RDI: ffff8881004cd0c8 RBP: ffff888177512ac8 R08: 47ffffffffffffff R09: 0000000000000001 R10: 0000000000000001 R11: 00000000000679af R12: 0000000000002a10 R13: ffff888177512d88 R14: 0000000077512a10 R15: 0000000000000000 FS: 00007f4bd76dbc40(0000)GS:ffff88842fd00000(0000)knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005653bf993cf8 CR3: 000000017bfdf000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ext4_es_cache_extent+0xe2/0x210 ext4_cache_extents+0xd2/0x110 ext4_find_extent+0x5d5/0x8c0 ext4_ext_map_blocks+0x9c/0x1d30 ext4_map_blocks+0x431/0xa50 ext4_getblk+0x82/0x340 ext4_bread+0x14/0x110 ext4_quota_read+0xf0/0x180 v2_read_header+0x24/0x90 v2_check_quota_file+0x2f/0xa0 dquot_load_quota_sb+0x26c/0x760 dquot_load_quota_inode+0xa5/0x190 ext4_enable_quotas+0x14c/0x300 __ext4_fill_super+0x31cc/0x32c0 ext4_fill_super+0x115/0x2d0 get_tree_bdev+0x1d2/0x360 ext4_get_tree+0x19/0x30 vfs_get_tree+0x26/0xe0 path_mount+0x81d/0xfc0 do_mount+0x8d/0xc0 __x64_sys_mount+0xc0/0x160 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd ================================================================== Above issue may happen as follows: ------------------------------------- ext4_fill_super ext4_orphan_cleanup ext4_enable_quotas ext4_quota_enable ext4_iget --> get error inode <5> ext4_ext_check_inode --> Wrong imode makes it escape inspection make_bad_inode(inode) --> EXT4_BOOT_LOADER_INO set imode dquot_load_quota_inode vfs_setup_quota_inode --> check pass dquot_load_quota_sb v2_check_quota_file v2_read_header ext4_quota_read ext4_bread ext4_getblk ext4_map_blocks ext4_ext_map_blocks ext4_find_extent ext4_cache_extents ext4_es_cache_extent __es_tree_search.isra.0 ext4_es_end --> Wrong extents trigger BUG_ON In the above issue, s_usr_quota_inum is set to 5, but inode<5> contains incorrect imode and disordered extents. Because 5 is EXT4_BOOT_LOADER_INO, the ext4_ext_check_inode check in the ext4_iget function can be bypassed, finally, the extents that are not checked trigger the BUG_ON in the __es_tree_search function. To solve this issue, check whether the inode is bad_inode in vfs_setup_quota_inode(). Signed-off-by: Baokun Li Reviewed-by: Chaitanya Kulkarni Reviewed-by: Jason Yan Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221026042310.3839669-2-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/quota/dquot.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 65f123d5809b..ad255f8ab5c5 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2319,6 +2319,8 @@ static int vfs_setup_quota_inode(struct inode *inode, int type) struct super_block *sb = inode->i_sb; struct quota_info *dqopt = sb_dqopt(sb); + if (is_bad_inode(inode)) + return -EUCLEAN; if (!S_ISREG(inode->i_mode)) return -EACCES; if (IS_RDONLY(inode)) From 86c2a2ec4bd3c7c74cbdc0c30fbf16e5862d834e Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 8 Dec 2022 11:34:24 +0800 Subject: [PATCH 0758/4345] ext4: fix reserved cluster accounting in __es_remove_extent() commit 1da18e38cb97e9521e93d63034521a9649524f64 upstream. When bigalloc is enabled, reserved cluster accounting for delayed allocation is handled in extent_status.c. With a corrupted file system, it's possible for this accounting to be incorrect, dsicovered by Syzbot: EXT4-fs error (device loop0): ext4_validate_block_bitmap:398: comm rep: bg 0: block 5: invalid block bitmap EXT4-fs (loop0): Delayed block allocation failed for inode 18 at logical offset 0 with max blocks 32 with error 28 EXT4-fs (loop0): This should not happen!! Data will be lost EXT4-fs (loop0): Total free blocks count 0 EXT4-fs (loop0): Free/Dirty block details EXT4-fs (loop0): free_blocks=0 EXT4-fs (loop0): dirty_blocks=32 EXT4-fs (loop0): Block reservation details EXT4-fs (loop0): i_reserved_data_blocks=2 EXT4-fs (loop0): Inode 18 (00000000845cd634): i_reserved_data_blocks (1) not cleared! Above issue happens as follows: Assume: sbi->s_cluster_ratio = 16 Step1: Insert delay block [0, 31] -> ei->i_reserved_data_blocks=2 Step2: ext4_writepages mpage_map_and_submit_extent -> return failed mpage_release_unused_pages -> to release [0, 30] ext4_es_remove_extent -> remove lblk=0 end=30 __es_remove_extent -> len1=0 len2=31-30=1 __es_remove_extent: ... if (len2 > 0) { ... if (len1 > 0) { ... } else { es->es_lblk = end + 1; es->es_len = len2; ... } if (count_reserved) count_rsvd(inode, lblk, ...); goto out; -> will return but didn't calculate 'reserved' ... Step3: ext4_destroy_inode -> trigger "i_reserved_data_blocks (1) not cleared!" To solve above issue if 'len2>0' call 'get_rsvd()' before goto out. Reported-by: syzbot+05a0f0ccab4a25626e38@syzkaller.appspotmail.com Fixes: 8fcc3a580651 ("ext4: rework reserved cluster accounting when invalidating pages") Signed-off-by: Ye Bin Reviewed-by: Eric Whitney Link: https://lore.kernel.org/r/20221208033426.1832460-2-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/extents_status.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 9a3a8996aacf..aa99a3659edf 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1372,7 +1372,7 @@ retry: if (count_reserved) count_rsvd(inode, lblk, orig_es.es_len - len1 - len2, &orig_es, &rc); - goto out; + goto out_get_reserved; } if (len1 > 0) { @@ -1414,6 +1414,7 @@ retry: } } +out_get_reserved: if (count_reserved) *reserved = get_rsvd(inode, end, es, &rc); out: From 9020f56a3cad1c97b81c7dab2aa67027b59c8f73 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Wed, 29 Jun 2022 19:26:47 +0800 Subject: [PATCH 0759/4345] ext4: check and assert if marking an no_delete evicting inode dirty commit 318cdc822c63b6e2befcfdc2088378ae6fa18def upstream. In ext4_evict_inode(), if we evicting an inode in the 'no_delete' path, it cannot be raced by another mark_inode_dirty(). If it happens, someone else may accidentally dirty it without holding inode refcount and probably cause use-after-free issues in the writeback procedure. It's indiscoverable and hard to debug, so add an WARN_ON_ONCE() to check and detect this issue in advance. Suggested-by: Jan Kara Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20220629112647.4141034-2-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0f9005cb1035..42fa3730e2d5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -336,6 +336,12 @@ stop_handle: ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: + /* + * Check out some where else accidentally dirty the evicting inode, + * which may probably cause inode use-after-free issues later. + */ + WARN_ON_ONCE(!list_empty_careful(&inode->i_io_list)); + if (!list_empty(&EXT4_I(inode)->i_fc_list)) ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ From 71e99ec1315fe98d322b17b9a28f204aaf15ffee Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 26 Oct 2022 12:23:10 +0800 Subject: [PATCH 0760/4345] ext4: fix bug_on in __es_tree_search caused by bad boot loader inode commit 991ed014de0840c5dc405b679168924afb2952ac upstream. We got a issue as fllows: ================================================================== kernel BUG at fs/ext4/extents_status.c:203! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 1 PID: 945 Comm: cat Not tainted 6.0.0-next-20221007-dirty #349 RIP: 0010:ext4_es_end.isra.0+0x34/0x42 RSP: 0018:ffffc9000143b768 EFLAGS: 00010203 RAX: 0000000000000000 RBX: ffff8881769cd0b8 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff8fc27cf7 RDI: 00000000ffffffff RBP: ffff8881769cd0bc R08: 0000000000000000 R09: ffffc9000143b5f8 R10: 0000000000000001 R11: 0000000000000001 R12: ffff8881769cd0a0 R13: ffff8881768e5668 R14: 00000000768e52f0 R15: 0000000000000000 FS: 00007f359f7f05c0(0000)GS:ffff88842fd00000(0000)knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f359f5a2000 CR3: 000000017130c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __es_tree_search.isra.0+0x6d/0xf5 ext4_es_cache_extent+0xfa/0x230 ext4_cache_extents+0xd2/0x110 ext4_find_extent+0x5d5/0x8c0 ext4_ext_map_blocks+0x9c/0x1d30 ext4_map_blocks+0x431/0xa50 ext4_mpage_readpages+0x48e/0xe40 ext4_readahead+0x47/0x50 read_pages+0x82/0x530 page_cache_ra_unbounded+0x199/0x2a0 do_page_cache_ra+0x47/0x70 page_cache_ra_order+0x242/0x400 ondemand_readahead+0x1e8/0x4b0 page_cache_sync_ra+0xf4/0x110 filemap_get_pages+0x131/0xb20 filemap_read+0xda/0x4b0 generic_file_read_iter+0x13a/0x250 ext4_file_read_iter+0x59/0x1d0 vfs_read+0x28f/0x460 ksys_read+0x73/0x160 __x64_sys_read+0x1e/0x30 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd ================================================================== In the above issue, ioctl invokes the swap_inode_boot_loader function to swap inode<5> and inode<12>. However, inode<5> contain incorrect imode and disordered extents, and i_nlink is set to 1. The extents check for inode in the ext4_iget function can be bypassed bacause 5 is EXT4_BOOT_LOADER_INO. While links_count is set to 1, the extents are not initialized in swap_inode_boot_loader. After the ioctl command is executed successfully, the extents are swapped to inode<12>, in this case, run the `cat` command to view inode<12>. And Bug_ON is triggered due to the incorrect extents. When the boot loader inode is not initialized, its imode can be one of the following: 1) the imode is a bad type, which is marked as bad_inode in ext4_iget and set to S_IFREG. 2) the imode is good type but not S_IFREG. 3) the imode is S_IFREG. The BUG_ON may be triggered by bypassing the check in cases 1 and 2. Therefore, when the boot loader inode is bad_inode or its imode is not S_IFREG, initialize the inode to avoid triggering the BUG. Signed-off-by: Baokun Li Reviewed-by: Jason Yan Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221026042310.3839669-5-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 879e637ef3e1..9a3d893cd390 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -171,7 +171,7 @@ static long swap_inode_boot_loader(struct super_block *sb, /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); - if (inode_bl->i_nlink == 0) { + if (is_bad_inode(inode_bl) || !S_ISREG(inode_bl->i_mode)) { /* this inode has never been used as a BOOT_LOADER */ set_nlink(inode_bl, 1); i_uid_write(inode_bl, 0); From 84a2f2ed49d6a4d92b354219077434c57d334620 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Mon, 7 Nov 2022 09:53:35 +0800 Subject: [PATCH 0761/4345] ext4: init quota for 'old.inode' in 'ext4_rename' commit fae381a3d79bb94aa2eb752170d47458d778b797 upstream. Syzbot found the following issue: ext4_parse_param: s_want_extra_isize=128 ext4_inode_info_init: s_want_extra_isize=32 ext4_rename: old.inode=ffff88823869a2c8 old.dir=ffff888238699828 new.inode=ffff88823869d7e8 new.dir=ffff888238699828 __ext4_mark_inode_dirty: inode=ffff888238699828 ea_isize=32 want_ea_size=128 __ext4_mark_inode_dirty: inode=ffff88823869a2c8 ea_isize=32 want_ea_size=128 ext4_xattr_block_set: inode=ffff88823869a2c8 ------------[ cut here ]------------ WARNING: CPU: 13 PID: 2234 at fs/ext4/xattr.c:2070 ext4_xattr_block_set.cold+0x22/0x980 Modules linked in: RIP: 0010:ext4_xattr_block_set.cold+0x22/0x980 RSP: 0018:ffff888227d3f3b0 EFLAGS: 00010202 RAX: 0000000000000001 RBX: ffff88823007a000 RCX: 0000000000000000 RDX: 0000000000000a03 RSI: 0000000000000040 RDI: ffff888230078178 RBP: 0000000000000000 R08: 000000000000002c R09: ffffed1075c7df8e R10: ffff8883ae3efc6b R11: ffffed1075c7df8d R12: 0000000000000000 R13: ffff88823869a2c8 R14: ffff8881012e0460 R15: dffffc0000000000 FS: 00007f350ac1f740(0000) GS:ffff8883ae200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f350a6ed6a0 CR3: 0000000237456000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? ext4_xattr_set_entry+0x3b7/0x2320 ? ext4_xattr_block_set+0x0/0x2020 ? ext4_xattr_set_entry+0x0/0x2320 ? ext4_xattr_check_entries+0x77/0x310 ? ext4_xattr_ibody_set+0x23b/0x340 ext4_xattr_move_to_block+0x594/0x720 ext4_expand_extra_isize_ea+0x59a/0x10f0 __ext4_expand_extra_isize+0x278/0x3f0 __ext4_mark_inode_dirty.cold+0x347/0x410 ext4_rename+0xed3/0x174f vfs_rename+0x13a7/0x2510 do_renameat2+0x55d/0x920 __x64_sys_rename+0x7d/0xb0 do_syscall_64+0x3b/0xa0 entry_SYSCALL_64_after_hwframe+0x72/0xdc As 'ext4_rename' will modify 'old.inode' ctime and mark inode dirty, which may trigger expand 'extra_isize' and allocate block. If inode didn't init quota will lead to warning. To solve above issue, init 'old.inode' firstly in 'ext4_rename'. Reported-by: syzbot+98346927678ac3059c77@syzkaller.appspotmail.com Signed-off-by: Ye Bin Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221107015335.2524319-1-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/namei.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index b2e131d11cf8..c17d5f399f9e 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3842,6 +3842,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, return -EXDEV; retval = dquot_initialize(old.dir); + if (retval) + return retval; + retval = dquot_initialize(old.inode); if (retval) return retval; retval = dquot_initialize(new.dir); From 9404839e0c9db5a517ea83c0ca3388b39d105fdf Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Thu, 17 Nov 2022 10:22:07 -0500 Subject: [PATCH 0762/4345] ext4: fix delayed allocation bug in ext4_clu_mapped for bigalloc + inline commit 131294c35ed6f777bd4e79d42af13b5c41bf2775 upstream. When converting files with inline data to extents, delayed allocations made on a file system created with both the bigalloc and inline options can result in invalid extent status cache content, incorrect reserved cluster counts, kernel memory leaks, and potential kernel panics. With bigalloc, the code that determines whether a block must be delayed allocated searches the extent tree to see if that block maps to a previously allocated cluster. If not, the block is delayed allocated, and otherwise, it isn't. However, if the inline option is also used, and if the file containing the block is marked as able to store data inline, there isn't a valid extent tree associated with the file. The current code in ext4_clu_mapped() calls ext4_find_extent() to search the non-existent tree for a previously allocated cluster anyway, which typically finds nothing, as desired. However, a side effect of the search can be to cache invalid content from the non-existent tree (garbage) in the extent status tree, including bogus entries in the pending reservation tree. To fix this, avoid searching the extent tree when allocating blocks for bigalloc + inline files that are being converted from inline to extent mapped. Signed-off-by: Eric Whitney Link: https://lore.kernel.org/r/20221117152207.2424-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/extents.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 54750b7c162d..bf0872bb34f6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5802,6 +5802,14 @@ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) struct ext4_extent *extent; ext4_lblk_t first_lblk, first_lclu, last_lclu; + /* + * if data can be stored inline, the logical cluster isn't + * mapped - no physical clusters have been allocated, and the + * file has no extents + */ + if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) + return 0; + /* search for the extent closest to the first block in the cluster */ path = ext4_find_extent(inode, EXT4_C2B(sbi, lclu), NULL, 0); if (IS_ERR(path)) { From f06c980287f165d4e8e0628de0cdcda87ffa022f Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Thu, 17 Nov 2022 12:03:41 +0800 Subject: [PATCH 0763/4345] ext4: fix corruption when online resizing a 1K bigalloc fs commit 0aeaa2559d6d53358fca3e3fce73807367adca74 upstream. When a backup superblock is updated in update_backups(), the primary superblock's offset in the group (that is, sbi->s_sbh->b_blocknr) is used as the backup superblock's offset in its group. However, when the block size is 1K and bigalloc is enabled, the two offsets are not equal. This causes the backup group descriptors to be overwritten by the superblock in update_backups(). Moreover, if meta_bg is enabled, the file system will be corrupted because this feature uses backup group descriptors. To solve this issue, we use a more accurate ext4_group_first_block_no() as the offset of the backup superblock in its group. Fixes: d77147ff443b ("ext4: add support for online resizing with bigalloc") Signed-off-by: Baokun Li Reviewed-by: Jan Kara Cc: stable@kernel.org Link: https://lore.kernel.org/r/20221117040341.1380702-4-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/resize.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c55ba0390021..51cebc1990eb 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1545,8 +1545,8 @@ exit_journal: int meta_bg = ext4_has_feature_meta_bg(sb); sector_t old_gdb = 0; - update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es, - sizeof(struct ext4_super_block), 0); + update_backups(sb, ext4_group_first_block_no(sb, 0), + (char *)es, sizeof(struct ext4_super_block), 0); for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; @@ -1753,7 +1753,7 @@ errout: if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: extended group to %llu " "blocks\n", ext4_blocks_count(es)); - update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, + update_backups(sb, ext4_group_first_block_no(sb, 0), (char *)es, sizeof(struct ext4_super_block), 0); } return err; From 00092b218d2b06603dda6043dac6313cb61f18a8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= Date: Wed, 9 Nov 2022 18:14:45 +0000 Subject: [PATCH 0764/4345] ext4: fix error code return to user-space in ext4_get_branch() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 26d75a16af285a70863ba6a81f85d81e7e65da50 upstream. If a block is out of range in ext4_get_branch(), -ENOMEM will be returned to user-space. Obviously, this error code isn't really useful. This patch fixes it by making sure the right error code (-EFSCORRUPTED) is propagated to user-space. EUCLEAN is more informative than ENOMEM. Signed-off-by: Luís Henriques Link: https://lore.kernel.org/r/20221109181445.17843-1-lhenriques@suse.de Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/indirect.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 05efa682bc2f..b7d130f4b5e4 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -148,6 +148,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, struct super_block *sb = inode->i_sb; Indirect *p = chain; struct buffer_head *bh; + unsigned int key; int ret = -EIO; *err = 0; @@ -156,7 +157,13 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, if (!p->key) goto no_block; while (--depth) { - bh = sb_getblk(sb, le32_to_cpu(p->key)); + key = le32_to_cpu(p->key); + if (key > ext4_blocks_count(EXT4_SB(sb)->s_es)) { + /* the block was out of range */ + ret = -EFSCORRUPTED; + goto failure; + } + bh = sb_getblk(sb, key); if (unlikely(!bh)) { ret = -ENOMEM; goto failure; From 407f47728c6cce8e37f9dbd11fd659d0fd251c46 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 21 Nov 2022 14:09:29 +0100 Subject: [PATCH 0765/4345] ext4: avoid BUG_ON when creating xattrs commit b40ebaf63851b3a401b0dc9263843538f64f5ce6 upstream. Commit fb0a387dcdcd ("ext4: limit block allocations for indirect-block files to < 2^32") added code to try to allocate xattr block with 32-bit block number for indirect block based files on the grounds that these files cannot use larger block numbers. It also added BUG_ON when allocated block could not fit into 32 bits. This is however bogus reasoning because xattr block is stored in inode->i_file_acl and inode->i_file_acl_hi and as such even indirect block based files can happily use full 48 bits for xattr block number. The proper handling seems to be there basically since 64-bit block number support was added. So remove the bogus limitation and BUG_ON. Cc: Eric Sandeen Fixes: fb0a387dcdcd ("ext4: limit block allocations for indirect-block files to < 2^32") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20221121130929.32031-1-jack@suse.cz Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 38531c5e16c6..e75bac97609c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2049,19 +2049,11 @@ inserted: goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); - - /* non-extent files can't have physical blocks past 2^32 */ - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; - block = ext4_new_meta_blocks(handle, inode, goal, 0, NULL, &error); if (error) goto cleanup; - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS); - ea_idebug(inode, "creating block %llu", (unsigned long long)block); From 9882601ee689975c1c0076ee65bf222a2a35e535 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 8 Dec 2022 10:32:33 +0800 Subject: [PATCH 0766/4345] ext4: fix inode leak in ext4_xattr_inode_create() on an error path commit e4db04f7d3dbbe16680e0ded27ea2a65b10f766a upstream. There is issue as follows when do setxattr with inject fault: [localhost]# fsck.ext4 -fn /dev/sda e2fsck 1.46.6-rc1 (12-Sep-2022) Pass 1: Checking inodes, blocks, and sizes Pass 2: Checking directory structure Pass 3: Checking directory connectivity Pass 4: Checking reference counts Unattached zero-length inode 15. Clear? no Unattached inode 15 Connect to /lost+found? no Pass 5: Checking group summary information /dev/sda: ********** WARNING: Filesystem still has errors ********** /dev/sda: 15/655360 files (0.0% non-contiguous), 66755/2621440 blocks This occurs in 'ext4_xattr_inode_create()'. If 'ext4_mark_inode_dirty()' fails, dropping i_nlink of the inode is needed. Or will lead to inode leak. Signed-off-by: Ye Bin Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221208023233.1231330-5-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index e75bac97609c..346334cadb6a 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1425,6 +1425,9 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle, if (!err) err = ext4_inode_attach_jinode(ea_inode); if (err) { + if (ext4_xattr_inode_dec_ref(handle, ea_inode)) + ext4_warning_inode(ea_inode, + "cleanup dec ref error %d", err); iput(ea_inode); return ERR_PTR(err); } From 15d0cf84df077fc0007df098803dc910a1a087c9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 7 Dec 2022 12:59:27 +0100 Subject: [PATCH 0767/4345] ext4: initialize quota before expanding inode in setproject ioctl commit 1485f726c6dec1a1f85438f2962feaa3d585526f upstream. Make sure we initialize quotas before possibly expanding inode space (and thus maybe needing to allocate external xattr block) in ext4_ioctl_setproject(). This prevents not accounting the necessary block allocation. Signed-off-by: Jan Kara Cc: stable@kernel.org Link: https://lore.kernel.org/r/20221207115937.26601-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ioctl.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 9a3d893cd390..240d792db9f7 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -495,6 +495,10 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) if (ext4_is_quota_file(inode)) return err; + err = dquot_initialize(inode); + if (err) + return err; + err = ext4_get_inode_loc(inode, &iloc); if (err) return err; @@ -510,10 +514,6 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) brelse(iloc.bh); } - err = dquot_initialize(inode); - if (err) - return err; - handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(sb) + EXT4_QUOTA_DEL_BLOCKS(sb) + 3); From 8d3e87d43c62ac1d0ffc9f55c47942cfe585fa56 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 7 Dec 2022 12:59:28 +0100 Subject: [PATCH 0768/4345] ext4: avoid unaccounted block allocation when expanding inode commit 8994d11395f8165b3deca1971946f549f0822630 upstream. When expanding inode space in ext4_expand_extra_isize_ea() we may need to allocate external xattr block. If quota is not initialized for the inode, the block allocation will not be accounted into quota usage. Make sure the quota is initialized before we try to expand inode space. Reported-by: Pengfei Xu Link: https://lore.kernel.org/all/Y5BT+k6xWqthZc1P@xpf.sh.intel.com Signed-off-by: Jan Kara Cc: stable@kernel.org Link: https://lore.kernel.org/r/20221207115937.26601-2-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 42fa3730e2d5..d7dbe1eb9da0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5879,6 +5879,14 @@ static int __ext4_expand_extra_isize(struct inode *inode, return 0; } + /* + * We may need to allocate external xattr block so we need quotas + * initialized. Here we can be called with various locks held so we + * cannot affort to initialize quotas ourselves. So just bail. + */ + if (dquot_initialize_needed(inode)) + return -EAGAIN; + /* try to expand with EAs present */ error = ext4_expand_extra_isize_ea(inode, new_extra_isize, raw_inode, handle); From 30e95fdc9609f79c3a9818edeafdf17ab39b2a11 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 8 Dec 2022 10:32:31 +0800 Subject: [PATCH 0769/4345] ext4: allocate extended attribute value in vmalloc area commit cc12a6f25e07ed05d5825a1664b67a970842b2ca upstream. Now, extended attribute value maximum length is 64K. The memory requested here does not need continuous physical addresses, so it is appropriate to use kvmalloc to request memory. At the same time, it can also cope with the situation that the extended attribute will become longer in the future. Signed-off-by: Ye Bin Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221208023233.1231330-3-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 346334cadb6a..795ef72f0d3c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2551,7 +2551,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); - buffer = kmalloc(value_size, GFP_NOFS); + buffer = kvmalloc(value_size, GFP_NOFS); b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS); if (!is || !bs || !buffer || !b_entry_name) { error = -ENOMEM; @@ -2603,7 +2603,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, error = 0; out: kfree(b_entry_name); - kfree(buffer); + kvfree(buffer); if (is) brelse(is->iloc.bh); if (bs) From dfc01905b87049229fab9ef8b41dd2ecdbf6813f Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 21 Nov 2022 15:52:19 -0500 Subject: [PATCH 0770/4345] drm/amdgpu: handle polaris10/11 overlap asics (v2) commit 1d4624cd72b912b2680c08d0be48338a1629a858 upstream. Some special polaris 10 chips overlap with the polaris11 DID range. Handle this properly in the driver. v2: use local flags for other function calls. Acked-by: Luben Tuikov Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 30659c1776e8..0d8c1c318ce8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1121,6 +1121,15 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, "See modparam exp_hw_support\n"); return -ENODEV; } + /* differentiate between P10 and P11 asics with the same DID */ + if (pdev->device == 0x67FF && + (pdev->revision == 0xE3 || + pdev->revision == 0xE7 || + pdev->revision == 0xF3 || + pdev->revision == 0xF7)) { + flags &= ~AMD_ASIC_MASK; + flags |= CHIP_POLARIS10; + } /* Due to hardware bugs, S/G Display on raven requires a 1:1 IOMMU mapping, * however, SME requires an indirect IOMMU mapping because the encryption @@ -1190,12 +1199,12 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, ddev->pdev = pdev; pci_set_drvdata(pdev, ddev); - ret = amdgpu_driver_load_kms(adev, ent->driver_data); + ret = amdgpu_driver_load_kms(adev, flags); if (ret) goto err_pci; retry_init: - ret = drm_dev_register(ddev, ent->driver_data); + ret = drm_dev_register(ddev, flags); if (ret == -EAGAIN && ++retry <= 3) { DRM_INFO("retry init %d\n", retry); /* Don't request EX mode too frequently which is attacking */ From 630270978483a63dd641c1183a179437ab4900df Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 7 Dec 2022 11:08:53 -0500 Subject: [PATCH 0771/4345] drm/amdgpu: make display pinning more flexible (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 81d0bcf9900932633d270d5bc4a54ff599c6ebdb upstream. Only apply the static threshold for Stoney and Carrizo. This hardware has certain requirements that don't allow mixing of GTT and VRAM. Newer asics do not have these requirements so we should be able to be more flexible with where buffers end up. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2270 Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2291 Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2255 Acked-by: Luben Tuikov Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 6937f8134008..b6ce64b87f48 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1531,7 +1531,8 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo) uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev, uint32_t domain) { - if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) { + if ((domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) && + ((adev->asic_type == CHIP_CARRIZO) || (adev->asic_type == CHIP_STONEY))) { domain = AMDGPU_GEM_DOMAIN_VRAM; if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD) domain = AMDGPU_GEM_DOMAIN_GTT; From 9620f8a5c72f57074ac09d5e392de89f0c02d60a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 4 Jan 2023 07:48:37 -0700 Subject: [PATCH 0772/4345] ARM: renumber bits related to _TIF_WORK_MASK commit 191f8453fc99a537ea78b727acea739782378b0d upstream. We want to ensure that the mask related to calling do_work_pending() is within the first 16 bits. Move bits unrelated to that outside of that range, to avoid spuriously calling do_work_pending() when we don't need to. Cc: stable@vger.kernel.org Fixes: 32d59773da38 ("arm: add support for TIF_NOTIFY_SIGNAL") Reported-and-tested-by: Hui Tang Suggested-by: Russell King (Oracle) Link: https://lore.kernel.org/lkml/7ecb8f3c-2aeb-a905-0d4a-aa768b9649b5@huawei.com/ Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- arch/arm/include/asm/thread_info.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index eb7ce2747eb0..fcccf35f5cf9 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -133,15 +133,16 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, #define TIF_NEED_RESCHED 1 /* rescheduling necessary */ #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ #define TIF_UPROBE 3 /* breakpointed or singlestepping */ -#define TIF_SYSCALL_TRACE 4 /* syscall trace active */ -#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ -#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ -#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ -#define TIF_NOTIFY_SIGNAL 8 /* signal notifications exist */ +#define TIF_NOTIFY_SIGNAL 4 /* signal notifications exist */ #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ -#define TIF_RESTORE_SIGMASK 20 +#define TIF_RESTORE_SIGMASK 19 +#define TIF_SYSCALL_TRACE 20 /* syscall trace active */ +#define TIF_SYSCALL_AUDIT 21 /* syscall auditing active */ +#define TIF_SYSCALL_TRACEPOINT 22 /* syscall tracepoint instrumentation */ +#define TIF_SECCOMP 23 /* seccomp syscall filtering active */ + #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) From 53d24a9592eb7a34e03f5449b67151b0a3b1ed1f Mon Sep 17 00:00:00 2001 From: Alexander Antonov Date: Mon, 26 Apr 2021 16:16:12 +0300 Subject: [PATCH 0773/4345] perf/x86/intel/uncore: Generalize I/O stacks to PMON mapping procedure [ Upstream commit f471fac77b41a2573c7b677ef790bf18a0e64195 ] Currently I/O stacks to IIO PMON mapping is available on Skylake servers only and need to make code more general to easily enable further platforms. So, introduce get_topology() callback in struct intel_uncore_type which allows to move common code to separate function and make mapping procedure more general. Signed-off-by: Alexander Antonov Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kan Liang Link: https://lkml.kernel.org/r/20210426131614.16205-2-alexander.antonov@linux.intel.com Signed-off-by: Sasha Levin --- arch/x86/events/intel/uncore.h | 1 + arch/x86/events/intel/uncore_snbep.c | 28 +++++++++++++++++++++------- 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 9efea154349d..4e2953a9eff0 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -84,6 +84,7 @@ struct intel_uncore_type { /* * Optional callbacks for managing mapping of Uncore units to PMONs */ + int (*get_topology)(struct intel_uncore_type *type); int (*set_mapping)(struct intel_uncore_type *type); void (*cleanup_mapping)(struct intel_uncore_type *type); }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 2fd49cd515f5..03e34a440cdf 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3643,12 +3643,19 @@ static inline u8 skx_iio_stack(struct intel_uncore_pmu *pmu, int die) } static umode_t -skx_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die) +pmu_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, + int die, int zero_bus_pmu) { struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(kobj_to_dev(kobj)); - /* Root bus 0x00 is valid only for die 0 AND pmu_idx = 0. */ - return (!skx_iio_stack(pmu, die) && pmu->pmu_idx) ? 0 : attr->mode; + return (!skx_iio_stack(pmu, die) && pmu->pmu_idx != zero_bus_pmu) ? 0 : attr->mode; +} + +static umode_t +skx_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die) +{ + /* Root bus 0x00 is valid only for pmu_idx = 0. */ + return pmu_iio_mapping_visible(kobj, attr, die, 0); } static ssize_t skx_iio_mapping_show(struct device *dev, @@ -3740,7 +3747,8 @@ static const struct attribute_group *skx_iio_attr_update[] = { NULL, }; -static int skx_iio_set_mapping(struct intel_uncore_type *type) +static int +pmu_iio_set_mapping(struct intel_uncore_type *type, struct attribute_group *ag) { char buf[64]; int ret; @@ -3748,8 +3756,8 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type) struct attribute **attrs = NULL; struct dev_ext_attribute *eas = NULL; - ret = skx_iio_get_topology(type); - if (ret) + ret = type->get_topology(type); + if (ret < 0) goto clear_attr_update; ret = -ENOMEM; @@ -3775,7 +3783,7 @@ static int skx_iio_set_mapping(struct intel_uncore_type *type) eas[die].var = (void *)die; attrs[die] = &eas[die].attr.attr; } - skx_iio_mapping_group.attrs = attrs; + ag->attrs = attrs; return 0; err: @@ -3791,6 +3799,11 @@ clear_attr_update: return ret; } +static int skx_iio_set_mapping(struct intel_uncore_type *type) +{ + return pmu_iio_set_mapping(type, &skx_iio_mapping_group); +} + static void skx_iio_cleanup_mapping(struct intel_uncore_type *type) { struct attribute **attr = skx_iio_mapping_group.attrs; @@ -3821,6 +3834,7 @@ static struct intel_uncore_type skx_uncore_iio = { .ops = &skx_uncore_iio_ops, .format_group = &skx_uncore_iio_format_group, .attr_update = skx_iio_attr_update, + .get_topology = skx_iio_get_topology, .set_mapping = skx_iio_set_mapping, .cleanup_mapping = skx_iio_cleanup_mapping, }; From 7a04f850092460ecba9f5ba165ac1c74ccfc2e84 Mon Sep 17 00:00:00 2001 From: Alexander Antonov Date: Thu, 17 Nov 2022 12:28:25 +0000 Subject: [PATCH 0774/4345] perf/x86/intel/uncore: Clear attr_update properly [ Upstream commit 6532783310e2b2f50dc13f46c49aa6546cb6e7a3 ] Current clear_attr_update procedure in pmu_set_mapping() sets attr_update field in NULL that is not correct because intel_uncore_type pmu types can contain several groups in attr_update field. For example, SPR platform already has uncore_alias_group to update and then UPI topology group will be added in next patches. Fix current behavior and clear attr_update group related to mapping only. Fixes: bb42b3d39781 ("perf/x86/intel/uncore: Expose an Uncore unit to IIO PMON mapping") Signed-off-by: Alexander Antonov Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kan Liang Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221117122833.3103580-4-alexander.antonov@linux.intel.com Signed-off-by: Sasha Levin --- arch/x86/events/intel/uncore_snbep.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 03e34a440cdf..ad084a5a1463 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3747,6 +3747,21 @@ static const struct attribute_group *skx_iio_attr_update[] = { NULL, }; +static void pmu_clear_mapping_attr(const struct attribute_group **groups, + struct attribute_group *ag) +{ + int i; + + for (i = 0; groups[i]; i++) { + if (groups[i] == ag) { + for (i++; groups[i]; i++) + groups[i - 1] = groups[i]; + groups[i - 1] = NULL; + break; + } + } +} + static int pmu_iio_set_mapping(struct intel_uncore_type *type, struct attribute_group *ag) { @@ -3795,7 +3810,7 @@ clear_attrs: clear_topology: kfree(type->topology); clear_attr_update: - type->attr_update = NULL; + pmu_clear_mapping_attr(type->attr_update, ag); return ret; } From 58de7a95f0e6c6da3f40fd0c49cfaf1cc06e21cc Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 4 Jan 2023 11:14:45 -0500 Subject: [PATCH 0775/4345] btrfs: replace strncpy() with strscpy() [ Upstream commit 63d5429f68a3d4c4aa27e65a05196c17f86c41d6 ] Using strncpy() on NUL-terminated strings are deprecated. To avoid possible forming of non-terminated string strscpy() should be used. Found by Linux Verification Center (linuxtesting.org) with SVACE. CC: stable@vger.kernel.org # 4.9+ Signed-off-by: Artem Chernyshev Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/ioctl.c | 9 +++------ fs/btrfs/rcu-string.h | 6 +++++- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a17076a05c4d..fc335b5e44df 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3401,13 +3401,10 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, di_args->bytes_used = btrfs_device_get_bytes_used(dev); di_args->total_bytes = btrfs_device_get_total_bytes(dev); memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid)); - if (dev->name) { - strncpy(di_args->path, rcu_str_deref(dev->name), - sizeof(di_args->path) - 1); - di_args->path[sizeof(di_args->path) - 1] = 0; - } else { + if (dev->name) + strscpy(di_args->path, rcu_str_deref(dev->name), sizeof(di_args->path)); + else di_args->path[0] = '\0'; - } out: rcu_read_unlock(); diff --git a/fs/btrfs/rcu-string.h b/fs/btrfs/rcu-string.h index 5c1a617eb25d..5c2b66d155ef 100644 --- a/fs/btrfs/rcu-string.h +++ b/fs/btrfs/rcu-string.h @@ -18,7 +18,11 @@ static inline struct rcu_string *rcu_string_strdup(const char *src, gfp_t mask) (len * sizeof(char)), mask); if (!ret) return ret; - strncpy(ret->str, src, len); + /* Warn if the source got unexpectedly truncated. */ + if (WARN_ON(strscpy(ret->str, src, len) < 0)) { + kfree(ret); + return NULL; + } return ret; } From ec75bc43681bb1fc0695168123004a50b12aa9b3 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 2 Sep 2021 13:33:22 +0200 Subject: [PATCH 0776/4345] x86/mce: Get rid of msr_ops [ Upstream commit 8121b8f947be0033f567619be204639a50cad298 ] Avoid having indirect calls and use a normal function which returns the proper MSR address based on ->smca setting. No functional changes. Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Link: https://lkml.kernel.org/r/20210922165101.18951-4-bp@alien8.de Stable-dep-of: bc1b705b0eee ("x86/MCE/AMD: Clear DFR errors found in THR handler") Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/mce/amd.c | 10 ++-- arch/x86/kernel/cpu/mce/core.c | 95 ++++++++++-------------------- arch/x86/kernel/cpu/mce/internal.h | 12 ++-- 3 files changed, 42 insertions(+), 75 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 09f7c652346a..34ebe1aea1c7 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -513,7 +513,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high, /* Fall back to method we used for older processors: */ switch (block) { case 0: - addr = msr_ops.misc(bank); + addr = mca_msr_reg(bank, MCA_MISC); break; case 1: offset = ((low & MASK_BLKPTR_LO) >> 21); @@ -965,8 +965,8 @@ static void log_error_deferred(unsigned int bank) { bool defrd; - defrd = _log_error_bank(bank, msr_ops.status(bank), - msr_ops.addr(bank), 0); + defrd = _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), + mca_msr_reg(bank, MCA_ADDR), 0); if (!mce_flags.smca) return; @@ -996,7 +996,7 @@ static void amd_deferred_error_interrupt(void) static void log_error_thresholding(unsigned int bank, u64 misc) { - _log_error_bank(bank, msr_ops.status(bank), msr_ops.addr(bank), misc); + _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), mca_msr_reg(bank, MCA_ADDR), misc); } static void log_and_reset_block(struct threshold_block *block) @@ -1384,7 +1384,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, } } - err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank)); + err = allocate_threshold_blocks(cpu, b, bank, 0, mca_msr_reg(bank, MCA_MISC)); if (err) goto out_kobj; diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 5cf1a024408b..1906387a0faf 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -176,53 +176,27 @@ void mce_unregister_decode_chain(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); -static inline u32 ctl_reg(int bank) +u32 mca_msr_reg(int bank, enum mca_msr reg) { - return MSR_IA32_MCx_CTL(bank); -} + if (mce_flags.smca) { + switch (reg) { + case MCA_CTL: return MSR_AMD64_SMCA_MCx_CTL(bank); + case MCA_ADDR: return MSR_AMD64_SMCA_MCx_ADDR(bank); + case MCA_MISC: return MSR_AMD64_SMCA_MCx_MISC(bank); + case MCA_STATUS: return MSR_AMD64_SMCA_MCx_STATUS(bank); + } + } -static inline u32 status_reg(int bank) -{ - return MSR_IA32_MCx_STATUS(bank); -} + switch (reg) { + case MCA_CTL: return MSR_IA32_MCx_CTL(bank); + case MCA_ADDR: return MSR_IA32_MCx_ADDR(bank); + case MCA_MISC: return MSR_IA32_MCx_MISC(bank); + case MCA_STATUS: return MSR_IA32_MCx_STATUS(bank); + } -static inline u32 addr_reg(int bank) -{ - return MSR_IA32_MCx_ADDR(bank); + return 0; } -static inline u32 misc_reg(int bank) -{ - return MSR_IA32_MCx_MISC(bank); -} - -static inline u32 smca_ctl_reg(int bank) -{ - return MSR_AMD64_SMCA_MCx_CTL(bank); -} - -static inline u32 smca_status_reg(int bank) -{ - return MSR_AMD64_SMCA_MCx_STATUS(bank); -} - -static inline u32 smca_addr_reg(int bank) -{ - return MSR_AMD64_SMCA_MCx_ADDR(bank); -} - -static inline u32 smca_misc_reg(int bank) -{ - return MSR_AMD64_SMCA_MCx_MISC(bank); -} - -struct mca_msr_regs msr_ops = { - .ctl = ctl_reg, - .status = status_reg, - .addr = addr_reg, - .misc = misc_reg -}; - static void __print_mce(struct mce *m) { pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n", @@ -371,11 +345,11 @@ static int msr_to_offset(u32 msr) if (msr == mca_cfg.rip_msr) return offsetof(struct mce, ip); - if (msr == msr_ops.status(bank)) + if (msr == mca_msr_reg(bank, MCA_STATUS)) return offsetof(struct mce, status); - if (msr == msr_ops.addr(bank)) + if (msr == mca_msr_reg(bank, MCA_ADDR)) return offsetof(struct mce, addr); - if (msr == msr_ops.misc(bank)) + if (msr == mca_msr_reg(bank, MCA_MISC)) return offsetof(struct mce, misc); if (msr == MSR_IA32_MCG_STATUS) return offsetof(struct mce, mcgstatus); @@ -694,10 +668,10 @@ static struct notifier_block mce_default_nb = { static noinstr void mce_read_aux(struct mce *m, int i) { if (m->status & MCI_STATUS_MISCV) - m->misc = mce_rdmsrl(msr_ops.misc(i)); + m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC)); if (m->status & MCI_STATUS_ADDRV) { - m->addr = mce_rdmsrl(msr_ops.addr(i)); + m->addr = mce_rdmsrl(mca_msr_reg(i, MCA_ADDR)); /* * Mask the reported address by the reported granularity. @@ -767,7 +741,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) m.bank = i; barrier(); - m.status = mce_rdmsrl(msr_ops.status(i)); + m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); /* If this entry is not valid, ignore it */ if (!(m.status & MCI_STATUS_VAL)) @@ -835,7 +809,7 @@ clear_it: /* * Clear state for this bank. */ - mce_wrmsrl(msr_ops.status(i), 0); + mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); } /* @@ -860,7 +834,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, int i; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { - m->status = mce_rdmsrl(msr_ops.status(i)); + m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); if (!(m->status & MCI_STATUS_VAL)) continue; @@ -1149,7 +1123,7 @@ static void mce_clear_state(unsigned long *toclear) for (i = 0; i < this_cpu_read(mce_num_banks); i++) { if (test_bit(i, toclear)) - mce_wrmsrl(msr_ops.status(i), 0); + mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); } } @@ -1208,7 +1182,7 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin m->addr = 0; m->bank = i; - m->status = mce_rdmsrl(msr_ops.status(i)); + m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); if (!(m->status & MCI_STATUS_VAL)) continue; @@ -1704,8 +1678,8 @@ static void __mcheck_cpu_init_clear_banks(void) if (!b->init) continue; - wrmsrl(msr_ops.ctl(i), b->ctl); - wrmsrl(msr_ops.status(i), 0); + wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl); + wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); } } @@ -1731,7 +1705,7 @@ static void __mcheck_cpu_check_banks(void) if (!b->init) continue; - rdmsrl(msr_ops.ctl(i), msrval); + rdmsrl(mca_msr_reg(i, MCA_CTL), msrval); b->init = !!msrval; } } @@ -1890,13 +1864,6 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); mce_flags.amd_threshold = 1; - - if (mce_flags.smca) { - msr_ops.ctl = smca_ctl_reg; - msr_ops.status = smca_status_reg; - msr_ops.addr = smca_addr_reg; - msr_ops.misc = smca_misc_reg; - } } } @@ -2272,7 +2239,7 @@ static void mce_disable_error_reporting(void) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(msr_ops.ctl(i), 0); + wrmsrl(mca_msr_reg(i, MCA_CTL), 0); } return; } @@ -2624,7 +2591,7 @@ static void mce_reenable_cpu(void) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(msr_ops.ctl(i), b->ctl); + wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl); } } diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 88dcc79cfb07..3a485c0d5791 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -168,14 +168,14 @@ struct mce_vendor_flags { extern struct mce_vendor_flags mce_flags; -struct mca_msr_regs { - u32 (*ctl) (int bank); - u32 (*status) (int bank); - u32 (*addr) (int bank); - u32 (*misc) (int bank); +enum mca_msr { + MCA_CTL, + MCA_STATUS, + MCA_ADDR, + MCA_MISC, }; -extern struct mca_msr_regs msr_ops; +u32 mca_msr_reg(int bank, enum mca_msr reg); /* Decide whether to add MCE record to MCE event pool or filter it out. */ extern bool filter_mce(struct mce *m); From 97e7896000cef10156e2ce7c55a8e4befb00dfed Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Tue, 21 Jun 2022 15:59:43 +0000 Subject: [PATCH 0777/4345] x86/MCE/AMD: Clear DFR errors found in THR handler [ Upstream commit bc1b705b0eee4c645ad8b3bbff3c8a66e9688362 ] AMD's MCA Thresholding feature counts errors of all severity levels, not just correctable errors. If a deferred error causes the threshold limit to be reached (it was the error that caused the overflow), then both a deferred error interrupt and a thresholding interrupt will be triggered. The order of the interrupts is not guaranteed. If the threshold interrupt handler is executed first, then it will clear MCA_STATUS for the error. It will not check or clear MCA_DESTAT which also holds a copy of the deferred error. When the deferred error interrupt handler runs it will not find an error in MCA_STATUS, but it will find the error in MCA_DESTAT. This will cause two errors to be logged. Check for deferred errors when handling a threshold interrupt. If a bank contains a deferred error, then clear the bank's MCA_DESTAT register. Define a new helper function to do the deferred error check and clearing of MCA_DESTAT. [ bp: Simplify, convert comment to passive voice. ] Fixes: 37d43acfd79f ("x86/mce/AMD: Redo error logging from APIC LVT interrupt handlers") Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220621155943.33623-1-yazen.ghannam@amd.com Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/mce/amd.c | 33 ++++++++++++++++++++------------- 1 file changed, 20 insertions(+), 13 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 34ebe1aea1c7..4f9b7c1cfc36 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -952,6 +952,24 @@ _log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) return status & MCI_STATUS_DEFERRED; } +static bool _log_error_deferred(unsigned int bank, u32 misc) +{ + if (!_log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), + mca_msr_reg(bank, MCA_ADDR), misc)) + return false; + + /* + * Non-SMCA systems don't have MCA_DESTAT/MCA_DEADDR registers. + * Return true here to avoid accessing these registers. + */ + if (!mce_flags.smca) + return true; + + /* Clear MCA_DESTAT if the deferred error was logged from MCA_STATUS. */ + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); + return true; +} + /* * We have three scenarios for checking for Deferred errors: * @@ -963,20 +981,9 @@ _log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) */ static void log_error_deferred(unsigned int bank) { - bool defrd; - - defrd = _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), - mca_msr_reg(bank, MCA_ADDR), 0); - - if (!mce_flags.smca) + if (_log_error_deferred(bank, 0)) return; - /* Clear MCA_DESTAT if we logged the deferred error from MCA_STATUS. */ - if (defrd) { - wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); - return; - } - /* * Only deferred errors are logged in MCA_DE{STAT,ADDR} so just check * for a valid error. @@ -996,7 +1003,7 @@ static void amd_deferred_error_interrupt(void) static void log_error_thresholding(unsigned int bank, u64 misc) { - _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), mca_msr_reg(bank, MCA_ADDR), misc); + _log_error_deferred(bank, misc); } static void log_and_reset_block(struct threshold_block *block) From dcd1a4ade5902691e7224f5dcf154d49ebaf49b6 Mon Sep 17 00:00:00 2001 From: Smitha T Murthy Date: Wed, 7 Sep 2022 16:02:27 +0530 Subject: [PATCH 0778/4345] media: s5p-mfc: Fix to handle reference queue during finishing [ Upstream commit d8a46bc4e1e0446459daa77c4ce14218d32dacf9 ] On receiving last buffer driver puts MFC to MFCINST_FINISHING state which in turn skips transferring of frame from SRC to REF queue. This causes driver to stop MFC encoding and last frame is lost. This patch guarantees safe handling of frames during MFCINST_FINISHING and correct clearing of workbit to avoid early stopping of encoding. Fixes: af9357467810 ("[media] MFC: Add MFC 5.1 V4L2 driver") Cc: stable@vger.kernel.org Cc: linux-fsd@tesla.com Signed-off-by: Smitha T Murthy Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/s5p-mfc/s5p_mfc_enc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c index acc2217dd7e9..62a1ad347fa7 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c @@ -1218,6 +1218,7 @@ static int enc_post_frame_start(struct s5p_mfc_ctx *ctx) unsigned long mb_y_addr, mb_c_addr; int slice_type; unsigned int strm_size; + bool src_ready; slice_type = s5p_mfc_hw_call(dev->mfc_ops, get_enc_slice_type, dev); strm_size = s5p_mfc_hw_call(dev->mfc_ops, get_enc_strm_size, dev); @@ -1257,7 +1258,8 @@ static int enc_post_frame_start(struct s5p_mfc_ctx *ctx) } } } - if ((ctx->src_queue_cnt > 0) && (ctx->state == MFCINST_RUNNING)) { + if (ctx->src_queue_cnt > 0 && (ctx->state == MFCINST_RUNNING || + ctx->state == MFCINST_FINISHING)) { mb_entry = list_entry(ctx->src_queue.next, struct s5p_mfc_buf, list); if (mb_entry->flags & MFC_BUF_FLAG_USED) { @@ -1288,7 +1290,13 @@ static int enc_post_frame_start(struct s5p_mfc_ctx *ctx) vb2_set_plane_payload(&mb_entry->b->vb2_buf, 0, strm_size); vb2_buffer_done(&mb_entry->b->vb2_buf, VB2_BUF_STATE_DONE); } - if ((ctx->src_queue_cnt == 0) || (ctx->dst_queue_cnt == 0)) + + src_ready = true; + if (ctx->state == MFCINST_RUNNING && ctx->src_queue_cnt == 0) + src_ready = false; + if (ctx->state == MFCINST_FINISHING && ctx->ref_queue_cnt == 0) + src_ready = false; + if (!src_ready || ctx->dst_queue_cnt == 0) clear_work_bit(ctx); return 0; From 8ff64edf9d16e8c277dcc8189794763624e6b4b8 Mon Sep 17 00:00:00 2001 From: Smitha T Murthy Date: Wed, 7 Sep 2022 16:02:26 +0530 Subject: [PATCH 0779/4345] media: s5p-mfc: Clear workbit to handle error condition [ Upstream commit d3f3c2fe54e30b0636496d842ffbb5ad3a547f9b ] During error on CLOSE_INSTANCE command, ctx_work_bits was not getting cleared. During consequent mfc execution NULL pointer dereferencing of this context led to kernel panic. This patch fixes this issue by making sure to clear ctx_work_bits always. Fixes: 818cd91ab8c6 ("[media] s5p-mfc: Extract open/close MFC instance commands") Cc: stable@vger.kernel.org Cc: linux-fsd@tesla.com Signed-off-by: Smitha T Murthy Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c b/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c index da138c314963..58822ec5370e 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c @@ -468,8 +468,10 @@ void s5p_mfc_close_mfc_inst(struct s5p_mfc_dev *dev, struct s5p_mfc_ctx *ctx) s5p_mfc_hw_call(dev->mfc_ops, try_run, dev); /* Wait until instance is returned or timeout occurred */ if (s5p_mfc_wait_for_done_ctx(ctx, - S5P_MFC_R2H_CMD_CLOSE_INSTANCE_RET, 0)) + S5P_MFC_R2H_CMD_CLOSE_INSTANCE_RET, 0)){ + clear_work_bit_irqsave(ctx); mfc_err("Err returning instance\n"); + } /* Free resources */ s5p_mfc_hw_call(dev->mfc_ops, release_codec_buffers, ctx); From c0a3d2158437ae4ad0737f1bf052d0ee18fcd52d Mon Sep 17 00:00:00 2001 From: Smitha T Murthy Date: Wed, 7 Sep 2022 16:02:25 +0530 Subject: [PATCH 0780/4345] media: s5p-mfc: Fix in register read and write for H264 [ Upstream commit 06710cd5d2436135046898d7e4b9408c8bb99446 ] Few of the H264 encoder registers written were not getting reflected since the read values were not stored and getting overwritten. Fixes: 6a9c6f681257 ("[media] s5p-mfc: Add variants to access mfc registers") Cc: stable@vger.kernel.org Cc: linux-fsd@tesla.com Signed-off-by: Smitha T Murthy Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c index a1453053e31a..ef8169f6c428 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c @@ -1060,7 +1060,7 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx) } /* aspect ratio VUI */ - readl(mfc_regs->e_h264_options); + reg = readl(mfc_regs->e_h264_options); reg &= ~(0x1 << 5); reg |= ((p_h264->vui_sar & 0x1) << 5); writel(reg, mfc_regs->e_h264_options); @@ -1083,7 +1083,7 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx) /* intra picture period for H.264 open GOP */ /* control */ - readl(mfc_regs->e_h264_options); + reg = readl(mfc_regs->e_h264_options); reg &= ~(0x1 << 4); reg |= ((p_h264->open_gop & 0x1) << 4); writel(reg, mfc_regs->e_h264_options); @@ -1097,23 +1097,23 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx) } /* 'WEIGHTED_BI_PREDICTION' for B is disable */ - readl(mfc_regs->e_h264_options); + reg = readl(mfc_regs->e_h264_options); reg &= ~(0x3 << 9); writel(reg, mfc_regs->e_h264_options); /* 'CONSTRAINED_INTRA_PRED_ENABLE' is disable */ - readl(mfc_regs->e_h264_options); + reg = readl(mfc_regs->e_h264_options); reg &= ~(0x1 << 14); writel(reg, mfc_regs->e_h264_options); /* ASO */ - readl(mfc_regs->e_h264_options); + reg = readl(mfc_regs->e_h264_options); reg &= ~(0x1 << 6); reg |= ((p_h264->aso & 0x1) << 6); writel(reg, mfc_regs->e_h264_options); /* hier qp enable */ - readl(mfc_regs->e_h264_options); + reg = readl(mfc_regs->e_h264_options); reg &= ~(0x1 << 8); reg |= ((p_h264->open_gop & 0x1) << 8); writel(reg, mfc_regs->e_h264_options); @@ -1134,7 +1134,7 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx) writel(reg, mfc_regs->e_h264_num_t_layer); /* frame packing SEI generation */ - readl(mfc_regs->e_h264_options); + reg = readl(mfc_regs->e_h264_options); reg &= ~(0x1 << 25); reg |= ((p_h264->sei_frame_packing & 0x1) << 25); writel(reg, mfc_regs->e_h264_options); From b5d0f7c24088b7b2bfd26419ac05ef840d3c2799 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 1 Nov 2022 22:48:39 +0900 Subject: [PATCH 0781/4345] perf probe: Use dwarf_attr_integrate as generic DWARF attr accessor [ Upstream commit f828929ab7f0dc3353e4a617f94f297fa8f3dec3 ] Use dwarf_attr_integrate() instead of dwarf_attr() for generic attribute acccessor functions, so that it can find the specified attribute from abstact origin DIE etc. Signed-off-by: Masami Hiramatsu Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Link: https://lore.kernel.org/r/166731051988.2100653.13595339994343449770.stgit@devnote3 Signed-off-by: Arnaldo Carvalho de Melo Stable-dep-of: a9dfc46c67b5 ("perf probe: Fix to get the DW_AT_decl_file and DW_AT_call_file as unsinged data") Signed-off-by: Sasha Levin --- tools/perf/util/dwarf-aux.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 4343356f3cf9..dc02685a1eec 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -308,7 +308,7 @@ static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name, { Dwarf_Attribute attr; - if (dwarf_attr(tp_die, attr_name, &attr) == NULL || + if (dwarf_attr_integrate(tp_die, attr_name, &attr) == NULL || dwarf_formudata(&attr, result) != 0) return -ENOENT; @@ -321,7 +321,7 @@ static int die_get_attr_sdata(Dwarf_Die *tp_die, unsigned int attr_name, { Dwarf_Attribute attr; - if (dwarf_attr(tp_die, attr_name, &attr) == NULL || + if (dwarf_attr_integrate(tp_die, attr_name, &attr) == NULL || dwarf_formsdata(&attr, result) != 0) return -ENOENT; From a1766efc5bbffefd4ca37cc7fcf3bf08f8eed109 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sat, 5 Nov 2022 12:01:14 +0900 Subject: [PATCH 0782/4345] perf probe: Fix to get the DW_AT_decl_file and DW_AT_call_file as unsinged data [ Upstream commit a9dfc46c67b52ad43b8e335e28f4cf8002c67793 ] DWARF version 5 standard Sec 2.14 says that Any debugging information entry representing the declaration of an object, module, subprogram or type may have DW_AT_decl_file, DW_AT_decl_line and DW_AT_decl_column attributes, each of whose value is an unsigned integer constant. So it should be an unsigned integer data. Also, even though the standard doesn't clearly say the DW_AT_call_file is signed or unsigned, the elfutils (eu-readelf) interprets it as unsigned integer data and it is natural to handle it as unsigned integer data as same as DW_AT_decl_file. This changes the DW_AT_call_file as unsigned integer data too. Fixes: 3f4460a28fb2f73d ("perf probe: Filter out redundant inline-instances") Signed-off-by: Masami Hiramatsu Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: stable@vger.kernel.org Cc: Steven Rostedt (VMware) Link: https://lore.kernel.org/r/166761727445.480106.3738447577082071942.stgit@devnote3 Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/dwarf-aux.c | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index dc02685a1eec..f8a10d5148f6 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -315,19 +315,6 @@ static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name, return 0; } -/* Get attribute and translate it as a sdata */ -static int die_get_attr_sdata(Dwarf_Die *tp_die, unsigned int attr_name, - Dwarf_Sword *result) -{ - Dwarf_Attribute attr; - - if (dwarf_attr_integrate(tp_die, attr_name, &attr) == NULL || - dwarf_formsdata(&attr, result) != 0) - return -ENOENT; - - return 0; -} - /** * die_is_signed_type - Check whether a type DIE is signed or not * @tp_die: a DIE of a type @@ -467,9 +454,9 @@ int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs) /* Get the call file index number in CU DIE */ static int die_get_call_fileno(Dwarf_Die *in_die) { - Dwarf_Sword idx; + Dwarf_Word idx; - if (die_get_attr_sdata(in_die, DW_AT_call_file, &idx) == 0) + if (die_get_attr_udata(in_die, DW_AT_call_file, &idx) == 0) return (int)idx; else return -ENOENT; @@ -478,9 +465,9 @@ static int die_get_call_fileno(Dwarf_Die *in_die) /* Get the declared file index number in CU DIE */ static int die_get_decl_fileno(Dwarf_Die *pdie) { - Dwarf_Sword idx; + Dwarf_Word idx; - if (die_get_attr_sdata(pdie, DW_AT_decl_file, &idx) == 0) + if (die_get_attr_udata(pdie, DW_AT_decl_file, &idx) == 0) return (int)idx; else return -ENOENT; From 5d112deb2a02701536d2b4446b8f0d843fcf6c0e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 16 Nov 2020 18:10:11 +0100 Subject: [PATCH 0783/4345] x86/kprobes: Convert to insn_decode() [ Upstream commit 77e768ec1391dc0d6cd89822aa60b9a1c1bd8128 ] Simplify code, improve decoding error checking. Signed-off-by: Borislav Petkov Acked-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20210304174237.31945-12-bp@alien8.de Stable-dep-of: 63dc6325ff41 ("x86/kprobes: Fix optprobe optimization check with CONFIG_RETHUNK") Signed-off-by: Sasha Levin --- arch/x86/kernel/kprobes/core.c | 17 +++++++++++------ arch/x86/kernel/kprobes/opt.c | 9 +++++++-- 2 files changed, 18 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 97e1d2a9898f..5de757099186 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -293,6 +293,8 @@ static int can_probe(unsigned long paddr) /* Decode instructions */ addr = paddr - offset; while (addr < paddr) { + int ret; + /* * Check if the instruction has been modified by another * kprobe, in which case we replace the breakpoint by the @@ -304,8 +306,10 @@ static int can_probe(unsigned long paddr) __addr = recover_probed_instruction(buf, addr); if (!__addr) return 0; - kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE); - insn_get_length(&insn); + + ret = insn_decode(&insn, (void *)__addr, MAX_INSN_SIZE, INSN_MODE_KERN); + if (ret < 0) + return 0; #ifdef CONFIG_KGDB /* @@ -351,8 +355,8 @@ static int is_IF_modifier(kprobe_opcode_t *insn) int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) { kprobe_opcode_t buf[MAX_INSN_SIZE]; - unsigned long recovered_insn = - recover_probed_instruction(buf, (unsigned long)src); + unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src); + int ret; if (!recovered_insn || !insn) return 0; @@ -362,8 +366,9 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) MAX_INSN_SIZE)) return 0; - kernel_insn_init(insn, dest, MAX_INSN_SIZE); - insn_get_length(insn); + ret = insn_decode(insn, dest, MAX_INSN_SIZE, INSN_MODE_KERN); + if (ret < 0) + return 0; /* We can not probe force emulate prefixed instruction */ if (insn_has_emulate_prefix(insn)) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 08eb23074f92..4299fc865732 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -312,6 +312,8 @@ static int can_optimize(unsigned long paddr) addr = paddr - offset; while (addr < paddr - offset + size) { /* Decode until function end */ unsigned long recovered_insn; + int ret; + if (search_exception_tables(addr)) /* * Since some fixup code will jumps into this function, @@ -321,8 +323,11 @@ static int can_optimize(unsigned long paddr) recovered_insn = recover_probed_instruction(buf, addr); if (!recovered_insn) return 0; - kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); - insn_get_length(&insn); + + ret = insn_decode(&insn, (void *)recovered_insn, MAX_INSN_SIZE, INSN_MODE_KERN); + if (ret < 0) + return 0; + /* * In the case of detecting unknown breakpoint, this could be * a padding INT3 between functions. Let's check that all the From f899baf6cb0f15fe7ca8ac74054986e449444f17 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 19 Dec 2022 23:35:19 +0900 Subject: [PATCH 0784/4345] x86/kprobes: Fix optprobe optimization check with CONFIG_RETHUNK [ Upstream commit 63dc6325ff41ee9e570bde705ac34a39c5dbeb44 ] Since the CONFIG_RETHUNK and CONFIG_SLS will use INT3 for stopping speculative execution after function return, kprobe jump optimization always fails on the functions with such INT3 inside the function body. (It already checks the INT3 padding between functions, but not inside the function) To avoid this issue, as same as kprobes, check whether the INT3 comes from kgdb or not, and if so, stop decoding and make it fail. The other INT3 will come from CONFIG_RETHUNK/CONFIG_SLS and those can be treated as a one-byte instruction. Fixes: e463a09af2f0 ("x86: Add straight-line-speculation mitigation") Suggested-by: Peter Zijlstra Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/167146051929.1374301.7419382929328081706.stgit@devnote3 Signed-off-by: Sasha Levin --- arch/x86/kernel/kprobes/opt.c | 28 ++++++++-------------------- 1 file changed, 8 insertions(+), 20 deletions(-) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 4299fc865732..3d6201492006 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -272,19 +273,6 @@ static int insn_is_indirect_jump(struct insn *insn) return ret; } -static bool is_padding_int3(unsigned long addr, unsigned long eaddr) -{ - unsigned char ops; - - for (; addr < eaddr; addr++) { - if (get_kernel_nofault(ops, (void *)addr) < 0 || - ops != INT3_INSN_OPCODE) - return false; - } - - return true; -} - /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { @@ -327,15 +315,15 @@ static int can_optimize(unsigned long paddr) ret = insn_decode(&insn, (void *)recovered_insn, MAX_INSN_SIZE, INSN_MODE_KERN); if (ret < 0) return 0; - +#ifdef CONFIG_KGDB /* - * In the case of detecting unknown breakpoint, this could be - * a padding INT3 between functions. Let's check that all the - * rest of the bytes are also INT3. + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. */ - if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) - return is_padding_int3(addr, paddr - offset + size) ? 1 : 0; - + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) + return 0; +#endif /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); From 5451efb2ca30f3c42b9efb8327ce35b62870dbd3 Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Wed, 2 Nov 2022 12:01:02 +0100 Subject: [PATCH 0785/4345] staging: media: tegra-video: fix device_node use after free [ Upstream commit c4d344163c3a7f90712525f931a6c016bbb35e18 ] At probe time this code path is followed: * tegra_csi_init * tegra_csi_channels_alloc * for_each_child_of_node(node, channel) -- iterates over channels * automatically gets 'channel' * tegra_csi_channel_alloc() * saves into chan->of_node a pointer to the channel OF node * automatically gets and puts 'channel' * now the node saved in chan->of_node has refcount 0, can disappear * tegra_csi_channels_init * iterates over channels * tegra_csi_channel_init -- uses chan->of_node After that, chan->of_node keeps storing the node until the device is removed. of_node_get() the node and of_node_put() it during teardown to avoid any risk. Fixes: 1ebaeb09830f ("media: tegra-video: Add support for external sensor capture") Cc: stable@vger.kernel.org Cc: Sowjanya Komatineni Signed-off-by: Luca Ceresoli Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/staging/media/tegra-video/csi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/staging/media/tegra-video/csi.c b/drivers/staging/media/tegra-video/csi.c index edfdf6db457d..dc5d432a09e8 100644 --- a/drivers/staging/media/tegra-video/csi.c +++ b/drivers/staging/media/tegra-video/csi.c @@ -420,7 +420,7 @@ static int tegra_csi_channel_alloc(struct tegra_csi *csi, chan->csi = csi; chan->csi_port_num = port_num; chan->numlanes = lanes; - chan->of_node = node; + chan->of_node = of_node_get(node); chan->numpads = num_pads; if (num_pads & 0x2) { chan->pads[0].flags = MEDIA_PAD_FL_SINK; @@ -621,6 +621,7 @@ static void tegra_csi_channels_cleanup(struct tegra_csi *csi) media_entity_cleanup(&subdev->entity); } + of_node_put(chan->of_node); list_del(&chan->list); kfree(chan); } From b5c75efd0a6cc181ae19244685e86f480955ffce Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 14 Dec 2022 10:51:18 +0000 Subject: [PATCH 0786/4345] ravb: Fix "failed to switch device to config mode" message during unbind [ Upstream commit c72a7e42592b2e18d862cf120876070947000d7a ] This patch fixes the error "ravb 11c20000.ethernet eth0: failed to switch device to config mode" during unbind. We are doing register access after pm_runtime_put_sync(). We usually do cleanup in reverse order of init. Currently in remove(), the "pm_runtime_put_sync" is not in reverse order. Probe reset_control_deassert(rstc); pm_runtime_enable(&pdev->dev); pm_runtime_get_sync(&pdev->dev); remove pm_runtime_put_sync(&pdev->dev); unregister_netdev(ndev); .. ravb_mdio_release(priv); pm_runtime_disable(&pdev->dev); Consider the call to unregister_netdev() unregister_netdev->unregister_netdevice_queue->rollback_registered_many that calls the below functions which access the registers after pm_runtime_put_sync() 1) ravb_get_stats 2) ravb_close Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper") Cc: stable@vger.kernel.org Signed-off-by: Biju Das Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20221214105118.2495313-1-biju.das.jz@bp.renesas.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/renesas/ravb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 9e7b85e178fd..9ec6d63691aa 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2253,11 +2253,11 @@ static int ravb_remove(struct platform_device *pdev) priv->desc_bat_dma); /* Set reset mode */ ravb_write(ndev, CCC_OPC_RESET, CCC); - pm_runtime_put_sync(&pdev->dev); unregister_netdev(ndev); netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); ravb_mdio_release(priv); + pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); free_netdev(ndev); platform_set_drvdata(pdev, NULL); From ecb8e8b2e55f05af705ccdb544f7a23ee3c3ce1b Mon Sep 17 00:00:00 2001 From: Chen Huang Date: Mon, 11 Jan 2021 20:40:14 +0800 Subject: [PATCH 0787/4345] riscv/stacktrace: Fix stack output without ra on the stack top [ Upstream commit f766f77a74f5784d8d4d3c36b1900731f97d08d0 ] When a function doesn't have a callee, then it will not push ra into the stack, such as lkdtm_BUG() function, addi sp,sp,-16 sd s0,8(sp) addi s0,sp,16 ebreak The struct stackframe use {fp,ra} to get information from stack, if walk_stackframe() with pr_regs, we will obtain wrong value and bad stacktrace, [] lkdtm_BUG+0x6/0x8 ---[ end trace 18da3fbdf08e25d5 ]--- Correct the next fp and pc, after that, full stacktrace shown as expects, [] lkdtm_BUG+0x6/0x8 [] lkdtm_do_action+0x14/0x1c [] direct_entry+0xc0/0x10a [] full_proxy_write+0x42/0x6a [] vfs_write+0x7e/0x214 [] ksys_write+0x98/0xc0 [] sys_write+0xe/0x16 [] ret_from_syscall+0x0/0x2 ---[ end trace 61917f3d9a9fadcd ]--- Signed-off-by: Chen Huang Signed-off-by: Kefeng Wang Signed-off-by: Palmer Dabbelt Stable-dep-of: 5c3022e4a616 ("riscv: stacktrace: Fixup ftrace_graph_ret_addr retp argument") Signed-off-by: Sasha Levin --- arch/riscv/kernel/stacktrace.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 595342910c3f..6cbde6b43fd2 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -57,9 +57,15 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, /* Unwind stack frame */ frame = (struct stackframe *)fp - 1; sp = fp; - fp = frame->fp; - pc = ftrace_graph_ret_addr(current, NULL, frame->ra, - (unsigned long *)(fp - 8)); + if (regs && (regs->epc == pc) && (frame->fp & 0x7)) { + fp = frame->ra; + pc = regs->ra; + } else { + fp = frame->fp; + pc = ftrace_graph_ret_addr(current, NULL, frame->ra, + (unsigned long *)(fp - 8)); + } + } } From 56d87959c654964699d8e5de3cd9a6c933af1897 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Wed, 9 Nov 2022 01:49:36 -0500 Subject: [PATCH 0788/4345] riscv: stacktrace: Fixup ftrace_graph_ret_addr retp argument [ Upstream commit 5c3022e4a616d800cf5f4c3a981d7992179e44a1 ] The 'retp' is a pointer to the return address on the stack, so we must pass the current return address pointer as the 'retp' argument to ftrace_push_return_trace(). Not parent function's return address on the stack. Fixes: b785ec129bd9 ("riscv/ftrace: Add HAVE_FUNCTION_GRAPH_RET_ADDR_PTR support") Signed-off-by: Guo Ren Signed-off-by: Guo Ren Link: https://lore.kernel.org/r/20221109064937.3643993-2-guoren@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/kernel/stacktrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 6cbde6b43fd2..1e53fbe5eb78 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -63,7 +63,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, } else { fp = frame->fp; pc = ftrace_graph_ret_addr(current, NULL, frame->ra, - (unsigned long *)(fp - 8)); + &frame->ra); } } From 99017eb3deee4e907350a50a10351770cc926375 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Fri, 16 Sep 2022 22:15:12 +0800 Subject: [PATCH 0789/4345] ext4: goto right label 'failed_mount3a' [ Upstream commit 43bd6f1b49b61f43de4d4e33661b8dbe8c911f14 ] Before these two branches neither loaded the journal nor created the xattr cache. So the right label to goto is 'failed_mount3a'. Although this did not cause any issues because the error handler validated if the pointer is null. However this still made me confused when reading the code. So it's still worth to modify to goto the right label. Signed-off-by: Jason Yan Reviewed-by: Jan Kara Reviewed-by: Ritesh Harjani (IBM) Link: https://lore.kernel.org/r/20220916141527.1012715-2-yanaijie@huawei.com Signed-off-by: Theodore Ts'o Stable-dep-of: 89481b5fa8c0 ("ext4: correct inconsistent error msg in nojournal mode") Signed-off-by: Sasha Levin --- fs/ext4/super.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index aa7bcc856de9..eb82c1d4883c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4809,30 +4809,30 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); - goto failed_mount_wq; + goto failed_mount3a; } else { /* Nojournal mode, all journal mount options are illegal */ if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_checksum, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; } if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; } if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { ext4_msg(sb, KERN_ERR, "can't mount with " "commit=%lu, fs mounted w/o journal", sbi->s_commit_interval / HZ); - goto failed_mount_wq; + goto failed_mount3a; } if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { ext4_msg(sb, KERN_ERR, "can't mount with " "data=, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); From f86d3338c87c6dad55030974be3b623f4771cfcf Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 9 Nov 2022 15:43:43 +0800 Subject: [PATCH 0790/4345] ext4: correct inconsistent error msg in nojournal mode [ Upstream commit 89481b5fa8c0640e62ba84c6020cee895f7ac643 ] When we used the journal_async_commit mounting option in nojournal mode, the kernel told me that "can't mount with journal_checksum", was very confusing. I find that when we mount with journal_async_commit, both the JOURNAL_ASYNC_COMMIT and EXPLICIT_JOURNAL_CHECKSUM flags are set. However, in the error branch, CHECKSUM is checked before ASYNC_COMMIT. As a result, the above inconsistency occurs, and the ASYNC_COMMIT branch becomes dead code that cannot be executed. Therefore, we exchange the positions of the two judgments to make the error msg more accurate. Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221109074343.4184862-1-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Sasha Levin --- fs/ext4/super.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eb82c1d4883c..43f06a71d612 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4812,16 +4812,17 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount3a; } else { /* Nojournal mode, all journal mount options are illegal */ - if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "journal_checksum, fs mounted w/o journal"); - goto failed_mount3a; - } if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit, fs mounted w/o journal"); goto failed_mount3a; } + + if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "journal_checksum, fs mounted w/o journal"); + goto failed_mount3a; + } if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { ext4_msg(sb, KERN_ERR, "can't mount with " "commit=%lu, fs mounted w/o journal", From 60d4383c1bda704c4b97f231f24bbff2e4875af1 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 9 Feb 2021 22:22:14 -0800 Subject: [PATCH 0791/4345] mm/highmem: Lift memcpy_[to|from]_page to core [ Upstream commit bb90d4bc7b6a536b2e4db45f4763e467c2008251 ] Working through a conversion to a call kmap_local_page() instead of kmap() revealed many places where the pattern kmap/memcpy/kunmap occurred. Eric Biggers, Matthew Wilcox, Christoph Hellwig, Dan Williams, and Al Viro all suggested putting this code into helper functions. Al Viro further pointed out that these functions already existed in the iov_iter code.[1] Various locations for the lifted functions were considered. Headers like mm.h or string.h seem ok but don't really portray the functionality well. pagemap.h made some sense but is for page cache functionality.[2] Another alternative would be to create a new header for the promoted memcpy functions, but it masks the fact that these are designed to copy to/from pages using the kernel direct mappings and complicates matters with a new header. Placing these functions in 'highmem.h' is suboptimal especially with the changes being proposed in the functionality of kmap. From a caller perspective including/using 'highmem.h' implies that the functions defined in that header are only required when highmem is in use which is increasingly not the case with modern processors. However, highmem.h is where all the current functions like this reside (zero_user(), clear_highpage(), clear_user_highpage(), copy_user_highpage(), and copy_highpage()). So it makes the most sense even though it is distasteful for some.[3] Lift memcpy_to_page() and memcpy_from_page() to pagemap.h. [1] https://lore.kernel.org/lkml/20201013200149.GI3576660@ZenIV.linux.org.uk/ https://lore.kernel.org/lkml/20201013112544.GA5249@infradead.org/ [2] https://lore.kernel.org/lkml/20201208122316.GH7338@casper.infradead.org/ [3] https://lore.kernel.org/lkml/20201013200149.GI3576660@ZenIV.linux.org.uk/#t https://lore.kernel.org/lkml/20201208163814.GN1563847@iweiny-DESK2.sc.intel.com/ Cc: Boris Pismenny Cc: Or Gerlitz Cc: Dave Hansen Suggested-by: Matthew Wilcox Suggested-by: Christoph Hellwig Suggested-by: Dan Williams Suggested-by: Al Viro Suggested-by: Eric Biggers Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: David Sterba Stable-dep-of: 956510c0c743 ("fs: ext4: initialize fsdata in pagecache_write()") Signed-off-by: Sasha Levin --- include/linux/highmem.h | 18 ++++++++++++++++++ lib/iov_iter.c | 14 -------------- 2 files changed, 18 insertions(+), 14 deletions(-) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 14e6202ce47f..b25df1f8d48d 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -345,4 +345,22 @@ static inline void copy_highpage(struct page *to, struct page *from) #endif +static inline void memcpy_from_page(char *to, struct page *page, + size_t offset, size_t len) +{ + char *from = kmap_atomic(page); + + memcpy(to, from + offset, len); + kunmap_atomic(from); +} + +static inline void memcpy_to_page(struct page *page, size_t offset, + const char *from, size_t len) +{ + char *to = kmap_atomic(page); + + memcpy(to + offset, from, len); + kunmap_atomic(to); +} + #endif /* _LINUX_HIGHMEM_H */ diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 650554964f18..6e30113303ba 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -467,20 +467,6 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction, } EXPORT_SYMBOL(iov_iter_init); -static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) -{ - char *from = kmap_atomic(page); - memcpy(to, from + offset, len); - kunmap_atomic(from); -} - -static void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) -{ - char *to = kmap_atomic(page); - memcpy(to + offset, from, len); - kunmap_atomic(to); -} - static void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_atomic(page); From b33e42d65efe06bb6d6281238d66f4c9573910f2 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 7 Feb 2021 11:04:23 -0800 Subject: [PATCH 0792/4345] ext4: use memcpy_to_page() in pagecache_write() [ Upstream commit bd256fda92efe97b692dc72e246d35fa724d42d8 ] Signed-off-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20210207190425.38107-7-chaitanya.kulkarni@wdc.com Signed-off-by: Theodore Ts'o Stable-dep-of: 956510c0c743 ("fs: ext4: initialize fsdata in pagecache_write()") Signed-off-by: Sasha Levin --- fs/ext4/verity.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 35be8e7ec2a0..130070ec491b 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -80,7 +80,6 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, PAGE_SIZE - offset_in_page(pos)); struct page *page; void *fsdata; - void *addr; int res; res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0, @@ -88,9 +87,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, if (res) return res; - addr = kmap_atomic(page); - memcpy(addr + offset_in_page(pos), buf, n); - kunmap_atomic(addr); + memcpy_to_page(page, offset_in_page(pos), buf, n); res = pagecache_write_end(NULL, inode->i_mapping, pos, n, n, page, fsdata); From 769469f8f188573431927be905aff50712b34c5a Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Mon, 21 Nov 2022 12:21:30 +0100 Subject: [PATCH 0793/4345] fs: ext4: initialize fsdata in pagecache_write() [ Upstream commit 956510c0c7439e90b8103aaeaf4da92878c622f0 ] When aops->write_begin() does not initialize fsdata, KMSAN reports an error passing the latter to aops->write_end(). Fix this by unconditionally initializing fsdata. Cc: Eric Biggers Fixes: c93d8f885809 ("ext4: add basic fs-verity support") Reported-by: syzbot+9767be679ef5016b6082@syzkaller.appspotmail.com Signed-off-by: Alexander Potapenko Reviewed-by: Eric Biggers Link: https://lore.kernel.org/r/20221121112134.407362-1-glider@google.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Sasha Levin --- fs/ext4/verity.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 130070ec491b..e3019f920222 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -79,7 +79,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); struct page *page; - void *fsdata; + void *fsdata = NULL; int res; res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0, From 95eaa8a95358d9b4a84b53ea59281936fbecaa11 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 27 Nov 2020 12:33:58 +0100 Subject: [PATCH 0794/4345] ext4: move functions in super.c [ Upstream commit 4067662388f97d0f360e568820d9d5bac6a3c9fa ] Just move error info related functions in super.c close to ext4_handle_error(). We'll want to combine save_error_info() with ext4_handle_error() and this makes change more obvious and saves a forward declaration as well. No functional change. Signed-off-by: Jan Kara Reviewed-by: Andreas Dilger Link: https://lore.kernel.org/r/20201127113405.26867-6-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/super.c | 196 ++++++++++++++++++++++++------------------------ 1 file changed, 98 insertions(+), 98 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 43f06a71d612..982341939a27 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -417,104 +417,6 @@ static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) #define ext4_get_tstamp(es, tstamp) \ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) -static void __save_error_info(struct super_block *sb, int error, - __u32 ino, __u64 block, - const char *func, unsigned int line) -{ - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - int err; - - EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; - if (bdev_read_only(sb->s_bdev)) - return; - es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_update_tstamp(es, s_last_error_time); - strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func)); - es->s_last_error_line = cpu_to_le32(line); - es->s_last_error_ino = cpu_to_le32(ino); - es->s_last_error_block = cpu_to_le64(block); - switch (error) { - case EIO: - err = EXT4_ERR_EIO; - break; - case ENOMEM: - err = EXT4_ERR_ENOMEM; - break; - case EFSBADCRC: - err = EXT4_ERR_EFSBADCRC; - break; - case 0: - case EFSCORRUPTED: - err = EXT4_ERR_EFSCORRUPTED; - break; - case ENOSPC: - err = EXT4_ERR_ENOSPC; - break; - case ENOKEY: - err = EXT4_ERR_ENOKEY; - break; - case EROFS: - err = EXT4_ERR_EROFS; - break; - case EFBIG: - err = EXT4_ERR_EFBIG; - break; - case EEXIST: - err = EXT4_ERR_EEXIST; - break; - case ERANGE: - err = EXT4_ERR_ERANGE; - break; - case EOVERFLOW: - err = EXT4_ERR_EOVERFLOW; - break; - case EBUSY: - err = EXT4_ERR_EBUSY; - break; - case ENOTDIR: - err = EXT4_ERR_ENOTDIR; - break; - case ENOTEMPTY: - err = EXT4_ERR_ENOTEMPTY; - break; - case ESHUTDOWN: - err = EXT4_ERR_ESHUTDOWN; - break; - case EFAULT: - err = EXT4_ERR_EFAULT; - break; - default: - err = EXT4_ERR_UNKNOWN; - } - es->s_last_error_errcode = err; - if (!es->s_first_error_time) { - es->s_first_error_time = es->s_last_error_time; - es->s_first_error_time_hi = es->s_last_error_time_hi; - strncpy(es->s_first_error_func, func, - sizeof(es->s_first_error_func)); - es->s_first_error_line = cpu_to_le32(line); - es->s_first_error_ino = es->s_last_error_ino; - es->s_first_error_block = es->s_last_error_block; - es->s_first_error_errcode = es->s_last_error_errcode; - } - /* - * Start the daily error reporting function if it hasn't been - * started already - */ - if (!es->s_error_count) - mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ); - le32_add_cpu(&es->s_error_count, 1); -} - -static void save_error_info(struct super_block *sb, int error, - __u32 ino, __u64 block, - const char *func, unsigned int line) -{ - __save_error_info(sb, error, ino, block, func, line); - if (!bdev_read_only(sb->s_bdev)) - ext4_commit_super(sb, 1); -} - /* * The del_gendisk() function uninitializes the disk-specific data * structures, including the bdi structure, without telling anyone @@ -643,6 +545,104 @@ static bool system_going_down(void) || system_state == SYSTEM_RESTART; } +static void __save_error_info(struct super_block *sb, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) +{ + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + int err; + + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + if (bdev_read_only(sb->s_bdev)) + return; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + ext4_update_tstamp(es, s_last_error_time); + strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func)); + es->s_last_error_line = cpu_to_le32(line); + es->s_last_error_ino = cpu_to_le32(ino); + es->s_last_error_block = cpu_to_le64(block); + switch (error) { + case EIO: + err = EXT4_ERR_EIO; + break; + case ENOMEM: + err = EXT4_ERR_ENOMEM; + break; + case EFSBADCRC: + err = EXT4_ERR_EFSBADCRC; + break; + case 0: + case EFSCORRUPTED: + err = EXT4_ERR_EFSCORRUPTED; + break; + case ENOSPC: + err = EXT4_ERR_ENOSPC; + break; + case ENOKEY: + err = EXT4_ERR_ENOKEY; + break; + case EROFS: + err = EXT4_ERR_EROFS; + break; + case EFBIG: + err = EXT4_ERR_EFBIG; + break; + case EEXIST: + err = EXT4_ERR_EEXIST; + break; + case ERANGE: + err = EXT4_ERR_ERANGE; + break; + case EOVERFLOW: + err = EXT4_ERR_EOVERFLOW; + break; + case EBUSY: + err = EXT4_ERR_EBUSY; + break; + case ENOTDIR: + err = EXT4_ERR_ENOTDIR; + break; + case ENOTEMPTY: + err = EXT4_ERR_ENOTEMPTY; + break; + case ESHUTDOWN: + err = EXT4_ERR_ESHUTDOWN; + break; + case EFAULT: + err = EXT4_ERR_EFAULT; + break; + default: + err = EXT4_ERR_UNKNOWN; + } + es->s_last_error_errcode = err; + if (!es->s_first_error_time) { + es->s_first_error_time = es->s_last_error_time; + es->s_first_error_time_hi = es->s_last_error_time_hi; + strncpy(es->s_first_error_func, func, + sizeof(es->s_first_error_func)); + es->s_first_error_line = cpu_to_le32(line); + es->s_first_error_ino = es->s_last_error_ino; + es->s_first_error_block = es->s_last_error_block; + es->s_first_error_errcode = es->s_last_error_errcode; + } + /* + * Start the daily error reporting function if it hasn't been + * started already + */ + if (!es->s_error_count) + mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ); + le32_add_cpu(&es->s_error_count, 1); +} + +static void save_error_info(struct super_block *sb, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) +{ + __save_error_info(sb, error, ino, block, func, line); + if (!bdev_read_only(sb->s_bdev)) + ext4_commit_super(sb, 1); +} + /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * From adfefe804b1f2fdcfa241a1f6018f54ac9d7929e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 27 Nov 2020 12:33:59 +0100 Subject: [PATCH 0795/4345] ext4: simplify ext4 error translation [ Upstream commit 02a7780e4d2fcf438ac6773bc469e7ada2af56be ] We convert errno's to ext4 on-disk format error codes in save_error_info(). Add a function and a bit of macro magic to make this simpler. Signed-off-by: Jan Kara Reviewed-by: Andreas Dilger Link: https://lore.kernel.org/r/20201127113405.26867-7-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/super.c | 95 +++++++++++++++++++++---------------------------- 1 file changed, 40 insertions(+), 55 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 982341939a27..ced84ed4e592 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -545,76 +545,61 @@ static bool system_going_down(void) || system_state == SYSTEM_RESTART; } +struct ext4_err_translation { + int code; + int errno; +}; + +#define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err } + +static struct ext4_err_translation err_translation[] = { + EXT4_ERR_TRANSLATE(EIO), + EXT4_ERR_TRANSLATE(ENOMEM), + EXT4_ERR_TRANSLATE(EFSBADCRC), + EXT4_ERR_TRANSLATE(EFSCORRUPTED), + EXT4_ERR_TRANSLATE(ENOSPC), + EXT4_ERR_TRANSLATE(ENOKEY), + EXT4_ERR_TRANSLATE(EROFS), + EXT4_ERR_TRANSLATE(EFBIG), + EXT4_ERR_TRANSLATE(EEXIST), + EXT4_ERR_TRANSLATE(ERANGE), + EXT4_ERR_TRANSLATE(EOVERFLOW), + EXT4_ERR_TRANSLATE(EBUSY), + EXT4_ERR_TRANSLATE(ENOTDIR), + EXT4_ERR_TRANSLATE(ENOTEMPTY), + EXT4_ERR_TRANSLATE(ESHUTDOWN), + EXT4_ERR_TRANSLATE(EFAULT), +}; + +static int ext4_errno_to_code(int errno) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(err_translation); i++) + if (err_translation[i].errno == errno) + return err_translation[i].code; + return EXT4_ERR_UNKNOWN; +} + static void __save_error_info(struct super_block *sb, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; - int err; EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (bdev_read_only(sb->s_bdev)) return; + /* We default to EFSCORRUPTED error... */ + if (error == 0) + error = EFSCORRUPTED; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); ext4_update_tstamp(es, s_last_error_time); strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func)); es->s_last_error_line = cpu_to_le32(line); es->s_last_error_ino = cpu_to_le32(ino); es->s_last_error_block = cpu_to_le64(block); - switch (error) { - case EIO: - err = EXT4_ERR_EIO; - break; - case ENOMEM: - err = EXT4_ERR_ENOMEM; - break; - case EFSBADCRC: - err = EXT4_ERR_EFSBADCRC; - break; - case 0: - case EFSCORRUPTED: - err = EXT4_ERR_EFSCORRUPTED; - break; - case ENOSPC: - err = EXT4_ERR_ENOSPC; - break; - case ENOKEY: - err = EXT4_ERR_ENOKEY; - break; - case EROFS: - err = EXT4_ERR_EROFS; - break; - case EFBIG: - err = EXT4_ERR_EFBIG; - break; - case EEXIST: - err = EXT4_ERR_EEXIST; - break; - case ERANGE: - err = EXT4_ERR_ERANGE; - break; - case EOVERFLOW: - err = EXT4_ERR_EOVERFLOW; - break; - case EBUSY: - err = EXT4_ERR_EBUSY; - break; - case ENOTDIR: - err = EXT4_ERR_ENOTDIR; - break; - case ENOTEMPTY: - err = EXT4_ERR_ENOTEMPTY; - break; - case ESHUTDOWN: - err = EXT4_ERR_ESHUTDOWN; - break; - case EFAULT: - err = EXT4_ERR_EFAULT; - break; - default: - err = EXT4_ERR_UNKNOWN; - } - es->s_last_error_errcode = err; + es->s_last_error_errcode = ext4_errno_to_code(error); if (!es->s_first_error_time) { es->s_first_error_time = es->s_last_error_time; es->s_first_error_time_hi = es->s_last_error_time_hi; From a5584ba9b3b6e522d00d9d59d53e20bdf80d6745 Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Sat, 27 Mar 2021 16:00:05 +0530 Subject: [PATCH 0796/4345] ext4: fix various seppling typos [ Upstream commit 3088e5a5153cda27ec26461e5edf2821e15e802c ] Signed-off-by: Bhaskar Chowdhury Link: https://lore.kernel.org/r/cover.1616840203.git.unixbhaskar@gmail.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/fast_commit.c | 2 +- fs/ext4/indirect.c | 2 +- fs/ext4/inline.c | 2 +- fs/ext4/inode.c | 2 +- fs/ext4/mballoc.h | 2 +- fs/ext4/migrate.c | 6 +++--- fs/ext4/namei.c | 2 +- fs/ext4/xattr.c | 2 +- 8 files changed, 10 insertions(+), 10 deletions(-) diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 41dcf21558c4..3b2d6106a703 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -66,7 +66,7 @@ * Fast Commit Ineligibility * ------------------------- * Not all operations are supported by fast commits today (e.g extended - * attributes). Fast commit ineligiblity is marked by calling one of the + * attributes). Fast commit ineligibility is marked by calling one of the * two following functions: * * - ext4_fc_mark_ineligible(): This makes next fast commit operation to fall diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index b7d130f4b5e4..237983cd8cdc 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -712,7 +712,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, /* * Truncate transactions can be complex and absolutely huge. So we need to - * be able to restart the transaction at a conventient checkpoint to make + * be able to restart the transaction at a convenient checkpoint to make * sure we don't overflow the journal. * * Try to extend this transaction for the purposes of truncation. If diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 88bd1d1cca23..77377befbb1c 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -799,7 +799,7 @@ ext4_journalled_write_inline_data(struct inode *inode, * clear the inode state safely. * 2. The inode has inline data, then we need to read the data, make it * update and dirty so that ext4_da_writepages can handle it. We don't - * need to start the journal since the file's metatdata isn't changed now. + * need to start the journal since the file's metadata isn't changed now. */ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d7dbe1eb9da0..2d3004b3fc56 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3885,7 +3885,7 @@ unlock: * starting from file offset 'from'. The range to be zero'd must * be contained with in one block. If the specified range exceeds * the end of the block it will be shortened to end of the block - * that cooresponds to 'from' + * that corresponds to 'from' */ static int ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index e75b4749aa1c..7be6288e48ec 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -59,7 +59,7 @@ * by the stream allocator, which purpose is to pack requests * as close each to other as possible to produce smooth I/O traffic * We use locality group prealloc space for stream request. - * We can tune the same via /proc/fs/ext4//stream_req + * We can tune the same via /proc/fs/ext4//stream_req */ #define MB_DEFAULT_STREAM_THRESHOLD 16 /* 64K */ diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 4bfe2252d9a4..b0ea646454ac 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -32,7 +32,7 @@ static int finish_range(handle_t *handle, struct inode *inode, newext.ee_block = cpu_to_le32(lb->first_block); newext.ee_len = cpu_to_le16(lb->last_block - lb->first_block + 1); ext4_ext_store_pblock(&newext, lb->first_pblock); - /* Locking only for convinience since we are operating on temp inode */ + /* Locking only for convenience since we are operating on temp inode */ down_write(&EXT4_I(inode)->i_data_sem); path = ext4_find_extent(inode, lb->first_block, NULL, 0); if (IS_ERR(path)) { @@ -43,8 +43,8 @@ static int finish_range(handle_t *handle, struct inode *inode, /* * Calculate the credit needed to inserting this extent - * Since we are doing this in loop we may accumalate extra - * credit. But below we try to not accumalate too much + * Since we are doing this in loop we may accumulate extra + * credit. But below we try to not accumulate too much * of them by restarting the journal. */ needed = ext4_ext_calc_credits_for_single_extent(inode, diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index c17d5f399f9e..ce4962bb62bc 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -995,7 +995,7 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash, * If the hash is 1, then continue only if the next page has a * continuation hash of any value. This is used for readdir * handling. Otherwise, check to see if the hash matches the - * desired contiuation hash. If it doesn't, return since + * desired continuation hash. If it doesn't, return since * there's no point to read in the successive index pages. */ bhash = dx_get_hash(p->at); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 795ef72f0d3c..74d045b426dd 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1617,7 +1617,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, * If storing the value in an external inode is an option, * reserve space for xattr entries/names in the external * attribute block so that a long value does not occupy the - * whole space and prevent futher entries being added. + * whole space and prevent further entries being added. */ if (ext4_has_feature_ea_inode(inode->i_sb) && new_size && is_block && From b8b7922374b00a44137e5bcdd46ef86c8b065f27 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 6 Nov 2022 14:48:37 -0800 Subject: [PATCH 0797/4345] ext4: fix leaking uninitialized memory in fast-commit journal [ Upstream commit 594bc43b410316d70bb42aeff168837888d96810 ] When space at the end of fast-commit journal blocks is unused, make sure to zero it out so that uninitialized memory is not leaked to disk. Fixes: aa75f4d3daae ("ext4: main fast-commit commit path") Cc: # v5.10+ Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20221106224841.279231-4-ebiggers@kernel.org Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/fast_commit.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 3b2d6106a703..eaa26477bceb 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -628,6 +628,9 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc) *crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl)); if (pad_len > 0) ext4_fc_memzero(sb, tl + 1, pad_len, crc); + /* Don't leak uninitialized memory in the unused last byte. */ + *((u8 *)(tl + 1) + pad_len) = 0; + ext4_fc_submit_bh(sb); ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh); @@ -684,6 +687,8 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc) dst += sizeof(tail.fc_tid); tail.fc_crc = cpu_to_le32(crc); ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL); + dst += sizeof(tail.fc_crc); + memset(dst, 0, bsize - off); /* Don't leak uninitialized memory. */ ext4_fc_submit_bh(sb); From 4c363e2961cd80389c5581e5679332aafb9cbfc0 Mon Sep 17 00:00:00 2001 From: Shuqi Zhang Date: Wed, 25 May 2022 11:01:20 +0800 Subject: [PATCH 0798/4345] ext4: use kmemdup() to replace kmalloc + memcpy [ Upstream commit 4efd9f0d120c55b08852ee5605dbb02a77089a5d ] Replace kmalloc + memcpy with kmemdup() Signed-off-by: Shuqi Zhang Reviewed-by: Ritesh Harjani Link: https://lore.kernel.org/r/20220525030120.803330-1-zhangshuqi3@huawei.com Signed-off-by: Theodore Ts'o Stable-dep-of: a44e84a9b776 ("ext4: fix deadlock due to mbcache entry corruption") Signed-off-by: Sasha Levin --- fs/ext4/xattr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 74d045b426dd..0b682c92bfe9 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1890,11 +1890,10 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, unlock_buffer(bs->bh); ea_bdebug(bs->bh, "cloning"); - s->base = kmalloc(bs->bh->b_size, GFP_NOFS); + s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); error = -ENOMEM; if (s->base == NULL) goto cleanup; - memcpy(s->base, BHDR(bs->bh), bs->bh->b_size); s->first = ENTRY(header(s->base)+1); header(s->base)->h_refcount = cpu_to_le32(1); s->here = ENTRY(s->base + offset); From fb59d12ae7f9f7584e6702d4c2e26ce10210af3d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 12 Jul 2022 12:54:20 +0200 Subject: [PATCH 0799/4345] mbcache: don't reclaim used entries [ Upstream commit 58318914186c157477b978b1739dfe2f1b9dc0fe ] Do not reclaim entries that are currently used by somebody from a shrinker. Firstly, these entries are likely useful. Secondly, we will need to keep such entries to protect pending increment of xattr block refcount. CC: stable@vger.kernel.org Fixes: 82939d7999df ("ext4: convert to mbcache2") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20220712105436.32204-1-jack@suse.cz Signed-off-by: Theodore Ts'o Stable-dep-of: a44e84a9b776 ("ext4: fix deadlock due to mbcache entry corruption") Signed-off-by: Sasha Levin --- fs/mbcache.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/mbcache.c b/fs/mbcache.c index 97c54d3a2227..cfc28129fb6f 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -288,7 +288,7 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache, while (nr_to_scan-- && !list_empty(&cache->c_list)) { entry = list_first_entry(&cache->c_list, struct mb_cache_entry, e_list); - if (entry->e_referenced) { + if (entry->e_referenced || atomic_read(&entry->e_refcnt) > 2) { entry->e_referenced = 0; list_move_tail(&entry->e_list, &cache->c_list); continue; @@ -302,6 +302,14 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache, spin_unlock(&cache->c_list_lock); head = mb_cache_entry_head(cache, entry->e_key); hlist_bl_lock(head); + /* Now a reliable check if the entry didn't get used... */ + if (atomic_read(&entry->e_refcnt) > 2) { + hlist_bl_unlock(head); + spin_lock(&cache->c_list_lock); + list_add_tail(&entry->e_list, &cache->c_list); + cache->c_entry_count++; + continue; + } if (!hlist_bl_unhashed(&entry->e_hash_list)) { hlist_bl_del_init(&entry->e_hash_list); atomic_dec(&entry->e_refcnt); From 27c08673978ebf31d56a822b3fb3aa74c8e1e4f2 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 12 Jul 2022 12:54:21 +0200 Subject: [PATCH 0800/4345] mbcache: add functions to delete entry if unused [ Upstream commit 3dc96bba65f53daa217f0a8f43edad145286a8f5 ] Add function mb_cache_entry_delete_or_get() to delete mbcache entry if it is unused and also add a function to wait for entry to become unused - mb_cache_entry_wait_unused(). We do not share code between the two deleting function as one of them will go away soon. CC: stable@vger.kernel.org Fixes: 82939d7999df ("ext4: convert to mbcache2") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20220712105436.32204-2-jack@suse.cz Signed-off-by: Theodore Ts'o Stable-dep-of: a44e84a9b776 ("ext4: fix deadlock due to mbcache entry corruption") Signed-off-by: Sasha Levin --- fs/mbcache.c | 66 +++++++++++++++++++++++++++++++++++++++-- include/linux/mbcache.h | 10 ++++++- 2 files changed, 73 insertions(+), 3 deletions(-) diff --git a/fs/mbcache.c b/fs/mbcache.c index cfc28129fb6f..2010bc80a3f2 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -11,7 +11,7 @@ /* * Mbcache is a simple key-value store. Keys need not be unique, however * key-value pairs are expected to be unique (we use this fact in - * mb_cache_entry_delete()). + * mb_cache_entry_delete_or_get()). * * Ext2 and ext4 use this cache for deduplication of extended attribute blocks. * Ext4 also uses it for deduplication of xattr values stored in inodes. @@ -125,6 +125,19 @@ void __mb_cache_entry_free(struct mb_cache_entry *entry) } EXPORT_SYMBOL(__mb_cache_entry_free); +/* + * mb_cache_entry_wait_unused - wait to be the last user of the entry + * + * @entry - entry to work on + * + * Wait to be the last user of the entry. + */ +void mb_cache_entry_wait_unused(struct mb_cache_entry *entry) +{ + wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 3); +} +EXPORT_SYMBOL(mb_cache_entry_wait_unused); + static struct mb_cache_entry *__entry_find(struct mb_cache *cache, struct mb_cache_entry *entry, u32 key) @@ -217,7 +230,7 @@ out: } EXPORT_SYMBOL(mb_cache_entry_get); -/* mb_cache_entry_delete - remove a cache entry +/* mb_cache_entry_delete - try to remove a cache entry * @cache - cache we work with * @key - key * @value - value @@ -254,6 +267,55 @@ void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value) } EXPORT_SYMBOL(mb_cache_entry_delete); +/* mb_cache_entry_delete_or_get - remove a cache entry if it has no users + * @cache - cache we work with + * @key - key + * @value - value + * + * Remove entry from cache @cache with key @key and value @value. The removal + * happens only if the entry is unused. The function returns NULL in case the + * entry was successfully removed or there's no entry in cache. Otherwise the + * function grabs reference of the entry that we failed to delete because it + * still has users and return it. + */ +struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, + u32 key, u64 value) +{ + struct hlist_bl_node *node; + struct hlist_bl_head *head; + struct mb_cache_entry *entry; + + head = mb_cache_entry_head(cache, key); + hlist_bl_lock(head); + hlist_bl_for_each_entry(entry, node, head, e_hash_list) { + if (entry->e_key == key && entry->e_value == value) { + if (atomic_read(&entry->e_refcnt) > 2) { + atomic_inc(&entry->e_refcnt); + hlist_bl_unlock(head); + return entry; + } + /* We keep hash list reference to keep entry alive */ + hlist_bl_del_init(&entry->e_hash_list); + hlist_bl_unlock(head); + spin_lock(&cache->c_list_lock); + if (!list_empty(&entry->e_list)) { + list_del_init(&entry->e_list); + if (!WARN_ONCE(cache->c_entry_count == 0, + "mbcache: attempt to decrement c_entry_count past zero")) + cache->c_entry_count--; + atomic_dec(&entry->e_refcnt); + } + spin_unlock(&cache->c_list_lock); + mb_cache_entry_put(cache, entry); + return NULL; + } + } + hlist_bl_unlock(head); + + return NULL; +} +EXPORT_SYMBOL(mb_cache_entry_delete_or_get); + /* mb_cache_entry_touch - cache entry got used * @cache - cache the entry belongs to * @entry - entry that got used diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index 20f1e3ff6013..8eca7f25c432 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -30,15 +30,23 @@ void mb_cache_destroy(struct mb_cache *cache); int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, u64 value, bool reusable); void __mb_cache_entry_free(struct mb_cache_entry *entry); +void mb_cache_entry_wait_unused(struct mb_cache_entry *entry); static inline int mb_cache_entry_put(struct mb_cache *cache, struct mb_cache_entry *entry) { - if (!atomic_dec_and_test(&entry->e_refcnt)) + unsigned int cnt = atomic_dec_return(&entry->e_refcnt); + + if (cnt > 0) { + if (cnt <= 3) + wake_up_var(&entry->e_refcnt); return 0; + } __mb_cache_entry_free(entry); return 1; } +struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, + u32 key, u64 value); void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, u64 value); From 0e6fbc566fcc4c230bf80f76cf5df26b42142d8a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 12 Jul 2022 12:54:22 +0200 Subject: [PATCH 0801/4345] ext4: remove EA inode entry from mbcache on inode eviction [ Upstream commit 6bc0d63dad7f9f54d381925ee855b402f652fa39 ] Currently we remove EA inode from mbcache as soon as its xattr refcount drops to zero. However there can be pending attempts to reuse the inode and thus refcount handling code has to handle the situation when refcount increases from zero anyway. So save some work and just keep EA inode in mbcache until it is getting evicted. At that moment we are sure following iget() of EA inode will fail anyway (or wait for eviction to finish and load things from the disk again) and so removing mbcache entry at that moment is fine and simplifies the code a bit. CC: stable@vger.kernel.org Fixes: 82939d7999df ("ext4: convert to mbcache2") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20220712105436.32204-3-jack@suse.cz Signed-off-by: Theodore Ts'o Stable-dep-of: a44e84a9b776 ("ext4: fix deadlock due to mbcache entry corruption") Signed-off-by: Sasha Levin --- fs/ext4/inode.c | 2 ++ fs/ext4/xattr.c | 24 ++++++++---------------- fs/ext4/xattr.h | 1 + 3 files changed, 11 insertions(+), 16 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2d3004b3fc56..355343cf4609 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -179,6 +179,8 @@ void ext4_evict_inode(struct inode *inode) trace_ext4_evict_inode(inode); + if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL) + ext4_evict_ea_inode(inode); if (inode->i_nlink) { /* * When journalling data dirty buffers are tracked only in the diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 0b682c92bfe9..0555f32f0fd4 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -436,6 +436,14 @@ error: return err; } +/* Remove entry from mbcache when EA inode is getting evicted */ +void ext4_evict_ea_inode(struct inode *inode) +{ + if (EA_INODE_CACHE(inode)) + mb_cache_entry_delete(EA_INODE_CACHE(inode), + ext4_xattr_inode_get_hash(inode), inode->i_ino); +} + static int ext4_xattr_inode_verify_hashes(struct inode *ea_inode, struct ext4_xattr_entry *entry, void *buffer, @@ -972,10 +980,8 @@ int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { - struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode); struct ext4_iloc iloc; s64 ref_count; - u32 hash; int ret; inode_lock(ea_inode); @@ -998,14 +1004,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, set_nlink(ea_inode, 1); ext4_orphan_del(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_create(ea_inode_cache, - GFP_NOFS, hash, - ea_inode->i_ino, - true /* reusable */); - } } } else { WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld", @@ -1018,12 +1016,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, clear_nlink(ea_inode); ext4_orphan_add(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_delete(ea_inode_cache, hash, - ea_inode->i_ino); - } } } diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 87e5863bb493..b357872ab83b 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -191,6 +191,7 @@ extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array); extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); +extern void ext4_evict_ea_inode(struct inode *inode); extern const struct xattr_handler *ext4_xattr_handlers[]; From 4cc218e217bf0f7c1899615745ba6b433f09e416 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 12 Jul 2022 12:54:23 +0200 Subject: [PATCH 0802/4345] ext4: unindent codeblock in ext4_xattr_block_set() [ Upstream commit fd48e9acdf26d0cbd80051de07d4a735d05d29b2 ] Remove unnecessary else (and thus indentation level) from a code block in ext4_xattr_block_set(). It will also make following code changes easier. No functional changes. CC: stable@vger.kernel.org Fixes: 82939d7999df ("ext4: convert to mbcache2") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20220712105436.32204-4-jack@suse.cz Signed-off-by: Theodore Ts'o Stable-dep-of: a44e84a9b776 ("ext4: fix deadlock due to mbcache entry corruption") Signed-off-by: Sasha Levin --- fs/ext4/xattr.c | 77 ++++++++++++++++++++++++------------------------- 1 file changed, 38 insertions(+), 39 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 0555f32f0fd4..9d5ccc90eb63 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1846,6 +1846,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, #define header(x) ((struct ext4_xattr_header *)(x)) if (s->base) { + int offset = (char *)s->here - bs->bh->b_data; + BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bs->bh); if (error) @@ -1877,49 +1879,46 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (error) goto cleanup; goto inserted; - } else { - int offset = (char *)s->here - bs->bh->b_data; + } + unlock_buffer(bs->bh); + ea_bdebug(bs->bh, "cloning"); + s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); + error = -ENOMEM; + if (s->base == NULL) + goto cleanup; + s->first = ENTRY(header(s->base)+1); + header(s->base)->h_refcount = cpu_to_le32(1); + s->here = ENTRY(s->base + offset); + s->end = s->base + bs->bh->b_size; - unlock_buffer(bs->bh); - ea_bdebug(bs->bh, "cloning"); - s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); - error = -ENOMEM; - if (s->base == NULL) + /* + * If existing entry points to an xattr inode, we need + * to prevent ext4_xattr_set_entry() from decrementing + * ref count on it because the reference belongs to the + * original block. In this case, make the entry look + * like it has an empty value. + */ + if (!s->not_found && s->here->e_value_inum) { + ea_ino = le32_to_cpu(s->here->e_value_inum); + error = ext4_xattr_inode_iget(inode, ea_ino, + le32_to_cpu(s->here->e_hash), + &tmp_inode); + if (error) goto cleanup; - s->first = ENTRY(header(s->base)+1); - header(s->base)->h_refcount = cpu_to_le32(1); - s->here = ENTRY(s->base + offset); - s->end = s->base + bs->bh->b_size; - /* - * If existing entry points to an xattr inode, we need - * to prevent ext4_xattr_set_entry() from decrementing - * ref count on it because the reference belongs to the - * original block. In this case, make the entry look - * like it has an empty value. - */ - if (!s->not_found && s->here->e_value_inum) { - ea_ino = le32_to_cpu(s->here->e_value_inum); - error = ext4_xattr_inode_iget(inode, ea_ino, - le32_to_cpu(s->here->e_hash), - &tmp_inode); - if (error) - goto cleanup; - - if (!ext4_test_inode_state(tmp_inode, - EXT4_STATE_LUSTRE_EA_INODE)) { - /* - * Defer quota free call for previous - * inode until success is guaranteed. - */ - old_ea_inode_quota = le32_to_cpu( - s->here->e_value_size); - } - iput(tmp_inode); - - s->here->e_value_inum = 0; - s->here->e_value_size = 0; + if (!ext4_test_inode_state(tmp_inode, + EXT4_STATE_LUSTRE_EA_INODE)) { + /* + * Defer quota free call for previous + * inode until success is guaranteed. + */ + old_ea_inode_quota = le32_to_cpu( + s->here->e_value_size); } + iput(tmp_inode); + + s->here->e_value_inum = 0; + s->here->e_value_size = 0; } } else { /* Allocate a buffer where we construct the new block. */ From 1a56cd972ce121b6cf2517a47a578782bbd2ec95 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 12 Jul 2022 12:54:24 +0200 Subject: [PATCH 0803/4345] ext4: fix race when reusing xattr blocks [ Upstream commit 65f8b80053a1b2fd602daa6814e62d6fa90e5e9b ] When ext4_xattr_block_set() decides to remove xattr block the following race can happen: CPU1 CPU2 ext4_xattr_block_set() ext4_xattr_release_block() new_bh = ext4_xattr_block_cache_find() lock_buffer(bh); ref = le32_to_cpu(BHDR(bh)->h_refcount); if (ref == 1) { ... mb_cache_entry_delete(); unlock_buffer(bh); ext4_free_blocks(); ... ext4_forget(..., bh, ...); jbd2_journal_revoke(..., bh); ext4_journal_get_write_access(..., new_bh, ...) do_get_write_access() jbd2_journal_cancel_revoke(..., new_bh); Later the code in ext4_xattr_block_set() finds out the block got freed and cancels reusal of the block but the revoke stays canceled and so in case of block reuse and journal replay the filesystem can get corrupted. If the race works out slightly differently, we can also hit assertions in the jbd2 code. Fix the problem by making sure that once matching mbcache entry is found, code dropping the last xattr block reference (or trying to modify xattr block in place) waits until the mbcache entry reference is dropped. This way code trying to reuse xattr block is protected from someone trying to drop the last reference to xattr block. Reported-and-tested-by: Ritesh Harjani CC: stable@vger.kernel.org Fixes: 82939d7999df ("ext4: convert to mbcache2") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20220712105436.32204-5-jack@suse.cz Signed-off-by: Theodore Ts'o Stable-dep-of: a44e84a9b776 ("ext4: fix deadlock due to mbcache entry corruption") Signed-off-by: Sasha Levin --- fs/ext4/xattr.c | 67 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 45 insertions(+), 22 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 9d5ccc90eb63..35251afdf770 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -439,9 +439,16 @@ error: /* Remove entry from mbcache when EA inode is getting evicted */ void ext4_evict_ea_inode(struct inode *inode) { - if (EA_INODE_CACHE(inode)) - mb_cache_entry_delete(EA_INODE_CACHE(inode), - ext4_xattr_inode_get_hash(inode), inode->i_ino); + struct mb_cache_entry *oe; + + if (!EA_INODE_CACHE(inode)) + return; + /* Wait for entry to get unused so that we can remove it */ + while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode), + ext4_xattr_inode_get_hash(inode), inode->i_ino))) { + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(EA_INODE_CACHE(inode), oe); + } } static int @@ -1223,6 +1230,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, if (error) goto out; +retry_ref: lock_buffer(bh); hash = le32_to_cpu(BHDR(bh)->h_hash); ref = le32_to_cpu(BHDR(bh)->h_refcount); @@ -1232,9 +1240,18 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, + bh->b_blocknr); + if (oe) { + unlock_buffer(bh); + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(ea_block_cache, oe); + goto retry_ref; + } + } get_bh(bh); unlock_buffer(bh); @@ -1862,9 +1879,20 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, * ext4_xattr_block_set() to reliably detect modified * block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bs->bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, + hash, bs->bh->b_blocknr); + if (oe) { + /* + * Xattr block is getting reused. Leave + * it alone. + */ + mb_cache_entry_put(ea_block_cache, oe); + goto clone_block; + } + } ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); @@ -1880,6 +1908,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, goto cleanup; goto inserted; } +clone_block: unlock_buffer(bs->bh); ea_bdebug(bs->bh, "cloning"); s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); @@ -1985,18 +2014,13 @@ inserted: lock_buffer(new_bh); /* * We have to be careful about races with - * freeing, rehashing or adding references to - * xattr block. Once we hold buffer lock xattr - * block's state is stable so we can check - * whether the block got freed / rehashed or - * not. Since we unhash mbcache entry under - * buffer lock when freeing / rehashing xattr - * block, checking whether entry is still - * hashed is reliable. Same rules hold for - * e_reusable handling. + * adding references to xattr block. Once we + * hold buffer lock xattr block's state is + * stable so we can check the additional + * reference fits. */ - if (hlist_bl_unhashed(&ce->e_hash_list) || - !ce->e_reusable) { + ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; + if (ref > EXT4_XATTR_REFCOUNT_MAX) { /* * Undo everything and check mbcache * again. @@ -2011,9 +2035,8 @@ inserted: new_bh = NULL; goto inserted; } - ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; BHDR(new_bh)->h_refcount = cpu_to_le32(ref); - if (ref >= EXT4_XATTR_REFCOUNT_MAX) + if (ref == EXT4_XATTR_REFCOUNT_MAX) ce->e_reusable = 0; ea_bdebug(new_bh, "reusing; refcount now=%d", ref); From 0da99012d3f7ccec903e9db4013647e1b831bced Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 12 Jul 2022 12:54:29 +0200 Subject: [PATCH 0804/4345] mbcache: automatically delete entries from cache on freeing [ Upstream commit 307af6c879377c1c63e71cbdd978201f9c7ee8df ] Use the fact that entries with elevated refcount are not removed from the hash and just move removal of the entry from the hash to the entry freeing time. When doing this we also change the generic code to hold one reference to the cache entry, not two of them, which makes code somewhat more obvious. Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20220712105436.32204-10-jack@suse.cz Signed-off-by: Theodore Ts'o Stable-dep-of: a44e84a9b776 ("ext4: fix deadlock due to mbcache entry corruption") Signed-off-by: Sasha Levin --- fs/mbcache.c | 108 +++++++++++++++------------------------- include/linux/mbcache.h | 24 ++++++--- 2 files changed, 55 insertions(+), 77 deletions(-) diff --git a/fs/mbcache.c b/fs/mbcache.c index 2010bc80a3f2..950f1829a7fd 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -90,7 +90,7 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, return -ENOMEM; INIT_LIST_HEAD(&entry->e_list); - /* One ref for hash, one ref returned */ + /* Initial hash reference */ atomic_set(&entry->e_refcnt, 1); entry->e_key = key; entry->e_value = value; @@ -106,21 +106,28 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, } } hlist_bl_add_head(&entry->e_hash_list, head); - hlist_bl_unlock(head); - + /* + * Add entry to LRU list before it can be found by + * mb_cache_entry_delete() to avoid races + */ spin_lock(&cache->c_list_lock); list_add_tail(&entry->e_list, &cache->c_list); - /* Grab ref for LRU list */ - atomic_inc(&entry->e_refcnt); cache->c_entry_count++; spin_unlock(&cache->c_list_lock); + hlist_bl_unlock(head); return 0; } EXPORT_SYMBOL(mb_cache_entry_create); -void __mb_cache_entry_free(struct mb_cache_entry *entry) +void __mb_cache_entry_free(struct mb_cache *cache, struct mb_cache_entry *entry) { + struct hlist_bl_head *head; + + head = mb_cache_entry_head(cache, entry->e_key); + hlist_bl_lock(head); + hlist_bl_del(&entry->e_hash_list); + hlist_bl_unlock(head); kmem_cache_free(mb_entry_cache, entry); } EXPORT_SYMBOL(__mb_cache_entry_free); @@ -134,7 +141,7 @@ EXPORT_SYMBOL(__mb_cache_entry_free); */ void mb_cache_entry_wait_unused(struct mb_cache_entry *entry) { - wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 3); + wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 2); } EXPORT_SYMBOL(mb_cache_entry_wait_unused); @@ -155,10 +162,9 @@ static struct mb_cache_entry *__entry_find(struct mb_cache *cache, while (node) { entry = hlist_bl_entry(node, struct mb_cache_entry, e_hash_list); - if (entry->e_key == key && entry->e_reusable) { - atomic_inc(&entry->e_refcnt); + if (entry->e_key == key && entry->e_reusable && + atomic_inc_not_zero(&entry->e_refcnt)) goto out; - } node = node->next; } entry = NULL; @@ -218,10 +224,9 @@ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_value == value) { - atomic_inc(&entry->e_refcnt); + if (entry->e_key == key && entry->e_value == value && + atomic_inc_not_zero(&entry->e_refcnt)) goto out; - } } entry = NULL; out: @@ -281,37 +286,25 @@ EXPORT_SYMBOL(mb_cache_entry_delete); struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, u32 key, u64 value) { - struct hlist_bl_node *node; - struct hlist_bl_head *head; struct mb_cache_entry *entry; - head = mb_cache_entry_head(cache, key); - hlist_bl_lock(head); - hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_value == value) { - if (atomic_read(&entry->e_refcnt) > 2) { - atomic_inc(&entry->e_refcnt); - hlist_bl_unlock(head); - return entry; - } - /* We keep hash list reference to keep entry alive */ - hlist_bl_del_init(&entry->e_hash_list); - hlist_bl_unlock(head); - spin_lock(&cache->c_list_lock); - if (!list_empty(&entry->e_list)) { - list_del_init(&entry->e_list); - if (!WARN_ONCE(cache->c_entry_count == 0, - "mbcache: attempt to decrement c_entry_count past zero")) - cache->c_entry_count--; - atomic_dec(&entry->e_refcnt); - } - spin_unlock(&cache->c_list_lock); - mb_cache_entry_put(cache, entry); - return NULL; - } - } - hlist_bl_unlock(head); + entry = mb_cache_entry_get(cache, key, value); + if (!entry) + return NULL; + /* + * Drop the ref we got from mb_cache_entry_get() and the initial hash + * ref if we are the last user + */ + if (atomic_cmpxchg(&entry->e_refcnt, 2, 0) != 2) + return entry; + + spin_lock(&cache->c_list_lock); + if (!list_empty(&entry->e_list)) + list_del_init(&entry->e_list); + cache->c_entry_count--; + spin_unlock(&cache->c_list_lock); + __mb_cache_entry_free(cache, entry); return NULL; } EXPORT_SYMBOL(mb_cache_entry_delete_or_get); @@ -343,42 +336,24 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache, unsigned long nr_to_scan) { struct mb_cache_entry *entry; - struct hlist_bl_head *head; unsigned long shrunk = 0; spin_lock(&cache->c_list_lock); while (nr_to_scan-- && !list_empty(&cache->c_list)) { entry = list_first_entry(&cache->c_list, struct mb_cache_entry, e_list); - if (entry->e_referenced || atomic_read(&entry->e_refcnt) > 2) { + /* Drop initial hash reference if there is no user */ + if (entry->e_referenced || + atomic_cmpxchg(&entry->e_refcnt, 1, 0) != 1) { entry->e_referenced = 0; list_move_tail(&entry->e_list, &cache->c_list); continue; } list_del_init(&entry->e_list); cache->c_entry_count--; - /* - * We keep LRU list reference so that entry doesn't go away - * from under us. - */ spin_unlock(&cache->c_list_lock); - head = mb_cache_entry_head(cache, entry->e_key); - hlist_bl_lock(head); - /* Now a reliable check if the entry didn't get used... */ - if (atomic_read(&entry->e_refcnt) > 2) { - hlist_bl_unlock(head); - spin_lock(&cache->c_list_lock); - list_add_tail(&entry->e_list, &cache->c_list); - cache->c_entry_count++; - continue; - } - if (!hlist_bl_unhashed(&entry->e_hash_list)) { - hlist_bl_del_init(&entry->e_hash_list); - atomic_dec(&entry->e_refcnt); - } - hlist_bl_unlock(head); - if (mb_cache_entry_put(cache, entry)) - shrunk++; + __mb_cache_entry_free(cache, entry); + shrunk++; cond_resched(); spin_lock(&cache->c_list_lock); } @@ -470,11 +445,6 @@ void mb_cache_destroy(struct mb_cache *cache) * point. */ list_for_each_entry_safe(entry, next, &cache->c_list, e_list) { - if (!hlist_bl_unhashed(&entry->e_hash_list)) { - hlist_bl_del_init(&entry->e_hash_list); - atomic_dec(&entry->e_refcnt); - } else - WARN_ON(1); list_del(&entry->e_list); WARN_ON(atomic_read(&entry->e_refcnt) != 1); mb_cache_entry_put(cache, entry); diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index 8eca7f25c432..e9d5ece87794 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -13,8 +13,16 @@ struct mb_cache; struct mb_cache_entry { /* List of entries in cache - protected by cache->c_list_lock */ struct list_head e_list; - /* Hash table list - protected by hash chain bitlock */ + /* + * Hash table list - protected by hash chain bitlock. The entry is + * guaranteed to be hashed while e_refcnt > 0. + */ struct hlist_bl_node e_hash_list; + /* + * Entry refcount. Once it reaches zero, entry is unhashed and freed. + * While refcount > 0, the entry is guaranteed to stay in the hash and + * e.g. mb_cache_entry_try_delete() will fail. + */ atomic_t e_refcnt; /* Key in hash - stable during lifetime of the entry */ u32 e_key; @@ -29,20 +37,20 @@ void mb_cache_destroy(struct mb_cache *cache); int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, u64 value, bool reusable); -void __mb_cache_entry_free(struct mb_cache_entry *entry); +void __mb_cache_entry_free(struct mb_cache *cache, + struct mb_cache_entry *entry); void mb_cache_entry_wait_unused(struct mb_cache_entry *entry); -static inline int mb_cache_entry_put(struct mb_cache *cache, - struct mb_cache_entry *entry) +static inline void mb_cache_entry_put(struct mb_cache *cache, + struct mb_cache_entry *entry) { unsigned int cnt = atomic_dec_return(&entry->e_refcnt); if (cnt > 0) { - if (cnt <= 3) + if (cnt <= 2) wake_up_var(&entry->e_refcnt); - return 0; + return; } - __mb_cache_entry_free(entry); - return 1; + __mb_cache_entry_free(cache, entry); } struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, From 1be16a0c2f10186df505e28b0cc92d7f3366e2a8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 23 Nov 2022 20:39:50 +0100 Subject: [PATCH 0805/4345] ext4: fix deadlock due to mbcache entry corruption [ Upstream commit a44e84a9b7764c72896f7241a0ec9ac7e7ef38dd ] When manipulating xattr blocks, we can deadlock infinitely looping inside ext4_xattr_block_set() where we constantly keep finding xattr block for reuse in mbcache but we are unable to reuse it because its reference count is too big. This happens because cache entry for the xattr block is marked as reusable (e_reusable set) although its reference count is too big. When this inconsistency happens, this inconsistent state is kept indefinitely and so ext4_xattr_block_set() keeps retrying indefinitely. The inconsistent state is caused by non-atomic update of e_reusable bit. e_reusable is part of a bitfield and e_reusable update can race with update of e_referenced bit in the same bitfield resulting in loss of one of the updates. Fix the problem by using atomic bitops instead. This bug has been around for many years, but it became *much* easier to hit after commit 65f8b80053a1 ("ext4: fix race when reusing xattr blocks"). Cc: stable@vger.kernel.org Fixes: 6048c64b2609 ("mbcache: add reusable flag to cache entries") Fixes: 65f8b80053a1 ("ext4: fix race when reusing xattr blocks") Reported-and-tested-by: Jeremi Piotrowski Reported-by: Thilo Fromm Link: https://lore.kernel.org/r/c77bf00f-4618-7149-56f1-b8d1664b9d07@linux.microsoft.com/ Signed-off-by: Jan Kara Reviewed-by: Andreas Dilger Link: https://lore.kernel.org/r/20221123193950.16758-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/xattr.c | 4 ++-- fs/mbcache.c | 14 ++++++++------ include/linux/mbcache.h | 9 +++++++-- 3 files changed, 17 insertions(+), 10 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 35251afdf770..6bf1c62eff04 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1275,7 +1275,7 @@ retry_ref: ce = mb_cache_entry_get(ea_block_cache, hash, bh->b_blocknr); if (ce) { - ce->e_reusable = 1; + set_bit(MBE_REUSABLE_B, &ce->e_flags); mb_cache_entry_put(ea_block_cache, ce); } } @@ -2037,7 +2037,7 @@ inserted: } BHDR(new_bh)->h_refcount = cpu_to_le32(ref); if (ref == EXT4_XATTR_REFCOUNT_MAX) - ce->e_reusable = 0; + clear_bit(MBE_REUSABLE_B, &ce->e_flags); ea_bdebug(new_bh, "reusing; refcount now=%d", ref); ext4_xattr_block_csum_set(inode, new_bh); diff --git a/fs/mbcache.c b/fs/mbcache.c index 950f1829a7fd..7a12ae87c806 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -94,8 +94,9 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, atomic_set(&entry->e_refcnt, 1); entry->e_key = key; entry->e_value = value; - entry->e_reusable = reusable; - entry->e_referenced = 0; + entry->e_flags = 0; + if (reusable) + set_bit(MBE_REUSABLE_B, &entry->e_flags); head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) { @@ -162,7 +163,8 @@ static struct mb_cache_entry *__entry_find(struct mb_cache *cache, while (node) { entry = hlist_bl_entry(node, struct mb_cache_entry, e_hash_list); - if (entry->e_key == key && entry->e_reusable && + if (entry->e_key == key && + test_bit(MBE_REUSABLE_B, &entry->e_flags) && atomic_inc_not_zero(&entry->e_refcnt)) goto out; node = node->next; @@ -318,7 +320,7 @@ EXPORT_SYMBOL(mb_cache_entry_delete_or_get); void mb_cache_entry_touch(struct mb_cache *cache, struct mb_cache_entry *entry) { - entry->e_referenced = 1; + set_bit(MBE_REFERENCED_B, &entry->e_flags); } EXPORT_SYMBOL(mb_cache_entry_touch); @@ -343,9 +345,9 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache, entry = list_first_entry(&cache->c_list, struct mb_cache_entry, e_list); /* Drop initial hash reference if there is no user */ - if (entry->e_referenced || + if (test_bit(MBE_REFERENCED_B, &entry->e_flags) || atomic_cmpxchg(&entry->e_refcnt, 1, 0) != 1) { - entry->e_referenced = 0; + clear_bit(MBE_REFERENCED_B, &entry->e_flags); list_move_tail(&entry->e_list, &cache->c_list); continue; } diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index e9d5ece87794..591bc4cefe1d 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -10,6 +10,12 @@ struct mb_cache; +/* Cache entry flags */ +enum { + MBE_REFERENCED_B = 0, + MBE_REUSABLE_B +}; + struct mb_cache_entry { /* List of entries in cache - protected by cache->c_list_lock */ struct list_head e_list; @@ -26,8 +32,7 @@ struct mb_cache_entry { atomic_t e_refcnt; /* Key in hash - stable during lifetime of the entry */ u32 e_key; - u32 e_referenced:1; - u32 e_reusable:1; + unsigned long e_flags; /* User provided value - stable during lifetime of the entry */ u64 e_value; }; From cb0d627bc711ef429467b8193c7130abea6df42e Mon Sep 17 00:00:00 2001 From: minoura makoto Date: Tue, 13 Dec 2022 13:14:31 +0900 Subject: [PATCH 0806/4345] SUNRPC: ensure the matching upcall is in-flight upon downcall [ Upstream commit b18cba09e374637a0a3759d856a6bca94c133952 ] Commit 9130b8dbc6ac ("SUNRPC: allow for upcalls for the same uid but different gss service") introduced `auth` argument to __gss_find_upcall(), but in gss_pipe_downcall() it was left as NULL since it (and auth->service) was not (yet) determined. When multiple upcalls with the same uid and different service are ongoing, it could happen that __gss_find_upcall(), which returns the first match found in the pipe->in_downcall list, could not find the correct gss_msg corresponding to the downcall we are looking for. Moreover, it might return a msg which is not sent to rpc.gssd yet. We could see mount.nfs process hung in D state with multiple mount.nfs are executed in parallel. The call trace below is of CentOS 7.9 kernel-3.10.0-1160.24.1.el7.x86_64 but we observed the same hang w/ elrepo kernel-ml-6.0.7-1.el7. PID: 71258 TASK: ffff91ebd4be0000 CPU: 36 COMMAND: "mount.nfs" #0 [ffff9203ca3234f8] __schedule at ffffffffa3b8899f #1 [ffff9203ca323580] schedule at ffffffffa3b88eb9 #2 [ffff9203ca323590] gss_cred_init at ffffffffc0355818 [auth_rpcgss] #3 [ffff9203ca323658] rpcauth_lookup_credcache at ffffffffc0421ebc [sunrpc] #4 [ffff9203ca3236d8] gss_lookup_cred at ffffffffc0353633 [auth_rpcgss] #5 [ffff9203ca3236e8] rpcauth_lookupcred at ffffffffc0421581 [sunrpc] #6 [ffff9203ca323740] rpcauth_refreshcred at ffffffffc04223d3 [sunrpc] #7 [ffff9203ca3237a0] call_refresh at ffffffffc04103dc [sunrpc] #8 [ffff9203ca3237b8] __rpc_execute at ffffffffc041e1c9 [sunrpc] #9 [ffff9203ca323820] rpc_execute at ffffffffc0420a48 [sunrpc] The scenario is like this. Let's say there are two upcalls for services A and B, A -> B in pipe->in_downcall, B -> A in pipe->pipe. When rpc.gssd reads pipe to get the upcall msg corresponding to service B from pipe->pipe and then writes the response, in gss_pipe_downcall the msg corresponding to service A will be picked because only uid is used to find the msg and it is before the one for B in pipe->in_downcall. And the process waiting for the msg corresponding to service A will be woken up. Actual scheduing of that process might be after rpc.gssd processes the next msg. In rpc_pipe_generic_upcall it clears msg->errno (for A). The process is scheduled to see gss_msg->ctx == NULL and gss_msg->msg.errno == 0, therefore it cannot break the loop in gss_create_upcall and is never woken up after that. This patch adds a simple check to ensure that a msg which is not sent to rpc.gssd yet is not chosen as the matching upcall upon receiving a downcall. Signed-off-by: minoura makoto Signed-off-by: Hiroshi Shimamoto Tested-by: Hiroshi Shimamoto Cc: Trond Myklebust Fixes: 9130b8dbc6ac ("SUNRPC: allow for upcalls for same uid but different gss service") Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- include/linux/sunrpc/rpc_pipe_fs.h | 5 +++++ net/sunrpc/auth_gss/auth_gss.c | 19 +++++++++++++++++-- 2 files changed, 22 insertions(+), 2 deletions(-) diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index cd188a527d16..3b35b6f6533a 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -92,6 +92,11 @@ extern ssize_t rpc_pipe_generic_upcall(struct file *, struct rpc_pipe_msg *, char __user *, size_t); extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *); +/* returns true if the msg is in-flight, i.e., already eaten by the peer */ +static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) { + return (msg->copied != 0 && list_empty(&msg->list)); +} + struct rpc_clnt; extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *); extern int rpc_remove_client_dir(struct rpc_clnt *); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 5f42aa5fc612..2ff66a6a7e54 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -301,7 +301,7 @@ __gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth list_for_each_entry(pos, &pipe->in_downcall, list) { if (!uid_eq(pos->uid, uid)) continue; - if (auth && pos->auth->service != auth->service) + if (pos->auth->service != auth->service) continue; refcount_inc(&pos->count); return pos; @@ -685,6 +685,21 @@ out: return err; } +static struct gss_upcall_msg * +gss_find_downcall(struct rpc_pipe *pipe, kuid_t uid) +{ + struct gss_upcall_msg *pos; + list_for_each_entry(pos, &pipe->in_downcall, list) { + if (!uid_eq(pos->uid, uid)) + continue; + if (!rpc_msg_is_inflight(&pos->msg)) + continue; + refcount_inc(&pos->count); + return pos; + } + return NULL; +} + #define MSG_BUF_MAXSIZE 1024 static ssize_t @@ -731,7 +746,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) err = -ENOENT; /* Find a matching upcall */ spin_lock(&pipe->lock); - gss_msg = __gss_find_upcall(pipe, uid, NULL); + gss_msg = gss_find_downcall(pipe, uid); if (gss_msg == NULL) { spin_unlock(&pipe->lock); goto err_put_ctx; From e68e088d0d6ada6dcc226d1ca147488f60abca0e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 19 Dec 2022 16:47:00 -0800 Subject: [PATCH 0807/4345] bpf: pull before calling skb_postpull_rcsum() [ Upstream commit 54c3f1a81421f85e60ae2eaae7be3727a09916ee ] Anand hit a BUG() when pulling off headers on egress to a SW tunnel. We get to skb_checksum_help() with an invalid checksum offset (commit d7ea0d9df2a6 ("net: remove two BUG() from skb_checksum_help()") converted those BUGs to WARN_ONs()). He points out oddness in how skb_postpull_rcsum() gets used. Indeed looks like we should pull before "postpull", otherwise the CHECKSUM_PARTIAL fixup from skb_postpull_rcsum() will not be able to do its job: if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; Reported-by: Anand Parthasarathy Fixes: 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper") Signed-off-by: Jakub Kicinski Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20221220004701.402165-1-kuba@kernel.org Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- net/core/filter.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index e3cdbd4996e0..a5df0cf46bbf 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3201,15 +3201,18 @@ static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len) { + void *old_data; + /* skb_ensure_writable() is not needed here, as we're * already working on an uncloned skb. */ if (unlikely(!pskb_may_pull(skb, off + len))) return -ENOMEM; - skb_postpull_rcsum(skb, skb->data + off, len); - memmove(skb->data + len, skb->data, off); + old_data = skb->data; __skb_pull(skb, len); + skb_postpull_rcsum(skb, old_data + off, len); + memmove(skb->data, old_data, off); return 0; } From 0b70f6ea4d4f2b4d4b291d86ab76b4d07394932c Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 19 Dec 2022 14:01:30 +0000 Subject: [PATCH 0808/4345] drm/panfrost: Fix GEM handle creation ref-counting [ Upstream commit 4217c6ac817451d5116687f3cc6286220dc43d49 ] panfrost_gem_create_with_handle() previously returned a BO but with the only reference being from the handle, which user space could in theory guess and release, causing a use-after-free. Additionally if the call to panfrost_gem_mapping_get() in panfrost_ioctl_create_bo() failed then a(nother) reference on the BO was dropped. The _create_with_handle() is a problematic pattern, so ditch it and instead create the handle in panfrost_ioctl_create_bo(). If the call to panfrost_gem_mapping_get() fails then this means that user space has indeed gone behind our back and freed the handle. In which case just return an error code. Reported-by: Rob Clark Fixes: f3ba91228e8e ("drm/panfrost: Add initial panfrost driver") Signed-off-by: Steven Price Reviewed-by: Rob Clark Link: https://patchwork.freedesktop.org/patch/msgid/20221219140130.410578-1-steven.price@arm.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/panfrost/panfrost_drv.c | 27 ++++++++++++++++--------- drivers/gpu/drm/panfrost/panfrost_gem.c | 16 +-------------- drivers/gpu/drm/panfrost/panfrost_gem.h | 5 +---- 3 files changed, 20 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 1dfc457bbefc..4af25c0b6570 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -81,6 +81,7 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data, struct panfrost_gem_object *bo; struct drm_panfrost_create_bo *args = data; struct panfrost_gem_mapping *mapping; + int ret; if (!args->size || args->pad || (args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP))) @@ -91,21 +92,29 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data, !(args->flags & PANFROST_BO_NOEXEC)) return -EINVAL; - bo = panfrost_gem_create_with_handle(file, dev, args->size, args->flags, - &args->handle); + bo = panfrost_gem_create(dev, args->size, args->flags); if (IS_ERR(bo)) return PTR_ERR(bo); + ret = drm_gem_handle_create(file, &bo->base.base, &args->handle); + if (ret) + goto out; + mapping = panfrost_gem_mapping_get(bo, priv); - if (!mapping) { - drm_gem_object_put(&bo->base.base); - return -EINVAL; + if (mapping) { + args->offset = mapping->mmnode.start << PAGE_SHIFT; + panfrost_gem_mapping_put(mapping); + } else { + /* This can only happen if the handle from + * drm_gem_handle_create() has already been guessed and freed + * by user space + */ + ret = -EINVAL; } - args->offset = mapping->mmnode.start << PAGE_SHIFT; - panfrost_gem_mapping_put(mapping); - - return 0; +out: + drm_gem_object_put(&bo->base.base); + return ret; } /** diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index 1d917cea5ceb..c843fbfdb878 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -232,12 +232,8 @@ struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t } struct panfrost_gem_object * -panfrost_gem_create_with_handle(struct drm_file *file_priv, - struct drm_device *dev, size_t size, - u32 flags, - uint32_t *handle) +panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags) { - int ret; struct drm_gem_shmem_object *shmem; struct panfrost_gem_object *bo; @@ -253,16 +249,6 @@ panfrost_gem_create_with_handle(struct drm_file *file_priv, bo->noexec = !!(flags & PANFROST_BO_NOEXEC); bo->is_heap = !!(flags & PANFROST_BO_HEAP); - /* - * Allocate an id of idr table where the obj is registered - * and handle has the id what user can see. - */ - ret = drm_gem_handle_create(file_priv, &shmem->base, handle); - /* drop reference from allocate - handle holds it now. */ - drm_gem_object_put(&shmem->base); - if (ret) - return ERR_PTR(ret); - return bo; } diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h index 8088d5fd8480..ad2877eeeccd 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.h +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h @@ -69,10 +69,7 @@ panfrost_gem_prime_import_sg_table(struct drm_device *dev, struct sg_table *sgt); struct panfrost_gem_object * -panfrost_gem_create_with_handle(struct drm_file *file_priv, - struct drm_device *dev, size_t size, - u32 flags, - uint32_t *handle); +panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags); int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv); void panfrost_gem_close(struct drm_gem_object *obj, From 5f41212dc2ec8cfc045740d0ca14ac1f32c7f9aa Mon Sep 17 00:00:00 2001 From: Ronak Doshi Date: Tue, 20 Dec 2022 12:25:55 -0800 Subject: [PATCH 0809/4345] vmxnet3: correctly report csum_level for encapsulated packet [ Upstream commit 3d8f2c4269d08f8793e946279dbdf5e972cc4911 ] Commit dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload support") added support for encapsulation offload. However, the pathc did not report correctly the csum_level for encapsulated packet. This patch fixes this issue by reporting correct csum level for the encapsulated packet. Fixes: dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload support") Signed-off-by: Ronak Doshi Acked-by: Peng Li Link: https://lore.kernel.org/r/20221220202556.24421-1-doshir@vmware.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/vmxnet3/vmxnet3_drv.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 43a4bcdd92c1..3b889fed9882 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1236,6 +1236,10 @@ vmxnet3_rx_csum(struct vmxnet3_adapter *adapter, (le32_to_cpu(gdesc->dword[3]) & VMXNET3_RCD_CSUM_OK) == VMXNET3_RCD_CSUM_OK) { skb->ip_summed = CHECKSUM_UNNECESSARY; + if ((le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) { + skb->csum_level = 1; + } WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) && !(le32_to_cpu(gdesc->dword[0]) & (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))); @@ -1245,6 +1249,10 @@ vmxnet3_rx_csum(struct vmxnet3_adapter *adapter, } else if (gdesc->rcd.v6 && (le32_to_cpu(gdesc->dword[3]) & (1 << VMXNET3_RCD_TUC_SHIFT))) { skb->ip_summed = CHECKSUM_UNNECESSARY; + if ((le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) { + skb->csum_level = 1; + } WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) && !(le32_to_cpu(gdesc->dword[0]) & (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))); From 69d896b60957f5612dc98c902fd4d5370b23923f Mon Sep 17 00:00:00 2001 From: Shawn Bohrer Date: Tue, 20 Dec 2022 12:59:03 -0600 Subject: [PATCH 0810/4345] veth: Fix race with AF_XDP exposing old or uninitialized descriptors [ Upstream commit fa349e396e4886d742fd6501c599ec627ef1353b ] When AF_XDP is used on on a veth interface the RX ring is updated in two steps. veth_xdp_rcv() removes packet descriptors from the FILL ring fills them and places them in the RX ring updating the cached_prod pointer. Later xdp_do_flush() syncs the RX ring prod pointer with the cached_prod pointer allowing user-space to see the recently filled in descriptors. The rings are intended to be SPSC, however the existing order in veth_poll allows the xdp_do_flush() to run concurrently with another CPU creating a race condition that allows user-space to see old or uninitialized descriptors in the RX ring. This bug has been observed in production systems. To summarize, we are expecting this ordering: CPU 0 __xsk_rcv_zc() CPU 0 __xsk_map_flush() CPU 2 __xsk_rcv_zc() CPU 2 __xsk_map_flush() But we are seeing this order: CPU 0 __xsk_rcv_zc() CPU 2 __xsk_rcv_zc() CPU 0 __xsk_map_flush() CPU 2 __xsk_map_flush() This occurs because we rely on NAPI to ensure that only one napi_poll handler is running at a time for the given veth receive queue. napi_schedule_prep() will prevent multiple instances from getting scheduled. However calling napi_complete_done() signals that this napi_poll is complete and allows subsequent calls to napi_schedule_prep() and __napi_schedule() to succeed in scheduling a concurrent napi_poll before the xdp_do_flush() has been called. For the veth driver a concurrent call to napi_schedule_prep() and __napi_schedule() can occur on a different CPU because the veth xmit path can additionally schedule a napi_poll creating the race. The fix as suggested by Magnus Karlsson, is to simply move the xdp_do_flush() call before napi_complete_done(). This syncs the producer ring pointers before another instance of napi_poll can be scheduled on another CPU. It will also slightly improve performance by moving the flush closer to when the descriptors were placed in the RX ring. Fixes: d1396004dd86 ("veth: Add XDP TX and REDIRECT") Suggested-by: Magnus Karlsson Signed-off-by: Shawn Bohrer Link: https://lore.kernel.org/r/20221220185903.1105011-1-sbohrer@cloudflare.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/veth.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 5be8ed910553..5aa23a036ed3 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -849,6 +849,9 @@ static int veth_poll(struct napi_struct *napi, int budget) xdp_set_return_frame_no_direct(); done = veth_xdp_rcv(rq, budget, &bq, &stats); + if (stats.xdp_redirect > 0) + xdp_do_flush(); + if (done < budget && napi_complete_done(napi, done)) { /* Write rx_notify_masked before reading ptr_ring */ smp_store_mb(rq->rx_notify_masked, false); @@ -862,8 +865,6 @@ static int veth_poll(struct napi_struct *napi, int budget) if (stats.xdp_tx > 0) veth_xdp_flush(rq, &bq); - if (stats.xdp_redirect > 0) - xdp_do_flush(); xdp_clear_return_frame_no_direct(); return done; From 998ebbdc3bb14411817a04c8f19e9199c5b9df32 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 22 Dec 2022 09:51:30 -0500 Subject: [PATCH 0811/4345] nfsd: shut down the NFSv4 state objects before the filecache [ Upstream commit 789e1e10f214c00ca18fc6610824c5b9876ba5f2 ] Currently, we shut down the filecache before trying to clean up the stateids that depend on it. This leads to the kernel trying to free an nfsd_file twice, and a refcount overput on the nf_mark. Change the shutdown procedure to tear down all of the stateids prior to shutting down the filecache. Reported-and-tested-by: Wang Yugui Signed-off-by: Jeff Layton Fixes: 5e113224c17e ("nfsd: nfsd_file cache entries should be per net namespace") Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/nfssvc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 9323e30a7eaf..c7fffe1453bd 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -426,8 +426,8 @@ static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nfsd_file_cache_shutdown_net(net); nfs4_state_shutdown_net(net); + nfsd_file_cache_shutdown_net(net); if (nn->lockd_up) { lockd_down(net); nn->lockd_up = false; From 4226ce95a9349f44c48e78b1fce1912fc7f90771 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Thu, 22 Dec 2022 14:43:41 +0800 Subject: [PATCH 0812/4345] net: hns3: add interrupts re-initialization while doing VF FLR [ Upstream commit 09e6b30eeb254f1818a008cace3547159e908dfd ] Currently keep alive message between PF and VF may be lost and the VF is unalive in PF. So the VF will not do reset during PF FLR reset process. This would make the allocated interrupt resources of VF invalid and VF would't receive or respond to PF any more. So this patch adds VF interrupts re-initialization during VF FLR for VF recovery in above cases. Fixes: 862d969a3a4d ("net: hns3: do VF's pci re-initialization while PF doing FLR") Signed-off-by: Jie Wang Signed-off-by: Hao Lan Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index d6580e942724..f7f3e4bbc477 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -3089,7 +3089,8 @@ static int hclgevf_pci_reset(struct hclgevf_dev *hdev) struct pci_dev *pdev = hdev->pdev; int ret = 0; - if (hdev->reset_type == HNAE3_VF_FULL_RESET && + if ((hdev->reset_type == HNAE3_VF_FULL_RESET || + hdev->reset_type == HNAE3_FLR_RESET) && test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) { hclgevf_misc_irq_uninit(hdev); hclgevf_uninit_msi(hdev); From b314f6c3512108d7a656c5caf07c82d1bbbdc0f1 Mon Sep 17 00:00:00 2001 From: Hawkins Jiawei Date: Thu, 22 Dec 2022 11:51:19 +0800 Subject: [PATCH 0813/4345] net: sched: fix memory leak in tcindex_set_parms [ Upstream commit 399ab7fe0fa0d846881685fd4e57e9a8ef7559f7 ] Syzkaller reports a memory leak as follows: ==================================== BUG: memory leak unreferenced object 0xffff88810c287f00 (size 256): comm "syz-executor105", pid 3600, jiffies 4294943292 (age 12.990s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmalloc_trace+0x20/0x90 mm/slab_common.c:1046 [] kmalloc include/linux/slab.h:576 [inline] [] kmalloc_array include/linux/slab.h:627 [inline] [] kcalloc include/linux/slab.h:659 [inline] [] tcf_exts_init include/net/pkt_cls.h:250 [inline] [] tcindex_set_parms+0xa7/0xbe0 net/sched/cls_tcindex.c:342 [] tcindex_change+0xdf/0x120 net/sched/cls_tcindex.c:553 [] tc_new_tfilter+0x4f2/0x1100 net/sched/cls_api.c:2147 [] rtnetlink_rcv_msg+0x4dc/0x5d0 net/core/rtnetlink.c:6082 [] netlink_rcv_skb+0x87/0x1d0 net/netlink/af_netlink.c:2540 [] netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] [] netlink_unicast+0x397/0x4c0 net/netlink/af_netlink.c:1345 [] netlink_sendmsg+0x396/0x710 net/netlink/af_netlink.c:1921 [] sock_sendmsg_nosec net/socket.c:714 [inline] [] sock_sendmsg+0x56/0x80 net/socket.c:734 [] ____sys_sendmsg+0x178/0x410 net/socket.c:2482 [] ___sys_sendmsg+0xa8/0x110 net/socket.c:2536 [] __sys_sendmmsg+0x105/0x330 net/socket.c:2622 [] __do_sys_sendmmsg net/socket.c:2651 [inline] [] __se_sys_sendmmsg net/socket.c:2648 [inline] [] __x64_sys_sendmmsg+0x24/0x30 net/socket.c:2648 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x63/0xcd ==================================== Kernel uses tcindex_change() to change an existing filter properties. Yet the problem is that, during the process of changing, if `old_r` is retrieved from `p->perfect`, then kernel uses tcindex_alloc_perfect_hash() to newly allocate filter results, uses tcindex_filter_result_init() to clear the old filter result, without destroying its tcf_exts structure, which triggers the above memory leak. To be more specific, there are only two source for the `old_r`, according to the tcindex_lookup(). `old_r` is retrieved from `p->perfect`, or `old_r` is retrieved from `p->h`. * If `old_r` is retrieved from `p->perfect`, kernel uses tcindex_alloc_perfect_hash() to newly allocate the filter results. Then `r` is assigned with `cp->perfect + handle`, which is newly allocated. So condition `old_r && old_r != r` is true in this situation, and kernel uses tcindex_filter_result_init() to clear the old filter result, without destroying its tcf_exts structure * If `old_r` is retrieved from `p->h`, then `p->perfect` is NULL according to the tcindex_lookup(). Considering that `cp->h` is directly copied from `p->h` and `p->perfect` is NULL, `r` is assigned with `tcindex_lookup(cp, handle)`, whose value should be the same as `old_r`, so condition `old_r && old_r != r` is false in this situation, kernel ignores using tcindex_filter_result_init() to clear the old filter result. So only when `old_r` is retrieved from `p->perfect` does kernel use tcindex_filter_result_init() to clear the old filter result, which triggers the above memory leak. Considering that there already exists a tc_filter_wq workqueue to destroy the old tcindex_data by tcindex_partial_destroy_work() at the end of tcindex_set_parms(), this patch solves this memory leak bug by removing this old filter result clearing part and delegating it to the tc_filter_wq workqueue. Note that this patch doesn't introduce any other issues. If `old_r` is retrieved from `p->perfect`, this patch just delegates old filter result clearing part to the tc_filter_wq workqueue; If `old_r` is retrieved from `p->h`, kernel doesn't reach the old filter result clearing part, so removing this part has no effect. [Thanks to the suggestion from Jakub Kicinski, Cong Wang, Paolo Abeni and Dmitry Vyukov] Fixes: b9a24bb76bf6 ("net_sched: properly handle failure case of tcf_exts_init()") Link: https://lore.kernel.org/all/0000000000001de5c505ebc9ec59@google.com/ Reported-by: syzbot+232ebdbd36706c965ebf@syzkaller.appspotmail.com Tested-by: syzbot+232ebdbd36706c965ebf@syzkaller.appspotmail.com Cc: Cong Wang Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Dmitry Vyukov Acked-by: Paolo Abeni Signed-off-by: Hawkins Jiawei Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/cls_tcindex.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index e9a8a2c86bbd..86250221d08d 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -332,7 +332,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct tcindex_filter_result *r, struct nlattr **tb, struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) { - struct tcindex_filter_result new_filter_result, *old_r = r; + struct tcindex_filter_result new_filter_result; struct tcindex_data *cp = NULL, *oldp; struct tcindex_filter *f = NULL; /* make gcc behave */ struct tcf_result cr = {}; @@ -401,7 +401,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcindex_filter_result_init(&new_filter_result, cp, net); if (err < 0) goto errout_alloc; - if (old_r) + if (r) cr = r->res; err = -EBUSY; @@ -478,14 +478,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, tcf_bind_filter(tp, &cr, base); } - if (old_r && old_r != r) { - err = tcindex_filter_result_init(old_r, cp, net); - if (err < 0) { - kfree(f); - goto errout_alloc; - } - } - oldp = p; r->res = cr; tcf_exts_change(&r->exts, &e); From 513787ff9a331b461115e8a145a983d650a84fcb Mon Sep 17 00:00:00 2001 From: Daniil Tatianin Date: Thu, 22 Dec 2022 14:52:28 +0300 Subject: [PATCH 0814/4345] qlcnic: prevent ->dcb use-after-free on qlcnic_dcb_enable() failure [ Upstream commit 13a7c8964afcd8ca43c0b6001ebb0127baa95362 ] adapter->dcb would get silently freed inside qlcnic_dcb_enable() in case qlcnic_dcb_attach() would return an error, which always happens under OOM conditions. This would lead to use-after-free because both of the existing callers invoke qlcnic_dcb_get_info() on the obtained pointer, which is potentially freed at that point. Propagate errors from qlcnic_dcb_enable(), and instead free the dcb pointer at callsite using qlcnic_dcb_free(). This also removes the now unused qlcnic_clear_dcb_ops() helper, which was a simple wrapper around kfree() also causing memory leaks for partially initialized dcb. Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Fixes: 3c44bba1d270 ("qlcnic: Disable DCB operations from SR-IOV VFs") Reviewed-by: Michal Swiatkowski Signed-off-by: Daniil Tatianin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c | 8 +++++++- drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h | 10 ++-------- drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 8 +++++++- 3 files changed, 16 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index d2c190732d3e..beeeec8516b8 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -2505,7 +2505,13 @@ int qlcnic_83xx_init(struct qlcnic_adapter *adapter, int pci_using_dac) goto disable_mbx_intr; qlcnic_83xx_clear_function_resources(adapter); - qlcnic_dcb_enable(adapter->dcb); + + err = qlcnic_dcb_enable(adapter->dcb); + if (err) { + qlcnic_dcb_free(adapter->dcb); + goto disable_mbx_intr; + } + qlcnic_83xx_initialize_nic(adapter, 1); qlcnic_dcb_get_info(adapter->dcb); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h index 7519773eaca6..22afa2be85fd 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h @@ -41,11 +41,6 @@ struct qlcnic_dcb { unsigned long state; }; -static inline void qlcnic_clear_dcb_ops(struct qlcnic_dcb *dcb) -{ - kfree(dcb); -} - static inline int qlcnic_dcb_get_hw_capability(struct qlcnic_dcb *dcb) { if (dcb && dcb->ops->get_hw_capability) @@ -112,9 +107,8 @@ static inline void qlcnic_dcb_init_dcbnl_ops(struct qlcnic_dcb *dcb) dcb->ops->init_dcbnl_ops(dcb); } -static inline void qlcnic_dcb_enable(struct qlcnic_dcb *dcb) +static inline int qlcnic_dcb_enable(struct qlcnic_dcb *dcb) { - if (dcb && qlcnic_dcb_attach(dcb)) - qlcnic_clear_dcb_ops(dcb); + return dcb ? qlcnic_dcb_attach(dcb) : 0; } #endif diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 27c07b2412f4..44b745293fd0 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -2622,7 +2622,13 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) "Device does not support MSI interrupts\n"); if (qlcnic_82xx_check(adapter)) { - qlcnic_dcb_enable(adapter->dcb); + err = qlcnic_dcb_enable(adapter->dcb); + if (err) { + qlcnic_dcb_free(adapter->dcb); + dev_err(&pdev->dev, "Failed to enable DCB\n"); + goto err_out_free_hw; + } + qlcnic_dcb_get_info(adapter->dcb); err = qlcnic_setup_intr(adapter); From e0f5c962c066e769c187f037fedc883f8abd4e82 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Fri, 23 Dec 2022 11:37:18 +0400 Subject: [PATCH 0815/4345] nfc: Fix potential resource leaks [ Upstream commit df49908f3c52d211aea5e2a14a93bbe67a2cb3af ] nfc_get_device() take reference for the device, add missing nfc_put_device() to release it when not need anymore. Also fix the style warnning by use error EOPNOTSUPP instead of ENOTSUPP. Fixes: 5ce3f32b5264 ("NFC: netlink: SE API implementation") Fixes: 29e76924cf08 ("nfc: netlink: Add capability to reply to vendor_cmd with data") Signed-off-by: Miaoqian Lin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/nfc/netlink.c | 52 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 38 insertions(+), 14 deletions(-) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index b8939ebaa6d3..610caea4feec 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1497,6 +1497,7 @@ static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info) u32 dev_idx, se_idx; u8 *apdu; size_t apdu_len; + int rc; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_SE_INDEX] || @@ -1510,25 +1511,37 @@ static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info) if (!dev) return -ENODEV; - if (!dev->ops || !dev->ops->se_io) - return -ENOTSUPP; + if (!dev->ops || !dev->ops->se_io) { + rc = -EOPNOTSUPP; + goto put_dev; + } apdu_len = nla_len(info->attrs[NFC_ATTR_SE_APDU]); - if (apdu_len == 0) - return -EINVAL; + if (apdu_len == 0) { + rc = -EINVAL; + goto put_dev; + } apdu = nla_data(info->attrs[NFC_ATTR_SE_APDU]); - if (!apdu) - return -EINVAL; + if (!apdu) { + rc = -EINVAL; + goto put_dev; + } ctx = kzalloc(sizeof(struct se_io_ctx), GFP_KERNEL); - if (!ctx) - return -ENOMEM; + if (!ctx) { + rc = -ENOMEM; + goto put_dev; + } ctx->dev_idx = dev_idx; ctx->se_idx = se_idx; - return nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx); + rc = nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx); + +put_dev: + nfc_put_device(dev); + return rc; } static int nfc_genl_vendor_cmd(struct sk_buff *skb, @@ -1551,14 +1564,21 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb, subcmd = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_SUBCMD]); dev = nfc_get_device(dev_idx); - if (!dev || !dev->vendor_cmds || !dev->n_vendor_cmds) + if (!dev) return -ENODEV; + if (!dev->vendor_cmds || !dev->n_vendor_cmds) { + err = -ENODEV; + goto put_dev; + } + if (info->attrs[NFC_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]); data_len = nla_len(info->attrs[NFC_ATTR_VENDOR_DATA]); - if (data_len == 0) - return -EINVAL; + if (data_len == 0) { + err = -EINVAL; + goto put_dev; + } } else { data = NULL; data_len = 0; @@ -1573,10 +1593,14 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb, dev->cur_cmd_info = info; err = cmd->doit(dev, data, data_len); dev->cur_cmd_info = NULL; - return err; + goto put_dev; } - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + +put_dev: + nfc_put_device(dev); + return err; } /* message building helper */ From eabb3ceb04cddbda22014059d29b8a27fc9607cb Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Tue, 8 Nov 2022 10:17:05 +0000 Subject: [PATCH 0816/4345] vhost/vsock: Fix error handling in vhost_vsock_init() [ Upstream commit 7a4efe182ca61fb3e5307e69b261c57cbf434cd4 ] A problem about modprobe vhost_vsock failed is triggered with the following log given: modprobe: ERROR: could not insert 'vhost_vsock': Device or resource busy The reason is that vhost_vsock_init() returns misc_register() directly without checking its return value, if misc_register() failed, it returns without calling vsock_core_unregister() on vhost_transport, resulting the vhost_vsock can never be installed later. A simple call graph is shown as below: vhost_vsock_init() vsock_core_register() # register vhost_transport misc_register() device_create_with_groups() device_create_groups_vargs() dev = kzalloc(...) # OOM happened # return without unregister vhost_transport Fix by calling vsock_core_unregister() when misc_register() returns error. Fixes: 433fc58e6bf2 ("VSOCK: Introduce vhost_vsock.ko") Signed-off-by: Yuan Can Message-Id: <20221108101705.45981-1-yuancan@huawei.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella Acked-by: Jason Wang Signed-off-by: Sasha Levin --- drivers/vhost/vsock.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index b0153617fe0e..7bce5f982e58 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -854,7 +854,14 @@ static int __init vhost_vsock_init(void) VSOCK_TRANSPORT_F_H2G); if (ret < 0) return ret; - return misc_register(&vhost_vsock_misc); + + ret = misc_register(&vhost_vsock_misc); + if (ret) { + vsock_core_unregister(&vhost_transport.transport); + return ret; + } + + return 0; }; static void __exit vhost_vsock_exit(void) From 264fb6dcbfde48e0686158dcebde89598685ba01 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Wed, 9 Nov 2022 11:25:02 +0100 Subject: [PATCH 0817/4345] vringh: fix range used in iotlb_translate() [ Upstream commit f85efa9b0f5381874f727bd98f56787840313f0b ] vhost_iotlb_itree_first() requires `start` and `last` parameters to search for a mapping that overlaps the range. In iotlb_translate() we cyclically call vhost_iotlb_itree_first(), incrementing `addr` by the amount already translated, so rightly we move the `start` parameter passed to vhost_iotlb_itree_first(), but we should hold the `last` parameter constant. Let's fix it by saving the `last` parameter value before incrementing `addr` in the loop. Fixes: 9ad9c49cfe97 ("vringh: IOTLB support") Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Message-Id: <20221109102503.18816-2-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- drivers/vhost/vringh.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 5a0340c85dc6..48f4ec2ba40a 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -1077,7 +1077,7 @@ static int iotlb_translate(const struct vringh *vrh, struct vhost_iotlb_map *map; struct vhost_iotlb *iotlb = vrh->iotlb; int ret = 0; - u64 s = 0; + u64 s = 0, last = addr + len - 1; while (len > s) { u64 size, pa, pfn; @@ -1087,8 +1087,7 @@ static int iotlb_translate(const struct vringh *vrh, break; } - map = vhost_iotlb_itree_first(iotlb, addr, - addr + len - 1); + map = vhost_iotlb_itree_first(iotlb, addr, last); if (!map || map->start > addr) { ret = -EINVAL; break; From b6c74d2376483d556c8156c3aadd550f1f2d4413 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Wed, 9 Nov 2022 11:25:03 +0100 Subject: [PATCH 0818/4345] vhost: fix range used in translate_desc() [ Upstream commit 98047313cdb46828093894d0ac8b1183b8b317f9 ] vhost_iotlb_itree_first() requires `start` and `last` parameters to search for a mapping that overlaps the range. In translate_desc() we cyclically call vhost_iotlb_itree_first(), incrementing `addr` by the amount already translated, so rightly we move the `start` parameter passed to vhost_iotlb_itree_first(), but we should hold the `last` parameter constant. Let's fix it by saving the `last` parameter value before incrementing `addr` in the loop. Fixes: a9709d6874d5 ("vhost: convert pre sorted vhost memory array to interval tree") Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Message-Id: <20221109102503.18816-3-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- drivers/vhost/vhost.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index f41463ab4031..da00a5c57db6 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2041,7 +2041,7 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, struct vhost_dev *dev = vq->dev; struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem; struct iovec *_iov; - u64 s = 0; + u64 s = 0, last = addr + len - 1; int ret = 0; while ((u64)len > s) { @@ -2051,7 +2051,7 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, break; } - map = vhost_iotlb_itree_first(umem, addr, addr + len - 1); + map = vhost_iotlb_itree_first(umem, addr, last); if (map == NULL || map->start > addr) { if (umem != dev->iotlb) { ret = -EFAULT; From 66b92b80c95ebd0fc080395d376b5f283bfc2266 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 18 Oct 2022 12:51:52 +0200 Subject: [PATCH 0819/4345] net/mlx5: Add forgotten cleanup calls into mlx5_init_once() error path [ Upstream commit 2a35b2c2e6a252eda2134aae6a756861d9299531 ] There are two cleanup calls missing in mlx5_init_once() error path. Add them making the error path flow to be the same as mlx5_cleanup_once(). Fixes: 52ec462eca9b ("net/mlx5: Add reserved-gids support") Fixes: 7c39afb394c7 ("net/mlx5: PTP code migration to driver core section") Signed-off-by: Jiri Pirko Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8246b6285d5a..29bc1df28aeb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -906,6 +906,8 @@ err_rl_cleanup: err_tables_cleanup: mlx5_geneve_destroy(dev->geneve); mlx5_vxlan_destroy(dev->vxlan); + mlx5_cleanup_clock(dev); + mlx5_cleanup_reserved_gids(dev); mlx5_cq_debugfs_cleanup(dev); mlx5_fw_reset_cleanup(dev); err_events_cleanup: From 670b20617346d4d4e9ddbeed971037fdb98b19d3 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 24 Nov 2022 13:34:12 +0200 Subject: [PATCH 0820/4345] net/mlx5: Avoid recovery in probe flows [ Upstream commit 9078e843efec530f279a155f262793c58b0746bd ] Currently, recovery is done without considering whether the device is still in probe flow. This may lead to recovery before device have finished probed successfully. e.g.: while mlx5_init_one() is running. Recovery flow is using functionality that is loaded only by mlx5_init_one(), and there is no point in running recovery without mlx5_init_one() finished successfully. Fix it by waiting for probe flow to finish and checking whether the device is probed before trying to perform recovery. Fixes: 51d138c2610a ("net/mlx5: Fix health error state handling") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 0c32c485eb58..b21054514736 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -618,6 +618,12 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) priv = container_of(health, struct mlx5_priv, health); dev = container_of(priv, struct mlx5_core_dev, priv); + mutex_lock(&dev->intf_state_mutex); + if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) { + mlx5_core_err(dev, "health works are not permitted at this stage\n"); + return; + } + mutex_unlock(&dev->intf_state_mutex); enter_error_state(dev, false); if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) { if (mlx5_health_try_recover(dev)) From 6d655a9d8251d1066104529c813ae138ed9f9de1 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Mon, 28 Nov 2022 15:24:21 +0200 Subject: [PATCH 0821/4345] net/mlx5e: IPoIB, Don't allow CQE compression to be turned on by default [ Upstream commit b12d581e83e3ae1080c32ab83f123005bd89a840 ] mlx5e_build_nic_params will turn CQE compression on if the hardware capability is enabled and the slow_pci_heuristic condition is detected. As IPoIB doesn't support CQE compression, make sure to disable the feature in the IPoIB profile init. Please note that the feature is not exposed to the user for IPoIB interfaces, so it can't be subsequently turned on. Fixes: b797a684b0dd ("net/mlx5e: Enable CQE compression when PCI is slower than link") Signed-off-by: Dragos Tatulea Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 5c6a376aa62e..0e7fd200b426 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -69,6 +69,10 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, params->lro_en = false; params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN; params->tunneled_offload_en = false; + + /* CQE compression is not supported for IPoIB */ + params->rx_cqe_compress_def = false; + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def); } /* Called directly after IPoIB netdevice was created to initialize SW structs */ From e3d90ca906524aa92aae5fe7c6e8b8fe5c34af35 Mon Sep 17 00:00:00 2001 From: Adham Faris Date: Wed, 14 Dec 2022 16:02:57 +0200 Subject: [PATCH 0822/4345] net/mlx5e: Fix hw mtu initializing at XDP SQ allocation [ Upstream commit 1e267ab88dc44c48f556218f7b7f14c76f7aa066 ] Current xdp xmit functions logic (mlx5e_xmit_xdp_frame_mpwqe or mlx5e_xmit_xdp_frame), validates xdp packet length by comparing it to hw mtu (configured at xdp sq allocation) before xmiting it. This check does not account for ethernet fcs length (calculated and filled by the nic). Hence, when we try sending packets with length > (hw-mtu - ethernet-fcs-size), the device port drops it and tx_errors_phy is incremented. Desired behavior is to catch these packets and drop them by the driver. Fix this behavior in XDP SQ allocation function (mlx5e_alloc_xdpsq) by subtracting ethernet FCS header size (4 Bytes) from current hw mtu value, since ethernet FCS is calculated and written to ethernet frames by the nic. Fixes: d8bec2b29a82 ("net/mlx5e: Support bpf_xdp_adjust_head()") Signed-off-by: Adham Faris Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cfc3bfcb04a2..5673a4113253 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -992,7 +992,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; - sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN; sq->xsk_pool = xsk_pool; sq->stats = sq->xsk_pool ? From 398e14bb735d92097215ff0bf1949b78c8421c81 Mon Sep 17 00:00:00 2001 From: Jiguang Xiao Date: Wed, 28 Dec 2022 16:14:47 +0800 Subject: [PATCH 0823/4345] net: amd-xgbe: add missed tasklet_kill [ Upstream commit d530ece70f16f912e1d1bfeea694246ab78b0a4b ] The driver does not call tasklet_kill in several places. Add the calls to fix it. Fixes: 85b85c853401 ("amd-xgbe: Re-issue interrupt if interrupt status not cleared") Signed-off-by: Jiguang Xiao Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 3 +++ drivers/net/ethernet/amd/xgbe/xgbe-i2c.c | 4 +++- drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 4 +++- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index a816b30bca04..a5d6faf7b89e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1064,6 +1064,9 @@ static void xgbe_free_irqs(struct xgbe_prv_data *pdata) devm_free_irq(pdata->dev, pdata->dev_irq, pdata); + tasklet_kill(&pdata->tasklet_dev); + tasklet_kill(&pdata->tasklet_ecc); + if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq)) devm_free_irq(pdata->dev, pdata->ecc_irq, pdata); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c index 22d4fc547a0a..a9ccc4258ee5 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c @@ -447,8 +447,10 @@ static void xgbe_i2c_stop(struct xgbe_prv_data *pdata) xgbe_i2c_disable(pdata); xgbe_i2c_clear_all_interrupts(pdata); - if (pdata->dev_irq != pdata->i2c_irq) + if (pdata->dev_irq != pdata->i2c_irq) { devm_free_irq(pdata->dev, pdata->i2c_irq, pdata); + tasklet_kill(&pdata->tasklet_i2c); + } } static int xgbe_i2c_start(struct xgbe_prv_data *pdata) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 4e97b4869522..0c5c1b155683 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1390,8 +1390,10 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata) /* Disable auto-negotiation */ xgbe_an_disable_all(pdata); - if (pdata->dev_irq != pdata->an_irq) + if (pdata->dev_irq != pdata->an_irq) { devm_free_irq(pdata->dev, pdata->an_irq, pdata); + tasklet_kill(&pdata->tasklet_an); + } pdata->phy_if.phy_impl.stop(pdata); From 106d0d33c9d1ec4ddeeffc1fdc717ff09953d4ed Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Thu, 29 Dec 2022 10:29:25 +0400 Subject: [PATCH 0824/4345] net: phy: xgmiitorgmii: Fix refcount leak in xgmiitorgmii_probe [ Upstream commit d039535850ee47079d59527e96be18d8e0daa84b ] of_phy_find_device() return device node with refcount incremented. Call put_device() to relese it when not needed anymore. Fixes: ab4e6ee578e8 ("net: phy: xgmiitorgmii: Check phy_driver ready before accessing") Signed-off-by: Miaoqian Lin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/phy/xilinx_gmii2rgmii.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c index 151c2a3f0b3a..7a78dfdfa5bd 100644 --- a/drivers/net/phy/xilinx_gmii2rgmii.c +++ b/drivers/net/phy/xilinx_gmii2rgmii.c @@ -82,6 +82,7 @@ static int xgmiitorgmii_probe(struct mdio_device *mdiodev) if (!priv->phy_dev->drv) { dev_info(dev, "Attached phy not ready\n"); + put_device(&priv->phy_dev->mdio.dev); return -EPROBE_DEFER; } From ae2639cd2c8cce5168a29be013b20ffa573be407 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 28 Dec 2022 14:56:10 +0200 Subject: [PATCH 0825/4345] RDMA/mlx5: Fix validation of max_rd_atomic caps for DC [ Upstream commit 8de8482fe5732fbef4f5af82bc0c0362c804cd1f ] Currently, when modifying DC, we validate max_rd_atomic user attribute against the RC cap, validate against DC. RC and DC QP types have different device limitations. This can cause userspace created DC QPs to malfunction. Fixes: c32a4f296e1d ("IB/mlx5: Add support for DC Initiator QP") Link: https://lore.kernel.org/r/0c5aee72cea188c3bb770f4207cce7abc9b6fc74.1672231736.git.leonro@nvidia.com Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx5/qp.c | 49 +++++++++++++++++++++++---------- 1 file changed, 35 insertions(+), 14 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 7a2bec0ac005..0caff276f2c1 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4258,6 +4258,40 @@ static bool mlx5_ib_modify_qp_allowed(struct mlx5_ib_dev *dev, return false; } +static int validate_rd_atomic(struct mlx5_ib_dev *dev, struct ib_qp_attr *attr, + int attr_mask, enum ib_qp_type qp_type) +{ + int log_max_ra_res; + int log_max_ra_req; + + if (qp_type == MLX5_IB_QPT_DCI) { + log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev, + log_max_ra_res_dc); + log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev, + log_max_ra_req_dc); + } else { + log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev, + log_max_ra_res_qp); + log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev, + log_max_ra_req_qp); + } + + if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC && + attr->max_rd_atomic > log_max_ra_res) { + mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n", + attr->max_rd_atomic); + return false; + } + + if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC && + attr->max_dest_rd_atomic > log_max_ra_req) { + mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n", + attr->max_dest_rd_atomic); + return false; + } + return true; +} + int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { @@ -4352,21 +4386,8 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, } } - if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC && - attr->max_rd_atomic > - (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_res_qp))) { - mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n", - attr->max_rd_atomic); + if (!validate_rd_atomic(dev, attr, attr_mask, qp_type)) goto out; - } - - if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC && - attr->max_dest_rd_atomic > - (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_req_qp))) { - mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n", - attr->max_dest_rd_atomic); - goto out; - } if (cur_state == new_state && cur_state == IB_QPS_RESET) { err = 0; From 9f0ff5de3e81635335e186f737f0c57be2526f4d Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Mon, 19 Dec 2022 09:43:05 +0100 Subject: [PATCH 0826/4345] drm/meson: Reduce the FIFO lines held when AFBC is not used [ Upstream commit 3b754ed6d1cd90017e66e5cc16f3923e4a952ffc ] Having a bigger number of FIFO lines held after vsync is only useful to SoCs using AFBC to give time to the AFBC decoder to be reset, configured and enabled again. For SoCs not using AFBC this, on the contrary, is causing on some displays issues and a few pixels vertical offset in the displayed image. Conditionally increase the number of lines held after vsync only for SoCs using AFBC, leaving the default value for all the others. Fixes: 24e0d4058eff ("drm/meson: hold 32 lines after vsync to give time for AFBC start") Signed-off-by: Carlo Caione Acked-by: Martin Blumenstingl Acked-by: Neil Armstrong [narmstrong: added fixes tag] Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20221216-afbc_s905x-v1-0-033bebf780d9@baylibre.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/meson/meson_viu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c index d4b907889a21..cd399b0b7181 100644 --- a/drivers/gpu/drm/meson/meson_viu.c +++ b/drivers/gpu/drm/meson/meson_viu.c @@ -436,15 +436,14 @@ void meson_viu_init(struct meson_drm *priv) /* Initialize OSD1 fifo control register */ reg = VIU_OSD_DDR_PRIORITY_URGENT | - VIU_OSD_HOLD_FIFO_LINES(31) | VIU_OSD_FIFO_DEPTH_VAL(32) | /* fifo_depth_val: 32*8=256 */ VIU_OSD_WORDS_PER_BURST(4) | /* 4 words in 1 burst */ VIU_OSD_FIFO_LIMITS(2); /* fifo_lim: 2*16=32 */ if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) - reg |= VIU_OSD_BURST_LENGTH_32; + reg |= (VIU_OSD_BURST_LENGTH_32 | VIU_OSD_HOLD_FIFO_LINES(31)); else - reg |= VIU_OSD_BURST_LENGTH_64; + reg |= (VIU_OSD_BURST_LENGTH_64 | VIU_OSD_HOLD_FIFO_LINES(4)); writel_relaxed(reg, priv->io_base + _REG(VIU_OSD1_FIFO_CTRL_STAT)); writel_relaxed(reg, priv->io_base + _REG(VIU_OSD2_FIFO_CTRL_STAT)); From 407710427dd53290b6406ca7583ba82ae7f7ba59 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 14 Nov 2022 08:33:09 -0500 Subject: [PATCH 0827/4345] filelock: new helper: vfs_inode_has_locks [ Upstream commit ab1ddef98a715eddb65309ffa83267e4e84a571e ] Ceph has a need to know whether a particular inode has any locks set on it. It's currently tracking that by a num_locks field in its filp->private_data, but that's problematic as it tries to decrement this field when releasing locks and that can race with the file being torn down. Add a new vfs_inode_has_locks helper that just returns whether any locks are currently held on the inode. Reviewed-by: Xiubo Li Reviewed-by: Christoph Hellwig Signed-off-by: Jeff Layton Stable-dep-of: 461ab10ef7e6 ("ceph: switch to vfs_inode_has_locks() to fix file lock bug") Signed-off-by: Sasha Levin --- fs/locks.c | 23 +++++++++++++++++++++++ include/linux/fs.h | 6 ++++++ 2 files changed, 29 insertions(+) diff --git a/fs/locks.c b/fs/locks.c index 32c948fe2944..12d72c3d8756 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2813,6 +2813,29 @@ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) } EXPORT_SYMBOL_GPL(vfs_cancel_lock); +/** + * vfs_inode_has_locks - are any file locks held on @inode? + * @inode: inode to check for locks + * + * Return true if there are any FL_POSIX or FL_FLOCK locks currently + * set on @inode. + */ +bool vfs_inode_has_locks(struct inode *inode) +{ + struct file_lock_context *ctx; + bool ret; + + ctx = smp_load_acquire(&inode->i_flctx); + if (!ctx) + return false; + + spin_lock(&ctx->flc_lock); + ret = !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_flock); + spin_unlock(&ctx->flc_lock); + return ret; +} +EXPORT_SYMBOL_GPL(vfs_inode_has_locks); + #ifdef CONFIG_PROC_FS #include #include diff --git a/include/linux/fs.h b/include/linux/fs.h index 9a477e537361..74e19bccbf73 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1145,6 +1145,7 @@ extern int locks_delete_block(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); +bool vfs_inode_has_locks(struct inode *inode); extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); extern void lease_get_mtime(struct inode *, struct timespec64 *time); @@ -1257,6 +1258,11 @@ static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) return 0; } +static inline bool vfs_inode_has_locks(struct inode *inode) +{ + return false; +} + static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; From 7ec369e215bfeb08cb58150cc0d527fbc81d4d38 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 17 Nov 2022 10:43:21 +0800 Subject: [PATCH 0828/4345] ceph: switch to vfs_inode_has_locks() to fix file lock bug [ Upstream commit 461ab10ef7e6ea9b41a0571a7fc6a72af9549a3c ] For the POSIX locks they are using the same owner, which is the thread id. And multiple POSIX locks could be merged into single one, so when checking whether the 'file' has locks may fail. For a file where some openers use locking and others don't is a really odd usage pattern though. Locks are like stoplights -- they only work if everyone pays attention to them. Just switch ceph_get_caps() to check whether any locks are set on the inode. If there are POSIX/OFD/FLOCK locks on the file at the time, we should set CHECK_FILELOCK, regardless of what fd was used to set the lock. Fixes: ff5d913dfc71 ("ceph: return -EIO if read/write against filp that lost file locks") Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov Signed-off-by: Sasha Levin --- fs/ceph/caps.c | 2 +- fs/ceph/locks.c | 4 ---- fs/ceph/super.h | 1 - 3 files changed, 1 insertion(+), 6 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 51562d36fa83..210496dc2fd4 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2957,7 +2957,7 @@ int ceph_get_caps(struct file *filp, int need, int want, while (true) { flags &= CEPH_FILE_MODE_MASK; - if (atomic_read(&fi->num_locks)) + if (vfs_inode_has_locks(inode)) flags |= CHECK_FILELOCK; _got = 0; ret = try_get_cap_refs(inode, need, want, endoff, diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 048a435a29be..674d6ea89f71 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -32,18 +32,14 @@ void __init ceph_flock_init(void) static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src) { - struct ceph_file_info *fi = dst->fl_file->private_data; struct inode *inode = file_inode(dst->fl_file); atomic_inc(&ceph_inode(inode)->i_filelock_ref); - atomic_inc(&fi->num_locks); } static void ceph_fl_release_lock(struct file_lock *fl) { - struct ceph_file_info *fi = fl->fl_file->private_data; struct inode *inode = file_inode(fl->fl_file); struct ceph_inode_info *ci = ceph_inode(inode); - atomic_dec(&fi->num_locks); if (atomic_dec_and_test(&ci->i_filelock_ref)) { /* clear error when all locks are released */ spin_lock(&ci->i_ceph_lock); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 4db305fd2a02..8716cb618cbb 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -772,7 +772,6 @@ struct ceph_file_info { struct list_head rw_contexts; u32 filp_gen; - atomic_t num_locks; }; struct ceph_dir_file_info { From f4a2ad1002006548e235255c65a4f1d07312be9d Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 2 Jan 2023 12:20:39 +0400 Subject: [PATCH 0829/4345] gpio: sifive: Fix refcount leak in sifive_gpio_probe [ Upstream commit 694175cd8a1643cde3acb45c9294bca44a8e08e9 ] of_irq_find_parent() returns a node pointer with refcount incremented, We should use of_node_put() on it when not needed anymore. Add missing of_node_put() to avoid refcount leak. Fixes: 96868dce644d ("gpio/sifive: Add GPIO driver for SiFive SoCs") Signed-off-by: Miaoqian Lin Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpio-sifive.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c index 4f28fa73450c..a42ffb9f3057 100644 --- a/drivers/gpio/gpio-sifive.c +++ b/drivers/gpio/gpio-sifive.c @@ -195,6 +195,7 @@ static int sifive_gpio_probe(struct platform_device *pdev) return -ENODEV; } parent = irq_find_host(irq_parent); + of_node_put(irq_parent); if (!parent) { dev_err(dev, "no IRQ parent domain\n"); return -ENODEV; From 5f65f48516bfeebaab1ccc52c8fad698ddf21282 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 1 Jan 2023 16:57:43 -0500 Subject: [PATCH 0830/4345] net: sched: atm: dont intepret cls results when asked to drop [ Upstream commit a2965c7be0522eaa18808684b7b82b248515511b ] If asked to drop a packet via TC_ACT_SHOT it is unsafe to assume res.class contains a valid pointer Fixes: b0188d4dbe5f ("[NET_SCHED]: sch_atm: Lindent") Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/sch_atm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 794c7377cd7e..95967ce1f370 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -396,10 +396,13 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, result = tcf_classify(skb, fl, &res, true); if (result < 0) continue; + if (result == TC_ACT_SHOT) + goto done; + flow = (struct atm_flow_data *)res.class; if (!flow) flow = lookup_flow(sch, res.classid); - goto done; + goto drop; } } flow = NULL; From b2c917e510e5ddbc7896329c87d20036c8b82952 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 1 Jan 2023 16:57:44 -0500 Subject: [PATCH 0831/4345] net: sched: cbq: dont intepret cls results when asked to drop [ Upstream commit caa4b35b4317d5147b3ab0fbdc9c075c7d2e9c12 ] If asked to drop a packet via TC_ACT_SHOT it is unsafe to assume that res.class contains a valid pointer Sample splat reported by Kyle Zeng [ 5.405624] 0: reclassify loop, rule prio 0, protocol 800 [ 5.406326] ================================================================== [ 5.407240] BUG: KASAN: slab-out-of-bounds in cbq_enqueue+0x54b/0xea0 [ 5.407987] Read of size 1 at addr ffff88800e3122aa by task poc/299 [ 5.408731] [ 5.408897] CPU: 0 PID: 299 Comm: poc Not tainted 5.10.155+ #15 [ 5.409516] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 5.410439] Call Trace: [ 5.410764] dump_stack+0x87/0xcd [ 5.411153] print_address_description+0x7a/0x6b0 [ 5.411687] ? vprintk_func+0xb9/0xc0 [ 5.411905] ? printk+0x76/0x96 [ 5.412110] ? cbq_enqueue+0x54b/0xea0 [ 5.412323] kasan_report+0x17d/0x220 [ 5.412591] ? cbq_enqueue+0x54b/0xea0 [ 5.412803] __asan_report_load1_noabort+0x10/0x20 [ 5.413119] cbq_enqueue+0x54b/0xea0 [ 5.413400] ? __kasan_check_write+0x10/0x20 [ 5.413679] __dev_queue_xmit+0x9c0/0x1db0 [ 5.413922] dev_queue_xmit+0xc/0x10 [ 5.414136] ip_finish_output2+0x8bc/0xcd0 [ 5.414436] __ip_finish_output+0x472/0x7a0 [ 5.414692] ip_finish_output+0x5c/0x190 [ 5.414940] ip_output+0x2d8/0x3c0 [ 5.415150] ? ip_mc_finish_output+0x320/0x320 [ 5.415429] __ip_queue_xmit+0x753/0x1760 [ 5.415664] ip_queue_xmit+0x47/0x60 [ 5.415874] __tcp_transmit_skb+0x1ef9/0x34c0 [ 5.416129] tcp_connect+0x1f5e/0x4cb0 [ 5.416347] tcp_v4_connect+0xc8d/0x18c0 [ 5.416577] __inet_stream_connect+0x1ae/0xb40 [ 5.416836] ? local_bh_enable+0x11/0x20 [ 5.417066] ? lock_sock_nested+0x175/0x1d0 [ 5.417309] inet_stream_connect+0x5d/0x90 [ 5.417548] ? __inet_stream_connect+0xb40/0xb40 [ 5.417817] __sys_connect+0x260/0x2b0 [ 5.418037] __x64_sys_connect+0x76/0x80 [ 5.418267] do_syscall_64+0x31/0x50 [ 5.418477] entry_SYSCALL_64_after_hwframe+0x61/0xc6 [ 5.418770] RIP: 0033:0x473bb7 [ 5.418952] Code: 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2a 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 18 89 54 24 0c 48 89 34 24 89 [ 5.420046] RSP: 002b:00007fffd20eb0f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002a [ 5.420472] RAX: ffffffffffffffda RBX: 00007fffd20eb578 RCX: 0000000000473bb7 [ 5.420872] RDX: 0000000000000010 RSI: 00007fffd20eb110 RDI: 0000000000000007 [ 5.421271] RBP: 00007fffd20eb150 R08: 0000000000000001 R09: 0000000000000004 [ 5.421671] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001 [ 5.422071] R13: 00007fffd20eb568 R14: 00000000004fc740 R15: 0000000000000002 [ 5.422471] [ 5.422562] Allocated by task 299: [ 5.422782] __kasan_kmalloc+0x12d/0x160 [ 5.423007] kasan_kmalloc+0x5/0x10 [ 5.423208] kmem_cache_alloc_trace+0x201/0x2e0 [ 5.423492] tcf_proto_create+0x65/0x290 [ 5.423721] tc_new_tfilter+0x137e/0x1830 [ 5.423957] rtnetlink_rcv_msg+0x730/0x9f0 [ 5.424197] netlink_rcv_skb+0x166/0x300 [ 5.424428] rtnetlink_rcv+0x11/0x20 [ 5.424639] netlink_unicast+0x673/0x860 [ 5.424870] netlink_sendmsg+0x6af/0x9f0 [ 5.425100] __sys_sendto+0x58d/0x5a0 [ 5.425315] __x64_sys_sendto+0xda/0xf0 [ 5.425539] do_syscall_64+0x31/0x50 [ 5.425764] entry_SYSCALL_64_after_hwframe+0x61/0xc6 [ 5.426065] [ 5.426157] The buggy address belongs to the object at ffff88800e312200 [ 5.426157] which belongs to the cache kmalloc-128 of size 128 [ 5.426955] The buggy address is located 42 bytes to the right of [ 5.426955] 128-byte region [ffff88800e312200, ffff88800e312280) [ 5.427688] The buggy address belongs to the page: [ 5.427992] page:000000009875fabc refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xe312 [ 5.428562] flags: 0x100000000000200(slab) [ 5.428812] raw: 0100000000000200 dead000000000100 dead000000000122 ffff888007843680 [ 5.429325] raw: 0000000000000000 0000000000100010 00000001ffffffff ffff88800e312401 [ 5.429875] page dumped because: kasan: bad access detected [ 5.430214] page->mem_cgroup:ffff88800e312401 [ 5.430471] [ 5.430564] Memory state around the buggy address: [ 5.430846] ffff88800e312180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 5.431267] ffff88800e312200: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fc [ 5.431705] >ffff88800e312280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 5.432123] ^ [ 5.432391] ffff88800e312300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fc [ 5.432810] ffff88800e312380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 5.433229] ================================================================== [ 5.433648] Disabling lock debugging due to kernel taint Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Kyle Zeng Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/sch_cbq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 9a3dff02b7a2..3da5eb313c24 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -231,6 +231,8 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) result = tcf_classify(skb, fl, &res, true); if (!fl || result < 0) goto fallback; + if (result == TC_ACT_SHOT) + return NULL; cl = (void *)res.class; if (!cl) { @@ -251,8 +253,6 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; fallthrough; - case TC_ACT_SHOT: - return NULL; case TC_ACT_RECLASSIFY: return cbq_reclassify(skb, cl); } From ba5d2790974535401155ae89e6077b766a64f001 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 30 Dec 2022 13:24:37 +0100 Subject: [PATCH 0832/4345] netfilter: ipset: fix hash:net,port,net hang with /0 subnet MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit a31d47be64b9b74f8cfedffe03e0a8a1f9e51f23 ] The hash:net,port,net set type supports /0 subnets. However, the patch commit 5f7b51bf09baca8e titled "netfilter: ipset: Limit the maximal range of consecutive elements to add/delete" did not take into account it and resulted in an endless loop. The bug is actually older but the patch 5f7b51bf09baca8e brings it out earlier. Handle /0 subnets properly in hash:net,port,net set types. Fixes: 5f7b51bf09ba ("netfilter: ipset: Limit the maximal range of consecutive elements to add/delete") Reported-by: Марк Коренберг Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/ipset/ip_set_hash_netportnet.c | 40 ++++++++++---------- 1 file changed, 21 insertions(+), 19 deletions(-) diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 6446f4fccc72..144346faffc1 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -172,17 +172,26 @@ hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } +static u32 +hash_netportnet4_range_to_cidr(u32 from, u32 to, u8 *cidr) +{ + if (from == 0 && to == UINT_MAX) { + *cidr = 0; + return to; + } + return ip_set_range_to_cidr(from, to, cidr); +} + static int hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_netportnet4 *h = set->data; + struct hash_netportnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2, ipn; - u64 n = 0, m = 0; + u32 ip2_from = 0, ip2_to = 0, ip2, i = 0; bool with_ports = false; int ret; @@ -284,19 +293,6 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); - n++; - } while (ipn++ < ip_to); - ipn = ip2_from; - do { - ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); - m++; - } while (ipn++ < ip2_to); - - if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); @@ -309,13 +305,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], do { e.ip[0] = htonl(ip); - ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); + ip = hash_netportnet4_range_to_cidr(ip, ip_to, &e.cidr[0]); for (; p <= port_to; p++) { e.port = htons(p); do { + i++; e.ip[1] = htonl(ip2); - ip2 = ip_set_range_to_cidr(ip2, ip2_to, - &e.cidr[1]); + if (i > IPSET_MAX_RANGE) { + hash_netportnet4_data_next(&h->next, + &e); + return -ERANGE; + } + ip2 = hash_netportnet4_range_to_cidr(ip2, + ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; From ee756980e491c829ba0495bb420b7224a9ee26b2 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 30 Dec 2022 13:24:38 +0100 Subject: [PATCH 0833/4345] netfilter: ipset: Rework long task execution when adding/deleting entries [ Upstream commit 5e29dc36bd5e2166b834ceb19990d9e68a734d7d ] When adding/deleting large number of elements in one step in ipset, it can take a reasonable amount of time and can result in soft lockup errors. The patch 5f7b51bf09ba ("netfilter: ipset: Limit the maximal range of consecutive elements to add/delete") tried to fix it by limiting the max elements to process at all. However it was not enough, it is still possible that we get hung tasks. Lowering the limit is not reasonable, so the approach in this patch is as follows: rely on the method used at resizing sets and save the state when we reach a smaller internal batch limit, unlock/lock and proceed from the saved state. Thus we can avoid long continuous tasks and at the same time removed the limit to add/delete large number of elements in one step. The nfnl mutex is held during the whole operation which prevents one to issue other ipset commands in parallel. Fixes: 5f7b51bf09ba ("netfilter: ipset: Limit the maximal range of consecutive elements to add/delete") Reported-by: syzbot+9204e7399656300bf271@syzkaller.appspotmail.com Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/linux/netfilter/ipset/ip_set.h | 2 +- net/netfilter/ipset/ip_set_core.c | 7 ++++--- net/netfilter/ipset/ip_set_hash_ip.c | 14 ++++++------- net/netfilter/ipset/ip_set_hash_ipmark.c | 13 ++++++------ net/netfilter/ipset/ip_set_hash_ipport.c | 13 ++++++------ net/netfilter/ipset/ip_set_hash_ipportip.c | 13 ++++++------ net/netfilter/ipset/ip_set_hash_ipportnet.c | 13 +++++++----- net/netfilter/ipset/ip_set_hash_net.c | 17 +++++++-------- net/netfilter/ipset/ip_set_hash_netiface.c | 15 ++++++-------- net/netfilter/ipset/ip_set_hash_netnet.c | 23 +++++++-------------- net/netfilter/ipset/ip_set_hash_netport.c | 19 +++++++---------- 11 files changed, 68 insertions(+), 81 deletions(-) diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 53c9a17ecb3e..62f7e7e257c1 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -199,7 +199,7 @@ struct ip_set_region { }; /* Max range where every element is added/deleted in one step */ -#define IPSET_MAX_RANGE (1<<20) +#define IPSET_MAX_RANGE (1<<14) /* The core set type structure */ struct ip_set_type { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index c17a7dda0163..1bf6ab83644b 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1708,9 +1708,10 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); ip_set_unlock(set); retried = true; - } while (ret == -EAGAIN && - set->variant->resize && - (ret = set->variant->resize(set, retried)) == 0); + } while (ret == -ERANGE || + (ret == -EAGAIN && + set->variant->resize && + (ret = set->variant->resize(set, retried)) == 0)); if (!ret || (ret == -IPSET_ERR_EXIST && eexist)) return 0; diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index d7a81b2250e7..8720dc3bb689 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -97,11 +97,11 @@ static int hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ip4 *h = set->data; + struct hash_ip4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ip4_elem e = { 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0, hosts; + u32 ip = 0, ip_to = 0, hosts, i = 0; int ret = 0; if (tb[IPSET_ATTR_LINENO]) @@ -146,14 +146,14 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); - /* 64bit division is not allowed on 32bit */ - if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) - return -ERANGE; - if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to;) { + for (; ip <= ip_to; i++) { e.ip = htonl(ip); + if (i > IPSET_MAX_RANGE) { + hash_ip4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index eefce34a34f0..cbb05cb188f2 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -96,11 +96,11 @@ static int hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ipmark4 *h = set->data; + struct hash_ipmark4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipmark4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip, ip_to = 0; + u32 ip, ip_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -147,13 +147,14 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ip_set_mask_from_to(ip, ip_to, cidr); } - if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE) - return -ERANGE; - if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to; ip++) { + for (; ip <= ip_to; ip++, i++) { e.ip = htonl(ip); + if (i > IPSET_MAX_RANGE) { + hash_ipmark4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 4a54e9e8ae59..c560f7873eca 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -104,11 +104,11 @@ static int hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ipport4 *h = set->data; + struct hash_ipport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip, ip_to = 0, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to, i = 0; bool with_ports = false; int ret; @@ -172,17 +172,18 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } - if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; - if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; - for (; p <= port_to; p++) { + for (; p <= port_to; p++, i++) { e.ip = htonl(ip); e.port = htons(p); + if (i > IPSET_MAX_RANGE) { + hash_ipport4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 09737de5ecc3..b7eb8d1e77d9 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -107,11 +107,11 @@ static int hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ipportip4 *h = set->data; + struct hash_ipportip4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip, ip_to = 0, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to, i = 0; bool with_ports = false; int ret; @@ -179,17 +179,18 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } - if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; - if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; - for (; p <= port_to; p++) { + for (; p <= port_to; p++, i++) { e.ip = htonl(ip); e.port = htons(p); + if (i > IPSET_MAX_RANGE) { + hash_ipportip4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 02685371a682..16c5641ced53 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -159,12 +159,12 @@ static int hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_ipportnet4 *h = set->data; + struct hash_ipportnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2; + u32 ip2_from = 0, ip2_to = 0, ip2, i = 0; bool with_ports = false; u8 cidr; int ret; @@ -252,9 +252,6 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } - if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; - ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); @@ -281,9 +278,15 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], for (; p <= port_to; p++) { e.port = htons(p); do { + i++; e.ip2 = htonl(ip2); ip2 = ip_set_range_to_cidr(ip2, ip2_to, &cidr); e.cidr = cidr - 1; + if (i > IPSET_MAX_RANGE) { + hash_ipportnet4_data_next(&h->next, + &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 9d1beaacb973..5ab5873d1d16 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -135,11 +135,11 @@ static int hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_net4 *h = set->data; + struct hash_net4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0, ipn, n = 0; + u32 ip = 0, ip_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -187,19 +187,16 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); - n++; - } while (ipn++ < ip_to); - - if (n > IPSET_MAX_RANGE) - return -ERANGE; if (retried) ip = ntohl(h->next.ip); do { + i++; e.ip = htonl(ip); + if (i > IPSET_MAX_RANGE) { + hash_net4_data_next(&h->next, &e); + return -ERANGE; + } ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index c3ada9c63fa3..7ef240380a45 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -201,7 +201,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0, ipn, n = 0; + u32 ip = 0, ip_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -255,19 +255,16 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr); } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); - n++; - } while (ipn++ < ip_to); - - if (n > IPSET_MAX_RANGE) - return -ERANGE; if (retried) ip = ntohl(h->next.ip); do { + i++; e.ip = htonl(ip); + if (i > IPSET_MAX_RANGE) { + hash_netiface4_data_next(&h->next, &e); + return -ERANGE; + } ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index b1411bc91a40..15f4b0292f0d 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -162,13 +162,12 @@ static int hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_netnet4 *h = set->data; + struct hash_netnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0; - u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn; - u64 n = 0, m = 0; + u32 ip2 = 0, ip2_from = 0, ip2_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -244,19 +243,6 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); - n++; - } while (ipn++ < ip_to); - ipn = ip2_from; - do { - ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); - m++; - } while (ipn++ < ip2_to); - - if (n*m > IPSET_MAX_RANGE) - return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); @@ -269,7 +255,12 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.ip[0] = htonl(ip); ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); do { + i++; e.ip[1] = htonl(ip2); + if (i > IPSET_MAX_RANGE) { + hash_netnet4_data_next(&h->next, &e); + return -ERANGE; + } ip2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index d26d13528fe8..e73ba50afe96 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -153,12 +153,11 @@ static int hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { - const struct hash_netport4 *h = set->data; + struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn; - u64 n = 0; + u32 port, port_to, p = 0, ip = 0, ip_to = 0, i = 0; bool with_ports = false; u8 cidr; int ret; @@ -235,14 +234,6 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } - ipn = ip; - do { - ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr); - n++; - } while (ipn++ < ip_to); - - if (n*(port_to - port + 1) > IPSET_MAX_RANGE) - return -ERANGE; if (retried) { ip = ntohl(h->next.ip); @@ -254,8 +245,12 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], e.ip = htonl(ip); ip = ip_set_range_to_cidr(ip, ip_to, &cidr); e.cidr = cidr - 1; - for (; p <= port_to; p++) { + for (; p <= port_to; p++, i++) { e.port = htons(p); + if (i > IPSET_MAX_RANGE) { + hash_netport4_data_next(&h->next, &e); + return -ERANGE; + } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; From bc6a0993bf8f026d8b67fcee9f75e6619324b5bb Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Thu, 29 Dec 2022 13:09:00 +0400 Subject: [PATCH 0834/4345] perf tools: Fix resources leak in perf_data__open_dir() [ Upstream commit 0a6564ebd953c4590663c9a3c99a3ea9920ade6f ] In perf_data__open_dir(), opendir() opens the directory stream. Add missing closedir() to release it after use. Fixes: eb6176709b235b96 ("perf data: Add perf_data__open_dir_data function") Reviewed-by: Adrian Hunter Signed-off-by: Miaoqian Lin Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20221229090903.1402395-1-linmq006@gmail.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/data.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 48754083791d..29d32ba046b5 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -127,6 +127,7 @@ int perf_data__open_dir(struct perf_data *data) file->size = st.st_size; } + closedir(dir); if (!files) return -EINVAL; @@ -135,6 +136,7 @@ int perf_data__open_dir(struct perf_data *data) return 0; out_err: + closedir(dir); close_dir(files, nr); return ret; } From 2a9ee7c24b3260ac7e57b51bbe9f9813d8724fb9 Mon Sep 17 00:00:00 2001 From: Daniil Tatianin Date: Mon, 2 Jan 2023 12:53:35 +0300 Subject: [PATCH 0835/4345] drivers/net/bonding/bond_3ad: return when there's no aggregator [ Upstream commit 9c807965483f42df1d053b7436eedd6cf28ece6f ] Otherwise we would dereference a NULL aggregator pointer when calling __set_agg_ports_ready on the line below. Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Daniil Tatianin Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/bonding/bond_3ad.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index acb6ff0be5ff..320e5461853f 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1520,6 +1520,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) slave_err(bond->dev, port->slave->dev, "Port %d did not find a suitable aggregator\n", port->actor_port_number); + return; } } /* if all aggregator's ports are READY_N == TRUE, set ready=TRUE From 232ef345e5d76e5542f430a29658a85dbef07f0b Mon Sep 17 00:00:00 2001 From: Szymon Heidrich Date: Tue, 3 Jan 2023 10:17:09 +0100 Subject: [PATCH 0836/4345] usb: rndis_host: Secure rndis_query check against int overflow [ Upstream commit c7dd13805f8b8fc1ce3b6d40f6aff47e66b72ad2 ] Variables off and len typed as uint32 in rndis_query function are controlled by incoming RNDIS response message thus their value may be manipulated. Setting off to a unexpectetly large value will cause the sum with len and 8 to overflow and pass the implemented validation step. Consequently the response pointer will be referring to a location past the expected buffer boundaries allowing information leakage e.g. via RNDIS_OID_802_3_PERMANENT_ADDRESS OID. Fixes: ddda08624013 ("USB: rndis_host, various cleanups") Signed-off-by: Szymon Heidrich Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/usb/rndis_host.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index 1505fe3f87ed..1ff723e15d52 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -255,7 +255,8 @@ static int rndis_query(struct usbnet *dev, struct usb_interface *intf, off = le32_to_cpu(u.get_c->offset); len = le32_to_cpu(u.get_c->len); - if (unlikely((8 + off + len) > CONTROL_BUFFER_SIZE)) + if (unlikely((off > CONTROL_BUFFER_SIZE - 8) || + (len > CONTROL_BUFFER_SIZE - 8 - off))) goto response_error; if (*reply_len != -1 && len != *reply_len) From e5a05837445e48620636551d5de98ddd3939ad7f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 15 Nov 2022 16:15:18 +0300 Subject: [PATCH 0837/4345] drm/i915: unpin on error in intel_vgpu_shadow_mm_pin() [ Upstream commit 3792fc508c095abd84b10ceae12bd773e61fdc36 ] Call intel_vgpu_unpin_mm() on this error path. Fixes: 418741480809 ("drm/i915/gvt: Adding ppgtt to GVT GEM context after shadow pdps settled.") Signed-off-by: Dan Carpenter Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/Y3OQ5tgZIVxyQ/WV@kili Reviewed-by: Zhenyu Wang Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gvt/scheduler.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index aed2ef6466a2..2bb6203298bc 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -647,6 +647,7 @@ intel_vgpu_shadow_mm_pin(struct intel_vgpu_workload *workload) if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT || !workload->shadow_mm->ppgtt_mm.shadowed) { + intel_vgpu_unpin_mm(workload->shadow_mm); gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); return -EINVAL; } From 84b2cc7b36b7f6957d307fb3d01603f93cb2d655 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 4 Jan 2023 14:51:46 +0800 Subject: [PATCH 0838/4345] caif: fix memory leak in cfctrl_linkup_request() [ Upstream commit fe69230f05897b3de758427b574fc98025dfc907 ] When linktype is unknown or kzalloc failed in cfctrl_linkup_request(), pkt is not released. Add release process to error path. Fixes: b482cd2053e3 ("net-caif: add CAIF core protocol stack") Fixes: 8d545c8f958f ("caif: Disconnect without waiting for response") Signed-off-by: Zhengchao Shao Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230104065146.1153009-1-shaozhengchao@huawei.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/caif/cfctrl.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 2809cbd6b7f7..d8cb4b2a076b 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -269,11 +269,15 @@ int cfctrl_linkup_request(struct cflayer *layer, default: pr_warn("Request setup of bad link type = %d\n", param->linktype); + cfpkt_destroy(pkt); return -EINVAL; } req = kzalloc(sizeof(*req), GFP_KERNEL); - if (!req) + if (!req) { + cfpkt_destroy(pkt); return -ENOMEM; + } + req->client_layer = user_layer; req->cmd = CFCTRL_CMD_LINK_SETUP; req->param = *param; From 6df376e245699666f9e9c2f37d6b9908dc9b925e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 21 Dec 2022 17:45:51 +0100 Subject: [PATCH 0839/4345] udf: Fix extension of the last extent in the file [ Upstream commit 83c7423d1eb6806d13c521d1002cc1a012111719 ] When extending the last extent in the file within the last block, we wrongly computed the length of the last extent. This is mostly a cosmetical problem since the extent does not contain any data and the length will be fixed up by following operations but still. Fixes: 1f3868f06855 ("udf: Fix extending file within last block") Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/udf/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index e94a18bb7f99..2132bfab67f3 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -599,7 +599,7 @@ static void udf_do_extend_final_block(struct inode *inode, */ if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK)) return; - added_bytes = (last_ext->extLength & UDF_EXTENT_LENGTH_MASK) - new_elen; + added_bytes = new_elen - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); last_ext->extLength += added_bytes; UDF_I(inode)->i_lenExtents += added_bytes; From 3f257a98e54cfbbd9921eb38bcbe047a9745a203 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 13 Dec 2022 13:32:46 +0100 Subject: [PATCH 0840/4345] ASoC: Intel: bytcr_rt5640: Add quirk for the Advantech MICA-071 tablet [ Upstream commit a1dec9d70b6ad97087b60b81d2492134a84208c6 ] The Advantech MICA-071 tablet deviates from the defaults for a non CR Bay Trail based tablet in several ways: 1. It uses an analog MIC on IN3 rather then using DMIC1 2. It only has 1 speaker 3. It needs the OVCD current threshold to be set to 1500uA instead of the default 2000uA to reliable differentiate between headphones vs headsets Add a quirk with these settings for this tablet. Signed-off-by: Hans de Goede Acked-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20221213123246.11226-1-hdegoede@redhat.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/intel/boards/bytcr_rt5640.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 3020a993f6ef..8a99cb6dfcd6 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -430,6 +430,21 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { + /* Advantech MICA-071 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Advantech"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "MICA-071"), + }, + /* OVCD Th = 1500uA to reliable detect head-phones vs -set */ + .driver_data = (void *)(BYT_RT5640_IN3_MAP | + BYT_RT5640_JD_SRC_JD2_IN4N | + BYT_RT5640_OVCD_TH_1500UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_MCLK_EN), + }, { .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ARCHOS"), From f13301a69ababa6c2236fb4f0393b7e914e7e1e0 Mon Sep 17 00:00:00 2001 From: Yanjun Zhang Date: Thu, 22 Dec 2022 09:57:21 +0800 Subject: [PATCH 0841/4345] nvme: fix multipath crash caused by flush request when blktrace is enabled [ Upstream commit 3659fb5ac29a5e6102bebe494ac789fd47fb78f4 ] The flush request initialized by blk_kick_flush has NULL bio, and it may be dealt with nvme_end_req during io completion. When blktrace is enabled, nvme_trace_bio_complete with multipath activated trying to access NULL pointer bio from flush request results in the following crash: [ 2517.831677] BUG: kernel NULL pointer dereference, address: 000000000000001a [ 2517.835213] #PF: supervisor read access in kernel mode [ 2517.838724] #PF: error_code(0x0000) - not-present page [ 2517.842222] PGD 7b2d51067 P4D 0 [ 2517.845684] Oops: 0000 [#1] SMP NOPTI [ 2517.849125] CPU: 2 PID: 732 Comm: kworker/2:1H Kdump: loaded Tainted: G S 5.15.67-0.cl9.x86_64 #1 [ 2517.852723] Hardware name: XFUSION 2288H V6/BC13MBSBC, BIOS 1.13 07/27/2022 [ 2517.856358] Workqueue: nvme_tcp_wq nvme_tcp_io_work [nvme_tcp] [ 2517.859993] RIP: 0010:blk_add_trace_bio_complete+0x6/0x30 [ 2517.863628] Code: 1f 44 00 00 48 8b 46 08 31 c9 ba 04 00 10 00 48 8b 80 50 03 00 00 48 8b 78 50 e9 e5 fe ff ff 0f 1f 44 00 00 41 54 49 89 f4 55 <0f> b6 7a 1a 48 89 d5 e8 3e 1c 2b 00 48 89 ee 4c 89 e7 5d 89 c1 ba [ 2517.871269] RSP: 0018:ff7f6a008d9dbcd0 EFLAGS: 00010286 [ 2517.875081] RAX: ff3d5b4be00b1d50 RBX: 0000000002040002 RCX: ff3d5b0a270f2000 [ 2517.878966] RDX: 0000000000000000 RSI: ff3d5b0b021fb9f8 RDI: 0000000000000000 [ 2517.882849] RBP: ff3d5b0b96a6fa00 R08: 0000000000000001 R09: 0000000000000000 [ 2517.886718] R10: 000000000000000c R11: 000000000000000c R12: ff3d5b0b021fb9f8 [ 2517.890575] R13: 0000000002000000 R14: ff3d5b0b021fb1b0 R15: 0000000000000018 [ 2517.894434] FS: 0000000000000000(0000) GS:ff3d5b42bfc80000(0000) knlGS:0000000000000000 [ 2517.898299] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 2517.902157] CR2: 000000000000001a CR3: 00000004f023e005 CR4: 0000000000771ee0 [ 2517.906053] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 2517.909930] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 2517.913761] PKRU: 55555554 [ 2517.917558] Call Trace: [ 2517.921294] [ 2517.924982] nvme_complete_rq+0x1c3/0x1e0 [nvme_core] [ 2517.928715] nvme_tcp_recv_pdu+0x4d7/0x540 [nvme_tcp] [ 2517.932442] nvme_tcp_recv_skb+0x4f/0x240 [nvme_tcp] [ 2517.936137] ? nvme_tcp_recv_pdu+0x540/0x540 [nvme_tcp] [ 2517.939830] tcp_read_sock+0x9c/0x260 [ 2517.943486] nvme_tcp_try_recv+0x65/0xa0 [nvme_tcp] [ 2517.947173] nvme_tcp_io_work+0x64/0x90 [nvme_tcp] [ 2517.950834] process_one_work+0x1e8/0x390 [ 2517.954473] worker_thread+0x53/0x3c0 [ 2517.958069] ? process_one_work+0x390/0x390 [ 2517.961655] kthread+0x10c/0x130 [ 2517.965211] ? set_kthread_struct+0x40/0x40 [ 2517.968760] ret_from_fork+0x1f/0x30 [ 2517.972285] To avoid this situation, add a NULL check for req->bio before calling trace_block_bio_complete. Signed-off-by: Yanjun Zhang Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 86336496c65c..c3e4d9b6f9c0 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -749,7 +749,7 @@ static inline void nvme_trace_bio_complete(struct request *req, { struct nvme_ns *ns = req->q->queuedata; - if (req->cmd_flags & REQ_NVME_MPATH) + if ((req->cmd_flags & REQ_NVME_MPATH) && req->bio) trace_block_bio_complete(ns->head->disk->queue, req->bio); } From 67e39c4f4cb318cfbbf8982ab016c649ed97edaf Mon Sep 17 00:00:00 2001 From: Rodrigo Branco Date: Tue, 3 Jan 2023 14:17:51 -0600 Subject: [PATCH 0842/4345] x86/bugs: Flush IBP in ib_prctl_set() commit a664ec9158eeddd75121d39c9a0758016097fa96 upstream. We missed the window between the TIF flag update and the next reschedule. Signed-off-by: Rodrigo Branco Reviewed-by: Borislav Petkov (AMD) Signed-off-by: Ingo Molnar Cc: Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/bugs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index e2e22a5740a4..a2a087a797ae 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1896,6 +1896,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); task_update_spec_tif(task); + if (task == current) + indirect_branch_prediction_barrier(); break; default: return -ERANGE; From d0c46b55d6d9962f532a0fd8af38272e5ce15927 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 13 Dec 2022 13:08:26 -0500 Subject: [PATCH 0843/4345] nfsd: fix handling of readdir in v4root vs. mount upcall timeout commit cad853374d85fe678d721512cecfabd7636e51f3 upstream. If v4 READDIR operation hits a mountpoint and gets back an error, then it will include that entry in the reply and set RDATTR_ERROR for it to the error. That's fine for "normal" exported filesystems, but on the v4root, we need to be more careful to only expose the existence of dentries that lead to exports. If the mountd upcall times out while checking to see whether a mountpoint on the v4root is exported, then we have no recourse other than to fail the whole operation. Cc: Steve Dickson Link: https://bugzilla.kernel.org/show_bug.cgi?id=216777 Reported-by: JianHong Yin Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever Cc: Signed-off-by: Greg Kroah-Hartman --- fs/nfsd/nfs4xdr.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index cc605ee0b2fa..1e3410a9b03e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3405,6 +3405,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, case nfserr_noent: xdr_truncate_encode(xdr, start_offset); goto skip_entry; + case nfserr_jukebox: + /* + * The pseudoroot should only display dentries that lead to + * exports. If we get EJUKEBOX here, then we can't tell whether + * this entry should be included. Just fail the whole READDIR + * with NFS4ERR_DELAY in that case, and hope that the situation + * will resolve itself by the client's next attempt. + */ + if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT) + goto fail; + fallthrough; default: /* * If the client requested the RDATTR_ERROR attribute, From f64e56fb285a4684d287e5325e930e3fce312326 Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Mon, 2 Jan 2023 14:57:30 +0100 Subject: [PATCH 0844/4345] fbdev: matroxfb: G200eW: Increase max memory from 1 MB to 16 MB MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f685dd7a8025f2554f73748cfdb8143a21fb92c7 upstream. Commit 62d89a7d49af ("video: fbdev: matroxfb: set maxvram of vbG200eW to the same as vbG200 to avoid black screen") accidently decreases the maximum memory size for the Matrox G200eW (102b:0532) from 8 MB to 1 MB by missing one zero. This caused the driver initialization to fail with the messages below, as the minimum required VRAM size is 2 MB: [ 9.436420] matroxfb: Matrox MGA-G200eW (PCI) detected [ 9.444502] matroxfb: cannot determine memory size [ 9.449316] matroxfb: probe of 0000:0a:03.0 failed with error -1 So, add the missing 0 to make it the intended 16 MB. Successfully tested on the Dell PowerEdge R910/0KYD3D, BIOS 2.10.0 08/29/2013, that the warning is gone. While at it, add a leading 0 to the maxdisplayable entry, so it’s aligned properly. The value could probably also be increased from 8 MB to 16 MB, as the G200 uses the same values, but I have not checked any datasheet. Note, matroxfb is obsolete and superseded by the maintained DRM driver mga200, which is used by default on most systems where both drivers are available. Therefore, on most systems it was only a cosmetic issue. Fixes: 62d89a7d49af ("video: fbdev: matroxfb: set maxvram of vbG200eW to the same as vbG200 to avoid black screen") Link: https://lore.kernel.org/linux-fbdev/972999d3-b75d-5680-fcef-6e6905c52ac5@suse.de/T/#mb6953a9995ebd18acc8552f99d6db39787aec775 Cc: it+linux-fbdev@molgen.mpg.de Cc: Z. Liu Cc: Rich Felker Cc: stable@vger.kernel.org Signed-off-by: Paul Menzel Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/matrox/matroxfb_base.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/matrox/matroxfb_base.c b/drivers/video/fbdev/matrox/matroxfb_base.c index daaa99818d3b..566f74832bc8 100644 --- a/drivers/video/fbdev/matrox/matroxfb_base.c +++ b/drivers/video/fbdev/matrox/matroxfb_base.c @@ -1377,8 +1377,8 @@ static struct video_board vbG200 = { .lowlevel = &matrox_G100 }; static struct video_board vbG200eW = { - .maxvram = 0x100000, - .maxdisplayable = 0x800000, + .maxvram = 0x1000000, + .maxdisplayable = 0x0800000, .accelID = FB_ACCEL_MATROX_MGAG200, .lowlevel = &matrox_G100 }; From bc847857fbd8973b7e106b9abd920e409a051aae Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Thu, 29 Dec 2022 17:05:45 +0000 Subject: [PATCH 0845/4345] riscv: uaccess: fix type of 0 variable on error in get_user() commit b9b916aee6715cd7f3318af6dc360c4729417b94 upstream. If the get_user(x, ptr) has x as a pointer, then the setting of (x) = 0 is going to produce the following sparse warning, so fix this by forcing the type of 'x' when access_ok() fails. fs/aio.c:2073:21: warning: Using plain integer as NULL pointer Signed-off-by: Ben Dooks Reviewed-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20221229170545.718264-1-ben-linux@fluff.org Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index f944062c9d99..66af6abfe8af 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -216,7 +216,7 @@ do { \ might_fault(); \ access_ok(__p, sizeof(*__p)) ? \ __get_user((x), __p) : \ - ((x) = 0, -EFAULT); \ + ((x) = (__force __typeof__(x))0, -EFAULT); \ }) #define __put_user_asm(insn, x, ptr, err) \ From bb7c7b2c89d2feb347b6f9bffc1c75987adb1048 Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Mon, 19 Dec 2022 22:03:56 +0800 Subject: [PATCH 0846/4345] drm/i915/gvt: fix gvt debugfs destroy commit c4b850d1f448a901fbf4f7f36dec38c84009b489 upstream. When gvt debug fs is destroyed, need to have a sane check if drm minor's debugfs root is still available or not, otherwise in case like device remove through unbinding, drm minor's debugfs directory has already been removed, then intel_gvt_debugfs_clean() would act upon dangling pointer like below oops. i915 0000:00:02.0: Direct firmware load for i915/gvt/vid_0x8086_did_0x1926_rid_0x0a.golden_hw_state failed with error -2 i915 0000:00:02.0: MDEV: Registered Console: switching to colour dummy device 80x25 i915 0000:00:02.0: MDEV: Unregistering BUG: kernel NULL pointer dereference, address: 00000000000000a0 PGD 0 P4D 0 Oops: 0002 [#1] PREEMPT SMP PTI CPU: 2 PID: 2486 Comm: gfx-unbind.sh Tainted: G I 6.1.0-rc8+ #15 Hardware name: Dell Inc. XPS 13 9350/0JXC1H, BIOS 1.13.0 02/10/2020 RIP: 0010:down_write+0x1f/0x90 Code: 1d ff ff 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 53 48 89 fb e8 62 c0 ff ff bf 01 00 00 00 e8 28 5e 31 ff 31 c0 ba 01 00 00 00 48 0f b1 13 75 33 65 48 8b 04 25 c0 bd 01 00 48 89 43 08 bf 01 RSP: 0018:ffff9eb3036ffcc8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 00000000000000a0 RCX: ffffff8100000000 RDX: 0000000000000001 RSI: 0000000000000064 RDI: ffffffffa48787a8 RBP: ffff9eb3036ffd30 R08: ffffeb1fc45a0608 R09: ffffeb1fc45a05c0 R10: 0000000000000002 R11: 0000000000000000 R12: 0000000000000000 R13: ffff91acc33fa328 R14: ffff91acc033f080 R15: ffff91acced533e0 FS: 00007f6947bba740(0000) GS:ffff91ae36d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000a0 CR3: 00000001133a2002 CR4: 00000000003706e0 Call Trace: simple_recursive_removal+0x9f/0x2a0 ? start_creating.part.0+0x120/0x120 ? _raw_spin_lock+0x13/0x40 debugfs_remove+0x40/0x60 intel_gvt_debugfs_clean+0x15/0x30 [kvmgt] intel_gvt_clean_device+0x49/0xe0 [kvmgt] intel_gvt_driver_remove+0x2f/0xb0 i915_driver_remove+0xa4/0xf0 i915_pci_remove+0x1a/0x30 pci_device_remove+0x33/0xa0 device_release_driver_internal+0x1b2/0x230 unbind_store+0xe0/0x110 kernfs_fop_write_iter+0x11b/0x1f0 vfs_write+0x203/0x3d0 ksys_write+0x63/0xe0 do_syscall_64+0x37/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f6947cb5190 Code: 40 00 48 8b 15 71 9c 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 80 3d 51 24 0e 00 00 74 17 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 48 89 RSP: 002b:00007ffcbac45a28 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f6947cb5190 RDX: 000000000000000d RSI: 0000555e35c866a0 RDI: 0000000000000001 RBP: 0000555e35c866a0 R08: 0000000000000002 R09: 0000555e358cb97c R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000001 R13: 000000000000000d R14: 0000000000000000 R15: 0000555e358cb8e0 Modules linked in: kvmgt CR2: 00000000000000a0 ---[ end trace 0000000000000000 ]--- Cc: Wang, Zhi Cc: He, Yu Cc: stable@vger.kernel.org Reviewed-by: Zhi Wang Fixes: bc7b0be316ae ("drm/i915/gvt: Add basic debugfs infrastructure") Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20221219140357.769557-1-zhenyuw@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gvt/debugfs.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c index 9f1c209d9251..d7df27feee8c 100644 --- a/drivers/gpu/drm/i915/gvt/debugfs.c +++ b/drivers/gpu/drm/i915/gvt/debugfs.c @@ -199,6 +199,10 @@ void intel_gvt_debugfs_init(struct intel_gvt *gvt) */ void intel_gvt_debugfs_clean(struct intel_gvt *gvt) { - debugfs_remove_recursive(gvt->debugfs_root); - gvt->debugfs_root = NULL; + struct drm_minor *minor = gvt->gt->i915->drm.primary; + + if (minor->debugfs_root) { + debugfs_remove_recursive(gvt->debugfs_root); + gvt->debugfs_root = NULL; + } } From af90f8b36d78544433a48a3eda6a5faeafacd0a1 Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Mon, 19 Dec 2022 22:03:57 +0800 Subject: [PATCH 0847/4345] drm/i915/gvt: fix vgpu debugfs clean in remove commit 704f3384f322b40ba24d958473edfb1c9750c8fd upstream. Check carefully on root debugfs available when destroying vgpu, e.g in remove case drm minor's debugfs root might already be destroyed, which led to kernel oops like below. Console: switching to colour dummy device 80x25 i915 0000:00:02.0: MDEV: Unregistering intel_vgpu_mdev b1338b2d-a709-4c23-b766-cc436c36cdf0: Removing from iommu group 14 BUG: kernel NULL pointer dereference, address: 0000000000000150 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP CPU: 3 PID: 1046 Comm: driverctl Not tainted 6.1.0-rc2+ #6 Hardware name: HP HP ProDesk 600 G3 MT/829D, BIOS P02 Ver. 02.44 09/13/2022 RIP: 0010:__lock_acquire+0x5e2/0x1f90 Code: 87 ad 09 00 00 39 05 e1 1e cc 02 0f 82 f1 09 00 00 ba 01 00 00 00 48 83 c4 48 89 d0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 45 31 ff <48> 81 3f 60 9e c2 b6 45 0f 45 f8 83 fe 01 0f 87 55 fa ff ff 89 f0 RSP: 0018:ffff9f770274f948 EFLAGS: 00010046 RAX: 0000000000000003 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000150 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: ffff8895d1173300 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000150 R14: 0000000000000000 R15: 0000000000000000 FS: 00007fc9b2ba0740(0000) GS:ffff889cdfcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000150 CR3: 000000010fd93005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: lock_acquire+0xbf/0x2b0 ? simple_recursive_removal+0xa5/0x2b0 ? lock_release+0x13d/0x2d0 down_write+0x2a/0xd0 ? simple_recursive_removal+0xa5/0x2b0 simple_recursive_removal+0xa5/0x2b0 ? start_creating.part.0+0x110/0x110 ? _raw_spin_unlock+0x29/0x40 debugfs_remove+0x40/0x60 intel_gvt_debugfs_remove_vgpu+0x15/0x30 [kvmgt] intel_gvt_destroy_vgpu+0x60/0x100 [kvmgt] intel_vgpu_release_dev+0xe/0x20 [kvmgt] device_release+0x30/0x80 kobject_put+0x79/0x1b0 device_release_driver_internal+0x1b8/0x230 bus_remove_device+0xec/0x160 device_del+0x189/0x400 ? up_write+0x9c/0x1b0 ? mdev_device_remove_common+0x60/0x60 [mdev] mdev_device_remove_common+0x22/0x60 [mdev] mdev_device_remove_cb+0x17/0x20 [mdev] device_for_each_child+0x56/0x80 mdev_unregister_parent+0x5a/0x81 [mdev] intel_gvt_clean_device+0x2d/0xe0 [kvmgt] intel_gvt_driver_remove+0x2e/0xb0 [i915] i915_driver_remove+0xac/0x100 [i915] i915_pci_remove+0x1a/0x30 [i915] pci_device_remove+0x31/0xa0 device_release_driver_internal+0x1b8/0x230 unbind_store+0xd8/0x100 kernfs_fop_write_iter+0x156/0x210 vfs_write+0x236/0x4a0 ksys_write+0x61/0xd0 do_syscall_64+0x55/0x80 ? find_held_lock+0x2b/0x80 ? lock_release+0x13d/0x2d0 ? up_read+0x17/0x20 ? lock_is_held_type+0xe3/0x140 ? asm_exc_page_fault+0x22/0x30 ? lockdep_hardirqs_on+0x7d/0x100 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fc9b2c9e0c4 Code: 15 71 7d 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 80 3d 3d 05 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 48 89 54 24 18 48 RSP: 002b:00007ffec29c81c8 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007fc9b2c9e0c4 RDX: 000000000000000d RSI: 0000559f8b5f48a0 RDI: 0000000000000001 RBP: 0000559f8b5f48a0 R08: 0000559f8b5f3540 R09: 00007fc9b2d76d30 R10: 0000000000000000 R11: 0000000000000202 R12: 000000000000000d R13: 00007fc9b2d77780 R14: 000000000000000d R15: 00007fc9b2d72a00 Modules linked in: sunrpc intel_rapl_msr intel_rapl_common intel_pmc_core_pltdrv intel_pmc_core intel_tcc_cooling x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel ee1004 igbvf rapl vfat fat intel_cstate intel_uncore pktcdvd i2c_i801 pcspkr wmi_bmof i2c_smbus acpi_pad vfio_pci vfio_pci_core vfio_virqfd zram fuse dm_multipath kvmgt mdev vfio_iommu_type1 vfio kvm irqbypass i915 nvme e1000e igb nvme_core crct10dif_pclmul crc32_pclmul crc32c_intel polyval_clmulni polyval_generic serio_raw ghash_clmulni_intel sha512_ssse3 dca drm_buddy intel_gtt video wmi drm_display_helper ttm CR2: 0000000000000150 ---[ end trace 0000000000000000 ]--- Cc: Wang Zhi Cc: He Yu Cc: Alex Williamson Cc: stable@vger.kernel.org Reviewed-by: Zhi Wang Tested-by: Yu He Fixes: bc7b0be316ae ("drm/i915/gvt: Add basic debugfs infrastructure") Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20221219140357.769557-2-zhenyuw@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gvt/debugfs.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c index d7df27feee8c..e08ed0e9f165 100644 --- a/drivers/gpu/drm/i915/gvt/debugfs.c +++ b/drivers/gpu/drm/i915/gvt/debugfs.c @@ -175,8 +175,13 @@ void intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu) */ void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu) { - debugfs_remove_recursive(vgpu->debugfs); - vgpu->debugfs = NULL; + struct intel_gvt *gvt = vgpu->gvt; + struct drm_minor *minor = gvt->gt->i915->drm.primary; + + if (minor->debugfs_root && gvt->debugfs_root) { + debugfs_remove_recursive(vgpu->debugfs); + vgpu->debugfs = NULL; + } } /** From a41d63f2047169ff05c3225ff6a8da5f0df141dc Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 1 Nov 2022 22:33:12 -0700 Subject: [PATCH 0848/4345] ext4: don't allow journal inode to have encrypt flag commit 105c78e12468413e426625831faa7db4284e1fec upstream. Mounting a filesystem whose journal inode has the encrypt flag causes a NULL dereference in fscrypt_limit_io_blocks() when the 'inlinecrypt' mount option is used. The problem is that when jbd2_journal_init_inode() calls bmap(), it eventually finds its way into ext4_iomap_begin(), which calls fscrypt_limit_io_blocks(). fscrypt_limit_io_blocks() requires that if the inode is encrypted, then its encryption key must already be set up. That's not the case here, since the journal inode is never "opened" like a normal file would be. Hence the crash. A reproducer is: mkfs.ext4 -F /dev/vdb debugfs -w /dev/vdb -R "set_inode_field <8> flags 0x80808" mount /dev/vdb /mnt -o inlinecrypt To fix this, make ext4 consider journal inodes with the encrypt flag to be invalid. (Note, maybe other flags should be rejected on the journal inode too. For now, this is just the minimal fix for the above issue.) I've marked this as fixing the commit that introduced the call to fscrypt_limit_io_blocks(), since that's what made an actual crash start being possible. But this fix could be applied to any version of ext4 that supports the encrypt feature. Reported-by: syzbot+ba9dac45bc76c490b7c3@syzkaller.appspotmail.com Fixes: 38ea50daa7a4 ("ext4: support direct I/O with fscrypt using blk-crypto") Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20221102053312.189962-1-ebiggers@kernel.org Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ced84ed4e592..935589579b8f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5262,7 +5262,7 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, jbd_debug(2, "Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); - if (!S_ISREG(journal_inode->i_mode)) { + if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); return NULL; From 434909edcae3eedf5c28f99daaaa05b5c2670ede Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Wed, 19 Jan 2022 15:15:22 +0500 Subject: [PATCH 0849/4345] selftests: set the BUILD variable to absolute path commit 5ad51ab618de5d05f4e692ebabeb6fe6289aaa57 upstream. The build of kselftests fails if relative path is specified through KBUILD_OUTPUT or O= method. BUILD variable is used to determine the path of the output objects. When make is run from other directories with relative paths, the exact path of the build objects is ambiguous and build fails. make[1]: Entering directory '/home/usama/repos/kernel/linux_mainline2/tools/testing/selftests/alsa' gcc mixer-test.c -L/usr/lib/x86_64-linux-gnu -lasound -o build/kselftest/alsa/mixer-test /usr/bin/ld: cannot open output file build/kselftest/alsa/mixer-test Set the BUILD variable to the absolute path of the output directory. Make the logic readable and easy to follow. Use spaces instead of tabs for indentation as if with tab indentation is considered recipe in make. Signed-off-by: Muhammad Usama Anjum Signed-off-by: Shuah Khan Signed-off-by: Tyler Hicks (Microsoft) Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/Makefile | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index d9c283503159..db1e24d7155f 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -103,19 +103,27 @@ ifdef building_out_of_srctree override LDFLAGS = endif -ifneq ($(O),) - BUILD := $(O)/kselftest +top_srcdir ?= ../../.. + +ifeq ("$(origin O)", "command line") + KBUILD_OUTPUT := $(O) +endif + +ifneq ($(KBUILD_OUTPUT),) + # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot + # expand a shell special character '~'. We use a somewhat tedious way here. + abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) + $(if $(abs_objtree),, \ + $(error failed to create output directory "$(KBUILD_OUTPUT)")) + # $(realpath ...) resolves symlinks + abs_objtree := $(realpath $(abs_objtree)) + BUILD := $(abs_objtree)/kselftest else - ifneq ($(KBUILD_OUTPUT),) - BUILD := $(KBUILD_OUTPUT)/kselftest - else - BUILD := $(shell pwd) - DEFAULT_INSTALL_HDR_PATH := 1 - endif + BUILD := $(CURDIR) + DEFAULT_INSTALL_HDR_PATH := 1 endif # Prepare for headers install -top_srcdir ?= ../../.. include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) export KSFT_KHDR_INSTALL_DONE := 1 From 1f881d9201f6e0a917004a14329f9ff3d0bfa1e5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 8 Nov 2021 18:35:04 -0800 Subject: [PATCH 0850/4345] hfs/hfsplus: use WARN_ON for sanity check commit 55d1cbbbb29e6656c662ee8f73ba1fc4777532eb upstream. gcc warns about a couple of instances in which a sanity check exists but the author wasn't sure how to react to it failing, which makes it look like a possible bug: fs/hfsplus/inode.c: In function 'hfsplus_cat_read_inode': fs/hfsplus/inode.c:503:37: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 503 | /* panic? */; | ^ fs/hfsplus/inode.c:524:37: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 524 | /* panic? */; | ^ fs/hfsplus/inode.c: In function 'hfsplus_cat_write_inode': fs/hfsplus/inode.c:582:37: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 582 | /* panic? */; | ^ fs/hfsplus/inode.c:608:37: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 608 | /* panic? */; | ^ fs/hfs/inode.c: In function 'hfs_write_inode': fs/hfs/inode.c:464:37: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 464 | /* panic? */; | ^ fs/hfs/inode.c:485:37: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 485 | /* panic? */; | ^ panic() is probably not the correct choice here, but a WARN_ON seems appropriate and avoids the compile-time warning. Link: https://lkml.kernel.org/r/20210927102149.1809384-1-arnd@kernel.org Link: https://lore.kernel.org/all/20210322223249.2632268-1-arnd@kernel.org/ Signed-off-by: Arnd Bergmann Reviewed-by: Christian Brauner Cc: Alexander Viro Cc: Christian Brauner Cc: Greg Kroah-Hartman Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/hfs/inode.c | 6 ++---- fs/hfsplus/inode.c | 12 ++++-------- 2 files changed, 6 insertions(+), 12 deletions(-) diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index e9b4249a4b01..844cfdca3684 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -462,8 +462,7 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) goto out; if (S_ISDIR(main_inode->i_mode)) { - if (fd.entrylength < sizeof(struct hfs_cat_dir)) - /* panic? */; + WARN_ON(fd.entrylength < sizeof(struct hfs_cat_dir)); hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_dir)); if (rec.type != HFS_CDR_DIR || @@ -483,8 +482,7 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); } else { - if (fd.entrylength < sizeof(struct hfs_cat_file)) - /* panic? */; + WARN_ON(fd.entrylength < sizeof(struct hfs_cat_file)); hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); if (rec.type != HFS_CDR_FIL || diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index fe825c41a2a0..c60d5ceb0d31 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -497,8 +497,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) if (type == HFSPLUS_FOLDER) { struct hfsplus_cat_folder *folder = &entry.folder; - if (fd->entrylength < sizeof(struct hfsplus_cat_folder)) - /* panic? */; + WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_folder)); hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_folder)); hfsplus_get_perms(inode, &folder->permissions, 1); @@ -518,8 +517,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) } else if (type == HFSPLUS_FILE) { struct hfsplus_cat_file *file = &entry.file; - if (fd->entrylength < sizeof(struct hfsplus_cat_file)) - /* panic? */; + WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_file)); hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_file)); @@ -576,8 +574,7 @@ int hfsplus_cat_write_inode(struct inode *inode) if (S_ISDIR(main_inode->i_mode)) { struct hfsplus_cat_folder *folder = &entry.folder; - if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) - /* panic? */; + WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_folder)); hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_folder)); /* simple node checks? */ @@ -602,8 +599,7 @@ int hfsplus_cat_write_inode(struct inode *inode) } else { struct hfsplus_cat_file *file = &entry.file; - if (fd.entrylength < sizeof(struct hfsplus_cat_file)) - /* panic? */; + WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_file)); hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_file)); hfsplus_inode_write_fork(inode, &file->data_fork); From be01f35efa876eb81cebab2cb0add068b7280ef4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 4 Jan 2023 11:06:28 -0800 Subject: [PATCH 0851/4345] hfs/hfsplus: avoid WARN_ON() for sanity check, use proper error handling commit cb7a95af78d29442b8294683eca4897544b8ef46 upstream. Commit 55d1cbbbb29e ("hfs/hfsplus: use WARN_ON for sanity check") fixed a build warning by turning a comment into a WARN_ON(), but it turns out that syzbot then complains because it can trigger said warning with a corrupted hfs image. The warning actually does warn about a bad situation, but we are much better off just handling it as the error it is. So rather than warn about us doing bad things, stop doing the bad things and return -EIO. While at it, also fix a memory leak that was introduced by an earlier fix for a similar syzbot warning situation, and add a check for one case that historically wasn't handled at all (ie neither comment nor subsequent WARN_ON). Reported-by: syzbot+7bb7cd3595533513a9e7@syzkaller.appspotmail.com Fixes: 55d1cbbbb29e ("hfs/hfsplus: use WARN_ON for sanity check") Fixes: 8d824e69d9f3 ("hfs: fix OOB Read in __hfs_brec_find") Link: https://lore.kernel.org/lkml/000000000000dbce4e05f170f289@google.com/ Tested-by: Michael Schmitz Cc: Arnd Bergmann Cc: Matthew Wilcox Cc: Viacheslav Dubeyko Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/hfs/inode.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 844cfdca3684..6fbde990e056 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -454,15 +454,16 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) /* panic? */ return -EIO; + res = -EIO; if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN) - return -EIO; + goto out; fd.search_key->cat = HFS_I(main_inode)->cat_key; if (hfs_brec_find(&fd)) - /* panic? */ goto out; if (S_ISDIR(main_inode->i_mode)) { - WARN_ON(fd.entrylength < sizeof(struct hfs_cat_dir)); + if (fd.entrylength < sizeof(struct hfs_cat_dir)) + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_dir)); if (rec.type != HFS_CDR_DIR || @@ -475,6 +476,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_dir)); } else if (HFS_IS_RSRC(inode)) { + if (fd.entrylength < sizeof(struct hfs_cat_file)) + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); hfs_inode_write_fork(inode, rec.file.RExtRec, @@ -482,7 +485,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); } else { - WARN_ON(fd.entrylength < sizeof(struct hfs_cat_file)); + if (fd.entrylength < sizeof(struct hfs_cat_file)) + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); if (rec.type != HFS_CDR_FIL || @@ -499,9 +503,10 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); } + res = 0; out: hfs_find_exit(&fd); - return 0; + return res; } static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, From da20f56a3532d7f407a6c7028d795381cdcff14e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Sep 2022 11:10:32 +0200 Subject: [PATCH 0852/4345] mbcache: Avoid nesting of cache->c_list_lock under bit locks commit 5fc4cbd9fde5d4630494fd6ffc884148fb618087 upstream. Commit 307af6c87937 ("mbcache: automatically delete entries from cache on freeing") started nesting cache->c_list_lock under the bit locks protecting hash buckets of the mbcache hash table in mb_cache_entry_create(). This causes problems for real-time kernels because there spinlocks are sleeping locks while bitlocks stay atomic. Luckily the nesting is easy to avoid by holding entry reference until the entry is added to the LRU list. This makes sure we cannot race with entry deletion. Cc: stable@kernel.org Fixes: 307af6c87937 ("mbcache: automatically delete entries from cache on freeing") Reported-by: Mike Galbraith Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20220908091032.10513-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/mbcache.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/fs/mbcache.c b/fs/mbcache.c index 7a12ae87c806..95b047256d09 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -90,8 +90,14 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, return -ENOMEM; INIT_LIST_HEAD(&entry->e_list); - /* Initial hash reference */ - atomic_set(&entry->e_refcnt, 1); + /* + * We create entry with two references. One reference is kept by the + * hash table, the other reference is used to protect us from + * mb_cache_entry_delete_or_get() until the entry is fully setup. This + * avoids nesting of cache->c_list_lock into hash table bit locks which + * is problematic for RT. + */ + atomic_set(&entry->e_refcnt, 2); entry->e_key = key; entry->e_value = value; entry->e_flags = 0; @@ -107,15 +113,12 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, } } hlist_bl_add_head(&entry->e_hash_list, head); - /* - * Add entry to LRU list before it can be found by - * mb_cache_entry_delete() to avoid races - */ + hlist_bl_unlock(head); spin_lock(&cache->c_list_lock); list_add_tail(&entry->e_list, &cache->c_list); cache->c_entry_count++; spin_unlock(&cache->c_list_lock); - hlist_bl_unlock(head); + mb_cache_entry_put(cache, entry); return 0; } From b57d7b1dcda15c7b9a4722405566c387a7047a40 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 20 Oct 2022 10:39:10 +0200 Subject: [PATCH 0853/4345] efi: random: combine bootloader provided RNG seed with RNG protocol output commit 196dff2712ca5a2e651977bb2fe6b05474111a83 upstream. Instead of blindly creating the EFI random seed configuration table if the RNG protocol is implemented and works, check whether such a EFI configuration table was provided by an earlier boot stage and if so, concatenate the existing and the new seeds, leaving it up to the core code to mix it in and credit it the way it sees fit. This can be used for, e.g., systemd-boot, to pass an additional seed to Linux in a way that can be consumed by the kernel very early. In that case, the following definitions should be used to pass the seed to the EFI stub: struct linux_efi_random_seed { u32 size; // of the 'seed' array in bytes u8 seed[]; }; The memory for the struct must be allocated as EFI_ACPI_RECLAIM_MEMORY pool memory, and the address of the struct in memory should be installed as a EFI configuration table using the following GUID: LINUX_EFI_RANDOM_SEED_TABLE_GUID 1ce1e5bc-7ceb-42f2-81e5-8aadf180f57b Note that doing so is safe even on kernels that were built without this patch applied, but the seed will simply be overwritten with a seed derived from the EFI RNG protocol, if available. The recommended seed size is 32 bytes, and seeds larger than 512 bytes are considered corrupted and ignored entirely. In order to preserve forward secrecy, seeds from previous bootloaders are memzero'd out, and in order to preserve memory, those older seeds are also freed from memory. Freeing from memory without first memzeroing is not safe to do, as it's possible that nothing else will ever overwrite those pages used by EFI. Reviewed-by: Jason A. Donenfeld [ardb: incorporate Jason's followup changes to extend the maximum seed size on the consumer end, memzero() it and drop a needless printk] Signed-off-by: Ard Biesheuvel Signed-off-by: Jason A. Donenfeld Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/efi/efi.c | 4 +-- drivers/firmware/efi/libstub/efistub.h | 2 ++ drivers/firmware/efi/libstub/random.c | 42 ++++++++++++++++++++++---- include/linux/efi.h | 2 -- 4 files changed, 40 insertions(+), 10 deletions(-) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 70be9c87fb67..ba03f5a4b30c 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -590,7 +590,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, seed = early_memremap(efi_rng_seed, sizeof(*seed)); if (seed != NULL) { - size = min(seed->size, EFI_RANDOM_SEED_SIZE); + size = min_t(u32, seed->size, SZ_1K); // sanity check early_memunmap(seed, sizeof(*seed)); } else { pr_err("Could not map UEFI random seed!\n"); @@ -599,8 +599,8 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, seed = early_memremap(efi_rng_seed, sizeof(*seed) + size); if (seed != NULL) { - pr_notice("seeding entropy pool\n"); add_bootloader_randomness(seed->bits, size); + memzero_explicit(seed->bits, size); early_memunmap(seed, sizeof(*seed) + size); } else { pr_err("Could not map UEFI random seed!\n"); diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 2d7abcd99de9..c5e0c6e99d20 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -767,6 +767,8 @@ efi_status_t efi_get_random_bytes(unsigned long size, u8 *out); efi_status_t efi_random_alloc(unsigned long size, unsigned long align, unsigned long *addr, unsigned long random_seed); +efi_status_t efi_random_get_seed(void); + efi_status_t check_platform_features(void); void *get_efi_config_table(efi_guid_t guid); diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c index 33ab56769595..f85d2c066877 100644 --- a/drivers/firmware/efi/libstub/random.c +++ b/drivers/firmware/efi/libstub/random.c @@ -67,27 +67,43 @@ efi_status_t efi_random_get_seed(void) efi_guid_t rng_proto = EFI_RNG_PROTOCOL_GUID; efi_guid_t rng_algo_raw = EFI_RNG_ALGORITHM_RAW; efi_guid_t rng_table_guid = LINUX_EFI_RANDOM_SEED_TABLE_GUID; + struct linux_efi_random_seed *prev_seed, *seed = NULL; + int prev_seed_size = 0, seed_size = EFI_RANDOM_SEED_SIZE; efi_rng_protocol_t *rng = NULL; - struct linux_efi_random_seed *seed = NULL; efi_status_t status; status = efi_bs_call(locate_protocol, &rng_proto, NULL, (void **)&rng); if (status != EFI_SUCCESS) return status; + /* + * Check whether a seed was provided by a prior boot stage. In that + * case, instead of overwriting it, let's create a new buffer that can + * hold both, and concatenate the existing and the new seeds. + * Note that we should read the seed size with caution, in case the + * table got corrupted in memory somehow. + */ + prev_seed = get_efi_config_table(LINUX_EFI_RANDOM_SEED_TABLE_GUID); + if (prev_seed && prev_seed->size <= 512U) { + prev_seed_size = prev_seed->size; + seed_size += prev_seed_size; + } + /* * Use EFI_ACPI_RECLAIM_MEMORY here so that it is guaranteed that the * allocation will survive a kexec reboot (although we refresh the seed * beforehand) */ status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY, - sizeof(*seed) + EFI_RANDOM_SEED_SIZE, + struct_size(seed, bits, seed_size), (void **)&seed); - if (status != EFI_SUCCESS) - return status; + if (status != EFI_SUCCESS) { + efi_warn("Failed to allocate memory for RNG seed.\n"); + goto err_warn; + } status = efi_call_proto(rng, get_rng, &rng_algo_raw, - EFI_RANDOM_SEED_SIZE, seed->bits); + EFI_RANDOM_SEED_SIZE, seed->bits); if (status == EFI_UNSUPPORTED) /* @@ -100,14 +116,28 @@ efi_status_t efi_random_get_seed(void) if (status != EFI_SUCCESS) goto err_freepool; - seed->size = EFI_RANDOM_SEED_SIZE; + seed->size = seed_size; + if (prev_seed_size) + memcpy(seed->bits + EFI_RANDOM_SEED_SIZE, prev_seed->bits, + prev_seed_size); + status = efi_bs_call(install_configuration_table, &rng_table_guid, seed); if (status != EFI_SUCCESS) goto err_freepool; + if (prev_seed_size) { + /* wipe and free the old seed if we managed to install the new one */ + memzero_explicit(prev_seed->bits, prev_seed_size); + efi_bs_call(free_pool, prev_seed); + } return EFI_SUCCESS; err_freepool: + memzero_explicit(seed, struct_size(seed, bits, seed_size)); efi_bs_call(free_pool, seed); + efi_warn("Failed to obtain seed from EFI_RNG_PROTOCOL\n"); +err_warn: + if (prev_seed) + efi_warn("Retaining bootloader-supplied seed only"); return status; } diff --git a/include/linux/efi.h b/include/linux/efi.h index 7feb70d32d95..084990390420 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1108,8 +1108,6 @@ void efi_check_for_embedded_firmwares(void); static inline void efi_check_for_embedded_firmwares(void) { } #endif -efi_status_t efi_random_get_seed(void); - void efi_retrieve_tpm2_eventlog(void); /* From 07b3672c4090d1e8147b1ae9c2546d8a8d8e13ae Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Tue, 10 Jan 2023 08:46:47 -0800 Subject: [PATCH 0854/4345] io_uring: Fix unsigned 'res' comparison with zero in io_fixup_rw_res() Smatch warning: io_fixup_rw_res() warn: unsigned 'res' is never less than zero. Change type of 'res' from unsigned to long. Fixes: d6b7efc722a2 ("io_uring/rw: fix error'ed retry return values") Signed-off-by: Harshit Mogalapalli Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 945faf036ad0..0c4d16afb9ef 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2702,7 +2702,7 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res) return false; } -static inline int io_fixup_rw_res(struct io_kiocb *req, unsigned res) +static inline int io_fixup_rw_res(struct io_kiocb *req, long res) { struct io_async_rw *io = req->async_data; From 5b700b9c0402b7040e6028536280600bba03182f Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 11 Dec 2022 19:50:20 +0100 Subject: [PATCH 0855/4345] parisc: Align parisc MADV_XXX constants with all other architectures commit 71bdea6f798b425bc0003780b13e3fdecb16a010 upstream. Adjust some MADV_XXX constants to be in sync what their values are on all other platforms. There is currently no reason to have an own numbering on parisc, but it requires workarounds in many userspace sources (e.g. glibc, qemu, ...) - which are often forgotten and thus introduce bugs and different behaviour on parisc. A wrapper avoids an ABI breakage for existing userspace applications by translating any old values to the new ones, so this change allows us to move over all programs to the new ABI over time. Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/include/uapi/asm/mman.h | 27 +++++++++++------------ arch/parisc/kernel/sys_parisc.c | 27 +++++++++++++++++++++++ arch/parisc/kernel/syscalls/syscall.tbl | 2 +- tools/arch/parisc/include/uapi/asm/mman.h | 12 +++++----- tools/perf/bench/bench.h | 12 ---------- 5 files changed, 47 insertions(+), 33 deletions(-) diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index ab78cba446ed..ef9b53b80b9d 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -49,28 +49,27 @@ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ +#define MADV_MERGEABLE 12 /* KSM may merge identical pages */ +#define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */ + +#define MADV_HUGEPAGE 14 /* Worth backing with hugepages */ +#define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */ + +#define MADV_DONTDUMP 16 /* Explicity exclude from the core dump, + overrides the coredump filter bits */ +#define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */ + +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ -#define MADV_MERGEABLE 65 /* KSM may merge identical pages */ -#define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */ - -#define MADV_HUGEPAGE 67 /* Worth backing with hugepages */ -#define MADV_NOHUGEPAGE 68 /* Not worth backing with hugepages */ - -#define MADV_DONTDUMP 69 /* Explicity exclude from the core dump, - overrides the coredump filter bits */ -#define MADV_DODUMP 70 /* Clear the MADV_NODUMP flag */ - -#define MADV_WIPEONFORK 71 /* Zero memory on fork, child only */ -#define MADV_KEEPONFORK 72 /* Undo MADV_WIPEONFORK */ - #define MADV_HWPOISON 100 /* poison a page for testing */ #define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */ /* compatibility flags */ #define MAP_FILE 0 -#define MAP_VARIABLE 0 #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 9549496f5523..40f881f729e4 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -444,3 +444,30 @@ asmlinkage long parisc_inotify_init1(int flags) flags = FIX_O_NONBLOCK(flags); return sys_inotify_init1(flags); } + +/* + * madvise() wrapper + * + * Up to kernel v6.1 parisc has different values than all other + * platforms for the MADV_xxx flags listed below. + * To keep binary compatibility with existing userspace programs + * translate the former values to the new values. + * + * XXX: Remove this wrapper in year 2025 (or later) + */ + +asmlinkage notrace long parisc_madvise(unsigned long start, size_t len_in, int behavior) +{ + switch (behavior) { + case 65: behavior = MADV_MERGEABLE; break; + case 66: behavior = MADV_UNMERGEABLE; break; + case 67: behavior = MADV_HUGEPAGE; break; + case 68: behavior = MADV_NOHUGEPAGE; break; + case 69: behavior = MADV_DONTDUMP; break; + case 70: behavior = MADV_DODUMP; break; + case 71: behavior = MADV_WIPEONFORK; break; + case 72: behavior = MADV_KEEPONFORK; break; + } + + return sys_madvise(start, len_in, behavior); +} diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index d526ebfa58e5..dfe9254ee74b 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -131,7 +131,7 @@ 116 common sysinfo sys_sysinfo compat_sys_sysinfo 117 common shutdown sys_shutdown 118 common fsync sys_fsync -119 common madvise sys_madvise +119 common madvise parisc_madvise 120 common clone sys_clone_wrapper 121 common setdomainname sys_setdomainname 122 common sendfile sys_sendfile compat_sys_sendfile diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h index 506c06a6536f..4cc88a642e10 100644 --- a/tools/arch/parisc/include/uapi/asm/mman.h +++ b/tools/arch/parisc/include/uapi/asm/mman.h @@ -1,20 +1,20 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H -#define MADV_DODUMP 70 +#define MADV_DODUMP 17 #define MADV_DOFORK 11 -#define MADV_DONTDUMP 69 +#define MADV_DONTDUMP 16 #define MADV_DONTFORK 10 #define MADV_DONTNEED 4 #define MADV_FREE 8 -#define MADV_HUGEPAGE 67 -#define MADV_MERGEABLE 65 -#define MADV_NOHUGEPAGE 68 +#define MADV_HUGEPAGE 14 +#define MADV_MERGEABLE 12 +#define MADV_NOHUGEPAGE 15 #define MADV_NORMAL 0 #define MADV_RANDOM 1 #define MADV_REMOVE 9 #define MADV_SEQUENTIAL 2 -#define MADV_UNMERGEABLE 66 +#define MADV_UNMERGEABLE 13 #define MADV_WILLNEED 3 #define MAP_ANONYMOUS 0x10 #define MAP_DENYWRITE 0x0800 diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index eac36afab2b3..9a56a44f87dd 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -10,25 +10,13 @@ extern struct timeval bench__start, bench__end, bench__runtime; * The madvise transparent hugepage constants were added in glibc * 2.13. For compatibility with older versions of glibc, define these * tokens if they are not already defined. - * - * PA-RISC uses different madvise values from other architectures and - * needs to be special-cased. */ -#ifdef __hppa__ -# ifndef MADV_HUGEPAGE -# define MADV_HUGEPAGE 67 -# endif -# ifndef MADV_NOHUGEPAGE -# define MADV_NOHUGEPAGE 68 -# endif -#else # ifndef MADV_HUGEPAGE # define MADV_HUGEPAGE 14 # endif # ifndef MADV_NOHUGEPAGE # define MADV_NOHUGEPAGE 15 # endif -#endif int bench_numa(int argc, const char **argv); int bench_sched_messaging(int argc, const char **argv); From d9ff5ad203b603164ea43de60bb3d5c5e8ce5792 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 6 Nov 2022 14:48:35 -0800 Subject: [PATCH 0856/4345] ext4: disable fast-commit of encrypted dir operations commit 0fbcb5251fc81b58969b272c4fb7374a7b922e3e upstream. fast-commit of create, link, and unlink operations in encrypted directories is completely broken because the unencrypted filenames are being written to the fast-commit journal instead of the encrypted filenames. These operations can't be replayed, as encryption keys aren't present at journal replay time. It is also an information leak. Until if/when we can get this working properly, make encrypted directory operations ineligible for fast-commit. Note that fast-commit operations on encrypted regular files continue to be allowed, as they seem to work. Fixes: aa75f4d3daae ("ext4: main fast-commit commit path") Cc: # v5.10+ Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20221106224841.279231-2-ebiggers@kernel.org Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/fast_commit.c | 40 ++++++++++++++++++++++--------------- fs/ext4/fast_commit.h | 1 + include/trace/events/ext4.h | 7 +++++-- 3 files changed, 30 insertions(+), 18 deletions(-) diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index eaa26477bceb..057b89f8c5a1 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -371,25 +371,33 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) struct __track_dentry_update_args *dentry_update = (struct __track_dentry_update_args *)arg; struct dentry *dentry = dentry_update->dentry; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct inode *dir = dentry->d_parent->d_inode; + struct super_block *sb = inode->i_sb; + struct ext4_sb_info *sbi = EXT4_SB(sb); mutex_unlock(&ei->i_fc_lock); + + if (IS_ENCRYPTED(dir)) { + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_ENCRYPTED_FILENAME); + mutex_lock(&ei->i_fc_lock); + return -EOPNOTSUPP; + } + node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } node->fcd_op = dentry_update->op; - node->fcd_parent = dentry->d_parent->d_inode->i_ino; + node->fcd_parent = dir->i_ino; node->fcd_ino = inode->i_ino; if (dentry->d_name.len > DNAME_INLINE_LEN) { node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS); if (!node->fcd_name.name) { kmem_cache_free(ext4_fc_dentry_cachep, node); - ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_NOMEM); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -2142,17 +2150,17 @@ void ext4_fc_init(struct super_block *sb, journal_t *journal) journal->j_fc_cleanup_callback = ext4_fc_cleanup; } -static const char *fc_ineligible_reasons[] = { - "Extended attributes changed", - "Cross rename", - "Journal flag changed", - "Insufficient memory", - "Swap boot", - "Resize", - "Dir renamed", - "Falloc range op", - "Data journalling", - "FC Commit Failed" +static const char * const fc_ineligible_reasons[] = { + [EXT4_FC_REASON_XATTR] = "Extended attributes changed", + [EXT4_FC_REASON_CROSS_RENAME] = "Cross rename", + [EXT4_FC_REASON_JOURNAL_FLAG_CHANGE] = "Journal flag changed", + [EXT4_FC_REASON_NOMEM] = "Insufficient memory", + [EXT4_FC_REASON_SWAP_BOOT] = "Swap boot", + [EXT4_FC_REASON_RESIZE] = "Resize", + [EXT4_FC_REASON_RENAME_DIR] = "Dir renamed", + [EXT4_FC_REASON_FALLOC_RANGE] = "Falloc range op", + [EXT4_FC_REASON_INODE_JOURNAL_DATA] = "Data journalling", + [EXT4_FC_REASON_ENCRYPTED_FILENAME] = "Encrypted filename", }; int ext4_fc_info_show(struct seq_file *seq, void *v) diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h index d8d0998a5c16..4a5f96a9c9d7 100644 --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -104,6 +104,7 @@ enum { EXT4_FC_REASON_FALLOC_RANGE, EXT4_FC_REASON_INODE_JOURNAL_DATA, EXT4_FC_COMMIT_FAILED, + EXT4_FC_REASON_ENCRYPTED_FILENAME, EXT4_FC_REASON_MAX }; diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 4973265655a7..1a91d5789df3 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -104,6 +104,7 @@ TRACE_DEFINE_ENUM(EXT4_FC_REASON_RESIZE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_RENAME_DIR); TRACE_DEFINE_ENUM(EXT4_FC_REASON_FALLOC_RANGE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_INODE_JOURNAL_DATA); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_ENCRYPTED_FILENAME); TRACE_DEFINE_ENUM(EXT4_FC_REASON_MAX); #define show_fc_reason(reason) \ @@ -116,7 +117,8 @@ TRACE_DEFINE_ENUM(EXT4_FC_REASON_MAX); { EXT4_FC_REASON_RESIZE, "RESIZE"}, \ { EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \ { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \ - { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"}) + { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"}, \ + { EXT4_FC_REASON_ENCRYPTED_FILENAME, "ENCRYPTED_FILENAME"}) TRACE_EVENT(ext4_other_inode_update_time, TP_PROTO(struct inode *inode, ino_t orig_ino), @@ -2940,7 +2942,7 @@ TRACE_EVENT(ext4_fc_stats, ), TP_printk("dev %d,%d fc ineligible reasons:\n" - "%s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u " + "%s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u" "num_commits:%lu, ineligible: %lu, numblks: %lu", MAJOR(__entry->dev), MINOR(__entry->dev), FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), @@ -2952,6 +2954,7 @@ TRACE_EVENT(ext4_fc_stats, FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA), + FC_REASON_NAME_STAT(EXT4_FC_REASON_ENCRYPTED_FILENAME), __entry->fc_commits, __entry->fc_ineligible_commits, __entry->fc_numblks) ); From 23ad034760dd38e12b0e0e1b28b9629f330810a1 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 6 Nov 2022 14:48:36 -0800 Subject: [PATCH 0857/4345] ext4: don't set up encryption key during jbd2 transaction commit 4c0d5778385cb3618ff26a561ce41de2b7d9de70 upstream. Commit a80f7fcf1867 ("ext4: fixup ext4_fc_track_* functions' signature") extended the scope of the transaction in ext4_unlink() too far, making it include the call to ext4_find_entry(). However, ext4_find_entry() can deadlock when called from within a transaction because it may need to set up the directory's encryption key. Fix this by restoring the transaction to its original scope. Reported-by: syzbot+1a748d0007eeac3ab079@syzkaller.appspotmail.com Fixes: a80f7fcf1867 ("ext4: fixup ext4_fc_track_* functions' signature") Cc: # v5.10+ Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20221106224841.279231-3-ebiggers@kernel.org Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ext4.h | 4 ++-- fs/ext4/fast_commit.c | 2 +- fs/ext4/namei.c | 44 +++++++++++++++++++++++-------------------- 3 files changed, 27 insertions(+), 23 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index fb9c9e1813bc..81dc61f1c557 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3486,8 +3486,8 @@ extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, extern int ext4_ci_compare(const struct inode *parent, const struct qstr *fname, const struct qstr *entry, bool quick); -extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name, - struct inode *inode); +extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name, + struct inode *inode, struct dentry *dentry); extern int __ext4_link(struct inode *dir, struct inode *inode, struct dentry *dentry); diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 057b89f8c5a1..be768ef1fd16 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1300,7 +1300,7 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl, return 0; } - ret = __ext4_unlink(NULL, old_parent, &entry, inode); + ret = __ext4_unlink(old_parent, &entry, inode, NULL); /* -ENOENT ok coz it might not exist anymore. */ if (ret == -ENOENT) ret = 0; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index ce4962bb62bc..7ec7c9c16a39 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3244,14 +3244,20 @@ end_rmdir: return retval; } -int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name, - struct inode *inode) +int __ext4_unlink(struct inode *dir, const struct qstr *d_name, + struct inode *inode, + struct dentry *dentry /* NULL during fast_commit recovery */) { int retval = -ENOENT; struct buffer_head *bh; struct ext4_dir_entry_2 *de; + handle_t *handle; int skip_remove_dentry = 0; + /* + * Keep this outside the transaction; it may have to set up the + * directory's encryption key, which isn't GFP_NOFS-safe. + */ bh = ext4_find_entry(dir, d_name, &de, NULL); if (IS_ERR(bh)) return PTR_ERR(bh); @@ -3268,7 +3274,14 @@ int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) skip_remove_dentry = 1; else - goto out; + goto out_bh; + } + + handle = ext4_journal_start(dir, EXT4_HT_DIR, + EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + goto out_bh; } if (IS_DIRSYNC(dir)) @@ -3277,12 +3290,12 @@ int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name if (!skip_remove_dentry) { retval = ext4_delete_entry(handle, dir, de, bh); if (retval) - goto out; + goto out_handle; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); retval = ext4_mark_inode_dirty(handle, dir); if (retval) - goto out; + goto out_handle; } else { retval = 0; } @@ -3295,15 +3308,17 @@ int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name ext4_orphan_add(handle, inode); inode->i_ctime = current_time(inode); retval = ext4_mark_inode_dirty(handle, inode); - -out: + if (dentry && !retval) + ext4_fc_track_unlink(handle, dentry); +out_handle: + ext4_journal_stop(handle); +out_bh: brelse(bh); return retval; } static int ext4_unlink(struct inode *dir, struct dentry *dentry) { - handle_t *handle; int retval; if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) @@ -3321,16 +3336,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (retval) goto out_trace; - handle = ext4_journal_start(dir, EXT4_HT_DIR, - EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) { - retval = PTR_ERR(handle); - goto out_trace; - } - - retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry)); - if (!retval) - ext4_fc_track_unlink(handle, dentry); + retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry), dentry); #ifdef CONFIG_UNICODE /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid @@ -3341,8 +3347,6 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (IS_CASEFOLDED(dir)) d_invalidate(dentry); #endif - if (handle) - ext4_journal_stop(handle); out_trace: trace_ext4_unlink_exit(dentry, retval); From 2ecf0819e441c074e18c543bcdb8a6f48cc98d3f Mon Sep 17 00:00:00 2001 From: Indan Zupancic Date: Thu, 5 May 2022 13:47:50 +0200 Subject: [PATCH 0858/4345] fsl_lpuart: Don't enable interrupts too early commit 401fb66a355eb0f22096cf26864324f8e63c7d78 upstream. If an irq is pending when devm_request_irq() is called, the irq handler will cause a NULL pointer access because initialisation is not done yet. Fixes: 9d7ee0e28da59 ("tty: serial: lpuart: avoid report NULL interrupt") Cc: stable Signed-off-by: Indan Zupancic Link: https://lore.kernel.org/r/20220505114750.45423-1-Indan.Zupancic@mep-info.com [5.10 did not have lpuart_global_reset or anything after uart_add_one_port(), so add the remove call in cleanup manually] Signed-off-by: Dominique Martinet Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 43aca5a2ef0f..223695947b65 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2586,6 +2586,7 @@ static int lpuart_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct lpuart_port *sport; struct resource *res; + irq_handler_t handler; int ret; sport = devm_kzalloc(&pdev->dev, sizeof(*sport), GFP_KERNEL); @@ -2658,17 +2659,12 @@ static int lpuart_probe(struct platform_device *pdev) if (lpuart_is_32(sport)) { lpuart_reg.cons = LPUART32_CONSOLE; - ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart32_int, 0, - DRIVER_NAME, sport); + handler = lpuart32_int; } else { lpuart_reg.cons = LPUART_CONSOLE; - ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart_int, 0, - DRIVER_NAME, sport); + handler = lpuart_int; } - if (ret) - goto failed_irq_request; - ret = uart_get_rs485_mode(&sport->port); if (ret) goto failed_get_rs485; @@ -2684,11 +2680,17 @@ static int lpuart_probe(struct platform_device *pdev) if (ret) goto failed_attach_port; + ret = devm_request_irq(&pdev->dev, sport->port.irq, handler, 0, + DRIVER_NAME, sport); + if (ret) + goto failed_irq_request; + return 0; +failed_irq_request: + uart_remove_one_port(&lpuart_reg, &sport->port); failed_get_rs485: failed_attach_port: -failed_irq_request: lpuart_disable_clks(sport); return ret; } From f5ef26276bb077e3da7a629e0c42875fa3e41911 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 23 Dec 2022 13:23:54 +0900 Subject: [PATCH 0859/4345] serial: fixup backport of "serial: Deassert Transmit Enable on probe in driver-specific way" When 7c7f9bc986e6 ("serial: Deassert Transmit Enable on probe in driver-specific way") got backported to 5.10.y, there known as 26a2b9c468de, some hunks were accidentally left out. In serial_core.c, it is possible that the omission in uart_suspend_port() is harmless, but the backport did have the corresponding hunk in uart_resume_port(), it runs counter to the original commit's intention of Skip any invocation of ->set_mctrl() if RS485 is enabled. and it's certainly better to be aligned with upstream. Link: https://lkml.kernel.org/r/20221222114414.1886632-1-linux@rasmusvillemoes.dk Fixes: 26a2b9c468de ("serial: Deassert Transmit Enable on probe in driver-specific way") Signed-off-by: Rasmus Villemoes [the fsl_lpuart part of the 5.15 patch is not required on 5.10, because the code before 26a2b9c468de was incorrectly not calling uart_remove_one_port on failed_get_rs485] Signed-off-by: Dominique Martinet Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 605f928f0636..40fff38588d4 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2254,7 +2254,8 @@ int uart_suspend_port(struct uart_driver *drv, struct uart_port *uport) spin_lock_irq(&uport->lock); ops->stop_tx(uport); - ops->set_mctrl(uport, 0); + if (!(uport->rs485.flags & SER_RS485_ENABLED)) + ops->set_mctrl(uport, 0); ops->stop_rx(uport); spin_unlock_irq(&uport->lock); From 5aa15a8400cc3f05e7884975f29fa0c1f9362f2e Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Fri, 6 Jan 2023 17:46:28 -0800 Subject: [PATCH 0860/4345] mptcp: mark ops structures as ro_after_init From: Florian Westphal commit 51fa7f8ebf0e25c7a9039fa3988a623d5f3855aa upstream. These structures are initialised from the init hooks, so we can't make them 'const'. But no writes occur afterwards, so we can use ro_after_init. Also, remove bogus EXPORT_SYMBOL, the only access comes from ip stack, not from kernel modules. Cc: stable@vger.kernel.org # 5.10 Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/mptcp/subflow.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 2e9238490924..61919e2499e7 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -360,8 +360,7 @@ do_reset: } struct request_sock_ops mptcp_subflow_request_sock_ops; -EXPORT_SYMBOL_GPL(mptcp_subflow_request_sock_ops); -static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops; +static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init; static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) { @@ -382,9 +381,9 @@ drop: } #if IS_ENABLED(CONFIG_MPTCP_IPV6) -static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops; -static struct inet_connection_sock_af_ops subflow_v6_specific; -static struct inet_connection_sock_af_ops subflow_v6m_specific; +static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init; +static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init; +static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init; static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { @@ -636,7 +635,7 @@ dispose_child: return child; } -static struct inet_connection_sock_af_ops subflow_specific; +static struct inet_connection_sock_af_ops subflow_specific __ro_after_init; enum mapping_status { MAPPING_OK, @@ -1017,7 +1016,7 @@ static void subflow_write_space(struct sock *sk) } } -static struct inet_connection_sock_af_ops * +static const struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -1032,7 +1031,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_connection_sock_af_ops *target; + const struct inet_connection_sock_af_ops *target; target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk); From 31472f94c68f5d9ebdd3432544044a9c27ea39d9 Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Fri, 6 Jan 2023 17:46:29 -0800 Subject: [PATCH 0861/4345] mptcp: remove MPTCP 'ifdef' in TCP SYN cookies From: Matthieu Baerts commit 3fff88186f047627bb128d65155f42517f8e448f upstream. To ease the maintenance, it is often recommended to avoid having #ifdef preprocessor conditions. Here the section related to CONFIG_MPTCP was quite short but the next commit needs to add more code around. It is then cleaner to move specific MPTCP code to functions located in net/mptcp directory. Now that mptcp_subflow_request_sock_ops structure can be static, it can also be marked as "read only after init". Suggested-by: Paolo Abeni Reviewed-by: Mat Martineau Cc: stable@vger.kernel.org # 5.10 Signed-off-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/mptcp.h | 12 ++++++++++-- net/ipv4/syncookies.c | 7 +++---- net/mptcp/subflow.c | 12 +++++++++++- 3 files changed, 24 insertions(+), 7 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 753ba7e755d6..3e529d8fce73 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -58,8 +58,6 @@ struct mptcp_out_options { }; #ifdef CONFIG_MPTCP -extern struct request_sock_ops mptcp_subflow_request_sock_ops; - void mptcp_init(void); static inline bool sk_is_mptcp(const struct sock *sk) @@ -133,6 +131,9 @@ void mptcp_seq_show(struct seq_file *seq); int mptcp_subflow_init_cookie_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb); +struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener, + bool attach_listener); #else static inline void mptcp_init(void) @@ -208,6 +209,13 @@ static inline int mptcp_subflow_init_cookie_req(struct request_sock *req, { return 0; /* TCP fallback */ } + +static inline struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener, + bool attach_listener) +{ + return NULL; +} #endif /* CONFIG_MPTCP */ #if IS_ENABLED(CONFIG_MPTCP_IPV6) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 41afc9155f31..542b66783493 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -290,12 +290,11 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct tcp_request_sock *treq; struct request_sock *req; -#ifdef CONFIG_MPTCP if (sk_is_mptcp(sk)) - ops = &mptcp_subflow_request_sock_ops; -#endif + req = mptcp_subflow_reqsk_alloc(ops, sk, false); + else + req = inet_reqsk_alloc(ops, sk, false); - req = inet_reqsk_alloc(ops, sk, false); if (!req) return NULL; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 61919e2499e7..6a149da3a4d9 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -359,7 +359,7 @@ do_reset: mptcp_subflow_reset(sk); } -struct request_sock_ops mptcp_subflow_request_sock_ops; +static struct request_sock_ops mptcp_subflow_request_sock_ops __ro_after_init; static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init; static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) @@ -411,6 +411,16 @@ drop: } #endif +struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener, + bool attach_listener) +{ + ops = &mptcp_subflow_request_sock_ops; + + return inet_reqsk_alloc(ops, sk_listener, attach_listener); +} +EXPORT_SYMBOL(mptcp_subflow_reqsk_alloc); + /* validate hmac received in third ACK */ static bool subflow_hmac_valid(const struct request_sock *req, const struct mptcp_options_received *mp_opt) From f4c7afa951eaa1f87a904bba84258b315814b376 Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Fri, 6 Jan 2023 17:46:30 -0800 Subject: [PATCH 0862/4345] mptcp: dedicated request sock for subflow in v6 From: Matthieu Baerts commit 34b21d1ddc8ace77a8fa35c1b1e06377209e0dae upstream. tcp_request_sock_ops structure is specific to IPv4. It should then not be used with MPTCP subflows on top of IPv6. For example, it contains the 'family' field, initialised to AF_INET. This 'family' field is used by TCP FastOpen code to generate the cookie but also by TCP Metrics, SELinux and SYN Cookies. Using the wrong family will not lead to crashes but displaying/using/checking wrong things. Note that 'send_reset' callback from request_sock_ops structure is used in some error paths. It is then also important to use the correct one for IPv4 or IPv6. The slab name can also be different in IPv4 and IPv6, it will be used when printing some log messages. The slab pointer will anyway be the same because the object size is the same for both v4 and v6. A BUILD_BUG_ON() has also been added to make sure this size is the same. Fixes: cec37a6e41aa ("mptcp: Handle MP_CAPABLE options for outgoing connections") Reviewed-by: Mat Martineau Cc: stable@vger.kernel.org # 5.10 Signed-off-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/mptcp/subflow.c | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 6a149da3a4d9..aeb723b38ced 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -359,7 +359,7 @@ do_reset: mptcp_subflow_reset(sk); } -static struct request_sock_ops mptcp_subflow_request_sock_ops __ro_after_init; +static struct request_sock_ops mptcp_subflow_v4_request_sock_ops __ro_after_init; static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init; static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) @@ -372,7 +372,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; - return tcp_conn_request(&mptcp_subflow_request_sock_ops, + return tcp_conn_request(&mptcp_subflow_v4_request_sock_ops, &subflow_request_sock_ipv4_ops, sk, skb); drop: @@ -381,6 +381,7 @@ drop: } #if IS_ENABLED(CONFIG_MPTCP_IPV6) +static struct request_sock_ops mptcp_subflow_v6_request_sock_ops __ro_after_init; static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init; @@ -402,7 +403,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) return 0; } - return tcp_conn_request(&mptcp_subflow_request_sock_ops, + return tcp_conn_request(&mptcp_subflow_v6_request_sock_ops, &subflow_request_sock_ipv6_ops, sk, skb); drop: @@ -415,7 +416,12 @@ struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *op struct sock *sk_listener, bool attach_listener) { - ops = &mptcp_subflow_request_sock_ops; + if (ops->family == AF_INET) + ops = &mptcp_subflow_v4_request_sock_ops; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + else if (ops->family == AF_INET6) + ops = &mptcp_subflow_v6_request_sock_ops; +#endif return inet_reqsk_alloc(ops, sk_listener, attach_listener); } @@ -1386,7 +1392,6 @@ static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = { static int subflow_ops_init(struct request_sock_ops *subflow_ops) { subflow_ops->obj_size = sizeof(struct mptcp_subflow_request_sock); - subflow_ops->slab_name = "request_sock_subflow"; subflow_ops->slab = kmem_cache_create(subflow_ops->slab_name, subflow_ops->obj_size, 0, @@ -1403,9 +1408,10 @@ static int subflow_ops_init(struct request_sock_ops *subflow_ops) void __init mptcp_subflow_init(void) { - mptcp_subflow_request_sock_ops = tcp_request_sock_ops; - if (subflow_ops_init(&mptcp_subflow_request_sock_ops) != 0) - panic("MPTCP: failed to init subflow request sock ops\n"); + mptcp_subflow_v4_request_sock_ops = tcp_request_sock_ops; + mptcp_subflow_v4_request_sock_ops.slab_name = "request_sock_subflow_v4"; + if (subflow_ops_init(&mptcp_subflow_v4_request_sock_ops) != 0) + panic("MPTCP: failed to init subflow v4 request sock ops\n"); subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops; subflow_request_sock_ipv4_ops.init_req = subflow_v4_init_req; @@ -1416,6 +1422,18 @@ void __init mptcp_subflow_init(void) subflow_specific.sk_rx_dst_set = subflow_finish_connect; #if IS_ENABLED(CONFIG_MPTCP_IPV6) + /* In struct mptcp_subflow_request_sock, we assume the TCP request sock + * structures for v4 and v6 have the same size. It should not changed in + * the future but better to make sure to be warned if it is no longer + * the case. + */ + BUILD_BUG_ON(sizeof(struct tcp_request_sock) != sizeof(struct tcp6_request_sock)); + + mptcp_subflow_v6_request_sock_ops = tcp6_request_sock_ops; + mptcp_subflow_v6_request_sock_ops.slab_name = "request_sock_subflow_v6"; + if (subflow_ops_init(&mptcp_subflow_v6_request_sock_ops) != 0) + panic("MPTCP: failed to init subflow v6 request sock ops\n"); + subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops; subflow_request_sock_ipv6_ops.init_req = subflow_v6_init_req; From 6eb02c596ec02e5897ae377e065cb7df55337a96 Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Fri, 6 Jan 2023 17:46:31 -0800 Subject: [PATCH 0863/4345] mptcp: use proper req destructor for IPv6 From: Matthieu Baerts commit d3295fee3c756ece33ac0d935e172e68c0a4161b upstream. Before, only the destructor from TCP request sock in IPv4 was called even if the subflow was IPv6. It is important to use the right destructor to avoid memory leaks with some advanced IPv6 features, e.g. when the request socks contain specific IPv6 options. Fixes: 79c0949e9a09 ("mptcp: Add key generation and token tree") Reviewed-by: Mat Martineau Cc: stable@vger.kernel.org # 5.10 Signed-off-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/mptcp/subflow.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index aeb723b38ced..3b154ad4945c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -40,7 +40,6 @@ static void subflow_req_destructor(struct request_sock *req) sock_put((struct sock *)subflow_req->msk); mptcp_token_destroy_request(req); - tcp_request_sock_ops.destructor(req); } static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2, @@ -380,6 +379,12 @@ drop: return 0; } +static void subflow_v4_req_destructor(struct request_sock *req) +{ + subflow_req_destructor(req); + tcp_request_sock_ops.destructor(req); +} + #if IS_ENABLED(CONFIG_MPTCP_IPV6) static struct request_sock_ops mptcp_subflow_v6_request_sock_ops __ro_after_init; static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init; @@ -410,6 +415,12 @@ drop: tcp_listendrop(sk); return 0; /* don't send reset */ } + +static void subflow_v6_req_destructor(struct request_sock *req) +{ + subflow_req_destructor(req); + tcp6_request_sock_ops.destructor(req); +} #endif struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops, @@ -1401,8 +1412,6 @@ static int subflow_ops_init(struct request_sock_ops *subflow_ops) if (!subflow_ops->slab) return -ENOMEM; - subflow_ops->destructor = subflow_req_destructor; - return 0; } @@ -1410,6 +1419,8 @@ void __init mptcp_subflow_init(void) { mptcp_subflow_v4_request_sock_ops = tcp_request_sock_ops; mptcp_subflow_v4_request_sock_ops.slab_name = "request_sock_subflow_v4"; + mptcp_subflow_v4_request_sock_ops.destructor = subflow_v4_req_destructor; + if (subflow_ops_init(&mptcp_subflow_v4_request_sock_ops) != 0) panic("MPTCP: failed to init subflow v4 request sock ops\n"); @@ -1431,6 +1442,8 @@ void __init mptcp_subflow_init(void) mptcp_subflow_v6_request_sock_ops = tcp6_request_sock_ops; mptcp_subflow_v6_request_sock_ops.slab_name = "request_sock_subflow_v6"; + mptcp_subflow_v6_request_sock_ops.destructor = subflow_v6_req_destructor; + if (subflow_ops_init(&mptcp_subflow_v6_request_sock_ops) != 0) panic("MPTCP: failed to init subflow v6 request sock ops\n"); From 9f7bc28a6b8afc2274e25650511555e93f45470f Mon Sep 17 00:00:00 2001 From: Frederick Lawler Date: Mon, 9 Jan 2023 10:39:06 -0600 Subject: [PATCH 0864/4345] net: sched: disallow noqueue for qdisc classes commit 96398560f26aa07e8f2969d73c8197e6a6d10407 upstream. While experimenting with applying noqueue to a classful queue discipline, we discovered a NULL pointer dereference in the __dev_queue_xmit() path that generates a kernel OOPS: # dev=enp0s5 # tc qdisc replace dev $dev root handle 1: htb default 1 # tc class add dev $dev parent 1: classid 1:1 htb rate 10mbit # tc qdisc add dev $dev parent 1:1 handle 10: noqueue # ping -I $dev -w 1 -c 1 1.1.1.1 [ 2.172856] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 2.173217] #PF: supervisor instruction fetch in kernel mode ... [ 2.178451] Call Trace: [ 2.178577] [ 2.178686] htb_enqueue+0x1c8/0x370 [ 2.178880] dev_qdisc_enqueue+0x15/0x90 [ 2.179093] __dev_queue_xmit+0x798/0xd00 [ 2.179305] ? _raw_write_lock_bh+0xe/0x30 [ 2.179522] ? __local_bh_enable_ip+0x32/0x70 [ 2.179759] ? ___neigh_create+0x610/0x840 [ 2.179968] ? eth_header+0x21/0xc0 [ 2.180144] ip_finish_output2+0x15e/0x4f0 [ 2.180348] ? dst_output+0x30/0x30 [ 2.180525] ip_push_pending_frames+0x9d/0xb0 [ 2.180739] raw_sendmsg+0x601/0xcb0 [ 2.180916] ? _raw_spin_trylock+0xe/0x50 [ 2.181112] ? _raw_spin_unlock_irqrestore+0x16/0x30 [ 2.181354] ? get_page_from_freelist+0xcd6/0xdf0 [ 2.181594] ? sock_sendmsg+0x56/0x60 [ 2.181781] sock_sendmsg+0x56/0x60 [ 2.181958] __sys_sendto+0xf7/0x160 [ 2.182139] ? handle_mm_fault+0x6e/0x1d0 [ 2.182366] ? do_user_addr_fault+0x1e1/0x660 [ 2.182627] __x64_sys_sendto+0x1b/0x30 [ 2.182881] do_syscall_64+0x38/0x90 [ 2.183085] entry_SYSCALL_64_after_hwframe+0x63/0xcd ... [ 2.187402] Previously in commit d66d6c3152e8 ("net: sched: register noqueue qdisc"), NULL was set for the noqueue discipline on noqueue init so that __dev_queue_xmit() falls through for the noqueue case. This also sets a bypass of the enqueue NULL check in the register_qdisc() function for the struct noqueue_disc_ops. Classful queue disciplines make it past the NULL check in __dev_queue_xmit() because the discipline is set to htb (in this case), and then in the call to __dev_xmit_skb(), it calls into htb_enqueue() which grabs a leaf node for a class and then calls qdisc_enqueue() by passing in a queue discipline which assumes ->enqueue() is not set to NULL. Fix this by not allowing classes to be assigned to the noqueue discipline. Linux TC Notes states that classes cannot be set to the noqueue discipline. [1] Let's enforce that here. Links: 1. https://linux-tc-notes.sourceforge.net/tc/doc/sch_noqueue.txt Fixes: d66d6c3152e8 ("net: sched: register noqueue qdisc") Cc: stable@vger.kernel.org Signed-off-by: Frederick Lawler Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20230109163906.706000-1-fred@cloudflare.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/sched/sch_api.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d8ffe4114385..54e2309315eb 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1114,6 +1114,11 @@ skip: return -ENOENT; } + if (new && new->ops == &noqueue_qdisc_ops) { + NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class"); + return -EINVAL; + } + err = cops->graft(parent, cl, new, &old, extack); if (err) return err; From f8ed0a93b5d576bbaf01639ad816473bdfd1dcb0 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 3 Jan 2023 12:19:17 +0100 Subject: [PATCH 0865/4345] net/ulp: prevent ULP without clone op from entering the LISTEN status commit 2c02d41d71f90a5168391b6a5f2954112ba2307c upstream. When an ULP-enabled socket enters the LISTEN status, the listener ULP data pointer is copied inside the child/accepted sockets by sk_clone_lock(). The relevant ULP can take care of de-duplicating the context pointer via the clone() operation, but only MPTCP and SMC implement such op. Other ULPs may end-up with a double-free at socket disposal time. We can't simply clear the ULP data at clone time, as TLS replaces the socket ops with custom ones assuming a valid TLS ULP context is available. Instead completely prevent clone-less ULP sockets from entering the LISTEN status. Fixes: 734942cc4ea6 ("tcp: ULP infrastructure") Reported-by: slipper Signed-off-by: Paolo Abeni Link: https://lore.kernel.org/r/4b80c3d1dbe3d0ab072f80450c202d9bc88b4b03.1672740602.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv4/inet_connection_sock.c | 16 +++++++++++++++- net/ipv4/tcp_ulp.c | 4 ++++ 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e54abccdffd0..9ed59147ef66 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -916,11 +916,25 @@ void inet_csk_prepare_forced_close(struct sock *sk) } EXPORT_SYMBOL(inet_csk_prepare_forced_close); +static int inet_ulp_can_listen(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone) + return -EINVAL; + + return 0; +} + int inet_csk_listen_start(struct sock *sk, int backlog) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); - int err = -EADDRINUSE; + int err; + + err = inet_ulp_can_listen(sk); + if (unlikely(err)) + return err; reqsk_queue_alloc(&icsk->icsk_accept_queue); diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 7c27aa629af1..b5d707a5a31b 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -136,6 +136,10 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops) if (icsk->icsk_ulp_ops) goto out_err; + err = -EINVAL; + if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN) + goto out_err; + err = ulp_ops->init(sk); if (err) goto out_err; From df02234e6b87d2a9a82acd3198e44bdeff8488c6 Mon Sep 17 00:00:00 2001 From: Clement Lecigne Date: Fri, 13 Jan 2023 13:07:45 +0100 Subject: [PATCH 0866/4345] ALSA: pcm: Move rwsem lock inside snd_ctl_elem_read to prevent UAF [ Note: this is a fix that works around the bug equivalently as the two upstream commits: 1fa4445f9adf ("ALSA: control - introduce snd_ctl_notify_one() helper") 56b88b50565c ("ALSA: pcm: Move rwsem lock inside snd_ctl_elem_read to prevent UAF") but in a simpler way to fit with older stable trees -- tiwai ] Add missing locking in ctl_elem_read_user/ctl_elem_write_user which can be easily triggered and turned into an use-after-free. Example code paths with SNDRV_CTL_IOCTL_ELEM_READ: 64-bits: snd_ctl_ioctl snd_ctl_elem_read_user [takes controls_rwsem] snd_ctl_elem_read [lock properly held, all good] [drops controls_rwsem] 32-bits (compat): snd_ctl_ioctl_compat snd_ctl_elem_write_read_compat ctl_elem_write_read snd_ctl_elem_read [missing lock, not good] CVE-2023-0266 was assigned for this issue. Signed-off-by: Clement Lecigne Cc: stable@kernel.org # 5.12 and older Signed-off-by: Takashi Iwai Reviewed-by: Jaroslav Kysela Signed-off-by: Greg Kroah-Hartman --- sound/core/control_compat.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index 97467f6a32a1..980ab3580f1b 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -304,7 +304,9 @@ static int ctl_elem_read_user(struct snd_card *card, err = snd_power_wait(card, SNDRV_CTL_POWER_D0); if (err < 0) goto error; + down_read(&card->controls_rwsem); err = snd_ctl_elem_read(card, data); + up_read(&card->controls_rwsem); if (err < 0) goto error; err = copy_ctl_value_to_user(userdata, valuep, data, type, count); @@ -332,7 +334,9 @@ static int ctl_elem_write_user(struct snd_ctl_file *file, err = snd_power_wait(card, SNDRV_CTL_POWER_D0); if (err < 0) goto error; + down_write(&card->controls_rwsem); err = snd_ctl_elem_write(card, file, data); + up_write(&card->controls_rwsem); if (err < 0) goto error; err = copy_ctl_value_to_user(userdata, valuep, data, type, count); From 0ad275c139a3e992cb420d5df1786526f0552077 Mon Sep 17 00:00:00 2001 From: Adrian Chan Date: Mon, 9 Jan 2023 16:05:20 -0500 Subject: [PATCH 0867/4345] ALSA: hda/hdmi: Add a HP device 0x8715 to force connect list commit de1ccb9e61728dd941fe0e955a7a129418657267 upstream. Add the 'HP Engage Flex Mini' device to the force connect list to enable audio through HDMI. Signed-off-by: Adrian Chan Cc: Link: https://lore.kernel.org/r/20230109210520.16060-1-adchan@google.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_hdmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 19566b75753e..1afe9cddb69e 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1966,6 +1966,7 @@ static const struct snd_pci_quirk force_connect_list[] = { SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1), SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1), + SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1), SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1), {} }; From de4a20e14823475363b36511dbba1fe6c7b754de Mon Sep 17 00:00:00 2001 From: Chris Chiu Date: Tue, 3 Jan 2023 17:53:32 +0800 Subject: [PATCH 0868/4345] ALSA: hda - Enable headset mic on another Dell laptop with ALC3254 commit a5751933a7f6abbdad90d98f25a25bb4b133a9e6 upstream. There is another Dell Latitude laptop (1028:0c03) with Realtek codec ALC3254 which needs the ALC269_FIXUP_DELL4_MIC_NO_PRESENCE instead of the default matched ALC269_FIXUP_DELL1_MIC_NO_PRESENCE. Apply correct fixup for this particular model to enable headset mic. Signed-off-by: Chris Chiu Cc: Link: https://lore.kernel.org/r/20230103095332.730677-1-chris.chiu@canonical.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 99e121f66d21..b2c9cdfb83e6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8847,6 +8847,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), + SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS), From 19ff2d645f7a9626146b6b3ba698488d60aa04de Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 14 Jan 2023 10:16:53 +0100 Subject: [PATCH 0869/4345] Linux 5.10.163 Link: https://lore.kernel.org/r/20230112135524.143670746@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Pavel Machek (CIP) Tested-by: Shuah Khan Tested-by: Guenter Roeck Tested-by: Hulk Robot Tested-by: Sudip Mukherjee Tested-by: Jon Hunter Tested-by: Linux Kernel Functional Testing Tested-by: Allen Pais Tested-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 704709f34da3..98fc6e7fd41d 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 162 +SUBLEVEL = 163 EXTRAVERSION = NAME = Dare mighty things From 550efeff989b041f3746118c0ddd863c39ddc1aa Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 11 Jan 2023 17:07:33 +0100 Subject: [PATCH 0870/4345] netfilter: nft_payload: incorrect arithmetics when fetching VLAN header bits commit 696e1a48b1a1b01edad542a1ef293665864a4dd0 upstream. If the offset + length goes over the ethernet + vlan header, then the length is adjusted to copy the bytes that are within the boundaries of the vlan_ethhdr scratchpad area. The remaining bytes beyond ethernet + vlan header are copied directly from the skbuff data area. Fix incorrect arithmetic operator: subtract, not add, the size of the vlan header in case of double-tagged packets to adjust the length accordingly to address CVE-2023-0179. Reported-by: Davide Ornaghi Fixes: f6ae9f120dad ("netfilter: nft_payload: add C-VLAN support") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nft_payload.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 551e0d6cf63d..74c220eeec1a 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -62,7 +62,7 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) return false; if (offset + len > VLAN_ETH_HLEN + vlan_hlen) - ethlen -= offset + len - VLAN_ETH_HLEN + vlan_hlen; + ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen; memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen); From 443b390f2cc9b04e70c243985e0fdf2d430af3e6 Mon Sep 17 00:00:00 2001 From: Luka Guzenko Date: Tue, 10 Jan 2023 21:25:14 +0100 Subject: [PATCH 0871/4345] ALSA: hda/realtek: Enable mute/micmute LEDs on HP Spectre x360 13-aw0xxx commit ca88eeb308a221c2dcd4a64031d2e5fcd3db9eaa upstream. The HP Spectre x360 13-aw0xxx devices use the ALC285 codec with GPIO 0x04 controlling the micmute LED and COEF 0x0b index 8 controlling the mute LED. A quirk was added to make these work as well as a fixup. Signed-off-by: Luka Guzenko Cc: Link: https://lore.kernel.org/r/20230110202514.2792-1-l.guzenko@web.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b2c9cdfb83e6..eb7dd457ef5a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4581,6 +4581,16 @@ static void alc285_fixup_hp_coef_micmute_led(struct hda_codec *codec, } } +static void alc285_fixup_hp_gpio_micmute_led(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) + spec->micmute_led_polarity = 1; + alc_fixup_hp_gpio_led(codec, action, 0, 0x04); +} + static void alc236_fixup_hp_coef_micmute_led(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -4602,6 +4612,13 @@ static void alc285_fixup_hp_mute_led(struct hda_codec *codec, alc285_fixup_hp_coef_micmute_led(codec, fix, action); } +static void alc285_fixup_hp_spectre_x360_mute_led(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + alc285_fixup_hp_mute_led_coefbit(codec, fix, action); + alc285_fixup_hp_gpio_micmute_led(codec, fix, action); +} + static void alc236_fixup_hp_mute_led(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -6856,6 +6873,7 @@ enum { ALC285_FIXUP_ASUS_G533Z_PINS, ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, + ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED, ALC236_FIXUP_HP_GPIO_LED, ALC236_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF, @@ -8224,6 +8242,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_mute_led, }, + [ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_spectre_x360_mute_led, + }, [ALC236_FIXUP_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, .v.func = alc236_fixup_hp_gpio_led, @@ -8936,6 +8958,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO), SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), + SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8720, "HP EliteBook x360 1040 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED), From c47883105cffa3ab85c92305a119592fe803bcba Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 20 Dec 2022 14:03:52 +0000 Subject: [PATCH 0872/4345] KVM: arm64: Fix S1PTW handling on RO memslots commit 406504c7b0405d74d74c15a667cd4c4620c3e7a9 upstream. A recent development on the EFI front has resulted in guests having their page tables baked in the firmware binary, and mapped into the IPA space as part of a read-only memslot. Not only is this legitimate, but it also results in added security, so thumbs up. It is possible to take an S1PTW translation fault if the S1 PTs are unmapped at stage-2. However, KVM unconditionally treats S1PTW as a write to correctly handle hardware AF/DB updates to the S1 PTs. Furthermore, KVM injects an exception into the guest for S1PTW writes. In the aforementioned case this results in the guest taking an abort it won't recover from, as the S1 PTs mapping the vectors suffer from the same problem. So clearly our handling is... wrong. Instead, switch to a two-pronged approach: - On S1PTW translation fault, handle the fault as a read - On S1PTW permission fault, handle the fault as a write This is of no consequence to SW that *writes* to its PTs (the write will trigger a non-S1PTW fault), and SW that uses RO PTs will not use HW-assisted AF/DB anyway, as that'd be wrong. Only in the case described in c4ad98e4b72c ("KVM: arm64: Assume write fault on S1PTW permission fault on instruction fetch") do we end-up with two back-to-back faults (page being evicted and faulted back). I don't think this is a case worth optimising for. Fixes: c4ad98e4b72c ("KVM: arm64: Assume write fault on S1PTW permission fault on instruction fetch") Reviewed-by: Oliver Upton Reviewed-by: Ard Biesheuvel Regression-tested-by: Ard Biesheuvel Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/kvm_emulate.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 472122d731b0..4bca3d10ab0e 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -382,8 +382,26 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_abt_iss1tw(vcpu)) - return true; + if (kvm_vcpu_abt_iss1tw(vcpu)) { + /* + * Only a permission fault on a S1PTW should be + * considered as a write. Otherwise, page tables baked + * in a read-only memslot will result in an exception + * being delivered in the guest. + * + * The drawback is that we end-up faulting twice if the + * guest is using any of HW AF/DB: a translation fault + * to map the page containing the PT (read only at + * first), then a permission fault to allow the flags + * to be set. + */ + switch (kvm_vcpu_trap_get_fault_type(vcpu)) { + case ESR_ELx_FSC_PERM: + return true; + default: + return false; + } + } if (kvm_vcpu_trap_is_iabt(vcpu)) return false; From 38c4a17c6b32f7c6679b30de390c466c7367fe6b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 9 Jan 2023 10:44:31 +0100 Subject: [PATCH 0873/4345] efi: tpm: Avoid READ_ONCE() for accessing the event log commit d3f450533bbcb6dd4d7d59cadc9b61b7321e4ac1 upstream. Nathan reports that recent kernels built with LTO will crash when doing EFI boot using Fedora's GRUB and SHIM. The culprit turns out to be a misaligned load from the TPM event log, which is annotated with READ_ONCE(), and under LTO, this gets translated into a LDAR instruction which does not tolerate misaligned accesses. Interestingly, this does not happen when booting the same kernel straight from the UEFI shell, and so the fact that the event log may appear misaligned in memory may be caused by a bug in GRUB or SHIM. However, using READ_ONCE() to access firmware tables is slightly unusual in any case, and here, we only need to ensure that 'event' is not dereferenced again after it gets unmapped, but this is already taken care of by the implicit barrier() semantics of the early_memunmap() call. Cc: Cc: Peter Jones Cc: Jarkko Sakkinen Cc: Matthew Garrett Reported-by: Nathan Chancellor Tested-by: Nathan Chancellor Link: https://github.com/ClangBuiltLinux/linux/issues/1782 Signed-off-by: Ard Biesheuvel Signed-off-by: Greg Kroah-Hartman --- include/linux/tpm_eventlog.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 20c0ff54b7a0..7d68a5cc5881 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -198,8 +198,8 @@ static __always_inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *ev * The loop below will unmap these fields if the log is larger than * one page, so save them here for reference: */ - count = READ_ONCE(event->count); - event_type = READ_ONCE(event->event_type); + count = event->count; + event_type = event->event_type; /* Verify that it's the log header */ if (event_header->pcr_idx != 0 || From eaabceae1b70d78c9d7ecc6f33dff5e173623973 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Wed, 4 Jan 2023 10:47:39 -0700 Subject: [PATCH 0874/4345] docs: Fix the docs build with Sphinx 6.0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 0283189e8f3d0917e2ac399688df85211f48447b upstream. Sphinx 6.0 removed the execfile_() function, which we use as part of the configuration process. They *did* warn us... Just open-code the functionality as is done in Sphinx itself. Tested (using SPHINX_CONF, since this code is only executed with an alternative config file) on various Sphinx versions from 2.5 through 6.0. Reported-by: Martin Liška Cc: stable@vger.kernel.org Signed-off-by: Jonathan Corbet Signed-off-by: Greg Kroah-Hartman --- Documentation/sphinx/load_config.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/Documentation/sphinx/load_config.py b/Documentation/sphinx/load_config.py index eeb394b39e2c..8b416bfd75ac 100644 --- a/Documentation/sphinx/load_config.py +++ b/Documentation/sphinx/load_config.py @@ -3,7 +3,7 @@ import os import sys -from sphinx.util.pycompat import execfile_ +from sphinx.util.osutil import fs_encoding # ------------------------------------------------------------------------------ def loadConfig(namespace): @@ -48,7 +48,9 @@ def loadConfig(namespace): sys.stdout.write("load additional sphinx-config: %s\n" % config_file) config = namespace.copy() config['__file__'] = config_file - execfile_(config_file, config) + with open(config_file, 'rb') as f: + code = compile(f.read(), fs_encoding, 'exec') + exec(code, config) del config['__file__'] namespace.update(config) else: From d1725dbf2310d87cd12bcdeeadf7d787bcadeb66 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 10 Jan 2023 20:56:59 +0200 Subject: [PATCH 0875/4345] perf auxtrace: Fix address filter duplicate symbol selection commit cf129830ee820f7fc90b98df193cd49d49344d09 upstream. When a match has been made to the nth duplicate symbol, return success not error. Example: Before: $ cat file.c cat: file.c: No such file or directory $ cat file1.c #include static void func(void) { printf("First func\n"); } void other(void); int main() { func(); other(); return 0; } $ cat file2.c #include static void func(void) { printf("Second func\n"); } void other(void) { func(); } $ gcc -Wall -Wextra -o test file1.c file2.c $ perf record -e intel_pt//u --filter 'filter func @ ./test' -- ./test Multiple symbols with name 'func' #1 0x1149 l func which is near main #2 0x1179 l func which is near other Disambiguate symbol name by inserting #n after the name e.g. func #2 Or select a global symbol by inserting #0 or #g or #G Failed to parse address filter: 'filter func @ ./test' Filter format is: filter|start|stop|tracestop [/ ] [@] Where multiple filters are separated by space or comma. $ perf record -e intel_pt//u --filter 'filter func #2 @ ./test' -- ./test Failed to parse address filter: 'filter func #2 @ ./test' Filter format is: filter|start|stop|tracestop [/ ] [@] Where multiple filters are separated by space or comma. After: $ perf record -e intel_pt//u --filter 'filter func #2 @ ./test' -- ./test First func Second func [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data ] $ perf script --itrace=b -Ftime,flags,ip,sym,addr --ns 1231062.526977619: tr strt 0 [unknown] => 558495708179 func 1231062.526977619: tr end call 558495708188 func => 558495708050 _init 1231062.526979286: tr strt 0 [unknown] => 55849570818d func 1231062.526979286: tr end return 55849570818f func => 55849570819d other Fixes: 1b36c03e356936d6 ("perf record: Add support for using symbols in address filters") Reported-by: Dmitrii Dolgov <9erthalion6@gmail.com> Signed-off-by: Adrian Hunter Tested-by: Dmitry Dolgov <9erthalion6@gmail.com> Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230110185659.15979-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/auxtrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index d96e86ddd2c5..18452f12510c 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -2449,7 +2449,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start, *size = sym->start - *start; if (idx > 0) { if (*size) - return 1; + return 0; } else if (dso_sym_match(sym, sym_name, &cnt, idx)) { print_duplicate_syms(dso, sym_name); return -EINVAL; From 5ee3083307efa0a7b4b0923f773787646e252043 Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Mon, 14 Nov 2022 11:40:08 +0100 Subject: [PATCH 0876/4345] s390/kexec: fix ipl report address for kdump commit c2337a40e04dde1692b5b0a46ecc59f89aaba8a1 upstream. This commit addresses the following erroneous situation with file-based kdump executed on a system with a valid IPL report. On s390, a kdump kernel, its initrd and IPL report if present are loaded into a special and reserved on boot memory region - crashkernel. When a system crashes and kdump was activated before, the purgatory code is entered first which swaps the crashkernel and [0 - crashkernel size] memory regions. Only after that the kdump kernel is entered. For this reason, the pointer to an IPL report in lowcore must point to the IPL report after the swap and not to the address of the IPL report that was located in crashkernel memory region before the swap. Failing to do so, makes the kdump's decompressor try to read memory from the crashkernel memory region which already contains the production's kernel memory. The situation described above caused spontaneous kdump failures/hangs on systems where the Secure IPL is activated because on such systems an IPL report is always present. In that case kdump's decompressor tried to parse an IPL report which frequently lead to illegal memory accesses because an IPL report contains addresses to various data. Cc: Fixes: 99feaa717e55 ("s390/kexec_file: Create ipl report and pass to next kernel") Reviewed-by: Vasily Gorbik Signed-off-by: Alexander Egorenkov Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/machine_kexec_file.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index 53da174754d9..bf0596749ebd 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -185,8 +185,6 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->memsz = ALIGN(data->memsz, PAGE_SIZE); buf.mem = data->memsz; - if (image->type == KEXEC_TYPE_CRASH) - buf.mem += crashk_res.start; ptr = (void *)ipl_cert_list_addr; end = ptr + ipl_cert_list_size; @@ -223,6 +221,9 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr); *lc_ipl_parmblock_ptr = (__u32)buf.mem; + if (image->type == KEXEC_TYPE_CRASH) + buf.mem += crashk_res.start; + ret = kexec_add_buffer(&buf); out: return ret; From 2adc64f3e669fb9ee1fb2a63f6fd4016a7004afe Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 30 Dec 2022 22:15:45 -0800 Subject: [PATCH 0877/4345] ASoC: qcom: lpass-cpu: Fix fallback SD line index handling commit 000bca8d706d1bf7cca01af75787247c5a2fdedf upstream. These indices should reference the ID placed within the dai_driver array, not the indices of the array itself. This fixes commit 4ff028f6c108 ("ASoC: qcom: lpass-cpu: Make I2S SD lines configurable"), which among others, broke IPQ8064 audio (sound/soc/qcom/lpass-ipq806x.c) because it uses ID 4 but we'd stop initializing the mi2s_playback_sd_mode and mi2s_capture_sd_mode arrays at ID 0. Fixes: 4ff028f6c108 ("ASoC: qcom: lpass-cpu: Make I2S SD lines configurable") Cc: Signed-off-by: Brian Norris Reviewed-by: Stephan Gerhold Link: https://lore.kernel.org/r/20221231061545.2110253-1-computersforpeace@gmail.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/qcom/lpass-cpu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index ecd6c049ace2..9e70c193d7f4 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -816,10 +816,11 @@ static void of_lpass_cpu_parse_dai_data(struct device *dev, struct lpass_data *data) { struct device_node *node; - int ret, id; + int ret, i, id; /* Allow all channels by default for backwards compatibility */ - for (id = 0; id < data->variant->num_dai; id++) { + for (i = 0; i < data->variant->num_dai; i++) { + id = data->variant->dai_driver[i].id; data->mi2s_playback_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH; data->mi2s_capture_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH; } From bddb355267849423306cc9dc313783303dd19f03 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 5 Jan 2023 15:44:20 +0100 Subject: [PATCH 0878/4345] s390/cpum_sf: add READ_ONCE() semantics to compare and swap loops commit 82d3edb50a11bf3c5ef63294d5358ba230181413 upstream. The current cmpxchg_double() loops within the perf hw sampling code do not have READ_ONCE() semantics to read the old value from memory. This allows the compiler to generate code which reads the "old" value several times from memory, which again allows for inconsistencies. For example: /* Reset trailer (using compare-double-and-swap) */ do { te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; te_flags |= SDB_TE_ALERT_REQ_MASK; } while (!cmpxchg_double(&te->flags, &te->overflow, te->flags, te->overflow, te_flags, 0ULL)); The compiler could generate code where te->flags used within the cmpxchg_double() call may be refetched from memory and which is not necessarily identical to the previous read version which was used to generate te_flags. Which in turn means that an incorrect update could happen. Fix this by adding READ_ONCE() semantics to all cmpxchg_double() loops. Given that READ_ONCE() cannot generate code on s390 which atomically reads 16 bytes, use a private compare-and-swap-double implementation to achieve that. Also replace cmpxchg_double() with the private implementation to be able to re-use the old value within the loops. As a side effect this converts the whole code to only use bit fields to read and modify bits within the hws trailer header. Reported-by: Alexander Gordeev Acked-by: Alexander Gordeev Acked-by: Hendrik Brueckner Reviewed-by: Thomas Richter Cc: Link: https://lore.kernel.org/linux-s390/Y71QJBhNTIatvxUT@osiris/T/#ma14e2a5f7aa8ed4b94b6f9576799b3ad9c60f333 Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- arch/s390/include/asm/cpu_mf.h | 31 +++++----- arch/s390/kernel/perf_cpum_sf.c | 101 ++++++++++++++++++++------------ 2 files changed, 77 insertions(+), 55 deletions(-) diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index 0d90cbeb89b4..a0914bc6c9bd 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -128,19 +128,21 @@ struct hws_combined_entry { struct hws_diag_entry diag; /* Diagnostic-sampling data entry */ } __packed; -struct hws_trailer_entry { - union { - struct { - unsigned int f:1; /* 0 - Block Full Indicator */ - unsigned int a:1; /* 1 - Alert request control */ - unsigned int t:1; /* 2 - Timestamp format */ - unsigned int :29; /* 3 - 31: Reserved */ - unsigned int bsdes:16; /* 32-47: size of basic SDE */ - unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ - }; - unsigned long long flags; /* 0 - 63: All indicators */ +union hws_trailer_header { + struct { + unsigned int f:1; /* 0 - Block Full Indicator */ + unsigned int a:1; /* 1 - Alert request control */ + unsigned int t:1; /* 2 - Timestamp format */ + unsigned int :29; /* 3 - 31: Reserved */ + unsigned int bsdes:16; /* 32-47: size of basic SDE */ + unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ + unsigned long long overflow; /* 64 - Overflow Count */ }; - unsigned long long overflow; /* 64 - sample Overflow count */ + __uint128_t val; +}; + +struct hws_trailer_entry { + union hws_trailer_header header; /* 0 - 15 Flags + Overflow Count */ unsigned char timestamp[16]; /* 16 - 31 timestamp */ unsigned long long reserved1; /* 32 -Reserved */ unsigned long long reserved2; /* */ @@ -287,14 +289,11 @@ static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi, return USEC_PER_SEC * qsi->cpu_speed / rate; } -#define SDB_TE_ALERT_REQ_MASK 0x4000000000000000UL -#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL - /* Return TOD timestamp contained in an trailer entry */ static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te) { /* TOD in STCKE format */ - if (te->t) + if (te->header.t) return *((unsigned long long *) &te->timestamp[1]); /* TOD in STCK format */ diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 19cd7b961c45..bcd31e0b4edb 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -163,14 +163,15 @@ static void free_sampling_buffer(struct sf_buffer *sfb) static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags) { - unsigned long sdb, *trailer; + struct hws_trailer_entry *te; + unsigned long sdb; /* Allocate and initialize sample-data-block */ sdb = get_zeroed_page(gfp_flags); if (!sdb) return -ENOMEM; - trailer = trailer_entry_ptr(sdb); - *trailer = SDB_TE_ALERT_REQ_MASK; + te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb); + te->header.a = 1; /* Link SDB into the sample-data-block-table */ *sdbt = sdb; @@ -1206,7 +1207,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, "%s: Found unknown" " sampling data entry: te->f %i" " basic.def %#4x (%p)\n", __func__, - te->f, sample->def, sample); + te->header.f, sample->def, sample); /* Sample slot is not yet written or other record. * * This condition can occur if the buffer was reused @@ -1217,7 +1218,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, * that are not full. Stop processing if the first * invalid format was detected. */ - if (!te->f) + if (!te->header.f) break; } @@ -1227,6 +1228,16 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, } } +static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t new) +{ + asm volatile( + " cdsg %[old],%[new],%[ptr]\n" + : [old] "+d" (old), [ptr] "+QS" (*ptr) + : [new] "d" (new) + : "memory", "cc"); + return old; +} + /* hw_perf_event_update() - Process sampling buffer * @event: The perf event * @flush_all: Flag to also flush partially filled sample-data-blocks @@ -1243,10 +1254,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, */ static void hw_perf_event_update(struct perf_event *event, int flush_all) { + unsigned long long event_overflow, sampl_overflow, num_sdb; + union hws_trailer_header old, prev, new; struct hw_perf_event *hwc = &event->hw; struct hws_trailer_entry *te; unsigned long *sdbt; - unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags; int done; /* @@ -1266,25 +1278,25 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt); /* Leave loop if no more work to do (block full indicator) */ - if (!te->f) { + if (!te->header.f) { done = 1; if (!flush_all) break; } /* Check the sample overflow count */ - if (te->overflow) + if (te->header.overflow) /* Account sample overflows and, if a particular limit * is reached, extend the sampling buffer. * For details, see sfb_account_overflows(). */ - sampl_overflow += te->overflow; + sampl_overflow += te->header.overflow; /* Timestamps are valid for full sample-data-blocks only */ debug_sprintf_event(sfdbg, 6, "%s: sdbt %#lx " "overflow %llu timestamp %#llx\n", - __func__, (unsigned long)sdbt, te->overflow, - (te->f) ? trailer_timestamp(te) : 0ULL); + __func__, (unsigned long)sdbt, te->header.overflow, + (te->header.f) ? trailer_timestamp(te) : 0ULL); /* Collect all samples from a single sample-data-block and * flag if an (perf) event overflow happened. If so, the PMU @@ -1294,12 +1306,16 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) num_sdb++; /* Reset trailer (using compare-double-and-swap) */ + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te_flags |= SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - te->flags, te->overflow, - te_flags, 0ULL)); + old.val = prev.val; + new.val = prev.val; + new.f = 0; + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); /* Advance to next sample-data-block */ sdbt++; @@ -1384,7 +1400,7 @@ static void aux_output_end(struct perf_output_handle *handle) range_scan = AUX_SDB_NUM_ALERT(aux); for (i = 0, idx = aux->head; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - if (!(te->flags & SDB_TE_BUFFER_FULL_MASK)) + if (!te->header.f) break; } /* i is num of SDBs which are full */ @@ -1392,7 +1408,7 @@ static void aux_output_end(struct perf_output_handle *handle) /* Remove alert indicators in the buffer */ te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags &= ~SDB_TE_ALERT_REQ_MASK; + te->header.a = 0; debug_sprintf_event(sfdbg, 6, "%s: SDBs %ld range %ld head %ld\n", __func__, i, range_scan, aux->head); @@ -1437,9 +1453,9 @@ static int aux_output_begin(struct perf_output_handle *handle, idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | - SDB_TE_ALERT_REQ_MASK); - te->overflow = 0; + te->header.f = 0; + te->header.a = 0; + te->header.overflow = 0; } /* Save the position of empty SDBs */ aux->empty_mark = aux->head + range - 1; @@ -1448,7 +1464,7 @@ static int aux_output_begin(struct perf_output_handle *handle, /* Set alert indicator */ aux->alert_mark = aux->head + range/2 - 1; te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags = te->flags | SDB_TE_ALERT_REQ_MASK; + te->header.a = 1; /* Reset hardware buffer head */ head = AUX_SDB_INDEX(aux, aux->head); @@ -1475,14 +1491,17 @@ static int aux_output_begin(struct perf_output_handle *handle, static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; + union hws_trailer_header old, prev, new; struct hws_trailer_entry *te; te = aux_sdb_trailer(aux, alert_index); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - *overflow = orig_overflow = te->overflow; - if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { + old.val = prev.val; + new.val = prev.val; + *overflow = old.overflow; + if (old.f) { /* * SDB is already set by hardware. * Abort and try to set somewhere @@ -1490,10 +1509,10 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, */ return false; } - new_flags = orig_flags | SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); return true; } @@ -1522,8 +1541,9 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; unsigned long i, range_scan, idx, idx_old; + union hws_trailer_header old, prev, new; + unsigned long long orig_overflow; struct hws_trailer_entry *te; debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld " @@ -1554,17 +1574,20 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, idx_old = idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - orig_overflow = te->overflow; - new_flags = orig_flags & ~SDB_TE_BUFFER_FULL_MASK; + old.val = prev.val; + new.val = prev.val; + orig_overflow = old.overflow; + new.f = 0; + new.overflow = 0; if (idx == aux->alert_mark) - new_flags |= SDB_TE_ALERT_REQ_MASK; + new.a = 1; else - new_flags &= ~SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); *overflow += orig_overflow; } From 51dbedee2ff3b000c9905189e33e1972b6c9f649 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 9 Jan 2023 11:51:20 +0100 Subject: [PATCH 0879/4345] s390/percpu: add READ_ONCE() to arch_this_cpu_to_op_simple() commit e3f360db08d55a14112bd27454e616a24296a8b0 upstream. Make sure that *ptr__ within arch_this_cpu_to_op_simple() is only dereferenced once by using READ_ONCE(). Otherwise the compiler could generate incorrect code. Cc: Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- arch/s390/include/asm/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index 918f0ba4f4d2..5e26e2c4641b 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -31,7 +31,7 @@ pcp_op_T__ *ptr__; \ preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ - prev__ = *ptr__; \ + prev__ = READ_ONCE(*ptr__); \ do { \ old__ = prev__; \ new__ = old__ op (val); \ From afb6063aa89f78bcecdb3264604ce8def499e186 Mon Sep 17 00:00:00 2001 From: Volker Lendecke Date: Wed, 11 Jan 2023 12:37:58 +0100 Subject: [PATCH 0880/4345] cifs: Fix uninitialized memory read for smb311 posix symlink create commit a152d05ae4a71d802d50cf9177dba34e8bb09f68 upstream. If smb311 posix is enabled, we send the intended mode for file creation in the posix create context. Instead of using what's there on the stack, create the mfsymlink file with 0644. Fixes: ce558b0e17f8a ("smb3: Add posix create context for smb3.11 posix mounts") Cc: stable@vger.kernel.org Signed-off-by: Volker Lendecke Reviewed-by: Tom Talpey Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/link.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 85d30fef98a2..4fc6eb8e786d 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -471,6 +471,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.disposition = FILE_CREATE; oparms.fid = &fid; oparms.reconnect = false; + oparms.mode = 0644; rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL, NULL); From 8c71777b6a17527ff0bb12a973193f481fa7fc5e Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 2 Jan 2023 11:02:00 +0100 Subject: [PATCH 0881/4345] drm/msm/adreno: Make adreno quirks not overwrite each other commit 13ef096e342b00e30b95a90c6c13eee1f0bec4c5 upstream. So far the adreno quirks have all been assigned with an OR operator, which is problematic, because they were assigned consecutive integer values, which makes checking them with an AND operator kind of no bueno.. Switch to using BIT(n) so that only the quirks that the programmer chose are taken into account when evaluating info->quirks & ADRENO_QUIRK_... Fixes: 370063ee427a ("drm/msm/adreno: Add A540 support") Reviewed-by: Dmitry Baryshkov Reviewed-by: Marijn Suijten Reviewed-by: Rob Clark Signed-off-by: Konrad Dybcio Reviewed-by: Akhil P Oommen Patchwork: https://patchwork.freedesktop.org/patch/516456/ Link: https://lore.kernel.org/r/20230102100201.77286-1-konrad.dybcio@linaro.org Signed-off-by: Rob Clark Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/msm/adreno/adreno_gpu.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index c3775f79525a..4656e707fe27 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -28,11 +28,9 @@ enum { ADRENO_FW_MAX, }; -enum adreno_quirks { - ADRENO_QUIRK_TWO_PASS_USE_WFI = 1, - ADRENO_QUIRK_FAULT_DETECT_MASK = 2, - ADRENO_QUIRK_LMLOADKILL_DISABLE = 3, -}; +#define ADRENO_QUIRK_TWO_PASS_USE_WFI BIT(0) +#define ADRENO_QUIRK_FAULT_DETECT_MASK BIT(1) +#define ADRENO_QUIRK_LMLOADKILL_DISABLE BIT(2) struct adreno_rev { uint8_t core; @@ -62,7 +60,7 @@ struct adreno_info { const char *name; const char *fw[ADRENO_FW_MAX]; uint32_t gmem; - enum adreno_quirks quirks; + u64 quirks; struct msm_gpu *(*init)(struct drm_device *dev); const char *zapfw; u32 inactive_period; From 785607e5e6fb52caf141e4580de40405565f04f1 Mon Sep 17 00:00:00 2001 From: Kuogee Hsieh Date: Tue, 27 Dec 2022 18:16:24 -0800 Subject: [PATCH 0882/4345] drm/msm/dp: do not complete dp_aux_cmd_fifo_tx() if irq is not for aux transfer commit 1cba0d150fa102439114a91b3e215909efc9f169 upstream. There are 3 possible interrupt sources are handled by DP controller, HPDstatus, Controller state changes and Aux read/write transaction. At every irq, DP controller have to check isr status of every interrupt sources and service the interrupt if its isr status bits shows interrupts are pending. There is potential race condition may happen at current aux isr handler implementation since it is always complete dp_aux_cmd_fifo_tx() even irq is not for aux read or write transaction. This may cause aux read transaction return premature if host aux data read is in the middle of waiting for sink to complete transferring data to host while irq happen. This will cause host's receiving buffer contains unexpected data. This patch fixes this problem by checking aux isr and return immediately at aux isr handler if there are no any isr status bits set. Current there is a bug report regrading eDP edid corruption happen during system booting up. After lengthy debugging to found that VIDEO_READY interrupt was continuously firing during system booting up which cause dp_aux_isr() to complete dp_aux_cmd_fifo_tx() prematurely to retrieve data from aux hardware buffer which is not yet contains complete data transfer from sink. This cause edid corruption. Follows are the signature at kernel logs when problem happen, EDID has corrupt header panel-simple-dp-aux aux-aea0000.edp: Couldn't identify panel via EDID Changes in v2: -- do complete if (ret == IRQ_HANDLED) ay dp-aux_isr() -- add more commit text Changes in v3: -- add Stephen suggested -- dp_aux_isr() return IRQ_XXX back to caller -- dp_ctrl_isr() return IRQ_XXX back to caller Changes in v4: -- split into two patches Changes in v5: -- delete empty line between tags Changes in v6: -- remove extra "that" and fixed line more than 75 char at commit text Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support") Signed-off-by: Kuogee Hsieh Tested-by: Douglas Anderson Reviewed-by: Abhinav Kumar Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/516121/ Link: https://lore.kernel.org/r/1672193785-11003-2-git-send-email-quic_khsieh@quicinc.com Signed-off-by: Abhinav Kumar Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/msm/dp/dp_aux.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index 19b35ae3e927..a73a2b28a70a 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -423,6 +423,10 @@ void dp_aux_isr(struct drm_dp_aux *dp_aux) aux->isr = dp_catalog_aux_get_irq(aux->catalog); + /* no interrupts pending, return immediately */ + if (!aux->isr) + return; + if (!aux->cmd_busy) return; From f401062d8dbd55fb86986403d93b1201bc95d4a2 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 13 Dec 2022 13:29:43 +0100 Subject: [PATCH 0883/4345] platform/x86: sony-laptop: Don't turn off 0x153 keyboard backlight during probe commit ad75bd85b1db69c97eefea07b375567821f6ef58 upstream. The 0x153 version of the kbd backlight control SNC handle has no separate address to probe if the backlight is there. This turns the probe call into a set keyboard backlight call with a value of 0 turning off the keyboard backlight. Skip probing when there is no separate probe address to avoid this. Link: https://bugzilla.redhat.com/show_bug.cgi?id=1583752 Fixes: 800f20170dcf ("Keyboard backlight control for some Vaio Fit models") Signed-off-by: Hans de Goede Reviewed-by: Mattia Dongili Link: https://lore.kernel.org/r/20221213122943.11123-1-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/sony-laptop.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index e5a1b5533408..f070e4eb74f4 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -1892,14 +1892,21 @@ static int sony_nc_kbd_backlight_setup(struct platform_device *pd, break; } - ret = sony_call_snc_handle(handle, probe_base, &result); - if (ret) - return ret; + /* + * Only probe if there is a separate probe_base, otherwise the probe call + * is equivalent to __sony_nc_kbd_backlight_mode_set(0), resulting in + * the keyboard backlight being turned off. + */ + if (probe_base) { + ret = sony_call_snc_handle(handle, probe_base, &result); + if (ret) + return ret; - if ((handle == 0x0137 && !(result & 0x02)) || - !(result & 0x01)) { - dprintk("no backlight keyboard found\n"); - return 0; + if ((handle == 0x0137 && !(result & 0x02)) || + !(result & 0x01)) { + dprintk("no backlight keyboard found\n"); + return 0; + } } kbdbl_ctl = kzalloc(sizeof(*kbdbl_ctl), GFP_KERNEL); From 112df4cd2b09acd64bcd18f5ef83ba5d07b34bf0 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 29 Nov 2022 09:57:48 +0800 Subject: [PATCH 0884/4345] ixgbe: fix pci device refcount leak commit b93fb4405fcb5112c5739c5349afb52ec7f15c07 upstream. As the comment of pci_get_domain_bus_and_slot() says, it returns a PCI device with refcount incremented, when finish using it, the caller must decrement the reference count by calling pci_dev_put(). In ixgbe_get_first_secondary_devfn() and ixgbe_x550em_a_has_mii(), pci_dev_put() is called to avoid leak. Fixes: 8fa10ef01260 ("ixgbe: register a mdiobus") Signed-off-by: Yang Yingliang Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index fc389eecdd2b..b0413904b798 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -851,9 +851,11 @@ static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn) rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn); if (rp_pdev && rp_pdev->subordinate) { bus = rp_pdev->subordinate->number; + pci_dev_put(rp_pdev); return pci_get_domain_bus_and_slot(0, bus, 0); } + pci_dev_put(rp_pdev); return NULL; } @@ -870,6 +872,7 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) struct ixgbe_adapter *adapter = hw->back; struct pci_dev *pdev = adapter->pdev; struct pci_dev *func0_pdev; + bool has_mii = false; /* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices * are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0 @@ -880,15 +883,16 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0)); if (func0_pdev) { if (func0_pdev == pdev) - return true; - else - return false; + has_mii = true; + goto out; } func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0)); if (func0_pdev == pdev) - return true; + has_mii = true; - return false; +out: + pci_dev_put(func0_pdev); + return has_mii; } /** From 6c9e2c11c33c35563d34d12b343d43b5c12200b5 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 10 Jan 2023 08:59:06 +0800 Subject: [PATCH 0885/4345] ipv6: raw: Deduct extension header length in rawv6_push_pending_frames commit cb3e9864cdbe35ff6378966660edbcbac955fe17 upstream. The total cork length created by ip6_append_data includes extension headers, so we must exclude them when comparing them against the IPV6_CHECKSUM offset which does not include extension headers. Reported-by: Kyle Zeng Fixes: 357b40a18b04 ("[IPV6]: IPV6_CHECKSUM socket option can corrupt kernel memory") Signed-off-by: Herbert Xu Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/raw.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 31eb54e92b3f..110254f44a46 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -539,6 +539,7 @@ csum_copy_err: static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { + struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; @@ -556,6 +557,9 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; + opt = inet6_sk(sk)->cork.opt; + total_len -= opt ? opt->opt_flen : 0; + if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); From ab9bb65b851973fd7843f83830e4ed518d9e213b Mon Sep 17 00:00:00 2001 From: Qiang Yu Date: Sun, 16 Oct 2022 11:05:32 +0800 Subject: [PATCH 0886/4345] bus: mhi: host: Fix race between channel preparation and M0 event [ Upstream commit 869a99907faea6d1835b0bd0d0422ae3519c6ea9 ] There is a race condition where mhi_prepare_channel() updates the read and write pointers as the base address and in parallel, if an M0 transition occurs, the tasklet goes ahead and rings doorbells for all channels with a delta in TRE rings assuming they are already enabled. This causes a null pointer access. Fix it by adding a channel enabled check before ringing channel doorbells. Cc: stable@vger.kernel.org # 5.19 Fixes: a6e2e3522f29 "bus: mhi: core: Add support for PM state transitions" Signed-off-by: Qiang Yu Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/1665889532-13634-1-git-send-email-quic_qianyu@quicinc.com [mani: CCed stable list] Signed-off-by: Manivannan Sadhasivam Signed-off-by: Sasha Levin --- drivers/bus/mhi/core/pm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c index 044dcdd723a7..7d69b740b9f9 100644 --- a/drivers/bus/mhi/core/pm.c +++ b/drivers/bus/mhi/core/pm.c @@ -298,7 +298,8 @@ int mhi_pm_m0_transition(struct mhi_controller *mhi_cntrl) read_lock_irq(&mhi_chan->lock); /* Only ring DB if ring is not empty */ - if (tre_ring->base && tre_ring->wp != tre_ring->rp) + if (tre_ring->base && tre_ring->wp != tre_ring->rp && + mhi_chan->ch_state == MHI_CH_STATE_ENABLED) mhi_ring_chan_db(mhi_cntrl, mhi_chan); read_unlock_irq(&mhi_chan->lock); } From 5badda810f69fea219e805a661d50815288b372b Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Wed, 6 Jul 2022 17:08:22 +0530 Subject: [PATCH 0887/4345] iommu/amd: Add PCI segment support for ivrs_[ioapic/hpet/acpihid] commands [ Upstream commit bbe3a106580c21bc883fb0c9fa3da01534392fe8 ] By default, PCI segment is zero and can be omitted. To support system with non-zero PCI segment ID, modify the parsing functions to allow PCI segment ID. Co-developed-by: Vasant Hegde Signed-off-by: Vasant Hegde Signed-off-by: Suravee Suthikulpanit Link: https://lore.kernel.org/r/20220706113825.25582-33-vasant.hegde@amd.com Signed-off-by: Joerg Roedel Stable-dep-of: 1198d2316dc4 ("iommu/amd: Fix ill-formed ivrs_ioapic, ivrs_hpet and ivrs_acpihid options") Signed-off-by: Sasha Levin --- .../admin-guide/kernel-parameters.txt | 34 ++++++++++---- drivers/iommu/amd/init.c | 44 ++++++++++++------- 2 files changed, 52 insertions(+), 26 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f577c29f2093..ce93bb358bc1 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2103,23 +2103,39 @@ ivrs_ioapic [HW,X86-64] Provide an override to the IOAPIC-ID<->DEVICE-ID - mapping provided in the IVRS ACPI table. For - example, to map IOAPIC-ID decimal 10 to - PCI device 00:14.0 write the parameter as: + mapping provided in the IVRS ACPI table. + By default, PCI segment is 0, and can be omitted. + For example: + * To map IOAPIC-ID decimal 10 to PCI device 00:14.0 + write the parameter as: ivrs_ioapic[10]=00:14.0 + * To map IOAPIC-ID decimal 10 to PCI segment 0x1 and + PCI device 00:14.0 write the parameter as: + ivrs_ioapic[10]=0001:00:14.0 ivrs_hpet [HW,X86-64] Provide an override to the HPET-ID<->DEVICE-ID - mapping provided in the IVRS ACPI table. For - example, to map HPET-ID decimal 0 to - PCI device 00:14.0 write the parameter as: + mapping provided in the IVRS ACPI table. + By default, PCI segment is 0, and can be omitted. + For example: + * To map HPET-ID decimal 0 to PCI device 00:14.0 + write the parameter as: ivrs_hpet[0]=00:14.0 + * To map HPET-ID decimal 10 to PCI segment 0x1 and + PCI device 00:14.0 write the parameter as: + ivrs_ioapic[10]=0001:00:14.0 ivrs_acpihid [HW,X86-64] Provide an override to the ACPI-HID:UID<->DEVICE-ID - mapping provided in the IVRS ACPI table. For - example, to map UART-HID:UID AMD0020:0 to - PCI device 00:14.5 write the parameter as: + mapping provided in the IVRS ACPI table. + + For example, to map UART-HID:UID AMD0020:0 to + PCI segment 0x1 and PCI device ID 00:14.5, + write the parameter as: + ivrs_acpihid[0001:00:14.5]=AMD0020:0 + + By default, PCI segment is 0, and can be omitted. + For example, PCI device 00:14.5 write the parameter as: ivrs_acpihid[00:14.5]=AMD0020:0 js= [HW,JOY] Analog joystick diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 310ab24d003a..85370f305aa8 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -85,6 +85,10 @@ #define ACPI_DEVFLAG_ATSDIS 0x10000000 #define LOOP_TIMEOUT 2000000 + +#define IVRS_GET_SBDF_ID(seg, bus, dev, fd) (((seg & 0xffff) << 16) | ((bus & 0xff) << 8) \ + | ((dev & 0x1f) << 3) | (fn & 0x7)) + /* * ACPI table definitions * @@ -3046,15 +3050,17 @@ static int __init parse_amd_iommu_options(char *str) static int __init parse_ivrs_ioapic(char *str) { - unsigned int bus, dev, fn; + u32 seg = 0, bus, dev, fn; int ret, id, i; - u16 devid; + u32 devid; ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn); - if (ret != 4) { - pr_err("Invalid command line: ivrs_ioapic%s\n", str); - return 1; + ret = sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn); + if (ret != 5) { + pr_err("Invalid command line: ivrs_ioapic%s\n", str); + return 1; + } } if (early_ioapic_map_size == EARLY_MAP_SIZE) { @@ -3063,7 +3069,7 @@ static int __init parse_ivrs_ioapic(char *str) return 1; } - devid = ((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7); + devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn); cmdline_maps = true; i = early_ioapic_map_size++; @@ -3076,15 +3082,17 @@ static int __init parse_ivrs_ioapic(char *str) static int __init parse_ivrs_hpet(char *str) { - unsigned int bus, dev, fn; + u32 seg = 0, bus, dev, fn; int ret, id, i; - u16 devid; + u32 devid; ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn); - if (ret != 4) { - pr_err("Invalid command line: ivrs_hpet%s\n", str); - return 1; + ret = sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn); + if (ret != 5) { + pr_err("Invalid command line: ivrs_hpet%s\n", str); + return 1; + } } if (early_hpet_map_size == EARLY_MAP_SIZE) { @@ -3093,7 +3101,7 @@ static int __init parse_ivrs_hpet(char *str) return 1; } - devid = ((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7); + devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn); cmdline_maps = true; i = early_hpet_map_size++; @@ -3106,15 +3114,18 @@ static int __init parse_ivrs_hpet(char *str) static int __init parse_ivrs_acpihid(char *str) { - u32 bus, dev, fn; + u32 seg = 0, bus, dev, fn; char *hid, *uid, *p; char acpiid[ACPIHID_UID_LEN + ACPIHID_HID_LEN] = {0}; int ret, i; ret = sscanf(str, "[%x:%x.%x]=%s", &bus, &dev, &fn, acpiid); if (ret != 4) { - pr_err("Invalid command line: ivrs_acpihid(%s)\n", str); - return 1; + ret = sscanf(str, "[%x:%x:%x.%x]=%s", &seg, &bus, &dev, &fn, acpiid); + if (ret != 5) { + pr_err("Invalid command line: ivrs_acpihid(%s)\n", str); + return 1; + } } p = acpiid; @@ -3136,8 +3147,7 @@ static int __init parse_ivrs_acpihid(char *str) i = early_acpihid_map_size++; memcpy(early_acpihid_map[i].hid, hid, strlen(hid)); memcpy(early_acpihid_map[i].uid, uid, strlen(uid)); - early_acpihid_map[i].devid = - ((bus & 0xff) << 8) | ((dev & 0x1f) << 3) | (fn & 0x7); + early_acpihid_map[i].devid = IVRS_GET_SBDF_ID(seg, bus, dev, fn); early_acpihid_map[i].cmd_line = true; return 1; From 6b21077146c533404078204c0e90fd2a0c0bab8d Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Mon, 19 Sep 2022 10:56:38 -0500 Subject: [PATCH 0888/4345] iommu/amd: Fix ill-formed ivrs_ioapic, ivrs_hpet and ivrs_acpihid options [ Upstream commit 1198d2316dc4265a97d0e8445a22c7a6d17580a4 ] Currently, these options cause the following libkmod error: libkmod: ERROR ../libkmod/libkmod-config.c:489 kcmdline_parse_result: \ Ignoring bad option on kernel command line while parsing module \ name: 'ivrs_xxxx[XX:XX' Fix by introducing a new parameter format for these options and throw a warning for the deprecated format. Users are still allowed to omit the PCI Segment if zero. Adding a Link: to the reason why we're modding the syntax parsing in the driver and not in libkmod. Fixes: ca3bf5d47cec ("iommu/amd: Introduces ivrs_acpihid kernel parameter") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-modules/20200310082308.14318-2-lucas.demarchi@intel.com/ Reported-by: Kim Phillips Co-developed-by: Suravee Suthikulpanit Signed-off-by: Suravee Suthikulpanit Signed-off-by: Kim Phillips Link: https://lore.kernel.org/r/20220919155638.391481-2-kim.phillips@amd.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- .../admin-guide/kernel-parameters.txt | 27 +++++-- drivers/iommu/amd/init.c | 77 +++++++++++++------ 2 files changed, 75 insertions(+), 29 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index ce93bb358bc1..eb437d659f2c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2105,7 +2105,13 @@ Provide an override to the IOAPIC-ID<->DEVICE-ID mapping provided in the IVRS ACPI table. By default, PCI segment is 0, and can be omitted. - For example: + + For example, to map IOAPIC-ID decimal 10 to + PCI segment 0x1 and PCI device 00:14.0, + write the parameter as: + ivrs_ioapic=10@0001:00:14.0 + + Deprecated formats: * To map IOAPIC-ID decimal 10 to PCI device 00:14.0 write the parameter as: ivrs_ioapic[10]=00:14.0 @@ -2117,7 +2123,13 @@ Provide an override to the HPET-ID<->DEVICE-ID mapping provided in the IVRS ACPI table. By default, PCI segment is 0, and can be omitted. - For example: + + For example, to map HPET-ID decimal 10 to + PCI segment 0x1 and PCI device 00:14.0, + write the parameter as: + ivrs_hpet=10@0001:00:14.0 + + Deprecated formats: * To map HPET-ID decimal 0 to PCI device 00:14.0 write the parameter as: ivrs_hpet[0]=00:14.0 @@ -2128,15 +2140,20 @@ ivrs_acpihid [HW,X86-64] Provide an override to the ACPI-HID:UID<->DEVICE-ID mapping provided in the IVRS ACPI table. + By default, PCI segment is 0, and can be omitted. For example, to map UART-HID:UID AMD0020:0 to PCI segment 0x1 and PCI device ID 00:14.5, write the parameter as: - ivrs_acpihid[0001:00:14.5]=AMD0020:0 + ivrs_acpihid=AMD0020:0@0001:00:14.5 - By default, PCI segment is 0, and can be omitted. - For example, PCI device 00:14.5 write the parameter as: + Deprecated formats: + * To map UART-HID:UID AMD0020:0 to PCI segment is 0, + PCI device ID 00:14.5, write the parameter as: ivrs_acpihid[00:14.5]=AMD0020:0 + * To map UART-HID:UID AMD0020:0 to PCI segment 0x1 and + PCI device ID 00:14.5, write the parameter as: + ivrs_acpihid[0001:00:14.5]=AMD0020:0 js= [HW,JOY] Analog joystick See Documentation/input/joydev/joystick.rst. diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 85370f305aa8..ce822347f747 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3051,18 +3051,24 @@ static int __init parse_amd_iommu_options(char *str) static int __init parse_ivrs_ioapic(char *str) { u32 seg = 0, bus, dev, fn; - int ret, id, i; + int id, i; u32 devid; - ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn); - if (ret != 4) { - ret = sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn); - if (ret != 5) { - pr_err("Invalid command line: ivrs_ioapic%s\n", str); - return 1; - } + if (sscanf(str, "=%d@%x:%x.%x", &id, &bus, &dev, &fn) == 4 || + sscanf(str, "=%d@%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) + goto found; + + if (sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn) == 4 || + sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) { + pr_warn("ivrs_ioapic%s option format deprecated; use ivrs_ioapic=%d@%04x:%02x:%02x.%d instead\n", + str, id, seg, bus, dev, fn); + goto found; } + pr_err("Invalid command line: ivrs_ioapic%s\n", str); + return 1; + +found: if (early_ioapic_map_size == EARLY_MAP_SIZE) { pr_err("Early IOAPIC map overflow - ignoring ivrs_ioapic%s\n", str); @@ -3083,18 +3089,24 @@ static int __init parse_ivrs_ioapic(char *str) static int __init parse_ivrs_hpet(char *str) { u32 seg = 0, bus, dev, fn; - int ret, id, i; + int id, i; u32 devid; - ret = sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn); - if (ret != 4) { - ret = sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn); - if (ret != 5) { - pr_err("Invalid command line: ivrs_hpet%s\n", str); - return 1; - } + if (sscanf(str, "=%d@%x:%x.%x", &id, &bus, &dev, &fn) == 4 || + sscanf(str, "=%d@%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) + goto found; + + if (sscanf(str, "[%d]=%x:%x.%x", &id, &bus, &dev, &fn) == 4 || + sscanf(str, "[%d]=%x:%x:%x.%x", &id, &seg, &bus, &dev, &fn) == 5) { + pr_warn("ivrs_hpet%s option format deprecated; use ivrs_hpet=%d@%04x:%02x:%02x.%d instead\n", + str, id, seg, bus, dev, fn); + goto found; } + pr_err("Invalid command line: ivrs_hpet%s\n", str); + return 1; + +found: if (early_hpet_map_size == EARLY_MAP_SIZE) { pr_err("Early HPET map overflow - ignoring ivrs_hpet%s\n", str); @@ -3115,19 +3127,36 @@ static int __init parse_ivrs_hpet(char *str) static int __init parse_ivrs_acpihid(char *str) { u32 seg = 0, bus, dev, fn; - char *hid, *uid, *p; + char *hid, *uid, *p, *addr; char acpiid[ACPIHID_UID_LEN + ACPIHID_HID_LEN] = {0}; - int ret, i; + int i; - ret = sscanf(str, "[%x:%x.%x]=%s", &bus, &dev, &fn, acpiid); - if (ret != 4) { - ret = sscanf(str, "[%x:%x:%x.%x]=%s", &seg, &bus, &dev, &fn, acpiid); - if (ret != 5) { - pr_err("Invalid command line: ivrs_acpihid(%s)\n", str); - return 1; + addr = strchr(str, '@'); + if (!addr) { + if (sscanf(str, "[%x:%x.%x]=%s", &bus, &dev, &fn, acpiid) == 4 || + sscanf(str, "[%x:%x:%x.%x]=%s", &seg, &bus, &dev, &fn, acpiid) == 5) { + pr_warn("ivrs_acpihid%s option format deprecated; use ivrs_acpihid=%s@%04x:%02x:%02x.%d instead\n", + str, acpiid, seg, bus, dev, fn); + goto found; } + goto not_found; } + /* We have the '@', make it the terminator to get just the acpiid */ + *addr++ = 0; + + if (sscanf(str, "=%s", acpiid) != 1) + goto not_found; + + if (sscanf(addr, "%x:%x.%x", &bus, &dev, &fn) == 3 || + sscanf(addr, "%x:%x:%x.%x", &seg, &bus, &dev, &fn) == 4) + goto found; + +not_found: + pr_err("Invalid command line: ivrs_acpihid%s\n", str); + return 1; + +found: p = acpiid; hid = strsep(&p, ":"); uid = p; From 85eaaa17c0a968b5a51948b1ac8368fe29c3c95b Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 13 Mar 2022 13:39:49 +0100 Subject: [PATCH 0889/4345] clk: imx8mp: Add DISP2 pixel clock [ Upstream commit 39772efd98adecbd5b8c6096d465d2fcbafbde6a ] Add pixel clock for second LCDIFv3 interface. Both LCDIFv3 interfaces use the same set of parent clock, so deduplicate imx8mp_media_disp1_pix_sels into common imx8mp_media_disp_pix_sels and use it for both. Signed-off-by: Marek Vasut Cc: Abel Vesa Cc: Fabio Estevam Cc: NXP Linux Team Cc: Peng Fan Cc: Shawn Guo Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20220313123949.207284-1-marex@denx.de Signed-off-by: Abel Vesa Stable-dep-of: 5c1f7f109094 ("dt-bindings: clocks: imx8mp: Add ID for usb suspend clock") Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx8mp.c | 5 +++-- include/dt-bindings/clock/imx8mp-clock.h | 4 +++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 36e8d619e334..2af39c8240fa 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -362,7 +362,7 @@ static const char * const imx8mp_media_mipi_phy1_ref_sels[] = {"osc_24m", "sys_p "clk_ext2", "audio_pll2_out", "video_pll1_out", }; -static const char * const imx8mp_media_disp1_pix_sels[] = {"osc_24m", "video_pll1_out", "audio_pll2_out", +static const char * const imx8mp_media_disp_pix_sels[] = {"osc_24m", "video_pll1_out", "audio_pll2_out", "audio_pll1_out", "sys_pll1_800m", "sys_pll2_1000m", "sys_pll3_out", "clk_ext4", }; @@ -566,6 +566,7 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000); hws[IMX8MP_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mp_audio_ahb_sels, ccm_base + 0x9100); hws[IMX8MP_CLK_MIPI_DSI_ESC_RX] = imx8m_clk_hw_composite_bus("mipi_dsi_esc_rx", imx8mp_mipi_dsi_esc_rx_sels, ccm_base + 0x9200); + hws[IMX8MP_CLK_MEDIA_DISP2_PIX] = imx8m_clk_hw_composite("media_disp2_pix", imx8mp_media_disp_pix_sels, ccm_base + 0x9300); hws[IMX8MP_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb_root", ccm_base + 0x9080, 0, 1); hws[IMX8MP_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", ccm_base + 0x9180, 0, 1); @@ -630,7 +631,7 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_USDHC3] = imx8m_clk_hw_composite("usdhc3", imx8mp_usdhc3_sels, ccm_base + 0xbc80); hws[IMX8MP_CLK_MEDIA_CAM1_PIX] = imx8m_clk_hw_composite("media_cam1_pix", imx8mp_media_cam1_pix_sels, ccm_base + 0xbd00); hws[IMX8MP_CLK_MEDIA_MIPI_PHY1_REF] = imx8m_clk_hw_composite("media_mipi_phy1_ref", imx8mp_media_mipi_phy1_ref_sels, ccm_base + 0xbd80); - hws[IMX8MP_CLK_MEDIA_DISP1_PIX] = imx8m_clk_hw_composite("media_disp1_pix", imx8mp_media_disp1_pix_sels, ccm_base + 0xbe00); + hws[IMX8MP_CLK_MEDIA_DISP1_PIX] = imx8m_clk_hw_composite("media_disp1_pix", imx8mp_media_disp_pix_sels, ccm_base + 0xbe00); hws[IMX8MP_CLK_MEDIA_CAM2_PIX] = imx8m_clk_hw_composite("media_cam2_pix", imx8mp_media_cam2_pix_sels, ccm_base + 0xbe80); hws[IMX8MP_CLK_MEDIA_LDB] = imx8m_clk_hw_composite("media_ldb", imx8mp_media_ldb_sels, ccm_base + 0xbf00); hws[IMX8MP_CLK_MEMREPAIR] = imx8m_clk_hw_composite_critical("mem_repair", imx8mp_memrepair_sels, ccm_base + 0xbf80); diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h index e8d68fbb6e3f..4a621fddfcd3 100644 --- a/include/dt-bindings/clock/imx8mp-clock.h +++ b/include/dt-bindings/clock/imx8mp-clock.h @@ -322,7 +322,9 @@ #define IMX8MP_CLK_HSIO_AXI 311 #define IMX8MP_CLK_MEDIA_ISP 312 -#define IMX8MP_CLK_END 313 +#define IMX8MP_CLK_MEDIA_DISP2_PIX 313 + +#define IMX8MP_CLK_END 314 #define IMX8MP_CLK_AUDIOMIX_SAI1_IPG 0 #define IMX8MP_CLK_AUDIOMIX_SAI1_MCLK1 1 From cb769960ef48fee1045bc8eca2ac0cf56d876b33 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Wed, 27 Apr 2022 18:21:31 +0200 Subject: [PATCH 0890/4345] clk: imx8mp: add clkout1/2 support [ Upstream commit 43896f56b59eeaf08687fa976257ae7083d01b41 ] clkout1 and clkout2 allow to supply clocks from the SoC to the board, which is used by some board designs to provide reference clocks. Signed-off-by: Lucas Stach Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20220427162131.3127303-1-l.stach@pengutronix.de Signed-off-by: Abel Vesa Stable-dep-of: 5c1f7f109094 ("dt-bindings: clocks: imx8mp: Add ID for usb suspend clock") Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx8mp.c | 14 ++++++++++++++ include/dt-bindings/clock/imx8mp-clock.h | 9 +++++++-- 2 files changed, 21 insertions(+), 2 deletions(-) diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 2af39c8240fa..187044b98bde 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -411,6 +411,11 @@ static const char * const imx8mp_sai7_sels[] = {"osc_24m", "audio_pll1_out", "au static const char * const imx8mp_dram_core_sels[] = {"dram_pll_out", "dram_alt_root", }; +static const char * const imx8mp_clkout_sels[] = {"audio_pll1_out", "audio_pll2_out", "video_pll1_out", + "dummy", "dummy", "gpu_pll_out", "vpu_pll_out", + "arm_pll_out", "sys_pll1", "sys_pll2", "sys_pll3", + "dummy", "dummy", "osc_24m", "dummy", "osc_32k"}; + static struct clk_hw **hws; static struct clk_hw_onecell_data *clk_hw_data; @@ -532,6 +537,15 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_SYS_PLL2_500M] = imx_clk_hw_fixed_factor("sys_pll2_500m", "sys_pll2_500m_cg", 1, 2); hws[IMX8MP_SYS_PLL2_1000M] = imx_clk_hw_fixed_factor("sys_pll2_1000m", "sys_pll2_out", 1, 1); + hws[IMX8MP_CLK_CLKOUT1_SEL] = imx_clk_hw_mux2("clkout1_sel", anatop_base + 0x128, 4, 4, + imx8mp_clkout_sels, ARRAY_SIZE(imx8mp_clkout_sels)); + hws[IMX8MP_CLK_CLKOUT1_DIV] = imx_clk_hw_divider("clkout1_div", "clkout1_sel", anatop_base + 0x128, 0, 4); + hws[IMX8MP_CLK_CLKOUT1] = imx_clk_hw_gate("clkout1", "clkout1_div", anatop_base + 0x128, 8); + hws[IMX8MP_CLK_CLKOUT2_SEL] = imx_clk_hw_mux2("clkout2_sel", anatop_base + 0x128, 20, 4, + imx8mp_clkout_sels, ARRAY_SIZE(imx8mp_clkout_sels)); + hws[IMX8MP_CLK_CLKOUT2_DIV] = imx_clk_hw_divider("clkout2_div", "clkout2_sel", anatop_base + 0x128, 16, 4); + hws[IMX8MP_CLK_CLKOUT2] = imx_clk_hw_gate("clkout2", "clkout2_div", anatop_base + 0x128, 24); + hws[IMX8MP_CLK_A53_DIV] = imx8m_clk_hw_composite_core("arm_a53_div", imx8mp_a53_sels, ccm_base + 0x8000); hws[IMX8MP_CLK_A53_SRC] = hws[IMX8MP_CLK_A53_DIV]; hws[IMX8MP_CLK_A53_CG] = hws[IMX8MP_CLK_A53_DIV]; diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h index 4a621fddfcd3..0ba16b76eb2f 100644 --- a/include/dt-bindings/clock/imx8mp-clock.h +++ b/include/dt-bindings/clock/imx8mp-clock.h @@ -321,10 +321,15 @@ #define IMX8MP_CLK_AUDIO_AXI 310 #define IMX8MP_CLK_HSIO_AXI 311 #define IMX8MP_CLK_MEDIA_ISP 312 - #define IMX8MP_CLK_MEDIA_DISP2_PIX 313 +#define IMX8MP_CLK_CLKOUT1_SEL 314 +#define IMX8MP_CLK_CLKOUT1_DIV 315 +#define IMX8MP_CLK_CLKOUT1 316 +#define IMX8MP_CLK_CLKOUT2_SEL 317 +#define IMX8MP_CLK_CLKOUT2_DIV 318 +#define IMX8MP_CLK_CLKOUT2 319 -#define IMX8MP_CLK_END 314 +#define IMX8MP_CLK_END 320 #define IMX8MP_CLK_AUDIOMIX_SAI1_IPG 0 #define IMX8MP_CLK_AUDIOMIX_SAI1_MCLK1 1 From 2b331d2137cc8d49c0893aa3c620ccf8b19be364 Mon Sep 17 00:00:00 2001 From: Li Jun Date: Fri, 30 Sep 2022 22:54:21 +0800 Subject: [PATCH 0891/4345] dt-bindings: clocks: imx8mp: Add ID for usb suspend clock [ Upstream commit 5c1f7f1090947d494c30042123e0ec846f696336 ] usb suspend clock has a gate shared with usb_root_clk. Fixes: 9c140d9926761 ("clk: imx: Add support for i.MX8MP clock driver") Cc: stable@vger.kernel.org # v5.19+ Acked-by: Krzysztof Kozlowski Tested-by: Alexander Stein Signed-off-by: Li Jun Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/1664549663-20364-1-git-send-email-jun.li@nxp.com Signed-off-by: Sasha Levin --- include/dt-bindings/clock/imx8mp-clock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h index 0ba16b76eb2f..d7e513243dd2 100644 --- a/include/dt-bindings/clock/imx8mp-clock.h +++ b/include/dt-bindings/clock/imx8mp-clock.h @@ -328,8 +328,9 @@ #define IMX8MP_CLK_CLKOUT2_SEL 317 #define IMX8MP_CLK_CLKOUT2_DIV 318 #define IMX8MP_CLK_CLKOUT2 319 +#define IMX8MP_CLK_USB_SUSP 320 -#define IMX8MP_CLK_END 320 +#define IMX8MP_CLK_END 321 #define IMX8MP_CLK_AUDIOMIX_SAI1_IPG 0 #define IMX8MP_CLK_AUDIOMIX_SAI1_MCLK1 1 From ba20d6056b6bc72274d772c95ff875776072911d Mon Sep 17 00:00:00 2001 From: Li Jun Date: Fri, 30 Sep 2022 22:54:22 +0800 Subject: [PATCH 0892/4345] clk: imx: imx8mp: add shared clk gate for usb suspend clk [ Upstream commit ed1f4ccfe947a3e1018a3bd7325134574c7ff9b3 ] 32K usb suspend clock gate is shared with usb_root_clk, this shared clock gate was initially defined only for usb suspend clock, usb suspend clk is kept on while system is active or system sleep with usb wakeup enabled, so usb root clock is fine with this situation; with the commit cf7f3f4fa9e5 ("clk: imx8mp: fix usb_root_clk parent"), this clock gate is changed to be for usb root clock, but usb root clock will be off while usb is suspended, so usb suspend clock will be gated too, this cause some usb functionalities will not work, so define this clock to be a shared clock gate to conform with the real HW status. Fixes: 9c140d9926761 ("clk: imx: Add support for i.MX8MP clock driver") Cc: stable@vger.kernel.org # v5.19+ Tested-by: Alexander Stein Signed-off-by: Li Jun Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/1664549663-20364-2-git-send-email-jun.li@nxp.com Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx8mp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 187044b98bde..72592e35836b 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -17,6 +17,7 @@ static u32 share_count_nand; static u32 share_count_media; +static u32 share_count_usb; static const char * const pll_ref_sels[] = { "osc_24m", "dummy", "dummy", "dummy", }; static const char * const audio_pll1_bypass_sels[] = {"audio_pll1", "audio_pll1_ref_sel", }; @@ -706,7 +707,8 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_UART2_ROOT] = imx_clk_hw_gate4("uart2_root_clk", "uart2", ccm_base + 0x44a0, 0); hws[IMX8MP_CLK_UART3_ROOT] = imx_clk_hw_gate4("uart3_root_clk", "uart3", ccm_base + 0x44b0, 0); hws[IMX8MP_CLK_UART4_ROOT] = imx_clk_hw_gate4("uart4_root_clk", "uart4", ccm_base + 0x44c0, 0); - hws[IMX8MP_CLK_USB_ROOT] = imx_clk_hw_gate4("usb_root_clk", "hsio_axi", ccm_base + 0x44d0, 0); + hws[IMX8MP_CLK_USB_ROOT] = imx_clk_hw_gate2_shared2("usb_root_clk", "hsio_axi", ccm_base + 0x44d0, 0, &share_count_usb); + hws[IMX8MP_CLK_USB_SUSP] = imx_clk_hw_gate2_shared2("usb_suspend_clk", "osc_32k", ccm_base + 0x44d0, 0, &share_count_usb); hws[IMX8MP_CLK_USB_PHY_ROOT] = imx_clk_hw_gate4("usb_phy_root_clk", "usb_phy_ref", ccm_base + 0x44f0, 0); hws[IMX8MP_CLK_USDHC1_ROOT] = imx_clk_hw_gate4("usdhc1_root_clk", "usdhc1", ccm_base + 0x4510, 0); hws[IMX8MP_CLK_USDHC2_ROOT] = imx_clk_hw_gate4("usdhc2_root_clk", "usdhc2", ccm_base + 0x4520, 0); From a81ace065694f3011f6f1247cbabaa095f574856 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 29 Jan 2021 15:00:18 +0200 Subject: [PATCH 0893/4345] xhci: Avoid parsing transfer events several times [ Upstream commit ab58f3bb6aaaf98ba81d5c627ac25c08ff4ed4f1 ] When handling transfer events the event is passed along the handling callpath and parsed again in several occasions. The event contains slot_id and endpoint index, from which the driver endpoint structure can be found. There wasn't however a way to get the endpoint index or parent usb device from this endpoint structure. A lot of extra event parsing, and thus some DMA doublefetch cases, and excess variables and code can be avoided by adding endpoint index and parent usb virt device pointer to the endpoint structure. Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20210129130044.206855-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: a1575120972e ("xhci: Prevent infinite loop in transaction errors recovery for streams") Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-mem.c | 2 ++ drivers/usb/host/xhci-ring.c | 28 ++++++++-------------------- drivers/usb/host/xhci.h | 2 ++ 3 files changed, 12 insertions(+), 20 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index d1a42300ae58..002e4948993d 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1021,6 +1021,8 @@ int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, /* Initialize the cancellation list and watchdog timers for each ep */ for (i = 0; i < 31; i++) { + dev->eps[i].ep_index = i; + dev->eps[i].vdev = dev; xhci_init_endpoint_timer(xhci, &dev->eps[i]); INIT_LIST_HEAD(&dev->eps[i].cancelled_td_list); INIT_LIST_HEAD(&dev->eps[i].bw_endpoint_list); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index fa3a7ac15f82..5cee7150376d 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1936,7 +1936,7 @@ static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci, * Avoid resetting endpoint if link is inactive. Can cause host hang. * Device will be reset soon to recover the link so don't do anything */ - if (xhci->devs[slot_id]->flags & VDEV_PORT_ERROR) + if (ep->vdev->flags & VDEV_PORT_ERROR) return; command = xhci_alloc_command(xhci, false, GFP_ATOMIC); @@ -2045,18 +2045,14 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, struct xhci_transfer_event *event, struct xhci_virt_ep *ep, int *status) { - struct xhci_virt_device *xdev; struct xhci_ep_ctx *ep_ctx; struct xhci_ring *ep_ring; unsigned int slot_id; u32 trb_comp_code; - int ep_index; slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags)); - xdev = xhci->devs[slot_id]; - ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1; ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer)); - ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index); + ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len)); if (trb_comp_code == COMP_STOPPED_LENGTH_INVALID || @@ -2081,9 +2077,9 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, * stall later. Hub TT buffer should only be cleared for FS/LS * devices behind HS hubs for functional stalls. */ - if ((ep_index != 0) || (trb_comp_code != COMP_STALL_ERROR)) + if ((ep->ep_index != 0) || (trb_comp_code != COMP_STALL_ERROR)) xhci_clear_hub_tt_buffer(xhci, td, ep); - xhci_cleanup_halted_endpoint(xhci, slot_id, ep_index, + xhci_cleanup_halted_endpoint(xhci, slot_id, ep->ep_index, ep_ring->stream_id, td, EP_HARD_RESET); } else { /* Update ring dequeue pointer */ @@ -2117,19 +2113,13 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, union xhci_trb *ep_trb, struct xhci_transfer_event *event, struct xhci_virt_ep *ep, int *status) { - struct xhci_virt_device *xdev; - unsigned int slot_id; - int ep_index; struct xhci_ep_ctx *ep_ctx; u32 trb_comp_code; u32 remaining, requested; u32 trb_type; trb_type = TRB_FIELD_TO_TYPE(le32_to_cpu(ep_trb->generic.field[3])); - slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags)); - xdev = xhci->devs[slot_id]; - ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1; - ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index); + ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len)); requested = td->urb->transfer_buffer_length; remaining = EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)); @@ -2177,7 +2167,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, ep_ctx, trb_comp_code)) break; xhci_dbg(xhci, "TRB error %u, halted endpoint index = %u\n", - trb_comp_code, ep_index); + trb_comp_code, ep->ep_index); fallthrough; case COMP_STALL_ERROR: /* Did we transfer part of the data (middle) phase? */ @@ -2339,11 +2329,9 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, u32 trb_comp_code; u32 remaining, requested, ep_trb_len; unsigned int slot_id; - int ep_index; slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags)); - slot_ctx = xhci_get_slot_ctx(xhci, xhci->devs[slot_id]->out_ctx); - ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1; + slot_ctx = xhci_get_slot_ctx(xhci, ep->vdev->out_ctx); ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer)); trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len)); remaining = EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)); @@ -2382,7 +2370,7 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, le32_to_cpu(slot_ctx->tt_info) & TT_SLOT) break; *status = 0; - xhci_cleanup_halted_endpoint(xhci, slot_id, ep_index, + xhci_cleanup_halted_endpoint(xhci, slot_id, ep->ep_index, ep_ring->stream_id, td, EP_SOFT_RESET); return 0; default: diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 059050f13522..5fbd159f6fa5 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -924,6 +924,8 @@ struct xhci_bw_info { #define SS_BW_RESERVED 10 struct xhci_virt_ep { + struct xhci_virt_device *vdev; /* parent */ + unsigned int ep_index; struct xhci_ring *ring; /* Related to endpoints that are configured to use stream IDs only */ struct xhci_stream_info *stream_info; From aaaa7cc4aba18dfe46415f4f2c738e861052f99b Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 29 Jan 2021 15:00:19 +0200 Subject: [PATCH 0894/4345] xhci: get isochronous ring directly from endpoint structure [ Upstream commit d4dff8043ea5b93a30cb9b19d4407bd506a6877a ] isochronous endpoints do not support streams, meaning that there is only one ring per endpoint. Avoid double-fetching the transfer event DMA to get the ring. Also makes passing the event to skip_isoc_td() uncecessary. Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20210129130044.206855-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: a1575120972e ("xhci: Prevent infinite loop in transaction errors recovery for streams") Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-ring.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 5cee7150376d..6d34c56376e5 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2209,7 +2209,6 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, union xhci_trb *ep_trb, struct xhci_transfer_event *event, struct xhci_virt_ep *ep, int *status) { - struct xhci_ring *ep_ring; struct urb_priv *urb_priv; int idx; struct usb_iso_packet_descriptor *frame; @@ -2218,7 +2217,6 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, u32 remaining, requested, ep_trb_len; int short_framestatus; - ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer)); trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len)); urb_priv = td->urb->hcpriv; idx = urb_priv->num_tds_done; @@ -2279,7 +2277,7 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, } if (sum_trbs_for_length) - frame->actual_length = sum_trb_lengths(xhci, ep_ring, ep_trb) + + frame->actual_length = sum_trb_lengths(xhci, ep->ring, ep_trb) + ep_trb_len - remaining; else frame->actual_length = requested; @@ -2290,15 +2288,12 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, } static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, - struct xhci_transfer_event *event, struct xhci_virt_ep *ep, int *status) { - struct xhci_ring *ep_ring; struct urb_priv *urb_priv; struct usb_iso_packet_descriptor *frame; int idx; - ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer)); urb_priv = td->urb->hcpriv; idx = urb_priv->num_tds_done; frame = &td->urb->iso_frame_desc[idx]; @@ -2310,11 +2305,11 @@ static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, frame->actual_length = 0; /* Update ring dequeue pointer */ - while (ep_ring->dequeue != td->last_trb) - inc_deq(xhci, ep_ring); - inc_deq(xhci, ep_ring); + while (ep->ring->dequeue != td->last_trb) + inc_deq(xhci, ep->ring); + inc_deq(xhci, ep->ring); - return xhci_td_cleanup(xhci, td, ep_ring, status); + return xhci_td_cleanup(xhci, td, ep->ring, status); } /* @@ -2693,7 +2688,7 @@ static int handle_tx_event(struct xhci_hcd *xhci, return -ESHUTDOWN; } - skip_isoc_td(xhci, td, event, ep, &status); + skip_isoc_td(xhci, td, ep, &status); goto cleanup; } if (trb_comp_code == COMP_SHORT_PACKET) From 10287d18f524d00043b82e6ee08d49438dcb53b7 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 29 Jan 2021 15:00:20 +0200 Subject: [PATCH 0895/4345] xhci: adjust parameters passed to cleanup_halted_endpoint() [ Upstream commit d70f4231b81eeb6dd78bd913ff42729b524eec51 ] Instead of passing slot id and endpoint index to cleanup_halted_endpoint() pass the endpoint structure pointer as it's already known. Avoids again digging out the endpoint structure based on slot id and endpoint index, and passing them along the call chain for this purpose only. Add slot_id to the virt_dev structure so that it can easily be found from a virt_dev, or its child, the virt_ep endpoint structure. Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20210129130044.206855-4-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: a1575120972e ("xhci: Prevent infinite loop in transaction errors recovery for streams") Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-mem.c | 2 ++ drivers/usb/host/xhci-ring.c | 35 ++++++++++++++--------------------- drivers/usb/host/xhci.h | 1 + 3 files changed, 17 insertions(+), 21 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 002e4948993d..a8a9addb4d25 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1003,6 +1003,8 @@ int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, if (!dev) return 0; + dev->slot_id = slot_id; + /* Allocate the (output) device context that will be used in the HC. */ dev->out_ctx = xhci_alloc_container_ctx(xhci, XHCI_CTX_TYPE_DEVICE, flags); if (!dev->out_ctx) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 6d34c56376e5..a0d210d3a3c6 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1925,13 +1925,12 @@ static void xhci_clear_hub_tt_buffer(struct xhci_hcd *xhci, struct xhci_td *td, } static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci, - unsigned int slot_id, unsigned int ep_index, - unsigned int stream_id, struct xhci_td *td, - enum xhci_ep_reset_type reset_type) + struct xhci_virt_ep *ep, unsigned int stream_id, + struct xhci_td *td, + enum xhci_ep_reset_type reset_type) { - struct xhci_virt_ep *ep = &xhci->devs[slot_id]->eps[ep_index]; struct xhci_command *command; - + unsigned int slot_id = ep->vdev->slot_id; /* * Avoid resetting endpoint if link is inactive. Can cause host hang. * Device will be reset soon to recover the link so don't do anything @@ -1945,11 +1944,11 @@ static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci, ep->ep_state |= EP_HALTED; - xhci_queue_reset_ep(xhci, command, slot_id, ep_index, reset_type); + xhci_queue_reset_ep(xhci, command, slot_id, ep->ep_index, reset_type); if (reset_type == EP_HARD_RESET) { ep->ep_state |= EP_HARD_CLEAR_TOGGLE; - xhci_cleanup_stalled_ring(xhci, slot_id, ep_index, stream_id, + xhci_cleanup_stalled_ring(xhci, slot_id, ep->ep_index, stream_id, td); } xhci_ring_cmd_db(xhci); @@ -2047,10 +2046,8 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, { struct xhci_ep_ctx *ep_ctx; struct xhci_ring *ep_ring; - unsigned int slot_id; u32 trb_comp_code; - slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags)); ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer)); ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len)); @@ -2079,8 +2076,8 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, */ if ((ep->ep_index != 0) || (trb_comp_code != COMP_STALL_ERROR)) xhci_clear_hub_tt_buffer(xhci, td, ep); - xhci_cleanup_halted_endpoint(xhci, slot_id, ep->ep_index, - ep_ring->stream_id, td, EP_HARD_RESET); + xhci_cleanup_halted_endpoint(xhci, ep, ep_ring->stream_id, td, + EP_HARD_RESET); } else { /* Update ring dequeue pointer */ while (ep_ring->dequeue != td->last_trb) @@ -2323,9 +2320,7 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, struct xhci_ring *ep_ring; u32 trb_comp_code; u32 remaining, requested, ep_trb_len; - unsigned int slot_id; - slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags)); slot_ctx = xhci_get_slot_ctx(xhci, ep->vdev->out_ctx); ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer)); trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len)); @@ -2365,8 +2360,8 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, le32_to_cpu(slot_ctx->tt_info) & TT_SLOT) break; *status = 0; - xhci_cleanup_halted_endpoint(xhci, slot_id, ep->ep_index, - ep_ring->stream_id, td, EP_SOFT_RESET); + xhci_cleanup_halted_endpoint(xhci, ep, ep_ring->stream_id, td, + EP_SOFT_RESET); return 0; default: /* do nothing */ @@ -2441,8 +2436,8 @@ static int handle_tx_event(struct xhci_hcd *xhci, case COMP_USB_TRANSACTION_ERROR: case COMP_INVALID_STREAM_TYPE_ERROR: case COMP_INVALID_STREAM_ID_ERROR: - xhci_cleanup_halted_endpoint(xhci, slot_id, ep_index, 0, - NULL, EP_SOFT_RESET); + xhci_cleanup_halted_endpoint(xhci, ep, 0, NULL, + EP_SOFT_RESET); goto cleanup; case COMP_RING_UNDERRUN: case COMP_RING_OVERRUN: @@ -2625,8 +2620,7 @@ static int handle_tx_event(struct xhci_hcd *xhci, if (trb_comp_code == COMP_STALL_ERROR || xhci_requires_manual_halt_cleanup(xhci, ep_ctx, trb_comp_code)) { - xhci_cleanup_halted_endpoint(xhci, slot_id, - ep_index, + xhci_cleanup_halted_endpoint(xhci, ep, ep_ring->stream_id, NULL, EP_HARD_RESET); @@ -2720,8 +2714,7 @@ static int handle_tx_event(struct xhci_hcd *xhci, if (trb_comp_code == COMP_STALL_ERROR || xhci_requires_manual_halt_cleanup(xhci, ep_ctx, trb_comp_code)) - xhci_cleanup_halted_endpoint(xhci, slot_id, - ep_index, + xhci_cleanup_halted_endpoint(xhci, ep, ep_ring->stream_id, td, EP_HARD_RESET); goto cleanup; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 5fbd159f6fa5..9cbf106fb3ee 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1004,6 +1004,7 @@ struct xhci_interval_bw_table { #define EP_CTX_PER_DEV 31 struct xhci_virt_device { + int slot_id; struct usb_device *udev; /* * Commands to the hardware are passed an "input context" that From 44c635c60f78a693b5e6ad80e18c7e9a97a0c4cd Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 29 Jan 2021 15:00:32 +0200 Subject: [PATCH 0896/4345] xhci: Add xhci_reset_halted_ep() helper function [ Upstream commit d8ac95001bea683d2088acb3e61613a27b8d2d5f ] Create a separate helper function to issue reset endpont commands to clear halted endpoints. This is useful for cases where a halted endpoint is discovered while completing another command, and the endpoint halt needs to be cleared with a endpoint reset first. No functional changes Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20210129130044.206855-16-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: a1575120972e ("xhci: Prevent infinite loop in transaction errors recovery for streams") Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-ring.c | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index a0d210d3a3c6..b4a510450ac2 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -773,6 +773,26 @@ static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci, seg->bounce_offs = 0; } +static int xhci_reset_halted_ep(struct xhci_hcd *xhci, unsigned int slot_id, + unsigned int ep_index, enum xhci_ep_reset_type reset_type) +{ + struct xhci_command *command; + int ret = 0; + + command = xhci_alloc_command(xhci, false, GFP_ATOMIC); + if (!command) { + ret = -ENOMEM; + goto done; + } + + ret = xhci_queue_reset_ep(xhci, command, slot_id, ep_index, reset_type); +done: + if (ret) + xhci_err(xhci, "ERROR queuing reset endpoint for slot %d ep_index %d, %d\n", + slot_id, ep_index, ret); + return ret; +} + /* * When we get a command completion for a Stop Endpoint Command, we need to * unlink any cancelled TDs from the ring. There are two ways to do that: @@ -1929,8 +1949,9 @@ static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci, struct xhci_td *td, enum xhci_ep_reset_type reset_type) { - struct xhci_command *command; unsigned int slot_id = ep->vdev->slot_id; + int err; + /* * Avoid resetting endpoint if link is inactive. Can cause host hang. * Device will be reset soon to recover the link so don't do anything @@ -1938,13 +1959,11 @@ static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci, if (ep->vdev->flags & VDEV_PORT_ERROR) return; - command = xhci_alloc_command(xhci, false, GFP_ATOMIC); - if (!command) - return; - ep->ep_state |= EP_HALTED; - xhci_queue_reset_ep(xhci, command, slot_id, ep->ep_index, reset_type); + err = xhci_reset_halted_ep(xhci, slot_id, ep->ep_index, reset_type); + if (err) + return; if (reset_type == EP_HARD_RESET) { ep->ep_state |= EP_HARD_CLEAR_TOGGLE; From 9b63a80c45e94b723d62dae59803c6286f6abcde Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 29 Jan 2021 15:00:33 +0200 Subject: [PATCH 0897/4345] xhci: move xhci_td_cleanup so it can be called by more functions [ Upstream commit 69eaf9e79fa7c7ff4b1eb626493ce5a81e467520 ] No funtional changes Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20210129130044.206855-17-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: a1575120972e ("xhci: Prevent infinite loop in transaction errors recovery for streams") Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-ring.c | 92 ++++++++++++++++++------------------ 1 file changed, 46 insertions(+), 46 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index b4a510450ac2..d523cbe7fcf1 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -773,6 +773,52 @@ static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci, seg->bounce_offs = 0; } +static int xhci_td_cleanup(struct xhci_hcd *xhci, struct xhci_td *td, + struct xhci_ring *ep_ring, int *status) +{ + struct urb *urb = NULL; + + /* Clean up the endpoint's TD list */ + urb = td->urb; + + /* if a bounce buffer was used to align this td then unmap it */ + xhci_unmap_td_bounce_buffer(xhci, ep_ring, td); + + /* Do one last check of the actual transfer length. + * If the host controller said we transferred more data than the buffer + * length, urb->actual_length will be a very big number (since it's + * unsigned). Play it safe and say we didn't transfer anything. + */ + if (urb->actual_length > urb->transfer_buffer_length) { + xhci_warn(xhci, "URB req %u and actual %u transfer length mismatch\n", + urb->transfer_buffer_length, urb->actual_length); + urb->actual_length = 0; + *status = 0; + } + list_del_init(&td->td_list); + /* Was this TD slated to be cancelled but completed anyway? */ + if (!list_empty(&td->cancelled_td_list)) + list_del_init(&td->cancelled_td_list); + + inc_td_cnt(urb); + /* Giveback the urb when all the tds are completed */ + if (last_td_in_urb(td)) { + if ((urb->actual_length != urb->transfer_buffer_length && + (urb->transfer_flags & URB_SHORT_NOT_OK)) || + (*status != 0 && !usb_endpoint_xfer_isoc(&urb->ep->desc))) + xhci_dbg(xhci, "Giveback URB %p, len = %d, expected = %d, status = %d\n", + urb, urb->actual_length, + urb->transfer_buffer_length, *status); + + /* set isoc urb status to 0 just as EHCI, UHCI, and OHCI */ + if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) + *status = 0; + xhci_giveback_urb_in_irq(xhci, td, *status); + } + + return 0; +} + static int xhci_reset_halted_ep(struct xhci_hcd *xhci, unsigned int slot_id, unsigned int ep_index, enum xhci_ep_reset_type reset_type) { @@ -2013,52 +2059,6 @@ int xhci_is_vendor_info_code(struct xhci_hcd *xhci, unsigned int trb_comp_code) return 0; } -static int xhci_td_cleanup(struct xhci_hcd *xhci, struct xhci_td *td, - struct xhci_ring *ep_ring, int *status) -{ - struct urb *urb = NULL; - - /* Clean up the endpoint's TD list */ - urb = td->urb; - - /* if a bounce buffer was used to align this td then unmap it */ - xhci_unmap_td_bounce_buffer(xhci, ep_ring, td); - - /* Do one last check of the actual transfer length. - * If the host controller said we transferred more data than the buffer - * length, urb->actual_length will be a very big number (since it's - * unsigned). Play it safe and say we didn't transfer anything. - */ - if (urb->actual_length > urb->transfer_buffer_length) { - xhci_warn(xhci, "URB req %u and actual %u transfer length mismatch\n", - urb->transfer_buffer_length, urb->actual_length); - urb->actual_length = 0; - *status = 0; - } - list_del_init(&td->td_list); - /* Was this TD slated to be cancelled but completed anyway? */ - if (!list_empty(&td->cancelled_td_list)) - list_del_init(&td->cancelled_td_list); - - inc_td_cnt(urb); - /* Giveback the urb when all the tds are completed */ - if (last_td_in_urb(td)) { - if ((urb->actual_length != urb->transfer_buffer_length && - (urb->transfer_flags & URB_SHORT_NOT_OK)) || - (*status != 0 && !usb_endpoint_xfer_isoc(&urb->ep->desc))) - xhci_dbg(xhci, "Giveback URB %p, len = %d, expected = %d, status = %d\n", - urb, urb->actual_length, - urb->transfer_buffer_length, *status); - - /* set isoc urb status to 0 just as EHCI, UHCI, and OHCI */ - if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) - *status = 0; - xhci_giveback_urb_in_irq(xhci, td, *status); - } - - return 0; -} - static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, struct xhci_transfer_event *event, struct xhci_virt_ep *ep, int *status) From cad965cedbc41236bea5f2642ea76e02ec033ff8 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 29 Jan 2021 15:00:35 +0200 Subject: [PATCH 0898/4345] xhci: store TD status in the td struct instead of passing it along [ Upstream commit a6ccd1fd4bd4fca37eaa3d76bef940d6332919bc ] In cases where the TD can't be given back in current handler we want to be able to store it until its time to return the TD. Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20210129130044.206855-19-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: a1575120972e ("xhci: Prevent infinite loop in transaction errors recovery for streams") Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-ring.c | 56 +++++++++++++++++++----------------- drivers/usb/host/xhci.h | 1 + 2 files changed, 30 insertions(+), 27 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index d523cbe7fcf1..2bd407ff9f0b 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -774,7 +774,7 @@ static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci, } static int xhci_td_cleanup(struct xhci_hcd *xhci, struct xhci_td *td, - struct xhci_ring *ep_ring, int *status) + struct xhci_ring *ep_ring, int status) { struct urb *urb = NULL; @@ -793,7 +793,7 @@ static int xhci_td_cleanup(struct xhci_hcd *xhci, struct xhci_td *td, xhci_warn(xhci, "URB req %u and actual %u transfer length mismatch\n", urb->transfer_buffer_length, urb->actual_length); urb->actual_length = 0; - *status = 0; + status = 0; } list_del_init(&td->td_list); /* Was this TD slated to be cancelled but completed anyway? */ @@ -805,15 +805,15 @@ static int xhci_td_cleanup(struct xhci_hcd *xhci, struct xhci_td *td, if (last_td_in_urb(td)) { if ((urb->actual_length != urb->transfer_buffer_length && (urb->transfer_flags & URB_SHORT_NOT_OK)) || - (*status != 0 && !usb_endpoint_xfer_isoc(&urb->ep->desc))) + (status != 0 && !usb_endpoint_xfer_isoc(&urb->ep->desc))) xhci_dbg(xhci, "Giveback URB %p, len = %d, expected = %d, status = %d\n", urb, urb->actual_length, - urb->transfer_buffer_length, *status); + urb->transfer_buffer_length, status); /* set isoc urb status to 0 just as EHCI, UHCI, and OHCI */ if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) - *status = 0; - xhci_giveback_urb_in_irq(xhci, td, *status); + status = 0; + xhci_giveback_urb_in_irq(xhci, td, status); } return 0; @@ -2060,8 +2060,7 @@ int xhci_is_vendor_info_code(struct xhci_hcd *xhci, unsigned int trb_comp_code) } static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, - struct xhci_transfer_event *event, - struct xhci_virt_ep *ep, int *status) + struct xhci_transfer_event *event, struct xhci_virt_ep *ep) { struct xhci_ep_ctx *ep_ctx; struct xhci_ring *ep_ring; @@ -2104,7 +2103,7 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, inc_deq(xhci, ep_ring); } - return xhci_td_cleanup(xhci, td, ep_ring, status); + return xhci_td_cleanup(xhci, td, ep_ring, td->status); } /* sum trb lengths from ring dequeue up to stop_trb, _excluding_ stop_trb */ @@ -2127,7 +2126,7 @@ static int sum_trb_lengths(struct xhci_hcd *xhci, struct xhci_ring *ring, */ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, union xhci_trb *ep_trb, struct xhci_transfer_event *event, - struct xhci_virt_ep *ep, int *status) + struct xhci_virt_ep *ep) { struct xhci_ep_ctx *ep_ctx; u32 trb_comp_code; @@ -2145,13 +2144,13 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, if (trb_type != TRB_STATUS) { xhci_warn(xhci, "WARN: Success on ctrl %s TRB without IOC set?\n", (trb_type == TRB_DATA) ? "data" : "setup"); - *status = -ESHUTDOWN; + td->status = -ESHUTDOWN; break; } - *status = 0; + td->status = 0; break; case COMP_SHORT_PACKET: - *status = 0; + td->status = 0; break; case COMP_STOPPED_SHORT_PACKET: if (trb_type == TRB_DATA || trb_type == TRB_NORMAL) @@ -2215,7 +2214,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->actual_length = requested; finish_td: - return finish_td(xhci, td, event, ep, status); + return finish_td(xhci, td, event, ep); } /* @@ -2223,7 +2222,7 @@ finish_td: */ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, union xhci_trb *ep_trb, struct xhci_transfer_event *event, - struct xhci_virt_ep *ep, int *status) + struct xhci_virt_ep *ep) { struct urb_priv *urb_priv; int idx; @@ -2300,11 +2299,11 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->actual_length += frame->actual_length; - return finish_td(xhci, td, event, ep, status); + return finish_td(xhci, td, event, ep); } static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, - struct xhci_virt_ep *ep, int *status) + struct xhci_virt_ep *ep, int status) { struct urb_priv *urb_priv; struct usb_iso_packet_descriptor *frame; @@ -2333,7 +2332,7 @@ static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, */ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, union xhci_trb *ep_trb, struct xhci_transfer_event *event, - struct xhci_virt_ep *ep, int *status) + struct xhci_virt_ep *ep) { struct xhci_slot_ctx *slot_ctx; struct xhci_ring *ep_ring; @@ -2357,13 +2356,13 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->ep->desc.bEndpointAddress, requested, remaining); } - *status = 0; + td->status = 0; break; case COMP_SHORT_PACKET: xhci_dbg(xhci, "ep %#x - asked for %d bytes, %d bytes untransferred\n", td->urb->ep->desc.bEndpointAddress, requested, remaining); - *status = 0; + td->status = 0; break; case COMP_STOPPED_SHORT_PACKET: td->urb->actual_length = remaining; @@ -2378,7 +2377,8 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, (ep_ring->err_count++ > MAX_SOFT_RETRY) || le32_to_cpu(slot_ctx->tt_info) & TT_SLOT) break; - *status = 0; + + td->status = 0; xhci_cleanup_halted_endpoint(xhci, ep, ep_ring->stream_id, td, EP_SOFT_RESET); return 0; @@ -2399,7 +2399,7 @@ finish_td: remaining); td->urb->actual_length = 0; } - return finish_td(xhci, td, event, ep, status); + return finish_td(xhci, td, event, ep); } /* @@ -2701,7 +2701,7 @@ static int handle_tx_event(struct xhci_hcd *xhci, return -ESHUTDOWN; } - skip_isoc_td(xhci, td, ep, &status); + skip_isoc_td(xhci, td, ep, status); goto cleanup; } if (trb_comp_code == COMP_SHORT_PACKET) @@ -2729,6 +2729,7 @@ static int handle_tx_event(struct xhci_hcd *xhci, * endpoint. Otherwise, the endpoint remains stalled * indefinitely. */ + if (trb_is_noop(ep_trb)) { if (trb_comp_code == COMP_STALL_ERROR || xhci_requires_manual_halt_cleanup(xhci, ep_ctx, @@ -2739,14 +2740,15 @@ static int handle_tx_event(struct xhci_hcd *xhci, goto cleanup; } + td->status = status; + /* update the urb's actual_length and give back to the core */ if (usb_endpoint_xfer_control(&td->urb->ep->desc)) - process_ctrl_td(xhci, td, ep_trb, event, ep, &status); + process_ctrl_td(xhci, td, ep_trb, event, ep); else if (usb_endpoint_xfer_isoc(&td->urb->ep->desc)) - process_isoc_td(xhci, td, ep_trb, event, ep, &status); + process_isoc_td(xhci, td, ep_trb, event, ep); else - process_bulk_intr_td(xhci, td, ep_trb, event, ep, - &status); + process_bulk_intr_td(xhci, td, ep_trb, event, ep); cleanup: handling_skipped_tds = ep->skip && trb_comp_code != COMP_MISSED_SERVICE_ERROR && diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 9cbf106fb3ee..af3759928a95 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1544,6 +1544,7 @@ struct xhci_segment { struct xhci_td { struct list_head td_list; struct list_head cancelled_td_list; + int status; struct urb *urb; struct xhci_segment *start_seg; union xhci_trb *first_trb; From 2f90fcedc5d6efcd5b608d28e0321521a6d9193e Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 29 Jan 2021 15:00:37 +0200 Subject: [PATCH 0899/4345] xhci: move and rename xhci_cleanup_halted_endpoint() [ Upstream commit 7c6c334e6fc8cd99e780fd74cd29687886a81862 ] Halted endpoints can be discoverd both when handling transfer events and command completion events. Move code that handles halted endpoints before both of those event handlers. Rename the function to xhci_handle_halted_ep() to better describe what it does. Try to reserve "cleanup" word in function names for last stage cleanup activities. No functional changes Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20210129130044.206855-21-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: a1575120972e ("xhci: Prevent infinite loop in transaction errors recovery for streams") Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-ring.c | 84 ++++++++++++++++++------------------ 1 file changed, 43 insertions(+), 41 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 2bd407ff9f0b..edb712081815 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -839,6 +839,35 @@ done: return ret; } +static void xhci_handle_halted_endpoint(struct xhci_hcd *xhci, + struct xhci_virt_ep *ep, unsigned int stream_id, + struct xhci_td *td, + enum xhci_ep_reset_type reset_type) +{ + unsigned int slot_id = ep->vdev->slot_id; + int err; + + /* + * Avoid resetting endpoint if link is inactive. Can cause host hang. + * Device will be reset soon to recover the link so don't do anything + */ + if (ep->vdev->flags & VDEV_PORT_ERROR) + return; + + ep->ep_state |= EP_HALTED; + + err = xhci_reset_halted_ep(xhci, slot_id, ep->ep_index, reset_type); + if (err) + return; + + if (reset_type == EP_HARD_RESET) { + ep->ep_state |= EP_HARD_CLEAR_TOGGLE; + xhci_cleanup_stalled_ring(xhci, slot_id, ep->ep_index, stream_id, + td); + } + xhci_ring_cmd_db(xhci); +} + /* * When we get a command completion for a Stop Endpoint Command, we need to * unlink any cancelled TDs from the ring. There are two ways to do that: @@ -1990,35 +2019,6 @@ static void xhci_clear_hub_tt_buffer(struct xhci_hcd *xhci, struct xhci_td *td, } } -static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci, - struct xhci_virt_ep *ep, unsigned int stream_id, - struct xhci_td *td, - enum xhci_ep_reset_type reset_type) -{ - unsigned int slot_id = ep->vdev->slot_id; - int err; - - /* - * Avoid resetting endpoint if link is inactive. Can cause host hang. - * Device will be reset soon to recover the link so don't do anything - */ - if (ep->vdev->flags & VDEV_PORT_ERROR) - return; - - ep->ep_state |= EP_HALTED; - - err = xhci_reset_halted_ep(xhci, slot_id, ep->ep_index, reset_type); - if (err) - return; - - if (reset_type == EP_HARD_RESET) { - ep->ep_state |= EP_HARD_CLEAR_TOGGLE; - xhci_cleanup_stalled_ring(xhci, slot_id, ep->ep_index, stream_id, - td); - } - xhci_ring_cmd_db(xhci); -} - /* Check if an error has halted the endpoint ring. The class driver will * cleanup the halt for a non-default control endpoint if we indicate a stall. * However, a babble and other errors also halt the endpoint ring, and the class @@ -2094,7 +2094,8 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, */ if ((ep->ep_index != 0) || (trb_comp_code != COMP_STALL_ERROR)) xhci_clear_hub_tt_buffer(xhci, td, ep); - xhci_cleanup_halted_endpoint(xhci, ep, ep_ring->stream_id, td, + + xhci_handle_halted_endpoint(xhci, ep, ep_ring->stream_id, td, EP_HARD_RESET); } else { /* Update ring dequeue pointer */ @@ -2379,8 +2380,9 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, break; td->status = 0; - xhci_cleanup_halted_endpoint(xhci, ep, ep_ring->stream_id, td, - EP_SOFT_RESET); + + xhci_handle_halted_endpoint(xhci, ep, ep_ring->stream_id, td, + EP_SOFT_RESET); return 0; default: /* do nothing */ @@ -2455,8 +2457,8 @@ static int handle_tx_event(struct xhci_hcd *xhci, case COMP_USB_TRANSACTION_ERROR: case COMP_INVALID_STREAM_TYPE_ERROR: case COMP_INVALID_STREAM_ID_ERROR: - xhci_cleanup_halted_endpoint(xhci, ep, 0, NULL, - EP_SOFT_RESET); + xhci_handle_halted_endpoint(xhci, ep, 0, NULL, + EP_SOFT_RESET); goto cleanup; case COMP_RING_UNDERRUN: case COMP_RING_OVERRUN: @@ -2639,10 +2641,10 @@ static int handle_tx_event(struct xhci_hcd *xhci, if (trb_comp_code == COMP_STALL_ERROR || xhci_requires_manual_halt_cleanup(xhci, ep_ctx, trb_comp_code)) { - xhci_cleanup_halted_endpoint(xhci, ep, - ep_ring->stream_id, - NULL, - EP_HARD_RESET); + xhci_handle_halted_endpoint(xhci, ep, + ep_ring->stream_id, + NULL, + EP_HARD_RESET); } goto cleanup; } @@ -2734,9 +2736,9 @@ static int handle_tx_event(struct xhci_hcd *xhci, if (trb_comp_code == COMP_STALL_ERROR || xhci_requires_manual_halt_cleanup(xhci, ep_ctx, trb_comp_code)) - xhci_cleanup_halted_endpoint(xhci, ep, - ep_ring->stream_id, - td, EP_HARD_RESET); + xhci_handle_halted_endpoint(xhci, ep, + ep_ring->stream_id, + td, EP_HARD_RESET); goto cleanup; } From 3d13818a9995116c230c067811cf137c19609c15 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Wed, 30 Nov 2022 11:19:43 +0200 Subject: [PATCH 0900/4345] xhci: Prevent infinite loop in transaction errors recovery for streams [ Upstream commit a1575120972ecd7baa6af6a69e4e7ea9213bde7c ] Make sure to also limit the amount of soft reset retries for transaction errors on streams in cases where the transaction error event doesn't point to any specific TRB. In these cases we don't know the TRB or stream ring, but we do know which endpoint had the error. To keep error counting simple and functional, move the current err_count from ring structure to endpoint structure. Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20221130091944.2171610-6-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-ring.c | 14 ++++++++++---- drivers/usb/host/xhci.h | 2 +- 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index edb712081815..ead42fc3e16d 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2349,7 +2349,7 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, switch (trb_comp_code) { case COMP_SUCCESS: - ep_ring->err_count = 0; + ep->err_count = 0; /* handle success with untransferred data as short packet */ if (ep_trb != td->last_trb || remaining) { xhci_warn(xhci, "WARN Successful completion on short TX\n"); @@ -2375,7 +2375,7 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, break; case COMP_USB_TRANSACTION_ERROR: if (xhci->quirks & XHCI_NO_SOFT_RETRY || - (ep_ring->err_count++ > MAX_SOFT_RETRY) || + (ep->err_count++ > MAX_SOFT_RETRY) || le32_to_cpu(slot_ctx->tt_info) & TT_SLOT) break; @@ -2457,8 +2457,14 @@ static int handle_tx_event(struct xhci_hcd *xhci, case COMP_USB_TRANSACTION_ERROR: case COMP_INVALID_STREAM_TYPE_ERROR: case COMP_INVALID_STREAM_ID_ERROR: - xhci_handle_halted_endpoint(xhci, ep, 0, NULL, - EP_SOFT_RESET); + xhci_dbg(xhci, "Stream transaction error ep %u no id\n", + ep_index); + if (ep->err_count++ > MAX_SOFT_RETRY) + xhci_handle_halted_endpoint(xhci, ep, 0, NULL, + EP_HARD_RESET); + else + xhci_handle_halted_endpoint(xhci, ep, 0, NULL, + EP_SOFT_RESET); goto cleanup; case COMP_RING_UNDERRUN: case COMP_RING_OVERRUN: diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index af3759928a95..ac09b171b783 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -933,6 +933,7 @@ struct xhci_virt_ep { * have to restore the device state to the previous state */ struct xhci_ring *new_ring; + unsigned int err_count; unsigned int ep_state; #define SET_DEQ_PENDING (1 << 0) #define EP_HALTED (1 << 1) /* For stall handling */ @@ -1616,7 +1617,6 @@ struct xhci_ring { * if we own the TRB (if we are the consumer). See section 4.9.1. */ u32 cycle_state; - unsigned int err_count; unsigned int stream_id; unsigned int num_segs; unsigned int num_trbs_free; From 98407a4ae34b8c3a38a1478e13366b0c20e07646 Mon Sep 17 00:00:00 2001 From: Ferry Toth Date: Mon, 5 Dec 2022 21:15:26 +0100 Subject: [PATCH 0901/4345] usb: ulpi: defer ulpi_register on ulpi_read_id timeout [ Upstream commit 8a7b31d545d3a15f0e6f5984ae16f0ca4fd76aac ] Since commit 0f0101719138 ("usb: dwc3: Don't switch OTG -> peripheral if extcon is present") Dual Role support on Intel Merrifield platform broke due to rearranging the call to dwc3_get_extcon(). It appears to be caused by ulpi_read_id() on the first test write failing with -ETIMEDOUT. Currently ulpi_read_id() expects to discover the phy via DT when the test write fails and returns 0 in that case, even if DT does not provide the phy. As a result usb probe completes without phy. Make ulpi_read_id() return -ETIMEDOUT to its user if the first test write fails. The user should then handle it appropriately. A follow up patch will make dwc3_core_init() set -EPROBE_DEFER in this case and bail out. Fixes: ef6a7bcfb01c ("usb: ulpi: Support device discovery via DT") Cc: stable@vger.kernel.org Acked-by: Heikki Krogerus Signed-off-by: Ferry Toth Link: https://lore.kernel.org/r/20221205201527.13525-2-ftoth@exalondelft.nl Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/common/ulpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 3c705f1bead8..1f077f2ea40f 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -208,7 +208,7 @@ static int ulpi_read_id(struct ulpi *ulpi) /* Test the interface */ ret = ulpi_write(ulpi, ULPI_SCRATCH, 0xaa); if (ret < 0) - goto err; + return ret; ret = ulpi_read(ulpi, ULPI_SCRATCH); if (ret < 0) From 091f85db4c3fb1734a6d7fb4777a2b2831da6631 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 17 Nov 2022 15:36:03 +0800 Subject: [PATCH 0902/4345] ext4: fix uninititialized value in 'ext4_evict_inode' [ Upstream commit 7ea71af94eaaaf6d9aed24bc94a05b977a741cb9 ] Syzbot found the following issue: ===================================================== BUG: KMSAN: uninit-value in ext4_evict_inode+0xdd/0x26b0 fs/ext4/inode.c:180 ext4_evict_inode+0xdd/0x26b0 fs/ext4/inode.c:180 evict+0x365/0x9a0 fs/inode.c:664 iput_final fs/inode.c:1747 [inline] iput+0x985/0xdd0 fs/inode.c:1773 __ext4_new_inode+0xe54/0x7ec0 fs/ext4/ialloc.c:1361 ext4_mknod+0x376/0x840 fs/ext4/namei.c:2844 vfs_mknod+0x79d/0x830 fs/namei.c:3914 do_mknodat+0x47d/0xaa0 __do_sys_mknodat fs/namei.c:3992 [inline] __se_sys_mknodat fs/namei.c:3989 [inline] __ia32_sys_mknodat+0xeb/0x150 fs/namei.c:3989 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178 do_fast_syscall_32+0x33/0x70 arch/x86/entry/common.c:203 do_SYSENTER_32+0x1b/0x20 arch/x86/entry/common.c:246 entry_SYSENTER_compat_after_hwframe+0x70/0x82 Uninit was created at: __alloc_pages+0x9f1/0xe80 mm/page_alloc.c:5578 alloc_pages+0xaae/0xd80 mm/mempolicy.c:2285 alloc_slab_page mm/slub.c:1794 [inline] allocate_slab+0x1b5/0x1010 mm/slub.c:1939 new_slab mm/slub.c:1992 [inline] ___slab_alloc+0x10c3/0x2d60 mm/slub.c:3180 __slab_alloc mm/slub.c:3279 [inline] slab_alloc_node mm/slub.c:3364 [inline] slab_alloc mm/slub.c:3406 [inline] __kmem_cache_alloc_lru mm/slub.c:3413 [inline] kmem_cache_alloc_lru+0x6f3/0xb30 mm/slub.c:3429 alloc_inode_sb include/linux/fs.h:3117 [inline] ext4_alloc_inode+0x5f/0x860 fs/ext4/super.c:1321 alloc_inode+0x83/0x440 fs/inode.c:259 new_inode_pseudo fs/inode.c:1018 [inline] new_inode+0x3b/0x430 fs/inode.c:1046 __ext4_new_inode+0x2a7/0x7ec0 fs/ext4/ialloc.c:959 ext4_mkdir+0x4d5/0x1560 fs/ext4/namei.c:2992 vfs_mkdir+0x62a/0x870 fs/namei.c:4035 do_mkdirat+0x466/0x7b0 fs/namei.c:4060 __do_sys_mkdirat fs/namei.c:4075 [inline] __se_sys_mkdirat fs/namei.c:4073 [inline] __ia32_sys_mkdirat+0xc4/0x120 fs/namei.c:4073 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178 do_fast_syscall_32+0x33/0x70 arch/x86/entry/common.c:203 do_SYSENTER_32+0x1b/0x20 arch/x86/entry/common.c:246 entry_SYSENTER_compat_after_hwframe+0x70/0x82 CPU: 1 PID: 4625 Comm: syz-executor.2 Not tainted 6.1.0-rc4-syzkaller-62821-gcb231e2f67ec #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 ===================================================== Now, 'ext4_alloc_inode()' didn't init 'ei->i_flags'. If new inode failed before set 'ei->i_flags' in '__ext4_new_inode()', then do 'iput()'. As after 6bc0d63dad7f commit will access 'ei->i_flags' in 'ext4_evict_inode()' which will lead to access uninit-value. To solve above issue just init 'ei->i_flags' in 'ext4_alloc_inode()'. Reported-by: syzbot+57b25da729eb0b88177d@syzkaller.appspotmail.com Signed-off-by: Ye Bin Fixes: 6bc0d63dad7f ("ext4: remove EA inode entry from mbcache on inode eviction") Reviewed-by: Jan Kara Reviewed-by: Eric Biggers Link: https://lore.kernel.org/r/20221117073603.2598882-1-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Sasha Levin --- fs/ext4/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 935589579b8f..e940fb07ef2e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1279,6 +1279,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) return NULL; inode_set_iversion(&ei->vfs_inode, 1); + ei->i_flags = 0; spin_lock_init(&ei->i_raw_lock); INIT_LIST_HEAD(&ei->i_prealloc_list); atomic_set(&ei->i_prealloc_active, 0); From a3a1114aa6159b31319d44314737edcd0cff6932 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Wed, 22 Sep 2021 10:50:06 +0200 Subject: [PATCH 0903/4345] xfrm: fix rcu lock in xfrm_notify_userpolicy() commit 93ec1320b0170d7a207eda2d119c669b673401ed upstream. As stated in the comment above xfrm_nlmsg_multicast(), rcu read lock must be held before calling this function. Reported-by: syzbot+3d9866419b4aa8f985d6@syzkaller.appspotmail.com Fixes: 703b94b93c19 ("xfrm: notify default policy on update") Signed-off-by: Nicolas Dichtel Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman --- net/xfrm/xfrm_user.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d9841f44487f..c6bf3898d1bf 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1920,6 +1920,7 @@ static int xfrm_notify_userpolicy(struct net *net) int len = NLMSG_ALIGN(sizeof(*up)); struct nlmsghdr *nlh; struct sk_buff *skb; + int err; skb = nlmsg_new(len, GFP_ATOMIC); if (skb == NULL) @@ -1938,7 +1939,11 @@ static int xfrm_notify_userpolicy(struct net *net) nlmsg_end(skb, nlh); - return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY); + rcu_read_lock(); + err = xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY); + rcu_read_unlock(); + + return err; } static bool xfrm_userpolicy_is_valid(__u8 policy) From 4e6a70fd840400e3a2e784a6673968a3eb2431c0 Mon Sep 17 00:00:00 2001 From: Gavrilov Ilia Date: Wed, 11 Jan 2023 11:57:39 +0000 Subject: [PATCH 0904/4345] netfilter: ipset: Fix overflow before widen in the bitmap_ip_create() function. commit 9ea4b476cea1b7d461d16dda25ca3c7e616e2d15 upstream. When first_ip is 0, last_ip is 0xFFFFFFFF, and netmask is 31, the value of an arithmetic expression 2 << (netmask - mask_bits - 1) is subject to overflow due to a failure casting operands to a larger data type before performing the arithmetic. Note that it's harmless since the value will be checked at the next step. Found by InfoTeCS on behalf of Linux Verification Center (linuxtesting.org) with SVACE. Fixes: b9fed748185a ("netfilter: ipset: Check and reject crazy /0 input parameters") Signed-off-by: Ilia.Gavrilov Reviewed-by: Simon Horman Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/ipset/ip_set_bitmap_ip.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index a8ce04a4bb72..e4fa00abde6a 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -308,8 +308,8 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], return -IPSET_ERR_BITMAP_RANGE; pr_debug("mask_bits %u, netmask %u\n", mask_bits, netmask); - hosts = 2 << (32 - netmask - 1); - elements = 2 << (netmask - mask_bits - 1); + hosts = 2U << (32 - netmask - 1); + elements = 2UL << (netmask - mask_bits - 1); } if (elements > IPSET_BITMAP_MAX_RANGE + 1) return -IPSET_ERR_BITMAP_RANGE_SIZE; From 8cbeb60320ac45a8240b561c8ef466b86c34dedc Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Fri, 6 Jan 2023 12:21:57 +0530 Subject: [PATCH 0905/4345] powerpc/imc-pmu: Fix use of mutex in IRQs disabled section commit 76d588dddc459fefa1da96e0a081a397c5c8e216 upstream. Current imc-pmu code triggers a WARNING with CONFIG_DEBUG_ATOMIC_SLEEP and CONFIG_PROVE_LOCKING enabled, while running a thread_imc event. Command to trigger the warning: # perf stat -e thread_imc/CPM_CS_FROM_L4_MEM_X_DPTEG/ sleep 5 Performance counter stats for 'sleep 5': 0 thread_imc/CPM_CS_FROM_L4_MEM_X_DPTEG/ 5.002117947 seconds time elapsed 0.000131000 seconds user 0.001063000 seconds sys Below is snippet of the warning in dmesg: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:580 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 2869, name: perf-exec preempt_count: 2, expected: 0 4 locks held by perf-exec/2869: #0: c00000004325c540 (&sig->cred_guard_mutex){+.+.}-{3:3}, at: bprm_execve+0x64/0xa90 #1: c00000004325c5d8 (&sig->exec_update_lock){++++}-{3:3}, at: begin_new_exec+0x460/0xef0 #2: c0000003fa99d4e0 (&cpuctx_lock){-...}-{2:2}, at: perf_event_exec+0x290/0x510 #3: c000000017ab8418 (&ctx->lock){....}-{2:2}, at: perf_event_exec+0x29c/0x510 irq event stamp: 4806 hardirqs last enabled at (4805): [] _raw_spin_unlock_irqrestore+0x94/0xd0 hardirqs last disabled at (4806): [] perf_event_exec+0x394/0x510 softirqs last enabled at (0): [] copy_process+0xc34/0x1ff0 softirqs last disabled at (0): [<0000000000000000>] 0x0 CPU: 36 PID: 2869 Comm: perf-exec Not tainted 6.2.0-rc2-00011-g1247637727f2 #61 Hardware name: 8375-42A POWER9 0x4e1202 opal:v7.0-16-g9b85f7d961 PowerNV Call Trace: dump_stack_lvl+0x98/0xe0 (unreliable) __might_resched+0x2f8/0x310 __mutex_lock+0x6c/0x13f0 thread_imc_event_add+0xf4/0x1b0 event_sched_in+0xe0/0x210 merge_sched_in+0x1f0/0x600 visit_groups_merge.isra.92.constprop.166+0x2bc/0x6c0 ctx_flexible_sched_in+0xcc/0x140 ctx_sched_in+0x20c/0x2a0 ctx_resched+0x104/0x1c0 perf_event_exec+0x340/0x510 begin_new_exec+0x730/0xef0 load_elf_binary+0x3f8/0x1e10 ... do not call blocking ops when !TASK_RUNNING; state=2001 set at [<00000000fd63e7cf>] do_nanosleep+0x60/0x1a0 WARNING: CPU: 36 PID: 2869 at kernel/sched/core.c:9912 __might_sleep+0x9c/0xb0 CPU: 36 PID: 2869 Comm: sleep Tainted: G W 6.2.0-rc2-00011-g1247637727f2 #61 Hardware name: 8375-42A POWER9 0x4e1202 opal:v7.0-16-g9b85f7d961 PowerNV NIP: c000000000194a1c LR: c000000000194a18 CTR: c000000000a78670 REGS: c00000004d2134e0 TRAP: 0700 Tainted: G W (6.2.0-rc2-00011-g1247637727f2) MSR: 9000000000021033 CR: 48002824 XER: 00000000 CFAR: c00000000013fb64 IRQMASK: 1 The above warning triggered because the current imc-pmu code uses mutex lock in interrupt disabled sections. The function mutex_lock() internally calls __might_resched(), which will check if IRQs are disabled and in case IRQs are disabled, it will trigger the warning. Fix the issue by changing the mutex lock to spinlock. Fixes: 8f95faaac56c ("powerpc/powernv: Detect and create IMC device") Reported-by: Michael Petlan Reported-by: Peter Zijlstra Signed-off-by: Kajol Jain [mpe: Fix comments, trim oops in change log, add reported-by tags] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230106065157.182648-1-kjain@linux.ibm.com Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/imc-pmu.h | 2 +- arch/powerpc/perf/imc-pmu.c | 136 ++++++++++++++--------------- 2 files changed, 67 insertions(+), 71 deletions(-) diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h index 4f897993b710..699a88584ae1 100644 --- a/arch/powerpc/include/asm/imc-pmu.h +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -137,7 +137,7 @@ struct imc_pmu { * are inited. */ struct imc_pmu_ref { - struct mutex lock; + spinlock_t lock; unsigned int id; int refc; }; diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index e8074d7f2401..e42c2fe3dd36 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -13,6 +13,7 @@ #include #include #include +#include /* Nest IMC data structures and variables */ @@ -20,7 +21,7 @@ * Used to avoid races in counting the nest-pmu units during hotplug * register and unregister */ -static DEFINE_MUTEX(nest_init_lock); +static DEFINE_SPINLOCK(nest_init_lock); static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); static struct imc_pmu **per_nest_pmu_arr; static cpumask_t nest_imc_cpumask; @@ -49,7 +50,7 @@ static int trace_imc_mem_size; * core and trace-imc */ static struct imc_pmu_ref imc_global_refc = { - .lock = __MUTEX_INITIALIZER(imc_global_refc.lock), + .lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock), .id = 0, .refc = 0, }; @@ -393,7 +394,7 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu) get_hard_smp_processor_id(cpu)); /* * If this is the last cpu in this chip then, skip the reference - * count mutex lock and make the reference count on this chip zero. + * count lock and make the reference count on this chip zero. */ ref = get_nest_pmu_ref(cpu); if (!ref) @@ -455,15 +456,15 @@ static void nest_imc_counters_release(struct perf_event *event) /* * See if we need to disable the nest PMU. * If no events are currently in use, then we have to take a - * mutex to ensure that we don't race with another task doing + * lock to ensure that we don't race with another task doing * enable or disable the nest counters. */ ref = get_nest_pmu_ref(event->cpu); if (!ref) return; - /* Take the mutex lock for this node and then decrement the reference count */ - mutex_lock(&ref->lock); + /* Take the lock for this node and then decrement the reference count */ + spin_lock(&ref->lock); if (ref->refc == 0) { /* * The scenario where this is true is, when perf session is @@ -475,7 +476,7 @@ static void nest_imc_counters_release(struct perf_event *event) * an OPAL call to disable the engine in that node. * */ - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return; } ref->refc--; @@ -483,7 +484,7 @@ static void nest_imc_counters_release(struct perf_event *event) rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id); return; } @@ -491,7 +492,7 @@ static void nest_imc_counters_release(struct perf_event *event) WARN(1, "nest-imc: Invalid event reference count\n"); ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); } static int nest_imc_event_init(struct perf_event *event) @@ -550,26 +551,25 @@ static int nest_imc_event_init(struct perf_event *event) /* * Get the imc_pmu_ref struct for this node. - * Take the mutex lock and then increment the count of nest pmu events - * inited. + * Take the lock and then increment the count of nest pmu events inited. */ ref = get_nest_pmu_ref(event->cpu); if (!ref) return -EINVAL; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("nest-imc: Unable to start the counters for node %d\n", node_id); return rc; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); event->destroy = nest_imc_counters_release; return 0; @@ -605,9 +605,8 @@ static int core_imc_mem_init(int cpu, int size) return -ENOMEM; mem_info->vbase = page_address(page); - /* Init the mutex */ core_imc_refc[core_id].id = core_id; - mutex_init(&core_imc_refc[core_id].lock); + spin_lock_init(&core_imc_refc[core_id].lock); rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE, __pa((void *)mem_info->vbase), @@ -696,9 +695,8 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu); } else { /* - * If this is the last cpu in this core then, skip taking refernce - * count mutex lock for this core and directly zero "refc" for - * this core. + * If this is the last cpu in this core then skip taking reference + * count lock for this core and directly zero "refc" for this core. */ opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(cpu)); @@ -713,11 +711,11 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) * last cpu in this core and core-imc event running * in this cpu. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_CORE) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); } return 0; } @@ -732,7 +730,7 @@ static int core_imc_pmu_cpumask_init(void) static void reset_global_refc(struct perf_event *event) { - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); imc_global_refc.refc--; /* @@ -744,7 +742,7 @@ static void reset_global_refc(struct perf_event *event) imc_global_refc.refc = 0; imc_global_refc.id = 0; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); } static void core_imc_counters_release(struct perf_event *event) @@ -757,17 +755,17 @@ static void core_imc_counters_release(struct perf_event *event) /* * See if we need to disable the IMC PMU. * If no events are currently in use, then we have to take a - * mutex to ensure that we don't race with another task doing + * lock to ensure that we don't race with another task doing * enable or disable the core counters. */ core_id = event->cpu / threads_per_core; - /* Take the mutex lock and decrement the refernce count for this core */ + /* Take the lock and decrement the refernce count for this core */ ref = &core_imc_refc[core_id]; if (!ref) return; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { /* * The scenario where this is true is, when perf session is @@ -779,7 +777,7 @@ static void core_imc_counters_release(struct perf_event *event) * an OPAL call to disable the engine in that core. * */ - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return; } ref->refc--; @@ -787,7 +785,7 @@ static void core_imc_counters_release(struct perf_event *event) rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("IMC: Unable to stop the counters for core %d\n", core_id); return; } @@ -795,7 +793,7 @@ static void core_imc_counters_release(struct perf_event *event) WARN(1, "core-imc: Invalid event reference count\n"); ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); reset_global_refc(event); } @@ -833,7 +831,6 @@ static int core_imc_event_init(struct perf_event *event) if ((!pcmi->vbase)) return -ENODEV; - /* Get the core_imc mutex for this core */ ref = &core_imc_refc[core_id]; if (!ref) return -EINVAL; @@ -841,22 +838,22 @@ static int core_imc_event_init(struct perf_event *event) /* * Core pmu units are enabled only when it is used. * See if this is triggered for the first time. - * If yes, take the mutex lock and enable the core counters. + * If yes, take the lock and enable the core counters. * If not, just increment the count in core_imc_refc struct. */ - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("core-imc: Unable to start the counters for core %d\n", core_id); return rc; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); /* * Since the system can run either in accumulation or trace-mode @@ -867,7 +864,7 @@ static int core_imc_event_init(struct perf_event *event) * to know whether any other trace/thread imc * events are running. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) { /* * No other trace/thread imc events are running in @@ -876,10 +873,10 @@ static int core_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_CORE; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK); event->destroy = core_imc_counters_release; @@ -951,10 +948,10 @@ static int ppc_thread_imc_cpu_offline(unsigned int cpu) mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); /* Reduce the refc if thread-imc event running on this cpu */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_THREAD) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return 0; } @@ -994,7 +991,7 @@ static int thread_imc_event_init(struct perf_event *event) if (!target) return -EINVAL; - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); /* * Check if any other trace/core imc events are running in the * system, if not set the global id to thread-imc. @@ -1003,10 +1000,10 @@ static int thread_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_THREAD; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->pmu->task_ctx_nr = perf_sw_context; event->destroy = reset_global_refc; @@ -1128,25 +1125,25 @@ static int thread_imc_event_add(struct perf_event *event, int flags) /* * imc pmus are enabled only when it is used. * See if this is triggered for the first time. - * If yes, take the mutex lock and enable the counters. + * If yes, take the lock and enable the counters. * If not, just increment the count in ref count struct. */ ref = &core_imc_refc[core_id]; if (!ref) return -EINVAL; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("thread-imc: Unable to start the counter\ for core %d\n", core_id); return -EINVAL; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return 0; } @@ -1163,12 +1160,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags) return; } - mutex_lock(&ref->lock); + spin_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("thread-imc: Unable to stop the counters\ for core %d\n", core_id); return; @@ -1176,7 +1173,7 @@ static void thread_imc_event_del(struct perf_event *event, int flags) } else if (ref->refc < 0) { ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); /* Set bit 0 of LDBAR to zero, to stop posting updates to memory */ mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); @@ -1217,9 +1214,8 @@ static int trace_imc_mem_alloc(int cpu_id, int size) } } - /* Init the mutex, if not already */ trace_imc_refc[core_id].id = core_id; - mutex_init(&trace_imc_refc[core_id].lock); + spin_lock_init(&trace_imc_refc[core_id].lock); mtspr(SPRN_LDBAR, 0); return 0; @@ -1239,10 +1235,10 @@ static int ppc_trace_imc_cpu_offline(unsigned int cpu) * Reduce the refc if any trace-imc event running * on this cpu. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_TRACE) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return 0; } @@ -1364,17 +1360,17 @@ static int trace_imc_event_add(struct perf_event *event, int flags) } mtspr(SPRN_LDBAR, ldbar_value); - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("trace-imc: Unable to start the counters for core %d\n", core_id); return -EINVAL; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return 0; } @@ -1407,19 +1403,19 @@ static void trace_imc_event_del(struct perf_event *event, int flags) return; } - mutex_lock(&ref->lock); + spin_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id); return; } } else if (ref->refc < 0) { ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); trace_imc_event_stop(event, flags); } @@ -1441,7 +1437,7 @@ static int trace_imc_event_init(struct perf_event *event) * no other thread is running any core/thread imc * events */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) { /* * No core/thread imc events are running in the @@ -1450,10 +1446,10 @@ static int trace_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_TRACE; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->hw.idx = -1; @@ -1525,10 +1521,10 @@ static int init_nest_pmu_ref(void) i = 0; for_each_node(nid) { /* - * Mutex lock to avoid races while tracking the number of + * Take the lock to avoid races while tracking the number of * sessions using the chip's nest pmu units. */ - mutex_init(&nest_imc_refc[i].lock); + spin_lock_init(&nest_imc_refc[i].lock); /* * Loop to init the "id" with the node_id. Variable "i" initialized to @@ -1625,7 +1621,7 @@ static void imc_common_mem_free(struct imc_pmu *pmu_ptr) static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) { if (pmu_ptr->domain == IMC_DOMAIN_NEST) { - mutex_lock(&nest_init_lock); + spin_lock(&nest_init_lock); if (nest_pmus == 1) { cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE); kfree(nest_imc_refc); @@ -1635,7 +1631,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) if (nest_pmus > 0) nest_pmus--; - mutex_unlock(&nest_init_lock); + spin_unlock(&nest_init_lock); } /* Free core_imc memory */ @@ -1792,11 +1788,11 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id * rest. To handle the cpuhotplug callback unregister, we track * the number of nest pmus in "nest_pmus". */ - mutex_lock(&nest_init_lock); + spin_lock(&nest_init_lock); if (nest_pmus == 0) { ret = init_nest_pmu_ref(); if (ret) { - mutex_unlock(&nest_init_lock); + spin_unlock(&nest_init_lock); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; goto err_free_mem; @@ -1804,7 +1800,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id /* Register for cpu hotplug notification. */ ret = nest_pmu_cpumask_init(); if (ret) { - mutex_unlock(&nest_init_lock); + spin_unlock(&nest_init_lock); kfree(nest_imc_refc); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; @@ -1812,7 +1808,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id } } nest_pmus++; - mutex_unlock(&nest_init_lock); + spin_unlock(&nest_init_lock); break; case IMC_DOMAIN_CORE: ret = core_imc_pmu_cpumask_init(); From 28b9a0e216dba31b19b8d2754fd65d2fba927b61 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 10 Jan 2023 12:15:40 +0100 Subject: [PATCH 0906/4345] x86/boot: Avoid using Intel mnemonics in AT&T syntax asm commit 7c6dd961d0c8e7e8f9fdc65071fb09ece702e18d upstream. With 'GNU assembler (GNU Binutils for Debian) 2.39.90.20221231' the build now reports: arch/x86/realmode/rm/../../boot/bioscall.S: Assembler messages: arch/x86/realmode/rm/../../boot/bioscall.S:35: Warning: found `movsd'; assuming `movsl' was meant arch/x86/realmode/rm/../../boot/bioscall.S:70: Warning: found `movsd'; assuming `movsl' was meant arch/x86/boot/bioscall.S: Assembler messages: arch/x86/boot/bioscall.S:35: Warning: found `movsd'; assuming `movsl' was meant arch/x86/boot/bioscall.S:70: Warning: found `movsd'; assuming `movsl' was meant Which is due to: PR gas/29525 Note that with the dropped CMPSD and MOVSD Intel Syntax string insn templates taking operands, mixed IsString/non-IsString template groups (with memory operands) cannot occur anymore. With that maybe_adjust_templates() becomes unnecessary (and is hence being removed). More details: https://sourceware.org/bugzilla/show_bug.cgi?id=29525 Borislav Petkov further explains: " the particular problem here is is that the 'd' suffix is "conflicting" in the sense that you can have SSE mnemonics like movsD %xmm... and the same thing also for string ops (which is the case here) so apparently the agreement in binutils land is to use the always accepted suffixes 'l' or 'q' and phase out 'd' slowly... " Fixes: 7a734e7dd93b ("x86, setup: "glove box" BIOS calls -- infrastructure") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Acked-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/Y71I3Ex2pvIxMpsP@hirez.programming.kicks-ass.net Signed-off-by: Greg Kroah-Hartman --- arch/x86/boot/bioscall.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S index 5521ea12f44e..aa9b96457584 100644 --- a/arch/x86/boot/bioscall.S +++ b/arch/x86/boot/bioscall.S @@ -32,7 +32,7 @@ intcall: movw %dx, %si movw %sp, %di movw $11, %cx - rep; movsd + rep; movsl /* Pop full state from the stack */ popal @@ -67,7 +67,7 @@ intcall: jz 4f movw %sp, %si movw $11, %cx - rep; movsd + rep; movsl 4: addw $44, %sp /* Restore state and return */ From 3ca8ef4d91ef1742fd4ec1c8827cb12677caf36f Mon Sep 17 00:00:00 2001 From: Eliav Farber Date: Thu, 20 Oct 2022 12:44:58 +0000 Subject: [PATCH 0907/4345] EDAC/device: Fix period calculation in edac_device_reset_delay_period() commit e84077437902ec99eba0a6b516df772653f142c7 upstream. Fix period calculation in case user sets a value of 1000. The input of round_jiffies_relative() should be in jiffies and not in milli-seconds. [ bp: Use the same code pattern as in edac_device_workq_setup() for clarity. ] Fixes: c4cf3b454eca ("EDAC: Rework workqueue handling") Signed-off-by: Eliav Farber Signed-off-by: Borislav Petkov (AMD) Cc: Link: https://lore.kernel.org/r/20221020124458.22153-1-farbere@amazon.com Signed-off-by: Greg Kroah-Hartman --- drivers/edac/edac_device.c | 17 ++++++++--------- drivers/edac/edac_module.h | 2 +- 2 files changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 8c4d947fb848..8220ce5b87ca 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -424,17 +424,16 @@ static void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev) * Then restart the workq on the new delay */ void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, - unsigned long value) + unsigned long msec) { - unsigned long jiffs = msecs_to_jiffies(value); + edac_dev->poll_msec = msec; + edac_dev->delay = msecs_to_jiffies(msec); - if (value == 1000) - jiffs = round_jiffies_relative(value); - - edac_dev->poll_msec = value; - edac_dev->delay = jiffs; - - edac_mod_work(&edac_dev->work, jiffs); + /* See comment in edac_device_workq_setup() above */ + if (edac_dev->poll_msec == 1000) + edac_mod_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); + else + edac_mod_work(&edac_dev->work, edac_dev->delay); } int edac_device_alloc_index(void) diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index aa1f91688eb8..841d238bc3f1 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -56,7 +56,7 @@ bool edac_stop_work(struct delayed_work *work); bool edac_mod_work(struct delayed_work *work, unsigned long delay); extern void edac_device_reset_delay_period(struct edac_device_ctl_info - *edac_dev, unsigned long value); + *edac_dev, unsigned long msec); extern void edac_mc_reset_delay_period(unsigned long value); extern void *edac_align_ptr(void **p, unsigned size, int n_elems); From d4aa749e046435f054e94ebf50cad143d6229fae Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Sun, 27 Nov 2022 22:06:02 +0100 Subject: [PATCH 0908/4345] regulator: da9211: Use irq handler when ready [ Upstream commit 02228f6aa6a64d588bc31e3267d05ff184d772eb ] If the system does not come from reset (like when it is kexec()), the regulator might have an IRQ waiting for us. If we enable the IRQ handler before its structures are ready, we crash. This patch fixes: [ 1.141839] Unable to handle kernel read from unreadable memory at virtual address 0000000000000078 [ 1.316096] Call trace: [ 1.316101] blocking_notifier_call_chain+0x20/0xa8 [ 1.322757] cpu cpu0: dummy supplies not allowed for exclusive requests [ 1.327823] regulator_notifier_call_chain+0x1c/0x2c [ 1.327825] da9211_irq_handler+0x68/0xf8 [ 1.327829] irq_thread+0x11c/0x234 [ 1.327833] kthread+0x13c/0x154 Signed-off-by: Ricardo Ribalda Reviewed-by: Adam Ward Link: https://lore.kernel.org/r/20221124-da9211-v2-0-1779e3c5d491@chromium.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/da9211-regulator.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index e01b32d1fa17..00828f5baa97 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -498,6 +498,12 @@ static int da9211_i2c_probe(struct i2c_client *i2c) chip->chip_irq = i2c->irq; + ret = da9211_regulator_init(chip); + if (ret < 0) { + dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); + return ret; + } + if (chip->chip_irq != 0) { ret = devm_request_threaded_irq(chip->dev, chip->chip_irq, NULL, da9211_irq_handler, @@ -512,11 +518,6 @@ static int da9211_i2c_probe(struct i2c_client *i2c) dev_warn(chip->dev, "No IRQ configured\n"); } - ret = da9211_regulator_init(chip); - - if (ret < 0) - dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); - return ret; } From d83cac6c00b8020b418d0bae2fffc7746c59f2b8 Mon Sep 17 00:00:00 2001 From: Emanuele Ghidoli Date: Fri, 23 Dec 2022 09:02:47 +0100 Subject: [PATCH 0909/4345] ASoC: wm8904: fix wrong outputs volume after power reactivation [ Upstream commit 472a6309c6467af89dbf660a8310369cc9cb041f ] Restore volume after charge pump and PGA activation to ensure that volume settings are correctly applied when re-enabling codec from SND_SOC_BIAS_OFF state. CLASS_W, CHARGE_PUMP and POWER_MANAGEMENT_2 register configuration affect how the volume register are applied and must be configured first. Fixes: a91eb199e4dc ("ASoC: Initial WM8904 CODEC driver") Link: https://lore.kernel.org/all/c7864c35-738c-a867-a6a6-ddf9f98df7e7@gmail.com/ Signed-off-by: Emanuele Ghidoli Signed-off-by: Francesco Dolcini Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20221223080247.7258-1-francesco@dolcini.it Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/wm8904.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index 1c360bae5652..cc96c9bdff41 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -697,6 +697,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w, int dcs_mask; int dcs_l, dcs_r; int dcs_l_reg, dcs_r_reg; + int an_out_reg; int timeout; int pwr_reg; @@ -712,6 +713,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w, dcs_mask = WM8904_DCS_ENA_CHAN_0 | WM8904_DCS_ENA_CHAN_1; dcs_r_reg = WM8904_DC_SERVO_8; dcs_l_reg = WM8904_DC_SERVO_9; + an_out_reg = WM8904_ANALOGUE_OUT1_LEFT; dcs_l = 0; dcs_r = 1; break; @@ -720,6 +722,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w, dcs_mask = WM8904_DCS_ENA_CHAN_2 | WM8904_DCS_ENA_CHAN_3; dcs_r_reg = WM8904_DC_SERVO_6; dcs_l_reg = WM8904_DC_SERVO_7; + an_out_reg = WM8904_ANALOGUE_OUT2_LEFT; dcs_l = 2; dcs_r = 3; break; @@ -792,6 +795,10 @@ static int out_pga_event(struct snd_soc_dapm_widget *w, snd_soc_component_update_bits(component, reg, WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP, WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP); + + /* Update volume, requires PGA to be powered */ + val = snd_soc_component_read(component, an_out_reg); + snd_soc_component_write(component, an_out_reg, val); break; case SND_SOC_DAPM_POST_PMU: From 0d0675bc33e655297562681200b06fafa5eb7ed8 Mon Sep 17 00:00:00 2001 From: Tung Nguyen Date: Thu, 5 Jan 2023 06:02:51 +0000 Subject: [PATCH 0910/4345] tipc: fix unexpected link reset due to discovery messages [ Upstream commit c244c092f1ed2acfb5af3d3da81e22367d3dd733 ] This unexpected behavior is observed: node 1 | node 2 ------ | ------ link is established | link is established reboot | link is reset up | send discovery message receive discovery message | link is established | link is established send discovery message | | receive discovery message | link is reset (unexpected) | send reset message link is reset | It is due to delayed re-discovery as described in function tipc_node_check_dest(): "this link endpoint has already reset and re-established contact with the peer, before receiving a discovery message from that node." However, commit 598411d70f85 has changed the condition for calling tipc_node_link_down() which was the acceptance of new media address. This commit fixes this by restoring the old and correct behavior. Fixes: 598411d70f85 ("tipc: make resetting of links non-atomic") Acked-by: Jon Maloy Signed-off-by: Tung Nguyen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/tipc/node.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/tipc/node.c b/net/tipc/node.c index 7589f2ac6fd0..38f61dccb855 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1152,8 +1152,9 @@ void tipc_node_check_dest(struct net *net, u32 addr, bool addr_match = false; bool sign_match = false; bool link_up = false; + bool link_is_reset = false; bool accept_addr = false; - bool reset = true; + bool reset = false; char *if_name; unsigned long intv; u16 session; @@ -1173,14 +1174,14 @@ void tipc_node_check_dest(struct net *net, u32 addr, /* Prepare to validate requesting node's signature and media address */ l = le->link; link_up = l && tipc_link_is_up(l); + link_is_reset = l && tipc_link_is_reset(l); addr_match = l && !memcmp(&le->maddr, maddr, sizeof(*maddr)); sign_match = (signature == n->signature); /* These three flags give us eight permutations: */ if (sign_match && addr_match && link_up) { - /* All is fine. Do nothing. */ - reset = false; + /* All is fine. Ignore requests. */ /* Peer node is not a container/local namespace */ if (!n->peer_hash_mix) n->peer_hash_mix = hash_mixes; @@ -1205,6 +1206,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, */ accept_addr = true; *respond = true; + reset = true; } else if (!sign_match && addr_match && link_up) { /* Peer node rebooted. Two possibilities: * - Delayed re-discovery; this link endpoint has already @@ -1236,6 +1238,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, n->signature = signature; accept_addr = true; *respond = true; + reset = true; } if (!accept_addr) @@ -1264,6 +1267,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, tipc_link_fsm_evt(l, LINK_RESET_EVT); if (n->state == NODE_FAILINGOVER) tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT); + link_is_reset = tipc_link_is_reset(l); le->link = l; n->link_cnt++; tipc_node_calculate_timer(n, l); @@ -1276,7 +1280,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, memcpy(&le->maddr, maddr, sizeof(*maddr)); exit: tipc_node_write_unlock(n); - if (reset && l && !tipc_link_is_reset(l)) + if (reset && !link_is_reset) tipc_node_link_down(n, b->identity, false); tipc_node_put(n); } From d9be5b57ab2cf1238f02e5200d0d123a03f9154b Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Thu, 29 Oct 2020 10:45:40 +0530 Subject: [PATCH 0911/4345] octeontx2-af: Update get/set resource count functions [ Upstream commit cdd41e878526797df29903fe592d6a26b096ac7d ] Since multiple blocks of same type are present in 98xx, modify functions which get resource count and which update resource count to work with individual block address instead of block type. Reviewed-by: Jesse Brandeburg Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Rakesh Babu Signed-off-by: Jakub Kicinski Stable-dep-of: b4e9b8763e41 ("octeontx2-af: Fix LMAC config in cgx_lmac_rx_tx_enable") Signed-off-by: Sasha Levin --- .../net/ethernet/marvell/octeontx2/af/rvu.c | 73 +++++++++++++------ .../net/ethernet/marvell/octeontx2/af/rvu.h | 2 + 2 files changed, 53 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index c26652436c53..9bab525ecd86 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -316,31 +316,36 @@ static void rvu_update_rsrc_map(struct rvu *rvu, struct rvu_pfvf *pfvf, block->fn_map[lf] = attach ? pcifunc : 0; - switch (block->type) { - case BLKTYPE_NPA: + switch (block->addr) { + case BLKADDR_NPA: pfvf->npalf = attach ? true : false; num_lfs = pfvf->npalf; break; - case BLKTYPE_NIX: + case BLKADDR_NIX0: + case BLKADDR_NIX1: pfvf->nixlf = attach ? true : false; num_lfs = pfvf->nixlf; break; - case BLKTYPE_SSO: + case BLKADDR_SSO: attach ? pfvf->sso++ : pfvf->sso--; num_lfs = pfvf->sso; break; - case BLKTYPE_SSOW: + case BLKADDR_SSOW: attach ? pfvf->ssow++ : pfvf->ssow--; num_lfs = pfvf->ssow; break; - case BLKTYPE_TIM: + case BLKADDR_TIM: attach ? pfvf->timlfs++ : pfvf->timlfs--; num_lfs = pfvf->timlfs; break; - case BLKTYPE_CPT: + case BLKADDR_CPT0: attach ? pfvf->cptlfs++ : pfvf->cptlfs--; num_lfs = pfvf->cptlfs; break; + case BLKADDR_CPT1: + attach ? pfvf->cpt1_lfs++ : pfvf->cpt1_lfs--; + num_lfs = pfvf->cpt1_lfs; + break; } reg = is_pf ? block->pf_lfcnt_reg : block->vf_lfcnt_reg; @@ -1035,7 +1040,30 @@ int rvu_mbox_handler_ready(struct rvu *rvu, struct msg_req *req, /* Get current count of a RVU block's LF/slots * provisioned to a given RVU func. */ -static u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blktype) +u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr) +{ + switch (blkaddr) { + case BLKADDR_NPA: + return pfvf->npalf ? 1 : 0; + case BLKADDR_NIX0: + case BLKADDR_NIX1: + return pfvf->nixlf ? 1 : 0; + case BLKADDR_SSO: + return pfvf->sso; + case BLKADDR_SSOW: + return pfvf->ssow; + case BLKADDR_TIM: + return pfvf->timlfs; + case BLKADDR_CPT0: + return pfvf->cptlfs; + case BLKADDR_CPT1: + return pfvf->cpt1_lfs; + } + return 0; +} + +/* Return true if LFs of block type are attached to pcifunc */ +static bool is_blktype_attached(struct rvu_pfvf *pfvf, int blktype) { switch (blktype) { case BLKTYPE_NPA: @@ -1043,15 +1071,16 @@ static u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blktype) case BLKTYPE_NIX: return pfvf->nixlf ? 1 : 0; case BLKTYPE_SSO: - return pfvf->sso; + return !!pfvf->sso; case BLKTYPE_SSOW: - return pfvf->ssow; + return !!pfvf->ssow; case BLKTYPE_TIM: - return pfvf->timlfs; + return !!pfvf->timlfs; case BLKTYPE_CPT: - return pfvf->cptlfs; + return pfvf->cptlfs || pfvf->cpt1_lfs; } - return 0; + + return false; } bool is_pffunc_map_valid(struct rvu *rvu, u16 pcifunc, int blktype) @@ -1064,7 +1093,7 @@ bool is_pffunc_map_valid(struct rvu *rvu, u16 pcifunc, int blktype) pfvf = rvu_get_pfvf(rvu, pcifunc); /* Check if this PFFUNC has a LF of type blktype attached */ - if (!rvu_get_rsrc_mapcount(pfvf, blktype)) + if (!is_blktype_attached(pfvf, blktype)) return false; return true; @@ -1105,7 +1134,7 @@ static void rvu_detach_block(struct rvu *rvu, int pcifunc, int blktype) block = &hw->block[blkaddr]; - num_lfs = rvu_get_rsrc_mapcount(pfvf, block->type); + num_lfs = rvu_get_rsrc_mapcount(pfvf, block->addr); if (!num_lfs) return; @@ -1226,7 +1255,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, int free_lfs, mappedlfs; /* Only one NPA LF can be attached */ - if (req->npalf && !rvu_get_rsrc_mapcount(pfvf, BLKTYPE_NPA)) { + if (req->npalf && !is_blktype_attached(pfvf, BLKTYPE_NPA)) { block = &hw->block[BLKADDR_NPA]; free_lfs = rvu_rsrc_free_count(&block->lf); if (!free_lfs) @@ -1239,7 +1268,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, } /* Only one NIX LF can be attached */ - if (req->nixlf && !rvu_get_rsrc_mapcount(pfvf, BLKTYPE_NIX)) { + if (req->nixlf && !is_blktype_attached(pfvf, BLKTYPE_NIX)) { block = &hw->block[BLKADDR_NIX0]; free_lfs = rvu_rsrc_free_count(&block->lf); if (!free_lfs) @@ -1260,7 +1289,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, pcifunc, req->sso, block->lf.max); return -EINVAL; } - mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type); + mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); free_lfs = rvu_rsrc_free_count(&block->lf); /* Check if additional resources are available */ if (req->sso > mappedlfs && @@ -1276,7 +1305,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, pcifunc, req->sso, block->lf.max); return -EINVAL; } - mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type); + mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); free_lfs = rvu_rsrc_free_count(&block->lf); if (req->ssow > mappedlfs && ((req->ssow - mappedlfs) > free_lfs)) @@ -1291,7 +1320,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, pcifunc, req->timlfs, block->lf.max); return -EINVAL; } - mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type); + mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); free_lfs = rvu_rsrc_free_count(&block->lf); if (req->timlfs > mappedlfs && ((req->timlfs - mappedlfs) > free_lfs)) @@ -1306,7 +1335,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, pcifunc, req->cptlfs, block->lf.max); return -EINVAL; } - mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type); + mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); free_lfs = rvu_rsrc_free_count(&block->lf); if (req->cptlfs > mappedlfs && ((req->cptlfs - mappedlfs) > free_lfs)) @@ -1942,7 +1971,7 @@ static void rvu_blklf_teardown(struct rvu *rvu, u16 pcifunc, u8 blkaddr) block = &rvu->hw->block[blkaddr]; num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc), - block->type); + block->addr); if (!num_lfs) return; for (slot = 0; slot < num_lfs; slot++) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 90eed3160915..0cb5093744fe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -137,6 +137,7 @@ struct rvu_pfvf { u16 ssow; u16 cptlfs; u16 timlfs; + u16 cpt1_lfs; u8 cgx_lmac; /* Block LF's MSIX vector info */ @@ -420,6 +421,7 @@ void rvu_free_rsrc(struct rsrc_bmap *rsrc, int id); int rvu_rsrc_free_count(struct rsrc_bmap *rsrc); int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc); bool rvu_rsrc_check_contig(struct rsrc_bmap *rsrc, int nrsrc); +u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr); int rvu_get_pf(u16 pcifunc); struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc); void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf); From 8e2bfcfaabc30a392030089d8dee21bf2eb68f5b Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Thu, 29 Oct 2020 10:45:43 +0530 Subject: [PATCH 0912/4345] octeontx2-af: Map NIX block from CGX connection [ Upstream commit c5a73b632b901c4b07d156bb8a8a2c5517678f35 ] Firmware configures NIX block mapping for all CGXs to achieve maximum throughput. This patch reads the configuration and create mapping between RVU PF and NIX blocks. And for LBK VFs assign NIX0 for even numbered VFs and NIX1 for odd numbered VFs. Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Rakesh Babu Signed-off-by: Jakub Kicinski Stable-dep-of: b4e9b8763e41 ("octeontx2-af: Fix LMAC config in cgx_lmac_rx_tx_enable") Signed-off-by: Sasha Levin --- .../net/ethernet/marvell/octeontx2/af/cgx.c | 13 +++- .../net/ethernet/marvell/octeontx2/af/cgx.h | 5 ++ .../net/ethernet/marvell/octeontx2/af/rvu.c | 61 ++++++++++++++++++- .../net/ethernet/marvell/octeontx2/af/rvu.h | 2 + .../ethernet/marvell/octeontx2/af/rvu_cgx.c | 15 +++++ .../ethernet/marvell/octeontx2/af/rvu_nix.c | 21 +++++-- 6 files changed, 107 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index fc27a40202c6..1a8f5a039d50 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -145,6 +145,16 @@ int cgx_get_cgxid(void *cgxd) return cgx->cgx_id; } +u8 cgx_lmac_get_p2x(int cgx_id, int lmac_id) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + u64 cfg; + + cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_CFG); + + return (cfg & CMR_P2X_SEL_MASK) >> CMR_P2X_SEL_SHIFT; +} + /* Ensure the required lock for event queue(where asynchronous events are * posted) is acquired before calling this API. Else an asynchronous event(with * latest link status) can reach the destination before this function returns @@ -814,8 +824,7 @@ static int cgx_lmac_verify_fwi_version(struct cgx *cgx) minor_ver = FIELD_GET(RESP_MINOR_VER, resp); dev_dbg(dev, "Firmware command interface version = %d.%d\n", major_ver, minor_ver); - if (major_ver != CGX_FIRMWARE_MAJOR_VER || - minor_ver != CGX_FIRMWARE_MINOR_VER) + if (major_ver != CGX_FIRMWARE_MAJOR_VER) return -EIO; else return 0; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 27ca3291682b..bcfc3e5f66bb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -27,6 +27,10 @@ /* Registers */ #define CGXX_CMRX_CFG 0x00 +#define CMR_P2X_SEL_MASK GENMASK_ULL(61, 59) +#define CMR_P2X_SEL_SHIFT 59ULL +#define CMR_P2X_SEL_NIX0 1ULL +#define CMR_P2X_SEL_NIX1 2ULL #define CMR_EN BIT_ULL(55) #define DATA_PKT_TX_EN BIT_ULL(53) #define DATA_PKT_RX_EN BIT_ULL(54) @@ -142,5 +146,6 @@ int cgx_lmac_get_pause_frm(void *cgxd, int lmac_id, int cgx_lmac_set_pause_frm(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause); void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable); +u8 cgx_lmac_get_p2x(int cgx_id, int lmac_id); #endif /* CGX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 9bab525ecd86..acbc67074f59 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1208,6 +1208,58 @@ int rvu_mbox_handler_detach_resources(struct rvu *rvu, return rvu_detach_rsrcs(rvu, detach, detach->hdr.pcifunc); } +static int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + int blkaddr = BLKADDR_NIX0, vf; + struct rvu_pfvf *pf; + + /* All CGX mapped PFs are set with assigned NIX block during init */ + if (is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) { + pf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); + blkaddr = pf->nix_blkaddr; + } else if (is_afvf(pcifunc)) { + vf = pcifunc - 1; + /* Assign NIX based on VF number. All even numbered VFs get + * NIX0 and odd numbered gets NIX1 + */ + blkaddr = (vf & 1) ? BLKADDR_NIX1 : BLKADDR_NIX0; + /* NIX1 is not present on all silicons */ + if (!is_block_implemented(rvu->hw, BLKADDR_NIX1)) + blkaddr = BLKADDR_NIX0; + } + + switch (blkaddr) { + case BLKADDR_NIX1: + pfvf->nix_blkaddr = BLKADDR_NIX1; + break; + case BLKADDR_NIX0: + default: + pfvf->nix_blkaddr = BLKADDR_NIX0; + break; + } + + return pfvf->nix_blkaddr; +} + +static int rvu_get_attach_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc) +{ + int blkaddr; + + switch (blktype) { + case BLKTYPE_NIX: + blkaddr = rvu_get_nix_blkaddr(rvu, pcifunc); + break; + default: + return rvu_get_blkaddr(rvu, blktype, 0); + }; + + if (is_block_implemented(rvu->hw, blkaddr)) + return blkaddr; + + return -ENODEV; +} + static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, int num_lfs) { @@ -1221,7 +1273,7 @@ static void rvu_attach_block(struct rvu *rvu, int pcifunc, if (!num_lfs) return; - blkaddr = rvu_get_blkaddr(rvu, blktype, 0); + blkaddr = rvu_get_attach_blkaddr(rvu, blktype, pcifunc); if (blkaddr < 0) return; @@ -1250,9 +1302,9 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, struct rsrc_attach *req, u16 pcifunc) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + int free_lfs, mappedlfs, blkaddr; struct rvu_hwinfo *hw = rvu->hw; struct rvu_block *block; - int free_lfs, mappedlfs; /* Only one NPA LF can be attached */ if (req->npalf && !is_blktype_attached(pfvf, BLKTYPE_NPA)) { @@ -1269,7 +1321,10 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, /* Only one NIX LF can be attached */ if (req->nixlf && !is_blktype_attached(pfvf, BLKTYPE_NIX)) { - block = &hw->block[BLKADDR_NIX0]; + blkaddr = rvu_get_attach_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (blkaddr < 0) + return blkaddr; + block = &hw->block[blkaddr]; free_lfs = rvu_rsrc_free_count(&block->lf); if (!free_lfs) goto fail; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 0cb5093744fe..fc6d785b98dd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -183,6 +183,8 @@ struct rvu_pfvf { bool cgx_in_use; /* this PF/VF using CGX? */ int cgx_users; /* number of cgx users - used only by PFs */ + + u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */ }; struct nix_txsch { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index f4ecc755eaff..6c6b411e78fd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -74,6 +74,20 @@ void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu) return rvu->cgx_idmap[cgx_id]; } +/* Based on P2X connectivity find mapped NIX block for a PF */ +static void rvu_map_cgx_nix_block(struct rvu *rvu, int pf, + int cgx_id, int lmac_id) +{ + struct rvu_pfvf *pfvf = &rvu->pf[pf]; + u8 p2x; + + p2x = cgx_lmac_get_p2x(cgx_id, lmac_id); + /* Firmware sets P2X_SELECT as either NIX0 or NIX1 */ + pfvf->nix_blkaddr = BLKADDR_NIX0; + if (p2x == CMR_P2X_SEL_NIX1) + pfvf->nix_blkaddr = BLKADDR_NIX1; +} + static int rvu_map_cgx_lmac_pf(struct rvu *rvu) { struct npc_pkind *pkind = &rvu->hw->pkind; @@ -117,6 +131,7 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) rvu->cgxlmac2pf_map[CGX_OFFSET(cgx) + lmac] = 1 << pf; free_pkind = rvu_alloc_rsrc(&pkind->rsrc); pkind->pfchan_map[free_pkind] = ((pf) & 0x3F) << 16; + rvu_map_cgx_nix_block(rvu, pf, cgx, lmac); rvu->cgx_mapped_pfs++; } } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index f6a3cf3e6f23..9886a30e9723 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -187,8 +187,8 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr, static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + int pkind, pf, vf, lbkid; u8 cgx_id, lmac_id; - int pkind, pf, vf; int err; pf = rvu_get_pf(pcifunc); @@ -221,13 +221,24 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) case NIX_INTF_TYPE_LBK: vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1; + /* If NIX1 block is present on the silicon then NIXes are + * assigned alternatively for lbk interfaces. NIX0 should + * send packets on lbk link 1 channels and NIX1 should send + * on lbk link 0 channels for the communication between + * NIX0 and NIX1. + */ + lbkid = 0; + if (rvu->hw->lbk_links > 1) + lbkid = vf & 0x1 ? 0 : 1; + /* Note that AF's VFs work in pairs and talk over consecutive * loopback channels.Therefore if odd number of AF VFs are * enabled then the last VF remains with no pair. */ - pfvf->rx_chan_base = NIX_CHAN_LBK_CHX(0, vf); - pfvf->tx_chan_base = vf & 0x1 ? NIX_CHAN_LBK_CHX(0, vf - 1) : - NIX_CHAN_LBK_CHX(0, vf + 1); + pfvf->rx_chan_base = NIX_CHAN_LBK_CHX(lbkid, vf); + pfvf->tx_chan_base = vf & 0x1 ? + NIX_CHAN_LBK_CHX(lbkid, vf - 1) : + NIX_CHAN_LBK_CHX(lbkid, vf + 1); pfvf->rx_chan_cnt = 1; pfvf->tx_chan_cnt = 1; rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf, @@ -3157,7 +3168,7 @@ int rvu_nix_init(struct rvu *rvu) hw->cgx = (cfg >> 12) & 0xF; hw->lmac_per_cgx = (cfg >> 8) & 0xF; hw->cgx_links = hw->cgx * hw->lmac_per_cgx; - hw->lbk_links = 1; + hw->lbk_links = (cfg >> 24) & 0xF; hw->sdp_links = 1; /* Initialize admin queue */ From 14e72a56e16c1924f07c0719fcf04b64a55a9af7 Mon Sep 17 00:00:00 2001 From: Angela Czubak Date: Thu, 5 Jan 2023 21:31:07 +0530 Subject: [PATCH 0913/4345] octeontx2-af: Fix LMAC config in cgx_lmac_rx_tx_enable [ Upstream commit b4e9b8763e417db31c7088103cc557d55cb7a8f5 ] PF netdev can request AF to enable or disable reception and transmission on assigned CGX::LMAC. The current code instead of disabling or enabling 'reception and transmission' also disables/enable the LMAC. This patch fixes this issue. Fixes: 1435f66a28b4 ("octeontx2-af: CGX Rx/Tx enable/disable mbox handlers") Signed-off-by: Angela Czubak Signed-off-by: Hariprasad Kelam Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230105160107.17638-1-hkelam@marvell.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 4 ++-- drivers/net/ethernet/marvell/octeontx2/af/cgx.h | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 1a8f5a039d50..c0a0a31272cc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -350,9 +350,9 @@ int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable) cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_CFG); if (enable) - cfg |= CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN; + cfg |= DATA_PKT_RX_EN | DATA_PKT_TX_EN; else - cfg &= ~(CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN); + cfg &= ~(DATA_PKT_RX_EN | DATA_PKT_TX_EN); cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index bcfc3e5f66bb..e176a6c654ef 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -31,7 +31,6 @@ #define CMR_P2X_SEL_SHIFT 59ULL #define CMR_P2X_SEL_NIX0 1ULL #define CMR_P2X_SEL_NIX1 2ULL -#define CMR_EN BIT_ULL(55) #define DATA_PKT_TX_EN BIT_ULL(53) #define DATA_PKT_RX_EN BIT_ULL(54) #define CGX_LMAC_TYPE_SHIFT 40 From 92b30a27e4fa5929d94d863dc1eb27b231590016 Mon Sep 17 00:00:00 2001 From: Roger Pau Monne Date: Wed, 30 Nov 2022 17:36:02 +0100 Subject: [PATCH 0914/4345] hvc/xen: lock console list traversal MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c0dccad87cf68fc6012aec7567e354353097ec1a ] The currently lockless access to the xen console list in vtermno_to_xencons() is incorrect, as additions and removals from the list can happen anytime, and as such the traversal of the list to get the private console data for a given termno needs to happen with the lock held. Note users that modify the list already do so with the lock taken. Adjust current lock takers to use the _irq{save,restore} helpers, since the context in which vtermno_to_xencons() is called can have interrupts disabled. Use the _irq{save,restore} set of helpers to switch the current callers to disable interrupts in the locked region. I haven't checked if existing users could instead use the _irq variant, as I think it's safer to use _irq{save,restore} upfront. While there switch from using list_for_each_entry_safe to list_for_each_entry: the current entry cursor won't be removed as part of the code in the loop body, so using the _safe variant is pointless. Fixes: 02e19f9c7cac ('hvc_xen: implement multiconsole support') Signed-off-by: Roger Pau Monné Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/20221130163611.14686-1-roger.pau@citrix.com Signed-off-by: Juergen Gross Signed-off-by: Sasha Levin --- drivers/tty/hvc/hvc_xen.c | 46 ++++++++++++++++++++++++--------------- 1 file changed, 29 insertions(+), 17 deletions(-) diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 7948660e042f..6f387a4fd96a 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -52,17 +52,22 @@ static DEFINE_SPINLOCK(xencons_lock); static struct xencons_info *vtermno_to_xencons(int vtermno) { - struct xencons_info *entry, *n, *ret = NULL; + struct xencons_info *entry, *ret = NULL; + unsigned long flags; - if (list_empty(&xenconsoles)) - return NULL; + spin_lock_irqsave(&xencons_lock, flags); + if (list_empty(&xenconsoles)) { + spin_unlock_irqrestore(&xencons_lock, flags); + return NULL; + } - list_for_each_entry_safe(entry, n, &xenconsoles, list) { + list_for_each_entry(entry, &xenconsoles, list) { if (entry->vtermno == vtermno) { ret = entry; break; } } + spin_unlock_irqrestore(&xencons_lock, flags); return ret; } @@ -223,7 +228,7 @@ static int xen_hvm_console_init(void) { int r; uint64_t v = 0; - unsigned long gfn; + unsigned long gfn, flags; struct xencons_info *info; if (!xen_hvm_domain()) @@ -258,9 +263,9 @@ static int xen_hvm_console_init(void) goto err; info->vtermno = HVC_COOKIE; - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_add_tail(&info->list, &xenconsoles); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; err: @@ -283,6 +288,7 @@ static int xencons_info_pv_init(struct xencons_info *info, int vtermno) static int xen_pv_console_init(void) { struct xencons_info *info; + unsigned long flags; if (!xen_pv_domain()) return -ENODEV; @@ -299,9 +305,9 @@ static int xen_pv_console_init(void) /* already configured */ return 0; } - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); xencons_info_pv_init(info, HVC_COOKIE); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; } @@ -309,6 +315,7 @@ static int xen_pv_console_init(void) static int xen_initial_domain_console_init(void) { struct xencons_info *info; + unsigned long flags; if (!xen_initial_domain()) return -ENODEV; @@ -323,9 +330,9 @@ static int xen_initial_domain_console_init(void) info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false); info->vtermno = HVC_COOKIE; - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_add_tail(&info->list, &xenconsoles); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; } @@ -380,10 +387,12 @@ static void xencons_free(struct xencons_info *info) static int xen_console_remove(struct xencons_info *info) { + unsigned long flags; + xencons_disconnect_backend(info); - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_del(&info->list); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); if (info->xbdev != NULL) xencons_free(info); else { @@ -464,6 +473,7 @@ static int xencons_probe(struct xenbus_device *dev, { int ret, devid; struct xencons_info *info; + unsigned long flags; devid = dev->nodename[strlen(dev->nodename) - 1] - '0'; if (devid == 0) @@ -482,9 +492,9 @@ static int xencons_probe(struct xenbus_device *dev, ret = xencons_connect_backend(dev, info); if (ret < 0) goto error; - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_add_tail(&info->list, &xenconsoles); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; @@ -583,10 +593,12 @@ static int __init xen_hvc_init(void) info->hvc = hvc_alloc(HVC_COOKIE, info->irq, ops, 256); if (IS_ERR(info->hvc)) { + unsigned long flags; + r = PTR_ERR(info->hvc); - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_del(&info->list); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); if (info->irq) unbind_from_irqhandler(info->irq, NULL); kfree(info); From 0ca78c99656f5c448567db1e148367aa3b01c80a Mon Sep 17 00:00:00 2001 From: Minsuk Kang Date: Fri, 6 Jan 2023 17:23:44 +0900 Subject: [PATCH 0915/4345] nfc: pn533: Wait for out_urb's completion in pn533_usb_send_frame() [ Upstream commit 9dab880d675b9d0dd56c6428e4e8352a3339371d ] Fix a use-after-free that occurs in hcd when in_urb sent from pn533_usb_send_frame() is completed earlier than out_urb. Its callback frees the skb data in pn533_send_async_complete() that is used as a transfer buffer of out_urb. Wait before sending in_urb until the callback of out_urb is called. To modify the callback of out_urb alone, separate the complete function of out_urb and ack_urb. Found by a modified version of syzkaller. BUG: KASAN: use-after-free in dummy_timer Call Trace: memcpy (mm/kasan/shadow.c:65) dummy_perform_transfer (drivers/usb/gadget/udc/dummy_hcd.c:1352) transfer (drivers/usb/gadget/udc/dummy_hcd.c:1453) dummy_timer (drivers/usb/gadget/udc/dummy_hcd.c:1972) arch_static_branch (arch/x86/include/asm/jump_label.h:27) static_key_false (include/linux/jump_label.h:207) timer_expire_exit (include/trace/events/timer.h:127) call_timer_fn (kernel/time/timer.c:1475) expire_timers (kernel/time/timer.c:1519) __run_timers (kernel/time/timer.c:1790) run_timer_softirq (kernel/time/timer.c:1803) Fixes: c46ee38620a2 ("NFC: pn533: add NXP pn533 nfc device driver") Signed-off-by: Minsuk Kang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/nfc/pn533/usb.c | 44 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 41 insertions(+), 3 deletions(-) diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index 84f2983bf384..57b07446bb76 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -153,10 +153,17 @@ static int pn533_usb_send_ack(struct pn533 *dev, gfp_t flags) return usb_submit_urb(phy->ack_urb, flags); } +struct pn533_out_arg { + struct pn533_usb_phy *phy; + struct completion done; +}; + static int pn533_usb_send_frame(struct pn533 *dev, struct sk_buff *out) { struct pn533_usb_phy *phy = dev->phy; + struct pn533_out_arg arg; + void *cntx; int rc; if (phy->priv == NULL) @@ -168,10 +175,17 @@ static int pn533_usb_send_frame(struct pn533 *dev, print_hex_dump_debug("PN533 TX: ", DUMP_PREFIX_NONE, 16, 1, out->data, out->len, false); + init_completion(&arg.done); + cntx = phy->out_urb->context; + phy->out_urb->context = &arg; + rc = usb_submit_urb(phy->out_urb, GFP_KERNEL); if (rc) return rc; + wait_for_completion(&arg.done); + phy->out_urb->context = cntx; + if (dev->protocol_type == PN533_PROTO_REQ_RESP) { /* request for response for sent packet directly */ rc = pn533_submit_urb_for_response(phy, GFP_KERNEL); @@ -412,7 +426,31 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy) return arg.rc; } -static void pn533_send_complete(struct urb *urb) +static void pn533_out_complete(struct urb *urb) +{ + struct pn533_out_arg *arg = urb->context; + struct pn533_usb_phy *phy = arg->phy; + + switch (urb->status) { + case 0: + break; /* success */ + case -ECONNRESET: + case -ENOENT: + dev_dbg(&phy->udev->dev, + "The urb has been stopped (status %d)\n", + urb->status); + break; + case -ESHUTDOWN: + default: + nfc_err(&phy->udev->dev, + "Urb failure (status %d)\n", + urb->status); + } + + complete(&arg->done); +} + +static void pn533_ack_complete(struct urb *urb) { struct pn533_usb_phy *phy = urb->context; @@ -500,10 +538,10 @@ static int pn533_usb_probe(struct usb_interface *interface, usb_fill_bulk_urb(phy->out_urb, phy->udev, usb_sndbulkpipe(phy->udev, out_endpoint), - NULL, 0, pn533_send_complete, phy); + NULL, 0, pn533_out_complete, phy); usb_fill_bulk_urb(phy->ack_urb, phy->udev, usb_sndbulkpipe(phy->udev, out_endpoint), - NULL, 0, pn533_send_complete, phy); + NULL, 0, pn533_ack_complete, phy); switch (id->driver_info) { case PN533_DEVICE_STD: From 453277feb41c2235cf2c0de9209eef962c401457 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 7 Jan 2023 19:10:04 +0200 Subject: [PATCH 0916/4345] net/sched: act_mpls: Fix warning during failed attribute validation [ Upstream commit 9e17f99220d111ea031b44153fdfe364b0024ff2 ] The 'TCA_MPLS_LABEL' attribute is of 'NLA_U32' type, but has a validation type of 'NLA_VALIDATE_FUNCTION'. This is an invalid combination according to the comment above 'struct nla_policy': " Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: NLA_BINARY Validation function called for the attribute. All other Unused - but note that it's a union " This can trigger the warning [1] in nla_get_range_unsigned() when validation of the attribute fails. Despite being of 'NLA_U32' type, the associated 'min'/'max' fields in the policy are negative as they are aliased by the 'validate' field. Fix by changing the attribute type to 'NLA_BINARY' which is consistent with the above comment and all other users of NLA_POLICY_VALIDATE_FN(). As a result, move the length validation to the validation function. No regressions in MPLS tests: # ./tdc.py -f tc-tests/actions/mpls.json [...] # echo $? 0 [1] WARNING: CPU: 0 PID: 17743 at lib/nlattr.c:118 nla_get_range_unsigned+0x1d8/0x1e0 lib/nlattr.c:117 Modules linked in: CPU: 0 PID: 17743 Comm: syz-executor.0 Not tainted 6.1.0-rc8 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014 RIP: 0010:nla_get_range_unsigned+0x1d8/0x1e0 lib/nlattr.c:117 [...] Call Trace: __netlink_policy_dump_write_attr+0x23d/0x990 net/netlink/policy.c:310 netlink_policy_dump_write_attr+0x22/0x30 net/netlink/policy.c:411 netlink_ack_tlv_fill net/netlink/af_netlink.c:2454 [inline] netlink_ack+0x546/0x760 net/netlink/af_netlink.c:2506 netlink_rcv_skb+0x1b7/0x240 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:6109 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2482 ___sys_sendmsg net/socket.c:2536 [inline] __sys_sendmsg+0x197/0x230 net/socket.c:2565 __do_sys_sendmsg net/socket.c:2574 [inline] __se_sys_sendmsg net/socket.c:2572 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2572 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Link: https://lore.kernel.org/netdev/CAO4mrfdmjvRUNbDyP0R03_DrD_eFCLCguz6OxZ2TYRSv0K9gxA@mail.gmail.com/ Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC") Reported-by: Wei Chen Tested-by: Wei Chen Signed-off-by: Ido Schimmel Reviewed-by: Alexander Duyck Link: https://lore.kernel.org/r/20230107171004.608436-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/act_mpls.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index d1486ea496a2..09799412b248 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -133,6 +133,11 @@ static int valid_label(const struct nlattr *attr, { const u32 *label = nla_data(attr); + if (nla_len(attr) != sizeof(*label)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length"); + return -EINVAL; + } + if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) { NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range"); return -EINVAL; @@ -144,7 +149,8 @@ static int valid_label(const struct nlattr *attr, static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = { [TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)), [TCA_MPLS_PROTO] = { .type = NLA_U16 }, - [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_U32, valid_label), + [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, + valid_label), [TCA_MPLS_TC] = NLA_POLICY_RANGE(NLA_U8, 0, 7), [TCA_MPLS_TTL] = NLA_POLICY_MIN(NLA_U8, 1), [TCA_MPLS_BOS] = NLA_POLICY_RANGE(NLA_U8, 0, 1), From b3d47227f06f0f3b9e6eafdc32d5d8a3036820f8 Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Mon, 5 Dec 2022 14:26:09 -0800 Subject: [PATCH 0917/4345] net/mlx5: Fix ptp max frequency adjustment range [ Upstream commit fe91d57277eef8bb4aca05acfa337b4a51d0bba4 ] .max_adj of ptp_clock_info acts as an absolute value for the amount in ppb that can be set for a single call of .adjfine. This means that a single call to .getfine cannot be greater than .max_adj or less than -(.max_adj). Provides correct value for max frequency adjustment value supported by devices. Fixes: 3d8c38af1493 ("net/mlx5e: Add PTP Hardware Clock (PHC) support") Signed-off-by: Rahul Rameshbabu Reviewed-by: Gal Pressman Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index c70c1f0ca0c1..44a434b1178b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -440,7 +440,7 @@ static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, static const struct ptp_clock_info mlx5_ptp_clock_info = { .owner = THIS_MODULE, .name = "mlx5_ptp", - .max_adj = 100000000, + .max_adj = 50000000, .n_alarm = 0, .n_ext_ts = 0, .n_per_out = 0, From 092f0c2d1f836498fff8f68b26d529daa24b94a6 Mon Sep 17 00:00:00 2001 From: Gavin Li Date: Tue, 27 Dec 2022 04:54:09 +0200 Subject: [PATCH 0918/4345] net/mlx5e: Don't support encap rules with gbp option [ Upstream commit d515d63cae2cd186acf40deaa8ef33067bb7f637 ] Previously, encap rules with gbp option would be offloaded by mistake but driver does not support gbp option offload. To fix this issue, check if the encap rule has gbp option and don't offload the rule Fixes: d8f9dfae49ce ("net: sched: allow flower to match vxlan options") Signed-off-by: Gavin Li Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index 038a0f1cecec..e44281ae570d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -88,6 +88,8 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[], struct udphdr *udp = (struct udphdr *)(buf); struct vxlanhdr *vxh; + if (tun_key->tun_flags & TUNNEL_VXLAN_OPT) + return -EOPNOTSUPP; vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr)); *ip_proto = IPPROTO_UDP; From 60806adc9be08b209e04f01d8a7a1bb412f3e820 Mon Sep 17 00:00:00 2001 From: Aaron Thompson Date: Fri, 6 Jan 2023 22:22:44 +0000 Subject: [PATCH 0919/4345] mm: Always release pages to the buddy allocator in memblock_free_late(). [ Upstream commit 115d9d77bb0f9152c60b6e8646369fa7f6167593 ] If CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, memblock_free_pages() only releases pages to the buddy allocator if they are not in the deferred range. This is correct for free pages (as defined by for_each_free_mem_pfn_range_in_zone()) because free pages in the deferred range will be initialized and released as part of the deferred init process. memblock_free_pages() is called by memblock_free_late(), which is used to free reserved ranges after memblock_free_all() has run. All pages in reserved ranges have been initialized at that point, and accordingly, those pages are not touched by the deferred init process. This means that currently, if the pages that memblock_free_late() intends to release are in the deferred range, they will never be released to the buddy allocator. They will forever be reserved. In addition, memblock_free_pages() calls kmsan_memblock_free_pages(), which is also correct for free pages but is not correct for reserved pages. KMSAN metadata for reserved pages is initialized by kmsan_init_shadow(), which runs shortly before memblock_free_all(). For both of these reasons, memblock_free_pages() should only be called for free pages, and memblock_free_late() should call __free_pages_core() directly instead. One case where this issue can occur in the wild is EFI boot on x86_64. The x86 EFI code reserves all EFI boot services memory ranges via memblock_reserve() and frees them later via memblock_free_late() (efi_reserve_boot_services() and efi_free_boot_services(), respectively). If any of those ranges happens to fall within the deferred init range, the pages will not be released and that memory will be unavailable. For example, on an Amazon EC2 t3.micro VM (1 GB) booting via EFI: v6.2-rc2: # grep -E 'Node|spanned|present|managed' /proc/zoneinfo Node 0, zone DMA spanned 4095 present 3999 managed 3840 Node 0, zone DMA32 spanned 246652 present 245868 managed 178867 v6.2-rc2 + patch: # grep -E 'Node|spanned|present|managed' /proc/zoneinfo Node 0, zone DMA spanned 4095 present 3999 managed 3840 Node 0, zone DMA32 spanned 246652 present 245868 managed 222816 # +43,949 pages Fixes: 3a80a7fa7989 ("mm: meminit: initialise a subset of struct pages if CONFIG_DEFERRED_STRUCT_PAGE_INIT is set") Signed-off-by: Aaron Thompson Link: https://lore.kernel.org/r/01010185892de53e-e379acfb-7044-4b24-b30a-e2657c1ba989-000000@us-west-2.amazonses.com Signed-off-by: Mike Rapoport (IBM) Signed-off-by: Sasha Levin --- mm/memblock.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/mm/memblock.c b/mm/memblock.c index f72d53957033..f6a4dffb9a88 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1597,7 +1597,13 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { - memblock_free_pages(pfn_to_page(cursor), cursor, 0); + /* + * Reserved pages are always initialized by the end of + * memblock_free_all() (by memmap_init() and, if deferred + * initialization is enabled, memmap_init_reserved_pages()), so + * these pages can be released directly to the buddy allocator. + */ + __free_pages_core(pfn_to_page(cursor), 0); totalram_pages_inc(); } } From cf38e7624179c93ed60482d795677d491d4b0136 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 12 Apr 2021 14:48:43 +0800 Subject: [PATCH 0920/4345] iommu/mediatek-v1: Add error handle for mtk_iommu_probe [ Upstream commit ac304c070c54413efabf29f9e73c54576d329774 ] In the original code, we lack the error handle. This patch adds them. Signed-off-by: Yong Wu Link: https://lore.kernel.org/r/20210412064843.11614-2-yong.wu@mediatek.com Signed-off-by: Joerg Roedel Stable-dep-of: 142e821f68cf ("iommu/mediatek-v1: Fix an error handling path in mtk_iommu_v1_probe()") Signed-off-by: Sasha Levin --- drivers/iommu/mtk_iommu_v1.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 82ddfe9170d4..4ed8bc755f5c 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -624,12 +624,26 @@ static int mtk_iommu_probe(struct platform_device *pdev) ret = iommu_device_register(&data->iommu); if (ret) - return ret; + goto out_sysfs_remove; - if (!iommu_present(&platform_bus_type)) - bus_set_iommu(&platform_bus_type, &mtk_iommu_ops); + if (!iommu_present(&platform_bus_type)) { + ret = bus_set_iommu(&platform_bus_type, &mtk_iommu_ops); + if (ret) + goto out_dev_unreg; + } - return component_master_add_with_match(dev, &mtk_iommu_com_ops, match); + ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match); + if (ret) + goto out_bus_set_null; + return ret; + +out_bus_set_null: + bus_set_iommu(&platform_bus_type, NULL); +out_dev_unreg: + iommu_device_unregister(&data->iommu); +out_sysfs_remove: + iommu_device_sysfs_remove(&data->iommu); + return ret; } static int mtk_iommu_remove(struct platform_device *pdev) From caaea2ab6b6d48f1261ead8c8737502bcf47c297 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 19 Dec 2022 19:06:22 +0100 Subject: [PATCH 0921/4345] iommu/mediatek-v1: Fix an error handling path in mtk_iommu_v1_probe() [ Upstream commit 142e821f68cf5da79ce722cb9c1323afae30e185 ] A clk, prepared and enabled in mtk_iommu_v1_hw_init(), is not released in the error handling path of mtk_iommu_v1_probe(). Add the corresponding clk_disable_unprepare(), as already done in the remove function. Fixes: b17336c55d89 ("iommu/mediatek: add support for mtk iommu generation one HW") Signed-off-by: Christophe JAILLET Reviewed-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/593e7b7d97c6e064b29716b091a9d4fd122241fb.1671473163.git.christophe.jaillet@wanadoo.fr Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/mtk_iommu_v1.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 4ed8bc755f5c..2abbdd71d8d9 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -618,7 +618,7 @@ static int mtk_iommu_probe(struct platform_device *pdev) ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL, dev_name(&pdev->dev)); if (ret) - return ret; + goto out_clk_unprepare; iommu_device_set_ops(&data->iommu, &mtk_iommu_ops); @@ -643,6 +643,8 @@ out_dev_unreg: iommu_device_unregister(&data->iommu); out_sysfs_remove: iommu_device_sysfs_remove(&data->iommu); +out_clk_unprepare: + clk_disable_unprepare(data->bclk); return ret; } From 0027164b24f252d54d6d5b8e718b7d782859713a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 22 Mar 2022 12:07:12 +0100 Subject: [PATCH 0922/4345] Documentation: KVM: add API issues section [ Upstream commit cde363ab7ca7aea7a853851cd6a6745a9e1aaf5e ] Add a section to document all the different ways in which the KVM API sucks. I am sure there are way more, give people a place to vent so that userspace authors are aware. Signed-off-by: Paolo Bonzini Message-Id: <20220322110712.222449-4-pbonzini@redhat.com> Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- Documentation/virt/kvm/api.rst | 46 ++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index cd8a58556804..d807994360d4 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6398,3 +6398,49 @@ When enabled, KVM will disable paravirtual features provided to the guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf (0x40000001). Otherwise, a guest may use the paravirtual features regardless of what has actually been exposed through the CPUID leaf. + +9. Known KVM API problems +========================= + +In some cases, KVM's API has some inconsistencies or common pitfalls +that userspace need to be aware of. This section details some of +these issues. + +Most of them are architecture specific, so the section is split by +architecture. + +9.1. x86 +-------- + +``KVM_GET_SUPPORTED_CPUID`` issues +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +In general, ``KVM_GET_SUPPORTED_CPUID`` is designed so that it is possible +to take its result and pass it directly to ``KVM_SET_CPUID2``. This section +documents some cases in which that requires some care. + +Local APIC features +~~~~~~~~~~~~~~~~~~~ + +CPU[EAX=1]:ECX[21] (X2APIC) is reported by ``KVM_GET_SUPPORTED_CPUID``, +but it can only be enabled if ``KVM_CREATE_IRQCHIP`` or +``KVM_ENABLE_CAP(KVM_CAP_IRQCHIP_SPLIT)`` are used to enable in-kernel emulation of +the local APIC. + +The same is true for the ``KVM_FEATURE_PV_UNHALT`` paravirtualized feature. + +CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID``. +It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel +has enabled in-kernel emulation of the local APIC. + +Obsolete ioctls and capabilities +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +KVM_CAP_DISABLE_QUIRKS does not let userspace know which quirks are actually +available. Use ``KVM_CHECK_EXTENSION(KVM_CAP_DISABLE_QUIRKS2)`` instead if +available. + +Ordering of KVM_GET_*/KVM_SET_* ioctls +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +TBD From 196c6f0c3e217223c060f5376f1095948df33781 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Sat, 22 Oct 2022 04:17:53 -0400 Subject: [PATCH 0923/4345] KVM: x86: Do not return host topology information from KVM_GET_SUPPORTED_CPUID [ Upstream commit 45e966fcca03ecdcccac7cb236e16eea38cc18af ] Passing the host topology to the guest is almost certainly wrong and will confuse the scheduler. In addition, several fields of these CPUID leaves vary on each processor; it is simply impossible to return the right values from KVM_GET_SUPPORTED_CPUID in such a way that they can be passed to KVM_SET_CPUID2. The values that will most likely prevent confusion are all zeroes. Userspace will have to override it anyway if it wishes to present a specific topology to the guest. Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- Documentation/virt/kvm/api.rst | 14 ++++++++++++++ arch/x86/kvm/cpuid.c | 34 +++++++++++++++++----------------- 2 files changed, 31 insertions(+), 17 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index d807994360d4..2b4b64797191 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6433,6 +6433,20 @@ CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID`` It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel has enabled in-kernel emulation of the local APIC. +CPU topology +~~~~~~~~~~~~ + +Several CPUID values include topology information for the host CPU: +0x0b and 0x1f for Intel systems, 0x8000001e for AMD systems. Different +versions of KVM return different values for this information and userspace +should not rely on it. Currently they return all zeroes. + +If userspace wishes to set up a guest topology, it should be careful that +the values of these three leaves differ for each CPU. In particular, +the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX +for 0x8000001e; the latter also encodes the core id and node id in bits +7:0 of EBX and ECX respectively. + Obsolete ioctls and capabilities ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 06a776fdb90c..de4b171cb76b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -511,15 +511,21 @@ struct kvm_cpuid_array { int nent; }; -static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, - u32 function, u32 index) +static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array) { - struct kvm_cpuid_entry2 *entry; - if (array->nent >= array->maxnent) return NULL; - entry = &array->entries[array->nent++]; + return &array->entries[array->nent++]; +} + +static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, + u32 function, u32 index) +{ + struct kvm_cpuid_entry2 *entry = get_next_cpuid(array); + + if (!entry) + return NULL; entry->function = function; entry->index = index; @@ -698,22 +704,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx = edx.full; break; } - /* - * Per Intel's SDM, the 0x1f is a superset of 0xb, - * thus they can be handled by common code. - */ case 0x1f: case 0xb: /* - * Populate entries until the level type (ECX[15:8]) of the - * previous entry is zero. Note, CPUID EAX.{0x1f,0xb}.0 is - * the starting entry, filled by the primary do_host_cpuid(). + * No topology; a valid topology is indicated by the presence + * of subleaf 1. */ - for (i = 1; entry->ecx & 0xff00; ++i) { - entry = do_host_cpuid(array, function, i); - if (!entry) - goto out; - } + entry->eax = entry->ebx = entry->ecx = 0; break; case 0xd: entry->eax &= supported_xcr0; @@ -866,6 +863,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ebx = entry->ecx = entry->edx = 0; break; case 0x8000001e: + /* Do not return host topology information. */ + entry->eax = entry->ebx = entry->ecx = 0; + entry->edx = 0; /* reserved */ break; /* Support memory encryption cpuid if host supports it */ case 0x8000001F: From 446c7251f007282b5f9dd9853be8d6737cb3c14d Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Thu, 17 Dec 2020 14:31:20 -0800 Subject: [PATCH 0924/4345] x86/resctrl: Use task_curr() instead of task_struct->on_cpu to prevent unnecessary IPI [ Upstream commit e0ad6dc8969f790f14bddcfd7ea284b7e5f88a16 ] James reported in [1] that there could be two tasks running on the same CPU with task_struct->on_cpu set. Using task_struct->on_cpu as a test if a task is running on a CPU may thus match the old task for a CPU while the scheduler is running and IPI it unnecessarily. task_curr() is the correct helper to use. While doing so move the #ifdef check of the CONFIG_SMP symbol to be a C conditional used to determine if this helper should be used to ensure the code is always checked for correctness by the compiler. [1] https://lore.kernel.org/lkml/a782d2f3-d2f6-795f-f4b1-9462205fd581@arm.com Reported-by: James Morse Signed-off-by: Reinette Chatre Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/e9e68ce1441a73401e08b641cc3b9a3cf13fe6d4.1608243147.git.reinette.chatre@intel.com Stable-dep-of: fe1f0714385f ("x86/resctrl: Fix task CLOSID/RMID update race") Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 5a59e3315b34..f2ad3c117426 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2313,19 +2313,15 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, t->closid = to->closid; t->rmid = to->mon.rmid; -#ifdef CONFIG_SMP /* - * This is safe on x86 w/o barriers as the ordering - * of writing to task_cpu() and t->on_cpu is - * reverse to the reading here. The detection is - * inaccurate as tasks might move or schedule - * before the smp function call takes place. In - * such a case the function call is pointless, but + * If the task is on a CPU, set the CPU in the mask. + * The detection is inaccurate as tasks might move or + * schedule before the smp function call takes place. + * In such a case the function call is pointless, but * there is no other side effect. */ - if (mask && t->on_cpu) + if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t)) cpumask_set_cpu(task_cpu(t), mask); -#endif } } read_unlock(&tasklist_lock); From 5dac4c7212a791d2996bc1df60edf0622d481351 Mon Sep 17 00:00:00 2001 From: Peter Newman Date: Tue, 20 Dec 2022 17:11:23 +0100 Subject: [PATCH 0925/4345] x86/resctrl: Fix task CLOSID/RMID update race [ Upstream commit fe1f0714385fbcf76b0cbceb02b7277d842014fc ] When the user moves a running task to a new rdtgroup using the task's file interface or by deleting its rdtgroup, the resulting change in CLOSID/RMID must be immediately propagated to the PQR_ASSOC MSR on the task(s) CPUs. x86 allows reordering loads with prior stores, so if the task starts running between a task_curr() check that the CPU hoisted before the stores in the CLOSID/RMID update then it can start running with the old CLOSID/RMID until it is switched again because __rdtgroup_move_task() failed to determine that it needs to be interrupted to obtain the new CLOSID/RMID. Refer to the diagram below: CPU 0 CPU 1 ----- ----- __rdtgroup_move_task(): curr <- t1->cpu->rq->curr __schedule(): rq->curr <- t1 resctrl_sched_in(): t1->{closid,rmid} -> {1,1} t1->{closid,rmid} <- {2,2} if (curr == t1) // false IPI(t1->cpu) A similar race impacts rdt_move_group_tasks(), which updates tasks in a deleted rdtgroup. In both cases, use smp_mb() to order the task_struct::{closid,rmid} stores before the loads in task_curr(). In particular, in the rdt_move_group_tasks() case, simply execute an smp_mb() on every iteration with a matching task. It is possible to use a single smp_mb() in rdt_move_group_tasks(), but this would require two passes and a means of remembering which task_structs were updated in the first loop. However, benchmarking results below showed too little performance impact in the simple approach to justify implementing the two-pass approach. Times below were collected using `perf stat` to measure the time to remove a group containing a 1600-task, parallel workload. CPU: Intel(R) Xeon(R) Platinum P-8136 CPU @ 2.00GHz (112 threads) # mkdir /sys/fs/resctrl/test # echo $$ > /sys/fs/resctrl/test/tasks # perf bench sched messaging -g 40 -l 100000 task-clock time ranges collected using: # perf stat rmdir /sys/fs/resctrl/test Baseline: 1.54 - 1.60 ms smp_mb() every matching task: 1.57 - 1.67 ms [ bp: Massage commit message. ] Fixes: ae28d1aae48a ("x86/resctrl: Use an IPI instead of task_work_add() to update PQR_ASSOC MSR") Fixes: 0efc89be9471 ("x86/intel_rdt: Update task closid immediately on CPU in rmdir and unmount") Signed-off-by: Peter Newman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Cc: Link: https://lore.kernel.org/r/20221220161123.432120-1-peternewman@google.com Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index f2ad3c117426..ff26de11b3f1 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -577,8 +577,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk, /* * Ensure the task's closid and rmid are written before determining if * the task is current that will decide if it will be interrupted. + * This pairs with the full barrier between the rq->curr update and + * resctrl_sched_in() during context switch. */ - barrier(); + smp_mb(); /* * By now, the task's closid and rmid are set. If the task is current @@ -2313,6 +2315,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, t->closid = to->closid; t->rmid = to->mon.rmid; + /* + * Order the closid/rmid stores above before the loads + * in task_curr(). This pairs with the full barrier + * between the rq->curr update and resctrl_sched_in() + * during context switch. + */ + smp_mb(); + /* * If the task is on a CPU, set the CPU in the mask. * The detection is inaccurate as tasks might move or From 28840e46eaafa049d10d525632eebccecc6d3f83 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 10 Dec 2021 15:14:06 +0000 Subject: [PATCH 0926/4345] arm64: atomics: format whitespace consistently [ Upstream commit 8e6082e94aac6d0338883b5953631b662a5a9188 ] The code for the atomic ops is formatted inconsistently, and while this is not a functional problem it is rather distracting when working on them. Some have ops have consistent indentation, e.g. | #define ATOMIC_OP_ADD_RETURN(name, mb, cl...) \ | static inline int __lse_atomic_add_return##name(int i, atomic_t *v) \ | { \ | u32 tmp; \ | \ | asm volatile( \ | __LSE_PREAMBLE \ | " ldadd" #mb " %w[i], %w[tmp], %[v]\n" \ | " add %w[i], %w[i], %w[tmp]" \ | : [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) \ | : "r" (v) \ | : cl); \ | \ | return i; \ | } While others have negative indentation for some lines, and/or have misaligned trailing backslashes, e.g. | static inline void __lse_atomic_##op(int i, atomic_t *v) \ | { \ | asm volatile( \ | __LSE_PREAMBLE \ | " " #asm_op " %w[i], %[v]\n" \ | : [i] "+r" (i), [v] "+Q" (v->counter) \ | : "r" (v)); \ | } This patch makes the indentation consistent and also aligns the trailing backslashes. This makes the code easier to read for those (like myself) who are easily distracted by these inconsistencies. This is intended as a cleanup. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Cc: Boqun Feng Cc: Peter Zijlstra Cc: Will Deacon Acked-by: Will Deacon Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211210151410.2782645-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas Stable-dep-of: 031af50045ea ("arm64: cmpxchg_double*: hazard against entire exchange variable") Signed-off-by: Sasha Levin --- arch/arm64/include/asm/atomic_ll_sc.h | 86 +++++++++++++-------------- arch/arm64/include/asm/atomic_lse.h | 14 ++--- 2 files changed, 50 insertions(+), 50 deletions(-) diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index 13869b76b58c..fe0db8d416fb 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -44,11 +44,11 @@ __ll_sc_atomic_##op(int i, atomic_t *v) \ \ asm volatile("// atomic_" #op "\n" \ __LL_SC_FALLBACK( \ -" prfm pstl1strm, %2\n" \ -"1: ldxr %w0, %2\n" \ -" " #asm_op " %w0, %w0, %w3\n" \ -" stxr %w1, %w0, %2\n" \ -" cbnz %w1, 1b\n") \ + " prfm pstl1strm, %2\n" \ + "1: ldxr %w0, %2\n" \ + " " #asm_op " %w0, %w0, %w3\n" \ + " stxr %w1, %w0, %2\n" \ + " cbnz %w1, 1b\n") \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i)); \ } @@ -62,12 +62,12 @@ __ll_sc_atomic_##op##_return##name(int i, atomic_t *v) \ \ asm volatile("// atomic_" #op "_return" #name "\n" \ __LL_SC_FALLBACK( \ -" prfm pstl1strm, %2\n" \ -"1: ld" #acq "xr %w0, %2\n" \ -" " #asm_op " %w0, %w0, %w3\n" \ -" st" #rel "xr %w1, %w0, %2\n" \ -" cbnz %w1, 1b\n" \ -" " #mb ) \ + " prfm pstl1strm, %2\n" \ + "1: ld" #acq "xr %w0, %2\n" \ + " " #asm_op " %w0, %w0, %w3\n" \ + " st" #rel "xr %w1, %w0, %2\n" \ + " cbnz %w1, 1b\n" \ + " " #mb ) \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -84,12 +84,12 @@ __ll_sc_atomic_fetch_##op##name(int i, atomic_t *v) \ \ asm volatile("// atomic_fetch_" #op #name "\n" \ __LL_SC_FALLBACK( \ -" prfm pstl1strm, %3\n" \ -"1: ld" #acq "xr %w0, %3\n" \ -" " #asm_op " %w1, %w0, %w4\n" \ -" st" #rel "xr %w2, %w1, %3\n" \ -" cbnz %w2, 1b\n" \ -" " #mb ) \ + " prfm pstl1strm, %3\n" \ + "1: ld" #acq "xr %w0, %3\n" \ + " " #asm_op " %w1, %w0, %w4\n" \ + " st" #rel "xr %w2, %w1, %3\n" \ + " cbnz %w2, 1b\n" \ + " " #mb ) \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -143,11 +143,11 @@ __ll_sc_atomic64_##op(s64 i, atomic64_t *v) \ \ asm volatile("// atomic64_" #op "\n" \ __LL_SC_FALLBACK( \ -" prfm pstl1strm, %2\n" \ -"1: ldxr %0, %2\n" \ -" " #asm_op " %0, %0, %3\n" \ -" stxr %w1, %0, %2\n" \ -" cbnz %w1, 1b") \ + " prfm pstl1strm, %2\n" \ + "1: ldxr %0, %2\n" \ + " " #asm_op " %0, %0, %3\n" \ + " stxr %w1, %0, %2\n" \ + " cbnz %w1, 1b") \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i)); \ } @@ -161,12 +161,12 @@ __ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v) \ \ asm volatile("// atomic64_" #op "_return" #name "\n" \ __LL_SC_FALLBACK( \ -" prfm pstl1strm, %2\n" \ -"1: ld" #acq "xr %0, %2\n" \ -" " #asm_op " %0, %0, %3\n" \ -" st" #rel "xr %w1, %0, %2\n" \ -" cbnz %w1, 1b\n" \ -" " #mb ) \ + " prfm pstl1strm, %2\n" \ + "1: ld" #acq "xr %0, %2\n" \ + " " #asm_op " %0, %0, %3\n" \ + " st" #rel "xr %w1, %0, %2\n" \ + " cbnz %w1, 1b\n" \ + " " #mb ) \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -176,19 +176,19 @@ __ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v) \ #define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\ static inline long \ -__ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v) \ +__ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v) \ { \ s64 result, val; \ unsigned long tmp; \ \ asm volatile("// atomic64_fetch_" #op #name "\n" \ __LL_SC_FALLBACK( \ -" prfm pstl1strm, %3\n" \ -"1: ld" #acq "xr %0, %3\n" \ -" " #asm_op " %1, %0, %4\n" \ -" st" #rel "xr %w2, %1, %3\n" \ -" cbnz %w2, 1b\n" \ -" " #mb ) \ + " prfm pstl1strm, %3\n" \ + "1: ld" #acq "xr %0, %3\n" \ + " " #asm_op " %1, %0, %4\n" \ + " st" #rel "xr %w2, %1, %3\n" \ + " cbnz %w2, 1b\n" \ + " " #mb ) \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -241,14 +241,14 @@ __ll_sc_atomic64_dec_if_positive(atomic64_t *v) asm volatile("// atomic64_dec_if_positive\n" __LL_SC_FALLBACK( -" prfm pstl1strm, %2\n" -"1: ldxr %0, %2\n" -" subs %0, %0, #1\n" -" b.lt 2f\n" -" stlxr %w1, %0, %2\n" -" cbnz %w1, 1b\n" -" dmb ish\n" -"2:") + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " subs %0, %0, #1\n" + " b.lt 2f\n" + " stlxr %w1, %0, %2\n" + " cbnz %w1, 1b\n" + " dmb ish\n" + "2:") : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) : : "cc", "memory"); diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index da3280f639cd..ab661375835e 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -11,11 +11,11 @@ #define __ASM_ATOMIC_LSE_H #define ATOMIC_OP(op, asm_op) \ -static inline void __lse_atomic_##op(int i, atomic_t *v) \ +static inline void __lse_atomic_##op(int i, atomic_t *v) \ { \ asm volatile( \ __LSE_PREAMBLE \ -" " #asm_op " %w[i], %[v]\n" \ + " " #asm_op " %w[i], %[v]\n" \ : [i] "+r" (i), [v] "+Q" (v->counter) \ : "r" (v)); \ } @@ -32,7 +32,7 @@ static inline int __lse_atomic_fetch_##op##name(int i, atomic_t *v) \ { \ asm volatile( \ __LSE_PREAMBLE \ -" " #asm_op #mb " %w[i], %w[i], %[v]" \ + " " #asm_op #mb " %w[i], %w[i], %[v]" \ : [i] "+r" (i), [v] "+Q" (v->counter) \ : "r" (v) \ : cl); \ @@ -130,7 +130,7 @@ static inline int __lse_atomic_sub_return##name(int i, atomic_t *v) \ " add %w[i], %w[i], %w[tmp]" \ : [i] "+&r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) \ : "r" (v) \ - : cl); \ + : cl); \ \ return i; \ } @@ -168,7 +168,7 @@ static inline void __lse_atomic64_##op(s64 i, atomic64_t *v) \ { \ asm volatile( \ __LSE_PREAMBLE \ -" " #asm_op " %[i], %[v]\n" \ + " " #asm_op " %[i], %[v]\n" \ : [i] "+r" (i), [v] "+Q" (v->counter) \ : "r" (v)); \ } @@ -185,7 +185,7 @@ static inline long __lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v)\ { \ asm volatile( \ __LSE_PREAMBLE \ -" " #asm_op #mb " %[i], %[i], %[v]" \ + " " #asm_op #mb " %[i], %[i], %[v]" \ : [i] "+r" (i), [v] "+Q" (v->counter) \ : "r" (v) \ : cl); \ @@ -272,7 +272,7 @@ static inline void __lse_atomic64_sub(s64 i, atomic64_t *v) } #define ATOMIC64_OP_SUB_RETURN(name, mb, cl...) \ -static inline long __lse_atomic64_sub_return##name(s64 i, atomic64_t *v) \ +static inline long __lse_atomic64_sub_return##name(s64 i, atomic64_t *v)\ { \ unsigned long tmp; \ \ From 9a5fd0844e7f06fac80512bbbe40e83314524a49 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 17 Aug 2022 16:59:13 +0100 Subject: [PATCH 0927/4345] arm64: atomics: remove LL/SC trampolines [ Upstream commit b2c3ccbd0011bb3b51d0fec24cb3a5812b1ec8ea ] When CONFIG_ARM64_LSE_ATOMICS=y, each use of an LL/SC atomic results in a fragment of code being generated in a subsection without a clear association with its caller. A trampoline in the caller branches to the LL/SC atomic with with a direct branch, and the atomic directly branches back into its trampoline. This breaks backtracing, as any PC within the out-of-line fragment will be symbolized as an offset from the nearest prior symbol (which may not be the function using the atomic), and since the atomic returns with a direct branch, the caller's PC may be missing from the backtrace. For example, with secondary_start_kernel() hacked to contain atomic_inc(NULL), the resulting exception can be reported as being taken from cpus_are_stuck_in_kernel(): | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 | Mem abort info: | ESR = 0x0000000096000004 | EC = 0x25: DABT (current EL), IL = 32 bits | SET = 0, FnV = 0 | EA = 0, S1PTW = 0 | FSC = 0x04: level 0 translation fault | Data abort info: | ISV = 0, ISS = 0x00000004 | CM = 0, WnR = 0 | [0000000000000000] user address but active_mm is swapper | Internal error: Oops: 96000004 [#1] PREEMPT SMP | Modules linked in: | CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.19.0-11219-geb555cb5b794-dirty #3 | Hardware name: linux,dummy-virt (DT) | pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : cpus_are_stuck_in_kernel+0xa4/0x120 | lr : secondary_start_kernel+0x164/0x170 | sp : ffff80000a4cbe90 | x29: ffff80000a4cbe90 x28: 0000000000000000 x27: 0000000000000000 | x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000000 | x23: 0000000000000000 x22: 0000000000000000 x21: 0000000000000000 | x20: 0000000000000001 x19: 0000000000000001 x18: 0000000000000008 | x17: 3030383832343030 x16: 3030303030307830 x15: ffff80000a4cbab0 | x14: 0000000000000001 x13: 5d31666130663133 x12: 3478305b20313030 | x11: 3030303030303078 x10: 3020726f73736563 x9 : 726f737365636f72 | x8 : ffff800009ff2ef0 x7 : 0000000000000003 x6 : 0000000000000000 | x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000100 | x2 : 0000000000000000 x1 : ffff0000029bd880 x0 : 0000000000000000 | Call trace: | cpus_are_stuck_in_kernel+0xa4/0x120 | __secondary_switched+0xb0/0xb4 | Code: 35ffffa3 17fffc6c d53cd040 f9800011 (885f7c01) | ---[ end trace 0000000000000000 ]--- This is confusing and hinders debugging, and will be problematic for CONFIG_LIVEPATCH as these cases cannot be unwound reliably. This is very similar to recent issues with out-of-line exception fixups, which were removed in commits: 35d67794b8828333 ("arm64: lib: __arch_clear_user(): fold fixups into body") 4012e0e22739eef9 ("arm64: lib: __arch_copy_from_user(): fold fixups into body") 139f9ab73d60cf76 ("arm64: lib: __arch_copy_to_user(): fold fixups into body") When the trampolines were introduced in commit: addfc38672c73efd ("arm64: atomics: avoid out-of-line ll/sc atomics") The rationale was to improve icache performance by grouping the LL/SC atomics together. This has never been measured, and this theoretical benefit is outweighed by other factors: * As the subsections are collapsed into sections at object file granularity, these are spread out throughout the kernel and can share cachelines with unrelated code regardless. * GCC 12.1.0 has been observed to place the trampoline out-of-line in specialised __ll_sc_*() functions, introducing more branching than was intended. * Removing the trampolines has been observed to shrink a defconfig kernel Image by 64KiB when building with GCC 12.1.0. This patch removes the LL/SC trampolines, meaning that the LL/SC atomics will be inlined into their callers (or placed in out-of line functions using regular BL/RET pairs). When CONFIG_ARM64_LSE_ATOMICS=y, the LL/SC atomics are always called in an unlikely branch, and will be placed in a cold portion of the function, so this should have minimal impact to the hot paths. Other than the improved backtracing, there should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Cc: Will Deacon Link: https://lore.kernel.org/r/20220817155914.3975112-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas Stable-dep-of: 031af50045ea ("arm64: cmpxchg_double*: hazard against entire exchange variable") Signed-off-by: Sasha Levin --- arch/arm64/include/asm/atomic_ll_sc.h | 40 ++++++--------------------- 1 file changed, 9 insertions(+), 31 deletions(-) diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index fe0db8d416fb..906e2d8c254c 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -12,19 +12,6 @@ #include -#ifdef CONFIG_ARM64_LSE_ATOMICS -#define __LL_SC_FALLBACK(asm_ops) \ -" b 3f\n" \ -" .subsection 1\n" \ -"3:\n" \ -asm_ops "\n" \ -" b 4f\n" \ -" .previous\n" \ -"4:\n" -#else -#define __LL_SC_FALLBACK(asm_ops) asm_ops -#endif - #ifndef CONFIG_CC_HAS_K_CONSTRAINT #define K #endif @@ -43,12 +30,11 @@ __ll_sc_atomic_##op(int i, atomic_t *v) \ int result; \ \ asm volatile("// atomic_" #op "\n" \ - __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ldxr %w0, %2\n" \ " " #asm_op " %w0, %w0, %w3\n" \ " stxr %w1, %w0, %2\n" \ - " cbnz %w1, 1b\n") \ + " cbnz %w1, 1b\n" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i)); \ } @@ -61,13 +47,12 @@ __ll_sc_atomic_##op##_return##name(int i, atomic_t *v) \ int result; \ \ asm volatile("// atomic_" #op "_return" #name "\n" \ - __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ld" #acq "xr %w0, %2\n" \ " " #asm_op " %w0, %w0, %w3\n" \ " st" #rel "xr %w1, %w0, %2\n" \ " cbnz %w1, 1b\n" \ - " " #mb ) \ + " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -83,13 +68,12 @@ __ll_sc_atomic_fetch_##op##name(int i, atomic_t *v) \ int val, result; \ \ asm volatile("// atomic_fetch_" #op #name "\n" \ - __LL_SC_FALLBACK( \ " prfm pstl1strm, %3\n" \ "1: ld" #acq "xr %w0, %3\n" \ " " #asm_op " %w1, %w0, %w4\n" \ " st" #rel "xr %w2, %w1, %3\n" \ " cbnz %w2, 1b\n" \ - " " #mb ) \ + " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -142,12 +126,11 @@ __ll_sc_atomic64_##op(s64 i, atomic64_t *v) \ unsigned long tmp; \ \ asm volatile("// atomic64_" #op "\n" \ - __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ldxr %0, %2\n" \ " " #asm_op " %0, %0, %3\n" \ " stxr %w1, %0, %2\n" \ - " cbnz %w1, 1b") \ + " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i)); \ } @@ -160,13 +143,12 @@ __ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v) \ unsigned long tmp; \ \ asm volatile("// atomic64_" #op "_return" #name "\n" \ - __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ld" #acq "xr %0, %2\n" \ " " #asm_op " %0, %0, %3\n" \ " st" #rel "xr %w1, %0, %2\n" \ " cbnz %w1, 1b\n" \ - " " #mb ) \ + " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -182,13 +164,12 @@ __ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v) \ unsigned long tmp; \ \ asm volatile("// atomic64_fetch_" #op #name "\n" \ - __LL_SC_FALLBACK( \ " prfm pstl1strm, %3\n" \ "1: ld" #acq "xr %0, %3\n" \ " " #asm_op " %1, %0, %4\n" \ " st" #rel "xr %w2, %1, %3\n" \ " cbnz %w2, 1b\n" \ - " " #mb ) \ + " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ @@ -240,7 +221,6 @@ __ll_sc_atomic64_dec_if_positive(atomic64_t *v) unsigned long tmp; asm volatile("// atomic64_dec_if_positive\n" - __LL_SC_FALLBACK( " prfm pstl1strm, %2\n" "1: ldxr %0, %2\n" " subs %0, %0, #1\n" @@ -248,7 +228,7 @@ __ll_sc_atomic64_dec_if_positive(atomic64_t *v) " stlxr %w1, %0, %2\n" " cbnz %w1, 1b\n" " dmb ish\n" - "2:") + "2:" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) : : "cc", "memory"); @@ -274,7 +254,6 @@ __ll_sc__cmpxchg_case_##name##sz(volatile void *ptr, \ old = (u##sz)old; \ \ asm volatile( \ - __LL_SC_FALLBACK( \ " prfm pstl1strm, %[v]\n" \ "1: ld" #acq "xr" #sfx "\t%" #w "[oldval], %[v]\n" \ " eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \ @@ -282,7 +261,7 @@ __ll_sc__cmpxchg_case_##name##sz(volatile void *ptr, \ " st" #rel "xr" #sfx "\t%w[tmp], %" #w "[new], %[v]\n" \ " cbnz %w[tmp], 1b\n" \ " " #mb "\n" \ - "2:") \ + "2:" \ : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ [v] "+Q" (*(u##sz *)ptr) \ : [old] __stringify(constraint) "r" (old), [new] "r" (new) \ @@ -326,7 +305,6 @@ __ll_sc__cmpxchg_double##name(unsigned long old1, \ unsigned long tmp, ret; \ \ asm volatile("// __cmpxchg_double" #name "\n" \ - __LL_SC_FALLBACK( \ " prfm pstl1strm, %2\n" \ "1: ldxp %0, %1, %2\n" \ " eor %0, %0, %3\n" \ @@ -336,7 +314,7 @@ __ll_sc__cmpxchg_double##name(unsigned long old1, \ " st" #rel "xp %w0, %5, %6, %2\n" \ " cbnz %w0, 1b\n" \ " " #mb "\n" \ - "2:") \ + "2:" \ : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \ : "r" (old1), "r" (old2), "r" (new1), "r" (new2) \ : cl); \ From 057f5ddfbc13749bdeb417c2133431075a64946c Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 4 Jan 2023 15:16:26 +0000 Subject: [PATCH 0928/4345] arm64: cmpxchg_double*: hazard against entire exchange variable [ Upstream commit 031af50045ea97ed4386eb3751ca2c134d0fc911 ] The inline assembly for arm64's cmpxchg_double*() implementations use a +Q constraint to hazard against other accesses to the memory location being exchanged. However, the pointer passed to the constraint is a pointer to unsigned long, and thus the hazard only applies to the first 8 bytes of the location. GCC can take advantage of this, assuming that other portions of the location are unchanged, leading to a number of potential problems. This is similar to what we fixed back in commit: fee960bed5e857eb ("arm64: xchg: hazard against entire exchange variable") ... but we forgot to adjust cmpxchg_double*() similarly at the same time. The same problem applies, as demonstrated with the following test: | struct big { | u64 lo, hi; | } __aligned(128); | | unsigned long foo(struct big *b) | { | u64 hi_old, hi_new; | | hi_old = b->hi; | cmpxchg_double_local(&b->lo, &b->hi, 0x12, 0x34, 0x56, 0x78); | hi_new = b->hi; | | return hi_old ^ hi_new; | } ... which GCC 12.1.0 compiles as: | 0000000000000000 : | 0: d503233f paciasp | 4: aa0003e4 mov x4, x0 | 8: 1400000e b 40 | c: d2800240 mov x0, #0x12 // #18 | 10: d2800681 mov x1, #0x34 // #52 | 14: aa0003e5 mov x5, x0 | 18: aa0103e6 mov x6, x1 | 1c: d2800ac2 mov x2, #0x56 // #86 | 20: d2800f03 mov x3, #0x78 // #120 | 24: 48207c82 casp x0, x1, x2, x3, [x4] | 28: ca050000 eor x0, x0, x5 | 2c: ca060021 eor x1, x1, x6 | 30: aa010000 orr x0, x0, x1 | 34: d2800000 mov x0, #0x0 // #0 <--- BANG | 38: d50323bf autiasp | 3c: d65f03c0 ret | 40: d2800240 mov x0, #0x12 // #18 | 44: d2800681 mov x1, #0x34 // #52 | 48: d2800ac2 mov x2, #0x56 // #86 | 4c: d2800f03 mov x3, #0x78 // #120 | 50: f9800091 prfm pstl1strm, [x4] | 54: c87f1885 ldxp x5, x6, [x4] | 58: ca0000a5 eor x5, x5, x0 | 5c: ca0100c6 eor x6, x6, x1 | 60: aa0600a6 orr x6, x5, x6 | 64: b5000066 cbnz x6, 70 | 68: c8250c82 stxp w5, x2, x3, [x4] | 6c: 35ffff45 cbnz w5, 54 | 70: d2800000 mov x0, #0x0 // #0 <--- BANG | 74: d50323bf autiasp | 78: d65f03c0 ret Notice that at the lines with "BANG" comments, GCC has assumed that the higher 8 bytes are unchanged by the cmpxchg_double() call, and that `hi_old ^ hi_new` can be reduced to a constant zero, for both LSE and LL/SC versions of cmpxchg_double(). This patch fixes the issue by passing a pointer to __uint128_t into the +Q constraint, ensuring that the compiler hazards against the entire 16 bytes being modified. With this change, GCC 12.1.0 compiles the above test as: | 0000000000000000 : | 0: f9400407 ldr x7, [x0, #8] | 4: d503233f paciasp | 8: aa0003e4 mov x4, x0 | c: 1400000f b 48 | 10: d2800240 mov x0, #0x12 // #18 | 14: d2800681 mov x1, #0x34 // #52 | 18: aa0003e5 mov x5, x0 | 1c: aa0103e6 mov x6, x1 | 20: d2800ac2 mov x2, #0x56 // #86 | 24: d2800f03 mov x3, #0x78 // #120 | 28: 48207c82 casp x0, x1, x2, x3, [x4] | 2c: ca050000 eor x0, x0, x5 | 30: ca060021 eor x1, x1, x6 | 34: aa010000 orr x0, x0, x1 | 38: f9400480 ldr x0, [x4, #8] | 3c: d50323bf autiasp | 40: ca0000e0 eor x0, x7, x0 | 44: d65f03c0 ret | 48: d2800240 mov x0, #0x12 // #18 | 4c: d2800681 mov x1, #0x34 // #52 | 50: d2800ac2 mov x2, #0x56 // #86 | 54: d2800f03 mov x3, #0x78 // #120 | 58: f9800091 prfm pstl1strm, [x4] | 5c: c87f1885 ldxp x5, x6, [x4] | 60: ca0000a5 eor x5, x5, x0 | 64: ca0100c6 eor x6, x6, x1 | 68: aa0600a6 orr x6, x5, x6 | 6c: b5000066 cbnz x6, 78 | 70: c8250c82 stxp w5, x2, x3, [x4] | 74: 35ffff45 cbnz w5, 5c | 78: f9400480 ldr x0, [x4, #8] | 7c: d50323bf autiasp | 80: ca0000e0 eor x0, x7, x0 | 84: d65f03c0 ret ... sampling the high 8 bytes before and after the cmpxchg, and performing an EOR, as we'd expect. For backporting, I've tested this atop linux-4.9.y with GCC 5.5.0. Note that linux-4.9.y is oldest currently supported stable release, and mandates GCC 5.1+. Unfortunately I couldn't get a GCC 5.1 binary to run on my machines due to library incompatibilities. I've also used a standalone test to check that we can use a __uint128_t pointer in a +Q constraint at least as far back as GCC 4.8.5 and LLVM 3.9.1. Fixes: 5284e1b4bc8a ("arm64: xchg: Implement cmpxchg_double") Fixes: e9a4b795652f ("arm64: cmpxchg_dbl: patch in lse instructions when supported by the CPU") Reported-by: Boqun Feng Link: https://lore.kernel.org/lkml/Y6DEfQXymYVgL3oJ@boqun-archlinux/ Reported-by: Peter Zijlstra Link: https://lore.kernel.org/lkml/Y6GXoO4qmH9OIZ5Q@hirez.programming.kicks-ass.net/ Signed-off-by: Mark Rutland Cc: stable@vger.kernel.org Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Steve Capper Cc: Will Deacon Link: https://lore.kernel.org/r/20230104151626.3262137-1-mark.rutland@arm.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/include/asm/atomic_ll_sc.h | 2 +- arch/arm64/include/asm/atomic_lse.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index 906e2d8c254c..abd302e521c0 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -315,7 +315,7 @@ __ll_sc__cmpxchg_double##name(unsigned long old1, \ " cbnz %w0, 1b\n" \ " " #mb "\n" \ "2:" \ - : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \ + : "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr) \ : "r" (old1), "r" (old2), "r" (new1), "r" (new2) \ : cl); \ \ diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index ab661375835e..28e96118c1e5 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -403,7 +403,7 @@ __lse__cmpxchg_double##name(unsigned long old1, \ " eor %[old2], %[old2], %[oldval2]\n" \ " orr %[old1], %[old1], %[old2]" \ : [old1] "+&r" (x0), [old2] "+&r" (x1), \ - [v] "+Q" (*(unsigned long *)ptr) \ + [v] "+Q" (*(__uint128_t *)ptr) \ : [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \ [oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \ : cl); \ From 4ca71bc0e1995d15486cd7b60845602a28399cb5 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 19 Dec 2022 10:10:04 +0100 Subject: [PATCH 0929/4345] efi: fix NULL-deref in init error path [ Upstream commit 703c13fe3c9af557d312f5895ed6a5fda2711104 ] In cases where runtime services are not supported or have been disabled, the runtime services workqueue will never have been allocated. Do not try to destroy the workqueue unconditionally in the unlikely event that EFI initialisation fails to avoid dereferencing a NULL pointer. Fixes: 98086df8b70c ("efi: add missed destroy_workqueue when efisubsys_init fails") Cc: stable@vger.kernel.org Cc: Li Heng Signed-off-by: Johan Hovold Signed-off-by: Ard Biesheuvel Signed-off-by: Sasha Levin --- drivers/firmware/efi/efi.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index ba03f5a4b30c..a2765d668856 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -385,8 +385,8 @@ static int __init efisubsys_init(void) efi_kobj = kobject_create_and_add("efi", firmware_kobj); if (!efi_kobj) { pr_err("efi: Firmware registration failed.\n"); - destroy_workqueue(efi_rts_wq); - return -ENOMEM; + error = -ENOMEM; + goto err_destroy_wq; } if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE | @@ -429,7 +429,10 @@ err_unregister: generic_ops_unregister(); err_put: kobject_put(efi_kobj); - destroy_workqueue(efi_rts_wq); +err_destroy_wq: + if (efi_rts_wq) + destroy_workqueue(efi_rts_wq); + return error; } From 68bcd063857075d2f9edfed6024387ac377923e2 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Fri, 16 Dec 2022 15:33:55 -0800 Subject: [PATCH 0930/4345] drm/virtio: Fix GEM handle creation UAF [ Upstream commit 52531258318ed59a2dc5a43df2eaf0eb1d65438e ] Userspace can guess the handle value and try to race GEM object creation with handle close, resulting in a use-after-free if we dereference the object after dropping the handle's reference. For that reason, dropping the handle's reference must be done *after* we are done dereferencing the object. Signed-off-by: Rob Clark Reviewed-by: Chia-I Wu Fixes: 62fb7a5e1096 ("virtio-gpu: add 3d/virgl support") Cc: stable@vger.kernel.org Signed-off-by: Dmitry Osipenko Link: https://patchwork.freedesktop.org/patch/msgid/20221216233355.542197-2-robdclark@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 33b8ebab178a..36efa273155d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -279,10 +279,18 @@ static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data, drm_gem_object_release(obj); return ret; } - drm_gem_object_put(obj); rc->res_handle = qobj->hw_res_handle; /* similiar to a VM address */ rc->bo_handle = handle; + + /* + * The handle owns the reference now. But we must drop our + * remaining reference *after* we no longer need to dereference + * the obj. Otherwise userspace could guess the handle and + * race closing it from another thread. + */ + drm_gem_object_put(obj); + return 0; } From b912ed1363b363d587fe1aac9636ce9e9366a775 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 2 Jan 2023 16:49:46 -0700 Subject: [PATCH 0931/4345] io_uring/io-wq: free worker if task_work creation is canceled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit af82425c6a2d2f347c79b63ce74fca6dc6be157f upstream. If we cancel the task_work, the worker will never come into existance. As this is the last reference to it, ensure that we get it freed appropriately. Cc: stable@vger.kernel.org Reported-by: 진호 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io-wq.c | 1 + 1 file changed, 1 insertion(+) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 6031fb319d87..81b5e4462dba 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1217,6 +1217,7 @@ static void io_wq_cancel_tw_create(struct io_wq *wq) worker = container_of(cb, struct io_worker, create_work); io_worker_cancel_cb(worker); + kfree(worker); } } From a88a0d16e18f18d7221f0c5a1fdf487f5f9079e3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 8 Jan 2023 10:39:17 -0700 Subject: [PATCH 0932/4345] io_uring/io-wq: only free worker if it was allocated for creation commit e6db6f9398dadcbc06318a133d4c44a2d3844e61 upstream. We have two types of task_work based creation, one is using an existing worker to setup a new one (eg when going to sleep and we have no free workers), and the other is allocating a new worker. Only the latter should be freed when we cancel task_work creation for a new worker. Fixes: af82425c6a2d ("io_uring/io-wq: free worker if task_work creation is canceled") Reported-by: syzbot+d56ec896af3637bdb7e4@syzkaller.appspotmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io-wq.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 81b5e4462dba..87bc38b47103 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1217,7 +1217,12 @@ static void io_wq_cancel_tw_create(struct io_wq *wq) worker = container_of(cb, struct io_worker, create_work); io_worker_cancel_cb(worker); - kfree(worker); + /* + * Only the worker continuation helper has worker allocated and + * hence needs freeing. + */ + if (cb->func == create_worker_cont) + kfree(worker); } } From 74985c57576792cadee5ff9edf73df84be2b8c98 Mon Sep 17 00:00:00 2001 From: Ferry Toth Date: Thu, 22 Dec 2022 21:53:02 +0100 Subject: [PATCH 0933/4345] Revert "usb: ulpi: defer ulpi_register on ulpi_read_id timeout" commit b659b613cea2ae39746ca8bd2b69d1985dd9d770 upstream. This reverts commit 8a7b31d545d3a15f0e6f5984ae16f0ca4fd76aac. This patch results in some qemu test failures, specifically xilinx-zynq-a9 machine and zynq-zc702 as well as zynq-zed devicetree files, when trying to boot from USB drive. Link: https://lore.kernel.org/lkml/20221220194334.GA942039@roeck-us.net/ Fixes: 8a7b31d545d3 ("usb: ulpi: defer ulpi_register on ulpi_read_id timeout") Cc: stable@vger.kernel.org Reported-by: Guenter Roeck Signed-off-by: Ferry Toth Link: https://lore.kernel.org/r/20221222205302.45761-1-ftoth@exalondelft.nl Signed-off-by: Greg Kroah-Hartman --- drivers/usb/common/ulpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 1f077f2ea40f..3c705f1bead8 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -208,7 +208,7 @@ static int ulpi_read_id(struct ulpi *ulpi) /* Test the interface */ ret = ulpi_write(ulpi, ULPI_SCRATCH, 0xaa); if (ret < 0) - return ret; + goto err; ret = ulpi_read(ulpi, ULPI_SCRATCH); if (ret < 0) From 3a9f1b907bc434a91f0d295533d2c7e3758efe92 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 18 Jan 2023 11:45:02 +0100 Subject: [PATCH 0934/4345] Linux 5.10.164 Link: https://lore.kernel.org/r/20230116154743.577276578@linuxfoundation.org Tested-by: Salvatore Bonaccorso Tested-by: Shuah Khan Tested-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20230117124526.766388541@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Guenter Roeck Tested-by: Linux Kernel Functional Testing Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 98fc6e7fd41d..68fd49d8d436 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 163 +SUBLEVEL = 164 EXTRAVERSION = NAME = Dare mighty things From 2cbd815970f82af428c9201db82a57835236ad30 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Wed, 14 Dec 2022 11:06:07 +0900 Subject: [PATCH 0935/4345] btrfs: fix trace event name typo for FLUSH_DELAYED_REFS [ Upstream commit 0a3212de8ab3e2ce5808c6265855e528d4a6767b ] Fix a typo of printing FLUSH_DELAYED_REFS event in flush_space() as FLUSH_ELAYED_REFS. Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- include/trace/events/btrfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index ecd24c719de4..041be3ce1071 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -95,7 +95,7 @@ struct btrfs_space_info; EM( FLUSH_DELALLOC, "FLUSH_DELALLOC") \ EM( FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT") \ EM( FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR") \ - EM( FLUSH_DELAYED_REFS, "FLUSH_ELAYED_REFS") \ + EM( FLUSH_DELAYED_REFS, "FLUSH_DELAYED_REFS") \ EM( ALLOC_CHUNK, "ALLOC_CHUNK") \ EM( ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE") \ EM( RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS") \ From c7c36bb6eafd3f349d2371a1c6f2a3a72400acbc Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 20 Dec 2022 12:31:29 -0500 Subject: [PATCH 0936/4345] pNFS/filelayout: Fix coalescing test for single DS [ Upstream commit a6b9d2fa0024e7e399c26facd0fb466b7396e2b9 ] When there is a single DS no striping constraints need to be placed on the IO. When such constraint is applied then buffered reads don't coalesce to the DS's rsize. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/filelayout/filelayout.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index ae5ed3a07494..deecfb50dd7e 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -783,6 +783,12 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, return &fl->generic_hdr; } +static bool +filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg) +{ + return flseg->num_fh > 1; +} + /* * filelayout_pg_test(). Called by nfs_can_coalesce_requests() * @@ -803,6 +809,8 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, size = pnfs_generic_pg_test(pgio, prev, req); if (!size) return 0; + else if (!filelayout_lseg_is_striped(FILELAYOUT_LSEG(pgio->pg_lseg))) + return size; /* see if req and prev are in the same stripe */ if (prev) { From 3093027183f2846365a76b2fb1e1309f1960084a Mon Sep 17 00:00:00 2001 From: Hao Sun Date: Thu, 22 Dec 2022 10:44:14 +0800 Subject: [PATCH 0937/4345] selftests/bpf: check null propagation only neither reg is PTR_TO_BTF_ID [ Upstream commit cedebd74cf3883f0384af9ec26b4e6f8f1964dd4 ] Verify that nullness information is not porpagated in the branches of register to register JEQ and JNE operations if one of them is PTR_TO_BTF_ID. Implement this in C level so we can use CO-RE. Signed-off-by: Hao Sun Suggested-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20221222024414.29539-2-sunhao.th@gmail.com Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- .../bpf/prog_tests/jeq_infer_not_null.c | 9 ++++ .../bpf/progs/jeq_infer_not_null_fail.c | 42 +++++++++++++++++++ 2 files changed, 51 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c create mode 100644 tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c diff --git a/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c b/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c new file mode 100644 index 000000000000..3add34df5767 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include "jeq_infer_not_null_fail.skel.h" + +void test_jeq_infer_not_null(void) +{ + RUN_TESTS(jeq_infer_not_null_fail); +} diff --git a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c new file mode 100644 index 000000000000..f46965053acb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, u64); + __type(value, u64); +} m_hash SEC(".maps"); + +SEC("?raw_tp") +__failure __msg("R8 invalid mem access 'map_value_or_null") +int jeq_infer_not_null_ptr_to_btfid(void *ctx) +{ + struct bpf_map *map = (struct bpf_map *)&m_hash; + struct bpf_map *inner_map = map->inner_map_meta; + u64 key = 0, ret = 0, *val; + + val = bpf_map_lookup_elem(map, &key); + /* Do not mark ptr as non-null if one of them is + * PTR_TO_BTF_ID (R9), reject because of invalid + * access to map value (R8). + * + * Here, we need to inline those insns to access + * R8 directly, since compiler may use other reg + * once it figures out val==inner_map. + */ + asm volatile("r8 = %[val];\n" + "r9 = %[inner_map];\n" + "if r8 != r9 goto +1;\n" + "%[ret] = *(u64 *)(r8 +0);\n" + : [ret] "+r"(ret) + : [inner_map] "r"(inner_map), [val] "r"(val) + : "r8", "r9"); + + return ret; +} From f7845de23f9066b576120ab29b1291d31517a425 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo?= Date: Wed, 12 Oct 2022 08:29:49 +0200 Subject: [PATCH 0938/4345] tools/virtio: initialize spinlocks in vring_test.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c262f75cb6bb5a63828e72ce3b8fe808e5029479 ] The virtio_device vqs_list spinlocks must be initialized before use to prevent functions that manipulate the device virtualqueues, such as vring_new_virtqueue(), from blocking indefinitely. Signed-off-by: Ricardo Cañuelo Message-Id: <20221012062949.1526176-1-ricardo.canuelo@collabora.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo Signed-off-by: Sasha Levin --- tools/virtio/vringh_test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c index fa87b58bd5fa..98ff808d6f0c 100644 --- a/tools/virtio/vringh_test.c +++ b/tools/virtio/vringh_test.c @@ -308,6 +308,7 @@ static int parallel_test(u64 features, gvdev.vdev.features = features; INIT_LIST_HEAD(&gvdev.vdev.vqs); + spin_lock_init(&gvdev.vdev.vqs_list_lock); gvdev.to_host_fd = to_host[1]; gvdev.notifies = 0; @@ -455,6 +456,7 @@ int main(int argc, char *argv[]) getrange = getrange_iov; vdev.features = 0; INIT_LIST_HEAD(&vdev.vqs); + spin_lock_init(&vdev.vqs_list_lock); while (argv[1]) { if (strcmp(argv[1], "--indirect") == 0) From 0040e48492f375a63ab68df35be4d228e64b41c8 Mon Sep 17 00:00:00 2001 From: Daniil Tatianin Date: Mon, 26 Dec 2022 14:48:23 +0300 Subject: [PATCH 0939/4345] net/ethtool/ioctl: return -EOPNOTSUPP if we have no phy stats [ Upstream commit 9deb1e9fb88b1120a908676fa33bdf9e2eeaefce ] It's not very useful to copy back an empty ethtool_stats struct and return 0 if we didn't actually have any stats. This also allows for further simplification of this function in the future commits. Signed-off-by: Daniil Tatianin Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ethtool/ioctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 47c2dd4a9b9f..12bf740e2fb3 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2052,7 +2052,8 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) return n_stats; if (n_stats > S32_MAX / sizeof(u64)) return -ENOMEM; - WARN_ON_ONCE(!n_stats); + if (WARN_ON_ONCE(!n_stats)) + return -EOPNOTSUPP; if (copy_from_user(&stats, useraddr, sizeof(stats))) return -EFAULT; From 936b8b15a23b615f6ba597ea5612f4cbc097c72b Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 12 Dec 2022 13:04:11 +0100 Subject: [PATCH 0940/4345] RDMA/srp: Move large values to a new enum for gcc13 [ Upstream commit 56c5dab20a6391604df9521f812c01d1e3fe1bd0 ] Since gcc13, each member of an enum has the same type as the enum [1]. And that is inherited from its members. Provided these two: SRP_TAG_NO_REQ = ~0U, SRP_TAG_TSK_MGMT = 1U << 31 all other members are unsigned ints. Esp. with SRP_MAX_SGE and SRP_TSK_MGMT_SQ_SIZE and their use in min(), this results in the following warnings: include/linux/minmax.h:20:35: error: comparison of distinct pointer types lacks a cast drivers/infiniband/ulp/srp/ib_srp.c:563:42: note: in expansion of macro 'min' include/linux/minmax.h:20:35: error: comparison of distinct pointer types lacks a cast drivers/infiniband/ulp/srp/ib_srp.c:2369:27: note: in expansion of macro 'min' So move the large values away to a separate enum, so that they don't affect other members. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=36113 Link: https://lore.kernel.org/r/20221212120411.13750-1-jirislaby@kernel.org Signed-off-by: Jiri Slaby (SUSE) Reviewed-by: Bart Van Assche Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/srp/ib_srp.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index 6818cac0a3b7..85bac20d9007 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -62,9 +62,6 @@ enum { SRP_DEFAULT_CMD_SQ_SIZE = SRP_DEFAULT_QUEUE_SIZE - SRP_RSP_SQ_SIZE - SRP_TSK_MGMT_SQ_SIZE, - SRP_TAG_NO_REQ = ~0U, - SRP_TAG_TSK_MGMT = 1U << 31, - SRP_MAX_PAGES_PER_MR = 512, SRP_MAX_ADD_CDB_LEN = 16, @@ -79,6 +76,11 @@ enum { sizeof(struct srp_imm_buf), }; +enum { + SRP_TAG_NO_REQ = ~0U, + SRP_TAG_TSK_MGMT = BIT(31), +}; + enum srp_target_state { SRP_TARGET_SCANNING, SRP_TARGET_LIVE, From 18bd1c9c02e64a3567f90c83c2c8b855531c8098 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 26 Dec 2022 09:00:40 +0800 Subject: [PATCH 0941/4345] btrfs: always report error in run_one_delayed_ref() [ Upstream commit 39f501d68ec1ed5cd5c66ac6ec2a7131c517bb92 ] Currently we have a btrfs_debug() for run_one_delayed_ref() failure, but if end users hit such problem, there will be no chance that btrfs_debug() is enabled. This can lead to very little useful info for debugging. This patch will: - Add extra info for error reporting Including: * logical bytenr * num_bytes * type * action * ref_mod - Replace the btrfs_debug() with btrfs_err() - Move the error reporting into run_one_delayed_ref() This is to avoid use-after-free, the @node can be freed in the caller. This error should only be triggered at most once. As if run_one_delayed_ref() failed, we trigger the error message, then causing the call chain to error out: btrfs_run_delayed_refs() `- btrfs_run_delayed_refs() `- btrfs_run_delayed_refs_for_head() `- run_one_delayed_ref() And we will abort the current transaction in btrfs_run_delayed_refs(). If we have to run delayed refs for the abort transaction, run_one_delayed_ref() will just cleanup the refs and do nothing, thus no new error messages would be output. Reviewed-by: Anand Jain Signed-off-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/extent-tree.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 284294620e9f..7d9b8050b09c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1684,6 +1684,11 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, BUG(); if (ret && insert_reserved) btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1); + if (ret < 0) + btrfs_err(trans->fs_info, +"failed to run delayed ref for logical %llu num_bytes %llu type %u action %u ref_mod %d: %d", + node->bytenr, node->num_bytes, node->type, + node->action, node->ref_mod, ret); return ret; } @@ -1935,8 +1940,6 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, if (ret) { unselect_delayed_ref_head(delayed_refs, locked_ref); btrfs_put_delayed_ref(ref); - btrfs_debug(fs_info, "run_one_delayed_ref returned %d", - ret); return ret; } From bf6c7f1801314a38e8049775003e4839db7c7bf6 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 3 Jan 2023 10:24:11 -0500 Subject: [PATCH 0942/4345] x86/asm: Fix an assembler warning with current binutils [ Upstream commit 55d235361fccef573990dfa5724ab453866e7816 ] Fix a warning: "found `movsd'; assuming `movsl' was meant" Signed-off-by: Mikulas Patocka Signed-off-by: Ingo Molnar Cc: linux-kernel@vger.kernel.org Signed-off-by: Sasha Levin --- arch/x86/lib/iomap_copy_64.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S index a1f9416bf67a..6ff2f56cb0f7 100644 --- a/arch/x86/lib/iomap_copy_64.S +++ b/arch/x86/lib/iomap_copy_64.S @@ -10,6 +10,6 @@ */ SYM_FUNC_START(__iowrite32_copy) movl %edx,%ecx - rep movsd + rep movsl RET SYM_FUNC_END(__iowrite32_copy) From 72009139a661ade5cb1da4239734ed02fa1cfff0 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 21 Dec 2022 16:14:10 -0800 Subject: [PATCH 0943/4345] f2fs: let's avoid panic if extent_tree is not created [ Upstream commit df9d44b645b83fffccfb4e28c1f93376585fdec8 ] This patch avoids the below panic. pc : __lookup_extent_tree+0xd8/0x760 lr : f2fs_do_write_data_page+0x104/0x87c sp : ffffffc010cbb3c0 x29: ffffffc010cbb3e0 x28: 0000000000000000 x27: ffffff8803e7f020 x26: ffffff8803e7ed40 x25: ffffff8803e7f020 x24: ffffffc010cbb460 x23: ffffffc010cbb480 x22: 0000000000000000 x21: 0000000000000000 x20: ffffffff22e90900 x19: 0000000000000000 x18: ffffffc010c5d080 x17: 0000000000000000 x16: 0000000000000020 x15: ffffffdb1acdbb88 x14: ffffff888759e2b0 x13: 0000000000000000 x12: ffffff802da49000 x11: 000000000a001200 x10: ffffff8803e7ed40 x9 : ffffff8023195800 x8 : ffffff802da49078 x7 : 0000000000000001 x6 : 0000000000000000 x5 : 0000000000000006 x4 : ffffffc010cbba28 x3 : 0000000000000000 x2 : ffffffc010cbb480 x1 : 0000000000000000 x0 : ffffff8803e7ed40 Call trace: __lookup_extent_tree+0xd8/0x760 f2fs_do_write_data_page+0x104/0x87c f2fs_write_single_data_page+0x420/0xb60 f2fs_write_cache_pages+0x418/0xb1c __f2fs_write_data_pages+0x428/0x58c f2fs_write_data_pages+0x30/0x40 do_writepages+0x88/0x190 __writeback_single_inode+0x48/0x448 writeback_sb_inodes+0x468/0x9e8 __writeback_inodes_wb+0xb8/0x2a4 wb_writeback+0x33c/0x740 wb_do_writeback+0x2b4/0x400 wb_workfn+0xe4/0x34c process_one_work+0x24c/0x5bc worker_thread+0x3e8/0xa50 kthread+0x150/0x1b4 Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/extent_cache.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index bd16c78b5bf2..ad0b83a41226 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -414,7 +414,8 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, struct extent_node *en; bool ret = false; - f2fs_bug_on(sbi, !et); + if (!et) + return false; trace_f2fs_lookup_extent_tree_start(inode, pgofs); From 2d1fd99e8e120d900d9971122ad71c88b73bde19 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Wed, 11 Jan 2023 12:24:19 +0100 Subject: [PATCH 0944/4345] wifi: brcmfmac: fix regression for Broadcom PCIe wifi devices commit ed05cb177ae5cd7f02f1d6e7706ba627d30f1696 upstream. A sanity check was introduced considering maximum flowrings above 256 as insane and effectively aborting the device probe. This resulted in regression for number of users as the value turns out to be sane after all. Fixes: 2aca4f3734bd ("brcmfmac: return error when getting invalid max_flowrings from dongle") Reported-by: chainofflowers Link: https://lore.kernel.org/all/4781984.GXAFRqVoOG@luna/ Reported-by: Christian Marillat Link: https://bugzilla.kernel.org/show_bug.cgi?id=216894 Cc: stable@vger.kernel.org Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230111112419.24185-1-arend.vanspriel@broadcom.com Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 6a5621f17bf5..721d587425c7 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1109,7 +1109,7 @@ static int brcmf_pcie_init_ringbuffers(struct brcmf_pciedev_info *devinfo) BRCMF_NROF_H2D_COMMON_MSGRINGS; max_completionrings = BRCMF_NROF_D2H_COMMON_MSGRINGS; } - if (max_flowrings > 256) { + if (max_flowrings > 512) { brcmf_err(bus, "invalid max_flowrings(%d)\n", max_flowrings); return -EIO; } From 187523fa7c2d4c780f775cb869216865c4a909ef Mon Sep 17 00:00:00 2001 From: Alexander Wetzel Date: Fri, 30 Dec 2022 13:18:50 +0100 Subject: [PATCH 0945/4345] wifi: mac80211: sdata can be NULL during AMPDU start commit 69403bad97aa0162e3d7911b27e25abe774093df upstream. ieee80211_tx_ba_session_handle_start() may get NULL for sdata when a deauthentication is ongoing. Here a trace triggering the race with the hostapd test multi_ap_fronthaul_on_ap: (gdb) list *drv_ampdu_action+0x46 0x8b16 is in drv_ampdu_action (net/mac80211/driver-ops.c:396). 391 int ret = -EOPNOTSUPP; 392 393 might_sleep(); 394 395 sdata = get_bss_sdata(sdata); 396 if (!check_sdata_in_driver(sdata)) 397 return -EIO; 398 399 trace_drv_ampdu_action(local, sdata, params); 400 wlan0: moving STA 02:00:00:00:03:00 to state 3 wlan0: associated wlan0: deauthenticating from 02:00:00:00:03:00 by local choice (Reason: 3=DEAUTH_LEAVING) wlan3.sta1: Open BA session requested for 02:00:00:00:00:00 tid 0 wlan3.sta1: dropped frame to 02:00:00:00:00:00 (unauthorized port) wlan0: moving STA 02:00:00:00:03:00 to state 2 wlan0: moving STA 02:00:00:00:03:00 to state 1 wlan0: Removed STA 02:00:00:00:03:00 wlan0: Destroyed STA 02:00:00:00:03:00 BUG: unable to handle page fault for address: fffffffffffffb48 PGD 11814067 P4D 11814067 PUD 11816067 PMD 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 2 PID: 133397 Comm: kworker/u16:1 Tainted: G W 6.1.0-rc8-wt+ #59 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.0-20220807_005459-localhost 04/01/2014 Workqueue: phy3 ieee80211_ba_session_work [mac80211] RIP: 0010:drv_ampdu_action+0x46/0x280 [mac80211] Code: 53 48 89 f3 be 89 01 00 00 e8 d6 43 bf ef e8 21 46 81 f0 83 bb a0 1b 00 00 04 75 0e 48 8b 9b 28 0d 00 00 48 81 eb 10 0e 00 00 <8b> 93 58 09 00 00 f6 c2 20 0f 84 3b 01 00 00 8b 05 dd 1c 0f 00 85 RSP: 0018:ffffc900025ebd20 EFLAGS: 00010287 RAX: 0000000000000000 RBX: fffffffffffff1f0 RCX: ffff888102228240 RDX: 0000000080000000 RSI: ffffffff918c5de0 RDI: ffff888102228b40 RBP: ffffc900025ebd40 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000000 R12: ffff888118c18ec0 R13: 0000000000000000 R14: ffffc900025ebd60 R15: ffff888018b7efb8 FS: 0000000000000000(0000) GS:ffff88817a600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffb48 CR3: 0000000105228006 CR4: 0000000000170ee0 Call Trace: ieee80211_tx_ba_session_handle_start+0xd0/0x190 [mac80211] ieee80211_ba_session_work+0xff/0x2e0 [mac80211] process_one_work+0x29f/0x620 worker_thread+0x4d/0x3d0 ? process_one_work+0x620/0x620 kthread+0xfb/0x120 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 Signed-off-by: Alexander Wetzel Link: https://lore.kernel.org/r/20221230121850.218810-2-alexander@wetzel-home.de Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/mac80211/agg-tx.c | 6 +++++- net/mac80211/driver-ops.c | 3 +++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 4b4ab1961068..92e5812daf89 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -491,7 +491,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; struct ieee80211_local *local = sta->local; - struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_sub_if_data *sdata; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .action = IEEE80211_AMPDU_TX_START, @@ -521,6 +521,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ synchronize_net(); + sdata = sta->sdata; params.ssn = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, ¶ms); tid_tx->ssn = params.ssn; @@ -534,6 +535,9 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state); } else if (ret) { + if (!sdata) + return; + ht_dbg(sdata, "BA request denied - HW unavailable for %pM tid %d\n", sta->sta.addr, tid); diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index 48322e45e7dd..120bd9cdf7df 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -331,6 +331,9 @@ int drv_ampdu_action(struct ieee80211_local *local, might_sleep(); + if (!sdata) + return -EIO; + sdata = get_bss_sdata(sdata); if (!check_sdata_in_driver(sdata)) return -EIO; From 20d0a6d17e85a8a816a64fa7d7cae616f1617833 Mon Sep 17 00:00:00 2001 From: "Shawn.Shao" Date: Thu, 12 Jan 2023 13:58:02 +0800 Subject: [PATCH 0946/4345] Add exception protection processing for vd in axi_chan_handle_err function commit 57054fe516d59d03a7bcf1888e82479ccc244f87 upstream. Since there is no protection for vd, a kernel panic will be triggered here in exceptional cases. You can refer to the processing of axi_chan_block_xfer_complete function The triggered kernel panic is as follows: [ 67.848444] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000060 [ 67.848447] Mem abort info: [ 67.848449] ESR = 0x96000004 [ 67.848451] EC = 0x25: DABT (current EL), IL = 32 bits [ 67.848454] SET = 0, FnV = 0 [ 67.848456] EA = 0, S1PTW = 0 [ 67.848458] Data abort info: [ 67.848460] ISV = 0, ISS = 0x00000004 [ 67.848462] CM = 0, WnR = 0 [ 67.848465] user pgtable: 4k pages, 48-bit VAs, pgdp=00000800c4c0b000 [ 67.848468] [0000000000000060] pgd=0000000000000000, p4d=0000000000000000 [ 67.848472] Internal error: Oops: 96000004 [#1] SMP [ 67.848475] Modules linked in: dmatest [ 67.848479] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.10.100-emu_x2rc+ #11 [ 67.848483] pstate: 62000085 (nZCv daIf -PAN -UAO +TCO BTYPE=--) [ 67.848487] pc : axi_chan_handle_err+0xc4/0x230 [ 67.848491] lr : axi_chan_handle_err+0x30/0x230 [ 67.848493] sp : ffff0803fe55ae50 [ 67.848495] x29: ffff0803fe55ae50 x28: ffff800011212200 [ 67.848500] x27: ffff0800c42c0080 x26: ffff0800c097c080 [ 67.848504] x25: ffff800010d33880 x24: ffff80001139d850 [ 67.848508] x23: ffff0800c097c168 x22: 0000000000000000 [ 67.848512] x21: 0000000000000080 x20: 0000000000002000 [ 67.848517] x19: ffff0800c097c080 x18: 0000000000000000 [ 67.848521] x17: 0000000000000000 x16: 0000000000000000 [ 67.848525] x15: 0000000000000000 x14: 0000000000000000 [ 67.848529] x13: 0000000000000000 x12: 0000000000000040 [ 67.848533] x11: ffff0800c0400248 x10: ffff0800c040024a [ 67.848538] x9 : ffff800010576cd4 x8 : ffff0800c0400270 [ 67.848542] x7 : 0000000000000000 x6 : ffff0800c04003e0 [ 67.848546] x5 : ffff0800c0400248 x4 : ffff0800c4294480 [ 67.848550] x3 : dead000000000100 x2 : dead000000000122 [ 67.848555] x1 : 0000000000000100 x0 : ffff0800c097c168 [ 67.848559] Call trace: [ 67.848562] axi_chan_handle_err+0xc4/0x230 [ 67.848566] dw_axi_dma_interrupt+0xf4/0x590 [ 67.848569] __handle_irq_event_percpu+0x60/0x220 [ 67.848573] handle_irq_event+0x64/0x120 [ 67.848576] handle_fasteoi_irq+0xc4/0x220 [ 67.848580] __handle_domain_irq+0x80/0xe0 [ 67.848583] gic_handle_irq+0xc0/0x138 [ 67.848585] el1_irq+0xc8/0x180 [ 67.848588] arch_cpu_idle+0x14/0x2c [ 67.848591] default_idle_call+0x40/0x16c [ 67.848594] do_idle+0x1f0/0x250 [ 67.848597] cpu_startup_entry+0x2c/0x60 [ 67.848600] rest_init+0xc0/0xcc [ 67.848603] arch_call_rest_init+0x14/0x1c [ 67.848606] start_kernel+0x4cc/0x500 [ 67.848610] Code: eb0002ff 9a9f12d6 f2fbd5a2 f2fbd5a3 (a94602c1) [ 67.848613] ---[ end trace 585a97036f88203a ]--- Signed-off-by: Shawn.Shao Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230112055802.1764-1-shawn.shao@jaguarmicro.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c index 14c1ac26f866..b8b5d91b7c1a 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c @@ -551,6 +551,11 @@ static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status) /* The bad descriptor currently is in the head of vc list */ vd = vchan_next_desc(&chan->vc); + if (!vd) { + dev_err(chan2dev(chan), "BUG: %s, IRQ with no descriptors\n", + axi_chan_name(chan)); + goto out; + } /* Remove the completed descriptor from issued list */ list_del(&vd->node); @@ -565,6 +570,7 @@ static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status) /* Try to restart the controller */ axi_chan_start_first_queued(chan); +out: spin_unlock_irqrestore(&chan->vc.lock, flags); } From 03bf73e09ad6c7180211d4c6d5e7fd5bc0baeaa7 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 6 Jan 2023 17:43:06 +0900 Subject: [PATCH 0947/4345] zonefs: Detect append writes at invalid locations commit a608da3bd730d718f2d3ebec1c26f9865f8f17ce upstream. Using REQ_OP_ZONE_APPEND operations for synchronous writes to sequential files succeeds regardless of the zone write pointer position, as long as the target zone is not full. This means that if an external (buggy) application writes to the zone of a sequential file underneath the file system, subsequent file write() operation will succeed but the file size will not be correct and the file will contain invalid data written by another application. Modify zonefs_file_dio_append() to check the written sector of an append write (returned in bio->bi_iter.bi_sector) and return -EIO if there is a mismatch with the file zone wp offset field. This change triggers a call to zonefs_io_error() and a zone check. Modify zonefs_io_error_cb() to not expose the unexpected data after the current inode size when the errors=remount-ro mode is used. Other error modes are correctly handled already. Fixes: 02ef12a663c7 ("zonefs: use REQ_OP_ZONE_APPEND for sync DIO") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Signed-off-by: Greg Kroah-Hartman --- fs/zonefs/super.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 475d23a4f8da..66a089a62c39 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -394,6 +394,10 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, data_size = zonefs_check_zone_condition(inode, zone, false, false); } + } else if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO && + data_size > isize) { + /* Do not expose garbage data */ + data_size = isize; } /* @@ -772,6 +776,24 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) ret = submit_bio_wait(bio); + /* + * If the file zone was written underneath the file system, the zone + * write pointer may not be where we expect it to be, but the zone + * append write can still succeed. So check manually that we wrote where + * we intended to, that is, at zi->i_wpoffset. + */ + if (!ret) { + sector_t wpsector = + zi->i_zsector + (zi->i_wpoffset >> SECTOR_SHIFT); + + if (bio->bi_iter.bi_sector != wpsector) { + zonefs_warn(inode->i_sb, + "Corrupted write pointer %llu for zone at %llu\n", + wpsector, zi->i_zsector); + ret = -EIO; + } + } + zonefs_file_write_dio_end_io(iocb, size, ret, 0); out_release: From 712bd74eccb9d3626a0a236641962eca8e11a243 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 5 Jan 2023 14:53:56 +0900 Subject: [PATCH 0948/4345] nilfs2: fix general protection fault in nilfs_btree_insert() commit 7633355e5c7f29c049a9048e461427d1d8ed3051 upstream. If nilfs2 reads a corrupted disk image and tries to reads a b-tree node block by calling __nilfs_btree_get_block() against an invalid virtual block address, it returns -ENOENT because conversion of the virtual block address to a disk block address fails. However, this return value is the same as the internal code that b-tree lookup routines return to indicate that the block being searched does not exist, so functions that operate on that b-tree may misbehave. When nilfs_btree_insert() receives this spurious 'not found' code from nilfs_btree_do_lookup(), it misunderstands that the 'not found' check was successful and continues the insert operation using incomplete lookup path data, causing the following crash: general protection fault, probably for non-canonical address 0xdffffc0000000005: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f] ... RIP: 0010:nilfs_btree_get_nonroot_node fs/nilfs2/btree.c:418 [inline] RIP: 0010:nilfs_btree_prepare_insert fs/nilfs2/btree.c:1077 [inline] RIP: 0010:nilfs_btree_insert+0x6d3/0x1c10 fs/nilfs2/btree.c:1238 Code: bc 24 80 00 00 00 4c 89 f8 48 c1 e8 03 42 80 3c 28 00 74 08 4c 89 ff e8 4b 02 92 fe 4d 8b 3f 49 83 c7 28 4c 89 f8 48 c1 e8 03 <42> 80 3c 28 00 74 08 4c 89 ff e8 2e 02 92 fe 4d 8b 3f 49 83 c7 02 ... Call Trace: nilfs_bmap_do_insert fs/nilfs2/bmap.c:121 [inline] nilfs_bmap_insert+0x20d/0x360 fs/nilfs2/bmap.c:147 nilfs_get_block+0x414/0x8d0 fs/nilfs2/inode.c:101 __block_write_begin_int+0x54c/0x1a80 fs/buffer.c:1991 __block_write_begin fs/buffer.c:2041 [inline] block_write_begin+0x93/0x1e0 fs/buffer.c:2102 nilfs_write_begin+0x9c/0x110 fs/nilfs2/inode.c:261 generic_perform_write+0x2e4/0x5e0 mm/filemap.c:3772 __generic_file_write_iter+0x176/0x400 mm/filemap.c:3900 generic_file_write_iter+0xab/0x310 mm/filemap.c:3932 call_write_iter include/linux/fs.h:2186 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x7dc/0xc50 fs/read_write.c:584 ksys_write+0x177/0x2a0 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd ... This patch fixes the root cause of this problem by replacing the error code that __nilfs_btree_get_block() returns on block address conversion failure from -ENOENT to another internal code -EINVAL which means that the b-tree metadata is corrupted. By returning -EINVAL, it propagates without glitches, and for all relevant b-tree operations, functions in the upper bmap layer output an error message indicating corrupted b-tree metadata via nilfs_bmap_convert_error(), and code -EIO will be eventually returned as it should be. Link: https://lkml.kernel.org/r/000000000000bd89e205f0e38355@google.com Link: https://lkml.kernel.org/r/20230105055356.8811-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+ede796cecd5296353515@syzkaller.appspotmail.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/btree.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 77efd69213a3..65cd599cb2ab 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -480,9 +480,18 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, 0, &bh, &submit_ptr); if (ret) { - if (ret != -EEXIST) - return ret; - goto out_check; + if (likely(ret == -EEXIST)) + goto out_check; + if (ret == -ENOENT) { + /* + * Block address translation failed due to invalid + * value of 'ptr'. In this case, return internal code + * -EINVAL (broken bmap) to notify bmap layer of fatal + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } if (ra) { From 5822baf9501ae61a28a99163c6fbbdfc55392bbf Mon Sep 17 00:00:00 2001 From: Ding Hui Date: Tue, 27 Dec 2022 23:09:36 +0800 Subject: [PATCH 0949/4345] efi: fix userspace infinite retry read efivars after EFI runtime services page fault [ Upstream commit e006ac3003080177cf0b673441a4241f77aaecce ] After [1][2], if we catch exceptions due to EFI runtime service, we will clear EFI_RUNTIME_SERVICES bit to disable EFI runtime service, then the subsequent routine which invoke the EFI runtime service should fail. But the userspace cat efivars through /sys/firmware/efi/efivars/ will stuck and infinite loop calling read() due to efivarfs_file_read() return -EINTR. The -EINTR is converted from EFI_ABORTED by efi_status_to_err(), and is an improper return value in this situation, so let virt_efi_xxx() return EFI_DEVICE_ERROR and converted to -EIO to invoker. Cc: Fixes: 3425d934fc03 ("efi/x86: Handle page faults occurring while running EFI runtime services") Fixes: 23715a26c8d8 ("arm64: efi: Recover from synchronous exceptions occurring in firmware") Signed-off-by: Ding Hui Signed-off-by: Ard Biesheuvel Signed-off-by: Sasha Levin --- drivers/firmware/efi/runtime-wrappers.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index f3e54f6616f0..60075e0e4943 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -62,6 +62,7 @@ struct efi_runtime_work efi_rts_work; \ if (!efi_enabled(EFI_RUNTIME_SERVICES)) { \ pr_warn_once("EFI Runtime Services are disabled!\n"); \ + efi_rts_work.status = EFI_DEVICE_ERROR; \ goto exit; \ } \ \ From cab2123567afacbd5e721f9013e1be7028224603 Mon Sep 17 00:00:00 2001 From: Yuchi Yang Date: Fri, 30 Dec 2022 15:22:25 +0800 Subject: [PATCH 0950/4345] ALSA: hda/realtek - Turn on power early [ Upstream commit 1f680609bf1beac20e2a31ddcb1b88874123c39f ] Turn on power early to avoid wrong state for power relation register. This can earlier update JD state when resume back. Signed-off-by: Yuchi Yang Cc: Link: https://lore.kernel.org/r/e35d8f4fa18f4448a2315cc7d4a3715f@realtek.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index eb7dd457ef5a..cfd86389d37f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3561,6 +3561,15 @@ static void alc256_init(struct hda_codec *codec) hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; + if (spec->ultra_low_power) { + alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1); + alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2); + alc_update_coef_idx(codec, 0x08, 7<<4, 0); + alc_update_coef_idx(codec, 0x3b, 1<<15, 0); + alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6); + msleep(30); + } + if (!hp_pin) hp_pin = 0x21; @@ -3572,14 +3581,6 @@ static void alc256_init(struct hda_codec *codec) msleep(2); alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */ - if (spec->ultra_low_power) { - alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1); - alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2); - alc_update_coef_idx(codec, 0x08, 7<<4, 0); - alc_update_coef_idx(codec, 0x3b, 1<<15, 0); - alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6); - msleep(30); - } snd_hda_codec_write(codec, hp_pin, 0, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); @@ -3661,6 +3662,13 @@ static void alc225_init(struct hda_codec *codec) hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp1_pin_sense, hp2_pin_sense; + if (spec->ultra_low_power) { + alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2); + alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6); + alc_update_coef_idx(codec, 0x33, 1<<11, 0); + msleep(30); + } + if (!hp_pin) hp_pin = 0x21; msleep(30); @@ -3672,12 +3680,6 @@ static void alc225_init(struct hda_codec *codec) msleep(2); alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */ - if (spec->ultra_low_power) { - alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2); - alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6); - alc_update_coef_idx(codec, 0x33, 1<<11, 0); - msleep(30); - } if (hp1_pin_sense || spec->ultra_low_power) snd_hda_codec_write(codec, hp_pin, 0, From 413638f61501c9e2a592a5846a789968cd7b39a6 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 12 Dec 2022 17:13:38 +0100 Subject: [PATCH 0951/4345] drm/i915/gt: Reset twice [ Upstream commit d3de5616d36462a646f5b360ba82d3b09ff668eb ] After applying an engine reset, on some platforms like Jasperlake, we occasionally detect that the engine state is not cleared until shortly after the resume. As we try to resume the engine with volatile internal state, the first request fails with a spurious CS event (it looks like it reports a lite-restore to the hung context, instead of the expected idle->active context switch). Signed-off-by: Chris Wilson Cc: stable@vger.kernel.org Cc: Mika Kuoppala Signed-off-by: Andi Shyti Reviewed-by: Gwan-gyeong Mun Link: https://patchwork.freedesktop.org/patch/msgid/20221212161338.1007659-1-andi.shyti@linux.intel.com (cherry picked from commit 3db9d590557da3aa2c952f2fecd3e9b703dad790) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gt/intel_reset.c | 34 ++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index ac36b67fb46b..00b5912a88b8 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -289,6 +289,7 @@ out: static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask) { struct intel_uncore *uncore = gt->uncore; + int loops = 2; int err; /* @@ -296,18 +297,39 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask) * for fifo space for the write or forcewake the chip for * the read */ - intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask); + do { + intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask); - /* Wait for the device to ack the reset requests */ - err = __intel_wait_for_register_fw(uncore, - GEN6_GDRST, hw_domain_mask, 0, - 500, 0, - NULL); + /* + * Wait for the device to ack the reset requests. + * + * On some platforms, e.g. Jasperlake, we see that the + * engine register state is not cleared until shortly after + * GDRST reports completion, causing a failure as we try + * to immediately resume while the internal state is still + * in flux. If we immediately repeat the reset, the second + * reset appears to serialise with the first, and since + * it is a no-op, the registers should retain their reset + * value. However, there is still a concern that upon + * leaving the second reset, the internal engine state + * is still in flux and not ready for resuming. + */ + err = __intel_wait_for_register_fw(uncore, GEN6_GDRST, + hw_domain_mask, 0, + 2000, 0, + NULL); + } while (err == 0 && --loops); if (err) drm_dbg(>->i915->drm, "Wait for 0x%08x engines reset failed\n", hw_domain_mask); + /* + * As we have observed that the engine state is still volatile + * after GDRST is acked, impose a small delay to let everything settle. + */ + udelay(50); + return err; } From 1ab0098333f57cc11890c07020a2e3e430000df7 Mon Sep 17 00:00:00 2001 From: Venkata Lakshmi Narayana Gubba Date: Tue, 6 Oct 2020 20:50:21 +0530 Subject: [PATCH 0952/4345] Bluetooth: hci_qca: Wait for timeout during suspend [ Upstream commit 2be43abac5a839d44bf9d14716573ae0ac920f2b ] Currently qca_suspend() is relied on IBS mechanism. During FW download and memory dump collections, IBS will be disabled. In those cases, driver will allow suspend and still uses the serdev port, which results to errors. Now added a wait timeout if suspend is triggered during FW download and memory collections. Signed-off-by: Venkata Lakshmi Narayana Gubba Signed-off-by: Balakrishna Godavarthi Reviewed-by: Abhishek Pandit-Subedi Signed-off-by: Marcel Holtmann Stable-dep-of: 272970be3dab ("Bluetooth: hci_qca: Fix driver shutdown on closed serdev") Signed-off-by: Sasha Levin --- drivers/bluetooth/hci_qca.c | 48 ++++++++++++++++++++++++++++++------- 1 file changed, 39 insertions(+), 9 deletions(-) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 60b0e13bb9fc..652290425028 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -50,6 +50,8 @@ #define IBS_HOST_TX_IDLE_TIMEOUT_MS 2000 #define CMD_TRANS_TIMEOUT_MS 100 #define MEMDUMP_TIMEOUT_MS 8000 +#define IBS_DISABLE_SSR_TIMEOUT_MS (MEMDUMP_TIMEOUT_MS + 1000) +#define FW_DOWNLOAD_TIMEOUT_MS 3000 /* susclk rate */ #define SUSCLK_RATE_32KHZ 32768 @@ -68,12 +70,13 @@ #define QCA_MEMDUMP_BYTE 0xFB enum qca_flags { - QCA_IBS_ENABLED, + QCA_IBS_DISABLED, QCA_DROP_VENDOR_EVENT, QCA_SUSPENDING, QCA_MEMDUMP_COLLECTION, QCA_HW_ERROR_EVENT, - QCA_SSR_TRIGGERED + QCA_SSR_TRIGGERED, + QCA_BT_OFF }; enum qca_capabilities { @@ -870,7 +873,7 @@ static int qca_enqueue(struct hci_uart *hu, struct sk_buff *skb) * Out-Of-Band(GPIOs control) sleep is selected. * Don't wake the device up when suspending. */ - if (!test_bit(QCA_IBS_ENABLED, &qca->flags) || + if (test_bit(QCA_IBS_DISABLED, &qca->flags) || test_bit(QCA_SUSPENDING, &qca->flags)) { skb_queue_tail(&qca->txq, skb); spin_unlock_irqrestore(&qca->hci_ibs_lock, flags); @@ -1015,7 +1018,7 @@ static void qca_controller_memdump(struct work_struct *work) * the controller to send the dump is 8 seconds. let us * start timer to handle this asynchronous activity. */ - clear_bit(QCA_IBS_ENABLED, &qca->flags); + set_bit(QCA_IBS_DISABLED, &qca->flags); set_bit(QCA_MEMDUMP_COLLECTION, &qca->flags); dump = (void *) skb->data; dump_size = __le32_to_cpu(dump->dump_size); @@ -1621,6 +1624,7 @@ static int qca_power_on(struct hci_dev *hdev) struct hci_uart *hu = hci_get_drvdata(hdev); enum qca_btsoc_type soc_type = qca_soc_type(hu); struct qca_serdev *qcadev; + struct qca_data *qca = hu->priv; int ret = 0; /* Non-serdev device usually is powered by external power @@ -1640,6 +1644,7 @@ static int qca_power_on(struct hci_dev *hdev) } } + clear_bit(QCA_BT_OFF, &qca->flags); return ret; } @@ -1659,7 +1664,7 @@ static int qca_setup(struct hci_uart *hu) return ret; /* Patch downloading has to be done without IBS mode */ - clear_bit(QCA_IBS_ENABLED, &qca->flags); + set_bit(QCA_IBS_DISABLED, &qca->flags); /* Enable controller to do both LE scan and BR/EDR inquiry * simultaneously. @@ -1710,7 +1715,7 @@ retry: ret = qca_uart_setup(hdev, qca_baudrate, soc_type, soc_ver, firmware_name); if (!ret) { - set_bit(QCA_IBS_ENABLED, &qca->flags); + clear_bit(QCA_IBS_DISABLED, &qca->flags); qca_debugfs_init(hdev); hu->hdev->hw_error = qca_hw_error; hu->hdev->cmd_timeout = qca_cmd_timeout; @@ -1814,7 +1819,7 @@ static void qca_power_shutdown(struct hci_uart *hu) * data in skb's. */ spin_lock_irqsave(&qca->hci_ibs_lock, flags); - clear_bit(QCA_IBS_ENABLED, &qca->flags); + set_bit(QCA_IBS_DISABLED, &qca->flags); qca_flush(hu); spin_unlock_irqrestore(&qca->hci_ibs_lock, flags); @@ -1833,6 +1838,8 @@ static void qca_power_shutdown(struct hci_uart *hu) } else if (qcadev->bt_en) { gpiod_set_value_cansleep(qcadev->bt_en, 0); } + + set_bit(QCA_BT_OFF, &qca->flags); } static int qca_power_off(struct hci_dev *hdev) @@ -2093,11 +2100,34 @@ static int __maybe_unused qca_suspend(struct device *dev) bool tx_pending = false; int ret = 0; u8 cmd; + u32 wait_timeout = 0; set_bit(QCA_SUSPENDING, &qca->flags); - /* Device is downloading patch or doesn't support in-band sleep. */ - if (!test_bit(QCA_IBS_ENABLED, &qca->flags)) + if (test_bit(QCA_BT_OFF, &qca->flags)) + return 0; + + if (test_bit(QCA_IBS_DISABLED, &qca->flags)) { + wait_timeout = test_bit(QCA_SSR_TRIGGERED, &qca->flags) ? + IBS_DISABLE_SSR_TIMEOUT_MS : + FW_DOWNLOAD_TIMEOUT_MS; + + /* QCA_IBS_DISABLED flag is set to true, During FW download + * and during memory dump collection. It is reset to false, + * After FW download complete and after memory dump collections. + */ + wait_on_bit_timeout(&qca->flags, QCA_IBS_DISABLED, + TASK_UNINTERRUPTIBLE, msecs_to_jiffies(wait_timeout)); + + if (test_bit(QCA_IBS_DISABLED, &qca->flags)) { + bt_dev_err(hu->hdev, "SSR or FW download time out"); + ret = -ETIMEDOUT; + goto error; + } + } + + /* After memory dump collection, Controller is powered off.*/ + if (test_bit(QCA_BT_OFF, &qca->flags)) return 0; cancel_work_sync(&qca->ws_awake_device); From e84ec6e25df9bb0968599e92eacedaf3a0a5b587 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 29 Dec 2022 11:28:29 +0100 Subject: [PATCH 0953/4345] Bluetooth: hci_qca: Fix driver shutdown on closed serdev [ Upstream commit 272970be3dabd24cbe50e393ffee8f04aec3b9a8 ] The driver shutdown callback (which sends EDL_SOC_RESET to the device over serdev) should not be invoked when HCI device is not open (e.g. if hci_dev_open_sync() failed), because the serdev and its TTY are not open either. Also skip this step if device is powered off (qca_power_shutdown()). The shutdown callback causes use-after-free during system reboot with Qualcomm Atheros Bluetooth: Unable to handle kernel paging request at virtual address 0072662f67726fd7 ... CPU: 6 PID: 1 Comm: systemd-shutdow Tainted: G W 6.1.0-rt5-00325-g8a5f56bcfcca #8 Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT) Call trace: tty_driver_flush_buffer+0x4/0x30 serdev_device_write_flush+0x24/0x34 qca_serdev_shutdown+0x80/0x130 [hci_uart] device_shutdown+0x15c/0x260 kernel_restart+0x48/0xac KASAN report: BUG: KASAN: use-after-free in tty_driver_flush_buffer+0x1c/0x50 Read of size 8 at addr ffff16270c2e0018 by task systemd-shutdow/1 CPU: 7 PID: 1 Comm: systemd-shutdow Not tainted 6.1.0-next-20221220-00014-gb85aaf97fb01-dirty #28 Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT) Call trace: dump_backtrace.part.0+0xdc/0xf0 show_stack+0x18/0x30 dump_stack_lvl+0x68/0x84 print_report+0x188/0x488 kasan_report+0xa4/0xf0 __asan_load8+0x80/0xac tty_driver_flush_buffer+0x1c/0x50 ttyport_write_flush+0x34/0x44 serdev_device_write_flush+0x48/0x60 qca_serdev_shutdown+0x124/0x274 device_shutdown+0x1e8/0x350 kernel_restart+0x48/0xb0 __do_sys_reboot+0x244/0x2d0 __arm64_sys_reboot+0x54/0x70 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x44/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xbc/0x140 el0t_64_sync+0x190/0x194 Fixes: 7e7bbddd029b ("Bluetooth: hci_qca: Fix qca6390 enable failure after warm reboot") Cc: Signed-off-by: Krzysztof Kozlowski Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/hci_qca.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 652290425028..096a604ef47f 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2064,10 +2064,17 @@ static void qca_serdev_shutdown(struct device *dev) int timeout = msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS); struct serdev_device *serdev = to_serdev_device(dev); struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev); + struct hci_uart *hu = &qcadev->serdev_hu; + struct hci_dev *hdev = hu->hdev; + struct qca_data *qca = hu->priv; const u8 ibs_wake_cmd[] = { 0xFD }; const u8 edl_reset_soc_cmd[] = { 0x01, 0x00, 0xFC, 0x01, 0x05 }; if (qcadev->btsoc_type == QCA_QCA6390) { + if (test_bit(QCA_BT_OFF, &qca->flags) || + !test_bit(HCI_RUNNING, &hdev->flags)) + return; + serdev_device_write_flush(serdev); ret = serdev_device_write_buf(serdev, ibs_wake_cmd, sizeof(ibs_wake_cmd)); From 2fd232bbd66fafdf7af3cc155c7bb82d96d07bc9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Jan 2023 20:50:24 -0700 Subject: [PATCH 0954/4345] io_uring: don't gate task_work run on TIF_NOTIFY_SIGNAL commit 46a525e199e4037516f7e498c18f065b09df32ac upstream. This isn't a reliable mechanism to tell if we have task_work pending, we really should be looking at whether we have any items queued. This is problematic if forward progress is gated on running said task_work. One such example is reading from a pipe, where the write side has been closed right before the read is started. The fput() of the file queues TWA_RESUME task_work, and we need that task_work to be run before ->release() is called for the pipe. If ->release() isn't called, then the read will sit forever waiting on data that will never arise. Fix this by io_run_task_work() so it checks if we have task_work pending rather than rely on TIF_NOTIFY_SIGNAL for that. The latter obviously doesn't work for task_work that is queued without TWA_SIGNAL. Reported-by: Christiano Haesbaert Cc: stable@vger.kernel.org Link: https://github.com/axboe/liburing/issues/665 Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io-wq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 87bc38b47103..81485c1a9879 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -513,7 +513,7 @@ static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, static bool io_flush_signals(void) { - if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); tracehook_notify_signal(); return true; From abdc16c8361b1420c1228068e0314b981a48bdcd Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 23 Nov 2021 00:07:47 +0000 Subject: [PATCH 0955/4345] io_uring: improve send/recv error handling commit 7297ce3d59449de49d3c9e1f64ae25488750a1fc upstream. Hide all error handling under common if block, removes two extra ifs on the success path and keeps the handling more condensed. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/5761545158a12968f3caf30f747eea65ed75dfc1.1637524285.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 55 +++++++++++++++++++++++++-------------------- 1 file changed, 31 insertions(+), 24 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 0c4d16afb9ef..34dd6267679a 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -4706,17 +4706,18 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) min_ret = iov_iter_count(&kmsg->msg.msg_iter); ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); - if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) - return io_setup_async_msg(req, kmsg); - if (ret == -ERESTARTSYS) - ret = -EINTR; + if (ret < min_ret) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return io_setup_async_msg(req, kmsg); + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } /* fast path, check for non-NULL to avoid function call */ if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < min_ret) - req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4752,13 +4753,13 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); - if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) - return -EAGAIN; - if (ret == -ERESTARTSYS) - ret = -EINTR; - - if (ret < min_ret) + if (ret < min_ret) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; req_set_fail(req); + } __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4945,10 +4946,15 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg, kmsg->uaddr, flags); - if (force_nonblock && ret == -EAGAIN) - return io_setup_async_msg(req, kmsg); - if (ret == -ERESTARTSYS) - ret = -EINTR; + if (ret < min_ret) { + if (ret == -EAGAIN && force_nonblock) + return io_setup_async_msg(req, kmsg); + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { + req_set_fail(req); + } if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); @@ -4956,8 +4962,6 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail(req); __io_req_complete(req, issue_flags, ret, cflags); return 0; } @@ -5004,15 +5008,18 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags) min_ret = iov_iter_count(&msg.msg_iter); ret = sock_recvmsg(sock, &msg, flags); - if (force_nonblock && ret == -EAGAIN) - return -EAGAIN; - if (ret == -ERESTARTSYS) - ret = -EINTR; out_free: + if (ret < min_ret) { + if (ret == -EAGAIN && force_nonblock) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { + req_set_fail(req); + } if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); - if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail(req); __io_req_complete(req, issue_flags, ret, cflags); return 0; } From aadd9b093018183c7895aa07395b786bc71c3d31 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 21 Jan 2023 10:21:22 -0700 Subject: [PATCH 0956/4345] io_uring: ensure recv and recvmsg handle MSG_WAITALL correctly commit 7ba89d2af17aa879dda30f5d5d3f152e587fc551 upstream. We currently don't attempt to get the full asked for length even if MSG_WAITALL is set, if we get a partial receive. If we do see a partial receive, then just note how many bytes we did and return -EAGAIN to get it retried. The iov is advanced appropriately for the vector based case, and we manually bump the buffer and remainder for the non-vector case. Cc: stable@vger.kernel.org Reported-by: Constantine Gavrilov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 34dd6267679a..3d67b9b4100f 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -578,6 +578,7 @@ struct io_sr_msg { int msg_flags; int bgid; size_t len; + size_t done_io; struct io_buffer *kbuf; }; @@ -4903,12 +4904,21 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif + sr->done_io = 0; return 0; } +static bool io_net_retry(struct socket *sock, int flags) +{ + if (!(flags & MSG_WAITALL)) + return false; + return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; +} + static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; + struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; struct io_buffer *kbuf; unsigned flags; @@ -4951,6 +4961,10 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + return io_setup_async_msg(req, kmsg); + } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { req_set_fail(req); @@ -4962,6 +4976,10 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, cflags); return 0; } @@ -5014,12 +5032,22 @@ out_free: return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + return -EAGAIN; + } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { req_set_fail(req); } if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, cflags); return 0; } From 96ccba4a1a59ae6bcfed405961dd399c74d0b2f8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 23 Mar 2022 09:30:05 -0600 Subject: [PATCH 0957/4345] io_uring: add flag for disabling provided buffer recycling commit 8a3e8ee56417f5e0e66580d93941ed9d6f4c8274 upstream. If we need to continue doing this IO, then we don't want a potentially selected buffer recycled. Add a flag for that. Set this for recv/recvmsg if they do partial IO. Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 3d67b9b4100f..7f9fb0cb9230 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -740,6 +740,7 @@ enum { REQ_F_CREDS_BIT, REQ_F_REFCOUNT_BIT, REQ_F_ARM_LTIMEOUT_BIT, + REQ_F_PARTIAL_IO_BIT, /* keep async read/write and isreg together and in order */ REQ_F_NOWAIT_READ_BIT, REQ_F_NOWAIT_WRITE_BIT, @@ -795,6 +796,8 @@ enum { REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), /* there is a linked timeout that has to be armed */ REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), + /* request has already done partial IO */ + REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), }; struct async_poll { @@ -4963,6 +4966,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; return io_setup_async_msg(req, kmsg); } req_set_fail(req); @@ -5036,6 +5040,7 @@ out_free: sr->len -= ret; sr->buf += ret; sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; return -EAGAIN; } req_set_fail(req); From f901b4bfd03ed234f72f28e27d965569531dc505 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 20 Apr 2022 19:21:36 -0600 Subject: [PATCH 0958/4345] io_uring: support MSG_WAITALL for IORING_OP_SEND(MSG) commit 4c3c09439c08b03d9503df0ca4c7619c5842892e upstream. Like commit 7ba89d2af17a for recv/recvmsg, support MSG_WAITALL for the send side. If this flag is set and we do a short send, retry for a stream of seqpacket socket. Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 36 +++++++++++++++++++++++++++++------- 1 file changed, 29 insertions(+), 7 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 7f9fb0cb9230..75d833269751 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -4617,6 +4617,13 @@ static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) } #if defined(CONFIG_NET) +static bool io_net_retry(struct socket *sock, int flags) +{ + if (!(flags & MSG_WAITALL)) + return false; + return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; +} + static int io_setup_async_msg(struct io_kiocb *req, struct io_async_msghdr *kmsg) { @@ -4680,12 +4687,14 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif + sr->done_io = 0; return 0; } static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; + struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; unsigned flags; int min_ret = 0; @@ -4716,12 +4725,21 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return io_setup_async_msg(req, kmsg); + } req_set_fail(req); } /* fast path, check for non-NULL to avoid function call */ if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4762,8 +4780,19 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return -EAGAIN; + } req_set_fail(req); } + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4911,13 +4940,6 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static bool io_net_retry(struct socket *sock, int flags) -{ - if (!(flags & MSG_WAITALL)) - return false; - return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; -} - static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; From 4bc17e6381bdbe7373ffccbda94db56631061a4a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 21 Jan 2023 10:39:22 -0700 Subject: [PATCH 0959/4345] io_uring: allow re-poll if we made progress commit 10c873334febaeea9aa0c25c10b5ac0951b77a5f upstream. We currently check REQ_F_POLLED before arming async poll for a notification to retry. If it's set, then we don't allow poll and will punt to io-wq instead. This is done to prevent a situation where a buggy driver will repeatedly return that there's space/data available yet we get -EAGAIN. However, if we already transferred data, then it should be safe to rely on poll again. Gate the check on whether or not REQ_F_PARTIAL_IO is also set. Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 75d833269751..cc8e13de5fa9 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5694,7 +5694,7 @@ static int io_arm_poll_handler(struct io_kiocb *req) if (!req->file || !file_can_poll(req->file)) return IO_APOLL_ABORTED; - if (req->flags & REQ_F_POLLED) + if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED) return IO_APOLL_ABORTED; if (!def->pollin && !def->pollout) return IO_APOLL_ABORTED; @@ -5710,7 +5710,10 @@ static int io_arm_poll_handler(struct io_kiocb *req) mask |= POLLOUT | POLLWRNORM; } - apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); + if (req->flags & REQ_F_POLLED) + apoll = req->apoll; + else + apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); if (unlikely(!apoll)) return IO_APOLL_ABORTED; apoll->double_poll = NULL; From aa4c9b3e45e234bc011bd26a045f6bdfd4783001 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Sat, 21 Jan 2023 09:13:12 -0700 Subject: [PATCH 0960/4345] io_uring: fix async accept on O_NONBLOCK sockets commit a73825ba70c93e1eb39a845bb3d9885a787f8ffe upstream. Do not set REQ_F_NOWAIT if the socket is non blocking. When enabled this causes the accept to immediately post a CQE with EAGAIN, which means you cannot perform an accept SQE on a NONBLOCK socket asynchronously. By removing the flag if there is no pending accept then poll is armed as usual and when a connection comes in the CQE is posted. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220324143435.2875844-1-dylany@fb.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index cc8e13de5fa9..8c8ba8c067ca 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5112,9 +5112,6 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) struct file *file; int ret, fd; - if (req->file->f_flags & O_NONBLOCK) - req->flags |= REQ_F_NOWAIT; - if (!fixed) { fd = __get_unused_fd_flags(accept->flags, accept->nofile); if (unlikely(fd < 0)) @@ -5127,6 +5124,8 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) if (!fixed) put_unused_fd(fd); ret = PTR_ERR(file); + /* safe to retry */ + req->flags |= REQ_F_PARTIAL_IO; if (ret == -EAGAIN && force_nonblock) return -EAGAIN; if (ret == -ERESTARTSYS) From 78e8151f04f0aa0a5809aafea5de3719c2360033 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Dec 2022 06:37:08 -0700 Subject: [PATCH 0961/4345] io_uring: check for valid register opcode earlier [ Upstream commit 343190841a1f22b96996d9f8cfab902a4d1bfd0e ] We only check the register opcode value inside the restricted ring section, move it into the main io_uring_register() function instead and check it up front. Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 8c8ba8c067ca..f05f033d8496 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -10805,8 +10805,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, return -ENXIO; if (ctx->restricted) { - if (opcode >= IORING_REGISTER_LAST) - return -EINVAL; opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); if (!test_bit(opcode, ctx->restrictions.register_op)) return -EACCES; @@ -10938,6 +10936,9 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, long ret = -EBADF; struct fd f; + if (opcode >= IORING_REGISTER_LAST) + return -EINVAL; + f = fdget(fd); if (!f.file) return -EBADF; From de77faee280163ff03b7ab64af6c9d779a43d4c4 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 14 Jan 2023 09:14:03 -0700 Subject: [PATCH 0962/4345] io_uring: lock overflowing for IOPOLL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 544d163d659d45a206d8929370d5a2984e546cb7 upstream. syzbot reports an issue with overflow filling for IOPOLL: WARNING: CPU: 0 PID: 28 at io_uring/io_uring.c:734 io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734 CPU: 0 PID: 28 Comm: kworker/u4:1 Not tainted 6.2.0-rc3-syzkaller-16369-g358a161a6a9e #0 Workqueue: events_unbound io_ring_exit_work Call trace:  io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734  io_req_cqe_overflow+0x5c/0x70 io_uring/io_uring.c:773  io_fill_cqe_req io_uring/io_uring.h:168 [inline]  io_do_iopoll+0x474/0x62c io_uring/rw.c:1065  io_iopoll_try_reap_events+0x6c/0x108 io_uring/io_uring.c:1513  io_uring_try_cancel_requests+0x13c/0x258 io_uring/io_uring.c:3056  io_ring_exit_work+0xec/0x390 io_uring/io_uring.c:2869  process_one_work+0x2d8/0x504 kernel/workqueue.c:2289  worker_thread+0x340/0x610 kernel/workqueue.c:2436  kthread+0x12c/0x158 kernel/kthread.c:376  ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:863 There is no real problem for normal IOPOLL as flush is also called with uring_lock taken, but it's getting more complicated for IOPOLL|SQPOLL, for which __io_cqring_overflow_flush() happens from the CQ waiting path. Reported-and-tested-by: syzbot+6805087452d72929404e@syzkaller.appspotmail.com Cc: stable@vger.kernel.org # 5.10+ Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index f05f033d8496..b7bd5138bdaf 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2482,12 +2482,26 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, io_init_req_batch(&rb); while (!list_empty(done)) { + struct io_uring_cqe *cqe; + unsigned cflags; + req = list_first_entry(done, struct io_kiocb, inflight_entry); list_del(&req->inflight_entry); - - io_fill_cqe_req(req, req->result, io_put_rw_kbuf(req)); + cflags = io_put_rw_kbuf(req); (*nr_events)++; + cqe = io_get_cqe(ctx); + if (cqe) { + WRITE_ONCE(cqe->user_data, req->user_data); + WRITE_ONCE(cqe->res, req->result); + WRITE_ONCE(cqe->flags, cflags); + } else { + spin_lock(&ctx->completion_lock); + io_cqring_event_overflow(ctx, req->user_data, + req->result, cflags); + spin_unlock(&ctx->completion_lock); + } + if (req_ref_put_and_test(req)) io_req_free_batch(&rb, req, &ctx->submit_state); } From e0140e9da31e1f89baca5f175e073e8aed92688f Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 5 Jan 2023 10:49:15 +0000 Subject: [PATCH 0963/4345] io_uring: fix CQ waiting timeout handling commit 12521a5d5cb7ff0ad43eadfc9c135d86e1131fa8 upstream. Jiffy to ktime CQ waiting conversion broke how we treat timeouts, in particular we rearm it anew every time we get into io_cqring_wait_schedule() without adjusting the timeout. Waiting for 2 CQEs and getting a task_work in the middle may double the timeout value, or even worse in some cases task may wait indefinitely. Cc: stable@vger.kernel.org Fixes: 228339662b398 ("io_uring: don't convert to jiffies for waiting on timeouts") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/f7bffddd71b08f28a877d44d37ac953ddb01590d.1672915663.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index b7bd5138bdaf..e8852d56b1ec 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -7518,7 +7518,7 @@ static int io_run_task_work_sig(void) /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, - ktime_t timeout) + ktime_t *timeout) { int ret; @@ -7530,7 +7530,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, if (test_bit(0, &ctx->check_cq_overflow)) return 1; - if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) + if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) return -ETIME; return 1; } @@ -7593,7 +7593,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, } prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); - ret = io_cqring_wait_schedule(ctx, &iowq, timeout); + ret = io_cqring_wait_schedule(ctx, &iowq, &timeout); finish_wait(&ctx->cq_wait, &iowq.wq); cond_resched(); } while (ret > 0); From e9c6556708d3b1f77f1a9e08881f8bb01e98e919 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 21 Jan 2023 12:36:08 -0700 Subject: [PATCH 0964/4345] io_uring: ensure that cached task references are always put on exit commit e775f93f2ab976a2cdb4a7b53063cbe890904f73 upstream. io_uring caches task references to avoid doing atomics for each of them per request. If a request is put from the same task that allocated it, then we can maintain a per-ctx cache of them. This obviously relies on io_uring always pruning caches in a reliable way, and there's currently a case off io_uring fd release where we can miss that. One example is a ring setup with IOPOLL, which relies on the task polling for completions, which will free them. However, if such a task submits a request and then exits or closes the ring without reaping the completion, then ring release will reap and put. If release happens from that very same task, the completed request task refs will get put back into the cache pool. This is problematic, as we're now beyond the point of pruning caches. Manually drop these caches after doing an IOPOLL reap. This releases references from the current task, which is enough. If another task happens to be doing the release, then the caching will not be triggered and there's no issue. Cc: stable@vger.kernel.org Fixes: e98e49b2bbf7 ("io_uring: extend task put optimisations") Reported-by: Homin Rhee Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index e8852d56b1ec..f8a0d228d799 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -9513,6 +9513,10 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); + /* drop cached put refs after potentially doing completions */ + if (current->io_uring) + io_uring_drop_tctx_refs(current); + INIT_WORK(&ctx->exit_work, io_ring_exit_work); /* * Use system_unbound_wq to avoid spawning tons of event kworkers From 076f872314d4da36e878673cbef1eae3514b0c6d Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 22 Feb 2022 02:55:01 -0800 Subject: [PATCH 0965/4345] io_uring: remove duplicated calls to io_kiocb_ppos commit af9c45ecebaf1b428306f41421f4bcffe439f735 upstream. io_kiocb_ppos is called in both branches, and it seems that the compiler does not fuse this. Fusing removes a few bytes from loop_rw_iter. Before: $ nm -S fs/io_uring.o | grep loop_rw_iter 0000000000002430 0000000000000124 t loop_rw_iter After: $ nm -S fs/io_uring.o | grep loop_rw_iter 0000000000002430 000000000000010d t loop_rw_iter Signed-off-by: Dylan Yudaken Reviewed-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index f8a0d228d799..d8926475cd88 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3300,6 +3300,7 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) struct kiocb *kiocb = &req->rw.kiocb; struct file *file = req->file; ssize_t ret = 0; + loff_t *ppos; /* * Don't support polled IO through this interface, and we can't @@ -3311,6 +3312,8 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) if (kiocb->ki_flags & IOCB_NOWAIT) return -EAGAIN; + ppos = io_kiocb_ppos(kiocb); + while (iov_iter_count(iter)) { struct iovec iovec; ssize_t nr; @@ -3324,10 +3327,10 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) if (rw == READ) { nr = file->f_op->read(file, iovec.iov_base, - iovec.iov_len, io_kiocb_ppos(kiocb)); + iovec.iov_len, ppos); } else { nr = file->f_op->write(file, iovec.iov_base, - iovec.iov_len, io_kiocb_ppos(kiocb)); + iovec.iov_len, ppos); } if (nr < 0) { From ea528ecac3ae58d8197871b29748eefca7d46be8 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 22 Feb 2022 02:55:02 -0800 Subject: [PATCH 0966/4345] io_uring: update kiocb->ki_pos at execution time commit d34e1e5b396a0dbaa4a29b7138df662cfb9d8e8e upstream. Update kiocb->ki_pos at execution time rather than in io_prep_rw(). io_prep_rw() happens before the job is enqueued to a worker and so the offset might be read multiple times before being executed once. Ensures that the file position in a set of _linked_ SQEs will be only obtained after earlier SQEs have completed, and so will include their incremented file position. Signed-off-by: Dylan Yudaken Reviewed-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index d8926475cd88..eaf8463c9b14 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2919,14 +2919,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, req->flags |= REQ_F_ISREG; kiocb->ki_pos = READ_ONCE(sqe->off); - if (kiocb->ki_pos == -1) { - if (!(file->f_mode & FMODE_STREAM)) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = file->f_pos; - } else { - kiocb->ki_pos = 0; - } - } kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); @@ -3008,6 +3000,20 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } } +static inline void io_kiocb_update_pos(struct io_kiocb *req) +{ + struct kiocb *kiocb = &req->rw.kiocb; + + if (kiocb->ki_pos == -1) { + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + } else { + kiocb->ki_pos = 0; + } + } +} + static void kiocb_done(struct kiocb *kiocb, ssize_t ret, unsigned int issue_flags) { @@ -3563,6 +3569,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return ret ?: -EAGAIN; } + io_kiocb_update_pos(req); + ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) { kfree(iovec); @@ -3697,6 +3705,8 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) (req->flags & REQ_F_ISREG)) goto copy_iov; + io_kiocb_update_pos(req); + ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) goto out_free; From e90cfb96999454b6d3f469f3a9414cf7f9df62fe Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 22 Feb 2022 02:55:03 -0800 Subject: [PATCH 0967/4345] io_uring: do not recalculate ppos unnecessarily commit b4aec40015953b65f2f114641e7fd7714c8df8e6 upstream. There is a slight optimisation to be had by calculating the correct pos pointer inside io_kiocb_update_pos and then using that later. It seems code size drops by a bit: 000000000000a1b0 0000000000000400 t io_read 000000000000a5b0 0000000000000319 t io_write vs 000000000000a1b0 00000000000003f6 t io_read 000000000000a5b0 0000000000000310 t io_write Signed-off-by: Dylan Yudaken Reviewed-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index eaf8463c9b14..d4e017b07371 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3000,18 +3000,22 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } } -static inline void io_kiocb_update_pos(struct io_kiocb *req) +static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; + bool is_stream = req->file->f_mode & FMODE_STREAM; if (kiocb->ki_pos == -1) { - if (!(req->file->f_mode & FMODE_STREAM)) { + if (!is_stream) { req->flags |= REQ_F_CUR_POS; kiocb->ki_pos = req->file->f_pos; + return &kiocb->ki_pos; } else { kiocb->ki_pos = 0; + return NULL; } } + return is_stream ? NULL : &kiocb->ki_pos; } static void kiocb_done(struct kiocb *kiocb, ssize_t ret, @@ -3537,6 +3541,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; struct iov_iter_state __state, *state; ssize_t ret, ret2; + loff_t *ppos; if (rw) { iter = &rw->iter; @@ -3569,9 +3574,9 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return ret ?: -EAGAIN; } - io_kiocb_update_pos(req); + ppos = io_kiocb_update_pos(req); - ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result); + ret = rw_verify_area(READ, req->file, ppos, req->result); if (unlikely(ret)) { kfree(iovec); return ret; @@ -3675,6 +3680,7 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; struct iov_iter_state __state, *state; ssize_t ret, ret2; + loff_t *ppos; if (rw) { iter = &rw->iter; @@ -3705,9 +3711,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) (req->flags & REQ_F_ISREG)) goto copy_iov; - io_kiocb_update_pos(req); + ppos = io_kiocb_update_pos(req); - ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result); + ret = rw_verify_area(WRITE, req->file, ppos, req->result); if (unlikely(ret)) goto out_free; From ea2e6286e3e89a115ae554e20ba9aec2b2e1ddff Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 21 Jan 2023 13:38:51 -0700 Subject: [PATCH 0968/4345] io_uring/rw: defer fsnotify calls to task context commit b000145e9907809406d8164c3b2b8861d95aecd1 upstream. We can't call these off the kiocb completion as that might be off soft/hard irq context. Defer the calls to when we process the task_work for this request. That avoids valid complaints like: stack backtrace: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.0.0-rc6-syzkaller-00321-g105a36f3694e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_usage_bug kernel/locking/lockdep.c:3961 [inline] valid_state kernel/locking/lockdep.c:3973 [inline] mark_lock_irq kernel/locking/lockdep.c:4176 [inline] mark_lock.part.0.cold+0x18/0xd8 kernel/locking/lockdep.c:4632 mark_lock kernel/locking/lockdep.c:4596 [inline] mark_usage kernel/locking/lockdep.c:4527 [inline] __lock_acquire+0x11d9/0x56d0 kernel/locking/lockdep.c:5007 lock_acquire kernel/locking/lockdep.c:5666 [inline] lock_acquire+0x1ab/0x570 kernel/locking/lockdep.c:5631 __fs_reclaim_acquire mm/page_alloc.c:4674 [inline] fs_reclaim_acquire+0x115/0x160 mm/page_alloc.c:4688 might_alloc include/linux/sched/mm.h:271 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc mm/slab.c:3278 [inline] __kmem_cache_alloc_lru mm/slab.c:3471 [inline] kmem_cache_alloc+0x39/0x520 mm/slab.c:3491 fanotify_alloc_fid_event fs/notify/fanotify/fanotify.c:580 [inline] fanotify_alloc_event fs/notify/fanotify/fanotify.c:813 [inline] fanotify_handle_event+0x1130/0x3f40 fs/notify/fanotify/fanotify.c:948 send_to_group fs/notify/fsnotify.c:360 [inline] fsnotify+0xafb/0x1680 fs/notify/fsnotify.c:570 __fsnotify_parent+0x62f/0xa60 fs/notify/fsnotify.c:230 fsnotify_parent include/linux/fsnotify.h:77 [inline] fsnotify_file include/linux/fsnotify.h:99 [inline] fsnotify_access include/linux/fsnotify.h:309 [inline] __io_complete_rw_common+0x485/0x720 io_uring/rw.c:195 io_complete_rw+0x1a/0x1f0 io_uring/rw.c:228 iomap_dio_complete_work fs/iomap/direct-io.c:144 [inline] iomap_dio_bio_end_io+0x438/0x5e0 fs/iomap/direct-io.c:178 bio_endio+0x5f9/0x780 block/bio.c:1564 req_bio_endio block/blk-mq.c:695 [inline] blk_update_request+0x3fc/0x1300 block/blk-mq.c:825 scsi_end_request+0x7a/0x9a0 drivers/scsi/scsi_lib.c:541 scsi_io_completion+0x173/0x1f70 drivers/scsi/scsi_lib.c:971 scsi_complete+0x122/0x3b0 drivers/scsi/scsi_lib.c:1438 blk_complete_reqs+0xad/0xe0 block/blk-mq.c:1022 __do_softirq+0x1d3/0x9c6 kernel/softirq.c:571 invoke_softirq kernel/softirq.c:445 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:650 irq_exit_rcu+0x5/0x20 kernel/softirq.c:662 common_interrupt+0xa9/0xc0 arch/x86/kernel/irq.c:240 Fixes: f63cf5192fe3 ("io_uring: ensure that fsnotify is always called") Link: https://lore.kernel.org/all/20220929135627.ykivmdks2w5vzrwg@quack3/ Reported-by: syzbot+dfcc5f4da15868df7d4d@syzkaller.appspotmail.com Reported-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- io_uring/io_uring.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index d4e017b07371..33e6e1011105 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2702,12 +2702,6 @@ static bool io_rw_should_reissue(struct io_kiocb *req) static bool __io_complete_rw_common(struct io_kiocb *req, long res) { - if (req->rw.kiocb.ki_flags & IOCB_WRITE) { - kiocb_end_write(req); - fsnotify_modify(req->file); - } else { - fsnotify_access(req->file); - } if (res != req->result) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { @@ -2760,6 +2754,20 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2, __io_req_complete(req, issue_flags, io_fixup_rw_res(req, res), io_put_rw_kbuf(req)); } +static void io_req_rw_complete(struct io_kiocb *req, bool *locked) +{ + struct io_rw *rw = &req->rw; + + if (rw->kiocb.ki_flags & IOCB_WRITE) { + kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } + + io_req_task_complete(req, locked); +} + static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); @@ -2767,7 +2775,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) if (__io_complete_rw_common(req, res)) return; req->result = io_fixup_rw_res(req, res); - req->io_task_work.func = io_req_task_complete; + req->io_task_work.func = io_req_rw_complete; io_req_task_work_add(req); } From 8ca60d59b963ed8af9d9a037a6610c6f66a0afe5 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Mon, 16 Jan 2023 16:22:10 +0200 Subject: [PATCH 0969/4345] xhci-pci: set the dma max_seg_size commit 93915a4170e9defd56a767a18e6c4076f3d18609 upstream. Allow devices to have dma operations beyond 64K, and avoid warnings such as: xhci_hcd 0000:00:14.0: mapping sg segment longer than device claims to support [len=98304] [max=65536] Cc: stable@vger.kernel.org Cc: Takashi Iwai Signed-off-by: Ricardo Ribalda Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230116142216.1141605-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 9168b492c02b..88248a09fdaa 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -451,6 +451,8 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) if (xhci->quirks & XHCI_DEFAULT_PM_RUNTIME_ALLOW) pm_runtime_allow(&dev->dev); + dma_set_max_seg_size(&dev->dev, UINT_MAX); + return 0; put_usb3_hcd: From 66fc1600855c05c4ba4e997184c91cf298e0405c Mon Sep 17 00:00:00 2001 From: Jimmy Hu Date: Mon, 16 Jan 2023 16:22:11 +0200 Subject: [PATCH 0970/4345] usb: xhci: Check endpoint is valid before dereferencing it commit e8fb5bc76eb86437ab87002d4a36d6da02165654 upstream. When the host controller is not responding, all URBs queued to all endpoints need to be killed. This can cause a kernel panic if we dereference an invalid endpoint. Fix this by using xhci_get_virt_ep() helper to find the endpoint and checking if the endpoint is valid before dereferencing it. [233311.853271] xhci-hcd xhci-hcd.1.auto: xHCI host controller not responding, assume dead [233311.853393] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000e8 [233311.853964] pc : xhci_hc_died+0x10c/0x270 [233311.853971] lr : xhci_hc_died+0x1ac/0x270 [233311.854077] Call trace: [233311.854085] xhci_hc_died+0x10c/0x270 [233311.854093] xhci_stop_endpoint_command_watchdog+0x100/0x1a4 [233311.854105] call_timer_fn+0x50/0x2d4 [233311.854112] expire_timers+0xac/0x2e4 [233311.854118] run_timer_softirq+0x300/0xabc [233311.854127] __do_softirq+0x148/0x528 [233311.854135] irq_exit+0x194/0x1a8 [233311.854143] __handle_domain_irq+0x164/0x1d0 [233311.854149] gic_handle_irq.22273+0x10c/0x188 [233311.854156] el1_irq+0xfc/0x1a8 [233311.854175] lpm_cpuidle_enter+0x25c/0x418 [msm_pm] [233311.854185] cpuidle_enter_state+0x1f0/0x764 [233311.854194] do_idle+0x594/0x6ac [233311.854201] cpu_startup_entry+0x7c/0x80 [233311.854209] secondary_start_kernel+0x170/0x198 Fixes: 50e8725e7c42 ("xhci: Refactor command watchdog and fix split string.") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Hu Signed-off-by: Mathias Nyman Message-ID: <0fe978ed-8269-9774-1c40-f8a98c17e838@linux.intel.com> Link: https://lore.kernel.org/r/20230116142216.1141605-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-ring.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index ead42fc3e16d..b69b8c7e7966 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1044,7 +1044,10 @@ static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci, struct xhci_virt_ep *ep; struct xhci_ring *ring; - ep = &xhci->devs[slot_id]->eps[ep_index]; + ep = xhci_get_virt_ep(xhci, slot_id, ep_index); + if (!ep) + return; + if ((ep->ep_state & EP_HAS_STREAMS) || (ep->ep_state & EP_GETTING_NO_STREAMS)) { int stream_id; From 081105213ff6f661c114781d469233c7d0e09c2e Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 16 Jan 2023 16:22:12 +0200 Subject: [PATCH 0971/4345] xhci: Fix null pointer dereference when host dies commit a2bc47c43e70cf904b1af49f76d572326c08bca7 upstream. Make sure xhci_free_dev() and xhci_kill_endpoint_urbs() do not race and cause null pointer dereference when host suddenly dies. Usb core may call xhci_free_dev() which frees the xhci->devs[slot_id] virt device at the same time that xhci_kill_endpoint_urbs() tries to loop through all the device's endpoints, checking if there are any cancelled urbs left to give back. hold the xhci spinlock while freeing the virt device Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230116142216.1141605-4-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index c968dd865314..bf1febdfa706 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3919,6 +3919,7 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); struct xhci_virt_device *virt_dev; struct xhci_slot_ctx *slot_ctx; + unsigned long flags; int i, ret; /* @@ -3947,7 +3948,11 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) } virt_dev->udev = NULL; xhci_disable_slot(xhci, udev->slot_id); + + spin_lock_irqsave(&xhci->lock, flags); xhci_free_virt_device(xhci, udev->slot_id); + spin_unlock_irqrestore(&xhci->lock, flags); + } int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) From 83e3a5be7475c4b1670b4f3a57728287077cec9e Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 16 Jan 2023 16:22:13 +0200 Subject: [PATCH 0972/4345] xhci: Add update_hub_device override for PCI xHCI hosts commit 23a3b8d5a2365653fd9bc5a9454d1e7f4facbf85 upstream. Allow PCI hosts to check and tune roothub and port settings before the hub is up and running. This override is needed to turn off U1 and U2 LPM for some ports based on per port ACPI _DSM, _UPC, or possibly vendor specific mmio values for Intel xHC hosts. Usb core calls the host update_hub_device once it creates a hub. Entering U1 or U2 link power save state on ports with this limitation will cause link to fail, turning the usb device unusable in that setup. Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230116142216.1141605-5-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 9 +++++++++ drivers/usb/host/xhci.c | 5 ++++- drivers/usb/host/xhci.h | 4 ++++ 3 files changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 88248a09fdaa..90c71979ba5e 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -77,9 +77,12 @@ static const char hcd_name[] = "xhci_hcd"; static struct hc_driver __read_mostly xhci_pci_hc_driver; static int xhci_pci_setup(struct usb_hcd *hcd); +static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, + struct usb_tt *tt, gfp_t mem_flags); static const struct xhci_driver_overrides xhci_pci_overrides __initconst = { .reset = xhci_pci_setup, + .update_hub_device = xhci_pci_update_hub_device, }; /* called after powerup, by probe or system-pm "wakeup" */ @@ -382,6 +385,12 @@ static int xhci_pci_setup(struct usb_hcd *hcd) return xhci_pci_reinit(xhci, pdev); } +static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, + struct usb_tt *tt, gfp_t mem_flags) +{ + return xhci_update_hub_device(hcd, hdev, tt, mem_flags); +} + /* * We need to register our own PCI probe function (instead of the USB core's * function) in order to create a second roothub under xHCI. diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index bf1febdfa706..7248a3d266bd 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -5081,7 +5081,7 @@ static int xhci_disable_usb3_lpm_timeout(struct usb_hcd *hcd, /* Once a hub descriptor is fetched for a device, we need to update the xHC's * internal data structures for the device. */ -static int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, +int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, struct usb_tt *tt, gfp_t mem_flags) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); @@ -5181,6 +5181,7 @@ static int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, xhci_free_command(xhci, config_cmd); return ret; } +EXPORT_SYMBOL_GPL(xhci_update_hub_device); static int xhci_get_frame(struct usb_hcd *hcd) { @@ -5451,6 +5452,8 @@ void xhci_init_driver(struct hc_driver *drv, drv->check_bandwidth = over->check_bandwidth; if (over->reset_bandwidth) drv->reset_bandwidth = over->reset_bandwidth; + if (over->update_hub_device) + drv->update_hub_device = over->update_hub_device; } } EXPORT_SYMBOL_GPL(xhci_init_driver); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index ac09b171b783..4395c94e227e 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1933,6 +1933,8 @@ struct xhci_driver_overrides { int (*start)(struct usb_hcd *hcd); int (*check_bandwidth)(struct usb_hcd *, struct usb_device *); void (*reset_bandwidth)(struct usb_hcd *, struct usb_device *); + int (*update_hub_device)(struct usb_hcd *hcd, struct usb_device *hdev, + struct usb_tt *tt, gfp_t mem_flags); }; #define XHCI_CFC_DELAY 10 @@ -2089,6 +2091,8 @@ void xhci_init_driver(struct hc_driver *drv, const struct xhci_driver_overrides *over); int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev); void xhci_reset_bandwidth(struct usb_hcd *hcd, struct usb_device *udev); +int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, + struct usb_tt *tt, gfp_t mem_flags); int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id); int xhci_ext_cap_init(struct xhci_hcd *xhci); From 4d70a8a9ab8edfa589cc13ad6e8bde3e26dfcdcf Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 16 Jan 2023 16:22:14 +0200 Subject: [PATCH 0973/4345] xhci: Add a flag to disable USB3 lpm on a xhci root port level. commit 0522b9a1653048440da5f21747f21e498b9220d1 upstream. One USB3 roothub port may support link power management, while another root port on the same xHC can't due to different retimers used for the ports. This is the case with Intel Alder Lake, and possible future platforms where retimers used for USB4 ports cause too long exit latecy to enable native USB3 lpm U1 and U2 states. Add a flag in the xhci port structure to indicate if the port is lpm_incapable, and check it while calculating exit latency. Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230116142216.1141605-6-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 8 ++++++++ drivers/usb/host/xhci.h | 1 + 2 files changed, 9 insertions(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 7248a3d266bd..2967372a9988 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -5009,6 +5009,7 @@ static int xhci_enable_usb3_lpm_timeout(struct usb_hcd *hcd, struct usb_device *udev, enum usb3_link_state state) { struct xhci_hcd *xhci; + struct xhci_port *port; u16 hub_encoded_timeout; int mel; int ret; @@ -5022,6 +5023,13 @@ static int xhci_enable_usb3_lpm_timeout(struct usb_hcd *hcd, !xhci->devs[udev->slot_id]) return USB3_LPM_DISABLED; + /* If connected to root port then check port can handle lpm */ + if (udev->parent && !udev->parent->parent) { + port = xhci->usb3_rhub.ports[udev->portnum - 1]; + if (port->lpm_incapable) + return USB3_LPM_DISABLED; + } + hub_encoded_timeout = xhci_calculate_lpm_timeout(hcd, udev, state); mel = calculate_max_exit_latency(udev, state, hub_encoded_timeout); if (mel < 0) { diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 4395c94e227e..c7749f6e3474 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1728,6 +1728,7 @@ struct xhci_port { int hcd_portnum; struct xhci_hub *rhub; struct xhci_port_cap *port_cap; + unsigned int lpm_incapable:1; }; struct xhci_hub { From 2551f8cbf2deb588b3b143d5f3399f1fa61fc408 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 16 Jan 2023 16:22:15 +0200 Subject: [PATCH 0974/4345] usb: acpi: add helper to check port lpm capability using acpi _DSM commit cd702d18c882d5a4ea44bbdb38edd5d5577ef640 upstream. Add a helper to evaluate ACPI usb device specific method (_DSM) provided in case the USB3 port shouldn't enter U1 and U2 link states. This _DSM was added as port specific retimer configuration may lead to exit latencies growing beyond U1/U2 exit limits, and OS needs a way to find which ports can't support U1/U2 link power management states. This _DSM is also used by windows: Link: https://docs.microsoft.com/en-us/windows-hardware/drivers/bringup/usb-device-specific-method---dsm- Some patch issues found in testing resolved by Ron Lee Cc: stable@vger.kernel.org Tested-by: Ron Lee Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230116142216.1141605-7-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/usb-acpi.c | 65 +++++++++++++++++++++++++++++++++++++ include/linux/usb.h | 3 ++ 2 files changed, 68 insertions(+) diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c index 50b2fc7fcc0e..8751276ef578 100644 --- a/drivers/usb/core/usb-acpi.c +++ b/drivers/usb/core/usb-acpi.c @@ -37,6 +37,71 @@ bool usb_acpi_power_manageable(struct usb_device *hdev, int index) } EXPORT_SYMBOL_GPL(usb_acpi_power_manageable); +#define UUID_USB_CONTROLLER_DSM "ce2ee385-00e6-48cb-9f05-2edb927c4899" +#define USB_DSM_DISABLE_U1_U2_FOR_PORT 5 + +/** + * usb_acpi_port_lpm_incapable - check if lpm should be disabled for a port. + * @hdev: USB device belonging to the usb hub + * @index: zero based port index + * + * Some USB3 ports may not support USB3 link power management U1/U2 states + * due to different retimer setup. ACPI provides _DSM method which returns 0x01 + * if U1 and U2 states should be disabled. Evaluate _DSM with: + * Arg0: UUID = ce2ee385-00e6-48cb-9f05-2edb927c4899 + * Arg1: Revision ID = 0 + * Arg2: Function Index = 5 + * Arg3: (empty) + * + * Return 1 if USB3 port is LPM incapable, negative on error, otherwise 0 + */ + +int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index) +{ + union acpi_object *obj; + acpi_handle port_handle; + int port1 = index + 1; + guid_t guid; + int ret; + + ret = guid_parse(UUID_USB_CONTROLLER_DSM, &guid); + if (ret) + return ret; + + port_handle = usb_get_hub_port_acpi_handle(hdev, port1); + if (!port_handle) { + dev_dbg(&hdev->dev, "port-%d no acpi handle\n", port1); + return -ENODEV; + } + + if (!acpi_check_dsm(port_handle, &guid, 0, + BIT(USB_DSM_DISABLE_U1_U2_FOR_PORT))) { + dev_dbg(&hdev->dev, "port-%d no _DSM function %d\n", + port1, USB_DSM_DISABLE_U1_U2_FOR_PORT); + return -ENODEV; + } + + obj = acpi_evaluate_dsm(port_handle, &guid, 0, + USB_DSM_DISABLE_U1_U2_FOR_PORT, NULL); + + if (!obj) + return -ENODEV; + + if (obj->type != ACPI_TYPE_INTEGER) { + dev_dbg(&hdev->dev, "evaluate port-%d _DSM failed\n", port1); + ACPI_FREE(obj); + return -EINVAL; + } + + if (obj->integer.value == 0x01) + ret = 1; + + ACPI_FREE(obj); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_acpi_port_lpm_incapable); + /** * usb_acpi_set_power_state - control usb port's power via acpi power * resource diff --git a/include/linux/usb.h b/include/linux/usb.h index a093667991bb..568be613bdb3 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -754,11 +754,14 @@ extern struct device *usb_intf_get_dma_device(struct usb_interface *intf); extern int usb_acpi_set_power_state(struct usb_device *hdev, int index, bool enable); extern bool usb_acpi_power_manageable(struct usb_device *hdev, int index); +extern int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index); #else static inline int usb_acpi_set_power_state(struct usb_device *hdev, int index, bool enable) { return 0; } static inline bool usb_acpi_power_manageable(struct usb_device *hdev, int index) { return true; } +static inline int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index) + { return 0; } #endif /* USB autosuspend and autoresume */ From 96562a23cfaf909bfa28d878fb70ce18a25201b1 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 16 Jan 2023 16:22:16 +0200 Subject: [PATCH 0975/4345] xhci: Detect lpm incapable xHC USB3 roothub ports from ACPI tables commit 74622f0a81d0c2bcfc39f9192b788124e8c7f0af upstream. USB3 ports on xHC hosts may have retimers that cause too long exit latency to work with native USB3 U1/U2 link power management states. For now only use usb_acpi_port_lpm_incapable() to evaluate if port lpm should be disabled while setting up the USB3 roothub. Other ways to identify lpm incapable ports can be added here later if ACPI _DSM does not exist. Limit this to Intel hosts for now, this is to my knowledge only an Intel issue. Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230116142216.1141605-8-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 90c71979ba5e..aff65cefead2 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -351,8 +351,38 @@ static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) NULL); ACPI_FREE(obj); } + +static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev) +{ + struct xhci_hcd *xhci = hcd_to_xhci(hcd); + struct xhci_hub *rhub = &xhci->usb3_rhub; + int ret; + int i; + + /* This is not the usb3 roothub we are looking for */ + if (hcd != rhub->hcd) + return; + + if (hdev->maxchild > rhub->num_ports) { + dev_err(&hdev->dev, "USB3 roothub port number mismatch\n"); + return; + } + + for (i = 0; i < hdev->maxchild; i++) { + ret = usb_acpi_port_lpm_incapable(hdev, i); + + dev_dbg(&hdev->dev, "port-%d disable U1/U2 _DSM: %d\n", i + 1, ret); + + if (ret >= 0) { + rhub->ports[i]->lpm_incapable = ret; + continue; + } + } +} + #else static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { } +static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev) { } #endif /* CONFIG_ACPI */ /* called during probe() after chip reset completes */ @@ -388,6 +418,10 @@ static int xhci_pci_setup(struct usb_hcd *hcd) static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, struct usb_tt *tt, gfp_t mem_flags) { + /* Check if acpi claims some USB3 roothub ports are lpm incapable */ + if (!hdev->parent) + xhci_find_lpm_incapable_ports(hcd, hdev); + return xhci_update_hub_device(hcd, hdev, tt, mem_flags); } From 9f8e45720e0e7edb661d0082422f662ed243d8d8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 20 Jan 2023 11:03:20 +0100 Subject: [PATCH 0976/4345] prlimit: do_prlimit needs to have a speculation check commit 739790605705ddcf18f21782b9c99ad7d53a8c11 upstream. do_prlimit() adds the user-controlled resource value to a pointer that will subsequently be dereferenced. In order to help prevent this codepath from being used as a spectre "gadget" a barrier needs to be added after checking the range. Reported-by: Jordy Zomer Tested-by: Jordy Zomer Suggested-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- kernel/sys.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/sys.c b/kernel/sys.c index 24a3a28ae228..9f59cc8ab8f8 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1548,6 +1548,8 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); + if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; From 3774654f7a63c45d52a02005e31a6301c695929a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?= Date: Tue, 27 Dec 2022 01:44:30 -0800 Subject: [PATCH 0977/4345] USB: serial: option: add Quectel EM05-G (GR) modem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6c331f32e32ac71eb3e8b93fceda2802d7ecb889 upstream. The EM05-G (GR) modem has 2 USB configurations that are configurable via the AT command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate with the following interfaces, respectively: "RMNET" : AT + DIAG + NMEA + Modem + QMI "MBIM" : MBIM + AT + DIAG + NMEA + Modem The detailed description of the USB configuration for each mode as follows: RMNET Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 21 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0313 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms MBIM Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 16 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0313 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Duke Xin(辛安文) Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 5636b8f52216..dd3247e3ed21 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -256,6 +256,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM05G 0x030a #define QUECTEL_PRODUCT_EM060K 0x030b #define QUECTEL_PRODUCT_EM05G_SG 0x0311 +#define QUECTEL_PRODUCT_EM05G_GR 0x0313 #define QUECTEL_PRODUCT_EM12 0x0512 #define QUECTEL_PRODUCT_RM500Q 0x0800 #define QUECTEL_PRODUCT_RM520N 0x0801 @@ -1161,6 +1162,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff), .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_GR, 0xff), + .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff), .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) }, From 46b898f9345d5da82b68e17fd52a4207cf755bd6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?= Date: Tue, 27 Dec 2022 01:28:25 -0800 Subject: [PATCH 0978/4345] USB: serial: option: add Quectel EM05-G (CS) modem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit bb78654b0b46316dac687fd4b7dc7cce636f46cd upstream. The EM05-G (CS) modem has 2 USB configurations that are configurable via the AT command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate with the following interfaces, respectively: "RMNET" : AT + DIAG + NMEA + Modem + QMI "MBIM" : MBIM + AT + DIAG + NMEA + Modem The detailed description of the USB configuration for each mode as follows: RMNET Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 21 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=030C Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms MBIM Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 16 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=030C Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Duke Xin(辛安文) Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index dd3247e3ed21..aae92302b15b 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -255,6 +255,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EP06 0x0306 #define QUECTEL_PRODUCT_EM05G 0x030a #define QUECTEL_PRODUCT_EM060K 0x030b +#define QUECTEL_PRODUCT_EM05G_CS 0x030c #define QUECTEL_PRODUCT_EM05G_SG 0x0311 #define QUECTEL_PRODUCT_EM05G_GR 0x0313 #define QUECTEL_PRODUCT_EM12 0x0512 @@ -1164,6 +1165,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_GR, 0xff), .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_CS, 0xff), + .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff), .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) }, From 21c5b618128bd4de52c95ab0f7027b85a4c3c557 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?= Date: Tue, 27 Dec 2022 01:51:27 -0800 Subject: [PATCH 0979/4345] USB: serial: option: add Quectel EM05-G (RS) modem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b72d13977689f0c717444010e108c4f20658dfee upstream. The EM05-G (RS) modem has 2 USB configurations that are configurable via the AT command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate with the following interfaces, respectively: "RMNET" : AT + DIAG + NMEA + Modem + QMI "MBIM" : MBIM + AT + DIAG + NMEA + Modem The detailed description of the USB configuration for each mode as follows: RMNET Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 21 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0314 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms MBIM Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 16 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0314 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-G C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Duke Xin(辛安文) Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index aae92302b15b..97231c145063 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -258,6 +258,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM05G_CS 0x030c #define QUECTEL_PRODUCT_EM05G_SG 0x0311 #define QUECTEL_PRODUCT_EM05G_GR 0x0313 +#define QUECTEL_PRODUCT_EM05G_RS 0x0314 #define QUECTEL_PRODUCT_EM12 0x0512 #define QUECTEL_PRODUCT_RM500Q 0x0800 #define QUECTEL_PRODUCT_RM520N 0x0801 @@ -1167,6 +1168,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_CS, 0xff), .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_RS, 0xff), + .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff), .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) }, From fcd49b230906747dc5906c0e582ed68b77cec791 Mon Sep 17 00:00:00 2001 From: Ali Mirghasemi Date: Wed, 28 Dec 2022 15:08:47 +0330 Subject: [PATCH 0980/4345] USB: serial: option: add Quectel EC200U modem commit d9bbb15881046bd76f8710c76e26a740eee997ef upstream. Add support for EC200U modem 0x0901: EC200U - AT + AP + CP + NMEA + DIAG + MOS usb-device output: T: Bus=01 Lev=02 Prnt=02 Port=02 Cnt=01 Dev#= 4 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0901 Rev= 3.18 S: Manufacturer=Android S: Product=Android C:* #Ifs= 9 Cfg#= 1 Atr=e0 MxPwr=400mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=06 Prot=00 I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=06 Prot=00 Driver=cdc_ether E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=83(I) Atr=03(Int.) MxPS= 512 Ivl=4096ms I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 7 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=8a(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=89(I) Atr=03(Int.) MxPS= 512 Ivl=4096ms I:* If#= 8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=08(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Ali Mirghasemi Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 97231c145063..3f76c25462a7 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -262,6 +262,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM12 0x0512 #define QUECTEL_PRODUCT_RM500Q 0x0800 #define QUECTEL_PRODUCT_RM520N 0x0801 +#define QUECTEL_PRODUCT_EC200U 0x0901 #define QUECTEL_PRODUCT_EC200S_CN 0x6002 #define QUECTEL_PRODUCT_EC200T 0x6026 #define QUECTEL_PRODUCT_RM500K 0x7001 @@ -1189,6 +1190,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) }, From 2f44c60bb89c0697718355befe9b386597201280 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?= Date: Sun, 15 Jan 2023 18:07:27 -0800 Subject: [PATCH 0981/4345] USB: serial: option: add Quectel EM05CN (SG) modem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1541dd0097c0f8f470e76eddf5120fc55a7e3101 upstream. The EM05CN (SG) modem has 2 USB configurations that are configurable via the AT command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate with the following interfaces, respectively: "MBIM" : AT + MBIM + DIAG + NMEA + MODEM "RMNET" : AT + DIAG + NMEA + Modem + QMI The detailed description of the USB configuration for each mode as follows: MBIM Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0310 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-CN C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA A: FirstIf#= 1 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I: If#= 2 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 2 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms RMNET Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 3 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0310 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-CN C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Duke Xin(辛安文) Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 3f76c25462a7..d6f01804d91a 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -256,6 +256,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM05G 0x030a #define QUECTEL_PRODUCT_EM060K 0x030b #define QUECTEL_PRODUCT_EM05G_CS 0x030c +#define QUECTEL_PRODUCT_EM05CN_SG 0x0310 #define QUECTEL_PRODUCT_EM05G_SG 0x0311 #define QUECTEL_PRODUCT_EM05G_GR 0x0313 #define QUECTEL_PRODUCT_EM05G_RS 0x0314 @@ -1163,6 +1164,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff), .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN_SG, 0xff), + .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff), .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_GR, 0xff), From a06e9ec5abde6fe0cc03f2199c259601c5d19304 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?= Date: Sun, 15 Jan 2023 18:33:28 -0800 Subject: [PATCH 0982/4345] USB: serial: option: add Quectel EM05CN modem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 71dfd381a7c051f16a61f82fbd38a4cca563bdca upstream. The EM05CN modem has 2 USB configurations that are configurable via the AT command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate with the following interfaces, respectively: "MBIM" : AT + MBIM + DIAG + NMEA + MODEM "RMNET" : AT + DIAG + NMEA + Modem + QMI The detailed description of the USB configuration for each mode as follows: MBIM Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0312 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-CN C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA A: FirstIf#= 1 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I: If#= 2 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 2 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms RMNET Mode -------------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 3 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0312 Rev= 3.18 S: Manufacturer=Quectel S: Product=Quectel EM05-CN C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Duke Xin(辛安文) Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index d6f01804d91a..2fc65cbbfea9 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -258,6 +258,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM05G_CS 0x030c #define QUECTEL_PRODUCT_EM05CN_SG 0x0310 #define QUECTEL_PRODUCT_EM05G_SG 0x0311 +#define QUECTEL_PRODUCT_EM05CN 0x0312 #define QUECTEL_PRODUCT_EM05G_GR 0x0313 #define QUECTEL_PRODUCT_EM05G_RS 0x0314 #define QUECTEL_PRODUCT_EM12 0x0512 @@ -1164,6 +1165,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff), .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN, 0xff), + .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN_SG, 0xff), .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff), From 20d0dedc7a04f8bb3d1acd79320b9aa61c8fbc33 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Jan 2023 17:39:32 +0100 Subject: [PATCH 0983/4345] staging: vchiq_arm: fix enum vchiq_status return types commit 7d83299351fe7c812c529f5e39fe63b5312e4233 upstream. gcc-13 notices a type mismatch between function declaration and definition for a few functions that have been converted from returning vchiq specific status values to regular error codes: drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c:662:5: error: conflicting types for 'vchiq_initialise' due to enum/integer mismatch; have 'int(struct vchiq_instance **)' [-Werror=enum-int-mismatch] drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c:1411:1: error: conflicting types for 'vchiq_use_internal' due to enum/integer mismatch; have 'int(struct vchiq_state *, struct vchiq_service *, enum USE_TYPE_E)' [-Werror=enum-int-mismatch] drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c:1468:1: error: conflicting types for 'vchiq_release_internal' due to enum/integer mismatch; have 'int(struct vchiq_state *, struct vchiq_service *)' [-Werror=enum-int-mismatch] Change the declarations to match the actual function definition. Fixes: a9fbd828be7f ("staging: vchiq_arm: drop enum vchiq_status from vchiq_*_internal") Cc: stable Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230117163957.1109872-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- .../staging/vc04_services/include/linux/raspberrypi/vchiq.h | 2 +- drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h b/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h index fefc664eefcf..f5e1ae5f5ee2 100644 --- a/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h +++ b/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h @@ -82,7 +82,7 @@ struct vchiq_service_params_kernel { struct vchiq_instance; -extern enum vchiq_status vchiq_initialise(struct vchiq_instance **pinstance); +extern int vchiq_initialise(struct vchiq_instance **pinstance); extern enum vchiq_status vchiq_shutdown(struct vchiq_instance *instance); extern enum vchiq_status vchiq_connect(struct vchiq_instance *instance); extern enum vchiq_status vchiq_open_service(struct vchiq_instance *instance, diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h index 0784c5002417..77d8fb180173 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h @@ -89,10 +89,10 @@ extern struct vchiq_arm_state* vchiq_platform_get_arm_state(struct vchiq_state *state); -extern enum vchiq_status +extern int vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service, enum USE_TYPE_E use_type); -extern enum vchiq_status +extern int vchiq_release_internal(struct vchiq_state *state, struct vchiq_service *service); From e0db5d44bc2739328be0a78c09e7b3b2e513c82e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 20 Jan 2023 14:53:30 +0100 Subject: [PATCH 0984/4345] USB: misc: iowarrior: fix up header size for USB_DEVICE_ID_CODEMERCS_IOW100 commit 14ff7460bb58662d86aa50298943cc7d25532e28 upstream. The USB_DEVICE_ID_CODEMERCS_IOW100 header size was incorrect, it should be 12, not 13. Cc: stable Fixes: 17a82716587e ("USB: iowarrior: fix up report size handling for some devices") Reported-by: Christoph Jung Link: https://lore.kernel.org/r/20230120135330.3842518-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/iowarrior.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index 72a06af25081..51a5d626134c 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -817,7 +817,7 @@ static int iowarrior_probe(struct usb_interface *interface, break; case USB_DEVICE_ID_CODEMERCS_IOW100: - dev->report_size = 13; + dev->report_size = 12; break; } } From 193cd853145b63e670bd73740250983af1475330 Mon Sep 17 00:00:00 2001 From: Abel Vesa Date: Thu, 24 Nov 2022 17:49:40 +0000 Subject: [PATCH 0985/4345] misc: fastrpc: Don't remove map on creater_process and device_release commit 5bb96c8f9268e2fdb0e5321cbc358ee5941efc15 upstream. Do not remove the map from the list on error path in fastrpc_init_create_process, instead call fastrpc_map_put, to avoid use-after-free. Do not remove it on fastrpc_device_release either, call fastrpc_map_put instead. The fastrpc_free_map is the only proper place to remove the map. This is called only after the reference count is 0. Fixes: b49f6d83e290 ("misc: fastrpc: Fix a possible double free") Cc: stable Co-developed-by: Ola Jeppsson Signed-off-by: Ola Jeppsson Signed-off-by: Abel Vesa Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20221124174941.418450-3-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 2c3142b4b5dd..e9d6bb2279fb 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -247,6 +247,13 @@ static void fastrpc_free_map(struct kref *ref) dma_buf_put(map->buf); } + if (map->fl) { + spin_lock(&map->fl->lock); + list_del(&map->node); + spin_unlock(&map->fl->lock); + map->fl = NULL; + } + kfree(map); } @@ -1112,12 +1119,7 @@ err_invoke: fl->init_mem = NULL; fastrpc_buf_free(imem); err_alloc: - if (map) { - spin_lock(&fl->lock); - list_del(&map->node); - spin_unlock(&fl->lock); - fastrpc_map_put(map); - } + fastrpc_map_put(map); err: kfree(args); @@ -1194,10 +1196,8 @@ static int fastrpc_device_release(struct inode *inode, struct file *file) fastrpc_context_put(ctx); } - list_for_each_entry_safe(map, m, &fl->maps, node) { - list_del(&map->node); + list_for_each_entry_safe(map, m, &fl->maps, node) fastrpc_map_put(map); - } list_for_each_entry_safe(buf, b, &fl->mmaps, node) { list_del(&buf->node); From b171d0d2cf1b8387c72c8d325c5d5746fa271e39 Mon Sep 17 00:00:00 2001 From: Ola Jeppsson Date: Thu, 24 Nov 2022 17:49:41 +0000 Subject: [PATCH 0986/4345] misc: fastrpc: Fix use-after-free race condition for maps commit 96b328d119eca7563c1edcc4e1039a62e6370ecb upstream. It is possible that in between calling fastrpc_map_get() until map->fl->lock is taken in fastrpc_free_map(), another thread can call fastrpc_map_lookup() and get a reference to a map that is about to be deleted. Rewrite fastrpc_map_get() to only increase the reference count of a map if it's non-zero. Propagate this to callers so they can know if a map is about to be deleted. Fixes this warning: refcount_t: addition on 0; use-after-free. WARNING: CPU: 5 PID: 10100 at lib/refcount.c:25 refcount_warn_saturate ... Call trace: refcount_warn_saturate [fastrpc_map_get inlined] [fastrpc_map_lookup inlined] fastrpc_map_create fastrpc_internal_invoke fastrpc_device_ioctl __arm64_sys_ioctl invoke_syscall Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Cc: stable Signed-off-by: Ola Jeppsson Signed-off-by: Abel Vesa Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20221124174941.418450-4-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index e9d6bb2279fb..67a51f69cf9a 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -263,10 +263,12 @@ static void fastrpc_map_put(struct fastrpc_map *map) kref_put(&map->refcount, fastrpc_free_map); } -static void fastrpc_map_get(struct fastrpc_map *map) +static int fastrpc_map_get(struct fastrpc_map *map) { - if (map) - kref_get(&map->refcount); + if (!map) + return -ENOENT; + + return kref_get_unless_zero(&map->refcount) ? 0 : -ENOENT; } static int fastrpc_map_find(struct fastrpc_user *fl, int fd, From 7efeed828c9018d69926831672b44df9a7b117ab Mon Sep 17 00:00:00 2001 From: Flavio Suligoi Date: Mon, 19 Dec 2022 13:47:59 +0100 Subject: [PATCH 0987/4345] usb: core: hub: disable autosuspend for TI TUSB8041 commit 7171b0e261b17de96490adf053b8bb4b00061bcf upstream. The Texas Instruments TUSB8041 has an autosuspend problem at high temperature. If there is not USB traffic, after a couple of ms, the device enters in autosuspend mode. In this condition the external clock stops working, to save energy. When the USB activity turns on, ther hub exits the autosuspend state, the clock starts running again and all works fine. At ambient temperature all works correctly, but at high temperature, when the USB activity turns on, the external clock doesn't restart and the hub disappears from the USB bus. Disabling the autosuspend mode for this hub solves the issue. Signed-off-by: Flavio Suligoi Cc: stable Acked-by: Alan Stern Link: https://lore.kernel.org/r/20221219124759.3207032-1-f.suligoi@asem.it Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index f2a3c0b5b535..5925b8eb9ee3 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -42,6 +42,9 @@ #define USB_PRODUCT_USB5534B 0x5534 #define USB_VENDOR_CYPRESS 0x04b4 #define USB_PRODUCT_CY7C65632 0x6570 +#define USB_VENDOR_TEXAS_INSTRUMENTS 0x0451 +#define USB_PRODUCT_TUSB8041_USB3 0x8140 +#define USB_PRODUCT_TUSB8041_USB2 0x8142 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 #define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02 @@ -5715,6 +5718,16 @@ static const struct usb_device_id hub_id_table[] = { .idVendor = USB_VENDOR_GENESYS_LOGIC, .bInterfaceClass = USB_CLASS_HUB, .driver_info = HUB_QUIRK_CHECK_PORT_AUTOSUSPEND}, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT, + .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS, + .idProduct = USB_PRODUCT_TUSB8041_USB2, + .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT, + .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS, + .idProduct = USB_PRODUCT_TUSB8041_USB3, + .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, { .match_flags = USB_DEVICE_ID_MATCH_DEV_CLASS, .bDeviceClass = USB_CLASS_HUB}, { .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS, From 2eed23765b7e54457a77c625c2a451ac57a904e0 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Tue, 3 Jan 2023 14:37:54 +0000 Subject: [PATCH 0988/4345] comedi: adv_pci1760: Fix PWM instruction handling commit 2efb6edd52dc50273f5e68ad863dd1b1fb2f2d1c upstream. (Actually, this is fixing the "Read the Current Status" command sent to the device's outgoing mailbox, but it is only currently used for the PWM instructions.) The PCI-1760 is operated mostly by sending commands to a set of Outgoing Mailbox registers, waiting for the command to complete, and reading the result from the Incoming Mailbox registers. One of these commands is the "Read the Current Status" command. The number of this command is 0x07 (see the User's Manual for the PCI-1760 at . The `PCI1760_CMD_GET_STATUS` macro defined in the driver should expand to this command number 0x07, but unfortunately it currently expands to 0x03. (Command number 0x03 is not defined in the User's Manual.) Correct the definition of the `PCI1760_CMD_GET_STATUS` macro to fix it. This is used by all the PWM subdevice related instructions handled by `pci1760_pwm_insn_config()` which are probably all broken. The effect of sending the undefined command number 0x03 is not known. Fixes: 14b93bb6bbf0 ("staging: comedi: adv_pci_dio: separate out PCI-1760 support") Cc: # v4.5+ Signed-off-by: Ian Abbott Link: https://lore.kernel.org/r/20230103143754.17564-1-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/drivers/adv_pci1760.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/comedi/drivers/adv_pci1760.c b/drivers/staging/comedi/drivers/adv_pci1760.c index 6de8ab97d346..d6934b6c436d 100644 --- a/drivers/staging/comedi/drivers/adv_pci1760.c +++ b/drivers/staging/comedi/drivers/adv_pci1760.c @@ -59,7 +59,7 @@ #define PCI1760_CMD_CLR_IMB2 0x00 /* Clears IMB2 */ #define PCI1760_CMD_SET_DO 0x01 /* Set output state */ #define PCI1760_CMD_GET_DO 0x02 /* Read output status */ -#define PCI1760_CMD_GET_STATUS 0x03 /* Read current status */ +#define PCI1760_CMD_GET_STATUS 0x07 /* Read current status */ #define PCI1760_CMD_GET_FW_VER 0x0e /* Read firmware version */ #define PCI1760_CMD_GET_HW_VER 0x0f /* Read hardware version */ #define PCI1760_CMD_SET_PWM_HI(x) (0x10 + (x) * 2) /* Set "hi" period */ From 79819909c2236a506f6ff38342398e34223a0e81 Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Tue, 9 Aug 2022 21:25:09 -0500 Subject: [PATCH 0989/4345] mmc: sunxi-mmc: Fix clock refcount imbalance during unbind commit 8509419758f2cc28dd05370385af0d91573b76b4 upstream. If the controller is suspended by runtime PM, the clock is already disabled, so do not try to disable it again during removal. Use pm_runtime_disable() to flush any pending runtime PM transitions. Fixes: 9a8e1e8cc2c0 ("mmc: sunxi: Add runtime_pm support") Signed-off-by: Samuel Holland Acked-by: Jernej Skrabec Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220810022509.43743-1-samuel@sholland.org Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/sunxi-mmc.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index fc62773602ec..9215069c6156 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1459,9 +1459,11 @@ static int sunxi_mmc_remove(struct platform_device *pdev) struct sunxi_mmc_host *host = mmc_priv(mmc); mmc_remove_host(mmc); - pm_runtime_force_suspend(&pdev->dev); - disable_irq(host->irq); - sunxi_mmc_disable(host); + pm_runtime_disable(&pdev->dev); + if (!pm_runtime_status_suspended(&pdev->dev)) { + disable_irq(host->irq); + sunxi_mmc_disable(host); + } dma_free_coherent(&pdev->dev, PAGE_SIZE, host->sg_cpu, host->sg_dma); mmc_free_host(mmc); From 6ee8feca915009f0abaa4f109144bc946d2a1532 Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Wed, 7 Dec 2022 19:23:15 +0800 Subject: [PATCH 0990/4345] mmc: sdhci-esdhc-imx: correct the tuning start tap and step setting commit 1e336aa0c0250ec84c6f16efac40c9f0138e367d upstream. Current code logic may be impacted by the setting of ROM/Bootloader, so unmask these bits first, then setting these bits accordingly. Fixes: 2b16cf326b70 ("mmc: sdhci-esdhc-imx: move tuning static configuration into hwinit function") Signed-off-by: Haibo Chen Acked-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221207112315.1812222-1-haibo.chen@nxp.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/sdhci-esdhc-imx.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 9e827bfe19ff..70f388f83485 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -103,6 +103,7 @@ #define ESDHC_TUNING_START_TAP_DEFAULT 0x1 #define ESDHC_TUNING_START_TAP_MASK 0x7f #define ESDHC_TUNING_CMD_CRC_CHECK_DISABLE (1 << 7) +#define ESDHC_TUNING_STEP_DEFAULT 0x1 #define ESDHC_TUNING_STEP_MASK 0x00070000 #define ESDHC_TUNING_STEP_SHIFT 16 @@ -1300,7 +1301,7 @@ static void sdhci_esdhc_imx_hwinit(struct sdhci_host *host) struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host); struct cqhci_host *cq_host = host->mmc->cqe_private; - int tmp; + u32 tmp; if (esdhc_is_usdhc(imx_data)) { /* @@ -1353,17 +1354,24 @@ static void sdhci_esdhc_imx_hwinit(struct sdhci_host *host) if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) { tmp = readl(host->ioaddr + ESDHC_TUNING_CTRL); - tmp |= ESDHC_STD_TUNING_EN | - ESDHC_TUNING_START_TAP_DEFAULT; - if (imx_data->boarddata.tuning_start_tap) { - tmp &= ~ESDHC_TUNING_START_TAP_MASK; + tmp |= ESDHC_STD_TUNING_EN; + + /* + * ROM code or bootloader may config the start tap + * and step, unmask them first. + */ + tmp &= ~(ESDHC_TUNING_START_TAP_MASK | ESDHC_TUNING_STEP_MASK); + if (imx_data->boarddata.tuning_start_tap) tmp |= imx_data->boarddata.tuning_start_tap; - } + else + tmp |= ESDHC_TUNING_START_TAP_DEFAULT; if (imx_data->boarddata.tuning_step) { - tmp &= ~ESDHC_TUNING_STEP_MASK; tmp |= imx_data->boarddata.tuning_step << ESDHC_TUNING_STEP_SHIFT; + } else { + tmp |= ESDHC_TUNING_STEP_DEFAULT + << ESDHC_TUNING_STEP_SHIFT; } /* Disable the CMD CRC check for tuning, if not, need to From 3bd43374857103ba3cac751d6d4afa8d83b5d92a Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 12 Jan 2023 16:31:08 +0000 Subject: [PATCH 0991/4345] btrfs: fix race between quota rescan and disable leading to NULL pointer deref commit b7adbf9ada3513d2092362c8eac5cddc5b651f5c upstream. If we have one task trying to start the quota rescan worker while another one is trying to disable quotas, we can end up hitting a race that results in the quota rescan worker doing a NULL pointer dereference. The steps for this are the following: 1) Quotas are enabled; 2) Task A calls the quota rescan ioctl and enters btrfs_qgroup_rescan(). It calls qgroup_rescan_init() which returns 0 (success) and then joins a transaction and commits it; 3) Task B calls the quota disable ioctl and enters btrfs_quota_disable(). It clears the bit BTRFS_FS_QUOTA_ENABLED from fs_info->flags and calls btrfs_qgroup_wait_for_completion(), which returns immediately since the rescan worker is not yet running. Then it starts a transaction and locks fs_info->qgroup_ioctl_lock; 4) Task A queues the rescan worker, by calling btrfs_queue_work(); 5) The rescan worker starts, and calls rescan_should_stop() at the start of its while loop, which results in 0 iterations of the loop, since the flag BTRFS_FS_QUOTA_ENABLED was cleared from fs_info->flags by task B at step 3); 6) Task B sets fs_info->quota_root to NULL; 7) The rescan worker tries to start a transaction and uses fs_info->quota_root as the root argument for btrfs_start_transaction(). This results in a NULL pointer dereference down the call chain of btrfs_start_transaction(). The stack trace is something like the one reported in Link tag below: general protection fault, probably for non-canonical address 0xdffffc0000000041: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000208-0x000000000000020f] CPU: 1 PID: 34 Comm: kworker/u4:2 Not tainted 6.1.0-syzkaller-13872-gb6bb9676f216 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Workqueue: btrfs-qgroup-rescan btrfs_work_helper RIP: 0010:start_transaction+0x48/0x10f0 fs/btrfs/transaction.c:564 Code: 48 89 fb 48 (...) RSP: 0018:ffffc90000ab7ab0 EFLAGS: 00010206 RAX: 0000000000000041 RBX: 0000000000000208 RCX: ffff88801779ba80 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: dffffc0000000000 R08: 0000000000000001 R09: fffff52000156f5d R10: fffff52000156f5d R11: 1ffff92000156f5c R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000000001 R15: 0000000000000003 FS: 0000000000000000(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2bea75b718 CR3: 000000001d0cc000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: btrfs_qgroup_rescan_worker+0x3bb/0x6a0 fs/btrfs/qgroup.c:3402 btrfs_work_helper+0x312/0x850 fs/btrfs/async-thread.c:280 process_one_work+0x877/0xdb0 kernel/workqueue.c:2289 worker_thread+0xb14/0x1330 kernel/workqueue.c:2436 kthread+0x266/0x300 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 Modules linked in: So fix this by having the rescan worker function not attempt to start a transaction if it didn't do any rescan work. Reported-by: syzbot+96977faa68092ad382c4@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/000000000000e5454b05f065a803@google.com/ Fixes: e804861bd4e6 ("btrfs: fix deadlock between quota disable and qgroup rescan worker") CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/qgroup.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 74cbbb5d8897..9fe6a01ea8b8 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3296,6 +3296,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) int err = -ENOMEM; int ret = 0; bool stopped = false; + bool did_leaf_rescans = false; path = btrfs_alloc_path(); if (!path) @@ -3316,6 +3317,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) } err = qgroup_rescan_leaf(trans, path); + did_leaf_rescans = true; if (err > 0) btrfs_commit_transaction(trans); @@ -3336,16 +3338,23 @@ out: mutex_unlock(&fs_info->qgroup_rescan_lock); /* - * only update status, since the previous part has already updated the - * qgroup info. + * Only update status, since the previous part has already updated the + * qgroup info, and only if we did any actual work. This also prevents + * race with a concurrent quota disable, which has already set + * fs_info->quota_root to NULL and cleared BTRFS_FS_QUOTA_ENABLED at + * btrfs_quota_disable(). */ - trans = btrfs_start_transaction(fs_info->quota_root, 1); - if (IS_ERR(trans)) { - err = PTR_ERR(trans); + if (did_leaf_rescans) { + trans = btrfs_start_transaction(fs_info->quota_root, 1); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + trans = NULL; + btrfs_err(fs_info, + "fail to start transaction for status update: %d", + err); + } + } else { trans = NULL; - btrfs_err(fs_info, - "fail to start transaction for status update: %d", - err); } mutex_lock(&fs_info->qgroup_rescan_lock); From 531268a875dca165a6c9de7e949ab437c7c93069 Mon Sep 17 00:00:00 2001 From: Enzo Matsumiya Date: Wed, 18 Jan 2023 14:06:57 -0300 Subject: [PATCH 0992/4345] cifs: do not include page data when checking signature commit 30b2b2196d6e4cc24cbec633535a2404f258ce69 upstream. On async reads, page data is allocated before sending. When the response is received but it has no data to fill (e.g. STATUS_END_OF_FILE), __calc_signature() will still include the pages in its computation, leading to an invalid signature check. This patch fixes this by not setting the async read smb_rqst page data (zeroed by default) if its got_bytes is 0. This can be reproduced/verified with xfstests generic/465. Cc: Signed-off-by: Enzo Matsumiya Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/smb2pdu.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 0c4a2474e75b..9a80047bc9b7 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3925,12 +3925,15 @@ smb2_readv_callback(struct mid_q_entry *mid) (struct smb2_sync_hdr *)rdata->iov[0].iov_base; struct cifs_credits credits = { .value = 0, .instance = 0 }; struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], - .rq_nvec = 1, - .rq_pages = rdata->pages, - .rq_offset = rdata->page_offset, - .rq_npages = rdata->nr_pages, - .rq_pagesz = rdata->pagesz, - .rq_tailsz = rdata->tailsz }; + .rq_nvec = 1, }; + + if (rdata->got_bytes) { + rqst.rq_pages = rdata->pages; + rqst.rq_offset = rdata->page_offset; + rqst.rq_npages = rdata->nr_pages; + rqst.rq_pagesz = rdata->pagesz; + rqst.rq_tailsz = rdata->tailsz; + } WARN_ONCE(rdata->server != mid->server, "rdata server %p != mid server %p", From c4ab24e3334bb8481a90538cdbfbbc95dbfee2ce Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 20 May 2022 13:35:19 +0300 Subject: [PATCH 0993/4345] thunderbolt: Use correct function to calculate maximum USB3 link rate commit e8ff07fb33026c5c1bb5b81293496faba5d68059 upstream. We need to take minimum of both sides of the USB3 link into consideration, not just the downstream port. Fix this by calling tb_usb3_max_link_rate() instead. Fixes: 0bd680cd900c ("thunderbolt: Add USB3 bandwidth management") Cc: stable@vger.kernel.org Acked-by: Yehezkel Bernat Signed-off-by: Mika Westerberg Signed-off-by: Greg Kroah-Hartman --- drivers/thunderbolt/tunnel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 829b6ccdd5d4..011ab5fed85b 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -956,7 +956,7 @@ static void tb_usb3_reclaim_available_bandwidth(struct tb_tunnel *tunnel, return; } else if (!ret) { /* Use maximum link rate if the link valid is not set */ - ret = usb4_usb3_port_max_link_rate(tunnel->src_port); + ret = tb_usb3_max_link_rate(tunnel->dst_port, tunnel->src_port); if (ret < 0) { tb_tunnel_warn(tunnel, "failed to read maximum link rate\n"); return; From 894681682dbefdad917b88f86cde1069140a047a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 21 Dec 2022 17:40:22 +0100 Subject: [PATCH 0994/4345] tty: serial: qcom-geni-serial: fix slab-out-of-bounds on RX FIFO buffer commit b8caf69a6946e18ffebad49847e258f5b6d52ac2 upstream. Driver's probe allocates memory for RX FIFO (port->rx_fifo) based on default RX FIFO depth, e.g. 16. Later during serial startup the qcom_geni_serial_port_setup() updates the RX FIFO depth (port->rx_fifo_depth) to match real device capabilities, e.g. to 32. The RX UART handle code will read "port->rx_fifo_depth" number of words into "port->rx_fifo" buffer, thus exceeding the bounds. This can be observed in certain configurations with Qualcomm Bluetooth HCI UART device and KASAN: Bluetooth: hci0: QCA Product ID :0x00000010 Bluetooth: hci0: QCA SOC Version :0x400a0200 Bluetooth: hci0: QCA ROM Version :0x00000200 Bluetooth: hci0: QCA Patch Version:0x00000d2b Bluetooth: hci0: QCA controller version 0x02000200 Bluetooth: hci0: QCA Downloading qca/htbtfw20.tlv bluetooth hci0: Direct firmware load for qca/htbtfw20.tlv failed with error -2 Bluetooth: hci0: QCA Failed to request file: qca/htbtfw20.tlv (-2) Bluetooth: hci0: QCA Failed to download patch (-2) ================================================================== BUG: KASAN: slab-out-of-bounds in handle_rx_uart+0xa8/0x18c Write of size 4 at addr ffff279347d578c0 by task swapper/0/0 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.1.0-rt5-00350-gb2450b7e00be-dirty #26 Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT) Call trace: dump_backtrace.part.0+0xe0/0xf0 show_stack+0x18/0x40 dump_stack_lvl+0x8c/0xb8 print_report+0x188/0x488 kasan_report+0xb4/0x100 __asan_store4+0x80/0xa4 handle_rx_uart+0xa8/0x18c qcom_geni_serial_handle_rx+0x84/0x9c qcom_geni_serial_isr+0x24c/0x760 __handle_irq_event_percpu+0x108/0x500 handle_irq_event+0x6c/0x110 handle_fasteoi_irq+0x138/0x2cc generic_handle_domain_irq+0x48/0x64 If the RX FIFO depth changes after probe, be sure to resize the buffer. Fixes: f9d690b6ece7 ("tty: serial: qcom_geni_serial: Allocate port->rx_fifo buffer in probe") Cc: Signed-off-by: Krzysztof Kozlowski Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/20221221164022.1087814-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/qcom_geni_serial.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 0d85b55ea823..f50ffc8076d8 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -866,9 +866,10 @@ out_unlock: return IRQ_HANDLED; } -static void get_tx_fifo_size(struct qcom_geni_serial_port *port) +static int setup_fifos(struct qcom_geni_serial_port *port) { struct uart_port *uport; + u32 old_rx_fifo_depth = port->rx_fifo_depth; uport = &port->uport; port->tx_fifo_depth = geni_se_get_tx_fifo_depth(&port->se); @@ -876,6 +877,16 @@ static void get_tx_fifo_size(struct qcom_geni_serial_port *port) port->rx_fifo_depth = geni_se_get_rx_fifo_depth(&port->se); uport->fifosize = (port->tx_fifo_depth * port->tx_fifo_width) / BITS_PER_BYTE; + + if (port->rx_fifo && (old_rx_fifo_depth != port->rx_fifo_depth) && port->rx_fifo_depth) { + port->rx_fifo = devm_krealloc(uport->dev, port->rx_fifo, + port->rx_fifo_depth * sizeof(u32), + GFP_KERNEL); + if (!port->rx_fifo) + return -ENOMEM; + } + + return 0; } @@ -890,6 +901,7 @@ static int qcom_geni_serial_port_setup(struct uart_port *uport) u32 rxstale = DEFAULT_BITS_PER_CHAR * STALE_TIMEOUT; u32 proto; u32 pin_swap; + int ret; proto = geni_se_read_proto(&port->se); if (proto != GENI_SE_UART) { @@ -899,7 +911,9 @@ static int qcom_geni_serial_port_setup(struct uart_port *uport) qcom_geni_serial_stop_rx(uport); - get_tx_fifo_size(port); + ret = setup_fifos(port); + if (ret) + return ret; writel(rxstale, uport->membase + SE_UART_RX_STALE_CNT); From 856e4b5e53f21edbd15d275dde62228dd94fb2b4 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 23 Dec 2022 09:59:09 -0500 Subject: [PATCH 0995/4345] USB: gadgetfs: Fix race between mounting and unmounting commit d18dcfe9860e842f394e37ba01ca9440ab2178f4 upstream. The syzbot fuzzer and Gerald Lee have identified a use-after-free bug in the gadgetfs driver, involving processes concurrently mounting and unmounting the gadgetfs filesystem. In particular, gadgetfs_fill_super() can race with gadgetfs_kill_sb(), causing the latter to deallocate the_device while the former is using it. The output from KASAN says, in part: BUG: KASAN: use-after-free in instrument_atomic_read_write include/linux/instrumented.h:102 [inline] BUG: KASAN: use-after-free in atomic_fetch_sub_release include/linux/atomic/atomic-instrumented.h:176 [inline] BUG: KASAN: use-after-free in __refcount_sub_and_test include/linux/refcount.h:272 [inline] BUG: KASAN: use-after-free in __refcount_dec_and_test include/linux/refcount.h:315 [inline] BUG: KASAN: use-after-free in refcount_dec_and_test include/linux/refcount.h:333 [inline] BUG: KASAN: use-after-free in put_dev drivers/usb/gadget/legacy/inode.c:159 [inline] BUG: KASAN: use-after-free in gadgetfs_kill_sb+0x33/0x100 drivers/usb/gadget/legacy/inode.c:2086 Write of size 4 at addr ffff8880276d7840 by task syz-executor126/18689 CPU: 0 PID: 18689 Comm: syz-executor126 Not tainted 6.1.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: ... atomic_fetch_sub_release include/linux/atomic/atomic-instrumented.h:176 [inline] __refcount_sub_and_test include/linux/refcount.h:272 [inline] __refcount_dec_and_test include/linux/refcount.h:315 [inline] refcount_dec_and_test include/linux/refcount.h:333 [inline] put_dev drivers/usb/gadget/legacy/inode.c:159 [inline] gadgetfs_kill_sb+0x33/0x100 drivers/usb/gadget/legacy/inode.c:2086 deactivate_locked_super+0xa7/0xf0 fs/super.c:332 vfs_get_super fs/super.c:1190 [inline] get_tree_single+0xd0/0x160 fs/super.c:1207 vfs_get_tree+0x88/0x270 fs/super.c:1531 vfs_fsconfig_locked fs/fsopen.c:232 [inline] The simplest solution is to ensure that gadgetfs_fill_super() and gadgetfs_kill_sb() are serialized by making them both acquire a new mutex. Signed-off-by: Alan Stern Reported-and-tested-by: syzbot+33d7ad66d65044b93f16@syzkaller.appspotmail.com Reported-and-tested-by: Gerald Lee Link: https://lore.kernel.org/linux-usb/CAO3qeMVzXDP-JU6v1u5Ags6Q-bb35kg3=C6d04DjzA9ffa5x1g@mail.gmail.com/ Fixes: e5d82a7360d1 ("vfs: Convert gadgetfs to use the new mount API") CC: Link: https://lore.kernel.org/r/Y6XCPXBpn3tmjdCC@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/legacy/inode.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index cd097474b6c3..cbe801640916 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -229,6 +229,7 @@ static void put_ep (struct ep_data *data) */ static const char *CHIP; +static DEFINE_MUTEX(sb_mutex); /* Serialize superblock operations */ /*----------------------------------------------------------------------*/ @@ -2012,13 +2013,20 @@ gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct dev_data *dev; + int rc; - if (the_device) - return -ESRCH; + mutex_lock(&sb_mutex); + + if (the_device) { + rc = -ESRCH; + goto Done; + } CHIP = usb_get_gadget_udc_name(); - if (!CHIP) - return -ENODEV; + if (!CHIP) { + rc = -ENODEV; + goto Done; + } /* superblock */ sb->s_blocksize = PAGE_SIZE; @@ -2055,13 +2063,17 @@ gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc) * from binding to a controller. */ the_device = dev; - return 0; + rc = 0; + goto Done; -Enomem: + Enomem: kfree(CHIP); CHIP = NULL; + rc = -ENOMEM; - return -ENOMEM; + Done: + mutex_unlock(&sb_mutex); + return rc; } /* "mount -t gadgetfs path /dev/gadget" ends up here */ @@ -2083,6 +2095,7 @@ static int gadgetfs_init_fs_context(struct fs_context *fc) static void gadgetfs_kill_sb (struct super_block *sb) { + mutex_lock(&sb_mutex); kill_litter_super (sb); if (the_device) { put_dev (the_device); @@ -2090,6 +2103,7 @@ gadgetfs_kill_sb (struct super_block *sb) } kfree(CHIP); CHIP = NULL; + mutex_unlock(&sb_mutex); } /*----------------------------------------------------------------------*/ From 3dc896db027bf0dbe41c290915be3e3f5ad25535 Mon Sep 17 00:00:00 2001 From: Michael Adler Date: Tue, 3 Jan 2023 14:48:50 +0100 Subject: [PATCH 0996/4345] USB: serial: cp210x: add SCALANCE LPE-9000 device id commit 3f9e76e31704a325170e5aec2243c8d084d74854 upstream. Add the USB serial console device ID for Siemens SCALANCE LPE-9000 which have a USB port for their serial console. Signed-off-by: Michael Adler Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 8a4a0d4dbc13..9ee0fa775612 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -64,6 +64,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */ { USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */ { USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */ + { USB_DEVICE(0x0908, 0x0070) }, /* Siemens SCALANCE LPE-9000 USB Serial Console */ { USB_DEVICE(0x0908, 0x01FF) }, /* Siemens RUGGEDCOM USB Serial Console */ { USB_DEVICE(0x0988, 0x0578) }, /* Teraoka AD2000 */ { USB_DEVICE(0x0B00, 0x3070) }, /* Ingenico 3070 */ From 9c58f1e9e693ccd834034ad55ae337000f78d431 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Fri, 20 Jan 2023 13:27:14 +0100 Subject: [PATCH 0997/4345] usb: host: ehci-fsl: Fix module alias commit 5d3d01ae15d2f37ed0325c99ab47ef0ae5d05f3c upstream. Commit ca07e1c1e4a6 ("drivers:usb:fsl:Make fsl ehci drv an independent driver module") changed DRV_NAME which was used for MODULE_ALIAS as well. Starting from this the module alias didn't match the platform device name created in fsl-mph-dr-of.c Change DRV_NAME to match the driver name for host mode in fsl-mph-dr-of. This is needed for module autoloading on ls1021a. Fixes: ca07e1c1e4a6 ("drivers:usb:fsl:Make fsl ehci drv an independent driver module") Cc: stable Signed-off-by: Alexander Stein Link: https://lore.kernel.org/r/20230120122714.3848784-1-alexander.stein@ew.tq-group.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/ehci-fsl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c index 1e8b59ab2272..c78f71a5faac 100644 --- a/drivers/usb/host/ehci-fsl.c +++ b/drivers/usb/host/ehci-fsl.c @@ -29,7 +29,7 @@ #include "ehci-fsl.h" #define DRIVER_DESC "Freescale EHCI Host controller driver" -#define DRV_NAME "ehci-fsl" +#define DRV_NAME "fsl-ehci" static struct hc_driver __read_mostly fsl_ehci_hc_driver; From d26f38d16fcb065b97ab97e6f099414529d6e19e Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 11 Jan 2023 02:05:41 +0000 Subject: [PATCH 0998/4345] usb: typec: altmodes/displayport: Add pin assignment helper commit 582836e3cfab4faafbdc93bbec96fce036a08ee1 upstream. The code to extract a peripheral's currently supported Pin Assignments is repeated in a couple of locations. Factor it out into a separate function. This will also make it easier to add fixes (we only need to update 1 location instead of 2). Fixes: c1e5c2f0cb8a ("usb: typec: altmodes/displayport: correct pin assignment for UFP receptacles") Cc: stable@vger.kernel.org Cc: Heikki Krogerus Signed-off-by: Prashant Malani Reviewed-by: Benson Leung Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230111020546.3384569-1-pmalani@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 5e293ccf0e90..93858dfd3d7d 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -409,6 +409,18 @@ static const char * const pin_assignments[] = { [DP_PIN_ASSIGN_F] = "F", }; +/* + * Helper function to extract a peripheral's currently supported + * Pin Assignments from its DisplayPort alternate mode state. + */ +static u8 get_current_pin_assignments(struct dp_altmode *dp) +{ + if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D) + return DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo); + else + return DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo); +} + static ssize_t pin_assignment_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) @@ -435,10 +447,7 @@ pin_assignment_store(struct device *dev, struct device_attribute *attr, goto out_unlock; } - if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D) - assignments = DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo); - else - assignments = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo); + assignments = get_current_pin_assignments(dp); if (!(DP_CONF_GET_PIN_ASSIGN(conf) & assignments)) { ret = -EINVAL; @@ -475,10 +484,7 @@ static ssize_t pin_assignment_show(struct device *dev, cur = get_count_order(DP_CONF_GET_PIN_ASSIGN(dp->data.conf)); - if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D) - assignments = DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo); - else - assignments = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo); + assignments = get_current_pin_assignments(dp); for (i = 0; assignments; assignments >>= 1, i++) { if (assignments & 1) { From 6107a8f15c0f1908c550729466f2b405d7eefc24 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 11 Jan 2023 02:05:42 +0000 Subject: [PATCH 0999/4345] usb: typec: altmodes/displayport: Fix pin assignment calculation commit 9682b41e52cc9f42f5c33caf410464392adaef04 upstream. Commit c1e5c2f0cb8a ("usb: typec: altmodes/displayport: correct pin assignment for UFP receptacles") fixed the pin assignment calculation to take into account whether the peripheral was a plug or a receptacle. But the "pin_assignments" sysfs logic was not updated. Address this by using the macros introduced in the aforementioned commit in the sysfs logic too. Fixes: c1e5c2f0cb8a ("usb: typec: altmodes/displayport: correct pin assignment for UFP receptacles") Cc: stable@vger.kernel.org Cc: Heikki Krogerus Signed-off-by: Prashant Malani Reviewed-by: Benson Leung Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230111020546.3384569-2-pmalani@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 93858dfd3d7d..eed719cf5552 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -416,9 +416,9 @@ static const char * const pin_assignments[] = { static u8 get_current_pin_assignments(struct dp_altmode *dp) { if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D) - return DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo); + return DP_CAP_PIN_ASSIGN_DFP_D(dp->alt->vdo); else - return DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo); + return DP_CAP_PIN_ASSIGN_UFP_D(dp->alt->vdo); } static ssize_t From 06600ae7e06903535a35256fd219fdf0fb85f933 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Fri, 16 Dec 2022 16:05:28 +0000 Subject: [PATCH 1000/4345] usb: gadget: g_webcam: Send color matching descriptor per frame commit e95765e97d9cb93258a4840440d410fa6ff7e819 upstream. Currently the color matching descriptor is only sent across the wire a single time, following the descriptors for each format and frame. According to the UVC 1.5 Specification 3.9.2.6 ("Color Matching Descriptors"): "Only one instance is allowed for a given format and if present, the Color Matching descriptor shall be placed following the Video and Still Image Frame descriptors for that format". Add another reference to the color matching descriptor after the yuyv frames so that it's correctly transmitted for that format too. Fixes: a9914127e834 ("USB gadget: Webcam device") Cc: stable Signed-off-by: Daniel Scally Reviewed-by: Laurent Pinchart Reviewed-by: Kieran Bingham Link: https://lore.kernel.org/r/20221216160528.479094-1-dan.scally@ideasonboard.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/legacy/webcam.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/legacy/webcam.c b/drivers/usb/gadget/legacy/webcam.c index 2c9eab2b863d..ff970a943347 100644 --- a/drivers/usb/gadget/legacy/webcam.c +++ b/drivers/usb/gadget/legacy/webcam.c @@ -293,6 +293,7 @@ static const struct uvc_descriptor_header * const uvc_fs_streaming_cls[] = { (const struct uvc_descriptor_header *) &uvc_format_yuv, (const struct uvc_descriptor_header *) &uvc_frame_yuv_360p, (const struct uvc_descriptor_header *) &uvc_frame_yuv_720p, + (const struct uvc_descriptor_header *) &uvc_color_matching, (const struct uvc_descriptor_header *) &uvc_format_mjpg, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p, @@ -305,6 +306,7 @@ static const struct uvc_descriptor_header * const uvc_hs_streaming_cls[] = { (const struct uvc_descriptor_header *) &uvc_format_yuv, (const struct uvc_descriptor_header *) &uvc_frame_yuv_360p, (const struct uvc_descriptor_header *) &uvc_frame_yuv_720p, + (const struct uvc_descriptor_header *) &uvc_color_matching, (const struct uvc_descriptor_header *) &uvc_format_mjpg, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p, @@ -317,6 +319,7 @@ static const struct uvc_descriptor_header * const uvc_ss_streaming_cls[] = { (const struct uvc_descriptor_header *) &uvc_format_yuv, (const struct uvc_descriptor_header *) &uvc_frame_yuv_360p, (const struct uvc_descriptor_header *) &uvc_frame_yuv_720p, + (const struct uvc_descriptor_header *) &uvc_color_matching, (const struct uvc_descriptor_header *) &uvc_format_mjpg, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p, From e92c70059178da751e5af7de02384b7dfadb5ec7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Tue, 17 Jan 2023 05:18:39 -0800 Subject: [PATCH 1001/4345] usb: gadget: f_ncm: fix potential NULL ptr deref in ncm_bitrate() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit c6ec929595c7443250b2a4faea988c62019d5cd2 upstream. In Google internal bug 265639009 we've received an (as yet) unreproducible crash report from an aarch64 GKI 5.10.149-android13 running device. AFAICT the source code is at: https://android.googlesource.com/kernel/common/+/refs/tags/ASB-2022-12-05_13-5.10 The call stack is: ncm_close() -> ncm_notify() -> ncm_do_notify() with the crash at: ncm_do_notify+0x98/0x270 Code: 79000d0b b9000a6c f940012a f9400269 (b9405d4b) Which I believe disassembles to (I don't know ARM assembly, but it looks sane enough to me...): // halfword (16-bit) store presumably to event->wLength (at offset 6 of struct usb_cdc_notification) 0B 0D 00 79 strh w11, [x8, #6] // word (32-bit) store presumably to req->Length (at offset 8 of struct usb_request) 6C 0A 00 B9 str w12, [x19, #8] // x10 (NULL) was read here from offset 0 of valid pointer x9 // IMHO we're reading 'cdev->gadget' and getting NULL // gadget is indeed at offset 0 of struct usb_composite_dev 2A 01 40 F9 ldr x10, [x9] // loading req->buf pointer, which is at offset 0 of struct usb_request 69 02 40 F9 ldr x9, [x19] // x10 is null, crash, appears to be attempt to read cdev->gadget->max_speed 4B 5D 40 B9 ldr w11, [x10, #0x5c] which seems to line up with ncm_do_notify() case NCM_NOTIFY_SPEED code fragment: event->wLength = cpu_to_le16(8); req->length = NCM_STATUS_BYTECOUNT; /* SPEED_CHANGE data is up/down speeds in bits/sec */ data = req->buf + sizeof *event; data[0] = cpu_to_le32(ncm_bitrate(cdev->gadget)); My analysis of registers and NULL ptr deref crash offset (Unable to handle kernel NULL pointer dereference at virtual address 000000000000005c) heavily suggests that the crash is due to 'cdev->gadget' being NULL when executing: data[0] = cpu_to_le32(ncm_bitrate(cdev->gadget)); which calls: ncm_bitrate(NULL) which then calls: gadget_is_superspeed(NULL) which reads ((struct usb_gadget *)NULL)->max_speed and hits a panic. AFAICT, if I'm counting right, the offset of max_speed is indeed 0x5C. (remember there's a GKI KABI reservation of 16 bytes in struct work_struct) It's not at all clear to me how this is all supposed to work... but returning 0 seems much better than panic-ing... Cc: Felipe Balbi Cc: Lorenzo Colitti Cc: Carlos Llamas Cc: stable@vger.kernel.org Signed-off-by: Maciej Żenczykowski Cc: stable Link: https://lore.kernel.org/r/20230117131839.1138208-1-maze@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_ncm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 855127249f24..f56147489835 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -85,7 +85,9 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f) /* peak (theoretical) bulk transfer rate in bits-per-second */ static inline unsigned ncm_bitrate(struct usb_gadget *g) { - if (gadget_is_superspeed(g) && g->speed >= USB_SPEED_SUPER_PLUS) + if (!g) + return 0; + else if (gadget_is_superspeed(g) && g->speed >= USB_SPEED_SUPER_PLUS) return 4250000000U; else if (gadget_is_superspeed(g) && g->speed == USB_SPEED_SUPER) return 3750000000U; From a9f2658a0192458cf3446ffa6bdbbec67aaf9952 Mon Sep 17 00:00:00 2001 From: Juhyung Park Date: Tue, 17 Jan 2023 17:51:54 +0900 Subject: [PATCH 1002/4345] usb-storage: apply IGNORE_UAS only for HIKSEMI MD202 on RTL9210 commit dbd24ec17b85b45f4e823d1aa5607721920f2b05 upstream. The commit e00b488e813f ("usb-storage: Add Hiksemi USB3-FW to IGNORE_UAS") blacklists UAS for all of RTL9210 enclosures. The RTL9210 controller was advertised with UAS since its release back in 2019 and was shipped with a lot of enclosure products with different firmware combinations. Blacklist UAS only for HIKSEMI MD202. This should hopefully be replaced with more robust method than just comparing strings. But with limited information [1] provided thus far (dmesg when the device is plugged in, which includes manufacturer and product, but no lsusb -v to compare against), this is the best we can do for now. [1] https://lore.kernel.org/all/20230109115550.71688-1-qkrwngud825@gmail.com Fixes: e00b488e813f ("usb-storage: Add Hiksemi USB3-FW to IGNORE_UAS") Cc: Alan Stern Cc: Hongling Zeng Cc: stable@vger.kernel.org Signed-off-by: Juhyung Park Acked-by: Oliver Neukum Link: https://lore.kernel.org/r/20230117085154.123301-1-qkrwngud825@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/uas-detect.h | 13 +++++++++++++ drivers/usb/storage/unusual_uas.h | 7 ------- 2 files changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h index 3f720faa6f97..d73282c0ec50 100644 --- a/drivers/usb/storage/uas-detect.h +++ b/drivers/usb/storage/uas-detect.h @@ -116,6 +116,19 @@ static int uas_use_uas_driver(struct usb_interface *intf, if (le16_to_cpu(udev->descriptor.idVendor) == 0x0bc2) flags |= US_FL_NO_ATA_1X; + /* + * RTL9210-based enclosure from HIKSEMI, MD202 reportedly have issues + * with UAS. This isn't distinguishable with just idVendor and + * idProduct, use manufacturer and product too. + * + * Reported-by: Hongling Zeng + */ + if (le16_to_cpu(udev->descriptor.idVendor) == 0x0bda && + le16_to_cpu(udev->descriptor.idProduct) == 0x9210 && + (udev->manufacturer && !strcmp(udev->manufacturer, "HIKSEMI")) && + (udev->product && !strcmp(udev->product, "MD202"))) + flags |= US_FL_IGNORE_UAS; + usb_stor_adjust_quirks(udev, &flags); if (flags & US_FL_IGNORE_UAS) { diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 251778d14e2d..c7b763d6d102 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -83,13 +83,6 @@ UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_REPORT_LUNS), -/* Reported-by: Hongling Zeng */ -UNUSUAL_DEV(0x0bda, 0x9210, 0x0000, 0x9999, - "Hiksemi", - "External HDD", - USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_IGNORE_UAS), - /* Reported-by: Benjamin Tissoires */ UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999, "Initio Corporation", From 31132df12a933fba09c0f6afd7edbc49902ae689 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 16 Jan 2023 21:17:39 +0100 Subject: [PATCH 1003/4345] dt-bindings: phy: g12a-usb2-phy: fix compatible string documentation commit c63835bf1c750c9b3aec1d5c23d811d6375fc23d upstream. The compatible strings in the driver don't have the meson prefix. Fix this in the documentation and rename the file accordingly. Fixes: da86d286cce8 ("dt-bindings: phy: meson-g12a-usb2-phy: convert to yaml") Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Reviewed-by: Martin Blumenstingl Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/8d960029-e94d-224b-911f-03e5deb47ebc@gmail.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- ...eson-g12a-usb2-phy.yaml => amlogic,g12a-usb2-phy.yaml} | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) rename Documentation/devicetree/bindings/phy/{amlogic,meson-g12a-usb2-phy.yaml => amlogic,g12a-usb2-phy.yaml} (85%) diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml similarity index 85% rename from Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml rename to Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml index 399ebde45409..ff86c87309a4 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml @@ -2,7 +2,7 @@ # Copyright 2019 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,meson-g12a-usb2-phy.yaml#" +$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb2-phy.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Amlogic G12A USB2 PHY @@ -13,8 +13,8 @@ maintainers: properties: compatible: enum: - - amlogic,meson-g12a-usb2-phy - - amlogic,meson-a1-usb2-phy + - amlogic,g12a-usb2-phy + - amlogic,a1-usb2-phy reg: maxItems: 1 @@ -68,7 +68,7 @@ additionalProperties: false examples: - | phy@36000 { - compatible = "amlogic,meson-g12a-usb2-phy"; + compatible = "amlogic,g12a-usb2-phy"; reg = <0x36000 0x2000>; clocks = <&xtal>; clock-names = "xtal"; From e924f79e67d7863a0f6a385e6120c2bf0fe18c25 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 16 Jan 2023 21:19:03 +0100 Subject: [PATCH 1004/4345] dt-bindings: phy: g12a-usb3-pcie-phy: fix compatible string documentation commit e181119046a0ec16126b682163040e8e33f310c1 upstream. The compatible string in the driver doesn't have the meson prefix. Fix this in the documentation and rename the file accordingly. Fixes: 87a55485f2fc ("dt-bindings: phy: meson-g12a-usb3-pcie-phy: convert to yaml") Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Reviewed-by: Martin Blumenstingl Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/0a82be92-ce85-da34-9d6f-4b33034473e5@gmail.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- ...a-usb3-pcie-phy.yaml => amlogic,g12a-usb3-pcie-phy.yaml} | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) rename Documentation/devicetree/bindings/phy/{amlogic,meson-g12a-usb3-pcie-phy.yaml => amlogic,g12a-usb3-pcie-phy.yaml} (82%) diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml similarity index 82% rename from Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml rename to Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml index 453c083cf44c..84738644e398 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml @@ -2,7 +2,7 @@ # Copyright 2019 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml#" +$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb3-pcie-phy.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Amlogic G12A USB3 + PCIE Combo PHY @@ -13,7 +13,7 @@ maintainers: properties: compatible: enum: - - amlogic,meson-g12a-usb3-pcie-phy + - amlogic,g12a-usb3-pcie-phy reg: maxItems: 1 @@ -49,7 +49,7 @@ additionalProperties: false examples: - | phy@46000 { - compatible = "amlogic,meson-g12a-usb3-pcie-phy"; + compatible = "amlogic,g12a-usb3-pcie-phy"; reg = <0x46000 0x2000>; clocks = <&ref_clk>; clock-names = "ref_clk"; From c9da2cb968ea9604ab0e742b523b997fb05b4994 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Tue, 3 Jan 2023 11:34:35 +0200 Subject: [PATCH 1005/4345] serial: pch_uart: Pass correct sg to dma_unmap_sg() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit e8914b52e5b024e4af3d810a935fe0805eee8a36 upstream. A local variable sg is used to store scatterlist pointer in pch_dma_tx_complete(). The for loop doing Tx byte accounting before dma_unmap_sg() alters sg in its increment statement. Therefore, the pointer passed into dma_unmap_sg() won't match to the one given to dma_map_sg(). To fix the problem, use priv->sg_tx_p directly in dma_unmap_sg() instead of the local variable. Fixes: da3564ee027e ("pch_uart: add multi-scatter processing") Cc: stable@vger.kernel.org Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230103093435.4396-1-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/pch_uart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index fa2061f1cf3d..cb68a1028090 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -769,7 +769,7 @@ static void pch_dma_tx_complete(void *arg) } xmit->tail &= UART_XMIT_SIZE - 1; async_tx_ack(priv->desc_tx); - dma_unmap_sg(port->dev, sg, priv->orig_nent, DMA_TO_DEVICE); + dma_unmap_sg(port->dev, priv->sg_tx_p, priv->orig_nent, DMA_TO_DEVICE); priv->tx_dma_use = 0; priv->nent = 0; priv->orig_nent = 0; From 5a7a0407959211994b7361f62956a52e656cc86d Mon Sep 17 00:00:00 2001 From: Mohan Kumar Date: Mon, 2 Jan 2023 12:18:44 +0530 Subject: [PATCH 1006/4345] dmaengine: tegra210-adma: fix global intr clear commit 9c7e355ccbb33d239360c876dbe49ad5ade65b47 upstream. The current global interrupt clear programming register offset was not correct. Fix the programming with right offset Fixes: ded1f3db4cd6 ("dmaengine: tegra210-adma: prepare for supporting newer Tegra chips") Cc: stable@vger.kernel.org Signed-off-by: Mohan Kumar Link: https://lore.kernel.org/r/20230102064844.31306-1-mkumard@nvidia.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/dma/tegra210-adma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index c5fa2ef74abc..d84010c2e4bf 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -224,7 +224,7 @@ static int tegra_adma_init(struct tegra_adma *tdma) int ret; /* Clear any interrupts */ - tdma_write(tdma, tdma->cdata->global_int_clear, 0x1); + tdma_write(tdma, tdma->cdata->ch_base_offset + tdma->cdata->global_int_clear, 0x1); /* Assert soft reset */ tdma_write(tdma, ADMA_GLOBAL_SOFT_RESET, 0x1); From a75e80d11826ad02ec153cff97d64033fd99623d Mon Sep 17 00:00:00 2001 From: Tobias Schramm Date: Mon, 9 Jan 2023 08:29:40 +0100 Subject: [PATCH 1007/4345] serial: atmel: fix incorrect baudrate setup commit 5bfdd3c654bd879bff50c2e85e42f85ae698b42f upstream. Commit ba47f97a18f2 ("serial: core: remove baud_rates when serial console setup") changed uart_set_options to select the correct baudrate configuration based on the absolute error between requested baudrate and available standard baudrate settings. Prior to that commit the baudrate was selected based on which predefined standard baudrate did not exceed the requested baudrate. This change of selection logic was never reflected in the atmel serial driver. Thus the comment left in the atmel serial driver is no longer accurate. Additionally the manual rounding up described in that comment and applied via (quot - 1) requests an incorrect baudrate. Since uart_set_options uses tty_termios_encode_baud_rate to determine the appropriate baudrate flags this can cause baudrate selection to fail entirely because tty_termios_encode_baud_rate will only select a baudrate if relative error between requested and selected baudrate does not exceed +/-2%. Fix that by requesting actual, exact baudrate used by the serial. Fixes: ba47f97a18f2 ("serial: core: remove baud_rates when serial console setup") Cc: stable Signed-off-by: Tobias Schramm Acked-by: Richard Genoud Link: https://lore.kernel.org/r/20230109072940.202936-1-t.schramm@manjaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/atmel_serial.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index b7872ad3e762..02fd0e79c8f7 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -2633,13 +2633,7 @@ static void __init atmel_console_get_options(struct uart_port *port, int *baud, else if (mr == ATMEL_US_PAR_ODD) *parity = 'o'; - /* - * The serial core only rounds down when matching this to a - * supported baud rate. Make sure we don't end up slightly - * lower than one of those, as it would make us fall through - * to a much lower baud rate than we really want. - */ - *baud = port->uartclk / (16 * (quot - 1)); + *baud = port->uartclk / (16 * quot); } static int __init atmel_console_setup(struct console *co, char *options) From ae2a9dcc8caa60b1e14671294e5ec902ea5d1dfd Mon Sep 17 00:00:00 2001 From: Khazhismel Kumykov Date: Tue, 17 Jan 2023 17:02:12 -0800 Subject: [PATCH 1008/4345] gsmi: fix null-deref in gsmi_get_variable commit a769b05eeed7accc4019a1ed9799dd72067f1ce8 upstream. We can get EFI variables without fetching the attribute, so we must allow for that in gsmi. commit 859748255b43 ("efi: pstore: Omit efivars caching EFI varstore access layer") added a new get_variable call with attr=NULL, which triggers panic in gsmi. Fixes: 74c5b31c6618 ("driver: Google EFI SMI") Cc: stable Signed-off-by: Khazhismel Kumykov Link: https://lore.kernel.org/r/20230118010212.1268474-1-khazhy@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/google/gsmi.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c index c1cd5ca875ca..407cac71c77d 100644 --- a/drivers/firmware/google/gsmi.c +++ b/drivers/firmware/google/gsmi.c @@ -360,9 +360,10 @@ static efi_status_t gsmi_get_variable(efi_char16_t *name, memcpy(data, gsmi_dev.data_buf->start, *data_size); /* All variables are have the following attributes */ - *attr = EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS; + if (attr) + *attr = EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS; } spin_unlock_irqrestore(&gsmi_dev.lock, flags); From d960fff8e2c0e72df2e83785d60e11e0236b8f15 Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Tue, 13 Dec 2022 00:02:47 +0200 Subject: [PATCH 1009/4345] mei: me: add meteor lake point M DID commit 0c4d68261717f89fa8c4f98a6967c3832fcb3ad0 upstream. Add Meteor Lake Point M device id. Cc: Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler Link: https://lore.kernel.org/r/20221212220247.286019-2-tomas.winkler@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/hw-me-regs.h | 2 ++ drivers/misc/mei/pci-me.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index afb2e78df4d6..eabbdf17b0c6 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -111,6 +111,8 @@ #define MEI_DEV_ID_RPL_S 0x7A68 /* Raptor Lake Point S */ +#define MEI_DEV_ID_MTL_M 0x7E70 /* Meteor Lake Point M */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 5324b65d0d29..f2765d6b8c04 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -117,6 +117,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)}, + /* required last entry */ {0, } }; From 59590f50ec9dee12c8c757c479b06c2fd7c370f5 Mon Sep 17 00:00:00 2001 From: Sasa Dragic Date: Mon, 19 Dec 2022 18:29:27 +0100 Subject: [PATCH 1010/4345] drm/i915: re-disable RC6p on Sandy Bridge MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 67b0b4ed259e425b7eed09da75b42c80682ca003 upstream. RC6p on Sandy Bridge got re-enabled over time, causing visual glitches and GPU hangs. Disabled originally in commit 1c8ecf80fdee ("drm/i915: do not enable RC6p on Sandy Bridge"). Signed-off-by: Sasa Dragic Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20221219172927.9603-2-sasa.dragic@gmail.com Fixes: fb6db0f5bf1d ("drm/i915: Remove unsafe i915.enable_rc6") Fixes: 13c5a577b342 ("drm/i915/gt: Select the deepest available parking mode for rc6") Cc: stable@vger.kernel.org Reviewed-by: Rodrigo Vivi (cherry picked from commit 0c8a6e9ea232c221976a0670256bd861408d9917) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index fb5e30de78c2..63dc0fcfcc8e 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -403,7 +403,8 @@ static const struct intel_device_info ilk_m_info = { .has_coherent_ggtt = true, \ .has_llc = 1, \ .has_rc6 = 1, \ - .has_rc6p = 1, \ + /* snb does support rc6p, but enabling it causes various issues */ \ + .has_rc6p = 0, \ .has_rps = true, \ .dma_mask_size = 40, \ .ppgtt_type = INTEL_PPGTT_ALIASING, \ From a3ef532483993985b47bed76e0fbb8ff1f8fad30 Mon Sep 17 00:00:00 2001 From: hongao Date: Tue, 22 Nov 2022 19:20:34 +0800 Subject: [PATCH 1011/4345] drm/amd/display: Fix set scaling doesn's work commit 040625ab82ce6dca7772cb3867fe5c9eb279a344 upstream. [Why] Setting scaling does not correctly update CRTC state. As a result dc stream state's src (composition area) && dest (addressable area) was not calculated as expected. This causes set scaling doesn's work. [How] Correctly update CRTC state when setting scaling property. Reviewed-by: Harry Wentland Tested-by: Rodrigo Siqueira Signed-off-by: hongao Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 167a1ee518a8..55e321512df3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8783,8 +8783,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; } - if (dm_old_con_state->abm_level != - dm_new_con_state->abm_level) + if (dm_old_con_state->abm_level != dm_new_con_state->abm_level || + dm_old_con_state->scaling != dm_new_con_state->scaling) new_crtc_state->connectors_changed = true; } From 75105d943d7a9de70856eb729c39ee73b3e541ec Mon Sep 17 00:00:00 2001 From: Joshua Ashton Date: Tue, 10 Jan 2023 20:12:21 +0000 Subject: [PATCH 1012/4345] drm/amd/display: Calculate output_color_space after pixel encoding adjustment commit 79601b894849cb6f6d6122e6590f1887ac4a66b3 upstream. Code in get_output_color_space depends on knowing the pixel encoding to determine whether to pick between eg. COLOR_SPACE_SRGB or COLOR_SPACE_YCBCR709 for transparent RGB -> YCbCr 4:4:4 in the driver. v2: Fixed patch being accidentally based on a personal feature branch, oops! Fixes: ea117312ea9f ("drm/amd/display: Reduce HDMI pixel encoding if max clock is exceeded") Reviewed-by: Melissa Wen Signed-off-by: Joshua Ashton Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 55e321512df3..fbe15f4b75fd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4567,8 +4567,6 @@ static void fill_stream_properties_from_drm_display_mode( timing_out->pix_clk_100hz = mode_in->crtc_clock * 10; timing_out->aspect_ratio = get_aspect_ratio(mode_in); - stream->output_color_space = get_output_color_space(timing_out); - stream->out_transfer_func->type = TF_TYPE_PREDEFINED; stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB; if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) { @@ -4579,6 +4577,8 @@ static void fill_stream_properties_from_drm_display_mode( adjust_colour_depth_from_display_info(timing_out, info); } } + + stream->output_color_space = get_output_color_space(timing_out); } static void fill_audio_info(struct audio_info *audio_info, From bf1d287c14139d399fbbfcb7dbdd7a7e1286bfea Mon Sep 17 00:00:00 2001 From: Joshua Ashton Date: Tue, 10 Jan 2023 22:50:42 +0000 Subject: [PATCH 1013/4345] drm/amd/display: Fix COLOR_SPACE_YCBCR2020_TYPE matrix commit 973a9c810c785ac270a6d50d8cf862b0c1643a10 upstream. The YCC conversion matrix for RGB -> COLOR_SPACE_YCBCR2020_TYPE is missing the values for the fourth column of the matrix. The fourth column of the matrix is essentially just a value that is added given that the color is 3 components in size. These values are needed to bias the chroma from the [-1, 1] -> [0, 1] range. This fixes color being very green when using Gamescope HDR on HDMI output which prefers YCC 4:4:4. Fixes: 40df2f809e8f ("drm/amd/display: color space ycbcr709 support") Reviewed-by: Melissa Wen Signed-off-by: Joshua Ashton Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c index 2a9080400bdd..86f3ea4edb31 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c @@ -92,8 +92,8 @@ static const struct out_csc_color_matrix_type output_csc_matrix[] = { { 0xE00, 0xF349, 0xFEB7, 0x1000, 0x6CE, 0x16E3, 0x24F, 0x200, 0xFCCB, 0xF535, 0xE00, 0x1000} }, { COLOR_SPACE_YCBCR2020_TYPE, - { 0x1000, 0xF149, 0xFEB7, 0x0000, 0x0868, 0x15B2, - 0x01E6, 0x0000, 0xFB88, 0xF478, 0x1000, 0x0000} }, + { 0x1000, 0xF149, 0xFEB7, 0x1004, 0x0868, 0x15B2, + 0x01E6, 0x201, 0xFB88, 0xF478, 0x1000, 0x1004} }, { COLOR_SPACE_YCBCR709_BLACK_TYPE, { 0x0000, 0x0000, 0x0000, 0x1000, 0x0000, 0x0000, 0x0000, 0x0200, 0x0000, 0x0000, 0x0000, 0x1000} }, From 4012603cbd469223f225637d265a233f034c567a Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 5 Dec 2022 11:31:25 +0100 Subject: [PATCH 1014/4345] arm64: efi: Execute runtime services from a dedicated stack commit ff7a167961d1b97e0e205f245f806e564d3505e7 upstream. With the introduction of PRMT in the ACPI subsystem, the EFI rts workqueue is no longer the only caller of efi_call_virt_pointer() in the kernel. This means the EFI runtime services lock is no longer sufficient to manage concurrent calls into firmware, but also that firmware calls may occur that are not marshalled via the workqueue mechanism, but originate directly from the caller context. For added robustness, and to ensure that the runtime services have 8 KiB of stack space available as per the EFI spec, introduce a spinlock protected EFI runtime stack of 8 KiB, where the spinlock also ensures serialization between the EFI rts workqueue (which itself serializes EFI runtime calls) and other callers of efi_call_virt_pointer(). While at it, use the stack pivot to avoid reloading the shadow call stack pointer from the ordinary stack, as doing so could produce a gadget to defeat it. Signed-off-by: Ard Biesheuvel Cc: Lee Jones Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/efi.h | 3 +++ arch/arm64/kernel/efi-rt-wrapper.S | 13 ++++++++++++- arch/arm64/kernel/efi.c | 27 +++++++++++++++++++++++++++ 3 files changed, 42 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 973b14415271..16892f0d05ad 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -25,6 +25,7 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); ({ \ efi_virtmap_load(); \ __efi_fpsimd_begin(); \ + spin_lock(&efi_rt_lock); \ }) #define arch_efi_call_virt(p, f, args...) \ @@ -36,10 +37,12 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); #define arch_efi_call_virt_teardown() \ ({ \ + spin_unlock(&efi_rt_lock); \ __efi_fpsimd_end(); \ efi_virtmap_unload(); \ }) +extern spinlock_t efi_rt_lock; efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...); #define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index 75691a2641c1..b2786b968fee 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -16,6 +16,12 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) */ stp x1, x18, [sp, #16] + ldr_l x16, efi_rt_stack_top + mov sp, x16 +#ifdef CONFIG_SHADOW_CALL_STACK + str x18, [sp, #-16]! +#endif + /* * We are lucky enough that no EFI runtime services take more than * 5 arguments, so all are passed in registers rather than via the @@ -29,6 +35,7 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) mov x4, x6 blr x8 + mov sp, x29 ldp x1, x2, [sp, #16] cmp x2, x18 ldp x29, x30, [sp], #32 @@ -42,6 +49,10 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) * called with preemption disabled and a separate shadow stack is used * for interrupts. */ - mov x18, x2 +#ifdef CONFIG_SHADOW_CALL_STACK + ldr_l x18, efi_rt_stack_top + ldr x18, [x18, #-16] +#endif + b efi_handle_corrupted_x18 // tail call SYM_FUNC_END(__efi_rt_asm_wrapper) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index c5685179db5a..72f432d23ec5 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -143,3 +143,30 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f) pr_err_ratelimited(FW_BUG "register x18 corrupted by EFI %s\n", f); return s; } + +DEFINE_SPINLOCK(efi_rt_lock); + +asmlinkage u64 *efi_rt_stack_top __ro_after_init; + +/* EFI requires 8 KiB of stack space for runtime services */ +static_assert(THREAD_SIZE >= SZ_8K); + +static int __init arm64_efi_rt_init(void) +{ + void *p; + + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return 0; + + p = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_KERNEL, + NUMA_NO_NODE, &&l); +l: if (!p) { + pr_warn("Failed to allocate EFI runtime stack\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return -ENOMEM; + } + + efi_rt_stack_top = p + THREAD_SIZE; + return 0; +} +core_initcall(arm64_efi_rt_init); From d6544bccc1967cd6a883d6abac71fc7d863e8baa Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 9 Jan 2023 12:41:46 +0100 Subject: [PATCH 1015/4345] efi: rt-wrapper: Add missing include commit 18bba1843fc7f264f58c9345d00827d082f9c558 upstream. Add the missing #include of asm/assembler.h, which is where the ldr_l macro is defined. Fixes: ff7a167961d1b97e ("arm64: efi: Execute runtime services from a dedicated stack") Signed-off-by: Ard Biesheuvel Cc: Lee Jones Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/efi-rt-wrapper.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index b2786b968fee..2d3c4b02393e 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -4,6 +4,7 @@ */ #include +#include SYM_FUNC_START(__efi_rt_asm_wrapper) stp x29, x30, [sp, #-32]! From 2f45b20c399966e894e5a175b482698855e40c7a Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 16 Jan 2023 16:44:11 -0500 Subject: [PATCH 1016/4345] Revert "drm/amdgpu: make display pinning more flexible (v2)" This reverts commit 630270978483a63dd641c1183a179437ab4900df which is commit 81d0bcf9900932633d270d5bc4a54ff599c6ebdb upstream. This commit causes hiberation regressions on some platforms on kernels older than 6.1.x (6.1.x and newer kernels works fine) so let's revert it from 5.15 and older stable kernels. This should be reverted from 6.0.x as well, but that kernel is no longer supported. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=216917 Signed-off-by: Alex Deucher Cc: kolAflash@kolahilft.de Cc: jrf@mailbox.org Cc: mario.limonciello@amd.com Cc: stable@vger.kernel.org # 5.15.x Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index b6ce64b87f48..6937f8134008 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1531,8 +1531,7 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo) uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev, uint32_t domain) { - if ((domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) && - ((adev->asic_type == CHIP_CARRIZO) || (adev->asic_type == CHIP_STONEY))) { + if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) { domain = AMDGPU_GEM_DOMAIN_VRAM; if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD) domain = AMDGPU_GEM_DOMAIN_GTT; From 03ba86bb381114a4bbbcb4a700c1e9f085c336c9 Mon Sep 17 00:00:00 2001 From: YingChi Long Date: Fri, 18 Nov 2022 08:55:35 +0800 Subject: [PATCH 1017/4345] x86/fpu: Use _Alignof to avoid undefined behavior in TYPE_ALIGN commit 55228db2697c09abddcb9487c3d9fa5854a932cd upstream. WG14 N2350 specifies that it is an undefined behavior to have type definitions within offsetof", see https://www.open-std.org/jtc1/sc22/wg14/www/docs/n2350.htm This specification is also part of C23. Therefore, replace the TYPE_ALIGN macro with the _Alignof builtin to avoid undefined behavior. (_Alignof itself is C11 and the kernel is built with -gnu11). ISO C11 _Alignof is subtly different from the GNU C extension __alignof__. Latter is the preferred alignment and _Alignof the minimal alignment. For long long on x86 these are 8 and 4 respectively. The macro TYPE_ALIGN's behavior matches _Alignof rather than __alignof__. [ bp: Massage commit message. ] Signed-off-by: YingChi Long Signed-off-by: Borislav Petkov Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20220925153151.2467884-1-me@inclyc.cn Signed-off-by: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/fpu/init.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 701f196d7c68..3c0a621b9792 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -138,9 +138,6 @@ static void __init fpu__init_system_generic(void) unsigned int fpu_kernel_xstate_size; EXPORT_SYMBOL_GPL(fpu_kernel_xstate_size); -/* Get alignment of the TYPE. */ -#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test) - /* * Enforce that 'MEMBER' is the last field of 'TYPE'. * @@ -148,8 +145,8 @@ EXPORT_SYMBOL_GPL(fpu_kernel_xstate_size); * because that's how C aligns structs. */ #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ - BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \ - TYPE_ALIGN(TYPE))) + BUILD_BUG_ON(sizeof(TYPE) != \ + ALIGN(offsetofend(TYPE, MEMBER), _Alignof(TYPE))) /* * We append the 'struct fpu' to the task_struct: From c6e3c12ff9fba32f1833b730a052f4b0a49a403d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 2 Aug 2022 15:44:12 -0400 Subject: [PATCH 1018/4345] tracing: Use alignof__(struct {type b;}) instead of offsetof() commit 09794a5a6c348f629b35fc1687071a1622ef4265 upstream. Simplify: #define ALIGN_STRUCTFIELD(type) ((int)(offsetof(struct {char a; type b;}, b))) with #define ALIGN_STRUCTFIELD(type) __alignof__(struct {type b;}) Which works just the same. Link: https://lore.kernel.org/all/a7d202457150472588df0bd3b7334b3f@AcuMS.aculab.com/ Link: https://lkml.kernel.org/r/20220802154412.513c50e3@gandalf.local.home Suggested-by: David Laight Signed-off-by: Steven Rostedt (Google) Signed-off-by: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- include/trace/trace_events.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index d74c076e9e2b..717d388ecbd6 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -400,7 +400,7 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#define ALIGN_STRUCTFIELD(type) ((int)(offsetof(struct {char a; type b;}, b))) +#define ALIGN_STRUCTFIELD(type) ((int)(__alignof__(struct {type b;}))) #undef __field_ext #define __field_ext(_type, _item, _filter_type) { \ From 89a77271d254752d83507fc347dc2d675885fe07 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 11 Apr 2022 09:48:30 -0600 Subject: [PATCH 1019/4345] io_uring: io_kiocb_update_pos() should not touch file for non -1 offset commit 6f83ab22adcb77a5824d2c274dace0d99e21319f upstream. -1 tells use to use the current position, but we check if the file is a stream regardless of that. Fix up io_kiocb_update_pos() to only dip into file if we need to. This is both more efficient and also drops 12 bytes of text on aarch64 and 64 bytes on x86-64. Fixes: b4aec4001595 ("io_uring: do not recalculate ppos unnecessarily") Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 33e6e1011105..a38c40b07a89 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3011,19 +3011,18 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; - bool is_stream = req->file->f_mode & FMODE_STREAM; - if (kiocb->ki_pos == -1) { - if (!is_stream) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; - return &kiocb->ki_pos; - } else { - kiocb->ki_pos = 0; - return NULL; - } + if (kiocb->ki_pos != -1) + return &kiocb->ki_pos; + + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + return &kiocb->ki_pos; } - return is_stream ? NULL : &kiocb->ki_pos; + + kiocb->ki_pos = 0; + return NULL; } static void kiocb_done(struct kiocb *kiocb, ssize_t ret, From fc2491562a9bed1f3e58a8ebdd4176962640e58c Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher Date: Thu, 29 Sep 2022 09:39:10 +0200 Subject: [PATCH 1020/4345] io_uring/net: fix fast_iov assignment in io_setup_async_msg() commit 3e4cb6ebbb2bad201c1186bc0b7e8cf41dd7f7e6 upstream. I hit a very bad problem during my tests of SENDMSG_ZC. BUG(); in first_iovec_segment() triggered very easily. The problem was io_setup_async_msg() in the partial retry case, which seems to happen more often with _ZC. iov_iter_iovec_advance() may change i->iov in order to have i->iov_offset being only relative to the first element. Which means kmsg->msg.msg_iter.iov is no longer the same as kmsg->fast_iov. But this would rewind the copy to be the start of async_msg->fast_iov, which means the internal state of sync_msg->msg.msg_iter is inconsitent. I tested with 5 vectors with length like this 4, 0, 64, 20, 8388608 and got a short writes with: - ret=2675244 min_ret=8388692 => remaining 5713448 sr->done_io=2675244 - ret=-EAGAIN => io_uring_poll_arm - ret=4911225 min_ret=5713448 => remaining 802223 sr->done_io=7586469 - ret=-EAGAIN => io_uring_poll_arm - ret=802223 min_ret=802223 => res=8388692 While this was easily triggered with SENDMSG_ZC (queued for 6.1), it was a potential problem starting with 7ba89d2af17aa879dda30f5d5d3f152e587fc551 in 5.18 for IORING_OP_RECVMSG. And also with 4c3c09439c08b03d9503df0ca4c7619c5842892e in 5.19 for IORING_OP_SENDMSG. However 257e84a5377fbbc336ff563833a8712619acce56 introduced the critical code into io_setup_async_msg() in 5.11. Fixes: 7ba89d2af17aa ("io_uring: ensure recv and recvmsg handle MSG_WAITALL correctly") Fixes: 257e84a5377fb ("io_uring: refactor sendmsg/recvmsg iov managing") Cc: stable@vger.kernel.org Signed-off-by: Stefan Metzmacher Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/b2e7be246e2fb173520862b0c7098e55767567a2.1664436949.git.metze@samba.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index a38c40b07a89..ac228efd5373 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -4681,8 +4681,10 @@ static int io_setup_async_msg(struct io_kiocb *req, if (async_msg->msg.msg_name) async_msg->msg.msg_name = &async_msg->addr; /* if were using fast_iov, set it to the new one */ - if (!async_msg->free_iov) - async_msg->msg.msg_iter.iov = async_msg->fast_iov; + if (!kmsg->free_iov) { + size_t fast_idx = kmsg->msg.msg_iter.iov - kmsg->fast_iov; + async_msg->msg.msg_iter.iov = &async_msg->fast_iov[fast_idx]; + } return -EAGAIN; } From f6c201b4382d1536f44b922b8f16dcb4772cc82c Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 18 Jan 2023 13:24:12 +0100 Subject: [PATCH 1021/4345] net/ulp: use consistent error code when blocking ULP commit 8ccc99362b60c6f27bb46f36fdaaccf4ef0303de upstream. The referenced commit changed the error code returned by the kernel when preventing a non-established socket from attaching the ktls ULP. Before to such a commit, the user-space got ENOTCONN instead of EINVAL. The existing self-tests depend on such error code, and the change caused a failure: RUN global.non_established ... tls.c:1673:non_established:Expected errno (22) == ENOTCONN (107) non_established: Test failed at step #3 FAIL global.non_established In the unlikely event existing applications do the same, address the issue by restoring the prior error code in the above scenario. Note that the only other ULP performing similar checks at init time - smc_ulp_ops - also fails with ENOTCONN when trying to attach the ULP to a non-established socket. Reported-by: Sabrina Dubroca Fixes: 2c02d41d71f9 ("net/ulp: prevent ULP without clone op from entering the LISTEN status") Signed-off-by: Paolo Abeni Reviewed-by: Sabrina Dubroca Link: https://lore.kernel.org/r/7bb199e7a93317fb6f8bf8b9b2dc71c18f337cde.1674042685.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_ulp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index b5d707a5a31b..8e135af0d4f7 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -136,7 +136,7 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops) if (icsk->icsk_ulp_ops) goto out_err; - err = -EINVAL; + err = -ENOTCONN; if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN) goto out_err; From be1067427abdb99148da5ecde4e5962d0f05c0e5 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 5 Jan 2023 19:42:20 +0800 Subject: [PATCH 1022/4345] net/mlx5: fix missing mutex_unlock in mlx5_fw_fatal_reporter_err_work() commit 90e7cb78b81543998217b0eb446c067ce2191a79 upstream. Add missing mutex_unlock() before returning from mlx5_fw_fatal_reporter_err_work(). Fixes: 9078e843efec ("net/mlx5: Avoid recovery in probe flows") Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Yang Yingliang Signed-off-by: Shay Drory Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index b21054514736..f42e118f3290 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -621,6 +621,7 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) { mlx5_core_err(dev, "health works are not permitted at this stage\n"); + mutex_unlock(&dev->intf_state_mutex); return; } mutex_unlock(&dev->intf_state_mutex); From 71e5cd1018d345e649e63f74a56c1897f99db7e9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 Jan 2023 12:43:26 +0000 Subject: [PATCH 1023/4345] Revert "wifi: mac80211: fix memory leak in ieee80211_if_add()" commit 80f8a66dede0a4b4e9e846765a97809c6fe49ce5 upstream. This reverts commit 13e5afd3d773c6fc6ca2b89027befaaaa1ea7293. ieee80211_if_free() is already called from free_netdev(ndev) because ndev->priv_destructor == ieee80211_if_free syzbot reported: general protection fault, probably for non-canonical address 0xdffffc0000000004: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] CPU: 0 PID: 10041 Comm: syz-executor.0 Not tainted 6.2.0-rc2-syzkaller-00388-g55b98837e37d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 RIP: 0010:pcpu_get_page_chunk mm/percpu.c:262 [inline] RIP: 0010:pcpu_chunk_addr_search mm/percpu.c:1619 [inline] RIP: 0010:free_percpu mm/percpu.c:2271 [inline] RIP: 0010:free_percpu+0x186/0x10f0 mm/percpu.c:2254 Code: 80 3c 02 00 0f 85 f5 0e 00 00 48 8b 3b 48 01 ef e8 cf b3 0b 00 48 ba 00 00 00 00 00 fc ff df 48 8d 78 20 48 89 f9 48 c1 e9 03 <80> 3c 11 00 0f 85 3b 0e 00 00 48 8b 58 20 48 b8 00 00 00 00 00 fc RSP: 0018:ffffc90004ba7068 EFLAGS: 00010002 RAX: 0000000000000000 RBX: ffff88823ffe2b80 RCX: 0000000000000004 RDX: dffffc0000000000 RSI: ffffffff81c1f4e7 RDI: 0000000000000020 RBP: ffffe8fffe8fc220 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000000 R11: 1ffffffff2179ab2 R12: ffff8880b983d000 R13: 0000000000000003 R14: 0000607f450fc220 R15: ffff88823ffe2988 FS: 00007fcb349de700(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b32220000 CR3: 000000004914f000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: netdev_run_todo+0x6bf/0x1100 net/core/dev.c:10352 ieee80211_register_hw+0x2663/0x4040 net/mac80211/main.c:1411 mac80211_hwsim_new_radio+0x2537/0x4d80 drivers/net/wireless/mac80211_hwsim.c:4583 hwsim_new_radio_nl+0xa09/0x10f0 drivers/net/wireless/mac80211_hwsim.c:5176 genl_family_rcv_msg_doit.isra.0+0x1e6/0x2d0 net/netlink/genetlink.c:968 genl_family_rcv_msg net/netlink/genetlink.c:1048 [inline] genl_rcv_msg+0x4ff/0x7e0 net/netlink/genetlink.c:1065 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2564 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1076 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x91b/0xe10 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xd3/0x120 net/socket.c:734 ____sys_sendmsg+0x712/0x8c0 net/socket.c:2476 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2530 __sys_sendmsg+0xf7/0x1c0 net/socket.c:2559 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported-by: syzbot Fixes: 13e5afd3d773 ("wifi: mac80211: fix memory leak in ieee80211_if_add()") Signed-off-by: Eric Dumazet Cc: Zhengchao Shao Cc: Johannes Berg Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230113124326.3533978-1-edumazet@google.com Signed-off-by: Greg Kroah-Hartman --- net/mac80211/iface.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d04e5a1a7e0e..3a15ef8dd322 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -2013,7 +2013,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = register_netdevice(ndev); if (ret) { - ieee80211_if_free(ndev); free_netdev(ndev); return ret; } From c392c350a0420390208a4a702482b72c37f2d6f6 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Thu, 29 Dec 2022 16:16:48 +0100 Subject: [PATCH 1024/4345] soc: qcom: apr: Make qcom,protection-domain optional again commit 599d41fb8ea8bd2a99ca9525dd69405020e43dda upstream. APR should not fail if the service device tree node does not have the qcom,protection-domain property, since this functionality does not exist on older platforms such as MSM8916 and MSM8996. Ignore -EINVAL (returned when the property does not exist) to fix a regression on 6.2-rc1 that prevents audio from working: qcom,apr remoteproc0:smd-edge.apr_audio_svc.-1.-1: Failed to read second value of qcom,protection-domain qcom,apr remoteproc0:smd-edge.apr_audio_svc.-1.-1: Failed to add apr 3 svc Fixes: 6d7860f5750d ("soc: qcom: apr: Add check for idr_alloc and of_property_read_string_index") Signed-off-by: Stephan Gerhold Reviewed-by: Bjorn Andersson Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221229151648.19839-3-stephan@gerhold.net Signed-off-by: Greg Kroah-Hartman --- drivers/soc/qcom/apr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index 7063e0d42c5e..660ee3aea447 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -319,9 +319,10 @@ static int apr_add_device(struct device *dev, struct device_node *np, goto out; } + /* Protection domain is optional, it does not exist on older platforms */ ret = of_property_read_string_index(np, "qcom,protection-domain", 1, &adev->service_path); - if (ret < 0) { + if (ret < 0 && ret != -EINVAL) { dev_err(dev, "Failed to read second value of qcom,protection-domain\n"); goto out; } From ef11bc4bb9757a5ee3ded5b8d8f7652fa0d079c0 Mon Sep 17 00:00:00 2001 From: Venkata Lakshmi Narayana Gubba Date: Wed, 30 Dec 2020 22:47:08 +0530 Subject: [PATCH 1025/4345] Bluetooth: hci_qca: Wait for SSR completion during suspend commit ad3a9c0ec2d2baed936cfdd05870f9d1e1f40e0e upstream. During SSR after memory dump collection,BT controller will be powered off, powered on and then FW will be downloaded.During suspend if BT controller is powered off due to SSR then we should wait until SSR is completed and then suspend. Fixes: 2be43abac5a8 ("Bluetooth: hci_qca: Wait for timeout during suspend") Signed-off-by: Venkata Lakshmi Narayana Gubba Signed-off-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_qca.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 096a604ef47f..ac58100dd824 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -50,7 +50,8 @@ #define IBS_HOST_TX_IDLE_TIMEOUT_MS 2000 #define CMD_TRANS_TIMEOUT_MS 100 #define MEMDUMP_TIMEOUT_MS 8000 -#define IBS_DISABLE_SSR_TIMEOUT_MS (MEMDUMP_TIMEOUT_MS + 1000) +#define IBS_DISABLE_SSR_TIMEOUT_MS \ + (MEMDUMP_TIMEOUT_MS + FW_DOWNLOAD_TIMEOUT_MS) #define FW_DOWNLOAD_TIMEOUT_MS 3000 /* susclk rate */ @@ -2111,7 +2112,12 @@ static int __maybe_unused qca_suspend(struct device *dev) set_bit(QCA_SUSPENDING, &qca->flags); - if (test_bit(QCA_BT_OFF, &qca->flags)) + /* During SSR after memory dump collection, controller will be + * powered off and then powered on.If controller is powered off + * during SSR then we should wait until SSR is completed. + */ + if (test_bit(QCA_BT_OFF, &qca->flags) && + !test_bit(QCA_SSR_TRIGGERED, &qca->flags)) return 0; if (test_bit(QCA_IBS_DISABLED, &qca->flags)) { @@ -2121,7 +2127,7 @@ static int __maybe_unused qca_suspend(struct device *dev) /* QCA_IBS_DISABLED flag is set to true, During FW download * and during memory dump collection. It is reset to false, - * After FW download complete and after memory dump collections. + * After FW download complete. */ wait_on_bit_timeout(&qca->flags, QCA_IBS_DISABLED, TASK_UNINTERRUPTIBLE, msecs_to_jiffies(wait_timeout)); @@ -2133,10 +2139,6 @@ static int __maybe_unused qca_suspend(struct device *dev) } } - /* After memory dump collection, Controller is powered off.*/ - if (test_bit(QCA_BT_OFF, &qca->flags)) - return 0; - cancel_work_sync(&qca->ws_awake_device); cancel_work_sync(&qca->ws_awake_rx); From c208f1e84a6757c42a954a6c161e65c2608f11e3 Mon Sep 17 00:00:00 2001 From: Venkata Lakshmi Narayana Gubba Date: Tue, 2 Feb 2021 20:27:42 +0530 Subject: [PATCH 1026/4345] Bluetooth: hci_qca: check for SSR triggered flag while suspend commit 1bb0c66332babc5cbc4581d962da0b03af9f23e8 upstream. QCA_IBS_DISABLED flag will be set after memorydump started from controller.Currently qca_suspend() is waiting for SSR to complete based on flag QCA_IBS_DISABLED.Added to check for QCA_SSR_TRIGGERED flag too. Fixes: 2be43abac5a8 ("Bluetooth: hci_qca: Wait for timeout during suspend") Signed-off-by: Venkata Lakshmi Narayana Gubba Signed-off-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_qca.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index ac58100dd824..3c945b12028e 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2120,7 +2120,8 @@ static int __maybe_unused qca_suspend(struct device *dev) !test_bit(QCA_SSR_TRIGGERED, &qca->flags)) return 0; - if (test_bit(QCA_IBS_DISABLED, &qca->flags)) { + if (test_bit(QCA_IBS_DISABLED, &qca->flags) || + test_bit(QCA_SSR_TRIGGERED, &qca->flags)) { wait_timeout = test_bit(QCA_SSR_TRIGGERED, &qca->flags) ? IBS_DISABLE_SSR_TIMEOUT_MS : FW_DOWNLOAD_TIMEOUT_MS; From 217721b7631348ff89825ea56a33235edef79f51 Mon Sep 17 00:00:00 2001 From: Venkata Lakshmi Narayana Gubba Date: Fri, 5 Feb 2021 21:07:16 +0530 Subject: [PATCH 1027/4345] Bluetooth: hci_qca: Fixed issue during suspend commit 55c0bd77479b60ea29fd390faf4545cfb3a1d79e upstream. If BT SoC is running with ROM FW then just return in qca_suspend function as ROM FW does not support in-band sleep. Fixes: 2be43abac5a8 ("Bluetooth: hci_qca: Wait for timeout during suspend") Signed-off-by: Venkata Lakshmi Narayana Gubba Signed-off-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_qca.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 3c945b12028e..5347fc465ce8 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -77,7 +77,8 @@ enum qca_flags { QCA_MEMDUMP_COLLECTION, QCA_HW_ERROR_EVENT, QCA_SSR_TRIGGERED, - QCA_BT_OFF + QCA_BT_OFF, + QCA_ROM_FW }; enum qca_capabilities { @@ -1664,6 +1665,7 @@ static int qca_setup(struct hci_uart *hu) if (ret) return ret; + clear_bit(QCA_ROM_FW, &qca->flags); /* Patch downloading has to be done without IBS mode */ set_bit(QCA_IBS_DISABLED, &qca->flags); @@ -1722,12 +1724,14 @@ retry: hu->hdev->cmd_timeout = qca_cmd_timeout; } else if (ret == -ENOENT) { /* No patch/nvm-config found, run with original fw/config */ + set_bit(QCA_ROM_FW, &qca->flags); ret = 0; } else if (ret == -EAGAIN) { /* * Userspace firmware loader will return -EAGAIN in case no * patch/nvm-config is found, so run with original fw/config. */ + set_bit(QCA_ROM_FW, &qca->flags); ret = 0; } else { if (retries < MAX_INIT_RETRIES) { @@ -2112,6 +2116,12 @@ static int __maybe_unused qca_suspend(struct device *dev) set_bit(QCA_SUSPENDING, &qca->flags); + /* if BT SoC is running with default firmware then it does not + * support in-band sleep + */ + if (test_bit(QCA_ROM_FW, &qca->flags)) + return 0; + /* During SSR after memory dump collection, controller will be * powered off and then powered on.If controller is powered off * during SSR then we should wait until SSR is completed. From 8bc72b4952cf5ac6656ed718953c4d860fb69b15 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 22 Dec 2022 12:41:50 -0800 Subject: [PATCH 1028/4345] mm/khugepaged: fix collapse_pte_mapped_thp() to allow anon_vma commit ab0c3f1251b4670978fde0bd54161795a139b060 upstream. uprobe_write_opcode() uses collapse_pte_mapped_thp() to restore huge pmd, when removing a breakpoint from hugepage text: vma->anon_vma is always set in that case, so undo the prohibition. And MADV_COLLAPSE ought to be able to collapse some page tables in a vma which happens to have anon_vma set from CoWing elsewhere. Is anon_vma lock required? Almost not: if any page other than expected subpage of the non-anon huge page is found in the page table, collapse is aborted without making any change. However, it is possible that an anon page was CoWed from this extent in another mm or vma, in which case a concurrent lookup might look here: so keep it away while clearing pmd (but perhaps we shall go back to using pmd_lock() there in future). Note that collapse_pte_mapped_thp() is exceptional in freeing a page table without having cleared its ptes: I'm uneasy about that, and had thought pte_clear()ing appropriate; but exclusive i_mmap lock does fix the problem, and we would have to move the mmu_notification if clearing those ptes. What this fixes is not a dangerous instability. But I suggest Cc stable because uprobes "healing" has regressed in that way, so this should follow 8d3c106e19e8 into those stable releases where it was backported (and may want adjustment there - I'll supply backports as needed). Link: https://lkml.kernel.org/r/b740c9fb-edba-92ba-59fb-7a5592e5dfc@google.com Fixes: 8d3c106e19e8 ("mm/khugepaged: take the right locks for page table retraction") Signed-off-by: Hugh Dickins Acked-by: David Hildenbrand Cc: Jann Horn Cc: Yang Shi Cc: Zach O'Keefe Cc: Song Liu Cc: [5.4+] Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/khugepaged.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 0eb3adf4ff68..b77186ec70e9 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1459,14 +1459,6 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE)) return; - /* - * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings - * that got written to. Without this, we'd have to also lock the - * anon_vma if one exists. - */ - if (vma->anon_vma) - return; - hpage = find_lock_page(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (!hpage) @@ -1538,6 +1530,10 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) } /* step 4: collapse pmd */ + /* we make no change to anon, but protect concurrent anon page lookup */ + if (vma->anon_vma) + anon_vma_lock_write(vma->anon_vma); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); @@ -1547,6 +1543,8 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) mmu_notifier_invalidate_range_end(&range); pte_free(mm, pmd_pgtable(_pmd)); + if (vma->anon_vma) + anon_vma_unlock_write(vma->anon_vma); i_mmap_unlock_write(vma->vm_file->f_mapping); drop_hpage: From ddaaadf22bea31cf7e94d55c6530ce75947bb1cc Mon Sep 17 00:00:00 2001 From: Alviro Iskandar Setiawan Date: Mon, 7 Feb 2022 21:05:33 +0700 Subject: [PATCH 1029/4345] io_uring: Clean up a false-positive warning from GCC 9.3.0 commit 0d7c1153d9291197c1dc473cfaade77acb874b4b upstream. In io_recv(), if import_single_range() fails, the @flags variable is uninitialized, then it will goto out_free. After the goto, the compiler doesn't know that (ret < min_ret) is always true, so it thinks the "if ((flags & MSG_WAITALL) ..." path could be taken. The complaint comes from gcc-9 (Debian 9.3.0-22) 9.3.0: ``` fs/io_uring.c:5238 io_recvfrom() error: uninitialized symbol 'flags' ``` Fix this by bypassing the @ret and @flags check when import_single_range() fails. Reasons: 1. import_single_range() only returns -EFAULT when it fails. 2. At that point, @flags is uninitialized and shouldn't be read. Reported-by: kernel test robot Reported-by: Dan Carpenter Reported-by: "Chen, Rong A" Link: https://lore.gnuweeb.org/timl/d33bb5a9-8173-f65b-f653-51fc0681c6d6@intel.com/ Cc: Pavel Begunkov Suggested-by: Ammar Faizi Fixes: 7297ce3d59449de49d3c9e1f64ae25488750a1fc ("io_uring: improve send/recv error handling") Signed-off-by: Alviro Iskandar Setiawan Signed-off-by: Ammar Faizi Link: https://lore.kernel.org/r/20220207140533.565411-1-ammarfaizi2@gnuweeb.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ac228efd5373..6852878e7762 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5094,7 +5094,6 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags) min_ret = iov_iter_count(&msg.msg_iter); ret = sock_recvmsg(sock, &msg, flags); -out_free: if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) return -EAGAIN; @@ -5109,6 +5108,7 @@ out_free: } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { +out_free: req_set_fail(req); } if (req->flags & REQ_F_BUFFER_SELECTED) From c1a279d79e313bd9b0ed31025edc68394bfc40ab Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 22 Jan 2023 10:24:20 -0700 Subject: [PATCH 1030/4345] io_uring: fix double poll leak on repolling commit c0737fa9a5a5cf5a053bcc983f72d58919b997c6 upstream. We have re-polling for partial IO, so a request can be polled twice. If it used two poll entries the first time then on the second io_arm_poll_handler() it will find the old apoll entry and NULL kmalloc()'ed second entry, i.e. apoll->double_poll, so leaking it. Fixes: 10c873334feba ("io_uring: allow re-poll if we made progress") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/fee2452494222ecc7f1f88c8fb659baef971414a.1655852245.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 6852878e7762..eb7e3aa85fa3 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5751,10 +5751,12 @@ static int io_arm_poll_handler(struct io_kiocb *req) mask |= POLLOUT | POLLWRNORM; } - if (req->flags & REQ_F_POLLED) + if (req->flags & REQ_F_POLLED) { apoll = req->apoll; - else + kfree(apoll->double_poll); + } else { apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); + } if (unlikely(!apoll)) return IO_APOLL_ABORTED; apoll->double_poll = NULL; From 3d5f181bda25112c4d5d10c1930a59787868e032 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 22 Jan 2023 10:36:37 -0700 Subject: [PATCH 1031/4345] io_uring/rw: ensure kiocb_end_write() is always called commit 2ec33a6c3cca9fe2465e82050c81f5ffdc508b36 upstream. A previous commit moved the notifications and end-write handling, but it is now missing a few spots where we also want to call both of those. Without that, we can potentially be missing file notifications, and more importantly, have an imbalance in the super_block writers sem accounting. Fixes: b000145e9907 ("io_uring/rw: defer fsnotify calls to task context") Reported-by: Dave Chinner Link: https://lore.kernel.org/all/20221010050319.GC2703033@dread.disaster.area/ Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 57 +++++++++++++++++++++++++++++---------------- 1 file changed, 37 insertions(+), 20 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index eb7e3aa85fa3..f989d699ed99 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2700,11 +2700,34 @@ static bool io_rw_should_reissue(struct io_kiocb *req) } #endif +/* + * Trigger the notifications after having done some IO, and finish the write + * accounting, if any. + */ +static void io_req_io_end(struct io_kiocb *req) +{ + struct io_rw *rw = &req->rw; + + WARN_ON(!in_task()); + + if (rw->kiocb.ki_flags & IOCB_WRITE) { + kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } +} + static bool __io_complete_rw_common(struct io_kiocb *req, long res) { if (res != req->result) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { + /* + * Reissue will start accounting again, finish the + * current cycle. + */ + io_req_io_end(req); req->flags |= REQ_F_REISSUE; return true; } @@ -2746,25 +2769,9 @@ static void io_req_task_complete(struct io_kiocb *req, bool *locked) } } -static void __io_complete_rw(struct io_kiocb *req, long res, long res2, - unsigned int issue_flags) -{ - if (__io_complete_rw_common(req, res)) - return; - __io_req_complete(req, issue_flags, io_fixup_rw_res(req, res), io_put_rw_kbuf(req)); -} - static void io_req_rw_complete(struct io_kiocb *req, bool *locked) { - struct io_rw *rw = &req->rw; - - if (rw->kiocb.ki_flags & IOCB_WRITE) { - kiocb_end_write(req); - fsnotify_modify(req->file); - } else { - fsnotify_access(req->file); - } - + io_req_io_end(req); io_req_task_complete(req, locked); } @@ -3032,10 +3039,20 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; - if (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) - __io_complete_rw(req, ret, 0, issue_flags); - else + if (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) { + if (!__io_complete_rw_common(req, ret)) { + /* + * Safe to call io_end from here as we're inline + * from the submission path. + */ + io_req_io_end(req); + __io_req_complete(req, issue_flags, + io_fixup_rw_res(req, ret), + io_put_rw_kbuf(req)); + } + } else { io_rw_done(kiocb, ret); + } if (req->flags & REQ_F_REISSUE) { req->flags &= ~REQ_F_REISSUE; From e699cce29accb713200ba94c88c5b98e2ccf4b75 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 16 Oct 2022 17:24:10 -0600 Subject: [PATCH 1032/4345] io_uring/rw: remove leftover debug statement commit 5c61795ea97c170347c5c4af0c159bd877b8af71 upstream. This debug statement was never meant to go into the upstream release, kill it off before it ends up in a release. It was just part of the testing for the initial version of the patch. Fixes: 2ec33a6c3cca ("io_uring/rw: ensure kiocb_end_write() is always called") Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index f989d699ed99..642e1a0560c6 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2708,8 +2708,6 @@ static void io_req_io_end(struct io_kiocb *req) { struct io_rw *rw = &req->rw; - WARN_ON(!in_task()); - if (rw->kiocb.ki_flags & IOCB_WRITE) { kiocb_end_write(req); fsnotify_modify(req->file); From 179624a57b78c02de833370b7bdf0b0f4a27ca31 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 24 Jan 2023 07:20:02 +0100 Subject: [PATCH 1033/4345] Linux 5.10.165 Link: https://lore.kernel.org/r/20230122150229.351631432@linuxfoundation.org Tested-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20230123094914.748265495@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Shuah Khan Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 68fd49d8d436..5fbff8603f44 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 164 +SUBLEVEL = 165 EXTRAVERSION = NAME = Dare mighty things From 0b8b21c0b38fbcbe6b5fa783cc363eeec1f686e5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 20 May 2022 09:57:35 +0200 Subject: [PATCH 1034/4345] clk: generalize devm_clk_get() a bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit abae8e57e49aa75f6db76aa866c775721523908f ] Allow to add an exit hook to devm managed clocks. Also use clk_get_optional() in devm_clk_get_optional instead of open coding it. The generalisation will be used in the next commit to add some more devm_clk helpers. Reviewed-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20220520075737.758761-3-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd Stable-dep-of: 340cb392a038 ("memory: atmel-sdramc: Fix missing clk_disable_unprepare in atmel_ramc_probe()") Signed-off-by: Sasha Levin --- drivers/clk/clk-devres.c | 76 ++++++++++++++++++++++++++++------------ 1 file changed, 54 insertions(+), 22 deletions(-) diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index f9d5b7334341..c822f4ef1584 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -4,39 +4,71 @@ #include #include +struct devm_clk_state { + struct clk *clk; + void (*exit)(struct clk *clk); +}; + static void devm_clk_release(struct device *dev, void *res) { - clk_put(*(struct clk **)res); + struct devm_clk_state *state = *(struct devm_clk_state **)res; + + if (state->exit) + state->exit(state->clk); + + clk_put(state->clk); +} + +static struct clk *__devm_clk_get(struct device *dev, const char *id, + struct clk *(*get)(struct device *dev, const char *id), + int (*init)(struct clk *clk), + void (*exit)(struct clk *clk)) +{ + struct devm_clk_state *state; + struct clk *clk; + int ret; + + state = devres_alloc(devm_clk_release, sizeof(*state), GFP_KERNEL); + if (!state) + return ERR_PTR(-ENOMEM); + + clk = get(dev, id); + if (IS_ERR(clk)) { + ret = PTR_ERR(clk); + goto err_clk_get; + } + + if (init) { + ret = init(clk); + if (ret) + goto err_clk_init; + } + + state->clk = clk; + state->exit = exit; + + devres_add(dev, state); + + return clk; + +err_clk_init: + + clk_put(clk); +err_clk_get: + + devres_free(state); + return ERR_PTR(ret); } struct clk *devm_clk_get(struct device *dev, const char *id) { - struct clk **ptr, *clk; - - ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL); - if (!ptr) - return ERR_PTR(-ENOMEM); - - clk = clk_get(dev, id); - if (!IS_ERR(clk)) { - *ptr = clk; - devres_add(dev, ptr); - } else { - devres_free(ptr); - } - - return clk; + return __devm_clk_get(dev, id, clk_get, NULL, NULL); } EXPORT_SYMBOL(devm_clk_get); struct clk *devm_clk_get_optional(struct device *dev, const char *id) { - struct clk *clk = devm_clk_get(dev, id); - - if (clk == ERR_PTR(-ENOENT)) - return NULL; - - return clk; + return __devm_clk_get(dev, id, clk_get_optional, NULL, NULL); } EXPORT_SYMBOL(devm_clk_get_optional); From 935ec78de50e21ac516b3d24d978281511b8417a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 20 May 2022 09:57:36 +0200 Subject: [PATCH 1035/4345] clk: Provide new devm_clk helpers for prepared and enabled clocks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7ef9651e9792b08eb310c6beb202cbc947f43cab ] When a driver keeps a clock prepared (or enabled) during the whole lifetime of the driver, these helpers allow to simplify the drivers. Reviewed-by: Jonathan Cameron Reviewed-by: Alexandru Ardelean Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20220520075737.758761-4-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd Stable-dep-of: 340cb392a038 ("memory: atmel-sdramc: Fix missing clk_disable_unprepare in atmel_ramc_probe()") Signed-off-by: Sasha Levin --- drivers/clk/clk-devres.c | 27 ++++++++++ include/linux/clk.h | 109 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 136 insertions(+) diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index c822f4ef1584..43ccd20e0298 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -66,12 +66,39 @@ struct clk *devm_clk_get(struct device *dev, const char *id) } EXPORT_SYMBOL(devm_clk_get); +struct clk *devm_clk_get_prepared(struct device *dev, const char *id) +{ + return __devm_clk_get(dev, id, clk_get, clk_prepare, clk_unprepare); +} +EXPORT_SYMBOL_GPL(devm_clk_get_prepared); + +struct clk *devm_clk_get_enabled(struct device *dev, const char *id) +{ + return __devm_clk_get(dev, id, clk_get, + clk_prepare_enable, clk_disable_unprepare); +} +EXPORT_SYMBOL_GPL(devm_clk_get_enabled); + struct clk *devm_clk_get_optional(struct device *dev, const char *id) { return __devm_clk_get(dev, id, clk_get_optional, NULL, NULL); } EXPORT_SYMBOL(devm_clk_get_optional); +struct clk *devm_clk_get_optional_prepared(struct device *dev, const char *id) +{ + return __devm_clk_get(dev, id, clk_get_optional, + clk_prepare, clk_unprepare); +} +EXPORT_SYMBOL_GPL(devm_clk_get_optional_prepared); + +struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id) +{ + return __devm_clk_get(dev, id, clk_get_optional, + clk_prepare_enable, clk_disable_unprepare); +} +EXPORT_SYMBOL_GPL(devm_clk_get_optional_enabled); + struct clk_bulk_devres { struct clk_bulk_data *clks; int num_clks; diff --git a/include/linux/clk.h b/include/linux/clk.h index 7fd6a1febcf4..1814eabb7c20 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -418,6 +418,47 @@ int __must_check devm_clk_bulk_get_all(struct device *dev, */ struct clk *devm_clk_get(struct device *dev, const char *id); +/** + * devm_clk_get_prepared - devm_clk_get() + clk_prepare() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. (IOW, @id may be identical strings, but + * clk_get may return different clock producers depending on @dev.) + * + * The returned clk (if valid) is prepared. Drivers must however assume + * that the clock is not enabled. + * + * The clock will automatically be unprepared and freed when the device + * is unbound from the bus. + */ +struct clk *devm_clk_get_prepared(struct device *dev, const char *id); + +/** + * devm_clk_get_enabled - devm_clk_get() + clk_prepare_enable() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. (IOW, @id may be identical strings, but + * clk_get may return different clock producers depending on @dev.) + * + * The returned clk (if valid) is prepared and enabled. + * + * The clock will automatically be disabled, unprepared and freed + * when the device is unbound from the bus. + */ +struct clk *devm_clk_get_enabled(struct device *dev, const char *id); + /** * devm_clk_get_optional - lookup and obtain a managed reference to an optional * clock producer. @@ -429,6 +470,50 @@ struct clk *devm_clk_get(struct device *dev, const char *id); */ struct clk *devm_clk_get_optional(struct device *dev, const char *id); +/** + * devm_clk_get_optional_prepared - devm_clk_get_optional() + clk_prepare() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. If no such clk is found, it returns NULL + * which serves as a dummy clk. That's the only difference compared + * to devm_clk_get_prepared(). + * + * The returned clk (if valid) is prepared. Drivers must however + * assume that the clock is not enabled. + * + * The clock will automatically be unprepared and freed when the + * device is unbound from the bus. + */ +struct clk *devm_clk_get_optional_prepared(struct device *dev, const char *id); + +/** + * devm_clk_get_optional_enabled - devm_clk_get_optional() + + * clk_prepare_enable() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. If no such clk is found, it returns NULL + * which serves as a dummy clk. That's the only difference compared + * to devm_clk_get_enabled(). + * + * The returned clk (if valid) is prepared and enabled. + * + * The clock will automatically be disabled, unprepared and freed + * when the device is unbound from the bus. + */ +struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id); + /** * devm_get_clk_from_child - lookup and obtain a managed reference to a * clock producer from child node. @@ -773,12 +858,36 @@ static inline struct clk *devm_clk_get(struct device *dev, const char *id) return NULL; } +static inline struct clk *devm_clk_get_prepared(struct device *dev, + const char *id) +{ + return NULL; +} + +static inline struct clk *devm_clk_get_enabled(struct device *dev, + const char *id) +{ + return NULL; +} + static inline struct clk *devm_clk_get_optional(struct device *dev, const char *id) { return NULL; } +static inline struct clk *devm_clk_get_optional_prepared(struct device *dev, + const char *id) +{ + return NULL; +} + +static inline struct clk *devm_clk_get_optional_enabled(struct device *dev, + const char *id) +{ + return NULL; +} + static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks) { From 53f55d6e07c413be72dbeee134a7a061afa4524a Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Fri, 25 Nov 2022 15:37:57 +0800 Subject: [PATCH 1036/4345] memory: atmel-sdramc: Fix missing clk_disable_unprepare in atmel_ramc_probe() [ Upstream commit 340cb392a038cf70540a4cdf2e98a247c66b6df4 ] The clk_disable_unprepare() should be called in the error handling of caps->has_mpddr_clk, fix it by replacing devm_clk_get and clk_prepare_enable by devm_clk_get_enabled. Fixes: e81b6abebc87 ("memory: add a driver for atmel ram controllers") Signed-off-by: Gaosheng Cui Link: https://lore.kernel.org/r/20221125073757.3535219-1-cuigaosheng1@huawei.com Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- drivers/memory/atmel-sdramc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/memory/atmel-sdramc.c b/drivers/memory/atmel-sdramc.c index 9c49d00c2a96..ea6e9e1eaf04 100644 --- a/drivers/memory/atmel-sdramc.c +++ b/drivers/memory/atmel-sdramc.c @@ -47,19 +47,17 @@ static int atmel_ramc_probe(struct platform_device *pdev) caps = of_device_get_match_data(&pdev->dev); if (caps->has_ddrck) { - clk = devm_clk_get(&pdev->dev, "ddrck"); + clk = devm_clk_get_enabled(&pdev->dev, "ddrck"); if (IS_ERR(clk)) return PTR_ERR(clk); - clk_prepare_enable(clk); } if (caps->has_mpddr_clk) { - clk = devm_clk_get(&pdev->dev, "mpddr"); + clk = devm_clk_get_enabled(&pdev->dev, "mpddr"); if (IS_ERR(clk)) { pr_err("AT91 RAMC: couldn't get mpddr clock\n"); return PTR_ERR(clk); } - clk_prepare_enable(clk); } return 0; From e57ea0c6ba7f9ba5944f2157861b99dec13303a4 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Sat, 26 Nov 2022 12:49:11 +0800 Subject: [PATCH 1037/4345] memory: mvebu-devbus: Fix missing clk_disable_unprepare in mvebu_devbus_probe() [ Upstream commit cb8fd6f75775165390ededea8799b60d93d9fe3e ] The clk_disable_unprepare() should be called in the error handling of devbus_get_timing_params() and of_platform_populate(), fix it by replacing devm_clk_get and clk_prepare_enable by devm_clk_get_enabled. Fixes: e81b6abebc87 ("memory: add a driver for atmel ram controllers") Signed-off-by: Gaosheng Cui Link: https://lore.kernel.org/r/20221126044911.7226-1-cuigaosheng1@huawei.com Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- drivers/memory/mvebu-devbus.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/memory/mvebu-devbus.c b/drivers/memory/mvebu-devbus.c index 8450638e8670..efc6c08db2b7 100644 --- a/drivers/memory/mvebu-devbus.c +++ b/drivers/memory/mvebu-devbus.c @@ -280,10 +280,9 @@ static int mvebu_devbus_probe(struct platform_device *pdev) if (IS_ERR(devbus->base)) return PTR_ERR(devbus->base); - clk = devm_clk_get(&pdev->dev, NULL); + clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(clk)) return PTR_ERR(clk); - clk_prepare_enable(clk); /* * Obtain clock period in picoseconds, From 2a3c3a01e2f02b864c6c35936248e1bbac975710 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Mon, 21 Nov 2022 13:31:23 -0300 Subject: [PATCH 1038/4345] ARM: dts: imx6ul-pico-dwarf: Use 'clock-frequency' [ Upstream commit 94e2cf1e0db5b06c7a6ae0878c5cbec925819a8a ] 'clock_frequency' is not a valid property. Use the correct 'clock-frequency' instead. Fixes: 47246fafef84 ("ARM: dts: imx6ul-pico: Add support for the dwarf baseboard") Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6ul-pico-dwarf.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6ul-pico-dwarf.dts b/arch/arm/boot/dts/imx6ul-pico-dwarf.dts index 162dc259edc8..5a74c7f68eb6 100644 --- a/arch/arm/boot/dts/imx6ul-pico-dwarf.dts +++ b/arch/arm/boot/dts/imx6ul-pico-dwarf.dts @@ -32,7 +32,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; From 6805e392f508c5831efe4477678d52a6cab7e090 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Mon, 21 Nov 2022 13:31:24 -0300 Subject: [PATCH 1039/4345] ARM: dts: imx7d-pico: Use 'clock-frequency' [ Upstream commit f4dd0845c4f1f5371f1e06fef0e4a1734a2db964 ] 'clock_frequency' is not a valid property. Use the correct 'clock-frequency' instead. Fixes: 8b646cfb84c3 ("ARM: dts: imx7d-pico: Add support for the dwarf baseboard") Fixes: 6418fd92417f ("ARM: dts: imx7d-pico: Add support for the nymph baseboard") Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx7d-pico-dwarf.dts | 4 ++-- arch/arm/boot/dts/imx7d-pico-nymph.dts | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/imx7d-pico-dwarf.dts b/arch/arm/boot/dts/imx7d-pico-dwarf.dts index 5162fe227d1e..fdc10563f147 100644 --- a/arch/arm/boot/dts/imx7d-pico-dwarf.dts +++ b/arch/arm/boot/dts/imx7d-pico-dwarf.dts @@ -32,7 +32,7 @@ }; &i2c1 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; @@ -52,7 +52,7 @@ }; &i2c4 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; diff --git a/arch/arm/boot/dts/imx7d-pico-nymph.dts b/arch/arm/boot/dts/imx7d-pico-nymph.dts index 104a85254adb..5afb1674e012 100644 --- a/arch/arm/boot/dts/imx7d-pico-nymph.dts +++ b/arch/arm/boot/dts/imx7d-pico-nymph.dts @@ -43,7 +43,7 @@ }; &i2c1 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; @@ -64,7 +64,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; From cccb0aea9c3f9aa88e4c41330a9d23bcd036b123 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Mon, 21 Nov 2022 17:22:59 -0300 Subject: [PATCH 1040/4345] ARM: dts: imx6qdl-gw560x: Remove incorrect 'uart-has-rtscts' [ Upstream commit 9dfbc72256b5de608ad10989bcbafdbbd1ac8d4e ] The following build warning is seen when running: make dtbs_check DT_SCHEMA_FILES=fsl-imx-uart.yaml arch/arm/boot/dts/imx6dl-gw560x.dtb: serial@2020000: rts-gpios: False schema does not allow [[20, 1, 0]] From schema: Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml The imx6qdl-gw560x board does not expose the UART RTS and CTS as native UART pins, so 'uart-has-rtscts' should not be used. Using 'uart-has-rtscts' with 'rts-gpios' is an invalid combination detected by serial.yaml. Fix the problem by removing the incorrect 'uart-has-rtscts' property. Fixes: b8a559feffb2 ("ARM: dts: imx: add Gateworks Ventana GW5600 support") Signed-off-by: Fabio Estevam Acked-by: Tim Harvey Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6qdl-gw560x.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi index 093a219a77ae..f520e337698a 100644 --- a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi @@ -634,7 +634,6 @@ &uart1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart1>; - uart-has-rtscts; rts-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>; status = "okay"; }; From 5c1dcedd5206c5233f2f7b3e82fe762c7a549180 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Fri, 2 Dec 2022 13:10:37 -0600 Subject: [PATCH 1041/4345] arm64: dts: imx8mm-beacon: Fix ecspi2 pinmux [ Upstream commit 5225ba9db112ec4ed67da5e4d8b72e618573955e ] Early hardware did not support hardware handshaking on the UART, but final production hardware did. When the hardware was updated the chip select was changed to facilitate hardware handshaking on UART3. Fix the ecspi2 pin mux to eliminate a pin conflict with UART3 and allow the EEPROM to operate again. Fixes: 4ce01ce36d77 ("arm64: dts: imx8mm-beacon: Enable RTS-CTS on UART3") Signed-off-by: Adam Ford Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi index 5667009aae13..674a0ab8a539 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi @@ -70,7 +70,7 @@ &ecspi2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_espi2>; - cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>; + cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>; status = "okay"; eeprom@0 { @@ -187,7 +187,7 @@ MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0x82 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0x82 MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0x82 - MX8MM_IOMUXC_ECSPI1_SS0_GPIO5_IO9 0x41 + MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0x41 >; }; From d775671dccf415d5e19581092270fbc52da6b06f Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 8 Dec 2022 17:54:03 +0100 Subject: [PATCH 1042/4345] ARM: imx: add missing of_node_put() [ Upstream commit 87b30c4b0efb6a194a7b8eac2568a3da520d905f ] Calling of_find_compatible_node() returns a node pointer with refcount incremented. Use of_node_put() on it when done. The patch fixes the same problem on different i.MX platforms. Fixes: 8b88f7ef31dde ("ARM: mx25: Retrieve IIM base from dt") Fixes: 94b2bec1b0e05 ("ARM: imx27: Retrieve the SYSCTRL base address from devicetree") Fixes: 3172225d45bd9 ("ARM: imx31: Retrieve the IIM base address from devicetree") Fixes: f68ea682d1da7 ("ARM: imx35: Retrieve the IIM base address from devicetree") Fixes: ee18a7154ee08 ("ARM: imx5: retrieve iim base from device tree") Signed-off-by: Dario Binacchi Reviewed-by: Fabio Estevam Reviewed-by: Martin Kaiser Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/mach-imx/cpu-imx25.c | 1 + arch/arm/mach-imx/cpu-imx27.c | 1 + arch/arm/mach-imx/cpu-imx31.c | 1 + arch/arm/mach-imx/cpu-imx35.c | 1 + arch/arm/mach-imx/cpu-imx5.c | 1 + 5 files changed, 5 insertions(+) diff --git a/arch/arm/mach-imx/cpu-imx25.c b/arch/arm/mach-imx/cpu-imx25.c index b2e1963f473d..2ee2d2813d57 100644 --- a/arch/arm/mach-imx/cpu-imx25.c +++ b/arch/arm/mach-imx/cpu-imx25.c @@ -23,6 +23,7 @@ static int mx25_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx25-iim"); iim_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!iim_base); rev = readl(iim_base + MXC_IIMSREV); iounmap(iim_base); diff --git a/arch/arm/mach-imx/cpu-imx27.c b/arch/arm/mach-imx/cpu-imx27.c index bf70e13bbe9e..1d2893908368 100644 --- a/arch/arm/mach-imx/cpu-imx27.c +++ b/arch/arm/mach-imx/cpu-imx27.c @@ -28,6 +28,7 @@ static int mx27_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx27-ccm"); ccm_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!ccm_base); /* * now we have access to the IO registers. As we need diff --git a/arch/arm/mach-imx/cpu-imx31.c b/arch/arm/mach-imx/cpu-imx31.c index b9c24b851d1a..35c544924e50 100644 --- a/arch/arm/mach-imx/cpu-imx31.c +++ b/arch/arm/mach-imx/cpu-imx31.c @@ -39,6 +39,7 @@ static int mx31_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx31-iim"); iim_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!iim_base); /* read SREV register from IIM module */ diff --git a/arch/arm/mach-imx/cpu-imx35.c b/arch/arm/mach-imx/cpu-imx35.c index 80e7d8ab9f1b..1fe75b39c2d9 100644 --- a/arch/arm/mach-imx/cpu-imx35.c +++ b/arch/arm/mach-imx/cpu-imx35.c @@ -21,6 +21,7 @@ static int mx35_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx35-iim"); iim_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!iim_base); rev = imx_readl(iim_base + MXC_IIMSREV); diff --git a/arch/arm/mach-imx/cpu-imx5.c b/arch/arm/mach-imx/cpu-imx5.c index ad56263778f9..a67c89bf155d 100644 --- a/arch/arm/mach-imx/cpu-imx5.c +++ b/arch/arm/mach-imx/cpu-imx5.c @@ -28,6 +28,7 @@ static u32 imx5_read_srev_reg(const char *compat) np = of_find_compatible_node(NULL, NULL, compat); iim_base = of_iomap(np, 0); + of_node_put(np); WARN_ON(!iim_base); srev = readl(iim_base + IIM_SREV) & 0xff; From 7b4516ba56f1fcb13ffc91912f3074e28362228d Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Tue, 22 Nov 2022 21:48:23 +0800 Subject: [PATCH 1043/4345] HID: intel_ish-hid: Add check for ishtp_dma_tx_map [ Upstream commit b3d40c3ec3dc4ad78017de6c3a38979f57aaaab8 ] As the kcalloc may return NULL pointer, it should be better to check the ishtp_dma_tx_map before use in order to avoid NULL pointer dereference. Fixes: 3703f53b99e4 ("HID: intel_ish-hid: ISH Transport layer") Signed-off-by: Jiasheng Jiang Acked-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/intel-ish-hid/ishtp/dma-if.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/hid/intel-ish-hid/ishtp/dma-if.c b/drivers/hid/intel-ish-hid/ishtp/dma-if.c index 40554c8daca0..00046cbfd4ed 100644 --- a/drivers/hid/intel-ish-hid/ishtp/dma-if.c +++ b/drivers/hid/intel-ish-hid/ishtp/dma-if.c @@ -104,6 +104,11 @@ void *ishtp_cl_get_dma_send_buf(struct ishtp_device *dev, int required_slots = (size / DMA_SLOT_SIZE) + 1 * (size % DMA_SLOT_SIZE != 0); + if (!dev->ishtp_dma_tx_map) { + dev_err(dev->devc, "Fail to allocate Tx map\n"); + return NULL; + } + spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags); for (i = 0; i <= (dev->ishtp_dma_num_slots - required_slots); i++) { free = 1; @@ -150,6 +155,11 @@ void ishtp_cl_release_dma_acked_mem(struct ishtp_device *dev, return; } + if (!dev->ishtp_dma_tx_map) { + dev_err(dev->devc, "Fail to allocate Tx map\n"); + return; + } + i = (msg_addr - dev->ishtp_host_dma_tx_buf) / DMA_SLOT_SIZE; spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags); for (j = 0; j < acked_slots; j++) { From 329fbd260352a7b9a83781d8b8bd96f95844a51f Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Thu, 29 Dec 2022 09:48:24 +0400 Subject: [PATCH 1044/4345] EDAC/highbank: Fix memory leak in highbank_mc_probe() [ Upstream commit e7a293658c20a7945014570e1921bf7d25d68a36 ] When devres_open_group() fails, it returns -ENOMEM without freeing memory allocated by edac_mc_alloc(). Call edac_mc_free() on the error handling path to avoid a memory leak. [ bp: Massage commit message. ] Fixes: a1b01edb2745 ("edac: add support for Calxeda highbank memory controller") Signed-off-by: Miaoqian Lin Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Andre Przywara Link: https://lore.kernel.org/r/20221229054825.1361993-1-linmq006@gmail.com Signed-off-by: Sasha Levin --- drivers/edac/highbank_mc_edac.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c index 61b76ec226af..19fba258ae10 100644 --- a/drivers/edac/highbank_mc_edac.c +++ b/drivers/edac/highbank_mc_edac.c @@ -174,8 +174,10 @@ static int highbank_mc_probe(struct platform_device *pdev) drvdata = mci->pvt_info; platform_set_drvdata(pdev, mci); - if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) - return -ENOMEM; + if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) { + res = -ENOMEM; + goto free; + } r = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!r) { @@ -243,6 +245,7 @@ err2: edac_mc_del_mc(&pdev->dev); err: devres_release_group(&pdev->dev, NULL); +free: edac_mc_free(mci); return res; } From e85df1db28dc93d3177f5770a8b2f2bb3b3eb863 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Thu, 22 Dec 2022 18:38:20 +0000 Subject: [PATCH 1045/4345] firmware: arm_scmi: Harden shared memory access in fetch_response [ Upstream commit ad78b81a1077f7d956952cd8bdfe1e61504e3eb8 ] A misbheaving SCMI platform firmware could reply with out-of-spec messages, shorter than the mimimum size comprising a header and a status field. Harden shmem_fetch_response to properly truncate such a bad messages. Fixes: 5c8a47a5a91d ("firmware: arm_scmi: Make scmi core independent of the transport type") Signed-off-by: Cristian Marussi Link: https://lore.kernel.org/r/20221222183823.518856-3-cristian.marussi@arm.com Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_scmi/shmem.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c index 0e3eaea5d852..415ef7df8fc3 100644 --- a/drivers/firmware/arm_scmi/shmem.c +++ b/drivers/firmware/arm_scmi/shmem.c @@ -58,10 +58,11 @@ u32 shmem_read_header(struct scmi_shared_mem __iomem *shmem) void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem, struct scmi_xfer *xfer) { + size_t len = ioread32(&shmem->length); + xfer->hdr.status = ioread32(shmem->msg_payload); /* Skip the length of header and status in shmem area i.e 8 bytes */ - xfer->rx.len = min_t(size_t, xfer->rx.len, - ioread32(&shmem->length) - 8); + xfer->rx.len = min_t(size_t, xfer->rx.len, len > 8 ? len - 8 : 0); /* Take a copy to the rx buffer.. */ memcpy_fromio(xfer->rx.buf, shmem->msg_payload + 4, xfer->rx.len); From 6813d8ba7dac2de37670e04cbe25dd7071d612fd Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Thu, 22 Dec 2022 18:38:21 +0000 Subject: [PATCH 1046/4345] firmware: arm_scmi: Harden shared memory access in fetch_notification [ Upstream commit 9bae076cd4e3e3c3dc185cae829d80b2dddec86e ] A misbheaving SCMI platform firmware could reply with out-of-spec notifications, shorter than the mimimum size comprising a header. Fixes: d5141f37c42e ("firmware: arm_scmi: Add notifications support in transport layer") Signed-off-by: Cristian Marussi Link: https://lore.kernel.org/r/20221222183823.518856-4-cristian.marussi@arm.com Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- drivers/firmware/arm_scmi/shmem.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c index 415ef7df8fc3..56a1f61aa3ff 100644 --- a/drivers/firmware/arm_scmi/shmem.c +++ b/drivers/firmware/arm_scmi/shmem.c @@ -71,8 +71,10 @@ void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem, void shmem_fetch_notification(struct scmi_shared_mem __iomem *shmem, size_t max_len, struct scmi_xfer *xfer) { + size_t len = ioread32(&shmem->length); + /* Skip only the length of header in shmem area i.e 4 bytes */ - xfer->rx.len = min_t(size_t, max_len, ioread32(&shmem->length) - 4); + xfer->rx.len = min_t(size_t, max_len, len > 4 ? len - 4 : 0); /* Take a copy to the rx buffer.. */ memcpy_fromio(xfer->rx.buf, shmem->msg_payload, xfer->rx.len); From eab7a920379af8d44a5a3c73edb29544063e7a5e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 7 Jan 2023 16:47:41 +0900 Subject: [PATCH 1047/4345] tomoyo: fix broken dependency on *.conf.default [ Upstream commit eaf2213ba563b2d74a1f2c13a6b258273f689802 ] If *.conf.default is updated, builtin-policy.h should be rebuilt, but this does not work when compiled with O= option. [Without this commit] $ touch security/tomoyo/policy/exception_policy.conf.default $ make O=/tmp security/tomoyo/ make[1]: Entering directory '/tmp' GEN Makefile CALL /home/masahiro/ref/linux/scripts/checksyscalls.sh DESCEND objtool make[1]: Leaving directory '/tmp' [With this commit] $ touch security/tomoyo/policy/exception_policy.conf.default $ make O=/tmp security/tomoyo/ make[1]: Entering directory '/tmp' GEN Makefile CALL /home/masahiro/ref/linux/scripts/checksyscalls.sh DESCEND objtool POLICY security/tomoyo/builtin-policy.h CC security/tomoyo/common.o AR security/tomoyo/built-in.a make[1]: Leaving directory '/tmp' $(srctree)/ is essential because $(wildcard ) does not follow VPATH. Fixes: f02dee2d148b ("tomoyo: Do not generate empty policy files") Signed-off-by: Masahiro Yamada Signed-off-by: Tetsuo Handa Signed-off-by: Sasha Levin --- security/tomoyo/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile index cca5a3012fee..221eaadffb09 100644 --- a/security/tomoyo/Makefile +++ b/security/tomoyo/Makefile @@ -10,7 +10,7 @@ endef quiet_cmd_policy = POLICY $@ cmd_policy = ($(call do_policy,profile); $(call do_policy,exception_policy); $(call do_policy,domain_policy); $(call do_policy,manager); $(call do_policy,stat)) >$@ -$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE +$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE $(call if_changed,policy) $(obj)/common.o: $(obj)/builtin-policy.h From d66c1d4178c219b6e7d7a6f714e3e3656faccc36 Mon Sep 17 00:00:00 2001 From: Yonatan Nachum Date: Mon, 9 Jan 2023 13:37:11 +0000 Subject: [PATCH 1048/4345] RDMA/core: Fix ib block iterator counter overflow [ Upstream commit 0afec5e9cea732cb47014655685a2a47fb180c31 ] When registering a new DMA MR after selecting the best aligned page size for it, we iterate over the given sglist to split each entry to smaller, aligned to the selected page size, DMA blocks. In given circumstances where the sg entry and page size fit certain sizes and the sg entry is not aligned to the selected page size, the total size of the aligned pages we need to cover the sg entry is >= 4GB. Under this circumstances, while iterating page aligned blocks, the counter responsible for counting how much we advanced from the start of the sg entry is overflowed because its type is u32 and we pass 4GB in size. This can lead to an infinite loop inside the iterator function because the overflow prevents the counter to be larger than the size of the sg entry. Fix the presented problem by changing the advancement condition to eliminate overflow. Backtrace: [ 192.374329] efa_reg_user_mr_dmabuf [ 192.376783] efa_register_mr [ 192.382579] pgsz_bitmap 0xfffff000 rounddown 0x80000000 [ 192.386423] pg_sz [0x80000000] umem_length[0xc0000000] [ 192.392657] start 0x0 length 0xc0000000 params.page_shift 31 params.page_num 3 [ 192.399559] hp_cnt[3], pages_in_hp[524288] [ 192.403690] umem->sgt_append.sgt.nents[1] [ 192.407905] number entries: [1], pg_bit: [31] [ 192.411397] biter->__sg_nents [1] biter->__sg [0000000008b0c5d8] [ 192.415601] biter->__sg_advance [665837568] sg_dma_len[3221225472] [ 192.419823] biter->__sg_nents [1] biter->__sg [0000000008b0c5d8] [ 192.423976] biter->__sg_advance [2813321216] sg_dma_len[3221225472] [ 192.428243] biter->__sg_nents [1] biter->__sg [0000000008b0c5d8] [ 192.432397] biter->__sg_advance [665837568] sg_dma_len[3221225472] Fixes: a808273a495c ("RDMA/verbs: Add a DMA iterator to return aligned contiguous memory blocks") Signed-off-by: Yonatan Nachum Link: https://lore.kernel.org/r/20230109133711.13678-1-ynachum@amazon.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/verbs.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 5889639e90a1..5123be0ab02f 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -2911,15 +2911,18 @@ EXPORT_SYMBOL(__rdma_block_iter_start); bool __rdma_block_iter_next(struct ib_block_iter *biter) { unsigned int block_offset; + unsigned int sg_delta; if (!biter->__sg_nents || !biter->__sg) return false; biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance; block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1); - biter->__sg_advance += BIT_ULL(biter->__pg_bit) - block_offset; + sg_delta = BIT_ULL(biter->__pg_bit) - block_offset; - if (biter->__sg_advance >= sg_dma_len(biter->__sg)) { + if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) { + biter->__sg_advance += sg_delta; + } else { biter->__sg_advance = 0; biter->__sg = sg_next(biter->__sg); biter->__sg_nents--; From 73e5666bf30d74cbc33c5b55f1ab0346a07d99a8 Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Mon, 9 Jan 2023 12:31:11 -0500 Subject: [PATCH 1049/4345] IB/hfi1: Reject a zero-length user expected buffer [ Upstream commit 0a0a6e80472c98947d73c3d13bcd7d101895f55d ] A zero length user buffer makes no sense and the code does not handle it correctly. Instead, reject a zero length as invalid. Fixes: 97736f36dbeb ("IB/hfi1: Validate page aligned for a given virtual addres") Signed-off-by: Dean Luick Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/167328547120.1472310.6362802432127399257.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/user_exp_rcv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index b94fc7fd75a9..dd8ce2a62d2b 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -298,6 +298,8 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, if (!PAGE_ALIGNED(tinfo->vaddr)) return -EINVAL; + if (tinfo->length == 0) + return -EINVAL; tidbuf = kzalloc(sizeof(*tidbuf), GFP_KERNEL); if (!tidbuf) From ee474dd66e82ac7711ecf700706f4fb4d7b46afd Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Mon, 9 Jan 2023 12:31:16 -0500 Subject: [PATCH 1050/4345] IB/hfi1: Reserve user expected TIDs [ Upstream commit ecf91551cdd2925ed6d9a9d99074fa5f67b90596 ] To avoid a race, reserve the number of user expected TIDs before setup. Fixes: 7e7a436ecb6e ("staging/hfi1: Add TID entry program function body") Signed-off-by: Dean Luick Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/167328547636.1472310.7419712824785353905.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/user_exp_rcv.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index dd8ce2a62d2b..1278cd55a480 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -324,16 +324,13 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, /* Find sets of physically contiguous pages */ tidbuf->n_psets = find_phys_blocks(tidbuf, pinned); - /* - * We don't need to access this under a lock since tid_used is per - * process and the same process cannot be in hfi1_user_exp_rcv_clear() - * and hfi1_user_exp_rcv_setup() at the same time. - */ + /* Reserve the number of expected tids to be used. */ spin_lock(&fd->tid_lock); if (fd->tid_used + tidbuf->n_psets > fd->tid_limit) pageset_count = fd->tid_limit - fd->tid_used; else pageset_count = tidbuf->n_psets; + fd->tid_used += pageset_count; spin_unlock(&fd->tid_lock); if (!pageset_count) @@ -442,10 +439,11 @@ unlock: nomem: hfi1_cdbg(TID, "total mapped: tidpairs:%u pages:%u (%d)", tididx, mapped_pages, ret); + /* adjust reserved tid_used to actual count */ + spin_lock(&fd->tid_lock); + fd->tid_used -= pageset_count - tididx; + spin_unlock(&fd->tid_lock); if (tididx) { - spin_lock(&fd->tid_lock); - fd->tid_used += tididx; - spin_unlock(&fd->tid_lock); tinfo->tidcnt = tididx; tinfo->length = mapped_pages * PAGE_SIZE; From 6dd8136fd1b365aeae47690fe4bddbc3e5d82657 Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Mon, 9 Jan 2023 12:31:21 -0500 Subject: [PATCH 1051/4345] IB/hfi1: Fix expected receive setup error exit issues [ Upstream commit e0c4a422f5246abefbf7c178ef99a1f2dc3c5f62 ] Fix three error exit issues in expected receive setup. Re-arrange error exits to increase readability. Issues and fixes: 1. Possible missed page unpin if tidlist copyout fails and not all pinned pages where made part of a TID. Fix: Unpin the unused pages. 2. Return success with unset return values tidcnt and length when no pages were pinned. Fix: Return -ENOSPC if no pages were pinned. 3. Return success with unset return values tidcnt and length when no rcvarray entries available. Fix: Return -ENOSPC if no rcvarray entries are available. Fixes: 7e7a436ecb6e ("staging/hfi1: Add TID entry program function body") Fixes: 97736f36dbeb ("IB/hfi1: Validate page aligned for a given virtual addres") Fixes: f404ca4c7ea8 ("IB/hfi1: Refactor hfi_user_exp_rcv_setup() IOCTL") Signed-off-by: Dean Luick Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/167328548150.1472310.1492305874804187634.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/user_exp_rcv.c | 87 ++++++++++++++--------- 1 file changed, 52 insertions(+), 35 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index 1278cd55a480..ba61d327a85d 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -310,15 +310,14 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets), GFP_KERNEL); if (!tidbuf->psets) { - kfree(tidbuf); - return -ENOMEM; + ret = -ENOMEM; + goto fail_release_mem; } pinned = pin_rcv_pages(fd, tidbuf); if (pinned <= 0) { - kfree(tidbuf->psets); - kfree(tidbuf); - return pinned; + ret = (pinned < 0) ? pinned : -ENOSPC; + goto fail_unpin; } /* Find sets of physically contiguous pages */ @@ -333,14 +332,16 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, fd->tid_used += pageset_count; spin_unlock(&fd->tid_lock); - if (!pageset_count) - goto bail; + if (!pageset_count) { + ret = -ENOSPC; + goto fail_unreserve; + } ngroups = pageset_count / dd->rcv_entries.group_size; tidlist = kcalloc(pageset_count, sizeof(*tidlist), GFP_KERNEL); if (!tidlist) { ret = -ENOMEM; - goto nomem; + goto fail_unreserve; } tididx = 0; @@ -436,44 +437,60 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, } unlock: mutex_unlock(&uctxt->exp_mutex); -nomem: hfi1_cdbg(TID, "total mapped: tidpairs:%u pages:%u (%d)", tididx, mapped_pages, ret); + + /* fail if nothing was programmed, set error if none provided */ + if (tididx == 0) { + if (ret >= 0) + ret = -ENOSPC; + goto fail_unreserve; + } + /* adjust reserved tid_used to actual count */ spin_lock(&fd->tid_lock); fd->tid_used -= pageset_count - tididx; spin_unlock(&fd->tid_lock); - if (tididx) { - tinfo->tidcnt = tididx; - tinfo->length = mapped_pages * PAGE_SIZE; - if (copy_to_user(u64_to_user_ptr(tinfo->tidlist), - tidlist, sizeof(tidlist[0]) * tididx)) { - /* - * On failure to copy to the user level, we need to undo - * everything done so far so we don't leak resources. - */ - tinfo->tidlist = (unsigned long)&tidlist; - hfi1_user_exp_rcv_clear(fd, tinfo); - tinfo->tidlist = 0; - ret = -EFAULT; - goto bail; - } + /* unpin all pages not covered by a TID */ + unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, pinned - mapped_pages, + false); + + tinfo->tidcnt = tididx; + tinfo->length = mapped_pages * PAGE_SIZE; + + if (copy_to_user(u64_to_user_ptr(tinfo->tidlist), + tidlist, sizeof(tidlist[0]) * tididx)) { + ret = -EFAULT; + goto fail_unprogram; } - /* - * If not everything was mapped (due to insufficient RcvArray entries, - * for example), unpin all unmapped pages so we can pin them nex time. - */ - if (mapped_pages != pinned) - unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, - (pinned - mapped_pages), false); -bail: - kfree(tidbuf->psets); - kfree(tidlist); kfree(tidbuf->pages); + kfree(tidbuf->psets); kfree(tidbuf); - return ret > 0 ? 0 : ret; + kfree(tidlist); + return 0; + +fail_unprogram: + /* unprogram, unmap, and unpin all allocated TIDs */ + tinfo->tidlist = (unsigned long)tidlist; + hfi1_user_exp_rcv_clear(fd, tinfo); + tinfo->tidlist = 0; + pinned = 0; /* nothing left to unpin */ + pageset_count = 0; /* nothing left reserved */ +fail_unreserve: + spin_lock(&fd->tid_lock); + fd->tid_used -= pageset_count; + spin_unlock(&fd->tid_lock); +fail_unpin: + if (pinned > 0) + unpin_rcv_pages(fd, tidbuf, NULL, 0, pinned, false); +fail_release_mem: + kfree(tidbuf->pages); + kfree(tidbuf->psets); + kfree(tidbuf); + kfree(tidlist); + return ret; } int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd, From 6ce4382bd1377dadba4c2b3ce23ca976e333b95f Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Mon, 9 Jan 2023 12:31:26 -0500 Subject: [PATCH 1052/4345] IB/hfi1: Immediately remove invalid memory from hardware [ Upstream commit 1c7edde1b5720ddb0aff5ca8c7f605a0f92526eb ] When a user expected receive page is unmapped, it should be immediately removed from hardware rather than depend on a reaction from user space. Fixes: 2677a7680e77 ("IB/hfi1: Fix memory leak during unexpected shutdown") Signed-off-by: Dean Luick Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/167328548663.1472310.7871808081861622659.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/user_exp_rcv.c | 43 +++++++++++++++-------- drivers/infiniband/hw/hfi1/user_exp_rcv.h | 1 + 2 files changed, 30 insertions(+), 14 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index ba61d327a85d..b70d1b135ee4 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -70,8 +70,9 @@ static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *, unsigned int start, u16 count, u32 *tidlist, unsigned int *tididx, unsigned int *pmapped); -static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo, - struct tid_group **grp); +static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo); +static void __clear_tid_node(struct hfi1_filedata *fd, + struct tid_rb_node *node); static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node); static const struct mmu_interval_notifier_ops tid_mn_ops = { @@ -511,7 +512,7 @@ int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd, mutex_lock(&uctxt->exp_mutex); for (tididx = 0; tididx < tinfo->tidcnt; tididx++) { - ret = unprogram_rcvarray(fd, tidinfo[tididx], NULL); + ret = unprogram_rcvarray(fd, tidinfo[tididx]); if (ret) { hfi1_cdbg(TID, "Failed to unprogram rcv array %d", ret); @@ -767,6 +768,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd, } node->fdata = fd; + mutex_init(&node->invalidate_mutex); node->phys = page_to_phys(pages[0]); node->npages = npages; node->rcventry = rcventry; @@ -806,8 +808,7 @@ out_unmap: return -EFAULT; } -static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo, - struct tid_group **grp) +static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo) { struct hfi1_ctxtdata *uctxt = fd->uctxt; struct hfi1_devdata *dd = uctxt->dd; @@ -830,9 +831,6 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo, if (!node || node->rcventry != (uctxt->expected_base + rcventry)) return -EBADF; - if (grp) - *grp = node->grp; - if (fd->use_mn) mmu_interval_notifier_remove(&node->notifier); cacheless_tid_rb_remove(fd, node); @@ -840,23 +838,34 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo, return 0; } -static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node) +static void __clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node) { struct hfi1_ctxtdata *uctxt = fd->uctxt; struct hfi1_devdata *dd = uctxt->dd; + mutex_lock(&node->invalidate_mutex); + if (node->freed) + goto done; + node->freed = true; + trace_hfi1_exp_tid_unreg(uctxt->ctxt, fd->subctxt, node->rcventry, node->npages, node->notifier.interval_tree.start, node->phys, node->dma_addr); - /* - * Make sure device has seen the write before we unpin the - * pages. - */ + /* Make sure device has seen the write before pages are unpinned */ hfi1_put_tid(dd, node->rcventry, PT_INVALID_FLUSH, 0, 0); unpin_rcv_pages(fd, NULL, node, 0, node->npages, true); +done: + mutex_unlock(&node->invalidate_mutex); +} + +static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node) +{ + struct hfi1_ctxtdata *uctxt = fd->uctxt; + + __clear_tid_node(fd, node); node->grp->used--; node->grp->map &= ~(1 << (node->rcventry - node->grp->base)); @@ -915,10 +924,16 @@ static bool tid_rb_invalidate(struct mmu_interval_notifier *mni, if (node->freed) return true; + /* take action only if unmapping */ + if (range->event != MMU_NOTIFY_UNMAP) + return true; + trace_hfi1_exp_tid_inval(uctxt->ctxt, fdata->subctxt, node->notifier.interval_tree.start, node->rcventry, node->npages, node->dma_addr); - node->freed = true; + + /* clear the hardware rcvarray entry */ + __clear_tid_node(fdata, node); spin_lock(&fdata->invalid_lock); if (fdata->invalid_tid_idx < uctxt->expected_count) { diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h index d45c7b6988d4..ba06ab3b4769 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h @@ -68,6 +68,7 @@ struct tid_user_buf { struct tid_rb_node { struct mmu_interval_notifier notifier; struct hfi1_filedata *fdata; + struct mutex invalidate_mutex; /* covers hw removal */ unsigned long phys; struct tid_group *grp; u32 rcventry; From f6fa12fbb17cdd46d6f981634dd502840df2d3ea Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Mon, 9 Jan 2023 12:31:31 -0500 Subject: [PATCH 1053/4345] IB/hfi1: Remove user expected buffer invalidate race [ Upstream commit b3deec25847bda34e34d5d7be02f633caf000bd8 ] During setup, there is a possible race between a page invalidate and hardware programming. Add a covering invalidate over the user target range during setup. If anything within that range is invalidated during setup, fail the setup. Once set up, each TID will have its own invalidate callback and invalidate. Fixes: 3889551db212 ("RDMA/hfi1: Use mmu_interval_notifier_insert for user_exp_rcv") Signed-off-by: Dean Luick Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/167328549178.1472310.9867497376936699488.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/user_exp_rcv.c | 58 +++++++++++++++++++++-- drivers/infiniband/hw/hfi1/user_exp_rcv.h | 2 + 2 files changed, 55 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index b70d1b135ee4..897923981855 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -65,6 +65,9 @@ static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata, static bool tid_rb_invalidate(struct mmu_interval_notifier *mni, const struct mmu_notifier_range *range, unsigned long cur_seq); +static bool tid_cover_invalidate(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq); static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *, struct tid_group *grp, unsigned int start, u16 count, @@ -78,6 +81,9 @@ static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node); static const struct mmu_interval_notifier_ops tid_mn_ops = { .invalidate = tid_rb_invalidate, }; +static const struct mmu_interval_notifier_ops tid_cover_ops = { + .invalidate = tid_cover_invalidate, +}; /* * Initialize context and file private data needed for Expected @@ -296,6 +302,7 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, tididx = 0, mapped, mapped_pages = 0; u32 *tidlist = NULL; struct tid_user_buf *tidbuf; + unsigned long mmu_seq = 0; if (!PAGE_ALIGNED(tinfo->vaddr)) return -EINVAL; @@ -306,6 +313,7 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, if (!tidbuf) return -ENOMEM; + mutex_init(&tidbuf->cover_mutex); tidbuf->vaddr = tinfo->vaddr; tidbuf->length = tinfo->length; tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets), @@ -315,6 +323,16 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, goto fail_release_mem; } + if (fd->use_mn) { + ret = mmu_interval_notifier_insert( + &tidbuf->notifier, current->mm, + tidbuf->vaddr, tidbuf->npages * PAGE_SIZE, + &tid_cover_ops); + if (ret) + goto fail_release_mem; + mmu_seq = mmu_interval_read_begin(&tidbuf->notifier); + } + pinned = pin_rcv_pages(fd, tidbuf); if (pinned <= 0) { ret = (pinned < 0) ? pinned : -ENOSPC; @@ -457,6 +475,20 @@ unlock: unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, pinned - mapped_pages, false); + if (fd->use_mn) { + /* check for an invalidate during setup */ + bool fail = false; + + mutex_lock(&tidbuf->cover_mutex); + fail = mmu_interval_read_retry(&tidbuf->notifier, mmu_seq); + mutex_unlock(&tidbuf->cover_mutex); + + if (fail) { + ret = -EBUSY; + goto fail_unprogram; + } + } + tinfo->tidcnt = tididx; tinfo->length = mapped_pages * PAGE_SIZE; @@ -466,6 +498,8 @@ unlock: goto fail_unprogram; } + if (fd->use_mn) + mmu_interval_notifier_remove(&tidbuf->notifier); kfree(tidbuf->pages); kfree(tidbuf->psets); kfree(tidbuf); @@ -484,6 +518,8 @@ fail_unreserve: fd->tid_used -= pageset_count; spin_unlock(&fd->tid_lock); fail_unpin: + if (fd->use_mn) + mmu_interval_notifier_remove(&tidbuf->notifier); if (pinned > 0) unpin_rcv_pages(fd, tidbuf, NULL, 0, pinned, false); fail_release_mem: @@ -784,11 +820,6 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd, &tid_mn_ops); if (ret) goto out_unmap; - /* - * FIXME: This is in the wrong order, the notifier should be - * established before the pages are pinned by pin_rcv_pages. - */ - mmu_interval_read_begin(&node->notifier); } fd->entry_to_rb[node->rcventry - uctxt->expected_base] = node; @@ -963,6 +994,23 @@ static bool tid_rb_invalidate(struct mmu_interval_notifier *mni, return true; } +static bool tid_cover_invalidate(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq) +{ + struct tid_user_buf *tidbuf = + container_of(mni, struct tid_user_buf, notifier); + + /* take action only if unmapping */ + if (range->event == MMU_NOTIFY_UNMAP) { + mutex_lock(&tidbuf->cover_mutex); + mmu_interval_set_seq(mni, cur_seq); + mutex_unlock(&tidbuf->cover_mutex); + } + + return true; +} + static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata, struct tid_rb_node *tnode) { diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h index ba06ab3b4769..849f265f2f11 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h @@ -57,6 +57,8 @@ struct tid_pageset { }; struct tid_user_buf { + struct mmu_interval_notifier notifier; + struct mutex cover_mutex; unsigned long vaddr; unsigned long length; unsigned int npages; From 39ab0fc4984285851048716e7f85ef8b11cabf11 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Tue, 10 Jan 2023 13:49:30 +0100 Subject: [PATCH 1054/4345] affs: initialize fsdata in affs_truncate() [ Upstream commit eef034ac6690118c88f357b00e2b3239c9d8575d ] When aops->write_begin() does not initialize fsdata, KMSAN may report an error passing the latter to aops->write_end(). Fix this by unconditionally initializing fsdata. Fixes: f2b6a16eb8f5 ("fs: affs convert to new aops") Suggested-by: Eric Biggers Signed-off-by: Alexander Potapenko Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/affs/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/affs/file.c b/fs/affs/file.c index d91b0133d95d..c3d89fa1bab7 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -879,7 +879,7 @@ affs_truncate(struct inode *inode) if (inode->i_size > AFFS_I(inode)->mmu_private) { struct address_space *mapping = inode->i_mapping; struct page *page; - void *fsdata; + void *fsdata = NULL; loff_t isize = inode->i_size; int res; From b18490138dc69ed83c5cfcdad8789004e67fee8d Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 17 Dec 2022 17:05:41 +0100 Subject: [PATCH 1055/4345] PM: AVS: qcom-cpr: Fix an error handling path in cpr_probe() [ Upstream commit 6049aae52392539e505bfb8ccbcff3c26f1d2f0b ] If an error occurs after a successful pm_genpd_init() call, it should be undone by a corresponding pm_genpd_remove(). Add the missing call in the error handling path, as already done in the remove function. Fixes: bf6910abf548 ("power: avs: Add support for CPR (Core Power Reduction)") Signed-off-by: Christophe JAILLET Reviewed-by: Ulf Hansson Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/0f520597dbad89ab99c217c8986912fa53eaf5f9.1671293108.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/soc/qcom/cpr.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/soc/qcom/cpr.c b/drivers/soc/qcom/cpr.c index 6298561bc29c..fac0414c3731 100644 --- a/drivers/soc/qcom/cpr.c +++ b/drivers/soc/qcom/cpr.c @@ -1743,12 +1743,16 @@ static int cpr_probe(struct platform_device *pdev) ret = of_genpd_add_provider_simple(dev->of_node, &drv->pd); if (ret) - return ret; + goto err_remove_genpd; platform_set_drvdata(pdev, drv); cpr_debugfs_init(drv); return 0; + +err_remove_genpd: + pm_genpd_remove(&drv->pd); + return ret; } static int cpr_remove(struct platform_device *pdev) From fa566549a152a99b6aca9be80b84d506eb2a91c6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 9 Jan 2023 22:25:29 -0800 Subject: [PATCH 1056/4345] phy: ti: fix Kconfig warning and operator precedence [ Upstream commit 7124c93887cc4e6c5b48920f83115e4a5892e870 ] Fix Kconfig depends operator precedence to prevent a Kconfig warning: WARNING: unmet direct dependencies detected for MUX_MMIO Depends on [n]: MULTIPLEXER [=m] && OF [=n] Selected by [m]: - PHY_AM654_SERDES [=m] && (OF [=n] && ARCH_K3 || COMPILE_TEST [=y]) && COMMON_CLK [=y] Fixes: 71e2f5c5c224 ("phy: ti: Add a new SERDES driver for TI's AM654x SoC") Fixes: 091876cc355d ("phy: ti: j721e-wiz: Add support for WIZ module present in TI J721E SoC") Signed-off-by: Randy Dunlap Cc: Vinod Koul Cc: Kishon Vijay Abraham I Cc: linux-phy@lists.infradead.org Cc: Arnd Bergmann Link: https://lore.kernel.org/r/20230110062529.22668-1-rdunlap@infradead.org Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/ti/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/phy/ti/Kconfig b/drivers/phy/ti/Kconfig index 15a3bcf32308..b905902d5750 100644 --- a/drivers/phy/ti/Kconfig +++ b/drivers/phy/ti/Kconfig @@ -23,7 +23,7 @@ config PHY_DM816X_USB config PHY_AM654_SERDES tristate "TI AM654 SERDES support" - depends on OF && ARCH_K3 || COMPILE_TEST + depends on OF && (ARCH_K3 || COMPILE_TEST) depends on COMMON_CLK select GENERIC_PHY select MULTIPLEXER @@ -35,7 +35,7 @@ config PHY_AM654_SERDES config PHY_J721E_WIZ tristate "TI J721E WIZ (SERDES Wrapper) support" - depends on OF && ARCH_K3 || COMPILE_TEST + depends on OF && (ARCH_K3 || COMPILE_TEST) depends on HAS_IOMEM && OF_ADDRESS depends on COMMON_CLK select GENERIC_PHY From aa8b584cec01e2a7245f27d53d36ad287df71436 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 8 Dec 2022 13:52:41 +0200 Subject: [PATCH 1057/4345] ARM: dts: at91: sam9x60: fix the ddr clock for sam9x60 [ Upstream commit 9bfa2544dbd1133f0b0af4e967de3bb9c1e3a497 ] The 2nd DDR clock for sam9x60 DDR controller is peripheral clock with id 49. Fixes: 1e5f532c2737 ("ARM: dts: at91: sam9x60: add device tree for soc and board") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20221208115241.36312-1-claudiu.beznea@microchip.com Signed-off-by: Sasha Levin --- arch/arm/boot/dts/sam9x60.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sam9x60.dtsi b/arch/arm/boot/dts/sam9x60.dtsi index ec45ced3cde6..e1e0dec8cc1f 100644 --- a/arch/arm/boot/dts/sam9x60.dtsi +++ b/arch/arm/boot/dts/sam9x60.dtsi @@ -567,7 +567,7 @@ mpddrc: mpddrc@ffffe800 { compatible = "microchip,sam9x60-ddramc", "atmel,sama5d3-ddramc"; reg = <0xffffe800 0x200>; - clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_CORE PMC_MCK>; + clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_PERIPHERAL 49>; clock-names = "ddrck", "mpddr"; }; From a65a8727a2fe606036933222313c775964de6e92 Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Wed, 11 Jan 2023 22:58:51 +0530 Subject: [PATCH 1058/4345] amd-xgbe: TX Flow Ctrl Registers are h/w ver dependent [ Upstream commit 579923d84b04abb6cd4cd1fd9974096a2dd1832b ] There is difference in the TX Flow Control registers (TFCR) between the revisions of the hardware. The older revisions of hardware used to have single register per queue. Whereas, the newer revision of hardware (from ver 30H onwards) have one register per priority. Update the driver to use the TFCR based on the reported version of the hardware. Fixes: c5aa9e3b8156 ("amd-xgbe: Initial AMD 10GbE platform driver") Co-developed-by: Ajith Nayak Signed-off-by: Ajith Nayak Signed-off-by: Raju Rangoju Acked-by: Shyam Sundar S K Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index d5fd49dd25f3..decc1c09a031 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -524,19 +524,28 @@ static void xgbe_disable_vxlan(struct xgbe_prv_data *pdata) netif_dbg(pdata, drv, pdata->netdev, "VXLAN acceleration disabled\n"); } +static unsigned int xgbe_get_fc_queue_count(struct xgbe_prv_data *pdata) +{ + unsigned int max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; + + /* From MAC ver 30H the TFCR is per priority, instead of per queue */ + if (XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER) >= 0x30) + return max_q_count; + else + return min_t(unsigned int, pdata->tx_q_count, max_q_count); +} + static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata) { - unsigned int max_q_count, q_count; unsigned int reg, reg_val; - unsigned int i; + unsigned int i, q_count; /* Clear MTL flow control */ for (i = 0; i < pdata->rx_q_count; i++) XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, EHFC, 0); /* Clear MAC flow control */ - max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + q_count = xgbe_get_fc_queue_count(pdata); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg); @@ -553,9 +562,8 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata) { struct ieee_pfc *pfc = pdata->pfc; struct ieee_ets *ets = pdata->ets; - unsigned int max_q_count, q_count; unsigned int reg, reg_val; - unsigned int i; + unsigned int i, q_count; /* Set MTL flow control */ for (i = 0; i < pdata->rx_q_count; i++) { @@ -579,8 +587,7 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata) } /* Set MAC flow control */ - max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + q_count = xgbe_get_fc_queue_count(pdata); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg); From f351af45e203787212cb027f6e1e482ea8d95d92 Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Wed, 11 Jan 2023 22:58:52 +0530 Subject: [PATCH 1059/4345] amd-xgbe: Delay AN timeout during KR training [ Upstream commit 926446ae24c03311a480fb96eb78f0ce7ea6d091 ] AN restart triggered during KR training not only aborts the KR training process but also move the HW to unstable state. Driver has to wait upto 500ms or until the KR training is completed before restarting AN cycle. Fixes: 7c12aa08779c ("amd-xgbe: Move the PHY support into amd-xgbe") Co-developed-by: Sudheesh Mavila Signed-off-by: Sudheesh Mavila Signed-off-by: Raju Rangoju Acked-by: Shyam Sundar S K Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 24 +++++++++++++++++++++++ drivers/net/ethernet/amd/xgbe/xgbe.h | 2 ++ 2 files changed, 26 insertions(+) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 0c5c1b155683..43fdd111235a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -496,6 +496,7 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata, reg |= XGBE_KR_TRAINING_ENABLE; reg |= XGBE_KR_TRAINING_START; XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg); + pdata->kr_start_time = jiffies; netif_dbg(pdata, link, pdata->netdev, "KR training initiated\n"); @@ -632,6 +633,8 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata) xgbe_switch_mode(pdata); + pdata->an_result = XGBE_AN_READY; + xgbe_an_restart(pdata); return XGBE_AN_INCOMPAT_LINK; @@ -1275,9 +1278,30 @@ static bool xgbe_phy_aneg_done(struct xgbe_prv_data *pdata) static void xgbe_check_link_timeout(struct xgbe_prv_data *pdata) { unsigned long link_timeout; + unsigned long kr_time; + int wait; link_timeout = pdata->link_check + (XGBE_LINK_TIMEOUT * HZ); if (time_after(jiffies, link_timeout)) { + if ((xgbe_cur_mode(pdata) == XGBE_MODE_KR) && + pdata->phy.autoneg == AUTONEG_ENABLE) { + /* AN restart should not happen while KR training is in progress. + * The while loop ensures no AN restart during KR training, + * waits up to 500ms and AN restart is triggered only if KR + * training is failed. + */ + wait = XGBE_KR_TRAINING_WAIT_ITER; + while (wait--) { + kr_time = pdata->kr_start_time + + msecs_to_jiffies(XGBE_AN_MS_TIMEOUT); + if (time_after(jiffies, kr_time)) + break; + /* AN restart is not required, if AN result is COMPLETE */ + if (pdata->an_result == XGBE_AN_COMPLETE) + return; + usleep_range(10000, 11000); + } + } netif_dbg(pdata, link, pdata->netdev, "AN link timeout\n"); xgbe_phy_config_aneg(pdata); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 3305979a9f7c..e0b8f3c4cc0b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -289,6 +289,7 @@ /* Auto-negotiation */ #define XGBE_AN_MS_TIMEOUT 500 #define XGBE_LINK_TIMEOUT 5 +#define XGBE_KR_TRAINING_WAIT_ITER 50 #define XGBE_SGMII_AN_LINK_STATUS BIT(1) #define XGBE_SGMII_AN_LINK_SPEED (BIT(2) | BIT(3)) @@ -1253,6 +1254,7 @@ struct xgbe_prv_data { unsigned int parallel_detect; unsigned int fec_ability; unsigned long an_start; + unsigned long kr_start_time; enum xgbe_an_mode an_mode; /* I2C support */ From da75dec7c6617bddad418159ffebcb133f008262 Mon Sep 17 00:00:00 2001 From: Luis Gerhorst Date: Mon, 9 Jan 2023 16:05:46 +0100 Subject: [PATCH 1060/4345] bpf: Fix pointer-leak due to insufficient speculative store bypass mitigation [ Upstream commit e4f4db47794c9f474b184ee1418f42e6a07412b6 ] To mitigate Spectre v4, 2039f26f3aca ("bpf: Fix leakage due to insufficient speculative store bypass mitigation") inserts lfence instructions after 1) initializing a stack slot and 2) spilling a pointer to the stack. However, this does not cover cases where a stack slot is first initialized with a pointer (subject to sanitization) but then overwritten with a scalar (not subject to sanitization because the slot was already initialized). In this case, the second write may be subject to speculative store bypass (SSB) creating a speculative pointer-as-scalar type confusion. This allows the program to subsequently leak the numerical pointer value using, for example, a branch-based cache side channel. To fix this, also sanitize scalars if they write a stack slot that previously contained a pointer. Assuming that pointer-spills are only generated by LLVM on register-pressure, the performance impact on most real-world BPF programs should be small. The following unprivileged BPF bytecode drafts a minimal exploit and the mitigation: [...] // r6 = 0 or 1 (skalar, unknown user input) // r7 = accessible ptr for side channel // r10 = frame pointer (fp), to be leaked // r9 = r10 # fp alias to encourage ssb *(u64 *)(r9 - 8) = r10 // fp[-8] = ptr, to be leaked // lfence added here because of pointer spill to stack. // // Ommitted: Dummy bpf_ringbuf_output() here to train alias predictor // for no r9-r10 dependency. // *(u64 *)(r10 - 8) = r6 // fp[-8] = scalar, overwrites ptr // 2039f26f3aca: no lfence added because stack slot was not STACK_INVALID, // store may be subject to SSB // // fix: also add an lfence when the slot contained a ptr // r8 = *(u64 *)(r9 - 8) // r8 = architecturally a scalar, speculatively a ptr // // leak ptr using branch-based cache side channel: r8 &= 1 // choose bit to leak if r8 == 0 goto SLOW // no mispredict // architecturally dead code if input r6 is 0, // only executes speculatively iff ptr bit is 1 r8 = *(u64 *)(r7 + 0) # encode bit in cache (0: slow, 1: fast) SLOW: [...] After running this, the program can time the access to *(r7 + 0) to determine whether the chosen pointer bit was 0 or 1. Repeat this 64 times to recover the whole address on amd64. In summary, sanitization can only be skipped if one scalar is overwritten with another scalar. Scalar-confusion due to speculative store bypass can not lead to invalid accesses because the pointer bounds deducted during verification are enforced using branchless logic. See 979d63d50c0c ("bpf: prevent out of bounds speculation on pointer arithmetic") for details. Do not make the mitigation depend on !env->allow_{uninit_stack,ptr_leaks} because speculative leaks are likely unexpected if these were enabled. For example, leaking the address to a protected log file may be acceptable while disabling the mitigation might unintentionally leak the address into the cached-state of a map that is accessible to unprivileged processes. Fixes: 2039f26f3aca ("bpf: Fix leakage due to insufficient speculative store bypass mitigation") Signed-off-by: Luis Gerhorst Signed-off-by: Daniel Borkmann Acked-by: Henriette Hofmeier Link: https://lore.kernel.org/bpf/edc95bad-aada-9cfc-ffe2-fa9bb206583c@cs.fau.de Link: https://lore.kernel.org/bpf/20230109150544.41465-1-gerhorst@cs.fau.de Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 232c93357b90..a6c931fed39b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2319,7 +2319,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, bool sanitize = reg && is_spillable_regtype(reg->type); for (i = 0; i < size; i++) { - if (state->stack[spi].slot_type[i] == STACK_INVALID) { + u8 type = state->stack[spi].slot_type[i]; + + if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; } From 2a0156a4aaea97a270a388f7f561c668aeeabc96 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Mon, 5 Dec 2022 19:58:23 +0800 Subject: [PATCH 1061/4345] phy: rockchip-inno-usb2: Fix missing clk_disable_unprepare() in rockchip_usb2phy_power_on() [ Upstream commit 5daba914da0e48950e9407ea4d75fa57029c9adc ] The clk_disable_unprepare() should be called in the error handling of rockchip_usb2phy_power_on(). Fixes: 0e08d2a727e6 ("phy: rockchip-inno-usb2: add a new driver for Rockchip usb2phy") Signed-off-by: Shang XiaoJing Link: https://lore.kernel.org/r/20221205115823.16957-1-shangxiaojing@huawei.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/rockchip/phy-rockchip-inno-usb2.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c index 46ebdb1460a3..cab6a94bf161 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c @@ -467,8 +467,10 @@ static int rockchip_usb2phy_power_on(struct phy *phy) return ret; ret = property_enable(base, &rport->port_cfg->phy_sus, false); - if (ret) + if (ret) { + clk_disable_unprepare(rphy->clk480m); return ret; + } /* waiting for the utmi_clk to become stable */ usleep_range(1500, 2000); From ad1baab3a5c03692d22ce446f38596a126377f6a Mon Sep 17 00:00:00 2001 From: Jisoo Jang Date: Wed, 11 Jan 2023 22:19:14 +0900 Subject: [PATCH 1062/4345] net: nfc: Fix use-after-free in local_cleanup() [ Upstream commit 4bb4db7f3187c6e3de6b229ffc87cdb30a2d22b6 ] Fix a use-after-free that occurs in kfree_skb() called from local_cleanup(). This could happen when killing nfc daemon (e.g. neard) after detaching an nfc device. When detaching an nfc device, local_cleanup() called from nfc_llcp_unregister_device() frees local->rx_pending and decreases local->ref by kref_put() in nfc_llcp_local_put(). In the terminating process, nfc daemon releases all sockets and it leads to decreasing local->ref. After the last release of local->ref, local_cleanup() called from local_release() frees local->rx_pending again, which leads to the bug. Setting local->rx_pending to NULL in local_cleanup() could prevent use-after-free when local_cleanup() is called twice. Found by a modified version of syzkaller. BUG: KASAN: use-after-free in kfree_skb() Call Trace: dump_stack_lvl (lib/dump_stack.c:106) print_address_description.constprop.0.cold (mm/kasan/report.c:306) kasan_check_range (mm/kasan/generic.c:189) kfree_skb (net/core/skbuff.c:955) local_cleanup (net/nfc/llcp_core.c:159) nfc_llcp_local_put.part.0 (net/nfc/llcp_core.c:172) nfc_llcp_local_put (net/nfc/llcp_core.c:181) llcp_sock_destruct (net/nfc/llcp_sock.c:959) __sk_destruct (net/core/sock.c:2133) sk_destruct (net/core/sock.c:2181) __sk_free (net/core/sock.c:2192) sk_free (net/core/sock.c:2203) llcp_sock_release (net/nfc/llcp_sock.c:646) __sock_release (net/socket.c:650) sock_close (net/socket.c:1365) __fput (fs/file_table.c:306) task_work_run (kernel/task_work.c:179) ptrace_notify (kernel/signal.c:2354) syscall_exit_to_user_mode_prepare (kernel/entry/common.c:278) syscall_exit_to_user_mode (kernel/entry/common.c:296) do_syscall_64 (arch/x86/entry/common.c:86) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:106) Allocated by task 4719: kasan_save_stack (mm/kasan/common.c:45) __kasan_slab_alloc (mm/kasan/common.c:325) slab_post_alloc_hook (mm/slab.h:766) kmem_cache_alloc_node (mm/slub.c:3497) __alloc_skb (net/core/skbuff.c:552) pn533_recv_response (drivers/nfc/pn533/usb.c:65) __usb_hcd_giveback_urb (drivers/usb/core/hcd.c:1671) usb_giveback_urb_bh (drivers/usb/core/hcd.c:1704) tasklet_action_common.isra.0 (kernel/softirq.c:797) __do_softirq (kernel/softirq.c:571) Freed by task 1901: kasan_save_stack (mm/kasan/common.c:45) kasan_set_track (mm/kasan/common.c:52) kasan_save_free_info (mm/kasan/genericdd.c:518) __kasan_slab_free (mm/kasan/common.c:236) kmem_cache_free (mm/slub.c:3809) kfree_skbmem (net/core/skbuff.c:874) kfree_skb (net/core/skbuff.c:931) local_cleanup (net/nfc/llcp_core.c:159) nfc_llcp_unregister_device (net/nfc/llcp_core.c:1617) nfc_unregister_device (net/nfc/core.c:1179) pn53x_unregister_nfc (drivers/nfc/pn533/pn533.c:2846) pn533_usb_disconnect (drivers/nfc/pn533/usb.c:579) usb_unbind_interface (drivers/usb/core/driver.c:458) device_release_driver_internal (drivers/base/dd.c:1279) bus_remove_device (drivers/base/bus.c:529) device_del (drivers/base/core.c:3665) usb_disable_device (drivers/usb/core/message.c:1420) usb_disconnect (drivers/usb/core.c:2261) hub_event (drivers/usb/core/hub.c:5833) process_one_work (arch/x86/include/asm/jump_label.h:27 include/linux/jump_label.h:212 include/trace/events/workqueue.h:108 kernel/workqueue.c:2281) worker_thread (include/linux/list.h:282 kernel/workqueue.c:2423) kthread (kernel/kthread.c:319) ret_from_fork (arch/x86/entry/entry_64.S:301) Fixes: 3536da06db0b ("NFC: llcp: Clean local timers and works when removing a device") Signed-off-by: Jisoo Jang Link: https://lore.kernel.org/r/20230111131914.3338838-1-jisoo.jang@yonsei.ac.kr Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/nfc/llcp_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index cc997518f79d..edadebb3efd2 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -159,6 +159,7 @@ static void local_cleanup(struct nfc_llcp_local *local) cancel_work_sync(&local->rx_work); cancel_work_sync(&local->timeout_work); kfree_skb(local->rx_pending); + local->rx_pending = NULL; del_timer_sync(&local->sdreq_timer); cancel_work_sync(&local->sdreq_timeout_work); nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs); From 613020d0489e3f6058d4f5c7c82bc4396cc880ed Mon Sep 17 00:00:00 2001 From: Esina Ekaterina Date: Thu, 12 Jan 2023 10:47:03 +0300 Subject: [PATCH 1063/4345] net: wan: Add checks for NULL for utdm in undo_uhdlc_init and unmap_si_regs [ Upstream commit 488e0bf7f34af3d42d1d5e56f7a5a7beaff188a3 ] If uhdlc_priv_tsa != 1 then utdm is not initialized. And if ret != NULL then goto undo_uhdlc_init, where utdm is dereferenced. Same if dev == NULL. Found by Astra Linux on behalf of Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 8d68100ab4ad ("soc/fsl/qe: fix err handling of ucc_of_parse_tdm") Signed-off-by: Esina Ekaterina Link: https://lore.kernel.org/r/20230112074703.13558-1-eesina@astralinux.ru Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/wan/fsl_ucc_hdlc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 7eac6a3e1cde..ae1ae65e7f90 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -1245,9 +1245,11 @@ static int ucc_hdlc_probe(struct platform_device *pdev) free_dev: free_netdev(dev); undo_uhdlc_init: - iounmap(utdm->siram); + if (utdm) + iounmap(utdm->siram); unmap_si_regs: - iounmap(utdm->si_regs); + if (utdm) + iounmap(utdm->si_regs); free_utdm: if (uhdlc_priv->tsa) kfree(utdm); From 1af8071bd08ec17bd9467f6a9c3f17053c05c98c Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 16 Jan 2023 10:49:57 +0100 Subject: [PATCH 1064/4345] gpio: mxc: Always set GPIOs used as interrupt source to INPUT mode [ Upstream commit 8e88a0feebb241cab0253698b2f7358b6ebec802 ] Always configure GPIO pins which are used as interrupt source as INPUTs. In case the default pin configuration is OUTPUT, or the prior stage does configure the pins as OUTPUT, then Linux will not reconfigure the pin as INPUT and no interrupts are received. Always configure the interrupt source GPIO pin as input to fix the above case. Reviewed-by: Linus Walleij Fixes: 07bd1a6cc7cbb ("MXC arch: Add gpio support for the whole platform") Signed-off-by: Marek Vasut Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpio-mxc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c index ba6ed2a413f5..0d5a9fee3c70 100644 --- a/drivers/gpio/gpio-mxc.c +++ b/drivers/gpio/gpio-mxc.c @@ -231,7 +231,7 @@ static int gpio_set_irq_type(struct irq_data *d, u32 type) writel(1 << gpio_idx, port->base + GPIO_ISR); - return 0; + return port->gc.direction_input(&port->gc, gpio_idx); } static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio) From 802fd7623e9ed19ee809b503e93fccc1e3f37bd6 Mon Sep 17 00:00:00 2001 From: Szymon Heidrich Date: Wed, 11 Jan 2023 18:50:31 +0100 Subject: [PATCH 1065/4345] wifi: rndis_wlan: Prevent buffer overflow in rndis_query_oid [ Upstream commit b870e73a56c4cccbec33224233eaf295839f228c ] Since resplen and respoffs are signed integers sufficiently large values of unsigned int len and offset members of RNDIS response will result in negative values of prior variables. This may be utilized to bypass implemented security checks to either extract memory contents by manipulating offset or overflow the data buffer via memcpy by manipulating both offset and len. Additionally assure that sum of resplen and respoffs does not overflow so buffer boundaries are kept. Fixes: 80f8c5b434f9 ("rndis_wlan: copy only useful data from rndis_command respond") Signed-off-by: Szymon Heidrich Reviewed-by: Alexander Duyck Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230111175031.7049-1-szymon.heidrich@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/rndis_wlan.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 75b5d545b49e..dc076d844868 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -694,8 +694,8 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len) struct rndis_query *get; struct rndis_query_c *get_c; } u; - int ret, buflen; - int resplen, respoffs, copylen; + int ret; + size_t buflen, resplen, respoffs, copylen; buflen = *len + sizeof(*u.get); if (buflen < CONTROL_BUFFER_SIZE) @@ -730,22 +730,15 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len) if (respoffs > buflen) { /* Device returned data offset outside buffer, error. */ - netdev_dbg(dev->net, "%s(%s): received invalid " - "data offset: %d > %d\n", __func__, - oid_to_string(oid), respoffs, buflen); + netdev_dbg(dev->net, + "%s(%s): received invalid data offset: %zu > %zu\n", + __func__, oid_to_string(oid), respoffs, buflen); ret = -EINVAL; goto exit_unlock; } - if ((resplen + respoffs) > buflen) { - /* Device would have returned more data if buffer would - * have been big enough. Copy just the bits that we got. - */ - copylen = buflen - respoffs; - } else { - copylen = resplen; - } + copylen = min(resplen, buflen - respoffs); if (copylen > *len) copylen = *len; From c60fe70078d6e515f424cb868d07e00411b27fbc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 Jan 2023 16:48:49 +0000 Subject: [PATCH 1066/4345] net/sched: sch_taprio: fix possible use-after-free [ Upstream commit 3a415d59c1dbec9d772dbfab2d2520d98360caae ] syzbot reported a nasty crash [1] in net_tx_action() which made little sense until we got a repro. This repro installs a taprio qdisc, but providing an invalid TCA_RATE attribute. qdisc_create() has to destroy the just initialized taprio qdisc, and taprio_destroy() is called. However, the hrtimer used by taprio had already fired, therefore advance_sched() called __netif_schedule(). Then net_tx_action was trying to use a destroyed qdisc. We can not undo the __netif_schedule(), so we must wait until one cpu serviced the qdisc before we can proceed. Many thanks to Alexander Potapenko for his help. [1] BUG: KMSAN: uninit-value in queued_spin_trylock include/asm-generic/qspinlock.h:94 [inline] BUG: KMSAN: uninit-value in do_raw_spin_trylock include/linux/spinlock.h:191 [inline] BUG: KMSAN: uninit-value in __raw_spin_trylock include/linux/spinlock_api_smp.h:89 [inline] BUG: KMSAN: uninit-value in _raw_spin_trylock+0x92/0xa0 kernel/locking/spinlock.c:138 queued_spin_trylock include/asm-generic/qspinlock.h:94 [inline] do_raw_spin_trylock include/linux/spinlock.h:191 [inline] __raw_spin_trylock include/linux/spinlock_api_smp.h:89 [inline] _raw_spin_trylock+0x92/0xa0 kernel/locking/spinlock.c:138 spin_trylock include/linux/spinlock.h:359 [inline] qdisc_run_begin include/net/sch_generic.h:187 [inline] qdisc_run+0xee/0x540 include/net/pkt_sched.h:125 net_tx_action+0x77c/0x9a0 net/core/dev.c:5086 __do_softirq+0x1cc/0x7fb kernel/softirq.c:571 run_ksoftirqd+0x2c/0x50 kernel/softirq.c:934 smpboot_thread_fn+0x554/0x9f0 kernel/smpboot.c:164 kthread+0x31b/0x430 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 Uninit was created at: slab_post_alloc_hook mm/slab.h:732 [inline] slab_alloc_node mm/slub.c:3258 [inline] __kmalloc_node_track_caller+0x814/0x1250 mm/slub.c:4970 kmalloc_reserve net/core/skbuff.c:358 [inline] __alloc_skb+0x346/0xcf0 net/core/skbuff.c:430 alloc_skb include/linux/skbuff.h:1257 [inline] nlmsg_new include/net/netlink.h:953 [inline] netlink_ack+0x5f3/0x12b0 net/netlink/af_netlink.c:2436 netlink_rcv_skb+0x55d/0x6c0 net/netlink/af_netlink.c:2507 rtnetlink_rcv+0x30/0x40 net/core/rtnetlink.c:6108 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0xf3b/0x1270 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x1288/0x1440 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0xabc/0xe90 net/socket.c:2482 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2536 __sys_sendmsg net/socket.c:2565 [inline] __do_sys_sendmsg net/socket.c:2574 [inline] __se_sys_sendmsg net/socket.c:2572 [inline] __x64_sys_sendmsg+0x367/0x540 net/socket.c:2572 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd CPU: 0 PID: 13 Comm: ksoftirqd/0 Not tainted 6.0.0-rc2-syzkaller-47461-gac3859c02d7f #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/22/2022 Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Alexander Potapenko Cc: Vinicius Costa Gomes Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/sch_generic.h | 7 +++++++ net/sched/sch_taprio.c | 3 +++ 2 files changed, 10 insertions(+) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e7e8c318925d..61cd19ee51f4 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1325,4 +1325,11 @@ static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res) return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb); } +/* Make sure qdisc is no longer in SCHED state. */ +static inline void qdisc_synchronize(const struct Qdisc *q) +{ + while (test_bit(__QDISC_STATE_SCHED, &q->state)) + msleep(1); +} + #endif diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 7f33b31c7b8b..5411bb4cdfc8 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1621,6 +1621,8 @@ static void taprio_reset(struct Qdisc *sch) int i; hrtimer_cancel(&q->advance_timer); + qdisc_synchronize(sch); + if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues; i++) if (q->qdiscs[i]) @@ -1642,6 +1644,7 @@ static void taprio_destroy(struct Qdisc *sch) * happens in qdisc_create(), after taprio_init() has been called. */ hrtimer_cancel(&q->advance_timer); + qdisc_synchronize(sch); taprio_disable_offload(dev, q, NULL); From e34a965f771f1977f172593c73e373036c765724 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Mon, 14 Nov 2022 20:16:19 +0100 Subject: [PATCH 1067/4345] l2tp: Serialize access to sk_user_data with sk_callback_lock [ Upstream commit b68777d54fac21fc833ec26ea1a2a84f975ab035 ] sk->sk_user_data has multiple users, which are not compatible with each other. Writers must synchronize by grabbing the sk->sk_callback_lock. l2tp currently fails to grab the lock when modifying the underlying tunnel socket fields. Fix it by adding appropriate locking. We err on the side of safety and grab the sk_callback_lock also inside the sk_destruct callback overridden by l2tp, even though there should be no refs allowing access to the sock at the time when sk_destruct gets called. v4: - serialize write to sk_user_data in l2tp sk_destruct v3: - switch from sock lock to sk_callback_lock - document write-protection for sk_user_data v2: - update Fixes to point to origin of the bug - use real names in Reported/Tested-by tags Cc: Tom Parkin Fixes: 3557baabf280 ("[L2TP]: PPP over L2TP driver core") Reported-by: Haowei Yan Signed-off-by: Jakub Sitnicki Signed-off-by: David S. Miller Stable-dep-of: 0b2c59720e65 ("l2tp: close all race conditions in l2tp_tunnel_register()") Signed-off-by: Sasha Levin --- include/net/sock.h | 2 +- net/l2tp/l2tp_core.c | 19 +++++++++++++------ 2 files changed, 14 insertions(+), 7 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 90a8b8b26a20..69bbbe8bbf34 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -315,7 +315,7 @@ struct bpf_local_storage; * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals - * @sk_user_data: RPC layer private data + * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index dc8987ed08ad..e89852bc5309 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1150,8 +1150,10 @@ static void l2tp_tunnel_destruct(struct sock *sk) } /* Remove hooks into tunnel socket */ + write_lock_bh(&sk->sk_callback_lock); sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; + write_unlock_bh(&sk->sk_callback_lock); /* Call the original destructor */ if (sk->sk_destruct) @@ -1471,16 +1473,18 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, sock = sockfd_lookup(tunnel->fd, &ret); if (!sock) goto err; - - ret = l2tp_validate_socket(sock->sk, net, tunnel->encap); - if (ret < 0) - goto err_sock; } + sk = sock->sk; + write_lock(&sk->sk_callback_lock); + + ret = l2tp_validate_socket(sk, net, tunnel->encap); + if (ret < 0) + goto err_sock; + tunnel->l2tp_net = net; pn = l2tp_pernet(net); - sk = sock->sk; sock_hold(sk); tunnel->sock = sk; @@ -1506,7 +1510,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, setup_udp_tunnel_sock(net, sock, &udp_cfg); } else { - sk->sk_user_data = tunnel; + rcu_assign_sk_user_data(sk, tunnel); } tunnel->old_sk_destruct = sk->sk_destruct; @@ -1520,6 +1524,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, if (tunnel->fd >= 0) sockfd_put(sock); + write_unlock(&sk->sk_callback_lock); return 0; err_sock: @@ -1527,6 +1532,8 @@ err_sock: sock_release(sock); else sockfd_put(sock); + + write_unlock(&sk->sk_callback_lock); err: return ret; } From 5b209b8c99d487a1c32983981bf3552980fda591 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Mon, 21 Nov 2022 09:54:26 +0100 Subject: [PATCH 1068/4345] l2tp: Don't sleep and disable BH under writer-side sk_callback_lock [ Upstream commit af295e854a4e3813ffbdef26dbb6a4d6226c3ea1 ] When holding a reader-writer spin lock we cannot sleep. Calling setup_udp_tunnel_sock() with write lock held violates this rule, because we end up calling percpu_down_read(), which might sleep, as syzbot reports [1]: __might_resched.cold+0x222/0x26b kernel/sched/core.c:9890 percpu_down_read include/linux/percpu-rwsem.h:49 [inline] cpus_read_lock+0x1b/0x140 kernel/cpu.c:310 static_key_slow_inc+0x12/0x20 kernel/jump_label.c:158 udp_tunnel_encap_enable include/net/udp_tunnel.h:187 [inline] setup_udp_tunnel_sock+0x43d/0x550 net/ipv4/udp_tunnel_core.c:81 l2tp_tunnel_register+0xc51/0x1210 net/l2tp/l2tp_core.c:1509 pppol2tp_connect+0xcdc/0x1a10 net/l2tp/l2tp_ppp.c:723 Trim the writer-side critical section for sk_callback_lock down to the minimum, so that it covers only operations on sk_user_data. Also, when grabbing the sk_callback_lock, we always need to disable BH, as Eric points out. Failing to do so leads to deadlocks because we acquire sk_callback_lock in softirq context, which can get stuck waiting on us if: 1) it runs on the same CPU, or CPU0 ---- lock(clock-AF_INET6); lock(clock-AF_INET6); 2) lock ordering leads to priority inversion CPU0 CPU1 ---- ---- lock(clock-AF_INET6); local_irq_disable(); lock(&tcp_hashinfo.bhash[i].lock); lock(clock-AF_INET6); lock(&tcp_hashinfo.bhash[i].lock); ... as syzbot reports [2,3]. Use the _bh variants for write_(un)lock. [1] https://lore.kernel.org/netdev/0000000000004e78ec05eda79749@google.com/ [2] https://lore.kernel.org/netdev/000000000000e38b6605eda76f98@google.com/ [3] https://lore.kernel.org/netdev/000000000000dfa31e05eda76f75@google.com/ v2: - Check and set sk_user_data while holding sk_callback_lock for both L2TP encapsulation types (IP and UDP) (Tetsuo) Cc: Tom Parkin Cc: Tetsuo Handa Fixes: b68777d54fac ("l2tp: Serialize access to sk_user_data with sk_callback_lock") Reported-by: Eric Dumazet Reported-by: syzbot+703d9e154b3b58277261@syzkaller.appspotmail.com Reported-by: syzbot+50680ced9e98a61f7698@syzkaller.appspotmail.com Reported-by: syzbot+de987172bb74a381879b@syzkaller.appspotmail.com Signed-off-by: Jakub Sitnicki Signed-off-by: David S. Miller Stable-dep-of: 0b2c59720e65 ("l2tp: close all race conditions in l2tp_tunnel_register()") Signed-off-by: Sasha Levin --- net/l2tp/l2tp_core.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index e89852bc5309..d6bb1795329a 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1476,11 +1476,12 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, } sk = sock->sk; - write_lock(&sk->sk_callback_lock); - + write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) - goto err_sock; + goto err_inval_sock; + rcu_assign_sk_user_data(sk, tunnel); + write_unlock_bh(&sk->sk_callback_lock); tunnel->l2tp_net = net; pn = l2tp_pernet(net); @@ -1509,8 +1510,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, }; setup_udp_tunnel_sock(net, sock, &udp_cfg); - } else { - rcu_assign_sk_user_data(sk, tunnel); } tunnel->old_sk_destruct = sk->sk_destruct; @@ -1524,16 +1523,18 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, if (tunnel->fd >= 0) sockfd_put(sock); - write_unlock(&sk->sk_callback_lock); return 0; err_sock: + write_lock_bh(&sk->sk_callback_lock); + rcu_assign_sk_user_data(sk, NULL); +err_inval_sock: + write_unlock_bh(&sk->sk_callback_lock); + if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); - - write_unlock(&sk->sk_callback_lock); err: return ret; } From 76c640d6a1e8a98afbc6ba3f884afe6e0bc5271d Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 13 Jan 2023 19:01:36 -0800 Subject: [PATCH 1069/4345] l2tp: convert l2tp_tunnel_list to idr [ Upstream commit c4d48a58f32c5972174a1d01c33b296fe378cce0 ] l2tp uses l2tp_tunnel_list to track all registered tunnels and to allocate tunnel ID's. IDR can do the same job. More importantly, with IDR we can hold the ID before a successful registration so that we don't need to worry about late error handling, it is not easy to rollback socket changes. This is a preparation for the following fix. Cc: Tetsuo Handa Cc: Guillaume Nault Cc: Jakub Sitnicki Cc: Eric Dumazet Cc: Tom Parkin Signed-off-by: Cong Wang Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller Stable-dep-of: 0b2c59720e65 ("l2tp: close all race conditions in l2tp_tunnel_register()") Signed-off-by: Sasha Levin --- net/l2tp/l2tp_core.c | 85 ++++++++++++++++++++++---------------------- 1 file changed, 42 insertions(+), 43 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index d6bb1795329a..1bd52b8bb29f 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -104,9 +104,9 @@ static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ static unsigned int l2tp_net_id; struct l2tp_net { - struct list_head l2tp_tunnel_list; - /* Lock for write access to l2tp_tunnel_list */ - spinlock_t l2tp_tunnel_list_lock; + /* Lock for write access to l2tp_tunnel_idr */ + spinlock_t l2tp_tunnel_idr_lock; + struct idr l2tp_tunnel_idr; struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2]; /* Lock for write access to l2tp_session_hlist */ spinlock_t l2tp_session_hlist_lock; @@ -208,13 +208,10 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (tunnel->tunnel_id == tunnel_id && - refcount_inc_not_zero(&tunnel->ref_count)) { - rcu_read_unlock_bh(); - - return tunnel; - } + tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id); + if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) { + rcu_read_unlock_bh(); + return tunnel; } rcu_read_unlock_bh(); @@ -224,13 +221,14 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_get); struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) { - const struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_net *pn = l2tp_pernet(net); + unsigned long tunnel_id, tmp; struct l2tp_tunnel *tunnel; int count = 0; rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (++count > nth && + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel && ++count > nth && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; @@ -1229,6 +1227,15 @@ static void l2tp_udp_encap_destroy(struct sock *sk) l2tp_tunnel_delete(tunnel); } +static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) +{ + struct l2tp_net *pn = l2tp_pernet(net); + + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); +} + /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { @@ -1236,7 +1243,6 @@ static void l2tp_tunnel_del_work(struct work_struct *work) del_work); struct sock *sk = tunnel->sock; struct socket *sock = sk->sk_socket; - struct l2tp_net *pn; l2tp_tunnel_closeall(tunnel); @@ -1250,12 +1256,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work) } } - /* Remove the tunnel struct from the tunnel list */ - pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_del_rcu(&tunnel->list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - + l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ l2tp_tunnel_dec_refcount(tunnel); @@ -1457,12 +1458,19 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net, int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg) { - struct l2tp_tunnel *tunnel_walk; - struct l2tp_net *pn; + struct l2tp_net *pn = l2tp_pernet(net); + u32 tunnel_id = tunnel->tunnel_id; struct socket *sock; struct sock *sk; int ret; + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id, + GFP_ATOMIC); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); + if (ret) + return ret == -ENOSPC ? -EEXIST : ret; + if (tunnel->fd < 0) { ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id, tunnel->peer_tunnel_id, cfg, @@ -1483,23 +1491,13 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, rcu_assign_sk_user_data(sk, tunnel); write_unlock_bh(&sk->sk_callback_lock); - tunnel->l2tp_net = net; - pn = l2tp_pernet(net); - sock_hold(sk); tunnel->sock = sk; + tunnel->l2tp_net = net; - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_for_each_entry(tunnel_walk, &pn->l2tp_tunnel_list, list) { - if (tunnel_walk->tunnel_id == tunnel->tunnel_id) { - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - sock_put(sk); - ret = -EEXIST; - goto err_sock; - } - } - list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { @@ -1525,9 +1523,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, return 0; -err_sock: - write_lock_bh(&sk->sk_callback_lock); - rcu_assign_sk_user_data(sk, NULL); err_inval_sock: write_unlock_bh(&sk->sk_callback_lock); @@ -1536,6 +1531,7 @@ err_inval_sock: else sockfd_put(sock); err: + l2tp_tunnel_remove(net, tunnel); return ret; } EXPORT_SYMBOL_GPL(l2tp_tunnel_register); @@ -1649,8 +1645,8 @@ static __net_init int l2tp_init_net(struct net *net) struct l2tp_net *pn = net_generic(net, l2tp_net_id); int hash; - INIT_LIST_HEAD(&pn->l2tp_tunnel_list); - spin_lock_init(&pn->l2tp_tunnel_list_lock); + idr_init(&pn->l2tp_tunnel_idr); + spin_lock_init(&pn->l2tp_tunnel_idr_lock); for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]); @@ -1664,11 +1660,13 @@ static __net_exit void l2tp_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; + unsigned long tunnel_id, tmp; int hash; rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - l2tp_tunnel_delete(tunnel); + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel) + l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); @@ -1678,6 +1676,7 @@ static __net_exit void l2tp_exit_net(struct net *net) for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash])); + idr_destroy(&pn->l2tp_tunnel_idr); } static struct pernet_operations l2tp_net_ops = { From 2d77e5c0ad79004b5ef901895437e9cce6dfcc7e Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 13 Jan 2023 19:01:37 -0800 Subject: [PATCH 1070/4345] l2tp: close all race conditions in l2tp_tunnel_register() [ Upstream commit 0b2c59720e65885a394a017d0cf9cab118914682 ] The code in l2tp_tunnel_register() is racy in several ways: 1. It modifies the tunnel socket _after_ publishing it. 2. It calls setup_udp_tunnel_sock() on an existing socket without locking. 3. It changes sock lock class on fly, which triggers many syzbot reports. This patch amends all of them by moving socket initialization code before publishing and under sock lock. As suggested by Jakub, the l2tp lockdep class is not necessary as we can just switch to bh_lock_sock_nested(). Fixes: 37159ef2c1ae ("l2tp: fix a lockdep splat") Fixes: 6b9f34239b00 ("l2tp: fix races in tunnel creation") Reported-by: syzbot+52866e24647f9a23403f@syzkaller.appspotmail.com Reported-by: syzbot+94cc2a66fc228b23f360@syzkaller.appspotmail.com Reported-by: Tetsuo Handa Cc: Guillaume Nault Cc: Jakub Sitnicki Cc: Eric Dumazet Cc: Tom Parkin Signed-off-by: Cong Wang Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/l2tp/l2tp_core.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 1bd52b8bb29f..386510a93696 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1041,7 +1041,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); - bh_lock_sock(sk); + bh_lock_sock_nested(sk); if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; @@ -1387,8 +1387,6 @@ out: return err; } -static struct lock_class_key l2tp_socket_class; - int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp) { @@ -1484,21 +1482,16 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, } sk = sock->sk; + lock_sock(sk); write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); - if (ret < 0) + if (ret < 0) { + release_sock(sk); goto err_inval_sock; + } rcu_assign_sk_user_data(sk, tunnel); write_unlock_bh(&sk->sk_callback_lock); - sock_hold(sk); - tunnel->sock = sk; - tunnel->l2tp_net = net; - - spin_lock_bh(&pn->l2tp_tunnel_idr_lock); - idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id); - spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); - if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { .sk_user_data = tunnel, @@ -1512,9 +1505,16 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; - lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, - "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; + release_sock(sk); + + sock_hold(sk); + tunnel->sock = sk; + tunnel->l2tp_net = net; + + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); trace_register_tunnel(tunnel); From 67866b1e0ab9ca7858547c38f8f69d45892e67a8 Mon Sep 17 00:00:00 2001 From: Szymon Heidrich Date: Sat, 14 Jan 2023 19:23:26 +0100 Subject: [PATCH 1071/4345] net: usb: sr9700: Handle negative len [ Upstream commit ecf7cf8efb59789e2b21d2f9ab926142579092b2 ] Packet len computed as difference of length word extracted from skb data and four may result in a negative value. In such case processing of the buffer should be interrupted rather than setting sr_skb->len to an unexpectedly large value (due to cast from signed to unsigned integer) and passing sr_skb to usbnet_skb_return. Fixes: e9da0b56fe27 ("sr9700: sanity check for packet length") Signed-off-by: Szymon Heidrich Link: https://lore.kernel.org/r/20230114182326.30479-1-szymon.heidrich@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/usb/sr9700.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index fce6713e970b..811c8751308c 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -410,7 +410,7 @@ static int sr9700_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* ignore the CRC length */ len = (skb->data[1] | (skb->data[2] << 8)) - 4; - if (len > ETH_FRAME_LEN || len > skb->len) + if (len > ETH_FRAME_LEN || len > skb->len || len < 0) return 0; /* the last packet of current skb */ From 4bc5f1f6bc94e695dfd912122af96e7115a0ddb8 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 15 Jan 2023 11:54:06 +0100 Subject: [PATCH 1072/4345] net: mdio: validate parameter addr in mdiobus_get_phy() [ Upstream commit 867dbe784c5010a466f00a7d1467c1c5ea569c75 ] The caller may pass any value as addr, what may result in an out-of-bounds access to array mdio_map. One existing case is stmmac_init_phy() that may pass -1 as addr. Therefore validate addr before using it. Fixes: 7f854420fbfe ("phy: Add API for {un}registering an mdio device to a bus.") Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/cdf664ea-3312-e915-73f8-021678d08887@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/phy/mdio_bus.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 77ba6c3c7a09..e9303be48655 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -108,7 +108,12 @@ EXPORT_SYMBOL(mdiobus_unregister_device); struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr) { - struct mdio_device *mdiodev = bus->mdio_map[addr]; + struct mdio_device *mdiodev; + + if (addr < 0 || addr >= ARRAY_SIZE(bus->mdio_map)) + return NULL; + + mdiodev = bus->mdio_map[addr]; if (!mdiodev) return NULL; From 5dc3469a1170dd1344d262a332b26994214eeb58 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Mon, 16 Jan 2023 11:11:24 +0000 Subject: [PATCH 1073/4345] HID: check empty report_list in hid_validate_values() [ Upstream commit b12fece4c64857e5fab4290bf01b2e0317a88456 ] Add a check for empty report_list in hid_validate_values(). The missing check causes a type confusion when issuing a list_entry() on an empty report_list. The problem is caused by the assumption that the device must have valid report_list. While this will be true for all normal HID devices, a suitably malicious device can violate the assumption. Fixes: 1b15d2e5b807 ("HID: core: fix validation of report id 0") Signed-off-by: Pietro Borrello Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index eaaf732f0630..baadead947c8 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -988,8 +988,8 @@ struct hid_report *hid_validate_values(struct hid_device *hid, * Validating on id 0 means we should examine the first * report in the list. */ - report = list_entry( - hid->report_enum[type].report_list.next, + report = list_first_entry_or_null( + &hid->report_enum[type].report_list, struct hid_report, list); } else { report = hid->report_enum[type].report_id_hash[id]; From 20fd4598762e2d717deb64ef028e6f5f587ac2a6 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Mon, 16 Jan 2023 11:11:25 +0000 Subject: [PATCH 1074/4345] HID: check empty report_list in bigben_probe() [ Upstream commit c7bf714f875531f227f2ef1fdcc8f4d44e7c7d9d ] Add a check for empty report_list in bigben_probe(). The missing check causes a type confusion when issuing a list_entry() on an empty report_list. The problem is caused by the assumption that the device must have valid report_list. While this will be true for all normal HID devices, a suitably malicious device can violate the assumption. Fixes: 256a90ed9e46 ("HID: hid-bigbenff: driver for BigBen Interactive PS3OFMINIPAD gamepad") Signed-off-by: Pietro Borrello Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-bigbenff.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index e8c5e3ac9fff..e8b16665860d 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -344,6 +344,11 @@ static int bigben_probe(struct hid_device *hid, } report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; + if (list_empty(report_list)) { + hid_err(hid, "no output report found\n"); + error = -ENODEV; + goto error_hw_stop; + } bigben->report = list_entry(report_list->next, struct hid_report, list); From 34f11949938b90f29886579fa3450a0df1ba3a5b Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 15 Jan 2023 18:24:08 +0100 Subject: [PATCH 1075/4345] net: stmmac: fix invalid call to mdiobus_get_phy() [ Upstream commit 1f3bd64ad921f051254591fbed04fd30b306cde6 ] In a number of cases the driver assigns a default value of -1 to priv->plat->phy_addr. This may result in calling mdiobus_get_phy() with addr parameter being -1. Therefore check for this scenario and bail out before calling mdiobus_get_phy(). Fixes: 42e87024f727 ("net: stmmac: Fix case when PHY handle is not present") Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/669f9671-ecd1-a41b-2727-7b73e3003985@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 14ea0168b548..b52ca2fe04d8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1125,6 +1125,11 @@ static int stmmac_init_phy(struct net_device *dev) int addr = priv->plat->phy_addr; struct phy_device *phydev; + if (addr < 0) { + netdev_err(priv->dev, "no phy found\n"); + return -ENODEV; + } + phydev = mdiobus_get_phy(priv->mii, addr); if (!phydev) { netdev_err(priv->dev, "no phy at addr %d\n", addr); From 55be77aa8974ada9c47b7d966592c4d4119785cc Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 17 Jan 2023 15:41:40 +0100 Subject: [PATCH 1076/4345] HID: revert CHERRY_MOUSE_000C quirk [ Upstream commit cbf44580ce6b310272a73e3e794233fd064330bd ] This partially reverts commit f6d910a89a2391 ("HID: usbhid: Add ALWAYS_POLL quirk for some mice"), as it turns out to break reboot on some platforms for reason yet to be understood. Fixes: f6d910a89a2391 ("HID: usbhid: Add ALWAYS_POLL quirk for some mice") Reported-by: Christian Zigotzky Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-ids.h | 1 - drivers/hid/hid-quirks.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 09c3f30f10d3..1d1306a6004e 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -257,7 +257,6 @@ #define USB_DEVICE_ID_CH_AXIS_295 0x001c #define USB_VENDOR_ID_CHERRY 0x046a -#define USB_DEVICE_ID_CHERRY_MOUSE_000C 0x000c #define USB_DEVICE_ID_CHERRY_CYMOTION 0x0023 #define USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR 0x0027 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 1efde40e5136..9f1fcbea19eb 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -54,7 +54,6 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_YOKE), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_THROTTLE), HID_QUIRK_NOGET }, - { HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_MOUSE_000C), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE), HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB), HID_QUIRK_NO_INIT_REPORTS }, From 6dd9ea05534f323668db94fcc2726c7a84547e78 Mon Sep 17 00:00:00 2001 From: Udipto Goswami Date: Thu, 15 Dec 2022 10:59:05 +0530 Subject: [PATCH 1077/4345] usb: gadget: f_fs: Prevent race during ffs_ep0_queue_wait [ Upstream commit 6a19da111057f69214b97c62fb0ac59023970850 ] While performing fast composition switch, there is a possibility that the process of ffs_ep0_write/ffs_ep0_read get into a race condition due to ep0req being freed up from functionfs_unbind. Consider the scenario that the ffs_ep0_write calls the ffs_ep0_queue_wait by taking a lock &ffs->ev.waitq.lock. However, the functionfs_unbind isn't bounded so it can go ahead and mark the ep0req to NULL, and since there is no NULL check in ffs_ep0_queue_wait we will end up in use-after-free. Fix this by making a serialized execution between the two functions using a mutex_lock(ffs->mutex). Fixes: ddf8abd25994 ("USB: f_fs: the FunctionFS driver") Signed-off-by: Udipto Goswami Tested-by: Krishna Kurapati Link: https://lore.kernel.org/r/20221215052906.8993-2-quic_ugoswami@quicinc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/f_fs.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index bb0d92837f67..38942c6d3019 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -278,6 +278,9 @@ static int __ffs_ep0_queue_wait(struct ffs_data *ffs, char *data, size_t len) struct usb_request *req = ffs->ep0req; int ret; + if (!req) + return -EINVAL; + req->zero = len < le16_to_cpu(ffs->ev.setup.wLength); spin_unlock_irq(&ffs->ev.waitq.lock); @@ -1881,10 +1884,12 @@ static void functionfs_unbind(struct ffs_data *ffs) ENTER(); if (!WARN_ON(!ffs->gadget)) { + mutex_lock(&ffs->mutex); usb_ep_free_request(ffs->gadget->ep0, ffs->ep0req); ffs->ep0req = NULL; ffs->gadget = NULL; clear_bit(FFS_FL_BOUND, &ffs->flags); + mutex_unlock(&ffs->mutex); ffs_data_put(ffs); } } From 4b3b5cc1a7dc28992dd728a1ebb2bb9e63a3f6fb Mon Sep 17 00:00:00 2001 From: Udipto Goswami Date: Thu, 15 Dec 2022 10:59:06 +0530 Subject: [PATCH 1078/4345] usb: gadget: f_fs: Ensure ep0req is dequeued before free_request [ Upstream commit ce405d561b020e5a46340eb5146805a625dcacee ] As per the documentation, function usb_ep_free_request guarantees the request will not be queued or no longer be re-queued (or otherwise used). However, with the current implementation it doesn't make sure that the request in ep0 isn't reused. Fix this by dequeuing the ep0req on functionfs_unbind before freeing the request to align with the definition. Fixes: ddf8abd25994 ("USB: f_fs: the FunctionFS driver") Signed-off-by: Udipto Goswami Tested-by: Krishna Kurapati Link: https://lore.kernel.org/r/20221215052906.8993-3-quic_ugoswami@quicinc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/f_fs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 38942c6d3019..94000fd190e5 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1884,6 +1884,8 @@ static void functionfs_unbind(struct ffs_data *ffs) ENTER(); if (!WARN_ON(!ffs->gadget)) { + /* dequeue before freeing ep0req */ + usb_ep_dequeue(ffs->gadget->ep0, ffs->ep0req); mutex_lock(&ffs->mutex); usb_ep_free_request(ffs->gadget->ep0, ffs->ep0req); ffs->ep0req = NULL; From 31f63c62a8e81911c65d83837c75ca81e508aa42 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 30 Aug 2022 20:12:29 -0700 Subject: [PATCH 1079/4345] net: mlx5: eliminate anonymous module_init & module_exit [ Upstream commit 2c1e1b949024989e20907b84e11a731a50778416 ] Eliminate anonymous module_init() and module_exit(), which can lead to confusion or ambiguity when reading System.map, crashes/oops/bugs, or an initcall_debug log. Give each of these init and exit functions unique driver-specific names to eliminate the anonymous names. Example 1: (System.map) ffffffff832fc78c t init ffffffff832fc79e t init ffffffff832fc8f8 t init Example 2: (initcall_debug log) calling init+0x0/0x12 @ 1 initcall init+0x0/0x12 returned 0 after 15 usecs calling init+0x0/0x60 @ 1 initcall init+0x0/0x60 returned 0 after 2 usecs calling init+0x0/0x9a @ 1 initcall init+0x0/0x9a returned 0 after 74 usecs Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Randy Dunlap Cc: Eli Cohen Cc: Saeed Mahameed Cc: Leon Romanovsky Cc: linux-rdma@vger.kernel.org Reviewed-by: Ira Weiny Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 29bc1df28aeb..112eaef186e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1642,7 +1642,7 @@ static void mlx5_core_verify_params(void) } } -static int __init init(void) +static int __init mlx5_init(void) { int err; @@ -1667,7 +1667,7 @@ err_debug: return err; } -static void __exit cleanup(void) +static void __exit mlx5_cleanup(void) { #ifdef CONFIG_MLX5_CORE_EN mlx5e_cleanup(); @@ -1676,5 +1676,5 @@ static void __exit cleanup(void) mlx5_unregister_debugfs(); } -module_init(init); -module_exit(cleanup); +module_init(mlx5_init); +module_exit(mlx5_cleanup); From 1e97e2e08e79a55488876d7d538d0ddb7d0a6552 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Jan 2023 17:44:43 +0100 Subject: [PATCH 1080/4345] drm/panfrost: fix GENERIC_ATOMIC64 dependency [ Upstream commit 6437a549ae178a3f5a5c03e983f291ebcdc2bbc7 ] On ARMv5 and earlier, a randconfig build can still run into WARNING: unmet direct dependencies detected for IOMMU_IO_PGTABLE_LPAE Depends on [n]: IOMMU_SUPPORT [=y] && (ARM [=y] || ARM64 || COMPILE_TEST [=y]) && !GENERIC_ATOMIC64 [=y] Selected by [y]: - DRM_PANFROST [=y] && HAS_IOMEM [=y] && DRM [=y] && (ARM [=y] || ARM64 || COMPILE_TEST [=y] && !GENERIC_ATOMIC64 [=y]) && MMU [=y] Rework the dependencies to always require a working cmpxchg64. Fixes: db594ba3fcf9 ("drm/panfrost: depend on !GENERIC_ATOMIC64 when using COMPILE_TEST") Signed-off-by: Arnd Bergmann Reviewed-by: Steven Price Signed-off-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20230117164456.1591901-1-arnd@kernel.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/panfrost/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panfrost/Kconfig b/drivers/gpu/drm/panfrost/Kconfig index 86cdc0ce79e6..77f4d32e5204 100644 --- a/drivers/gpu/drm/panfrost/Kconfig +++ b/drivers/gpu/drm/panfrost/Kconfig @@ -3,7 +3,8 @@ config DRM_PANFROST tristate "Panfrost (DRM support for ARM Mali Midgard/Bifrost GPUs)" depends on DRM - depends on ARM || ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on ARM || ARM64 || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE depends on MMU select DRM_SCHED select IOMMU_SUPPORT From 42ecd72f02cd657b00b559621e7ef7d2c4d3e5f1 Mon Sep 17 00:00:00 2001 From: Koba Ko Date: Thu, 1 Dec 2022 11:00:50 +0800 Subject: [PATCH 1081/4345] dmaengine: Fix double increment of client_count in dma_chan_get() [ Upstream commit f3dc1b3b4750851a94212dba249703dd0e50bb20 ] The first time dma_chan_get() is called for a channel the channel client_count is incorrectly incremented twice for public channels, first in balance_ref_count(), and again prior to returning. This results in an incorrect client count which will lead to the channel resources not being freed when they should be. A simple test of repeated module load and unload of async_tx on a Dell Power Edge R7425 also shows this resulting in a kref underflow warning. [ 124.329662] async_tx: api initialized (async) [ 129.000627] async_tx: api initialized (async) [ 130.047839] ------------[ cut here ]------------ [ 130.052472] refcount_t: underflow; use-after-free. [ 130.057279] WARNING: CPU: 3 PID: 19364 at lib/refcount.c:28 refcount_warn_saturate+0xba/0x110 [ 130.065811] Modules linked in: async_tx(-) rfkill intel_rapl_msr intel_rapl_common amd64_edac edac_mce_amd ipmi_ssif kvm_amd dcdbas kvm mgag200 drm_shmem_helper acpi_ipmi irqbypass drm_kms_helper ipmi_si syscopyarea sysfillrect rapl pcspkr ipmi_devintf sysimgblt fb_sys_fops k10temp i2c_piix4 ipmi_msghandler acpi_power_meter acpi_cpufreq vfat fat drm fuse xfs libcrc32c sd_mod t10_pi sg ahci crct10dif_pclmul libahci crc32_pclmul crc32c_intel ghash_clmulni_intel igb megaraid_sas i40e libata i2c_algo_bit ccp sp5100_tco dca dm_mirror dm_region_hash dm_log dm_mod [last unloaded: async_tx] [ 130.117361] CPU: 3 PID: 19364 Comm: modprobe Kdump: loaded Not tainted 5.14.0-185.el9.x86_64 #1 [ 130.126091] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.18.0 01/17/2022 [ 130.133806] RIP: 0010:refcount_warn_saturate+0xba/0x110 [ 130.139041] Code: 01 01 e8 6d bd 55 00 0f 0b e9 72 9d 8a 00 80 3d 26 18 9c 01 00 75 85 48 c7 c7 f8 a3 03 9d c6 05 16 18 9c 01 01 e8 4a bd 55 00 <0f> 0b e9 4f 9d 8a 00 80 3d 01 18 9c 01 00 0f 85 5e ff ff ff 48 c7 [ 130.157807] RSP: 0018:ffffbf98898afe68 EFLAGS: 00010286 [ 130.163036] RAX: 0000000000000000 RBX: ffff9da06028e598 RCX: 0000000000000000 [ 130.170172] RDX: ffff9daf9de26480 RSI: ffff9daf9de198a0 RDI: ffff9daf9de198a0 [ 130.177316] RBP: ffff9da7cddf3970 R08: 0000000000000000 R09: 00000000ffff7fff [ 130.184459] R10: ffffbf98898afd00 R11: ffffffff9d9e8c28 R12: ffff9da7cddf1970 [ 130.191596] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 130.198739] FS: 00007f646435c740(0000) GS:ffff9daf9de00000(0000) knlGS:0000000000000000 [ 130.206832] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 130.212586] CR2: 00007f6463b214f0 CR3: 00000008ab98c000 CR4: 00000000003506e0 [ 130.219729] Call Trace: [ 130.222192] [ 130.224305] dma_chan_put+0x10d/0x110 [ 130.227988] dmaengine_put+0x7a/0xa0 [ 130.231575] __do_sys_delete_module.constprop.0+0x178/0x280 [ 130.237157] ? syscall_trace_enter.constprop.0+0x145/0x1d0 [ 130.242652] do_syscall_64+0x5c/0x90 [ 130.246240] ? exc_page_fault+0x62/0x150 [ 130.250178] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 130.255243] RIP: 0033:0x7f6463a3f5ab [ 130.258830] Code: 73 01 c3 48 8b 0d 75 a8 1b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 45 a8 1b 00 f7 d8 64 89 01 48 [ 130.277591] RSP: 002b:00007fff22f972c8 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 [ 130.285164] RAX: ffffffffffffffda RBX: 000055b6786edd40 RCX: 00007f6463a3f5ab [ 130.292303] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 000055b6786edda8 [ 130.299443] RBP: 000055b6786edd40 R08: 0000000000000000 R09: 0000000000000000 [ 130.306584] R10: 00007f6463b9eac0 R11: 0000000000000206 R12: 000055b6786edda8 [ 130.313731] R13: 0000000000000000 R14: 000055b6786edda8 R15: 00007fff22f995f8 [ 130.320875] [ 130.323081] ---[ end trace eff7156d56b5cf25 ]--- cat /sys/class/dma/dma0chan*/in_use would get the wrong result. 2 2 2 Fixes: d2f4f99db3e9 ("dmaengine: Rework dma_chan_get") Signed-off-by: Koba Ko Reviewed-by: Jie Hai Test-by: Jie Hai Reviewed-by: Jerry Snitselaar Reviewed-by: Dave Jiang Tested-by: Joel Savitz Link: https://lore.kernel.org/r/20221201030050.978595-1-koba.ko@canonical.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/dmaengine.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index af3ee288bc11..4ec7bb58c195 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -451,7 +451,8 @@ static int dma_chan_get(struct dma_chan *chan) /* The channel is already in use, update client count */ if (chan->client_count) { __module_get(owner); - goto out; + chan->client_count++; + return 0; } if (!try_module_get(owner)) @@ -470,11 +471,11 @@ static int dma_chan_get(struct dma_chan *chan) goto err_out; } + chan->client_count++; + if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask)) balance_ref_count(chan); -out: - chan->client_count++; return 0; err_out: From f96b2f690887332e02a8994d8bcb6f98b6750539 Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Mon, 16 Jan 2023 15:41:33 -0600 Subject: [PATCH 1082/4345] net: macb: fix PTP TX timestamp failure due to packet padding [ Upstream commit 7b90f5a665acd46efbbfa677a3a3a18d01ad6487 ] PTP TX timestamp handling was observed to be broken with this driver when using the raw Layer 2 PTP encapsulation. ptp4l was not receiving the expected TX timestamp after transmitting a packet, causing it to enter a failure state. The problem appears to be due to the way that the driver pads packets which are smaller than the Ethernet minimum of 60 bytes. If headroom space was available in the SKB, this caused the driver to move the data back to utilize it. However, this appears to cause other data references in the SKB to become inconsistent. In particular, this caused the ptp_one_step_sync function to later (in the TX completion path) falsely detect the packet as a one-step SYNC packet, even when it was not, which caused the TX timestamp to not be processed when it should be. Using the headroom for this purpose seems like an unnecessary complexity as this is not a hot path in the driver, and in most cases it appears that there is sufficient tailroom to not require using the headroom anyway. Remove this usage of headroom to prevent this inconsistency from occurring and causing other problems. Fixes: 653e92a9175e ("net: macb: add support for padding and fcs computation") Signed-off-by: Robert Hancock Reviewed-by: Jacob Keller Tested-by: Claudiu Beznea # on SAMA7G5 Reviewed-by: Claudiu Beznea Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/cadence/macb_main.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 792c8147c2c4..e0d62e251387 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1963,7 +1963,6 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) || skb_is_nonlinear(*skb); int padlen = ETH_ZLEN - (*skb)->len; - int headroom = skb_headroom(*skb); int tailroom = skb_tailroom(*skb); struct sk_buff *nskb; u32 fcs; @@ -1977,9 +1976,6 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) /* FCS could be appeded to tailroom. */ if (tailroom >= ETH_FCS_LEN) goto add_fcs; - /* FCS could be appeded by moving data to headroom. */ - else if (!cloned && headroom + tailroom >= ETH_FCS_LEN) - padlen = 0; /* No room for FCS, need to reallocate skb. */ else padlen = ETH_FCS_LEN; @@ -1988,10 +1984,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) padlen += ETH_FCS_LEN; } - if (!cloned && headroom + tailroom >= padlen) { - (*skb)->data = memmove((*skb)->head, (*skb)->data, (*skb)->len); - skb_set_tail_pointer(*skb, (*skb)->len); - } else { + if (cloned || tailroom < padlen) { nskb = skb_copy_expand(*skb, 0, padlen, GFP_ATOMIC); if (!nskb) return -ENOMEM; From 16791d5a7a9ae5d0010fc751d2da6c57770889f4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Jan 2023 11:01:31 +0000 Subject: [PATCH 1083/4345] l2tp: prevent lockdep issue in l2tp_tunnel_register() [ Upstream commit b9fb10d131b8c84af9bb14e2078d5c63600c7dea ] lockdep complains with the following lock/unlock sequence: lock_sock(sk); write_lock_bh(&sk->sk_callback_lock); [1] release_sock(sk); [2] write_unlock_bh(&sk->sk_callback_lock); We need to swap [1] and [2] to fix this issue. Fixes: 0b2c59720e65 ("l2tp: close all race conditions in l2tp_tunnel_register()") Reported-by: syzbot+bbd35b345c7cab0d9a08@syzkaller.appspotmail.com Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/netdev/20230114030137.672706-1-xiyou.wangcong@gmail.com/T/#m1164ff20628671b0f326a24cb106ab3239c70ce3 Cc: Cong Wang Cc: Guillaume Nault Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/l2tp/l2tp_core.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 386510a93696..a4b793d1b7d7 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1485,10 +1485,8 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, lock_sock(sk); write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); - if (ret < 0) { - release_sock(sk); + if (ret < 0) goto err_inval_sock; - } rcu_assign_sk_user_data(sk, tunnel); write_unlock_bh(&sk->sk_callback_lock); @@ -1525,6 +1523,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, err_inval_sock: write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); if (tunnel->fd < 0) sock_release(sock); From 28fc6095da22dc88433d79578ae1c495ebe8ca43 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Wed, 11 Jan 2023 18:12:16 +0000 Subject: [PATCH 1084/4345] HID: betop: check shape of output reports [ Upstream commit 3782c0d6edf658b71354a64d60aa7a296188fc90 ] betopff_init() only checks the total sum of the report counts for each report field to be at least 4, but hid_betopff_play() expects 4 report fields. A device advertising an output report with one field and 4 report counts would pass the check but crash the kernel with a NULL pointer dereference in hid_betopff_play(). Fixes: 52cd7785f3cd ("HID: betop: add drivers/hid/hid-betopff.c") Signed-off-by: Pietro Borrello Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-betopff.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/hid/hid-betopff.c b/drivers/hid/hid-betopff.c index 467d789f9bc2..25ed7b9a917e 100644 --- a/drivers/hid/hid-betopff.c +++ b/drivers/hid/hid-betopff.c @@ -60,7 +60,6 @@ static int betopff_init(struct hid_device *hid) struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; struct input_dev *dev; - int field_count = 0; int error; int i, j; @@ -86,19 +85,21 @@ static int betopff_init(struct hid_device *hid) * ----------------------------------------- * Do init them with default value. */ + if (report->maxfield < 4) { + hid_err(hid, "not enough fields in the report: %d\n", + report->maxfield); + return -ENODEV; + } for (i = 0; i < report->maxfield; i++) { + if (report->field[i]->report_count < 1) { + hid_err(hid, "no values in the field\n"); + return -ENODEV; + } for (j = 0; j < report->field[i]->report_count; j++) { report->field[i]->value[j] = 0x00; - field_count++; } } - if (field_count < 4) { - hid_err(hid, "not enough fields in the report: %d\n", - field_count); - return -ENODEV; - } - betopff = kzalloc(sizeof(*betopff), GFP_KERNEL); if (!betopff) return -ENOMEM; From 98519ed6911357cafd8572e6945c5e1240bea73f Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Tue, 22 Nov 2022 10:16:12 +0800 Subject: [PATCH 1085/4345] dmaengine: xilinx_dma: call of_node_put() when breaking out of for_each_child_of_node() [ Upstream commit 596b53ccc36a546ab28e8897315c5b4d1d5a0200 ] Since for_each_child_of_node() will increase the refcount of node, we need to call of_node_put() manually when breaking out of the iteration. Fixes: 9cd4360de609 ("dma: Add Xilinx AXI Video Direct Memory Access Engine driver support") Signed-off-by: Liu Shixin Acked-by: Peter Korsgaard Link: https://lore.kernel.org/r/20221122021612.1908866-1-liushixin2@huawei.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/xilinx/xilinx_dma.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index e76adc31ab66..12ad4bb3c5f2 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -3119,8 +3119,10 @@ static int xilinx_dma_probe(struct platform_device *pdev) /* Initialize the channels */ for_each_child_of_node(node, child) { err = xilinx_dma_child_probe(xdev, child); - if (err < 0) + if (err < 0) { + of_node_put(child); goto error; + } } if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) { From 5f10f7efe0fc97c0ee2112a1032914f6fb2f940c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 18 Jan 2023 08:44:16 -0800 Subject: [PATCH 1086/4345] nvme-pci: fix timeout request state check [ Upstream commit 1c5842085851f786eba24a39ecd02650ad892064 ] Polling the completion can progress the request state to IDLE, either inline with the completion, or through softirq. Either way, the state may not be COMPLETED, so don't check for that. We only care if the state isn't IN_FLIGHT. This is fixing an issue where the driver aborts an IO that we just completed. Seeing the "aborting" message instead of "polled" is very misleading as to where the timeout problem resides. Fixes: bf392a5dc02a9b ("nvme-pci: Remove tag from process cq") Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 67dd68462b81..c47512da9872 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1292,7 +1292,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) else nvme_poll_irqdisable(nvmeq); - if (blk_mq_request_completed(req)) { + if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) { dev_warn(dev->ctrl.device, "I/O %d QID %d timeout, completion polled\n", req->tag, nvmeq->qid); From ddf16dae65d386eee5117f42c613422804701aef Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Wed, 18 Jan 2023 09:59:41 +0800 Subject: [PATCH 1087/4345] tcp: avoid the lookup process failing to get sk in ehash table [ Upstream commit 3f4ca5fafc08881d7a57daa20449d171f2887043 ] While one cpu is working on looking up the right socket from ehash table, another cpu is done deleting the request socket and is about to add (or is adding) the big socket from the table. It means that we could miss both of them, even though it has little chance. Let me draw a call trace map of the server side. CPU 0 CPU 1 ----- ----- tcp_v4_rcv() syn_recv_sock() inet_ehash_insert() -> sk_nulls_del_node_init_rcu(osk) __inet_lookup_established() -> __sk_nulls_add_node_rcu(sk, list) Notice that the CPU 0 is receiving the data after the final ack during 3-way shakehands and CPU 1 is still handling the final ack. Why could this be a real problem? This case is happening only when the final ack and the first data receiving by different CPUs. Then the server receiving data with ACK flag tries to search one proper established socket from ehash table, but apparently it fails as my map shows above. After that, the server fetches a listener socket and then sends a RST because it finds a ACK flag in the skb (data), which obeys RST definition in RFC 793. Besides, Eric pointed out there's one more race condition where it handles tw socket hashdance. Only by adding to the tail of the list before deleting the old one can we avoid the race if the reader has already begun the bucket traversal and it would possibly miss the head. Many thanks to Eric for great help from beginning to end. Fixes: 5e0724d027f0 ("tcp/dccp: fix hashdance race for passive sessions") Suggested-by: Eric Dumazet Signed-off-by: Jason Xing Reviewed-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/lkml/20230112065336.41034-1-kerneljasonxing@gmail.com/ Link: https://lore.kernel.org/r/20230118015941.1313-1-kerneljasonxing@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/ipv4/inet_hashtables.c | 17 +++++++++++++++-- net/ipv4/inet_timewait_sock.c | 8 ++++---- 2 files changed, 19 insertions(+), 6 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c68a1dae25ca..2615b72118d1 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -571,8 +571,20 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_nulls_del_node_init_rcu(osk); - } else if (found_dup_sk) { + ret = sk_hashed(osk); + if (ret) { + /* Before deleting the node, we insert a new one to make + * sure that the look-up-sk process would not miss either + * of them and that at least one node would exist in ehash + * table all the time. Otherwise there's a tiny chance + * that lookup process could find nothing in ehash table. + */ + __sk_nulls_add_node_tail_rcu(sk, list); + sk_nulls_del_node_init_rcu(osk); + } + goto unlock; + } + if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -581,6 +593,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); +unlock: spin_unlock(lock); return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c411c87ae865..a00102d7c7fd 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -81,10 +81,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_head_rcu(&tw->tw_node, list); + hlist_nulls_add_tail_rcu(&tw->tw_node, list); } static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -120,7 +120,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); - inet_twsk_add_node_rcu(tw, &ehead->chain); + inet_twsk_add_node_tail_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) From 8e5be0ae5506de89dc9683075cdc855457dfb680 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 5 Dec 2022 16:04:34 +0800 Subject: [PATCH 1088/4345] w1: fix deadloop in __w1_remove_master_device() [ Upstream commit 25d5648802f12ae486076ceca5d7ddf1fef792b2 ] I got a deadloop report while doing device(ds2482) add/remove test: [ 162.241881] w1_master_driver w1_bus_master1: Waiting for w1_bus_master1 to become free: refcnt=1. [ 163.272251] w1_master_driver w1_bus_master1: Waiting for w1_bus_master1 to become free: refcnt=1. [ 164.296157] w1_master_driver w1_bus_master1: Waiting for w1_bus_master1 to become free: refcnt=1. ... __w1_remove_master_device() can't return, because the dev->refcnt is not zero. w1_add_master_device() | w1_alloc_dev() | atomic_set(&dev->refcnt, 2) | kthread_run() | |__w1_remove_master_device() | kthread_stop() // KTHREAD_SHOULD_STOP is set, | // threadfn(w1_process) won't be | // called. | kthread() | | // refcnt will never be 0, it's deadloop. | while (atomic_read(&dev->refcnt)) {...} After calling w1_add_master_device(), w1_process() is not really invoked, before w1_process() starting, if kthread_stop() is called in __w1_remove_master_device(), w1_process() will never be called, the refcnt can not be decreased, then it causes deadloop in remove function because of non-zero refcnt. We need to make sure w1_process() is really started, so move the set refcnt into w1_process() to fix this problem. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221205080434.3149205-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/w1/w1.c | 2 ++ drivers/w1/w1_int.c | 5 ++--- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 15a2ee32f116..6e9f3569971d 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -1131,6 +1131,8 @@ int w1_process(void *data) /* remainder if it woke up early */ unsigned long jremain = 0; + atomic_inc(&dev->refcnt); + for (;;) { if (!jremain && dev->search_count) { diff --git a/drivers/w1/w1_int.c b/drivers/w1/w1_int.c index b3e1792d9c49..3a71c5eb2f83 100644 --- a/drivers/w1/w1_int.c +++ b/drivers/w1/w1_int.c @@ -51,10 +51,9 @@ static struct w1_master *w1_alloc_dev(u32 id, int slave_count, int slave_ttl, dev->search_count = w1_search_count; dev->enable_pullup = w1_enable_pullup; - /* 1 for w1_process to decrement - * 1 for __w1_remove_master_device to decrement + /* For __w1_remove_master_device to decrement */ - atomic_set(&dev->refcnt, 2); + atomic_set(&dev->refcnt, 1); INIT_LIST_HEAD(&dev->slist); INIT_LIST_HEAD(&dev->async_list); From 216f35db6ec6a667cd9db4838d657c1d2f4684da Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 5 Dec 2022 18:15:58 +0800 Subject: [PATCH 1089/4345] w1: fix WARNING after calling w1_process() [ Upstream commit 36225a7c72e9e3e1ce4001b6ce72849f5c9a2d3b ] I got the following WARNING message while removing driver(ds2482): ------------[ cut here ]------------ do not call blocking ops when !TASK_RUNNING; state=1 set at [<000000002d50bfb6>] w1_process+0x9e/0x1d0 [wire] WARNING: CPU: 0 PID: 262 at kernel/sched/core.c:9817 __might_sleep+0x98/0xa0 CPU: 0 PID: 262 Comm: w1_bus_master1 Tainted: G N 6.1.0-rc3+ #307 RIP: 0010:__might_sleep+0x98/0xa0 Call Trace: exit_signals+0x6c/0x550 do_exit+0x2b4/0x17e0 kthread_exit+0x52/0x60 kthread+0x16d/0x1e0 ret_from_fork+0x1f/0x30 The state of task is set to TASK_INTERRUPTIBLE in loop in w1_process(), set it to TASK_RUNNING when it breaks out of the loop to avoid the warning. Fixes: 3c52e4e62789 ("W1: w1_process, block or sleep") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221205101558.3599162-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/w1/w1.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 6e9f3569971d..15842377c8d2 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -1160,8 +1160,10 @@ int w1_process(void *data) */ mutex_unlock(&dev->list_mutex); - if (kthread_should_stop()) + if (kthread_should_stop()) { + __set_current_state(TASK_RUNNING); break; + } /* Only sleep when the search is active. */ if (dev->search_count) { From 704a423c9379a27edf14a88313f1c26ff7a3dc04 Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Fri, 25 Nov 2022 14:35:41 +0800 Subject: [PATCH 1090/4345] driver core: Fix test_async_probe_init saves device in wrong array [ Upstream commit 9be182da0a7526f1b9a3777a336f83baa2e64d23 ] In test_async_probe_init, second set of asynchronous devices are saved in sync_dev[sync_id], which should be async_dev[async_id]. This makes these devices not unregistered when exit. > modprobe test_async_driver_probe && \ > modprobe -r test_async_driver_probe && \ > modprobe test_async_driver_probe ... > sysfs: cannot create duplicate filename '/devices/platform/test_async_driver.4' > kobject_add_internal failed for test_async_driver.4 with -EEXIST, don't try to register things with the same name in the same directory. Fixes: 57ea974fb871 ("driver core: Rewrite test_async_driver_probe to cover serialization and NUMA affinity") Signed-off-by: Chen Zhongjin Link: https://lore.kernel.org/r/20221125063541.241328-1-chenzhongjin@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/base/test/test_async_driver_probe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/test/test_async_driver_probe.c b/drivers/base/test/test_async_driver_probe.c index 3bb7beb127a9..c157a912d673 100644 --- a/drivers/base/test/test_async_driver_probe.c +++ b/drivers/base/test/test_async_driver_probe.c @@ -146,7 +146,7 @@ static int __init test_async_probe_init(void) calltime = ktime_get(); for_each_online_cpu(cpu) { nid = cpu_to_node(cpu); - pdev = &sync_dev[sync_id]; + pdev = &async_dev[async_id]; *pdev = test_platform_device_register_node("test_async_driver", async_id, From a84240df70793d53d43ba8569e399500712c3651 Mon Sep 17 00:00:00 2001 From: Rakesh Sankaranarayanan Date: Wed, 18 Jan 2023 23:17:35 +0530 Subject: [PATCH 1091/4345] net: dsa: microchip: ksz9477: port map correction in ALU table entry register [ Upstream commit 6c977c5c2e4c5d8ad1b604724cc344e38f96fe9b ] ALU table entry 2 register in KSZ9477 have bit positions reserved for forwarding port map. This field is referred in ksz9477_fdb_del() for clearing forward port map and alu table. But current fdb_del refer ALU table entry 3 register for accessing forward port map. Update ksz9477_fdb_del() to get forward port map from correct alu table entry register. With this bug, issue can be observed while deleting static MAC entries. Delete any specific MAC entry using "bridge fdb del" command. This should clear all the specified MAC entries. But it is observed that entries with self static alone are retained. Tested on LAN9370 EVB since ksz9477_fdb_del() is used common across LAN937x and KSZ series. Fixes: b987e98e50ab ("dsa: add DSA switch driver for Microchip KSZ9477") Signed-off-by: Rakesh Sankaranarayanan Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230118174735.702377-1-rakesh.sankaranarayanan@microchip.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/microchip/ksz9477.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index ece4c0512ee2..f42f2f4e4b60 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -678,10 +678,10 @@ static int ksz9477_port_fdb_del(struct dsa_switch *ds, int port, ksz_read32(dev, REG_SW_ALU_VAL_D, &alu_table[3]); /* clear forwarding port */ - alu_table[2] &= ~BIT(port); + alu_table[1] &= ~BIT(port); /* if there is no port to forward, clear table */ - if ((alu_table[2] & ALU_V_PORT_MAP) == 0) { + if ((alu_table[1] & ALU_V_PORT_MAP) == 0) { alu_table[0] = 0; alu_table[1] = 0; alu_table[2] = 0; From d79e700680f9407abc8aa43e7bb758f94ccfecbf Mon Sep 17 00:00:00 2001 From: David Morley Date: Thu, 19 Jan 2023 19:00:28 +0000 Subject: [PATCH 1092/4345] tcp: fix rate_app_limited to default to 1 [ Upstream commit 300b655db1b5152d6101bcb6801d50899b20c2d6 ] The initial default value of 0 for tp->rate_app_limited was incorrect, since a flow is indeed application-limited until it first sends data. Fixing the default to be 1 is generally correct but also specifically will help user-space applications avoid using the initial tcpi_delivery_rate value of 0 that persists until the connection has some non-zero bandwidth sample. Fixes: eb8329e0a04d ("tcp: export data delivery rate") Suggested-by: Yuchung Cheng Signed-off-by: David Morley Signed-off-by: Neal Cardwell Tested-by: David Morley Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cc588bc2b11d..6a0560a735ce 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -432,6 +432,7 @@ void tcp_init_sock(struct sock *sk) /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; + tp->rate_app_limited = 1; /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. @@ -2837,6 +2838,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->last_oow_ack_time = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; + tp->rate_app_limited = 1; tp->rack.mstamp = 0; tp->rack.advanced = 0; tp->rack.reo_wnd_steps = 1; From 6bc564f3fec0a8ae4a26ec43a21001a2742d5d2e Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Sat, 26 Nov 2022 09:07:52 +0800 Subject: [PATCH 1093/4345] scsi: iscsi: Fix multiple iSCSI session unbind events sent to userspace [ Upstream commit a3be19b91ea7121d388084e8c07f5b1b982eb40c ] It was observed that the kernel would potentially send ISCSI_KEVENT_UNBIND_SESSION multiple times. Introduce 'target_state' in iscsi_cls_session() to make sure session will send only one unbind session event. This introduces a regression wrt. the issue fixed in commit 13e60d3ba287 ("scsi: iscsi: Report unbind session event when the target has been removed"). If iscsid dies for any reason after sending an unbind session to kernel, once iscsid is restarted, the kernel's ISCSI_KEVENT_UNBIND_SESSION event is lost and userspace is then unable to logout. However, the session is actually in invalid state (its target_id is INVALID) so iscsid should not sync this session during restart. Consequently we need to check the session's target state during iscsid restart. If session is in unbound state, do not sync this session and perform session teardown. This is OK because once a session is unbound, we can not recover it any more (mainly because its target id is INVALID). Signed-off-by: Wenchao Hao Link: https://lore.kernel.org/r/20221126010752.231917-1-haowenchao@huawei.com Reviewed-by: Mike Christie Reviewed-by: Wu Bo Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_transport_iscsi.c | 50 ++++++++++++++++++++++++++--- include/scsi/scsi_transport_iscsi.h | 9 ++++++ 2 files changed, 54 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index ef7cd7520e7c..092bd6a3d64a 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -1674,6 +1674,13 @@ static const char *iscsi_session_state_name(int state) return name; } +static char *iscsi_session_target_state_name[] = { + [ISCSI_SESSION_TARGET_UNBOUND] = "UNBOUND", + [ISCSI_SESSION_TARGET_ALLOCATED] = "ALLOCATED", + [ISCSI_SESSION_TARGET_SCANNED] = "SCANNED", + [ISCSI_SESSION_TARGET_UNBINDING] = "UNBINDING", +}; + int iscsi_session_chkready(struct iscsi_cls_session *session) { unsigned long flags; @@ -1805,9 +1812,13 @@ static int iscsi_user_scan_session(struct device *dev, void *data) if ((scan_data->channel == SCAN_WILD_CARD || scan_data->channel == 0) && (scan_data->id == SCAN_WILD_CARD || - scan_data->id == id)) + scan_data->id == id)) { scsi_scan_target(&session->dev, 0, id, scan_data->lun, scan_data->rescan); + spin_lock_irqsave(&session->lock, flags); + session->target_state = ISCSI_SESSION_TARGET_SCANNED; + spin_unlock_irqrestore(&session->lock, flags); + } } user_scan_exit: @@ -1996,31 +2007,41 @@ static void __iscsi_unbind_session(struct work_struct *work) struct iscsi_cls_host *ihost = shost->shost_data; unsigned long flags; unsigned int target_id; + bool remove_target = true; ISCSI_DBG_TRANS_SESSION(session, "Unbinding session\n"); /* Prevent new scans and make sure scanning is not in progress */ mutex_lock(&ihost->mutex); spin_lock_irqsave(&session->lock, flags); - if (session->target_id == ISCSI_MAX_TARGET) { + if (session->target_state == ISCSI_SESSION_TARGET_ALLOCATED) { + remove_target = false; + } else if (session->target_state != ISCSI_SESSION_TARGET_SCANNED) { spin_unlock_irqrestore(&session->lock, flags); mutex_unlock(&ihost->mutex); - goto unbind_session_exit; + ISCSI_DBG_TRANS_SESSION(session, + "Skipping target unbinding: Session is unbound/unbinding.\n"); + return; } + session->target_state = ISCSI_SESSION_TARGET_UNBINDING; target_id = session->target_id; session->target_id = ISCSI_MAX_TARGET; spin_unlock_irqrestore(&session->lock, flags); mutex_unlock(&ihost->mutex); - scsi_remove_target(&session->dev); + if (remove_target) + scsi_remove_target(&session->dev); if (session->ida_used) ida_simple_remove(&iscsi_sess_ida, target_id); -unbind_session_exit: iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION); ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n"); + + spin_lock_irqsave(&session->lock, flags); + session->target_state = ISCSI_SESSION_TARGET_UNBOUND; + spin_unlock_irqrestore(&session->lock, flags); } static void __iscsi_destroy_session(struct work_struct *work) @@ -2089,6 +2110,9 @@ int iscsi_add_session(struct iscsi_cls_session *session, unsigned int target_id) session->ida_used = true; } else session->target_id = target_id; + spin_lock_irqsave(&session->lock, flags); + session->target_state = ISCSI_SESSION_TARGET_ALLOCATED; + spin_unlock_irqrestore(&session->lock, flags); dev_set_name(&session->dev, "session%u", session->sid); err = device_add(&session->dev); @@ -4343,6 +4367,19 @@ iscsi_session_attr(def_taskmgmt_tmo, ISCSI_PARAM_DEF_TASKMGMT_TMO, 0); iscsi_session_attr(discovery_parent_idx, ISCSI_PARAM_DISCOVERY_PARENT_IDX, 0); iscsi_session_attr(discovery_parent_type, ISCSI_PARAM_DISCOVERY_PARENT_TYPE, 0); +static ssize_t +show_priv_session_target_state(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct iscsi_cls_session *session = iscsi_dev_to_session(dev->parent); + + return sysfs_emit(buf, "%s\n", + iscsi_session_target_state_name[session->target_state]); +} + +static ISCSI_CLASS_ATTR(priv_sess, target_state, S_IRUGO, + show_priv_session_target_state, NULL); + static ssize_t show_priv_session_state(struct device *dev, struct device_attribute *attr, char *buf) @@ -4445,6 +4482,7 @@ static struct attribute *iscsi_session_attrs[] = { &dev_attr_sess_boot_target.attr, &dev_attr_priv_sess_recovery_tmo.attr, &dev_attr_priv_sess_state.attr, + &dev_attr_priv_sess_target_state.attr, &dev_attr_priv_sess_creator.attr, &dev_attr_sess_chap_out_idx.attr, &dev_attr_sess_chap_in_idx.attr, @@ -4558,6 +4596,8 @@ static umode_t iscsi_session_attr_is_visible(struct kobject *kobj, return S_IRUGO | S_IWUSR; else if (attr == &dev_attr_priv_sess_state.attr) return S_IRUGO; + else if (attr == &dev_attr_priv_sess_target_state.attr) + return S_IRUGO; else if (attr == &dev_attr_priv_sess_creator.attr) return S_IRUGO; else if (attr == &dev_attr_priv_sess_target_id.attr) diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 037c77fb5dc5..c4de15f7a0a5 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -236,6 +236,14 @@ enum { ISCSI_SESSION_FREE, }; +enum { + ISCSI_SESSION_TARGET_UNBOUND, + ISCSI_SESSION_TARGET_ALLOCATED, + ISCSI_SESSION_TARGET_SCANNED, + ISCSI_SESSION_TARGET_UNBINDING, + ISCSI_SESSION_TARGET_MAX, +}; + #define ISCSI_MAX_TARGET -1 struct iscsi_cls_session { @@ -262,6 +270,7 @@ struct iscsi_cls_session { */ pid_t creator; int state; + int target_state; /* session target bind state */ int sid; /* session id */ void *dd_data; /* LLD private data */ struct device dev; /* sysfs transport/container device */ From b75e9fc402c404f704e20fb7ae535a2e06ab9f5f Mon Sep 17 00:00:00 2001 From: Sumit Gupta Date: Tue, 20 Dec 2022 21:32:37 +0530 Subject: [PATCH 1094/4345] cpufreq: Add Tegra234 to cpufreq-dt-platdev blocklist [ Upstream commit 01c5bb0cc2a39fbc56ff9a5ef28b79447f0c2351 ] Tegra234 platform uses the tegra194-cpufreq driver, so add it to the blocklist in cpufreq-dt-platdev driver to avoid the cpufreq driver registration from there. Signed-off-by: Sumit Gupta Signed-off-by: Viresh Kumar Signed-off-by: Sasha Levin --- drivers/cpufreq/cpufreq-dt-platdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index a3734014db47..aea285651fba 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -130,6 +130,7 @@ static const struct of_device_id blacklist[] __initconst = { { .compatible = "nvidia,tegra30", }, { .compatible = "nvidia,tegra124", }, { .compatible = "nvidia,tegra210", }, + { .compatible = "nvidia,tegra234", }, { .compatible = "qcom,apq8096", }, { .compatible = "qcom,msm8996", }, From 3b154d5204ff8aa82a2bd4d5ed29a7cf80723706 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Thu, 22 Dec 2022 23:28:21 -0800 Subject: [PATCH 1095/4345] kcsan: test: don't put the expect array on the stack [ Upstream commit 5b24ac2dfd3eb3e36f794af3aa7f2828b19035bd ] Size of the 'expect' array in the __report_matches is 1536 bytes, which is exactly the default frame size warning limit of the xtensa architecture. As a result allmodconfig xtensa kernel builds with the gcc that does not support the compiler plugins (which otherwise would push the said warning limit to 2K) fail with the following message: kernel/kcsan/kcsan_test.c:257:1: error: the frame size of 1680 bytes is larger than 1536 bytes Fix it by dynamically allocating the 'expect' array. Signed-off-by: Max Filippov Reviewed-by: Marco Elver Tested-by: Marco Elver Signed-off-by: Sasha Levin --- kernel/kcsan/kcsan-test.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/kcsan/kcsan-test.c b/kernel/kcsan/kcsan-test.c index ebe7fd245104..8a8ccaf4f38f 100644 --- a/kernel/kcsan/kcsan-test.c +++ b/kernel/kcsan/kcsan-test.c @@ -149,7 +149,7 @@ static bool report_matches(const struct expect_report *r) const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT; bool ret = false; unsigned long flags; - typeof(observed.lines) expect; + typeof(*observed.lines) *expect; const char *end; char *cur; int i; @@ -158,6 +158,10 @@ static bool report_matches(const struct expect_report *r) if (!report_available()) return false; + expect = kmalloc(sizeof(observed.lines), GFP_KERNEL); + if (WARN_ON(!expect)) + return false; + /* Generate expected report contents. */ /* Title */ @@ -241,6 +245,7 @@ static bool report_matches(const struct expect_report *r) strstr(observed.lines[2], expect[1]))); out: spin_unlock_irqrestore(&observed.lock, flags); + kfree(expect); return ret; } From 96f4899a3810053f45779e59cfe4b161f6a69c3d Mon Sep 17 00:00:00 2001 From: Chancel Liu Date: Wed, 4 Jan 2023 10:57:54 +0800 Subject: [PATCH 1096/4345] ASoC: fsl_micfil: Correct the number of steps on SX controls [ Upstream commit cdfa92eb90f5770b26a79824ef213ebdbbd988b1 ] The parameter "max" of SOC_SINGLE_SX_TLV() means the number of steps rather than maximum value. This patch corrects the minimum value to -8 and the number of steps to 15. Signed-off-by: Chancel Liu Acked-by: Shengjiu Wang Link: https://lore.kernel.org/r/20230104025754.3019235-1-chancel.liu@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_micfil.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 6c794605e33c..97f83c63e765 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -87,21 +87,21 @@ static DECLARE_TLV_DB_SCALE(gain_tlv, 0, 100, 0); static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = { SOC_SINGLE_SX_TLV("CH0 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(0), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(0), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH1 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(1), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(1), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH2 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(2), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(2), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH3 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(3), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(3), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH4 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(4), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(4), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH5 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(5), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(5), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH6 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(6), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(6), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH7 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(7), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(7), 0x8, 0xF, gain_tlv), SOC_ENUM_EXT("MICFIL Quality Select", fsl_micfil_quality_enum, snd_soc_get_enum_double, snd_soc_put_enum_double), From ae108a5fc9298ba273df4a070b07392e852a481f Mon Sep 17 00:00:00 2001 From: Patrick Thompson Date: Tue, 20 Dec 2022 15:58:26 -0500 Subject: [PATCH 1097/4345] drm: Add orientation quirk for Lenovo ideapad D330-10IGL [ Upstream commit 0688773f0710528e1ab302c3d6317e269f2e2e6e ] Panel is 800x1280 but mounted on a detachable form factor sideways. Signed-off-by: Patrick Thompson Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20221220205826.178008-1-ptf@google.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_panel_orientation_quirks.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index ca0fefeaab20..ce739ba45c55 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -272,6 +272,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGM"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Lenovo Ideapad D330-10IGL (HD) */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGL"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* Lenovo Yoga Book X90F / X91F / X91L */ .matches = { /* Non exact match to match all versions */ From 2ca345d19cbd694ed9ea086e5b69289c22750a20 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 3 Jan 2023 15:11:07 +0100 Subject: [PATCH 1098/4345] s390/debug: add _ASM_S390_ prefix to header guard [ Upstream commit 0d4d52361b6c29bf771acd4fa461f06d78fb2fac ] Using DEBUG_H without a prefix is very generic and inconsistent with other header guards in arch/s390/include/asm. In fact it collides with the same name in the ath9k wireless driver though that depends on !S390 via disabled wireless support. Let's just use a consistent header guard name and prevent possible future trouble. Signed-off-by: Niklas Schnelle Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- arch/s390/include/asm/debug.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index c1b82bcc017c..29a1badbe2f5 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -4,8 +4,8 @@ * * Copyright IBM Corp. 1999, 2020 */ -#ifndef DEBUG_H -#define DEBUG_H +#ifndef _ASM_S390_DEBUG_H +#define _ASM_S390_DEBUG_H #include #include @@ -425,4 +425,4 @@ int debug_unregister_view(debug_info_t *id, struct debug_view *view); #define PRINT_FATAL(x...) printk(KERN_DEBUG PRINTK_HEADER x) #endif /* DASD_DEBUG */ -#endif /* DEBUG_H */ +#endif /* _ASM_S390_DEBUG_H */ From 00f23016118781f85d7ffda2dccf9a43de6f1c98 Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Tue, 10 Jan 2023 11:12:52 +0800 Subject: [PATCH 1099/4345] cpufreq: armada-37xx: stop using 0 as NULL pointer [ Upstream commit 08f0adb193c008de640fde34a2e00a666c01d77c ] Use NULL for NULL pointer to fix the following sparse warning: drivers/cpufreq/armada-37xx-cpufreq.c:448:32: sparse: warning: Using plain integer as NULL pointer Signed-off-by: Miles Chen Signed-off-by: Viresh Kumar Signed-off-by: Sasha Levin --- drivers/cpufreq/armada-37xx-cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c index 2de7fd18f66a..f0be8a43ec49 100644 --- a/drivers/cpufreq/armada-37xx-cpufreq.c +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -443,7 +443,7 @@ static int __init armada37xx_cpufreq_driver_init(void) return -ENODEV; } - clk = clk_get(cpu_dev, 0); + clk = clk_get(cpu_dev, NULL); if (IS_ERR(clk)) { dev_err(cpu_dev, "Cannot get clock for CPU0\n"); return PTR_ERR(clk); From d9a0752a6a1126e30dc4c68f310b4a5050518583 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 6 Jan 2023 23:15:06 +0000 Subject: [PATCH 1100/4345] ASoC: fsl_ssi: Rename AC'97 streams to avoid collisions with AC'97 CODEC [ Upstream commit 8c6a42b5b0ed6f96624f56954e93eeae107440a6 ] The SSI driver calls the AC'97 playback and transmit streams "AC97 Playback" and "AC97 Capture" respectively. This is the same name used by the generic AC'97 CODEC driver in ASoC, creating confusion for the Freescale ASoC card when it attempts to use these widgets in routing. Add a "CPU" in the name like the regular DAIs registered by the driver to disambiguate. Acked-by: Shengjiu Wang Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20230106-asoc-udoo-probe-v1-1-a5d7469d4f67@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl-asoc-card.c | 8 ++++---- sound/soc/fsl/fsl_ssi.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index 7cd14d6b9436..8c976fde44f0 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -117,11 +117,11 @@ static const struct snd_soc_dapm_route audio_map[] = { static const struct snd_soc_dapm_route audio_map_ac97[] = { /* 1st half -- Normal DAPM routes */ - {"Playback", NULL, "AC97 Playback"}, - {"AC97 Capture", NULL, "Capture"}, + {"Playback", NULL, "CPU AC97 Playback"}, + {"CPU AC97 Capture", NULL, "Capture"}, /* 2nd half -- ASRC DAPM routes */ - {"AC97 Playback", NULL, "ASRC-Playback"}, - {"ASRC-Capture", NULL, "AC97 Capture"}, + {"CPU AC97 Playback", NULL, "ASRC-Playback"}, + {"ASRC-Capture", NULL, "CPU AC97 Capture"}, }; static const struct snd_soc_dapm_route audio_map_tx[] = { diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index 1d774c876c52..94229ce1a30e 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -1161,14 +1161,14 @@ static struct snd_soc_dai_driver fsl_ssi_ac97_dai = { .symmetric_channels = 1, .probe = fsl_ssi_dai_probe, .playback = { - .stream_name = "AC97 Playback", + .stream_name = "CPU AC97 Playback", .channels_min = 2, .channels_max = 2, .rates = SNDRV_PCM_RATE_8000_48000, .formats = SNDRV_PCM_FMTBIT_S16 | SNDRV_PCM_FMTBIT_S20, }, .capture = { - .stream_name = "AC97 Capture", + .stream_name = "CPU AC97 Capture", .channels_min = 2, .channels_max = 2, .rates = SNDRV_PCM_RATE_48000, From a84def9b108a44bba2d6afc800302f977738f94f Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 6 Jan 2023 23:15:07 +0000 Subject: [PATCH 1101/4345] ASoC: fsl-asoc-card: Fix naming of AC'97 CODEC widgets [ Upstream commit 242fc66ae6e1e2b8519daacc7590a73cd0e8a6e4 ] The fsl-asoc-card AC'97 support currently tries to route to Playback and Capture widgets provided by the AC'97 CODEC. This doesn't work since the generic AC'97 driver registers with an "AC97" at the front of the stream and hence widget names, update to reflect reality. It's not clear to me if or how this ever worked. Acked-by: Shengjiu Wang Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20230106-asoc-udoo-probe-v1-2-a5d7469d4f67@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl-asoc-card.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index 8c976fde44f0..9a756d0a6032 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -117,8 +117,8 @@ static const struct snd_soc_dapm_route audio_map[] = { static const struct snd_soc_dapm_route audio_map_ac97[] = { /* 1st half -- Normal DAPM routes */ - {"Playback", NULL, "CPU AC97 Playback"}, - {"CPU AC97 Capture", NULL, "Capture"}, + {"AC97 Playback", NULL, "CPU AC97 Playback"}, + {"CPU AC97 Capture", NULL, "AC97 Capture"}, /* 2nd half -- ASRC DAPM routes */ {"CPU AC97 Playback", NULL, "ASRC-Playback"}, {"ASRC-Capture", NULL, "CPU AC97 Capture"}, From 300da569a12808adb7acd0dc798f0437a8423fa7 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 6 Jan 2023 11:07:19 +0100 Subject: [PATCH 1102/4345] spi: spidev: remove debug messages that access spidev->spi without locking [ Upstream commit 6b35b173dbc1711f8d272e3f322d2ad697015919 ] The two debug messages in spidev_open() dereference spidev->spi without taking the lock and without checking if it's not null. This can lead to a crash. Drop the messages as they're not needed - the user-space will get informed about ENOMEM with the syscall return value. Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20230106100719.196243-2-brgl@bgdev.pl Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spidev.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 9c5ec99431d2..aee960a7d7f9 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -592,7 +592,6 @@ static int spidev_open(struct inode *inode, struct file *filp) if (!spidev->tx_buffer) { spidev->tx_buffer = kmalloc(bufsiz, GFP_KERNEL); if (!spidev->tx_buffer) { - dev_dbg(&spidev->spi->dev, "open/ENOMEM\n"); status = -ENOMEM; goto err_find_dev; } @@ -601,7 +600,6 @@ static int spidev_open(struct inode *inode, struct file *filp) if (!spidev->rx_buffer) { spidev->rx_buffer = kmalloc(bufsiz, GFP_KERNEL); if (!spidev->rx_buffer) { - dev_dbg(&spidev->spi->dev, "open/ENOMEM\n"); status = -ENOMEM; goto err_alloc_rx_buf; } From 71bd134c4e9e2a12f4e210badb0b253dfee3712d Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 9 Jan 2023 15:54:56 +0100 Subject: [PATCH 1103/4345] KVM: s390: interrupt: use READ_ONCE() before cmpxchg() [ Upstream commit 42400d99e9f0728c17240edb9645637ead40f6b9 ] Use READ_ONCE() before cmpxchg() to prevent that the compiler generates code that fetches the to be compared old value several times from memory. Reviewed-by: Christian Borntraeger Acked-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20230109145456.2895385-1-hca@linux.ibm.com Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- arch/s390/kvm/interrupt.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index b51ab19eb972..64d1dfe6dca5 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -81,8 +81,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union esca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -93,8 +94,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union bsca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -124,16 +126,18 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl old = *sigp_ctrl; + union esca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } else { struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl old = *sigp_ctrl; + union bsca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } From 52249c2168af44f56a7fd914661599a0d1409a6e Mon Sep 17 00:00:00 2001 From: Yihang Li Date: Wed, 4 Jan 2023 12:03:20 +0800 Subject: [PATCH 1104/4345] scsi: hisi_sas: Set a port invalid only if there are no devices attached when refreshing port id [ Upstream commit f58c89700630da6554b24fd3df293a24874c10c1 ] Currently the driver sets the port invalid if one phy in the port is not enabled, which may cause issues in expander situation. In directly attached situation, if phy up doesn't occur in time when refreshing port id, the port is incorrectly set to invalid which will also cause disk lost. Therefore set a port invalid only if there are no devices attached to the port. Signed-off-by: Yihang Li Signed-off-by: Xiang Chen Link: https://lore.kernel.org/r/1672805000-141102-3-git-send-email-chenxiang66@hisilicon.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hisi_sas/hisi_sas_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 1feca45384c7..e5b9229310a0 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1408,7 +1408,7 @@ static void hisi_sas_refresh_port_id(struct hisi_hba *hisi_hba) device->linkrate = phy->sas_phy.linkrate; hisi_hba->hw->setup_itct(hisi_hba, sas_dev); - } else + } else if (!port->port_attached) port->id = 0xff; } } From 9968f9a86251d697c223031be2ae3d3f11eb0fd9 Mon Sep 17 00:00:00 2001 From: Michael Klein Date: Tue, 20 Dec 2022 13:11:03 +0100 Subject: [PATCH 1105/4345] platform/x86: touchscreen_dmi: Add info for the CSL Panther Tab HD [ Upstream commit 36c2b9d6710427f802494ba070621cb415198293 ] Add touchscreen info for the CSL Panther Tab HD. Signed-off-by: Michael Klein Link: https://lore.kernel.org/r/20221220121103.uiwn5l7fii2iggct@LLGMVZLB-0037 Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/touchscreen_dmi.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 110ff1e6ef81..bc26acace2c3 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -255,6 +255,23 @@ static const struct ts_dmi_data connect_tablet9_data = { .properties = connect_tablet9_props, }; +static const struct property_entry csl_panther_tab_hd_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 1), + PROPERTY_ENTRY_U32("touchscreen-min-y", 20), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1526), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-csl-panther-tab-hd.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data csl_panther_tab_hd_data = { + .acpi_name = "MSSL1680:00", + .properties = csl_panther_tab_hd_props, +}; + static const struct property_entry cube_iwork8_air_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 1), PROPERTY_ENTRY_U32("touchscreen-min-y", 3), @@ -1057,6 +1074,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Tablet 9"), }, }, + { + /* CSL Panther Tab HD */ + .driver_data = (void *)&csl_panther_tab_hd_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "CSL Computer GmbH & Co. KG"), + DMI_MATCH(DMI_PRODUCT_NAME, "CSL Panther Tab HD"), + }, + }, { /* CUBE iwork8 Air */ .driver_data = (void *)&cube_iwork8_air_data, From f8ddf7dbf5e79fd3a5e890b6e45e9c51d6397a9e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 12 Jan 2023 19:18:41 +0100 Subject: [PATCH 1106/4345] platform/x86: asus-nb-wmi: Add alternate mapping for KEY_SCREENLOCK [ Upstream commit db9494895b405bf318dc7e563dee6daa51b3b6ed ] The 0x33 keycode is emitted by Fn + F6 on a ASUS FX705GE laptop. Reported-by: Nemcev Aleksey Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230112181841.84652-1-hdegoede@redhat.com Signed-off-by: Sasha Levin --- drivers/platform/x86/asus-nb-wmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 949ddeb673bc..74637bd0433e 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -478,6 +478,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x30, { KEY_VOLUMEUP } }, { KE_KEY, 0x31, { KEY_VOLUMEDOWN } }, { KE_KEY, 0x32, { KEY_MUTE } }, + { KE_KEY, 0x33, { KEY_SCREENLOCK } }, { KE_KEY, 0x35, { KEY_SCREENLOCK } }, { KE_KEY, 0x40, { KEY_PREVIOUSSONG } }, { KE_KEY, 0x41, { KEY_NEXTSONG } }, From 20a02bc845083abe5c7406caa9c6408ab0b2cc76 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Fri, 13 Jan 2023 19:44:47 +0100 Subject: [PATCH 1107/4345] lockref: stop doing cpu_relax in the cmpxchg loop [ Upstream commit f5fe24ef17b5fbe6db49534163e77499fb10ae8c ] On the x86-64 architecture even a failing cmpxchg grants exclusive access to the cacheline, making it preferable to retry the failed op immediately instead of stalling with the pause instruction. To illustrate the impact, below are benchmark results obtained by running various will-it-scale tests on top of the 6.2-rc3 kernel and Cascade Lake (2 sockets * 24 cores * 2 threads) CPU. All results in ops/s. Note there is some variance in re-runs, but the code is consistently faster when contention is present. open3 ("Same file open/close"): proc stock no-pause 1 805603 814942 (+%1) 2 1054980 1054781 (-0%) 8 1544802 1822858 (+18%) 24 1191064 2199665 (+84%) 48 851582 1469860 (+72%) 96 609481 1427170 (+134%) fstat2 ("Same file fstat"): proc stock no-pause 1 3013872 3047636 (+1%) 2 4284687 4400421 (+2%) 8 3257721 5530156 (+69%) 24 2239819 5466127 (+144%) 48 1701072 5256609 (+209%) 96 1269157 6649326 (+423%) Additionally, a kernel with a private patch to help access() scalability: access2 ("Same file access"): proc stock patched patched +nopause 24 2378041 2005501 5370335 (-15% / +125%) That is, fixing the problems in access itself *reduces* scalability after the cacheline ping-pong only happens in lockref with the pause instruction. Note that fstat and access benchmarks are not currently integrated into will-it-scale, but interested parties can find them in pull requests to said project. Code at hand has a rather tortured history. First modification showed up in commit d472d9d98b46 ("lockref: Relax in cmpxchg loop"), written with Itanium in mind. Later it got patched up to use an arch-dependent macro to stop doing it on s390 where it caused a significant regression. Said macro had undergone revisions and was ultimately eliminated later, going back to cpu_relax. While I intended to only remove cpu_relax for x86-64, I got the following comment from Linus: I would actually prefer just removing it entirely and see if somebody else hollers. You have the numbers to prove it hurts on real hardware, and I don't think we have any numbers to the contrary. So I think it's better to trust the numbers and remove it as a failure, than say "let's just remove it on x86-64 and leave everybody else with the potentially broken code" Additionally, Will Deacon (maintainer of the arm64 port, one of the architectures previously benchmarked): So, from the arm64 side of the fence, I'm perfectly happy just removing the cpu_relax() calls from lockref. As such, come back full circle in history and whack it altogether. Signed-off-by: Mateusz Guzik Link: https://lore.kernel.org/all/CAGudoHHx0Nqg6DE70zAVA75eV-HXfWyhVMWZ-aSeOofkA_=WdA@mail.gmail.com/ Acked-by: Tony Luck # ia64 Acked-by: Nicholas Piggin # powerpc Acked-by: Will Deacon # arm64 Acked-by: Peter Zijlstra Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- lib/lockref.c | 1 - 1 file changed, 1 deletion(-) diff --git a/lib/lockref.c b/lib/lockref.c index 5b34bbd3eba8..81ac5f355242 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -24,7 +24,6 @@ } \ if (!--retry) \ break; \ - cpu_relax(); \ } \ } while (0) From a7345145e7bdd7cfc4359e16a23ebde846c8ebf9 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Tue, 24 Jan 2023 07:02:31 -0500 Subject: [PATCH 1108/4345] Revert "selftests/bpf: check null propagation only neither reg is PTR_TO_BTF_ID" This reverts commit 3093027183f2846365a76b2fb1e1309f1960084a. Signed-off-by: Sasha Levin --- .../bpf/prog_tests/jeq_infer_not_null.c | 9 ---- .../bpf/progs/jeq_infer_not_null_fail.c | 42 ------------------- 2 files changed, 51 deletions(-) delete mode 100644 tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c delete mode 100644 tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c diff --git a/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c b/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c deleted file mode 100644 index 3add34df5767..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c +++ /dev/null @@ -1,9 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include -#include "jeq_infer_not_null_fail.skel.h" - -void test_jeq_infer_not_null(void) -{ - RUN_TESTS(jeq_infer_not_null_fail); -} diff --git a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c deleted file mode 100644 index f46965053acb..000000000000 --- a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c +++ /dev/null @@ -1,42 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include "vmlinux.h" -#include -#include "bpf_misc.h" - -char _license[] SEC("license") = "GPL"; - -struct { - __uint(type, BPF_MAP_TYPE_HASH); - __uint(max_entries, 1); - __type(key, u64); - __type(value, u64); -} m_hash SEC(".maps"); - -SEC("?raw_tp") -__failure __msg("R8 invalid mem access 'map_value_or_null") -int jeq_infer_not_null_ptr_to_btfid(void *ctx) -{ - struct bpf_map *map = (struct bpf_map *)&m_hash; - struct bpf_map *inner_map = map->inner_map_meta; - u64 key = 0, ret = 0, *val; - - val = bpf_map_lookup_elem(map, &key); - /* Do not mark ptr as non-null if one of them is - * PTR_TO_BTF_ID (R9), reject because of invalid - * access to map value (R8). - * - * Here, we need to inline those insns to access - * R8 directly, since compiler may use other reg - * once it figures out val==inner_map. - */ - asm volatile("r8 = %[val];\n" - "r9 = %[inner_map];\n" - "if r8 != r9 goto +1;\n" - "%[ret] = *(u64 *)(r8 +0);\n" - : [ret] "+r"(ret) - : [inner_map] "r"(inner_map), [val] "r"(val) - : "r8", "r9"); - - return ret; -} From 5fb884d748e438f87ecca4694933a4fae3efe34b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 24 Jun 2021 12:36:42 +0200 Subject: [PATCH 1109/4345] netfilter: conntrack: do not renew entry stuck in tcp SYN_SENT state [ Upstream commit e15d4cdf27cb0c1e977270270b2cea12e0955edd ] Consider: client -----> conntrack ---> Host client sends a SYN, but $Host is unreachable/silent. Client eventually gives up and the conntrack entry will time out. However, if the client is restarted with same addr/port pair, it may prevent the conntrack entry from timing out. This is noticeable when the existing conntrack entry has no NAT transformation or an outdated one and port reuse happens either on client or due to a NAT middlebox. This change prevents refresh of the timeout for SYN retransmits, so entry is going away after nf_conntrack_tcp_timeout_syn_sent seconds (default: 60). Entry will be re-created on next connection attempt, but then nat rules will be evaluated again. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_proto_tcp.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3f785bdfa942..c1d02c0b4f00 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1158,6 +1158,16 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } + + if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) { + /* do not renew timeout on SYN retransmit. + * + * Else port reuse by client or NAT middlebox can keep + * entry alive indefinitely (including nat info). + */ + return NF_ACCEPT; + } + /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection * pickup with loose=1. Avoid large ESTABLISHED timeout. */ From 1f6768143bf76cdad9ec83b25929bab061df48ec Mon Sep 17 00:00:00 2001 From: Deepak Sharma Date: Thu, 23 Sep 2021 23:12:05 -0700 Subject: [PATCH 1110/4345] x86: ACPI: cstate: Optimize C3 entry on AMD CPUs commit a8fb40966f19ff81520d9ccf8f7e2b95201368b8 upstream. All Zen or newer CPU which support C3 shares cache. Its not necessary to flush the caches in software before entering C3. This will cause drop in performance for the cores which share some caches. ARB_DIS is not used with current AMD C state implementation. So set related flags correctly. Signed-off-by: Deepak Sharma Acked-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki Signed-off-by: Guilherme G. Piccoli Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/acpi/cstate.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 49ae4e1ac9cd..d28d43d774a2 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -79,6 +79,21 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, */ flags->bm_control = 0; } + if (c->x86_vendor == X86_VENDOR_AMD && c->x86 >= 0x17) { + /* + * For all AMD Zen or newer CPUs that support C3, caches + * should not be flushed by software while entering C3 + * type state. Set bm->check to 1 so that kernel doesn't + * need to execute cache flush operation. + */ + flags->bm_check = 1; + /* + * In current AMD C state implementation ARB_DIS is no longer + * used. So set bm_control to zero to indicate ARB_DIS is not + * required while entering C3 type state. + */ + flags->bm_control = 0; + } } EXPORT_SYMBOL(acpi_processor_power_init_bm_check); From c4097e844a6e1368b7de1fded5713e7c52c07237 Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Wed, 27 Oct 2021 22:34:41 +0800 Subject: [PATCH 1111/4345] fs: reiserfs: remove useless new_opts in reiserfs_remount commit 81dedaf10c20959bdf5624f9783f408df26ba7a4 upstream. Since the commit c3d98ea08291 ("VFS: Don't use save/replace_mount_options if not using generic_show_options") eliminates replace_mount_options in reiserfs_remount, but does not handle the allocated new_opts, it will cause memory leak in the reiserfs_remount. Because new_opts is useless in reiserfs_mount, so we fix this bug by removing the useless new_opts in reiserfs_remount. Fixes: c3d98ea08291 ("VFS: Don't use save/replace_mount_options if not using generic_show_options") Link: https://lore.kernel.org/r/20211027143445.4156459-1-mudongliangabcd@gmail.com Signed-off-by: Dongliang Mu Signed-off-by: Jan Kara Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- fs/reiserfs/super.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 913f5af9bf24..0ebb6e684908 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1437,7 +1437,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) unsigned long safe_mask = 0; unsigned int commit_max_age = (unsigned int)-1; struct reiserfs_journal *journal = SB_JOURNAL(s); - char *new_opts; int err; char *qf_names[REISERFS_MAXQUOTAS]; unsigned int qfmt = 0; @@ -1445,10 +1444,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) int i; #endif - new_opts = kstrdup(arg, GFP_KERNEL); - if (arg && !new_opts) - return -ENOMEM; - sync_filesystem(s); reiserfs_write_lock(s); @@ -1599,7 +1594,6 @@ out_ok_unlocked: out_err_unlock: reiserfs_write_unlock(s); out_err: - kfree(new_opts); return err; } From e6226917f4cf7f37f8b256b9edf4669a8d383009 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Tue, 24 Jan 2023 11:29:45 -0800 Subject: [PATCH 1112/4345] sysctl: add a new register_sysctl_init() interface commit 3ddd9a808cee7284931312f2f3e854c9617f44b2 upstream. Patch series "sysctl: first set of kernel/sysctl cleanups", v2. Finally had time to respin the series of the work we had started last year on cleaning up the kernel/sysct.c kitchen sink. People keeps stuffing their sysctls in that file and this creates a maintenance burden. So this effort is aimed at placing sysctls where they actually belong. I'm going to split patches up into series as there is quite a bit of work. This first set adds register_sysctl_init() for uses of registerting a sysctl on the init path, adds const where missing to a few places, generalizes common values so to be more easy to share, and starts the move of a few kernel/sysctl.c out where they belong. The majority of rework on v2 in this first patch set is 0-day fixes. Eric Biederman's feedback is later addressed in subsequent patch sets. I'll only post the first two patch sets for now. We can address the rest once the first two patch sets get completely reviewed / Acked. This patch (of 9): The kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. Today though folks heavily rely on tables on kernel/sysctl.c so they can easily just extend this table with their needed sysctls. In order to help users move their sysctls out we need to provide a helper which can be used during code initialization. We special-case the initialization use of register_sysctl() since it *is* safe to fail, given all that sysctls do is provide a dynamic interface to query or modify at runtime an existing variable. So the use case of register_sysctl() on init should *not* stop if the sysctls don't end up getting registered. It would be counter productive to stop boot if a simple sysctl registration failed. Provide a helper for init then, and document the recommended init levels to use for callers of this routine. We will later use this in subsequent patches to start slimming down kernel/sysctl.c tables and moving sysctl registration to the code which actually needs these sysctls. [mcgrof@kernel.org: major commit log and documentation rephrasing also moved to fs/proc/proc_sysctl.c ] Link: https://lkml.kernel.org/r/20211123202347.818157-1-mcgrof@kernel.org Link: https://lkml.kernel.org/r/20211123202347.818157-2-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Reviewed-by: Kees Cook Cc: Iurii Zaikin Cc: "Eric W. Biederman" Cc: Peter Zijlstra Cc: Greg Kroah-Hartman Cc: Paul Turner Cc: Andy Shevchenko Cc: Sebastian Reichel Cc: Tetsuo Handa Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Qing Wang Cc: Benjamin LaHaise Cc: Al Viro Cc: Jan Kara Cc: Amir Goldstein Cc: Stephen Kitt Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Clemens Ladisch Cc: David Airlie Cc: Jani Nikula Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Phillip Potter Cc: Rodrigo Vivi Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Jani Nikula Cc: John Ogness Cc: Martin K. Petersen Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- fs/proc/proc_sysctl.c | 33 +++++++++++++++++++++++++++++++++ include/linux/sysctl.h | 3 +++ 2 files changed, 36 insertions(+) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 070d2df8ab9c..cd7c6c4af83a 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "internal.h" static const struct dentry_operations proc_sys_dentry_operations; @@ -1380,6 +1381,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab } EXPORT_SYMBOL(register_sysctl); +/** + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base + * @table: This is the sysctl table that needs to be registered to the path + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. + * + * Context: Can only be called after your respective sysctl base path has been + * registered. So for instance, most base directories are registered early on + * init before init levels are processed through proc_sys_init() and + * sysctl_init(). + */ +void __init __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name) +{ + struct ctl_table_header *hdr = register_sysctl(path, table); + + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl %s to %s\n", table_name, path); + return; + } + kmemleak_not_leak(hdr); +} + static char *append_path(const char *path, char *pos, const char *name) { int namelen; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 51298a4f4623..161eba9fd912 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -195,6 +195,9 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init(void); +extern void __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name); +#define register_sysctl_init(path, table) __register_sysctl_init(path, table, #table) void do_sysctl_args(void); extern int pwrsw_enabled; From e97ec099d7fd2d963414bb9f5a0e895603d79b7b Mon Sep 17 00:00:00 2001 From: tangmeng Date: Tue, 24 Jan 2023 11:29:46 -0800 Subject: [PATCH 1113/4345] kernel/panic: move panic sysctls to its own file commit 9df918698408fd914493aba0b7858fef50eba63a upstream. kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the oops_all_cpu_backtrace sysctl to its own file, kernel/panic.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- include/linux/kernel.h | 6 ------ kernel/panic.c | 26 +++++++++++++++++++++++++- kernel/sysctl.c | 11 ----------- 3 files changed, 25 insertions(+), 18 deletions(-) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f5392d96d688..084d97070ed9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -520,12 +520,6 @@ static inline u32 int_sqrt64(u64 x) } #endif -#ifdef CONFIG_SMP -extern unsigned int sysctl_oops_all_cpu_backtrace; -#else -#define sysctl_oops_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - extern void bust_spinlocks(int yes); extern int panic_timeout; extern unsigned long panic_print; diff --git a/kernel/panic.c b/kernel/panic.c index 332736a72a58..f567195d45d9 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -41,7 +41,9 @@ * Should we dump all CPUs backtraces in an oops event? * Defaults to 0, can be changed via sysctl. */ -unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; +static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; +#else +#define sysctl_oops_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE; @@ -70,6 +72,28 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); +#if defined(CONFIG_SMP) && defined(CONFIG_SYSCTL) +static struct ctl_table kern_panic_table[] = { + { + .procname = "oops_all_cpu_backtrace", + .data = &sysctl_oops_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; + +static __init int kernel_panic_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_panic_table); + return 0; +} +late_initcall(kernel_panic_sysctls_init); +#endif + static long no_blink(int state) { return 0; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3eb527f8a269..d8b7b2846313 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2199,17 +2199,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_SMP - { - .procname = "oops_all_cpu_backtrace", - .data = &sysctl_oops_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ { .procname = "pid_max", .data = &pid_max, From 590ba6fee0956127b7ec62af3a658ed71d175f83 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Tue, 24 Jan 2023 11:29:47 -0800 Subject: [PATCH 1114/4345] panic: unset panic_on_warn inside panic() commit 1a2383e8b84c0451fd9b1eec3b9aab16f30b597c upstream. In the current code, the following three places need to unset panic_on_warn before calling panic() to avoid recursive panics: kernel/kcsan/report.c: print_report() kernel/sched/core.c: __schedule_bug() mm/kfence/report.c: kfence_report_error() In order to avoid copy-pasting "panic_on_warn = 0" all over the places, it is better to move it inside panic() and then remove it from the other places. Link: https://lkml.kernel.org/r/1644324666-15947-4-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Tiezhu Yang Reviewed-by: Marco Elver Cc: Andrey Ryabinin Cc: Baoquan He Cc: Jonathan Corbet Cc: Xuefeng Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- kernel/panic.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/kernel/panic.c b/kernel/panic.c index f567195d45d9..960c2be2759c 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -207,6 +207,16 @@ void panic(const char *fmt, ...) int old_cpu, this_cpu; bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; + if (panic_on_warn) { + /* + * This thread may hit another WARN() in the panic path. + * Resetting this prevents additional WARN() from panicking the + * system on this thread. Other threads are blocked by the + * panic_mutex in panic(). + */ + panic_on_warn = 0; + } + /* * Disable local interrupts. This will prevent panic_smp_self_stop * from deadlocking the first cpu that invokes the panic, since @@ -618,16 +628,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint, if (regs) show_regs(regs); - if (panic_on_warn) { - /* - * This thread may hit another WARN() in the panic path. - * Resetting this prevents additional WARN() from panicking the - * system on this thread. Other threads are blocked by the - * panic_mutex in panic(). - */ - panic_on_warn = 0; + if (panic_on_warn) panic("panic_on_warn set ...\n"); - } if (!regs) dump_stack(); From b857b42a8c0992256d3129bce141724e4eb2b438 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Tue, 24 Jan 2023 11:29:48 -0800 Subject: [PATCH 1115/4345] ubsan: no need to unset panic_on_warn in ubsan_epilogue() commit d83ce027a54068fabb70d2c252e1ce2da86784a4 upstream. panic_on_warn is unset inside panic(), so no need to unset it before calling panic() in ubsan_epilogue(). Link: https://lkml.kernel.org/r/1644324666-15947-5-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Tiezhu Yang Reviewed-by: Marco Elver Cc: Andrey Ryabinin Cc: Baoquan He Cc: Jonathan Corbet Cc: Xuefeng Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- lib/ubsan.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/lib/ubsan.c b/lib/ubsan.c index adf8dcf3c84e..d81d107f64f4 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -151,16 +151,8 @@ static void ubsan_epilogue(void) current->in_ubsan--; - if (panic_on_warn) { - /* - * This thread may hit another WARN() in the panic path. - * Resetting this prevents additional WARN() from panicking the - * system on this thread. Other threads are blocked by the - * panic_mutex in panic(). - */ - panic_on_warn = 0; + if (panic_on_warn) panic("panic_on_warn set ...\n"); - } } static void handle_overflow(struct overflow_data *data, void *lhs, From 715a63588f5602eae9ee7699ad83863cb500a019 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Tue, 24 Jan 2023 11:29:49 -0800 Subject: [PATCH 1116/4345] kasan: no need to unset panic_on_warn in end_report() commit e7ce7500375a63348e1d3a703c8d5003cbe3fea6 upstream. panic_on_warn is unset inside panic(), so no need to unset it before calling panic() in end_report(). Link: https://lkml.kernel.org/r/1644324666-15947-6-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Tiezhu Yang Reviewed-by: Marco Elver Cc: Andrey Ryabinin Cc: Baoquan He Cc: Jonathan Corbet Cc: Xuefeng Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- mm/kasan/report.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 00a53f1355ae..91714acea0d6 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -95,16 +95,8 @@ static void end_report(unsigned long *flags) pr_err("==================================================================\n"); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); spin_unlock_irqrestore(&report_lock, *flags); - if (panic_on_warn && !test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) { - /* - * This thread may hit another WARN() in the panic path. - * Resetting this prevents additional WARN() from panicking the - * system on this thread. Other threads are blocked by the - * panic_mutex in panic(). - */ - panic_on_warn = 0; + if (panic_on_warn && !test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) panic("panic_on_warn set ...\n"); - } kasan_enable_current(); } From d9c740c765e5b5d27bc6e7a500430a9bd4e14e75 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 24 Jan 2023 11:29:50 -0800 Subject: [PATCH 1117/4345] exit: Add and use make_task_dead. commit 0e25498f8cd43c1b5aa327f373dd094e9a006da7 upstream. There are two big uses of do_exit. The first is it's design use to be the guts of the exit(2) system call. The second use is to terminate a task after something catastrophic has happened like a NULL pointer in kernel code. Add a function make_task_dead that is initialy exactly the same as do_exit to cover the cases where do_exit is called to handle catastrophic failure. In time this can probably be reduced to just a light wrapper around do_task_dead. For now keep it exactly the same so that there will be no behavioral differences introducing this new concept. Replace all of the uses of do_exit that use it for catastraphic task cleanup with make_task_dead to make it clear what the code is doing. As part of this rename rewind_stack_do_exit rewind_stack_and_make_dead. Signed-off-by: "Eric W. Biederman" Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- arch/alpha/kernel/traps.c | 6 +++--- arch/alpha/mm/fault.c | 2 +- arch/arm/kernel/traps.c | 2 +- arch/arm/mm/fault.c | 2 +- arch/arm64/kernel/traps.c | 2 +- arch/arm64/mm/fault.c | 2 +- arch/csky/abiv1/alignment.c | 2 +- arch/csky/kernel/traps.c | 2 +- arch/h8300/kernel/traps.c | 2 +- arch/h8300/mm/fault.c | 2 +- arch/hexagon/kernel/traps.c | 2 +- arch/ia64/kernel/mca_drv.c | 2 +- arch/ia64/kernel/traps.c | 2 +- arch/ia64/mm/fault.c | 2 +- arch/m68k/kernel/traps.c | 2 +- arch/m68k/mm/fault.c | 2 +- arch/microblaze/kernel/exceptions.c | 4 ++-- arch/mips/kernel/traps.c | 2 +- arch/nds32/kernel/fpu.c | 2 +- arch/nds32/kernel/traps.c | 8 ++++---- arch/nios2/kernel/traps.c | 4 ++-- arch/openrisc/kernel/traps.c | 2 +- arch/parisc/kernel/traps.c | 2 +- arch/powerpc/kernel/traps.c | 2 +- arch/riscv/kernel/traps.c | 2 +- arch/riscv/mm/fault.c | 2 +- arch/s390/kernel/dumpstack.c | 2 +- arch/s390/kernel/nmi.c | 2 +- arch/sh/kernel/traps.c | 2 +- arch/sparc/kernel/traps_32.c | 4 +--- arch/sparc/kernel/traps_64.c | 4 +--- arch/x86/entry/entry_32.S | 6 +++--- arch/x86/entry/entry_64.S | 6 +++--- arch/x86/kernel/dumpstack.c | 4 ++-- arch/xtensa/kernel/traps.c | 2 +- include/linux/sched/task.h | 1 + kernel/exit.c | 9 +++++++++ tools/objtool/check.c | 3 ++- 38 files changed, 59 insertions(+), 52 deletions(-) diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 921d4b6e4d95..8b0f81a58b94 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -192,7 +192,7 @@ die_if_kernel(char * str, struct pt_regs *regs, long err, unsigned long *r9_15) local_irq_enable(); while (1); } - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } #ifndef CONFIG_MATHEMU @@ -577,7 +577,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg, printk("Bad unaligned kernel access at %016lx: %p %lx %lu\n", pc, va, opcode, reg); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); got_exception: /* Ok, we caught the exception, but we don't want it. Is there @@ -632,7 +632,7 @@ got_exception: local_irq_enable(); while (1); } - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } /* diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 09172f017efc..5d42f94887da 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -204,7 +204,7 @@ retry: printk(KERN_ALERT "Unable to handle kernel paging request at " "virtual address %016lx\n", address); die_if_kernel("Oops", regs, cause, (unsigned long*)regs - 16); - do_exit(SIGKILL); + make_task_dead(SIGKILL); /* We ran out of memory, or some other thing happened to us that made us unable to handle the page fault gracefully. */ diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index a531afad87fd..7878c33e188d 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -348,7 +348,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, int signr) if (panic_on_oops) panic("Fatal exception"); if (signr) - do_exit(signr); + make_task_dead(signr); } /* diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index efa402025031..af5177801fb1 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -125,7 +125,7 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, show_pte(KERN_ALERT, mm, addr); die("Oops", regs, fsr); bust_spinlocks(0); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } /* diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 2059d8f43f55..2cdd53425509 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -144,7 +144,7 @@ void die(const char *str, struct pt_regs *regs, int err) raw_spin_unlock_irqrestore(&die_lock, flags); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } static void arm64_show_signal(int signo, const char *str) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 795d224f184f..2be856731e81 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -293,7 +293,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, show_pte(addr); die("Oops", regs, esr); bust_spinlocks(0); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } static void __do_kernel_fault(unsigned long addr, unsigned int esr, diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c index cb2a0d94a144..5e2fb45d605c 100644 --- a/arch/csky/abiv1/alignment.c +++ b/arch/csky/abiv1/alignment.c @@ -294,7 +294,7 @@ bad_area: __func__, opcode, rz, rx, imm, addr); show_regs(regs); bust_spinlocks(0); - do_exit(SIGKILL); + make_dead_task(SIGKILL); } force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr); diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c index 22721468a04b..3c648305f2c3 100644 --- a/arch/csky/kernel/traps.c +++ b/arch/csky/kernel/traps.c @@ -111,7 +111,7 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception"); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_dead_task(SIGSEGV); } void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c index 5d8b969cd8f3..2b1366c958e3 100644 --- a/arch/h8300/kernel/traps.c +++ b/arch/h8300/kernel/traps.c @@ -110,7 +110,7 @@ void die(const char *str, struct pt_regs *fp, unsigned long err) dump(fp); spin_unlock_irq(&die_lock); - do_exit(SIGSEGV); + make_dead_task(SIGSEGV); } static int kstack_depth_to_print = 24; diff --git a/arch/h8300/mm/fault.c b/arch/h8300/mm/fault.c index d4bc9c16f2df..0223528565dd 100644 --- a/arch/h8300/mm/fault.c +++ b/arch/h8300/mm/fault.c @@ -51,7 +51,7 @@ asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address, printk(" at virtual address %08lx\n", address); if (!user_mode(regs)) die("Oops", regs, error_code); - do_exit(SIGKILL); + make_dead_task(SIGKILL); return 1; } diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c index 904134b37232..25e8bdbfd685 100644 --- a/arch/hexagon/kernel/traps.c +++ b/arch/hexagon/kernel/traps.c @@ -218,7 +218,7 @@ int die(const char *str, struct pt_regs *regs, long err) panic("Fatal exception"); oops_exit(); - do_exit(err); + make_dead_task(err); return 0; } diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index 2a40268c3d49..d9ee3b186249 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -176,7 +176,7 @@ mca_handler_bh(unsigned long paddr, void *iip, unsigned long ipsr) spin_unlock(&mca_bh_lock); /* This process is about to be killed itself */ - do_exit(SIGKILL); + make_task_dead(SIGKILL); } /** diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index e13cb905930f..753642366e12 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -85,7 +85,7 @@ die (const char *str, struct pt_regs *regs, long err) if (panic_on_oops) panic("Fatal exception"); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); return 0; } diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index cd9766d2b6e0..829198180ca6 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -274,7 +274,7 @@ retry: regs = NULL; bust_spinlocks(0); if (regs) - do_exit(SIGKILL); + make_task_dead(SIGKILL); return; out_of_memory: diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 9e1261462bcc..b2a31afb998c 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -1136,7 +1136,7 @@ void die_if_kernel (char *str, struct pt_regs *fp, int nr) pr_crit("%s: %08x\n", str, nr); show_registers(fp); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } asmlinkage void set_esp0(unsigned long ssp) diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index ef46e77e97a5..fcb3a0d8421c 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -48,7 +48,7 @@ int send_fault_sig(struct pt_regs *regs) pr_alert("Unable to handle kernel access"); pr_cont(" at virtual address %p\n", addr); die_if_kernel("Oops", regs, 0 /*error_code*/); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } return 1; diff --git a/arch/microblaze/kernel/exceptions.c b/arch/microblaze/kernel/exceptions.c index cf99c411503e..6d3a6a644220 100644 --- a/arch/microblaze/kernel/exceptions.c +++ b/arch/microblaze/kernel/exceptions.c @@ -44,10 +44,10 @@ void die(const char *str, struct pt_regs *fp, long err) pr_warn("Oops: %s, sig: %ld\n", str, err); show_regs(fp); spin_unlock_irq(&die_lock); - /* do_exit() should take care of panic'ing from an interrupt + /* make_task_dead() should take care of panic'ing from an interrupt * context so we don't handle it here */ - do_exit(err); + make_task_dead(err); } /* for user application debugging */ diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index b1fe4518bd22..ebd0101f0958 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -413,7 +413,7 @@ void __noreturn die(const char *str, struct pt_regs *regs) if (regs && kexec_should_crash(current)) crash_kexec(regs); - do_exit(sig); + make_task_dead(sig); } extern struct exception_table_entry __start___dbe_table[]; diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c index 9edd7ed7d7bf..701c09a668de 100644 --- a/arch/nds32/kernel/fpu.c +++ b/arch/nds32/kernel/fpu.c @@ -223,7 +223,7 @@ inline void handle_fpu_exception(struct pt_regs *regs) } } else if (fpcsr & FPCSR_mskRIT) { if (!user_mode(regs)) - do_exit(SIGILL); + make_task_dead(SIGILL); si_signo = SIGILL; } diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c index 6a9772ba7392..12cdd6549360 100644 --- a/arch/nds32/kernel/traps.c +++ b/arch/nds32/kernel/traps.c @@ -185,7 +185,7 @@ void die(const char *str, struct pt_regs *regs, int err) bust_spinlocks(0); spin_unlock_irq(&die_lock); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } EXPORT_SYMBOL(die); @@ -289,7 +289,7 @@ void unhandled_interruption(struct pt_regs *regs) pr_emerg("unhandled_interruption\n"); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGKILL); + make_task_dead(SIGKILL); force_sig(SIGKILL); } @@ -300,7 +300,7 @@ void unhandled_exceptions(unsigned long entry, unsigned long addr, addr, type); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGKILL); + make_task_dead(SIGKILL); force_sig(SIGKILL); } @@ -327,7 +327,7 @@ void do_revinsn(struct pt_regs *regs) pr_emerg("Reserved Instruction\n"); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGILL); + make_task_dead(SIGILL); force_sig(SIGILL); } diff --git a/arch/nios2/kernel/traps.c b/arch/nios2/kernel/traps.c index b172da4eb1a9..86208178024f 100644 --- a/arch/nios2/kernel/traps.c +++ b/arch/nios2/kernel/traps.c @@ -37,10 +37,10 @@ void die(const char *str, struct pt_regs *regs, long err) show_regs(regs); spin_unlock_irq(&die_lock); /* - * do_exit() should take care of panic'ing from an interrupt + * make_task_dead() should take care of panic'ing from an interrupt * context so we don't handle it here */ - do_exit(err); + make_task_dead(err); } void _exception(int signo, struct pt_regs *regs, int code, unsigned long addr) diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 206e5325e61b..fca5317f3ce1 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -212,7 +212,7 @@ void die(const char *str, struct pt_regs *regs, long err) __asm__ __volatile__("l.nop 1"); do {} while (1); #endif - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } /* This is normally the 'Oops' routine */ diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index bce47e0fb692..2fad7867af10 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -268,7 +268,7 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) panic("Fatal exception"); oops_exit(); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } /* gdb uses break 4,8 */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 069d451240fa..5e5a2448ae79 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -245,7 +245,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, if (panic_on_oops) panic("Fatal exception"); - do_exit(signr); + make_task_dead(signr); } NOKPROBE_SYMBOL(oops_end); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index c1a13011fb8e..23fe03ca7ec7 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -57,7 +57,7 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception"); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 8f84bbe0ac33..54b12943cc7b 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -34,7 +34,7 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr) (addr < PAGE_SIZE) ? "NULL pointer dereference" : "paging request", addr); die(regs, "Oops"); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 0dc4b258b98d..763e726025b3 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -214,5 +214,5 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception: panic_on_oops"); oops_exit(); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 86c8d5370e7f..0102376eca3d 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -178,7 +178,7 @@ void s390_handle_mcck(void) "malfunction (code 0x%016lx).\n", mcck.mcck_code); printk(KERN_EMERG "mcck: task: %s, pid: %d.\n", current->comm, current->pid); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } } EXPORT_SYMBOL_GPL(s390_handle_mcck); diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index 9c3d32b80038..4efffc18c851 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -57,7 +57,7 @@ void die(const char *str, struct pt_regs *regs, long err) if (panic_on_oops) panic("Fatal exception"); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } void die_if_kernel(const char *str, struct pt_regs *regs, long err) diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c index 247a0d9683b2..5d47f4a34226 100644 --- a/arch/sparc/kernel/traps_32.c +++ b/arch/sparc/kernel/traps_32.c @@ -86,9 +86,7 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs) } printk("Instruction DUMP:"); instruction_dump ((unsigned long *) regs->pc); - if(regs->psr & PSR_PS) - do_exit(SIGKILL); - do_exit(SIGSEGV); + make_task_dead((regs->psr & PSR_PS) ? SIGKILL : SIGSEGV); } void do_hw_interrupt(struct pt_regs *regs, unsigned long type) diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index a850dccd78ea..814277d0e3e8 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2564,9 +2564,7 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs) } if (panic_on_oops) panic("Fatal exception"); - if (regs->tstate & TSTATE_PRIV) - do_exit(SIGKILL); - do_exit(SIGSEGV); + make_task_dead((regs->tstate & TSTATE_PRIV)? SIGKILL : SIGSEGV); } EXPORT_SYMBOL(die_if_kernel); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 8fcd6a42b3a1..70bd81b6c612 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1333,14 +1333,14 @@ SYM_CODE_START(asm_exc_nmi) SYM_CODE_END(asm_exc_nmi) .pushsection .text, "ax" -SYM_CODE_START(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_and_make_dead) /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp movl PER_CPU_VAR(cpu_current_top_of_stack), %esi leal -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp - call do_exit + call make_task_dead 1: jmp 1b -SYM_CODE_END(rewind_stack_do_exit) +SYM_CODE_END(rewind_stack_and_make_dead) .popsection diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 559c82b83475..23212c53cef7 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1509,7 +1509,7 @@ SYM_CODE_END(ignore_sysret) #endif .pushsection .text, "ax" -SYM_CODE_START(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_and_make_dead) UNWIND_HINT_FUNC /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp @@ -1518,6 +1518,6 @@ SYM_CODE_START(rewind_stack_do_exit) leaq -PTREGS_SIZE(%rax), %rsp UNWIND_HINT_REGS - call do_exit -SYM_CODE_END(rewind_stack_do_exit) + call make_task_dead +SYM_CODE_END(rewind_stack_and_make_dead) .popsection diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 97aa900386cb..b4964300153a 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -351,7 +351,7 @@ unsigned long oops_begin(void) } NOKPROBE_SYMBOL(oops_begin); -void __noreturn rewind_stack_do_exit(int signr); +void __noreturn rewind_stack_and_make_dead(int signr); void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { @@ -386,7 +386,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) * reuse the task stack and that existing poisons are invalid. */ kasan_unpoison_task_stack(current); - rewind_stack_do_exit(signr); + rewind_stack_and_make_dead(signr); } NOKPROBE_SYMBOL(oops_end); diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index efc3a29cde80..129f23c0ab55 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -545,5 +545,5 @@ void die(const char * str, struct pt_regs * regs, long err) if (panic_on_oops) panic("Fatal exception"); - do_exit(err); + make_task_dead(err); } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4ce511437a8a..2832cc6be062 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -61,6 +61,7 @@ extern void sched_post_fork(struct task_struct *p, extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); +void __noreturn make_task_dead(int signr); extern void proc_caches_init(void); diff --git a/kernel/exit.c b/kernel/exit.c index 8989e1d1f79b..8d7577940077 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -863,6 +863,15 @@ void __noreturn do_exit(long code) } EXPORT_SYMBOL_GPL(do_exit); +void __noreturn make_task_dead(int signr) +{ + /* + * Take the task off the cpu after something catastrophic has + * happened. + */ + do_exit(signr); +} + void complete_and_exit(struct completion *comp, long code) { if (comp) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 700984e7f5ba..3c2baeb86c57 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -168,6 +168,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "panic", "do_exit", "do_task_dead", + "make_task_dead", "__module_put_and_exit", "complete_and_exit", "__reiserfs_panic", @@ -175,7 +176,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "fortify_panic", "usercopy_abort", "machine_real_restart", - "rewind_stack_do_exit", + "rewind_stack_and_make_dead" "kunit_try_catch_throw", "xen_start_kernel", "cpu_bringup_and_idle", From b2c178f31162abe0c1123b815b50059f2d1163dd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 24 Jan 2023 11:29:51 -0800 Subject: [PATCH 1118/4345] objtool: Add a missing comma to avoid string concatenation commit 1fb466dff904e4a72282af336f2c355f011eec61 upstream. Recently the kbuild robot reported two new errors: >> lib/kunit/kunit-example-test.o: warning: objtool: .text.unlikely: unexpected end of section >> arch/x86/kernel/dumpstack.o: warning: objtool: oops_end() falls through to next function show_opcodes() I don't know why they did not occur in my test setup but after digging it I realized I had accidentally dropped a comma in tools/objtool/check.c when I renamed rewind_stack_do_exit to rewind_stack_and_make_dead. Add that comma back to fix objtool errors. Link: https://lkml.kernel.org/r/202112140949.Uq5sFKR1-lkp@intel.com Fixes: 0e25498f8cd4 ("exit: Add and use make_task_dead.") Reported-by: kernel test robot Signed-off-by: "Eric W. Biederman" Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- tools/objtool/check.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 3c2baeb86c57..985bcc5cea8a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -176,7 +176,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "fortify_panic", "usercopy_abort", "machine_real_restart", - "rewind_stack_and_make_dead" + "rewind_stack_and_make_dead", "kunit_try_catch_throw", "xen_start_kernel", "cpu_bringup_and_idle", From 63d77c559678f9cff5f689728c8c5cf4af7563ca Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 24 Jan 2023 11:29:52 -0800 Subject: [PATCH 1119/4345] hexagon: Fix function name in die() commit 4f0712ccec09c071e221242a2db9a6779a55a949 upstream. When building ARCH=hexagon defconfig: arch/hexagon/kernel/traps.c:217:2: error: implicit declaration of function 'make_dead_task' [-Werror,-Wimplicit-function-declaration] make_dead_task(err); ^ The function's name is make_task_dead(), change it so there is no more build error. Fixes: 0e25498f8cd4 ("exit: Add and use make_task_dead.") Signed-off-by: Nathan Chancellor Link: https://lkml.kernel.org/r/20211227184851.2297759-2-nathan@kernel.org Signed-off-by: Eric W. Biederman Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- arch/hexagon/kernel/traps.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c index 25e8bdbfd685..b334e8071709 100644 --- a/arch/hexagon/kernel/traps.c +++ b/arch/hexagon/kernel/traps.c @@ -218,7 +218,7 @@ int die(const char *str, struct pt_regs *regs, long err) panic("Fatal exception"); oops_exit(); - make_dead_task(err); + make_task_dead(err); return 0; } From 648d8b8c4938c88fef0747dee1166dbaf4e97c4c Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 24 Jan 2023 11:29:53 -0800 Subject: [PATCH 1120/4345] h8300: Fix build errors from do_exit() to make_task_dead() transition commit ab4ababdf77ccc56c7301c751dff49c79709c51c upstream. When building ARCH=h8300 defconfig: arch/h8300/kernel/traps.c: In function 'die': arch/h8300/kernel/traps.c:109:2: error: implicit declaration of function 'make_dead_task' [-Werror=implicit-function-declaration] 109 | make_dead_task(SIGSEGV); | ^~~~~~~~~~~~~~ arch/h8300/mm/fault.c: In function 'do_page_fault': arch/h8300/mm/fault.c:54:2: error: implicit declaration of function 'make_dead_task' [-Werror=implicit-function-declaration] 54 | make_dead_task(SIGKILL); | ^~~~~~~~~~~~~~ The function's name is make_task_dead(), change it so there is no more build error. Additionally, include linux/sched/task.h in arch/h8300/kernel/traps.c to avoid the same error because do_exit()'s declaration is in kernel.h but make_task_dead()'s is in task.h, which is not included in traps.c. Fixes: 0e25498f8cd4 ("exit: Add and use make_task_dead.") Signed-off-by: Nathan Chancellor Link: https://lkml.kernel.org/r/20211227184851.2297759-3-nathan@kernel.org Signed-off-by: Eric W. Biederman Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- arch/h8300/kernel/traps.c | 3 ++- arch/h8300/mm/fault.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c index 2b1366c958e3..cf23ccb50c17 100644 --- a/arch/h8300/kernel/traps.c +++ b/arch/h8300/kernel/traps.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -110,7 +111,7 @@ void die(const char *str, struct pt_regs *fp, unsigned long err) dump(fp); spin_unlock_irq(&die_lock); - make_dead_task(SIGSEGV); + make_task_dead(SIGSEGV); } static int kstack_depth_to_print = 24; diff --git a/arch/h8300/mm/fault.c b/arch/h8300/mm/fault.c index 0223528565dd..b465441f490d 100644 --- a/arch/h8300/mm/fault.c +++ b/arch/h8300/mm/fault.c @@ -51,7 +51,7 @@ asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address, printk(" at virtual address %08lx\n", address); if (!user_mode(regs)) die("Oops", regs, error_code); - make_dead_task(SIGKILL); + make_task_dead(SIGKILL); return 1; } From 6d971830da31148070a16577371d73fff5c16a57 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 24 Jan 2023 11:29:54 -0800 Subject: [PATCH 1121/4345] csky: Fix function name in csky_alignment() and die() commit 751971af2e3615dc5bd12674080bc795505fefeb upstream. When building ARCH=csky defconfig: arch/csky/kernel/traps.c: In function 'die': arch/csky/kernel/traps.c:112:17: error: implicit declaration of function 'make_dead_task' [-Werror=implicit-function-declaration] 112 | make_dead_task(SIGSEGV); | ^~~~~~~~~~~~~~ The function's name is make_task_dead(), change it so there is no more build error. Fixes: 0e25498f8cd4 ("exit: Add and use make_task_dead.") Signed-off-by: Nathan Chancellor Reviewed-by: Guo Ren Link: https://lkml.kernel.org/r/20211227184851.2297759-4-nathan@kernel.org Signed-off-by: Eric W. Biederman Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- arch/csky/abiv1/alignment.c | 2 +- arch/csky/kernel/traps.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c index 5e2fb45d605c..2df115d0e210 100644 --- a/arch/csky/abiv1/alignment.c +++ b/arch/csky/abiv1/alignment.c @@ -294,7 +294,7 @@ bad_area: __func__, opcode, rz, rx, imm, addr); show_regs(regs); bust_spinlocks(0); - make_dead_task(SIGKILL); + make_task_dead(SIGKILL); } force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr); diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c index 3c648305f2c3..15711efa14a4 100644 --- a/arch/csky/kernel/traps.c +++ b/arch/csky/kernel/traps.c @@ -111,7 +111,7 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception"); if (ret != NOTIFY_STOP) - make_dead_task(SIGSEGV); + make_task_dead(SIGSEGV); } void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) From 1b9a33a94b9c686616c3dc14f795488924ba39cd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 24 Jan 2023 11:29:55 -0800 Subject: [PATCH 1122/4345] ia64: make IA64_MCA_RECOVERY bool instead of tristate commit dbecf9b8b8ce580f4e11afed9d61e8aa294cddd2 upstream. In linux-next, IA64_MCA_RECOVERY uses the (new) function make_task_dead(), which is not exported for use by modules. Instead of exporting it for one user, convert IA64_MCA_RECOVERY to be a bool Kconfig symbol. In a config file from "kernel test robot " for a different problem, this linker error was exposed when CONFIG_IA64_MCA_RECOVERY=m. Fixes this build error: ERROR: modpost: "make_task_dead" [arch/ia64/kernel/mca_recovery.ko] undefined! Link: https://lkml.kernel.org/r/20220124213129.29306-1-rdunlap@infradead.org Fixes: 0e25498f8cd4 ("exit: Add and use make_task_dead.") Signed-off-by: Randy Dunlap Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: "Eric W. Biederman" Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- arch/ia64/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 39b25a5a591b..1d0579bc9d65 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -361,7 +361,7 @@ config ARCH_PROC_KCORE_TEXT depends on PROC_KCORE config IA64_MCA_RECOVERY - tristate "MCA recovery from errors other than TLB." + bool "MCA recovery from errors other than TLB." config IA64_PALINFO tristate "/proc/pal support" From 191a3b17dd9b55dc92283935247f8a854e6fffba Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 24 Jan 2023 11:29:56 -0800 Subject: [PATCH 1123/4345] panic: Separate sysctl logic from CONFIG_SMP commit 9360d035a579d95d1e76c471061b9065b18a0eb1 upstream. In preparation for adding more sysctls directly in kernel/panic.c, split CONFIG_SMP from the logic that adds sysctls. Cc: Petr Mladek Cc: Andrew Morton Cc: tangmeng Cc: "Guilherme G. Piccoli" Cc: Tiezhu Yang Cc: Sebastian Andrzej Siewior Reviewed-by: Luis Chamberlain Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221117234328.594699-1-keescook@chromium.org Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- kernel/panic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/panic.c b/kernel/panic.c index 960c2be2759c..09f0802212c3 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -72,8 +72,9 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); -#if defined(CONFIG_SMP) && defined(CONFIG_SYSCTL) +#ifdef CONFIG_SYSCTL static struct ctl_table kern_panic_table[] = { +#ifdef CONFIG_SMP { .procname = "oops_all_cpu_backtrace", .data = &sysctl_oops_all_cpu_backtrace, @@ -83,6 +84,7 @@ static struct ctl_table kern_panic_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, +#endif { } }; From de586785b981d24ccc432becd1cdb55c81bb09fa Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 24 Jan 2023 11:29:57 -0800 Subject: [PATCH 1124/4345] exit: Put an upper limit on how often we can oops commit d4ccd54d28d3c8598e2354acc13e28c060961dbb upstream. Many Linux systems are configured to not panic on oops; but allowing an attacker to oops the system **really** often can make even bugs that look completely unexploitable exploitable (like NULL dereferences and such) if each crash elevates a refcount by one or a lock is taken in read mode, and this causes a counter to eventually overflow. The most interesting counters for this are 32 bits wide (like open-coded refcounts that don't use refcount_t). (The ldsem reader count on 32-bit platforms is just 16 bits, but probably nobody cares about 32-bit platforms that much nowadays.) So let's panic the system if the kernel is constantly oopsing. The speed of oopsing 2^32 times probably depends on several factors, like how long the stack trace is and which unwinder you're using; an empirically important one is whether your console is showing a graphical environment or a text console that oopses will be printed to. In a quick single-threaded benchmark, it looks like oopsing in a vfork() child with a very short stack trace only takes ~510 microseconds per run when a graphical console is active; but switching to a text console that oopses are printed to slows it down around 87x, to ~45 milliseconds per run. (Adding more threads makes this faster, but the actual oops printing happens under &die_lock on x86, so you can maybe speed this up by a factor of around 2 and then any further improvement gets eaten up by lock contention.) It looks like it would take around 8-12 days to overflow a 32-bit counter with repeated oopsing on a multi-core X86 system running a graphical environment; both me (in an X86 VM) and Seth (with a distro kernel on normal hardware in a standard configuration) got numbers in that ballpark. 12 days aren't *that* short on a desktop system, and you'd likely need much longer on a typical server system (assuming that people don't run graphical desktop environments on their servers), and this is a *very* noisy and violent approach to exploiting the kernel; and it also seems to take orders of magnitude longer on some machines, probably because stuff like EFI pstore will slow it down a ton if that's active. Signed-off-by: Jann Horn Link: https://lore.kernel.org/r/20221107201317.324457-1-jannh@google.com Reviewed-by: Luis Chamberlain Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221117234328.594699-2-keescook@chromium.org Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- Documentation/admin-guide/sysctl/kernel.rst | 8 ++++ kernel/exit.c | 43 +++++++++++++++++++++ 2 files changed, 51 insertions(+) diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index a4b1ebc2e70b..cd9247b48fc7 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -663,6 +663,14 @@ This is the default behavior. an oops event is detected. +oops_limit +========== + +Number of kernel oopses after which the kernel should panic when +``panic_on_oops`` is not set. Setting this to 0 or 1 has the same effect +as setting ``panic_on_oops=1``. + + osrelease, ostype & version =========================== diff --git a/kernel/exit.c b/kernel/exit.c index 8d7577940077..db832cff6b7b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -69,6 +69,33 @@ #include #include +/* + * The default value should be high enough to not crash a system that randomly + * crashes its kernel from time to time, but low enough to at least not permit + * overflowing 32-bit refcounts or the ldsem writer count. + */ +static unsigned int oops_limit = 10000; + +#ifdef CONFIG_SYSCTL +static struct ctl_table kern_exit_table[] = { + { + .procname = "oops_limit", + .data = &oops_limit, + .maxlen = sizeof(oops_limit), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + { } +}; + +static __init int kernel_exit_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_exit_table); + return 0; +} +late_initcall(kernel_exit_sysctls_init); +#endif + static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; @@ -865,10 +892,26 @@ EXPORT_SYMBOL_GPL(do_exit); void __noreturn make_task_dead(int signr) { + static atomic_t oops_count = ATOMIC_INIT(0); + /* * Take the task off the cpu after something catastrophic has * happened. */ + + /* + * Every time the system oopses, if the oops happens while a reference + * to an object was held, the reference leaks. + * If the oops doesn't also leak memory, repeated oopsing can cause + * reference counters to wrap around (if they're not using refcount_t). + * This means that repeated oopsing can make unexploitable-looking bugs + * exploitable through repeated oopsing. + * To make sure this can't happen, place an upper bound on how often the + * kernel may oops without panic(). + */ + if (atomic_inc_return(&oops_count) >= READ_ONCE(oops_limit)) + panic("Oopsed too often (kernel.oops_limit is %d)", oops_limit); + do_exit(signr); } From 7cffbcd68f1c1579173e6d4d6fdfd5c99a4f5ba5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 24 Jan 2023 11:29:58 -0800 Subject: [PATCH 1125/4345] exit: Expose "oops_count" to sysfs commit 9db89b41117024f80b38b15954017fb293133364 upstream. Since Oops count is now tracked and is a fairly interesting signal, add the entry /sys/kernel/oops_count to expose it to userspace. Cc: "Eric W. Biederman" Cc: Jann Horn Cc: Arnd Bergmann Reviewed-by: Luis Chamberlain Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221117234328.594699-3-keescook@chromium.org Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- .../ABI/testing/sysfs-kernel-oops_count | 6 +++++ kernel/exit.c | 22 +++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-oops_count diff --git a/Documentation/ABI/testing/sysfs-kernel-oops_count b/Documentation/ABI/testing/sysfs-kernel-oops_count new file mode 100644 index 000000000000..156cca9dbc96 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-oops_count @@ -0,0 +1,6 @@ +What: /sys/kernel/oops_count +Date: November 2022 +KernelVersion: 6.2.0 +Contact: Linux Kernel Hardening List +Description: + Shows how many times the system has Oopsed since last boot. diff --git a/kernel/exit.c b/kernel/exit.c index db832cff6b7b..b519abee2c54 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -64,6 +64,7 @@ #include #include #include +#include #include #include @@ -96,6 +97,25 @@ static __init int kernel_exit_sysctls_init(void) late_initcall(kernel_exit_sysctls_init); #endif +static atomic_t oops_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); +} + +static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); + +static __init int kernel_exit_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_exit_sysfs_init); +#endif + static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; @@ -892,8 +912,6 @@ EXPORT_SYMBOL_GPL(do_exit); void __noreturn make_task_dead(int signr) { - static atomic_t oops_count = ATOMIC_INIT(0); - /* * Take the task off the cpu after something catastrophic has * happened. From 530cdae5c2b2cc30bd09054edd75abf515564354 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 24 Jan 2023 11:29:59 -0800 Subject: [PATCH 1126/4345] exit: Allow oops_limit to be disabled commit de92f65719cd672f4b48397540b9f9eff67eca40 upstream. In preparation for keeping oops_limit logic in sync with warn_limit, have oops_limit == 0 disable checking the Oops counter. Cc: Jann Horn Cc: Jonathan Corbet Cc: Andrew Morton Cc: Baolin Wang Cc: "Jason A. Donenfeld" Cc: Eric Biggers Cc: Huang Ying Cc: "Eric W. Biederman" Cc: Arnd Bergmann Cc: linux-doc@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- Documentation/admin-guide/sysctl/kernel.rst | 5 +++-- kernel/exit.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index cd9247b48fc7..470262c08858 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -667,8 +667,9 @@ oops_limit ========== Number of kernel oopses after which the kernel should panic when -``panic_on_oops`` is not set. Setting this to 0 or 1 has the same effect -as setting ``panic_on_oops=1``. +``panic_on_oops`` is not set. Setting this to 0 disables checking +the count. Setting this to 1 has the same effect as setting +``panic_on_oops=1``. The default value is 10000. osrelease, ostype & version diff --git a/kernel/exit.c b/kernel/exit.c index b519abee2c54..8c820aa7b9c5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -927,7 +927,7 @@ void __noreturn make_task_dead(int signr) * To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ - if (atomic_inc_return(&oops_count) >= READ_ONCE(oops_limit)) + if (atomic_inc_return(&oops_count) >= READ_ONCE(oops_limit) && oops_limit) panic("Oopsed too often (kernel.oops_limit is %d)", oops_limit); do_exit(signr); From 55eba18262cbc289ded9e7a8fe1b61a92140b59a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 24 Jan 2023 11:30:00 -0800 Subject: [PATCH 1127/4345] panic: Consolidate open-coded panic_on_warn checks commit 79cc1ba7badf9e7a12af99695a557e9ce27ee967 upstream. Several run-time checkers (KASAN, UBSAN, KFENCE, KCSAN, sched) roll their own warnings, and each check "panic_on_warn". Consolidate this into a single function so that future instrumentation can be added in a single location. Cc: Marco Elver Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Juri Lelli Cc: Vincent Guittot Cc: Dietmar Eggemann Cc: Steven Rostedt Cc: Ben Segall Cc: Mel Gorman Cc: Daniel Bristot de Oliveira Cc: Valentin Schneider Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Vincenzo Frascino Cc: Andrew Morton Cc: David Gow Cc: tangmeng Cc: Jann Horn Cc: Shuah Khan Cc: Petr Mladek Cc: "Paul E. McKenney" Cc: Sebastian Andrzej Siewior Cc: "Guilherme G. Piccoli" Cc: Tiezhu Yang Cc: kasan-dev@googlegroups.com Cc: linux-mm@kvack.org Reviewed-by: Luis Chamberlain Signed-off-by: Kees Cook Reviewed-by: Marco Elver Reviewed-by: Andrey Konovalov Link: https://lore.kernel.org/r/20221117234328.594699-4-keescook@chromium.org Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- include/linux/kernel.h | 1 + kernel/kcsan/report.c | 4 ++-- kernel/panic.c | 9 +++++++-- kernel/sched/core.c | 3 +-- lib/ubsan.c | 3 +-- mm/kasan/report.c | 4 ++-- 6 files changed, 14 insertions(+), 10 deletions(-) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 084d97070ed9..394f10fc29aa 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -320,6 +320,7 @@ extern long (*panic_blink)(int state); __printf(1, 2) void panic(const char *fmt, ...) __noreturn __cold; void nmi_panic(struct pt_regs *regs, const char *msg); +void check_panic_on_warn(const char *origin); extern void oops_enter(void); extern void oops_exit(void); extern bool oops_may_print(void); diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c index d3bf87e6007c..069830f5a5d2 100644 --- a/kernel/kcsan/report.c +++ b/kernel/kcsan/report.c @@ -630,8 +630,8 @@ void kcsan_report(const volatile void *ptr, size_t size, int access_type, bool reported = value_change != KCSAN_VALUE_CHANGE_FALSE && print_report(value_change, type, &ai, other_info); - if (reported && panic_on_warn) - panic("panic_on_warn set ...\n"); + if (reported) + check_panic_on_warn("KCSAN"); release_report(&flags, other_info); } diff --git a/kernel/panic.c b/kernel/panic.c index 09f0802212c3..0da47888f72e 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -192,6 +192,12 @@ static void panic_print_sys_info(void) ftrace_dump(DUMP_ALL); } +void check_panic_on_warn(const char *origin) +{ + if (panic_on_warn) + panic("%s: panic_on_warn set ...\n", origin); +} + /** * panic - halt the system * @fmt: The text string to print @@ -630,8 +636,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, if (regs) show_regs(regs); - if (panic_on_warn) - panic("panic_on_warn set ...\n"); + check_panic_on_warn("kernel"); if (!regs) dump_stack(); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a875bc59804e..1303a2607f1f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4280,8 +4280,7 @@ static noinline void __schedule_bug(struct task_struct *prev) pr_err("Preemption disabled at:"); print_ip_sym(KERN_ERR, preempt_disable_ip); } - if (panic_on_warn) - panic("scheduling while atomic\n"); + check_panic_on_warn("scheduling while atomic"); dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); diff --git a/lib/ubsan.c b/lib/ubsan.c index d81d107f64f4..ee14c46cac89 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -151,8 +151,7 @@ static void ubsan_epilogue(void) current->in_ubsan--; - if (panic_on_warn) - panic("panic_on_warn set ...\n"); + check_panic_on_warn("UBSAN"); } static void handle_overflow(struct overflow_data *data, void *lhs, diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 91714acea0d6..2f5e96ac4d00 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -95,8 +95,8 @@ static void end_report(unsigned long *flags) pr_err("==================================================================\n"); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); spin_unlock_irqrestore(&report_lock, *flags); - if (panic_on_warn && !test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) - panic("panic_on_warn set ...\n"); + if (!test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) + check_panic_on_warn("KASAN"); kasan_enable_current(); } From 8c99d4c4c192770e7ea622220e36f53b85152a75 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 24 Jan 2023 11:30:01 -0800 Subject: [PATCH 1128/4345] panic: Introduce warn_limit commit 9fc9e278a5c0b708eeffaf47d6eb0c82aa74ed78 upstream. Like oops_limit, add warn_limit for limiting the number of warnings when panic_on_warn is not set. Cc: Jonathan Corbet Cc: Andrew Morton Cc: Baolin Wang Cc: "Jason A. Donenfeld" Cc: Eric Biggers Cc: Huang Ying Cc: Petr Mladek Cc: tangmeng Cc: "Guilherme G. Piccoli" Cc: Tiezhu Yang Cc: Sebastian Andrzej Siewior Cc: linux-doc@vger.kernel.org Reviewed-by: Luis Chamberlain Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221117234328.594699-5-keescook@chromium.org Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- Documentation/admin-guide/sysctl/kernel.rst | 10 ++++++++++ kernel/panic.c | 14 ++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 470262c08858..6b0c7b650dea 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -1478,6 +1478,16 @@ entry will default to 2 instead of 0. 2 Unprivileged calls to ``bpf()`` are disabled = ============================================================= + +warn_limit +========== + +Number of kernel warnings after which the kernel should panic when +``panic_on_warn`` is not set. Setting this to 0 disables checking +the warning count. Setting this to 1 has the same effect as setting +``panic_on_warn=1``. The default value is 0. + + watchdog ======== diff --git a/kernel/panic.c b/kernel/panic.c index 0da47888f72e..e341366bd3e8 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -56,6 +56,7 @@ bool crash_kexec_post_notifiers; int panic_on_warn __read_mostly; unsigned long panic_on_taint; bool panic_on_taint_nousertaint = false; +static unsigned int warn_limit __read_mostly; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -85,6 +86,13 @@ static struct ctl_table kern_panic_table[] = { .extra2 = SYSCTL_ONE, }, #endif + { + .procname = "warn_limit", + .data = &warn_limit, + .maxlen = sizeof(warn_limit), + .mode = 0644, + .proc_handler = proc_douintvec, + }, { } }; @@ -194,8 +202,14 @@ static void panic_print_sys_info(void) void check_panic_on_warn(const char *origin) { + static atomic_t warn_count = ATOMIC_INIT(0); + if (panic_on_warn) panic("%s: panic_on_warn set ...\n", origin); + + if (atomic_inc_return(&warn_count) >= READ_ONCE(warn_limit) && warn_limit) + panic("%s: system warned too often (kernel.warn_limit is %d)", + origin, warn_limit); } /** From b0bd5dcfa608cb6896d1a43baaf532dc80e0b657 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 24 Jan 2023 11:30:02 -0800 Subject: [PATCH 1129/4345] panic: Expose "warn_count" to sysfs commit 8b05aa26336113c4cea25f1c333ee8cd4fc212a6 upstream. Since Warn count is now tracked and is a fairly interesting signal, add the entry /sys/kernel/warn_count to expose it to userspace. Cc: Petr Mladek Cc: Andrew Morton Cc: tangmeng Cc: "Guilherme G. Piccoli" Cc: Sebastian Andrzej Siewior Cc: Tiezhu Yang Reviewed-by: Luis Chamberlain Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221117234328.594699-6-keescook@chromium.org Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- .../ABI/testing/sysfs-kernel-warn_count | 6 +++++ kernel/panic.c | 22 +++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-warn_count diff --git a/Documentation/ABI/testing/sysfs-kernel-warn_count b/Documentation/ABI/testing/sysfs-kernel-warn_count new file mode 100644 index 000000000000..08f083d2fd51 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-warn_count @@ -0,0 +1,6 @@ +What: /sys/kernel/oops_count +Date: November 2022 +KernelVersion: 6.2.0 +Contact: Linux Kernel Hardening List +Description: + Shows how many times the system has Warned since last boot. diff --git a/kernel/panic.c b/kernel/panic.c index e341366bd3e8..6e30455eb2e7 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #define PANIC_TIMER_STEP 100 @@ -104,6 +105,25 @@ static __init int kernel_panic_sysctls_init(void) late_initcall(kernel_panic_sysctls_init); #endif +static atomic_t warn_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&warn_count)); +} + +static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count); + +static __init int kernel_panic_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_panic_sysfs_init); +#endif + static long no_blink(int state) { return 0; @@ -202,8 +222,6 @@ static void panic_print_sys_info(void) void check_panic_on_warn(const char *origin) { - static atomic_t warn_count = ATOMIC_INIT(0); - if (panic_on_warn) panic("%s: panic_on_warn set ...\n", origin); From 53f177b50449ab741599e402759d413f40b4073d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 24 Jan 2023 11:30:03 -0800 Subject: [PATCH 1130/4345] docs: Fix path paste-o for /sys/kernel/warn_count commit 00dd027f721e0458418f7750d8a5a664ed3e5994 upstream. Running "make htmldocs" shows that "/sys/kernel/oops_count" was duplicated. This should have been "warn_count": Warning: /sys/kernel/oops_count is defined 2 times: ./Documentation/ABI/testing/sysfs-kernel-warn_count:0 ./Documentation/ABI/testing/sysfs-kernel-oops_count:0 Fix the typo. Reported-by: kernel test robot Link: https://lore.kernel.org/linux-doc/202212110529.A3Qav8aR-lkp@intel.com Fixes: 8b05aa263361 ("panic: Expose "warn_count" to sysfs") Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- Documentation/ABI/testing/sysfs-kernel-warn_count | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/ABI/testing/sysfs-kernel-warn_count b/Documentation/ABI/testing/sysfs-kernel-warn_count index 08f083d2fd51..90a029813717 100644 --- a/Documentation/ABI/testing/sysfs-kernel-warn_count +++ b/Documentation/ABI/testing/sysfs-kernel-warn_count @@ -1,4 +1,4 @@ -What: /sys/kernel/oops_count +What: /sys/kernel/warn_count Date: November 2022 KernelVersion: 6.2.0 Contact: Linux Kernel Hardening List From b98a8b731bd2a97a2b59d079d14b25472dd0acfd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 24 Jan 2023 11:30:04 -0800 Subject: [PATCH 1131/4345] exit: Use READ_ONCE() for all oops/warn limit reads commit 7535b832c6399b5ebfc5b53af5c51dd915ee2538 upstream. Use a temporary variable to take full advantage of READ_ONCE() behavior. Without this, the report (and even the test) might be out of sync with the initial test. Reported-by: Peter Zijlstra Link: https://lore.kernel.org/lkml/Y5x7GXeluFmZ8E0E@hirez.programming.kicks-ass.net Fixes: 9fc9e278a5c0 ("panic: Introduce warn_limit") Fixes: d4ccd54d28d3 ("exit: Put an upper limit on how often we can oops") Cc: "Eric W. Biederman" Cc: Jann Horn Cc: Arnd Bergmann Cc: Petr Mladek Cc: Andrew Morton Cc: Luis Chamberlain Cc: Marco Elver Cc: tangmeng Cc: Sebastian Andrzej Siewior Cc: Tiezhu Yang Signed-off-by: Kees Cook Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- kernel/exit.c | 6 ++++-- kernel/panic.c | 7 +++++-- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 8c820aa7b9c5..bacdaf980933 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -916,6 +916,7 @@ void __noreturn make_task_dead(int signr) * Take the task off the cpu after something catastrophic has * happened. */ + unsigned int limit; /* * Every time the system oopses, if the oops happens while a reference @@ -927,8 +928,9 @@ void __noreturn make_task_dead(int signr) * To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ - if (atomic_inc_return(&oops_count) >= READ_ONCE(oops_limit) && oops_limit) - panic("Oopsed too often (kernel.oops_limit is %d)", oops_limit); + limit = READ_ONCE(oops_limit); + if (atomic_inc_return(&oops_count) >= limit && limit) + panic("Oopsed too often (kernel.oops_limit is %d)", limit); do_exit(signr); } diff --git a/kernel/panic.c b/kernel/panic.c index 6e30455eb2e7..bc39e2b27d31 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -222,12 +222,15 @@ static void panic_print_sys_info(void) void check_panic_on_warn(const char *origin) { + unsigned int limit; + if (panic_on_warn) panic("%s: panic_on_warn set ...\n", origin); - if (atomic_inc_return(&warn_count) >= READ_ONCE(warn_limit) && warn_limit) + limit = READ_ONCE(warn_limit); + if (atomic_inc_return(&warn_count) >= limit && limit) panic("%s: system warned too often (kernel.warn_limit is %d)", - origin, warn_limit); + origin, limit); } /** From 1d580d3e1311c5d28f0f28137cbcb999e9d446d8 Mon Sep 17 00:00:00 2001 From: Archie Pusaka Date: Thu, 26 Jan 2023 16:38:17 +0300 Subject: [PATCH 1132/4345] Bluetooth: hci_sync: cancel cmd_timer if hci_open failed commit 97dfaf073f5881c624856ef293be307b6166115c upstream. If a command is already sent, we take care of freeing it, but we also need to cancel the timeout as well. Signed-off-by: Archie Pusaka Reviewed-by: Abhishek Pandit-Subedi Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Fedor Pchelkin Signed-off-by: Sasha Levin --- net/bluetooth/hci_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2af1477a05ca..08c473aa0113 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1623,6 +1623,7 @@ setup_failed: hdev->flush(hdev); if (hdev->sent_cmd) { + cancel_delayed_work_sync(&hdev->cmd_timer); kfree_skb(hdev->sent_cmd); hdev->sent_cmd = NULL; } From 6da7055826a10b3c1de7c7cc22d509ab41310b8b Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 10 May 2022 14:46:30 +0530 Subject: [PATCH 1133/4345] xhci: Set HCD flag to defer primary roothub registration commit b7a4f9b5d0e4b6dd937678c546c0b322dd1a4054 upstream. Set "HCD_FLAG_DEFER_RH_REGISTER" to hcd->flags in xhci_run() to defer registering primary roothub in usb_add_hcd() if xhci has two roothubs. This will make sure both primary roothub and secondary roothub will be registered along with the second HCD. This is required for cold plugged USB devices to be detected in certain PCIe USB cards (like Inateck USB card connected to AM64 EVM or J7200 EVM). This patch has been added and reverted earier as it triggered a race in usb device enumeration. That race is now fixed in 5.16-rc3, and in stable back to 5.4 commit 6cca13de26ee ("usb: hub: Fix locking issues with address0_mutex") commit 6ae6dc22d2d1 ("usb: hub: Fix usb enumeration issue due to address0 race") [minor rebase change, and commit message update -Mathias] CC: stable@vger.kernel.org # 5.4+ Suggested-by: Mathias Nyman Tested-by: Chris Chiu Signed-off-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20220510091630.16564-3-kishon@ti.com Signed-off-by: Adrian Zaharia Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 2967372a9988..473b0b64dd57 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -696,6 +696,8 @@ int xhci_run(struct usb_hcd *hcd) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Finished xhci_run for USB2 roothub"); + set_bit(HCD_FLAG_DEFER_RH_REGISTER, &hcd->flags); + xhci_dbc_init(xhci); xhci_debugfs_init(xhci); From ce3aa7694627c35e761459d8dbd1b3b4ef0121ce Mon Sep 17 00:00:00 2001 From: "Alexey V. Vissarionov" Date: Wed, 18 Jan 2023 06:12:55 +0300 Subject: [PATCH 1134/4345] scsi: hpsa: Fix allocation size for scsi_host_alloc() [ Upstream commit bbbd25499100c810ceaf5193c3cfcab9f7402a33 ] The 'h' is a pointer to struct ctlr_info, so it's just 4 or 8 bytes, while the structure itself is much bigger. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: edd163687ea5 ("hpsa: add driver for HP Smart Array controllers.") Link: https://lore.kernel.org/r/20230118031255.GE15213@altlinux.org Signed-off-by: Alexey V. Vissarionov Acked-by: Don Brace Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hpsa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index b2d4b6c78b5c..a44a098dbb9c 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -5834,7 +5834,7 @@ static int hpsa_scsi_host_alloc(struct ctlr_info *h) { struct Scsi_Host *sh; - sh = scsi_host_alloc(&hpsa_driver_template, sizeof(h)); + sh = scsi_host_alloc(&hpsa_driver_template, sizeof(struct ctlr_info)); if (sh == NULL) { dev_err(&h->pdev->dev, "scsi_host_alloc failed\n"); return -ENOMEM; From 083b3dda86f81f9493d43e0210e6a9a2cc1bee7a Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 5 Dec 2022 11:35:57 +0100 Subject: [PATCH 1135/4345] module: Don't wait for GOING modules commit 0254127ab977e70798707a7a2b757c9f3c971210 upstream. During a system boot, it can happen that the kernel receives a burst of requests to insert the same module but loading it eventually fails during its init call. For instance, udev can make a request to insert a frequency module for each individual CPU when another frequency module is already loaded which causes the init function of the new module to return an error. Since commit 6e6de3dee51a ("kernel/module.c: Only return -EEXIST for modules that have finished loading"), the kernel waits for modules in MODULE_STATE_GOING state to finish unloading before making another attempt to load the same module. This creates unnecessary work in the described scenario and delays the boot. In the worst case, it can prevent udev from loading drivers for other devices and might cause timeouts of services waiting on them and subsequently a failed boot. This patch attempts a different solution for the problem 6e6de3dee51a was trying to solve. Rather than waiting for the unloading to complete, it returns a different error code (-EBUSY) for modules in the GOING state. This should avoid the error situation that was described in 6e6de3dee51a (user space attempting to load a dependent module because the -EEXIST error code would suggest to user space that the first module had been loaded successfully), while avoiding the delay situation too. This has been tested on linux-next since December 2022 and passes all kmod selftests except test 0009 with module compression enabled but it has been confirmed that this issue has existed and has gone unnoticed since prior to this commit and can also be reproduced without module compression with a simple usleep(5000000) on tools/modprobe.c [0]. These failures are caused by hitting the kernel mod_concurrent_max and can happen either due to a self inflicted kernel module auto-loead DoS somehow or on a system with large CPU count and each CPU count incorrectly triggering many module auto-loads. Both of those issues need to be fixed in-kernel. [0] https://lore.kernel.org/all/Y9A4fiobL6IHp%2F%2FP@bombadil.infradead.org/ Fixes: 6e6de3dee51a ("kernel/module.c: Only return -EEXIST for modules that have finished loading") Co-developed-by: Martin Wilck Signed-off-by: Martin Wilck Signed-off-by: Petr Pavlu Cc: stable@vger.kernel.org Reviewed-by: Petr Mladek [mcgrof: enhance commit log with testing and kmod test result interpretation ] Signed-off-by: Luis Chamberlain Signed-off-by: Greg Kroah-Hartman --- kernel/module.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/kernel/module.c b/kernel/module.c index 6a0fd245c048..33d1dc6d4cd6 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3661,7 +3661,8 @@ static bool finished_loading(const char *name) sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); - ret = !mod || mod->state == MODULE_STATE_LIVE; + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex); return ret; @@ -3827,20 +3828,35 @@ static int add_unformed_module(struct module *mod) mod->state = MODULE_STATE_UNFORMED; -again: mutex_lock(&module_mutex); old = find_module_all(mod->name, strlen(mod->name), true); if (old != NULL) { - if (old->state != MODULE_STATE_LIVE) { + if (old->state == MODULE_STATE_COMING + || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); err = wait_event_interruptible(module_wq, finished_loading(mod->name)); if (err) goto out_unlocked; - goto again; + + /* The module might have gone in the meantime. */ + mutex_lock(&module_mutex); + old = find_module_all(mod->name, strlen(mod->name), + true); } - err = -EEXIST; + + /* + * We are here only when the same module was being loaded. Do + * not try to load it again right now. It prevents long delays + * caused by serialized module load failures. It might happen + * when more devices of the same type trigger load of + * a particular module. + */ + if (old && old->state == MODULE_STATE_LIVE) + err = -EEXIST; + else + err = -EBUSY; goto out; } mod_update_bounds(mod); From de3930a4883ddad2244efd6d349013294c62c75c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 4 Jan 2023 16:14:12 -0500 Subject: [PATCH 1136/4345] tracing: Make sure trace_printk() can output as soon as it can be used commit 3bb06eb6e9acf7c4a3e1b5bc87aed398ff8e2253 upstream. Currently trace_printk() can be used as soon as early_trace_init() is called from start_kernel(). But if a crash happens, and "ftrace_dump_on_oops" is set on the kernel command line, all you get will be: [ 0.456075] -0 0dN.2. 347519us : Unknown type 6 [ 0.456075] -0 0dN.2. 353141us : Unknown type 6 [ 0.456075] -0 0dN.2. 358684us : Unknown type 6 This is because the trace_printk() event (type 6) hasn't been registered yet. That gets done via an early_initcall(), which may be early, but not early enough. Instead of registering the trace_printk() event (and other ftrace events, which are not trace events) via an early_initcall(), have them registered at the same time that trace_printk() can be used. This way, if there is a crash before early_initcall(), then the trace_printk()s will actually be useful. Link: https://lkml.kernel.org/r/20230104161412.019f6c55@gandalf.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Fixes: e725c731e3bb1 ("tracing: Split tracing initialization into two for early initialization") Reported-by: "Joel Fernandes (Google)" Tested-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 2 ++ kernel/trace/trace.h | 1 + kernel/trace/trace_output.c | 3 +-- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c7c92b0eed04..f06d48be5a96 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9680,6 +9680,8 @@ void __init early_trace_init(void) static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); + + init_events(); } void __init trace_init(void) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8d67f7f44840..37f616bf5fa9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1673,6 +1673,7 @@ extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); extern int event_trace_init(void); +extern int init_events(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); extern void __trace_early_add_events(struct trace_array *tr); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 000e9dc224c6..b3ee8d9b6b62 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1378,7 +1378,7 @@ static struct trace_event *events[] __initdata = { NULL }; -__init static int init_events(void) +__init int init_events(void) { struct trace_event *event; int i, ret; @@ -1396,4 +1396,3 @@ __init static int init_events(void) return 0; } -early_initcall(init_events); From 886aa449235f478e262bbd5dcdee6ed6bc202949 Mon Sep 17 00:00:00 2001 From: Natalia Petrova Date: Wed, 11 Jan 2023 15:04:09 +0300 Subject: [PATCH 1137/4345] trace_events_hist: add check for return value of 'create_hist_field' commit 8b152e9150d07a885f95e1fd401fc81af202d9a4 upstream. Function 'create_hist_field' is called recursively at trace_events_hist.c:1954 and can return NULL-value that's why we have to check it to avoid null pointer dereference. Found by Linux Verification Center (linuxtesting.org) with SVACE. Link: https://lkml.kernel.org/r/20230111120409.4111-1-n.petrova@fintech.ru Cc: stable@vger.kernel.org Fixes: 30350d65ac56 ("tracing: Add variable support to hist triggers") Signed-off-by: Natalia Petrova Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_events_hist.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0ae3e4454ff2..ccc99cd23f3c 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1646,6 +1646,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, unsigned long fl = flags & ~HIST_FIELD_FL_LOG2; hist_field->fn = hist_field_log2; hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL); + if (!hist_field->operands[0]) + goto free; hist_field->size = hist_field->operands[0]->size; hist_field->type = kstrdup(hist_field->operands[0]->type, GFP_KERNEL); if (!hist_field->type) From c42a6e68706090e4307cd19b662eeead8fa6be3c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Mon, 23 Jan 2023 11:22:52 -0500 Subject: [PATCH 1138/4345] ftrace/scripts: Update the instructions for ftrace-bisect.sh commit 7ae4ba7195b1bac04a4210a499da9d8c63b0ba9c upstream. The instructions for the ftrace-bisect.sh script, which is used to find what function is being traced that is causing a kernel crash, and possibly a triple fault reboot, uses the old method. In 5.1, a new feature was added that let the user write in the index into available_filter_functions that maps to the function a user wants to set in set_ftrace_filter (or set_ftrace_notrace). This takes O(1) to set, as suppose to writing a function name, which takes O(n) (where n is the number of functions in available_filter_functions). The ftrace-bisect.sh requires setting half of the functions in available_filter_functions, which is O(n^2) using the name method to enable and can take several minutes to complete. The number method is O(n) which takes less than a second to complete. Using the number method for any kernel 5.1 and after is the proper way to do the bisect. Update the usage to reflect the new change, as well as using the /sys/kernel/tracing path instead of the obsolete debugfs path. Link: https://lkml.kernel.org/r/20230123112252.022003dd@gandalf.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Acked-by: Mark Rutland Fixes: f79b3f338564e ("ftrace: Allow enabling of filters via index of available_filter_functions") Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- scripts/tracing/ftrace-bisect.sh | 34 ++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) diff --git a/scripts/tracing/ftrace-bisect.sh b/scripts/tracing/ftrace-bisect.sh index 926701162bc8..bb4f59262bbe 100755 --- a/scripts/tracing/ftrace-bisect.sh +++ b/scripts/tracing/ftrace-bisect.sh @@ -12,7 +12,7 @@ # (note, if this is a problem with function_graph tracing, then simply # replace "function" with "function_graph" in the following steps). # -# # cd /sys/kernel/debug/tracing +# # cd /sys/kernel/tracing # # echo schedule > set_ftrace_filter # # echo function > current_tracer # @@ -20,22 +20,40 @@ # # # echo nop > current_tracer # -# # cat available_filter_functions > ~/full-file +# Starting with v5.1 this can be done with numbers, making it much faster: +# +# The old (slow) way, for kernels before v5.1. +# +# [old-way] # cat available_filter_functions > ~/full-file +# +# [old-way] *** Note *** this process will take several minutes to update the +# [old-way] filters. Setting multiple functions is an O(n^2) operation, and we +# [old-way] are dealing with thousands of functions. So go have coffee, talk +# [old-way] with your coworkers, read facebook. And eventually, this operation +# [old-way] will end. +# +# The new way (using numbers) is an O(n) operation, and usually takes less than a second. +# +# seq `wc -l available_filter_functions | cut -d' ' -f1` > ~/full-file +# +# This will create a sequence of numbers that match the functions in +# available_filter_functions, and when echoing in a number into the +# set_ftrace_filter file, it will enable the corresponding function in +# O(1) time. Making enabling all functions O(n) where n is the number of +# functions to enable. +# +# For either the new or old way, the rest of the operations remain the same. +# # # ftrace-bisect ~/full-file ~/test-file ~/non-test-file # # cat ~/test-file > set_ftrace_filter # -# *** Note *** this will take several minutes. Setting multiple functions is -# an O(n^2) operation, and we are dealing with thousands of functions. So go -# have coffee, talk with your coworkers, read facebook. And eventually, this -# operation will end. -# # # echo function > current_tracer # # If it crashes, we know that ~/test-file has a bad function. # # Reboot back to test kernel. # -# # cd /sys/kernel/debug/tracing +# # cd /sys/kernel/tracing # # mv ~/test-file ~/full-file # # If it didn't crash. From e037baee16e0b9ace7e730888fcae9cec11daff2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 25 Jan 2023 14:02:13 +0000 Subject: [PATCH 1139/4345] cifs: Fix oops due to uncleared server->smbd_conn in reconnect commit b7ab9161cf5ddc42a288edf9d1a61f3bdffe17c7 upstream. In smbd_destroy(), clear the server->smbd_conn pointer after freeing the smbd_connection struct that it points to so that reconnection doesn't get confused. Fixes: 8ef130f9ec27 ("CIFS: SMBD: Implement function to destroy a SMB Direct connection") Cc: stable@vger.kernel.org Reviewed-by: Paulo Alcantara (SUSE) Acked-by: Tom Talpey Signed-off-by: David Howells Cc: Long Li Cc: Pavel Shilovsky Cc: Ronnie Sahlberg Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/smbdirect.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index b029ed31ef91..f73f9b062525 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -1394,6 +1394,7 @@ void smbd_destroy(struct TCP_Server_Info *server) destroy_workqueue(info->workqueue); log_rdma_event(INFO, "rdma session destroyed\n"); kfree(info); + server->smbd_conn = NULL; } /* From 76c5640737b82cf0a8d3a001437405c139b12b58 Mon Sep 17 00:00:00 2001 From: Hendrik Borghorst Date: Mon, 14 Nov 2022 16:48:23 +0000 Subject: [PATCH 1140/4345] KVM: x86/vmx: Do not skip segment attributes if unusable bit is set commit a44b331614e6f7e63902ed7dff7adc8c85edd8bc upstream. When serializing and deserializing kvm_sregs, attributes of the segment descriptors are stored by user space. For unusable segments, vmx_segment_access_rights skips all attributes and sets them to 0. This means we zero out the DPL (Descriptor Privilege Level) for unusable entries. Unusable segments are - contrary to their name - usable in 64bit mode and are used by guests to for example create a linear map through the NULL selector. VMENTER checks if SS.DPL is correct depending on the CS segment type. For types 9 (Execute Only) and 11 (Execute Read), CS.DPL must be equal to SS.DPL [1]. We have seen real world guests setting CS to a usable segment with DPL=3 and SS to an unusable segment with DPL=3. Once we go through an sregs get/set cycle, SS.DPL turns to 0. This causes the virtual machine to crash reproducibly. This commit changes the attribute logic to always preserve attributes for unusable segments. According to [2] SS.DPL is always saved on VM exits, regardless of the unusable bit so user space applications should have saved the information on serialization correctly. [3] specifies that besides SS.DPL the rest of the attributes of the descriptors are undefined after VM entry if unusable bit is set. So, there should be no harm in setting them all to the previous state. [1] Intel SDM Vol 3C 26.3.1.2 Checks on Guest Segment Registers [2] Intel SDM Vol 3C 27.3.2 Saving Segment Registers and Descriptor-Table Registers [3] Intel SDM Vol 3C 26.3.2.2 Loading Guest Segment Registers and Descriptor-Table Registers Cc: Alexander Graf Cc: stable@vger.kernel.org Signed-off-by: Hendrik Borghorst Reviewed-by: Jim Mattson Reviewed-by: Alexander Graf Message-Id: <20221114164823.69555-1-hborghor@amazon.de> Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx/vmx.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index af6742d11ca1..8f7152e158e2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -3332,18 +3332,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable || !var->present) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } + ar = var->type & 15; + ar |= (var->s & 1) << 4; + ar |= (var->dpl & 3) << 5; + ar |= (var->present & 1) << 7; + ar |= (var->avl & 1) << 12; + ar |= (var->l & 1) << 13; + ar |= (var->db & 1) << 14; + ar |= (var->g & 1) << 15; + ar |= (var->unusable || !var->present) << 16; return ar; } From 98d85586aace82fbe903f606aa0eb5263df6137a Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Mon, 23 Jan 2023 09:21:10 -0800 Subject: [PATCH 1141/4345] thermal: intel: int340x: Protect trip temperature from concurrent updates commit 6757a7abe47bcb12cb2d45661067e182424b0ee3 upstream. Trip temperatures are read using ACPI methods and stored in the memory during zone initializtion and when the firmware sends a notification for change. This trip temperature is returned when the thermal core calls via callback get_trip_temp(). But it is possible that while updating the memory copy of the trips when the firmware sends a notification for change, thermal core is reading the trip temperature via the callback get_trip_temp(). This may return invalid trip temperature. To address this add a mutex to protect the invalid temperature reads in the callback get_trip_temp() and int340x_thermal_read_trips(). Fixes: 5fbf7f27fa3d ("Thermal/int340x: Add common thermal zone handler") Signed-off-by: Srinivas Pandruvada Cc: 5.0+ # 5.0+ Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- .../int340x_thermal/int340x_thermal_zone.c | 18 +++++++++++++++--- .../int340x_thermal/int340x_thermal_zone.h | 1 + 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c index a337600d5bc4..c9e0050bce17 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c @@ -44,11 +44,13 @@ static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone, int trip, int *temp) { struct int34x_thermal_zone *d = zone->devdata; - int i; + int i, ret = 0; if (d->override_ops && d->override_ops->get_trip_temp) return d->override_ops->get_trip_temp(zone, trip, temp); + mutex_lock(&d->trip_mutex); + if (trip < d->aux_trip_nr) *temp = d->aux_trips[trip]; else if (trip == d->crt_trip_id) @@ -66,10 +68,12 @@ static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone, } } if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT) - return -EINVAL; + ret = -EINVAL; } - return 0; + mutex_unlock(&d->trip_mutex); + + return ret; } static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, @@ -174,6 +178,8 @@ int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone) int trip_cnt = int34x_zone->aux_trip_nr; int i; + mutex_lock(&int34x_zone->trip_mutex); + int34x_zone->crt_trip_id = -1; if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_CRT", &int34x_zone->crt_temp)) @@ -201,6 +207,8 @@ int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone) int34x_zone->act_trips[i].valid = true; } + mutex_unlock(&int34x_zone->trip_mutex); + return trip_cnt; } EXPORT_SYMBOL_GPL(int340x_thermal_read_trips); @@ -224,6 +232,8 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev, if (!int34x_thermal_zone) return ERR_PTR(-ENOMEM); + mutex_init(&int34x_thermal_zone->trip_mutex); + int34x_thermal_zone->adev = adev; int34x_thermal_zone->override_ops = override_ops; @@ -275,6 +285,7 @@ err_thermal_zone: acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); kfree(int34x_thermal_zone->aux_trips); err_trip_alloc: + mutex_destroy(&int34x_thermal_zone->trip_mutex); kfree(int34x_thermal_zone); return ERR_PTR(ret); } @@ -286,6 +297,7 @@ void int340x_thermal_zone_remove(struct int34x_thermal_zone thermal_zone_device_unregister(int34x_thermal_zone->zone); acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); kfree(int34x_thermal_zone->aux_trips); + mutex_destroy(&int34x_thermal_zone->trip_mutex); kfree(int34x_thermal_zone); } EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove); diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h index 3b4971df1b33..8f9872afd0d3 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h @@ -32,6 +32,7 @@ struct int34x_thermal_zone { struct thermal_zone_device_ops *override_ops; void *priv_data; struct acpi_lpat_conversion_table *lpat_table; + struct mutex trip_mutex; }; struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *, From 0cb922cef7e93a565e8eeccf810a863a24be9fd6 Mon Sep 17 00:00:00 2001 From: Giulio Benetti Date: Tue, 13 Dec 2022 20:24:03 +0100 Subject: [PATCH 1142/4345] ARM: 9280/1: mm: fix warning on phys_addr_t to void pointer assignment commit a4e03921c1bb118e6718e0a3b0322a2c13ed172b upstream. zero_page is a void* pointer but memblock_alloc() returns phys_addr_t type so this generates a warning while using clang and with -Wint-error enabled that becomes and error. So let's cast the return of memblock_alloc() to (void *). Cc: # 4.14.x + Fixes: 340a982825f7 ("ARM: 9266/1: mm: fix no-MMU ZERO_PAGE() implementation") Signed-off-by: Giulio Benetti Signed-off-by: Russell King (Oracle) Signed-off-by: Greg Kroah-Hartman --- arch/arm/mm/nommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 959f05701738..c4d5b3bacf64 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -161,7 +161,7 @@ void __init paging_init(const struct machine_desc *mdesc) mpu_setup(); /* allocate the zero page. */ - zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!zero_page) panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, PAGE_SIZE, PAGE_SIZE); From 511f6c7c40b03685779a3cfe49c9f25b383e3c25 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Wed, 18 Jan 2023 20:38:48 +0530 Subject: [PATCH 1143/4345] EDAC/device: Respect any driver-supplied workqueue polling value commit cec669ff716cc83505c77b242aecf6f7baad869d upstream. The EDAC drivers may optionally pass the poll_msec value. Use that value if available, else fall back to 1000ms. [ bp: Touchups. ] Fixes: e27e3dac6517 ("drivers/edac: add edac_device class") Reported-by: Luca Weiss Signed-off-by: Manivannan Sadhasivam Signed-off-by: Borislav Petkov (AMD) Tested-by: Steev Klimaszewski # Thinkpad X13s Tested-by: Andrew Halaney # sa8540p-ride Cc: # 4.9 Link: https://lore.kernel.org/r/COZYL8MWN97H.MROQ391BGA09@otso Signed-off-by: Greg Kroah-Hartman --- drivers/edac/edac_device.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 8220ce5b87ca..85c229985f90 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -34,6 +34,9 @@ static DEFINE_MUTEX(device_ctls_mutex); static LIST_HEAD(edac_device_list); +/* Default workqueue processing interval on this instance, in msecs */ +#define DEFAULT_POLL_INTERVAL 1000 + #ifdef CONFIG_EDAC_DEBUG static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev) { @@ -366,7 +369,7 @@ static void edac_device_workq_function(struct work_struct *work_req) * whole one second to save timers firing all over the period * between integral seconds */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_queue_work(&edac_dev->work, edac_dev->delay); @@ -396,7 +399,7 @@ static void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev, * timers firing on sub-second basis, while they are happy * to fire together on the 1 second exactly */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_queue_work(&edac_dev->work, edac_dev->delay); @@ -430,7 +433,7 @@ void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, edac_dev->delay = msecs_to_jiffies(msec); /* See comment in edac_device_workq_setup() above */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_mod_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_mod_work(&edac_dev->work, edac_dev->delay); @@ -472,11 +475,7 @@ int edac_device_add_device(struct edac_device_ctl_info *edac_dev) /* This instance is NOW RUNNING */ edac_dev->op_state = OP_RUNNING_POLL; - /* - * enable workq processing on this instance, - * default = 1000 msec - */ - edac_device_workq_setup(edac_dev, 1000); + edac_device_workq_setup(edac_dev, edac_dev->poll_msec ?: DEFAULT_POLL_INTERVAL); } else { edac_dev->op_state = OP_RUNNING_INTERRUPT; } From 76d9ebb7f0bc10fbc78b6d576751552edf743968 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Wed, 18 Jan 2023 20:38:50 +0530 Subject: [PATCH 1144/4345] EDAC/qcom: Do not pass llcc_driv_data as edac_device_ctl_info's pvt_info commit 977c6ba624f24ae20cf0faee871257a39348d4a9 upstream. The memory for llcc_driv_data is allocated by the LLCC driver. But when it is passed as the private driver info to the EDAC core, it will get freed during the qcom_edac driver release. So when the qcom_edac driver gets probed again, it will try to use the freed data leading to the use-after-free bug. Hence, do not pass llcc_driv_data as pvt_info but rather reference it using the platform_data pointer in the qcom_edac driver. Fixes: 27450653f1db ("drivers: edac: Add EDAC driver support for QCOM SoCs") Reported-by: Steev Klimaszewski Signed-off-by: Manivannan Sadhasivam Signed-off-by: Borislav Petkov (AMD) Tested-by: Steev Klimaszewski # Thinkpad X13s Tested-by: Andrew Halaney # sa8540p-ride Cc: # 4.20 Link: https://lore.kernel.org/r/20230118150904.26913-4-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/edac/qcom_edac.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c index 97a27e42dd61..c45519f59dc1 100644 --- a/drivers/edac/qcom_edac.c +++ b/drivers/edac/qcom_edac.c @@ -252,7 +252,7 @@ clear: static int dump_syn_reg(struct edac_device_ctl_info *edev_ctl, int err_type, u32 bank) { - struct llcc_drv_data *drv = edev_ctl->pvt_info; + struct llcc_drv_data *drv = edev_ctl->dev->platform_data; int ret; ret = dump_syn_reg_values(drv, bank, err_type); @@ -289,7 +289,7 @@ static irqreturn_t llcc_ecc_irq_handler(int irq, void *edev_ctl) { struct edac_device_ctl_info *edac_dev_ctl = edev_ctl; - struct llcc_drv_data *drv = edac_dev_ctl->pvt_info; + struct llcc_drv_data *drv = edac_dev_ctl->dev->platform_data; irqreturn_t irq_rc = IRQ_NONE; u32 drp_error, trp_error, i; int ret; @@ -358,7 +358,6 @@ static int qcom_llcc_edac_probe(struct platform_device *pdev) edev_ctl->dev_name = dev_name(dev); edev_ctl->ctl_name = "llcc"; edev_ctl->panic_on_ue = LLCC_ERP_PANIC_ON_UE; - edev_ctl->pvt_info = llcc_driv_data; rc = edac_device_add_device(edev_ctl); if (rc) From 974aaf11804f658aad8b03e3950e41c80efd04a8 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 8 Dec 2020 17:41:42 +0100 Subject: [PATCH 1145/4345] units: Add Watt units [ Upstream commit 2ee5f8f05949735fa2f4c463a5e13fcb3660c719 ] As there are the temperature units, let's add the Watt macros definition. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki Stable-dep-of: c8c37bc51451 ("i2c: designware: use casting of u64 in clock multiplication to avoid overflow") Signed-off-by: Sasha Levin --- include/linux/units.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/units.h b/include/linux/units.h index aaf716364ec3..92c234e71cab 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -4,6 +4,10 @@ #include +#define MILLIWATT_PER_WATT 1000L +#define MICROWATT_PER_MILLIWATT 1000L +#define MICROWATT_PER_WATT 1000000L + #define ABSOLUTE_ZERO_MILLICELSIUS -273150 static inline long milli_kelvin_to_millicelsius(long t) From 8ebc2efcb6d6731c12a3c3b18f9c2d17b651e888 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 12 Jul 2021 17:20:25 +0300 Subject: [PATCH 1146/4345] units: Add SI metric prefix definitions [ Upstream commit 26471d4a6cf8d5d0bd0fb55c7169de7d67cc703a ] Sometimes it's useful to have well-defined SI metric prefix to be used to self-describe the formulas or equations. List most popular ones in the units.h. Signed-off-by: Andy Shevchenko Signed-off-by: Wolfram Sang Stable-dep-of: c8c37bc51451 ("i2c: designware: use casting of u64 in clock multiplication to avoid overflow") Signed-off-by: Sasha Levin --- include/linux/units.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/include/linux/units.h b/include/linux/units.h index 92c234e71cab..3457179f7116 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -4,6 +4,22 @@ #include +/* Metric prefixes in accordance with Système international (d'unités) */ +#define PETA 1000000000000000ULL +#define TERA 1000000000000ULL +#define GIGA 1000000000UL +#define MEGA 1000000UL +#define KILO 1000UL +#define HECTO 100UL +#define DECA 10UL +#define DECI 10UL +#define CENTI 100UL +#define MILLI 1000UL +#define MICRO 1000000UL +#define NANO 1000000000UL +#define PICO 1000000000000ULL +#define FEMTO 1000000000000000ULL + #define MILLIWATT_PER_WATT 1000L #define MICROWATT_PER_MILLIWATT 1000L #define MICROWATT_PER_WATT 1000000L From 8949ef3a7a0c938e3813f79085af97f32d060347 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 12 Jul 2021 17:20:26 +0300 Subject: [PATCH 1147/4345] i2c: designware: Use DIV_ROUND_CLOSEST() macro [ Upstream commit c045214a0f31dd5d6be716ed2f119b57b6c5d3a2 ] Instead of open-coding DIV_ROUND_CLOSEST() and similar use the macros directly. While at it, replace numbers with predefined SI metric prefixes. No functional change intended. Signed-off-by: Andy Shevchenko Signed-off-by: Wolfram Sang Stable-dep-of: c8c37bc51451 ("i2c: designware: use casting of u64 in clock multiplication to avoid overflow") Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-designware-common.c | 8 ++++---- drivers/i2c/busses/i2c-designware-platdrv.c | 5 +++-- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index 9468c6c89b3f..73a4ef8130e6 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "i2c-designware-core.h" @@ -347,7 +348,7 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset) * * If your hardware is free from tHD;STA issue, try this one. */ - return (ic_clk * tSYMBOL + 500000) / 1000000 - 8 + offset; + return DIV_ROUND_CLOSEST(ic_clk * tSYMBOL, MICRO) - 8 + offset; else /* * Conditional expression: @@ -363,8 +364,7 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset) * The reason why we need to take into account "tf" here, * is the same as described in i2c_dw_scl_lcnt(). */ - return (ic_clk * (tSYMBOL + tf) + 500000) / 1000000 - - 3 + offset; + return DIV_ROUND_CLOSEST(ic_clk * (tSYMBOL + tf), MICRO) - 3 + offset; } u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset) @@ -380,7 +380,7 @@ u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset) * account the fall time of SCL signal (tf). Default tf value * should be 0.3 us, for safety. */ - return ((ic_clk * (tLOW + tf) + 500000) / 1000000) - 1 + offset; + return DIV_ROUND_CLOSEST(ic_clk * (tLOW + tf), MICRO) - 1 + offset; } int i2c_dw_set_sda_hold(struct dw_i2c_dev *dev) diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index ad91c7c0faa5..474754151725 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -32,12 +32,13 @@ #include #include #include +#include #include "i2c-designware-core.h" static u32 i2c_dw_get_clk_rate_khz(struct dw_i2c_dev *dev) { - return clk_get_rate(dev->clk)/1000; + return clk_get_rate(dev->clk) / KILO; } #ifdef CONFIG_ACPI @@ -284,7 +285,7 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) if (!dev->sda_hold_time && t->sda_hold_ns) dev->sda_hold_time = - div_u64(clk_khz * t->sda_hold_ns + 500000, 1000000); + DIV_S64_ROUND_CLOSEST(clk_khz * t->sda_hold_ns, MICRO); } adap = &dev->adapter; From ed173f77fd28a3e4fffc13b3f28687b9eba61157 Mon Sep 17 00:00:00 2001 From: Lareine Khawaly Date: Wed, 21 Dec 2022 19:59:00 +0000 Subject: [PATCH 1148/4345] i2c: designware: use casting of u64 in clock multiplication to avoid overflow [ Upstream commit c8c37bc514514999e62a17e95160ed9ebf75ca8d ] In functions i2c_dw_scl_lcnt() and i2c_dw_scl_hcnt() may have overflow by depending on the values of the given parameters including the ic_clk. For example in our use case where ic_clk is larger than one million, multiplication of ic_clk * 4700 will result in 32 bit overflow. Add cast of u64 to the calculation to avoid multiplication overflow, and use the corresponding define for divide. Fixes: 2373f6b9744d ("i2c-designware: split of i2c-designware.c into core and bus specific parts") Signed-off-by: Lareine Khawaly Signed-off-by: Hanna Hawa Reviewed-by: Andy Shevchenko Acked-by: Jarkko Nikula Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-designware-common.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index 73a4ef8130e6..682fffaab2b4 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -348,7 +348,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset) * * If your hardware is free from tHD;STA issue, try this one. */ - return DIV_ROUND_CLOSEST(ic_clk * tSYMBOL, MICRO) - 8 + offset; + return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * tSYMBOL, MICRO) - + 8 + offset; else /* * Conditional expression: @@ -364,7 +365,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset) * The reason why we need to take into account "tf" here, * is the same as described in i2c_dw_scl_lcnt(). */ - return DIV_ROUND_CLOSEST(ic_clk * (tSYMBOL + tf), MICRO) - 3 + offset; + return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tSYMBOL + tf), MICRO) - + 3 + offset; } u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset) @@ -380,7 +382,8 @@ u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset) * account the fall time of SCL signal (tf). Default tf value * should be 0.3 us, for safety. */ - return DIV_ROUND_CLOSEST(ic_clk * (tLOW + tf), MICRO) - 1 + offset; + return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tLOW + tf), MICRO) - + 1 + offset; } int i2c_dw_set_sda_hold(struct dw_i2c_dev *dev) From 539ca5dcbc91134bbe2c45677811c31d8b030d2d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 Jan 2023 11:01:50 +0000 Subject: [PATCH 1149/4345] netlink: prevent potential spectre v1 gadgets [ Upstream commit f0950402e8c76e7dcb08563f1b4e8000fbc62455 ] Most netlink attributes are parsed and validated from __nla_validate_parse() or validate_nla() u16 type = nla_type(nla); if (type == 0 || type > maxtype) { /* error or continue */ } @type is then used as an array index and can be used as a Spectre v1 gadget. array_index_nospec() can be used to prevent leaking content of kernel memory to malicious users. This should take care of vast majority of netlink uses, but an audit is needed to take care of others where validation is not yet centralized in core netlink functions. Fixes: bfa83a9e03cf ("[NETLINK]: Type-safe netlink messages/attributes interface") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230119110150.2678537-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- lib/nlattr.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lib/nlattr.c b/lib/nlattr.c index fe60f9ae9db1..aa8fc4371e93 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -369,6 +370,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype, if (type <= 0 || type > maxtype) return 0; + type = array_index_nospec(type, maxtype + 1); pt = &policy[type]; BUG_ON(pt->type > NLA_TYPE_MAX); @@ -584,6 +586,7 @@ static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, } continue; } + type = array_index_nospec(type, maxtype + 1); if (policy) { int err = validate_nla(nla, maxtype, policy, validate, extack, depth); From d4c008f3b7f7d4ffd311eb2dae5e75b3cbddacd0 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 19 Jan 2023 19:55:45 +0100 Subject: [PATCH 1150/4345] net: fix UaF in netns ops registration error path [ Upstream commit 71ab9c3e2253619136c31c89dbb2c69305cc89b1 ] If net_assign_generic() fails, the current error path in ops_init() tries to clear the gen pointer slot. Anyway, in such error path, the gen pointer itself has not been modified yet, and the existing and accessed one is smaller than the accessed index, causing an out-of-bounds error: BUG: KASAN: slab-out-of-bounds in ops_init+0x2de/0x320 Write of size 8 at addr ffff888109124978 by task modprobe/1018 CPU: 2 PID: 1018 Comm: modprobe Not tainted 6.2.0-rc2.mptcp_ae5ac65fbed5+ #1641 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.1-2.fc37 04/01/2014 Call Trace: dump_stack_lvl+0x6a/0x9f print_address_description.constprop.0+0x86/0x2b5 print_report+0x11b/0x1fb kasan_report+0x87/0xc0 ops_init+0x2de/0x320 register_pernet_operations+0x2e4/0x750 register_pernet_subsys+0x24/0x40 tcf_register_action+0x9f/0x560 do_one_initcall+0xf9/0x570 do_init_module+0x190/0x650 load_module+0x1fa5/0x23c0 __do_sys_finit_module+0x10d/0x1b0 do_syscall_64+0x58/0x80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f42518f778d Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d cb 56 2c 00 f7 d8 64 89 01 48 RSP: 002b:00007fff96869688 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 00005568ef7f7c90 RCX: 00007f42518f778d RDX: 0000000000000000 RSI: 00005568ef41d796 RDI: 0000000000000003 RBP: 00005568ef41d796 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000000 R13: 00005568ef7f7d30 R14: 0000000000040000 R15: 0000000000000000 This change addresses the issue by skipping the gen pointer de-reference in the mentioned error-path. Found by code inspection and verified with explicit error injection on a kasan-enabled kernel. Fixes: d266935ac43d ("net: fix UAF issue in nfqnl_nf_hook_drop() when ops_init() failed") Signed-off-by: Paolo Abeni Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/cec4e0f3bb2c77ac03a6154a8508d3930beb5f0f.1674154348.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/net_namespace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index a3b7d965e9c0..e05dd4f3279a 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -155,12 +155,12 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) return 0; if (ops->id && ops->size) { -cleanup: ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; } +cleanup: kfree(data); out: From 4aacf3d78424293e318c616016865380b37b9cc5 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 14 Jan 2023 23:38:32 +0100 Subject: [PATCH 1151/4345] netfilter: nft_set_rbtree: Switch to node list walk for overlap detection [ Upstream commit c9e6978e2725a7d4b6cd23b2facd3f11422c0643 ] ...instead of a tree descent, which became overly complicated in an attempt to cover cases where expired or inactive elements would affect comparisons with the new element being inserted. Further, it turned out that it's probably impossible to cover all those cases, as inactive nodes might entirely hide subtrees consisting of a complete interval plus a node that makes the current insertion not overlap. To speed up the overlap check, descent the tree to find a greater element that is closer to the key value to insert. Then walk down the node list for overlap detection. Starting the overlap check from rb_first() unconditionally is slow, it takes 10 times longer due to the full linear traversal of the list. Moreover, perform garbage collection of expired elements when walking down the node list to avoid bogus overlap reports. For the insertion operation itself, this essentially reverts back to the implementation before commit 7c84d41416d8 ("netfilter: nft_set_rbtree: Detect partial overlaps on insertion"), except that cases of complete overlap are already handled in the overlap detection phase itself, which slightly simplifies the loop to find the insertion point. Based on initial patch from Stefano Brivio, including text from the original patch description too. Fixes: 7c84d41416d8 ("netfilter: nft_set_rbtree: Detect partial overlaps on insertion") Reviewed-by: Stefano Brivio Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_rbtree.c | 322 ++++++++++++++++++++------------- 1 file changed, 192 insertions(+), 130 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 94a5446c5eae..81c747008da3 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -38,10 +38,12 @@ static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) return !nft_rbtree_interval_end(rbe); } -static bool nft_rbtree_equal(const struct nft_set *set, const void *this, - const struct nft_rbtree_elem *interval) +static int nft_rbtree_cmp(const struct nft_set *set, + const struct nft_rbtree_elem *e1, + const struct nft_rbtree_elem *e2) { - return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0; + return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext), + set->klen); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, @@ -52,7 +54,6 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set const struct nft_rbtree_elem *rbe, *interval = NULL; u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; - const void *this; int d; parent = rcu_dereference_raw(priv->root.rb_node); @@ -62,12 +63,11 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set rbe = rb_entry(parent, struct nft_rbtree_elem, node); - this = nft_set_ext_key(&rbe->ext); - d = memcmp(this, key, set->klen); + d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (interval && - nft_rbtree_equal(set, this, interval) && + !nft_rbtree_cmp(set, rbe, interval) && nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; @@ -214,154 +214,216 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static int nft_rbtree_gc_elem(const struct nft_set *__set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set *set = (struct nft_set *)__set; + struct rb_node *prev = rb_prev(&rbe->node); + struct nft_rbtree_elem *rbe_prev; + struct nft_set_gc_batch *gcb; + + gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); + if (!gcb) + return -ENOMEM; + + /* search for expired end interval coming before this element. */ + do { + rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + if (nft_rbtree_interval_end(rbe_prev)) + break; + + prev = rb_prev(prev); + } while (prev != NULL); + + rb_erase(&rbe_prev->node, &priv->root); + rb_erase(&rbe->node, &priv->root); + atomic_sub(2, &set->nelems); + + nft_set_gc_batch_add(gcb, rbe); + nft_set_gc_batch_complete(gcb); + + return 0; +} + +static bool nft_rbtree_update_first(const struct nft_set *set, + struct nft_rbtree_elem *rbe, + struct rb_node *first) +{ + struct nft_rbtree_elem *first_elem; + + first_elem = rb_entry(first, struct nft_rbtree_elem, node); + /* this element is closest to where the new element is to be inserted: + * update the first element for the node list path. + */ + if (nft_rbtree_cmp(set, rbe, first_elem) < 0) + return true; + + return false; +} + static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_set_ext **ext) { - bool overlap = false, dup_end_left = false, dup_end_right = false; + struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; + struct rb_node *node, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); - struct nft_rbtree_elem *rbe; - struct rb_node *parent, **p; - int d; + int d, err; - /* Detect overlaps as we descend the tree. Set the flag in these cases: - * - * a1. _ _ __>| ?_ _ __| (insert end before existing end) - * a2. _ _ ___| ?_ _ _>| (insert end after existing end) - * a3. _ _ ___? >|_ _ __| (insert start before existing end) - * - * and clear it later on, as we eventually reach the points indicated by - * '?' above, in the cases described below. We'll always meet these - * later, locally, due to tree ordering, and overlaps for the intervals - * that are the closest together are always evaluated last. - * - * b1. _ _ __>| !_ _ __| (insert end before existing start) - * b2. _ _ ___| !_ _ _>| (insert end after existing start) - * b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf) - * '--' no nodes falling in this range - * b4. >|_ _ ! (insert start before existing start) - * - * Case a3. resolves to b3.: - * - if the inserted start element is the leftmost, because the '0' - * element in the tree serves as end element - * - otherwise, if an existing end is found immediately to the left. If - * there are existing nodes in between, we need to further descend the - * tree before we can conclude the new start isn't causing an overlap - * - * or to b4., which, preceded by a3., means we already traversed one or - * more existing intervals entirely, from the right. - * - * For a new, rightmost pair of elements, we'll hit cases b3. and b2., - * in that order. - * - * The flag is also cleared in two special cases: - * - * b5. |__ _ _!|<_ _ _ (insert start right before existing end) - * b6. |__ _ >|!__ _ _ (insert end right after existing start) - * - * which always happen as last step and imply that no further - * overlapping is possible. - * - * Another special case comes from the fact that start elements matching - * an already existing start element are allowed: insertion is not - * performed but we return -EEXIST in that case, and the error will be - * cleared by the caller if NLM_F_EXCL is not present in the request. - * This way, request for insertion of an exact overlap isn't reported as - * error to userspace if not desired. - * - * However, if the existing start matches a pre-existing start, but the - * end element doesn't match the corresponding pre-existing end element, - * we need to report a partial overlap. This is a local condition that - * can be noticed without need for a tracking flag, by checking for a - * local duplicated end for a corresponding start, from left and right, - * separately. + /* Descend the tree to search for an existing element greater than the + * key value to insert that is greater than the new element. This is the + * first element to walk the ordered elements to find possible overlap. */ - parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = memcmp(nft_set_ext_key(&rbe->ext), - nft_set_ext_key(&new->ext), - set->klen); + d = nft_rbtree_cmp(set, rbe, new); + if (d < 0) { p = &parent->rb_left; - - if (nft_rbtree_interval_start(new)) { - if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext) && !*p) - overlap = false; - } else { - if (dup_end_left && !*p) - return -ENOTEMPTY; - - overlap = nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, - genmask) && - !nft_set_elem_expired(&rbe->ext); - - if (overlap) { - dup_end_right = true; - continue; - } - } } else if (d > 0) { + if (!first || + nft_rbtree_update_first(set, rbe, first)) + first = &rbe->node; + p = &parent->rb_right; - - if (nft_rbtree_interval_end(new)) { - if (dup_end_right && !*p) - return -ENOTEMPTY; - - overlap = nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, - genmask) && - !nft_set_elem_expired(&rbe->ext); - - if (overlap) { - dup_end_left = true; - continue; - } - } else if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) { - overlap = nft_rbtree_interval_end(rbe); - } } else { - if (nft_rbtree_interval_end(rbe) && - nft_rbtree_interval_start(new)) { + if (nft_rbtree_interval_end(rbe)) p = &parent->rb_left; - - if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) - overlap = false; - } else if (nft_rbtree_interval_start(rbe) && - nft_rbtree_interval_end(new)) { + else p = &parent->rb_right; - - if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) - overlap = false; - } else if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) { - *ext = &rbe->ext; - return -EEXIST; - } else { - overlap = false; - if (nft_rbtree_interval_end(rbe)) - p = &parent->rb_left; - else - p = &parent->rb_right; - } } - - dup_end_left = dup_end_right = false; } - if (overlap) + if (!first) + first = rb_first(&priv->root); + + /* Detect overlap by going through the list of valid tree nodes. + * Values stored in the tree are in reversed order, starting from + * highest to lowest value. + */ + for (node = first; node != NULL; node = rb_next(node)) { + rbe = rb_entry(node, struct nft_rbtree_elem, node); + + if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* perform garbage collection to avoid bogus overlap reports. */ + if (nft_set_elem_expired(&rbe->ext)) { + err = nft_rbtree_gc_elem(set, priv, rbe); + if (err < 0) + return err; + + continue; + } + + d = nft_rbtree_cmp(set, rbe, new); + if (d == 0) { + /* Matching end element: no need to look for an + * overlapping greater or equal element. + */ + if (nft_rbtree_interval_end(rbe)) { + rbe_le = rbe; + break; + } + + /* first element that is greater or equal to key value. */ + if (!rbe_ge) { + rbe_ge = rbe; + continue; + } + + /* this is a closer more or equal element, update it. */ + if (nft_rbtree_cmp(set, rbe_ge, new) != 0) { + rbe_ge = rbe; + continue; + } + + /* element is equal to key value, make sure flags are + * the same, an existing more or equal start element + * must not be replaced by more or equal end element. + */ + if ((nft_rbtree_interval_start(new) && + nft_rbtree_interval_start(rbe_ge)) || + (nft_rbtree_interval_end(new) && + nft_rbtree_interval_end(rbe_ge))) { + rbe_ge = rbe; + continue; + } + } else if (d > 0) { + /* annotate element greater than the new element. */ + rbe_ge = rbe; + continue; + } else if (d < 0) { + /* annotate element less than the new element. */ + rbe_le = rbe; + break; + } + } + + /* - new start element matching existing start element: full overlap + * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. + */ + if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && + nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { + *ext = &rbe_ge->ext; + return -EEXIST; + } + + /* - new end element matching existing end element: full overlap + * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. + */ + if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && + nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { + *ext = &rbe_le->ext; + return -EEXIST; + } + + /* - new start element with existing closest, less or equal key value + * being a start element: partial overlap, reported as -ENOTEMPTY. + * Anonymous sets allow for two consecutive start element since they + * are constant, skip them to avoid bogus overlap reports. + */ + if (!nft_set_is_anonymous(set) && rbe_le && + nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new)) return -ENOTEMPTY; + /* - new end element with existing closest, less or equal key value + * being a end element: partial overlap, reported as -ENOTEMPTY. + */ + if (rbe_le && + nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new)) + return -ENOTEMPTY; + + /* - new end element with existing closest, greater or equal key value + * being an end element: partial overlap, reported as -ENOTEMPTY + */ + if (rbe_ge && + nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new)) + return -ENOTEMPTY; + + /* Accepted element: pick insertion point depending on key value */ + parent = NULL; + p = &priv->root.rb_node; + while (*p != NULL) { + parent = *p; + rbe = rb_entry(parent, struct nft_rbtree_elem, node); + d = nft_rbtree_cmp(set, rbe, new); + + if (d < 0) + p = &parent->rb_left; + else if (d > 0) + p = &parent->rb_right; + else if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + rb_link_node_rcu(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); return 0; From 0308b7dfea6f9f9fb92e96216126dabff25aa510 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 14 Jan 2023 23:49:46 +0100 Subject: [PATCH 1152/4345] netfilter: nft_set_rbtree: skip elements in transaction from garbage collection [ Upstream commit 5d235d6ce75c12a7fdee375eb211e4116f7ab01b ] Skip interference with an ongoing transaction, do not perform garbage collection on inactive elements. Reset annotated previous end interval if the expired element is marked as busy (control plane removed the element right before expiration). Fixes: 8d8540c4f5e0 ("netfilter: nft_set_rbtree: add timeout support") Reviewed-by: Stefano Brivio Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_rbtree.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 81c747008da3..4b9a499fe8f4 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -562,23 +562,37 @@ static void nft_rbtree_gc(struct work_struct *work) struct nft_rbtree *priv; struct rb_node *node; struct nft_set *set; + struct net *net; + u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + genmask = nft_genmask_cur(net); write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node); + if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* elements are reversed in the rbtree for historical reasons, + * from highest to lowest value, that is why end element is + * always visited before the start element. + */ if (nft_rbtree_interval_end(rbe)) { rbe_end = rbe; continue; } if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) + + if (nft_set_elem_mark_busy(&rbe->ext)) { + rbe_end = NULL; continue; + } if (rbe_prev) { rb_erase(&rbe_prev->node, &priv->root); From eccb532adabc9f9419a115fa79e47abeb48fe49e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Jan 2023 12:59:53 +0000 Subject: [PATCH 1153/4345] netlink: annotate data races around nlk->portid [ Upstream commit c1bb9484e3b05166880da8574504156ccbd0549e ] syzbot reminds us netlink_getname() runs locklessly [1] This first patch annotates the race against nlk->portid. Following patches take care of the remaining races. [1] BUG: KCSAN: data-race in netlink_getname / netlink_insert write to 0xffff88814176d310 of 4 bytes by task 2315 on cpu 1: netlink_insert+0xf1/0x9a0 net/netlink/af_netlink.c:583 netlink_autobind+0xae/0x180 net/netlink/af_netlink.c:856 netlink_sendmsg+0x444/0x760 net/netlink/af_netlink.c:1895 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x38f/0x500 net/socket.c:2476 ___sys_sendmsg net/socket.c:2530 [inline] __sys_sendmsg+0x19a/0x230 net/socket.c:2559 __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff88814176d310 of 4 bytes by task 2316 on cpu 0: netlink_getname+0xcd/0x1a0 net/netlink/af_netlink.c:1144 __sys_getsockname+0x11d/0x1b0 net/socket.c:2026 __do_sys_getsockname net/socket.c:2041 [inline] __se_sys_getsockname net/socket.c:2038 [inline] __x64_sys_getsockname+0x3e/0x50 net/socket.c:2038 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x00000000 -> 0xc9a49780 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 2316 Comm: syz-executor.2 Not tainted 6.2.0-rc3-syzkaller-00030-ge8f60cd7db24-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index d96a610929d9..438f45222ca5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -570,7 +570,9 @@ static int netlink_insert(struct sock *sk, u32 portid) if (nlk_sk(sk)->bound) goto err; - nlk_sk(sk)->portid = portid; + /* portid can be read locklessly from netlink_getname(). */ + WRITE_ONCE(nlk_sk(sk)->portid, portid); + sock_hold(sk); err = __netlink_insert(table, sk); @@ -1124,7 +1126,8 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_pid = nlk->dst_portid; nladdr->nl_groups = netlink_group_mask(nlk->dst_group); } else { - nladdr->nl_pid = nlk->portid; + /* Paired with WRITE_ONCE() in netlink_insert() */ + nladdr->nl_pid = READ_ONCE(nlk->portid); netlink_lock_table(); nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); From 8583f52c23c33b411a9c2e1546d6761f41e44d69 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Jan 2023 12:59:54 +0000 Subject: [PATCH 1154/4345] netlink: annotate data races around dst_portid and dst_group [ Upstream commit 004db64d185a5f23dfb891d7701e23713b2420ee ] netlink_getname(), netlink_sendmsg() and netlink_getsockbyportid() can read nlk->dst_portid and nlk->dst_group while another thread is changing them. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 438f45222ca5..cdecd1977583 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1082,8 +1082,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, if (addr->sa_family == AF_UNSPEC) { sk->sk_state = NETLINK_UNCONNECTED; - nlk->dst_portid = 0; - nlk->dst_group = 0; + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, 0); + WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) @@ -1105,8 +1106,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, if (err == 0) { sk->sk_state = NETLINK_CONNECTED; - nlk->dst_portid = nladdr->nl_pid; - nlk->dst_group = ffs(nladdr->nl_groups); + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); + WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); } return err; @@ -1123,8 +1125,9 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_pad = 0; if (peer) { - nladdr->nl_pid = nlk->dst_portid; - nladdr->nl_groups = netlink_group_mask(nlk->dst_group); + /* Paired with WRITE_ONCE() in netlink_connect() */ + nladdr->nl_pid = READ_ONCE(nlk->dst_portid); + nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { /* Paired with WRITE_ONCE() in netlink_insert() */ nladdr->nl_pid = READ_ONCE(nlk->portid); @@ -1154,8 +1157,9 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); + /* dst_portid can be changed in netlink_connect() */ if (sock->sk_state == NETLINK_CONNECTED && - nlk->dst_portid != nlk_sk(ssk)->portid) { + READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } @@ -1891,8 +1895,9 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { - dst_portid = nlk->dst_portid; - dst_group = nlk->dst_group; + /* Paired with WRITE_ONCE() in netlink_connect() */ + dst_portid = READ_ONCE(nlk->dst_portid); + dst_group = READ_ONCE(nlk->dst_group); } /* Paired with WRITE_ONCE() in netlink_insert() */ From 870a565bd6fecacf5be818da962d380184b9401b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Jan 2023 12:59:55 +0000 Subject: [PATCH 1155/4345] netlink: annotate data races around sk_state [ Upstream commit 9b663b5cbb15b494ef132a3c937641c90646eb73 ] netlink_getsockbyportid() reads sk_state while a concurrent netlink_connect() can change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index cdecd1977583..2104fbdd63d2 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1081,7 +1081,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; if (addr->sa_family == AF_UNSPEC) { - sk->sk_state = NETLINK_UNCONNECTED; + /* paired with READ_ONCE() in netlink_getsockbyportid() */ + WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, 0); WRITE_ONCE(nlk->dst_group, 0); @@ -1105,7 +1106,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, err = netlink_autobind(sock); if (err == 0) { - sk->sk_state = NETLINK_CONNECTED; + /* paired with READ_ONCE() in netlink_getsockbyportid() */ + WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); @@ -1157,8 +1159,8 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); - /* dst_portid can be changed in netlink_connect() */ - if (sock->sk_state == NETLINK_CONNECTED && + /* dst_portid and sk_state can be changed in netlink_connect() */ + if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); From 34c6142f0df9cd75cba5a7aa9df0960d2854b415 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Jan 2023 13:30:40 +0000 Subject: [PATCH 1156/4345] ipv4: prevent potential spectre v1 gadget in ip_metrics_convert() [ Upstream commit 1d1d63b612801b3f0a39b7d4467cad0abd60e5c8 ] if (!type) continue; if (type > RTAX_MAX) return -EINVAL; ... metrics[type - 1] = val; @type being used as an array index, we need to prevent cpu speculation or risk leaking kernel memory content. Fixes: 6cf9dfd3bd62 ("net: fib: move metrics parsing to a helper") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230120133040.3623463-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/metrics.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 3205d5f7c8c9..4966ac2aaf87 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include #include #include #include @@ -28,6 +29,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, return -EINVAL; } + type = array_index_nospec(type, RTAX_MAX + 1); if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX]; From 7f9828fb1f688210e681268490576f0ca65c322a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Jan 2023 13:31:40 +0000 Subject: [PATCH 1157/4345] ipv4: prevent potential spectre v1 gadget in fib_metrics_match() [ Upstream commit 5e9398a26a92fc402d82ce1f97cc67d832527da0 ] if (!type) continue; if (type > RTAX_MAX) return false; ... fi_val = fi->fib_metrics->metrics[type - 1]; @type being used as an array index, we need to prevent cpu speculation or risk leaking kernel memory content. Fixes: 5f9ae3d9e7e4 ("ipv4: do metrics match when looking up and deleting a route") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230120133140.3624204-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/fib_semantics.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ab9fcc6231b8..4e94796ccdbd 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -1021,6 +1022,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) if (type > RTAX_MAX) return false; + type = array_index_nospec(type, RTAX_MAX + 1); if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX]; bool ecn_ca = false; From 498584ccf46c1996aa4d5677ae7a6417632b9e10 Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Tue, 24 Jan 2023 02:47:18 +0100 Subject: [PATCH 1158/4345] netfilter: conntrack: fix vtag checks for ABORT/SHUTDOWN_COMPLETE [ Upstream commit a9993591fa94246b16b444eea55d84c54608282a ] RFC 9260, Sec 8.5.1 states that for ABORT/SHUTDOWN_COMPLETE, the chunk MUST be accepted if the vtag of the packet matches its own tag and the T bit is not set OR if it is set to its peer's vtag and the T bit is set in chunk flags. Otherwise the packet MUST be silently dropped. Update vtag verification for ABORT/SHUTDOWN_COMPLETE based on the above description. Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Signed-off-by: Sriram Yagnaraman Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_proto_sctp.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 7626f3e1c70a..72d0aa603cd6 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -412,22 +412,29 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Special cases of Verification tag check (Sec 8.5.1) */ if (sch->type == SCTP_CID_INIT) { - /* Sec 8.5.1 (A) */ + /* (A) vtag MUST be zero */ if (sh->vtag != 0) goto out_unlock; } else if (sch->type == SCTP_CID_ABORT) { - /* Sec 8.5.1 (B) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir]) + /* (B) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) { - /* Sec 8.5.1 (C) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir] && - sch->flags & SCTP_CHUNK_FLAG_T) + /* (C) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_COOKIE_ECHO) { - /* Sec 8.5.1 (D) */ + /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; } else if (sch->type == SCTP_CID_HEARTBEAT) { From 7de16d75b20ab13b75a7291f449a1b00090edfea Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 20 Jan 2023 15:19:27 -0800 Subject: [PATCH 1159/4345] netrom: Fix use-after-free of a listening socket. [ Upstream commit 409db27e3a2eb5e8ef7226ca33be33361b3ed1c9 ] syzbot reported a use-after-free in do_accept(), precisely nr_accept() as sk_prot_alloc() allocated the memory and sock_put() frees it. [0] The issue could happen if the heartbeat timer is fired and nr_heartbeat_expiry() calls nr_destroy_socket(), where a socket has SOCK_DESTROY or a listening socket has SOCK_DEAD. In this case, the first condition cannot be true. SOCK_DESTROY is flagged in nr_release() only when the file descriptor is close()d, but accept() is being called for the listening socket, so the second condition must be true. Usually, the AF_NETROM listener neither starts timers nor sets SOCK_DEAD. However, the condition is met if connect() fails before listen(). connect() starts the t1 timer and heartbeat timer, and t1timer calls nr_disconnect() when timeout happens. Then, SOCK_DEAD is set, and if we call listen(), the heartbeat timer calls nr_destroy_socket(). nr_connect nr_establish_data_link(sk) nr_start_t1timer(sk) nr_start_heartbeat(sk) nr_t1timer_expiry nr_disconnect(sk, ETIMEDOUT) nr_sk(sk)->state = NR_STATE_0 sk->sk_state = TCP_CLOSE sock_set_flag(sk, SOCK_DEAD) nr_listen if (sk->sk_state != TCP_LISTEN) sk->sk_state = TCP_LISTEN nr_heartbeat_expiry switch (nr->state) case NR_STATE_0 if (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD)) nr_destroy_socket(sk) This path seems expected, and nr_destroy_socket() is called to clean up resources. Initially, there was sock_hold() before nr_destroy_socket() so that the socket would not be freed, but the commit 517a16b1a88b ("netrom: Decrease sock refcount when sock timers expire") accidentally removed it. To fix use-after-free, let's add sock_hold(). [0]: BUG: KASAN: use-after-free in do_accept+0x483/0x510 net/socket.c:1848 Read of size 8 at addr ffff88807978d398 by task syz-executor.3/5315 CPU: 0 PID: 5315 Comm: syz-executor.3 Not tainted 6.2.0-rc3-syzkaller-00165-gd9fc1511728c #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:306 [inline] print_report+0x15e/0x461 mm/kasan/report.c:417 kasan_report+0xbf/0x1f0 mm/kasan/report.c:517 do_accept+0x483/0x510 net/socket.c:1848 __sys_accept4_file net/socket.c:1897 [inline] __sys_accept4+0x9a/0x120 net/socket.c:1927 __do_sys_accept net/socket.c:1944 [inline] __se_sys_accept net/socket.c:1941 [inline] __x64_sys_accept+0x75/0xb0 net/socket.c:1941 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fa436a8c0c9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fa437784168 EFLAGS: 00000246 ORIG_RAX: 000000000000002b RAX: ffffffffffffffda RBX: 00007fa436bac050 RCX: 00007fa436a8c0c9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000005 RBP: 00007fa436ae7ae9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffebc6700df R14: 00007fa437784300 R15: 0000000000022000 Allocated by task 5294: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:371 [inline] ____kasan_kmalloc mm/kasan/common.c:330 [inline] __kasan_kmalloc+0xa3/0xb0 mm/kasan/common.c:380 kasan_kmalloc include/linux/kasan.h:211 [inline] __do_kmalloc_node mm/slab_common.c:968 [inline] __kmalloc+0x5a/0xd0 mm/slab_common.c:981 kmalloc include/linux/slab.h:584 [inline] sk_prot_alloc+0x140/0x290 net/core/sock.c:2038 sk_alloc+0x3a/0x7a0 net/core/sock.c:2091 nr_create+0xb6/0x5f0 net/netrom/af_netrom.c:433 __sock_create+0x359/0x790 net/socket.c:1515 sock_create net/socket.c:1566 [inline] __sys_socket_create net/socket.c:1603 [inline] __sys_socket_create net/socket.c:1588 [inline] __sys_socket+0x133/0x250 net/socket.c:1636 __do_sys_socket net/socket.c:1649 [inline] __se_sys_socket net/socket.c:1647 [inline] __x64_sys_socket+0x73/0xb0 net/socket.c:1647 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 14: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2b/0x40 mm/kasan/generic.c:518 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free+0x13b/0x1a0 mm/kasan/common.c:200 kasan_slab_free include/linux/kasan.h:177 [inline] __cache_free mm/slab.c:3394 [inline] __do_kmem_cache_free mm/slab.c:3580 [inline] __kmem_cache_free+0xcd/0x3b0 mm/slab.c:3587 sk_prot_free net/core/sock.c:2074 [inline] __sk_destruct+0x5df/0x750 net/core/sock.c:2166 sk_destruct net/core/sock.c:2181 [inline] __sk_free+0x175/0x460 net/core/sock.c:2192 sk_free+0x7c/0xa0 net/core/sock.c:2203 sock_put include/net/sock.h:1991 [inline] nr_heartbeat_expiry+0x1d7/0x460 net/netrom/nr_timer.c:148 call_timer_fn+0x1da/0x7c0 kernel/time/timer.c:1700 expire_timers+0x2c6/0x5c0 kernel/time/timer.c:1751 __run_timers kernel/time/timer.c:2022 [inline] __run_timers kernel/time/timer.c:1995 [inline] run_timer_softirq+0x326/0x910 kernel/time/timer.c:2035 __do_softirq+0x1fb/0xadc kernel/softirq.c:571 Fixes: 517a16b1a88b ("netrom: Decrease sock refcount when sock timers expire") Reported-by: syzbot+5fafd5cfe1fc91f6b352@syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230120231927.51711-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/netrom/nr_timer.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index a8da88db7893..4e7c968cde2d 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -121,6 +121,7 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { + sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); goto out; From cf9a2ce0383e2cb182d223d2ece17f964432367e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jan 2023 08:45:52 +0000 Subject: [PATCH 1160/4345] net/sched: sch_taprio: do not schedule in taprio_reset() [ Upstream commit ea4fdbaa2f7798cb25adbe4fd52ffc6356f097bb ] As reported by syzbot and hinted by Vinicius, I should not have added a qdisc_synchronize() call in taprio_reset() taprio_reset() can be called with qdisc spinlock held (and BH disabled) as shown in included syzbot report [1]. Only taprio_destroy() needed this synchronization, as explained in the blamed commit changelog. [1] BUG: scheduling while atomic: syz-executor150/5091/0x00000202 2 locks held by syz-executor150/5091: Modules linked in: Preemption disabled at: [<0000000000000000>] 0x0 Kernel panic - not syncing: scheduling while atomic: panic_on_warn set ... CPU: 1 PID: 5091 Comm: syz-executor150 Not tainted 6.2.0-rc3-syzkaller-00219-g010a74f52203 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106 panic+0x2cc/0x626 kernel/panic.c:318 check_panic_on_warn.cold+0x19/0x35 kernel/panic.c:238 __schedule_bug.cold+0xd5/0xfe kernel/sched/core.c:5836 schedule_debug kernel/sched/core.c:5865 [inline] __schedule+0x34e4/0x5450 kernel/sched/core.c:6500 schedule+0xde/0x1b0 kernel/sched/core.c:6682 schedule_timeout+0x14e/0x2a0 kernel/time/timer.c:2167 schedule_timeout_uninterruptible kernel/time/timer.c:2201 [inline] msleep+0xb6/0x100 kernel/time/timer.c:2322 qdisc_synchronize include/net/sch_generic.h:1295 [inline] taprio_reset+0x93/0x270 net/sched/sch_taprio.c:1703 qdisc_reset+0x10c/0x770 net/sched/sch_generic.c:1022 dev_reset_queue+0x92/0x130 net/sched/sch_generic.c:1285 netdev_for_each_tx_queue include/linux/netdevice.h:2464 [inline] dev_deactivate_many+0x36d/0x9f0 net/sched/sch_generic.c:1351 dev_deactivate+0xed/0x1b0 net/sched/sch_generic.c:1374 qdisc_graft+0xe4a/0x1380 net/sched/sch_api.c:1080 tc_modify_qdisc+0xb6b/0x19a0 net/sched/sch_api.c:1689 rtnetlink_rcv_msg+0x43e/0xca0 net/core/rtnetlink.c:6141 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2564 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x91b/0xe10 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xd3/0x120 net/socket.c:734 ____sys_sendmsg+0x712/0x8c0 net/socket.c:2476 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2530 __sys_sendmsg+0xf7/0x1c0 net/socket.c:2559 do_syscall_x64 arch/x86/entry/common.c:50 [inline] Fixes: 3a415d59c1db ("net/sched: sch_taprio: fix possible use-after-free") Link: https://lore.kernel.org/netdev/167387581653.2747.13878941339893288655.git-patchwork-notify@kernel.org/T/ Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Vinicius Costa Gomes Link: https://lore.kernel.org/r/20230123084552.574396-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_taprio.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 5411bb4cdfc8..e25fe44899ff 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1621,7 +1621,6 @@ static void taprio_reset(struct Qdisc *sch) int i; hrtimer_cancel(&q->advance_timer); - qdisc_synchronize(sch); if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues; i++) From 6ef652f35dcfaa1ab2b2cf6c1694718595148eee Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Mon, 23 Jan 2023 14:59:33 -0300 Subject: [PATCH 1161/4345] sctp: fail if no bound addresses can be used for a given scope [ Upstream commit 458e279f861d3f61796894cd158b780765a1569f ] Currently, if you bind the socket to something like: servaddr.sin6_family = AF_INET6; servaddr.sin6_port = htons(0); servaddr.sin6_scope_id = 0; inet_pton(AF_INET6, "::1", &servaddr.sin6_addr); And then request a connect to: connaddr.sin6_family = AF_INET6; connaddr.sin6_port = htons(20000); connaddr.sin6_scope_id = if_nametoindex("lo"); inet_pton(AF_INET6, "fe88::1", &connaddr.sin6_addr); What the stack does is: - bind the socket - create a new asoc - to handle the connect - copy the addresses that can be used for the given scope - try to connect But the copy returns 0 addresses, and the effect is that it ends up trying to connect as if the socket wasn't bound, which is not the desired behavior. This unexpected behavior also allows KASLR leaks through SCTP diag interface. The fix here then is, if when trying to copy the addresses that can be used for the scope used in connect() it returns 0 addresses, bail out. This is what TCP does with a similar reproducer. Reported-by: Pietro Borrello Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Marcelo Ricardo Leitner Reviewed-by: Xin Long Link: https://lore.kernel.org/r/9fcd182f1099f86c6661f3717f63712ddd1c676c.1674496737.git.marcelo.leitner@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sctp/bind_addr.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 59e653b528b1..6b95d3ba8fe1 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -73,6 +73,12 @@ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, } } + /* If somehow no addresses were found that can be used with this + * scope, it's an error. + */ + if (list_empty(&dest->address_list)) + error = -ENETUNREACH; + out: if (error) sctp_bind_addr_clean(dest); From 3af20f63212d04ad68e370ac17603829b3121362 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Tue, 24 Jan 2023 09:02:11 +0900 Subject: [PATCH 1162/4345] net: ravb: Fix possible hang if RIS2_QFF1 happen [ Upstream commit f3c07758c9007a6bfff5290d9e19d3c41930c897 ] Since this driver enables the interrupt by RIC2_QFE1, this driver should clear the interrupt flag if it happens. Otherwise, the interrupt causes to hang the system. Note that this also fix a minor coding style (a comment indentation) around the fixed code. Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper") Signed-off-by: Yoshihiro Shimoda Reviewed-by: Sergey Shtylyov Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/renesas/ravb_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 9ec6d63691aa..410ccd28f653 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -736,14 +736,14 @@ static void ravb_error_interrupt(struct net_device *ndev) ravb_write(ndev, ~(EIS_QFS | EIS_RESERVED), EIS); if (eis & EIS_QFS) { ris2 = ravb_read(ndev, RIS2); - ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF | RIS2_RESERVED), + ravb_write(ndev, ~(RIS2_QFF0 | RIS2_QFF1 | RIS2_RFFF | RIS2_RESERVED), RIS2); /* Receive Descriptor Empty int */ if (ris2 & RIS2_QFF0) priv->stats[RAVB_BE].rx_over_errors++; - /* Receive Descriptor Empty int */ + /* Receive Descriptor Empty int */ if (ris2 & RIS2_QFF1) priv->stats[RAVB_NC].rx_over_errors++; From e9c1b1e1a00b0c668212792d263951a7f3d1ee60 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 25 Jan 2023 13:17:42 +0100 Subject: [PATCH 1163/4345] thermal: intel: int340x: Add locking to int340x_thermal_get_trip_type() [ Upstream commit acd7e9ee57c880b99671dd99680cb707b7b5b0ee ] In order to prevent int340x_thermal_get_trip_type() from possibly racing with int340x_thermal_read_trips() invoked by int3403_notify() add locking to it in analogy with int340x_thermal_get_trip_temp(). Fixes: 6757a7abe47b ("thermal: intel: int340x: Protect trip temperature from concurrent updates") Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- .../intel/int340x_thermal/int340x_thermal_zone.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c index c9e0050bce17..6952f4e237e1 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c @@ -81,11 +81,13 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, enum thermal_trip_type *type) { struct int34x_thermal_zone *d = zone->devdata; - int i; + int i, ret = 0; if (d->override_ops && d->override_ops->get_trip_type) return d->override_ops->get_trip_type(zone, trip, type); + mutex_lock(&d->trip_mutex); + if (trip < d->aux_trip_nr) *type = THERMAL_TRIP_PASSIVE; else if (trip == d->crt_trip_id) @@ -103,10 +105,12 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, } } if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT) - return -EINVAL; + ret = -EINVAL; } - return 0; + mutex_unlock(&d->trip_mutex); + + return ret; } static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone, From 62a0806eb4d2318874563f79c8fdd6bfe34ceddd Mon Sep 17 00:00:00 2001 From: David Christensen Date: Tue, 24 Jan 2023 13:53:39 -0500 Subject: [PATCH 1164/4345] net/tg3: resolve deadlock in tg3_reset_task() during EEH [ Upstream commit 6c4ca03bd890566d873e3593b32d034bf2f5a087 ] During EEH error injection testing, a deadlock was encountered in the tg3 driver when tg3_io_error_detected() was attempting to cancel outstanding reset tasks: crash> foreach UN bt ... PID: 159 TASK: c0000000067c6000 CPU: 8 COMMAND: "eehd" ... #5 [c00000000681f990] __cancel_work_timer at c00000000019fd18 #6 [c00000000681fa30] tg3_io_error_detected at c00800000295f098 [tg3] #7 [c00000000681faf0] eeh_report_error at c00000000004e25c ... PID: 290 TASK: c000000036e5f800 CPU: 6 COMMAND: "kworker/6:1" ... #4 [c00000003721fbc0] rtnl_lock at c000000000c940d8 #5 [c00000003721fbe0] tg3_reset_task at c008000002969358 [tg3] #6 [c00000003721fc60] process_one_work at c00000000019e5c4 ... PID: 296 TASK: c000000037a65800 CPU: 21 COMMAND: "kworker/21:1" ... #4 [c000000037247bc0] rtnl_lock at c000000000c940d8 #5 [c000000037247be0] tg3_reset_task at c008000002969358 [tg3] #6 [c000000037247c60] process_one_work at c00000000019e5c4 ... PID: 655 TASK: c000000036f49000 CPU: 16 COMMAND: "kworker/16:2" ...:1 #4 [c0000000373ebbc0] rtnl_lock at c000000000c940d8 #5 [c0000000373ebbe0] tg3_reset_task at c008000002969358 [tg3] #6 [c0000000373ebc60] process_one_work at c00000000019e5c4 ... Code inspection shows that both tg3_io_error_detected() and tg3_reset_task() attempt to acquire the RTNL lock at the beginning of their code blocks. If tg3_reset_task() should happen to execute between the times when tg3_io_error_deteced() acquires the RTNL lock and tg3_reset_task_cancel() is called, a deadlock will occur. Moving tg3_reset_task_cancel() call earlier within the code block, prior to acquiring RTNL, prevents this from happening, but also exposes another deadlock issue where tg3_reset_task() may execute AFTER tg3_io_error_detected() has executed: crash> foreach UN bt PID: 159 TASK: c0000000067d2000 CPU: 9 COMMAND: "eehd" ... #4 [c000000006867a60] rtnl_lock at c000000000c940d8 #5 [c000000006867a80] tg3_io_slot_reset at c0080000026c2ea8 [tg3] #6 [c000000006867b00] eeh_report_reset at c00000000004de88 ... PID: 363 TASK: c000000037564000 CPU: 6 COMMAND: "kworker/6:1" ... #3 [c000000036c1bb70] msleep at c000000000259e6c #4 [c000000036c1bba0] napi_disable at c000000000c6b848 #5 [c000000036c1bbe0] tg3_reset_task at c0080000026d942c [tg3] #6 [c000000036c1bc60] process_one_work at c00000000019e5c4 ... This issue can be avoided by aborting tg3_reset_task() if EEH error recovery is already in progress. Fixes: db84bf43ef23 ("tg3: tg3_reset_task() needs to use rtnl_lock to synchronize") Signed-off-by: David Christensen Reviewed-by: Pavan Chebbi Link: https://lore.kernel.org/r/20230124185339.225806-1-drc@linux.vnet.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/tg3.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index be96116dc2cc..613ca6124e3c 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -11185,7 +11185,7 @@ static void tg3_reset_task(struct work_struct *work) rtnl_lock(); tg3_full_lock(tp, 0); - if (!netif_running(tp->dev)) { + if (tp->pcierr_recovery || !netif_running(tp->dev)) { tg3_flag_clear(tp, RESET_TASK_PENDING); tg3_full_unlock(tp); rtnl_unlock(); @@ -18179,6 +18179,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, netdev_info(netdev, "PCI I/O error detected\n"); + /* Want to make sure that the reset task doesn't run */ + tg3_reset_task_cancel(tp); + rtnl_lock(); /* Could be second call or maybe we don't have netdev yet */ @@ -18195,9 +18198,6 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, tg3_timer_stop(tp); - /* Want to make sure that the reset task doesn't run */ - tg3_reset_task_cancel(tp); - netif_device_detach(netdev); /* Clean up software state, even if MMIO is blocked */ From 7ff8128bb11651dde6cb45821bd2665790a173b6 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Tue, 24 Jan 2023 11:11:57 +0100 Subject: [PATCH 1165/4345] net: mdio-mux-meson-g12a: force internal PHY off on mux switch [ Upstream commit 7083df59abbc2b7500db312cac706493be0273ff ] Force the internal PHY off then on when switching to the internal path. This fixes problems where the PHY ID is not properly set. Fixes: 7090425104db ("net: phy: add amlogic g12a mdio mux support") Suggested-by: Qi Duan Co-developed-by: Heiner Kallweit Signed-off-by: Heiner Kallweit Signed-off-by: Jerome Brunet Link: https://lore.kernel.org/r/20230124101157.232234-1-jbrunet@baylibre.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/mdio/mdio-mux-meson-g12a.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/net/mdio/mdio-mux-meson-g12a.c b/drivers/net/mdio/mdio-mux-meson-g12a.c index bf86c9c7a288..ab863530c9e8 100644 --- a/drivers/net/mdio/mdio-mux-meson-g12a.c +++ b/drivers/net/mdio/mdio-mux-meson-g12a.c @@ -4,6 +4,7 @@ */ #include +#include #include #include #include @@ -150,6 +151,7 @@ static const struct clk_ops g12a_ephy_pll_ops = { static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv) { + u32 value; int ret; /* Enable the phy clock */ @@ -163,18 +165,25 @@ static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv) /* Initialize ephy control */ writel(EPHY_G12A_ID, priv->regs + ETH_PHY_CNTL0); - writel(FIELD_PREP(PHY_CNTL1_ST_MODE, 3) | - FIELD_PREP(PHY_CNTL1_ST_PHYADD, EPHY_DFLT_ADD) | - FIELD_PREP(PHY_CNTL1_MII_MODE, EPHY_MODE_RMII) | - PHY_CNTL1_CLK_EN | - PHY_CNTL1_CLKFREQ | - PHY_CNTL1_PHY_ENB, - priv->regs + ETH_PHY_CNTL1); + + /* Make sure we get a 0 -> 1 transition on the enable bit */ + value = FIELD_PREP(PHY_CNTL1_ST_MODE, 3) | + FIELD_PREP(PHY_CNTL1_ST_PHYADD, EPHY_DFLT_ADD) | + FIELD_PREP(PHY_CNTL1_MII_MODE, EPHY_MODE_RMII) | + PHY_CNTL1_CLK_EN | + PHY_CNTL1_CLKFREQ; + writel(value, priv->regs + ETH_PHY_CNTL1); writel(PHY_CNTL2_USE_INTERNAL | PHY_CNTL2_SMI_SRC_MAC | PHY_CNTL2_RX_CLK_EPHY, priv->regs + ETH_PHY_CNTL2); + value |= PHY_CNTL1_PHY_ENB; + writel(value, priv->regs + ETH_PHY_CNTL1); + + /* The phy needs a bit of time to power up */ + mdelay(10); + return 0; } From 230be65a18f8288585a8681e668a694b25ac1f67 Mon Sep 17 00:00:00 2001 From: Ivo Borisov Shopov Date: Thu, 26 Jan 2023 15:10:33 +0200 Subject: [PATCH 1166/4345] tools: gpio: fix -c option of gpio-event-mon [ Upstream commit 677d85e1a1ee69fa05ccea83847309484be3781c ] Following line should listen for a rising edge and exit after the first one since '-c 1' is provided. # gpio-event-mon -n gpiochip1 -o 0 -r -c 1 It works with kernel 4.19 but it doesn't work with 5.10. In 5.10 the above command doesn't exit after the first rising edge it keep listening for an event forever. The '-c 1' is not taken into an account. The problem is in commit 62757c32d5db ("tools: gpio: add multi-line monitoring to gpio-event-mon"). Before this commit the iterator 'i' in monitor_device() is used for counting of the events (loops). In the case of the above command (-c 1) we should start from 0 and increment 'i' only ones and hit the 'break' statement and exit the process. But after the above commit counting doesn't start from 0, it start from 1 when we listen on one line. It is because 'i' is used from one more purpose, counting of lines (num_lines) and it isn't restore to 0 after following code for (i = 0; i < num_lines; i++) gpiotools_set_bit(&values.mask, i); Restore the initial value of the iterator to 0 in order to allow counting of loops to work for any cases. Fixes: 62757c32d5db ("tools: gpio: add multi-line monitoring to gpio-event-mon") Signed-off-by: Ivo Borisov Shopov Reviewed-by: Andy Shevchenko [Bartosz: tweak the commit message] Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- tools/gpio/gpio-event-mon.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 84ae1039b0a8..367c10636890 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -86,6 +86,7 @@ int monitor_device(const char *device_name, gpiotools_test_bit(values.bits, i)); } + i = 0; while (1) { struct gpio_v2_line_event event; From 9f3dd454fea589adf8cf2ae842e441e7fb4be608 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 16 Dec 2022 13:15:34 -0800 Subject: [PATCH 1167/4345] Revert "Input: synaptics - switch touchpad on HP Laptop 15-da3001TU to RMI mode" commit 3c44e2b6cde674797b76e76d3a903a63ce8a18bb upstream. This reverts commit ac5408991ea6b06e29129b4d4861097c4c3e0d59 because it causes loss of keyboard on HP 15-da1xxx. Fixes: ac5408991ea6 ("Input: synaptics - switch touchpad on HP Laptop 15-da3001TU to RMI mode") Reported-by: Jiri Slaby Link: https://lore.kernel.org/r/824effa5-8b9a-c28a-82bb-9b0ab24623e1@kernel.org Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1206358 Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/mouse/synaptics.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index f1013b950d57..82577095e175 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -191,7 +191,6 @@ static const char * const smbus_pnp_ids[] = { "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ - "SYN3286", /* HP Laptop 15-da3001TU */ NULL }; From 8fe3e574b3ac426ff4a11299f098e1c91538f3e5 Mon Sep 17 00:00:00 2001 From: Karol Herbst Date: Fri, 19 Aug 2022 22:09:28 +0200 Subject: [PATCH 1168/4345] nouveau: explicitly wait on the fence in nouveau_bo_move_m2mf commit 6b04ce966a738ecdd9294c9593e48513c0dc90aa upstream. It is a bit unlcear to us why that's helping, but it does and unbreaks suspend/resume on a lot of GPUs without any known drawbacks. Cc: stable@vger.kernel.org # v5.15+ Closes: https://gitlab.freedesktop.org/drm/nouveau/-/issues/156 Signed-off-by: Karol Herbst Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20220819200928.401416-1-kherbst@redhat.com Cc: Salvatore Bonaccorso Cc: Computer Enthusiastic Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/nouveau/nouveau_bo.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index b57dcad8865f..7633f56bc0a4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -823,6 +823,15 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr, if (ret == 0) { ret = nouveau_fence_new(chan, false, &fence); if (ret == 0) { + /* TODO: figure out a better solution here + * + * wait on the fence here explicitly as going through + * ttm_bo_move_accel_cleanup somehow doesn't seem to do it. + * + * Without this the operation can timeout and we'll fallback to a + * software copy, which might take several minutes to finish. + */ + nouveau_fence_wait(fence, false, false); ret = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, false, From 032a7d5ff519888f31ea91e24623f7e26befe641 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 13 Mar 2021 16:08:47 -0500 Subject: [PATCH 1169/4345] nfsd: Ensure knfsd shuts down when the "nfsd" pseudofs is unmounted commit c6c7f2a84da459bcc3714044e74a9cb66de31039 upstream. In order to ensure that knfsd threads don't linger once the nfsd pseudofs is unmounted (e.g. when the container is killed) we let nfsd_umount() shut down those threads and wait for them to exit. This also should ensure that we don't need to do a kernel mount of the pseudofs, since the thread lifetime is now limited by the lifetime of the filesystem. Signed-off-by: Trond Myklebust Signed-off-by: Chuck Lever Signed-off-by: Nikos Tsironis Signed-off-by: Greg Kroah-Hartman --- fs/nfsd/netns.h | 6 +++--- fs/nfsd/nfs4state.c | 8 +------- fs/nfsd/nfsctl.c | 14 ++------------ fs/nfsd/nfsd.h | 3 +-- fs/nfsd/nfssvc.c | 35 ++++++++++++++++++++++++++++++++++- 5 files changed, 41 insertions(+), 25 deletions(-) diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 7346acda9d76..02d3d2f0e616 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -42,9 +42,6 @@ struct nfsd_net { bool grace_ended; time64_t boot_time; - /* internal mount of the "nfsd" pseudofilesystem: */ - struct vfsmount *nfsd_mnt; - struct dentry *nfsd_client_dir; /* @@ -121,6 +118,9 @@ struct nfsd_net { wait_queue_head_t ntf_wq; atomic_t ntf_refcnt; + /* Allow umount to wait for nfsd state cleanup */ + struct completion nfsd_shutdown_complete; + /* * clientid and stateid data for construction of net unique COPY * stateids. diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9a47cc66963f..cb13a1649632 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7394,14 +7394,9 @@ nfs4_state_start_net(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; - ret = get_nfsdfs(net); + ret = nfs4_state_create_net(net); if (ret) return ret; - ret = nfs4_state_create_net(net); - if (ret) { - mntput(nn->nfsd_mnt); - return ret; - } locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) @@ -7471,7 +7466,6 @@ nfs4_state_shutdown_net(struct net *net) nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); - mntput(nn->nfsd_mnt); } void diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index dedec4771ecc..c4b11560ac1b 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1417,6 +1417,8 @@ static void nfsd_umount(struct super_block *sb) { struct net *net = sb->s_fs_info; + nfsd_shutdown_threads(net); + kill_litter_super(sb); put_net(net); } @@ -1429,18 +1431,6 @@ static struct file_system_type nfsd_fs_type = { }; MODULE_ALIAS_FS("nfsd"); -int get_nfsdfs(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct vfsmount *mnt; - - mnt = vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL); - if (IS_ERR(mnt)) - return PTR_ERR(mnt); - nn->nfsd_mnt = mnt; - return 0; -} - #ifdef CONFIG_PROC_FS static int create_proc_exports_entry(void) { diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index cb742e17e04a..4362d295ed34 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -85,13 +85,12 @@ int nfsd_get_nrthreads(int n, int *, struct net *); int nfsd_set_nrthreads(int n, int *, struct net *); int nfsd_pool_stats_open(struct inode *, struct file *); int nfsd_pool_stats_release(struct inode *, struct file *); +void nfsd_shutdown_threads(struct net *net); void nfsd_destroy(struct net *net); bool i_am_nfsd(void); -int get_nfsdfs(struct net *); - struct nfsdfs_client { struct kref cl_ref; void (*cl_release)(struct kref *kref); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index c7fffe1453bd..2e61a565cdbd 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -600,6 +600,37 @@ static const struct svc_serv_ops nfsd_thread_sv_ops = { .svo_module = THIS_MODULE, }; +static void nfsd_complete_shutdown(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + WARN_ON(!mutex_is_locked(&nfsd_mutex)); + + nn->nfsd_serv = NULL; + complete(&nn->nfsd_shutdown_complete); +} + +void nfsd_shutdown_threads(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; + + mutex_lock(&nfsd_mutex); + serv = nn->nfsd_serv; + if (serv == NULL) { + mutex_unlock(&nfsd_mutex); + return; + } + + svc_get(serv); + /* Kill outstanding nfsd threads */ + serv->sv_ops->svo_setup(serv, NULL, 0); + nfsd_destroy(net); + mutex_unlock(&nfsd_mutex); + /* Wait for shutdown of nfsd_serv to complete */ + wait_for_completion(&nn->nfsd_shutdown_complete); +} + bool i_am_nfsd(void) { return kthread_func(current) == nfsd; @@ -622,11 +653,13 @@ int nfsd_create_serv(struct net *net) &nfsd_thread_sv_ops); if (nn->nfsd_serv == NULL) return -ENOMEM; + init_completion(&nn->nfsd_shutdown_complete); nn->nfsd_serv->sv_maxconn = nn->max_connections; error = svc_bind(nn->nfsd_serv, net); if (error < 0) { svc_destroy(nn->nfsd_serv); + nfsd_complete_shutdown(net); return error; } @@ -675,7 +708,7 @@ void nfsd_destroy(struct net *net) svc_shutdown_net(nn->nfsd_serv, net); svc_destroy(nn->nfsd_serv); if (destroy) - nn->nfsd_serv = NULL; + nfsd_complete_shutdown(net); } int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) From 7fe4fab870613f912662efd9cc88fa588e8d5696 Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Tue, 17 Jan 2023 20:47:09 +0800 Subject: [PATCH 1170/4345] Revert "selftests/ftrace: Update synthetic event syntax errors" This reverts commit 31c2e369b5335d70e913afee3ae11e54d61afef2 which is commit b5734e997e1117afb479ffda500e36fa91aea3e8 upstream. The reverted commit belongs to patchset which updated synthetic event command parsing and testcase 'trigger-synthetic_event_syntax_errors.tc' Link: https://lore.kernel.org/all/20210211020950.102294806@goodmis.org/ However this testcase update was backported alone without feature update, which makes the testcase cannot pass on stable branch. Revert this commit to make the testcase correct. Fixes: 31c2e369b533 ("selftests/ftrace: Update synthetic event syntax errors") Reported-by: Chen Zhongjin Signed-off-by: Zheng Yejian Signed-off-by: Greg Kroah-Hartman --- .../trigger-synthetic_event_syntax_errors.tc | 35 +++++-------------- 1 file changed, 8 insertions(+), 27 deletions(-) diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc index 955e3ceea44b..ada594fe16cb 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc @@ -1,38 +1,19 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test synthetic_events syntax parser errors -# requires: synthetic_events error_log "char name[]' >> synthetic_events":README +# requires: synthetic_events error_log check_error() { # command-with-error-pos-by-^ ftrace_errlog_check 'synthetic_events' "$1" 'synthetic_events' } -check_dyn_error() { # command-with-error-pos-by-^ - ftrace_errlog_check 'synthetic_events' "$1" 'dynamic_events' -} - check_error 'myevent ^chr arg' # INVALID_TYPE -check_error 'myevent ^unsigned arg' # INCOMPLETE_TYPE - -check_error 'myevent char ^str]; int v' # BAD_NAME -check_error '^mye-vent char str[]' # BAD_NAME -check_error 'myevent char ^st-r[]' # BAD_NAME - -check_error 'myevent char str;^[]' # INVALID_FIELD -check_error 'myevent char str; ^int' # INVALID_FIELD - -check_error 'myevent char ^str[; int v' # INVALID_ARRAY_SPEC -check_error 'myevent char ^str[kdjdk]' # INVALID_ARRAY_SPEC -check_error 'myevent char ^str[257]' # INVALID_ARRAY_SPEC - -check_error '^mye;vent char str[]' # INVALID_CMD -check_error '^myevent ; char str[]' # INVALID_CMD -check_error '^myevent; char str[]' # INVALID_CMD -check_error '^myevent ;char str[]' # INVALID_CMD -check_error '^; char str[]' # INVALID_CMD -check_error '^;myevent char str[]' # INVALID_CMD -check_error '^myevent' # INVALID_CMD - -check_dyn_error '^s:junk/myevent char str[' # INVALID_DYN_CMD +check_error 'myevent ^char str[];; int v' # INVALID_TYPE +check_error 'myevent char ^str]; int v' # INVALID_NAME +check_error 'myevent char ^str;[]' # INVALID_NAME +check_error 'myevent ^char str[; int v' # INVALID_TYPE +check_error '^mye;vent char str[]' # BAD_NAME +check_error 'myevent char str[]; ^int' # INVALID_FIELD +check_error '^myevent' # INCOMPLETE_CMD exit 0 From 2eca102b350f5dd1870e615fb660dc0cc498b4db Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Mar 2022 19:00:56 +0100 Subject: [PATCH 1171/4345] block: fix and cleanup bio_check_ro commit 57e95e4670d1126c103305bcf34a9442f49f6d6a upstream. Don't use a WARN_ON when printing a potentially user triggered condition. Also don't print the partno when the block device name already includes it, and use the %pg specifier to simplify printing the block device name. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20220304180105.409765-2-hch@lst.de Signed-off-by: Jens Axboe Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- block/blk-core.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 26664f2a139e..9afb79b322fb 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -700,9 +700,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; - - WARN_ONCE(1, - "Trying to write to read-only block-device %s (partno %d)\n", + pr_warn("Trying to write to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); /* Older lvm-tools actually trigger this */ return false; From e284c273dbb4c1ed68d4204bff94d0b10e4a90f5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 9 Jan 2023 22:57:13 +0100 Subject: [PATCH 1172/4345] x86/i8259: Mark legacy PIC interrupts with IRQ_LEVEL commit 5fa55950729d0762a787451dc52862c3f850f859 upstream. Baoquan reported that after triggering a crash the subsequent crash-kernel fails to boot about half of the time. It triggers a NULL pointer dereference in the periodic tick code. This happens because the legacy timer interrupt (IRQ0) is resent in software which happens in soft interrupt (tasklet) context. In this context get_irq_regs() returns NULL which leads to the NULL pointer dereference. The reason for the resend is a spurious APIC interrupt on the IRQ0 vector which is captured and leads to a resend when the legacy timer interrupt is enabled. This is wrong because the legacy PIC interrupts are level triggered and therefore should never be resent in software, but nothing ever sets the IRQ_LEVEL flag on those interrupts, so the core code does not know about their trigger type. Ensure that IRQ_LEVEL is set when the legacy PCI interrupts are set up. Fixes: a4633adcdbc1 ("[PATCH] genirq: add genirq sw IRQ-retrigger") Reported-by: Baoquan He Signed-off-by: Thomas Gleixner Tested-by: Baoquan He Link: https://lore.kernel.org/r/87mt6rjrra.ffs@tglx Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/i8259.c | 1 + arch/x86/kernel/irqinit.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 282b4ee1339f..f325389d0351 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned int irq) disable_irq_nosync(irq); io_apic_irqs &= ~(1<init(0); - for (i = 0; i < nr_legacy_irqs(); i++) + for (i = 0; i < nr_legacy_irqs(); i++) { irq_set_chip_and_handler(i, chip, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); + } } void __init init_IRQ(void) From 743435cd1705b4a3a4b8e73a538c4c1a1efc7edb Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Tue, 24 Jan 2023 02:47:21 +0100 Subject: [PATCH 1173/4345] netfilter: conntrack: unify established states for SCTP paths commit a44b7651489f26271ac784b70895e8a85d0cebf4 upstream. An SCTP endpoint can start an association through a path and tear it down over another one. That means the initial path will not see the shutdown sequence, and the conntrack entry will remain in ESTABLISHED state for 5 days. By merging the HEARTBEAT_ACKED and ESTABLISHED states into one ESTABLISHED state, there remains no difference between a primary or secondary path. The timeout for the merged ESTABLISHED state is set to 210 seconds (hb_interval * max_path_retrans + rto_max). So, even if a path doesn't see the shutdown sequence, it will expire in a reasonable amount of time. With this change in place, there is now more than one state from which we can transition to ESTABLISHED, COOKIE_ECHOED and HEARTBEAT_SENT, so handle the setting of ASSURED bit whenever a state change has happened and the new state is ESTABLISHED. Removed the check for dir==REPLY since the transition to ESTABLISHED can happen only in the reply direction. Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Signed-off-by: Sriram Yagnaraman Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- .../uapi/linux/netfilter/nf_conntrack_sctp.h | 2 +- .../linux/netfilter/nfnetlink_cttimeout.h | 2 +- net/netfilter/nf_conntrack_proto_sctp.c | 93 ++++++++----------- net/netfilter/nf_conntrack_standalone.c | 8 -- 4 files changed, 41 insertions(+), 64 deletions(-) diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h index edc6ddab0de6..2d6f80d75ae7 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h @@ -15,7 +15,7 @@ enum sctp_conntrack { SCTP_CONNTRACK_SHUTDOWN_RECD, SCTP_CONNTRACK_SHUTDOWN_ACK_SENT, SCTP_CONNTRACK_HEARTBEAT_SENT, - SCTP_CONNTRACK_HEARTBEAT_ACKED, + SCTP_CONNTRACK_HEARTBEAT_ACKED, /* no longer used */ SCTP_CONNTRACK_MAX }; diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h index 6b20fb22717b..aa805e6d4e28 100644 --- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h +++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h @@ -94,7 +94,7 @@ enum ctattr_timeout_sctp { CTA_TIMEOUT_SCTP_SHUTDOWN_RECD, CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_SENT, - CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, + CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, /* no longer used */ __CTA_TIMEOUT_SCTP_MAX }; #define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 72d0aa603cd6..cec4b16170a0 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -27,22 +27,16 @@ #include #include -/* FIXME: Examine ipfilter's timeouts and conntrack transitions more - closely. They're more complex. --RR - - And so for me for SCTP :D -Kiran */ - static const char *const sctp_conntrack_names[] = { - "NONE", - "CLOSED", - "COOKIE_WAIT", - "COOKIE_ECHOED", - "ESTABLISHED", - "SHUTDOWN_SENT", - "SHUTDOWN_RECD", - "SHUTDOWN_ACK_SENT", - "HEARTBEAT_SENT", - "HEARTBEAT_ACKED", + [SCTP_CONNTRACK_NONE] = "NONE", + [SCTP_CONNTRACK_CLOSED] = "CLOSED", + [SCTP_CONNTRACK_COOKIE_WAIT] = "COOKIE_WAIT", + [SCTP_CONNTRACK_COOKIE_ECHOED] = "COOKIE_ECHOED", + [SCTP_CONNTRACK_ESTABLISHED] = "ESTABLISHED", + [SCTP_CONNTRACK_SHUTDOWN_SENT] = "SHUTDOWN_SENT", + [SCTP_CONNTRACK_SHUTDOWN_RECD] = "SHUTDOWN_RECD", + [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = "SHUTDOWN_ACK_SENT", + [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT", }; #define SECS * HZ @@ -54,12 +48,11 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_CLOSED] = 10 SECS, [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, - [SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS, + [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, - [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, }; #define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 @@ -73,7 +66,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { #define sSR SCTP_CONNTRACK_SHUTDOWN_RECD #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sHS SCTP_CONNTRACK_HEARTBEAT_SENT -#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED #define sIV SCTP_CONNTRACK_MAX /* @@ -96,9 +88,6 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. -HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to - that of the HEARTBEAT chunk. Secondary connection is - established. */ /* TODO @@ -115,33 +104,33 @@ cookie echoed to closed. static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA}, -/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA}, -/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sES}, } }; @@ -508,8 +497,12 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } ct->proto.sctp.state = new_state; - if (old_state != new_state) + if (old_state != new_state) { nf_conntrack_event_cache(IPCT_PROTOINFO, ct); + if (new_state == SCTP_CONNTRACK_ESTABLISHED && + !test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) + nf_conntrack_event_cache(IPCT_ASSURED, ct); + } } spin_unlock_bh(&ct->lock); @@ -523,14 +516,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); - if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED && - dir == IP_CT_DIR_REPLY && - new_state == SCTP_CONNTRACK_ESTABLISHED) { - pr_debug("Setting assured bit\n"); - set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_ASSURED, ct); - } - return NF_ACCEPT; out_unlock: diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index a7f88cdf3f87..e12b52019a55 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -583,7 +583,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, - NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, @@ -853,12 +852,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { - .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { @@ -987,7 +980,6 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, XASSIGN(SHUTDOWN_RECD, sn); XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); - XASSIGN(HEARTBEAT_ACKED, sn); #undef XASSIGN #endif } From f84c9b72fb200633774704d8020f769c88a4b249 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 2 Dec 2022 13:51:49 +0000 Subject: [PATCH 1174/4345] perf/x86/amd: fix potential integer overflow on shift of a int commit 08245672cdc6505550d1a5020603b0a8d4a6dcc7 upstream. The left shift of int 32 bit integer constant 1 is evaluated using 32 bit arithmetic and then passed as a 64 bit function argument. In the case where i is 32 or more this can lead to an overflow. Avoid this by shifting using the BIT_ULL macro instead. Fixes: 471af006a747 ("perf/x86/amd: Constrain Large Increment per Cycle events") Signed-off-by: Colin Ian King Signed-off-by: Peter Zijlstra (Intel) Acked-by: Ian Rogers Acked-by: Kim Phillips Link: https://lore.kernel.org/r/20221202135149.1797974-1-colin.i.king@gmail.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/events/amd/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 39eb276d0277..52eba415928a 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -976,7 +976,7 @@ static int __init amd_core_pmu_init(void) * numbered counter following it. */ for (i = 0; i < x86_pmu.num_counters - 1; i += 2) - even_ctr_mask |= 1 << i; + even_ctr_mask |= BIT_ULL(i); pair_constraint = (struct event_constraint) __EVENT_CONSTRAINT(0, even_ctr_mask, 0, From 19f1f99be3716cc08071e25ba159813318ab0d9e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 20 Jun 2022 19:18:15 +0200 Subject: [PATCH 1175/4345] clk: Fix pointer casting to prevent oops in devm_clk_release() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8b3d743fc9e2542822826890b482afabf0e7522a upstream. The release function is called with a pointer to the memory returned by devres_alloc(). I was confused about that by the code before the generalization that used a struct clk **ptr. Reported-by: Marek Szyprowski Fixes: abae8e57e49a ("clk: generalize devm_clk_get() a bit") Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20220620171815.114212-1-u.kleine-koenig@pengutronix.de Tested-by: Marek Szyprowski Tested-by: Linux Kernel Functional Testing Signed-off-by: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- drivers/clk/clk-devres.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index 43ccd20e0298..4fb4fd4b06bd 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -11,7 +11,7 @@ struct devm_clk_state { static void devm_clk_release(struct device *dev, void *res) { - struct devm_clk_state *state = *(struct devm_clk_state **)res; + struct devm_clk_state *state = res; if (state->exit) state->exit(state->clk); From 8d823aaa220eebec88c9f307225d3e163252ea95 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Feb 2023 08:23:27 +0100 Subject: [PATCH 1176/4345] Linux 5.10.166 Link: https://lore.kernel.org/r/20230130134306.862721518@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Shuah Khan Tested-by: Pavel Machek (CIP) Tested-by: Guenter Roeck Tested-by: Linux Kernel Functional Testing Tested-by: Sudip Mukherjee Tested-by: Salvatore Bonaccorso Tested-by: Jon Hunter Tested-by: Allen Pais Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5fbff8603f44..efdfb40a82ab 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 165 +SUBLEVEL = 166 EXTRAVERSION = NAME = Dare mighty things From 332c489d8bb3bcb2cfdbebd1272c4f69226caa56 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Jan 2023 12:14:31 +0000 Subject: [PATCH 1177/4345] ANDROID: add flags variable back to struct proto_ops In commit a3025359ffa7 ("net: remove cmsg restriction from io_uring based send/recvmsg calls") the flags variable was removed from struct proto_ops as it is no longer needed. But the ABI signatures break, so put it back to preserve this, there's no functional change here. Bug: 161946584 Fixes: a3025359ffa7 ("net: remove cmsg restriction from io_uring based send/recvmsg calls") Change-Id: Ic6a868f038701a61c993e18b44cdd8ec8b0a4d58 Signed-off-by: Greg Kroah-Hartman --- include/linux/net.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/net.h b/include/linux/net.h index 3414d63a52f4..e201a7fbf3bc 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -137,6 +137,8 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, struct proto_ops { int family; + unsigned int flags; // ANDROID - removed in 5.10.162, but remains to + // preserve ABI. It is not used anywhere. struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, From 4c961b9302a7ca76a3f3dc6cdafafa62ca2b80dd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 9 Jan 2023 15:53:12 +0000 Subject: [PATCH 1178/4345] ANDROID: fix up struct task_struct ABI change in 5.10.162 In commit 788d0824269b ("io_uring: import 5.15-stable io_uring"), a new field was added to struct task_struct. Move it to the proper location and macro in order to preserve the kernel ABI. Bug: 161946584 Fixes: 788d0824269b ("io_uring: import 5.15-stable io_uring") Signed-off-by: Greg Kroah-Hartman Change-Id: Ib2f65b7c1a973794b7ab525a9304f666ffebc9ee --- include/linux/sched.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index b8b8f18bbbbb..d3cc279a4639 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -901,9 +901,6 @@ struct task_struct { /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; - /* PF_IO_WORKER */ - void *pf_io_worker; - u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME @@ -1379,7 +1376,9 @@ struct task_struct { ANDROID_VENDOR_DATA_ARRAY(1, 64); ANDROID_OEM_DATA_ARRAY(1, 32); - ANDROID_KABI_RESERVE(1); + /* PF_IO_WORKER */ + ANDROID_KABI_USE(1, void *pf_io_worker); + ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); From 1cd4863ea87442b14a9f7c93cef61a419f9079f3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jan 2023 14:46:15 +0000 Subject: [PATCH 1179/4345] ANDROID: struct io_uring ABI preservation hack for 5.10.162 changes In the 5.10.162 release, the io_uring code was synced with the version that is in the 5.15.y kernel tree in order to resolve a huge number of potential, and known, problems with the codebase. This makes for a more secure and easier-to-update-and-maintain 5.10.y kernel tree, so this is a great thing, however this caused some issues when it comes to the Android KABI preservation and checking tools. A number of the io_uring structures get used in other core kernel structures, only as "opaque" pointers, so there is not any real ABI breakage. But, due to the visibility of the structures going away, the CRC values of many scheduler variables and functions were changed. In order to preserve the CRC values, to prevent all device kernels to be forced to rebuild for no reason whatsoever from a functional point of view, we need to keep around the "old" io_uring structures for the CRC calculation only. This is done by the following definitions of struct io_identity and struct io_uring_task which will only be visible when the CRC calculation build happens, not in any functional kernel build. Yes, this all is a horrible hack, and these really are not the true structures that any code uses, but so life is in the world of stable apis. Bug: 161946584 Fixes: 788d0824269b ("io_uring: import 5.15-stable io_uring") Signed-off-by: Greg Kroah-Hartman Change-Id: I2294f220ae78fe9aa32ee25b81829ae765e9deb2 --- include/linux/io_uring.h | 62 ++++++++++++++++++++++++++++++++++++++++ io_uring/io-wq.h | 11 +++++++ io_uring/io_uring.c | 10 +++++++ 3 files changed, 83 insertions(+) diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 649a4d7c241b..5ae871af45de 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,6 +5,68 @@ #include #include +#ifdef __GENKSYMS__ +/* + * ANDROID ABI HACK + * + * In the 5.10.162 release, the io_uring code was synced with the version + * that is in the 5.15.y kernel tree in order to resolve a huge number of + * potential, and known, problems with the codebase. This makes for a more + * secure and easier-to-update-and-maintain 5.10.y kernel tree, so this is + * a great thing, however this caused some issues when it comes to the + * Android KABI preservation and checking tools. + * + * A number of the io_uring structures get used in other core kernel + * structures, only as "opaque" pointers, so there is not any real ABI + * breakage. But, due to the visibility of the structures going away, the + * CRC values of many scheduler variables and functions were changed. + * + * In order to preserve the CRC values, to prevent all device kernels to be + * forced to rebuild for no reason whatsoever from a functional point of + * view, we need to keep around the "old" io_uring structures for the CRC + * calculation only. This is done by the following definitions of struct + * io_identity and struct io_uring_task which will only be visible when the + * CRC calculation build happens, not in any functional kernel build. + * + * Yes, this all is a horrible hack, and these really are not the true + * structures that any code uses, but so life is in the world of stable + * apis... + * The real structures are in io_uring/io_uring.c, see the ones there if + * you need to touch or do anything with it. + * + * NEVER touch these structure definitions, they are fake and not valid code. + */ +struct io_identity { + struct files_struct *files; + struct mm_struct *mm; +#ifdef CONFIG_BLK_CGROUP + struct cgroup_subsys_state *blkcg_css; +#endif + const struct cred *creds; + struct nsproxy *nsproxy; + struct fs_struct *fs; + unsigned long fsize; +#ifdef CONFIG_AUDIT + kuid_t loginuid; + unsigned int sessionid; +#endif + refcount_t count; +}; + +struct io_uring_task { + /* submission side */ + struct xarray xa; + struct wait_queue_head wait; + struct file *last; + struct percpu_counter inflight; + struct io_identity __identity; + struct io_identity *identity; + atomic_t in_idle; + bool sqpoll; +}; +#endif /* ANDROID ABI HACK */ + + #if defined(CONFIG_IO_URING) struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h index bf5c4c533760..300a695d191d 100644 --- a/io_uring/io-wq.h +++ b/io_uring/io-wq.h @@ -1,6 +1,17 @@ #ifndef INTERNAL_IO_WQ_H #define INTERNAL_IO_WQ_H +#ifdef __GENKSYMS__ +/* + * ANDROID ABI HACK + * + * See the big comment in the linux/io_uring.h file for details. This + * include is not needed for any real functionality, but must be here to + * preserve the CRC of a number of variables and functions. + */ +#include +#endif + #include struct io_wq; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 945faf036ad0..35a9bcd5648b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -461,6 +461,15 @@ struct io_ring_ctx { }; }; +#ifndef __GENKSYMS__ +/* + * ANDROID ABI HACK + * + * See the big comment in the linux/io_uring.h file for details. This + * structure definition should NOT be used if __GENKSYMS__ is enabled, + * as a "fake" structure definition has already been read in the + * linux/io_uring.h file in order to preserve the Android kernel ABI. + */ struct io_uring_task { /* submission side */ int cached_refs; @@ -477,6 +486,7 @@ struct io_uring_task { struct callback_head task_work; bool task_running; }; +#endif /* * First field must be the file pointer in all the From 9e60339cb4bbb76b983576d0cc7591c7b892f300 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 3 Feb 2023 05:37:31 +0000 Subject: [PATCH 1180/4345] ANDROID: Update .xml due to ABI preservation fix In commit 4c961b9302a7 ("ANDROID: fix up struct task_struct ABI change in 5.10.162") an ABI-reserved field was used to preserve the overall kernel abi, but the .xml file needs an update to properly reflect the structure change: type 'struct task_struct' changed member 'union { void* pf_io_worker; struct { u64 android_kabi_reserved1; }; union { }; }' was added member 'u64 android_kabi_reserved1' was removed Fixes: 4c961b9302a7 ("ANDROID: fix up struct task_struct ABI change in 5.10.162") Change-Id: I17f944f4222d7b26b2edbe7781325c19b99ba9e4 Signed-off-by: Greg Kroah-Hartman --- android/abi_gki_aarch64.xml | 564 ++++++++++++++++++++---------------- 1 file changed, 318 insertions(+), 246 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 9fb761ab3b74..14cad3ed4d4f 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -13095,6 +13095,7 @@ + @@ -14967,37 +14968,12 @@ - + - - - - - - - - - - - - - - - - - - - - - - - - - - - + + @@ -15330,6 +15306,7 @@ + @@ -22296,6 +22273,11 @@ + + + + + @@ -23524,7 +23506,7 @@ - + @@ -24269,6 +24251,17 @@ + + + + + + + + + + + @@ -25197,6 +25190,17 @@ + + + + + + + + + + + @@ -33703,7 +33707,7 @@ - + @@ -36577,105 +36581,105 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -37895,38 +37899,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -38143,7 +38115,7 @@ - + @@ -45017,7 +44989,11 @@ - + + + + + @@ -50346,6 +50322,7 @@ + @@ -53974,6 +53951,11 @@ + + + + + @@ -62347,15 +62329,15 @@ - + - + - + - + @@ -62789,7 +62771,6 @@ - @@ -63548,18 +63529,18 @@ - + - + - + - + - + @@ -66046,6 +66027,14 @@ + + + + + + + + @@ -68540,6 +68529,11 @@ + + + + + @@ -70010,18 +70004,18 @@ - + - + - + - + - + @@ -72648,6 +72642,7 @@ + @@ -73319,7 +73314,11 @@ - + + + + + @@ -78067,6 +78066,11 @@ + + + + + @@ -82581,6 +82585,7 @@ + @@ -84502,6 +84507,12 @@ + + + + + + @@ -85365,31 +85376,31 @@ - + - + - + - + - + - + - + - + - + @@ -86322,6 +86333,7 @@ + @@ -88883,6 +88895,53 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -90400,6 +90459,7 @@ + @@ -91639,6 +91699,7 @@ + @@ -95607,6 +95668,17 @@ + + + + + + + + + + + @@ -103588,12 +103660,12 @@ - + - + - + @@ -106367,12 +106439,12 @@ - + - + - + @@ -108877,27 +108949,27 @@ - + - + - + - + - + - + - + - + @@ -110605,21 +110677,21 @@ - + - + - + - + - + - + @@ -116490,9 +116562,9 @@ - - - + + + @@ -116830,8 +116902,8 @@ - - + + @@ -130512,27 +130584,27 @@ - - + + - - + + - - + + - - - - + + + + - - - + + + @@ -130629,13 +130701,13 @@ - - - + + + - - + + @@ -130716,21 +130788,21 @@ - - - + + + - - - - + + + + - - - - + + + + @@ -131255,10 +131327,10 @@ - - - - + + + + @@ -131536,9 +131608,9 @@ - - - + + + @@ -131815,12 +131887,12 @@ - - + + - - + + @@ -131847,8 +131919,8 @@ - - + + @@ -132261,9 +132333,9 @@ - - - + + + @@ -134275,11 +134347,11 @@ - - - - - + + + + + @@ -134368,33 +134440,33 @@ - - - - + + + + - - - - + + + + - - - - - + + + + + - - - + + + @@ -134436,14 +134508,14 @@ - - - + + + - - - + + + @@ -136236,8 +136308,8 @@ - - + + @@ -136755,9 +136827,9 @@ - - - + + + @@ -137740,10 +137812,10 @@ - - - - + + + + @@ -137791,10 +137863,10 @@ - - - - + + + + @@ -140023,8 +140095,8 @@ - - + + @@ -142873,10 +142945,10 @@ - - - - + + + + @@ -144500,8 +144572,8 @@ - - + + @@ -144516,8 +144588,8 @@ - - + + @@ -144884,9 +144956,9 @@ - - - + + + From 67a8beb8544e4b15ea27620439b1c63c3fbdd187 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 2 Dec 2022 17:49:18 +0100 Subject: [PATCH 1181/4345] ARM: dts: imx: Fix pca9547 i2c-mux node name [ Upstream commit f78985f9f58380eec37f82c8a2c765aa7670fc29 ] "make dtbs_check": arch/arm/boot/dts/imx53-ppd.dtb: i2c-switch@70: $nodename:0: 'i2c-switch@70' does not match '^(i2c-?)?mux' From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml arch/arm/boot/dts/imx53-ppd.dtb: i2c-switch@70: Unevaluated properties are not allowed ('#address-cells', '#size-cells', 'i2c@0', 'i2c@1', 'i2c@2', 'i2c@3', 'i2c@4', 'i2c@5', 'i2c@6', 'i2c@7' were unexpected) From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml Fix this by renaming the PCA9547 node to "i2c-mux", to match the I2C bus multiplexer/switch DT bindings and the Generic Names Recommendation in the Devicetree Specification. Signed-off-by: Geert Uytterhoeven Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx53-ppd.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts index 006fbd7f5432..54e39db447c4 100644 --- a/arch/arm/boot/dts/imx53-ppd.dts +++ b/arch/arm/boot/dts/imx53-ppd.dts @@ -487,7 +487,7 @@ scl-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; status = "okay"; - i2c-switch@70 { + i2c-mux@70 { compatible = "nxp,pca9547"; #address-cells = <1>; #size-cells = <0>; From a26cef004146cc49463e88a8511269d5a414067e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 2 Dec 2022 17:49:21 +0100 Subject: [PATCH 1182/4345] ARM: dts: vf610: Fix pca9548 i2c-mux node names [ Upstream commit 42825d1f269355d63554ab3c3762611e4d8053e9 ] "make dtbs_check": arch/arm/boot/dts/vf610-zii-dev-rev-b.dtb: tca9548@70: $nodename:0: 'tca9548@70' does not match '^(i2c-?)?mux' From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml arch/arm/boot/dts/vf610-zii-dev-rev-b.dtb: tca9548@70: Unevaluated properties are not allowed ('#address-cells', '#size-cells', 'i2c@0', 'i2c@1', 'i2c@2', 'i2c@3', 'i2c@4' were unexpected) From schema: /scratch/geert/linux/linux-renesas/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml ... Fix this by renaming PCA9548 nodes to "i2c-mux", to match the I2C bus multiplexer/switch DT bindings and the Generic Names Recommendation in the Devicetree Specification. Signed-off-by: Geert Uytterhoeven Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/vf610-zii-dev-rev-b.dts | 2 +- arch/arm/boot/dts/vf610-zii-dev-rev-c.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts index 6f1e0f0d4f0a..073f5d196ca9 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts @@ -345,7 +345,7 @@ }; &i2c2 { - tca9548@70 { + i2c-mux@70 { compatible = "nxp,pca9548"; pinctrl-0 = <&pinctrl_i2c_mux_reset>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts index de79dcfd32e6..ba2001f37315 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts @@ -340,7 +340,7 @@ }; &i2c2 { - tca9548@70 { + i2c-mux@70 { compatible = "nxp,pca9548"; pinctrl-0 = <&pinctrl_i2c_mux_reset>; pinctrl-names = "default"; From f185468631238a98c0cf98e0403a90dc3eab5c70 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 4 Dec 2022 10:44:17 +0100 Subject: [PATCH 1183/4345] arm64: dts: imx8mq-thor96: fix no-mmc property for SDHCI [ Upstream commit ef10d57936ead5e817ef7cea6a87531085e77773 ] There is no "no-emmc" property, so intention for SD/SDIO only nodes was to use "no-mmc". Signed-off-by: Krzysztof Kozlowski Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mq-thor96.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts b/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts index 5d5aa6537225..6e6182709d22 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts @@ -339,7 +339,7 @@ bus-width = <4>; non-removable; no-sd; - no-emmc; + no-mmc; status = "okay"; brcmf: wifi@1 { @@ -359,7 +359,7 @@ cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>; bus-width = <4>; no-sdio; - no-emmc; + no-mmc; disable-wp; status = "okay"; }; From a1c0263f1eb4deee132e11e52ee6982435460d81 Mon Sep 17 00:00:00 2001 From: Hao Sun Date: Fri, 6 Jan 2023 16:48:38 +0800 Subject: [PATCH 1184/4345] bpf: Skip task with pid=1 in send_signal_common() [ Upstream commit a3d81bc1eaef48e34dd0b9b48eefed9e02a06451 ] The following kernel panic can be triggered when a task with pid=1 attaches a prog that attempts to send killing signal to itself, also see [1] for more details: Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b CPU: 3 PID: 1 Comm: systemd Not tainted 6.1.0-09652-g59fe41b5255f #148 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x100/0x178 lib/dump_stack.c:106 panic+0x2c4/0x60f kernel/panic.c:275 do_exit.cold+0x63/0xe4 kernel/exit.c:789 do_group_exit+0xd4/0x2a0 kernel/exit.c:950 get_signal+0x2460/0x2600 kernel/signal.c:2858 arch_do_signal_or_restart+0x78/0x5d0 arch/x86/kernel/signal.c:306 exit_to_user_mode_loop kernel/entry/common.c:168 [inline] exit_to_user_mode_prepare+0x15f/0x250 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x1d/0x50 kernel/entry/common.c:296 do_syscall_64+0x44/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd So skip task with pid=1 in bpf_send_signal_common() to avoid the panic. [1] https://lore.kernel.org/bpf/20221222043507.33037-1-sunhao.th@gmail.com Signed-off-by: Hao Sun Signed-off-by: Daniel Borkmann Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20230106084838.12690-1-sunhao.th@gmail.com Signed-off-by: Sasha Levin --- kernel/trace/bpf_trace.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a9e074769881..ab4f51716645 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1072,6 +1072,9 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; + /* Task should not be pid=1 to avoid kernel panic. */ + if (unlikely(is_global_init(current))) + return -EPERM; if (irqs_disabled()) { /* Do an early check on signal validity. Otherwise, From 19c9a2ba46996f2dbc5bfbf1e8f3dc50b347c91c Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 3 Jan 2023 19:28:33 +0800 Subject: [PATCH 1185/4345] blk-cgroup: fix missing pd_online_fn() while activating policy [ Upstream commit e3ff8887e7db757360f97634e0d6f4b8e27a8c46 ] If the policy defines pd_online_fn(), it should be called after pd_init_fn(), like blkg_create(). Signed-off-by: Yu Kuai Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20230103112833.2013432-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-cgroup.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 484c6b2dd264..c623632c1cda 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1370,6 +1370,10 @@ retry: list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) pol->pd_init_fn(blkg->pd[pol->plid]); + if (pol->pd_online_fn) + list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) + pol->pd_online_fn(blkg->pd[pol->plid]); + __set_bit(pol->plid, q->blkcg_pols); ret = 0; From bd0050b7ffa87c7b260d563646af612f4112a778 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Wed, 30 Nov 2022 17:08:00 +0800 Subject: [PATCH 1186/4345] dmaengine: imx-sdma: Fix a possible memory leak in sdma_transfer_init [ Upstream commit 1417f59ac0b02130ee56c0c50794b9b257be3d17 ] If the function sdma_load_context() fails, the sdma_desc will be freed, but the allocated desc->bd is forgot to be freed. We already met the sdma_load_context() failure case and the log as below: [ 450.699064] imx-sdma 30bd0000.dma-controller: Timeout waiting for CH0 ready ... In this case, the desc->bd will not be freed without this change. Signed-off-by: Hui Wang Reviewed-by: Sascha Hauer Link: https://lore.kernel.org/r/20221130090800.102035-1-hui.wang@canonical.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/imx-sdma.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 2283dcd8bf91..6514db824473 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1363,10 +1363,12 @@ static struct sdma_desc *sdma_transfer_init(struct sdma_channel *sdmac, sdma_config_ownership(sdmac, false, true, false); if (sdma_load_context(sdmac)) - goto err_desc_out; + goto err_bd_out; return desc; +err_bd_out: + sdma_free_bd(desc); err_desc_out: kfree(desc); err_out: From d744c03c04a76b3732b18c034bb5d872c3808b7b Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Thu, 22 Sep 2022 11:47:45 -0700 Subject: [PATCH 1187/4345] ACPI: processor idle: Practically limit "Dummy wait" workaround to old Intel systems commit e400ad8b7e6a1b9102123c6240289a811501f7d9 upstream. Old, circa 2002 chipsets have a bug: they don't go idle when they are supposed to. So, a workaround was added to slow the CPU down and ensure that the CPU waits a bit for the chipset to actually go idle. This workaround is ancient and has been in place in some form since the original kernel ACPI implementation. But, this workaround is very painful on modern systems. The "inl()" can take thousands of cycles (see Link: for some more detailed numbers and some fun kernel archaeology). First and foremost, modern systems should not be using this code. Typical Intel systems have not used it in over a decade because it is horribly inferior to MWAIT-based idle. Despite this, people do seem to be tripping over this workaround on AMD system today. Limit the "dummy wait" workaround to Intel systems. Keep Modern AMD systems from tripping over the workaround. Remotely modern Intel systems use intel_idle instead of this code and will, in practice, remain unaffected by the dummy wait. Reported-by: K Prateek Nayak Suggested-by: Rafael J. Wysocki Signed-off-by: Dave Hansen Reviewed-by: Mario Limonciello Tested-by: K Prateek Nayak Link: https://lore.kernel.org/all/20220921063638.2489-1-kprateek.nayak@amd.com/ Link: https://lkml.kernel.org/r/20220922184745.3252932-1-dave.hansen@intel.com Signed-off-by: Guilherme G. Piccoli Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/processor_idle.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index e5dd87ddc6b3..59781e765e0e 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -536,10 +536,27 @@ static void wait_for_freeze(void) /* No delay is needed if we are in guest */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) return; + /* + * Modern (>=Nehalem) Intel systems use ACPI via intel_idle, + * not this code. Assume that any Intel systems using this + * are ancient and may need the dummy wait. This also assumes + * that the motivating chipset issue was Intel-only. + */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; #endif - /* Dummy wait op - must do something useless after P_LVL2 read - because chipsets cannot guarantee that STPCLK# signal - gets asserted in time to freeze execution properly. */ + /* + * Dummy wait op - must do something useless after P_LVL2 read + * because chipsets cannot guarantee that STPCLK# signal gets + * asserted in time to freeze execution properly + * + * This workaround has been in place since the original ACPI + * implementation was merged, circa 2002. + * + * If a profile is pointing to this instruction, please first + * consider moving your system to a more modern idle + * mechanism. + */ inl(acpi_gbl_FADT.xpm_timer_block.address); } From 0f9db1209f59844839175b5b907d3778cafde93d Mon Sep 17 00:00:00 2001 From: Soenke Huster Date: Fri, 14 Jan 2022 17:44:02 +0100 Subject: [PATCH 1188/4345] Bluetooth: fix null ptr deref on hci_sync_conn_complete_evt commit 3afee2118132e93e5f6fa636dfde86201a860ab3 upstream. This event is just specified for SCO and eSCO link types. On the reception of a HCI_Synchronous_Connection_Complete for a BDADDR of an existing LE connection, LE link type and a status that triggers the second case of the packet processing a NULL pointer dereference happens, as conn->link is NULL. Signed-off-by: Soenke Huster Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/hci_event.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 954b29605c94..eb111504afc6 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4307,6 +4307,19 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, struct hci_ev_sync_conn_complete *ev = (void *) skb->data; struct hci_conn *conn; + switch (ev->link_type) { + case SCO_LINK: + case ESCO_LINK: + break; + default: + /* As per Core 5.3 Vol 4 Part E 7.7.35 (p.2219), Link_Type + * for HCI_Synchronous_Connection_Complete is limited to + * either SCO or eSCO + */ + bt_dev_err(hdev, "Ignoring connect complete event for invalid link type"); + return; + } + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); From 6446369fb9f083ce032448c5047da08e298b22e6 Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Mon, 30 Jan 2023 12:51:48 -0800 Subject: [PATCH 1189/4345] net: fix NULL pointer in skb_segment_list commit 876e8ca8366735a604bac86ff7e2732fc9d85d2d upstream. Commit 3a1296a38d0c ("net: Support GRO/GSO fraglist chaining.") introduced UDP listifyed GRO. The segmentation relies on frag_list being untouched when passing through the network stack. This assumption can be broken sometimes, where frag_list itself gets pulled into linear area, leaving frag_list being NULL. When this happens it can trigger following NULL pointer dereference, and panic the kernel. Reverse the test condition should fix it. [19185.577801][ C1] BUG: kernel NULL pointer dereference, address: ... [19185.663775][ C1] RIP: 0010:skb_segment_list+0x1cc/0x390 ... [19185.834644][ C1] Call Trace: [19185.841730][ C1] [19185.848563][ C1] __udp_gso_segment+0x33e/0x510 [19185.857370][ C1] inet_gso_segment+0x15b/0x3e0 [19185.866059][ C1] skb_mac_gso_segment+0x97/0x110 [19185.874939][ C1] __skb_gso_segment+0xb2/0x160 [19185.883646][ C1] udp_queue_rcv_skb+0xc3/0x1d0 [19185.892319][ C1] udp_unicast_rcv_skb+0x75/0x90 [19185.900979][ C1] ip_protocol_deliver_rcu+0xd2/0x200 [19185.910003][ C1] ip_local_deliver_finish+0x44/0x60 [19185.918757][ C1] __netif_receive_skb_one_core+0x8b/0xa0 [19185.927834][ C1] process_backlog+0x88/0x130 [19185.935840][ C1] __napi_poll+0x27/0x150 [19185.943447][ C1] net_rx_action+0x27e/0x5f0 [19185.951331][ C1] ? mlx5_cq_tasklet_cb+0x70/0x160 [mlx5_core] [19185.960848][ C1] __do_softirq+0xbc/0x25d [19185.968607][ C1] irq_exit_rcu+0x83/0xb0 [19185.976247][ C1] common_interrupt+0x43/0xa0 [19185.984235][ C1] asm_common_interrupt+0x22/0x40 ... [19186.094106][ C1] Fixes: 3a1296a38d0c ("net: Support GRO/GSO fraglist chaining.") Suggested-by: Daniel Borkmann Reviewed-by: Willem de Bruijn Signed-off-by: Yan Zhai Acked-by: Daniel Borkmann Link: https://lore.kernel.org/r/Y9gt5EUizK1UImEP@debian Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/core/skbuff.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2b12e0730b85..668a9d0fbbc6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3688,7 +3688,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_shinfo(skb)->frag_list = NULL; - do { + while (list_skb) { nskb = list_skb; list_skb = list_skb->next; @@ -3732,8 +3732,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, if (skb_needs_linearize(nskb, features) && __skb_linearize(nskb)) goto err_linearize; - - } while (list_skb); + } skb->truesize = skb->truesize - delta_truesize; skb->data_len = skb->data_len - delta_len; From a5acb54d4066f27e9707af9d93f047f542d5ad88 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 6 Feb 2023 07:56:16 +0100 Subject: [PATCH 1190/4345] Linux 5.10.167 Link: https://lore.kernel.org/r/20230203101006.422534094@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Shuah Khan Tested-by: Guenter Roeck Tested-by: Linux Kernel Functional Testing Tested-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index efdfb40a82ab..84b78e657357 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 166 +SUBLEVEL = 167 EXTRAVERSION = NAME = Dare mighty things From a234cc4e557764c893b5f6ffab72f4fea73ea0cf Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 9 Dec 2020 20:19:15 +0200 Subject: [PATCH 1191/4345] UPSTREAM: um: Increase stack frame size threshold for signal.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The signal.c can't use heap for bit data located on stack. However, by default a compiler warns us about overstepping stack frame size threshold: arch/um/os-Linux/signal.c: In function ‘sig_handler_common’: arch/um/os-Linux/signal.c:51:1: warning: the frame size of 2960 bytes is larger than 2048 bytes [-Wframe-larger-than=] 51 | } | ^ arch/um/os-Linux/signal.c: In function ‘timer_real_alarm_handler’: arch/um/os-Linux/signal.c:95:1: warning: the frame size of 2960 bytes is larger than 2048 bytes [-Wframe-larger-than=] 95 | } | ^ Due to above increase stack frame size threshold explicitly for signal.c to avoid unnecessary warning. Bug: 269057599 Change-Id: Ib7474bddfefa97f9c60087db6a607a111e4d23bc Signed-off-by: Andy Shevchenko Tested-by: David Gow Signed-off-by: Richard Weinberger (cherry picked from commit 517f60206ee5d5f75c44bd9c8b1683d1d18a616a) Signed-off-by: Srinivasarao Pathipati --- arch/um/os-Linux/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile index 839915b8c31c..77ac50baa3f8 100644 --- a/arch/um/os-Linux/Makefile +++ b/arch/um/os-Linux/Makefile @@ -10,6 +10,8 @@ obj-y = execvp.o file.o helper.o irq.o main.o mem.o process.o \ registers.o sigio.o signal.o start_up.o time.o tty.o \ umid.o user_syms.o util.o drivers/ skas/ +CFLAGS_signal.o += -Wframe-larger-than=4096 + obj-$(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) += elf_aux.o USER_OBJS := $(user-objs-y) elf_aux.o execvp.o file.o helper.o irq.o \ From f1242cd1469bde79e27d8cb3c30c3fe635c96797 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 15 Feb 2023 14:56:51 +0000 Subject: [PATCH 1192/4345] Revert "PM/devfreq: governor: Add a private governor_data for governor" This reverts commit cea018aaf7218a50bdbf17540b311e6b2982d883 which is commit 5fdded8448924e3631d466eea499b11606c43640 upstream. It breaks the Android kernel api and is not needed for Android systems as they do not support this type of functionality. If it is needed to be brought back in the future, it can be done so in a way that does not break the ABI. Bug: 161946584 Fixes: cea018aaf721 ("PM/devfreq: governor: Add a private governor_data for governor") Signed-off-by: Greg Kroah-Hartman Change-Id: I0107d52a8f445548f7de462315dbe99ec4ab3d98 --- drivers/devfreq/devfreq.c | 6 ++++-- drivers/devfreq/governor_userspace.c | 12 ++++++------ include/linux/devfreq.h | 7 +++---- 3 files changed, 13 insertions(+), 12 deletions(-) diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index c6f460550f5e..829128c0cc68 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -740,7 +740,8 @@ static void devfreq_dev_release(struct device *dev) * @dev: the device to add devfreq feature. * @profile: device-specific profile to run devfreq. * @governor_name: name of the policy to choose frequency. - * @data: devfreq driver pass to governors, governor should not change it. + * @data: private data for the governor. The devfreq framework does not + * touch this value. */ struct devfreq *devfreq_add_device(struct device *dev, struct devfreq_dev_profile *profile, @@ -952,7 +953,8 @@ static void devm_devfreq_dev_release(struct device *dev, void *res) * @dev: the device to add devfreq feature. * @profile: device-specific profile to run devfreq. * @governor_name: name of the policy to choose frequency. - * @data: devfreq driver pass to governors, governor should not change it. + * @data: private data for the governor. The devfreq framework does not + * touch this value. * * This function manages automatically the memory of devfreq device using device * resource management and simplify the free operation for memory of devfreq diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c index 8a9cf8220808..0fd6c4851071 100644 --- a/drivers/devfreq/governor_userspace.c +++ b/drivers/devfreq/governor_userspace.c @@ -21,7 +21,7 @@ struct userspace_data { static int devfreq_userspace_func(struct devfreq *df, unsigned long *freq) { - struct userspace_data *data = df->governor_data; + struct userspace_data *data = df->data; if (data->valid) *freq = data->user_frequency; @@ -40,7 +40,7 @@ static ssize_t store_freq(struct device *dev, struct device_attribute *attr, int err = 0; mutex_lock(&devfreq->lock); - data = devfreq->governor_data; + data = devfreq->data; sscanf(buf, "%lu", &wanted); data->user_frequency = wanted; @@ -60,7 +60,7 @@ static ssize_t show_freq(struct device *dev, struct device_attribute *attr, int err = 0; mutex_lock(&devfreq->lock); - data = devfreq->governor_data; + data = devfreq->data; if (data->valid) err = sprintf(buf, "%lu\n", data->user_frequency); @@ -91,7 +91,7 @@ static int userspace_init(struct devfreq *devfreq) goto out; } data->valid = false; - devfreq->governor_data = data; + devfreq->data = data; err = sysfs_create_group(&devfreq->dev.kobj, &dev_attr_group); out: @@ -107,8 +107,8 @@ static void userspace_exit(struct devfreq *devfreq) if (devfreq->dev.kobj.sd) sysfs_remove_group(&devfreq->dev.kobj, &dev_attr_group); - kfree(devfreq->governor_data); - devfreq->governor_data = NULL; + kfree(devfreq->data); + devfreq->data = NULL; } static int devfreq_userspace_handler(struct devfreq *devfreq, diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index fc4c7ad49cee..121a2430d7f7 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -146,8 +146,8 @@ struct devfreq_stats { * @work: delayed work for load monitoring. * @previous_freq: previously configured frequency value. * @last_status: devfreq user device info, performance statistics - * @data: devfreq driver pass to governors, governor should not change it. - * @governor_data: private data for governors, devfreq core doesn't touch it. + * @data: Private data of the governor. The devfreq framework does not + * touch this. * @user_min_freq_req: PM QoS minimum frequency request from user (via sysfs) * @user_max_freq_req: PM QoS maximum frequency request from user (via sysfs) * @scaling_min_freq: Limit minimum frequency requested by OPP interface @@ -183,8 +183,7 @@ struct devfreq { unsigned long previous_freq; struct devfreq_dev_status last_status; - void *data; - void *governor_data; + void *data; /* private data for governors */ struct dev_pm_qos_request user_min_freq_req; struct dev_pm_qos_request user_max_freq_req; From c35badfe0d91b25312d195422c6525c89faf925e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 19 Jan 2023 11:36:11 +0000 Subject: [PATCH 1193/4345] Revert "net: add atomic_long_t to net_device_stats fields" This reverts commit 037db10e3f93f0d51ab3f52fbdaa7e67a7edd0b8 which is commit 6c1c5097781f563b70a81683ea6fdac21637573b upstream. It breaks the CRC checking for the Android KABI (doesn't really break any actual ABI, but it isn't nice.) As this isn't needed for Android systems at this point in time, just revert it to keep the CRC abi stable. If it is needed to come back, it can be reworked to be a CRC-abi neutral change if so desired. Bug: 161946584 Fixes: 037db10e3f93 ("net: add atomic_long_t to net_device_stats fields") Cc: Eric Dumazet Change-Id: I9d3d9fb55ab5482a4ea92fcc4a2fb70c4471edec Signed-off-by: Greg Kroah-Hartman --- include/linux/netdevice.h | 58 ++++++++++++++++----------------------- include/net/dst.h | 5 ++-- net/core/dev.c | 14 ++++++++-- 3 files changed, 37 insertions(+), 40 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 297a037a77f5..7e7a003dd25a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -167,38 +167,31 @@ static inline bool dev_xmit_complete(int rc) * (unsigned long) so they can be read and written atomically. */ -#define NET_DEV_STAT(FIELD) \ - union { \ - unsigned long FIELD; \ - atomic_long_t __##FIELD; \ - } - struct net_device_stats { - NET_DEV_STAT(rx_packets); - NET_DEV_STAT(tx_packets); - NET_DEV_STAT(rx_bytes); - NET_DEV_STAT(tx_bytes); - NET_DEV_STAT(rx_errors); - NET_DEV_STAT(tx_errors); - NET_DEV_STAT(rx_dropped); - NET_DEV_STAT(tx_dropped); - NET_DEV_STAT(multicast); - NET_DEV_STAT(collisions); - NET_DEV_STAT(rx_length_errors); - NET_DEV_STAT(rx_over_errors); - NET_DEV_STAT(rx_crc_errors); - NET_DEV_STAT(rx_frame_errors); - NET_DEV_STAT(rx_fifo_errors); - NET_DEV_STAT(rx_missed_errors); - NET_DEV_STAT(tx_aborted_errors); - NET_DEV_STAT(tx_carrier_errors); - NET_DEV_STAT(tx_fifo_errors); - NET_DEV_STAT(tx_heartbeat_errors); - NET_DEV_STAT(tx_window_errors); - NET_DEV_STAT(rx_compressed); - NET_DEV_STAT(tx_compressed); + unsigned long rx_packets; + unsigned long tx_packets; + unsigned long rx_bytes; + unsigned long tx_bytes; + unsigned long rx_errors; + unsigned long tx_errors; + unsigned long rx_dropped; + unsigned long tx_dropped; + unsigned long multicast; + unsigned long collisions; + unsigned long rx_length_errors; + unsigned long rx_over_errors; + unsigned long rx_crc_errors; + unsigned long rx_frame_errors; + unsigned long rx_fifo_errors; + unsigned long rx_missed_errors; + unsigned long tx_aborted_errors; + unsigned long tx_carrier_errors; + unsigned long tx_fifo_errors; + unsigned long tx_heartbeat_errors; + unsigned long tx_window_errors; + unsigned long rx_compressed; + unsigned long tx_compressed; }; -#undef NET_DEV_STAT #include @@ -5310,9 +5303,4 @@ do { \ extern struct net_device *blackhole_netdev; -/* Note: Avoid these macros in fast path, prefer per-cpu or per-queue counters. */ -#define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD) -#define DEV_STATS_ADD(DEV, FIELD, VAL) \ - atomic_long_add((VAL), &(DEV)->stats.__##FIELD) - #endif /* _LINUX_NETDEVICE_H */ diff --git a/include/net/dst.h b/include/net/dst.h index ae2cf57d796b..acd15c544cf3 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -356,8 +356,9 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { - DEV_STATS_INC(dev, rx_packets); - DEV_STATS_ADD(dev, rx_bytes, skb->len); + /* TODO : stats should be SMP safe */ + dev->stats.rx_packets++; + dev->stats.rx_bytes += skb->len; __skb_tunnel_rx(skb, dev, net); } diff --git a/net/core/dev.c b/net/core/dev.c index 5a31c6085a37..149504ef8f07 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10325,16 +10325,24 @@ void netdev_run_todo(void) void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { - size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); - const atomic_long_t *src = (atomic_long_t *)netdev_stats; +#if BITS_PER_LONG == 64 + BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats)); + memcpy(stats64, netdev_stats, sizeof(*netdev_stats)); + /* zero out counters that only exist in rtnl_link_stats64 */ + memset((char *)stats64 + sizeof(*netdev_stats), 0, + sizeof(*stats64) - sizeof(*netdev_stats)); +#else + size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long); + const unsigned long *src = (const unsigned long *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) - dst[i] = atomic_long_read(&src[i]); + dst[i] = src[i]; /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); +#endif } EXPORT_SYMBOL(netdev_stats_to_stats64); From d5a2dcee53fa6e6e2822f93cb3f1b0cd23163bee Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Tue, 17 Jan 2023 18:06:10 +0900 Subject: [PATCH 1194/4345] firewire: fix memory leak for payload of request subaction to IEC 61883-1 FCP region commit 531390a243ef47448f8bad01c186c2787666bf4d upstream. This patch is fix for Linux kernel v2.6.33 or later. For request subaction to IEC 61883-1 FCP region, Linux FireWire subsystem have had an issue of use-after-free. The subsystem allows multiple user space listeners to the region, while data of the payload was likely released before the listeners execute read(2) to access to it for copying to user space. The issue was fixed by a commit 281e20323ab7 ("firewire: core: fix use-after-free regression in FCP handler"). The object of payload is duplicated in kernel space for each listener. When the listener executes ioctl(2) with FW_CDEV_IOC_SEND_RESPONSE request, the object is going to be released. However, it causes memory leak since the commit relies on call of release_request() in drivers/firewire/core-cdev.c. Against the expectation, the function is never called due to the design of release_client_resource(). The function delegates release task to caller when called with non-NULL fourth argument. The implementation of ioctl_send_response() is the case. It should release the object explicitly. This commit fixes the bug. Cc: Fixes: 281e20323ab7 ("firewire: core: fix use-after-free regression in FCP handler") Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20230117090610.93792-2-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- drivers/firewire/core-cdev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index b0cc3f1e9bb0..16ea847ade5f 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -818,8 +818,10 @@ static int ioctl_send_response(struct client *client, union ioctl_arg *arg) r = container_of(resource, struct inbound_transaction_resource, resource); - if (is_fcp_request(r->request)) + if (is_fcp_request(r->request)) { + kfree(r->data); goto out; + } if (a->length != fw_get_response_length(r->request)) { ret = -EINVAL; From 60c27e0e37c82935ea5495172e090c0416b91d6e Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Wed, 23 Nov 2022 09:42:00 +0000 Subject: [PATCH 1195/4345] bus: sunxi-rsb: Fix error handling in sunxi_rsb_init() [ Upstream commit f71eaf2708be7831428eacae7db25d8ec6b8b4c5 ] The sunxi_rsb_init() returns the platform_driver_register() directly without checking its return value, if platform_driver_register() failed, the sunxi_rsb_bus is not unregistered. Fix by unregister sunxi_rsb_bus when platform_driver_register() failed. Fixes: d787dcdb9c8f ("bus: sunxi-rsb: Add driver for Allwinner Reduced Serial Bus") Signed-off-by: Yuan Can Reviewed-by: Jernej Skrabec Link: https://lore.kernel.org/r/20221123094200.12036-1-yuancan@huawei.com Signed-off-by: Jernej Skrabec Signed-off-by: Sasha Levin --- drivers/bus/sunxi-rsb.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index f8c29b888e6b..98cbb18f17fa 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -781,7 +781,13 @@ static int __init sunxi_rsb_init(void) return ret; } - return platform_driver_register(&sunxi_rsb_driver); + ret = platform_driver_register(&sunxi_rsb_driver); + if (ret) { + bus_unregister(&sunxi_rsb_bus); + return ret; + } + + return 0; } module_init(sunxi_rsb_init); From 9ff2bebc2ceaa2f2ab795093aee1b0ce3fc4ab5f Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Fri, 10 Dec 2021 00:46:31 +0100 Subject: [PATCH 1196/4345] bpf: Fix incorrect state pruning for <8B spill/fill commit 345e004d023343d38088fdfea39688aa11e06ccf upstream. Commit 354e8f1970f8 ("bpf: Support <8-byte scalar spill and refill") introduced support in the verifier to track <8B spill/fills of scalars. The backtracking logic for the precision bit was however skipping spill/fills of less than 8B. That could cause state pruning to consider two states equivalent when they shouldn't be. As an example, consider the following bytecode snippet: 0: r7 = r1 1: call bpf_get_prandom_u32 2: r6 = 2 3: if r0 == 0 goto pc+1 4: r6 = 3 ... 8: [state pruning point] ... /* u32 spill/fill */ 10: *(u32 *)(r10 - 8) = r6 11: r8 = *(u32 *)(r10 - 8) 12: r0 = 0 13: if r8 == 3 goto pc+1 14: r0 = 1 15: exit The verifier first walks the path with R6=3. Given the support for <8B spill/fills, at instruction 13, it knows the condition is true and skips instruction 14. At that point, the backtracking logic kicks in but stops at the fill instruction since it only propagates the precision bit for 8B spill/fill. When the verifier then walks the path with R6=2, it will consider it safe at instruction 8 because R6 is not marked as needing precision. Instruction 14 is thus never walked and is then incorrectly removed as 'dead code'. It's also possible to lead the verifier to accept e.g. an out-of-bound memory access instead of causing an incorrect dead code elimination. This regression was found via Cilium's bpf-next CI where it was causing a conntrack map update to be silently skipped because the code had been removed by the verifier. This commit fixes it by enabling support for <8B spill/fills in the bactracking logic. In case of a <8B spill/fill, the full 8B stack slot will be marked as needing precision. Then, in __mark_chain_precision, any tracked register spilled in a marked slot will itself be marked as needing precision, regardless of the spill size. This logic makes two assumptions: (1) only 8B-aligned spill/fill are tracked and (2) spilled registers are only tracked if the spill and fill sizes are equal. Commit ef979017b837 ("bpf: selftest: Add verifier tests for <8-byte scalar spill and refill") covers the first assumption and the next commit in this patchset covers the second. Fixes: 354e8f1970f8 ("bpf: Support <8-byte scalar spill and refill") Signed-off-by: Paul Chaignon Signed-off-by: Alexei Starovoitov Signed-off-by: Greg Kroah-Hartman --- kernel/bpf/verifier.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a6c931fed39b..72b7fdcc08cc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1876,8 +1876,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ if (insn->src_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be @@ -1900,8 +1898,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, /* scalars can only be spilled into stack */ if (insn->dst_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); From 2d0f276d504fb41f07ba806dfe1ba7eecad6feb8 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 30 Jan 2023 12:44:01 +1100 Subject: [PATCH 1197/4345] powerpc/imc-pmu: Revert nest_init_lock to being a mutex commit ad53db4acb415976761d7302f5b02e97f2bd097e upstream. The recent commit 76d588dddc45 ("powerpc/imc-pmu: Fix use of mutex in IRQs disabled section") fixed warnings (and possible deadlocks) in the IMC PMU driver by converting the locking to use spinlocks. It also converted the init-time nest_init_lock to a spinlock, even though it's not used at runtime in IRQ disabled sections or while holding other spinlocks. This leads to warnings such as: BUG: sleeping function called from invalid context at include/linux/percpu-rwsem.h:49 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0 preempt_count: 1, expected: 0 CPU: 7 PID: 1 Comm: swapper/0 Not tainted 6.2.0-rc2-14719-gf12cd06109f4-dirty #1 Hardware name: Mambo,Simulated-System POWER9 0x4e1203 opal:v6.6.6 PowerNV Call Trace: dump_stack_lvl+0x74/0xa8 (unreliable) __might_resched+0x178/0x1a0 __cpuhp_setup_state+0x64/0x1e0 init_imc_pmu+0xe48/0x1250 opal_imc_counters_probe+0x30c/0x6a0 platform_probe+0x78/0x110 really_probe+0x104/0x420 __driver_probe_device+0xb0/0x170 driver_probe_device+0x58/0x180 __driver_attach+0xd8/0x250 bus_for_each_dev+0xb4/0x140 driver_attach+0x34/0x50 bus_add_driver+0x1e8/0x2d0 driver_register+0xb4/0x1c0 __platform_driver_register+0x38/0x50 opal_imc_driver_init+0x2c/0x40 do_one_initcall+0x80/0x360 kernel_init_freeable+0x310/0x3b8 kernel_init+0x30/0x1a0 ret_from_kernel_thread+0x5c/0x64 Fix it by converting nest_init_lock back to a mutex, so that we can call sleeping functions while holding it. There is no interaction between nest_init_lock and the runtime spinlocks used by the actual PMU routines. Fixes: 76d588dddc45 ("powerpc/imc-pmu: Fix use of mutex in IRQs disabled section") Tested-by: Kajol Jain Reviewed-by: Kajol Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230130014401.540543-1-mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/perf/imc-pmu.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index e42c2fe3dd36..b773c411aa5c 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -21,7 +21,7 @@ * Used to avoid races in counting the nest-pmu units during hotplug * register and unregister */ -static DEFINE_SPINLOCK(nest_init_lock); +static DEFINE_MUTEX(nest_init_lock); static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); static struct imc_pmu **per_nest_pmu_arr; static cpumask_t nest_imc_cpumask; @@ -1621,7 +1621,7 @@ static void imc_common_mem_free(struct imc_pmu *pmu_ptr) static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) { if (pmu_ptr->domain == IMC_DOMAIN_NEST) { - spin_lock(&nest_init_lock); + mutex_lock(&nest_init_lock); if (nest_pmus == 1) { cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE); kfree(nest_imc_refc); @@ -1631,7 +1631,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) if (nest_pmus > 0) nest_pmus--; - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); } /* Free core_imc memory */ @@ -1788,11 +1788,11 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id * rest. To handle the cpuhotplug callback unregister, we track * the number of nest pmus in "nest_pmus". */ - spin_lock(&nest_init_lock); + mutex_lock(&nest_init_lock); if (nest_pmus == 0) { ret = init_nest_pmu_ref(); if (ret) { - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; goto err_free_mem; @@ -1800,7 +1800,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id /* Register for cpu hotplug notification. */ ret = nest_pmu_cpumask_init(); if (ret) { - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); kfree(nest_imc_refc); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; @@ -1808,7 +1808,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id } } nest_pmus++; - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); break; case IMC_DOMAIN_CORE: ret = core_imc_pmu_cpumask_init(); From 1b1f56cc0eaa104a8e0b8207a45dbe71687b5015 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 18 Jan 2023 12:48:15 -0800 Subject: [PATCH 1198/4345] bpf: Fix a possible task gone issue with bpf_send_signal[_thread]() helpers [ Upstream commit bdb7fdb0aca8b96cef9995d3a57e251c2289322f ] In current bpf_send_signal() and bpf_send_signal_thread() helper implementation, irq_work is used to handle nmi context. Hao Sun reported in [1] that the current task at the entry of the helper might be gone during irq_work callback processing. To fix the issue, a reference is acquired for the current task before enqueuing into the irq_work so that the queued task is still available during irq_work callback processing. [1] https://lore.kernel.org/bpf/20230109074425.12556-1-sunhao.th@gmail.com/ Fixes: 8b401f9ed244 ("bpf: implement bpf_send_signal() helper") Tested-by: Hao Sun Reported-by: Hao Sun Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20230118204815.3331855-1-yhs@fb.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/trace/bpf_trace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ab4f51716645..94e51d36fb49 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1055,6 +1055,7 @@ static void do_bpf_send_signal(struct irq_work *entry) work = container_of(entry, struct send_signal_irq_work, irq_work); group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); + put_task_struct(work->task); } static int bpf_send_signal_common(u32 sig, enum pid_type type) @@ -1091,7 +1092,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) * to the irq_work. The current task may change when queued * irq works get executed. */ - work->task = current; + work->task = get_task_struct(current); work->sig = sig; work->type = type; irq_work_queue(&work->irq_work); From 2b557fa635e7487f638c0f030c305870839eeda2 Mon Sep 17 00:00:00 2001 From: Artemii Karasev Date: Thu, 19 Jan 2023 00:22:59 -0800 Subject: [PATCH 1199/4345] ALSA: hda/via: Avoid potential array out-of-bound in add_secret_dac_path() [ Upstream commit b9cee506da2b7920b5ea02ccd8e78a907d0ee7aa ] snd_hda_get_connections() can return a negative error code. It may lead to accessing 'conn' array at a negative index. Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Artemii Karasev Fixes: 30b4503378c9 ("ALSA: hda - Expose secret DAC-AA connection of some VIA codecs") Link: https://lore.kernel.org/r/20230119082259.3634-1-karasev@ispras.ru Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_via.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index a188901a83bb..29abc96dc146 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -821,6 +821,9 @@ static int add_secret_dac_path(struct hda_codec *codec) return 0; nums = snd_hda_get_connections(codec, spec->gen.mixer_nid, conn, ARRAY_SIZE(conn) - 1); + if (nums < 0) + return nums; + for (i = 0; i < nums; i++) { if (get_wcaps_type(get_wcaps(codec, conn[i])) == AC_WID_AUD_OUT) return 0; From 8de8c4a25ed8924b09cf8cd542feea854d5ee5bf Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 21 Sep 2021 17:49:41 -0700 Subject: [PATCH 1200/4345] bpf: Support <8-byte scalar spill and refill [ Upstream commit 354e8f1970f821d4952458f77b1ab6c3eb24d530 ] The verifier currently does not save the reg state when spilling <8byte bounded scalar to the stack. The bpf program will be incorrectly rejected when this scalar is refilled to the reg and then used to offset into a packet header. The later patch has a simplified bpf prog from a real use case to demonstrate this case. The current work around is to reparse the packet again such that this offset scalar is close to where the packet data will be accessed to avoid the spill. Thus, the header is parsed twice. The llvm patch [1] will align the <8bytes spill to the 8-byte stack address. This can simplify the verifier support by avoiding to store multiple reg states for each 8 byte stack slot. This patch changes the verifier to save the reg state when spilling <8bytes scalar to the stack. This reg state saving is limited to spill aligned to the 8-byte stack address. The current refill logic has already called coerce_reg_to_size(), so coerce_reg_to_size() is not called on state->stack[spi].spilled_ptr during spill. When refilling in check_stack_read_fixed_off(), it checks the refill size is the same as the number of bytes marked with STACK_SPILL before restoring the reg state. When restoring the reg state to state->regs[dst_regno], it needs to avoid the state->regs[dst_regno].subreg_def being over written because it has been marked by the check_reg_arg() earlier [check_mem_access() is called after check_reg_arg() in do_check()]. Reordering check_mem_access() and check_reg_arg() will need a lot of changes in test_verifier's tests because of the difference in verifier's error message. Thus, the patch here is to save the state->regs[dst_regno].subreg_def first in check_stack_read_fixed_off(). There are cases that the verifier needs to scrub the spilled slot from STACK_SPILL to STACK_MISC. After this patch the spill is not always in 8 bytes now, so it can no longer assume the other 7 bytes are always marked as STACK_SPILL. In particular, the scrub needs to avoid marking an uninitialized byte from STACK_INVALID to STACK_MISC. Otherwise, the verifier will incorrectly accept bpf program reading uninitialized bytes from the stack. A new helper scrub_spilled_slot() is created for this purpose. [1]: https://reviews.llvm.org/D109073 Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210922004941.625398-1-kafai@fb.com Stable-dep-of: 71f656a50176 ("bpf: Fix to preserve reg parent/live fields when copying range info") Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 69 +++++++++++++++++++++++++++++++++---------- 1 file changed, 53 insertions(+), 16 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 72b7fdcc08cc..2c5207134121 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -570,6 +570,12 @@ static bool is_spilled_reg(const struct bpf_stack_state *stack) return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; } +static void scrub_spilled_slot(u8 *stype) +{ + if (*stype != STACK_INVALID) + *stype = STACK_MISC; +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { @@ -2269,15 +2275,21 @@ static bool __is_pointer_value(bool allow_ptr_leaks, } static void save_register_state(struct bpf_func_state *state, - int spi, struct bpf_reg_state *reg) + int spi, struct bpf_reg_state *reg, + int size) { int i; state->stack[spi].spilled_ptr = *reg; - state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + if (size == BPF_REG_SIZE) + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; - for (i = 0; i < BPF_REG_SIZE; i++) - state->stack[spi].slot_type[i] = STACK_SPILL; + for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--) + state->stack[spi].slot_type[i - 1] = STACK_SPILL; + + /* size < 8 bytes spill */ + for (; i; i--) + scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); } /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, @@ -2327,7 +2339,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, env->insn_aux_data[insn_idx].sanitize_stack_spill = true; } - if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) && + if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { if (dst_reg != BPF_REG_FP) { /* The backtracking logic can only recognize explicit @@ -2340,7 +2352,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, if (err) return err; } - save_register_state(state, spi, reg); + save_register_state(state, spi, reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -2352,7 +2364,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - save_register_state(state, spi, reg); + save_register_state(state, spi, reg, size); } else { u8 type = STACK_MISC; @@ -2361,7 +2373,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ if (is_spilled_reg(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) - state->stack[spi].slot_type[i] = STACK_MISC; + scrub_spilled_slot(&state->stack[spi].slot_type[i]); /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -2568,23 +2580,50 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; - u8 *stype; + u8 *stype, type; stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; if (is_spilled_reg(®_state->stack[spi])) { if (size != BPF_REG_SIZE) { + u8 scalar_size = 0; + if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); return -EACCES; } - if (dst_regno >= 0) { - mark_reg_unknown(env, state->regs, dst_regno); - state->regs[dst_regno].live |= REG_LIVE_WRITTEN; - } + mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); + if (dst_regno < 0) + return 0; + + for (i = BPF_REG_SIZE; i > 0 && stype[i - 1] == STACK_SPILL; i--) + scalar_size++; + + if (!(off % BPF_REG_SIZE) && size == scalar_size) { + /* The earlier check_reg_arg() has decided the + * subreg_def for this insn. Save it first. + */ + s32 subreg_def = state->regs[dst_regno].subreg_def; + + state->regs[dst_regno] = *reg; + state->regs[dst_regno].subreg_def = subreg_def; + } else { + for (i = 0; i < size; i++) { + type = stype[(slot - i) % BPF_REG_SIZE]; + if (type == STACK_SPILL) + continue; + if (type == STACK_MISC) + continue; + verbose(env, "invalid read from stack off %d+%d size %d\n", + off, i, size); + return -EACCES; + } + mark_reg_unknown(env, state->regs, dst_regno); + } + state->regs[dst_regno].live |= REG_LIVE_WRITTEN; return 0; } for (i = 1; i < BPF_REG_SIZE; i++) { @@ -2615,8 +2654,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { - u8 type; - for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_MISC) @@ -4102,7 +4139,7 @@ static int check_stack_range_initialized( if (clobber) { __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) - state->stack[spi].slot_type[j] = STACK_MISC; + scrub_spilled_slot(&state->stack[spi].slot_type[j]); } goto mark; } From 36dbb8daf08a131a31a4940c314a1c585cba28ee Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 6 Jan 2023 16:22:13 +0200 Subject: [PATCH 1201/4345] bpf: Fix to preserve reg parent/live fields when copying range info [ Upstream commit 71f656a50176915d6813751188b5758daa8d012b ] Register range information is copied in several places. The intent is to transfer range/id information from one register/stack spill to another. Currently this is done using direct register assignment, e.g.: static void find_equal_scalars(..., struct bpf_reg_state *known_reg) { ... struct bpf_reg_state *reg; ... *reg = *known_reg; ... } However, such assignments also copy the following bpf_reg_state fields: struct bpf_reg_state { ... struct bpf_reg_state *parent; ... enum bpf_reg_liveness live; ... }; Copying of these fields is accidental and incorrect, as could be demonstrated by the following example: 0: call ktime_get_ns() 1: r6 = r0 2: call ktime_get_ns() 3: r7 = r0 4: if r0 > r6 goto +1 ; r0 & r6 are unbound thus generated ; branch states are identical 5: *(u64 *)(r10 - 8) = 0xdeadbeef ; 64-bit write to fp[-8] --- checkpoint --- 6: r1 = 42 ; r1 marked as written 7: *(u8 *)(r10 - 8) = r1 ; 8-bit write, fp[-8] parent & live ; overwritten 8: r2 = *(u64 *)(r10 - 8) 9: r0 = 0 10: exit This example is unsafe because 64-bit write to fp[-8] at (5) is conditional, thus not all bytes of fp[-8] are guaranteed to be set when it is read at (8). However, currently the example passes verification. First, the execution path 1-10 is examined by verifier. Suppose that a new checkpoint is created by is_state_visited() at (6). After checkpoint creation: - r1.parent points to checkpoint.r1, - fp[-8].parent points to checkpoint.fp[-8]. At (6) the r1.live is set to REG_LIVE_WRITTEN. At (7) the fp[-8].parent is set to r1.parent and fp[-8].live is set to REG_LIVE_WRITTEN, because of the following code called in check_stack_write_fixed_off(): static void save_register_state(struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { ... state->stack[spi].spilled_ptr = *reg; // <--- parent & live copied if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; ... } Note the intent to mark stack spill as written only if 8 bytes are spilled to a slot, however this intent is spoiled by a 'live' field copy. At (8) the checkpoint.fp[-8] should be marked as REG_LIVE_READ but this does not happen: - fp[-8] in a current state is already marked as REG_LIVE_WRITTEN; - fp[-8].parent points to checkpoint.r1, parentage chain is used by mark_reg_read() to mark checkpoint states. At (10) the verification is finished for path 1-10 and jump 4-6 is examined. The checkpoint.fp[-8] never gets REG_LIVE_READ mark and this spill is pruned from the cached states by clean_live_states(). Hence verifier state obtained via path 1-4,6 is deemed identical to one obtained via path 1-6 and program marked as safe. Note: the example should be executed with BPF_F_TEST_STATE_FREQ flag set to force creation of intermediate verifier states. This commit revisits the locations where bpf_reg_state instances are copied and replaces the direct copies with a call to a function copy_register_state(dst, src) that preserves 'parent' and 'live' fields of the 'dst'. Fixes: 679c782de14b ("bpf/verifier: per-register parent pointers") Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20230106142214.1040390-2-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2c5207134121..0d0d7b140f05 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2274,13 +2274,24 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } +/* Copy src state preserving dst->parent and dst->live fields */ +static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) +{ + struct bpf_reg_state *parent = dst->parent; + enum bpf_reg_liveness live = dst->live; + + *dst = *src; + dst->parent = parent; + dst->live = live; +} + static void save_register_state(struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { int i; - state->stack[spi].spilled_ptr = *reg; + copy_register_state(&state->stack[spi].spilled_ptr, reg); if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; @@ -2608,7 +2619,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, */ s32 subreg_def = state->regs[dst_regno].subreg_def; - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; } else { for (i = 0; i < size; i++) { @@ -2635,7 +2646,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno >= 0) { /* restore register state from stack */ - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions @@ -5896,7 +5907,7 @@ do_sim: */ if (!ptr_is_dst_reg) { tmp = *dst_reg; - *dst_reg = *ptr_reg; + copy_register_state(dst_reg, ptr_reg); } ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); @@ -7150,7 +7161,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * to propagate min/max range. */ src_reg->id = ++env->id_gen; - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { @@ -7161,7 +7172,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared otherwise * dst_reg min/max could be incorrectly * propagated into src_reg by find_equal_scalars() @@ -7981,7 +7992,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate, bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) - *reg = *known_reg; + copy_register_state(reg, known_reg); })); } From 9bd6074e1872d22190a8da30e796cbf937d334f0 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sat, 21 Jan 2023 13:41:44 +0100 Subject: [PATCH 1202/4345] bpf, sockmap: Check for any of tcp_bpf_prots when cloning a listener [ Upstream commit ddce1e091757d0259107c6c0c7262df201de2b66 ] A listening socket linked to a sockmap has its sk_prot overridden. It points to one of the struct proto variants in tcp_bpf_prots. The variant depends on the socket's family and which sockmap programs are attached. A child socket cloned from a TCP listener initially inherits their sk_prot. But before cloning is finished, we restore the child's proto to the listener's original non-tcp_bpf_prots one. This happens in tcp_create_openreq_child -> tcp_bpf_clone. Today, in tcp_bpf_clone we detect if the child's proto should be restored by checking only for the TCP_BPF_BASE proto variant. This is not correct. The sk_prot of listening socket linked to a sockmap can point to to any variant in tcp_bpf_prots. If the listeners sk_prot happens to be not the TCP_BPF_BASE variant, then the child socket unintentionally is left if the inherited sk_prot by tcp_bpf_clone. This leads to issues like infinite recursion on close [1], because the child state is otherwise not set up for use with tcp_bpf_prot operations. Adjust the check in tcp_bpf_clone to detect all of tcp_bpf_prots variants. Note that it wouldn't be sufficient to check the socket state when overriding the sk_prot in tcp_bpf_update_proto in order to always use the TCP_BPF_BASE variant for listening sockets. Since commit b8b8315e39ff ("bpf, sockmap: Remove unhash handler for BPF sockmap usage") it is possible for a socket to transition to TCP_LISTEN state while already linked to a sockmap, e.g. connect() -> insert into map -> connect(AF_UNSPEC) -> listen(). [1]: https://lore.kernel.org/all/00000000000073b14905ef2e7401@google.com/ Fixes: e80251555f0b ("tcp_bpf: Don't let child socket inherit parent protocol ops on copy") Reported-by: syzbot+04c21ed96d861dccc5cd@syzkaller.appspotmail.com Signed-off-by: Jakub Sitnicki Acked-by: John Fastabend Link: https://lore.kernel.org/r/20230113-sockmap-fix-v2-2-1e0ee7ac2f90@cloudflare.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- include/linux/util_macros.h | 12 ++++++++++++ net/ipv4/tcp_bpf.c | 4 ++-- 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h index 72299f261b25..43db6e47503c 100644 --- a/include/linux/util_macros.h +++ b/include/linux/util_macros.h @@ -38,4 +38,16 @@ */ #define find_closest_descending(x, a, as) __find_closest(x, a, as, >=) +/** + * is_insidevar - check if the @ptr points inside the @var memory range. + * @ptr: the pointer to a memory address. + * @var: the variable which address and size identify the memory range. + * + * Evaluates to true if the address in @ptr lies within the memory + * range allocated to @var. + */ +#define is_insidevar(ptr, var) \ + ((uintptr_t)(ptr) >= (uintptr_t)(var) && \ + (uintptr_t)(ptr) < (uintptr_t)(var) + sizeof(var)) + #endif diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 6a1685461f89..926e29e84b40 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -642,10 +643,9 @@ struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock) */ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { - int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; struct proto *prot = newsk->sk_prot; - if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE]) + if (is_insidevar(prot, tcp_bpf_prots)) newsk->sk_prot = sk->sk_prot_creator; } #endif /* CONFIG_BPF_STREAM_PARSER */ From 8c6b46d426ed9138a6a7fe9fb5b27df5a8ec7c74 Mon Sep 17 00:00:00 2001 From: Pierluigi Passaro Date: Sun, 15 Jan 2023 22:35:03 +0100 Subject: [PATCH 1203/4345] arm64: dts: imx8mm: Fix pad control for UART1_DTE_RX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 47123900f3e4a7f769631d6ec15abf44086276f6 ] According section     8.2.5.313 Select Input Register (IOMUXC_UART1_RXD_SELECT_INPUT) of      i.MX 8M Mini Applications Processor Reference Manual, Rev. 3, 11/2020 the required setting for this specific pin configuration is "1" Signed-off-by: Pierluigi Passaro Reviewed-by: Fabio Estevam Fixes: c1c9d41319c3 ("dt-bindings: imx: Add pinctrl binding doc for imx8mm") Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h index a003e6af3353..56271abfb7e0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h @@ -601,7 +601,7 @@ #define MX8MM_IOMUXC_UART1_RXD_GPIO5_IO22 0x234 0x49C 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_RXD_TPSMP_HDATA24 0x234 0x49C 0x000 0x7 0x0 #define MX8MM_IOMUXC_UART1_TXD_UART1_DCE_TX 0x238 0x4A0 0x000 0x0 0x0 -#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x0 +#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x1 #define MX8MM_IOMUXC_UART1_TXD_ECSPI3_MOSI 0x238 0x4A0 0x000 0x1 0x0 #define MX8MM_IOMUXC_UART1_TXD_GPIO5_IO23 0x238 0x4A0 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_TXD_TPSMP_HDATA25 0x238 0x4A0 0x000 0x7 0x0 From d08a9b0ad2111aff59ee3e06e53287b9b6e47af3 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 19 Jan 2023 10:02:19 +0100 Subject: [PATCH 1204/4345] drm/vc4: hdmi: make CEC adapter name unique [ Upstream commit 51128c3f2a7c98055ea1d27e34910dc10977f618 ] The bcm2711 has two HDMI outputs, each with their own CEC adapter. The CEC adapter name has to be unique, but it is currently hardcoded to "vc4" for both outputs. Change this to use the card_name from the variant information in order to make the adapter name unique. Signed-off-by: Hans Verkuil Fixes: 15b4511a4af6 ("drm/vc4: add HDMI CEC support") Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/dcf1db75-d9cc-62cc-fa12-baf1b2b3bf31@xs4all.nl Signed-off-by: Sasha Levin --- drivers/gpu/drm/vc4/vc4_hdmi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 08175c3dd374..539ebf85fd7c 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1491,7 +1491,8 @@ static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi) return 0; vc4_hdmi->cec_adap = cec_allocate_adapter(&vc4_hdmi_cec_adap_ops, - vc4_hdmi, "vc4", + vc4_hdmi, + vc4_hdmi->variant->card_name, CEC_CAP_DEFAULTS | CEC_CAP_CONNECTOR_INFO, 1); ret = PTR_ERR_OR_ZERO(vc4_hdmi->cec_adap); From de990d157179369135b6f48bed6853524178c177 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 26 Jan 2023 22:06:08 -0500 Subject: [PATCH 1205/4345] scsi: Revert "scsi: core: map PQ=1, PDT=other values to SCSI_SCAN_TARGET_PRESENT" [ Upstream commit 15600159bcc6abbeae6b33a849bef90dca28b78f ] This reverts commit 948e922fc44611ee2de0c89583ca958cb5307d36. Not all targets that return PQ=1 and PDT=0 should be ignored. While the SCSI spec is vague in this department, there appears to be a critical mass of devices which rely on devices being accessible with this combination of reported values. Fixes: 948e922fc446 ("scsi: core: map PQ=1, PDT=other values to SCSI_SCAN_TARGET_PRESENT") Link: https://lore.kernel.org/r/yq1lelrleqr.fsf@ca-mkp.ca.oracle.com Acked-by: Bart Van Assche Acked-by: Martin Wilck Acked-by: Hannes Reinecke Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_scan.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 8e474b145249..6f7c4d41c51d 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1129,8 +1129,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * that no LUN is present, so don't add sdev in these cases. * Two specific examples are: * 1) NetApp targets: return PQ=1, PDT=0x1f - * 2) IBM/2145 targets: return PQ=1, PDT=0 - * 3) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved" + * 2) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved" * in the UFI 1.0 spec (we cannot rely on reserved bits). * * References: @@ -1144,8 +1143,8 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * PDT=00h Direct-access device (floppy) * PDT=1Fh none (no FDD connected to the requested logical unit) */ - if (((result[0] >> 5) == 1 || - (starget->pdt_1f_for_no_lun && (result[0] & 0x1f) == 0x1f)) && + if (((result[0] >> 5) == 1 || starget->pdt_1f_for_no_lun) && + (result[0] & 0x1f) == 0x1f && !scsi_is_wlun(lun)) { SCSI_LOG_SCAN_BUS(3, sdev_printk(KERN_INFO, sdev, "scsi scan: peripheral device type" From f9815b303e61c70ab5724b5059ce96571b4eeefd Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Tue, 17 Jan 2023 10:15:18 -0500 Subject: [PATCH 1206/4345] vhost/net: Clear the pending messages when the backend is removed [ Upstream commit 9526f9a2b762af16be94a72aca5d65c677d28f50 ] When the vhost iotlb is used along with a guest virtual iommu and the guest gets rebooted, some MISS messages may have been recorded just before the reboot and spuriously executed by the virtual iommu after the reboot. As vhost does not have any explicit reset user API, VHOST_NET_SET_BACKEND looks a reasonable point where to clear the pending messages, in case the backend is removed. Export vhost_clear_msg() and call it in vhost_net_set_backend() when fd == -1. Signed-off-by: Eric Auger Suggested-by: Jason Wang Fixes: 6b1e6cc7855b0 ("vhost: new device IOTLB API") Message-Id: <20230117151518.44725-3-eric.auger@redhat.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- drivers/vhost/net.c | 3 +++ drivers/vhost/vhost.c | 3 ++- drivers/vhost/vhost.h | 1 + 3 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 5beb20768b20..b9c8e4025214 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1517,6 +1517,9 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) nvq = &n->vqs[index]; mutex_lock(&vq->mutex); + if (fd == -1) + vhost_clear_msg(&n->dev); + /* Verify that ring has been setup correctly. */ if (!vhost_vq_access_ok(vq)) { r = -EFAULT; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index da00a5c57db6..1f9a1554ce5f 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -669,7 +669,7 @@ void vhost_dev_stop(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_dev_stop); -static void vhost_clear_msg(struct vhost_dev *dev) +void vhost_clear_msg(struct vhost_dev *dev) { struct vhost_msg_node *node, *n; @@ -687,6 +687,7 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } +EXPORT_SYMBOL_GPL(vhost_clear_msg); void vhost_dev_cleanup(struct vhost_dev *dev) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index b063324c7669..8f80d6b0d843 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -183,6 +183,7 @@ long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp); long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp); bool vhost_vq_access_ok(struct vhost_virtqueue *vq); bool vhost_log_access_ok(struct vhost_dev *); +void vhost_clear_msg(struct vhost_dev *dev); int vhost_get_vq_desc(struct vhost_virtqueue *, struct iovec iov[], unsigned int iov_count, From fefb47a8331c55d3e981b7e34485c31eb50c2a14 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 15 Sep 2022 18:59:12 -0400 Subject: [PATCH 1207/4345] WRITE is "data source", not destination... [ Upstream commit 974c36fb828aeae7b4f9063f94860ae6c5633efd ] Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- drivers/fsi/fsi-sbefifo.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/fsi/fsi-sbefifo.c b/drivers/fsi/fsi-sbefifo.c index 84cb965bfed5..97045a8d9422 100644 --- a/drivers/fsi/fsi-sbefifo.c +++ b/drivers/fsi/fsi-sbefifo.c @@ -640,7 +640,7 @@ static void sbefifo_collect_async_ffdc(struct sbefifo *sbefifo) } ffdc_iov.iov_base = ffdc; ffdc_iov.iov_len = SBEFIFO_MAX_FFDC_SIZE; - iov_iter_kvec(&ffdc_iter, WRITE, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); + iov_iter_kvec(&ffdc_iter, READ, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); cmd[0] = cpu_to_be32(2); cmd[1] = cpu_to_be32(SBEFIFO_CMD_GET_SBE_FFDC); rc = sbefifo_do_command(sbefifo, cmd, 2, &ffdc_iter); @@ -737,7 +737,7 @@ int sbefifo_submit(struct device *dev, const __be32 *command, size_t cmd_len, rbytes = (*resp_len) * sizeof(__be32); resp_iov.iov_base = response; resp_iov.iov_len = rbytes; - iov_iter_kvec(&resp_iter, WRITE, &resp_iov, 1, rbytes); + iov_iter_kvec(&resp_iter, READ, &resp_iov, 1, rbytes); /* Perform the command */ mutex_lock(&sbefifo->lock); @@ -817,7 +817,7 @@ static ssize_t sbefifo_user_read(struct file *file, char __user *buf, /* Prepare iov iterator */ resp_iov.iov_base = buf; resp_iov.iov_len = len; - iov_iter_init(&resp_iter, WRITE, &resp_iov, 1, len); + iov_iter_init(&resp_iter, READ, &resp_iov, 1, len); /* Perform the command */ mutex_lock(&sbefifo->lock); From b5437e0ba9e75ce29498f2f53e8e9d91cc59edf6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 15 Sep 2022 19:01:10 -0400 Subject: [PATCH 1208/4345] READ is "data destination", not source... [ Upstream commit 355d2c2798e9dc39f6714fa7ef8902c0d4c5350b ] Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 5c39e4c4bef7..1a5805260778 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -902,7 +902,7 @@ static void rtrs_clt_init_req(struct rtrs_clt_io_req *req, req->need_inv_comp = false; req->inv_errno = 0; - iov_iter_kvec(&iter, READ, vec, 1, usr_len); + iov_iter_kvec(&iter, WRITE, vec, 1, usr_len); len = _copy_from_iter(req->iu->buf, usr_len, &iter); WARN_ON(len != usr_len); From 0c67fb7775086a7159980153ad8518746e7a6b64 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 15 Sep 2022 19:04:18 -0400 Subject: [PATCH 1209/4345] fix iov_iter_bvec() "direction" argument [ Upstream commit b676668d99155e6859d99bbf2df18b3f03851902 ] Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- drivers/target/target_core_file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 7143d03f0e02..18fbbe510d01 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -340,7 +340,7 @@ static int fd_do_rw(struct se_cmd *cmd, struct file *fd, len += sg->length; } - iov_iter_bvec(&iter, READ, bvec, sgl_nents, len); + iov_iter_bvec(&iter, is_write, bvec, sgl_nents, len); if (is_write) ret = vfs_iter_write(fd, &iter, &pos, 0); else @@ -477,7 +477,7 @@ fd_execute_write_same(struct se_cmd *cmd) len += se_dev->dev_attrib.block_size; } - iov_iter_bvec(&iter, READ, bvec, nolb, len); + iov_iter_bvec(&iter, WRITE, bvec, nolb, len); ret = vfs_iter_write(fd_dev->fd_file, &iter, &pos, 0); kfree(bvec); From 63d1c4edbfc1e93f40170bbee7965ca55973cd12 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 15 Sep 2022 19:16:56 -0400 Subject: [PATCH 1210/4345] fix "direction" argument of iov_iter_kvec() [ Upstream commit fc02f33787d8dd227b54f263eba983d5b249c032 ] Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- drivers/xen/pvcalls-back.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index a7d293fa8d14..3b5a8e2c4d47 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -129,13 +129,13 @@ static bool pvcalls_conn_back_read(void *opaque) if (masked_prod < masked_cons) { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = wanted; - iov_iter_kvec(&msg.msg_iter, WRITE, vec, 1, wanted); + iov_iter_kvec(&msg.msg_iter, READ, vec, 1, wanted); } else { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = array_size - masked_prod; vec[1].iov_base = data->in; vec[1].iov_len = wanted - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, WRITE, vec, 2, wanted); + iov_iter_kvec(&msg.msg_iter, READ, vec, 2, wanted); } atomic_set(&map->read, 0); @@ -188,13 +188,13 @@ static bool pvcalls_conn_back_write(struct sock_mapping *map) if (pvcalls_mask(prod, array_size) > pvcalls_mask(cons, array_size)) { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = size; - iov_iter_kvec(&msg.msg_iter, READ, vec, 1, size); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 1, size); } else { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = array_size - pvcalls_mask(cons, array_size); vec[1].iov_base = data->out; vec[1].iov_len = size - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, READ, vec, 2, size); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 2, size); } atomic_set(&map->write, 0); From 539fc3ef5104852625b5cb96fcf99503d7473408 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 25 Jan 2023 08:48:59 +0100 Subject: [PATCH 1211/4345] virtio-net: execute xdp_do_flush() before napi_complete_done() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ad7e615f646c9b5b2cf655cdfb9d91a28db4f25a ] Make sure that xdp_do_flush() is always executed before napi_complete_done(). This is important for two reasons. First, a redirect to an XSKMAP assumes that a call to xdp_do_redirect() from napi context X on CPU Y will be followed by a xdp_do_flush() from the same napi context and CPU. This is not guaranteed if the napi_complete_done() is executed before xdp_do_flush(), as it tells the napi logic that it is fine to schedule napi context X on another CPU. Details from a production system triggering this bug using the veth driver can be found following the first link below. The second reason is that the XDP_REDIRECT logic in itself relies on being inside a single NAPI instance through to the xdp_do_flush() call for RCU protection of all in-kernel data structures. Details can be found in the second link below. Fixes: 186b3c998c50 ("virtio-net: support XDP_REDIRECT") Signed-off-by: Magnus Karlsson Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20221220185903.1105011-1-sbohrer@cloudflare.com Link: https://lore.kernel.org/all/20210624160609.292325-1-toke@redhat.com/ Acked-by: Michael S. Tsirkin Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/virtio_net.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c942cd6a2c65..0605c28c684b 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1525,13 +1525,13 @@ static int virtnet_poll(struct napi_struct *napi, int budget) received = virtnet_receive(rq, budget, &xdp_xmit); + if (xdp_xmit & VIRTIO_XDP_REDIR) + xdp_do_flush(); + /* Out of packets? */ if (received < budget) virtqueue_napi_complete(napi, rq->vq, received); - if (xdp_xmit & VIRTIO_XDP_REDIR) - xdp_do_flush(); - if (xdp_xmit & VIRTIO_XDP_TX) { sq = virtnet_xdp_get_sq(vi); if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { From 6824169e7488b10ee12d364bc55c1a8be0bad332 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Wed, 25 Jan 2023 15:35:13 +0100 Subject: [PATCH 1212/4345] sfc: correctly advertise tunneled IPv6 segmentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ffffd2454a7a1bc9f7242b12c4cc0b05c12692b4 ] Recent sfc NICs are TSO capable for some tunnel protocols. However, it was not working properly because the feature was not advertised in hw_enc_features, but in hw_features only. Setting up a GENEVE tunnel and using iperf3 to send IPv4 and IPv6 traffic to the tunnel show, with tcpdump, that the IPv4 packets still had ~64k size but the IPv6 ones had only ~1500 bytes (they had been segmented by software, not offloaded). With this patch segmentation is offloaded as expected and the traffic is correctly received at the other end. Fixes: 24b2c3751aa3 ("sfc: advertise encapsulated offloads on EF10") Reported-by: Tianhao Zhao Signed-off-by: Íñigo Huguet Acked-by: Martin Habets Link: https://lore.kernel.org/r/20230125143513.25841-1-ihuguet@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/sfc/efx.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 718308076341..29c8d2c99004 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1047,8 +1047,11 @@ static int efx_pci_probe_post_io(struct efx_nic *efx) /* Determine netdevice features */ net_dev->features |= (efx->type->offload_features | NETIF_F_SG | NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_RXALL); - if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) + if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) { net_dev->features |= NETIF_F_TSO6; + if (efx_has_cap(efx, TX_TSO_V2_ENCAP)) + net_dev->hw_enc_features |= NETIF_F_TSO6; + } /* Check whether device supports TSO */ if (!efx->type->tso_versions || !efx->type->tso_versions(efx)) net_dev->features &= ~NETIF_F_ALL_TSO; From 362a2f5531dc0e5b0b5b3e3a541000dbffa75461 Mon Sep 17 00:00:00 2001 From: Andre Kalb Date: Wed, 25 Jan 2023 19:23:26 +0100 Subject: [PATCH 1213/4345] net: phy: dp83822: Fix null pointer access on DP83825/DP83826 devices [ Upstream commit 422ae7d9c7221e8d4c8526d0f54106307d69d2dc ] The probe() function is only used for the DP83822 PHY, leaving the private data pointer uninitialized for the smaller DP83825/26 models. While all uses of the private data structure are hidden in 82822 specific callbacks, configuring the interrupt is shared across all models. This causes a NULL pointer dereference on the smaller PHYs as it accesses the private data unchecked. Verifying the pointer avoids that. Fixes: 5dc39fd5ef35 ("net: phy: DP83822: Add ability to advertise Fiber connection") Signed-off-by: Andre Kalb Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/Y9FzniUhUtbaGKU7@pc6682 Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/dp83822.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index db651649e0b8..81412999445d 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -247,7 +247,8 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_ENERGY_DET_INT_EN | DP83822_LINK_QUAL_INT_EN); - if (!dp83822->fx_enabled) + /* Private data pointer is NULL on DP83825/26 */ + if (!dp83822 || !dp83822->fx_enabled) misr_status |= DP83822_ANEG_COMPLETE_INT_EN | DP83822_DUP_MODE_CHANGE_INT_EN | DP83822_SPEED_CHANGED_INT_EN; @@ -267,7 +268,8 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_PAGE_RX_INT_EN | DP83822_EEE_ERROR_CHANGE_INT_EN); - if (!dp83822->fx_enabled) + /* Private data pointer is NULL on DP83825/26 */ + if (!dp83822 || !dp83822->fx_enabled) misr_status |= DP83822_ANEG_ERR_INT_EN | DP83822_WOL_PKT_INT_EN; From dd6991251a1382a9b4984962a0c7a467e9d71812 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 26 Jan 2023 18:32:50 -0800 Subject: [PATCH 1214/4345] netrom: Fix use-after-free caused by accept on already connected socket [ Upstream commit 611792920925fb088ddccbe2783c7f92fdfb6b64 ] If you call listen() and accept() on an already connect()ed AF_NETROM socket, accept() can successfully connect. This is because when the peer socket sends data to sendmsg, the skb with its own sk stored in the connected socket's sk->sk_receive_queue is connected, and nr_accept() dequeues the skb waiting in the sk->sk_receive_queue. As a result, nr_accept() allocates and returns a sock with the sk of the parent AF_NETROM socket. And here use-after-free can happen through complex race conditions: ``` cpu0 cpu1 1. socket_2 = socket(AF_NETROM) . . listen(socket_2) accepted_socket = accept(socket_2) 2. socket_1 = socket(AF_NETROM) nr_create() // sk refcount : 1 connect(socket_1) 3. write(accepted_socket) nr_sendmsg() nr_output() nr_kick() nr_send_iframe() nr_transmit_buffer() nr_route_frame() nr_loopback_queue() nr_loopback_timer() nr_rx_frame() nr_process_rx_frame(sk, skb); // sk : socket_1's sk nr_state3_machine() nr_queue_rx_frame() sock_queue_rcv_skb() sock_queue_rcv_skb_reason() __sock_queue_rcv_skb() __skb_queue_tail(list, skb); // list : socket_1's sk->sk_receive_queue 4. listen(socket_1) nr_listen() uaf_socket = accept(socket_1) nr_accept() skb_dequeue(&sk->sk_receive_queue); 5. close(accepted_socket) nr_release() nr_write_internal(sk, NR_DISCREQ) nr_transmit_buffer() // NR_DISCREQ nr_route_frame() nr_loopback_queue() nr_loopback_timer() nr_rx_frame() // sk : socket_1's sk nr_process_rx_frame() // NR_STATE_3 nr_state3_machine() // NR_DISCREQ nr_disconnect() nr_sk(sk)->state = NR_STATE_0; 6. close(socket_1) // sk refcount : 3 nr_release() // NR_STATE_0 sock_put(sk); // sk refcount : 0 sk_free(sk); close(uaf_socket) nr_release() sock_hold(sk); // UAF ``` KASAN report by syzbot: ``` BUG: KASAN: use-after-free in nr_release+0x66/0x460 net/netrom/af_netrom.c:520 Write of size 4 at addr ffff8880235d8080 by task syz-executor564/5128 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:306 [inline] print_report+0x15e/0x461 mm/kasan/report.c:417 kasan_report+0xbf/0x1f0 mm/kasan/report.c:517 check_region_inline mm/kasan/generic.c:183 [inline] kasan_check_range+0x141/0x190 mm/kasan/generic.c:189 instrument_atomic_read_write include/linux/instrumented.h:102 [inline] atomic_fetch_add_relaxed include/linux/atomic/atomic-instrumented.h:116 [inline] __refcount_add include/linux/refcount.h:193 [inline] __refcount_inc include/linux/refcount.h:250 [inline] refcount_inc include/linux/refcount.h:267 [inline] sock_hold include/net/sock.h:775 [inline] nr_release+0x66/0x460 net/netrom/af_netrom.c:520 __sock_release+0xcd/0x280 net/socket.c:650 sock_close+0x1c/0x20 net/socket.c:1365 __fput+0x27c/0xa90 fs/file_table.c:320 task_work_run+0x16f/0x270 kernel/task_work.c:179 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0xaa8/0x2950 kernel/exit.c:867 do_group_exit+0xd4/0x2a0 kernel/exit.c:1012 get_signal+0x21c3/0x2450 kernel/signal.c:2859 arch_do_signal_or_restart+0x79/0x5c0 arch/x86/kernel/signal.c:306 exit_to_user_mode_loop kernel/entry/common.c:168 [inline] exit_to_user_mode_prepare+0x15f/0x250 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x1d/0x50 kernel/entry/common.c:296 do_syscall_64+0x46/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f6c19e3c9b9 Code: Unable to access opcode bytes at 0x7f6c19e3c98f. RSP: 002b:00007fffd4ba2ce8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: 0000000000000116 RBX: 0000000000000003 RCX: 00007f6c19e3c9b9 RDX: 0000000000000318 RSI: 00000000200bd000 RDI: 0000000000000006 RBP: 0000000000000003 R08: 000000000000000d R09: 000000000000000d R10: 0000000000000000 R11: 0000000000000246 R12: 000055555566a2c0 R13: 0000000000000011 R14: 0000000000000000 R15: 0000000000000000 Allocated by task 5128: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:371 [inline] ____kasan_kmalloc mm/kasan/common.c:330 [inline] __kasan_kmalloc+0xa3/0xb0 mm/kasan/common.c:380 kasan_kmalloc include/linux/kasan.h:211 [inline] __do_kmalloc_node mm/slab_common.c:968 [inline] __kmalloc+0x5a/0xd0 mm/slab_common.c:981 kmalloc include/linux/slab.h:584 [inline] sk_prot_alloc+0x140/0x290 net/core/sock.c:2038 sk_alloc+0x3a/0x7a0 net/core/sock.c:2091 nr_create+0xb6/0x5f0 net/netrom/af_netrom.c:433 __sock_create+0x359/0x790 net/socket.c:1515 sock_create net/socket.c:1566 [inline] __sys_socket_create net/socket.c:1603 [inline] __sys_socket_create net/socket.c:1588 [inline] __sys_socket+0x133/0x250 net/socket.c:1636 __do_sys_socket net/socket.c:1649 [inline] __se_sys_socket net/socket.c:1647 [inline] __x64_sys_socket+0x73/0xb0 net/socket.c:1647 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 5128: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2b/0x40 mm/kasan/generic.c:518 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free+0x13b/0x1a0 mm/kasan/common.c:200 kasan_slab_free include/linux/kasan.h:177 [inline] __cache_free mm/slab.c:3394 [inline] __do_kmem_cache_free mm/slab.c:3580 [inline] __kmem_cache_free+0xcd/0x3b0 mm/slab.c:3587 sk_prot_free net/core/sock.c:2074 [inline] __sk_destruct+0x5df/0x750 net/core/sock.c:2166 sk_destruct net/core/sock.c:2181 [inline] __sk_free+0x175/0x460 net/core/sock.c:2192 sk_free+0x7c/0xa0 net/core/sock.c:2203 sock_put include/net/sock.h:1991 [inline] nr_release+0x39e/0x460 net/netrom/af_netrom.c:554 __sock_release+0xcd/0x280 net/socket.c:650 sock_close+0x1c/0x20 net/socket.c:1365 __fput+0x27c/0xa90 fs/file_table.c:320 task_work_run+0x16f/0x270 kernel/task_work.c:179 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0xaa8/0x2950 kernel/exit.c:867 do_group_exit+0xd4/0x2a0 kernel/exit.c:1012 get_signal+0x21c3/0x2450 kernel/signal.c:2859 arch_do_signal_or_restart+0x79/0x5c0 arch/x86/kernel/signal.c:306 exit_to_user_mode_loop kernel/entry/common.c:168 [inline] exit_to_user_mode_prepare+0x15f/0x250 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x1d/0x50 kernel/entry/common.c:296 do_syscall_64+0x46/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd ``` To fix this issue, nr_listen() returns -EINVAL for sockets that successfully nr_connect(). Reported-by: syzbot+caa188bdfc1eeafeb418@syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Hyunwoo Kim Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/netrom/af_netrom.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index e5c8a295e640..5c04da4cfbad 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -400,6 +400,11 @@ static int nr_listen(struct socket *sock, int backlog) struct sock *sk = sock->sk; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; From f53c6e7e77df63566d2b5e94825107813debbb04 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 30 Jan 2023 11:39:29 +0100 Subject: [PATCH 1215/4345] netfilter: br_netfilter: disable sabotage_in hook after first suppression [ Upstream commit 2b272bb558f1d3a5aa95ed8a82253786fd1a48ba ] When using a xfrm interface in a bridged setup (the outgoing device is bridged), the incoming packets in the xfrm interface are only tracked in the outgoing direction. $ brctl show bridge name interfaces br_eth1 eth1 $ conntrack -L tcp 115 SYN_SENT src=192... dst=192... [UNREPLIED] ... If br_netfilter is enabled, the first (encrypted) packet is received onR eth1, conntrack hooks are called from br_netfilter emulation which allocates nf_bridge info for this skb. If the packet is for local machine, skb gets passed up the ip stack. The skb passes through ip prerouting a second time. br_netfilter ip_sabotage_in supresses the re-invocation of the hooks. After this, skb gets decrypted in xfrm layer and appears in network stack a second time (after decryption). Then, ip_sabotage_in is called again and suppresses netfilter hook invocation, even though the bridge layer never called them for the plaintext incarnation of the packet. Free the bridge info after the first suppression to avoid this. I was unable to figure out where the regression comes from, as far as i can see br_netfilter always had this problem; i did not expect that skb is looped again with different headers. Fixes: c4b0e771f906 ("netfilter: avoid using skb->nf_bridge directly") Reported-and-tested-by: Wolfgang Nothdurft Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/bridge/br_netfilter_hooks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index a718204c4bfd..f3c7cfba31e1 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -871,6 +871,7 @@ static unsigned int ip_sabotage_in(void *priv, if (nf_bridge && !nf_bridge->in_prerouting && !netif_is_l3_master(skb->dev) && !netif_is_l3_slave(skb->dev)) { + nf_bridge_info_free(skb); state->okfn(state->net, state->sk, skb); return NF_STOLEN; } From de2785aa3448d1ee7be3ab47fd4a873025f1b3d7 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Tue, 17 Jan 2023 13:52:26 +0300 Subject: [PATCH 1216/4345] squashfs: harden sanity check in squashfs_read_xattr_id_table [ Upstream commit 72e544b1b28325fe78a4687b980871a7e4101f76 ] While mounting a corrupted filesystem, a signed integer '*xattr_ids' can become less than zero. This leads to the incorrect computation of 'len' and 'indexes' values which can cause null-ptr-deref in copy_bio_to_actor() or out-of-bounds accesses in the next sanity checks inside squashfs_read_xattr_id_table(). Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Link: https://lkml.kernel.org/r/20230117105226.329303-2-pchelkin@ispras.ru Fixes: 506220d2ba21 ("squashfs: add more sanity checks in xattr id lookup") Reported-by: Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Cc: Phillip Lougher Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/squashfs/xattr_id.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index 087cab8c78f4..f6d78cbc3e74 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, /* Sanity check values */ /* there is always at least one xattr id */ - if (*xattr_ids == 0) + if (*xattr_ids <= 0) return ERR_PTR(-EINVAL); len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); From 98c93a01608f23a28a3c9e6736f74d078fa8400f Mon Sep 17 00:00:00 2001 From: Chris Healy Date: Mon, 30 Jan 2023 15:14:02 -0800 Subject: [PATCH 1217/4345] net: phy: meson-gxl: Add generic dummy stubs for MMD register access [ Upstream commit afc2336f89dc0fc0ef25b92366814524b0fd90fb ] The Meson G12A Internal PHY does not support standard IEEE MMD extended register access, therefore add generic dummy stubs to fail the read and write MMD calls. This is necessary to prevent the core PHY code from erroneously believing that EEE is supported by this PHY even though this PHY does not support EEE, as MMD register access returns all FFFFs. Fixes: 5c3407abb338 ("net: phy: meson-gxl: add g12a support") Reviewed-by: Heiner Kallweit Signed-off-by: Chris Healy Reviewed-by: Jerome Brunet Link: https://lore.kernel.org/r/20230130231402.471493-1-cphealy@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/meson-gxl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index e8f2ca625837..f7a9e6599a64 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -245,6 +245,8 @@ static struct phy_driver meson_gxl_phy[] = { .config_intr = meson_gxl_config_intr, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, }; From 6362b861704fbf7d331bba35407927d9cd84eb9b Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 31 Jan 2023 13:54:37 -0800 Subject: [PATCH 1218/4345] igc: return an error if the mac type is unknown in igc_ptp_systim_to_hwtstamp() [ Upstream commit a2df8463e15c10a8a882090f3d7a760fdb7b189d ] clang static analysis reports drivers/net/ethernet/intel/igc/igc_ptp.c:673:3: warning: The left operand of '+' is a garbage value [core.UndefinedBinaryOperatorResult] ktime_add_ns(shhwtstamps.hwtstamp, adjust); ^ ~~~~~~~~~~~~~~~~~~~~ igc_ptp_systim_to_hwtstamp() silently returns without setting the hwtstamp if the mac type is unknown. This should be treated as an error. Fixes: 81b055205e8b ("igc: Add support for RX timestamping") Signed-off-by: Tom Rix Reviewed-by: Simon Horman Acked-by: Sasha Neftin Tested-by: Naama Meir Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20230131215437.1528994-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_ptp.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 4ab46eee3d93..ef53f7665b58 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -134,10 +134,12 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, * * We need to convert the system time value stored in the RX/TXSTMP registers * into a hwtstamp which can be used by the upper level timestamping functions. + * + * Returns 0 on success. **/ -static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, - struct skb_shared_hwtstamps *hwtstamps, - u64 systim) +static int igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, + struct skb_shared_hwtstamps *hwtstamps, + u64 systim) { switch (adapter->hw.mac.type) { case igc_i225: @@ -147,8 +149,9 @@ static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, systim & 0xFFFFFFFF); break; default: - break; + return -EINVAL; } + return 0; } /** @@ -372,7 +375,8 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) regval = rd32(IGC_TXSTMPL); regval |= (u64)rd32(IGC_TXSTMPH) << 32; - igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval)) + return; switch (adapter->link_speed) { case SPEED_10: From b6d44072117bba057d50f7a2f96e5d070c65926d Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Mon, 6 Sep 2021 17:42:00 +0800 Subject: [PATCH 1219/4345] can: j1939: fix errant WARN_ON_ONCE in j1939_session_deactivate [ Upstream commit d0553680f94c49bbe0e39eb50d033ba563b4212d ] The conclusion "j1939_session_deactivate() should be called with a session ref-count of at least 2" is incorrect. In some concurrent scenarios, j1939_session_deactivate can be called with the session ref-count less than 2. But there is not any problem because it will check the session active state before session putting in j1939_session_deactivate_locked(). Here is the concurrent scenario of the problem reported by syzbot and my reproduction log. cpu0 cpu1 j1939_xtp_rx_eoma j1939_xtp_rx_abort_one j1939_session_get_by_addr [kref == 2] j1939_session_get_by_addr [kref == 3] j1939_session_deactivate [kref == 2] j1939_session_put [kref == 1] j1939_session_completed j1939_session_deactivate WARN_ON_ONCE(kref < 2) ===================================================== WARNING: CPU: 1 PID: 21 at net/can/j1939/transport.c:1088 j1939_session_deactivate+0x5f/0x70 CPU: 1 PID: 21 Comm: ksoftirqd/1 Not tainted 5.14.0-rc7+ #32 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1 04/01/2014 RIP: 0010:j1939_session_deactivate+0x5f/0x70 Call Trace: j1939_session_deactivate_activate_next+0x11/0x28 j1939_xtp_rx_eoma+0x12a/0x180 j1939_tp_recv+0x4a2/0x510 j1939_can_recv+0x226/0x380 can_rcv_filter+0xf8/0x220 can_receive+0x102/0x220 ? process_backlog+0xf0/0x2c0 can_rcv+0x53/0xf0 __netif_receive_skb_one_core+0x67/0x90 ? process_backlog+0x97/0x2c0 __netif_receive_skb+0x22/0x80 Fixes: 0c71437dd50d ("can: j1939: j1939_session_deactivate(): clarify lifetime of session object") Reported-by: syzbot+9981a614060dcee6eeca@syzkaller.appspotmail.com Signed-off-by: Ziyang Xuan Acked-by: Oleksij Rempel Link: https://lore.kernel.org/all/20210906094200.95868-1-william.xuanziyang@huawei.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- net/can/j1939/transport.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 78f6a9110699..57d6aac7f435 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1087,10 +1087,6 @@ static bool j1939_session_deactivate(struct j1939_session *session) bool active; j1939_session_list_lock(priv); - /* This function should be called with a session ref-count of at - * least 2. - */ - WARN_ON_ONCE(kref_read(&session->kref) < 2); active = j1939_session_deactivate_locked(session); j1939_session_list_unlock(priv); From 4d9c9627161a06c098f9d7bb566a42da87759463 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 30 Jan 2023 12:27:41 +0900 Subject: [PATCH 1220/4345] ata: libata: Fix sata_down_spd_limit() when no link speed is reported [ Upstream commit 69f2c9346313ba3d3dfa4091ff99df26c67c9021 ] Commit 2dc0b46b5ea3 ("libata: sata_down_spd_limit should return if driver has not recorded sstatus speed") changed the behavior of sata_down_spd_limit() to return doing nothing if a drive does not report a current link speed, to avoid reducing the link speed to the lowest 1.5 Gbps speed. However, the change assumed that a speed was recorded before probing (e.g. before a suspend/resume) and set in link->sata_spd. This causes problems with adapters/drives combination failing to establish a link speed during probe autonegotiation. One example reported of this problem is an mvebu adapter with a 3Gbps port-multiplier box: autonegotiation fails, leaving no recorded link speed and no reported current link speed. Probe retries also fail as no action is taken by sata_set_spd() after each retry. Fix this by returning early in sata_down_spd_limit() only if we do have a recorded link speed, that is, if link->sata_spd is not 0. With this fix, a failed probe not leading to a recorded link speed is retried at the lower 1.5 Gbps speed, with the link speed potentially increased later on the second revalidate of the device if the device reports that it supports higher link speeds. Reported-by: Marius Dinu Fixes: 2dc0b46b5ea3 ("libata: sata_down_spd_limit should return if driver has not recorded sstatus speed") Reviewed-by: Niklas Cassel Tested-by: Marius Dinu Signed-off-by: Damien Le Moal Signed-off-by: Sasha Levin --- drivers/ata/libata-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index d13474c6d181..14150767be44 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3051,7 +3051,7 @@ int sata_down_spd_limit(struct ata_link *link, u32 spd_limit) */ if (spd > 1) mask &= (1 << (spd - 1)) - 1; - else + else if (link->sata_spd) return -EINVAL; /* were we already at the bottom? */ From a4a493e599e362ec7c890a516bf4425b1f45d540 Mon Sep 17 00:00:00 2001 From: Andrei Gherzan Date: Wed, 1 Feb 2023 00:16:10 +0000 Subject: [PATCH 1221/4345] selftests: net: udpgso_bench_rx: Fix 'used uninitialized' compiler warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c03c80e3a03ffb4f790901d60797e9810539d946 ] This change fixes the following compiler warning: /usr/include/x86_64-linux-gnu/bits/error.h:40:5: warning: ‘gso_size’ may be used uninitialized [-Wmaybe-uninitialized] 40 | __error_noreturn (__status, __errnum, __format, __va_arg_pack ()); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ udpgso_bench_rx.c: In function ‘main’: udpgso_bench_rx.c:253:23: note: ‘gso_size’ was declared here 253 | int ret, len, gso_size, budget = 256; Fixes: 3327a9c46352 ("selftests: add functionals test for UDP GRO") Signed-off-by: Andrei Gherzan Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20230201001612.515730-1-andrei.gherzan@canonical.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- tools/testing/selftests/net/udpgso_bench_rx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 6a193425c367..d0895bd1933f 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -250,7 +250,7 @@ static int recv_msg(int fd, char *buf, int len, int *gso_size) static void do_flush_udp(int fd) { static char rbuf[ETH_MAX_MTU]; - int ret, len, gso_size, budget = 256; + int ret, len, gso_size = 0, budget = 256; len = cfg_read_all ? sizeof(rbuf) : 0; while (budget--) { From 4babbd1f594d2004c4c106419187ca1a24428941 Mon Sep 17 00:00:00 2001 From: Andrei Gherzan Date: Wed, 1 Feb 2023 00:16:12 +0000 Subject: [PATCH 1222/4345] selftests: net: udpgso_bench_rx/tx: Stop when wrong CLI args are provided [ Upstream commit db9b47ee9f5f375ab0c5daeb20321c75b4fa657d ] Leaving unrecognized arguments buried in the output, can easily hide a CLI/script typo. Avoid this by exiting when wrong arguments are provided to the udpgso_bench test programs. Fixes: 3a687bef148d ("selftests: udp gso benchmark") Signed-off-by: Andrei Gherzan Cc: Willem de Bruijn Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20230201001612.515730-2-andrei.gherzan@canonical.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- tools/testing/selftests/net/udpgso_bench_rx.c | 2 ++ tools/testing/selftests/net/udpgso_bench_tx.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index d0895bd1933f..4058c7451e70 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -336,6 +336,8 @@ static void parse_opts(int argc, char **argv) cfg_verify = true; cfg_read_all = true; break; + default: + exit(1); } } diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index f1fdaa270291..b47b5c32039f 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -490,6 +490,8 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_zerocopy = true; break; + default: + exit(1); } } From 9e7e2887ccb8f0e3cc16228521a32fb80c35a26f Mon Sep 17 00:00:00 2001 From: Andrei Gherzan Date: Wed, 1 Feb 2023 00:16:14 +0000 Subject: [PATCH 1223/4345] selftests: net: udpgso_bench: Fix racing bug between the rx/tx programs [ Upstream commit dafe93b9ee21028d625dce347118b82659652eff ] "udpgro_bench.sh" invokes udpgso_bench_rx/udpgso_bench_tx programs subsequently and while doing so, there is a chance that the rx one is not ready to accept socket connections. This racing bug could fail the test with at least one of the following: ./udpgso_bench_tx: connect: Connection refused ./udpgso_bench_tx: sendmsg: Connection refused ./udpgso_bench_tx: write: Connection refused This change addresses this by making udpgro_bench.sh wait for the rx program to be ready before firing off the tx one - up to a 10s timeout. Fixes: 3a687bef148d ("selftests: udp gso benchmark") Signed-off-by: Andrei Gherzan Cc: Paolo Abeni Cc: Willem de Bruijn Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20230201001612.515730-3-andrei.gherzan@canonical.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- tools/testing/selftests/net/udpgso_bench.sh | 22 ++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index dc932fd65363..640bc43452fa 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -7,6 +7,7 @@ readonly GREEN='\033[0;92m' readonly YELLOW='\033[0;33m' readonly RED='\033[0;31m' readonly NC='\033[0m' # No Color +readonly TESTPORT=8000 readonly KSFT_PASS=0 readonly KSFT_FAIL=1 @@ -56,11 +57,26 @@ trap wake_children EXIT run_one() { local -r args=$@ + local nr_socks=0 + local i=0 + local -r timeout=10 - ./udpgso_bench_rx & - ./udpgso_bench_rx -t & + ./udpgso_bench_rx -p "$TESTPORT" & + ./udpgso_bench_rx -p "$TESTPORT" -t & - ./udpgso_bench_tx ${args} + # Wait for the above test program to get ready to receive connections. + while [ "$i" -lt "$timeout" ]; do + nr_socks="$(ss -lnHi | grep -c "\*:${TESTPORT}")" + [ "$nr_socks" -eq 2 ] && break + i=$((i + 1)) + sleep 1 + done + if [ "$nr_socks" -ne 2 ]; then + echo "timed out while waiting for udpgso_bench_rx" + exit 1 + fi + + ./udpgso_bench_tx -p "$TESTPORT" ${args} } run_in_netns() { From 812236bb6a89f1a00ac29e6a78033e8ad9f6e73c Mon Sep 17 00:00:00 2001 From: Andrei Gherzan Date: Wed, 1 Feb 2023 00:16:16 +0000 Subject: [PATCH 1224/4345] selftests: net: udpgso_bench_tx: Cater for pending datagrams zerocopy benchmarking [ Upstream commit 329c9cd769c2e306957df031efff656c40922c76 ] The test tool can check that the zerocopy number of completions value is valid taking into consideration the number of datagram send calls. This can catch the system into a state where the datagrams are still in the system (for example in a qdisk, waiting for the network interface to return a completion notification, etc). This change adds a retry logic of computing the number of completions up to a configurable (via CLI) timeout (default: 2 seconds). Fixes: 79ebc3c26010 ("net/udpgso_bench_tx: options to exercise TX CMSG") Signed-off-by: Andrei Gherzan Cc: Willem de Bruijn Cc: Paolo Abeni Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20230201001612.515730-4-andrei.gherzan@canonical.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- tools/testing/selftests/net/udpgso_bench_tx.c | 34 +++++++++++++++---- 1 file changed, 27 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index b47b5c32039f..477392715a9a 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -62,6 +62,7 @@ static int cfg_payload_len = (1472 * 42); static int cfg_port = 8000; static int cfg_runtime_ms = -1; static bool cfg_poll; +static int cfg_poll_loop_timeout_ms = 2000; static bool cfg_segment; static bool cfg_sendmmsg; static bool cfg_tcp; @@ -235,16 +236,17 @@ static void flush_errqueue_recv(int fd) } } -static void flush_errqueue(int fd, const bool do_poll) +static void flush_errqueue(int fd, const bool do_poll, + unsigned long poll_timeout, const bool poll_err) { if (do_poll) { struct pollfd fds = {0}; int ret; fds.fd = fd; - ret = poll(&fds, 1, 500); + ret = poll(&fds, 1, poll_timeout); if (ret == 0) { - if (cfg_verbose) + if ((cfg_verbose) && (poll_err)) fprintf(stderr, "poll timeout\n"); } else if (ret < 0) { error(1, errno, "poll"); @@ -254,6 +256,20 @@ static void flush_errqueue(int fd, const bool do_poll) flush_errqueue_recv(fd); } +static void flush_errqueue_retry(int fd, unsigned long num_sends) +{ + unsigned long tnow, tstop; + bool first_try = true; + + tnow = gettimeofday_ms(); + tstop = tnow + cfg_poll_loop_timeout_ms; + do { + flush_errqueue(fd, true, tstop - tnow, first_try); + first_try = false; + tnow = gettimeofday_ms(); + } while ((stat_zcopies != num_sends) && (tnow < tstop)); +} + static int send_tcp(int fd, char *data) { int ret, done = 0, count = 0; @@ -413,7 +429,8 @@ static int send_udp_segment(int fd, char *data) static void usage(const char *filepath) { - error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", + error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] " + "[-L secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", filepath); } @@ -423,7 +440,7 @@ static void parse_opts(int argc, char **argv) int max_len, hdrlen; int c; - while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) { + while ((c = getopt(argc, argv, "46acC:D:Hl:L:mM:p:s:PS:tTuvz")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -452,6 +469,9 @@ static void parse_opts(int argc, char **argv) case 'l': cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000; break; + case 'L': + cfg_poll_loop_timeout_ms = strtoul(optarg, NULL, 10) * 1000; + break; case 'm': cfg_sendmmsg = true; break; @@ -679,7 +699,7 @@ int main(int argc, char **argv) num_sends += send_udp(fd, buf[i]); num_msgs++; if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp) - flush_errqueue(fd, cfg_poll); + flush_errqueue(fd, cfg_poll, 500, true); if (cfg_msg_nr && num_msgs >= cfg_msg_nr) break; @@ -698,7 +718,7 @@ int main(int argc, char **argv) } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop)); if (cfg_zerocopy || cfg_tx_tstamp) - flush_errqueue(fd, true); + flush_errqueue_retry(fd, num_sends); if (close(fd)) error(1, errno, "close"); From 4fb430c6987817b5992e04b417755c339f72f8fe Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 2 Feb 2023 18:35:16 +0200 Subject: [PATCH 1225/4345] virtio-net: Keep stop() to follow mirror sequence of open() [ Upstream commit 63b114042d8a9c02d9939889177c36dbdb17a588 ] Cited commit in fixes tag frees rxq xdp info while RQ NAPI is still enabled and packet processing may be ongoing. Follow the mirror sequence of open() in the stop() callback. This ensures that when rxq info is unregistered, no rx packet processing is ongoing. Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info") Acked-by: Michael S. Tsirkin Reviewed-by: Jiri Pirko Signed-off-by: Parav Pandit Link: https://lore.kernel.org/r/20230202163516.12559-1-parav@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0605c28c684b..d53321116136 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1928,8 +1928,8 @@ static int virtnet_close(struct net_device *dev) cancel_delayed_work_sync(&vi->refill); for (i = 0; i < vi->max_queue_pairs; i++) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); napi_disable(&vi->rq[i].napi); + xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); virtnet_napi_tx_disable(&vi->sq[i].napi); } From 70154489f531587996f3e9d7cceeee65cff0001d Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Thu, 2 Feb 2023 00:02:18 +0300 Subject: [PATCH 1226/4345] net: openvswitch: fix flow memory leak in ovs_flow_cmd_new [ Upstream commit 0c598aed445eb45b0ee7ba405f7ece99ee349c30 ] Syzkaller reports a memory leak of new_flow in ovs_flow_cmd_new() as it is not freed when an allocation of a key fails. BUG: memory leak unreferenced object 0xffff888116668000 (size 632): comm "syz-executor231", pid 1090, jiffies 4294844701 (age 18.871s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000defa3494>] kmem_cache_zalloc include/linux/slab.h:654 [inline] [<00000000defa3494>] ovs_flow_alloc+0x19/0x180 net/openvswitch/flow_table.c:77 [<00000000c67d8873>] ovs_flow_cmd_new+0x1de/0xd40 net/openvswitch/datapath.c:957 [<0000000010a539a8>] genl_family_rcv_msg_doit+0x22d/0x330 net/netlink/genetlink.c:739 [<00000000dff3302d>] genl_family_rcv_msg net/netlink/genetlink.c:783 [inline] [<00000000dff3302d>] genl_rcv_msg+0x328/0x590 net/netlink/genetlink.c:800 [<000000000286dd87>] netlink_rcv_skb+0x153/0x430 net/netlink/af_netlink.c:2515 [<0000000061fed410>] genl_rcv+0x24/0x40 net/netlink/genetlink.c:811 [<000000009dc0f111>] netlink_unicast_kernel net/netlink/af_netlink.c:1313 [inline] [<000000009dc0f111>] netlink_unicast+0x545/0x7f0 net/netlink/af_netlink.c:1339 [<000000004a5ee816>] netlink_sendmsg+0x8e7/0xde0 net/netlink/af_netlink.c:1934 [<00000000482b476f>] sock_sendmsg_nosec net/socket.c:651 [inline] [<00000000482b476f>] sock_sendmsg+0x152/0x190 net/socket.c:671 [<00000000698574ba>] ____sys_sendmsg+0x70a/0x870 net/socket.c:2356 [<00000000d28d9e11>] ___sys_sendmsg+0xf3/0x170 net/socket.c:2410 [<0000000083ba9120>] __sys_sendmsg+0xe5/0x1b0 net/socket.c:2439 [<00000000c00628f8>] do_syscall_64+0x30/0x40 arch/x86/entry/common.c:46 [<000000004abfdcf4>] entry_SYSCALL_64_after_hwframe+0x61/0xc6 To fix this the patch rearranges the goto labels to reflect the order of object allocations and adds appropriate goto statements on the error paths. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: 68bb10101e6b ("openvswitch: Fix flow lookup to use unmasked key") Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Acked-by: Eelco Chaudron Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230201210218.361970-1-pchelkin@ispras.ru Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/openvswitch/datapath.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 435f7f1be614..b625ab5e9a43 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -964,14 +964,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) { error = -ENOMEM; - goto err_kfree_key; + goto err_kfree_flow; } ovs_match_init(&match, key, false, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) - goto err_kfree_flow; + goto err_kfree_key; ovs_flow_mask_key(&new_flow->key, key, true, &mask); @@ -979,14 +979,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], key, log); if (error) - goto err_kfree_flow; + goto err_kfree_key; /* Validate actions. */ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, &acts, log); if (error) { OVS_NLERR(log, "Flow actions may not be safe on all matching packets."); - goto err_kfree_flow; + goto err_kfree_key; } reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false, @@ -1086,10 +1086,10 @@ err_unlock_ovs: kfree_skb(reply); err_kfree_acts: ovs_nla_free_flow_actions(acts); -err_kfree_flow: - ovs_flow_free(new_flow, false); err_kfree_key: kfree(key); +err_kfree_flow: + ovs_flow_free(new_flow, false); error: return error; } From 87d4ff18738fd71e7e3c10827c80257da6283697 Mon Sep 17 00:00:00 2001 From: Anton Gusev Date: Fri, 3 Feb 2023 16:22:13 +0300 Subject: [PATCH 1227/4345] efi: fix potential NULL deref in efi_mem_reserve_persistent [ Upstream commit 966d47e1f27c45507c5df82b2a2157e5a4fd3909 ] When iterating on a linked list, a result of memremap is dereferenced without checking it for NULL. This patch adds a check that falls back on allocating a new page in case memremap doesn't succeed. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 18df7577adae ("efi/memreserve: deal with memreserve entries in unmapped memory") Signed-off-by: Anton Gusev [ardb: return -ENOMEM instead of breaking out of the loop] Signed-off-by: Ard Biesheuvel Signed-off-by: Sasha Levin --- drivers/firmware/efi/efi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index a2765d668856..332739f3eded 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -950,6 +950,8 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) /* first try to find a slot in an existing linked list entry */ for (prsv = efi_memreserve_root->next; prsv; ) { rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB); + if (!rsv) + return -ENOMEM; index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size); if (index < rsv->size) { rsv->entry[index].base = addr; From 8aba483f70344aaeca03630d4e8b8de31febcddd Mon Sep 17 00:00:00 2001 From: Bhaskar Upadhaya Date: Wed, 10 Feb 2021 12:28:29 -0800 Subject: [PATCH 1228/4345] qede: add netpoll support for qede driver [ Upstream commit 961aa716235f58088e99acafbe66027d678061ce ] handle netpoll case when qede_poll is called by netpoll layer with budget 0 Signed-off-by: Bhaskar Upadhaya Signed-off-by: Igor Russkikh Signed-off-by: Ariel Elior Signed-off-by: David S. Miller Stable-dep-of: 2ccce20d51fa ("qede: execute xdp_do_flush() before napi_complete_done()") Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qede/qede_fp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index d210632676d3..5b1885c0a8bd 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1456,7 +1456,8 @@ int qede_poll(struct napi_struct *napi, int budget) rx_work_done = (likely(fp->type & QEDE_FASTPATH_RX) && qede_has_rx_work(fp->rxq)) ? qede_rx_int(fp, budget) : 0; - if (rx_work_done < budget) { + /* Handle case where we are called by netpoll with a budget of 0 */ + if (rx_work_done < budget || !budget) { if (!qede_poll_is_more_work(fp)) { napi_complete_done(napi, rx_work_done); From d09b0bf9ffd37e66ce74787b2076d83e938253e8 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 25 Jan 2023 08:48:57 +0100 Subject: [PATCH 1229/4345] qede: execute xdp_do_flush() before napi_complete_done() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2ccce20d51faa0178086163ccb6c84a099a87ab4 ] Make sure that xdp_do_flush() is always executed before napi_complete_done(). This is important for two reasons. First, a redirect to an XSKMAP assumes that a call to xdp_do_redirect() from napi context X on CPU Y will be followed by a xdp_do_flush() from the same napi context and CPU. This is not guaranteed if the napi_complete_done() is executed before xdp_do_flush(), as it tells the napi logic that it is fine to schedule napi context X on another CPU. Details from a production system triggering this bug using the veth driver can be found following the first link below. The second reason is that the XDP_REDIRECT logic in itself relies on being inside a single NAPI instance through to the xdp_do_flush() call for RCU protection of all in-kernel data structures. Details can be found in the second link below. Fixes: d1b25b79e162b ("qede: add .ndo_xdp_xmit() and XDP_REDIRECT support") Signed-off-by: Magnus Karlsson Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20221220185903.1105011-1-sbohrer@cloudflare.com Link: https://lore.kernel.org/all/20210624160609.292325-1-toke@redhat.com/ Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qede/qede_fp.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 5b1885c0a8bd..a632de208a7d 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1456,6 +1456,10 @@ int qede_poll(struct napi_struct *napi, int budget) rx_work_done = (likely(fp->type & QEDE_FASTPATH_RX) && qede_has_rx_work(fp->rxq)) ? qede_rx_int(fp, budget) : 0; + + if (fp->xdp_xmit & QEDE_XDP_REDIRECT) + xdp_do_flush(); + /* Handle case where we are called by netpoll with a budget of 0 */ if (rx_work_done < budget || !budget) { if (!qede_poll_is_more_work(fp)) { @@ -1475,9 +1479,6 @@ int qede_poll(struct napi_struct *napi, int budget) qede_update_tx_producer(fp->xdp_tx); } - if (fp->xdp_xmit & QEDE_XDP_REDIRECT) - xdp_do_flush_map(); - return rx_work_done; } From 4e66ba3cfb4fd353bac7f6675f7a9a51386e7a4b Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sat, 7 Jan 2023 13:32:29 +0100 Subject: [PATCH 1230/4345] i2c: mxs: suppress probe-deferral error message [ Upstream commit 78a4471fa1a76a8bef4919105de67660a89a1e9b ] During boot of I2SE Duckbill the kernel log contains a confusing error: Failed to request dma This is caused by i2c-mxs tries to request a not yet available DMA channel (-EPROBE_DEFER). So suppress this message by using dev_err_probe(). Signed-off-by: Stefan Wahren Reviewed-by: Fabio Estevam Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-mxs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c index c4b08a924461..abad24808e85 100644 --- a/drivers/i2c/busses/i2c-mxs.c +++ b/drivers/i2c/busses/i2c-mxs.c @@ -842,8 +842,8 @@ static int mxs_i2c_probe(struct platform_device *pdev) /* Setup the DMA */ i2c->dmach = dma_request_chan(dev, "rx-tx"); if (IS_ERR(i2c->dmach)) { - dev_err(dev, "Failed to request dma\n"); - return PTR_ERR(i2c->dmach); + return dev_err_probe(dev, PTR_ERR(i2c->dmach), + "Failed to request dma\n"); } platform_set_drvdata(pdev, i2c); From 1b28bf868fceba7e1260d87cfe5a3e5069546bad Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Tue, 10 Jan 2023 13:53:10 +0100 Subject: [PATCH 1231/4345] scsi: target: core: Fix warning on RT kernels [ Upstream commit 84ed64b1a7a7fcd507598dee7708c1f225123711 ] Calling spin_lock_irqsave() does not disable the interrupts on realtime kernels, remove the warning and replace assert_spin_locked() with lockdep_assert_held(). Signed-off-by: Maurizio Lombardi Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230110125310.55884-1-mlombard@redhat.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/target_core_tmr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index e4513ef09159..3efd5a3bd69d 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -82,8 +82,8 @@ static bool __target_check_io_state(struct se_cmd *se_cmd, { struct se_session *sess = se_cmd->se_sess; - assert_spin_locked(&sess->sess_cmd_lock); - WARN_ON_ONCE(!irqs_disabled()); + lockdep_assert_held(&sess->sess_cmd_lock); + /* * If command already reached CMD_T_COMPLETE state within * target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown, From 9758ffe1c07b86aefd7ca8e40d9a461293427ca0 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Tue, 17 Jan 2023 13:39:37 -0600 Subject: [PATCH 1232/4345] scsi: iscsi_tcp: Fix UAF during login when accessing the shost ipaddress [ Upstream commit f484a794e4ee2a9ce61f52a78e810ac45f3fe3b3 ] If during iscsi_sw_tcp_session_create() iscsi_tcp_r2tpool_alloc() fails, userspace could be accessing the host's ipaddress attr. If we then free the session via iscsi_session_teardown() while userspace is still accessing the session we will hit a use after free bug. Set the tcp_sw_host->session after we have completed session creation and can no longer fail. Link: https://lore.kernel.org/r/20230117193937.21244-3-michael.christie@oracle.com Signed-off-by: Mike Christie Reviewed-by: Lee Duncan Acked-by: Ding Hui Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/iscsi_tcp.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 6485c1aa9e74..252d7881f99c 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -802,7 +802,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, enum iscsi_host_param param, char *buf) { struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(shost); - struct iscsi_session *session = tcp_sw_host->session; + struct iscsi_session *session; struct iscsi_conn *conn; struct iscsi_tcp_conn *tcp_conn; struct iscsi_sw_tcp_conn *tcp_sw_conn; @@ -812,6 +812,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, switch (param) { case ISCSI_HOST_PARAM_IPADDRESS: + session = tcp_sw_host->session; if (!session) return -ENOTCONN; @@ -906,12 +907,14 @@ iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max, if (!cls_session) goto remove_host; session = cls_session->dd_data; - tcp_sw_host = iscsi_host_priv(shost); - tcp_sw_host->session = session; shost->can_queue = session->scsi_cmds_max; if (iscsi_tcp_r2tpool_alloc(session)) goto remove_session; + + /* We are now fully setup so expose the session to sysfs. */ + tcp_sw_host = iscsi_host_priv(shost); + tcp_sw_host->session = session; return cls_session; remove_session: From ac4d9c86e9f5dafc21af50d24d915a63f1cc0c97 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 12 Jan 2023 22:38:05 -0800 Subject: [PATCH 1233/4345] i2c: rk3x: fix a bunch of kernel-doc warnings [ Upstream commit 0582d984793d30442da88fe458674502bad1ad29 ] Fix multiple W=1 kernel-doc warnings in i2c-rk3x.c: drivers/i2c/busses/i2c-rk3x.c:83: warning: missing initial short description on line: * struct i2c_spec_values: drivers/i2c/busses/i2c-rk3x.c:139: warning: missing initial short description on line: * struct rk3x_i2c_calced_timings: drivers/i2c/busses/i2c-rk3x.c:162: warning: missing initial short description on line: * struct rk3x_i2c_soc_data: drivers/i2c/busses/i2c-rk3x.c:242: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Generate a START condition, which triggers a REG_INT_START interrupt. drivers/i2c/busses/i2c-rk3x.c:261: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Generate a STOP condition, which triggers a REG_INT_STOP interrupt. drivers/i2c/busses/i2c-rk3x.c:304: warning: expecting prototype for Setup a read according to i2c(). Prototype was for rk3x_i2c_prepare_read() instead drivers/i2c/busses/i2c-rk3x.c:335: warning: expecting prototype for Fill the transmit buffer with data from i2c(). Prototype was for rk3x_i2c_fill_transmit_buf() instead drivers/i2c/busses/i2c-rk3x.c:535: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Get timing values of I2C specification drivers/i2c/busses/i2c-rk3x.c:552: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Calculate divider values for desired SCL frequency drivers/i2c/busses/i2c-rk3x.c:713: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Calculate timing values for desired SCL frequency drivers/i2c/busses/i2c-rk3x.c:963: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Setup I2C registers for an I2C operation specified by msgs, num. Signed-off-by: Randy Dunlap Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-rk3x.c | 44 +++++++++++++++++------------------ 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index 02ddb237f69a..13c14eb175e9 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -80,7 +80,7 @@ enum { #define DEFAULT_SCL_RATE (100 * 1000) /* Hz */ /** - * struct i2c_spec_values: + * struct i2c_spec_values - I2C specification values for various modes * @min_hold_start_ns: min hold time (repeated) START condition * @min_low_ns: min LOW period of the SCL clock * @min_high_ns: min HIGH period of the SCL cloc @@ -136,7 +136,7 @@ static const struct i2c_spec_values fast_mode_plus_spec = { }; /** - * struct rk3x_i2c_calced_timings: + * struct rk3x_i2c_calced_timings - calculated V1 timings * @div_low: Divider output for low * @div_high: Divider output for high * @tuning: Used to adjust setup/hold data time, @@ -159,7 +159,7 @@ enum rk3x_i2c_state { }; /** - * struct rk3x_i2c_soc_data: + * struct rk3x_i2c_soc_data - SOC-specific data * @grf_offset: offset inside the grf regmap for setting the i2c type * @calc_timings: Callback function for i2c timing information calculated */ @@ -239,7 +239,8 @@ static inline void rk3x_i2c_clean_ipd(struct rk3x_i2c *i2c) } /** - * Generate a START condition, which triggers a REG_INT_START interrupt. + * rk3x_i2c_start - Generate a START condition, which triggers a REG_INT_START interrupt. + * @i2c: target controller data */ static void rk3x_i2c_start(struct rk3x_i2c *i2c) { @@ -258,8 +259,8 @@ static void rk3x_i2c_start(struct rk3x_i2c *i2c) } /** - * Generate a STOP condition, which triggers a REG_INT_STOP interrupt. - * + * rk3x_i2c_stop - Generate a STOP condition, which triggers a REG_INT_STOP interrupt. + * @i2c: target controller data * @error: Error code to return in rk3x_i2c_xfer */ static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error) @@ -298,7 +299,8 @@ static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error) } /** - * Setup a read according to i2c->msg + * rk3x_i2c_prepare_read - Setup a read according to i2c->msg + * @i2c: target controller data */ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c) { @@ -329,7 +331,8 @@ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c) } /** - * Fill the transmit buffer with data from i2c->msg + * rk3x_i2c_fill_transmit_buf - Fill the transmit buffer with data from i2c->msg + * @i2c: target controller data */ static void rk3x_i2c_fill_transmit_buf(struct rk3x_i2c *i2c) { @@ -532,11 +535,10 @@ out: } /** - * Get timing values of I2C specification - * + * rk3x_i2c_get_spec - Get timing values of I2C specification * @speed: Desired SCL frequency * - * Returns: Matched i2c spec values. + * Return: Matched i2c_spec_values. */ static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed) { @@ -549,13 +551,12 @@ static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed) } /** - * Calculate divider values for desired SCL frequency - * + * rk3x_i2c_v0_calc_timings - Calculate divider values for desired SCL frequency * @clk_rate: I2C input clock rate * @t: Known I2C timing information * @t_calc: Caculated rk3x private timings that would be written into regs * - * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case + * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case * a best-effort divider value is returned in divs. If the target rate is * too high, we silently use the highest possible rate. */ @@ -710,13 +711,12 @@ static int rk3x_i2c_v0_calc_timings(unsigned long clk_rate, } /** - * Calculate timing values for desired SCL frequency - * + * rk3x_i2c_v1_calc_timings - Calculate timing values for desired SCL frequency * @clk_rate: I2C input clock rate * @t: Known I2C timing information * @t_calc: Caculated rk3x private timings that would be written into regs * - * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case + * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case * a best-effort divider value is returned in divs. If the target rate is * too high, we silently use the highest possible rate. * The following formulas are v1's method to calculate timings. @@ -960,14 +960,14 @@ static int rk3x_i2c_clk_notifier_cb(struct notifier_block *nb, unsigned long } /** - * Setup I2C registers for an I2C operation specified by msgs, num. - * - * Must be called with i2c->lock held. - * + * rk3x_i2c_setup - Setup I2C registers for an I2C operation specified by msgs, num. + * @i2c: target controller data * @msgs: I2C msgs to process * @num: Number of msgs * - * returns: Number of I2C msgs processed or negative in case of error + * Must be called with i2c->lock held. + * + * Return: Number of I2C msgs processed or negative in case of error */ static int rk3x_i2c_setup(struct rk3x_i2c *i2c, struct i2c_msg *msgs, int num) { From 2b1e8e20b9840041439bbe1e70475bd5b611b5b1 Mon Sep 17 00:00:00 2001 From: Koba Ko Date: Tue, 17 Jan 2023 20:34:36 +0800 Subject: [PATCH 1234/4345] platform/x86: dell-wmi: Add a keymap for KEY_MUTE in type 0x0010 table [ Upstream commit 83bcf3e52e9cfc727df33f1055ef0618c91719d0 ] Some platforms send the speaker-mute key from EC. dell-wmi can't recognize it. Add a new keymap for KEY_MUTE in type 0x0010 table. Signed-off-by: Koba Ko Link: https://lore.kernel.org/r/20230117123436.200440-1-koba.ko@canonical.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/dell-wmi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index bbdb3e860892..6ef327a80ccf 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -259,6 +259,9 @@ static const struct key_entry dell_wmi_keymap_type_0010[] = { { KE_KEY, 0x57, { KEY_BRIGHTNESSDOWN } }, { KE_KEY, 0x58, { KEY_BRIGHTNESSUP } }, + /*Speaker Mute*/ + { KE_KEY, 0x109, { KEY_MUTE} }, + /* Mic mute */ { KE_KEY, 0x150, { KEY_MICMUTE } }, From 4bbc34401d9792c8b21d3ffb149f2a22d6036ab0 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Mon, 23 Jan 2023 11:43:23 -0800 Subject: [PATCH 1235/4345] net/x25: Fix to not accept on connected socket [ Upstream commit f2b0b5210f67c56a3bcdf92ff665fb285d6e0067 ] When listen() and accept() are called on an x25 socket that connect() succeeds, accept() succeeds immediately. This is because x25_connect() queues the skb to sk->sk_receive_queue, and x25_accept() dequeues it. This creates a child socket with the sk of the parent x25 socket, which can cause confusion. Fix x25_listen() to return -EINVAL if the socket has already been successfully connect()ed to avoid this issue. Signed-off-by: Hyunwoo Kim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/x25/af_x25.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index d231d4620c38..161dc194e634 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -492,6 +492,12 @@ static int x25_listen(struct socket *sock, int backlog) int rc = -EOPNOTSUPP; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + rc = -EINVAL; + release_sock(sk); + return rc; + } + if (sk->sk_state != TCP_LISTEN) { memset(&x25_sk(sk)->dest_addr, 0, X25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; From 30d0e2cf9900efe2b96ba0a8d879e24cfe5ad7cb Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Fri, 2 Dec 2022 16:28:48 +0100 Subject: [PATCH 1236/4345] iio: adc: stm32-dfsdm: fill module aliases [ Upstream commit cc3304052a89ab6ac887ed9224420a27e3d354e1 ] When STM32 DFSDM driver is built as module, no modalias information is available. This prevents module to be loaded by udev. Add MODULE_DEVICE_TABLE() to fill module aliases. Fixes: e2e6771c6462 ("IIO: ADC: add STM32 DFSDM sigma delta ADC support") Signed-off-by: Olivier Moysan Link: https://lore.kernel.org/r/20221202152848.45585-1-olivier.moysan@foss.st.com Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/adc/stm32-dfsdm-adc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index 9234f14167b7..171d73efb2f8 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -1521,6 +1521,7 @@ static const struct of_device_id stm32_dfsdm_adc_match[] = { }, {} }; +MODULE_DEVICE_TABLE(of, stm32_dfsdm_adc_match); static int stm32_dfsdm_adc_probe(struct platform_device *pdev) { From 1ca8629505fdea93bf0c9c99055e3cd0fa2350a3 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Sun, 4 Jul 2021 02:33:12 +0100 Subject: [PATCH 1237/4345] usb: dwc3: dwc3-qcom: Fix typo in the dwc3 vbus override API [ Upstream commit 8e6cb5d27e8246d9c986ec162d066a502d2b602b ] There was an extra character in the dwc3_qcom_vbus_override_enable() function. Removed the extra character. Signed-off-by: Wesley Cheng Signed-off-by: Bryan O'Donoghue Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210704013314.200951-2-bryan.odonoghue@linaro.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: eb320f76e31d ("usb: dwc3: qcom: enable vbus override when in OTG dr-mode") Signed-off-by: Sasha Levin --- drivers/usb/dwc3/dwc3-qcom.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index 528e36cc58ea..c2662e3a5b84 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -115,7 +115,7 @@ static inline void dwc3_qcom_clrbits(void __iomem *base, u32 offset, u32 val) readl(base + offset); } -static void dwc3_qcom_vbus_overrride_enable(struct dwc3_qcom *qcom, bool enable) +static void dwc3_qcom_vbus_override_enable(struct dwc3_qcom *qcom, bool enable) { if (enable) { dwc3_qcom_setbits(qcom->qscratch_base, QSCRATCH_SS_PHY_CTRL, @@ -136,7 +136,7 @@ static int dwc3_qcom_vbus_notifier(struct notifier_block *nb, struct dwc3_qcom *qcom = container_of(nb, struct dwc3_qcom, vbus_nb); /* enable vbus override for device mode */ - dwc3_qcom_vbus_overrride_enable(qcom, event); + dwc3_qcom_vbus_override_enable(qcom, event); qcom->mode = event ? USB_DR_MODE_PERIPHERAL : USB_DR_MODE_HOST; return NOTIFY_DONE; @@ -148,7 +148,7 @@ static int dwc3_qcom_host_notifier(struct notifier_block *nb, struct dwc3_qcom *qcom = container_of(nb, struct dwc3_qcom, host_nb); /* disable vbus override in host mode */ - dwc3_qcom_vbus_overrride_enable(qcom, !event); + dwc3_qcom_vbus_override_enable(qcom, !event); qcom->mode = event ? USB_DR_MODE_HOST : USB_DR_MODE_PERIPHERAL; return NOTIFY_DONE; @@ -833,7 +833,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev) /* enable vbus override for device mode */ if (qcom->mode == USB_DR_MODE_PERIPHERAL) - dwc3_qcom_vbus_overrride_enable(qcom, true); + dwc3_qcom_vbus_override_enable(qcom, true); /* register extcon to override sw_vbus on Vbus change later */ ret = dwc3_qcom_register_extcon(qcom); From 6e5565aa004741646df73255e3823b59b216c3af Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 09:31:21 +0100 Subject: [PATCH 1238/4345] usb: dwc3: qcom: enable vbus override when in OTG dr-mode [ Upstream commit eb320f76e31dc835b9f57f04af1a2353b13bb7d8 ] With vbus override enabled when in OTG dr_mode, Host<->Peripheral switch now works on SM8550, otherwise the DWC3 seems to be stuck in Host mode only. Fixes: a4333c3a6ba9 ("usb: dwc3: Add Qualcomm DWC3 glue driver") Reviewed-by: Bryan O'Donoghue Signed-off-by: Neil Armstrong Link: https://lore.kernel.org/r/20230123-topic-sm8550-upstream-dwc3-qcom-otg-v2-1-2d400e598463@linaro.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/dwc3/dwc3-qcom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index c2662e3a5b84..dac13fe97811 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -832,7 +832,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev) qcom->mode = usb_get_dr_mode(&qcom->dwc3->dev); /* enable vbus override for device mode */ - if (qcom->mode == USB_DR_MODE_PERIPHERAL) + if (qcom->mode != USB_DR_MODE_HOST) dwc3_qcom_vbus_override_enable(qcom, true); /* register extcon to override sw_vbus on Vbus change later */ From 434a36ed64ac399b567174075b75d59d916dadfc Mon Sep 17 00:00:00 2001 From: Udipto Goswami Date: Tue, 24 Jan 2023 14:41:49 +0530 Subject: [PATCH 1239/4345] usb: gadget: f_fs: Fix unbalanced spinlock in __ffs_ep0_queue_wait [ Upstream commit 921deb9da15851425ccbb6ee409dc2fd8fbdfe6b ] __ffs_ep0_queue_wait executes holding the spinlock of &ffs->ev.waitq.lock and unlocks it after the assignments to usb_request are done. However in the code if the request is already NULL we bail out returning -EINVAL but never unlocked the spinlock. Fix this by adding spin_unlock_irq &ffs->ev.waitq.lock before returning. Fixes: 6a19da111057 ("usb: gadget: f_fs: Prevent race during ffs_ep0_queue_wait") Reviewed-by: John Keeping Signed-off-by: Udipto Goswami Link: https://lore.kernel.org/r/20230124091149.18647-1-quic_ugoswami@quicinc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/f_fs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 94000fd190e5..8c48c9f801be 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -278,8 +278,10 @@ static int __ffs_ep0_queue_wait(struct ffs_data *ffs, char *data, size_t len) struct usb_request *req = ffs->ep0req; int ret; - if (!req) + if (!req) { + spin_unlock_irq(&ffs->ev.waitq.lock); return -EINVAL; + } req->zero = len < le16_to_cpu(ffs->ev.setup.wLength); From 55515d7d8743b71b80bfe68e89eb9d92630626ab Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Tue, 24 Jan 2023 11:16:54 -0500 Subject: [PATCH 1240/4345] vc_screen: move load of struct vc_data pointer in vcs_read() to avoid UAF [ Upstream commit 226fae124b2dac217ea5436060d623ff3385bc34 ] After a call to console_unlock() in vcs_read() the vc_data struct can be freed by vc_deallocate(). Because of that, the struct vc_data pointer load must be done at the top of while loop in vcs_read() to avoid a UAF when vcs_size() is called. Syzkaller reported a UAF in vcs_size(). BUG: KASAN: use-after-free in vcs_size (drivers/tty/vt/vc_screen.c:215) Read of size 4 at addr ffff8881137479a8 by task 4a005ed81e27e65/1537 CPU: 0 PID: 1537 Comm: 4a005ed81e27e65 Not tainted 6.2.0-rc5 #1 Hardware name: Red Hat KVM, BIOS 1.15.0-2.module Call Trace: __asan_report_load4_noabort (mm/kasan/report_generic.c:350) vcs_size (drivers/tty/vt/vc_screen.c:215) vcs_read (drivers/tty/vt/vc_screen.c:415) vfs_read (fs/read_write.c:468 fs/read_write.c:450) ... Allocated by task 1191: ... kmalloc_trace (mm/slab_common.c:1069) vc_allocate (./include/linux/slab.h:580 ./include/linux/slab.h:720 drivers/tty/vt/vt.c:1128 drivers/tty/vt/vt.c:1108) con_install (drivers/tty/vt/vt.c:3383) tty_init_dev (drivers/tty/tty_io.c:1301 drivers/tty/tty_io.c:1413 drivers/tty/tty_io.c:1390) tty_open (drivers/tty/tty_io.c:2080 drivers/tty/tty_io.c:2126) chrdev_open (fs/char_dev.c:415) do_dentry_open (fs/open.c:883) vfs_open (fs/open.c:1014) ... Freed by task 1548: ... kfree (mm/slab_common.c:1021) vc_port_destruct (drivers/tty/vt/vt.c:1094) tty_port_destructor (drivers/tty/tty_port.c:296) tty_port_put (drivers/tty/tty_port.c:312) vt_disallocate_all (drivers/tty/vt/vt_ioctl.c:662 (discriminator 2)) vt_ioctl (drivers/tty/vt/vt_ioctl.c:903) tty_ioctl (drivers/tty/tty_io.c:2776) ... The buggy address belongs to the object at ffff888113747800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 424 bytes inside of 1024-byte region [ffff888113747800, ffff888113747c00) The buggy address belongs to the physical page: page:00000000b3fe6c7c refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x113740 head:00000000b3fe6c7c order:3 compound_mapcount:0 subpages_mapcount:0 compound_pincount:0 anon flags: 0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) raw: 0017ffffc0010200 ffff888100042dc0 0000000000000000 dead000000000001 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888113747880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888113747900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb > ffff888113747980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888113747a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888113747a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Disabling lock debugging due to kernel taint Fixes: ac751efa6a0d ("console: rename acquire/release_console_sem() to console_lock/unlock()") Reported-by: syzkaller Suggested-by: Jiri Slaby Signed-off-by: George Kennedy Link: https://lore.kernel.org/r/1674577014-12374-1-git-send-email-george.kennedy@oracle.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/vt/vc_screen.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 1850bacdb5b0..f566eb1839dc 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -386,10 +386,6 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) uni_mode = use_unicode(inode); attr = use_attributes(inode); - ret = -ENXIO; - vc = vcs_vc(inode, &viewed); - if (!vc) - goto unlock_out; ret = -EINVAL; if (pos < 0) @@ -407,6 +403,11 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) unsigned int this_round, skip = 0; int size; + ret = -ENXIO; + vc = vcs_vc(inode, &viewed); + if (!vc) + goto unlock_out; + /* Check whether we are above size each round, * as copy_to_user at the end of this loop * could sleep. From ab85074c308fdbf5d48c0b235412960f07ff788f Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Wed, 29 Jun 2022 17:34:42 -0700 Subject: [PATCH 1241/4345] Input: i8042 - move __initconst to fix code styling warning [ Upstream commit 95a9916c909f0b1d95e24b4232b4bc38ff755415 ] Move __intconst from before i8042_dmi_laptop_table[] to after it for consistent code styling. Signed-off-by: Werner Sembach Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20220629112725.12922-2-wse@tuxedocomputers.com Signed-off-by: Dmitry Torokhov Stable-dep-of: 9c445d2637c9 ("Input: i8042 - add Clevo PCX0DX to i8042 quirk table") Signed-off-by: Sasha Levin --- drivers/input/serio/i8042-x86ia64io.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 148a7c5fd0e2..91c6f24b4837 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -791,7 +791,7 @@ static const struct dmi_system_id __initconst i8042_dmi_nopnp_table[] = { { } }; -static const struct dmi_system_id __initconst i8042_dmi_laptop_table[] = { +static const struct dmi_system_id i8042_dmi_laptop_table[] __initconst = { { .matches = { DMI_MATCH(DMI_CHASSIS_TYPE, "8"), /* Portable */ From 04d99a0a966a4f3b901e3fa762114895aa994ea3 Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Wed, 29 Jun 2022 17:38:07 -0700 Subject: [PATCH 1242/4345] Input: i8042 - merge quirk tables [ Upstream commit ff946268a0813c35b790dfbe07c3bfaa7bfb869c ] Merge i8042 quirk tables to reduce code duplication for devices that need more than one quirk. Before every quirk had its own table with devices needing that quirk. If a new quirk needed to be added a new table had to be created. When a device needed multiple quirks, it appeared in multiple tables. Now only one table called i8042_dmi_quirk_table exists. In it every device has one entry and required quirks are coded in the .driver_data field of the struct dmi_system_id used by this table. Multiple quirks for one device can be applied by bitwise-or of the new SERIO_QUIRK_* defines. Also align quirkable options with command line parameters and make vendor wide quirks per device overwriteable on a per device basis. The first match is honored while following matches are ignored. So when a vendor wide quirk is defined in the table, a device can inserted before and therefore ignoring the vendor wide define. Signed-off-by: Werner Sembach Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20220629112725.12922-3-wse@tuxedocomputers.com Signed-off-by: Dmitry Torokhov Stable-dep-of: 9c445d2637c9 ("Input: i8042 - add Clevo PCX0DX to i8042 quirk table") Signed-off-by: Sasha Levin --- drivers/input/serio/i8042-x86ia64io.h | 1802 +++++++++++++------------ 1 file changed, 946 insertions(+), 856 deletions(-) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 91c6f24b4837..1d2b34aac0c7 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -67,25 +67,84 @@ static inline void i8042_write_command(int val) #include -static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { +#define SERIO_QUIRK_NOKBD BIT(0) +#define SERIO_QUIRK_NOAUX BIT(1) +#define SERIO_QUIRK_NOMUX BIT(2) +#define SERIO_QUIRK_FORCEMUX BIT(3) +#define SERIO_QUIRK_UNLOCK BIT(4) +#define SERIO_QUIRK_PROBE_DEFER BIT(5) +#define SERIO_QUIRK_RESET_ALWAYS BIT(6) +#define SERIO_QUIRK_RESET_NEVER BIT(7) +#define SERIO_QUIRK_DIECT BIT(8) +#define SERIO_QUIRK_DUMBKBD BIT(9) +#define SERIO_QUIRK_NOLOOP BIT(10) +#define SERIO_QUIRK_NOTIMEOUT BIT(11) +#define SERIO_QUIRK_KBDRESET BIT(12) +#define SERIO_QUIRK_DRITEK BIT(13) +#define SERIO_QUIRK_NOPNP BIT(14) + +/* Quirk table for different mainboards. Options similar or identical to i8042 + * module parameters. + * ORDERING IS IMPORTANT! The first match will be apllied and the rest ignored. + * This allows entries to overwrite vendor wide quirks on a per device basis. + * Where this is irrelevant, entries are sorted case sensitive by DMI_SYS_VENDOR + * and/or DMI_BOARD_VENDOR to make it easier to avoid dublicate entries. + */ +static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { { - /* - * Arima-Rioworks HDAMB - - * AUX LOOP command does not raise AUX IRQ - */ .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "RIOWORKS"), - DMI_MATCH(DMI_BOARD_NAME, "HDAMB"), - DMI_MATCH(DMI_BOARD_VERSION, "Rev E"), + DMI_MATCH(DMI_SYS_VENDOR, "ALIENWARE"), + DMI_MATCH(DMI_PRODUCT_NAME, "Sentia"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { - /* ASUS G1S */ .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc."), - DMI_MATCH(DMI_BOARD_NAME, "G1S"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Asus X450LCP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X450LCP"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_NEVER) + }, + { + /* ASUS ZenBook UX425UA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"), + }, + .driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER) + }, + { + /* ASUS ZenBook UM325UA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"), + }, + .driver_data = (void *)(SERIO_QUIRK_PROBE_DEFER | SERIO_QUIRK_RESET_NEVER) + }, + /* + * On some Asus laptops, just running self tests cause problems. + */ + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */ + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_NEVER) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /* Convertible Notebook */ + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_NEVER) }, { /* ASUS P65UP5 - AUX LOOP command does not raise AUX IRQ */ @@ -94,362 +153,23 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P/I-P65UP5"), DMI_MATCH(DMI_BOARD_VERSION, "REV 2.X"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { + /* ASUS G1S */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), - DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"), - DMI_MATCH(DMI_PRODUCT_VERSION, "8500"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), - DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"), - DMI_MATCH(DMI_PRODUCT_VERSION, "DL760"), - }, - }, - { - /* Dell Embedded Box PC 3000 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"), - }, - }, - { - /* OQO Model 01 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "OQO"), - DMI_MATCH(DMI_PRODUCT_NAME, "ZEPTO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "00"), - }, - }, - { - /* ULI EV4873 - AUX LOOP does not work properly */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ULI"), - DMI_MATCH(DMI_PRODUCT_NAME, "EV4873"), - DMI_MATCH(DMI_PRODUCT_VERSION, "5a"), - }, - }, - { - /* Microsoft Virtual Machine */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "Virtual Machine"), - DMI_MATCH(DMI_PRODUCT_VERSION, "VS2005R2"), - }, - }, - { - /* Medion MAM 2070 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), - DMI_MATCH(DMI_PRODUCT_NAME, "MAM 2070"), - DMI_MATCH(DMI_PRODUCT_VERSION, "5a"), - }, - }, - { - /* Medion Akoya E7225 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Medion"), - DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"), - DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), - }, - }, - { - /* Blue FB5601 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "blue"), - DMI_MATCH(DMI_PRODUCT_NAME, "FB5601"), - DMI_MATCH(DMI_PRODUCT_VERSION, "M606"), - }, - }, - { - /* Gigabyte M912 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "M912"), - DMI_MATCH(DMI_PRODUCT_VERSION, "01"), - }, - }, - { - /* Gigabyte M1022M netbook */ - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co.,Ltd."), - DMI_MATCH(DMI_BOARD_NAME, "M1022E"), - DMI_MATCH(DMI_BOARD_VERSION, "1.02"), - }, - }, - { - /* Gigabyte Spring Peak - defines wrong chassis type */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "Spring Peak"), - }, - }, - { - /* Gigabyte T1005 - defines wrong chassis type ("Other") */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "T1005"), - }, - }, - { - /* Gigabyte T1005M/P - defines wrong chassis type ("Other") */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "T1005M/P"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv9700"), - DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"), - DMI_MATCH(DMI_PRODUCT_NAME, "C15B"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"), - DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"), - }, - }, - { } -}; - -/* - * Some Fujitsu notebooks are having trouble with touchpads if - * active multiplexing mode is activated. Luckily they don't have - * external PS/2 ports so we can safely disable it. - * ... apparently some Toshibas don't like MUX mode either and - * die horrible death on reboot. - */ -static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { - { - /* Fujitsu Lifebook P7010/P7010D */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "P7010"), - }, - }, - { - /* Fujitsu Lifebook P7010 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "0000000000"), - }, - }, - { - /* Fujitsu Lifebook P5020D */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook P Series"), - }, - }, - { - /* Fujitsu Lifebook S2000 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S Series"), - }, - }, - { - /* Fujitsu Lifebook S6230 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S6230"), - }, - }, - { - /* Fujitsu Lifebook T725 laptop */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"), - }, - }, - { - /* Fujitsu Lifebook U745 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U745"), - }, - }, - { - /* Fujitsu T70H */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "FMVLT70H"), - }, - }, - { - /* Fujitsu-Siemens Lifebook T3010 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T3010"), - }, - }, - { - /* Fujitsu-Siemens Lifebook E4010 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E4010"), - }, - }, - { - /* Fujitsu-Siemens Amilo Pro 2010 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "AMILO Pro V2010"), - }, - }, - { - /* Fujitsu-Siemens Amilo Pro 2030 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), - DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"), - }, - }, - { - /* - * No data is coming from the touchscreen unless KBC - * is in legacy mode. - */ - /* Panasonic CF-29 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Matsushita"), - DMI_MATCH(DMI_PRODUCT_NAME, "CF-29"), - }, - }, - { - /* - * HP Pavilion DV4017EA - - * errors on MUX ports are reported without raising AUXDATA - * causing "spurious NAK" messages. - */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EA032EA#ABF)"), - }, - }, - { - /* - * HP Pavilion ZT1000 - - * like DV4017EA does not raise AUXERR for errors on MUX ports. - */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Notebook PC"), - DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook ZT1000"), - }, - }, - { - /* - * HP Pavilion DV4270ca - - * like DV4017EA does not raise AUXERR for errors on MUX ports. - */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EH476UA#ABL)"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "Satellite P10"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "EQUIUM A110"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE C850D"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ALIENWARE"), - DMI_MATCH(DMI_PRODUCT_NAME, "Sentia"), - }, - }, - { - /* Sharp Actius MM20 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SHARP"), - DMI_MATCH(DMI_PRODUCT_NAME, "PC-MM20 Series"), - }, - }, - { - /* Sony Vaio FS-115b */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FS115B"), - }, - }, - { - /* - * Sony Vaio FZ-240E - - * reset and GET ID commands issued via KBD port are - * sometimes being delivered to AUX3. - */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FZ240E"), - }, - }, - { - /* - * Most (all?) VAIOs do not have external PS/2 ports nor - * they implement active multiplexing properly, and - * MUX discovery usually messes up keyboard/touchpad. - */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), - DMI_MATCH(DMI_BOARD_NAME, "VAIO"), - }, - }, - { - /* Amoi M636/A737 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "M636/A737 platform"), - }, - }, - { - /* Lenovo 3000 n100 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "076804U"), - }, - }, - { - /* Lenovo XiaoXin Air 12 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "80UN"), + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc."), + DMI_MATCH(DMI_BOARD_NAME, "G1S"), + DMI_MATCH(DMI_BOARD_VERSION, "1.0"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 1360"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { /* Acer Aspire 5710 */ @@ -457,6 +177,7 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5710"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { /* Acer Aspire 7738 */ @@ -464,41 +185,7 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7738"), }, - }, - { - /* Gericom Bellagio */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Gericom"), - DMI_MATCH(DMI_PRODUCT_NAME, "N34AS6"), - }, - }, - { - /* IBM 2656 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "IBM"), - DMI_MATCH(DMI_PRODUCT_NAME, "2656"), - }, - }, - { - /* Dell XPS M1530 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "XPS M1530"), - }, - }, - { - /* Compal HEL80I */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "COMPAL"), - DMI_MATCH(DMI_PRODUCT_NAME, "HEL80I"), - }, - }, - { - /* Dell Vostro 1510 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro1510"), - }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { /* Acer Aspire 5536 */ @@ -507,48 +194,7 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5536"), DMI_MATCH(DMI_PRODUCT_VERSION, "0100"), }, - }, - { - /* Dell Vostro V13 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"), - }, - }, - { - /* Newer HP Pavilion dv4 models */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), - }, - }, - { - /* Asus X450LCP */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "X450LCP"), - }, - }, - { - /* Avatar AVIU-145A6 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Intel"), - DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"), - }, - }, - { - /* TUXEDO BU1406 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), - DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"), - }, - }, - { - /* Lenovo LaVie Z */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"), - }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { /* @@ -560,6 +206,253 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Acer Aspire One 150 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A114-31"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A314-31"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-31"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-132"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-332"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-432"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate Spin B118-RN"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + /* + * Some Wistron based laptops need us to explicitly enable the 'Dritek + * keyboard extension' to make their extra keys start generating scancodes. + * Originally, this was just confined to older laptops, but a few Acer laptops + * have turned up in 2007 that also need this again. + */ + { + /* Acer Aspire 5100 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5100"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Acer Aspire 5610 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5610"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Acer Aspire 5630 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5630"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Acer Aspire 5650 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5650"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Acer Aspire 5680 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5680"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Acer Aspire 5720 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5720"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Acer Aspire 9110 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 9110"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Acer TravelMate 660 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 660"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Acer TravelMate 2490 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 2490"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Acer TravelMate 4280 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 4280"), + }, + .driver_data = (void *)(SERIO_QUIRK_DRITEK) + }, + { + /* Amoi M636/A737 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "M636/A737 platform"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"), + DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Compal HEL80I */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "COMPAL"), + DMI_MATCH(DMI_PRODUCT_NAME, "HEL80I"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant"), + DMI_MATCH(DMI_PRODUCT_VERSION, "8500"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), + DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant"), + DMI_MATCH(DMI_PRODUCT_VERSION, "DL760"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Advent 4211 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "DIXONSXP"), + DMI_MATCH(DMI_PRODUCT_NAME, "Advent 4211"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* Dell Embedded Box PC 3000 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Embedded Box PC 3000"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Dell XPS M1530 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS M1530"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Dell Vostro 1510 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro1510"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Dell Vostro V13 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_NOTIMEOUT) + }, + { + /* Dell Vostro 1320 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1320"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* Dell Vostro 1520 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1520"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* Dell Vostro 1720 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1720"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) }, { /* Entroware Proteus */ @@ -568,11 +461,538 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"), DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS) + }, + /* + * Some Fujitsu notebooks are having trouble with touchpads if + * active multiplexing mode is activated. Luckily they don't have + * external PS/2 ports so we can safely disable it. + * ... apparently some Toshibas don't like MUX mode either and + * die horrible death on reboot. + */ + { + /* Fujitsu Lifebook P7010/P7010D */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "P7010"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu Lifebook P5020D */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook P Series"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu Lifebook S2000 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S Series"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu Lifebook S6230 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S6230"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu Lifebook T725 laptop */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_NOTIMEOUT) + }, + { + /* Fujitsu Lifebook U745 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U745"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu T70H */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "FMVLT70H"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu A544 laptop */ + /* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT) + }, + { + /* Fujitsu AH544 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT) + }, + { + /* Fujitsu U574 laptop */ + /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT) + }, + { + /* Fujitsu UH554 laptop */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK UH544"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOTIMEOUT) + }, + { + /* Fujitsu Lifebook P7010 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "0000000000"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu-Siemens Lifebook T3010 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T3010"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu-Siemens Lifebook E4010 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E4010"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu-Siemens Amilo Pro 2010 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "AMILO Pro V2010"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Fujitsu-Siemens Amilo Pro 2030 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Gigabyte M912 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "M912"), + DMI_MATCH(DMI_PRODUCT_VERSION, "01"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Gigabyte Spring Peak - defines wrong chassis type */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "Spring Peak"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Gigabyte T1005 - defines wrong chassis type ("Other") */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "T1005"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Gigabyte T1005M/P - defines wrong chassis type ("Other") */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "T1005M/P"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + /* + * Some laptops need keyboard reset before probing for the trackpad to get + * it detected, initialised & finally work. + */ + { + /* Gigabyte P35 v2 - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"), + }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) + }, + { + /* Aorus branded Gigabyte X3 Plus - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "X3"), + }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) + }, + { + /* Gigabyte P34 - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P34"), + }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) + }, + { + /* Gigabyte P57 - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), + DMI_MATCH(DMI_PRODUCT_NAME, "P57"), + }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) + }, + { + /* Gericom Bellagio */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Gericom"), + DMI_MATCH(DMI_PRODUCT_NAME, "N34AS6"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Gigabyte M1022M netbook */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co.,Ltd."), + DMI_MATCH(DMI_BOARD_NAME, "M1022E"), + DMI_MATCH(DMI_BOARD_VERSION, "1.02"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv9700"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Rev 1"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* + * HP Pavilion DV4017EA - + * errors on MUX ports are reported without raising AUXDATA + * causing "spurious NAK" messages. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EA032EA#ABF)"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* + * HP Pavilion ZT1000 - + * like DV4017EA does not raise AUXERR for errors on MUX ports. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Notebook PC"), + DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook ZT1000"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* + * HP Pavilion DV4270ca - + * like DV4017EA does not raise AUXERR for errors on MUX ports. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "Pavilion dv4000 (EH476UA#ABL)"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Newer HP Pavilion dv4 models */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_NOTIMEOUT) + }, + { + /* IBM 2656 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "IBM"), + DMI_MATCH(DMI_PRODUCT_NAME, "2656"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Avatar AVIU-145A6 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel"), + DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Intel MBO Desktop D845PESV */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "D845PESV"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOPNP) + }, + { + /* + * Intel NUC D54250WYK - does not have i8042 controller but + * declares PS/2 devices in DSDT. + */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "D54250WYK"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOPNP) + }, + { + /* Lenovo 3000 n100 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "076804U"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Lenovo XiaoXin Air 12 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "80UN"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Lenovo LaVie Z */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Lenovo Ideapad U455 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "20046"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* Lenovo ThinkPad L460 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L460"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* Lenovo ThinkPad Twist S230u */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* LG Electronics X110 */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LG Electronics Inc."), + DMI_MATCH(DMI_BOARD_NAME, "X110"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* Medion Akoya Mini E1210 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), + DMI_MATCH(DMI_PRODUCT_NAME, "E1210"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* Medion Akoya E1222 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), + DMI_MATCH(DMI_PRODUCT_NAME, "E122X"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* MSI Wind U-100 */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), + DMI_MATCH(DMI_BOARD_NAME, "U-100"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOPNP) + }, + { + /* + * No data is coming from the touchscreen unless KBC + * is in legacy mode. + */ + /* Panasonic CF-29 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Matsushita"), + DMI_MATCH(DMI_PRODUCT_NAME, "CF-29"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Medion Akoya E7225 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Medion"), + DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Microsoft Virtual Machine */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Virtual Machine"), + DMI_MATCH(DMI_PRODUCT_VERSION, "VS2005R2"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Medion MAM 2070 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), + DMI_MATCH(DMI_PRODUCT_NAME, "MAM 2070"), + DMI_MATCH(DMI_PRODUCT_VERSION, "5a"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* TUXEDO BU1406 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), + DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Clevo P650RS, 650RP6, Sager NP8152-S, and others */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), + DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"), + }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + { + /* OQO Model 01 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "OQO"), + DMI_MATCH(DMI_PRODUCT_NAME, "ZEPTO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "00"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"), + DMI_MATCH(DMI_PRODUCT_NAME, "C15B"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Acer Aspire 5 A515 */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "PK"), + DMI_MATCH(DMI_BOARD_NAME, "Grumpy_PK"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOPNP) + }, + { + /* ULI EV4873 - AUX LOOP does not work properly */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ULI"), + DMI_MATCH(DMI_PRODUCT_NAME, "EV4873"), + DMI_MATCH(DMI_PRODUCT_VERSION, "5a"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* + * Arima-Rioworks HDAMB - + * AUX LOOP command does not raise AUX IRQ + */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "RIOWORKS"), + DMI_MATCH(DMI_BOARD_NAME, "HDAMB"), + DMI_MATCH(DMI_BOARD_VERSION, "Rev E"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) + }, + { + /* Sharp Actius MM20 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SHARP"), + DMI_MATCH(DMI_PRODUCT_NAME, "PC-MM20 Series"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* + * Sony Vaio FZ-240E - + * reset and GET ID commands issued via KBD port are + * sometimes being delivered to AUX3. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FZ240E"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* + * Most (all?) VAIOs do not have external PS/2 ports nor + * they implement active multiplexing properly, and + * MUX discovery usually messes up keyboard/touchpad. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "VAIO"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, + { + /* Sony Vaio FS-115b */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FS115B"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, - { } -}; - -static const struct dmi_system_id i8042_dmi_forcemux_table[] __initconst = { { /* * Sony Vaio VGN-CS series require MUX or the touch sensor @@ -582,111 +1002,28 @@ static const struct dmi_system_id i8042_dmi_forcemux_table[] __initconst = { DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), DMI_MATCH(DMI_PRODUCT_NAME, "VGN-CS"), }, - }, - { } -}; - -/* - * On some Asus laptops, just running self tests cause problems. - */ -static const struct dmi_system_id i8042_dmi_noselftest_table[] = { - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */ - }, - }, { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /* Convertible Notebook */ - }, - }, - { } -}; -static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { - { - /* MSI Wind U-100 */ - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "U-100"), - DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), - }, - }, - { - /* LG Electronics X110 */ - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "X110"), - DMI_MATCH(DMI_BOARD_VENDOR, "LG Electronics Inc."), - }, - }, - { - /* Acer Aspire One 150 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"), - }, + .driver_data = (void *)(SERIO_QUIRK_FORCEMUX) }, { .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A114-31"), + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "Satellite P10"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A314-31"), + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "EQUIUM A110"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-31"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-132"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-332"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-432"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate Spin B118-RN"), - }, - }, - { - /* Advent 4211 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "DIXONSXP"), - DMI_MATCH(DMI_PRODUCT_NAME, "Advent 4211"), - }, - }, - { - /* Medion Akoya Mini E1210 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), - DMI_MATCH(DMI_PRODUCT_NAME, "E1210"), - }, - }, - { - /* Medion Akoya E1222 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), - DMI_MATCH(DMI_PRODUCT_NAME, "E122X"), + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE C850D"), }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { /* Mivvy M310 */ @@ -694,103 +1031,33 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "VIOOO"), DMI_MATCH(DMI_PRODUCT_NAME, "N10"), }, + .driver_data = (void *)(SERIO_QUIRK_RESET_ALWAYS) + }, + /* + * Some laptops need keyboard reset before probing for the trackpad to get + * it detected, initialised & finally work. + */ + { + /* Schenker XMG C504 - Elantech touchpad */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "XMG"), + DMI_MATCH(DMI_PRODUCT_NAME, "C504"), + }, + .driver_data = (void *)(SERIO_QUIRK_KBDRESET) }, { - /* Dell Vostro 1320 */ + /* Blue FB5601 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1320"), - }, - }, - { - /* Dell Vostro 1520 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1520"), - }, - }, - { - /* Dell Vostro 1720 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 1720"), - }, - }, - { - /* Lenovo Ideapad U455 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "20046"), - }, - }, - { - /* Lenovo ThinkPad L460 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L460"), - }, - }, - { - /* Clevo P650RS, 650RP6, Sager NP8152-S, and others */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), - DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"), - }, - }, - { - /* Lenovo ThinkPad Twist S230u */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"), - }, - }, - { - /* Entroware Proteus */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Entroware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"), - DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"), + DMI_MATCH(DMI_SYS_VENDOR, "blue"), + DMI_MATCH(DMI_PRODUCT_NAME, "FB5601"), + DMI_MATCH(DMI_PRODUCT_VERSION, "M606"), }, + .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, { } }; #ifdef CONFIG_PNP -static const struct dmi_system_id __initconst i8042_dmi_nopnp_table[] = { - { - /* Intel MBO Desktop D845PESV */ - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "D845PESV"), - DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), - }, - }, - { - /* - * Intel NUC D54250WYK - does not have i8042 controller but - * declares PS/2 devices in DSDT. - */ - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "D54250WYK"), - DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), - }, - }, - { - /* MSI Wind U-100 */ - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "U-100"), - DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), - }, - }, - { - /* Acer Aspire 5 A515 */ - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "Grumpy_PK"), - DMI_MATCH(DMI_BOARD_VENDOR, "PK"), - }, - }, - { } -}; - static const struct dmi_system_id i8042_dmi_laptop_table[] __initconst = { { .matches = { @@ -816,203 +1083,6 @@ static const struct dmi_system_id i8042_dmi_laptop_table[] __initconst = { }; #endif -static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = { - { - /* Dell Vostro V13 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"), - }, - }, - { - /* Newer HP Pavilion dv4 models */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"), - }, - }, - { - /* Fujitsu A544 laptop */ - /* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"), - }, - }, - { - /* Fujitsu AH544 laptop */ - /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"), - }, - }, - { - /* Fujitsu Lifebook T725 laptop */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK T725"), - }, - }, - { - /* Fujitsu U574 laptop */ - /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"), - }, - }, - { - /* Fujitsu UH554 laptop */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK UH544"), - }, - }, - { } -}; - -/* - * Some Wistron based laptops need us to explicitly enable the 'Dritek - * keyboard extension' to make their extra keys start generating scancodes. - * Originally, this was just confined to older laptops, but a few Acer laptops - * have turned up in 2007 that also need this again. - */ -static const struct dmi_system_id __initconst i8042_dmi_dritek_table[] = { - { - /* Acer Aspire 5100 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5100"), - }, - }, - { - /* Acer Aspire 5610 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5610"), - }, - }, - { - /* Acer Aspire 5630 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5630"), - }, - }, - { - /* Acer Aspire 5650 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5650"), - }, - }, - { - /* Acer Aspire 5680 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5680"), - }, - }, - { - /* Acer Aspire 5720 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5720"), - }, - }, - { - /* Acer Aspire 9110 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 9110"), - }, - }, - { - /* Acer TravelMate 660 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 660"), - }, - }, - { - /* Acer TravelMate 2490 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 2490"), - }, - }, - { - /* Acer TravelMate 4280 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 4280"), - }, - }, - { } -}; - -/* - * Some laptops need keyboard reset before probing for the trackpad to get - * it detected, initialised & finally work. - */ -static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = { - { - /* Gigabyte P35 v2 - Elantech touchpad */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"), - }, - }, - { - /* Aorus branded Gigabyte X3 Plus - Elantech touchpad */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "X3"), - }, - }, - { - /* Gigabyte P34 - Elantech touchpad */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "P34"), - }, - }, - { - /* Gigabyte P57 - Elantech touchpad */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), - DMI_MATCH(DMI_PRODUCT_NAME, "P57"), - }, - }, - { - /* Schenker XMG C504 - Elantech touchpad */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "XMG"), - DMI_MATCH(DMI_PRODUCT_NAME, "C504"), - }, - }, - { } -}; - -static const struct dmi_system_id i8042_dmi_probe_defer_table[] __initconst = { - { - /* ASUS ZenBook UX425UA */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"), - }, - }, - { - /* ASUS ZenBook UM325UA */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"), - }, - }, - { } -}; - #endif /* CONFIG_X86 */ #ifdef CONFIG_PNP @@ -1167,11 +1237,6 @@ static int __init i8042_pnp_init(void) bool pnp_data_busted = false; int err; -#ifdef CONFIG_X86 - if (dmi_check_system(i8042_dmi_nopnp_table)) - i8042_nopnp = true; -#endif - if (i8042_nopnp) { pr_info("PNP detection disabled\n"); return 0; @@ -1275,6 +1340,59 @@ static inline int i8042_pnp_init(void) { return 0; } static inline void i8042_pnp_exit(void) { } #endif /* CONFIG_PNP */ + +#ifdef CONFIG_X86 +static void __init i8042_check_quirks(void) +{ + const struct dmi_system_id *device_quirk_info; + uintptr_t quirks; + + device_quirk_info = dmi_first_match(i8042_dmi_quirk_table); + if (!device_quirk_info) + return; + + quirks = (uintptr_t)device_quirk_info->driver_data; + + if (quirks & SERIO_QUIRK_NOKBD) + i8042_nokbd = true; + if (quirks & SERIO_QUIRK_NOAUX) + i8042_noaux = true; + if (quirks & SERIO_QUIRK_NOMUX) + i8042_nomux = true; + if (quirks & SERIO_QUIRK_FORCEMUX) + i8042_nomux = false; + if (quirks & SERIO_QUIRK_UNLOCK) + i8042_unlock = true; + if (quirks & SERIO_QUIRK_PROBE_DEFER) + i8042_probe_defer = true; + /* Honor module parameter when value is not default */ + if (i8042_reset == I8042_RESET_DEFAULT) { + if (quirks & SERIO_QUIRK_RESET_ALWAYS) + i8042_reset = I8042_RESET_ALWAYS; + if (quirks & SERIO_QUIRK_RESET_NEVER) + i8042_reset = I8042_RESET_NEVER; + } + if (quirks & SERIO_QUIRK_DIECT) + i8042_direct = true; + if (quirks & SERIO_QUIRK_DUMBKBD) + i8042_dumbkbd = true; + if (quirks & SERIO_QUIRK_NOLOOP) + i8042_noloop = true; + if (quirks & SERIO_QUIRK_NOTIMEOUT) + i8042_notimeout = true; + if (quirks & SERIO_QUIRK_KBDRESET) + i8042_kbdreset = true; + if (quirks & SERIO_QUIRK_DRITEK) + i8042_dritek = true; +#ifdef CONFIG_PNP + if (quirks & SERIO_QUIRK_NOPNP) + i8042_nopnp = true; +#endif +} +#else +static inline void i8042_check_quirks(void) {} +#endif + static int __init i8042_platform_init(void) { int retval; @@ -1297,45 +1415,17 @@ static int __init i8042_platform_init(void) i8042_kbd_irq = I8042_MAP_IRQ(1); i8042_aux_irq = I8042_MAP_IRQ(12); +#if defined(__ia64__) + i8042_reset = I8042_RESET_ALWAYS; +#endif + + i8042_check_quirks(); + retval = i8042_pnp_init(); if (retval) return retval; -#if defined(__ia64__) - i8042_reset = I8042_RESET_ALWAYS; -#endif - #ifdef CONFIG_X86 - /* Honor module parameter when value is not default */ - if (i8042_reset == I8042_RESET_DEFAULT) { - if (dmi_check_system(i8042_dmi_reset_table)) - i8042_reset = I8042_RESET_ALWAYS; - - if (dmi_check_system(i8042_dmi_noselftest_table)) - i8042_reset = I8042_RESET_NEVER; - } - - if (dmi_check_system(i8042_dmi_noloop_table)) - i8042_noloop = true; - - if (dmi_check_system(i8042_dmi_nomux_table)) - i8042_nomux = true; - - if (dmi_check_system(i8042_dmi_forcemux_table)) - i8042_nomux = false; - - if (dmi_check_system(i8042_dmi_notimeout_table)) - i8042_notimeout = true; - - if (dmi_check_system(i8042_dmi_dritek_table)) - i8042_dritek = true; - - if (dmi_check_system(i8042_dmi_kbdreset_table)) - i8042_kbdreset = true; - - if (dmi_check_system(i8042_dmi_probe_defer_table)) - i8042_probe_defer = true; - /* * A20 was already enabled during early kernel init. But some buggy * BIOSes (in MSI Laptops) require A20 to be enabled using 8042 to From a82d49360496c489cddd6629a2865049208fa9bc Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Wed, 29 Jun 2022 17:38:52 -0700 Subject: [PATCH 1243/4345] Input: i8042 - add TUXEDO devices to i8042 quirk tables [ Upstream commit a6a87c36165e6791eeaed88025cde270536c3198 ] A lot of modern Clevo barebones have touchpad and/or keyboard issues after suspend fixable with nomux + reset + noloop + nopnp. Luckily, none of them have an external PS/2 port so this can safely be set for all of them. I'm not entirely sure if every device listed really needs all four quirks, but after testing and production use. No negative effects could be observed when setting all four. The list is quite massive as neither the TUXEDO nor the Clevo dmi strings have been very consistent historically. I tried to keep the list as short as possible without risking on missing an affected device. This is revision 3. The Clevo N150CU barebone is still removed as it might have problems with the fix and needs further investigations. The SchenkerTechnologiesGmbH System-/Board-Vendor string variations are added. This is now based in the quirk table refactor. This now also includes the additional noaux flag for the NS7xMU. Signed-off-by: Werner Sembach Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20220629112725.12922-5-wse@tuxedocomputers.com Signed-off-by: Dmitry Torokhov Stable-dep-of: 9c445d2637c9 ("Input: i8042 - add Clevo PCX0DX to i8042 quirk table") Signed-off-by: Sasha Levin --- drivers/input/serio/i8042-x86ia64io.h | 129 ++++++++++++++++++++++++++ 1 file changed, 129 insertions(+) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 1d2b34aac0c7..184d7c30f732 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -1025,6 +1025,29 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, + /* + * A lot of modern Clevo barebones have touchpad and/or keyboard issues + * after suspend fixable with nomux + reset + noloop + nopnp. Luckily, + * none of them have an external PS/2 port so this can safely be set for + * all of them. These two are based on a Clevo design, but have the + * board_name changed. + */ + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "AURA1501"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, { /* Mivvy M310 */ .matches = { @@ -1054,6 +1077,112 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, .driver_data = (void *)(SERIO_QUIRK_NOLOOP) }, + /* + * A lot of modern Clevo barebones have touchpad and/or keyboard issues + * after suspend fixable with nomux + reset + noloop + nopnp. Luckily, + * none of them have an external PS/2 port so this can safely be set for + * all of them. + * Clevo barebones come with board_vendor and/or system_vendor set to + * either the very generic string "Notebook" and/or a different value + * for each individual reseller. The only somewhat universal way to + * identify them is by board_name. + */ + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "LAPQC71A"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "LAPQC71B"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "N140CU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "N141CU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NH5xAx"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + /* + * At least one modern Clevo barebone has the touchpad connected both + * via PS/2 and i2c interface. This causes a race condition between the + * psmouse and i2c-hid driver. Since the full capability of the touchpad + * is available via the i2c interface and the device has no external + * PS/2 port, it is safe to just ignore all ps2 mouses here to avoid + * this issue. The known affected device is the + * TUXEDO InfinityBook S17 Gen6 / Clevo NS70MU which comes with one of + * the two different dmi strings below. NS50MU is not a typo! + */ + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NS50MU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX | + SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | + SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NS50_70MU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX | + SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | + SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PB50_70DFx,DDx"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "X170SM"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "X170KM-G"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, { } }; From 658e0d99dbfb39be4bbd1c1c6bff2b3eda3ee8e6 Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Tue, 10 Jan 2023 14:45:24 +0100 Subject: [PATCH 1244/4345] Input: i8042 - add Clevo PCX0DX to i8042 quirk table [ Upstream commit 9c445d2637c938a800fcc8b5f0b10e60c94460c7 ] The Clevo PCX0DX/TUXEDO XP1511, need quirks for the keyboard to not be occasionally unresponsive after resume. Signed-off-by: Werner Sembach Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede Reviewed-by: Mattijs Korpershoek Link: https://lore.kernel.org/r/20230110134524.553620-1-wse@tuxedocomputers.com Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/serio/i8042-x86ia64io.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 184d7c30f732..65c0081838e3 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -1169,6 +1169,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PCX0DX"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, { .matches = { DMI_MATCH(DMI_BOARD_NAME, "X170SM"), From 28d190882ba55cbcee1db8e4ae90c149178dcf64 Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Sun, 29 Jan 2023 16:17:40 +0100 Subject: [PATCH 1245/4345] fbcon: Check font dimension limits commit 2b09d5d364986f724f17001ccfe4126b9b43a0be upstream. blit_x and blit_y are u32, so fbcon currently cannot support fonts larger than 32x32. The 32x32 case also needs shifting an unsigned int, to properly set bit 31, otherwise we get "UBSAN: shift-out-of-bounds in fbcon_set_font", as reported on: http://lore.kernel.org/all/IA1PR07MB98308653E259A6F2CE94A4AFABCE9@IA1PR07MB9830.namprd07.prod.outlook.com Kernel Branch: 6.2.0-rc5-next-20230124 Kernel config: https://drive.google.com/file/d/1F-LszDAizEEH0ZX0HcSR06v5q8FPl2Uv/view?usp=sharing Reproducer: https://drive.google.com/file/d/1mP1jcLBY7vWCNM60OMf-ogw-urQRjNrm/view?usp=sharing Reported-by: Sanan Hasanov Signed-off-by: Samuel Thibault Fixes: 2d2699d98492 ("fbcon: font setting should check limitation of driver") Cc: stable@vger.kernel.org Tested-by: Miko Larsson Reviewed-by: Greg Kroah-Hartman Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/core/fbcon.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 27828435dd4f..6d58c8a5cb44 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2513,9 +2513,12 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, h > FBCON_SWAP(info->var.rotate, info->var.yres, info->var.xres)) return -EINVAL; + if (font->width > 32 || font->height > 32) + return -EINVAL; + /* Make sure drawing engine can handle the font */ - if (!(info->pixmap.blit_x & (1 << (font->width - 1))) || - !(info->pixmap.blit_y & (1 << (font->height - 1)))) + if (!(info->pixmap.blit_x & BIT(font->width - 1)) || + !(info->pixmap.blit_y & BIT(font->height - 1))) return -EINVAL; /* Make sure driver can handle the font length */ From 0c76eddc1f89c52e197f43a5827a51b36af38c36 Mon Sep 17 00:00:00 2001 From: Natalia Petrova Date: Wed, 25 Jan 2023 16:48:31 +0300 Subject: [PATCH 1246/4345] net: qrtr: free memory on error path in radix_tree_insert() commit 29de68c2b32ce58d64dea496d281e25ad0f551bd upstream. Function radix_tree_insert() returns errors if the node hasn't been initialized and added to the tree. "kfree(node)" and return value "NULL" of node_get() help to avoid using unclear node in other calls. Found by Linux Verification Center (linuxtesting.org) with SVACE. Cc: # 5.7 Fixes: 0c2204a4ad71 ("net: qrtr: Migrate nameservice to kernel from userspace") Signed-off-by: Natalia Petrova Reviewed-by: Simon Horman Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230125134831.8090-1-n.petrova@fintech.ru Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/qrtr/ns.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index e760d4a38faf..fe81e0385168 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -83,7 +83,10 @@ static struct qrtr_node *node_get(unsigned int node_id) node->id = node_id; - radix_tree_insert(&nodes, node_id, node); + if (radix_tree_insert(&nodes, node_id, node)) { + kfree(node); + return NULL; + } return node; } From 5bcdcf437d3f7ecd9103adc2b60af8f27c70301d Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Fri, 27 Jan 2023 14:52:41 +0100 Subject: [PATCH 1247/4345] watchdog: diag288_wdt: do not use stack buffers for hardware data commit fe8973a3ad0905cb9ba2d42db42ed51de14737df upstream. With CONFIG_VMAP_STACK=y the stack is allocated from the vmalloc space. Data passed to a hardware or a hypervisor interface that requires V=R can no longer be allocated on the stack. Use kmalloc() to get memory for a diag288 command. Signed-off-by: Alexander Egorenkov Reviewed-by: Heiko Carstens Cc: Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- drivers/watchdog/diag288_wdt.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/diag288_wdt.c b/drivers/watchdog/diag288_wdt.c index aafc8d98bf9f..f0b6d5eeee1b 100644 --- a/drivers/watchdog/diag288_wdt.c +++ b/drivers/watchdog/diag288_wdt.c @@ -272,12 +272,21 @@ static int __init diag288_init(void) char ebc_begin[] = { 194, 197, 199, 201, 213 }; + char *ebc_cmd; watchdog_set_nowayout(&wdt_dev, nowayout_info); if (MACHINE_IS_VM) { - if (__diag288_vm(WDT_FUNC_INIT, 15, - ebc_begin, sizeof(ebc_begin)) != 0) { + ebc_cmd = kmalloc(sizeof(ebc_begin), GFP_KERNEL); + if (!ebc_cmd) { + pr_err("The watchdog cannot be initialized\n"); + return -ENOMEM; + } + memcpy(ebc_cmd, ebc_begin, sizeof(ebc_begin)); + ret = __diag288_vm(WDT_FUNC_INIT, 15, + ebc_cmd, sizeof(ebc_begin)); + kfree(ebc_cmd); + if (ret != 0) { pr_err("The watchdog cannot be initialized\n"); return -EINVAL; } From 192fd121d04f79ce9ac7d53dd44189f010133d0f Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Fri, 27 Jan 2023 14:52:42 +0100 Subject: [PATCH 1248/4345] watchdog: diag288_wdt: fix __diag288() inline assembly commit 32e40f9506b9e32917eb73154f93037b443124d1 upstream. The DIAG 288 statement consumes an EBCDIC string the address of which is passed in a register. Use a "memory" clobber to tell the compiler that memory is accessed within the inline assembly. Signed-off-by: Alexander Egorenkov Reviewed-by: Heiko Carstens Cc: Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- drivers/watchdog/diag288_wdt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/watchdog/diag288_wdt.c b/drivers/watchdog/diag288_wdt.c index f0b6d5eeee1b..370f648cb4b1 100644 --- a/drivers/watchdog/diag288_wdt.c +++ b/drivers/watchdog/diag288_wdt.c @@ -86,7 +86,7 @@ static int __diag288(unsigned int func, unsigned int timeout, "1:\n" EX_TABLE(0b, 1b) : "+d" (err) : "d"(__func), "d"(__timeout), - "d"(__action), "d"(__len) : "1", "cc"); + "d"(__action), "d"(__len) : "1", "cc", "memory"); return err; } From 8fb515c8b127c852bbbc23738e27c7a08e79b9fd Mon Sep 17 00:00:00 2001 From: Victor Shyba Date: Mon, 23 Jan 2023 19:21:29 -0300 Subject: [PATCH 1249/4345] ALSA: hda/realtek: Add Acer Predator PH315-54 commit 6a28a25d358079b7d0d144689f850aecacf63cba upstream. Same issue as SP513-54N: Headset microphone does not work without ALC255_FIXUP_ACER_MIC_NO_PRESENCE fixup. BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=211853 Cc: Signed-off-by: Victor Shyba Link: https://lore.kernel.org/r/20230123222129.17589-1-victor1984@riseup.net Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index cfd86389d37f..ae9ab6d2ae76 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8811,6 +8811,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x142b, "Acer Swift SF314-42", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), + SND_PCI_QUIRK(0x1025, 0x1534, "Acer Predator PH315-54", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x053c, "Dell Latitude E5430", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS), From 55cf65461b2090ee541e77664080c05cd2a03bbd Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 2 Feb 2023 18:30:06 +0100 Subject: [PATCH 1250/4345] efi: Accept version 2 of memory attributes table commit 636ab417a7aec4ee993916e688eb5c5977570836 upstream. UEFI v2.10 introduces version 2 of the memory attributes table, which turns the reserved field into a flags field, but is compatible with version 1 in all other respects. So let's not complain about version 2 if we encounter it. Cc: Signed-off-by: Ard Biesheuvel Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/efi/memattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c index 0a9aba5f9cef..f178b2984dfb 100644 --- a/drivers/firmware/efi/memattr.c +++ b/drivers/firmware/efi/memattr.c @@ -33,7 +33,7 @@ int __init efi_memattr_init(void) return -ENOMEM; } - if (tbl->version > 1) { + if (tbl->version > 2) { pr_warn("Unexpected EFI Memory Attributes table version %d\n", tbl->version); goto unmap; From 33483172b35c984537415b9cb29fe2eb8032fe46 Mon Sep 17 00:00:00 2001 From: Dmitry Perchanov Date: Wed, 11 Jan 2023 14:22:10 +0200 Subject: [PATCH 1251/4345] iio: hid: fix the retval in accel_3d_capture_sample commit f7b23d1c35d8b8de1425bdfccaefd01f3b7c9d1c upstream. Return value should be zero for success. This was forgotten for timestamp feature. Verified on RealSense cameras. Fixes: a96cd0f901ee ("iio: accel: hid-sensor-accel-3d: Add timestamp") Signed-off-by: Dmitry Perchanov Link: https://lore.kernel.org/r/a6dc426498221c81fa71045b41adf782ebd42136.camel@intel.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/accel/hid-sensor-accel-3d.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c index f05840d17fb7..8d929a4f9110 100644 --- a/drivers/iio/accel/hid-sensor-accel-3d.c +++ b/drivers/iio/accel/hid-sensor-accel-3d.c @@ -277,6 +277,7 @@ static int accel_3d_capture_sample(struct hid_sensor_hub_device *hsdev, hid_sensor_convert_timestamp( &accel_state->common_attributes, *(int64_t *)raw_data); + ret = 0; break; default: break; From 5602f6a244ab8c80d3c1b860cb5ba056b118d445 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Tue, 29 Nov 2022 10:03:16 +0800 Subject: [PATCH 1252/4345] iio: adc: berlin2-adc: Add missing of_node_put() in error path commit cbd3a0153cd18a2cbef6bf3cf31bb406c3fc9f55 upstream. of_get_parent() will return a device_node pointer with refcount incremented. We need to use of_node_put() on it when done. Add the missing of_node_put() in the error path of berlin2_adc_probe(); Fixes: 70f1937911ca ("iio: adc: add support for Berlin") Signed-off-by: Xiongfeng Wang Link: https://lore.kernel.org/r/20221129020316.191731-1-wangxiongfeng2@huawei.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/berlin2-adc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iio/adc/berlin2-adc.c b/drivers/iio/adc/berlin2-adc.c index 8b04b95b7b7a..fa2c87946e16 100644 --- a/drivers/iio/adc/berlin2-adc.c +++ b/drivers/iio/adc/berlin2-adc.c @@ -289,8 +289,10 @@ static int berlin2_adc_probe(struct platform_device *pdev) int ret; indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*priv)); - if (!indio_dev) + if (!indio_dev) { + of_node_put(parent_np); return -ENOMEM; + } priv = iio_priv(indio_dev); platform_set_drvdata(pdev, indio_dev); From 11ac43f7631e45a75d0e764b0659469c351cd8ff Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Thu, 1 Dec 2022 19:16:35 +0100 Subject: [PATCH 1253/4345] iio:adc:twl6030: Enable measurements of VUSB, VBAT and others commit f804bd0dc28683a93a60f271aaefb2fc5b0853dd upstream. Some inputs need to be wired up to produce proper measurements, without this change only near zero values are reported. Signed-off-by: Andreas Kemnade Fixes: 1696f36482e70 ("iio: twl6030-gpadc: TWL6030, TWL6032 GPADC driver") Link: https://lore.kernel.org/r/20221201181635.3522962-1-andreas@kemnade.info Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/twl6030-gpadc.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/drivers/iio/adc/twl6030-gpadc.c b/drivers/iio/adc/twl6030-gpadc.c index 256177b15c51..9ab23b29bee3 100644 --- a/drivers/iio/adc/twl6030-gpadc.c +++ b/drivers/iio/adc/twl6030-gpadc.c @@ -57,6 +57,18 @@ #define TWL6030_GPADCS BIT(1) #define TWL6030_GPADCR BIT(0) +#define USB_VBUS_CTRL_SET 0x04 +#define USB_ID_CTRL_SET 0x06 + +#define TWL6030_MISC1 0xE4 +#define VBUS_MEAS 0x01 +#define ID_MEAS 0x01 + +#define VAC_MEAS 0x04 +#define VBAT_MEAS 0x02 +#define BB_MEAS 0x01 + + /** * struct twl6030_chnl_calib - channel calibration * @gain: slope coefficient for ideal curve @@ -927,6 +939,26 @@ static int twl6030_gpadc_probe(struct platform_device *pdev) return ret; } + ret = twl_i2c_write_u8(TWL_MODULE_USB, VBUS_MEAS, USB_VBUS_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL_MODULE_USB, ID_MEAS, USB_ID_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL6030_MODULE_ID0, + VBAT_MEAS | BB_MEAS | BB_MEAS, + TWL6030_MISC1); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + indio_dev->name = DRIVER_NAME; indio_dev->info = &twl6030_gpadc_iio_info; indio_dev->modes = INDIO_DIRECT_MODE; From f7d996c953bffe82d3360f17b52220a1596d1b25 Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Thu, 8 Dec 2022 15:19:09 +0800 Subject: [PATCH 1254/4345] iio: imu: fxos8700: fix ACCEL measurement range selection commit 9d61c1820598a5ea474576ed55318a6dadee37ed upstream. When device is in active mode, it fails to set an ACCEL full-scale range(2g/4g/8g) in FXOS8700_XYZ_DATA_CFG. This is not align with the datasheet, but it is a fxos8700 chip behavior. Keep the device in standby mode before setting ACCEL full-scale range into FXOS8700_XYZ_DATA_CFG in chip initialization phase and setting scale phase. Fixes: 84e5ddd5c46e ("iio: imu: Add support for the FXOS8700 IMU") Signed-off-by: Carlos Song Link: https://lore.kernel.org/r/20221208071911.2405922-6-carlos.song@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/fxos8700_core.c | 41 +++++++++++++++++++++++++++------ 1 file changed, 34 insertions(+), 7 deletions(-) diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index ab288186f36e..1d07de88e240 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -345,7 +345,8 @@ static int fxos8700_set_active_mode(struct fxos8700_data *data, static int fxos8700_set_scale(struct fxos8700_data *data, enum fxos8700_sensor t, int uscale) { - int i; + int i, ret, val; + bool active_mode; static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale); struct device *dev = regmap_get_device(data->regmap); @@ -354,6 +355,25 @@ static int fxos8700_set_scale(struct fxos8700_data *data, return -EINVAL; } + /* + * When device is in active mode, it failed to set an ACCEL + * full-scale range(2g/4g/8g) in FXOS8700_XYZ_DATA_CFG. + * This is not align with the datasheet, but it is a fxos8700 + * chip behavier. Set the device in standby mode before setting + * an ACCEL full-scale range. + */ + ret = regmap_read(data->regmap, FXOS8700_CTRL_REG1, &val); + if (ret) + return ret; + + active_mode = val & FXOS8700_ACTIVE; + if (active_mode) { + ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1, + val & ~FXOS8700_ACTIVE); + if (ret) + return ret; + } + for (i = 0; i < scale_num; i++) if (fxos8700_accel_scale[i].uscale == uscale) break; @@ -361,8 +381,12 @@ static int fxos8700_set_scale(struct fxos8700_data *data, if (i == scale_num) return -EINVAL; - return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, + ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, fxos8700_accel_scale[i].bits); + if (ret) + return ret; + return regmap_write(data->regmap, FXOS8700_CTRL_REG1, + active_mode); } static int fxos8700_get_scale(struct fxos8700_data *data, @@ -592,14 +616,17 @@ static int fxos8700_chip_init(struct fxos8700_data *data, bool use_spi) if (ret) return ret; - /* Max ODR (800Hz individual or 400Hz hybrid), active mode */ - ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1, - FXOS8700_CTRL_ODR_MAX | FXOS8700_ACTIVE); + /* + * Set max full-scale range (+/-8G) for ACCEL sensor in chip + * initialization then activate the device. + */ + ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G); if (ret) return ret; - /* Set for max full-scale range (+/-8G) */ - return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G); + /* Max ODR (800Hz individual or 400Hz hybrid), active mode */ + return regmap_write(data->regmap, FXOS8700_CTRL_REG1, + FXOS8700_CTRL_ODR_MAX | FXOS8700_ACTIVE); } static void fxos8700_chip_uninit(void *data) From 6d43eddc567bfe424b37bd1bf59ef72c10146168 Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Thu, 8 Dec 2022 15:19:07 +0800 Subject: [PATCH 1255/4345] iio: imu: fxos8700: fix incomplete ACCEL and MAGN channels readback commit 37a94d86d7050665d6d01378b2c916c28e454f10 upstream. The length of ACCEL and MAGN 3-axis channels output data is 6 byte individually. However block only read 3 bytes data into buffer from ACCEL or MAGN output data registers every time. It causes an incomplete ACCEL and MAGN channels readback. Set correct value count for regmap_bulk_read to get 6 bytes ACCEL and MAGN channels readback. Fixes: 84e5ddd5c46e ("iio: imu: Add support for the FXOS8700 IMU") Signed-off-by: Carlos Song Link: https://lore.kernel.org/r/20221208071911.2405922-4-carlos.song@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/fxos8700_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 1d07de88e240..9c8e0d6ec87e 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -425,7 +425,7 @@ static int fxos8700_get_data(struct fxos8700_data *data, int chan_type, /* Block read 6 bytes of device output registers to avoid data loss */ ret = regmap_bulk_read(data->regmap, base, data->buf, - FXOS8700_DATA_BUF_SIZE); + sizeof(data->buf)); if (ret) return ret; From 9545ce720ab1998d657bf0be870a0ac8e444d86e Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Thu, 8 Dec 2022 15:19:08 +0800 Subject: [PATCH 1256/4345] iio: imu: fxos8700: fix IMU data bits returned to user space commit a53f945879c0cb9de3a4c05a665f5157884b5208 upstream. ACCEL output data registers contain the X-axis, Y-axis, and Z-axis 14-bit left-justified sample data and MAGN output data registers contain the X-axis, Y-axis, and Z-axis 16-bit sample data. The ACCEL raw register output data should be divided by 4 before sent to userspace. Apply a 2 bits signed right shift to the raw data from ACCEL output data register but keep that from MAGN sensor as the origin. Fixes: 84e5ddd5c46e ("iio: imu: Add support for the FXOS8700 IMU") Signed-off-by: Carlos Song Link: https://lore.kernel.org/r/20221208071911.2405922-5-carlos.song@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/fxos8700_core.c | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 9c8e0d6ec87e..07d6c6bdd255 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -418,6 +418,7 @@ static int fxos8700_get_data(struct fxos8700_data *data, int chan_type, int axis, int *val) { u8 base, reg; + s16 tmp; int ret; enum fxos8700_sensor type = fxos8700_to_sensor(chan_type); @@ -432,8 +433,33 @@ static int fxos8700_get_data(struct fxos8700_data *data, int chan_type, /* Convert axis to buffer index */ reg = axis - IIO_MOD_X; + /* + * Convert to native endianness. The accel data and magn data + * are signed, so a forced type conversion is needed. + */ + tmp = be16_to_cpu(data->buf[reg]); + + /* + * ACCEL output data registers contain the X-axis, Y-axis, and Z-axis + * 14-bit left-justified sample data and MAGN output data registers + * contain the X-axis, Y-axis, and Z-axis 16-bit sample data. Apply + * a signed 2 bits right shift to the readback raw data from ACCEL + * output data register and keep that from MAGN sensor as the origin. + * Value should be extended to 32 bit. + */ + switch (chan_type) { + case IIO_ACCEL: + tmp = tmp >> 2; + break; + case IIO_MAGN: + /* Nothing to do */ + break; + default: + return -EINVAL; + } + /* Convert to native endianness */ - *val = sign_extend32(be16_to_cpu(data->buf[reg]), 15); + *val = sign_extend32(tmp, 15); return 0; } From aff4add609988bb047f39a34f87f2a586f0b4257 Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Thu, 8 Dec 2022 15:19:05 +0800 Subject: [PATCH 1257/4345] iio: imu: fxos8700: fix map label of channel type to MAGN sensor commit 429e1e8ec696e0e7a0742904e3dc2f83b7b23dfb upstream. FXOS8700 is an IMU sensor with ACCEL sensor and MAGN sensor. Sensor type is indexed by corresponding channel type in a switch. IIO_ANGL_VEL channel type mapped to MAGN sensor has caused confusion. Fix the mapping label of "IIO_MAGN" channel type instead of "IIO_ANGL_VEL" channel type to MAGN sensor. Fixes: 84e5ddd5c46e ("iio: imu: Add support for the FXOS8700 IMU") Signed-off-by: Carlos Song Link: https://lore.kernel.org/r/20221208071911.2405922-2-carlos.song@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/fxos8700_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 07d6c6bdd255..7a53d74e21d9 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -320,7 +320,7 @@ static enum fxos8700_sensor fxos8700_to_sensor(enum iio_chan_type iio_type) switch (iio_type) { case IIO_ACCEL: return FXOS8700_ACCEL; - case IIO_ANGL_VEL: + case IIO_MAGN: return FXOS8700_MAGN; default: return -EINVAL; From 9d6502ed6314fd62ba7df569df7ee1f682ccda9e Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Thu, 8 Dec 2022 15:19:06 +0800 Subject: [PATCH 1258/4345] iio: imu: fxos8700: fix swapped ACCEL and MAGN channels readback commit c68b44bc7d9b1469774a1c985ee71d2cbc5ebef5 upstream. Because ACCEL and MAGN channels data register base address is swapped the accelerometer and magnetometer channels readback is swapped. Fixes: 84e5ddd5c46e ("iio: imu: Add support for the FXOS8700 IMU") Signed-off-by: Carlos Song Link: https://lore.kernel.org/r/20221208071911.2405922-3-carlos.song@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/fxos8700_core.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 7a53d74e21d9..9e87a0fe0132 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -420,9 +420,22 @@ static int fxos8700_get_data(struct fxos8700_data *data, int chan_type, u8 base, reg; s16 tmp; int ret; - enum fxos8700_sensor type = fxos8700_to_sensor(chan_type); - base = type ? FXOS8700_OUT_X_MSB : FXOS8700_M_OUT_X_MSB; + /* + * Different register base addresses varies with channel types. + * This bug hasn't been noticed before because using an enum is + * really hard to read. Use an a switch statement to take over that. + */ + switch (chan_type) { + case IIO_ACCEL: + base = FXOS8700_OUT_X_MSB; + break; + case IIO_MAGN: + base = FXOS8700_M_OUT_X_MSB; + break; + default: + return -EINVAL; + } /* Block read 6 bytes of device output registers to avoid data loss */ ret = regmap_bulk_read(data->regmap, base, data->buf, From ab976ecd0430fd5c3072f4f99470ae845cb95715 Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Wed, 18 Jan 2023 15:42:24 +0800 Subject: [PATCH 1259/4345] iio: imu: fxos8700: fix incorrect ODR mode readback commit 78ad6864e9e012cdba7c353d044d21ffcfd5f34b upstream. The absence of a correct offset leads an incorrect ODR mode readback after use a hexadecimal number to mark the value from FXOS8700_CTRL_REG1. Get ODR mode by field mask and FIELD_GET clearly and conveniently. And attach other additional fix for keeping the original code logic and a good readability. Fixes: 84e5ddd5c46e ("iio: imu: Add support for the FXOS8700 IMU") Signed-off-by: Carlos Song Link: https://lore.kernel.org/r/20230118074227.1665098-2-carlos.song@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/fxos8700_core.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 9e87a0fe0132..bb65ef349280 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -144,9 +145,9 @@ #define FXOS8700_NVM_DATA_BNK0 0xa7 /* Bit definitions for FXOS8700_CTRL_REG1 */ -#define FXOS8700_CTRL_ODR_MSK 0x38 #define FXOS8700_CTRL_ODR_MAX 0x00 #define FXOS8700_CTRL_ODR_MIN GENMASK(4, 3) +#define FXOS8700_CTRL_ODR_MSK GENMASK(5, 3) /* Bit definitions for FXOS8700_M_CTRL_REG1 */ #define FXOS8700_HMS_MASK GENMASK(1, 0) @@ -508,10 +509,9 @@ static int fxos8700_set_odr(struct fxos8700_data *data, enum fxos8700_sensor t, if (i >= odr_num) return -EINVAL; - return regmap_update_bits(data->regmap, - FXOS8700_CTRL_REG1, - FXOS8700_CTRL_ODR_MSK + FXOS8700_ACTIVE, - fxos8700_odr[i].bits << 3 | active_mode); + val &= ~FXOS8700_CTRL_ODR_MSK; + val |= FIELD_PREP(FXOS8700_CTRL_ODR_MSK, fxos8700_odr[i].bits) | FXOS8700_ACTIVE; + return regmap_write(data->regmap, FXOS8700_CTRL_REG1, val); } static int fxos8700_get_odr(struct fxos8700_data *data, enum fxos8700_sensor t, @@ -524,7 +524,7 @@ static int fxos8700_get_odr(struct fxos8700_data *data, enum fxos8700_sensor t, if (ret) return ret; - val &= FXOS8700_CTRL_ODR_MSK; + val = FIELD_GET(FXOS8700_CTRL_ODR_MSK, val); for (i = 0; i < odr_num; i++) if (val == fxos8700_odr[i].bits) From 42e34a08394a4fa469bbfccdf590b515bf45c03f Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Wed, 18 Jan 2023 15:42:25 +0800 Subject: [PATCH 1260/4345] iio: imu: fxos8700: fix failed initialization ODR mode assignment commit eb6d8f8705bc19141bac81d8161461f9e256948a upstream. The absence of correct offset leads a failed initialization ODR mode assignment. Select MAX ODR mode as the initialization ODR mode by field mask and FIELD_PREP. Fixes: 84e5ddd5c46e ("iio: imu: Add support for the FXOS8700 IMU") Signed-off-by: Carlos Song Link: https://lore.kernel.org/r/20230118074227.1665098-3-carlos.song@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/fxos8700_core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index bb65ef349280..2bee9a7f859d 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -664,8 +664,10 @@ static int fxos8700_chip_init(struct fxos8700_data *data, bool use_spi) return ret; /* Max ODR (800Hz individual or 400Hz hybrid), active mode */ - return regmap_write(data->regmap, FXOS8700_CTRL_REG1, - FXOS8700_CTRL_ODR_MAX | FXOS8700_ACTIVE); + return regmap_update_bits(data->regmap, FXOS8700_CTRL_REG1, + FXOS8700_CTRL_ODR_MSK | FXOS8700_ACTIVE, + FIELD_PREP(FXOS8700_CTRL_ODR_MSK, FXOS8700_CTRL_ODR_MAX) | + FXOS8700_ACTIVE); } static void fxos8700_chip_uninit(void *data) From 5b30998c7f05a07fc64ddc78180009bfddf4c040 Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Wed, 18 Jan 2023 15:42:26 +0800 Subject: [PATCH 1261/4345] iio: imu: fxos8700: remove definition FXOS8700_CTRL_ODR_MIN commit ff5e2cd92ffda9a25ffa2cbdb3a0cf17650172a6 upstream. FXOS8700_CTRL_ODR_MIN is not used but value is probably wrong. Remove it for a good readability. Fixes: 84e5ddd5c46e ("iio: imu: Add support for the FXOS8700 IMU") Signed-off-by: Carlos Song Link: https://lore.kernel.org/r/20230118074227.1665098-4-carlos.song@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/fxos8700_core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 2bee9a7f859d..041042d671dc 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -146,7 +146,6 @@ /* Bit definitions for FXOS8700_CTRL_REG1 */ #define FXOS8700_CTRL_ODR_MAX 0x00 -#define FXOS8700_CTRL_ODR_MIN GENMASK(4, 3) #define FXOS8700_CTRL_ODR_MSK GENMASK(5, 3) /* Bit definitions for FXOS8700_M_CTRL_REG1 */ From f11330b7ba51613d0a660ee1cde35abb9cef6abb Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Wed, 18 Jan 2023 15:42:27 +0800 Subject: [PATCH 1262/4345] iio: imu: fxos8700: fix MAGN sensor scale and unit commit 2acd031347f645871959a799238a7caf6803aa18 upstream. +/-1200uT is a MAGN sensor full measurement range. Magnetometer scale is the magnetic sensitivity parameter. It is referenced as 0.1uT according to datasheet and magnetometer channel unit is Gauss in sysfs-bus-iio documentation. Gauss and uTesla unit conversion relationship as follows: 0.1uT = 0.001Gs. Set magnetometer scale and available magnetometer scale as fixed 0.001Gs. Fixes: 84e5ddd5c46e ("iio: imu: Add support for the FXOS8700 IMU") Signed-off-by: Carlos Song Link: https://lore.kernel.org/r/20230118074227.1665098-5-carlos.song@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/fxos8700_core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 041042d671dc..04d3778fcc15 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -351,7 +351,7 @@ static int fxos8700_set_scale(struct fxos8700_data *data, struct device *dev = regmap_get_device(data->regmap); if (t == FXOS8700_MAGN) { - dev_err(dev, "Magnetometer scale is locked at 1200uT\n"); + dev_err(dev, "Magnetometer scale is locked at 0.001Gs\n"); return -EINVAL; } @@ -396,7 +396,7 @@ static int fxos8700_get_scale(struct fxos8700_data *data, static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale); if (t == FXOS8700_MAGN) { - *uscale = 1200; /* Magnetometer is locked at 1200uT */ + *uscale = 1000; /* Magnetometer is locked at 0.001Gs */ return 0; } @@ -588,7 +588,7 @@ static IIO_CONST_ATTR(in_accel_sampling_frequency_available, static IIO_CONST_ATTR(in_magn_sampling_frequency_available, "1.5625 6.25 12.5 50 100 200 400 800"); static IIO_CONST_ATTR(in_accel_scale_available, "0.000244 0.000488 0.000976"); -static IIO_CONST_ATTR(in_magn_scale_available, "0.000001200"); +static IIO_CONST_ATTR(in_magn_scale_available, "0.001000"); static struct attribute *fxos8700_attrs[] = { &iio_const_attr_in_accel_sampling_frequency_available.dev_attr.attr, From 170e1cc3c00fae434c40edd5535d2665c7afeb11 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 27 Jan 2023 10:40:15 +0000 Subject: [PATCH 1263/4345] nvmem: qcom-spmi-sdam: fix module autoloading commit 1ca7fca349316231bbaa68d16f819a08d683c5a7 upstream. Add the missing module device table so that the driver can be autoloaded when built as a module. Fixes: 40ce9798794f ("nvmem: add QTI SDAM driver") Cc: stable@vger.kernel.org # 5.6 Reviewed-by: Bjorn Andersson Signed-off-by: Johan Hovold Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230127104015.23839-11-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/qcom-spmi-sdam.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c index f6e9f96933ca..1549bfcc4c2d 100644 --- a/drivers/nvmem/qcom-spmi-sdam.c +++ b/drivers/nvmem/qcom-spmi-sdam.c @@ -166,6 +166,7 @@ static const struct of_device_id sdam_match_table[] = { { .compatible = "qcom,spmi-sdam" }, {}, }; +MODULE_DEVICE_TABLE(of, sdam_match_table); static struct platform_driver sdam_driver = { .driver = { From 2982b473d764b4d02a40c84246a2d576d411427d Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Mon, 19 Dec 2022 20:56:36 +0100 Subject: [PATCH 1264/4345] parisc: Fix return code of pdc_iodc_print() commit 5d1335dabb3c493a3d6d5b233953b6ac7b6c1ff2 upstream. There is an off-by-one if the printed string includes a new-line char. Cc: stable@vger.kernel.org Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/firmware.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 665b70086685..7ed28ddcaba7 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1230,7 +1230,7 @@ static char __attribute__((aligned(64))) iodc_dbuf[4096]; */ int pdc_iodc_print(const unsigned char *str, unsigned count) { - unsigned int i; + unsigned int i, found = 0; unsigned long flags; for (i = 0; i < count;) { @@ -1239,6 +1239,7 @@ int pdc_iodc_print(const unsigned char *str, unsigned count) iodc_dbuf[i+0] = '\r'; iodc_dbuf[i+1] = '\n'; i += 2; + found = 1; goto print; default: iodc_dbuf[i] = str[i]; @@ -1255,7 +1256,7 @@ print: __pa(iodc_retbuf), 0, __pa(iodc_dbuf), i, 0); spin_unlock_irqrestore(&pdc_lock, flags); - return i; + return i - found; } #if !defined(BOOTLOADER) From 71a4f39f99e85cf6bb140af6322a4364e81cf1f6 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 1 Feb 2023 16:41:54 +0100 Subject: [PATCH 1265/4345] parisc: Wire up PTRACE_GETREGS/PTRACE_SETREGS for compat case commit 316f1f42b5cc1d95124c1f0387c867c1ba7b6d0e upstream. Wire up the missing ptrace requests PTRACE_GETREGS, PTRACE_SETREGS, PTRACE_GETFPREGS and PTRACE_SETFPREGS when running 32-bit applications on 64-bit kernels. Signed-off-by: Helge Deller Cc: stable@vger.kernel.org # 4.7+ Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/ptrace.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 2127974982df..df9b9f0591bf 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -127,6 +127,12 @@ long arch_ptrace(struct task_struct *child, long request, unsigned long tmp; long ret = -EIO; + unsigned long user_regs_struct_size = sizeof(struct user_regs_struct); +#ifdef CONFIG_64BIT + if (is_compat_task()) + user_regs_struct_size /= 2; +#endif + switch (request) { /* Read the word at location addr in the USER area. For ptraced @@ -182,14 +188,14 @@ long arch_ptrace(struct task_struct *child, long request, return copy_regset_to_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ @@ -303,6 +309,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, } } break; + case PTRACE_GETREGS: + case PTRACE_SETREGS: + case PTRACE_GETFPREGS: + case PTRACE_SETFPREGS: + return arch_ptrace(child, request, addr, data); default: ret = compat_ptrace_request(child, request, addr, data); From 50d31309c999fba1879e2581abc313eabbed744b Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Wed, 1 Feb 2023 10:29:45 +0100 Subject: [PATCH 1266/4345] riscv: disable generation of unwind tables commit 2f394c0e7d1129a35156e492bc8f445fb20f43ac upstream. GCC 13 will enable -fasynchronous-unwind-tables by default on riscv. In the kernel, we don't have any use for unwind tables yet, so disable them. More importantly, the .eh_frame section brings relocations (R_RISC_32_PCREL, R_RISCV_SET{6,8,16}, R_RISCV_SUB{6,8,16}) into modules that we are not prepared to handle. Signed-off-by: Andreas Schwab Link: https://lore.kernel.org/r/mvmzg9xybqu.fsf@suse.de Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/Makefile | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 1bb1bf1141cc..9446282b52ba 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -74,6 +74,9 @@ ifeq ($(CONFIG_PERF_EVENTS),y) KBUILD_CFLAGS += -fno-omit-frame-pointer endif +# Avoid generating .eh_frame sections. +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables + KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) From 556959327b190a4efcfccc4ed311a08f6ea520ed Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Thu, 26 Jan 2023 14:27:20 -0800 Subject: [PATCH 1267/4345] mm: hugetlb: proc: check for hugetlb shared PMD in /proc/PID/smaps commit 3489dbb696d25602aea8c3e669a6d43b76bd5358 upstream. Patch series "Fixes for hugetlb mapcount at most 1 for shared PMDs". This issue of mapcount in hugetlb pages referenced by shared PMDs was discussed in [1]. The following two patches address user visible behavior caused by this issue. [1] https://lore.kernel.org/linux-mm/Y9BF+OCdWnCSilEu@monkey/ This patch (of 2): A hugetlb page will have a mapcount of 1 if mapped by multiple processes via a shared PMD. This is because only the first process increases the map count, and subsequent processes just add the shared PMD page to their page table. page_mapcount is being used to decide if a hugetlb page is shared or private in /proc/PID/smaps. Pages referenced via a shared PMD were incorrectly being counted as private. To fix, check for a shared PMD if mapcount is 1. If a shared PMD is found count the hugetlb page as shared. A new helper to check for a shared PMD is added. [akpm@linux-foundation.org: simplification, per David] [akpm@linux-foundation.org: hugetlb.h: include page_ref.h for page_count()] Link: https://lkml.kernel.org/r/20230126222721.222195-2-mike.kravetz@oracle.com Fixes: 25ee01a2fca0 ("mm: hugetlb: proc: add hugetlb-related fields to /proc/PID/smaps") Signed-off-by: Mike Kravetz Acked-by: Peter Xu Cc: David Hildenbrand Cc: James Houghton Cc: Matthew Wilcox Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Vishal Moola (Oracle) Cc: Yang Shi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/proc/task_mmu.c | 4 +--- include/linux/hugetlb.h | 13 +++++++++++++ 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 8b75a04836b6..39b1038076c3 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -714,9 +714,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, page = device_private_entry_to_page(swpent); } if (page) { - int mapcount = page_mapcount(page); - - if (mapcount >= 2) + if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte)) mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 955b19dc28a8..a18fc8e5a3dd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -942,4 +943,16 @@ static inline __init void hugetlb_cma_check(void) } #endif +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return page_count(virt_to_page(pte)) > 1; +} +#else +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return false; +} +#endif + #endif /* _LINUX_HUGETLB_H */ From 0139d61d28a229a60572ae3494a845c42925be95 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 31 Jan 2023 09:57:18 +0100 Subject: [PATCH 1268/4345] x86/debug: Fix stack recursion caused by wrongly ordered DR7 accesses commit 9d2c7203ffdb846399b82b0660563c89e918c751 upstream. In kernels compiled with CONFIG_PARAVIRT=n, the compiler re-orders the DR7 read in exc_nmi() to happen before the call to sev_es_ist_enter(). This is problematic when running as an SEV-ES guest because in this environment the DR7 read might cause a #VC exception, and taking #VC exceptions is not safe in exc_nmi() before sev_es_ist_enter() has run. The result is stack recursion if the NMI was caused on the #VC IST stack, because a subsequent #VC exception in the NMI handler will overwrite the stack frame of the interrupted #VC handler. As there are no compiler barriers affecting the ordering of DR7 reads/writes, make the accesses to this register volatile, forbidding the compiler to re-order them. [ bp: Massage text, make them volatile too, to make sure some aggressive compiler optimization pass doesn't discard them. ] Fixes: 315562c9af3d ("x86/sev-es: Adjust #VC IST Stack on entering NMI handler") Reported-by: Alexey Kardashevskiy Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230127035616.508966-1-aik@amd.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/debugreg.h | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index cfdf307ddc01..9ed8343c9b3c 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -39,7 +39,20 @@ static __always_inline unsigned long native_get_debugreg(int regno) asm("mov %%db6, %0" :"=r" (val)); break; case 7: - asm("mov %%db7, %0" :"=r" (val)); + /* + * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them + * with other code. + * + * This is needed because a DR7 access can cause a #VC exception + * when running under SEV-ES. Taking a #VC exception is not a + * safe thing to do just anywhere in the entry code and + * re-ordering might place the access into an unsafe location. + * + * This happened in the NMI handler, where the DR7 read was + * re-ordered to happen before the call to sev_es_ist_enter(), + * causing stack recursion. + */ + asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER); break; default: BUG(); @@ -66,7 +79,16 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value) asm("mov %0, %%db6" ::"r" (value)); break; case 7: - asm("mov %0, %%db7" ::"r" (value)); + /* + * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them + * with other code. + * + * While is didn't happen with a DR7 write (see the DR7 read + * comment above which explains where it happened), add the + * __FORCE_ORDER here too to avoid similar problems in the + * future. + */ + asm volatile("mov %0, %%db7" ::"r" (value), __FORCE_ORDER); break; default: BUG(); From 639b40007a480ee880228bfa4ee10f4c6f695ab7 Mon Sep 17 00:00:00 2001 From: Zheng Yongjun Date: Sat, 26 Nov 2022 07:14:30 +0000 Subject: [PATCH 1269/4345] fpga: stratix10-soc: Fix return value check in s10_ops_write_init() commit 65ea840afd508194b0ee903256162aa87e46ec30 upstream. In case of error, the function stratix10_svc_allocate_memory() returns ERR_PTR() and never returns NULL. The NULL test in the return value check should be replaced with IS_ERR(). Fixes: e7eef1d7633a ("fpga: add intel stratix10 soc fpga manager driver") Signed-off-by: Zheng Yongjun Reviewed-by: Russ Weight Cc: stable@vger.kernel.org Acked-by: Xu Yilun Link: https://lore.kernel.org/r/20221126071430.19540-1-zhengyongjun3@huawei.com Signed-off-by: Xu Yilun Signed-off-by: Greg Kroah-Hartman --- drivers/fpga/stratix10-soc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index 9e34bbbce26e..7a8269b52723 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -213,9 +213,9 @@ static int s10_ops_write_init(struct fpga_manager *mgr, /* Allocate buffers from the service layer's pool. */ for (i = 0; i < NUM_SVC_BUFS; i++) { kbuf = stratix10_svc_allocate_memory(priv->chan, SVC_BUF_SIZE); - if (!kbuf) { + if (IS_ERR(kbuf)) { s10_free_buffers(mgr); - ret = -ENOMEM; + ret = PTR_ERR(kbuf); goto init_done; } From 30187be29052bba9203b0ae2bdd815e0bc2faaab Mon Sep 17 00:00:00 2001 From: Longlong Xia Date: Sat, 28 Jan 2023 09:47:57 +0000 Subject: [PATCH 1270/4345] mm/swapfile: add cond_resched() in get_swap_pages() commit 7717fc1a12f88701573f9ed897cc4f6699c661e3 upstream. The softlockup still occurs in get_swap_pages() under memory pressure. 64 CPU cores, 64GB memory, and 28 zram devices, the disksize of each zram device is 50MB with same priority as si. Use the stress-ng tool to increase memory pressure, causing the system to oom frequently. The plist_for_each_entry_safe() loops in get_swap_pages() could reach tens of thousands of times to find available space (extreme case: cond_resched() is not called in scan_swap_map_slots()). Let's add cond_resched() into get_swap_pages() when failed to find available space to avoid softlockup. Link: https://lkml.kernel.org/r/20230128094757.1060525-1-xialonglong1@huawei.com Signed-off-by: Longlong Xia Reviewed-by: "Huang, Ying" Cc: Chen Wandun Cc: Huang Ying Cc: Kefeng Wang Cc: Nanyong Sun Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/swapfile.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/swapfile.c b/mm/swapfile.c index 5af6b0f770de..d87d6971afc9 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1104,6 +1104,7 @@ start_over: goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); + cond_resched(); spin_lock(&swap_avail_lock); nextsi: From 5c4d4a83bf1a862d80c1efff1c6e3ce33b501e2e Mon Sep 17 00:00:00 2001 From: Phillip Lougher Date: Fri, 27 Jan 2023 06:18:42 +0000 Subject: [PATCH 1271/4345] Squashfs: fix handling and sanity checking of xattr_ids count commit f65c4bbbd682b0877b669828b4e033b8d5d0a2dc upstream. A Sysbot [1] corrupted filesystem exposes two flaws in the handling and sanity checking of the xattr_ids count in the filesystem. Both of these flaws cause computation overflow due to incorrect typing. In the corrupted filesystem the xattr_ids value is 4294967071, which stored in a signed variable becomes the negative number -225. Flaw 1 (64-bit systems only): The signed integer xattr_ids variable causes sign extension. This causes variable overflow in the SQUASHFS_XATTR_*(A) macros. The variable is first multiplied by sizeof(struct squashfs_xattr_id) where the type of the sizeof operator is "unsigned long". On a 64-bit system this is 64-bits in size, and causes the negative number to be sign extended and widened to 64-bits and then become unsigned. This produces the very large number 18446744073709548016 or 2^64 - 3600. This number when rounded up by SQUASHFS_METADATA_SIZE - 1 (8191 bytes) and divided by SQUASHFS_METADATA_SIZE overflows and produces a length of 0 (stored in len). Flaw 2 (32-bit systems only): On a 32-bit system the integer variable is not widened by the unsigned long type of the sizeof operator (32-bits), and the signedness of the variable has no effect due it always being treated as unsigned. The above corrupted xattr_ids value of 4294967071, when multiplied overflows and produces the number 4294963696 or 2^32 - 3400. This number when rounded up by SQUASHFS_METADATA_SIZE - 1 (8191 bytes) and divided by SQUASHFS_METADATA_SIZE overflows again and produces a length of 0. The effect of the 0 length computation: In conjunction with the corrupted xattr_ids field, the filesystem also has a corrupted xattr_table_start value, where it matches the end of filesystem value of 850. This causes the following sanity check code to fail because the incorrectly computed len of 0 matches the incorrect size of the table reported by the superblock (0 bytes). len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); indexes = SQUASHFS_XATTR_BLOCKS(*xattr_ids); /* * The computed size of the index table (len bytes) should exactly * match the table start and end points */ start = table_start + sizeof(*id_table); end = msblk->bytes_used; if (len != (end - start)) return ERR_PTR(-EINVAL); Changing the xattr_ids variable to be "usigned int" fixes the flaw on a 64-bit system. This relies on the fact the computation is widened by the unsigned long type of the sizeof operator. Casting the variable to u64 in the above macro fixes this flaw on a 32-bit system. It also means 64-bit systems do not implicitly rely on the type of the sizeof operator to widen the computation. [1] https://lore.kernel.org/lkml/000000000000cd44f005f1a0f17f@google.com/ Link: https://lkml.kernel.org/r/20230127061842.10965-1-phillip@squashfs.org.uk Fixes: 506220d2ba21 ("squashfs: add more sanity checks in xattr id lookup") Signed-off-by: Phillip Lougher Reported-by: Cc: Alexey Khoroshilov Cc: Fedor Pchelkin Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/squashfs/squashfs_fs.h | 2 +- fs/squashfs/squashfs_fs_sb.h | 2 +- fs/squashfs/xattr.h | 4 ++-- fs/squashfs/xattr_id.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index b3fdc8212c5f..95f8e8901768 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -183,7 +183,7 @@ static inline int squashfs_block_size(__le32 raw) #define SQUASHFS_ID_BLOCK_BYTES(A) (SQUASHFS_ID_BLOCKS(A) *\ sizeof(u64)) /* xattr id lookup table defines */ -#define SQUASHFS_XATTR_BYTES(A) ((A) * sizeof(struct squashfs_xattr_id)) +#define SQUASHFS_XATTR_BYTES(A) (((u64) (A)) * sizeof(struct squashfs_xattr_id)) #define SQUASHFS_XATTR_BLOCK(A) (SQUASHFS_XATTR_BYTES(A) / \ SQUASHFS_METADATA_SIZE) diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 166e98806265..8f9445e290e7 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -63,7 +63,7 @@ struct squashfs_sb_info { long long bytes_used; unsigned int inodes; unsigned int fragments; - int xattr_ids; + unsigned int xattr_ids; unsigned int ids; }; #endif diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index d8a270d3ac4c..f1a463d8bfa0 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -10,12 +10,12 @@ #ifdef CONFIG_SQUASHFS_XATTR extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, - u64 *, int *); + u64 *, unsigned int *); extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, unsigned int *, unsigned long long *); #else static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, - u64 start, u64 *xattr_table_start, int *xattr_ids) + u64 start, u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_xattr_id_table *id_table; diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index f6d78cbc3e74..b88d19e9581e 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -56,7 +56,7 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, * Read uncompressed xattr id lookup table indexes from disk into memory */ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, - u64 *xattr_table_start, int *xattr_ids) + u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_sb_info *msblk = sb->s_fs_info; unsigned int len, indexes; From b591abac78e25269b12e3d7170c99463f8c5cb02 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Fri, 27 Jan 2023 12:05:31 -0800 Subject: [PATCH 1272/4345] drm/i915: Fix potential bit_17 double-free commit 7057a8f126f14f14b040faecfa220fd27c6c2f85 upstream. A userspace with multiple threads racing I915_GEM_SET_TILING to set the tiling to I915_TILING_NONE could trigger a double free of the bit_17 bitmask. (Or conversely leak memory on the transition to tiled.) Move allocation/free'ing of the bitmask within the section protected by the obj lock. Signed-off-by: Rob Clark Fixes: 2850748ef876 ("drm/i915: Pull i915_vma_pin under the vm->mutex") Cc: # v5.5+ [tursulin: Correct fixes tag and added cc stable.] Reviewed-by: Tvrtko Ursulin Signed-off-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20230127200550.3531984-1-robdclark@gmail.com (cherry picked from commit 10e0cbaaf1104f449d695c80bcacf930dcd3c42e) Signed-off-by: Rodrigo Vivi Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gem/i915_gem_tiling.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index ffcaee74a249..545fa703d975 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -296,10 +296,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, spin_unlock(&obj->vma.lock); obj->tiling_and_stride = tiling | stride; - i915_gem_object_unlock(obj); - - /* Force the fence to be reacquired for GTT access */ - i915_gem_object_release_mmap_gtt(obj); /* Try to preallocate memory required to save swizzling on put-pages */ if (i915_gem_object_needs_bit17_swizzle(obj)) { @@ -312,6 +308,11 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, obj->bit_17 = NULL; } + i915_gem_object_unlock(obj); + + /* Force the fence to be reacquired for GTT access */ + i915_gem_object_release_mmap_gtt(obj); + return 0; } From bb875f0a34e775500f74bfaedf72e049733d9211 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 27 Jan 2023 10:40:08 +0000 Subject: [PATCH 1273/4345] nvmem: core: initialise nvmem->id early commit 3bd747c7ea13cb145f0d84444e00df928b0842d9 upstream. The error path for wp_gpio attempts to free the IDA nvmem->id, but this has yet to be assigned, so will always be zero - leaking the ID allocated by ida_alloc(). Fix this by moving the initialisation of nvmem->id earlier. Fixes: f7d8d7dcd978 ("nvmem: fix memory leak in error path") Cc: stable@vger.kernel.org Signed-off-by: Russell King (Oracle) Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230127104015.23839-4-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 21d89d80d083..4126c7002fc8 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -625,6 +625,8 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) return ERR_PTR(rval); } + nvmem->id = rval; + if (config->wp_gpio) nvmem->wp_gpio = config->wp_gpio; else @@ -640,7 +642,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) kref_init(&nvmem->refcnt); INIT_LIST_HEAD(&nvmem->cells); - nvmem->id = rval; nvmem->owner = config->owner; if (!nvmem->owner && config->dev->driver) nvmem->owner = config->dev->driver->owner; From 1fd7a6a579687fc55e9c5c8cfe787533ee07b2d5 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Fri, 27 Jan 2023 10:40:13 +0000 Subject: [PATCH 1274/4345] nvmem: core: fix cell removal on error commit db3546d58b5a0fa581d9c9f2bdc2856fa6c5e43e upstream. nvmem_add_cells() could return an error after some cells are already added to the provider. In this case, the added cells are not removed. Remove any registered cells if nvmem_add_cells() fails. Fixes: fa72d847d68d7 ("nvmem: check the return value of nvmem_add_cells()") Cc: stable@vger.kernel.org Signed-off-by: Michael Walle Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230127104015.23839-9-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 4126c7002fc8..7b281ae540ad 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -695,7 +695,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (config->cells) { rval = nvmem_add_cells(nvmem, config->cells, config->ncells); if (rval) - goto err_teardown_compat; + goto err_remove_cells; } rval = nvmem_add_cells_from_table(nvmem); @@ -712,7 +712,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) err_remove_cells: nvmem_device_remove_all_cells(nvmem); -err_teardown_compat: if (config->compat) nvmem_sysfs_remove_compat(nvmem, config); err_device_del: From 967e726e57c3bd0cd3b618d9cf81d91c21f764a6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 30 Jan 2023 13:48:40 +0200 Subject: [PATCH 1275/4345] serial: 8250_dma: Fix DMA Rx completion race MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 31352811e13dc2313f101b890fd4b1ce760b5fe7 upstream. __dma_rx_complete() is called from two places: - Through the DMA completion callback dma_rx_complete() - From serial8250_rx_dma_flush() after IIR_RLSI or IIR_RX_TIMEOUT The former does not hold port's lock during __dma_rx_complete() which allows these two to race and potentially insert the same data twice. Extend port's lock coverage in dma_rx_complete() to prevent the race and check if the DMA Rx is still pending completion before calling into __dma_rx_complete(). Reported-by: Gilles BULOZ Tested-by: Gilles BULOZ Fixes: 9ee4b83e51f7 ("serial: 8250: Add support for dmaengine") Cc: stable@vger.kernel.org Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230130114841.25749-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_dma.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index b3c3f7e5851a..c703ad45b5e9 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -59,6 +59,18 @@ static void __dma_rx_complete(void *param) tty_flip_buffer_push(tty_port); } +static void dma_rx_complete(void *param) +{ + struct uart_8250_port *p = param; + struct uart_8250_dma *dma = p->dma; + unsigned long flags; + + spin_lock_irqsave(&p->port.lock, flags); + if (dma->rx_running) + __dma_rx_complete(p); + spin_unlock_irqrestore(&p->port.lock, flags); +} + int serial8250_tx_dma(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; @@ -130,7 +142,7 @@ int serial8250_rx_dma(struct uart_8250_port *p) return -EBUSY; dma->rx_running = 1; - desc->callback = __dma_rx_complete; + desc->callback = dma_rx_complete; desc->callback_param = p; dma->rx_cookie = dmaengine_submit(desc); From 6c8a2c67a9d6de379b23aa3bbf4d8081dc014bd8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 30 Jan 2023 13:48:41 +0200 Subject: [PATCH 1276/4345] serial: 8250_dma: Fix DMA Rx rearm race MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 57e9af7831dcf211c5c689c2a6f209f4abdf0bce upstream. As DMA Rx can be completed from two places, it is possible that DMA Rx completes before DMA completion callback had a chance to complete it. Once the previous DMA Rx has been completed, a new one can be started on the next UART interrupt. The following race is possible (uart_unlock_and_check_sysrq_irqrestore() replaced with spin_unlock_irqrestore() for simplicity/clarity): CPU0 CPU1 dma_rx_complete() serial8250_handle_irq() spin_lock_irqsave(&port->lock) handle_rx_dma() serial8250_rx_dma_flush() __dma_rx_complete() dma->rx_running = 0 // Complete DMA Rx spin_unlock_irqrestore(&port->lock) serial8250_handle_irq() spin_lock_irqsave(&port->lock) handle_rx_dma() serial8250_rx_dma() dma->rx_running = 1 // Setup a new DMA Rx spin_unlock_irqrestore(&port->lock) spin_lock_irqsave(&port->lock) // sees dma->rx_running = 1 __dma_rx_complete() dma->rx_running = 0 // Incorrectly complete // running DMA Rx This race seems somewhat theoretical to occur for real but handle it correctly regardless. Check what is the DMA status before complething anything in __dma_rx_complete(). Reported-by: Gilles BULOZ Tested-by: Gilles BULOZ Fixes: 9ee4b83e51f7 ("serial: 8250: Add support for dmaengine") Cc: stable@vger.kernel.org Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230130114841.25749-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_dma.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index c703ad45b5e9..33ce4b218d9e 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -46,15 +46,23 @@ static void __dma_rx_complete(void *param) struct uart_8250_dma *dma = p->dma; struct tty_port *tty_port = &p->port.state->port; struct dma_tx_state state; + enum dma_status dma_status; int count; - dma->rx_running = 0; - dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + /* + * New DMA Rx can be started during the completion handler before it + * could acquire port's lock and it might still be ongoing. Don't to + * anything in such case. + */ + dma_status = dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + if (dma_status == DMA_IN_PROGRESS) + return; count = dma->rx_size - state.residue; tty_insert_flip_string(tty_port, dma->rx_buf, count); p->port.icount.rx += count; + dma->rx_running = 0; tty_flip_buffer_push(tty_port); } From 3931014367ef31d26af65386a4ca496f50f0cfdf Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Fri, 11 Nov 2022 13:49:49 +0800 Subject: [PATCH 1277/4345] fbdev: smscufx: fix error handling code in ufx_usb_probe commit b76449ee75e21acfe9fa4c653d8598f191ed7d68 upstream. The current error handling code in ufx_usb_probe have many unmatching issues, e.g., missing ufx_free_usb_list, destroy_modedb label should only include framebuffer_release, fb_dealloc_cmap only matches fb_alloc_cmap. My local syzkaller reports a memory leak bug: memory leak in ufx_usb_probe BUG: memory leak unreferenced object 0xffff88802f879580 (size 128): comm "kworker/0:7", pid 17416, jiffies 4295067474 (age 46.710s) hex dump (first 32 bytes): 80 21 7c 2e 80 88 ff ff 18 d0 d0 0c 80 88 ff ff .!|............. 00 d0 d0 0c 80 88 ff ff e0 ff ff ff 0f 00 00 00 ................ backtrace: [] kmalloc_trace+0x20/0x90 mm/slab_common.c:1045 [] kmalloc include/linux/slab.h:553 [inline] [] kzalloc include/linux/slab.h:689 [inline] [] ufx_alloc_urb_list drivers/video/fbdev/smscufx.c:1873 [inline] [] ufx_usb_probe+0x11c/0x15a0 drivers/video/fbdev/smscufx.c:1655 [] usb_probe_interface+0x177/0x370 drivers/usb/core/driver.c:396 [] call_driver_probe drivers/base/dd.c:560 [inline] [] really_probe+0x12d/0x390 drivers/base/dd.c:639 [] __driver_probe_device+0xbf/0x140 drivers/base/dd.c:778 [] driver_probe_device+0x2a/0x120 drivers/base/dd.c:808 [] __device_attach_driver+0xf7/0x150 drivers/base/dd.c:936 [] bus_for_each_drv+0xb7/0x100 drivers/base/bus.c:427 [] __device_attach+0x105/0x2d0 drivers/base/dd.c:1008 [] bus_probe_device+0xc6/0xe0 drivers/base/bus.c:487 [] device_add+0x642/0xdc0 drivers/base/core.c:3517 [] usb_set_configuration+0x8ef/0xb80 drivers/usb/core/message.c:2170 [] usb_generic_driver_probe+0x8c/0xc0 drivers/usb/core/generic.c:238 [] usb_probe_device+0x5c/0x140 drivers/usb/core/driver.c:293 [] call_driver_probe drivers/base/dd.c:560 [inline] [] really_probe+0x12d/0x390 drivers/base/dd.c:639 [] __driver_probe_device+0xbf/0x140 drivers/base/dd.c:778 Fix this bug by rewriting the error handling code in ufx_usb_probe. Reported-by: syzkaller Tested-by: Dongliang Mu Signed-off-by: Dongliang Mu Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/smscufx.c | 46 +++++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 15 deletions(-) diff --git a/drivers/video/fbdev/smscufx.c b/drivers/video/fbdev/smscufx.c index 5fa3f1e5dfe8..b3295cd7fd4f 100644 --- a/drivers/video/fbdev/smscufx.c +++ b/drivers/video/fbdev/smscufx.c @@ -1621,7 +1621,7 @@ static int ufx_usb_probe(struct usb_interface *interface, struct usb_device *usbdev; struct ufx_data *dev; struct fb_info *info; - int retval; + int retval = -ENOMEM; u32 id_rev, fpga_rev; /* usb initialization */ @@ -1653,15 +1653,17 @@ static int ufx_usb_probe(struct usb_interface *interface, if (!ufx_alloc_urb_list(dev, WRITES_IN_FLIGHT, MAX_TRANSFER)) { dev_err(dev->gdev, "ufx_alloc_urb_list failed\n"); - goto e_nomem; + goto put_ref; } /* We don't register a new USB class. Our client interface is fbdev */ /* allocates framebuffer driver structure, not framebuffer memory */ info = framebuffer_alloc(0, &usbdev->dev); - if (!info) - goto e_nomem; + if (!info) { + dev_err(dev->gdev, "framebuffer_alloc failed\n"); + goto free_urb_list; + } dev->info = info; info->par = dev; @@ -1704,22 +1706,34 @@ static int ufx_usb_probe(struct usb_interface *interface, check_warn_goto_error(retval, "unable to find common mode for display and adapter"); retval = ufx_reg_set_bits(dev, 0x4000, 0x00000001); - check_warn_goto_error(retval, "error %d enabling graphics engine", retval); + if (retval < 0) { + dev_err(dev->gdev, "error %d enabling graphics engine", retval); + goto setup_modes; + } /* ready to begin using device */ atomic_set(&dev->usb_active, 1); dev_dbg(dev->gdev, "checking var"); retval = ufx_ops_check_var(&info->var, info); - check_warn_goto_error(retval, "error %d ufx_ops_check_var", retval); + if (retval < 0) { + dev_err(dev->gdev, "error %d ufx_ops_check_var", retval); + goto reset_active; + } dev_dbg(dev->gdev, "setting par"); retval = ufx_ops_set_par(info); - check_warn_goto_error(retval, "error %d ufx_ops_set_par", retval); + if (retval < 0) { + dev_err(dev->gdev, "error %d ufx_ops_set_par", retval); + goto reset_active; + } dev_dbg(dev->gdev, "registering framebuffer"); retval = register_framebuffer(info); - check_warn_goto_error(retval, "error %d register_framebuffer", retval); + if (retval < 0) { + dev_err(dev->gdev, "error %d register_framebuffer", retval); + goto reset_active; + } dev_info(dev->gdev, "SMSC UDX USB device /dev/fb%d attached. %dx%d resolution." " Using %dK framebuffer memory\n", info->node, @@ -1727,21 +1741,23 @@ static int ufx_usb_probe(struct usb_interface *interface, return 0; -error: - fb_dealloc_cmap(&info->cmap); -destroy_modedb: +reset_active: + atomic_set(&dev->usb_active, 0); +setup_modes: fb_destroy_modedb(info->monspecs.modedb); vfree(info->screen_base); fb_destroy_modelist(&info->modelist); +error: + fb_dealloc_cmap(&info->cmap); +destroy_modedb: framebuffer_release(info); +free_urb_list: + if (dev->urbs.count > 0) + ufx_free_urb_list(dev); put_ref: kref_put(&dev->kref, ufx_free); /* ref for framebuffer */ kref_put(&dev->kref, ufx_free); /* last ref from kref_init */ return retval; - -e_nomem: - retval = -ENOMEM; - goto put_ref; } static void ufx_usb_disconnect(struct usb_interface *interface) From 914e38f02a490dafd980ff0f39cccedc074deb29 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 15 Nov 2022 00:08:47 +0800 Subject: [PATCH 1278/4345] f2fs: fix to do sanity check on i_extra_isize in is_alive() commit d3b7b4afd6b2c344eabf9cc26b8bfa903c164c7c upstream. syzbot found a f2fs bug: BUG: KASAN: slab-out-of-bounds in data_blkaddr fs/f2fs/f2fs.h:2891 [inline] BUG: KASAN: slab-out-of-bounds in is_alive fs/f2fs/gc.c:1117 [inline] BUG: KASAN: slab-out-of-bounds in gc_data_segment fs/f2fs/gc.c:1520 [inline] BUG: KASAN: slab-out-of-bounds in do_garbage_collect+0x386a/0x3df0 fs/f2fs/gc.c:1734 Read of size 4 at addr ffff888076557568 by task kworker/u4:3/52 CPU: 1 PID: 52 Comm: kworker/u4:3 Not tainted 6.1.0-rc4-syzkaller-00362-gfef7fd48922d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Workqueue: writeback wb_workfn (flush-7:0) Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:284 [inline] print_report+0x15e/0x45d mm/kasan/report.c:395 kasan_report+0xbb/0x1f0 mm/kasan/report.c:495 data_blkaddr fs/f2fs/f2fs.h:2891 [inline] is_alive fs/f2fs/gc.c:1117 [inline] gc_data_segment fs/f2fs/gc.c:1520 [inline] do_garbage_collect+0x386a/0x3df0 fs/f2fs/gc.c:1734 f2fs_gc+0x88c/0x20a0 fs/f2fs/gc.c:1831 f2fs_balance_fs+0x544/0x6b0 fs/f2fs/segment.c:410 f2fs_write_inode+0x57e/0xe20 fs/f2fs/inode.c:753 write_inode fs/fs-writeback.c:1440 [inline] __writeback_single_inode+0xcfc/0x1440 fs/fs-writeback.c:1652 writeback_sb_inodes+0x54d/0xf90 fs/fs-writeback.c:1870 wb_writeback+0x2c5/0xd70 fs/fs-writeback.c:2044 wb_do_writeback fs/fs-writeback.c:2187 [inline] wb_workfn+0x2dc/0x12f0 fs/fs-writeback.c:2227 process_one_work+0x9bf/0x1710 kernel/workqueue.c:2289 worker_thread+0x665/0x1080 kernel/workqueue.c:2436 kthread+0x2e4/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 The root cause is that we forgot to do sanity check on .i_extra_isize in below path, result in accessing invalid address later, fix it. - gc_data_segment - is_alive - data_blkaddr - offset_in_addr Reported-by: syzbot+f8f3dfa4abc489e768a1@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-f2fs-devel/0000000000003cb3c405ed5c17f9@google.com/T/#u Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/gc.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ce6a2a247804..66ac048cc899 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -977,7 +977,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, { struct page *node_page; nid_t nid; - unsigned int ofs_in_node, max_addrs; + unsigned int ofs_in_node, max_addrs, base; block_t source_blkaddr; nid = le32_to_cpu(sum->nid); @@ -1003,11 +1003,17 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, return false; } - max_addrs = IS_INODE(node_page) ? DEF_ADDRS_PER_INODE : - DEF_ADDRS_PER_BLOCK; - if (ofs_in_node >= max_addrs) { - f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%u, nid:%u, max:%u", - ofs_in_node, dni->ino, dni->nid, max_addrs); + if (IS_INODE(node_page)) { + base = offset_in_addr(F2FS_INODE(node_page)); + max_addrs = DEF_ADDRS_PER_INODE; + } else { + base = 0; + max_addrs = DEF_ADDRS_PER_BLOCK; + } + + if (base + ofs_in_node >= max_addrs) { + f2fs_err(sbi, "Inconsistent blkaddr offset: base:%u, ofs_in_node:%u, max:%u, ino:%u, nid:%u", + base, ofs_in_node, max_addrs, dni->ino, dni->nid); f2fs_put_page(node_page, 1); return false; } From b2e412879595821ff1b5545cbed5f108fba7f5b6 Mon Sep 17 00:00:00 2001 From: Minsuk Kang Date: Wed, 16 Nov 2022 23:29:52 +0900 Subject: [PATCH 1279/4345] wifi: brcmfmac: Check the count value of channel spec to prevent out-of-bounds reads commit 4920ab131b2dbae7464b72bdcac465d070254209 upstream. This patch fixes slab-out-of-bounds reads in brcmfmac that occur in brcmf_construct_chaninfo() and brcmf_enable_bw40_2g() when the count value of channel specifications provided by the device is greater than the length of 'list->element[]', decided by the size of the 'list' allocated with kzalloc(). The patch adds checks that make the functions free the buffer and return -EINVAL if that is the case. Note that the negative return is handled by the caller, brcmf_setup_wiphybands() or brcmf_cfg80211_attach(). Found by a modified version of syzkaller. Crash Report from brcmf_construct_chaninfo(): ================================================================== BUG: KASAN: slab-out-of-bounds in brcmf_setup_wiphybands+0x1238/0x1430 Read of size 4 at addr ffff888115f24600 by task kworker/0:2/1896 CPU: 0 PID: 1896 Comm: kworker/0:2 Tainted: G W O 5.14.0+ #132 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 Workqueue: usb_hub_wq hub_event Call Trace: dump_stack_lvl+0x57/0x7d print_address_description.constprop.0.cold+0x93/0x334 kasan_report.cold+0x83/0xdf brcmf_setup_wiphybands+0x1238/0x1430 brcmf_cfg80211_attach+0x2118/0x3fd0 brcmf_attach+0x389/0xd40 brcmf_usb_probe+0x12de/0x1690 usb_probe_interface+0x25f/0x710 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 bus_for_each_drv+0x123/0x1a0 __device_attach+0x207/0x330 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 usb_set_configuration+0x984/0x1770 usb_generic_driver_probe+0x69/0x90 usb_probe_device+0x9c/0x220 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 bus_for_each_drv+0x123/0x1a0 __device_attach+0x207/0x330 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 usb_new_device.cold+0x463/0xf66 hub_event+0x10d5/0x3330 process_one_work+0x873/0x13e0 worker_thread+0x8b/0xd10 kthread+0x379/0x450 ret_from_fork+0x1f/0x30 Allocated by task 1896: kasan_save_stack+0x1b/0x40 __kasan_kmalloc+0x7c/0x90 kmem_cache_alloc_trace+0x19e/0x330 brcmf_setup_wiphybands+0x290/0x1430 brcmf_cfg80211_attach+0x2118/0x3fd0 brcmf_attach+0x389/0xd40 brcmf_usb_probe+0x12de/0x1690 usb_probe_interface+0x25f/0x710 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 bus_for_each_drv+0x123/0x1a0 __device_attach+0x207/0x330 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 usb_set_configuration+0x984/0x1770 usb_generic_driver_probe+0x69/0x90 usb_probe_device+0x9c/0x220 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 bus_for_each_drv+0x123/0x1a0 __device_attach+0x207/0x330 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 usb_new_device.cold+0x463/0xf66 hub_event+0x10d5/0x3330 process_one_work+0x873/0x13e0 worker_thread+0x8b/0xd10 kthread+0x379/0x450 ret_from_fork+0x1f/0x30 The buggy address belongs to the object at ffff888115f24000 which belongs to the cache kmalloc-2k of size 2048 The buggy address is located 1536 bytes inside of 2048-byte region [ffff888115f24000, ffff888115f24800) Memory state around the buggy address: ffff888115f24500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff888115f24580: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff888115f24600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff888115f24680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888115f24700: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Crash Report from brcmf_enable_bw40_2g(): ================================================================== BUG: KASAN: slab-out-of-bounds in brcmf_cfg80211_attach+0x3d11/0x3fd0 Read of size 4 at addr ffff888103787600 by task kworker/0:2/1896 CPU: 0 PID: 1896 Comm: kworker/0:2 Tainted: G W O 5.14.0+ #132 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 Workqueue: usb_hub_wq hub_event Call Trace: dump_stack_lvl+0x57/0x7d print_address_description.constprop.0.cold+0x93/0x334 kasan_report.cold+0x83/0xdf brcmf_cfg80211_attach+0x3d11/0x3fd0 brcmf_attach+0x389/0xd40 brcmf_usb_probe+0x12de/0x1690 usb_probe_interface+0x25f/0x710 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 bus_for_each_drv+0x123/0x1a0 __device_attach+0x207/0x330 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 usb_set_configuration+0x984/0x1770 usb_generic_driver_probe+0x69/0x90 usb_probe_device+0x9c/0x220 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 bus_for_each_drv+0x123/0x1a0 __device_attach+0x207/0x330 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 usb_new_device.cold+0x463/0xf66 hub_event+0x10d5/0x3330 process_one_work+0x873/0x13e0 worker_thread+0x8b/0xd10 kthread+0x379/0x450 ret_from_fork+0x1f/0x30 Allocated by task 1896: kasan_save_stack+0x1b/0x40 __kasan_kmalloc+0x7c/0x90 kmem_cache_alloc_trace+0x19e/0x330 brcmf_cfg80211_attach+0x3302/0x3fd0 brcmf_attach+0x389/0xd40 brcmf_usb_probe+0x12de/0x1690 usb_probe_interface+0x25f/0x710 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 bus_for_each_drv+0x123/0x1a0 __device_attach+0x207/0x330 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 usb_set_configuration+0x984/0x1770 usb_generic_driver_probe+0x69/0x90 usb_probe_device+0x9c/0x220 really_probe+0x1be/0xa90 __driver_probe_device+0x2ab/0x460 driver_probe_device+0x49/0x120 __device_attach_driver+0x18a/0x250 bus_for_each_drv+0x123/0x1a0 __device_attach+0x207/0x330 bus_probe_device+0x1a2/0x260 device_add+0xa61/0x1ce0 usb_new_device.cold+0x463/0xf66 hub_event+0x10d5/0x3330 process_one_work+0x873/0x13e0 worker_thread+0x8b/0xd10 kthread+0x379/0x450 ret_from_fork+0x1f/0x30 The buggy address belongs to the object at ffff888103787000 which belongs to the cache kmalloc-2k of size 2048 The buggy address is located 1536 bytes inside of 2048-byte region [ffff888103787000, ffff888103787800) Memory state around the buggy address: ffff888103787500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff888103787580: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff888103787600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff888103787680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888103787700: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Reported-by: Dokyung Song Reported-by: Jisoo Jang Reported-by: Minsuk Kang Reviewed-by: Arend van Spriel Signed-off-by: Minsuk Kang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221116142952.518241-1-linuxlovemin@yonsei.ac.kr Signed-off-by: Greg Kroah-Hartman --- .../broadcom/brcm80211/brcmfmac/cfg80211.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index c2b6e5c966d0..0a069bc7f156 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -90,6 +90,9 @@ #define BRCMF_ASSOC_PARAMS_FIXED_SIZE \ (sizeof(struct brcmf_assoc_params_le) - sizeof(u16)) +#define BRCMF_MAX_CHANSPEC_LIST \ + (BRCMF_DCMD_MEDLEN / sizeof(__le32) - 1) + static bool check_vif_up(struct brcmf_cfg80211_vif *vif) { if (!test_bit(BRCMF_VIF_STATUS_READY, &vif->sme_state)) { @@ -6459,6 +6462,13 @@ static int brcmf_construct_chaninfo(struct brcmf_cfg80211_info *cfg, band->channels[i].flags = IEEE80211_CHAN_DISABLED; total = le32_to_cpu(list->count); + if (total > BRCMF_MAX_CHANSPEC_LIST) { + bphy_err(drvr, "Invalid count of channel Spec. (%u)\n", + total); + err = -EINVAL; + goto fail_pbuf; + } + for (i = 0; i < total; i++) { ch.chspec = (u16)le32_to_cpu(list->element[i]); cfg->d11inf.decchspec(&ch); @@ -6604,6 +6614,13 @@ static int brcmf_enable_bw40_2g(struct brcmf_cfg80211_info *cfg) band = cfg_to_wiphy(cfg)->bands[NL80211_BAND_2GHZ]; list = (struct brcmf_chanspec_list *)pbuf; num_chan = le32_to_cpu(list->count); + if (num_chan > BRCMF_MAX_CHANSPEC_LIST) { + bphy_err(drvr, "Invalid count of channel Spec. (%u)\n", + num_chan); + kfree(pbuf); + return -EINVAL; + } + for (i = 0; i < num_chan; i++) { ch.chspec = (u16)le32_to_cpu(list->element[i]); cfg->d11inf.decchspec(&ch); From 34ec4c7831c416ac56619477f1701986634a7efc Mon Sep 17 00:00:00 2001 From: Christophe Kerello Date: Sun, 20 Feb 2022 15:14:31 +0000 Subject: [PATCH 1280/4345] nvmem: core: Fix a conflict between MTD and NVMEM on wp-gpios property [ Upstream commit f6c052afe6f802d87c74153b7a57c43b2e9faf07 ] Wp-gpios property can be used on NVMEM nodes and the same property can be also used on MTD NAND nodes. In case of the wp-gpios property is defined at NAND level node, the GPIO management is done at NAND driver level. Write protect is disabled when the driver is probed or resumed and is enabled when the driver is released or suspended. When no partitions are defined in the NAND DT node, then the NAND DT node will be passed to NVMEM framework. If wp-gpios property is defined in this node, the GPIO resource is taken twice and the NAND controller driver fails to probe. It would be possible to set config->wp_gpio at MTD level before calling nvmem_register function but NVMEM framework will toggle this GPIO on each write when this GPIO should only be controlled at NAND level driver to ensure that the Write Protect has not been enabled. A way to fix this conflict is to add a new boolean flag in nvmem_config named ignore_wp. In case ignore_wp is set, the GPIO resource will be managed by the provider. Fixes: 2a127da461a9 ("nvmem: add support for the write-protect pin") Cc: stable@vger.kernel.org Signed-off-by: Christophe Kerello Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20220220151432.16605-2-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: ab3428cfd9aa ("nvmem: core: fix registration vs use race") Signed-off-by: Sasha Levin --- drivers/nvmem/core.c | 2 +- include/linux/nvmem-provider.h | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 7b281ae540ad..48fbe49e3772 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -629,7 +629,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (config->wp_gpio) nvmem->wp_gpio = config->wp_gpio; - else + else if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 06409a6c40bc..39ec67689898 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -49,7 +49,8 @@ enum nvmem_type { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin + * @wp-gpio: Write protect pin + * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem" name will be assigned to the device if * no name is specified in its configuration. In such case "" is @@ -69,6 +70,7 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; + bool ignore_wp; bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; From e4c3ea9b6045912d87de83f616c50a0a0fc74b86 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 1 Nov 2021 23:45:35 -0700 Subject: [PATCH 1281/4345] bpf: Do not reject when the stack read size is different from the tracked scalar size [ Upstream commit f30d4968e9aee737e174fc97942af46cfb49b484 ] Below is a simplified case from a report in bcc [0]: r4 = 20 *(u32 *)(r10 -4) = r4 *(u32 *)(r10 -8) = r4 /* r4 state is tracked */ r4 = *(u64 *)(r10 -8) /* Read more than the tracked 32bit scalar. * verifier rejects as 'corrupted spill memory'. */ After commit 354e8f1970f8 ("bpf: Support <8-byte scalar spill and refill"), the 8-byte aligned 32bit spill is also tracked by the verifier and the register state is stored. However, if 8 bytes are read from the stack instead of the tracked 4 byte scalar, then verifier currently rejects the program as "corrupted spill memory". This patch fixes this case by allowing it to read but marks the register as unknown. Also note that, if the prog is trying to corrupt/leak an earlier spilled pointer by spilling another <8 bytes register on top, this has already been rejected in the check_stack_write_fixed_off(). [0] https://github.com/iovisor/bcc/pull/3683 Fixes: 354e8f1970f8 ("bpf: Support <8-byte scalar spill and refill") Reported-by: Hengqi Chen Reported-by: Yonghong Song Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Tested-by: Hengqi Chen Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211102064535.316018-1-kafai@fb.com Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0d0d7b140f05..9e5f1ebe67d7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2597,9 +2597,12 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, reg = ®_state->stack[spi].spilled_ptr; if (is_spilled_reg(®_state->stack[spi])) { - if (size != BPF_REG_SIZE) { - u8 scalar_size = 0; + u8 spill_size = 1; + for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--) + spill_size++; + + if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); @@ -2610,10 +2613,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno < 0) return 0; - for (i = BPF_REG_SIZE; i > 0 && stype[i - 1] == STACK_SPILL; i--) - scalar_size++; - - if (!(off % BPF_REG_SIZE) && size == scalar_size) { + if (!(off % BPF_REG_SIZE) && size == spill_size) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ @@ -2637,12 +2637,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, state->regs[dst_regno].live |= REG_LIVE_WRITTEN; return 0; } - for (i = 1; i < BPF_REG_SIZE; i++) { - if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) { - verbose(env, "corrupted spill memory\n"); - return -EACCES; - } - } if (dst_regno >= 0) { /* restore register state from stack */ From 91ad3104b211e57842dc2289d2716589ced1affc Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Sat, 17 Dec 2022 23:13:05 +0100 Subject: [PATCH 1282/4345] iio:adc:twl6030: Enable measurement of VAC [ Upstream commit bffb7d9d1a3dbd09e083b88aefd093b3b10abbfb ] VAC needs to be wired up to produce proper measurements, without this change only near zero values are reported. Reported-by: kernel test robot Reported-by: Julia Lawall Fixes: 1696f36482e7 ("iio: twl6030-gpadc: TWL6030, TWL6032 GPADC driver") Signed-off-by: Andreas Kemnade Link: https://lore.kernel.org/r/20221217221305.671117-1-andreas@kemnade.info Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/adc/twl6030-gpadc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/twl6030-gpadc.c b/drivers/iio/adc/twl6030-gpadc.c index 9ab23b29bee3..024bdc1ef77e 100644 --- a/drivers/iio/adc/twl6030-gpadc.c +++ b/drivers/iio/adc/twl6030-gpadc.c @@ -952,7 +952,7 @@ static int twl6030_gpadc_probe(struct platform_device *pdev) } ret = twl_i2c_write_u8(TWL6030_MODULE_ID0, - VBAT_MEAS | BB_MEAS | BB_MEAS, + VBAT_MEAS | BB_MEAS | VAC_MEAS, TWL6030_MISC1); if (ret < 0) { dev_err(dev, "failed to wire up inputs\n"); From 97a5104d640da5867dd55243b8300a3867da90a9 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 30 May 2022 19:30:15 +0800 Subject: [PATCH 1283/4345] mm/migration: return errno when isolate_huge_page failed [ Upstream commit 7ce82f4c3f3ead13a9d9498768e3b1a79975c4d8 ] We might fail to isolate huge page due to e.g. the page is under migration which cleared HPageMigratable. We should return errno in this case rather than always return 1 which could confuse the user, i.e. the caller might think all of the memory is migrated while the hugetlb page is left behind. We make the prototype of isolate_huge_page consistent with isolate_lru_page as suggested by Huang Ying and rename isolate_huge_page to isolate_hugetlb as suggested by Muchun to improve the readability. Link: https://lkml.kernel.org/r/20220530113016.16663-4-linmiaohe@huawei.com Fixes: e8db67eb0ded ("mm: migrate: move_pages() supports thp migration") Signed-off-by: Miaohe Lin Suggested-by: Huang Ying Reported-by: kernel test robot (build error) Cc: Alistair Popple Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Hildenbrand Cc: David Howells Cc: Mike Kravetz Cc: Muchun Song Cc: Oscar Salvador Cc: Peter Xu Signed-off-by: Andrew Morton Stable-dep-of: 73bdf65ea748 ("migrate: hugetlb: check for hugetlb shared PMD in node migration") Signed-off-by: Sasha Levin --- include/linux/hugetlb.h | 6 +++--- mm/gup.c | 2 +- mm/hugetlb.c | 6 +++--- mm/memory-failure.c | 2 +- mm/memory_hotplug.c | 2 +- mm/mempolicy.c | 2 +- mm/migrate.c | 7 ++++--- 7 files changed, 14 insertions(+), 13 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a18fc8e5a3dd..c0ba379574a4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -145,7 +145,7 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -bool isolate_huge_page(struct page *page, struct list_head *list); +int isolate_hugetlb(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -326,9 +326,9 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return NULL; } -static inline bool isolate_huge_page(struct page *page, struct list_head *list) +static inline int isolate_hugetlb(struct page *page, struct list_head *list) { - return false; + return -EBUSY; } static inline void putback_active_hugepage(struct page *page) diff --git a/mm/gup.c b/mm/gup.c index 6d5e4fd55d32..11307a8b20d5 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1627,7 +1627,7 @@ check_again: */ if (is_migrate_cma_page(head)) { if (PageHuge(head)) { - if (!isolate_huge_page(head, &cma_page_list)) + if (isolate_hugetlb(head, &cma_page_list)) isolation_error_count++; } else { if (!PageLRU(head) && drain_allow) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3499b3803384..81949f6d29af 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5655,14 +5655,14 @@ follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int fla return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT); } -bool isolate_huge_page(struct page *page, struct list_head *list) +int isolate_hugetlb(struct page *page, struct list_head *list) { - bool ret = true; + int ret = 0; spin_lock(&hugetlb_lock); if (!PageHeadHuge(page) || !page_huge_active(page) || !get_page_unless_zero(page)) { - ret = false; + ret = -EBUSY; goto unlock; } clear_page_huge_active(page); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index aef267c6a724..b21dd4a79392 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1763,7 +1763,7 @@ static bool isolate_page(struct page *page, struct list_head *pagelist) bool lru = PageLRU(page); if (PageHuge(page)) { - isolated = isolate_huge_page(page, pagelist); + isolated = !isolate_hugetlb(page, pagelist); } else { if (lru) isolated = !isolate_lru_page(page); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 6275b1c05f11..f0633f9a9116 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1288,7 +1288,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (PageHuge(page)) { pfn = page_to_pfn(head) + compound_nr(head) - 1; - isolate_huge_page(head, &source); + isolate_hugetlb(head, &source); continue; } else if (PageTransHuge(page)) pfn = page_to_pfn(head) + thp_nr_pages(page) - 1; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f9f47449e8dd..59d72b121346 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -623,7 +623,7 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) { - if (!isolate_huge_page(page, qp->pagelist) && + if (isolate_hugetlb(page, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* * Failed to isolate page but allow migrating pages diff --git a/mm/migrate.c b/mm/migrate.c index b716b8fa2c3f..fcb7eb6a6eca 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -164,7 +164,7 @@ void putback_movable_page(struct page *page) * * This function shall be used whenever the isolated pageset has been * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() - * and isolate_huge_page(). + * and isolate_hugetlb(). */ void putback_movable_pages(struct list_head *l) { @@ -1657,8 +1657,9 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, if (PageHuge(page)) { if (PageHead(page)) { - isolate_huge_page(page, pagelist); - err = 1; + err = isolate_hugetlb(page, pagelist); + if (!err) + err = 1; } } else { struct page *head; From dbe5a11954d8537ea0a0dc14f175353755b7eab0 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Thu, 26 Jan 2023 14:27:21 -0800 Subject: [PATCH 1284/4345] migrate: hugetlb: check for hugetlb shared PMD in node migration [ Upstream commit 73bdf65ea74857d7fb2ec3067a3cec0e261b1462 ] migrate_pages/mempolicy semantics state that CAP_SYS_NICE is required to move pages shared with another process to a different node. page_mapcount > 1 is being used to determine if a hugetlb page is shared. However, a hugetlb page will have a mapcount of 1 if mapped by multiple processes via a shared PMD. As a result, hugetlb pages shared by multiple processes and mapped with a shared PMD can be moved by a process without CAP_SYS_NICE. To fix, check for a shared PMD if mapcount is 1. If a shared PMD is found consider the page shared. Link: https://lkml.kernel.org/r/20230126222721.222195-3-mike.kravetz@oracle.com Fixes: e2d8cf405525 ("migrate: add hugepage migration code to migrate_pages()") Signed-off-by: Mike Kravetz Acked-by: Peter Xu Acked-by: David Hildenbrand Cc: James Houghton Cc: Matthew Wilcox Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Vishal Moola (Oracle) Cc: Yang Shi Cc: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- mm/mempolicy.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 59d72b121346..6c98585f20df 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -622,7 +622,8 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || - (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) { + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && + !hugetlb_pmd_shared(pte))) { if (isolate_hugetlb(page, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* From a1406d5aa39361b4f62edde1dfd8f86e1bdf1323 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 18 Jan 2023 16:35:13 -0500 Subject: [PATCH 1285/4345] btrfs: limit device extents to the device size commit 3c538de0f2a74d50aff7278c092f88ae59cee688 upstream. There was a recent regression in btrfs/177 that started happening with the size class patches ("btrfs: introduce size class to block group allocator"). This however isn't a regression introduced by those patches, but rather the bug was uncovered by a change in behavior in these patches. The patches triggered more chunk allocations in the ^free-space-tree case, which uncovered a race with device shrink. The problem is we will set the device total size to the new size, and use this to find a hole for a device extent. However during shrink we may have device extents allocated past this range, so we could potentially find a hole in a range past our new shrink size. We don't actually limit our found extent to the device size anywhere, we assume that we will not find a hole past our device size. This isn't true with shrink as we're relocating block groups and thus creating holes past the device size. Fix this by making sure we do not search past the new device size, and if we wander into any device extents that start after our device size simply break from the loop and use whatever hole we've already found. CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/volumes.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d4d89e0738ff..7a4373d27760 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1580,7 +1580,7 @@ again: goto out; } - while (1) { + while (search_start < search_end) { l = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(l)) { @@ -1603,6 +1603,9 @@ again: if (key.type != BTRFS_DEV_EXTENT_KEY) goto next; + if (key.offset > search_end) + break; + if (key.offset > search_start) { hole_size = key.offset - search_start; dev_extent_hole_check(device, &search_start, &hole_size, @@ -1663,6 +1666,7 @@ next: else ret = 0; + ASSERT(max_hole_start + max_hole_size <= search_end); out: btrfs_free_path(path); *start = max_hole_start; From f1fd16cd975397e8998660b4413d73280afabfe3 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Tue, 24 Jan 2023 12:32:34 +0100 Subject: [PATCH 1286/4345] btrfs: zlib: zero-initialize zlib workspace commit eadd7deca0ad8a83edb2b894d8326c78e78635d6 upstream. KMSAN reports uses of uninitialized memory in zlib's longest_match() called on memory originating from zlib_alloc_workspace(). This issue is known by zlib maintainers and is claimed to be harmless, but to be on the safe side we'd better initialize the memory. Link: https://zlib.net/zlib_faq.html#faq36 Reported-by: syzbot+14d9e7602ebdf7ec0a60@syzkaller.appspotmail.com CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Alexander Potapenko Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/zlib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 05615a1099db..673d74d7f718 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -63,7 +63,7 @@ struct list_head *zlib_alloc_workspace(unsigned int level) workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL), zlib_inflate_workspacesize()); - workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL); + workspace->strm.workspace = kvzalloc(workspacesize, GFP_KERNEL); workspace->level = level; workspace->buf = NULL; /* From 1c657623990666a4f4117640a12b41fb29cd9575 Mon Sep 17 00:00:00 2001 From: Edson Juliano Drosdeck Date: Tue, 7 Feb 2023 15:37:20 -0300 Subject: [PATCH 1287/4345] ALSA: hda/realtek: Add Positivo N14KP6-TG commit 88d18b8896bd98e636b632f805b7e84e61458255 upstream. Positivo N14KP6-TG (1c6c:1251) require quirk for enabling headset-mic Signed-off-by: Edson Juliano Drosdeck Cc: Link: https://lore.kernel.org/r/20230207183720.2519-1-edson.drosdeck@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index ae9ab6d2ae76..dc5ad4d1b6a8 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9261,6 +9261,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), + SND_PCI_QUIRK(0x1c6c, 0x1251, "Positivo N14KP6-TG", ALC288_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS), SND_PCI_QUIRK(0x1d05, 0x1096, "TongFang GMxMRxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x1100, "TongFang GKxNRxx", ALC269_FIXUP_NO_SHUTUP), From e1646e2be9561469ff26c11295ad14b6c32e670f Mon Sep 17 00:00:00 2001 From: Artemii Karasev Date: Tue, 7 Feb 2023 18:20:26 +0500 Subject: [PATCH 1288/4345] ALSA: emux: Avoid potential array out-of-bound in snd_emux_xg_control() commit 6a32425f953b955b4ff82f339d01df0b713caa5d upstream. snd_emux_xg_control() can be called with an argument 'param' greater than size of 'control' array. It may lead to accessing 'control' array at a wrong index. Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Artemii Karasev Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: Link: https://lore.kernel.org/r/20230207132026.2870-1-karasev@ispras.ru Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/synth/emux/emux_nrpn.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/synth/emux/emux_nrpn.c b/sound/synth/emux/emux_nrpn.c index 7eed5791972c..a7d83182f7d2 100644 --- a/sound/synth/emux/emux_nrpn.c +++ b/sound/synth/emux/emux_nrpn.c @@ -349,6 +349,9 @@ int snd_emux_xg_control(struct snd_emux_port *port, struct snd_midi_channel *chan, int param) { + if (param >= ARRAY_SIZE(chan->control)) + return -EINVAL; + return send_converted_effect(xg_effects, ARRAY_SIZE(xg_effects), port, chan, param, chan->control[param], From 35452bf986ab016b368d80e91e5ee1b339a4fd8f Mon Sep 17 00:00:00 2001 From: Guillaume Pinot Date: Sun, 29 Jan 2023 18:13:38 +0100 Subject: [PATCH 1289/4345] ALSA: hda/realtek: Fix the speaker output on Samsung Galaxy Book2 Pro 360 commit bd401fd730cbcb0717bbc5438f15084db10f9259 upstream. Samsung Galaxy Book2 Pro 360 (13" 2022 NP930QED-KA1FR) with codec SSID 144d:ca03 requires the same workaround for enabling the speaker amp like other Samsung models with ALC298 codec. Cc: Signed-off-by: Guillaume Pinot Link: https://lore.kernel.org/r/20230129171338.17249-1-texitoi@texitoi.eu Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index dc5ad4d1b6a8..d66d2cf7708e 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9090,6 +9090,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc832, "Samsung Galaxy Book Flex Alpha (NP730QCJ)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xca03, "Samsung Galaxy Book2 Pro 360 (NP930QED)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), From b7d5fa8052ad9278d21115db43950c01c92e4059 Mon Sep 17 00:00:00 2001 From: Shiju Jose Date: Thu, 2 Feb 2023 18:23:09 +0000 Subject: [PATCH 1290/4345] tracing: Fix poll() and select() do not work on per_cpu trace_pipe and trace_pipe_raw commit 3e46d910d8acf94e5360126593b68bf4fee4c4a1 upstream. poll() and select() on per_cpu trace_pipe and trace_pipe_raw do not work since kernel 6.1-rc6. This issue is seen after the commit 42fb0a1e84ff525ebe560e2baf9451ab69127e2b ("tracing/ring-buffer: Have polling block on watermark"). This issue is firstly detected and reported, when testing the CXL error events in the rasdaemon and also erified using the test application for poll() and select(). This issue occurs for the per_cpu case, when calling the ring_buffer_poll_wait(), in kernel/trace/ring_buffer.c, with the buffer_percent > 0 and then wait until the percentage of pages are available. The default value set for the buffer_percent is 50 in the kernel/trace/trace.c. As a fix, allow userspace application could set buffer_percent as 0 through the buffer_percent_fops, so that the task will wake up as soon as data is added to any of the specific cpu buffer. Link: https://lore.kernel.org/linux-trace-kernel/20230202182309.742-2-shiju.jose@huawei.com Cc: Cc: Cc: Cc: stable@vger.kernel.org Fixes: 42fb0a1e84ff5 ("tracing/ring-buffer: Have polling block on watermark") Signed-off-by: Shiju Jose Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f06d48be5a96..8637eab2986e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8569,9 +8569,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf, if (val > 100) return -EINVAL; - if (!val) - val = 1; - tr->buffer_percent = val; (*ppos)++; From edaf5c718314386f8ac4fd083538963bd984afa9 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sat, 28 Jan 2023 17:47:50 +0000 Subject: [PATCH 1291/4345] of/address: Return an error when no valid dma-ranges are found commit f6933c01e42d2fc83b9133ed755609e4aac6eadd upstream. Commit 7a8b64d17e35 ("of/address: use range parser for of_dma_get_range") converted the parsing of dma-range properties to use code shared with the PCI range parser. The intent was to introduce no functional changes however in the case where we fail to translate the first resource instead of returning -EINVAL the new code we return 0. Restore the previous behaviour by returning an error if we find no valid ranges, the original code only handled the first range but subsequently support for parsing all supplied ranges was added. This avoids confusing code using the parsed ranges which doesn't expect to successfully parse ranges but have only a list terminator returned, this fixes breakage with so far as I can tell all DMA for on SoC devices on the Socionext Synquacer platform which has a firmware supplied DT. A bisect identified the original conversion as triggering the issues there. Fixes: 7a8b64d17e35 ("of/address: use range parser for of_dma_get_range") Signed-off-by: Mark Brown Cc: Luca Di Stefano Cc: 993612@bugs.debian.org Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230126-synquacer-boot-v2-1-cb80fd23c4e2@kernel.org Signed-off-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- drivers/of/address.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/drivers/of/address.c b/drivers/of/address.c index 73ddf2540f3f..f686fb5011b8 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -990,8 +990,19 @@ int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map) } of_dma_range_parser_init(&parser, node); - for_each_of_range(&parser, &range) + for_each_of_range(&parser, &range) { + if (range.cpu_addr == OF_BAD_ADDR) { + pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n", + range.bus_addr, node); + continue; + } num_ranges++; + } + + if (!num_ranges) { + ret = -EINVAL; + goto out; + } r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL); if (!r) { @@ -1000,18 +1011,16 @@ int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map) } /* - * Record all info in the generic DMA ranges array for struct device. + * Record all info in the generic DMA ranges array for struct device, + * returning an error if we don't find any parsable ranges. */ *map = r; of_dma_range_parser_init(&parser, node); for_each_of_range(&parser, &range) { pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n", range.bus_addr, range.cpu_addr, range.size); - if (range.cpu_addr == OF_BAD_ADDR) { - pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n", - range.bus_addr, node); + if (range.cpu_addr == OF_BAD_ADDR) continue; - } r->cpu_start = range.cpu_addr; r->dma_start = range.bus_addr; r->size = range.size; From bc9771cd63981c42b674abda1ab6f35181eb8be0 Mon Sep 17 00:00:00 2001 From: Devid Antonio Filoni Date: Fri, 25 Nov 2022 18:04:18 +0100 Subject: [PATCH 1292/4345] can: j1939: do not wait 250 ms if the same addr was already claimed commit 4ae5e1e97c44f4654516c1d41591a462ed62fa7b upstream. The ISO 11783-5 standard, in "4.5.2 - Address claim requirements", states: d) No CF shall begin, or resume, transmission on the network until 250 ms after it has successfully claimed an address except when responding to a request for address-claimed. But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim prioritization" show that the CF begins the transmission after 250 ms from the first AC (address-claimed) message even if it sends another AC message during that time window to resolve the address contention with another CF. As stated in "4.4.2.3 - Address-claimed message": In order to successfully claim an address, the CF sending an address claimed message shall not receive a contending claim from another CF for at least 250 ms. As stated in "4.4.3.2 - NAME management (NM) message": 1) A commanding CF can d) request that a CF with a specified NAME transmit the address- claimed message with its current NAME. 2) A target CF shall d) send an address-claimed message in response to a request for a matching NAME Taking the above arguments into account, the 250 ms wait is requested only during network initialization. Do not restart the timer on AC message if both the NAME and the address match and so if the address has already been claimed (timer has expired) or the AC message has been sent to resolve the contention with another CF (timer is still running). Signed-off-by: Devid Antonio Filoni Acked-by: Oleksij Rempel Link: https://lore.kernel.org/all/20221125170418.34575-1-devid.filoni@egluetechnologies.com Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/j1939/address-claim.c | 40 +++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c index f33c47327927..ca4ad6cdd5cb 100644 --- a/net/can/j1939/address-claim.c +++ b/net/can/j1939/address-claim.c @@ -165,6 +165,46 @@ static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb) * leaving this function. */ ecu = j1939_ecu_get_by_name_locked(priv, name); + + if (ecu && ecu->addr == skcb->addr.sa) { + /* The ISO 11783-5 standard, in "4.5.2 - Address claim + * requirements", states: + * d) No CF shall begin, or resume, transmission on the + * network until 250 ms after it has successfully claimed + * an address except when responding to a request for + * address-claimed. + * + * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim + * prioritization" show that the CF begins the transmission + * after 250 ms from the first AC (address-claimed) message + * even if it sends another AC message during that time window + * to resolve the address contention with another CF. + * + * As stated in "4.4.2.3 - Address-claimed message": + * In order to successfully claim an address, the CF sending + * an address claimed message shall not receive a contending + * claim from another CF for at least 250 ms. + * + * As stated in "4.4.3.2 - NAME management (NM) message": + * 1) A commanding CF can + * d) request that a CF with a specified NAME transmit + * the address-claimed message with its current NAME. + * 2) A target CF shall + * d) send an address-claimed message in response to a + * request for a matching NAME + * + * Taking the above arguments into account, the 250 ms wait is + * requested only during network initialization. + * + * Do not restart the timer on AC message if both the NAME and + * the address match and so if the address has already been + * claimed (timer has expired) or the AC message has been sent + * to resolve the contention with another CF (timer is still + * running). + */ + goto out_ecu_put; + } + if (!ecu && j1939_address_is_unicast(skcb->addr.sa)) ecu = j1939_ecu_create_locked(priv, name); From 3797e94c1992c92038911df5efdab2b4496bb1e9 Mon Sep 17 00:00:00 2001 From: Anastasia Belova Date: Tue, 10 Jan 2023 12:14:50 +0300 Subject: [PATCH 1293/4345] xfrm: compat: change expression for switch in xfrm_xlate64 [ Upstream commit eb6c59b735aa6cca77cdbb59cc69d69a0d63d986 ] Compare XFRM_MSG_NEWSPDINFO (value from netlink configuration messages enum) with nlh_src->nlmsg_type instead of nlh_src->nlmsg_type - XFRM_MSG_BASE. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 4e9505064f58 ("net/xfrm/compat: Copy xfrm_spdattr_type_t atributes") Signed-off-by: Anastasia Belova Acked-by: Dmitry Safonov <0x7f454c46@gmail.com> Tested-by: Dmitry Safonov <0x7f454c46@gmail.com> Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a0f62fa02e06..12405aa5bce8 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -302,7 +302,7 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) nla_for_each_attr(nla, attrs, len, remaining) { int err; - switch (type) { + switch (nlh_src->nlmsg_type) { case XFRM_MSG_NEWSPDINFO: err = xfrm_nla_cpy(dst, nla, nla_len(nla)); break; From 79b595d9591426156a9e0635a5b5115508a36fef Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Thu, 12 Jan 2023 13:16:02 -0500 Subject: [PATCH 1294/4345] IB/hfi1: Restore allocated resources on failed copyout [ Upstream commit 6601fc0d15ffc20654e39486f9bef35567106d68 ] Fix a resource leak if an error occurs. Fixes: f404ca4c7ea8 ("IB/hfi1: Refactor hfi_user_exp_rcv_setup() IOCTL") Signed-off-by: Dean Luick Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/167354736291.2132367.10894218740150168180.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/file_ops.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index d84b1098762c..7828fb593120 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -1359,12 +1359,15 @@ static int user_exp_rcv_setup(struct hfi1_filedata *fd, unsigned long arg, addr = arg + offsetof(struct hfi1_tid_info, tidcnt); if (copy_to_user((void __user *)addr, &tinfo.tidcnt, sizeof(tinfo.tidcnt))) - return -EFAULT; + ret = -EFAULT; addr = arg + offsetof(struct hfi1_tid_info, length); - if (copy_to_user((void __user *)addr, &tinfo.length, + if (!ret && copy_to_user((void __user *)addr, &tinfo.length, sizeof(tinfo.length))) ret = -EFAULT; + + if (ret) + hfi1_user_exp_rcv_invalid(fd, &tinfo); } return ret; From a893cc644812728e86e9aff517fd5698812ecef0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Jan 2023 13:02:49 +0000 Subject: [PATCH 1295/4345] xfrm/compat: prevent potential spectre v1 gadget in xfrm_xlate32_attr() [ Upstream commit b6ee896385380aa621102e8ea402ba12db1cabff ] int type = nla_type(nla); if (type > XFRMA_MAX) { return -EOPNOTSUPP; } @type is then used as an array index and can be used as a Spectre v1 gadget. if (nla_len(nla) < compat_policy[type].len) { array_index_nospec() can be used to prevent leaking content of kernel memory to malicious users. Fixes: 5106f4a8acff ("xfrm/compat: Add 32=>64-bit messages translator") Signed-off-by: Eric Dumazet Cc: Dmitry Safonov Cc: Steffen Klassert Reviewed-by: Dmitry Safonov Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_compat.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 12405aa5bce8..8cbf45a8bcdc 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -5,6 +5,7 @@ * Based on code and translator idea by: Florian Westphal */ #include +#include #include #include @@ -437,6 +438,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } + type = array_index_nospec(type, XFRMA_MAX + 1); if (nla_len(nla) < compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; From b1afb666c32931667c15ad1b58e7203f0119dcaf Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Tue, 24 Jan 2023 20:24:18 +0200 Subject: [PATCH 1296/4345] IB/IPoIB: Fix legacy IPoIB due to wrong number of queues [ Upstream commit e632291a2dbce45a24cddeb5fe28fe71d724ba43 ] The cited commit creates child PKEY interfaces over netlink will multiple tx and rx queues, but some devices doesn't support more than 1 tx and 1 rx queues. This causes to a crash when traffic is sent over the PKEY interface due to the parent having a single queue but the child having multiple queues. This patch fixes the number of queues to 1 for legacy IPoIB at the earliest possible point in time. BUG: kernel NULL pointer dereference, address: 000000000000036b PGD 0 P4D 0 Oops: 0000 [#1] SMP CPU: 4 PID: 209665 Comm: python3 Not tainted 6.1.0_for_upstream_min_debug_2022_12_12_17_02 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:kmem_cache_alloc+0xcb/0x450 Code: ce 7e 49 8b 50 08 49 83 78 10 00 4d 8b 28 0f 84 cb 02 00 00 4d 85 ed 0f 84 c2 02 00 00 41 8b 44 24 28 48 8d 4a 01 49 8b 3c 24 <49> 8b 5c 05 00 4c 89 e8 65 48 0f c7 0f 0f 94 c0 84 c0 74 b8 41 8b RSP: 0018:ffff88822acbbab8 EFLAGS: 00010202 RAX: 0000000000000070 RBX: ffff8881c28e3e00 RCX: 00000000064f8dae RDX: 00000000064f8dad RSI: 0000000000000a20 RDI: 0000000000030d00 RBP: 0000000000000a20 R08: ffff8882f5d30d00 R09: ffff888104032f40 R10: ffff88810fade828 R11: 736f6d6570736575 R12: ffff88810081c000 R13: 00000000000002fb R14: ffffffff817fc865 R15: 0000000000000000 FS: 00007f9324ff9700(0000) GS:ffff8882f5d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000036b CR3: 00000001125af004 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: skb_clone+0x55/0xd0 ip6_finish_output2+0x3fe/0x690 ip6_finish_output+0xfa/0x310 ip6_send_skb+0x1e/0x60 udp_v6_send_skb+0x1e5/0x420 udpv6_sendmsg+0xb3c/0xe60 ? ip_mc_finish_output+0x180/0x180 ? __switch_to_asm+0x3a/0x60 ? __switch_to_asm+0x34/0x60 sock_sendmsg+0x33/0x40 __sys_sendto+0x103/0x160 ? _copy_to_user+0x21/0x30 ? kvm_clock_get_cycles+0xd/0x10 ? ktime_get_ts64+0x49/0xe0 __x64_sys_sendto+0x25/0x30 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f9374f1ed14 Code: 42 41 f8 ff 44 8b 4c 24 2c 4c 8b 44 24 20 89 c5 44 8b 54 24 28 48 8b 54 24 18 b8 2c 00 00 00 48 8b 74 24 10 8b 7c 24 08 0f 05 <48> 3d 00 f0 ff ff 77 34 89 ef 48 89 44 24 08 e8 68 41 f8 ff 48 8b RSP: 002b:00007f9324ff7bd0 EFLAGS: 00000293 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007f9324ff7cc8 RCX: 00007f9374f1ed14 RDX: 00000000000002fb RSI: 00007f93000052f0 RDI: 0000000000000030 RBP: 0000000000000000 R08: 00007f9324ff7d40 R09: 000000000000001c R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000000000 R13: 000000012a05f200 R14: 0000000000000001 R15: 00007f9374d57bdc Fixes: dbc94a0fb817 ("IB/IPoIB: Fix queue count inconsistency for PKEY child interfaces") Signed-off-by: Dragos Tatulea Link: https://lore.kernel.org/r/95eb6b74c7cf49fa46281f9d056d685c9fa11d38.1674584576.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index abfab89423f4..35322d23fc34 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2188,6 +2188,14 @@ int ipoib_intf_init(struct ib_device *hca, u8 port, const char *name, rn->attach_mcast = ipoib_mcast_attach; rn->detach_mcast = ipoib_mcast_detach; rn->hca = hca; + + rc = netif_set_real_num_tx_queues(dev, 1); + if (rc) + goto out; + + rc = netif_set_real_num_rx_queues(dev, 1); + if (rc) + goto out; } priv->rn_ops = dev->netdev_ops; From 491b7a5fc8e28ceb0688191d611fe8037905f0fb Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Sun, 29 Jan 2023 17:37:57 +0800 Subject: [PATCH 1297/4345] RDMA/usnic: use iommu_map_atomic() under spin_lock() [ Upstream commit b7e08a5a63a11627601915473c3b569c1f6c6c06 ] usnic_uiom_map_sorted_intervals() is called under spin_lock(), iommu_map() might sleep, use iommu_map_atomic() to avoid potential sleep in atomic context. Fixes: e3cf00d0a87f ("IB/usnic: Add Cisco VIC low-level hardware driver") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20230129093757.637354-1-yangyingliang@huawei.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/usnic/usnic_uiom.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c index 760b254ba42d..48a57568cad6 100644 --- a/drivers/infiniband/hw/usnic/usnic_uiom.c +++ b/drivers/infiniband/hw/usnic/usnic_uiom.c @@ -281,8 +281,8 @@ iter_chunk: size = pa_end - pa_start + PAGE_SIZE; usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x", va_start, &pa_start, size, flags); - err = iommu_map(pd->domain, va_start, pa_start, - size, flags); + err = iommu_map_atomic(pd->domain, va_start, + pa_start, size, flags); if (err) { usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n", va_start, &pa_start, size, err); @@ -298,8 +298,8 @@ iter_chunk: size = pa - pa_start + PAGE_SIZE; usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x\n", va_start, &pa_start, size, flags); - err = iommu_map(pd->domain, va_start, pa_start, - size, flags); + err = iommu_map_atomic(pd->domain, va_start, + pa_start, size, flags); if (err) { usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n", va_start, &pa_start, size, err); From 30fdf660356f708917b722a9aa01d70d27d96280 Mon Sep 17 00:00:00 2001 From: Christian Hopps Date: Thu, 26 Jan 2023 11:33:50 -0500 Subject: [PATCH 1298/4345] xfrm: fix bug with DSCP copy to v6 from v4 tunnel [ Upstream commit 6028da3f125fec34425dbd5fec18e85d372b2af6 ] When copying the DSCP bits for decap-dscp into IPv6 don't assume the outer encap is always IPv6. Instead, as with the inner IPv4 case, copy the DSCP bits from the correctly saved "tos" value in the control block. Fixes: 227620e29509 ("[IPSEC]: Separate inner/outer mode processing on input") Signed-off-by: Christian Hopps Acked-by: Herbert Xu Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_input.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 77e82033ad70..fef99a1c5df1 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -277,8 +277,7 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)), - ipipv6_hdr(skb)); + ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); From cafa2ad4f1d71a0cc6e079f04ca2f786314fd7cc Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Thu, 2 Feb 2023 17:32:55 +0800 Subject: [PATCH 1299/4345] bonding: fix error checking in bond_debug_reregister() [ Upstream commit cbe83191d40d8925b7a99969d037d2a0caf69294 ] Since commit ff9fb72bc077 ("debugfs: return error values, not NULL") changed return value of debugfs_rename() in error cases from %NULL to %ERR_PTR(-ERROR), we should also check error values instead of NULL. Fixes: ff9fb72bc077 ("debugfs: return error values, not NULL") Signed-off-by: Qi Zheng Acked-by: Jay Vosburgh Link: https://lore.kernel.org/r/20230202093256.32458-1-zhengqi.arch@bytedance.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/bonding/bond_debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index f3f86ef68ae0..8b6cf2bf9025 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -76,7 +76,7 @@ void bond_debug_reregister(struct bonding *bond) d = debugfs_rename(bonding_debug_root, bond->debug_dir, bonding_debug_root, bond->dev->name); - if (d) { + if (!IS_ERR(d)) { bond->debug_dir = d; } else { netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n"); From 07097ad30b36b79ae23826291978a1775fb14f94 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 2 Feb 2023 21:45:36 +0100 Subject: [PATCH 1300/4345] net: phy: meson-gxl: use MMD access dummy stubs for GXL, internal PHY [ Upstream commit 69ff53e4a4c9498eeed7d1441f68a1481dc69251 ] Jerome provided the information that also the GXL internal PHY doesn't support MMD register access and EEE. MMD reads return 0xffff, what results in e.g. completely wrong ethtool --show-eee output. Therefore use the MMD dummy stubs. Fixes: d853d145ea3e ("net: phy: add an option to disable EEE advertisement") Suggested-by: Jerome Brunet Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/84432fe4-0be4-bc82-4e5c-557206b40f56@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/meson-gxl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index f7a9e6599a64..39151ec6f65e 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -235,6 +235,8 @@ static struct phy_driver meson_gxl_phy[] = { .config_intr = meson_gxl_config_intr, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, { PHY_ID_MATCH_EXACT(0x01803301), .name = "Meson G12A Internal PHY", From 4259a40827728a1749bffa46441ef75ca138961b Mon Sep 17 00:00:00 2001 From: Neel Patel Date: Thu, 2 Feb 2023 13:55:35 -0800 Subject: [PATCH 1301/4345] ionic: clean interrupt before enabling queue to avoid credit race [ Upstream commit e8797a058466b60fc5a3291b92430c93ba90eaff ] Clear the interrupt credits before enabling the queue rather than after to be sure that the enabled queue starts at 0 and that we don't wipe away possible credits after enabling the queue. Fixes: 0f3154e6bcb3 ("ionic: Add Tx and Rx handling") Signed-off-by: Neel Patel Signed-off-by: Shannon Nelson Reviewed-by: Leon Romanovsky Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index cb12d0171517..fcd4213c99b8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -257,6 +257,7 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) .oper = IONIC_Q_ENABLE, }, }; + int ret; idev = &lif->ionic->idev; dev = lif->ionic->dev; @@ -264,16 +265,24 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) dev_dbg(dev, "q_enable.index %d q_enable.qtype %d\n", ctx.cmd.q_control.index, ctx.cmd.q_control.type); + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); + + ret = ionic_adminq_post_wait(lif, &ctx); + if (ret) + return ret; + + if (qcq->napi.poll) + napi_enable(&qcq->napi); + if (qcq->flags & IONIC_QCQ_F_INTR) { irq_set_affinity_hint(qcq->intr.vector, &qcq->intr.affinity_mask); - napi_enable(&qcq->napi); - ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); } - return ionic_adminq_post_wait(lif, &ctx); + return 0; } static int ionic_qcq_disable(struct ionic_qcq *qcq, bool send_to_hw) From 34a5af788ed405992f829d33dbd818b8cca85681 Mon Sep 17 00:00:00 2001 From: "Herton R. Krzesinski" Date: Fri, 3 Feb 2023 13:04:48 -0300 Subject: [PATCH 1302/4345] uapi: add missing ip/ipv6 header dependencies for linux/stddef.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 03702d4d29be4e2510ec80b248dbbde4e57030d9 ] Since commit 58e0be1ef6118 ("net: use struct_group to copy ip/ipv6 header addresses"), ip and ipv6 headers started to use the __struct_group definition, which is defined at include/uapi/linux/stddef.h. However, linux/stddef.h isn't explicitly included in include/uapi/linux/{ip,ipv6}.h, which breaks build of xskxceiver bpf selftest if you install the uapi headers in the system: $ make V=1 xskxceiver -C tools/testing/selftests/bpf ... make: Entering directory '(...)/tools/testing/selftests/bpf' gcc -g -O0 -rdynamic -Wall -Werror (...) In file included from xskxceiver.c:79: /usr/include/linux/ip.h:103:9: error: expected specifier-qualifier-list before ‘__struct_group’ 103 | __struct_group(/* no tag */, addrs, /* no attrs */, | ^~~~~~~~~~~~~~ ... Include the missing dependency in ip.h and do the same for the ipv6.h header. Fixes: 58e0be1ef611 ("net: use struct_group to copy ip/ipv6 header addresses") Signed-off-by: Herton R. Krzesinski Reviewed-by: Carlos O'Donell Tested-by: Carlos O'Donell Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/uapi/linux/ip.h | 1 + include/uapi/linux/ipv6.h | 1 + 2 files changed, 2 insertions(+) diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index d2f143393780..860bbf6bf29c 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -18,6 +18,7 @@ #ifndef _UAPI_LINUX_IP_H #define _UAPI_LINUX_IP_H #include +#include #include #define IPTOS_TOS_MASK 0x1E diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 766ab5c8ee65..d44d0483fd73 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -4,6 +4,7 @@ #include #include +#include #include #include From 1ad4112c9fcf0bc08222b2b1614fba52ffd12255 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Mon, 30 Jan 2023 14:06:40 -0800 Subject: [PATCH 1303/4345] ice: Do not use WQ_MEM_RECLAIM flag for workqueue [ Upstream commit 4d159f7884f78b1aacb99b4fc37d1e3cb1194e39 ] When both ice and the irdma driver are loaded, a warning in check_flush_dependency is being triggered. This is due to ice driver workqueue being allocated with the WQ_MEM_RECLAIM flag and the irdma one is not. According to kernel documentation, this flag should be set if the workqueue will be involved in the kernel's memory reclamation flow. Since it is not, there is no need for the ice driver's WQ to have this flag set so remove it. Example trace: [ +0.000004] workqueue: WQ_MEM_RECLAIM ice:ice_service_task [ice] is flushing !WQ_MEM_RECLAIM infiniband:0x0 [ +0.000139] WARNING: CPU: 0 PID: 728 at kernel/workqueue.c:2632 check_flush_dependency+0x178/0x1a0 [ +0.000011] Modules linked in: bonding tls xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_cha in_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables nfnetlink bridge stp llc rfkill vfat fat intel_rapl_msr intel _rapl_common isst_if_common skx_edac nfit libnvdimm x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm irqbypass crct1 0dif_pclmul crc32_pclmul ghash_clmulni_intel rapl intel_cstate rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_ core_mod ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_cm iw_cm iTCO_wdt iTCO_vendor_support ipmi_ssif irdma mei_me ib_uverbs ib_core intel_uncore joydev pcspkr i2c_i801 acpi_ipmi mei lpc_ich i2c_smbus intel_pch_thermal ioatdma ipmi_si acpi_power_meter acpi_pad xfs libcrc32c sd_mod t10_pi crc64_rocksoft crc64 sg ahci ixgbe libahci ice i40e igb crc32c_intel mdio i2c_algo_bit liba ta dca wmi dm_mirror dm_region_hash dm_log dm_mod ipmi_devintf ipmi_msghandler fuse [ +0.000161] [last unloaded: bonding] [ +0.000006] CPU: 0 PID: 728 Comm: kworker/0:2 Tainted: G S 6.2.0-rc2_next-queue-13jan-00458-gc20aabd57164 #1 [ +0.000006] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0010.010620200716 01/06/2020 [ +0.000003] Workqueue: ice ice_service_task [ice] [ +0.000127] RIP: 0010:check_flush_dependency+0x178/0x1a0 [ +0.000005] Code: 89 8e 02 01 e8 49 3d 40 00 49 8b 55 18 48 8d 8d d0 00 00 00 48 8d b3 d0 00 00 00 4d 89 e0 48 c7 c7 e0 3b 08 9f e8 bb d3 07 01 <0f> 0b e9 be fe ff ff 80 3d 24 89 8e 02 00 0f 85 6b ff ff ff e9 06 [ +0.000004] RSP: 0018:ffff88810a39f990 EFLAGS: 00010282 [ +0.000005] RAX: 0000000000000000 RBX: ffff888141bc2400 RCX: 0000000000000000 [ +0.000004] RDX: 0000000000000001 RSI: dffffc0000000000 RDI: ffffffffa1213a80 [ +0.000003] RBP: ffff888194bf3400 R08: ffffed117b306112 R09: ffffed117b306112 [ +0.000003] R10: ffff888bd983088b R11: ffffed117b306111 R12: 0000000000000000 [ +0.000003] R13: ffff888111f84d00 R14: ffff88810a3943ac R15: ffff888194bf3400 [ +0.000004] FS: 0000000000000000(0000) GS:ffff888bd9800000(0000) knlGS:0000000000000000 [ +0.000003] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ +0.000003] CR2: 000056035b208b60 CR3: 000000017795e005 CR4: 00000000007706f0 [ +0.000003] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ +0.000003] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ +0.000002] PKRU: 55555554 [ +0.000003] Call Trace: [ +0.000002] [ +0.000003] __flush_workqueue+0x203/0x840 [ +0.000006] ? mutex_unlock+0x84/0xd0 [ +0.000008] ? __pfx_mutex_unlock+0x10/0x10 [ +0.000004] ? __pfx___flush_workqueue+0x10/0x10 [ +0.000006] ? mutex_lock+0xa3/0xf0 [ +0.000005] ib_cache_cleanup_one+0x39/0x190 [ib_core] [ +0.000174] __ib_unregister_device+0x84/0xf0 [ib_core] [ +0.000094] ib_unregister_device+0x25/0x30 [ib_core] [ +0.000093] irdma_ib_unregister_device+0x97/0xc0 [irdma] [ +0.000064] ? __pfx_irdma_ib_unregister_device+0x10/0x10 [irdma] [ +0.000059] ? up_write+0x5c/0x90 [ +0.000005] irdma_remove+0x36/0x90 [irdma] [ +0.000062] auxiliary_bus_remove+0x32/0x50 [ +0.000007] device_release_driver_internal+0xfa/0x1c0 [ +0.000005] bus_remove_device+0x18a/0x260 [ +0.000007] device_del+0x2e5/0x650 [ +0.000005] ? __pfx_device_del+0x10/0x10 [ +0.000003] ? mutex_unlock+0x84/0xd0 [ +0.000004] ? __pfx_mutex_unlock+0x10/0x10 [ +0.000004] ? _raw_spin_unlock+0x18/0x40 [ +0.000005] ice_unplug_aux_dev+0x52/0x70 [ice] [ +0.000160] ice_service_task+0x1309/0x14f0 [ice] [ +0.000134] ? __pfx___schedule+0x10/0x10 [ +0.000006] process_one_work+0x3b1/0x6c0 [ +0.000008] worker_thread+0x69/0x670 [ +0.000005] ? __kthread_parkme+0xec/0x110 [ +0.000007] ? __pfx_worker_thread+0x10/0x10 [ +0.000005] kthread+0x17f/0x1b0 [ +0.000005] ? __pfx_kthread+0x10/0x10 [ +0.000004] ret_from_fork+0x29/0x50 [ +0.000009] Fixes: 940b61af02f4 ("ice: Initialize PF and setup miscellaneous interrupt") Signed-off-by: Anirudh Venkataramanan Signed-off-by: Marcin Szycik Tested-by: Jakub Andrysiak Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f193709c8efc..c1465096239b 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4853,7 +4853,7 @@ static int __init ice_module_init(void) pr_info("%s\n", ice_driver_string); pr_info("%s\n", ice_copyright); - ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME); + ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; From 896bd85688b40e7242562b68b0fd13e4d29048b8 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 5 Feb 2023 21:24:08 +0200 Subject: [PATCH 1304/4345] net: mscc: ocelot: fix VCAP filters not matching on MAC with "protocol 802.1Q" [ Upstream commit f964f8399df29d3e3ced77177cf35131cd2491bf ] Alternative short title: don't instruct the hardware to match on EtherType with "protocol 802.1Q" flower filters. It doesn't work for the reasons detailed below. With a command such as the following: tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \ protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \ action vlan modify id 300 \ action goto chain $(IS2 0 0) the created filter is set by ocelot_flower_parse_key() to be of type OCELOT_VCAP_KEY_ETYPE, and etype is set to {value=0x8100, mask=0xffff}. This gets propagated all the way to is1_entry_set() which commits it to hardware (the VCAP_IS1_HK_ETYPE field of the key). Compare this to the case where src_mac isn't specified - the key type is OCELOT_VCAP_KEY_ANY, and is1_entry_set() doesn't populate VCAP_IS1_HK_ETYPE. The problem is that for VLAN-tagged frames, the hardware interprets the ETYPE field as holding the encapsulated VLAN protocol. So the above filter will only match those packets which have an encapsulated protocol of 0x8100, rather than all packets with VLAN ID 200 and the given src_mac. The reason why this is allowed to occur is because, although we have a block of code in ocelot_flower_parse_key() which sets "match_protocol" to false when VLAN keys are present, that code executes too late. There is another block of code, which executes for Ethernet addresses, and has a "goto finished_key_parsing" and skips the VLAN header parsing. By skipping it, "match_protocol" remains with the value it was initialized with, i.e. "true", and "proto" is set to f->common.protocol, or 0x8100. The concept of ignoring some keys rather than erroring out when they are present but can't be offloaded is dubious in itself, but is present since the initial commit fe3490e6107e ("net: mscc: ocelot: Hardware ofload for tc flower filter"), and it's outside of the scope of this patch to change that. The problem was introduced when the driver started to interpret the flower filter's protocol, and populate the VCAP filter's ETYPE field based on it. To fix this, it is sufficient to move the code that parses the VLAN keys earlier than the "goto finished_key_parsing" instruction. This will ensure that if we have a flower filter with both VLAN and Ethernet address keys, it won't match on ETYPE 0x8100, because the VLAN key parsing sets "match_protocol = false". Fixes: 86b956de119c ("net: mscc: ocelot: support matching on EtherType") Signed-off-by: Vladimir Oltean Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230205192409.1796428-1-vladimir.oltean@nxp.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/mscc/ocelot_flower.c | 24 +++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index b221b83ec5a6..e56e540ce05c 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -468,6 +468,18 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, flow_rule_match_control(rule, &match); } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + filter->key_type = OCELOT_VCAP_KEY_ANY; + filter->vlan.vid.value = match.key->vlan_id; + filter->vlan.vid.mask = match.mask->vlan_id; + filter->vlan.pcp.value[0] = match.key->vlan_priority; + filter->vlan.pcp.mask[0] = match.mask->vlan_priority; + match_protocol = false; + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match; @@ -600,18 +612,6 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, match_protocol = false; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_match_vlan match; - - flow_rule_match_vlan(rule, &match); - filter->key_type = OCELOT_VCAP_KEY_ANY; - filter->vlan.vid.value = match.key->vlan_id; - filter->vlan.vid.mask = match.mask->vlan_id; - filter->vlan.pcp.value[0] = match.key->vlan_priority; - filter->vlan.pcp.mask[0] = match.mask->vlan_priority; - match_protocol = false; - } - finished_key_parsing: if (match_protocol && proto != ETH_P_ALL) { if (filter->block_id == VCAP_ES0) { From 703c3efa4b0b50a9c6a3726026c0f528857db812 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Mon, 23 Jan 2023 16:06:32 +0200 Subject: [PATCH 1305/4345] net/mlx5e: IPoIB, Show unknown speed instead of error [ Upstream commit 8aa5f171d51c1cb69e5e3106df4dd1a446102823 ] ethtool is returning an error for unknown speeds for the IPoIB interface: $ ethtool ib0 netlink error: failed to retrieve link settings netlink error: Invalid argument netlink error: failed to retrieve link settings netlink error: Invalid argument Settings for ib0: Link detected: no After this change, ethtool will return success and show "unknown speed": $ ethtool ib0 Settings for ib0: Supported ports: [ ] Supported link modes: Not reported Supported pause frame use: No Supports auto-negotiation: No Supported FEC modes: Not reported Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: Not reported Speed: Unknown! Duplex: Full Auto-negotiation: off Port: Other PHYAD: 0 Transceiver: internal Link detected: no Fixes: eb234ee9d541 ("net/mlx5e: IPoIB, Add support for get_link_ksettings in ethtool") Signed-off-by: Dragos Tatulea Reviewed-by: Gal Pressman Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- .../net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index cac8f085b16d..2cf7f0fc170b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -166,16 +166,16 @@ static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) } } -static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) +static u32 mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) { int rate, width; rate = mlx5_ptys_rate_enum_to_int(ib_proto_oper); if (rate < 0) - return -EINVAL; + return SPEED_UNKNOWN; width = mlx5_ptys_width_enum_to_int(ib_link_width_oper); if (width < 0) - return -EINVAL; + return SPEED_UNKNOWN; return rate * width; } @@ -198,16 +198,13 @@ static int mlx5i_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); speed = mlx5i_get_speed_settings(ib_link_width_oper, ib_proto_oper); - if (speed < 0) - return -EINVAL; + link_ksettings->base.speed = speed; + link_ksettings->base.duplex = speed == SPEED_UNKNOWN ? DUPLEX_UNKNOWN : DUPLEX_FULL; - link_ksettings->base.duplex = DUPLEX_FULL; link_ksettings->base.port = PORT_OTHER; link_ksettings->base.autoneg = AUTONEG_DISABLE; - link_ksettings->base.speed = speed; - return 0; } From fac1fb80088ab9f6cae5a0480236d1d03fcfe002 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 9 Jan 2023 15:27:40 +0200 Subject: [PATCH 1306/4345] net/mlx5: fw_tracer, Clear load bit when freeing string DBs buffers [ Upstream commit db561fed6b8fa3878e74d5df6512a4a38152b63e ] Whenever the driver is reading the string DBs into buffers, the driver is setting the load bit, but the driver never clears this bit. As a result, in case load bit is on and the driver query the device for new string DBs, the driver won't read again the string DBs. Fix it by clearing the load bit when query the device for new string DBs. Fixes: 2d69356752ff ("net/mlx5: Add support for fw live patch event") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index f800e1ca5ba6..76232abfc786 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -64,6 +64,7 @@ static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer) MLX5_GET(mtrc_cap, out, num_string_trace); tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db); tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner); + tracer->str_db.loaded = false; for (i = 0; i < tracer->str_db.num_string_db; i++) { mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]); From 3eb04ef27811e334987cbf3de3dbad97cfe3a74d Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 25 Jan 2023 17:39:36 +0200 Subject: [PATCH 1307/4345] net/mlx5: fw_tracer, Zero consumer index when reloading the tracer [ Upstream commit 184e1e4474dbcfebc4dbd1fa823a329978f25506 ] When tracer is reloaded, the device will log the traces at the beginning of the log buffer. Also, driver is reading the log buffer in chunks in accordance to the consumer index. Hence, zero consumer index when reloading the tracer. Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload") Signed-off-by: Shay Drory Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 76232abfc786..40d7bfca3749 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -757,6 +757,7 @@ static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer) if (err) mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err); + tracer->buff.consumer_index = 0; return err; } @@ -821,7 +822,6 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work) mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner); if (tracer->owner) { tracer->owner = false; - tracer->buff.consumer_index = 0; return; } From c53f34ec3fbf3e9f67574118a6bb35ae1146f7ca Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Tue, 7 Feb 2023 18:26:34 +0000 Subject: [PATCH 1308/4345] rds: rds_rm_zerocopy_callback() use list_first_entry() [ Upstream commit f753a68980cf4b59a80fe677619da2b1804f526d ] rds_rm_zerocopy_callback() uses list_entry() on the head of a list causing a type confusion. Use list_first_entry() to actually access the first element of the rs_zcookie_queue list. Fixes: 9426bbc6de99 ("rds: use list structure to track information for zerocopy completion notification") Reviewed-by: Willem de Bruijn Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230202-rds-zerocopy-v3-1-83b0df974f9a@diag.uniroma1.it Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/rds/message.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/rds/message.c b/net/rds/message.c index 799034e0f513..b363ef13c75e 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ From 3914b71dad5a5527819f82f1d085f0087583bdeb Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 8 Feb 2023 11:21:10 +0800 Subject: [PATCH 1309/4345] selftests: forwarding: lib: quote the sysctl values [ Upstream commit 3a082086aa200852545cf15159213582c0c80eba ] When set/restore sysctl value, we should quote the value as some keys may have multi values, e.g. net.ipv4.ping_group_range Fixes: f5ae57784ba8 ("selftests: forwarding: lib: Add sysctl_set(), sysctl_restore()") Signed-off-by: Hangbin Liu Reviewed-by: Petr Machata Link: https://lore.kernel.org/r/20230208032110.879205-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- tools/testing/selftests/net/forwarding/lib.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 54020d05a62b..9605e158a0bf 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -731,14 +731,14 @@ sysctl_set() local value=$1; shift SYSCTL_ORIG[$key]=$(sysctl -n $key) - sysctl -qw $key=$value + sysctl -qw $key="$value" } sysctl_restore() { local key=$1; shift - sysctl -qw $key=${SYSCTL_ORIG["$key"]} + sysctl -qw $key="${SYSCTL_ORIG[$key]}" } forwarding_enable() From ef3edede7b732395db145735bf4feaa960573995 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 31 Jan 2023 13:02:13 +0300 Subject: [PATCH 1310/4345] ALSA: pci: lx6464es: fix a debug loop [ Upstream commit 5dac9f8dc25fefd9d928b98f6477ff3daefd73e3 ] This loop accidentally reuses the "i" iterator for both the inside and the outside loop. The value of MAX_STREAM_BUFFER is 5. I believe that chip->rmh.stat_len is in the 2-12 range. If the value of .stat_len is 4 or more then it will loop exactly one time, but if it's less then it is a forever loop. It looks like it was supposed to combined into one loop where conditions are checked. Fixes: 8e6320064c33 ("ALSA: lx_core: Remove useless #if 0 .. #endif") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/Y9jnJTis/mRFJAQp@kili Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/lx6464es/lx_core.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/sound/pci/lx6464es/lx_core.c b/sound/pci/lx6464es/lx_core.c index f884f5a6a61c..a49a3254f967 100644 --- a/sound/pci/lx6464es/lx_core.c +++ b/sound/pci/lx6464es/lx_core.c @@ -493,12 +493,11 @@ int lx_buffer_ask(struct lx6464es *chip, u32 pipe, int is_capture, dev_dbg(chip->card->dev, "CMD_08_ASK_BUFFERS: needed %d, freed %d\n", *r_needed, *r_freed); - for (i = 0; i < MAX_STREAM_BUFFER; ++i) { - for (i = 0; i != chip->rmh.stat_len; ++i) - dev_dbg(chip->card->dev, - " stat[%d]: %x, %x\n", i, - chip->rmh.stat[i], - chip->rmh.stat[i] & MASK_DATA_SIZE); + for (i = 0; i < MAX_STREAM_BUFFER && i < chip->rmh.stat_len; + ++i) { + dev_dbg(chip->card->dev, " stat[%d]: %x, %x\n", i, + chip->rmh.stat[i], + chip->rmh.stat[i] & MASK_DATA_SIZE); } } From 61f8a493c0760883f73565d7a23af5a18f2077b2 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Fri, 20 Jan 2023 09:48:56 +1030 Subject: [PATCH 1311/4345] pinctrl: aspeed: Fix confusing types in return value [ Upstream commit 287a344a11f1ebd31055cf9b22c88d7005f108d7 ] The function signature is int, but we return a bool. Instead return a negative errno as the kerneldoc suggests. Fixes: 4d3d0e4272d8 ("pinctrl: Add core support for Aspeed SoCs") Signed-off-by: Joel Stanley Reviewed-by: Andrew Jeffery Link: https://lore.kernel.org/r/20230119231856.52014-1-joel@jms.id.au Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/aspeed/pinctrl-aspeed.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c index e792318c3894..d26d85954627 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c @@ -121,7 +121,7 @@ static int aspeed_disable_sig(struct aspeed_pinmux_data *ctx, int ret = 0; if (!exprs) - return true; + return -EINVAL; while (*exprs && !ret) { ret = aspeed_sig_expr_disable(ctx, *exprs); From 6e2a0521e4e84a2698f2da3950fb5c5496a4d208 Mon Sep 17 00:00:00 2001 From: Maxim Korotkov Date: Fri, 18 Nov 2022 13:43:32 +0300 Subject: [PATCH 1312/4345] pinctrl: single: fix potential NULL dereference [ Upstream commit d2d73e6d4822140445ad4a7b1c6091e0f5fe703b ] Added checking of pointer "function" in pcs_set_mux(). pinmux_generic_get_function() can return NULL and the pointer "function" was dereferenced without checking against NULL. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 571aec4df5b7 ("pinctrl: single: Use generic pinmux helpers for managing functions") Signed-off-by: Maxim Korotkov Reviewed-by: Tony Lindgren Link: https://lore.kernel.org/r/20221118104332.943-1-korotkov.maxim.s@gmail.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-single.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index d139cd9e6d13..22e471933b37 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -372,6 +372,8 @@ static int pcs_set_mux(struct pinctrl_dev *pctldev, unsigned fselector, if (!pcs->fmask) return 0; function = pinmux_generic_get_function(pctldev, fselector); + if (!function) + return -EINVAL; func = function->data; if (!func) return -EINVAL; From 4863f46ddaf9ceca8acd0cb9d2f02a2c8e9c55ad Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Fri, 13 Jan 2023 21:59:42 +0300 Subject: [PATCH 1313/4345] spi: dw: Fix wrong FIFO level setting for long xfers [ Upstream commit c63b8fd14a7db719f8252038a790638728c4eb66 ] Due to using the u16 type in the min_t() macros the SPI transfer length will be cast to word before participating in the conditional statement implied by the macro. Thus if the transfer length is greater than 64KB the Tx/Rx FIFO threshold level value will be determined by the leftover of the truncated after the type-case length. In the worst case it will cause the dramatical performance drop due to the "Tx FIFO Empty" or "Rx FIFO Full" interrupts triggered on each xfer word sent/received to/from the bus. The problem can be easily fixed by specifying the unsigned int type in the min_t() macros thus preventing the possible data loss. Fixes: ea11370fffdf ("spi: dw: get TX level without an additional variable") Reported-by: Sergey Nazarov Signed-off-by: Serge Semin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230113185942.2516-1-Sergey.Semin@baikalelectronics.ru Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-dw-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c index c33866f747db..aa116cee1fd8 100644 --- a/drivers/spi/spi-dw-core.c +++ b/drivers/spi/spi-dw-core.c @@ -353,7 +353,7 @@ static void dw_spi_irq_setup(struct dw_spi *dws) * will be adjusted at the final stage of the IRQ-based SPI transfer * execution so not to lose the leftover of the incoming data. */ - level = min_t(u16, dws->fifo_len / 2, dws->tx_len); + level = min_t(unsigned int, dws->fifo_len / 2, dws->tx_len); dw_writel(dws, DW_SPI_TXFTLR, level); dw_writel(dws, DW_SPI_RXFTLR, level - 1); From bbc850904457567e5e3bf431e38dd039742887aa Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 6 Feb 2023 16:15:59 +0200 Subject: [PATCH 1314/4345] pinctrl: intel: Restore the pins that used to be in Direct IRQ mode [ Upstream commit a8520be3ffef3d25b53bf171a7ebe17ee0154175 ] If the firmware mangled the register contents too much, check the saved value for the Direct IRQ mode. If it matches, we will restore the pin state. Reported-by: Jim Minter Fixes: 6989ea4881c8 ("pinctrl: intel: Save and restore pins in "direct IRQ" mode") Tested-by: Jim Minter Signed-off-by: Andy Shevchenko Acked-by: Mika Westerberg Link: https://lore.kernel.org/r/20230206141558.20916-1-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/intel/pinctrl-intel.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index db9087c129c0..2ef9e2d8fd9c 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -1606,6 +1606,12 @@ const struct intel_pinctrl_soc_data *intel_pinctrl_get_soc_data(struct platform_ EXPORT_SYMBOL_GPL(intel_pinctrl_get_soc_data); #ifdef CONFIG_PM_SLEEP +static bool __intel_gpio_is_direct_irq(u32 value) +{ + return (value & PADCFG0_GPIROUTIOXAPIC) && (value & PADCFG0_GPIOTXDIS) && + (__intel_gpio_get_gpio_mode(value) == PADCFG0_PMODE_GPIO); +} + static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned int pin) { const struct pin_desc *pd = pin_desc_get(pctrl->pctldev, pin); @@ -1639,8 +1645,7 @@ static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned int * See https://bugzilla.kernel.org/show_bug.cgi?id=214749. */ value = readl(intel_get_padcfg(pctrl, pin, PADCFG0)); - if ((value & PADCFG0_GPIROUTIOXAPIC) && (value & PADCFG0_GPIOTXDIS) && - (__intel_gpio_get_gpio_mode(value) == PADCFG0_PMODE_GPIO)) + if (__intel_gpio_is_direct_irq(value)) return true; return false; @@ -1770,7 +1775,12 @@ int intel_pinctrl_resume_noirq(struct device *dev) for (i = 0; i < pctrl->soc->npins; i++) { const struct pinctrl_pin_desc *desc = &pctrl->soc->pins[i]; - if (!intel_pinctrl_should_save(pctrl, desc->number)) + if (!(intel_pinctrl_should_save(pctrl, desc->number) || + /* + * If the firmware mangled the register contents too much, + * check the saved value for the Direct IRQ mode. + */ + __intel_gpio_is_direct_irq(pads[i].padcfg0))) continue; intel_restore_padcfg(pctrl, desc->number, PADCFG0, pads[i].padcfg0); From 2b693fe3f760c87fd9768e759f6297f743a1b3b0 Mon Sep 17 00:00:00 2001 From: ZhaoLong Wang Date: Mon, 6 Feb 2023 09:10:09 +0800 Subject: [PATCH 1315/4345] cifs: Fix use-after-free in rdata->read_into_pages() commit aa5465aeca3c66fecdf7efcf554aed79b4c4b211 upstream. When the network status is unstable, use-after-free may occur when read data from the server. BUG: KASAN: use-after-free in readpages_fill_pages+0x14c/0x7e0 Call Trace: dump_stack_lvl+0x38/0x4c print_report+0x16f/0x4a6 kasan_report+0xb7/0x130 readpages_fill_pages+0x14c/0x7e0 cifs_readv_receive+0x46d/0xa40 cifs_demultiplex_thread+0x121c/0x1490 kthread+0x16b/0x1a0 ret_from_fork+0x2c/0x50 Allocated by task 2535: kasan_save_stack+0x22/0x50 kasan_set_track+0x25/0x30 __kasan_kmalloc+0x82/0x90 cifs_readdata_direct_alloc+0x2c/0x110 cifs_readdata_alloc+0x2d/0x60 cifs_readahead+0x393/0xfe0 read_pages+0x12f/0x470 page_cache_ra_unbounded+0x1b1/0x240 filemap_get_pages+0x1c8/0x9a0 filemap_read+0x1c0/0x540 cifs_strict_readv+0x21b/0x240 vfs_read+0x395/0x4b0 ksys_read+0xb8/0x150 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 79: kasan_save_stack+0x22/0x50 kasan_set_track+0x25/0x30 kasan_save_free_info+0x2e/0x50 __kasan_slab_free+0x10e/0x1a0 __kmem_cache_free+0x7a/0x1a0 cifs_readdata_release+0x49/0x60 process_one_work+0x46c/0x760 worker_thread+0x2a4/0x6f0 kthread+0x16b/0x1a0 ret_from_fork+0x2c/0x50 Last potentially related work creation: kasan_save_stack+0x22/0x50 __kasan_record_aux_stack+0x95/0xb0 insert_work+0x2b/0x130 __queue_work+0x1fe/0x660 queue_work_on+0x4b/0x60 smb2_readv_callback+0x396/0x800 cifs_abort_connection+0x474/0x6a0 cifs_reconnect+0x5cb/0xa50 cifs_readv_from_socket.cold+0x22/0x6c cifs_read_page_from_socket+0xc1/0x100 readpages_fill_pages.cold+0x2f/0x46 cifs_readv_receive+0x46d/0xa40 cifs_demultiplex_thread+0x121c/0x1490 kthread+0x16b/0x1a0 ret_from_fork+0x2c/0x50 The following function calls will cause UAF of the rdata pointer. readpages_fill_pages cifs_read_page_from_socket cifs_readv_from_socket cifs_reconnect __cifs_reconnect cifs_abort_connection mid->callback() --> smb2_readv_callback queue_work(&rdata->work) # if the worker completes first, # the rdata is freed cifs_readv_complete kref_put cifs_readdata_release kfree(rdata) return rdata->... # UAF in readpages_fill_pages() Similarly, this problem also occurs in the uncache_fill_pages(). Fix this by adjusts the order of condition judgment in the return statement. Signed-off-by: ZhaoLong Wang Cc: stable@vger.kernel.org Acked-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 144064dc0d38..5fe85dc0e265 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3539,7 +3539,7 @@ uncached_fill_pages(struct TCP_Server_Info *server, rdata->got_bytes += result; } - return rdata->got_bytes > 0 && result != -ECONNABORTED ? + return result != -ECONNABORTED && rdata->got_bytes > 0 ? rdata->got_bytes : result; } @@ -4302,7 +4302,7 @@ readpages_fill_pages(struct TCP_Server_Info *server, rdata->got_bytes += result; } - return rdata->got_bytes > 0 && result != -ECONNABORTED ? + return result != -ECONNABORTED && rdata->got_bytes > 0 ? rdata->got_bytes : result; } From 1be271c52bf3554edcb8d124d1f8c7f777ee5727 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 3 Feb 2023 14:32:09 -0500 Subject: [PATCH 1316/4345] net: USB: Fix wrong-direction WARNING in plusb.c commit 811d581194f7412eda97acc03d17fc77824b561f upstream. The syzbot fuzzer detected a bug in the plusb network driver: A zero-length control-OUT transfer was treated as a read instead of a write. In modern kernels this error provokes a WARNING: usb 1-1: BOGUS control dir, pipe 80000280 doesn't match bRequestType c0 WARNING: CPU: 0 PID: 4645 at drivers/usb/core/urb.c:411 usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 Modules linked in: CPU: 1 PID: 4645 Comm: dhcpcd Not tainted 6.2.0-rc6-syzkaller-00050-g9f266ccaa2f5 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 RIP: 0010:usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 ... Call Trace: usb_start_wait_urb+0x101/0x4b0 drivers/usb/core/message.c:58 usb_internal_control_msg drivers/usb/core/message.c:102 [inline] usb_control_msg+0x320/0x4a0 drivers/usb/core/message.c:153 __usbnet_read_cmd+0xb9/0x390 drivers/net/usb/usbnet.c:2010 usbnet_read_cmd+0x96/0xf0 drivers/net/usb/usbnet.c:2068 pl_vendor_req drivers/net/usb/plusb.c:60 [inline] pl_set_QuickLink_features drivers/net/usb/plusb.c:75 [inline] pl_reset+0x2f/0xf0 drivers/net/usb/plusb.c:85 usbnet_open+0xcc/0x5d0 drivers/net/usb/usbnet.c:889 __dev_open+0x297/0x4d0 net/core/dev.c:1417 __dev_change_flags+0x587/0x750 net/core/dev.c:8530 dev_change_flags+0x97/0x170 net/core/dev.c:8602 devinet_ioctl+0x15a2/0x1d70 net/ipv4/devinet.c:1147 inet_ioctl+0x33f/0x380 net/ipv4/af_inet.c:979 sock_do_ioctl+0xcc/0x230 net/socket.c:1169 sock_ioctl+0x1f8/0x680 net/socket.c:1286 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x197/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The fix is to call usbnet_write_cmd() instead of usbnet_read_cmd() and remove the USB_DIR_IN flag. Reported-and-tested-by: syzbot+2a0e7abd24f1eb90ce25@syzkaller.appspotmail.com Signed-off-by: Alan Stern Fixes: 090ffa9d0e90 ("[PATCH] USB: usbnet (9/9) module for pl2301/2302 cables") CC: stable@vger.kernel.org Link: https://lore.kernel.org/r/00000000000052099f05f3b3e298@google.com/ Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/plusb.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 17c9c63b8eeb..ce7862dac2b7 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -57,9 +57,7 @@ static inline int pl_vendor_req(struct usbnet *dev, u8 req, u8 val, u8 index) { - return usbnet_read_cmd(dev, req, - USB_DIR_IN | USB_TYPE_VENDOR | - USB_RECIP_DEVICE, + return usbnet_write_cmd(dev, req, USB_TYPE_VENDOR | USB_RECIP_DEVICE, val, index, NULL, 0); } From dd965ad39de494de5f4cbe02c3090401cb915791 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 20 Jan 2023 21:47:16 +0800 Subject: [PATCH 1317/4345] btrfs: free device in btrfs_close_devices for a single device filesystem commit 5f58d783fd7823b2c2d5954d1126e702f94bfc4c upstream. We have this check to make sure we don't accidentally add older devices that may have disappeared and re-appeared with an older generation from being added to an fs_devices (such as a replace source device). This makes sense, we don't want stale disks in our file system. However for single disks this doesn't really make sense. I've seen this in testing, but I was provided a reproducer from a project that builds btrfs images on loopback devices. The loopback device gets cached with the new generation, and then if it is re-used to generate a new file system we'll fail to mount it because the new fs is "older" than what we have in cache. Fix this by freeing the cache when closing the device for a single device filesystem. This will ensure that the mount command passed device path is scanned successfully during the next mount. CC: stable@vger.kernel.org # 5.10+ Reported-by: Daan De Meyer Signed-off-by: Josef Bacik Signed-off-by: Anand Jain Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/volumes.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 7a4373d27760..15435f983180 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -381,6 +381,7 @@ void btrfs_free_device(struct btrfs_device *device) static void free_fs_devices(struct btrfs_fs_devices *fs_devices) { struct btrfs_device *device; + WARN_ON(fs_devices->opened); while (!list_empty(&fs_devices->devices)) { device = list_entry(fs_devices->devices.next, @@ -1227,9 +1228,22 @@ void btrfs_close_devices(struct btrfs_fs_devices *fs_devices) mutex_lock(&uuid_mutex); close_fs_devices(fs_devices); - if (!fs_devices->opened) + if (!fs_devices->opened) { list_splice_init(&fs_devices->seed_list, &list); + /* + * If the struct btrfs_fs_devices is not assembled with any + * other device, it can be re-initialized during the next mount + * without the needing device-scan step. Therefore, it can be + * fully freed. + */ + if (fs_devices->num_devices == 1) { + list_del(&fs_devices->fs_list); + free_fs_devices(fs_devices); + } + } + + list_for_each_entry_safe(fs_devices, tmp, &list, seed_list) { close_fs_devices(fs_devices); list_del(&fs_devices->seed_list); From f25fa93e52367d78ced6b33cfe97c8044b6724be Mon Sep 17 00:00:00 2001 From: Mark Pearson Date: Wed, 8 Feb 2023 13:12:23 -0500 Subject: [PATCH 1318/4345] usb: core: add quirk for Alcor Link AK9563 smartcard reader commit 303e724d7b1e1a0a93daf0b1ab5f7c4f53543b34 upstream. The Alcor Link AK9563 smartcard reader used on some Lenovo platforms doesn't work. If LPM is enabled the reader will provide an invalid usb config descriptor. Added quirk to disable LPM. Verified fix on Lenovo P16 G1 and T14 G3 Tested-by: Miroslav Zatko Tested-by: Dennis Wassenberg Cc: stable@vger.kernel.org Signed-off-by: Dennis Wassenberg Signed-off-by: Mark Pearson Link: https://lore.kernel.org/r/20230208181223.1092654-1-mpearson-lenovo@squebb.ca Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/quirks.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 6d24d138cc77..4ac1c22f13be 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -527,6 +527,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* Alcor Link AK9563 SC Reader used in 2022 Lenovo ThinkPads */ + { USB_DEVICE(0x2ce3, 0x9563), .driver_info = USB_QUIRK_NO_LPM }, + /* DELL USB GEN2 */ { USB_DEVICE(0x413c, 0xb062), .driver_info = USB_QUIRK_NO_LPM | USB_QUIRK_RESET_RESUME }, From 4f518a4a79bddfd1f87fe62a85bdece5ee809614 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 8 Feb 2023 20:53:19 +0000 Subject: [PATCH 1319/4345] usb: typec: altmodes/displayport: Fix probe pin assign check commit 54e5c00a4eb0a4c663445b245f641bbfab142430 upstream. While checking Pin Assignments of the port and partner during probe, we don't take into account whether the peripheral is a plug or receptacle. This manifests itself in a mode entry failure on certain docks and dongles with captive cables. For instance, the Startech.com Type-C to DP dongle (Model #CDP2DP) advertises its DP VDO as 0x405. This would fail the Pin Assignment compatibility check, despite it supporting Pin Assignment C as a UFP. Update the check to use the correct DP Pin Assign macros that take the peripheral's receptacle bit into account. Fixes: c1e5c2f0cb8a ("usb: typec: altmodes/displayport: correct pin assignment for UFP receptacles") Cc: stable@vger.kernel.org Reported-by: Diana Zigterman Signed-off-by: Prashant Malani Link: https://lore.kernel.org/r/20230208205318.131385-1-pmalani@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index eed719cf5552..e8eaca5a84db 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -524,10 +524,10 @@ int dp_altmode_probe(struct typec_altmode *alt) /* FIXME: Port can only be DFP_U. */ /* Make sure we have compatiple pin configurations */ - if (!(DP_CAP_DFP_D_PIN_ASSIGN(port->vdo) & - DP_CAP_UFP_D_PIN_ASSIGN(alt->vdo)) && - !(DP_CAP_UFP_D_PIN_ASSIGN(port->vdo) & - DP_CAP_DFP_D_PIN_ASSIGN(alt->vdo))) + if (!(DP_CAP_PIN_ASSIGN_DFP_D(port->vdo) & + DP_CAP_PIN_ASSIGN_UFP_D(alt->vdo)) && + !(DP_CAP_PIN_ASSIGN_UFP_D(port->vdo) & + DP_CAP_PIN_ASSIGN_DFP_D(alt->vdo))) return -ENODEV; ret = sysfs_create_group(&alt->dev.kobj, &dp_altmode_group); From 6ff8b48253926147e441b9d0c833ca6494707d0b Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 7 Feb 2023 13:04:52 +0800 Subject: [PATCH 1320/4345] ceph: flush cap releases when the session is flushed commit e7d84c6a1296d059389f7342d9b4b7defb518d3a upstream. MDS expects the completed cap release prior to responding to the session flush for cache drop. Cc: stable@vger.kernel.org Link: http://tracker.ceph.com/issues/38009 Signed-off-by: Xiubo Li Reviewed-by: Venky Shankar Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- fs/ceph/mds_client.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index fa51872ff850..87a9e9096421 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3496,6 +3496,12 @@ static void handle_session(struct ceph_mds_session *session, break; case CEPH_SESSION_FLUSHMSG: + /* flush cap releases */ + spin_lock(&session->s_cap_lock); + if (session->s_num_cap_releases) + ceph_flush_cap_releases(mdsc, session); + spin_unlock(&session->s_cap_lock); + send_flushmsg_ack(mdsc, session, seq); break; From 8eee3521bca7104de4859b853d4358373291f681 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Thu, 26 Jan 2023 22:53:06 -0500 Subject: [PATCH 1321/4345] riscv: Fixup race condition on PG_dcache_clean in flush_icache_pte commit 950b879b7f0251317d26bae0687e72592d607532 upstream. In commit 588a513d3425 ("arm64: Fix race condition on PG_dcache_clean in __sync_icache_dcache()"), we found RISC-V has the same issue as the previous arm64. The previous implementation didn't guarantee the correct sequence of operations, which means flush_icache_all() hasn't been called when the PG_dcache_clean was set. That would cause a risk of page synchronization. Fixes: 08f051eda33b ("RISC-V: Flush I$ when making a dirty page executable") Signed-off-by: Guo Ren Signed-off-by: Guo Ren Reviewed-by: Andrew Jones Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230127035306.1819561-1-guoren@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/mm/cacheflush.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 89f81067e09e..2ae1201cff88 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -85,7 +85,9 @@ void flush_icache_pte(pte_t pte) { struct page *page = pte_page(pte); - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) + if (!test_bit(PG_dcache_clean, &page->flags)) { flush_icache_all(); + set_bit(PG_dcache_clean, &page->flags); + } } #endif /* CONFIG_MMU */ From 809f4acb7f015e087c60ea74b935e24a16779b0a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 9 Feb 2023 21:11:47 +0100 Subject: [PATCH 1322/4345] arm64: dts: meson-gx: Make mmc host controller interrupts level-sensitive commit 66e45351f7d6798751f98001d1fcd572024d87f0 upstream. The usage of edge-triggered interrupts lead to lost interrupts under load, see [0]. This was confirmed to be fixed by using level-triggered interrupts. The report was about SDIO. However, as the host controller is the same for SD and MMC, apply the change to all mmc controller instances. [0] https://www.spinics.net/lists/linux-mmc/msg73991.html Fixes: ef8d2ffedf18 ("ARM64: dts: meson-gxbb: add MMC support") Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Acked-by: Neil Armstrong Link: https://lore.kernel.org/r/76e042e0-a610-5ed5-209f-c4d7f879df44@gmail.com Signed-off-by: Neil Armstrong Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/amlogic/meson-gx.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 47cbb0a1eb18..88a7db5c55a0 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -595,21 +595,21 @@ sd_emmc_a: mmc@70000 { compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc"; reg = <0x0 0x70000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; }; sd_emmc_b: mmc@72000 { compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc"; reg = <0x0 0x72000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; }; sd_emmc_c: mmc@74000 { compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc"; reg = <0x0 0x74000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; }; }; From 5bfc8f09619a9c31f812d85efe13091afede97bc Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 9 Feb 2023 21:11:10 +0100 Subject: [PATCH 1323/4345] arm64: dts: meson-g12-common: Make mmc host controller interrupts level-sensitive commit ac8db4cceed218cca21c84f9d75ce88182d8b04f upstream. The usage of edge-triggered interrupts lead to lost interrupts under load, see [0]. This was confirmed to be fixed by using level-triggered interrupts. The report was about SDIO. However, as the host controller is the same for SD and MMC, apply the change to all mmc controller instances. [0] https://www.spinics.net/lists/linux-mmc/msg73991.html Fixes: 4759fd87b928 ("arm64: dts: meson: g12a: add mmc nodes") Tested-by: FUKAUMI Naoki Tested-by: Martin Blumenstingl Tested-by: Jerome Brunet Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Acked-by: Neil Armstrong Link: https://lore.kernel.org/r/27d89baa-b8fa-baca-541b-ef17a97cde3c@gmail.com Signed-off-by: Neil Armstrong Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index 075153a4d49f..2091db7c9b8a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -2317,7 +2317,7 @@ sd_emmc_a: sd@ffe03000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0xffe03000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_A>, <&clkc CLKID_SD_EMMC_A_CLK0>, @@ -2329,7 +2329,7 @@ sd_emmc_b: sd@ffe05000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0xffe05000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_B>, <&clkc CLKID_SD_EMMC_B_CLK0>, @@ -2341,7 +2341,7 @@ sd_emmc_c: mmc@ffe07000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0xffe07000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_C>, <&clkc CLKID_SD_EMMC_C_CLK0>, From 0ef2490a876b47c1e2db84ea3f4f69c8aca165f2 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 9 Feb 2023 21:10:31 +0100 Subject: [PATCH 1324/4345] arm64: dts: meson-axg: Make mmc host controller interrupts level-sensitive commit d182bcf300772d8b2e5f43e47fa0ebda2b767cc4 upstream. The usage of edge-triggered interrupts lead to lost interrupts under load, see [0]. This was confirmed to be fixed by using level-triggered interrupts. The report was about SDIO. However, as the host controller is the same for SD and MMC, apply the change to all mmc controller instances. [0] https://www.spinics.net/lists/linux-mmc/msg73991.html Fixes: 221cf34bac54 ("ARM64: dts: meson-axg: enable the eMMC controller") Reported-by: Peter Suti Tested-by: Vyacheslav Bocharov Tested-by: Peter Suti Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Acked-by: Neil Armstrong Link: https://lore.kernel.org/r/c00655d3-02f8-6f5f-4239-ca2412420cad@gmail.com Signed-off-by: Neil Armstrong Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/amlogic/meson-axg.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index fae48efae83e..5c75fbf0d470 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -1754,7 +1754,7 @@ sd_emmc_b: sd@5000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0x5000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_B>, <&clkc CLKID_SD_EMMC_B_CLK0>, @@ -1766,7 +1766,7 @@ sd_emmc_c: mmc@7000 { compatible = "amlogic,meson-axg-mmc"; reg = <0x0 0x7000 0x0 0x800>; - interrupts = ; + interrupts = ; status = "disabled"; clocks = <&clkc CLKID_SD_EMMC_C>, <&clkc CLKID_SD_EMMC_C_CLK0>, From 0a626e27f984dfbe96bd8e4fd08f20a2ede3ea23 Mon Sep 17 00:00:00 2001 From: David Chen Date: Thu, 9 Feb 2023 17:48:28 +0000 Subject: [PATCH 1325/4345] Fix page corruption caused by racy check in __free_pages commit 462a8e08e0e6287e5ce13187257edbf24213ed03 upstream. When we upgraded our kernel, we started seeing some page corruption like the following consistently: BUG: Bad page state in process ganesha.nfsd pfn:1304ca page:0000000022261c55 refcount:0 mapcount:-128 mapping:0000000000000000 index:0x0 pfn:0x1304ca flags: 0x17ffffc0000000() raw: 0017ffffc0000000 ffff8a513ffd4c98 ffffeee24b35ec08 0000000000000000 raw: 0000000000000000 0000000000000001 00000000ffffff7f 0000000000000000 page dumped because: nonzero mapcount CPU: 0 PID: 15567 Comm: ganesha.nfsd Kdump: loaded Tainted: P B O 5.10.158-1.nutanix.20221209.el7.x86_64 #1 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/05/2016 Call Trace: dump_stack+0x74/0x96 bad_page.cold+0x63/0x94 check_new_page_bad+0x6d/0x80 rmqueue+0x46e/0x970 get_page_from_freelist+0xcb/0x3f0 ? _cond_resched+0x19/0x40 __alloc_pages_nodemask+0x164/0x300 alloc_pages_current+0x87/0xf0 skb_page_frag_refill+0x84/0x110 ... Sometimes, it would also show up as corruption in the free list pointer and cause crashes. After bisecting the issue, we found the issue started from commit e320d3012d25 ("mm/page_alloc.c: fix freeing non-compound pages"): if (put_page_testzero(page)) free_the_page(page, order); else if (!PageHead(page)) while (order-- > 0) free_the_page(page + (1 << order), order); So the problem is the check PageHead is racy because at this point we already dropped our reference to the page. So even if we came in with compound page, the page can already be freed and PageHead can return false and we will end up freeing all the tail pages causing double free. Fixes: e320d3012d25 ("mm/page_alloc.c: fix freeing non-compound pages") Link: https://lore.kernel.org/lkml/BYAPR02MB448855960A9656EEA81141FC94D99@BYAPR02MB4488.namprd02.prod.outlook.com/ Cc: Andrew Morton Cc: stable@vger.kernel.org Signed-off-by: Chunwei Chen Reviewed-by: Vlastimil Babka Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/page_alloc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a56f2b9df5a0..1fd41b91a1a8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5054,9 +5054,12 @@ static inline void free_the_page(struct page *page, unsigned int order) void __free_pages(struct page *page, unsigned int order) { + /* get PageHead before we drop reference */ + int head = PageHead(page); + if (put_page_testzero(page)) free_the_page(page, order); - else if (!PageHead(page)) + else if (!head) while (order-- > 0) free_the_page(page + (1 << order), order); } From 707c48210a5384a72c82655a37895b7e822755f2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 15 Feb 2023 17:22:27 +0100 Subject: [PATCH 1326/4345] Linux 5.10.168 Link: https://lore.kernel.org/r/20230213144745.696901179@linuxfoundation.org Tested-by: Pavel Machek (CIP) Tested-by: Shuah Khan Tested-by: Sudip Mukherjee Tested-by: Hulk Robot Link: https://lore.kernel.org/r/20230214172549.450713187@linuxfoundation.org Tested-by: Jon Hunter Tested-by: Guenter Roeck Tested-by: Linux Kernel Functional Testing Tested-by: Sudip Mukherjee Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 84b78e657357..af3270277fd0 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 167 +SUBLEVEL = 168 EXTRAVERSION = NAME = Dare mighty things From 5417a09eec771e8d0525a4bb7c4dfd599a6cfdba Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 31 Jan 2023 14:35:36 +0000 Subject: [PATCH 1327/4345] Revert "ASoC: Intel/SOF: use set_stream() instead of set_tdm_slots() for HDAudio" This reverts commit 185c141946e0fd1921638593181311b39b51255f which is commit 636110411ca726f19ef8e87b0be51bb9a4cdef06 upstream. The api used here is going away as it breaks the Android kernel api and isn't needed at this point in time. If it is needed in the future it can come back in an abi-safe way. Bug: 161946584 Change-Id: I6946ab6122a67c16af8ac3931633b8c57e9738df Signed-off-by: Greg Kroah-Hartman --- sound/soc/codecs/hdac_hda.c | 22 +++++++++++----------- sound/soc/intel/skylake/skl-pcm.c | 7 +++++-- sound/soc/sof/intel/hda-dai.c | 7 +++++-- 3 files changed, 21 insertions(+), 15 deletions(-) diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c index de5955db0a5f..390dd6c7f6a5 100644 --- a/sound/soc/codecs/hdac_hda.c +++ b/sound/soc/codecs/hdac_hda.c @@ -46,8 +46,9 @@ static int hdac_hda_dai_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai); static int hdac_hda_dai_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai); -static int hdac_hda_dai_set_stream(struct snd_soc_dai *dai, void *stream, - int direction); +static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai, + unsigned int tx_mask, unsigned int rx_mask, + int slots, int slot_width); static struct hda_pcm *snd_soc_find_pcm_from_dai(struct hdac_hda_priv *hda_pvt, struct snd_soc_dai *dai); @@ -57,7 +58,7 @@ static const struct snd_soc_dai_ops hdac_hda_dai_ops = { .prepare = hdac_hda_dai_prepare, .hw_params = hdac_hda_dai_hw_params, .hw_free = hdac_hda_dai_hw_free, - .set_stream = hdac_hda_dai_set_stream, + .set_tdm_slot = hdac_hda_dai_set_tdm_slot, }; static struct snd_soc_dai_driver hdac_hda_dais[] = { @@ -179,22 +180,21 @@ static struct snd_soc_dai_driver hdac_hda_dais[] = { }; -static int hdac_hda_dai_set_stream(struct snd_soc_dai *dai, - void *stream, int direction) +static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai, + unsigned int tx_mask, unsigned int rx_mask, + int slots, int slot_width) { struct snd_soc_component *component = dai->component; struct hdac_hda_priv *hda_pvt; struct hdac_hda_pcm *pcm; - struct hdac_stream *hstream; - - if (!stream) - return -EINVAL; hda_pvt = snd_soc_component_get_drvdata(component); pcm = &hda_pvt->pcm[dai->id]; - hstream = (struct hdac_stream *)stream; - pcm->stream_tag[direction] = hstream->stream_tag; + if (tx_mask) + pcm->stream_tag[SNDRV_PCM_STREAM_PLAYBACK] = tx_mask; + else + pcm->stream_tag[SNDRV_PCM_STREAM_CAPTURE] = rx_mask; return 0; } diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c index b531d9dfc2d6..b1897a057397 100644 --- a/sound/soc/intel/skylake/skl-pcm.c +++ b/sound/soc/intel/skylake/skl-pcm.c @@ -563,8 +563,11 @@ static int skl_link_hw_params(struct snd_pcm_substream *substream, stream_tag = hdac_stream(link_dev)->stream_tag; - /* set the hdac_stream in the codec dai */ - snd_soc_dai_set_stream(codec_dai, hdac_stream(link_dev), substream->stream); + /* set the stream tag in the codec dai dma params */ + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + snd_soc_dai_set_tdm_slot(codec_dai, stream_tag, 0, 0, 0); + else + snd_soc_dai_set_tdm_slot(codec_dai, 0, stream_tag, 0, 0); p_params.s_fmt = snd_pcm_format_width(params_format(params)); p_params.ch = params_channels(params); diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index de80f1b3d7f2..ef316311e959 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -236,8 +236,11 @@ static int hda_link_hw_params(struct snd_pcm_substream *substream, if (!link) return -EINVAL; - /* set the hdac_stream in the codec dai */ - snd_soc_dai_set_stream(codec_dai, hdac_stream(link_dev), substream->stream); + /* set the stream tag in the codec dai dma params */ + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + snd_soc_dai_set_tdm_slot(codec_dai, stream_tag, 0, 0, 0); + else + snd_soc_dai_set_tdm_slot(codec_dai, 0, stream_tag, 0, 0); p_params.s_fmt = snd_pcm_format_width(params_format(params)); p_params.ch = params_channels(params); From 2702f0975871af0e614f3d2354e36f4998c8f2e8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 16 Feb 2023 07:24:56 +0000 Subject: [PATCH 1328/4345] Revert "ASoC/SoundWire: dai: expand 'stream' concept beyond SoundWire" This reverts commit 8b20aab8cfd0fe311a5388765d43d0e5febbcc81 which is commit e8444560b4d9302a511f0996f4cfdf85b628f4ca upstream. It breaks the android kernel abi and is not needed for android at this point in time as SoundWire is not a supported configuration option. Bug: 161946584 Change-Id: I905ba0e6b70fb686eb9b578df3864302570bf4e7 Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/intel.c | 8 ++++---- drivers/soundwire/qcom.c | 8 ++++---- drivers/soundwire/stream.c | 4 ++-- include/sound/soc-dai.h | 32 ++++++++++++++++---------------- sound/soc/codecs/max98373-sdw.c | 2 +- sound/soc/codecs/rt1308-sdw.c | 2 +- sound/soc/codecs/rt5682-sdw.c | 2 +- sound/soc/codecs/rt700.c | 2 +- sound/soc/codecs/rt711.c | 2 +- sound/soc/codecs/rt715.c | 2 +- sound/soc/codecs/wsa881x.c | 2 +- sound/soc/intel/boards/sof_sdw.c | 6 +++--- sound/soc/qcom/sdm845.c | 4 ++-- 13 files changed, 38 insertions(+), 38 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 4487fbb8f2e6..942d2fe13218 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -1140,8 +1140,8 @@ static const struct snd_soc_dai_ops intel_pcm_dai_ops = { .prepare = intel_prepare, .hw_free = intel_hw_free, .shutdown = intel_shutdown, - .set_stream = intel_pcm_set_sdw_stream, - .get_stream = intel_get_sdw_stream, + .set_sdw_stream = intel_pcm_set_sdw_stream, + .get_sdw_stream = intel_get_sdw_stream, }; static const struct snd_soc_dai_ops intel_pdm_dai_ops = { @@ -1150,8 +1150,8 @@ static const struct snd_soc_dai_ops intel_pdm_dai_ops = { .prepare = intel_prepare, .hw_free = intel_hw_free, .shutdown = intel_shutdown, - .set_stream = intel_pdm_set_sdw_stream, - .get_stream = intel_get_sdw_stream, + .set_sdw_stream = intel_pdm_set_sdw_stream, + .get_sdw_stream = intel_get_sdw_stream, }; static const struct snd_soc_component_driver dai_component = { diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index ac73258792e6..6d22df01f354 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -649,8 +649,8 @@ static int qcom_swrm_startup(struct snd_pcm_substream *substream, ctrl->sruntime[dai->id] = sruntime; for_each_rtd_codec_dais(rtd, i, codec_dai) { - ret = snd_soc_dai_set_stream(codec_dai, sruntime, - substream->stream); + ret = snd_soc_dai_set_sdw_stream(codec_dai, sruntime, + substream->stream); if (ret < 0 && ret != -ENOTSUPP) { dev_err(dai->dev, "Failed to set sdw stream on %s", codec_dai->name); @@ -676,8 +676,8 @@ static const struct snd_soc_dai_ops qcom_swrm_pdm_dai_ops = { .hw_free = qcom_swrm_hw_free, .startup = qcom_swrm_startup, .shutdown = qcom_swrm_shutdown, - .set_stream = qcom_swrm_set_sdw_stream, - .get_stream = qcom_swrm_get_sdw_stream, + .set_sdw_stream = qcom_swrm_set_sdw_stream, + .get_sdw_stream = qcom_swrm_get_sdw_stream, }; static const struct snd_soc_component_driver qcom_swrm_dai_component = { diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 79554d28f08a..304ff2ee7d75 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -1860,7 +1860,7 @@ static int set_stream(struct snd_pcm_substream *substream, /* Set stream pointer on all DAIs */ for_each_rtd_dais(rtd, i, dai) { - ret = snd_soc_dai_set_stream(dai, sdw_stream, substream->stream); + ret = snd_soc_dai_set_sdw_stream(dai, sdw_stream, substream->stream); if (ret < 0) { dev_err(rtd->dev, "failed to set stream pointer on dai %s", dai->name); break; @@ -1931,7 +1931,7 @@ void sdw_shutdown_stream(void *sdw_substream) /* Find stream from first CPU DAI */ dai = asoc_rtd_to_cpu(rtd, 0); - sdw_stream = snd_soc_dai_get_stream(dai, substream->stream); + sdw_stream = snd_soc_dai_get_sdw_stream(dai, substream->stream); if (IS_ERR(sdw_stream)) { dev_err(rtd->dev, "no stream found for DAI %s", dai->name); diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index fe86172e8602..2150bd4c7a05 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -239,9 +239,9 @@ struct snd_soc_dai_ops { unsigned int *rx_num, unsigned int *rx_slot); int (*set_tristate)(struct snd_soc_dai *dai, int tristate); - int (*set_stream)(struct snd_soc_dai *dai, - void *stream, int direction); - void *(*get_stream)(struct snd_soc_dai *dai, int direction); + int (*set_sdw_stream)(struct snd_soc_dai *dai, + void *stream, int direction); + void *(*get_sdw_stream)(struct snd_soc_dai *dai, int direction); /* * DAI digital mute - optional. @@ -446,42 +446,42 @@ static inline void *snd_soc_dai_get_drvdata(struct snd_soc_dai *dai) } /** - * snd_soc_dai_set_stream() - Configures a DAI for stream operation + * snd_soc_dai_set_sdw_stream() - Configures a DAI for SDW stream operation * @dai: DAI - * @stream: STREAM (opaque structure depending on DAI type) + * @stream: STREAM * @direction: Stream direction(Playback/Capture) - * Some subsystems, such as SoundWire, don't have a notion of direction and we reuse + * SoundWire subsystem doesn't have a notion of direction and we reuse * the ASoC stream direction to configure sink/source ports. * Playback maps to source ports and Capture for sink ports. * * This should be invoked with NULL to clear the stream set previously. * Returns 0 on success, a negative error code otherwise. */ -static inline int snd_soc_dai_set_stream(struct snd_soc_dai *dai, - void *stream, int direction) +static inline int snd_soc_dai_set_sdw_stream(struct snd_soc_dai *dai, + void *stream, int direction) { - if (dai->driver->ops->set_stream) - return dai->driver->ops->set_stream(dai, stream, direction); + if (dai->driver->ops->set_sdw_stream) + return dai->driver->ops->set_sdw_stream(dai, stream, direction); else return -ENOTSUPP; } /** - * snd_soc_dai_get_stream() - Retrieves stream from DAI + * snd_soc_dai_get_sdw_stream() - Retrieves SDW stream from DAI * @dai: DAI * @direction: Stream direction(Playback/Capture) * * This routine only retrieves that was previously configured - * with snd_soc_dai_get_stream() + * with snd_soc_dai_get_sdw_stream() * * Returns pointer to stream or an ERR_PTR value, e.g. * ERR_PTR(-ENOTSUPP) if callback is not supported; */ -static inline void *snd_soc_dai_get_stream(struct snd_soc_dai *dai, - int direction) +static inline void *snd_soc_dai_get_sdw_stream(struct snd_soc_dai *dai, + int direction) { - if (dai->driver->ops->get_stream) - return dai->driver->ops->get_stream(dai, direction); + if (dai->driver->ops->get_sdw_stream) + return dai->driver->ops->get_sdw_stream(dai, direction); else return ERR_PTR(-ENOTSUPP); } diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c index a2bb93fb830b..39afa011f0e2 100644 --- a/sound/soc/codecs/max98373-sdw.c +++ b/sound/soc/codecs/max98373-sdw.c @@ -728,7 +728,7 @@ static int max98373_sdw_set_tdm_slot(struct snd_soc_dai *dai, static const struct snd_soc_dai_ops max98373_dai_sdw_ops = { .hw_params = max98373_sdw_dai_hw_params, .hw_free = max98373_pcm_hw_free, - .set_stream = max98373_set_sdw_stream, + .set_sdw_stream = max98373_set_sdw_stream, .shutdown = max98373_shutdown, .set_tdm_slot = max98373_sdw_set_tdm_slot, }; diff --git a/sound/soc/codecs/rt1308-sdw.c b/sound/soc/codecs/rt1308-sdw.c index a13296edf295..31daa749c3db 100644 --- a/sound/soc/codecs/rt1308-sdw.c +++ b/sound/soc/codecs/rt1308-sdw.c @@ -613,7 +613,7 @@ static const struct snd_soc_component_driver soc_component_sdw_rt1308 = { static const struct snd_soc_dai_ops rt1308_aif_dai_ops = { .hw_params = rt1308_sdw_hw_params, .hw_free = rt1308_sdw_pcm_hw_free, - .set_stream = rt1308_set_sdw_stream, + .set_sdw_stream = rt1308_set_sdw_stream, .shutdown = rt1308_sdw_shutdown, .set_tdm_slot = rt1308_sdw_set_tdm_slot, }; diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c index 2fb6b1edf933..c9868dd096fc 100644 --- a/sound/soc/codecs/rt5682-sdw.c +++ b/sound/soc/codecs/rt5682-sdw.c @@ -272,7 +272,7 @@ static int rt5682_sdw_hw_free(struct snd_pcm_substream *substream, static struct snd_soc_dai_ops rt5682_sdw_ops = { .hw_params = rt5682_sdw_hw_params, .hw_free = rt5682_sdw_hw_free, - .set_stream = rt5682_set_sdw_stream, + .set_sdw_stream = rt5682_set_sdw_stream, .shutdown = rt5682_sdw_shutdown, }; diff --git a/sound/soc/codecs/rt700.c b/sound/soc/codecs/rt700.c index 80acf0daabf8..687ac2153666 100644 --- a/sound/soc/codecs/rt700.c +++ b/sound/soc/codecs/rt700.c @@ -1005,7 +1005,7 @@ static int rt700_pcm_hw_free(struct snd_pcm_substream *substream, static struct snd_soc_dai_ops rt700_ops = { .hw_params = rt700_pcm_hw_params, .hw_free = rt700_pcm_hw_free, - .set_stream = rt700_set_sdw_stream, + .set_sdw_stream = rt700_set_sdw_stream, .shutdown = rt700_shutdown, }; diff --git a/sound/soc/codecs/rt711.c b/sound/soc/codecs/rt711.c index 9bdcc7872053..93d86f7558e0 100644 --- a/sound/soc/codecs/rt711.c +++ b/sound/soc/codecs/rt711.c @@ -1059,7 +1059,7 @@ static int rt711_pcm_hw_free(struct snd_pcm_substream *substream, static struct snd_soc_dai_ops rt711_ops = { .hw_params = rt711_pcm_hw_params, .hw_free = rt711_pcm_hw_free, - .set_stream = rt711_set_sdw_stream, + .set_sdw_stream = rt711_set_sdw_stream, .shutdown = rt711_shutdown, }; diff --git a/sound/soc/codecs/rt715.c b/sound/soc/codecs/rt715.c index 22bdccf66346..532c5303e7ab 100644 --- a/sound/soc/codecs/rt715.c +++ b/sound/soc/codecs/rt715.c @@ -686,7 +686,7 @@ static int rt715_pcm_hw_free(struct snd_pcm_substream *substream, static struct snd_soc_dai_ops rt715_ops = { .hw_params = rt715_pcm_hw_params, .hw_free = rt715_pcm_hw_free, - .set_stream = rt715_set_sdw_stream, + .set_sdw_stream = rt715_set_sdw_stream, .shutdown = rt715_shutdown, }; diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 15b3f47fbfa3..601525c77bba 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -1026,7 +1026,7 @@ static struct snd_soc_dai_ops wsa881x_dai_ops = { .hw_params = wsa881x_hw_params, .hw_free = wsa881x_hw_free, .mute_stream = wsa881x_digital_mute, - .set_stream = wsa881x_set_sdw_stream, + .set_sdw_stream = wsa881x_set_sdw_stream, }; static struct snd_soc_dai_driver wsa881x_dais[] = { diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index f5d8f7951cfc..25548555d8d7 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -231,7 +231,7 @@ int sdw_prepare(struct snd_pcm_substream *substream) /* Find stream from first CPU DAI */ dai = asoc_rtd_to_cpu(rtd, 0); - sdw_stream = snd_soc_dai_get_stream(dai, substream->stream); + sdw_stream = snd_soc_dai_get_sdw_stream(dai, substream->stream); if (IS_ERR(sdw_stream)) { dev_err(rtd->dev, "no stream found for DAI %s", dai->name); @@ -251,7 +251,7 @@ int sdw_trigger(struct snd_pcm_substream *substream, int cmd) /* Find stream from first CPU DAI */ dai = asoc_rtd_to_cpu(rtd, 0); - sdw_stream = snd_soc_dai_get_stream(dai, substream->stream); + sdw_stream = snd_soc_dai_get_sdw_stream(dai, substream->stream); if (IS_ERR(sdw_stream)) { dev_err(rtd->dev, "no stream found for DAI %s", dai->name); @@ -290,7 +290,7 @@ int sdw_hw_free(struct snd_pcm_substream *substream) /* Find stream from first CPU DAI */ dai = asoc_rtd_to_cpu(rtd, 0); - sdw_stream = snd_soc_dai_get_stream(dai, substream->stream); + sdw_stream = snd_soc_dai_get_sdw_stream(dai, substream->stream); if (IS_ERR(sdw_stream)) { dev_err(rtd->dev, "no stream found for DAI %s", dai->name); diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c index 6be7a32933ad..153e9b2de0b5 100644 --- a/sound/soc/qcom/sdm845.c +++ b/sound/soc/qcom/sdm845.c @@ -56,8 +56,8 @@ static int sdm845_slim_snd_hw_params(struct snd_pcm_substream *substream, int ret = 0, i; for_each_rtd_codec_dais(rtd, i, codec_dai) { - sruntime = snd_soc_dai_get_stream(codec_dai, - substream->stream); + sruntime = snd_soc_dai_get_sdw_stream(codec_dai, + substream->stream); if (sruntime != ERR_PTR(-ENOTSUPP)) pdata->sruntime[cpu_dai->id] = sruntime; From 1e32d1c96a75522029f8b06d194ccdcc15189f1a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 30 Jan 2023 16:59:23 +0000 Subject: [PATCH 1329/4345] Revert "xhci: Prevent infinite loop in transaction errors recovery for streams" This reverts commit 3d13818a9995116c230c067811cf137c19609c15 which is commit a1575120972ecd7baa6af6a69e4e7ea9213bde7c upstream. It breaks the current Android ABI. If this is needed on any systems, it can be brought back in the future in an ABI-safe way. Bug: 161946584 Signed-off-by: Greg Kroah-Hartman Change-Id: I925b73525cae44d65454ce7dbef855e1e545d2a0 --- drivers/usb/host/xhci-ring.c | 4 ++-- drivers/usb/host/xhci.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index bdc3da966da0..70d8b33afb88 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2526,7 +2526,7 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, switch (trb_comp_code) { case COMP_SUCCESS: - ep->err_count = 0; + ep_ring->err_count = 0; /* handle success with untransferred data as short packet */ if (ep_trb != td->last_trb || remaining) { xhci_warn(xhci, "WARN Successful completion on short TX\n"); @@ -2552,7 +2552,7 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, break; case COMP_USB_TRANSACTION_ERROR: if (xhci->quirks & XHCI_NO_SOFT_RETRY || - (ep->err_count++ > MAX_SOFT_RETRY) || + (ep_ring->err_count++ > MAX_SOFT_RETRY) || le32_to_cpu(slot_ctx->tt_info) & TT_SLOT) break; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 261e1b40194c..782cee6d5e7e 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -937,7 +937,6 @@ struct xhci_virt_ep { * have to restore the device state to the previous state */ struct xhci_ring *new_ring; - unsigned int err_count; unsigned int ep_state; #define SET_DEQ_PENDING (1 << 0) #define EP_HALTED (1 << 1) /* For stall handling */ @@ -1626,6 +1625,7 @@ struct xhci_ring { * if we own the TRB (if we are the consumer). See section 4.9.1. */ u32 cycle_state; + unsigned int err_count; unsigned int stream_id; unsigned int num_segs; unsigned int num_trbs_free; From fa89210a0e2d6626d912862f3ae19e8dfed8417d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Feb 2023 13:31:38 +0000 Subject: [PATCH 1330/4345] Revert "xhci: Add a flag to disable USB3 lpm on a xhci root port level." This reverts commit 4d70a8a9ab8edfa589cc13ad6e8bde3e26dfcdcf which is commit 0522b9a1653048440da5f21747f21e498b9220d1 upstream. It breaks the android kernel abi and is not needed for android at this point in time as the USB3 issues it resolves are not in Android devices. If this is needed in the future, it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: I06a9e667eb91d6502d040b7ba5db7c43f9ccdcb5 Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 8 -------- drivers/usb/host/xhci.h | 1 - 2 files changed, 9 deletions(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 13077051aa0d..380d3d3b4705 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -5003,7 +5003,6 @@ static int xhci_enable_usb3_lpm_timeout(struct usb_hcd *hcd, struct usb_device *udev, enum usb3_link_state state) { struct xhci_hcd *xhci; - struct xhci_port *port; u16 hub_encoded_timeout; int mel; int ret; @@ -5017,13 +5016,6 @@ static int xhci_enable_usb3_lpm_timeout(struct usb_hcd *hcd, !xhci->devs[udev->slot_id]) return USB3_LPM_DISABLED; - /* If connected to root port then check port can handle lpm */ - if (udev->parent && !udev->parent->parent) { - port = xhci->usb3_rhub.ports[udev->portnum - 1]; - if (port->lpm_incapable) - return USB3_LPM_DISABLED; - } - hub_encoded_timeout = xhci_calculate_lpm_timeout(hcd, udev, state); mel = calculate_max_exit_latency(udev, state, hub_encoded_timeout); if (mel < 0) { diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 1e4b7d3d5a99..b17a6c7b866d 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1742,7 +1742,6 @@ struct xhci_port { int hcd_portnum; struct xhci_hub *rhub; struct xhci_port_cap *port_cap; - unsigned int lpm_incapable:1; }; struct xhci_hub { From a73c1dbdd5f450b3c718aaa3da8e09be582241d8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Feb 2023 13:36:09 +0000 Subject: [PATCH 1331/4345] Revert "xhci: Detect lpm incapable xHC USB3 roothub ports from ACPI tables" This reverts commit 96562a23cfaf909bfa28d878fb70ce18a25201b1 which is commit 74622f0a81d0c2bcfc39f9192b788124e8c7f0af upstream. It breaks the android kernel abi and is not needed for android at this point in time as the USB3 issues it resolves are not in Android devices. If this is needed in the future, it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: I8284b5237ebd06c9b2fe5f518a4edb6d1765b4f9 Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 34 ---------------------------------- 1 file changed, 34 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index aff65cefead2..90c71979ba5e 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -351,38 +351,8 @@ static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) NULL); ACPI_FREE(obj); } - -static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev) -{ - struct xhci_hcd *xhci = hcd_to_xhci(hcd); - struct xhci_hub *rhub = &xhci->usb3_rhub; - int ret; - int i; - - /* This is not the usb3 roothub we are looking for */ - if (hcd != rhub->hcd) - return; - - if (hdev->maxchild > rhub->num_ports) { - dev_err(&hdev->dev, "USB3 roothub port number mismatch\n"); - return; - } - - for (i = 0; i < hdev->maxchild; i++) { - ret = usb_acpi_port_lpm_incapable(hdev, i); - - dev_dbg(&hdev->dev, "port-%d disable U1/U2 _DSM: %d\n", i + 1, ret); - - if (ret >= 0) { - rhub->ports[i]->lpm_incapable = ret; - continue; - } - } -} - #else static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { } -static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev) { } #endif /* CONFIG_ACPI */ /* called during probe() after chip reset completes */ @@ -418,10 +388,6 @@ static int xhci_pci_setup(struct usb_hcd *hcd) static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, struct usb_tt *tt, gfp_t mem_flags) { - /* Check if acpi claims some USB3 roothub ports are lpm incapable */ - if (!hdev->parent) - xhci_find_lpm_incapable_ports(hcd, hdev); - return xhci_update_hub_device(hcd, hdev, tt, mem_flags); } From e5ea3c44c8894774d326e4fcc2fdccaab8961e4f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Feb 2023 13:36:15 +0000 Subject: [PATCH 1332/4345] Revert "xhci: Add update_hub_device override for PCI xHCI hosts" This reverts commit 83e3a5be7475c4b1670b4f3a57728287077cec9e which is commit 23a3b8d5a2365653fd9bc5a9454d1e7f4facbf85 upstream. It breaks the android kernel abi and is not needed for android at this point in time as the USB3 issues it resolves are not in Android devices. If this is needed in the future, it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: Iccadc22dd77b1c9f6f0c20c8f0ed4b554762b899 Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 9 --------- drivers/usb/host/xhci.c | 5 +---- drivers/usb/host/xhci.h | 4 ---- 3 files changed, 1 insertion(+), 17 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 90c71979ba5e..88248a09fdaa 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -77,12 +77,9 @@ static const char hcd_name[] = "xhci_hcd"; static struct hc_driver __read_mostly xhci_pci_hc_driver; static int xhci_pci_setup(struct usb_hcd *hcd); -static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, - struct usb_tt *tt, gfp_t mem_flags); static const struct xhci_driver_overrides xhci_pci_overrides __initconst = { .reset = xhci_pci_setup, - .update_hub_device = xhci_pci_update_hub_device, }; /* called after powerup, by probe or system-pm "wakeup" */ @@ -385,12 +382,6 @@ static int xhci_pci_setup(struct usb_hcd *hcd) return xhci_pci_reinit(xhci, pdev); } -static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, - struct usb_tt *tt, gfp_t mem_flags) -{ - return xhci_update_hub_device(hcd, hdev, tt, mem_flags); -} - /* * We need to register our own PCI probe function (instead of the USB core's * function) in order to create a second roothub under xHCI. diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 380d3d3b4705..cdb65d40810b 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -5075,7 +5075,7 @@ static int xhci_disable_usb3_lpm_timeout(struct usb_hcd *hcd, /* Once a hub descriptor is fetched for a device, we need to update the xHC's * internal data structures for the device. */ -int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, +static int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, struct usb_tt *tt, gfp_t mem_flags) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); @@ -5184,7 +5184,6 @@ int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, xhci_free_command(xhci, config_cmd); return ret; } -EXPORT_SYMBOL_GPL(xhci_update_hub_device); static int xhci_get_frame(struct usb_hcd *hcd) { @@ -5465,8 +5464,6 @@ void xhci_init_driver(struct hc_driver *drv, drv->bus_suspend = over->bus_suspend; if (over->bus_resume) drv->bus_resume = over->bus_resume; - if (over->update_hub_device) - drv->update_hub_device = over->update_hub_device; } } EXPORT_SYMBOL_GPL(xhci_init_driver); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index b17a6c7b866d..782cee6d5e7e 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1962,8 +1962,6 @@ struct xhci_driver_overrides { int (*address_device)(struct usb_hcd *hcd, struct usb_device *udev); int (*bus_suspend)(struct usb_hcd *hcd); int (*bus_resume)(struct usb_hcd *hcd); - int (*update_hub_device)(struct usb_hcd *hcd, struct usb_device *hdev, - struct usb_tt *tt, gfp_t mem_flags); }; #define XHCI_CFC_DELAY 10 @@ -2121,8 +2119,6 @@ int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev, int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev); void xhci_reset_bandwidth(struct usb_hcd *hcd, struct usb_device *udev); int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev); -int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, - struct usb_tt *tt, gfp_t mem_flags); int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id); int xhci_ext_cap_init(struct xhci_hcd *xhci); From 98a15feed048e556d3999b66b050ea0b977d3923 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Tue, 10 Jan 2023 08:46:47 -0800 Subject: [PATCH 1333/4345] UPSTREAM: io_uring: Fix unsigned 'res' comparison with zero in io_fixup_rw_res() Smatch warning: io_fixup_rw_res() warn: unsigned 'res' is never less than zero. Change type of 'res' from unsigned to long. Fixes: d6b7efc722a2 ("io_uring/rw: fix error'ed retry return values") Signed-off-by: Harshit Mogalapalli Signed-off-by: Greg Kroah-Hartman Bug: 268174392 (cherry picked from commit 07b3672c4090d1e8147b1ae9c2546d8a8d8e13ae) Signed-off-by: Greg Kroah-Hartman Change-Id: I3534398af5e77e92a1ac48170e3ae4dffa42463b --- io_uring/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 35a9bcd5648b..5947c8140229 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2712,7 +2712,7 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res) return false; } -static inline int io_fixup_rw_res(struct io_kiocb *req, unsigned res) +static inline int io_fixup_rw_res(struct io_kiocb *req, long res) { struct io_async_rw *io = req->async_data; From ac069120750b94b182aba9c735567d558c7ec1dc Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 2 Jan 2023 16:49:46 -0700 Subject: [PATCH 1334/4345] UPSTREAM: io_uring/io-wq: free worker if task_work creation is canceled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit af82425c6a2d2f347c79b63ce74fca6dc6be157f upstream. If we cancel the task_work, the worker will never come into existance. As this is the last reference to it, ensure that we get it freed appropriately. Cc: stable@vger.kernel.org Reported-by: 진호 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Bug: 268174392 (cherry picked from commit b912ed1363b363d587fe1aac9636ce9e9366a775) Signed-off-by: Greg Kroah-Hartman Change-Id: Iacfd7a5db15c417fd1f02c85e414e3137e8729ec --- io_uring/io-wq.c | 1 + 1 file changed, 1 insertion(+) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 6031fb319d87..81b5e4462dba 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1217,6 +1217,7 @@ static void io_wq_cancel_tw_create(struct io_wq *wq) worker = container_of(cb, struct io_worker, create_work); io_worker_cancel_cb(worker); + kfree(worker); } } From 60944bdddcb67fc1576d903c44439320f5541cbe Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 8 Jan 2023 10:39:17 -0700 Subject: [PATCH 1335/4345] UPSTREAM: io_uring/io-wq: only free worker if it was allocated for creation commit e6db6f9398dadcbc06318a133d4c44a2d3844e61 upstream. We have two types of task_work based creation, one is using an existing worker to setup a new one (eg when going to sleep and we have no free workers), and the other is allocating a new worker. Only the latter should be freed when we cancel task_work creation for a new worker. Fixes: af82425c6a2d ("io_uring/io-wq: free worker if task_work creation is canceled") Reported-by: syzbot+d56ec896af3637bdb7e4@syzkaller.appspotmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Bug: 268174392 (cherry picked from commit a88a0d16e18f18d7221f0c5a1fdf487f5f9079e3) Signed-off-by: Greg Kroah-Hartman Change-Id: I75c9b22dce02151b2687cf90d6c5b74c08d0f04b --- io_uring/io-wq.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 81b5e4462dba..87bc38b47103 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1217,7 +1217,12 @@ static void io_wq_cancel_tw_create(struct io_wq *wq) worker = container_of(cb, struct io_worker, create_work); io_worker_cancel_cb(worker); - kfree(worker); + /* + * Only the worker continuation helper has worker allocated and + * hence needs freeing. + */ + if (cb->func == create_worker_cont) + kfree(worker); } } From 1531e1fb8d81c0175961e6aa90e92a5e8af1f2e3 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 4 Nov 2022 19:51:43 +0000 Subject: [PATCH 1336/4345] BACKPORT: iommu: Avoid races around device probe We currently have 3 different ways that __iommu_probe_device() may be called, but no real guarantee that multiple callers can't tread on each other, especially once asynchronous driver probe gets involved. It would likely have taken a fair bit of luck to hit this previously, but commit 57365a04c921 ("iommu: Move bus setup to IOMMU device registration") ups the odds since now it's not just omap-iommu that may trigger multiple bus_iommu_probe() calls in parallel if probing asynchronously. Add a lock to ensure we can't try to double-probe a device, and also close some possible race windows to make sure we're truly robust against trying to double-initialise a group via two different member devices. Reported-by: Brian Norris Signed-off-by: Robin Murphy Tested-by: Brian Norris Fixes: 57365a04c921 ("iommu: Move bus setup to IOMMU device registration") Link: https://lore.kernel.org/r/1946ef9f774851732eed78760a78ec40dbc6d178.1667591503.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel Bug: 269232600 (cherry picked from commit 01657bc14a3990c665375f77978631fee77b1fce) Change-Id: Ie87f8f7a7b90431c3a2682923961885ce7b239f3 Signed-off-by: Zhenhua Huang --- drivers/iommu/iommu.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index ed6902eb8d91..9bf7042768a4 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -201,13 +201,23 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list const struct iommu_ops *ops = dev->bus->iommu_ops; struct iommu_device *iommu_dev; struct iommu_group *group; + static DEFINE_MUTEX(iommu_probe_device_lock); int ret; if (!ops) return -ENODEV; - - if (!dev_iommu_get(dev)) - return -ENOMEM; + /* + * Serialise to avoid races between IOMMU drivers registering in + * parallel and/or the "replay" calls from ACPI/OF code via client + * driver probe. Once the latter have been cleaned up we should + * probably be able to use device_lock() here to minimise the scope, + * but for now enforcing a simple global ordering is fine. + */ + mutex_lock(&iommu_probe_device_lock); + if (!dev_iommu_get(dev)) { + ret = -ENOMEM; + goto err_unlock; + } if (!try_module_get(ops->owner)) { ret = -EINVAL; @@ -227,11 +237,14 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list ret = PTR_ERR(group); goto out_release; } - iommu_group_put(group); + mutex_lock(&group->mutex); if (group_list && !group->default_domain && list_empty(&group->entry)) list_add_tail(&group->entry, group_list); + mutex_unlock(&group->mutex); + iommu_group_put(group); + mutex_unlock(&iommu_probe_device_lock); iommu_device_link(iommu_dev, dev); return 0; @@ -245,6 +258,9 @@ out_module_put: err_free: dev_iommu_free(dev); +err_unlock: + mutex_unlock(&iommu_probe_device_lock); + return ret; } @@ -1766,11 +1782,11 @@ int bus_iommu_probe(struct bus_type *bus) return ret; list_for_each_entry_safe(group, next, &group_list, entry) { + mutex_lock(&group->mutex); + /* Remove item from the list */ list_del_init(&group->entry); - mutex_lock(&group->mutex); - /* Try to allocate default domain */ probe_alloc_default_domain(bus, group); From ef0c71d0f11e983b68ce826ee43900c3cb8d80b3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Jan 2023 20:50:24 -0700 Subject: [PATCH 1337/4345] UPSTREAM: io_uring: don't gate task_work run on TIF_NOTIFY_SIGNAL commit 46a525e199e4037516f7e498c18f065b09df32ac upstream. This isn't a reliable mechanism to tell if we have task_work pending, we really should be looking at whether we have any items queued. This is problematic if forward progress is gated on running said task_work. One such example is reading from a pipe, where the write side has been closed right before the read is started. The fput() of the file queues TWA_RESUME task_work, and we need that task_work to be run before ->release() is called for the pipe. If ->release() isn't called, then the read will sit forever waiting on data that will never arise. Fix this by io_run_task_work() so it checks if we have task_work pending rather than rely on TIF_NOTIFY_SIGNAL for that. The latter obviously doesn't work for task_work that is queued without TWA_SIGNAL. Reported-by: Christiano Haesbaert Cc: stable@vger.kernel.org Link: https://github.com/axboe/liburing/issues/665 Change-Id: I042b07491afac06692639d91bdf7dd21a2405651 Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit 2fd232bbd66fafdf7af3cc155c7bb82d96d07bc9) Signed-off-by: Greg Kroah-Hartman --- io_uring/io-wq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 87bc38b47103..81485c1a9879 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -513,7 +513,7 @@ static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, static bool io_flush_signals(void) { - if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); tracehook_notify_signal(); return true; From 4b912a635eb12792ed1d9177ff39ec4201234a14 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 23 Nov 2021 00:07:47 +0000 Subject: [PATCH 1338/4345] UPSTREAM: io_uring: improve send/recv error handling commit 7297ce3d59449de49d3c9e1f64ae25488750a1fc upstream. Hide all error handling under common if block, removes two extra ifs on the success path and keeps the handling more condensed. Change-Id: If6864c8ddd06bc853cef6b543fc06cf99d9ad147 Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/5761545158a12968f3caf30f747eea65ed75dfc1.1637524285.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit abdc16c8361b1420c1228068e0314b981a48bdcd) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 55 +++++++++++++++++++++++++-------------------- 1 file changed, 31 insertions(+), 24 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 5947c8140229..7672f2068be5 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -4716,17 +4716,18 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) min_ret = iov_iter_count(&kmsg->msg.msg_iter); ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); - if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) - return io_setup_async_msg(req, kmsg); - if (ret == -ERESTARTSYS) - ret = -EINTR; + if (ret < min_ret) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return io_setup_async_msg(req, kmsg); + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } /* fast path, check for non-NULL to avoid function call */ if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < min_ret) - req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4762,13 +4763,13 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); - if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) - return -EAGAIN; - if (ret == -ERESTARTSYS) - ret = -EINTR; - - if (ret < min_ret) + if (ret < min_ret) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; req_set_fail(req); + } __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4955,10 +4956,15 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg, kmsg->uaddr, flags); - if (force_nonblock && ret == -EAGAIN) - return io_setup_async_msg(req, kmsg); - if (ret == -ERESTARTSYS) - ret = -EINTR; + if (ret < min_ret) { + if (ret == -EAGAIN && force_nonblock) + return io_setup_async_msg(req, kmsg); + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { + req_set_fail(req); + } if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); @@ -4966,8 +4972,6 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail(req); __io_req_complete(req, issue_flags, ret, cflags); return 0; } @@ -5014,15 +5018,18 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags) min_ret = iov_iter_count(&msg.msg_iter); ret = sock_recvmsg(sock, &msg, flags); - if (force_nonblock && ret == -EAGAIN) - return -EAGAIN; - if (ret == -ERESTARTSYS) - ret = -EINTR; out_free: + if (ret < min_ret) { + if (ret == -EAGAIN && force_nonblock) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { + req_set_fail(req); + } if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); - if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail(req); __io_req_complete(req, issue_flags, ret, cflags); return 0; } From 45b2a34e21809e90633784397fa59491cf322ca3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 21 Jan 2023 10:21:22 -0700 Subject: [PATCH 1339/4345] UPSTREAM: io_uring: ensure recv and recvmsg handle MSG_WAITALL correctly commit 7ba89d2af17aa879dda30f5d5d3f152e587fc551 upstream. We currently don't attempt to get the full asked for length even if MSG_WAITALL is set, if we get a partial receive. If we do see a partial receive, then just note how many bytes we did and return -EAGAIN to get it retried. The iov is advanced appropriately for the vector based case, and we manually bump the buffer and remainder for the non-vector case. Cc: stable@vger.kernel.org Reported-by: Constantine Gavrilov Change-Id: I618bde7c86b29f6053dd8cd19682f2916e57dd54 Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit aadd9b093018183c7895aa07395b786bc71c3d31) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 7672f2068be5..7855e557f9ae 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -588,6 +588,7 @@ struct io_sr_msg { int msg_flags; int bgid; size_t len; + size_t done_io; struct io_buffer *kbuf; }; @@ -4913,12 +4914,21 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif + sr->done_io = 0; return 0; } +static bool io_net_retry(struct socket *sock, int flags) +{ + if (!(flags & MSG_WAITALL)) + return false; + return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; +} + static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; + struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; struct io_buffer *kbuf; unsigned flags; @@ -4961,6 +4971,10 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + return io_setup_async_msg(req, kmsg); + } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { req_set_fail(req); @@ -4972,6 +4986,10 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, cflags); return 0; } @@ -5024,12 +5042,22 @@ out_free: return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + return -EAGAIN; + } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { req_set_fail(req); } if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, cflags); return 0; } From cf7ef78842be277430b37f60eefe148bb3ecf4a8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 23 Mar 2022 09:30:05 -0600 Subject: [PATCH 1340/4345] UPSTREAM: io_uring: add flag for disabling provided buffer recycling commit 8a3e8ee56417f5e0e66580d93941ed9d6f4c8274 upstream. If we need to continue doing this IO, then we don't want a potentially selected buffer recycled. Add a flag for that. Set this for recv/recvmsg if they do partial IO. Change-Id: If9381bd6a5695c8c85c7a51c3adccc0dc09f8999 Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit 96ccba4a1a59ae6bcfed405961dd399c74d0b2f8) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 7855e557f9ae..98948e4232a6 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -750,6 +750,7 @@ enum { REQ_F_CREDS_BIT, REQ_F_REFCOUNT_BIT, REQ_F_ARM_LTIMEOUT_BIT, + REQ_F_PARTIAL_IO_BIT, /* keep async read/write and isreg together and in order */ REQ_F_NOWAIT_READ_BIT, REQ_F_NOWAIT_WRITE_BIT, @@ -805,6 +806,8 @@ enum { REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), /* there is a linked timeout that has to be armed */ REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), + /* request has already done partial IO */ + REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), }; struct async_poll { @@ -4973,6 +4976,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; return io_setup_async_msg(req, kmsg); } req_set_fail(req); @@ -5046,6 +5050,7 @@ out_free: sr->len -= ret; sr->buf += ret; sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; return -EAGAIN; } req_set_fail(req); From a64d6ea01bbcf7b7ef6c58e1810adeca0cff9187 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 20 Apr 2022 19:21:36 -0600 Subject: [PATCH 1341/4345] UPSTREAM: io_uring: support MSG_WAITALL for IORING_OP_SEND(MSG) commit 4c3c09439c08b03d9503df0ca4c7619c5842892e upstream. Like commit 7ba89d2af17a for recv/recvmsg, support MSG_WAITALL for the send side. If this flag is set and we do a short send, retry for a stream of seqpacket socket. Change-Id: If67a4462576af1b683d53d2dc0d46e44c9dd8863 Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit f901b4bfd03ed234f72f28e27d965569531dc505) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 36 +++++++++++++++++++++++++++++------- 1 file changed, 29 insertions(+), 7 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 98948e4232a6..ec8f05f27260 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -4627,6 +4627,13 @@ static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) } #if defined(CONFIG_NET) +static bool io_net_retry(struct socket *sock, int flags) +{ + if (!(flags & MSG_WAITALL)) + return false; + return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; +} + static int io_setup_async_msg(struct io_kiocb *req, struct io_async_msghdr *kmsg) { @@ -4690,12 +4697,14 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif + sr->done_io = 0; return 0; } static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; + struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; unsigned flags; int min_ret = 0; @@ -4726,12 +4735,21 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return io_setup_async_msg(req, kmsg); + } req_set_fail(req); } /* fast path, check for non-NULL to avoid function call */ if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4772,8 +4790,19 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; + if (ret > 0 && io_net_retry(sock, flags)) { + sr->len -= ret; + sr->buf += ret; + sr->done_io += ret; + req->flags |= REQ_F_PARTIAL_IO; + return -EAGAIN; + } req_set_fail(req); } + if (ret >= 0) + ret += sr->done_io; + else if (sr->done_io) + ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4921,13 +4950,6 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static bool io_net_retry(struct socket *sock, int flags) -{ - if (!(flags & MSG_WAITALL)) - return false; - return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; -} - static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; From 63bf975936c02ff7010513305068008d835686c1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 21 Jan 2023 10:39:22 -0700 Subject: [PATCH 1342/4345] UPSTREAM: io_uring: allow re-poll if we made progress commit 10c873334febaeea9aa0c25c10b5ac0951b77a5f upstream. We currently check REQ_F_POLLED before arming async poll for a notification to retry. If it's set, then we don't allow poll and will punt to io-wq instead. This is done to prevent a situation where a buggy driver will repeatedly return that there's space/data available yet we get -EAGAIN. However, if we already transferred data, then it should be safe to rely on poll again. Gate the check on whether or not REQ_F_PARTIAL_IO is also set. Change-Id: I36b6d16ac43202fdf9ae5eea64f9dfbcfbe7fee5 Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit 4bc17e6381bdbe7373ffccbda94db56631061a4a) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ec8f05f27260..91a177a2e7da 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5704,7 +5704,7 @@ static int io_arm_poll_handler(struct io_kiocb *req) if (!req->file || !file_can_poll(req->file)) return IO_APOLL_ABORTED; - if (req->flags & REQ_F_POLLED) + if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED) return IO_APOLL_ABORTED; if (!def->pollin && !def->pollout) return IO_APOLL_ABORTED; @@ -5720,7 +5720,10 @@ static int io_arm_poll_handler(struct io_kiocb *req) mask |= POLLOUT | POLLWRNORM; } - apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); + if (req->flags & REQ_F_POLLED) + apoll = req->apoll; + else + apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); if (unlikely(!apoll)) return IO_APOLL_ABORTED; apoll->double_poll = NULL; From 1b735b5eb254928c0565ae33bfd7afb6e8b32b7c Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Sat, 21 Jan 2023 09:13:12 -0700 Subject: [PATCH 1343/4345] UPSTREAM: io_uring: fix async accept on O_NONBLOCK sockets commit a73825ba70c93e1eb39a845bb3d9885a787f8ffe upstream. Do not set REQ_F_NOWAIT if the socket is non blocking. When enabled this causes the accept to immediately post a CQE with EAGAIN, which means you cannot perform an accept SQE on a NONBLOCK socket asynchronously. By removing the flag if there is no pending accept then poll is armed as usual and when a connection comes in the CQE is posted. Change-Id: I0fae3f75c7fbbf44f85da7d83f48c4cfed1fcae9 Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220324143435.2875844-1-dylany@fb.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit aa4c9b3e45e234bc011bd26a045f6bdfd4783001) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 91a177a2e7da..951a936b1c48 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5122,9 +5122,6 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) struct file *file; int ret, fd; - if (req->file->f_flags & O_NONBLOCK) - req->flags |= REQ_F_NOWAIT; - if (!fixed) { fd = __get_unused_fd_flags(accept->flags, accept->nofile); if (unlikely(fd < 0)) @@ -5137,6 +5134,8 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) if (!fixed) put_unused_fd(fd); ret = PTR_ERR(file); + /* safe to retry */ + req->flags |= REQ_F_PARTIAL_IO; if (ret == -EAGAIN && force_nonblock) return -EAGAIN; if (ret == -ERESTARTSYS) From 0dfe72e89062e204d12a27b05d1c38da04c38c1b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Dec 2022 06:37:08 -0700 Subject: [PATCH 1344/4345] UPSTREAM: io_uring: check for valid register opcode earlier [ Upstream commit 343190841a1f22b96996d9f8cfab902a4d1bfd0e ] We only check the register opcode value inside the restricted ring section, move it into the main io_uring_register() function instead and check it up front. Change-Id: I4b5f782dad48eb0e7f04d5956cc087494e02b2ec Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit 78e8151f04f0aa0a5809aafea5de3719c2360033) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 951a936b1c48..2309fdcc7b52 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -10815,8 +10815,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, return -ENXIO; if (ctx->restricted) { - if (opcode >= IORING_REGISTER_LAST) - return -EINVAL; opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); if (!test_bit(opcode, ctx->restrictions.register_op)) return -EACCES; @@ -10948,6 +10946,9 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, long ret = -EBADF; struct fd f; + if (opcode >= IORING_REGISTER_LAST) + return -EINVAL; + f = fdget(fd); if (!f.file) return -EBADF; From a4d056e3507b5c49b23265a0d22a3f8ba6dd6733 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 14 Jan 2023 09:14:03 -0700 Subject: [PATCH 1345/4345] UPSTREAM: io_uring: lock overflowing for IOPOLL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 544d163d659d45a206d8929370d5a2984e546cb7 upstream. syzbot reports an issue with overflow filling for IOPOLL: WARNING: CPU: 0 PID: 28 at io_uring/io_uring.c:734 io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734 CPU: 0 PID: 28 Comm: kworker/u4:1 Not tainted 6.2.0-rc3-syzkaller-16369-g358a161a6a9e #0 Workqueue: events_unbound io_ring_exit_work Call trace:  io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734  io_req_cqe_overflow+0x5c/0x70 io_uring/io_uring.c:773  io_fill_cqe_req io_uring/io_uring.h:168 [inline]  io_do_iopoll+0x474/0x62c io_uring/rw.c:1065  io_iopoll_try_reap_events+0x6c/0x108 io_uring/io_uring.c:1513  io_uring_try_cancel_requests+0x13c/0x258 io_uring/io_uring.c:3056  io_ring_exit_work+0xec/0x390 io_uring/io_uring.c:2869  process_one_work+0x2d8/0x504 kernel/workqueue.c:2289  worker_thread+0x340/0x610 kernel/workqueue.c:2436  kthread+0x12c/0x158 kernel/kthread.c:376  ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:863 There is no real problem for normal IOPOLL as flush is also called with uring_lock taken, but it's getting more complicated for IOPOLL|SQPOLL, for which __io_cqring_overflow_flush() happens from the CQ waiting path. Reported-and-tested-by: syzbot+6805087452d72929404e@syzkaller.appspotmail.com Cc: stable@vger.kernel.org # 5.10+ Change-Id: I3449b2ea1b71ff2f04f119741751b42870386923 Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit de77faee280163ff03b7ab64af6c9d779a43d4c4) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 2309fdcc7b52..35b877bd636f 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2492,12 +2492,26 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, io_init_req_batch(&rb); while (!list_empty(done)) { + struct io_uring_cqe *cqe; + unsigned cflags; + req = list_first_entry(done, struct io_kiocb, inflight_entry); list_del(&req->inflight_entry); - - io_fill_cqe_req(req, req->result, io_put_rw_kbuf(req)); + cflags = io_put_rw_kbuf(req); (*nr_events)++; + cqe = io_get_cqe(ctx); + if (cqe) { + WRITE_ONCE(cqe->user_data, req->user_data); + WRITE_ONCE(cqe->res, req->result); + WRITE_ONCE(cqe->flags, cflags); + } else { + spin_lock(&ctx->completion_lock); + io_cqring_event_overflow(ctx, req->user_data, + req->result, cflags); + spin_unlock(&ctx->completion_lock); + } + if (req_ref_put_and_test(req)) io_req_free_batch(&rb, req, &ctx->submit_state); } From fee5372abf8ae42131af91cd88cf3790892a7599 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 5 Jan 2023 10:49:15 +0000 Subject: [PATCH 1346/4345] UPSTREAM: io_uring: fix CQ waiting timeout handling commit 12521a5d5cb7ff0ad43eadfc9c135d86e1131fa8 upstream. Jiffy to ktime CQ waiting conversion broke how we treat timeouts, in particular we rearm it anew every time we get into io_cqring_wait_schedule() without adjusting the timeout. Waiting for 2 CQEs and getting a task_work in the middle may double the timeout value, or even worse in some cases task may wait indefinitely. Cc: stable@vger.kernel.org Fixes: 228339662b398 ("io_uring: don't convert to jiffies for waiting on timeouts") Change-Id: If8605a13266ae2b49b1f7d7cd5ee092f9ffd2805 Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/f7bffddd71b08f28a877d44d37ac953ddb01590d.1672915663.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit e0140e9da31e1f89baca5f175e073e8aed92688f) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 35b877bd636f..07ad8347f980 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -7528,7 +7528,7 @@ static int io_run_task_work_sig(void) /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, - ktime_t timeout) + ktime_t *timeout) { int ret; @@ -7540,7 +7540,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, if (test_bit(0, &ctx->check_cq_overflow)) return 1; - if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) + if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) return -ETIME; return 1; } @@ -7603,7 +7603,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, } prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); - ret = io_cqring_wait_schedule(ctx, &iowq, timeout); + ret = io_cqring_wait_schedule(ctx, &iowq, &timeout); finish_wait(&ctx->cq_wait, &iowq.wq); cond_resched(); } while (ret > 0); From 9166f5418ae21037d1ed7a676df50c7958b1a34c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 21 Jan 2023 12:36:08 -0700 Subject: [PATCH 1347/4345] UPSTREAM: io_uring: ensure that cached task references are always put on exit commit e775f93f2ab976a2cdb4a7b53063cbe890904f73 upstream. io_uring caches task references to avoid doing atomics for each of them per request. If a request is put from the same task that allocated it, then we can maintain a per-ctx cache of them. This obviously relies on io_uring always pruning caches in a reliable way, and there's currently a case off io_uring fd release where we can miss that. One example is a ring setup with IOPOLL, which relies on the task polling for completions, which will free them. However, if such a task submits a request and then exits or closes the ring without reaping the completion, then ring release will reap and put. If release happens from that very same task, the completed request task refs will get put back into the cache pool. This is problematic, as we're now beyond the point of pruning caches. Manually drop these caches after doing an IOPOLL reap. This releases references from the current task, which is enough. If another task happens to be doing the release, then the caching will not be triggered and there's no issue. Cc: stable@vger.kernel.org Fixes: e98e49b2bbf7 ("io_uring: extend task put optimisations") Reported-by: Homin Rhee Change-Id: I9495121af065424141fa9c39840ab9aa91f45c72 Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit e9c6556708d3b1f77f1a9e08881f8bb01e98e919) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 07ad8347f980..713a2436feef 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -9523,6 +9523,10 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); + /* drop cached put refs after potentially doing completions */ + if (current->io_uring) + io_uring_drop_tctx_refs(current); + INIT_WORK(&ctx->exit_work, io_ring_exit_work); /* * Use system_unbound_wq to avoid spawning tons of event kworkers From b543e0d210da1240b6059a6d8d360902812998e1 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 22 Feb 2022 02:55:01 -0800 Subject: [PATCH 1348/4345] UPSTREAM: io_uring: remove duplicated calls to io_kiocb_ppos commit af9c45ecebaf1b428306f41421f4bcffe439f735 upstream. io_kiocb_ppos is called in both branches, and it seems that the compiler does not fuse this. Fusing removes a few bytes from loop_rw_iter. Before: $ nm -S fs/io_uring.o | grep loop_rw_iter 0000000000002430 0000000000000124 t loop_rw_iter After: $ nm -S fs/io_uring.o | grep loop_rw_iter 0000000000002430 000000000000010d t loop_rw_iter Change-Id: Ibd662d59697d9cb1e484319050f6e5f960f6ac5c Signed-off-by: Dylan Yudaken Reviewed-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit 076f872314d4da36e878673cbef1eae3514b0c6d) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 713a2436feef..7b26c0c08375 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3310,6 +3310,7 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) struct kiocb *kiocb = &req->rw.kiocb; struct file *file = req->file; ssize_t ret = 0; + loff_t *ppos; /* * Don't support polled IO through this interface, and we can't @@ -3321,6 +3322,8 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) if (kiocb->ki_flags & IOCB_NOWAIT) return -EAGAIN; + ppos = io_kiocb_ppos(kiocb); + while (iov_iter_count(iter)) { struct iovec iovec; ssize_t nr; @@ -3334,10 +3337,10 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) if (rw == READ) { nr = file->f_op->read(file, iovec.iov_base, - iovec.iov_len, io_kiocb_ppos(kiocb)); + iovec.iov_len, ppos); } else { nr = file->f_op->write(file, iovec.iov_base, - iovec.iov_len, io_kiocb_ppos(kiocb)); + iovec.iov_len, ppos); } if (nr < 0) { From 84e34d2ef5f38ca5492fc6fae7e6097c21080c1b Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 22 Feb 2022 02:55:02 -0800 Subject: [PATCH 1349/4345] UPSTREAM: io_uring: update kiocb->ki_pos at execution time commit d34e1e5b396a0dbaa4a29b7138df662cfb9d8e8e upstream. Update kiocb->ki_pos at execution time rather than in io_prep_rw(). io_prep_rw() happens before the job is enqueued to a worker and so the offset might be read multiple times before being executed once. Ensures that the file position in a set of _linked_ SQEs will be only obtained after earlier SQEs have completed, and so will include their incremented file position. Change-Id: I3c5abbf6a337ec1958fd6600c5feb44fb61a5772 Signed-off-by: Dylan Yudaken Reviewed-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit ea528ecac3ae58d8197871b29748eefca7d46be8) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 7b26c0c08375..ad5860309f0d 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2929,14 +2929,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, req->flags |= REQ_F_ISREG; kiocb->ki_pos = READ_ONCE(sqe->off); - if (kiocb->ki_pos == -1) { - if (!(file->f_mode & FMODE_STREAM)) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = file->f_pos; - } else { - kiocb->ki_pos = 0; - } - } kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); @@ -3018,6 +3010,20 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } } +static inline void io_kiocb_update_pos(struct io_kiocb *req) +{ + struct kiocb *kiocb = &req->rw.kiocb; + + if (kiocb->ki_pos == -1) { + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + } else { + kiocb->ki_pos = 0; + } + } +} + static void kiocb_done(struct kiocb *kiocb, ssize_t ret, unsigned int issue_flags) { @@ -3573,6 +3579,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return ret ?: -EAGAIN; } + io_kiocb_update_pos(req); + ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) { kfree(iovec); @@ -3707,6 +3715,8 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) (req->flags & REQ_F_ISREG)) goto copy_iov; + io_kiocb_update_pos(req); + ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) goto out_free; From b29c357309e5a8e347489f46ed1479b5af739f72 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 22 Feb 2022 02:55:03 -0800 Subject: [PATCH 1350/4345] UPSTREAM: io_uring: do not recalculate ppos unnecessarily commit b4aec40015953b65f2f114641e7fd7714c8df8e6 upstream. There is a slight optimisation to be had by calculating the correct pos pointer inside io_kiocb_update_pos and then using that later. It seems code size drops by a bit: 000000000000a1b0 0000000000000400 t io_read 000000000000a5b0 0000000000000319 t io_write vs 000000000000a1b0 00000000000003f6 t io_read 000000000000a5b0 0000000000000310 t io_write Change-Id: I19d8cdb6ea88d8fc4625e521363d5a8f638dfdcb Signed-off-by: Dylan Yudaken Reviewed-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit e90cfb96999454b6d3f469f3a9414cf7f9df62fe) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ad5860309f0d..a4941265a9b7 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3010,18 +3010,22 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } } -static inline void io_kiocb_update_pos(struct io_kiocb *req) +static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; + bool is_stream = req->file->f_mode & FMODE_STREAM; if (kiocb->ki_pos == -1) { - if (!(req->file->f_mode & FMODE_STREAM)) { + if (!is_stream) { req->flags |= REQ_F_CUR_POS; kiocb->ki_pos = req->file->f_pos; + return &kiocb->ki_pos; } else { kiocb->ki_pos = 0; + return NULL; } } + return is_stream ? NULL : &kiocb->ki_pos; } static void kiocb_done(struct kiocb *kiocb, ssize_t ret, @@ -3547,6 +3551,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; struct iov_iter_state __state, *state; ssize_t ret, ret2; + loff_t *ppos; if (rw) { iter = &rw->iter; @@ -3579,9 +3584,9 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return ret ?: -EAGAIN; } - io_kiocb_update_pos(req); + ppos = io_kiocb_update_pos(req); - ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result); + ret = rw_verify_area(READ, req->file, ppos, req->result); if (unlikely(ret)) { kfree(iovec); return ret; @@ -3685,6 +3690,7 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; struct iov_iter_state __state, *state; ssize_t ret, ret2; + loff_t *ppos; if (rw) { iter = &rw->iter; @@ -3715,9 +3721,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) (req->flags & REQ_F_ISREG)) goto copy_iov; - io_kiocb_update_pos(req); + ppos = io_kiocb_update_pos(req); - ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result); + ret = rw_verify_area(WRITE, req->file, ppos, req->result); if (unlikely(ret)) goto out_free; From 0c50a117bf4341a0480c199885cdcae615fa619a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 21 Jan 2023 13:38:51 -0700 Subject: [PATCH 1351/4345] UPSTREAM: io_uring/rw: defer fsnotify calls to task context commit b000145e9907809406d8164c3b2b8861d95aecd1 upstream. We can't call these off the kiocb completion as that might be off soft/hard irq context. Defer the calls to when we process the task_work for this request. That avoids valid complaints like: stack backtrace: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.0.0-rc6-syzkaller-00321-g105a36f3694e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_usage_bug kernel/locking/lockdep.c:3961 [inline] valid_state kernel/locking/lockdep.c:3973 [inline] mark_lock_irq kernel/locking/lockdep.c:4176 [inline] mark_lock.part.0.cold+0x18/0xd8 kernel/locking/lockdep.c:4632 mark_lock kernel/locking/lockdep.c:4596 [inline] mark_usage kernel/locking/lockdep.c:4527 [inline] __lock_acquire+0x11d9/0x56d0 kernel/locking/lockdep.c:5007 lock_acquire kernel/locking/lockdep.c:5666 [inline] lock_acquire+0x1ab/0x570 kernel/locking/lockdep.c:5631 __fs_reclaim_acquire mm/page_alloc.c:4674 [inline] fs_reclaim_acquire+0x115/0x160 mm/page_alloc.c:4688 might_alloc include/linux/sched/mm.h:271 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc mm/slab.c:3278 [inline] __kmem_cache_alloc_lru mm/slab.c:3471 [inline] kmem_cache_alloc+0x39/0x520 mm/slab.c:3491 fanotify_alloc_fid_event fs/notify/fanotify/fanotify.c:580 [inline] fanotify_alloc_event fs/notify/fanotify/fanotify.c:813 [inline] fanotify_handle_event+0x1130/0x3f40 fs/notify/fanotify/fanotify.c:948 send_to_group fs/notify/fsnotify.c:360 [inline] fsnotify+0xafb/0x1680 fs/notify/fsnotify.c:570 __fsnotify_parent+0x62f/0xa60 fs/notify/fsnotify.c:230 fsnotify_parent include/linux/fsnotify.h:77 [inline] fsnotify_file include/linux/fsnotify.h:99 [inline] fsnotify_access include/linux/fsnotify.h:309 [inline] __io_complete_rw_common+0x485/0x720 io_uring/rw.c:195 io_complete_rw+0x1a/0x1f0 io_uring/rw.c:228 iomap_dio_complete_work fs/iomap/direct-io.c:144 [inline] iomap_dio_bio_end_io+0x438/0x5e0 fs/iomap/direct-io.c:178 bio_endio+0x5f9/0x780 block/bio.c:1564 req_bio_endio block/blk-mq.c:695 [inline] blk_update_request+0x3fc/0x1300 block/blk-mq.c:825 scsi_end_request+0x7a/0x9a0 drivers/scsi/scsi_lib.c:541 scsi_io_completion+0x173/0x1f70 drivers/scsi/scsi_lib.c:971 scsi_complete+0x122/0x3b0 drivers/scsi/scsi_lib.c:1438 blk_complete_reqs+0xad/0xe0 block/blk-mq.c:1022 __do_softirq+0x1d3/0x9c6 kernel/softirq.c:571 invoke_softirq kernel/softirq.c:445 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:650 irq_exit_rcu+0x5/0x20 kernel/softirq.c:662 common_interrupt+0xa9/0xc0 arch/x86/kernel/irq.c:240 Fixes: f63cf5192fe3 ("io_uring: ensure that fsnotify is always called") Link: https://lore.kernel.org/all/20220929135627.ykivmdks2w5vzrwg@quack3/ Reported-by: syzbot+dfcc5f4da15868df7d4d@syzkaller.appspotmail.com Reported-by: Jan Kara Change-Id: Ia16078bdf53c6b2536cacb7aafa03a4ec1079a94 Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Bug: 268174392 (cherry picked from commit ea2e6286e3e89a115ae554e20ba9aec2b2e1ddff) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index a4941265a9b7..06267fb28546 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2712,12 +2712,6 @@ static bool io_rw_should_reissue(struct io_kiocb *req) static bool __io_complete_rw_common(struct io_kiocb *req, long res) { - if (req->rw.kiocb.ki_flags & IOCB_WRITE) { - kiocb_end_write(req); - fsnotify_modify(req->file); - } else { - fsnotify_access(req->file); - } if (res != req->result) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { @@ -2770,6 +2764,20 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2, __io_req_complete(req, issue_flags, io_fixup_rw_res(req, res), io_put_rw_kbuf(req)); } +static void io_req_rw_complete(struct io_kiocb *req, bool *locked) +{ + struct io_rw *rw = &req->rw; + + if (rw->kiocb.ki_flags & IOCB_WRITE) { + kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } + + io_req_task_complete(req, locked); +} + static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); @@ -2777,7 +2785,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) if (__io_complete_rw_common(req, res)) return; req->result = io_fixup_rw_res(req, res); - req->io_task_work.func = io_req_task_complete; + req->io_task_work.func = io_req_rw_complete; io_req_task_work_add(req); } From 403642c036c51f980faff9d951a26ab139f7e3e2 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 11 Apr 2022 09:48:30 -0600 Subject: [PATCH 1352/4345] UPSTREAM: io_uring: io_kiocb_update_pos() should not touch file for non -1 offset commit 6f83ab22adcb77a5824d2c274dace0d99e21319f upstream. -1 tells use to use the current position, but we check if the file is a stream regardless of that. Fix up io_kiocb_update_pos() to only dip into file if we need to. This is both more efficient and also drops 12 bytes of text on aarch64 and 64 bytes on x86-64. Fixes: b4aec4001595 ("io_uring: do not recalculate ppos unnecessarily") Change-Id: I5c22ce8122b0e1f0ad423a5b3aa520ee416feff1 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Bug: 268174392 (cherry picked from commit 89a77271d254752d83507fc347dc2d675885fe07) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 06267fb28546..d758427877e3 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3021,19 +3021,18 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; - bool is_stream = req->file->f_mode & FMODE_STREAM; - if (kiocb->ki_pos == -1) { - if (!is_stream) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; - return &kiocb->ki_pos; - } else { - kiocb->ki_pos = 0; - return NULL; - } + if (kiocb->ki_pos != -1) + return &kiocb->ki_pos; + + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + return &kiocb->ki_pos; } - return is_stream ? NULL : &kiocb->ki_pos; + + kiocb->ki_pos = 0; + return NULL; } static void kiocb_done(struct kiocb *kiocb, ssize_t ret, From 827f8fcb2979d701cd80435975a3bd56aba3dde5 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher Date: Thu, 29 Sep 2022 09:39:10 +0200 Subject: [PATCH 1353/4345] UPSTREAM: io_uring/net: fix fast_iov assignment in io_setup_async_msg() commit 3e4cb6ebbb2bad201c1186bc0b7e8cf41dd7f7e6 upstream. I hit a very bad problem during my tests of SENDMSG_ZC. BUG(); in first_iovec_segment() triggered very easily. The problem was io_setup_async_msg() in the partial retry case, which seems to happen more often with _ZC. iov_iter_iovec_advance() may change i->iov in order to have i->iov_offset being only relative to the first element. Which means kmsg->msg.msg_iter.iov is no longer the same as kmsg->fast_iov. But this would rewind the copy to be the start of async_msg->fast_iov, which means the internal state of sync_msg->msg.msg_iter is inconsitent. I tested with 5 vectors with length like this 4, 0, 64, 20, 8388608 and got a short writes with: - ret=2675244 min_ret=8388692 => remaining 5713448 sr->done_io=2675244 - ret=-EAGAIN => io_uring_poll_arm - ret=4911225 min_ret=5713448 => remaining 802223 sr->done_io=7586469 - ret=-EAGAIN => io_uring_poll_arm - ret=802223 min_ret=802223 => res=8388692 While this was easily triggered with SENDMSG_ZC (queued for 6.1), it was a potential problem starting with 7ba89d2af17aa879dda30f5d5d3f152e587fc551 in 5.18 for IORING_OP_RECVMSG. And also with 4c3c09439c08b03d9503df0ca4c7619c5842892e in 5.19 for IORING_OP_SENDMSG. However 257e84a5377fbbc336ff563833a8712619acce56 introduced the critical code into io_setup_async_msg() in 5.11. Fixes: 7ba89d2af17aa ("io_uring: ensure recv and recvmsg handle MSG_WAITALL correctly") Fixes: 257e84a5377fb ("io_uring: refactor sendmsg/recvmsg iov managing") Cc: stable@vger.kernel.org Change-Id: I72c459fdbae2938d176126ed2f17eea990c42d49 Signed-off-by: Stefan Metzmacher Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/b2e7be246e2fb173520862b0c7098e55767567a2.1664436949.git.metze@samba.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Bug: 268174392 (cherry picked from commit fc2491562a9bed1f3e58a8ebdd4176962640e58c) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index d758427877e3..9c3acfdc10b0 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -4691,8 +4691,10 @@ static int io_setup_async_msg(struct io_kiocb *req, if (async_msg->msg.msg_name) async_msg->msg.msg_name = &async_msg->addr; /* if were using fast_iov, set it to the new one */ - if (!async_msg->free_iov) - async_msg->msg.msg_iter.iov = async_msg->fast_iov; + if (!kmsg->free_iov) { + size_t fast_idx = kmsg->msg.msg_iter.iov - kmsg->fast_iov; + async_msg->msg.msg_iter.iov = &async_msg->fast_iov[fast_idx]; + } return -EAGAIN; } From fc978be7b20234b7f0ff4bd1c278be4f1339dcc5 Mon Sep 17 00:00:00 2001 From: Alviro Iskandar Setiawan Date: Mon, 7 Feb 2022 21:05:33 +0700 Subject: [PATCH 1354/4345] UPSTREAM: io_uring: Clean up a false-positive warning from GCC 9.3.0 commit 0d7c1153d9291197c1dc473cfaade77acb874b4b upstream. In io_recv(), if import_single_range() fails, the @flags variable is uninitialized, then it will goto out_free. After the goto, the compiler doesn't know that (ret < min_ret) is always true, so it thinks the "if ((flags & MSG_WAITALL) ..." path could be taken. The complaint comes from gcc-9 (Debian 9.3.0-22) 9.3.0: ``` fs/io_uring.c:5238 io_recvfrom() error: uninitialized symbol 'flags' ``` Fix this by bypassing the @ret and @flags check when import_single_range() fails. Reasons: 1. import_single_range() only returns -EFAULT when it fails. 2. At that point, @flags is uninitialized and shouldn't be read. Reported-by: kernel test robot Reported-by: Dan Carpenter Reported-by: "Chen, Rong A" Link: https://lore.gnuweeb.org/timl/d33bb5a9-8173-f65b-f653-51fc0681c6d6@intel.com/ Cc: Pavel Begunkov Suggested-by: Ammar Faizi Fixes: 7297ce3d59449de49d3c9e1f64ae25488750a1fc ("io_uring: improve send/recv error handling") Change-Id: Ifd324b3213a0682dae11177c93a5b8272516c2cd Signed-off-by: Alviro Iskandar Setiawan Signed-off-by: Ammar Faizi Link: https://lore.kernel.org/r/20220207140533.565411-1-ammarfaizi2@gnuweeb.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Bug: 268174392 (cherry picked from commit ddaaadf22bea31cf7e94d55c6530ce75947bb1cc) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 9c3acfdc10b0..0eed453fd469 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5104,7 +5104,6 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags) min_ret = iov_iter_count(&msg.msg_iter); ret = sock_recvmsg(sock, &msg, flags); -out_free: if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) return -EAGAIN; @@ -5119,6 +5118,7 @@ out_free: } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { +out_free: req_set_fail(req); } if (req->flags & REQ_F_BUFFER_SELECTED) From d54d41716dc1fc35bed4d6ec20bfd8650e45dfd6 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 22 Jan 2023 10:24:20 -0700 Subject: [PATCH 1355/4345] UPSTREAM: io_uring: fix double poll leak on repolling commit c0737fa9a5a5cf5a053bcc983f72d58919b997c6 upstream. We have re-polling for partial IO, so a request can be polled twice. If it used two poll entries the first time then on the second io_arm_poll_handler() it will find the old apoll entry and NULL kmalloc()'ed second entry, i.e. apoll->double_poll, so leaking it. Fixes: 10c873334feba ("io_uring: allow re-poll if we made progress") Change-Id: If720ddcd7e488c0c336533d8dde00864689648ca Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/fee2452494222ecc7f1f88c8fb659baef971414a.1655852245.git.asml.silence@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Bug: 268174392 (cherry picked from commit c1a279d79e313bd9b0ed31025edc68394bfc40ab) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 0eed453fd469..9ef72355f5c1 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5761,10 +5761,12 @@ static int io_arm_poll_handler(struct io_kiocb *req) mask |= POLLOUT | POLLWRNORM; } - if (req->flags & REQ_F_POLLED) + if (req->flags & REQ_F_POLLED) { apoll = req->apoll; - else + kfree(apoll->double_poll); + } else { apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); + } if (unlikely(!apoll)) return IO_APOLL_ABORTED; apoll->double_poll = NULL; From ca331f289a22f1cbe25d09d1e8b6a2933e6b70fb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 22 Jan 2023 10:36:37 -0700 Subject: [PATCH 1356/4345] UPSTREAM: io_uring/rw: ensure kiocb_end_write() is always called commit 2ec33a6c3cca9fe2465e82050c81f5ffdc508b36 upstream. A previous commit moved the notifications and end-write handling, but it is now missing a few spots where we also want to call both of those. Without that, we can potentially be missing file notifications, and more importantly, have an imbalance in the super_block writers sem accounting. Fixes: b000145e9907 ("io_uring/rw: defer fsnotify calls to task context") Reported-by: Dave Chinner Link: https://lore.kernel.org/all/20221010050319.GC2703033@dread.disaster.area/ Change-Id: Iaaa509f5dadcae04f58c929901225bc968b35d52 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Bug: 268174392 (cherry picked from commit 3d5f181bda25112c4d5d10c1930a59787868e032) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 57 +++++++++++++++++++++++++++++---------------- 1 file changed, 37 insertions(+), 20 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 9ef72355f5c1..d1a079b7f1ca 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2710,11 +2710,34 @@ static bool io_rw_should_reissue(struct io_kiocb *req) } #endif +/* + * Trigger the notifications after having done some IO, and finish the write + * accounting, if any. + */ +static void io_req_io_end(struct io_kiocb *req) +{ + struct io_rw *rw = &req->rw; + + WARN_ON(!in_task()); + + if (rw->kiocb.ki_flags & IOCB_WRITE) { + kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } +} + static bool __io_complete_rw_common(struct io_kiocb *req, long res) { if (res != req->result) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { + /* + * Reissue will start accounting again, finish the + * current cycle. + */ + io_req_io_end(req); req->flags |= REQ_F_REISSUE; return true; } @@ -2756,25 +2779,9 @@ static void io_req_task_complete(struct io_kiocb *req, bool *locked) } } -static void __io_complete_rw(struct io_kiocb *req, long res, long res2, - unsigned int issue_flags) -{ - if (__io_complete_rw_common(req, res)) - return; - __io_req_complete(req, issue_flags, io_fixup_rw_res(req, res), io_put_rw_kbuf(req)); -} - static void io_req_rw_complete(struct io_kiocb *req, bool *locked) { - struct io_rw *rw = &req->rw; - - if (rw->kiocb.ki_flags & IOCB_WRITE) { - kiocb_end_write(req); - fsnotify_modify(req->file); - } else { - fsnotify_access(req->file); - } - + io_req_io_end(req); io_req_task_complete(req, locked); } @@ -3042,10 +3049,20 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; - if (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) - __io_complete_rw(req, ret, 0, issue_flags); - else + if (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) { + if (!__io_complete_rw_common(req, ret)) { + /* + * Safe to call io_end from here as we're inline + * from the submission path. + */ + io_req_io_end(req); + __io_req_complete(req, issue_flags, + io_fixup_rw_res(req, ret), + io_put_rw_kbuf(req)); + } + } else { io_rw_done(kiocb, ret); + } if (req->flags & REQ_F_REISSUE) { req->flags &= ~REQ_F_REISSUE; From fb952695c8516dbd3dab639bb4d105bbecf5d82d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 16 Oct 2022 17:24:10 -0600 Subject: [PATCH 1357/4345] UPSTREAM: io_uring/rw: remove leftover debug statement commit 5c61795ea97c170347c5c4af0c159bd877b8af71 upstream. This debug statement was never meant to go into the upstream release, kill it off before it ends up in a release. It was just part of the testing for the initial version of the patch. Fixes: 2ec33a6c3cca ("io_uring/rw: ensure kiocb_end_write() is always called") Change-Id: Iee9f436c34cc137a7ab934aafa3aa0c584369418 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Bug: 268174392 (cherry picked from commit e699cce29accb713200ba94c88c5b98e2ccf4b75) Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index d1a079b7f1ca..2be25b6fe65a 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2718,8 +2718,6 @@ static void io_req_io_end(struct io_kiocb *req) { struct io_rw *rw = &req->rw; - WARN_ON(!in_task()); - if (rw->kiocb.ki_flags & IOCB_WRITE) { kiocb_end_write(req); fsnotify_modify(req->file); From b34e092097a727ad3bb2eea81e9b6791dda61280 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 18 Feb 2023 09:12:29 +0000 Subject: [PATCH 1358/4345] Revert "nvmem: core: Fix a conflict between MTD and NVMEM on wp-gpios property" This reverts commit 34ec4c7831c416ac56619477f1701986634a7efc which is commit f6c052afe6f802d87c74153b7a57c43b2e9faf07 upstream. It breaks the Android kernel api, and isn't even really needed in the 5.10.y kernel tree yet, as there are no users of the new field. So revert it for now. If it is needed, it can be brought back in an abi-safe way in the future. Bug: 161946584 Change-Id: I85af757d31cf1d9ef5b0ac3c36d8c2ee67f9bc7f Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 2 +- include/linux/nvmem-provider.h | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 48fbe49e3772..7b281ae540ad 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -629,7 +629,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (config->wp_gpio) nvmem->wp_gpio = config->wp_gpio; - else if (!config->ignore_wp) + else nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 39ec67689898..06409a6c40bc 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -49,8 +49,7 @@ enum nvmem_type { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin - * @ignore_wp: Write Protect pin is managed by the provider. + * @wp-gpio: Write protect pin * * Note: A default "nvmem" name will be assigned to the device if * no name is specified in its configuration. In such case "" is @@ -70,7 +69,6 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; - bool ignore_wp; bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; From a4d6d4d1e7c83952a668ac03998fca172829a3c2 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 17 Dec 2022 14:17:07 -0800 Subject: [PATCH 1359/4345] UPSTREAM: net_sched: reject TCF_EM_SIMPLE case for complex ematch module [ Upstream commit 9cd3fd2054c3b3055163accbf2f31a4426f10317 ] When TCF_EM_SIMPLE was introduced, it is supposed to be convenient for ematch implementation: https://lore.kernel.org/all/20050105110048.GO26856@postel.suug.ch/ "You don't have to, providing a 32bit data chunk without TCF_EM_SIMPLE set will simply result in allocating & copy. It's an optimization, nothing more." So if an ematch module provides ops->datalen that means it wants a complex data structure (saved in its em->data) instead of a simple u32 value. We should simply reject such a combination, otherwise this u32 could be misinterpreted as a pointer. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-and-tested-by: syzbot+4caeae4c7103813598ae@syzkaller.appspotmail.com Reported-by: Jun Nie Cc: Jamal Hadi Salim Cc: Paolo Abeni Signed-off-by: Cong Wang Acked-by: Paolo Abeni Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Bug: 262113355 Bug: 262114215 Change-Id: I03be57351f76f699d4635cf31178e0f3a19e61a5 Signed-off-by: Tudor Ambarus --- net/sched/ematch.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sched/ematch.c b/net/sched/ematch.c index f885bea5b452..b7154103e9cd 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -255,6 +255,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * the value carried. */ if (em_hdr->flags & TCF_EM_SIMPLE) { + if (em->ops->datalen > 0) + goto errout; if (data_len < sizeof(u32)) goto errout; em->data = *(u32 *) data; From 80b27def69a147215873e70cd3e093d87f4e902f Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 17 Aug 2022 21:27:01 +0800 Subject: [PATCH 1360/4345] UPSTREAM: ext4: add inode table check in __ext4_get_inode_loc to aovid possible infinite loop commit eee22187b53611e173161e38f61de1c7ecbeb876 upstream. In do_writepages, if the value returned by ext4_writepages is "-ENOMEM" and "wbc->sync_mode == WB_SYNC_ALL", retry until the condition is not met. In __ext4_get_inode_loc, if the bh returned by sb_getblk is NULL, the function returns -ENOMEM. In __getblk_slow, if the return value of grow_buffers is less than 0, the function returns NULL. When the three processes are connected in series like the following stack, an infinite loop may occur: do_writepages <--- keep retrying ext4_writepages mpage_map_and_submit_extent mpage_map_one_extent ext4_map_blocks ext4_ext_map_blocks ext4_ext_handle_unwritten_extents ext4_ext_convert_to_initialized ext4_split_extent ext4_split_extent_at __ext4_ext_dirty __ext4_mark_inode_dirty ext4_reserve_inode_write ext4_get_inode_loc __ext4_get_inode_loc <--- return -ENOMEM sb_getblk __getblk_gfp __getblk_slow <--- return NULL grow_buffers grow_dev_page <--- return -ENXIO ret = (block < end_block) ? 1 : -ENXIO; In this issue, bg_inode_table_hi is overwritten as an incorrect value. As a result, `block < end_block` cannot be met in grow_dev_page. Therefore, __ext4_get_inode_loc always returns '-ENOMEM' and do_writepages keeps retrying. As a result, the writeback process is in the D state due to an infinite loop. Add a check on inode table block in the __ext4_get_inode_loc function by referring to ext4_read_inode_bitmap to avoid this infinite loop. Cc: stable@kernel.org Signed-off-by: Baokun Li Reviewed-by: Ritesh Harjani (IBM) Link: https://lore.kernel.org/r/20220817132701.3015912-3-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman Bug: 264629802 Bug: 264632463 Change-Id: Id3bb71336059cac33f16fca383e783add3a01295 Signed-off-by: Tudor Ambarus --- fs/ext4/inode.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 3c8859b33326..8c9e57490cfd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4418,9 +4418,17 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; inode_offset = ((ino - 1) % EXT4_INODES_PER_GROUP(sb)); - block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block); iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb); + block = ext4_inode_table(sb, gdp); + if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) || + (block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) { + ext4_error(sb, "Invalid inode table block %llu in " + "block_group %u", block, iloc->block_group); + return -EFSCORRUPTED; + } + block += (inode_offset / inodes_per_block); + bh = sb_getblk(sb, block); if (unlikely(!bh)) return -ENOMEM; From 579f8bf863e6fba89813edb55150e76869ad2799 Mon Sep 17 00:00:00 2001 From: Chun-Hung Wu Date: Mon, 20 Feb 2023 09:55:16 +0800 Subject: [PATCH 1361/4345] ANDROID: Update symbol list for mtk Leaf changes summary: 1 artifact changed (2 filtered out) Changed leaf types summary: 0 (1 filtered out) leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 1 Added function Removed/Changed/Added variables summary: 0 Removed, 0 Changed (1 filtered out), 0 Added variable 1 Added function: [A] 'function void arm64_noalias_setup_dma_ops(device*)' Bug: 223346425 Change-Id: I34405abbdd5bc7dd3f2e19718a5dd483ac01c95e Signed-off-by: Chun-Hung Wu --- android/abi_gki_aarch64.xml | 641 ++++++++++++++---------------------- android/abi_gki_aarch64_mtk | 1 + 2 files changed, 252 insertions(+), 390 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 1bc86e8755d1..cd677dd12122 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -863,6 +863,7 @@ + @@ -14971,37 +14972,12 @@ - + - - - - - - - - - - - - - - - - - - - - - - - - - - - + + @@ -15013,7 +14989,6 @@ - @@ -23534,7 +23509,7 @@ - + @@ -25218,6 +25193,17 @@ + + + + + + + + + + + @@ -33724,7 +33710,7 @@ - + @@ -36598,105 +36584,105 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -37508,12 +37494,6 @@ - - - - - - @@ -37916,38 +37896,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -38164,7 +38112,7 @@ - + @@ -44536,23 +44484,7 @@ - - - - - - - - - - - - - - - - - + @@ -45302,9 +45234,6 @@ - - - @@ -48882,7 +48811,6 @@ - @@ -53826,13 +53754,6 @@ - - - - - - - @@ -62402,15 +62323,15 @@ - + - + - + - + @@ -62844,7 +62765,6 @@ - @@ -63603,18 +63523,18 @@ - + - + - + - + - + @@ -66493,13 +66413,6 @@ - - - - - - - @@ -69908,26 +69821,7 @@ - - - - - - - - - - - - - - - - - - - - + @@ -70085,18 +69979,18 @@ - + - + - + - + - + @@ -83817,9 +83711,6 @@ - - - @@ -85457,31 +85348,31 @@ - + - + - + - + - + - + - + - + - + @@ -91248,7 +91139,6 @@ - @@ -92801,9 +92691,6 @@ - - - @@ -96569,17 +96456,7 @@ - - - - - - - - - - - + @@ -103015,12 +102892,6 @@ - - - - - - @@ -103748,12 +103619,12 @@ - + - + - + @@ -106143,20 +106014,7 @@ - - - - - - - - - - - - - - + @@ -106527,12 +106385,12 @@ - + - + - + @@ -109037,27 +108895,27 @@ - + - + - + - + - + - + - + - + @@ -110765,21 +110623,21 @@ - + - + - + - + - + - + @@ -111266,7 +111124,6 @@ - @@ -116329,9 +116186,9 @@ - + - + @@ -116651,9 +116508,9 @@ - - - + + + @@ -116991,8 +116848,8 @@ - - + + @@ -117066,12 +116923,12 @@ - - - - - - + + + + + + @@ -121342,9 +121199,9 @@ - - - + + + @@ -121964,6 +121821,10 @@ + + + + @@ -130409,10 +130270,10 @@ - - - - + + + + @@ -130685,27 +130546,27 @@ - - + + - - + + - - + + - - - - + + + + - - - + + + @@ -130802,13 +130663,13 @@ - - - + + + - - + + @@ -130889,21 +130750,21 @@ - - - + + + - - - - + + + + - - - - + + + + @@ -131428,10 +131289,10 @@ - - - - + + + + @@ -131709,9 +131570,9 @@ - - - + + + @@ -131988,12 +131849,12 @@ - - + + - - + + @@ -132020,8 +131881,8 @@ - - + + @@ -132434,9 +132295,9 @@ - - - + + + @@ -134448,11 +134309,11 @@ - - - - - + + + + + @@ -134541,33 +134402,33 @@ - - - - + + + + - - - - + + + + - - - - - + + + + + - - - + + + @@ -134609,14 +134470,14 @@ - - - + + + - - - + + + @@ -136409,8 +136270,8 @@ - - + + @@ -136928,9 +136789,9 @@ - - - + + + @@ -137913,10 +137774,10 @@ - - - - + + + + @@ -137964,10 +137825,10 @@ - - - - + + + + @@ -140196,8 +140057,8 @@ - - + + @@ -141160,10 +141021,10 @@ - - - - + + + + @@ -143046,10 +142907,10 @@ - - - - + + + + @@ -144673,8 +144534,8 @@ - - + + @@ -144689,8 +144550,8 @@ - - + + @@ -145057,9 +144918,9 @@ - - - + + + @@ -148914,8 +148775,8 @@ - - + + @@ -149311,10 +149172,10 @@ - - - - + + + + @@ -149335,12 +149196,12 @@ - + - - - + + + @@ -149348,8 +149209,8 @@ - - + + @@ -149363,15 +149224,15 @@ - - + + - - - - - + + + + + @@ -149499,17 +149360,17 @@ - - + + - - + + - - - + + + diff --git a/android/abi_gki_aarch64_mtk b/android/abi_gki_aarch64_mtk index 8d2c95696079..253f8ff87289 100644 --- a/android/abi_gki_aarch64_mtk +++ b/android/abi_gki_aarch64_mtk @@ -34,6 +34,7 @@ __arch_copy_to_user arch_timer_read_counter arm64_const_caps_ready + arm64_noalias_setup_dma_ops arm64_use_ng_mappings __arm_smccc_hvc __arm_smccc_smc From 781e1c83ef75dfbe34f475f4c6d4821556b148a8 Mon Sep 17 00:00:00 2001 From: Sarannya S Date: Fri, 17 Feb 2023 12:26:24 +0530 Subject: [PATCH 1362/4345] ANDROID: ABI: Update allowed list for QCOM Add __xa_alloc_cyclic to the symbol list. This function will be used in qrtr for cyclic port id allocation. Leaf changes summary: 1 artifact changed (2 filtered out) Changed leaf types summary: 0 (1 filtered out) leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 1 Added function Removed/Changed/Added variables summary: 0 Removed, 0 Changed (1 filtered out), 0 Added variable 1 Added function: [A] 'function int __xa_alloc_cyclic(xarray*, u32*, void*, xa_limit, u32*, gfp_t)' Bug: 269687040 Change-Id: I9543ad1320e79daa781f0075decd74612bc694a1 Signed-off-by: Sarannya S --- android/abi_gki_aarch64.xml | 10 ++++++++++ android/abi_gki_aarch64_qcom | 1 + 2 files changed, 11 insertions(+) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index cd677dd12122..0b8222af6994 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -754,6 +754,7 @@ + @@ -121258,6 +121259,15 @@ + + + + + + + + + diff --git a/android/abi_gki_aarch64_qcom b/android/abi_gki_aarch64_qcom index f3e65159f870..0004b141d673 100644 --- a/android/abi_gki_aarch64_qcom +++ b/android/abi_gki_aarch64_qcom @@ -3045,6 +3045,7 @@ ww_mutex_lock ww_mutex_unlock __xa_alloc + __xa_alloc_cyclic xa_destroy xa_erase xa_find From f0be4b9779cbe5fd83338ebdfc888a540d1903be Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 18 Feb 2023 14:04:57 +0000 Subject: [PATCH 1363/4345] Revert "ANDROID: GKI: loadavg: Export for get_avenrun" This reverts commit 64ea6f327359a90eca8ec9fe2a8f0caba0188e45. The symbol get_avenrun is not used by any external modules, so remove the export as it is useless. If this is needed, the original commit can be added back and the symbol added to the relevant symbol list. Bug: 158067689 Bug: 203756332 Cc: Abhilasha Rao Cc: Todd Kjos Change-Id: I394d074a6cd4afaaf8eb97d528e039bc168e2fe1 Signed-off-by: Greg Kroah-Hartman --- kernel/sched/loadavg.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index b5837e27718e..d2a655643a02 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -75,7 +75,6 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift) loads[1] = (avenrun[1] + offset) << shift; loads[2] = (avenrun[2] + offset) << shift; } -EXPORT_SYMBOL_GPL(get_avenrun); long calc_load_fold_active(struct rq *this_rq, long adjust) { From 6a8037d4ebdaf8cf28234fcaef94b9e63905c499 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Mon, 13 Feb 2023 23:00:38 +0530 Subject: [PATCH 1364/4345] UPSTREAM: usb: gadget: u_serial: Add null pointer check in gserial_resume Consider a case where gserial_disconnect has already cleared gser->ioport. And if a wakeup interrupt triggers afterwards, gserial_resume gets called, which will lead to accessing of gser->ioport and thus causing null pointer dereference.Add a null pointer check to prevent this. Added a static spinlock to prevent gser->ioport from becoming null after the newly added check. Fixes: aba3a8d01d62 ("usb: gadget: u_serial: add suspend resume callbacks") Cc: stable Signed-off-by: Prashanth K Acked-by: Alan Stern Link: https://lore.kernel.org/r/1676309438-14922-1-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman Bug: 270271430 (cherry picked from commit 5ec63fdbca604568890c577753c6f66c5b3ef0b5 https://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git/ usb-next) Change-Id: Ib54ccfc7921fd399d538d93d13d6fe8beef0fb39 Signed-off-by: Prashanth K --- drivers/usb/gadget/function/u_serial.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 1e59204ec7aa..948eabf3cebd 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -81,6 +81,9 @@ #define WRITE_BUF_SIZE 8192 /* TX only */ #define GS_CONSOLE_BUF_SIZE 8192 +/* Prevents race conditions while accessing gser->ioport */ +static DEFINE_SPINLOCK(serial_port_lock); + /* console info */ struct gs_console { struct console console; @@ -1374,8 +1377,10 @@ void gserial_disconnect(struct gserial *gser) if (!port) return; + spin_lock_irqsave(&serial_port_lock, flags); + /* tell the TTY glue not to do I/O here any more */ - spin_lock_irqsave(&port->port_lock, flags); + spin_lock(&port->port_lock); gs_console_disconnect(port); @@ -1390,7 +1395,8 @@ void gserial_disconnect(struct gserial *gser) tty_hangup(port->port.tty); } port->suspended = false; - spin_unlock_irqrestore(&port->port_lock, flags); + spin_unlock(&port->port_lock); + spin_unlock_irqrestore(&serial_port_lock, flags); /* disable endpoints, aborting down any active I/O */ usb_ep_disable(gser->out); @@ -1424,10 +1430,19 @@ EXPORT_SYMBOL_GPL(gserial_suspend); void gserial_resume(struct gserial *gser) { - struct gs_port *port = gser->ioport; + struct gs_port *port; unsigned long flags; - spin_lock_irqsave(&port->port_lock, flags); + spin_lock_irqsave(&serial_port_lock, flags); + port = gser->ioport; + + if (!port) { + spin_unlock_irqrestore(&serial_port_lock, flags); + return; + } + + spin_lock(&port->port_lock); + spin_unlock(&serial_port_lock); port->suspended = false; if (!port->start_delayed) { spin_unlock_irqrestore(&port->port_lock, flags); From 7d3a5ec579759a57b0a6c192e2aadab956879a26 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 19 Jan 2023 18:34:56 +0200 Subject: [PATCH 1365/4345] ASoC: Intel: sof_rt5682: always set dpcm_capture for amplifiers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 324f065cdbaba1b879a63bf07e61ca156b789537 ] The amplifier may provide hardware support for I/V feedback, or alternatively the firmware may generate an echo reference attached to the SSP and dailink used for the amplifier. To avoid any issues with invalid/NULL substreams in the latter case, always unconditionally set dpcm_capture. Link: https://github.com/thesofproject/linux/issues/4083 Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Péter Ujfalusi Reviewed-by: Bard Liao Signed-off-by: Kai Vehmanen Link: https://lore.kernel.org/r/20230119163459.2235843-2-kai.vehmanen@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/intel/boards/sof_rt5682.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index 1f94fa5a15db..5883d1fa3b7e 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -704,6 +704,9 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].num_platforms = ARRAY_SIZE(platform_component); links[id].nonatomic = true; links[id].dpcm_playback = 1; + /* feedback stream or firmware-generated echo reference */ + links[id].dpcm_capture = 1; + links[id].no_pcm = 1; links[id].cpus = &cpus[id]; links[id].num_cpus = 1; From 490fcbc7b5f6c4d7841de2baf59211dd3395cf21 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 6 Jan 2023 16:22:14 +0200 Subject: [PATCH 1366/4345] selftests/bpf: Verify copy_register_state() preserves parent/live fields [ Upstream commit b9fa9bc839291020b362ab5392e5f18ba79657ac ] A testcase to check that verifier.c:copy_register_state() preserves register parentage chain and livness information. Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20230106142214.1040390-3-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- .../selftests/bpf/verifier/search_pruning.c | 36 +++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 7e50cb80873a..7e36078f8f48 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -154,3 +154,39 @@ .result_unpriv = ACCEPT, .insn_processed = 15, }, +/* The test performs a conditional 64-bit write to a stack location + * fp[-8], this is followed by an unconditional 8-bit write to fp[-8], + * then data is read from fp[-8]. This sequence is unsafe. + * + * The test would be mistakenly marked as safe w/o dst register parent + * preservation in verifier.c:copy_register_state() function. + * + * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the + * checkpoint state after conditional 64-bit assignment. + */ +{ + "write tracking and register parent chain bug", + .insns = { + /* r6 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* r0 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + /* if r0 > r6 goto +1 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1), + /* *(u64 *)(r10 - 8) = 0xdeadbeef */ + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef), + /* r1 = 42 */ + BPF_MOV64_IMM(BPF_REG_1, 42), + /* *(u8 *)(r10 - 8) = r1 */ + BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8), + /* r2 = *(u64 *)(r10 - 8) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8), + /* exit(0) */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = "invalid read from stack off -8+1 size 8", + .result = REJECT, +}, From 7fc4e7191eae9d9325511e03deadfdb2224914f8 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Thu, 19 Jan 2023 15:32:35 +0100 Subject: [PATCH 1367/4345] ALSA: hda: Do not unset preset when cleaning up codec [ Upstream commit 87978e6ad45a16835cc58234451111091be3c59a ] Several functions that take part in codec's initialization and removal are re-used by ASoC codec drivers implementations. Drivers mimic the behavior of hda_codec_driver_probe/remove() found in sound/pci/hda/hda_bind.c with their component->probe/remove() instead. One of the reasons for that is the expectation of snd_hda_codec_device_new() to receive a valid pointer to an instance of struct snd_card. This expectation can be met only once sound card components probing commences. As ASoC sound card may be unbound without codec device being actually removed from the system, unsetting ->preset in snd_hda_codec_cleanup_for_unbind() interferes with module unload -> load scenario causing null-ptr-deref. Preset is assigned only once, during device/driver matching whereas ASoC codec driver's module reloading may occur several times throughout the lifetime of an audio stack. Suggested-by: Takashi Iwai Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20230119143235.1159814-1-cezary.rojewski@intel.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/hda_bind.c | 2 ++ sound/pci/hda/hda_codec.c | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 4efbcc41fdfb..0a83afa5f373 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -143,6 +143,7 @@ static int hda_codec_driver_probe(struct device *dev) error: snd_hda_codec_cleanup_for_unbind(codec); + codec->preset = NULL; return err; } @@ -159,6 +160,7 @@ static int hda_codec_driver_remove(struct device *dev) if (codec->patch_ops.free) codec->patch_ops.free(codec); snd_hda_codec_cleanup_for_unbind(codec); + codec->preset = NULL; module_put(dev->driver->owner); return 0; } diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 39281106477e..fc4a64a83ff2 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -784,7 +784,6 @@ void snd_hda_codec_cleanup_for_unbind(struct hda_codec *codec) snd_array_free(&codec->cvt_setups); snd_array_free(&codec->spdif_out); snd_array_free(&codec->verbs); - codec->preset = NULL; codec->follower_dig_outs = NULL; codec->spdif_status_reset = 0; snd_array_free(&codec->mixers); From 3ec44268e29cb0f3ed65aa12624d8589d7ac2feb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 26 Jan 2023 17:21:24 +0100 Subject: [PATCH 1368/4345] ASoC: cs42l56: fix DT probe [ Upstream commit e18c6da62edc780e4f4f3c9ce07bdacd69505182 ] While looking through legacy platform data users, I noticed that the DT probing never uses data from the DT properties, as the platform_data structure gets overwritten directly after it is initialized. There have never been any boards defining the platform_data in the mainline kernel either, so this driver so far only worked with patched kernels or with the default values. For the benefit of possible downstream users, fix the DT probe by no longer overwriting the data. Signed-off-by: Arnd Bergmann Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20230126162203.2986339-1-arnd@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/cs42l56.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/sound/soc/codecs/cs42l56.c b/sound/soc/codecs/cs42l56.c index d41e03193106..3c5ec47a8fe6 100644 --- a/sound/soc/codecs/cs42l56.c +++ b/sound/soc/codecs/cs42l56.c @@ -1193,18 +1193,12 @@ static int cs42l56_i2c_probe(struct i2c_client *i2c_client, if (pdata) { cs42l56->pdata = *pdata; } else { - pdata = devm_kzalloc(&i2c_client->dev, sizeof(*pdata), - GFP_KERNEL); - if (!pdata) - return -ENOMEM; - if (i2c_client->dev.of_node) { ret = cs42l56_handle_of_data(i2c_client, &cs42l56->pdata); if (ret != 0) return ret; } - cs42l56->pdata = *pdata; } if (cs42l56->pdata.gpio_nreset) { From 37bb61763d9f62c12064c0c5b37ec4edcc7f5e76 Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Tue, 10 Jan 2023 12:43:10 +0900 Subject: [PATCH 1369/4345] tools/virtio: fix the vringh test for virtio ring changes [ Upstream commit 3f7b75abf41cc4143aa295f62acbb060a012868d ] Fix the build caused by missing kmsan_handle_dma() and is_power_of_2() that are used in drivers/virtio/virtio_ring.c. Signed-off-by: Shunsuke Mie Message-Id: <20230110034310.779744-1-mie@igel.co.jp> Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- tools/virtio/linux/bug.h | 8 +++----- tools/virtio/linux/build_bug.h | 7 +++++++ tools/virtio/linux/cpumask.h | 7 +++++++ tools/virtio/linux/gfp.h | 7 +++++++ tools/virtio/linux/kernel.h | 1 + tools/virtio/linux/kmsan.h | 12 ++++++++++++ tools/virtio/linux/scatterlist.h | 1 + tools/virtio/linux/topology.h | 7 +++++++ 8 files changed, 45 insertions(+), 5 deletions(-) create mode 100644 tools/virtio/linux/build_bug.h create mode 100644 tools/virtio/linux/cpumask.h create mode 100644 tools/virtio/linux/gfp.h create mode 100644 tools/virtio/linux/kmsan.h create mode 100644 tools/virtio/linux/topology.h diff --git a/tools/virtio/linux/bug.h b/tools/virtio/linux/bug.h index b14c2c3b6b85..74aef964f509 100644 --- a/tools/virtio/linux/bug.h +++ b/tools/virtio/linux/bug.h @@ -1,11 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef BUG_H -#define BUG_H +#ifndef _LINUX_BUG_H +#define _LINUX_BUG_H #define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond)) -#define BUILD_BUG_ON(x) - #define BUG() abort() -#endif /* BUG_H */ +#endif /* _LINUX_BUG_H */ diff --git a/tools/virtio/linux/build_bug.h b/tools/virtio/linux/build_bug.h new file mode 100644 index 000000000000..cdbb75e28a60 --- /dev/null +++ b/tools/virtio/linux/build_bug.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#define BUILD_BUG_ON(x) + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/tools/virtio/linux/cpumask.h b/tools/virtio/linux/cpumask.h new file mode 100644 index 000000000000..307da69d6b26 --- /dev/null +++ b/tools/virtio/linux/cpumask.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CPUMASK_H +#define _LINUX_CPUMASK_H + +#include + +#endif /* _LINUX_CPUMASK_H */ diff --git a/tools/virtio/linux/gfp.h b/tools/virtio/linux/gfp.h new file mode 100644 index 000000000000..43d146f236f1 --- /dev/null +++ b/tools/virtio/linux/gfp.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GFP_H +#define __LINUX_GFP_H + +#include + +#endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 315e85cabeda..063ccc897564 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -10,6 +10,7 @@ #include #include +#include #include #include #include diff --git a/tools/virtio/linux/kmsan.h b/tools/virtio/linux/kmsan.h new file mode 100644 index 000000000000..272b5aa285d5 --- /dev/null +++ b/tools/virtio/linux/kmsan.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KMSAN_H +#define _LINUX_KMSAN_H + +#include + +inline void kmsan_handle_dma(struct page *page, size_t offset, size_t size, + enum dma_data_direction dir) +{ +} + +#endif /* _LINUX_KMSAN_H */ diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h index 369ee308b668..74d9e1825748 100644 --- a/tools/virtio/linux/scatterlist.h +++ b/tools/virtio/linux/scatterlist.h @@ -2,6 +2,7 @@ #ifndef SCATTERLIST_H #define SCATTERLIST_H #include +#include struct scatterlist { unsigned long page_link; diff --git a/tools/virtio/linux/topology.h b/tools/virtio/linux/topology.h new file mode 100644 index 000000000000..910794afb993 --- /dev/null +++ b/tools/virtio/linux/topology.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TOPOLOGY_H +#define _LINUX_TOPOLOGY_H + +#include + +#endif /* _LINUX_TOPOLOGY_H */ From aa84a8cc1b536883bc381d03fc036fa9b21d0e6a Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Wed, 25 Jan 2023 02:59:44 -0800 Subject: [PATCH 1370/4345] net/rose: Fix to not accept on connected socket [ Upstream commit 14caefcf9837a2be765a566005ad82cd0d2a429f ] If you call listen() and accept() on an already connect()ed rose socket, accept() can successfully connect. This is because when the peer socket sends data to sendmsg, the skb with its own sk stored in the connected socket's sk->sk_receive_queue is connected, and rose_accept() dequeues the skb waiting in the sk->sk_receive_queue. This creates a child socket with the sk of the parent rose socket, which can cause confusion. Fix rose_listen() to return -EINVAL if the socket has already been successfully connected, and add lock_sock to prevent this issue. Signed-off-by: Hyunwoo Kim Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230125105944.GA133314@ubuntu Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/rose/af_rose.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 29a208ed8fb8..86c93cf1744b 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -487,6 +487,12 @@ static int rose_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; + lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { struct rose_sock *rose = rose_sk(sk); @@ -496,8 +502,10 @@ static int rose_listen(struct socket *sock, int backlog) memset(rose->dest_digis, 0, AX25_ADDR_LEN * ROSE_MAX_DIGIS); sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; + release_sock(sk); return 0; } + release_sock(sk); return -EOPNOTSUPP; } From 614a58e00d7bcbaf0d698712e0decd29d53a3847 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 27 Jan 2023 00:35:39 +0300 Subject: [PATCH 1371/4345] net: stmmac: do not stop RX_CLK in Rx LPI state for qcs404 SoC [ Upstream commit 54aa39a513dbf2164ca462a19f04519b2407a224 ] Currently in phy_init_eee() the driver unconditionally configures the PHY to stop RX_CLK after entering Rx LPI state. This causes an LPI interrupt storm on my qcs404-base board. Change the PHY initialization so that for "qcom,qcs404-ethqos" compatible device RX_CLK continues to run even in Rx LPI state. Signed-off-by: Andrey Konovalov Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 2 ++ drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- include/linux/stmmac.h | 1 + 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index bfc4a92f1d92..78be62ecc9a9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -505,6 +505,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->has_gmac4 = 1; plat_dat->pmt = 1; plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); + if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) + plat_dat->rx_clk_runs_in_lpi = 1; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b52ca2fe04d8..1ec000d4c770 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1058,7 +1058,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, stmmac_mac_set(priv, priv->ioaddr, true); if (phy && priv->dma_cap.eee) { - priv->eee_active = phy_init_eee(phy, 1) >= 0; + priv->eee_active = + phy_init_eee(phy, !priv->plat->rx_clk_runs_in_lpi) >= 0; priv->eee_enabled = stmmac_eee_init(priv); priv->tx_lpi_enabled = priv->eee_enabled; stmmac_set_eee_pls(priv, priv->hw, true); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 40df88728a6f..abf7b8ec1fb6 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -199,6 +199,7 @@ struct plat_stmmacenet_data { int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; + bool rx_clk_runs_in_lpi; int has_xgmac; bool vlan_fail_q_en; u8 vlan_fail_q; From 90fcf55d83b20da1091f926a291af05fb74f61c6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 27 Jan 2023 14:40:37 -0800 Subject: [PATCH 1372/4345] net: sched: sch: Bounds check priority [ Upstream commit de5ca4c3852f896cacac2bf259597aab5e17d9e3 ] Nothing was explicitly bounds checking the priority index used to access clpriop[]. WARN and bail out early if it's pathological. Seen with GCC 13: ../net/sched/sch_htb.c: In function 'htb_activate_prios': ../net/sched/sch_htb.c:437:44: warning: array subscript [0, 31] is outside array bounds of 'struct htb_prio[8]' [-Warray-bounds=] 437 | if (p->inner.clprio[prio].feed.rb_node) | ~~~~~~~~~~~~~~~^~~~~~ ../net/sched/sch_htb.c:131:41: note: while referencing 'clprio' 131 | struct htb_prio clprio[TC_HTB_NUMPRIO]; | ^~~~~~ Cc: Jamal Hadi Salim Cc: Cong Wang Cc: Jiri Pirko Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Simon Horman Reviewed-by: Cong Wang Link: https://lore.kernel.org/r/20230127224036.never.561-kees@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/sch_htb.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c3ba018fd083..c3e773d2ca41 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -405,7 +405,10 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (cl->cmode == HTB_MAY_BORROW && p && mask) { m = mask; while (m) { - int prio = ffz(~m); + unsigned int prio = ffz(~m); + + if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio))) + break; m &= ~(1 << prio); if (p->inner.clprio[prio].feed.rb_node) From 55dbd6f4ea954751340f4f73d5dcd7c8f12208b2 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sun, 29 Jan 2023 23:47:23 +0100 Subject: [PATCH 1373/4345] s390/decompressor: specify __decompress() buf len to avoid overflow [ Upstream commit 7ab41c2c08a32132ba8c14624910e2fe8ce4ba4b ] Historically calls to __decompress() didn't specify "out_len" parameter on many architectures including s390, expecting that no writes beyond uncompressed kernel image are performed. This has changed since commit 2aa14b1ab2c4 ("zstd: import usptream v1.5.2") which includes zstd library commit 6a7ede3dfccb ("Reduce size of dctx by reutilizing dst buffer (#2751)"). Now zstd decompression code might store literal buffer in the unwritten portion of the destination buffer. Since "out_len" is not set, it is considered to be unlimited and hence free to use for optimization needs. On s390 this might corrupt initrd or ipl report which are often placed right after the decompressor buffer. Luckily the size of uncompressed kernel image is already known to the decompressor, so to avoid the problem simply specify it in the "out_len" parameter. Link: https://github.com/facebook/zstd/commit/6a7ede3dfccb Signed-off-by: Vasily Gorbik Tested-by: Alexander Egorenkov Link: https://lore.kernel.org/r/patch-1.thread-41c676.git-41c676c2d153.your-ad-here.call-01675030179-ext-9637@work.hours Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- arch/s390/boot/compressed/decompressor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/compressed/decompressor.c index 3061b11c4d27..8eaa1712a1c8 100644 --- a/arch/s390/boot/compressed/decompressor.c +++ b/arch/s390/boot/compressed/decompressor.c @@ -79,6 +79,6 @@ void *decompress_kernel(void) void *output = (void *)decompress_offset; __decompress(_compressed_start, _compressed_end - _compressed_start, - NULL, NULL, output, 0, NULL, error); + NULL, NULL, output, vmlinux.image_size, NULL, error); return output; } From ecf5b49df38fa26e5039894e247fa12a8b796799 Mon Sep 17 00:00:00 2001 From: Amit Engel Date: Mon, 23 Jan 2023 14:37:28 +0200 Subject: [PATCH 1374/4345] nvme-fc: fix a missing queue put in nvmet_fc_ls_create_association [ Upstream commit 0cab4404874f2de52617de8400c844891c6ea1ce ] As part of nvmet_fc_ls_create_association there is a case where nvmet_fc_alloc_target_queue fails right after a new association with an admin queue is created. In this case, no one releases the get taken in nvmet_fc_alloc_target_assoc. This fix is adding the missing put. Signed-off-by: Amit Engel Reviewed-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/target/fc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 640031cbda7c..46fc44ce8671 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1675,8 +1675,10 @@ nvmet_fc_ls_create_association(struct nvmet_fc_tgtport *tgtport, else { queue = nvmet_fc_alloc_target_queue(iod->assoc, 0, be16_to_cpu(rqst->assoc_cmd.sqsize)); - if (!queue) + if (!queue) { ret = VERR_QUEUE_ALLOC_FAIL; + nvmet_fc_tgt_a_put(iod->assoc); + } } } From 25f65c83f5f7c5de3d7c7f0b10e15a7413dfe5bf Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 2 Feb 2023 11:34:13 +0100 Subject: [PATCH 1375/4345] platform/x86: touchscreen_dmi: Add Chuwi Vi8 (CWI501) DMI match [ Upstream commit eecf2acd4a580e9364e5087daf0effca60a240b7 ] Add a DMI match for the CWI501 version of the Chuwi Vi8 tablet, pointing to the same chuwi_vi8_data as the existing CWI506 version DMI match. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230202103413.331459-1-hdegoede@redhat.com Signed-off-by: Sasha Levin --- drivers/platform/x86/touchscreen_dmi.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index bc26acace2c3..b96fbc8dba09 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -1030,6 +1030,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BIOS_DATE, "05/07/2016"), }, }, + { + /* Chuwi Vi8 (CWI501) */ + .driver_data = (void *)&chuwi_vi8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "i86"), + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI.W86JLBNR01"), + }, + }, { /* Chuwi Vi8 (CWI506) */ .driver_data = (void *)&chuwi_vi8_data, From a19a0f67dbb89ad2bfc466f2003841acba645884 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Fri, 16 Sep 2022 13:20:50 +0100 Subject: [PATCH 1376/4345] nvmem: core: add error handling for dev_set_name [ Upstream commit 5544e90c81261e82e02bbf7c6015a4b9c8c825ef ] The type of return value of dev_set_name is int, which may return wrong result, so we add error handling for it to reclaim memory of nvmem resource, and return early when an error occurs. Signed-off-by: Gaosheng Cui Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20220916122100.170016-4-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: ab3428cfd9aa ("nvmem: core: fix registration vs use race") Signed-off-by: Sasha Levin --- drivers/nvmem/core.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 48fbe49e3772..9da4edbabfe7 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -661,18 +661,24 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) switch (config->id) { case NVMEM_DEVID_NONE: - dev_set_name(&nvmem->dev, "%s", config->name); + rval = dev_set_name(&nvmem->dev, "%s", config->name); break; case NVMEM_DEVID_AUTO: - dev_set_name(&nvmem->dev, "%s%d", config->name, nvmem->id); + rval = dev_set_name(&nvmem->dev, "%s%d", config->name, nvmem->id); break; default: - dev_set_name(&nvmem->dev, "%s%d", + rval = dev_set_name(&nvmem->dev, "%s%d", config->name ? : "nvmem", config->name ? config->id : nvmem->id); break; } + if (rval) { + ida_free(&nvmem_ida, nvmem->id); + kfree(nvmem); + return ERR_PTR(rval); + } + nvmem->read_only = device_property_present(config->dev, "read-only") || config->read_only || !nvmem->reg_write; From 89991ededcb557dcfe6398fa37eb182d01cfe257 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 27 Jan 2023 10:40:09 +0000 Subject: [PATCH 1377/4345] nvmem: core: remove nvmem_config wp_gpio [ Upstream commit 569653f022a29a1a44ea9de5308b657228303fa5 ] No one provides wp_gpio, so let's remove it to avoid issues with the nvmem core putting this gpio. Cc: stable@vger.kernel.org Signed-off-by: Russell King (Oracle) Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230127104015.23839-5-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: ab3428cfd9aa ("nvmem: core: fix registration vs use race") Signed-off-by: Sasha Levin --- drivers/nvmem/core.c | 4 +--- include/linux/nvmem-provider.h | 2 -- 2 files changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 9da4edbabfe7..38c05fce7d74 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -627,9 +627,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->id = rval; - if (config->wp_gpio) - nvmem->wp_gpio = config->wp_gpio; - else if (!config->ignore_wp) + if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 39ec67689898..5e07f3cfad30 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -49,7 +49,6 @@ enum nvmem_type { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem" name will be assigned to the device if @@ -64,7 +63,6 @@ struct nvmem_config { const char *name; int id; struct module *owner; - struct gpio_desc *wp_gpio; const struct nvmem_cell_info *cells; int ncells; enum nvmem_type type; From 23676ecd2eb377f7c24a6ff578b0f4c7135658b6 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 27 Jan 2023 10:40:10 +0000 Subject: [PATCH 1378/4345] nvmem: core: fix cleanup after dev_set_name() [ Upstream commit 560181d3ace61825f4ca9dd3481d6c0ee6709fa8 ] If dev_set_name() fails, we leak nvmem->wp_gpio as the cleanup does not put this. While a minimal fix for this would be to add the gpiod_put() call, we can do better if we split device_register(), and use the tested nvmem_release() cleanup code by initialising the device early, and putting the device. This results in a slightly larger fix, but results in clear code. Note: this patch depends on "nvmem: core: initialise nvmem->id early" and "nvmem: core: remove nvmem_config wp_gpio". Fixes: 5544e90c8126 ("nvmem: core: add error handling for dev_set_name") Cc: stable@vger.kernel.org Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Russell King (Oracle) [Srini: Fixed subject line and error code handing with wp_gpio while applying.] Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230127104015.23839-6-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: ab3428cfd9aa ("nvmem: core: fix registration vs use race") Signed-off-by: Sasha Levin --- drivers/nvmem/core.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 38c05fce7d74..de356cdde4ce 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -627,14 +627,18 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->id = rval; + nvmem->dev.type = &nvmem_provider_type; + nvmem->dev.bus = &nvmem_bus_type; + nvmem->dev.parent = config->dev; + + device_initialize(&nvmem->dev); + if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { - ida_free(&nvmem_ida, nvmem->id); rval = PTR_ERR(nvmem->wp_gpio); - kfree(nvmem); - return ERR_PTR(rval); + goto err_put_device; } kref_init(&nvmem->refcnt); @@ -646,9 +650,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->stride = config->stride ?: 1; nvmem->word_size = config->word_size ?: 1; nvmem->size = config->size; - nvmem->dev.type = &nvmem_provider_type; - nvmem->dev.bus = &nvmem_bus_type; - nvmem->dev.parent = config->dev; nvmem->root_only = config->root_only; nvmem->priv = config->priv; nvmem->type = config->type; @@ -671,11 +672,8 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) break; } - if (rval) { - ida_free(&nvmem_ida, nvmem->id); - kfree(nvmem); - return ERR_PTR(rval); - } + if (rval) + goto err_put_device; nvmem->read_only = device_property_present(config->dev, "read-only") || config->read_only || !nvmem->reg_write; @@ -686,7 +684,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); - rval = device_register(&nvmem->dev); + rval = device_add(&nvmem->dev); if (rval) goto err_put_device; From 2dcb474af1d5d06c1e343a0d7248219bb87a08b7 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 27 Jan 2023 10:40:11 +0000 Subject: [PATCH 1379/4345] nvmem: core: fix registration vs use race [ Upstream commit ab3428cfd9aa2f3463ee4b2909b5bb2193bd0c4a ] The i.MX6 CPU frequency driver sometimes fails to register at boot time due to nvmem_cell_read_u32() sporadically returning -ENOENT. This happens because there is a window where __nvmem_device_get() in of_nvmem_cell_get() is able to return the nvmem device, but as cells have been setup, nvmem_find_cell_entry_by_node() returns NULL. The occurs because the nvmem core registration code violates one of the fundamental principles of kernel programming: do not publish data structures before their setup is complete. Fix this by making nvmem core code conform with this principle. Fixes: eace75cfdcf7 ("nvmem: Add a simple NVMEM framework for nvmem providers") Cc: stable@vger.kernel.org Signed-off-by: Russell King (Oracle) Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230127104015.23839-7-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/nvmem/core.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index de356cdde4ce..0ef7b95348b1 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -682,16 +682,10 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->dev.groups = nvmem_dev_groups; #endif - dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); - - rval = device_add(&nvmem->dev); - if (rval) - goto err_put_device; - if (config->compat) { rval = nvmem_sysfs_setup_compat(nvmem, config); if (rval) - goto err_device_del; + goto err_put_device; } if (config->cells) { @@ -708,6 +702,12 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (rval) goto err_remove_cells; + dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); + + rval = device_add(&nvmem->dev); + if (rval) + goto err_remove_cells; + blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem); return nvmem; @@ -716,8 +716,6 @@ err_remove_cells: nvmem_device_remove_all_cells(nvmem); if (config->compat) nvmem_sysfs_remove_compat(nvmem, config); -err_device_del: - device_del(&nvmem->dev); err_put_device: put_device(&nvmem->dev); From c261f798f7baa8080cf0214081d43d5f86bb073f Mon Sep 17 00:00:00 2001 From: Seth Jenkins Date: Tue, 31 Jan 2023 12:25:55 -0500 Subject: [PATCH 1380/4345] aio: fix mremap after fork null-deref commit 81e9d6f8647650a7bead74c5f926e29970e834d1 upstream. Commit e4a0d3e720e7 ("aio: Make it possible to remap aio ring") introduced a null-deref if mremap is called on an old aio mapping after fork as mm->ioctx_table will be set to NULL. [jmoyer@redhat.com: fix 80 column issue] Link: https://lkml.kernel.org/r/x49sffq4nvg.fsf@segfault.boston.devel.redhat.com Fixes: e4a0d3e720e7 ("aio: Make it possible to remap aio ring") Signed-off-by: Seth Jenkins Signed-off-by: Jeff Moyer Cc: Alexander Viro Cc: Benjamin LaHaise Cc: Jann Horn Cc: Pavel Emelyanov Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/aio.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/aio.c b/fs/aio.c index 2a9dfa58ec3a..5934ea84b499 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -335,6 +335,9 @@ static int aio_ring_mremap(struct vm_area_struct *vma) spin_lock(&mm->ioctx_lock); rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); + if (!table) + goto out_unlock; + for (i = 0; i < table->nr; i++) { struct kioctx *ctx; @@ -348,6 +351,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma) } } +out_unlock: rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); return res; From 645df4047bd67e368c5fe9783a115916c4128c1d Mon Sep 17 00:00:00 2001 From: Sumanth Korikkar Date: Wed, 15 Feb 2023 15:13:24 +0100 Subject: [PATCH 1381/4345] s390/signal: fix endless loop in do_signal No upstream commit exists: the problem addressed here is that 'commit 75309018a24d ("s390: add support for TIF_NOTIFY_SIGNAL")' was backported to 5.10. This commit is broken, but nobody noticed upstream, since shortly after s390 converted to generic entry with 'commit 56e62a737028 ("s390: convert to generic entry")', which implicitly fixed the problem outlined below. Thread flag is set to TIF_NOTIFY_SIGNAL for io_uring work. The io work user or syscall calls do_signal when either one of the TIF_SIGPENDING or TIF_NOTIFY_SIGNAL flag is set. However, do_signal does consider only TIF_SIGPENDING signal and ignores TIF_NOTIFY_SIGNAL condition. This means get_signal is never invoked for TIF_NOTIFY_SIGNAL and hence the flag is not cleared, which results in an endless do_signal loop. Reference: 'commit 788d0824269b ("io_uring: import 5.15-stable io_uring")' Fixes: 75309018a24d ("s390: add support for TIF_NOTIFY_SIGNAL") Cc: stable@vger.kernel.org # 5.10.162 Acked-by: Heiko Carstens Acked-by: Sven Schnelle Signed-off-by: Sumanth Korikkar Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index b27b6c1f058d..9e900a8977bd 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -472,7 +472,7 @@ void do_signal(struct pt_regs *regs) current->thread.system_call = test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0; - if (test_thread_flag(TIF_SIGPENDING) && get_signal(&ksig)) { + if (get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ if (current->thread.system_call) { regs->int_code = current->thread.system_call; From f6f94837d92f0f5f94700589bab6d880009dfc22 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 17 Oct 2022 17:06:38 +0200 Subject: [PATCH 1382/4345] ovl: remove privs in ovl_copyfile() commit b306e90ffabdaa7e3b3350dbcd19b7663e71ab17 upstream. Underlying fs doesn't remove privs because copy_range/remap_range are called with privileged mounter credentials. This fixes some failures in fstest generic/673. Fixes: 8ede205541ff ("ovl: add reflink/copyfile/dedup support") Acked-by: Miklos Szeredi Signed-off-by: Amir Goldstein Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/file.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index b019f27c1360..259b2d41b707 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -687,14 +687,23 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, const struct cred *old_cred; loff_t ret; + inode_lock(inode_out); + if (op != OVL_DEDUPE) { + /* Update mode */ + ovl_copyattr(ovl_inode_real(inode_out), inode_out); + ret = file_remove_privs(file_out); + if (ret) + goto out_unlock; + } + ret = ovl_real_fdget(file_out, &real_out); if (ret) - return ret; + goto out_unlock; ret = ovl_real_fdget(file_in, &real_in); if (ret) { fdput(real_out); - return ret; + goto out_unlock; } old_cred = ovl_override_creds(file_inode(file_out)->i_sb); @@ -723,6 +732,9 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, fdput(real_in); fdput(real_out); +out_unlock: + inode_unlock(inode_out); + return ret; } From 6618b0dcf265975555e3eb24183e2a9e9b1c947c Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 17 Oct 2022 17:06:39 +0200 Subject: [PATCH 1383/4345] ovl: remove privs in ovl_fallocate() commit 23a8ce16419a3066829ad4a8b7032a75817af65b upstream. Underlying fs doesn't remove privs because fallocate is called with privileged mounter credentials. This fixes some failure in fstests generic/683..687. Fixes: aab8848cee5e ("ovl: add ovl_fallocate()") Acked-by: Miklos Szeredi Signed-off-by: Amir Goldstein Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/file.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 259b2d41b707..0e734c8b4dfa 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -531,9 +531,16 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len const struct cred *old_cred; int ret; + inode_lock(inode); + /* Update mode */ + ovl_copyattr(ovl_inode_real(inode), inode); + ret = file_remove_privs(file); + if (ret) + goto out_unlock; + ret = ovl_real_fdget(file, &real); if (ret) - return ret; + goto out_unlock; old_cred = ovl_override_creds(file_inode(file)->i_sb); ret = vfs_fallocate(real.file, mode, offset, len); @@ -544,6 +551,9 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len fdput(real); +out_unlock: + inode_unlock(inode); + return ret; } From eaba3f9b672c3a3f820da8ee9584b9520674eafa Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 20 Aug 2022 17:54:06 +0200 Subject: [PATCH 1384/4345] netfilter: nft_tproxy: restrict to prerouting hook commit 18bbc3213383a82b05383827f4b1b882e3f0a5a5 upstream. TPROXY is only allowed from prerouting, but nft_tproxy doesn't check this. This fixes a crash (null dereference) when using tproxy from e.g. output. Fixes: 4ed8eb6570a4 ("netfilter: nf_tables: Add native tproxy support") Reported-by: Shell Chen Signed-off-by: Florian Westphal Signed-off-by: Qingfang DENG Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nft_tproxy.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 37c728bdad41..c49d318f8e6e 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -289,6 +289,13 @@ static int nft_tproxy_dump(struct sk_buff *skb, return 0; } +static int nft_tproxy_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING); +} + static struct nft_expr_type nft_tproxy_type; static const struct nft_expr_ops nft_tproxy_ops = { .type = &nft_tproxy_type, @@ -296,6 +303,7 @@ static const struct nft_expr_ops nft_tproxy_ops = { .eval = nft_tproxy_eval, .init = nft_tproxy_init, .dump = nft_tproxy_dump, + .validate = nft_tproxy_validate, }; static struct nft_expr_type nft_tproxy_type __read_mostly = { From 73ad25c50d3c3eba6ea4c6735a585c4613eae537 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 31 Jan 2023 21:02:28 +0000 Subject: [PATCH 1385/4345] mmc: jz4740: Work around bug on JZ4760(B) commit 3f18c5046e633cc4bbad396b74c05d46d353033d upstream. On JZ4760 and JZ4760B, SD cards fail to run if the maximum clock rate is set to 50 MHz, even though the controller officially does support it. Until the actual bug is found and fixed, limit the maximum clock rate to 24 MHz. Signed-off-by: Paul Cercueil Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230131210229.68129-1-paul@crapouillou.net Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/jz4740_mmc.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index aa3dfb9c1071..62d00232f85e 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -1041,6 +1041,16 @@ static int jz4740_mmc_probe(struct platform_device* pdev) mmc->ops = &jz4740_mmc_ops; if (!mmc->f_max) mmc->f_max = JZ_MMC_CLK_RATE; + + /* + * There seems to be a problem with this driver on the JZ4760 and + * JZ4760B SoCs. There, when using the maximum rate supported (50 MHz), + * the communication fails with many SD cards. + * Until this bug is sorted out, limit the maximum rate to 24 MHz. + */ + if (host->version == JZ_MMC_JZ4760 && mmc->f_max > JZ_MMC_CLK_RATE) + mmc->f_max = JZ_MMC_CLK_RATE; + mmc->f_min = mmc->f_max / 128; mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34; From 30716d9f0fa1766e522cf24c8a456244e4fc9931 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 30 Jan 2023 20:58:08 +0800 Subject: [PATCH 1386/4345] mmc: sdio: fix possible resource leaks in some error paths commit 605d9fb9556f8f5fb4566f4df1480f280f308ded upstream. If sdio_add_func() or sdio_init_func() fails, sdio_remove_func() can not release the resources, because the sdio function is not presented in these two cases, it won't call of_node_put() or put_device(). To fix these leaks, make sdio_func_present() only control whether device_del() needs to be called or not, then always call of_node_put() and put_device(). In error case in sdio_init_func(), the reference of 'card->dev' is not get, to avoid redundant put in sdio_free_func_cis(), move the get_device() to sdio_alloc_func() and put_device() to sdio_release_func(), it can keep the get/put function be balanced. Without this patch, while doing fault inject test, it can get the following leak reports, after this fix, the leak is gone. unreferenced object 0xffff888112514000 (size 2048): comm "kworker/3:2", pid 65, jiffies 4294741614 (age 124.774s) hex dump (first 32 bytes): 00 e0 6f 12 81 88 ff ff 60 58 8d 06 81 88 ff ff ..o.....`X...... 10 40 51 12 81 88 ff ff 10 40 51 12 81 88 ff ff .@Q......@Q..... backtrace: [<000000009e5931da>] kmalloc_trace+0x21/0x110 [<000000002f839ccb>] mmc_alloc_card+0x38/0xb0 [mmc_core] [<0000000004adcbf6>] mmc_sdio_init_card+0xde/0x170 [mmc_core] [<000000007538fea0>] mmc_attach_sdio+0xcb/0x1b0 [mmc_core] [<00000000d4fdeba7>] mmc_rescan+0x54a/0x640 [mmc_core] unreferenced object 0xffff888112511000 (size 2048): comm "kworker/3:2", pid 65, jiffies 4294741623 (age 124.766s) hex dump (first 32 bytes): 00 40 51 12 81 88 ff ff e0 58 8d 06 81 88 ff ff .@Q......X...... 10 10 51 12 81 88 ff ff 10 10 51 12 81 88 ff ff ..Q.......Q..... backtrace: [<000000009e5931da>] kmalloc_trace+0x21/0x110 [<00000000fcbe706c>] sdio_alloc_func+0x35/0x100 [mmc_core] [<00000000c68f4b50>] mmc_attach_sdio.cold.18+0xb1/0x395 [mmc_core] [<00000000d4fdeba7>] mmc_rescan+0x54a/0x640 [mmc_core] Fixes: 3d10a1ba0d37 ("sdio: fix reference counting in sdio_remove_func()") Signed-off-by: Yang Yingliang Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230130125808.3471254-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/core/sdio_bus.c | 17 ++++++++++++++--- drivers/mmc/core/sdio_cis.c | 12 ------------ 2 files changed, 14 insertions(+), 15 deletions(-) diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index a448535c1265..89dd49260080 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -295,6 +295,12 @@ static void sdio_release_func(struct device *dev) if (!(func->card->quirks & MMC_QUIRK_NONSTD_SDIO)) sdio_free_func_cis(func); + /* + * We have now removed the link to the tuples in the + * card structure, so remove the reference. + */ + put_device(&func->card->dev); + kfree(func->info); kfree(func->tmpbuf); kfree(func); @@ -325,6 +331,12 @@ struct sdio_func *sdio_alloc_func(struct mmc_card *card) device_initialize(&func->dev); + /* + * We may link to tuples in the card structure, + * we need make sure we have a reference to it. + */ + get_device(&func->card->dev); + func->dev.parent = &card->dev; func->dev.bus = &sdio_bus_type; func->dev.release = sdio_release_func; @@ -378,10 +390,9 @@ int sdio_add_func(struct sdio_func *func) */ void sdio_remove_func(struct sdio_func *func) { - if (!sdio_func_present(func)) - return; + if (sdio_func_present(func)) + device_del(&func->dev); - device_del(&func->dev); of_node_put(func->dev.of_node); put_device(&func->dev); } diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c index b23773583179..ce524f7e11fb 100644 --- a/drivers/mmc/core/sdio_cis.c +++ b/drivers/mmc/core/sdio_cis.c @@ -391,12 +391,6 @@ int sdio_read_func_cis(struct sdio_func *func) if (ret) return ret; - /* - * Since we've linked to tuples in the card structure, - * we must make sure we have a reference to it. - */ - get_device(&func->card->dev); - /* * Vendor/device id is optional for function CIS, so * copy it from the card structure as needed. @@ -422,11 +416,5 @@ void sdio_free_func_cis(struct sdio_func *func) } func->tuples = NULL; - - /* - * We have now removed the link to the tuples in the - * card structure, so remove the reference. - */ - put_device(&func->card->dev); } From 0b3edcb24bd81b3b2e3dac89f4733bfd47d283be Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 31 Jan 2023 09:38:35 +0800 Subject: [PATCH 1387/4345] mmc: mmc_spi: fix error handling in mmc_spi_probe() commit cf4c9d2ac1e42c7d18b921bec39486896645b714 upstream. If mmc_add_host() fails, it doesn't need to call mmc_remove_host(), or it will cause null-ptr-deref, because of deleting a not added device in mmc_remove_host(). To fix this, goto label 'fail_glue_init', if mmc_add_host() fails, and change the label 'fail_add_host' to 'fail_gpiod_request'. Fixes: 15a0580ced08 ("mmc_spi host driver") Signed-off-by: Yang Yingliang Cc:stable@vger.kernel.org Link: https://lore.kernel.org/r/20230131013835.3564011-1-yangyingliang@huawei.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/mmc_spi.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 02f4fd26e76a..1d814919eb6b 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1450,7 +1450,7 @@ static int mmc_spi_probe(struct spi_device *spi) status = mmc_add_host(mmc); if (status != 0) - goto fail_add_host; + goto fail_glue_init; /* * Index 0 is card detect @@ -1458,7 +1458,7 @@ static int mmc_spi_probe(struct spi_device *spi) */ status = mmc_gpiod_request_cd(mmc, NULL, 0, false, 1000); if (status == -EPROBE_DEFER) - goto fail_add_host; + goto fail_gpiod_request; if (!status) { /* * The platform has a CD GPIO signal that may support @@ -1473,7 +1473,7 @@ static int mmc_spi_probe(struct spi_device *spi) /* Index 1 is write protect/read only */ status = mmc_gpiod_request_ro(mmc, NULL, 1, 0); if (status == -EPROBE_DEFER) - goto fail_add_host; + goto fail_gpiod_request; if (!status) has_ro = true; @@ -1487,7 +1487,7 @@ static int mmc_spi_probe(struct spi_device *spi) ? ", cd polling" : ""); return 0; -fail_add_host: +fail_gpiod_request: mmc_remove_host(mmc); fail_glue_init: mmc_spi_dma_free(host); From 59d5c80ce538e64074e0f6089d94bb9928938a8a Mon Sep 17 00:00:00 2001 From: Bo Liu Date: Thu, 9 Feb 2023 10:13:48 +0800 Subject: [PATCH 1388/4345] ALSA: hda/conexant: add a new hda codec SN6180 commit 18d7e16c917a08f08778ecf2b780d63648d5d923 upstream. The current kernel does not support the SN6180 codec chip. Add the SN6180 codec configuration item to kernel. Signed-off-by: Bo Liu Cc: Link: https://lore.kernel.org/r/1675908828-1012-1-git-send-email-bo.liu@senarytech.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_conexant.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 2bd0a5839e80..48b802563c2d 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -1117,6 +1117,7 @@ static const struct hda_device_id snd_hda_id_conexant[] = { HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f120d0, "CX11970", patch_conexant_auto), + HDA_CODEC_ENTRY(0x14f120d1, "SN6180", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto), From 7ed5c147220fc205bb8a33ed36facc56ad6f3fd2 Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Mon, 13 Feb 2023 14:54:22 +0800 Subject: [PATCH 1389/4345] ALSA: hda/realtek - fixed wrong gpio assigned commit 2bdccfd290d421b50df4ec6a68d832dad1310748 upstream. GPIO2 PIN use for output. Mask Dir and Data need to assign for 0x4. Not 0x3. This fixed was for Lenovo Desktop(0x17aa1056). GPIO2 use for AMP enable. Signed-off-by: Kailang Yang Cc: Link: https://lore.kernel.org/r/8d02bb9ac8134f878cd08607fdf088fd@realtek.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index d66d2cf7708e..fffa681313b6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -827,7 +827,7 @@ do_sku: alc_setup_gpio(codec, 0x02); break; case 7: - alc_setup_gpio(codec, 0x03); + alc_setup_gpio(codec, 0x04); break; case 5: default: From ec9c7aa08819f976b2492fa63c41b5712d2924b5 Mon Sep 17 00:00:00 2001 From: Munehisa Kamata Date: Tue, 14 Feb 2023 13:27:05 -0800 Subject: [PATCH 1390/4345] sched/psi: Fix use-after-free in ep_remove_wait_queue() commit c2dbe32d5db5c4ead121cf86dabd5ab691fb47fe upstream. If a non-root cgroup gets removed when there is a thread that registered trigger and is polling on a pressure file within the cgroup, the polling waitqueue gets freed in the following path: do_rmdir cgroup_rmdir kernfs_drain_open_files cgroup_file_release cgroup_pressure_release psi_trigger_destroy However, the polling thread still has a reference to the pressure file and will access the freed waitqueue when the file is closed or upon exit: fput ep_eventpoll_release ep_free ep_remove_wait_queue remove_wait_queue This results in use-after-free as pasted below. The fundamental problem here is that cgroup_file_release() (and consequently waitqueue's lifetime) is not tied to the file's real lifetime. Using wake_up_pollfree() here might be less than ideal, but it is in line with the comment at commit 42288cb44c4b ("wait: add wake_up_pollfree()") since the waitqueue's lifetime is not tied to file's one and can be considered as another special case. While this would be fixable by somehow making cgroup_file_release() be tied to the fput(), it would require sizable refactoring at cgroups or higher layer which might be more justifiable if we identify more cases like this. BUG: KASAN: use-after-free in _raw_spin_lock_irqsave+0x60/0xc0 Write of size 4 at addr ffff88810e625328 by task a.out/4404 CPU: 19 PID: 4404 Comm: a.out Not tainted 6.2.0-rc6 #38 Hardware name: Amazon EC2 c5a.8xlarge/, BIOS 1.0 10/16/2017 Call Trace: dump_stack_lvl+0x73/0xa0 print_report+0x16c/0x4e0 kasan_report+0xc3/0xf0 kasan_check_range+0x2d2/0x310 _raw_spin_lock_irqsave+0x60/0xc0 remove_wait_queue+0x1a/0xa0 ep_free+0x12c/0x170 ep_eventpoll_release+0x26/0x30 __fput+0x202/0x400 task_work_run+0x11d/0x170 do_exit+0x495/0x1130 do_group_exit+0x100/0x100 get_signal+0xd67/0xde0 arch_do_signal_or_restart+0x2a/0x2b0 exit_to_user_mode_prepare+0x94/0x100 syscall_exit_to_user_mode+0x20/0x40 do_syscall_64+0x52/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Allocated by task 4404: kasan_set_track+0x3d/0x60 __kasan_kmalloc+0x85/0x90 psi_trigger_create+0x113/0x3e0 pressure_write+0x146/0x2e0 cgroup_file_write+0x11c/0x250 kernfs_fop_write_iter+0x186/0x220 vfs_write+0x3d8/0x5c0 ksys_write+0x90/0x110 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 4407: kasan_set_track+0x3d/0x60 kasan_save_free_info+0x27/0x40 ____kasan_slab_free+0x11d/0x170 slab_free_freelist_hook+0x87/0x150 __kmem_cache_free+0xcb/0x180 psi_trigger_destroy+0x2e8/0x310 cgroup_file_release+0x4f/0xb0 kernfs_drain_open_files+0x165/0x1f0 kernfs_drain+0x162/0x1a0 __kernfs_remove+0x1fb/0x310 kernfs_remove_by_name_ns+0x95/0xe0 cgroup_addrm_files+0x67f/0x700 cgroup_destroy_locked+0x283/0x3c0 cgroup_rmdir+0x29/0x100 kernfs_iop_rmdir+0xd1/0x140 vfs_rmdir+0xfe/0x240 do_rmdir+0x13d/0x280 __x64_sys_rmdir+0x2c/0x30 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 0e94682b73bf ("psi: introduce psi monitor") Signed-off-by: Munehisa Kamata Signed-off-by: Mengchi Cheng Signed-off-by: Ingo Molnar Acked-by: Suren Baghdasaryan Acked-by: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lore.kernel.org/lkml/20230106224859.4123476-1-kamatam@amazon.com/ Link: https://lore.kernel.org/r/20230214212705.4058045-1-kamatam@amazon.com Signed-off-by: Greg Kroah-Hartman --- kernel/sched/psi.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index b7f38f3ad42a..debaeb07ae53 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1158,10 +1158,11 @@ void psi_trigger_destroy(struct psi_trigger *t) group = t->group; /* - * Wakeup waiters to stop polling. Can happen if cgroup is deleted - * from under a polling process. + * Wakeup waiters to stop polling and clear the queue to prevent it from + * being accessed later. Can happen if cgroup is deleted from under a + * polling process. */ - wake_up_interruptible(&t->event_wait); + wake_up_pollfree(&t->event_wait); mutex_lock(&group->trigger_lock); From 9662320238b9903e691958add64f4125615a143a Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 15 Feb 2023 17:35:42 -0800 Subject: [PATCH 1391/4345] hugetlb: check for undefined shift on 32 bit architectures commit ec4288fe63966b26d53907212ecd05dfa81dd2cc upstream. Users can specify the hugetlb page size in the mmap, shmget and memfd_create system calls. This is done by using 6 bits within the flags argument to encode the base-2 logarithm of the desired page size. The routine hstate_sizelog() uses the log2 value to find the corresponding hugetlb hstate structure. Converting the log2 value (page_size_log) to potential hugetlb page size is the simple statement: 1UL << page_size_log Because only 6 bits are used for page_size_log, the left shift can not be greater than 63. This is fine on 64 bit architectures where a long is 64 bits. However, if a value greater than 31 is passed on a 32 bit architecture (where long is 32 bits) the shift will result in undefined behavior. This was generally not an issue as the result of the undefined shift had to exactly match hugetlb page size to proceed. Recent improvements in runtime checking have resulted in this undefined behavior throwing errors such as reported below. Fix by comparing page_size_log to BITS_PER_LONG before doing shift. Link: https://lkml.kernel.org/r/20230216013542.138708-1-mike.kravetz@oracle.com Link: https://lore.kernel.org/lkml/CA+G9fYuei_Tr-vN9GS7SfFyU1y9hNysnf=PB7kT0=yv4MiPgVg@mail.gmail.com/ Fixes: 42d7395feb56 ("mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB") Signed-off-by: Mike Kravetz Reported-by: Naresh Kamboju Reviewed-by: Jesper Juhl Acked-by: Muchun Song Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Cc: Anders Roxell Cc: Andi Kleen Cc: Sasha Levin Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/hugetlb.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c0ba379574a4..99b73fc4a824 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -542,7 +542,10 @@ static inline struct hstate *hstate_sizelog(int page_size_log) if (!page_size_log) return &default_hstate; - return size_to_hstate(1UL << page_size_log); + if (page_size_log < BITS_PER_LONG) + return size_to_hstate(1UL << page_size_log); + + return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) From 1933be146c96b5a707ce297eddfc3c49a9eec775 Mon Sep 17 00:00:00 2001 From: Aaron Thompson Date: Tue, 7 Feb 2023 08:21:51 +0000 Subject: [PATCH 1392/4345] Revert "mm: Always release pages to the buddy allocator in memblock_free_late()." commit 647037adcad00f2bab8828d3d41cd0553d41f3bd upstream. This reverts commit 115d9d77bb0f9152c60b6e8646369fa7f6167593. The pages being freed by memblock_free_late() have already been initialized, but if they are in the deferred init range, __free_one_page() might access nearby uninitialized pages when trying to coalesce buddies. This can, for example, trigger this BUG: BUG: unable to handle page fault for address: ffffe964c02580c8 RIP: 0010:__list_del_entry_valid+0x3f/0x70 __free_one_page+0x139/0x410 __free_pages_ok+0x21d/0x450 memblock_free_late+0x8c/0xb9 efi_free_boot_services+0x16b/0x25c efi_enter_virtual_mode+0x403/0x446 start_kernel+0x678/0x714 secondary_startup_64_no_verify+0xd2/0xdb A proper fix will be more involved so revert this change for the time being. Fixes: 115d9d77bb0f ("mm: Always release pages to the buddy allocator in memblock_free_late().") Signed-off-by: Aaron Thompson Link: https://lore.kernel.org/r/20230207082151.1303-1-dev@aaront.org Signed-off-by: Mike Rapoport (IBM) Signed-off-by: Greg Kroah-Hartman --- mm/memblock.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/mm/memblock.c b/mm/memblock.c index f6a4dffb9a88..f72d53957033 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1597,13 +1597,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { - /* - * Reserved pages are always initialized by the end of - * memblock_free_all() (by memmap_init() and, if deferred - * initialization is enabled, memmap_init_reserved_pages()), so - * these pages can be released directly to the buddy allocator. - */ - __free_pages_core(pfn_to_page(cursor), 0); + memblock_free_pages(pfn_to_page(cursor), cursor, 0); totalram_pages_inc(); } } From e2bf52ff159db37b5b60d34069464c00a1f54fd6 Mon Sep 17 00:00:00 2001 From: Felix Riemann Date: Fri, 10 Feb 2023 13:36:44 +0100 Subject: [PATCH 1393/4345] net: Fix unwanted sign extension in netdev_stats_to_stats64() commit 9b55d3f0a69af649c62cbc2633e6d695bb3cc583 upstream. When converting net_device_stats to rtnl_link_stats64 sign extension is triggered on ILP32 machines as 6c1c509778 changed the previous "ulong -> u64" conversion to "long -> u64" by accessing the net_device_stats fields through a (signed) atomic_long_t. This causes for example the received bytes counter to jump to 16EiB after having received 2^31 bytes. Casting the atomic value to "unsigned long" beforehand converting it into u64 avoids this. Fixes: 6c1c5097781f ("net: add atomic_long_t to net_device_stats fields") Signed-off-by: Felix Riemann Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 37bb60a7e97e..b7646d4e079b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10326,7 +10326,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) - dst[i] = atomic_long_read(&src[i]); + dst[i] = (unsigned long)atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); From 3a63392c19e95f631a7ed24a215727d059c1feeb Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 2 Feb 2023 18:07:35 -0800 Subject: [PATCH 1394/4345] revert "squashfs: harden sanity check in squashfs_read_xattr_id_table" commit a5b21d8d791cd4db609d0bbcaa9e0c7e019888d1 upstream. This fix was nacked by Philip, for reasons identified in the email linked below. Link: https://lkml.kernel.org/r/68f15d67-8945-2728-1f17-5b53a80ec52d@squashfs.org.uk Fixes: 72e544b1b28325 ("squashfs: harden sanity check in squashfs_read_xattr_id_table") Cc: Alexey Khoroshilov Cc: Fedor Pchelkin Cc: Phillip Lougher Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/squashfs/xattr_id.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index b88d19e9581e..c8469c656e0d 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, /* Sanity check values */ /* there is always at least one xattr id */ - if (*xattr_ids <= 0) + if (*xattr_ids == 0) return ERR_PTR(-EINVAL); len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); From 152a5f32ac9ec497b514130b603e720ed61df575 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Wed, 8 Feb 2023 10:43:32 +0800 Subject: [PATCH 1395/4345] ixgbe: allow to increase MTU to 3K with XDP enabled commit f9cd6a4418bac6a046ee78382423b1ae7565fb24 upstream. Recently I encountered one case where I cannot increase the MTU size directly from 1500 to a much bigger value with XDP enabled if the server is equipped with IXGBE card, which happened on thousands of servers in production environment. After applying the current patch, we can set the maximum MTU size to 3K. This patch follows the behavior of changing MTU as i40e/ice does. References: [1] commit 23b44513c3e6 ("ice: allow 3k MTU for XDP") [2] commit 0c8493d90b6b ("i40e: add XDP support for pass and drop actions") Fixes: fabf1bce103a ("ixgbe: Prevent unsupported configurations with XDP") Signed-off-by: Jason Xing Reviewed-by: Alexander Duyck Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 25 ++++++++++++------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index b5b8be4672aa..dbfd0cc3df90 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6728,6 +6728,18 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) ixgbe_free_rx_resources(adapter->rx_ring[i]); } +/** + * ixgbe_max_xdp_frame_size - returns the maximum allowed frame size for XDP + * @adapter: device handle, pointer to adapter + */ +static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter) +{ + if (PAGE_SIZE >= 8192 || adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) + return IXGBE_RXBUFFER_2K; + else + return IXGBE_RXBUFFER_3K; +} + /** * ixgbe_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure @@ -6739,18 +6751,13 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - if (adapter->xdp_prog) { + if (ixgbe_enabled_xdp_adapter(adapter)) { int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; - int i; - for (i = 0; i < adapter->num_rx_queues; i++) { - struct ixgbe_ring *ring = adapter->rx_ring[i]; - - if (new_frame_size > ixgbe_rx_bufsz(ring)) { - e_warn(probe, "Requested MTU size is not supported with XDP\n"); - return -EINVAL; - } + if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) { + e_warn(probe, "Requested MTU size is not supported with XDP\n"); + return -EINVAL; } } From 23974088fd6a57922abc80ac7d6219572cd48a4f Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Wed, 8 Feb 2023 10:43:33 +0800 Subject: [PATCH 1396/4345] i40e: add double of VLAN header when computing the max MTU commit ce45ffb815e8e238f05de1630be3969b6bb15e4e upstream. Include the second VLAN HLEN into account when computing the maximum MTU size as other drivers do. Fixes: 0c8493d90b6b ("i40e: add XDP support for pass and drop actions") Signed-off-by: Jason Xing Reviewed-by: Alexander Duyck Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2c60d2a93330..c4f4ee34d58a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2788,7 +2788,7 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu) struct i40e_pf *pf = vsi->back; if (i40e_enabled_xdp_vsi(vsi)) { - int frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int frame_size = new_mtu + I40E_PACKET_HDR_PAD; if (frame_size > i40e_max_xdp_frame_size(vsi)) return -EINVAL; From a5c51e0c3202820192db3f3809e072f3ca2b1177 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 8 Feb 2023 10:16:37 +0100 Subject: [PATCH 1397/4345] net: bgmac: fix BCM5358 support by setting correct flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit d61615c366a489646a1bfe5b33455f916762d5f4 upstream. Code blocks handling BCMA_CHIP_ID_BCM5357 and BCMA_CHIP_ID_BCM53572 were incorrectly unified. Chip package values are not unique and cannot be checked independently. They are meaningful only in a context of a given chip. Packages BCM5358 and BCM47188 share the same value but then belong to different chips. Code unification resulted in treating BCM5358 as BCM47188 and broke its initialization. Link: https://github.com/openwrt/openwrt/issues/8278 Fixes: cb1b0f90acfe ("net: ethernet: bgmac: unify code of the same family") Cc: Jon Mason Signed-off-by: Rafał Miłecki Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20230208091637.16291-1-zajec5@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/broadcom/bgmac-bcma.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 26746197515f..022aebb68f46 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -228,12 +228,12 @@ static int bgmac_probe(struct bcma_device *core) bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST; bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1; bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY; - if (ci->pkg == BCMA_PKG_ID_BCM47188 || - ci->pkg == BCMA_PKG_ID_BCM47186) { + if ((ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM47186) || + (ci->id == BCMA_CHIP_ID_BCM53572 && ci->pkg == BCMA_PKG_ID_BCM47188)) { bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII; bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED; } - if (ci->pkg == BCMA_PKG_ID_BCM5358) + if (ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM5358) bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII; break; case BCMA_CHIP_ID_BCM53573: From 747a17e25aecb4ea8a66427058e0d2d2a25046ad Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Thu, 9 Feb 2023 12:13:05 +0000 Subject: [PATCH 1398/4345] sctp: sctp_sock_filter(): avoid list_entry() on possibly empty list commit a1221703a0f75a9d81748c516457e0fc76951496 upstream. Use list_is_first() to check whether tsp->asoc matches the first element of ep->asocs, as the list is not guaranteed to have an entry. Fixes: 8f840e47f190 ("sctp: add the sctp_diag.c file") Signed-off-by: Pietro Borrello Acked-by: Xin Long Link: https://lore.kernel.org/r/20230208-sctp-filter-v2-1-6e1f4017f326@diag.uniroma1.it Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/sctp/diag.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 68ff82ff49a3..07d0ada23bfd 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -349,11 +349,9 @@ static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp struct sctp_comm_param *commp = p; struct sock *sk = ep->base.sk; const struct inet_diag_req_v2 *r = commp->r; - struct sctp_association *assoc = - list_entry(ep->asocs.next, struct sctp_association, asocs); /* find the ep only once through the transports by this condition */ - if (tsp->asoc != assoc) + if (!list_is_first(&tsp->asoc->asocs, &ep->asocs)) return 0; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) From eb8e9d8572d1d9df17272783ad8a84843ce559d4 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Thu, 9 Feb 2023 11:37:39 -0300 Subject: [PATCH 1399/4345] net/sched: tcindex: update imperfect hash filters respecting rcu commit ee059170b1f7e94e55fa6cadee544e176a6e59c2 upstream. The imperfect hash area can be updated while packets are traversing, which will cause a use-after-free when 'tcf_exts_exec()' is called with the destroyed tcf_ext. CPU 0: CPU 1: tcindex_set_parms tcindex_classify tcindex_lookup tcindex_lookup tcf_exts_change tcf_exts_exec [UAF] Stop operating on the shared area directly, by using a local copy, and update the filter with 'rcu_replace_pointer()'. Delete the old filter version only after a rcu grace period elapsed. Fixes: 9b0d4446b569 ("net: sched: avoid atomic swap in tcf_exts_change") Reported-by: valis Suggested-by: valis Signed-off-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Link: https://lore.kernel.org/r/20230209143739.279867-1-pctammela@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/sched/cls_tcindex.c | 34 ++++++++++++++++++++++++++++++---- 1 file changed, 30 insertions(+), 4 deletions(-) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 86250221d08d..50bf7ec4b5b2 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -338,6 +339,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct tcf_result cr = {}; int err, balloc = 0; struct tcf_exts e; + bool update_h = false; err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) @@ -455,10 +457,13 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } } - if (cp->perfect) + if (cp->perfect) { r = cp->perfect + handle; - else - r = tcindex_lookup(cp, handle) ? : &new_filter_result; + } else { + /* imperfect area is updated in-place using rcu */ + update_h = !!tcindex_lookup(cp, handle); + r = &new_filter_result; + } if (r == &new_filter_result) { f = kzalloc(sizeof(*f), GFP_KERNEL); @@ -484,7 +489,28 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, rcu_assign_pointer(tp->root, cp); - if (r == &new_filter_result) { + if (update_h) { + struct tcindex_filter __rcu **fp; + struct tcindex_filter *cf; + + f->result.res = r->res; + tcf_exts_change(&f->result.exts, &r->exts); + + /* imperfect area bucket */ + fp = cp->h + (handle % cp->hash); + + /* lookup the filter, guaranteed to exist */ + for (cf = rcu_dereference_bh_rtnl(*fp); cf; + fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp)) + if (cf->key == handle) + break; + + f->next = cf->next; + + cf = rcu_replace_pointer(*fp, f, 1); + tcf_exts_get_net(&cf->result.exts); + tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work); + } else if (r == &new_filter_result) { struct tcindex_filter *nfp; struct tcindex_filter __rcu **fp; From 9d68bfa2205d249f705469d6799d0e081ac2b017 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 9 Feb 2023 16:22:01 -0800 Subject: [PATCH 1400/4345] dccp/tcp: Avoid negative sk_forward_alloc by ipv6_pinfo.pktoptions. commit ca43ccf41224b023fc290073d5603a755fd12eed upstream. Eric Dumazet pointed out [0] that when we call skb_set_owner_r() for ipv6_pinfo.pktoptions, sk_rmem_schedule() has not been called, resulting in a negative sk_forward_alloc. We add a new helper which clones a skb and sets its owner only when sk_rmem_schedule() succeeds. Note that we move skb_set_owner_r() forward in (dccp|tcp)_v6_do_rcv() because tcp_send_synack() can make sk_forward_alloc negative before ipv6_opt_accepted() in the crossed SYN-ACK or self-connect() cases. [0]: https://lore.kernel.org/netdev/CANn89iK9oc20Jdi_41jb9URdF210r7d1Y-+uypbMSbOfY6jqrg@mail.gmail.com/ Fixes: 323fbd0edf3f ("net: dccp: Add handling of IPV6_PKTOPTIONS to dccp_v6_do_rcv()") Fixes: 3df80d9320bc ("[DCCP]: Introduce DCCPv6") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/sock.h | 13 +++++++++++++ net/dccp/ipv6.c | 7 ++----- net/ipv6/tcp_ipv6.c | 10 +++------- 3 files changed, 18 insertions(+), 12 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 69bbbe8bbf34..0f48d50a6dde 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2243,6 +2243,19 @@ static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struc return false; } +static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk) +{ + skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + if (skb) { + if (sk_rmem_schedule(sk, skb, skb->truesize)) { + skb_set_owner_r(skb, sk); + return skb; + } + __kfree_skb(skb); + } + return NULL; +} + void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 21c61a9c3b15..c563f9b325d0 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -541,11 +541,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) - skb_set_owner_r(newnp->pktoptions, newsk); } return newsk; @@ -605,7 +603,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len)) @@ -669,7 +667,6 @@ ipv6_pktoptions: np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &DCCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); memmove(IP6CB(opt_skb), &DCCP_SKB_CB(opt_skb)->header.h6, sizeof(struct inet6_skb_parm)); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c599e14be414..6df042863860 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1406,14 +1406,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, - sk_gfp_mask(sk, GFP_ATOMIC)); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) { + if (newnp->pktoptions) tcp_v6_restore_cb(newnp->pktoptions); - skb_set_owner_r(newnp->pktoptions, newsk); - } } } else { if (!req_unhash && found_dup_sk) { @@ -1481,7 +1478,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; @@ -1563,7 +1560,6 @@ ipv6_pktoptions: if (np->repflow) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { From 525bdcb0838d19d918c7786151ee14661967a030 Mon Sep 17 00:00:00 2001 From: Miko Larsson Date: Fri, 10 Feb 2023 09:13:44 +0100 Subject: [PATCH 1401/4345] net/usb: kalmia: Don't pass act_len in usb_bulk_msg error path commit c68f345b7c425b38656e1791a0486769a8797016 upstream. syzbot reported that act_len in kalmia_send_init_packet() is uninitialized when passing it to the first usb_bulk_msg error path. Jiri Pirko noted that it's pointless to pass it in the error path, and that the value that would be printed in the second error path would be the value of act_len from the first call to usb_bulk_msg.[1] With this in mind, let's just not pass act_len to the usb_bulk_msg error paths. 1: https://lore.kernel.org/lkml/Y9pY61y1nwTuzMOa@nanopsycho/ Fixes: d40261236e8e ("net/usb: Add Samsung Kalmia driver for Samsung GT-B3730") Reported-and-tested-by: syzbot+cd80c5ef5121bfe85b55@syzkaller.appspotmail.com Signed-off-by: Miko Larsson Reviewed-by: Alexander Duyck Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/kalmia.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c index fc5895f85cee..a552bb1665b8 100644 --- a/drivers/net/usb/kalmia.c +++ b/drivers/net/usb/kalmia.c @@ -65,8 +65,8 @@ kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len, init_msg, init_msg_len, &act_len, KALMIA_USB_TIMEOUT); if (status != 0) { netdev_err(dev->net, - "Error sending init packet. Status %i, length %i\n", - status, act_len); + "Error sending init packet. Status %i\n", + status); return status; } else if (act_len != init_msg_len) { @@ -83,8 +83,8 @@ kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len, if (status != 0) netdev_err(dev->net, - "Error receiving init result. Status %i, length %i\n", - status, act_len); + "Error receiving init result. Status %i\n", + status); else if (act_len != expected_len) netdev_err(dev->net, "Unexpected init result length: %i\n", act_len); From c0f65ee0a3329eb4b94beaef0268633696e2d0c6 Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Fri, 10 Feb 2023 10:05:51 +0800 Subject: [PATCH 1402/4345] net: openvswitch: fix possible memory leak in ovs_meter_cmd_set() commit 2fa28f5c6fcbfc794340684f36d2581b4f2d20b5 upstream. old_meter needs to be free after it is detached regardless of whether the new meter is successfully attached. Fixes: c7c4c44c9a95 ("net: openvswitch: expand the meters supported number") Signed-off-by: Hangyu Hua Acked-by: Eelco Chaudron Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/openvswitch/meter.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index e594b4d6b58a..0cf3dda5319f 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -450,7 +450,7 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) err = attach_meter(meter_tbl, meter); if (err) - goto exit_unlock; + goto exit_free_old_meter; ovs_unlock(); @@ -473,6 +473,8 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); +exit_free_old_meter: + ovs_meter_free(old_meter); exit_unlock: ovs_unlock(); nlmsg_free(reply); From cc7ca4871a92611d537b75a2a8e466106782bb31 Mon Sep 17 00:00:00 2001 From: Johannes Zink Date: Fri, 10 Feb 2023 15:39:37 +0100 Subject: [PATCH 1403/4345] net: stmmac: fix order of dwmac5 FlexPPS parametrization sequence commit 4562c65ec852067c6196abdcf2d925f08841dcbc upstream. So far changing the period by just setting new period values while running did not work. The order as indicated by the publicly available reference manual of the i.MX8MP [1] indicates a sequence: * initiate the programming sequence * set the values for PPS period and start time * start the pulse train generation. This is currently not used in dwmac5_flex_pps_config(), which instead does: * initiate the programming sequence and immediately start the pulse train generation * set the values for PPS period and start time This caused the period values written not to take effect until the FlexPPS output was disabled and re-enabled again. This patch fix the order and allows the period to be set immediately. [1] https://www.nxp.com/webapp/Download?colCode=IMX8MPRM Fixes: 9a8a02c9d46d ("net: stmmac: Add Flexible PPS support") Signed-off-by: Johannes Zink Link: https://lore.kernel.org/r/20230210143937.3427483-1-j.zink@pengutronix.de Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/stmicro/stmmac/dwmac5.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index de5255b951e1..d1b8b51bf6ad 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -520,9 +520,9 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, return 0; } - val |= PPSCMDx(index, 0x2); val |= TRGTMODSELx(index, 0x2); val |= PPSEN0; + writel(val, ioaddr + MAC_PPS_CONTROL); writel(cfg->start.tv_sec, ioaddr + MAC_PPSx_TARGET_TIME_SEC(index)); @@ -547,6 +547,7 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, writel(period - 1, ioaddr + MAC_PPSx_WIDTH(index)); /* Finally, activate it */ + val |= PPSCMDx(index, 0x2); writel(val, ioaddr + MAC_PPS_CONTROL); return 0; } From 7eb8ebb5e83f8fdbac2eda1f81ed70048cbdb090 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 10 Feb 2023 12:31:55 -0500 Subject: [PATCH 1404/4345] bnxt_en: Fix mqprio and XDP ring checking logic commit 2038cc592811209de20c4e094ca08bfb1e6fbc6c upstream. In bnxt_reserve_rings(), there is logic to check that the number of TX rings reserved is enough to cover all the mqprio TCs, but it fails to account for the TX XDP rings. So the check will always fail if there are mqprio TCs and TX XDP rings. As a result, the driver always fails to initialize after the XDP program is attached and the device will be brought down. A subsequent ifconfig up will also fail because the number of TX rings is set to an inconsistent number. Fix the check to properly account for TX XDP rings. If the check fails, set the number of TX rings back to a consistent number after calling netdev_reset_tc(). Fixes: 674f50a5b026 ("bnxt_en: Implement new method to reserve rings.") Reviewed-by: Hongguang Gao Signed-off-by: Michael Chan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 92f54e333395..c4a768ce8c99 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8761,10 +8761,14 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc); return rc; } - if (tcs && (bp->tx_nr_rings_per_tc * tcs != bp->tx_nr_rings)) { + if (tcs && (bp->tx_nr_rings_per_tc * tcs != + bp->tx_nr_rings - bp->tx_nr_rings_xdp)) { netdev_err(bp->dev, "tx ring reservation failure\n"); netdev_reset_tc(bp->dev); - bp->tx_nr_rings_per_tc = bp->tx_nr_rings; + if (bp->tx_nr_rings_xdp) + bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp; + else + bp->tx_nr_rings_per_tc = bp->tx_nr_rings; return -ENOMEM; } return 0; From 2dd914105a1e59df820edee3a408f480f65c3705 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Fri, 10 Feb 2023 22:21:26 +0200 Subject: [PATCH 1405/4345] net: stmmac: Restrict warning on disabling DMA store and fwd mode commit 05d7623a892a9da62da0e714428e38f09e4a64d8 upstream. When setting 'snps,force_thresh_dma_mode' DT property, the following warning is always emitted, regardless the status of force_sf_dma_mode: dwmac-starfive 10020000.ethernet: force_sf_dma_mode is ignored if force_thresh_dma_mode is set. Do not print the rather misleading message when DMA store and forward mode is already disabled. Fixes: e2a240c7d3bc ("driver:net:stmmac: Disable DMA store and forward mode if platform data force_thresh_dma_mode is set.") Signed-off-by: Cristian Ciocaltea Link: https://lore.kernel.org/r/20230210202126.877548-1-cristian.ciocaltea@collabora.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 1ed74cfb61fc..f02ce09020fb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -559,7 +559,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst"); plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode"); - if (plat->force_thresh_dma_mode) { + if (plat->force_thresh_dma_mode && plat->force_sf_dma_mode) { plat->force_sf_dma_mode = 0; dev_warn(&pdev->dev, "force_sf_dma_mode is ignored if force_thresh_dma_mode is set.\n"); From 7ff0fdba82298d1f456c685e24930da89703c0fb Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 13 Feb 2023 22:53:55 -0800 Subject: [PATCH 1406/4345] net: mpls: fix stale pointer if allocation fails during device rename commit fda6c89fe3d9aca073495a664e1d5aea28cd4377 upstream. lianhui reports that when MPLS fails to register the sysctl table under new location (during device rename) the old pointers won't get overwritten and may be freed again (double free). Handle this gracefully. The best option would be unregistering the MPLS from the device completely on failure, but unfortunately mpls_ifdown() can fail. So failing fully is also unreliable. Another option is to register the new table first then only remove old one if the new one succeeds. That requires more code, changes order of notifications and two tables may be visible at the same time. sysctl point is not used in the rest of the code - set to NULL on failures and skip unregister if already NULL. Reported-by: lianhui tang Fixes: 0fae3bf018d9 ("mpls: handle device renames for per-device sysctls") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/mpls/af_mpls.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 72398149e4d4..1dcbdab9319b 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1427,6 +1427,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev, free: kfree(table); out: + mdev->sysctl = NULL; return -ENOBUFS; } @@ -1436,6 +1437,9 @@ static void mpls_dev_sysctl_unregister(struct net_device *dev, struct net *net = dev_net(dev); struct ctl_table *table; + if (!mdev->sysctl) + return; + table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); From 1a4a5fd652dd6f84eb7ca1ac4cba682196e3ea7d Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 9 Feb 2023 10:41:28 +0800 Subject: [PATCH 1407/4345] ixgbe: add double of VLAN header when computing the max MTU commit 0967bf837784a11c65d66060623a74e65211af0b upstream. Include the second VLAN HLEN into account when computing the maximum MTU size as other drivers do. Fixes: fabf1bce103a ("ixgbe: Prevent unsupported configurations with XDP") Signed-off-by: Jason Xing Reviewed-by: Alexander Duyck Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 2 ++ drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 27c6f911737b..18251edbfabf 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -67,6 +67,8 @@ #define IXGBE_RXBUFFER_4K 4096 #define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ +#define IXGBE_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) + /* Attempt to maximize the headroom available for incoming frames. We * use a 2K buffer for receives and need 1536/1534 to store the data for * the frame. This leaves us with 512 bytes of room. From that we need diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index dbfd0cc3df90..5c542f5d2b20 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6752,8 +6752,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) struct ixgbe_adapter *adapter = netdev_priv(netdev); if (ixgbe_enabled_xdp_adapter(adapter)) { - int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + - VLAN_HLEN; + int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD; if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) { e_warn(probe, "Requested MTU size is not supported with XDP\n"); From 5337bb508ba2b9cb086472def6c0aa0c832ca9d7 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Wed, 8 Feb 2023 18:13:59 +0100 Subject: [PATCH 1408/4345] ipv6: Fix datagram socket connection with DSCP. commit e010ae08c71fda8be3d6bda256837795a0b3ea41 upstream. Take into account the IPV6_TCLASS socket option (DSCP) in ip6_datagram_flow_key_init(). Otherwise fib6_rule_match() can't properly match the DSCP value, resulting in invalid route lookup. For example: ip route add unreachable table main 2001:db8::10/124 ip route add table 100 2001:db8::10/124 dev eth0 ip -6 rule add dsfield 0x04 table 100 echo test | socat - UDP6:[2001:db8::11]:54321,ipv6-tclass=0x04 Without this patch, socat fails at connect() time ("No route to host") because the fib-rule doesn't jump to table 100 and the lookup ends up being done in the main table. Fixes: 2cc67cc731d9 ("[IPV6] ROUTE: Routing by Traffic Class.") Signed-off-by: Guillaume Nault Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv6/datagram.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index f4559e5bc84b..a30ff5d6808a 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -51,7 +51,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk) fl6->flowi6_mark = sk->sk_mark; fl6->fl6_dport = inet->inet_dport; fl6->fl6_sport = inet->inet_sport; - fl6->flowlabel = np->flow_label; + fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6->flowi6_uid = sk->sk_uid; if (!fl6->flowi6_oif) From 7546fb3554df580e49b490c21a61dd3c38212571 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Wed, 8 Feb 2023 18:14:03 +0100 Subject: [PATCH 1409/4345] ipv6: Fix tcp socket connection with DSCP. commit 8230680f36fd1525303d1117768c8852314c488c upstream. Take into account the IPV6_TCLASS socket option (DSCP) in tcp_v6_connect(). Otherwise fib6_rule_match() can't properly match the DSCP value, resulting in invalid route lookup. For example: ip route add unreachable table main 2001:db8::10/124 ip route add table 100 2001:db8::10/124 dev eth0 ip -6 rule add dsfield 0x04 table 100 echo test | socat - TCP6:[2001:db8::11]:54321,ipv6-tclass=0x04 Without this patch, socat fails at connect() time ("No route to host") because the fib-rule doesn't jump to table 100 and the lookup ends up being done in the main table. Fixes: 2cc67cc731d9 ("[IPV6] ROUTE: Routing by Traffic Class.") Signed-off-by: Guillaume Nault Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/ipv6/tcp_ipv6.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6df042863860..e4ae5362cb51 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -269,6 +269,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; + fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; From 0ee5ed0126a2211f7174492da2ca2c29f43755c5 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Wed, 15 Feb 2023 07:40:43 +0900 Subject: [PATCH 1410/4345] nilfs2: fix underflow in second superblock position calculations commit 99b9402a36f0799f25feee4465bfa4b8dfa74b4d upstream. Macro NILFS_SB2_OFFSET_BYTES, which computes the position of the second superblock, underflows when the argument device size is less than 4096 bytes. Therefore, when using this macro, it is necessary to check in advance that the device size is not less than a lower limit, or at least that underflow does not occur. The current nilfs2 implementation lacks this check, causing out-of-bound block access when mounting devices smaller than 4096 bytes: I/O error, dev loop0, sector 36028797018963960 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 2 NILFS (loop0): unable to read secondary superblock (blocksize = 1024) In addition, when trying to resize the filesystem to a size below 4096 bytes, this underflow occurs in nilfs_resize_fs(), passing a huge number of segments to nilfs_sufile_resize(), corrupting parameters such as the number of segments in superblocks. This causes excessive loop iterations in nilfs_sufile_resize() during a subsequent resize ioctl, causing semaphore ns_segctor_sem to block for a long time and hang the writer thread: INFO: task segctord:5067 blocked for more than 143 seconds. Not tainted 6.2.0-rc8-syzkaller-00015-gf6feea56f66d #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:segctord state:D stack:23456 pid:5067 ppid:2 flags:0x00004000 Call Trace: context_switch kernel/sched/core.c:5293 [inline] __schedule+0x1409/0x43f0 kernel/sched/core.c:6606 schedule+0xc3/0x190 kernel/sched/core.c:6682 rwsem_down_write_slowpath+0xfcf/0x14a0 kernel/locking/rwsem.c:1190 nilfs_transaction_lock+0x25c/0x4f0 fs/nilfs2/segment.c:357 nilfs_segctor_thread_construct fs/nilfs2/segment.c:2486 [inline] nilfs_segctor_thread+0x52f/0x1140 fs/nilfs2/segment.c:2570 kthread+0x270/0x300 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 ... Call Trace: folio_mark_accessed+0x51c/0xf00 mm/swap.c:515 __nilfs_get_page_block fs/nilfs2/page.c:42 [inline] nilfs_grab_buffer+0x3d3/0x540 fs/nilfs2/page.c:61 nilfs_mdt_submit_block+0xd7/0x8f0 fs/nilfs2/mdt.c:121 nilfs_mdt_read_block+0xeb/0x430 fs/nilfs2/mdt.c:176 nilfs_mdt_get_block+0x12d/0xbb0 fs/nilfs2/mdt.c:251 nilfs_sufile_get_segment_usage_block fs/nilfs2/sufile.c:92 [inline] nilfs_sufile_truncate_range fs/nilfs2/sufile.c:679 [inline] nilfs_sufile_resize+0x7a3/0x12b0 fs/nilfs2/sufile.c:777 nilfs_resize_fs+0x20c/0xed0 fs/nilfs2/super.c:422 nilfs_ioctl_resize fs/nilfs2/ioctl.c:1033 [inline] nilfs_ioctl+0x137c/0x2440 fs/nilfs2/ioctl.c:1301 ... This fixes these issues by inserting appropriate minimum device size checks or anti-underflow checks, depending on where the macro is used. Link: https://lkml.kernel.org/r/0000000000004e1dfa05f4a48e6b@google.com Link: https://lkml.kernel.org/r/20230214224043.24141-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/ioctl.c | 7 +++++++ fs/nilfs2/super.c | 9 +++++++++ fs/nilfs2/the_nilfs.c | 8 +++++++- 3 files changed, 23 insertions(+), 1 deletion(-) diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 07d26f61f22a..3a1dea5d1448 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -1129,7 +1129,14 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp) minseg = range[0] + segbytes - 1; do_div(minseg, segbytes); + + if (range[1] < 4096) + goto out; + maxseg = NILFS_SB2_OFFSET_BYTES(range[1]); + if (maxseg < segbytes) + goto out; + do_div(maxseg, segbytes); maxseg--; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 7a41c9727c9e..775184868763 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -408,6 +408,15 @@ int nilfs_resize_fs(struct super_block *sb, __u64 newsize) if (newsize > devsize) goto out; + /* + * Prevent underflow in second superblock position calculation. + * The exact minimum size check is done in nilfs_sufile_resize(). + */ + if (newsize < 4096) { + ret = -ENOSPC; + goto out; + } + /* * Write lock is required to protect some functions depending * on the number of segments, the number of reserved segments, diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 211937054c31..38a1206cf948 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -544,9 +544,15 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, { struct nilfs_super_block **sbp = nilfs->ns_sbp; struct buffer_head **sbh = nilfs->ns_sbh; - u64 sb2off = NILFS_SB2_OFFSET_BYTES(nilfs->ns_bdev->bd_inode->i_size); + u64 sb2off, devsize = nilfs->ns_bdev->bd_inode->i_size; int valid[2], swp = 0; + if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) { + nilfs_err(sb, "device size too small"); + return -EINVAL; + } + sb2off = NILFS_SB2_OFFSET_BYTES(devsize); + sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize, &sbh[0]); sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]); From 210e6011806acba0bc7ad57b1cf24be7ba76d836 Mon Sep 17 00:00:00 2001 From: Raviteja Goud Talla Date: Fri, 3 Dec 2021 20:26:03 +0530 Subject: [PATCH 1411/4345] drm/i915/gen11: Moving WAs to icl_gt_workarounds_init() [ Upstream commit 67b858dd89932086ae0ee2d0ce4dd070a2c88bb3 ] Bspec page says "Reset: BUS", Accordingly moving w/a's: Wa_1407352427,Wa_1406680159 to proper function icl_gt_workarounds_init() Which will resolve guc enabling error v2: - Previous patch rev2 was created by email client which caused the Build failure, This v2 is to resolve the previous broken series Reviewed-by: John Harrison Signed-off-by: Raviteja Goud Talla Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20211203145603.4006937-1-ravitejax.goud.talla@intel.com Stable-dep-of: d5a1224aa68c ("drm/i915/gen11: Wa_1408615072/Wa_1407596294 should be on GT list") Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 4a3bde7c9f21..5c92789504d0 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1212,6 +1212,15 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) GAMT_CHKN_BIT_REG, GAMT_CHKN_DISABLE_L3_COH_PIPE); + /* Wa_1407352427:icl,ehl */ + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, + PSDUNIT_CLKGATE_DIS); + + /* Wa_1406680159:icl,ehl */ + wa_write_or(wal, + SUBSLICE_UNIT_LEVEL_CLKGATE, + GWUNIT_CLKGATE_DIS); + /* Wa_1607087056:icl,ehl,jsl */ if (IS_ICELAKE(i915) || IS_EHL_REVID(i915, EHL_REVID_A0, EHL_REVID_A0)) { @@ -1823,15 +1832,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS); - /* Wa_1407352427:icl,ehl */ - wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, - PSDUNIT_CLKGATE_DIS); - - /* Wa_1406680159:icl,ehl */ - wa_write_or(wal, - SUBSLICE_UNIT_LEVEL_CLKGATE, - GWUNIT_CLKGATE_DIS); - /* * Wa_1408767742:icl[a2..forever],ehl[all] * Wa_1605460711:icl[a0..c0] From 1d76a844487490fbb2165953d5523ed9feb3cdc4 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Wed, 1 Feb 2023 14:28:29 -0800 Subject: [PATCH 1412/4345] drm/i915/gen11: Wa_1408615072/Wa_1407596294 should be on GT list [ Upstream commit d5a1224aa68c8b124a4c5c390186e571815ed390 ] The UNSLICE_UNIT_LEVEL_CLKGATE register programmed by this workaround has 'BUS' style reset, indicating that it does not lose its value on engine resets. Furthermore, this register is part of the GT forcewake domain rather than the RENDER domain, so it should not be impacted by RCS engine resets. As such, we should implement this on the GT workaround list rather than an engine list. Bspec: 19219 Fixes: 3551ff928744 ("drm/i915/gen11: Moving WAs to rcs_engine_wa_init()") Signed-off-by: Matt Roper Reviewed-by: Gustavo Sousa Link: https://patchwork.freedesktop.org/patch/msgid/20230201222831.608281-2-matthew.d.roper@intel.com (cherry picked from commit 5f21dc07b52eb54a908e66f5d6e05a87bcb5b049) Signed-off-by: Rodrigo Vivi Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 5c92789504d0..ae5cf2b55e15 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1212,6 +1212,13 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) GAMT_CHKN_BIT_REG, GAMT_CHKN_DISABLE_L3_COH_PIPE); + /* + * Wa_1408615072:icl,ehl (vsunit) + * Wa_1407596294:icl,ehl (hsunit) + */ + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, + VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS); + /* Wa_1407352427:icl,ehl */ wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, PSDUNIT_CLKGATE_DIS); @@ -1825,13 +1832,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) wa_masked_en(wal, GEN9_CSFE_CHICKEN1_RCS, GEN11_ENABLE_32_PLANE_MODE); - /* - * Wa_1408615072:icl,ehl (vsunit) - * Wa_1407596294:icl,ehl (hsunit) - */ - wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, - VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS); - /* * Wa_1408767742:icl[a2..forever],ehl[all] * Wa_1605460711:icl[a0..c0] From 015ea70d72c3449ab708024521bcdce7aad58aba Mon Sep 17 00:00:00 2001 From: Baowen Zheng Date: Fri, 17 Dec 2021 19:16:17 +0100 Subject: [PATCH 1413/4345] flow_offload: fill flags to action structure [ Upstream commit 40bd094d65fc9f83941b024cde7c24516f036879 ] Fill flags to action structure to allow user control if the action should be offloaded to hardware or not. Signed-off-by: Baowen Zheng Signed-off-by: Louis Peens Signed-off-by: Simon Horman Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller Stable-dep-of: 21c167aa0ba9 ("net/sched: act_ctinfo: use percpu stats") Signed-off-by: Sasha Levin --- net/sched/act_bpf.c | 2 +- net/sched/act_connmark.c | 2 +- net/sched/act_ctinfo.c | 2 +- net/sched/act_gate.c | 2 +- net/sched/act_ife.c | 2 +- net/sched/act_ipt.c | 2 +- net/sched/act_mpls.c | 2 +- net/sched/act_nat.c | 2 +- net/sched/act_pedit.c | 2 +- net/sched/act_police.c | 2 +- net/sched/act_sample.c | 2 +- net/sched/act_simple.c | 2 +- net/sched/act_skbedit.c | 2 +- net/sched/act_skbmod.c | 2 +- 14 files changed, 14 insertions(+), 14 deletions(-) diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index a4c7ba35a343..78f1cd70c8d1 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -307,7 +307,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, ret = tcf_idr_check_alloc(tn, &index, act, bind); if (!ret) { ret = tcf_idr_create(tn, index, est, act, - &act_bpf_ops, bind, true, 0); + &act_bpf_ops, bind, true, flags); if (ret < 0) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 31d268eedf3f..b6576a250e85 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -124,7 +124,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, ret = tcf_idr_check_alloc(tn, &index, a, bind); if (!ret) { ret = tcf_idr_create(tn, index, est, a, - &act_connmark_ops, bind, false, 0); + &act_connmark_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 06c74f22ab98..9bde94e7bb93 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -212,7 +212,7 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create(tn, index, est, a, - &act_ctinfo_ops, bind, false, 0); + &act_ctinfo_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index a78cb7965718..0e7568a06351 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -357,7 +357,7 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (!err) { ret = tcf_idr_create(tn, index, est, a, - &act_gate_ops, bind, false, 0); + &act_gate_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index a2ddea04183a..99548b2a1bc8 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -553,7 +553,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_ife_ops, - bind, true, 0); + bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); kfree(p); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 8dc3bec0d325..080f2952cd53 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -144,7 +144,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, ops, bind, - false, 0); + false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 09799412b248..47b963ded4e4 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -254,7 +254,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_mpls_ops, bind, true, 0); + &act_mpls_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 1ebd2a86d980..8466dc25fe39 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -61,7 +61,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create(tn, index, est, a, - &act_nat_ops, bind, false, 0); + &act_nat_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 0d5463ddfd62..db0d3bff19eb 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -189,7 +189,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create(tn, index, est, a, - &act_pedit_ops, bind, false, 0); + &act_pedit_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); goto out_free; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 380733588959..c30cd3ecb391 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -87,7 +87,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, NULL, a, - &act_police_ops, bind, true, 0); + &act_police_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 3ebf9ede3cf1..2f0e98bcf494 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -69,7 +69,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_sample_ops, bind, true, 0); + &act_sample_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index a4f3d0f0daa9..b9bbc87a87c5 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -128,7 +128,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_simp_ops, bind, false, 0); + &act_simp_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index e5f3fb8b00e3..a5661f2d93e9 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -176,7 +176,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_skbedit_ops, bind, true, 0); + &act_skbedit_ops, bind, true, act_flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 8d17a543cc9f..aa98dcac94b9 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -147,7 +147,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_skbmod_ops, bind, true, 0); + &act_skbmod_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; From 5dfa51dbfc123fb42ce3464a3124e5cd758e0c59 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Fri, 10 Feb 2023 17:08:25 -0300 Subject: [PATCH 1414/4345] net/sched: act_ctinfo: use percpu stats [ Upstream commit 21c167aa0ba943a7cac2f6969814f83bb701666b ] The tc action act_ctinfo was using shared stats, fix it to use percpu stats since bstats_update() must be called with locks or with a percpu pointer argument. tdc results: 1..12 ok 1 c826 - Add ctinfo action with default setting ok 2 0286 - Add ctinfo action with dscp ok 3 4938 - Add ctinfo action with valid cpmark and zone ok 4 7593 - Add ctinfo action with drop control ok 5 2961 - Replace ctinfo action zone and action control ok 6 e567 - Delete ctinfo action with valid index ok 7 6a91 - Delete ctinfo action with invalid index ok 8 5232 - List ctinfo actions ok 9 7702 - Flush ctinfo actions ok 10 3201 - Add ctinfo action with duplicate index ok 11 8295 - Add ctinfo action with invalid index ok 12 3964 - Replace ctinfo action with invalid goto_chain control Fixes: 24ec483cec98 ("net: sched: Introduce act_ctinfo action") Reviewed-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Reviewed-by: Larysa Zaremba Link: https://lore.kernel.org/r/20230210200824.444856-1-pctammela@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/act_ctinfo.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 9bde94e7bb93..5aa005835c06 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -92,7 +92,7 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, cp = rcu_dereference_bh(ca->params); tcf_lastuse_update(&ca->tcf_tm); - bstats_update(&ca->tcf_bstats, skb); + tcf_action_update_bstats(&ca->common, skb); action = READ_ONCE(ca->tcf_action); wlen = skb_network_offset(skb); @@ -211,8 +211,8 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, index = actparm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, index, est, a, - &act_ctinfo_ops, bind, false, flags); + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_ctinfo_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; From b452e20b95d7e0b09ee4a6f773e3ebe6764ff1cf Mon Sep 17 00:00:00 2001 From: Natalia Petrova Date: Thu, 9 Feb 2023 09:28:33 -0800 Subject: [PATCH 1415/4345] i40e: Add checking for null for nlmsg_find_attr() [ Upstream commit 7fa0b526f865cb42aa33917fd02a92cb03746f4d ] The result of nlmsg_find_attr() 'br_spec' is dereferenced in nla_for_each_nested(), but it can take NULL value in nla_find() function, which will result in an error. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 51616018dd1b ("i40e: Add support for getlink, setlink ndo ops") Signed-off-by: Natalia Petrova Reviewed-by: Jesse Brandeburg Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20230209172833.3596034-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c4f4ee34d58a..9e8a20a94862 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12520,6 +12520,8 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, } br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; nla_for_each_nested(attr, br_spec, rem) { __u16 mode; From 4fe9950815e19051b7b8268b4d4c3ac286a741bf Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Mon, 13 Feb 2023 22:47:29 -0300 Subject: [PATCH 1416/4345] net/sched: tcindex: search key must be 16 bits [ Upstream commit 42018a322bd453e38b3ffee294982243e50a484f ] Syzkaller found an issue where a handle greater than 16 bits would trigger a null-ptr-deref in the imperfect hash area update. general protection fault, probably for non-canonical address 0xdffffc0000000015: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x00000000000000a8-0x00000000000000af] CPU: 0 PID: 5070 Comm: syz-executor456 Not tainted 6.2.0-rc7-syzkaller-00112-gc68f345b7c42 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/21/2023 RIP: 0010:tcindex_set_parms+0x1a6a/0x2990 net/sched/cls_tcindex.c:509 Code: 01 e9 e9 fe ff ff 4c 8b bd 28 fe ff ff e8 0e 57 7d f9 48 8d bb a8 00 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 94 0c 00 00 48 8b 85 f8 fd ff ff 48 8b 9b a8 00 RSP: 0018:ffffc90003d3ef88 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000015 RSI: ffffffff8803a102 RDI: 00000000000000a8 RBP: ffffc90003d3f1d8 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffff88801e2b10a8 R13: dffffc0000000000 R14: 0000000000030000 R15: ffff888017b3be00 FS: 00005555569af300(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000056041c6d2000 CR3: 000000002bfca000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcindex_change+0x1ea/0x320 net/sched/cls_tcindex.c:572 tc_new_tfilter+0x96e/0x2220 net/sched/cls_api.c:2155 rtnetlink_rcv_msg+0x959/0xca0 net/core/rtnetlink.c:6132 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2574 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x91b/0xe10 net/netlink/af_netlink.c:1942 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xd3/0x120 net/socket.c:734 ____sys_sendmsg+0x334/0x8c0 net/socket.c:2476 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2530 __sys_sendmmsg+0x18f/0x460 net/socket.c:2616 __do_sys_sendmmsg net/socket.c:2645 [inline] __se_sys_sendmmsg net/socket.c:2642 [inline] __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2642 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 Fixes: ee059170b1f7 ("net/sched: tcindex: update imperfect hash filters respecting rcu") Signed-off-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Reported-by: syzbot Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/cls_tcindex.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 50bf7ec4b5b2..2c0c95204cb5 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -502,7 +502,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, /* lookup the filter, guaranteed to exist */ for (cf = rcu_dereference_bh_rtnl(*fp); cf; fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp)) - if (cf->key == handle) + if (cf->key == (u16)handle) break; f->next = cf->next; From 6416c2108ba54d569e4c98d3b62ac78cb12e7107 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 14 Feb 2023 11:33:04 +0100 Subject: [PATCH 1417/4345] kvm: initialize all of the kvm_debugregs structure before sending it to userspace commit 2c10b61421a28e95a46ab489fd56c0f442ff6952 upstream. When calling the KVM_GET_DEBUGREGS ioctl, on some configurations, there might be some unitialized portions of the kvm_debugregs structure that could be copied to userspace. Prevent this as is done in the other kvm ioctls, by setting the whole structure to 0 before copying anything into it. Bonus is that this reduces the lines of code as the explicit flag setting and reserved space zeroing out can be removed. Cc: Sean Christopherson Cc: Paolo Bonzini Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Cc: "H. Peter Anvin" Cc: stable Reported-by: Xingyuan Mo Signed-off-by: Greg Kroah-Hartman Message-Id: <20230214103304.3689213-1-gregkh@linuxfoundation.org> Tested-by: Xingyuan Mo Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 23d7c563e012..554d37873c25 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4455,12 +4455,11 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, { unsigned long val; + memset(dbgregs, 0, sizeof(*dbgregs)); memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); kvm_get_dr(vcpu, 6, &val); dbgregs->dr6 = val; dbgregs->dr7 = vcpu->arch.dr7; - dbgregs->flags = 0; - memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, From 6af2872cc62549b2b034dcd02770ac52edf440ba Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 9 Feb 2023 23:25:49 +0100 Subject: [PATCH 1418/4345] alarmtimer: Prevent starvation by small intervals and SIG_IGN commit d125d1349abeb46945dc5e98f7824bf688266f13 upstream. syzbot reported a RCU stall which is caused by setting up an alarmtimer with a very small interval and ignoring the signal. The reproducer arms the alarm timer with a relative expiry of 8ns and an interval of 9ns. Not a problem per se, but that's an issue when the signal is ignored because then the timer is immediately rearmed because there is no way to delay that rearming to the signal delivery path. See posix_timer_fn() and commit 58229a189942 ("posix-timers: Prevent softirq starvation by small intervals and SIG_IGN") for details. The reproducer does not set SIG_IGN explicitely, but it sets up the timers signal with SIGCONT. That has the same effect as explicitely setting SIG_IGN for a signal as SIGCONT is ignored if there is no handler set and the task is not ptraced. The log clearly shows that: [pid 5102] --- SIGCONT {si_signo=SIGCONT, si_code=SI_TIMER, si_timerid=0, si_overrun=316014, si_int=0, si_ptr=NULL} --- It works because the tasks are traced and therefore the signal is queued so the tracer can see it, which delays the restart of the timer to the signal delivery path. But then the tracer is killed: [pid 5087] kill(-5102, SIGKILL ... ./strace-static-x86_64: Process 5107 detached and after it's gone the stall can be observed: syzkaller login: [ 79.439102][ C0] hrtimer: interrupt took 68471 ns [ 184.460538][ C1] rcu: INFO: rcu_preempt detected stalls on CPUs/tasks: ... [ 184.658237][ C1] rcu: Stack dump where RCU GP kthread last ran: [ 184.664574][ C1] Sending NMI from CPU 1 to CPUs 0: [ 184.669821][ C0] NMI backtrace for cpu 0 [ 184.669831][ C0] CPU: 0 PID: 5108 Comm: syz-executor192 Not tainted 6.2.0-rc6-next-20230203-syzkaller #0 ... [ 184.670036][ C0] Call Trace: [ 184.670041][ C0] [ 184.670045][ C0] alarmtimer_fired+0x327/0x670 posix_timer_fn() prevents that by checking whether the interval for timers which have the signal ignored is smaller than a jiffie and artifically delay it by shifting the next expiry out by a jiffie. That's accurate vs. the overrun accounting, but slightly inaccurate vs. timer_gettimer(2). The comment in that function says what needs to be done and there was a fix available for the regular userspace induced SIG_IGN mechanism, but that did not work due to the implicit ignore for SIGCONT and similar signals. This needs to be worked on, but for now the only available workaround is to do exactly what posix_timer_fn() does: Increase the interval of self-rearming timers, which have their signal ignored, to at least a jiffie. Interestingly this has been fixed before via commit ff86bf0c65f1 ("alarmtimer: Rate limit periodic intervals") already, but that fix got lost in a later rework. Reported-by: syzbot+b9564ba6e8e00694511b@syzkaller.appspotmail.com Fixes: f2c45807d399 ("alarmtimer: Switch over to generic set/get/rearm routine") Signed-off-by: Thomas Gleixner Acked-by: John Stultz Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87k00q1no2.ffs@tglx Signed-off-by: Greg Kroah-Hartman --- kernel/time/alarmtimer.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index daeaa7140d0a..1de426d3f694 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -470,11 +470,35 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) } EXPORT_SYMBOL_GPL(alarm_forward); -u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle) { struct alarm_base *base = &alarm_bases[alarm->type]; + ktime_t now = base->get_ktime(); - return alarm_forward(alarm, base->get_ktime(), interval); + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) { + /* + * Same issue as with posix_timer_fn(). Timers which are + * periodic but the signal is ignored can starve the system + * with a very small interval. The real fix which was + * promised in the context of posix_timer_fn() never + * materialized, but someone should really work on it. + * + * To prevent DOS fake @now to be 1 jiffie out which keeps + * the overrun accounting correct but creates an + * inconsistency vs. timer_gettime(2). + */ + ktime_t kj = NSEC_PER_SEC / HZ; + + if (interval < kj) + now = ktime_add(now, kj); + } + + return alarm_forward(alarm, now, interval); +} + +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + return __alarm_forward_now(alarm, interval, false); } EXPORT_SYMBOL_GPL(alarm_forward_now); @@ -548,9 +572,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, if (posix_timer_event(ptr, si_private) && ptr->it_interval) { /* * Handle ignored signals and rearm the timer. This will go - * away once we handle ignored signals proper. + * away once we handle ignored signals proper. Ensure that + * small intervals cannot starve the system. */ - ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval); + ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true); ++ptr->it_requeue_pending; ptr->it_active = 1; result = ALARMTIMER_RESTART; From 31167df7c21feb2a74d69a758a5226d83cbfe905 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 16 Feb 2023 18:23:40 +0200 Subject: [PATCH 1419/4345] ASoC: SOF: Intel: hda-dai: fix possible stream_tag leak commit 1f810d2b6b2fbdc5279644d8b2c140b1f7c9d43d upstream. The HDaudio stream allocation is done first, and in a second step the LOSIDV parameter is programmed for the multi-link used by a codec. This leads to a possible stream_tag leak, e.g. if a DisplayAudio link is not used. This would happen when a non-Intel graphics card is used and userspace unconditionally uses the Intel Display Audio PCMs without checking if they are connected to a receiver with jack controls. We should first check that there is a valid multi-link entry to configure before allocating a stream_tag. This change aligns the dma_assign and dma_cleanup phases. Complements: b0cd60f3e9f5 ("ALSA/ASoC: hda: clarify bus_get_link() and bus_link_get() helpers") Link: https://github.com/thesofproject/linux/issues/4151 Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Rander Wang Reviewed-by: Bard Liao Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20230216162340.19480-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/sof/intel/hda-dai.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index de80f1b3d7f2..a6275cc92a40 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -212,6 +212,10 @@ static int hda_link_hw_params(struct snd_pcm_substream *substream, int stream_tag; int ret; + link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name); + if (!link) + return -EINVAL; + /* get stored dma data if resuming from system suspend */ link_dev = snd_soc_dai_get_dma_data(dai, substream); if (!link_dev) { @@ -232,10 +236,6 @@ static int hda_link_hw_params(struct snd_pcm_substream *substream, if (ret < 0) return ret; - link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name); - if (!link) - return -EINVAL; - /* set the hdac_stream in the codec dai */ snd_soc_dai_set_stream(codec_dai, hdac_stream(link_dev), substream->stream); From c00867afe4efd5754e696d5c0a8d3f682efd7ffb Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 6 Feb 2023 16:18:32 +0300 Subject: [PATCH 1420/4345] net: sched: sch: Fix off by one in htb_activate_prios() commit 9cec2aaffe969f2a3e18b5ec105fc20bb908e475 upstream. The > needs be >= to prevent an out of bounds access. Fixes: de5ca4c3852f ("net: sched: sch: Bounds check priority") Signed-off-by: Dan Carpenter Reviewed-by: Simon Horman Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/Y+D+KN18FQI2DKLq@kili Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/sched/sch_htb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c3e773d2ca41..ff84ed531199 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -407,7 +407,7 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (m) { unsigned int prio = ffz(~m); - if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio))) + if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio))) break; m &= ~(1 << prio); From e95381034519a8c5a3150f7b03f4664b1da651b2 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 27 Jan 2023 10:40:14 +0000 Subject: [PATCH 1421/4345] nvmem: core: fix return value commit 0c4862b1c1465e473bc961a02765490578bf5c20 upstream. Dan Carpenter points out that the return code was not set in commit 60c8b4aebd8e ("nvmem: core: fix cleanup after dev_set_name()"), but this is not the only issue - we also need to zero wp_gpio to prevent gpiod_put() being called on an error value. Fixes: 560181d3ace6 ("nvmem: core: fix cleanup after dev_set_name()") Cc: stable@vger.kernel.org Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Russell King (Oracle) Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230127104015.23839-10-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 0ef7b95348b1..1505c745154e 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -638,6 +638,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { rval = PTR_ERR(nvmem->wp_gpio); + nvmem->wp_gpio = NULL; goto err_put_device; } From 2ae73796985b582b79711dfed2941d190b571fb5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 22 Feb 2023 12:56:00 +0100 Subject: [PATCH 1422/4345] Linux 5.10.169 Link: https://lore.kernel.org/r/20230220133549.360169435@linuxfoundation.org Tested-by: Pavel Machek (CIP) Tested-by: Linux Kernel Functional Testing Tested-by: Jon Hunter Tested-by: Sudip Mukherjee Tested-by: Guenter Roeck Tested-by: Salvatore Bonaccorso Tested-by: Florian Fainelli Tested-by: Shuah Khan Tested-by: Hulk Robot Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index af3270277fd0..dbbfaa5d4fe2 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 168 +SUBLEVEL = 169 EXTRAVERSION = NAME = Dare mighty things From 5d9b0e83e3c8bb0adff68e5e21b4df6e79b38998 Mon Sep 17 00:00:00 2001 From: Paul Lawrence Date: Fri, 6 Jan 2023 13:36:29 -0800 Subject: [PATCH 1423/4345] ANDROID: incremental fs: Fix race between truncate and write last block Also fix race whereby multiple providers writinig the same block would actually write out the same block. Note that multiple_providers_test started failing when incfs was ported to 5.15, and these fixes are needed to make the test reliable Bug: 264703896 Test: incfs-test passes, specifically multiple_providers_test. Ran 100 times Change-Id: I05ad5b2b2f62cf218256222cecb79bbe9953bd97 Signed-off-by: Paul Lawrence --- fs/incfs/data_mgmt.c | 44 ++++++++++++++++++++++++++++++-------------- fs/incfs/data_mgmt.h | 3 ++- fs/incfs/vfs.c | 12 +++++------- 3 files changed, 37 insertions(+), 22 deletions(-) diff --git a/fs/incfs/data_mgmt.c b/fs/incfs/data_mgmt.c index fbab68a280d5..ff3cddcaa696 100644 --- a/fs/incfs/data_mgmt.c +++ b/fs/incfs/data_mgmt.c @@ -1379,7 +1379,8 @@ ssize_t incfs_read_merkle_tree_blocks(struct mem_range dst, } int incfs_process_new_data_block(struct data_file *df, - struct incfs_fill_block *block, u8 *data) + struct incfs_fill_block *block, u8 *data, + bool *complete) { struct mount_info *mi = NULL; struct backing_file_context *bfc = NULL; @@ -1418,27 +1419,42 @@ int incfs_process_new_data_block(struct data_file *df, if (error) return error; - if (is_data_block_present(&existing_block)) { + if (is_data_block_present(&existing_block)) /* Block is already present, nothing to do here */ return 0; - } error = down_write_killable(&segment->rwsem); if (error) return error; - error = mutex_lock_interruptible(&bfc->bc_mutex); - if (!error) { - error = incfs_write_data_block_to_backing_file( - bfc, range(data, block->data_len), block->block_index, - df->df_blockmap_off, flags); - mutex_unlock(&bfc->bc_mutex); - } - if (!error) { - notify_pending_reads(mi, segment, block->block_index); - atomic_inc(&df->df_data_blocks_written); - } + /* Recheck inside write lock */ + error = get_data_file_block(df, block->block_index, &existing_block); + if (error) + goto out_up_write; + if (is_data_block_present(&existing_block)) + goto out_up_write; + + error = mutex_lock_interruptible(&bfc->bc_mutex); + if (error) + goto out_up_write; + + error = incfs_write_data_block_to_backing_file(bfc, + range(data, block->data_len), block->block_index, + df->df_blockmap_off, flags); + if (error) + goto out_mutex_unlock; + + if (atomic_inc_return(&df->df_data_blocks_written) + >= df->df_data_block_count) + *complete = true; + +out_mutex_unlock: + mutex_unlock(&bfc->bc_mutex); + if (!error) + notify_pending_reads(mi, segment, block->block_index); + +out_up_write: up_write(&segment->rwsem); if (error) diff --git a/fs/incfs/data_mgmt.h b/fs/incfs/data_mgmt.h index 2227913674a4..2b6121d6131f 100644 --- a/fs/incfs/data_mgmt.h +++ b/fs/incfs/data_mgmt.h @@ -441,7 +441,8 @@ int incfs_get_filled_blocks(struct data_file *df, int incfs_read_file_signature(struct data_file *df, struct mem_range dst); int incfs_process_new_data_block(struct data_file *df, - struct incfs_fill_block *block, u8 *data); + struct incfs_fill_block *block, u8 *data, + bool *complete); int incfs_process_new_hash_block(struct data_file *df, struct incfs_fill_block *block, u8 *data); diff --git a/fs/incfs/vfs.c b/fs/incfs/vfs.c index 342998f24090..ad616cfe1252 100644 --- a/fs/incfs/vfs.c +++ b/fs/incfs/vfs.c @@ -662,8 +662,7 @@ out: dput(file); } -static void maybe_delete_incomplete_file(struct file *f, - struct data_file *df) +static void handle_file_completed(struct file *f, struct data_file *df) { struct backing_file_context *bfc; struct mount_info *mi = df->df_mount_info; @@ -672,9 +671,6 @@ static void maybe_delete_incomplete_file(struct file *f, const struct cred *old_cred = override_creds(mi->mi_owner); int error; - if (atomic_read(&df->df_data_blocks_written) < df->df_data_block_count) - goto out; - /* Truncate file to remove any preallocated space */ bfc = df->df_backing_file_context; if (bfc) { @@ -733,6 +729,7 @@ static long ioctl_fill_blocks(struct file *f, void __user *arg) u8 *data_buf = NULL; ssize_t error = 0; int i = 0; + bool complete = false; if (!df) return -EBADF; @@ -774,7 +771,7 @@ static long ioctl_fill_blocks(struct file *f, void __user *arg) data_buf); } else { error = incfs_process_new_data_block(df, &fill_block, - data_buf); + data_buf, &complete); } if (error) break; @@ -783,7 +780,8 @@ static long ioctl_fill_blocks(struct file *f, void __user *arg) if (data_buf) free_pages((unsigned long)data_buf, get_order(data_buf_size)); - maybe_delete_incomplete_file(f, df); + if (complete) + handle_file_completed(f, df); /* * Only report the error if no records were processed, otherwise From 7fd4fbe615ab6453147ae806fa043a623c9fc2fe Mon Sep 17 00:00:00 2001 From: Paul Lawrence Date: Thu, 7 Jul 2022 08:24:12 -0700 Subject: [PATCH 1424/4345] ANDROID: incremental fs: Move throttling to outside page lock Bug: 241479010 Test: incfs_test passes, play confirm behavior in bug is fixed Signed-off-by: Paul Lawrence Change-Id: Ie51f2b76d0873057f54fecf7fcc793c66df20969 --- Documentation/ABI/testing/sysfs-fs-incfs | 6 ++++ Documentation/filesystems/incfs.rst | 3 ++ fs/incfs/data_mgmt.c | 43 +++++++----------------- fs/incfs/data_mgmt.h | 3 +- fs/incfs/sysfs.c | 2 ++ fs/incfs/verity.c | 2 +- fs/incfs/vfs.c | 28 +++++++++++++-- 7 files changed, 51 insertions(+), 36 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-fs-incfs b/Documentation/ABI/testing/sysfs-fs-incfs index 690c687c67ab..e4e05f950f9e 100644 --- a/Documentation/ABI/testing/sysfs-fs-incfs +++ b/Documentation/ABI/testing/sysfs-fs-incfs @@ -15,6 +15,12 @@ Contact: Paul Lawrence Description: Reads 'supported'. Present if zstd compression is supported for data blocks. +What: /sys/fs/incremental-fs/features/bugfix_throttling +Date: January 2023 +Contact: Paul Lawrence +Description: Reads 'supported'. Present if the throttling lock bug is fixed + https://android-review.git.corp.google.com/c/kernel/common/+/2381827 + What: /sys/fs/incremental-fs/instances/[name] Date: April 2021 Contact: Paul Lawrence diff --git a/Documentation/filesystems/incfs.rst b/Documentation/filesystems/incfs.rst index 19db303b8327..f0fb1d02d530 100644 --- a/Documentation/filesystems/incfs.rst +++ b/Documentation/filesystems/incfs.rst @@ -35,6 +35,9 @@ Features /sys/fs/incremental-fs/features/zstd Reads 'supported'. Present if zstd compression is supported for data blocks. +/sys/fs/incremental-fs/features/bugfix_throttling + Reads 'supported'. Present if the throttling lock bug is fixed + Optional per mount ------------------ diff --git a/fs/incfs/data_mgmt.c b/fs/incfs/data_mgmt.c index ff3cddcaa696..6381f8fd4e87 100644 --- a/fs/incfs/data_mgmt.c +++ b/fs/incfs/data_mgmt.c @@ -3,7 +3,6 @@ * Copyright 2019 Google LLC */ #include -#include #include #include #include @@ -1104,25 +1103,10 @@ static void notify_pending_reads(struct mount_info *mi, wake_up_all(&mi->mi_blocks_written_notif_wq); } -static int usleep_interruptible(u32 us) -{ - /* See: - * https://www.kernel.org/doc/Documentation/timers/timers-howto.txt - * for explanation - */ - if (us < 10) { - udelay(us); - return 0; - } else if (us < 20000) { - usleep_range(us, us + us / 10); - return 0; - } else - return msleep_interruptible(us / 1000); -} - static int wait_for_data_block(struct data_file *df, int block_index, struct data_file_block *res_block, - struct incfs_read_data_file_timeouts *timeouts) + struct incfs_read_data_file_timeouts *timeouts, + unsigned int *delayed_min_us) { struct data_file_block block = {}; struct data_file_segment *segment = NULL; @@ -1130,7 +1114,7 @@ static int wait_for_data_block(struct data_file *df, int block_index, struct mount_info *mi = NULL; int error; int wait_res = 0; - unsigned int delayed_pending_us = 0, delayed_min_us = 0; + unsigned int delayed_pending_us = 0; bool delayed_pending = false; if (!df || !res_block) @@ -1161,8 +1145,7 @@ static int wait_for_data_block(struct data_file *df, int block_index, if (is_data_block_present(&block)) { *res_block = block; if (timeouts && timeouts->min_time_us) { - delayed_min_us = timeouts->min_time_us; - error = usleep_interruptible(delayed_min_us); + *delayed_min_us = timeouts->min_time_us; goto out; } return 0; @@ -1209,13 +1192,9 @@ static int wait_for_data_block(struct data_file *df, int block_index, delayed_pending = true; delayed_pending_us = timeouts->max_pending_time_us - jiffies_to_usecs(wait_res); - if (timeouts->min_pending_time_us > delayed_pending_us) { - delayed_min_us = timeouts->min_pending_time_us - + if (timeouts->min_pending_time_us > delayed_pending_us) + *delayed_min_us = timeouts->min_pending_time_us - delayed_pending_us; - error = usleep_interruptible(delayed_min_us); - if (error) - return error; - } error = down_read_killable(&segment->rwsem); if (error) @@ -1250,9 +1229,9 @@ out: delayed_pending_us; } - if (delayed_min_us) { + if (delayed_min_us && *delayed_min_us) { mi->mi_reads_delayed_min++; - mi->mi_reads_delayed_min_us += delayed_min_us; + mi->mi_reads_delayed_min_us += *delayed_min_us; } return 0; @@ -1282,7 +1261,8 @@ static int incfs_update_sysfs_error(struct file *file, int index, int result, ssize_t incfs_read_data_file_block(struct mem_range dst, struct file *f, int index, struct mem_range tmp, - struct incfs_read_data_file_timeouts *timeouts) + struct incfs_read_data_file_timeouts *timeouts, + unsigned int *delayed_min_us) { loff_t pos; ssize_t result; @@ -1301,7 +1281,8 @@ ssize_t incfs_read_data_file_block(struct mem_range dst, struct file *f, mi = df->df_mount_info; bfc = df->df_backing_file_context; - result = wait_for_data_block(df, index, &block, timeouts); + result = wait_for_data_block(df, index, &block, timeouts, + delayed_min_us); if (result < 0) goto out; diff --git a/fs/incfs/data_mgmt.h b/fs/incfs/data_mgmt.h index 2b6121d6131f..8bd5c2fcf6dc 100644 --- a/fs/incfs/data_mgmt.h +++ b/fs/incfs/data_mgmt.h @@ -429,7 +429,8 @@ struct incfs_read_data_file_timeouts { ssize_t incfs_read_data_file_block(struct mem_range dst, struct file *f, int index, struct mem_range tmp, - struct incfs_read_data_file_timeouts *timeouts); + struct incfs_read_data_file_timeouts *timeouts, + unsigned int *delayed_min_us); ssize_t incfs_read_merkle_tree_blocks(struct mem_range dst, struct data_file *df, size_t offset); diff --git a/fs/incfs/sysfs.c b/fs/incfs/sysfs.c index 360f03ca9b63..5c7e0fd4496c 100644 --- a/fs/incfs/sysfs.c +++ b/fs/incfs/sysfs.c @@ -33,11 +33,13 @@ static struct kobj_attribute name##_attr = __ATTR_RO(name) DECLARE_FEATURE_FLAG(corefs); DECLARE_FEATURE_FLAG(zstd); DECLARE_FEATURE_FLAG(v2); +DECLARE_FEATURE_FLAG(bugfix_throttling); static struct attribute *attributes[] = { &corefs_attr.attr, &zstd_attr.attr, &v2_attr.attr, + &bugfix_throttling_attr.attr, NULL, }; diff --git a/fs/incfs/verity.c b/fs/incfs/verity.c index a3dc94b5b036..22308f8c4143 100644 --- a/fs/incfs/verity.c +++ b/fs/incfs/verity.c @@ -323,7 +323,7 @@ static int incfs_build_merkle_tree(struct file *f, struct data_file *df, if (lvl == 0) result = incfs_read_data_file_block(partial_buf, - f, i, tmp, NULL); + f, i, tmp, NULL, NULL); else { hash_level_offset = hash_offset + hash_tree->hash_level_suboffset[lvl - 1]; diff --git a/fs/incfs/vfs.c b/fs/incfs/vfs.c index ad616cfe1252..a0726a505e6c 100644 --- a/fs/incfs/vfs.c +++ b/fs/incfs/vfs.c @@ -5,6 +5,7 @@ #include #include +#include #include #include #include @@ -477,7 +478,8 @@ static struct dentry *open_or_create_special_dir(struct dentry *backing_dir, static int read_single_page_timeouts(struct data_file *df, struct file *f, int block_index, struct mem_range range, - struct mem_range tmp) + struct mem_range tmp, + unsigned int *delayed_min_us) { struct mount_info *mi = df->df_mount_info; struct incfs_read_data_file_timeouts timeouts = { @@ -509,7 +511,23 @@ static int read_single_page_timeouts(struct data_file *df, struct file *f, } return incfs_read_data_file_block(range, f, block_index, tmp, - &timeouts); + &timeouts, delayed_min_us); +} + +static int usleep_interruptible(u32 us) +{ + /* See: + * https://www.kernel.org/doc/Documentation/timers/timers-howto.txt + * for explanation + */ + if (us < 10) { + udelay(us); + return 0; + } else if (us < 20000) { + usleep_range(us, us + us / 10); + return 0; + } else + return msleep_interruptible(us / 1000); } static int read_single_page(struct file *f, struct page *page) @@ -522,6 +540,7 @@ static int read_single_page(struct file *f, struct page *page) int result = 0; void *page_start; int block_index; + unsigned int delayed_min_us = 0; if (!df) { SetPageError(page); @@ -547,7 +566,8 @@ static int read_single_page(struct file *f, struct page *page) bytes_to_read = min_t(loff_t, size - offset, PAGE_SIZE); read_result = read_single_page_timeouts(df, f, block_index, - range(page_start, bytes_to_read), tmp); + range(page_start, bytes_to_read), tmp, + &delayed_min_us); free_pages((unsigned long)tmp.data, get_order(tmp.len)); } else { @@ -569,6 +589,8 @@ err: flush_dcache_page(page); kunmap(page); unlock_page(page); + if (delayed_min_us) + usleep_interruptible(delayed_min_us); return result; } From b086cc7361c3f485f9d2bfdc1c955c67262cc919 Mon Sep 17 00:00:00 2001 From: Srinivasarao Pathipati Date: Wed, 15 Feb 2023 18:46:45 +0530 Subject: [PATCH 1425/4345] FROMLIST: rcu-tasks: Fix build error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixing below build error that got exposed by 'commit 824c55581dde ("UPSTREAM: Enable '-Werror' by default for all kernel builds")' by making show_rcu_tasks_rude_gp_kthread() function as 'inline'. In file included from kernel/rcu/update.c:579:0: kernel/rcu/tasks.h:710:13: error: ‘show_rcu_tasks_rude_gp_kthread’ defined but not used [-Werror=unused-function] static void show_rcu_tasks_rude_gp_kthread(void) {} All warnings are treated as errors after picking upstream 'commit 824c55581dde ("UPSTREAM: Enable '-Werror' by default for all kernel builds")' into android[12/13]-5.10 kernels. In latest Linux kernels this issue won't exist as problematic code got modified by 'commit 27c0f1448389 ("rcutorture: Make grace-period kthread report match RCU flavor being tested")'. Even though buggy code present in 5.10 stable kernel, the 'commit 824c55581dde ("UPSTREAM: Enable '-Werror' by default for all kernel builds")' is not present so this fix is not relevant here and got rejected by community. Bug: 269057599 Link: https://lore.kernel.org/stable/1676916839-32235-1-git-send-email-quic_c_spathi@quicinc.com/ Fixes: 824c55581dde ("UPSTREAM: Enable '-Werror' by default for all kernel builds") Change-Id: I95f6a7a81883d7a6b0f56068b1eb49dc02788685 Signed-off-by: Srinivasarao Pathipati --- kernel/rcu/tasks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 8b51e6a5b386..53ddb4e1a2cb 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -707,7 +707,7 @@ static void show_rcu_tasks_rude_gp_kthread(void) #endif /* #ifndef CONFIG_TINY_RCU */ #else /* #ifdef CONFIG_TASKS_RUDE_RCU */ -static void show_rcu_tasks_rude_gp_kthread(void) {} +static inline void show_rcu_tasks_rude_gp_kthread(void) {} #endif /* #else #ifdef CONFIG_TASKS_RUDE_RCU */ //////////////////////////////////////////////////////////////////////// From 4b9d11ae5f86475d10ce0aa4370eddae22e00ed7 Mon Sep 17 00:00:00 2001 From: Seiya Wang Date: Fri, 24 Feb 2023 10:10:16 +0800 Subject: [PATCH 1426/4345] ANDROID: GKI: Update symbol list for mtk 5 Added functions: [A] 'function void netdev_notice(const net_device*, const char*, ...)' [A] 'function int usb_driver_set_configuration(usb_device*, int)' [A] 'function void usb_enable_lpm(usb_device*)' [A] 'function int usb_reset_device(usb_device*)' [A] 'function int usb_wait_anchor_empty_timeout(usb_anchor*, unsigned int)' Bug: 270620523 Signed-off-by: Seiya Wang Change-Id: I918dc81101c3d66a00fa3147671c0e477c796408 --- android/abi_gki_aarch64.xml | 520 ++++++++++++++++++++++++------------ android/abi_gki_aarch64_mtk | 7 + 2 files changed, 358 insertions(+), 169 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 0b8222af6994..7179cf786230 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -3676,6 +3676,7 @@ + @@ -5753,8 +5754,10 @@ + + @@ -5847,6 +5850,7 @@ + @@ -5869,6 +5873,7 @@ + @@ -14990,6 +14995,7 @@ + @@ -21416,6 +21422,14 @@ + + + + + + + + @@ -34329,66 +34343,66 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -37495,6 +37509,12 @@ + + + + + + @@ -40859,6 +40879,17 @@ + + + + + + + + + + + @@ -42668,6 +42699,7 @@ + @@ -45235,6 +45267,9 @@ + + + @@ -55179,6 +55214,7 @@ + @@ -63134,7 +63170,65 @@ - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -67922,6 +68016,11 @@ + + + + + @@ -69822,7 +69921,26 @@ - + + + + + + + + + + + + + + + + + + + + @@ -83712,6 +83830,9 @@ + + + @@ -83750,6 +83871,7 @@ + @@ -84294,6 +84416,14 @@ + + + + + + + + @@ -92692,6 +92822,9 @@ + + + @@ -95945,6 +96078,7 @@ + @@ -96457,7 +96591,17 @@ - + + + + + + + + + + + @@ -106015,7 +106159,20 @@ - + + + + + + + + + + + + + + @@ -115980,6 +116137,7 @@ + @@ -123044,9 +123202,9 @@ - - - + + + @@ -131531,8 +131689,8 @@ - - + + @@ -131607,9 +131765,9 @@ - - - + + + @@ -132232,40 +132390,40 @@ - - - - + + + + - - - + + + - - + + - - - + + + - - + + - - + + - - + + - - + + @@ -133593,56 +133751,56 @@ - - - - - + + + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + @@ -133685,42 +133843,42 @@ - - + + - - + + - - - - + + + + - - - - + + + + - - - - + + + + - - + + - - + + @@ -133728,100 +133886,100 @@ - + - - - - + + + + - - + + - - + + - - + + - - + + - - + + - - - - - - - + - + + + + + + + - - - + + + - - - - - - + + + + + + - - - - - - + + + + + + - - + + - - - - + + + + - - - + + + - - - - + + + + - - - - + + + + - - + + @@ -136513,6 +136671,12 @@ + + + + + + @@ -138054,8 +138218,8 @@ - - + + @@ -141062,11 +141226,11 @@ - - - - - + + + + + @@ -147188,6 +147352,11 @@ + + + + + @@ -147196,6 +147365,10 @@ + + + + @@ -147634,6 +147807,10 @@ + + + + @@ -147734,6 +147911,11 @@ + + + + + diff --git a/android/abi_gki_aarch64_mtk b/android/abi_gki_aarch64_mtk index 253f8ff87289..69e3dcacf161 100644 --- a/android/abi_gki_aarch64_mtk +++ b/android/abi_gki_aarch64_mtk @@ -1310,6 +1310,7 @@ __netdev_alloc_skb netdev_err netdev_info + netdev_notice netdev_set_default_ethtool_ops netdev_warn netif_carrier_off @@ -2422,6 +2423,8 @@ usb_add_hcd usb_add_phy_dev usb_assign_descriptors + usb_autopm_get_interface_async + usb_autopm_put_interface_async usb_composite_probe usb_composite_unregister usb_copy_descriptors @@ -2431,6 +2434,8 @@ usb_del_gadget_udc usb_deregister usb_disabled + usb_driver_set_configuration + usb_enable_lpm usb_ep_alloc_request usb_ep_autoconfig usb_ep_dequeue @@ -2502,6 +2507,7 @@ usb_remove_function usb_remove_hcd usb_remove_phy + usb_reset_device usb_role_switch_get usb_role_switch_get_drvdata usb_role_switch_get_role @@ -2510,6 +2516,7 @@ usb_role_switch_unregister usb_speed_string usb_string_id + usb_wait_anchor_empty_timeout __usecs_to_jiffies usleep_range uuid_null From 5692e2bb4e82349a965fc7ad2012d30129264a9c Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Tue, 28 Sep 2021 19:11:57 +0200 Subject: [PATCH 1427/4345] UPSTREAM: net: qrtr: combine nameservice into main module Previously with CONFIG_QRTR=m a separate ns.ko would be built which wasn't done on purpose and should be included in qrtr.ko. Rename qrtr.c to af_qrtr.c so we can build a qrtr.ko with both af_qrtr.c and ns.c. Bug: 270636606 Change-Id: Ied36534abd1d589a5a1a5853e3440526271440b0 Signed-off-by: Luca Weiss Reviewed-by: Bjorn Andersson Tested-By: Steev Klimaszewski Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20210928171156.6353-1-luca@z3ntu.xyz Signed-off-by: Jakub Kicinski (cherry picked from commit a365023a76f231cc2fc6e33797e66f3bcaa9f9a9) Signed-off-by: Srinivasarao Pathipati --- net/qrtr/Makefile | 3 ++- net/qrtr/{qrtr.c => af_qrtr.c} | 0 2 files changed, 2 insertions(+), 1 deletion(-) rename net/qrtr/{qrtr.c => af_qrtr.c} (100%) diff --git a/net/qrtr/Makefile b/net/qrtr/Makefile index 1b1411d158a7..8e0605f88a73 100644 --- a/net/qrtr/Makefile +++ b/net/qrtr/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_QRTR) := qrtr.o ns.o +obj-$(CONFIG_QRTR) += qrtr.o +qrtr-y := af_qrtr.o ns.o obj-$(CONFIG_QRTR_SMD) += qrtr-smd.o qrtr-smd-y := smd.o diff --git a/net/qrtr/qrtr.c b/net/qrtr/af_qrtr.c similarity index 100% rename from net/qrtr/qrtr.c rename to net/qrtr/af_qrtr.c From eb9236d74c8cf2a7d68784018e290a48cebbee2e Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 16 Sep 2022 12:40:31 +0200 Subject: [PATCH 1428/4345] drm/etnaviv: don't truncate physical page address [ Upstream commit d37c120b73128690434cc093952439eef9d56af1 ] While the interface for the MMU mapping takes phys_addr_t to hold a full 64bit address when necessary and MMUv2 is able to map physical addresses with up to 40bit, etnaviv_iommu_map() truncates the address to 32bits. Fix this by using the correct type. Fixes: 931e97f3afd8 ("drm/etnaviv: mmuv2: support 40 bit phys address") Signed-off-by: Lucas Stach Reviewed-by: Philipp Zabel Signed-off-by: Sasha Levin --- drivers/gpu/drm/etnaviv/etnaviv_mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c index 9ba2fe48228f..44fbc0a123bf 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c @@ -80,10 +80,10 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova, return -EINVAL; for_each_sgtable_dma_sg(sgt, sg, i) { - u32 pa = sg_dma_address(sg) - sg->offset; + phys_addr_t pa = sg_dma_address(sg) - sg->offset; size_t bytes = sg_dma_len(sg) + sg->offset; - VERB("map[%d]: %08x %08x(%zx)", i, iova, pa, bytes); + VERB("map[%d]: %08x %pap(%zx)", i, iova, &pa, bytes); ret = etnaviv_context_map(context, da, pa, bytes, prot); if (ret) From 051d73eb9ab456bcf5214554f1b37d97bedbb6d0 Mon Sep 17 00:00:00 2001 From: Bitterblue Smith Date: Wed, 28 Sep 2022 23:36:51 +0300 Subject: [PATCH 1429/4345] wifi: rtl8xxxu: gen2: Turn on the rate control [ Upstream commit 791082ec0ab843e0be07c8ce3678e4c2afd2e33d ] Re-enable the function rtl8xxxu_gen2_report_connect. It informs the firmware when connecting to a network. This makes the firmware enable the rate control, which makes the upload faster. It also informs the firmware when disconnecting from a network. In the past this made reconnecting impossible because it was sending the auth on queue 0x7 (TXDESC_QUEUE_VO) instead of queue 0x12 (TXDESC_QUEUE_MGNT): wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 1/3) wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 2/3) wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 3/3) wlp0s20f0u3: authentication with 90:55:de:__:__:__ timed out Probably the firmware disables the unnecessary TX queues when it knows it's disconnected. However, this was fixed in commit edd5747aa12e ("wifi: rtl8xxxu: Fix skb misuse in TX queue selection"). Fixes: c59f13bbead4 ("rtl8xxxu: Work around issue with 8192eu and 8723bu devices not reconnecting") Signed-off-by: Bitterblue Smith Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/43200afc-0c65-ee72-48f8-231edd1df493@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 9a12f1d38007..2cb86c28d11f 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -4369,12 +4369,9 @@ void rtl8xxxu_gen1_report_connect(struct rtl8xxxu_priv *priv, void rtl8xxxu_gen2_report_connect(struct rtl8xxxu_priv *priv, u8 macid, bool connect) { -#ifdef RTL8XXXU_GEN2_REPORT_CONNECT /* - * Barry Day reports this causes issues with 8192eu and 8723bu - * devices reconnecting. The reason for this is unclear, but - * until it is better understood, leave the code in place but - * disabled, so it is not lost. + * The firmware turns on the rate control when it knows it's + * connected to a network. */ struct h2c_cmd h2c; @@ -4387,7 +4384,6 @@ void rtl8xxxu_gen2_report_connect(struct rtl8xxxu_priv *priv, h2c.media_status_rpt.parm &= ~BIT(0); rtl8xxxu_gen2_h2c_cmd(priv, &h2c, sizeof(h2c.media_status_rpt)); -#endif } void rtl8xxxu_gen1_init_aggregation(struct rtl8xxxu_priv *priv) From 072eb5fbd69c1e566e1c9c4b08c199dbbf1dc181 Mon Sep 17 00:00:00 2001 From: Rahul Tanwar Date: Thu, 13 Oct 2022 14:48:30 +0800 Subject: [PATCH 1430/4345] clk: mxl: Switch from direct readl/writel based IO to regmap based IO [ Upstream commit 036177310bac5534de44ff6a7b60a4d2c0b6567c ] Earlier version of driver used direct io remapped register read writes using readl/writel. But we need secure boot access which is only possible when registers are read & written using regmap. This is because the security bus/hook is written & coupled only with regmap layer. Switch the driver from direct readl/writel based register accesses to regmap based register accesses. Additionally, update the license headers to latest status. Reviewed-by: Yi xin Zhu Signed-off-by: Rahul Tanwar Link: https://lore.kernel.org/r/2610331918206e0e3bd18babb39393a558fb34f9.1665642720.git.rtanwar@maxlinear.com Signed-off-by: Stephen Boyd Stable-dep-of: 106ef3bda210 ("clk: mxl: Fix a clk entry by adding relevant flags") Signed-off-by: Sasha Levin --- drivers/clk/x86/Kconfig | 5 +++-- drivers/clk/x86/clk-cgu-pll.c | 10 +++++---- drivers/clk/x86/clk-cgu.c | 5 +++-- drivers/clk/x86/clk-cgu.h | 38 +++++++++++++++++++---------------- drivers/clk/x86/clk-lgm.c | 13 ++++++++---- 5 files changed, 42 insertions(+), 29 deletions(-) diff --git a/drivers/clk/x86/Kconfig b/drivers/clk/x86/Kconfig index 69642e15fcc1..ced99e082e3d 100644 --- a/drivers/clk/x86/Kconfig +++ b/drivers/clk/x86/Kconfig @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only config CLK_LGM_CGU depends on OF && HAS_IOMEM && (X86 || COMPILE_TEST) + select MFD_SYSCON select OF_EARLY_FLATTREE bool "Clock driver for Lightning Mountain(LGM) platform" help - Clock Generation Unit(CGU) driver for Intel Lightning Mountain(LGM) - network processor SoC. + Clock Generation Unit(CGU) driver for MaxLinear's x86 based + Lightning Mountain(LGM) network processor SoC. diff --git a/drivers/clk/x86/clk-cgu-pll.c b/drivers/clk/x86/clk-cgu-pll.c index 3179557b5f78..c83083affe88 100644 --- a/drivers/clk/x86/clk-cgu-pll.c +++ b/drivers/clk/x86/clk-cgu-pll.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2020-2022 MaxLinear, Inc. * Copyright (C) 2020 Intel Corporation. - * Zhu YiXin - * Rahul Tanwar + * Zhu Yixin + * Rahul Tanwar */ #include @@ -76,8 +77,9 @@ static int lgm_pll_enable(struct clk_hw *hw) spin_lock_irqsave(&pll->lock, flags); lgm_set_clk_val(pll->membase, pll->reg, 0, 1, 1); - ret = readl_poll_timeout_atomic(pll->membase + pll->reg, - val, (val & 0x1), 1, 100); + ret = regmap_read_poll_timeout_atomic(pll->membase, pll->reg, + val, (val & 0x1), 1, 100); + spin_unlock_irqrestore(&pll->lock, flags); return ret; diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c index 33de600e0c38..f5f30a18f486 100644 --- a/drivers/clk/x86/clk-cgu.c +++ b/drivers/clk/x86/clk-cgu.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2020-2022 MaxLinear, Inc. * Copyright (C) 2020 Intel Corporation. - * Zhu YiXin - * Rahul Tanwar + * Zhu Yixin + * Rahul Tanwar */ #include #include diff --git a/drivers/clk/x86/clk-cgu.h b/drivers/clk/x86/clk-cgu.h index 4e22bfb22312..dbcb66468797 100644 --- a/drivers/clk/x86/clk-cgu.h +++ b/drivers/clk/x86/clk-cgu.h @@ -1,18 +1,19 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright(c) 2020 Intel Corporation. - * Zhu YiXin - * Rahul Tanwar + * Copyright (C) 2020-2022 MaxLinear, Inc. + * Copyright (C) 2020 Intel Corporation. + * Zhu Yixin + * Rahul Tanwar */ #ifndef __CLK_CGU_H #define __CLK_CGU_H -#include +#include struct lgm_clk_mux { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; u8 shift; u8 width; @@ -22,7 +23,7 @@ struct lgm_clk_mux { struct lgm_clk_divider { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; u8 shift; u8 width; @@ -35,7 +36,7 @@ struct lgm_clk_divider { struct lgm_clk_ddiv { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; u8 shift0; u8 width0; @@ -53,7 +54,7 @@ struct lgm_clk_ddiv { struct lgm_clk_gate { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; u8 shift; unsigned long flags; @@ -77,7 +78,7 @@ enum lgm_clk_type { * @clk_data: array of hw clocks and clk number. */ struct lgm_clk_provider { - void __iomem *membase; + struct regmap *membase; struct device_node *np; struct device *dev; struct clk_hw_onecell_data clk_data; @@ -92,7 +93,7 @@ enum pll_type { struct lgm_clk_pll { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; unsigned long flags; enum pll_type type; @@ -300,29 +301,32 @@ struct lgm_clk_branch { .div = _d, \ } -static inline void lgm_set_clk_val(void __iomem *membase, u32 reg, +static inline void lgm_set_clk_val(struct regmap *membase, u32 reg, u8 shift, u8 width, u32 set_val) { u32 mask = (GENMASK(width - 1, 0) << shift); - u32 regval; - regval = readl(membase + reg); - regval = (regval & ~mask) | ((set_val << shift) & mask); - writel(regval, membase + reg); + regmap_update_bits(membase, reg, mask, set_val << shift); } -static inline u32 lgm_get_clk_val(void __iomem *membase, u32 reg, +static inline u32 lgm_get_clk_val(struct regmap *membase, u32 reg, u8 shift, u8 width) { u32 mask = (GENMASK(width - 1, 0) << shift); u32 val; - val = readl(membase + reg); + if (regmap_read(membase, reg, &val)) { + WARN_ONCE(1, "Failed to read clk reg: 0x%x\n", reg); + return 0; + } + val = (val & mask) >> shift; return val; } + + int lgm_clk_register_branches(struct lgm_clk_provider *ctx, const struct lgm_clk_branch *list, unsigned int nr_clk); diff --git a/drivers/clk/x86/clk-lgm.c b/drivers/clk/x86/clk-lgm.c index 020f4e83a5cc..4fa2bcaf71c8 100644 --- a/drivers/clk/x86/clk-lgm.c +++ b/drivers/clk/x86/clk-lgm.c @@ -1,10 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2020-2022 MaxLinear, Inc. * Copyright (C) 2020 Intel Corporation. - * Zhu YiXin - * Rahul Tanwar + * Zhu Yixin + * Rahul Tanwar */ #include +#include #include #include #include @@ -433,9 +435,12 @@ static int lgm_cgu_probe(struct platform_device *pdev) ctx->clk_data.num = CLK_NR_CLKS; - ctx->membase = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(ctx->membase)) + ctx->membase = syscon_node_to_regmap(np); + if (IS_ERR_OR_NULL(ctx->membase)) { + dev_err(dev, "Failed to get clk CGU iomem\n"); return PTR_ERR(ctx->membase); + } + ctx->np = np; ctx->dev = dev; From 3789e905f4885522ebf37b040eefd62422cff249 Mon Sep 17 00:00:00 2001 From: Rahul Tanwar Date: Thu, 13 Oct 2022 14:48:31 +0800 Subject: [PATCH 1431/4345] clk: mxl: Remove redundant spinlocks [ Upstream commit eaabee88a88a26b108be8d120fc072dfaf462cef ] Patch 1/4 of this patch series switches from direct readl/writel based register access to regmap based register access. Instead of using direct readl/writel, regmap API's are used to read, write & read-modify-write clk registers. Regmap API's already use their own spinlocks to serialize the register accesses across multiple cores in which case additional driver spinlocks becomes redundant. Hence, remove redundant spinlocks from driver in this patch 2/4. Reviewed-by: Yi xin Zhu Signed-off-by: Rahul Tanwar Link: https://lore.kernel.org/r/a8a02c8773b88924503a9fdaacd37dd2e6488bf3.1665642720.git.rtanwar@maxlinear.com Signed-off-by: Stephen Boyd Stable-dep-of: 106ef3bda210 ("clk: mxl: Fix a clk entry by adding relevant flags") Signed-off-by: Sasha Levin --- drivers/clk/x86/clk-cgu-pll.c | 13 ------ drivers/clk/x86/clk-cgu.c | 80 ++++------------------------------- drivers/clk/x86/clk-cgu.h | 6 --- drivers/clk/x86/clk-lgm.c | 1 - 4 files changed, 9 insertions(+), 91 deletions(-) diff --git a/drivers/clk/x86/clk-cgu-pll.c b/drivers/clk/x86/clk-cgu-pll.c index c83083affe88..409dbf55f4ca 100644 --- a/drivers/clk/x86/clk-cgu-pll.c +++ b/drivers/clk/x86/clk-cgu-pll.c @@ -41,13 +41,10 @@ static unsigned long lgm_pll_recalc_rate(struct clk_hw *hw, unsigned long prate) { struct lgm_clk_pll *pll = to_lgm_clk_pll(hw); unsigned int div, mult, frac; - unsigned long flags; - spin_lock_irqsave(&pll->lock, flags); mult = lgm_get_clk_val(pll->membase, PLL_REF_DIV(pll->reg), 0, 12); div = lgm_get_clk_val(pll->membase, PLL_REF_DIV(pll->reg), 18, 6); frac = lgm_get_clk_val(pll->membase, pll->reg, 2, 24); - spin_unlock_irqrestore(&pll->lock, flags); if (pll->type == TYPE_LJPLL) div *= 4; @@ -58,12 +55,9 @@ static unsigned long lgm_pll_recalc_rate(struct clk_hw *hw, unsigned long prate) static int lgm_pll_is_enabled(struct clk_hw *hw) { struct lgm_clk_pll *pll = to_lgm_clk_pll(hw); - unsigned long flags; unsigned int ret; - spin_lock_irqsave(&pll->lock, flags); ret = lgm_get_clk_val(pll->membase, pll->reg, 0, 1); - spin_unlock_irqrestore(&pll->lock, flags); return ret; } @@ -71,16 +65,13 @@ static int lgm_pll_is_enabled(struct clk_hw *hw) static int lgm_pll_enable(struct clk_hw *hw) { struct lgm_clk_pll *pll = to_lgm_clk_pll(hw); - unsigned long flags; u32 val; int ret; - spin_lock_irqsave(&pll->lock, flags); lgm_set_clk_val(pll->membase, pll->reg, 0, 1, 1); ret = regmap_read_poll_timeout_atomic(pll->membase, pll->reg, val, (val & 0x1), 1, 100); - spin_unlock_irqrestore(&pll->lock, flags); return ret; } @@ -88,11 +79,8 @@ static int lgm_pll_enable(struct clk_hw *hw) static void lgm_pll_disable(struct clk_hw *hw) { struct lgm_clk_pll *pll = to_lgm_clk_pll(hw); - unsigned long flags; - spin_lock_irqsave(&pll->lock, flags); lgm_set_clk_val(pll->membase, pll->reg, 0, 1, 0); - spin_unlock_irqrestore(&pll->lock, flags); } static const struct clk_ops lgm_pll_ops = { @@ -123,7 +111,6 @@ lgm_clk_register_pll(struct lgm_clk_provider *ctx, return ERR_PTR(-ENOMEM); pll->membase = ctx->membase; - pll->lock = ctx->lock; pll->reg = list->reg; pll->flags = list->flags; pll->type = list->type; diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c index f5f30a18f486..1f7e93de67bc 100644 --- a/drivers/clk/x86/clk-cgu.c +++ b/drivers/clk/x86/clk-cgu.c @@ -25,14 +25,10 @@ static struct clk_hw *lgm_clk_register_fixed(struct lgm_clk_provider *ctx, const struct lgm_clk_branch *list) { - unsigned long flags; - if (list->div_flags & CLOCK_FLAG_VAL_INIT) { - spin_lock_irqsave(&ctx->lock, flags); + if (list->div_flags & CLOCK_FLAG_VAL_INIT) lgm_set_clk_val(ctx->membase, list->div_off, list->div_shift, list->div_width, list->div_val); - spin_unlock_irqrestore(&ctx->lock, flags); - } return clk_hw_register_fixed_rate(NULL, list->name, list->parent_data[0].name, @@ -42,33 +38,27 @@ static struct clk_hw *lgm_clk_register_fixed(struct lgm_clk_provider *ctx, static u8 lgm_clk_mux_get_parent(struct clk_hw *hw) { struct lgm_clk_mux *mux = to_lgm_clk_mux(hw); - unsigned long flags; u32 val; - spin_lock_irqsave(&mux->lock, flags); if (mux->flags & MUX_CLK_SW) val = mux->reg; else val = lgm_get_clk_val(mux->membase, mux->reg, mux->shift, mux->width); - spin_unlock_irqrestore(&mux->lock, flags); return clk_mux_val_to_index(hw, NULL, mux->flags, val); } static int lgm_clk_mux_set_parent(struct clk_hw *hw, u8 index) { struct lgm_clk_mux *mux = to_lgm_clk_mux(hw); - unsigned long flags; u32 val; val = clk_mux_index_to_val(NULL, mux->flags, index); - spin_lock_irqsave(&mux->lock, flags); if (mux->flags & MUX_CLK_SW) mux->reg = val; else lgm_set_clk_val(mux->membase, mux->reg, mux->shift, mux->width, val); - spin_unlock_irqrestore(&mux->lock, flags); return 0; } @@ -91,7 +81,7 @@ static struct clk_hw * lgm_clk_register_mux(struct lgm_clk_provider *ctx, const struct lgm_clk_branch *list) { - unsigned long flags, cflags = list->mux_flags; + unsigned long cflags = list->mux_flags; struct device *dev = ctx->dev; u8 shift = list->mux_shift; u8 width = list->mux_width; @@ -112,7 +102,6 @@ lgm_clk_register_mux(struct lgm_clk_provider *ctx, init.num_parents = list->num_parents; mux->membase = ctx->membase; - mux->lock = ctx->lock; mux->reg = reg; mux->shift = shift; mux->width = width; @@ -124,11 +113,8 @@ lgm_clk_register_mux(struct lgm_clk_provider *ctx, if (ret) return ERR_PTR(ret); - if (cflags & CLOCK_FLAG_VAL_INIT) { - spin_lock_irqsave(&mux->lock, flags); + if (cflags & CLOCK_FLAG_VAL_INIT) lgm_set_clk_val(mux->membase, reg, shift, width, list->mux_val); - spin_unlock_irqrestore(&mux->lock, flags); - } return hw; } @@ -137,13 +123,10 @@ static unsigned long lgm_clk_divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) { struct lgm_clk_divider *divider = to_lgm_clk_divider(hw); - unsigned long flags; unsigned int val; - spin_lock_irqsave(÷r->lock, flags); val = lgm_get_clk_val(divider->membase, divider->reg, divider->shift, divider->width); - spin_unlock_irqrestore(÷r->lock, flags); return divider_recalc_rate(hw, parent_rate, val, divider->table, divider->flags, divider->width); @@ -164,7 +147,6 @@ lgm_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long prate) { struct lgm_clk_divider *divider = to_lgm_clk_divider(hw); - unsigned long flags; int value; value = divider_get_val(rate, prate, divider->table, @@ -172,10 +154,8 @@ lgm_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, if (value < 0) return value; - spin_lock_irqsave(÷r->lock, flags); lgm_set_clk_val(divider->membase, divider->reg, divider->shift, divider->width, value); - spin_unlock_irqrestore(÷r->lock, flags); return 0; } @@ -183,12 +163,9 @@ lgm_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, static int lgm_clk_divider_enable_disable(struct clk_hw *hw, int enable) { struct lgm_clk_divider *div = to_lgm_clk_divider(hw); - unsigned long flags; - spin_lock_irqsave(&div->lock, flags); lgm_set_clk_val(div->membase, div->reg, div->shift_gate, div->width_gate, enable); - spin_unlock_irqrestore(&div->lock, flags); return 0; } @@ -214,7 +191,7 @@ static struct clk_hw * lgm_clk_register_divider(struct lgm_clk_provider *ctx, const struct lgm_clk_branch *list) { - unsigned long flags, cflags = list->div_flags; + unsigned long cflags = list->div_flags; struct device *dev = ctx->dev; struct lgm_clk_divider *div; struct clk_init_data init = {}; @@ -237,7 +214,6 @@ lgm_clk_register_divider(struct lgm_clk_provider *ctx, init.num_parents = 1; div->membase = ctx->membase; - div->lock = ctx->lock; div->reg = reg; div->shift = shift; div->width = width; @@ -252,11 +228,8 @@ lgm_clk_register_divider(struct lgm_clk_provider *ctx, if (ret) return ERR_PTR(ret); - if (cflags & CLOCK_FLAG_VAL_INIT) { - spin_lock_irqsave(&div->lock, flags); + if (cflags & CLOCK_FLAG_VAL_INIT) lgm_set_clk_val(div->membase, reg, shift, width, list->div_val); - spin_unlock_irqrestore(&div->lock, flags); - } return hw; } @@ -265,7 +238,6 @@ static struct clk_hw * lgm_clk_register_fixed_factor(struct lgm_clk_provider *ctx, const struct lgm_clk_branch *list) { - unsigned long flags; struct clk_hw *hw; hw = clk_hw_register_fixed_factor(ctx->dev, list->name, @@ -274,12 +246,9 @@ lgm_clk_register_fixed_factor(struct lgm_clk_provider *ctx, if (IS_ERR(hw)) return ERR_CAST(hw); - if (list->div_flags & CLOCK_FLAG_VAL_INIT) { - spin_lock_irqsave(&ctx->lock, flags); + if (list->div_flags & CLOCK_FLAG_VAL_INIT) lgm_set_clk_val(ctx->membase, list->div_off, list->div_shift, list->div_width, list->div_val); - spin_unlock_irqrestore(&ctx->lock, flags); - } return hw; } @@ -287,13 +256,10 @@ lgm_clk_register_fixed_factor(struct lgm_clk_provider *ctx, static int lgm_clk_gate_enable(struct clk_hw *hw) { struct lgm_clk_gate *gate = to_lgm_clk_gate(hw); - unsigned long flags; unsigned int reg; - spin_lock_irqsave(&gate->lock, flags); reg = GATE_HW_REG_EN(gate->reg); lgm_set_clk_val(gate->membase, reg, gate->shift, 1, 1); - spin_unlock_irqrestore(&gate->lock, flags); return 0; } @@ -301,25 +267,19 @@ static int lgm_clk_gate_enable(struct clk_hw *hw) static void lgm_clk_gate_disable(struct clk_hw *hw) { struct lgm_clk_gate *gate = to_lgm_clk_gate(hw); - unsigned long flags; unsigned int reg; - spin_lock_irqsave(&gate->lock, flags); reg = GATE_HW_REG_DIS(gate->reg); lgm_set_clk_val(gate->membase, reg, gate->shift, 1, 1); - spin_unlock_irqrestore(&gate->lock, flags); } static int lgm_clk_gate_is_enabled(struct clk_hw *hw) { struct lgm_clk_gate *gate = to_lgm_clk_gate(hw); unsigned int reg, ret; - unsigned long flags; - spin_lock_irqsave(&gate->lock, flags); reg = GATE_HW_REG_STAT(gate->reg); ret = lgm_get_clk_val(gate->membase, reg, gate->shift, 1); - spin_unlock_irqrestore(&gate->lock, flags); return ret; } @@ -334,7 +294,7 @@ static struct clk_hw * lgm_clk_register_gate(struct lgm_clk_provider *ctx, const struct lgm_clk_branch *list) { - unsigned long flags, cflags = list->gate_flags; + unsigned long cflags = list->gate_flags; const char *pname = list->parent_data[0].name; struct device *dev = ctx->dev; u8 shift = list->gate_shift; @@ -355,7 +315,6 @@ lgm_clk_register_gate(struct lgm_clk_provider *ctx, init.num_parents = pname ? 1 : 0; gate->membase = ctx->membase; - gate->lock = ctx->lock; gate->reg = reg; gate->shift = shift; gate->flags = cflags; @@ -367,9 +326,7 @@ lgm_clk_register_gate(struct lgm_clk_provider *ctx, return ERR_PTR(ret); if (cflags & CLOCK_FLAG_VAL_INIT) { - spin_lock_irqsave(&gate->lock, flags); lgm_set_clk_val(gate->membase, reg, shift, 1, list->gate_val); - spin_unlock_irqrestore(&gate->lock, flags); } return hw; @@ -444,24 +401,18 @@ lgm_clk_ddiv_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) static int lgm_clk_ddiv_enable(struct clk_hw *hw) { struct lgm_clk_ddiv *ddiv = to_lgm_clk_ddiv(hw); - unsigned long flags; - spin_lock_irqsave(&ddiv->lock, flags); lgm_set_clk_val(ddiv->membase, ddiv->reg, ddiv->shift_gate, ddiv->width_gate, 1); - spin_unlock_irqrestore(&ddiv->lock, flags); return 0; } static void lgm_clk_ddiv_disable(struct clk_hw *hw) { struct lgm_clk_ddiv *ddiv = to_lgm_clk_ddiv(hw); - unsigned long flags; - spin_lock_irqsave(&ddiv->lock, flags); lgm_set_clk_val(ddiv->membase, ddiv->reg, ddiv->shift_gate, ddiv->width_gate, 0); - spin_unlock_irqrestore(&ddiv->lock, flags); } static int @@ -498,32 +449,25 @@ lgm_clk_ddiv_set_rate(struct clk_hw *hw, unsigned long rate, { struct lgm_clk_ddiv *ddiv = to_lgm_clk_ddiv(hw); u32 div, ddiv1, ddiv2; - unsigned long flags; div = DIV_ROUND_CLOSEST_ULL((u64)prate, rate); - spin_lock_irqsave(&ddiv->lock, flags); if (lgm_get_clk_val(ddiv->membase, ddiv->reg, ddiv->shift2, 1)) { div = DIV_ROUND_CLOSEST_ULL((u64)div, 5); div = div * 2; } - if (div <= 0) { - spin_unlock_irqrestore(&ddiv->lock, flags); + if (div <= 0) return -EINVAL; - } - if (lgm_clk_get_ddiv_val(div, &ddiv1, &ddiv2)) { - spin_unlock_irqrestore(&ddiv->lock, flags); + if (lgm_clk_get_ddiv_val(div, &ddiv1, &ddiv2)) return -EINVAL; - } lgm_set_clk_val(ddiv->membase, ddiv->reg, ddiv->shift0, ddiv->width0, ddiv1 - 1); lgm_set_clk_val(ddiv->membase, ddiv->reg, ddiv->shift1, ddiv->width1, ddiv2 - 1); - spin_unlock_irqrestore(&ddiv->lock, flags); return 0; } @@ -534,18 +478,15 @@ lgm_clk_ddiv_round_rate(struct clk_hw *hw, unsigned long rate, { struct lgm_clk_ddiv *ddiv = to_lgm_clk_ddiv(hw); u32 div, ddiv1, ddiv2; - unsigned long flags; u64 rate64; div = DIV_ROUND_CLOSEST_ULL((u64)*prate, rate); /* if predivide bit is enabled, modify div by factor of 2.5 */ - spin_lock_irqsave(&ddiv->lock, flags); if (lgm_get_clk_val(ddiv->membase, ddiv->reg, ddiv->shift2, 1)) { div = div * 2; div = DIV_ROUND_CLOSEST_ULL((u64)div, 5); } - spin_unlock_irqrestore(&ddiv->lock, flags); if (div <= 0) return *prate; @@ -559,12 +500,10 @@ lgm_clk_ddiv_round_rate(struct clk_hw *hw, unsigned long rate, do_div(rate64, ddiv2); /* if predivide bit is enabled, modify rounded rate by factor of 2.5 */ - spin_lock_irqsave(&ddiv->lock, flags); if (lgm_get_clk_val(ddiv->membase, ddiv->reg, ddiv->shift2, 1)) { rate64 = rate64 * 2; rate64 = DIV_ROUND_CLOSEST_ULL(rate64, 5); } - spin_unlock_irqrestore(&ddiv->lock, flags); return rate64; } @@ -601,7 +540,6 @@ int lgm_clk_register_ddiv(struct lgm_clk_provider *ctx, init.num_parents = 1; ddiv->membase = ctx->membase; - ddiv->lock = ctx->lock; ddiv->reg = list->reg; ddiv->shift0 = list->shift0; ddiv->width0 = list->width0; diff --git a/drivers/clk/x86/clk-cgu.h b/drivers/clk/x86/clk-cgu.h index dbcb66468797..0aa0f35d63a0 100644 --- a/drivers/clk/x86/clk-cgu.h +++ b/drivers/clk/x86/clk-cgu.h @@ -18,7 +18,6 @@ struct lgm_clk_mux { u8 shift; u8 width; unsigned long flags; - spinlock_t lock; }; struct lgm_clk_divider { @@ -31,7 +30,6 @@ struct lgm_clk_divider { u8 width_gate; unsigned long flags; const struct clk_div_table *table; - spinlock_t lock; }; struct lgm_clk_ddiv { @@ -49,7 +47,6 @@ struct lgm_clk_ddiv { unsigned int mult; unsigned int div; unsigned long flags; - spinlock_t lock; }; struct lgm_clk_gate { @@ -58,7 +55,6 @@ struct lgm_clk_gate { unsigned int reg; u8 shift; unsigned long flags; - spinlock_t lock; }; enum lgm_clk_type { @@ -82,7 +78,6 @@ struct lgm_clk_provider { struct device_node *np; struct device *dev; struct clk_hw_onecell_data clk_data; - spinlock_t lock; }; enum pll_type { @@ -97,7 +92,6 @@ struct lgm_clk_pll { unsigned int reg; unsigned long flags; enum pll_type type; - spinlock_t lock; }; /** diff --git a/drivers/clk/x86/clk-lgm.c b/drivers/clk/x86/clk-lgm.c index 4fa2bcaf71c8..e312af42e97a 100644 --- a/drivers/clk/x86/clk-lgm.c +++ b/drivers/clk/x86/clk-lgm.c @@ -444,7 +444,6 @@ static int lgm_cgu_probe(struct platform_device *pdev) ctx->np = np; ctx->dev = dev; - spin_lock_init(&ctx->lock); ret = lgm_clk_register_plls(ctx, lgm_pll_clks, ARRAY_SIZE(lgm_pll_clks)); From 9dcf2ca5d30147d56037679432908e4222c5794f Mon Sep 17 00:00:00 2001 From: Rahul Tanwar Date: Thu, 13 Oct 2022 14:48:32 +0800 Subject: [PATCH 1432/4345] clk: mxl: Add option to override gate clks [ Upstream commit a5d49bd369b8588c0ee9d4d0a2c0160558a3ab69 ] In MxL's LGM SoC, gate clocks can be controlled either from CGU clk driver i.e. this driver or directly from power management driver/daemon. It is dependent on the power policy/profile requirements of the end product. To support such use cases, provide option to override gate clks enable/disable by adding a flag GATE_CLK_HW which controls if these gate clks are controlled by HW i.e. this driver or overridden in order to allow it to be controlled by power profiles instead. Reviewed-by: Yi xin Zhu Signed-off-by: Rahul Tanwar Link: https://lore.kernel.org/r/bdc9c89317b5d338a6c4f1d49386b696e947a672.1665642720.git.rtanwar@maxlinear.com [sboyd@kernel.org: Add braces on many line if-else] Signed-off-by: Stephen Boyd Stable-dep-of: 106ef3bda210 ("clk: mxl: Fix a clk entry by adding relevant flags") Signed-off-by: Sasha Levin --- drivers/clk/x86/clk-cgu.c | 16 +++++++++++++++- drivers/clk/x86/clk-cgu.h | 1 + 2 files changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c index 1f7e93de67bc..4278a687076c 100644 --- a/drivers/clk/x86/clk-cgu.c +++ b/drivers/clk/x86/clk-cgu.c @@ -354,8 +354,22 @@ int lgm_clk_register_branches(struct lgm_clk_provider *ctx, hw = lgm_clk_register_fixed_factor(ctx, list); break; case CLK_TYPE_GATE: - hw = lgm_clk_register_gate(ctx, list); + if (list->gate_flags & GATE_CLK_HW) { + hw = lgm_clk_register_gate(ctx, list); + } else { + /* + * GATE_CLKs can be controlled either from + * CGU clk driver i.e. this driver or directly + * from power management driver/daemon. It is + * dependent on the power policy/profile requirements + * of the end product. To override control of gate + * clks from this driver, provide NULL for this index + * of gate clk provider. + */ + hw = NULL; + } break; + default: dev_err(ctx->dev, "invalid clk type\n"); return -EINVAL; diff --git a/drivers/clk/x86/clk-cgu.h b/drivers/clk/x86/clk-cgu.h index 0aa0f35d63a0..73ce84345f81 100644 --- a/drivers/clk/x86/clk-cgu.h +++ b/drivers/clk/x86/clk-cgu.h @@ -197,6 +197,7 @@ struct lgm_clk_branch { /* clock flags definition */ #define CLOCK_FLAG_VAL_INIT BIT(16) #define MUX_CLK_SW BIT(17) +#define GATE_CLK_HW BIT(18) #define LGM_MUX(_id, _name, _pdata, _f, _reg, \ _shift, _width, _cf, _v) \ From caa47d91738f0e65687733fad53d87cc2048ed98 Mon Sep 17 00:00:00 2001 From: Rahul Tanwar Date: Thu, 13 Oct 2022 14:48:33 +0800 Subject: [PATCH 1433/4345] clk: mxl: Fix a clk entry by adding relevant flags [ Upstream commit 106ef3bda21006fe37b62c85931230a6355d78d3 ] One of the clock entry "dcl" clk has some HW limitations. One is that its rate can only by changed by changing its parent clk's rate & two is that HW does not support enable/disable for this clk. Handle above two limitations by adding relevant flags. Add standard flag CLK_SET_RATE_PARENT to handle rate change and add driver internal flag DIV_CLK_NO_MASK to handle enable/disable. Fixes: d058fd9e8984 ("clk: intel: Add CGU clock driver for a new SoC") Reviewed-by: Yi xin Zhu Signed-off-by: Rahul Tanwar Link: https://lore.kernel.org/r/a4770e7225f8a0c03c8ab2ba80434a4e8e9afb17.1665642720.git.rtanwar@maxlinear.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/x86/clk-cgu.c | 5 +++-- drivers/clk/x86/clk-cgu.h | 1 + drivers/clk/x86/clk-lgm.c | 4 ++-- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c index 4278a687076c..89b53f280aee 100644 --- a/drivers/clk/x86/clk-cgu.c +++ b/drivers/clk/x86/clk-cgu.c @@ -164,8 +164,9 @@ static int lgm_clk_divider_enable_disable(struct clk_hw *hw, int enable) { struct lgm_clk_divider *div = to_lgm_clk_divider(hw); - lgm_set_clk_val(div->membase, div->reg, div->shift_gate, - div->width_gate, enable); + if (div->flags != DIV_CLK_NO_MASK) + lgm_set_clk_val(div->membase, div->reg, div->shift_gate, + div->width_gate, enable); return 0; } diff --git a/drivers/clk/x86/clk-cgu.h b/drivers/clk/x86/clk-cgu.h index 73ce84345f81..bcaf8aec94e5 100644 --- a/drivers/clk/x86/clk-cgu.h +++ b/drivers/clk/x86/clk-cgu.h @@ -198,6 +198,7 @@ struct lgm_clk_branch { #define CLOCK_FLAG_VAL_INIT BIT(16) #define MUX_CLK_SW BIT(17) #define GATE_CLK_HW BIT(18) +#define DIV_CLK_NO_MASK BIT(19) #define LGM_MUX(_id, _name, _pdata, _f, _reg, \ _shift, _width, _cf, _v) \ diff --git a/drivers/clk/x86/clk-lgm.c b/drivers/clk/x86/clk-lgm.c index e312af42e97a..4de77b2c750d 100644 --- a/drivers/clk/x86/clk-lgm.c +++ b/drivers/clk/x86/clk-lgm.c @@ -255,8 +255,8 @@ static const struct lgm_clk_branch lgm_branch_clks[] = { LGM_FIXED(LGM_CLK_SLIC, "slic", NULL, 0, CGU_IF_CLK1, 8, 2, CLOCK_FLAG_VAL_INIT, 8192000, 2), LGM_FIXED(LGM_CLK_DOCSIS, "v_docsis", NULL, 0, 0, 0, 0, 0, 16000000, 0), - LGM_DIV(LGM_CLK_DCL, "dcl", "v_ifclk", 0, CGU_PCMCR, - 25, 3, 0, 0, 0, 0, dcl_div), + LGM_DIV(LGM_CLK_DCL, "dcl", "v_ifclk", CLK_SET_RATE_PARENT, CGU_PCMCR, + 25, 3, 0, 0, DIV_CLK_NO_MASK, 0, dcl_div), LGM_MUX(LGM_CLK_PCM, "pcm", pcm_p, 0, CGU_C55_PCMCR, 0, 1, CLK_MUX_ROUND_CLOSEST, 0), LGM_FIXED_FACTOR(LGM_CLK_DDR_PHY, "ddr_phy", "ddr", From 1423d88753ed4cc9c2564a76ef0858b927dbc5a7 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Mon, 17 Oct 2022 16:22:39 -0400 Subject: [PATCH 1434/4345] powerpc: dts: t208x: Mark MAC1 and MAC2 as 10G [ Upstream commit 36926a7d70c2d462fca1ed85bfee000d17fd8662 ] On the T208X SoCs, MAC1 and MAC2 support XGMII. Add some new MAC dtsi fragments, and mark the QMAN ports as 10G. Fixes: da414bb923d9 ("powerpc/mpc85xx: Add FSL QorIQ DPAA FMan support to the SoC device tree(s)") Signed-off-by: Sean Anderson Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi | 44 +++++++++++++++++++ .../boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi | 44 +++++++++++++++++++ arch/powerpc/boot/dts/fsl/t2081si-post.dtsi | 4 +- 3 files changed, 90 insertions(+), 2 deletions(-) create mode 100644 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi create mode 100644 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi new file mode 100644 index 000000000000..437dab3fc017 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0-or-later +/* + * QorIQ FMan v3 10g port #2 device tree stub [ controller @ offset 0x400000 ] + * + * Copyright 2022 Sean Anderson + * Copyright 2012 - 2015 Freescale Semiconductor Inc. + */ + +fman@400000 { + fman0_rx_0x08: port@88000 { + cell-index = <0x8>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x88000 0x1000>; + fsl,fman-10g-port; + }; + + fman0_tx_0x28: port@a8000 { + cell-index = <0x28>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xa8000 0x1000>; + fsl,fman-10g-port; + }; + + ethernet@e0000 { + cell-index = <0>; + compatible = "fsl,fman-memac"; + reg = <0xe0000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x08 &fman0_tx_0x28>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy0>; + }; + + mdio@e1000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xe1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ + + pcsphy0: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi new file mode 100644 index 000000000000..ad116b17850a --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0-or-later +/* + * QorIQ FMan v3 10g port #3 device tree stub [ controller @ offset 0x400000 ] + * + * Copyright 2022 Sean Anderson + * Copyright 2012 - 2015 Freescale Semiconductor Inc. + */ + +fman@400000 { + fman0_rx_0x09: port@89000 { + cell-index = <0x9>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x89000 0x1000>; + fsl,fman-10g-port; + }; + + fman0_tx_0x29: port@a9000 { + cell-index = <0x29>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xa9000 0x1000>; + fsl,fman-10g-port; + }; + + ethernet@e2000 { + cell-index = <1>; + compatible = "fsl,fman-memac"; + reg = <0xe2000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x09 &fman0_tx_0x29>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy1>; + }; + + mdio@e3000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xe3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ + + pcsphy1: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi index ecbb447920bc..74e17e134387 100644 --- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -609,8 +609,8 @@ /include/ "qoriq-bman1.dtsi" /include/ "qoriq-fman3-0.dtsi" -/include/ "qoriq-fman3-0-1g-0.dtsi" -/include/ "qoriq-fman3-0-1g-1.dtsi" +/include/ "qoriq-fman3-0-10g-2.dtsi" +/include/ "qoriq-fman3-0-10g-3.dtsi" /include/ "qoriq-fman3-0-1g-2.dtsi" /include/ "qoriq-fman3-0-1g-3.dtsi" /include/ "qoriq-fman3-0-1g-4.dtsi" From 2da1f95085791ad8912dc4d9584e2ae003616662 Mon Sep 17 00:00:00 2001 From: Rahul Tanwar Date: Tue, 25 Oct 2022 19:03:57 +0800 Subject: [PATCH 1435/4345] clk: mxl: syscon_node_to_regmap() returns error pointers [ Upstream commit 7256d1f4618b40792d1e9b9b6cb1406a13cad2dd ] Commit 036177310bac ("clk: mxl: Switch from direct readl/writel based IO to regmap based IO") introduced code resulting in below warning issued by the smatch static checker. drivers/clk/x86/clk-lgm.c:441 lgm_cgu_probe() warn: passing zero to 'PTR_ERR' Fix the warning by replacing incorrect IS_ERR_OR_NULL() with IS_ERR(). Fixes: 036177310bac ("clk: mxl: Switch from direct readl/writel based IO to regmap based IO") Reported-by: Dan Carpenter Signed-off-by: Rahul Tanwar Link: https://lore.kernel.org/r/49e339d4739e4ae4c92b00c1b2918af0755d4122.1666695221.git.rtanwar@maxlinear.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/x86/clk-lgm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/x86/clk-lgm.c b/drivers/clk/x86/clk-lgm.c index 4de77b2c750d..f69455dd1c98 100644 --- a/drivers/clk/x86/clk-lgm.c +++ b/drivers/clk/x86/clk-lgm.c @@ -436,7 +436,7 @@ static int lgm_cgu_probe(struct platform_device *pdev) ctx->clk_data.num = CLK_NR_CLKS; ctx->membase = syscon_node_to_regmap(np); - if (IS_ERR_OR_NULL(ctx->membase)) { + if (IS_ERR(ctx->membase)) { dev_err(dev, "Failed to get clk CGU iomem\n"); return PTR_ERR(ctx->membase); } From 119e75d8fe4ddc758a04568fdf28f3c3cda130e9 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 1 Jun 2022 22:45:33 +0200 Subject: [PATCH 1436/4345] random: always mix cycle counter in add_latent_entropy() [ Upstream commit d7bf7f3b813e3755226bcb5114ad2ac477514ebf ] add_latent_entropy() is called every time a process forks, in kernel_clone(). This in turn calls add_device_randomness() using the latent entropy global state. add_device_randomness() does two things: 2) Mixes into the input pool the latent entropy argument passed; and 1) Mixes in a cycle counter, a sort of measurement of when the event took place, the high precision bits of which are presumably difficult to predict. (2) is impossible without CONFIG_GCC_PLUGIN_LATENT_ENTROPY=y. But (1) is always possible. However, currently CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n disables both (1) and (2), instead of just (2). This commit causes the CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n case to still do (1) by passing NULL (len 0) to add_device_randomness() when add_latent_ entropy() is called. Cc: Dominik Brodowski Cc: PaX Team Cc: Emese Revfy Fixes: 38addce8b600 ("gcc-plugins: Add latent_entropy plugin") Signed-off-by: Jason A. Donenfeld Signed-off-by: Sasha Levin --- include/linux/random.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/random.h b/include/linux/random.h index 917470c4490a..ed2bac6c7a8a 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -19,14 +19,14 @@ void add_input_randomness(unsigned int type, unsigned int code, void add_interrupt_randomness(int irq) __latent_entropy; void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy); -#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) { +#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); -} #else -static inline void add_latent_entropy(void) { } + add_device_randomness(NULL, 0); #endif +} void get_random_bytes(void *buf, size_t len); size_t __must_check get_random_bytes_arch(void *buf, size_t len); From a7ef904b68f001b1faef6ba324a267b9b5d74000 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 30 Sep 2022 23:36:32 +0000 Subject: [PATCH 1437/4345] KVM: x86: Fail emulation during EMULTYPE_SKIP on any exception [ Upstream commit 17122c06b86c9f77f45b86b8e62c3ed440847a59 ] Treat any exception during instruction decode for EMULTYPE_SKIP as a "full" emulation failure, i.e. signal failure instead of queuing the exception. When decoding purely to skip an instruction, KVM and/or the CPU has already done some amount of emulation that cannot be unwound, e.g. on an EPT misconfig VM-Exit KVM has already processeed the emulated MMIO. KVM already does this if a #UD is encountered, but not for other exceptions, e.g. if a #PF is encountered during fetch. In SVM's soft-injection use case, queueing the exception is particularly problematic as queueing exceptions while injecting events can put KVM into an infinite loop due to bailing from VM-Enter to service the newly pending exception. E.g. multiple warnings to detect such behavior fire: ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1017 at arch/x86/kvm/x86.c:9873 kvm_arch_vcpu_ioctl_run+0x1de5/0x20a0 [kvm] Modules linked in: kvm_amd ccp kvm irqbypass CPU: 3 PID: 1017 Comm: svm_nested_soft Not tainted 6.0.0-rc1+ #220 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:kvm_arch_vcpu_ioctl_run+0x1de5/0x20a0 [kvm] Call Trace: kvm_vcpu_ioctl+0x223/0x6d0 [kvm] __x64_sys_ioctl+0x85/0xc0 do_syscall_64+0x2b/0x50 entry_SYSCALL_64_after_hwframe+0x46/0xb0 ---[ end trace 0000000000000000 ]--- ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1017 at arch/x86/kvm/x86.c:9987 kvm_arch_vcpu_ioctl_run+0x12a3/0x20a0 [kvm] Modules linked in: kvm_amd ccp kvm irqbypass CPU: 3 PID: 1017 Comm: svm_nested_soft Tainted: G W 6.0.0-rc1+ #220 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:kvm_arch_vcpu_ioctl_run+0x12a3/0x20a0 [kvm] Call Trace: kvm_vcpu_ioctl+0x223/0x6d0 [kvm] __x64_sys_ioctl+0x85/0xc0 do_syscall_64+0x2b/0x50 entry_SYSCALL_64_after_hwframe+0x46/0xb0 ---[ end trace 0000000000000000 ]--- Fixes: 6ea6e84309ca ("KVM: x86: inject exceptions produced by x86_decode_insn") Signed-off-by: Sean Christopherson Link: https://lore.kernel.org/r/20220930233632.1725475-1-seanjc@google.com Signed-off-by: Sasha Levin --- arch/x86/kvm/x86.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 554d37873c25..0ccc8d1b972c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7534,7 +7534,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, write_fault_to_spt, emulation_type)) return 1; - if (ctxt->have_exception) { + + if (ctxt->have_exception && + !(emulation_type & EMULTYPE_SKIP)) { /* * #UD should result in just EMULATION_FAILED, and trap-like * exception should not be encountered during decode. From c41d856b7064e20252e660ff4f2cc49569213b31 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 30 Sep 2022 23:40:31 +0000 Subject: [PATCH 1438/4345] KVM: SVM: Skip WRMSR fastpath on VM-Exit if next RIP isn't valid [ Upstream commit 5c30e8101e8d5d020b1d7119117889756a6ed713 ] Skip the WRMSR fastpath in SVM's VM-Exit handler if the next RIP isn't valid, e.g. because KVM is running with nrips=false. SVM must decode and emulate to skip the WRMSR if the CPU doesn't provide the next RIP. Getting the instruction bytes to decode the WRMSR requires reading guest memory, which in turn means dereferencing memslots, and that isn't safe because KVM doesn't hold SRCU when the fastpath runs. Don't bother trying to enable the fastpath for this case, e.g. by doing only the WRMSR and leaving the "skip" until later. NRIPS is supported on all modern CPUs (KVM has considered making it mandatory), and the next RIP will be valid the vast, vast majority of the time. ============================= WARNING: suspicious RCU usage 6.0.0-smp--4e557fcd3d80-skip #13 Tainted: G O ----------------------------- include/linux/kvm_host.h:954 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by stable/206475: #0: ffff9d9dfebcc0f0 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x8b/0x620 [kvm] stack backtrace: CPU: 152 PID: 206475 Comm: stable Tainted: G O 6.0.0-smp--4e557fcd3d80-skip #13 Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 10.48.0 01/27/2022 Call Trace: dump_stack_lvl+0x69/0xaa dump_stack+0x10/0x12 lockdep_rcu_suspicious+0x11e/0x130 kvm_vcpu_gfn_to_memslot+0x155/0x190 [kvm] kvm_vcpu_gfn_to_hva_prot+0x18/0x80 [kvm] paging64_walk_addr_generic+0x183/0x450 [kvm] paging64_gva_to_gpa+0x63/0xd0 [kvm] kvm_fetch_guest_virt+0x53/0xc0 [kvm] __do_insn_fetch_bytes+0x18b/0x1c0 [kvm] x86_decode_insn+0xf0/0xef0 [kvm] x86_emulate_instruction+0xba/0x790 [kvm] kvm_emulate_instruction+0x17/0x20 [kvm] __svm_skip_emulated_instruction+0x85/0x100 [kvm_amd] svm_skip_emulated_instruction+0x13/0x20 [kvm_amd] handle_fastpath_set_msr_irqoff+0xae/0x180 [kvm] svm_vcpu_run+0x4b8/0x5a0 [kvm_amd] vcpu_enter_guest+0x16ca/0x22f0 [kvm] kvm_arch_vcpu_ioctl_run+0x39d/0x900 [kvm] kvm_vcpu_ioctl+0x538/0x620 [kvm] __se_sys_ioctl+0x77/0xc0 __x64_sys_ioctl+0x1d/0x20 do_syscall_64+0x3d/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 404d5d7bff0d ("KVM: X86: Introduce more exit_fastpath_completion enum values") Signed-off-by: Sean Christopherson Link: https://lore.kernel.org/r/20220930234031.1732249-1-seanjc@google.com Signed-off-by: Sasha Levin --- arch/x86/kvm/svm/svm.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index c34ba034ca11..5775983fec56 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3480,8 +3480,14 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu) static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { - if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && - to_svm(vcpu)->vmcb->control.exit_info_1) + struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control; + + /* + * Note, the next RIP must be provided as SRCU isn't held, i.e. KVM + * can't read guest memory (dereference memslots) to decode the WRMSR. + */ + if (control->exit_code == SVM_EXIT_MSR && control->exit_info_1 && + nrips && control->next_rip) return handle_fastpath_set_msr_irqoff(vcpu); return EXIT_FASTPATH_NONE; From 1b0cafaae8884726c597caded50af185ffc13349 Mon Sep 17 00:00:00 2001 From: Jim Mattson Date: Wed, 19 Oct 2022 14:36:20 -0700 Subject: [PATCH 1439/4345] KVM: VMX: Execute IBPB on emulated VM-exit when guest has IBRS [ Upstream commit 2e7eab81425ad6c875f2ed47c0ce01e78afc38a5 ] According to Intel's document on Indirect Branch Restricted Speculation, "Enabling IBRS does not prevent software from controlling the predicted targets of indirect branches of unrelated software executed later at the same predictor mode (for example, between two different user applications, or two different virtual machines). Such isolation can be ensured through use of the Indirect Branch Predictor Barrier (IBPB) command." This applies to both basic and enhanced IBRS. Since L1 and L2 VMs share hardware predictor modes (guest-user and guest-kernel), hardware IBRS is not sufficient to virtualize IBRS. (The way that basic IBRS is implemented on pre-eIBRS parts, hardware IBRS is actually sufficient in practice, even though it isn't sufficient architecturally.) For virtual CPUs that support IBRS, add an indirect branch prediction barrier on emulated VM-exit, to ensure that the predicted targets of indirect branches executed in L1 cannot be controlled by software that was executed in L2. Since we typically don't intercept guest writes to IA32_SPEC_CTRL, perform the IBPB at emulated VM-exit regardless of the current IA32_SPEC_CTRL.IBRS value, even though the IBPB could technically be deferred until L1 sets IA32_SPEC_CTRL.IBRS, if IA32_SPEC_CTRL.IBRS is clear at emulated VM-exit. This is CVE-2022-2196. Fixes: 5c911beff20a ("KVM: nVMX: Skip IBPB when switching between vmcs01 and vmcs02") Cc: Sean Christopherson Signed-off-by: Jim Mattson Reviewed-by: Sean Christopherson Link: https://lore.kernel.org/r/20221019213620.1953281-3-jmattson@google.com Signed-off-by: Sean Christopherson Signed-off-by: Sasha Levin --- arch/x86/kvm/vmx/nested.c | 11 +++++++++++ arch/x86/kvm/vmx/vmx.c | 6 ++++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f15ddf58a5bc..91371b01eae0 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4556,6 +4556,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmx_switch_vmcs(vcpu, &vmx->vmcs01); + /* + * If IBRS is advertised to the vCPU, KVM must flush the indirect + * branch predictors when transitioning from L2 to L1, as L1 expects + * hardware (KVM in this case) to provide separate predictor modes. + * Bare metal isolates VMX root (host) from VMX non-root (guest), but + * doesn't isolate different VMCSs, i.e. in this case, doesn't provide + * separate modes for L2 vs L1. + */ + if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + indirect_branch_prediction_barrier(); + /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 8f7152e158e2..c37cbd3fdd85 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1431,8 +1431,10 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, /* * No indirect branch prediction barrier needed when switching - * the active VMCS within a guest, e.g. on nested VM-Enter. - * The L1 VMM can protect itself with retpolines, IBPB or IBRS. + * the active VMCS within a vCPU, unless IBRS is advertised to + * the vCPU. To minimize the number of IBPBs executed, KVM + * performs IBPB on nested VM-Exit (a single nested transition + * may switch the active VMCS multiple times). */ if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)) indirect_branch_prediction_barrier(); From 6a3fb887da7d85aaf9a32539976b8ceb12a6306d Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 19 Dec 2022 11:39:27 +0100 Subject: [PATCH 1440/4345] can: kvaser_usb: hydra: help gcc-13 to figure out cmd_len MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f006229135b7debf4037adb1eb93e358559593db ] Debian's gcc-13 [1] throws the following error in kvaser_usb_hydra_cmd_size(): [1] gcc version 13.0.0 20221214 (experimental) [master r13-4693-g512098a3316] (Debian 13-20221214-1) | drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c:502:65: error: | array subscript ‘struct kvaser_cmd_ext[0]’ is partly outside array | bounds of ‘unsigned char[32]’ [-Werror=array-bounds=] | 502 | ret = le16_to_cpu(((struct kvaser_cmd_ext *)cmd)->len); kvaser_usb_hydra_cmd_size() returns the size of given command. It depends on the command number (cmd->header.cmd_no). For extended commands (cmd->header.cmd_no == CMD_EXTENDED) the above shown code is executed. Help gcc to recognize that this code path is not taken in all cases, by calling kvaser_usb_hydra_cmd_size() directly after assigning the command number. Fixes: aec5fb2268b7 ("can: kvaser_usb: Add support for Kvaser USB hydra family") Cc: Jimmy Assarsson Cc: Anssi Hannula Link: https://lore.kernel.org/all/20221219110104.1073881-1-mkl@pengutronix.de Tested-by: Jimmy Assarsson Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- .../net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 33 ++++++++++++++----- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 2764fdd7e84b..233bbfeaa771 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -518,6 +518,7 @@ static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev, u8 cmd_no, int channel) { struct kvaser_cmd *cmd; + size_t cmd_len; int err; cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); @@ -525,6 +526,7 @@ static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev, return -ENOMEM; cmd->header.cmd_no = cmd_no; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); if (channel < 0) { kvaser_usb_hydra_set_cmd_dest_he (cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL); @@ -541,7 +543,7 @@ static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev, kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev)); - err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); if (err) goto end; @@ -557,6 +559,7 @@ kvaser_usb_hydra_send_simple_cmd_async(struct kvaser_usb_net_priv *priv, { struct kvaser_cmd *cmd; struct kvaser_usb *dev = priv->dev; + size_t cmd_len; int err; cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC); @@ -564,14 +567,14 @@ kvaser_usb_hydra_send_simple_cmd_async(struct kvaser_usb_net_priv *priv, return -ENOMEM; cmd->header.cmd_no = cmd_no; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); kvaser_usb_hydra_set_cmd_dest_he (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev)); - err = kvaser_usb_send_cmd_async(priv, cmd, - kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd_async(priv, cmd, cmd_len); if (err) kfree(cmd); @@ -715,6 +718,7 @@ static int kvaser_usb_hydra_get_single_capability(struct kvaser_usb *dev, { struct kvaser_usb_dev_card_data *card_data = &dev->card_data; struct kvaser_cmd *cmd; + size_t cmd_len; u32 value = 0; u32 mask = 0; u16 cap_cmd_res; @@ -726,13 +730,14 @@ static int kvaser_usb_hydra_get_single_capability(struct kvaser_usb *dev, return -ENOMEM; cmd->header.cmd_no = CMD_GET_CAPABILITIES_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); cmd->cap_req.cap_cmd = cpu_to_le16(cap_cmd_req); kvaser_usb_hydra_set_cmd_dest_he(cmd, card_data->hydra.sysdbg_he); kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev)); - err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); if (err) goto end; @@ -1555,6 +1560,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv, struct kvaser_usb *dev = priv->dev; struct kvaser_usb_net_hydra_priv *hydra = priv->sub_priv; struct kvaser_cmd *cmd; + size_t cmd_len; int err; if (!hydra) @@ -1565,6 +1571,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv, return -ENOMEM; cmd->header.cmd_no = CMD_GET_BUSPARAMS_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); kvaser_usb_hydra_set_cmd_dest_he (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); kvaser_usb_hydra_set_cmd_transid @@ -1574,7 +1581,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv, reinit_completion(&priv->get_busparams_comp); - err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); if (err) return err; @@ -1601,6 +1608,7 @@ static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev, struct kvaser_cmd *cmd; struct kvaser_usb_net_priv *priv = netdev_priv(netdev); struct kvaser_usb *dev = priv->dev; + size_t cmd_len; int err; cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); @@ -1608,6 +1616,7 @@ static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev, return -ENOMEM; cmd->header.cmd_no = CMD_SET_BUSPARAMS_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); memcpy(&cmd->set_busparams_req.busparams_nominal, busparams, sizeof(cmd->set_busparams_req.busparams_nominal)); @@ -1616,7 +1625,7 @@ static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev, kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev)); - err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); kfree(cmd); @@ -1629,6 +1638,7 @@ static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev, struct kvaser_cmd *cmd; struct kvaser_usb_net_priv *priv = netdev_priv(netdev); struct kvaser_usb *dev = priv->dev; + size_t cmd_len; int err; cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); @@ -1636,6 +1646,7 @@ static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev, return -ENOMEM; cmd->header.cmd_no = CMD_SET_BUSPARAMS_FD_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); memcpy(&cmd->set_busparams_req.busparams_data, busparams, sizeof(cmd->set_busparams_req.busparams_data)); @@ -1653,7 +1664,7 @@ static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev, kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev)); - err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); kfree(cmd); @@ -1781,6 +1792,7 @@ static int kvaser_usb_hydra_get_software_info(struct kvaser_usb *dev) static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev) { struct kvaser_cmd *cmd; + size_t cmd_len; int err; u32 flags; struct kvaser_usb_dev_card_data *card_data = &dev->card_data; @@ -1790,6 +1802,7 @@ static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev) return -ENOMEM; cmd->header.cmd_no = CMD_GET_SOFTWARE_DETAILS_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); cmd->sw_detail_req.use_ext_cmd = 1; kvaser_usb_hydra_set_cmd_dest_he (cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL); @@ -1797,7 +1810,7 @@ static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev) kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev)); - err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); if (err) goto end; @@ -1913,6 +1926,7 @@ static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv) { struct kvaser_usb *dev = priv->dev; struct kvaser_cmd *cmd; + size_t cmd_len; int err; if ((priv->can.ctrlmode & @@ -1928,6 +1942,7 @@ static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv) return -ENOMEM; cmd->header.cmd_no = CMD_SET_DRIVERMODE_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); kvaser_usb_hydra_set_cmd_dest_he (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); kvaser_usb_hydra_set_cmd_transid @@ -1937,7 +1952,7 @@ static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv) else cmd->set_ctrlmode.mode = KVASER_USB_HYDRA_CTRLMODE_NORMAL; - err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); kfree(cmd); return err; From b50f6fc9d79f0dc875df004c73b6b3fd31186b0b Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Fri, 16 Dec 2022 12:29:37 -0500 Subject: [PATCH 1441/4345] powerpc: dts: t208x: Disable 10G on MAC1 and MAC2 [ Upstream commit 8d8bee13ae9e316443c6666286360126a19c8d94 ] There aren't enough resources to run these ports at 10G speeds. Disable 10G for these ports, reverting to the previous speed. Fixes: 36926a7d70c2 ("powerpc: dts: t208x: Mark MAC1 and MAC2 as 10G") Reported-by: Camelia Alexandra Groza Signed-off-by: Sean Anderson Reviewed-by: Camelia Groza Tested-by: Camelia Groza Link: https://lore.kernel.org/r/20221216172937.2960054-1-sean.anderson@seco.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- arch/powerpc/boot/dts/fsl/t2081si-post.dtsi | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi index 74e17e134387..27714dc2f04a 100644 --- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -659,3 +659,19 @@ interrupts = <16 2 1 9>; }; }; + +&fman0_rx_0x08 { + /delete-property/ fsl,fman-10g-port; +}; + +&fman0_tx_0x28 { + /delete-property/ fsl,fman-10g-port; +}; + +&fman0_rx_0x09 { + /delete-property/ fsl,fman-10g-port; +}; + +&fman0_tx_0x29 { + /delete-property/ fsl,fman-10g-port; +}; From 3d743415c6fb092167df6c23e9c7e9f6df7db625 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Fri, 30 Dec 2022 00:56:41 +0800 Subject: [PATCH 1442/4345] drm/i915/gvt: fix double free bug in split_2MB_gtt_entry commit 4a61648af68f5ba4884f0e3b494ee1cabc4b6620 upstream. If intel_gvt_dma_map_guest_page failed, it will call ppgtt_invalidate_spt, which will finally free the spt. But the caller function ppgtt_populate_spt_by_guest_entry does not notice that, it will free spt again in its error path. Fix this by canceling the mapping of DMA address and freeing sub_spt. Besides, leave the handle of spt destroy to caller function instead of callee function when error occurs. Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support") Signed-off-by: Zheng Wang Reviewed-by: Zhenyu Wang Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20221229165641.1192455-1-zyytlz.wz@163.com Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gvt/gtt.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index a3a4305eda01..0201f9b5f87e 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1192,10 +1192,8 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, for_each_shadow_entry(sub_spt, &sub_se, sub_index) { ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, start_gfn + sub_index, PAGE_SIZE, &dma_addr); - if (ret) { - ppgtt_invalidate_spt(spt); - return ret; - } + if (ret) + goto err; sub_se.val64 = se->val64; /* Copy the PAT field from PDE. */ @@ -1214,6 +1212,17 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, ops->set_pfn(se, sub_spt->shadow_page.mfn); ppgtt_set_shadow_entry(spt, se, index); return 0; +err: + /* Cancel the existing addess mappings of DMA addr. */ + for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) { + gvt_vdbg_mm("invalidate 4K entry\n"); + ppgtt_invalidate_pte(sub_spt, &sub_se); + } + /* Release the new allocated spt. */ + trace_spt_change(sub_spt->vgpu->id, "release", sub_spt, + sub_spt->guest_page.gfn, sub_spt->shadow_page.type); + ppgtt_free_spt(sub_spt); + return ret; } static int split_64KB_gtt_entry(struct intel_vgpu *vgpu, From 267f62b7f3ee94bb0242a72a173073e0da04836f Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Thu, 30 Dec 2021 22:55:47 +0300 Subject: [PATCH 1443/4345] mac80211: mesh: embedd mesh_paths and mpp_paths into ieee80211_if_mesh commit 8b5cb7e41d9d77ffca036b0239177de123394a55 upstream. Syzbot hit NULL deref in rhashtable_free_and_destroy(). The problem was in mesh_paths and mpp_paths being NULL. mesh_pathtbl_init() could fail in case of memory allocation failure, but nobody cared, since ieee80211_mesh_init_sdata() returns void. It led to leaving 2 pointers as NULL. Syzbot has found null deref on exit path, but it could happen anywhere else, because code assumes these pointers are valid. Since all ieee80211_*_setup_sdata functions are void and do not fail, let's embedd mesh_paths and mpp_paths into parent struct to avoid adding error handling on higher levels and follow the pattern of others setup_sdata functions Fixes: 60854fd94573 ("mac80211: mesh: convert path table to rhashtable") Reported-and-tested-by: syzbot+860268315ba86ea6b96b@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Link: https://lore.kernel.org/r/20211230195547.23977-1-paskripkin@gmail.com Signed-off-by: Johannes Berg [pchelkin@ispras.ru: adapt a comment spell fixing issue] Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- net/mac80211/ieee80211_i.h | 24 +++++++++- net/mac80211/mesh.h | 22 +-------- net/mac80211/mesh_pathtbl.c | 89 +++++++++++++------------------------ 3 files changed, 54 insertions(+), 81 deletions(-) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 63499db5c63d..bd349ae9ee4b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -644,6 +644,26 @@ struct mesh_csa_settings { struct cfg80211_csa_settings settings; }; +/** + * struct mesh_table + * + * @known_gates: list of known mesh gates and their mpaths by the station. The + * gate's mpath may or may not be resolved and active. + * @gates_lock: protects updates to known_gates + * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr + * @walk_head: linked list containing all mesh_path objects + * @walk_lock: lock protecting walk_head + * @entries: number of entries in the table + */ +struct mesh_table { + struct hlist_head known_gates; + spinlock_t gates_lock; + struct rhashtable rhead; + struct hlist_head walk_head; + spinlock_t walk_lock; + atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ +}; + struct ieee80211_if_mesh { struct timer_list housekeeping_timer; struct timer_list mesh_path_timer; @@ -718,8 +738,8 @@ struct ieee80211_if_mesh { /* offset from skb->data while building IE */ int meshconf_offset; - struct mesh_table *mesh_paths; - struct mesh_table *mpp_paths; /* Store paths for MPP&MAP */ + struct mesh_table mesh_paths; + struct mesh_table mpp_paths; /* Store paths for MPP&MAP */ int mesh_paths_generation; int mpp_paths_generation; }; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 40492d1bd8fd..b2b717a78114 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -127,26 +127,6 @@ struct mesh_path { u32 path_change_count; }; -/** - * struct mesh_table - * - * @known_gates: list of known mesh gates and their mpaths by the station. The - * gate's mpath may or may not be resolved and active. - * @gates_lock: protects updates to known_gates - * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr - * @walk_head: linked list containging all mesh_path objects - * @walk_lock: lock protecting walk_head - * @entries: number of entries in the table - */ -struct mesh_table { - struct hlist_head known_gates; - spinlock_t gates_lock; - struct rhashtable rhead; - struct hlist_head walk_head; - spinlock_t walk_lock; - atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ -}; - /* Recent multicast cache */ /* RMC_BUCKETS must be a power of 2, maximum 256 */ #define RMC_BUCKETS 256 @@ -308,7 +288,7 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta); void mesh_path_flush_pending(struct mesh_path *mpath); void mesh_path_tx_pending(struct mesh_path *mpath); -int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); +void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata); int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_path_timer(struct timer_list *t); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index c2b051e0610a..d936ef0c17a3 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -47,32 +47,24 @@ static void mesh_path_rht_free(void *ptr, void *tblptr) mesh_path_free_rcu(tbl, mpath); } -static struct mesh_table *mesh_table_alloc(void) +static void mesh_table_init(struct mesh_table *tbl) { - struct mesh_table *newtbl; + INIT_HLIST_HEAD(&tbl->known_gates); + INIT_HLIST_HEAD(&tbl->walk_head); + atomic_set(&tbl->entries, 0); + spin_lock_init(&tbl->gates_lock); + spin_lock_init(&tbl->walk_lock); - newtbl = kmalloc(sizeof(struct mesh_table), GFP_ATOMIC); - if (!newtbl) - return NULL; - - INIT_HLIST_HEAD(&newtbl->known_gates); - INIT_HLIST_HEAD(&newtbl->walk_head); - atomic_set(&newtbl->entries, 0); - spin_lock_init(&newtbl->gates_lock); - spin_lock_init(&newtbl->walk_lock); - if (rhashtable_init(&newtbl->rhead, &mesh_rht_params)) { - kfree(newtbl); - return NULL; - } - - return newtbl; + /* rhashtable_init() may fail only in case of wrong + * mesh_rht_params + */ + WARN_ON(rhashtable_init(&tbl->rhead, &mesh_rht_params)); } static void mesh_table_free(struct mesh_table *tbl) { rhashtable_free_and_destroy(&tbl->rhead, mesh_path_rht_free, tbl); - kfree(tbl); } /** @@ -238,13 +230,13 @@ static struct mesh_path *mpath_lookup(struct mesh_table *tbl, const u8 *dst, struct mesh_path * mesh_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) { - return mpath_lookup(sdata->u.mesh.mesh_paths, dst, sdata); + return mpath_lookup(&sdata->u.mesh.mesh_paths, dst, sdata); } struct mesh_path * mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) { - return mpath_lookup(sdata->u.mesh.mpp_paths, dst, sdata); + return mpath_lookup(&sdata->u.mesh.mpp_paths, dst, sdata); } static struct mesh_path * @@ -281,7 +273,7 @@ __mesh_path_lookup_by_idx(struct mesh_table *tbl, int idx) struct mesh_path * mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { - return __mesh_path_lookup_by_idx(sdata->u.mesh.mesh_paths, idx); + return __mesh_path_lookup_by_idx(&sdata->u.mesh.mesh_paths, idx); } /** @@ -296,7 +288,7 @@ mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) struct mesh_path * mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { - return __mesh_path_lookup_by_idx(sdata->u.mesh.mpp_paths, idx); + return __mesh_path_lookup_by_idx(&sdata->u.mesh.mpp_paths, idx); } /** @@ -309,7 +301,7 @@ int mesh_path_add_gate(struct mesh_path *mpath) int err; rcu_read_lock(); - tbl = mpath->sdata->u.mesh.mesh_paths; + tbl = &mpath->sdata->u.mesh.mesh_paths; spin_lock_bh(&mpath->state_lock); if (mpath->is_gate) { @@ -418,7 +410,7 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, if (!new_mpath) return ERR_PTR(-ENOMEM); - tbl = sdata->u.mesh.mesh_paths; + tbl = &sdata->u.mesh.mesh_paths; spin_lock_bh(&tbl->walk_lock); mpath = rhashtable_lookup_get_insert_fast(&tbl->rhead, &new_mpath->rhash, @@ -460,7 +452,7 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, return -ENOMEM; memcpy(new_mpath->mpp, mpp, ETH_ALEN); - tbl = sdata->u.mesh.mpp_paths; + tbl = &sdata->u.mesh.mpp_paths; spin_lock_bh(&tbl->walk_lock); ret = rhashtable_lookup_insert_fast(&tbl->rhead, @@ -489,7 +481,7 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, void mesh_plink_broken(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; - struct mesh_table *tbl = sdata->u.mesh.mesh_paths; + struct mesh_table *tbl = &sdata->u.mesh.mesh_paths; static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; @@ -548,7 +540,7 @@ static void __mesh_path_del(struct mesh_table *tbl, struct mesh_path *mpath) void mesh_path_flush_by_nexthop(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; - struct mesh_table *tbl = sdata->u.mesh.mesh_paths; + struct mesh_table *tbl = &sdata->u.mesh.mesh_paths; struct mesh_path *mpath; struct hlist_node *n; @@ -563,7 +555,7 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, const u8 *proxy) { - struct mesh_table *tbl = sdata->u.mesh.mpp_paths; + struct mesh_table *tbl = &sdata->u.mesh.mpp_paths; struct mesh_path *mpath; struct hlist_node *n; @@ -597,8 +589,8 @@ static void table_flush_by_iface(struct mesh_table *tbl) */ void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) { - table_flush_by_iface(sdata->u.mesh.mesh_paths); - table_flush_by_iface(sdata->u.mesh.mpp_paths); + table_flush_by_iface(&sdata->u.mesh.mesh_paths); + table_flush_by_iface(&sdata->u.mesh.mpp_paths); } /** @@ -644,7 +636,7 @@ int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr) /* flush relevant mpp entries first */ mpp_flush_by_proxy(sdata, addr); - err = table_path_del(sdata->u.mesh.mesh_paths, sdata, addr); + err = table_path_del(&sdata->u.mesh.mesh_paths, sdata, addr); sdata->u.mesh.mesh_paths_generation++; return err; } @@ -682,7 +674,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) struct mesh_path *gate; bool copy = false; - tbl = sdata->u.mesh.mesh_paths; + tbl = &sdata->u.mesh.mesh_paths; rcu_read_lock(); hlist_for_each_entry_rcu(gate, &tbl->known_gates, gate_list) { @@ -762,29 +754,10 @@ void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop) mesh_path_tx_pending(mpath); } -int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) +void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) { - struct mesh_table *tbl_path, *tbl_mpp; - int ret; - - tbl_path = mesh_table_alloc(); - if (!tbl_path) - return -ENOMEM; - - tbl_mpp = mesh_table_alloc(); - if (!tbl_mpp) { - ret = -ENOMEM; - goto free_path; - } - - sdata->u.mesh.mesh_paths = tbl_path; - sdata->u.mesh.mpp_paths = tbl_mpp; - - return 0; - -free_path: - mesh_table_free(tbl_path); - return ret; + mesh_table_init(&sdata->u.mesh.mesh_paths); + mesh_table_init(&sdata->u.mesh.mpp_paths); } static @@ -806,12 +779,12 @@ void mesh_path_tbl_expire(struct ieee80211_sub_if_data *sdata, void mesh_path_expire(struct ieee80211_sub_if_data *sdata) { - mesh_path_tbl_expire(sdata, sdata->u.mesh.mesh_paths); - mesh_path_tbl_expire(sdata, sdata->u.mesh.mpp_paths); + mesh_path_tbl_expire(sdata, &sdata->u.mesh.mesh_paths); + mesh_path_tbl_expire(sdata, &sdata->u.mesh.mpp_paths); } void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata) { - mesh_table_free(sdata->u.mesh.mesh_paths); - mesh_table_free(sdata->u.mesh.mpp_paths); + mesh_table_free(&sdata->u.mesh.mesh_paths); + mesh_table_free(&sdata->u.mesh.mpp_paths); } From 3b6ce54cfa2c04f0636fd0c985913af8703b408d Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 21 Feb 2023 12:30:15 -0800 Subject: [PATCH 1444/4345] uaccess: Add speculation barrier to copy_from_user() commit 74e19ef0ff8061ef55957c3abd71614ef0f42f47 upstream. The results of "access_ok()" can be mis-speculated. The result is that you can end speculatively: if (access_ok(from, size)) // Right here even for bad from/size combinations. On first glance, it would be ideal to just add a speculation barrier to "access_ok()" so that its results can never be mis-speculated. But there are lots of system calls just doing access_ok() via "copy_to_user()" and friends (example: fstat() and friends). Those are generally not problematic because they do not _consume_ data from userspace other than the pointer. They are also very quick and common system calls that should not be needlessly slowed down. "copy_from_user()" on the other hand uses a user-controller pointer and is frequently followed up with code that might affect caches. Take something like this: if (!copy_from_user(&kernelvar, uptr, size)) do_something_with(kernelvar); If userspace passes in an evil 'uptr' that *actually* points to a kernel addresses, and then do_something_with() has cache (or other) side-effects, it could allow userspace to infer kernel data values. Add a barrier to the common copy_from_user() code to prevent mis-speculated values which happen after the copy. Also add a stub for architectures that do not define barrier_nospec(). This makes the macro usable in generic code. Since the barrier is now usable in generic code, the x86 #ifdef in the BPF code can also go away. Reported-by: Jordy Zomer Suggested-by: Linus Torvalds Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Acked-by: Daniel Borkmann # BPF bits Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/nospec.h | 4 ++++ kernel/bpf/core.c | 2 -- lib/usercopy.c | 7 +++++++ 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/include/linux/nospec.h b/include/linux/nospec.h index c1e79f72cd89..9f0af4f116d9 100644 --- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -11,6 +11,10 @@ struct task_struct; +#ifndef barrier_nospec +# define barrier_nospec() do { } while (0) +#endif + /** * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise * @index: array element index diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index fd2aa6b9909e..c18aed60ce40 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1642,9 +1642,7 @@ out: * reuse preexisting logic from Spectre v1 mitigation that * happens to produce the required code on x86 for v4 as well. */ -#ifdef CONFIG_X86 barrier_nospec(); -#endif CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ diff --git a/lib/usercopy.c b/lib/usercopy.c index 7413dd300516..7ee63df042d7 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -3,6 +3,7 @@ #include #include #include +#include /* out-of-line parts */ @@ -12,6 +13,12 @@ unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { + /* + * Ensure that bad access_ok() speculation will not + * lead to nasty side effects *after* the copy is + * finished: + */ + barrier_nospec(); instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } From f3f6b33b77bac0bd27f1f1bec05ab58a54948fc9 Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Tue, 21 Feb 2023 02:04:46 +0800 Subject: [PATCH 1445/4345] Revert "Revert "block: nbd: add sanity check for first_minor"" This reverts commit 0daa75bf750c400af0a0127fae37cd959d36dee7. These problems such as: https://lore.kernel.org/all/CACPK8XfUWoOHr-0RwRoYoskia4fbAbZ7DYf5wWBnv6qUnGq18w@mail.gmail.com/ It was introduced by introduced by commit b1a811633f73 ("block: nbd: add sanity check for first_minor") and has been have been fixed by commit e4c4871a7394 ("nbd: fix max value for 'first_minor'"). Cc: Joel Stanley Cc: Christoph Hellwig Cc: Pavel Skripkin Cc: Jens Axboe Cc: Sasha Levin Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Wen Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/nbd.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index b0d3dadeb964..bf8148ebd858 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1771,7 +1771,17 @@ static int nbd_dev_add(int index) refcount_set(&nbd->refs, 1); INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; + + /* Too big first_minor can cause duplicate creation of + * sysfs files/links, since first_minor will be truncated to + * byte in __device_add_disk(). + */ disk->first_minor = index << part_shift; + if (disk->first_minor > 0xff) { + err = -EINVAL; + goto out_free_idr; + } + disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); From fd8107206a672f5a529a819e8930bf81fb54ae0f Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 2 Nov 2021 09:52:34 +0800 Subject: [PATCH 1446/4345] nbd: fix max value for 'first_minor' commit e4c4871a73944353ea23e319de27ef73ce546623 upstream. commit b1a811633f73 ("block: nbd: add sanity check for first_minor") checks that 'first_minor' should not be greater than 0xff, which is wrong. Whitout the commit, the details that when user pass 0x100000, it ends up create sysfs dir "/sys/block/43:0" are as follows: nbd_dev_add disk->first_minor = index << part_shift -> default part_shift is 5, first_minor is 0x2000000 device_add_disk ddev->devt = MKDEV(disk->major, disk->first_minor) -> (0x2b << 20) | (0x2000000) = 0x2b00000 device_add device_create_sys_dev_entry format_dev_t sprintf(buffer, "%u:%u", MAJOR(dev), MINOR(dev)); -> got 43:0 sysfs_create_link -> /sys/block/43:0 By the way, with the wrong fix, when part_shift is the default value, only 8 ndb devices can be created since 8 << 5 is greater than 0xff. Since the max bits for 'first_minor' should be the same as what MKDEV() does, which is 20. Change the upper bound of 'first_minor' from 0xff to 0xfffff. Fixes: b1a811633f73 ("block: nbd: add sanity check for first_minor") Signed-off-by: Yu Kuai Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20211102015237.2309763-2-yebin10@huawei.com Signed-off-by: Jens Axboe Signed-off-by: Wen Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/nbd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index bf8148ebd858..bd05eaf04143 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1773,11 +1773,11 @@ static int nbd_dev_add(int index) disk->major = NBD_MAJOR; /* Too big first_minor can cause duplicate creation of - * sysfs files/links, since first_minor will be truncated to - * byte in __device_add_disk(). + * sysfs files/links, since MKDEV() expect that the max bits of + * first_minor is 20. */ disk->first_minor = index << part_shift; - if (disk->first_minor > 0xff) { + if (disk->first_minor > MINORMASK) { err = -EINVAL; goto out_free_idr; } From 2e0c3e43ebb99c2b495229f8fade4c043fbd06a5 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 2 Nov 2021 09:52:35 +0800 Subject: [PATCH 1447/4345] nbd: fix possible overflow for 'first_minor' in nbd_dev_add() commit 940c264984fd1457918393c49674f6b39ee16506 upstream. If 'part_shift' is not zero, then 'index << part_shift' might overflow to a value that is not greater than '0xfffff', then sysfs might complains about duplicate creation. Fixes: b0d9111a2d53 ("nbd: use an idr to keep track of nbd devices") Signed-off-by: Yu Kuai Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20211102015237.2309763-3-yebin10@huawei.com Signed-off-by: Jens Axboe Signed-off-by: Wen Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/nbd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index bd05eaf04143..1ddae8f768d5 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1773,11 +1773,11 @@ static int nbd_dev_add(int index) disk->major = NBD_MAJOR; /* Too big first_minor can cause duplicate creation of - * sysfs files/links, since MKDEV() expect that the max bits of - * first_minor is 20. + * sysfs files/links, since index << part_shift might overflow, or + * MKDEV() expect that the max bits of first_minor is 20. */ disk->first_minor = index << part_shift; - if (disk->first_minor > MINORMASK) { + if (disk->first_minor < index || disk->first_minor > MINORMASK) { err = -EINVAL; goto out_free_idr; } From 4311ad1e7654f9dd569a4d1b0059f838f474e9d3 Mon Sep 17 00:00:00 2001 From: Zhang Wensheng Date: Sat, 21 May 2022 15:37:48 +0800 Subject: [PATCH 1448/4345] nbd: fix possible overflow on 'first_minor' in nbd_dev_add() commit 858f1bf65d3d9c00b5e2d8ca87dc79ed88267c98 upstream. When 'index' is a big numbers, it may become negative which forced to 'int'. then 'index << part_shift' might overflow to a positive value that is not greater than '0xfffff', then sysfs might complains about duplicate creation. Because of this, move the 'index' judgment to the front will fix it and be better. Fixes: b0d9111a2d53 ("nbd: use an idr to keep track of nbd devices") Fixes: 940c264984fd ("nbd: fix possible overflow for 'first_minor' in nbd_dev_add()") Signed-off-by: Zhang Wensheng Signed-off-by: Yu Kuai Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20220521073749.3146892-6-yukuai3@huawei.com Signed-off-by: Jens Axboe Signed-off-by: Wen Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/nbd.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 1ddae8f768d5..dbcd903ba128 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1771,17 +1771,7 @@ static int nbd_dev_add(int index) refcount_set(&nbd->refs, 1); INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; - - /* Too big first_minor can cause duplicate creation of - * sysfs files/links, since index << part_shift might overflow, or - * MKDEV() expect that the max bits of first_minor is 20. - */ disk->first_minor = index << part_shift; - if (disk->first_minor < index || disk->first_minor > MINORMASK) { - err = -EINVAL; - goto out_free_idr; - } - disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); @@ -1875,8 +1865,19 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; - if (info->attrs[NBD_ATTR_INDEX]) + if (info->attrs[NBD_ATTR_INDEX]) { index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); + + /* + * Too big first_minor can cause duplicate creation of + * sysfs files/links, since index << part_shift might overflow, or + * MKDEV() expect that the max bits of first_minor is 20. + */ + if (index < 0 || index > MINORMASK >> part_shift) { + printk(KERN_ERR "nbd: illegal input index %d\n", index); + return -EINVAL; + } + } if (!info->attrs[NBD_ATTR_SOCKETS]) { printk(KERN_ERR "nbd: must specify at least one socket\n"); return -EINVAL; From e1dc3f102a8127255975ddbdd81fa2525d861d00 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 27 Jan 2023 15:01:00 +0100 Subject: [PATCH 1449/4345] wifi: mwifiex: Add missing compatible string for SD8787 commit 36dd7a4c6226133b0b7aa92b8e604e688d958d0c upstream. Commit e3fffc1f0b47 ("devicetree: document new marvell-8xxx and pwrseq-sd8787 options") documented a compatible string for SD8787 in the devicetree bindings, but neglected to add it to the mwifiex driver. Fixes: e3fffc1f0b47 ("devicetree: document new marvell-8xxx and pwrseq-sd8787 options") Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v4.11+ Cc: Matt Ranostay Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/320de5005ff3b8fd76be2d2b859fd021689c3681.1674827105.git.lukas@wunner.de Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/marvell/mwifiex/sdio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index bde9e4bbfffe..7fb6eef40928 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -485,6 +485,7 @@ static struct memory_type_mapping mem_type_mapping_tbl[] = { }; static const struct of_device_id mwifiex_sdio_of_match_table[] = { + { .compatible = "marvell,sd8787" }, { .compatible = "marvell,sd8897" }, { .compatible = "marvell,sd8997" }, { } From 01e652f03a865b41cfc44e04dbdbbc1d83f15dd4 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 7 Feb 2023 10:21:47 -0500 Subject: [PATCH 1450/4345] audit: update the mailing list in MAINTAINERS commit 6c6cd913accd77008f74a1a9d57b816db3651daa upstream. We've moved the upstream Linux Kernel audit subsystem discussions to a new mailing list, this patch updates the MAINTAINERS info with the new list address. Marking this for stable inclusion to help speed uptake of the new list across all of the supported kernel releases. This is a doc only patch so the risk should be close to nil. Cc: stable@vger.kernel.org Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index f6c6b403a1b7..6c5efc4013ab 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3001,7 +3001,7 @@ F: drivers/net/ieee802154/atusb.h AUDIT SUBSYSTEM M: Paul Moore M: Eric Paris -L: linux-audit@redhat.com (moderated for non-subscribers) +L: audit@vger.kernel.org S: Supported W: https://github.com/linux-audit T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git From 1ba10d3640e9783dad811fe4e24d55465c37c64d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Jan 2023 13:09:12 -0800 Subject: [PATCH 1451/4345] ext4: Fix function prototype mismatch for ext4_feat_ktype commit 118901ad1f25d2334255b3d50512fa20591531cd upstream. With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. ext4_feat_ktype was setting the "release" handler to "kfree", which doesn't have a matching function prototype. Add a simple wrapper with the correct prototype. This was found as a result of Clang's new -Wcast-function-type-strict flag, which is more sensitive than the simpler -Wcast-function-type, which only checks for type width mismatches. Note that this code is only reached when ext4 is a loadable module and it is being unloaded: CFI failure at kobject_put+0xbb/0x1b0 (target: kfree+0x0/0x180; expected type: 0x7c4aa698) ... RIP: 0010:kobject_put+0xbb/0x1b0 ... Call Trace: ext4_exit_sysfs+0x14/0x60 [ext4] cleanup_module+0x67/0xedb [ext4] Fixes: b99fee58a20a ("ext4: create ext4_feat kobject dynamically") Cc: Theodore Ts'o Cc: Eric Biggers Cc: stable@vger.kernel.org Build-tested-by: Gustavo A. R. Silva Reviewed-by: Gustavo A. R. Silva Reviewed-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230103234616.never.915-kees@kernel.org Signed-off-by: Kees Cook Reviewed-by: Eric Biggers Link: https://lore.kernel.org/r/20230104210908.gonna.388-kees@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/ext4/sysfs.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index f24bef3be48a..ce74cde6d8fa 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -487,6 +487,11 @@ static void ext4_sb_release(struct kobject *kobj) complete(&sbi->s_kobj_unregister); } +static void ext4_feat_release(struct kobject *kobj) +{ + kfree(kobj); +} + static const struct sysfs_ops ext4_attr_ops = { .show = ext4_attr_show, .store = ext4_attr_store, @@ -501,7 +506,7 @@ static struct kobj_type ext4_sb_ktype = { static struct kobj_type ext4_feat_ktype = { .default_groups = ext4_feat_groups, .sysfs_ops = &ext4_attr_ops, - .release = (void (*)(struct kobject *))kfree, + .release = ext4_feat_release, }; static struct kobject *ext4_root; From c44e96d6c31a0937c6b82c3dc3e6500545fb1024 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 5 Oct 2022 01:01:00 +0300 Subject: [PATCH 1452/4345] Revert "net/sched: taprio: make qdisc_leaf() see the per-netdev-queue pfifo child qdiscs" commit af7b29b1deaac6da3bb7637f0e263dfab7bfc7a3 upstream. taprio_attach() has this logic at the end, which should have been removed with the blamed patch (which is now being reverted): /* access to the child qdiscs is not needed in offload mode */ if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { kfree(q->qdiscs); q->qdiscs = NULL; } because otherwise, we make use of q->qdiscs[] even after this array was deallocated, namely in taprio_leaf(). Therefore, whenever one would try to attach a valid child qdisc to a fully offloaded taprio root, one would immediately dereference a NULL pointer. $ tc qdisc replace dev eno0 handle 8001: parent root taprio \ num_tc 8 \ map 0 1 2 3 4 5 6 7 \ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \ max-sdu 0 0 0 0 0 200 0 0 \ base-time 200 \ sched-entry S 80 20000 \ sched-entry S a0 20000 \ sched-entry S 5f 60000 \ flags 2 $ max_frame_size=1500 $ data_rate_kbps=20000 $ port_transmit_rate_kbps=1000000 $ idleslope=$data_rate_kbps $ sendslope=$(($idleslope - $port_transmit_rate_kbps)) $ locredit=$(($max_frame_size * $sendslope / $port_transmit_rate_kbps)) $ hicredit=$(($max_frame_size * $idleslope / $port_transmit_rate_kbps)) $ tc qdisc replace dev eno0 parent 8001:7 cbs \ idleslope $idleslope \ sendslope $sendslope \ hicredit $hicredit \ locredit $locredit \ offload 0 Unable to handle kernel NULL pointer dereference at virtual address 0000000000000030 pc : taprio_leaf+0x28/0x40 lr : qdisc_leaf+0x3c/0x60 Call trace: taprio_leaf+0x28/0x40 tc_modify_qdisc+0xf0/0x72c rtnetlink_rcv_msg+0x12c/0x390 netlink_rcv_skb+0x5c/0x130 rtnetlink_rcv+0x1c/0x2c The solution is not as obvious as the problem. The code which deallocates q->qdiscs[] is in fact copied and pasted from mqprio, which also deallocates the array in mqprio_attach() and never uses it afterwards. Therefore, the identical cleanup logic of priv->qdiscs[] that mqprio_destroy() has is deceptive because it will never take place at qdisc_destroy() time, but just at raw ops->destroy() time (otherwise said, priv->qdiscs[] do not last for the entire lifetime of the mqprio root), but rather, this is just the twisted way in which the Qdisc API understands error path cleanup should be done (Qdisc_ops :: destroy() is called even when Qdisc_ops :: init() never succeeded). Side note, in fact this is also what the comment in mqprio_init() says: /* pre-allocate qdisc, attachment can't fail */ Or reworded, mqprio's priv->qdiscs[] scheme is only meant to serve as data passing between Qdisc_ops :: init() and Qdisc_ops :: attach(). [ this comment was also copied and pasted into the initial taprio commit, even though taprio_attach() came way later ] The problem is that taprio also makes extensive use of the q->qdiscs[] array in the software fast path (taprio_enqueue() and taprio_dequeue()), but it does not keep a reference of its own on q->qdiscs[i] (you'd think that since it creates these Qdiscs, it holds the reference, but nope, this is not completely true). To understand the difference between taprio_destroy() and mqprio_destroy() one must look before commit 13511704f8d7 ("net: taprio offload: enforce qdisc to netdev queue mapping"), because that just muddied the waters. In the "original" taprio design, taprio always attached itself (the root Qdisc) to all netdev TX queues, so that dev_qdisc_enqueue() would go through taprio_enqueue(). It also called qdisc_refcount_inc() on itself for as many times as there were netdev TX queues, in order to counter-balance what tc_get_qdisc() does when destroying a Qdisc (simplified for brevity below): if (n->nlmsg_type == RTM_DELQDISC) err = qdisc_graft(dev, parent=NULL, new=NULL, q, extack); qdisc_graft(where "new" is NULL so this deletes the Qdisc): for (i = 0; i < num_q; i++) { struct netdev_queue *dev_queue; dev_queue = netdev_get_tx_queue(dev, i); old = dev_graft_qdisc(dev_queue, new); if (new && i > 0) qdisc_refcount_inc(new); qdisc_put(old); ~~~~~~~~~~~~~~ this decrements taprio's refcount once for each TX queue } notify_and_destroy(net, skb, n, classid, rtnl_dereference(dev->qdisc), new); ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ and this finally decrements it to zero, making qdisc_put() call qdisc_destroy() The q->qdiscs[] created using qdisc_create_dflt() (or their replacements, if taprio_graft() was ever to get called) were then privately freed by taprio_destroy(). This is still what is happening after commit 13511704f8d7 ("net: taprio offload: enforce qdisc to netdev queue mapping"), but only for software mode. In full offload mode, the per-txq "qdisc_put(old)" calls from qdisc_graft() now deallocate the child Qdiscs rather than decrement taprio's refcount. So when notify_and_destroy(taprio) finally calls taprio_destroy(), the difference is that the child Qdiscs were already deallocated. And this is exactly why the taprio_attach() comment "access to the child qdiscs is not needed in offload mode" is deceptive too. Not only the q->qdiscs[] array is not needed, but it is also necessary to get rid of it as soon as possible, because otherwise, we will also call qdisc_put() on the child Qdiscs in qdisc_destroy() -> taprio_destroy(), and this will cause a nasty use-after-free/refcount-saturate/whatever. In short, the problem is that since the blamed commit, taprio_leaf() needs q->qdiscs[] to not be freed by taprio_attach(), while qdisc_destroy() -> taprio_destroy() does need q->qdiscs[] to be freed by taprio_attach() for full offload. Fixing one problem triggers the other. All of this can be solved by making taprio keep its q->qdiscs[i] with a refcount elevated at 2 (in offloaded mode where they are attached to the netdev TX queues), both in taprio_attach() and in taprio_graft(). The generic qdisc_graft() would just decrement the child qdiscs' refcounts to 1, and taprio_destroy() would give them the final coup de grace. However the rabbit hole of changes is getting quite deep, and the complexity increases. The blamed commit was supposed to be a bug fix in the first place, and the bug it addressed is not so significant so as to justify further rework in stable trees. So I'd rather just revert it. I don't know enough about multi-queue Qdisc design to make a proper judgement right now regarding what is/isn't idiomatic use of Qdisc concepts in taprio. I will try to study the problem more and come with a different solution in net-next. Fixes: 1461d212ab27 ("net/sched: taprio: make qdisc_leaf() see the per-netdev-queue pfifo child qdiscs") Reported-by: Muhammad Husaini Zulkifli Reported-by: Vinicius Costa Gomes Signed-off-by: Vladimir Oltean Reviewed-by: Vinicius Costa Gomes Link: https://lore.kernel.org/r/20221004220100.1650558-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/sched/sch_taprio.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index e25fe44899ff..2d842f31ec5a 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1906,14 +1906,12 @@ start_error: static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) { - struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); - unsigned int ntx = cl - 1; + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); - if (ntx >= dev->num_tx_queues) + if (!dev_queue) return NULL; - return q->qdiscs[ntx]; + return dev_queue->qdisc_sleeping; } static unsigned long taprio_find(struct Qdisc *sch, u32 classid) From 12e3119a87627741bd3871c895ce198f21529eb3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 22 Feb 2023 09:52:32 -0800 Subject: [PATCH 1453/4345] bpf: add missing header file include MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f3dd0c53370e70c0f9b7e931bbec12916f3bb8cc upstream. Commit 74e19ef0ff80 ("uaccess: Add speculation barrier to copy_from_user()") built fine on x86-64 and arm64, and that's the extent of my local build testing. It turns out those got the include incidentally through other header files ( in particular), but that was not true of other architectures, resulting in build errors kernel/bpf/core.c: In function ‘___bpf_prog_run’: kernel/bpf/core.c:1913:3: error: implicit declaration of function ‘barrier_nospec’ so just make sure to explicitly include the proper header file to make everybody see it. Fixes: 74e19ef0ff80 ("uaccess: Add speculation barrier to copy_from_user()") Reported-by: kernel test robot Reported-by: Viresh Kumar Reported-by: Huacai Chen Tested-by: Geert Uytterhoeven Tested-by: Dave Hansen Acked-by: Alexei Starovoitov Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- kernel/bpf/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c18aed60ce40..73d4b1e32fbd 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include From 22d269bb30db7f5a4e71a8a813a0f4df5255f7de Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 25 Feb 2023 11:55:05 +0100 Subject: [PATCH 1454/4345] Linux 5.10.170 Link: https://lore.kernel.org/r/20230223130426.817998725@linuxfoundation.org Link: https://lore.kernel.org/r/20230223141540.701637224@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Pavel Machek (CIP) Tested-by: Shuah Khan Tested-by: Slade Watkins Tested-by: Guenter Roeck Tested-by: Sudip Mukherjee Tested-by: Linux Kernel Functional Testing Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index dbbfaa5d4fe2..028fca7ec5cf 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 169 +SUBLEVEL = 170 EXTRAVERSION = NAME = Dare mighty things From bb0ae42d0bea1ce79f5499940c27ea1f7a13c7ac Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 25 Feb 2023 15:27:49 +0000 Subject: [PATCH 1455/4345] Revert "Revert "nvmem: core: Fix a conflict between MTD and NVMEM on wp-gpios property"" This reverts commit b34e092097a727ad3bb2eea81e9b6791dda61280. It needs to come back to handle the 5.10.169 merge properly, it will be reverted again afterward to resolve the abi issues. Bug: 161946584 Change-Id: I8ff6a57edb206a515edd856341e0a916cc4d9c08 Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 2 +- include/linux/nvmem-provider.h | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 7b281ae540ad..48fbe49e3772 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -629,7 +629,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (config->wp_gpio) nvmem->wp_gpio = config->wp_gpio; - else + else if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 06409a6c40bc..39ec67689898 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -49,7 +49,8 @@ enum nvmem_type { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin + * @wp-gpio: Write protect pin + * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem" name will be assigned to the device if * no name is specified in its configuration. In such case "" is @@ -69,6 +70,7 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; + bool ignore_wp; bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; From fda8a58faa7d721322b255a8b6f35e25f827c190 Mon Sep 17 00:00:00 2001 From: Jim Mattson Date: Wed, 19 Oct 2022 14:36:20 -0700 Subject: [PATCH 1456/4345] UPSTREAM: KVM: VMX: Execute IBPB on emulated VM-exit when guest has IBRS [ Upstream commit 2e7eab81425ad6c875f2ed47c0ce01e78afc38a5 ] According to Intel's document on Indirect Branch Restricted Speculation, "Enabling IBRS does not prevent software from controlling the predicted targets of indirect branches of unrelated software executed later at the same predictor mode (for example, between two different user applications, or two different virtual machines). Such isolation can be ensured through use of the Indirect Branch Predictor Barrier (IBPB) command." This applies to both basic and enhanced IBRS. Since L1 and L2 VMs share hardware predictor modes (guest-user and guest-kernel), hardware IBRS is not sufficient to virtualize IBRS. (The way that basic IBRS is implemented on pre-eIBRS parts, hardware IBRS is actually sufficient in practice, even though it isn't sufficient architecturally.) For virtual CPUs that support IBRS, add an indirect branch prediction barrier on emulated VM-exit, to ensure that the predicted targets of indirect branches executed in L1 cannot be controlled by software that was executed in L2. Since we typically don't intercept guest writes to IA32_SPEC_CTRL, perform the IBPB at emulated VM-exit regardless of the current IA32_SPEC_CTRL.IBRS value, even though the IBPB could technically be deferred until L1 sets IA32_SPEC_CTRL.IBRS, if IA32_SPEC_CTRL.IBRS is clear at emulated VM-exit. This is CVE-2022-2196. Bug: 265479180 Fixes: 5c911beff20a ("KVM: nVMX: Skip IBPB when switching between vmcs01 and vmcs02") Cc: Sean Christopherson Signed-off-by: Jim Mattson Reviewed-by: Sean Christopherson Link: https://lore.kernel.org/r/20221019213620.1953281-3-jmattson@google.com Signed-off-by: Sean Christopherson Signed-off-by: Sasha Levin Signed-off-by: Lee Jones Change-Id: Ic3ac006d834719d41f8a84c7a557d60b82e05197 --- arch/x86/kvm/vmx/nested.c | 11 +++++++++++ arch/x86/kvm/vmx/vmx.c | 6 ++++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 498fed0dda98..bbcd635164be 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4556,6 +4556,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmx_switch_vmcs(vcpu, &vmx->vmcs01); + /* + * If IBRS is advertised to the vCPU, KVM must flush the indirect + * branch predictors when transitioning from L2 to L1, as L1 expects + * hardware (KVM in this case) to provide separate predictor modes. + * Bare metal isolates VMX root (host) from VMX non-root (guest), but + * doesn't isolate different VMCSs, i.e. in this case, doesn't provide + * separate modes for L2 vs L1. + */ + if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + indirect_branch_prediction_barrier(); + /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index af6742d11ca1..2101f849e441 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1431,8 +1431,10 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, /* * No indirect branch prediction barrier needed when switching - * the active VMCS within a guest, e.g. on nested VM-Enter. - * The L1 VMM can protect itself with retpolines, IBPB or IBRS. + * the active VMCS within a vCPU, unless IBRS is advertised to + * the vCPU. To minimize the number of IBPBs executed, KVM + * performs IBPB on nested VM-Exit (a single nested transition + * may switch the active VMCS multiple times). */ if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)) indirect_branch_prediction_barrier(); From 1d05213028b6dbdb8801e20f29b6a6f91c216033 Mon Sep 17 00:00:00 2001 From: Patrick Daly Date: Mon, 10 Oct 2022 19:25:27 -0700 Subject: [PATCH 1457/4345] ANDROID: mm/filemap: Fix missing put_page() for speculative page fault find_get_page() returns a page with increased refcount, assuming a page exists at the given index. Ensure this refcount is dropped on error. Bug: 271079833 Fixes: 59d4d125 ("BACKPORT: FROMLIST: mm: implement speculative handling in filemap_fault()") Change-Id: Idc7b9e3f11f32a02bed4c6f4e11cec9200a5c790 Signed-off-by: Patrick Daly (cherry picked from commit 6232eecfa7ca0d8d0ca088da6d0edb2c3a879ff9) Signed-off-by: Zhenhua Huang --- mm/filemap.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index aeb45f36aba1..dd1db5745741 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2736,11 +2736,14 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) if (vmf->flags & FAULT_FLAG_SPECULATIVE) { page = find_get_page(mapping, offset); - if (unlikely(!page) || unlikely(PageReadahead(page))) + if (unlikely(!page)) return VM_FAULT_RETRY; + if (unlikely(PageReadahead(page))) + goto page_put; + if (!trylock_page(page)) - return VM_FAULT_RETRY; + goto page_put; if (unlikely(compound_head(page)->mapping != mapping)) goto page_unlock; @@ -2772,6 +2775,8 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) return VM_FAULT_LOCKED; page_unlock: unlock_page(page); +page_put: + put_page(page); return VM_FAULT_RETRY; } From d4d05c6e6e719e38074ed755378b91b0925a4d2c Mon Sep 17 00:00:00 2001 From: "T.J. Mercier" Date: Thu, 16 Feb 2023 19:17:27 +0000 Subject: [PATCH 1458/4345] ANDROID: dma-buf: heaps: Don't lock unused dmabuf_page_pool mutex On backports where the dmabuf_page_pool mutex could not be completely removed because of KMI constraints, we lock the mutex to prevent anyone from acquiring it. While this is fine for regular builds, lockdep reports a deadlock because of this behavior. So here we remove the call to mutex_lock for this unused mutex. Bug: 269576779 Fixes: d55aeb40292f ("BACKPORT: ANDROID: dma-buf: heaps: replace mutex lock with spinlock") Change-Id: Ic426b6e435ec4ac7b0355c50ec9ea14d38acfa43 Signed-off-by: T.J. Mercier --- drivers/dma-buf/heaps/page_pool.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/dma-buf/heaps/page_pool.c b/drivers/dma-buf/heaps/page_pool.c index de9d72809412..9d3ddb5c381a 100644 --- a/drivers/dma-buf/heaps/page_pool.c +++ b/drivers/dma-buf/heaps/page_pool.c @@ -144,7 +144,6 @@ struct dmabuf_page_pool *dmabuf_page_pool_create(gfp_t gfp_mask, unsigned int or pool->gfp_mask = gfp_mask | __GFP_COMP; pool->order = order; mutex_init(&pool->mutex); /* No longer used! */ - mutex_lock(&pool->mutex); /* Make sure anyone who attempts to acquire this hangs */ mutex_lock(&pool_list_lock); list_add(&pool->list, &pool_list); From d01f7e1269d2651768a0bd91a88f76339a1cb427 Mon Sep 17 00:00:00 2001 From: Liujie Xie Date: Tue, 14 Feb 2023 14:42:26 +0800 Subject: [PATCH 1459/4345] ANDROID: vendor_hooks: Add hooks for mutex and rwsem optimistic spin These hooks help us do the following things: a) Record the number of mutex and rwsem optimistic spin. b) Monitor the time of mutex and rwsem optimistic spin. c) Make it possible if oems don't want mutex and rwsem to optimistic spin for a long time. Bug: 267565260 Change-Id: I2bee30fb17946be85e026213b481aeaeaee2459f Signed-off-by: Liujie Xie --- drivers/android/vendor_hooks.c | 6 ++++++ include/trace/hooks/dtask.h | 18 ++++++++++++++++++ kernel/locking/mutex.c | 10 ++++++++++ kernel/locking/rwsem.c | 13 +++++++++++++ 4 files changed, 47 insertions(+) diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index 18ef4406879f..54c46c11c09a 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -122,6 +122,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_mutex_wait_start); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_mutex_wait_finish); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rtmutex_wait_start); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rtmutex_wait_finish); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_mutex_opt_spin_start); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_mutex_opt_spin_finish); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_mutex_can_spin_on_owner); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_read_wait_start); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_read_wait_finish); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_write_wait_start); @@ -131,6 +134,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_set_reader_owned); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_mark_wake_readers); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_up_read_end); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_up_write_end); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_opt_spin_start); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_opt_spin_finish); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_can_spin_on_owner); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_sched_show_task); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_shmem_alloc_page); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_cpu_idle_enter); diff --git a/include/trace/hooks/dtask.h b/include/trace/hooks/dtask.h index 956e8421755c..081a60af0e26 100644 --- a/include/trace/hooks/dtask.h +++ b/include/trace/hooks/dtask.h @@ -32,6 +32,15 @@ DECLARE_HOOK(android_vh_mutex_wait_start, DECLARE_HOOK(android_vh_mutex_wait_finish, TP_PROTO(struct mutex *lock), TP_ARGS(lock)); +DECLARE_HOOK(android_vh_mutex_opt_spin_start, + TP_PROTO(struct mutex *lock, bool *time_out, int *cnt), + TP_ARGS(lock, time_out, cnt)); +DECLARE_HOOK(android_vh_mutex_opt_spin_finish, + TP_PROTO(struct mutex *lock, bool taken), + TP_ARGS(lock, taken)); +DECLARE_HOOK(android_vh_mutex_can_spin_on_owner, + TP_PROTO(struct mutex *lock, int *retval), + TP_ARGS(lock, retval)); DECLARE_HOOK(android_vh_rtmutex_wait_start, TP_PROTO(struct rt_mutex *lock), @@ -52,6 +61,15 @@ DECLARE_HOOK(android_vh_rwsem_write_wait_start, DECLARE_HOOK(android_vh_rwsem_write_wait_finish, TP_PROTO(struct rw_semaphore *sem), TP_ARGS(sem)); +DECLARE_HOOK(android_vh_rwsem_opt_spin_start, + TP_PROTO(struct rw_semaphore *sem, bool *time_out, int *cnt, bool chk_only), + TP_ARGS(sem, time_out, cnt, chk_only)); +DECLARE_HOOK(android_vh_rwsem_opt_spin_finish, + TP_PROTO(struct rw_semaphore *sem, bool taken, bool wlock), + TP_ARGS(sem, taken, wlock)); +DECLARE_HOOK(android_vh_rwsem_can_spin_on_owner, + TP_PROTO(struct rw_semaphore *sem, bool *ret, bool wlock), + TP_ARGS(sem, ret, wlock)); DECLARE_HOOK(android_vh_sched_show_task, TP_PROTO(struct task_struct *task), diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 93020a888b09..b9a10aacb139 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -568,9 +568,16 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner, struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter) { bool ret = true; + int cnt = 0; + bool time_out = false; rcu_read_lock(); while (__mutex_owner(lock) == owner) { + trace_android_vh_mutex_opt_spin_start(lock, &time_out, &cnt); + if (time_out) { + ret = false; + break; + } /* * Ensure we emit the owner->on_cpu, dereference _after_ * checking lock->owner still matches owner. If that fails, @@ -621,6 +628,7 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) if (owner) retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); rcu_read_unlock(); + trace_android_vh_mutex_can_spin_on_owner(lock, &retval); /* * If lock->owner is not set, the mutex has been released. Return true @@ -702,6 +710,7 @@ mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, if (!waiter) osq_unlock(&lock->osq); + trace_android_vh_mutex_opt_spin_finish(lock, true); return true; @@ -710,6 +719,7 @@ fail_unlock: osq_unlock(&lock->osq); fail: + trace_android_vh_mutex_opt_spin_finish(lock, false); /* * If we fell out of the spin path because of need_resched(), * reschedule now, before we try-lock the mutex. This avoids getting diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index d368d1a1af49..057c9e99251a 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -673,6 +673,7 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem, ret = false; rcu_read_unlock(); preempt_enable(); + trace_android_vh_rwsem_can_spin_on_owner(sem, &ret, nonspinnable == RWSEM_WR_NONSPINNABLE); lockevent_cond_inc(rwsem_opt_fail, !ret); return ret; @@ -715,6 +716,8 @@ rwsem_spin_on_owner(struct rw_semaphore *sem, unsigned long nonspinnable) struct task_struct *new, *owner; unsigned long flags, new_flags; enum owner_state state; + int cnt = 0; + bool time_out = false; owner = rwsem_owner_flags(sem, &flags); state = rwsem_owner_state(owner, flags, nonspinnable); @@ -723,6 +726,9 @@ rwsem_spin_on_owner(struct rw_semaphore *sem, unsigned long nonspinnable) rcu_read_lock(); for (;;) { + trace_android_vh_rwsem_opt_spin_start(sem, &time_out, &cnt, true); + if (time_out) + break; /* * When a waiting writer set the handoff flag, it may spin * on the owner as well. Once that writer acquires the lock, @@ -786,6 +792,8 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock) int prev_owner_state = OWNER_NULL; int loop = 0; u64 rspin_threshold = 0; + int cnt = 0; + bool time_out = false; unsigned long nonspinnable = wlock ? RWSEM_WR_NONSPINNABLE : RWSEM_RD_NONSPINNABLE; @@ -804,6 +812,10 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock) for (;;) { enum owner_state owner_state; + trace_android_vh_rwsem_opt_spin_start(sem, &time_out, &cnt, false); + if (time_out) + break; + owner_state = rwsem_spin_on_owner(sem, nonspinnable); if (!(owner_state & OWNER_SPINNABLE)) break; @@ -898,6 +910,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock) cpu_relax(); } osq_unlock(&sem->osq); + trace_android_vh_rwsem_opt_spin_finish(sem, taken, wlock); done: preempt_enable(); lockevent_cond_inc(rwsem_opt_fail, !taken); From 52cc662810cc71208d3577fe92f14df4dd3f4376 Mon Sep 17 00:00:00 2001 From: Liujie Xie Date: Wed, 22 Feb 2023 19:24:01 +0800 Subject: [PATCH 1460/4345] ANDROID: ABI: Update oplus symbol list Leaf changes summary: 12 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 6 Added functions Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 6 Added variables 6 Added functions: [A] 'function int __traceiter_android_vh_mutex_can_spin_on_owner(void*, mutex*, int*)' [A] 'function int __traceiter_android_vh_mutex_opt_spin_finish(void*, mutex*, bool)' [A] 'function int __traceiter_android_vh_mutex_opt_spin_start(void*, mutex*, bool*, int*)' [A] 'function int __traceiter_android_vh_rwsem_can_spin_on_owner(void*, rw_semaphore*, bool*, bool)' [A] 'function int __traceiter_android_vh_rwsem_opt_spin_finish(void*, rw_semaphore*, bool, bool)' [A] 'function int __traceiter_android_vh_rwsem_opt_spin_start(void*, rw_semaphore*, bool*, int*, bool)' 6 Added variables: [A] 'tracepoint __tracepoint_android_vh_mutex_can_spin_on_owner' [A] 'tracepoint __tracepoint_android_vh_mutex_opt_spin_finish' [A] 'tracepoint __tracepoint_android_vh_mutex_opt_spin_start' [A] 'tracepoint __tracepoint_android_vh_rwsem_can_spin_on_owner' [A] 'tracepoint __tracepoint_android_vh_rwsem_opt_spin_finish' [A] 'tracepoint __tracepoint_android_vh_rwsem_opt_spin_start' Bug: 267565260 Change-Id: If7f68d800f726ceecfec1f45376d37f9d1772014 Signed-off-by: Liujie Xie --- android/abi_gki_aarch64.xml | 306 +++++++++++++++++++++++++--------- android/abi_gki_aarch64_oplus | 12 ++ 2 files changed, 240 insertions(+), 78 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 7179cf786230..d44112f52bef 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -549,6 +549,9 @@ + + + @@ -578,8 +581,11 @@ + + + @@ -6560,6 +6566,9 @@ + + + @@ -6594,8 +6603,11 @@ + + + @@ -15311,6 +15323,89 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -68505,7 +68600,14 @@ - + + + + + + + + @@ -93782,6 +93884,7 @@ + @@ -116345,9 +116448,9 @@ - + - + @@ -118848,12 +118951,12 @@ - - - - - - + + + + + + @@ -119711,15 +119814,34 @@ - - - + + + + - - - - + + + + + + + + + + + + + + + + + + + + + + @@ -119831,28 +119953,28 @@ - - - - + + + + - - - - + + + + - - - - + + + + - - - - + + + + @@ -119886,6 +120008,13 @@ + + + + + + + @@ -119897,6 +120026,21 @@ + + + + + + + + + + + + + + + @@ -120912,7 +121056,7 @@ - + @@ -121050,8 +121194,11 @@ - - + + + + + @@ -121073,21 +121220,24 @@ - - - - + + + + - - + + + - - + + + + @@ -121095,13 +121245,13 @@ - - + + - + @@ -127659,16 +127809,16 @@ - - + + - - + + - - + + @@ -127680,16 +127830,16 @@ - - + + - - + + - - + + @@ -136538,24 +136688,24 @@ - - + + - - + + - - + + - - + + @@ -147119,12 +147269,12 @@ - - + + - - + + @@ -149757,18 +149907,18 @@ - - - + + + - - - + + + - - + + diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index d1c65a2281cb..eb8aba0710d9 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -2841,6 +2841,9 @@ __traceiter_android_vh_meminfo_proc_show __traceiter_android_vh_alloc_pages_slowpath_begin __traceiter_android_vh_alloc_pages_slowpath_end + __traceiter_android_vh_mutex_can_spin_on_owner + __traceiter_android_vh_mutex_opt_spin_finish + __traceiter_android_vh_mutex_opt_spin_start __traceiter_android_vh_mutex_unlock_slowpath __traceiter_android_vh_mutex_unlock_slowpath_end __traceiter_android_vh_mutex_wait_finish @@ -2868,8 +2871,11 @@ __traceiter_android_vh_record_rwsem_lock_starttime __traceiter_android_vh_record_pcpu_rwsem_starttime __traceiter_android_vh_rmqueue + __traceiter_android_vh_rwsem_can_spin_on_owner __traceiter_android_vh_rwsem_init __traceiter_android_vh_rwsem_mark_wake_readers + __traceiter_android_vh_rwsem_opt_spin_finish + __traceiter_android_vh_rwsem_opt_spin_start __traceiter_android_vh_rwsem_set_owner __traceiter_android_vh_rwsem_set_reader_owned __traceiter_android_vh_rwsem_up_read_end @@ -3085,6 +3091,9 @@ __tracepoint_android_vh_meminfo_proc_show __tracepoint_android_vh_alloc_pages_slowpath_begin __tracepoint_android_vh_alloc_pages_slowpath_end + __tracepoint_android_vh_mutex_can_spin_on_owner + __tracepoint_android_vh_mutex_opt_spin_finish + __tracepoint_android_vh_mutex_opt_spin_start __tracepoint_android_vh_mutex_unlock_slowpath __tracepoint_android_vh_mutex_unlock_slowpath_end __tracepoint_android_vh_mutex_wait_finish @@ -3112,8 +3121,11 @@ __tracepoint_android_vh_record_rwsem_lock_starttime __tracepoint_android_vh_record_pcpu_rwsem_starttime __tracepoint_android_vh_rmqueue + __tracepoint_android_vh_rwsem_can_spin_on_owner __tracepoint_android_vh_rwsem_init __tracepoint_android_vh_rwsem_mark_wake_readers + __tracepoint_android_vh_rwsem_opt_spin_finish + __tracepoint_android_vh_rwsem_opt_spin_start __tracepoint_android_vh_rwsem_set_owner __tracepoint_android_vh_rwsem_set_reader_owned __tracepoint_android_vh_rwsem_up_read_end From 887975834dea744dde636dd73bbd1e597f211d7d Mon Sep 17 00:00:00 2001 From: Benedict Wong Date: Thu, 5 Jan 2023 21:28:12 +0000 Subject: [PATCH 1461/4345] Fix XFRM-I support for nested ESP tunnels [ Upstream commit b0355dbbf13c0052931dd14c38c789efed64d3de ] This change adds support for nested IPsec tunnels by ensuring that XFRM-I verifies existing policies before decapsulating a subsequent policies. Addtionally, this clears the secpath entries after policies are verified, ensuring that previous tunnels with no-longer-valid do not pollute subsequent policy checks. This is necessary especially for nested tunnels, as the IP addresses, protocol and ports may all change, thus not matching the previous policies. In order to ensure that packets match the relevant inbound templates, the xfrm_policy_check should be done before handing off to the inner XFRM protocol to decrypt and decapsulate. Notably, raw ESP/AH packets did not perform policy checks inherently, whereas all other encapsulated packets (UDP, TCP encapsulated) do policy checks after calling xfrm_input handling in the respective encapsulation layer. Test: Verified with additional Android Kernel Unit tests Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_interface.c | 54 ++++++++++++++++++++++++++++++++++++--- net/xfrm/xfrm_policy.c | 3 +++ 2 files changed, 53 insertions(+), 4 deletions(-) diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index da518b4ca84c..e4f21a692415 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -207,6 +207,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } +static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -780,8 +826,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -831,8 +877,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 0d12bdf59d4c..d15aa62887de 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3710,6 +3710,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } + if (if_id) + secpath_reset(skb); + xfrm_pols_put(pols, npols); return 1; } From 1f3a209b2f4ec238d4b0c77b558527e7dab52aab Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 25 Nov 2022 15:41:34 +0100 Subject: [PATCH 1462/4345] arm64: dts: rockchip: drop unused LED mode property from rk3328-roc-cc [ Upstream commit 1692bffec674551163a7a4be32f59fdde04ecd27 ] GPIO LEDs do not have a 'mode' property: rockchip/rk3328-roc-pc.dtb: leds: led-0: Unevaluated properties are not allowed ('mode' was unexpected) Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20221125144135.477144-1-krzysztof.kozlowski@linaro.org Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts index daa9a0c601a9..22ab5e1d7319 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts @@ -91,7 +91,6 @@ linux,default-trigger = "heartbeat"; gpios = <&rk805 1 GPIO_ACTIVE_LOW>; default-state = "on"; - mode = <0x23>; }; user_led: led-1 { @@ -99,7 +98,6 @@ linux,default-trigger = "mmc1"; gpios = <&rk805 0 GPIO_ACTIVE_LOW>; default-state = "off"; - mode = <0x05>; }; }; }; From abbf52efadebc1aba898d4493ffed22de5dc29f6 Mon Sep 17 00:00:00 2001 From: Johan Jonker Date: Wed, 28 Dec 2022 21:17:32 +0100 Subject: [PATCH 1463/4345] ARM: dts: rockchip: add power-domains property to dp node on rk3288 [ Upstream commit 80422339a75088322b4d3884bd12fa0fe5d11050 ] The clocks in the Rockchip rk3288 DisplayPort node are included in the power-domain@RK3288_PD_VIO logic, but the power-domains property in the dp node is missing, so fix it. Signed-off-by: Johan Jonker Link: https://lore.kernel.org/r/dab85bfb-9f55-86a1-5cd5-7388c43e0ec5@gmail.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm/boot/dts/rk3288.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index 9051fb4a267d..aab28161b9ae 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -1203,6 +1203,7 @@ clock-names = "dp", "pclk"; phys = <&edp_phy>; phy-names = "dp"; + power-domains = <&power RK3288_PD_VIO>; resets = <&cru SRST_EDP>; reset-names = "dp"; rockchip,grf = <&grf>; From 8e833fe47f45c4e43f40f8bb6cf7088879dd3139 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 25 Jan 2023 11:34:18 -0700 Subject: [PATCH 1464/4345] ACPI: NFIT: fix a potential deadlock during NFIT teardown [ Upstream commit fb6df4366f86dd252bfa3049edffa52d17e7b895 ] Lockdep reports that acpi_nfit_shutdown() may deadlock against an opportune acpi_nfit_scrub(). acpi_nfit_scrub () is run from inside a 'work' and therefore has already acquired workqueue-internal locks. It also acquiires acpi_desc->init_mutex. acpi_nfit_shutdown() first acquires init_mutex, and was subsequently attempting to cancel any pending workqueue items. This reversed locking order causes a potential deadlock: ====================================================== WARNING: possible circular locking dependency detected 6.2.0-rc3 #116 Tainted: G O N ------------------------------------------------------ libndctl/1958 is trying to acquire lock: ffff888129b461c0 ((work_completion)(&(&acpi_desc->dwork)->work)){+.+.}-{0:0}, at: __flush_work+0x43/0x450 but task is already holding lock: ffff888129b460e8 (&acpi_desc->init_mutex){+.+.}-{3:3}, at: acpi_nfit_shutdown+0x87/0xd0 [nfit] which lock already depends on the new lock. ... Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&acpi_desc->init_mutex); lock((work_completion)(&(&acpi_desc->dwork)->work)); lock(&acpi_desc->init_mutex); lock((work_completion)(&(&acpi_desc->dwork)->work)); *** DEADLOCK *** Since the workqueue manipulation is protected by its own internal locking, the cancellation of pending work doesn't need to be done under acpi_desc->init_mutex. Move cancel_delayed_work_sync() outside the init_mutex to fix the deadlock. Any work that starts after acpi_nfit_shutdown() drops the lock will see ARS_CANCEL, and the cancel_delayed_work_sync() will safely flush it out. Reported-by: Dan Williams Signed-off-by: Vishal Verma Link: https://lore.kernel.org/r/20230112-acpi_nfit_lockdep-v1-1-660be4dd10be@intel.com Signed-off-by: Dan Williams Signed-off-by: Sasha Levin --- drivers/acpi/nfit/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 99e23a5df026..2306abb09f7f 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3687,8 +3687,8 @@ void acpi_nfit_shutdown(void *data) mutex_lock(&acpi_desc->init_mutex); set_bit(ARS_CANCEL, &acpi_desc->scrub_flags); - cancel_delayed_work_sync(&acpi_desc->dwork); mutex_unlock(&acpi_desc->init_mutex); + cancel_delayed_work_sync(&acpi_desc->dwork); /* * Bounce the nvdimm bus lock to make sure any in-flight From 6195cea4c738146f6665f71944325766daef1a5f Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 24 Jan 2023 20:32:10 +0100 Subject: [PATCH 1465/4345] btrfs: send: limit number of clones and allocated memory size [ Upstream commit 33e17b3f5ab74af12aca58c515bc8424ff69a343 ] The arg->clone_sources_count is u64 and can trigger a warning when a huge value is passed from user space and a huge array is allocated. Limit the allocated memory to 8MiB (can be increased if needed), which in turn limits the number of clone sources to 8M / sizeof(struct clone_root) = 8M / 40 = 209715. Real world number of clones is from tens to hundreds, so this is future proof. Reported-by: syzbot+4376a9a073770c173269@syzkaller.appspotmail.com Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/send.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4a6ba0997e39..b081b61e97c8 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -7276,10 +7276,10 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) /* * Check that we don't overflow at later allocations, we request * clone_sources_count + 1 items, and compare to unsigned long inside - * access_ok. + * access_ok. Also set an upper limit for allocation size so this can't + * easily exhaust memory. Max number of clone sources is about 200K. */ - if (arg->clone_sources_count > - ULONG_MAX / sizeof(struct clone_root) - 1) { + if (arg->clone_sources_count > SZ_8M / sizeof(struct clone_root)) { ret = -EINVAL; goto out; } From 065f6a66339226fe33d18998afa8533076751444 Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Mon, 9 Jan 2023 14:04:08 -0500 Subject: [PATCH 1466/4345] IB/hfi1: Assign npages earlier [ Upstream commit f9c47b2caa7ffc903ec950b454b59c209afe3182 ] Improve code clarity and enable earlier use of tidbuf->npages by moving its assignment to structure creation time. Signed-off-by: Dean Luick Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/167329104884.1472990.4639750192433251493.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/user_exp_rcv.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index 897923981855..0e0be6c62e3d 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -202,16 +202,11 @@ static void unpin_rcv_pages(struct hfi1_filedata *fd, static int pin_rcv_pages(struct hfi1_filedata *fd, struct tid_user_buf *tidbuf) { int pinned; - unsigned int npages; + unsigned int npages = tidbuf->npages; unsigned long vaddr = tidbuf->vaddr; struct page **pages = NULL; struct hfi1_devdata *dd = fd->uctxt->dd; - /* Get the number of pages the user buffer spans */ - npages = num_user_pages(vaddr, tidbuf->length); - if (!npages) - return -EINVAL; - if (npages > fd->uctxt->expected_count) { dd_dev_err(dd, "Expected buffer too big\n"); return -EINVAL; @@ -238,7 +233,6 @@ static int pin_rcv_pages(struct hfi1_filedata *fd, struct tid_user_buf *tidbuf) return pinned; } tidbuf->pages = pages; - tidbuf->npages = npages; fd->tid_n_pinned += pinned; return pinned; } @@ -316,6 +310,7 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, mutex_init(&tidbuf->cover_mutex); tidbuf->vaddr = tinfo->vaddr; tidbuf->length = tinfo->length; + tidbuf->npages = num_user_pages(tidbuf->vaddr, tidbuf->length); tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets), GFP_KERNEL); if (!tidbuf->psets) { From 2fd5059f4fdf4df813414fe85f732187554528a3 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 2 Feb 2023 17:25:51 +0200 Subject: [PATCH 1467/4345] neigh: make sure used and confirmed times are valid [ Upstream commit c1d2ecdf5e38e3489ce8328238b558b3b2866fe1 ] Entries can linger in cache without timer for days, thanks to the gc_thresh1 limit. As result, without traffic, the confirmed time can be outdated and to appear to be in the future. Later, on traffic, NUD_STALE entries can switch to NUD_DELAY and start the timer which can see the invalid confirmed time and wrongly switch to NUD_REACHABLE state instead of NUD_PROBE. As result, timer is set many days in the future. This is more visible on 32-bit platforms, with higher HZ value. Why this is a problem? While we expect unused entries to expire, such entries stay in REACHABLE state for too long, locked in cache. They are not expired normally, only when cache is full. Problem and the wrong state change reported by Zhang Changzhong: 172.16.1.18 dev bond0 lladdr 0a:0e:0f:01:12:01 ref 1 used 350521/15994171/350520 probes 4 REACHABLE 350520 seconds have elapsed since this entry was last updated, but it is still in the REACHABLE state (base_reachable_time_ms is 30000), preventing lladdr from being updated through probe. Fix it by ensuring timer is started with valid used/confirmed times. Considering the valid time range is LONG_MAX jiffies, we try not to go too much in the past while we are in DELAY/PROBE state. There are also places that need used/updated times to be validated while timer is not running. Reported-by: Zhang Changzhong Signed-off-by: Julian Anastasov Tested-by: Zhang Changzhong Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/neighbour.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f6f580e9d282..82ccc3eebe71 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -242,7 +242,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || - time_after(tref, n->updated)) + !time_in_range(n->updated, tref, jiffies)) remove = true; write_unlock(&n->lock); @@ -262,7 +262,17 @@ static int neigh_forced_gc(struct neigh_table *tbl) static void neigh_add_timer(struct neighbour *n, unsigned long when) { + /* Use safe distance from the jiffies - LONG_MAX point while timer + * is running in DELAY/PROBE state but still show to user space + * large times in the past. + */ + unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ); + neigh_hold(n); + if (!time_in_range(n->confirmed, mint, jiffies)) + n->confirmed = mint; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; if (unlikely(mod_timer(&n->timer, when))) { printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state); @@ -948,12 +958,14 @@ static void neigh_periodic_work(struct work_struct *work) goto next_elt; } - if (time_before(n->used, n->confirmed)) + if (time_before(n->used, n->confirmed) && + time_is_before_eq_jiffies(n->confirmed)) n->used = n->confirmed; if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { + !time_in_range_open(jiffies, n->used, + n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; neigh_mark_dead(n); write_unlock(&n->lock); From 75fbe1e43505f3474d6f590314671e0e53a2afa7 Mon Sep 17 00:00:00 2001 From: Xin Zhao Date: Mon, 30 Jan 2023 21:29:47 +0000 Subject: [PATCH 1468/4345] HID: core: Fix deadloop in hid_apply_multiplier. [ Upstream commit ea427a222d8bdf2bc1a8a6da3ebe247f7dced70c ] The initial value of hid->collection[].parent_idx if 0. When Report descriptor doesn't contain "HID Collection", the value remains as 0. In the meanwhile, when the Report descriptor fullfill all following conditions, it will trigger hid_apply_multiplier function call. 1. Usage page is Generic Desktop Ctrls (0x01) 2. Usage is RESOLUTION_MULTIPLIER (0x48) 3. Contain any FEATURE items The while loop in hid_apply_multiplier will search the top-most collection by searching parent_idx == -1. Because all parent_idx is 0. The loop will run forever. There is a Report Descriptor triggerring the deadloop 0x05, 0x01, // Usage Page (Generic Desktop Ctrls) 0x09, 0x48, // Usage (0x48) 0x95, 0x01, // Report Count (1) 0x75, 0x08, // Report Size (8) 0xB1, 0x01, // Feature Signed-off-by: Xin Zhao Link: https://lore.kernel.org/r/20230130212947.1315941-1-xnzhao@google.com Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index baadead947c8..5f9ec1d1464a 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1197,6 +1197,7 @@ int hid_open_report(struct hid_device *device) __u8 *end; __u8 *next; int ret; + int i; static int (*dispatch_type[])(struct hid_parser *parser, struct hid_item *item) = { hid_parser_main, @@ -1247,6 +1248,8 @@ int hid_open_report(struct hid_device *device) goto err; } device->collection_size = HID_DEFAULT_NUM_COLLECTIONS; + for (i = 0; i < HID_DEFAULT_NUM_COLLECTIONS; i++) + device->collection[i].parent_idx = -1; ret = -EINVAL; while ((next = fetch_item(start, end, &item)) != NULL) { From a2957adbf3f5450f7425c545863da4a3287e06a1 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 16 Feb 2023 16:41:48 -0800 Subject: [PATCH 1469/4345] bpf: bpf_fib_lookup should not return neigh in NUD_FAILED state commit 1fe4850b34ab512ff911e2c035c75fb6438f7307 upstream. The bpf_fib_lookup() helper does not only look up the fib (ie. route) but it also looks up the neigh. Before returning the neigh, the helper does not check for NUD_VALID. When a neigh state (neigh->nud_state) is in NUD_FAILED, its dmac (neigh->ha) could be all zeros. The helper still returns SUCCESS instead of NO_NEIGH in this case. Because of the SUCCESS return value, the bpf prog directly uses the returned dmac and ends up filling all zero in the eth header. This patch checks for NUD_VALID and returns NO_NEIGH if the neigh is not valid. Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230217004150.2980689-3-martin.lau@linux.dev Signed-off-by: Greg Kroah-Hartman --- net/core/filter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index a5df0cf46bbf..b9c954182b37 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5401,7 +5401,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); } - if (!neigh) + if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; return bpf_fib_set_fwd_params(params, neigh, dev); @@ -5514,7 +5514,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, * not needed here. */ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); - if (!neigh) + if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; return bpf_fib_set_fwd_params(params, neigh, dev); From 3e4bbd1f38a8d35bd2d3aaffdb5f6ada546b669a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 9 Feb 2023 16:22:02 -0800 Subject: [PATCH 1470/4345] net: Remove WARN_ON_ONCE(sk->sk_forward_alloc) from sk_stream_kill_queues(). commit 62ec33b44e0f7168ff2886520fec6fb62d03b5a3 upstream. Christoph Paasch reported that commit b5fc29233d28 ("inet6: Remove inet6_destroy_sock() in sk->sk_prot->destroy().") started triggering WARN_ON_ONCE(sk->sk_forward_alloc) in sk_stream_kill_queues(). [0 - 2] Also, we can reproduce it by a program in [3]. In the commit, we delay freeing ipv6_pinfo.pktoptions from sk->destroy() to sk->sk_destruct(), so sk->sk_forward_alloc is no longer zero in inet_csk_destroy_sock(). The same check has been in inet_sock_destruct() from at least v2.6, we can just remove the WARN_ON_ONCE(). However, among the users of sk_stream_kill_queues(), only CAIF is not calling inet_sock_destruct(). Thus, we add the same WARN_ON_ONCE() to caif_sock_destructor(). [0]: https://lore.kernel.org/netdev/39725AB4-88F1-41B3-B07F-949C5CAEFF4F@icloud.com/ [1]: https://github.com/multipath-tcp/mptcp_net-next/issues/341 [2]: WARNING: CPU: 0 PID: 3232 at net/core/stream.c:212 sk_stream_kill_queues+0x2f9/0x3e0 Modules linked in: CPU: 0 PID: 3232 Comm: syz-executor.0 Not tainted 6.2.0-rc5ab24eb4698afbe147b424149c529e2a43ec24eb5 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:sk_stream_kill_queues+0x2f9/0x3e0 Code: 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e ec 00 00 00 8b ab 08 01 00 00 e9 60 ff ff ff e8 d0 5f b6 fe 0f 0b eb 97 e8 c7 5f b6 fe <0f> 0b eb a0 e8 be 5f b6 fe 0f 0b e9 6a fe ff ff e8 02 07 e3 fe e9 RSP: 0018:ffff88810570fc68 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: ffff888101f38f40 RSI: ffffffff8285e529 RDI: 0000000000000005 RBP: 0000000000000ce0 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000ce0 R11: 0000000000000001 R12: ffff8881009e9488 R13: ffffffff84af2cc0 R14: 0000000000000000 R15: ffff8881009e9458 FS: 00007f7fdfbd5800(0000) GS:ffff88811b600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b32923000 CR3: 00000001062fc006 CR4: 0000000000170ef0 Call Trace: inet_csk_destroy_sock+0x1a1/0x320 __tcp_close+0xab6/0xe90 tcp_close+0x30/0xc0 inet_release+0xe9/0x1f0 inet6_release+0x4c/0x70 __sock_release+0xd2/0x280 sock_close+0x15/0x20 __fput+0x252/0xa20 task_work_run+0x169/0x250 exit_to_user_mode_prepare+0x113/0x120 syscall_exit_to_user_mode+0x1d/0x40 do_syscall_64+0x48/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f7fdf7ae28d Code: c1 20 00 00 75 10 b8 03 00 00 00 0f 05 48 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ee fb ff ff 48 89 04 24 b8 03 00 00 00 0f 05 <48> 8b 3c 24 48 89 c2 e8 37 fc ff ff 48 89 d0 48 83 c4 08 48 3d 01 RSP: 002b:00000000007dfbb0 EFLAGS: 00000293 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 0000000000000004 RCX: 00007f7fdf7ae28d RDX: 0000000000000000 RSI: ffffffffffffffff RDI: 0000000000000003 RBP: 0000000000000000 R08: 000000007f338e0f R09: 0000000000000e0f R10: 000000007f338e13 R11: 0000000000000293 R12: 00007f7fdefff000 R13: 00007f7fdefffcd8 R14: 00007f7fdefffce0 R15: 00007f7fdefffcd8 [3]: https://lore.kernel.org/netdev/20230208004245.83497-1-kuniyu@amazon.com/ Fixes: b5fc29233d28 ("inet6: Remove inet6_destroy_sock() in sk->sk_prot->destroy().") Reported-by: syzbot Reported-by: Christoph Paasch Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/caif/caif_socket.c | 1 + net/core/stream.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 9d26c5e9da05..d35ea927ca8a 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -1020,6 +1020,7 @@ static void caif_sock_destructor(struct sock *sk) return; } sk_stream_kill_queues(&cf_sk->sk); + WARN_ON(sk->sk_forward_alloc); caif_free_client(&cf_sk->layer); } diff --git a/net/core/stream.c b/net/core/stream.c index d7c5413d16d5..cd60746877b1 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -209,7 +209,6 @@ void sk_stream_kill_queues(struct sock *sk) sk_mem_reclaim(sk); WARN_ON(sk->sk_wmem_queued); - WARN_ON(sk->sk_forward_alloc); /* It is _impossible_ for the backlog to contain anything * when we get here. All user references to this socket From 80653a6e6e287eb982be9aa9f60f94382b6767b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 20 Feb 2023 06:46:12 +0000 Subject: [PATCH 1471/4345] vc_screen: don't clobber return value in vcs_read MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ae3419fbac845b4d3f3a9fae4cc80c68d82cdf6e upstream. Commit 226fae124b2d ("vc_screen: move load of struct vc_data pointer in vcs_read() to avoid UAF") moved the call to vcs_vc() into the loop. While doing this it also moved the unconditional assignment of ret = -ENXIO; This unconditional assignment was valid outside the loop but within it it clobbers the actual value of ret. To avoid this only assign "ret = -ENXIO" when actually needed. [ Also, the 'goto unlock_out" needs to be just a "break", so that it does the right thing when it exits on later iterations when partial success has happened - Linus ] Reported-by: Storm Dragon Link: https://lore.kernel.org/lkml/Y%2FKS6vdql2pIsCiI@hotmail.com/ Fixes: 226fae124b2d ("vc_screen: move load of struct vc_data pointer in vcs_read() to avoid UAF") Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/lkml/64981d94-d00c-4b31-9063-43ad0a384bde@t-8ch.de/ Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vc_screen.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index f566eb1839dc..71e091f879f0 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -403,10 +403,11 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) unsigned int this_round, skip = 0; int size; - ret = -ENXIO; vc = vcs_vc(inode, &viewed); - if (!vc) - goto unlock_out; + if (!vc) { + ret = -ENXIO; + break; + } /* Check whether we are above size each round, * as copy_to_user at the end of this loop From 1c44109c30946e4e8dfad785bb006fafad9b3caf Mon Sep 17 00:00:00 2001 From: David Sloan Date: Thu, 11 Aug 2022 11:14:13 -0600 Subject: [PATCH 1472/4345] md: Flush workqueue md_rdev_misc_wq in md_alloc() commit 5e8daf906f890560df430d30617c692a794acb73 upstream. A race condition still exists when removing and re-creating md devices in test cases. However, it is only seen on some setups. The race condition was tracked down to a reference still being held to the kobject by the rdev in the md_rdev_misc_wq which will be released in rdev_delayed_delete(). md_alloc() waits for previous deletions by waiting on the md_misc_wq, but the md_rdev_misc_wq may still be holding a reference to a recently removed device. To fix this, also flush the md_rdev_misc_wq in md_alloc(). Signed-off-by: David Sloan [logang@deltatee.com: rewrote commit message] Signed-off-by: Logan Gunthorpe Signed-off-by: Song Liu Signed-off-by: Hou Tao Signed-off-by: Greg Kroah-Hartman --- drivers/md/md.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index 3038e7ecb7e1..c0b34637bd66 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5683,6 +5683,7 @@ static int md_alloc(dev_t dev, char *name) * completely removed (mddev_delayed_delete). */ flush_workqueue(md_misc_wq); + flush_workqueue(md_rdev_misc_wq); mutex_lock(&disks_mutex); error = -EEXIST; From 65c07e15f2ce7f9e2cf68ea02bd2631cca53594e Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 17 May 2022 02:46:46 +0300 Subject: [PATCH 1473/4345] scripts/tags.sh: Invoke 'realpath' via 'xargs' commit 7394d2ebb651a9f62e08c6ab864aac015d27c64d upstream. When COMPILED_SOURCE is set, running make ARCH=x86_64 COMPILED_SOURCE=1 cscope tags could throw the following errors: scripts/tags.sh: line 98: /usr/bin/realpath: Argument list too long cscope: no source files found scripts/tags.sh: line 98: /usr/bin/realpath: Argument list too long ctags: No files specified. Try "ctags --help". This is most likely to happen when the kernel is configured to build a large number of modules, which has the consequence of passing too many arguments when calling 'realpath' in 'all_compiled_sources()'. Let's improve this by invoking 'realpath' through 'xargs', which takes care of properly limiting the argument list. Signed-off-by: Cristian Ciocaltea Link: https://lore.kernel.org/r/20220516234646.531208-1-cristian.ciocaltea@collabora.com Cc: Carlos Llamas Signed-off-by: Greg Kroah-Hartman --- scripts/tags.sh | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/scripts/tags.sh b/scripts/tags.sh index fd96734deff1..c15f3b4ea2a4 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -95,10 +95,13 @@ all_sources() all_compiled_sources() { - realpath -es $([ -z "$KBUILD_ABS_SRCTREE" ] && echo --relative-to=.) \ - include/generated/autoconf.h $(find $ignore -name "*.cmd" -exec \ - grep -Poh '(?(?=^source_.* \K).*|(?=^ \K\S).*(?= \\))' {} \+ | - awk '!a[$0]++') | sort -u + { + echo include/generated/autoconf.h + find $ignore -name "*.cmd" -exec \ + grep -Poh '(?(?=^source_.* \K).*|(?=^ \K\S).*(?= \\))' {} \+ | + awk '!a[$0]++' + } | xargs realpath -es $([ -z "$KBUILD_ABS_SRCTREE" ] && echo --relative-to=.) | + sort -u } all_target_sources() From a401ef0557da5b7f5b9c4baf0d861b33883d9228 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Wed, 15 Feb 2023 18:38:50 +0000 Subject: [PATCH 1474/4345] scripts/tags.sh: fix incompatibility with PCRE2 commit 6ec363fc6142226b9ab5a6528f65333d729d2b6b upstream. Starting with release 10.38 PCRE2 drops default support for using \K in lookaround patterns as described in [1]. Unfortunately, scripts/tags.sh relies on such functionality to collect all_compiled_soures() leading to the following error: $ make COMPILED_SOURCE=1 tags GEN tags grep: \K is not allowed in lookarounds (but see PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK) The usage of \K for this pattern was introduced in commit 4f491bb6ea2a ("scripts/tags.sh: collect compiled source precisely") which speeds up the generation of tags significantly. In order to fix this issue without compromising the performance we can switch over to an equivalent sed expression. The same matching pattern is preserved here except \K is replaced with a backreference \1. [1] https://www.pcre.org/current/doc/html/pcre2syntax.html#SEC11 Cc: Greg Kroah-Hartman Cc: Cristian Ciocaltea Cc: Masahiro Yamada Cc: Jialu Xu Cc: Vipin Sharma Cc: stable@vger.kernel.org Fixes: 4f491bb6ea2a ("scripts/tags.sh: collect compiled source precisely") Signed-off-by: Carlos Llamas Link: https://lore.kernel.org/r/20230215183850.3353198-1-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- scripts/tags.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/tags.sh b/scripts/tags.sh index c15f3b4ea2a4..b82aebb0c995 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -98,7 +98,7 @@ all_compiled_sources() { echo include/generated/autoconf.h find $ignore -name "*.cmd" -exec \ - grep -Poh '(?(?=^source_.* \K).*|(?=^ \K\S).*(?= \\))' {} \+ | + sed -n -E 's/^source_.* (.*)/\1/p; s/^ (\S.*) \\/\1/p' {} \+ | awk '!a[$0]++' } | xargs realpath -es $([ -z "$KBUILD_ABS_SRCTREE" ] && echo --relative-to=.) | sort -u From 0a4181b23acf53e9c95b351df6a7891116b98f9b Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Thu, 2 Jun 2022 14:42:22 +0400 Subject: [PATCH 1475/4345] drm/virtio: Fix NULL vs IS_ERR checking in virtio_gpu_object_shmem_init commit c24968734abfed81c8f93dc5f44a7b7a9aecadfa upstream. Since drm_prime_pages_to_sg() function return error pointers. The drm_gem_shmem_get_sg_table() function returns error pointers too. Using IS_ERR() to check the return value to fix this. Fixes: 2f2aa13724d5 ("drm/virtio: move virtio_gpu_mem_entry initialization to new function") Signed-off-by: Miaoqian Lin Link: http://patchwork.freedesktop.org/patch/msgid/20220602104223.54527-1-linmq006@gmail.com Signed-off-by: Gerd Hoffmann Signed-off-by: Greg Kroah-Hartman Signed-off-by: Ovidiu Panait --- drivers/gpu/drm/virtio/virtgpu_object.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 0c98978e2e55..d4fab3361d2c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -157,9 +157,9 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, * since virtio_gpu doesn't support dma-buf import from other devices. */ shmem->pages = drm_gem_shmem_get_sg_table(&bo->base.base); - if (!shmem->pages) { + if (IS_ERR(shmem->pages)) { drm_gem_shmem_unpin(&bo->base.base); - return -EINVAL; + return PTR_ERR(shmem->pages); } if (use_dma_api) { From 87c647def389354c95263d6635c62ca0de7d12ca Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 30 Jun 2022 23:07:18 +0300 Subject: [PATCH 1476/4345] drm/virtio: Correct drm_gem_shmem_get_sg_table() error handling commit 64b88afbd92fbf434759d1896a7cf705e1c00e79 upstream. Previous commit fixed checking of the ERR_PTR value returned by drm_gem_shmem_get_sg_table(), but it missed to zero out the shmem->pages, which will crash virtio_gpu_cleanup_object(). Add the missing zeroing of the shmem->pages. Fixes: c24968734abf ("drm/virtio: Fix NULL vs IS_ERR checking in virtio_gpu_object_shmem_init") Reviewed-by: Emil Velikov Signed-off-by: Dmitry Osipenko Link: http://patchwork.freedesktop.org/patch/msgid/20220630200726.1884320-2-dmitry.osipenko@collabora.com Signed-off-by: Gerd Hoffmann Signed-off-by: Greg Kroah-Hartman Signed-off-by: Ovidiu Panait --- drivers/gpu/drm/virtio/virtgpu_object.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index d4fab3361d2c..168148686001 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -159,6 +159,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, shmem->pages = drm_gem_shmem_get_sg_table(&bo->base.base); if (IS_ERR(shmem->pages)) { drm_gem_shmem_unpin(&bo->base.base); + shmem->pages = NULL; return PTR_ERR(shmem->pages); } From cebcd4300af9074e0e831090ca6c1b3154ef942a Mon Sep 17 00:00:00 2001 From: Florian Zumbiehl Date: Mon, 6 Feb 2023 02:04:28 +0100 Subject: [PATCH 1477/4345] USB: serial: option: add support for VW/Skoda "Carstick LTE" commit 617c331d91077f896111044628c096802551dc66 upstream. Add support for VW/Skoda "Carstick LTE" D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=1c9e ProdID=7605 Rev=02.00 S: Manufacturer=USB Modem S: Product=USB Modem C: #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) The stick has AT command interfaces on interfaces 1, 2, and 3, and does PPP on interface 3. Signed-off-by: Florian Zumbiehl Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 2fc65cbbfea9..14a7af7f3bcd 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -402,6 +402,8 @@ static void option_instat_callback(struct urb *urb); #define LONGCHEER_VENDOR_ID 0x1c9e /* 4G Systems products */ +/* This one was sold as the VW and Skoda "Carstick LTE" */ +#define FOUR_G_SYSTEMS_PRODUCT_CARSTICK_LTE 0x7605 /* This is the 4G XS Stick W14 a.k.a. Mobilcom Debitel Surf-Stick * * It seems to contain a Qualcomm QSC6240/6290 chipset */ #define FOUR_G_SYSTEMS_PRODUCT_W14 0x9603 @@ -1976,6 +1978,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(2) }, { USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) }, { USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_CARSTICK_LTE), + .driver_info = RSVD(0) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14), .driver_info = NCTRL(0) | NCTRL(1) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W100), From c5360eec648bd506afa304ae4a71f82e13d41897 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Mon, 13 Feb 2023 23:00:38 +0530 Subject: [PATCH 1478/4345] usb: gadget: u_serial: Add null pointer check in gserial_resume commit 5ec63fdbca604568890c577753c6f66c5b3ef0b5 upstream. Consider a case where gserial_disconnect has already cleared gser->ioport. And if a wakeup interrupt triggers afterwards, gserial_resume gets called, which will lead to accessing of gser->ioport and thus causing null pointer dereference.Add a null pointer check to prevent this. Added a static spinlock to prevent gser->ioport from becoming null after the newly added check. Fixes: aba3a8d01d62 ("usb: gadget: u_serial: add suspend resume callbacks") Cc: stable Signed-off-by: Prashanth K Acked-by: Alan Stern Link: https://lore.kernel.org/r/1676309438-14922-1-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_serial.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 2caccbb6e014..7b54e814aefb 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -81,6 +81,9 @@ #define WRITE_BUF_SIZE 8192 /* TX only */ #define GS_CONSOLE_BUF_SIZE 8192 +/* Prevents race conditions while accessing gser->ioport */ +static DEFINE_SPINLOCK(serial_port_lock); + /* console info */ struct gs_console { struct console console; @@ -1376,8 +1379,10 @@ void gserial_disconnect(struct gserial *gser) if (!port) return; + spin_lock_irqsave(&serial_port_lock, flags); + /* tell the TTY glue not to do I/O here any more */ - spin_lock_irqsave(&port->port_lock, flags); + spin_lock(&port->port_lock); gs_console_disconnect(port); @@ -1392,7 +1397,8 @@ void gserial_disconnect(struct gserial *gser) tty_hangup(port->port.tty); } port->suspended = false; - spin_unlock_irqrestore(&port->port_lock, flags); + spin_unlock(&port->port_lock); + spin_unlock_irqrestore(&serial_port_lock, flags); /* disable endpoints, aborting down any active I/O */ usb_ep_disable(gser->out); @@ -1426,10 +1432,19 @@ EXPORT_SYMBOL_GPL(gserial_suspend); void gserial_resume(struct gserial *gser) { - struct gs_port *port = gser->ioport; + struct gs_port *port; unsigned long flags; - spin_lock_irqsave(&port->port_lock, flags); + spin_lock_irqsave(&serial_port_lock, flags); + port = gser->ioport; + + if (!port) { + spin_unlock_irqrestore(&serial_port_lock, flags); + return; + } + + spin_lock(&port->port_lock); + spin_unlock(&serial_port_lock); port->suspended = false; if (!port->start_delayed) { spin_unlock_irqrestore(&port->port_lock, flags); From 218925bfd5d1436e337c4f961e9c149fbe32de6d Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 31 Jan 2023 15:49:04 -0500 Subject: [PATCH 1479/4345] USB: core: Don't hold device lock while reading the "descriptors" sysfs file commit 45bf39f8df7f05efb83b302c65ae3b9bc92b7065 upstream. Ever since commit 83e83ecb79a8 ("usb: core: get config and string descriptors for unauthorized devices") was merged in 2013, there has been no mechanism for reallocating the rawdescriptors buffers in struct usb_device after the initial enumeration. Before that commit, the buffers would be deallocated when a device was deauthorized and reallocated when it was authorized and enumerated. This means that the locking in the read_descriptors() routine is not needed, since the buffers it reads will never be reallocated while the routine is running. This locking can interfere with user programs trying to read a hub's descriptors via sysfs while new child devices of the hub are being initialized, since the hub is locked during this procedure. Since the locking in read_descriptors() hasn't been needed for over nine years, we can remove it. Reported-and-tested-by: Troels Liebe Bentsen Signed-off-by: Alan Stern CC: stable@vger.kernel.org Link: https://lore.kernel.org/r/Y9l+wDTRbuZABzsE@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 5 ++--- drivers/usb/core/sysfs.c | 5 ----- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 5925b8eb9ee3..7af2def631a2 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2380,9 +2380,8 @@ static int usb_enumerate_device_otg(struct usb_device *udev) * usb_enumerate_device - Read device configs/intfs/otg (usbcore-internal) * @udev: newly addressed device (in ADDRESS state) * - * This is only called by usb_new_device() and usb_authorize_device() - * and FIXME -- all comments that apply to them apply here wrt to - * environment. + * This is only called by usb_new_device() -- all comments that apply there + * apply here wrt to environment. * * If the device is WUSB and not authorized, we don't attempt to read * the string descriptors, as they will be errored out by the device diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index 8d134193fa0c..a2ca38e25e0c 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -889,11 +889,7 @@ read_descriptors(struct file *filp, struct kobject *kobj, size_t srclen, n; int cfgno; void *src; - int retval; - retval = usb_lock_device_interruptible(udev); - if (retval < 0) - return -EINTR; /* The binary attribute begins with the device descriptor. * Following that are the raw descriptor entries for all the * configurations (config plus subsidiary descriptors). @@ -918,7 +914,6 @@ read_descriptors(struct file *filp, struct kobject *kobj, off -= srclen; } } - usb_unlock_device(udev); return count - nleft; } From 08681391b84da27133deefaaddefd0acfa90c2be Mon Sep 17 00:00:00 2001 From: Bing-Jhong Billy Jheng Date: Thu, 2 Mar 2023 21:00:06 +0800 Subject: [PATCH 1480/4345] io_uring: add missing lock in io_get_file_fixed io_get_file_fixed will access io_uring's context. Lock it if it is invoked unlocked (eg via io-wq) to avoid a race condition with fixed files getting unregistered. No single upstream patch exists for this issue, it was fixed as part of the file assignment changes that went into the 5.18 cycle. Signed-off-by: Jheng, Bing-Jhong Billy Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 642e1a0560c6..0c27b81ee1eb 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1092,7 +1092,8 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -3975,7 +3976,7 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; @@ -4015,7 +4016,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; @@ -6876,13 +6877,16 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file } static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) + struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct file *file = NULL; unsigned long file_ptr; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); @@ -6890,6 +6894,8 @@ static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT); io_req_set_rsrc_node(req); +out: + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return file; } @@ -6907,10 +6913,11 @@ static struct file *io_file_get_normal(struct io_ring_ctx *ctx, } static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags) { if (fixed) - return io_file_get_fixed(ctx, req, fd); + return io_file_get_fixed(ctx, req, fd, issue_flags); else return io_file_get_normal(ctx, req, fd); } @@ -7132,7 +7139,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[req->opcode].needs_file) { req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); + (sqe_flags & IOSQE_FIXED_FILE), 0); if (unlikely(!req->file)) ret = -EBADF; } From a25aa776b0c49b17c67ee047e58537552f16776f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 3 Mar 2023 11:44:52 +0100 Subject: [PATCH 1481/4345] Linux 5.10.171 Link: https://lore.kernel.org/r/20230301180652.316428563@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Slade Watkins Tested-by: Pavel Machek (CIP) Tested-by: Shuah Khan Tested-by: Jon Hunter Tested-by: Sudip Mukherjee Tested-by: Salvatore Bonaccorso Tested-by: Linux Kernel Functional Testing Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 028fca7ec5cf..9dde2c230789 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 170 +SUBLEVEL = 171 EXTRAVERSION = NAME = Dare mighty things From d415c6e56fa928b7ef3c59a492e016fab05185a3 Mon Sep 17 00:00:00 2001 From: Bing-Jhong Billy Jheng Date: Thu, 2 Mar 2023 21:00:06 +0800 Subject: [PATCH 1482/4345] UPSTREAM: io_uring: add missing lock in io_get_file_fixed io_get_file_fixed will access io_uring's context. Lock it if it is invoked unlocked (eg via io-wq) to avoid a race condition with fixed files getting unregistered. No single upstream patch exists for this issue, it was fixed as part of the file assignment changes that went into the 5.18 cycle. Signed-off-by: Jheng, Bing-Jhong Billy Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 08681391b84da27133deefaaddefd0acfa90c2be) Bug: 268174392 Signed-off-by: Greg Kroah-Hartman Change-Id: I01ec4283589acde1d17318eb76f87ce099ec3fa0 --- io_uring/io_uring.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 2be25b6fe65a..87e1256cea04 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1102,7 +1102,8 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -3985,7 +3986,7 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; @@ -4025,7 +4026,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; @@ -6886,13 +6887,16 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file } static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) + struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct file *file = NULL; unsigned long file_ptr; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); @@ -6900,6 +6904,8 @@ static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT); io_req_set_rsrc_node(req); +out: + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return file; } @@ -6917,10 +6923,11 @@ static struct file *io_file_get_normal(struct io_ring_ctx *ctx, } static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags) { if (fixed) - return io_file_get_fixed(ctx, req, fd); + return io_file_get_fixed(ctx, req, fd, issue_flags); else return io_file_get_normal(ctx, req, fd); } @@ -7142,7 +7149,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[req->opcode].needs_file) { req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); + (sqe_flags & IOSQE_FIXED_FILE), 0); if (unlikely(!req->file)) ret = -EBADF; } From 365c551e77e7c1d2861f53f836ae4fc7b51cfcca Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 3 Mar 2023 12:46:48 +0000 Subject: [PATCH 1483/4345] Revert "nvmem: core: fix return value" This reverts commit e95381034519a8c5a3150f7b03f4664b1da651b2 which is commit 0c4862b1c1465e473bc961a02765490578bf5c20 upstream. It breaks the Android kernel api, and isn't even really needed in the 5.10.y kernel tree yet, as there are no users of the new field. So revert it for now. If it is needed, it can be brought back in an abi-safe way in the future. Bug: 161946584 Change-Id: I4e335c73a46ba291c790e54f40350a754ff6376b Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 1505c745154e..0ef7b95348b1 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -638,7 +638,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { rval = PTR_ERR(nvmem->wp_gpio); - nvmem->wp_gpio = NULL; goto err_put_device; } From 07d89b34a942934a67b1bfed01a618cdce96bb68 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 3 Mar 2023 12:47:15 +0000 Subject: [PATCH 1484/4345] Revert "nvmem: core: fix registration vs use race" This reverts commit 2dcb474af1d5d06c1e343a0d7248219bb87a08b7 which is commit ab3428cfd9aa2f3463ee4b2909b5bb2193bd0c4a upstream. It breaks the Android kernel api, and isn't even really needed in the 5.10.y kernel tree yet, as there are no users of the new field. So revert it for now. If it is needed, it can be brought back in an abi-safe way in the future. Bug: 161946584 Change-Id: Ibff0d5602c36121fdb31767fd37a013bd26f94cb Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 0ef7b95348b1..de356cdde4ce 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -682,10 +682,16 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->dev.groups = nvmem_dev_groups; #endif + dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); + + rval = device_add(&nvmem->dev); + if (rval) + goto err_put_device; + if (config->compat) { rval = nvmem_sysfs_setup_compat(nvmem, config); if (rval) - goto err_put_device; + goto err_device_del; } if (config->cells) { @@ -702,12 +708,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (rval) goto err_remove_cells; - dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); - - rval = device_add(&nvmem->dev); - if (rval) - goto err_remove_cells; - blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem); return nvmem; @@ -716,6 +716,8 @@ err_remove_cells: nvmem_device_remove_all_cells(nvmem); if (config->compat) nvmem_sysfs_remove_compat(nvmem, config); +err_device_del: + device_del(&nvmem->dev); err_put_device: put_device(&nvmem->dev); From a4160f76c75807d2d55ffc651e6bea3787d8e6be Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 3 Mar 2023 12:48:27 +0000 Subject: [PATCH 1485/4345] Revert "nvmem: core: fix cleanup after dev_set_name()" This reverts commit 23676ecd2eb377f7c24a6ff578b0f4c7135658b6 which is commit 560181d3ace61825f4ca9dd3481d6c0ee6709fa8 upstream. It breaks the Android kernel api, and isn't even really needed in the 5.10.y kernel tree yet, as there are no users of the new field. So revert it for now. If it is needed, it can be brought back in an abi-safe way in the future. Bug: 161946584 Change-Id: Ie5f1017d74bcf014b0ba5fe2f9e91eed8b735af4 Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index de356cdde4ce..38c05fce7d74 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -627,18 +627,14 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->id = rval; - nvmem->dev.type = &nvmem_provider_type; - nvmem->dev.bus = &nvmem_bus_type; - nvmem->dev.parent = config->dev; - - device_initialize(&nvmem->dev); - if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { + ida_free(&nvmem_ida, nvmem->id); rval = PTR_ERR(nvmem->wp_gpio); - goto err_put_device; + kfree(nvmem); + return ERR_PTR(rval); } kref_init(&nvmem->refcnt); @@ -650,6 +646,9 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->stride = config->stride ?: 1; nvmem->word_size = config->word_size ?: 1; nvmem->size = config->size; + nvmem->dev.type = &nvmem_provider_type; + nvmem->dev.bus = &nvmem_bus_type; + nvmem->dev.parent = config->dev; nvmem->root_only = config->root_only; nvmem->priv = config->priv; nvmem->type = config->type; @@ -672,8 +671,11 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) break; } - if (rval) - goto err_put_device; + if (rval) { + ida_free(&nvmem_ida, nvmem->id); + kfree(nvmem); + return ERR_PTR(rval); + } nvmem->read_only = device_property_present(config->dev, "read-only") || config->read_only || !nvmem->reg_write; @@ -684,7 +686,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); - rval = device_add(&nvmem->dev); + rval = device_register(&nvmem->dev); if (rval) goto err_put_device; From d480976b056c3089ac12e2b463f66a5c8ed36dca Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 3 Mar 2023 12:48:31 +0000 Subject: [PATCH 1486/4345] Revert "nvmem: core: remove nvmem_config wp_gpio" This reverts commit 89991ededcb557dcfe6398fa37eb182d01cfe257 which is commit 569653f022a29a1a44ea9de5308b657228303fa5 upstream. It breaks the Android kernel api, and isn't even really needed in the 5.10.y kernel tree yet, as there are no users of the new field. So revert it for now. If it is needed, it can be brought back in an abi-safe way in the future. Bug: 161946584 Change-Id: Ib69df930ea19f91d0d35d792e3b90dc1d391980b Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 4 +++- include/linux/nvmem-provider.h | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 38c05fce7d74..9da4edbabfe7 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -627,7 +627,9 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->id = rval; - if (!config->ignore_wp) + if (config->wp_gpio) + nvmem->wp_gpio = config->wp_gpio; + else if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 5e07f3cfad30..39ec67689898 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -49,6 +49,7 @@ enum nvmem_type { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. + * @wp-gpio: Write protect pin * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem" name will be assigned to the device if @@ -63,6 +64,7 @@ struct nvmem_config { const char *name; int id; struct module *owner; + struct gpio_desc *wp_gpio; const struct nvmem_cell_info *cells; int ncells; enum nvmem_type type; From a02b4a8660e1889e334db7b75e28078ee40f0d50 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 18 Feb 2023 09:12:29 +0000 Subject: [PATCH 1487/4345] Revert "nvmem: core: Fix a conflict between MTD and NVMEM on wp-gpios property" This reverts commit 34ec4c7831c416ac56619477f1701986634a7efc which is commit f6c052afe6f802d87c74153b7a57c43b2e9faf07 upstream. It breaks the Android kernel api, and isn't even really needed in the 5.10.y kernel tree yet, as there are no users of the new field. So revert it for now. If it is needed, it can be brought back in an abi-safe way in the future. Bug: 161946584 Change-Id: Ib1df4adb89fa493d044d1108da6ce6e667a5e0c7 Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 2 +- include/linux/nvmem-provider.h | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 9da4edbabfe7..1c17c5d09228 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -629,7 +629,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (config->wp_gpio) nvmem->wp_gpio = config->wp_gpio; - else if (!config->ignore_wp) + else nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 39ec67689898..06409a6c40bc 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -49,8 +49,7 @@ enum nvmem_type { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin - * @ignore_wp: Write Protect pin is managed by the provider. + * @wp-gpio: Write protect pin * * Note: A default "nvmem" name will be assigned to the device if * no name is specified in its configuration. In such case "" is @@ -70,7 +69,6 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; - bool ignore_wp; bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; From da24142b1ef9fd5d36b76e36bab328a5b27523e8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 3 Mar 2023 06:49:57 -0700 Subject: [PATCH 1488/4345] io_uring: ensure that io_init_req() passes in the right issue_flags We can't use 0 here, as io_init_req() is always invoked with the ctx uring_lock held. Newer kernels have IO_URING_F_UNLOCKED for this, but previously we used IO_URING_F_NONBLOCK to indicate this as well. Fixes: 08681391b84d ("io_uring: add missing lock in io_get_file_fixed") Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 0c27b81ee1eb..cf6f8aeb450d 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -7139,7 +7139,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[req->opcode].needs_file) { req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE), 0); + (sqe_flags & IOSQE_FIXED_FILE), + IO_URING_F_NONBLOCK); if (unlikely(!req->file)) ret = -EBADF; } From 9fd42770b50756c08f04b4070ab6572adb2d6e1b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 3 Mar 2023 15:13:15 +0100 Subject: [PATCH 1489/4345] Linux 5.10.172 Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 9dde2c230789..447ed158d6bc 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 171 +SUBLEVEL = 172 EXTRAVERSION = NAME = Dare mighty things From 9abdacf47f741baa88331bf255b2ad28428fe65d Mon Sep 17 00:00:00 2001 From: Udipto Goswami Date: Wed, 1 Feb 2023 18:53:08 +0530 Subject: [PATCH 1490/4345] FROMGIT: usb: gadget: configfs: Restrict symlink creation is UDC already binded During enumeration or composition switch,a userspace process agnostic of the conventions of configs can try to create function symlinks even after the UDC is bound to current config which is not correct. Potentially it can create duplicates within the current config. Prevent this by adding a check if udc_name already exists, then bail out of cfg_link. Following is an example: Step1: ln -s X1 ffs.a -->cfg_link --> usb_get_function(ffs.a) ->ffs_alloc CFG->FUNC_LIST: C->FUNCTION: Step2: echo udc.name > /config/usb_gadget/g1/UDC --> UDC_store ->composite_bind ->usb_add_function CFG->FUNC_LIST: C->FUNCTION: Step3: ln -s Y1 ffs.a -->cfg_link -->usb_get_function(ffs.a) ->ffs_alloc CFG->FUNC_LIST: C->FUNCTION: both the lists corresponds to the same function instance ffs.a but the usb_function* pointer is different because in step 3 ffs_alloc has created a new reference to usb_function* for ffs.a and added it to cfg_list. Step4: Now a composition switch involving is executed. the composition switch will involve 3 things: 1. unlinking the previous functions existing 2. creating new symlinks 3. writing UDC However, the composition switch is generally taken care by userspace process which creates the symlinks in its own nomenclature(X*) and removes only those. So it won't be able to remove Y1 which user had created by own. Due to this the new symlinks cannot be created for ffs.a since the entry already exists in CFG->FUNC_LIST. The state of the CFG->FUNC_LIST is as follows: CFG->FUNC_LIST: Fixes: 88af8bbe4ef7 ("usb: gadget: the start of the configfs interface") Signed-off-by: Krishna Kurapati PSSNV Signed-off-by: Udipto Goswami Link: https://lore.kernel.org/r/20230201132308.31523-1-quic_ugoswami@quicinc.com Signed-off-by: Greg Kroah-Hartman BUG: 267715065 (cherry picked from commit 89e7252d6c7e7eeb31971cd7df987316ecc64ff5 usb-next) Change-Id: I0f21c75ce0929756efacd0035ae21085ab9742f2 Signed-off-by: Udipto Goswami --- drivers/usb/gadget/configfs.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index b6f86463a26e..c7c819d54437 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -461,6 +461,12 @@ static int config_usb_cfg_link( * from another gadget or a random directory. * Also a function instance can only be linked once. */ + + if (gi->composite.gadget_driver.udc_name) { + ret = -EINVAL; + goto out; + } + list_for_each_entry(a_fi, &gi->available_func, cfs_list) { if (a_fi == fi) break; From c2e3f757d344e1588331e83b95078c44f1cc7c58 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 3 Mar 2023 06:49:57 -0700 Subject: [PATCH 1491/4345] UPSTREAM: io_uring: ensure that io_init_req() passes in the right issue_flags We can't use 0 here, as io_init_req() is always invoked with the ctx uring_lock held. Newer kernels have IO_URING_F_UNLOCKED for this, but previously we used IO_URING_F_NONBLOCK to indicate this as well. Fixes: 08681391b84d ("io_uring: add missing lock in io_get_file_fixed") Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman (cherry picked from commit da24142b1ef9fd5d36b76e36bab328a5b27523e8) Bug: 268174392 Signed-off-by: Greg Kroah-Hartman Change-Id: I762eacf1b49ca8a38d8b77c44db4ca2bc49b2c4c --- io_uring/io_uring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 87e1256cea04..43ccd6ca8302 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -7149,7 +7149,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[req->opcode].needs_file) { req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE), 0); + (sqe_flags & IOSQE_FIXED_FILE), + IO_URING_F_NONBLOCK); if (unlikely(!req->file)) ret = -EBADF; } From 278dfb09d7bfbea2c30b57784cd8de2553fd86cf Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 18 Feb 2023 13:33:02 +0000 Subject: [PATCH 1492/4345] Revert "ANDROID: dma-ops: Add restricted vendor hook" This reverts commit 9d2ec2e0b69e81d5925e363f3a4e0b6cfaefb7e7. The hook android_rvh_setup_dma_ops is not used by any vendor, so remove it to help with merge issues with future LTS releases. If this is needed by any real user, it can easily be reverted to add it back and then the symbol should be added to the abi list at the same time to prevent it from being removed again later. Bug: 263236925 Bug: 203756332 Cc: Beata Michalska Signed-off-by: Greg Kroah-Hartman Change-Id: I7741910039ac9914e2e2adf974204278d37db94d --- arch/arm64/mm/dma-mapping.c | 4 ---- drivers/android/vendor_hooks.c | 2 -- include/trace/hooks/dma_noalias.h | 19 ------------------- 3 files changed, 25 deletions(-) delete mode 100644 include/trace/hooks/dma_noalias.h diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 19ceea8fea1a..e75e5e75b192 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -11,7 +11,6 @@ #include #include #include -#include #include @@ -57,9 +56,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, trace_android_rvh_iommu_setup_dma_ops(dev, dma_base, size); } - /* Allow vendor modules to opt-in for the 2454944 erratum workaround */ - trace_android_rvh_setup_dma_ops(dev); - #ifdef CONFIG_XEN if (xen_initial_domain()) dev->dma_ops = &xen_swiotlb_dma_ops; diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index 54c46c11c09a..5702bf54e0e6 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -42,7 +42,6 @@ #include #include #include -#include #include #include #include @@ -217,7 +216,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_die_kernel_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_do_sea); EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_do_mem_abort); EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_do_sp_pc_abort); -EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_setup_dma_ops); EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_iommu_setup_dma_ops); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_iommu_setup_dma_ops); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_iommu_alloc_iova); diff --git a/include/trace/hooks/dma_noalias.h b/include/trace/hooks/dma_noalias.h deleted file mode 100644 index 2dc7b04d9ab2..000000000000 --- a/include/trace/hooks/dma_noalias.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM dma_noalias - -#define TRACE_INCLUDE_PATH trace/hooks - -#if !defined(_TRACE_HOOK_DMA_NOALIAS_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_HOOK_DMA_NOALIAS_H - -#include - -DECLARE_RESTRICTED_HOOK(android_rvh_setup_dma_ops, - TP_PROTO(struct device *dev), - TP_ARGS(dev), 1); - -#endif /*_TRACE_HOOK_DMA_NOALIAS_H */ - -/* This part must be outside protection */ -#include From 631630d75f2018ee5b0376a96dcffe4e513e7431 Mon Sep 17 00:00:00 2001 From: Ram Muthiah Date: Mon, 6 Mar 2023 14:04:00 -0800 Subject: [PATCH 1493/4345] ANDROID: ABI: Cuttlefish Symbol update The cuttlefish symbol list is out of date. Updating it with the following steps. $ BUILD_CONFIG=common/build.config.gki.aarch64 build/build.sh $ BUILD_CONFIG=common-modules/virtual-\ device/build.config.cuttlefish.aarch64 build/build.sh $ build/abi/extract_symbols out/android12-5.10/dist/ --whitelist \ common/android/abi_gki_aarch64_virtual_device --additions-only $ BUILD_CONFIG=common/build.config.gki.aarch64 build/build_abi.sh \ --update --print-report Bug: 203806616 Test: Local boot on cuttlefish arm64 android11-gsi Change-Id: I48fbc598e5a3e4ac8db68c51d699922099da7de8 Signed-off-by: Ram Muthiah --- android/abi_gki_aarch64_virtual_device | 92 +++++++++++++++++--------- 1 file changed, 59 insertions(+), 33 deletions(-) diff --git a/android/abi_gki_aarch64_virtual_device b/android/abi_gki_aarch64_virtual_device index 692983348396..034100b8f973 100644 --- a/android/abi_gki_aarch64_virtual_device +++ b/android/abi_gki_aarch64_virtual_device @@ -211,8 +211,12 @@ kstrndup kstrtobool kstrtoint + kstrtoll kstrtouint kstrtoull + kthread_create_on_node + kthread_should_stop + kthread_stop ktime_get ktime_get_mono_fast_ns ktime_get_raw_ts64 @@ -307,6 +311,10 @@ __per_cpu_offset perf_trace_buf_alloc perf_trace_run_bpf_submit + platform_device_add + platform_device_alloc + platform_device_del + platform_device_put platform_device_register_full platform_device_unregister __platform_driver_register @@ -350,7 +358,6 @@ __rcu_read_unlock refcount_warn_saturate register_blkdev - register_netdev register_netdevice register_netdevice_notifier register_pernet_device @@ -448,12 +455,14 @@ sscanf __stack_chk_fail __stack_chk_guard + strchr strcmp strcpy strlcpy strlen strncmp strncpy + strscpy strsep submit_bio __sw_hweight16 @@ -465,7 +474,6 @@ synchronize_rcu sysfs_create_group sysfs_create_link - __sysfs_match_string sysfs_remove_group sysfs_remove_link system_freezable_wq @@ -514,8 +522,11 @@ usleep_range vabits_actual vfree + virtio_break_device virtio_check_driver_offered_feature virtio_config_changed + virtio_device_freeze + virtio_device_restore virtqueue_add_inbuf virtqueue_add_outbuf virtqueue_add_sgs @@ -531,12 +542,14 @@ virtqueue_kick virtqueue_kick_prepare virtqueue_notify + vmalloc_to_page vring_create_virtqueue vring_del_virtqueue vring_interrupt vring_transport_features wait_for_completion __wake_up + wake_up_process __warn_printk # required by ambakmi.ko @@ -711,7 +724,6 @@ set_page_dirty # required by goldfish_sync.ko - __close_fd dma_fence_default_wait dma_fence_free @@ -821,7 +833,6 @@ simple_attr_open simple_attr_release __skb_ext_put - skb_unlink # required by md-mod.ko ack_all_badblocks @@ -867,22 +878,12 @@ kernfs_put kobject_del kobject_get - kstrtoll - kthread_create_on_node kthread_parkme kthread_should_park - kthread_should_stop - kthread_stop - mempool_alloc mempool_create mempool_destroy - mempool_exit - mempool_free - mempool_init mempool_kfree mempool_kmalloc - part_end_io_acct - part_start_io_acct percpu_ref_exit percpu_ref_init percpu_ref_is_zero @@ -902,7 +903,6 @@ unregister_reboot_notifier unregister_sysctl_table vfs_fsync - wake_up_process # required by nd_virtio.ko bio_chain @@ -923,6 +923,7 @@ netdev_lower_state_changed netdev_pick_tx pci_bus_type + register_netdev # required by psmouse.ko bus_register_notifier @@ -969,16 +970,11 @@ cec_s_phys_addr cec_transmit_attempt_done_ts cec_unregister_adapter - strscpy wait_for_completion_timeout # required by rtc-test.ko add_timer devm_rtc_allocate_device - platform_device_add - platform_device_alloc - platform_device_del - platform_device_put __rtc_register_device rtc_time64_to_tm rtc_tm_to_time64 @@ -1002,9 +998,9 @@ strcat # required by snd-hda-codec-generic.ko - devm_led_classdev_register_ext + led_classdev_register_ext + led_classdev_unregister snd_ctl_boolean_stereo_info - strchr strlcat # required by snd-hda-codec.ko @@ -1106,6 +1102,9 @@ compat_ptr_ioctl # required by usbip-core.ko + iov_iter_kvec + param_ops_ulong + print_hex_dump sock_recvmsg # required by vcan.ko @@ -1128,9 +1127,27 @@ devm_mfd_add_devices # required by vhci-hcd.ko + kernel_sendmsg kernel_sock_shutdown platform_bus + platform_device_add_data sockfd_lookup + usb_add_hcd + usb_create_hcd + usb_create_shared_hcd + usb_disabled + usb_get_dev + usb_hcd_check_unlink_urb + usb_hcd_giveback_urb + usb_hcd_is_primary_hcd + usb_hcd_link_urb_to_ep + usb_hcd_poll_rh_status + usb_hcd_resume_root_hub + usb_hcd_unlink_urb_from_ep + usb_put_dev + usb_put_hcd + usb_remove_hcd + usb_speed_string # required by virt_wifi.ko __module_get @@ -1259,7 +1276,6 @@ __traceiter_gpu_mem_total __tracepoint_dma_fence_emit __tracepoint_gpu_mem_total - vmalloc_to_page vmemdup_user vm_get_page_prot ww_mutex_lock_interruptible @@ -1309,6 +1325,7 @@ __blk_rq_map_sg set_capacity_revalidate_and_notify string_get_size + __sysfs_match_string virtio_max_dma_size # required by virtio_console.ko @@ -1412,9 +1429,6 @@ pci_request_selected_regions pci_vfs_assigned synchronize_irq - virtio_break_device - virtio_device_freeze - virtio_device_restore # required by virtio_pmem.ko nvdimm_bus_register @@ -1422,14 +1436,8 @@ nvdimm_pmem_region_create # required by virtio_snd.ko - snd_ctl_notify snd_pcm_format_physical_width - snd_pcm_lib_free_pages snd_pcm_lib_ioctl - snd_pcm_lib_malloc_pages - snd_pcm_lib_preallocate_pages - _snd_pcm_stream_lock_irqsave - snd_pcm_stream_unlock_irqrestore wait_for_completion_interruptible_timeout # required by vmw_vsock_virtio_transport.ko @@ -1489,9 +1497,27 @@ # required by zsmalloc.ko dec_zone_page_state inc_zone_page_state - __lock_page page_mapping _raw_read_lock _raw_read_unlock _raw_write_lock _raw_write_unlock + wait_on_page_bit + +# preserved by --additions-only + __close_fd + devm_led_classdev_register_ext + __lock_page + mempool_alloc + mempool_exit + mempool_free + mempool_init + part_end_io_acct + part_start_io_acct + skb_unlink + snd_ctl_notify + snd_pcm_lib_free_pages + snd_pcm_lib_malloc_pages + snd_pcm_lib_preallocate_pages + _snd_pcm_stream_lock_irqsave + snd_pcm_stream_unlock_irqrestore From dbcd8cb5350ea104c3d775164810a668fa61a07a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 1 Oct 2021 18:05:53 +0100 Subject: [PATCH 1494/4345] UPSTREAM: KVM: arm64: Allow KVM to be disabled from the command line Although KVM can be compiled out of the kernel, it cannot be disabled at runtime. Allow this possibility by introducing a new mode that will prevent KVM from initialising. This is useful in the (limited) circumstances where you don't want KVM to be available (what is wrong with you?), or when you want to install another hypervisor instead (good luck with that). Reviewed-by: David Brazdil Acked-by: Will Deacon Acked-by: Suzuki K Poulose Signed-off-by: Marc Zyngier Reviewed-by: Andrew Scull Link: https://lore.kernel.org/r/20211001170553.3062988-1-maz@kernel.org (cherry picked from commit b6a68b97af23cc75781bed38221ce73144ac2e39) Bug: 204960018 Signed-off-by: Will Deacon Change-Id: Ie796c716fc7cece906a8cded0ae4652a828988bb (cherry picked from commit a621a4e6cb1e249d165f643d511c887c7fc4cdc7) --- Documentation/admin-guide/kernel-parameters.txt | 2 ++ arch/arm64/include/asm/kvm_host.h | 1 + arch/arm64/kvm/arm.c | 14 +++++++++++++- 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index c841b5208771..3a16cdd1e251 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2311,6 +2311,8 @@ kvm-arm.mode= [KVM,ARM] Select one of KVM/arm64's modes of operation. + none: Forcefully disable KVM. + nvhe: Standard nVHE-based mode, without support for protected guests. diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index b7fa62950b78..b714f048481c 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -58,6 +58,7 @@ enum kvm_mode { KVM_MODE_DEFAULT, KVM_MODE_PROTECTED, + KVM_MODE_NONE, }; enum kvm_mode kvm_get_mode(void); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 78550c856c24..20974e71c9a6 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2061,6 +2061,11 @@ int kvm_arch_init(void *opaque) return -ENODEV; } + if (kvm_get_mode() == KVM_MODE_NONE) { + kvm_info("KVM disabled from command line\n"); + return -ENODEV; + } + in_hyp_mode = is_kernel_in_hyp_mode(); if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) || @@ -2142,8 +2147,15 @@ static int __init early_kvm_mode_cfg(char *arg) return 0; } - if (strcmp(arg, "nvhe") == 0 && !WARN_ON(is_kernel_in_hyp_mode())) + if (strcmp(arg, "nvhe") == 0 && !WARN_ON(is_kernel_in_hyp_mode())) { + kvm_mode = KVM_MODE_DEFAULT; return 0; + } + + if (strcmp(arg, "none") == 0) { + kvm_mode = KVM_MODE_NONE; + return 0; + } return -EINVAL; } From 9a1be9a472468ef0f5f30ab84de390cc0c571ab8 Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Tue, 20 Sep 2022 12:06:58 -0700 Subject: [PATCH 1495/4345] FROMGIT: KVM: arm64: Ignore kvm-arm.mode if !is_hyp_mode_available() Ignore kvm-arm.mode if !is_hyp_mode_available(). Specifically, we want to avoid switching kvm_mode to KVM_MODE_PROTECTED if hypervisor mode is not available. This prevents "Protected KVM" cpu capability being reported when Linux is booting in EL1 and would not have KVM enabled. Reasonably though, we should warn if the command line is requesting a KVM mode at all if KVM isn't actually available. Allow "kvm-arm.mode=none" to skip the warning since this would disable KVM anyway. Signed-off-by: Elliot Berman Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220920190658.2880184-1-quic_eberman@quicinc.com Bug: 249052880 (cherry picked from commit b2a4d007c347b4cb4c60f7512733c3f8300a129c https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git next) Change-Id: I196649fc00537e563a1fab0a22bf23c5b7abe00d Signed-off-by: Elliot Berman (cherry picked from commit 8015dd49c00e036b214801b34a727b7c98aa84e3) --- arch/arm64/kvm/arm.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 20974e71c9a6..67c20d4d6ade 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2142,6 +2142,16 @@ static int __init early_kvm_mode_cfg(char *arg) if (!arg) return -EINVAL; + if (strcmp(arg, "none") == 0) { + kvm_mode = KVM_MODE_NONE; + return 0; + } + + if (!is_hyp_mode_available()) { + pr_warn_once("KVM is not available. Ignoring kvm-arm.mode\n"); + return 0; + } + if (strcmp(arg, "protected") == 0) { kvm_mode = KVM_MODE_PROTECTED; return 0; @@ -2152,11 +2162,6 @@ static int __init early_kvm_mode_cfg(char *arg) return 0; } - if (strcmp(arg, "none") == 0) { - kvm_mode = KVM_MODE_NONE; - return 0; - } - return -EINVAL; } early_param("kvm-arm.mode", early_kvm_mode_cfg); From 193b312b2f60bf7e7c4793713260568233745a28 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Thu, 9 Feb 2023 11:37:39 -0300 Subject: [PATCH 1496/4345] UPSTREAM: net/sched: tcindex: update imperfect hash filters respecting rcu commit ee059170b1f7e94e55fa6cadee544e176a6e59c2 upstream. The imperfect hash area can be updated while packets are traversing, which will cause a use-after-free when 'tcf_exts_exec()' is called with the destroyed tcf_ext. CPU 0: CPU 1: tcindex_set_parms tcindex_classify tcindex_lookup tcindex_lookup tcf_exts_change tcf_exts_exec [UAF] Stop operating on the shared area directly, by using a local copy, and update the filter with 'rcu_replace_pointer()'. Delete the old filter version only after a rcu grace period elapsed. Bug: 272274675 Fixes: 9b0d4446b569 ("net: sched: avoid atomic swap in tcf_exts_change") Reported-by: valis Suggested-by: valis Signed-off-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Link: https://lore.kernel.org/r/20230209143739.279867-1-pctammela@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman Signed-off-by: Lee Jones Change-Id: I02ce525a338242efdb8080e2e2c705d3b59d9a68 --- net/sched/cls_tcindex.c | 34 ++++++++++++++++++++++++++++++---- 1 file changed, 30 insertions(+), 4 deletions(-) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index e9a8a2c86bbd..dc87feaa3cb3 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -338,6 +339,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct tcf_result cr = {}; int err, balloc = 0; struct tcf_exts e; + bool update_h = false; err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) @@ -455,10 +457,13 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } } - if (cp->perfect) + if (cp->perfect) { r = cp->perfect + handle; - else - r = tcindex_lookup(cp, handle) ? : &new_filter_result; + } else { + /* imperfect area is updated in-place using rcu */ + update_h = !!tcindex_lookup(cp, handle); + r = &new_filter_result; + } if (r == &new_filter_result) { f = kzalloc(sizeof(*f), GFP_KERNEL); @@ -492,7 +497,28 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, rcu_assign_pointer(tp->root, cp); - if (r == &new_filter_result) { + if (update_h) { + struct tcindex_filter __rcu **fp; + struct tcindex_filter *cf; + + f->result.res = r->res; + tcf_exts_change(&f->result.exts, &r->exts); + + /* imperfect area bucket */ + fp = cp->h + (handle % cp->hash); + + /* lookup the filter, guaranteed to exist */ + for (cf = rcu_dereference_bh_rtnl(*fp); cf; + fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp)) + if (cf->key == handle) + break; + + f->next = cf->next; + + cf = rcu_replace_pointer(*fp, f, 1); + tcf_exts_get_net(&cf->result.exts); + tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work); + } else if (r == &new_filter_result) { struct tcindex_filter *nfp; struct tcindex_filter __rcu **fp; From 26638f8e54003c0c2f21f0aeedeba892407d1c44 Mon Sep 17 00:00:00 2001 From: fengqi Date: Fri, 10 Mar 2023 17:23:23 +0800 Subject: [PATCH 1497/4345] ANDROID: GKI: update xiaomi symbol list Leaf changes summary: 4 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 4 Added functions Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 0 Added variable 4 Added functions: [A] 'function int __iio_trigger_register(iio_trigger*, module*)' [A] 'function iio_trigger* iio_trigger_alloc(const char*, ...)' [A] 'function void iio_trigger_free(iio_trigger*)' [A] 'function void iio_trigger_unregister(iio_trigger*)' Bug: 272669403 Change-Id: Ieb112f091b22e9893e627e0f934c45bd1ca940b2 Signed-off-by: fengqi --- android/abi_gki_aarch64.xml | 373 +++++++++++---------------------- android/abi_gki_aarch64_xiaomi | 6 + 2 files changed, 130 insertions(+), 249 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index d44112f52bef..8b3cf2d10c07 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -144,6 +144,7 @@ + @@ -3035,7 +3036,10 @@ + + + @@ -15323,89 +15327,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -21517,14 +21438,6 @@ - - - - - - - - @@ -40974,17 +40887,6 @@ - - - - - - - - - - - @@ -42794,7 +42696,6 @@ - @@ -44612,7 +44513,23 @@ - + + + + + + + + + + + + + + + + + @@ -48942,6 +48859,7 @@ + @@ -53885,6 +53803,13 @@ + + + + + + + @@ -55309,7 +55234,6 @@ - @@ -63265,65 +63189,7 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + @@ -66603,6 +66469,13 @@ + + + + + + + @@ -68111,11 +67984,6 @@ - - - - - @@ -68600,14 +68468,7 @@ - - - - - - - - + @@ -83973,7 +83834,6 @@ - @@ -84518,14 +84378,6 @@ - - - - - - - - @@ -91372,6 +91224,7 @@ + @@ -93884,7 +93737,6 @@ - @@ -96181,7 +96033,6 @@ - @@ -103140,6 +102991,12 @@ + + + + + + @@ -111385,6 +111242,7 @@ + @@ -116240,7 +116098,6 @@ - @@ -116448,9 +116305,9 @@ - + - + @@ -117164,9 +117021,9 @@ - - - + + + @@ -117289,6 +117146,11 @@ + + + + + @@ -127722,8 +127584,8 @@ - - + + @@ -131031,7 +130893,7 @@ - + @@ -131056,10 +130918,10 @@ - - - - + + + + @@ -131864,9 +131726,9 @@ - - - + + + @@ -131883,9 +131745,9 @@ - - - + + + @@ -131927,10 +131789,10 @@ - - - - + + + + @@ -132520,10 +132382,10 @@ - - - - + + + + @@ -133535,10 +133397,23 @@ + + + + + + + + + + + + + @@ -138173,24 +138048,24 @@ - - - - - - - - + + + + + + + + - - - - - - - - + + + + + + + + @@ -140691,17 +140566,17 @@ - - - - - + + + + + - - - - + + + + @@ -146191,9 +146066,9 @@ - - - + + + @@ -147864,12 +147739,12 @@ - - - - - - + + + + + + diff --git a/android/abi_gki_aarch64_xiaomi b/android/abi_gki_aarch64_xiaomi index ebbbb0e81420..ded2c5464994 100644 --- a/android/abi_gki_aarch64_xiaomi +++ b/android/abi_gki_aarch64_xiaomi @@ -208,3 +208,9 @@ __tracepoint_android_vh_alloc_pages_reclaim_bypass __traceiter_android_vh_alloc_pages_failure_bypass __tracepoint_android_vh_alloc_pages_failure_bypass + +#required by us_prox.ko module + iio_trigger_alloc + __iio_trigger_register + iio_trigger_free + iio_trigger_unregister From 87a065fb94a3377019d94c0340e6a626187efcd2 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Fri, 24 Feb 2023 11:16:58 +0530 Subject: [PATCH 1498/4345] UPSTREAM: usb: dwc3: gadget: Change condition for processing suspend event Currently we process the suspend interrupt event only if the device is in configured state. Consider a case where device is not configured and got suspend interrupt, in that case our gadget will still use 100mA as composite_suspend didn't happen. But battery charging specification (BC1.2) expects a downstream device to draw less than 2.5mA when unconnected OR suspended. Fix this by removing the condition for processing suspend event, and thus composite_resume would set vbus draw to 2. Fixes: 72704f876f50 ("dwc3: gadget: Implement the suspend entry event handler") Signed-off-by: Prashanth K Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/1677217619-10261-2-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman Bug: 272680990 (cherry picked from commit 4decf4060ecfee1f7a710999fcd421645ac0c419 https://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git/ usb-next) Change-Id: I902b8911debb7c049a4a0128077ea8d931900d1d Signed-off-by: Prashanth K --- drivers/usb/dwc3/gadget.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index a6ffa60b7de9..0ed907e7aaef 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4210,15 +4210,8 @@ static void dwc3_gadget_interrupt(struct dwc3 *dwc, break; case DWC3_DEVICE_EVENT_SUSPEND: /* It changed to be suspend event for version 2.30a and above */ - if (!DWC3_VER_IS_PRIOR(DWC3, 230A)) { - /* - * Ignore suspend event until the gadget enters into - * USB_STATE_CONFIGURED state. - */ - if (dwc->gadget->state >= USB_STATE_CONFIGURED) - dwc3_gadget_suspend_interrupt(dwc, - event->event_info); - } + if (!DWC3_VER_IS_PRIOR(DWC3, 230A)) + dwc3_gadget_suspend_interrupt(dwc, event->event_info); break; case DWC3_DEVICE_EVENT_SOF: case DWC3_DEVICE_EVENT_ERRATIC_ERROR: From 8926771f7e66c599c5d0fc62ccd1d878d71f05ca Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Fri, 24 Feb 2023 11:16:59 +0530 Subject: [PATCH 1499/4345] UPSTREAM: usb: gadget: composite: Draw 100mA current if not configured Currently we don't change the current value if device isn't in configured state. But in battery charging specification (section 1.2 and 1.4.13), it is mentioned that the device can draw up to 100mA of current if it's in unconfigured state. Hence add vbus draw work in composite_resume to draw 100mA if the device isn't configured. Signed-off-by: Prashanth K Link: https://lore.kernel.org/r/1677217619-10261-3-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman Bug: 272680990 (cherry picked from commit 2ae4e0dea3b0c7b380821bac05e03a71da1f452f https://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git/ usb-next) Change-Id: I51688c84f66d2d5e023b61444e03503092ef41d0 Signed-off-by: Prashanth K --- drivers/usb/gadget/composite.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 9315313108c9..83df30b73522 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2447,6 +2447,10 @@ void composite_resume(struct usb_gadget *gadget) usb_gadget_clear_selfpowered(gadget); usb_gadget_vbus_draw(gadget, maxpower); + } else { + maxpower = CONFIG_USB_GADGET_VBUS_DRAW; + maxpower = min(maxpower, 100U); + usb_gadget_vbus_draw(gadget, maxpower); } cdev->suspended = 0; From cb8382c3714540e404fa62bb9440f5387f8dd8f0 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Mon, 5 Jul 2021 10:26:59 +1200 Subject: [PATCH 1500/4345] HID: asus: Remove check for same LED brightness on set commit 3fdcf7cdfc229346d028242e73562704ad644dd0 upstream. Remove the early return on LED brightness set so that any controller application, daemon, or desktop may set the same brightness at any stage. This is required because many ASUS ROG keyboards will default to max brightness on laptop resume if the LEDs were set to off before sleep. Signed-off-by: Luke D Jones Signed-off-by: Jiri Kosina Signed-off-by: Stefan Ghinea Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-asus.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index f85c6e3309a0..9a6b63828634 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -402,9 +402,6 @@ static void asus_kbd_backlight_set(struct led_classdev *led_cdev, { struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds, cdev); - if (led->brightness == brightness) - return; - led->brightness = brightness; schedule_work(&led->work); } From 6a63a3334acad9821b21e2dabcf67d82cdcbc44e Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 19:00:02 +0000 Subject: [PATCH 1501/4345] HID: asus: use spinlock to protect concurrent accesses commit 315c537068a13f0b5681d33dd045a912f4bece6f upstream. asus driver has a worker that may access data concurrently. Proct the accesses using a spinlock. Fixes: af22a610bc38 ("HID: asus: support backlight on USB keyboards") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230125-hid-unregister-leds-v4-4-7860c5763c38@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Stefan Ghinea Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-asus.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 9a6b63828634..112c0c25a77f 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -95,6 +95,7 @@ struct asus_kbd_leds { struct hid_device *hdev; struct work_struct work; unsigned int brightness; + spinlock_t lock; bool removed; }; @@ -402,7 +403,12 @@ static void asus_kbd_backlight_set(struct led_classdev *led_cdev, { struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds, cdev); + unsigned long flags; + + spin_lock_irqsave(&led->lock, flags); led->brightness = brightness; + spin_unlock_irqrestore(&led->lock, flags); + schedule_work(&led->work); } @@ -410,8 +416,14 @@ static enum led_brightness asus_kbd_backlight_get(struct led_classdev *led_cdev) { struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds, cdev); + enum led_brightness brightness; + unsigned long flags; - return led->brightness; + spin_lock_irqsave(&led->lock, flags); + brightness = led->brightness; + spin_unlock_irqrestore(&led->lock, flags); + + return brightness; } static void asus_kbd_backlight_work(struct work_struct *work) @@ -419,11 +431,14 @@ static void asus_kbd_backlight_work(struct work_struct *work) struct asus_kbd_leds *led = container_of(work, struct asus_kbd_leds, work); u8 buf[] = { FEATURE_KBD_REPORT_ID, 0xba, 0xc5, 0xc4, 0x00 }; int ret; + unsigned long flags; if (led->removed) return; + spin_lock_irqsave(&led->lock, flags); buf[4] = led->brightness; + spin_unlock_irqrestore(&led->lock, flags); ret = asus_kbd_set_report(led->hdev, buf, sizeof(buf)); if (ret < 0) @@ -485,6 +500,7 @@ static int asus_kbd_register_leds(struct hid_device *hdev) drvdata->kbd_backlight->cdev.brightness_set = asus_kbd_backlight_set; drvdata->kbd_backlight->cdev.brightness_get = asus_kbd_backlight_get; INIT_WORK(&drvdata->kbd_backlight->work, asus_kbd_backlight_work); + spin_lock_init(&drvdata->kbd_backlight->lock); ret = devm_led_classdev_register(&hdev->dev, &drvdata->kbd_backlight->cdev); if (ret < 0) { @@ -1013,9 +1029,13 @@ err_stop_hw: static void asus_remove(struct hid_device *hdev) { struct asus_drvdata *drvdata = hid_get_drvdata(hdev); + unsigned long flags; if (drvdata->kbd_backlight) { + spin_lock_irqsave(&drvdata->kbd_backlight->lock, flags); drvdata->kbd_backlight->removed = true; + spin_unlock_irqrestore(&drvdata->kbd_backlight->lock, flags); + cancel_work_sync(&drvdata->kbd_backlight->work); } From 21a2eec4a440060a6eb294dc890eaf553101ba09 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 19:00:03 +0000 Subject: [PATCH 1502/4345] HID: asus: use spinlock to safely schedule workers commit 4ab3a086d10eeec1424f2e8a968827a6336203df upstream. Use spinlocks to deal with workers introducing a wrapper asus_schedule_work(), and several spinlock checks. Otherwise, asus_kbd_backlight_set() may schedule led->work after the structure has been freed, causing a use-after-free. Fixes: af22a610bc38 ("HID: asus: support backlight on USB keyboards") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230125-hid-unregister-leds-v4-5-7860c5763c38@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Stefan Ghinea Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-asus.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 112c0c25a77f..6865cab33cf8 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -398,6 +398,16 @@ static int asus_kbd_get_functions(struct hid_device *hdev, return ret; } +static void asus_schedule_work(struct asus_kbd_leds *led) +{ + unsigned long flags; + + spin_lock_irqsave(&led->lock, flags); + if (!led->removed) + schedule_work(&led->work); + spin_unlock_irqrestore(&led->lock, flags); +} + static void asus_kbd_backlight_set(struct led_classdev *led_cdev, enum led_brightness brightness) { @@ -409,7 +419,7 @@ static void asus_kbd_backlight_set(struct led_classdev *led_cdev, led->brightness = brightness; spin_unlock_irqrestore(&led->lock, flags); - schedule_work(&led->work); + asus_schedule_work(led); } static enum led_brightness asus_kbd_backlight_get(struct led_classdev *led_cdev) @@ -433,9 +443,6 @@ static void asus_kbd_backlight_work(struct work_struct *work) int ret; unsigned long flags; - if (led->removed) - return; - spin_lock_irqsave(&led->lock, flags); buf[4] = led->brightness; spin_unlock_irqrestore(&led->lock, flags); From e1bb97947cac54822c92816dcb483544765c10ca Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Wed, 10 Aug 2022 13:43:18 +0200 Subject: [PATCH 1503/4345] powerpc/mm: Rearrange if-else block to avoid clang warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit d78c8e32890ef7eca79ffd67c96022c7f9d8cce4 upstream. Clang warns: arch/powerpc/mm/book3s64/radix_tlb.c:1191:23: error: variable 'hstart' is uninitialized when used here __tlbiel_va_range(hstart, hend, pid, ^~~~~~ arch/powerpc/mm/book3s64/radix_tlb.c:1191:31: error: variable 'hend' is uninitialized when used here __tlbiel_va_range(hstart, hend, pid, ^~~~ Rework the 'if (IS_ENABLE(CONFIG_TRANSPARENT_HUGEPAGE))' so hstart/hend is always initialized to silence the warnings. That will also simplify the 'else' path. Clang is getting confused with these warnings, but the warnings is a false-positive. Suggested-by: Arnd Bergmann Suggested-by: Nathan Chancellor Reviewed-by: Christophe Leroy Reviewed-by: Nathan Chancellor Signed-off-by: Anders Roxell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220810114318.3220630-1-anders.roxell@linaro.org Signed-off-by: Daniel Díaz Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/mm/book3s64/radix_tlb.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 4c2f75916a7e..abbfd5cc40c9 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -941,15 +941,12 @@ is_local: } } } else { - bool hflush = false; + bool hflush; unsigned long hstart, hend; - if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { - hstart = (start + PMD_SIZE - 1) & PMD_MASK; - hend = end & PMD_MASK; - if (hstart < hend) - hflush = true; - } + hstart = (start + PMD_SIZE - 1) & PMD_MASK; + hend = end & PMD_MASK; + hflush = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hstart < hend; if (local) { asm volatile("ptesync": : :"memory"); From 4862c41d5f3bee1ec64c979c82bd8cfe96b78f7d Mon Sep 17 00:00:00 2001 From: Chen Hui Date: Tue, 8 Nov 2022 22:19:17 +0800 Subject: [PATCH 1504/4345] ARM: OMAP2+: Fix memory leak in realtime_counter_init() [ Upstream commit ed8167cbf65c2b6ff6faeb0f96ded4d6d581e1ac ] The "sys_clk" resource is malloced by clk_get(), it is not released when the function return. Fixes: fa6d79d27614 ("ARM: OMAP: Add initialisation for the real-time counter.") Signed-off-by: Chen Hui Message-Id: <20221108141917.46796-1-judy.chenhui@huawei.com> Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- arch/arm/mach-omap2/timer.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 620ba69c8f11..5677c4a08f37 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -76,6 +76,7 @@ static void __init realtime_counter_init(void) } rate = clk_get_rate(sys_clk); + clk_put(sys_clk); if (soc_is_dra7xx()) { /* From 644688a92162781d887a7d858617f056fc5b2946 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 26 Dec 2022 06:21:51 +0200 Subject: [PATCH 1505/4345] arm64: dts: qcom: qcs404: use symbol names for PCIe resets [ Upstream commit 41a37d157a613444c97e8f71a5fb2a21116b70d7 ] The commit e5bbbff5b7d7 ("clk: gcc-qcs404: Add PCIe resets") added names for PCIe resets, but it did not change the existing qcs404.dtsi to use these names. Do it now and use symbol names to make it easier to check and modify the dtsi in future. Fixes: e5bbbff5b7d7 ("clk: gcc-qcs404: Add PCIe resets") Reviewed-by: Konrad Dybcio Signed-off-by: Dmitry Baryshkov Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221226042154.2666748-14-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/qcs404.dtsi | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/qcs404.dtsi b/arch/arm64/boot/dts/qcom/qcs404.dtsi index 7bddc5ebc6aa..d41f068dde16 100644 --- a/arch/arm64/boot/dts/qcom/qcs404.dtsi +++ b/arch/arm64/boot/dts/qcom/qcs404.dtsi @@ -775,7 +775,7 @@ clocks = <&gcc GCC_PCIE_0_PIPE_CLK>; resets = <&gcc GCC_PCIEPHY_0_PHY_BCR>, - <&gcc 21>; + <&gcc GCC_PCIE_0_PIPE_ARES>; reset-names = "phy", "pipe"; clock-output-names = "pcie_0_pipe_clk"; @@ -1305,12 +1305,12 @@ <&gcc GCC_PCIE_0_SLV_AXI_CLK>; clock-names = "iface", "aux", "master_bus", "slave_bus"; - resets = <&gcc 18>, - <&gcc 17>, - <&gcc 15>, - <&gcc 19>, + resets = <&gcc GCC_PCIE_0_AXI_MASTER_ARES>, + <&gcc GCC_PCIE_0_AXI_SLAVE_ARES>, + <&gcc GCC_PCIE_0_AXI_MASTER_STICKY_ARES>, + <&gcc GCC_PCIE_0_CORE_STICKY_ARES>, <&gcc GCC_PCIE_0_BCR>, - <&gcc 16>; + <&gcc GCC_PCIE_0_AHB_ARES>; reset-names = "axi_m", "axi_s", "axi_m_sticky", From 227f8c1c5c4b3d131b66e57e58d38054f441b915 Mon Sep 17 00:00:00 2001 From: Qiheng Lin Date: Tue, 29 Nov 2022 22:05:44 +0800 Subject: [PATCH 1506/4345] ARM: zynq: Fix refcount leak in zynq_early_slcr_init [ Upstream commit 9eedb910a3be0005b88c696a8552c0d4c9937cd4 ] of_find_compatible_node() returns a node pointer with refcount incremented, we should use of_node_put() on error path. Add missing of_node_put() to avoid refcount leak. Fixes: 3329659df030 ("ARM: zynq: Simplify SLCR initialization") Signed-off-by: Qiheng Lin Link: https://lore.kernel.org/r/20221129140544.41293-1-linqiheng@huawei.com Signed-off-by: Michal Simek Signed-off-by: Sasha Levin --- arch/arm/mach-zynq/slcr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-zynq/slcr.c b/arch/arm/mach-zynq/slcr.c index 37707614885a..9765b3f4c2fc 100644 --- a/arch/arm/mach-zynq/slcr.c +++ b/arch/arm/mach-zynq/slcr.c @@ -213,6 +213,7 @@ int __init zynq_early_slcr_init(void) zynq_slcr_regmap = syscon_regmap_lookup_by_compatible("xlnx,zynq-slcr"); if (IS_ERR(zynq_slcr_regmap)) { pr_err("%s: failed to find zynq-slcr\n", __func__); + of_node_put(np); return -ENODEV; } From 717aa39846524ce1790f1130c4a0fc560fcecc89 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Thu, 1 Dec 2022 16:42:26 +0800 Subject: [PATCH 1507/4345] arm64: dts: mediatek: mt8183: Fix systimer 13 MHz clock description [ Upstream commit ce8a06b5bac75ccce99c0cf91b96b767d64f28a7 ] The systimer block derives its 13 MHz clock by dividing the main 26 MHz oscillator clock by 2 internally, not through the TOPCKGEN clock controller. On the MT8183 this divider is set either by power-on-reset or by the bootloader. The bootloader may then make the divider unconfigurable to, but can be read out by, the operating system. Making the systimer block take the 26 MHz clock directly requires changing the implementations. As an ABI compatible fix, change the input clock of the systimer block a fixed factor divide-by-2 clock that takes the 26 MHz oscillator as its input. Fixes: 5bc8e2875ffb ("arm64: dts: mt8183: add systimer0 device node") Signed-off-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221201084229.3464449-2-wenst@chromium.org Signed-off-by: Matthias Brugger Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt8183.dtsi | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi index 08a914d3a643..31bc8bae8cff 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi @@ -205,6 +205,15 @@ method = "smc"; }; + clk13m: fixed-factor-clock-13m { + compatible = "fixed-factor-clock"; + #clock-cells = <0>; + clocks = <&clk26m>; + clock-div = <2>; + clock-mult = <1>; + clock-output-names = "clk13m"; + }; + clk26m: oscillator { compatible = "fixed-clock"; #clock-cells = <0>; @@ -355,8 +364,7 @@ "mediatek,mt6765-timer"; reg = <0 0x10017000 0 0x1000>; interrupts = ; - clocks = <&topckgen CLK_TOP_CLK13M>; - clock-names = "clk13m"; + clocks = <&clk13m>; }; gce: mailbox@10238000 { From 64b69cb420c5b6a185e72fb6e685d3736734f763 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 22 Dec 2022 16:13:16 +0100 Subject: [PATCH 1508/4345] arm64: dts: qcom: sdm845-db845c: fix audio codec interrupt pin name [ Upstream commit 740862bb5f59b93efb390a417995f88a64bdc323 ] The pin config entry should have a string, not number, for the GPIO used as WCD9340 audio codec interrupt. Fixes: 89a32a4e769c ("arm64: dts: qcom: db845c: add analog audio support") Reported-by: Doug Anderson Signed-off-by: Krzysztof Kozlowski Reviewed-by: Douglas Anderson Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221222151319.122398-1-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845-db845c.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index c6691bdc8100..1e889ca932e4 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -896,7 +896,7 @@ }; wcd_intr_default: wcd_intr_default { - pins = <54>; + pins = "gpio54"; function = "gpio"; input-enable; From 2df155a114475359f3383c4547bb67a0b83147c4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 13 Dec 2022 11:19:17 +0100 Subject: [PATCH 1509/4345] arm64: dts: qcom: sc7180: correct SPMI bus address cells [ Upstream commit 1f75745537222172f84783d369bbd1fb2d4b6414 ] The SPMI bus uses two address cells and zero size cells (second reg entry - SPMI_USID - is not the size): spmi@c440000: #address-cells:0:0: 2 was expected Fixes: 0f9dc5f09fbd ("arm64: dts: qcom: sc7180: Add SPMI PMIC arbiter device") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221213101921.47924-1-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sc7180.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index c71f3afc1cc9..eb07a882d43b 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -3066,8 +3066,8 @@ interrupts-extended = <&pdc 1 IRQ_TYPE_LEVEL_HIGH>; qcom,ee = <0>; qcom,channel = <0>; - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <0>; interrupt-controller; #interrupt-cells = <4>; cell-index = <0>; From 8303a34fce2ae22381d4a2dae0806bc75b707693 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Wed, 11 Jan 2023 22:13:48 +0100 Subject: [PATCH 1510/4345] arm64: dts: meson-gx: Fix Ethernet MAC address unit name [ Upstream commit 8ed5310356bfa47cc6bb4221ae6b21258c52e3d1 ] Unit names should use hyphens instead of underscores to not cause warnings. Fixes: bfe59f92d306 ("ARM64: dts: amlogic: gxbb: Enable NVMEM") Suggested-by: Vyacheslav Bocharov Signed-off-by: Martin Blumenstingl Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20230111211350.1461860-5-martin.blumenstingl@googlemail.com Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gx.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 88a7db5c55a0..46018df13cc2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -226,7 +226,7 @@ reg = <0x14 0x10>; }; - eth_mac: eth_mac@34 { + eth_mac: eth-mac@34 { reg = <0x34 0x10>; }; From bd55aa16bf34231e128d1f1540a29bf27d6df7e6 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Wed, 11 Jan 2023 22:13:49 +0100 Subject: [PATCH 1511/4345] arm64: dts: meson-g12a: Fix internal Ethernet PHY unit name [ Upstream commit e7303651bbc76c848007f1cfac1fbeaa65f600d1 ] Documentation/devicetree/bindings/net/ethernet-phy.yaml defines that the node name for Ethernet PHYs should match the following pattern: ^ethernet-phy(@[a-f0-9]+)?$ Replace the underscore with a hyphen to adhere to this binding. Fixes: 280c17df8fbf ("arm64: dts: meson: g12a: add mdio multiplexer") Signed-off-by: Martin Blumenstingl Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20230111211350.1461860-6-martin.blumenstingl@googlemail.com Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index 2091db7c9b8a..c0defb36592d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -1727,7 +1727,7 @@ #address-cells = <1>; #size-cells = <0>; - internal_ephy: ethernet_phy@8 { + internal_ephy: ethernet-phy@8 { compatible = "ethernet-phy-id0180.3301", "ethernet-phy-ieee802.3-c22"; interrupts = ; From 5633e86cce6a653d69919a2a8827d2911d16fa09 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Wed, 11 Jan 2023 22:13:50 +0100 Subject: [PATCH 1512/4345] arm64: dts: meson-gx: Fix the SCPI DVFS node name and unit address [ Upstream commit f189c869ad92787ddd753558bcbae89d75825bb6 ] Node names should be generic and use hyphens instead of underscores to not cause warnings. Also nodes without a reg property should not have a unit-address. Change the scpi_dvfs node to use clock-controller as node name without a unit address (since it does not have a reg property). Fixes: 70db166a2baa ("ARM64: dts: meson-gxbb: Add SCPI with cpufreq & sensors Nodes") Signed-off-by: Martin Blumenstingl Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20230111211350.1461860-7-martin.blumenstingl@googlemail.com Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gx.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 46018df13cc2..85f4876c509a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -243,7 +243,7 @@ scpi_clocks: clocks { compatible = "arm,scpi-clocks"; - scpi_dvfs: scpi_clocks@0 { + scpi_dvfs: clock-controller { compatible = "arm,scpi-dvfs-clocks"; #clock-cells = <1>; clock-indices = <0>; From 7ee2ca51e35715fafd4ad27dc2eb2129055efdae Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Sun, 8 Jan 2023 14:04:40 +0100 Subject: [PATCH 1513/4345] arm64: dts: qcom: ipq8074: correct USB3 QMP PHY-s clock output names [ Upstream commit 877cff3568c0f54511d77918ae16b2d6e9a0dfce ] It seems that clock-output-names for the USB3 QMP PHY-s where set without actually checking what is the GCC clock driver expecting, so clock core could never actually find the parents for usb0_pipe_clk_src and usb1_pipe_clk_src clocks in the GCC driver. So, correct the names to be what the driver expects so that parenting works. Before: gcc_usb0_pipe_clk_src 0 0 0 125000000 0 0 50000 Y gcc_usb1_pipe_clk_src 0 0 0 125000000 0 0 50000 Y After: usb3phy_0_cc_pipe_clk 1 1 0 125000000 0 0 50000 Y usb0_pipe_clk_src 1 1 0 125000000 0 0 50000 Y gcc_usb0_pipe_clk 1 1 0 125000000 0 0 50000 Y usb3phy_1_cc_pipe_clk 1 1 0 125000000 0 0 50000 Y usb1_pipe_clk_src 1 1 0 125000000 0 0 50000 Y gcc_usb1_pipe_clk 1 1 0 125000000 0 0 50000 Y Fixes: 5e09bc51d07b ("arm64: dts: ipq8074: enable USB support") Signed-off-by: Robert Marko Reviewed-by: Dmitry Baryshkov Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230108130440.670181-2-robimarko@gmail.com Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 99e2488b92dc..9114402c044b 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -108,7 +108,7 @@ #phy-cells = <0>; clocks = <&gcc GCC_USB1_PIPE_CLK>; clock-names = "pipe0"; - clock-output-names = "gcc_usb1_pipe_clk_src"; + clock-output-names = "usb3phy_1_cc_pipe_clk"; }; }; @@ -151,7 +151,7 @@ #phy-cells = <0>; clocks = <&gcc GCC_USB0_PIPE_CLK>; clock-names = "pipe0"; - clock-output-names = "gcc_usb0_pipe_clk_src"; + clock-output-names = "usb3phy_0_cc_pipe_clk"; }; }; From 8f1cb871f948f616af395c18f34ae1479806d1cd Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Wed, 29 Sep 2021 11:42:51 +0800 Subject: [PATCH 1514/4345] arm64: dts: qcom: Fix IPQ8074 PCIe PHY nodes [ Upstream commit 942bcd33ed455ad40b71a59901bd926bbf4a500e ] IPQ8074 PCIe PHY nodes are broken in the many ways: - '#address-cells', '#size-cells' and 'ranges' are missing. - Child phy/lane node is missing, and the child properties like '#phy-cells' and 'clocks' are mistakenly put into parent node. - The clocks properties for parent node are missing. Fix them to get the nodes comply with the bindings schema. Signed-off-by: Shawn Guo Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210929034253.24570-9-shawn.guo@linaro.org Stable-dep-of: 7ba33591b45f ("arm64: dts: qcom: ipq8074: fix Gen3 PCIe QMP PHY") Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 46 +++++++++++++++++++++------ 1 file changed, 36 insertions(+), 10 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 9114402c044b..5b17dbefe5cf 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -167,34 +167,60 @@ resets = <&gcc GCC_QUSB2_0_PHY_BCR>; }; - pcie_phy0: phy@86000 { + pcie_qmp0: phy@86000 { compatible = "qcom,ipq8074-qmp-pcie-phy"; reg = <0x00086000 0x1000>; - #phy-cells = <0>; - clocks = <&gcc GCC_PCIE0_PIPE_CLK>; - clock-names = "pipe_clk"; - clock-output-names = "pcie20_phy0_pipe_clk"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + clocks = <&gcc GCC_PCIE0_AUX_CLK>, + <&gcc GCC_PCIE0_AHB_CLK>; + clock-names = "aux", "cfg_ahb"; resets = <&gcc GCC_PCIE0_PHY_BCR>, <&gcc GCC_PCIE0PHY_PHY_BCR>; reset-names = "phy", "common"; status = "disabled"; + + pcie_phy0: phy@86200 { + reg = <0x86200 0x16c>, + <0x86400 0x200>, + <0x86800 0x4f4>; + #phy-cells = <0>; + #clock-cells = <0>; + clocks = <&gcc GCC_PCIE0_PIPE_CLK>; + clock-names = "pipe0"; + clock-output-names = "pcie_0_pipe_clk"; + }; }; - pcie_phy1: phy@8e000 { + pcie_qmp1: phy@8e000 { compatible = "qcom,ipq8074-qmp-pcie-phy"; reg = <0x0008e000 0x1000>; - #phy-cells = <0>; - clocks = <&gcc GCC_PCIE1_PIPE_CLK>; - clock-names = "pipe_clk"; - clock-output-names = "pcie20_phy1_pipe_clk"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + clocks = <&gcc GCC_PCIE1_AUX_CLK>, + <&gcc GCC_PCIE1_AHB_CLK>; + clock-names = "aux", "cfg_ahb"; resets = <&gcc GCC_PCIE1_PHY_BCR>, <&gcc GCC_PCIE1PHY_PHY_BCR>; reset-names = "phy", "common"; status = "disabled"; + + pcie_phy1: phy@8e200 { + reg = <0x8e200 0x16c>, + <0x8e400 0x200>, + <0x8e800 0x4f4>; + #phy-cells = <0>; + #clock-cells = <0>; + clocks = <&gcc GCC_PCIE1_PIPE_CLK>; + clock-names = "pipe0"; + clock-output-names = "pcie_1_pipe_clk"; + }; }; tlmm: pinctrl@1000000 { From 9b5b1652e330f463f90e7a06846a750c3bc08633 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 15 Sep 2022 16:34:30 +0200 Subject: [PATCH 1515/4345] arm64: dts: qcom: ipq8074: fix PCIe PHY serdes size [ Upstream commit ed22cc93abae68f9d3fc4957c20a1d902cf28882 ] The size of the PCIe PHY serdes register region is 0x1c4 and the corresponding 'reg' property should specifically not include the adjacent regions that are defined in the child node (e.g. tx and rx). Fixes: 33057e1672fe ("ARM: dts: ipq8074: Add pcie nodes") Signed-off-by: Johan Hovold Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220915143431.19842-1-johan+linaro@kernel.org Stable-dep-of: 7ba33591b45f ("arm64: dts: qcom: ipq8074: fix Gen3 PCIe QMP PHY") Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 5b17dbefe5cf..555f633ef20e 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -169,7 +169,7 @@ pcie_qmp0: phy@86000 { compatible = "qcom,ipq8074-qmp-pcie-phy"; - reg = <0x00086000 0x1000>; + reg = <0x00086000 0x1c4>; #address-cells = <1>; #size-cells = <1>; ranges; @@ -197,7 +197,7 @@ pcie_qmp1: phy@8e000 { compatible = "qcom,ipq8074-qmp-pcie-phy"; - reg = <0x0008e000 0x1000>; + reg = <0x0008e000 0x1c4>; #address-cells = <1>; #size-cells = <1>; ranges; From 77970cf38954b790a51fcfe3bf85d487a944053f Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 13 Jan 2023 17:44:42 +0100 Subject: [PATCH 1516/4345] arm64: dts: qcom: ipq8074: fix Gen3 PCIe QMP PHY [ Upstream commit 7ba33591b45f9d547a317e42f1c2acd19c925eb6 ] IPQ8074 comes in 2 silicon versions: * v1 with 2x Gen2 PCIe ports and QMP PHY-s * v2 with 1x Gen3 and 1x Gen2 PCIe ports and QMP PHY-s v2 is the final and production version that is actually supported by the kernel, however it looks like PCIe related nodes were added for the v1 SoC. Now that we have Gen3 QMP PHY support, we can start fixing the PCIe support by fixing the Gen3 QMP PHY node first. Change the compatible to the Gen3 QMP PHY, correct the register space start and size, add the missing misc PCS register space. Fixes: 33057e1672fe ("ARM: dts: ipq8074: Add pcie nodes") Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230113164449.906002-2-robimarko@gmail.com Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 555f633ef20e..98f0001fc709 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -167,9 +167,9 @@ resets = <&gcc GCC_QUSB2_0_PHY_BCR>; }; - pcie_qmp0: phy@86000 { - compatible = "qcom,ipq8074-qmp-pcie-phy"; - reg = <0x00086000 0x1c4>; + pcie_qmp0: phy@84000 { + compatible = "qcom,ipq8074-qmp-gen3-pcie-phy"; + reg = <0x00084000 0x1bc>; #address-cells = <1>; #size-cells = <1>; ranges; @@ -183,10 +183,11 @@ "common"; status = "disabled"; - pcie_phy0: phy@86200 { - reg = <0x86200 0x16c>, - <0x86400 0x200>, - <0x86800 0x4f4>; + pcie_phy0: phy@84200 { + reg = <0x84200 0x16c>, + <0x84400 0x200>, + <0x84800 0x1f0>, + <0x84c00 0xf4>; #phy-cells = <0>; #clock-cells = <0>; clocks = <&gcc GCC_PCIE0_PIPE_CLK>; From e839d027d71a8f20ba4218dd039c6d28431ccd27 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 13 Jan 2023 17:44:43 +0100 Subject: [PATCH 1517/4345] arm64: dts: qcom: ipq8074: correct Gen2 PCIe ranges [ Upstream commit 2055cb7dccea16bafa3adf9c5e3216949512c34a ] Current ranges property set in Gen2 PCIe node is incorrect, replace it with the downstream 5.4 QCA kernel value. Fixes: 33057e1672fe ("ARM: dts: ipq8074: Add pcie nodes") Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230113164449.906002-3-robimarko@gmail.com Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 98f0001fc709..1dbae9c73c59 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -610,9 +610,9 @@ phy-names = "pciephy"; ranges = <0x81000000 0 0x10200000 0x10200000 - 0 0x100000 /* downstream I/O */ - 0x82000000 0 0x10300000 0x10300000 - 0 0xd00000>; /* non-prefetchable memory */ + 0 0x10000>, /* downstream I/O */ + <0x82000000 0 0x10220000 0x10220000 + 0 0xfde0000>; /* non-prefetchable memory */ interrupts = ; interrupt-names = "msi"; From 192cb335d89b9bb6fdc96f1108916a9ac5235054 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 13 Jan 2023 17:44:48 +0100 Subject: [PATCH 1518/4345] arm64: dts: qcom: ipq8074: fix Gen3 PCIe node [ Upstream commit 3e83a9c41ab0244a45a4a2800b9adb8de0d15f82 ] IPQ8074 comes in 2 silicon versions: * v1 with 2x Gen2 PCIe ports and QMP PHY-s * v2 with 1x Gen3 and 1x Gen2 PCIe ports and QMP PHY-s v2 is the final and production version that is actually supported by the kernel, however it looks like PCIe related nodes were added for the v1 SoC. Finish the PCIe fixup by using the correct compatible, adding missing ATU register space, declaring max-link-speed, use correct ranges, add missing clocks and resets. Fixes: 33057e1672fe ("ARM: dts: ipq8074: Add pcie nodes") Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230113164449.906002-8-robimarko@gmail.com Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 30 +++++++++++++++------------ 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 1dbae9c73c59..4ef364c01012 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -655,16 +655,18 @@ }; pcie0: pci@20000000 { - compatible = "qcom,pcie-ipq8074"; + compatible = "qcom,pcie-ipq8074-gen3"; reg = <0x20000000 0xf1d>, <0x20000f20 0xa8>, - <0x00080000 0x2000>, + <0x20001000 0x1000>, + <0x00080000 0x4000>, <0x20100000 0x1000>; - reg-names = "dbi", "elbi", "parf", "config"; + reg-names = "dbi", "elbi", "atu", "parf", "config"; device_type = "pci"; linux,pci-domain = <0>; bus-range = <0x00 0xff>; num-lanes = <1>; + max-link-speed = <3>; #address-cells = <3>; #size-cells = <2>; @@ -672,9 +674,9 @@ phy-names = "pciephy"; ranges = <0x81000000 0 0x20200000 0x20200000 - 0 0x100000 /* downstream I/O */ - 0x82000000 0 0x20300000 0x20300000 - 0 0xd00000>; /* non-prefetchable memory */ + 0 0x10000>, /* downstream I/O */ + <0x82000000 0 0x20220000 0x20220000 + 0 0xfde0000>; /* non-prefetchable memory */ interrupts = ; interrupt-names = "msi"; @@ -692,28 +694,30 @@ clocks = <&gcc GCC_SYS_NOC_PCIE0_AXI_CLK>, <&gcc GCC_PCIE0_AXI_M_CLK>, <&gcc GCC_PCIE0_AXI_S_CLK>, - <&gcc GCC_PCIE0_AHB_CLK>, - <&gcc GCC_PCIE0_AUX_CLK>; - + <&gcc GCC_PCIE0_AXI_S_BRIDGE_CLK>, + <&gcc GCC_PCIE0_RCHNG_CLK>; clock-names = "iface", "axi_m", "axi_s", - "ahb", - "aux"; + "axi_bridge", + "rchng"; + resets = <&gcc GCC_PCIE0_PIPE_ARES>, <&gcc GCC_PCIE0_SLEEP_ARES>, <&gcc GCC_PCIE0_CORE_STICKY_ARES>, <&gcc GCC_PCIE0_AXI_MASTER_ARES>, <&gcc GCC_PCIE0_AXI_SLAVE_ARES>, <&gcc GCC_PCIE0_AHB_ARES>, - <&gcc GCC_PCIE0_AXI_MASTER_STICKY_ARES>; + <&gcc GCC_PCIE0_AXI_MASTER_STICKY_ARES>, + <&gcc GCC_PCIE0_AXI_SLAVE_STICKY_ARES>; reset-names = "pipe", "sleep", "sticky", "axi_m", "axi_s", "ahb", - "axi_m_sticky"; + "axi_m_sticky", + "axi_s_sticky"; status = "disabled"; }; }; From c56595b948ad42de867c9e64e3540b151e7c77dc Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 13 Jan 2023 17:44:49 +0100 Subject: [PATCH 1519/4345] arm64: dts: qcom: ipq8074: correct PCIe QMP PHY output clock names [ Upstream commit 0e8b90c0256cf9c9589e2cee517dedc987a34355 ] Current PCIe QMP PHY output name were changed in ("arm64: dts: qcom: Fix IPQ8074 PCIe PHY nodes") however it did not account for the fact that GCC driver is relying on the old names to match them as they are being used as the parent for the gcc_pcie0_pipe_clk and gcc_pcie1_pipe_clk. This broke parenting as GCC could not find the parent clock, so fix it by changing to the names that driver is expecting. Fixes: 942bcd33ed45 ("arm64: dts: qcom: Fix IPQ8074 PCIe PHY nodes") Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230113164449.906002-9-robimarko@gmail.com Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 4ef364c01012..25f78c71e010 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -192,7 +192,7 @@ #clock-cells = <0>; clocks = <&gcc GCC_PCIE0_PIPE_CLK>; clock-names = "pipe0"; - clock-output-names = "pcie_0_pipe_clk"; + clock-output-names = "pcie20_phy0_pipe_clk"; }; }; @@ -220,7 +220,7 @@ #clock-cells = <0>; clocks = <&gcc GCC_PCIE1_PIPE_CLK>; clock-names = "pipe0"; - clock-output-names = "pcie_1_pipe_clk"; + clock-output-names = "pcie20_phy1_pipe_clk"; }; }; From 1fa673af0af8f70f244d3c534b361898e2960ab3 Mon Sep 17 00:00:00 2001 From: Christian Hewitt Date: Thu, 19 Jan 2023 05:30:31 +0000 Subject: [PATCH 1520/4345] arm64: dts: meson: remove CPU opps below 1GHz for G12A boards [ Upstream commit 3cbd431c2b34d84605d358c8c57654193fd661fb ] Amlogic G12A devices experience CPU stalls and random board wedges when the system idles and CPU cores clock down to lower opp points. Recent vendor kernels include a change to remove 100-250MHz and other distro sources also remove the 500/667MHz points. Unless all 100-667Mhz opps are removed or the CPU governor forced to performance stalls are still observed, so let's remove them to improve stability and uptime. Fixes: b190056fa9ee ("arm64: dts: meson-g12a: add cpus OPP table") Signed-off-by: Christian Hewitt Link: https://lore.kernel.org/r/20230119053031.21400-1-christianshewitt@gmail.com Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-g12a.dtsi | 20 -------------------- 1 file changed, 20 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi index fb0ab27d1f64..6eaceb717d61 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi @@ -57,26 +57,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <666666666>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <731000>; From 66315db914aab58a55b3648baad645314f8993b5 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 19 Jan 2023 11:57:54 +0200 Subject: [PATCH 1521/4345] ARM: OMAP1: call platform_device_put() in error case in omap1_dm_timer_init() [ Upstream commit 0414a100d6ab32721efa70ab55524540fdfe0ede ] If platform_device_add() is not called or failed, it should call platform_device_put() in error case. Fixes: 97933d6ced60 ("ARM: OMAP1: dmtimer: conversion to platform devices") Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Message-Id: <20220701094602.2365099-1-yangyingliang@huawei.com> Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- arch/arm/mach-omap1/timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-omap1/timer.c b/arch/arm/mach-omap1/timer.c index 97fc2096b970..05f016d5e9f6 100644 --- a/arch/arm/mach-omap1/timer.c +++ b/arch/arm/mach-omap1/timer.c @@ -165,7 +165,7 @@ err_free_pdata: kfree(pdata); err_free_pdev: - platform_device_unregister(pdev); + platform_device_put(pdev); return ret; } From 4811cfd28622d1c2f29779ba1e1554d57b7dfb24 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Jan 2023 10:02:12 +0100 Subject: [PATCH 1522/4345] ARM: s3c: fix s3c64xx_set_timer_source prototype [ Upstream commit 5bf52f5e4d12b8109f348cab60cb7d51092c4270 ] The prototype does not match the definition, as gcc-13 points out: arch/arm/mach-s3c/s3c64xx.c:169:13: error: conflicting types for 's3c64xx_set_timer_source' due to enum/integer mismatch; have 'void(unsigned int, unsigned int)' [-Werror=enum-int-mismatch] 169 | void __init s3c64xx_set_timer_source(unsigned int event, unsigned int source) | ^~~~~~~~~~~~~~~~~~~~~~~~ In file included from arch/arm/mach-s3c/s3c64xx.c:50: arch/arm/mach-s3c/s3c64xx.h:62:20: note: previous declaration of 's3c64xx_set_timer_source' with type 'void(enum s3c64xx_timer_mode, enum s3c64xx_timer_mode)' 62 | extern void __init s3c64xx_set_timer_source(enum s3c64xx_timer_mode event, | ^~~~~~~~~~~~~~~~~~~~~~~~ Fixes: 4280506ac9bb ("ARM: SAMSUNG: Move all platforms to new clocksource driver") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230118090224.2162863-1-arnd@kernel.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- arch/arm/mach-s3c/s3c64xx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-s3c/s3c64xx.c b/arch/arm/mach-s3c/s3c64xx.c index 4dfb648142f2..17f006503149 100644 --- a/arch/arm/mach-s3c/s3c64xx.c +++ b/arch/arm/mach-s3c/s3c64xx.c @@ -173,7 +173,8 @@ static struct samsung_pwm_variant s3c64xx_pwm_variant = { .tclk_mask = (1 << 7) | (1 << 6) | (1 << 5), }; -void __init s3c64xx_set_timer_source(unsigned int event, unsigned int source) +void __init s3c64xx_set_timer_source(enum s3c64xx_timer_mode event, + enum s3c64xx_timer_mode source) { s3c64xx_pwm_variant.output_mask = BIT(SAMSUNG_PWM_NUM) - 1; s3c64xx_pwm_variant.output_mask &= ~(BIT(event) | BIT(source)); From 5325b8a1208c864b8bd2a94892da6ab73543e389 Mon Sep 17 00:00:00 2001 From: Vaishnav Achath Date: Thu, 19 Jan 2023 09:56:22 +0530 Subject: [PATCH 1523/4345] arm64: dts: ti: k3-j7200: Fix wakeup pinmux range [ Upstream commit 9ae21ac445e911e3541985c20052fc05d60f6879 ] The WKUP_PADCONFIG register region in J7200 has multiple non-addressable regions, split the existing wkup_pmx region as follows to avoid the non-addressable regions and include all valid WKUP_PADCONFIG registers. Also update references to old nodes with new ones. wkup_pmx0 -> 13 pins (WKUP_PADCONFIG 0 - 12) wkup_pmx1 -> 2 pins (WKUP_PADCONFIG 14 - 15) wkup_pmx2 -> 59 pins (WKUP_PADCONFIG 26 - 84) wkup_pmx3 -> 8 pins (WKUP_PADCONFIG 93 - 100) J7200 Datasheet (Table 6-106, Section 6.4 Pin Multiplexing) : https://www.ti.com/lit/ds/symlink/dra821u.pdf Fixes: d361ed88455f ("arm64: dts: ti: Add support for J7200 SoC") Signed-off-by: Vaishnav Achath Reviewed-by: Jayesh Choudhary Signed-off-by: Vignesh Raghavendra Link: https://lore.kernel.org/r/20230119042622.22310-1-vaishnav.a@ti.com Signed-off-by: Sasha Levin --- .../dts/ti/k3-j7200-common-proc-board.dts | 2 +- .../boot/dts/ti/k3-j7200-mcu-wakeup.dtsi | 29 ++++++++++++++++++- 2 files changed, 29 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts index e8a4143e1c24..909ab6661aef 100644 --- a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts @@ -16,7 +16,7 @@ }; }; -&wkup_pmx0 { +&wkup_pmx2 { mcu_cpsw_pins_default: mcu-cpsw-pins-default { pinctrl-single,pins = < J721E_WKUP_IOPAD(0x0068, PIN_OUTPUT, 0) /* MCU_RGMII1_TX_CTL */ diff --git a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi index eb2a78a53512..7f252cc6eb37 100644 --- a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi @@ -56,7 +56,34 @@ wkup_pmx0: pinctrl@4301c000 { compatible = "pinctrl-single"; /* Proxy 0 addressing */ - reg = <0x00 0x4301c000 0x00 0x178>; + reg = <0x00 0x4301c000 0x00 0x34>; + #pinctrl-cells = <1>; + pinctrl-single,register-width = <32>; + pinctrl-single,function-mask = <0xffffffff>; + }; + + wkup_pmx1: pinctrl@0x4301c038 { + compatible = "pinctrl-single"; + /* Proxy 0 addressing */ + reg = <0x00 0x4301c038 0x00 0x8>; + #pinctrl-cells = <1>; + pinctrl-single,register-width = <32>; + pinctrl-single,function-mask = <0xffffffff>; + }; + + wkup_pmx2: pinctrl@0x4301c068 { + compatible = "pinctrl-single"; + /* Proxy 0 addressing */ + reg = <0x00 0x4301c068 0x00 0xec>; + #pinctrl-cells = <1>; + pinctrl-single,register-width = <32>; + pinctrl-single,function-mask = <0xffffffff>; + }; + + wkup_pmx3: pinctrl@0x4301c174 { + compatible = "pinctrl-single"; + /* Proxy 0 addressing */ + reg = <0x00 0x4301c174 0x00 0x20>; #pinctrl-cells = <1>; pinctrl-single,register-width = <32>; pinctrl-single,function-mask = <0xffffffff>; From 23134f7a5429153a61d976aa727a92b05b045a11 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 20 Jan 2023 16:53:54 +0100 Subject: [PATCH 1524/4345] ARM: dts: exynos: correct wr-active property in Exynos3250 Rinato [ Upstream commit d15d2a617499882971ddb773a583015bf36fa492 ] The property is wr-active: exynos3250-rinato.dtb: fimd@11c00000: i80-if-timings: 'wr-act' does not match any of the regexes: 'pinctrl-[0-9]+' Fixes: b59b3afb94d4 ("ARM: dts: add fimd device support for exynos3250-rinato") Link: https://lore.kernel.org/r/20230120155404.323386-2-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- arch/arm/boot/dts/exynos3250-rinato.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos3250-rinato.dts b/arch/arm/boot/dts/exynos3250-rinato.dts index f9e3b13d3aac..bbf01f76ce3b 100644 --- a/arch/arm/boot/dts/exynos3250-rinato.dts +++ b/arch/arm/boot/dts/exynos3250-rinato.dts @@ -249,7 +249,7 @@ i80-if-timings { cs-setup = <0>; wr-setup = <0>; - wr-act = <1>; + wr-active = <1>; wr-hold = <0>; }; }; From 14736f2eaec5e3fe812c50031400293fd11b3608 Mon Sep 17 00:00:00 2001 From: Angus Chen Date: Thu, 5 Jan 2023 14:11:23 +0800 Subject: [PATCH 1525/4345] ARM: imx: Call ida_simple_remove() for ida_simple_get [ Upstream commit ebeb49f43c8952f12aa20f03f00d7009edc2d1c5 ] The function call ida_simple_get maybe fail,we should deal with it. And if ida_simple_get success ,it need to call ida_simple_remove also. BTW,devm_kasprintf can handle id is zero for consistency. Fixes: e76bdfd7403a ("ARM: imx: Added perf functionality to mmdc driver") Signed-off-by: Angus Chen Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/mach-imx/mmdc.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c index af12668d0bf5..b9efe9da06e0 100644 --- a/arch/arm/mach-imx/mmdc.c +++ b/arch/arm/mach-imx/mmdc.c @@ -99,6 +99,7 @@ struct mmdc_pmu { cpumask_t cpu; struct hrtimer hrtimer; unsigned int active_events; + int id; struct device *dev; struct perf_event *mmdc_events[MMDC_NUM_COUNTERS]; struct hlist_node node; @@ -433,8 +434,6 @@ static enum hrtimer_restart mmdc_pmu_timer_handler(struct hrtimer *hrtimer) static int mmdc_pmu_init(struct mmdc_pmu *pmu_mmdc, void __iomem *mmdc_base, struct device *dev) { - int mmdc_num; - *pmu_mmdc = (struct mmdc_pmu) { .pmu = (struct pmu) { .task_ctx_nr = perf_invalid_context, @@ -452,15 +451,16 @@ static int mmdc_pmu_init(struct mmdc_pmu *pmu_mmdc, .active_events = 0, }; - mmdc_num = ida_simple_get(&mmdc_ida, 0, 0, GFP_KERNEL); + pmu_mmdc->id = ida_simple_get(&mmdc_ida, 0, 0, GFP_KERNEL); - return mmdc_num; + return pmu_mmdc->id; } static int imx_mmdc_remove(struct platform_device *pdev) { struct mmdc_pmu *pmu_mmdc = platform_get_drvdata(pdev); + ida_simple_remove(&mmdc_ida, pmu_mmdc->id); cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node); perf_pmu_unregister(&pmu_mmdc->pmu); iounmap(pmu_mmdc->mmdc_base); @@ -474,7 +474,6 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b { struct mmdc_pmu *pmu_mmdc; char *name; - int mmdc_num; int ret; const struct of_device_id *of_id = of_match_device(imx_mmdc_dt_ids, &pdev->dev); @@ -497,14 +496,14 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b cpuhp_mmdc_state = ret; } - mmdc_num = mmdc_pmu_init(pmu_mmdc, mmdc_base, &pdev->dev); - pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk; - if (mmdc_num == 0) - name = "mmdc"; - else - name = devm_kasprintf(&pdev->dev, - GFP_KERNEL, "mmdc%d", mmdc_num); + ret = mmdc_pmu_init(pmu_mmdc, mmdc_base, &pdev->dev); + if (ret < 0) + goto pmu_free; + name = devm_kasprintf(&pdev->dev, + GFP_KERNEL, "mmdc%d", ret); + + pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk; pmu_mmdc->devtype_data = (struct fsl_mmdc_devtype_data *)of_id->data; hrtimer_init(&pmu_mmdc->hrtimer, CLOCK_MONOTONIC, @@ -525,6 +524,7 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b pmu_register_err: pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret); + ida_simple_remove(&mmdc_ida, pmu_mmdc->id); cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node); hrtimer_cancel(&pmu_mmdc->hrtimer); pmu_free: From a7163b258ae8ab4013bb6feaca3f3c000ff210ca Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 11:34:22 +0100 Subject: [PATCH 1526/4345] arm64: dts: amlogic: meson-gx: fix SCPI clock dvfs node name [ Upstream commit 127f79212b07c5d9a6657a87e3eafdd889335814 ] Fixes: scpi: clocks: 'clock-controller' does not match any of the regexes: '^clocks-[0-9a-f]+$', 'pinctrl-[0-9]+' Link: https://lore.kernel.org/r/20230124-b4-amlogic-bindings-fixups-v1-1-44351528957e@linaro.org Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gx.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 85f4876c509a..39293450135a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -243,7 +243,7 @@ scpi_clocks: clocks { compatible = "arm,scpi-clocks"; - scpi_dvfs: clock-controller { + scpi_dvfs: clocks-0 { compatible = "arm,scpi-dvfs-clocks"; #clock-cells = <1>; clock-indices = <0>; From eb5f2c56577920f28b4defa3731b06cecc09097b Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 11:34:23 +0100 Subject: [PATCH 1527/4345] arm64: dts: amlogic: meson-axg: fix SCPI clock dvfs node name [ Upstream commit 5b7069d72f03c92a0ab919725017394ebce03a81 ] Fixes: scpi: clocks: 'clock-controller' does not match any of the regexes: '^clocks-[0-9a-f]+$', 'pinctrl-[0-9]+' Link: https://lore.kernel.org/r/20230124-b4-amlogic-bindings-fixups-v1-2-44351528957e@linaro.org Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-axg.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index 5c75fbf0d470..ddf9eb79e493 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -151,7 +151,7 @@ scpi_clocks: clocks { compatible = "arm,scpi-clocks"; - scpi_dvfs: clock-controller { + scpi_dvfs: clocks-0 { compatible = "arm,scpi-dvfs-clocks"; #clock-cells = <1>; clock-indices = <0>; From 6a46320f2ae7372003b333f45019709334405e9f Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 11:34:24 +0100 Subject: [PATCH 1528/4345] arm64: dts: amlogic: meson-gx: add missing SCPI sensors compatible [ Upstream commit 2ff650051493d5bdb6dd09d4c2850bb37db6be31 ] Fixes: scpi: sensors:compatible: 'oneOf' conditional failed, one must be fixed: ['amlogic,meson-gxbb-scpi-sensors'] is too short 'arm,scpi-sensors' was expected Link: https://lore.kernel.org/r/20230124-b4-amlogic-bindings-fixups-v1-3-44351528957e@linaro.org Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-axg.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index ddf9eb79e493..c892b252e5b0 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -160,7 +160,7 @@ }; scpi_sensors: sensors { - compatible = "amlogic,meson-gxbb-scpi-sensors"; + compatible = "amlogic,meson-gxbb-scpi-sensors", "arm,scpi-sensors"; #thermal-sensor-cells = <1>; }; }; From 436060c1b6684815eb7219ce3af034feeedbe4da Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 11:34:26 +0100 Subject: [PATCH 1529/4345] arm64: dts: amlogic: meson-gxl-s905d-sml5442tw: drop invalid clock-names property [ Upstream commit e3bd275ccbacf5eb18eaa311cea39f8bf8655feb ] Fixes: bluetooth: 'clock-names' does not match any of the regexes: 'pinctrl-[0-9]+' Link: https://lore.kernel.org/r/20230124-b4-amlogic-bindings-fixups-v1-5-44351528957e@linaro.org Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gxl-s905d-sml5442tw.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-sml5442tw.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-sml5442tw.dts index 0b95e9ecbef0..ca3fd6b67b94 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-sml5442tw.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-sml5442tw.dts @@ -75,6 +75,5 @@ enable-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>; max-speed = <2000000>; clocks = <&wifi32k>; - clock-names = "lpo"; }; }; From 1c30db46dd1d4a4f45600cc88fa92d1373855f2b Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 11:34:27 +0100 Subject: [PATCH 1530/4345] arm64: dts: amlogic: meson-gx: add missing unit address to rng node name [ Upstream commit 61ff70708b98a85516eccb3755084ac97b42cf48 ] Fixes: bus@c8834000: rng: {...} should not be valid under {'type': 'object'} Link: https://lore.kernel.org/r/20230124-b4-amlogic-bindings-fixups-v1-6-44351528957e@linaro.org Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gx.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 39293450135a..4c7131526c4d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -524,7 +524,7 @@ #size-cells = <2>; ranges = <0x0 0x0 0x0 0xc8834000 0x0 0x2000>; - hwrng: rng { + hwrng: rng@0 { compatible = "amlogic,meson-rng"; reg = <0x0 0x0 0x0 0x4>; }; From 373bb505ffe605086fa470790d806d661ac111fa Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 11:34:30 +0100 Subject: [PATCH 1531/4345] arm64: dts: amlogic: meson-gxl: add missing unit address to eth-phy-mux node name [ Upstream commit d19189f70ba596798ea49166d2d1ef36a8df5289 ] Fixes: bus@c8834000: eth-phy-mux: {...} should not be valid under {'type': 'object'} Link: https://lore.kernel.org/r/20230124-b4-amlogic-bindings-fixups-v1-9-44351528957e@linaro.org Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gxl.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index c3ac531c4f84..350022935052 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -759,7 +759,7 @@ }; }; - eth-phy-mux { + eth-phy-mux@55c { compatible = "mdio-mux-mmioreg", "mdio-mux"; #address-cells = <1>; #size-cells = <0>; From 269fd2fb043e01aaf1b59e730319397f56099edf Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 11:34:31 +0100 Subject: [PATCH 1532/4345] arm64: dts: amlogic: meson-gx-libretech-pc: fix update button name [ Upstream commit 6bb506ed36968207a8832f0143ebc127f0770eef ] Fixes: adc-keys: 'update-button' does not match any of the regexes: '^button-', 'pinctrl-[0-9]+' Link: https://lore.kernel.org/r/20230124-b4-amlogic-bindings-fixups-v1-10-44351528957e@linaro.org Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi index c2480bab8d33..27e964bfa947 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi @@ -17,7 +17,7 @@ io-channel-names = "buttons"; keyup-threshold-microvolt = <1800000>; - update-button { + button-update { label = "update"; linux,code = ; press-threshold-microvolt = <1300000>; From c39c3ed4a3b9d4f1667f7966a60b3ec6abdacf37 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 11:34:33 +0100 Subject: [PATCH 1533/4345] arm64: dts: amlogic: meson-gxl-s905d-phicomm-n1: fix led node name [ Upstream commit eee64d8fbbdaab72bbab3e462f3a7b742d20c8c2 ] Fixes: leds: status: {...} is not of type 'array' Link: https://lore.kernel.org/r/20230124-b4-amlogic-bindings-fixups-v1-12-44351528957e@linaro.org Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gxl-s905d-phicomm-n1.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-phicomm-n1.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-phicomm-n1.dts index 9ef210f17b4a..393d3cb33b9e 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-phicomm-n1.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905d-phicomm-n1.dts @@ -18,7 +18,7 @@ leds { compatible = "gpio-leds"; - status { + led { label = "n1:white:status"; gpios = <&gpio_ao GPIOAO_9 GPIO_ACTIVE_HIGH>; default-state = "on"; From 4c37a37743a6bc52e79b758599552cdb18912d82 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 24 Jan 2023 11:34:34 +0100 Subject: [PATCH 1534/4345] arm64: dts: amlogic: meson-gxbb-kii-pro: fix led node name [ Upstream commit afdef3b188c934f79ad4b0a7bd8c692742f9b5af ] Fixes: leds: status: {...} is not of type 'array' Link: https://lore.kernel.org/r/20230124-b4-amlogic-bindings-fixups-v1-13-44351528957e@linaro.org Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts index e8394a8269ee..802faf7e4e3c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-kii-pro.dts @@ -16,7 +16,7 @@ leds { compatible = "gpio-leds"; - status { + led { gpios = <&gpio_ao GPIOAO_13 GPIO_ACTIVE_LOW>; default-state = "off"; color = ; From a451c1377aa89ab9b503b846cc1e6e434b2401d3 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Sat, 14 Jan 2023 16:56:45 -0600 Subject: [PATCH 1535/4345] arm64: dts: renesas: beacon-renesom: Fix gpio expander reference [ Upstream commit d7f9492dfc03153ac56ab59066a196558748f575 ] The board used to originally introduce the Beacon Embedded RZ/G2[M/N/H] boards had a GPIO expander with address 20, but this was changed when the final board went to production. The production boards changed both the part itself and the address. With the incorrect address, the LCD cannot come up. If the LCD fails, the rcar-du driver fails to come up, and that also breaks HDMI. Pre-release board were not shipped to the general public, so it should be safe to push this as a fix. Anyone with a production board would have video fail due to this GPIO expander change. Fixes: a1d8a344f1ca ("arm64: dts: renesas: Introduce r8a774a1-beacon-rzg2m-kit") Signed-off-by: Adam Ford Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230114225647.227972-1-aford173@gmail.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- .../dts/renesas/beacon-renesom-baseboard.dtsi | 24 ++++++++----------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/arch/arm64/boot/dts/renesas/beacon-renesom-baseboard.dtsi b/arch/arm64/boot/dts/renesas/beacon-renesom-baseboard.dtsi index 53e1d43cbecf..663adf79471b 100644 --- a/arch/arm64/boot/dts/renesas/beacon-renesom-baseboard.dtsi +++ b/arch/arm64/boot/dts/renesas/beacon-renesom-baseboard.dtsi @@ -399,20 +399,6 @@ }; }; - /* 0 - lcd_reset */ - /* 1 - lcd_pwr */ - /* 2 - lcd_select */ - /* 3 - backlight-enable */ - /* 4 - Touch_shdwn */ - /* 5 - LCD_H_pol */ - /* 6 - lcd_V_pol */ - gpio_exp1: gpio@20 { - compatible = "onnn,pca9654"; - reg = <0x20>; - gpio-controller; - #gpio-cells = <2>; - }; - touchscreen@26 { compatible = "ilitek,ili2117"; reg = <0x26>; @@ -445,6 +431,16 @@ }; }; }; + + gpio_exp1: gpio@70 { + compatible = "nxp,pca9538"; + reg = <0x70>; + gpio-controller; + #gpio-cells = <2>; + gpio-line-names = "lcd_reset", "lcd_pwr", "lcd_select", + "backlight-enable", "Touch_shdwn", + "LCD_H_pol", "lcd_V_pol"; + }; }; &lvds0 { From bbddc7c708704df61451e759bd3f530d68a86ee2 Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Sat, 31 Dec 2022 16:58:54 -0600 Subject: [PATCH 1536/4345] ARM: dts: sun8i: nanopi-duo2: Fix regulator GPIO reference [ Upstream commit 2177d4ae971f79b4a9a3c411f2fb8ae6113d1430 ] The property named in the schema is 'enable-gpios', not 'enable-gpio'. This makes no difference at runtime, because the regulator is marked as always-on, but it breaks validation. Fixes: 4701fc6e5dd9 ("ARM: dts: sun8i: add FriendlyARM NanoPi Duo2") Reviewed-by: Andre Przywara Acked-by: Jernej Skrabec Signed-off-by: Samuel Holland Link: https://lore.kernel.org/r/20221231225854.16320-2-samuel@sholland.org Signed-off-by: Jernej Skrabec Signed-off-by: Sasha Levin --- arch/arm/boot/dts/sun8i-h3-nanopi-duo2.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun8i-h3-nanopi-duo2.dts b/arch/arm/boot/dts/sun8i-h3-nanopi-duo2.dts index 6b149271ef13..8722fdf77ebc 100644 --- a/arch/arm/boot/dts/sun8i-h3-nanopi-duo2.dts +++ b/arch/arm/boot/dts/sun8i-h3-nanopi-duo2.dts @@ -57,7 +57,7 @@ regulator-ramp-delay = <50>; /* 4ms */ enable-active-high; - enable-gpio = <&r_pio 0 8 GPIO_ACTIVE_HIGH>; /* PL8 */ + enable-gpios = <&r_pio 0 8 GPIO_ACTIVE_HIGH>; /* PL8 */ gpios = <&r_pio 0 6 GPIO_ACTIVE_HIGH>; /* PL6 */ gpios-states = <0x1>; states = <1100000 0>, <1300000 1>; From e874629c5fb77ac1a09190f0c2352791f5f8e844 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Fri, 23 Dec 2022 11:04:33 +0800 Subject: [PATCH 1537/4345] ARM: dts: imx7s: correct iomuxc gpr mux controller cells [ Upstream commit 0e3e1946606a2919b1dda9967ab2e1c5af2fedd6 ] Per binding doc reg-mux.yaml, the #mux-control-cells should be 1 Signed-off-by: Peng Fan Reviewed-by: Marco Felsch Fixes: 94a905a79f2c ("ARM: dts: imx7s: add multiplexer controls") Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx7s.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 9e1b0af0aa43..43b39ad9ddce 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -494,7 +494,7 @@ mux: mux-controller { compatible = "mmio-mux"; - #mux-control-cells = <0>; + #mux-control-cells = <1>; mux-reg-masks = <0x14 0x00000010>; }; From d7cf3864d781469cb8b323c6d8606890758afaee Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 28 Nov 2022 12:20:27 +0100 Subject: [PATCH 1538/4345] arm64: dts: mediatek: mt7622: Add missing pwm-cells to pwm node [ Upstream commit 22925af785fa3470efdf566339616d801119d348 ] Specify #pwm-cells on pwm@11006000 to make it actually usable. Fixes: ae457b7679c4 ("arm64: dts: mt7622: add SoC and peripheral related device nodes") Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221128112028.58021-2-angelogioacchino.delregno@collabora.com Signed-off-by: Matthias Brugger Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/mediatek/mt7622.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 7c6d871538a6..884930a5849a 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -428,6 +428,7 @@ pwm: pwm@11006000 { compatible = "mediatek,mt7622-pwm"; reg = <0 0x11006000 0 0x1000>; + #pwm-cells = <2>; interrupts = ; clocks = <&topckgen CLK_TOP_PWM_SEL>, <&pericfg CLK_PERI_PWM_PD>, From 12bcc4ec54967c3169e702d1179c2b618039e4b5 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Wed, 18 Jan 2023 17:37:13 +0800 Subject: [PATCH 1539/4345] blk-mq: avoid sleep in blk_mq_alloc_request_hctx [ Upstream commit 6ee858a3d3270a68902d66bb47c151a83622535c ] Commit 1f5bd336b9150 ("blk-mq: add blk_mq_alloc_request_hctx") add blk_mq_alloc_request_hctx to send commands to a specific queue. If BLK_MQ_REQ_NOWAIT is not set in tag allocation, we may change to different hctx after sleep and get tag from unexpected hctx. So BLK_MQ_REQ_NOWAIT must be set in flags for blk_mq_alloc_request_hctx. After commit 600c3b0cea784 ("blk-mq: open code __blk_mq_alloc_request in blk_mq_alloc_request_hctx"), blk_mq_alloc_request_hctx return -EINVAL if both BLK_MQ_REQ_NOWAIT and BLK_MQ_REQ_RESERVED are not set instead of if BLK_MQ_REQ_NOWAIT is not set. So if BLK_MQ_REQ_NOWAIT is not set and BLK_MQ_REQ_RESERVED is set, blk_mq_alloc_request_hctx could alloc tag from unexpected hctx. I guess what we need here is that return -EINVAL if either BLK_MQ_REQ_NOWAIT or BLK_MQ_REQ_RESERVED is not set. Currently both BLK_MQ_REQ_NOWAIT and BLK_MQ_REQ_RESERVED will be set if specific hctx is needed in nvme_auth_submit, nvmf_connect_io_queue and nvmf_connect_admin_queue. Fix the potential BLK_MQ_REQ_NOWAIT missed case in future. Fixes: 600c3b0cea78 ("blk-mq: open code __blk_mq_alloc_request in blk_mq_alloc_request_hctx") Reviewed-by: Christoph Hellwig Signed-off-by: Kemeng Shi Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-mq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index e37ba792902a..cf66de0f00fd 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -448,7 +448,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, * allocator for this for the rare use case of a command tied to * a specific queue. */ - if (WARN_ON_ONCE(!(flags & (BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED)))) + if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)) || + WARN_ON_ONCE(!(flags & BLK_MQ_REQ_RESERVED))) return ERR_PTR(-EINVAL); if (hctx_idx >= q->nr_hw_queues) From 2c58012d9656491392cdf60191492874c11ecc43 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Wed, 18 Jan 2023 17:37:14 +0800 Subject: [PATCH 1540/4345] blk-mq: remove stale comment for blk_mq_sched_mark_restart_hctx [ Upstream commit c31e76bcc379182fe67a82c618493b7b8868c672 ] Commit 97889f9ac24f8 ("blk-mq: remove synchronize_rcu() from blk_mq_del_queue_tag_set()") remove handle of TAG_SHARED in restart, then shared_hctx_restart counted for how many hardware queues are marked for restart is removed too. Remove the stale comment that we still count hardware queues need restart. Fixes: 97889f9ac24f ("blk-mq: remove synchronize_rcu() from blk_mq_del_queue_tag_set()") Reviewed-by: Christoph Hellwig Signed-off-by: Kemeng Shi Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-mq-sched.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 72e64ba661fc..862acb5a8452 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -45,8 +45,7 @@ void blk_mq_sched_assign_ioc(struct request *rq) } /* - * Mark a hardware queue as needing a restart. For shared queues, maintain - * a count of how many hardware queues are marked for restart. + * Mark a hardware queue as needing a restart. */ void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) { From a33c33593b66d37d3eb4027a4f03645bde31262e Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Wed, 18 Jan 2023 17:37:26 +0800 Subject: [PATCH 1541/4345] blk-mq: correct stale comment of .get_budget [ Upstream commit 01542f651a9f58a9b176c3d3dc3eefbacee53b78 ] Commit 88022d7201e96 ("blk-mq: don't handle failure in .get_budget") remove BLK_STS_RESOURCE return value and we only check if we can get the budget from .get_budget() now. Correct stale comment that ".get_budget() returns BLK_STS_NO_RESOURCE" to ".get_budget() fails to get the budget". Fixes: 88022d7201e9 ("blk-mq: don't handle failure in .get_budget") Signed-off-by: Kemeng Shi Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-mq-sched.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 862acb5a8452..7858c5a3535e 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -109,7 +109,7 @@ dispatch: /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to - * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. + * restart queue if .get_budget() fails to get the budget. * * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. @@ -223,7 +223,7 @@ static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx, /* * Only SCSI implements .get_budget and .put_budget, and SCSI restarts * its queue by itself in its completion handler, so we don't need to - * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. + * restart queue if .get_budget() fails to get the budget. * * Returns -EAGAIN if hctx->dispatch was found non-empty and run_work has to * be run again. This is necessary to avoid starving flushes. From 72aebdac390bf0dc04c0385d2db7ee522f4ffa3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=C3=B6ppner?= Date: Thu, 8 Oct 2020 15:13:35 +0200 Subject: [PATCH 1542/4345] s390/dasd: Prepare for additional path event handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b72949328869dfd45f6452c2410647afd7db5f1a ] As more path events need to be handled for ECKD the current path verification infrastructure can be reused. Rename all path verifcation code to fit the more broadly based task of path event handling and put the path verification in a new separate function. Signed-off-by: Jan Höppner Signed-off-by: Stefan Haberland Reviewed-by: Stefan Haberland Reviewed-by: Cornelia Huck Signed-off-by: Jens Axboe Stable-dep-of: 460e9bed82e4 ("s390/dasd: Fix potential memleak in dasd_eckd_init()") Signed-off-by: Sasha Levin --- drivers/s390/block/dasd.c | 4 +- drivers/s390/block/dasd_eckd.c | 78 +++++++++++++++++++--------------- drivers/s390/block/dasd_int.h | 1 + 3 files changed, 47 insertions(+), 36 deletions(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index f4edfe383e9d..9f26f55e4988 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2128,8 +2128,8 @@ static void __dasd_device_check_path_events(struct dasd_device *device) if (device->stopped & ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM)) return; - rc = device->discipline->verify_path(device, - dasd_path_get_tbvpm(device)); + rc = device->discipline->pe_handler(device, + dasd_path_get_tbvpm(device)); if (rc) dasd_device_set_timer(device, 50); else diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 53d22975a32f..d1429936f38c 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -103,7 +103,7 @@ struct ext_pool_exhaust_work_data { }; /* definitions for the path verification worker */ -struct path_verification_work_data { +struct pe_handler_work_data { struct work_struct worker; struct dasd_device *device; struct dasd_ccw_req cqr; @@ -112,8 +112,8 @@ struct path_verification_work_data { int isglobal; __u8 tbvpm; }; -static struct path_verification_work_data *path_verification_worker; -static DEFINE_MUTEX(dasd_path_verification_mutex); +static struct pe_handler_work_data *pe_handler_worker; +static DEFINE_MUTEX(dasd_pe_handler_mutex); struct check_attention_work_data { struct work_struct worker; @@ -1219,7 +1219,7 @@ static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm) } static int rebuild_device_uid(struct dasd_device *device, - struct path_verification_work_data *data) + struct pe_handler_work_data *data) { struct dasd_eckd_private *private = device->private; __u8 lpm, opm = dasd_path_get_opm(device); @@ -1257,10 +1257,9 @@ static int rebuild_device_uid(struct dasd_device *device, return rc; } -static void do_path_verification_work(struct work_struct *work) +static void dasd_eckd_path_available_action(struct dasd_device *device, + struct pe_handler_work_data *data) { - struct path_verification_work_data *data; - struct dasd_device *device; struct dasd_eckd_private path_private; struct dasd_uid *uid; __u8 path_rcd_buf[DASD_ECKD_RCD_DATA_SIZE]; @@ -1269,19 +1268,6 @@ static void do_path_verification_work(struct work_struct *work) char print_uid[60]; int rc; - data = container_of(work, struct path_verification_work_data, worker); - device = data->device; - - /* delay path verification until device was resumed */ - if (test_bit(DASD_FLAG_SUSPENDED, &device->flags)) { - schedule_work(work); - return; - } - /* check if path verification already running and delay if so */ - if (test_and_set_bit(DASD_FLAG_PATH_VERIFY, &device->flags)) { - schedule_work(work); - return; - } opm = 0; npm = 0; ppm = 0; @@ -1418,30 +1404,54 @@ static void do_path_verification_work(struct work_struct *work) dasd_path_add_nohpfpm(device, hpfpm); spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); } +} + +static void do_pe_handler_work(struct work_struct *work) +{ + struct pe_handler_work_data *data; + struct dasd_device *device; + + data = container_of(work, struct pe_handler_work_data, worker); + device = data->device; + + /* delay path verification until device was resumed */ + if (test_bit(DASD_FLAG_SUSPENDED, &device->flags)) { + schedule_work(work); + return; + } + /* check if path verification already running and delay if so */ + if (test_and_set_bit(DASD_FLAG_PATH_VERIFY, &device->flags)) { + schedule_work(work); + return; + } + + dasd_eckd_path_available_action(device, data); + clear_bit(DASD_FLAG_PATH_VERIFY, &device->flags); dasd_put_device(device); if (data->isglobal) - mutex_unlock(&dasd_path_verification_mutex); + mutex_unlock(&dasd_pe_handler_mutex); else kfree(data); } -static int dasd_eckd_verify_path(struct dasd_device *device, __u8 lpm) +static int dasd_eckd_pe_handler(struct dasd_device *device, __u8 lpm) { - struct path_verification_work_data *data; + struct pe_handler_work_data *data; data = kmalloc(sizeof(*data), GFP_ATOMIC | GFP_DMA); if (!data) { - if (mutex_trylock(&dasd_path_verification_mutex)) { - data = path_verification_worker; + if (mutex_trylock(&dasd_pe_handler_mutex)) { + data = pe_handler_worker; data->isglobal = 1; - } else + } else { return -ENOMEM; + } } else { memset(data, 0, sizeof(*data)); data->isglobal = 0; } - INIT_WORK(&data->worker, do_path_verification_work); + INIT_WORK(&data->worker, do_pe_handler_work); dasd_get_device(device); data->device = device; data->tbvpm = lpm; @@ -6694,7 +6704,7 @@ static struct dasd_discipline dasd_eckd_discipline = { .check_device = dasd_eckd_check_characteristics, .uncheck_device = dasd_eckd_uncheck_device, .do_analysis = dasd_eckd_do_analysis, - .verify_path = dasd_eckd_verify_path, + .pe_handler = dasd_eckd_pe_handler, .basic_to_ready = dasd_eckd_basic_to_ready, .online_to_ready = dasd_eckd_online_to_ready, .basic_to_known = dasd_eckd_basic_to_known, @@ -6755,16 +6765,16 @@ dasd_eckd_init(void) GFP_KERNEL | GFP_DMA); if (!dasd_vol_info_req) return -ENOMEM; - path_verification_worker = kmalloc(sizeof(*path_verification_worker), - GFP_KERNEL | GFP_DMA); - if (!path_verification_worker) { + pe_handler_worker = kmalloc(sizeof(*pe_handler_worker), + GFP_KERNEL | GFP_DMA); + if (!pe_handler_worker) { kfree(dasd_reserve_req); kfree(dasd_vol_info_req); return -ENOMEM; } rawpadpage = (void *)__get_free_page(GFP_KERNEL); if (!rawpadpage) { - kfree(path_verification_worker); + kfree(pe_handler_worker); kfree(dasd_reserve_req); kfree(dasd_vol_info_req); return -ENOMEM; @@ -6773,7 +6783,7 @@ dasd_eckd_init(void) if (!ret) wait_for_device_probe(); else { - kfree(path_verification_worker); + kfree(pe_handler_worker); kfree(dasd_reserve_req); kfree(dasd_vol_info_req); free_page((unsigned long)rawpadpage); @@ -6785,7 +6795,7 @@ static void __exit dasd_eckd_cleanup(void) { ccw_driver_unregister(&dasd_eckd_driver); - kfree(path_verification_worker); + kfree(pe_handler_worker); kfree(dasd_reserve_req); free_page((unsigned long)rawpadpage); } diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 9d9685c25253..e8a06d85d6f7 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -299,6 +299,7 @@ struct dasd_discipline { * configuration. */ int (*verify_path)(struct dasd_device *, __u8); + int (*pe_handler)(struct dasd_device *, __u8); /* * Last things to do when a device is set online, and first things From a50e28d433acf22258f9f34831057387f04ef074 Mon Sep 17 00:00:00 2001 From: Qiheng Lin Date: Fri, 10 Feb 2023 01:02:53 +0100 Subject: [PATCH 1543/4345] s390/dasd: Fix potential memleak in dasd_eckd_init() [ Upstream commit 460e9bed82e49db1b823dcb4e421783854d86c40 ] `dasd_reserve_req` is allocated before `dasd_vol_info_req`, and it also needs to be freed before the error returns, just like the other cases in this function. Fixes: 9e12e54c7a8f ("s390/dasd: Handle out-of-space constraint") Signed-off-by: Qiheng Lin Link: https://lore.kernel.org/r/20221208133809.16796-1-linqiheng@huawei.com Signed-off-by: Stefan Haberland Link: https://lore.kernel.org/r/20230210000253.1644903-3-sth@linux.ibm.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/s390/block/dasd_eckd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index d1429936f38c..c6930c159d2a 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -6763,8 +6763,10 @@ dasd_eckd_init(void) return -ENOMEM; dasd_vol_info_req = kmalloc(sizeof(*dasd_vol_info_req), GFP_KERNEL | GFP_DMA); - if (!dasd_vol_info_req) + if (!dasd_vol_info_req) { + kfree(dasd_reserve_req); return -ENOMEM; + } pe_handler_worker = kmalloc(sizeof(*pe_handler_worker), GFP_KERNEL | GFP_DMA); if (!pe_handler_worker) { From 53dbbe36340d602017b435e67c3ce5f80ab9df98 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Wed, 2 Mar 2022 19:34:33 +0100 Subject: [PATCH 1544/4345] sched/deadline,rt: Remove unused parameter from pick_next_[rt|dl]_entity() [ Upstream commit 821aecd09e5ad2f8d4c3d8195333d272b392f7d3 ] The `struct rq *rq` parameter isn't used. Remove it. Signed-off-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Juri Lelli Link: https://lore.kernel.org/r/20220302183433.333029-7-dietmar.eggemann@arm.com Stable-dep-of: 7c4a5b89a0b5 ("sched/rt: pick_next_rt_entity(): check list_entry") Signed-off-by: Sasha Levin --- kernel/sched/deadline.c | 5 ++--- kernel/sched/rt.c | 5 ++--- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index aaf98771f935..f59cb3e8a613 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1847,8 +1847,7 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first) deadline_queue_push_tasks(rq); } -static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, - struct dl_rq *dl_rq) +static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq) { struct rb_node *left = rb_first_cached(&dl_rq->root); @@ -1867,7 +1866,7 @@ static struct task_struct *pick_next_task_dl(struct rq *rq) if (!sched_dl_runnable(rq)) return NULL; - dl_se = pick_next_dl_entity(rq, dl_rq); + dl_se = pick_next_dl_entity(dl_rq); BUG_ON(!dl_se); p = dl_task_of(dl_se); set_next_task_dl(rq, p, true); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e6f22836c600..e1ce5d1868b5 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1605,8 +1605,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool f rt_queue_push_tasks(rq); } -static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, - struct rt_rq *rt_rq) +static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq) { struct rt_prio_array *array = &rt_rq->active; struct sched_rt_entity *next = NULL; @@ -1628,7 +1627,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) struct rt_rq *rt_rq = &rq->rt; do { - rt_se = pick_next_rt_entity(rq, rt_rq); + rt_se = pick_next_rt_entity(rt_rq); BUG_ON(!rt_se); rt_rq = group_rt_rq(rt_se); } while (rt_rq); From 80a1751730b302d8ab63a084b2fa52c820ad0273 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Mon, 6 Feb 2023 22:33:54 +0000 Subject: [PATCH 1545/4345] sched/rt: pick_next_rt_entity(): check list_entry [ Upstream commit 7c4a5b89a0b5a57a64b601775b296abf77a9fe97 ] Commit 326587b84078 ("sched: fix goto retry in pick_next_task_rt()") removed any path which could make pick_next_rt_entity() return NULL. However, BUG_ON(!rt_se) in _pick_next_task_rt() (the only caller of pick_next_rt_entity()) still checks the error condition, which can never happen, since list_entry() never returns NULL. Remove the BUG_ON check, and instead emit a warning in the only possible error condition here: the queue being empty which should never happen. Fixes: 326587b84078 ("sched: fix goto retry in pick_next_task_rt()") Signed-off-by: Pietro Borrello Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Phil Auld Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20230128-list-entry-null-check-sched-v3-1-b1a71bd1ac6b@diag.uniroma1.it Signed-off-by: Sasha Levin --- kernel/sched/rt.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e1ce5d1868b5..f690f901b6cc 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1616,6 +1616,8 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq) BUG_ON(idx >= MAX_RT_PRIO); queue = array->queue + idx; + if (SCHED_WARN_ON(list_empty(queue))) + return NULL; next = list_entry(queue->next, struct sched_rt_entity, run_list); return next; @@ -1628,7 +1630,8 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) do { rt_se = pick_next_rt_entity(rt_rq); - BUG_ON(!rt_se); + if (unlikely(!rt_se)) + return NULL; rt_rq = group_rt_rq(rt_se); } while (rt_rq); From 895cb50196ab4bcd53959385aafec593bbd23755 Mon Sep 17 00:00:00 2001 From: silviazhao Date: Wed, 8 Feb 2023 16:27:22 +0800 Subject: [PATCH 1546/4345] x86/perf/zhaoxin: Add stepping check for ZXC [ Upstream commit fd636b6a9bc6034f2e5bb869658898a2b472c037 ] Some of Nano series processors will lead GP when accessing PMC fixed counter. Meanwhile, their hardware support for PMC has not announced externally. So exclude Nano CPUs from ZXC by checking stepping information. This is an unambiguous way to differentiate between ZXC and Nano CPUs. Following are Nano and ZXC FMS information: Nano FMS: Family=6, Model=F, Stepping=[0-A][C-D] ZXC FMS: Family=6, Model=F, Stepping=E-F OR Family=6, Model=0x19, Stepping=0-3 Fixes: 3a4ac121c2ca ("x86/perf: Add hardware performance events support for Zhaoxin CPU.") Reported-by: Arjan <8vvbbqzo567a@nospam.xutrox.com> Reported-by: Kevin Brace Signed-off-by: silviazhao Signed-off-by: Peter Zijlstra (Intel) Link: https://bugzilla.kernel.org/show_bug.cgi?id=212389 Signed-off-by: Sasha Levin --- arch/x86/events/zhaoxin/core.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c index e68827e604ad..e92734696030 100644 --- a/arch/x86/events/zhaoxin/core.c +++ b/arch/x86/events/zhaoxin/core.c @@ -541,7 +541,13 @@ __init int zhaoxin_pmu_init(void) switch (boot_cpu_data.x86) { case 0x06: - if (boot_cpu_data.x86_model == 0x0f || boot_cpu_data.x86_model == 0x19) { + /* + * Support Zhaoxin CPU from ZXC series, exclude Nano series through FMS. + * Nano FMS: Family=6, Model=F, Stepping=[0-A][C-D] + * ZXC FMS: Family=6, Model=F, Stepping=E-F OR Family=6, Model=0x19, Stepping=0-3 + */ + if ((boot_cpu_data.x86_model == 0x0f && boot_cpu_data.x86_stepping >= 0x0e) || + boot_cpu_data.x86_model == 0x19) { x86_pmu.max_period = x86_pmu.cntval_mask >> 1; From 0a82c1e0573b87bf32f96165a76d19e2ebd23c35 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 15 Feb 2023 12:18:01 -0500 Subject: [PATCH 1547/4345] block: bio-integrity: Copy flags when bio_integrity_payload is cloned [ Upstream commit b6a4bdcda430e3ca43bbb9cb1d4d4d34ebe15c40 ] Make sure to copy the flags when a bio_integrity_payload is cloned. Otherwise per-I/O properties such as IP checksum flag will not be passed down to the HBA driver. Since the integrity buffer is owned by the original bio, the BIP_BLOCK_INTEGRITY flag needs to be masked off to avoid a double free in the completion path. Fixes: aae7df50190a ("block: Integrity checksum flag") Fixes: b1f01388574c ("block: Relocate bio integrity flags") Reported-by: Saurav Kashyap Tested-by: Saurav Kashyap Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20230215171801.21062-1-martin.petersen@oracle.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/bio-integrity.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 4f6f140a44e0..a4cfc97275df 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -428,6 +428,7 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, bip->bip_vcnt = bip_src->bip_vcnt; bip->bip_iter = bip_src->bip_iter; + bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY; return 0; } From efc8df970561ff708379b89b348e16d3b410cc7b Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Mon, 5 Dec 2022 06:14:41 +0000 Subject: [PATCH 1548/4345] wifi: rsi: Fix memory leak in rsi_coex_attach() [ Upstream commit 956fb851a6e19da5ab491e19c1bc323bb2c2cf6f ] The coex_cb needs to be freed when rsi_create_kthread() failed in rsi_coex_attach(). Fixes: 2108df3c4b18 ("rsi: add coex support") Signed-off-by: Yuan Can Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221205061441.114632-1-yuancan@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/rsi/rsi_91x_coex.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/rsi/rsi_91x_coex.c b/drivers/net/wireless/rsi/rsi_91x_coex.c index a0c5d02ae88c..7395359b43b7 100644 --- a/drivers/net/wireless/rsi/rsi_91x_coex.c +++ b/drivers/net/wireless/rsi/rsi_91x_coex.c @@ -160,6 +160,7 @@ int rsi_coex_attach(struct rsi_common *common) rsi_coex_scheduler_thread, "Coex-Tx-Thread")) { rsi_dbg(ERR_ZONE, "%s: Unable to init tx thrd\n", __func__); + kfree(coex_cb); return -EINVAL; } return 0; From d85d0b1a6135bb218d140052e291a3f1292b976f Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 22:14:09 +0800 Subject: [PATCH 1549/4345] wifi: rtlwifi: rtl8821ae: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 106031c1f4a850915190d7ec1026696282f9359b ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. All the SKBs have been dequeued from the old queue, so it's safe to enqueue these SKBs to a free queue, then free them after spin_unlock_irqrestore() at once. Compile tested only. Fixes: 5c99f04fec93 ("rtlwifi: rtl8723be: Update driver to match Realtek release of 06/28/14") Signed-off-by: Yang Yingliang Acked-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207141411.46098-2-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c index 33ffc24d3675..c4ee65cc2d5e 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c @@ -26,8 +26,10 @@ static void _rtl8821ae_return_beacon_queue_skb(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[BEACON_QUEUE]; + struct sk_buff_head free_list; unsigned long flags; + skb_queue_head_init(&free_list); spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags); while (skb_queue_len(&ring->queue)) { struct rtl_tx_desc *entry = &ring->desc[ring->idx]; @@ -37,10 +39,12 @@ static void _rtl8821ae_return_beacon_queue_skb(struct ieee80211_hw *hw) rtlpriv->cfg->ops->get_desc(hw, (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), skb->len, DMA_TO_DEVICE); - kfree_skb(skb); + __skb_queue_tail(&free_list, skb); ring->idx = (ring->idx + 1) % ring->entries; } spin_unlock_irqrestore(&rtlpriv->locks.irq_th_lock, flags); + + __skb_queue_purge(&free_list); } static void _rtl8821ae_set_bcn_ctrl_reg(struct ieee80211_hw *hw, From 97018e737bd0d3391c3a8c6fcce652fa1dff64b7 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 22:14:10 +0800 Subject: [PATCH 1550/4345] wifi: rtlwifi: rtl8188ee: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 2611687fa7ffc84190f92292de0b80468de17220 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. All the SKBs have been dequeued from the old queue, so it's safe to enqueue these SKBs to a free queue, then free them after spin_unlock_irqrestore() at once. Compile tested only. Fixes: 7fe3b3abb5da ("rtlwifi: rtl8188ee: rtl8821ae: Fix a queue locking problem") Signed-off-by: Yang Yingliang Acked-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207141411.46098-3-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c index 63f9ea21962f..335a3c9cdbab 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c @@ -68,8 +68,10 @@ static void _rtl88ee_return_beacon_queue_skb(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[BEACON_QUEUE]; + struct sk_buff_head free_list; unsigned long flags; + skb_queue_head_init(&free_list); spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags); while (skb_queue_len(&ring->queue)) { struct rtl_tx_desc *entry = &ring->desc[ring->idx]; @@ -79,10 +81,12 @@ static void _rtl88ee_return_beacon_queue_skb(struct ieee80211_hw *hw) rtlpriv->cfg->ops->get_desc(hw, (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), skb->len, DMA_TO_DEVICE); - kfree_skb(skb); + __skb_queue_tail(&free_list, skb); ring->idx = (ring->idx + 1) % ring->entries; } spin_unlock_irqrestore(&rtlpriv->locks.irq_th_lock, flags); + + __skb_queue_purge(&free_list); } static void _rtl88ee_disable_bcn_sub_func(struct ieee80211_hw *hw) From 0e5b782c1c728546642a5d4e518a822cb7050a31 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 22:14:11 +0800 Subject: [PATCH 1551/4345] wifi: rtlwifi: rtl8723be: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 313950c2114e7051c4e3020fd82495fa1fb526a8 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. All the SKBs have been dequeued from the old queue, so it's safe to enqueue these SKBs to a free queue, then free them after spin_unlock_irqrestore() at once. Compile tested only. Fixes: 5c99f04fec93 ("rtlwifi: rtl8723be: Update driver to match Realtek release of 06/28/14") Signed-off-by: Yang Yingliang Acked-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207141411.46098-4-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c index 0748aedce2ad..ccbb082d5e92 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c @@ -30,8 +30,10 @@ static void _rtl8723be_return_beacon_queue_skb(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[BEACON_QUEUE]; + struct sk_buff_head free_list; unsigned long flags; + skb_queue_head_init(&free_list); spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags); while (skb_queue_len(&ring->queue)) { struct rtl_tx_desc *entry = &ring->desc[ring->idx]; @@ -41,10 +43,12 @@ static void _rtl8723be_return_beacon_queue_skb(struct ieee80211_hw *hw) rtlpriv->cfg->ops->get_desc(hw, (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), skb->len, DMA_TO_DEVICE); - kfree_skb(skb); + __skb_queue_tail(&free_list, skb); ring->idx = (ring->idx + 1) % ring->entries; } spin_unlock_irqrestore(&rtlpriv->locks.irq_th_lock, flags); + + __skb_queue_purge(&free_list); } static void _rtl8723be_set_bcn_ctrl_reg(struct ieee80211_hw *hw, From e9ef5631dd43d3cdcd55c2c7c6e0be9bff41552c Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 22:40:13 +0800 Subject: [PATCH 1552/4345] wifi: iwlegacy: common: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit 0c1528675d7a9787cb516b64d8f6c0f6f8efcb48 ] It is not allowed to call consume_skb() from hardware interrupt context or with interrupts being disabled. So replace dev_kfree_skb() with dev_consume_skb_irq() under spin_lock_irqsave(). Compile tested only. Fixes: 4bc85c1324aa ("Revert "iwlwifi: split the drivers for agn and legacy devices 3945/4965"") Signed-off-by: Yang Yingliang Acked-by: Stanislaw Gruszka Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207144013.70210-1-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlegacy/common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c index 0651a6a416d1..4b55779de00a 100644 --- a/drivers/net/wireless/intel/iwlegacy/common.c +++ b/drivers/net/wireless/intel/iwlegacy/common.c @@ -5176,7 +5176,7 @@ il_mac_reset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) memset(&il->current_ht_config, 0, sizeof(struct il_ht_config)); /* new association get rid of ibss beacon skb */ - dev_kfree_skb(il->beacon_skb); + dev_consume_skb_irq(il->beacon_skb); il->beacon_skb = NULL; il->timestamp = 0; @@ -5295,7 +5295,7 @@ il_beacon_update(struct ieee80211_hw *hw, struct ieee80211_vif *vif) } spin_lock_irqsave(&il->lock, flags); - dev_kfree_skb(il->beacon_skb); + dev_consume_skb_irq(il->beacon_skb); il->beacon_skb = skb; timestamp = ((struct ieee80211_mgmt *)skb->data)->u.beacon.timestamp; From 9c8f50c7433bdfba1588831c413136ecc3f29f99 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Thu, 8 Dec 2022 20:14:48 +0800 Subject: [PATCH 1553/4345] wifi: libertas: fix memory leak in lbs_init_adapter() [ Upstream commit 16a03958618fb91bb1bc7077cf3211055162cc2f ] When kfifo_alloc() failed in lbs_init_adapter(), cmd buffer is not released. Add free memory to processing error path. Fixes: 7919b89c8276 ("libertas: convert libertas driver to use an event/cmdresp queue") Signed-off-by: Zhengchao Shao Reviewed-by: Jiri Pirko Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221208121448.2845986-1-shaozhengchao@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/libertas/main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c index ee4cf3437e28..36237457d136 100644 --- a/drivers/net/wireless/marvell/libertas/main.c +++ b/drivers/net/wireless/marvell/libertas/main.c @@ -870,6 +870,7 @@ static int lbs_init_adapter(struct lbs_private *priv) ret = kfifo_alloc(&priv->event_fifo, sizeof(u32) * 16, GFP_KERNEL); if (ret) { pr_err("Out of memory allocating event FIFO buffer\n"); + lbs_free_cmd_buffer(priv); goto out; } From 75f4eed70a519717ea91347370207e57b97a632f Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 22:35:17 +0800 Subject: [PATCH 1554/4345] wifi: rtl8xxxu: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit 4c2005ac87685907b3719b4f40215b578efd27c4 ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. It should use dev_kfree_skb_irq() or dev_consume_skb_irq() instead. The difference between them is free reason, dev_kfree_skb_irq() means the SKB is dropped in error and dev_consume_skb_irq() means the SKB is consumed in normal. In this case, dev_kfree_skb() is called to free and drop the SKB when it's shutdown, so replace it with dev_kfree_skb_irq(). Compile tested only. Fixes: 26f1fad29ad9 ("New driver: rtl8xxxu (mac80211)") Signed-off-by: Yang Yingliang Reviewed-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221208143517.2383424-1-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 2cb86c28d11f..f8b1871fe290 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -5184,7 +5184,7 @@ static void rtl8xxxu_queue_rx_urb(struct rtl8xxxu_priv *priv, pending = priv->rx_urb_pending_count; } else { skb = (struct sk_buff *)rx_urb->urb.context; - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); usb_free_urb(&rx_urb->urb); } From d4fddfd7282f57c63c8099c246a4b852a0e7020c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 26 Oct 2020 22:29:53 +0100 Subject: [PATCH 1555/4345] rtlwifi: fix -Wpointer-sign warning [ Upstream commit ef41937631bfee855e2b406e1d536efdaa9ce512 ] There are thousands of warnings in a W=2 build from just one file: drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.c:3788:15: warning: pointer targets in initialization of 'u8 *' {aka 'unsigned char *'} from 'char *' differ in signedness [-Wpointer-sign] Change the types to consistently use 'const char *' for the strings. Signed-off-by: Arnd Bergmann Acked-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20201026213040.3889546-6-arnd@kernel.org Stable-dep-of: 117dbeda22ec ("wifi: rtlwifi: Fix global-out-of-bounds bug in _rtl8812ae_phy_set_txpower_limit()") Signed-off-by: Sasha Levin --- .../wireless/realtek/rtlwifi/rtl8821ae/phy.c | 81 ++++++++++--------- .../realtek/rtlwifi/rtl8821ae/table.c | 4 +- .../realtek/rtlwifi/rtl8821ae/table.h | 4 +- 3 files changed, 45 insertions(+), 44 deletions(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c index f41a7643b9c4..119e0f799826 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c @@ -1581,7 +1581,7 @@ static void _rtl8821ae_phy_txpower_by_rate_configuration(struct ieee80211_hw *hw } /* string is in decimal */ -static bool _rtl8812ae_get_integer_from_string(char *str, u8 *pint) +static bool _rtl8812ae_get_integer_from_string(const char *str, u8 *pint) { u16 i = 0; *pint = 0; @@ -1599,7 +1599,7 @@ static bool _rtl8812ae_get_integer_from_string(char *str, u8 *pint) return true; } -static bool _rtl8812ae_eq_n_byte(u8 *str1, u8 *str2, u32 num) +static bool _rtl8812ae_eq_n_byte(const char *str1, const char *str2, u32 num) { if (num == 0) return false; @@ -1637,10 +1637,11 @@ static s8 _rtl8812ae_phy_get_chnl_idx_of_txpwr_lmt(struct ieee80211_hw *hw, return channel_index; } -static void _rtl8812ae_phy_set_txpower_limit(struct ieee80211_hw *hw, u8 *pregulation, - u8 *pband, u8 *pbandwidth, - u8 *prate_section, u8 *prf_path, - u8 *pchannel, u8 *ppower_limit) +static void _rtl8812ae_phy_set_txpower_limit(struct ieee80211_hw *hw, + const char *pregulation, + const char *pband, const char *pbandwidth, + const char *prate_section, const char *prf_path, + const char *pchannel, const char *ppower_limit) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &rtlpriv->phy; @@ -1648,8 +1649,8 @@ static void _rtl8812ae_phy_set_txpower_limit(struct ieee80211_hw *hw, u8 *pregul u8 channel_index; s8 power_limit = 0, prev_power_limit, ret; - if (!_rtl8812ae_get_integer_from_string((char *)pchannel, &channel) || - !_rtl8812ae_get_integer_from_string((char *)ppower_limit, + if (!_rtl8812ae_get_integer_from_string(pchannel, &channel) || + !_rtl8812ae_get_integer_from_string(ppower_limit, &power_limit)) { rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE, "Illegal index of pwr_lmt table [chnl %d][val %d]\n", @@ -1659,42 +1660,42 @@ static void _rtl8812ae_phy_set_txpower_limit(struct ieee80211_hw *hw, u8 *pregul power_limit = power_limit > MAX_POWER_INDEX ? MAX_POWER_INDEX : power_limit; - if (_rtl8812ae_eq_n_byte(pregulation, (u8 *)("FCC"), 3)) + if (_rtl8812ae_eq_n_byte(pregulation, "FCC", 3)) regulation = 0; - else if (_rtl8812ae_eq_n_byte(pregulation, (u8 *)("MKK"), 3)) + else if (_rtl8812ae_eq_n_byte(pregulation, "MKK", 3)) regulation = 1; - else if (_rtl8812ae_eq_n_byte(pregulation, (u8 *)("ETSI"), 4)) + else if (_rtl8812ae_eq_n_byte(pregulation, "ETSI", 4)) regulation = 2; - else if (_rtl8812ae_eq_n_byte(pregulation, (u8 *)("WW13"), 4)) + else if (_rtl8812ae_eq_n_byte(pregulation, "WW13", 4)) regulation = 3; - if (_rtl8812ae_eq_n_byte(prate_section, (u8 *)("CCK"), 3)) + if (_rtl8812ae_eq_n_byte(prate_section, "CCK", 3)) rate_section = 0; - else if (_rtl8812ae_eq_n_byte(prate_section, (u8 *)("OFDM"), 4)) + else if (_rtl8812ae_eq_n_byte(prate_section, "OFDM", 4)) rate_section = 1; - else if (_rtl8812ae_eq_n_byte(prate_section, (u8 *)("HT"), 2) && - _rtl8812ae_eq_n_byte(prf_path, (u8 *)("1T"), 2)) + else if (_rtl8812ae_eq_n_byte(prate_section, "HT", 2) && + _rtl8812ae_eq_n_byte(prf_path, "1T", 2)) rate_section = 2; - else if (_rtl8812ae_eq_n_byte(prate_section, (u8 *)("HT"), 2) && - _rtl8812ae_eq_n_byte(prf_path, (u8 *)("2T"), 2)) + else if (_rtl8812ae_eq_n_byte(prate_section, "HT", 2) && + _rtl8812ae_eq_n_byte(prf_path, "2T", 2)) rate_section = 3; - else if (_rtl8812ae_eq_n_byte(prate_section, (u8 *)("VHT"), 3) && - _rtl8812ae_eq_n_byte(prf_path, (u8 *)("1T"), 2)) + else if (_rtl8812ae_eq_n_byte(prate_section, "VHT", 3) && + _rtl8812ae_eq_n_byte(prf_path, "1T", 2)) rate_section = 4; - else if (_rtl8812ae_eq_n_byte(prate_section, (u8 *)("VHT"), 3) && - _rtl8812ae_eq_n_byte(prf_path, (u8 *)("2T"), 2)) + else if (_rtl8812ae_eq_n_byte(prate_section, "VHT", 3) && + _rtl8812ae_eq_n_byte(prf_path, "2T", 2)) rate_section = 5; - if (_rtl8812ae_eq_n_byte(pbandwidth, (u8 *)("20M"), 3)) + if (_rtl8812ae_eq_n_byte(pbandwidth, "20M", 3)) bandwidth = 0; - else if (_rtl8812ae_eq_n_byte(pbandwidth, (u8 *)("40M"), 3)) + else if (_rtl8812ae_eq_n_byte(pbandwidth, "40M", 3)) bandwidth = 1; - else if (_rtl8812ae_eq_n_byte(pbandwidth, (u8 *)("80M"), 3)) + else if (_rtl8812ae_eq_n_byte(pbandwidth, "80M", 3)) bandwidth = 2; - else if (_rtl8812ae_eq_n_byte(pbandwidth, (u8 *)("160M"), 4)) + else if (_rtl8812ae_eq_n_byte(pbandwidth, "160M", 4)) bandwidth = 3; - if (_rtl8812ae_eq_n_byte(pband, (u8 *)("2.4G"), 4)) { + if (_rtl8812ae_eq_n_byte(pband, "2.4G", 4)) { ret = _rtl8812ae_phy_get_chnl_idx_of_txpwr_lmt(hw, BAND_ON_2_4G, channel); @@ -1718,7 +1719,7 @@ static void _rtl8812ae_phy_set_txpower_limit(struct ieee80211_hw *hw, u8 *pregul regulation, bandwidth, rate_section, channel_index, rtlphy->txpwr_limit_2_4g[regulation][bandwidth] [rate_section][channel_index][RF90_PATH_A]); - } else if (_rtl8812ae_eq_n_byte(pband, (u8 *)("5G"), 2)) { + } else if (_rtl8812ae_eq_n_byte(pband, "5G", 2)) { ret = _rtl8812ae_phy_get_chnl_idx_of_txpwr_lmt(hw, BAND_ON_5G, channel); @@ -1749,10 +1750,10 @@ static void _rtl8812ae_phy_set_txpower_limit(struct ieee80211_hw *hw, u8 *pregul } static void _rtl8812ae_phy_config_bb_txpwr_lmt(struct ieee80211_hw *hw, - u8 *regulation, u8 *band, - u8 *bandwidth, u8 *rate_section, - u8 *rf_path, u8 *channel, - u8 *power_limit) + const char *regulation, const char *band, + const char *bandwidth, const char *rate_section, + const char *rf_path, const char *channel, + const char *power_limit) { _rtl8812ae_phy_set_txpower_limit(hw, regulation, band, bandwidth, rate_section, rf_path, channel, @@ -1765,7 +1766,7 @@ static void _rtl8821ae_phy_read_and_config_txpwr_lmt(struct ieee80211_hw *hw) struct rtl_hal *rtlhal = rtl_hal(rtlpriv); u32 i = 0; u32 array_len; - u8 **array; + const char **array; if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) { array_len = RTL8812AE_TXPWR_LMT_ARRAY_LEN; @@ -1778,13 +1779,13 @@ static void _rtl8821ae_phy_read_and_config_txpwr_lmt(struct ieee80211_hw *hw) rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE, "\n"); for (i = 0; i < array_len; i += 7) { - u8 *regulation = array[i]; - u8 *band = array[i+1]; - u8 *bandwidth = array[i+2]; - u8 *rate = array[i+3]; - u8 *rf_path = array[i+4]; - u8 *chnl = array[i+5]; - u8 *val = array[i+6]; + const char *regulation = array[i]; + const char *band = array[i+1]; + const char *bandwidth = array[i+2]; + const char *rate = array[i+3]; + const char *rf_path = array[i+4]; + const char *chnl = array[i+5]; + const char *val = array[i+6]; _rtl8812ae_phy_config_bb_txpwr_lmt(hw, regulation, band, bandwidth, rate, rf_path, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.c index ed72a2aeb6c8..fcaaf664cbec 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.c @@ -2894,7 +2894,7 @@ u32 RTL8821AE_AGC_TAB_1TARRAYLEN = ARRAY_SIZE(RTL8821AE_AGC_TAB_ARRAY); * TXPWR_LMT.TXT ******************************************************************************/ -u8 *RTL8812AE_TXPWR_LMT[] = { +const char *RTL8812AE_TXPWR_LMT[] = { "FCC", "2.4G", "20M", "CCK", "1T", "01", "36", "ETSI", "2.4G", "20M", "CCK", "1T", "01", "32", "MKK", "2.4G", "20M", "CCK", "1T", "01", "32", @@ -3463,7 +3463,7 @@ u8 *RTL8812AE_TXPWR_LMT[] = { u32 RTL8812AE_TXPWR_LMT_ARRAY_LEN = ARRAY_SIZE(RTL8812AE_TXPWR_LMT); -u8 *RTL8821AE_TXPWR_LMT[] = { +const char *RTL8821AE_TXPWR_LMT[] = { "FCC", "2.4G", "20M", "CCK", "1T", "01", "32", "ETSI", "2.4G", "20M", "CCK", "1T", "01", "32", "MKK", "2.4G", "20M", "CCK", "1T", "01", "32", diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.h index 540159c25078..76c62b7c0fb2 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/table.h @@ -28,7 +28,7 @@ extern u32 RTL8821AE_AGC_TAB_ARRAY[]; extern u32 RTL8812AE_AGC_TAB_1TARRAYLEN; extern u32 RTL8812AE_AGC_TAB_ARRAY[]; extern u32 RTL8812AE_TXPWR_LMT_ARRAY_LEN; -extern u8 *RTL8812AE_TXPWR_LMT[]; +extern const char *RTL8812AE_TXPWR_LMT[]; extern u32 RTL8821AE_TXPWR_LMT_ARRAY_LEN; -extern u8 *RTL8821AE_TXPWR_LMT[]; +extern const char *RTL8821AE_TXPWR_LMT[]; #endif From 1e950b9a841bc96e98ee25680d5c7aa305120be1 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Mon, 12 Dec 2022 10:58:12 +0800 Subject: [PATCH 1556/4345] wifi: rtlwifi: Fix global-out-of-bounds bug in _rtl8812ae_phy_set_txpower_limit() [ Upstream commit 117dbeda22ec5ea0918254d03b540ef8b8a64d53 ] There is a global-out-of-bounds reported by KASAN: BUG: KASAN: global-out-of-bounds in _rtl8812ae_eq_n_byte.part.0+0x3d/0x84 [rtl8821ae] Read of size 1 at addr ffffffffa0773c43 by task NetworkManager/411 CPU: 6 PID: 411 Comm: NetworkManager Tainted: G D 6.1.0-rc8+ #144 e15588508517267d37 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), Call Trace: ... kasan_report+0xbb/0x1c0 _rtl8812ae_eq_n_byte.part.0+0x3d/0x84 [rtl8821ae] rtl8821ae_phy_bb_config.cold+0x346/0x641 [rtl8821ae] rtl8821ae_hw_init+0x1f5e/0x79b0 [rtl8821ae] ... The root cause of the problem is that the comparison order of "prate_section" in _rtl8812ae_phy_set_txpower_limit() is wrong. The _rtl8812ae_eq_n_byte() is used to compare the first n bytes of the two strings from tail to head, which causes the problem. In the _rtl8812ae_phy_set_txpower_limit(), it was originally intended to meet this requirement by carefully designing the comparison order. For example, "pregulation" and "pbandwidth" are compared in order of length from small to large, first is 3 and last is 4. However, the comparison order of "prate_section" dose not obey such order requirement, therefore when "prate_section" is "HT", when comparing from tail to head, it will lead to access out of bounds in _rtl8812ae_eq_n_byte(). As mentioned above, the _rtl8812ae_eq_n_byte() has the same function as strcmp(), so just strcmp() is enough. Fix it by removing _rtl8812ae_eq_n_byte() and use strcmp() barely. Although it can be fixed by adjusting the comparison order of "prate_section", this may cause the value of "rate_section" to not be from 0 to 5. In addition, commit "21e4b0726dc6" not only moved driver from staging to regular tree, but also added setting txpower limit function during the driver config phase, so the problem was introduced by this commit. Fixes: 21e4b0726dc6 ("rtlwifi: rtl8821ae: Move driver from staging to regular tree") Signed-off-by: Li Zetao Acked-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221212025812.1541311-1-lizetao1@huawei.com Signed-off-by: Sasha Levin --- .../wireless/realtek/rtlwifi/rtl8821ae/phy.c | 52 +++++++------------ 1 file changed, 20 insertions(+), 32 deletions(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c index 119e0f799826..c0c06ab6d3e7 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c @@ -1599,18 +1599,6 @@ static bool _rtl8812ae_get_integer_from_string(const char *str, u8 *pint) return true; } -static bool _rtl8812ae_eq_n_byte(const char *str1, const char *str2, u32 num) -{ - if (num == 0) - return false; - while (num > 0) { - num--; - if (str1[num] != str2[num]) - return false; - } - return true; -} - static s8 _rtl8812ae_phy_get_chnl_idx_of_txpwr_lmt(struct ieee80211_hw *hw, u8 band, u8 channel) { @@ -1660,42 +1648,42 @@ static void _rtl8812ae_phy_set_txpower_limit(struct ieee80211_hw *hw, power_limit = power_limit > MAX_POWER_INDEX ? MAX_POWER_INDEX : power_limit; - if (_rtl8812ae_eq_n_byte(pregulation, "FCC", 3)) + if (strcmp(pregulation, "FCC") == 0) regulation = 0; - else if (_rtl8812ae_eq_n_byte(pregulation, "MKK", 3)) + else if (strcmp(pregulation, "MKK") == 0) regulation = 1; - else if (_rtl8812ae_eq_n_byte(pregulation, "ETSI", 4)) + else if (strcmp(pregulation, "ETSI") == 0) regulation = 2; - else if (_rtl8812ae_eq_n_byte(pregulation, "WW13", 4)) + else if (strcmp(pregulation, "WW13") == 0) regulation = 3; - if (_rtl8812ae_eq_n_byte(prate_section, "CCK", 3)) + if (strcmp(prate_section, "CCK") == 0) rate_section = 0; - else if (_rtl8812ae_eq_n_byte(prate_section, "OFDM", 4)) + else if (strcmp(prate_section, "OFDM") == 0) rate_section = 1; - else if (_rtl8812ae_eq_n_byte(prate_section, "HT", 2) && - _rtl8812ae_eq_n_byte(prf_path, "1T", 2)) + else if (strcmp(prate_section, "HT") == 0 && + strcmp(prf_path, "1T") == 0) rate_section = 2; - else if (_rtl8812ae_eq_n_byte(prate_section, "HT", 2) && - _rtl8812ae_eq_n_byte(prf_path, "2T", 2)) + else if (strcmp(prate_section, "HT") == 0 && + strcmp(prf_path, "2T") == 0) rate_section = 3; - else if (_rtl8812ae_eq_n_byte(prate_section, "VHT", 3) && - _rtl8812ae_eq_n_byte(prf_path, "1T", 2)) + else if (strcmp(prate_section, "VHT") == 0 && + strcmp(prf_path, "1T") == 0) rate_section = 4; - else if (_rtl8812ae_eq_n_byte(prate_section, "VHT", 3) && - _rtl8812ae_eq_n_byte(prf_path, "2T", 2)) + else if (strcmp(prate_section, "VHT") == 0 && + strcmp(prf_path, "2T") == 0) rate_section = 5; - if (_rtl8812ae_eq_n_byte(pbandwidth, "20M", 3)) + if (strcmp(pbandwidth, "20M") == 0) bandwidth = 0; - else if (_rtl8812ae_eq_n_byte(pbandwidth, "40M", 3)) + else if (strcmp(pbandwidth, "40M") == 0) bandwidth = 1; - else if (_rtl8812ae_eq_n_byte(pbandwidth, "80M", 3)) + else if (strcmp(pbandwidth, "80M") == 0) bandwidth = 2; - else if (_rtl8812ae_eq_n_byte(pbandwidth, "160M", 4)) + else if (strcmp(pbandwidth, "160M") == 0) bandwidth = 3; - if (_rtl8812ae_eq_n_byte(pband, "2.4G", 4)) { + if (strcmp(pband, "2.4G") == 0) { ret = _rtl8812ae_phy_get_chnl_idx_of_txpwr_lmt(hw, BAND_ON_2_4G, channel); @@ -1719,7 +1707,7 @@ static void _rtl8812ae_phy_set_txpower_limit(struct ieee80211_hw *hw, regulation, bandwidth, rate_section, channel_index, rtlphy->txpwr_limit_2_4g[regulation][bandwidth] [rate_section][channel_index][RF90_PATH_A]); - } else if (_rtl8812ae_eq_n_byte(pband, "5G", 2)) { + } else if (strcmp(pband, "5G") == 0) { ret = _rtl8812ae_phy_get_chnl_idx_of_txpwr_lmt(hw, BAND_ON_5G, channel); From 3938f01405d61fde44b25a960c2d6cc851c80467 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 12 Dec 2022 13:15:03 -0800 Subject: [PATCH 1557/4345] libbpf: Fix btf__align_of() by taking into account field offsets [ Upstream commit 25a4481b4136af7794e1df2d6c90ed2f354d60ce ] btf__align_of() is supposed to be return alignment requirement of a requested BTF type. For STRUCT/UNION it doesn't always return correct value, because it calculates alignment only based on field types. But for packed structs this is not enough, we need to also check field offsets and struct size. If field offset isn't aligned according to field type's natural alignment, then struct must be packed. Similarly, if struct size is not a multiple of struct's natural alignment, then struct must be packed as well. This patch fixes this issue precisely by additionally checking these conditions. Fixes: 3d208f4ca111 ("libbpf: Expose btf__align_of() API") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20221212211505.558851-5-andrii@kernel.org Signed-off-by: Sasha Levin --- tools/lib/bpf/btf.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index e6f644cdc9f1..f7c48b1fb3a0 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -614,8 +614,21 @@ int btf__align_of(const struct btf *btf, __u32 id) if (align <= 0) return align; max_align = max(max_align, align); + + /* if field offset isn't aligned according to field + * type's alignment, then struct must be packed + */ + if (btf_member_bitfield_size(t, i) == 0 && + (m->offset % (8 * align)) != 0) + return 1; } + /* if struct/union size isn't a multiple of its alignment, + * then struct must be packed + */ + if ((t->size % max_align) != 0) + return 1; + return max_align; } default: From 841ae9b924f4e7ff3bfa887fafb113a6665d01ff Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 8 Dec 2022 22:38:26 +0800 Subject: [PATCH 1558/4345] wifi: ipw2x00: don't call dev_kfree_skb() under spin_lock_irqsave() [ Upstream commit 45fc6d7461f18df2f238caf0cbc5acc4163203d1 ] It is not allowed to call kfree_skb() or consume_skb() from hardware interrupt context or with hardware interrupts being disabled. It should use dev_kfree_skb_irq() or dev_consume_skb_irq() instead. The difference between them is free reason, dev_kfree_skb_irq() means the SKB is dropped in error and dev_consume_skb_irq() means the SKB is consumed in normal. In this case, dev_kfree_skb() is called to free and drop the SKB when it's reset, so replace it with dev_kfree_skb_irq(). Compile tested only. Fixes: 43f66a6ce8da ("Add ipw2200 wireless driver.") Signed-off-by: Yang Yingliang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221208143826.2385218-1-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/ipw2x00/ipw2200.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c index ada6ce32c1f1..df28e4a05e14 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c @@ -3444,7 +3444,7 @@ static void ipw_rx_queue_reset(struct ipw_priv *priv, dma_unmap_single(&priv->pci_dev->dev, rxq->pool[i].dma_addr, IPW_RX_BUF_SIZE, DMA_FROM_DEVICE); - dev_kfree_skb(rxq->pool[i].skb); + dev_kfree_skb_irq(rxq->pool[i].skb); rxq->pool[i].skb = NULL; } list_add_tail(&rxq->pool[i].list, &rxq->rx_used); From 8a2eb9d9d0c1535bc8e22840193bff4cdcac878b Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Fri, 9 Dec 2022 09:24:22 +0800 Subject: [PATCH 1559/4345] wifi: ipw2200: fix memory leak in ipw_wdev_init() [ Upstream commit 9fe21dc626117fb44a8eb393713a86a620128ce3 ] In the error path of ipw_wdev_init(), exception value is returned, and the memory applied for in the function is not released. Also the memory is not released in ipw_pci_probe(). As a result, memory leakage occurs. So memory release needs to be added to the error path of ipw_wdev_init(). Fixes: a3caa99e6c68 ("libipw: initiate cfg80211 API conversion (v2)") Signed-off-by: Zhengchao Shao Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221209012422.182669-1-shaozhengchao@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/ipw2x00/ipw2200.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c index df28e4a05e14..bb728fb24b8a 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c @@ -11400,9 +11400,14 @@ static int ipw_wdev_init(struct net_device *dev) set_wiphy_dev(wdev->wiphy, &priv->pci_dev->dev); /* With that information in place, we can now register the wiphy... */ - if (wiphy_register(wdev->wiphy)) - rc = -EIO; + rc = wiphy_register(wdev->wiphy); + if (rc) + goto out; + + return 0; out: + kfree(priv->ieee->a_band.channels); + kfree(priv->ieee->bg_band.channels); return rc; } From a1e94fb4d09d0fcfeaa73aa49d787f06c42db7ee Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Thu, 17 Nov 2022 19:36:03 +0800 Subject: [PATCH 1560/4345] wifi: wilc1000: fix potential memory leak in wilc_mac_xmit() [ Upstream commit deb962ec9e1c9a81babd3d37542ad4bd6ac3396e ] The wilc_mac_xmit() returns NETDEV_TX_OK without freeing skb, add dev_kfree_skb() to fix it. Compile tested only. Fixes: c5c77ba18ea6 ("staging: wilc1000: Add SDIO/SPI 802.11 driver") Signed-off-by: Zhang Changzhong Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1668684964-48622-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/microchip/wilc1000/netdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c index 20615c7ec168..c508f429984a 100644 --- a/drivers/net/wireless/microchip/wilc1000/netdev.c +++ b/drivers/net/wireless/microchip/wilc1000/netdev.c @@ -684,6 +684,7 @@ netdev_tx_t wilc_mac_xmit(struct sk_buff *skb, struct net_device *ndev) if (skb->dev != ndev) { netdev_err(ndev, "Packet not destined to this device\n"); + dev_kfree_skb(skb); return NETDEV_TX_OK; } From e08e6812efb6a8c676e733de0518594d1517e0d9 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Thu, 17 Nov 2022 19:33:01 +0800 Subject: [PATCH 1561/4345] wifi: brcmfmac: fix potential memory leak in brcmf_netdev_start_xmit() [ Upstream commit 212fde3fe76e962598ce1d47b97cc78afdfc71b3 ] The brcmf_netdev_start_xmit() returns NETDEV_TX_OK without freeing skb in case of pskb_expand_head() fails, add dev_kfree_skb() to fix it. Compile tested only. Fixes: 270a6c1f65fe ("brcmfmac: rework headroom check in .start_xmit()") Signed-off-by: Zhang Changzhong Reviewed-by: Arend van Spriel Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1668684782-47422-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index c8e1d505f7b5..3d544eedc1a3 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -333,6 +333,7 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb, bphy_err(drvr, "%s: failed to expand headroom\n", brcmf_ifname(ifp)); atomic_inc(&drvr->bus_if->stats.pktcow_failed); + dev_kfree_skb(skb); goto done; } } From b4b4447481dbdffb0220632b4ba3be397b1d2676 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 7 Dec 2022 09:31:14 +0800 Subject: [PATCH 1562/4345] wifi: brcmfmac: unmap dma buffer in brcmf_msgbuf_alloc_pktid() [ Upstream commit b9f420032f2ba1e634b22ca7b433e5c40ea663af ] After the DMA buffer is mapped to a physical address, address is stored in pktids in brcmf_msgbuf_alloc_pktid(). Then, pktids is parsed in brcmf_msgbuf_get_pktid()/brcmf_msgbuf_release_array() to obtain physaddr and later unmap the DMA buffer. But when count is always equal to pktids->array_size, physaddr isn't stored in pktids and the DMA buffer will not be unmapped anyway. Fixes: 9a1bb60250d2 ("brcmfmac: Adding msgbuf protocol.") Signed-off-by: Zhengchao Shao Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207013114.1748936-1-shaozhengchao@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c index 7c8e08ee8f0f..bd3b234b7803 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c @@ -346,8 +346,11 @@ brcmf_msgbuf_alloc_pktid(struct device *dev, count++; } while (count < pktids->array_size); - if (count == pktids->array_size) + if (count == pktids->array_size) { + dma_unmap_single(dev, *physaddr, skb->len - data_offset, + pktids->direction); return -ENOMEM; + } array[*idx].data_offset = data_offset; array[*idx].physaddr = *physaddr; From 0258757caab5e987b725243cfef0c4a105654db2 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 23:00:05 +0800 Subject: [PATCH 1563/4345] wifi: libertas_tf: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 9388ce97b98216833c969191ee6df61a7201d797 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Compile tested only. Fixes: fc75122fabb5 ("libertas_tf: use irqsave() in USB's complete callback") Signed-off-by: Yang Yingliang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207150008.111743-2-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/libertas_tf/if_usb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/marvell/libertas_tf/if_usb.c b/drivers/net/wireless/marvell/libertas_tf/if_usb.c index ecce8b56f8a2..2c45ef6e0407 100644 --- a/drivers/net/wireless/marvell/libertas_tf/if_usb.c +++ b/drivers/net/wireless/marvell/libertas_tf/if_usb.c @@ -613,7 +613,7 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff, spin_lock_irqsave(&priv->driver_lock, flags); memcpy(priv->cmd_resp_buff, recvbuff + MESSAGE_HEADER_LEN, recvlength - MESSAGE_HEADER_LEN); - kfree_skb(skb); + dev_kfree_skb_irq(skb); lbtf_cmd_response_rx(priv); spin_unlock_irqrestore(&priv->driver_lock, flags); } From 647230e71e1c306810996966721ad581899d5b2c Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 23:00:06 +0800 Subject: [PATCH 1564/4345] wifi: libertas: if_usb: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 3968e81ba644f10a7d45bae2539560db9edac501 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Compile tested only. Fixes: a3128feef6d5 ("libertas: use irqsave() in USB's complete callback") Signed-off-by: Yang Yingliang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207150008.111743-3-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/libertas/if_usb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/marvell/libertas/if_usb.c b/drivers/net/wireless/marvell/libertas/if_usb.c index 32fdc4150b60..2240b4db8c03 100644 --- a/drivers/net/wireless/marvell/libertas/if_usb.c +++ b/drivers/net/wireless/marvell/libertas/if_usb.c @@ -637,7 +637,7 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff, priv->resp_len[i] = (recvlength - MESSAGE_HEADER_LEN); memcpy(priv->resp_buf[i], recvbuff + MESSAGE_HEADER_LEN, priv->resp_len[i]); - kfree_skb(skb); + dev_kfree_skb_irq(skb); lbs_notify_command_response(priv, i); spin_unlock_irqrestore(&priv->driver_lock, flags); From 2ddb1820bdacbccc0f296c70b3344308ed2c7623 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 23:00:07 +0800 Subject: [PATCH 1565/4345] wifi: libertas: main: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit f393df151540bf858effbd29ff572ab94e76a4c4 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Compile tested only. Fixes: d2e7b3425c47 ("libertas: disable functionality when interface is down") Signed-off-by: Yang Yingliang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207150008.111743-4-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/libertas/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c index 36237457d136..1c56cc2742b0 100644 --- a/drivers/net/wireless/marvell/libertas/main.c +++ b/drivers/net/wireless/marvell/libertas/main.c @@ -217,7 +217,7 @@ int lbs_stop_iface(struct lbs_private *priv) spin_lock_irqsave(&priv->driver_lock, flags); priv->iface_running = false; - kfree_skb(priv->currenttxskb); + dev_kfree_skb_irq(priv->currenttxskb); priv->currenttxskb = NULL; priv->tx_pending_len = 0; spin_unlock_irqrestore(&priv->driver_lock, flags); From 93b8809be5ba7d28218fd5561560c10cf058e998 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 23:00:08 +0800 Subject: [PATCH 1566/4345] wifi: libertas: cmdresp: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 708a49a64237f19bd404852f297aaadbc9e7fee0 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Compile tested only. Fixes: f52b041aed77 ("libertas: Add spinlock to avoid race condition") Signed-off-by: Yang Yingliang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207150008.111743-5-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/libertas/cmdresp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/marvell/libertas/cmdresp.c b/drivers/net/wireless/marvell/libertas/cmdresp.c index cb515c5584c1..74cb7551f427 100644 --- a/drivers/net/wireless/marvell/libertas/cmdresp.c +++ b/drivers/net/wireless/marvell/libertas/cmdresp.c @@ -48,7 +48,7 @@ void lbs_mac_event_disconnected(struct lbs_private *priv, /* Free Tx and Rx packets */ spin_lock_irqsave(&priv->driver_lock, flags); - kfree_skb(priv->currenttxskb); + dev_kfree_skb_irq(priv->currenttxskb); priv->currenttxskb = NULL; priv->tx_pending_len = 0; spin_unlock_irqrestore(&priv->driver_lock, flags); From f6e429cde9ead0c42aba9fee5dc640fa9ba31ad0 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Wed, 7 Dec 2022 23:04:53 +0800 Subject: [PATCH 1567/4345] wifi: wl3501_cs: don't call kfree_skb() under spin_lock_irqsave() [ Upstream commit 44bacbdf9066c590423259dbd6d520baac99c1a8 ] It is not allowed to call kfree_skb() from hardware interrupt context or with interrupts being disabled. So replace kfree_skb() with dev_kfree_skb_irq() under spin_lock_irqsave(). Compile tested only. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yang Yingliang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221207150453.114742-1-yangyingliang@huawei.com Signed-off-by: Sasha Levin --- drivers/net/wireless/wl3501_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c index ff1701adbb17..ccf6344ed6fd 100644 --- a/drivers/net/wireless/wl3501_cs.c +++ b/drivers/net/wireless/wl3501_cs.c @@ -1330,7 +1330,7 @@ static netdev_tx_t wl3501_hard_start_xmit(struct sk_buff *skb, } else { ++dev->stats.tx_packets; dev->stats.tx_bytes += skb->len; - kfree_skb(skb); + dev_kfree_skb_irq(skb); if (this->tx_buffer_cnt < 2) netif_stop_queue(dev); From 6e43b2d9d166286c232d91302906108063e33181 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 19 Dec 2022 21:40:40 -0800 Subject: [PATCH 1568/4345] crypto: x86/ghash - fix unaligned access in ghash_setkey() [ Upstream commit 116db2704c193fff6d73ea6c2219625f0c9bdfc8 ] The key can be unaligned, so use the unaligned memory access helpers. Fixes: 8ceee72808d1 ("crypto: ghash-clmulni-intel - use C implementation for setkey()") Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- arch/x86/crypto/ghash-clmulni-intel_glue.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 1f1a95f3dd0c..c0ab0ff4af65 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -19,6 +19,7 @@ #include #include #include +#include #define GHASH_BLOCK_SIZE 16 #define GHASH_DIGEST_SIZE 16 @@ -54,15 +55,14 @@ static int ghash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct ghash_ctx *ctx = crypto_shash_ctx(tfm); - be128 *x = (be128 *)key; u64 a, b; if (keylen != GHASH_BLOCK_SIZE) return -EINVAL; /* perform multiplication by 'x' in GF(2^128) */ - a = be64_to_cpu(x->a); - b = be64_to_cpu(x->b); + a = get_unaligned_be64(key); + b = get_unaligned_be64(key + 8); ctx->shash.a = (b << 1) | (a >> 63); ctx->shash.b = (a << 1) | (b >> 63); From 5562585c4aa26ba4f044c52a0af244b4b772bfe5 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 15 Dec 2022 09:51:20 -0600 Subject: [PATCH 1569/4345] ACPICA: Drop port I/O validation for some regions [ Upstream commit e1d9148582ab2c3dada5c5cf8ca7531ca269fee5 ] Microsoft introduced support in Windows XP for blocking port I/O to various regions. For Windows compatibility ACPICA has adopted the same protections and will disallow writes to those (presumably) the same regions. On some systems the AML included with the firmware will issue 4 byte long writes to 0x80. These writes aren't making it over because of this blockage. The first 4 byte write attempt is rejected, and then subsequently 1 byte at a time each offset is tried. The first at 0x80 works, but then the next 3 bytes are rejected. This manifests in bizarre failures for devices that expected the AML to write all 4 bytes. Trying the same AML on Windows 10 or 11 doesn't hit this failure and all 4 bytes are written. Either some of these regions were wrong or some point after Windows XP some of these regions blocks have been lifted. In the last 15 years there doesn't seem to be any reports popping up of this error in the Windows event viewer anymore. There is no documentation at Microsoft's developer site indicating that Windows ACPI interpreter blocks these regions. Between the lack of documentation and the fact that the writes actually do work in Windows 10 and 11, it's quite likely Windows doesn't actually enforce this anymore. So to help the issue, only enforce Windows XP specific entries if the latest _OSI supported is Windows XP. Continue to enforce the ALWAYS_ILLEGAL entries. Link: https://github.com/acpica/acpica/pull/817 Fixes: 7f0719039085 ("ACPICA: New: I/O port protection") Signed-off-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/acpica/hwvalid.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c index b2ca7dfd3fc9..0cc4de3f71d5 100644 --- a/drivers/acpi/acpica/hwvalid.c +++ b/drivers/acpi/acpica/hwvalid.c @@ -23,8 +23,8 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width); * * The table is used to implement the Microsoft port access rules that * first appeared in Windows XP. Some ports are always illegal, and some - * ports are only illegal if the BIOS calls _OSI with a win_XP string or - * later (meaning that the BIOS itelf is post-XP.) + * ports are only illegal if the BIOS calls _OSI with nothing newer than + * the specific _OSI strings. * * This provides ACPICA with the desired port protections and * Microsoft compatibility. @@ -145,7 +145,8 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width) /* Port illegality may depend on the _OSI calls made by the BIOS */ - if (acpi_gbl_osi_data >= port_info->osi_dependency) { + if (port_info->osi_dependency == ACPI_ALWAYS_ILLEGAL || + acpi_gbl_osi_data == port_info->osi_dependency) { ACPI_DEBUG_PRINT((ACPI_DB_VALUES, "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)\n", ACPI_FORMAT_UINT64(address), From a4935bb734448a71e4eae539b1d7768f6ed134ac Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Sat, 19 Nov 2022 17:25:03 +0800 Subject: [PATCH 1570/4345] genirq: Fix the return type of kstat_cpu_irqs_sum() [ Upstream commit 47904aed898a08f028572b9b5a5cc101ddfb2d82 ] The type of member ->irqs_sum is unsigned long, but kstat_cpu_irqs_sum() returns int, which can result in truncation. Therefore, change the kstat_cpu_irqs_sum() function's return value to unsigned long to avoid truncation. Fixes: f2c66cd8eedd ("/proc/stat: scalability of irq num per cpu") Reported-by: Elliott, Robert (Servers) Signed-off-by: Zhen Lei Cc: Tejun Heo Cc: "Peter Zijlstra (Intel)" Cc: Josh Don Cc: Andrew Morton Reviewed-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- include/linux/kernel_stat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 8fff3500d50e..1160e20995a0 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -73,7 +73,7 @@ extern unsigned int kstat_irqs_usr(unsigned int irq); /* * Number of interrupts per cpu, since bootup */ -static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu) +static inline unsigned long kstat_cpu_irqs_sum(unsigned int cpu) { return kstat_cpu(cpu).irqs_sum; } From b02b6bb83c683efb69f62f709ac1b064a176ac32 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 25 Nov 2022 14:54:58 +0100 Subject: [PATCH 1571/4345] rcu-tasks: Improve comments explaining tasks_rcu_exit_srcu purpose [ Upstream commit e4e1e8089c5fd948da12cb9f4adc93821036945f ] Make sure we don't need to look again into the depths of git blame in order not to miss a subtle part about how rcu-tasks is dealing with exiting tasks. Suggested-by: Boqun Feng Suggested-by: Neeraj Upadhyay Suggested-by: Paul E. McKenney Cc: Oleg Nesterov Cc: Lai Jiangshan Cc: Eric W. Biederman Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Stable-dep-of: 28319d6dc5e2 ("rcu-tasks: Fix synchronize_rcu_tasks() VS zap_pid_ns_processes()") Signed-off-by: Sasha Levin --- kernel/rcu/tasks.h | 37 +++++++++++++++++++++++++++++-------- 1 file changed, 29 insertions(+), 8 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 8b51e6a5b386..372644126b0d 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -416,11 +416,21 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop) static void rcu_tasks_postscan(struct list_head *hop) { /* - * Wait for tasks that are in the process of exiting. This - * does only part of the job, ensuring that all tasks that were - * previously exiting reach the point where they have disabled - * preemption, allowing the later synchronize_rcu() to finish - * the job. + * Exiting tasks may escape the tasklist scan. Those are vulnerable + * until their final schedule() with TASK_DEAD state. To cope with + * this, divide the fragile exit path part in two intersecting + * read side critical sections: + * + * 1) An _SRCU_ read side starting before calling exit_notify(), + * which may remove the task from the tasklist, and ending after + * the final preempt_disable() call in do_exit(). + * + * 2) An _RCU_ read side starting with the final preempt_disable() + * call in do_exit() and ending with the final call to schedule() + * with TASK_DEAD state. + * + * This handles the part 1). And postgp will handle part 2) with a + * call to synchronize_rcu(). */ synchronize_srcu(&tasks_rcu_exit_srcu); } @@ -487,7 +497,10 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp) * * In addition, this synchronize_rcu() waits for exiting tasks * to complete their final preempt_disable() region of execution, - * cleaning up after the synchronize_srcu() above. + * cleaning up after synchronize_srcu(&tasks_rcu_exit_srcu), + * enforcing the whole region before tasklist removal until + * the final schedule() with TASK_DEAD state to be an RCU TASKS + * read side critical section. */ synchronize_rcu(); } @@ -576,7 +589,11 @@ static void show_rcu_tasks_classic_gp_kthread(void) } #endif /* #ifndef CONFIG_TINY_RCU */ -/* Do the srcu_read_lock() for the above synchronize_srcu(). */ +/* + * Contribute to protect against tasklist scan blind spot while the + * task is exiting and may be removed from the tasklist. See + * corresponding synchronize_srcu() for further details. + */ void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu) { preempt_disable(); @@ -584,7 +601,11 @@ void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu) preempt_enable(); } -/* Do the srcu_read_unlock() for the above synchronize_srcu(). */ +/* + * Contribute to protect against tasklist scan blind spot while the + * task is exiting and may be removed from the tasklist. See + * corresponding synchronize_srcu() for further details. + */ void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu) { struct task_struct *t = current; From ad410f64f7ab189e71192b1edb5786ffbe59c622 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 25 Nov 2022 14:54:59 +0100 Subject: [PATCH 1572/4345] rcu-tasks: Remove preemption disablement around srcu_read_[un]lock() calls [ Upstream commit 44757092958bdd749775022f915b7ac974384c2a ] Ever since the following commit: 5a41344a3d83 ("srcu: Simplify __srcu_read_unlock() via this_cpu_dec()") SRCU doesn't rely anymore on preemption to be disabled in order to modify the per-CPU counter. And even then it used to be done from the API itself. Therefore and after checking further, it appears to be safe to remove the preemption disablement around __srcu_read_[un]lock() in exit_tasks_rcu_start() and exit_tasks_rcu_finish() Suggested-by: Boqun Feng Suggested-by: Paul E. McKenney Suggested-by: Neeraj Upadhyay Cc: Lai Jiangshan Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Stable-dep-of: 28319d6dc5e2 ("rcu-tasks: Fix synchronize_rcu_tasks() VS zap_pid_ns_processes()") Signed-off-by: Sasha Levin --- kernel/rcu/tasks.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 372644126b0d..c4af3c05663f 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -596,9 +596,7 @@ static void show_rcu_tasks_classic_gp_kthread(void) */ void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu) { - preempt_disable(); current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu); - preempt_enable(); } /* @@ -610,9 +608,7 @@ void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu) { struct task_struct *t = current; - preempt_disable(); __srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx); - preempt_enable(); exit_tasks_rcu_finish_trace(t); } From 1c37e86a78c20b3b9d6997ad3f43431b6b2fe2f0 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 25 Nov 2022 14:55:00 +0100 Subject: [PATCH 1573/4345] rcu-tasks: Fix synchronize_rcu_tasks() VS zap_pid_ns_processes() [ Upstream commit 28319d6dc5e2ffefa452c2377dd0f71621b5bff0 ] RCU Tasks and PID-namespace unshare can interact in do_exit() in a complicated circular dependency: 1) TASK A calls unshare(CLONE_NEWPID), this creates a new PID namespace that every subsequent child of TASK A will belong to. But TASK A doesn't itself belong to that new PID namespace. 2) TASK A forks() and creates TASK B. TASK A stays attached to its PID namespace (let's say PID_NS1) and TASK B is the first task belonging to the new PID namespace created by unshare() (let's call it PID_NS2). 3) Since TASK B is the first task attached to PID_NS2, it becomes the PID_NS2 child reaper. 4) TASK A forks() again and creates TASK C which get attached to PID_NS2. Note how TASK C has TASK A as a parent (belonging to PID_NS1) but has TASK B (belonging to PID_NS2) as a pid_namespace child_reaper. 5) TASK B exits and since it is the child reaper for PID_NS2, it has to kill all other tasks attached to PID_NS2, and wait for all of them to die before getting reaped itself (zap_pid_ns_process()). 6) TASK A calls synchronize_rcu_tasks() which leads to synchronize_srcu(&tasks_rcu_exit_srcu). 7) TASK B is waiting for TASK C to get reaped. But TASK B is under a tasks_rcu_exit_srcu SRCU critical section (exit_notify() is between exit_tasks_rcu_start() and exit_tasks_rcu_finish()), blocking TASK A. 8) TASK C exits and since TASK A is its parent, it waits for it to reap TASK C, but it can't because TASK A waits for TASK B that waits for TASK C. Pid_namespace semantics can hardly be changed at this point. But the coverage of tasks_rcu_exit_srcu can be reduced instead. The current task is assumed not to be concurrently reapable at this stage of exit_notify() and therefore tasks_rcu_exit_srcu can be temporarily relaxed without breaking its constraints, providing a way out of the deadlock scenario. [ paulmck: Fix build failure by adding additional declaration. ] Fixes: 3f95aa81d265 ("rcu: Make TASKS_RCU handle tasks that are almost done exiting") Reported-by: Pengfei Xu Suggested-by: Boqun Feng Suggested-by: Neeraj Upadhyay Suggested-by: Paul E. McKenney Cc: Oleg Nesterov Cc: Lai Jiangshan Cc: Eric W . Biederman Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- include/linux/rcupdate.h | 2 ++ kernel/pid_namespace.c | 17 +++++++++++++++++ kernel/rcu/tasks.h | 15 +++++++++++++-- 3 files changed, 32 insertions(+), 2 deletions(-) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 095b3b39bd03..1f46db38d6ec 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -189,6 +189,7 @@ void synchronize_rcu_tasks_rude(void); #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); +void exit_tasks_rcu_stop(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_qs(t, preempt) do { } while (0) @@ -196,6 +197,7 @@ void exit_tasks_rcu_finish(void); #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } +static inline void exit_tasks_rcu_stop(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index ef8733e2a476..20243682e605 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -251,7 +251,24 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) set_current_state(TASK_INTERRUPTIBLE); if (pid_ns->pid_allocated == init_pids) break; + /* + * Release tasks_rcu_exit_srcu to avoid following deadlock: + * + * 1) TASK A unshare(CLONE_NEWPID) + * 2) TASK A fork() twice -> TASK B (child reaper for new ns) + * and TASK C + * 3) TASK B exits, kills TASK C, waits for TASK A to reap it + * 4) TASK A calls synchronize_rcu_tasks() + * -> synchronize_srcu(tasks_rcu_exit_srcu) + * 5) *DEADLOCK* + * + * It is considered safe to release tasks_rcu_exit_srcu here + * because we assume the current task can not be concurrently + * reaped at this point. + */ + exit_tasks_rcu_stop(); schedule(); + exit_tasks_rcu_start(); } __set_current_state(TASK_RUNNING); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index c4af3c05663f..df8143c8a6a8 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -604,17 +604,28 @@ void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu) * task is exiting and may be removed from the tasklist. See * corresponding synchronize_srcu() for further details. */ -void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu) +void exit_tasks_rcu_stop(void) __releases(&tasks_rcu_exit_srcu) { struct task_struct *t = current; __srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx); - exit_tasks_rcu_finish_trace(t); +} + +/* + * Contribute to protect against tasklist scan blind spot while the + * task is exiting and may be removed from the tasklist. See + * corresponding synchronize_srcu() for further details. + */ +void exit_tasks_rcu_finish(void) +{ + exit_tasks_rcu_stop(); + exit_tasks_rcu_finish_trace(current); } #else /* #ifdef CONFIG_TASKS_RCU */ static inline void show_rcu_tasks_classic_gp_kthread(void) { } void exit_tasks_rcu_start(void) { } +void exit_tasks_rcu_stop(void) { } void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); } #endif /* #else #ifdef CONFIG_TASKS_RCU */ From 318dd6f5b7b401a7496e8474ed41a6a0e345afe1 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 27 Dec 2022 15:27:39 +0100 Subject: [PATCH 1574/4345] lib/mpi: Fix buffer overrun when SG is too long [ Upstream commit 7361d1bc307b926cbca214ab67b641123c2d6357 ] The helper mpi_read_raw_from_sgl sets the number of entries in the SG list according to nbytes. However, if the last entry in the SG list contains more data than nbytes, then it may overrun the buffer because it only allocates enough memory for nbytes. Fixes: 2d4d1eea540b ("lib/mpi: Add mpi sgl helpers") Reported-by: Roberto Sassu Signed-off-by: Herbert Xu Reviewed-by: Eric Biggers Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- lib/mpi/mpicoder.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c index 7ea225b2204f..7054311d7879 100644 --- a/lib/mpi/mpicoder.c +++ b/lib/mpi/mpicoder.c @@ -504,7 +504,8 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes) while (sg_miter_next(&miter)) { buff = miter.addr; - len = miter.length; + len = min_t(unsigned, miter.length, nbytes); + nbytes -= len; for (x = 0; x < len; x++) { a <<= 8; From c997b509fd0168a3ced0b903c717f5b1a18a396b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 6 Apr 2021 15:49:49 -0700 Subject: [PATCH 1575/4345] crypto: ccp: Use the stack for small SEV command buffers [ Upstream commit e4a9af799e5539b0feb99571f0aaed5a3c81dc5a ] For commands with small input/output buffers, use the local stack to "allocate" the structures used to communicate with the PSP. Now that __sev_do_cmd_locked() gracefully handles vmalloc'd buffers, there's no reason to avoid using the stack, e.g. CONFIG_VMAP_STACK=y will just work. Signed-off-by: Sean Christopherson Message-Id: <20210406224952.4177376-6-seanjc@google.com> Reviewed-by: Brijesh Singh Acked-by: Tom Lendacky Signed-off-by: Paolo Bonzini Stable-dep-of: 91dfd98216d8 ("crypto: ccp - Avoid page allocation failure warning for SEV_GET_ID2") Signed-off-by: Sasha Levin --- drivers/crypto/ccp/sev-dev.c | 117 +++++++++++++---------------------- 1 file changed, 44 insertions(+), 73 deletions(-) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index ed39a22e1b2b..75341ad2fdd8 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -385,7 +385,7 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable) { struct sev_device *sev = psp_master->sev_data; struct sev_user_data_pek_csr input; - struct sev_data_pek_csr *data; + struct sev_data_pek_csr data; void __user *input_address; void *blob = NULL; int ret; @@ -396,9 +396,7 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable) if (copy_from_user(&input, (void __user *)argp->data, sizeof(input))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; + memset(&data, 0, sizeof(data)); /* userspace wants to query CSR length */ if (!input.address || !input.length) @@ -406,19 +404,15 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable) /* allocate a physically contiguous buffer to store the CSR blob */ input_address = (void __user *)input.address; - if (input.length > SEV_FW_BLOB_MAX_SIZE) { - ret = -EFAULT; - goto e_free; - } + if (input.length > SEV_FW_BLOB_MAX_SIZE) + return -EFAULT; blob = kmalloc(input.length, GFP_KERNEL); - if (!blob) { - ret = -ENOMEM; - goto e_free; - } + if (!blob) + return -ENOMEM; - data->address = __psp_pa(blob); - data->len = input.length; + data.address = __psp_pa(blob); + data.len = input.length; cmd: if (sev->state == SEV_STATE_UNINIT) { @@ -427,10 +421,10 @@ cmd: goto e_free_blob; } - ret = __sev_do_cmd_locked(SEV_CMD_PEK_CSR, data, &argp->error); + ret = __sev_do_cmd_locked(SEV_CMD_PEK_CSR, &data, &argp->error); /* If we query the CSR length, FW responded with expected data. */ - input.length = data->len; + input.length = data.len; if (copy_to_user((void __user *)argp->data, &input, sizeof(input))) { ret = -EFAULT; @@ -444,8 +438,6 @@ cmd: e_free_blob: kfree(blob); -e_free: - kfree(data); return ret; } @@ -577,7 +569,7 @@ static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) { struct sev_device *sev = psp_master->sev_data; struct sev_user_data_pek_cert_import input; - struct sev_data_pek_cert_import *data; + struct sev_data_pek_cert_import data; void *pek_blob, *oca_blob; int ret; @@ -587,19 +579,14 @@ static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) if (copy_from_user(&input, (void __user *)argp->data, sizeof(input))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; - /* copy PEK certificate blobs from userspace */ pek_blob = psp_copy_user_blob(input.pek_cert_address, input.pek_cert_len); - if (IS_ERR(pek_blob)) { - ret = PTR_ERR(pek_blob); - goto e_free; - } + if (IS_ERR(pek_blob)) + return PTR_ERR(pek_blob); - data->pek_cert_address = __psp_pa(pek_blob); - data->pek_cert_len = input.pek_cert_len; + data.reserved = 0; + data.pek_cert_address = __psp_pa(pek_blob); + data.pek_cert_len = input.pek_cert_len; /* copy PEK certificate blobs from userspace */ oca_blob = psp_copy_user_blob(input.oca_cert_address, input.oca_cert_len); @@ -608,8 +595,8 @@ static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) goto e_free_pek; } - data->oca_cert_address = __psp_pa(oca_blob); - data->oca_cert_len = input.oca_cert_len; + data.oca_cert_address = __psp_pa(oca_blob); + data.oca_cert_len = input.oca_cert_len; /* If platform is not in INIT state then transition it to INIT */ if (sev->state != SEV_STATE_INIT) { @@ -618,21 +605,19 @@ static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) goto e_free_oca; } - ret = __sev_do_cmd_locked(SEV_CMD_PEK_CERT_IMPORT, data, &argp->error); + ret = __sev_do_cmd_locked(SEV_CMD_PEK_CERT_IMPORT, &data, &argp->error); e_free_oca: kfree(oca_blob); e_free_pek: kfree(pek_blob); -e_free: - kfree(data); return ret; } static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp) { struct sev_user_data_get_id2 input; - struct sev_data_get_id *data; + struct sev_data_get_id data; void __user *input_address; void *id_blob = NULL; int ret; @@ -646,28 +631,25 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp) input_address = (void __user *)input.address; - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; - if (input.address && input.length) { id_blob = kmalloc(input.length, GFP_KERNEL); - if (!id_blob) { - kfree(data); + if (!id_blob) return -ENOMEM; - } - data->address = __psp_pa(id_blob); - data->len = input.length; + data.address = __psp_pa(id_blob); + data.len = input.length; + } else { + data.address = 0; + data.len = 0; } - ret = __sev_do_cmd_locked(SEV_CMD_GET_ID, data, &argp->error); + ret = __sev_do_cmd_locked(SEV_CMD_GET_ID, &data, &argp->error); /* * Firmware will return the length of the ID value (either the minimum * required length or the actual length written), return it to the user. */ - input.length = data->len; + input.length = data.len; if (copy_to_user((void __user *)argp->data, &input, sizeof(input))) { ret = -EFAULT; @@ -675,7 +657,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp) } if (id_blob) { - if (copy_to_user(input_address, id_blob, data->len)) { + if (copy_to_user(input_address, id_blob, data.len)) { ret = -EFAULT; goto e_free; } @@ -683,7 +665,6 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp) e_free: kfree(id_blob); - kfree(data); return ret; } @@ -733,7 +714,7 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) struct sev_device *sev = psp_master->sev_data; struct sev_user_data_pdh_cert_export input; void *pdh_blob = NULL, *cert_blob = NULL; - struct sev_data_pdh_cert_export *data; + struct sev_data_pdh_cert_export data; void __user *input_cert_chain_address; void __user *input_pdh_cert_address; int ret; @@ -751,9 +732,7 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) if (copy_from_user(&input, (void __user *)argp->data, sizeof(input))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; + memset(&data, 0, sizeof(data)); /* Userspace wants to query the certificate length. */ if (!input.pdh_cert_address || @@ -765,25 +744,19 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) input_cert_chain_address = (void __user *)input.cert_chain_address; /* Allocate a physically contiguous buffer to store the PDH blob. */ - if (input.pdh_cert_len > SEV_FW_BLOB_MAX_SIZE) { - ret = -EFAULT; - goto e_free; - } + if (input.pdh_cert_len > SEV_FW_BLOB_MAX_SIZE) + return -EFAULT; /* Allocate a physically contiguous buffer to store the cert chain blob. */ - if (input.cert_chain_len > SEV_FW_BLOB_MAX_SIZE) { - ret = -EFAULT; - goto e_free; - } + if (input.cert_chain_len > SEV_FW_BLOB_MAX_SIZE) + return -EFAULT; pdh_blob = kmalloc(input.pdh_cert_len, GFP_KERNEL); - if (!pdh_blob) { - ret = -ENOMEM; - goto e_free; - } + if (!pdh_blob) + return -ENOMEM; - data->pdh_cert_address = __psp_pa(pdh_blob); - data->pdh_cert_len = input.pdh_cert_len; + data.pdh_cert_address = __psp_pa(pdh_blob); + data.pdh_cert_len = input.pdh_cert_len; cert_blob = kmalloc(input.cert_chain_len, GFP_KERNEL); if (!cert_blob) { @@ -791,15 +764,15 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) goto e_free_pdh; } - data->cert_chain_address = __psp_pa(cert_blob); - data->cert_chain_len = input.cert_chain_len; + data.cert_chain_address = __psp_pa(cert_blob); + data.cert_chain_len = input.cert_chain_len; cmd: - ret = __sev_do_cmd_locked(SEV_CMD_PDH_CERT_EXPORT, data, &argp->error); + ret = __sev_do_cmd_locked(SEV_CMD_PDH_CERT_EXPORT, &data, &argp->error); /* If we query the length, FW responded with expected data. */ - input.cert_chain_len = data->cert_chain_len; - input.pdh_cert_len = data->pdh_cert_len; + input.cert_chain_len = data.cert_chain_len; + input.pdh_cert_len = data.pdh_cert_len; if (copy_to_user((void __user *)argp->data, &input, sizeof(input))) { ret = -EFAULT; @@ -824,8 +797,6 @@ e_free_cert: kfree(cert_blob); e_free_pdh: kfree(pdh_blob); -e_free: - kfree(data); return ret; } From daaec051cd19e917215a5889bc67d58c0931e433 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 6 Apr 2021 15:49:50 -0700 Subject: [PATCH 1576/4345] crypto: ccp: Use the stack and common buffer for status commands [ Upstream commit 38103671aad38e888743dd26c767869cfc15adca ] Drop the dedicated status_cmd_buf and instead use a local variable for PLATFORM_STATUS. Now that the low level helper uses an internal buffer for all commands, using the stack for the upper layers is safe even when running with CONFIG_VMAP_STACK=y. Signed-off-by: Sean Christopherson Message-Id: <20210406224952.4177376-7-seanjc@google.com> Reviewed-by: Brijesh Singh Acked-by: Tom Lendacky Signed-off-by: Paolo Bonzini Stable-dep-of: 91dfd98216d8 ("crypto: ccp - Avoid page allocation failure warning for SEV_GET_ID2") Signed-off-by: Sasha Levin --- drivers/crypto/ccp/sev-dev.c | 27 ++++++++++++--------------- drivers/crypto/ccp/sev-dev.h | 1 - 2 files changed, 12 insertions(+), 16 deletions(-) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 75341ad2fdd8..1aac3a12a6c7 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -304,15 +304,14 @@ static int sev_platform_shutdown(int *error) static int sev_get_platform_state(int *state, int *error) { - struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_status data; int rc; - rc = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, - &sev->status_cmd_buf, error); + rc = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, &data, error); if (rc) return rc; - *state = sev->status_cmd_buf.state; + *state = data.state; return rc; } @@ -350,15 +349,14 @@ static int sev_ioctl_do_reset(struct sev_issue_cmd *argp, bool writable) static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp) { - struct sev_device *sev = psp_master->sev_data; - struct sev_user_data_status *data = &sev->status_cmd_buf; + struct sev_user_data_status data; int ret; - ret = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, data, &argp->error); + ret = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, &data, &argp->error); if (ret) return ret; - if (copy_to_user((void __user *)argp->data, data, sizeof(*data))) + if (copy_to_user((void __user *)argp->data, &data, sizeof(data))) ret = -EFAULT; return ret; @@ -457,21 +455,20 @@ EXPORT_SYMBOL_GPL(psp_copy_user_blob); static int sev_get_api_version(void) { struct sev_device *sev = psp_master->sev_data; - struct sev_user_data_status *status; + struct sev_user_data_status status; int error = 0, ret; - status = &sev->status_cmd_buf; - ret = sev_platform_status(status, &error); + ret = sev_platform_status(&status, &error); if (ret) { dev_err(sev->dev, "SEV: failed to get status. Error: %#x\n", error); return 1; } - sev->api_major = status->api_major; - sev->api_minor = status->api_minor; - sev->build = status->build; - sev->state = status->state; + sev->api_major = status.api_major; + sev->api_minor = status.api_minor; + sev->build = status.build; + sev->state = status.state; return 0; } diff --git a/drivers/crypto/ccp/sev-dev.h b/drivers/crypto/ccp/sev-dev.h index dd5c4fe82914..3b0cd0f854df 100644 --- a/drivers/crypto/ccp/sev-dev.h +++ b/drivers/crypto/ccp/sev-dev.h @@ -46,7 +46,6 @@ struct sev_device { unsigned int int_rcvd; wait_queue_head_t int_queue; struct sev_misc_dev *misc; - struct sev_user_data_status status_cmd_buf; struct sev_data_init init_cmd_buf; u8 api_major; From 4c5300f6f5e18b11c02a92f136e69b98fddba15e Mon Sep 17 00:00:00 2001 From: John Allen Date: Wed, 18 May 2022 15:31:26 +0000 Subject: [PATCH 1577/4345] crypto: ccp - Use kzalloc for sev ioctl interfaces to prevent kernel memory leak [ Upstream commit 13dc15a3f5fd7f884e4bfa8c011a0ae868df12ae ] For some sev ioctl interfaces, input may be passed that is less than or equal to SEV_FW_BLOB_MAX_SIZE, but larger than the data that PSP firmware returns. In this case, kmalloc will allocate memory that is the size of the input rather than the size of the data. Since PSP firmware doesn't fully overwrite the buffer, the sev ioctl interfaces with the issue may return uninitialized slab memory. Currently, all of the ioctl interfaces in the ccp driver are safe, but to prevent future problems, change all ioctl interfaces that allocate memory with kmalloc to use kzalloc and memset the data buffer to zero in sev_ioctl_do_platform_status. Fixes: 38103671aad3 ("crypto: ccp: Use the stack and common buffer for status commands") Fixes: e799035609e15 ("crypto: ccp: Implement SEV_PEK_CSR ioctl command") Fixes: 76a2b524a4b1d ("crypto: ccp: Implement SEV_PDH_CERT_EXPORT ioctl command") Fixes: d6112ea0cb344 ("crypto: ccp - introduce SEV_GET_ID2 command") Cc: stable@vger.kernel.org Reported-by: Andy Nguyen Suggested-by: David Rientjes Suggested-by: Peter Gonda Signed-off-by: John Allen Reviewed-by: Peter Gonda Acked-by: David Rientjes Signed-off-by: Herbert Xu Stable-dep-of: 91dfd98216d8 ("crypto: ccp - Avoid page allocation failure warning for SEV_GET_ID2") Signed-off-by: Sasha Levin --- drivers/crypto/ccp/sev-dev.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 1aac3a12a6c7..6edd938ce6ac 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -352,6 +352,8 @@ static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp) struct sev_user_data_status data; int ret; + memset(&data, 0, sizeof(data)); + ret = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, &data, &argp->error); if (ret) return ret; @@ -405,7 +407,7 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable) if (input.length > SEV_FW_BLOB_MAX_SIZE) return -EFAULT; - blob = kmalloc(input.length, GFP_KERNEL); + blob = kzalloc(input.length, GFP_KERNEL); if (!blob) return -ENOMEM; @@ -629,7 +631,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp) input_address = (void __user *)input.address; if (input.address && input.length) { - id_blob = kmalloc(input.length, GFP_KERNEL); + id_blob = kzalloc(input.length, GFP_KERNEL); if (!id_blob) return -ENOMEM; @@ -748,14 +750,14 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) if (input.cert_chain_len > SEV_FW_BLOB_MAX_SIZE) return -EFAULT; - pdh_blob = kmalloc(input.pdh_cert_len, GFP_KERNEL); + pdh_blob = kzalloc(input.pdh_cert_len, GFP_KERNEL); if (!pdh_blob) return -ENOMEM; data.pdh_cert_address = __psp_pa(pdh_blob); data.pdh_cert_len = input.pdh_cert_len; - cert_blob = kmalloc(input.cert_chain_len, GFP_KERNEL); + cert_blob = kzalloc(input.cert_chain_len, GFP_KERNEL); if (!cert_blob) { ret = -ENOMEM; goto e_free_pdh; From 4c33e01fe1d294b46c0212f213b8553e53604375 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 30 Dec 2022 14:18:46 -0800 Subject: [PATCH 1578/4345] crypto: ccp - Avoid page allocation failure warning for SEV_GET_ID2 [ Upstream commit 91dfd98216d817ec5f1c55890bacb7b4fe9b068a ] For SEV_GET_ID2, the user provided length does not have a specified limitation because the length of the ID may change in the future. The kernel memory allocation, however, is implicitly limited to 4MB on x86 by the page allocator, otherwise the kzalloc() will fail. When this happens, it is best not to spam the kernel log with the warning. Simply fail the allocation and return ENOMEM to the user. Fixes: d6112ea0cb34 ("crypto: ccp - introduce SEV_GET_ID2 command") Reported-by: Andy Nguyen Reported-by: Peter Gonda Suggested-by: Herbert Xu Signed-off-by: David Rientjes Acked-by: Tom Lendacky Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/ccp/sev-dev.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 6edd938ce6ac..e70ae98de118 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -631,7 +631,14 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp) input_address = (void __user *)input.address; if (input.address && input.length) { - id_blob = kzalloc(input.length, GFP_KERNEL); + /* + * The length of the ID shouldn't be assumed by software since + * it may change in the future. The allocation size is limited + * to 1 << (PAGE_SHIFT + MAX_ORDER - 1) by the page allocator. + * If the allocation fails, simply return ENOMEM rather than + * warning in the kernel log. + */ + id_blob = kzalloc(input.length, GFP_KERNEL | __GFP_NOWARN); if (!id_blob) return -ENOMEM; From 5419cd28c8f29ccb347b5adbda1c2acc967700e6 Mon Sep 17 00:00:00 2001 From: Daniil Tatianin Date: Sat, 7 Jan 2023 02:53:08 +0300 Subject: [PATCH 1579/4345] ACPICA: nsrepair: handle cases without a return value correctly [ Upstream commit ca843a4c79486e99a19b859ef0b9887854afe146 ] Previously acpi_ns_simple_repair() would crash if expected_btypes contained any combination of ACPI_RTYPE_NONE with a different type, e.g | ACPI_RTYPE_INTEGER because of slightly incorrect logic in the !return_object branch, which wouldn't return AE_AML_NO_RETURN_VALUE for such cases. Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Link: https://github.com/acpica/acpica/pull/811 Fixes: 61db45ca2163 ("ACPICA: Restore code that repairs NULL package elements in return values.") Signed-off-by: Daniil Tatianin Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/acpica/nsrepair.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c index 90db2d85e7f5..f28d811a3724 100644 --- a/drivers/acpi/acpica/nsrepair.c +++ b/drivers/acpi/acpica/nsrepair.c @@ -181,8 +181,9 @@ acpi_ns_simple_repair(struct acpi_evaluate_info *info, * Try to fix if there was no return object. Warning if failed to fix. */ if (!return_object) { - if (expected_btypes && (!(expected_btypes & ACPI_RTYPE_NONE))) { - if (package_index != ACPI_NOT_PACKAGE_ELEMENT) { + if (expected_btypes) { + if (!(expected_btypes & ACPI_RTYPE_NONE) && + package_index != ACPI_NOT_PACKAGE_ELEMENT) { ACPI_WARN_PREDEFINED((AE_INFO, info->full_pathname, ACPI_WARN_ALWAYS, @@ -196,14 +197,15 @@ acpi_ns_simple_repair(struct acpi_evaluate_info *info, if (ACPI_SUCCESS(status)) { return (AE_OK); /* Repair was successful */ } - } else { + } + + if (expected_btypes != ACPI_RTYPE_NONE) { ACPI_WARN_PREDEFINED((AE_INFO, info->full_pathname, ACPI_WARN_ALWAYS, "Missing expected return value")); + return (AE_AML_NO_RETURN_VALUE); } - - return (AE_AML_NO_RETURN_VALUE); } } From e6ec7fa688d93839dcc1949b524e6b9bcea3a069 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sun, 1 Jan 2023 21:40:19 +0200 Subject: [PATCH 1580/4345] thermal/drivers/tsens: Drop msm8976-specific defines [ Upstream commit 3bf0ea99e2e32b0335106b86d84404cc85bcd113 ] Drop msm8976-specific defines, which duplicate generic ones. Fixes: 0e580290170d ("thermal: qcom: tsens-v1: Add support for MSM8956 and MSM8976") Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Konrad Dybcio Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230101194034.831222-6-dmitry.baryshkov@linaro.org Signed-off-by: Daniel Lezcano Signed-off-by: Sasha Levin --- drivers/thermal/qcom/tsens-v1.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/thermal/qcom/tsens-v1.c b/drivers/thermal/qcom/tsens-v1.c index 3c19a3800c6d..bff50f3b9d0b 100644 --- a/drivers/thermal/qcom/tsens-v1.c +++ b/drivers/thermal/qcom/tsens-v1.c @@ -78,11 +78,6 @@ #define MSM8976_CAL_SEL_MASK 0x3 -#define MSM8976_CAL_DEGC_PT1 30 -#define MSM8976_CAL_DEGC_PT2 120 -#define MSM8976_SLOPE_FACTOR 1000 -#define MSM8976_SLOPE_DEFAULT 3200 - /* eeprom layout data for qcs404/405 (v1) */ #define BASE0_MASK 0x000007f8 #define BASE1_MASK 0x0007f800 @@ -160,8 +155,8 @@ static void compute_intercept_slope_8976(struct tsens_priv *priv, priv->sensor[10].slope = 3286; for (i = 0; i < priv->num_sensors; i++) { - priv->sensor[i].offset = (p1[i] * MSM8976_SLOPE_FACTOR) - - (MSM8976_CAL_DEGC_PT1 * + priv->sensor[i].offset = (p1[i] * SLOPE_FACTOR) - + (CAL_DEGC_PT1 * priv->sensor[i].slope); } } From a9f2002484ec6bd40094fb5d3d2feb90dbcd705a Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Thu, 25 Feb 2021 22:31:19 +0100 Subject: [PATCH 1581/4345] thermal/drivers/qcom/tsens_v1: Enable sensor 3 on MSM8976 [ Upstream commit 007d81a4519f04fa5ced5e9e28bf70cd753c398d ] The sensor *is* in fact used and does report temperature. Signed-off-by: Konrad Dybcio Acked-by: Thara Gopinath Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20210225213119.116550-1-konrad.dybcio@somainline.org Stable-dep-of: a7d3006be5ca ("thermal/drivers/tsens: Sort out msm8976 vs msm8956 data") Signed-off-by: Sasha Levin --- drivers/thermal/qcom/tsens-v1.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/qcom/tsens-v1.c b/drivers/thermal/qcom/tsens-v1.c index bff50f3b9d0b..13624263f1df 100644 --- a/drivers/thermal/qcom/tsens-v1.c +++ b/drivers/thermal/qcom/tsens-v1.c @@ -375,11 +375,11 @@ static const struct tsens_ops ops_8976 = { .get_temp = get_temp_tsens_valid, }; -/* Valid for both MSM8956 and MSM8976. Sensor ID 3 is unused. */ +/* Valid for both MSM8956 and MSM8976. */ struct tsens_plat_data data_8976 = { .num_sensors = 11, .ops = &ops_8976, - .hw_ids = (unsigned int[]){0, 1, 2, 4, 5, 6, 7, 8, 9, 10}, + .hw_ids = (unsigned int[]){0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10}, .feat = &tsens_v1_feat, .fields = tsens_v1_regfields, }; From 40f62ff0d7edbbc77d0074e5321f7fe0d275e57f Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 6 Apr 2022 03:26:46 +0300 Subject: [PATCH 1582/4345] thermal/drivers/tsens: Add compat string for the qcom,msm8960 [ Upstream commit 2caf73969de6675318a711d0622406c8c66afc03 ] On apq8064 (msm8960) platforms the tsens device is created manually by the gcc driver. Prepare the tsens driver for the qcom,msm8960-tsens device instantiated from the device tree. Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20220406002648.393486-3-dmitry.baryshkov@linaro.org Signed-off-by: Daniel Lezcano Stable-dep-of: a7d3006be5ca ("thermal/drivers/tsens: Sort out msm8976 vs msm8956 data") Signed-off-by: Sasha Levin --- drivers/thermal/qcom/tsens.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c index cb4f4b522446..9e4a60db6e23 100644 --- a/drivers/thermal/qcom/tsens.c +++ b/drivers/thermal/qcom/tsens.c @@ -902,6 +902,9 @@ static const struct of_device_id tsens_table[] = { }, { .compatible = "qcom,msm8939-tsens", .data = &data_8939, + }, { + .compatible = "qcom,msm8960-tsens", + .data = &data_8960, }, { .compatible = "qcom,msm8974-tsens", .data = &data_8974, From 695f1d9431ff702eeecd637ff24698b17ceb7d42 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sun, 1 Jan 2023 21:40:20 +0200 Subject: [PATCH 1583/4345] thermal/drivers/tsens: Sort out msm8976 vs msm8956 data [ Upstream commit a7d3006be5ca7b04e4b84b5ceaae55a700e511bd ] Tsens driver mentions that msm8976 data should be used for both msm8976 and msm8956 SoCs. This is not quite correct, as according to the vendor kernels, msm8976 should use standard slope values (3200), while msm8956 really uses the slope values found in the driver. Add separate compatibility string for msm8956, move slope value overrides to the corresponding init function and use the standard compute_intercept_slope() function for both platforms. Fixes: 0e580290170d ("thermal: qcom: tsens-v1: Add support for MSM8956 and MSM8976") Cc: AngeloGioacchino Del Regno Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Konrad Dybcio Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230101194034.831222-7-dmitry.baryshkov@linaro.org Signed-off-by: Daniel Lezcano Signed-off-by: Sasha Levin --- drivers/thermal/qcom/tsens-v1.c | 56 ++++++++++++++++++--------------- drivers/thermal/qcom/tsens.c | 3 ++ drivers/thermal/qcom/tsens.h | 2 +- 3 files changed, 34 insertions(+), 27 deletions(-) diff --git a/drivers/thermal/qcom/tsens-v1.c b/drivers/thermal/qcom/tsens-v1.c index 13624263f1df..faa4576fa028 100644 --- a/drivers/thermal/qcom/tsens-v1.c +++ b/drivers/thermal/qcom/tsens-v1.c @@ -137,30 +137,6 @@ #define CAL_SEL_MASK 7 #define CAL_SEL_SHIFT 0 -static void compute_intercept_slope_8976(struct tsens_priv *priv, - u32 *p1, u32 *p2, u32 mode) -{ - int i; - - priv->sensor[0].slope = 3313; - priv->sensor[1].slope = 3275; - priv->sensor[2].slope = 3320; - priv->sensor[3].slope = 3246; - priv->sensor[4].slope = 3279; - priv->sensor[5].slope = 3257; - priv->sensor[6].slope = 3234; - priv->sensor[7].slope = 3269; - priv->sensor[8].slope = 3255; - priv->sensor[9].slope = 3239; - priv->sensor[10].slope = 3286; - - for (i = 0; i < priv->num_sensors; i++) { - priv->sensor[i].offset = (p1[i] * SLOPE_FACTOR) - - (CAL_DEGC_PT1 * - priv->sensor[i].slope); - } -} - static int calibrate_v1(struct tsens_priv *priv) { u32 base0 = 0, base1 = 0; @@ -286,7 +262,7 @@ static int calibrate_8976(struct tsens_priv *priv) break; } - compute_intercept_slope_8976(priv, p1, p2, mode); + compute_intercept_slope(priv, p1, p2, mode); kfree(qfprom_cdata); return 0; @@ -357,6 +333,22 @@ static const struct reg_field tsens_v1_regfields[MAX_REGFIELDS] = { [TRDY] = REG_FIELD(TM_TRDY_OFF, 0, 0), }; +static int __init init_8956(struct tsens_priv *priv) { + priv->sensor[0].slope = 3313; + priv->sensor[1].slope = 3275; + priv->sensor[2].slope = 3320; + priv->sensor[3].slope = 3246; + priv->sensor[4].slope = 3279; + priv->sensor[5].slope = 3257; + priv->sensor[6].slope = 3234; + priv->sensor[7].slope = 3269; + priv->sensor[8].slope = 3255; + priv->sensor[9].slope = 3239; + priv->sensor[10].slope = 3286; + + return init_common(priv); +} + static const struct tsens_ops ops_generic_v1 = { .init = init_common, .calibrate = calibrate_v1, @@ -369,13 +361,25 @@ struct tsens_plat_data data_tsens_v1 = { .fields = tsens_v1_regfields, }; +static const struct tsens_ops ops_8956 = { + .init = init_8956, + .calibrate = calibrate_8976, + .get_temp = get_temp_tsens_valid, +}; + +struct tsens_plat_data data_8956 = { + .num_sensors = 11, + .ops = &ops_8956, + .feat = &tsens_v1_feat, + .fields = tsens_v1_regfields, +}; + static const struct tsens_ops ops_8976 = { .init = init_common, .calibrate = calibrate_8976, .get_temp = get_temp_tsens_valid, }; -/* Valid for both MSM8956 and MSM8976. */ struct tsens_plat_data data_8976 = { .num_sensors = 11, .ops = &ops_8976, diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c index 9e4a60db6e23..c73792ca727a 100644 --- a/drivers/thermal/qcom/tsens.c +++ b/drivers/thermal/qcom/tsens.c @@ -902,6 +902,9 @@ static const struct of_device_id tsens_table[] = { }, { .compatible = "qcom,msm8939-tsens", .data = &data_8939, + }, { + .compatible = "qcom,msm8956-tsens", + .data = &data_8956, }, { .compatible = "qcom,msm8960-tsens", .data = &data_8960, diff --git a/drivers/thermal/qcom/tsens.h b/drivers/thermal/qcom/tsens.h index f40b625f897e..bbb1e8332821 100644 --- a/drivers/thermal/qcom/tsens.h +++ b/drivers/thermal/qcom/tsens.h @@ -588,7 +588,7 @@ extern struct tsens_plat_data data_8960; extern struct tsens_plat_data data_8916, data_8939, data_8974; /* TSENS v1 targets */ -extern struct tsens_plat_data data_tsens_v1, data_8976; +extern struct tsens_plat_data data_tsens_v1, data_8976, data_8956; /* TSENS v2 targets */ extern struct tsens_plat_data data_8996, data_tsens_v2; From 430f9f9bec53a75f9ccc53e156a66f13fc098b83 Mon Sep 17 00:00:00 2001 From: Bitterblue Smith Date: Thu, 22 Dec 2022 13:48:04 +0200 Subject: [PATCH 1584/4345] wifi: rtl8xxxu: Fix memory leaks with RTL8723BU, RTL8192EU [ Upstream commit b39f662ce1648db0b9de32e6a849b098480793cb ] The wifi + bluetooth combo chip RTL8723BU can leak memory (especially?) when it's connected to a bluetooth audio device. The busy bluetooth traffic generates lots of C2H (card to host) messages, which are not freed correctly. To fix this, move the dev_kfree_skb() call in rtl8xxxu_c2hcmd_callback() inside the loop where skb_dequeue() is called. The RTL8192EU leaks memory because the C2H messages are added to the queue and left there forever. (This was fine in the past because it probably wasn't sending any C2H messages until commit e542e66b7c2e ("wifi: rtl8xxxu: gen2: Turn on the rate control"). Since that commit it sends a C2H message when the TX rate changes.) To fix this, delete the check for rf_paths > 1 and the goto. Let the function process the C2H messages from RTL8192EU like the ones from the other chips. Theoretically the RTL8188FU could also leak like RTL8723BU, but it most likely doesn't send C2H messages frequently enough. This change was tested with RTL8723BU by Erhard F. I tested it with RTL8188FU and RTL8192EU. Reported-by: Erhard F. Tested-by: Erhard F. Link: https://bugzilla.kernel.org/show_bug.cgi?id=215197 Fixes: e542e66b7c2e ("rtl8xxxu: add bluetooth co-existence support for single antenna") Signed-off-by: Bitterblue Smith Reviewed-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/03b099c1-c671-d252-36f4-57b70d721f9d@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index f8b1871fe290..376782b7aba8 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -5491,9 +5491,6 @@ static void rtl8xxxu_c2hcmd_callback(struct work_struct *work) btcoex = &priv->bt_coex; rarpt = &priv->ra_report; - if (priv->rf_paths > 1) - goto out; - while (!skb_queue_empty(&priv->c2hcmd_queue)) { spin_lock_irqsave(&priv->c2hcmd_lock, flags); skb = __skb_dequeue(&priv->c2hcmd_queue); @@ -5547,10 +5544,9 @@ static void rtl8xxxu_c2hcmd_callback(struct work_struct *work) default: break; } - } -out: - dev_kfree_skb(skb); + dev_kfree_skb(skb); + } } static void rtl8723bu_handle_c2h(struct rtl8xxxu_priv *priv, From b44178e71810b9556fb14515fcea527b73b9573c Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Tue, 27 Dec 2022 16:33:06 +0300 Subject: [PATCH 1585/4345] wifi: orinoco: check return value of hermes_write_wordrec() [ Upstream commit 1e346cbb096a5351a637ec1992beffbf330547f0 ] There is currently no return check for writing an authentication type (HERMES_AUTH_SHARED_KEY or HERMES_AUTH_OPEN). It looks like it was accidentally skipped. This patch adds a return check similar to the other checks in __orinoco_hw_setup_enc() for hermes_write_wordrec(). Detected using the static analysis tool - Svace. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Alexey Kodanev Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221227133306.201356-1-aleksei.kodanev@bell-sw.com Signed-off-by: Sasha Levin --- drivers/net/wireless/intersil/orinoco/hw.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wireless/intersil/orinoco/hw.c b/drivers/net/wireless/intersil/orinoco/hw.c index 61af5a28f269..af49aa421e47 100644 --- a/drivers/net/wireless/intersil/orinoco/hw.c +++ b/drivers/net/wireless/intersil/orinoco/hw.c @@ -931,6 +931,8 @@ int __orinoco_hw_setup_enc(struct orinoco_private *priv) err = hermes_write_wordrec(hw, USER_BAP, HERMES_RID_CNFAUTHENTICATION_AGERE, auth_flag); + if (err) + return err; } err = hermes_write_wordrec(hw, USER_BAP, HERMES_RID_CNFWEPENABLED_AGERE, From ec246dfe006b2a8f36353f7489e4f525114db9a5 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Wed, 4 Jan 2023 15:35:46 +0300 Subject: [PATCH 1586/4345] wifi: ath9k: htc_hst: free skb in ath9k_htc_rx_msg() if there is no callback function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9b25e3985477ac3f02eca5fc1e0cc6850a3f7e69 ] It is stated that ath9k_htc_rx_msg() either frees the provided skb or passes its management to another callback function. However, the skb is not freed in case there is no another callback function, and Syzkaller was able to cause a memory leak. Also minor comment fix. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.") Reported-by: syzbot+e008dccab31bd3647609@syzkaller.appspotmail.com Reported-by: syzbot+6692c72009680f7c4eb2@syzkaller.appspotmail.com Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230104123546.51427-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/htc_hst.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c index ca05b07a45e6..fe62ff668f75 100644 --- a/drivers/net/wireless/ath/ath9k/htc_hst.c +++ b/drivers/net/wireless/ath/ath9k/htc_hst.c @@ -391,7 +391,7 @@ static void ath9k_htc_fw_panic_report(struct htc_target *htc_handle, * HTC Messages are handled directly here and the obtained SKB * is freed. * - * Service messages (Data, WMI) passed to the corresponding + * Service messages (Data, WMI) are passed to the corresponding * endpoint RX handlers, which have to free the SKB. */ void ath9k_htc_rx_msg(struct htc_target *htc_handle, @@ -478,6 +478,8 @@ invalid: if (endpoint->ep_callbacks.rx) endpoint->ep_callbacks.rx(endpoint->ep_callbacks.priv, skb, epid); + else + goto invalid; } } From 221f9bd5ec56933c3e1ee07ff941804296ad5560 Mon Sep 17 00:00:00 2001 From: Wan Jiabing Date: Wed, 27 Apr 2022 10:37:32 +0300 Subject: [PATCH 1587/4345] ath9k: hif_usb: simplify if-if to if-else MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2950833f10cfa601813262e1d9c8473f9415681b ] Use if and else instead of if(A) and if (!A). Signed-off-by: Wan Jiabing Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220424094441.104937-1-wanjiabing@vivo.com Stable-dep-of: 0af54343a762 ("wifi: ath9k: hif_usb: clean up skbs if ath9k_hif_usb_rx_stream() fails") Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/hif_usb.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index f938ac1a4abd..f54380fb6c9e 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -368,10 +368,9 @@ static int __hif_usb_tx(struct hif_device_usb *hif_dev) __skb_queue_head_init(&tx_buf->skb_queue); list_move_tail(&tx_buf->list, &hif_dev->tx.tx_buf); hif_dev->tx.tx_buf_cnt++; - } - - if (!ret) + } else { TX_STAT_INC(buf_queued); + } return ret; } From 5668e63e2673303d969a075aa5c028d3758a4a6e Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Mon, 13 Jun 2022 21:44:07 +0300 Subject: [PATCH 1588/4345] ath9k: htc: clean up statistics macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d7fc76039b74ad37b7056d5607b05d7cb31a5404 ] I've changed *STAT_* macros a bit in previous patch and I seems like they become really unreadable. Align these macros definitions to make code cleaner and fix folllowing checkpatch warning ERROR: Macros with complex values should be enclosed in parentheses Also, statistics macros now accept an hif_dev as argument, since macros that depend on having a local variable with a magic name don't abide by the coding style. No functional change Suggested-by: Jeff Johnson Signed-off-by: Pavel Skripkin Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/ebb2306d06a496cd1b032155ae52fdc5fa8cc2c5.1655145743.git.paskripkin@gmail.com Stable-dep-of: 0af54343a762 ("wifi: ath9k: hif_usb: clean up skbs if ath9k_hif_usb_rx_stream() fails") Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/hif_usb.c | 26 ++++++++-------- drivers/net/wireless/ath/ath9k/htc.h | 30 +++++++++++-------- drivers/net/wireless/ath/ath9k/htc_drv_txrx.c | 10 +++---- 3 files changed, 35 insertions(+), 31 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index f54380fb6c9e..1a2e0c7eeb02 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -244,11 +244,11 @@ static inline void ath9k_skb_queue_complete(struct hif_device_usb *hif_dev, ath9k_htc_txcompletion_cb(hif_dev->htc_handle, skb, txok); if (txok) { - TX_STAT_INC(skb_success); - TX_STAT_ADD(skb_success_bytes, ln); + TX_STAT_INC(hif_dev, skb_success); + TX_STAT_ADD(hif_dev, skb_success_bytes, ln); } else - TX_STAT_INC(skb_failed); + TX_STAT_INC(hif_dev, skb_failed); } } @@ -302,7 +302,7 @@ static void hif_usb_tx_cb(struct urb *urb) hif_dev->tx.tx_buf_cnt++; if (!(hif_dev->tx.flags & HIF_USB_TX_STOP)) __hif_usb_tx(hif_dev); /* Check for pending SKBs */ - TX_STAT_INC(buf_completed); + TX_STAT_INC(hif_dev, buf_completed); spin_unlock(&hif_dev->tx.tx_lock); } @@ -353,7 +353,7 @@ static int __hif_usb_tx(struct hif_device_usb *hif_dev) tx_buf->len += tx_buf->offset; __skb_queue_tail(&tx_buf->skb_queue, nskb); - TX_STAT_INC(skb_queued); + TX_STAT_INC(hif_dev, skb_queued); } usb_fill_bulk_urb(tx_buf->urb, hif_dev->udev, @@ -369,7 +369,7 @@ static int __hif_usb_tx(struct hif_device_usb *hif_dev) list_move_tail(&tx_buf->list, &hif_dev->tx.tx_buf); hif_dev->tx.tx_buf_cnt++; } else { - TX_STAT_INC(buf_queued); + TX_STAT_INC(hif_dev, buf_queued); } return ret; @@ -514,7 +514,7 @@ static void hif_usb_sta_drain(void *hif_handle, u8 idx) ath9k_htc_txcompletion_cb(hif_dev->htc_handle, skb, false); hif_dev->tx.tx_skb_cnt--; - TX_STAT_INC(skb_failed); + TX_STAT_INC(hif_dev, skb_failed); } } @@ -585,14 +585,14 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, pkt_tag = get_unaligned_le16(ptr + index + 2); if (pkt_tag != ATH_USB_RX_STREAM_MODE_TAG) { - RX_STAT_INC(skb_dropped); + RX_STAT_INC(hif_dev, skb_dropped); return; } if (pkt_len > 2 * MAX_RX_BUF_SIZE) { dev_err(&hif_dev->udev->dev, "ath9k_htc: invalid pkt_len (%x)\n", pkt_len); - RX_STAT_INC(skb_dropped); + RX_STAT_INC(hif_dev, skb_dropped); return; } @@ -618,7 +618,7 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, goto err; } skb_reserve(nskb, 32); - RX_STAT_INC(skb_allocated); + RX_STAT_INC(hif_dev, skb_allocated); memcpy(nskb->data, &(skb->data[chk_idx+4]), hif_dev->rx_transfer_len); @@ -639,7 +639,7 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, goto err; } skb_reserve(nskb, 32); - RX_STAT_INC(skb_allocated); + RX_STAT_INC(hif_dev, skb_allocated); memcpy(nskb->data, &(skb->data[chk_idx+4]), pkt_len); skb_put(nskb, pkt_len); @@ -649,10 +649,10 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, err: for (i = 0; i < pool_index; i++) { - RX_STAT_ADD(skb_completed_bytes, skb_pool[i]->len); + RX_STAT_ADD(hif_dev, skb_completed_bytes, skb_pool[i]->len); ath9k_htc_rx_msg(hif_dev->htc_handle, skb_pool[i], skb_pool[i]->len, USB_WLAN_RX_PIPE); - RX_STAT_INC(skb_completed); + RX_STAT_INC(hif_dev, skb_completed); } } diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index e3d546ef71dd..30f0765fb9fd 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -327,14 +327,18 @@ static inline struct ath9k_htc_tx_ctl *HTC_SKB_CB(struct sk_buff *skb) } #ifdef CONFIG_ATH9K_HTC_DEBUGFS -#define __STAT_SAFE(expr) (hif_dev->htc_handle->drv_priv ? (expr) : 0) -#define TX_STAT_INC(c) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.tx_stats.c++) -#define TX_STAT_ADD(c, a) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.tx_stats.c += a) -#define RX_STAT_INC(c) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c++) -#define RX_STAT_ADD(c, a) __STAT_SAFE(hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c += a) -#define CAB_STAT_INC priv->debug.tx_stats.cab_queued++ +#define __STAT_SAFE(hif_dev, expr) ((hif_dev)->htc_handle->drv_priv ? (expr) : 0) +#define CAB_STAT_INC(priv) ((priv)->debug.tx_stats.cab_queued++) +#define TX_QSTAT_INC(priv, q) ((priv)->debug.tx_stats.queue_stats[q]++) -#define TX_QSTAT_INC(q) (priv->debug.tx_stats.queue_stats[q]++) +#define TX_STAT_INC(hif_dev, c) \ + __STAT_SAFE((hif_dev), (hif_dev)->htc_handle->drv_priv->debug.tx_stats.c++) +#define TX_STAT_ADD(hif_dev, c, a) \ + __STAT_SAFE((hif_dev), (hif_dev)->htc_handle->drv_priv->debug.tx_stats.c += a) +#define RX_STAT_INC(hif_dev, c) \ + __STAT_SAFE((hif_dev), (hif_dev)->htc_handle->drv_priv->debug.skbrx_stats.c++) +#define RX_STAT_ADD(hif_dev, c, a) \ + __STAT_SAFE((hif_dev), (hif_dev)->htc_handle->drv_priv->debug.skbrx_stats.c += a) void ath9k_htc_err_stat_rx(struct ath9k_htc_priv *priv, struct ath_rx_status *rs); @@ -374,13 +378,13 @@ void ath9k_htc_get_et_stats(struct ieee80211_hw *hw, struct ethtool_stats *stats, u64 *data); #else -#define TX_STAT_INC(c) do { } while (0) -#define TX_STAT_ADD(c, a) do { } while (0) -#define RX_STAT_INC(c) do { } while (0) -#define RX_STAT_ADD(c, a) do { } while (0) -#define CAB_STAT_INC do { } while (0) +#define TX_STAT_INC(hif_dev, c) +#define TX_STAT_ADD(hif_dev, c, a) +#define RX_STAT_INC(hif_dev, c) +#define RX_STAT_ADD(hif_dev, c, a) -#define TX_QSTAT_INC(c) do { } while (0) +#define CAB_STAT_INC(priv) +#define TX_QSTAT_INC(priv, c) static inline void ath9k_htc_err_stat_rx(struct ath9k_htc_priv *priv, struct ath_rx_status *rs) diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c index 43a743ec9d9e..622fc7f17040 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c @@ -106,20 +106,20 @@ static inline enum htc_endpoint_id get_htc_epid(struct ath9k_htc_priv *priv, switch (qnum) { case 0: - TX_QSTAT_INC(IEEE80211_AC_VO); + TX_QSTAT_INC(priv, IEEE80211_AC_VO); epid = priv->data_vo_ep; break; case 1: - TX_QSTAT_INC(IEEE80211_AC_VI); + TX_QSTAT_INC(priv, IEEE80211_AC_VI); epid = priv->data_vi_ep; break; case 2: - TX_QSTAT_INC(IEEE80211_AC_BE); + TX_QSTAT_INC(priv, IEEE80211_AC_BE); epid = priv->data_be_ep; break; case 3: default: - TX_QSTAT_INC(IEEE80211_AC_BK); + TX_QSTAT_INC(priv, IEEE80211_AC_BK); epid = priv->data_bk_ep; break; } @@ -323,7 +323,7 @@ static void ath9k_htc_tx_data(struct ath9k_htc_priv *priv, memcpy(tx_fhdr, (u8 *) &tx_hdr, sizeof(tx_hdr)); if (is_cab) { - CAB_STAT_INC; + CAB_STAT_INC(priv); tx_ctl->epid = priv->cab_ep; return; } From f26dd69f61eff2eedf5df2d199bdd23108309947 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Wed, 4 Jan 2023 15:36:15 +0300 Subject: [PATCH 1589/4345] wifi: ath9k: hif_usb: clean up skbs if ath9k_hif_usb_rx_stream() fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0af54343a76263a12dbae7fafb64eb47c4a6ad38 ] Syzkaller detected a memory leak of skbs in ath9k_hif_usb_rx_stream(). While processing skbs in ath9k_hif_usb_rx_stream(), the already allocated skbs in skb_pool are not freed if ath9k_hif_usb_rx_stream() fails. If we have an incorrect pkt_len or pkt_tag, the input skb is considered invalid and dropped. All the associated packets already in skb_pool should be dropped and freed. Added a comment describing this issue. The patch also makes remain_skb NULL after being processed so that it cannot be referenced after potential free. The initialization of hif_dev fields which are associated with remain_skb (rx_remain_len, rx_transfer_len and rx_pad_len) is moved after a new remain_skb is allocated. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: 6ce708f54cc8 ("ath9k: Fix out-of-bound memcpy in ath9k_hif_usb_rx_stream") Fixes: 44b23b488d44 ("ath9k: hif_usb: Reduce indent 1 column") Reported-by: syzbot+e9632e3eb038d93d6bc6@syzkaller.appspotmail.com Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230104123615.51511-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/hif_usb.c | 31 +++++++++++++++++------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 1a2e0c7eeb02..de6c0824c9ca 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -561,11 +561,11 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, memcpy(ptr, skb->data, rx_remain_len); rx_pkt_len += rx_remain_len; - hif_dev->rx_remain_len = 0; skb_put(remain_skb, rx_pkt_len); skb_pool[pool_index++] = remain_skb; - + hif_dev->remain_skb = NULL; + hif_dev->rx_remain_len = 0; } else { index = rx_remain_len; } @@ -584,16 +584,21 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, pkt_len = get_unaligned_le16(ptr + index); pkt_tag = get_unaligned_le16(ptr + index + 2); + /* It is supposed that if we have an invalid pkt_tag or + * pkt_len then the whole input SKB is considered invalid + * and dropped; the associated packets already in skb_pool + * are dropped, too. + */ if (pkt_tag != ATH_USB_RX_STREAM_MODE_TAG) { RX_STAT_INC(hif_dev, skb_dropped); - return; + goto invalid_pkt; } if (pkt_len > 2 * MAX_RX_BUF_SIZE) { dev_err(&hif_dev->udev->dev, "ath9k_htc: invalid pkt_len (%x)\n", pkt_len); RX_STAT_INC(hif_dev, skb_dropped); - return; + goto invalid_pkt; } pad_len = 4 - (pkt_len & 0x3); @@ -605,11 +610,6 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, if (index > MAX_RX_BUF_SIZE) { spin_lock(&hif_dev->rx_lock); - hif_dev->rx_remain_len = index - MAX_RX_BUF_SIZE; - hif_dev->rx_transfer_len = - MAX_RX_BUF_SIZE - chk_idx - 4; - hif_dev->rx_pad_len = pad_len; - nskb = __dev_alloc_skb(pkt_len + 32, GFP_ATOMIC); if (!nskb) { dev_err(&hif_dev->udev->dev, @@ -617,6 +617,12 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, spin_unlock(&hif_dev->rx_lock); goto err; } + + hif_dev->rx_remain_len = index - MAX_RX_BUF_SIZE; + hif_dev->rx_transfer_len = + MAX_RX_BUF_SIZE - chk_idx - 4; + hif_dev->rx_pad_len = pad_len; + skb_reserve(nskb, 32); RX_STAT_INC(hif_dev, skb_allocated); @@ -654,6 +660,13 @@ err: skb_pool[i]->len, USB_WLAN_RX_PIPE); RX_STAT_INC(hif_dev, skb_completed); } + return; +invalid_pkt: + for (i = 0; i < pool_index; i++) { + dev_kfree_skb_any(skb_pool[i]); + RX_STAT_INC(hif_dev, skb_dropped); + } + return; } static void ath9k_hif_usb_rx_cb(struct urb *urb) From 78b56b0a613a87b61290b95be497fdfe2fe58aa6 Mon Sep 17 00:00:00 2001 From: Minsuk Kang Date: Wed, 4 Jan 2023 21:41:30 +0900 Subject: [PATCH 1590/4345] wifi: ath9k: Fix potential stack-out-of-bounds write in ath9k_wmi_rsp_callback() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 8a2f35b9830692f7a616f2f627f943bc748af13a ] Fix a stack-out-of-bounds write that occurs in a WMI response callback function that is called after a timeout occurs in ath9k_wmi_cmd(). The callback writes to wmi->cmd_rsp_buf, a stack-allocated buffer that could no longer be valid when a timeout occurs. Set wmi->last_seq_id to 0 when a timeout occurred. Found by a modified version of syzkaller. BUG: KASAN: stack-out-of-bounds in ath9k_wmi_ctrl_rx Write of size 4 Call Trace: memcpy ath9k_wmi_ctrl_rx ath9k_htc_rx_msg ath9k_hif_usb_reg_in_cb __usb_hcd_giveback_urb usb_hcd_giveback_urb dummy_timer call_timer_fn run_timer_softirq __do_softirq irq_exit_rcu sysvec_apic_timer_interrupt Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.") Signed-off-by: Minsuk Kang Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230104124130.10996-1-linuxlovemin@yonsei.ac.kr Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/wmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c index f315c54bd3ac..19345b8f7bfd 100644 --- a/drivers/net/wireless/ath/ath9k/wmi.c +++ b/drivers/net/wireless/ath/ath9k/wmi.c @@ -341,6 +341,7 @@ int ath9k_wmi_cmd(struct wmi *wmi, enum wmi_cmd_id cmd_id, if (!time_left) { ath_dbg(common, WMI, "Timeout waiting for WMI command: %s\n", wmi_cmd_to_name(cmd_id)); + wmi->last_seq_id = 0; mutex_unlock(&wmi->op_mutex); return -ETIMEDOUT; } From 137963e3b95776f1d57c62f249a93fe47e019a22 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 2 Jan 2023 12:11:42 +0400 Subject: [PATCH 1591/4345] wifi: ath11k: Fix memory leak in ath11k_peer_rx_frag_setup [ Upstream commit ed3f83b3459a67a3ab9d806490ac304b567b1c2d ] crypto_alloc_shash() allocates resources, which should be released by crypto_free_shash(). When ath11k_peer_find() fails, there has memory leak. Add missing crypto_free_shash() to fix this. Fixes: 243874c64c81 ("ath11k: handle RX fragments") Signed-off-by: Miaoqian Lin Reviewed-by: Leon Romanovsky Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230102081142.3937570-1-linmq006@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/dp_rx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 2e77dca6b1ad..578fdc446bc0 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -3022,6 +3022,7 @@ int ath11k_peer_rx_frag_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id if (!peer) { ath11k_warn(ab, "failed to find the peer to set up fragment info\n"); spin_unlock_bh(&ab->base_lock); + crypto_free_shash(tfm); return -ENOENT; } From 45a1ca6f3ae7c75cc317a0850196e08af76f583b Mon Sep 17 00:00:00 2001 From: Shivani Baranwal Date: Tue, 6 Dec 2022 20:07:14 +0530 Subject: [PATCH 1592/4345] wifi: cfg80211: Fix extended KCK key length check in nl80211_set_rekey_data() [ Upstream commit df4969ca135b9b3b2c38c07514aaa775112ac835 ] The extended KCK key length check wrongly using the KEK key attribute for validation. Due to this GTK rekey offload is failing when the KCK key length is 24 bytes even though the driver advertising WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK flag. Use correct attribute to fix the same. Fixes: 093a48d2aa4b ("cfg80211: support bigger kek/kck key length") Signed-off-by: Shivani Baranwal Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/20221206143715.1802987-2-quic_vjakkam@quicinc.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/nl80211.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8a7f0c8fba5e..ea36d8c47b31 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12675,7 +12675,7 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) return -ERANGE; if (nla_len(tb[NL80211_REKEY_DATA_KCK]) != NL80211_KCK_LEN && !(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK && - nla_len(tb[NL80211_REKEY_DATA_KEK]) == NL80211_KCK_EXT_LEN)) + nla_len(tb[NL80211_REKEY_DATA_KCK]) == NL80211_KCK_EXT_LEN)) return -ERANGE; rekey_data.kek = nla_data(tb[NL80211_REKEY_DATA_KEK]); From 6fb7dead798c97f6c13acdea1023979d16dd7482 Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Sat, 14 Jan 2023 09:50:50 +0100 Subject: [PATCH 1593/4345] ACPI: battery: Fix missing NUL-termination with large strings [ Upstream commit f2ac14b5f197e4a2dec51e5ceaa56682ff1592bc ] When encountering a string bigger than the destination buffer (32 bytes), the string is not properly NUL-terminated, causing buffer overreads later. This for example happens on the Inspiron 3505, where the battery model name is larger than 32 bytes, which leads to sysfs showing the model name together with the serial number string (which is NUL-terminated and thus prevents worse). Fix this by using strscpy() which ensures that the result is always NUL-terminated. Fixes: 106449e870b3 ("ACPI: Battery: Allow extract string from integer") Signed-off-by: Armin Wolf Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/battery.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index be743d177bcb..8b43efe97da5 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -454,7 +454,7 @@ static int extract_package(struct acpi_battery *battery, u8 *ptr = (u8 *)battery + offsets[i].offset; if (element->type == ACPI_TYPE_STRING || element->type == ACPI_TYPE_BUFFER) - strncpy(ptr, element->string.pointer, 32); + strscpy(ptr, element->string.pointer, 32); else if (element->type == ACPI_TYPE_INTEGER) { strncpy(ptr, (u8 *)&element->integer.value, sizeof(u64)); From 62d428c9fe1b3c1c4aabab710e464f8e360b2786 Mon Sep 17 00:00:00 2001 From: Koba Ko Date: Mon, 9 Jan 2023 10:15:02 +0800 Subject: [PATCH 1594/4345] crypto: ccp - Failure on re-initialization due to duplicate sysfs filename [ Upstream commit 299bf602b3f92f1456aef59c6413591fb02e762a ] The following warning appears during the CCP module re-initialization: [ 140.965403] sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:07.1/0000:03:00.2/dma/dma0chan0' [ 140.975736] CPU: 0 PID: 388 Comm: kworker/0:2 Kdump: loaded Not tainted 6.2.0-0.rc2.18.eln124.x86_64 #1 [ 140.985185] Hardware name: HPE ProLiant DL325 Gen10/ProLiant DL325 Gen10, BIOS A41 07/17/2020 [ 140.993761] Workqueue: events work_for_cpu_fn [ 140.998151] Call Trace: [ 141.000613] [ 141.002726] dump_stack_lvl+0x33/0x46 [ 141.006415] sysfs_warn_dup.cold+0x17/0x23 [ 141.010542] sysfs_create_dir_ns+0xba/0xd0 [ 141.014670] kobject_add_internal+0xba/0x260 [ 141.018970] kobject_add+0x81/0xb0 [ 141.022395] device_add+0xdc/0x7e0 [ 141.025822] ? complete_all+0x20/0x90 [ 141.029510] __dma_async_device_channel_register+0xc9/0x130 [ 141.035119] dma_async_device_register+0x19e/0x3b0 [ 141.039943] ccp_dmaengine_register+0x334/0x3f0 [ccp] [ 141.045042] ccp5_init+0x662/0x6a0 [ccp] [ 141.049000] ? devm_kmalloc+0x40/0xd0 [ 141.052688] ccp_dev_init+0xbb/0xf0 [ccp] [ 141.056732] ? __pci_set_master+0x56/0xd0 [ 141.060768] sp_init+0x70/0x90 [ccp] [ 141.064377] sp_pci_probe+0x186/0x1b0 [ccp] [ 141.068596] local_pci_probe+0x41/0x80 [ 141.072374] work_for_cpu_fn+0x16/0x20 [ 141.076145] process_one_work+0x1c8/0x380 [ 141.080181] worker_thread+0x1ab/0x380 [ 141.083953] ? __pfx_worker_thread+0x10/0x10 [ 141.088250] kthread+0xda/0x100 [ 141.091413] ? __pfx_kthread+0x10/0x10 [ 141.095185] ret_from_fork+0x2c/0x50 [ 141.098788] [ 141.100996] kobject_add_internal failed for dma0chan0 with -EEXIST, don't try to register things with the same name in the same directory. [ 141.113703] ccp 0000:03:00.2: ccp initialization failed The /dma/dma0chan0 sysfs file is not removed since dma_chan object has been released in ccp_dma_release() before releasing dma device. A correct procedure would be: release dma channels first => unregister dma device => release ccp dma object. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216888 Fixes: 68dbe80f5b51 ("crypto: ccp - Release dma channels before dmaengine unrgister") Tested-by: Vladis Dronov Signed-off-by: Koba Ko Reviewed-by: Vladis Dronov Acked-by: Tom Lendacky Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/ccp/ccp-dmaengine.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c index b9299defb431..e416456b2b8a 100644 --- a/drivers/crypto/ccp/ccp-dmaengine.c +++ b/drivers/crypto/ccp/ccp-dmaengine.c @@ -643,14 +643,26 @@ static void ccp_dma_release(struct ccp_device *ccp) chan = ccp->ccp_dma_chan + i; dma_chan = &chan->dma_chan; - if (dma_chan->client_count) - dma_release_channel(dma_chan); - tasklet_kill(&chan->cleanup_tasklet); list_del_rcu(&dma_chan->device_node); } } +static void ccp_dma_release_channels(struct ccp_device *ccp) +{ + struct ccp_dma_chan *chan; + struct dma_chan *dma_chan; + unsigned int i; + + for (i = 0; i < ccp->cmd_q_count; i++) { + chan = ccp->ccp_dma_chan + i; + dma_chan = &chan->dma_chan; + + if (dma_chan->client_count) + dma_release_channel(dma_chan); + } +} + int ccp_dmaengine_register(struct ccp_device *ccp) { struct ccp_dma_chan *chan; @@ -771,8 +783,9 @@ void ccp_dmaengine_unregister(struct ccp_device *ccp) if (!dmaengine) return; - ccp_dma_release(ccp); + ccp_dma_release_channels(ccp); dma_async_device_unregister(dma_dev); + ccp_dma_release(ccp); kmem_cache_destroy(ccp->dma_desc_cache); kmem_cache_destroy(ccp->dma_cmd_cache); From 796e02cca30a67322161f0745e5ce994bbe75605 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 13 Jan 2023 18:24:09 +0800 Subject: [PATCH 1595/4345] crypto: essiv - Handle EBUSY correctly [ Upstream commit b5a772adf45a32c68bef28e60621f12617161556 ] As it is essiv only handles the special return value of EINPROGERSS, which means that in all other cases it will free data related to the request. However, as the caller of essiv may specify MAY_BACKLOG, we also need to expect EBUSY and treat it in the same way. Otherwise backlogged requests will trigger a use-after-free. Fixes: be1eb7f78aa8 ("crypto: essiv - create wrapper template...") Signed-off-by: Herbert Xu Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/essiv.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/crypto/essiv.c b/crypto/essiv.c index d012be23d496..85bb624e32b9 100644 --- a/crypto/essiv.c +++ b/crypto/essiv.c @@ -170,7 +170,12 @@ static void essiv_aead_done(struct crypto_async_request *areq, int err) struct aead_request *req = areq->data; struct essiv_aead_request_ctx *rctx = aead_request_ctx(req); + if (err == -EINPROGRESS) + goto out; + kfree(rctx->assoc); + +out: aead_request_complete(req, err); } @@ -246,7 +251,7 @@ static int essiv_aead_crypt(struct aead_request *req, bool enc) err = enc ? crypto_aead_encrypt(subreq) : crypto_aead_decrypt(subreq); - if (rctx->assoc && err != -EINPROGRESS) + if (rctx->assoc && err != -EINPROGRESS && err != -EBUSY) kfree(rctx->assoc); return err; } From ae849d2f48019ff9c104e32bf588ccbfb200e971 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 13 Jan 2023 18:27:51 +0800 Subject: [PATCH 1596/4345] crypto: seqiv - Handle EBUSY correctly [ Upstream commit 32e62025e5e52fbe4812ef044759de7010b15dbc ] As it is seqiv only handles the special return value of EINPROGERSS, which means that in all other cases it will free data related to the request. However, as the caller of seqiv may specify MAY_BACKLOG, we also need to expect EBUSY and treat it in the same way. Otherwise backlogged requests will trigger a use-after-free. Fixes: 0a270321dbf9 ("[CRYPTO] seqiv: Add Sequence Number IV Generator") Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/seqiv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crypto/seqiv.c b/crypto/seqiv.c index 0899d527c284..b1bcfe537daf 100644 --- a/crypto/seqiv.c +++ b/crypto/seqiv.c @@ -23,7 +23,7 @@ static void seqiv_aead_encrypt_complete2(struct aead_request *req, int err) struct aead_request *subreq = aead_request_ctx(req); struct crypto_aead *geniv; - if (err == -EINPROGRESS) + if (err == -EINPROGRESS || err == -EBUSY) return; if (err) From 0e7a569929acdea82e56f0d0c2f45ff85dc25161 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 3 Jan 2023 20:57:26 +0800 Subject: [PATCH 1597/4345] powercap: fix possible name leak in powercap_register_zone() [ Upstream commit 1b6599f741a4525ca761ecde46e5885ff1e6ba58 ] In the error path after calling dev_set_name(), the device name is leaked. To fix this, calling dev_set_name() before device_register(), and call put_device() if it returns error. All the resources is released in powercap_release(), so it can return from powercap_register_zone() directly. Fixes: 75d2364ea0ca ("PowerCap: Add class driver") Signed-off-by: Yang Yingliang Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/powercap/powercap_sys.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index 3f0b8e2ef3d4..7a3109a53881 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -530,9 +530,6 @@ struct powercap_zone *powercap_register_zone( power_zone->name = kstrdup(name, GFP_KERNEL); if (!power_zone->name) goto err_name_alloc; - dev_set_name(&power_zone->dev, "%s:%x", - dev_name(power_zone->dev.parent), - power_zone->id); power_zone->constraints = kcalloc(nr_constraints, sizeof(*power_zone->constraints), GFP_KERNEL); @@ -555,9 +552,16 @@ struct powercap_zone *powercap_register_zone( power_zone->dev_attr_groups[0] = &power_zone->dev_zone_attr_group; power_zone->dev_attr_groups[1] = NULL; power_zone->dev.groups = power_zone->dev_attr_groups; + dev_set_name(&power_zone->dev, "%s:%x", + dev_name(power_zone->dev.parent), + power_zone->id); result = device_register(&power_zone->dev); - if (result) - goto err_dev_ret; + if (result) { + put_device(&power_zone->dev); + mutex_unlock(&control_type->lock); + + return ERR_PTR(result); + } control_type->nr_zones++; mutex_unlock(&control_type->lock); From 2e3bd75f64d2f844a0f8c7b2d80eba17d1959677 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 10 May 2021 23:29:25 +0200 Subject: [PATCH 1598/4345] x86/cpu: Init AP exception handling from cpu_init_secondary() [ Upstream commit b1efd0ff4bd16e8bb8607ba566b03f2024a830bb ] SEV-ES guests require properly setup task register with which the TSS descriptor in the GDT can be located so that the IST-type #VC exception handler which they need to function properly, can be executed. This setup needs to happen before attempting to load microcode in ucode_cpu_init() on secondary CPUs which can cause such #VC exceptions. Simplify the machinery by running that exception setup from a new function cpu_init_secondary() and explicitly call cpu_init_exception_handling() for the boot CPU before cpu_init(). The latter prepares for fixing and simplifying the exception/IST setup on the boot CPU. There should be no functional changes resulting from this patch. [ tglx: Reworked it so cpu_init_exception_handling() stays seperate ] Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Reviewed-by: Lai Jiangshan Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/87k0o6gtvu.ffs@nanos.tec.linutronix.de Stable-dep-of: c0dd9245aa9e ("x86/microcode: Check CPU capabilities after late microcode update correctly") Signed-off-by: Sasha Levin --- arch/x86/include/asm/processor.h | 1 + arch/x86/kernel/cpu/common.c | 28 +++++++++++++++------------- arch/x86/kernel/smpboot.c | 3 +-- arch/x86/kernel/traps.c | 4 +--- 4 files changed, 18 insertions(+), 18 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d428d611a43a..388541ec77aa 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -682,6 +682,7 @@ extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); extern void load_percpu_segment(int); extern void cpu_init(void); +extern void cpu_init_secondary(void); extern void cpu_init_exception_handling(void); extern void cr4_init(void); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 56573241d029..4402589a1ee1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2048,13 +2048,12 @@ void cpu_init_exception_handling(void) /* * cpu_init() initializes state that is per-CPU. Some data is already - * initialized (naturally) in the bootstrap process, such as the GDT - * and IDT. We reload them nevertheless, this function acts as a - * 'CPU state barrier', nothing should get across. + * initialized (naturally) in the bootstrap process, such as the GDT. We + * reload it nevertheless, this function acts as a 'CPU state barrier', + * nothing should get across. */ void cpu_init(void) { - struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); struct task_struct *cur = current; int cpu = raw_smp_processor_id(); @@ -2067,8 +2066,6 @@ void cpu_init(void) early_cpu_to_node(cpu) != NUMA_NO_NODE) set_numa_node(early_cpu_to_node(cpu)); #endif - setup_getcpu(cpu); - pr_debug("Initializing CPU#%d\n", cpu); if (IS_ENABLED(CONFIG_X86_64) || cpu_feature_enabled(X86_FEATURE_VME) || @@ -2080,7 +2077,6 @@ void cpu_init(void) * and set up the GDT descriptor: */ switch_to_new_gdt(cpu); - load_current_idt(); if (IS_ENABLED(CONFIG_X86_64)) { loadsegment(fs, 0); @@ -2100,12 +2096,6 @@ void cpu_init(void) initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, cur); - /* Initialize the TSS. */ - tss_setup_ist(tss); - tss_setup_io_bitmap(tss); - set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); - - load_TR_desc(); /* * sp0 points to the entry trampoline stack regardless of what task * is running. @@ -2127,6 +2117,18 @@ void cpu_init(void) load_fixmap_gdt(cpu); } +#ifdef CONFIG_SMP +void cpu_init_secondary(void) +{ + /* + * Relies on the BP having set-up the IDT tables, which are loaded + * on this CPU in cpu_init_exception_handling(). + */ + cpu_init_exception_handling(); + cpu_init(); +} +#endif + /* * The microcode loader calls this upon late microcode load to recheck features, * only when microcode has been updated. Caller holds microcode_mutex and CPU diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e8e5515fb7e9..bda89ecc7799 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -227,8 +227,7 @@ static void notrace start_secondary(void *unused) load_cr3(swapper_pg_dir); __flush_tlb_all(); #endif - cpu_init_exception_handling(); - cpu_init(); + cpu_init_secondary(); rcu_cpu_starting(raw_smp_processor_id()); x86_cpuinit.early_percpu_clock_init(); smp_callin(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 2a39a2df6f43..3780c728345c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -1185,9 +1185,7 @@ void __init trap_init(void) idt_setup_traps(); - /* - * Should be a barrier for any external CPU state: - */ + cpu_init_exception_handling(); cpu_init(); idt_setup_ist_traps(); From 3900b7de1df724bc8d70c8d48ff6dab39611b6d4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 3 Aug 2021 16:15:51 +0200 Subject: [PATCH 1599/4345] x86/microcode: Replace deprecated CPU-hotplug functions. [ Upstream commit 2089f34f8c5b91f7235023ec72e71e3247261ecc ] The functions get_online_cpus() and put_online_cpus() have been deprecated during the CPU hotplug rework. They map directly to cpus_read_lock() and cpus_read_unlock(). Replace deprecated CPU-hotplug functions with the official version. The behavior remains unchanged. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210803141621.780504-9-bigeasy@linutronix.de Stable-dep-of: c0dd9245aa9e ("x86/microcode: Check CPU capabilities after late microcode update correctly") Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/microcode/core.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 0b1732b98e71..38a58819c1b9 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -55,7 +55,7 @@ LIST_HEAD(microcode_cache); * All non cpu-hotplug-callback call sites use: * * - microcode_mutex to synchronize with each other; - * - get/put_online_cpus() to synchronize with + * - cpus_read_lock/unlock() to synchronize with * the cpu-hotplug-callback call sites. * * We guarantee that only a single cpu is being @@ -431,7 +431,7 @@ static ssize_t microcode_write(struct file *file, const char __user *buf, return ret; } - get_online_cpus(); + cpus_read_lock(); mutex_lock(µcode_mutex); if (do_microcode_update(buf, len) == 0) @@ -441,7 +441,7 @@ static ssize_t microcode_write(struct file *file, const char __user *buf, perf_check_microcode(); mutex_unlock(µcode_mutex); - put_online_cpus(); + cpus_read_unlock(); return ret; } @@ -629,7 +629,7 @@ static ssize_t reload_store(struct device *dev, if (val != 1) return size; - get_online_cpus(); + cpus_read_lock(); ret = check_online_cpus(); if (ret) @@ -644,7 +644,7 @@ static ssize_t reload_store(struct device *dev, mutex_unlock(µcode_mutex); put: - put_online_cpus(); + cpus_read_unlock(); if (ret == 0) ret = size; @@ -853,14 +853,14 @@ int __init microcode_init(void) if (IS_ERR(microcode_pdev)) return PTR_ERR(microcode_pdev); - get_online_cpus(); + cpus_read_lock(); mutex_lock(µcode_mutex); error = subsys_interface_register(&mc_cpu_interface); if (!error) perf_check_microcode(); mutex_unlock(µcode_mutex); - put_online_cpus(); + cpus_read_unlock(); if (error) goto out_pdev; @@ -892,13 +892,13 @@ int __init microcode_init(void) &cpu_root_microcode_group); out_driver: - get_online_cpus(); + cpus_read_lock(); mutex_lock(µcode_mutex); subsys_interface_unregister(&mc_cpu_interface); mutex_unlock(µcode_mutex); - put_online_cpus(); + cpus_read_unlock(); out_pdev: platform_device_unregister(microcode_pdev); From 8078a170baab3696dba1b6a2bd48ec59aefaacdc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Mar 2022 16:30:47 +0100 Subject: [PATCH 1600/4345] x86: Mark stop_this_cpu() __noreturn [ Upstream commit f9cdf7ca57cada055f61ef6d0eb4db21c3f200db ] vmlinux.o: warning: objtool: smp_stop_nmi_callback()+0x2b: unreachable instruction 0000 0000000000047cf0 : ... 0026 47d16: e8 00 00 00 00 call 47d1b 47d17: R_X86_64_PLT32 stop_this_cpu-0x4 002b 47d1b: b8 01 00 00 00 mov $0x1,%eax Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220308154319.290905453@infradead.org Stable-dep-of: c0dd9245aa9e ("x86/microcode: Check CPU capabilities after late microcode update correctly") Signed-off-by: Sasha Levin --- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/process.c | 2 +- tools/objtool/check.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 388541ec77aa..01bcbf8a25b2 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -839,7 +839,7 @@ bool xen_set_default_idle(void); #define xen_set_default_idle 0 #endif -void stop_this_cpu(void *dummy); +void __noreturn stop_this_cpu(void *dummy); void microcode_check(void); enum l1tf_mitigations { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 5e17c3939dd1..1cba09a9f1c1 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -720,7 +720,7 @@ bool xen_set_default_idle(void) } #endif -void stop_this_cpu(void *dummy) +void __noreturn stop_this_cpu(void *dummy) { local_irq_disable(); /* diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 985bcc5cea8a..ff47aed7ef6f 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -180,6 +180,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "kunit_try_catch_throw", "xen_start_kernel", "cpu_bringup_and_idle", + "stop_this_cpu", }; if (!func) From 9e56938f207241512aab787b17c88c96dc150b90 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 25 May 2022 18:12:29 +0200 Subject: [PATCH 1601/4345] x86/microcode: Rip out the OLD_INTERFACE [ Upstream commit 181b6f40e9ea80c76756d4d0cdeed396016c487e ] Everything should be using the early initrd loading by now. Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220525161232.14924-2-bp@alien8.de Stable-dep-of: c0dd9245aa9e ("x86/microcode: Check CPU capabilities after late microcode update correctly") Signed-off-by: Sasha Levin --- arch/x86/Kconfig | 12 ---- arch/x86/kernel/cpu/microcode/core.c | 100 --------------------------- 2 files changed, 112 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d64e69013995..1f55fc647037 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1329,18 +1329,6 @@ config MICROCODE_AMD If you select this option, microcode patch loading support for AMD processors will be enabled. -config MICROCODE_OLD_INTERFACE - bool "Ancient loading interface (DEPRECATED)" - default n - depends on MICROCODE - help - DO NOT USE THIS! This is the ancient /dev/cpu/microcode interface - which was used by userspace tools like iucode_tool and microcode.ctl. - It is inadequate because it runs too late to be able to properly - load microcode on a machine and it needs special tools. Instead, you - should've switched to the early loading method with the initrd or - builtin microcode by now: Documentation/x86/microcode.rst - config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" help diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 38a58819c1b9..8d8d7ee47e1c 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -390,98 +390,6 @@ static int apply_microcode_on_target(int cpu) return ret; } -#ifdef CONFIG_MICROCODE_OLD_INTERFACE -static int do_microcode_update(const void __user *buf, size_t size) -{ - int error = 0; - int cpu; - - for_each_online_cpu(cpu) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; - - if (!uci->valid) - continue; - - ustate = microcode_ops->request_microcode_user(cpu, buf, size); - if (ustate == UCODE_ERROR) { - error = -1; - break; - } else if (ustate == UCODE_NEW) { - apply_microcode_on_target(cpu); - } - } - - return error; -} - -static int microcode_open(struct inode *inode, struct file *file) -{ - return capable(CAP_SYS_RAWIO) ? stream_open(inode, file) : -EPERM; -} - -static ssize_t microcode_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) -{ - ssize_t ret = -EINVAL; - unsigned long nr_pages = totalram_pages(); - - if ((len >> PAGE_SHIFT) > nr_pages) { - pr_err("too much data (max %ld pages)\n", nr_pages); - return ret; - } - - cpus_read_lock(); - mutex_lock(µcode_mutex); - - if (do_microcode_update(buf, len) == 0) - ret = (ssize_t)len; - - if (ret > 0) - perf_check_microcode(); - - mutex_unlock(µcode_mutex); - cpus_read_unlock(); - - return ret; -} - -static const struct file_operations microcode_fops = { - .owner = THIS_MODULE, - .write = microcode_write, - .open = microcode_open, - .llseek = no_llseek, -}; - -static struct miscdevice microcode_dev = { - .minor = MICROCODE_MINOR, - .name = "microcode", - .nodename = "cpu/microcode", - .fops = µcode_fops, -}; - -static int __init microcode_dev_init(void) -{ - int error; - - error = misc_register(µcode_dev); - if (error) { - pr_err("can't misc_register on minor=%d\n", MICROCODE_MINOR); - return error; - } - - return 0; -} - -static void __exit microcode_dev_exit(void) -{ - misc_deregister(µcode_dev); -} -#else -#define microcode_dev_init() 0 -#define microcode_dev_exit() do { } while (0) -#endif - /* fake device for request_firmware */ static struct platform_device *microcode_pdev; @@ -873,10 +781,6 @@ int __init microcode_init(void) goto out_driver; } - error = microcode_dev_init(); - if (error) - goto out_ucode_group; - register_syscore_ops(&mc_syscore_ops); cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting", mc_cpu_starting, NULL); @@ -887,10 +791,6 @@ int __init microcode_init(void) return 0; - out_ucode_group: - sysfs_remove_group(&cpu_subsys.dev_root->kobj, - &cpu_root_microcode_group); - out_driver: cpus_read_lock(); mutex_lock(µcode_mutex); From e6230806681fa25b7a3829c021d5b33d68c9bd09 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 25 May 2022 18:12:30 +0200 Subject: [PATCH 1602/4345] x86/microcode: Default-disable late loading [ Upstream commit a77a94f86273ce42a39cb479217dd8d68acfe0ff ] It is dangerous and it should not be used anyway - there's a nice early loading already. Requested-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220525161232.14924-3-bp@alien8.de Stable-dep-of: c0dd9245aa9e ("x86/microcode: Check CPU capabilities after late microcode update correctly") Signed-off-by: Sasha Levin --- arch/x86/Kconfig | 11 +++++++++++ arch/x86/kernel/cpu/common.c | 2 ++ arch/x86/kernel/cpu/microcode/core.c | 7 ++++++- 3 files changed, 19 insertions(+), 1 deletion(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1f55fc647037..2284666e8c90 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1329,6 +1329,17 @@ config MICROCODE_AMD If you select this option, microcode patch loading support for AMD processors will be enabled. +config MICROCODE_LATE_LOADING + bool "Late microcode loading (DANGEROUS)" + default n + depends on MICROCODE + help + Loading microcode late, when the system is up and executing instructions + is a tricky business and should be avoided if possible. Just the sequence + of synchronizing all cores and SMT threads is one fragile dance which does + not guarantee that cores might not softlock after the loading. Therefore, + use this at your own risk. Late loading taints the kernel too. + config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" help diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4402589a1ee1..95f52540db37 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2129,6 +2129,7 @@ void cpu_init_secondary(void) } #endif +#ifdef CONFIG_MICROCODE_LATE_LOADING /* * The microcode loader calls this upon late microcode load to recheck features, * only when microcode has been updated. Caller holds microcode_mutex and CPU @@ -2158,6 +2159,7 @@ void microcode_check(void) pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n"); pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); } +#endif /* * Invoked from core CPU hotplug code after hotplug operations diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 8d8d7ee47e1c..5b27030714e4 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -393,6 +393,7 @@ static int apply_microcode_on_target(int cpu) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; +#ifdef CONFIG_MICROCODE_LATE_LOADING /* * Late loading dance. Why the heavy-handed stomp_machine effort? * @@ -560,6 +561,9 @@ put: return ret; } +static DEVICE_ATTR_WO(reload); +#endif + static ssize_t version_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -576,7 +580,6 @@ static ssize_t pf_show(struct device *dev, return sprintf(buf, "0x%x\n", uci->cpu_sig.pf); } -static DEVICE_ATTR_WO(reload); static DEVICE_ATTR(version, 0444, version_show, NULL); static DEVICE_ATTR(processor_flags, 0444, pf_show, NULL); @@ -729,7 +732,9 @@ static int mc_cpu_down_prep(unsigned int cpu) } static struct attribute *cpu_root_microcode_attrs[] = { +#ifdef CONFIG_MICROCODE_LATE_LOADING &dev_attr_reload.attr, +#endif NULL }; From f5e78fa916aafe2dbcb323ee8b436f3e81cf0aec Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Mon, 29 Aug 2022 18:10:30 +0000 Subject: [PATCH 1603/4345] x86/microcode: Print previous version of microcode after reload [ Upstream commit 7fce8d6eccbc31a561d07c79f359ad09f0424347 ] Print both old and new versions of microcode after a reload is complete because knowing the previous microcode version is sometimes important from a debugging perspective. [ bp: Massage commit message. ] Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov Acked-by: Tony Luck Link: https://lore.kernel.org/r/20220829181030.722891-1-ashok.raj@intel.com Stable-dep-of: c0dd9245aa9e ("x86/microcode: Check CPU capabilities after late microcode update correctly") Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/microcode/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 5b27030714e4..707a385943b4 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -508,7 +508,7 @@ wait_for_siblings: */ static int microcode_reload_late(void) { - int ret; + int old = boot_cpu_data.microcode, ret; atomic_set(&late_cpus_in, 0); atomic_set(&late_cpus_out, 0); @@ -517,7 +517,8 @@ static int microcode_reload_late(void) if (ret == 0) microcode_check(); - pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode); + pr_info("Reload completed, microcode revision: 0x%x -> 0x%x\n", + old, boot_cpu_data.microcode); return ret; } From 89e848bb4aa140e701eb0d017736ce5d1ee198da Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Mon, 9 Jan 2023 07:35:50 -0800 Subject: [PATCH 1604/4345] x86/microcode: Add a parameter to microcode_check() to store CPU capabilities [ Upstream commit ab31c74455c64e69342ddab21fd9426fcbfefde7 ] Add a parameter to store CPU capabilities before performing a microcode update so that CPU capabilities can be compared before and after update. [ bp: Massage. ] Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230109153555.4986-2-ashok.raj@intel.com Stable-dep-of: c0dd9245aa9e ("x86/microcode: Check CPU capabilities after late microcode update correctly") Signed-off-by: Sasha Levin --- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/cpu/common.c | 21 +++++++++++++-------- arch/x86/kernel/cpu/microcode/core.c | 3 ++- 3 files changed, 16 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 01bcbf8a25b2..6d40c409ebc1 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -840,7 +840,7 @@ bool xen_set_default_idle(void); #endif void __noreturn stop_this_cpu(void *dummy); -void microcode_check(void); +void microcode_check(struct cpuinfo_x86 *prev_info); enum l1tf_mitigations { L1TF_MITIGATION_OFF, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 95f52540db37..f724002adbfc 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2130,30 +2130,35 @@ void cpu_init_secondary(void) #endif #ifdef CONFIG_MICROCODE_LATE_LOADING -/* +/** + * microcode_check() - Check if any CPU capabilities changed after an update. + * @prev_info: CPU capabilities stored before an update. + * * The microcode loader calls this upon late microcode load to recheck features, * only when microcode has been updated. Caller holds microcode_mutex and CPU * hotplug lock. + * + * Return: None */ -void microcode_check(void) +void microcode_check(struct cpuinfo_x86 *prev_info) { - struct cpuinfo_x86 info; - perf_check_microcode(); /* Reload CPUID max function as it might've changed. */ - info.cpuid_level = cpuid_eax(0); + prev_info->cpuid_level = cpuid_eax(0); /* * Copy all capability leafs to pick up the synthetic ones so that * memcmp() below doesn't fail on that. The ones coming from CPUID will * get overwritten in get_cpu_cap(). */ - memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)); + memcpy(&prev_info->x86_capability, &boot_cpu_data.x86_capability, + sizeof(prev_info->x86_capability)); - get_cpu_cap(&info); + get_cpu_cap(prev_info); - if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability))) + if (!memcmp(&prev_info->x86_capability, &boot_cpu_data.x86_capability, + sizeof(prev_info->x86_capability))) return; pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n"); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 707a385943b4..2c70f3cfae68 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -509,13 +509,14 @@ wait_for_siblings: static int microcode_reload_late(void) { int old = boot_cpu_data.microcode, ret; + struct cpuinfo_x86 prev_info; atomic_set(&late_cpus_in, 0); atomic_set(&late_cpus_out, 0); ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); if (ret == 0) - microcode_check(); + microcode_check(&prev_info); pr_info("Reload completed, microcode revision: 0x%x -> 0x%x\n", old, boot_cpu_data.microcode); From 511e27e5fdd658e6cb06b4947fb0d3ac76163776 Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Mon, 9 Jan 2023 07:35:51 -0800 Subject: [PATCH 1605/4345] x86/microcode: Check CPU capabilities after late microcode update correctly [ Upstream commit c0dd9245aa9e25a697181f6085692272c9ec61bc ] The kernel caches each CPU's feature bits at boot in an x86_capability[] structure. However, the capabilities in the BSP's copy can be turned off as a result of certain command line parameters or configuration restrictions, for example the SGX bit. This can cause a mismatch when comparing the values before and after the microcode update. Another example is X86_FEATURE_SRBDS_CTRL which gets added only after microcode update: # --- cpuid.before 2023-01-21 14:54:15.652000747 +0100 # +++ cpuid.after 2023-01-21 14:54:26.632001024 +0100 # @@ -10,7 +10,7 @@ CPU: # 0x00000004 0x04: eax=0x00000000 ebx=0x00000000 ecx=0x00000000 edx=0x00000000 # 0x00000005 0x00: eax=0x00000040 ebx=0x00000040 ecx=0x00000003 edx=0x11142120 # 0x00000006 0x00: eax=0x000027f7 ebx=0x00000002 ecx=0x00000001 edx=0x00000000 # - 0x00000007 0x00: eax=0x00000000 ebx=0x029c6fbf ecx=0x40000000 edx=0xbc002400 # + 0x00000007 0x00: eax=0x00000000 ebx=0x029c6fbf ecx=0x40000000 edx=0xbc002e00 ^^^ and which proves for a gazillionth time that late loading is a bad bad idea. microcode_check() is called after an update to report any previously cached CPUID bits which might have changed due to the update. Therefore, store the cached CPU caps before the update and compare them with the CPU caps after the microcode update has succeeded. Thus, the comparison is done between the CPUID *hardware* bits before and after the upgrade instead of using the cached, possibly runtime modified values in BSP's boot_cpu_data copy. As a result, false warnings about CPUID bits changes are avoided. [ bp: - Massage. - Add SRBDS_CTRL example. - Add kernel-doc. - Incorporate forgotten review feedback from dhansen. ] Fixes: 1008c52c09dc ("x86/CPU: Add a microcode loader callback") Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230109153555.4986-3-ashok.raj@intel.com Signed-off-by: Sasha Levin --- arch/x86/include/asm/processor.h | 1 + arch/x86/kernel/cpu/common.c | 36 ++++++++++++++++++---------- arch/x86/kernel/cpu/microcode/core.c | 6 +++++ 3 files changed, 30 insertions(+), 13 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6d40c409ebc1..60514502ead6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -841,6 +841,7 @@ bool xen_set_default_idle(void); void __noreturn stop_this_cpu(void *dummy); void microcode_check(struct cpuinfo_x86 *prev_info); +void store_cpu_caps(struct cpuinfo_x86 *info); enum l1tf_mitigations { L1TF_MITIGATION_OFF, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f724002adbfc..e2dee6010846 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2130,6 +2130,25 @@ void cpu_init_secondary(void) #endif #ifdef CONFIG_MICROCODE_LATE_LOADING +/** + * store_cpu_caps() - Store a snapshot of CPU capabilities + * @curr_info: Pointer where to store it + * + * Returns: None + */ +void store_cpu_caps(struct cpuinfo_x86 *curr_info) +{ + /* Reload CPUID max function as it might've changed. */ + curr_info->cpuid_level = cpuid_eax(0); + + /* Copy all capability leafs and pick up the synthetic ones. */ + memcpy(&curr_info->x86_capability, &boot_cpu_data.x86_capability, + sizeof(curr_info->x86_capability)); + + /* Get the hardware CPUID leafs */ + get_cpu_cap(curr_info); +} + /** * microcode_check() - Check if any CPU capabilities changed after an update. * @prev_info: CPU capabilities stored before an update. @@ -2142,22 +2161,13 @@ void cpu_init_secondary(void) */ void microcode_check(struct cpuinfo_x86 *prev_info) { + struct cpuinfo_x86 curr_info; + perf_check_microcode(); - /* Reload CPUID max function as it might've changed. */ - prev_info->cpuid_level = cpuid_eax(0); + store_cpu_caps(&curr_info); - /* - * Copy all capability leafs to pick up the synthetic ones so that - * memcmp() below doesn't fail on that. The ones coming from CPUID will - * get overwritten in get_cpu_cap(). - */ - memcpy(&prev_info->x86_capability, &boot_cpu_data.x86_capability, - sizeof(prev_info->x86_capability)); - - get_cpu_cap(prev_info); - - if (!memcmp(&prev_info->x86_capability, &boot_cpu_data.x86_capability, + if (!memcmp(&prev_info->x86_capability, &curr_info.x86_capability, sizeof(prev_info->x86_capability))) return; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 2c70f3cfae68..122da99bac4e 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -514,6 +514,12 @@ static int microcode_reload_late(void) atomic_set(&late_cpus_in, 0); atomic_set(&late_cpus_out, 0); + /* + * Take a snapshot before the microcode update in order to compare and + * check whether any bits changed after an update. + */ + store_cpu_caps(&prev_info); + ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); if (ret == 0) microcode_check(&prev_info); From 8e83e1619fac9151b1515177f5066ae67b0cbda2 Mon Sep 17 00:00:00 2001 From: Ashok Raj Date: Mon, 9 Jan 2023 07:35:52 -0800 Subject: [PATCH 1606/4345] x86/microcode: Adjust late loading result reporting message [ Upstream commit 6eab3abac7043226e5375e9ead0c7607ced6767b ] During late microcode loading, the "Reload completed" message is issued unconditionally, regardless of success or failure. Adjust the message to report the result of the update. [ bp: Massage. ] Fixes: 9bd681251b7c ("x86/microcode: Announce reload operation's completion") Suggested-by: Thomas Gleixner Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Tony Luck Link: https://lore.kernel.org/lkml/874judpqqd.ffs@tglx/ Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/microcode/core.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 122da99bac4e..36583bc4b88c 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -521,11 +521,14 @@ static int microcode_reload_late(void) store_cpu_caps(&prev_info); ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); - if (ret == 0) + if (!ret) { + pr_info("Reload succeeded, microcode revision: 0x%x -> 0x%x\n", + old, boot_cpu_data.microcode); microcode_check(&prev_info); - - pr_info("Reload completed, microcode revision: 0x%x -> 0x%x\n", - old, boot_cpu_data.microcode); + } else { + pr_info("Reload failed, current microcode revision: 0x%x\n", + boot_cpu_data.microcode); + } return ret; } From 37f0ca73fe81305bc889d8d765bbb6f8756b53b5 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Fri, 30 Oct 2020 22:07:04 +0200 Subject: [PATCH 1607/4345] net: ethernet: ti: am65-cpsw: fix tx csum offload for multi mac mode [ Upstream commit 97067aaf127487788a297267dede0008cd75bb7b ] The current implementation uses .ndo_set_features() callback to track NETIF_F_HW_CSUM feature changes and update generic CPSW_P0_CONTROL_REG.RX_CHECKSUM_EN option accordingly. It's not going to work in case of multi-port devices as TX csum offload can be changed per netdev. On K3 CPSWxG devices TX csum offload enabled in the following way: - the CPSW_P0_CONTROL_REG.RX_CHECKSUM_EN option enables TX csum offload in generic and affects all TX DMA channels and packets; - corresponding fields in TX DMA descriptor have to be filed properly when upper layer wants to offload TX csum (skb->ip_summed == CHECKSUM_PARTIAL) and it's per-packet option. The Linux Network core is expected to never request TX csum offload if netdev NETIF_F_HW_CSUM feature is disabled, and, as result, TX DMA descriptors should not be modified, and per-packet TX csum offload will be disabled (or enabled) on per-netdev basis. Which, in turn, makes it safe to enable the CPSW_P0_CONTROL_REG.RX_CHECKSUM_EN option unconditionally. Hence, fix TX csum offload for multi-port devices by: - enabling the CPSW_P0_CONTROL_REG.RX_CHECKSUM_EN option in am65_cpsw_nuss_common_open() unconditionally - and removing .ndo_set_features() callback implementation, which was used only NETIF_F_HW_CSUM feature update purposes Signed-off-by: Grygorii Strashko Reviewed-by: Jesse Brandeburg Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 30 +----------------------- 1 file changed, 1 insertion(+), 29 deletions(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 059d68d48f1e..487c1570dd42 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -426,9 +426,7 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common, writel(common->rx_flow_id_base, host_p->port_base + AM65_CPSW_PORT0_REG_FLOW_ID_OFFSET); /* en tx crc offload */ - if (features & NETIF_F_HW_CSUM) - writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN, - host_p->port_base + AM65_CPSW_P0_REG_CTL); + writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN, host_p->port_base + AM65_CPSW_P0_REG_CTL); am65_cpsw_nuss_set_p0_ptype(common); @@ -1369,31 +1367,6 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev, stats->tx_dropped = dev->stats.tx_dropped; } -static int am65_cpsw_nuss_ndo_slave_set_features(struct net_device *ndev, - netdev_features_t features) -{ - struct am65_cpsw_common *common = am65_ndev_to_common(ndev); - netdev_features_t changes = features ^ ndev->features; - struct am65_cpsw_host *host_p; - - host_p = am65_common_get_host(common); - - if (changes & NETIF_F_HW_CSUM) { - bool enable = !!(features & NETIF_F_HW_CSUM); - - dev_info(common->dev, "Turn %s tx-checksum-ip-generic\n", - enable ? "ON" : "OFF"); - if (enable) - writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN, - host_p->port_base + AM65_CPSW_P0_REG_CTL); - else - writel(0, - host_p->port_base + AM65_CPSW_P0_REG_CTL); - } - - return 0; -} - static const struct net_device_ops am65_cpsw_nuss_netdev_ops_2g = { .ndo_open = am65_cpsw_nuss_ndo_slave_open, .ndo_stop = am65_cpsw_nuss_ndo_slave_stop, @@ -1406,7 +1379,6 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops_2g = { .ndo_vlan_rx_add_vid = am65_cpsw_nuss_ndo_slave_add_vid, .ndo_vlan_rx_kill_vid = am65_cpsw_nuss_ndo_slave_kill_vid, .ndo_do_ioctl = am65_cpsw_nuss_ndo_slave_ioctl, - .ndo_set_features = am65_cpsw_nuss_ndo_slave_set_features, .ndo_setup_tc = am65_cpsw_qos_ndo_setup_tc, }; From 80c81aafc998a551d41f7efbcfa27aff7cec6ef5 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Fri, 30 Oct 2020 22:07:07 +0200 Subject: [PATCH 1608/4345] net: ethernet: ti: am65-cpsw: handle deferred probe with dev_err_probe() [ Upstream commit 8fbc2f9edce23d19fc09ef5bf8d4eb38be2db0f8 ] Use new dev_err_probe() API to handle deferred probe properly and simplify the code. Signed-off-by: Grygorii Strashko Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 28 +++++++++--------------- 1 file changed, 10 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 487c1570dd42..5300e1439e1e 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1487,9 +1487,8 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) tx_chn->tx_chn_name, &tx_cfg); if (IS_ERR(tx_chn->tx_chn)) { - ret = PTR_ERR(tx_chn->tx_chn); - dev_err(dev, "Failed to request tx dma channel %d\n", - ret); + ret = dev_err_probe(dev, PTR_ERR(tx_chn->tx_chn), + "Failed to request tx dma channel\n"); goto err; } @@ -1560,8 +1559,8 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, "rx", &rx_cfg); if (IS_ERR(rx_chn->rx_chn)) { - ret = PTR_ERR(rx_chn->rx_chn); - dev_err(dev, "Failed to request rx dma channel %d\n", ret); + ret = dev_err_probe(dev, PTR_ERR(rx_chn->rx_chn), + "Failed to request rx dma channel\n"); goto err; } @@ -1768,12 +1767,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) /* get phy/link info */ if (of_phy_is_fixed_link(port_np)) { ret = of_phy_register_fixed_link(port_np); - if (ret) { - if (ret != -EPROBE_DEFER) - dev_err(dev, "%pOF failed to register fixed-link phy: %d\n", - port_np, ret); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, + "failed to register fixed-link phy %pOF\n", + port_np); port->slave.phy_node = of_node_get(port_np); } else { port->slave.phy_node = @@ -2062,13 +2059,8 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) return -ENOMEM; clk = devm_clk_get(dev, "fck"); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - - if (ret != -EPROBE_DEFER) - dev_err(dev, "error getting fck clock %d\n", ret); - return ret; - } + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "getting fck clock\n"); common->bus_freq = clk_get_rate(clk); pm_runtime_enable(dev); From 119848416480f70d57d7cff7597391f2c2735838 Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Mon, 13 Dec 2021 01:44:36 -0800 Subject: [PATCH 1609/4345] net: ethernet: ti: add missing of_node_put before return [ Upstream commit be565ec71d1d59438bed0c7ed0a252a327e0b0ef ] Fix following coccicheck warning: WARNING: Function "for_each_child_of_node" should have of_node_put() before return. Early exits from for_each_child_of_node should decrement the node reference counter. Signed-off-by: Wang Qing Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 29 ++++++++++++++++-------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 5300e1439e1e..4074310abcff 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1724,13 +1724,14 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) if (ret < 0) { dev_err(dev, "%pOF error reading port_id %d\n", port_np, ret); - return ret; + goto of_node_put; } if (!port_id || port_id > common->port_num) { dev_err(dev, "%pOF has invalid port_id %u %s\n", port_np, port_id, port_np->name); - return -EINVAL; + ret = -EINVAL; + goto of_node_put; } port = am65_common_get_port(common, port_id); @@ -1746,8 +1747,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) (AM65_CPSW_NU_FRAM_PORT_OFFSET * (port_id - 1)); port->slave.mac_sl = cpsw_sl_get("am65", dev, port->port_base); - if (IS_ERR(port->slave.mac_sl)) - return PTR_ERR(port->slave.mac_sl); + if (IS_ERR(port->slave.mac_sl)) { + ret = PTR_ERR(port->slave.mac_sl); + goto of_node_put; + } port->disabled = !of_device_is_available(port_np); if (port->disabled) @@ -1758,7 +1761,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) ret = PTR_ERR(port->slave.ifphy); dev_err(dev, "%pOF error retrieving port phy: %d\n", port_np, ret); - return ret; + goto of_node_put; } port->slave.mac_only = @@ -1767,10 +1770,12 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) /* get phy/link info */ if (of_phy_is_fixed_link(port_np)) { ret = of_phy_register_fixed_link(port_np); - if (ret) - return dev_err_probe(dev, ret, + if (ret) { + ret = dev_err_probe(dev, ret, "failed to register fixed-link phy %pOF\n", port_np); + goto of_node_put; + } port->slave.phy_node = of_node_get(port_np); } else { port->slave.phy_node = @@ -1780,14 +1785,15 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) if (!port->slave.phy_node) { dev_err(dev, "slave[%d] no phy found\n", port_id); - return -ENODEV; + ret = -ENODEV; + goto of_node_put; } ret = of_get_phy_mode(port_np, &port->slave.phy_if); if (ret) { dev_err(dev, "%pOF read phy-mode err %d\n", port_np, ret); - return ret; + goto of_node_put; } mac_addr = of_get_mac_address(port_np); @@ -1804,6 +1810,11 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) of_node_put(node); return 0; + +of_node_put: + of_node_put(port_np); + of_node_put(node); + return ret; } static void am65_cpsw_pcpu_stats_free(void *data) From 92a07ba4f0af2cccdc2aa5ee32679c9c9714db90 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 22 Jan 2023 16:07:37 +0800 Subject: [PATCH 1610/4345] crypto: xts - Handle EBUSY correctly [ Upstream commit 51c082514c2dedf2711c99d93c196cc4eedceb40 ] As it is xts only handles the special return value of EINPROGRESS, which means that in all other cases it will free data related to the request. However, as the caller of xts may specify MAY_BACKLOG, we also need to expect EBUSY and treat it in the same way. Otherwise backlogged requests will trigger a use-after-free. Fixes: 8083b1bf8163 ("crypto: xts - add support for ciphertext stealing") Signed-off-by: Herbert Xu Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/xts.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/crypto/xts.c b/crypto/xts.c index ad45b009774b..c6a105dba38b 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -202,12 +202,12 @@ static void xts_encrypt_done(struct crypto_async_request *areq, int err) if (!err) { struct xts_request_ctx *rctx = skcipher_request_ctx(req); - rctx->subreq.base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + rctx->subreq.base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; err = xts_xor_tweak_post(req, true); if (!err && unlikely(req->cryptlen % XTS_BLOCK_SIZE)) { err = xts_cts_final(req, crypto_skcipher_encrypt); - if (err == -EINPROGRESS) + if (err == -EINPROGRESS || err == -EBUSY) return; } } @@ -222,12 +222,12 @@ static void xts_decrypt_done(struct crypto_async_request *areq, int err) if (!err) { struct xts_request_ctx *rctx = skcipher_request_ctx(req); - rctx->subreq.base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + rctx->subreq.base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG; err = xts_xor_tweak_post(req, false); if (!err && unlikely(req->cryptlen % XTS_BLOCK_SIZE)) { err = xts_cts_final(req, crypto_skcipher_decrypt); - if (err == -EINPROGRESS) + if (err == -EINPROGRESS || err == -EBUSY) return; } } From 6952629bed36a0ba0dd4bedf8d4d799bdae757ae Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 20 Jan 2023 12:45:14 +0100 Subject: [PATCH 1611/4345] leds: led-class: Add missing put_device() to led_put() [ Upstream commit 445110941eb94709216363f9d807d2508e64abd7 ] led_put() is used to "undo" a successful of_led_get() call, of_led_get() uses class_find_device_by_of_node() which returns a reference to the device which must be free-ed with put_device() when the caller is done with it. Add a put_device() call to led_put() to free the reference returned by class_find_device_by_of_node(). And also add a put_device() in the error-exit case of try_module_get() failing. Fixes: 699a8c7c4bd3 ("leds: Add of_led_get() and led_put()") Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Signed-off-by: Hans de Goede Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230120114524.408368-2-hdegoede@redhat.com Signed-off-by: Sasha Levin --- drivers/leds/led-class.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 4365c1cc4505..e28a4bb71603 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -242,8 +242,10 @@ struct led_classdev *of_led_get(struct device_node *np, int index) led_cdev = dev_get_drvdata(led_dev); - if (!try_module_get(led_cdev->dev->parent->driver->owner)) + if (!try_module_get(led_cdev->dev->parent->driver->owner)) { + put_device(led_cdev->dev); return ERR_PTR(-ENODEV); + } return led_cdev; } @@ -256,6 +258,7 @@ EXPORT_SYMBOL_GPL(of_led_get); void led_put(struct led_classdev *led_cdev) { module_put(led_cdev->dev->parent->driver->owner); + put_device(led_cdev->dev); } EXPORT_SYMBOL_GPL(led_put); From 959bd9d42a839809b00c7243037919d61b4b7763 Mon Sep 17 00:00:00 2001 From: Peter Gonda Date: Tue, 7 Dec 2021 15:33:04 -0800 Subject: [PATCH 1612/4345] crypto: ccp - Refactor out sev_fw_alloc() [ Upstream commit cc17982d58d1e67eab831e7023ede999dda56173 ] Create a helper function sev_fw_alloc() which can be used to allocate aligned memory regions for use by the PSP firmware. Currently only used for the SEV-ES TMR region but will be used for the SEV_INIT_EX NV memory region. Signed-off-by: Peter Gonda Reviewed-by: Marc Orr Acked-by: David Rientjes Acked-by: Brijesh Singh Cc: Tom Lendacky Cc: Brijesh Singh Cc: Marc Orr Cc: Joerg Roedel Cc: Herbert Xu Cc: David Rientjes Cc: John Allen Cc: "David S. Miller" Cc: Paolo Bonzini Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu Stable-dep-of: 46a334a98f58 ("crypto: ccp - Flush the SEV-ES TMR memory before giving it to firmware") Signed-off-by: Sasha Levin --- drivers/crypto/ccp/sev-dev.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index e70ae98de118..8a900226d73a 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -138,6 +138,17 @@ static int sev_cmd_buffer_len(int cmd) return 0; } +static void *sev_fw_alloc(unsigned long len) +{ + struct page *page; + + page = alloc_pages(GFP_KERNEL, get_order(len)); + if (!page) + return NULL; + + return page_address(page); +} + static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) { struct psp_device *psp = psp_master; @@ -1040,7 +1051,6 @@ EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user); void sev_pci_init(void) { struct sev_device *sev = psp_master->sev_data; - struct page *tmr_page; int error, rc; if (!sev) @@ -1056,14 +1066,10 @@ void sev_pci_init(void) sev_get_api_version(); /* Obtain the TMR memory area for SEV-ES use */ - tmr_page = alloc_pages(GFP_KERNEL, get_order(SEV_ES_TMR_SIZE)); - if (tmr_page) { - sev_es_tmr = page_address(tmr_page); - } else { - sev_es_tmr = NULL; + sev_es_tmr = sev_fw_alloc(SEV_ES_TMR_SIZE); + if (!sev_es_tmr) dev_warn(sev->dev, "SEV: TMR allocation failed, SEV-ES support unavailable\n"); - } /* Initialize the platform */ rc = sev_platform_init(&error); From 627e140a5b7df4ec285271b8566720a3990732b8 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 23 Jan 2023 16:53:08 -0600 Subject: [PATCH 1613/4345] crypto: ccp - Flush the SEV-ES TMR memory before giving it to firmware [ Upstream commit 46a334a98f585ef78d51d8f5736596887bdd7f54 ] Perform a cache flush on the SEV-ES TMR memory after allocation to prevent any possibility of the firmware encountering an error should dirty cache lines be present. Use clflush_cache_range() to flush the SEV-ES TMR memory. Fixes: 97f9ac3db661 ("crypto: ccp - Add support for SEV-ES to the PSP driver") Signed-off-by: Tom Lendacky Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/ccp/sev-dev.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 8a900226d73a..856d867f46eb 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -23,6 +23,7 @@ #include #include +#include #include "psp-dev.h" #include "sev-dev.h" @@ -1067,7 +1068,10 @@ void sev_pci_init(void) /* Obtain the TMR memory area for SEV-ES use */ sev_es_tmr = sev_fw_alloc(SEV_ES_TMR_SIZE); - if (!sev_es_tmr) + if (sev_es_tmr) + /* Must flush the cache before giving it to the firmware */ + clflush_cache_range(sev_es_tmr, SEV_ES_TMR_SIZE); + else dev_warn(sev->dev, "SEV: TMR allocation failed, SEV-ES support unavailable\n"); From 94c4eafbbde36de86685a78526ab52c2b5c2cd56 Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Thu, 2 Feb 2023 21:17:01 +0800 Subject: [PATCH 1614/4345] bpftool: profile online CPUs instead of possible [ Upstream commit 377c16fa3f3c60d21e4b05314c8be034ce37f2eb ] The number of online cpu may be not equal to possible cpu. "bpftool prog profile" can not create pmu event on possible but on online cpu. $ dmidecode -s system-product-name PowerEdge R620 $ cat /sys/devices/system/cpu/possible 0-47 $ cat /sys/devices/system/cpu/online 0-31 Disable cpu dynamically: $ echo 0 > /sys/devices/system/cpu/cpuX/online If one cpu is offline, perf_event_open will return ENODEV. To fix this issue: * check value returned and skip offline cpu. * close pmu_fd immediately on error path, avoid fd leaking. Fixes: 47c09d6a9f67 ("bpftool: Introduce "prog profile" command") Signed-off-by: Tonghao Zhang Cc: Quentin Monnet Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Andrii Nakryiko Cc: Martin KaFai Lau Cc: Song Liu Cc: Yonghong Song Cc: John Fastabend Cc: KP Singh Cc: Stanislav Fomichev Cc: Hao Luo Cc: Jiri Olsa Acked-by: John Fastabend Link: https://lore.kernel.org/r/20230202131701.29519-1-tong@infragraf.org Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- tools/bpf/bpftool/prog.c | 38 ++++++++++++++++++++++++++++++-------- 1 file changed, 30 insertions(+), 8 deletions(-) diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 592536904dde..d2bcce627b32 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1912,10 +1912,38 @@ static void profile_close_perf_events(struct profiler_bpf *obj) profile_perf_event_cnt = 0; } +static int profile_open_perf_event(int mid, int cpu, int map_fd) +{ + int pmu_fd; + + pmu_fd = syscall(__NR_perf_event_open, &metrics[mid].attr, + -1 /*pid*/, cpu, -1 /*group_fd*/, 0); + if (pmu_fd < 0) { + if (errno == ENODEV) { + p_info("cpu %d may be offline, skip %s profiling.", + cpu, metrics[mid].name); + profile_perf_event_cnt++; + return 0; + } + return -1; + } + + if (bpf_map_update_elem(map_fd, + &profile_perf_event_cnt, + &pmu_fd, BPF_ANY) || + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + close(pmu_fd); + return -1; + } + + profile_perf_events[profile_perf_event_cnt++] = pmu_fd; + return 0; +} + static int profile_open_perf_events(struct profiler_bpf *obj) { unsigned int cpu, m; - int map_fd, pmu_fd; + int map_fd; profile_perf_events = calloc( sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); @@ -1934,17 +1962,11 @@ static int profile_open_perf_events(struct profiler_bpf *obj) if (!metrics[m].selected) continue; for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { - pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr, - -1/*pid*/, cpu, -1/*group_fd*/, 0); - if (pmu_fd < 0 || - bpf_map_update_elem(map_fd, &profile_perf_event_cnt, - &pmu_fd, BPF_ANY) || - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + if (profile_open_perf_event(m, cpu, map_fd)) { p_err("failed to create event %s on cpu %d", metrics[m].name, cpu); return -1; } - profile_perf_events[profile_perf_event_cnt++] = pmu_fd; } } return 0; From 9cc2a41c5804e2de2cbc74cfeceff0606b23896b Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 18 Jan 2023 19:57:04 +0200 Subject: [PATCH 1615/4345] net/mlx5: Enhance debug print in page allocation failure [ Upstream commit 7eef93003e5d20e1a6a6e59e12d914b5431cbda2 ] Provide more details to aid debugging. Fixes: bf0bf77f6519 ("mlx5: Support communicating arbitrary host page size to firmware") Signed-off-by: Eran Ben Elisha Signed-off-by: Majd Dibbiny Signed-off-by: Jack Morgenstein Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index a44a2bad5bbb..1ea71f06fdb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -216,7 +216,8 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u32 function) n = find_first_bit(&fp->bitmask, 8 * sizeof(fp->bitmask)); if (n >= MLX5_NUM_4K_IN_PAGE) { - mlx5_core_warn(dev, "alloc 4k bug\n"); + mlx5_core_warn(dev, "alloc 4k bug: fw page = 0x%llx, n = %u, bitmask: %lu, max num of 4K pages: %d\n", + fp->addr, n, fp->bitmask, MLX5_NUM_4K_IN_PAGE); return -ENOENT; } clear_bit(n, &fp->bitmask); From b00baffcc2561374f8fe8af873d00531f19864eb Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 2 Jan 2023 16:13:18 +0400 Subject: [PATCH 1616/4345] irqchip: Fix refcount leak in platform_irqchip_probe [ Upstream commit 6caa5a2b78f5f53c433d3a3781e53325da22f0ac ] of_irq_find_parent() returns a node pointer with refcount incremented, We should use of_node_put() on it when not needed anymore. Add missing of_node_put() to avoid refcount leak. Fixes: f8410e626569 ("irqchip: Add IRQCHIP_PLATFORM_DRIVER_BEGIN/END and IRQCHIP_MATCH helper macros") Signed-off-by: Miaoqian Lin Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230102121318.3990586-1-linmq006@gmail.com Signed-off-by: Sasha Levin --- drivers/irqchip/irqchip.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c index 3570f0a588c4..7899607fbee8 100644 --- a/drivers/irqchip/irqchip.c +++ b/drivers/irqchip/irqchip.c @@ -38,8 +38,10 @@ int platform_irqchip_probe(struct platform_device *pdev) struct device_node *par_np = of_irq_find_parent(np); of_irq_init_cb_t irq_init_cb = of_device_get_match_data(&pdev->dev); - if (!irq_init_cb) + if (!irq_init_cb) { + of_node_put(par_np); return -EINVAL; + } if (par_np == np) par_np = NULL; @@ -52,8 +54,10 @@ int platform_irqchip_probe(struct platform_device *pdev) * interrupt controller. The actual initialization callback of this * interrupt controller can check for specific domains as necessary. */ - if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY)) + if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY)) { + of_node_put(par_np); return -EPROBE_DEFER; + } return irq_init_cb(np, par_np); } From c9aaf4efe1f02b2fef21a69fb3652f5ad12a5710 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 2 Jan 2023 12:28:10 +0400 Subject: [PATCH 1617/4345] irqchip/alpine-msi: Fix refcount leak in alpine_msix_init_domains [ Upstream commit 071d068b89e95d1b078aa6bbcb9d0961b77d6aa1 ] of_irq_find_parent() returns a node pointer with refcount incremented, We should use of_node_put() on it when not needed anymore. Add missing of_node_put() to avoid refcount leak. Fixes: e6b78f2c3e14 ("irqchip: Add the Alpine MSIX interrupt controller") Signed-off-by: Miaoqian Lin Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230102082811.3947760-1-linmq006@gmail.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-alpine-msi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/irqchip/irq-alpine-msi.c b/drivers/irqchip/irq-alpine-msi.c index ede02dc2bcd0..1819bb1d2723 100644 --- a/drivers/irqchip/irq-alpine-msi.c +++ b/drivers/irqchip/irq-alpine-msi.c @@ -199,6 +199,7 @@ static int alpine_msix_init_domains(struct alpine_msix_data *priv, } gic_domain = irq_find_host(gic_node); + of_node_put(gic_node); if (!gic_domain) { pr_err("Failed to find the GIC domain\n"); return -ENXIO; From cee12e8be8e227731a845ae43a4c9ce2e404be45 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 2 Jan 2023 12:42:08 +0400 Subject: [PATCH 1618/4345] irqchip/irq-mvebu-gicp: Fix refcount leak in mvebu_gicp_probe [ Upstream commit 9419e700021a393f67be36abd0c4f3acc6139041 ] of_irq_find_parent() returns a node pointer with refcount incremented, We should use of_node_put() on it when not needed anymore. Add missing of_node_put() to avoid refcount leak. Fixes: a68a63cb4dfc ("irqchip/irq-mvebu-gicp: Add new driver for Marvell GICP") Signed-off-by: Miaoqian Lin Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230102084208.3951758-1-linmq006@gmail.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-mvebu-gicp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c index 3be5c5dba1da..5caec411059f 100644 --- a/drivers/irqchip/irq-mvebu-gicp.c +++ b/drivers/irqchip/irq-mvebu-gicp.c @@ -223,6 +223,7 @@ static int mvebu_gicp_probe(struct platform_device *pdev) } parent_domain = irq_find_host(irq_parent_dn); + of_node_put(irq_parent_dn); if (!parent_domain) { dev_err(&pdev->dev, "failed to find parent IRQ domain\n"); return -ENODEV; From df8d3536b660c6c6f6b25fa8b157e9b38ad78142 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 2 Jan 2023 12:56:10 +0400 Subject: [PATCH 1619/4345] irqchip/ti-sci: Fix refcount leak in ti_sci_intr_irq_domain_probe [ Upstream commit 02298b7bae12936ca313975b02e7f98b06670d37 ] of_irq_find_parent() returns a node pointer with refcount incremented, We should use of_node_put() on it when not needed anymore. Add missing of_node_put() to avoid refcount leak. Fixes: cd844b0715ce ("irqchip/ti-sci-intr: Add support for Interrupt Router driver") Signed-off-by: Miaoqian Lin Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230102085611.3955984-1-linmq006@gmail.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-ti-sci-intr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/irqchip/irq-ti-sci-intr.c b/drivers/irqchip/irq-ti-sci-intr.c index fe8fad22bcf9..020ddf29efb8 100644 --- a/drivers/irqchip/irq-ti-sci-intr.c +++ b/drivers/irqchip/irq-ti-sci-intr.c @@ -236,6 +236,7 @@ static int ti_sci_intr_irq_domain_probe(struct platform_device *pdev) } parent_domain = irq_find_host(parent_node); + of_node_put(parent_node); if (!parent_domain) { dev_err(dev, "Failed to find IRQ parent domain\n"); return -ENODEV; From 4a614a68d9f87b22b4177e5e255a0ab90239b20d Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sat, 28 Jan 2023 17:35:12 +0100 Subject: [PATCH 1620/4345] s390/vmem: fix empty page tables cleanup under KASAN [ Upstream commit 108303b0a2d27cb14eed565e33e64ad9eefe5d7e ] Commit b9ff81003cf1 ("s390/vmem: cleanup empty page tables") introduced empty page tables cleanup in vmem code, but when the kernel is built with KASAN enabled the code has no effect due to wrong KASAN shadow memory intersection condition, which effectively ignores any memory range below KASAN shadow. Fix intersection condition to make code work as anticipated. Fixes: b9ff81003cf1 ("s390/vmem: cleanup empty page tables") Reviewed-by: Alexander Gordeev Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Sasha Levin --- arch/s390/mm/vmem.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index b239f2ba93b0..cbfff2460e58 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -296,7 +296,7 @@ static void try_free_pmd_table(pud_t *pud, unsigned long start) if (end > VMALLOC_START) return; #ifdef CONFIG_KASAN - if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end) + if (start < KASAN_SHADOW_END && end > KASAN_SHADOW_START) return; #endif pmd = pmd_offset(pud, start); @@ -371,7 +371,7 @@ static void try_free_pud_table(p4d_t *p4d, unsigned long start) if (end > VMALLOC_START) return; #ifdef CONFIG_KASAN - if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end) + if (start < KASAN_SHADOW_END && end > KASAN_SHADOW_START) return; #endif @@ -425,7 +425,7 @@ static void try_free_p4d_table(pgd_t *pgd, unsigned long start) if (end > VMALLOC_START) return; #ifdef CONFIG_KASAN - if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end) + if (start < KASAN_SHADOW_END && end > KASAN_SHADOW_START) return; #endif From 2416abd6bad28b8de107ccffe55095812369dd2b Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sat, 4 Feb 2023 17:39:20 +0000 Subject: [PATCH 1621/4345] net: add sock_init_data_uid() [ Upstream commit 584f3742890e966d2f0a1f3c418c9ead70b2d99e ] Add sock_init_data_uid() to explicitly initialize the socket uid. To initialise the socket uid, sock_init_data() assumes a the struct socket* sock is always embedded in a struct socket_alloc, used to access the corresponding inode uid. This may not be true. Examples are sockets created in tun_chr_open() and tap_open(). Fixes: 86741ec25462 ("net: core: Add a UID field to struct sock.") Signed-off-by: Pietro Borrello Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/sock.h | 7 ++++++- net/core/sock.c | 15 ++++++++++++--- 2 files changed, 18 insertions(+), 4 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 0f48d50a6dde..1d8529311d6f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1775,7 +1775,12 @@ void sk_common_release(struct sock *sk); * Default socket callbacks and setup code */ -/* Initialise core socket variables */ +/* Initialise core socket variables using an explicit uid. */ +void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid); + +/* Initialise core socket variables. + * Assumes struct socket *sock is embedded in a struct socket_alloc. + */ void sock_init_data(struct socket *sock, struct sock *sk); /* diff --git a/net/core/sock.c b/net/core/sock.c index 1bb6a003323b..c5ae520d4a69 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2968,7 +2968,7 @@ void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) } EXPORT_SYMBOL(sk_stop_timer_sync); -void sock_init_data(struct socket *sock, struct sock *sk) +void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; @@ -2987,11 +2987,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_type = sock->type; RCU_INIT_POINTER(sk->sk_wq, &sock->wq); sock->sk = sk; - sk->sk_uid = SOCK_INODE(sock)->i_uid; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); - sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0); } + sk->sk_uid = uid; rwlock_init(&sk->sk_callback_lock); if (sk->sk_kern_sock) @@ -3049,6 +3048,16 @@ void sock_init_data(struct socket *sock, struct sock *sk) refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } +EXPORT_SYMBOL(sock_init_data_uid); + +void sock_init_data(struct socket *sock, struct sock *sk) +{ + kuid_t uid = sock ? + SOCK_INODE(sock)->i_uid : + make_kuid(sock_net(sk)->user_ns, 0); + + sock_init_data_uid(sock, sk, uid); +} EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) From 9a31af61f397500ccae49d56d809b2217d1e2178 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sat, 4 Feb 2023 17:39:21 +0000 Subject: [PATCH 1622/4345] tun: tun_chr_open(): correctly initialize socket uid [ Upstream commit a096ccca6e503a5c575717ff8a36ace27510ab0a ] sock_init_data() assumes that the `struct socket` passed in input is contained in a `struct socket_alloc` allocated with sock_alloc(). However, tun_chr_open() passes a `struct socket` embedded in a `struct tun_file` allocated with sk_alloc(). This causes a type confusion when issuing a container_of() with SOCK_INODE() in sock_init_data() which results in assigning a wrong sk_uid to the `struct sock` in input. On default configuration, the type confused field overlaps with the high 4 bytes of `struct tun_struct __rcu *tun` of `struct tun_file`, NULL at the time of call, which makes the uid of all tun sockets 0, i.e., the root one. Fix the assignment by using sock_init_data_uid(). Fixes: 86741ec25462 ("net: core: Add a UID field to struct sock.") Signed-off-by: Pietro Borrello Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/tun.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 67ce7b779af6..f1d46aea8a2b 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3457,7 +3457,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; - sock_init_data(&tfile->socket, &tfile->sk); + sock_init_data_uid(&tfile->socket, &tfile->sk, inode->i_uid); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; From 4a9272a864cbf6dacc3f4b35213108dd01691d31 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sat, 4 Feb 2023 17:39:22 +0000 Subject: [PATCH 1623/4345] tap: tap_open(): correctly initialize socket uid [ Upstream commit 66b2c338adce580dfce2199591e65e2bab889cff ] sock_init_data() assumes that the `struct socket` passed in input is contained in a `struct socket_alloc` allocated with sock_alloc(). However, tap_open() passes a `struct socket` embedded in a `struct tap_queue` allocated with sk_alloc(). This causes a type confusion when issuing a container_of() with SOCK_INODE() in sock_init_data() which results in assigning a wrong sk_uid to the `struct sock` in input. On default configuration, the type confused field overlaps with padding bytes between `int vnet_hdr_sz` and `struct tap_dev __rcu *tap` in `struct tap_queue`, which makes the uid of all tap sockets 0, i.e., the root one. Fix the assignment by using sock_init_data_uid(). Fixes: 86741ec25462 ("net: core: Add a UID field to struct sock.") Signed-off-by: Pietro Borrello Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/tap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 8f7bb15206e9..d9018d9fe310 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -523,7 +523,7 @@ static int tap_open(struct inode *inode, struct file *file) q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; - sock_init_data(&q->sock, &q->sk); + sock_init_data_uid(&q->sock, &q->sk, inode->i_uid); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; From 4f4c970a05a24f4e3ecbfda534ec95caf498d2a0 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Wed, 8 Feb 2023 12:00:37 +0800 Subject: [PATCH 1624/4345] OPP: fix error checking in opp_migrate_dentry() [ Upstream commit eca4c0eea53432ec4b711b2a8ad282cbad231b4f ] Since commit ff9fb72bc077 ("debugfs: return error values, not NULL") changed return value of debugfs_rename() in error cases from %NULL to %ERR_PTR(-ERROR), we should also check error values instead of NULL. Fixes: ff9fb72bc077 ("debugfs: return error values, not NULL") Signed-off-by: Qi Zheng Signed-off-by: Viresh Kumar Signed-off-by: Sasha Levin --- drivers/opp/debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c index 596c185b5dda..60f4ff8e044d 100644 --- a/drivers/opp/debugfs.c +++ b/drivers/opp/debugfs.c @@ -204,7 +204,7 @@ static void opp_migrate_dentry(struct opp_device *opp_dev, dentry = debugfs_rename(rootdir, opp_dev->dentry, rootdir, opp_table->dentry_name); - if (!dentry) { + if (IS_ERR(dentry)) { dev_err(dev, "%s: Failed to rename link from: %s to %s\n", __func__, dev_name(opp_dev->dev), dev_name(dev)); return; From b8ed41cc04fb74005aa51d17865ca3d022760335 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 1 Feb 2023 14:01:11 -0800 Subject: [PATCH 1625/4345] Bluetooth: L2CAP: Fix potential user-after-free [ Upstream commit df5703348813235874d851934e957c3723d71644 ] This fixes all instances of which requires to allocate a buffer calling alloc_skb which may release the chan lock and reacquire later which makes it possible that the chan is disconnected in the meantime. Fixes: a6a5568c03c4 ("Bluetooth: Lock the L2CAP channel when sending") Reported-by: Alexander Coffin Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 24 ------------------------ net/bluetooth/l2cap_sock.c | 8 ++++++++ 2 files changed, 8 insertions(+), 24 deletions(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index cf56582d298a..bde90df6b497 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -2679,14 +2679,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) if (IS_ERR(skb)) return PTR_ERR(skb); - /* Channel lock is released before requesting new skb and then - * reacquired thus we need to recheck channel state. - */ - if (chan->state != BT_CONNECTED) { - kfree_skb(skb); - return -ENOTCONN; - } - l2cap_do_send(chan, skb); return len; } @@ -2731,14 +2723,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) if (IS_ERR(skb)) return PTR_ERR(skb); - /* Channel lock is released before requesting new skb and then - * reacquired thus we need to recheck channel state. - */ - if (chan->state != BT_CONNECTED) { - kfree_skb(skb); - return -ENOTCONN; - } - l2cap_do_send(chan, skb); err = len; break; @@ -2759,14 +2743,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) */ err = l2cap_segment_sdu(chan, &seg_queue, msg, len); - /* The channel could have been closed while segmenting, - * check that it is still connected. - */ - if (chan->state != BT_CONNECTED) { - __skb_queue_purge(&seg_queue); - err = -ENOTCONN; - } - if (err) break; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index d2c678520599..a267c9b6bcef 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1623,6 +1623,14 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan, if (!skb) return ERR_PTR(err); + /* Channel lock is released before requesting new skb and then + * reacquired thus we need to recheck channel state. + */ + if (chan->state != BT_CONNECTED) { + kfree_skb(skb); + return ERR_PTR(-ENOTCONN); + } + skb->priority = sk->sk_priority; bt_cb(skb)->l2cap.chan = chan; From b7aa7fbc16936efa5171b8038848e18acdbab63d Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 10 Feb 2023 01:12:01 +0100 Subject: [PATCH 1626/4345] libbpf: Fix alen calculation in libbpf_nla_dump_errormsg() [ Upstream commit 17bcd27a08a21397698edf143084d7c87ce17946 ] The code assumes that everything that comes after nlmsgerr are nlattrs. When calculating their size, it does not account for the initial nlmsghdr. This may lead to accessing uninitialized memory. Fixes: bbf48c18ee0c ("libbpf: add error reporting in XDP") Signed-off-by: Ilya Leoshkevich Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230210001210.395194-8-iii@linux.ibm.com Signed-off-by: Sasha Levin --- tools/lib/bpf/nlattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index b607fa9852b1..1a04299a2a60 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -178,7 +178,7 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh) hlen += nlmsg_len(&err->msg); attr = (struct nlattr *) ((void *) err + hlen); - alen = nlh->nlmsg_len - hlen; + alen = (void *)nlh + nlh->nlmsg_len - (void *)attr; if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) { From eb209a35d3627b6345bea0f07020c99897a2ca87 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Thu, 9 Feb 2023 12:26:23 +0000 Subject: [PATCH 1627/4345] rds: rds_rm_zerocopy_callback() correct order for list_add_tail() [ Upstream commit 68762148d1b011d47bc2ceed7321739b5aea1e63 ] rds_rm_zerocopy_callback() uses list_add_tail() with swapped arguments. This links the list head with the new entry, losing the references to the remaining part of the list. Fixes: 9426bbc6de99 ("rds: use list structure to track information for zerocopy completion notification") Suggested-by: Paolo Abeni Signed-off-by: Pietro Borrello Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/rds/message.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rds/message.c b/net/rds/message.c index b363ef13c75e..8fa3d19c2e66 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -118,7 +118,7 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, ck = &info->zcookies; memset(ck, 0, sizeof(*ck)); WARN_ON(!rds_zcookie_add(info, cookie)); - list_add_tail(&q->zcookie_head, &info->rs_zcookie_next); + list_add_tail(&info->rs_zcookie_next, &q->zcookie_head); spin_unlock_irqrestore(&q->lock, flags); /* caller invokes rds_wake_sk_sleep() */ From c9c87142260cd2278aaa432588788916e54d461c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 31 Jan 2023 16:02:04 +0800 Subject: [PATCH 1628/4345] crypto: rsa-pkcs1pad - Use akcipher_request_complete [ Upstream commit 564cabc0ca0bdfa8f0fc1ae74b24d0a7554522c5 ] Use the akcipher_request_complete helper instead of calling the completion function directly. In fact the previous code was buggy in that EINPROGRESS was never passed back to the original caller. Fixes: 3d5b1ecdea6f ("crypto: rsa - RSA padding algorithm") Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/rsa-pkcs1pad.c | 34 +++++++++++++++------------------- 1 file changed, 15 insertions(+), 19 deletions(-) diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c index 9d804831c8b3..a4ebbb889274 100644 --- a/crypto/rsa-pkcs1pad.c +++ b/crypto/rsa-pkcs1pad.c @@ -214,16 +214,14 @@ static void pkcs1pad_encrypt_sign_complete_cb( struct crypto_async_request *child_async_req, int err) { struct akcipher_request *req = child_async_req->data; - struct crypto_async_request async_req; if (err == -EINPROGRESS) - return; + goto out; - async_req.data = req->base.data; - async_req.tfm = crypto_akcipher_tfm(crypto_akcipher_reqtfm(req)); - async_req.flags = child_async_req->flags; - req->base.complete(&async_req, - pkcs1pad_encrypt_sign_complete(req, err)); + err = pkcs1pad_encrypt_sign_complete(req, err); + +out: + akcipher_request_complete(req, err); } static int pkcs1pad_encrypt(struct akcipher_request *req) @@ -332,15 +330,14 @@ static void pkcs1pad_decrypt_complete_cb( struct crypto_async_request *child_async_req, int err) { struct akcipher_request *req = child_async_req->data; - struct crypto_async_request async_req; if (err == -EINPROGRESS) - return; + goto out; - async_req.data = req->base.data; - async_req.tfm = crypto_akcipher_tfm(crypto_akcipher_reqtfm(req)); - async_req.flags = child_async_req->flags; - req->base.complete(&async_req, pkcs1pad_decrypt_complete(req, err)); + err = pkcs1pad_decrypt_complete(req, err); + +out: + akcipher_request_complete(req, err); } static int pkcs1pad_decrypt(struct akcipher_request *req) @@ -512,15 +509,14 @@ static void pkcs1pad_verify_complete_cb( struct crypto_async_request *child_async_req, int err) { struct akcipher_request *req = child_async_req->data; - struct crypto_async_request async_req; if (err == -EINPROGRESS) - return; + goto out; - async_req.data = req->base.data; - async_req.tfm = crypto_akcipher_tfm(crypto_akcipher_reqtfm(req)); - async_req.flags = child_async_req->flags; - req->base.complete(&async_req, pkcs1pad_verify_complete(req, err)); + err = pkcs1pad_verify_complete(req, err); + +out: + akcipher_request_complete(req, err); } /* From dabc22a30d83f97128992a8e1f9b8ee2f8a16f55 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 8 Feb 2023 17:08:25 -0800 Subject: [PATCH 1629/4345] m68k: /proc/hardware should depend on PROC_FS [ Upstream commit 1e5b5df65af99013b4d31607ddb3ca5731dbe44d ] When CONFIG_PROC_FS is not set, there is a build error for an unused function. Make PROC_HARDWARE depend on PROC_FS to prevent this error. In file included from ../arch/m68k/kernel/setup.c:3: ../arch/m68k/kernel/setup_mm.c:477:12: error: 'hardware_proc_show' defined but not used [-Werror=unused-function] 477 | static int hardware_proc_show(struct seq_file *m, void *v) | ^~~~~~~~~~~~~~~~~~ Fixes: 66d857b08b8c ("m68k: merge m68k and m68knommu arch directories") # v3.0 Signed-off-by: Randy Dunlap Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230209010825.24136-1-rdunlap@infradead.org Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- arch/m68k/Kconfig.devices | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/m68k/Kconfig.devices b/arch/m68k/Kconfig.devices index 6a87b4a5fcac..e6e3efac1840 100644 --- a/arch/m68k/Kconfig.devices +++ b/arch/m68k/Kconfig.devices @@ -19,6 +19,7 @@ config HEARTBEAT # We have a dedicated heartbeat LED. :-) config PROC_HARDWARE bool "/proc/hardware support" + depends on PROC_FS help Say Y here to support the /proc/hardware file, which gives you access to information about the machine you're running on, From 5da95a7eb9e3e045db4082fd906b40e67181c443 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 3 Jan 2023 19:41:00 +0530 Subject: [PATCH 1630/4345] RISC-V: time: initialize hrtimer based broadcast clock event device [ Upstream commit 8b3b8fbb4896984b5564789a42240e4b3caddb61 ] Similarly to commit 022eb8ae8b5e ("ARM: 8938/1: kernel: initialize broadcast hrtimer based clock event device"), RISC-V needs to initiate hrtimer based broadcast clock event device before C3STOP can be used. Otherwise, the introduction of C3STOP for the RISC-V arch timer in commit 232ccac1bd9b ("clocksource/drivers/riscv: Events are stopped during CPU suspend") leaves us without any broadcast timer registered. This prevents the kernel from entering oneshot mode, which breaks timer behaviour, for example clock_nanosleep(). A test app that sleeps each cpu for 6, 5, 4, 3 ms respectively, HZ=250 & C3STOP enabled, the sleep times are rounded up to the next jiffy: == CPU: 1 == == CPU: 2 == == CPU: 3 == == CPU: 4 == Mean: 7.974992 Mean: 7.976534 Mean: 7.962591 Mean: 3.952179 Std Dev: 0.154374 Std Dev: 0.156082 Std Dev: 0.171018 Std Dev: 0.076193 Hi: 9.472000 Hi: 10.495000 Hi: 8.864000 Hi: 4.736000 Lo: 6.087000 Lo: 6.380000 Lo: 4.872000 Lo: 3.403000 Samples: 521 Samples: 521 Samples: 521 Samples: 521 Link: https://lore.kernel.org/linux-riscv/YzYTNQRxLr7Q9JR0@spud/ Fixes: 232ccac1bd9b ("clocksource/drivers/riscv: Events are stopped during CPU suspend") Suggested-by: Samuel Holland Signed-off-by: Conor Dooley Signed-off-by: Anup Patel Reviewed-by: Samuel Holland Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20230103141102.772228-2-apatel@ventanamicro.com Signed-off-by: Daniel Lezcano Signed-off-by: Sasha Levin --- arch/riscv/kernel/time.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 8a5cf99c0776..303ae47dfb4d 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -5,6 +5,7 @@ */ #include +#include #include #include #include @@ -28,6 +29,8 @@ void __init time_init(void) of_clk_init(NULL); timer_probe(); + + tick_setup_hrtimer_broadcast(); } void clocksource_arch_init(struct clocksource *cs) From 2f80b3ff92514ebd227e5c55d3d1e480401b02b7 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 8 Feb 2023 14:30:32 +0800 Subject: [PATCH 1631/4345] wifi: iwl3945: Add missing check for create_singlethread_workqueue [ Upstream commit 1fdeb8b9f29dfd64805bb49475ac7566a3cb06cb ] Add the check for the return value of the create_singlethread_workqueue in order to avoid NULL pointer dereference. Fixes: b481de9ca074 ("[IWLWIFI]: add iwlwifi wireless drivers") Signed-off-by: Jiasheng Jiang Acked-by: Stanislaw Gruszka Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230208063032.42763-2-jiasheng@iscas.ac.cn Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlegacy/3945-mac.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c index 4ca8212d4fa4..ef0ac42a55a2 100644 --- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c @@ -3380,10 +3380,12 @@ static DEVICE_ATTR(dump_errors, 0200, NULL, il3945_dump_error_log); * *****************************************************************************/ -static void +static int il3945_setup_deferred_work(struct il_priv *il) { il->workqueue = create_singlethread_workqueue(DRV_NAME); + if (!il->workqueue) + return -ENOMEM; init_waitqueue_head(&il->wait_command_queue); @@ -3400,6 +3402,8 @@ il3945_setup_deferred_work(struct il_priv *il) timer_setup(&il->watchdog, il_bg_watchdog, 0); tasklet_setup(&il->irq_tasklet, il3945_irq_tasklet); + + return 0; } static void @@ -3721,7 +3725,10 @@ il3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } il_set_rxon_channel(il, &il->bands[NL80211_BAND_2GHZ].channels[5]); - il3945_setup_deferred_work(il); + err = il3945_setup_deferred_work(il); + if (err) + goto out_remove_sysfs; + il3945_setup_handlers(il); il_power_initialize(il); @@ -3733,7 +3740,7 @@ il3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = il3945_setup_mac(il); if (err) - goto out_remove_sysfs; + goto out_destroy_workqueue; il_dbgfs_register(il, DRV_NAME); @@ -3742,9 +3749,10 @@ il3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; -out_remove_sysfs: +out_destroy_workqueue: destroy_workqueue(il->workqueue); il->workqueue = NULL; +out_remove_sysfs: sysfs_remove_group(&pdev->dev.kobj, &il3945_attribute_group); out_release_irq: free_irq(il->pci_dev->irq, il); From 3185d6cfc59277a77bf311dce701b7e25193f66a Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Thu, 9 Feb 2023 09:07:48 +0800 Subject: [PATCH 1632/4345] wifi: iwl4965: Add missing check for create_singlethread_workqueue() [ Upstream commit 26e6775f75517ad6844fe5b79bc5f3fa8c22ee61 ] Add the check for the return value of the create_singlethread_workqueue() in order to avoid NULL pointer dereference. Fixes: b481de9ca074 ("[IWLWIFI]: add iwlwifi wireless drivers") Signed-off-by: Jiasheng Jiang Acked-by: Stanislaw Gruszka Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230209010748.45454-1-jiasheng@iscas.ac.cn Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlegacy/4965-mac.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c index 28675a4ad861..12cf22d0e994 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c @@ -6212,10 +6212,12 @@ out: mutex_unlock(&il->mutex); } -static void +static int il4965_setup_deferred_work(struct il_priv *il) { il->workqueue = create_singlethread_workqueue(DRV_NAME); + if (!il->workqueue) + return -ENOMEM; init_waitqueue_head(&il->wait_command_queue); @@ -6234,6 +6236,8 @@ il4965_setup_deferred_work(struct il_priv *il) timer_setup(&il->watchdog, il_bg_watchdog, 0); tasklet_setup(&il->irq_tasklet, il4965_irq_tasklet); + + return 0; } static void @@ -6623,7 +6627,10 @@ il4965_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_disable_msi; } - il4965_setup_deferred_work(il); + err = il4965_setup_deferred_work(il); + if (err) + goto out_free_irq; + il4965_setup_handlers(il); /********************************************* @@ -6661,6 +6668,7 @@ il4965_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) out_destroy_workqueue: destroy_workqueue(il->workqueue); il->workqueue = NULL; +out_free_irq: free_irq(il->pci_dev->irq, il); out_disable_msi: pci_disable_msi(il->pci_dev); From d7c5ecbc4915be882a305e4aadf43857cca6eb93 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 6 Feb 2023 17:41:33 +0300 Subject: [PATCH 1633/4345] wifi: mwifiex: fix loop iterator in mwifiex_update_ampdu_txwinsize() [ Upstream commit 3cfb7df24cee0f5fdc4cc5d3176cab9aadfcb430 ] This code re-uses "i" to be the iterator for both the inside and outside loops. It means the outside loop will exit earlier than intended. Fixes: d219b7eb3792 ("mwifiex: handle BT coex event to adjust Rx BA window size") Signed-off-by: Dan Carpenter Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/Y+ERnaDaZD7RtLvX@kili Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/11n.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c index cf08a4af84d6..b99381ebb82a 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n.c +++ b/drivers/net/wireless/marvell/mwifiex/11n.c @@ -890,7 +890,7 @@ mwifiex_send_delba_txbastream_tbl(struct mwifiex_private *priv, u8 tid) */ void mwifiex_update_ampdu_txwinsize(struct mwifiex_adapter *adapter) { - u8 i; + u8 i, j; u32 tx_win_size; struct mwifiex_private *priv; @@ -921,8 +921,8 @@ void mwifiex_update_ampdu_txwinsize(struct mwifiex_adapter *adapter) if (tx_win_size != priv->add_ba_param.tx_win_size) { if (!priv->media_connected) continue; - for (i = 0; i < MAX_NUM_TID; i++) - mwifiex_send_delba_txbastream_tbl(priv, i); + for (j = 0; j < MAX_NUM_TID; j++) + mwifiex_send_delba_txbastream_tbl(priv, j); } } } From b10827bce73943b0823b26ef5aebc4b971733d50 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Thu, 9 Feb 2023 00:12:11 +0100 Subject: [PATCH 1634/4345] selftests/bpf: Fix out-of-srctree build [ Upstream commit 0b0757244754ea1d0721195c824770f5576e119e ] Building BPF selftests out of srctree fails with: make: *** No rule to make target '/linux-build//ima_setup.sh', needed by 'ima_setup.sh'. Stop. The culprit is the rule that defines convenient shorthands like "make test_progs", which builds $(OUTPUT)/test_progs. These shorthands make sense only for binaries that are built though; scripts that live in the source tree do not end up in $(OUTPUT). Therefore drop $(TEST_PROGS) and $(TEST_PROGS_EXTENDED) from the rule. The issue exists for a while, but it became a problem only after commit d68ae4982cb7 ("selftests/bpf: Install all required files to run selftests"), which added dependencies on these scripts. Fixes: 03dcb78460c2 ("selftests/bpf: Add simple per-test targets to Makefile") Signed-off-by: Ilya Leoshkevich Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230208231211.283606-1-iii@linux.ibm.com Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/Makefile | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 1d9155533360..a845724e0906 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -119,8 +119,6 @@ RESOLVE_BTFIDS := $(BUILD_DIR)/resolve_btfids/resolve_btfids # NOTE: Semicolon at the end is critical to override lib.mk's default static # rule for binaries. $(notdir $(TEST_GEN_PROGS) \ - $(TEST_PROGS) \ - $(TEST_PROGS_EXTENDED) \ $(TEST_GEN_PROGS_EXTENDED) \ $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ; From f333346001f9ea152d04b3848e77f986ab69e5aa Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 6 Feb 2023 14:01:53 +0800 Subject: [PATCH 1635/4345] crypto: crypto4xx - Call dma_unmap_page when done [ Upstream commit bcdda4301bdc4955d45f7e1ffefb6207967b067e ] In crypto4xx_cipher_done, we should be unmapping the dst page, not mapping it. This was flagged by a sparse warning about the unused addr variable. While we're at it, also fix a sparse warning regarding the unused ctx variable in crypto4xx_ahash_done (by actually using it). Fixes: 049359d65527 ("crypto: amcc - Add crypt4xx driver") Signed-off-by: Herbert Xu Tested-by: Christian Lamparter Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/amcc/crypto4xx_core.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c index 2e3690f65786..6d05ac0c0513 100644 --- a/drivers/crypto/amcc/crypto4xx_core.c +++ b/drivers/crypto/amcc/crypto4xx_core.c @@ -522,7 +522,6 @@ static void crypto4xx_cipher_done(struct crypto4xx_device *dev, { struct skcipher_request *req; struct scatterlist *dst; - dma_addr_t addr; req = skcipher_request_cast(pd_uinfo->async_req); @@ -531,8 +530,8 @@ static void crypto4xx_cipher_done(struct crypto4xx_device *dev, req->cryptlen, req->dst); } else { dst = pd_uinfo->dest_va; - addr = dma_map_page(dev->core_dev->device, sg_page(dst), - dst->offset, dst->length, DMA_FROM_DEVICE); + dma_unmap_page(dev->core_dev->device, pd->dest, dst->length, + DMA_FROM_DEVICE); } if (pd_uinfo->sa_va->sa_command_0.bf.save_iv == SA_SAVE_IV) { @@ -557,10 +556,9 @@ static void crypto4xx_ahash_done(struct crypto4xx_device *dev, struct ahash_request *ahash_req; ahash_req = ahash_request_cast(pd_uinfo->async_req); - ctx = crypto_tfm_ctx(ahash_req->base.tfm); + ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(ahash_req)); - crypto4xx_copy_digest_to_dst(ahash_req->result, pd_uinfo, - crypto_tfm_ctx(ahash_req->base.tfm)); + crypto4xx_copy_digest_to_dst(ahash_req->result, pd_uinfo, ctx); crypto4xx_ret_sg_desc(dev, pd_uinfo); if (pd_uinfo->state & PD_ENTRY_BUSY) From 3856f7559722b76a66a3f59eb3217dfd7fcaca15 Mon Sep 17 00:00:00 2001 From: Shayne Chen Date: Thu, 9 Feb 2023 19:06:59 +0800 Subject: [PATCH 1636/4345] wifi: mac80211: make rate u32 in sta_set_rate_info_rx() [ Upstream commit 59336e07b287d91dc4ec265e07724e8f7e3d0209 ] The value of last_rate in ieee80211_sta_rx_stats is degraded from u32 to u16 after being assigned to rate variable, which causes information loss in STA_STATS_FIELD_TYPE and later bitfields. Signed-off-by: Shayne Chen Link: https://lore.kernel.org/r/20230209110659.25447-1-shayne.chen@mediatek.com Fixes: 41cbb0f5a295 ("mac80211: add support for HE") Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/sta_info.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index cee39ae52245..d572478c4d68 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2159,7 +2159,7 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate, static int sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) { - u16 rate = READ_ONCE(sta_get_last_rx_stats(sta)->last_rate); + u32 rate = READ_ONCE(sta_get_last_rx_stats(sta)->last_rate); if (rate == STA_STATS_RATE_INVALID) return -EINVAL; From e02bc492883abf751fd1a8d89fc025fbce6744c6 Mon Sep 17 00:00:00 2001 From: Yongqin Liu Date: Fri, 10 Feb 2023 22:15:07 +0800 Subject: [PATCH 1637/4345] thermal/drivers/hisi: Drop second sensor hi3660 [ Upstream commit 15cc25829a97c3957e520e971868aacc84341317 ] The commit 74c8e6bffbe1 ("driver core: Add __alloc_size hint to devm allocators") exposes a panic "BRK handler: Fatal exception" on the hi3660_thermal_probe funciton. This is because the function allocates memory for only one sensors array entry, but tries to fill up a second one. Fix this by removing the unneeded second access. Fixes: 7d3a2a2bbadb ("thermal/drivers/hisi: Fix number of sensors on hi3660") Signed-off-by: Yongqin Liu Link: https://lore.kernel.org/linux-mm/20221101223321.1326815-5-keescook@chromium.org/ Link: https://lore.kernel.org/r/20230210141507.71014-1-yongqin.liu@linaro.org Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/thermal/hisi_thermal.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index ee05950afd2f..7b1e81912ccf 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -435,10 +435,6 @@ static int hi3660_thermal_probe(struct hisi_thermal_data *data) data->sensor[0].irq_name = "tsensor_a73"; data->sensor[0].data = data; - data->sensor[1].id = HI3660_LITTLE_SENSOR; - data->sensor[1].irq_name = "tsensor_a53"; - data->sensor[1].data = data; - return 0; } From 3e8733949f81c5e95002f7365974adcef2ea3888 Mon Sep 17 00:00:00 2001 From: Frank Jungclaus Date: Thu, 16 Feb 2023 20:04:48 +0100 Subject: [PATCH 1638/4345] can: esd_usb: Move mislocated storage of SJA1000_ECC_SEG bits in case of a bus error [ Upstream commit 118469f88180438ef43dee93d71f77c00e7b425d ] Move the supply for cf->data[3] (bit stream position of CAN error), in case of a bus- or protocol-error, outside of the "switch (ecc & SJA1000_ECC_MASK){}"-statement, because this bit stream position is independent of the error type. Fixes: 96d8e90382dc ("can: Add driver for esd CAN-USB/2 device") Signed-off-by: Frank Jungclaus Link: https://lore.kernel.org/all/20230216190450.3901254-2-frank.jungclaus@esd.eu Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- drivers/net/can/usb/esd_usb2.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index 73c5343e609b..c9ccce6c60b4 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -278,7 +278,6 @@ static void esd_usb2_rx_event(struct esd_usb2_net_priv *priv, cf->data[2] |= CAN_ERR_PROT_STUFF; break; default: - cf->data[3] = ecc & SJA1000_ECC_SEG; break; } @@ -286,6 +285,9 @@ static void esd_usb2_rx_event(struct esd_usb2_net_priv *priv, if (!(ecc & SJA1000_ECC_DIR)) cf->data[2] |= CAN_ERR_PROT_TX; + /* Bit stream position in CAN frame as the error was detected */ + cf->data[3] = ecc & SJA1000_ECC_SEG; + if (priv->can.state == CAN_STATE_ERROR_WARNING || priv->can.state == CAN_STATE_ERROR_PASSIVE) { cf->data[1] = (txerr > rxerr) ? From 9f487d888ee5cddc6d78c16ae6cd554ceda78a78 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 15 Feb 2023 20:59:52 -0800 Subject: [PATCH 1639/4345] bpf: Fix global subprog context argument resolution logic [ Upstream commit d384dce281ed1b504fae2e279507827638d56fa3 ] KPROBE program's user-facing context type is defined as typedef bpf_user_pt_regs_t. This leads to a problem when trying to passing kprobe/uprobe/usdt context argument into global subprog, as kernel always strip away mods and typedefs of user-supplied type, but takes expected type from bpf_ctx_convert as is, which causes mismatch. Current way to work around this is to define a fake struct with the same name as expected typedef: struct bpf_user_pt_regs_t {}; __noinline my_global_subprog(struct bpf_user_pt_regs_t *ctx) { ... } This patch fixes the issue by resolving expected type, if it's not a struct. It still leaves the above work-around working for backwards compatibility. Fixes: 91cc1a99740e ("bpf: Annotate context types") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20230216045954.3002473-2-andrii@kernel.org Signed-off-by: Sasha Levin --- kernel/bpf/btf.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 52e704860739..11b612e94e4e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4273,6 +4273,7 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, if (!ctx_struct) /* should not happen */ return NULL; +again: ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off); if (!ctx_tname) { /* should not happen */ @@ -4286,8 +4287,16 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, * int socket_filter_bpf_prog(struct __sk_buff *skb) * { // no fields of skb are ever used } */ - if (strcmp(ctx_tname, tname)) - return NULL; + if (strcmp(ctx_tname, tname)) { + /* bpf_user_pt_regs_t is a typedef, so resolve it to + * underlying struct and check name again + */ + if (!btf_type_is_modifier(ctx_struct)) + return NULL; + while (btf_type_is_modifier(ctx_struct)) + ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type); + goto again; + } return ctx_type; } From 27a601623dde64da601dc4a881691ee592cfaab0 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 16 Dec 2022 15:09:33 -0800 Subject: [PATCH 1640/4345] irqchip/irq-brcmstb-l2: Set IRQ_LEVEL for level triggered interrupts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 94debe03e8afa1267f95a9001786a6aa506b9ff3 ] When support for the level triggered interrupt controller flavor was added with c0ca7262088e, we forgot to update the flags to be set to contain IRQ_LEVEL. While the flow handler is correct, the output from /proc/interrupts does not show such interrupts as being level triggered when they are, correct that. Fixes: c0ca7262088e ("irqchip/brcmstb-l2: Add support for the BCM7271 L2 controller") Signed-off-by: Florian Fainelli Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221216230934.2478345-2-f.fainelli@gmail.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-brcmstb-l2.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index cdd6a42d4efa..a4aee16db531 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -161,6 +161,7 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np, *init_params) { unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; + unsigned int set = 0; struct brcmstb_l2_intc_data *data; struct irq_chip_type *ct; int ret; @@ -208,9 +209,12 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np, if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) flags |= IRQ_GC_BE_IO; + if (init_params->handler == handle_level_irq) + set |= IRQ_LEVEL; + /* Allocate a single Generic IRQ chip for this node */ ret = irq_alloc_domain_generic_chips(data->domain, 32, 1, - np->full_name, init_params->handler, clr, 0, flags); + np->full_name, init_params->handler, clr, set, flags); if (ret) { pr_err("failed to allocate generic irq chip\n"); goto out_free_domain; From 7cefa692224a94ae65ef844037c74119ad13f855 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 16 Dec 2022 15:09:34 -0800 Subject: [PATCH 1641/4345] irqchip/irq-bcm7120-l2: Set IRQ_LEVEL for level triggered interrupts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 13a157b38ca5b4f9eed81442b8821db293755961 ] When support for the interrupt controller was added with a5042de2688d, we forgot to update the flags to be set to contain IRQ_LEVEL. While the flow handler is correct, the output from /proc/interrupts does not show such interrupts as being level triggered when they are, correct that. Fixes: a5042de2688d ("irqchip: bcm7120-l2: Add Broadcom BCM7120-style Level 2 interrupt controller") Signed-off-by: Florian Fainelli Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221216230934.2478345-3-f.fainelli@gmail.com Signed-off-by: Sasha Levin --- drivers/irqchip/irq-bcm7120-l2.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c index c7c9e976acbb..7d776c905b7d 100644 --- a/drivers/irqchip/irq-bcm7120-l2.c +++ b/drivers/irqchip/irq-bcm7120-l2.c @@ -273,7 +273,8 @@ static int __init bcm7120_l2_intc_probe(struct device_node *dn, flags |= IRQ_GC_BE_IO; ret = irq_alloc_domain_generic_chips(data->domain, IRQS_PER_WORD, 1, - dn->full_name, handle_level_irq, clr, 0, flags); + dn->full_name, handle_level_irq, clr, + IRQ_LEVEL, flags); if (ret) { pr_err("failed to allocate generic irq chip\n"); goto out_free_domain; From 5663df20622d0e19283de8d348037a841f33ff65 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Thu, 16 Feb 2023 13:43:40 +0100 Subject: [PATCH 1642/4345] selftests/net: Interpret UDP_GRO cmsg data as an int value [ Upstream commit 436864095a95fcc611c20c44a111985fa9848730 ] Data passed to user-space with a (SOL_UDP, UDP_GRO) cmsg carries an int (see udp_cmsg_recv), not a u16 value, as strace confirms: recvmsg(8, {msg_name=..., msg_iov=[{iov_base="\0\0..."..., iov_len=96000}], msg_iovlen=1, msg_control=[{cmsg_len=20, <-- sizeof(cmsghdr) + 4 cmsg_level=SOL_UDP, cmsg_type=0x68}], <-- UDP_GRO msg_controllen=24, msg_flags=0}, 0) = 11200 Interpreting the data as an u16 value won't work on big-endian platforms. Since it is too late to back out of this API decision [1], fix the test. [1]: https://lore.kernel.org/netdev/20230131174601.203127-1-jakub@cloudflare.com/ Fixes: 3327a9c46352 ("selftests: add functionals test for UDP GRO") Suggested-by: Eric Dumazet Signed-off-by: Jakub Sitnicki Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- tools/testing/selftests/net/udpgso_bench_rx.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 4058c7451e70..f35a924d4a30 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -214,11 +214,10 @@ static void do_verify_udp(const char *data, int len) static int recv_msg(int fd, char *buf, int len, int *gso_size) { - char control[CMSG_SPACE(sizeof(uint16_t))] = {0}; + char control[CMSG_SPACE(sizeof(int))] = {0}; struct msghdr msg = {0}; struct iovec iov = {0}; struct cmsghdr *cmsg; - uint16_t *gsosizeptr; int ret; iov.iov_base = buf; @@ -237,8 +236,7 @@ static int recv_msg(int fd, char *buf, int len, int *gso_size) cmsg = CMSG_NXTHDR(&msg, cmsg)) { if (cmsg->cmsg_level == SOL_UDP && cmsg->cmsg_type == UDP_GRO) { - gsosizeptr = (uint16_t *) CMSG_DATA(cmsg); - *gso_size = *gsosizeptr; + *gso_size = *(int *)CMSG_DATA(cmsg); break; } } From 4a413d360959962995e16a899cf2b9ef53e9fcb9 Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Fri, 17 Feb 2023 01:37:10 +0900 Subject: [PATCH 1643/4345] l2tp: Avoid possible recursive deadlock in l2tp_tunnel_register() [ Upstream commit 9ca5e7ecab064f1f47da07f7c1ddf40e4bc0e5ac ] When a file descriptor of pppol2tp socket is passed as file descriptor of UDP socket, a recursive deadlock occurs in l2tp_tunnel_register(). This situation is reproduced by the following program: int main(void) { int sock; struct sockaddr_pppol2tp addr; sock = socket(AF_PPPOX, SOCK_DGRAM, PX_PROTO_OL2TP); if (sock < 0) { perror("socket"); return 1; } addr.sa_family = AF_PPPOX; addr.sa_protocol = PX_PROTO_OL2TP; addr.pppol2tp.pid = 0; addr.pppol2tp.fd = sock; addr.pppol2tp.addr.sin_family = PF_INET; addr.pppol2tp.addr.sin_port = htons(0); addr.pppol2tp.addr.sin_addr.s_addr = inet_addr("192.168.0.1"); addr.pppol2tp.s_tunnel = 1; addr.pppol2tp.s_session = 0; addr.pppol2tp.d_tunnel = 0; addr.pppol2tp.d_session = 0; if (connect(sock, (const struct sockaddr *)&addr, sizeof(addr)) < 0) { perror("connect"); return 1; } return 0; } This program causes the following lockdep warning: ============================================ WARNING: possible recursive locking detected 6.2.0-rc5-00205-gc96618275234 #56 Not tainted -------------------------------------------- repro/8607 is trying to acquire lock: ffff8880213c8130 (sk_lock-AF_PPPOX){+.+.}-{0:0}, at: l2tp_tunnel_register+0x2b7/0x11c0 but task is already holding lock: ffff8880213c8130 (sk_lock-AF_PPPOX){+.+.}-{0:0}, at: pppol2tp_connect+0xa82/0x1a30 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(sk_lock-AF_PPPOX); lock(sk_lock-AF_PPPOX); *** DEADLOCK *** May be due to missing lock nesting notation 1 lock held by repro/8607: #0: ffff8880213c8130 (sk_lock-AF_PPPOX){+.+.}-{0:0}, at: pppol2tp_connect+0xa82/0x1a30 stack backtrace: CPU: 0 PID: 8607 Comm: repro Not tainted 6.2.0-rc5-00205-gc96618275234 #56 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.1-2.fc37 04/01/2014 Call Trace: dump_stack_lvl+0x100/0x178 __lock_acquire.cold+0x119/0x3b9 ? lockdep_hardirqs_on_prepare+0x410/0x410 lock_acquire+0x1e0/0x610 ? l2tp_tunnel_register+0x2b7/0x11c0 ? lock_downgrade+0x710/0x710 ? __fget_files+0x283/0x3e0 lock_sock_nested+0x3a/0xf0 ? l2tp_tunnel_register+0x2b7/0x11c0 l2tp_tunnel_register+0x2b7/0x11c0 ? sprintf+0xc4/0x100 ? l2tp_tunnel_del_work+0x6b0/0x6b0 ? debug_object_deactivate+0x320/0x320 ? lockdep_init_map_type+0x16d/0x7a0 ? lockdep_init_map_type+0x16d/0x7a0 ? l2tp_tunnel_create+0x2bf/0x4b0 ? l2tp_tunnel_create+0x3c6/0x4b0 pppol2tp_connect+0x14e1/0x1a30 ? pppol2tp_put_sk+0xd0/0xd0 ? aa_sk_perm+0x2b7/0xa80 ? aa_af_perm+0x260/0x260 ? bpf_lsm_socket_connect+0x9/0x10 ? pppol2tp_put_sk+0xd0/0xd0 __sys_connect_file+0x14f/0x190 __sys_connect+0x133/0x160 ? __sys_connect_file+0x190/0x190 ? lockdep_hardirqs_on+0x7d/0x100 ? ktime_get_coarse_real_ts64+0x1b7/0x200 ? ktime_get_coarse_real_ts64+0x147/0x200 ? __audit_syscall_entry+0x396/0x500 __x64_sys_connect+0x72/0xb0 do_syscall_64+0x38/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd This patch fixes the issue by getting/creating the tunnel before locking the pppol2tp socket. Fixes: 0b2c59720e65 ("l2tp: close all race conditions in l2tp_tunnel_register()") Cc: Cong Wang Signed-off-by: Shigeru Yoshida Reviewed-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/l2tp/l2tp_ppp.c | 127 ++++++++++++++++++++++++-------------------- 1 file changed, 68 insertions(+), 59 deletions(-) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index aea85f91f059..5ecc0f200944 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -651,6 +651,65 @@ static int pppol2tp_tunnel_mtu(const struct l2tp_tunnel *tunnel) return mtu - PPPOL2TP_HEADER_OVERHEAD; } +static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net, + const struct l2tp_connect_info *info, + bool *new_tunnel) +{ + struct l2tp_tunnel *tunnel; + int error; + + *new_tunnel = false; + + tunnel = l2tp_tunnel_get(net, info->tunnel_id); + + /* Special case: create tunnel context if session_id and + * peer_session_id is 0. Otherwise look up tunnel using supplied + * tunnel id. + */ + if (!info->session_id && !info->peer_session_id) { + if (!tunnel) { + struct l2tp_tunnel_cfg tcfg = { + .encap = L2TP_ENCAPTYPE_UDP, + }; + + /* Prevent l2tp_tunnel_register() from trying to set up + * a kernel socket. + */ + if (info->fd < 0) + return ERR_PTR(-EBADF); + + error = l2tp_tunnel_create(info->fd, + info->version, + info->tunnel_id, + info->peer_tunnel_id, &tcfg, + &tunnel); + if (error < 0) + return ERR_PTR(error); + + l2tp_tunnel_inc_refcount(tunnel); + error = l2tp_tunnel_register(tunnel, net, &tcfg); + if (error < 0) { + kfree(tunnel); + return ERR_PTR(error); + } + + *new_tunnel = true; + } + } else { + /* Error if we can't find the tunnel */ + if (!tunnel) + return ERR_PTR(-ENOENT); + + /* Error if socket is not prepped */ + if (!tunnel->sock) { + l2tp_tunnel_dec_refcount(tunnel); + return ERR_PTR(-ENOENT); + } + } + + return tunnel; +} + /* connect() handler. Attach a PPPoX socket to a tunnel UDP socket */ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, @@ -664,7 +723,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, struct pppol2tp_session *ps; struct l2tp_session_cfg cfg = { 0, }; bool drop_refcnt = false; - bool drop_tunnel = false; bool new_session = false; bool new_tunnel = false; int error; @@ -673,6 +731,14 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (error < 0) return error; + /* Don't bind if tunnel_id is 0 */ + if (!info.tunnel_id) + return -EINVAL; + + tunnel = pppol2tp_tunnel_get(sock_net(sk), &info, &new_tunnel); + if (IS_ERR(tunnel)) + return PTR_ERR(tunnel); + lock_sock(sk); /* Check for already bound sockets */ @@ -685,62 +751,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (sk->sk_user_data) goto end; /* socket is already attached */ - /* Don't bind if tunnel_id is 0 */ - error = -EINVAL; - if (!info.tunnel_id) - goto end; - - tunnel = l2tp_tunnel_get(sock_net(sk), info.tunnel_id); - if (tunnel) - drop_tunnel = true; - - /* Special case: create tunnel context if session_id and - * peer_session_id is 0. Otherwise look up tunnel using supplied - * tunnel id. - */ - if (!info.session_id && !info.peer_session_id) { - if (!tunnel) { - struct l2tp_tunnel_cfg tcfg = { - .encap = L2TP_ENCAPTYPE_UDP, - }; - - /* Prevent l2tp_tunnel_register() from trying to set up - * a kernel socket. - */ - if (info.fd < 0) { - error = -EBADF; - goto end; - } - - error = l2tp_tunnel_create(info.fd, - info.version, - info.tunnel_id, - info.peer_tunnel_id, &tcfg, - &tunnel); - if (error < 0) - goto end; - - l2tp_tunnel_inc_refcount(tunnel); - error = l2tp_tunnel_register(tunnel, sock_net(sk), - &tcfg); - if (error < 0) { - kfree(tunnel); - goto end; - } - drop_tunnel = true; - new_tunnel = true; - } - } else { - /* Error if we can't find the tunnel */ - error = -ENOENT; - if (!tunnel) - goto end; - - /* Error if socket is not prepped */ - if (!tunnel->sock) - goto end; - } - if (tunnel->peer_tunnel_id == 0) tunnel->peer_tunnel_id = info.peer_tunnel_id; @@ -841,8 +851,7 @@ end: } if (drop_refcnt) l2tp_session_dec_refcount(session); - if (drop_tunnel) - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_dec_refcount(tunnel); release_sock(sk); return error; From e1c848d9ddd56f67f201e6e7571cbca90dfdf4fb Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Thu, 16 Feb 2023 11:41:28 -0800 Subject: [PATCH 1644/4345] net: bcmgenet: fix MoCA LED control [ Upstream commit a7515af9fb8f0890fe540b108def4a86b9e8330a ] When the bcmgenet_mii_config() code was refactored it was missed that the LED control for the MoCA interface got overwritten by the port_ctrl value. Its previous programming is restored here. Fixes: 4f8d81b77e66 ("net: bcmgenet: Refactor register access in bcmgenet_mii_config") Signed-off-by: Doug Berger Acked-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/genet/bcmmii.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index f9e91304d232..4b875838a646 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -165,15 +165,6 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable) static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) { - u32 reg; - - if (!GENET_IS_V5(priv)) { - /* Speed settings are set in bcmgenet_mii_setup() */ - reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL); - reg |= LED_ACT_SOURCE_MAC; - bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL); - } - if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET) fixed_phy_set_link_update(priv->dev->phydev, bcmgenet_fixed_phy_link_update); @@ -206,6 +197,8 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) if (!phy_name) { phy_name = "MoCA"; + if (!GENET_IS_V5(priv)) + port_ctrl |= LED_ACT_SOURCE_MAC; bcmgenet_moca_phy_setup(priv); } break; From 6038e458798d578d9e6736f4b424d8b851fc6d10 Mon Sep 17 00:00:00 2001 From: Roxana Nicolescu Date: Mon, 20 Feb 2023 12:04:00 +0100 Subject: [PATCH 1645/4345] selftest: fib_tests: Always cleanup before exit [ Upstream commit b60417a9f2b890a8094477b2204d4f73c535725e ] Usage of `set -e` before executing a command causes immediate exit on failure, without cleanup up the resources allocated at setup. This can affect the next tests that use the same resources, leading to a chain of failures. A simple fix is to always call cleanup function when the script exists. This approach is already used by other existing tests. Fixes: 1056691b2680 ("selftests: fib_tests: Make test results more verbose") Signed-off-by: Roxana Nicolescu Link: https://lore.kernel.org/r/20230220110400.26737-2-roxana.nicolescu@canonical.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- tools/testing/selftests/net/fib_tests.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 0f3bf90e04d3..8f42e17db5d0 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1773,6 +1773,8 @@ EOF ################################################################################ # main +trap cleanup EXIT + while getopts :t:pPhv o do case $o in From 8f06907f9f5814cf14c9fd8b0e4e616fd29b2b26 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 20 Feb 2023 14:23:36 +0100 Subject: [PATCH 1646/4345] sefltests: netdevsim: wait for devlink instance after netns removal [ Upstream commit f922c7b1c1c45740d329bf248936fdb78c0cff6e ] When devlink instance is put into network namespace and that network namespace gets deleted, devlink instance is moved back into init_ns. This is done as a part of cleanup_net() routine. Since cleanup_net() is called asynchronously from workqueue, there is no guarantee that the devlink instance move is done after "ip netns del" returns. So fix this race by making sure that the devlink instance is present before any other operation. Reported-by: Amir Tzin Fixes: b74c37fd35a2 ("selftests: netdevsim: add tests for devlink reload with resources") Signed-off-by: Jiri Pirko Reviewed-by: Pavan Chebbi Link: https://lore.kernel.org/r/20230220132336.198597-1-jiri@resnulli.us Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- .../selftests/drivers/net/netdevsim/devlink.sh | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index 16d2de18591d..2c81e01c30b3 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -16,6 +16,18 @@ SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV_NAME/net/ DEBUGFS_DIR=/sys/kernel/debug/netdevsim/$DEV_NAME/ DL_HANDLE=netdevsim/$DEV_NAME +wait_for_devlink() +{ + "$@" | grep -q $DL_HANDLE +} + +devlink_wait() +{ + local timeout=$1 + + busywait "$timeout" wait_for_devlink devlink dev +} + fw_flash_test() { RET=0 @@ -255,6 +267,9 @@ netns_reload_test() ip netns del testns2 ip netns del testns1 + # Wait until netns async cleanup is done. + devlink_wait 2000 + log_test "netns reload test" } @@ -347,6 +362,9 @@ resource_test() ip netns del testns2 ip netns del testns1 + # Wait until netns async cleanup is done. + devlink_wait 2000 + log_test "resource test" } From 5ae70041a6d7de62a0cdb2bbcfe0c9cf753035d0 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Fri, 18 Nov 2022 10:16:51 +0800 Subject: [PATCH 1647/4345] drm: Fix potential null-ptr-deref due to drmm_mode_config_init() [ Upstream commit 834c23e4f798dcdc8af251b3c428ceef94741991 ] drmm_mode_config_init() will call drm_mode_create_standard_properties() and won't check the ret value. When drm_mode_create_standard_properties() failed due to alloc, property will be a NULL pointer and may causes the null-ptr-deref. Fix the null-ptr-deref by adding the ret value check. Found null-ptr-deref while testing insert module bochs: general protection fault, probably for non-canonical address 0xdffffc000000000c: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000060-0x0000000000000067] CPU: 3 PID: 249 Comm: modprobe Not tainted 6.1.0-rc1+ #364 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 RIP: 0010:drm_object_attach_property+0x73/0x3c0 [drm] Call Trace: __drm_connector_init+0xb6c/0x1100 [drm] bochs_pci_probe.cold.11+0x4cb/0x7fe [bochs] pci_device_probe+0x17d/0x340 really_probe+0x1db/0x5d0 __driver_probe_device+0x1e7/0x250 driver_probe_device+0x4a/0x120 __driver_attach+0xcd/0x2c0 bus_for_each_dev+0x11a/0x1b0 bus_add_driver+0x3d7/0x500 driver_register+0x18e/0x320 do_one_initcall+0xc4/0x3e0 do_init_module+0x1b4/0x630 load_module+0x5dca/0x7230 __do_sys_finit_module+0x100/0x170 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7ff65af9f839 Fixes: 6b4959f43a04 ("drm/atomic: atomic plane properties") Signed-off-by: Shang XiaoJing Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20221118021651.2460-1-shangxiaojing@huawei.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_mode_config.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c index f1affc1bb679..fad2c1181127 100644 --- a/drivers/gpu/drm/drm_mode_config.c +++ b/drivers/gpu/drm/drm_mode_config.c @@ -398,6 +398,8 @@ static void drm_mode_config_init_release(struct drm_device *dev, void *ptr) */ int drmm_mode_config_init(struct drm_device *dev) { + int ret; + mutex_init(&dev->mode_config.mutex); drm_modeset_lock_init(&dev->mode_config.connection_mutex); mutex_init(&dev->mode_config.idr_mutex); @@ -419,7 +421,11 @@ int drmm_mode_config_init(struct drm_device *dev) init_llist_head(&dev->mode_config.connector_free_list); INIT_WORK(&dev->mode_config.connector_free_work, drm_connector_free_work_fn); - drm_mode_create_standard_properties(dev); + ret = drm_mode_create_standard_properties(dev); + if (ret) { + drm_mode_config_cleanup(dev); + return ret; + } /* Just to be sure */ dev->mode_config.num_fb = 0; From a86bd12bd974c20d0f045ac601f96ab0e8db0410 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 23 Nov 2022 17:43:10 +0100 Subject: [PATCH 1648/4345] drm/fourcc: Add missing big-endian XRGB1555 and RGB565 formats [ Upstream commit 6fb6c979ca628583d4d0c59a0f8ff977e581ecc0 ] As of commit eae06120f1974e1a ("drm: refuse ADDFB2 ioctl for broken bigendian drivers"), drivers must set the quirk_addfb_prefer_host_byte_order quirk to make the drm_mode_addfb() compat code work correctly on big-endian machines. While that works fine for big-endian XRGB8888 and ARGB8888, which are mapped to the existing little-endian BGRX8888 and BGRA8888 formats, it does not work for big-endian XRGB1555 and RGB565, as the latter are not listed in the format database. Fix this by adding the missing formats. Limit this to big-endian platforms, as there is currently no need to support these formats on little-endian platforms. Fixes: 6960e6da9cec3f66 ("drm: fix drm_mode_addfb() on big endian machines.") Signed-off-by: Geert Uytterhoeven Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/3ee1f8144feb96c28742b22384189f1f83bcfc1a.1669221671.git.geert@linux-m68k.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_fourcc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index 92152c06b75b..8d1064061e83 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -178,6 +178,10 @@ const struct drm_format_info *__drm_format_info(u32 format) { .format = DRM_FORMAT_BGRA5551, .depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true }, { .format = DRM_FORMAT_RGB565, .depth = 16, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_BGR565, .depth = 16, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, +#ifdef __BIG_ENDIAN + { .format = DRM_FORMAT_XRGB1555 | DRM_FORMAT_BIG_ENDIAN, .depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, + { .format = DRM_FORMAT_RGB565 | DRM_FORMAT_BIG_ENDIAN, .depth = 16, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, +#endif { .format = DRM_FORMAT_RGB888, .depth = 24, .num_planes = 1, .cpp = { 3, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_BGR888, .depth = 24, .num_planes = 1, .cpp = { 3, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 }, From 181fb5efb64974709ac3b9ebc0c8278ccc96a3d0 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 21 Nov 2022 16:59:55 +0100 Subject: [PATCH 1649/4345] drm: mxsfb: DRM_MXSFB should depend on ARCH_MXS || ARCH_MXC [ Upstream commit 7783cc67862f9166c901bfa0f80b717aa8d354dd ] Freescale/NXP i.MX LCDIF and eLCDIF LCD controllers are only present on Freescale/NXP i.MX SoCs. Hence add a dependency on ARCH_MXS || ARCH_MXC, to prevent asking the user about this driver when configuring a kernel without Freescale/NXP i.MX support. Fixes: 45d59d704080cc0c ("drm: Add new driver for MXSFB controller") Signed-off-by: Geert Uytterhoeven Reviewed-by: Marek Vasut Signed-off-by: Marek Vasut Link: https://patchwork.freedesktop.org/patch/msgid/98e74779ca2bc575d91afff03369e86b080c01ac.1669046358.git.geert+renesas@glider.be Signed-off-by: Sasha Levin --- drivers/gpu/drm/mxsfb/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/mxsfb/Kconfig b/drivers/gpu/drm/mxsfb/Kconfig index ee22cd25d3e3..e7201e16119a 100644 --- a/drivers/gpu/drm/mxsfb/Kconfig +++ b/drivers/gpu/drm/mxsfb/Kconfig @@ -8,6 +8,7 @@ config DRM_MXSFB tristate "i.MX (e)LCDIF LCD controller" depends on DRM && OF depends on COMMON_CLK + depends on ARCH_MXS || ARCH_MXC || COMPILE_TEST select DRM_MXS select DRM_KMS_HELPER select DRM_KMS_CMA_HELPER From 5b9bcb33cf3ffa60c520c02b33a364cb64d7e7df Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Tue, 8 Nov 2022 09:12:26 +0000 Subject: [PATCH 1650/4345] drm/bridge: megachips: Fix error handling in i2c_register_driver() [ Upstream commit 4ecff954c370b82bce45bdca2846c5c5563e8a8a ] A problem about insmod megachips-stdpxxxx-ge-b850v3-fw.ko failed is triggered with the following log given: [ 4497.981497] Error: Driver 'stdp4028-ge-b850v3-fw' is already registered, aborting... insmod: ERROR: could not insert module megachips-stdpxxxx-ge-b850v3-fw.ko: Device or resource busy The reason is that stdpxxxx_ge_b850v3_init() returns i2c_add_driver() directly without checking its return value, if i2c_add_driver() failed, it returns without calling i2c_del_driver() on the previous i2c driver, resulting the megachips-stdpxxxx-ge-b850v3-fw can never be installed later. A simple call graph is shown as below: stdpxxxx_ge_b850v3_init() i2c_add_driver(&stdp4028_ge_b850v3_fw_driver) i2c_add_driver(&stdp2690_ge_b850v3_fw_driver) i2c_register_driver() driver_register() bus_add_driver() priv = kzalloc(...) # OOM happened # return without delete stdp4028_ge_b850v3_fw_driver Fix by calling i2c_del_driver() on stdp4028_ge_b850v3_fw_driver when i2c_add_driver() returns error. Fixes: fcfa0ddc18ed ("drm/bridge: Drivers for megachips-stdpxxxx-ge-b850v3-fw (LVDS-DP++)") Signed-off-by: Yuan Can Reviewed-by: Andrzej Hajda Tested-by: Ian Ray Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20221108091226.114524-1-yuancan@huawei.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c index 72248a565579..e41afcc5326b 100644 --- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c +++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c @@ -444,7 +444,11 @@ static int __init stdpxxxx_ge_b850v3_init(void) if (ret) return ret; - return i2c_add_driver(&stdp2690_ge_b850v3_fw_driver); + ret = i2c_add_driver(&stdp2690_ge_b850v3_fw_driver); + if (ret) + i2c_del_driver(&stdp4028_ge_b850v3_fw_driver); + + return ret; } module_init(stdpxxxx_ge_b850v3_init); From 0b8f390e2251191f1b179cc87f65d54c96565f0d Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Tue, 1 Nov 2022 06:51:56 +0000 Subject: [PATCH 1651/4345] drm/vkms: Fix null-ptr-deref in vkms_release() [ Upstream commit 2fe2a8f40c21161ffe7653cc234e7934db5b7cc5 ] A null-ptr-deref is triggered when it tries to destroy the workqueue in vkms->output.composer_workq in vkms_release(). KASAN: null-ptr-deref in range [0x0000000000000118-0x000000000000011f] CPU: 5 PID: 17193 Comm: modprobe Not tainted 6.0.0-11331-gd465bff130bf #24 RIP: 0010:destroy_workqueue+0x2f/0x710 ... Call Trace: ? vkms_config_debugfs_init+0x50/0x50 [vkms] __devm_drm_dev_alloc+0x15a/0x1c0 [drm] vkms_init+0x245/0x1000 [vkms] do_one_initcall+0xd0/0x4f0 do_init_module+0x1a4/0x680 load_module+0x6249/0x7110 __do_sys_finit_module+0x140/0x200 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 The reason is that an OOM happened which triggers the destroy of the workqueue, however, the workqueue is alloced in the later process, thus a null-ptr-deref happened. A simple call graph is shown as below: vkms_init() vkms_create() devm_drm_dev_alloc() __devm_drm_dev_alloc() devm_drm_dev_init() devm_add_action_or_reset() devm_add_action() # an error happened devm_drm_dev_init_release() drm_dev_put() kref_put() drm_dev_release() vkms_release() destroy_workqueue() # null-ptr-deref happened vkms_modeset_init() vkms_output_init() vkms_crtc_init() # where the workqueue get allocated Fix this by checking if composer_workq is NULL before passing it to the destroy_workqueue() in vkms_release(). Fixes: 6c234fe37c57 ("drm/vkms: Implement CRC debugfs API") Signed-off-by: Yuan Can Reviewed-by: Melissa Wen Signed-off-by: Melissa Wen Link: https://patchwork.freedesktop.org/patch/msgid/20221101065156.41584-3-yuancan@huawei.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/vkms/vkms_drv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index cb0b6230c22c..838428988f79 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -61,7 +61,8 @@ static void vkms_release(struct drm_device *dev) { struct vkms_device *vkms = container_of(dev, struct vkms_device, drm); - destroy_workqueue(vkms->output.composer_workq); + if (vkms->output.composer_workq) + destroy_workqueue(vkms->output.composer_workq); } static void vkms_atomic_commit_tail(struct drm_atomic_state *old_state) From 09c6e21d6a1eaacac54a5d1ea7202e8383a886e6 Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Mon, 13 Jun 2022 16:47:36 +0200 Subject: [PATCH 1652/4345] drm/vc4: dpi: Add option for inverting pixel clock and output enable [ Upstream commit 3c2707632146b22e97b0fbf6778bab8add2eaa1d ] DRM provides flags for inverting pixel clock and output enable signals, but these were not mapped to the relevant registers. Add those mappings. Signed-off-by: Dave Stevenson Link: https://lore.kernel.org/r/20220613144800.326124-10-maxime@cerno.tech Signed-off-by: Maxime Ripard Stable-dep-of: 0870d86eac8a ("drm/vc4: dpi: Fix format mapping for RGB565") Signed-off-by: Sasha Levin --- drivers/gpu/drm/vc4/vc4_dpi.c | 64 ++++++++++++++++++++--------------- 1 file changed, 37 insertions(+), 27 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_dpi.c b/drivers/gpu/drm/vc4/vc4_dpi.c index a90f2545baee..0e25add2df07 100644 --- a/drivers/gpu/drm/vc4/vc4_dpi.c +++ b/drivers/gpu/drm/vc4/vc4_dpi.c @@ -148,35 +148,45 @@ static void vc4_dpi_encoder_enable(struct drm_encoder *encoder) } drm_connector_list_iter_end(&conn_iter); - if (connector && connector->display_info.num_bus_formats) { - u32 bus_format = connector->display_info.bus_formats[0]; + if (connector) { + if (connector->display_info.num_bus_formats) { + u32 bus_format = connector->display_info.bus_formats[0]; - switch (bus_format) { - case MEDIA_BUS_FMT_RGB888_1X24: - dpi_c |= VC4_SET_FIELD(DPI_FORMAT_24BIT_888_RGB, - DPI_FORMAT); - break; - case MEDIA_BUS_FMT_BGR888_1X24: - dpi_c |= VC4_SET_FIELD(DPI_FORMAT_24BIT_888_RGB, - DPI_FORMAT); - dpi_c |= VC4_SET_FIELD(DPI_ORDER_BGR, DPI_ORDER); - break; - case MEDIA_BUS_FMT_RGB666_1X24_CPADHI: - dpi_c |= VC4_SET_FIELD(DPI_FORMAT_18BIT_666_RGB_2, - DPI_FORMAT); - break; - case MEDIA_BUS_FMT_RGB666_1X18: - dpi_c |= VC4_SET_FIELD(DPI_FORMAT_18BIT_666_RGB_1, - DPI_FORMAT); - break; - case MEDIA_BUS_FMT_RGB565_1X16: - dpi_c |= VC4_SET_FIELD(DPI_FORMAT_16BIT_565_RGB_3, - DPI_FORMAT); - break; - default: - DRM_ERROR("Unknown media bus format %d\n", bus_format); - break; + switch (bus_format) { + case MEDIA_BUS_FMT_RGB888_1X24: + dpi_c |= VC4_SET_FIELD(DPI_FORMAT_24BIT_888_RGB, + DPI_FORMAT); + break; + case MEDIA_BUS_FMT_BGR888_1X24: + dpi_c |= VC4_SET_FIELD(DPI_FORMAT_24BIT_888_RGB, + DPI_FORMAT); + dpi_c |= VC4_SET_FIELD(DPI_ORDER_BGR, + DPI_ORDER); + break; + case MEDIA_BUS_FMT_RGB666_1X24_CPADHI: + dpi_c |= VC4_SET_FIELD(DPI_FORMAT_18BIT_666_RGB_2, + DPI_FORMAT); + break; + case MEDIA_BUS_FMT_RGB666_1X18: + dpi_c |= VC4_SET_FIELD(DPI_FORMAT_18BIT_666_RGB_1, + DPI_FORMAT); + break; + case MEDIA_BUS_FMT_RGB565_1X16: + dpi_c |= VC4_SET_FIELD(DPI_FORMAT_16BIT_565_RGB_3, + DPI_FORMAT); + break; + default: + DRM_ERROR("Unknown media bus format %d\n", + bus_format); + break; + } } + + if (connector->display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE) + dpi_c |= DPI_PIXEL_CLK_INVERT; + + if (connector->display_info.bus_flags & DRM_BUS_FLAG_DE_LOW) + dpi_c |= DPI_OUTPUT_ENABLE_INVERT; } else { /* Default to 24bit if no connector found. */ dpi_c |= VC4_SET_FIELD(DPI_FORMAT_24BIT_888_RGB, DPI_FORMAT); From 2adbcf94ebfcd183223d434227d55b9841458bf0 Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Thu, 1 Dec 2022 09:42:52 +0100 Subject: [PATCH 1653/4345] drm/vc4: dpi: Fix format mapping for RGB565 [ Upstream commit 0870d86eac8a9abd89a0be1b719d5dc5bac936f0 ] The mapping is incorrect for RGB565_1X16 as it should be DPI_FORMAT_18BIT_666_RGB_1 instead of DPI_FORMAT_18BIT_666_RGB_3. Fixes: 08302c35b59d ("drm/vc4: Add DPI driver") Signed-off-by: Dave Stevenson Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20221013-rpi-dpi-improvements-v3-7-eb76e26a772d@cerno.tech Signed-off-by: Maxime Ripard Signed-off-by: Sasha Levin --- drivers/gpu/drm/vc4/vc4_dpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vc4/vc4_dpi.c b/drivers/gpu/drm/vc4/vc4_dpi.c index 0e25add2df07..9c8a71d7426a 100644 --- a/drivers/gpu/drm/vc4/vc4_dpi.c +++ b/drivers/gpu/drm/vc4/vc4_dpi.c @@ -172,7 +172,7 @@ static void vc4_dpi_encoder_enable(struct drm_encoder *encoder) DPI_FORMAT); break; case MEDIA_BUS_FMT_RGB565_1X16: - dpi_c |= VC4_SET_FIELD(DPI_FORMAT_16BIT_565_RGB_3, + dpi_c |= VC4_SET_FIELD(DPI_FORMAT_16BIT_565_RGB_1, DPI_FORMAT); break; default: From fdcacfd11015cd46aaad2d7a6be0b10ebe247102 Mon Sep 17 00:00:00 2001 From: Randolph Sapp Date: Thu, 1 Dec 2022 18:18:03 -0600 Subject: [PATCH 1654/4345] drm: tidss: Fix pixel format definition [ Upstream commit 2df0433b18f2735a49d2c3a968b40fa2881137c0 ] There was a long-standing bug from a typo that created 2 ARGB1555 and ABGR1555 pixel format entries. Weston 10 has a sanity check that alerted me to this issue. According to the Supported Pixel Data formats table we have the later entries should have been for Alpha-X instead. Signed-off-by: Randolph Sapp Fixes: 32a1795f57eecc ("drm/tidss: New driver for TI Keystone platform Display SubSystem") Reviewed-by: Aradhya Bhatia Acked-by: Andrew Davis Signed-off-by: Tomi Valkeinen Link: https://patchwork.freedesktop.org/patch/msgid/20221202001803.1765805-1-rs@ti.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/tidss/tidss_dispc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/tidss/tidss_dispc.c b/drivers/gpu/drm/tidss/tidss_dispc.c index b669168ae7cb..33716213a821 100644 --- a/drivers/gpu/drm/tidss/tidss_dispc.c +++ b/drivers/gpu/drm/tidss/tidss_dispc.c @@ -1855,8 +1855,8 @@ static const struct { { DRM_FORMAT_XBGR4444, 0x21, }, { DRM_FORMAT_RGBX4444, 0x22, }, - { DRM_FORMAT_ARGB1555, 0x25, }, - { DRM_FORMAT_ABGR1555, 0x26, }, + { DRM_FORMAT_XRGB1555, 0x25, }, + { DRM_FORMAT_XBGR1555, 0x26, }, { DRM_FORMAT_XRGB8888, 0x27, }, { DRM_FORMAT_XBGR8888, 0x28, }, From 8eb74bd9c9726425fe62330a2eda4d862edb6dd1 Mon Sep 17 00:00:00 2001 From: Liang He Date: Wed, 20 Jul 2022 23:22:27 +0800 Subject: [PATCH 1655/4345] gpu: ipu-v3: common: Add of_node_put() for reference returned by of_graph_get_port_by_id() [ Upstream commit 9afdf98cfdfa2ba8ec068cf08c5fcdc1ed8daf3f ] In ipu_add_client_devices(), we need to call of_node_put() for reference returned by of_graph_get_port_by_id() in fail path. Fixes: 17e052175039 ("gpu: ipu-v3: Do not bail out on missing optional port nodes") Signed-off-by: Liang He Reviewed-by: Philipp Zabel Link: https://lore.kernel.org/r/20220720152227.1288413-1-windhl@126.com Signed-off-by: Philipp Zabel Link: https://patchwork.freedesktop.org/patch/msgid/20220720152227.1288413-1-windhl@126.com Signed-off-by: Sasha Levin --- drivers/gpu/ipu-v3/ipu-common.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index d166ee262ce4..22dae3f51051 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -1168,6 +1168,7 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) pdev = platform_device_alloc(reg->name, id++); if (!pdev) { ret = -ENOMEM; + of_node_put(of_node); goto err_register; } From 1bab31a0969ca4ac90907a5d3b44af104229eafd Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Fri, 6 Jan 2023 10:30:11 +0800 Subject: [PATCH 1656/4345] drm/msm/hdmi: Add missing check for alloc_ordered_workqueue [ Upstream commit afe4cb96153a0d8003e4e4ebd91b5c543e10df84 ] Add check for the return value of alloc_ordered_workqueue as it may return NULL pointer and cause NULL pointer dereference in `hdmi_hdcp.c` and `hdmi_hpd.c`. Fixes: c6a57a50ad56 ("drm/msm/hdmi: add hdmi hdcp support (V3)") Signed-off-by: Jiasheng Jiang Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/517211/ Link: https://lore.kernel.org/r/20230106023011.3985-1-jiasheng@iscas.ac.cn Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/hdmi/hdmi.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index efb14043a6ec..bee208773bee 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -264,6 +264,10 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); hdmi->workq = alloc_ordered_workqueue("msm_hdmi", 0); + if (!hdmi->workq) { + ret = -ENOMEM; + goto fail; + } hdmi->i2c = msm_hdmi_i2c_init(hdmi); if (IS_ERR(hdmi->i2c)) { From 86704e50ffb589f81af74b6a9c48d9629fb89bfc Mon Sep 17 00:00:00 2001 From: Adam Skladowski Date: Sat, 31 Dec 2022 17:42:50 +0100 Subject: [PATCH 1657/4345] pinctrl: qcom: pinctrl-msm8976: Correct function names for wcss pins [ Upstream commit a7cc0e2685082a0d79baec02df184dfa83cbfac3 ] Adjust names of function for wcss pins, also fix third gpio in bt group. Fixes: bcd11493f0ab ("pinctrl: qcom: Add a pinctrl driver for MSM8976 and 8956") Signed-off-by: Adam Skladowski Reviewed-by: Marijn Suijten Link: https://lore.kernel.org/r/20221231164250.74550-1-a39.skl@gmail.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/qcom/pinctrl-msm8976.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-msm8976.c b/drivers/pinctrl/qcom/pinctrl-msm8976.c index ec43edf9b660..e11d84584719 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm8976.c +++ b/drivers/pinctrl/qcom/pinctrl-msm8976.c @@ -733,7 +733,7 @@ static const char * const codec_int2_groups[] = { "gpio74", }; static const char * const wcss_bt_groups[] = { - "gpio39", "gpio47", "gpio88", + "gpio39", "gpio47", "gpio48", }; static const char * const sdc3_groups[] = { "gpio39", "gpio40", "gpio41", @@ -958,9 +958,9 @@ static const struct msm_pingroup msm8976_groups[] = { PINGROUP(37, NA, NA, NA, qdss_tracedata_b, NA, NA, NA, NA, NA), PINGROUP(38, NA, NA, NA, NA, NA, NA, NA, qdss_tracedata_b, NA), PINGROUP(39, wcss_bt, sdc3, NA, qdss_tracedata_a, NA, NA, NA, NA, NA), - PINGROUP(40, wcss_wlan, sdc3, NA, qdss_tracedata_a, NA, NA, NA, NA, NA), - PINGROUP(41, wcss_wlan, sdc3, NA, qdss_tracedata_a, NA, NA, NA, NA, NA), - PINGROUP(42, wcss_wlan, sdc3, NA, qdss_tracedata_a, NA, NA, NA, NA, NA), + PINGROUP(40, wcss_wlan2, sdc3, NA, qdss_tracedata_a, NA, NA, NA, NA, NA), + PINGROUP(41, wcss_wlan1, sdc3, NA, qdss_tracedata_a, NA, NA, NA, NA, NA), + PINGROUP(42, wcss_wlan0, sdc3, NA, qdss_tracedata_a, NA, NA, NA, NA, NA), PINGROUP(43, wcss_wlan, sdc3, NA, NA, qdss_tracedata_a, NA, NA, NA, NA), PINGROUP(44, wcss_wlan, sdc3, NA, NA, NA, NA, NA, NA, NA), PINGROUP(45, wcss_fm, NA, qdss_tracectl_a, NA, NA, NA, NA, NA, NA), From 8ab860dd8717a7e4a143988885fea0d7e5a9412e Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 2 Jan 2023 12:24:56 +0400 Subject: [PATCH 1658/4345] pinctrl: stm32: Fix refcount leak in stm32_pctrl_get_irq_domain [ Upstream commit dcef18c8ac40aa85bb339f64c1dd31dd458b06fb ] of_irq_find_parent() returns a node pointer with refcount incremented, We should use of_node_put() on it when not needed anymore. Add missing of_node_put() to avoid refcount leak. Fixes: d86f4d71e42a ("pinctrl: stm32: check irq controller availability at probe") Signed-off-by: Miaoqian Lin Link: https://lore.kernel.org/r/20230102082503.3944927-1-linmq006@gmail.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/stm32/pinctrl-stm32.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index 60406f1f8337..2d852f15cc50 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -1338,6 +1338,7 @@ static struct irq_domain *stm32_pctrl_get_irq_domain(struct device_node *np) return ERR_PTR(-ENXIO); domain = irq_find_host(parent); + of_node_put(parent); if (!domain) /* domain not registered yet */ return ERR_PTR(-EPROBE_DEFER); From 6da121152ada3f158dcab9430ada8291eb39c2bc Mon Sep 17 00:00:00 2001 From: Jianqun Xu Date: Fri, 19 Mar 2021 16:14:41 +0800 Subject: [PATCH 1659/4345] pinctrl: rockchip: add support for rk3568 [ Upstream commit c0dadc0e47a895e95c17a4df1fa12737e1d57d6f ] RK3568 SoCs have 5 gpio controllers, each gpio has 32 pins. GPIO supports set iomux, pull, drive strength and schmitt. Signed-off-by: Jianqun Xu Link: https://lore.kernel.org/r/20210319081441.368358-1-jay.xu@rock-chips.com Signed-off-by: Linus Walleij Stable-dep-of: c818ae563bf9 ("pinctrl: rockchip: Fix refcount leak in rockchip_pinctrl_parse_groups") Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-rockchip.c | 292 ++++++++++++++++++++++++++++- 1 file changed, 290 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 07b1204174bf..38ea70f49cb0 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -61,8 +61,17 @@ enum rockchip_pinctrl_type { RK3308, RK3368, RK3399, + RK3568, }; + +/** + * Generate a bitmask for setting a value (v) with a write mask bit in hiword + * register 31:16 area. + */ +#define WRITE_MASK_VAL(h, l, v) \ + (GENMASK(((h) + 16), ((l) + 16)) | (((v) << (l)) & GENMASK((h), (l)))) + /* * Encode variants of iomux registers into a type variable */ @@ -290,6 +299,25 @@ struct rockchip_pin_bank { .pull_type[3] = pull3, \ } +#define PIN_BANK_MUX_ROUTE_FLAGS(ID, PIN, FUNC, REG, VAL, FLAG) \ + { \ + .bank_num = ID, \ + .pin = PIN, \ + .func = FUNC, \ + .route_offset = REG, \ + .route_val = VAL, \ + .route_location = FLAG, \ + } + +#define RK_MUXROUTE_SAME(ID, PIN, FUNC, REG, VAL) \ + PIN_BANK_MUX_ROUTE_FLAGS(ID, PIN, FUNC, REG, VAL, ROCKCHIP_ROUTE_SAME) + +#define RK_MUXROUTE_GRF(ID, PIN, FUNC, REG, VAL) \ + PIN_BANK_MUX_ROUTE_FLAGS(ID, PIN, FUNC, REG, VAL, ROCKCHIP_ROUTE_GRF) + +#define RK_MUXROUTE_PMU(ID, PIN, FUNC, REG, VAL) \ + PIN_BANK_MUX_ROUTE_FLAGS(ID, PIN, FUNC, REG, VAL, ROCKCHIP_ROUTE_PMU) + /** * struct rockchip_mux_recalced_data: represent a pin iomux data. * @num: bank number. @@ -1409,6 +1437,102 @@ static struct rockchip_mux_route_data rk3399_mux_route_data[] = { }, }; +static struct rockchip_mux_route_data rk3568_mux_route_data[] = { + RK_MUXROUTE_PMU(0, RK_PB7, 1, 0x0110, WRITE_MASK_VAL(1, 0, 0)), /* PWM0 IO mux M0 */ + RK_MUXROUTE_PMU(0, RK_PC7, 2, 0x0110, WRITE_MASK_VAL(1, 0, 1)), /* PWM0 IO mux M1 */ + RK_MUXROUTE_PMU(0, RK_PC0, 1, 0x0110, WRITE_MASK_VAL(3, 2, 0)), /* PWM1 IO mux M0 */ + RK_MUXROUTE_PMU(0, RK_PB5, 4, 0x0110, WRITE_MASK_VAL(3, 2, 1)), /* PWM1 IO mux M1 */ + RK_MUXROUTE_PMU(0, RK_PC1, 1, 0x0110, WRITE_MASK_VAL(5, 4, 0)), /* PWM2 IO mux M0 */ + RK_MUXROUTE_PMU(0, RK_PB6, 4, 0x0110, WRITE_MASK_VAL(5, 4, 1)), /* PWM2 IO mux M1 */ + RK_MUXROUTE_PMU(0, RK_PB3, 2, 0x0300, WRITE_MASK_VAL(0, 0, 0)), /* CAN0 IO mux M0 */ + RK_MUXROUTE_GRF(2, RK_PA1, 4, 0x0300, WRITE_MASK_VAL(0, 0, 1)), /* CAN0 IO mux M1 */ + RK_MUXROUTE_GRF(1, RK_PA1, 3, 0x0300, WRITE_MASK_VAL(2, 2, 0)), /* CAN1 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PC3, 3, 0x0300, WRITE_MASK_VAL(2, 2, 1)), /* CAN1 IO mux M1 */ + RK_MUXROUTE_GRF(4, RK_PB5, 3, 0x0300, WRITE_MASK_VAL(4, 4, 0)), /* CAN2 IO mux M0 */ + RK_MUXROUTE_GRF(2, RK_PB2, 4, 0x0300, WRITE_MASK_VAL(4, 4, 1)), /* CAN2 IO mux M1 */ + RK_MUXROUTE_GRF(4, RK_PC4, 1, 0x0300, WRITE_MASK_VAL(6, 6, 0)), /* HPDIN IO mux M0 */ + RK_MUXROUTE_PMU(0, RK_PC2, 2, 0x0300, WRITE_MASK_VAL(6, 6, 1)), /* HPDIN IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PB1, 3, 0x0300, WRITE_MASK_VAL(8, 8, 0)), /* GMAC1 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PA7, 3, 0x0300, WRITE_MASK_VAL(8, 8, 1)), /* GMAC1 IO mux M1 */ + RK_MUXROUTE_GRF(4, RK_PD1, 1, 0x0300, WRITE_MASK_VAL(10, 10, 0)), /* HDMITX IO mux M0 */ + RK_MUXROUTE_PMU(0, RK_PC7, 1, 0x0300, WRITE_MASK_VAL(10, 10, 1)), /* HDMITX IO mux M1 */ + RK_MUXROUTE_PMU(0, RK_PB6, 1, 0x0300, WRITE_MASK_VAL(14, 14, 0)), /* I2C2 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PB4, 1, 0x0300, WRITE_MASK_VAL(14, 14, 1)), /* I2C2 IO mux M1 */ + RK_MUXROUTE_GRF(1, RK_PA0, 1, 0x0304, WRITE_MASK_VAL(0, 0, 0)), /* I2C3 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PB6, 4, 0x0304, WRITE_MASK_VAL(0, 0, 1)), /* I2C3 IO mux M1 */ + RK_MUXROUTE_GRF(4, RK_PB2, 1, 0x0304, WRITE_MASK_VAL(2, 2, 0)), /* I2C4 IO mux M0 */ + RK_MUXROUTE_GRF(2, RK_PB1, 2, 0x0304, WRITE_MASK_VAL(2, 2, 1)), /* I2C4 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PB4, 4, 0x0304, WRITE_MASK_VAL(4, 4, 0)), /* I2C5 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PD0, 2, 0x0304, WRITE_MASK_VAL(4, 4, 1)), /* I2C5 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PB1, 5, 0x0304, WRITE_MASK_VAL(14, 14, 0)), /* PWM8 IO mux M0 */ + RK_MUXROUTE_GRF(1, RK_PD5, 4, 0x0304, WRITE_MASK_VAL(14, 14, 1)), /* PWM8 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PB2, 5, 0x0308, WRITE_MASK_VAL(0, 0, 0)), /* PWM9 IO mux M0 */ + RK_MUXROUTE_GRF(1, RK_PD6, 4, 0x0308, WRITE_MASK_VAL(0, 0, 1)), /* PWM9 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PB5, 5, 0x0308, WRITE_MASK_VAL(2, 2, 0)), /* PWM10 IO mux M0 */ + RK_MUXROUTE_GRF(2, RK_PA1, 2, 0x0308, WRITE_MASK_VAL(2, 2, 1)), /* PWM10 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PB6, 5, 0x0308, WRITE_MASK_VAL(4, 4, 0)), /* PWM11 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PC0, 3, 0x0308, WRITE_MASK_VAL(4, 4, 1)), /* PWM11 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PB7, 2, 0x0308, WRITE_MASK_VAL(6, 6, 0)), /* PWM12 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PC5, 1, 0x0308, WRITE_MASK_VAL(6, 6, 1)), /* PWM12 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PC0, 2, 0x0308, WRITE_MASK_VAL(8, 8, 0)), /* PWM13 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PC6, 1, 0x0308, WRITE_MASK_VAL(8, 8, 1)), /* PWM13 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PC4, 1, 0x0308, WRITE_MASK_VAL(10, 10, 0)), /* PWM14 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PC2, 1, 0x0308, WRITE_MASK_VAL(10, 10, 1)), /* PWM14 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PC5, 1, 0x0308, WRITE_MASK_VAL(12, 12, 0)), /* PWM15 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PC3, 1, 0x0308, WRITE_MASK_VAL(12, 12, 1)), /* PWM15 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PD2, 3, 0x0308, WRITE_MASK_VAL(14, 14, 0)), /* SDMMC2 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PA5, 5, 0x0308, WRITE_MASK_VAL(14, 14, 1)), /* SDMMC2 IO mux M1 */ + RK_MUXROUTE_PMU(0, RK_PB5, 2, 0x030c, WRITE_MASK_VAL(0, 0, 0)), /* SPI0 IO mux M0 */ + RK_MUXROUTE_GRF(2, RK_PD3, 3, 0x030c, WRITE_MASK_VAL(0, 0, 1)), /* SPI0 IO mux M1 */ + RK_MUXROUTE_GRF(2, RK_PB5, 3, 0x030c, WRITE_MASK_VAL(2, 2, 0)), /* SPI1 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PC3, 3, 0x030c, WRITE_MASK_VAL(2, 2, 1)), /* SPI1 IO mux M1 */ + RK_MUXROUTE_GRF(2, RK_PC1, 4, 0x030c, WRITE_MASK_VAL(4, 4, 0)), /* SPI2 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PA0, 3, 0x030c, WRITE_MASK_VAL(4, 4, 1)), /* SPI2 IO mux M1 */ + RK_MUXROUTE_GRF(4, RK_PB3, 4, 0x030c, WRITE_MASK_VAL(6, 6, 0)), /* SPI3 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PC2, 2, 0x030c, WRITE_MASK_VAL(6, 6, 1)), /* SPI3 IO mux M1 */ + RK_MUXROUTE_GRF(2, RK_PB4, 2, 0x030c, WRITE_MASK_VAL(8, 8, 0)), /* UART1 IO mux M0 */ + RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(8, 8, 1)), /* UART1 IO mux M1 */ + RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(10, 10, 0)), /* UART2 IO mux M0 */ + RK_MUXROUTE_GRF(1, RK_PD5, 2, 0x030c, WRITE_MASK_VAL(10, 10, 1)), /* UART2 IO mux M1 */ + RK_MUXROUTE_GRF(1, RK_PA1, 2, 0x030c, WRITE_MASK_VAL(12, 12, 0)), /* UART3 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PB7, 4, 0x030c, WRITE_MASK_VAL(12, 12, 1)), /* UART3 IO mux M1 */ + RK_MUXROUTE_GRF(1, RK_PA6, 2, 0x030c, WRITE_MASK_VAL(14, 14, 0)), /* UART4 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PB2, 4, 0x030c, WRITE_MASK_VAL(14, 14, 1)), /* UART4 IO mux M1 */ + RK_MUXROUTE_GRF(2, RK_PA2, 3, 0x0310, WRITE_MASK_VAL(0, 0, 0)), /* UART5 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PC2, 4, 0x0310, WRITE_MASK_VAL(0, 0, 1)), /* UART5 IO mux M1 */ + RK_MUXROUTE_GRF(2, RK_PA4, 3, 0x0310, WRITE_MASK_VAL(2, 2, 0)), /* UART6 IO mux M0 */ + RK_MUXROUTE_GRF(1, RK_PD5, 3, 0x0310, WRITE_MASK_VAL(2, 2, 1)), /* UART6 IO mux M1 */ + RK_MUXROUTE_GRF(2, RK_PA6, 3, 0x0310, WRITE_MASK_VAL(5, 4, 0)), /* UART7 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PC4, 4, 0x0310, WRITE_MASK_VAL(5, 4, 1)), /* UART7 IO mux M1 */ + RK_MUXROUTE_GRF(4, RK_PA2, 4, 0x0310, WRITE_MASK_VAL(5, 4, 2)), /* UART7 IO mux M2 */ + RK_MUXROUTE_GRF(2, RK_PC5, 3, 0x0310, WRITE_MASK_VAL(6, 6, 0)), /* UART8 IO mux M0 */ + RK_MUXROUTE_GRF(2, RK_PD7, 4, 0x0310, WRITE_MASK_VAL(6, 6, 1)), /* UART8 IO mux M1 */ + RK_MUXROUTE_GRF(2, RK_PB0, 3, 0x0310, WRITE_MASK_VAL(9, 8, 0)), /* UART9 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PC5, 4, 0x0310, WRITE_MASK_VAL(9, 8, 1)), /* UART9 IO mux M1 */ + RK_MUXROUTE_GRF(4, RK_PA4, 4, 0x0310, WRITE_MASK_VAL(9, 8, 2)), /* UART9 IO mux M2 */ + RK_MUXROUTE_GRF(1, RK_PA2, 1, 0x0310, WRITE_MASK_VAL(11, 10, 0)), /* I2S1 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PC6, 4, 0x0310, WRITE_MASK_VAL(11, 10, 1)), /* I2S1 IO mux M1 */ + RK_MUXROUTE_GRF(2, RK_PD0, 5, 0x0310, WRITE_MASK_VAL(11, 10, 2)), /* I2S1 IO mux M2 */ + RK_MUXROUTE_GRF(2, RK_PC1, 1, 0x0310, WRITE_MASK_VAL(12, 12, 0)), /* I2S2 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PB6, 5, 0x0310, WRITE_MASK_VAL(12, 12, 1)), /* I2S2 IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PA2, 4, 0x0310, WRITE_MASK_VAL(14, 14, 0)), /* I2S3 IO mux M0 */ + RK_MUXROUTE_GRF(4, RK_PC2, 5, 0x0310, WRITE_MASK_VAL(14, 14, 1)), /* I2S3 IO mux M1 */ + RK_MUXROUTE_GRF(1, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(1, 0, 0)), /* PDM IO mux M0 */ + RK_MUXROUTE_GRF(1, RK_PA6, 3, 0x0314, WRITE_MASK_VAL(1, 0, 0)), /* PDM IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PD6, 5, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */ + RK_MUXROUTE_GRF(4, RK_PA0, 4, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */ + RK_MUXROUTE_GRF(3, RK_PC4, 5, 0x0314, WRITE_MASK_VAL(1, 0, 2)), /* PDM IO mux M2 */ + RK_MUXROUTE_PMU(0, RK_PA5, 3, 0x0314, WRITE_MASK_VAL(3, 2, 0)), /* PCIE20 IO mux M0 */ + RK_MUXROUTE_GRF(2, RK_PD0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 1)), /* PCIE20 IO mux M1 */ + RK_MUXROUTE_GRF(1, RK_PB0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 2)), /* PCIE20 IO mux M2 */ + RK_MUXROUTE_PMU(0, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(5, 4, 0)), /* PCIE30X1 IO mux M0 */ + RK_MUXROUTE_GRF(2, RK_PD2, 4, 0x0314, WRITE_MASK_VAL(5, 4, 1)), /* PCIE30X1 IO mux M1 */ + RK_MUXROUTE_GRF(1, RK_PA5, 4, 0x0314, WRITE_MASK_VAL(5, 4, 2)), /* PCIE30X1 IO mux M2 */ + RK_MUXROUTE_PMU(0, RK_PA6, 2, 0x0314, WRITE_MASK_VAL(7, 6, 0)), /* PCIE30X2 IO mux M0 */ + RK_MUXROUTE_GRF(2, RK_PD4, 4, 0x0314, WRITE_MASK_VAL(7, 6, 1)), /* PCIE30X2 IO mux M1 */ + RK_MUXROUTE_GRF(4, RK_PC2, 4, 0x0314, WRITE_MASK_VAL(7, 6, 2)), /* PCIE30X2 IO mux M2 */ +}; + static bool rockchip_get_mux_route(struct rockchip_pin_bank *bank, int pin, int mux, u32 *loc, u32 *reg, u32 *value) { @@ -2117,6 +2241,68 @@ static void rk3399_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank, *bit = (pin_num % 8) * 2; } +#define RK3568_PULL_PMU_OFFSET 0x20 +#define RK3568_PULL_GRF_OFFSET 0x80 +#define RK3568_PULL_BITS_PER_PIN 2 +#define RK3568_PULL_PINS_PER_REG 8 +#define RK3568_PULL_BANK_STRIDE 0x10 + +static void rk3568_calc_pull_reg_and_bit(struct rockchip_pin_bank *bank, + int pin_num, struct regmap **regmap, + int *reg, u8 *bit) +{ + struct rockchip_pinctrl *info = bank->drvdata; + + if (bank->bank_num == 0) { + *regmap = info->regmap_pmu; + *reg = RK3568_PULL_PMU_OFFSET; + *reg += bank->bank_num * RK3568_PULL_BANK_STRIDE; + *reg += ((pin_num / RK3568_PULL_PINS_PER_REG) * 4); + + *bit = pin_num % RK3568_PULL_PINS_PER_REG; + *bit *= RK3568_PULL_BITS_PER_PIN; + } else { + *regmap = info->regmap_base; + *reg = RK3568_PULL_GRF_OFFSET; + *reg += (bank->bank_num - 1) * RK3568_PULL_BANK_STRIDE; + *reg += ((pin_num / RK3568_PULL_PINS_PER_REG) * 4); + + *bit = (pin_num % RK3568_PULL_PINS_PER_REG); + *bit *= RK3568_PULL_BITS_PER_PIN; + } +} + +#define RK3568_DRV_PMU_OFFSET 0x70 +#define RK3568_DRV_GRF_OFFSET 0x200 +#define RK3568_DRV_BITS_PER_PIN 8 +#define RK3568_DRV_PINS_PER_REG 2 +#define RK3568_DRV_BANK_STRIDE 0x40 + +static void rk3568_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank, + int pin_num, struct regmap **regmap, + int *reg, u8 *bit) +{ + struct rockchip_pinctrl *info = bank->drvdata; + + /* The first 32 pins of the first bank are located in PMU */ + if (bank->bank_num == 0) { + *regmap = info->regmap_pmu; + *reg = RK3568_DRV_PMU_OFFSET; + *reg += ((pin_num / RK3568_DRV_PINS_PER_REG) * 4); + + *bit = pin_num % RK3568_DRV_PINS_PER_REG; + *bit *= RK3568_DRV_BITS_PER_PIN; + } else { + *regmap = info->regmap_base; + *reg = RK3568_DRV_GRF_OFFSET; + *reg += (bank->bank_num - 1) * RK3568_DRV_BANK_STRIDE; + *reg += ((pin_num / RK3568_DRV_PINS_PER_REG) * 4); + + *bit = (pin_num % RK3568_DRV_PINS_PER_REG); + *bit *= RK3568_DRV_BITS_PER_PIN; + } +} + static int rockchip_perpin_drv_list[DRV_TYPE_MAX][8] = { { 2, 4, 8, 12, -1, -1, -1, -1 }, { 3, 6, 9, 12, -1, -1, -1, -1 }, @@ -2217,6 +2403,11 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank, bank->bank_num, pin_num, strength); ctrl->drv_calc_reg(bank, pin_num, ®map, ®, &bit); + if (ctrl->type == RK3568) { + rmask_bits = RK3568_DRV_BITS_PER_PIN; + ret = (1 << (strength + 1)) - 1; + goto config; + } ret = -EINVAL; for (i = 0; i < ARRAY_SIZE(rockchip_perpin_drv_list[drv_type]); i++) { @@ -2286,6 +2477,7 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank, return -EINVAL; } +config: /* enable the write to the equivalent lower bits */ data = ((1 << rmask_bits) - 1) << (bit + 16); rmask = data | (data >> 16); @@ -2388,6 +2580,7 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank, case RK3308: case RK3368: case RK3399: + case RK3568: pull_type = bank->pull_type[pin_num / 8]; ret = -EINVAL; for (i = 0; i < ARRAY_SIZE(rockchip_pull_list[pull_type]); @@ -2397,6 +2590,14 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank, break; } } + /* + * In the TRM, pull-up being 1 for everything except the GPIO0_D0-D6, + * where that pull up value becomes 3. + */ + if (ctrl->type == RK3568 && bank->bank_num == 0 && pin_num >= 27 && pin_num <= 30) { + if (ret == 1) + ret = 3; + } if (ret < 0) { dev_err(info->dev, "unsupported pull setting %d\n", @@ -2441,6 +2642,35 @@ static int rk3328_calc_schmitt_reg_and_bit(struct rockchip_pin_bank *bank, return 0; } +#define RK3568_SCHMITT_BITS_PER_PIN 2 +#define RK3568_SCHMITT_PINS_PER_REG 8 +#define RK3568_SCHMITT_BANK_STRIDE 0x10 +#define RK3568_SCHMITT_GRF_OFFSET 0xc0 +#define RK3568_SCHMITT_PMUGRF_OFFSET 0x30 + +static int rk3568_calc_schmitt_reg_and_bit(struct rockchip_pin_bank *bank, + int pin_num, + struct regmap **regmap, + int *reg, u8 *bit) +{ + struct rockchip_pinctrl *info = bank->drvdata; + + if (bank->bank_num == 0) { + *regmap = info->regmap_pmu; + *reg = RK3568_SCHMITT_PMUGRF_OFFSET; + } else { + *regmap = info->regmap_base; + *reg = RK3568_SCHMITT_GRF_OFFSET; + *reg += (bank->bank_num - 1) * RK3568_SCHMITT_BANK_STRIDE; + } + + *reg += ((pin_num / RK3568_SCHMITT_PINS_PER_REG) * 4); + *bit = pin_num % RK3568_SCHMITT_PINS_PER_REG; + *bit *= RK3568_SCHMITT_BITS_PER_PIN; + + return 0; +} + static int rockchip_get_schmitt(struct rockchip_pin_bank *bank, int pin_num) { struct rockchip_pinctrl *info = bank->drvdata; @@ -2459,6 +2689,13 @@ static int rockchip_get_schmitt(struct rockchip_pin_bank *bank, int pin_num) return ret; data >>= bit; + switch (ctrl->type) { + case RK3568: + return data & ((1 << RK3568_SCHMITT_BITS_PER_PIN) - 1); + default: + break; + } + return data & 0x1; } @@ -2480,8 +2717,17 @@ static int rockchip_set_schmitt(struct rockchip_pin_bank *bank, return ret; /* enable the write to the equivalent lower bits */ - data = BIT(bit + 16) | (enable << bit); - rmask = BIT(bit + 16) | BIT(bit); + switch (ctrl->type) { + case RK3568: + data = ((1 << RK3568_SCHMITT_BITS_PER_PIN) - 1) << (bit + 16); + rmask = data | (data >> 16); + data |= ((enable ? 0x2 : 0x1) << bit); + break; + default: + data = BIT(bit + 16) | (enable << bit); + rmask = BIT(bit + 16) | BIT(bit); + break; + } return regmap_update_bits(regmap, reg, rmask, data); } @@ -2655,6 +2901,7 @@ static bool rockchip_pinconf_pull_valid(struct rockchip_pin_ctrl *ctrl, case RK3308: case RK3368: case RK3399: + case RK3568: return (pull != PIN_CONFIG_BIAS_PULL_PIN_DEFAULT); } @@ -4230,6 +4477,45 @@ static struct rockchip_pin_ctrl rk3399_pin_ctrl = { .drv_calc_reg = rk3399_calc_drv_reg_and_bit, }; +static struct rockchip_pin_bank rk3568_pin_banks[] = { + PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", IOMUX_SOURCE_PMU | IOMUX_WIDTH_4BIT, + IOMUX_SOURCE_PMU | IOMUX_WIDTH_4BIT, + IOMUX_SOURCE_PMU | IOMUX_WIDTH_4BIT, + IOMUX_SOURCE_PMU | IOMUX_WIDTH_4BIT), + PIN_BANK_IOMUX_FLAGS(1, 32, "gpio1", IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT), + PIN_BANK_IOMUX_FLAGS(2, 32, "gpio2", IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT), + PIN_BANK_IOMUX_FLAGS(3, 32, "gpio3", IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT), + PIN_BANK_IOMUX_FLAGS(4, 32, "gpio4", IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT, + IOMUX_WIDTH_4BIT), +}; + +static struct rockchip_pin_ctrl rk3568_pin_ctrl = { + .pin_banks = rk3568_pin_banks, + .nr_banks = ARRAY_SIZE(rk3568_pin_banks), + .label = "RK3568-GPIO", + .type = RK3568, + .grf_mux_offset = 0x0, + .pmu_mux_offset = 0x0, + .grf_drv_offset = 0x0200, + .pmu_drv_offset = 0x0070, + .iomux_routes = rk3568_mux_route_data, + .niomux_routes = ARRAY_SIZE(rk3568_mux_route_data), + .pull_calc_reg = rk3568_calc_pull_reg_and_bit, + .drv_calc_reg = rk3568_calc_drv_reg_and_bit, + .schmitt_calc_reg = rk3568_calc_schmitt_reg_and_bit, +}; + static const struct of_device_id rockchip_pinctrl_dt_match[] = { { .compatible = "rockchip,px30-pinctrl", .data = &px30_pin_ctrl }, @@ -4259,6 +4545,8 @@ static const struct of_device_id rockchip_pinctrl_dt_match[] = { .data = &rk3368_pin_ctrl }, { .compatible = "rockchip,rk3399-pinctrl", .data = &rk3399_pin_ctrl }, + { .compatible = "rockchip,rk3568-pinctrl", + .data = &rk3568_pin_ctrl }, {}, }; From 3dd6f159385d13853e41e697cb71070a942f221c Mon Sep 17 00:00:00 2001 From: Jianqun Xu Date: Tue, 20 Apr 2021 17:12:40 +0800 Subject: [PATCH 1660/4345] pinctrl: rockchip: do coding style for mux route struct [ Upstream commit fe202ea8e5b170ef7b3741da885e8cb7bae1106e ] The mux route tables take many lines for each SoC, and it will be more instances for newly SoC, that makes the file size increase larger. This patch only do coding style for mux route struct, by adding a new definition and replace the structs by script which supplied by huangtao@rock-chips.com sed -i -e " /static struct rockchip_mux_route_data /bcheck b :append-next-line N :check /^[^;]*$/bappend-next-line s/[[:blank:]]*.bank_num = \([[:digit:]]*,\)\n/\tRK_MUXROUTE_SAME(\1/g s/[[:blank:]]*.pin =[[:blank:]]*0,\n/ RK_PA0,/g s/[[:blank:]]*.pin =[[:blank:]]*1,\n/ RK_PA1,/g s/[[:blank:]]*.pin =[[:blank:]]*2,\n/ RK_PA2,/g s/[[:blank:]]*.pin =[[:blank:]]*3,\n/ RK_PA3,/g s/[[:blank:]]*.pin =[[:blank:]]*4,\n/ RK_PA4,/g s/[[:blank:]]*.pin =[[:blank:]]*5,\n/ RK_PA5,/g s/[[:blank:]]*.pin =[[:blank:]]*6,\n/ RK_PA6,/g s/[[:blank:]]*.pin =[[:blank:]]*7,\n/ RK_PA7,/g s/[[:blank:]]*.pin =[[:blank:]]*8,\n/ RK_PB0,/g s/[[:blank:]]*.pin =[[:blank:]]*9,\n/ RK_PB1,/g s/[[:blank:]]*.pin =[[:blank:]]*10,\n/ RK_PB2,/g s/[[:blank:]]*.pin =[[:blank:]]*11,\n/ RK_PB3,/g s/[[:blank:]]*.pin =[[:blank:]]*12,\n/ RK_PB4,/g s/[[:blank:]]*.pin =[[:blank:]]*13,\n/ RK_PB5,/g s/[[:blank:]]*.pin =[[:blank:]]*14,\n/ RK_PB6,/g s/[[:blank:]]*.pin =[[:blank:]]*15,\n/ RK_PB7,/g s/[[:blank:]]*.pin =[[:blank:]]*16,\n/ RK_PC0,/g s/[[:blank:]]*.pin =[[:blank:]]*17,\n/ RK_PC1,/g s/[[:blank:]]*.pin =[[:blank:]]*18,\n/ RK_PC2,/g s/[[:blank:]]*.pin =[[:blank:]]*19,\n/ RK_PC3,/g s/[[:blank:]]*.pin =[[:blank:]]*20,\n/ RK_PC4,/g s/[[:blank:]]*.pin =[[:blank:]]*21,\n/ RK_PC5,/g s/[[:blank:]]*.pin =[[:blank:]]*22,\n/ RK_PC6,/g s/[[:blank:]]*.pin =[[:blank:]]*23,\n/ RK_PC7,/g s/[[:blank:]]*.pin =[[:blank:]]*24,\n/ RK_PD0,/g s/[[:blank:]]*.pin =[[:blank:]]*25,\n/ RK_PD1,/g s/[[:blank:]]*.pin =[[:blank:]]*26,\n/ RK_PD2,/g s/[[:blank:]]*.pin =[[:blank:]]*27,\n/ RK_PD3,/g s/[[:blank:]]*.pin =[[:blank:]]*28,\n/ RK_PD4,/g s/[[:blank:]]*.pin =[[:blank:]]*29,\n/ RK_PD5,/g s/[[:blank:]]*.pin =[[:blank:]]*30,\n/ RK_PD6,/g s/[[:blank:]]*.pin =[[:blank:]]*31,\n/ RK_PD7,/g s/[[:blank:]]*.func = \([[:digit:]]*,\)\n/ \1/g s/[[:blank:]]*.route_location =[[:blank:]]*\([[:print:]]*,\)\n//g s/[[:blank:]]*.route_offset = \(0x[[:xdigit:]]*,\)\n/ \1/g s/[[:blank:]]*.route_val =[[:blank:]]*\([[:print:]]*\),\n/ \1),/g s/\t{\n//g s/\t}, {\n//g s/\t},//g s/[[:blank:]]*\(\/\*[[:print:]]*\*\/\)\n[[:blank:]]*RK_MUXROUTE_SAME(\([[:print:]]*\)),\n/\tRK_MUXROUTE_SAME(\2), \1\n/g s/[[:blank:]]*\(\/\*[[:print:]]*\*\/\)\n[[:blank:]]*RK_MUXROUTE_SAME(\([[:print:]]*\)),/\tRK_MUXROUTE_SAME(\2), \1\n/g " drivers/pinctrl/pinctrl-rockchip.c Reviewed-by: Heiko Stuebner Signed-off-by: Jianqun Xu Link: https://lore.kernel.org/r/20210420091240.1246429-1-jay.xu@rock-chips.com Signed-off-by: Linus Walleij Stable-dep-of: c818ae563bf9 ("pinctrl: rockchip: Fix refcount leak in rockchip_pinctrl_parse_groups") Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-rockchip.c | 650 ++++------------------------- 1 file changed, 80 insertions(+), 570 deletions(-) diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 38ea70f49cb0..944c7254f672 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -844,597 +844,107 @@ static void rockchip_get_recalced_mux(struct rockchip_pin_bank *bank, int pin, } static struct rockchip_mux_route_data px30_mux_route_data[] = { - { - /* cif-d2m0 */ - .bank_num = 2, - .pin = 0, - .func = 1, - .route_offset = 0x184, - .route_val = BIT(16 + 7), - }, { - /* cif-d2m1 */ - .bank_num = 3, - .pin = 3, - .func = 3, - .route_offset = 0x184, - .route_val = BIT(16 + 7) | BIT(7), - }, { - /* pdm-m0 */ - .bank_num = 3, - .pin = 22, - .func = 2, - .route_offset = 0x184, - .route_val = BIT(16 + 8), - }, { - /* pdm-m1 */ - .bank_num = 2, - .pin = 22, - .func = 1, - .route_offset = 0x184, - .route_val = BIT(16 + 8) | BIT(8), - }, { - /* uart2-rxm0 */ - .bank_num = 1, - .pin = 27, - .func = 2, - .route_offset = 0x184, - .route_val = BIT(16 + 10), - }, { - /* uart2-rxm1 */ - .bank_num = 2, - .pin = 14, - .func = 2, - .route_offset = 0x184, - .route_val = BIT(16 + 10) | BIT(10), - }, { - /* uart3-rxm0 */ - .bank_num = 0, - .pin = 17, - .func = 2, - .route_offset = 0x184, - .route_val = BIT(16 + 9), - }, { - /* uart3-rxm1 */ - .bank_num = 1, - .pin = 15, - .func = 2, - .route_offset = 0x184, - .route_val = BIT(16 + 9) | BIT(9), - }, + RK_MUXROUTE_SAME(2, RK_PA0, 1, 0x184, BIT(16 + 7)), /* cif-d2m0 */ + RK_MUXROUTE_SAME(3, RK_PA3, 3, 0x184, BIT(16 + 7) | BIT(7)), /* cif-d2m1 */ + RK_MUXROUTE_SAME(3, RK_PC6, 2, 0x184, BIT(16 + 8)), /* pdm-m0 */ + RK_MUXROUTE_SAME(2, RK_PC6, 1, 0x184, BIT(16 + 8) | BIT(8)), /* pdm-m1 */ + RK_MUXROUTE_SAME(1, RK_PD3, 2, 0x184, BIT(16 + 10)), /* uart2-rxm0 */ + RK_MUXROUTE_SAME(2, RK_PB6, 2, 0x184, BIT(16 + 10) | BIT(10)), /* uart2-rxm1 */ + RK_MUXROUTE_SAME(0, RK_PC1, 2, 0x184, BIT(16 + 9)), /* uart3-rxm0 */ + RK_MUXROUTE_SAME(1, RK_PB7, 2, 0x184, BIT(16 + 9) | BIT(9)), /* uart3-rxm1 */ }; static struct rockchip_mux_route_data rk3128_mux_route_data[] = { - { - /* spi-0 */ - .bank_num = 1, - .pin = 10, - .func = 1, - .route_offset = 0x144, - .route_val = BIT(16 + 3) | BIT(16 + 4), - }, { - /* spi-1 */ - .bank_num = 1, - .pin = 27, - .func = 3, - .route_offset = 0x144, - .route_val = BIT(16 + 3) | BIT(16 + 4) | BIT(3), - }, { - /* spi-2 */ - .bank_num = 0, - .pin = 13, - .func = 2, - .route_offset = 0x144, - .route_val = BIT(16 + 3) | BIT(16 + 4) | BIT(4), - }, { - /* i2s-0 */ - .bank_num = 1, - .pin = 5, - .func = 1, - .route_offset = 0x144, - .route_val = BIT(16 + 5), - }, { - /* i2s-1 */ - .bank_num = 0, - .pin = 14, - .func = 1, - .route_offset = 0x144, - .route_val = BIT(16 + 5) | BIT(5), - }, { - /* emmc-0 */ - .bank_num = 1, - .pin = 22, - .func = 2, - .route_offset = 0x144, - .route_val = BIT(16 + 6), - }, { - /* emmc-1 */ - .bank_num = 2, - .pin = 4, - .func = 2, - .route_offset = 0x144, - .route_val = BIT(16 + 6) | BIT(6), - }, + RK_MUXROUTE_SAME(1, RK_PB2, 1, 0x144, BIT(16 + 3) | BIT(16 + 4)), /* spi-0 */ + RK_MUXROUTE_SAME(1, RK_PD3, 3, 0x144, BIT(16 + 3) | BIT(16 + 4) | BIT(3)), /* spi-1 */ + RK_MUXROUTE_SAME(0, RK_PB5, 2, 0x144, BIT(16 + 3) | BIT(16 + 4) | BIT(4)), /* spi-2 */ + RK_MUXROUTE_SAME(1, RK_PA5, 1, 0x144, BIT(16 + 5)), /* i2s-0 */ + RK_MUXROUTE_SAME(0, RK_PB6, 1, 0x144, BIT(16 + 5) | BIT(5)), /* i2s-1 */ + RK_MUXROUTE_SAME(1, RK_PC6, 2, 0x144, BIT(16 + 6)), /* emmc-0 */ + RK_MUXROUTE_SAME(2, RK_PA4, 2, 0x144, BIT(16 + 6) | BIT(6)), /* emmc-1 */ }; static struct rockchip_mux_route_data rk3188_mux_route_data[] = { - { - /* non-iomuxed emmc/flash pins on flash-dqs */ - .bank_num = 0, - .pin = 24, - .func = 1, - .route_location = ROCKCHIP_ROUTE_GRF, - .route_offset = 0xa0, - .route_val = BIT(16 + 11), - }, { - /* non-iomuxed emmc/flash pins on emmc-clk */ - .bank_num = 0, - .pin = 24, - .func = 2, - .route_location = ROCKCHIP_ROUTE_GRF, - .route_offset = 0xa0, - .route_val = BIT(16 + 11) | BIT(11), - }, + RK_MUXROUTE_SAME(0, RK_PD0, 1, 0xa0, BIT(16 + 11)), /* non-iomuxed emmc/flash pins on flash-dqs */ + RK_MUXROUTE_SAME(0, RK_PD0, 2, 0xa0, BIT(16 + 11) | BIT(11)), /* non-iomuxed emmc/flash pins on emmc-clk */ }; static struct rockchip_mux_route_data rk3228_mux_route_data[] = { - { - /* pwm0-0 */ - .bank_num = 0, - .pin = 26, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16), - }, { - /* pwm0-1 */ - .bank_num = 3, - .pin = 21, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16) | BIT(0), - }, { - /* pwm1-0 */ - .bank_num = 0, - .pin = 27, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16 + 1), - }, { - /* pwm1-1 */ - .bank_num = 0, - .pin = 30, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 1) | BIT(1), - }, { - /* pwm2-0 */ - .bank_num = 0, - .pin = 28, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16 + 2), - }, { - /* pwm2-1 */ - .bank_num = 1, - .pin = 12, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 2) | BIT(2), - }, { - /* pwm3-0 */ - .bank_num = 3, - .pin = 26, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16 + 3), - }, { - /* pwm3-1 */ - .bank_num = 1, - .pin = 11, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 3) | BIT(3), - }, { - /* sdio-0_d0 */ - .bank_num = 1, - .pin = 1, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16 + 4), - }, { - /* sdio-1_d0 */ - .bank_num = 3, - .pin = 2, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16 + 4) | BIT(4), - }, { - /* spi-0_rx */ - .bank_num = 0, - .pin = 13, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 5), - }, { - /* spi-1_rx */ - .bank_num = 2, - .pin = 0, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 5) | BIT(5), - }, { - /* emmc-0_cmd */ - .bank_num = 1, - .pin = 22, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 7), - }, { - /* emmc-1_cmd */ - .bank_num = 2, - .pin = 4, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 7) | BIT(7), - }, { - /* uart2-0_rx */ - .bank_num = 1, - .pin = 19, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 8), - }, { - /* uart2-1_rx */ - .bank_num = 1, - .pin = 10, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 8) | BIT(8), - }, { - /* uart1-0_rx */ - .bank_num = 1, - .pin = 10, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16 + 11), - }, { - /* uart1-1_rx */ - .bank_num = 3, - .pin = 13, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16 + 11) | BIT(11), - }, + RK_MUXROUTE_SAME(0, RK_PD2, 1, 0x50, BIT(16)), /* pwm0-0 */ + RK_MUXROUTE_SAME(3, RK_PC5, 1, 0x50, BIT(16) | BIT(0)), /* pwm0-1 */ + RK_MUXROUTE_SAME(0, RK_PD3, 1, 0x50, BIT(16 + 1)), /* pwm1-0 */ + RK_MUXROUTE_SAME(0, RK_PD6, 2, 0x50, BIT(16 + 1) | BIT(1)), /* pwm1-1 */ + RK_MUXROUTE_SAME(0, RK_PD4, 1, 0x50, BIT(16 + 2)), /* pwm2-0 */ + RK_MUXROUTE_SAME(1, RK_PB4, 2, 0x50, BIT(16 + 2) | BIT(2)), /* pwm2-1 */ + RK_MUXROUTE_SAME(3, RK_PD2, 1, 0x50, BIT(16 + 3)), /* pwm3-0 */ + RK_MUXROUTE_SAME(1, RK_PB3, 2, 0x50, BIT(16 + 3) | BIT(3)), /* pwm3-1 */ + RK_MUXROUTE_SAME(1, RK_PA1, 1, 0x50, BIT(16 + 4)), /* sdio-0_d0 */ + RK_MUXROUTE_SAME(3, RK_PA2, 1, 0x50, BIT(16 + 4) | BIT(4)), /* sdio-1_d0 */ + RK_MUXROUTE_SAME(0, RK_PB5, 2, 0x50, BIT(16 + 5)), /* spi-0_rx */ + RK_MUXROUTE_SAME(2, RK_PA0, 2, 0x50, BIT(16 + 5) | BIT(5)), /* spi-1_rx */ + RK_MUXROUTE_SAME(1, RK_PC6, 2, 0x50, BIT(16 + 7)), /* emmc-0_cmd */ + RK_MUXROUTE_SAME(2, RK_PA4, 2, 0x50, BIT(16 + 7) | BIT(7)), /* emmc-1_cmd */ + RK_MUXROUTE_SAME(1, RK_PC3, 2, 0x50, BIT(16 + 8)), /* uart2-0_rx */ + RK_MUXROUTE_SAME(1, RK_PB2, 2, 0x50, BIT(16 + 8) | BIT(8)), /* uart2-1_rx */ + RK_MUXROUTE_SAME(1, RK_PB2, 1, 0x50, BIT(16 + 11)), /* uart1-0_rx */ + RK_MUXROUTE_SAME(3, RK_PB5, 1, 0x50, BIT(16 + 11) | BIT(11)), /* uart1-1_rx */ }; static struct rockchip_mux_route_data rk3288_mux_route_data[] = { - { - /* edphdmi_cecinoutt1 */ - .bank_num = 7, - .pin = 16, - .func = 2, - .route_offset = 0x264, - .route_val = BIT(16 + 12) | BIT(12), - }, { - /* edphdmi_cecinout */ - .bank_num = 7, - .pin = 23, - .func = 4, - .route_offset = 0x264, - .route_val = BIT(16 + 12), - }, + RK_MUXROUTE_SAME(7, RK_PC0, 2, 0x264, BIT(16 + 12) | BIT(12)), /* edphdmi_cecinoutt1 */ + RK_MUXROUTE_SAME(7, RK_PC7, 4, 0x264, BIT(16 + 12)), /* edphdmi_cecinout */ }; static struct rockchip_mux_route_data rk3308_mux_route_data[] = { - { - /* rtc_clk */ - .bank_num = 0, - .pin = 19, - .func = 1, - .route_offset = 0x314, - .route_val = BIT(16 + 0) | BIT(0), - }, { - /* uart2_rxm0 */ - .bank_num = 1, - .pin = 22, - .func = 2, - .route_offset = 0x314, - .route_val = BIT(16 + 2) | BIT(16 + 3), - }, { - /* uart2_rxm1 */ - .bank_num = 4, - .pin = 26, - .func = 2, - .route_offset = 0x314, - .route_val = BIT(16 + 2) | BIT(16 + 3) | BIT(2), - }, { - /* i2c3_sdam0 */ - .bank_num = 0, - .pin = 15, - .func = 2, - .route_offset = 0x608, - .route_val = BIT(16 + 8) | BIT(16 + 9), - }, { - /* i2c3_sdam1 */ - .bank_num = 3, - .pin = 12, - .func = 2, - .route_offset = 0x608, - .route_val = BIT(16 + 8) | BIT(16 + 9) | BIT(8), - }, { - /* i2c3_sdam2 */ - .bank_num = 2, - .pin = 0, - .func = 3, - .route_offset = 0x608, - .route_val = BIT(16 + 8) | BIT(16 + 9) | BIT(9), - }, { - /* i2s-8ch-1-sclktxm0 */ - .bank_num = 1, - .pin = 3, - .func = 2, - .route_offset = 0x308, - .route_val = BIT(16 + 3), - }, { - /* i2s-8ch-1-sclkrxm0 */ - .bank_num = 1, - .pin = 4, - .func = 2, - .route_offset = 0x308, - .route_val = BIT(16 + 3), - }, { - /* i2s-8ch-1-sclktxm1 */ - .bank_num = 1, - .pin = 13, - .func = 2, - .route_offset = 0x308, - .route_val = BIT(16 + 3) | BIT(3), - }, { - /* i2s-8ch-1-sclkrxm1 */ - .bank_num = 1, - .pin = 14, - .func = 2, - .route_offset = 0x308, - .route_val = BIT(16 + 3) | BIT(3), - }, { - /* pdm-clkm0 */ - .bank_num = 1, - .pin = 4, - .func = 3, - .route_offset = 0x308, - .route_val = BIT(16 + 12) | BIT(16 + 13), - }, { - /* pdm-clkm1 */ - .bank_num = 1, - .pin = 14, - .func = 4, - .route_offset = 0x308, - .route_val = BIT(16 + 12) | BIT(16 + 13) | BIT(12), - }, { - /* pdm-clkm2 */ - .bank_num = 2, - .pin = 6, - .func = 2, - .route_offset = 0x308, - .route_val = BIT(16 + 12) | BIT(16 + 13) | BIT(13), - }, { - /* pdm-clkm-m2 */ - .bank_num = 2, - .pin = 4, - .func = 3, - .route_offset = 0x600, - .route_val = BIT(16 + 2) | BIT(2), - }, { - /* spi1_miso */ - .bank_num = 3, - .pin = 10, - .func = 3, - .route_offset = 0x314, - .route_val = BIT(16 + 9), - }, { - /* spi1_miso_m1 */ - .bank_num = 2, - .pin = 4, - .func = 2, - .route_offset = 0x314, - .route_val = BIT(16 + 9) | BIT(9), - }, { - /* owire_m0 */ - .bank_num = 0, - .pin = 11, - .func = 3, - .route_offset = 0x314, - .route_val = BIT(16 + 10) | BIT(16 + 11), - }, { - /* owire_m1 */ - .bank_num = 1, - .pin = 22, - .func = 7, - .route_offset = 0x314, - .route_val = BIT(16 + 10) | BIT(16 + 11) | BIT(10), - }, { - /* owire_m2 */ - .bank_num = 2, - .pin = 2, - .func = 5, - .route_offset = 0x314, - .route_val = BIT(16 + 10) | BIT(16 + 11) | BIT(11), - }, { - /* can_rxd_m0 */ - .bank_num = 0, - .pin = 11, - .func = 2, - .route_offset = 0x314, - .route_val = BIT(16 + 12) | BIT(16 + 13), - }, { - /* can_rxd_m1 */ - .bank_num = 1, - .pin = 22, - .func = 5, - .route_offset = 0x314, - .route_val = BIT(16 + 12) | BIT(16 + 13) | BIT(12), - }, { - /* can_rxd_m2 */ - .bank_num = 2, - .pin = 2, - .func = 4, - .route_offset = 0x314, - .route_val = BIT(16 + 12) | BIT(16 + 13) | BIT(13), - }, { - /* mac_rxd0_m0 */ - .bank_num = 1, - .pin = 20, - .func = 3, - .route_offset = 0x314, - .route_val = BIT(16 + 14), - }, { - /* mac_rxd0_m1 */ - .bank_num = 4, - .pin = 2, - .func = 2, - .route_offset = 0x314, - .route_val = BIT(16 + 14) | BIT(14), - }, { - /* uart3_rx */ - .bank_num = 3, - .pin = 12, - .func = 4, - .route_offset = 0x314, - .route_val = BIT(16 + 15), - }, { - /* uart3_rx_m1 */ - .bank_num = 0, - .pin = 17, - .func = 3, - .route_offset = 0x314, - .route_val = BIT(16 + 15) | BIT(15), - }, + RK_MUXROUTE_SAME(0, RK_PC3, 1, 0x314, BIT(16 + 0) | BIT(0)), /* rtc_clk */ + RK_MUXROUTE_SAME(1, RK_PC6, 2, 0x314, BIT(16 + 2) | BIT(16 + 3)), /* uart2_rxm0 */ + RK_MUXROUTE_SAME(4, RK_PD2, 2, 0x314, BIT(16 + 2) | BIT(16 + 3) | BIT(2)), /* uart2_rxm1 */ + RK_MUXROUTE_SAME(0, RK_PB7, 2, 0x608, BIT(16 + 8) | BIT(16 + 9)), /* i2c3_sdam0 */ + RK_MUXROUTE_SAME(3, RK_PB4, 2, 0x608, BIT(16 + 8) | BIT(16 + 9) | BIT(8)), /* i2c3_sdam1 */ + RK_MUXROUTE_SAME(2, RK_PA0, 3, 0x608, BIT(16 + 8) | BIT(16 + 9) | BIT(9)), /* i2c3_sdam2 */ + RK_MUXROUTE_SAME(1, RK_PA3, 2, 0x308, BIT(16 + 3)), /* i2s-8ch-1-sclktxm0 */ + RK_MUXROUTE_SAME(1, RK_PA4, 2, 0x308, BIT(16 + 3)), /* i2s-8ch-1-sclkrxm0 */ + RK_MUXROUTE_SAME(1, RK_PB5, 2, 0x308, BIT(16 + 3) | BIT(3)), /* i2s-8ch-1-sclktxm1 */ + RK_MUXROUTE_SAME(1, RK_PB6, 2, 0x308, BIT(16 + 3) | BIT(3)), /* i2s-8ch-1-sclkrxm1 */ + RK_MUXROUTE_SAME(1, RK_PA4, 3, 0x308, BIT(16 + 12) | BIT(16 + 13)), /* pdm-clkm0 */ + RK_MUXROUTE_SAME(1, RK_PB6, 4, 0x308, BIT(16 + 12) | BIT(16 + 13) | BIT(12)), /* pdm-clkm1 */ + RK_MUXROUTE_SAME(2, RK_PA6, 2, 0x308, BIT(16 + 12) | BIT(16 + 13) | BIT(13)), /* pdm-clkm2 */ + RK_MUXROUTE_SAME(2, RK_PA4, 3, 0x600, BIT(16 + 2) | BIT(2)), /* pdm-clkm-m2 */ + RK_MUXROUTE_SAME(3, RK_PB2, 3, 0x314, BIT(16 + 9)), /* spi1_miso */ + RK_MUXROUTE_SAME(2, RK_PA4, 2, 0x314, BIT(16 + 9) | BIT(9)), /* spi1_miso_m1 */ + RK_MUXROUTE_SAME(0, RK_PB3, 3, 0x314, BIT(16 + 10) | BIT(16 + 11)), /* owire_m0 */ + RK_MUXROUTE_SAME(1, RK_PC6, 7, 0x314, BIT(16 + 10) | BIT(16 + 11) | BIT(10)), /* owire_m1 */ + RK_MUXROUTE_SAME(2, RK_PA2, 5, 0x314, BIT(16 + 10) | BIT(16 + 11) | BIT(11)), /* owire_m2 */ + RK_MUXROUTE_SAME(0, RK_PB3, 2, 0x314, BIT(16 + 12) | BIT(16 + 13)), /* can_rxd_m0 */ + RK_MUXROUTE_SAME(1, RK_PC6, 5, 0x314, BIT(16 + 12) | BIT(16 + 13) | BIT(12)), /* can_rxd_m1 */ + RK_MUXROUTE_SAME(2, RK_PA2, 4, 0x314, BIT(16 + 12) | BIT(16 + 13) | BIT(13)), /* can_rxd_m2 */ + RK_MUXROUTE_SAME(1, RK_PC4, 3, 0x314, BIT(16 + 14)), /* mac_rxd0_m0 */ + RK_MUXROUTE_SAME(4, RK_PA2, 2, 0x314, BIT(16 + 14) | BIT(14)), /* mac_rxd0_m1 */ + RK_MUXROUTE_SAME(3, RK_PB4, 4, 0x314, BIT(16 + 15)), /* uart3_rx */ + RK_MUXROUTE_SAME(0, RK_PC1, 3, 0x314, BIT(16 + 15) | BIT(15)), /* uart3_rx_m1 */ }; static struct rockchip_mux_route_data rk3328_mux_route_data[] = { - { - /* uart2dbg_rxm0 */ - .bank_num = 1, - .pin = 1, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16) | BIT(16 + 1), - }, { - /* uart2dbg_rxm1 */ - .bank_num = 2, - .pin = 1, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16) | BIT(16 + 1) | BIT(0), - }, { - /* gmac-m1_rxd0 */ - .bank_num = 1, - .pin = 11, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 2) | BIT(2), - }, { - /* gmac-m1-optimized_rxd3 */ - .bank_num = 1, - .pin = 14, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 10) | BIT(10), - }, { - /* pdm_sdi0m0 */ - .bank_num = 2, - .pin = 19, - .func = 2, - .route_offset = 0x50, - .route_val = BIT(16 + 3), - }, { - /* pdm_sdi0m1 */ - .bank_num = 1, - .pin = 23, - .func = 3, - .route_offset = 0x50, - .route_val = BIT(16 + 3) | BIT(3), - }, { - /* spi_rxdm2 */ - .bank_num = 3, - .pin = 2, - .func = 4, - .route_offset = 0x50, - .route_val = BIT(16 + 4) | BIT(16 + 5) | BIT(5), - }, { - /* i2s2_sdim0 */ - .bank_num = 1, - .pin = 24, - .func = 1, - .route_offset = 0x50, - .route_val = BIT(16 + 6), - }, { - /* i2s2_sdim1 */ - .bank_num = 3, - .pin = 2, - .func = 6, - .route_offset = 0x50, - .route_val = BIT(16 + 6) | BIT(6), - }, { - /* card_iom1 */ - .bank_num = 2, - .pin = 22, - .func = 3, - .route_offset = 0x50, - .route_val = BIT(16 + 7) | BIT(7), - }, { - /* tsp_d5m1 */ - .bank_num = 2, - .pin = 16, - .func = 3, - .route_offset = 0x50, - .route_val = BIT(16 + 8) | BIT(8), - }, { - /* cif_data5m1 */ - .bank_num = 2, - .pin = 16, - .func = 4, - .route_offset = 0x50, - .route_val = BIT(16 + 9) | BIT(9), - }, + RK_MUXROUTE_SAME(1, RK_PA1, 2, 0x50, BIT(16) | BIT(16 + 1)), /* uart2dbg_rxm0 */ + RK_MUXROUTE_SAME(2, RK_PA1, 1, 0x50, BIT(16) | BIT(16 + 1) | BIT(0)), /* uart2dbg_rxm1 */ + RK_MUXROUTE_SAME(1, RK_PB3, 2, 0x50, BIT(16 + 2) | BIT(2)), /* gmac-m1_rxd0 */ + RK_MUXROUTE_SAME(1, RK_PB6, 2, 0x50, BIT(16 + 10) | BIT(10)), /* gmac-m1-optimized_rxd3 */ + RK_MUXROUTE_SAME(2, RK_PC3, 2, 0x50, BIT(16 + 3)), /* pdm_sdi0m0 */ + RK_MUXROUTE_SAME(1, RK_PC7, 3, 0x50, BIT(16 + 3) | BIT(3)), /* pdm_sdi0m1 */ + RK_MUXROUTE_SAME(3, RK_PA2, 4, 0x50, BIT(16 + 4) | BIT(16 + 5) | BIT(5)), /* spi_rxdm2 */ + RK_MUXROUTE_SAME(1, RK_PD0, 1, 0x50, BIT(16 + 6)), /* i2s2_sdim0 */ + RK_MUXROUTE_SAME(3, RK_PA2, 6, 0x50, BIT(16 + 6) | BIT(6)), /* i2s2_sdim1 */ + RK_MUXROUTE_SAME(2, RK_PC6, 3, 0x50, BIT(16 + 7) | BIT(7)), /* card_iom1 */ + RK_MUXROUTE_SAME(2, RK_PC0, 3, 0x50, BIT(16 + 8) | BIT(8)), /* tsp_d5m1 */ + RK_MUXROUTE_SAME(2, RK_PC0, 4, 0x50, BIT(16 + 9) | BIT(9)), /* cif_data5m1 */ }; static struct rockchip_mux_route_data rk3399_mux_route_data[] = { - { - /* uart2dbga_rx */ - .bank_num = 4, - .pin = 8, - .func = 2, - .route_offset = 0xe21c, - .route_val = BIT(16 + 10) | BIT(16 + 11), - }, { - /* uart2dbgb_rx */ - .bank_num = 4, - .pin = 16, - .func = 2, - .route_offset = 0xe21c, - .route_val = BIT(16 + 10) | BIT(16 + 11) | BIT(10), - }, { - /* uart2dbgc_rx */ - .bank_num = 4, - .pin = 19, - .func = 1, - .route_offset = 0xe21c, - .route_val = BIT(16 + 10) | BIT(16 + 11) | BIT(11), - }, { - /* pcie_clkreqn */ - .bank_num = 2, - .pin = 26, - .func = 2, - .route_offset = 0xe21c, - .route_val = BIT(16 + 14), - }, { - /* pcie_clkreqnb */ - .bank_num = 4, - .pin = 24, - .func = 1, - .route_offset = 0xe21c, - .route_val = BIT(16 + 14) | BIT(14), - }, + RK_MUXROUTE_SAME(4, RK_PB0, 2, 0xe21c, BIT(16 + 10) | BIT(16 + 11)), /* uart2dbga_rx */ + RK_MUXROUTE_SAME(4, RK_PC0, 2, 0xe21c, BIT(16 + 10) | BIT(16 + 11) | BIT(10)), /* uart2dbgb_rx */ + RK_MUXROUTE_SAME(4, RK_PC3, 1, 0xe21c, BIT(16 + 10) | BIT(16 + 11) | BIT(11)), /* uart2dbgc_rx */ + RK_MUXROUTE_SAME(2, RK_PD2, 2, 0xe21c, BIT(16 + 14)), /* pcie_clkreqn */ + RK_MUXROUTE_SAME(4, RK_PD0, 1, 0xe21c, BIT(16 + 14) | BIT(14)), /* pcie_clkreqnb */ }; static struct rockchip_mux_route_data rk3568_mux_route_data[] = { From d562054a3a2eede3507a5461011ee82b671fcb88 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 2 Jan 2023 15:28:45 +0400 Subject: [PATCH 1661/4345] pinctrl: rockchip: Fix refcount leak in rockchip_pinctrl_parse_groups [ Upstream commit c818ae563bf99457f02e8170aabd6b174f629f65 ] of_find_node_by_phandle() returns a node pointer with refcount incremented, We should use of_node_put() on it when not needed anymore. Add missing of_node_put() to avoid refcount leak. Fixes: d3e5116119bd ("pinctrl: add pinctrl driver for Rockchip SoCs") Signed-off-by: Miaoqian Lin Link: https://lore.kernel.org/r/20230102112845.3982407-1-linmq006@gmail.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-rockchip.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 944c7254f672..764c96ddfc76 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -2650,6 +2650,7 @@ static int rockchip_pinctrl_parse_groups(struct device_node *np, np_config = of_find_node_by_phandle(be32_to_cpup(phandle)); ret = pinconf_generic_parse_dt_config(np_config, NULL, &grp->data[j].configs, &grp->data[j].nconfigs); + of_node_put(np_config); if (ret) return ret; } From bc65127ba4c0091886811d94c7d46aecfd13c2f1 Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Wed, 7 Dec 2022 12:53:13 +0100 Subject: [PATCH 1662/4345] drm/vc4: hvs: Set AXI panic modes [ Upstream commit df993fced230daa8452892406f3180c93ebf7e7b ] The HVS can change AXI request mode based on how full the COB FIFOs are. Until now the vc4 driver has been relying on the firmware to have set these to sensible values. With HVS channel 2 now being used for live video, change the panic mode for all channels to be explicitly set by the driver, and the same for all channels. Fixes: c54619b0bfb3 ("drm/vc4: Add support for the BCM2711 HVS5") Signed-off-by: Dave Stevenson Link: https://lore.kernel.org/r/20221207-rpi-hvs-crtc-misc-v1-2-1f8e0770798b@cerno.tech Signed-off-by: Maxime Ripard Signed-off-by: Sasha Levin --- drivers/gpu/drm/vc4/vc4_hvs.c | 11 +++++++++++ drivers/gpu/drm/vc4/vc4_regs.h | 6 ++++++ 2 files changed, 17 insertions(+) diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c index 95fa6fc052a7..f8f2fc3d15f7 100644 --- a/drivers/gpu/drm/vc4/vc4_hvs.c +++ b/drivers/gpu/drm/vc4/vc4_hvs.c @@ -677,6 +677,17 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data) SCALER_DISPCTRL_DSPEISLUR(2) | SCALER_DISPCTRL_SCLEIRQ); + /* Set AXI panic mode. + * VC4 panics when < 2 lines in FIFO. + * VC5 panics when less than 1 line in the FIFO. + */ + dispctrl &= ~(SCALER_DISPCTRL_PANIC0_MASK | + SCALER_DISPCTRL_PANIC1_MASK | + SCALER_DISPCTRL_PANIC2_MASK); + dispctrl |= VC4_SET_FIELD(2, SCALER_DISPCTRL_PANIC0); + dispctrl |= VC4_SET_FIELD(2, SCALER_DISPCTRL_PANIC1); + dispctrl |= VC4_SET_FIELD(2, SCALER_DISPCTRL_PANIC2); + HVS_WRITE(SCALER_DISPCTRL, dispctrl); ret = devm_request_irq(dev, platform_get_irq(pdev, 0), diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h index be2c32a519b3..a324ef88ceaf 100644 --- a/drivers/gpu/drm/vc4/vc4_regs.h +++ b/drivers/gpu/drm/vc4/vc4_regs.h @@ -220,6 +220,12 @@ #define SCALER_DISPCTRL 0x00000000 /* Global register for clock gating the HVS */ # define SCALER_DISPCTRL_ENABLE BIT(31) +# define SCALER_DISPCTRL_PANIC0_MASK VC4_MASK(25, 24) +# define SCALER_DISPCTRL_PANIC0_SHIFT 24 +# define SCALER_DISPCTRL_PANIC1_MASK VC4_MASK(27, 26) +# define SCALER_DISPCTRL_PANIC1_SHIFT 26 +# define SCALER_DISPCTRL_PANIC2_MASK VC4_MASK(29, 28) +# define SCALER_DISPCTRL_PANIC2_SHIFT 28 # define SCALER_DISPCTRL_DSP3_MUX_MASK VC4_MASK(19, 18) # define SCALER_DISPCTRL_DSP3_MUX_SHIFT 18 From 15a6be1011c2965a3fbaaf2ce110c63d06351fe5 Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Wed, 7 Dec 2022 12:53:17 +0100 Subject: [PATCH 1663/4345] drm/vc4: hvs: Fix colour order for xRGB1555 on HVS5 [ Upstream commit 902973dc1a049c0d7bf0c222b8f2b3876f01b4a2 ] Same as the xRGB8888 formats, HVS5 has managed to swap the colour channels for the xRGB1555 formats as well. Add the relevant config for pixel_order_hvs5. Fixes: c54619b0bfb3 ("drm/vc4: Add support for the BCM2711 HVS5") Signed-off-by: Dave Stevenson Link: https://lore.kernel.org/r/20221207-rpi-hvs-crtc-misc-v1-6-1f8e0770798b@cerno.tech Signed-off-by: Maxime Ripard Signed-off-by: Sasha Levin --- drivers/gpu/drm/vc4/vc4_plane.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 4df222a83049..2e03c16c60bb 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -72,11 +72,13 @@ static const struct hvs_format { .drm = DRM_FORMAT_ARGB1555, .hvs = HVS_PIXEL_FORMAT_RGBA5551, .pixel_order = HVS_PIXEL_ORDER_ABGR, + .pixel_order_hvs5 = HVS_PIXEL_ORDER_ARGB, }, { .drm = DRM_FORMAT_XRGB1555, .hvs = HVS_PIXEL_FORMAT_RGBA5551, .pixel_order = HVS_PIXEL_ORDER_ABGR, + .pixel_order_hvs5 = HVS_PIXEL_ORDER_ARGB, }, { .drm = DRM_FORMAT_RGB888, From d4438cbd9c04c7a5cee457193ece2e012cf9ed9b Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Wed, 7 Dec 2022 12:53:25 +0100 Subject: [PATCH 1664/4345] drm/vc4: hdmi: Correct interlaced timings again [ Upstream commit 771d6539f27bd55f43d8a95d53a7eeaaffa2681c ] The back porch timings were correct, only the sync offset was wrong. Correct timing is now reported for 1080i and 576i, but the h offset is incorrect for 480i for non-obvious reasons. Fixes: fb10dc451c0f ("drm/vc4: hdmi: Correct HDMI timing registers for interlaced modes") Signed-off-by: Dave Stevenson Link: https://lore.kernel.org/r/20221207-rpi-hvs-crtc-misc-v1-14-1f8e0770798b@cerno.tech Signed-off-by: Maxime Ripard Signed-off-by: Sasha Levin --- drivers/gpu/drm/vc4/vc4_hdmi.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 539ebf85fd7c..7e8620838de9 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -567,11 +567,12 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi, VC4_SET_FIELD(mode->crtc_vdisplay, VC5_HDMI_VERTA_VAL)); u32 vertb = (VC4_SET_FIELD(mode->htotal >> (2 - pixel_rep), VC5_HDMI_VERTB_VSPO) | - VC4_SET_FIELD(mode->crtc_vtotal - mode->crtc_vsync_end, + VC4_SET_FIELD(mode->crtc_vtotal - mode->crtc_vsync_end + + interlaced, VC4_HDMI_VERTB_VBP)); u32 vertb_even = (VC4_SET_FIELD(0, VC5_HDMI_VERTB_VSPO) | VC4_SET_FIELD(mode->crtc_vtotal - - mode->crtc_vsync_end - interlaced, + mode->crtc_vsync_end, VC4_HDMI_VERTB_VBP)); HDMI_WRITE(HDMI_VEC_INTERFACE_XBAR, 0x354021); From a3bf72eab8c8c2286fbcddb1d2776342f655332f Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Mon, 16 Jan 2023 15:07:54 +0800 Subject: [PATCH 1665/4345] ASoC: fsl_sai: initialize is_dsp_mode flag [ Upstream commit a23924b7dd7b748fff8e305e1daf590fed2af21b ] Initialize is_dsp_mode flag in the beginning of function fsl_sai_set_dai_fmt_tr(). When the DAIFMT is DAIFMT_DSP_B the first time, is_dsp_mode is true, then the second time DAIFMT is DAIFMT_I2S, is_dsp_mode still true, which is a wrong state. So need to initialize is_dsp_mode flag every time. Fixes: a3f7dcc9cc03 ("ASoC: fsl-sai: Add SND_SOC_DAIFMT_DSP_A/B support.") Signed-off-by: Shengjiu Wang Reviewed-by: Iuliana Prodan Link: https://lore.kernel.org/r/1673852874-32200-1-git-send-email-shengjiu.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_sai.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 3e5c1eaccd5e..6a5d2b08e271 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -230,6 +230,7 @@ static int fsl_sai_set_dai_fmt_tr(struct snd_soc_dai *cpu_dai, if (!sai->is_lsb_first) val_cr4 |= FSL_SAI_CR4_MF; + sai->is_dsp_mode = false; /* DAI mode */ switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_I2S: From b26bd7791f3cdf3c3318162b1d40c9d1910facca Mon Sep 17 00:00:00 2001 From: Akhil P Oommen Date: Wed, 21 Dec 2022 20:39:56 +0530 Subject: [PATCH 1666/4345] drm/msm/adreno: Fix null ptr access in adreno_gpu_cleanup() [ Upstream commit dbeedbcb268d055d8895aceca427f897e12c2b50 ] Fix the below kernel panic due to null pointer access: [ 18.504431] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000048 [ 18.513464] Mem abort info: [ 18.516346] ESR = 0x0000000096000005 [ 18.520204] EC = 0x25: DABT (current EL), IL = 32 bits [ 18.525706] SET = 0, FnV = 0 [ 18.528878] EA = 0, S1PTW = 0 [ 18.532117] FSC = 0x05: level 1 translation fault [ 18.537138] Data abort info: [ 18.540110] ISV = 0, ISS = 0x00000005 [ 18.544060] CM = 0, WnR = 0 [ 18.547109] user pgtable: 4k pages, 39-bit VAs, pgdp=0000000112826000 [ 18.553738] [0000000000000048] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000 [ 18.562690] Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP **Snip** [ 18.696758] Call trace: [ 18.699278] adreno_gpu_cleanup+0x30/0x88 [ 18.703396] a6xx_destroy+0xc0/0x130 [ 18.707066] a6xx_gpu_init+0x308/0x424 [ 18.710921] adreno_bind+0x178/0x288 [ 18.714590] component_bind_all+0xe0/0x214 [ 18.718797] msm_drm_bind+0x1d4/0x614 [ 18.722566] try_to_bring_up_aggregate_device+0x16c/0x1b8 [ 18.728105] __component_add+0xa0/0x158 [ 18.732048] component_add+0x20/0x2c [ 18.735719] adreno_probe+0x40/0xc0 [ 18.739300] platform_probe+0xb4/0xd4 [ 18.743068] really_probe+0xfc/0x284 [ 18.746738] __driver_probe_device+0xc0/0xec [ 18.751129] driver_probe_device+0x48/0x110 [ 18.755421] __device_attach_driver+0xa8/0xd0 [ 18.759900] bus_for_each_drv+0x90/0xdc [ 18.763843] __device_attach+0xfc/0x174 [ 18.767786] device_initial_probe+0x20/0x2c [ 18.772090] bus_probe_device+0x40/0xa0 [ 18.776032] deferred_probe_work_func+0x94/0xd0 [ 18.780686] process_one_work+0x190/0x3d0 [ 18.784805] worker_thread+0x280/0x3d4 [ 18.788659] kthread+0x104/0x1c0 [ 18.791981] ret_from_fork+0x10/0x20 [ 18.795654] Code: f9400408 aa0003f3 aa1f03f4 91142015 (f9402516) [ 18.801913] ---[ end trace 0000000000000000 ]--- [ 18.809039] Kernel panic - not syncing: Oops: Fatal exception Fixes: 17e822f7591f ("drm/msm: fix unbalanced pm_runtime_enable in adreno_gpu_{init, cleanup}") Signed-off-by: Akhil P Oommen Patchwork: https://patchwork.freedesktop.org/patch/515605/ Link: https://lore.kernel.org/r/20221221203925.v2.1.Ib978de92c4bd000b515486aad72e96c2481f84d0@changeid Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/adreno_gpu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index de8cc25506d6..78181e2d78a9 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -954,13 +954,13 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu) { struct msm_gpu *gpu = &adreno_gpu->base; - struct msm_drm_private *priv = gpu->dev->dev_private; + struct msm_drm_private *priv = gpu->dev ? gpu->dev->dev_private : NULL; unsigned int i; for (i = 0; i < ARRAY_SIZE(adreno_gpu->info->fw); i++) release_firmware(adreno_gpu->fw[i]); - if (pm_runtime_enabled(&priv->gpu_pdev->dev)) + if (priv && pm_runtime_enabled(&priv->gpu_pdev->dev)) pm_runtime_disable(&priv->gpu_pdev->dev); msm_gpu_cleanup(&adreno_gpu->base); From 42fdae9f59b181fbee772a1d85fef6b7ee2e03b7 Mon Sep 17 00:00:00 2001 From: "Alexey V. Vissarionov" Date: Tue, 17 Jan 2023 14:15:23 +0300 Subject: [PATCH 1667/4345] ALSA: hda/ca0132: minor fix for allocation size [ Upstream commit 3ee0fe7fa39b14d1cea455b7041f2df933bd97d2 ] Although the "dma_chan" pointer occupies more or equal space compared to "*dma_chan", the allocation size should use the size of variable itself. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 01ef7dbffb41 ("ALSA: hda - Update CA0132 codec to load DSP firmware binary") Signed-off-by: Alexey V. Vissarionov Link: https://lore.kernel.org/r/20230117111522.GA15213@altlinux.org Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_ca0132.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 82f14c3f642b..24c2638cde37 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -2331,7 +2331,7 @@ static int dspio_set_uint_param_no_source(struct hda_codec *codec, int mod_id, static int dspio_alloc_dma_chan(struct hda_codec *codec, unsigned int *dma_chan) { int status = 0; - unsigned int size = sizeof(dma_chan); + unsigned int size = sizeof(*dma_chan); codec_dbg(codec, " dspio_alloc_dma_chan() -- begin\n"); status = dspio_scp(codec, MASTERCONTROL, 0x20, From 8dbd54d679e3ab37be43bc1ed9f463dbf83a2259 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Tue, 10 Jan 2023 00:15:55 +0100 Subject: [PATCH 1668/4345] drm/msm/dpu: Disallow unallocated resources to be returned [ Upstream commit abc40122d9a69f56c04efb5a7485795f5ac799d1 ] In the event that the topology requests resources that have not been created by the system (because they are typically not represented in dpu_mdss_cfg ^1), the resource(s) in global_state (in this case DSC blocks, until their allocation/assignment is being sanity-checked in "drm/msm/dpu: Reject topologies for which no DSC blocks are available") remain NULL but will still be returned out of dpu_rm_get_assigned_resources, where the caller expects to get an array containing num_blks valid pointers (but instead gets these NULLs). To prevent this from happening, where null-pointer dereferences typically result in a hard-to-debug platform lockup, num_blks shouldn't increase past NULL blocks and will print an error and break instead. After all, max_blks represents the static size of the maximum number of blocks whereas the actual amount varies per platform. ^1: which can happen after a git rebase ended up moving additions to _dpu_cfg to a different struct which has the same patch context. Fixes: bb00a452d6f7 ("drm/msm/dpu: Refactor resource manager") Signed-off-by: Marijn Suijten Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/517636/ Link: https://lore.kernel.org/r/20230109231556.344977-1-marijn.suijten@somainline.org Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 74a13ccad34c..948300529743 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -633,6 +633,11 @@ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, blks_size, enc_id); break; } + if (!hw_blks[i]) { + DPU_ERROR("Allocated resource %d unavailable to assign to enc %d\n", + type, enc_id); + break; + } blks[num_blks++] = hw_blks[i]; } From 88618e800acf13f54ee435a132bd40466a02ea31 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 18 Jan 2023 10:16:46 +0200 Subject: [PATCH 1669/4345] drm/bridge: lt9611: fix sleep mode setup [ Upstream commit ae2d329f104b75a0a78dcaded29fe6283289cdf9 ] On atomic_post_disable the bridge goes to the low power state. However the code disables too much of the chip, so the HPD event is not being detected and delivered to the host. Reduce the power saving in order to get the HPD event. Fixes: 23278bf54afe ("drm/bridge: Introduce LT9611 DSI to HDMI bridge") Reviewed-by: Neil Armstrong Signed-off-by: Dmitry Baryshkov Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230118081658.2198520-2-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/lontium-lt9611.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 1dcc28a4d853..5e5641ac5ea3 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -446,12 +446,11 @@ static void lt9611_sleep_setup(struct lt9611 *lt9611) { 0x8023, 0x01 }, { 0x8157, 0x03 }, /* set addr pin as output */ { 0x8149, 0x0b }, - { 0x8151, 0x30 }, /* disable IRQ */ + { 0x8102, 0x48 }, /* MIPI Rx power down */ { 0x8123, 0x80 }, { 0x8130, 0x00 }, - { 0x8100, 0x01 }, /* bandgap power down */ - { 0x8101, 0x00 }, /* system clk power down */ + { 0x8011, 0x0a }, }; regmap_multi_reg_write(lt9611->regmap, From 3c865a014623f525acd822b00ee0804364802ce2 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 18 Jan 2023 10:16:47 +0200 Subject: [PATCH 1670/4345] drm/bridge: lt9611: fix HPD reenablement [ Upstream commit a7790f6bd38f3642b60ae3504a2c749135b89451 ] The driver will reset the bridge in the atomic_pre_enable(). However this will also drop the HPD interrupt state. Instead of resetting the bridge, properly wake it up. This fixes the HPD interrupt delivery after the disable/enable cycle. Fixes: 23278bf54afe ("drm/bridge: Introduce LT9611 DSI to HDMI bridge") Reviewed-by: Neil Armstrong Signed-off-by: Dmitry Baryshkov Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230118081658.2198520-3-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/lontium-lt9611.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 5e5641ac5ea3..fe660d667daf 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -880,12 +880,18 @@ static enum drm_mode_status lt9611_bridge_mode_valid(struct drm_bridge *bridge, static void lt9611_bridge_pre_enable(struct drm_bridge *bridge) { struct lt9611 *lt9611 = bridge_to_lt9611(bridge); + static const struct reg_sequence reg_cfg[] = { + { 0x8102, 0x12 }, + { 0x8123, 0x40 }, + { 0x8130, 0xea }, + { 0x8011, 0xfa }, + }; if (!lt9611->sleep) return; - lt9611_reset(lt9611); - regmap_write(lt9611->regmap, 0x80ee, 0x01); + regmap_multi_reg_write(lt9611->regmap, + reg_cfg, ARRAY_SIZE(reg_cfg)); lt9611->sleep = false; } From bffd0078026fd9578e41fb57cdec87d35629b5b1 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 18 Jan 2023 10:16:48 +0200 Subject: [PATCH 1671/4345] drm/bridge: lt9611: fix polarity programming [ Upstream commit 0b157efa384ea417304b1da284ee2f603c607fc3 ] Fix programming of hsync and vsync polarities Fixes: 23278bf54afe ("drm/bridge: Introduce LT9611 DSI to HDMI bridge") Reviewed-by: Neil Armstrong Signed-off-by: Dmitry Baryshkov Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230118081658.2198520-4-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/lontium-lt9611.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index fe660d667daf..4c56407c4cf0 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -205,7 +205,6 @@ static void lt9611_pcr_setup(struct lt9611 *lt9611, const struct drm_display_mod /* stage 2 */ { 0x834a, 0x40 }, - { 0x831d, 0x10 }, /* MK limit */ { 0x832d, 0x38 }, @@ -220,11 +219,19 @@ static void lt9611_pcr_setup(struct lt9611 *lt9611, const struct drm_display_mod { 0x8325, 0x00 }, { 0x832a, 0x01 }, { 0x834a, 0x10 }, - { 0x831d, 0x10 }, - { 0x8326, 0x37 }, }; + u8 pol = 0x10; - regmap_multi_reg_write(lt9611->regmap, reg_cfg, ARRAY_SIZE(reg_cfg)); + if (mode->flags & DRM_MODE_FLAG_NHSYNC) + pol |= 0x2; + if (mode->flags & DRM_MODE_FLAG_NVSYNC) + pol |= 0x1; + regmap_write(lt9611->regmap, 0x831d, pol); + + if (mode->hdisplay == 3840) + regmap_multi_reg_write(lt9611->regmap, reg_cfg2, ARRAY_SIZE(reg_cfg2)); + else + regmap_multi_reg_write(lt9611->regmap, reg_cfg, ARRAY_SIZE(reg_cfg)); switch (mode->hdisplay) { case 640: @@ -234,7 +241,7 @@ static void lt9611_pcr_setup(struct lt9611 *lt9611, const struct drm_display_mod regmap_write(lt9611->regmap, 0x8326, 0x37); break; case 3840: - regmap_multi_reg_write(lt9611->regmap, reg_cfg2, ARRAY_SIZE(reg_cfg2)); + regmap_write(lt9611->regmap, 0x8326, 0x37); break; } From aa37ec52c1a98c7cf757e5204d93bf0873c07b99 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 18 Jan 2023 10:16:49 +0200 Subject: [PATCH 1672/4345] drm/bridge: lt9611: fix programming of video modes [ Upstream commit ad188aa47edaa033a270e1a3efae43836ff47569 ] Program the upper part of the hfront_porch into the proper register. Fixes: 23278bf54afe ("drm/bridge: Introduce LT9611 DSI to HDMI bridge") Reviewed-by: Neil Armstrong Signed-off-by: Dmitry Baryshkov Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230118081658.2198520-5-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/lontium-lt9611.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 4c56407c4cf0..4925566dfc54 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -185,7 +185,8 @@ static void lt9611_mipi_video_setup(struct lt9611 *lt9611, regmap_write(lt9611->regmap, 0x8319, (u8)(hfront_porch % 256)); - regmap_write(lt9611->regmap, 0x831a, (u8)(hsync_porch / 256)); + regmap_write(lt9611->regmap, 0x831a, (u8)(hsync_porch / 256) | + ((hfront_porch / 256) << 4)); regmap_write(lt9611->regmap, 0x831b, (u8)(hsync_porch % 256)); } From ffd4cbd7eabd7c082504512ac90d236ee162b276 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 18 Jan 2023 10:16:50 +0200 Subject: [PATCH 1673/4345] drm/bridge: lt9611: fix clock calculation [ Upstream commit 2576eb26494eb0509dd9ceb0cd27771a7a5e3674 ] Instead of having several fixed values for the pcr register, calculate it before programming. This allows the bridge to support most of the display modes. Fixes: 23278bf54afe ("drm/bridge: Introduce LT9611 DSI to HDMI bridge") Reviewed-by: Neil Armstrong Signed-off-by: Dmitry Baryshkov Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230118081658.2198520-6-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/lontium-lt9611.c | 32 +++++++++++-------------- 1 file changed, 14 insertions(+), 18 deletions(-) diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 4925566dfc54..bb13511dd426 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -190,8 +190,9 @@ static void lt9611_mipi_video_setup(struct lt9611 *lt9611, regmap_write(lt9611->regmap, 0x831b, (u8)(hsync_porch % 256)); } -static void lt9611_pcr_setup(struct lt9611 *lt9611, const struct drm_display_mode *mode) +static void lt9611_pcr_setup(struct lt9611 *lt9611, const struct drm_display_mode *mode, unsigned int postdiv) { + unsigned int pcr_m = mode->clock * 5 * postdiv / 27000; const struct reg_sequence reg_cfg[] = { { 0x830b, 0x01 }, { 0x830c, 0x10 }, @@ -234,24 +235,14 @@ static void lt9611_pcr_setup(struct lt9611 *lt9611, const struct drm_display_mod else regmap_multi_reg_write(lt9611->regmap, reg_cfg, ARRAY_SIZE(reg_cfg)); - switch (mode->hdisplay) { - case 640: - regmap_write(lt9611->regmap, 0x8326, 0x14); - break; - case 1920: - regmap_write(lt9611->regmap, 0x8326, 0x37); - break; - case 3840: - regmap_write(lt9611->regmap, 0x8326, 0x37); - break; - } + regmap_write(lt9611->regmap, 0x8326, pcr_m); /* pcr rst */ regmap_write(lt9611->regmap, 0x8011, 0x5a); regmap_write(lt9611->regmap, 0x8011, 0xfa); } -static int lt9611_pll_setup(struct lt9611 *lt9611, const struct drm_display_mode *mode) +static int lt9611_pll_setup(struct lt9611 *lt9611, const struct drm_display_mode *mode, unsigned int *postdiv) { unsigned int pclk = mode->clock; const struct reg_sequence reg_cfg[] = { @@ -269,12 +260,16 @@ static int lt9611_pll_setup(struct lt9611 *lt9611, const struct drm_display_mode regmap_multi_reg_write(lt9611->regmap, reg_cfg, ARRAY_SIZE(reg_cfg)); - if (pclk > 150000) + if (pclk > 150000) { regmap_write(lt9611->regmap, 0x812d, 0x88); - else if (pclk > 70000) + *postdiv = 1; + } else if (pclk > 70000) { regmap_write(lt9611->regmap, 0x812d, 0x99); - else + *postdiv = 2; + } else { regmap_write(lt9611->regmap, 0x812d, 0xaa); + *postdiv = 4; + } /* * first divide pclk by 2 first @@ -917,14 +912,15 @@ static void lt9611_bridge_mode_set(struct drm_bridge *bridge, { struct lt9611 *lt9611 = bridge_to_lt9611(bridge); struct hdmi_avi_infoframe avi_frame; + unsigned int postdiv; int ret; lt9611_bridge_pre_enable(bridge); lt9611_mipi_input_digital(lt9611, mode); - lt9611_pll_setup(lt9611, mode); + lt9611_pll_setup(lt9611, mode, &postdiv); lt9611_mipi_video_setup(lt9611, mode); - lt9611_pcr_setup(lt9611, mode); + lt9611_pcr_setup(lt9611, mode, postdiv); ret = drm_hdmi_avi_infoframe_from_display_mode(&avi_frame, <9611->connector, From 10c58ca62a54bbf513b290f4ae05b26d9446a364 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 18 Jan 2023 10:16:51 +0200 Subject: [PATCH 1674/4345] drm/bridge: lt9611: pass a pointer to the of node [ Upstream commit b0a7f8736789935f62d6df32d441cdf05a5c05d2 ] Pass a pointer to the OF node while registering lt9611 MIPI device. Fixes: 23278bf54afe ("drm/bridge: Introduce LT9611 DSI to HDMI bridge") Reviewed-by: Neil Armstrong Signed-off-by: Dmitry Baryshkov Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230118081658.2198520-7-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/lontium-lt9611.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index bb13511dd426..0c6dea9ccb72 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -759,7 +759,7 @@ static const struct drm_connector_funcs lt9611_bridge_connector_funcs = { static struct mipi_dsi_device *lt9611_attach_dsi(struct lt9611 *lt9611, struct device_node *dsi_node) { - const struct mipi_dsi_device_info info = { "lt9611", 0, NULL }; + const struct mipi_dsi_device_info info = { "lt9611", 0, lt9611->dev->of_node}; struct mipi_dsi_device *dsi; struct mipi_dsi_host *host; int ret; From 23770064a339ae9130cbe03de4bf47989298de59 Mon Sep 17 00:00:00 2001 From: Daniel Mentz Date: Mon, 16 Jan 2023 17:49:07 -0500 Subject: [PATCH 1675/4345] drm/mipi-dsi: Fix byte order of 16-bit DCS set/get brightness [ Upstream commit c9d27c6be518b4ef2966d9564654ef99292ea1b3 ] The MIPI DCS specification demands that brightness values are sent in big endian byte order. It also states that one parameter (i.e. one byte) shall be sent/received for 8 bit wide values, and two parameters shall be used for values that are between 9 and 16 bits wide. Add new functions to properly handle 16-bit brightness in big endian, since the two 8- and 16-bit cases are distinct from each other. [richard: use separate functions instead of switch/case] [richard: split into 16-bit component] Fixes: 1a9d759331b8 ("drm/dsi: Implement DCS set/get display brightness") Signed-off-by: Daniel Mentz Link: https://android.googlesource.com/kernel/msm/+/754affd62d0ee268c686c53169b1dbb7deac8550 [richard: fix 16-bit brightness_get] Signed-off-by: Richard Acayan Tested-by: Caleb Connolly Reviewed-by: Neil Armstrong Reviewed-by: Sam Ravnborg Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230116224909.23884-2-mailingradian@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_mipi_dsi.c | 52 ++++++++++++++++++++++++++++++++++ include/drm/drm_mipi_dsi.h | 4 +++ 2 files changed, 56 insertions(+) diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 2c43d54766f3..19fb1d93a4f0 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -1143,6 +1143,58 @@ int mipi_dsi_dcs_get_display_brightness(struct mipi_dsi_device *dsi, } EXPORT_SYMBOL(mipi_dsi_dcs_get_display_brightness); +/** + * mipi_dsi_dcs_set_display_brightness_large() - sets the 16-bit brightness value + * of the display + * @dsi: DSI peripheral device + * @brightness: brightness value + * + * Return: 0 on success or a negative error code on failure. + */ +int mipi_dsi_dcs_set_display_brightness_large(struct mipi_dsi_device *dsi, + u16 brightness) +{ + u8 payload[2] = { brightness >> 8, brightness & 0xff }; + ssize_t err; + + err = mipi_dsi_dcs_write(dsi, MIPI_DCS_SET_DISPLAY_BRIGHTNESS, + payload, sizeof(payload)); + if (err < 0) + return err; + + return 0; +} +EXPORT_SYMBOL(mipi_dsi_dcs_set_display_brightness_large); + +/** + * mipi_dsi_dcs_get_display_brightness_large() - gets the current 16-bit + * brightness value of the display + * @dsi: DSI peripheral device + * @brightness: brightness value + * + * Return: 0 on success or a negative error code on failure. + */ +int mipi_dsi_dcs_get_display_brightness_large(struct mipi_dsi_device *dsi, + u16 *brightness) +{ + u8 brightness_be[2]; + ssize_t err; + + err = mipi_dsi_dcs_read(dsi, MIPI_DCS_GET_DISPLAY_BRIGHTNESS, + brightness_be, sizeof(brightness_be)); + if (err <= 0) { + if (err == 0) + err = -ENODATA; + + return err; + } + + *brightness = (brightness_be[0] << 8) | brightness_be[1]; + + return 0; +} +EXPORT_SYMBOL(mipi_dsi_dcs_get_display_brightness_large); + static int mipi_dsi_drv_probe(struct device *dev) { struct mipi_dsi_driver *drv = to_mipi_dsi_driver(dev->driver); diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index 360e6377e84b..31ba85a4110a 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -283,6 +283,10 @@ int mipi_dsi_dcs_set_display_brightness(struct mipi_dsi_device *dsi, u16 brightness); int mipi_dsi_dcs_get_display_brightness(struct mipi_dsi_device *dsi, u16 *brightness); +int mipi_dsi_dcs_set_display_brightness_large(struct mipi_dsi_device *dsi, + u16 brightness); +int mipi_dsi_dcs_get_display_brightness_large(struct mipi_dsi_device *dsi, + u16 *brightness); /** * struct mipi_dsi_driver - DSI driver From 70bc4db1fb7b47ef17b5342529d022497a6e1e7d Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 18 Jan 2023 04:01:52 +0200 Subject: [PATCH 1676/4345] drm/msm: use strscpy instead of strncpy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d7fd8634f48d76aa799ed57beb7d87dab91bde80 ] Using strncpy can result in non-NULL-terminated destination string. Use strscpy instead. This fixes following warning: drivers/gpu/drm/msm/msm_fence.c: In function ‘msm_fence_context_alloc’: drivers/gpu/drm/msm/msm_fence.c:25:9: warning: ‘strncpy’ specified bound 32 equals destination size [-Wstringop-truncation] 25 | strncpy(fctx->name, name, sizeof(fctx->name)); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fixes: f97decac5f4c ("drm/msm: Support multiple ringbuffers") Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/518787/ Link: https://lore.kernel.org/r/20230118020152.1689213-1-dmitry.baryshkov@linaro.org Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/msm_fence.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c index cd59a5918038..50a25c119f4d 100644 --- a/drivers/gpu/drm/msm/msm_fence.c +++ b/drivers/gpu/drm/msm/msm_fence.c @@ -20,7 +20,7 @@ msm_fence_context_alloc(struct drm_device *dev, const char *name) return ERR_PTR(-ENOMEM); fctx->dev = dev; - strncpy(fctx->name, name, sizeof(fctx->name)); + strscpy(fctx->name, name, sizeof(fctx->name)); fctx->context = dma_fence_context_alloc(1); init_waitqueue_head(&fctx->event); spin_lock_init(&fctx->spinlock); From 31f2f8de0ea7387cde18a24f94ba5e0b886b9842 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Tue, 6 Dec 2022 16:05:17 +0800 Subject: [PATCH 1677/4345] drm/msm/dpu: Add check for cstate [ Upstream commit c96988b7d99327bb08bd9efd29a203b22cd88ace ] As kzalloc may fail and return NULL pointer, it should be better to check cstate in order to avoid the NULL pointer dereference in __drm_atomic_helper_crtc_reset. Fixes: 1cff7440a86e ("drm/msm: Convert to using __drm_atomic_helper_crtc_reset() for reset.") Signed-off-by: Jiasheng Jiang Reviewed-by: Abhinav Kumar Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/514163/ Link: https://lore.kernel.org/r/20221206080517.43786-1-jiasheng@iscas.ac.cn Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index f56414a06ec4..d6e9efed8b6a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -682,7 +682,10 @@ static void dpu_crtc_reset(struct drm_crtc *crtc) if (crtc->state) dpu_crtc_destroy_state(crtc, crtc->state); - __drm_atomic_helper_crtc_reset(crtc, &cstate->base); + if (cstate) + __drm_atomic_helper_crtc_reset(crtc, &cstate->base); + else + __drm_atomic_helper_crtc_reset(crtc, NULL); } /** From e9743b3052e125c44b555f07f2876a4bdccfd983 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Tue, 6 Dec 2022 16:02:36 +0800 Subject: [PATCH 1678/4345] drm/msm/dpu: Add check for pstates [ Upstream commit 93340e10b9c5fc86730d149636e0aa8b47bb5a34 ] As kzalloc may fail and return NULL pointer, it should be better to check pstates in order to avoid the NULL pointer dereference. Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Signed-off-by: Jiasheng Jiang Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/514160/ Link: https://lore.kernel.org/r/20221206080236.43687-1-jiasheng@iscas.ac.cn Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index d6e9efed8b6a..5afb3c544653 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -834,6 +834,8 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, struct drm_rect crtc_rect = { 0 }; pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL); + if (!pstates) + return -ENOMEM; if (!state->enable || !state->active) { DPU_DEBUG("crtc%d -> enable %d, active %d, skip atomic_check\n", From 49907c8873826ee771ba0ca1629e809c6479f617 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Tue, 6 Dec 2022 15:48:19 +0800 Subject: [PATCH 1679/4345] drm/msm/mdp5: Add check for kzalloc [ Upstream commit 13fcfcb2a9a4787fe4e49841d728f6f2e9fa6911 ] As kzalloc may fail and return NULL pointer, it should be better to check the return value in order to avoid the NULL pointer dereference. Fixes: 1cff7440a86e ("drm/msm: Convert to using __drm_atomic_helper_crtc_reset() for reset.") Signed-off-by: Jiasheng Jiang Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/514154/ Link: https://lore.kernel.org/r/20221206074819.18134-1-jiasheng@iscas.ac.cn Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index ff4f207cbdea..60e7371cd0e0 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -1124,7 +1124,10 @@ static void mdp5_crtc_reset(struct drm_crtc *crtc) if (crtc->state) mdp5_crtc_destroy_state(crtc, crtc->state); - __drm_atomic_helper_crtc_reset(crtc, &mdp5_cstate->base); + if (mdp5_cstate) + __drm_atomic_helper_crtc_reset(crtc, &mdp5_cstate->base); + else + __drm_atomic_helper_crtc_reset(crtc, NULL); } static const struct drm_crtc_funcs mdp5_crtc_no_lm_cursor_funcs = { From a46d29437b0a2a948d368758cd50396272be910c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 13 Jan 2023 23:53:50 +0200 Subject: [PATCH 1680/4345] pinctrl: bcm2835: Remove of_node_put() in bcm2835_of_gpio_ranges_fallback() [ Upstream commit 2d578dd27871372f7159dd3206149ec616700d87 ] Remove wrong of_node_put() in bcm2835_of_gpio_ranges_fallback(), there is no counterpart of_node_get() for it. Fixes: d2b67744fd99 ("pinctrl: bcm2835: implement hook for missing gpio-ranges") Signed-off-by: Andy Shevchenko Reviewed-by: Stefan Wahren Tested-by: Stefan Wahren Tested-by: Florian Fainelli Reviewed-by: Florian Fainelli Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20230113215352.44272-3-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/bcm/pinctrl-bcm2835.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index 39d2024dc2ee..c7ae9f900b53 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -356,8 +356,6 @@ static int bcm2835_of_gpio_ranges_fallback(struct gpio_chip *gc, { struct pinctrl_dev *pctldev = of_pinctrl_get(np); - of_node_put(np); - if (!pctldev) return 0; From d2eb2e7125143fc4531b938c2c47e365b9f1a436 Mon Sep 17 00:00:00 2001 From: Guodong Liu Date: Wed, 18 Jan 2023 14:20:35 +0800 Subject: [PATCH 1681/4345] pinctrl: mediatek: Initialize variable pullen and pullup to zero [ Upstream commit a298c70a10c604a6b3df5a0aa56597b705ba0f6b ] Coverity spotted that pullen and pullup is not initialized to zero in mtk_pctrl_show_one_pin. The uninitialized variable pullen is used in assignment statement "rsel = pullen;" in mtk_pctrl_show_one_pin, and Uninitialized variable pullup is used when calling scnprintf. Fix this coverity by initializing pullen and pullup as zero. Fixes: 184d8e13f9b1 ("pinctrl: mediatek: Add support for pin configuration dump via debugfs.") Signed-off-by: Guodong Liu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230118062036.26258-2-Guodong.Liu@mediatek.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/mediatek/pinctrl-paris.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c index d0a4ebbe1e7e..2a9d2801388d 100644 --- a/drivers/pinctrl/mediatek/pinctrl-paris.c +++ b/drivers/pinctrl/mediatek/pinctrl-paris.c @@ -574,7 +574,7 @@ static int mtk_hw_get_value_wrap(struct mtk_pinctrl *hw, unsigned int gpio, int ssize_t mtk_pctrl_show_one_pin(struct mtk_pinctrl *hw, unsigned int gpio, char *buf, unsigned int bufLen) { - int pinmux, pullup, pullen, len = 0, r1 = -1, r0 = -1; + int pinmux, pullup = 0, pullen = 0, len = 0, r1 = -1, r0 = -1; const struct mtk_pin_desc *desc; if (gpio >= hw->soc->npins) From 53f98ffcd89bf382ae3e4792cef5b1b25268424e Mon Sep 17 00:00:00 2001 From: Guodong Liu Date: Wed, 18 Jan 2023 14:20:36 +0800 Subject: [PATCH 1682/4345] pinctrl: mediatek: Initialize variable *buf to zero [ Upstream commit 2e34f82ba214134ecf590fbe0cdbd87401645a8a ] Coverity spotted that *buf is not initialized to zero in mtk_pctrl_dbg_show. Using uninitialized variable *buf as argument to %s when calling seq_printf. Fix this coverity by initializing *buf as zero. Fixes: 184d8e13f9b1 ("pinctrl: mediatek: Add support for pin configuration dump via debugfs.") Signed-off-by: Guodong Liu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230118062036.26258-3-Guodong.Liu@mediatek.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/mediatek/pinctrl-paris.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c index 2a9d2801388d..e486d66e220b 100644 --- a/drivers/pinctrl/mediatek/pinctrl-paris.c +++ b/drivers/pinctrl/mediatek/pinctrl-paris.c @@ -637,7 +637,7 @@ static void mtk_pctrl_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s, unsigned int gpio) { struct mtk_pinctrl *hw = pinctrl_dev_get_drvdata(pctldev); - char buf[PIN_DBG_BUF_SZ]; + char buf[PIN_DBG_BUF_SZ] = { 0 }; (void)mtk_pctrl_show_one_pin(hw, gpio, buf, PIN_DBG_BUF_SZ); From cfd710a7e5a53b3c537d6ba142bb9933bad87357 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 19 Jan 2023 15:39:00 +0200 Subject: [PATCH 1683/4345] gpu: host1x: Don't skip assigning syncpoints to channels [ Upstream commit eb258cc1fd458e584082be987dbc6ec42668c05e ] The code to write the syncpoint channel assignment register incorrectly skips the write if hypervisor registers are not available. The register, however, is within the guest aperture so remove the check and assign syncpoints properly even on virtualized systems. Fixes: c3f52220f276 ("gpu: host1x: Enable Tegra186 syncpoint protection") Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/gpu/host1x/hw/syncpt_hw.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/host1x/hw/syncpt_hw.c b/drivers/gpu/host1x/hw/syncpt_hw.c index dd39d67ccec3..8cf35b2eff3d 100644 --- a/drivers/gpu/host1x/hw/syncpt_hw.c +++ b/drivers/gpu/host1x/hw/syncpt_hw.c @@ -106,9 +106,6 @@ static void syncpt_assign_to_channel(struct host1x_syncpt *sp, #if HOST1X_HW >= 6 struct host1x *host = sp->host; - if (!host->hv_regs) - return; - host1x_sync_writel(host, HOST1X_SYNC_SYNCPT_CH_APP_CH(ch ? ch->id : 0xff), HOST1X_SYNC_SYNCPT_CH_APP(sp->id)); From da5fd53999335be8296410b41304457788a4b1cf Mon Sep 17 00:00:00 2001 From: Xinlei Lee Date: Tue, 10 Jan 2023 13:54:51 +0800 Subject: [PATCH 1684/4345] drm/mediatek: dsi: Reduce the time of dsi from LP11 to sending cmd [ Upstream commit 91aeaed2c1147e3b1157dc084d23f190856a6c23 ] According to Figure 16 Turnaround Procedure on page 36 in [1], you can see the status of LP-00 -> LP10 -> LP11. This state can correspond to the state of DSI from LP00 -> LP11 in mtk_dsi_lane_ready function in mtk_dsi.c. LP-00 -> LP10 -> LP11 takes about 2*TLPX time (refer to [1] page 51 to see that TLPX is 50ns) The delay at the end of the mtk_dsi_lane_ready function should be greater than the 2*TLPX specified by the DSI spec, and less than the time specified by the DSI_RX (generally 6ms to 40ms), to avoid problems caused by the RX specification [1]:mipi_D-PHY_specification_v1-1 Fixes: 39e8d062b03c ("drm/mediatek: Keep dsi as LP00 before dcs cmds transfer") Signed-off-by: Xinlei Lee Acked-by: Sam Ravnborg Reviewed-by: AngeloGioacchino Del Regno Link: https://patchwork.kernel.org/project/linux-mediatek/patch/1673330093-6771-2-git-send-email-xinlei.lee@mediatek.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_dsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 146c4d04f572..a6e71b7b69b8 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -704,7 +704,7 @@ static void mtk_dsi_lane_ready(struct mtk_dsi *dsi) mtk_dsi_clk_ulp_mode_leave(dsi); mtk_dsi_lane0_ulp_mode_leave(dsi); mtk_dsi_clk_hs_mode(dsi, 0); - msleep(20); + usleep_range(1000, 3000); /* The reaction time after pulling up the mipi signal for dsi_rx */ } } From 55bc7babc094db91342a8dc98270fe240e35e96b Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Wed, 11 Jan 2023 10:44:41 +0800 Subject: [PATCH 1685/4345] drm/mediatek: Use NULL instead of 0 for NULL pointer [ Upstream commit 4744cde06f57dd6fbaac468663b1fe2f653eaa16 ] Use NULL for NULL pointer to fix the following sparse warning: drivers/gpu/drm/mediatek/mtk_drm_gem.c:265:27: sparse: warning: Using plain integer as NULL pointer Fixes: 3df64d7b0a4f ("drm/mediatek: Implement gem prime vmap/vunmap function") Signed-off-by: Miles Chen Reviewed-by: AngeloGioacchino Del Regno Link: https://patchwork.kernel.org/project/linux-mediatek/patch/20230111024443.24559-1-miles.chen@mediatek.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_drm_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 0583e557ad37..43c54dde2f3f 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -266,6 +266,6 @@ void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr) return; vunmap(vaddr); - mtk_gem->kvaddr = 0; + mtk_gem->kvaddr = NULL; kfree(mtk_gem->pages); } From 3a50d86696f6a7305b84987a9096ed111bf85e8f Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 19 Jan 2023 15:12:55 -0800 Subject: [PATCH 1686/4345] drm/mediatek: Drop unbalanced obj unref [ Upstream commit 4deef811828e87e26a978d5d6433b261d4713849 ] In the error path, mtk_drm_gem_object_mmap() is dropping an obj reference that it doesn't own. Fixes: 119f5173628a ("drm/mediatek: Add DRM Driver for Mediatek SoC MT8173.") Signed-off-by: Rob Clark Link: https://patchwork.kernel.org/project/linux-mediatek/patch/20230119231255.2883365-1-robdclark@gmail.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_drm_gem.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 43c54dde2f3f..29702dd8631d 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -142,8 +142,6 @@ static int mtk_drm_gem_object_mmap(struct drm_gem_object *obj, ret = dma_mmap_attrs(priv->dma_dev, vma, mtk_gem->cookie, mtk_gem->dma_addr, obj->size, mtk_gem->dma_attrs); - if (ret) - drm_gem_vm_close(vma); return ret; } From b64b6dff15a38468b8cd33fc7864fa4e02b0933a Mon Sep 17 00:00:00 2001 From: ruanjinjie Date: Mon, 5 Dec 2022 17:51:15 +0800 Subject: [PATCH 1687/4345] drm/mediatek: mtk_drm_crtc: Add checks for devm_kcalloc [ Upstream commit 5bf1e3bd7da625ccf9a22c8cb7d65271e6e47f4c ] As the devm_kcalloc may return NULL, the return value needs to be checked to avoid NULL poineter dereference. Fixes: 31c5558dae05 ("drm/mediatek: Refactor plane init") Signed-off-by: ruanjinjie Reviewed-by: AngeloGioacchino Del Regno Link: https://patchwork.kernel.org/project/linux-mediatek/patch/20221205095115.2905090-1-ruanjinjie@huawei.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_drm_crtc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index dfd5ed15a7f4..e83b1c406b96 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -803,6 +803,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, mtk_crtc->planes = devm_kcalloc(dev, num_comp_planes, sizeof(struct drm_plane), GFP_KERNEL); + if (!mtk_crtc->planes) + return -ENOMEM; for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) { ret = mtk_drm_crtc_init_comp_planes(drm_dev, mtk_crtc, i, From 6a89ddee1686a8872384aaa9f0bcfa6b675acd86 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?= Date: Tue, 22 Nov 2022 09:39:49 -0500 Subject: [PATCH 1688/4345] drm/mediatek: Clean dangling pointer on bind error path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 36aa8c61af55675ed967900fbe5deb32d776f051 ] mtk_drm_bind() can fail, in which case drm_dev_put() is called, destroying the drm_device object. However a pointer to it was still being held in the private object, and that pointer would be passed along to DRM in mtk_drm_sys_prepare() if a suspend were triggered at that point, resulting in a panic. Clean the pointer when destroying the object in the error path to prevent this from happening. Fixes: 119f5173628a ("drm/mediatek: Add DRM Driver for Mediatek SoC MT8173.") Signed-off-by: Nícolas F. R. A. Prado Reviewed-by: AngeloGioacchino Del Regno Link: https://patchwork.kernel.org/project/linux-mediatek/patch/20221122143949.3493104-1-nfraprado@collabora.com/ Signed-off-by: Chun-Kuang Hu Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 59c85c63b7cc..719c46d245dd 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -378,6 +378,7 @@ static int mtk_drm_bind(struct device *dev) err_deinit: mtk_drm_kms_deinit(drm); err_free: + private->drm = NULL; drm_dev_put(drm); return ret; } From f2f6e683d9e76b2678a39b5d18a29098a41dc281 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 23 Jan 2023 23:17:20 +0000 Subject: [PATCH 1689/4345] ASoC: soc-compress.c: fixup private_data on snd_soc_new_compress() [ Upstream commit ffe4c0f0bfaa571a676a0e946d4a6a0607f94294 ] commit d3268a40d4b19f ("ASoC: soc-compress.c: fix NULL dereference") enables DPCM capture, but it should independent from playback. This patch fixup it. Fixes: d3268a40d4b1 ("ASoC: soc-compress.c: fix NULL dereference") Link: https://lore.kernel.org/r/87tu0i6j7j.wl-kuninori.morimoto.gx@renesas.com Acked-by: Charles Keepax Acked-by: Pierre-Louis Bossart Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/871qnkvo1s.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/soc-compress.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index d0f3ff8edd90..8f4ebb189e01 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -822,7 +822,7 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->fe_compr = 1; if (rtd->dai_link->dpcm_playback) be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd; - else if (rtd->dai_link->dpcm_capture) + if (rtd->dai_link->dpcm_capture) be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd; memcpy(compr->ops, &soc_compr_dyn_ops, sizeof(soc_compr_dyn_ops)); } else { From 33033f392d8122a94074472191f961243079a14c Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Tue, 20 Dec 2022 17:02:47 +0800 Subject: [PATCH 1690/4345] gpio: vf610: connect GPIO label to dev name [ Upstream commit 6f8ecb7f85f441eb7d78ba2a4df45ee8a821934e ] Current GPIO label is fixed, so can't distinguish different GPIO controllers through labels. Use dev name instead. Fixes: 7f2691a19627 ("gpio: vf610: add gpiolib/IRQ chip driver for Vybrid") Signed-off-by: Clark Wang Signed-off-by: Haibo Chen Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpio-vf610.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index 1ae612c796ee..396a687e020f 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -304,7 +304,7 @@ static int vf610_gpio_probe(struct platform_device *pdev) gc = &port->gc; gc->of_node = np; gc->parent = dev; - gc->label = "vf610-gpio"; + gc->label = dev_name(dev); gc->ngpio = VF610_GPIO_PER_PORT; gc->base = of_alias_get_id(np, "gpio") * VF610_GPIO_PER_PORT; From b33ca7b7bb66332e3498d0e3f3d912af5cbcc465 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 30 Jan 2023 15:01:40 +0100 Subject: [PATCH 1691/4345] spi: dw_bt1: fix MUX_MMIO dependencies [ Upstream commit d4bde04318c0d33705e9a77d4c7df72f262011e0 ] Selecting a symbol with additional dependencies requires adding the same dependency here: WARNING: unmet direct dependencies detected for MUX_MMIO Depends on [n]: MULTIPLEXER [=y] && OF [=n] Selected by [y]: - SPI_DW_BT1 [=y] && SPI [=y] && SPI_MASTER [=y] && SPI_DESIGNWARE [=y] && (MIPS_BAIKAL_T1 || COMPILE_TEST [=y]) Drop the 'select' here to avoid the problem. Anyone using the dw-bt1 SPI driver should make sure they include the mux driver as well now. Fixes: 7218838109fe ("spi: dw-bt1: Fix undefined devm_mux_control_get symbol") Fixes: abf00907538e ("spi: dw: Add Baikal-T1 SPI Controller glue driver") Link: https://lore.kernel.org/all/20221218192523.c6vnfo26ua6xqf26@mobilestation/ Signed-off-by: Arnd Bergmann Reviewed-by: Serge Semin Link: https://lore.kernel.org/r/20230130140156.3620863-1-arnd@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index aadaea052f51..4d98ce7571df 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -256,7 +256,6 @@ config SPI_DW_BT1 tristate "Baikal-T1 SPI driver for DW SPI core" depends on MIPS_BAIKAL_T1 || COMPILE_TEST select MULTIPLEXER - select MUX_MMIO help Baikal-T1 SoC is equipped with three DW APB SSI-based MMIO SPI controllers. Two of them are pretty much normal: with IRQ, DMA, From 1983a70778eb999f62fe4d6dfa8bcfefe0b7f47f Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Mon, 30 Jan 2023 14:06:40 +0200 Subject: [PATCH 1692/4345] ASoC: mchp-spdifrx: fix controls which rely on rsr register [ Upstream commit fa09fa60385abbf99342494b280da8b4aebbc0e9 ] The SPDIFRX block is clocked by 2 clocks: peripheral and generic clocks. Peripheral clock feeds user interface (registers) and generic clock feeds the receiver. To enable the receiver the generic clock needs to be enabled and also the ENABLE bit of MCHP_SPDIFRX_MR register need to be set. The signal control exported by mchp-spdifrx driver reports wrong status when the receiver is disabled. This can happen when requesting the signal and the capture was not previously started. To solve this the receiver needs to be enabled (by enabling generic clock and setting ENABLE bit of MR register) before reading the signal status. As with this fix there are 2 paths now that need to control the generic clock and ENABLE bit of SPDIFRX_MR register (one path though controls, one path though configuration) a mutex has been introduced. We can't rely on subsystem locking as the controls are protected by struct snd_card::controls_rwsem semaphore and configuration is protected by a different lock (embedded in snd_pcm_stream_lock_irq()). The introduction of mutex is also extended to other controls which rely on SPDIFRX_RSR.ULOCK bit as it has been discovered experimentally that having both clocks enabled but not the receiver (through ENABLE bit of SPDIFRX.MR) leads to inconsistent values of SPDIFRX_RSR.ULOCK. Thus on some controls we rely on software state (dev->trigger_enabled protected by mutex) to retrieve proper values. Fixes: ef265c55c1ac ("ASoC: mchp-spdifrx: add driver for SPDIF RX") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230130120647.638049-2-claudiu.beznea@microchip.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/atmel/mchp-spdifrx.c | 190 ++++++++++++++++++++++++--------- 1 file changed, 141 insertions(+), 49 deletions(-) diff --git a/sound/soc/atmel/mchp-spdifrx.c b/sound/soc/atmel/mchp-spdifrx.c index 46f3407ed0e8..c83f32a462f6 100644 --- a/sound/soc/atmel/mchp-spdifrx.c +++ b/sound/soc/atmel/mchp-spdifrx.c @@ -233,11 +233,13 @@ struct mchp_spdifrx_dev { struct mchp_spdifrx_mixer_control control; spinlock_t blockend_lock; /* protect access to blockend_refcount */ int blockend_refcount; + struct mutex mlock; struct device *dev; struct regmap *regmap; struct clk *pclk; struct clk *gclk; unsigned int fmt; + unsigned int trigger_enabled; unsigned int gclk_enabled:1; }; @@ -353,47 +355,40 @@ static int mchp_spdifrx_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { struct mchp_spdifrx_dev *dev = snd_soc_dai_get_drvdata(dai); - u32 mr; - int running; - int ret; - - regmap_read(dev->regmap, SPDIFRX_MR, &mr); - running = !!(mr & SPDIFRX_MR_RXEN_ENABLE); + int ret = 0; switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - if (!running) { - mr &= ~SPDIFRX_MR_RXEN_MASK; - mr |= SPDIFRX_MR_RXEN_ENABLE; - /* enable overrun interrupts */ - regmap_write(dev->regmap, SPDIFRX_IER, - SPDIFRX_IR_OVERRUN); - } + mutex_lock(&dev->mlock); + /* Enable overrun interrupts */ + regmap_write(dev->regmap, SPDIFRX_IER, SPDIFRX_IR_OVERRUN); + + /* Enable receiver. */ + regmap_update_bits(dev->regmap, SPDIFRX_MR, SPDIFRX_MR_RXEN_MASK, + SPDIFRX_MR_RXEN_ENABLE); + dev->trigger_enabled = true; + mutex_unlock(&dev->mlock); break; case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - if (running) { - mr &= ~SPDIFRX_MR_RXEN_MASK; - mr |= SPDIFRX_MR_RXEN_DISABLE; - /* disable overrun interrupts */ - regmap_write(dev->regmap, SPDIFRX_IDR, - SPDIFRX_IR_OVERRUN); - } + mutex_lock(&dev->mlock); + /* Disable overrun interrupts */ + regmap_write(dev->regmap, SPDIFRX_IDR, SPDIFRX_IR_OVERRUN); + + /* Disable receiver. */ + regmap_update_bits(dev->regmap, SPDIFRX_MR, SPDIFRX_MR_RXEN_MASK, + SPDIFRX_MR_RXEN_DISABLE); + dev->trigger_enabled = false; + mutex_unlock(&dev->mlock); break; default: - return -EINVAL; + ret = -EINVAL; } - ret = regmap_write(dev->regmap, SPDIFRX_MR, mr); - if (ret) { - dev_err(dev->dev, "unable to enable/disable RX: %d\n", ret); - return ret; - } - - return 0; + return ret; } static int mchp_spdifrx_hw_params(struct snd_pcm_substream *substream, @@ -413,13 +408,6 @@ static int mchp_spdifrx_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - regmap_read(dev->regmap, SPDIFRX_MR, &mr); - - if (mr & SPDIFRX_MR_RXEN_ENABLE) { - dev_err(dev->dev, "PCM already running\n"); - return -EBUSY; - } - if (params_channels(params) != SPDIFRX_CHANNELS) { dev_err(dev->dev, "unsupported number of channels: %d\n", params_channels(params)); @@ -445,6 +433,13 @@ static int mchp_spdifrx_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } + mutex_lock(&dev->mlock); + if (dev->trigger_enabled) { + dev_err(dev->dev, "PCM already running\n"); + ret = -EBUSY; + goto unlock; + } + if (dev->gclk_enabled) { clk_disable_unprepare(dev->gclk); dev->gclk_enabled = 0; @@ -455,19 +450,24 @@ static int mchp_spdifrx_hw_params(struct snd_pcm_substream *substream, dev_err(dev->dev, "unable to set gclk min rate: rate %u * ratio %u + 1\n", params_rate(params), SPDIFRX_GCLK_RATIO_MIN); - return ret; + goto unlock; } ret = clk_prepare_enable(dev->gclk); if (ret) { dev_err(dev->dev, "unable to enable gclk: %d\n", ret); - return ret; + goto unlock; } dev->gclk_enabled = 1; dev_dbg(dev->dev, "GCLK range min set to %d\n", params_rate(params) * SPDIFRX_GCLK_RATIO_MIN + 1); - return regmap_write(dev->regmap, SPDIFRX_MR, mr); + ret = regmap_write(dev->regmap, SPDIFRX_MR, mr); + +unlock: + mutex_unlock(&dev->mlock); + + return ret; } static int mchp_spdifrx_hw_free(struct snd_pcm_substream *substream, @@ -475,10 +475,12 @@ static int mchp_spdifrx_hw_free(struct snd_pcm_substream *substream, { struct mchp_spdifrx_dev *dev = snd_soc_dai_get_drvdata(dai); + mutex_lock(&dev->mlock); if (dev->gclk_enabled) { clk_disable_unprepare(dev->gclk); dev->gclk_enabled = 0; } + mutex_unlock(&dev->mlock); return 0; } @@ -627,10 +629,24 @@ static int mchp_spdifrx_ulock_get(struct snd_kcontrol *kcontrol, u32 val; bool ulock_old = ctrl->ulock; - regmap_read(dev->regmap, SPDIFRX_RSR, &val); - ctrl->ulock = !(val & SPDIFRX_RSR_ULOCK); + mutex_lock(&dev->mlock); + + /* + * The RSR.ULOCK has wrong value if both pclk and gclk are enabled + * and the receiver is disabled. Thus we take into account the + * dev->trigger_enabled here to return a real status. + */ + if (dev->trigger_enabled) { + regmap_read(dev->regmap, SPDIFRX_RSR, &val); + ctrl->ulock = !(val & SPDIFRX_RSR_ULOCK); + } else { + ctrl->ulock = 0; + } + uvalue->value.integer.value[0] = ctrl->ulock; + mutex_unlock(&dev->mlock); + return ulock_old != ctrl->ulock; } @@ -643,8 +659,22 @@ static int mchp_spdifrx_badf_get(struct snd_kcontrol *kcontrol, u32 val; bool badf_old = ctrl->badf; - regmap_read(dev->regmap, SPDIFRX_RSR, &val); - ctrl->badf = !!(val & SPDIFRX_RSR_BADF); + mutex_lock(&dev->mlock); + + /* + * The RSR.ULOCK has wrong value if both pclk and gclk are enabled + * and the receiver is disabled. Thus we take into account the + * dev->trigger_enabled here to return a real status. + */ + if (dev->trigger_enabled) { + regmap_read(dev->regmap, SPDIFRX_RSR, &val); + ctrl->badf = !!(val & SPDIFRX_RSR_BADF); + } else { + ctrl->badf = 0; + } + + mutex_unlock(&dev->mlock); + uvalue->value.integer.value[0] = ctrl->badf; return badf_old != ctrl->badf; @@ -656,11 +686,48 @@ static int mchp_spdifrx_signal_get(struct snd_kcontrol *kcontrol, struct snd_soc_dai *dai = snd_kcontrol_chip(kcontrol); struct mchp_spdifrx_dev *dev = snd_soc_dai_get_drvdata(dai); struct mchp_spdifrx_mixer_control *ctrl = &dev->control; - u32 val; + u32 val = ~0U, loops = 10; + int ret; bool signal_old = ctrl->signal; - regmap_read(dev->regmap, SPDIFRX_RSR, &val); - ctrl->signal = !(val & SPDIFRX_RSR_NOSIGNAL); + mutex_lock(&dev->mlock); + + /* + * To get the signal we need to have receiver enabled. This + * could be enabled also from trigger() function thus we need to + * take care of not disabling the receiver when it runs. + */ + if (!dev->trigger_enabled) { + ret = clk_prepare_enable(dev->gclk); + if (ret) + goto unlock; + + regmap_update_bits(dev->regmap, SPDIFRX_MR, SPDIFRX_MR_RXEN_MASK, + SPDIFRX_MR_RXEN_ENABLE); + + /* Wait for RSR.ULOCK bit. */ + while (--loops) { + regmap_read(dev->regmap, SPDIFRX_RSR, &val); + if (!(val & SPDIFRX_RSR_ULOCK)) + break; + usleep_range(100, 150); + } + + regmap_update_bits(dev->regmap, SPDIFRX_MR, SPDIFRX_MR_RXEN_MASK, + SPDIFRX_MR_RXEN_DISABLE); + + clk_disable_unprepare(dev->gclk); + } else { + regmap_read(dev->regmap, SPDIFRX_RSR, &val); + } + +unlock: + mutex_unlock(&dev->mlock); + + if (!(val & SPDIFRX_RSR_ULOCK)) + ctrl->signal = !(val & SPDIFRX_RSR_NOSIGNAL); + else + ctrl->signal = 0; uvalue->value.integer.value[0] = ctrl->signal; return signal_old != ctrl->signal; @@ -685,18 +752,32 @@ static int mchp_spdifrx_rate_get(struct snd_kcontrol *kcontrol, u32 val; int rate; - regmap_read(dev->regmap, SPDIFRX_RSR, &val); + mutex_lock(&dev->mlock); - /* if the receiver is not locked, ISF data is invalid */ - if (val & SPDIFRX_RSR_ULOCK || !(val & SPDIFRX_RSR_IFS_MASK)) { + /* + * The RSR.ULOCK has wrong value if both pclk and gclk are enabled + * and the receiver is disabled. Thus we take into account the + * dev->trigger_enabled here to return a real status. + */ + if (dev->trigger_enabled) { + regmap_read(dev->regmap, SPDIFRX_RSR, &val); + /* If the receiver is not locked, ISF data is invalid. */ + if (val & SPDIFRX_RSR_ULOCK || !(val & SPDIFRX_RSR_IFS_MASK)) { + ucontrol->value.integer.value[0] = 0; + goto unlock; + } + } else { + /* Reveicer is not locked, IFS data is invalid. */ ucontrol->value.integer.value[0] = 0; - return 0; + goto unlock; } rate = clk_get_rate(dev->gclk); ucontrol->value.integer.value[0] = rate / (32 * SPDIFRX_RSR_IFS(val)); +unlock: + mutex_unlock(&dev->mlock); return 0; } @@ -912,7 +993,18 @@ static int mchp_spdifrx_probe(struct platform_device *pdev) "failed to get the PMC generated clock: %d\n", err); return err; } + + /* + * Signal control need a valid rate on gclk. hw_params() configures + * it propertly but requesting signal before any hw_params() has been + * called lead to invalid value returned for signal. Thus, configure + * gclk at a valid rate, here, in initialization, to simplify the + * control path. + */ + clk_set_min_rate(dev->gclk, 48000 * SPDIFRX_GCLK_RATIO_MIN + 1); + spin_lock_init(&dev->blockend_lock); + mutex_init(&dev->mlock); dev->dev = &pdev->dev; dev->regmap = regmap; From 426423ed55def0667770b05ef8fcb1b3f6fe9317 Mon Sep 17 00:00:00 2001 From: Gu Shengxian Date: Tue, 6 Jul 2021 18:02:30 +0800 Subject: [PATCH 1693/4345] ASoC: atmel: fix spelling mistakes [ Upstream commit 55233b22502151e0b2d9cc599e1ddf1f5584c87a ] Fix some spelling mistakes as follows: regaedles ==> regardless prezent ==> present underrrun ==> underrun controlls ==> controls Signed-off-by: Gu Shengxian Link: https://lore.kernel.org/r/20210706100230.32633-1-gushengxian507419@gmail.com Signed-off-by: Mark Brown Stable-dep-of: a4c4161d6eae ("ASoC: mchp-spdifrx: fix return value in case completion times out") Signed-off-by: Sasha Levin --- sound/soc/atmel/mchp-spdifrx.c | 6 +++--- sound/soc/atmel/mchp-spdiftx.c | 2 +- sound/soc/atmel/tse850-pcm5142.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/sound/soc/atmel/mchp-spdifrx.c b/sound/soc/atmel/mchp-spdifrx.c index c83f32a462f6..3962ce00ad34 100644 --- a/sound/soc/atmel/mchp-spdifrx.c +++ b/sound/soc/atmel/mchp-spdifrx.c @@ -56,7 +56,7 @@ /* Validity Bit Mode */ #define SPDIFRX_MR_VBMODE_MASK GENAMSK(1, 1) #define SPDIFRX_MR_VBMODE_ALWAYS_LOAD \ - (0 << 1) /* Load sample regardles of validity bit value */ + (0 << 1) /* Load sample regardless of validity bit value */ #define SPDIFRX_MR_VBMODE_DISCARD_IF_VB1 \ (1 << 1) /* Load sample only if validity bit is 0 */ @@ -523,7 +523,7 @@ static int mchp_spdifrx_cs_get(struct mchp_spdifrx_dev *dev, /* check for new data available */ ret = wait_for_completion_interruptible_timeout(&ch_stat->done, msecs_to_jiffies(100)); - /* IP might not be started or valid stream might not be prezent */ + /* IP might not be started or valid stream might not be present */ if (ret < 0) { dev_dbg(dev->dev, "channel status for channel %d timeout\n", channel); @@ -575,7 +575,7 @@ static int mchp_spdifrx_subcode_ch_get(struct mchp_spdifrx_dev *dev, mchp_spdifrx_isr_blockend_en(dev); ret = wait_for_completion_interruptible_timeout(&user_data->done, msecs_to_jiffies(100)); - /* IP might not be started or valid stream might not be prezent */ + /* IP might not be started or valid stream might not be present */ if (ret <= 0) { dev_dbg(dev->dev, "user data for channel %d timeout\n", channel); diff --git a/sound/soc/atmel/mchp-spdiftx.c b/sound/soc/atmel/mchp-spdiftx.c index 0d2e3fa21519..bcca1cf3cd7b 100644 --- a/sound/soc/atmel/mchp-spdiftx.c +++ b/sound/soc/atmel/mchp-spdiftx.c @@ -80,7 +80,7 @@ #define SPDIFTX_MR_VALID1 BIT(24) #define SPDIFTX_MR_VALID2 BIT(25) -/* Disable Null Frame on underrrun */ +/* Disable Null Frame on underrun */ #define SPDIFTX_MR_DNFR_MASK GENMASK(27, 27) #define SPDIFTX_MR_DNFR_INVALID (0 << 27) #define SPDIFTX_MR_DNFR_VALID (1 << 27) diff --git a/sound/soc/atmel/tse850-pcm5142.c b/sound/soc/atmel/tse850-pcm5142.c index 59e2edb22b3a..50c3dc6936f9 100644 --- a/sound/soc/atmel/tse850-pcm5142.c +++ b/sound/soc/atmel/tse850-pcm5142.c @@ -23,7 +23,7 @@ // IN2 +---o--+------------+--o---+ OUT2 // loop2 relays // -// The 'loop1' gpio pin controlls two relays, which are either in loop +// The 'loop1' gpio pin controls two relays, which are either in loop // position, meaning that input and output are directly connected, or // they are in mixer position, meaning that the signal is passed through // the 'Sum' mixer. Similarly for 'loop2'. From 45956f1764ca8067c1817fea060bf1835acc2cb8 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Mon, 30 Jan 2023 14:06:41 +0200 Subject: [PATCH 1694/4345] ASoC: mchp-spdifrx: fix return value in case completion times out [ Upstream commit a4c4161d6eae3ef5f486d1638ef452d9bc1376b0 ] wait_for_completion_interruptible_timeout() returns 0 in case of timeout. Check this into account when returning from function. Fixes: ef265c55c1ac ("ASoC: mchp-spdifrx: add driver for SPDIF RX") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230130120647.638049-3-claudiu.beznea@microchip.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/atmel/mchp-spdifrx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/sound/soc/atmel/mchp-spdifrx.c b/sound/soc/atmel/mchp-spdifrx.c index 3962ce00ad34..076a78fd0b12 100644 --- a/sound/soc/atmel/mchp-spdifrx.c +++ b/sound/soc/atmel/mchp-spdifrx.c @@ -524,9 +524,10 @@ static int mchp_spdifrx_cs_get(struct mchp_spdifrx_dev *dev, ret = wait_for_completion_interruptible_timeout(&ch_stat->done, msecs_to_jiffies(100)); /* IP might not be started or valid stream might not be present */ - if (ret < 0) { + if (ret <= 0) { dev_dbg(dev->dev, "channel status for channel %d timeout\n", channel); + return ret ? : -ETIMEDOUT; } memcpy(uvalue->value.iec958.status, ch_stat->data, @@ -580,7 +581,7 @@ static int mchp_spdifrx_subcode_ch_get(struct mchp_spdifrx_dev *dev, dev_dbg(dev->dev, "user data for channel %d timeout\n", channel); mchp_spdifrx_isr_blockend_dis(dev); - return ret; + return ret ? : -ETIMEDOUT; } spin_lock_irqsave(&user_data->lock, flags); From d8f5539b5e7f37a522c69d7561d2419a435363b6 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Mon, 30 Jan 2023 14:06:42 +0200 Subject: [PATCH 1695/4345] ASoC: mchp-spdifrx: fix controls that works with completion mechanism [ Upstream commit d3681df44e856aab523a6eb7ba15b5e41efcbb1c ] Channel status get and channel subcode get controls relies on data returned by controls when certain IRQs are raised. To achieve that completions are used b/w controls and interrupt service routine. The concurrent accesses to these controls are protected by struct snd_card::controls_rwsem. Issues identified: - reinit_completion() may be called while waiting for completion which should be avoided - in case of multiple threads waiting, the complete() call in interrupt will signal only one waiting thread per interrupt which may lead to timeout for the others - in case of channel status get as the CSC interrupt is not refcounted ISR may disable interrupt for threads that were just enabled it. To solve these the access to controls were protected by a mutex. Along with this there is no need for spinlock to protect the software cache reads/updates b/w controls and ISR as the update is happening only when requested from control, and only one reader can reach the control. Fixes: ef265c55c1ac ("ASoC: mchp-spdifrx: add driver for SPDIF RX") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230130120647.638049-4-claudiu.beznea@microchip.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/atmel/mchp-spdifrx.c | 143 ++++++++++++++++++--------------- 1 file changed, 77 insertions(+), 66 deletions(-) diff --git a/sound/soc/atmel/mchp-spdifrx.c b/sound/soc/atmel/mchp-spdifrx.c index 076a78fd0b12..eb1b8724e11f 100644 --- a/sound/soc/atmel/mchp-spdifrx.c +++ b/sound/soc/atmel/mchp-spdifrx.c @@ -217,7 +217,6 @@ struct mchp_spdifrx_ch_stat { struct mchp_spdifrx_user_data { unsigned char data[SPDIFRX_UD_BITS / 8]; struct completion done; - spinlock_t lock; /* protect access to user data */ }; struct mchp_spdifrx_mixer_control { @@ -231,8 +230,6 @@ struct mchp_spdifrx_mixer_control { struct mchp_spdifrx_dev { struct snd_dmaengine_dai_dma_data capture; struct mchp_spdifrx_mixer_control control; - spinlock_t blockend_lock; /* protect access to blockend_refcount */ - int blockend_refcount; struct mutex mlock; struct device *dev; struct regmap *regmap; @@ -277,37 +274,11 @@ static void mchp_spdifrx_channel_user_data_read(struct mchp_spdifrx_dev *dev, } } -/* called from non-atomic context only */ -static void mchp_spdifrx_isr_blockend_en(struct mchp_spdifrx_dev *dev) -{ - unsigned long flags; - - spin_lock_irqsave(&dev->blockend_lock, flags); - dev->blockend_refcount++; - /* don't enable BLOCKEND interrupt if it's already enabled */ - if (dev->blockend_refcount == 1) - regmap_write(dev->regmap, SPDIFRX_IER, SPDIFRX_IR_BLOCKEND); - spin_unlock_irqrestore(&dev->blockend_lock, flags); -} - -/* called from atomic/non-atomic context */ -static void mchp_spdifrx_isr_blockend_dis(struct mchp_spdifrx_dev *dev) -{ - unsigned long flags; - - spin_lock_irqsave(&dev->blockend_lock, flags); - dev->blockend_refcount--; - /* don't enable BLOCKEND interrupt if it's already enabled */ - if (dev->blockend_refcount == 0) - regmap_write(dev->regmap, SPDIFRX_IDR, SPDIFRX_IR_BLOCKEND); - spin_unlock_irqrestore(&dev->blockend_lock, flags); -} - static irqreturn_t mchp_spdif_interrupt(int irq, void *dev_id) { struct mchp_spdifrx_dev *dev = dev_id; struct mchp_spdifrx_mixer_control *ctrl = &dev->control; - u32 sr, imr, pending, idr = 0; + u32 sr, imr, pending; irqreturn_t ret = IRQ_NONE; int ch; @@ -322,13 +293,10 @@ static irqreturn_t mchp_spdif_interrupt(int irq, void *dev_id) if (pending & SPDIFRX_IR_BLOCKEND) { for (ch = 0; ch < SPDIFRX_CHANNELS; ch++) { - spin_lock(&ctrl->user_data[ch].lock); mchp_spdifrx_channel_user_data_read(dev, ch); - spin_unlock(&ctrl->user_data[ch].lock); - complete(&ctrl->user_data[ch].done); } - mchp_spdifrx_isr_blockend_dis(dev); + regmap_write(dev->regmap, SPDIFRX_IDR, SPDIFRX_IR_BLOCKEND); ret = IRQ_HANDLED; } @@ -336,7 +304,7 @@ static irqreturn_t mchp_spdif_interrupt(int irq, void *dev_id) if (pending & SPDIFRX_IR_CSC(ch)) { mchp_spdifrx_channel_status_read(dev, ch); complete(&ctrl->ch_stat[ch].done); - idr |= SPDIFRX_IR_CSC(ch); + regmap_write(dev->regmap, SPDIFRX_IDR, SPDIFRX_IR_CSC(ch)); ret = IRQ_HANDLED; } } @@ -346,8 +314,6 @@ static irqreturn_t mchp_spdif_interrupt(int irq, void *dev_id) ret = IRQ_HANDLED; } - regmap_write(dev->regmap, SPDIFRX_IDR, idr); - return ret; } @@ -517,23 +483,51 @@ static int mchp_spdifrx_cs_get(struct mchp_spdifrx_dev *dev, { struct mchp_spdifrx_mixer_control *ctrl = &dev->control; struct mchp_spdifrx_ch_stat *ch_stat = &ctrl->ch_stat[channel]; - int ret; + int ret = 0; - regmap_write(dev->regmap, SPDIFRX_IER, SPDIFRX_IR_CSC(channel)); - /* check for new data available */ - ret = wait_for_completion_interruptible_timeout(&ch_stat->done, - msecs_to_jiffies(100)); - /* IP might not be started or valid stream might not be present */ - if (ret <= 0) { - dev_dbg(dev->dev, "channel status for channel %d timeout\n", - channel); - return ret ? : -ETIMEDOUT; + mutex_lock(&dev->mlock); + + /* + * We may reach this point with both clocks enabled but the receiver + * still disabled. To void waiting for completion and return with + * timeout check the dev->trigger_enabled. + * + * To retrieve data: + * - if the receiver is enabled CSC IRQ will update the data in software + * caches (ch_stat->data) + * - otherwise we just update it here the software caches with latest + * available information and return it; in this case we don't need + * spin locking as the IRQ is disabled and will not be raised from + * anywhere else. + */ + + if (dev->trigger_enabled) { + reinit_completion(&ch_stat->done); + regmap_write(dev->regmap, SPDIFRX_IER, SPDIFRX_IR_CSC(channel)); + /* Check for new data available */ + ret = wait_for_completion_interruptible_timeout(&ch_stat->done, + msecs_to_jiffies(100)); + /* Valid stream might not be present */ + if (ret <= 0) { + dev_dbg(dev->dev, "channel status for channel %d timeout\n", + channel); + regmap_write(dev->regmap, SPDIFRX_IDR, SPDIFRX_IR_CSC(channel)); + ret = ret ? : -ETIMEDOUT; + goto unlock; + } else { + ret = 0; + } + } else { + /* Update software cache with latest channel status. */ + mchp_spdifrx_channel_status_read(dev, channel); } memcpy(uvalue->value.iec958.status, ch_stat->data, sizeof(ch_stat->data)); - return 0; +unlock: + mutex_unlock(&dev->mlock); + return ret; } static int mchp_spdifrx_cs1_get(struct snd_kcontrol *kcontrol, @@ -567,29 +561,49 @@ static int mchp_spdifrx_subcode_ch_get(struct mchp_spdifrx_dev *dev, int channel, struct snd_ctl_elem_value *uvalue) { - unsigned long flags; struct mchp_spdifrx_mixer_control *ctrl = &dev->control; struct mchp_spdifrx_user_data *user_data = &ctrl->user_data[channel]; - int ret; + int ret = 0; - reinit_completion(&user_data->done); - mchp_spdifrx_isr_blockend_en(dev); - ret = wait_for_completion_interruptible_timeout(&user_data->done, - msecs_to_jiffies(100)); - /* IP might not be started or valid stream might not be present */ - if (ret <= 0) { - dev_dbg(dev->dev, "user data for channel %d timeout\n", - channel); - mchp_spdifrx_isr_blockend_dis(dev); - return ret ? : -ETIMEDOUT; + mutex_lock(&dev->mlock); + + /* + * We may reach this point with both clocks enabled but the receiver + * still disabled. To void waiting for completion to just timeout we + * check here the dev->trigger_enabled flag. + * + * To retrieve data: + * - if the receiver is enabled we need to wait for blockend IRQ to read + * data to and update it for us in software caches + * - otherwise reading the SPDIFRX_CHUD() registers is enough. + */ + + if (dev->trigger_enabled) { + reinit_completion(&user_data->done); + regmap_write(dev->regmap, SPDIFRX_IER, SPDIFRX_IR_BLOCKEND); + ret = wait_for_completion_interruptible_timeout(&user_data->done, + msecs_to_jiffies(100)); + /* Valid stream might not be present. */ + if (ret <= 0) { + dev_dbg(dev->dev, "user data for channel %d timeout\n", + channel); + regmap_write(dev->regmap, SPDIFRX_IDR, SPDIFRX_IR_BLOCKEND); + ret = ret ? : -ETIMEDOUT; + goto unlock; + } else { + ret = 0; + } + } else { + /* Update software cache with last available data. */ + mchp_spdifrx_channel_user_data_read(dev, channel); } - spin_lock_irqsave(&user_data->lock, flags); memcpy(uvalue->value.iec958.subcode, user_data->data, sizeof(user_data->data)); - spin_unlock_irqrestore(&user_data->lock, flags); - return 0; +unlock: + mutex_unlock(&dev->mlock); + return ret; } static int mchp_spdifrx_subcode_ch1_get(struct snd_kcontrol *kcontrol, @@ -890,11 +904,9 @@ static int mchp_spdifrx_dai_probe(struct snd_soc_dai *dai) SPDIFRX_MR_AUTORST_NOACTION | SPDIFRX_MR_PACK_DISABLED); - dev->blockend_refcount = 0; for (ch = 0; ch < SPDIFRX_CHANNELS; ch++) { init_completion(&ctrl->ch_stat[ch].done); init_completion(&ctrl->user_data[ch].done); - spin_lock_init(&ctrl->user_data[ch].lock); } /* Add controls */ @@ -1004,7 +1016,6 @@ static int mchp_spdifrx_probe(struct platform_device *pdev) */ clk_set_min_rate(dev->gclk, 48000 * SPDIFRX_GCLK_RATIO_MIN + 1); - spin_lock_init(&dev->blockend_lock); mutex_init(&dev->mlock); dev->dev = &pdev->dev; From ce07bbe038aead7d9fc996e52a5d92d0243abaac Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Mon, 30 Jan 2023 14:06:43 +0200 Subject: [PATCH 1696/4345] ASoC: mchp-spdifrx: disable all interrupts in mchp_spdifrx_dai_remove() [ Upstream commit aaecdc32b7e35b4f9b457fb3509414aa9a932589 ] CSC interrupts which might be used in controls are on bits 8 and 9 of SPDIFRX_IDR register. Thus disable all the interrupts that are exported by driver. Fixes: ef265c55c1ac ("ASoC: mchp-spdifrx: add driver for SPDIF RX") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230130120647.638049-5-claudiu.beznea@microchip.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/atmel/mchp-spdifrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/atmel/mchp-spdifrx.c b/sound/soc/atmel/mchp-spdifrx.c index eb1b8724e11f..03b7037239b8 100644 --- a/sound/soc/atmel/mchp-spdifrx.c +++ b/sound/soc/atmel/mchp-spdifrx.c @@ -921,7 +921,7 @@ static int mchp_spdifrx_dai_remove(struct snd_soc_dai *dai) struct mchp_spdifrx_dev *dev = snd_soc_dai_get_drvdata(dai); /* Disable interrupts */ - regmap_write(dev->regmap, SPDIFRX_IDR, 0xFF); + regmap_write(dev->regmap, SPDIFRX_IDR, GENMASK(14, 0)); clk_disable_unprepare(dev->pclk); From b4d74716da0079ce6c8241e8ad74c7b14450efe8 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 2 Feb 2023 09:34:19 -0700 Subject: [PATCH 1697/4345] ASoC: mchp-spdifrx: Fix uninitialized use of mr in mchp_spdifrx_hw_params() [ Upstream commit 218674a45930c700486d27b765bf2f1b43f8cbf7 ] Clang warns: ../sound/soc/atmel/mchp-spdifrx.c:455:3: error: variable 'mr' is uninitialized when used here [-Werror,-Wuninitialized] mr |= SPDIFRX_MR_ENDIAN_BIG; ^~ ../sound/soc/atmel/mchp-spdifrx.c:432:8: note: initialize the variable 'mr' to silence this warning u32 mr; ^ = 0 1 error generated. Zero initialize mr so that these bitwise OR and assignment operation works unconditionally. Fixes: fa09fa60385a ("ASoC: mchp-spdifrx: fix controls which rely on rsr register") Link: https://github.com/ClangBuiltLinux/linux/issues/1797 Signed-off-by: Nathan Chancellor Reviewed-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230202-mchp-spdifrx-fix-uninit-mr-v1-1-629a045d7a2f@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/atmel/mchp-spdifrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/atmel/mchp-spdifrx.c b/sound/soc/atmel/mchp-spdifrx.c index 03b7037239b8..39a3c2a33bdb 100644 --- a/sound/soc/atmel/mchp-spdifrx.c +++ b/sound/soc/atmel/mchp-spdifrx.c @@ -362,7 +362,7 @@ static int mchp_spdifrx_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct mchp_spdifrx_dev *dev = snd_soc_dai_get_drvdata(dai); - u32 mr; + u32 mr = 0; int ret; dev_dbg(dev->dev, "%s() rate=%u format=%#x width=%u channels=%u\n", From d9bcf67b8bb39e951e8e16c46e3a7274f3d3774f Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 2 Feb 2023 19:36:46 +0100 Subject: [PATCH 1698/4345] ASoC: dt-bindings: meson: fix gx-card codec node regex [ Upstream commit 480b26226873c88e482575ceb0d0a38d76e1be57 ] 'codec' is a valid node name when there is a single codec in the link. Fix the node regular expression to apply this. Fixes: fd00366b8e41 ("ASoC: meson: gx: add sound card dt-binding documentation") Signed-off-by: Jerome Brunet Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230202183653.486216-3-jbrunet@baylibre.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- .../devicetree/bindings/sound/amlogic,gx-sound-card.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/sound/amlogic,gx-sound-card.yaml b/Documentation/devicetree/bindings/sound/amlogic,gx-sound-card.yaml index 2e35aeaa8781..89e3819c6127 100644 --- a/Documentation/devicetree/bindings/sound/amlogic,gx-sound-card.yaml +++ b/Documentation/devicetree/bindings/sound/amlogic,gx-sound-card.yaml @@ -61,7 +61,7 @@ patternProperties: description: phandle of the CPU DAI patternProperties: - "^codec-[0-9]+$": + "^codec(-[0-9]+)?$": type: object description: |- Codecs: From 859bdc96ba89b253fc8e8997ef717b5c1e67c909 Mon Sep 17 00:00:00 2001 From: Jonathan Cormier Date: Thu, 26 Jan 2023 17:32:25 -0500 Subject: [PATCH 1699/4345] hwmon: (ltc2945) Handle error case in ltc2945_value_store [ Upstream commit 178b01eccfb0b8149682f61388400bd3d903dddc ] ltc2945_val_to_reg errors were not being handled which would have resulted in register being set to 0 (clamped) instead of being left alone. Fixes: 6700ce035f83 ("hwmon: Driver for Linear Technologies LTC2945") Signed-off-by: Jonathan Cormier Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/ltc2945.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/hwmon/ltc2945.c b/drivers/hwmon/ltc2945.c index ba9c868a8641..65d792f18425 100644 --- a/drivers/hwmon/ltc2945.c +++ b/drivers/hwmon/ltc2945.c @@ -248,6 +248,8 @@ static ssize_t ltc2945_value_store(struct device *dev, /* convert to register value, then clamp and write result */ regval = ltc2945_val_to_reg(dev, reg, val); + if (regval < 0) + return regval; if (is_power_reg(reg)) { regval = clamp_val(regval, 0, 0xffffff); regbuf[0] = regval >> 16; From 0cb8a92a880d4cae226f52a72fcde495ef655e9a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 6 Feb 2023 20:36:02 +0100 Subject: [PATCH 1700/4345] drm/amdgpu: fix enum odm_combine_mode mismatch [ Upstream commit 087bad7eb1f6945f8232f132953ecc2bda8bd38d ] A conversion from 'bool' to 'enum odm_combine_mode' was incomplete, and gcc warns about this with many instances of display/dc/dml/dcn20/display_mode_vba_20.c:3899:44: warning: implicit conversion from 'enum ' to 'enum odm_combine_mode' [-Wenum-conversion] 3899 | locals->ODMCombineEnablePerState[i][k] = false; Change the ones that we get a warning for, using the same numerical values to leave the behavior unchanged. Fixes: 5fc11598166d ("drm/amd/display: expand dml structs") Link: https://lore.kernel.org/all/20201026210039.3884312-3-arnd@kernel.org/ Link: https://lore.kernel.org/all/20210927100659.1431744-1-arnd@kernel.org/ Signed-off-by: Arnd Bergmann Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../amd/display/dc/dml/dcn20/display_mode_vba_20.c | 8 ++++---- .../amd/display/dc/dml/dcn20/display_mode_vba_20v2.c | 10 +++++----- .../amd/display/dc/dml/dcn21/display_mode_vba_21.c | 12 ++++++------ 3 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c index b3f0476899d3..14e7a59a9cd1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c @@ -3897,14 +3897,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2 * (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); - locals->ODMCombineEnablePerState[i][k] = false; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; if (mode_lib->vba.ODMCapability) { if (locals->PlaneRequiredDISPCLKWithoutODMCombine > mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity) { - locals->ODMCombineEnablePerState[i][k] = true; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; } else if (locals->HActive[k] > DCN20_MAX_420_IMAGE_WIDTH && locals->OutputFormat[k] == dm_420) { - locals->ODMCombineEnablePerState[i][k] = true; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; } } @@ -3957,7 +3957,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->RequiredDISPCLK[i][j] = 0.0; locals->DISPCLK_DPPCLK_Support[i][j] = true; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - locals->ODMCombineEnablePerState[i][k] = false; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled; if (locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k]) { locals->NoOfDPP[i][j][k] = 1; locals->RequiredDPPCLK[i][j][k] = locals->MinDPPCLKUsingSingleDPP[k] diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c index 1bcda7eba4a6..ee1c80366bd6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c @@ -3974,17 +3974,17 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2 * (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); - locals->ODMCombineEnablePerState[i][k] = false; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; if (mode_lib->vba.ODMCapability) { if (locals->PlaneRequiredDISPCLKWithoutODMCombine > MaxMaxDispclkRoundedDown) { - locals->ODMCombineEnablePerState[i][k] = true; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; } else if (locals->DSCEnabled[k] && (locals->HActive[k] > DCN20_MAX_DSC_IMAGE_WIDTH)) { - locals->ODMCombineEnablePerState[i][k] = true; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; } else if (locals->HActive[k] > DCN20_MAX_420_IMAGE_WIDTH && locals->OutputFormat[k] == dm_420) { - locals->ODMCombineEnablePerState[i][k] = true; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; } } @@ -4037,7 +4037,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode locals->RequiredDISPCLK[i][j] = 0.0; locals->DISPCLK_DPPCLK_Support[i][j] = true; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - locals->ODMCombineEnablePerState[i][k] = false; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled; if (locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k]) { locals->NoOfDPP[i][j][k] = 1; locals->RequiredDPPCLK[i][j][k] = locals->MinDPPCLKUsingSingleDPP[k] diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c index c09bca335068..25693e62db80 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c @@ -3975,17 +3975,17 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2 * (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0); - locals->ODMCombineEnablePerState[i][k] = false; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine; if (mode_lib->vba.ODMCapability) { if (locals->PlaneRequiredDISPCLKWithoutODMCombine > MaxMaxDispclkRoundedDown) { - locals->ODMCombineEnablePerState[i][k] = true; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; } else if (locals->DSCEnabled[k] && (locals->HActive[k] > DCN21_MAX_DSC_IMAGE_WIDTH)) { - locals->ODMCombineEnablePerState[i][k] = true; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; } else if (locals->HActive[k] > DCN21_MAX_420_IMAGE_WIDTH && locals->OutputFormat[k] == dm_420) { - locals->ODMCombineEnablePerState[i][k] = true; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine; } } @@ -4038,7 +4038,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l locals->RequiredDISPCLK[i][j] = 0.0; locals->DISPCLK_DPPCLK_Support[i][j] = true; for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) { - locals->ODMCombineEnablePerState[i][k] = false; + locals->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled; if (locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k]) { locals->NoOfDPP[i][j][k] = 1; locals->RequiredDPPCLK[i][j][k] = locals->MinDPPCLKUsingSingleDPP[k] @@ -5213,7 +5213,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.ODMCombineEnabled[k] = locals->ODMCombineEnablePerState[mode_lib->vba.VoltageLevel][k]; } else { - mode_lib->vba.ODMCombineEnabled[k] = false; + mode_lib->vba.ODMCombineEnabled[k] = dm_odm_combine_mode_disabled; } mode_lib->vba.DSCEnabled[k] = locals->RequiresDSC[mode_lib->vba.VoltageLevel][k]; From 30c7c72b6cf9d8c95f9b219c9d2e4e31b15bebe5 Mon Sep 17 00:00:00 2001 From: Tomas Henzl Date: Tue, 7 Feb 2023 16:21:59 +0100 Subject: [PATCH 1701/4345] scsi: mpt3sas: Fix a memory leak [ Upstream commit 54dd96015e8d7a2a07359e2dfebf05b529d1780c ] Add a forgotten kfree(). Fixes: dbec4c9040ed ("scsi: mpt3sas: lockless command submission") Link: https://lore.kernel.org/r/20230207152159.18627-1-thenzl@redhat.com Signed-off-by: Tomas Henzl Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_base.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index c1b76cda60db..2ad75c9a9088 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -4905,6 +4905,9 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc) } dma_pool_destroy(ioc->pcie_sgl_dma_pool); } + kfree(ioc->pcie_sg_lookup); + ioc->pcie_sg_lookup = NULL; + if (ioc->config_page) { dexitprintk(ioc, ioc_info(ioc, "config_page(0x%p): free\n", From ca769960cb570b539acdd00e6b9cf0f9b5c5c66d Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Sat, 28 Jan 2023 19:08:32 +0800 Subject: [PATCH 1702/4345] scsi: aic94xx: Add missing check for dma_map_single() [ Upstream commit 32fe45274edb5926abc0fac7263d9f889d02d9cf ] Add check for dma_map_single() and return error if it fails in order to avoid invalid DMA address. Fixes: 2908d778ab3e ("[SCSI] aic94xx: new driver") Link: https://lore.kernel.org/r/20230128110832.6792-1-jiasheng@iscas.ac.cn Signed-off-by: Jiasheng Jiang Reviewed-by: Jason Yan Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/aic94xx/aic94xx_task.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/aic94xx/aic94xx_task.c b/drivers/scsi/aic94xx/aic94xx_task.c index f923ed019d4a..593b167ceefe 100644 --- a/drivers/scsi/aic94xx/aic94xx_task.c +++ b/drivers/scsi/aic94xx/aic94xx_task.c @@ -50,6 +50,9 @@ static int asd_map_scatterlist(struct sas_task *task, dma_addr_t dma = dma_map_single(&asd_ha->pcidev->dev, p, task->total_xfer_len, task->data_dir); + if (dma_mapping_error(&asd_ha->pcidev->dev, dma)) + return -ENOMEM; + sg_arr[0].bus_addr = cpu_to_le64((u64)dma); sg_arr[0].size = cpu_to_le32(task->total_xfer_len); sg_arr[0].flags |= ASD_SG_EL_LIST_EOL; From 59b0ce292a0990316abbf21490c6b88b814bb6f0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Tue, 23 Feb 2021 16:18:51 +0100 Subject: [PATCH 1703/4345] spi: bcm63xx-hsspi: fix pm_runtime MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 216e8e80057a9f0b6366327881acf88eaf9f1fd4 ] The driver sets auto_runtime_pm to true, but it doesn't call pm_runtime_enable(), which results in "Failed to power device" when PM support is enabled. Signed-off-by: Álvaro Fernández Rojas Link: https://lore.kernel.org/r/20210223151851.4110-3-noltari@gmail.com Signed-off-by: Mark Brown Stable-dep-of: 811ff802aaf8 ("spi: bcm63xx-hsspi: Fix multi-bit mode setting") Signed-off-by: Sasha Levin --- drivers/spi/spi-bcm63xx-hsspi.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c index 1f08d7553f07..b871fd810d80 100644 --- a/drivers/spi/spi-bcm63xx-hsspi.c +++ b/drivers/spi/spi-bcm63xx-hsspi.c @@ -21,6 +21,7 @@ #include #include #include +#include #define HSSPI_GLOBAL_CTRL_REG 0x0 #define GLOBAL_CTRL_CS_POLARITY_SHIFT 0 @@ -439,13 +440,17 @@ static int bcm63xx_hsspi_probe(struct platform_device *pdev) if (ret) goto out_put_master; + pm_runtime_enable(&pdev->dev); + /* register and we are done */ ret = devm_spi_register_master(dev, master); if (ret) - goto out_put_master; + goto out_pm_disable; return 0; +out_pm_disable: + pm_runtime_disable(&pdev->dev); out_put_master: spi_master_put(master); out_disable_pll_clk: From a79f1e71e7b57329b157569037d3f8e98be9bd6e Mon Sep 17 00:00:00 2001 From: William Zhang Date: Thu, 9 Feb 2023 12:02:41 -0800 Subject: [PATCH 1704/4345] spi: bcm63xx-hsspi: Fix multi-bit mode setting [ Upstream commit 811ff802aaf878ebbbaeac0307a0164fa21e7d40 ] Currently the driver always sets the controller to dual data bit mode for both tx and rx data in the profile mode control register even for single data bit transfer. Luckily the opcode is set correctly according to SPI transfer data bit width so it does not actually cause issues. This change fixes the problem by setting tx and rx data bit mode field correctly according to the actual SPI transfer tx and rx data bit width. Fixes: 142168eba9dc ("spi: bcm63xx-hsspi: add bcm63xx HSSPI driver") Signed-off-by: William Zhang Link: https://lore.kernel.org/r/20230209200246.141520-11-william.zhang@broadcom.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-bcm63xx-hsspi.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c index b871fd810d80..02f56fc001b4 100644 --- a/drivers/spi/spi-bcm63xx-hsspi.c +++ b/drivers/spi/spi-bcm63xx-hsspi.c @@ -163,6 +163,7 @@ static int bcm63xx_hsspi_do_txrx(struct spi_device *spi, struct spi_transfer *t) int step_size = HSSPI_BUFFER_LEN; const u8 *tx = t->tx_buf; u8 *rx = t->rx_buf; + u32 val = 0; bcm63xx_hsspi_set_clk(bs, spi, t->speed_hz); bcm63xx_hsspi_set_cs(bs, spi->chip_select, true); @@ -178,11 +179,16 @@ static int bcm63xx_hsspi_do_txrx(struct spi_device *spi, struct spi_transfer *t) step_size -= HSSPI_OPCODE_LEN; if ((opcode == HSSPI_OP_READ && t->rx_nbits == SPI_NBITS_DUAL) || - (opcode == HSSPI_OP_WRITE && t->tx_nbits == SPI_NBITS_DUAL)) + (opcode == HSSPI_OP_WRITE && t->tx_nbits == SPI_NBITS_DUAL)) { opcode |= HSSPI_OP_MULTIBIT; - __raw_writel(1 << MODE_CTRL_MULTIDATA_WR_SIZE_SHIFT | - 1 << MODE_CTRL_MULTIDATA_RD_SIZE_SHIFT | 0xff, + if (t->rx_nbits == SPI_NBITS_DUAL) + val |= 1 << MODE_CTRL_MULTIDATA_RD_SIZE_SHIFT; + if (t->tx_nbits == SPI_NBITS_DUAL) + val |= 1 << MODE_CTRL_MULTIDATA_WR_SIZE_SHIFT; + } + + __raw_writel(val | 0xff, bs->regs + HSSPI_PROFILE_MODE_CTRL_REG(chip_select)); while (pending > 0) { From 4c6d18ea71d86efbdf8861628699af050fb71868 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Sun, 12 Feb 2023 16:57:30 +0200 Subject: [PATCH 1705/4345] hwmon: (mlxreg-fan) Return zero speed for broken fan [ Upstream commit a1ffd3c46267ee5c807acd780e15df9bb692223f ] Currently for broken fan driver returns value calculated based on error code (0xFF) in related fan speed register. Thus, for such fan user gets fan{n}_fault to 1 and fan{n}_input with misleading value. Add check for fan fault prior return speed value and return zero if fault is detected. Fixes: 65afb4c8e7e4 ("hwmon: (mlxreg-fan) Add support for Mellanox FAN driver") Signed-off-by: Vadim Pasternak Link: https://lore.kernel.org/r/20230212145730.24247-1-vadimp@nvidia.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/mlxreg-fan.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c index bd8f5a3aaad9..052c897a635d 100644 --- a/drivers/hwmon/mlxreg-fan.c +++ b/drivers/hwmon/mlxreg-fan.c @@ -127,6 +127,12 @@ mlxreg_fan_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, if (err) return err; + if (MLXREG_FAN_GET_FAULT(regval, tacho->mask)) { + /* FAN is broken - return zero for FAN speed. */ + *val = 0; + return 0; + } + *val = MLXREG_FAN_GET_RPM(regval, fan->divider, fan->samples); break; From f23a4b9bf8950fd914c61c99e2189f3582909998 Mon Sep 17 00:00:00 2001 From: Steffen Aschbacher Date: Mon, 13 Feb 2023 09:38:05 +0200 Subject: [PATCH 1706/4345] ASoC: tlv320adcx140: fix 'ti,gpio-config' DT property init [ Upstream commit 771725efe5e2e5396dd9d1220437e5f9d6b9ca9d ] When the 'ti,gpio-config' property is not defined, the device_property_count_u32() will return an error, rather than zero. The current check, only handles a return value of zero, which assumes that the property is defined and has nothing defined. This change extends the check to also check for an error case (most likely to be hit by the case that the 'ti,gpio-config' is not defined). In case that the 'ti,gpio-config' and the returned 'gpio_count' is not correct, there is a 'if (gpio_count != ADCX140_NUM_GPIO_CFGS)' check, a few lines lower that will return -EINVAL. This means that someone tried to define 'ti,gpio-config', but with the wrong number of GPIOs. Fixes: d5214321498a ("ASoC: tlv320adcx140: Add support for configuring GPIO pin") Signed-off-by: Steffen Aschbacher Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20230213073805.14640-1-alex@shruggie.ro Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/tlv320adcx140.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/tlv320adcx140.c b/sound/soc/codecs/tlv320adcx140.c index 53a80246aee1..a6241a045369 100644 --- a/sound/soc/codecs/tlv320adcx140.c +++ b/sound/soc/codecs/tlv320adcx140.c @@ -870,7 +870,7 @@ static int adcx140_configure_gpio(struct adcx140_priv *adcx140) gpio_count = device_property_count_u32(adcx140->dev, "ti,gpio-config"); - if (gpio_count == 0) + if (gpio_count <= 0) return 0; if (gpio_count != ADCX140_NUM_GPIO_CFGS) From c550f65a54a0de1d8199e4dc146820d484856118 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 14 Feb 2023 13:06:05 -0500 Subject: [PATCH 1707/4345] dm: remove flush_scheduled_work() during local_exit() [ Upstream commit 0b22ff5360f5c4e11050b89206370fdf7dc0a226 ] Commit acfe0ad74d2e1 ("dm: allocate a special workqueue for deferred device removal") switched from using system workqueue to a single workqueue local to DM. But it didn't eliminate the call to flush_scheduled_work() that was introduced purely for the benefit of deferred device removal with commit 2c140a246dc ("dm: allow remove to be deferred"). Since DM core uses its own workqueue (and queue_work) there is no need to call flush_scheduled_work() from local_exit(). local_exit()'s destroy_workqueue(deferred_remove_workqueue) handles flushing work started with queue_work(). Fixes: acfe0ad74d2e1 ("dm: allocate a special workqueue for deferred device removal") Signed-off-by: Mike Snitzer Signed-off-by: Sasha Levin --- drivers/md/dm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1005abf76860..7163ecc4d53f 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -265,7 +265,6 @@ out_uevent_exit: static void local_exit(void) { - flush_scheduled_work(); destroy_workqueue(deferred_remove_workqueue); unregister_blkdev(_major, _name); From d601f782824e3541887cc4628c3aa61526bda431 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 25 Mar 2021 14:51:36 -0400 Subject: [PATCH 1708/4345] NFS: Fix up handling of outstanding layoutcommit in nfs_update_inode() [ Upstream commit 709fa5769914b377af87962bbe4ff81ffb019b2d ] If there is an outstanding layoutcommit, then the list of attributes whose values are expected to change is not the full set. So let's be explicit about the full list. Signed-off-by: Trond Myklebust Stable-dep-of: b46d80bd2d6e ("nfs4trace: fix state manager flag printing") Signed-off-by: Sasha Levin --- fs/nfs/inode.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 1adece1cff3e..36f415278c04 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1906,7 +1906,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_wcc_update_inode(inode, fattr); if (pnfs_layoutcommit_outstanding(inode)) { - nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_ATTR; + nfsi->cache_validity |= + save_cache_validity & + (NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | + NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | + NFS_INO_REVAL_FORCED); cache_revalidated = false; } From 6d434b4c49f05924d722e773ee02240b64ffe19d Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: [PATCH 1709/4345] NFSv4: keep state manager thread active if swap is enabled [ Upstream commit 4dc73c679114a2f408567e2e44770ed934190db2 ] If we are swapping over NFSv4, we may not be able to allocate memory to start the state-manager thread at the time when we need it. So keep it always running when swap is enabled, and just signal it to start. This requires updating and testing the cl_swapper count on the root rpc_clnt after following all ->cl_parent links. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust Stable-dep-of: b46d80bd2d6e ("nfs4trace: fix state manager flag printing") Signed-off-by: Sasha Levin --- fs/nfs/file.c | 15 ++++++++++++--- fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4proc.c | 20 ++++++++++++++++++++ fs/nfs/nfs4state.c | 40 +++++++++++++++++++++++++++++++++------- include/linux/nfs_xdr.h | 2 ++ net/sunrpc/clnt.c | 2 ++ 6 files changed, 70 insertions(+), 10 deletions(-) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index ad856b7b9a46..7be1a7f7fcb2 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -487,8 +487,9 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, { unsigned long blocks; long long isize; - struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host); - struct inode *inode = file->f_mapping->host; + struct inode *inode = file_inode(file); + struct rpc_clnt *clnt = NFS_CLIENT(inode); + struct nfs_client *cl = NFS_SERVER(inode)->nfs_client; spin_lock(&inode->i_lock); blocks = inode->i_blocks; @@ -501,14 +502,22 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, *span = sis->pages; + + if (cl->rpc_ops->enable_swap) + cl->rpc_ops->enable_swap(inode); + return rpc_clnt_swap_activate(clnt); } static void nfs_swap_deactivate(struct file *file) { - struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host); + struct inode *inode = file_inode(file); + struct rpc_clnt *clnt = NFS_CLIENT(inode); + struct nfs_client *cl = NFS_SERVER(inode)->nfs_client; rpc_clnt_swap_deactivate(clnt); + if (cl->rpc_ops->disable_swap) + cl->rpc_ops->disable_swap(file_inode(file)); } const struct address_space_operations nfs_file_aops = { diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 6d916563356e..8b41c0b8624e 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -42,6 +42,7 @@ enum nfs4_client_state { NFS4CLNT_LEASE_MOVED, NFS4CLNT_DELEGATION_EXPIRED, NFS4CLNT_RUN_MANAGER, + NFS4CLNT_MANAGER_AVAILABLE, NFS4CLNT_RECALL_RUNNING, NFS4CLNT_RECALL_ANY_LAYOUT_READ, NFS4CLNT_RECALL_ANY_LAYOUT_RW, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ee46ab09e330..8f502e2ac34f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10385,6 +10385,24 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) return error + error2 + error3; } +static void nfs4_enable_swap(struct inode *inode) +{ + /* The state manager thread must always be running. + * It will notice the client is a swapper, and stay put. + */ + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + + nfs4_schedule_state_manager(clp); +} + +static void nfs4_disable_swap(struct inode *inode) +{ + /* The state manager thread will now exit once it is + * woken. + */ + wake_up_var(&NFS_SERVER(inode)->nfs_client->cl_state); +} + static const struct inode_operations nfs4_dir_inode_operations = { .create = nfs_create, .lookup = nfs_lookup, @@ -10461,6 +10479,8 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .free_client = nfs4_free_client, .create_server = nfs4_create_server, .clone_server = nfs_clone_server, + .enable_swap = nfs4_enable_swap, + .disable_swap = nfs4_disable_swap, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 175b2e064003..628e030f8e3b 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1208,10 +1208,17 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + struct rpc_clnt *cl = clp->cl_rpcclient; + + while (cl != cl->cl_parent) + cl = cl->cl_parent; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); - if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { + wake_up_var(&clp->cl_state); return; + } + set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); __module_get(THIS_MODULE); refcount_inc(&clp->cl_count); @@ -1229,6 +1236,7 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) if (!nfs_client_init_is_complete(clp)) nfs_mark_client_ready(clp, PTR_ERR(task)); nfs4_clear_state_manager_bit(clp); + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs_put_client(clp); module_put(THIS_MODULE); } @@ -2680,12 +2688,8 @@ static void nfs4_state_manager(struct nfs_client *clp) clear_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state); } - /* Did we race with an attempt to give us more work? */ - if (!test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) - return; - if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) - return; - memflags = memalloc_nofs_save(); + return; + } while (refcount_read(&clp->cl_count) > 1 && !signalled()); goto out_drain; @@ -2706,9 +2710,31 @@ out_drain: static int nfs4_run_state_manager(void *ptr) { struct nfs_client *clp = ptr; + struct rpc_clnt *cl = clp->cl_rpcclient; + + while (cl != cl->cl_parent) + cl = cl->cl_parent; allow_signal(SIGKILL); +again: + set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); nfs4_state_manager(clp); + if (atomic_read(&cl->cl_swapper)) { + wait_var_event_interruptible(&clp->cl_state, + test_bit(NFS4CLNT_RUN_MANAGER, + &clp->cl_state)); + if (atomic_read(&cl->cl_swapper) && + test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + goto again; + /* Either no longer a swapper, or were signalled */ + } + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + + if (refcount_read(&clp->cl_count) > 1 && !signalled() && + test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && + !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state)) + goto again; + nfs_put_client(clp); module_put_and_exit(0); return 0; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5491ad5f48a9..33442fd018a0 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1789,6 +1789,8 @@ struct nfs_rpc_ops { struct nfs_server *(*create_server)(struct fs_context *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); + void (*enable_swap)(struct inode *inode); + void (*disable_swap)(struct inode *inode); }; /* diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index c478108ca6a6..e190d38c4c82 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -3026,6 +3026,8 @@ rpc_clnt_swap_activate_callback(struct rpc_clnt *clnt, int rpc_clnt_swap_activate(struct rpc_clnt *clnt) { + while (clnt != clnt->cl_parent) + clnt = clnt->cl_parent; if (atomic_inc_return(&clnt->cl_swapper) == 1) return rpc_clnt_iterate_for_each_xprt(clnt, rpc_clnt_swap_activate_callback, NULL); From 242df51a829185cef75c7bdb4495ebb1b19f7dfa Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 14 Feb 2023 08:18:23 -0500 Subject: [PATCH 1710/4345] nfs4trace: fix state manager flag printing [ Upstream commit b46d80bd2d6e7e063c625a20de54248afe8d4889 ] __print_flags wants a mask, not the enum value. Add two more flags. Fixes: 511ba52e4c01 ("NFS4: Trace state recovery operation") Signed-off-by: Benjamin Coddington Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs4trace.h | 42 ++++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 20 deletions(-) diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 484c1da96dea..d862df9761e7 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -584,32 +584,34 @@ TRACE_DEFINE_ENUM(NFS4CLNT_MOVED); TRACE_DEFINE_ENUM(NFS4CLNT_LEASE_MOVED); TRACE_DEFINE_ENUM(NFS4CLNT_DELEGATION_EXPIRED); TRACE_DEFINE_ENUM(NFS4CLNT_RUN_MANAGER); +TRACE_DEFINE_ENUM(NFS4CLNT_MANAGER_AVAILABLE); TRACE_DEFINE_ENUM(NFS4CLNT_RECALL_RUNNING); TRACE_DEFINE_ENUM(NFS4CLNT_RECALL_ANY_LAYOUT_READ); TRACE_DEFINE_ENUM(NFS4CLNT_RECALL_ANY_LAYOUT_RW); +TRACE_DEFINE_ENUM(NFS4CLNT_DELEGRETURN_DELAYED); #define show_nfs4_clp_state(state) \ __print_flags(state, "|", \ - { NFS4CLNT_MANAGER_RUNNING, "MANAGER_RUNNING" }, \ - { NFS4CLNT_CHECK_LEASE, "CHECK_LEASE" }, \ - { NFS4CLNT_LEASE_EXPIRED, "LEASE_EXPIRED" }, \ - { NFS4CLNT_RECLAIM_REBOOT, "RECLAIM_REBOOT" }, \ - { NFS4CLNT_RECLAIM_NOGRACE, "RECLAIM_NOGRACE" }, \ - { NFS4CLNT_DELEGRETURN, "DELEGRETURN" }, \ - { NFS4CLNT_SESSION_RESET, "SESSION_RESET" }, \ - { NFS4CLNT_LEASE_CONFIRM, "LEASE_CONFIRM" }, \ - { NFS4CLNT_SERVER_SCOPE_MISMATCH, \ - "SERVER_SCOPE_MISMATCH" }, \ - { NFS4CLNT_PURGE_STATE, "PURGE_STATE" }, \ - { NFS4CLNT_BIND_CONN_TO_SESSION, \ - "BIND_CONN_TO_SESSION" }, \ - { NFS4CLNT_MOVED, "MOVED" }, \ - { NFS4CLNT_LEASE_MOVED, "LEASE_MOVED" }, \ - { NFS4CLNT_DELEGATION_EXPIRED, "DELEGATION_EXPIRED" }, \ - { NFS4CLNT_RUN_MANAGER, "RUN_MANAGER" }, \ - { NFS4CLNT_RECALL_RUNNING, "RECALL_RUNNING" }, \ - { NFS4CLNT_RECALL_ANY_LAYOUT_READ, "RECALL_ANY_LAYOUT_READ" }, \ - { NFS4CLNT_RECALL_ANY_LAYOUT_RW, "RECALL_ANY_LAYOUT_RW" }) + { BIT(NFS4CLNT_MANAGER_RUNNING), "MANAGER_RUNNING" }, \ + { BIT(NFS4CLNT_CHECK_LEASE), "CHECK_LEASE" }, \ + { BIT(NFS4CLNT_LEASE_EXPIRED), "LEASE_EXPIRED" }, \ + { BIT(NFS4CLNT_RECLAIM_REBOOT), "RECLAIM_REBOOT" }, \ + { BIT(NFS4CLNT_RECLAIM_NOGRACE), "RECLAIM_NOGRACE" }, \ + { BIT(NFS4CLNT_DELEGRETURN), "DELEGRETURN" }, \ + { BIT(NFS4CLNT_SESSION_RESET), "SESSION_RESET" }, \ + { BIT(NFS4CLNT_LEASE_CONFIRM), "LEASE_CONFIRM" }, \ + { BIT(NFS4CLNT_SERVER_SCOPE_MISMATCH), "SERVER_SCOPE_MISMATCH" }, \ + { BIT(NFS4CLNT_PURGE_STATE), "PURGE_STATE" }, \ + { BIT(NFS4CLNT_BIND_CONN_TO_SESSION), "BIND_CONN_TO_SESSION" }, \ + { BIT(NFS4CLNT_MOVED), "MOVED" }, \ + { BIT(NFS4CLNT_LEASE_MOVED), "LEASE_MOVED" }, \ + { BIT(NFS4CLNT_DELEGATION_EXPIRED), "DELEGATION_EXPIRED" }, \ + { BIT(NFS4CLNT_RUN_MANAGER), "RUN_MANAGER" }, \ + { BIT(NFS4CLNT_MANAGER_AVAILABLE), "MANAGER_AVAILABLE" }, \ + { BIT(NFS4CLNT_RECALL_RUNNING), "RECALL_RUNNING" }, \ + { BIT(NFS4CLNT_RECALL_ANY_LAYOUT_READ), "RECALL_ANY_LAYOUT_READ" }, \ + { BIT(NFS4CLNT_RECALL_ANY_LAYOUT_RW), "RECALL_ANY_LAYOUT_RW" }, \ + { BIT(NFS4CLNT_DELEGRETURN_DELAYED), "DELERETURN_DELAYED" }) TRACE_EVENT(nfs4_state_mgr, TP_PROTO( From ac3a513d4fa888a3d3778419a19fe75cc856eade Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 8 Feb 2023 15:45:38 +1100 Subject: [PATCH 1711/4345] NFS: fix disabling of swap [ Upstream commit 5bab56fff53ce161ed859d9559a10361d4f79578 ] When swap is activated to a file on an NFSv4 mount we arrange that the state manager thread is always present as starting a new thread requires memory allocations that might block waiting for swap. Unfortunately the code for allowing the state manager thread to exit when swap is disabled was not tested properly and does not work. This can be seen by examining /proc/fs/nfsfs/servers after disabling swap and unmounting the filesystem. The servers file will still list one entry. Also a "ps" listing will show the state manager thread is still present. There are two problems. 1/ rpc_clnt_swap_deactivate() doesn't walk up the ->cl_parent list to find the primary client on which the state manager runs. 2/ The thread is not woken up properly and it immediately goes back to sleep without checking whether it is really needed. Using nfs4_schedule_state_manager() ensures a proper wake-up. Reported-by: Olga Kornievskaia Fixes: 4dc73c679114 ("NFSv4: keep state manager thread active if swap is enabled") Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs4proc.c | 4 +++- net/sunrpc/clnt.c | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8f502e2ac34f..8653335c17b6 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10400,7 +10400,9 @@ static void nfs4_disable_swap(struct inode *inode) /* The state manager thread will now exit once it is * woken. */ - wake_up_var(&NFS_SERVER(inode)->nfs_client->cl_state); + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + + nfs4_schedule_state_manager(clp); } static const struct inode_operations nfs4_dir_inode_operations = { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index e190d38c4c82..c6e8bd78e35d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -3047,6 +3047,8 @@ rpc_clnt_swap_deactivate_callback(struct rpc_clnt *clnt, void rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) { + while (clnt != clnt->cl_parent) + clnt = clnt->cl_parent; if (atomic_dec_if_positive(&clnt->cl_swapper) == 0) rpc_clnt_iterate_for_each_xprt(clnt, rpc_clnt_swap_deactivate_callback, NULL); From c785a87d9a7745b06ef48e0d4bc905a102b3272d Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 15 Feb 2023 14:01:28 +0100 Subject: [PATCH 1712/4345] spi: synquacer: Fix timeout handling in synquacer_spi_transfer_one() [ Upstream commit e6a0b671880207566e1ece983bf989dde60bc1d7 ] wait_for_completion_timeout() never returns a <0 value. It returns either on timeout or a positive value (at least 1, or number of jiffies left till timeout) So, fix the error handling path and return -ETIMEDOUT should a timeout occur. Fixes: b0823ee35cf9 ("spi: Add spi driver for Socionext SynQuacer platform") Signed-off-by: Christophe JAILLET Acked-by: Jassi Brar Link: https://lore.kernel.org/r/c2040bf3cfa201fd8890cfab14fa5a701ffeca14.1676466072.git.christophe.jaillet@wanadoo.fr Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-synquacer.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/spi/spi-synquacer.c b/drivers/spi/spi-synquacer.c index 47cbe73137c2..dc188f9202c9 100644 --- a/drivers/spi/spi-synquacer.c +++ b/drivers/spi/spi-synquacer.c @@ -472,10 +472,9 @@ static int synquacer_spi_transfer_one(struct spi_master *master, read_fifo(sspi); } - if (status < 0) { - dev_err(sspi->dev, "failed to transfer. status: 0x%x\n", - status); - return status; + if (status == 0) { + dev_err(sspi->dev, "failed to transfer. Timeout.\n"); + return -ETIMEDOUT; } return 0; From f69065e1bd901781d04f91b1cc95a980642f97b2 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 15 Feb 2023 13:28:51 +0000 Subject: [PATCH 1713/4345] ASoC: soc-dapm.h: fixup warning struct snd_pcm_substream not declared [ Upstream commit fdff966bfde7cf0c85562d2bfb1ff1ba83da5f7b ] Add struct snd_pcm_substream forward declaration Fixes: 078a85f2806f ("ASoC: dapm: Only power up active channels from a DAI") Signed-off-by: Lucas Tanure Reviewed-by: Charles Keepax Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230215132851.1626881-1-lucas.tanure@collabora.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- include/sound/soc-dapm.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index c3039e97929a..32e93d55acf7 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -16,6 +16,7 @@ #include struct device; +struct snd_pcm_substream; struct snd_soc_pcm_runtime; struct soc_enum; From 2ca8ae5cf61e5598dcbc5f66c114649660e997ec Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 18:59:59 +0000 Subject: [PATCH 1714/4345] HID: bigben: use spinlock to protect concurrent accesses [ Upstream commit 9fefb6201c4f8dd9f58c581b2a66e5cde2895ea2 ] bigben driver has a worker that may access data concurrently. Proct the accesses using a spinlock. Fixes: 256a90ed9e46 ("HID: hid-bigbenff: driver for BigBen Interactive PS3OFMINIPAD gamepad") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230125-hid-unregister-leds-v4-1-7860c5763c38@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-bigbenff.c | 52 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 50 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index e8b16665860d..ed3d2d7bc1dd 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -174,6 +174,7 @@ static __u8 pid0902_rdesc_fixed[] = { struct bigben_device { struct hid_device *hid; struct hid_report *report; + spinlock_t lock; bool removed; u8 led_state; /* LED1 = 1 .. LED4 = 8 */ u8 right_motor_on; /* right motor off/on 0/1 */ @@ -190,12 +191,27 @@ static void bigben_worker(struct work_struct *work) struct bigben_device *bigben = container_of(work, struct bigben_device, worker); struct hid_field *report_field = bigben->report->field[0]; + bool do_work_led = false; + bool do_work_ff = false; + u8 *buf; + u32 len; + unsigned long flags; if (bigben->removed || !report_field) return; + buf = hid_alloc_report_buf(bigben->report, GFP_KERNEL); + if (!buf) + return; + + len = hid_report_len(bigben->report); + + /* LED work */ + spin_lock_irqsave(&bigben->lock, flags); + if (bigben->work_led) { bigben->work_led = false; + do_work_led = true; report_field->value[0] = 0x01; /* 1 = led message */ report_field->value[1] = 0x08; /* reserved value, always 8 */ report_field->value[2] = bigben->led_state; @@ -204,11 +220,22 @@ static void bigben_worker(struct work_struct *work) report_field->value[5] = 0x00; /* padding */ report_field->value[6] = 0x00; /* padding */ report_field->value[7] = 0x00; /* padding */ - hid_hw_request(bigben->hid, bigben->report, HID_REQ_SET_REPORT); + hid_output_report(bigben->report, buf); } + spin_unlock_irqrestore(&bigben->lock, flags); + + if (do_work_led) { + hid_hw_raw_request(bigben->hid, bigben->report->id, buf, len, + bigben->report->type, HID_REQ_SET_REPORT); + } + + /* FF work */ + spin_lock_irqsave(&bigben->lock, flags); + if (bigben->work_ff) { bigben->work_ff = false; + do_work_ff = true; report_field->value[0] = 0x02; /* 2 = rumble effect message */ report_field->value[1] = 0x08; /* reserved value, always 8 */ report_field->value[2] = bigben->right_motor_on; @@ -217,8 +244,17 @@ static void bigben_worker(struct work_struct *work) report_field->value[5] = 0x00; /* padding */ report_field->value[6] = 0x00; /* padding */ report_field->value[7] = 0x00; /* padding */ - hid_hw_request(bigben->hid, bigben->report, HID_REQ_SET_REPORT); + hid_output_report(bigben->report, buf); } + + spin_unlock_irqrestore(&bigben->lock, flags); + + if (do_work_ff) { + hid_hw_raw_request(bigben->hid, bigben->report->id, buf, len, + bigben->report->type, HID_REQ_SET_REPORT); + } + + kfree(buf); } static int hid_bigben_play_effect(struct input_dev *dev, void *data, @@ -228,6 +264,7 @@ static int hid_bigben_play_effect(struct input_dev *dev, void *data, struct bigben_device *bigben = hid_get_drvdata(hid); u8 right_motor_on; u8 left_motor_force; + unsigned long flags; if (!bigben) { hid_err(hid, "no device data\n"); @@ -242,9 +279,12 @@ static int hid_bigben_play_effect(struct input_dev *dev, void *data, if (right_motor_on != bigben->right_motor_on || left_motor_force != bigben->left_motor_force) { + spin_lock_irqsave(&bigben->lock, flags); bigben->right_motor_on = right_motor_on; bigben->left_motor_force = left_motor_force; bigben->work_ff = true; + spin_unlock_irqrestore(&bigben->lock, flags); + schedule_work(&bigben->worker); } @@ -259,6 +299,7 @@ static void bigben_set_led(struct led_classdev *led, struct bigben_device *bigben = hid_get_drvdata(hid); int n; bool work; + unsigned long flags; if (!bigben) { hid_err(hid, "no device data\n"); @@ -267,6 +308,7 @@ static void bigben_set_led(struct led_classdev *led, for (n = 0; n < NUM_LEDS; n++) { if (led == bigben->leds[n]) { + spin_lock_irqsave(&bigben->lock, flags); if (value == LED_OFF) { work = (bigben->led_state & BIT(n)); bigben->led_state &= ~BIT(n); @@ -274,6 +316,7 @@ static void bigben_set_led(struct led_classdev *led, work = !(bigben->led_state & BIT(n)); bigben->led_state |= BIT(n); } + spin_unlock_irqrestore(&bigben->lock, flags); if (work) { bigben->work_led = true; @@ -307,8 +350,12 @@ static enum led_brightness bigben_get_led(struct led_classdev *led) static void bigben_remove(struct hid_device *hid) { struct bigben_device *bigben = hid_get_drvdata(hid); + unsigned long flags; + spin_lock_irqsave(&bigben->lock, flags); bigben->removed = true; + spin_unlock_irqrestore(&bigben->lock, flags); + cancel_work_sync(&bigben->worker); hid_hw_stop(hid); } @@ -362,6 +409,7 @@ static int bigben_probe(struct hid_device *hid, set_bit(FF_RUMBLE, hidinput->input->ffbit); INIT_WORK(&bigben->worker, bigben_worker); + spin_lock_init(&bigben->lock); error = input_ff_create_memless(hidinput->input, NULL, hid_bigben_play_effect); From ec8b79668ebf0df155b360b5480362f07cdd37d2 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 19:00:00 +0000 Subject: [PATCH 1715/4345] HID: bigben_worker() remove unneeded check on report_field [ Upstream commit 27d2a2fd844ec7da70d19fabb482304fd1e0595b ] bigben_worker() checks report_field to be non-NULL. The check has been added in commit 918aa1ef104d ("HID: bigbenff: prevent null pointer dereference") to prevent a NULL pointer crash. However, the true root cause was a missing check for output reports, patched in commit c7bf714f8755 ("HID: check empty report_list in bigben_probe()"), where the type-confused report list_entry was overlapping with a NULL pointer, which was then causing the crash. Fixes: 918aa1ef104d ("HID: bigbenff: prevent null pointer dereference") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230125-hid-unregister-leds-v4-2-7860c5763c38@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-bigbenff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index ed3d2d7bc1dd..b98c5f31c184 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -197,7 +197,7 @@ static void bigben_worker(struct work_struct *work) u32 len; unsigned long flags; - if (bigben->removed || !report_field) + if (bigben->removed) return; buf = hid_alloc_report_buf(bigben->report, GFP_KERNEL); From fddde36316da8acb45a3cca2e5fda102f5215877 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 19:00:01 +0000 Subject: [PATCH 1716/4345] HID: bigben: use spinlock to safely schedule workers [ Upstream commit 76ca8da989c7d97a7f76c75d475fe95a584439d7 ] Use spinlocks to deal with workers introducing a wrapper bigben_schedule_work(), and several spinlock checks. Otherwise, bigben_set_led() may schedule bigben->worker after the structure has been freed, causing a use-after-free. Fixes: 4eb1b01de5b9 ("HID: hid-bigbenff: fix race condition for scheduled work during removal") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230125-hid-unregister-leds-v4-3-7860c5763c38@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-bigbenff.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index b98c5f31c184..9d6560db762b 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -185,6 +185,15 @@ struct bigben_device { struct work_struct worker; }; +static inline void bigben_schedule_work(struct bigben_device *bigben) +{ + unsigned long flags; + + spin_lock_irqsave(&bigben->lock, flags); + if (!bigben->removed) + schedule_work(&bigben->worker); + spin_unlock_irqrestore(&bigben->lock, flags); +} static void bigben_worker(struct work_struct *work) { @@ -197,9 +206,6 @@ static void bigben_worker(struct work_struct *work) u32 len; unsigned long flags; - if (bigben->removed) - return; - buf = hid_alloc_report_buf(bigben->report, GFP_KERNEL); if (!buf) return; @@ -285,7 +291,7 @@ static int hid_bigben_play_effect(struct input_dev *dev, void *data, bigben->work_ff = true; spin_unlock_irqrestore(&bigben->lock, flags); - schedule_work(&bigben->worker); + bigben_schedule_work(bigben); } return 0; @@ -320,7 +326,7 @@ static void bigben_set_led(struct led_classdev *led, if (work) { bigben->work_led = true; - schedule_work(&bigben->worker); + bigben_schedule_work(bigben); } return; } @@ -450,7 +456,7 @@ static int bigben_probe(struct hid_device *hid, bigben->left_motor_force = 0; bigben->work_led = true; bigben->work_ff = true; - schedule_work(&bigben->worker); + bigben_schedule_work(bigben); hid_info(hid, "LED and force feedback support for BigBen gamepad\n"); From e73640184cb6f74b9c425f6e503f98ea102e0670 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 00:01:44 +0000 Subject: [PATCH 1717/4345] hid: bigben_probe(): validate report count [ Upstream commit b94335f899542a0da5fafc38af8edcaf90195843 ] bigben_probe() does not validate that the output report has the needed report values in the first field. A malicious device registering a report with one field and a single value causes an head OOB write in bigben_worker() when accessing report_field->value[1] to report_field->value[7]. Use hid_validate_values() which takes care of all the needed checks. Fixes: 256a90ed9e46 ("HID: hid-bigbenff: driver for BigBen Interactive PS3OFMINIPAD gamepad") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230211-bigben-oob-v1-1-d2849688594c@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-bigbenff.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index 9d6560db762b..a02cb517b4c4 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -371,7 +371,6 @@ static int bigben_probe(struct hid_device *hid, { struct bigben_device *bigben; struct hid_input *hidinput; - struct list_head *report_list; struct led_classdev *led; char *name; size_t name_sz; @@ -396,14 +395,12 @@ static int bigben_probe(struct hid_device *hid, return error; } - report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; - if (list_empty(report_list)) { + bigben->report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 8); + if (!bigben->report) { hid_err(hid, "no output report found\n"); error = -ENODEV; goto error_hw_stop; } - bigben->report = list_entry(report_list->next, - struct hid_report, list); if (list_empty(&hid->inputs)) { hid_err(hid, "no inputs found\n"); From 9e8ccaf4ff2c4808004276267365da72693b9ddc Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Fri, 27 Jan 2023 11:18:56 -0500 Subject: [PATCH 1718/4345] nfsd: fix race to check ls_layouts [ Upstream commit fb610c4dbc996415d57d7090957ecddd4fd64fb6 ] Its possible for __break_lease to find the layout's lease before we've added the layout to the owner's ls_layouts list. In that case, setting ls_recalled = true without actually recalling the layout will cause the server to never send a recall callback. Move the check for ls_layouts before setting ls_recalled. Fixes: c5c707f96fc9 ("nfsd: implement pNFS layout recalls") Signed-off-by: Benjamin Coddington Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/nfs4layouts.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index a97873f2d22b..2673019d30ec 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -322,11 +322,11 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) if (ls->ls_recalled) goto out_unlock; - ls->ls_recalled = true; - atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); if (list_empty(&ls->ls_layouts)) goto out_unlock; + ls->ls_recalled = true; + atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); trace_nfsd_layout_recall(&ls->ls_stid.sc_stateid); refcount_inc(&ls->ls_stid.sc_count); From caac205e0d5b44c4c23a10c6c0976d50ebe16ac2 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Fri, 18 Nov 2022 16:42:07 +0800 Subject: [PATCH 1719/4345] cifs: Fix lost destroy smbd connection when MR allocate failed [ Upstream commit e9d3401d95d62a9531082cd2453ed42f2740e3fd ] If the MR allocate failed, the smb direct connection info is NULL, then smbd_destroy() will directly return, then the connection info will be leaked. Let's set the smb direct connection info to the server before call smbd_destroy(). Fixes: c7398583340a ("CIFS: SMBD: Implement RDMA memory registration") Signed-off-by: Zhang Xiaoxu Acked-by: Paulo Alcantara (SUSE) Reviewed-by: David Howells Reviewed-by: Tom Talpey Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/cifs/smbdirect.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index f73f9b062525..c93d4ec843be 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -1691,6 +1691,7 @@ static struct smbd_connection *_smbd_get_connection( allocate_mr_failed: /* At this point, need to a full transport shutdown */ + server->smbd_conn = info; smbd_destroy(server); return NULL; From cfd85a0922c4696d768965e686ad805a58d9d834 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Fri, 18 Nov 2022 16:42:08 +0800 Subject: [PATCH 1720/4345] cifs: Fix warning and UAF when destroy the MR list [ Upstream commit 3e161c2791f8e661eed24a2c624087084d910215 ] If the MR allocate failed, the MR recovery work not initialized and list not cleared. Then will be warning and UAF when release the MR: WARNING: CPU: 4 PID: 824 at kernel/workqueue.c:3066 __flush_work.isra.0+0xf7/0x110 CPU: 4 PID: 824 Comm: mount.cifs Not tainted 6.1.0-rc5+ #82 RIP: 0010:__flush_work.isra.0+0xf7/0x110 Call Trace: __cancel_work_timer+0x2ba/0x2e0 smbd_destroy+0x4e1/0x990 _smbd_get_connection+0x1cbd/0x2110 smbd_get_connection+0x21/0x40 cifs_get_tcp_session+0x8ef/0xda0 mount_get_conns+0x60/0x750 cifs_mount+0x103/0xd00 cifs_smb3_do_mount+0x1dd/0xcb0 smb3_get_tree+0x1d5/0x300 vfs_get_tree+0x41/0xf0 path_mount+0x9b3/0xdd0 __x64_sys_mount+0x190/0x1d0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 BUG: KASAN: use-after-free in smbd_destroy+0x4fc/0x990 Read of size 8 at addr ffff88810b156a08 by task mount.cifs/824 CPU: 4 PID: 824 Comm: mount.cifs Tainted: G W 6.1.0-rc5+ #82 Call Trace: dump_stack_lvl+0x34/0x44 print_report+0x171/0x472 kasan_report+0xad/0x130 smbd_destroy+0x4fc/0x990 _smbd_get_connection+0x1cbd/0x2110 smbd_get_connection+0x21/0x40 cifs_get_tcp_session+0x8ef/0xda0 mount_get_conns+0x60/0x750 cifs_mount+0x103/0xd00 cifs_smb3_do_mount+0x1dd/0xcb0 smb3_get_tree+0x1d5/0x300 vfs_get_tree+0x41/0xf0 path_mount+0x9b3/0xdd0 __x64_sys_mount+0x190/0x1d0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Allocated by task 824: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 __kasan_kmalloc+0x7a/0x90 _smbd_get_connection+0x1b6f/0x2110 smbd_get_connection+0x21/0x40 cifs_get_tcp_session+0x8ef/0xda0 mount_get_conns+0x60/0x750 cifs_mount+0x103/0xd00 cifs_smb3_do_mount+0x1dd/0xcb0 smb3_get_tree+0x1d5/0x300 vfs_get_tree+0x41/0xf0 path_mount+0x9b3/0xdd0 __x64_sys_mount+0x190/0x1d0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Freed by task 824: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x40 ____kasan_slab_free+0x143/0x1b0 __kmem_cache_free+0xc8/0x330 _smbd_get_connection+0x1c6a/0x2110 smbd_get_connection+0x21/0x40 cifs_get_tcp_session+0x8ef/0xda0 mount_get_conns+0x60/0x750 cifs_mount+0x103/0xd00 cifs_smb3_do_mount+0x1dd/0xcb0 smb3_get_tree+0x1d5/0x300 vfs_get_tree+0x41/0xf0 path_mount+0x9b3/0xdd0 __x64_sys_mount+0x190/0x1d0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Let's initialize the MR recovery work before MR allocate to prevent the warning, remove the MRs from the list to prevent the UAF. Fixes: c7398583340a ("CIFS: SMBD: Implement RDMA memory registration") Acked-by: Paulo Alcantara (SUSE) Reviewed-by: Tom Talpey Signed-off-by: Zhang Xiaoxu Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/cifs/smbdirect.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index c93d4ec843be..bcc611069308 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -2240,6 +2240,7 @@ static int allocate_mr_list(struct smbd_connection *info) atomic_set(&info->mr_ready_count, 0); atomic_set(&info->mr_used_count, 0); init_waitqueue_head(&info->wait_for_mr_cleanup); + INIT_WORK(&info->mr_recovery_work, smbd_mr_recovery_work); /* Allocate more MRs (2x) than hardware responder_resources */ for (i = 0; i < info->responder_resources * 2; i++) { smbdirect_mr = kzalloc(sizeof(*smbdirect_mr), GFP_KERNEL); @@ -2267,13 +2268,13 @@ static int allocate_mr_list(struct smbd_connection *info) list_add_tail(&smbdirect_mr->list, &info->mr_list); atomic_inc(&info->mr_ready_count); } - INIT_WORK(&info->mr_recovery_work, smbd_mr_recovery_work); return 0; out: kfree(smbdirect_mr); list_for_each_entry_safe(smbdirect_mr, tmp, &info->mr_list, list) { + list_del(&smbdirect_mr->list); ib_dereg_mr(smbdirect_mr->mr); kfree(smbdirect_mr->sgl); kfree(smbdirect_mr); From deece7bd60b0890dc9cb9b7e7295ca994a38abde Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 1 Feb 2023 15:08:50 +0100 Subject: [PATCH 1721/4345] gfs2: jdata writepage fix [ Upstream commit cbb60951ce18c9b6e91d2eb97deb41d8ff616622 ] The ->writepage() and ->writepages() operations are supposed to write entire pages. However, on filesystems with a block size smaller than PAGE_SIZE, __gfs2_jdata_writepage() only adds the first block to the current transaction instead of adding the entire page. Fix that. Fixes: 18ec7d5c3f43 ("[GFS2] Make journaled data files identical to normal files on disk") Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/aops.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index cc4f987687f3..530659554870 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -152,7 +152,6 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w { struct inode *inode = page->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); if (PageChecked(page)) { ClearPageChecked(page); @@ -160,7 +159,7 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w create_empty_buffers(page, inode->i_sb->s_blocksize, BIT(BH_Dirty)|BIT(BH_Uptodate)); } - gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize); + gfs2_page_add_databufs(ip, page, 0, PAGE_SIZE); } return gfs2_write_jdata_page(page, wbc); } From 071b7f572051259f9f5aaae1cecda1a7055a03d5 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 5 Jan 2023 00:26:09 -0800 Subject: [PATCH 1722/4345] perf llvm: Fix inadvertent file creation [ Upstream commit 9f19aab47ced012eddef1e2bc96007efc7713b61 ] The LLVM template is first echo-ed into command_out and then command_out executed. The echo surrounds the template with double quotes, however, the template itself may contain quotes. This is generally innocuous but in tools/perf/tests/bpf-script-test-prologue.c we see: ... SEC("func=null_lseek file->f_mode offset orig") ... where the first double quote ends the double quote of the echo, then the > redirects output into a file called f_mode. To avoid this inadvertent behavior substitute redirects and similar characters to be ASCII control codes, then substitute the output in the echo back again. Fixes: 5eab5a7ee032acaa ("perf llvm: Display eBPF compiling command in debug output") Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Ingo Molnar Cc: Jiri Olsa Cc: llvm@lists.linux.dev Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Tom Rix Link: https://lore.kernel.org/r/20230105082609.344538-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/llvm-utils.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 0bf6b4d4c90a..570cde4640d0 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -525,14 +525,37 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, pr_debug("llvm compiling command template: %s\n", template); + /* + * Below, substitute control characters for values that can cause the + * echo to misbehave, then substitute the values back. + */ err = -ENOMEM; - if (asprintf(&command_echo, "echo -n \"%s\"", template) < 0) + if (asprintf(&command_echo, "echo -n \a%s\a", template) < 0) goto errout; +#define SWAP_CHAR(a, b) do { if (*p == a) *p = b; } while (0) + for (char *p = command_echo; *p; p++) { + SWAP_CHAR('<', '\001'); + SWAP_CHAR('>', '\002'); + SWAP_CHAR('"', '\003'); + SWAP_CHAR('\'', '\004'); + SWAP_CHAR('|', '\005'); + SWAP_CHAR('&', '\006'); + SWAP_CHAR('\a', '"'); + } err = read_from_pipe(command_echo, (void **) &command_out, NULL); if (err) goto errout; + for (char *p = command_out; *p; p++) { + SWAP_CHAR('\001', '<'); + SWAP_CHAR('\002', '>'); + SWAP_CHAR('\003', '"'); + SWAP_CHAR('\004', '\''); + SWAP_CHAR('\005', '|'); + SWAP_CHAR('\006', '&'); + } +#undef SWAP_CHAR pr_debug("llvm compiling command : %s\n", command_out); err = read_from_pipe(template, &obj_buf, &obj_buf_sz); From 1d6101d9222e1ca8c01b3fa9ebf0dcf7bcd82564 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Tue, 20 Dec 2022 16:18:07 +0400 Subject: [PATCH 1723/4345] leds: led-core: Fix refcount leak in of_led_get() [ Upstream commit da1afe8e6099980fe1e2fd7436dca284af9d3f29 ] class_find_device_by_of_node() calls class_find_device(), it will take the reference, use the put_device() to drop the reference when not need anymore. Fixes: 699a8c7c4bd3 ("leds: Add of_led_get() and led_put()") Signed-off-by: Miaoqian Lin Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20221220121807.1543790-1-linmq006@gmail.com Signed-off-by: Sasha Levin --- drivers/leds/led-class.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index e28a4bb71603..fcb9eee3b609 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -236,6 +236,7 @@ struct led_classdev *of_led_get(struct device_node *np, int index) led_dev = class_find_device_by_of_node(leds_class, led_node); of_node_put(led_node); + put_device(led_dev); if (!led_dev) return ERR_PTR(-EPROBE_DEFER); From 93925ab9dd74dc65e1c63b829c0bee8467be29d0 Mon Sep 17 00:00:00 2001 From: Yicong Yang Date: Tue, 7 Feb 2023 11:50:57 +0800 Subject: [PATCH 1724/4345] perf tools: Fix auto-complete on aarch64 [ Upstream commit ffd1240e8f0814262ceb957dbe961f6e0aef1e7a ] On aarch64 CPU related events are not under event_source/devices/cpu/events, they're under event_source/devices/armv8_pmuv3_0/events on my machine. Using current auto-complete script will generate below error: [root@localhost bin]# perf stat -e ls: cannot access '/sys/bus/event_source/devices/cpu/events': No such file or directory Fix this by not testing /sys/bus/event_source/devices/cpu/events on aarch64 machine. Fixes: 74cd5815d9af6e6c ("perf tool: Improve bash command line auto-complete for multiple events with comma") Reviewed-by: James Clark Signed-off-by: Yicong Yang Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jin Yao Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Cc: linuxarm@huawei.com Cc: prime.zeng@hisilicon.com Link: https://lore.kernel.org/r/20230207035057.43394-1-yangyicong@huawei.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/perf-completion.sh | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh index fdf75d45efff..978249d7868c 100644 --- a/tools/perf/perf-completion.sh +++ b/tools/perf/perf-completion.sh @@ -165,7 +165,12 @@ __perf_main () local cur1=${COMP_WORDS[COMP_CWORD]} local raw_evts=$($cmd list --raw-dump) - local arr s tmp result + local arr s tmp result cpu_evts + + # aarch64 doesn't have /sys/bus/event_source/devices/cpu/events + if [[ `uname -m` != aarch64 ]]; then + cpu_evts=$(ls /sys/bus/event_source/devices/cpu/events) + fi if [[ "$cur1" == */* && ${cur1#*/} =~ ^[A-Z] ]]; then OLD_IFS="$IFS" @@ -183,9 +188,9 @@ __perf_main () fi done - evts=${result}" "$(ls /sys/bus/event_source/devices/cpu/events) + evts=${result}" "${cpu_evts} else - evts=${raw_evts}" "$(ls /sys/bus/event_source/devices/cpu/events) + evts=${raw_evts}" "${cpu_evts} fi if [[ "$cur1" == , ]]; then From b8dc9f6fde194631f6e6158a65cdfcc77f597de3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 4 Feb 2023 16:43:57 -0800 Subject: [PATCH 1725/4345] sparc: allow PM configs for sparc32 COMPILE_TEST [ Upstream commit 7be6a87c2473957090995b7eb541e31d57a2c801 ] When doing randconfig builds for sparc32 with COMPILE_TEST, some (non-Sparc) drivers cause kconfig warnings with the Kconfig symbols PM, PM_GENERIC_DOMAINS, or PM_GENERIC_DOMAINS_OF. This is due to arch/sparc/Kconfig not using the PM Kconfig for Sparc32: if SPARC64 source "kernel/power/Kconfig" endif Arnd suggested adding "|| COMPILE_TEST" to the conditional, instead of trying to track down every driver that selects any of these PM symbols. Fixes the following kconfig warnings: WARNING: unmet direct dependencies detected for PM Depends on [n]: SPARC64 [=n] Selected by [y]: - SUN20I_PPU [=y] && (ARCH_SUNXI || COMPILE_TEST [=y]) WARNING: unmet direct dependencies detected for PM Depends on [n]: SPARC64 [=n] Selected by [y]: - SUN20I_PPU [=y] && (ARCH_SUNXI || COMPILE_TEST [=y]) WARNING: unmet direct dependencies detected for PM_GENERIC_DOMAINS Depends on [n]: SPARC64 [=n] && PM [=y] Selected by [y]: - QCOM_GDSC [=y] && COMMON_CLK [=y] && PM [=y] - SUN20I_PPU [=y] && (ARCH_SUNXI || COMPILE_TEST [=y]) - MESON_GX_PM_DOMAINS [=y] && (ARCH_MESON || COMPILE_TEST [=y]) && PM [=y] && OF [=y] - BCM2835_POWER [=y] && (ARCH_BCM2835 || COMPILE_TEST [=y] && OF [=y]) && PM [=y] - BCM_PMB [=y] && (ARCH_BCMBCA || COMPILE_TEST [=y] && OF [=y]) && PM [=y] - ROCKCHIP_PM_DOMAINS [=y] && (ARCH_ROCKCHIP || COMPILE_TEST [=y]) && PM [=y] Selected by [m]: - ARM_SCPI_POWER_DOMAIN [=m] && (ARM_SCPI_PROTOCOL [=m] || COMPILE_TEST [=y] && OF [=y]) && PM [=y] - MESON_EE_PM_DOMAINS [=m] && (ARCH_MESON || COMPILE_TEST [=y]) && PM [=y] && OF [=y] - QCOM_AOSS_QMP [=m] && (ARCH_QCOM || COMPILE_TEST [=y]) && MAILBOX [=y] && COMMON_CLK [=y] && PM [=y] WARNING: unmet direct dependencies detected for PM_GENERIC_DOMAINS_OF Depends on [n]: SPARC64 [=n] && PM_GENERIC_DOMAINS [=y] && OF [=y] Selected by [y]: - MESON_GX_PM_DOMAINS [=y] && (ARCH_MESON || COMPILE_TEST [=y]) && PM [=y] && OF [=y] Selected by [m]: - MESON_EE_PM_DOMAINS [=m] && (ARCH_MESON || COMPILE_TEST [=y]) && PM [=y] && OF [=y] Link: https://lkml.kernel.org/r/20230205004357.29459-1-rdunlap@infradead.org Fixes: bdde6b3c8ba4 ("sparc64: Hibernation support") Signed-off-by: Randy Dunlap Suggested-by: Arnd Bergmann Acked-by: Sam Ravnborg Cc: "David S. Miller" Cc: Kirill Tkhai Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- arch/sparc/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 530b7ec5d3ca..b5ed89342059 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -293,7 +293,7 @@ config FORCE_MAX_ZONEORDER This config option is actually maximum order plus one. For example, a value of 13 means that the largest free memory block is 2^12 pages. -if SPARC64 +if SPARC64 || COMPILE_TEST source "kernel/power/Kconfig" endif From b18946a9cee2d239a556d6f94f2ea118c84d7a9e Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sun, 22 Jan 2023 08:32:50 +0900 Subject: [PATCH 1726/4345] selftests/ftrace: Fix bash specific "==" operator [ Upstream commit 1e6b485c922fbedf41d5a9f4e6449c5aeb923a32 ] Since commit a1d6cd88c897 ("selftests/ftrace: event_triggers: wait longer for test_event_enable") introduced bash specific "==" comparation operator, that test will fail when we run it on a posix-shell. `checkbashisms` warned it as below. possible bashism in ftrace/func_event_triggers.tc line 45 (should be 'b = a'): if [ "$e" == $val ]; then This replaces it with "=". Fixes: a1d6cd88c897 ("selftests/ftrace: event_triggers: wait longer for test_event_enable") Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- .../selftests/ftrace/test.d/ftrace/func_event_triggers.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc index 27a68bbe778b..d9b812795077 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc @@ -42,7 +42,7 @@ test_event_enabled() { while [ $check_times -ne 0 ]; do e=`cat $EVENT_ENABLE` - if [ "$e" == $val ]; then + if [ "$e" = $val ]; then return 0 fi sleep $SLEEP_TIME From 455cf05161be58d3f3892d001f09a5c315a27680 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 6 Feb 2023 20:40:57 +0100 Subject: [PATCH 1727/4345] printf: fix errname.c list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0c2baf6509af1d11310ae4c1c839481a6e9a4bc4 ] On most architectures, gcc -Wextra warns about the list of error numbers containing both EDEADLK and EDEADLOCK: lib/errname.c:15:67: warning: initialized field overwritten [-Woverride-init] 15 | #define E(err) [err + BUILD_BUG_ON_ZERO(err <= 0 || err > 300)] = "-" #err | ^~~ lib/errname.c:172:2: note: in expansion of macro 'E' 172 | E(EDEADLK), /* EDEADLOCK */ | ^ On parisc, a similar error happens with -ECANCELLED, which is an alias for ECANCELED. Make the EDEADLK printing conditional on the number being distinct from EDEADLOCK, and remove the -ECANCELLED bit completely as it can never be hit. To ensure these are correct, add static_assert lines that verify all the remaining aliases are in fact identical to the canonical name. Fixes: 57f5677e535b ("printf: add support for printing symbolic error names") Cc: Petr Mladek Suggested-by: Rasmus Villemoes Acked-by: Uwe Kleine-König Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/all/20210514213456.745039-1-arnd@kernel.org/ Link: https://lore.kernel.org/all/20210927123409.1109737-1-arnd@kernel.org/ Signed-off-by: Arnd Bergmann Reviewed-by: Sergey Senozhatsky Acked-by: Rasmus Villemoes Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230206194126.380350-1-arnd@kernel.org Signed-off-by: Sasha Levin --- lib/errname.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/lib/errname.c b/lib/errname.c index 0c4d3e66170e..a5799a8c9cab 100644 --- a/lib/errname.c +++ b/lib/errname.c @@ -20,6 +20,7 @@ static const char *names_0[] = { E(EADDRNOTAVAIL), E(EADV), E(EAFNOSUPPORT), + E(EAGAIN), /* EWOULDBLOCK */ E(EALREADY), E(EBADE), E(EBADF), @@ -30,15 +31,17 @@ static const char *names_0[] = { E(EBADSLT), E(EBFONT), E(EBUSY), -#ifdef ECANCELLED - E(ECANCELLED), -#endif + E(ECANCELED), /* ECANCELLED */ E(ECHILD), E(ECHRNG), E(ECOMM), E(ECONNABORTED), + E(ECONNREFUSED), /* EREFUSED */ E(ECONNRESET), + E(EDEADLK), /* EDEADLOCK */ +#if EDEADLK != EDEADLOCK /* mips, sparc, powerpc */ E(EDEADLOCK), +#endif E(EDESTADDRREQ), E(EDOM), E(EDOTDOT), @@ -165,14 +168,17 @@ static const char *names_0[] = { E(EUSERS), E(EXDEV), E(EXFULL), - - E(ECANCELED), /* ECANCELLED */ - E(EAGAIN), /* EWOULDBLOCK */ - E(ECONNREFUSED), /* EREFUSED */ - E(EDEADLK), /* EDEADLOCK */ }; #undef E +#ifdef EREFUSED /* parisc */ +static_assert(EREFUSED == ECONNREFUSED); +#endif +#ifdef ECANCELLED /* parisc */ +static_assert(ECANCELLED == ECANCELED); +#endif +static_assert(EAGAIN == EWOULDBLOCK); /* everywhere */ + #define E(err) [err - 512 + BUILD_BUG_ON_ZERO(err < 512 || err > 550)] = "-" #err static const char *names_512[] = { E(ERESTARTSYS), From 8a041377a4583850be020db01fd8f45bad0abaaf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 15 Feb 2023 14:00:58 +0100 Subject: [PATCH 1728/4345] objtool: add UACCESS exceptions for __tsan_volatile_read/write [ Upstream commit d5d469247264e56960705dc5ae7e1d014861fe40 ] A lot of the tsan helpers are already excempt from the UACCESS warnings, but some more functions were added that need the same thing: kernel/kcsan/core.o: warning: objtool: __tsan_volatile_read16+0x0: call to __tsan_unaligned_read16() with UACCESS enabled kernel/kcsan/core.o: warning: objtool: __tsan_volatile_write16+0x0: call to __tsan_unaligned_write16() with UACCESS enabled vmlinux.o: warning: objtool: __tsan_unaligned_volatile_read16+0x4: call to __tsan_unaligned_read16() with UACCESS enabled vmlinux.o: warning: objtool: __tsan_unaligned_volatile_write16+0x4: call to __tsan_unaligned_write16() with UACCESS enabled As Marco points out, these functions don't even call each other explicitly but instead gcc (but not clang) notices the functions being identical and turns one symbol into a direct branch to the other. Link: https://lkml.kernel.org/r/20230215130058.3836177-4-arnd@kernel.org Fixes: 75d75b7a4d54 ("kcsan: Support distinguishing volatile accesses") Signed-off-by: Arnd Bergmann Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Josh Poimboeuf Cc: Kuan-Ying Lee Cc: Peter Zijlstra (Intel) Cc: Vincenzo Frascino Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- tools/objtool/check.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index ff47aed7ef6f..5c4190382a51 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -864,6 +864,8 @@ static const char *uaccess_safe_builtin[] = { "__tsan_atomic64_compare_exchange_val", "__tsan_atomic_thread_fence", "__tsan_atomic_signal_fence", + "__tsan_unaligned_read16", + "__tsan_unaligned_write16", /* KCOV */ "write_comp_data", "check_kcov_mode", From 3ee13bdf0d25ae8752ae6185b6d13bbb0d5a8e30 Mon Sep 17 00:00:00 2001 From: Qiheng Lin Date: Thu, 8 Dec 2022 14:15:55 +0800 Subject: [PATCH 1729/4345] mfd: pcf50633-adc: Fix potential memleak in pcf50633_adc_async_read() [ Upstream commit 8b450dcff23aa254844492831a8e2b508a9d522d ] `req` is allocated in pcf50633_adc_async_read(), but adc_enqueue_request() could fail to insert the `req` into queue. We need to check the return value and free it in the case of failure. Fixes: 08c3e06a5eb2 ("mfd: PCF50633 adc driver") Signed-off-by: Qiheng Lin Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20221208061555.8776-1-linqiheng@huawei.com Signed-off-by: Sasha Levin --- drivers/mfd/pcf50633-adc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/mfd/pcf50633-adc.c b/drivers/mfd/pcf50633-adc.c index 5cd653e61512..191b1bc6141c 100644 --- a/drivers/mfd/pcf50633-adc.c +++ b/drivers/mfd/pcf50633-adc.c @@ -136,6 +136,7 @@ int pcf50633_adc_async_read(struct pcf50633 *pcf, int mux, int avg, void *callback_param) { struct pcf50633_adc_request *req; + int ret; /* req is freed when the result is ready, in interrupt handler */ req = kmalloc(sizeof(*req), GFP_KERNEL); @@ -147,7 +148,11 @@ int pcf50633_adc_async_read(struct pcf50633 *pcf, int mux, int avg, req->callback = callback; req->callback_param = callback_param; - return adc_enqueue_request(pcf, req); + ret = adc_enqueue_request(pcf, req); + if (ret) + kfree(req); + + return ret; } EXPORT_SYMBOL_GPL(pcf50633_adc_async_read); From 7fd6fd898b64834e3e7d7b344ced7b7dba62c9ab Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 26 Dec 2022 06:21:43 +0200 Subject: [PATCH 1730/4345] clk: qcom: gcc-qcs404: disable gpll[04]_out_aux parents [ Upstream commit 712c64caf31374de57aa193a9dff57172b2f6f82 ] On the QCS404 platform the driver for the Global Clock Controller doens't define gpll0_out_aux and gpll4_out_aux clocks, so it's not possible to use them as parents. Remove entries for these clocks. Note: backporting this patch to earlier kernels would also require a previous patch which switches the gcc driver to use ARRAY_SIZE for parent data arrays. Fixes: 652f1813c113 ("clk: qcom: gcc: Add global clock controller driver for QCS404") Signed-off-by: Dmitry Baryshkov Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221226042154.2666748-6-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-qcs404.c | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c index 46d314d69250..4299fe8f1927 100644 --- a/drivers/clk/qcom/gcc-qcs404.c +++ b/drivers/clk/qcom/gcc-qcs404.c @@ -25,11 +25,9 @@ enum { P_CORE_BI_PLL_TEST_SE, P_DSI0_PHY_PLL_OUT_BYTECLK, P_DSI0_PHY_PLL_OUT_DSICLK, - P_GPLL0_OUT_AUX, P_GPLL0_OUT_MAIN, P_GPLL1_OUT_MAIN, P_GPLL3_OUT_MAIN, - P_GPLL4_OUT_AUX, P_GPLL4_OUT_MAIN, P_GPLL6_OUT_AUX, P_HDMI_PHY_PLL_CLK, @@ -109,28 +107,24 @@ static const char * const gcc_parent_names_4[] = { static const struct parent_map gcc_parent_map_5[] = { { P_XO, 0 }, { P_DSI0_PHY_PLL_OUT_BYTECLK, 1 }, - { P_GPLL0_OUT_AUX, 2 }, { P_CORE_BI_PLL_TEST_SE, 7 }, }; static const char * const gcc_parent_names_5[] = { "cxo", "dsi0pll_byteclk_src", - "gpll0_out_aux", "core_bi_pll_test_se", }; static const struct parent_map gcc_parent_map_6[] = { { P_XO, 0 }, { P_DSI0_PHY_PLL_OUT_BYTECLK, 2 }, - { P_GPLL0_OUT_AUX, 3 }, { P_CORE_BI_PLL_TEST_SE, 7 }, }; static const char * const gcc_parent_names_6[] = { "cxo", "dsi0_phy_pll_out_byteclk", - "gpll0_out_aux", "core_bi_pll_test_se", }; @@ -139,7 +133,6 @@ static const struct parent_map gcc_parent_map_7[] = { { P_GPLL0_OUT_MAIN, 1 }, { P_GPLL3_OUT_MAIN, 2 }, { P_GPLL6_OUT_AUX, 3 }, - { P_GPLL4_OUT_AUX, 4 }, { P_CORE_BI_PLL_TEST_SE, 7 }, }; @@ -148,7 +141,6 @@ static const char * const gcc_parent_names_7[] = { "gpll0_out_main", "gpll3_out_main", "gpll6_out_aux", - "gpll4_out_aux", "core_bi_pll_test_se", }; @@ -207,14 +199,12 @@ static const char * const gcc_parent_names_11[] = { static const struct parent_map gcc_parent_map_12[] = { { P_XO, 0 }, { P_DSI0_PHY_PLL_OUT_DSICLK, 1 }, - { P_GPLL0_OUT_AUX, 2 }, { P_CORE_BI_PLL_TEST_SE, 7 }, }; static const char * const gcc_parent_names_12[] = { "cxo", "dsi0pll_pclk_src", - "gpll0_out_aux", "core_bi_pll_test_se", }; @@ -237,40 +227,34 @@ static const char * const gcc_parent_names_13[] = { static const struct parent_map gcc_parent_map_14[] = { { P_XO, 0 }, { P_GPLL0_OUT_MAIN, 1 }, - { P_GPLL4_OUT_AUX, 2 }, { P_CORE_BI_PLL_TEST_SE, 7 }, }; static const char * const gcc_parent_names_14[] = { "cxo", "gpll0_out_main", - "gpll4_out_aux", "core_bi_pll_test_se", }; static const struct parent_map gcc_parent_map_15[] = { { P_XO, 0 }, - { P_GPLL0_OUT_AUX, 2 }, { P_CORE_BI_PLL_TEST_SE, 7 }, }; static const char * const gcc_parent_names_15[] = { "cxo", - "gpll0_out_aux", "core_bi_pll_test_se", }; static const struct parent_map gcc_parent_map_16[] = { { P_XO, 0 }, { P_GPLL0_OUT_MAIN, 1 }, - { P_GPLL0_OUT_AUX, 2 }, { P_CORE_BI_PLL_TEST_SE, 7 }, }; static const char * const gcc_parent_names_16[] = { "cxo", "gpll0_out_main", - "gpll0_out_aux", "core_bi_pll_test_se", }; From c7950aa8728085d4ef374f2b03572ffaf8eeed3c Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 26 Dec 2022 06:21:44 +0200 Subject: [PATCH 1731/4345] clk: qcom: gcc-qcs404: fix names of the DSI clocks used as parents [ Upstream commit 47d94d30cd3dcc743241b4208b1eec7247610c84 ] The QCS404 uses 28nm LPM DSI PHY, which registers dsi0pll and dsi0pllbyte clocks. Fix all DSI PHY clock names used as parents inside the GCC driver. Fixes: 652f1813c113 ("clk: qcom: gcc: Add global clock controller driver for QCS404") Reviewed-by: Konrad Dybcio Signed-off-by: Dmitry Baryshkov Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221226042154.2666748-7-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-qcs404.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c index 4299fe8f1927..a7a9884799cd 100644 --- a/drivers/clk/qcom/gcc-qcs404.c +++ b/drivers/clk/qcom/gcc-qcs404.c @@ -112,7 +112,7 @@ static const struct parent_map gcc_parent_map_5[] = { static const char * const gcc_parent_names_5[] = { "cxo", - "dsi0pll_byteclk_src", + "dsi0pllbyte", "core_bi_pll_test_se", }; @@ -124,7 +124,7 @@ static const struct parent_map gcc_parent_map_6[] = { static const char * const gcc_parent_names_6[] = { "cxo", - "dsi0_phy_pll_out_byteclk", + "dsi0pllbyte", "core_bi_pll_test_se", }; @@ -167,7 +167,7 @@ static const struct parent_map gcc_parent_map_9[] = { static const char * const gcc_parent_names_9[] = { "cxo", "gpll0_out_main", - "dsi0_phy_pll_out_dsiclk", + "dsi0pll", "gpll6_out_aux", "core_bi_pll_test_se", }; @@ -204,7 +204,7 @@ static const struct parent_map gcc_parent_map_12[] = { static const char * const gcc_parent_names_12[] = { "cxo", - "dsi0pll_pclk_src", + "dsi0pll", "core_bi_pll_test_se", }; From c90fa32bd4d200fa972b39e0d3b28f6c900b23e8 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Fri, 23 Dec 2022 23:13:21 +0100 Subject: [PATCH 1732/4345] RISC-V: fix funct4 definition for c.jalr in parse_asm.h [ Upstream commit a3775634f6da23f5511d0282d7e792cf606e5f3b ] The opcode definition for c.jalr is c.jalr c_rs1_n0 1..0=2 15..13=4 12=1 6..2=0 This means funct4 consisting of bit [15:12] is 1001b, so the value is 0x9. Fixes: edde5584c7ab ("riscv: Add SW single-step support for KDB") Reported-by: Andrew Jones Reviewed-by: Andrew Jones Reviewed-by: Lad Prabhakar Signed-off-by: Heiko Stuebner Link: https://lore.kernel.org/r/20221223221332.4127602-2-heiko@sntech.de Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/include/asm/parse_asm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/parse_asm.h b/arch/riscv/include/asm/parse_asm.h index f36368de839f..7fee806805c1 100644 --- a/arch/riscv/include/asm/parse_asm.h +++ b/arch/riscv/include/asm/parse_asm.h @@ -125,7 +125,7 @@ #define FUNCT3_C_J 0xa000 #define FUNCT3_C_JAL 0x2000 #define FUNCT4_C_JR 0x8000 -#define FUNCT4_C_JALR 0xf000 +#define FUNCT4_C_JALR 0x9000 #define FUNCT12_SRET 0x10200000 From b7fb5b5d2c8c6196d8b8dccaaefc40dbf59f31d9 Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Thu, 29 Dec 2022 12:15:24 -0600 Subject: [PATCH 1733/4345] mtd: rawnand: sunxi: Fix the size of the last OOB region [ Upstream commit 34569d869532b54d6e360d224a0254dcdd6a1785 ] The previous code assigned to the wrong structure member. Fixes: c66811e6d350 ("mtd: nand: sunxi: switch to mtd_ooblayout_ops") Signed-off-by: Samuel Holland Acked-By: Dhruva Gole Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20221229181526.53766-6-samuel@sholland.org Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/sunxi_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c index 2a7ca3072f35..52eb28f3277c 100644 --- a/drivers/mtd/nand/raw/sunxi_nand.c +++ b/drivers/mtd/nand/raw/sunxi_nand.c @@ -1587,7 +1587,7 @@ static int sunxi_nand_ooblayout_free(struct mtd_info *mtd, int section, if (section < ecc->steps) oobregion->length = 4; else - oobregion->offset = mtd->oobsize - oobregion->offset; + oobregion->length = mtd->oobsize - oobregion->offset; return 0; } From a6a70ab2bbe24704b5241d4cab6f4e031ceef3ce Mon Sep 17 00:00:00 2001 From: Jeff LaBundy Date: Tue, 3 Jan 2023 11:58:31 -0600 Subject: [PATCH 1734/4345] Input: iqs269a - drop unused device node references [ Upstream commit 59bc9cb3b80abaa42643abede0d5db8477901d9c ] Each call to device/fwnode_get_named_child_node() must be matched with a call to fwnode_handle_put() once the corresponding node is no longer in use. This ensures a reference count remains balanced in the case of dynamic device tree support. Currently, the driver does not call fwnode_handle_put() on nested event nodes. This patch solves this problem by adding the missing instances of fwnode_handle_put(). As part of this change, the logic which parses each channel's key code is gently refactored in order to reduce the number of places from which fwnode_handle_put() is called. Fixes: 04e49867fad1 ("Input: add support for Azoteq IQS269A") Signed-off-by: Jeff LaBundy Link: https://lore.kernel.org/r/Y7Rsx68k/gvDVXAt@nixie71 Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/misc/iqs269a.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c index a348247d3d38..ea3c97c5f764 100644 --- a/drivers/input/misc/iqs269a.c +++ b/drivers/input/misc/iqs269a.c @@ -694,6 +694,7 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269, dev_err(&client->dev, "Invalid channel %u threshold: %u\n", reg, val); + fwnode_handle_put(ev_node); return -EINVAL; } @@ -707,6 +708,7 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269, dev_err(&client->dev, "Invalid channel %u hysteresis: %u\n", reg, val); + fwnode_handle_put(ev_node); return -EINVAL; } @@ -721,8 +723,16 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269, } } - if (fwnode_property_read_u32(ev_node, "linux,code", &val)) + error = fwnode_property_read_u32(ev_node, "linux,code", &val); + fwnode_handle_put(ev_node); + if (error == -EINVAL) { continue; + } else if (error) { + dev_err(&client->dev, + "Failed to read channel %u code: %d\n", reg, + error); + return error; + } switch (reg) { case IQS269_CHx_HALL_ACTIVE: From b7afc359f6e57dc9d0e0a58d3072692a237c5998 Mon Sep 17 00:00:00 2001 From: Jeff LaBundy Date: Tue, 3 Jan 2023 11:58:59 -0600 Subject: [PATCH 1735/4345] Input: iqs269a - increase interrupt handler return delay [ Upstream commit e023cc4abde3c01b895660b0e5a8488deb36b8c1 ] The time the device takes to deassert its RDY output following an I2C stop condition scales with the core clock frequency. To prevent level-triggered interrupts from being reasserted after the interrupt handler returns, increase the time before returning to account for the worst-case delay (~140 us) plus margin. Fixes: 04e49867fad1 ("Input: add support for Azoteq IQS269A") Signed-off-by: Jeff LaBundy Reviewed-by: Mattijs Korpershoek Link: https://lore.kernel.org/r/Y7Rs484ypy4dab5G@nixie71 Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/misc/iqs269a.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c index ea3c97c5f764..ea3401a1000f 100644 --- a/drivers/input/misc/iqs269a.c +++ b/drivers/input/misc/iqs269a.c @@ -153,7 +153,7 @@ #define IQS269_PWR_MODE_POLL_SLEEP_US IQS269_ATI_POLL_SLEEP_US #define IQS269_PWR_MODE_POLL_TIMEOUT_US IQS269_ATI_POLL_TIMEOUT_US -#define iqs269_irq_wait() usleep_range(100, 150) +#define iqs269_irq_wait() usleep_range(200, 250) enum iqs269_local_cap_size { IQS269_LOCAL_CAP_SIZE_0, From 9a6dca86cfae3cefe857633d6670a5c9a64e31c3 Mon Sep 17 00:00:00 2001 From: Jeff LaBundy Date: Tue, 3 Jan 2023 11:59:12 -0600 Subject: [PATCH 1736/4345] Input: iqs269a - configure device with a single block write [ Upstream commit 3689abfc4e369a643d758a02fb9ad0b2403d6d6d ] Unless it is being done as part of servicing a soft reset interrupt, configuring channels on-the-fly (as is the case when writing to the ati_trigger attribute) may cause GPIO3 (which reflects the state of touch for a selected channel) to be inadvertently asserted. To solve this problem, follow the vendor's recommendation and write all channel configuration as well as the REDO_ATI register field as part of a single block write. This ensures the device has been told to re-calibrate itself following an I2C stop condition, after which sensing resumes and GPIO3 may be asserted. Fixes: 04e49867fad1 ("Input: add support for Azoteq IQS269A") Signed-off-by: Jeff LaBundy Reviewed-by: Mattijs Korpershoek Link: https://lore.kernel.org/r/Y7Rs8GyV7g0nF5Yy@nixie71 Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/misc/iqs269a.c | 98 ++++++++++++++---------------------- 1 file changed, 39 insertions(+), 59 deletions(-) diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c index ea3401a1000f..1530efd301c2 100644 --- a/drivers/input/misc/iqs269a.c +++ b/drivers/input/misc/iqs269a.c @@ -96,8 +96,6 @@ #define IQS269_MISC_B_TRACKING_UI_ENABLE BIT(4) #define IQS269_MISC_B_FILT_STR_SLIDER GENMASK(1, 0) -#define IQS269_CHx_SETTINGS 0x8C - #define IQS269_CHx_ENG_A_MEAS_CAP_SIZE BIT(15) #define IQS269_CHx_ENG_A_RX_GND_INACTIVE BIT(13) #define IQS269_CHx_ENG_A_LOCAL_CAP_SIZE BIT(12) @@ -245,6 +243,18 @@ struct iqs269_ver_info { u8 padding; } __packed; +struct iqs269_ch_reg { + u8 rx_enable; + u8 tx_enable; + __be16 engine_a; + __be16 engine_b; + __be16 ati_comp; + u8 thresh[3]; + u8 hyst; + u8 assoc_select; + u8 assoc_weight; +} __packed; + struct iqs269_sys_reg { __be16 general; u8 active; @@ -266,18 +276,7 @@ struct iqs269_sys_reg { u8 timeout_swipe; u8 thresh_swipe; u8 redo_ati; -} __packed; - -struct iqs269_ch_reg { - u8 rx_enable; - u8 tx_enable; - __be16 engine_a; - __be16 engine_b; - __be16 ati_comp; - u8 thresh[3]; - u8 hyst; - u8 assoc_select; - u8 assoc_weight; + struct iqs269_ch_reg ch_reg[IQS269_NUM_CH]; } __packed; struct iqs269_flags { @@ -292,7 +291,6 @@ struct iqs269_private { struct regmap *regmap; struct mutex lock; struct iqs269_switch_desc switches[ARRAY_SIZE(iqs269_events)]; - struct iqs269_ch_reg ch_reg[IQS269_NUM_CH]; struct iqs269_sys_reg sys_reg; struct input_dev *keypad; struct input_dev *slider[IQS269_NUM_SL]; @@ -307,6 +305,7 @@ struct iqs269_private { static int iqs269_ati_mode_set(struct iqs269_private *iqs269, unsigned int ch_num, unsigned int mode) { + struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; u16 engine_a; if (ch_num >= IQS269_NUM_CH) @@ -317,12 +316,12 @@ static int iqs269_ati_mode_set(struct iqs269_private *iqs269, mutex_lock(&iqs269->lock); - engine_a = be16_to_cpu(iqs269->ch_reg[ch_num].engine_a); + engine_a = be16_to_cpu(ch_reg[ch_num].engine_a); engine_a &= ~IQS269_CHx_ENG_A_ATI_MODE_MASK; engine_a |= (mode << IQS269_CHx_ENG_A_ATI_MODE_SHIFT); - iqs269->ch_reg[ch_num].engine_a = cpu_to_be16(engine_a); + ch_reg[ch_num].engine_a = cpu_to_be16(engine_a); iqs269->ati_current = false; mutex_unlock(&iqs269->lock); @@ -333,13 +332,14 @@ static int iqs269_ati_mode_set(struct iqs269_private *iqs269, static int iqs269_ati_mode_get(struct iqs269_private *iqs269, unsigned int ch_num, unsigned int *mode) { + struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; u16 engine_a; if (ch_num >= IQS269_NUM_CH) return -EINVAL; mutex_lock(&iqs269->lock); - engine_a = be16_to_cpu(iqs269->ch_reg[ch_num].engine_a); + engine_a = be16_to_cpu(ch_reg[ch_num].engine_a); mutex_unlock(&iqs269->lock); engine_a &= IQS269_CHx_ENG_A_ATI_MODE_MASK; @@ -351,6 +351,7 @@ static int iqs269_ati_mode_get(struct iqs269_private *iqs269, static int iqs269_ati_base_set(struct iqs269_private *iqs269, unsigned int ch_num, unsigned int base) { + struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; u16 engine_b; if (ch_num >= IQS269_NUM_CH) @@ -379,12 +380,12 @@ static int iqs269_ati_base_set(struct iqs269_private *iqs269, mutex_lock(&iqs269->lock); - engine_b = be16_to_cpu(iqs269->ch_reg[ch_num].engine_b); + engine_b = be16_to_cpu(ch_reg[ch_num].engine_b); engine_b &= ~IQS269_CHx_ENG_B_ATI_BASE_MASK; engine_b |= base; - iqs269->ch_reg[ch_num].engine_b = cpu_to_be16(engine_b); + ch_reg[ch_num].engine_b = cpu_to_be16(engine_b); iqs269->ati_current = false; mutex_unlock(&iqs269->lock); @@ -395,13 +396,14 @@ static int iqs269_ati_base_set(struct iqs269_private *iqs269, static int iqs269_ati_base_get(struct iqs269_private *iqs269, unsigned int ch_num, unsigned int *base) { + struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; u16 engine_b; if (ch_num >= IQS269_NUM_CH) return -EINVAL; mutex_lock(&iqs269->lock); - engine_b = be16_to_cpu(iqs269->ch_reg[ch_num].engine_b); + engine_b = be16_to_cpu(ch_reg[ch_num].engine_b); mutex_unlock(&iqs269->lock); switch (engine_b & IQS269_CHx_ENG_B_ATI_BASE_MASK) { @@ -429,6 +431,7 @@ static int iqs269_ati_base_get(struct iqs269_private *iqs269, static int iqs269_ati_target_set(struct iqs269_private *iqs269, unsigned int ch_num, unsigned int target) { + struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; u16 engine_b; if (ch_num >= IQS269_NUM_CH) @@ -439,12 +442,12 @@ static int iqs269_ati_target_set(struct iqs269_private *iqs269, mutex_lock(&iqs269->lock); - engine_b = be16_to_cpu(iqs269->ch_reg[ch_num].engine_b); + engine_b = be16_to_cpu(ch_reg[ch_num].engine_b); engine_b &= ~IQS269_CHx_ENG_B_ATI_TARGET_MASK; engine_b |= target / 32; - iqs269->ch_reg[ch_num].engine_b = cpu_to_be16(engine_b); + ch_reg[ch_num].engine_b = cpu_to_be16(engine_b); iqs269->ati_current = false; mutex_unlock(&iqs269->lock); @@ -455,13 +458,14 @@ static int iqs269_ati_target_set(struct iqs269_private *iqs269, static int iqs269_ati_target_get(struct iqs269_private *iqs269, unsigned int ch_num, unsigned int *target) { + struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; u16 engine_b; if (ch_num >= IQS269_NUM_CH) return -EINVAL; mutex_lock(&iqs269->lock); - engine_b = be16_to_cpu(iqs269->ch_reg[ch_num].engine_b); + engine_b = be16_to_cpu(ch_reg[ch_num].engine_b); mutex_unlock(&iqs269->lock); *target = (engine_b & IQS269_CHx_ENG_B_ATI_TARGET_MASK) * 32; @@ -531,13 +535,7 @@ static int iqs269_parse_chan(struct iqs269_private *iqs269, if (fwnode_property_present(ch_node, "azoteq,slider1-select")) iqs269->sys_reg.slider_select[1] |= BIT(reg); - ch_reg = &iqs269->ch_reg[reg]; - - error = regmap_raw_read(iqs269->regmap, - IQS269_CHx_SETTINGS + reg * sizeof(*ch_reg) / 2, - ch_reg, sizeof(*ch_reg)); - if (error) - return error; + ch_reg = &iqs269->sys_reg.ch_reg[reg]; error = iqs269_parse_mask(ch_node, "azoteq,rx-enable", &ch_reg->rx_enable); @@ -1042,10 +1040,8 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269) static int iqs269_dev_init(struct iqs269_private *iqs269) { - struct iqs269_sys_reg *sys_reg = &iqs269->sys_reg; - struct iqs269_ch_reg *ch_reg; unsigned int val; - int error, i; + int error; mutex_lock(&iqs269->lock); @@ -1055,27 +1051,8 @@ static int iqs269_dev_init(struct iqs269_private *iqs269) if (error) goto err_mutex; - for (i = 0; i < IQS269_NUM_CH; i++) { - if (!(sys_reg->active & BIT(i))) - continue; - - ch_reg = &iqs269->ch_reg[i]; - - error = regmap_raw_write(iqs269->regmap, - IQS269_CHx_SETTINGS + i * - sizeof(*ch_reg) / 2, ch_reg, - sizeof(*ch_reg)); - if (error) - goto err_mutex; - } - - /* - * The REDO-ATI and ATI channel selection fields must be written in the - * same block write, so every field between registers 0x80 through 0x8B - * (inclusive) must be written as well. - */ - error = regmap_raw_write(iqs269->regmap, IQS269_SYS_SETTINGS, sys_reg, - sizeof(*sys_reg)); + error = regmap_raw_write(iqs269->regmap, IQS269_SYS_SETTINGS, + &iqs269->sys_reg, sizeof(iqs269->sys_reg)); if (error) goto err_mutex; @@ -1349,6 +1326,7 @@ static ssize_t hall_bin_show(struct device *dev, struct device_attribute *attr, char *buf) { struct iqs269_private *iqs269 = dev_get_drvdata(dev); + struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; struct i2c_client *client = iqs269->client; unsigned int val; int error; @@ -1363,8 +1341,8 @@ static ssize_t hall_bin_show(struct device *dev, if (error) return error; - switch (iqs269->ch_reg[IQS269_CHx_HALL_ACTIVE].rx_enable & - iqs269->ch_reg[IQS269_CHx_HALL_INACTIVE].rx_enable) { + switch (ch_reg[IQS269_CHx_HALL_ACTIVE].rx_enable & + ch_reg[IQS269_CHx_HALL_INACTIVE].rx_enable) { case IQS269_HALL_PAD_R: val &= IQS269_CAL_DATA_A_HALL_BIN_R_MASK; val >>= IQS269_CAL_DATA_A_HALL_BIN_R_SHIFT; @@ -1444,9 +1422,10 @@ static ssize_t rx_enable_show(struct device *dev, struct device_attribute *attr, char *buf) { struct iqs269_private *iqs269 = dev_get_drvdata(dev); + struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; return scnprintf(buf, PAGE_SIZE, "%u\n", - iqs269->ch_reg[iqs269->ch_num].rx_enable); + ch_reg[iqs269->ch_num].rx_enable); } static ssize_t rx_enable_store(struct device *dev, @@ -1454,6 +1433,7 @@ static ssize_t rx_enable_store(struct device *dev, size_t count) { struct iqs269_private *iqs269 = dev_get_drvdata(dev); + struct iqs269_ch_reg *ch_reg = iqs269->sys_reg.ch_reg; unsigned int val; int error; @@ -1466,7 +1446,7 @@ static ssize_t rx_enable_store(struct device *dev, mutex_lock(&iqs269->lock); - iqs269->ch_reg[iqs269->ch_num].rx_enable = val; + ch_reg[iqs269->ch_num].rx_enable = val; iqs269->ati_current = false; mutex_unlock(&iqs269->lock); From 44a2a912c75049fa6cb2306ec8bc1276544b0c62 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 6 May 2021 02:45:15 +0900 Subject: [PATCH 1737/4345] linux/kconfig.h: replace IF_ENABLED() with PTR_IF() in [ Upstream commit 0ab1438bad43d95877f848b7df551bd431680270 ] is included from all the kernel-space source files, including C, assembly, linker scripts. It is intended to contain a minimal set of macros to evaluate CONFIG options. IF_ENABLED() is an intruder here because (x ? y : z) is C code, which should not be included from assembly files or linker scripts. Also, is no longer self-contained because NULL is defined in . Move IF_ENABLED() out to as PTR_IF(). PTF_IF() takes the general boolean expression instead of a CONFIG option so that it fits better in . Signed-off-by: Masahiro Yamada Reviewed-by: Kees Cook Stable-dep-of: 18ab69c8ca56 ("Input: iqs269a - do not poll during suspend or resume") Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-ingenic.c | 3 +++ include/linux/kernel.h | 2 ++ 2 files changed, 5 insertions(+) diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index e0df5ad6741d..4d07c531371c 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -2826,6 +2827,8 @@ static int __init ingenic_pinctrl_probe(struct platform_device *pdev) return 0; } +#define IF_ENABLED(cfg, ptr) PTR_IF(IS_ENABLED(cfg), (ptr)) + static const struct of_device_id ingenic_pinctrl_of_match[] = { { .compatible = "ingenic,jz4740-pinctrl", .data = &jz4740_chip_info }, { .compatible = "ingenic,jz4725b-pinctrl", .data = &jz4725b_chip_info }, diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 394f10fc29aa..66948e1bf4fa 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -47,6 +47,8 @@ */ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) +#define PTR_IF(cond, ptr) ((cond) ? (ptr) : NULL) + #define u64_to_user_ptr(x) ( \ { \ typecheck(u64, (x)); \ From 7beb9b4538e785a72061a4cff9afa18d77b943f4 Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Fri, 23 Dec 2022 17:40:17 +0300 Subject: [PATCH 1738/4345] clk: renesas: cpg-mssr: Fix use after free if cpg_mssr_common_init() failed [ Upstream commit fbfd614aeaa2853c2c575299dfe2458db8eff67e ] If cpg_mssr_common_init() fails after assigning priv to global variable cpg_mssr_priv, it deallocates priv, but cpg_mssr_priv keeps dangling pointer that potentially can be used later. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 1f7db7bbf031 ("clk: renesas: cpg-mssr: Add early clock support") Signed-off-by: Alexey Khoroshilov Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/1671806417-32623-1-git-send-email-khoroshilov@ispras.ru Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- drivers/clk/renesas/renesas-cpg-mssr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c index 94db88370337..12e5a7881977 100644 --- a/drivers/clk/renesas/renesas-cpg-mssr.c +++ b/drivers/clk/renesas/renesas-cpg-mssr.c @@ -960,7 +960,6 @@ static int __init cpg_mssr_common_init(struct device *dev, goto out_err; } - cpg_mssr_priv = priv; priv->num_core_clks = info->num_total_core_clks; priv->num_mod_clks = info->num_hw_mod_clks; priv->last_dt_core_clk = info->last_dt_core_clk; @@ -990,6 +989,8 @@ static int __init cpg_mssr_common_init(struct device *dev, if (error) goto out_err; + cpg_mssr_priv = priv; + return 0; out_err: From 092f17eca84be0f0b7bd9dc70a9e3bd9e93e3329 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 11 Jan 2023 09:23:34 +0100 Subject: [PATCH 1739/4345] clk: renesas: cpg-mssr: Remove superfluous check in resume code [ Upstream commit 1c052043c79af5f70e80e2acd4dd70904ae08666 ] When the code flow arrives at printing the error message in cpg_mssr_resume_noirq(), we know for sure that we are not running on an RZ/A Soc, as the code checked for that before. Fixes: ace342097768e35f ("clk: renesas: cpg-mssr: Fix STBCR suspend/resume handling") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/144a3e66d748c0c17f3524ac8fa6ece5bf5b6f1e.1673425314.git.geert+renesas@glider.be Signed-off-by: Sasha Levin --- drivers/clk/renesas/renesas-cpg-mssr.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c index 12e5a7881977..a5a68e1e7549 100644 --- a/drivers/clk/renesas/renesas-cpg-mssr.c +++ b/drivers/clk/renesas/renesas-cpg-mssr.c @@ -914,9 +914,8 @@ static int cpg_mssr_resume_noirq(struct device *dev) } if (!i) - dev_warn(dev, "Failed to enable %s%u[0x%x]\n", - priv->reg_layout == CLK_REG_LAYOUT_RZ_A ? - "STB" : "SMSTP", reg, oldval & mask); + dev_warn(dev, "Failed to enable SMSTP%u[0x%x]\n", reg, + oldval & mask); } return 0; From 092effd9f99282dbc936b9597dfec0e8d8cb66fa Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 4 Jan 2023 19:00:29 +0800 Subject: [PATCH 1740/4345] clk: imx: avoid memory leak [ Upstream commit f4419db4086e8c31821da14140e81498516a3c75 ] In case imx_register_uart_clocks return early, the imx_uart_clocks memory will be no freed. So execute kfree always to avoid memory leak. Fixes: 379c9a24cc23 ("clk: imx: Fix reparenting of UARTs not associated with stdout") Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230104110032.1220721-2-peng.fan@oss.nxp.com Signed-off-by: Sasha Levin --- drivers/clk/imx/clk.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk.c b/drivers/clk/imx/clk.c index 7cc669934253..d4cf0c7045ab 100644 --- a/drivers/clk/imx/clk.c +++ b/drivers/clk/imx/clk.c @@ -201,9 +201,10 @@ static int __init imx_clk_disable_uart(void) clk_disable_unprepare(imx_uart_clocks[i]); clk_put(imx_uart_clocks[i]); } - kfree(imx_uart_clocks); } + kfree(imx_uart_clocks); + return 0; } late_initcall_sync(imx_clk_disable_uart); From 7f2034b9b0610c0fa1cc623287c315de70faec9f Mon Sep 17 00:00:00 2001 From: Luca Ellero Date: Thu, 26 Jan 2023 11:52:25 +0100 Subject: [PATCH 1741/4345] Input: ads7846 - don't report pressure for ads7845 [ Upstream commit d50584d783313c8b05b84d0b07a2142f1bde46dd ] ADS7845 doesn't support pressure. Avoid the following error reported by libinput-list-devices: "ADS7845 Touchscreen: kernel bug: device has min == max on ABS_PRESSURE". Fixes: ffa458c1bd9b ("spi: ads7846 driver") Signed-off-by: Luca Ellero Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230126105227.47648-2-l.ellero@asem.it Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/touchscreen/ads7846.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index ff97897feaf2..370e0dbc02de 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -1381,8 +1381,9 @@ static int ads7846_probe(struct spi_device *spi) pdata->y_min ? : 0, pdata->y_max ? : MAX_12BIT, 0, 0); - input_set_abs_params(input_dev, ABS_PRESSURE, - pdata->pressure_min, pdata->pressure_max, 0, 0); + if (ts->model != 7845) + input_set_abs_params(input_dev, ABS_PRESSURE, + pdata->pressure_min, pdata->pressure_max, 0, 0); /* * Parse common framework properties. Must be done here to ensure the From a6c43844462ec89b6fe796ba91614f7f9f280fc2 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 11 Nov 2020 16:39:05 -0800 Subject: [PATCH 1742/4345] Input: ads7846 - convert to full duplex [ Upstream commit 9c9509717b53e701469493a8d87ed42c7d782502 ] Starting with 3eac5c7e44f3 ("Input: ads7846 - extend the driver for ads7845 controller support"), the ads7845 was partially converted to full duplex mode. Since it is not touchscreen controller specific, it is better to extend this conversion to cover entire driver. This will reduce CPU load and make driver more readable. Signed-off-by: Oleksij Rempel Link: https://lore.kernel.org/r/20201110085041.16303-2-o.rempel@pengutronix.de Signed-off-by: Dmitry Torokhov Stable-dep-of: 13f82ca3878d ("Input: ads7846 - always set last command to PWRDOWN") Signed-off-by: Sasha Levin --- drivers/input/touchscreen/ads7846.c | 192 +++++++++------------------- 1 file changed, 62 insertions(+), 130 deletions(-) diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index 370e0dbc02de..04ca0e13acd3 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -63,19 +63,26 @@ /* this driver doesn't aim at the peak continuous sample rate */ #define SAMPLE_BITS (8 /*cmd*/ + 16 /*sample*/ + 2 /* before, after */) -struct ts_event { +struct ads7846_buf { + u8 cmd; /* - * For portability, we can't read 12 bit values using SPI (which - * would make the controller deliver them as native byte order u16 - * with msbs zeroed). Instead, we read them as two 8-bit values, - * *** WHICH NEED BYTESWAPPING *** and range adjustment. + * This union is a temporary hack. The driver does an in-place + * endianness conversion. This will be cleaned up in the next + * patch. */ - u16 x; - u16 y; - u16 z1, z2; - bool ignore; - u8 x_buf[3]; - u8 y_buf[3]; + union { + __be16 data_be16; + u16 data; + }; +} __packed; + + +struct ts_event { + bool ignore; + struct ads7846_buf x; + struct ads7846_buf y; + struct ads7846_buf z1; + struct ads7846_buf z2; }; /* @@ -84,11 +91,12 @@ struct ts_event { * systems where main memory is not DMA-coherent (most non-x86 boards). */ struct ads7846_packet { - u8 read_x, read_y, read_z1, read_z2, pwrdown; - u16 dummy; /* for the pwrdown read */ - struct ts_event tc; - /* for ads7845 with mpc5121 psc spi we use 3-byte buffers */ - u8 read_x_cmd[3], read_y_cmd[3], pwrdown_cmd[3]; + struct ts_event tc; + struct ads7846_buf read_x_cmd; + struct ads7846_buf read_y_cmd; + struct ads7846_buf read_z1_cmd; + struct ads7846_buf read_z2_cmd; + struct ads7846_buf pwrdown_cmd; }; struct ads7846 { @@ -687,16 +695,9 @@ static int ads7846_get_value(struct ads7846 *ts, struct spi_message *m) int value; struct spi_transfer *t = list_entry(m->transfers.prev, struct spi_transfer, transfer_list); + struct ads7846_buf *buf = t->rx_buf; - if (ts->model == 7845) { - value = be16_to_cpup((__be16 *)&(((char *)t->rx_buf)[1])); - } else { - /* - * adjust: on-wire is a must-ignore bit, a BE12 value, then - * padding; built from two 8 bit values written msb-first. - */ - value = be16_to_cpup((__be16 *)t->rx_buf); - } + value = be16_to_cpup(&buf->data_be16); /* enforce ADC output is 12 bits width */ return (value >> 3) & 0xfff; @@ -706,8 +707,9 @@ static void ads7846_update_value(struct spi_message *m, int val) { struct spi_transfer *t = list_entry(m->transfers.prev, struct spi_transfer, transfer_list); + struct ads7846_buf *buf = t->rx_buf; - *(u16 *)t->rx_buf = val; + buf->data = val; } static void ads7846_read_state(struct ads7846 *ts) @@ -775,16 +777,14 @@ static void ads7846_report_state(struct ads7846 *ts) * from on-the-wire format as part of debouncing to get stable * readings. */ + x = packet->tc.x.data; + y = packet->tc.y.data; if (ts->model == 7845) { - x = *(u16 *)packet->tc.x_buf; - y = *(u16 *)packet->tc.y_buf; z1 = 0; z2 = 0; } else { - x = packet->tc.x; - y = packet->tc.y; - z1 = packet->tc.z1; - z2 = packet->tc.z2; + z1 = packet->tc.z1.data; + z2 = packet->tc.z2.data; } /* range filtering */ @@ -1002,26 +1002,11 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, spi_message_init(m); m->context = ts; - if (ts->model == 7845) { - packet->read_y_cmd[0] = READ_Y(vref); - packet->read_y_cmd[1] = 0; - packet->read_y_cmd[2] = 0; - x->tx_buf = &packet->read_y_cmd[0]; - x->rx_buf = &packet->tc.y_buf[0]; - x->len = 3; - spi_message_add_tail(x, m); - } else { - /* y- still on; turn on only y+ (and ADC) */ - packet->read_y = READ_Y(vref); - x->tx_buf = &packet->read_y; - x->len = 1; - spi_message_add_tail(x, m); - - x++; - x->rx_buf = &packet->tc.y; - x->len = 2; - spi_message_add_tail(x, m); - } + packet->read_y_cmd.cmd = READ_Y(vref); + x->tx_buf = &packet->read_y_cmd; + x->rx_buf = &packet->tc.y; + x->len = 3; + spi_message_add_tail(x, m); /* * The first sample after switching drivers can be low quality; @@ -1031,15 +1016,11 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, if (pdata->settle_delay_usecs) { x->delay.value = pdata->settle_delay_usecs; x->delay.unit = SPI_DELAY_UNIT_USECS; - x++; - x->tx_buf = &packet->read_y; - x->len = 1; - spi_message_add_tail(x, m); - x++; + x->tx_buf = &packet->read_y_cmd; x->rx_buf = &packet->tc.y; - x->len = 2; + x->len = 3; spi_message_add_tail(x, m); } @@ -1048,28 +1029,13 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, spi_message_init(m); m->context = ts; - if (ts->model == 7845) { - x++; - packet->read_x_cmd[0] = READ_X(vref); - packet->read_x_cmd[1] = 0; - packet->read_x_cmd[2] = 0; - x->tx_buf = &packet->read_x_cmd[0]; - x->rx_buf = &packet->tc.x_buf[0]; - x->len = 3; - spi_message_add_tail(x, m); - } else { - /* turn y- off, x+ on, then leave in lowpower */ - x++; - packet->read_x = READ_X(vref); - x->tx_buf = &packet->read_x; - x->len = 1; - spi_message_add_tail(x, m); - - x++; - x->rx_buf = &packet->tc.x; - x->len = 2; - spi_message_add_tail(x, m); - } + /* turn y- off, x+ on, then leave in lowpower */ + x++; + packet->read_x_cmd.cmd = READ_X(vref); + x->tx_buf = &packet->read_x_cmd; + x->rx_buf = &packet->tc.x; + x->len = 3; + spi_message_add_tail(x, m); /* ... maybe discard first sample ... */ if (pdata->settle_delay_usecs) { @@ -1077,13 +1043,9 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, x->delay.unit = SPI_DELAY_UNIT_USECS; x++; - x->tx_buf = &packet->read_x; - x->len = 1; - spi_message_add_tail(x, m); - - x++; + x->tx_buf = &packet->read_x_cmd; x->rx_buf = &packet->tc.x; - x->len = 2; + x->len = 3; spi_message_add_tail(x, m); } @@ -1095,14 +1057,10 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, m->context = ts; x++; - packet->read_z1 = READ_Z1(vref); - x->tx_buf = &packet->read_z1; - x->len = 1; - spi_message_add_tail(x, m); - - x++; + packet->read_z1_cmd.cmd = READ_Z1(vref); + x->tx_buf = &packet->read_z1_cmd; x->rx_buf = &packet->tc.z1; - x->len = 2; + x->len = 3; spi_message_add_tail(x, m); /* ... maybe discard first sample ... */ @@ -1111,13 +1069,9 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, x->delay.unit = SPI_DELAY_UNIT_USECS; x++; - x->tx_buf = &packet->read_z1; - x->len = 1; - spi_message_add_tail(x, m); - - x++; + x->tx_buf = &packet->read_z1_cmd; x->rx_buf = &packet->tc.z1; - x->len = 2; + x->len = 3; spi_message_add_tail(x, m); } @@ -1127,14 +1081,10 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, m->context = ts; x++; - packet->read_z2 = READ_Z2(vref); - x->tx_buf = &packet->read_z2; - x->len = 1; - spi_message_add_tail(x, m); - - x++; + packet->read_z2_cmd.cmd = READ_Z2(vref); + x->tx_buf = &packet->read_z2_cmd; x->rx_buf = &packet->tc.z2; - x->len = 2; + x->len = 3; spi_message_add_tail(x, m); /* ... maybe discard first sample ... */ @@ -1143,13 +1093,9 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, x->delay.unit = SPI_DELAY_UNIT_USECS; x++; - x->tx_buf = &packet->read_z2; - x->len = 1; - spi_message_add_tail(x, m); - - x++; + x->tx_buf = &packet->read_z2_cmd; x->rx_buf = &packet->tc.z2; - x->len = 2; + x->len = 3; spi_message_add_tail(x, m); } } @@ -1160,24 +1106,10 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, spi_message_init(m); m->context = ts; - if (ts->model == 7845) { - x++; - packet->pwrdown_cmd[0] = PWRDOWN; - packet->pwrdown_cmd[1] = 0; - packet->pwrdown_cmd[2] = 0; - x->tx_buf = &packet->pwrdown_cmd[0]; - x->len = 3; - } else { - x++; - packet->pwrdown = PWRDOWN; - x->tx_buf = &packet->pwrdown; - x->len = 1; - spi_message_add_tail(x, m); - - x++; - x->rx_buf = &packet->dummy; - x->len = 2; - } + x++; + packet->pwrdown_cmd.cmd = PWRDOWN; + x->tx_buf = &packet->pwrdown_cmd; + x->len = 3; CS_CHANGE(*x); spi_message_add_tail(x, m); From d247f3527b314d2b197b9cea5615edeaa488bfa9 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 20 Jan 2021 23:18:28 -0800 Subject: [PATCH 1743/4345] Input: ads7846 - convert to one message [ Upstream commit 6965eece2a89c3f1d00881c6052ee1e987870c08 ] Convert multiple full duplex transfers in to a single transfer to reduce CPU load. Current driver version support following filtering modes: - ads7846_no_filter() - not filtered - ads7846_debounce_filter() - driver specific debounce filter - pdata->filter - platform specific debounce filter (do any platform provides such filter?) Without filter this HW is not really usable, since the physic of resistive touchscreen can provide some bounce effects. With driver internal filter, we have constant amount of retries + debounce retries if some anomaly was detected. High amount of tiny SPI transfers is the primer reason of high CPU load and interrupt frequency. This patch create one SPI transfer with all fields and not optional retires. If bounce anomaly was detected, we will make more transfer if needed. Without this patch, we will get about 10% CPU load on iMX6S on pen-down event. For example by holding stylus on the screen. With this patch, depending in the amount of retries, the CPU load will be 1% with "ti,debounce-rep = <3>". One buffer transfer allows us to use PIO FIFO or DMA engine, depending on the platform. Signed-off-by: Oleksij Rempel Link: https://lore.kernel.org/r/20201110085041.16303-3-o.rempel@pengutronix.de Signed-off-by: Dmitry Torokhov Stable-dep-of: 13f82ca3878d ("Input: ads7846 - always set last command to PWRDOWN") Signed-off-by: Sasha Levin --- drivers/input/touchscreen/ads7846.c | 376 ++++++++++++++-------------- 1 file changed, 193 insertions(+), 183 deletions(-) diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index 04ca0e13acd3..0610fab5ed93 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -65,24 +65,13 @@ struct ads7846_buf { u8 cmd; - /* - * This union is a temporary hack. The driver does an in-place - * endianness conversion. This will be cleaned up in the next - * patch. - */ - union { - __be16 data_be16; - u16 data; - }; + __be16 data; } __packed; - -struct ts_event { - bool ignore; - struct ads7846_buf x; - struct ads7846_buf y; - struct ads7846_buf z1; - struct ads7846_buf z2; +struct ads7846_buf_layout { + unsigned int offset; + unsigned int count; + unsigned int skip; }; /* @@ -91,12 +80,18 @@ struct ts_event { * systems where main memory is not DMA-coherent (most non-x86 boards). */ struct ads7846_packet { - struct ts_event tc; - struct ads7846_buf read_x_cmd; - struct ads7846_buf read_y_cmd; - struct ads7846_buf read_z1_cmd; - struct ads7846_buf read_z2_cmd; + unsigned int count; + unsigned int count_skip; + unsigned int cmds; + unsigned int last_cmd_idx; + struct ads7846_buf_layout l[5]; + struct ads7846_buf *rx; + struct ads7846_buf *tx; + struct ads7846_buf pwrdown_cmd; + + bool ignore; + u16 x, y, z1, z2; }; struct ads7846 { @@ -195,7 +190,6 @@ struct ads7846 { #define READ_Y(vref) (READ_12BIT_DFR(y, 1, vref)) #define READ_Z1(vref) (READ_12BIT_DFR(z1, 1, vref)) #define READ_Z2(vref) (READ_12BIT_DFR(z2, 1, vref)) - #define READ_X(vref) (READ_12BIT_DFR(x, 1, vref)) #define PWRDOWN (READ_12BIT_DFR(y, 0, 0)) /* LAST */ @@ -208,6 +202,21 @@ struct ads7846 { #define REF_ON (READ_12BIT_DFR(x, 1, 1)) #define REF_OFF (READ_12BIT_DFR(y, 0, 0)) +/* Order commands in the most optimal way to reduce Vref switching and + * settling time: + * Measure: X; Vref: X+, X-; IN: Y+ + * Measure: Y; Vref: Y+, Y-; IN: X+ + * Measure: Z1; Vref: Y+, X-; IN: X+ + * Measure: Z2; Vref: Y+, X-; IN: Y- + */ +enum ads7846_cmds { + ADS7846_X, + ADS7846_Y, + ADS7846_Z1, + ADS7846_Z2, + ADS7846_PWDOWN, +}; + static int get_pendown_state(struct ads7846 *ts) { if (ts->get_pendown_state) @@ -690,26 +699,109 @@ static int ads7846_no_filter(void *ads, int data_idx, int *val) return ADS7846_FILTER_OK; } -static int ads7846_get_value(struct ads7846 *ts, struct spi_message *m) +static int ads7846_get_value(struct ads7846_buf *buf) { int value; - struct spi_transfer *t = - list_entry(m->transfers.prev, struct spi_transfer, transfer_list); - struct ads7846_buf *buf = t->rx_buf; - value = be16_to_cpup(&buf->data_be16); + value = be16_to_cpup(&buf->data); /* enforce ADC output is 12 bits width */ return (value >> 3) & 0xfff; } -static void ads7846_update_value(struct spi_message *m, int val) +static void ads7846_set_cmd_val(struct ads7846 *ts, enum ads7846_cmds cmd_idx, + u16 val) { - struct spi_transfer *t = - list_entry(m->transfers.prev, struct spi_transfer, transfer_list); - struct ads7846_buf *buf = t->rx_buf; + struct ads7846_packet *packet = ts->packet; - buf->data = val; + switch (cmd_idx) { + case ADS7846_Y: + packet->y = val; + break; + case ADS7846_X: + packet->x = val; + break; + case ADS7846_Z1: + packet->z1 = val; + break; + case ADS7846_Z2: + packet->z2 = val; + break; + default: + WARN_ON_ONCE(1); + } +} + +static u8 ads7846_get_cmd(enum ads7846_cmds cmd_idx, int vref) +{ + switch (cmd_idx) { + case ADS7846_Y: + return READ_Y(vref); + case ADS7846_X: + return READ_X(vref); + + /* 7846 specific commands */ + case ADS7846_Z1: + return READ_Z1(vref); + case ADS7846_Z2: + return READ_Z2(vref); + case ADS7846_PWDOWN: + return PWRDOWN; + default: + WARN_ON_ONCE(1); + } + + return 0; +} + +static bool ads7846_cmd_need_settle(enum ads7846_cmds cmd_idx) +{ + switch (cmd_idx) { + case ADS7846_X: + case ADS7846_Y: + case ADS7846_Z1: + case ADS7846_Z2: + return true; + case ADS7846_PWDOWN: + return false; + default: + WARN_ON_ONCE(1); + } + + return false; +} + +static int ads7846_filter(struct ads7846 *ts) +{ + struct ads7846_packet *packet = ts->packet; + int action; + int val; + unsigned int cmd_idx, b; + + packet->ignore = false; + for (cmd_idx = packet->last_cmd_idx; cmd_idx < packet->cmds - 1; cmd_idx++) { + struct ads7846_buf_layout *l = &packet->l[cmd_idx]; + + packet->last_cmd_idx = cmd_idx; + + for (b = l->skip; b < l->count; b++) { + val = ads7846_get_value(&packet->rx[l->offset + b]); + + action = ts->filter(ts->filter_data, cmd_idx, &val); + if (action == ADS7846_FILTER_REPEAT) { + if (b == l->count - 1) + return -EAGAIN; + } else if (action == ADS7846_FILTER_OK) { + ads7846_set_cmd_val(ts, cmd_idx, val); + break; + } else { + packet->ignore = true; + return 0; + } + } + } + + return 0; } static void ads7846_read_state(struct ads7846 *ts) @@ -717,52 +809,26 @@ static void ads7846_read_state(struct ads7846 *ts) struct ads7846_packet *packet = ts->packet; struct spi_message *m; int msg_idx = 0; - int val; - int action; int error; - while (msg_idx < ts->msg_count) { + packet->last_cmd_idx = 0; + while (true) { ts->wait_for_sync(); m = &ts->msg[msg_idx]; error = spi_sync(ts->spi, m); if (error) { dev_err(&ts->spi->dev, "spi_sync --> %d\n", error); - packet->tc.ignore = true; + packet->ignore = true; return; } - /* - * Last message is power down request, no need to convert - * or filter the value. - */ - if (msg_idx < ts->msg_count - 1) { + error = ads7846_filter(ts); + if (error) + continue; - val = ads7846_get_value(ts, m); - - action = ts->filter(ts->filter_data, msg_idx, &val); - switch (action) { - case ADS7846_FILTER_REPEAT: - continue; - - case ADS7846_FILTER_IGNORE: - packet->tc.ignore = true; - msg_idx = ts->msg_count - 1; - continue; - - case ADS7846_FILTER_OK: - ads7846_update_value(m, val); - packet->tc.ignore = false; - msg_idx++; - break; - - default: - BUG(); - } - } else { - msg_idx++; - } + return; } } @@ -772,19 +838,14 @@ static void ads7846_report_state(struct ads7846 *ts) unsigned int Rt; u16 x, y, z1, z2; - /* - * ads7846_get_value() does in-place conversion (including byte swap) - * from on-the-wire format as part of debouncing to get stable - * readings. - */ - x = packet->tc.x.data; - y = packet->tc.y.data; + x = packet->x; + y = packet->y; if (ts->model == 7845) { z1 = 0; z2 = 0; } else { - z1 = packet->tc.z1.data; - z2 = packet->tc.z2.data; + z1 = packet->z1; + z2 = packet->z2; } /* range filtering */ @@ -817,9 +878,9 @@ static void ads7846_report_state(struct ads7846 *ts) * the maximum. Don't report it to user space, repeat at least * once more the measurement */ - if (packet->tc.ignore || Rt > ts->pressure_max) { + if (packet->ignore || Rt > ts->pressure_max) { dev_vdbg(&ts->spi->dev, "ignored %d pressure %d\n", - packet->tc.ignore, Rt); + packet->ignore, Rt); return; } @@ -980,13 +1041,59 @@ static int ads7846_setup_pendown(struct spi_device *spi, * Set up the transfers to read touchscreen state; this assumes we * use formula #2 for pressure, not #3. */ -static void ads7846_setup_spi_msg(struct ads7846 *ts, +static int ads7846_setup_spi_msg(struct ads7846 *ts, const struct ads7846_platform_data *pdata) { struct spi_message *m = &ts->msg[0]; struct spi_transfer *x = ts->xfer; struct ads7846_packet *packet = ts->packet; int vref = pdata->keep_vref_on; + unsigned int count, offset = 0; + unsigned int cmd_idx, b; + unsigned long time; + size_t size = 0; + + /* time per bit */ + time = NSEC_PER_SEC / ts->spi->max_speed_hz; + + count = pdata->settle_delay_usecs * NSEC_PER_USEC / time; + packet->count_skip = DIV_ROUND_UP(count, 24); + + if (ts->debounce_max && ts->debounce_rep) + /* ads7846_debounce_filter() is making ts->debounce_rep + 2 + * reads. So we need to get all samples for normal case. */ + packet->count = ts->debounce_rep + 2; + else + packet->count = 1; + + if (ts->model == 7846) + packet->cmds = 5; /* x, y, z1, z2, pwdown */ + else + packet->cmds = 3; /* x, y, pwdown */ + + for (cmd_idx = 0; cmd_idx < packet->cmds; cmd_idx++) { + struct ads7846_buf_layout *l = &packet->l[cmd_idx]; + unsigned int max_count; + + if (ads7846_cmd_need_settle(cmd_idx)) + max_count = packet->count + packet->count_skip; + else + max_count = packet->count; + + l->offset = offset; + offset += max_count; + l->count = max_count; + l->skip = packet->count_skip; + size += sizeof(*packet->tx) * max_count; + } + + packet->tx = devm_kzalloc(&ts->spi->dev, size, GFP_KERNEL); + if (!packet->tx) + return -ENOMEM; + + packet->rx = devm_kzalloc(&ts->spi->dev, size, GFP_KERNEL); + if (!packet->rx) + return -ENOMEM; if (ts->model == 7873) { /* @@ -1002,117 +1109,20 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts, spi_message_init(m); m->context = ts; - packet->read_y_cmd.cmd = READ_Y(vref); - x->tx_buf = &packet->read_y_cmd; - x->rx_buf = &packet->tc.y; - x->len = 3; - spi_message_add_tail(x, m); + for (cmd_idx = 0; cmd_idx < packet->cmds; cmd_idx++) { + struct ads7846_buf_layout *l = &packet->l[cmd_idx]; + u8 cmd = ads7846_get_cmd(cmd_idx, vref); - /* - * The first sample after switching drivers can be low quality; - * optionally discard it, using a second one after the signals - * have had enough time to stabilize. - */ - if (pdata->settle_delay_usecs) { - x->delay.value = pdata->settle_delay_usecs; - x->delay.unit = SPI_DELAY_UNIT_USECS; - x++; - - x->tx_buf = &packet->read_y_cmd; - x->rx_buf = &packet->tc.y; - x->len = 3; - spi_message_add_tail(x, m); + for (b = 0; b < l->count; b++) + packet->tx[l->offset + b].cmd = cmd; } - ts->msg_count++; - m++; - spi_message_init(m); - m->context = ts; - - /* turn y- off, x+ on, then leave in lowpower */ - x++; - packet->read_x_cmd.cmd = READ_X(vref); - x->tx_buf = &packet->read_x_cmd; - x->rx_buf = &packet->tc.x; - x->len = 3; + x->tx_buf = packet->tx; + x->rx_buf = packet->rx; + x->len = size; spi_message_add_tail(x, m); - /* ... maybe discard first sample ... */ - if (pdata->settle_delay_usecs) { - x->delay.value = pdata->settle_delay_usecs; - x->delay.unit = SPI_DELAY_UNIT_USECS; - - x++; - x->tx_buf = &packet->read_x_cmd; - x->rx_buf = &packet->tc.x; - x->len = 3; - spi_message_add_tail(x, m); - } - - /* turn y+ off, x- on; we'll use formula #2 */ - if (ts->model == 7846) { - ts->msg_count++; - m++; - spi_message_init(m); - m->context = ts; - - x++; - packet->read_z1_cmd.cmd = READ_Z1(vref); - x->tx_buf = &packet->read_z1_cmd; - x->rx_buf = &packet->tc.z1; - x->len = 3; - spi_message_add_tail(x, m); - - /* ... maybe discard first sample ... */ - if (pdata->settle_delay_usecs) { - x->delay.value = pdata->settle_delay_usecs; - x->delay.unit = SPI_DELAY_UNIT_USECS; - - x++; - x->tx_buf = &packet->read_z1_cmd; - x->rx_buf = &packet->tc.z1; - x->len = 3; - spi_message_add_tail(x, m); - } - - ts->msg_count++; - m++; - spi_message_init(m); - m->context = ts; - - x++; - packet->read_z2_cmd.cmd = READ_Z2(vref); - x->tx_buf = &packet->read_z2_cmd; - x->rx_buf = &packet->tc.z2; - x->len = 3; - spi_message_add_tail(x, m); - - /* ... maybe discard first sample ... */ - if (pdata->settle_delay_usecs) { - x->delay.value = pdata->settle_delay_usecs; - x->delay.unit = SPI_DELAY_UNIT_USECS; - - x++; - x->tx_buf = &packet->read_z2_cmd; - x->rx_buf = &packet->tc.z2; - x->len = 3; - spi_message_add_tail(x, m); - } - } - - /* power down */ - ts->msg_count++; - m++; - spi_message_init(m); - m->context = ts; - - x++; - packet->pwrdown_cmd.cmd = PWRDOWN; - x->tx_buf = &packet->pwrdown_cmd; - x->len = 3; - - CS_CHANGE(*x); - spi_message_add_tail(x, m); + return 0; } #ifdef CONFIG_OF From 8d9b9e56c2b618bd3e45fdbdc2cc966d9f5efb50 Mon Sep 17 00:00:00 2001 From: Luca Ellero Date: Thu, 26 Jan 2023 11:52:26 +0100 Subject: [PATCH 1744/4345] Input: ads7846 - always set last command to PWRDOWN [ Upstream commit 13f82ca3878db8284a70ef9711d7f710a31eb562 ] Controllers that report pressure (e.g. ADS7846) use 5 commands and the correct sequence is READ_X, READ_Y, READ_Z1, READ_Z2, PWRDOWN. Controllers that don't report pressure (e.g. ADS7845/ADS7843) use only 3 commands and the correct sequence should be READ_X, READ_Y, PWRDOWN. But the sequence sent was incorrect: READ_X, READ_Y, READ_Z1. Fix this by setting the third (and last) command to PWRDOWN. Fixes: ffa458c1bd9b ("spi: ads7846 driver") Signed-off-by: Luca Ellero Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230126105227.47648-3-l.ellero@asem.it Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/touchscreen/ads7846.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index 0610fab5ed93..9f5cc42a567a 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -1075,6 +1075,9 @@ static int ads7846_setup_spi_msg(struct ads7846 *ts, struct ads7846_buf_layout *l = &packet->l[cmd_idx]; unsigned int max_count; + if (cmd_idx == packet->cmds - 1) + cmd_idx = ADS7846_PWDOWN; + if (ads7846_cmd_need_settle(cmd_idx)) max_count = packet->count + packet->count_skip; else @@ -1111,7 +1114,12 @@ static int ads7846_setup_spi_msg(struct ads7846 *ts, for (cmd_idx = 0; cmd_idx < packet->cmds; cmd_idx++) { struct ads7846_buf_layout *l = &packet->l[cmd_idx]; - u8 cmd = ads7846_get_cmd(cmd_idx, vref); + u8 cmd; + + if (cmd_idx == packet->cmds - 1) + cmd_idx = ADS7846_PWDOWN; + + cmd = ads7846_get_cmd(cmd_idx, vref); for (b = 0; b < l->count; b++) packet->tx[l->offset + b].cmd = cmd; From 1957c5b5ec4bb492150acb9ce97afcf1b07bc2a8 Mon Sep 17 00:00:00 2001 From: Luca Ellero Date: Thu, 26 Jan 2023 11:52:27 +0100 Subject: [PATCH 1745/4345] Input: ads7846 - don't check penirq immediately for 7845 [ Upstream commit fa9f4275b20ec7b2a8fb05c66362d10b36f9efec ] To discard false readings, one should use "ti,penirq-recheck-delay-usecs". Checking get_pendown_state() at the beginning, most of the time fails causing malfunctioning. Fixes: ffa458c1bd9b ("spi: ads7846 driver") Signed-off-by: Luca Ellero Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230126105227.47648-4-l.ellero@asem.it Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/touchscreen/ads7846.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index 9f5cc42a567a..1753288cedde 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -852,14 +852,8 @@ static void ads7846_report_state(struct ads7846 *ts) if (x == MAX_12BIT) x = 0; - if (ts->model == 7843) { + if (ts->model == 7843 || ts->model == 7845) { Rt = ts->pressure_max / 2; - } else if (ts->model == 7845) { - if (get_pendown_state(ts)) - Rt = ts->pressure_max / 2; - else - Rt = 0; - dev_vdbg(&ts->spi->dev, "x/y: %d/%d, PD %d\n", x, y, Rt); } else if (likely(x && z1)) { /* compute touch pressure resistance using equation #2 */ Rt = z2; From 241048adcb40246908a486258e98bd190e60d22c Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 1 Feb 2023 19:23:04 +0200 Subject: [PATCH 1746/4345] clk: qcom: gpucc-sc7180: fix clk_dis_wait being programmed for CX GDSC [ Upstream commit 658c82caffa042b351f5a1b6325819297a951a04 ] The gdsc_init() function will rewrite the CLK_DIS_WAIT field while registering the GDSC (writing the value 0x2 by default). This will override the setting done in the driver's probe function. Set cx_gdsc.clk_dis_wait_val to 8 to follow the intention of the probe function. Fixes: 745ff069a49c ("clk: qcom: Add graphics clock controller driver for SC7180") Reviewed-by: Stephen Boyd Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230201172305.993146-1-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/clk/qcom/gpucc-sc7180.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/clk/qcom/gpucc-sc7180.c b/drivers/clk/qcom/gpucc-sc7180.c index 88a739b6fec3..c51114e7e1e6 100644 --- a/drivers/clk/qcom/gpucc-sc7180.c +++ b/drivers/clk/qcom/gpucc-sc7180.c @@ -21,8 +21,6 @@ #define CX_GMU_CBCR_SLEEP_SHIFT 4 #define CX_GMU_CBCR_WAKE_MASK 0xF #define CX_GMU_CBCR_WAKE_SHIFT 8 -#define CLK_DIS_WAIT_SHIFT 12 -#define CLK_DIS_WAIT_MASK (0xf << CLK_DIS_WAIT_SHIFT) enum { P_BI_TCXO, @@ -163,6 +161,7 @@ static struct clk_branch gpu_cc_cxo_clk = { static struct gdsc cx_gdsc = { .gdscr = 0x106c, .gds_hw_ctrl = 0x1540, + .clk_dis_wait_val = 8, .pd = { .name = "cx_gdsc", }, @@ -245,10 +244,6 @@ static int gpu_cc_sc7180_probe(struct platform_device *pdev) value = 0xF << CX_GMU_CBCR_WAKE_SHIFT | 0xF << CX_GMU_CBCR_SLEEP_SHIFT; regmap_update_bits(regmap, 0x1098, mask, value); - /* Configure clk_dis_wait for gpu_cx_gdsc */ - regmap_update_bits(regmap, 0x106c, CLK_DIS_WAIT_MASK, - 8 << CLK_DIS_WAIT_SHIFT); - return qcom_cc_really_probe(pdev, &gpu_cc_sc7180_desc, regmap); } From 15fed9258b844b4cec78f1c38a07ff33af1410c2 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 1 Feb 2023 19:23:05 +0200 Subject: [PATCH 1747/4345] clk: qcom: gpucc-sdm845: fix clk_dis_wait being programmed for CX GDSC [ Upstream commit cb81719e3c1165ef1bc33137dc628f750eed8ea4 ] The gdsc_init() function will rewrite the CLK_DIS_WAIT field while registering the GDSC (writing the value 0x2 by default). This will override the setting done in the driver's probe function. Set cx_gdsc.clk_dis_wait_val to 8 to follow the intention of the probe function. Fixes: 453361cdd757 ("clk: qcom: Add graphics clock controller driver for SDM845") Reviewed-by: Stephen Boyd Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230201172305.993146-2-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/clk/qcom/gpucc-sdm845.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/clk/qcom/gpucc-sdm845.c b/drivers/clk/qcom/gpucc-sdm845.c index 5663698b306b..658c6ac700e1 100644 --- a/drivers/clk/qcom/gpucc-sdm845.c +++ b/drivers/clk/qcom/gpucc-sdm845.c @@ -22,8 +22,6 @@ #define CX_GMU_CBCR_SLEEP_SHIFT 4 #define CX_GMU_CBCR_WAKE_MASK 0xf #define CX_GMU_CBCR_WAKE_SHIFT 8 -#define CLK_DIS_WAIT_SHIFT 12 -#define CLK_DIS_WAIT_MASK (0xf << CLK_DIS_WAIT_SHIFT) enum { P_BI_TCXO, @@ -124,6 +122,7 @@ static struct clk_branch gpu_cc_cxo_clk = { static struct gdsc gpu_cx_gdsc = { .gdscr = 0x106c, .gds_hw_ctrl = 0x1540, + .clk_dis_wait_val = 0x8, .pd = { .name = "gpu_cx_gdsc", }, @@ -196,10 +195,6 @@ static int gpu_cc_sdm845_probe(struct platform_device *pdev) value = 0xf << CX_GMU_CBCR_WAKE_SHIFT | 0xf << CX_GMU_CBCR_SLEEP_SHIFT; regmap_update_bits(regmap, 0x1098, mask, value); - /* Configure clk_dis_wait for gpu_cx_gdsc */ - regmap_update_bits(regmap, 0x106c, CLK_DIS_WAIT_MASK, - 8 << CLK_DIS_WAIT_SHIFT); - return qcom_cc_really_probe(pdev, &gpu_cc_sdm845_desc, regmap); } From 4f060379aaf2a05b13bf27cccf93555e640e90a1 Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Fri, 20 Jan 2023 10:32:15 +0100 Subject: [PATCH 1748/4345] powerpc/powernv/ioda: Skip unallocated resources when mapping to PE [ Upstream commit e64e71056f323a1e178dccf04d4c0f032d84436c ] pnv_ioda_setup_pe_res() calls opal to map a resource with a PE. However, the code assumes the resource is allocated and it uses the resource address to find out the segment(s) which need to be mapped to the PE. In the unlikely case where the resource hasn't been allocated, the computation for the segment number is garbage, which can lead to invalid memory access and potentially a kernel crash, such as: [ ] pci_bus 0002:02: Configuring PE for bus [ ] pci 0002:02 : [PE# fc] Secondary bus 0x0000000000000002..0x0000000000000002 associated with PE#fc [ ] BUG: Kernel NULL pointer dereference on write at 0x00000000 [ ] Faulting instruction address: 0xc00000000005eac4 [ ] Oops: Kernel access of bad area, sig: 7 [#1] [ ] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA PowerNV [ ] Modules linked in: [ ] CPU: 12 PID: 1 Comm: swapper/20 Not tainted 5.10.50-openpower1 #2 [ ] NIP: c00000000005eac4 LR: c00000000005ea44 CTR: 0000000030061b9c [ ] REGS: c000200007383650 TRAP: 0300 Not tainted (5.10.50-openpower1) [ ] MSR: 9000000000009033 CR: 44000224 XER: 20040000 [ ] CFAR: c00000000005eaa0 DAR: 0000000000000000 DSISR: 02080000 IRQMASK: 0 [ ] GPR00: c00000000005dd98 c0002000073838e0 c00000000185de00 c000200fff018960 [ ] GPR04: 00000000000000fc 0000000000000003 0000000000000000 0000000000000000 [ ] GPR08: 0000000000000000 0000000000000000 0000000000000000 9000000000001033 [ ] GPR12: 0000000031cb0000 c000000ffffe6a80 c000000000010a58 0000000000000000 [ ] GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ ] GPR20: 0000000000000000 0000000000000000 0000000000000000 c00000000711e200 [ ] GPR24: 0000000000000100 c000200009501120 c00020000cee2800 00000000000003ff [ ] GPR28: c000200fff018960 0000000000000000 c000200ffcb7fd00 0000000000000000 [ ] NIP [c00000000005eac4] pnv_ioda_setup_pe_res+0x94/0x1a0 [ ] LR [c00000000005ea44] pnv_ioda_setup_pe_res+0x14/0x1a0 [ ] Call Trace: [ ] [c0002000073838e0] [c00000000005eb98] pnv_ioda_setup_pe_res+0x168/0x1a0 (unreliable) [ ] [c000200007383970] [c00000000005dd98] pnv_pci_ioda_dma_dev_setup+0x43c/0x970 [ ] [c000200007383a60] [c000000000032cdc] pcibios_bus_add_device+0x78/0x18c [ ] [c000200007383aa0] [c00000000028f2bc] pci_bus_add_device+0x28/0xbc [ ] [c000200007383b10] [c00000000028f3a0] pci_bus_add_devices+0x50/0x7c [ ] [c000200007383b50] [c00000000028f3c4] pci_bus_add_devices+0x74/0x7c [ ] [c000200007383b90] [c00000000028f3c4] pci_bus_add_devices+0x74/0x7c [ ] [c000200007383bd0] [c00000000069ad0c] pcibios_init+0xf0/0x104 [ ] [c000200007383c50] [c0000000000106d8] do_one_initcall+0x84/0x1c4 [ ] [c000200007383d20] [c0000000006910b8] kernel_init_freeable+0x264/0x268 [ ] [c000200007383dc0] [c000000000010a68] kernel_init+0x18/0x138 [ ] [c000200007383e20] [c00000000000cbfc] ret_from_kernel_thread+0x5c/0x80 [ ] Instruction dump: [ ] 7f89e840 409d000c 7fbbf840 409c000c 38210090 4848f448 809c002c e95e0120 [ ] 7ba91764 38a00003 57a7043e 38c00000 <7c8a492e> 5484043e e87e0018 4bff23bd Hitting the problem is not that easy. It was seen with a (semi-bogus) PCI device with a class code of 0. The generic PCI framework doesn't allocate resources in such a case. The patch is simply skipping resources which are still flagged with IORESOURCE_UNSET. We don't have the problem with 64-bit mem resources, as the address of the resource is checked to be within the range of the 64-bit mmio window. See pnv_ioda_reserve_dev_m64_pe() and pnv_pci_is_m64(). Reported-by: Andrew Jeffery Fixes: 23e79425fe7c ("powerpc/powernv: Simplify pnv_ioda_setup_pe_seg()") Signed-off-by: Frederic Barrat Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230120093215.19496-1-fbarrat@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/powernv/pci-ioda.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 2b4ceb5e6ce4..a1e6dd47743f 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2260,7 +2260,8 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe, int index; int64_t rc; - if (!res || !res->flags || res->start > res->end) + if (!res || !res->flags || res->start > res->end || + res->flags & IORESOURCE_UNSET) return; if (res->flags & IORESOURCE_IO) { From 831a2d8de1d605be23f3afb0caa4690a5bfc3bfb Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Tue, 3 Jan 2023 17:23:30 +0800 Subject: [PATCH 1749/4345] clk: Honor CLK_OPS_PARENT_ENABLE in clk_core_is_enabled() [ Upstream commit 79200d5851c8e7179f68a4a6f162d8f1bde4986f ] In the previous commits that added CLK_OPS_PARENT_ENABLE, support for this flag was only added to rate change operations (rate setting and reparent) and disabling unused subtree. It was not added to the clock gate related operations. Any hardware driver that needs it for these operations will either see bogus results, or worse, hang. This has been seen on MT8192 and MT8195, where the imp_ii2_* clk drivers set this, but dumping debugfs clk_summary would cause it to hang. Prepare parent on prepare and enable parent on enable dependencies are already handled automatically by the core as part of its sequencing. Whether the case for "enable parent on prepare" should be supported by this flag or not is not clear, and thus ignored for now. This change solely fixes the handling of clk_core_is_enabled, i.e. enabling the parent clock when reading the hardware state. Unfortunately clk_core_is_enabled is called in a variety of places, sometimes with the enable clock already held. To avoid deadlocking, the core will ignore readouts and just return false if CLK_OPS_PARENT_ENABLE is set but the parent isn't currently enabled. Fixes: fc8726a2c021 ("clk: core: support clocks which requires parents enable (part 2)") Fixes: a4b3518d146f ("clk: core: support clocks which requires parents enable (part 1)") Signed-off-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230103092330.494102-1-wenst@chromium.org Tested-by: AngeloGioacchino Del Regno Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/clk.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index b355d3d40f63..3575afe16a57 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -251,6 +251,17 @@ static bool clk_core_is_enabled(struct clk_core *core) } } + /* + * This could be called with the enable lock held, or from atomic + * context. If the parent isn't enabled already, we can't do + * anything here. We can also assume this clock isn't enabled. + */ + if ((core->flags & CLK_OPS_PARENT_ENABLE) && core->parent) + if (!clk_core_is_enabled(core->parent)) { + ret = false; + goto done; + } + ret = core->ops->is_enabled(core->hw); done: if (core->rpm_enabled) From 9626f83a6ec72caceeaa22ffe400d746cf2ccfff Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Fri, 10 Feb 2023 12:41:50 -0600 Subject: [PATCH 1750/4345] powerpc/perf/hv-24x7: add missing RTAS retry status handling [ Upstream commit cc4b26eab1859fa1a70711872caaf6414809973f ] The ibm,get-system-parameter RTAS function may return -2 or 990x, which indicate that the caller should try again. read_24x7_sys_info() ignores this, allowing transient failures in reporting processor module information. Move the RTAS call into a coventional rtas_busy_delay()-based loop, along with the parsing of results on success. Signed-off-by: Nathan Lynch Fixes: 8ba214267382 ("powerpc/hv-24x7: Add rtas call in hv-24x7 driver to get processor details") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230125-b4-powerpc-rtas-queue-v3-2-26929c8cce78@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/perf/hv-24x7.c | 42 ++++++++++++++++--------------------- 1 file changed, 18 insertions(+), 24 deletions(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 6e7e820508df..1cd2351d241e 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -79,9 +79,8 @@ static u32 phys_coresperchip; /* Physical cores per chip */ */ void read_24x7_sys_info(void) { - int call_status, len, ntypes; - - spin_lock(&rtas_data_buf_lock); + const s32 token = rtas_token("ibm,get-system-parameter"); + int call_status; /* * Making system parameter: chips and sockets and cores per chip @@ -91,32 +90,27 @@ void read_24x7_sys_info(void) phys_chipspersocket = 1; phys_coresperchip = 1; - call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, - NULL, - PROCESSOR_MODULE_INFO, - __pa(rtas_data_buf), - RTAS_DATA_BUF_SIZE); + do { + spin_lock(&rtas_data_buf_lock); + call_status = rtas_call(token, 3, 1, NULL, PROCESSOR_MODULE_INFO, + __pa(rtas_data_buf), RTAS_DATA_BUF_SIZE); + if (call_status == 0) { + int ntypes = be16_to_cpup((__be16 *)&rtas_data_buf[2]); + int len = be16_to_cpup((__be16 *)&rtas_data_buf[0]); + + if (len >= 8 && ntypes != 0) { + phys_sockets = be16_to_cpup((__be16 *)&rtas_data_buf[4]); + phys_chipspersocket = be16_to_cpup((__be16 *)&rtas_data_buf[6]); + phys_coresperchip = be16_to_cpup((__be16 *)&rtas_data_buf[8]); + } + } + spin_unlock(&rtas_data_buf_lock); + } while (rtas_busy_delay(call_status)); if (call_status != 0) { pr_err("Error calling get-system-parameter %d\n", call_status); - } else { - len = be16_to_cpup((__be16 *)&rtas_data_buf[0]); - if (len < 8) - goto out; - - ntypes = be16_to_cpup((__be16 *)&rtas_data_buf[2]); - - if (!ntypes) - goto out; - - phys_sockets = be16_to_cpup((__be16 *)&rtas_data_buf[4]); - phys_chipspersocket = be16_to_cpup((__be16 *)&rtas_data_buf[6]); - phys_coresperchip = be16_to_cpup((__be16 *)&rtas_data_buf[8]); } - -out: - spin_unlock(&rtas_data_buf_lock); } /* Domains for which more than one result element are returned for each event. */ From df995aef6400fc5f854ea892bb57760f85f360ee Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Fri, 10 Feb 2023 12:41:51 -0600 Subject: [PATCH 1751/4345] powerpc/pseries/lpar: add missing RTAS retry status handling [ Upstream commit daa8ab59044610aa8ef2ee45a6c157b5e11635e9 ] The ibm,get-system-parameter RTAS function may return -2 or 990x, which indicate that the caller should try again. pseries_lpar_read_hblkrm_characteristics() ignores this, making it possible to incorrectly detect TLB block invalidation characteristics at boot. Move the RTAS call into a coventional rtas_busy_delay()-based loop. Signed-off-by: Nathan Lynch Fixes: 1211ee61b4a8 ("powerpc/pseries: Read TLB Block Invalidate Characteristics") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230125-b4-powerpc-rtas-queue-v3-3-26929c8cce78@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/lpar.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 1c3ac0f66336..115d196560b8 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1433,22 +1433,22 @@ static inline void __init check_lp_set_hblkrm(unsigned int lp, void __init pseries_lpar_read_hblkrm_characteristics(void) { + const s32 token = rtas_token("ibm,get-system-parameter"); unsigned char local_buffer[SPLPAR_TLB_BIC_MAXLENGTH]; int call_status, len, idx, bpsize; if (!firmware_has_feature(FW_FEATURE_BLOCK_REMOVE)) return; - spin_lock(&rtas_data_buf_lock); - memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE); - call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, - NULL, - SPLPAR_TLB_BIC_TOKEN, - __pa(rtas_data_buf), - RTAS_DATA_BUF_SIZE); - memcpy(local_buffer, rtas_data_buf, SPLPAR_TLB_BIC_MAXLENGTH); - local_buffer[SPLPAR_TLB_BIC_MAXLENGTH - 1] = '\0'; - spin_unlock(&rtas_data_buf_lock); + do { + spin_lock(&rtas_data_buf_lock); + memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE); + call_status = rtas_call(token, 3, 1, NULL, SPLPAR_TLB_BIC_TOKEN, + __pa(rtas_data_buf), RTAS_DATA_BUF_SIZE); + memcpy(local_buffer, rtas_data_buf, SPLPAR_TLB_BIC_MAXLENGTH); + local_buffer[SPLPAR_TLB_BIC_MAXLENGTH - 1] = '\0'; + spin_unlock(&rtas_data_buf_lock); + } while (rtas_busy_delay(call_status)); if (call_status != 0) { pr_warn("%s %s Error calling get-system-parameter (0x%x)\n", From 7afd768784bd7ae499f151ecd3f27c38ddcf5dc7 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Fri, 10 Feb 2023 12:41:52 -0600 Subject: [PATCH 1752/4345] powerpc/pseries/lparcfg: add missing RTAS retry status handling [ Upstream commit 5d08633e5f6564b60f1cbe09af3af40a74d66431 ] The ibm,get-system-parameter RTAS function may return -2 or 990x, which indicate that the caller should try again. lparcfg's parse_system_parameter_string() ignores this, making it possible to intermittently report incorrect SPLPAR characteristics. Move the RTAS call into a coventional rtas_busy_delay()-based loop. Signed-off-by: Nathan Lynch Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230125-b4-powerpc-rtas-queue-v3-4-26929c8cce78@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/pseries/lparcfg.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index e278390ab28d..d3517e498512 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -322,6 +322,7 @@ static void parse_mpp_x_data(struct seq_file *m) */ static void parse_system_parameter_string(struct seq_file *m) { + const s32 token = rtas_token("ibm,get-system-parameter"); int call_status; unsigned char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL); @@ -331,16 +332,15 @@ static void parse_system_parameter_string(struct seq_file *m) return; } - spin_lock(&rtas_data_buf_lock); - memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH); - call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, - NULL, - SPLPAR_CHARACTERISTICS_TOKEN, - __pa(rtas_data_buf), - RTAS_DATA_BUF_SIZE); - memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH); - local_buffer[SPLPAR_MAXLENGTH - 1] = '\0'; - spin_unlock(&rtas_data_buf_lock); + do { + spin_lock(&rtas_data_buf_lock); + memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH); + call_status = rtas_call(token, 3, 1, NULL, SPLPAR_CHARACTERISTICS_TOKEN, + __pa(rtas_data_buf), RTAS_DATA_BUF_SIZE); + memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH); + local_buffer[SPLPAR_MAXLENGTH - 1] = '\0'; + spin_unlock(&rtas_data_buf_lock); + } while (rtas_busy_delay(call_status)); if (call_status != 0) { printk(KERN_INFO From c9a299f2f465697b95a2431c036b43acaed265f9 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Tue, 24 Jan 2023 08:04:46 -0600 Subject: [PATCH 1753/4345] powerpc/rtas: make all exports GPL [ Upstream commit 9bce6243848dfd0ff7c2be6e8d82ab9b1e6c7858 ] The first symbol exports of RTAS functions and data came with the (now removed) scanlog driver in 2003: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/?id=f92e361842d5251e50562b09664082dcbd0548bb At the time this was applied, EXPORT_SYMBOL_GPL() was very new, and the exports of rtas_call() etc have remained non-GPL. As new APIs have been added to the RTAS subsystem, their symbol exports have followed the convention set by existing code. However, the historical evidence is that RTAS function exports have been added over time only to satisfy the needs of in-kernel users, and these clients must have fairly intimate knowledge of how the APIs work to use them safely. No out of tree users are known, and future ones seem unlikely. Arguably the default for RTAS symbols should have become EXPORT_SYMBOL_GPL once it was available. Let's make it so now, and exceptions can be evaluated as needed. Signed-off-by: Nathan Lynch Reviewed-by: Laurent Dufour Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230124140448.45938-3-nathanl@linux.ibm.com Stable-dep-of: 836b5b9fcc8e ("powerpc/rtas: ensure 4KB alignment for rtas_data_buf") Signed-off-by: Sasha Levin --- arch/powerpc/kernel/rtas.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 014229c40435..7d0bcc515a05 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -52,10 +52,10 @@ struct rtas_t rtas = { EXPORT_SYMBOL(rtas); DEFINE_SPINLOCK(rtas_data_buf_lock); -EXPORT_SYMBOL(rtas_data_buf_lock); +EXPORT_SYMBOL_GPL(rtas_data_buf_lock); char rtas_data_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned; -EXPORT_SYMBOL(rtas_data_buf); +EXPORT_SYMBOL_GPL(rtas_data_buf); unsigned long rtas_rmo_buf; @@ -64,7 +64,7 @@ unsigned long rtas_rmo_buf; * This is done like this so rtas_flash can be a module. */ void (*rtas_flash_term_hook)(int); -EXPORT_SYMBOL(rtas_flash_term_hook); +EXPORT_SYMBOL_GPL(rtas_flash_term_hook); /* RTAS use home made raw locking instead of spin_lock_irqsave * because those can be called from within really nasty contexts @@ -312,7 +312,7 @@ void rtas_progress(char *s, unsigned short hex) spin_unlock(&progress_lock); } -EXPORT_SYMBOL(rtas_progress); /* needed by rtas_flash module */ +EXPORT_SYMBOL_GPL(rtas_progress); /* needed by rtas_flash module */ int rtas_token(const char *service) { @@ -322,7 +322,7 @@ int rtas_token(const char *service) tokp = of_get_property(rtas.dev, service, NULL); return tokp ? be32_to_cpu(*tokp) : RTAS_UNKNOWN_SERVICE; } -EXPORT_SYMBOL(rtas_token); +EXPORT_SYMBOL_GPL(rtas_token); int rtas_service_present(const char *service) { @@ -482,7 +482,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) } return ret; } -EXPORT_SYMBOL(rtas_call); +EXPORT_SYMBOL_GPL(rtas_call); /* For RTAS_BUSY (-2), delay for 1 millisecond. For an extended busy status * code of 990n, perform the hinted delay of 10^n (last digit) milliseconds. @@ -517,7 +517,7 @@ unsigned int rtas_busy_delay(int status) return ms; } -EXPORT_SYMBOL(rtas_busy_delay); +EXPORT_SYMBOL_GPL(rtas_busy_delay); static int rtas_error_rc(int rtas_rc) { @@ -563,7 +563,7 @@ int rtas_get_power_level(int powerdomain, int *level) return rtas_error_rc(rc); return rc; } -EXPORT_SYMBOL(rtas_get_power_level); +EXPORT_SYMBOL_GPL(rtas_get_power_level); int rtas_set_power_level(int powerdomain, int level, int *setlevel) { @@ -581,7 +581,7 @@ int rtas_set_power_level(int powerdomain, int level, int *setlevel) return rtas_error_rc(rc); return rc; } -EXPORT_SYMBOL(rtas_set_power_level); +EXPORT_SYMBOL_GPL(rtas_set_power_level); int rtas_get_sensor(int sensor, int index, int *state) { @@ -599,7 +599,7 @@ int rtas_get_sensor(int sensor, int index, int *state) return rtas_error_rc(rc); return rc; } -EXPORT_SYMBOL(rtas_get_sensor); +EXPORT_SYMBOL_GPL(rtas_get_sensor); int rtas_get_sensor_fast(int sensor, int index, int *state) { @@ -660,7 +660,7 @@ int rtas_set_indicator(int indicator, int index, int new_value) return rtas_error_rc(rc); return rc; } -EXPORT_SYMBOL(rtas_set_indicator); +EXPORT_SYMBOL_GPL(rtas_set_indicator); /* * Ignoring RTAS extended delay From 386cc2af90e94f6b55e5ff19ebdb98cac56fe1ff Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Fri, 10 Feb 2023 12:41:54 -0600 Subject: [PATCH 1754/4345] powerpc/rtas: ensure 4KB alignment for rtas_data_buf [ Upstream commit 836b5b9fcc8e09cea7e8a59a070349a00e818308 ] Some RTAS functions that have work area parameters impose alignment requirements on the work area passed to them by the OS. Examples include: - ibm,configure-connector - ibm,update-nodes - ibm,update-properties 4KB is the greatest alignment required by PAPR for such buffers. rtas_data_buf used to have a __page_aligned attribute in the arch/ppc64 days, but that was changed to __cacheline_aligned for unknown reasons by commit 033ef338b6e0 ("powerpc: Merge rtas.c into arch/powerpc/kernel"). That works out to 128-byte alignment on ppc64, which isn't right. This was found by inspection and I'm not aware of any real problems caused by this. Either current RTAS implementations don't enforce the alignment constraints, or rtas_data_buf is always being placed at a 4KB boundary by accident (or both, perhaps). Use __aligned(SZ_4K) to ensure the rtas_data_buf has alignment appropriate for all users. Signed-off-by: Nathan Lynch Fixes: 033ef338b6e0 ("powerpc: Merge rtas.c into arch/powerpc/kernel") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230125-b4-powerpc-rtas-queue-v3-6-26929c8cce78@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/rtas.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 7d0bcc515a05..c2e407a112a2 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -54,7 +54,7 @@ EXPORT_SYMBOL(rtas); DEFINE_SPINLOCK(rtas_data_buf_lock); EXPORT_SYMBOL_GPL(rtas_data_buf_lock); -char rtas_data_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned; +char rtas_data_buf[RTAS_DATA_BUF_SIZE] __aligned(SZ_4K); EXPORT_SYMBOL_GPL(rtas_data_buf); unsigned long rtas_rmo_buf; From dfc41e3859152593f8fe843dfbdab303e9b152cc Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Fri, 15 Oct 2021 18:06:27 +1100 Subject: [PATCH 1755/4345] powerpc/eeh: Small refactor of eeh_handle_normal_event() [ Upstream commit 10b34ece132ee46dc4e6459c765d180c422a09fa ] The control flow of eeh_handle_normal_event() is a bit tricky. Break out one of the error handling paths - rather than be in an else block, we'll make it part of the regular body of the function and put a 'goto out;' in the true limb of the if. Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211015070628.1331635-1-dja@axtens.net Stable-dep-of: 9efcdaac36e1 ("powerpc/eeh: Set channel state after notifying the drivers") Signed-off-by: Sasha Levin --- arch/powerpc/kernel/eeh_driver.c | 69 ++++++++++++++++---------------- 1 file changed, 35 insertions(+), 34 deletions(-) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 3eff6a4888e7..cb3ac555c944 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -1054,45 +1054,46 @@ void eeh_handle_normal_event(struct eeh_pe *pe) } pr_info("EEH: Recovery successful.\n"); - } else { - /* - * About 90% of all real-life EEH failures in the field - * are due to poorly seated PCI cards. Only 10% or so are - * due to actual, failed cards. - */ - pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n" - "Please try reseating or replacing it\n", - pe->phb->global_number, pe->addr); + goto out; + } - eeh_slot_error_detail(pe, EEH_LOG_PERM); + /* + * About 90% of all real-life EEH failures in the field + * are due to poorly seated PCI cards. Only 10% or so are + * due to actual, failed cards. + */ + pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n" + "Please try reseating or replacing it\n", + pe->phb->global_number, pe->addr); - /* Notify all devices that they're about to go down. */ - eeh_set_channel_state(pe, pci_channel_io_perm_failure); - eeh_set_irq_state(pe, false); - eeh_pe_report("error_detected(permanent failure)", pe, - eeh_report_failure, NULL); + eeh_slot_error_detail(pe, EEH_LOG_PERM); - /* Mark the PE to be removed permanently */ - eeh_pe_state_mark(pe, EEH_PE_REMOVED); + /* Notify all devices that they're about to go down. */ + eeh_set_channel_state(pe, pci_channel_io_perm_failure); + eeh_set_irq_state(pe, false); + eeh_pe_report("error_detected(permanent failure)", pe, + eeh_report_failure, NULL); - /* - * Shut down the device drivers for good. We mark - * all removed devices correctly to avoid access - * the their PCI config any more. - */ - if (pe->type & EEH_PE_VF) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + /* Mark the PE to be removed permanently */ + eeh_pe_state_mark(pe, EEH_PE_REMOVED); - pci_lock_rescan_remove(); - pci_hp_remove_devices(bus); - pci_unlock_rescan_remove(); - /* The passed PE should no longer be used */ - return; - } + /* + * Shut down the device drivers for good. We mark + * all removed devices correctly to avoid access + * the their PCI config any more. + */ + if (pe->type & EEH_PE_VF) { + eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + + pci_lock_rescan_remove(); + pci_hp_remove_devices(bus); + pci_unlock_rescan_remove(); + /* The passed PE should no longer be used */ + return; } out: From 6fc6d29be811b677409c22db1eb27e5d7a42a241 Mon Sep 17 00:00:00 2001 From: Ganesh Goudar Date: Thu, 9 Feb 2023 16:26:49 +0530 Subject: [PATCH 1756/4345] powerpc/eeh: Set channel state after notifying the drivers [ Upstream commit 9efcdaac36e1643a1b7f5337e6143ce142d381b1 ] When a PCI error is encountered 6th time in an hour we set the channel state to perm_failure and notify the driver about the permanent failure. However, after upstream commit 38ddc011478e ("powerpc/eeh: Make permanently failed devices non-actionable"), EEH handler stops calling any routine once the device is marked as permanent failure. This issue can lead to fatal consequences like kernel hang with certain PCI devices. Following log is observed with lpfc driver, with and without this change, Without this change kernel hangs, If PCI error is encountered 6 times for a device in an hour. Without the change EEH: Beginning: 'error_detected(permanent failure)' PCI 0132:60:00.0#600000: EEH: not actionable (1,1,1) PCI 0132:60:00.1#600000: EEH: not actionable (1,1,1) EEH: Finished:'error_detected(permanent failure)' With the change EEH: Beginning: 'error_detected(permanent failure)' EEH: Invoking lpfc->error_detected(permanent failure) EEH: lpfc driver reports: 'disconnect' EEH: Invoking lpfc->error_detected(permanent failure) EEH: lpfc driver reports: 'disconnect' EEH: Finished:'error_detected(permanent failure)' To fix the issue, set channel state to permanent failure after notifying the drivers. Fixes: 38ddc011478e ("powerpc/eeh: Make permanently failed devices non-actionable") Suggested-by: Mahesh Salgaonkar Signed-off-by: Ganesh Goudar Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230209105649.127707-1-ganeshgr@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/eeh_driver.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index cb3ac555c944..665d847ef9b5 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -1069,10 +1069,10 @@ void eeh_handle_normal_event(struct eeh_pe *pe) eeh_slot_error_detail(pe, EEH_LOG_PERM); /* Notify all devices that they're about to go down. */ - eeh_set_channel_state(pe, pci_channel_io_perm_failure); eeh_set_irq_state(pe, false); eeh_pe_report("error_detected(permanent failure)", pe, eeh_report_failure, NULL); + eeh_set_channel_state(pe, pci_channel_io_perm_failure); /* Mark the PE to be removed permanently */ eeh_pe_state_mark(pe, EEH_PE_REMOVED); @@ -1189,10 +1189,10 @@ void eeh_handle_special_event(void) /* Notify all devices to be down */ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); - eeh_set_channel_state(pe, pci_channel_io_perm_failure); eeh_pe_report( "error_detected(permanent failure)", pe, eeh_report_failure, NULL); + eeh_set_channel_state(pe, pci_channel_io_perm_failure); pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { From 132203ce40d050dd6f09668cab54b4ea70a2ba4a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Feb 2023 12:07:49 -0800 Subject: [PATCH 1757/4345] MIPS: SMP-CPS: fix build error when HOTPLUG_CPU not set [ Upstream commit 6f02e39fa40f16c24e7a5c599a854c0d1682788d ] When MIPS_CPS=y, MIPS_CPS_PM is not set, HOTPLUG_CPU is not set, and KEXEC=y, cps_shutdown_this_cpu() attempts to call cps_pm_enter_state(), which is not built when MIPS_CPS_PM is not set. Conditionally execute the else branch based on CONFIG_HOTPLUG_CPU to remove the build error. This build failure is from a randconfig file. mips-linux-ld: arch/mips/kernel/smp-cps.o: in function `$L162': smp-cps.c:(.text.cps_kexec_nonboot_cpu+0x31c): undefined reference to `cps_pm_enter_state' Fixes: 1447864bee4c ("MIPS: kexec: CPS systems to halt nonboot CPUs") Signed-off-by: Randy Dunlap Cc: Dengcheng Zhu Cc: Paul Burton Cc: Thomas Bogendoerfer Cc: linux-mips@vger.kernel.org Cc: Sergei Shtylyov Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/kernel/smp-cps.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index dbb3f1fc71ab..f659adb681bc 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -423,9 +423,11 @@ static void cps_shutdown_this_cpu(enum cpu_death death) wmb(); } } else { - pr_debug("Gating power to core %d\n", core); - /* Power down the core */ - cps_pm_enter_state(CPS_PM_POWER_GATED); + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) { + pr_debug("Gating power to core %d\n", core); + /* Power down the core */ + cps_pm_enter_state(CPS_PM_POWER_GATED); + } } } From bccccd43a06dfea5f5a8295a0cb384d74b90a9b3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 19 Feb 2023 15:15:25 -0800 Subject: [PATCH 1758/4345] MIPS: vpe-mt: drop physical_memsize MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 91dc288f4edf0d768e46c2c6d33e0ab703403459 ] When neither LANTIQ nor MIPS_MALTA is set, 'physical_memsize' is not declared. This causes the build to fail with: mips-linux-ld: arch/mips/kernel/vpe-mt.o: in function `vpe_run': arch/mips/kernel/vpe-mt.c:(.text.vpe_run+0x280): undefined reference to `physical_memsize' LANTIQ is not using 'physical_memsize' and MIPS_MALTA's use of it is self-contained in mti-malta/malta-dtshim.c. Use of physical_memsize in vpe-mt.c appears to be unused, so eliminate this loader mode completely and require VPE programs to be compiled with DFLT_STACK_SIZE and DFLT_HEAP_SIZE defined. Fixes: 9050d50e2244 ("MIPS: lantiq: Set physical_memsize") Fixes: 1a2a6d7e8816 ("MIPS: APRP: Split VPE loader into separate files.") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Link: https://lore.kernel.org/all/202302030625.2g3E98sY-lkp@intel.com/ Cc: Dengcheng Zhu Cc: John Crispin Cc: Thomas Bogendoerfer Cc: Philippe Mathieu-Daudé Cc: "Steven J. Hill" Cc: Qais Yousef Cc: Yang Yingliang Cc: Hauke Mehrtens Cc: James Hogan Cc: linux-mips@vger.kernel.org Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/include/asm/vpe.h | 1 - arch/mips/kernel/vpe-mt.c | 7 +++---- arch/mips/lantiq/prom.c | 6 ------ 3 files changed, 3 insertions(+), 11 deletions(-) diff --git a/arch/mips/include/asm/vpe.h b/arch/mips/include/asm/vpe.h index 80e70dbd1f64..012731546cf6 100644 --- a/arch/mips/include/asm/vpe.h +++ b/arch/mips/include/asm/vpe.h @@ -104,7 +104,6 @@ struct vpe_control { struct list_head tc_list; /* Thread contexts */ }; -extern unsigned long physical_memsize; extern struct vpe_control vpecontrol; extern const struct file_operations vpe_fops; diff --git a/arch/mips/kernel/vpe-mt.c b/arch/mips/kernel/vpe-mt.c index 9fd7cd48ea1d..496ed8f362f6 100644 --- a/arch/mips/kernel/vpe-mt.c +++ b/arch/mips/kernel/vpe-mt.c @@ -92,12 +92,11 @@ int vpe_run(struct vpe *v) write_tc_c0_tchalt(read_tc_c0_tchalt() & ~TCHALT_H); /* - * The sde-kit passes 'memsize' to __start in $a3, so set something - * here... Or set $a3 to zero and define DFLT_STACK_SIZE and - * DFLT_HEAP_SIZE when you compile your program + * We don't pass the memsize here, so VPE programs need to be + * compiled with DFLT_STACK_SIZE and DFLT_HEAP_SIZE defined. */ + mttgpr(7, 0); mttgpr(6, v->ntcs); - mttgpr(7, physical_memsize); /* set up VPE1 */ /* diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c index 3f568f5aae2d..2729a4b63e18 100644 --- a/arch/mips/lantiq/prom.c +++ b/arch/mips/lantiq/prom.c @@ -22,12 +22,6 @@ DEFINE_SPINLOCK(ebu_lock); EXPORT_SYMBOL_GPL(ebu_lock); -/* - * This is needed by the VPE loader code, just set it to 0 and assume - * that the firmware hardcodes this value to something useful. - */ -unsigned long physical_memsize = 0L; - /* * this struct is filled by the soc specific detection code and holds * information about the specific soc type, revision and name From 4cab7debf3e05a6a2411c1b0192d849190be79a6 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 6 Feb 2023 14:19:56 +0200 Subject: [PATCH 1759/4345] vdpa/mlx5: Don't clear mr struct on destroy MR [ Upstream commit aef24311bd2d8a6d39a80c34f278b0fd1692aed3 ] Clearing the mr struct erases the lock owner and causes warnings to be emitted. It is not required to clear the mr so remove the memset call. Fixes: 94abbccdf291 ("vdpa/mlx5: Add shared memory registration code") Signed-off-by: Eli Cohen Message-Id: <20230206121956.1149356-1-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- drivers/vdpa/mlx5/core/mr.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index 32c9925de473..1f94ea46c01a 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -448,7 +448,6 @@ void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) unmap_direct_mr(mvdev, dmr); kfree(dmr); } - memset(mr, 0, sizeof(*mr)); mr->initialized = false; out: mutex_unlock(&mr->mkey_mtx); From b0b84fd32cb48dcb7d617f1abe476533447ef67f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 9 Jan 2023 00:14:02 -0500 Subject: [PATCH 1760/4345] alpha/boot/tools/objstrip: fix the check for ELF header [ Upstream commit 1878787797cbb019eeefe6f905514dcd557302b6 ] Just memcmp() with ELFMAG - that's the normal way to do it in userland code, which that thing is. Besides, that has the benefit of actually building - str_has_prefix() is *NOT* present in . Fixes: 5f14596e55de "alpha: Replace strncmp with str_has_prefix" Signed-off-by: Al Viro Signed-off-by: Sasha Levin --- arch/alpha/boot/tools/objstrip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/boot/tools/objstrip.c b/arch/alpha/boot/tools/objstrip.c index 08b430d25a31..7cf92d172dce 100644 --- a/arch/alpha/boot/tools/objstrip.c +++ b/arch/alpha/boot/tools/objstrip.c @@ -148,7 +148,7 @@ main (int argc, char *argv[]) #ifdef __ELF__ elf = (struct elfhdr *) buf; - if (elf->e_ident[0] == 0x7f && str_has_prefix((char *)elf->e_ident + 1, "ELF")) { + if (memcmp(&elf->e_ident[EI_MAG0], ELFMAG, SELFMAG) == 0) { if (elf->e_type != ET_EXEC) { fprintf(stderr, "%s: %s is not an ELF executable\n", prog_name, inname); From 65e39fdce1fc3f2144844051508a11d913e41fdd Mon Sep 17 00:00:00 2001 From: Jeff LaBundy Date: Tue, 3 Jan 2023 11:59:21 -0600 Subject: [PATCH 1761/4345] Input: iqs269a - do not poll during suspend or resume [ Upstream commit 18ab69c8ca5678324efbeed874b707ce7b2feae1 ] Polling the device while it transitions from automatic to manual power mode switching may keep the device from actually finishing the transition. The process appears to time out depending on the polling rate and the device's core clock frequency. This is ultimately unnecessary in the first place; instead it is sufficient to write the desired mode during initialization, then disable automatic switching at suspend. This eliminates the need to ensure the device is prepared for a manual change and removes the 'suspend_mode' variable. Similarly, polling the device while it transitions from one mode to another under manual control may time out as well. This added step does not appear to be necessary either, so drop it. Fixes: 04e49867fad1 ("Input: add support for Azoteq IQS269A") Signed-off-by: Jeff LaBundy Reviewed-by: Mattijs Korpershoek Link: https://lore.kernel.org/r/Y7Rs+eEXlRw4Vq57@nixie71 Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/misc/iqs269a.c | 118 +++++++++-------------------------- 1 file changed, 31 insertions(+), 87 deletions(-) diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c index 1530efd301c2..814d1a898e7f 100644 --- a/drivers/input/misc/iqs269a.c +++ b/drivers/input/misc/iqs269a.c @@ -148,9 +148,6 @@ #define IQS269_ATI_POLL_TIMEOUT_US (iqs269->delay_mult * 500000) #define IQS269_ATI_STABLE_DELAY_MS (iqs269->delay_mult * 150) -#define IQS269_PWR_MODE_POLL_SLEEP_US IQS269_ATI_POLL_SLEEP_US -#define IQS269_PWR_MODE_POLL_TIMEOUT_US IQS269_ATI_POLL_TIMEOUT_US - #define iqs269_irq_wait() usleep_range(200, 250) enum iqs269_local_cap_size { @@ -295,7 +292,6 @@ struct iqs269_private { struct input_dev *keypad; struct input_dev *slider[IQS269_NUM_SL]; unsigned int keycode[ARRAY_SIZE(iqs269_events) * IQS269_NUM_CH]; - unsigned int suspend_mode; unsigned int delay_mult; unsigned int ch_num; bool hall_enable; @@ -767,17 +763,6 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269) iqs269->hall_enable = device_property_present(&client->dev, "azoteq,hall-enable"); - if (!device_property_read_u32(&client->dev, "azoteq,suspend-mode", - &val)) { - if (val > IQS269_SYS_SETTINGS_PWR_MODE_MAX) { - dev_err(&client->dev, "Invalid suspend mode: %u\n", - val); - return -EINVAL; - } - - iqs269->suspend_mode = val; - } - error = regmap_raw_read(iqs269->regmap, IQS269_SYS_SETTINGS, sys_reg, sizeof(*sys_reg)); if (error) @@ -1005,6 +990,17 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269) general &= ~IQS269_SYS_SETTINGS_DIS_AUTO; general &= ~IQS269_SYS_SETTINGS_PWR_MODE_MASK; + if (!device_property_read_u32(&client->dev, "azoteq,suspend-mode", + &val)) { + if (val > IQS269_SYS_SETTINGS_PWR_MODE_MAX) { + dev_err(&client->dev, "Invalid suspend mode: %u\n", + val); + return -EINVAL; + } + + general |= (val << IQS269_SYS_SETTINGS_PWR_MODE_SHIFT); + } + if (!device_property_read_u32(&client->dev, "azoteq,ulp-update", &val)) { if (val > IQS269_SYS_SETTINGS_ULP_UPDATE_MAX) { @@ -1687,59 +1683,30 @@ static int iqs269_probe(struct i2c_client *client) return error; } +static u16 iqs269_general_get(struct iqs269_private *iqs269) +{ + u16 general = be16_to_cpu(iqs269->sys_reg.general); + + general &= ~IQS269_SYS_SETTINGS_REDO_ATI; + general &= ~IQS269_SYS_SETTINGS_ACK_RESET; + + return general | IQS269_SYS_SETTINGS_DIS_AUTO; +} + static int __maybe_unused iqs269_suspend(struct device *dev) { struct iqs269_private *iqs269 = dev_get_drvdata(dev); struct i2c_client *client = iqs269->client; - unsigned int val; int error; + u16 general = iqs269_general_get(iqs269); - if (!iqs269->suspend_mode) + if (!(general & IQS269_SYS_SETTINGS_PWR_MODE_MASK)) return 0; disable_irq(client->irq); - /* - * Automatic power mode switching must be disabled before the device is - * forced into any particular power mode. In this case, the device will - * transition into normal-power mode. - */ - error = regmap_update_bits(iqs269->regmap, IQS269_SYS_SETTINGS, - IQS269_SYS_SETTINGS_DIS_AUTO, ~0); - if (error) - goto err_irq; + error = regmap_write(iqs269->regmap, IQS269_SYS_SETTINGS, general); - /* - * The following check ensures the device has completed its transition - * into normal-power mode before a manual mode switch is performed. - */ - error = regmap_read_poll_timeout(iqs269->regmap, IQS269_SYS_FLAGS, val, - !(val & IQS269_SYS_FLAGS_PWR_MODE_MASK), - IQS269_PWR_MODE_POLL_SLEEP_US, - IQS269_PWR_MODE_POLL_TIMEOUT_US); - if (error) - goto err_irq; - - error = regmap_update_bits(iqs269->regmap, IQS269_SYS_SETTINGS, - IQS269_SYS_SETTINGS_PWR_MODE_MASK, - iqs269->suspend_mode << - IQS269_SYS_SETTINGS_PWR_MODE_SHIFT); - if (error) - goto err_irq; - - /* - * This last check ensures the device has completed its transition into - * the desired power mode to prevent any spurious interrupts from being - * triggered after iqs269_suspend has already returned. - */ - error = regmap_read_poll_timeout(iqs269->regmap, IQS269_SYS_FLAGS, val, - (val & IQS269_SYS_FLAGS_PWR_MODE_MASK) - == (iqs269->suspend_mode << - IQS269_SYS_FLAGS_PWR_MODE_SHIFT), - IQS269_PWR_MODE_POLL_SLEEP_US, - IQS269_PWR_MODE_POLL_TIMEOUT_US); - -err_irq: iqs269_irq_wait(); enable_irq(client->irq); @@ -1750,43 +1717,20 @@ static int __maybe_unused iqs269_resume(struct device *dev) { struct iqs269_private *iqs269 = dev_get_drvdata(dev); struct i2c_client *client = iqs269->client; - unsigned int val; int error; + u16 general = iqs269_general_get(iqs269); - if (!iqs269->suspend_mode) + if (!(general & IQS269_SYS_SETTINGS_PWR_MODE_MASK)) return 0; disable_irq(client->irq); - error = regmap_update_bits(iqs269->regmap, IQS269_SYS_SETTINGS, - IQS269_SYS_SETTINGS_PWR_MODE_MASK, 0); - if (error) - goto err_irq; + error = regmap_write(iqs269->regmap, IQS269_SYS_SETTINGS, + general & ~IQS269_SYS_SETTINGS_PWR_MODE_MASK); + if (!error) + error = regmap_write(iqs269->regmap, IQS269_SYS_SETTINGS, + general & ~IQS269_SYS_SETTINGS_DIS_AUTO); - /* - * This check ensures the device has returned to normal-power mode - * before automatic power mode switching is re-enabled. - */ - error = regmap_read_poll_timeout(iqs269->regmap, IQS269_SYS_FLAGS, val, - !(val & IQS269_SYS_FLAGS_PWR_MODE_MASK), - IQS269_PWR_MODE_POLL_SLEEP_US, - IQS269_PWR_MODE_POLL_TIMEOUT_US); - if (error) - goto err_irq; - - error = regmap_update_bits(iqs269->regmap, IQS269_SYS_SETTINGS, - IQS269_SYS_SETTINGS_DIS_AUTO, 0); - if (error) - goto err_irq; - - /* - * This step reports any events that may have been "swallowed" as a - * result of polling PWR_MODE (which automatically acknowledges any - * pending interrupts). - */ - error = iqs269_report(iqs269); - -err_irq: iqs269_irq_wait(); enable_irq(client->irq); From 7e5bc675eb7b3e1e1442dc721e074e3cc02f44d0 Mon Sep 17 00:00:00 2001 From: Jeff LaBundy Date: Tue, 3 Jan 2023 11:59:35 -0600 Subject: [PATCH 1762/4345] Input: iqs269a - do not poll during ATI [ Upstream commit b08134eb254db56e9ce8170d9b82f0d7a616b6f8 ] After initial start-up, the driver triggers ATI (calibration) with the newly loaded register configuration in place. Next, the driver polls a register field to ensure ATI completed in a timely fashion and that the device is ready to sense. However, communicating with the device over I2C while ATI is under- way may induce noise in the device and cause ATI to fail. As such, the vendor recommends not to poll the device during ATI. To solve this problem, let the device naturally signal to the host that ATI is complete by way of an interrupt. A completion prevents the device from successfully probing until this happens. As an added benefit, initial switch states are now reported in the interrupt handler at the same time ATI status is checked. As such, duplicate code that reports initial switch states has been removed from iqs269_input_init(). The former logic that scaled ATI timeout and filter settling delay is not carried forward with the new implementation, as it produces overly conservative delays at the lower clock rate. Rather, a single timeout that covers both clock rates is used. The filter settling delay does not happen to be necessary and has been removed as well. Fixes: 04e49867fad1 ("Input: add support for Azoteq IQS269A") Signed-off-by: Jeff LaBundy Reviewed-by: Mattijs Korpershoek Link: https://lore.kernel.org/r/Y7RtB2T7AF9rYMjK@nixie71 Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/misc/iqs269a.c | 97 +++++++++++++++++------------------- 1 file changed, 46 insertions(+), 51 deletions(-) diff --git a/drivers/input/misc/iqs269a.c b/drivers/input/misc/iqs269a.c index 814d1a898e7f..8b30c911f789 100644 --- a/drivers/input/misc/iqs269a.c +++ b/drivers/input/misc/iqs269a.c @@ -9,6 +9,7 @@ * axial sliders presented by the device. */ +#include #include #include #include @@ -144,10 +145,6 @@ #define IQS269_NUM_CH 8 #define IQS269_NUM_SL 2 -#define IQS269_ATI_POLL_SLEEP_US (iqs269->delay_mult * 10000) -#define IQS269_ATI_POLL_TIMEOUT_US (iqs269->delay_mult * 500000) -#define IQS269_ATI_STABLE_DELAY_MS (iqs269->delay_mult * 150) - #define iqs269_irq_wait() usleep_range(200, 250) enum iqs269_local_cap_size { @@ -289,10 +286,10 @@ struct iqs269_private { struct mutex lock; struct iqs269_switch_desc switches[ARRAY_SIZE(iqs269_events)]; struct iqs269_sys_reg sys_reg; + struct completion ati_done; struct input_dev *keypad; struct input_dev *slider[IQS269_NUM_SL]; unsigned int keycode[ARRAY_SIZE(iqs269_events) * IQS269_NUM_CH]; - unsigned int delay_mult; unsigned int ch_num; bool hall_enable; bool ati_current; @@ -973,13 +970,8 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269) general = be16_to_cpu(sys_reg->general); - if (device_property_present(&client->dev, "azoteq,clk-div")) { + if (device_property_present(&client->dev, "azoteq,clk-div")) general |= IQS269_SYS_SETTINGS_CLK_DIV; - iqs269->delay_mult = 4; - } else { - general &= ~IQS269_SYS_SETTINGS_CLK_DIV; - iqs269->delay_mult = 1; - } /* * Configure the device to automatically switch between normal and low- @@ -1036,7 +1028,6 @@ static int iqs269_parse_prop(struct iqs269_private *iqs269) static int iqs269_dev_init(struct iqs269_private *iqs269) { - unsigned int val; int error; mutex_lock(&iqs269->lock); @@ -1052,14 +1043,12 @@ static int iqs269_dev_init(struct iqs269_private *iqs269) if (error) goto err_mutex; - error = regmap_read_poll_timeout(iqs269->regmap, IQS269_SYS_FLAGS, val, - !(val & IQS269_SYS_FLAGS_IN_ATI), - IQS269_ATI_POLL_SLEEP_US, - IQS269_ATI_POLL_TIMEOUT_US); - if (error) - goto err_mutex; + /* + * The following delay gives the device time to deassert its RDY output + * so as to prevent an interrupt from being serviced prematurely. + */ + usleep_range(2000, 2100); - msleep(IQS269_ATI_STABLE_DELAY_MS); iqs269->ati_current = true; err_mutex: @@ -1071,10 +1060,8 @@ err_mutex: static int iqs269_input_init(struct iqs269_private *iqs269) { struct i2c_client *client = iqs269->client; - struct iqs269_flags flags; unsigned int sw_code, keycode; int error, i, j; - u8 dir_mask, state; iqs269->keypad = devm_input_allocate_device(&client->dev); if (!iqs269->keypad) @@ -1087,23 +1074,7 @@ static int iqs269_input_init(struct iqs269_private *iqs269) iqs269->keypad->name = "iqs269a_keypad"; iqs269->keypad->id.bustype = BUS_I2C; - if (iqs269->hall_enable) { - error = regmap_raw_read(iqs269->regmap, IQS269_SYS_FLAGS, - &flags, sizeof(flags)); - if (error) { - dev_err(&client->dev, - "Failed to read initial status: %d\n", error); - return error; - } - } - for (i = 0; i < ARRAY_SIZE(iqs269_events); i++) { - dir_mask = flags.states[IQS269_ST_OFFS_DIR]; - if (!iqs269_events[i].dir_up) - dir_mask = ~dir_mask; - - state = flags.states[iqs269_events[i].st_offs] & dir_mask; - sw_code = iqs269->switches[i].code; for (j = 0; j < IQS269_NUM_CH; j++) { @@ -1116,13 +1087,9 @@ static int iqs269_input_init(struct iqs269_private *iqs269) switch (j) { case IQS269_CHx_HALL_ACTIVE: if (iqs269->hall_enable && - iqs269->switches[i].enabled) { + iqs269->switches[i].enabled) input_set_capability(iqs269->keypad, EV_SW, sw_code); - input_report_switch(iqs269->keypad, - sw_code, - state & BIT(j)); - } fallthrough; case IQS269_CHx_HALL_INACTIVE: @@ -1138,14 +1105,6 @@ static int iqs269_input_init(struct iqs269_private *iqs269) } } - input_sync(iqs269->keypad); - - error = input_register_device(iqs269->keypad); - if (error) { - dev_err(&client->dev, "Failed to register keypad: %d\n", error); - return error; - } - for (i = 0; i < IQS269_NUM_SL; i++) { if (!iqs269->sys_reg.slider_select[i]) continue; @@ -1205,6 +1164,9 @@ static int iqs269_report(struct iqs269_private *iqs269) return error; } + if (be16_to_cpu(flags.system) & IQS269_SYS_FLAGS_IN_ATI) + return 0; + error = regmap_raw_read(iqs269->regmap, IQS269_SLIDER_X, slider_x, sizeof(slider_x)); if (error) { @@ -1267,6 +1229,12 @@ static int iqs269_report(struct iqs269_private *iqs269) input_sync(iqs269->keypad); + /* + * The following completion signals that ATI has finished, any initial + * switch states have been reported and the keypad can be registered. + */ + complete_all(&iqs269->ati_done); + return 0; } @@ -1298,6 +1266,9 @@ static ssize_t counts_show(struct device *dev, if (!iqs269->ati_current || iqs269->hall_enable) return -EPERM; + if (!completion_done(&iqs269->ati_done)) + return -EBUSY; + /* * Unsolicited I2C communication prompts the device to assert its RDY * pin, so disable the interrupt line until the operation is finished @@ -1554,7 +1525,9 @@ static ssize_t ati_trigger_show(struct device *dev, { struct iqs269_private *iqs269 = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%u\n", iqs269->ati_current); + return scnprintf(buf, PAGE_SIZE, "%u\n", + iqs269->ati_current && + completion_done(&iqs269->ati_done)); } static ssize_t ati_trigger_store(struct device *dev, @@ -1574,6 +1547,7 @@ static ssize_t ati_trigger_store(struct device *dev, return count; disable_irq(client->irq); + reinit_completion(&iqs269->ati_done); error = iqs269_dev_init(iqs269); @@ -1583,6 +1557,10 @@ static ssize_t ati_trigger_store(struct device *dev, if (error) return error; + if (!wait_for_completion_timeout(&iqs269->ati_done, + msecs_to_jiffies(2000))) + return -ETIMEDOUT; + return count; } @@ -1641,6 +1619,7 @@ static int iqs269_probe(struct i2c_client *client) } mutex_init(&iqs269->lock); + init_completion(&iqs269->ati_done); error = regmap_raw_read(iqs269->regmap, IQS269_VER_INFO, &ver_info, sizeof(ver_info)); @@ -1676,6 +1655,22 @@ static int iqs269_probe(struct i2c_client *client) return error; } + if (!wait_for_completion_timeout(&iqs269->ati_done, + msecs_to_jiffies(2000))) { + dev_err(&client->dev, "Failed to complete ATI\n"); + return -ETIMEDOUT; + } + + /* + * The keypad may include one or more switches and is not registered + * until ATI is complete and the initial switch states are read. + */ + error = input_register_device(iqs269->keypad); + if (error) { + dev_err(&client->dev, "Failed to register keypad: %d\n", error); + return error; + } + error = devm_device_add_group(&client->dev, &iqs269_attr_group); if (error) dev_err(&client->dev, "Failed to add attributes: %d\n", error); From 0a2e2674f720836e294523cf165deac9ba3b1425 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Tue, 17 Jan 2023 14:28:35 +0530 Subject: [PATCH 1763/4345] remoteproc: qcom_q6v5_mss: Use a carveout to authenticate modem headers [ Upstream commit 57f72170a2b2a362c35bb9407fc844eac5afdec1 ] Any access to the dynamically allocated metadata region by the application processor after assigning it to the remote Q6 will result in a XPU violation. Fix this by replacing the dynamically allocated memory region with a no-map carveout and unmap the modem metadata memory region before passing control to the remote Q6. Reported-and-tested-by: Amit Pundir Fixes: 6c5a9dc2481b ("remoteproc: qcom: Make secure world call for mem ownership switch") Signed-off-by: Sibi Sankar Reviewed-by: Manivannan Sadhasivam Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230117085840.32356-7-quic_sibis@quicinc.com Signed-off-by: Sasha Levin --- drivers/remoteproc/qcom_q6v5_mss.c | 59 +++++++++++++++++++++++++++--- 1 file changed, 53 insertions(+), 6 deletions(-) diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index 1b3aa84e36e7..3d975ecd9336 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -190,6 +191,9 @@ struct q6v5 { size_t mba_size; size_t dp_size; + phys_addr_t mdata_phys; + size_t mdata_size; + phys_addr_t mpss_phys; phys_addr_t mpss_reloc; size_t mpss_size; @@ -816,15 +820,35 @@ static int q6v5_mpss_init_image(struct q6v5 *qproc, const struct firmware *fw) if (IS_ERR(metadata)) return PTR_ERR(metadata); - ptr = dma_alloc_attrs(qproc->dev, size, &phys, GFP_KERNEL, dma_attrs); - if (!ptr) { - kfree(metadata); - dev_err(qproc->dev, "failed to allocate mdt buffer\n"); - return -ENOMEM; + if (qproc->mdata_phys) { + if (size > qproc->mdata_size) { + ret = -EINVAL; + dev_err(qproc->dev, "metadata size outside memory range\n"); + goto free_metadata; + } + + phys = qproc->mdata_phys; + ptr = memremap(qproc->mdata_phys, size, MEMREMAP_WC); + if (!ptr) { + ret = -EBUSY; + dev_err(qproc->dev, "unable to map memory region: %pa+%zx\n", + &qproc->mdata_phys, size); + goto free_metadata; + } + } else { + ptr = dma_alloc_attrs(qproc->dev, size, &phys, GFP_KERNEL, dma_attrs); + if (!ptr) { + ret = -ENOMEM; + dev_err(qproc->dev, "failed to allocate mdt buffer\n"); + goto free_metadata; + } } memcpy(ptr, metadata, size); + if (qproc->mdata_phys) + memunmap(ptr); + /* Hypervisor mapping to access metadata by modem */ mdata_perm = BIT(QCOM_SCM_VMID_HLOS); ret = q6v5_xfer_mem_ownership(qproc, &mdata_perm, false, true, @@ -853,7 +877,9 @@ static int q6v5_mpss_init_image(struct q6v5 *qproc, const struct firmware *fw) "mdt buffer not reclaimed system may become unstable\n"); free_dma_attrs: - dma_free_attrs(qproc->dev, size, ptr, phys, dma_attrs); + if (!qproc->mdata_phys) + dma_free_attrs(qproc->dev, size, ptr, phys, dma_attrs); +free_metadata: kfree(metadata); return ret < 0 ? ret : 0; @@ -1585,6 +1611,7 @@ static int q6v5_init_reset(struct q6v5 *qproc) static int q6v5_alloc_memory_region(struct q6v5 *qproc) { struct device_node *child; + struct reserved_mem *rmem; struct device_node *node; struct resource r; int ret; @@ -1637,6 +1664,26 @@ static int q6v5_alloc_memory_region(struct q6v5 *qproc) qproc->mpss_phys = qproc->mpss_reloc = r.start; qproc->mpss_size = resource_size(&r); + if (!child) { + node = of_parse_phandle(qproc->dev->of_node, "memory-region", 2); + } else { + child = of_get_child_by_name(qproc->dev->of_node, "metadata"); + node = of_parse_phandle(child, "memory-region", 0); + of_node_put(child); + } + + if (!node) + return 0; + + rmem = of_reserved_mem_lookup(node); + if (!rmem) { + dev_err(qproc->dev, "unable to resolve metadata region\n"); + return -EINVAL; + } + + qproc->mdata_phys = rmem->base; + qproc->mdata_size = rmem->size; + return 0; } From c7a218cbf67fffcd99b76ae3b5e9c2e8bef17c8c Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 29 Nov 2022 12:01:59 +0100 Subject: [PATCH 1764/4345] media: ti: cal: fix possible memory leak in cal_ctx_create() [ Upstream commit 7acd650a0484d92985a0d6d867d980c6dd019885 ] The memory of ctx is allocated in cal_ctx_create(), but it will not be freed when cal_ctx_v4l2_init() fails, so add kfree() when cal_ctx_v4l2_init() fails to fix it. Fixes: d68a94e98a89 ("media: ti-vpe: cal: Split video device initialization and registration") Signed-off-by: Gaosheng Cui Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/platform/ti-vpe/cal.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c index 2eef245c31a1..93121c90d76a 100644 --- a/drivers/media/platform/ti-vpe/cal.c +++ b/drivers/media/platform/ti-vpe/cal.c @@ -624,8 +624,10 @@ static struct cal_ctx *cal_ctx_create(struct cal_dev *cal, int inst) ctx->cport = inst; ret = cal_ctx_v4l2_init(ctx); - if (ret) + if (ret) { + kfree(ctx); return NULL; + } return ctx; } From b74aaa314f6a9e6b4e0deac993abcaf9a0029e8c Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 4 Jan 2023 09:55:37 +0100 Subject: [PATCH 1765/4345] media: platform: ti: Add missing check for devm_regulator_get [ Upstream commit da8e05f84a11c3cc3b0ba0a3c62d20e358002d99 ] Add check for the return value of devm_regulator_get since it may return error pointer. Fixes: 448de7e7850b ("[media] omap3isp: OMAP3 ISP core") Signed-off-by: Jiasheng Jiang Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/platform/omap3isp/isp.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c index 1311b4996ece..21c16698cc2d 100644 --- a/drivers/media/platform/omap3isp/isp.c +++ b/drivers/media/platform/omap3isp/isp.c @@ -2297,7 +2297,16 @@ static int isp_probe(struct platform_device *pdev) /* Regulators */ isp->isp_csiphy1.vdd = devm_regulator_get(&pdev->dev, "vdd-csiphy1"); + if (IS_ERR(isp->isp_csiphy1.vdd)) { + ret = PTR_ERR(isp->isp_csiphy1.vdd); + goto error; + } + isp->isp_csiphy2.vdd = devm_regulator_get(&pdev->dev, "vdd-csiphy2"); + if (IS_ERR(isp->isp_csiphy2.vdd)) { + ret = PTR_ERR(isp->isp_csiphy2.vdd); + goto error; + } /* Clocks * From 55f3bca25d3fd555935f84734d5203e25c41793b Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 11 Jan 2023 20:05:02 -0700 Subject: [PATCH 1766/4345] powerpc: Remove linker flag from KBUILD_AFLAGS [ Upstream commit 31f48f16264bc70962fb3e7ec62da64d0a2ba04a ] When clang's -Qunused-arguments is dropped from KBUILD_CPPFLAGS, it points out that KBUILD_AFLAGS contains a linker flag, which will be unused: clang: error: -Wl,-a32: 'linker' input unused [-Werror,-Wunused-command-line-argument] This was likely supposed to be '-Wa,-a$(BITS)'. However, this change is unnecessary, as all supported versions of clang and gcc will pass '-a64' or '-a32' to GNU as based on the value of '-m'; the behavior of the latest stable release of the oldest supported major version of each compiler is shown below and each compiler's latest release exhibits the same behavior (GCC 12.2.0 and Clang 15.0.6). $ powerpc64-linux-gcc --version | head -1 powerpc64-linux-gcc (GCC) 5.5.0 $ powerpc64-linux-gcc -m64 -### -x assembler-with-cpp -c -o /dev/null /dev/null &| grep 'as ' .../as -a64 -mppc64 -many -mbig -o /dev/null /tmp/cctwuBzZ.s $ powerpc64-linux-gcc -m32 -### -x assembler-with-cpp -c -o /dev/null /dev/null &| grep 'as ' .../as -a32 -mppc -many -mbig -o /dev/null /tmp/ccaZP4mF.sg $ clang --version | head -1 Ubuntu clang version 11.1.0-++20211011094159+1fdec59bffc1-1~exp1~20211011214622.5 $ clang --target=powerpc64-linux-gnu -fno-integrated-as -m64 -### \ -x assembler-with-cpp -c -o /dev/null /dev/null &| grep gnu-as "/usr/bin/powerpc64-linux-gnu-as" "-a64" "-mppc64" "-many" "-o" "/dev/null" "/tmp/null-80267c.s" $ clang --target=powerpc64-linux-gnu -fno-integrated-as -m64 -### \ -x assembler-with-cpp -c -o /dev/null /dev/null &| grep gnu-as "/usr/bin/powerpc64-linux-gnu-as" "-a32" "-mppc" "-many" "-o" "/dev/null" "/tmp/null-ab8f8d.s" Remove this flag altogether to avoid future issues. Fixes: 1421dc6d4829 ("powerpc/kbuild: Use flags variables rather than overriding LD/CC/AS") Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Tested-by: Linux Kernel Functional Testing Tested-by: Anders Roxell Acked-by: Michael Ellerman Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- arch/powerpc/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 612254141296..a3f66ade09b3 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -92,7 +92,7 @@ aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian ifeq ($(HAS_BIARCH),y) KBUILD_CFLAGS += -m$(BITS) -KBUILD_AFLAGS += -m$(BITS) -Wl,-a$(BITS) +KBUILD_AFLAGS += -m$(BITS) KBUILD_LDFLAGS += -m elf$(BITS)$(LDEMULATION) endif From f3e10a3437dcbee7900b437c5bceaa4f105d75e6 Mon Sep 17 00:00:00 2001 From: Bastian Germann Date: Wed, 26 May 2021 01:01:37 +0200 Subject: [PATCH 1767/4345] builddeb: clean generated package content [ Upstream commit c9f9cf2560e40b62015c6c4a04be60f55ce5240e ] For each binary Debian package, a directory with the package name is created in the debian directory. Correct the generated file matches in the package's clean target, which were renamed without adjusting the target. Fixes: 1694e94e4f46 ("builddeb: match temporary directory name to the package name") Signed-off-by: Bastian Germann Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- scripts/package/mkdebian | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 60a2a63a5e90..32d528a36786 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -236,7 +236,7 @@ binary-arch: build-arch KBUILD_BUILD_VERSION=${revision} -f \$(srctree)/Makefile intdeb-pkg clean: - rm -rf debian/*tmp debian/files + rm -rf debian/files debian/linux-* \$(MAKE) clean binary: binary-arch From 505ff3a0c5951684c3a43094ca4c1a74683d5681 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Tue, 6 Dec 2022 14:05:55 +0100 Subject: [PATCH 1768/4345] media: max9286: Fix memleak in max9286_v4l2_register() [ Upstream commit 8636c5fc7658c7c6299fb8b352d24ea4b9ba99e2 ] There is a kmemleak when testing the media/i2c/max9286.c with bpf mock device: kmemleak: 5 new suspected memory leaks (see /sys/kernel/debug/kmemleak) unreferenced object 0xffff88810defc400 (size 256): comm "python3", pid 278, jiffies 4294737563 (age 31.978s) hex dump (first 32 bytes): 28 06 a7 0a 81 88 ff ff 00 fe 22 12 81 88 ff ff (........."..... 10 c4 ef 0d 81 88 ff ff 10 c4 ef 0d 81 88 ff ff ................ backtrace: [<00000000191de6a7>] __kmalloc_node+0x44/0x1b0 [<000000002f4912b7>] kvmalloc_node+0x34/0x180 [<0000000057dc4cae>] v4l2_ctrl_new+0x325/0x10f0 [videodev] [<0000000026030272>] v4l2_ctrl_new_std+0x16f/0x210 [videodev] [<00000000f0d9ea2f>] max9286_probe+0x76e/0xbff [max9286] [<00000000ea8f6455>] i2c_device_probe+0x28d/0x680 [<0000000087529af3>] really_probe+0x17c/0x3f0 [<00000000b08be526>] __driver_probe_device+0xe3/0x170 [<000000004382edea>] driver_probe_device+0x49/0x120 [<000000007bde528a>] __device_attach_driver+0xf7/0x150 [<000000009f9c6ab4>] bus_for_each_drv+0x114/0x180 [<00000000c8aaf588>] __device_attach+0x1e5/0x2d0 [<0000000041cc06b9>] bus_probe_device+0x126/0x140 [<000000002309860d>] device_add+0x810/0x1130 [<000000002827bf98>] i2c_new_client_device+0x359/0x4f0 [<00000000593bdc85>] of_i2c_register_device+0xf1/0x110 max9286_v4l2_register() calls v4l2_ctrl_new_std(), but won't free the created v412_ctrl when fwnode_graph_get_endpoint_by_id() failed, which causes the memleak. Call v4l2_ctrl_handler_free() to free the v412_ctrl. Fixes: 66d8c9d2422d ("media: i2c: Add MAX9286 driver") Signed-off-by: Shang XiaoJing Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/max9286.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/i2c/max9286.c b/drivers/media/i2c/max9286.c index b1e2476d3c9e..79a11c0184c6 100644 --- a/drivers/media/i2c/max9286.c +++ b/drivers/media/i2c/max9286.c @@ -890,6 +890,7 @@ static int max9286_v4l2_register(struct max9286_priv *priv) err_put_node: fwnode_handle_put(ep); err_async: + v4l2_ctrl_handler_free(&priv->ctrls); max9286_v4l2_notifier_unregister(priv); return ret; From a163ee11345d8322321c28bd61631de32455b987 Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Thu, 8 Dec 2022 08:59:37 +0100 Subject: [PATCH 1769/4345] media: ov2740: Fix memleak in ov2740_init_controls() [ Upstream commit 2d899592ed7829d0d5140853bac4d58742a6b8af ] There is a kmemleak when testing the media/i2c/ov2740.c with bpf mock device: unreferenced object 0xffff8881090e19e0 (size 16): comm "51-i2c-ov2740", pid 278, jiffies 4294781584 (age 23.613s) hex dump (first 16 bytes): 00 f3 7c 0b 81 88 ff ff 80 75 6a 09 81 88 ff ff ..|......uj..... backtrace: [<000000004e9fad8f>] __kmalloc_node+0x44/0x1b0 [<0000000039c802f4>] kvmalloc_node+0x34/0x180 [<000000009b8b5c63>] v4l2_ctrl_handler_init_class+0x11d/0x180 [videodev] [<0000000038644056>] ov2740_probe+0x37d/0x84f [ov2740] [<0000000092489f59>] i2c_device_probe+0x28d/0x680 [<000000001038babe>] really_probe+0x17c/0x3f0 [<0000000098c7af1c>] __driver_probe_device+0xe3/0x170 [<00000000e1b3dc24>] device_driver_attach+0x34/0x80 [<000000005a04a34d>] bind_store+0x10b/0x1a0 [<00000000ce25d4f2>] drv_attr_store+0x49/0x70 [<000000007d9f4e9a>] sysfs_kf_write+0x8c/0xb0 [<00000000be6cff0f>] kernfs_fop_write_iter+0x216/0x2e0 [<0000000031ddb40a>] vfs_write+0x658/0x810 [<0000000041beecdd>] ksys_write+0xd6/0x1b0 [<0000000023755840>] do_syscall_64+0x38/0x90 [<00000000b2cc2da2>] entry_SYSCALL_64_after_hwframe+0x63/0xcd ov2740_init_controls() won't clean all the allocated resources in fail path, which may causes the memleaks. Add v4l2_ctrl_handler_free() to prevent memleak. Fixes: 866edc895171 ("media: i2c: Add ov2740 image sensor driver") Signed-off-by: Shang XiaoJing Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov2740.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/i2c/ov2740.c b/drivers/media/i2c/ov2740.c index bd0d45b0d43f..34d74e575a43 100644 --- a/drivers/media/i2c/ov2740.c +++ b/drivers/media/i2c/ov2740.c @@ -577,8 +577,10 @@ static int ov2740_init_controls(struct ov2740 *ov2740) V4L2_CID_TEST_PATTERN, ARRAY_SIZE(ov2740_test_pattern_menu) - 1, 0, 0, ov2740_test_pattern_menu); - if (ctrl_hdlr->error) + if (ctrl_hdlr->error) { + v4l2_ctrl_handler_free(ctrl_hdlr); return ctrl_hdlr->error; + } ov2740->sd.ctrl_handler = ctrl_hdlr; From bcae9115a163198dce9126aa8bedc1c007ec30ed Mon Sep 17 00:00:00 2001 From: Shang XiaoJing Date: Thu, 8 Dec 2022 08:59:38 +0100 Subject: [PATCH 1770/4345] media: ov5675: Fix memleak in ov5675_init_controls() [ Upstream commit dd74ed6c213003533e3abf4c204374ef01d86978 ] There is a kmemleak when testing the media/i2c/ov5675.c with bpf mock device: AssertionError: unreferenced object 0xffff888107362160 (size 16): comm "python3", pid 277, jiffies 4294832798 (age 20.722s) hex dump (first 16 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000abe7d67c>] __kmalloc_node+0x44/0x1b0 [<000000008a725aac>] kvmalloc_node+0x34/0x180 [<000000009a53cd11>] v4l2_ctrl_handler_init_class+0x11d/0x180 [videodev] [<0000000055b46db0>] ov5675_probe+0x38b/0x897 [ov5675] [<00000000153d886c>] i2c_device_probe+0x28d/0x680 [<000000004afb7e8f>] really_probe+0x17c/0x3f0 [<00000000ff2f18e4>] __driver_probe_device+0xe3/0x170 [<000000000a001029>] driver_probe_device+0x49/0x120 [<00000000e39743c7>] __device_attach_driver+0xf7/0x150 [<00000000d32fd070>] bus_for_each_drv+0x114/0x180 [<000000009083ac41>] __device_attach+0x1e5/0x2d0 [<0000000015b4a830>] bus_probe_device+0x126/0x140 [<000000007813deaf>] device_add+0x810/0x1130 [<000000007becb867>] i2c_new_client_device+0x386/0x540 [<000000007f9cf4b4>] of_i2c_register_device+0xf1/0x110 [<00000000ebfdd032>] of_i2c_notify+0xfc/0x1f0 ov5675_init_controls() won't clean all the allocated resources in fail path, which may causes the memleaks. Add v4l2_ctrl_handler_free() to prevent memleak. Fixes: bf27502b1f3b ("media: ov5675: Add support for OV5675 sensor") Signed-off-by: Shang XiaoJing Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov5675.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/i2c/ov5675.c b/drivers/media/i2c/ov5675.c index 9540ce8918f0..aa35a9546177 100644 --- a/drivers/media/i2c/ov5675.c +++ b/drivers/media/i2c/ov5675.c @@ -791,8 +791,10 @@ static int ov5675_init_controls(struct ov5675 *ov5675) v4l2_ctrl_new_std(ctrl_hdlr, &ov5675_ctrl_ops, V4L2_CID_VFLIP, 0, 1, 1, 0); - if (ctrl_hdlr->error) + if (ctrl_hdlr->error) { + v4l2_ctrl_handler_free(ctrl_hdlr); return ctrl_hdlr->error; + } ov5675->sd.ctrl_handler = ctrl_hdlr; From dfaafeb8e9537969e8dba75491f732478c7fa9d6 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Thu, 8 Dec 2022 09:06:25 +0100 Subject: [PATCH 1771/4345] media: i2c: ov772x: Fix memleak in ov772x_probe() [ Upstream commit 7485edb2b6ca5960205c0a49bedfd09bba30e521 ] A memory leak was reported when testing ov772x with bpf mock device: AssertionError: unreferenced object 0xffff888109afa7a8 (size 8): comm "python3", pid 279, jiffies 4294805921 (age 20.681s) hex dump (first 8 bytes): 80 22 88 15 81 88 ff ff ."...... backtrace: [<000000009990b438>] __kmalloc_node+0x44/0x1b0 [<000000009e32f7d7>] kvmalloc_node+0x34/0x180 [<00000000faf48134>] v4l2_ctrl_handler_init_class+0x11d/0x180 [videodev] [<00000000da376937>] ov772x_probe+0x1c3/0x68c [ov772x] [<000000003f0d225e>] i2c_device_probe+0x28d/0x680 [<00000000e0b6db89>] really_probe+0x17c/0x3f0 [<000000001b19fcee>] __driver_probe_device+0xe3/0x170 [<0000000048370519>] driver_probe_device+0x49/0x120 [<000000005ead07a0>] __device_attach_driver+0xf7/0x150 [<0000000043f452b8>] bus_for_each_drv+0x114/0x180 [<00000000358e5596>] __device_attach+0x1e5/0x2d0 [<0000000043f83c5d>] bus_probe_device+0x126/0x140 [<00000000ee0f3046>] device_add+0x810/0x1130 [<00000000e0278184>] i2c_new_client_device+0x359/0x4f0 [<0000000070baf34f>] of_i2c_register_device+0xf1/0x110 [<00000000a9f2159d>] of_i2c_notify+0x100/0x160 unreferenced object 0xffff888119825c00 (size 256): comm "python3", pid 279, jiffies 4294805921 (age 20.681s) hex dump (first 32 bytes): 00 b4 a5 17 81 88 ff ff 00 5e 82 19 81 88 ff ff .........^...... 10 5c 82 19 81 88 ff ff 10 5c 82 19 81 88 ff ff .\.......\...... backtrace: [<000000009990b438>] __kmalloc_node+0x44/0x1b0 [<000000009e32f7d7>] kvmalloc_node+0x34/0x180 [<0000000073d88e0b>] v4l2_ctrl_new.cold+0x19b/0x86f [videodev] [<00000000b1f576fb>] v4l2_ctrl_new_std+0x16f/0x210 [videodev] [<00000000caf7ac99>] ov772x_probe+0x1fa/0x68c [ov772x] [<000000003f0d225e>] i2c_device_probe+0x28d/0x680 [<00000000e0b6db89>] really_probe+0x17c/0x3f0 [<000000001b19fcee>] __driver_probe_device+0xe3/0x170 [<0000000048370519>] driver_probe_device+0x49/0x120 [<000000005ead07a0>] __device_attach_driver+0xf7/0x150 [<0000000043f452b8>] bus_for_each_drv+0x114/0x180 [<00000000358e5596>] __device_attach+0x1e5/0x2d0 [<0000000043f83c5d>] bus_probe_device+0x126/0x140 [<00000000ee0f3046>] device_add+0x810/0x1130 [<00000000e0278184>] i2c_new_client_device+0x359/0x4f0 [<0000000070baf34f>] of_i2c_register_device+0xf1/0x110 The reason is that if priv->hdl.error is set, ov772x_probe() jumps to the error_mutex_destroy without doing v4l2_ctrl_handler_free(), and all resources allocated in v4l2_ctrl_handler_init() and v4l2_ctrl_new_std() are leaked. Fixes: 1112babde214 ("media: i2c: Copy ov772x soc_camera sensor driver") Signed-off-by: Yuan Can Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov772x.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c index 2cc6a678069a..5033950a48ab 100644 --- a/drivers/media/i2c/ov772x.c +++ b/drivers/media/i2c/ov772x.c @@ -1397,7 +1397,7 @@ static int ov772x_probe(struct i2c_client *client) priv->subdev.ctrl_handler = &priv->hdl; if (priv->hdl.error) { ret = priv->hdl.error; - goto error_mutex_destroy; + goto error_ctrl_free; } priv->clk = clk_get(&client->dev, NULL); @@ -1446,7 +1446,6 @@ error_clk_put: clk_put(priv->clk); error_ctrl_free: v4l2_ctrl_handler_free(&priv->hdl); -error_mutex_destroy: mutex_destroy(&priv->lock); return ret; From 09a0410886aa80269d5fee39a5d61dde98694f90 Mon Sep 17 00:00:00 2001 From: Sameer Puri Date: Mon, 13 Apr 2020 17:51:47 +0200 Subject: [PATCH 1772/4345] media: i2c: imx219: remove redundant writes [ Upstream commit fbef89886da6d7735d20fdde16a1ee6ed6c6ab56 ] These writes to 0x162, 0x163 already appear earlier in the struct for the 1920x1080 mode and do not need to be repeated. Signed-off-by: Sameer Puri Reviewed-by: Dave Stevenson Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: ef86447e775f ("media: i2c: imx219: Fix binning for RAW8 capture") Signed-off-by: Sasha Levin --- drivers/media/i2c/imx219.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c index 4771d0ef2c46..cad0a8df203e 100644 --- a/drivers/media/i2c/imx219.c +++ b/drivers/media/i2c/imx219.c @@ -262,8 +262,6 @@ static const struct imx219_reg mode_1920_1080_regs[] = { {0x4793, 0x10}, {0x4797, 0x0e}, {0x479b, 0x0e}, - {0x0162, 0x0d}, - {0x0163, 0x78}, }; static const struct imx219_reg mode_1640_1232_regs[] = { From a34288e3a1169abc6509c943fc76ddc43843ec9c Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Tue, 20 Dec 2022 13:07:53 +0100 Subject: [PATCH 1773/4345] media: i2c: imx219: Split common registers from mode tables [ Upstream commit 8508455961d5a9e8907bcfd8dcd58f19d9b6ce47 ] There are four modes, and each mode has a table of registers. Some of the registers are common to all modes, so create new tables for these common registers to reduce duplicate code. Signed-off-by: Adam Ford Reviewed-by: Dave Stevenson Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: ef86447e775f ("media: i2c: imx219: Fix binning for RAW8 capture") Signed-off-by: Sasha Levin --- drivers/media/i2c/imx219.c | 206 +++++++++++-------------------------- 1 file changed, 59 insertions(+), 147 deletions(-) diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c index cad0a8df203e..a28926069b82 100644 --- a/drivers/media/i2c/imx219.c +++ b/drivers/media/i2c/imx219.c @@ -145,23 +145,61 @@ struct imx219_mode { struct imx219_reg_list reg_list; }; -/* - * Register sets lifted off the i2C interface from the Raspberry Pi firmware - * driver. - * 3280x2464 = mode 2, 1920x1080 = mode 1, 1640x1232 = mode 4, 640x480 = mode 7. - */ -static const struct imx219_reg mode_3280x2464_regs[] = { - {0x0100, 0x00}, +static const struct imx219_reg imx219_common_regs[] = { + {0x0100, 0x00}, /* Mode Select */ + + /* To Access Addresses 3000-5fff, send the following commands */ {0x30eb, 0x0c}, {0x30eb, 0x05}, {0x300a, 0xff}, {0x300b, 0xff}, {0x30eb, 0x05}, {0x30eb, 0x09}, - {0x0114, 0x01}, - {0x0128, 0x00}, - {0x012a, 0x18}, + + /* PLL Clock Table */ + {0x0301, 0x05}, /* VTPXCK_DIV */ + {0x0303, 0x01}, /* VTSYSCK_DIV */ + {0x0304, 0x03}, /* PREPLLCK_VT_DIV 0x03 = AUTO set */ + {0x0305, 0x03}, /* PREPLLCK_OP_DIV 0x03 = AUTO set */ + {0x0306, 0x00}, /* PLL_VT_MPY */ + {0x0307, 0x39}, + {0x030b, 0x01}, /* OP_SYS_CLK_DIV */ + {0x030c, 0x00}, /* PLL_OP_MPY */ + {0x030d, 0x72}, + + /* Undocumented registers */ + {0x455e, 0x00}, + {0x471e, 0x4b}, + {0x4767, 0x0f}, + {0x4750, 0x14}, + {0x4540, 0x00}, + {0x47b4, 0x14}, + {0x4713, 0x30}, + {0x478b, 0x10}, + {0x478f, 0x10}, + {0x4793, 0x10}, + {0x4797, 0x0e}, + {0x479b, 0x0e}, + + /* Frame Bank Register Group "A" */ + {0x0162, 0x0d}, /* Line_Length_A */ + {0x0163, 0x78}, + {0x0170, 0x01}, /* X_ODD_INC_A */ + {0x0171, 0x01}, /* Y_ODD_INC_A */ + + /* Output setup registers */ + {0x0114, 0x01}, /* CSI 2-Lane Mode */ + {0x0128, 0x00}, /* DPHY Auto Mode */ + {0x012a, 0x18}, /* EXCK_Freq */ {0x012b, 0x00}, +}; + +/* + * Register sets lifted off the i2C interface from the Raspberry Pi firmware + * driver. + * 3280x2464 = mode 2, 1920x1080 = mode 1, 1640x1232 = mode 4, 640x480 = mode 7. + */ +static const struct imx219_reg mode_3280x2464_regs[] = { {0x0164, 0x00}, {0x0165, 0x00}, {0x0166, 0x0c}, @@ -174,53 +212,15 @@ static const struct imx219_reg mode_3280x2464_regs[] = { {0x016d, 0xd0}, {0x016e, 0x09}, {0x016f, 0xa0}, - {0x0170, 0x01}, - {0x0171, 0x01}, - {0x0174, 0x00}, + {0x0174, 0x00}, /* No-Binning */ {0x0175, 0x00}, - {0x0301, 0x05}, - {0x0303, 0x01}, - {0x0304, 0x03}, - {0x0305, 0x03}, - {0x0306, 0x00}, - {0x0307, 0x39}, - {0x030b, 0x01}, - {0x030c, 0x00}, - {0x030d, 0x72}, {0x0624, 0x0c}, {0x0625, 0xd0}, {0x0626, 0x09}, {0x0627, 0xa0}, - {0x455e, 0x00}, - {0x471e, 0x4b}, - {0x4767, 0x0f}, - {0x4750, 0x14}, - {0x4540, 0x00}, - {0x47b4, 0x14}, - {0x4713, 0x30}, - {0x478b, 0x10}, - {0x478f, 0x10}, - {0x4793, 0x10}, - {0x4797, 0x0e}, - {0x479b, 0x0e}, - {0x0162, 0x0d}, - {0x0163, 0x78}, }; static const struct imx219_reg mode_1920_1080_regs[] = { - {0x0100, 0x00}, - {0x30eb, 0x05}, - {0x30eb, 0x0c}, - {0x300a, 0xff}, - {0x300b, 0xff}, - {0x30eb, 0x05}, - {0x30eb, 0x09}, - {0x0114, 0x01}, - {0x0128, 0x00}, - {0x012a, 0x18}, - {0x012b, 0x00}, - {0x0162, 0x0d}, - {0x0163, 0x78}, {0x0164, 0x02}, {0x0165, 0xa8}, {0x0166, 0x0a}, @@ -233,49 +233,15 @@ static const struct imx219_reg mode_1920_1080_regs[] = { {0x016d, 0x80}, {0x016e, 0x04}, {0x016f, 0x38}, - {0x0170, 0x01}, - {0x0171, 0x01}, - {0x0174, 0x00}, + {0x0174, 0x00}, /* No-Binning */ {0x0175, 0x00}, - {0x0301, 0x05}, - {0x0303, 0x01}, - {0x0304, 0x03}, - {0x0305, 0x03}, - {0x0306, 0x00}, - {0x0307, 0x39}, - {0x030b, 0x01}, - {0x030c, 0x00}, - {0x030d, 0x72}, {0x0624, 0x07}, {0x0625, 0x80}, {0x0626, 0x04}, {0x0627, 0x38}, - {0x455e, 0x00}, - {0x471e, 0x4b}, - {0x4767, 0x0f}, - {0x4750, 0x14}, - {0x4540, 0x00}, - {0x47b4, 0x14}, - {0x4713, 0x30}, - {0x478b, 0x10}, - {0x478f, 0x10}, - {0x4793, 0x10}, - {0x4797, 0x0e}, - {0x479b, 0x0e}, }; static const struct imx219_reg mode_1640_1232_regs[] = { - {0x0100, 0x00}, - {0x30eb, 0x0c}, - {0x30eb, 0x05}, - {0x300a, 0xff}, - {0x300b, 0xff}, - {0x30eb, 0x05}, - {0x30eb, 0x09}, - {0x0114, 0x01}, - {0x0128, 0x00}, - {0x012a, 0x18}, - {0x012b, 0x00}, {0x0164, 0x00}, {0x0165, 0x00}, {0x0166, 0x0c}, @@ -288,53 +254,15 @@ static const struct imx219_reg mode_1640_1232_regs[] = { {0x016d, 0x68}, {0x016e, 0x04}, {0x016f, 0xd0}, - {0x0170, 0x01}, - {0x0171, 0x01}, - {0x0174, 0x01}, + {0x0174, 0x01}, /* x2-Binning */ {0x0175, 0x01}, - {0x0301, 0x05}, - {0x0303, 0x01}, - {0x0304, 0x03}, - {0x0305, 0x03}, - {0x0306, 0x00}, - {0x0307, 0x39}, - {0x030b, 0x01}, - {0x030c, 0x00}, - {0x030d, 0x72}, {0x0624, 0x06}, {0x0625, 0x68}, {0x0626, 0x04}, {0x0627, 0xd0}, - {0x455e, 0x00}, - {0x471e, 0x4b}, - {0x4767, 0x0f}, - {0x4750, 0x14}, - {0x4540, 0x00}, - {0x47b4, 0x14}, - {0x4713, 0x30}, - {0x478b, 0x10}, - {0x478f, 0x10}, - {0x4793, 0x10}, - {0x4797, 0x0e}, - {0x479b, 0x0e}, - {0x0162, 0x0d}, - {0x0163, 0x78}, }; static const struct imx219_reg mode_640_480_regs[] = { - {0x0100, 0x00}, - {0x30eb, 0x05}, - {0x30eb, 0x0c}, - {0x300a, 0xff}, - {0x300b, 0xff}, - {0x30eb, 0x05}, - {0x30eb, 0x09}, - {0x0114, 0x01}, - {0x0128, 0x00}, - {0x012a, 0x18}, - {0x012b, 0x00}, - {0x0162, 0x0d}, - {0x0163, 0x78}, {0x0164, 0x03}, {0x0165, 0xe8}, {0x0166, 0x08}, @@ -347,35 +275,12 @@ static const struct imx219_reg mode_640_480_regs[] = { {0x016d, 0x80}, {0x016e, 0x01}, {0x016f, 0xe0}, - {0x0170, 0x01}, - {0x0171, 0x01}, - {0x0174, 0x03}, + {0x0174, 0x03}, /* x2-analog binning */ {0x0175, 0x03}, - {0x0301, 0x05}, - {0x0303, 0x01}, - {0x0304, 0x03}, - {0x0305, 0x03}, - {0x0306, 0x00}, - {0x0307, 0x39}, - {0x030b, 0x01}, - {0x030c, 0x00}, - {0x030d, 0x72}, {0x0624, 0x06}, {0x0625, 0x68}, {0x0626, 0x04}, {0x0627, 0xd0}, - {0x455e, 0x00}, - {0x471e, 0x4b}, - {0x4767, 0x0f}, - {0x4750, 0x14}, - {0x4540, 0x00}, - {0x47b4, 0x14}, - {0x4713, 0x30}, - {0x478b, 0x10}, - {0x478f, 0x10}, - {0x4793, 0x10}, - {0x4797, 0x0e}, - {0x479b, 0x0e}, }; static const struct imx219_reg raw8_framefmt_regs[] = { @@ -1030,6 +935,13 @@ static int imx219_start_streaming(struct imx219 *imx219) return ret; } + /* Send all registers that are common to all modes */ + ret = imx219_write_regs(imx219, imx219_common_regs, ARRAY_SIZE(imx219_common_regs)); + if (ret) { + dev_err(&client->dev, "%s failed to send mfg header\n", __func__); + goto err_rpm_put; + } + /* Apply default values of current mode */ reg_list = &imx219->mode->reg_list; ret = imx219_write_regs(imx219, reg_list->regs, reg_list->num_of_regs); From c6c3b4ae31664e2b52e31a80b231c6f37f370c97 Mon Sep 17 00:00:00 2001 From: Jai Luthra Date: Tue, 17 Jan 2023 09:16:23 +0100 Subject: [PATCH 1774/4345] media: i2c: imx219: Fix binning for RAW8 capture [ Upstream commit ef86447e775fb1f2ced00d4c7fff2c0a1c63f165 ] 2x2 binning works fine for RAW10 capture, but for RAW8 1232p mode it leads to corrupted frames [1][2]. Using the special 2x2 analog binning mode fixes the issue, but causes artefacts for RAW10 1232p capture. So here we choose the binning mode depending upon the frame format selected. As both binning modes work fine for 480p RAW8 and RAW10 capture, it can share the same code path as 1232p for selecting binning mode. [1] https://forums.raspberrypi.com/viewtopic.php?t=332103 [2] https://github.com/raspberrypi/libcamera-apps/issues/281 Fixes: 22da1d56e982 ("media: i2c: imx219: Add support for RAW8 bit bayer format") Signed-off-by: Jai Luthra Reviewed-by: Dave Stevenson Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/imx219.c | 57 ++++++++++++++++++++++++++++++++------ 1 file changed, 49 insertions(+), 8 deletions(-) diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c index a28926069b82..b975636d9440 100644 --- a/drivers/media/i2c/imx219.c +++ b/drivers/media/i2c/imx219.c @@ -89,6 +89,12 @@ #define IMX219_REG_ORIENTATION 0x0172 +/* Binning Mode */ +#define IMX219_REG_BINNING_MODE 0x0174 +#define IMX219_BINNING_NONE 0x0000 +#define IMX219_BINNING_2X2 0x0101 +#define IMX219_BINNING_2X2_ANALOG 0x0303 + /* Test Pattern Control */ #define IMX219_REG_TEST_PATTERN 0x0600 #define IMX219_TEST_PATTERN_DISABLE 0 @@ -143,6 +149,9 @@ struct imx219_mode { /* Default register values */ struct imx219_reg_list reg_list; + + /* 2x2 binning is used */ + bool binning; }; static const struct imx219_reg imx219_common_regs[] = { @@ -212,8 +221,6 @@ static const struct imx219_reg mode_3280x2464_regs[] = { {0x016d, 0xd0}, {0x016e, 0x09}, {0x016f, 0xa0}, - {0x0174, 0x00}, /* No-Binning */ - {0x0175, 0x00}, {0x0624, 0x0c}, {0x0625, 0xd0}, {0x0626, 0x09}, @@ -233,8 +240,6 @@ static const struct imx219_reg mode_1920_1080_regs[] = { {0x016d, 0x80}, {0x016e, 0x04}, {0x016f, 0x38}, - {0x0174, 0x00}, /* No-Binning */ - {0x0175, 0x00}, {0x0624, 0x07}, {0x0625, 0x80}, {0x0626, 0x04}, @@ -254,8 +259,6 @@ static const struct imx219_reg mode_1640_1232_regs[] = { {0x016d, 0x68}, {0x016e, 0x04}, {0x016f, 0xd0}, - {0x0174, 0x01}, /* x2-Binning */ - {0x0175, 0x01}, {0x0624, 0x06}, {0x0625, 0x68}, {0x0626, 0x04}, @@ -275,8 +278,6 @@ static const struct imx219_reg mode_640_480_regs[] = { {0x016d, 0x80}, {0x016e, 0x01}, {0x016f, 0xe0}, - {0x0174, 0x03}, /* x2-analog binning */ - {0x0175, 0x03}, {0x0624, 0x06}, {0x0625, 0x68}, {0x0626, 0x04}, @@ -386,6 +387,7 @@ static const struct imx219_mode supported_modes[] = { .num_of_regs = ARRAY_SIZE(mode_3280x2464_regs), .regs = mode_3280x2464_regs, }, + .binning = false, }, { /* 1080P 30fps cropped */ @@ -402,6 +404,7 @@ static const struct imx219_mode supported_modes[] = { .num_of_regs = ARRAY_SIZE(mode_1920_1080_regs), .regs = mode_1920_1080_regs, }, + .binning = false, }, { /* 2x2 binned 30fps mode */ @@ -418,6 +421,7 @@ static const struct imx219_mode supported_modes[] = { .num_of_regs = ARRAY_SIZE(mode_1640_1232_regs), .regs = mode_1640_1232_regs, }, + .binning = true, }, { /* 640x480 30fps mode */ @@ -434,6 +438,7 @@ static const struct imx219_mode supported_modes[] = { .num_of_regs = ARRAY_SIZE(mode_640_480_regs), .regs = mode_640_480_regs, }, + .binning = true, }, }; @@ -872,6 +877,35 @@ static int imx219_set_framefmt(struct imx219 *imx219) return -EINVAL; } +static int imx219_set_binning(struct imx219 *imx219) +{ + if (!imx219->mode->binning) { + return imx219_write_reg(imx219, IMX219_REG_BINNING_MODE, + IMX219_REG_VALUE_16BIT, + IMX219_BINNING_NONE); + } + + switch (imx219->fmt.code) { + case MEDIA_BUS_FMT_SRGGB8_1X8: + case MEDIA_BUS_FMT_SGRBG8_1X8: + case MEDIA_BUS_FMT_SGBRG8_1X8: + case MEDIA_BUS_FMT_SBGGR8_1X8: + return imx219_write_reg(imx219, IMX219_REG_BINNING_MODE, + IMX219_REG_VALUE_16BIT, + IMX219_BINNING_2X2_ANALOG); + + case MEDIA_BUS_FMT_SRGGB10_1X10: + case MEDIA_BUS_FMT_SGRBG10_1X10: + case MEDIA_BUS_FMT_SGBRG10_1X10: + case MEDIA_BUS_FMT_SBGGR10_1X10: + return imx219_write_reg(imx219, IMX219_REG_BINNING_MODE, + IMX219_REG_VALUE_16BIT, + IMX219_BINNING_2X2); + } + + return -EINVAL; +} + static const struct v4l2_rect * __imx219_get_pad_crop(struct imx219 *imx219, struct v4l2_subdev_pad_config *cfg, unsigned int pad, enum v4l2_subdev_format_whence which) @@ -957,6 +991,13 @@ static int imx219_start_streaming(struct imx219 *imx219) goto err_rpm_put; } + ret = imx219_set_binning(imx219); + if (ret) { + dev_err(&client->dev, "%s failed to set binning: %d\n", + __func__, ret); + goto err_rpm_put; + } + /* Apply customized values from user */ ret = __v4l2_ctrl_handler_setup(imx219->sd.ctrl_handler); if (ret) From 78da5a378bdacd5bf68c3a6389bdc1dd0c0f5b3c Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Tue, 24 Jan 2023 08:55:33 +0100 Subject: [PATCH 1775/4345] media: rc: Fix use-after-free bugs caused by ene_tx_irqsim() [ Upstream commit 29b0589a865b6f66d141d79b2dd1373e4e50fe17 ] When the ene device is detaching, function ene_remove() will be called. But there is no function to cancel tx_sim_timer in ene_remove(), the timer handler ene_tx_irqsim() could race with ene_remove(). As a result, the UAF bugs could happen, the process is shown below. (cleanup routine) | (timer routine) | mod_timer(&dev->tx_sim_timer, ..) ene_remove() | (wait a time) | ene_tx_irqsim() | dev->hw_lock //USE | ene_tx_sample(dev) //USE Fix by adding del_timer_sync(&dev->tx_sim_timer) in ene_remove(), The tx_sim_timer could stop before ene device is deallocated. What's more, The rc_unregister_device() and del_timer_sync() should be called first in ene_remove() and the deallocated functions such as free_irq(), release_region() and so on should be called behind them. Because the rc_unregister_device() is well synchronized. Otherwise, race conditions may happen. The situations that may lead to race conditions are shown below. Firstly, the rx receiver is disabled with ene_rx_disable() before rc_unregister_device() in ene_remove(), which means it can be enabled again if a process opens /dev/lirc0 between ene_rx_disable() and rc_unregister_device(). Secondly, the irqaction descriptor is freed by free_irq() before the rc device is unregistered, which means irqaction descriptor may be accessed again after it is deallocated. Thirdly, the timer can call ene_tx_sample() that can write to the io ports, which means the io ports could be accessed again after they are deallocated by release_region(). Therefore, the rc_unregister_device() and del_timer_sync() should be called first in ene_remove(). Suggested by: Sean Young Fixes: 9ea53b74df9c ("V4L/DVB: STAGING: remove lirc_ene0100 driver") Signed-off-by: Duoming Zhou Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/rc/ene_ir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/rc/ene_ir.c b/drivers/media/rc/ene_ir.c index 6049e5c95394..5aa3953cab82 100644 --- a/drivers/media/rc/ene_ir.c +++ b/drivers/media/rc/ene_ir.c @@ -1106,6 +1106,8 @@ static void ene_remove(struct pnp_dev *pnp_dev) struct ene_device *dev = pnp_get_drvdata(pnp_dev); unsigned long flags; + rc_unregister_device(dev->rdev); + del_timer_sync(&dev->tx_sim_timer); spin_lock_irqsave(&dev->hw_lock, flags); ene_rx_disable(dev); ene_rx_restore_hw_buffer(dev); @@ -1113,7 +1115,6 @@ static void ene_remove(struct pnp_dev *pnp_dev) free_irq(dev->irq, dev); release_region(dev->hw_io, ENE_IO_SIZE); - rc_unregister_device(dev->rdev); kfree(dev); } From cc2f9c8eb1ee470e055d6d383027077d072899d8 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 26 Jan 2023 14:03:51 +0100 Subject: [PATCH 1776/4345] media: i2c: ov7670: 0 instead of -EINVAL was returned [ Upstream commit 6a4c664539e6de9b32b65ddcf767ec1bcc1d7f8a ] If the media bus is unsupported, then return -EINVAL. Instead it returned 'ret' which happened to be 0. This fixes a smatch warning: ov7670.c:1843 ov7670_parse_dt() warn: missing error code? 'ret' Signed-off-by: Hans Verkuil Fixes: 01b8444828fc ("media: v4l2: i2c: ov7670: Implement OF mbus configuration") Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov7670.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c index 154776d0069e..e47800cb6c0f 100644 --- a/drivers/media/i2c/ov7670.c +++ b/drivers/media/i2c/ov7670.c @@ -1824,7 +1824,7 @@ static int ov7670_parse_dt(struct device *dev, if (bus_cfg.bus_type != V4L2_MBUS_PARALLEL) { dev_err(dev, "Unsupported media bus type\n"); - return ret; + return -EINVAL; } info->mbus_config = bus_cfg.bus.parallel.flags; From 42f8ba8355682f6c4125b75503cac0cef4ac91d3 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Mon, 23 Jan 2023 03:04:38 +0100 Subject: [PATCH 1777/4345] media: usb: siano: Fix use after free bugs caused by do_submit_urb [ Upstream commit ebad8e731c1c06adf04621d6fd327b860c0861b5 ] There are UAF bugs caused by do_submit_urb(). One of the KASan reports is shown below: [ 36.403605] BUG: KASAN: use-after-free in worker_thread+0x4a2/0x890 [ 36.406105] Read of size 8 at addr ffff8880059600e8 by task kworker/0:2/49 [ 36.408316] [ 36.408867] CPU: 0 PID: 49 Comm: kworker/0:2 Not tainted 6.2.0-rc3-15798-g5a41237ad1d4-dir8 [ 36.411696] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g15584 [ 36.416157] Workqueue: 0x0 (events) [ 36.417654] Call Trace: [ 36.418546] [ 36.419320] dump_stack_lvl+0x96/0xd0 [ 36.420522] print_address_description+0x75/0x350 [ 36.421992] print_report+0x11b/0x250 [ 36.423174] ? _raw_spin_lock_irqsave+0x87/0xd0 [ 36.424806] ? __virt_addr_valid+0xcf/0x170 [ 36.426069] ? worker_thread+0x4a2/0x890 [ 36.427355] kasan_report+0x131/0x160 [ 36.428556] ? worker_thread+0x4a2/0x890 [ 36.430053] worker_thread+0x4a2/0x890 [ 36.431297] ? worker_clr_flags+0x90/0x90 [ 36.432479] kthread+0x166/0x190 [ 36.433493] ? kthread_blkcg+0x50/0x50 [ 36.434669] ret_from_fork+0x22/0x30 [ 36.435923] [ 36.436684] [ 36.437215] Allocated by task 24: [ 36.438289] kasan_set_track+0x50/0x80 [ 36.439436] __kasan_kmalloc+0x89/0xa0 [ 36.440566] smsusb_probe+0x374/0xc90 [ 36.441920] usb_probe_interface+0x2d1/0x4c0 [ 36.443253] really_probe+0x1d5/0x580 [ 36.444539] __driver_probe_device+0xe3/0x130 [ 36.446085] driver_probe_device+0x49/0x220 [ 36.447423] __device_attach_driver+0x19e/0x1b0 [ 36.448931] bus_for_each_drv+0xcb/0x110 [ 36.450217] __device_attach+0x132/0x1f0 [ 36.451470] bus_probe_device+0x59/0xf0 [ 36.452563] device_add+0x4ec/0x7b0 [ 36.453830] usb_set_configuration+0xc63/0xe10 [ 36.455230] usb_generic_driver_probe+0x3b/0x80 [ 36.456166] printk: console [ttyGS0] disabled [ 36.456569] usb_probe_device+0x90/0x110 [ 36.459523] really_probe+0x1d5/0x580 [ 36.461027] __driver_probe_device+0xe3/0x130 [ 36.462465] driver_probe_device+0x49/0x220 [ 36.463847] __device_attach_driver+0x19e/0x1b0 [ 36.465229] bus_for_each_drv+0xcb/0x110 [ 36.466466] __device_attach+0x132/0x1f0 [ 36.467799] bus_probe_device+0x59/0xf0 [ 36.469010] device_add+0x4ec/0x7b0 [ 36.470125] usb_new_device+0x863/0xa00 [ 36.471374] hub_event+0x18c7/0x2220 [ 36.472746] process_one_work+0x34c/0x5b0 [ 36.474041] worker_thread+0x4b7/0x890 [ 36.475216] kthread+0x166/0x190 [ 36.476267] ret_from_fork+0x22/0x30 [ 36.477447] [ 36.478160] Freed by task 24: [ 36.479239] kasan_set_track+0x50/0x80 [ 36.480512] kasan_save_free_info+0x2b/0x40 [ 36.481808] ____kasan_slab_free+0x122/0x1a0 [ 36.483173] __kmem_cache_free+0xc4/0x200 [ 36.484563] smsusb_term_device+0xcd/0xf0 [ 36.485896] smsusb_probe+0xc85/0xc90 [ 36.486976] usb_probe_interface+0x2d1/0x4c0 [ 36.488303] really_probe+0x1d5/0x580 [ 36.489498] __driver_probe_device+0xe3/0x130 [ 36.491140] driver_probe_device+0x49/0x220 [ 36.492475] __device_attach_driver+0x19e/0x1b0 [ 36.493988] bus_for_each_drv+0xcb/0x110 [ 36.495171] __device_attach+0x132/0x1f0 [ 36.496617] bus_probe_device+0x59/0xf0 [ 36.497875] device_add+0x4ec/0x7b0 [ 36.498972] usb_set_configuration+0xc63/0xe10 [ 36.500264] usb_generic_driver_probe+0x3b/0x80 [ 36.501740] usb_probe_device+0x90/0x110 [ 36.503084] really_probe+0x1d5/0x580 [ 36.504241] __driver_probe_device+0xe3/0x130 [ 36.505548] driver_probe_device+0x49/0x220 [ 36.506766] __device_attach_driver+0x19e/0x1b0 [ 36.508368] bus_for_each_drv+0xcb/0x110 [ 36.509646] __device_attach+0x132/0x1f0 [ 36.510911] bus_probe_device+0x59/0xf0 [ 36.512103] device_add+0x4ec/0x7b0 [ 36.513215] usb_new_device+0x863/0xa00 [ 36.514736] hub_event+0x18c7/0x2220 [ 36.516130] process_one_work+0x34c/0x5b0 [ 36.517396] worker_thread+0x4b7/0x890 [ 36.518591] kthread+0x166/0x190 [ 36.519599] ret_from_fork+0x22/0x30 [ 36.520851] [ 36.521405] Last potentially related work creation: [ 36.523143] kasan_save_stack+0x3f/0x60 [ 36.524275] kasan_record_aux_stack_noalloc+0x9d/0xb0 [ 36.525831] insert_work+0x25/0x130 [ 36.527039] __queue_work+0x4d4/0x620 [ 36.528236] queue_work_on+0x72/0xb0 [ 36.529344] __usb_hcd_giveback_urb+0x13f/0x1b0 [ 36.530819] dummy_timer+0x350/0x1a40 [ 36.532149] call_timer_fn+0x2c/0x190 [ 36.533567] expire_timers+0x69/0x1f0 [ 36.534736] __run_timers+0x289/0x2d0 [ 36.535841] run_timer_softirq+0x2d/0x60 [ 36.537110] __do_softirq+0x116/0x380 [ 36.538377] [ 36.538950] Second to last potentially related work creation: [ 36.540855] kasan_save_stack+0x3f/0x60 [ 36.542084] kasan_record_aux_stack_noalloc+0x9d/0xb0 [ 36.543592] insert_work+0x25/0x130 [ 36.544891] __queue_work+0x4d4/0x620 [ 36.546168] queue_work_on+0x72/0xb0 [ 36.547328] __usb_hcd_giveback_urb+0x13f/0x1b0 [ 36.548805] dummy_timer+0x350/0x1a40 [ 36.550116] call_timer_fn+0x2c/0x190 [ 36.551570] expire_timers+0x69/0x1f0 [ 36.552762] __run_timers+0x289/0x2d0 [ 36.553916] run_timer_softirq+0x2d/0x60 [ 36.555118] __do_softirq+0x116/0x380 [ 36.556239] [ 36.556807] The buggy address belongs to the object at ffff888005960000 [ 36.556807] which belongs to the cache kmalloc-4k of size 4096 [ 36.560652] The buggy address is located 232 bytes inside of [ 36.560652] 4096-byte region [ffff888005960000, ffff888005961000) [ 36.564791] [ 36.565355] The buggy address belongs to the physical page: [ 36.567212] page:000000004f0a0731 refcount:1 mapcount:0 mapping:0000000000000000 index:0x00 [ 36.570534] head:000000004f0a0731 order:3 compound_mapcount:0 subpages_mapcount:0 compound0 [ 36.573717] flags: 0x100000000010200(slab|head|node=0|zone=1) [ 36.575481] raw: 0100000000010200 ffff888001042140 dead000000000122 0000000000000000 [ 36.577842] raw: 0000000000000000 0000000000040004 00000001ffffffff 0000000000000000 [ 36.580175] page dumped because: kasan: bad access detected [ 36.581994] [ 36.582548] Memory state around the buggy address: [ 36.583983] ffff88800595ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 36.586240] ffff888005960000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 36.588884] >ffff888005960080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 36.591071] ^ [ 36.593295] ffff888005960100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 36.595705] ffff888005960180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 36.598026] ================================================================== [ 36.600224] Disabling lock debugging due to kernel taint [ 36.602681] general protection fault, probably for non-canonical address 0x43600a000000060I [ 36.607129] CPU: 0 PID: 49 Comm: kworker/0:2 Tainted: G B 6.2.0-rc3-15798-8 [ 36.611115] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g15584 [ 36.615026] Workqueue: events do_submit_urb [ 36.616290] RIP: 0010:_raw_spin_lock_irqsave+0x8a/0xd0 [ 36.618107] Code: 24 00 00 00 00 48 89 df be 04 00 00 00 e8 9e b5 c6 fe 48 89 ef be 04 00 5 [ 36.623522] RSP: 0018:ffff888004b6fcf0 EFLAGS: 00010046 [ 36.625072] RAX: 0000000000000000 RBX: 043600a000000060 RCX: ffffffff9fc0e0d7 [ 36.627206] RDX: 0000000000000000 RSI: dffffc0000000000 RDI: ffff888004b6fcf0 [ 36.629813] RBP: ffff888004b6fcf0 R08: dffffc0000000000 R09: ffffed100096df9f [ 36.631974] R10: dfffe9100096dfa0 R11: 1ffff1100096df9e R12: ffff888005960020 [ 36.634285] R13: ffff8880059600f0 R14: 0000000000000246 R15: 0000000000000001 [ 36.636438] FS: 0000000000000000(0000) GS:ffff88806d600000(0000) knlGS:0000000000000000 [ 36.639092] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 36.640951] CR2: 00007f07476819a3 CR3: 0000000004a34000 CR4: 00000000000006f0 [ 36.643411] Call Trace: [ 36.644215] [ 36.644902] smscore_getbuffer+0x3e/0x1e0 [ 36.646147] do_submit_urb+0x4f/0x190 [ 36.647449] process_one_work+0x34c/0x5b0 [ 36.648777] worker_thread+0x4b7/0x890 [ 36.649984] ? worker_clr_flags+0x90/0x90 [ 36.651166] kthread+0x166/0x190 [ 36.652151] ? kthread_blkcg+0x50/0x50 [ 36.653547] ret_from_fork+0x22/0x30 [ 36.655051] [ 36.655733] Modules linked in: [ 36.656787] ---[ end trace 0000000000000000 ]--- [ 36.658328] RIP: 0010:_raw_spin_lock_irqsave+0x8a/0xd0 [ 36.660045] Code: 24 00 00 00 00 48 89 df be 04 00 00 00 e8 9e b5 c6 fe 48 89 ef be 04 00 5 [ 36.665730] RSP: 0018:ffff888004b6fcf0 EFLAGS: 00010046 [ 36.667448] RAX: 0000000000000000 RBX: 043600a000000060 RCX: ffffffff9fc0e0d7 [ 36.669675] RDX: 0000000000000000 RSI: dffffc0000000000 RDI: ffff888004b6fcf0 [ 36.672645] RBP: ffff888004b6fcf0 R08: dffffc0000000000 R09: ffffed100096df9f [ 36.674921] R10: dfffe9100096dfa0 R11: 1ffff1100096df9e R12: ffff888005960020 [ 36.677034] R13: ffff8880059600f0 R14: 0000000000000246 R15: 0000000000000001 [ 36.679184] FS: 0000000000000000(0000) GS:ffff88806d600000(0000) knlGS:0000000000000000 [ 36.681655] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 36.683383] CR2: 00007f07476819a3 CR3: 0000000004a34000 CR4: 00000000000006f0 [ 36.685733] Kernel panic - not syncing: Fatal exception [ 36.688585] Kernel Offset: 0x1d400000 from 0xffffffff81000000 (relocation range: 0xfffffff) [ 36.692199] ---[ end Kernel panic - not syncing: Fatal exception ]--- When the siano device is plugged in, it may call the following functions to initialize the device. smsusb_probe()-->smsusb_init_device()-->smscore_start_device(). When smscore_start_device() gets failed, the function smsusb_term_device() will be called and smsusb_device_t will be deallocated. Although we use usb_kill_urb() in smsusb_stop_streaming() to cancel transfer requests and wait for them to finish, the worker threads that are scheduled by smsusb_onresponse() may be still running. As a result, the UAF bugs could happen. We add cancel_work_sync() in smsusb_stop_streaming() in order that the worker threads could finish before the smsusb_device_t is deallocated. Fixes: dd47fbd40e6e ("[media] smsusb: don't sleep while atomic") Signed-off-by: Duoming Zhou Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/siano/smsusb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c index df4c5dcba39c..1babfe6e2c36 100644 --- a/drivers/media/usb/siano/smsusb.c +++ b/drivers/media/usb/siano/smsusb.c @@ -179,6 +179,7 @@ static void smsusb_stop_streaming(struct smsusb_device_t *dev) for (i = 0; i < MAX_URBS; i++) { usb_kill_urb(&dev->surbs[i].urb); + cancel_work_sync(&dev->surbs[i].wq); if (dev->surbs[i].cb) { smscore_putbuffer(dev->coredev, dev->surbs[i].cb); From 2b72ceef174041b9e74fd2897876841737fd8f19 Mon Sep 17 00:00:00 2001 From: Tasos Sahanidis Date: Thu, 26 Jan 2023 12:00:59 +0100 Subject: [PATCH 1778/4345] media: saa7134: Use video_unregister_device for radio_dev [ Upstream commit bc7635c6435c77a0c168e2cc6535740adfaff4e4 ] The radio device doesn't use vb2, thus calling vb2_video_unregister_device() which results in the following warning being printed on module unload. WARNING: CPU: 1 PID: 215963 at drivers/media/common/videobuf2/videobuf2-v4l2.c:1236 vb2_video_unregister_device+0xc6/0xe0 [videobuf2_v4l2] Fixes: 11788d9b7e91 ("media: media/pci: use vb2_video_unregister_device()") Signed-off-by: Tasos Sahanidis Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/pci/saa7134/saa7134-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c index efb757d5168a..e97c30070fc6 100644 --- a/drivers/media/pci/saa7134/saa7134-core.c +++ b/drivers/media/pci/saa7134/saa7134-core.c @@ -977,7 +977,7 @@ static void saa7134_unregister_video(struct saa7134_dev *dev) } if (dev->radio_dev) { if (video_is_registered(dev->radio_dev)) - vb2_video_unregister_device(dev->radio_dev); + video_unregister_device(dev->radio_dev); else video_device_release(dev->radio_dev); dev->radio_dev = NULL; From 91f9d708716daf9dfc4d585ff57ef5ef05b69437 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 14 Feb 2023 15:42:31 -0800 Subject: [PATCH 1779/4345] rpmsg: glink: Avoid infinite loop on intent for missing channel [ Upstream commit 3e74ec2f39362bffbd42854acbb67c7f4cb808f9 ] In the event that an intent advertisement arrives on an unknown channel the fifo is not advanced, resulting in the same message being handled over and over. Fixes: dacbb35e930f ("rpmsg: glink: Receive and store the remote intent buffers") Signed-off-by: Bjorn Andersson Reviewed-by: Chris Lew Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230214234231.2069751-1-quic_bjorande@quicinc.com Signed-off-by: Sasha Levin --- drivers/rpmsg/qcom_glink_native.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 7cbed0310c09..98b6d4c09c82 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -929,6 +929,7 @@ static void qcom_glink_handle_intent(struct qcom_glink *glink, spin_unlock_irqrestore(&glink->idr_lock, flags); if (!channel) { dev_err(glink->dev, "intents for non-existing channel\n"); + qcom_glink_rx_advance(glink, ALIGN(msglen, 8)); return; } From f34cc701ea0a0a915b17ad5b108341bd78e8a634 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 29 Sep 2022 16:34:45 +0200 Subject: [PATCH 1780/4345] udf: Define EFSCORRUPTED error code [ Upstream commit 3d2d7e61553dbcc8ba45201d8ae4f383742c8202 ] Similarly to other filesystems define EFSCORRUPTED error code for reporting internal filesystem corruption. Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/udf/udf_sb.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h index 4fa620543d30..2205859731dc 100644 --- a/fs/udf/udf_sb.h +++ b/fs/udf/udf_sb.h @@ -51,6 +51,8 @@ #define MF_DUPLICATE_MD 0x01 #define MF_MIRROR_FE_LOADED 0x02 +#define EFSCORRUPTED EUCLEAN + struct udf_meta_data { __u32 s_meta_file_loc; __u32 s_mirror_file_loc; From 199624f3144d79fab1cff533ce6a4b82390520a3 Mon Sep 17 00:00:00 2001 From: Markuss Broks Date: Sat, 21 Jan 2023 22:18:42 +0200 Subject: [PATCH 1781/4345] ARM: dts: exynos: Use Exynos5420 compatible for the MIPI video phy [ Upstream commit 5d5aa219a790d61cad2c38e1aa32058f16ad2f0b ] For some reason, the driver adding support for Exynos5420 MIPI phy back in 2016 wasn't used on Exynos5420, which caused a kernel panic. Add the proper compatible for it. Signed-off-by: Markuss Broks Link: https://lore.kernel.org/r/20230121201844.46872-2-markuss.broks@gmail.com Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- arch/arm/boot/dts/exynos5420.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi index 83580f076a58..34886535f847 100644 --- a/arch/arm/boot/dts/exynos5420.dtsi +++ b/arch/arm/boot/dts/exynos5420.dtsi @@ -605,7 +605,7 @@ }; mipi_phy: mipi-video-phy { - compatible = "samsung,s5pv210-mipi-video-phy"; + compatible = "samsung,exynos5420-mipi-video-phy"; syscon = <&pmu_system_controller>; #phy-cells = <1>; }; From 6e291810fe83a384700eb24a1f714966391ed562 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Tue, 17 Jan 2023 15:08:05 +0800 Subject: [PATCH 1782/4345] blk-iocost: fix divide by 0 error in calc_lcoefs() [ Upstream commit 984af1e66b4126cf145153661cc24c213e2ec231 ] echo max of u64 to cost.model can cause divide by 0 error. # echo 8:0 rbps=18446744073709551615 > /sys/fs/cgroup/io.cost.model divide error: 0000 [#1] PREEMPT SMP RIP: 0010:calc_lcoefs+0x4c/0xc0 Call Trace: ioc_refresh_params+0x2b3/0x4f0 ioc_cost_model_write+0x3cb/0x4c0 ? _copy_from_iter+0x6d/0x6c0 ? kernfs_fop_write_iter+0xfc/0x270 cgroup_file_write+0xa0/0x200 kernfs_fop_write_iter+0x17d/0x270 vfs_write+0x414/0x620 ksys_write+0x73/0x160 __x64_sys_write+0x1e/0x30 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd calc_lcoefs() uses the input value of cost.model in DIV_ROUND_UP_ULL, overflow would happen if bps plus IOC_PAGE_SIZE is greater than ULLONG_MAX, it can cause divide by 0 error. Fix the problem by setting basecost Signed-off-by: Li Nan Signed-off-by: Yu Kuai Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20230117070806.3857142-5-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-iocost.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index fb8f959a7f32..9255b642d6ad 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -872,9 +872,14 @@ static void calc_lcoefs(u64 bps, u64 seqiops, u64 randiops, *page = *seqio = *randio = 0; - if (bps) - *page = DIV64_U64_ROUND_UP(VTIME_PER_SEC, - DIV_ROUND_UP_ULL(bps, IOC_PAGE_SIZE)); + if (bps) { + u64 bps_pages = DIV_ROUND_UP_ULL(bps, IOC_PAGE_SIZE); + + if (bps_pages) + *page = DIV64_U64_ROUND_UP(VTIME_PER_SEC, bps_pages); + else + *page = 1; + } if (seqiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, seqiops); From 99ff971b62e5bd5dee65bbe9777375206f5db791 Mon Sep 17 00:00:00 2001 From: Minsuk Kang Date: Mon, 5 Dec 2022 10:43:08 +0900 Subject: [PATCH 1783/4345] wifi: ath9k: Fix use-after-free in ath9k_hif_usb_disconnect() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f099c5c9e2ba08a379bd354a82e05ef839ae29ac ] This patch fixes a use-after-free in ath9k that occurs in ath9k_hif_usb_disconnect() when ath9k_destroy_wmi() is trying to access 'drv_priv' that has already been freed by ieee80211_free_hw(), called by ath9k_htc_hw_deinit(). The patch moves ath9k_destroy_wmi() before ieee80211_free_hw(). Note that urbs from the driver should be killed before freeing 'wmi' with ath9k_destroy_wmi() as their callbacks will access 'wmi'. Found by a modified version of syzkaller. ================================================================== BUG: KASAN: use-after-free in ath9k_destroy_wmi+0x38/0x40 Read of size 8 at addr ffff8881069132a0 by task kworker/0:1/7 CPU: 0 PID: 7 Comm: kworker/0:1 Tainted: G O 5.14.0+ #131 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 Workqueue: usb_hub_wq hub_event Call Trace: dump_stack_lvl+0x8e/0xd1 print_address_description.constprop.0.cold+0x93/0x334 ? ath9k_destroy_wmi+0x38/0x40 ? ath9k_destroy_wmi+0x38/0x40 kasan_report.cold+0x83/0xdf ? ath9k_destroy_wmi+0x38/0x40 ath9k_destroy_wmi+0x38/0x40 ath9k_hif_usb_disconnect+0x329/0x3f0 ? ath9k_hif_usb_suspend+0x120/0x120 ? usb_disable_interface+0xfc/0x180 usb_unbind_interface+0x19b/0x7e0 ? usb_autoresume_device+0x50/0x50 device_release_driver_internal+0x44d/0x520 bus_remove_device+0x2e5/0x5a0 device_del+0x5b2/0xe30 ? __device_link_del+0x370/0x370 ? usb_remove_ep_devs+0x43/0x80 ? remove_intf_ep_devs+0x112/0x1a0 usb_disable_device+0x1e3/0x5a0 usb_disconnect+0x267/0x870 hub_event+0x168d/0x3950 ? rcu_read_lock_sched_held+0xa1/0xd0 ? hub_port_debounce+0x2e0/0x2e0 ? check_irq_usage+0x860/0xf20 ? drain_workqueue+0x281/0x360 ? lock_release+0x640/0x640 ? rcu_read_lock_sched_held+0xa1/0xd0 ? rcu_read_lock_bh_held+0xb0/0xb0 ? lockdep_hardirqs_on_prepare+0x273/0x3e0 process_one_work+0x92b/0x1460 ? pwq_dec_nr_in_flight+0x330/0x330 ? rwlock_bug.part.0+0x90/0x90 worker_thread+0x95/0xe00 ? __kthread_parkme+0x115/0x1e0 ? process_one_work+0x1460/0x1460 kthread+0x3a1/0x480 ? set_kthread_struct+0x120/0x120 ret_from_fork+0x1f/0x30 The buggy address belongs to the page: page:ffffea00041a44c0 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x106913 flags: 0x200000000000000(node=0|zone=2) raw: 0200000000000000 0000000000000000 dead000000000122 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as freed page last allocated via order 3, migratetype Unmovable, gfp_mask 0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), pid 7, ts 38347963444, free_ts 41399957635 prep_new_page+0x1aa/0x240 get_page_from_freelist+0x159a/0x27c0 __alloc_pages+0x2da/0x6a0 alloc_pages+0xec/0x1e0 kmalloc_order+0x39/0xf0 kmalloc_order_trace+0x19/0x120 __kmalloc+0x308/0x390 wiphy_new_nm+0x6f5/0x1dd0 ieee80211_alloc_hw_nm+0x36d/0x2230 ath9k_htc_probe_device+0x9d/0x1e10 ath9k_htc_hw_init+0x34/0x50 ath9k_hif_usb_firmware_cb+0x25f/0x4e0 request_firmware_work_func+0x131/0x240 process_one_work+0x92b/0x1460 worker_thread+0x95/0xe00 kthread+0x3a1/0x480 page last free stack trace: free_pcp_prepare+0x3d3/0x7f0 free_unref_page+0x1e/0x3d0 device_release+0xa4/0x240 kobject_put+0x186/0x4c0 put_device+0x20/0x30 ath9k_htc_disconnect_device+0x1cf/0x2c0 ath9k_htc_hw_deinit+0x26/0x30 ath9k_hif_usb_disconnect+0x2d9/0x3f0 usb_unbind_interface+0x19b/0x7e0 device_release_driver_internal+0x44d/0x520 bus_remove_device+0x2e5/0x5a0 device_del+0x5b2/0xe30 usb_disable_device+0x1e3/0x5a0 usb_disconnect+0x267/0x870 hub_event+0x168d/0x3950 process_one_work+0x92b/0x1460 Memory state around the buggy address: ffff888106913180: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888106913200: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff888106913280: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff888106913300: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888106913380: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== Reported-by: Dokyung Song Reported-by: Jisoo Jang Reported-by: Minsuk Kang Signed-off-by: Minsuk Kang Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221205014308.1617597-1-linuxlovemin@yonsei.ac.kr Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/hif_usb.c | 2 -- drivers/net/wireless/ath/ath9k/htc_drv_init.c | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index de6c0824c9ca..f521dfa2f194 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -1424,8 +1424,6 @@ static void ath9k_hif_usb_disconnect(struct usb_interface *interface) if (hif_dev->flags & HIF_USB_READY) { ath9k_htc_hw_deinit(hif_dev->htc_handle, unplugged); - ath9k_hif_usb_dev_deinit(hif_dev); - ath9k_destroy_wmi(hif_dev->htc_handle->drv_priv); ath9k_htc_hw_free(hif_dev->htc_handle); } diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index 07ac88fb1c57..96a3185a96d7 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -988,6 +988,8 @@ void ath9k_htc_disconnect_device(struct htc_target *htc_handle, bool hotunplug) ath9k_deinit_device(htc_handle->drv_priv); ath9k_stop_wmi(htc_handle->drv_priv); + ath9k_hif_usb_dealloc_urbs((struct hif_device_usb *)htc_handle->hif_dev); + ath9k_destroy_wmi(htc_handle->drv_priv); ieee80211_free_hw(htc_handle->drv_priv->hw); } } From d6ef66194bb4a6c18f5b9649bf62597909b040e4 Mon Sep 17 00:00:00 2001 From: Jisoo Jang Date: Tue, 15 Nov 2022 13:34:58 +0900 Subject: [PATCH 1784/4345] wifi: brcmfmac: Fix potential stack-out-of-bounds in brcmf_c_preinit_dcmds() [ Upstream commit 0a06cadcc2a0044e4a117cc0e61436fc3a0dad69 ] This patch fixes a stack-out-of-bounds read in brcmfmac that occurs when 'buf' that is not null-terminated is passed as an argument of strsep() in brcmf_c_preinit_dcmds(). This buffer is filled with a firmware version string by memcpy() in brcmf_fil_iovar_data_get(). The patch ensures buf is null-terminated. Found by a modified version of syzkaller. [ 47.569679][ T1897] brcmfmac: brcmf_fw_alloc_request: using brcm/brcmfmac43236b for chip BCM43236/3 [ 47.582839][ T1897] brcmfmac: brcmf_c_process_clm_blob: no clm_blob available (err=-2), device may have limited channels available [ 47.601565][ T1897] ================================================================== [ 47.602574][ T1897] BUG: KASAN: stack-out-of-bounds in strsep+0x1b2/0x1f0 [ 47.603447][ T1897] Read of size 1 at addr ffffc90001f6f000 by task kworker/0:2/1897 [ 47.604336][ T1897] [ 47.604621][ T1897] CPU: 0 PID: 1897 Comm: kworker/0:2 Tainted: G O 5.14.0+ #131 [ 47.605617][ T1897] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 [ 47.606907][ T1897] Workqueue: usb_hub_wq hub_event [ 47.607453][ T1897] Call Trace: [ 47.607801][ T1897] dump_stack_lvl+0x8e/0xd1 [ 47.608295][ T1897] print_address_description.constprop.0.cold+0xf/0x334 [ 47.609009][ T1897] ? strsep+0x1b2/0x1f0 [ 47.609434][ T1897] ? strsep+0x1b2/0x1f0 [ 47.609863][ T1897] kasan_report.cold+0x83/0xdf [ 47.610366][ T1897] ? strsep+0x1b2/0x1f0 [ 47.610882][ T1897] strsep+0x1b2/0x1f0 [ 47.611300][ T1897] ? brcmf_fil_iovar_data_get+0x3a/0xf0 [ 47.611883][ T1897] brcmf_c_preinit_dcmds+0x995/0xc40 [ 47.612434][ T1897] ? brcmf_c_set_joinpref_default+0x100/0x100 [ 47.613078][ T1897] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 47.613662][ T1897] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 47.614208][ T1897] ? lock_acquire+0x19d/0x4e0 [ 47.614704][ T1897] ? find_held_lock+0x2d/0x110 [ 47.615236][ T1897] ? brcmf_usb_deq+0x1a7/0x260 [ 47.615741][ T1897] ? brcmf_usb_rx_fill_all+0x5a/0xf0 [ 47.616288][ T1897] brcmf_attach+0x246/0xd40 [ 47.616758][ T1897] ? wiphy_new_nm+0x1703/0x1dd0 [ 47.617280][ T1897] ? kmemdup+0x43/0x50 [ 47.617720][ T1897] brcmf_usb_probe+0x12de/0x1690 [ 47.618244][ T1897] ? brcmf_usbdev_qinit.constprop.0+0x470/0x470 [ 47.618901][ T1897] usb_probe_interface+0x2aa/0x760 [ 47.619429][ T1897] ? usb_probe_device+0x250/0x250 [ 47.619950][ T1897] really_probe+0x205/0xb70 [ 47.620435][ T1897] ? driver_allows_async_probing+0x130/0x130 [ 47.621048][ T1897] __driver_probe_device+0x311/0x4b0 [ 47.621595][ T1897] ? driver_allows_async_probing+0x130/0x130 [ 47.622209][ T1897] driver_probe_device+0x4e/0x150 [ 47.622739][ T1897] __device_attach_driver+0x1cc/0x2a0 [ 47.623287][ T1897] bus_for_each_drv+0x156/0x1d0 [ 47.623796][ T1897] ? bus_rescan_devices+0x30/0x30 [ 47.624309][ T1897] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 47.624907][ T1897] ? trace_hardirqs_on+0x46/0x160 [ 47.625437][ T1897] __device_attach+0x23f/0x3a0 [ 47.625924][ T1897] ? device_bind_driver+0xd0/0xd0 [ 47.626433][ T1897] ? kobject_uevent_env+0x287/0x14b0 [ 47.627057][ T1897] bus_probe_device+0x1da/0x290 [ 47.627557][ T1897] device_add+0xb7b/0x1eb0 [ 47.628027][ T1897] ? wait_for_completion+0x290/0x290 [ 47.628593][ T1897] ? __fw_devlink_link_to_suppliers+0x5a0/0x5a0 [ 47.629249][ T1897] usb_set_configuration+0xf59/0x16f0 [ 47.629829][ T1897] usb_generic_driver_probe+0x82/0xa0 [ 47.630385][ T1897] usb_probe_device+0xbb/0x250 [ 47.630927][ T1897] ? usb_suspend+0x590/0x590 [ 47.631397][ T1897] really_probe+0x205/0xb70 [ 47.631855][ T1897] ? driver_allows_async_probing+0x130/0x130 [ 47.632469][ T1897] __driver_probe_device+0x311/0x4b0 [ 47.633002][ T1897] ? usb_generic_driver_match+0x75/0x90 [ 47.633573][ T1897] ? driver_allows_async_probing+0x130/0x130 [ 47.634170][ T1897] driver_probe_device+0x4e/0x150 [ 47.634703][ T1897] __device_attach_driver+0x1cc/0x2a0 [ 47.635248][ T1897] bus_for_each_drv+0x156/0x1d0 [ 47.635748][ T1897] ? bus_rescan_devices+0x30/0x30 [ 47.636271][ T1897] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 47.636881][ T1897] ? trace_hardirqs_on+0x46/0x160 [ 47.637396][ T1897] __device_attach+0x23f/0x3a0 [ 47.637904][ T1897] ? device_bind_driver+0xd0/0xd0 [ 47.638426][ T1897] ? kobject_uevent_env+0x287/0x14b0 [ 47.638985][ T1897] bus_probe_device+0x1da/0x290 [ 47.639512][ T1897] device_add+0xb7b/0x1eb0 [ 47.639977][ T1897] ? __fw_devlink_link_to_suppliers+0x5a0/0x5a0 [ 47.640612][ T1897] ? kfree+0x14a/0x6b0 [ 47.641055][ T1897] ? __usb_get_extra_descriptor+0x116/0x160 [ 47.641679][ T1897] usb_new_device.cold+0x49c/0x1029 [ 47.642245][ T1897] ? hub_disconnect+0x450/0x450 [ 47.642756][ T1897] ? rwlock_bug.part.0+0x90/0x90 [ 47.643273][ T1897] ? _raw_spin_unlock_irq+0x24/0x30 [ 47.643822][ T1897] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 47.644445][ T1897] hub_event+0x1c98/0x3950 [ 47.644939][ T1897] ? hub_port_debounce+0x2e0/0x2e0 [ 47.645467][ T1897] ? check_irq_usage+0x861/0xf20 [ 47.645975][ T1897] ? drain_workqueue+0x280/0x360 [ 47.646506][ T1897] ? lock_release+0x640/0x640 [ 47.646994][ T1897] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 47.647572][ T1897] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 47.648111][ T1897] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 47.648735][ T1897] process_one_work+0x92b/0x1460 [ 47.649262][ T1897] ? pwq_dec_nr_in_flight+0x330/0x330 [ 47.649816][ T1897] ? rwlock_bug.part.0+0x90/0x90 [ 47.650336][ T1897] worker_thread+0x95/0xe00 [ 47.650830][ T1897] ? __kthread_parkme+0x115/0x1e0 [ 47.651361][ T1897] ? process_one_work+0x1460/0x1460 [ 47.651904][ T1897] kthread+0x3a1/0x480 [ 47.652329][ T1897] ? set_kthread_struct+0x120/0x120 [ 47.652878][ T1897] ret_from_fork+0x1f/0x30 [ 47.653370][ T1897] [ 47.653608][ T1897] [ 47.653848][ T1897] addr ffffc90001f6f000 is located in stack of task kworker/0:2/1897 at offset 512 in frame: [ 47.654891][ T1897] brcmf_c_preinit_dcmds+0x0/0xc40 [ 47.655442][ T1897] [ 47.655690][ T1897] this frame has 4 objects: [ 47.656151][ T1897] [48, 56) 'ptr' [ 47.656159][ T1897] [80, 148) 'revinfo' [ 47.656534][ T1897] [192, 210) 'eventmask' [ 47.656953][ T1897] [256, 512) 'buf' [ 47.657410][ T1897] [ 47.658035][ T1897] Memory state around the buggy address: [ 47.658743][ T1897] ffffc90001f6ef00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 47.659577][ T1897] ffffc90001f6ef80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 47.660394][ T1897] >ffffc90001f6f000: f3 f3 f3 f3 f3 f3 f3 f3 00 00 00 00 00 00 00 00 [ 47.661199][ T1897] ^ [ 47.661625][ T1897] ffffc90001f6f080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 47.662455][ T1897] ffffc90001f6f100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 f1 f1 [ 47.663318][ T1897] ================================================================== [ 47.664147][ T1897] Disabling lock debugging due to kernel taint Reported-by: Dokyung Song Reported-by: Jisoo Jang Reported-by: Minsuk Kang Signed-off-by: Jisoo Jang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221115043458.37562-1-jisoo.jang@yonsei.ac.kr Signed-off-by: Sasha Levin --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c index e3758bd86acf..57bb1fbedaa8 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c @@ -264,6 +264,7 @@ int brcmf_c_preinit_dcmds(struct brcmf_if *ifp) err); goto done; } + buf[sizeof(buf) - 1] = '\0'; ptr = (char *)buf; strsep(&ptr, "\n"); From f5657f3306031d4ee338d1a91ea5115f0f9c7af7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 14 Dec 2022 11:41:44 -0800 Subject: [PATCH 1785/4345] rcu: Make RCU_LOCKDEP_WARN() avoid early lockdep checks [ Upstream commit 0cae5ded535c3a80aed94f119bbd4ee3ae284a65 ] Currently, RCU_LOCKDEP_WARN() checks the condition before checking to see if lockdep is still enabled. This is necessary to avoid the false-positive splats fixed by commit 3066820034b5dd ("rcu: Reject RCU_LOCKDEP_WARN() false positives"). However, the current state can result in false-positive splats during early boot before lockdep is fully initialized. This commit therefore checks debug_lockdep_rcu_enabled() both before and after checking the condition, thus avoiding both sets of false-positive error reports. Reported-by: Steven Rostedt Reported-by: Masami Hiramatsu (Google) Reported-by: Mathieu Desnoyers Signed-off-by: Paul E. McKenney Reviewed-by: Mathieu Desnoyers Cc: Boqun Feng Cc: Matthew Wilcox Cc: Thomas Gleixner Signed-off-by: Sasha Levin --- include/linux/rcupdate.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 1f46db38d6ec..ef8d56b18da6 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -308,11 +308,18 @@ static inline int rcu_read_lock_any_held(void) * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message + * + * This checks debug_lockdep_rcu_enabled() before checking (c) to + * prevent early boot splats due to lockdep not yet being initialized, + * and rechecks it after checking (c) to prevent false-positive splats + * due to races with lockdep being disabled. See commit 3066820034b5dd + * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data.unlikely") __warned; \ - if ((c) && debug_lockdep_rcu_enabled() && !__warned) { \ + if (debug_lockdep_rcu_enabled() && (c) && \ + debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ From 2bf501f1bc78883222bba17aad9402deae11ef1e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 16 Dec 2022 15:55:48 -0800 Subject: [PATCH 1786/4345] rcu: Suppress smp_processor_id() complaint in synchronize_rcu_expedited_wait() [ Upstream commit 2d7f00b2f01301d6e41fd4a28030dab0442265be ] The normal grace period's RCU CPU stall warnings are invoked from the scheduling-clock interrupt handler, and can thus invoke smp_processor_id() with impunity, which allows them to directly invoke dump_cpu_task(). In contrast, the expedited grace period's RCU CPU stall warnings are invoked from process context, which causes the dump_cpu_task() function's calls to smp_processor_id() to complain bitterly in debug kernels. This commit therefore causes synchronize_rcu_expedited_wait() to disable preemption around its call to dump_cpu_task(). Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- kernel/rcu/tree_exp.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 0dc16345e668..ef6570137dcd 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -564,7 +564,9 @@ static void synchronize_rcu_expedited_wait(void) mask = leaf_node_cpu_bit(rnp, cpu); if (!(READ_ONCE(rnp->expmask) & mask)) continue; + preempt_disable(); // For smp_processor_id() in dump_cpu_task(). dump_cpu_task(cpu); + preempt_enable(); } } jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3; From d99d194e2f8c7809ebf8b27f345b6ce9a87c17bd Mon Sep 17 00:00:00 2001 From: Zqiang Date: Thu, 1 Dec 2022 07:45:33 +0800 Subject: [PATCH 1787/4345] rcu-tasks: Make rude RCU-Tasks work well with CPU hotplug [ Upstream commit ea5c8987fef20a8cca07e428aa28bc64649c5104 ] The synchronize_rcu_tasks_rude() function invokes rcu_tasks_rude_wait_gp() to wait one rude RCU-tasks grace period. The rcu_tasks_rude_wait_gp() function in turn checks if there is only a single online CPU. If so, it will immediately return, because a call to synchronize_rcu_tasks_rude() is by definition a grace period on a single-CPU system. (We could have blocked!) Unfortunately, this check uses num_online_cpus() without synchronization, which can result in too-short grace periods. To see this, consider the following scenario: CPU0 CPU1 (going offline) migration/1 task: cpu_stopper_thread -> take_cpu_down -> _cpu_disable (dec __num_online_cpus) ->cpuhp_invoke_callback preempt_disable access old_data0 task1 del old_data0 ..... synchronize_rcu_tasks_rude() task1 schedule out .... task2 schedule in rcu_tasks_rude_wait_gp() ->__num_online_cpus == 1 ->return .... task1 schedule in ->free old_data0 preempt_enable When CPU1 decrements __num_online_cpus, its value becomes 1. However, CPU1 has not finished going offline, and will take one last trip through the scheduler and the idle loop before it actually stops executing instructions. Because synchronize_rcu_tasks_rude() is mostly used for tracing, and because both the scheduler and the idle loop can be traced, this means that CPU0's prematurely ended grace period might disrupt the tracing on CPU1. Given that this disruption might include CPU1 executing instructions in memory that was just now freed (and maybe reallocated), this is a matter of some concern. This commit therefore removes that problematic single-CPU check from the rcu_tasks_rude_wait_gp() function. This dispenses with the single-CPU optimization, but there is no evidence indicating that this optimization is important. In addition, synchronize_rcu_tasks_generic() contains a similar optimization (albeit only for early boot), which also splats. (As in exactly why are you invoking synchronize_rcu_tasks_rude() so early in boot, anyway???) It is OK for the synchronize_rcu_tasks_rude() function's check to be unsynchronized because the only times that this check can evaluate to true is when there is only a single CPU running with preemption disabled. While in the area, this commit also fixes a minor bug in which a call to synchronize_rcu_tasks_rude() would instead be attributed to synchronize_rcu_tasks(). [ paulmck: Add "synchronize_" prefix and "()" suffix. ] Signed-off-by: Zqiang Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- kernel/rcu/tasks.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index df8143c8a6a8..c66d47685b28 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -171,8 +171,9 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp) { /* Complain if the scheduler has not started. */ - WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE, - "synchronize_rcu_tasks called too soon"); + if (WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE, + "synchronize_%s() called too soon", rtp->name)) + return; /* Wait for the grace period. */ wait_rcu_gp(rtp->call_func); @@ -648,9 +649,6 @@ static void rcu_tasks_be_rude(struct work_struct *work) // Wait for one rude RCU-tasks grace period. static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp) { - if (num_online_cpus() <= 1) - return; // Fastpath for only one CPU. - rtp->n_ipis += cpumask_weight(cpu_online_mask); schedule_on_each_cpu(rcu_tasks_be_rude); } From 744e538dcf27f06b44a4f50eb45c0f2417747d18 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Thu, 22 Dec 2022 19:15:59 +0200 Subject: [PATCH 1788/4345] wifi: ath11k: debugfs: fix to work with multiple PCI devices [ Upstream commit 323d91d4684d238f6bc3693fed93caf795378fe0 ] ath11k fails to load if there are multiple ath11k PCI devices with same name: ath11k_pci 0000:01:00.0: Hardware name qcn9074 hw1.0 debugfs: Directory 'ath11k' with parent '/' already present! ath11k_pci 0000:01:00.0: failed to create ath11k debugfs ath11k_pci 0000:01:00.0: failed to create soc core: -17 ath11k_pci 0000:01:00.0: failed to init core: -17 ath11k_pci: probe of 0000:01:00.0 failed with error -17 Fix this by creating a directory for each ath11k device using schema -, for example "pci-0000:06:00.0". This directory created under the top-level ath11k directory, for example /sys/kernel/debug/ath11k. The reference to the toplevel ath11k directory is not stored anymore within ath11k, instead it's retrieved using debugfs_lookup(). If the directory does not exist it will be created. After the last directory from the ath11k directory is removed, for example when doing rmmod ath11k, the empty ath11k directory is left in place, it's a minor cosmetic issue anyway. Here's an example hierarchy with one WCN6855: ath11k `-- pci-0000:06:00.0 |-- mac0 | |-- dfs_block_radar_events | |-- dfs_simulate_radar | |-- ext_rx_stats | |-- ext_tx_stats | |-- fw_dbglog_config | |-- fw_stats | | |-- beacon_stats | | |-- pdev_stats | | `-- vdev_stats | |-- htt_stats | |-- htt_stats_reset | |-- htt_stats_type | `-- pktlog_filter |-- simulate_fw_crash `-- soc_dp_stats I didn't have a test setup where I could connect multiple ath11k devices to the same the host, so I have only tested this with one device. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.9 Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.5.0.1-01208-QCAHKSWPL_SILICONZ-1 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.5.0.1-01208-QCAHKSWPL_SILICONZ-1 Tested-by: Robert Marko Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221220121231.20120-1-kvalo@kernel.org Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/core.h | 1 - drivers/net/wireless/ath/ath11k/debugfs.c | 48 +++++++++++++++++++---- 2 files changed, 40 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index d2f2898d17b4..a66e275af1eb 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -712,7 +712,6 @@ struct ath11k_base { enum ath11k_dfs_region dfs_region; #ifdef CONFIG_ATH11K_DEBUGFS struct dentry *debugfs_soc; - struct dentry *debugfs_ath11k; #endif struct ath11k_soc_dp_stats soc_stats; diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c index 1b914e67d314..196314ab4ff0 100644 --- a/drivers/net/wireless/ath/ath11k/debugfs.c +++ b/drivers/net/wireless/ath/ath11k/debugfs.c @@ -836,10 +836,6 @@ int ath11k_debugfs_pdev_create(struct ath11k_base *ab) if (test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags)) return 0; - ab->debugfs_soc = debugfs_create_dir(ab->hw_params.name, ab->debugfs_ath11k); - if (IS_ERR(ab->debugfs_soc)) - return PTR_ERR(ab->debugfs_soc); - debugfs_create_file("simulate_fw_crash", 0600, ab->debugfs_soc, ab, &fops_simulate_fw_crash); @@ -857,15 +853,51 @@ void ath11k_debugfs_pdev_destroy(struct ath11k_base *ab) int ath11k_debugfs_soc_create(struct ath11k_base *ab) { - ab->debugfs_ath11k = debugfs_create_dir("ath11k", NULL); + struct dentry *root; + bool dput_needed; + char name[64]; + int ret; - return PTR_ERR_OR_ZERO(ab->debugfs_ath11k); + root = debugfs_lookup("ath11k", NULL); + if (!root) { + root = debugfs_create_dir("ath11k", NULL); + if (IS_ERR_OR_NULL(root)) + return PTR_ERR(root); + + dput_needed = false; + } else { + /* a dentry from lookup() needs dput() after we don't use it */ + dput_needed = true; + } + + scnprintf(name, sizeof(name), "%s-%s", ath11k_bus_str(ab->hif.bus), + dev_name(ab->dev)); + + ab->debugfs_soc = debugfs_create_dir(name, root); + if (IS_ERR_OR_NULL(ab->debugfs_soc)) { + ret = PTR_ERR(ab->debugfs_soc); + goto out; + } + + ret = 0; + +out: + if (dput_needed) + dput(root); + + return ret; } void ath11k_debugfs_soc_destroy(struct ath11k_base *ab) { - debugfs_remove_recursive(ab->debugfs_ath11k); - ab->debugfs_ath11k = NULL; + debugfs_remove_recursive(ab->debugfs_soc); + ab->debugfs_soc = NULL; + + /* We are not removing ath11k directory on purpose, even if it + * would be empty. This simplifies the directory handling and it's + * a minor cosmetic issue to leave an empty ath11k directory to + * debugfs. + */ } void ath11k_debugfs_fw_stats_init(struct ath11k *ar) From 781bff0a532fd9590eff75cc99634d2e75ae6625 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 6 Jan 2023 08:59:51 +0800 Subject: [PATCH 1789/4345] thermal: intel: Fix unsigned comparison with less than zero [ Upstream commit e7fcfe67f9f410736b758969477b17ea285e8e6c ] The return value from the call to intel_tcc_get_tjmax() is int, which can be a negative error code. However, the return value is being assigned to an u32 variable 'tj_max', so making 'tj_max' an int. Eliminate the following warning: ./drivers/thermal/intel/intel_soc_dts_iosf.c:394:5-11: WARNING: Unsigned expression compared with zero: tj_max < 0 Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=3637 Reported-by: Abaci Robot Signed-off-by: Yang Li Acked-by: Zhang Rui Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/thermal/intel/intel_soc_dts_iosf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/intel/intel_soc_dts_iosf.c b/drivers/thermal/intel/intel_soc_dts_iosf.c index 4f1a2f7c016c..8d6707e48d02 100644 --- a/drivers/thermal/intel/intel_soc_dts_iosf.c +++ b/drivers/thermal/intel/intel_soc_dts_iosf.c @@ -404,7 +404,7 @@ struct intel_soc_dts_sensors *intel_soc_dts_iosf_init( { struct intel_soc_dts_sensors *sensors; bool notification; - u32 tj_max; + int tj_max; int ret; int i; From 6ef02cdb5a304cd06eba6724975b5d9d2991afad Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 5 Jan 2023 14:44:03 +0100 Subject: [PATCH 1790/4345] timers: Prevent union confusion from unexpected restart_syscall() [ Upstream commit 9f76d59173d9d146e96c66886b671c1915a5c5e5 ] The nanosleep syscalls use the restart_block mechanism, with a quirk: The `type` and `rmtp`/`compat_rmtp` fields are set up unconditionally on syscall entry, while the rest of the restart_block is only set up in the unlikely case that the syscall is actually interrupted by a signal (or pseudo-signal) that doesn't have a signal handler. If the restart_block was set up by a previous syscall (futex(..., FUTEX_WAIT, ...) or poll()) and hasn't been invalidated somehow since then, this will clobber some of the union fields used by futex_wait_restart() and do_restart_poll(). If userspace afterwards wrongly calls the restart_syscall syscall, futex_wait_restart()/do_restart_poll() will read struct fields that have been clobbered. This doesn't actually lead to anything particularly interesting because none of the union fields contain trusted kernel data, and futex(..., FUTEX_WAIT, ...) and poll() aren't syscalls where it makes much sense to apply seccomp filters to their arguments. So the current consequences are just of the "if userspace does bad stuff, it can damage itself, and that's not a problem" flavor. But still, it seems like a hazard for future developers, so invalidate the restart_block when partly setting it up in the nanosleep syscalls. Signed-off-by: Jann Horn Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230105134403.754986-1-jannh@google.com Signed-off-by: Sasha Levin --- kernel/time/hrtimer.c | 2 ++ kernel/time/posix-stubs.c | 2 ++ kernel/time/posix-timers.c | 2 ++ 3 files changed, 6 insertions(+) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 544ce87ba38a..70deb2f01e97 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -2024,6 +2024,7 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, if (!timespec64_valid(&tu)) return -EINVAL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, @@ -2045,6 +2046,7 @@ SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, if (!timespec64_valid(&tu)) return -EINVAL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index fcb3b21d8bdc..3783d07d60ba 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -146,6 +146,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; texp = timespec64_to_ktime(t); @@ -239,6 +240,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; texp = timespec64_to_ktime(t); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index b624788023d8..724ca7eb1a6e 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1270,6 +1270,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; @@ -1297,6 +1298,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; From 4707c94f7f89da7fa656df38d890d9d6a32bd0e0 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 28 Nov 2022 07:31:48 -0800 Subject: [PATCH 1791/4345] x86/bugs: Reset speculation control settings on init [ Upstream commit 0125acda7d76b943ca55811df40ed6ec0ecf670f ] Currently, x86_spec_ctrl_base is read at boot time and speculative bits are set if Kconfig items are enabled. For example, IBRS is enabled if CONFIG_CPU_IBRS_ENTRY is configured, etc. These MSR bits are not cleared if the mitigations are disabled. This is a problem when kexec-ing a kernel that has the mitigation disabled from a kernel that has the mitigation enabled. In this case, the MSR bits are not cleared during the new kernel boot. As a result, this might have some performance degradation that is hard to pinpoint. This problem does not happen if the machine is (hard) rebooted because the bit will be cleared by default. [ bp: Massage. ] Suggested-by: Pawan Gupta Signed-off-by: Breno Leitao Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20221128153148.1129350-1-leitao@debian.org Signed-off-by: Sasha Levin --- arch/x86/include/asm/msr-index.h | 4 ++++ arch/x86/kernel/cpu/bugs.c | 10 +++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 5a8ee3b83af2..f71a177b6b18 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -54,6 +54,10 @@ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +/* A mask for bits which the kernel toggles when controlling mitigations */ +#define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ + | SPEC_CTRL_RRSBA_DIS_S) + #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index a2a087a797ae..c5034986ea44 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -136,9 +136,17 @@ void __init check_bugs(void) * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD * init code as it is not enumerated and depends on the family. */ - if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + if (cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) { rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + /* + * Previously running kernel (kexec), may have some controls + * turned ON. Clear them and let the mitigations setup below + * rediscover them based on configuration. + */ + x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK; + } + /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); From 0ca2efea4f11c6255061e852ac188264c469c197 Mon Sep 17 00:00:00 2001 From: Jisoo Jang Date: Fri, 30 Dec 2022 16:51:39 +0900 Subject: [PATCH 1792/4345] wifi: brcmfmac: ensure CLM version is null-terminated to prevent stack-out-of-bounds [ Upstream commit 660145d708be52f946a82e5b633c020f58f996de ] Fix a stack-out-of-bounds read in brcmfmac that occurs when 'buf' that is not null-terminated is passed as an argument of strreplace() in brcmf_c_preinit_dcmds(). This buffer is filled with a CLM version string by memcpy() in brcmf_fil_iovar_data_get(). Ensure buf is null-terminated. Found by a modified version of syzkaller. [ 33.004414][ T1896] brcmfmac: brcmf_c_process_clm_blob: no clm_blob available (err=-2), device may have limited channels available [ 33.013486][ T1896] brcmfmac: brcmf_c_preinit_dcmds: Firmware: BCM43236/3 wl0: Nov 30 2011 17:33:42 version 5.90.188.22 [ 33.021554][ T1896] ================================================================== [ 33.022379][ T1896] BUG: KASAN: stack-out-of-bounds in strreplace+0xf2/0x110 [ 33.023122][ T1896] Read of size 1 at addr ffffc90001d6efc8 by task kworker/0:2/1896 [ 33.023852][ T1896] [ 33.024096][ T1896] CPU: 0 PID: 1896 Comm: kworker/0:2 Tainted: G O 5.14.0+ #132 [ 33.024927][ T1896] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 [ 33.026065][ T1896] Workqueue: usb_hub_wq hub_event [ 33.026581][ T1896] Call Trace: [ 33.026896][ T1896] dump_stack_lvl+0x57/0x7d [ 33.027372][ T1896] print_address_description.constprop.0.cold+0xf/0x334 [ 33.028037][ T1896] ? strreplace+0xf2/0x110 [ 33.028403][ T1896] ? strreplace+0xf2/0x110 [ 33.028807][ T1896] kasan_report.cold+0x83/0xdf [ 33.029283][ T1896] ? strreplace+0xf2/0x110 [ 33.029666][ T1896] strreplace+0xf2/0x110 [ 33.029966][ T1896] brcmf_c_preinit_dcmds+0xab1/0xc40 [ 33.030351][ T1896] ? brcmf_c_set_joinpref_default+0x100/0x100 [ 33.030787][ T1896] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 33.031223][ T1896] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 33.031661][ T1896] ? lock_acquire+0x19d/0x4e0 [ 33.032091][ T1896] ? find_held_lock+0x2d/0x110 [ 33.032605][ T1896] ? brcmf_usb_deq+0x1a7/0x260 [ 33.033087][ T1896] ? brcmf_usb_rx_fill_all+0x5a/0xf0 [ 33.033582][ T1896] brcmf_attach+0x246/0xd40 [ 33.034022][ T1896] ? wiphy_new_nm+0x1476/0x1d50 [ 33.034383][ T1896] ? kmemdup+0x30/0x40 [ 33.034722][ T1896] brcmf_usb_probe+0x12de/0x1690 [ 33.035223][ T1896] ? brcmf_usbdev_qinit.constprop.0+0x470/0x470 [ 33.035833][ T1896] usb_probe_interface+0x25f/0x710 [ 33.036315][ T1896] really_probe+0x1be/0xa90 [ 33.036656][ T1896] __driver_probe_device+0x2ab/0x460 [ 33.037026][ T1896] ? usb_match_id.part.0+0x88/0xc0 [ 33.037383][ T1896] driver_probe_device+0x49/0x120 [ 33.037790][ T1896] __device_attach_driver+0x18a/0x250 [ 33.038300][ T1896] ? driver_allows_async_probing+0x120/0x120 [ 33.038986][ T1896] bus_for_each_drv+0x123/0x1a0 [ 33.039906][ T1896] ? bus_rescan_devices+0x20/0x20 [ 33.041412][ T1896] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 33.041861][ T1896] ? trace_hardirqs_on+0x1c/0x120 [ 33.042330][ T1896] __device_attach+0x207/0x330 [ 33.042664][ T1896] ? device_bind_driver+0xb0/0xb0 [ 33.043026][ T1896] ? kobject_uevent_env+0x230/0x12c0 [ 33.043515][ T1896] bus_probe_device+0x1a2/0x260 [ 33.043914][ T1896] device_add+0xa61/0x1ce0 [ 33.044227][ T1896] ? __mutex_unlock_slowpath+0xe7/0x660 [ 33.044891][ T1896] ? __fw_devlink_link_to_suppliers+0x550/0x550 [ 33.045531][ T1896] usb_set_configuration+0x984/0x1770 [ 33.046051][ T1896] ? kernfs_create_link+0x175/0x230 [ 33.046548][ T1896] usb_generic_driver_probe+0x69/0x90 [ 33.046931][ T1896] usb_probe_device+0x9c/0x220 [ 33.047434][ T1896] really_probe+0x1be/0xa90 [ 33.047760][ T1896] __driver_probe_device+0x2ab/0x460 [ 33.048134][ T1896] driver_probe_device+0x49/0x120 [ 33.048516][ T1896] __device_attach_driver+0x18a/0x250 [ 33.048910][ T1896] ? driver_allows_async_probing+0x120/0x120 [ 33.049437][ T1896] bus_for_each_drv+0x123/0x1a0 [ 33.049814][ T1896] ? bus_rescan_devices+0x20/0x20 [ 33.050164][ T1896] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 33.050579][ T1896] ? trace_hardirqs_on+0x1c/0x120 [ 33.050936][ T1896] __device_attach+0x207/0x330 [ 33.051399][ T1896] ? device_bind_driver+0xb0/0xb0 [ 33.051888][ T1896] ? kobject_uevent_env+0x230/0x12c0 [ 33.052314][ T1896] bus_probe_device+0x1a2/0x260 [ 33.052688][ T1896] device_add+0xa61/0x1ce0 [ 33.053121][ T1896] ? __fw_devlink_link_to_suppliers+0x550/0x550 [ 33.053568][ T1896] usb_new_device.cold+0x463/0xf66 [ 33.053953][ T1896] ? hub_disconnect+0x400/0x400 [ 33.054313][ T1896] ? rwlock_bug.part.0+0x90/0x90 [ 33.054661][ T1896] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 33.055094][ T1896] hub_event+0x10d5/0x3330 [ 33.055530][ T1896] ? hub_port_debounce+0x280/0x280 [ 33.055934][ T1896] ? __lock_acquire+0x1671/0x5790 [ 33.056387][ T1896] ? wq_calc_node_cpumask+0x170/0x2a0 [ 33.056924][ T1896] ? lock_release+0x640/0x640 [ 33.057383][ T1896] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 33.057916][ T1896] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 33.058402][ T1896] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 33.059019][ T1896] process_one_work+0x873/0x13e0 [ 33.059488][ T1896] ? lock_release+0x640/0x640 [ 33.059932][ T1896] ? pwq_dec_nr_in_flight+0x320/0x320 [ 33.060446][ T1896] ? rwlock_bug.part.0+0x90/0x90 [ 33.060898][ T1896] worker_thread+0x8b/0xd10 [ 33.061348][ T1896] ? __kthread_parkme+0xd9/0x1d0 [ 33.061810][ T1896] ? process_one_work+0x13e0/0x13e0 [ 33.062288][ T1896] kthread+0x379/0x450 [ 33.062660][ T1896] ? _raw_spin_unlock_irq+0x24/0x30 [ 33.063148][ T1896] ? set_kthread_struct+0x100/0x100 [ 33.063606][ T1896] ret_from_fork+0x1f/0x30 [ 33.064070][ T1896] [ 33.064313][ T1896] [ 33.064545][ T1896] addr ffffc90001d6efc8 is located in stack of task kworker/0:2/1896 at offset 512 in frame: [ 33.065478][ T1896] brcmf_c_preinit_dcmds+0x0/0xc40 [ 33.065973][ T1896] [ 33.066191][ T1896] this frame has 4 objects: [ 33.066614][ T1896] [48, 56) 'ptr' [ 33.066618][ T1896] [80, 148) 'revinfo' [ 33.066957][ T1896] [192, 210) 'eventmask' [ 33.067338][ T1896] [256, 512) 'buf' [ 33.067742][ T1896] [ 33.068304][ T1896] Memory state around the buggy address: [ 33.068838][ T1896] ffffc90001d6ee80: f2 00 00 02 f2 f2 f2 f2 f2 00 00 00 00 00 00 00 [ 33.069545][ T1896] ffffc90001d6ef00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 33.070626][ T1896] >ffffc90001d6ef80: 00 00 00 00 00 00 00 00 00 f3 f3 f3 f3 f3 f3 f3 [ 33.072052][ T1896] ^ [ 33.073043][ T1896] ffffc90001d6f000: f3 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 33.074230][ T1896] ffffc90001d6f080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 33.074914][ T1896] ================================================================== [ 33.075713][ T1896] Disabling lock debugging due to kernel taint Reviewed-by: Arend van Spriel Signed-off-by: Jisoo Jang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221230075139.56591-1-jisoo.jang@yonsei.ac.kr Signed-off-by: Sasha Levin --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c index 57bb1fbedaa8..f29de630908d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c @@ -281,15 +281,17 @@ int brcmf_c_preinit_dcmds(struct brcmf_if *ifp) if (err) { brcmf_dbg(TRACE, "retrieving clmver failed, %d\n", err); } else { + buf[sizeof(buf) - 1] = '\0'; clmver = (char *)buf; - /* store CLM version for adding it to revinfo debugfs file */ - memcpy(ifp->drvr->clmver, clmver, sizeof(ifp->drvr->clmver)); /* Replace all newline/linefeed characters with space * character */ strreplace(clmver, '\n', ' '); + /* store CLM version for adding it to revinfo debugfs file */ + memcpy(ifp->drvr->clmver, clmver, sizeof(ifp->drvr->clmver)); + brcmf_dbg(INFO, "CLM version = %s\n", clmver); } From 47dc1f425af57b71111d7b01ebd24e04e8d967ef Mon Sep 17 00:00:00 2001 From: Jisoo Jang Date: Thu, 29 Dec 2022 18:29:06 +0900 Subject: [PATCH 1793/4345] wifi: mt7601u: fix an integer underflow [ Upstream commit 803f3176c5df3b5582c27ea690f204abb60b19b9 ] Fix an integer underflow that leads to a null pointer dereference in 'mt7601u_rx_skb_from_seg()'. The variable 'dma_len' in the URB packet could be manipulated, which could trigger an integer underflow of 'seg_len' in 'mt7601u_rx_process_seg()'. This underflow subsequently causes the 'bad_frame' checks in 'mt7601u_rx_skb_from_seg()' to be bypassed, eventually leading to a dereference of the pointer 'p', which is a null pointer. Ensure that 'dma_len' is greater than 'min_seg_len'. Found by a modified version of syzkaller. KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 0 PID: 12 Comm: ksoftirqd/0 Tainted: G W O 5.14.0+ #139 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 RIP: 0010:skb_add_rx_frag+0x143/0x370 Code: e2 07 83 c2 03 38 ca 7c 08 84 c9 0f 85 86 01 00 00 4c 8d 7d 08 44 89 68 08 48 b8 00 00 00 00 00 fc ff df 4c 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 cd 01 00 00 48 8b 45 08 a8 01 0f 85 3d 01 00 00 RSP: 0018:ffffc900000cfc90 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff888115520dc0 RCX: 0000000000000000 RDX: 0000000000000001 RSI: ffff8881118430c0 RDI: ffff8881118430f8 RBP: 0000000000000000 R08: 0000000000000e09 R09: 0000000000000010 R10: ffff888111843017 R11: ffffed1022308602 R12: 0000000000000000 R13: 0000000000000e09 R14: 0000000000000010 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff88811a800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000004035af40 CR3: 00000001157f2000 CR4: 0000000000750ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: mt7601u_rx_tasklet+0xc73/0x1270 ? mt7601u_submit_rx_buf.isra.0+0x510/0x510 ? tasklet_action_common.isra.0+0x79/0x2f0 tasklet_action_common.isra.0+0x206/0x2f0 __do_softirq+0x1b5/0x880 ? tasklet_unlock+0x30/0x30 run_ksoftirqd+0x26/0x50 smpboot_thread_fn+0x34f/0x7d0 ? smpboot_register_percpu_thread+0x370/0x370 kthread+0x3a1/0x480 ? set_kthread_struct+0x120/0x120 ret_from_fork+0x1f/0x30 Modules linked in: 88XXau(O) 88x2bu(O) ---[ end trace 57f34f93b4da0f9b ]--- RIP: 0010:skb_add_rx_frag+0x143/0x370 Code: e2 07 83 c2 03 38 ca 7c 08 84 c9 0f 85 86 01 00 00 4c 8d 7d 08 44 89 68 08 48 b8 00 00 00 00 00 fc ff df 4c 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 cd 01 00 00 48 8b 45 08 a8 01 0f 85 3d 01 00 00 RSP: 0018:ffffc900000cfc90 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff888115520dc0 RCX: 0000000000000000 RDX: 0000000000000001 RSI: ffff8881118430c0 RDI: ffff8881118430f8 RBP: 0000000000000000 R08: 0000000000000e09 R09: 0000000000000010 R10: ffff888111843017 R11: ffffed1022308602 R12: 0000000000000000 R13: 0000000000000e09 R14: 0000000000000010 R15: 0000000000000008 FS: 0000000000000000(0000) GS:ffff88811a800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000004035af40 CR3: 00000001157f2000 CR4: 0000000000750ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Signed-off-by: Jisoo Jang Acked-by: Jakub Kicinski Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221229092906.2328282-1-jisoo.jang@yonsei.ac.kr Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt7601u/dma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt7601u/dma.c b/drivers/net/wireless/mediatek/mt7601u/dma.c index 11071519fce8..8ba291abecff 100644 --- a/drivers/net/wireless/mediatek/mt7601u/dma.c +++ b/drivers/net/wireless/mediatek/mt7601u/dma.c @@ -118,7 +118,8 @@ static u16 mt7601u_rx_next_seg_len(u8 *data, u32 data_len) if (data_len < min_seg_len || WARN_ON_ONCE(!dma_len) || WARN_ON_ONCE(dma_len + MT_DMA_HDRS > data_len) || - WARN_ON_ONCE(dma_len & 0x3)) + WARN_ON_ONCE(dma_len & 0x3) || + WARN_ON_ONCE(dma_len < min_seg_len)) return 0; return MT_DMA_HDRS + dma_len; From b33091fc28963deed329ccfce0d53f5323acf663 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sat, 14 Jan 2023 13:11:41 +0000 Subject: [PATCH 1794/4345] inet: fix fast path in __inet_hash_connect() [ Upstream commit 21cbd90a6fab7123905386985e3e4a80236b8714 ] __inet_hash_connect() has a fast path taken if sk_head(&tb->owners) is equal to the sk parameter. sk_head() returns the hlist_entry() with respect to the sk_node field. However entries in the tb->owners list are inserted with respect to the sk_bind_node field with sk_add_bind_node(). Thus the check would never pass and the fast path never execute. This fast path has never been executed or tested as this bug seems to be present since commit 1da177e4c3f4 ("Linux-2.6.12-rc2"), thus remove it to reduce code complexity. Signed-off-by: Pietro Borrello Reviewed-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230112-inet_hash_connect_bind_head-v3-1-b591fd212b93@diag.uniroma1.it Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/ipv4/inet_hashtables.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 2615b72118d1..79bf550c9dfc 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -760,17 +760,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, u32 index; if (port) { - head = &hinfo->bhash[inet_bhashfn(net, port, - hinfo->bhash_size)]; - tb = inet_csk(sk)->icsk_bind_hash; - spin_lock_bh(&head->lock); - if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - inet_ehash_nolisten(sk, NULL, NULL); - spin_unlock_bh(&head->lock); - return 0; - } - spin_unlock(&head->lock); - /* No definite answer... Walk to established hash table */ + local_bh_disable(); ret = check_established(death_row, sk, port, NULL); local_bh_enable(); return ret; From 9f1865ebfa7a81263746521c1dc1ed4346266d8b Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Tue, 13 Dec 2022 16:01:31 -0800 Subject: [PATCH 1795/4345] ice: add missing checks for PF vsi type [ Upstream commit 6a8d013e904ad9a66706fcc926ec9993bed7d190 ] There were a few places we had missed checking the VSI type to make sure it was definitely a PF VSI, before calling setup functions intended only for the PF VSI. This doesn't fix any explicit bugs but cleans up the code in a few places and removes one explicit != vsi->type check that can be superseded by this code (it's a super set) Signed-off-by: Jesse Brandeburg Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_main.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index c1465096239b..4f0d63fa5709 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5200,15 +5200,12 @@ int ice_vsi_cfg(struct ice_vsi *vsi) { int err; - if (vsi->netdev) { + if (vsi->netdev && vsi->type == ICE_VSI_PF) { ice_set_rx_mode(vsi->netdev); - if (vsi->type != ICE_VSI_LB) { - err = ice_vsi_vlan_setup(vsi); - - if (err) - return err; - } + err = ice_vsi_vlan_setup(vsi); + if (err) + return err; } ice_vsi_cfg_dcb_rings(vsi); @@ -5267,7 +5264,7 @@ static int ice_up_complete(struct ice_vsi *vsi) if (vsi->port_info && (vsi->port_info->phy.link_info.link_info & ICE_AQ_LINK_UP) && - vsi->netdev) { + vsi->netdev && vsi->type == ICE_VSI_PF) { ice_print_link_msg(vsi, true); netif_tx_start_all_queues(vsi->netdev); netif_carrier_on(vsi->netdev); @@ -5277,7 +5274,9 @@ static int ice_up_complete(struct ice_vsi *vsi) * set the baseline so counters are ready when interface is up */ ice_update_eth_stats(vsi); - ice_service_task_schedule(pf); + + if (vsi->type == ICE_VSI_PF) + ice_service_task_schedule(pf); return 0; } From 94933dab75d595fc4fd2389577d19fee3015729e Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 23 Jan 2023 13:45:58 +0000 Subject: [PATCH 1796/4345] ACPI: Don't build ACPICA with '-Os' [ Upstream commit 8f9e0a52810dd83406c768972d022c37e7a18f1f ] The ACPICA code has been built with '-Os' since the beginning of git history, though there's no explanatory comment as to why. This is unfortunate as GCC drops the alignment specificed by '-falign-functions=N' when '-Os' is used, as reported in GCC bug 88345: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345 This prevents CONFIG_FUNCTION_ALIGNMENT and CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B from having their expected effect on the ACPICA code. This is doubly unfortunate as in subsequent patches arm64 will depend upon CONFIG_FUNCTION_ALIGNMENT for its ftrace implementation. Drop the '-Os' flag when building the ACPICA code. With this removed, the code builds cleanly and works correctly in testing so far. I've tested this by selecting CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B=y, building and booting a kernel using ACPI, and looking for misaligned text symbols: * arm64: Before, v6.2-rc3: # uname -rm 6.2.0-rc3 aarch64 # grep ' [Tt] ' /proc/kallsyms | grep -iv '[048c]0 [Tt] ' | wc -l 5009 Before, v6.2-rc3 + fixed __cold: # uname -rm 6.2.0-rc3-00001-g2a2bedf8bfa9 aarch64 # grep ' [Tt] ' /proc/kallsyms | grep -iv '[048c]0 [Tt] ' | wc -l 919 After: # uname -rm 6.2.0-rc3-00002-g267bddc38572 aarch64 # grep ' [Tt] ' /proc/kallsyms | grep -iv '[048c]0 [Tt] ' | wc -l 323 # grep ' [Tt] ' /proc/kallsyms | grep -iv '[048c]0 [Tt] ' | grep acpi | wc -l 0 * x86_64: Before, v6.2-rc3: # uname -rm 6.2.0-rc3 x86_64 # grep ' [Tt] ' /proc/kallsyms | grep -iv '[048c]0 [Tt] ' | wc -l 11537 Before, v6.2-rc3 + fixed __cold: # uname -rm 6.2.0-rc3-00001-g2a2bedf8bfa9 x86_64 # grep ' [Tt] ' /proc/kallsyms | grep -iv '[048c]0 [Tt] ' | wc -l 2805 After: # uname -rm 6.2.0-rc3-00002-g267bddc38572 x86_64 # grep ' [Tt] ' /proc/kallsyms | grep -iv '[048c]0 [Tt] ' | wc -l 1357 # grep ' [Tt] ' /proc/kallsyms | grep -iv '[048c]0 [Tt] ' | grep acpi | wc -l 0 With the patch applied, the remaining unaligned text labels are a combination of static call trampolines and labels in assembly, which can be dealt with in subsequent patches. Signed-off-by: Mark Rutland Acked-by: Rafael J. Wysocki Cc: Florent Revest Cc: Len Brown Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Robert Moore Cc: Steven Rostedt Cc: Will Deacon Cc: linux-acpi@vger.kernel.org Link: https://lore.kernel.org/r/20230123134603.1064407-4-mark.rutland@arm.com Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- drivers/acpi/acpica/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile index 59700433a96e..f919811156b1 100644 --- a/drivers/acpi/acpica/Makefile +++ b/drivers/acpi/acpica/Makefile @@ -3,7 +3,7 @@ # Makefile for ACPICA Core interpreter # -ccflags-y := -Os -D_LINUX -DBUILDING_ACPICA +ccflags-y := -D_LINUX -DBUILDING_ACPICA ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT # use acpi.o to put all files here into acpi.o modparam namespace From 2fc7748d4823fc69a05d0003608b9398ca8cc165 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Tue, 20 Dec 2022 16:25:12 +0800 Subject: [PATCH 1797/4345] clocksource: Suspend the watchdog temporarily when high read latency detected [ Upstream commit b7082cdfc464bf9231300605d03eebf943dda307 ] Bugs have been reported on 8 sockets x86 machines in which the TSC was wrongly disabled when the system is under heavy workload. [ 818.380354] clocksource: timekeeping watchdog on CPU336: hpet wd-wd read-back delay of 1203520ns [ 818.436160] clocksource: wd-tsc-wd read-back delay of 181880ns, clock-skew test skipped! [ 819.402962] clocksource: timekeeping watchdog on CPU338: hpet wd-wd read-back delay of 324000ns [ 819.448036] clocksource: wd-tsc-wd read-back delay of 337240ns, clock-skew test skipped! [ 819.880863] clocksource: timekeeping watchdog on CPU339: hpet read-back delay of 150280ns, attempt 3, marking unstable [ 819.936243] tsc: Marking TSC unstable due to clocksource watchdog [ 820.068173] TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'. [ 820.092382] sched_clock: Marking unstable (818769414384, 1195404998) [ 820.643627] clocksource: Checking clocksource tsc synchronization from CPU 267 to CPUs 0,4,25,70,126,430,557,564. [ 821.067990] clocksource: Switched to clocksource hpet This can be reproduced by running memory intensive 'stream' tests, or some of the stress-ng subcases such as 'ioport'. The reason for these issues is the when system is under heavy load, the read latency of the clocksources can be very high. Even lightweight TSC reads can show high latencies, and latencies are much worse for external clocksources such as HPET or the APIC PM timer. These latencies can result in false-positive clocksource-unstable determinations. These issues were initially reported by a customer running on a production system, and this problem was reproduced on several generations of Xeon servers, especially when running the stress-ng test. These Xeon servers were not production systems, but they did have the latest steppings and firmware. Given that the clocksource watchdog is a continual diagnostic check with frequency of twice a second, there is no need to rush it when the system is under heavy load. Therefore, when high clocksource read latencies are detected, suspend the watchdog timer for 5 minutes. Signed-off-by: Feng Tang Acked-by: Waiman Long Cc: John Stultz Cc: Thomas Gleixner Cc: Stephen Boyd Cc: Feng Tang Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- kernel/time/clocksource.c | 45 ++++++++++++++++++++++++++++----------- 1 file changed, 32 insertions(+), 13 deletions(-) diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index e34ceb91f4c5..86e0fbe583f2 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -312,6 +312,15 @@ static void clocksource_verify_percpu(struct clocksource *cs) testcpu, cs_nsec_min, cs_nsec_max, cs->name); } +static inline void clocksource_reset_watchdog(void) +{ + struct clocksource *cs; + + list_for_each_entry(cs, &watchdog_list, wd_list) + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; +} + + static void clocksource_watchdog(struct timer_list *unused) { u64 csnow, wdnow, cslast, wdlast, delta; @@ -319,6 +328,7 @@ static void clocksource_watchdog(struct timer_list *unused) int64_t wd_nsec, cs_nsec; struct clocksource *cs; enum wd_read_status read_ret; + unsigned long extra_wait = 0; u32 md; spin_lock(&watchdog_lock); @@ -338,13 +348,30 @@ static void clocksource_watchdog(struct timer_list *unused) read_ret = cs_watchdog_read(cs, &csnow, &wdnow); - if (read_ret != WD_READ_SUCCESS) { - if (read_ret == WD_READ_UNSTABLE) - /* Clock readout unreliable, so give it up. */ - __clocksource_unstable(cs); + if (read_ret == WD_READ_UNSTABLE) { + /* Clock readout unreliable, so give it up. */ + __clocksource_unstable(cs); continue; } + /* + * When WD_READ_SKIP is returned, it means the system is likely + * under very heavy load, where the latency of reading + * watchdog/clocksource is very big, and affect the accuracy of + * watchdog check. So give system some space and suspend the + * watchdog check for 5 minutes. + */ + if (read_ret == WD_READ_SKIP) { + /* + * As the watchdog timer will be suspended, and + * cs->last could keep unchanged for 5 minutes, reset + * the counters. + */ + clocksource_reset_watchdog(); + extra_wait = HZ * 300; + break; + } + /* Clocksource initialized ? */ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) || atomic_read(&watchdog_reset_pending)) { @@ -434,7 +461,7 @@ static void clocksource_watchdog(struct timer_list *unused) * pair clocksource_stop_watchdog() clocksource_start_watchdog(). */ if (!timer_pending(&watchdog_timer)) { - watchdog_timer.expires += WATCHDOG_INTERVAL; + watchdog_timer.expires += WATCHDOG_INTERVAL + extra_wait; add_timer_on(&watchdog_timer, next_cpu); } out: @@ -459,14 +486,6 @@ static inline void clocksource_stop_watchdog(void) watchdog_running = 0; } -static inline void clocksource_reset_watchdog(void) -{ - struct clocksource *cs; - - list_for_each_entry(cs, &watchdog_list, wd_list) - cs->flags &= ~CLOCK_SOURCE_WATCHDOG; -} - static void clocksource_resume_watchdog(void) { atomic_inc(&watchdog_reset_pending); From 1fc9760afd8a012f303eea4532a205a2eb158e8f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 5 Jan 2023 20:19:48 -0800 Subject: [PATCH 1798/4345] crypto: hisilicon: Wipe entire pool on error [ Upstream commit aa85923a954e7704bc9d3847dabeb8540aa98d13 ] To work around a Clang __builtin_object_size bug that shows up under CONFIG_FORTIFY_SOURCE and UBSAN_BOUNDS, move the per-loop-iteration mem_block wipe into a single wipe of the entire pool structure after the loop. Reported-by: Nathan Chancellor Link: https://github.com/ClangBuiltLinux/linux/issues/1780 Cc: Weili Qian Cc: Zhou Wang Cc: Herbert Xu Cc: "David S. Miller" Cc: linux-crypto@vger.kernel.org Signed-off-by: Kees Cook Tested-by: Nathan Chancellor # build Link: https://lore.kernel.org/r/20230106041945.never.831-kees@kernel.org Signed-off-by: Sasha Levin --- drivers/crypto/hisilicon/sgl.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c index 725a739800b0..ce77826c7fb0 100644 --- a/drivers/crypto/hisilicon/sgl.c +++ b/drivers/crypto/hisilicon/sgl.c @@ -113,9 +113,8 @@ err_free_mem: for (j = 0; j < i; j++) { dma_free_coherent(dev, block_size, block[j].sgl, block[j].sgl_dma); - memset(block + j, 0, sizeof(*block)); } - kfree(pool); + kfree_sensitive(pool); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(hisi_acc_create_sgl_pool); From 841881320562cbeac7046b537b91cd000480cea2 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 26 Jan 2023 16:08:19 -0800 Subject: [PATCH 1799/4345] net: bcmgenet: Add a check for oversized packets [ Upstream commit 5c0862c2c962052ed5055220a00ac1cefb92fbcd ] Occasionnaly we may get oversized packets from the hardware which exceed the nomimal 2KiB buffer size we allocate SKBs with. Add an early check which drops the packet to avoid invoking skb_over_panic() and move on to processing the next packet. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index e0a6a2e62d23..7667cbb5adfd 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2263,6 +2263,14 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring, __func__, p_index, ring->c_index, ring->read_ptr, dma_length_status); + if (unlikely(len > RX_BUF_LENGTH)) { + netif_err(priv, rx_status, dev, "oversized packet\n"); + dev->stats.rx_length_errors++; + dev->stats.rx_errors++; + dev_kfree_skb_any(skb); + goto next; + } + if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) { netif_err(priv, rx_status, dev, "dropping fragmented packet!\n"); From 7873def499dfc1a5406f0ac06d288b4e9ee461e4 Mon Sep 17 00:00:00 2001 From: Michael Schmitz Date: Thu, 12 Jan 2023 16:55:27 +1300 Subject: [PATCH 1800/4345] m68k: Check syscall_trace_enter() return code [ Upstream commit 2ca8a1de4437f21562e57f9ac123914747a8e7a1 ] Check return code of syscall_trace_enter(), and skip syscall if -1. Return code will be left at what had been set by ptrace or seccomp (in regs->d0). No regression seen in testing with strace on ARAnyM. Signed-off-by: Michael Schmitz Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230112035529.13521-2-schmitzmic@gmail.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- arch/m68k/68000/entry.S | 2 ++ arch/m68k/coldfire/entry.S | 2 ++ arch/m68k/kernel/entry.S | 3 +++ 3 files changed, 7 insertions(+) diff --git a/arch/m68k/68000/entry.S b/arch/m68k/68000/entry.S index 259b3661b614..94abf3d8afc5 100644 --- a/arch/m68k/68000/entry.S +++ b/arch/m68k/68000/entry.S @@ -47,6 +47,8 @@ do_trace: jbsr syscall_trace_enter RESTORE_SWITCH_STACK addql #4,%sp + addql #1,%d0 + jeq ret_from_exception movel %sp@(PT_OFF_ORIG_D0),%d1 movel #-ENOSYS,%d0 cmpl #NR_syscalls,%d1 diff --git a/arch/m68k/coldfire/entry.S b/arch/m68k/coldfire/entry.S index d43a02795a4a..f1d41a9328a2 100644 --- a/arch/m68k/coldfire/entry.S +++ b/arch/m68k/coldfire/entry.S @@ -92,6 +92,8 @@ ENTRY(system_call) jbsr syscall_trace_enter RESTORE_SWITCH_STACK addql #4,%sp + addql #1,%d0 + jeq ret_from_exception movel %d3,%a0 jbsr %a0@ movel %d0,%sp@(PT_OFF_D0) /* save the return value */ diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 9dd76fbb7c6b..546bab6bfc27 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -167,9 +167,12 @@ do_trace_entry: jbsr syscall_trace RESTORE_SWITCH_STACK addql #4,%sp + addql #1,%d0 | optimization for cmpil #-1,%d0 + jeq ret_from_syscall movel %sp@(PT_OFF_ORIG_D0),%d0 cmpl #NR_syscalls,%d0 jcs syscall + jra ret_from_syscall badsys: movel #-ENOSYS,%sp@(PT_OFF_D0) jra ret_from_syscall From 46ce77b07cd83b12cbe6f1aa617cf4487b06317a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 1 Jan 2023 12:47:57 +0100 Subject: [PATCH 1801/4345] wifi: mt76: dma: free rx_head in mt76_dma_rx_cleanup [ Upstream commit 1b88b47e898edef0e56e3a2f4e49f052a136153d ] Free rx_head skb in mt76_dma_rx_cleanup routine in order to avoid possible memory leak at module unload. Signed-off-by: Lorenzo Bianconi Signed-off-by: Felix Fietkau Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/dma.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index f01b455783b2..7991705e9d13 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -476,6 +476,7 @@ mt76_dma_rx_cleanup(struct mt76_dev *dev, struct mt76_queue *q) bool more; spin_lock_bh(&q->lock); + do { buf = mt76_dma_dequeue(dev, q, true, NULL, NULL, &more); if (!buf) @@ -483,6 +484,12 @@ mt76_dma_rx_cleanup(struct mt76_dev *dev, struct mt76_queue *q) skb_free_frag(buf); } while (1); + + if (q->rx_head) { + dev_kfree_skb(q->rx_head); + q->rx_head = NULL; + } + spin_unlock_bh(&q->lock); if (!q->rx_page.va) @@ -505,12 +512,6 @@ mt76_dma_rx_reset(struct mt76_dev *dev, enum mt76_rxq_id qid) mt76_dma_rx_cleanup(dev, q); mt76_dma_sync_idx(dev, q); mt76_dma_rx_fill(dev, q); - - if (!q->rx_head) - return; - - dev_kfree_skb(q->rx_head); - q->rx_head = NULL; } static void From 1ef724fed392f7ed56e64817b04ba75e64903101 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 2 Feb 2023 13:44:49 +0100 Subject: [PATCH 1802/4345] ACPI: video: Fix Lenovo Ideapad Z570 DMI match [ Upstream commit 2d11eae42d52a131f06061015e49dc0f085c5bfc ] Multiple Ideapad Z570 variants need acpi_backlight=native to force native use on these pre Windows 8 machines since acpi_video backlight control does not work here. The original DMI quirk matches on a product_name of "102434U" but other variants may have different product_name-s such as e.g. "1024D9U". Move to checking product_version instead as is more or less standard for Lenovo DMI quirks for similar reasons. Signed-off-by: Hans de Goede Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/video_detect.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index b13713199ad9..038542b3a80a 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -313,7 +313,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { .ident = "Lenovo Ideapad Z570", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "102434U"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Ideapad Z570"), }, }, { From 206c511e4214b713a684022cfa84b1bd5ccae5c6 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 11 Jan 2023 13:34:02 +0200 Subject: [PATCH 1803/4345] net/mlx5: fw_tracer: Fix debug print [ Upstream commit 988c2352273997a242f15c4fc3711773515006a2 ] The debug message specify tdsn, but takes as an argument the tmsn. The correct argument is tmsn, hence, fix the print. Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 40d7bfca3749..0a011a41c039 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -603,7 +603,7 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, } else { cur_string = mlx5_tracer_message_get(tracer, tracer_event); if (!cur_string) { - pr_debug("%s Got string event for unknown string tdsm: %d\n", + pr_debug("%s Got string event for unknown string tmsn: %d\n", __func__, tracer_event->string_event.tmsn); return -1; } From d80f947bb303f501d397bcad285393ed1e532035 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 27 Jan 2023 14:39:21 -0800 Subject: [PATCH 1804/4345] coda: Avoid partial allocation of sig_inputArgs [ Upstream commit 48df133578c70185a95a49390d42df1996ddba2a ] GCC does not like having a partially allocated object, since it cannot reason about it for bounds checking when it is passed to other code. Instead, fully allocate sig_inputArgs. (Alternatively, sig_inputArgs should be defined as a struct coda_in_hdr, if it is actually not using any other part of the union.) Seen under GCC 13: ../fs/coda/upcall.c: In function 'coda_upcall': ../fs/coda/upcall.c:801:22: warning: array subscript 'union inputArgs[0]' is partly outside array bounds of 'unsigned char[20]' [-Warray-bounds=] 801 | sig_inputArgs->ih.opcode = CODA_SIGNAL; | ^~ Cc: Jan Harkes Cc: coda@cs.cmu.edu Cc: codalist@coda.cs.cmu.edu Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230127223921.never.882-kees@kernel.org Signed-off-by: Sasha Levin --- fs/coda/upcall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c index eb3b1898da46..610484c90260 100644 --- a/fs/coda/upcall.c +++ b/fs/coda/upcall.c @@ -790,7 +790,7 @@ static int coda_upcall(struct venus_comm *vcp, sig_req = kmalloc(sizeof(struct upc_req), GFP_KERNEL); if (!sig_req) goto exit; - sig_inputArgs = kvzalloc(sizeof(struct coda_in_hdr), GFP_KERNEL); + sig_inputArgs = kvzalloc(sizeof(*sig_inputArgs), GFP_KERNEL); if (!sig_inputArgs) { kfree(sig_req); goto exit; From 0c2b778edd8a4609e6650c55d490af9359c1e62f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 31 Jan 2023 17:37:59 -0800 Subject: [PATCH 1805/4345] uaccess: Add minimum bounds check on kernel buffer size [ Upstream commit 04ffde1319a715bd0550ded3580d4ea3bc003776 ] While there is logic about the difference between ksize and usize, copy_struct_from_user() didn't check the size of the destination buffer (when it was known) against ksize. Add this check so there is an upper bounds check on the possible memset() call, otherwise lower bounds checks made by callers will trigger bounds warnings under -Warray-bounds. Seen under GCC 13: In function 'copy_struct_from_user', inlined from 'iommufd_fops_ioctl' at ../drivers/iommu/iommufd/main.c:333:8: ../include/linux/fortify-string.h:59:33: warning: '__builtin_memset' offset [57, 4294967294] is out of the bounds [0, 56] of object 'buf' with type 'union ucmd_buffer' [-Warray-bounds=] 59 | #define __underlying_memset __builtin_memset | ^ ../include/linux/fortify-string.h:453:9: note: in expansion of macro '__underlying_memset' 453 | __underlying_memset(p, c, __fortify_size); \ | ^~~~~~~~~~~~~~~~~~~ ../include/linux/fortify-string.h:461:25: note: in expansion of macro '__fortify_memset_chk' 461 | #define memset(p, c, s) __fortify_memset_chk(p, c, s, \ | ^~~~~~~~~~~~~~~~~~~~ ../include/linux/uaccess.h:334:17: note: in expansion of macro 'memset' 334 | memset(dst + size, 0, rest); | ^~~~~~ ../drivers/iommu/iommufd/main.c: In function 'iommufd_fops_ioctl': ../drivers/iommu/iommufd/main.c:311:27: note: 'buf' declared here 311 | union ucmd_buffer buf; | ^~~ Cc: Christian Brauner Cc: Rasmus Villemoes Cc: Arnd Bergmann Cc: Dinh Nguyen Cc: Catalin Marinas Cc: Andrew Morton Cc: Geert Uytterhoeven Cc: Alexander Potapenko Acked-by: Aleksa Sarai Signed-off-by: Kees Cook Link: https://lore.kernel.org/lkml/20230203193523.never.667-kees@kernel.org/ Signed-off-by: Sasha Levin --- include/linux/uaccess.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index c7c6e8b8344d..20668760daa0 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -348,6 +348,10 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; + /* Double check if ksize is larger than a known object size. */ + if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) + return -E2BIG; + /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); From e974e8f1e37d22c0de07374f8ddc84073fef2f1d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 2 Feb 2023 16:15:15 +0100 Subject: [PATCH 1806/4345] PM: EM: fix memory leak with using debugfs_lookup() [ Upstream commit a0e8c13ccd6a9a636d27353da62c2410c4eca337 ] When calling debugfs_lookup() the result must have dput() called on it, otherwise the memory will leak over time. To make things simpler, just call debugfs_lookup_and_remove() instead which handles all of the logic at once. Signed-off-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- kernel/power/energy_model.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 119b929dcff0..334173fe6940 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -72,10 +72,7 @@ static void em_debug_create_pd(struct device *dev) static void em_debug_remove_pd(struct device *dev) { - struct dentry *debug_dir; - - debug_dir = debugfs_lookup(dev_name(dev), rootdir); - debugfs_remove_recursive(debug_dir); + debugfs_lookup_and_remove(dev_name(dev), rootdir); } static int __init em_debug_init(void) From 348cc9ab33803bc0ed6e9cfd61b07f09f98debec Mon Sep 17 00:00:00 2001 From: Moises Cardona Date: Sun, 25 Dec 2022 14:07:13 -0500 Subject: [PATCH 1807/4345] Bluetooth: btusb: Add VID:PID 13d3:3529 for Realtek RTL8821CE [ Upstream commit 1eec3b95b5ce7fb2cdd273ac4f8b24b1ed6776a1 ] This patch adds VID:PID 13d3:3529 to the btusb.c file. This VID:PID is found in the Realtek RTL8821CE module (M.2 module AW-CB304NF on an ASUS E210MA laptop) Output of /sys/kernel/debug/usb/devices: T: Bus=01 Lev=01 Prnt=01 Port=07 Cnt=02 Dev#= 3 Spd=12 MxCh= 0 D: Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=13d3 ProdID=3529 Rev= 1.10 S: Manufacturer=Realtek S: Product=Bluetooth Radio C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms Signed-off-by: Moises Cardona Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/btusb.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 3d905fda9b29..2695ece47eb0 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -393,6 +393,10 @@ static const struct usb_device_id blacklist_table[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x8087, 0xe0, 0x01, 0x01), .driver_info = BTUSB_IGNORE }, + /* Realtek 8821CE Bluetooth devices */ + { USB_DEVICE(0x13d3, 0x3529), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + /* Realtek 8822CE Bluetooth devices */ { USB_DEVICE(0x0bda, 0xb00c), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, From 9f73793b81637c60ccc83cc508645310b8ab7d80 Mon Sep 17 00:00:00 2001 From: Roman Li Date: Thu, 1 Dec 2022 09:06:42 -0500 Subject: [PATCH 1808/4345] drm/amd/display: Fix potential null-deref in dm_resume [ Upstream commit 7a7175a2cd84b7874bebbf8e59f134557a34161b ] [Why] Fixing smatch error: dm_resume() error: we previously assumed 'aconnector->dc_link' could be null [How] Check if dc_link null at the beginning of the loop, so further checks can be dropped. Reported-by: kernel test robot Reported-by: Dan Carpenter Reviewed-by: Wayne Lin Acked-by: Jasdeep Dhillon Signed-off-by: Roman Li Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index fbe15f4b75fd..dbdf0e210522 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2051,12 +2051,14 @@ static int dm_resume(void *handle) drm_for_each_connector_iter(connector, &iter) { aconnector = to_amdgpu_dm_connector(connector); + if (!aconnector->dc_link) + continue; + /* * this is the case when traversing through already created * MST connectors, should be skipped */ - if (aconnector->dc_link && - aconnector->dc_link->type == dc_connection_mst_branch) + if (aconnector->dc_link->type == dc_connection_mst_branch) continue; mutex_lock(&aconnector->hpd_lock); From f4cb425252086a5f81e77200a84837102dddfea3 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Fri, 16 Sep 2022 11:22:05 +0300 Subject: [PATCH 1809/4345] drm/omap: dsi: Fix excessive stack usage [ Upstream commit cfca78971b9233aef0891507a98fba62046d4542 ] dsi_dump_dsi_irqs(), a function used for debugfs prints, has a large struct in its frame, which can result in: drivers/gpu/drm/omapdrm/dss/dsi.c:1126:1: warning: the frame size of 1060 bytes is larger than 1024 bytes [-Wframe-larger-than=] As the performance of the function is of no concern, let's allocate the struct with kmalloc instead. Compile-tested only. Signed-off-by: Tomi Valkeinen Reported-by: kernel test robot Reviewed-by: Arnd Bergmann Link: https://patchwork.freedesktop.org/patch/msgid/20220916082206.167427-1-tomi.valkeinen@ideasonboard.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/omapdrm/dss/dsi.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c index eeccf40bae41..1b1ddc5fe6dc 100644 --- a/drivers/gpu/drm/omapdrm/dss/dsi.c +++ b/drivers/gpu/drm/omapdrm/dss/dsi.c @@ -1444,22 +1444,26 @@ static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) { struct dsi_data *dsi = s->private; unsigned long flags; - struct dsi_irq_stats stats; + struct dsi_irq_stats *stats; + + stats = kmalloc(sizeof(*stats), GFP_KERNEL); + if (!stats) + return -ENOMEM; spin_lock_irqsave(&dsi->irq_stats_lock, flags); - stats = dsi->irq_stats; + *stats = dsi->irq_stats; memset(&dsi->irq_stats, 0, sizeof(dsi->irq_stats)); dsi->irq_stats.last_reset = jiffies; spin_unlock_irqrestore(&dsi->irq_stats_lock, flags); seq_printf(s, "period %u ms\n", - jiffies_to_msecs(jiffies - stats.last_reset)); + jiffies_to_msecs(jiffies - stats->last_reset)); - seq_printf(s, "irqs %d\n", stats.irq_count); + seq_printf(s, "irqs %d\n", stats->irq_count); #define PIS(x) \ - seq_printf(s, "%-20s %10d\n", #x, stats.dsi_irqs[ffs(DSI_IRQ_##x)-1]); + seq_printf(s, "%-20s %10d\n", #x, stats->dsi_irqs[ffs(DSI_IRQ_##x)-1]); seq_printf(s, "-- DSI%d interrupts --\n", dsi->module_id + 1); PIS(VC0); @@ -1483,10 +1487,10 @@ static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) #define PIS(x) \ seq_printf(s, "%-20s %10d %10d %10d %10d\n", #x, \ - stats.vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \ - stats.vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \ - stats.vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \ - stats.vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]); + stats->vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \ + stats->vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \ + stats->vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \ + stats->vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]); seq_printf(s, "-- VC interrupts --\n"); PIS(CS); @@ -1502,7 +1506,7 @@ static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) #define PIS(x) \ seq_printf(s, "%-20s %10d\n", #x, \ - stats.cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]); + stats->cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]); seq_printf(s, "-- CIO interrupts --\n"); PIS(ERRSYNCESC1); @@ -1527,6 +1531,8 @@ static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) PIS(ULPSACTIVENOT_ALL1); #undef PIS + kfree(stats); + return 0; } #endif From bc919c866dd5a6bc0533f1418cb021ac83b1b913 Mon Sep 17 00:00:00 2001 From: Jingyuan Liang Date: Tue, 13 Dec 2022 22:53:30 +0000 Subject: [PATCH 1810/4345] HID: Add Mapping for System Microphone Mute [ Upstream commit 2d60f9f4f26785a00273cb81fe60eff129ebd449 ] HUTRR110 added a new usage code for a key that is supposed to mute/unmute microphone system-wide. Map the new usage code(0x01 0xa9) to keycode KEY_MICMUTE. Additionally hid-debug is adjusted to recognize this keycode as well. Signed-off-by: Jingyuan Liang Reviewed-by: Dmitry Torokhov Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/hid-debug.c | 1 + drivers/hid/hid-input.c | 8 ++++++++ 2 files changed, 9 insertions(+) diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index f4e2e6937758..1f60a381ae63 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -933,6 +933,7 @@ static const char *keys[KEY_MAX + 1] = { [KEY_VOICECOMMAND] = "VoiceCommand", [KEY_EMOJI_PICKER] = "EmojiPicker", [KEY_DICTATE] = "Dictate", + [KEY_MICMUTE] = "MicrophoneMute", [KEY_BRIGHTNESS_MIN] = "BrightnessMin", [KEY_BRIGHTNESS_MAX] = "BrightnessMax", [KEY_BRIGHTNESS_AUTO] = "BrightnessAuto", diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 75a4d8d6bb0f..3399953256d8 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -675,6 +675,14 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel break; } + if ((usage->hid & 0xf0) == 0xa0) { /* SystemControl */ + switch (usage->hid & 0xf) { + case 0x9: map_key_clear(KEY_MICMUTE); break; + default: goto ignore; + } + break; + } + if ((usage->hid & 0xf0) == 0xb0) { /* SC - Display */ switch (usage->hid & 0xf) { case 0x05: map_key_clear(KEY_SWITCHVIDEOMODE); break; From 819d8dba030dc99bdf6dfacac671db23cec28427 Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Mon, 19 Dec 2022 10:02:38 +0100 Subject: [PATCH 1811/4345] drm/tiny: ili9486: Do not assume 8-bit only SPI controllers [ Upstream commit 77772e607522daa61f3af74df018559db75c43d6 ] The pixel data for the ILI9486 is always 16-bits wide and it must be sent over the SPI bus. When the controller is only able to deal with 8-bit transfers, this 16-bits data needs to be swapped before the sending to account for the big endian bus, this is on the contrary not needed when the SPI controller already supports 16-bits transfers. The decision about swapping the pixel data or not is taken in the MIPI DBI code by probing the controller capabilities: if the controller only suppors 8-bit transfers the data is swapped, otherwise it is not. This swapping/non-swapping is relying on the assumption that when the controller does support 16-bit transactions then the data is sent unswapped in 16-bits-per-word over SPI. The problem with the ILI9486 driver is that it is forcing 8-bit transactions also for controllers supporting 16-bits, violating the assumption and corrupting the pixel data. Align the driver to what is done in the MIPI DBI code by adjusting the transfer size to the maximum allowed by the SPI controller. Reviewed-by: Neil Armstrong Signed-off-by: Carlo Caione Reviewed-by: Kamlesh Gurudasani Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20221116-s905x_spi_ili9486-v4-2-f86b4463b9e4@baylibre.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/tiny/ili9486.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/tiny/ili9486.c b/drivers/gpu/drm/tiny/ili9486.c index 403af68fa440..7ea26e5fbcb2 100644 --- a/drivers/gpu/drm/tiny/ili9486.c +++ b/drivers/gpu/drm/tiny/ili9486.c @@ -43,6 +43,7 @@ static int waveshare_command(struct mipi_dbi *mipi, u8 *cmd, u8 *par, size_t num) { struct spi_device *spi = mipi->spi; + unsigned int bpw = 8; void *data = par; u32 speed_hz; int i, ret; @@ -56,8 +57,6 @@ static int waveshare_command(struct mipi_dbi *mipi, u8 *cmd, u8 *par, * The displays are Raspberry Pi HATs and connected to the 8-bit only * SPI controller, so 16-bit command and parameters need byte swapping * before being transferred as 8-bit on the big endian SPI bus. - * Pixel data bytes have already been swapped before this function is - * called. */ buf[0] = cpu_to_be16(*cmd); gpiod_set_value_cansleep(mipi->dc, 0); @@ -71,12 +70,18 @@ static int waveshare_command(struct mipi_dbi *mipi, u8 *cmd, u8 *par, for (i = 0; i < num; i++) buf[i] = cpu_to_be16(par[i]); num *= 2; - speed_hz = mipi_dbi_spi_cmd_max_speed(spi, num); data = buf; } + /* + * Check whether pixel data bytes needs to be swapped or not + */ + if (*cmd == MIPI_DCS_WRITE_MEMORY_START && !mipi->swap_bytes) + bpw = 16; + gpiod_set_value_cansleep(mipi->dc, 1); - ret = mipi_dbi_spi_transfer(spi, speed_hz, 8, data, num); + speed_hz = mipi_dbi_spi_cmd_max_speed(spi, num); + ret = mipi_dbi_spi_transfer(spi, speed_hz, bpw, data, num); free: kfree(buf); From ce9e9d3dcbb0d1551ffd1a7f16e7c051f3ba4140 Mon Sep 17 00:00:00 2001 From: Liwei Song Date: Fri, 6 Jan 2023 17:47:29 +0800 Subject: [PATCH 1812/4345] drm/radeon: free iio for atombios when driver shutdown [ Upstream commit 4773fadedca918faec443daaca5e4ea1c0ced144 ] Fix below kmemleak when unload radeon driver: unreferenced object 0xffff9f8608ede200 (size 512): comm "systemd-udevd", pid 326, jiffies 4294682822 (age 716.338s) hex dump (first 32 bytes): 00 00 00 00 c4 aa ec aa 14 ab 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000062fadebe>] kmem_cache_alloc_trace+0x2f1/0x500 [<00000000b6883cea>] atom_parse+0x117/0x230 [radeon] [<00000000158c23fd>] radeon_atombios_init+0xab/0x170 [radeon] [<00000000683f672e>] si_init+0x57/0x750 [radeon] [<00000000566cc31f>] radeon_device_init+0x559/0x9c0 [radeon] [<0000000046efabb3>] radeon_driver_load_kms+0xc1/0x1a0 [radeon] [<00000000b5155064>] drm_dev_register+0xdd/0x1d0 [<0000000045fec835>] radeon_pci_probe+0xbd/0x100 [radeon] [<00000000e69ecca3>] pci_device_probe+0xe1/0x160 [<0000000019484b76>] really_probe.part.0+0xc1/0x2c0 [<000000003f2649da>] __driver_probe_device+0x96/0x130 [<00000000231c5bb1>] driver_probe_device+0x24/0xf0 [<0000000000a42377>] __driver_attach+0x77/0x190 [<00000000d7574da6>] bus_for_each_dev+0x7f/0xd0 [<00000000633166d2>] driver_attach+0x1e/0x30 [<00000000313b05b8>] bus_add_driver+0x12c/0x1e0 iio was allocated in atom_index_iio() called by atom_parse(), but it doesn't got released when the dirver is shutdown. Fix this kmemleak by free it in radeon_atombios_fini(). Signed-off-by: Liwei Song Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/radeon/radeon_device.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 8287410f471f..131f425c363a 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1022,6 +1022,7 @@ void radeon_atombios_fini(struct radeon_device *rdev) { if (rdev->mode_info.atom_context) { kfree(rdev->mode_info.atom_context->scratch); + kfree(rdev->mode_info.atom_context->iio); } kfree(rdev->mode_info.atom_context); rdev->mode_info.atom_context = NULL; From d473c55ce1975c9e601c25293328a5039225d2b2 Mon Sep 17 00:00:00 2001 From: Konstantin Meskhidze Date: Wed, 30 Nov 2022 10:50:46 +0800 Subject: [PATCH 1813/4345] drm: amd: display: Fix memory leakage [ Upstream commit 6b8701be1f66064ca72733c5f6e13748cdbf8397 ] This commit fixes memory leakage in dc_construct_ctx() function. Signed-off-by: Konstantin Meskhidze Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/core/dc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 99887bcfada0..7e0a55aa2b18 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -616,6 +616,7 @@ static bool dc_construct_ctx(struct dc *dc, dc_ctx->perf_trace = dc_perf_trace_create(); if (!dc_ctx->perf_trace) { + kfree(dc_ctx); ASSERT_CRITICAL(false); return false; } From 540c66180afd59309a442d3bf1f2393464c8b4c5 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Tue, 10 Jan 2023 10:16:51 +0800 Subject: [PATCH 1814/4345] drm/msm/dsi: Add missing check for alloc_ordered_workqueue [ Upstream commit 115906ca7b535afb1fe7b5406c566ccd3873f82b ] Add check for the return value of alloc_ordered_workqueue as it may return NULL pointer and cause NULL pointer dereference. Signed-off-by: Jiasheng Jiang Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/517646/ Link: https://lore.kernel.org/r/20230110021651.12770-1-jiasheng@iscas.ac.cn Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dsi/dsi_host.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 51e8318cc8ff..5a76aa138917 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1913,6 +1913,9 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) /* setup workqueue */ msm_host->workqueue = alloc_ordered_workqueue("dsi_drm_work", 0); + if (!msm_host->workqueue) + return -ENOMEM; + INIT_WORK(&msm_host->err_work, dsi_err_worker); INIT_WORK(&msm_host->hpd_work, dsi_hpd_worker); From fcfc7740228d2a4ce105950a41494ede86712d09 Mon Sep 17 00:00:00 2001 From: Jakob Koschel Date: Fri, 20 Jan 2023 00:23:20 +0100 Subject: [PATCH 1815/4345] docs/scripts/gdb: add necessary make scripts_gdb step [ Upstream commit 6b219431037bf98c9efd49716aea9b68440477a3 ] In order to debug the kernel successfully with gdb you need to run 'make scripts_gdb' nowadays. This was changed with the following commit: Commit 67274c083438340ad16c ("scripts/gdb: delay generation of gdb constants.py") In order to have a complete guide for beginners this remark should be added to the offial documentation. Signed-off-by: Jakob Koschel Link: https://lore.kernel.org/r/20230112-documentation-gdb-v2-1-292785c43dc9@gmail.com Signed-off-by: Jonathan Corbet Signed-off-by: Sasha Levin --- Documentation/dev-tools/gdb-kernel-debugging.rst | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/dev-tools/gdb-kernel-debugging.rst b/Documentation/dev-tools/gdb-kernel-debugging.rst index 4756f6b3a04e..10cdd990b63d 100644 --- a/Documentation/dev-tools/gdb-kernel-debugging.rst +++ b/Documentation/dev-tools/gdb-kernel-debugging.rst @@ -39,6 +39,10 @@ Setup this mode. In this case, you should build the kernel with CONFIG_RANDOMIZE_BASE disabled if the architecture supports KASLR. +- Build the gdb scripts (required on kernels v5.1 and above):: + + make scripts_gdb + - Enable the gdb stub of QEMU/KVM, either - at VM startup time by appending "-s" to the QEMU command line From 0adacf6d6b1233f24a1e1775e0e2766fd0b69314 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 27 Jan 2023 14:41:29 -0800 Subject: [PATCH 1816/4345] ASoC: kirkwood: Iterate over array indexes instead of using pointer math [ Upstream commit b3bcedc0402fcdc5c8624c433562d9d1882749d8 ] Walking the dram->cs array was seen as accesses beyond the first array item by the compiler. Instead, use the array index directly. This allows for run-time bounds checking under CONFIG_UBSAN_BOUNDS as well. Seen with GCC 13 with -fstrict-flex-arrays: ../sound/soc/kirkwood/kirkwood-dma.c: In function 'kirkwood_dma_conf_mbus_windows.constprop': ../sound/soc/kirkwood/kirkwood-dma.c:90:24: warning: array subscript 0 is outside array bounds of 'const struct mbus_dram_window[0]' [-Warray-bounds=] 90 | if ((cs->base & 0xffff0000) < (dma & 0xffff0000)) { | ~~^~~~~~ Cc: Liam Girdwood Cc: Mark Brown Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: alsa-devel@alsa-project.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230127224128.never.410-kees@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/kirkwood/kirkwood-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/kirkwood/kirkwood-dma.c b/sound/soc/kirkwood/kirkwood-dma.c index e037826b2451..2d41e6ab2ce4 100644 --- a/sound/soc/kirkwood/kirkwood-dma.c +++ b/sound/soc/kirkwood/kirkwood-dma.c @@ -86,7 +86,7 @@ kirkwood_dma_conf_mbus_windows(void __iomem *base, int win, /* try to find matching cs for current dma address */ for (i = 0; i < dram->num_cs; i++) { - const struct mbus_dram_window *cs = dram->cs + i; + const struct mbus_dram_window *cs = &dram->cs[i]; if ((cs->base & 0xffff0000) < (dma & 0xffff0000)) { writel(cs->base & 0xffff0000, base + KIRKWOOD_AUDIO_WIN_BASE_REG(win)); From b4ff71c6f0290f9a12437ae27e0e666147e91e1e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 27 Jan 2023 14:52:07 -0800 Subject: [PATCH 1817/4345] regulator: max77802: Bounds check regulator id against opmode [ Upstream commit 4fd8bcec5fd7c0d586206fa2f42bd67b06cdaa7e ] Explicitly bounds-check the id before accessing the opmode array. Seen with GCC 13: ../drivers/regulator/max77802-regulator.c: In function 'max77802_enable': ../drivers/regulator/max77802-regulator.c:217:29: warning: array subscript [0, 41] is outside array bounds of 'unsigned int[42]' [-Warray-bounds=] 217 | if (max77802->opmode[id] == MAX77802_OFF_PWRREQ) | ~~~~~~~~~~~~~~~~^~~~ ../drivers/regulator/max77802-regulator.c:62:22: note: while referencing 'opmode' 62 | unsigned int opmode[MAX77802_REG_MAX]; | ^~~~~~ Cc: Javier Martinez Canillas Cc: Liam Girdwood Cc: Mark Brown Signed-off-by: Kees Cook Acked-by: Javier Martinez Canillas Link: https://lore.kernel.org/r/20230127225203.never.864-kees@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/max77802-regulator.c | 34 ++++++++++++++++++-------- 1 file changed, 24 insertions(+), 10 deletions(-) diff --git a/drivers/regulator/max77802-regulator.c b/drivers/regulator/max77802-regulator.c index 7b8ec8c0bd15..660e179a82a2 100644 --- a/drivers/regulator/max77802-regulator.c +++ b/drivers/regulator/max77802-regulator.c @@ -95,9 +95,11 @@ static int max77802_set_suspend_disable(struct regulator_dev *rdev) { unsigned int val = MAX77802_OFF_PWRREQ; struct max77802_regulator_prv *max77802 = rdev_get_drvdata(rdev); - int id = rdev_get_id(rdev); + unsigned int id = rdev_get_id(rdev); int shift = max77802_get_opmode_shift(id); + if (WARN_ON_ONCE(id >= ARRAY_SIZE(max77802->opmode))) + return -EINVAL; max77802->opmode[id] = val; return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg, rdev->desc->enable_mask, val << shift); @@ -111,7 +113,7 @@ static int max77802_set_suspend_disable(struct regulator_dev *rdev) static int max77802_set_mode(struct regulator_dev *rdev, unsigned int mode) { struct max77802_regulator_prv *max77802 = rdev_get_drvdata(rdev); - int id = rdev_get_id(rdev); + unsigned int id = rdev_get_id(rdev); unsigned int val; int shift = max77802_get_opmode_shift(id); @@ -128,6 +130,9 @@ static int max77802_set_mode(struct regulator_dev *rdev, unsigned int mode) return -EINVAL; } + if (WARN_ON_ONCE(id >= ARRAY_SIZE(max77802->opmode))) + return -EINVAL; + max77802->opmode[id] = val; return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg, rdev->desc->enable_mask, val << shift); @@ -136,8 +141,10 @@ static int max77802_set_mode(struct regulator_dev *rdev, unsigned int mode) static unsigned max77802_get_mode(struct regulator_dev *rdev) { struct max77802_regulator_prv *max77802 = rdev_get_drvdata(rdev); - int id = rdev_get_id(rdev); + unsigned int id = rdev_get_id(rdev); + if (WARN_ON_ONCE(id >= ARRAY_SIZE(max77802->opmode))) + return -EINVAL; return max77802_map_mode(max77802->opmode[id]); } @@ -161,10 +168,13 @@ static int max77802_set_suspend_mode(struct regulator_dev *rdev, unsigned int mode) { struct max77802_regulator_prv *max77802 = rdev_get_drvdata(rdev); - int id = rdev_get_id(rdev); + unsigned int id = rdev_get_id(rdev); unsigned int val; int shift = max77802_get_opmode_shift(id); + if (WARN_ON_ONCE(id >= ARRAY_SIZE(max77802->opmode))) + return -EINVAL; + /* * If the regulator has been disabled for suspend * then is invalid to try setting a suspend mode. @@ -210,9 +220,11 @@ static int max77802_set_suspend_mode(struct regulator_dev *rdev, static int max77802_enable(struct regulator_dev *rdev) { struct max77802_regulator_prv *max77802 = rdev_get_drvdata(rdev); - int id = rdev_get_id(rdev); + unsigned int id = rdev_get_id(rdev); int shift = max77802_get_opmode_shift(id); + if (WARN_ON_ONCE(id >= ARRAY_SIZE(max77802->opmode))) + return -EINVAL; if (max77802->opmode[id] == MAX77802_OFF_PWRREQ) max77802->opmode[id] = MAX77802_OPMODE_NORMAL; @@ -541,7 +553,7 @@ static int max77802_pmic_probe(struct platform_device *pdev) for (i = 0; i < MAX77802_REG_MAX; i++) { struct regulator_dev *rdev; - int id = regulators[i].id; + unsigned int id = regulators[i].id; int shift = max77802_get_opmode_shift(id); int ret; @@ -559,10 +571,12 @@ static int max77802_pmic_probe(struct platform_device *pdev) * the hardware reports OFF as the regulator operating mode. * Default to operating mode NORMAL in that case. */ - if (val == MAX77802_STATUS_OFF) - max77802->opmode[id] = MAX77802_OPMODE_NORMAL; - else - max77802->opmode[id] = val; + if (id < ARRAY_SIZE(max77802->opmode)) { + if (val == MAX77802_STATUS_OFF) + max77802->opmode[id] = MAX77802_OPMODE_NORMAL; + else + max77802->opmode[id] = val; + } rdev = devm_regulator_register(&pdev->dev, ®ulators[i], &config); From bfa4ffd8159159ea17d4759a4c3a355a81617c99 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 27 Jan 2023 16:53:58 -0800 Subject: [PATCH 1818/4345] regulator: s5m8767: Bounds check id indexing into arrays [ Upstream commit e314e15a0b58f9d051c00b25951073bcdae61953 ] The compiler has no way to know if "id" is within the array bounds of the regulators array. Add a check for this and a build-time check that the regulators and reg_voltage_map arrays are sized the same. Seen with GCC 13: ../drivers/regulator/s5m8767.c: In function 's5m8767_pmic_probe': ../drivers/regulator/s5m8767.c:936:35: warning: array subscript [0, 36] is outside array bounds of 'struct regulator_desc[37]' [-Warray-bounds=] 936 | regulators[id].vsel_reg = | ~~~~~~~~~~^~~~ Cc: Krzysztof Kozlowski Cc: Liam Girdwood Cc: Mark Brown Cc: linux-samsung-soc@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230128005358.never.313-kees@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/s5m8767.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c index 35269f998210..754c6fcc6e64 100644 --- a/drivers/regulator/s5m8767.c +++ b/drivers/regulator/s5m8767.c @@ -923,10 +923,14 @@ static int s5m8767_pmic_probe(struct platform_device *pdev) for (i = 0; i < pdata->num_regulators; i++) { const struct sec_voltage_desc *desc; - int id = pdata->regulators[i].id; + unsigned int id = pdata->regulators[i].id; int enable_reg, enable_val; struct regulator_dev *rdev; + BUILD_BUG_ON(ARRAY_SIZE(regulators) != ARRAY_SIZE(reg_voltage_map)); + if (WARN_ON_ONCE(id >= ARRAY_SIZE(regulators))) + continue; + desc = reg_voltage_map[id]; if (desc) { regulators[id].n_voltages = From 2f8623377f3e0cfaa80558631b8694d02a492b4c Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 31 Jan 2023 15:06:53 +0100 Subject: [PATCH 1819/4345] gfs2: Improve gfs2_make_fs_rw error handling [ Upstream commit b66f723bb552ad59c2acb5d45ea45c890f84498b ] In gfs2_make_fs_rw(), make sure to call gfs2_consist() to report an inconsistency and mark the filesystem as withdrawn when gfs2_find_jhead() fails. At the end of gfs2_make_fs_rw(), when we discover that the filesystem has been withdrawn, make sure we report an error. This also replaces the gfs2_withdrawn() check after gfs2_find_jhead(). Reported-by: Tetsuo Handa Cc: syzbot+f51cb4b9afbd87ec06f2@syzkaller.appspotmail.com Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/super.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index d14b98aa1c3e..5cb7e771b57a 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -145,8 +145,10 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) return -EIO; error = gfs2_find_jhead(sdp->sd_jdesc, &head, false); - if (error || gfs2_withdrawn(sdp)) + if (error) { + gfs2_consist(sdp); return error; + } if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) { gfs2_consist(sdp); @@ -158,7 +160,9 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) gfs2_log_pointers_init(sdp, head.lh_blkno); error = gfs2_quota_init(sdp); - if (!error && !gfs2_withdrawn(sdp)) + if (!error && gfs2_withdrawn(sdp)) + error = -EIO; + if (!error) set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); return error; } From 5735878a7b7db7e9ce731cb36cec298a9de67549 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 3 Jan 2023 12:46:20 +0100 Subject: [PATCH 1820/4345] hwmon: (coretemp) Simplify platform device handling [ Upstream commit 6d03bbff456befeccdd4d663177c4d6c75d0c4ff ] Coretemp's platform driver is unconventional. All the real work is done globally by the initcall and CPU hotplug notifiers, while the "driver" effectively just wraps an allocation and the registration of the hwmon interface in a long-winded round-trip through the driver core. The whole logic of dynamically creating and destroying platform devices to bring the interfaces up and down is error prone, since it assumes platform_device_add() will synchronously bind the driver and set drvdata before it returns, thus results in a NULL dereference if drivers_autoprobe is turned off for the platform bus. Furthermore, the unusual approach of doing that from within a CPU hotplug notifier, already commented in the code that it deadlocks suspend, also causes lockdep issues for other drivers or subsystems which may want to legitimately register a CPU hotplug notifier from a platform bus notifier. All of these issues can be solved by ripping this unusual behaviour out completely, simply tying the platform devices to the lifetime of the module itself, and directly managing the hwmon interfaces from the hotplug notifiers. There is a slight user-visible change in that /sys/bus/platform/drivers/coretemp will no longer appear, and /sys/devices/platform/coretemp.n will remain present if package n is hotplugged off, but hwmon users should really only be looking for the presence of the hwmon interfaces, whose behaviour remains unchanged. Link: https://lore.kernel.org/lkml/20220922101036.87457-1-janusz.krzysztofik@linux.intel.com/ Link: https://gitlab.freedesktop.org/drm/intel/issues/6641 Signed-off-by: Robin Murphy Signed-off-by: Janusz Krzysztofik Link: https://lore.kernel.org/r/20230103114620.15319-1-janusz.krzysztofik@linux.intel.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/coretemp.c | 134 ++++++++++++++++++--------------------- 1 file changed, 61 insertions(+), 73 deletions(-) diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 42b84ebff057..eaae5de2ab61 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -550,66 +550,49 @@ static void coretemp_remove_core(struct platform_data *pdata, int indx) ida_free(&pdata->ida, indx - BASE_SYSFS_ATTR_NO); } -static int coretemp_probe(struct platform_device *pdev) +static int coretemp_device_add(int zoneid) { - struct device *dev = &pdev->dev; + struct platform_device *pdev; struct platform_data *pdata; + int err; /* Initialize the per-zone data structures */ - pdata = devm_kzalloc(dev, sizeof(struct platform_data), GFP_KERNEL); + pdata = kzalloc(sizeof(*pdata), GFP_KERNEL); if (!pdata) return -ENOMEM; - pdata->pkg_id = pdev->id; + pdata->pkg_id = zoneid; ida_init(&pdata->ida); - platform_set_drvdata(pdev, pdata); - - pdata->hwmon_dev = devm_hwmon_device_register_with_groups(dev, DRVNAME, - pdata, NULL); - return PTR_ERR_OR_ZERO(pdata->hwmon_dev); -} - -static int coretemp_remove(struct platform_device *pdev) -{ - struct platform_data *pdata = platform_get_drvdata(pdev); - int i; - - for (i = MAX_CORE_DATA - 1; i >= 0; --i) - if (pdata->core_data[i]) - coretemp_remove_core(pdata, i); - - ida_destroy(&pdata->ida); - return 0; -} - -static struct platform_driver coretemp_driver = { - .driver = { - .name = DRVNAME, - }, - .probe = coretemp_probe, - .remove = coretemp_remove, -}; - -static struct platform_device *coretemp_device_add(unsigned int cpu) -{ - int err, zoneid = topology_logical_die_id(cpu); - struct platform_device *pdev; - - if (zoneid < 0) - return ERR_PTR(-ENOMEM); pdev = platform_device_alloc(DRVNAME, zoneid); - if (!pdev) - return ERR_PTR(-ENOMEM); - - err = platform_device_add(pdev); - if (err) { - platform_device_put(pdev); - return ERR_PTR(err); + if (!pdev) { + err = -ENOMEM; + goto err_free_pdata; } + err = platform_device_add(pdev); + if (err) + goto err_put_dev; + + platform_set_drvdata(pdev, pdata); zone_devices[zoneid] = pdev; - return pdev; + return 0; + +err_put_dev: + platform_device_put(pdev); +err_free_pdata: + kfree(pdata); + return err; +} + +static void coretemp_device_remove(int zoneid) +{ + struct platform_device *pdev = zone_devices[zoneid]; + struct platform_data *pdata = platform_get_drvdata(pdev); + + ida_destroy(&pdata->ida); + kfree(pdata); + platform_device_unregister(pdev); } static int coretemp_cpu_online(unsigned int cpu) @@ -633,7 +616,10 @@ static int coretemp_cpu_online(unsigned int cpu) if (!cpu_has(c, X86_FEATURE_DTHERM)) return -ENODEV; - if (!pdev) { + pdata = platform_get_drvdata(pdev); + if (!pdata->hwmon_dev) { + struct device *hwmon; + /* Check the microcode version of the CPU */ if (chk_ucode_version(cpu)) return -EINVAL; @@ -644,9 +630,11 @@ static int coretemp_cpu_online(unsigned int cpu) * online. So, initialize per-pkg data structures and * then bring this core online. */ - pdev = coretemp_device_add(cpu); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); + hwmon = hwmon_device_register_with_groups(&pdev->dev, DRVNAME, + pdata, NULL); + if (IS_ERR(hwmon)) + return PTR_ERR(hwmon); + pdata->hwmon_dev = hwmon; /* * Check whether pkgtemp support is available. @@ -656,7 +644,6 @@ static int coretemp_cpu_online(unsigned int cpu) coretemp_add_core(pdev, cpu, 1); } - pdata = platform_get_drvdata(pdev); /* * Check whether a thread sibling is already online. If not add the * interface for this CPU core. @@ -675,18 +662,14 @@ static int coretemp_cpu_offline(unsigned int cpu) struct temp_data *tdata; int i, indx = -1, target; - /* - * Don't execute this on suspend as the device remove locks - * up the machine. - */ + /* No need to tear down any interfaces for suspend */ if (cpuhp_tasks_frozen) return 0; /* If the physical CPU device does not exist, just return */ - if (!pdev) - return 0; - pd = platform_get_drvdata(pdev); + if (!pd->hwmon_dev) + return 0; for (i = 0; i < NUM_REAL_CORES; i++) { if (pd->cpu_map[i] == topology_core_id(cpu)) { @@ -718,13 +701,14 @@ static int coretemp_cpu_offline(unsigned int cpu) } /* - * If all cores in this pkg are offline, remove the device. This - * will invoke the platform driver remove function, which cleans up - * the rest. + * If all cores in this pkg are offline, remove the interface. */ + tdata = pd->core_data[PKG_SYSFS_ATTR_NO]; if (cpumask_empty(&pd->cpumask)) { - zone_devices[topology_logical_die_id(cpu)] = NULL; - platform_device_unregister(pdev); + if (tdata) + coretemp_remove_core(pd, PKG_SYSFS_ATTR_NO); + hwmon_device_unregister(pd->hwmon_dev); + pd->hwmon_dev = NULL; return 0; } @@ -732,7 +716,6 @@ static int coretemp_cpu_offline(unsigned int cpu) * Check whether this core is the target for the package * interface. We need to assign it to some other cpu. */ - tdata = pd->core_data[PKG_SYSFS_ATTR_NO]; if (tdata && tdata->cpu == cpu) { target = cpumask_first(&pd->cpumask); mutex_lock(&tdata->update_lock); @@ -751,7 +734,7 @@ static enum cpuhp_state coretemp_hp_online; static int __init coretemp_init(void) { - int err; + int i, err; /* * CPUID.06H.EAX[0] indicates whether the CPU has thermal @@ -767,20 +750,22 @@ static int __init coretemp_init(void) if (!zone_devices) return -ENOMEM; - err = platform_driver_register(&coretemp_driver); - if (err) - goto outzone; + for (i = 0; i < max_zones; i++) { + err = coretemp_device_add(i); + if (err) + goto outzone; + } err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hwmon/coretemp:online", coretemp_cpu_online, coretemp_cpu_offline); if (err < 0) - goto outdrv; + goto outzone; coretemp_hp_online = err; return 0; -outdrv: - platform_driver_unregister(&coretemp_driver); outzone: + while (i--) + coretemp_device_remove(i); kfree(zone_devices); return err; } @@ -788,8 +773,11 @@ module_init(coretemp_init) static void __exit coretemp_exit(void) { + int i; + cpuhp_remove_state(coretemp_hp_online); - platform_driver_unregister(&coretemp_driver); + for (i = 0; i < max_zones; i++) + coretemp_device_remove(i); kfree(zone_devices); } module_exit(coretemp_exit) From ca64ebcb45019a1f80c16c4824b4493fa0c24dca Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Fri, 3 Feb 2023 15:27:14 +0200 Subject: [PATCH 1821/4345] pinctrl: at91: use devm_kasprintf() to avoid potential leaks [ Upstream commit 1c4e5c470a56f7f7c649c0c70e603abc1eab15c4 ] Use devm_kasprintf() instead of kasprintf() to avoid any potential leaks. At the moment drivers have no remove functionality thus there is no need for fixes tag. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230203132714.1931596-1-claudiu.beznea@microchip.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-at91-pio4.c | 4 ++-- drivers/pinctrl/pinctrl-at91.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 578b387100d9..d2e2b101978f 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1081,8 +1081,8 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) pin_desc[i].number = i; /* Pin naming convention: P(bank_name)(bank_pin_number). */ - pin_desc[i].name = kasprintf(GFP_KERNEL, "P%c%d", - bank + 'A', line); + pin_desc[i].name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "P%c%d", + bank + 'A', line); group->name = group_names[i] = pin_desc[i].name; group->pin = pin_desc[i].number; diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index 9015486e38c1..52ecd47c18e2 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -1891,7 +1891,7 @@ static int at91_gpio_probe(struct platform_device *pdev) } for (i = 0; i < chip->ngpio; i++) - names[i] = kasprintf(GFP_KERNEL, "pio%c%d", alias_idx + 'A', i); + names[i] = devm_kasprintf(&pdev->dev, GFP_KERNEL, "pio%c%d", alias_idx + 'A', i); chip->names = (const char *const *)names; From 7df5da8e6bcf27f09d74c55e3d6e3b8f7c973307 Mon Sep 17 00:00:00 2001 From: Bastien Nocera Date: Wed, 25 Jan 2023 13:17:22 +0100 Subject: [PATCH 1822/4345] HID: logitech-hidpp: Don't restart communication if not necessary [ Upstream commit 498ba20690357691103de0f766960355247c78be ] Don't stop and restart communication with the device unless we need to modify the connect flags used because of a device quirk. Signed-off-by: Bastien Nocera Link: https://lore.kernel.org/r/20230125121723.3122-1-hadess@hadess.net Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-logitech-hidpp.c | 32 ++++++++++++++++++++------------ 1 file changed, 20 insertions(+), 12 deletions(-) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 66b105162039..f5ea8e1d8445 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3763,6 +3763,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) bool connected; unsigned int connect_mask = HID_CONNECT_DEFAULT; struct hidpp_ff_private_data data; + bool will_restart = false; /* report_fixup needs drvdata to be set before we call hid_parse */ hidpp = devm_kzalloc(&hdev->dev, sizeof(*hidpp), GFP_KERNEL); @@ -3818,6 +3819,10 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) return ret; } + if (hidpp->quirks & HIDPP_QUIRK_DELAYED_INIT || + hidpp->quirks & HIDPP_QUIRK_UNIFYING) + will_restart = true; + INIT_WORK(&hidpp->work, delayed_work_cb); mutex_init(&hidpp->send_mutex); init_waitqueue_head(&hidpp->wait); @@ -3832,7 +3837,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) * Plain USB connections need to actually call start and open * on the transport driver to allow incoming data. */ - ret = hid_hw_start(hdev, 0); + ret = hid_hw_start(hdev, will_restart ? 0 : connect_mask); if (ret) { hid_err(hdev, "hw start failed\n"); goto hid_hw_start_fail; @@ -3869,6 +3874,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) hidpp->wireless_feature_index = 0; else if (ret) goto hid_hw_init_fail; + ret = 0; } if (connected && (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)) { @@ -3883,19 +3889,21 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) hidpp_connect_event(hidpp); - /* Reset the HID node state */ - hid_device_io_stop(hdev); - hid_hw_close(hdev); - hid_hw_stop(hdev); + if (will_restart) { + /* Reset the HID node state */ + hid_device_io_stop(hdev); + hid_hw_close(hdev); + hid_hw_stop(hdev); - if (hidpp->quirks & HIDPP_QUIRK_NO_HIDINPUT) - connect_mask &= ~HID_CONNECT_HIDINPUT; + if (hidpp->quirks & HIDPP_QUIRK_NO_HIDINPUT) + connect_mask &= ~HID_CONNECT_HIDINPUT; - /* Now export the actual inputs and hidraw nodes to the world */ - ret = hid_hw_start(hdev, connect_mask); - if (ret) { - hid_err(hdev, "%s:hid_hw_start returned error\n", __func__); - goto hid_hw_start_fail; + /* Now export the actual inputs and hidraw nodes to the world */ + ret = hid_hw_start(hdev, connect_mask); + if (ret) { + hid_err(hdev, "%s:hid_hw_start returned error\n", __func__); + goto hid_hw_start_fail; + } } if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) { From 861229a52bac05d8259346fe6959d125676b63cb Mon Sep 17 00:00:00 2001 From: Darrell Kavanagh Date: Tue, 14 Feb 2023 16:46:59 +0000 Subject: [PATCH 1823/4345] drm: panel-orientation-quirks: Add quirk for Lenovo IdeaPad Duet 3 10IGL5 [ Upstream commit 38b2d8efd03d2e56431b611e3523f0158306451d ] Another Lenovo convertable where the panel is installed landscape but is reported to the kernel as portrait. Signed-off-by: Darrell Kavanagh Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20230214164659.3583-1-darrell.kavanagh@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_panel_orientation_quirks.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index ce739ba45c55..8768073794fb 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -278,6 +278,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGL"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* Lenovo IdeaPad Duet 3 10IGL5 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Duet 3 10IGL5"), + }, + .driver_data = (void *)&lcd1200x1920_rightside_up, }, { /* Lenovo Yoga Book X90F / X91F / X91L */ .matches = { /* Non exact match to match all versions */ From 52206dd1c77f04093be0dce7c9a6d58634ae6a53 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 16 Feb 2023 15:29:44 -0500 Subject: [PATCH 1824/4345] dm thin: add cond_resched() to various workqueue loops [ Upstream commit e4f80303c2353952e6e980b23914e4214487f2a6 ] Otherwise on resource constrained systems these workqueues may be too greedy. Signed-off-by: Mike Snitzer Signed-off-by: Sasha Levin --- drivers/md/dm-thin.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index f3c519e18a12..c890bb3e5185 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2217,6 +2217,7 @@ static void process_thin_deferred_bios(struct thin_c *tc) throttle_work_update(&pool->throttle); dm_pool_issue_prefetches(pool->pmd); } + cond_resched(); } blk_finish_plug(&plug); } @@ -2299,6 +2300,7 @@ static void process_thin_deferred_cells(struct thin_c *tc) else pool->process_cell(tc, cell); } + cond_resched(); } while (!list_empty(&cells)); } From 9b8047b2100081e42b7c2a513db9bbeac9c25958 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 16 Feb 2023 15:31:08 -0500 Subject: [PATCH 1825/4345] dm cache: add cond_resched() to various workqueue loops [ Upstream commit 76227f6dc805e9e960128bcc6276647361e0827c ] Otherwise on resource constrained systems these workqueues may be too greedy. Signed-off-by: Mike Snitzer Signed-off-by: Sasha Levin --- drivers/md/dm-cache-target.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 9b2aec309801..f98ad4366301 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1883,6 +1883,7 @@ static void process_deferred_bios(struct work_struct *ws) else commit_needed = process_bio(cache, bio) || commit_needed; + cond_resched(); } if (commit_needed) @@ -1905,6 +1906,7 @@ static void requeue_deferred_bios(struct cache *cache) while ((bio = bio_list_pop(&bios))) { bio->bi_status = BLK_STS_DM_REQUEUE; bio_endio(bio); + cond_resched(); } } @@ -1945,6 +1947,8 @@ static void check_migrations(struct work_struct *ws) r = mg_start(cache, op, NULL); if (r) break; + + cond_resched(); } } From 759f6a72bc5aaa44634adbac26e14fac709a3c8b Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 17 Jan 2023 14:38:30 -0500 Subject: [PATCH 1826/4345] nfsd: zero out pointers after putting nfsd_files on COPY setup error [ Upstream commit 1f0001d43d0c0ac2a19a34a914f6595ad97cbc1d ] At first, I thought this might be a source of nfsd_file overputs, but the current callers seem to avoid an extra put when nfsd4_verify_copy returns an error. Still, it's "bad form" to leave the pointers filled out when we don't have a reference to them anymore, and that might lead to bugs later. Zero them out as a defensive coding measure. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/nfs4proc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 735ee8a79870..f82cfe843b99 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1075,8 +1075,10 @@ out: return status; out_put_dst: nfsd_file_put(*dst); + *dst = NULL; out_put_src: nfsd_file_put(*src); + *src = NULL; goto out; } From bf990eebeaa7585326ee7b02ea589480deda1181 Mon Sep 17 00:00:00 2001 From: Jun ASAKA Date: Sat, 17 Dec 2022 11:06:59 +0800 Subject: [PATCH 1827/4345] wifi: rtl8xxxu: fixing transmisison failure for rtl8192eu commit c6015bf3ff1ffb3caa27eb913797438a0fc634a0 upstream. Fixing transmission failure which results in "authentication with ... timed out". This can be fixed by disable the REG_TXPAUSE. Signed-off-by: Jun ASAKA Reviewed-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221217030659.12577-1-JunASAKA@zzy040330.moe Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c index 199e7e031d7d..3b3cb3a6e2e8 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c @@ -1671,6 +1671,11 @@ static void rtl8192e_enable_rf(struct rtl8xxxu_priv *priv) val8 = rtl8xxxu_read8(priv, REG_PAD_CTRL1); val8 &= ~BIT(0); rtl8xxxu_write8(priv, REG_PAD_CTRL1, val8); + + /* + * Fix transmission failure of rtl8192e. + */ + rtl8xxxu_write8(priv, REG_TXPAUSE, 0x00); } struct rtl8xxxu_fileops rtl8192eu_fops = { From e5b643645a9af861b31356374446dc34a8129a4e Mon Sep 17 00:00:00 2001 From: Alper Nebi Yasak Date: Sun, 22 Jan 2023 22:04:31 +0300 Subject: [PATCH 1828/4345] firmware: coreboot: framebuffer: Ignore reserved pixel color bits commit e6acaf25cba14661211bb72181c35dd13b24f5b3 upstream. The coreboot framebuffer doesn't support transparency, its 'reserved' bit field is merely padding for byte/word alignment of pixel colors [1]. When trying to match the framebuffer to a simplefb format, the kernel driver unnecessarily requires the format's transparency bit field to exactly match this padding, even if the former is zero-width. Due to a coreboot bug [2] (fixed upstream), some boards misreport the reserved field's size as equal to its position (0x18 for both on a 'Lick' Chromebook), and the driver fails to probe where it would have otherwise worked fine with e.g. the a8r8g8b8 or x8r8g8b8 formats. Remove the transparency comparison with reserved bits. When the bits-per-pixel and other color components match, transparency will already be in a subset of the reserved field. Not forcing it to match reserved bits allows the driver to work on the boards which misreport the reserved field. It also enables using simplefb formats that don't have transparency bits, although this doesn't currently happen due to format support and ordering in linux/platform_data/simplefb.h. [1] https://review.coreboot.org/plugins/gitiles/coreboot/+/4.19/src/commonlib/include/commonlib/coreboot_tables.h#255 [2] https://review.coreboot.org/plugins/gitiles/coreboot/+/4.13/src/drivers/intel/fsp2_0/graphics.c#82 Signed-off-by: Alper Nebi Yasak Link: https://lore.kernel.org/r/20230122190433.195941-1-alpernebiyasak@gmail.com Cc: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/google/framebuffer-coreboot.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/firmware/google/framebuffer-coreboot.c b/drivers/firmware/google/framebuffer-coreboot.c index 916f26adc595..922c079d13c8 100644 --- a/drivers/firmware/google/framebuffer-coreboot.c +++ b/drivers/firmware/google/framebuffer-coreboot.c @@ -43,9 +43,7 @@ static int framebuffer_probe(struct coreboot_device *dev) fb->green_mask_pos == formats[i].green.offset && fb->green_mask_size == formats[i].green.length && fb->blue_mask_pos == formats[i].blue.offset && - fb->blue_mask_size == formats[i].blue.length && - fb->reserved_mask_pos == formats[i].transp.offset && - fb->reserved_mask_size == formats[i].transp.length) + fb->blue_mask_size == formats[i].blue.length) pdata.format = formats[i].name; } if (!pdata.format) From 66b40f8756d2ef55c60a20831fa5ce28ffdb6f03 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 2 Feb 2023 16:54:27 +0100 Subject: [PATCH 1829/4345] rtc: pm8xxx: fix set-alarm race commit c88db0eff9722fc2b6c4d172a50471d20e08ecc6 upstream. Make sure to disable the alarm before updating the four alarm time registers to avoid spurious alarms during the update. Note that the disable needs to be done outside of the ctrl_reg_lock section to prevent a racing alarm interrupt from disabling the newly set alarm when the lock is released. Fixes: 9a9a54ad7aa2 ("drivers/rtc: add support for Qualcomm PMIC8xxx RTC") Cc: stable@vger.kernel.org # 3.1 Signed-off-by: Johan Hovold Reviewed-by: David Collins Link: https://lore.kernel.org/r/20230202155448.6715-2-johan+linaro@kernel.org Signed-off-by: Alexandre Belloni Signed-off-by: Greg Kroah-Hartman --- drivers/rtc/rtc-pm8xxx.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c index b45ee2cb2c04..3417eef0aca3 100644 --- a/drivers/rtc/rtc-pm8xxx.c +++ b/drivers/rtc/rtc-pm8xxx.c @@ -219,7 +219,6 @@ static int pm8xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) { int rc, i; u8 value[NUM_8_BIT_RTC_REGS]; - unsigned int ctrl_reg; unsigned long secs, irq_flags; struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev); const struct pm8xxx_rtc_regs *regs = rtc_dd->regs; @@ -231,6 +230,11 @@ static int pm8xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) secs >>= 8; } + rc = regmap_update_bits(rtc_dd->regmap, regs->alarm_ctrl, + regs->alarm_en, 0); + if (rc) + return rc; + spin_lock_irqsave(&rtc_dd->ctrl_reg_lock, irq_flags); rc = regmap_bulk_write(rtc_dd->regmap, regs->alarm_rw, value, @@ -240,19 +244,11 @@ static int pm8xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) goto rtc_rw_fail; } - rc = regmap_read(rtc_dd->regmap, regs->alarm_ctrl, &ctrl_reg); - if (rc) - goto rtc_rw_fail; - - if (alarm->enabled) - ctrl_reg |= regs->alarm_en; - else - ctrl_reg &= ~regs->alarm_en; - - rc = regmap_write(rtc_dd->regmap, regs->alarm_ctrl, ctrl_reg); - if (rc) { - dev_err(dev, "Write to RTC alarm control register failed\n"); - goto rtc_rw_fail; + if (alarm->enabled) { + rc = regmap_update_bits(rtc_dd->regmap, regs->alarm_ctrl, + regs->alarm_en, regs->alarm_en); + if (rc) + goto rtc_rw_fail; } dev_dbg(dev, "Alarm Set for h:m:s=%ptRt, y-m-d=%ptRdr\n", From be2dad7bc932216f9db755e92cbfda46b0dfa513 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 25 Jan 2023 10:13:13 -0600 Subject: [PATCH 1830/4345] ipmi_ssif: Rename idle state and check commit 8230831c43a328c2be6d28c65d3f77e14c59986b upstream. Rename the SSIF_IDLE() to IS_SSIF_IDLE(), since that is more clear, and rename SSIF_NORMAL to SSIF_IDLE, since that's more accurate. Cc: stable@vger.kernel.org Signed-off-by: Corey Minyard Signed-off-by: Greg Kroah-Hartman --- drivers/char/ipmi/ipmi_ssif.c | 46 +++++++++++++++++------------------ 1 file changed, 23 insertions(+), 23 deletions(-) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 477139749513..0f2bac24e564 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -92,7 +92,7 @@ #define SSIF_WATCH_WATCHDOG_TIMEOUT msecs_to_jiffies(250) enum ssif_intf_state { - SSIF_NORMAL, + SSIF_IDLE, SSIF_GETTING_FLAGS, SSIF_GETTING_EVENTS, SSIF_CLEARING_FLAGS, @@ -100,8 +100,8 @@ enum ssif_intf_state { /* FIXME - add watchdog stuff. */ }; -#define SSIF_IDLE(ssif) ((ssif)->ssif_state == SSIF_NORMAL \ - && (ssif)->curr_msg == NULL) +#define IS_SSIF_IDLE(ssif) ((ssif)->ssif_state == SSIF_IDLE \ + && (ssif)->curr_msg == NULL) /* * Indexes into stats[] in ssif_info below. @@ -348,9 +348,9 @@ static void return_hosed_msg(struct ssif_info *ssif_info, /* * Must be called with the message lock held. This will release the - * message lock. Note that the caller will check SSIF_IDLE and start a - * new operation, so there is no need to check for new messages to - * start in here. + * message lock. Note that the caller will check IS_SSIF_IDLE and + * start a new operation, so there is no need to check for new + * messages to start in here. */ static void start_clear_flags(struct ssif_info *ssif_info, unsigned long *flags) { @@ -367,7 +367,7 @@ static void start_clear_flags(struct ssif_info *ssif_info, unsigned long *flags) if (start_send(ssif_info, msg, 3) != 0) { /* Error, just go to normal state. */ - ssif_info->ssif_state = SSIF_NORMAL; + ssif_info->ssif_state = SSIF_IDLE; } } @@ -382,7 +382,7 @@ static void start_flag_fetch(struct ssif_info *ssif_info, unsigned long *flags) mb[0] = (IPMI_NETFN_APP_REQUEST << 2); mb[1] = IPMI_GET_MSG_FLAGS_CMD; if (start_send(ssif_info, mb, 2) != 0) - ssif_info->ssif_state = SSIF_NORMAL; + ssif_info->ssif_state = SSIF_IDLE; } static void check_start_send(struct ssif_info *ssif_info, unsigned long *flags, @@ -393,7 +393,7 @@ static void check_start_send(struct ssif_info *ssif_info, unsigned long *flags, flags = ipmi_ssif_lock_cond(ssif_info, &oflags); ssif_info->curr_msg = NULL; - ssif_info->ssif_state = SSIF_NORMAL; + ssif_info->ssif_state = SSIF_IDLE; ipmi_ssif_unlock_cond(ssif_info, flags); ipmi_free_smi_msg(msg); } @@ -407,7 +407,7 @@ static void start_event_fetch(struct ssif_info *ssif_info, unsigned long *flags) msg = ipmi_alloc_smi_msg(); if (!msg) { - ssif_info->ssif_state = SSIF_NORMAL; + ssif_info->ssif_state = SSIF_IDLE; ipmi_ssif_unlock_cond(ssif_info, flags); return; } @@ -430,7 +430,7 @@ static void start_recv_msg_fetch(struct ssif_info *ssif_info, msg = ipmi_alloc_smi_msg(); if (!msg) { - ssif_info->ssif_state = SSIF_NORMAL; + ssif_info->ssif_state = SSIF_IDLE; ipmi_ssif_unlock_cond(ssif_info, flags); return; } @@ -448,9 +448,9 @@ static void start_recv_msg_fetch(struct ssif_info *ssif_info, /* * Must be called with the message lock held. This will release the - * message lock. Note that the caller will check SSIF_IDLE and start a - * new operation, so there is no need to check for new messages to - * start in here. + * message lock. Note that the caller will check IS_SSIF_IDLE and + * start a new operation, so there is no need to check for new + * messages to start in here. */ static void handle_flags(struct ssif_info *ssif_info, unsigned long *flags) { @@ -466,7 +466,7 @@ static void handle_flags(struct ssif_info *ssif_info, unsigned long *flags) /* Events available. */ start_event_fetch(ssif_info, flags); else { - ssif_info->ssif_state = SSIF_NORMAL; + ssif_info->ssif_state = SSIF_IDLE; ipmi_ssif_unlock_cond(ssif_info, flags); } } @@ -579,7 +579,7 @@ static void watch_timeout(struct timer_list *t) if (ssif_info->watch_timeout) { mod_timer(&ssif_info->watch_timer, jiffies + ssif_info->watch_timeout); - if (SSIF_IDLE(ssif_info)) { + if (IS_SSIF_IDLE(ssif_info)) { start_flag_fetch(ssif_info, flags); /* Releases lock */ return; } @@ -782,7 +782,7 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, } switch (ssif_info->ssif_state) { - case SSIF_NORMAL: + case SSIF_IDLE: ipmi_ssif_unlock_cond(ssif_info, flags); if (!msg) break; @@ -800,7 +800,7 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, * Error fetching flags, or invalid length, * just give up for now. */ - ssif_info->ssif_state = SSIF_NORMAL; + ssif_info->ssif_state = SSIF_IDLE; ipmi_ssif_unlock_cond(ssif_info, flags); dev_warn(&ssif_info->client->dev, "Error getting flags: %d %d, %x\n", @@ -835,7 +835,7 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, "Invalid response clearing flags: %x %x\n", data[0], data[1]); } - ssif_info->ssif_state = SSIF_NORMAL; + ssif_info->ssif_state = SSIF_IDLE; ipmi_ssif_unlock_cond(ssif_info, flags); break; @@ -913,7 +913,7 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, } flags = ipmi_ssif_lock_cond(ssif_info, &oflags); - if (SSIF_IDLE(ssif_info) && !ssif_info->stopping) { + if (IS_SSIF_IDLE(ssif_info) && !ssif_info->stopping) { if (ssif_info->req_events) start_event_fetch(ssif_info, flags); else if (ssif_info->req_flags) @@ -1087,7 +1087,7 @@ static void start_next_msg(struct ssif_info *ssif_info, unsigned long *flags) unsigned long oflags; restart: - if (!SSIF_IDLE(ssif_info)) { + if (!IS_SSIF_IDLE(ssif_info)) { ipmi_ssif_unlock_cond(ssif_info, flags); return; } @@ -1310,7 +1310,7 @@ static void shutdown_ssif(void *send_info) dev_set_drvdata(&ssif_info->client->dev, NULL); /* make sure the driver is not looking for flags any more. */ - while (ssif_info->ssif_state != SSIF_NORMAL) + while (ssif_info->ssif_state != SSIF_IDLE) schedule_timeout(1); ssif_info->stopping = true; @@ -1882,7 +1882,7 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id) } spin_lock_init(&ssif_info->lock); - ssif_info->ssif_state = SSIF_NORMAL; + ssif_info->ssif_state = SSIF_IDLE; timer_setup(&ssif_info->retry_timer, retry_timeout, 0); timer_setup(&ssif_info->watch_timer, watch_timeout, 0); From 6cf48403c46ae4f4ac74a439ca2ff2ddb5eab8c5 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 27 Feb 2023 20:03:00 +0100 Subject: [PATCH 1831/4345] s390/extmem: return correct segment type in __segment_load() commit 8c42dd78df148c90e48efff204cce38743906a79 upstream. Commit f05f62d04271f ("s390/vmem: get rid of memory segment list") reshuffled the call to vmem_add_mapping() in __segment_load(), which now overwrites rc after it was set to contain the segment type code. As result, __segment_load() will now always return 0 on success, which corresponds to the segment type code SEG_TYPE_SW, i.e. a writeable segment. This results in a kernel crash when loading a read-only segment as dcssblk block device, and trying to write to it. Instead of reshuffling code again, make sure to return the segment type on success, and also describe this rather delicate and unexpected logic in the function comment. Also initialize new segtype variable with invalid value, to prevent possible future confusion. Fixes: f05f62d04271 ("s390/vmem: get rid of memory segment list") Cc: # 5.9+ Signed-off-by: Gerald Schaefer Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- arch/s390/mm/extmem.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 5060956b8e7d..1bc42ce26599 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -289,15 +289,17 @@ segment_overlaps_others (struct dcss_segment *seg) /* * real segment loading function, called from segment_load + * Must return either an error code < 0, or the segment type code >= 0 */ static int __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long *end) { unsigned long start_addr, end_addr, dummy; struct dcss_segment *seg; - int rc, diag_cc; + int rc, diag_cc, segtype; start_addr = end_addr = 0; + segtype = -1; seg = kmalloc(sizeof(*seg), GFP_KERNEL | GFP_DMA); if (seg == NULL) { rc = -ENOMEM; @@ -326,9 +328,9 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long seg->res_name[8] = '\0'; strlcat(seg->res_name, " (DCSS)", sizeof(seg->res_name)); seg->res->name = seg->res_name; - rc = seg->vm_segtype; - if (rc == SEG_TYPE_SC || - ((rc == SEG_TYPE_SR || rc == SEG_TYPE_ER) && !do_nonshared)) + segtype = seg->vm_segtype; + if (segtype == SEG_TYPE_SC || + ((segtype == SEG_TYPE_SR || segtype == SEG_TYPE_ER) && !do_nonshared)) seg->res->flags |= IORESOURCE_READONLY; /* Check for overlapping resources before adding the mapping. */ @@ -386,7 +388,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long out_free: kfree(seg); out: - return rc; + return rc < 0 ? rc : segtype; } /* From d43abcf91c5ed55443d26cd8c7721bd8409a7aff Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Mon, 23 Jan 2023 22:50:32 +0100 Subject: [PATCH 1832/4345] s390: discard .interp section commit e9c9cb90e76ffaabcc7ca8f275d9e82195fd6367 upstream. When debugging vmlinux with QEMU + GDB, the following GDB error may occur: (gdb) c Continuing. Warning: Cannot insert breakpoint -1. Cannot access memory at address 0xffffffffffff95c0 Command aborted. (gdb) The reason is that, when .interp section is present, GDB tries to locate the file specified in it in memory and put a number of breakpoints there (see enable_break() function in gdb/solib-svr4.c). Sometimes GDB finds a bogus location that matches its heuristics, fails to set a breakpoint and stops. This makes further debugging impossible. The .interp section contains misleading information anyway (vmlinux does not need ld.so), so fix by discarding it. Signed-off-by: Ilya Leoshkevich Cc: Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/vmlinux.lds.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 9505bdb0aa54..d7291eb0d0c0 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -188,5 +188,6 @@ SECTIONS DISCARDS /DISCARD/ : { *(.eh_frame) + *(.interp) } } From d8724dc0ce7642081b399ad5c1009cc4964d8ac7 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 1 Mar 2023 02:23:08 +0100 Subject: [PATCH 1833/4345] s390/kprobes: fix irq mask clobbering on kprobe reenter from post_handler commit 42e19e6f04984088b6f9f0507c4c89a8152d9730 upstream. Recent test_kprobe_missed kprobes kunit test uncovers the following error (reported when CONFIG_DEBUG_ATOMIC_SLEEP is enabled): BUG: sleeping function called from invalid context at kernel/locking/mutex.c:580 in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 662, name: kunit_try_catch preempt_count: 0, expected: 0 RCU nest depth: 0, expected: 0 no locks held by kunit_try_catch/662. irq event stamp: 280 hardirqs last enabled at (279): [<00000003e60a3d42>] __do_pgm_check+0x17a/0x1c0 hardirqs last disabled at (280): [<00000003e3bd774a>] kprobe_exceptions_notify+0x27a/0x318 softirqs last enabled at (0): [<00000003e3c5c890>] copy_process+0x14a8/0x4c80 softirqs last disabled at (0): [<0000000000000000>] 0x0 CPU: 46 PID: 662 Comm: kunit_try_catch Tainted: G N 6.2.0-173644-g44c18d77f0c0 #2 Hardware name: IBM 3931 A01 704 (LPAR) Call Trace: [<00000003e60a3a00>] dump_stack_lvl+0x120/0x198 [<00000003e3d02e82>] __might_resched+0x60a/0x668 [<00000003e60b9908>] __mutex_lock+0xc0/0x14e0 [<00000003e60bad5a>] mutex_lock_nested+0x32/0x40 [<00000003e3f7b460>] unregister_kprobe+0x30/0xd8 [<00000003e51b2602>] test_kprobe_missed+0xf2/0x268 [<00000003e51b5406>] kunit_try_run_case+0x10e/0x290 [<00000003e51b7dfa>] kunit_generic_run_threadfn_adapter+0x62/0xb8 [<00000003e3ce30f8>] kthread+0x2d0/0x398 [<00000003e3b96afa>] __ret_from_fork+0x8a/0xe8 [<00000003e60ccada>] ret_from_fork+0xa/0x40 The reason for this error report is that kprobes handling code failed to restore irqs. The problem is that when kprobe is triggered from another kprobe post_handler current sequence of enable_singlestep / disable_singlestep is the following: enable_singlestep <- original kprobe (saves kprobe_saved_imask) enable_singlestep <- kprobe triggered from post_handler (clobbers kprobe_saved_imask) disable_singlestep <- kprobe triggered from post_handler (restores kprobe_saved_imask) disable_singlestep <- original kprobe (restores wrong clobbered kprobe_saved_imask) There is just one kprobe_ctlblk per cpu and both calls saves and loads irq mask to kprobe_saved_imask. To fix the problem simply move resume_execution (which calls disable_singlestep) before calling post_handler. This also fixes the problem that post_handler is called with pt_regs which were not yet adjusted after single-stepping. Cc: stable@vger.kernel.org Fixes: 4ba069b802c2 ("[S390] add kprobes support.") Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/kprobes.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index aae24dc75df6..4f0d5ead3547 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -402,12 +402,11 @@ static int post_kprobe_handler(struct pt_regs *regs) if (!p) return 0; + resume_execution(p, regs); if (kcb->kprobe_status != KPROBE_REENTER && p->post_handler) { kcb->kprobe_status = KPROBE_HIT_SSDONE; p->post_handler(p, regs, 0); } - - resume_execution(p, regs); pop_kprobe(kcb); preempt_enable_no_resched(); From 59102ded74805820e5114ead1f7bb5a84bc029e2 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 1 Mar 2023 17:58:06 +0100 Subject: [PATCH 1834/4345] s390/kprobes: fix current_kprobe never cleared after kprobes reenter commit cd57953936f2213dfaccce10d20f396956222c7d upstream. Recent test_kprobe_missed kprobes kunit test uncovers the following problem. Once kprobe is triggered from another kprobe (kprobe reenter), all future kprobes on this cpu are considered as kprobe reenter, thus pre_handler and post_handler are not being called and kprobes are counted as "missed". Commit b9599798f953 ("[S390] kprobes: activation and deactivation") introduced a simpler scheme for kprobes (de)activation and status tracking by using push_kprobe/pop_kprobe, which supposed to work for both initial kprobe entry as well as kprobe reentry and helps to avoid handling those two cases differently. The problem is that a sequence of calls in case of kprobes reenter: push_kprobe() <- NULL (current_kprobe) push_kprobe() <- kprobe1 (current_kprobe) pop_kprobe() -> kprobe1 (current_kprobe) pop_kprobe() -> kprobe1 (current_kprobe) leaves "kprobe1" as "current_kprobe" on this cpu, instead of setting it to NULL. In fact push_kprobe/pop_kprobe can only store a single state (there is just one prev_kprobe in kprobe_ctlblk). Which is a hack but sufficient, there is no need to have another prev_kprobe just to store NULL. To make a simple and backportable fix simply reset "prev_kprobe" when kprobe is poped from this "stack". No need to worry about "kprobe_status" in this case, because its value is only checked when current_kprobe != NULL. Cc: stable@vger.kernel.org Fixes: b9599798f953 ("[S390] kprobes: activation and deactivation") Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/kprobes.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 4f0d5ead3547..0f7e7a68d57b 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -241,6 +241,7 @@ static void pop_kprobe(struct kprobe_ctlblk *kcb) { __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; + kcb->prev_kprobe.kp = NULL; } NOKPROBE_SYMBOL(pop_kprobe); From 69493675fdfb81192981bf106533c248cc980752 Mon Sep 17 00:00:00 2001 From: Volker Lendecke Date: Wed, 11 Jan 2023 12:37:58 +0100 Subject: [PATCH 1835/4345] cifs: Fix uninitialized memory read in smb3_qfs_tcon() commit d447e794a37288ec7a080aa1b044a8d9deebbab7 upstream. oparms was not fully initialized Signed-off-by: Volker Lendecke Reviewed-by: Paulo Alcantara (SUSE) Cc: stable@vger.kernel.org Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/smb2ops.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 844db4652dd1..8fdd34ff20ef 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -859,12 +859,13 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon, bool no_cached_open = tcon->nohandlecache; struct cached_fid *cfid = NULL; - oparms.tcon = tcon; - oparms.desired_access = FILE_READ_ATTRIBUTES; - oparms.disposition = FILE_OPEN; - oparms.create_options = cifs_create_options(cifs_sb, 0); - oparms.fid = &fid; - oparms.reconnect = false; + oparms = (struct cifs_open_parms) { + .tcon = tcon, + .desired_access = FILE_READ_ATTRIBUTES, + .disposition = FILE_OPEN, + .create_options = cifs_create_options(cifs_sb, 0), + .fid = &fid, + }; if (no_cached_open) { rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, From 300b6404e60161355bca54552ae38b49c3bbf63d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 25 Jan 2023 10:45:05 +0100 Subject: [PATCH 1836/4345] ARM: dts: exynos: correct HDMI phy compatible in Exynos4 commit af1c89ddb74f170eccd5a57001d7317560b638ea upstream. The HDMI phy compatible was missing vendor prefix. Fixes: ed80d4cab772 ("ARM: dts: add hdmi related nodes for exynos4 SoCs") Cc: Link: https://lore.kernel.org/r/20230125094513.155063-1-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos4.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi index a1e54449f33f..41f0e64b1365 100644 --- a/arch/arm/boot/dts/exynos4.dtsi +++ b/arch/arm/boot/dts/exynos4.dtsi @@ -605,7 +605,7 @@ status = "disabled"; hdmi_i2c_phy: hdmiphy@38 { - compatible = "exynos4210-hdmiphy"; + compatible = "samsung,exynos4210-hdmiphy"; reg = <0x38>; }; }; From dc9f78b6d254427a06e568f2887b1011ef3143ef Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Mon, 12 Dec 2022 10:16:27 +0800 Subject: [PATCH 1837/4345] hfs: fix missing hfs_bnode_get() in __hfs_bnode_create commit a9dc087fd3c484fd1ed18c5efb290efaaf44ce03 upstream. Syzbot found a kernel BUG in hfs_bnode_put(): kernel BUG at fs/hfs/bnode.c:466! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 3634 Comm: kworker/u4:5 Not tainted 6.1.0-rc7-syzkaller-00190-g97ee9d1c1696 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Workqueue: writeback wb_workfn (flush-7:0) RIP: 0010:hfs_bnode_put+0x46f/0x480 fs/hfs/bnode.c:466 Code: 8a 80 ff e9 73 fe ff ff 89 d9 80 e1 07 80 c1 03 38 c1 0f 8c a0 fe ff ff 48 89 df e8 db 8a 80 ff e9 93 fe ff ff e8 a1 68 2c ff <0f> 0b e8 9a 68 2c ff 0f 0b 0f 1f 84 00 00 00 00 00 55 41 57 41 56 RSP: 0018:ffffc90003b4f258 EFLAGS: 00010293 RAX: ffffffff825e318f RBX: 0000000000000000 RCX: ffff8880739dd7c0 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffc90003b4f430 R08: ffffffff825e2d9b R09: ffffed10045157d1 R10: ffffed10045157d1 R11: 1ffff110045157d0 R12: ffff8880228abe80 R13: ffff88807016c000 R14: dffffc0000000000 R15: ffff8880228abe00 FS: 0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fa6ebe88718 CR3: 000000001e93d000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: hfs_write_inode+0x1bc/0xb40 write_inode fs/fs-writeback.c:1440 [inline] __writeback_single_inode+0x4d6/0x670 fs/fs-writeback.c:1652 writeback_sb_inodes+0xb3b/0x18f0 fs/fs-writeback.c:1878 __writeback_inodes_wb+0x125/0x420 fs/fs-writeback.c:1949 wb_writeback+0x440/0x7b0 fs/fs-writeback.c:2054 wb_check_start_all fs/fs-writeback.c:2176 [inline] wb_do_writeback fs/fs-writeback.c:2202 [inline] wb_workfn+0x827/0xef0 fs/fs-writeback.c:2235 process_one_work+0x877/0xdb0 kernel/workqueue.c:2289 worker_thread+0xb14/0x1330 kernel/workqueue.c:2436 kthread+0x266/0x300 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 The BUG_ON() is triggered at here: /* Dispose of resources used by a node */ void hfs_bnode_put(struct hfs_bnode *node) { if (node) { BUG_ON(!atomic_read(&node->refcnt)); <- we have issue here!!!! } } By tracing the refcnt, I found the node is created by hfs_bmap_alloc() with refcnt 1. Then the node is used by hfs_btree_write(). There is a missing of hfs_bnode_get() after find the node. The issue happened in following path: hfs_bmap_alloc hfs_bnode_find __hfs_bnode_create <- allocate a new node with refcnt 1. hfs_bnode_put <- decrease the refcnt hfs_btree_write hfs_bnode_find __hfs_bnode_create hfs_bnode_findhash <- find the node without refcnt increased. hfs_bnode_put <- trigger the BUG_ON() since refcnt is 0. Link: https://lkml.kernel.org/r/20221212021627.3766829-1-liushixin2@huawei.com Reported-by: syzbot+5b04b49a7ec7226c7426@syzkaller.appspotmail.com Signed-off-by: Liu Shixin Cc: Fabio M. De Francesco Cc: Viacheslav Dubeyko Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/hfs/bnode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index c0a73a6ffb28..397e02a56697 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -281,6 +281,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) tree->node_hash[hash] = node; tree->node_hash_cnt++; } else { + hfs_bnode_get(node2); spin_unlock(&tree->hash_lock); kfree(node); wait_event(node2->lock_wq, !test_bit(HFS_BNODE_NEW, &node2->flags)); From ef7d71d7bd57b8b7fe514e459927696c1c6d1047 Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Sun, 26 Feb 2023 20:49:47 +0800 Subject: [PATCH 1838/4345] fs: hfsplus: fix UAF issue in hfsplus_put_super commit 07db5e247ab5858439b14dd7cc1fe538b9efcf32 upstream. The current hfsplus_put_super first calls hfs_btree_close on sbi->ext_tree, then invokes iput on sbi->hidden_dir, resulting in an use-after-free issue in hfsplus_release_folio. As shown in hfsplus_fill_super, the error handling code also calls iput before hfs_btree_close. To fix this error, we move all iput calls before hfsplus_btree_close. Note that this patch is tested on Syzbot. Link: https://lkml.kernel.org/r/20230226124948.3175736-1-mudongliangabcd@gmail.com Reported-by: syzbot+57e3e98f7e3b80f64d56@syzkaller.appspotmail.com Tested-by: Dongliang Mu Signed-off-by: Dongliang Mu Cc: Bart Van Assche Cc: Jens Axboe Cc: Muchun Song Cc: Roman Gushchin Cc: "Theodore Ts'o" Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/hfsplus/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 807119ae5adf..7648f64a17a8 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -295,11 +295,11 @@ static void hfsplus_put_super(struct super_block *sb) hfsplus_sync_fs(sb, 1); } + iput(sbi->alloc_file); + iput(sbi->hidden_dir); hfs_btree_close(sbi->attr_tree); hfs_btree_close(sbi->cat_tree); hfs_btree_close(sbi->ext_tree); - iput(sbi->alloc_file); - iput(sbi->hidden_dir); kfree(sbi->s_vhdr_buf); kfree(sbi->s_backup_vhdr_buf); unload_nls(sbi->nls); From 34b05883414cc97e4c592988bb45225aede4ff63 Mon Sep 17 00:00:00 2001 From: Yuezhang Mo Date: Thu, 20 Oct 2022 14:27:37 +0800 Subject: [PATCH 1839/4345] exfat: fix reporting fs error when reading dir beyond EOF commit 706fdcac002316893434d753be8cfb549fe1d40d upstream. Since seekdir() does not check whether the position is valid, the position may exceed the size of the directory. We found that for a directory with discontinuous clusters, if the position exceeds the size of the directory and the excess size is greater than or equal to the cluster size, exfat_readdir() will return -EIO, causing a file system error and making the file system unavailable. Reproduce this bug by: seekdir(dir, dir_size + cluster_size); dirent = readdir(dir); The following log will be printed if mount with 'errors=remount-ro'. [11166.712896] exFAT-fs (sdb1): error, invalid access to FAT (entry 0xffffffff) [11166.712905] exFAT-fs (sdb1): Filesystem has been set read-only Fixes: 1e5654de0f51 ("exfat: handle wrong stream entry size in exfat_readdir()") Cc: stable@vger.kernel.org # v5.7+ Signed-off-by: Yuezhang Mo Reviewed-by: Andy Wu Reviewed-by: Aoyama Wataru Reviewed-by: Sungjong Seo Signed-off-by: Namjae Jeon Signed-off-by: Greg Kroah-Hartman --- fs/exfat/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index dedbc55cd48f..09c5ea4c4556 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -102,7 +102,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent clu.dir = ei->hint_bmap.clu; } - while (clu_offset > 0) { + while (clu_offset > 0 && clu.dir != EXFAT_EOF_CLUSTER) { if (exfat_get_next_cluster(sb, &(clu.dir))) return -EIO; From c2d1997074ce3207cd779c26bc8b32b077d93085 Mon Sep 17 00:00:00 2001 From: Yuezhang Mo Date: Thu, 22 Sep 2022 14:43:47 +0800 Subject: [PATCH 1840/4345] exfat: fix unexpected EOF while reading dir commit 6cb5d1a16a51d080fbc1649a5144cbc5ca7d6f88 upstream. If the position is not aligned with the dentry size, the return value of readdir() will be NULL and errno is 0, which means the end of the directory stream is reached. If the position is aligned with dentry size, but there is no file or directory at the position, exfat_readdir() will continue to get dentry from the next dentry. So the dentry gotten by readdir() may not be at the position. After this commit, if the position is not aligned with the dentry size, round the position up to the dentry size and continue to get the dentry. Fixes: ca06197382bd ("exfat: add directory operations") Cc: stable@vger.kernel.org # v5.7+ Reported-by: Wang Yugui Signed-off-by: Yuezhang Mo Reviewed-by: Andy Wu Reviewed-by: Aoyama Wataru Reviewed-by: Sungjong Seo Signed-off-by: Namjae Jeon Signed-off-by: Greg Kroah-Hartman --- fs/exfat/dir.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 09c5ea4c4556..6caded58cda5 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -236,10 +236,7 @@ static int exfat_iterate(struct file *filp, struct dir_context *ctx) fake_offset = 1; } - if (cpos & (DENTRY_SIZE - 1)) { - err = -ENOENT; - goto unlock; - } + cpos = round_up(cpos, DENTRY_SIZE); /* name buffer should be allocated before use */ err = exfat_alloc_namebuf(nb); From 4017209e08d23ab6f52f51caa7a81df23a7fd8f8 Mon Sep 17 00:00:00 2001 From: Sungjong Seo Date: Thu, 29 Dec 2022 20:52:38 +0900 Subject: [PATCH 1841/4345] exfat: redefine DIR_DELETED as the bad cluster number commit bdaadfd343e3cba49ad0b009ff4b148dad0fa404 upstream. When a file or a directory is deleted, the hint for the cluster of its parent directory in its in-memory inode is set as DIR_DELETED. Therefore, DIR_DELETED must be one of invalid cluster numbers. According to the exFAT specification, a volume can have at most 2^32-11 clusters. However, DIR_DELETED is wrongly defined as 0xFFFF0321, which could be a valid cluster number. To fix it, let's redefine DIR_DELETED as 0xFFFFFFF7, the bad cluster number. Fixes: 1acf1a564b60 ("exfat: add in-memory and on-disk structures and headers") Cc: stable@vger.kernel.org # v5.7+ Reported-by: Yuezhang Mo Signed-off-by: Sungjong Seo Signed-off-by: Namjae Jeon Signed-off-by: Greg Kroah-Hartman --- fs/exfat/exfat_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 0d139c7d150d..07b09af57436 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -42,7 +42,7 @@ enum { #define ES_2_ENTRIES 2 #define ES_ALL_ENTRIES 0 -#define DIR_DELETED 0xFFFF0321 +#define DIR_DELETED 0xFFFFFFF7 /* type values */ #define TYPE_UNUSED 0x0000 From f9dbc35ecb9431d1396f550c4a471486e3133b68 Mon Sep 17 00:00:00 2001 From: Yuezhang Mo Date: Wed, 4 Jan 2023 14:37:47 +0800 Subject: [PATCH 1842/4345] exfat: fix inode->i_blocks for non-512 byte sector size device commit 39c1ce8eafc0ff64fb9e28536ccc7df6a8e2999d upstream. inode->i_blocks is not real number of blocks, but 512 byte ones. Fixes: 98d917047e8b ("exfat: add file operations") Cc: stable@vger.kernel.org # v5.7+ Reported-by: Wang Yugui Tested-by: Wang Yugui Signed-off-by: Yuezhang Mo Reviewed-by: Andy Wu Signed-off-by: Namjae Jeon Signed-off-by: Greg Kroah-Hartman --- fs/exfat/file.c | 3 +-- fs/exfat/inode.c | 6 ++---- fs/exfat/namei.c | 2 +- fs/exfat/super.c | 3 +-- 4 files changed, 5 insertions(+), 9 deletions(-) diff --git a/fs/exfat/file.c b/fs/exfat/file.c index c819e8427ea5..819f47278305 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -250,8 +250,7 @@ void exfat_truncate(struct inode *inode, loff_t size) else mark_inode_dirty(inode); - inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> - inode->i_blkbits; + inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; write_size: aligned_size = i_size_read(inode); if (aligned_size & (blocksize - 1)) { diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index 2a9f6a80584e..4bd73820a4ac 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -242,8 +242,7 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, return err; } /* end of if != DIR_DELETED */ - inode->i_blocks += - num_to_be_allocated << sbi->sect_per_clus_bits; + inode->i_blocks += EXFAT_CLU_TO_B(num_to_be_allocated, sbi) >> 9; /* * Move *clu pointer along FAT chains (hole care) because the @@ -600,8 +599,7 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) exfat_save_attr(inode, info->attr); - inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> - inode->i_blkbits; + inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; inode->i_mtime = info->mtime; inode->i_ctime = info->mtime; ei->i_crtime = info->crtime; diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 935f60050900..1382d816912c 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -398,7 +398,7 @@ static int exfat_find_empty_entry(struct inode *inode, ei->i_size_ondisk += sbi->cluster_size; ei->i_size_aligned += sbi->cluster_size; ei->flags = p_dir->flags; - inode->i_blocks += 1 << sbi->sect_per_clus_bits; + inode->i_blocks += sbi->cluster_size >> 9; } return dentry; diff --git a/fs/exfat/super.c b/fs/exfat/super.c index ba70ed1c9804..62d79af257a9 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -364,8 +364,7 @@ static int exfat_read_root(struct inode *inode) inode->i_op = &exfat_dir_inode_operations; inode->i_fop = &exfat_dir_operations; - inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> - inode->i_blkbits; + inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; ei->i_pos = ((loff_t)sbi->root_dir << 32) | 0xffffffff; ei->i_size_aligned = i_size_read(inode); ei->i_size_ondisk = i_size_read(inode); From 00b5587326625d0fddb2a5f5a3d4acd950102ace Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 22 Jan 2023 23:04:14 -0800 Subject: [PATCH 1843/4345] f2fs: fix information leak in f2fs_move_inline_dirents() commit 9a5571cff4ffcfc24847df9fd545cc5799ac0ee5 upstream. When converting an inline directory to a regular one, f2fs is leaking uninitialized memory to disk because it doesn't initialize the entire directory block. Fix this by zero-initializing the block. This bug was introduced by commit 4ec17d688d74 ("f2fs: avoid unneeded initializing when converting inline dentry"), which didn't consider the security implications of leaking uninitialized memory to disk. This was found by running xfstest generic/435 on a KMSAN-enabled kernel. Fixes: 4ec17d688d74 ("f2fs: avoid unneeded initializing when converting inline dentry") Cc: # v4.3+ Signed-off-by: Eric Biggers Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/inline.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index f97c23ec93ce..4e794c1390cc 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -420,18 +420,17 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, dentry_blk = page_address(page); + /* + * Start by zeroing the full block, to ensure that all unused space is + * zeroed and no uninitialized memory is leaked to disk. + */ + memset(dentry_blk, 0, F2FS_BLKSIZE); + make_dentry_ptr_inline(dir, &src, inline_dentry); make_dentry_ptr_block(dir, &dst, dentry_blk); /* copy data from inline dentry block to new dentry block */ memcpy(dst.bitmap, src.bitmap, src.nr_bitmap); - memset(dst.bitmap + src.nr_bitmap, 0, dst.nr_bitmap - src.nr_bitmap); - /* - * we do not need to zero out remainder part of dentry and filename - * field, since we have used bitmap for marking the usage status of - * them, besides, we can also ignore copying/zeroing reserved space - * of dentry block, because them haven't been used so far. - */ memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max); memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN); From e9f20138b5fb1a70e3ff5b50606f65e4461eda9e Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 2 Feb 2023 17:02:39 -0800 Subject: [PATCH 1844/4345] f2fs: fix cgroup writeback accounting with fs-layer encryption commit 844545c51a5b2a524b22a2fe9d0b353b827d24b4 upstream. When writing a page from an encrypted file that is using filesystem-layer encryption (not inline encryption), f2fs encrypts the pagecache page into a bounce page, then writes the bounce page. It also passes the bounce page to wbc_account_cgroup_owner(). That's incorrect, because the bounce page is a newly allocated temporary page that doesn't have the memory cgroup of the original pagecache page. This makes wbc_account_cgroup_owner() not account the I/O to the owner of the pagecache page as it should. Fix this by always passing the pagecache page to wbc_account_cgroup_owner(). Fixes: 578c647879f7 ("f2fs: implement cgroup writeback support") Cc: stable@vger.kernel.org Reported-by: Matthew Wilcox (Oracle) Signed-off-by: Eric Biggers Acked-by: Tejun Heo Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/data.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9270330ec5ce..db26e87b8f0d 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -721,7 +721,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) } if (fio->io_wbc && !is_read_io(fio->op)) - wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE); + wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); __attach_io_flag(fio); bio_set_op_attrs(bio, fio->op, fio->op_flags); @@ -929,7 +929,7 @@ alloc_new: } if (fio->io_wbc) - wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE); + wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); inc_page_count(fio->sbi, WB_DATA_TYPE(page)); @@ -1003,7 +1003,7 @@ alloc_new: } if (fio->io_wbc) - wbc_account_cgroup_owner(fio->io_wbc, bio_page, PAGE_SIZE); + wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); io->last_block_in_bio = fio->new_blkaddr; f2fs_trace_ios(fio, 0); From 2c559b3ba8e0b9e3c4bb08159a28ccadc698410f Mon Sep 17 00:00:00 2001 From: Heming Zhao via Ocfs2-devel Date: Fri, 17 Feb 2023 08:37:17 +0800 Subject: [PATCH 1845/4345] ocfs2: fix defrag path triggering jbd2 ASSERT commit 60eed1e3d45045623e46944ebc7c42c30a4350f0 upstream. code path: ocfs2_ioctl_move_extents ocfs2_move_extents ocfs2_defrag_extent __ocfs2_move_extent + ocfs2_journal_access_di + ocfs2_split_extent //sub-paths call jbd2_journal_restart + ocfs2_journal_dirty //crash by jbs2 ASSERT crash stacks: PID: 11297 TASK: ffff974a676dcd00 CPU: 67 COMMAND: "defragfs.ocfs2" #0 [ffffb25d8dad3900] machine_kexec at ffffffff8386fe01 #1 [ffffb25d8dad3958] __crash_kexec at ffffffff8395959d #2 [ffffb25d8dad3a20] crash_kexec at ffffffff8395a45d #3 [ffffb25d8dad3a38] oops_end at ffffffff83836d3f #4 [ffffb25d8dad3a58] do_trap at ffffffff83833205 #5 [ffffb25d8dad3aa0] do_invalid_op at ffffffff83833aa6 #6 [ffffb25d8dad3ac0] invalid_op at ffffffff84200d18 [exception RIP: jbd2_journal_dirty_metadata+0x2ba] RIP: ffffffffc09ca54a RSP: ffffb25d8dad3b70 RFLAGS: 00010207 RAX: 0000000000000000 RBX: ffff9706eedc5248 RCX: 0000000000000000 RDX: 0000000000000001 RSI: ffff97337029ea28 RDI: ffff9706eedc5250 RBP: ffff9703c3520200 R8: 000000000f46b0b2 R9: 0000000000000000 R10: 0000000000000001 R11: 00000001000000fe R12: ffff97337029ea28 R13: 0000000000000000 R14: ffff9703de59bf60 R15: ffff9706eedc5250 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ffffb25d8dad3ba8] ocfs2_journal_dirty at ffffffffc137fb95 [ocfs2] #8 [ffffb25d8dad3be8] __ocfs2_move_extent at ffffffffc139a950 [ocfs2] #9 [ffffb25d8dad3c80] ocfs2_defrag_extent at ffffffffc139b2d2 [ocfs2] Analysis This bug has the same root cause of 'commit 7f27ec978b0e ("ocfs2: call ocfs2_journal_access_di() before ocfs2_journal_dirty() in ocfs2_write_end_nolock()")'. For this bug, jbd2_journal_restart() is called by ocfs2_split_extent() during defragmenting. How to fix For ocfs2_split_extent() can handle journal operations totally by itself. Caller doesn't need to call journal access/dirty pair, and caller only needs to call journal start/stop pair. The fix method is to remove journal access/dirty from __ocfs2_move_extent(). The discussion for this patch: https://oss.oracle.com/pipermail/ocfs2-devel/2023-February/000647.html Link: https://lkml.kernel.org/r/20230217003717.32469-1-heming.zhao@suse.com Signed-off-by: Heming Zhao Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/move_extents.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 758d9661ef1e..e2742546a977 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -107,14 +107,6 @@ static int __ocfs2_move_extent(handle_t *handle, */ replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED; - ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), - context->et.et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (ret) { - mlog_errno(ret); - goto out; - } - ret = ocfs2_split_extent(handle, &context->et, path, index, &replace_rec, context->meta_ac, &context->dealloc); @@ -123,8 +115,6 @@ static int __ocfs2_move_extent(handle_t *handle, goto out; } - ocfs2_journal_dirty(handle, context->et.et_root_bh); - context->new_phys_cpos = new_p_cpos; /* From 6bf9caa58526eef67411733f4f26e6c13cfb94a4 Mon Sep 17 00:00:00 2001 From: Heming Zhao via Ocfs2-devel Date: Mon, 20 Feb 2023 13:05:26 +0800 Subject: [PATCH 1846/4345] ocfs2: fix non-auto defrag path not working issue commit 236b9254f8d1edc273ad88b420aa85fbd84f492d upstream. This fixes three issues on move extents ioctl without auto defrag: a) In ocfs2_find_victim_alloc_group(), we have to convert bits to block first in case of global bitmap. b) In ocfs2_probe_alloc_group(), when finding enough bits in block group bitmap, we have to back off move_len to start pos as well, otherwise it may corrupt filesystem. c) In ocfs2_ioctl_move_extents(), set me_threshold both for non-auto and auto defrag paths. Otherwise it will set move_max_hop to 0 and finally cause unexpectedly ENOSPC error. Currently there are no tools triggering the above issues since defragfs.ocfs2 enables auto defrag by default. Tested with manually changing defragfs.ocfs2 to run non auto defrag path. Link: https://lkml.kernel.org/r/20230220050526.22020-1-heming.zhao@suse.com Signed-off-by: Heming Zhao Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/move_extents.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index e2742546a977..98e77ea957ff 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -436,7 +436,7 @@ static int ocfs2_find_victim_alloc_group(struct inode *inode, bg = (struct ocfs2_group_desc *)gd_bh->b_data; if (vict_blkno < (le64_to_cpu(bg->bg_blkno) + - le16_to_cpu(bg->bg_bits))) { + (le16_to_cpu(bg->bg_bits) << bits_per_unit))) { *ret_bh = gd_bh; *vict_bit = (vict_blkno - blkno) >> @@ -551,6 +551,7 @@ static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh, last_free_bits++; if (last_free_bits == move_len) { + i -= move_len; *goal_bit = i; *phys_cpos = base_cpos + i; break; @@ -1022,18 +1023,19 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) context->range = ⦥ + /* + * ok, the default theshold for the defragmentation + * is 1M, since our maximum clustersize was 1M also. + * any thought? + */ + if (!range.me_threshold) + range.me_threshold = 1024 * 1024; + + if (range.me_threshold > i_size_read(inode)) + range.me_threshold = i_size_read(inode); + if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) { context->auto_defrag = 1; - /* - * ok, the default theshold for the defragmentation - * is 1M, since our maximum clustersize was 1M also. - * any thought? - */ - if (!range.me_threshold) - range.me_threshold = 1024 * 1024; - - if (range.me_threshold > i_size_read(inode)) - range.me_threshold = i_size_read(inode); if (range.me_flags & OCFS2_MOVE_EXT_FL_PART_DEFRAG) context->partial = 1; From 9c792a59e078cb9675a23a9ce633c475957d1a18 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 15 Dec 2022 14:24:03 +0100 Subject: [PATCH 1847/4345] udf: Truncate added extents on failed expansion commit 70bfb3a8d661d4fdc742afc061b88a7f3fc9f500 upstream. When a file expansion failed because we didn't have enough space for indirect extents make sure we truncate extents created so far so that we don't leave extents beyond EOF. CC: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 2132bfab67f3..bd649f1a82a0 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -525,8 +525,10 @@ static int udf_do_extend_file(struct inode *inode, } if (fake) { - udf_add_aext(inode, last_pos, &last_ext->extLocation, - last_ext->extLength, 1); + err = udf_add_aext(inode, last_pos, &last_ext->extLocation, + last_ext->extLength, 1); + if (err < 0) + goto out_err; count++; } else { struct kernel_lb_addr tmploc; @@ -560,7 +562,7 @@ static int udf_do_extend_file(struct inode *inode, err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) - return err; + goto out_err; count++; } if (new_block_bytes) { @@ -569,7 +571,7 @@ static int udf_do_extend_file(struct inode *inode, err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) - return err; + goto out_err; count++; } @@ -583,6 +585,11 @@ out: return -EIO; return count; +out_err: + /* Remove extents we've created so far */ + udf_clear_extent_cache(inode); + udf_truncate_extents(inode); + return err; } /* Extend the final block of the file to final_block_len bytes */ From 965982feb333aefa9256c0fe188b5f1b958aef63 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 16 Dec 2022 12:37:51 +0100 Subject: [PATCH 1848/4345] udf: Do not bother merging very long extents commit 53cafe1d6d8ef9f93318e5bfccc0d24f27d41ced upstream. When merging very long extents we try to push as much length as possible to the first extent. However this is unnecessarily complicated and not really worth the trouble. Furthermore there was a bug in the logic resulting in corrupting extents in the file as syzbot reproducer shows. So just don't bother with the merging of extents that are too long together. CC: stable@vger.kernel.org Reported-by: syzbot+60f291a24acecb3c2bd5@syzkaller.appspotmail.com Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index bd649f1a82a0..6b6968f4c55e 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1093,23 +1093,8 @@ static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, blocksize - 1) >> blocksize_bits)))) { if (((li->extLength & UDF_EXTENT_LENGTH_MASK) + - (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + - blocksize - 1) & ~UDF_EXTENT_LENGTH_MASK) { - lip1->extLength = (lip1->extLength - - (li->extLength & - UDF_EXTENT_LENGTH_MASK) + - UDF_EXTENT_LENGTH_MASK) & - ~(blocksize - 1); - li->extLength = (li->extLength & - UDF_EXTENT_FLAG_MASK) + - (UDF_EXTENT_LENGTH_MASK + 1) - - blocksize; - lip1->extLocation.logicalBlockNum = - li->extLocation.logicalBlockNum + - ((li->extLength & - UDF_EXTENT_LENGTH_MASK) >> - blocksize_bits); - } else { + (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + + blocksize - 1) <= UDF_EXTENT_LENGTH_MASK) { li->extLength = lip1->extLength + (((li->extLength & UDF_EXTENT_LENGTH_MASK) + From eb2133900cac2d2f78befd6be41666cf1a2315d9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 2 Jan 2023 20:14:47 +0100 Subject: [PATCH 1849/4345] udf: Do not update file length for failed writes to inline files commit 256fe4162f8b5a1625b8603ca5f7ff79725bfb47 upstream. When write to inline file fails (or happens only partly), we still updated length of inline data as if the whole write succeeded. Fix the update of length of inline data to happen only if the write succeeds. Reported-by: syzbot+0937935b993956ba28ab@syzkaller.appspotmail.com CC: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/file.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/fs/udf/file.c b/fs/udf/file.c index ad8eefad27d7..e283a62701b8 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -147,26 +147,24 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; down_write(&iinfo->i_data_sem); - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - loff_t end = iocb->ki_pos + iov_iter_count(from); - - if (inode->i_sb->s_blocksize < - (udf_file_entry_alloc_offset(inode) + end)) { - err = udf_expand_file_adinicb(inode); - if (err) { - inode_unlock(inode); - udf_debug("udf_expand_adinicb: err=%d\n", err); - return err; - } - } else { - iinfo->i_lenAlloc = max(end, inode->i_size); - up_write(&iinfo->i_data_sem); + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && + inode->i_sb->s_blocksize < (udf_file_entry_alloc_offset(inode) + + iocb->ki_pos + iov_iter_count(from))) { + err = udf_expand_file_adinicb(inode); + if (err) { + inode_unlock(inode); + udf_debug("udf_expand_adinicb: err=%d\n", err); + return err; } } else up_write(&iinfo->i_data_sem); retval = __generic_file_write_iter(iocb, from); out: + down_write(&iinfo->i_data_sem); + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && retval > 0) + iinfo->i_lenAlloc = inode->i_size; + up_write(&iinfo->i_data_sem); inode_unlock(inode); if (retval > 0) { From 63478c3ce24bba1fb4736102bfb1aa986e215cb0 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 3 Jan 2023 09:56:56 +0100 Subject: [PATCH 1850/4345] udf: Preserve link count of system files commit fc8033a34a3ca7d23353e645e6dde5d364ac5f12 upstream. System files in UDF filesystem have link count 0. To not confuse VFS we fudge the link count to be 1 when reading such inodes however we forget to restore the link count of 0 when writing such inodes. Fix that. CC: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 9 +++++++-- fs/udf/super.c | 1 + fs/udf/udf_i.h | 3 ++- 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 6b6968f4c55e..8fed514be5f3 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1385,6 +1385,7 @@ reread: ret = -EIO; goto out; } + iinfo->i_hidden = hidden_inode; iinfo->i_unique = 0; iinfo->i_lenEAttr = 0; iinfo->i_lenExtents = 0; @@ -1720,8 +1721,12 @@ static int udf_update_inode(struct inode *inode, int do_sync) if (S_ISDIR(inode->i_mode) && inode->i_nlink > 0) fe->fileLinkCount = cpu_to_le16(inode->i_nlink - 1); - else - fe->fileLinkCount = cpu_to_le16(inode->i_nlink); + else { + if (iinfo->i_hidden) + fe->fileLinkCount = cpu_to_le16(0); + else + fe->fileLinkCount = cpu_to_le16(inode->i_nlink); + } fe->informationLength = cpu_to_le64(inode->i_size); diff --git a/fs/udf/super.c b/fs/udf/super.c index 3448098e5476..4af9ce34ee80 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -147,6 +147,7 @@ static struct inode *udf_alloc_inode(struct super_block *sb) ei->i_next_alloc_goal = 0; ei->i_strat4096 = 0; ei->i_streamdir = 0; + ei->i_hidden = 0; init_rwsem(&ei->i_data_sem); ei->cached_extent.lstart = -1; spin_lock_init(&ei->i_extent_cache_lock); diff --git a/fs/udf/udf_i.h b/fs/udf/udf_i.h index 06ff7006b822..312b7c9ef10e 100644 --- a/fs/udf/udf_i.h +++ b/fs/udf/udf_i.h @@ -44,7 +44,8 @@ struct udf_inode_info { unsigned i_use : 1; /* unallocSpaceEntry */ unsigned i_strat4096 : 1; unsigned i_streamdir : 1; - unsigned reserved : 25; + unsigned i_hidden : 1; /* hidden system inode */ + unsigned reserved : 24; __u8 *i_data; struct kernel_lb_addr i_locStreamdir; __u64 i_lenStreams; From a44ec34b90440ada190924f5908b97026504fdcd Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 3 Jan 2023 10:03:35 +0100 Subject: [PATCH 1851/4345] udf: Detect system inodes linked into directory hierarchy commit 85a37983ec69cc9fcd188bc37c4de15ee326355a upstream. When UDF filesystem is corrupted, hidden system inodes can be linked into directory hierarchy which is an avenue for further serious corruption of the filesystem and kernel confusion as noticed by syzbot fuzzed images. Refuse to access system inodes linked into directory hierarchy and vice versa. CC: stable@vger.kernel.org Reported-by: syzbot+38695a20b8addcbc1084@syzkaller.appspotmail.com Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 8fed514be5f3..71acce2c0b6a 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1897,8 +1897,13 @@ struct inode *__udf_iget(struct super_block *sb, struct kernel_lb_addr *ino, if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode->i_state & I_NEW)) { + if (UDF_I(inode)->i_hidden != hidden_inode) { + iput(inode); + return ERR_PTR(-EFSCORRUPTED); + } return inode; + } memcpy(&UDF_I(inode)->i_location, ino, sizeof(struct kernel_lb_addr)); err = udf_read_inode(inode, hidden_inode); From bacfce056ea694ad023ce577950abde515de0599 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 23 Jan 2023 14:18:47 +0100 Subject: [PATCH 1852/4345] udf: Fix file corruption when appending just after end of preallocated extent commit 36ec52ea038b18a53e198116ef7d7e70c87db046 upstream. When we append new block just after the end of preallocated extent, the code in inode_getblk() wrongly determined we're going to use the preallocated extent which resulted in adding block into a wrong logical offset in the file. Sequence like this manifests it: xfs_io -f -c "pwrite 0x2cacf 0xd122" -c "truncate 0x2dd6f" \ -c "pwrite 0x27fd9 0x69a9" -c "pwrite 0x32981 0x7244" The code that determined the use of preallocated extent is actually stale because udf_do_extend_file() does not create preallocation anymore so after calling that function we are sure there's no usable preallocation. Just remove the faulty condition. CC: stable@vger.kernel.org Fixes: 16d055656814 ("udf: Discard preallocation before extending file with a hole") Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 71acce2c0b6a..81876284a83c 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -804,19 +804,17 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, c = 0; offset = 0; count += ret; - /* We are not covered by a preallocated extent? */ - if ((laarr[0].extLength & UDF_EXTENT_FLAG_MASK) != - EXT_NOT_RECORDED_ALLOCATED) { - /* Is there any real extent? - otherwise we overwrite - * the fake one... */ - if (count) - c = !c; - laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - inode->i_sb->s_blocksize; - memset(&laarr[c].extLocation, 0x00, - sizeof(struct kernel_lb_addr)); - count++; - } + /* + * Is there any real extent? - otherwise we overwrite the fake + * one... + */ + if (count) + c = !c; + laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | + inode->i_sb->s_blocksize; + memset(&laarr[c].extLocation, 0x00, + sizeof(struct kernel_lb_addr)); + count++; endnum = c + 1; lastblock = 1; } else { From 76a9886e1b61ce5592df5ae78a19ed30399ae189 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 19 Dec 2022 17:19:24 +0000 Subject: [PATCH 1853/4345] KVM: Destroy target device if coalesced MMIO unregistration fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b1cb1fac22abf102ffeb29dd3eeca208a3869d54 upstream. Destroy and free the target coalesced MMIO device if unregistering said device fails. As clearly noted in the code, kvm_io_bus_unregister_dev() does not destroy the target device. BUG: memory leak unreferenced object 0xffff888112a54880 (size 64): comm "syz-executor.2", pid 5258, jiffies 4297861402 (age 14.129s) hex dump (first 32 bytes): 38 c7 67 15 00 c9 ff ff 38 c7 67 15 00 c9 ff ff 8.g.....8.g..... e0 c7 e1 83 ff ff ff ff 00 30 67 15 00 c9 ff ff .........0g..... backtrace: [<0000000006995a8a>] kmalloc include/linux/slab.h:556 [inline] [<0000000006995a8a>] kzalloc include/linux/slab.h:690 [inline] [<0000000006995a8a>] kvm_vm_ioctl_register_coalesced_mmio+0x8e/0x3d0 arch/x86/kvm/../../../virt/kvm/coalesced_mmio.c:150 [<00000000022550c2>] kvm_vm_ioctl+0x47d/0x1600 arch/x86/kvm/../../../virt/kvm/kvm_main.c:3323 [<000000008a75102f>] vfs_ioctl fs/ioctl.c:46 [inline] [<000000008a75102f>] file_ioctl fs/ioctl.c:509 [inline] [<000000008a75102f>] do_vfs_ioctl+0xbab/0x1160 fs/ioctl.c:696 [<0000000080e3f669>] ksys_ioctl+0x76/0xa0 fs/ioctl.c:713 [<0000000059ef4888>] __do_sys_ioctl fs/ioctl.c:720 [inline] [<0000000059ef4888>] __se_sys_ioctl fs/ioctl.c:718 [inline] [<0000000059ef4888>] __x64_sys_ioctl+0x6f/0xb0 fs/ioctl.c:718 [<000000006444fa05>] do_syscall_64+0x9f/0x4e0 arch/x86/entry/common.c:290 [<000000009a4ed50b>] entry_SYSCALL_64_after_hwframe+0x49/0xbe BUG: leak checking failed Fixes: 5d3c4c79384a ("KVM: Stop looking for coalesced MMIO zones if the bus is destroyed") Cc: stable@vger.kernel.org Reported-by: 柳菁峰 Reported-by: Michal Luczaj Link: https://lore.kernel.org/r/20221219171924.67989-1-seanjc@google.com Link: https://lore.kernel.org/all/20230118220003.1239032-1-mhal@rbox.co Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- virt/kvm/coalesced_mmio.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index d5bebb37238c..ce6f3b916ef9 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -187,15 +187,17 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, r = kvm_io_bus_unregister_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev); + kvm_iodevice_destructor(&dev->dev); + /* * On failure, unregister destroys all devices on the * bus _except_ the target device, i.e. coalesced_zones - * has been modified. No need to restart the walk as - * there aren't any zones left. + * has been modified. Bail after destroying the target + * device, there's no need to restart the walk as there + * aren't any zones left. */ if (r) break; - kvm_iodevice_destructor(&dev->dev); } } From 018798c6fbefe03b05eff96629fb9b15a1115c3d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Sat, 7 Jan 2023 01:10:20 +0000 Subject: [PATCH 1854/4345] KVM: x86: Inject #GP if WRMSR sets reserved bits in APIC Self-IPI commit ba5838abb05334e4abfdff1490585c7f365e0424 upstream. Inject a #GP if the guest attempts to set reserved bits in the x2APIC-only Self-IPI register. Bits 7:0 hold the vector, all other bits are reserved. Reported-by: Marc Orr Cc: Ben Gardon Cc: Venkatesh Srinivas Cc: stable@vger.kernel.org Reviewed-by: Maxim Levitsky Link: https://lore.kernel.org/r/20230107011025.565472-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/lapic.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 260727eaa6b9..21189804524a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2115,10 +2115,14 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; case APIC_SELF_IPI: - if (apic_x2apic_mode(apic)) - kvm_apic_send_ipi(apic, APIC_DEST_SELF | (val & APIC_VECTOR_MASK), 0); - else + /* + * Self-IPI exists only when x2APIC is enabled. Bits 7:0 hold + * the vector, everything else is reserved. + */ + if (!apic_x2apic_mode(apic) || (val & ~APIC_VECTOR_MASK)) ret = 1; + else + kvm_apic_send_ipi(apic, APIC_DEST_SELF | val, 0); break; default: ret = 1; From edd7f5bc6f9749a5093921e01fc120c465000f01 Mon Sep 17 00:00:00 2001 From: Nico Boehr Date: Fri, 27 Jan 2023 15:05:32 +0100 Subject: [PATCH 1855/4345] KVM: s390: disable migration mode when dirty tracking is disabled commit f2d3155e2a6bac44d16f04415a321e8707d895c6 upstream. Migration mode is a VM attribute which enables tracking of changes in storage attributes (PGSTE). It assumes dirty tracking is enabled on all memslots to keep a dirty bitmap of pages with changed storage attributes. When enabling migration mode, we currently check that dirty tracking is enabled for all memslots. However, userspace can disable dirty tracking without disabling migration mode. Since migration mode is pointless with dirty tracking disabled, disable migration mode whenever userspace disables dirty tracking on any slot. Also update the documentation to clarify that dirty tracking must be enabled when enabling migration mode, which is already enforced by the code in kvm_s390_vm_start_migration(). Also highlight in the documentation for KVM_S390_GET_CMMA_BITS that it can now fail with -EINVAL when dirty tracking is disabled while migration mode is on. Move all the error codes to a table so this stays readable. To disable migration mode, slots_lock should be held, which is taken in kvm_set_memory_region() and thus held in kvm_arch_prepare_memory_region(). Restructure the prepare code a bit so all the sanity checking is done before disabling migration mode. This ensures migration mode isn't disabled when some sanity check fails. Cc: stable@vger.kernel.org Fixes: 190df4a212a7 ("KVM: s390: CMMA tracking, ESSA emulation, migration mode") Signed-off-by: Nico Boehr Reviewed-by: Janosch Frank Reviewed-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20230127140532.230651-2-nrb@linux.ibm.com Message-Id: <20230127140532.230651-2-nrb@linux.ibm.com> [frankja@linux.ibm.com: fixed commit message typo, moved api.rst error table upwards] Signed-off-by: Janosch Frank Signed-off-by: Greg Kroah-Hartman --- Documentation/virt/kvm/api.rst | 18 ++++++++++++------ Documentation/virt/kvm/devices/vm.rst | 4 ++++ arch/s390/kvm/kvm-s390.c | 17 +++++++++++++++++ 3 files changed, 33 insertions(+), 6 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 2b4b64797191..08295f488d05 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4031,6 +4031,18 @@ not holding a previously reported uncorrected error). :Parameters: struct kvm_s390_cmma_log (in, out) :Returns: 0 on success, a negative value on error +Errors: + + ====== ============================================================= + ENOMEM not enough memory can be allocated to complete the task + ENXIO if CMMA is not enabled + EINVAL if KVM_S390_CMMA_PEEK is not set but migration mode was not enabled + EINVAL if KVM_S390_CMMA_PEEK is not set but dirty tracking has been + disabled (and thus migration mode was automatically disabled) + EFAULT if the userspace address is invalid or if no page table is + present for the addresses (e.g. when using hugepages). + ====== ============================================================= + This ioctl is used to get the values of the CMMA bits on the s390 architecture. It is meant to be used in two scenarios: @@ -4111,12 +4123,6 @@ mask is unused. values points to the userspace buffer where the result will be stored. -This ioctl can fail with -ENOMEM if not enough memory can be allocated to -complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if -KVM_S390_CMMA_PEEK is not set but migration mode was not enabled, with --EFAULT if the userspace address is invalid or if no page table is -present for the addresses (e.g. when using hugepages). - 4.108 KVM_S390_SET_CMMA_BITS ---------------------------- diff --git a/Documentation/virt/kvm/devices/vm.rst b/Documentation/virt/kvm/devices/vm.rst index 60acc39e0e93..147efec626e5 100644 --- a/Documentation/virt/kvm/devices/vm.rst +++ b/Documentation/virt/kvm/devices/vm.rst @@ -302,6 +302,10 @@ Allows userspace to start migration mode, needed for PGSTE migration. Setting this attribute when migration mode is already active will have no effects. +Dirty tracking must be enabled on all memslots, else -EINVAL is returned. When +dirty tracking is disabled on any memslot, migration mode is automatically +stopped. + :Parameters: none :Returns: -ENOMEM if there is not enough free memory to start migration mode; -EINVAL if the state of the VM is invalid (e.g. no memory defined); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 59db85fb63e1..7ffc73ba220f 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -5012,6 +5012,23 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, /* When we are protected, we should not change the memory slots */ if (kvm_s390_pv_get_handle(kvm)) return -EINVAL; + + if (!kvm->arch.migration_mode) + return 0; + + /* + * Turn off migration mode when: + * - userspace creates a new memslot with dirty logging off, + * - userspace modifies an existing memslot (MOVE or FLAGS_ONLY) and + * dirty logging is turned off. + * Migration mode expects dirty page logging being enabled to store + * its dirty bitmap. + */ + if (change != KVM_MR_DELETE && + !(mem->flags & KVM_MEM_LOG_DIRTY_PAGES)) + WARN(kvm_s390_vm_stop_migration(kvm), + "Failed to stop migration mode"); + return 0; } From 537be939a86a37793705f926b6a1882f8bb7ffee Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:36:48 +0000 Subject: [PATCH 1856/4345] x86/virt: Force GIF=1 prior to disabling SVM (for reboot flows) commit 6a3236580b0b1accc3976345e723104f74f6f8e6 upstream. Set GIF=1 prior to disabling SVM to ensure that INIT is recognized if the kernel is disabling SVM in an emergency, e.g. if the kernel is about to jump into a crash kernel or may reboot without doing a full CPU RESET. If GIF is left cleared, the new kernel (or firmware) will be unabled to awaken APs. Eat faults on STGI (due to EFER.SVME=0) as it's possible that SVM could be disabled via NMI shootdown between reading EFER.SVME and executing STGI. Link: https://lore.kernel.org/all/cbcb6f35-e5d7-c1c9-4db9-fe5cc4de579a@amd.com Cc: stable@vger.kernel.org Cc: Andrew Cooper Cc: Tom Lendacky Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20221130233650.1404148-3-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/virtext.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index fda3e7747c22..8eefa3386d8c 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -120,7 +120,21 @@ static inline void cpu_svm_disable(void) wrmsrl(MSR_VM_HSAVE_PA, 0); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer & ~EFER_SVME); + if (efer & EFER_SVME) { + /* + * Force GIF=1 prior to disabling SVM to ensure INIT and NMI + * aren't blocked, e.g. if a fatal error occurred between CLGI + * and STGI. Note, STGI may #UD if SVM is disabled from NMI + * context between reading EFER and executing STGI. In that + * case, GIF must already be set, otherwise the NMI would have + * been blocked, so just eat the fault. + */ + asm_volatile_goto("1: stgi\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "memory" : fault); +fault: + wrmsrl(MSR_EFER, efer & ~EFER_SVME); + } } /** Makes sure SVM is disabled, if it is supported on the CPU From 8ff2cc2f87750507048d372e8d0f4d27ef446d3b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:36:47 +0000 Subject: [PATCH 1857/4345] x86/crash: Disable virt in core NMI crash handler to avoid double shootdown commit 26044aff37a5455b19a91785086914fd33053ef4 upstream. Disable virtualization in crash_nmi_callback() and rework the emergency_vmx_disable_all() path to do an NMI shootdown if and only if a shootdown has not already occurred. NMI crash shootdown fundamentally can't support multiple invocations as responding CPUs are deliberately put into halt state without unblocking NMIs. But, the emergency reboot path doesn't have any work of its own, it simply cares about disabling virtualization, i.e. so long as a shootdown occurred, emergency reboot doesn't care who initiated the shootdown, or when. If "crash_kexec_post_notifiers" is specified on the kernel command line, panic() will invoke crash_smp_send_stop() and result in a second call to nmi_shootdown_cpus() during native_machine_emergency_restart(). Invoke the callback _before_ disabling virtualization, as the current VMCS needs to be cleared before doing VMXOFF. Note, this results in a subtle change in ordering between disabling virtualization and stopping Intel PT on the responding CPUs. While VMX and Intel PT do interact, VMXOFF and writes to MSR_IA32_RTIT_CTL do not induce faults between one another, which is all that matters when panicking. Harden nmi_shootdown_cpus() against multiple invocations to try and capture any such kernel bugs via a WARN instead of hanging the system during a crash/dump, e.g. prior to the recent hardening of register_nmi_handler(), re-registering the NMI handler would trigger a double list_add() and hang the system if CONFIG_BUG_ON_DATA_CORRUPTION=y. list_add double add: new=ffffffff82220800, prev=ffffffff8221cfe8, next=ffffffff82220800. WARNING: CPU: 2 PID: 1319 at lib/list_debug.c:29 __list_add_valid+0x67/0x70 Call Trace: __register_nmi_handler+0xcf/0x130 nmi_shootdown_cpus+0x39/0x90 native_machine_emergency_restart+0x1c9/0x1d0 panic+0x237/0x29b Extract the disabling logic to a common helper to deduplicate code, and to prepare for doing the shootdown in the emergency reboot path if SVM is supported. Note, prior to commit ed72736183c4 ("x86/reboot: Force all cpus to exit VMX root if VMX is supported"), nmi_shootdown_cpus() was subtly protected against a second invocation by a cpu_vmx_enabled() check as the kdump handler would disable VMX if it ran first. Fixes: ed72736183c4 ("x86/reboot: Force all cpus to exit VMX root if VMX is supported") Cc: stable@vger.kernel.org Reported-by: Guilherme G. Piccoli Cc: Vitaly Kuznetsov Cc: Paolo Bonzini Link: https://lore.kernel.org/all/20220427224924.592546-2-gpiccoli@igalia.com Tested-by: Guilherme G. Piccoli Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20221130233650.1404148-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/reboot.h | 2 ++ arch/x86/kernel/crash.c | 17 +-------- arch/x86/kernel/reboot.c | 65 ++++++++++++++++++++++++++++------- 3 files changed, 56 insertions(+), 28 deletions(-) diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 04c17be9b5fd..bc5b4d788c08 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,6 +25,8 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_BIOS 0 #define MRR_APM 1 +void cpu_emergency_disable_virtualization(void); + typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_panic_self_stop(struct pt_regs *regs); void nmi_shootdown_cpus(nmi_shootdown_cb callback); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index b1deacbeb266..a932a07d0025 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include #include @@ -94,15 +93,6 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) */ cpu_crash_vmclear_loaded_vmcss(); - /* Disable VMX or SVM if needed. - * - * We need to disable virtualization on all CPUs. - * Having VMX or SVM enabled on any CPU may break rebooting - * after the kdump kernel has finished its task. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); - /* * Disable Intel PT to stop its logging */ @@ -161,12 +151,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) */ cpu_crash_vmclear_loaded_vmcss(); - /* Booting kdump kernel with VMX or SVM enabled won't work, - * because (among other limitations) we can't disable paging - * with the virt flags. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); + cpu_emergency_disable_virtualization(); /* * Disable Intel PT to stop its logging diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index df3514835b35..aa615803c1bc 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -528,10 +528,7 @@ static inline void kb_wait(void) } } -static void vmxoff_nmi(int cpu, struct pt_regs *regs) -{ - cpu_emergency_vmxoff(); -} +static inline void nmi_shootdown_cpus_on_restart(void); /* Use NMIs as IPIs to tell all CPUs to disable virtualization */ static void emergency_vmx_disable_all(void) @@ -554,7 +551,7 @@ static void emergency_vmx_disable_all(void) __cpu_emergency_vmxoff(); /* Halt and exit VMX root operation on the other CPUs. */ - nmi_shootdown_cpus(vmxoff_nmi); + nmi_shootdown_cpus_on_restart(); } } @@ -795,6 +792,17 @@ void machine_crash_shutdown(struct pt_regs *regs) /* This is the CPU performing the emergency shutdown work. */ int crashing_cpu = -1; +/* + * Disable virtualization, i.e. VMX or SVM, to ensure INIT is recognized during + * reboot. VMX blocks INIT if the CPU is post-VMXON, and SVM blocks INIT if + * GIF=0, i.e. if the crash occurred between CLGI and STGI. + */ +void cpu_emergency_disable_virtualization(void) +{ + cpu_emergency_vmxoff(); + cpu_emergency_svm_disable(); +} + #if defined(CONFIG_SMP) static nmi_shootdown_cb shootdown_callback; @@ -817,7 +825,14 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) return NMI_HANDLED; local_irq_disable(); - shootdown_callback(cpu, regs); + if (shootdown_callback) + shootdown_callback(cpu, regs); + + /* + * Prepare the CPU for reboot _after_ invoking the callback so that the + * callback can safely use virtualization instructions, e.g. VMCLEAR. + */ + cpu_emergency_disable_virtualization(); atomic_dec(&waiting_for_crash_ipi); /* Assume hlt works */ @@ -828,18 +843,32 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) return NMI_HANDLED; } -/* - * Halt all other CPUs, calling the specified function on each of them +/** + * nmi_shootdown_cpus - Stop other CPUs via NMI + * @callback: Optional callback to be invoked from the NMI handler * - * This function can be used to halt all other CPUs on crash - * or emergency reboot time. The function passed as parameter - * will be called inside a NMI handler on all CPUs. + * The NMI handler on the remote CPUs invokes @callback, if not + * NULL, first and then disables virtualization to ensure that + * INIT is recognized during reboot. + * + * nmi_shootdown_cpus() can only be invoked once. After the first + * invocation all other CPUs are stuck in crash_nmi_callback() and + * cannot respond to a second NMI. */ void nmi_shootdown_cpus(nmi_shootdown_cb callback) { unsigned long msecs; + local_irq_disable(); + /* + * Avoid certain doom if a shootdown already occurred; re-registering + * the NMI handler will cause list corruption, modifying the callback + * will do who knows what, etc... + */ + if (WARN_ON_ONCE(crash_ipi_issued)) + return; + /* Make a note of crashing cpu. Will be used in NMI callback. */ crashing_cpu = safe_smp_processor_id(); @@ -867,7 +896,17 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) msecs--; } - /* Leave the nmi callback set */ + /* + * Leave the nmi callback set, shootdown is a one-time thing. Clearing + * the callback could result in a NULL pointer dereference if a CPU + * (finally) responds after the timeout expires. + */ +} + +static inline void nmi_shootdown_cpus_on_restart(void) +{ + if (!crash_ipi_issued) + nmi_shootdown_cpus(NULL); } /* @@ -897,6 +936,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) /* No other CPUs to shoot down */ } +static inline void nmi_shootdown_cpus_on_restart(void) { } + void run_crash_ipi_callback(struct pt_regs *regs) { } From 051f991c571bb17d5b37eb7d73741ff0bd8b1b99 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:36:49 +0000 Subject: [PATCH 1858/4345] x86/reboot: Disable virtualization in an emergency if SVM is supported commit d81f952aa657b76cea381384bef1fea35c5fd266 upstream. Disable SVM on all CPUs via NMI shootdown during an emergency reboot. Like VMX, SVM can block INIT, e.g. if the emergency reboot is triggered between CLGI and STGI, and thus can prevent bringing up other CPUs via INIT-SIPI-SIPI. Cc: stable@vger.kernel.org Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20221130233650.1404148-4-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/reboot.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index aa615803c1bc..4d8c0e258150 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -530,27 +530,26 @@ static inline void kb_wait(void) static inline void nmi_shootdown_cpus_on_restart(void); -/* Use NMIs as IPIs to tell all CPUs to disable virtualization */ -static void emergency_vmx_disable_all(void) +static void emergency_reboot_disable_virtualization(void) { /* Just make sure we won't change CPUs while doing this */ local_irq_disable(); /* - * Disable VMX on all CPUs before rebooting, otherwise we risk hanging - * the machine, because the CPU blocks INIT when it's in VMX root. + * Disable virtualization on all CPUs before rebooting to avoid hanging + * the system, as VMX and SVM block INIT when running in the host. * * We can't take any locks and we may be on an inconsistent state, so - * use NMIs as IPIs to tell the other CPUs to exit VMX root and halt. + * use NMIs as IPIs to tell the other CPUs to disable VMX/SVM and halt. * - * Do the NMI shootdown even if VMX if off on _this_ CPU, as that - * doesn't prevent a different CPU from being in VMX root operation. + * Do the NMI shootdown even if virtualization is off on _this_ CPU, as + * other CPUs may have virtualization enabled. */ - if (cpu_has_vmx()) { - /* Safely force _this_ CPU out of VMX root operation. */ - __cpu_emergency_vmxoff(); + if (cpu_has_vmx() || cpu_has_svm(NULL)) { + /* Safely force _this_ CPU out of VMX/SVM operation. */ + cpu_emergency_disable_virtualization(); - /* Halt and exit VMX root operation on the other CPUs. */ + /* Disable VMX/SVM and halt on other CPUs. */ nmi_shootdown_cpus_on_restart(); } } @@ -587,7 +586,7 @@ static void native_machine_emergency_restart(void) unsigned short mode; if (reboot_emergency) - emergency_vmx_disable_all(); + emergency_reboot_disable_virtualization(); tboot_shutdown(TB_SHUTDOWN_REBOOT); From f75ee95196cecd0375c28f56d1bc713368474c63 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:36:50 +0000 Subject: [PATCH 1859/4345] x86/reboot: Disable SVM, not just VMX, when stopping CPUs commit a2b07fa7b93321c059af0c6d492cc9a4f1e390aa upstream. Disable SVM and more importantly force GIF=1 when halting a CPU or rebooting the machine. Similar to VMX, SVM allows software to block INITs via CLGI, and thus can be problematic for a crash/reboot. The window for failure is smaller with SVM as INIT is only blocked while GIF=0, i.e. between CLGI and STGI, but the window does exist. Fixes: fba4f472b33a ("x86/reboot: Turn off KVM when halting a CPU") Cc: stable@vger.kernel.org Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20221130233650.1404148-5-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/smp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index eff4ce3b10da..95758ae120ba 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include /* * Some notes on x86 processor bugs affecting SMP operation: @@ -122,7 +122,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) if (raw_smp_processor_id() == atomic_read(&stopping_cpu)) return NMI_HANDLED; - cpu_emergency_vmxoff(); + cpu_emergency_disable_virtualization(); stop_this_cpu(NULL); return NMI_HANDLED; @@ -134,7 +134,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) DEFINE_IDTENTRY_SYSVEC(sysvec_reboot) { ack_APIC_irq(); - cpu_emergency_vmxoff(); + cpu_emergency_disable_virtualization(); stop_this_cpu(NULL); } From c16e4610d5e5e2698f25280121173292c1c3f805 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 21 Feb 2023 08:49:16 +0900 Subject: [PATCH 1860/4345] x86/kprobes: Fix __recover_optprobed_insn check optimizing logic commit 868a6fc0ca2407622d2833adefe1c4d284766c4c upstream. Since the following commit: commit f66c0447cca1 ("kprobes: Set unoptimized flag after unoptimizing code") modified the update timing of the KPROBE_FLAG_OPTIMIZED, a optimized_kprobe may be in the optimizing or unoptimizing state when op.kp->flags has KPROBE_FLAG_OPTIMIZED and op->list is not empty. The __recover_optprobed_insn check logic is incorrect, a kprobe in the unoptimizing state may be incorrectly determined as unoptimizing. As a result, incorrect instructions are copied. The optprobe_queued_unopt function needs to be exported for invoking in arch directory. Link: https://lore.kernel.org/all/20230216034247.32348-2-yangjihong1@huawei.com/ Fixes: f66c0447cca1 ("kprobes: Set unoptimized flag after unoptimizing code") Cc: stable@vger.kernel.org Signed-off-by: Yang Jihong Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/kprobes/opt.c | 4 ++-- include/linux/kprobes.h | 1 + kernel/kprobes.c | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 3d6201492006..e81adc1070f3 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -46,8 +46,8 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) /* This function only handles jump-optimized kprobe */ if (kp && kprobe_optimized(kp)) { op = container_of(kp, struct optimized_kprobe, kp); - /* If op->list is not empty, op is under optimizing */ - if (list_empty(&op->list)) + /* If op is optimized or under unoptimizing */ + if (list_empty(&op->list) || optprobe_queued_unopt(op)) goto found; } } diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 4dbebd319b6f..0ed50f1a9578 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -342,6 +342,7 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, size_t *length, loff_t *ppos); #endif extern void wait_for_kprobe_optimizer(void); +bool optprobe_queued_unopt(struct optimized_kprobe *op); #else static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 75150e755518..80a57d45f5f7 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -652,7 +652,7 @@ void wait_for_kprobe_optimizer(void) mutex_unlock(&kprobe_mutex); } -static bool optprobe_queued_unopt(struct optimized_kprobe *op) +bool optprobe_queued_unopt(struct optimized_kprobe *op) { struct optimized_kprobe *_op; From 5255fd8dfbd2944aecf69c338aa9e9f2a3e38f00 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 21 Feb 2023 08:49:16 +0900 Subject: [PATCH 1861/4345] x86/kprobes: Fix arch_check_optimized_kprobe check within optimized_kprobe range commit f1c97a1b4ef709e3f066f82e3ba3108c3b133ae6 upstream. When arch_prepare_optimized_kprobe calculating jump destination address, it copies original instructions from jmp-optimized kprobe (see __recover_optprobed_insn), and calculated based on length of original instruction. arch_check_optimized_kprobe does not check KPROBE_FLAG_OPTIMATED when checking whether jmp-optimized kprobe exists. As a result, setup_detour_execution may jump to a range that has been overwritten by jump destination address, resulting in an inval opcode error. For example, assume that register two kprobes whose addresses are and in "func" function. The original code of "func" function is as follows: 0xffffffff816cb5e9 <+9>: push %r12 0xffffffff816cb5eb <+11>: xor %r12d,%r12d 0xffffffff816cb5ee <+14>: test %rdi,%rdi 0xffffffff816cb5f1 <+17>: setne %r12b 0xffffffff816cb5f5 <+21>: push %rbp 1.Register the kprobe for , assume that is kp1, corresponding optimized_kprobe is op1. After the optimization, "func" code changes to: 0xffffffff816cc079 <+9>: push %r12 0xffffffff816cc07b <+11>: jmp 0xffffffffa0210000 0xffffffff816cc080 <+16>: incl 0xf(%rcx) 0xffffffff816cc083 <+19>: xchg %eax,%ebp 0xffffffff816cc084 <+20>: (bad) 0xffffffff816cc085 <+21>: push %rbp Now op1->flags == KPROBE_FLAG_OPTIMATED; 2. Register the kprobe for , assume that is kp2, corresponding optimized_kprobe is op2. register_kprobe(kp2) register_aggr_kprobe alloc_aggr_kprobe __prepare_optimized_kprobe arch_prepare_optimized_kprobe __recover_optprobed_insn // copy original bytes from kp1->optinsn.copied_insn, // jump address = 3. disable kp1: disable_kprobe(kp1) __disable_kprobe ... if (p == orig_p || aggr_kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true) // add op1 in unoptimizing_list, not unoptimized orig_p->flags |= KPROBE_FLAG_DISABLED; // op1->flags == KPROBE_FLAG_OPTIMATED | KPROBE_FLAG_DISABLED ... 4. unregister kp2 __unregister_kprobe_top ... if (!kprobe_disabled(ap) && !kprobes_all_disarmed) { optimize_kprobe(op) ... if (arch_check_optimized_kprobe(op) < 0) // because op1 has KPROBE_FLAG_DISABLED, here not return return; p->kp.flags |= KPROBE_FLAG_OPTIMIZED; // now op2 has KPROBE_FLAG_OPTIMIZED } "func" code now is: 0xffffffff816cc079 <+9>: int3 0xffffffff816cc07a <+10>: push %rsp 0xffffffff816cc07b <+11>: jmp 0xffffffffa0210000 0xffffffff816cc080 <+16>: incl 0xf(%rcx) 0xffffffff816cc083 <+19>: xchg %eax,%ebp 0xffffffff816cc084 <+20>: (bad) 0xffffffff816cc085 <+21>: push %rbp 5. if call "func", int3 handler call setup_detour_execution: if (p->flags & KPROBE_FLAG_OPTIMIZED) { ... regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; ... } The code for the destination address is 0xffffffffa021072c: push %r12 0xffffffffa021072e: xor %r12d,%r12d 0xffffffffa0210731: jmp 0xffffffff816cb5ee However, is not a valid start instruction address. As a result, an error occurs. Link: https://lore.kernel.org/all/20230216034247.32348-3-yangjihong1@huawei.com/ Fixes: f66c0447cca1 ("kprobes: Set unoptimized flag after unoptimizing code") Signed-off-by: Yang Jihong Cc: stable@vger.kernel.org Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/kprobes/opt.c | 2 +- include/linux/kprobes.h | 1 + kernel/kprobes.c | 4 ++-- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index e81adc1070f3..e37e5e82481a 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -346,7 +346,7 @@ int arch_check_optimized_kprobe(struct optimized_kprobe *op) for (i = 1; i < op->optinsn.size; i++) { p = get_kprobe(op->kp.addr + i); - if (p && !kprobe_disabled(p)) + if (p && !kprobe_disarmed(p)) return -EEXIST; } diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 0ed50f1a9578..18b7c40ffb37 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -343,6 +343,7 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, #endif extern void wait_for_kprobe_optimizer(void); bool optprobe_queued_unopt(struct optimized_kprobe *op); +bool kprobe_disarmed(struct kprobe *p); #else static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 80a57d45f5f7..86d71c49b495 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -447,8 +447,8 @@ static inline int kprobe_optready(struct kprobe *p) return 0; } -/* Return true(!0) if the kprobe is disarmed. Note: p must be on hash list */ -static inline int kprobe_disarmed(struct kprobe *p) +/* Return true if the kprobe is disarmed. Note: p must be on hash list */ +bool kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; From 0a89768b85f010107b8051285379dc88c002715b Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Tue, 17 Jan 2023 23:59:24 +0100 Subject: [PATCH 1862/4345] x86/microcode/amd: Remove load_microcode_amd()'s bsp parameter commit 2355370cd941cbb20882cc3f34460f9f2b8f9a18 upstream. It is always the BSP. No functional changes. Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230130161709.11615-2-bp@alien8.de Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/microcode/amd.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 234a96f25248..9d0889386a33 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -548,8 +548,7 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax) apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, false); } -static enum ucode_state -load_microcode_amd(bool save, u8 family, const u8 *data, size_t size); +static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) { @@ -567,7 +566,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) if (!desc.mc) return -EINVAL; - ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size); + ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size); if (ret > UCODE_UPDATED) return -EINVAL; @@ -845,8 +844,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, return UCODE_OK; } -static enum ucode_state -load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) +static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) { struct ucode_patch *p; enum ucode_state ret; @@ -870,10 +868,6 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) ret = UCODE_NEW; } - /* save BSP's matching patch for early load */ - if (!save) - return ret; - memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); memcpy(amd_ucode_patch, p->data, min_t(u32, p->size, PATCH_MAX_SIZE)); @@ -901,12 +895,11 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, { char fw_name[36] = "amd-ucode/microcode_amd.bin"; struct cpuinfo_x86 *c = &cpu_data(cpu); - bool bsp = c->cpu_index == boot_cpu_data.cpu_index; enum ucode_state ret = UCODE_NFOUND; const struct firmware *fw; /* reload ucode container only on the boot cpu */ - if (!refresh_fw || !bsp) + if (!refresh_fw) return UCODE_OK; if (c->x86 >= 0x15) @@ -921,7 +914,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, if (!verify_container(fw->data, fw->size, false)) goto fw_release; - ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size); + ret = load_microcode_amd(c->x86, fw->data, fw->size); fw_release: release_firmware(fw); From 87cf9bc78c433c005d769111c007adb58d7697a6 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Thu, 26 Jan 2023 00:08:03 +0100 Subject: [PATCH 1863/4345] x86/microcode/AMD: Add a @cpu parameter to the reloading functions commit a5ad92134bd153a9ccdcddf09a95b088f36c3cce upstream. Will be used in a subsequent change. Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230130161709.11615-3-bp@alien8.de Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/microcode.h | 4 ++-- arch/x86/include/asm/microcode_amd.h | 4 ++-- arch/x86/kernel/cpu/microcode/amd.c | 2 +- arch/x86/kernel/cpu/microcode/core.c | 6 +++--- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index f73327397b89..509cc0262fdc 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -131,7 +131,7 @@ static inline unsigned int x86_cpuid_family(void) int __init microcode_init(void); extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); -void reload_early_microcode(void); +void reload_early_microcode(unsigned int cpu); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); extern bool initrd_gone; void microcode_bsp_resume(void); @@ -139,7 +139,7 @@ void microcode_bsp_resume(void); static inline int __init microcode_init(void) { return 0; }; static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } -static inline void reload_early_microcode(void) { } +static inline void reload_early_microcode(unsigned int cpu) { } static inline void microcode_bsp_resume(void) { } static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; } diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 7063b5a43220..a645b25ee442 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -47,12 +47,12 @@ struct microcode_amd { extern void __init load_ucode_amd_bsp(unsigned int family); extern void load_ucode_amd_ap(unsigned int family); extern int __init save_microcode_in_initrd_amd(unsigned int family); -void reload_ucode_amd(void); +void reload_ucode_amd(unsigned int cpu); #else static inline void __init load_ucode_amd_bsp(unsigned int family) {} static inline void load_ucode_amd_ap(unsigned int family) {} static inline int __init save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } -static inline void reload_ucode_amd(void) {} +static inline void reload_ucode_amd(unsigned int cpu) {} #endif #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 9d0889386a33..95b398df30bd 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -573,7 +573,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) return 0; } -void reload_ucode_amd(void) +void reload_ucode_amd(unsigned int cpu) { struct microcode_amd *mc; u32 rev, dummy __always_unused; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 36583bc4b88c..24254d141178 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -315,7 +315,7 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) #endif } -void reload_early_microcode(void) +void reload_early_microcode(unsigned int cpu) { int vendor, family; @@ -329,7 +329,7 @@ void reload_early_microcode(void) break; case X86_VENDOR_AMD: if (family >= 0x10) - reload_ucode_amd(); + reload_ucode_amd(cpu); break; default: break; @@ -707,7 +707,7 @@ void microcode_bsp_resume(void) if (uci->valid && uci->mc) microcode_ops->apply_microcode(cpu); else if (!uci->mc) - reload_early_microcode(); + reload_early_microcode(cpu); } static struct syscore_ops mc_syscore_ops = { From 44a44b57e88f311c1415be1f567c50050913c149 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Thu, 26 Jan 2023 16:26:17 +0100 Subject: [PATCH 1864/4345] x86/microcode/AMD: Fix mixed steppings support commit 7ff6edf4fef38ab404ee7861f257e28eaaeed35f upstream. The AMD side of the loader has always claimed to support mixed steppings. But somewhere along the way, it broke that by assuming that the cached patch blob is a single one instead of it being one per *node*. So turn it into a per-node one so that each node can stash the blob relevant for it. [ NB: Fixes tag is not really the exactly correct one but it is good enough. ] Fixes: fe055896c040 ("x86/microcode: Merge the early microcode loader") Signed-off-by: Borislav Petkov (AMD) Cc: # 2355370cd941 ("x86/microcode/amd: Remove load_microcode_amd()'s bsp parameter") Cc: # a5ad92134bd1 ("x86/microcode/AMD: Add a @cpu parameter to the reloading functions") Link: https://lore.kernel.org/r/20230130161709.11615-4-bp@alien8.de Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/microcode/amd.c | 34 ++++++++++++++++++----------- 1 file changed, 21 insertions(+), 13 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 95b398df30bd..d3bce6d380ed 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -55,7 +55,9 @@ struct cont_desc { }; static u32 ucode_new_rev; -static u8 amd_ucode_patch[PATCH_MAX_SIZE]; + +/* One blob per node. */ +static u8 amd_ucode_patch[MAX_NUMNODES][PATCH_MAX_SIZE]; /* * Microcode patch container file is prepended to the initrd in cpio @@ -429,7 +431,7 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); #else new_rev = &ucode_new_rev; - patch = &amd_ucode_patch; + patch = &amd_ucode_patch[0]; #endif desc.cpuid_1_eax = cpuid_1_eax; @@ -575,10 +577,10 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) void reload_ucode_amd(unsigned int cpu) { - struct microcode_amd *mc; u32 rev, dummy __always_unused; + struct microcode_amd *mc; - mc = (struct microcode_amd *)amd_ucode_patch; + mc = (struct microcode_amd *)amd_ucode_patch[cpu_to_node(cpu)]; rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); @@ -846,6 +848,8 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) { + struct cpuinfo_x86 *c; + unsigned int nid, cpu; struct ucode_patch *p; enum ucode_state ret; @@ -858,18 +862,22 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz return ret; } - p = find_patch(0); - if (!p) { - return ret; - } else { - if (boot_cpu_data.microcode >= p->patch_id) - return ret; + for_each_node(nid) { + cpu = cpumask_first(cpumask_of_node(nid)); + c = &cpu_data(cpu); + + p = find_patch(cpu); + if (!p) + continue; + + if (c->microcode >= p->patch_id) + continue; ret = UCODE_NEW; - } - memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); - memcpy(amd_ucode_patch, p->data, min_t(u32, p->size, PATCH_MAX_SIZE)); + memset(&amd_ucode_patch[nid], 0, PATCH_MAX_SIZE); + memcpy(&amd_ucode_patch[nid], p->data, min_t(u32, p->size, PATCH_MAX_SIZE)); + } return ret; } From abfed855f05863d292de2d0ebab4656791bab9c8 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Mon, 27 Feb 2023 07:05:40 +0100 Subject: [PATCH 1865/4345] x86/speculation: Allow enabling STIBP with legacy IBRS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6921ed9049bc7457f66c1596c5b78aec0dae4a9d upstream. When plain IBRS is enabled (not enhanced IBRS), the logic in spectre_v2_user_select_mitigation() determines that STIBP is not needed. The IBRS bit implicitly protects against cross-thread branch target injection. However, with legacy IBRS, the IBRS bit is cleared on returning to userspace for performance reasons which leaves userspace threads vulnerable to cross-thread branch target injection against which STIBP protects. Exclude IBRS from the spectre_v2_in_ibrs_mode() check to allow for enabling STIBP (through seccomp/prctl() by default or always-on, if selected by spectre_v2_user kernel cmdline parameter). [ bp: Massage. ] Fixes: 7c693f54c873 ("x86/speculation: Add spectre_v2=ibrs option to support Kernel IBRS") Reported-by: José Oliveira Reported-by: Rodrigo Branco Signed-off-by: KP Singh Signed-off-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230220120127.1975241-1-kpsingh@kernel.org Link: https://lore.kernel.org/r/20230221184908.2349578-1-kpsingh@kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/bugs.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c5034986ea44..c81b8b029b68 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1066,14 +1066,18 @@ spectre_v2_parse_user_cmdline(void) return SPECTRE_V2_USER_CMD_AUTO; } -static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) +static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) { - return mode == SPECTRE_V2_IBRS || - mode == SPECTRE_V2_EIBRS || + return mode == SPECTRE_V2_EIBRS || mode == SPECTRE_V2_EIBRS_RETPOLINE || mode == SPECTRE_V2_EIBRS_LFENCE; } +static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) +{ + return spectre_v2_in_eibrs_mode(mode) || mode == SPECTRE_V2_IBRS; +} + static void __init spectre_v2_user_select_mitigation(void) { @@ -1136,12 +1140,19 @@ spectre_v2_user_select_mitigation(void) } /* - * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible, - * STIBP is not required. + * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP + * is not required. + * + * Enhanced IBRS also protects against cross-thread branch target + * injection in user-mode as the IBRS bit remains always set which + * implicitly enables cross-thread protections. However, in legacy IBRS + * mode, the IBRS bit is set only on kernel entry and cleared on return + * to userspace. This disables the implicit cross-thread protection, + * so allow for STIBP to be selected in that case. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_ibrs_mode(spectre_v2_enabled)) + spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return; /* @@ -2235,7 +2246,7 @@ static ssize_t mmio_stale_data_show_state(char *buf) static char *stibp_state(void) { - if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return ""; switch (spectre_v2_user_stibp) { From 3326ef84cdbe13a3872a6ac9e428cd60ed243f70 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Mon, 27 Feb 2023 07:05:41 +0100 Subject: [PATCH 1866/4345] Documentation/hw-vuln: Document the interaction between IBRS and STIBP commit e02b50ca442e88122e1302d4dbc1b71a4808c13f upstream. Explain why STIBP is needed with legacy IBRS as currently implemented (KERNEL_IBRS) and why STIBP is not needed when enhanced IBRS is enabled. Fixes: 7c693f54c873 ("x86/speculation: Add spectre_v2=ibrs option to support Kernel IBRS") Signed-off-by: KP Singh Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230227060541.1939092-2-kpsingh@kernel.org Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/hw-vuln/spectre.rst | 21 ++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 7e061ed449aa..0fba3758d0da 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -479,8 +479,16 @@ Spectre variant 2 On Intel Skylake-era systems the mitigation covers most, but not all, cases. See :ref:`[3] ` for more details. - On CPUs with hardware mitigation for Spectre variant 2 (e.g. Enhanced - IBRS on x86), retpoline is automatically disabled at run time. + On CPUs with hardware mitigation for Spectre variant 2 (e.g. IBRS + or enhanced IBRS on x86), retpoline is automatically disabled at run time. + + Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at + boot, by setting the IBRS bit, and they're automatically protected against + Spectre v2 variant attacks, including cross-thread branch target injections + on SMT systems (STIBP). In other words, eIBRS enables STIBP too. + + Legacy IBRS systems clear the IBRS bit on exit to userspace and + therefore explicitly enable STIBP for that The retpoline mitigation is turned on by default on vulnerable CPUs. It can be forced on or off by the administrator @@ -504,9 +512,12 @@ Spectre variant 2 For Spectre variant 2 mitigation, individual user programs can be compiled with return trampolines for indirect branches. This protects them from consuming poisoned entries in the branch - target buffer left by malicious software. Alternatively, the - programs can disable their indirect branch speculation via prctl() - (See :ref:`Documentation/userspace-api/spec_ctrl.rst `). + target buffer left by malicious software. + + On legacy IBRS systems, at return to userspace, implicit STIBP is disabled + because the kernel clears the IBRS bit. In this case, the userspace programs + can disable indirect branch speculation via prctl() (See + :ref:`Documentation/userspace-api/spec_ctrl.rst `). On x86, this will turn on STIBP to guard against attacks from the sibling thread when the user program is running, and use IBPB to flush the branch target buffer when switching to/from the program. From c1aa96927b242acfd25457b73cf9d175b58ede7a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 16 Feb 2023 07:57:32 -0700 Subject: [PATCH 1867/4345] brd: return 0/-error from brd_insert_page() commit db0ccc44a20b4bb3039c0f6885a1f9c3323c7673 upstream. It currently returns a page, but callers just check for NULL/page to gauge success. Clean this up and return the appropriate error directly instead. Cc: stable@vger.kernel.org # 5.10+ Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/brd.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/drivers/block/brd.c b/drivers/block/brd.c index cc49a921339f..11078e166368 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -80,11 +80,9 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector) } /* - * Look up and return a brd's page for a given sector. - * If one does not exist, allocate an empty page, and insert that. Then - * return it. + * Insert a new page for a given sector, if one does not already exist. */ -static struct page *brd_insert_page(struct brd_device *brd, sector_t sector) +static int brd_insert_page(struct brd_device *brd, sector_t sector) { pgoff_t idx; struct page *page; @@ -92,7 +90,7 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector) page = brd_lookup_page(brd, sector); if (page) - return page; + return 0; /* * Must use NOIO because we don't want to recurse back into the @@ -101,11 +99,11 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector) gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM; page = alloc_page(gfp_flags); if (!page) - return NULL; + return -ENOMEM; if (radix_tree_preload(GFP_NOIO)) { __free_page(page); - return NULL; + return -ENOMEM; } spin_lock(&brd->brd_lock); @@ -120,8 +118,7 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector) spin_unlock(&brd->brd_lock); radix_tree_preload_end(); - - return page; + return 0; } /* @@ -174,16 +171,17 @@ static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n) { unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT; size_t copy; + int ret; copy = min_t(size_t, n, PAGE_SIZE - offset); - if (!brd_insert_page(brd, sector)) - return -ENOSPC; + ret = brd_insert_page(brd, sector); + if (ret) + return ret; if (copy < n) { sector += copy >> SECTOR_SHIFT; - if (!brd_insert_page(brd, sector)) - return -ENOSPC; + ret = brd_insert_page(brd, sector); } - return 0; + return ret; } /* From 8c64acd24aedf723e5f289d35220467d7cfdc637 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 31 Jan 2023 18:42:43 +0100 Subject: [PATCH 1868/4345] ima: Align ima_file_mmap() parameters with mmap_file LSM hook commit 4971c268b85e1c7a734a61622fc0813c86e2362e upstream. Commit 98de59bfe4b2f ("take calculation of final prot in security_mmap_file() into a helper") moved the code to update prot, to be the actual protections applied to the kernel, to a new helper called mmap_prot(). However, while without the helper ima_file_mmap() was getting the updated prot, with the helper ima_file_mmap() gets the original prot, which contains the protections requested by the application. A possible consequence of this change is that, if an application calls mmap() with only PROT_READ, and the kernel applies PROT_EXEC in addition, that application would have access to executable memory without having this event recorded in the IMA measurement list. This situation would occur for example if the application, before mmap(), calls the personality() system call with READ_IMPLIES_EXEC as the first argument. Align ima_file_mmap() parameters with those of the mmap_file LSM hook, so that IMA can receive both the requested prot and the final prot. Since the requested protections are stored in a new variable, and the final protections are stored in the existing variable, this effectively restores the original behavior of the MMAP_CHECK hook. Cc: stable@vger.kernel.org Fixes: 98de59bfe4b2 ("take calculation of final prot in security_mmap_file() into a helper") Signed-off-by: Roberto Sassu Reviewed-by: Stefan Berger Signed-off-by: Mimi Zohar Signed-off-by: Greg Kroah-Hartman --- include/linux/ima.h | 6 ++++-- security/integrity/ima/ima_main.c | 7 +++++-- security/security.c | 7 ++++--- 3 files changed, 13 insertions(+), 7 deletions(-) diff --git a/include/linux/ima.h b/include/linux/ima.h index 8fa7bcfb2da2..cd8483fa703e 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -18,7 +18,8 @@ extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask); extern void ima_post_create_tmpfile(struct inode *inode); extern void ima_file_free(struct file *file); -extern int ima_file_mmap(struct file *file, unsigned long prot); +extern int ima_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags); extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot); extern int ima_load_data(enum kernel_load_data_id id, bool contents); extern int ima_post_load_data(char *buf, loff_t size, @@ -70,7 +71,8 @@ static inline void ima_file_free(struct file *file) return; } -static inline int ima_file_mmap(struct file *file, unsigned long prot) +static inline int ima_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) { return 0; } diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 600b97677085..dd4b28b11ebe 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -378,7 +378,9 @@ out: /** * ima_file_mmap - based on policy, collect/store measurement. * @file: pointer to the file to be measured (May be NULL) - * @prot: contains the protection that will be applied by the kernel. + * @reqprot: protection requested by the application + * @prot: protection that will be applied by the kernel + * @flags: operational flags * * Measure files being mmapped executable based on the ima_must_measure() * policy decision. @@ -386,7 +388,8 @@ out: * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ -int ima_file_mmap(struct file *file, unsigned long prot) +int ima_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) { u32 secid; diff --git a/security/security.c b/security/security.c index 8ea826ea6167..f9157d5023c6 100644 --- a/security/security.c +++ b/security/security.c @@ -1534,12 +1534,13 @@ static inline unsigned long mmap_prot(struct file *file, unsigned long prot) int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { + unsigned long prot_adj = mmap_prot(file, prot); int ret; - ret = call_int_hook(mmap_file, 0, file, prot, - mmap_prot(file, prot), flags); + + ret = call_int_hook(mmap_file, 0, file, prot, prot_adj, flags); if (ret) return ret; - return ima_file_mmap(file, prot); + return ima_file_mmap(file, prot, prot_adj, flags); } int security_mmap_addr(unsigned long addr) From 6b24bd85ae5c86e54f05874f2edd35ffd2496522 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 13 Feb 2023 11:42:43 +0100 Subject: [PATCH 1869/4345] irqdomain: Fix association race commit b06730a571a9ff1ba5bd6b20bf9e50e5a12f1ec6 upstream. The sanity check for an already mapped virq is done outside of the irq_domain_mutex-protected section which means that an (unlikely) racing association may not be detected. Fix this by factoring out the association implementation, which will also be used in a follow-on change to fix a shared-interrupt mapping race. Fixes: ddaf144c61da ("irqdomain: Refactor irq_domain_associate_many()") Cc: stable@vger.kernel.org # 3.11 Tested-by: Hsin-Yi Wang Tested-by: Mark-PK Tsai Signed-off-by: Johan Hovold Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230213104302.17307-2-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- kernel/irq/irqdomain.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index c6b419db68ef..3cd67b062501 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -516,8 +516,8 @@ void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) irq_domain_clear_mapping(domain, hwirq); } -int irq_domain_associate(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq) +static int irq_domain_associate_locked(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) { struct irq_data *irq_data = irq_get_irq_data(virq); int ret; @@ -530,7 +530,6 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq, if (WARN(irq_data->domain, "error: virq%i is already associated", virq)) return -EINVAL; - mutex_lock(&irq_domain_mutex); irq_data->hwirq = hwirq; irq_data->domain = domain; if (domain->ops->map) { @@ -547,7 +546,6 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq, } irq_data->domain = NULL; irq_data->hwirq = 0; - mutex_unlock(&irq_domain_mutex); return ret; } @@ -558,12 +556,23 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq, domain->mapcount++; irq_domain_set_mapping(domain, hwirq, irq_data); - mutex_unlock(&irq_domain_mutex); irq_clear_status_flags(virq, IRQ_NOREQUEST); return 0; } + +int irq_domain_associate(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) +{ + int ret; + + mutex_lock(&irq_domain_mutex); + ret = irq_domain_associate_locked(domain, virq, hwirq); + mutex_unlock(&irq_domain_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(irq_domain_associate); void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, From e0538aa7e099d494cf523958a84bfbedc5b56d02 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 13 Feb 2023 11:42:44 +0100 Subject: [PATCH 1870/4345] irqdomain: Fix disassociation race commit 3f883c38f5628f46b30bccf090faec054088e262 upstream. The global irq_domain_mutex is held when mapping interrupts from non-hierarchical domains but currently not when disposing them. This specifically means that updates of the domain mapcount is racy (currently only used for statistics in debugfs). Make sure to hold the global irq_domain_mutex also when disposing mappings from non-hierarchical domains. Fixes: 9dc6be3d4193 ("genirq/irqdomain: Add map counter") Cc: stable@vger.kernel.org # 4.13 Tested-by: Hsin-Yi Wang Tested-by: Mark-PK Tsai Signed-off-by: Johan Hovold Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230213104302.17307-3-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- kernel/irq/irqdomain.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 3cd67b062501..e9b3d2028a58 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -495,6 +495,9 @@ void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) return; hwirq = irq_data->hwirq; + + mutex_lock(&irq_domain_mutex); + irq_set_status_flags(irq, IRQ_NOREQUEST); /* remove chip and handler */ @@ -514,6 +517,8 @@ void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) /* Clear reverse map for this hwirq */ irq_domain_clear_mapping(domain, hwirq); + + mutex_unlock(&irq_domain_mutex); } static int irq_domain_associate_locked(struct irq_domain *domain, unsigned int virq, From 306c8b49b5666856dfe74d032e2dc5ac17d3784e Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 13 Feb 2023 11:42:45 +0100 Subject: [PATCH 1871/4345] irqdomain: Drop bogus fwspec-mapping error handling commit e3b7ab025e931accdc2c12acf9b75c6197f1c062 upstream. In case a newly allocated IRQ ever ends up not having any associated struct irq_data it would not even be possible to dispose the mapping. Replace the bogus disposal with a WARN_ON(). This will also be used to fix a shared-interrupt mapping race, hence the CC-stable tag. Fixes: 1e2a7d78499e ("irqdomain: Don't set type when mapping an IRQ") Cc: stable@vger.kernel.org # 4.8 Tested-by: Hsin-Yi Wang Tested-by: Mark-PK Tsai Signed-off-by: Johan Hovold Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230213104302.17307-4-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- kernel/irq/irqdomain.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e9b3d2028a58..1720998933f8 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -837,13 +837,8 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) } irq_data = irq_get_irq_data(virq); - if (!irq_data) { - if (irq_domain_is_hierarchy(domain)) - irq_domain_free_irqs(virq, 1); - else - irq_dispose_mapping(virq); + if (WARN_ON(!irq_data)) return 0; - } /* Store trigger type */ irqd_set_trigger_type(irq_data, type); From 3f32f8492e10ec740552c051a1b0a331490f356b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 6 Mar 2023 13:15:06 -0700 Subject: [PATCH 1872/4345] io_uring: handle TIF_NOTIFY_RESUME when checking for task_work commit b5d3ae202fbfe055aa2a8ae8524531ee1dcab717 upstream. If TIF_NOTIFY_RESUME is set, then we need to call resume_user_mode_work() for PF_IO_WORKER threads. They never return to usermode, hence never get a chance to process any items that are marked by this flag. Most notably this includes the final put of files, but also any throttling markers set by block cgroups. Cc: stable@vger.kernel.org # 5.10+ Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index cf6f8aeb450d..67e820798d25 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2460,6 +2460,13 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) static inline bool io_run_task_work(void) { + /* + * PF_IO_WORKER never returns to userspace, so check here if we have + * notify work that needs processing. + */ + if (current->flags & PF_IO_WORKER && + test_thread_flag(TIF_NOTIFY_RESUME)) + tracehook_notify_resume(NULL); if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); tracehook_notify_signal(); From 3d1f9533a39d16f18ed7e630ecb07c0c2181b2cd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 6 Mar 2023 13:16:38 -0700 Subject: [PATCH 1873/4345] io_uring: mark task TASK_RUNNING before handling resume/task work commit 2f2bb1ffc9983e227424d0787289da5483b0c74f upstream. Just like for task_work, set the task mode to TASK_RUNNING before doing potential resume work. We're not holding any locks at this point, but we may have already set the task state to TASK_INTERRUPTIBLE in preparation for going to sleep waiting for events. Ensure that we set it back to TASK_RUNNING if we have work to process, to avoid warnings on calling blocking operations with !TASK_RUNNING. Fixes: b5d3ae202fbf ("io_uring: handle TIF_NOTIFY_RESUME when checking for task_work") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-lkp/202302062208.24d3e563-oliver.sang@intel.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 67e820798d25..af3d5517c710 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2465,8 +2465,10 @@ static inline bool io_run_task_work(void) * notify work that needs processing. */ if (current->flags & PF_IO_WORKER && - test_thread_flag(TIF_NOTIFY_RESUME)) + test_thread_flag(TIF_NOTIFY_RESUME)) { + __set_current_state(TASK_RUNNING); tracehook_notify_resume(NULL); + } if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); tracehook_notify_signal(); From a442f12e47aa866d09d442522eea14d5280e3a18 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 6 Mar 2023 13:18:27 -0700 Subject: [PATCH 1874/4345] io_uring: add a conditional reschedule to the IOPOLL cancelation loop commit fcc926bb857949dbfa51a7d95f3f5ebc657f198c upstream. If the kernel is configured with CONFIG_PREEMPT_NONE, we could be sitting in a tight loop reaping events but not giving them a chance to finish. This results in a trace ala: rcu: INFO: rcu_sched self-detected stall on CPU rcu: 2-...!: (5249 ticks this GP) idle=935c/1/0x4000000000000000 softirq=4265/4274 fqs=1 (t=5251 jiffies g=465 q=4135 ncpus=4) rcu: rcu_sched kthread starved for 5249 jiffies! g465 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x0 ->cpu=0 rcu: Unless rcu_sched kthread gets sufficient CPU time, OOM is now expected behavior. rcu: RCU grace-period kthread stack dump: task:rcu_sched state:R running task stack:0 pid:12 ppid:2 flags:0x00000008 Call trace: __switch_to+0xb0/0xc8 __schedule+0x43c/0x520 schedule+0x4c/0x98 schedule_timeout+0xbc/0xdc rcu_gp_fqs_loop+0x308/0x344 rcu_gp_kthread+0xd8/0xf0 kthread+0xb8/0xc8 ret_from_fork+0x10/0x20 rcu: Stack dump where RCU GP kthread last ran: Task dump for CPU 0: task:kworker/u8:10 state:R running task stack:0 pid:89 ppid:2 flags:0x0000000a Workqueue: events_unbound io_ring_exit_work Call trace: __switch_to+0xb0/0xc8 0xffff0000c8fefd28 CPU: 2 PID: 95 Comm: kworker/u8:13 Not tainted 6.2.0-rc5-00042-g40316e337c80-dirty #2759 Hardware name: linux,dummy-virt (DT) Workqueue: events_unbound io_ring_exit_work pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) pc : io_do_iopoll+0x344/0x360 lr : io_do_iopoll+0xb8/0x360 sp : ffff800009bebc60 x29: ffff800009bebc60 x28: 0000000000000000 x27: 0000000000000000 x26: ffff0000c0f67d48 x25: ffff0000c0f67840 x24: ffff800008950024 x23: 0000000000000001 x22: 0000000000000000 x21: ffff0000c27d3200 x20: ffff0000c0f67840 x19: ffff0000c0f67800 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000001 x13: 0000000000000001 x12: 0000000000000000 x11: 0000000000000179 x10: 0000000000000870 x9 : ffff800009bebd60 x8 : ffff0000c27d3ad0 x7 : fefefefefefefeff x6 : 0000646e756f626e x5 : ffff0000c0f67840 x4 : 0000000000000000 x3 : ffff0000c2398000 x2 : 0000000000000000 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: io_do_iopoll+0x344/0x360 io_uring_try_cancel_requests+0x21c/0x334 io_ring_exit_work+0x90/0x40c process_one_work+0x1a4/0x254 worker_thread+0x1ec/0x258 kthread+0xb8/0xc8 ret_from_fork+0x10/0x20 Add a cond_resched() in the cancelation IOPOLL loop to fix this. Cc: stable@vger.kernel.org # 5.10+ Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 1 + 1 file changed, 1 insertion(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index af3d5517c710..200cd28679ab 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -9690,6 +9690,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, while (!list_empty_careful(&ctx->iopoll_list)) { io_iopoll_try_reap_events(ctx); ret = true; + cond_resched(); } } From 72783d2af89b622282f7d83b166052292b70c87b Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 6 Mar 2023 13:21:40 -0700 Subject: [PATCH 1875/4345] io_uring/rsrc: disallow multi-source reg buffers commit edd478269640b360c6f301f2baa04abdda563ef3 upstream. If two or more mappings go back to back to each other they can be passed into io_uring to be registered as a single registered buffer. That would even work if mappings came from different sources, e.g. it's possible to mix in this way anon pages and pages from shmem or hugetlb. That is not a problem but it'd rather be less prone if we forbid such mixing. Cc: Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 200cd28679ab..5d07e0e9aadf 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -9057,14 +9057,17 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, pages, vmas); if (pret == nr_pages) { + struct file *file = vmas[0]->vm_file; + /* don't support file backed memory */ for (i = 0; i < nr_pages; i++) { - struct vm_area_struct *vma = vmas[i]; - - if (vma_is_shmem(vma)) + if (vmas[i]->vm_file != file) { + ret = -EINVAL; + break; + } + if (!file) continue; - if (vma->vm_file && - !is_file_hugepages(vma->vm_file)) { + if (!vma_is_shmem(vmas[i]) && !is_file_hugepages(file)) { ret = -EOPNOTSUPP; break; } From 7f3d13241574663c33c7ecda72ff1978a82a4db5 Mon Sep 17 00:00:00 2001 From: David Lamparter Date: Mon, 6 Mar 2023 13:23:06 -0700 Subject: [PATCH 1876/4345] io_uring: remove MSG_NOSIGNAL from recvmsg commit 7605c43d67face310b4b87dee1a28bc0c8cd8c0f upstream. MSG_NOSIGNAL is not applicable for the receiving side, SIGPIPE is generated when trying to write to a "broken pipe". AF_PACKET's packet_recvmsg() does enforce this, giving back EINVAL when MSG_NOSIGNAL is set - making it unuseable in io_uring's recvmsg. Remove MSG_NOSIGNAL from io_recvmsg_prep(). Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: David Lamparter Cc: Eric Dumazet Cc: Jens Axboe Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230224150123.128346-1-equinox@diac24.net Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 5d07e0e9aadf..1016cf13a02a 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -4995,7 +4995,7 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); sr->bgid = READ_ONCE(sqe->buf_group); - sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; + sr->msg_flags = READ_ONCE(sqe->msg_flags); if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; From 246f26664b2ec47b4d6ba41b5c2b779550bda61d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 6 Mar 2023 13:28:57 -0700 Subject: [PATCH 1877/4345] io_uring/poll: allow some retries for poll triggering spuriously commit c16bda37594f83147b167d381d54c010024efecf upstream. If we get woken spuriously when polling and fail the operation with -EAGAIN again, then we generally only allow polling again if data had been transferred at some point. This is indicated with REQ_F_PARTIAL_IO. However, if the spurious poll triggers when the socket was originally empty, then we haven't transferred data yet and we will fail the poll re-arm. This either punts the socket to io-wq if it's blocking, or it fails the request with -EAGAIN if not. Neither condition is desirable, as the former will slow things down, while the latter will make the application confused. We want to ensure that a repeated poll trigger doesn't lead to infinite work making no progress, that's what the REQ_F_PARTIAL_IO check was for. But it doesn't protect against a loop post the first receive, and it's unnecessarily strict if we started out with an empty socket. Add a somewhat random retry count, just to put an upper limit on the potential number of retries that will be done. This should be high enough that we won't really hit it in practice, unless something needs to be aborted anyway. Cc: stable@vger.kernel.org # v5.10+ Link: https://github.com/axboe/liburing/issues/364 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 1016cf13a02a..445afda927f4 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -486,6 +486,7 @@ struct io_poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; + int retries; struct wait_queue_entry wait; }; @@ -5749,6 +5750,14 @@ enum { IO_APOLL_READY }; +/* + * We can't reliably detect loops in repeated poll triggers and issue + * subsequently failing. But rather than fail these immediately, allow a + * certain amount of retries before we give up. Given that this condition + * should _rarely_ trigger even once, we should be fine with a larger value. + */ +#define APOLL_MAX_RETRY 128 + static int io_arm_poll_handler(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; @@ -5760,8 +5769,6 @@ static int io_arm_poll_handler(struct io_kiocb *req) if (!req->file || !file_can_poll(req->file)) return IO_APOLL_ABORTED; - if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED) - return IO_APOLL_ABORTED; if (!def->pollin && !def->pollout) return IO_APOLL_ABORTED; @@ -5779,8 +5786,13 @@ static int io_arm_poll_handler(struct io_kiocb *req) if (req->flags & REQ_F_POLLED) { apoll = req->apoll; kfree(apoll->double_poll); + if (unlikely(!--apoll->poll.retries)) { + apoll->double_poll = NULL; + return IO_APOLL_ABORTED; + } } else { apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); + apoll->poll.retries = APOLL_MAX_RETRY; } if (unlikely(!apoll)) return IO_APOLL_ABORTED; From ae2340769ed3c2a3d3de0fab64b667db6df27744 Mon Sep 17 00:00:00 2001 From: Dmitry Fomin Date: Sat, 25 Feb 2023 21:43:21 +0300 Subject: [PATCH 1878/4345] ALSA: ice1712: Do not left ice->gpio_mutex locked in aureon_add_controls() commit 951606a14a8901e3551fe4d8d3cedd73fe954ce1 upstream. If snd_ctl_add() fails in aureon_add_controls(), it immediately returns and leaves ice->gpio_mutex locked. ice->gpio_mutex locks in snd_ice1712_save_gpio_status and unlocks in snd_ice1712_restore_gpio_status(ice). It seems that the mutex is required only for aureon_cs8415_get(), so snd_ice1712_restore_gpio_status(ice) can be placed just after that. Compile tested only. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Dmitry Fomin Cc: Link: https://lore.kernel.org/r/20230225184322.6286-1-fomindmitriyfoma@mail.ru Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/ice1712/aureon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/ice1712/aureon.c b/sound/pci/ice1712/aureon.c index 9a30f6d35d13..40a0e0095030 100644 --- a/sound/pci/ice1712/aureon.c +++ b/sound/pci/ice1712/aureon.c @@ -1892,6 +1892,7 @@ static int aureon_add_controls(struct snd_ice1712 *ice) unsigned char id; snd_ice1712_save_gpio_status(ice); id = aureon_cs8415_get(ice, CS8415_ID); + snd_ice1712_restore_gpio_status(ice); if (id != 0x41) dev_info(ice->card->dev, "No CS8415 chip. Skipping CS8415 controls.\n"); @@ -1909,7 +1910,6 @@ static int aureon_add_controls(struct snd_ice1712 *ice) kctl->id.device = ice->pcm->device; } } - snd_ice1712_restore_gpio_status(ice); } return 0; From a9cd89463ea44606b68c149da1b27e1c1ee704de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C5=81ukasz=20Stelmach?= Date: Thu, 23 Feb 2023 08:47:48 +0100 Subject: [PATCH 1879/4345] ALSA: hda/realtek: Add quirk for HP EliteDesk 800 G6 Tower PC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ea24b9953bcd3889f77a66e7f1d7e86e995dd9c3 upstream. HP EliteDesk 800 G6 Tower PC (103c:870c) requires a quirk for enabling headset-mic. Signed-off-by: Łukasz Stelmach Cc: Link: https://bugzilla.kernel.org/show_bug.cgi?id=217008 Link: https://lore.kernel.org/r/20230223074749.1026060-1-l.stelmach@samsung.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index fffa681313b6..f2ef75c8de42 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11153,6 +11153,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0698, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x069f, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), + SND_PCI_QUIRK(0x103c, 0x870c, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2), From ab22799f11e378a37d1c8c4e47e796f84be97a60 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 10 Jan 2023 09:53:27 +0800 Subject: [PATCH 1880/4345] jbd2: fix data missing when reusing bh which is ready to be checkpointed commit e6b9bd7290d334451ce054e98e752abc055e0034 upstream. Following process will make data lost and could lead to a filesystem corrupted problem: 1. jh(bh) is inserted into T1->t_checkpoint_list, bh is dirty, and jh->b_transaction = NULL 2. T1 is added into journal->j_checkpoint_transactions. 3. Get bh prepare to write while doing checkpoing: PA PB do_get_write_access jbd2_log_do_checkpoint spin_lock(&jh->b_state_lock) if (buffer_dirty(bh)) clear_buffer_dirty(bh) // clear buffer dirty set_buffer_jbddirty(bh) transaction = journal->j_checkpoint_transactions jh = transaction->t_checkpoint_list if (!buffer_dirty(bh)) __jbd2_journal_remove_checkpoint(jh) // bh won't be flushed jbd2_cleanup_journal_tail __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved) 4. Aborting journal/Power-cut before writing latest bh on journal area. In this way we get a corrupted filesystem with bh's data lost. Fix it by moving the clearing of buffer_dirty bit just before the call to __jbd2_journal_file_buffer(), both bit clearing and jh->b_transaction assignment are under journal->j_list_lock locked, so that jbd2_log_do_checkpoint() will wait until jh's new transaction fininshed even bh is currently not dirty. And journal_shrink_one_cp_list() won't remove jh from checkpoint list if the buffer head is reused in do_get_write_access(). Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216898 Cc: Signed-off-by: Zhihao Cheng Signed-off-by: zhanchengbin Suggested-by: Jan Kara Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230110015327.1181863-1-chengzhihao1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/jbd2/transaction.c | 50 +++++++++++++++++++++++++------------------ 1 file changed, 29 insertions(+), 21 deletions(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 86472212cce1..1923528154b5 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -984,36 +984,28 @@ repeat: * ie. locked but not dirty) or tune2fs (which may actually have * the buffer dirtied, ugh.) */ - if (buffer_dirty(bh)) { + if (buffer_dirty(bh) && jh->b_transaction) { + warn_dirty_buffer(bh); /* - * First question: is this buffer already part of the current - * transaction or the existing committing transaction? - */ - if (jh->b_transaction) { - J_ASSERT_JH(jh, - jh->b_transaction == transaction || - jh->b_transaction == - journal->j_committing_transaction); - if (jh->b_next_transaction) - J_ASSERT_JH(jh, jh->b_next_transaction == - transaction); - warn_dirty_buffer(bh); - } - /* - * In any case we need to clean the dirty flag and we must - * do it under the buffer lock to be sure we don't race - * with running write-out. + * We need to clean the dirty flag and we must do it under the + * buffer lock to be sure we don't race with running write-out. */ JBUFFER_TRACE(jh, "Journalling dirty buffer"); clear_buffer_dirty(bh); + /* + * The buffer is going to be added to BJ_Reserved list now and + * nothing guarantees jbd2_journal_dirty_metadata() will be + * ever called for it. So we need to set jbddirty bit here to + * make sure the buffer is dirtied and written out when the + * journaling machinery is done with it. + */ set_buffer_jbddirty(bh); } - unlock_buffer(bh); - error = -EROFS; if (is_handle_aborted(handle)) { spin_unlock(&jh->b_state_lock); + unlock_buffer(bh); goto out; } error = 0; @@ -1023,8 +1015,10 @@ repeat: * b_next_transaction points to it */ if (jh->b_transaction == transaction || - jh->b_next_transaction == transaction) + jh->b_next_transaction == transaction) { + unlock_buffer(bh); goto done; + } /* * this is the first time this transaction is touching this buffer, @@ -1048,10 +1042,24 @@ repeat: */ smp_wmb(); spin_lock(&journal->j_list_lock); + if (test_clear_buffer_dirty(bh)) { + /* + * Execute buffer dirty clearing and jh->b_transaction + * assignment under journal->j_list_lock locked to + * prevent bh being removed from checkpoint list if + * the buffer is in an intermediate state (not dirty + * and jh->b_transaction is NULL). + */ + JBUFFER_TRACE(jh, "Journalling dirty buffer"); + set_buffer_jbddirty(bh); + } __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); spin_unlock(&journal->j_list_lock); + unlock_buffer(bh); goto done; } + unlock_buffer(bh); + /* * If there is already a copy-out version of this buffer, then we don't * need to make another one From d738789ae9ec47d3458a008788f3cdc862ebf0cb Mon Sep 17 00:00:00 2001 From: Jun Nie Date: Tue, 3 Jan 2023 09:45:16 +0800 Subject: [PATCH 1881/4345] ext4: optimize ea_inode block expansion commit 1e9d62d252812575ded7c620d8fc67c32ff06c16 upstream. Copy ea data from inode entry when expanding ea block if possible. Then remove the ea entry if expansion success. Thus memcpy to a temporary buffer may be avoided. If the expansion fails, we do not need to recovery the removed ea entry neither in this way. Reported-by: syzbot+2dacb8f015bf1420155f@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=3613786cb88c93aa1c6a279b1df6a7b201347d08 Link: https://lore.kernel.org/r/20230103014517.495275-2-jun.nie@linaro.org Cc: stable@kernel.org Signed-off-by: Jun Nie Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 6bf1c62eff04..bd073bfe03df 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2564,9 +2564,8 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); - buffer = kvmalloc(value_size, GFP_NOFS); b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS); - if (!is || !bs || !buffer || !b_entry_name) { + if (!is || !bs || !b_entry_name) { error = -ENOMEM; goto out; } @@ -2578,12 +2577,18 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, /* Save the entry name and the entry value */ if (entry->e_value_inum) { + buffer = kvmalloc(value_size, GFP_NOFS); + if (!buffer) { + error = -ENOMEM; + goto out; + } + error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; } else { size_t value_offs = le16_to_cpu(entry->e_value_offs); - memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size); + buffer = (void *)IFIRST(header) + value_offs; } memcpy(b_entry_name, entry->e_name, entry->e_name_len); @@ -2598,25 +2603,26 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, if (error) goto out; - /* Remove the chosen entry from the inode */ - error = ext4_xattr_ibody_set(handle, inode, &i, is); - if (error) - goto out; - i.value = buffer; i.value_len = value_size; error = ext4_xattr_block_find(inode, &i, bs); if (error) goto out; - /* Add entry which was removed from the inode into the block */ + /* Move ea entry from the inode into the block */ error = ext4_xattr_block_set(handle, inode, &i, bs); if (error) goto out; - error = 0; + + /* Remove the chosen entry from the inode */ + i.value = NULL; + i.value_len = 0; + error = ext4_xattr_ibody_set(handle, inode, &i, is); + out: kfree(b_entry_name); - kvfree(buffer); + if (entry->e_value_inum && buffer) + kvfree(buffer); if (is) brelse(is->iloc.bh); if (bs) From 0dc0fa313bb4e86382a3e7125429710d44383196 Mon Sep 17 00:00:00 2001 From: Jun Nie Date: Tue, 3 Jan 2023 09:45:17 +0800 Subject: [PATCH 1882/4345] ext4: refuse to create ea block when umounted commit f31173c19901a96bb2ebf6bcfec8a08df7095c91 upstream. The ea block expansion need to access s_root while it is already set as NULL when umount is triggered. Refuse this request to avoid panic. Reported-by: syzbot+2dacb8f015bf1420155f@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=3613786cb88c93aa1c6a279b1df6a7b201347d08 Link: https://lore.kernel.org/r/20230103014517.495275-3-jun.nie@linaro.org Cc: stable@kernel.org Signed-off-by: Jun Nie Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index bd073bfe03df..b80ad5a7b05c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1415,6 +1415,13 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle, uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) }; int err; + if (inode->i_sb->s_root == NULL) { + ext4_warning(inode->i_sb, + "refuse to create EA inode when umounting"); + WARN_ON(1); + return ERR_PTR(-EINVAL); + } + /* * Let the next inode be the goal, so we try and allocate the EA inode * in the same group, or nearby one. From e6409208c13f7c56adc12dd795abf4141e3d5e64 Mon Sep 17 00:00:00 2001 From: Louis Rannou Date: Fri, 3 Feb 2023 09:07:54 +0200 Subject: [PATCH 1883/4345] mtd: spi-nor: Fix shift-out-of-bounds in spi_nor_set_erase_type commit f0f0cfdc3a024e21161714f2e05f0df3b84d42ad upstream. spi_nor_set_erase_type() was used either to set or to mask out an erase type. When we used it to mask out an erase type a shift-out-of-bounds was hit: UBSAN: shift-out-of-bounds in drivers/mtd/spi-nor/core.c:2237:24 shift exponent 4294967295 is too large for 32-bit type 'int' The setting of the size_{shift, mask} and of the opcode are unnecessary when the erase size is zero, as throughout the code just the erase size is considered to determine whether an erase type is supported or not. Setting the opcode to 0xFF was wrong too as nobody guarantees that 0xFF is an unused opcode. Thus when masking out an erase type, just set the erase size to zero. This will fix the shift-out-of-bounds. Fixes: 5390a8df769e ("mtd: spi-nor: add support to non-uniform SFDP SPI NOR flash memories") Cc: stable@vger.kernel.org Reported-by: Alexander Stein Signed-off-by: Louis Rannou Tested-by: Alexander Stein Link: https://lore.kernel.org/r/20230203070754.50677-1-tudor.ambarus@linaro.org [ta: refine changes, new commit message, fix compilation error] Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/spi-nor/core.c | 9 +++++++++ drivers/mtd/spi-nor/core.h | 1 + drivers/mtd/spi-nor/sfdp.c | 4 ++-- 3 files changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index 2c256d455c9f..342215231932 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -2424,6 +2424,15 @@ void spi_nor_set_erase_type(struct spi_nor_erase_type *erase, u32 size, erase->size_mask = (1 << erase->size_shift) - 1; } +/** + * spi_nor_mask_erase_type() - mask out a SPI NOR erase type + * @erase: pointer to a structure that describes a SPI NOR erase type + */ +void spi_nor_mask_erase_type(struct spi_nor_erase_type *erase) +{ + erase->size = 0; +} + /** * spi_nor_init_uniform_erase_map() - Initialize uniform erase map * @map: the erase map of the SPI NOR diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h index 6f62ee861231..788775bb6795 100644 --- a/drivers/mtd/spi-nor/core.h +++ b/drivers/mtd/spi-nor/core.h @@ -424,6 +424,7 @@ void spi_nor_set_pp_settings(struct spi_nor_pp_command *pp, u8 opcode, void spi_nor_set_erase_type(struct spi_nor_erase_type *erase, u32 size, u8 opcode); +void spi_nor_mask_erase_type(struct spi_nor_erase_type *erase); struct spi_nor_erase_region * spi_nor_region_next(struct spi_nor_erase_region *region); void spi_nor_init_uniform_erase_map(struct spi_nor_erase_map *map, diff --git a/drivers/mtd/spi-nor/sfdp.c b/drivers/mtd/spi-nor/sfdp.c index 08de2a2b4452..9dc0528ea884 100644 --- a/drivers/mtd/spi-nor/sfdp.c +++ b/drivers/mtd/spi-nor/sfdp.c @@ -852,7 +852,7 @@ spi_nor_init_non_uniform_erase_map(struct spi_nor *nor, */ for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) if (!(regions_erase_type & BIT(erase[i].idx))) - spi_nor_set_erase_type(&erase[i], 0, 0xFF); + spi_nor_mask_erase_type(&erase[i]); return 0; } @@ -1063,7 +1063,7 @@ static int spi_nor_parse_4bait(struct spi_nor *nor, erase_type[i].opcode = (dwords[1] >> erase_type[i].idx * 8) & 0xFF; else - spi_nor_set_erase_type(&erase_type[i], 0u, 0xFF); + spi_nor_mask_erase_type(&erase_type[i]); } /* From 3383f79d6b0a0641f767052fda3952dd1805d2d6 Mon Sep 17 00:00:00 2001 From: Pingfan Liu Date: Wed, 15 Feb 2023 19:23:40 +0800 Subject: [PATCH 1884/4345] dm: add cond_resched() to dm_wq_work() commit 0ca44fcef241768fd25ee763b3d203b9852f269b upstream. Otherwise the while() loop in dm_wq_work() can result in a "dead loop" on systems that have preemption disabled. This is particularly problematic on single cpu systems. Cc: stable@vger.kernel.org Signed-off-by: Pingfan Liu Acked-by: Ming Lei Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7163ecc4d53f..c60febd14be1 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2393,6 +2393,7 @@ static void dm_wq_work(struct work_struct *work) break; submit_bio_noacct(bio); + cond_resched(); } } From 73090cebe3f3f4c5a13d2e76b5da4761fb15186b Mon Sep 17 00:00:00 2001 From: Bitterblue Smith Date: Sun, 8 Jan 2023 17:08:16 +0200 Subject: [PATCH 1885/4345] wifi: rtl8xxxu: Use a longer retry limit of 48 commit 2a86aa9a1892d60ef2e3f310f5b42b8b05546d65 upstream. The Realtek rate control algorithm goes back and forth a lot between the highest and the lowest rate it's allowed to use. This is due to a lot of frames being dropped because the retry limits set by IEEE80211_CONF_CHANGE_RETRY_LIMITS are too low. (Experimentally, they are 4 for long frames and 7 for short frames.) The vendor drivers hardcode the value 48 for both retry limits (for station mode), which makes dropped frames very rare and thus the rate control is more stable. Because most Realtek chips handle the rate control in the firmware, which can't be modified, ignore the limits set by IEEE80211_CONF_CHANGE_RETRY_LIMITS and use the value 48 (set during chip initialisation), same as the vendor drivers. Cc: stable@vger.kernel.org Signed-off-by: Bitterblue Smith Reviewed-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/477d745b-6bac-111d-403c-487fc19aa30d@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 376782b7aba8..deef1c09de31 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -5908,7 +5908,6 @@ static int rtl8xxxu_config(struct ieee80211_hw *hw, u32 changed) { struct rtl8xxxu_priv *priv = hw->priv; struct device *dev = &priv->udev->dev; - u16 val16; int ret = 0, channel; bool ht40; @@ -5918,14 +5917,6 @@ static int rtl8xxxu_config(struct ieee80211_hw *hw, u32 changed) __func__, hw->conf.chandef.chan->hw_value, changed, hw->conf.chandef.width); - if (changed & IEEE80211_CONF_CHANGE_RETRY_LIMITS) { - val16 = ((hw->conf.long_frame_max_tx_count << - RETRY_LIMIT_LONG_SHIFT) & RETRY_LIMIT_LONG_MASK) | - ((hw->conf.short_frame_max_tx_count << - RETRY_LIMIT_SHORT_SHIFT) & RETRY_LIMIT_SHORT_MASK); - rtl8xxxu_write16(priv, REG_RETRY_LIMIT, val16); - } - if (changed & IEEE80211_CONF_CHANGE_CHANNEL) { switch (hw->conf.chandef.width) { case NL80211_CHAN_WIDTH_20_NOHT: From 2cfe78619b0de6d2da773978bc2d22797212eaa7 Mon Sep 17 00:00:00 2001 From: Alexander Wetzel Date: Tue, 24 Jan 2023 15:18:56 +0100 Subject: [PATCH 1886/4345] wifi: cfg80211: Fix use after free for wext commit 015b8cc5e7c4d7bb671f1984d7b7338c310b185b upstream. Key information in wext.connect is not reset on (re)connect and can hold data from a previous connection. Reset key data to avoid that drivers or mac80211 incorrectly detect a WEP connection request and access the freed or already reused memory. Additionally optimize cfg80211_sme_connect() and avoid an useless schedule of conn_work. Fixes: fffd0934b939 ("cfg80211: rework key operation") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230124141856.356646-1-alexander@wetzel-home.de Signed-off-by: Alexander Wetzel Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/wireless/sme.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 060e365c8259..f4d98ed8fa31 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -269,6 +269,15 @@ void cfg80211_conn_work(struct work_struct *work) rtnl_unlock(); } +static void cfg80211_step_auth_next(struct cfg80211_conn *conn, + struct cfg80211_bss *bss) +{ + memcpy(conn->bssid, bss->bssid, ETH_ALEN); + conn->params.bssid = conn->bssid; + conn->params.channel = bss->channel; + conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; +} + /* Returned bss is reference counted and must be cleaned up appropriately. */ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) { @@ -286,10 +295,7 @@ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) if (!bss) return NULL; - memcpy(wdev->conn->bssid, bss->bssid, ETH_ALEN); - wdev->conn->params.bssid = wdev->conn->bssid; - wdev->conn->params.channel = bss->channel; - wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; + cfg80211_step_auth_next(wdev->conn, bss); schedule_work(&rdev->conn_work); return bss; @@ -568,7 +574,12 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, wdev->conn->params.ssid_len = wdev->ssid_len; /* see if we have the bss already */ - bss = cfg80211_get_conn_bss(wdev); + bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, + wdev->conn->params.bssid, + wdev->conn->params.ssid, + wdev->conn->params.ssid_len, + wdev->conn_bss_type, + IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (prev_bssid) { memcpy(wdev->conn->prev_bssid, prev_bssid, ETH_ALEN); @@ -579,6 +590,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, if (bss) { enum nl80211_timeout_reason treason; + cfg80211_step_auth_next(wdev->conn, bss); err = cfg80211_conn_do_work(wdev, &treason); cfg80211_put_bss(wdev->wiphy, bss); } else { @@ -1245,6 +1257,15 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, } else { if (WARN_ON(connkeys)) return -EINVAL; + + /* connect can point to wdev->wext.connect which + * can hold key data from a previous connection + */ + connect->key = NULL; + connect->key_len = 0; + connect->key_idx = 0; + connect->crypto.cipher_group = 0; + connect->crypto.n_ciphers_pairwise = 0; } wdev->connect_keys = connkeys; From 17f81b127712afb47060941a0290db9114b2f83a Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 1 Feb 2023 12:39:41 -0800 Subject: [PATCH 1887/4345] thermal: intel: powerclamp: Fix cur_state for multi package system commit 8e47363588377e1bdb65e2b020b409cfb44dd260 upstream. The powerclamp cooling device cur_state shows actual idle observed by package C-state idle counters. But the implementation is not sufficient for multi package or multi die system. The cur_state value is incorrect. On these systems, these counters must be read from each package/die and somehow aggregate them. But there is no good method for aggregation. It was not a problem when explicit CPU model addition was required to enable intel powerclamp. In this way certain CPU models could have been avoided. But with the removal of CPU model check with the availability of Package C-state counters, the driver is loaded on most of the recent systems. For multi package/die systems, just show the actual target idle state, the system is trying to achieve. In powerclamp this is the user set state minus one. Also there is no use of starting a worker thread for polling package C-state counters and applying any compensation for multiple package or multiple die systems. Fixes: b721ca0d1927 ("thermal/powerclamp: remove cpu whitelist") Signed-off-by: Srinivas Pandruvada Cc: 4.14+ # 4.14+ Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/thermal/intel/intel_powerclamp.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c index fb04470d7d4b..6e7c230d308f 100644 --- a/drivers/thermal/intel/intel_powerclamp.c +++ b/drivers/thermal/intel/intel_powerclamp.c @@ -57,6 +57,7 @@ static unsigned int target_mwait; static struct dentry *debug_dir; +static bool poll_pkg_cstate_enable; /* user selected target */ static unsigned int set_target_ratio; @@ -262,6 +263,9 @@ static unsigned int get_compensation(int ratio) { unsigned int comp = 0; + if (!poll_pkg_cstate_enable) + return 0; + /* we only use compensation if all adjacent ones are good */ if (ratio == 1 && cal_data[ratio].confidence >= CONFIDENCE_OK && @@ -534,7 +538,8 @@ static int start_power_clamp(void) control_cpu = cpumask_first(cpu_online_mask); clamping = true; - schedule_delayed_work(&poll_pkg_cstate_work, 0); + if (poll_pkg_cstate_enable) + schedule_delayed_work(&poll_pkg_cstate_work, 0); /* start one kthread worker per online cpu */ for_each_online_cpu(cpu) { @@ -603,11 +608,15 @@ static int powerclamp_get_max_state(struct thermal_cooling_device *cdev, static int powerclamp_get_cur_state(struct thermal_cooling_device *cdev, unsigned long *state) { - if (true == clamping) - *state = pkg_cstate_ratio_cur; - else + if (clamping) { + if (poll_pkg_cstate_enable) + *state = pkg_cstate_ratio_cur; + else + *state = set_target_ratio; + } else { /* to save power, do not poll idle ratio while not clamping */ *state = -1; /* indicates invalid state */ + } return 0; } @@ -732,6 +741,9 @@ static int __init powerclamp_init(void) goto exit_unregister; } + if (topology_max_packages() == 1 && topology_max_die_per_package() == 1) + poll_pkg_cstate_enable = true; + cooling_dev = thermal_cooling_device_register("intel_powerclamp", NULL, &powerclamp_cooling_ops); if (IS_ERR(cooling_dev)) { From 07e375c18af0d661c128937a88c54c332d04bc95 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Sun, 22 Jan 2023 14:03:56 -0500 Subject: [PATCH 1888/4345] dm flakey: fix logic when corrupting a bio commit aa56b9b75996ff4c76a0a4181c2fa0206c3d91cc upstream. If "corrupt_bio_byte" is set to corrupt reads and corrupt_bio_flags is used, dm-flakey would erroneously return all writes as errors. Likewise, if "corrupt_bio_byte" is set to corrupt writes, dm-flakey would return errors for all reads. Fix the logic so that if fc->corrupt_bio_byte is non-zero, dm-flakey will not abort reads on writes with an error. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka Reviewed-by: Sweet Tea Dorminy Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-flakey.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index a2cc9e45cbba..e4d52caf816f 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -359,9 +359,11 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) /* * Corrupt matching writes. */ - if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == WRITE)) { - if (all_corrupt_bio_flags_match(bio, fc)) - corrupt_bio_data(bio, fc); + if (fc->corrupt_bio_byte) { + if (fc->corrupt_bio_rw == WRITE) { + if (all_corrupt_bio_flags_match(bio, fc)) + corrupt_bio_data(bio, fc); + } goto map_bio; } @@ -387,13 +389,14 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, return DM_ENDIO_DONE; if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { - if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && - all_corrupt_bio_flags_match(bio, fc)) { - /* - * Corrupt successful matching READs while in down state. - */ - corrupt_bio_data(bio, fc); - + if (fc->corrupt_bio_byte) { + if ((fc->corrupt_bio_rw == READ) && + all_corrupt_bio_flags_match(bio, fc)) { + /* + * Corrupt successful matching READs while in down state. + */ + corrupt_bio_data(bio, fc); + } } else if (!test_bit(DROP_WRITES, &fc->flags) && !test_bit(ERROR_WRITES, &fc->flags)) { /* From f2b478228bfdd11e358c5bc197561331f5d5c394 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Sun, 22 Jan 2023 14:02:57 -0500 Subject: [PATCH 1889/4345] dm flakey: don't corrupt the zero page commit f50714b57aecb6b3dc81d578e295f86d9c73f078 upstream. When we need to zero some range on a block device, the function __blkdev_issue_zero_pages submits a write bio with the bio vector pointing to the zero page. If we use dm-flakey with corrupt bio writes option, it will corrupt the content of the zero page which results in crashes of various userspace programs. Glibc assumes that memory returned by mmap is zeroed and it uses it for calloc implementation; if the newly mapped memory is not zeroed, calloc will return non-zeroed memory. Fix this bug by testing if the page is equal to ZERO_PAGE(0) and avoiding the corruption in this case. Cc: stable@vger.kernel.org Fixes: a00f5276e266 ("dm flakey: Properly corrupt multi-page bios.") Signed-off-by: Mikulas Patocka Reviewed-by: Sweet Tea Dorminy Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-flakey.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index e4d52caf816f..36a4ef51ecaa 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -301,8 +301,11 @@ static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc) */ bio_for_each_segment(bvec, bio, iter) { if (bio_iter_len(bio, iter) > corrupt_bio_byte) { - char *segment = (page_address(bio_iter_page(bio, iter)) - + bio_iter_offset(bio, iter)); + char *segment; + struct page *page = bio_iter_page(bio, iter); + if (unlikely(page == ZERO_PAGE(0))) + break; + segment = (page_address(page) + bio_iter_offset(bio, iter)); segment[corrupt_bio_byte] = fc->corrupt_bio_value; DMDEBUG("Corrupting data bio=%p by writing %u to byte %u " "(rw=%c bi_opf=%u bi_sector=%llu size=%u)\n", From aaa2d2249c90b3ec91dc98b5a93958cdee2f685f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Feb 2023 11:58:37 +0100 Subject: [PATCH 1890/4345] ARM: dts: exynos: correct TMU phandle in Exynos4210 commit 408ab6786dbf6dd696488054c9559681112ef994 upstream. TMU node uses 0 as thermal-sensor-cells, thus thermal zone referencing it must not have an argument to phandle. Since thermal-sensors property is already defined in included exynos4-cpu-thermal.dtsi, drop it from exynos4210.dtsi to fix the error and remoev redundancy. Fixes: 9843a2236003 ("ARM: dts: Provide dt bindings identical for Exynos TMU") Cc: Link: https://lore.kernel.org/r/20230209105841.779596-2-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos4210.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi index fddc661ded28..448e1b153a01 100644 --- a/arch/arm/boot/dts/exynos4210.dtsi +++ b/arch/arm/boot/dts/exynos4210.dtsi @@ -382,7 +382,6 @@ &cpu_thermal { polling-delay-passive = <0>; polling-delay = <0>; - thermal-sensors = <&tmu 0>; }; &gic { From 135e968d6a86e6091a9c68851d39d9d5e8bab19c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Feb 2023 11:58:36 +0100 Subject: [PATCH 1891/4345] ARM: dts: exynos: correct TMU phandle in Exynos4 commit 8e4505e617a80f601e2f53a917611777f128f925 upstream. TMU node uses 0 as thermal-sensor-cells, thus thermal zone referencing it must not have an argument to phandle. Fixes: 328829a6ad70 ("ARM: dts: define default thermal-zones for exynos4") Cc: Link: https://lore.kernel.org/r/20230209105841.779596-1-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos4-cpu-thermal.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi b/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi index 021d9fc1b492..27a1a8952665 100644 --- a/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi +++ b/arch/arm/boot/dts/exynos4-cpu-thermal.dtsi @@ -10,7 +10,7 @@ / { thermal-zones { cpu_thermal: cpu-thermal { - thermal-sensors = <&tmu 0>; + thermal-sensors = <&tmu>; polling-delay-passive = <0>; polling-delay = <0>; trips { From 136d6f3c5dc96d5bc67e63cd607f343158f7b7ba Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Feb 2023 11:58:41 +0100 Subject: [PATCH 1892/4345] ARM: dts: exynos: correct TMU phandle in Odroid XU3 family commit a3583e92d188ec6c58c7f603ac5e72dd8a11c21a upstream. TMU node uses 0 as thermal-sensor-cells, thus thermal zone referencing it must not have an argument to phandle. This was not critical before, but since rework of thermal Devicetree initialization in the commit 3fd6d6e2b4e8 ("thermal/of: Rework the thermal device tree initialization"), this leads to errors registering thermal zones other than first one: thermal_sys: cpu0-thermal: Failed to read thermal-sensors cells: -2 thermal_sys: Failed to find thermal zone for tmu id=0 exynos-tmu 10064000.tmu: Failed to register sensor: -2 exynos-tmu: probe of 10064000.tmu failed with error -2 Fixes: f1722d7dd8b8 ("ARM: dts: Define default thermal-zones for exynos5422") Cc: Link: https://lore.kernel.org/r/20230209105841.779596-6-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi index 5da2d81e3be2..099ed4384be8 100644 --- a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi +++ b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi @@ -50,7 +50,7 @@ thermal-zones { cpu0_thermal: cpu0-thermal { - thermal-sensors = <&tmu_cpu0 0>; + thermal-sensors = <&tmu_cpu0>; polling-delay-passive = <250>; polling-delay = <0>; trips { @@ -139,7 +139,7 @@ }; }; cpu1_thermal: cpu1-thermal { - thermal-sensors = <&tmu_cpu1 0>; + thermal-sensors = <&tmu_cpu1>; polling-delay-passive = <250>; polling-delay = <0>; trips { @@ -212,7 +212,7 @@ }; }; cpu2_thermal: cpu2-thermal { - thermal-sensors = <&tmu_cpu2 0>; + thermal-sensors = <&tmu_cpu2>; polling-delay-passive = <250>; polling-delay = <0>; trips { @@ -285,7 +285,7 @@ }; }; cpu3_thermal: cpu3-thermal { - thermal-sensors = <&tmu_cpu3 0>; + thermal-sensors = <&tmu_cpu3>; polling-delay-passive = <250>; polling-delay = <0>; trips { @@ -358,7 +358,7 @@ }; }; gpu_thermal: gpu-thermal { - thermal-sensors = <&tmu_gpu 0>; + thermal-sensors = <&tmu_gpu>; polling-delay-passive = <250>; polling-delay = <0>; trips { From d1887cca652603076ae814c16935c8a956d6aa28 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Feb 2023 11:58:38 +0100 Subject: [PATCH 1893/4345] ARM: dts: exynos: correct TMU phandle in Exynos5250 commit 33e2c595e2e4016991ead44933a29d1ef93d5f26 upstream. TMU node uses 0 as thermal-sensor-cells, thus thermal zone referencing it must not have an argument to phandle. Cc: Fixes: 9843a2236003 ("ARM: dts: Provide dt bindings identical for Exynos TMU") Link: https://lore.kernel.org/r/20230209105841.779596-3-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos5250.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi index bd2d8835dd36..62051e600b32 100644 --- a/arch/arm/boot/dts/exynos5250.dtsi +++ b/arch/arm/boot/dts/exynos5250.dtsi @@ -1109,7 +1109,7 @@ &cpu_thermal { polling-delay-passive = <0>; polling-delay = <0>; - thermal-sensors = <&tmu 0>; + thermal-sensors = <&tmu>; cooling-maps { map0 { From 7dd9de2e2f7b040c31dbf3695b102ad0398dfeb6 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Feb 2023 11:58:39 +0100 Subject: [PATCH 1894/4345] ARM: dts: exynos: correct TMU phandle in Odroid XU commit 9372eca505e7a19934d750b4b4c89a3652738e66 upstream. TMU node uses 0 as thermal-sensor-cells, thus thermal zone referencing it must not have an argument to phandle. Since thermal-sensors property is already defined in included exynosi5410.dtsi, drop it from exynos5410-odroidxu.dts to fix the error and remoev redundancy. Fixes: 88644b4c750b ("ARM: dts: exynos: Configure PWM, usb3503, PMIC and thermal on Odroid XU board") Cc: Link: https://lore.kernel.org/r/20230209105841.779596-4-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos5410-odroidxu.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos5410-odroidxu.dts b/arch/arm/boot/dts/exynos5410-odroidxu.dts index bd1d8499a108..147c077e8855 100644 --- a/arch/arm/boot/dts/exynos5410-odroidxu.dts +++ b/arch/arm/boot/dts/exynos5410-odroidxu.dts @@ -116,7 +116,6 @@ }; &cpu0_thermal { - thermal-sensors = <&tmu_cpu0 0>; polling-delay-passive = <0>; polling-delay = <0>; From 0f2fd21b5b54530f14f75ef11cc62dc7f52dab1b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Feb 2023 11:58:40 +0100 Subject: [PATCH 1895/4345] ARM: dts: exynos: correct TMU phandle in Odroid HC1 commit 2e3d0e20d8456f876607a8af61fdb83dfbf98cb6 upstream. TMU node uses 0 as thermal-sensor-cells, thus thermal zone referencing it must not have an argument to phandle. This was not critical before, but since rework of thermal Devicetree initialization in the commit 3fd6d6e2b4e8 ("thermal/of: Rework the thermal device tree initialization"), this leads to errors registering thermal zones other than first one: thermal_sys: cpu0-thermal: Failed to read thermal-sensors cells: -2 thermal_sys: Failed to find thermal zone for tmu id=0 exynos-tmu 10064000.tmu: Failed to register sensor: -2 exynos-tmu: probe of 10064000.tmu failed with error -2 Fixes: 1ac49427b566 ("ARM: dts: exynos: Add support for Hardkernel's Odroid HC1 board") Cc: Link: https://lore.kernel.org/r/20230209105841.779596-5-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos5422-odroidhc1.dts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/boot/dts/exynos5422-odroidhc1.dts b/arch/arm/boot/dts/exynos5422-odroidhc1.dts index 88f5c150a30a..a1871d4a0f2a 100644 --- a/arch/arm/boot/dts/exynos5422-odroidhc1.dts +++ b/arch/arm/boot/dts/exynos5422-odroidhc1.dts @@ -29,7 +29,7 @@ thermal-zones { cpu0_thermal: cpu0-thermal { - thermal-sensors = <&tmu_cpu0 0>; + thermal-sensors = <&tmu_cpu0>; trips { cpu0_alert0: cpu-alert-0 { temperature = <70000>; /* millicelsius */ @@ -84,7 +84,7 @@ }; }; cpu1_thermal: cpu1-thermal { - thermal-sensors = <&tmu_cpu1 0>; + thermal-sensors = <&tmu_cpu1>; trips { cpu1_alert0: cpu-alert-0 { temperature = <70000>; @@ -128,7 +128,7 @@ }; }; cpu2_thermal: cpu2-thermal { - thermal-sensors = <&tmu_cpu2 0>; + thermal-sensors = <&tmu_cpu2>; trips { cpu2_alert0: cpu-alert-0 { temperature = <70000>; @@ -172,7 +172,7 @@ }; }; cpu3_thermal: cpu3-thermal { - thermal-sensors = <&tmu_cpu3 0>; + thermal-sensors = <&tmu_cpu3>; trips { cpu3_alert0: cpu-alert-0 { temperature = <70000>; @@ -216,7 +216,7 @@ }; }; gpu_thermal: gpu-thermal { - thermal-sensors = <&tmu_gpu 0>; + thermal-sensors = <&tmu_gpu>; trips { gpu_alert0: gpu-alert-0 { temperature = <70000>; From ae16346078b1189aee934afd872d9f3d0a682c33 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 24 Feb 2023 18:48:54 +0100 Subject: [PATCH 1896/4345] rbd: avoid use-after-free in do_rbd_add() when rbd_dev_create() fails commit f7c4d9b133c7a04ca619355574e96b6abf209fba upstream. If getting an ID or setting up a work queue in rbd_dev_create() fails, use-after-free on rbd_dev->rbd_client, rbd_dev->spec and rbd_dev->opts is triggered in do_rbd_add(). The root cause is that the ownership of these structures is transfered to rbd_dev prematurely and they all end up getting freed when rbd_dev_create() calls rbd_dev_free() prior to returning to do_rbd_add(). Found by Linux Verification Center (linuxtesting.org) with SVACE, an incomplete patch submitted by Natalia Petrova . Cc: stable@vger.kernel.org Fixes: 1643dfa4c2c8 ("rbd: introduce a per-device ordered workqueue") Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- drivers/block/rbd.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 340b1df365f7..932d4bb8e403 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -5369,8 +5369,7 @@ static void rbd_dev_release(struct device *dev) module_put(THIS_MODULE); } -static struct rbd_device *__rbd_dev_create(struct rbd_client *rbdc, - struct rbd_spec *spec) +static struct rbd_device *__rbd_dev_create(struct rbd_spec *spec) { struct rbd_device *rbd_dev; @@ -5415,9 +5414,6 @@ static struct rbd_device *__rbd_dev_create(struct rbd_client *rbdc, rbd_dev->dev.parent = &rbd_root_dev; device_initialize(&rbd_dev->dev); - rbd_dev->rbd_client = rbdc; - rbd_dev->spec = spec; - return rbd_dev; } @@ -5430,12 +5426,10 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc, { struct rbd_device *rbd_dev; - rbd_dev = __rbd_dev_create(rbdc, spec); + rbd_dev = __rbd_dev_create(spec); if (!rbd_dev) return NULL; - rbd_dev->opts = opts; - /* get an id and fill in device name */ rbd_dev->dev_id = ida_simple_get(&rbd_dev_id_ida, 0, minor_to_rbd_dev_id(1 << MINORBITS), @@ -5452,6 +5446,10 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc, /* we have a ref from do_rbd_add() */ __module_get(THIS_MODULE); + rbd_dev->rbd_client = rbdc; + rbd_dev->spec = spec; + rbd_dev->opts = opts; + dout("%s rbd_dev %p dev_id %d\n", __func__, rbd_dev, rbd_dev->dev_id); return rbd_dev; @@ -6812,7 +6810,7 @@ static int rbd_dev_probe_parent(struct rbd_device *rbd_dev, int depth) goto out_err; } - parent = __rbd_dev_create(rbd_dev->rbd_client, rbd_dev->parent_spec); + parent = __rbd_dev_create(rbd_dev->parent_spec); if (!parent) { ret = -ENOMEM; goto out_err; @@ -6822,8 +6820,8 @@ static int rbd_dev_probe_parent(struct rbd_device *rbd_dev, int depth) * Images related by parent/child relationships always share * rbd_client and spec/parent_spec, so bump their refcounts. */ - __rbd_get_client(rbd_dev->rbd_client); - rbd_spec_get(rbd_dev->parent_spec); + parent->rbd_client = __rbd_get_client(rbd_dev->rbd_client); + parent->spec = rbd_spec_get(rbd_dev->parent_spec); __set_bit(RBD_DEV_FLAG_READONLY, &parent->flags); From 241e893df474c18340bea83eef3fd35fc4bb1d0e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 6 Jan 2023 19:25:59 -0500 Subject: [PATCH 1897/4345] alpha: fix FEN fault handling commit 977a3009547dad4a5bc95d91be4a58c9f7eedac0 upstream. Type 3 instruction fault (FPU insn with FPU disabled) is handled by quietly enabling FPU and returning. Which is fine, except that we need to do that both for fault in userland and in the kernel; the latter *can* legitimately happen - all it takes is this: .global _start _start: call_pal 0xae lda $0, 0 ldq $0, 0($0) - call_pal CLRFEN to clear "FPU enabled" flag and arrange for a signal delivery (SIGSEGV in this case). Fixed by moving the handling of type 3 into the common part of do_entIF(), before we check for kernel vs. user mode. Incidentally, the check for kernel mode is unidiomatic; the normal way to do that is !user_mode(regs). The difference is that the open-coded variant treats any of bits 63..3 of regs->ps being set as "it's user mode" while the normal approach is to check just the bit 3. PS is a 4-bit register and regs->ps always will have bits 63..4 clear, so the open-coded variant here is actually equivalent to !user_mode(regs). Harder to follow, though... Cc: stable@vger.kernel.org Reviewed-by: Richard Henderson Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- arch/alpha/kernel/traps.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 8b0f81a58b94..751d3197ca76 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -235,7 +235,21 @@ do_entIF(unsigned long type, struct pt_regs *regs) { int signo, code; - if ((regs->ps & ~IPL_MAX) == 0) { + if (type == 3) { /* FEN fault */ + /* Irritating users can call PAL_clrfen to disable the + FPU for the process. The kernel will then trap in + do_switch_stack and undo_switch_stack when we try + to save and restore the FP registers. + + Given that GCC by default generates code that uses the + FP registers, PAL_clrfen is not useful except for DoS + attacks. So turn the bleeding FPU back on and be done + with it. */ + current_thread_info()->pcb.flags |= 1; + __reload_thread(¤t_thread_info()->pcb); + return; + } + if (!user_mode(regs)) { if (type == 1) { const unsigned int *data = (const unsigned int *) regs->pc; @@ -368,20 +382,6 @@ do_entIF(unsigned long type, struct pt_regs *regs) } break; - case 3: /* FEN fault */ - /* Irritating users can call PAL_clrfen to disable the - FPU for the process. The kernel will then trap in - do_switch_stack and undo_switch_stack when we try - to save and restore the FP registers. - - Given that GCC by default generates code that uses the - FP registers, PAL_clrfen is not useful except for DoS - attacks. So turn the bleeding FPU back on and be done - with it. */ - current_thread_info()->pcb.flags |= 1; - __reload_thread(¤t_thread_info()->pcb); - return; - case 5: /* illoc */ default: /* unexpected instruction-fault type */ ; From cd4d3eab231006f6c174a2630f3158ee25c3fceb Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 16 Feb 2023 00:36:02 -0800 Subject: [PATCH 1898/4345] dax/kmem: Fix leak of memory-hotplug resources commit e686c32590f40bffc45f105c04c836ffad3e531a upstream. While experimenting with CXL region removal the following corruption of /proc/iomem appeared. Before: f010000000-f04fffffff : CXL Window 0 f010000000-f02fffffff : region4 f010000000-f02fffffff : dax4.0 f010000000-f02fffffff : System RAM (kmem) After (modprobe -r cxl_test): f010000000-f02fffffff : **redacted binary garbage** f010000000-f02fffffff : System RAM (kmem) ...and testing further the same is visible with persistent memory assigned to kmem: Before: 480000000-243fffffff : Persistent Memory 480000000-57e1fffff : namespace3.0 580000000-243fffffff : dax3.0 580000000-243fffffff : System RAM (kmem) After (ndctl disable-region all): 480000000-243fffffff : Persistent Memory 580000000-243fffffff : ***redacted binary garbage*** 580000000-243fffffff : System RAM (kmem) The corrupted data is from a use-after-free of the "dax4.0" and "dax3.0" resources, and it also shows that the "System RAM (kmem)" resource is not being removed. The bug does not appear after "modprobe -r kmem", it requires the parent of "dax4.0" and "dax3.0" to be removed which re-parents the leaked "System RAM (kmem)" instances. Those in turn reference the freed resource as a parent. First up for the fix is release_mem_region_adjustable() needs to reliably delete the resource inserted by add_memory_driver_managed(). That is thwarted by a check for IORESOURCE_SYSRAM that predates the dax/kmem driver, from commit: 65c78784135f ("kernel, resource: check for IORESOURCE_SYSRAM in release_mem_region_adjustable") That appears to be working around the behavior of HMM's "MEMORY_DEVICE_PUBLIC" facility that has since been deleted. With that check removed the "System RAM (kmem)" resource gets removed, but corruption still occurs occasionally because the "dax" resource is not reliably removed. The dax range information is freed before the device is unregistered, so the driver can not reliably recall (another use after free) what it is meant to release. Lastly if that use after free got lucky, the driver was covering up the leak of "System RAM (kmem)" due to its use of release_resource() which detaches, but does not free, child resources. The switch to remove_resource() forces remove_memory() to be responsible for the deletion of the resource added by add_memory_driver_managed(). Fixes: c2f3011ee697 ("device-dax: add an allocation interface for device-dax instances") Cc: Cc: Oscar Salvador Cc: David Hildenbrand Cc: Pavel Tatashin Reviewed-by: Vishal Verma Reviewed-by: Pasha Tatashin Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/167653656244.3147810.5705900882794040229.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams Signed-off-by: Greg Kroah-Hartman --- drivers/dax/bus.c | 2 +- drivers/dax/kmem.c | 4 ++-- kernel/resource.c | 14 -------------- 3 files changed, 3 insertions(+), 17 deletions(-) diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index c1d379bd7af3..a02777c93c07 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -398,8 +398,8 @@ static void unregister_dev_dax(void *dev) dev_dbg(dev, "%s\n", __func__); kill_dev_dax(dev_dax); - free_dev_dax_ranges(dev_dax); device_del(dev); + free_dev_dax_ranges(dev_dax); put_device(dev); } diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c index b4368c5b6a0c..27d669f8b5f3 100644 --- a/drivers/dax/kmem.c +++ b/drivers/dax/kmem.c @@ -114,7 +114,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) if (rc) { dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n", i, range.start, range.end); - release_resource(res); + remove_resource(res); kfree(res); data->res[i] = NULL; if (mapped) @@ -159,7 +159,7 @@ static int dev_dax_kmem_remove(struct dev_dax *dev_dax) rc = remove_memory(dev_dax->target_node, range.start, range_len(&range)); if (rc == 0) { - release_resource(data->res[i]); + remove_resource(data->res[i]); kfree(data->res[i]); data->res[i] = NULL; success++; diff --git a/kernel/resource.c b/kernel/resource.c index 817545ff80b9..100253d4909c 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1293,20 +1293,6 @@ retry: continue; } - /* - * All memory regions added from memory-hotplug path have the - * flag IORESOURCE_SYSTEM_RAM. If the resource does not have - * this flag, we know that we are dealing with a resource coming - * from HMM/devm. HMM/devm use another mechanism to add/release - * a resource. This goes via devm_request_mem_region and - * devm_release_mem_region. - * HMM/devm take care to release their resources when they want, - * so if we are dealing with them, let us just back off here. - */ - if (!(res->flags & IORESOURCE_SYSRAM)) { - break; - } - if (!(res->flags & IORESOURCE_MEM)) break; From 6c96c0b2e32661b2da11d4eab9c895336b2e9680 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Sat, 18 Feb 2023 23:43:59 +0100 Subject: [PATCH 1899/4345] mips: fix syscall_get_nr commit 85cc91e2ba4262a602ec65e2b76c4391a9e60d3d upstream. The implementation of syscall_get_nr on mips used to ignore the task argument and return the syscall number of the calling thread instead of the target thread. The bug was exposed to user space by commit 201766a20e30f ("ptrace: add PTRACE_GET_SYSCALL_INFO request") and detected by strace test suite. Link: https://github.com/strace/strace/issues/235 Fixes: c2d9f1775731 ("MIPS: Fix syscall_get_nr for the syscall exit tracing.") Cc: # v3.19+ Co-developed-by: Dmitry V. Levin Signed-off-by: Dmitry V. Levin Signed-off-by: Elvira Khabirova Signed-off-by: Thomas Bogendoerfer Signed-off-by: Greg Kroah-Hartman --- arch/mips/include/asm/syscall.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 25fa651c937d..ebdf4d910af2 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -38,7 +38,7 @@ static inline bool mips_syscall_is_indirect(struct task_struct *task, static inline long syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - return current_thread_info()->syscall; + return task_thread_info(task)->syscall; } static inline void mips_syscall_update_nr(struct task_struct *task, From 3b78c2482bbe1889bc8c441e113c666ff6b6b329 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 21 Dec 2022 09:30:11 +0100 Subject: [PATCH 1900/4345] media: ipu3-cio2: Fix PM runtime usage_count in driver unbind commit 909d3096ac99fa2289f9b8945a3eab2269947a0a upstream. Get the PM runtime usage_count and forbid PM runtime at driver unbind. The opposite is being done in probe() already. Fixes: commit c2a6a07afe4a ("media: intel-ipu3: cio2: add new MIPI-CSI2 driver") Cc: stable@vger.kernel.org # for >= 4.16 Signed-off-by: Sakari Ailus Reviewed-by: Bingbu Cao Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/pci/intel/ipu3/ipu3-cio2.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/media/pci/intel/ipu3/ipu3-cio2.c b/drivers/media/pci/intel/ipu3/ipu3-cio2.c index 2fe4a0bd0284..d6838c8ebd7e 100644 --- a/drivers/media/pci/intel/ipu3/ipu3-cio2.c +++ b/drivers/media/pci/intel/ipu3/ipu3-cio2.c @@ -1831,6 +1831,9 @@ static void cio2_pci_remove(struct pci_dev *pci_dev) v4l2_device_unregister(&cio2->v4l2_dev); media_device_cleanup(&cio2->media_dev); mutex_destroy(&cio2->lock); + + pm_runtime_forbid(&pci_dev->dev); + pm_runtime_get_noresume(&pci_dev->dev); } static int __maybe_unused cio2_runtime_suspend(struct device *dev) From 6814e8e4202f3507a5b51c80a3c38f6e7a3973fb Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Wed, 4 Jan 2023 16:31:10 +0800 Subject: [PATCH 1901/4345] remoteproc/mtk_scp: Move clk ops outside send_lock commit e46ceea3148163166ef9b7bcac578e72dd30c064 upstream. Clocks are properly reference counted and do not need to be inside the lock range. Right now this triggers a false-positive lockdep warning on MT8192 based Chromebooks, through a combination of mtk-scp that has a cros-ec-rpmsg sub-device, the (actual) cros-ec I2C adapter registration, I2C client (not on cros-ec) probe doing i2c transfers and enabling clocks. This is a false positive because the cros-ec-rpmsg under mtk-scp does not have an I2C adapter, and also each I2C adapter and cros-ec instance have their own mutex. Move the clk operations outside of the send_lock range. Fixes: 63c13d61eafe ("remoteproc/mediatek: add SCP support for mt8183") Signed-off-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230104083110.736377-1-wenst@chromium.org [Fixed "Fixes:" tag line] Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/remoteproc/mtk_scp_ipi.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/remoteproc/mtk_scp_ipi.c b/drivers/remoteproc/mtk_scp_ipi.c index 6dc955ecab80..968128b78e59 100644 --- a/drivers/remoteproc/mtk_scp_ipi.c +++ b/drivers/remoteproc/mtk_scp_ipi.c @@ -164,21 +164,21 @@ int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len, WARN_ON(len > sizeof(send_obj->share_buf)) || WARN_ON(!buf)) return -EINVAL; - mutex_lock(&scp->send_lock); - ret = clk_prepare_enable(scp->clk); if (ret) { dev_err(scp->dev, "failed to enable clock\n"); - goto unlock_mutex; + return ret; } + mutex_lock(&scp->send_lock); + /* Wait until SCP receives the last command */ timeout = jiffies + msecs_to_jiffies(2000); do { if (time_after(jiffies, timeout)) { dev_err(scp->dev, "%s: IPI timeout!\n", __func__); ret = -ETIMEDOUT; - goto clock_disable; + goto unlock_mutex; } } while (readl(scp->reg_base + scp->data->host_to_scp_reg)); @@ -205,10 +205,9 @@ int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len, ret = 0; } -clock_disable: - clk_disable_unprepare(scp->clk); unlock_mutex: mutex_unlock(&scp->send_lock); + clk_disable_unprepare(scp->clk); return ret; } From f1f6c87d82248b59904889538fff1b8063800af4 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 29 Dec 2022 14:49:39 +0106 Subject: [PATCH 1902/4345] docs: gdbmacros: print newest record commit f2e4cca2f670c8e52fbb551a295f2afc9aa2bd72 upstream. @head_id points to the newest record, but the printing loop exits when it increments to this value (before printing). Exit the printing loop after the newest record has been printed. The python-based function in scripts/gdb/linux/dmesg.py already does this correctly. Fixes: e60768311af8 ("scripts/gdb: update for lockless printk ringbuffer") Cc: stable@vger.kernel.org Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20221229134339.197627-1-john.ogness@linutronix.de Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/kdump/gdbmacros.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/kdump/gdbmacros.txt b/Documentation/admin-guide/kdump/gdbmacros.txt index 82aecdcae8a6..030de95e3e6b 100644 --- a/Documentation/admin-guide/kdump/gdbmacros.txt +++ b/Documentation/admin-guide/kdump/gdbmacros.txt @@ -312,10 +312,10 @@ define dmesg set var $prev_flags = $info->flags end - set var $id = ($id + 1) & $id_mask if ($id == $end_id) loop_break end + set var $id = ($id + 1) & $id_mask end end document dmesg From e6d20325f422b3252aff2d42d8d09b2ebb434892 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 7 Dec 2022 14:00:39 +0100 Subject: [PATCH 1903/4345] mm: memcontrol: deprecate charge moving commit da34a8484d162585e22ed8c1e4114aa2f60e3567 upstream. Charge moving mode in cgroup1 allows memory to follow tasks as they migrate between cgroups. This is, and always has been, a questionable thing to do - for several reasons. First, it's expensive. Pages need to be identified, locked and isolated from various MM operations, and reassigned, one by one. Second, it's unreliable. Once pages are charged to a cgroup, there isn't always a clear owner task anymore. Cache isn't moved at all, for example. Mapped memory is moved - but if trylocking or isolating a page fails, it's arbitrarily left behind. Frequent moving between domains may leave a task's memory scattered all over the place. Third, it isn't really needed. Launcher tasks can kick off workload tasks directly in their target cgroup. Using dedicated per-workload groups allows fine-grained policy adjustments - no need to move tasks and their physical pages between control domains. The feature was never forward-ported to cgroup2, and it hasn't been missed. Despite it being a niche usecase, the maintenance overhead of supporting it is enormous. Because pages are moved while they are live and subject to various MM operations, the synchronization rules are complicated. There are lock_page_memcg() in MM and FS code, which non-cgroup people don't understand. In some cases we've been able to shift code and cgroup API calls around such that we can rely on native locking as much as possible. But that's fragile, and sometimes we need to hold MM locks for longer than we otherwise would (pte lock e.g.). Mark the feature deprecated. Hopefully we can remove it soon. And backport into -stable kernels so that people who develop against earlier kernels are warned about this deprecation as early as possible. [akpm@linux-foundation.org: fix memory.rst underlining] Link: https://lkml.kernel.org/r/Y5COd+qXwk/S+n8N@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Shakeel Butt Acked-by: Hugh Dickins Acked-by: Michal Hocko Cc: Muchun Song Cc: Roman Gushchin Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/cgroup-v1/memory.rst | 13 +++++++++++-- mm/memcontrol.c | 4 ++++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index 12757e63b26c..7882037aca67 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -82,6 +82,8 @@ Brief summary of control files. memory.swappiness set/show swappiness parameter of vmscan (See sysctl's vm.swappiness) memory.move_charge_at_immigrate set/show controls of moving charges + This knob is deprecated and shouldn't be + used. memory.oom_control set/show oom controls. memory.numa_stat show the number of memory usage per numa node @@ -740,8 +742,15 @@ NOTE2: It is recommended to set the soft limit always below the hard limit, otherwise the hard limit will take precedence. -8. Move charges at task migration -================================= +8. Move charges at task migration (DEPRECATED!) +=============================================== + +THIS IS DEPRECATED! + +It's expensive and unreliable! It's better practice to launch workload +tasks directly from inside their target cgroup. Use dedicated workload +cgroups to allow fine-grained policy adjustments without having to +move physical pages between control domains. Users can move charges associated with a task along with task migration, that is, uncharge task's pages from the old cgroup and charge them to the new cgroup. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c62d997c8ca1..751e3670d7b0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3930,6 +3930,10 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, { struct mem_cgroup *memcg = mem_cgroup_from_css(css); + pr_warn_once("Cgroup memory moving (move_charge_at_immigrate) is deprecated. " + "Please report your usecase to linux-mm@kvack.org if you " + "depend on this functionality.\n"); + if (val & ~MOVE_MASK) return -EINVAL; From ed77831e69ee85a09ff3e8c179bc01c06cb76e3d Mon Sep 17 00:00:00 2001 From: Yin Fengwei Date: Fri, 23 Dec 2022 21:52:07 +0800 Subject: [PATCH 1904/4345] mm/thp: check and bail out if page in deferred queue already commit 81e506bec9be1eceaf5a2c654e28ba5176ef48d8 upstream. Kernel build regression with LLVM was reported here: https://lore.kernel.org/all/Y1GCYXGtEVZbcv%2F5@dev-arch.thelio-3990X/ with commit f35b5d7d676e ("mm: align larger anonymous mappings on THP boundaries"). And the commit f35b5d7d676e was reverted. It turned out the regression is related with madvise(MADV_DONTNEED) was used by ld.lld. But with none PMD_SIZE aligned parameter len. trace-bpfcc captured: 531607 531732 ld.lld do_madvise.part.0 start: 0x7feca9000000, len: 0x7fb000, behavior: 0x4 531607 531793 ld.lld do_madvise.part.0 start: 0x7fec86a00000, len: 0x7fb000, behavior: 0x4 If the underneath physical page is THP, the madvise(MADV_DONTNEED) can trigger split_queue_lock contention raised significantly. perf showed following data: 14.85% 0.00% ld.lld [kernel.kallsyms] [k] entry_SYSCALL_64_after_hwframe 11.52% entry_SYSCALL_64_after_hwframe do_syscall_64 __x64_sys_madvise do_madvise.part.0 zap_page_range unmap_single_vma unmap_page_range page_remove_rmap deferred_split_huge_page __lock_text_start native_queued_spin_lock_slowpath If THP can't be removed from rmap as whole THP, partial THP will be removed from rmap by removing sub-pages from rmap. Even the THP head page is added to deferred queue already, the split_queue_lock will be acquired and check whether the THP head page is in the queue already. Thus, the contention of split_queue_lock is raised. Before acquire split_queue_lock, check and bail out early if the THP head page is in the queue already. The checking without holding split_queue_lock could race with deferred_split_scan, but it doesn't impact the correctness here. Test result of building kernel with ld.lld: commit 7b5a0b664ebe (parent commit of f35b5d7d676e): time -f "\t%E real,\t%U user,\t%S sys" make LD=ld.lld -skj96 allmodconfig all 6:07.99 real, 26367.77 user, 5063.35 sys commit f35b5d7d676e: time -f "\t%E real,\t%U user,\t%S sys" make LD=ld.lld -skj96 allmodconfig all 7:22.15 real, 26235.03 user, 12504.55 sys commit f35b5d7d676e with the fixing patch: time -f "\t%E real,\t%U user,\t%S sys" make LD=ld.lld -skj96 allmodconfig all 6:08.49 real, 26520.15 user, 5047.91 sys Link: https://lkml.kernel.org/r/20221223135207.2275317-1-fengwei.yin@intel.com Signed-off-by: Yin Fengwei Tested-by: Nathan Chancellor Acked-by: David Rientjes Reviewed-by: "Huang, Ying" Cc: Feng Tang Cc: Matthew Wilcox Cc: Rik van Riel Cc: Xing Zhengjun Cc: Yang Shi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/huge_memory.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index cb7b0aead709..9b15760e0541 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2803,6 +2803,9 @@ void deferred_split_huge_page(struct page *page) if (PageSwapCache(page)) return; + if (!list_empty(page_deferred_list(page))) + return; + spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (list_empty(page_deferred_list(page))) { count_vm_event(THP_DEFERRED_SPLIT_PAGE); From 0dfb3f4588bc03d344e4ca4a70a06f24cf0cf6ec Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 18 Jan 2023 16:32:13 -0500 Subject: [PATCH 1905/4345] ktest.pl: Give back console on Ctrt^C on monitor commit 83d29d439cd3ef23041570d55841f814af2ecac0 upstream. When monitoring the console output, the stdout is being redirected to do so. If Ctrl^C is hit during this mode, the stdout is not back to the console, the user does not see anything they type (no echo). Add "end_monitor" to the SIGINT interrupt handler to give back the console on Ctrl^C. Cc: stable@vger.kernel.org Fixes: 9f2cdcbbb90e7 ("ktest: Give console process a dedicated tty") Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- tools/testing/ktest/ktest.pl | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 8b1e3ae8fe50..a9fb5a48751e 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -4283,6 +4283,9 @@ sub send_email { } sub cancel_test { + if ($monitor_cnt) { + end_monitor; + } if ($email_when_canceled) { my $name = get_test_name; send_email("KTEST: Your [$name] test was cancelled", From 39255e4788fb5a27dd6957540a62b037aa7841ea Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 18 Jan 2023 11:31:25 -0500 Subject: [PATCH 1906/4345] ktest.pl: Fix missing "end_monitor" when machine check fails commit e8bf9b98d40dbdf4e39362e3b85a70c61da68cb7 upstream. In the "reboot" command, it does a check of the machine to see if it is still alive with a simple "ssh echo" command. If it fails, it will assume that a normal "ssh reboot" is not possible and force a power cycle. In this case, the "start_monitor" is executed, but the "end_monitor" is not, and this causes the screen will not be given back to the console. That is, after the test, a "reset" command needs to be performed, as "echo" is turned off. Cc: stable@vger.kernel.org Fixes: 6474ace999edd ("ktest.pl: Powercycle the box on reboot if no connection can be made") Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- tools/testing/ktest/ktest.pl | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index a9fb5a48751e..2b2061a70b78 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1433,7 +1433,8 @@ sub reboot { # Still need to wait for the reboot to finish wait_for_monitor($time, $reboot_success_line); - + } + if ($powercycle || $time) { end_monitor; } } From 1693f3bc1f2566718993747166b9afe98c572fec Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 18 Jan 2023 16:37:25 -0500 Subject: [PATCH 1907/4345] ktest.pl: Add RUN_TIMEOUT option with default unlimited commit 4e7d2a8f0b52abf23b1dc13b3d88bc0923383cd5 upstream. There is a disconnect between the run_command function and the wait_for_input. The wait_for_input has a default timeout of 2 minutes. But if that happens, the run_command loop will exit out to the waitpid() of the executing command. This fails in that it no longer monitors the command, and also, the ssh to the test box can hang when its finished, as it's waiting for the pipe it's writing to to flush, but the loop that reads that pipe has already exited, leaving the command stuck, and the test hangs. Instead, make the default "wait_for_input" of the run_command infinite, and allow the user to override it if they want with a default timeout option "RUN_TIMEOUT". But this fixes the hang that happens when the pipe is full and the ssh session never exits. Cc: stable@vger.kernel.org Fixes: 6e98d1b4415fe ("ktest: Add timeout to ssh command") Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- tools/testing/ktest/ktest.pl | 20 ++++++++++++++++---- tools/testing/ktest/sample.conf | 5 +++++ 2 files changed, 21 insertions(+), 4 deletions(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 2b2061a70b78..ea26f2b0c1bc 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -178,6 +178,7 @@ my $store_failures; my $store_successes; my $test_name; my $timeout; +my $run_timeout; my $connect_timeout; my $config_bisect_exec; my $booted_timeout; @@ -340,6 +341,7 @@ my %option_map = ( "STORE_SUCCESSES" => \$store_successes, "TEST_NAME" => \$test_name, "TIMEOUT" => \$timeout, + "RUN_TIMEOUT" => \$run_timeout, "CONNECT_TIMEOUT" => \$connect_timeout, "CONFIG_BISECT_EXEC" => \$config_bisect_exec, "BOOTED_TIMEOUT" => \$booted_timeout, @@ -1800,6 +1802,14 @@ sub run_command { $command =~ s/\$SSH_USER/$ssh_user/g; $command =~ s/\$MACHINE/$machine/g; + if (!defined($timeout)) { + $timeout = $run_timeout; + } + + if (!defined($timeout)) { + $timeout = -1; # tell wait_for_input to wait indefinitely + } + doprint("$command ... "); $start_time = time; @@ -1826,13 +1836,10 @@ sub run_command { while (1) { my $fp = \*CMD; - if (defined($timeout)) { - doprint "timeout = $timeout\n"; - } my $line = wait_for_input($fp, $timeout); if (!defined($line)) { my $now = time; - if (defined($timeout) && (($now - $start_time) >= $timeout)) { + if ($timeout >= 0 && (($now - $start_time) >= $timeout)) { doprint "Hit timeout of $timeout, killing process\n"; $hit_timeout = 1; kill 9, $pid; @@ -2005,6 +2012,11 @@ sub wait_for_input $time = $timeout; } + if ($time < 0) { + # Negative number means wait indefinitely + undef $time; + } + $rin = ''; vec($rin, fileno($fp), 1) = 1; vec($rin, fileno(\*STDIN), 1) = 1; diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf index 5e7d1d729752..65957a9803b5 100644 --- a/tools/testing/ktest/sample.conf +++ b/tools/testing/ktest/sample.conf @@ -809,6 +809,11 @@ # is issued instead of a reboot. # CONNECT_TIMEOUT = 25 +# The timeout in seconds for how long to wait for any running command +# to timeout. If not defined, it will let it go indefinitely. +# (default undefined) +#RUN_TIMEOUT = 600 + # In between tests, a reboot of the box may occur, and this # is the time to wait for the console after it stops producing # output. Some machines may not produce a large lag on reboot From 6e02a43acd0691791df79ce538f2dd497a6c9b76 Mon Sep 17 00:00:00 2001 From: Mukesh Ojha Date: Tue, 14 Feb 2023 17:36:43 +0530 Subject: [PATCH 1908/4345] ring-buffer: Handle race between rb_move_tail and rb_check_pages commit 8843e06f67b14f71c044bf6267b2387784c7e198 upstream. It seems a data race between ring_buffer writing and integrity check. That is, RB_FLAG of head_page is been updating, while at same time RB_FLAG was cleared when doing integrity check rb_check_pages(): rb_check_pages() rb_handle_head_page(): -------- -------- rb_head_page_deactivate() rb_head_page_set_normal() rb_head_page_activate() We do intergrity test of the list to check if the list is corrupted and it is still worth doing it. So, let's refactor rb_check_pages() such that we no longer clear and set flag during the list sanity checking. [1] and [2] are the test to reproduce and the crash report respectively. 1: ``` read_trace.sh while true; do # the "trace" file is closed after read head -1 /sys/kernel/tracing/trace > /dev/null done ``` ``` repro.sh sysctl -w kernel.panic_on_warn=1 # function tracer will writing enough data into ring_buffer echo function > /sys/kernel/tracing/current_tracer ./read_trace.sh & ./read_trace.sh & ./read_trace.sh & ./read_trace.sh & ./read_trace.sh & ./read_trace.sh & ./read_trace.sh & ./read_trace.sh & ``` 2: ------------[ cut here ]------------ WARNING: CPU: 9 PID: 62 at kernel/trace/ring_buffer.c:2653 rb_move_tail+0x450/0x470 Modules linked in: CPU: 9 PID: 62 Comm: ksoftirqd/9 Tainted: G W 6.2.0-rc6+ Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 RIP: 0010:rb_move_tail+0x450/0x470 Code: ff ff 4c 89 c8 f0 4d 0f b1 02 48 89 c2 48 83 e2 fc 49 39 d0 75 24 83 e0 03 83 f8 02 0f 84 e1 fb ff ff 48 8b 57 10 f0 ff 42 08 <0f> 0b 83 f8 02 0f 84 ce fb ff ff e9 db RSP: 0018:ffffb5564089bd00 EFLAGS: 00000203 RAX: 0000000000000000 RBX: ffff9db385a2bf81 RCX: ffffb5564089bd18 RDX: ffff9db281110100 RSI: 0000000000000fe4 RDI: ffff9db380145400 RBP: ffff9db385a2bf80 R08: ffff9db385a2bfc0 R09: ffff9db385a2bfc2 R10: ffff9db385a6c000 R11: ffff9db385a2bf80 R12: 0000000000000000 R13: 00000000000003e8 R14: ffff9db281110100 R15: ffffffffbb006108 FS: 0000000000000000(0000) GS:ffff9db3bdcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005602323024c8 CR3: 0000000022e0c000 CR4: 00000000000006e0 Call Trace: ring_buffer_lock_reserve+0x136/0x360 ? __do_softirq+0x287/0x2df ? __pfx_rcu_softirq_qs+0x10/0x10 trace_function+0x21/0x110 ? __pfx_rcu_softirq_qs+0x10/0x10 ? __do_softirq+0x287/0x2df function_trace_call+0xf6/0x120 0xffffffffc038f097 ? rcu_softirq_qs+0x5/0x140 rcu_softirq_qs+0x5/0x140 __do_softirq+0x287/0x2df run_ksoftirqd+0x2a/0x30 smpboot_thread_fn+0x188/0x220 ? __pfx_smpboot_thread_fn+0x10/0x10 kthread+0xe7/0x110 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2c/0x50 ---[ end trace 0000000000000000 ]--- [ crash report and test reproducer credit goes to Zheng Yejian] Link: https://lore.kernel.org/linux-trace-kernel/1676376403-16462-1-git-send-email-quic_mojha@quicinc.com Cc: Cc: stable@vger.kernel.org Fixes: 1039221cc278 ("ring-buffer: Do not disable recording when there is an iterator") Reported-by: Zheng Yejian Signed-off-by: Mukesh Ojha Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ring_buffer.c | 42 +++++++++----------------------------- 1 file changed, 10 insertions(+), 32 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 49ebb8c66268..c00463613eab 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1449,19 +1449,6 @@ static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, return 0; } -/** - * rb_check_list - make sure a pointer to a list has the last bits zero - */ -static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer, - struct list_head *list) -{ - if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev)) - return 1; - if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next)) - return 1; - return 0; -} - /** * rb_check_pages - integrity check of buffer pages * @cpu_buffer: CPU buffer with pages to test @@ -1471,36 +1458,27 @@ static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer, */ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) { - struct list_head *head = cpu_buffer->pages; - struct buffer_page *bpage, *tmp; + struct list_head *head = rb_list_head(cpu_buffer->pages); + struct list_head *tmp; - /* Reset the head page if it exists */ - if (cpu_buffer->head_page) - rb_set_head_page(cpu_buffer); - - rb_head_page_deactivate(cpu_buffer); - - if (RB_WARN_ON(cpu_buffer, head->next->prev != head)) - return -1; - if (RB_WARN_ON(cpu_buffer, head->prev->next != head)) + if (RB_WARN_ON(cpu_buffer, + rb_list_head(rb_list_head(head->next)->prev) != head)) return -1; - if (rb_check_list(cpu_buffer, head)) + if (RB_WARN_ON(cpu_buffer, + rb_list_head(rb_list_head(head->prev)->next) != head)) return -1; - list_for_each_entry_safe(bpage, tmp, head, list) { + for (tmp = rb_list_head(head->next); tmp != head; tmp = rb_list_head(tmp->next)) { if (RB_WARN_ON(cpu_buffer, - bpage->list.next->prev != &bpage->list)) + rb_list_head(rb_list_head(tmp->next)->prev) != tmp)) return -1; + if (RB_WARN_ON(cpu_buffer, - bpage->list.prev->next != &bpage->list)) - return -1; - if (rb_check_list(cpu_buffer, &bpage->list)) + rb_list_head(rb_list_head(tmp->prev)->next) != tmp)) return -1; } - rb_head_page_activate(cpu_buffer); - return 0; } From 40bedbf10d562d3702b3dde88e9e501058d287f1 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Mon, 19 Dec 2022 03:07:39 -0800 Subject: [PATCH 1909/4345] scsi: qla2xxx: Fix link failure in NPIV environment commit b1ae65c082f74536ec292b15766f2846f0238373 upstream. User experienced symptoms of adapter failure in NPIV environment. NPIV hosts were allowed to trigger chip reset back to back due to NPIV link state being slow to come online. Fix link failure in NPIV environment by removing NPIV host from directly being able to perform chip reset. kernel: qla2xxx [0000:04:00.1]-6009:261: Loop down - aborting ISP. kernel: qla2xxx [0000:04:00.1]-6009:262: Loop down - aborting ISP. kernel: qla2xxx [0000:04:00.1]-6009:281: Loop down - aborting ISP. kernel: qla2xxx [0000:04:00.1]-6009:285: Loop down - aborting ISP Fixes: 0d6e61bc6a4f ("[SCSI] qla2xxx: Correct various NPIV issues.") Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_os.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 419156121cb5..bc6a7cf488ba 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -7145,7 +7145,7 @@ qla2x00_timer(struct timer_list *t) /* if the loop has been down for 4 minutes, reinit adapter */ if (atomic_dec_and_test(&vha->loop_down_timer) != 0) { - if (!(vha->device_flags & DFLG_NO_CABLE)) { + if (!(vha->device_flags & DFLG_NO_CABLE) && !vha->vp_idx) { ql_log(ql_log_warn, vha, 0x6009, "Loop down - aborting ISP.\n"); From e596253113b69b4018818260bd5da40c201bee73 Mon Sep 17 00:00:00 2001 From: Arun Easi Date: Mon, 19 Dec 2022 03:07:40 -0800 Subject: [PATCH 1910/4345] scsi: qla2xxx: Fix DMA-API call trace on NVMe LS requests commit c75e6aef5039830cce5d4cf764dd204522f89e6b upstream. The following message and call trace was seen with debug kernels: DMA-API: qla2xxx 0000:41:00.0: device driver failed to check map error [device address=0x00000002a3ff38d8] [size=1024 bytes] [mapped as single] WARNING: CPU: 0 PID: 2930 at kernel/dma/debug.c:1017 check_unmap+0xf42/0x1990 Call Trace: debug_dma_unmap_page+0xc9/0x100 qla_nvme_ls_unmap+0x141/0x210 [qla2xxx] Remove DMA mapping from the driver altogether, as it is already done by FC layer. This prevents the warning. Fixes: c85ab7d9e27a ("scsi: qla2xxx: Fix missed DMA unmap for NVMe ls requests") Cc: stable@vger.kernel.org Signed-off-by: Arun Easi Signed-off-by: Nilesh Javali Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_nvme.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index d63ccdf6e988..695dd89be330 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -165,18 +165,6 @@ out: qla2xxx_rel_qpair_sp(sp->qpair, sp); } -static void qla_nvme_ls_unmap(struct srb *sp, struct nvmefc_ls_req *fd) -{ - if (sp->flags & SRB_DMA_VALID) { - struct srb_iocb *nvme = &sp->u.iocb_cmd; - struct qla_hw_data *ha = sp->fcport->vha->hw; - - dma_unmap_single(&ha->pdev->dev, nvme->u.nvme.cmd_dma, - fd->rqstlen, DMA_TO_DEVICE); - sp->flags &= ~SRB_DMA_VALID; - } -} - static void qla_nvme_release_ls_cmd_kref(struct kref *kref) { struct srb *sp = container_of(kref, struct srb, cmd_kref); @@ -194,7 +182,6 @@ static void qla_nvme_release_ls_cmd_kref(struct kref *kref) fd = priv->fd; - qla_nvme_ls_unmap(sp, fd); fd->done(fd, priv->comp_status); out: qla2x00_rel_sp(sp); @@ -336,13 +323,10 @@ static int qla_nvme_ls_req(struct nvme_fc_local_port *lport, nvme->u.nvme.rsp_len = fd->rsplen; nvme->u.nvme.rsp_dma = fd->rspdma; nvme->u.nvme.timeout_sec = fd->timeout; - nvme->u.nvme.cmd_dma = dma_map_single(&ha->pdev->dev, fd->rqstaddr, - fd->rqstlen, DMA_TO_DEVICE); + nvme->u.nvme.cmd_dma = fd->rqstdma; dma_sync_single_for_device(&ha->pdev->dev, nvme->u.nvme.cmd_dma, fd->rqstlen, DMA_TO_DEVICE); - sp->flags |= SRB_DMA_VALID; - rval = qla2x00_start_sp(sp); if (rval != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x700e, @@ -350,7 +334,6 @@ static int qla_nvme_ls_req(struct nvme_fc_local_port *lport, wake_up(&sp->nvme_ls_waitq); sp->priv = NULL; priv->sp = NULL; - qla_nvme_ls_unmap(sp, fd); qla2x00_rel_sp(sp); return rval; } From 0d14ace68dd5b58365bca8991cd72f40975fe0df Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Mon, 19 Dec 2022 03:07:45 -0800 Subject: [PATCH 1911/4345] scsi: qla2xxx: Fix erroneous link down commit 3fbc74feb642deb688cc97f76d40b7287ddd4cb1 upstream. If after an adapter reset the appearance of link is not recovered, the devices are not rediscovered. This is result of a race condition between adapter reset (abort_isp) and the topology scan. During adapter reset, the ABORT_ISP_ACTIVE flag is set. Topology scan usually occurred after adapter reset. In this case, the topology scan came earlier than usual where it ran into problem due to ABORT_ISP_ACTIVE flag was still set. kernel: qla2xxx [0000:13:00.0]-1005:1: Cmd 0x6a aborted with timeout since ISP Abort is pending kernel: qla2xxx [0000:13:00.0]-28a0:1: MBX_GET_PORT_NAME failed, No FL Port. kernel: qla2xxx [0000:13:00.0]-286b:1: qla2x00_configure_loop: exiting normally. local port wwpn 51402ec0123d9a80 id 012300) kernel: qla2xxx [0000:13:00.0]-8017:1: ADAPTER RESET SUCCEEDED nexus=1:0:15. Allow adapter reset to complete before any scan can start. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_os.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index bc6a7cf488ba..e1132970f189 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -6899,9 +6899,12 @@ qla2x00_do_dpc(void *data) } } loop_resync_check: - if (test_and_clear_bit(LOOP_RESYNC_NEEDED, + if (!qla2x00_reset_active(base_vha) && + test_and_clear_bit(LOOP_RESYNC_NEEDED, &base_vha->dpc_flags)) { - + /* + * Allow abort_isp to complete before moving on to scanning. + */ ql_dbg(ql_dbg_dpc, base_vha, 0x400f, "Loop resync scheduled.\n"); From d68937dfc73ee7f61cf3424fa3225be93cacaa00 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Sat, 28 Nov 2020 15:27:21 -0800 Subject: [PATCH 1912/4345] scsi: ses: Don't attach if enclosure has no components commit 3fe97ff3d94934649abb0652028dd7296170c8d0 upstream. An enclosure with no components can't usefully be operated by the driver (since effectively it has nothing to manage), so report the problem and don't attach. Not attaching also fixes an oops which could occur if the driver tries to manage a zero component enclosure. [mkp: Switched to KERN_WARNING since this scenario is common] Link: https://lore.kernel.org/r/c5deac044ac409e32d9ad9968ce0dcbc996bfc7a.camel@linux.ibm.com Cc: stable@vger.kernel.org Reported-by: Ding Hui Signed-off-by: James Bottomley Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/ses.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 0a1734f34587..b61d7e490606 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -704,6 +704,12 @@ static int ses_intf_add(struct device *cdev, type_ptr[0] == ENCLOSURE_COMPONENT_ARRAY_DEVICE) components += type_ptr[1]; } + + if (components == 0) { + sdev_printk(KERN_WARNING, sdev, "enclosure has no enumerated components\n"); + goto err_free; + } + ses_dev->page1 = buf; ses_dev->page1_len = len; buf = NULL; From e4dd25da784b2e07dbfbf04509afa4c5a1375227 Mon Sep 17 00:00:00 2001 From: Tomas Henzl Date: Thu, 2 Feb 2023 17:24:48 +0100 Subject: [PATCH 1913/4345] scsi: ses: Fix slab-out-of-bounds in ses_enclosure_data_process() commit 9b4f5028e493cb353a5c8f5c45073eeea0303abd upstream. A fix for: BUG: KASAN: slab-out-of-bounds in ses_enclosure_data_process+0x949/0xe30 [ses] Read of size 1 at addr ffff88a1b043a451 by task systemd-udevd/3271 Checking after (and before in next loop) addl_desc_ptr[1] is sufficient, we expect the size to be sanitized before first access to addl_desc_ptr[1]. Make sure we don't walk beyond end of page. Link: https://lore.kernel.org/r/20230202162451.15346-2-thenzl@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Tomas Henzl Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/ses.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index b61d7e490606..4739c03b4e1d 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -603,9 +603,11 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, /* these elements are optional */ type_ptr[0] == ENCLOSURE_COMPONENT_SCSI_TARGET_PORT || type_ptr[0] == ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT || - type_ptr[0] == ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS)) + type_ptr[0] == ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS)) { addl_desc_ptr += addl_desc_ptr[1] + 2; - + if (addl_desc_ptr + 1 >= ses_dev->page10 + ses_dev->page10_len) + addl_desc_ptr = NULL; + } } } kfree(buf); From 2ecd344173a5663d523433819da0484cb268b186 Mon Sep 17 00:00:00 2001 From: Tomas Henzl Date: Thu, 2 Feb 2023 17:24:49 +0100 Subject: [PATCH 1914/4345] scsi: ses: Fix possible addl_desc_ptr out-of-bounds accesses commit db95d4df71cb55506425b6e4a5f8d68e3a765b63 upstream. Sanitize possible addl_desc_ptr out-of-bounds accesses in ses_enclosure_data_process(). Link: https://lore.kernel.org/r/20230202162451.15346-3-thenzl@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Tomas Henzl Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/ses.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 4739c03b4e1d..4b66f9aec0f4 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -433,8 +433,8 @@ int ses_match_host(struct enclosure_device *edev, void *data) } #endif /* 0 */ -static void ses_process_descriptor(struct enclosure_component *ecomp, - unsigned char *desc) +static int ses_process_descriptor(struct enclosure_component *ecomp, + unsigned char *desc, int max_desc_len) { int eip = desc[0] & 0x10; int invalid = desc[0] & 0x80; @@ -445,22 +445,32 @@ static void ses_process_descriptor(struct enclosure_component *ecomp, unsigned char *d; if (invalid) - return; + return 0; switch (proto) { case SCSI_PROTOCOL_FCP: if (eip) { + if (max_desc_len <= 7) + return 1; d = desc + 4; slot = d[3]; } break; case SCSI_PROTOCOL_SAS: + if (eip) { + if (max_desc_len <= 27) + return 1; d = desc + 4; slot = d[3]; d = desc + 8; - } else + } else { + if (max_desc_len <= 23) + return 1; d = desc + 4; + } + + /* only take the phy0 addr */ addr = (u64)d[12] << 56 | (u64)d[13] << 48 | @@ -477,6 +487,8 @@ static void ses_process_descriptor(struct enclosure_component *ecomp, } ecomp->slot = slot; scomp->addr = addr; + + return 0; } struct efd { @@ -549,7 +561,7 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, /* skip past overall descriptor */ desc_ptr += len + 4; } - if (ses_dev->page10) + if (ses_dev->page10 && ses_dev->page10_len > 9) addl_desc_ptr = ses_dev->page10 + 8; type_ptr = ses_dev->page1_types; components = 0; @@ -557,6 +569,7 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, for (j = 0; j < type_ptr[1]; j++) { char *name = NULL; struct enclosure_component *ecomp; + int max_desc_len; if (desc_ptr) { if (desc_ptr >= buf + page7_len) { @@ -583,10 +596,14 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, ecomp = &edev->component[components++]; if (!IS_ERR(ecomp)) { - if (addl_desc_ptr) - ses_process_descriptor( - ecomp, - addl_desc_ptr); + if (addl_desc_ptr) { + max_desc_len = ses_dev->page10_len - + (addl_desc_ptr - ses_dev->page10); + if (ses_process_descriptor(ecomp, + addl_desc_ptr, + max_desc_len)) + addl_desc_ptr = NULL; + } if (create) enclosure_component_register( ecomp); From c315560e3ef77c1d822249f1743e647dc9c9912a Mon Sep 17 00:00:00 2001 From: Tomas Henzl Date: Thu, 2 Feb 2023 17:24:50 +0100 Subject: [PATCH 1915/4345] scsi: ses: Fix possible desc_ptr out-of-bounds accesses commit 801ab13d50cf3d26170ee073ea8bb4eececb76ab upstream. Sanitize possible desc_ptr out-of-bounds accesses in ses_enclosure_data_process(). Link: https://lore.kernel.org/r/20230202162451.15346-4-thenzl@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Tomas Henzl Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/ses.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 4b66f9aec0f4..77f4322e2f71 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -572,15 +572,19 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, int max_desc_len; if (desc_ptr) { - if (desc_ptr >= buf + page7_len) { + if (desc_ptr + 3 >= buf + page7_len) { desc_ptr = NULL; } else { len = (desc_ptr[2] << 8) + desc_ptr[3]; desc_ptr += 4; - /* Add trailing zero - pushes into - * reserved space */ - desc_ptr[len] = '\0'; - name = desc_ptr; + if (desc_ptr + len > buf + page7_len) + desc_ptr = NULL; + else { + /* Add trailing zero - pushes into + * reserved space */ + desc_ptr[len] = '\0'; + name = desc_ptr; + } } } if (type_ptr[0] == ENCLOSURE_COMPONENT_DEVICE || From 8f9542cad6c27297c8391de3a659f0b7948495d0 Mon Sep 17 00:00:00 2001 From: Tomas Henzl Date: Thu, 2 Feb 2023 17:24:51 +0100 Subject: [PATCH 1916/4345] scsi: ses: Fix slab-out-of-bounds in ses_intf_remove() commit 578797f0c8cbc2e3ec5fc0dab87087b4c7073686 upstream. A fix for: BUG: KASAN: slab-out-of-bounds in ses_intf_remove+0x23f/0x270 [ses] Read of size 8 at addr ffff88a10d32e5d8 by task rmmod/12013 When edev->components is zero, accessing edev->component[0] members is wrong. Link: https://lore.kernel.org/r/20230202162451.15346-5-thenzl@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Tomas Henzl Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/ses.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 77f4322e2f71..1707d6d144d2 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -856,7 +856,8 @@ static void ses_intf_remove_enclosure(struct scsi_device *sdev) kfree(ses_dev->page2); kfree(ses_dev); - kfree(edev->component[0].scratch); + if (edev->components) + kfree(edev->component[0].scratch); put_device(&edev->edev); enclosure_unregister(edev); From 285d8390d98e2a3e44d79f391e09cc7047a50579 Mon Sep 17 00:00:00 2001 From: Andy Chiu Date: Mon, 6 Feb 2023 04:04:40 -0500 Subject: [PATCH 1917/4345] riscv: jump_label: Fixup unaligned arch_static_branch function commit 9ddfc3cd806081ce1f6c9c2f988cbb031f35d28f upstream. Runtime code patching must be done at a naturally aligned address, or we may execute on a partial instruction. We have encountered problems traced back to static jump functions during the test. We switched the tracer randomly for every 1~5 seconds on a dual-core QEMU setup and found the kernel sucking at a static branch where it jumps to itself. The reason is that the static branch was 2-byte but not 4-byte aligned. Then, the kernel would patch the instruction, either J or NOP, with two half-word stores if the machine does not have efficient unaligned accesses. Thus, moments exist where half of the NOP mixes with the other half of the J when transitioning the branch. In our particular case, on a little-endian machine, the upper half of the NOP was mixed with the lower part of the J when enabling the branch, resulting in a jump that jumped to itself. Conversely, it would result in a HINT instruction when disabling the branch, but it might not be observable. ARM64 does not have this problem since all instructions must be 4-byte aligned. Fixes: ebc00dde8a97 ("riscv: Add jump-label implementation") Link: https://lore.kernel.org/linux-riscv/20220913094252.3555240-6-andy.chiu@sifive.com/ Reviewed-by: Greentime Hu Signed-off-by: Andy Chiu Signed-off-by: Guo Ren Link: https://lore.kernel.org/r/20230206090440.1255001-1-guoren@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/include/asm/jump_label.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h index 38af2ec7b9bf..729991e8f782 100644 --- a/arch/riscv/include/asm/jump_label.h +++ b/arch/riscv/include/asm/jump_label.h @@ -18,6 +18,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto( + " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" " .option norvc \n\t" @@ -39,6 +40,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { asm_volatile_goto( + " .align 2 \n\t" " .option push \n\t" " .option norelax \n\t" " .option norvc \n\t" From d219b19e1f26997a4c864ad2d0931fd859967e44 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sun, 15 Jan 2023 09:20:31 +0100 Subject: [PATCH 1918/4345] PCI/PM: Observe reset delay irrespective of bridge_d3 commit 8ef0217227b42e2c34a18de316cee3da16c9bf1e upstream. If a PCI bridge is suspended to D3cold upon entering system sleep, resuming it entails a Fundamental Reset per PCIe r6.0 sec 5.8. The delay prescribed after a Fundamental Reset in PCIe r6.0 sec 6.6.1 is sought to be observed by: pci_pm_resume_noirq() pci_pm_bridge_power_up_actions() pci_bridge_wait_for_secondary_bus() However, pci_bridge_wait_for_secondary_bus() bails out if the bridge_d3 flag is not set. That flag indicates whether a bridge is allowed to suspend to D3cold at *runtime*. Hence *no* delay is observed on resume from system sleep if runtime D3cold is forbidden. That doesn't make any sense, so drop the bridge_d3 check from pci_bridge_wait_for_secondary_bus(). The purpose of the bridge_d3 check was probably to avoid delays if a bridge remained in D0 during suspend. However the sole caller of pci_bridge_wait_for_secondary_bus(), pci_pm_bridge_power_up_actions(), is only invoked if the previous power state was D3cold. Hence the additional bridge_d3 check seems superfluous. Fixes: ad9001f2f411 ("PCI/PM: Add missing link delays required by the PCIe spec") Link: https://lore.kernel.org/r/eb37fa345285ec8bacabbf06b020b803f77bdd3d.1673769517.git.lukas@wunner.de Tested-by: Ravi Kishore Koppuravuri Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg Reviewed-by: Kuppuswamy Sathyanarayanan Cc: stable@vger.kernel.org # v5.5+ Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 262577c81d30..845851e23352 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4808,7 +4808,7 @@ void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) if (pci_dev_is_disconnected(dev)) return; - if (!pci_is_bridge(dev) || !dev->bridge_d3) + if (!pci_is_bridge(dev)) return; down_read(&pci_bus_sem); From 88b51c6a6d57f90638d54e28e58dca3f73c31bca Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 20 Jan 2023 10:19:02 +0100 Subject: [PATCH 1919/4345] PCI: hotplug: Allow marking devices as disconnected during bind/unbind commit 74ff8864cc842be994853095dba6db48e716400a upstream. On surprise removal, pciehp_unconfigure_device() and acpiphp's trim_stale_devices() call pci_dev_set_disconnected() to mark removed devices as permanently offline. Thereby, the PCI core and drivers know to skip device accesses. However pci_dev_set_disconnected() takes the device_lock and thus waits for a concurrent driver bind or unbind to complete. As a result, the driver's ->probe and ->remove hooks have no chance to learn that the device is gone. That doesn't make any sense, so drop the device_lock and instead use atomic xchg() and cmpxchg() operations to update the device state. As a byproduct, an AB-BA deadlock reported by Anatoli is fixed which occurs on surprise removal with AER concurrently performing a bus reset. AER bus reset: INFO: task irq/26-aerdrv:95 blocked for more than 120 seconds. Tainted: G W 6.2.0-rc3-custom-norework-jan11+ schedule rwsem_down_write_slowpath down_write_nested pciehp_reset_slot # acquires reset_lock pci_reset_hotplug_slot pci_slot_reset # acquires device_lock pci_bus_error_reset aer_root_reset pcie_do_recovery aer_process_err_devices aer_isr pciehp surprise removal: INFO: task irq/26-pciehp:96 blocked for more than 120 seconds. Tainted: G W 6.2.0-rc3-custom-norework-jan11+ schedule_preempt_disabled __mutex_lock mutex_lock_nested pci_dev_set_disconnected # acquires device_lock pci_walk_bus pciehp_unconfigure_device pciehp_disable_slot pciehp_handle_presence_or_link_change pciehp_ist # acquires reset_lock Link: https://bugzilla.kernel.org/show_bug.cgi?id=215590 Fixes: a6bd101b8f84 ("PCI: Unify device inaccessible") Link: https://lore.kernel.org/r/3dc88ea82bdc0e37d9000e413d5ebce481cbd629.1674205689.git.lukas@wunner.de Reported-by: Anatoli Antonovitch Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org # v4.20+ Cc: Keith Busch Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci.h | 43 +++++++++++++------------------------------ 1 file changed, 13 insertions(+), 30 deletions(-) diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 0039460c6ab0..9197d7362731 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -351,53 +351,36 @@ struct pci_sriov { * @dev - pci device to set new error_state * @new - the state we want dev to be in * - * Must be called with device_lock held. + * If the device is experiencing perm_failure, it has to remain in that state. + * Any other transition is allowed. * * Returns true if state has been changed to the requested state. */ static inline bool pci_dev_set_io_state(struct pci_dev *dev, pci_channel_state_t new) { - bool changed = false; + pci_channel_state_t old; - device_lock_assert(&dev->dev); switch (new) { case pci_channel_io_perm_failure: - switch (dev->error_state) { - case pci_channel_io_frozen: - case pci_channel_io_normal: - case pci_channel_io_perm_failure: - changed = true; - break; - } - break; + xchg(&dev->error_state, pci_channel_io_perm_failure); + return true; case pci_channel_io_frozen: - switch (dev->error_state) { - case pci_channel_io_frozen: - case pci_channel_io_normal: - changed = true; - break; - } - break; + old = cmpxchg(&dev->error_state, pci_channel_io_normal, + pci_channel_io_frozen); + return old != pci_channel_io_perm_failure; case pci_channel_io_normal: - switch (dev->error_state) { - case pci_channel_io_frozen: - case pci_channel_io_normal: - changed = true; - break; - } - break; + old = cmpxchg(&dev->error_state, pci_channel_io_frozen, + pci_channel_io_normal); + return old != pci_channel_io_perm_failure; + default: + return false; } - if (changed) - dev->error_state = new; - return changed; } static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) { - device_lock(&dev->dev); pci_dev_set_io_state(dev, pci_channel_io_perm_failure); - device_unlock(&dev->dev); return 0; } From 691a8e26de7809fe15284713c2338c93ffe0345c Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sat, 28 Jan 2023 10:39:51 +0900 Subject: [PATCH 1920/4345] PCI: Avoid FLR for AMD FCH AHCI adapters commit 63ba51db24ed1b8f8088a897290eb6c036c5435d upstream. PCI passthrough to VMs does not work with AMD FCH AHCI adapters: the guest OS fails to correctly probe devices attached to the controller due to FIS communication failures: ata4: softreset failed (1st FIS failed) ... ata4.00: qc timeout after 5000 msecs (cmd 0xec) ata4.00: failed to IDENTIFY (I/O error, err_mask=0x4) Forcing the "bus" reset method before unbinding & binding the adapter to the vfio-pci driver solves this issue, e.g.: echo "bus" > /sys/bus/pci/devices//reset_method gives a working guest OS, indicating that the default FLR reset method doesn't work correctly. Apply quirk_no_flr() to AMD FCH AHCI devices to work around this issue. Link: https://lore.kernel.org/r/20230128013951.523247-1-damien.lemoal@opensource.wdc.com Reported-by: Niklas Cassel Signed-off-by: Damien Le Moal Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index fb2e52fd01b3..f30c42f0ac31 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5302,6 +5302,7 @@ static void quirk_no_flr(struct pci_dev *dev) DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1487, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x148c, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x149c, quirk_no_flr); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x7901, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_no_flr); From 5a271242716846cc016736fb76be2b40ee49b0c3 Mon Sep 17 00:00:00 2001 From: Steve Sistare Date: Tue, 31 Jan 2023 08:58:04 -0800 Subject: [PATCH 1921/4345] vfio/type1: prevent underflow of locked_vm via exec() commit 046eca5018f8a5dd1dc2cedf87fb5843b9ea3026 upstream. When a vfio container is preserved across exec, the task does not change, but it gets a new mm with locked_vm=0, and loses the count from existing dma mappings. If the user later unmaps a dma mapping, locked_vm underflows to a large unsigned value, and a subsequent dma map request fails with ENOMEM in __account_locked_vm. To avoid underflow, grab and save the mm at the time a dma is mapped. Use that mm when adjusting locked_vm, rather than re-acquiring the saved task's mm, which may have changed. If the saved mm is dead, do nothing. locked_vm is incremented for existing mappings in a subsequent patch. Fixes: 73fa0d10d077 ("vfio: Type1 IOMMU implementation") Cc: stable@vger.kernel.org Signed-off-by: Steve Sistare Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1675184289-267876-3-git-send-email-steven.sistare@oracle.com Signed-off-by: Alex Williamson Signed-off-by: Greg Kroah-Hartman --- drivers/vfio/vfio_iommu_type1.c | 41 +++++++++++---------------------- 1 file changed, 14 insertions(+), 27 deletions(-) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index ce50ca9a320c..ec1428dbdf9d 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -96,6 +96,7 @@ struct vfio_dma { struct task_struct *task; struct rb_root pfn_list; /* Ex-user pinned pfn list */ unsigned long *bitmap; + struct mm_struct *mm; }; struct vfio_batch { @@ -391,8 +392,8 @@ static int vfio_lock_acct(struct vfio_dma *dma, long npage, bool async) if (!npage) return 0; - mm = async ? get_task_mm(dma->task) : dma->task->mm; - if (!mm) + mm = dma->mm; + if (async && !mmget_not_zero(mm)) return -ESRCH; /* process exited */ ret = mmap_write_lock_killable(mm); @@ -666,8 +667,8 @@ static int vfio_pin_page_external(struct vfio_dma *dma, unsigned long vaddr, struct mm_struct *mm; int ret; - mm = get_task_mm(dma->task); - if (!mm) + mm = dma->mm; + if (!mmget_not_zero(mm)) return -ENODEV; ret = vaddr_get_pfns(mm, vaddr, 1, dma->prot, pfn_base, pages); @@ -677,7 +678,7 @@ static int vfio_pin_page_external(struct vfio_dma *dma, unsigned long vaddr, ret = 0; if (do_accounting && !is_invalid_reserved_pfn(*pfn_base)) { - ret = vfio_lock_acct(dma, 1, true); + ret = vfio_lock_acct(dma, 1, false); if (ret) { put_pfn(*pfn_base, dma->prot); if (ret == -ENOMEM) @@ -1031,6 +1032,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma) vfio_unmap_unpin(iommu, dma, true); vfio_unlink_dma(iommu, dma); put_task_struct(dma->task); + mmdrop(dma->mm); vfio_dma_bitmap_free(dma); kfree(dma); iommu->dma_avail++; @@ -1452,29 +1454,15 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu, * against the locked memory limit and we need to be able to do both * outside of this call path as pinning can be asynchronous via the * external interfaces for mdev devices. RLIMIT_MEMLOCK requires a - * task_struct and VM locked pages requires an mm_struct, however - * holding an indefinite mm reference is not recommended, therefore we - * only hold a reference to a task. We could hold a reference to - * current, however QEMU uses this call path through vCPU threads, - * which can be killed resulting in a NULL mm and failure in the unmap - * path when called via a different thread. Avoid this problem by - * using the group_leader as threads within the same group require - * both CLONE_THREAD and CLONE_VM and will therefore use the same - * mm_struct. - * - * Previously we also used the task for testing CAP_IPC_LOCK at the - * time of pinning and accounting, however has_capability() makes use - * of real_cred, a copy-on-write field, so we can't guarantee that it - * matches group_leader, or in fact that it might not change by the - * time it's evaluated. If a process were to call MAP_DMA with - * CAP_IPC_LOCK but later drop it, it doesn't make sense that they - * possibly see different results for an iommu_mapped vfio_dma vs - * externally mapped. Therefore track CAP_IPC_LOCK in vfio_dma at the - * time of calling MAP_DMA. + * task_struct. Save the group_leader so that all DMA tracking uses + * the same task, to make debugging easier. VM locked pages requires + * an mm_struct, so grab the mm in case the task dies. */ get_task_struct(current->group_leader); dma->task = current->group_leader; dma->lock_cap = capable(CAP_IPC_LOCK); + dma->mm = current->mm; + mmgrab(dma->mm); dma->pfn_list = RB_ROOT; @@ -2998,9 +2986,8 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu, !(dma->prot & IOMMU_READ)) return -EPERM; - mm = get_task_mm(dma->task); - - if (!mm) + mm = dma->mm; + if (!mmget_not_zero(mm)) return -EPERM; if (kthread) From 266864c1e0edb4034f6346b5309f0e68494bcfb3 Mon Sep 17 00:00:00 2001 From: Mavroudis Chatzilaridis Date: Wed, 1 Feb 2023 18:51:25 +0000 Subject: [PATCH 1922/4345] drm/i915/quirks: Add inverted backlight quirk for HP 14-r206nv commit 5e438bf7f9a1705ebcae5fa89cdbfbc6932a7871 upstream. This laptop uses inverted backlight PWM. Thus, without this quirk, backlight brightness decreases as the brightness value increases and vice versa. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/8013 Cc: stable@vger.kernel.org Signed-off-by: Mavroudis Chatzilaridis Reviewed-by: Jani Nikula Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20230201184947.8835-1-mavchatz@protonmail.com (cherry picked from commit 83e7d6fd330d413cb2064e680ffea91b0512a520) Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/display/intel_quirks.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c index 8eb1842f14ce..b4e74c86fae7 100644 --- a/drivers/gpu/drm/i915/display/intel_quirks.c +++ b/drivers/gpu/drm/i915/display/intel_quirks.c @@ -159,6 +159,8 @@ static struct intel_quirk intel_quirks[] = { /* ECS Liva Q2 */ { 0x3185, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time }, { 0x3184, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time }, + /* HP Notebook - 14-r206nv */ + { 0x0f31, 0x103c, 0x220f, quirk_invert_brightness }, }; void intel_init_quirks(struct drm_i915_private *i915) From 1f064aaa81af466ea5da53181debe9c82aeed4be Mon Sep 17 00:00:00 2001 From: Mark Hawrylak Date: Sun, 19 Feb 2023 16:02:00 +1100 Subject: [PATCH 1923/4345] drm/radeon: Fix eDP for single-display iMac11,2 commit 05eacc198c68cbb35a7281ce4011f8899ee1cfb8 upstream. Apple iMac11,2 (mid 2010) also with Radeon HD-4670 that has the same issue as iMac10,1 (late 2009) where the internal eDP panel stays dark on driver load. This patch treats iMac11,2 the same as iMac10,1, so the eDP panel stays active. Additional steps: Kernel boot parameter radeon.nomodeset=0 required to keep the eDP panel active. This patch is an extension of commit 564d8a2cf3ab ("drm/radeon: Fix eDP for single-display iMac10,1 (v2)") Link: https://lore.kernel.org/all/lsq.1507553064.833262317@decadent.org.uk/ Signed-off-by: Mark Hawrylak Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/radeon/atombios_encoders.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 12aa7877a625..8cca58f25c0f 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -2191,11 +2191,12 @@ int radeon_atom_pick_dig_encoder(struct drm_encoder *encoder, int fe_idx) /* * On DCE32 any encoder can drive any block so usually just use crtc id, - * but Apple thinks different at least on iMac10,1, so there use linkb, + * but Apple thinks different at least on iMac10,1 and iMac11,2, so there use linkb, * otherwise the internal eDP panel will stay dark. */ if (ASIC_IS_DCE32(rdev)) { - if (dmi_match(DMI_PRODUCT_NAME, "iMac10,1")) + if (dmi_match(DMI_PRODUCT_NAME, "iMac10,1") || + dmi_match(DMI_PRODUCT_NAME, "iMac11,2")) enc_idx = (dig->linkb) ? 1 : 0; else enc_idx = radeon_crtc->crtc_id; From 64a99c0ac6f8b714960a71d34a91a54acb4117e4 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 4 Jan 2023 12:05:16 +0200 Subject: [PATCH 1924/4345] drm/edid: fix AVI infoframe aspect ratio handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1cbc1f0d324ba6c4d1b10ac6362b5e0b029f63d5 upstream. We try to avoid sending VICs defined in the later specs in AVI infoframes to sinks that conform to the earlier specs, to not upset them, and use 0 for the VIC instead. However, we do this detection and conversion to 0 too early, as we'll need the actual VIC to figure out the aspect ratio. In particular, for a mode with 64:27 aspect ratio, 0 for VIC fails the AVI infoframe generation altogether with -EINVAL. Separate the VIC lookup from the "filtering", and postpone the filtering, to use the proper VIC for aspect ratio handling, and the 0 VIC for the infoframe video code as needed. Reported-by: William Tseng Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/6153 References: https://lore.kernel.org/r/20220920062316.43162-1-william.tseng@intel.com Cc: Cc: Ville Syrjälä Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/c3e78cc6d01ed237f71ad0038826b08d83d75eef.1672826282.git.jani.nikula@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_edid.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 4334e466b4e0..39eb39e78d7a 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -5560,8 +5560,6 @@ static u8 drm_mode_hdmi_vic(const struct drm_connector *connector, static u8 drm_mode_cea_vic(const struct drm_connector *connector, const struct drm_display_mode *mode) { - u8 vic; - /* * HDMI spec says if a mode is found in HDMI 1.4b 4K modes * we should send its VIC in vendor infoframes, else send the @@ -5571,13 +5569,18 @@ static u8 drm_mode_cea_vic(const struct drm_connector *connector, if (drm_mode_hdmi_vic(connector, mode)) return 0; - vic = drm_match_cea_mode(mode); + return drm_match_cea_mode(mode); +} - /* - * HDMI 1.4 VIC range: 1 <= VIC <= 64 (CEA-861-D) but - * HDMI 2.0 VIC range: 1 <= VIC <= 107 (CEA-861-F). So we - * have to make sure we dont break HDMI 1.4 sinks. - */ +/* + * Avoid sending VICs defined in HDMI 2.0 in AVI infoframes to sinks that + * conform to HDMI 1.4. + * + * HDMI 1.4 (CTA-861-D) VIC range: [1..64] + * HDMI 2.0 (CTA-861-F) VIC range: [1..107] + */ +static u8 vic_for_avi_infoframe(const struct drm_connector *connector, u8 vic) +{ if (!is_hdmi2_sink(connector) && vic > 64) return 0; @@ -5653,7 +5656,7 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame, picture_aspect = HDMI_PICTURE_ASPECT_NONE; } - frame->video_code = vic; + frame->video_code = vic_for_avi_infoframe(connector, vic); frame->picture_aspect = picture_aspect; frame->active_aspect = HDMI_ACTIVE_ASPECT_PICTURE; frame->scan_mode = HDMI_SCAN_MODE_UNDERSCAN; From a2a1e3f4ed5bf698b41f0aeddfdb931bb0718168 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 13 Jan 2023 17:44:41 +0100 Subject: [PATCH 1925/4345] arm64: dts: qcom: ipq8074: fix Gen2 PCIe QMP PHY commit 100d9c94ccf15b02742c326cd04f422ab729153b upstream. Serdes register space sizes are incorrect, update them to match the actual sizes from downstream QCA 5.4 kernel. Fixes: 942bcd33ed45 ("arm64: dts: qcom: Fix IPQ8074 PCIe PHY nodes") Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230113164449.906002-1-robimarko@gmail.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 25f78c71e010..e191a7bc532b 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -213,9 +213,9 @@ status = "disabled"; pcie_phy1: phy@8e200 { - reg = <0x8e200 0x16c>, + reg = <0x8e200 0x130>, <0x8e400 0x200>, - <0x8e800 0x4f4>; + <0x8e800 0x1f8>; #phy-cells = <0>; #clock-cells = <0>; clocks = <&gcc GCC_PCIE1_PIPE_CLK>; From 844da3901304d6946c42edc89b793cc07981683b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 15 Dec 2022 17:55:42 +0100 Subject: [PATCH 1926/4345] wifi: ath9k: use proper statements in conditionals MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b7dc753fe33a707379e2254317794a4dad6c0fe2 upstream. A previous cleanup patch accidentally broke some conditional expressions by replacing the safe "do {} while (0)" constructs with empty macros. gcc points this out when extra warnings are enabled: drivers/net/wireless/ath/ath9k/hif_usb.c: In function 'ath9k_skb_queue_complete': drivers/net/wireless/ath/ath9k/hif_usb.c:251:57: error: suggest braces around empty body in an 'else' statement [-Werror=empty-body] 251 | TX_STAT_INC(hif_dev, skb_failed); Make both sets of macros proper expressions again. Fixes: d7fc76039b74 ("ath9k: htc: clean up statistics macros") Signed-off-by: Arnd Bergmann Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221215165553.1950307-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ath/ath9k/htc.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index 30f0765fb9fd..237f4ec2cffd 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -327,9 +327,9 @@ static inline struct ath9k_htc_tx_ctl *HTC_SKB_CB(struct sk_buff *skb) } #ifdef CONFIG_ATH9K_HTC_DEBUGFS -#define __STAT_SAFE(hif_dev, expr) ((hif_dev)->htc_handle->drv_priv ? (expr) : 0) -#define CAB_STAT_INC(priv) ((priv)->debug.tx_stats.cab_queued++) -#define TX_QSTAT_INC(priv, q) ((priv)->debug.tx_stats.queue_stats[q]++) +#define __STAT_SAFE(hif_dev, expr) do { ((hif_dev)->htc_handle->drv_priv ? (expr) : 0); } while (0) +#define CAB_STAT_INC(priv) do { ((priv)->debug.tx_stats.cab_queued++); } while (0) +#define TX_QSTAT_INC(priv, q) do { ((priv)->debug.tx_stats.queue_stats[q]++); } while (0) #define TX_STAT_INC(hif_dev, c) \ __STAT_SAFE((hif_dev), (hif_dev)->htc_handle->drv_priv->debug.tx_stats.c++) @@ -378,10 +378,10 @@ void ath9k_htc_get_et_stats(struct ieee80211_hw *hw, struct ethtool_stats *stats, u64 *data); #else -#define TX_STAT_INC(hif_dev, c) -#define TX_STAT_ADD(hif_dev, c, a) -#define RX_STAT_INC(hif_dev, c) -#define RX_STAT_ADD(hif_dev, c, a) +#define TX_STAT_INC(hif_dev, c) do { } while (0) +#define TX_STAT_ADD(hif_dev, c, a) do { } while (0) +#define RX_STAT_INC(hif_dev, c) do { } while (0) +#define RX_STAT_ADD(hif_dev, c, a) do { } while (0) #define CAB_STAT_INC(priv) #define TX_QSTAT_INC(priv, c) From 50afcd5316f263d42fdef0b25c2104a2609eb535 Mon Sep 17 00:00:00 2001 From: Jonas Karlman Date: Tue, 10 Jan 2023 08:46:53 +0000 Subject: [PATCH 1927/4345] pinctrl: rockchip: fix mux route data for rk3568 commit 431d1531466033909d2e8c754a7dc3704b70843f upstream. IO mux selection is configured in PMU_GRF_SOC_CON4 and GRF_IOFUNC_SEL0-5 regs on RK3568. pwm0-2 is configured in PMU_GRF reg and the rest is configured in GRF_IOFUNC regs according to TRM [1]. Update mux route data to reflect this and use proper detection pin for UART1 IO mux M1. This fixes HDMITX IO mux M1 selection and makes it possible to enable HDMI CEC on my Radxa ROCK 3 Model A v1.31 board. [1] http://opensource.rock-chips.com/images/2/26/Rockchip_RK3568_TRM_Part1_V1.3-20220930P.PDF Fixes: c0dadc0e47a8 ("pinctrl: rockchip: add support for rk3568") Signed-off-by: Jonas Karlman Link: https://lore.kernel.org/r/20230110084636.1141740-1-jonas@kwiboo.se Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-rockchip.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 764c96ddfc76..11791afeaf82 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -954,19 +954,19 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = { RK_MUXROUTE_PMU(0, RK_PB5, 4, 0x0110, WRITE_MASK_VAL(3, 2, 1)), /* PWM1 IO mux M1 */ RK_MUXROUTE_PMU(0, RK_PC1, 1, 0x0110, WRITE_MASK_VAL(5, 4, 0)), /* PWM2 IO mux M0 */ RK_MUXROUTE_PMU(0, RK_PB6, 4, 0x0110, WRITE_MASK_VAL(5, 4, 1)), /* PWM2 IO mux M1 */ - RK_MUXROUTE_PMU(0, RK_PB3, 2, 0x0300, WRITE_MASK_VAL(0, 0, 0)), /* CAN0 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PB3, 2, 0x0300, WRITE_MASK_VAL(0, 0, 0)), /* CAN0 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PA1, 4, 0x0300, WRITE_MASK_VAL(0, 0, 1)), /* CAN0 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PA1, 3, 0x0300, WRITE_MASK_VAL(2, 2, 0)), /* CAN1 IO mux M0 */ RK_MUXROUTE_GRF(4, RK_PC3, 3, 0x0300, WRITE_MASK_VAL(2, 2, 1)), /* CAN1 IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PB5, 3, 0x0300, WRITE_MASK_VAL(4, 4, 0)), /* CAN2 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PB2, 4, 0x0300, WRITE_MASK_VAL(4, 4, 1)), /* CAN2 IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PC4, 1, 0x0300, WRITE_MASK_VAL(6, 6, 0)), /* HPDIN IO mux M0 */ - RK_MUXROUTE_PMU(0, RK_PC2, 2, 0x0300, WRITE_MASK_VAL(6, 6, 1)), /* HPDIN IO mux M1 */ + RK_MUXROUTE_GRF(0, RK_PC2, 2, 0x0300, WRITE_MASK_VAL(6, 6, 1)), /* HPDIN IO mux M1 */ RK_MUXROUTE_GRF(3, RK_PB1, 3, 0x0300, WRITE_MASK_VAL(8, 8, 0)), /* GMAC1 IO mux M0 */ RK_MUXROUTE_GRF(4, RK_PA7, 3, 0x0300, WRITE_MASK_VAL(8, 8, 1)), /* GMAC1 IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PD1, 1, 0x0300, WRITE_MASK_VAL(10, 10, 0)), /* HDMITX IO mux M0 */ - RK_MUXROUTE_PMU(0, RK_PC7, 1, 0x0300, WRITE_MASK_VAL(10, 10, 1)), /* HDMITX IO mux M1 */ - RK_MUXROUTE_PMU(0, RK_PB6, 1, 0x0300, WRITE_MASK_VAL(14, 14, 0)), /* I2C2 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PC7, 1, 0x0300, WRITE_MASK_VAL(10, 10, 1)), /* HDMITX IO mux M1 */ + RK_MUXROUTE_GRF(0, RK_PB6, 1, 0x0300, WRITE_MASK_VAL(14, 14, 0)), /* I2C2 IO mux M0 */ RK_MUXROUTE_GRF(4, RK_PB4, 1, 0x0300, WRITE_MASK_VAL(14, 14, 1)), /* I2C2 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PA0, 1, 0x0304, WRITE_MASK_VAL(0, 0, 0)), /* I2C3 IO mux M0 */ RK_MUXROUTE_GRF(3, RK_PB6, 4, 0x0304, WRITE_MASK_VAL(0, 0, 1)), /* I2C3 IO mux M1 */ @@ -992,7 +992,7 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = { RK_MUXROUTE_GRF(4, RK_PC3, 1, 0x0308, WRITE_MASK_VAL(12, 12, 1)), /* PWM15 IO mux M1 */ RK_MUXROUTE_GRF(3, RK_PD2, 3, 0x0308, WRITE_MASK_VAL(14, 14, 0)), /* SDMMC2 IO mux M0 */ RK_MUXROUTE_GRF(3, RK_PA5, 5, 0x0308, WRITE_MASK_VAL(14, 14, 1)), /* SDMMC2 IO mux M1 */ - RK_MUXROUTE_PMU(0, RK_PB5, 2, 0x030c, WRITE_MASK_VAL(0, 0, 0)), /* SPI0 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PB5, 2, 0x030c, WRITE_MASK_VAL(0, 0, 0)), /* SPI0 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PD3, 3, 0x030c, WRITE_MASK_VAL(0, 0, 1)), /* SPI0 IO mux M1 */ RK_MUXROUTE_GRF(2, RK_PB5, 3, 0x030c, WRITE_MASK_VAL(2, 2, 0)), /* SPI1 IO mux M0 */ RK_MUXROUTE_GRF(3, RK_PC3, 3, 0x030c, WRITE_MASK_VAL(2, 2, 1)), /* SPI1 IO mux M1 */ @@ -1001,8 +1001,8 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = { RK_MUXROUTE_GRF(4, RK_PB3, 4, 0x030c, WRITE_MASK_VAL(6, 6, 0)), /* SPI3 IO mux M0 */ RK_MUXROUTE_GRF(4, RK_PC2, 2, 0x030c, WRITE_MASK_VAL(6, 6, 1)), /* SPI3 IO mux M1 */ RK_MUXROUTE_GRF(2, RK_PB4, 2, 0x030c, WRITE_MASK_VAL(8, 8, 0)), /* UART1 IO mux M0 */ - RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(8, 8, 1)), /* UART1 IO mux M1 */ - RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(10, 10, 0)), /* UART2 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PD6, 4, 0x030c, WRITE_MASK_VAL(8, 8, 1)), /* UART1 IO mux M1 */ + RK_MUXROUTE_GRF(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(10, 10, 0)), /* UART2 IO mux M0 */ RK_MUXROUTE_GRF(1, RK_PD5, 2, 0x030c, WRITE_MASK_VAL(10, 10, 1)), /* UART2 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PA1, 2, 0x030c, WRITE_MASK_VAL(12, 12, 0)), /* UART3 IO mux M0 */ RK_MUXROUTE_GRF(3, RK_PB7, 4, 0x030c, WRITE_MASK_VAL(12, 12, 1)), /* UART3 IO mux M1 */ @@ -1032,13 +1032,13 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = { RK_MUXROUTE_GRF(3, RK_PD6, 5, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PA0, 4, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */ RK_MUXROUTE_GRF(3, RK_PC4, 5, 0x0314, WRITE_MASK_VAL(1, 0, 2)), /* PDM IO mux M2 */ - RK_MUXROUTE_PMU(0, RK_PA5, 3, 0x0314, WRITE_MASK_VAL(3, 2, 0)), /* PCIE20 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PA5, 3, 0x0314, WRITE_MASK_VAL(3, 2, 0)), /* PCIE20 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PD0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 1)), /* PCIE20 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PB0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 2)), /* PCIE20 IO mux M2 */ - RK_MUXROUTE_PMU(0, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(5, 4, 0)), /* PCIE30X1 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(5, 4, 0)), /* PCIE30X1 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PD2, 4, 0x0314, WRITE_MASK_VAL(5, 4, 1)), /* PCIE30X1 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PA5, 4, 0x0314, WRITE_MASK_VAL(5, 4, 2)), /* PCIE30X1 IO mux M2 */ - RK_MUXROUTE_PMU(0, RK_PA6, 2, 0x0314, WRITE_MASK_VAL(7, 6, 0)), /* PCIE30X2 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PA6, 2, 0x0314, WRITE_MASK_VAL(7, 6, 0)), /* PCIE30X2 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PD4, 4, 0x0314, WRITE_MASK_VAL(7, 6, 1)), /* PCIE30X2 IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PC2, 4, 0x0314, WRITE_MASK_VAL(7, 6, 2)), /* PCIE30X2 IO mux M2 */ }; From f8ac5467e1f3f773326454bea793172ed7cff5be Mon Sep 17 00:00:00 2001 From: Jonas Karlman Date: Tue, 10 Jan 2023 17:29:58 +0000 Subject: [PATCH 1928/4345] pinctrl: rockchip: fix reading pull type on rk3568 commit 31b62a98de42cf65d76e4dcfb571af067d27d83a upstream. When reading pinconf-pins from debugfs it fails to get the configured pull type on RK3568, "unsupported pinctrl type" error messages is also reported. Fix this by adding support for RK3568 in rockchip_get_pull, including a reverse of the pull-up value swap applied in rockchip_set_pull so that pull-up is correctly reported in pinconf-pins. Also update the workaround comment to reflect affected pins, GPIO0_D3-D6. Fixes: c0dadc0e47a8 ("pinctrl: rockchip: add support for rk3568") Signed-off-by: Jonas Karlman Reviewed-by: Heiko Stuebner Reviewed-by: Jianqun Xu Link: https://lore.kernel.org/r/20230110172955.1258840-1-jonas@kwiboo.se Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-rockchip.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 11791afeaf82..2a454098eaaa 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -2045,9 +2045,18 @@ static int rockchip_get_pull(struct rockchip_pin_bank *bank, int pin_num) case RK3308: case RK3368: case RK3399: + case RK3568: pull_type = bank->pull_type[pin_num / 8]; data >>= bit; data &= (1 << RK3188_PULL_BITS_PER_PIN) - 1; + /* + * In the TRM, pull-up being 1 for everything except the GPIO0_D3-D6, + * where that pull up value becomes 3. + */ + if (ctrl->type == RK3568 && bank->bank_num == 0 && pin_num >= 27 && pin_num <= 30) { + if (data == 3) + data = 1; + } return rockchip_pull_list[pull_type][data]; default: @@ -2101,7 +2110,7 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank, } } /* - * In the TRM, pull-up being 1 for everything except the GPIO0_D0-D6, + * In the TRM, pull-up being 1 for everything except the GPIO0_D3-D6, * where that pull up value becomes 3. */ if (ctrl->type == RK3568 && bank->bank_num == 0 && pin_num >= 27 && pin_num <= 30) { From 322df540ba0590103839f94f441818f5696b8b00 Mon Sep 17 00:00:00 2001 From: Dmitry Goncharov Date: Mon, 5 Dec 2022 16:48:19 -0500 Subject: [PATCH 1929/4345] kbuild: Port silent mode detection to future gnu make. commit 4bf73588165ba7d32131a043775557a54b6e1db5 upstream. Port silent mode detection to the future (post make-4.4) versions of gnu make. Makefile contains the following piece of make code to detect if option -s is specified on the command line. ifneq ($(findstring s,$(filter-out --%,$(MAKEFLAGS))),) This code is executed by make at parse time and assumes that MAKEFLAGS does not contain command line variable definitions. Currently if the user defines a=s on the command line, then at build only time MAKEFLAGS contains " -- a=s". However, starting with commit dc2d963989b96161472b2cd38cef5d1f4851ea34 MAKEFLAGS contains command line definitions at both parse time and build time. This '-s' detection code then confuses a command line variable definition which contains letter 's' with option -s. $ # old make $ make net/wireless/ocb.o a=s CALL scripts/checksyscalls.sh DESCEND objtool $ # this a new make which defines makeflags at parse time $ ~/src/gmake/make/l64/make net/wireless/ocb.o a=s $ We can see here that the letter 's' from 'a=s' was confused with -s. This patch checks for presence of -s using a method recommended by the make manual here https://www.gnu.org/software/make/manual/make.html#Testing-Flags. Link: https://lists.gnu.org/archive/html/bug-make/2022-11/msg00190.html Reported-by: Jan Palus Signed-off-by: Dmitry Goncharov Signed-off-by: Masahiro Yamada Signed-off-by: Greg Kroah-Hartman --- Makefile | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 447ed158d6bc..5ca862041b71 100644 --- a/Makefile +++ b/Makefile @@ -93,9 +93,16 @@ endif # If the user is running make -s (silent mode), suppress echoing of # commands +# make-4.0 (and later) keep single letter options in the 1st word of MAKEFLAGS. -ifneq ($(findstring s,$(filter-out --%,$(MAKEFLAGS))),) - quiet=silent_ +ifeq ($(filter 3.%,$(MAKE_VERSION)),) +silence:=$(findstring s,$(firstword -$(MAKEFLAGS))) +else +silence:=$(findstring s,$(filter-out --%,$(MAKEFLAGS))) +endif + +ifeq ($(silence),s) +quiet=silent_ endif export quiet Q KBUILD_VERBOSE From 18c3fa7a7fdbb4d21dafc8a7710ae2c1680930f6 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 14 Feb 2023 08:49:14 -0500 Subject: [PATCH 1930/4345] net/sched: Retire tcindex classifier commit 8c710f75256bb3cf05ac7b1672c82b92c43f3d28 upstream. The tcindex classifier has served us well for about a quarter of a century but has not been getting much TLC due to lack of known users. Most recently it has become easy prey to syzkaller. For this reason, we are retiring it. Signed-off-by: Jamal Hadi Salim Acked-by: Jiri Pirko Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- net/sched/Kconfig | 11 - net/sched/Makefile | 1 - net/sched/cls_tcindex.c | 756 ---------------------------------------- 3 files changed, 768 deletions(-) delete mode 100644 net/sched/cls_tcindex.c diff --git a/net/sched/Kconfig b/net/sched/Kconfig index bc4e5da76fa6..697522371914 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -503,17 +503,6 @@ config NET_CLS_BASIC To compile this code as a module, choose M here: the module will be called cls_basic. -config NET_CLS_TCINDEX - tristate "Traffic-Control Index (TCINDEX)" - select NET_CLS - help - Say Y here if you want to be able to classify packets based on - traffic control indices. You will want this feature if you want - to implement Differentiated Services together with DSMARK. - - To compile this code as a module, choose M here: the - module will be called cls_tcindex. - config NET_CLS_ROUTE4 tristate "Routing decision (ROUTE)" depends on INET diff --git a/net/sched/Makefile b/net/sched/Makefile index 66bbf9a98f9e..4311fdb21119 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -69,7 +69,6 @@ obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o -obj-$(CONFIG_NET_CLS_TCINDEX) += cls_tcindex.o obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c deleted file mode 100644 index 2c0c95204cb5..000000000000 --- a/net/sched/cls_tcindex.c +++ /dev/null @@ -1,756 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * net/sched/cls_tcindex.c Packet classifier for skb->tc_index - * - * Written 1998,1999 by Werner Almesberger, EPFL ICA - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * Passing parameters to the root seems to be done more awkwardly than really - * necessary. At least, u32 doesn't seem to use such dirty hacks. To be - * verified. FIXME. - */ - -#define PERFECT_HASH_THRESHOLD 64 /* use perfect hash if not bigger */ -#define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */ - - -struct tcindex_data; - -struct tcindex_filter_result { - struct tcf_exts exts; - struct tcf_result res; - struct tcindex_data *p; - struct rcu_work rwork; -}; - -struct tcindex_filter { - u16 key; - struct tcindex_filter_result result; - struct tcindex_filter __rcu *next; - struct rcu_work rwork; -}; - - -struct tcindex_data { - struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */ - struct tcindex_filter __rcu **h; /* imperfect hash; */ - struct tcf_proto *tp; - u16 mask; /* AND key with mask */ - u32 shift; /* shift ANDed key to the right */ - u32 hash; /* hash table size; 0 if undefined */ - u32 alloc_hash; /* allocated size */ - u32 fall_through; /* 0: only classify if explicit match */ - refcount_t refcnt; /* a temporary refcnt for perfect hash */ - struct rcu_work rwork; -}; - -static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) -{ - return tcf_exts_has_actions(&r->exts) || r->res.classid; -} - -static void tcindex_data_get(struct tcindex_data *p) -{ - refcount_inc(&p->refcnt); -} - -static void tcindex_data_put(struct tcindex_data *p) -{ - if (refcount_dec_and_test(&p->refcnt)) { - kfree(p->perfect); - kfree(p->h); - kfree(p); - } -} - -static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p, - u16 key) -{ - if (p->perfect) { - struct tcindex_filter_result *f = p->perfect + key; - - return tcindex_filter_is_set(f) ? f : NULL; - } else if (p->h) { - struct tcindex_filter __rcu **fp; - struct tcindex_filter *f; - - fp = &p->h[key % p->hash]; - for (f = rcu_dereference_bh_rtnl(*fp); - f; - fp = &f->next, f = rcu_dereference_bh_rtnl(*fp)) - if (f->key == key) - return &f->result; - } - - return NULL; -} - - -static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct tcindex_data *p = rcu_dereference_bh(tp->root); - struct tcindex_filter_result *f; - int key = (skb->tc_index & p->mask) >> p->shift; - - pr_debug("tcindex_classify(skb %p,tp %p,res %p),p %p\n", - skb, tp, res, p); - - f = tcindex_lookup(p, key); - if (!f) { - struct Qdisc *q = tcf_block_q(tp->chain->block); - - if (!p->fall_through) - return -1; - res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key); - res->class = 0; - pr_debug("alg 0x%x\n", res->classid); - return 0; - } - *res = f->res; - pr_debug("map 0x%x\n", res->classid); - - return tcf_exts_exec(skb, &f->exts, res); -} - - -static void *tcindex_get(struct tcf_proto *tp, u32 handle) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r; - - pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); - if (p->perfect && handle >= p->alloc_hash) - return NULL; - r = tcindex_lookup(p, handle); - return r && tcindex_filter_is_set(r) ? r : NULL; -} - -static int tcindex_init(struct tcf_proto *tp) -{ - struct tcindex_data *p; - - pr_debug("tcindex_init(tp %p)\n", tp); - p = kzalloc(sizeof(struct tcindex_data), GFP_KERNEL); - if (!p) - return -ENOMEM; - - p->mask = 0xffff; - p->hash = DEFAULT_HASH_SIZE; - p->fall_through = 1; - refcount_set(&p->refcnt, 1); /* Paired with tcindex_destroy_work() */ - - rcu_assign_pointer(tp->root, p); - return 0; -} - -static void __tcindex_destroy_rexts(struct tcindex_filter_result *r) -{ - tcf_exts_destroy(&r->exts); - tcf_exts_put_net(&r->exts); - tcindex_data_put(r->p); -} - -static void tcindex_destroy_rexts_work(struct work_struct *work) -{ - struct tcindex_filter_result *r; - - r = container_of(to_rcu_work(work), - struct tcindex_filter_result, - rwork); - rtnl_lock(); - __tcindex_destroy_rexts(r); - rtnl_unlock(); -} - -static void __tcindex_destroy_fexts(struct tcindex_filter *f) -{ - tcf_exts_destroy(&f->result.exts); - tcf_exts_put_net(&f->result.exts); - kfree(f); -} - -static void tcindex_destroy_fexts_work(struct work_struct *work) -{ - struct tcindex_filter *f = container_of(to_rcu_work(work), - struct tcindex_filter, - rwork); - - rtnl_lock(); - __tcindex_destroy_fexts(f); - rtnl_unlock(); -} - -static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last, - bool rtnl_held, struct netlink_ext_ack *extack) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = arg; - struct tcindex_filter __rcu **walk; - struct tcindex_filter *f = NULL; - - pr_debug("tcindex_delete(tp %p,arg %p),p %p\n", tp, arg, p); - if (p->perfect) { - if (!r->res.class) - return -ENOENT; - } else { - int i; - - for (i = 0; i < p->hash; i++) { - walk = p->h + i; - for (f = rtnl_dereference(*walk); f; - walk = &f->next, f = rtnl_dereference(*walk)) { - if (&f->result == r) - goto found; - } - } - return -ENOENT; - -found: - rcu_assign_pointer(*walk, rtnl_dereference(f->next)); - } - tcf_unbind_filter(tp, &r->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (f) { - if (tcf_exts_get_net(&f->result.exts)) - tcf_queue_work(&f->rwork, tcindex_destroy_fexts_work); - else - __tcindex_destroy_fexts(f); - } else { - tcindex_data_get(p); - - if (tcf_exts_get_net(&r->exts)) - tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work); - else - __tcindex_destroy_rexts(r); - } - - *last = false; - return 0; -} - -static void tcindex_destroy_work(struct work_struct *work) -{ - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); - - tcindex_data_put(p); -} - -static inline int -valid_perfect_hash(struct tcindex_data *p) -{ - return p->hash > (p->mask >> p->shift); -} - -static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { - [TCA_TCINDEX_HASH] = { .type = NLA_U32 }, - [TCA_TCINDEX_MASK] = { .type = NLA_U16 }, - [TCA_TCINDEX_SHIFT] = { .type = NLA_U32 }, - [TCA_TCINDEX_FALL_THROUGH] = { .type = NLA_U32 }, - [TCA_TCINDEX_CLASSID] = { .type = NLA_U32 }, -}; - -static int tcindex_filter_result_init(struct tcindex_filter_result *r, - struct tcindex_data *p, - struct net *net) -{ - memset(r, 0, sizeof(*r)); - r->p = p; - return tcf_exts_init(&r->exts, net, TCA_TCINDEX_ACT, - TCA_TCINDEX_POLICE); -} - -static void tcindex_free_perfect_hash(struct tcindex_data *cp); - -static void tcindex_partial_destroy_work(struct work_struct *work) -{ - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); - - rtnl_lock(); - if (p->perfect) - tcindex_free_perfect_hash(p); - kfree(p); - rtnl_unlock(); -} - -static void tcindex_free_perfect_hash(struct tcindex_data *cp) -{ - int i; - - for (i = 0; i < cp->hash; i++) - tcf_exts_destroy(&cp->perfect[i].exts); - kfree(cp->perfect); -} - -static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) -{ - int i, err = 0; - - cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result), - GFP_KERNEL | __GFP_NOWARN); - if (!cp->perfect) - return -ENOMEM; - - for (i = 0; i < cp->hash; i++) { - err = tcf_exts_init(&cp->perfect[i].exts, net, - TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - goto errout; - cp->perfect[i].p = cp; - } - - return 0; - -errout: - tcindex_free_perfect_hash(cp); - return err; -} - -static int -tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, - u32 handle, struct tcindex_data *p, - struct tcindex_filter_result *r, struct nlattr **tb, - struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) -{ - struct tcindex_filter_result new_filter_result; - struct tcindex_data *cp = NULL, *oldp; - struct tcindex_filter *f = NULL; /* make gcc behave */ - struct tcf_result cr = {}; - int err, balloc = 0; - struct tcf_exts e; - bool update_h = false; - - err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr, true, extack); - if (err < 0) - goto errout; - - err = -ENOMEM; - /* tcindex_data attributes must look atomic to classifier/lookup so - * allocate new tcindex data and RCU assign it onto root. Keeping - * perfect hash and hash pointers from old data. - */ - cp = kzalloc(sizeof(*cp), GFP_KERNEL); - if (!cp) - goto errout; - - cp->mask = p->mask; - cp->shift = p->shift; - cp->hash = p->hash; - cp->alloc_hash = p->alloc_hash; - cp->fall_through = p->fall_through; - cp->tp = tp; - refcount_set(&cp->refcnt, 1); /* Paired with tcindex_destroy_work() */ - - if (tb[TCA_TCINDEX_HASH]) - cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); - - if (tb[TCA_TCINDEX_MASK]) - cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); - - if (tb[TCA_TCINDEX_SHIFT]) { - cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); - if (cp->shift > 16) { - err = -EINVAL; - goto errout; - } - } - if (!cp->hash) { - /* Hash not specified, use perfect hash if the upper limit - * of the hashing index is below the threshold. - */ - if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) - cp->hash = (cp->mask >> cp->shift) + 1; - else - cp->hash = DEFAULT_HASH_SIZE; - } - - if (p->perfect) { - int i; - - if (tcindex_alloc_perfect_hash(net, cp) < 0) - goto errout; - cp->alloc_hash = cp->hash; - for (i = 0; i < min(cp->hash, p->hash); i++) - cp->perfect[i].res = p->perfect[i].res; - balloc = 1; - } - cp->h = p->h; - - err = tcindex_filter_result_init(&new_filter_result, cp, net); - if (err < 0) - goto errout_alloc; - if (r) - cr = r->res; - - err = -EBUSY; - - /* Hash already allocated, make sure that we still meet the - * requirements for the allocated hash. - */ - if (cp->perfect) { - if (!valid_perfect_hash(cp) || - cp->hash > cp->alloc_hash) - goto errout_alloc; - } else if (cp->h && cp->hash != cp->alloc_hash) { - goto errout_alloc; - } - - err = -EINVAL; - if (tb[TCA_TCINDEX_FALL_THROUGH]) - cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]); - - if (!cp->perfect && !cp->h) - cp->alloc_hash = cp->hash; - - /* Note: this could be as restrictive as if (handle & ~(mask >> shift)) - * but then, we'd fail handles that may become valid after some future - * mask change. While this is extremely unlikely to ever matter, - * the check below is safer (and also more backwards-compatible). - */ - if (cp->perfect || valid_perfect_hash(cp)) - if (handle >= cp->alloc_hash) - goto errout_alloc; - - - err = -ENOMEM; - if (!cp->perfect && !cp->h) { - if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(net, cp) < 0) - goto errout_alloc; - balloc = 1; - } else { - struct tcindex_filter __rcu **hash; - - hash = kcalloc(cp->hash, - sizeof(struct tcindex_filter *), - GFP_KERNEL); - - if (!hash) - goto errout_alloc; - - cp->h = hash; - balloc = 2; - } - } - - if (cp->perfect) { - r = cp->perfect + handle; - } else { - /* imperfect area is updated in-place using rcu */ - update_h = !!tcindex_lookup(cp, handle); - r = &new_filter_result; - } - - if (r == &new_filter_result) { - f = kzalloc(sizeof(*f), GFP_KERNEL); - if (!f) - goto errout_alloc; - f->key = handle; - f->next = NULL; - err = tcindex_filter_result_init(&f->result, cp, net); - if (err < 0) { - kfree(f); - goto errout_alloc; - } - } - - if (tb[TCA_TCINDEX_CLASSID]) { - cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr, base); - } - - oldp = p; - r->res = cr; - tcf_exts_change(&r->exts, &e); - - rcu_assign_pointer(tp->root, cp); - - if (update_h) { - struct tcindex_filter __rcu **fp; - struct tcindex_filter *cf; - - f->result.res = r->res; - tcf_exts_change(&f->result.exts, &r->exts); - - /* imperfect area bucket */ - fp = cp->h + (handle % cp->hash); - - /* lookup the filter, guaranteed to exist */ - for (cf = rcu_dereference_bh_rtnl(*fp); cf; - fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp)) - if (cf->key == (u16)handle) - break; - - f->next = cf->next; - - cf = rcu_replace_pointer(*fp, f, 1); - tcf_exts_get_net(&cf->result.exts); - tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work); - } else if (r == &new_filter_result) { - struct tcindex_filter *nfp; - struct tcindex_filter __rcu **fp; - - f->result.res = r->res; - tcf_exts_change(&f->result.exts, &r->exts); - - fp = cp->h + (handle % cp->hash); - for (nfp = rtnl_dereference(*fp); - nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) - ; /* nothing */ - - rcu_assign_pointer(*fp, f); - } else { - tcf_exts_destroy(&new_filter_result.exts); - } - - if (oldp) - tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work); - return 0; - -errout_alloc: - if (balloc == 1) - tcindex_free_perfect_hash(cp); - else if (balloc == 2) - kfree(cp->h); - tcf_exts_destroy(&new_filter_result.exts); -errout: - kfree(cp); - tcf_exts_destroy(&e); - return err; -} - -static int -tcindex_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, - bool rtnl_held, struct netlink_ext_ack *extack) -{ - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_TCINDEX_MAX + 1]; - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = *arg; - int err; - - pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p," - "p %p,r %p,*arg %p\n", - tp, handle, tca, arg, opt, p, r, *arg); - - if (!opt) - return 0; - - err = nla_parse_nested_deprecated(tb, TCA_TCINDEX_MAX, opt, - tcindex_policy, NULL); - if (err < 0) - return err; - - return tcindex_set_parms(net, tp, base, handle, p, r, tb, - tca[TCA_RATE], ovr, extack); -} - -static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker, - bool rtnl_held) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter *f, *next; - int i; - - pr_debug("tcindex_walk(tp %p,walker %p),p %p\n", tp, walker, p); - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - if (!p->perfect[i].res.class) - continue; - if (walker->count >= walker->skip) { - if (walker->fn(tp, p->perfect + i, walker) < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } - if (!p->h) - return; - for (i = 0; i < p->hash; i++) { - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - if (walker->count >= walker->skip) { - if (walker->fn(tp, &f->result, walker) < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } -} - -static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - int i; - - pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); - - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - struct tcindex_filter_result *r = p->perfect + i; - - /* tcf_queue_work() does not guarantee the ordering we - * want, so we have to take this refcnt temporarily to - * ensure 'p' is freed after all tcindex_filter_result - * here. Imperfect hash does not need this, because it - * uses linked lists rather than an array. - */ - tcindex_data_get(p); - - tcf_unbind_filter(tp, &r->res); - if (tcf_exts_get_net(&r->exts)) - tcf_queue_work(&r->rwork, - tcindex_destroy_rexts_work); - else - __tcindex_destroy_rexts(r); - } - } - - for (i = 0; p->h && i < p->hash; i++) { - struct tcindex_filter *f, *next; - bool last; - - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - tcindex_delete(tp, &f->result, &last, rtnl_held, NULL); - } - } - - tcf_queue_work(&p->rwork, tcindex_destroy_work); -} - - -static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = fh; - struct nlattr *nest; - - pr_debug("tcindex_dump(tp %p,fh %p,skb %p,t %p),p %p,r %p\n", - tp, fh, skb, t, p, r); - pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h); - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (!fh) { - t->tcm_handle = ~0; /* whatever ... */ - if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) || - nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) || - nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) || - nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through)) - goto nla_put_failure; - nla_nest_end(skb, nest); - } else { - if (p->perfect) { - t->tcm_handle = r - p->perfect; - } else { - struct tcindex_filter *f; - struct tcindex_filter __rcu **fp; - int i; - - t->tcm_handle = 0; - for (i = 0; !t->tcm_handle && i < p->hash; i++) { - fp = &p->h[i]; - for (f = rtnl_dereference(*fp); - !t->tcm_handle && f; - fp = &f->next, f = rtnl_dereference(*fp)) { - if (&f->result == r) - t->tcm_handle = f->key; - } - } - } - pr_debug("handle = %d\n", t->tcm_handle); - if (r->res.class && - nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &r->exts) < 0) - goto nla_put_failure; - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &r->exts) < 0) - goto nla_put_failure; - } - - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl, - void *q, unsigned long base) -{ - struct tcindex_filter_result *r = fh; - - if (r && r->res.classid == classid) { - if (cl) - __tcf_bind_filter(q, &r->res, base); - else - __tcf_unbind_filter(q, &r->res); - } -} - -static struct tcf_proto_ops cls_tcindex_ops __read_mostly = { - .kind = "tcindex", - .classify = tcindex_classify, - .init = tcindex_init, - .destroy = tcindex_destroy, - .get = tcindex_get, - .change = tcindex_change, - .delete = tcindex_delete, - .walk = tcindex_walk, - .dump = tcindex_dump, - .bind_class = tcindex_bind_class, - .owner = THIS_MODULE, -}; - -static int __init init_tcindex(void) -{ - return register_tcf_proto_ops(&cls_tcindex_ops); -} - -static void __exit exit_tcindex(void) -{ - unregister_tcf_proto_ops(&cls_tcindex_ops); -} - -module_init(init_tcindex) -module_exit(exit_tcindex) -MODULE_LICENSE("GPL"); From 5d03a19ac7e81f80d96c3bfeb719da38257f75e5 Mon Sep 17 00:00:00 2001 From: Liu Shixin via Jfs-discussion Date: Thu, 3 Nov 2022 11:01:59 +0800 Subject: [PATCH 1931/4345] fs/jfs: fix shift exponent db_agl2size negative [ Upstream commit fad376fce0af58deebc5075b8539dc05bf639af3 ] As a shift exponent, db_agl2size can not be less than 0. Add the missing check to fix the shift-out-of-bounds bug reported by syzkaller: UBSAN: shift-out-of-bounds in fs/jfs/jfs_dmap.c:2227:15 shift exponent -744642816 is negative Reported-by: syzbot+0be96567042453c0c820@syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Liu Shixin Signed-off-by: Dave Kleikamp Signed-off-by: Sasha Levin --- fs/jfs/jfs_dmap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 2c9493011aec..501263355ef4 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -193,7 +193,8 @@ int dbMount(struct inode *ipbmap) bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth); bmp->db_agstart = le32_to_cpu(dbmp_le->dn_agstart); bmp->db_agl2size = le32_to_cpu(dbmp_le->dn_agl2size); - if (bmp->db_agl2size > L2MAXL2SIZE - L2MAXAG) { + if (bmp->db_agl2size > L2MAXL2SIZE - L2MAXAG || + bmp->db_agl2size < 0) { err = -EINVAL; goto err_release_metapage; } From a1368eaea058e451d20ea99ca27e72d9df0d16dd Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 5 Dec 2022 12:06:42 +0400 Subject: [PATCH 1932/4345] objtool: Fix memory leak in create_static_call_sections() [ Upstream commit 3da73f102309fe29150e5c35acd20dd82063ff67 ] strdup() allocates memory for key_name. We need to release the memory in the following error paths. Add free() to avoid memory leak. Fixes: 1e7e47883830 ("x86/static_call: Add inline static call implementation for x86-64") Signed-off-by: Miaoqian Lin Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20221205080642.558583-1-linmq006@gmail.com Cc: Josh Poimboeuf Cc: Peter Zijlstra Signed-off-by: Sasha Levin --- tools/objtool/check.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5c4190382a51..9a0a54194636 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -572,6 +572,7 @@ static int create_static_call_sections(struct objtool_file *file) if (strncmp(key_name, STATIC_CALL_TRAMP_PREFIX_STR, STATIC_CALL_TRAMP_PREFIX_LEN)) { WARN("static_call: trampoline name malformed: %s", key_name); + free(key_name); return -1; } tmp = key_name + STATIC_CALL_TRAMP_PREFIX_LEN - STATIC_CALL_KEY_PREFIX_LEN; @@ -581,6 +582,7 @@ static int create_static_call_sections(struct objtool_file *file) if (!key_sym) { if (!module) { WARN("static_call: can't find static_call_key symbol: %s", tmp); + free(key_name); return -1; } From 8b98e7a45e6382b75cacf7932bcdb27482a56e49 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 21 Jul 2022 12:31:25 +0200 Subject: [PATCH 1933/4345] pwm: sifive: Reduce time the controller lock is held MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0f02f491b786143f08eb19840f1cf4f12aec6dee ] The lock is only to serialize access and update to user_count and approx_period between different PWMs served by the same pwm_chip. So the lock needs only to be taken during the check if the (chip global) period can and/or needs to be changed. Signed-off-by: Uwe Kleine-König Tested-by: Emil Renner Berthing Signed-off-by: Thierry Reding Stable-dep-of: 334c7b13d383 ("pwm: sifive: Always let the first pwm_apply_state succeed") Signed-off-by: Sasha Levin --- drivers/pwm/pwm-sifive.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/pwm/pwm-sifive.c b/drivers/pwm/pwm-sifive.c index 12e9e23272ab..400cc91057ac 100644 --- a/drivers/pwm/pwm-sifive.c +++ b/drivers/pwm/pwm-sifive.c @@ -41,7 +41,7 @@ struct pwm_sifive_ddata { struct pwm_chip chip; - struct mutex lock; /* lock to protect user_count */ + struct mutex lock; /* lock to protect user_count and approx_period */ struct notifier_block notifier; struct clk *clk; void __iomem *regs; @@ -76,6 +76,7 @@ static void pwm_sifive_free(struct pwm_chip *chip, struct pwm_device *pwm) mutex_unlock(&ddata->lock); } +/* Called holding ddata->lock */ static void pwm_sifive_update_clock(struct pwm_sifive_ddata *ddata, unsigned long rate) { @@ -163,7 +164,6 @@ static int pwm_sifive_apply(struct pwm_chip *chip, struct pwm_device *pwm, return ret; } - mutex_lock(&ddata->lock); cur_state = pwm->state; enabled = cur_state.enabled; @@ -182,14 +182,17 @@ static int pwm_sifive_apply(struct pwm_chip *chip, struct pwm_device *pwm, /* The hardware cannot generate a 100% duty cycle */ frac = min(frac, (1U << PWM_SIFIVE_CMPWIDTH) - 1); + mutex_lock(&ddata->lock); if (state->period != ddata->approx_period) { if (ddata->user_count != 1) { + mutex_unlock(&ddata->lock); ret = -EBUSY; goto exit; } ddata->approx_period = state->period; pwm_sifive_update_clock(ddata, clk_get_rate(ddata->clk)); } + mutex_unlock(&ddata->lock); writel(frac, ddata->regs + PWM_SIFIVE_PWMCMP(pwm->hwpwm)); @@ -198,7 +201,6 @@ static int pwm_sifive_apply(struct pwm_chip *chip, struct pwm_device *pwm, exit: clk_disable(ddata->clk); - mutex_unlock(&ddata->lock); return ret; } From c2677c49b766b365578ef7a0641bf0c857545d7b Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Wed, 9 Nov 2022 12:37:24 +0100 Subject: [PATCH 1934/4345] pwm: sifive: Always let the first pwm_apply_state succeed [ Upstream commit 334c7b13d38321e47d1a51dba0bef9f4c403ec75 ] Commit 2cfe9bbec56ea579135cdd92409fff371841904f added support for the RGB and green PWM controlled LEDs on the HiFive Unmatched board managed by the leds-pwm-multicolor and leds-pwm drivers respectively. All three colours of the RGB LED and the green LED run from different lines of the same PWM, but with the same period so this works fine when the LED drivers are loaded one after the other. Unfortunately it does expose a race in the PWM driver when both LED drivers are loaded at roughly the same time. Here is an example: | Thread A | Thread B | | led_pwm_mc_probe | led_pwm_probe | | devm_fwnode_pwm_get | | | pwm_sifive_request | | | ddata->user_count++ | | | | devm_fwnode_pwm_get | | | pwm_sifive_request | | | ddata->user_count++ | | ... | ... | | pwm_state_apply | pwm_state_apply | | pwm_sifive_apply | pwm_sifive_apply | Now both calls to pwm_sifive_apply will see that ddata->approx_period, initially 0, is different from the requested period and the clock needs to be updated. But since ddata->user_count >= 2 both calls will fail with -EBUSY, which will then cause both LED drivers to fail to probe. Fix it by letting the first call to pwm_sifive_apply update the clock even when ddata->user_count != 1. Fixes: 9e37a53eb051 ("pwm: sifive: Add a driver for SiFive SoC PWM") Signed-off-by: Emil Renner Berthing Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-sifive.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-sifive.c b/drivers/pwm/pwm-sifive.c index 400cc91057ac..52a55bae033d 100644 --- a/drivers/pwm/pwm-sifive.c +++ b/drivers/pwm/pwm-sifive.c @@ -184,7 +184,13 @@ static int pwm_sifive_apply(struct pwm_chip *chip, struct pwm_device *pwm, mutex_lock(&ddata->lock); if (state->period != ddata->approx_period) { - if (ddata->user_count != 1) { + /* + * Don't let a 2nd user change the period underneath the 1st user. + * However if ddate->approx_period == 0 this is the first time we set + * any period, so let whoever gets here first set the period so other + * users who agree on the period won't fail. + */ + if (ddata->user_count != 1 && ddata->approx_period) { mutex_unlock(&ddata->lock); ret = -EBUSY; goto exit; From 9d4a4a9ee95e054ad2384421f91acd823ceee021 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Wed, 23 Nov 2022 14:36:52 +0100 Subject: [PATCH 1935/4345] pwm: stm32-lp: fix the check on arr and cmp registers update MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3066bc2d58be31275afb51a589668f265e419c37 ] The ARR (auto reload register) and CMP (compare) registers are successively written. The status bits to check the update of these registers are polled together with regmap_read_poll_timeout(). The condition to end the loop may become true, even if one of the register isn't correctly updated. So ensure both status bits are set before clearing them. Fixes: e70a540b4e02 ("pwm: Add STM32 LPTimer PWM driver") Signed-off-by: Fabrice Gasnier Acked-by: Uwe Kleine-König Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-stm32-lp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c index 945a8b2b8564..c8a847fcb775 100644 --- a/drivers/pwm/pwm-stm32-lp.c +++ b/drivers/pwm/pwm-stm32-lp.c @@ -127,7 +127,7 @@ static int stm32_pwm_lp_apply(struct pwm_chip *chip, struct pwm_device *pwm, /* ensure CMP & ARR registers are properly written */ ret = regmap_read_poll_timeout(priv->regmap, STM32_LPTIM_ISR, val, - (val & STM32_LPTIM_CMPOK_ARROK), + (val & STM32_LPTIM_CMPOK_ARROK) == STM32_LPTIM_CMPOK_ARROK, 100, 1000); if (ret) { dev_err(priv->chip.dev, "ARR/CMP registers write issue\n"); From 33909b1a646d1f31d631ff4a77a7303317e4a82b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 19 Aug 2022 15:33:00 -0700 Subject: [PATCH 1936/4345] f2fs: use memcpy_{to,from}_page() where possible [ Upstream commit b87846bd61c7c09560617da416208a5454530d57 ] This is simpler, and as a side effect it replaces several uses of kmap_atomic() with its recommended replacement kmap_local_page(). Signed-off-by: Eric Biggers Reviewed-by: Fabio M. De Francesco Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Stable-dep-of: b1b9896718bc ("fs: f2fs: initialize fsdata in pagecache_write()") Signed-off-by: Sasha Levin --- fs/f2fs/inline.c | 15 ++++----------- fs/f2fs/super.c | 11 ++--------- fs/f2fs/verity.c | 10 ++-------- 3 files changed, 8 insertions(+), 28 deletions(-) diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 4e794c1390cc..df1a0cbfa1be 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -64,7 +64,6 @@ bool f2fs_may_inline_dentry(struct inode *inode) void f2fs_do_read_inline_data(struct page *page, struct page *ipage) { struct inode *inode = page->mapping->host; - void *src_addr, *dst_addr; if (PageUptodate(page)) return; @@ -74,11 +73,8 @@ void f2fs_do_read_inline_data(struct page *page, struct page *ipage) zero_user_segment(page, MAX_INLINE_DATA(inode), PAGE_SIZE); /* Copy the whole inline data block */ - src_addr = inline_data_addr(inode, ipage); - dst_addr = kmap_atomic(page); - memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode)); - flush_dcache_page(page); - kunmap_atomic(dst_addr); + memcpy_to_page(page, 0, inline_data_addr(inode, ipage), + MAX_INLINE_DATA(inode)); if (!PageUptodate(page)) SetPageUptodate(page); } @@ -245,7 +241,6 @@ out: int f2fs_write_inline_data(struct inode *inode, struct page *page) { - void *src_addr, *dst_addr; struct dnode_of_data dn; int err; @@ -262,10 +257,8 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) f2fs_bug_on(F2FS_I_SB(inode), page->index); f2fs_wait_on_page_writeback(dn.inode_page, NODE, true, true); - src_addr = kmap_atomic(page); - dst_addr = inline_data_addr(inode, dn.inode_page); - memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode)); - kunmap_atomic(src_addr); + memcpy_from_page(inline_data_addr(inode, dn.inode_page), + page, 0, MAX_INLINE_DATA(inode)); set_page_dirty(dn.inode_page); f2fs_clear_page_cache_dirty_tag(page); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index fba413ced982..0bba5c72fc77 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2034,7 +2034,6 @@ static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data, size_t toread; loff_t i_size = i_size_read(inode); struct page *page; - char *kaddr; if (off > i_size) return 0; @@ -2068,9 +2067,7 @@ repeat: return -EIO; } - kaddr = kmap_atomic(page); - memcpy(data, kaddr + offset, tocopy); - kunmap_atomic(kaddr); + memcpy_from_page(data, page, offset, tocopy); f2fs_put_page(page, 1); offset = 0; @@ -2092,7 +2089,6 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, size_t towrite = len; struct page *page; void *fsdata = NULL; - char *kaddr; int err = 0; int tocopy; @@ -2112,10 +2108,7 @@ retry: break; } - kaddr = kmap_atomic(page); - memcpy(kaddr + offset, data, tocopy); - kunmap_atomic(kaddr); - flush_dcache_page(page); + memcpy_to_page(page, offset, data, tocopy); a_ops->write_end(NULL, mapping, off, tocopy, tocopy, page, fsdata); diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index cff94d095d0f..dafdb19ec0db 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -47,16 +47,13 @@ static int pagecache_read(struct inode *inode, void *buf, size_t count, size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); struct page *page; - void *addr; page = read_mapping_page(inode->i_mapping, pos >> PAGE_SHIFT, NULL); if (IS_ERR(page)) return PTR_ERR(page); - addr = kmap_atomic(page); - memcpy(buf, addr + offset_in_page(pos), n); - kunmap_atomic(addr); + memcpy_from_page(buf, page, offset_in_page(pos), n); put_page(page); @@ -82,7 +79,6 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, PAGE_SIZE - offset_in_page(pos)); struct page *page; void *fsdata; - void *addr; int res; res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0, @@ -90,9 +86,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, if (res) return res; - addr = kmap_atomic(page); - memcpy(addr + offset_in_page(pos), buf, n); - kunmap_atomic(addr); + memcpy_to_page(page, offset_in_page(pos), buf, n); res = pagecache_write_end(NULL, inode->i_mapping, pos, n, n, page, fsdata); From 6be349d7388f3af7957dc6c7e241dc92a969fb38 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Mon, 21 Nov 2022 12:21:32 +0100 Subject: [PATCH 1937/4345] fs: f2fs: initialize fsdata in pagecache_write() [ Upstream commit b1b9896718bc1a212dc288ad66a5fa2fef11353d ] When aops->write_begin() does not initialize fsdata, KMSAN may report an error passing the latter to aops->write_end(). Fix this by unconditionally initializing fsdata. Suggested-by: Eric Biggers Fixes: 95ae251fe828 ("f2fs: add fs-verity support") Signed-off-by: Alexander Potapenko Reviewed-by: Eric Biggers Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/verity.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index dafdb19ec0db..cef40d92268f 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -78,7 +78,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); struct page *page; - void *fsdata; + void *fsdata = NULL; int res; res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0, From f2b9c4544e3bd60f353732291300097b0e8d8454 Mon Sep 17 00:00:00 2001 From: Xiang Yang Date: Tue, 15 Nov 2022 15:32:25 +0800 Subject: [PATCH 1938/4345] um: vector: Fix memory leak in vector_config [ Upstream commit 8f88c73afe481f93d40801596927e8c0047b6d96 ] If the return value of the uml_parse_vector_ifspec function is NULL, we should call kfree(params) to prevent memory leak. Fixes: 49da7e64f33e ("High Performance UML Vector Network Driver") Signed-off-by: Xiang Yang Acked-By: Anton Ivanov Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- arch/um/drivers/vector_kern.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 555203e3e7b4..fc662f7cc2af 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -771,6 +771,7 @@ static int vector_config(char *str, char **error_out) if (parsed == NULL) { *error_out = "vector_config failed to parse parameters"; + kfree(params); return -EINVAL; } From 846bfba34175c23b13cc2023c2d67b96e8c14c43 Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Tue, 15 Nov 2022 10:14:44 -0500 Subject: [PATCH 1939/4345] ubi: ensure that VID header offset + VID header size <= alloc, size [ Upstream commit 1b42b1a36fc946f0d7088425b90d491b4257ca3e ] Ensure that the VID header offset + VID header size does not exceed the allocated area to avoid slab OOB. BUG: KASAN: slab-out-of-bounds in crc32_body lib/crc32.c:111 [inline] BUG: KASAN: slab-out-of-bounds in crc32_le_generic lib/crc32.c:179 [inline] BUG: KASAN: slab-out-of-bounds in crc32_le_base+0x58c/0x626 lib/crc32.c:197 Read of size 4 at addr ffff88802bb36f00 by task syz-executor136/1555 CPU: 2 PID: 1555 Comm: syz-executor136 Tainted: G W 6.0.0-1868 #1 Hardware name: Red Hat KVM, BIOS 1.13.0-2.module+el8.3.0+7860+a7792d29 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x85/0xad lib/dump_stack.c:106 print_address_description mm/kasan/report.c:317 [inline] print_report.cold.13+0xb6/0x6bb mm/kasan/report.c:433 kasan_report+0xa7/0x11b mm/kasan/report.c:495 crc32_body lib/crc32.c:111 [inline] crc32_le_generic lib/crc32.c:179 [inline] crc32_le_base+0x58c/0x626 lib/crc32.c:197 ubi_io_write_vid_hdr+0x1b7/0x472 drivers/mtd/ubi/io.c:1067 create_vtbl+0x4d5/0x9c4 drivers/mtd/ubi/vtbl.c:317 create_empty_lvol drivers/mtd/ubi/vtbl.c:500 [inline] ubi_read_volume_table+0x67b/0x288a drivers/mtd/ubi/vtbl.c:812 ubi_attach+0xf34/0x1603 drivers/mtd/ubi/attach.c:1601 ubi_attach_mtd_dev+0x6f3/0x185e drivers/mtd/ubi/build.c:965 ctrl_cdev_ioctl+0x2db/0x347 drivers/mtd/ubi/cdev.c:1043 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x193/0x213 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3e/0x86 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0x0 RIP: 0033:0x7f96d5cf753d Code: RSP: 002b:00007fffd72206f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f96d5cf753d RDX: 0000000020000080 RSI: 0000000040186f40 RDI: 0000000000000003 RBP: 0000000000400cd0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000400be0 R13: 00007fffd72207e0 R14: 0000000000000000 R15: 0000000000000000 Allocated by task 1555: kasan_save_stack+0x20/0x3d mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:45 [inline] set_alloc_info mm/kasan/common.c:437 [inline] ____kasan_kmalloc mm/kasan/common.c:516 [inline] __kasan_kmalloc+0x88/0xa3 mm/kasan/common.c:525 kasan_kmalloc include/linux/kasan.h:234 [inline] __kmalloc+0x138/0x257 mm/slub.c:4429 kmalloc include/linux/slab.h:605 [inline] ubi_alloc_vid_buf drivers/mtd/ubi/ubi.h:1093 [inline] create_vtbl+0xcc/0x9c4 drivers/mtd/ubi/vtbl.c:295 create_empty_lvol drivers/mtd/ubi/vtbl.c:500 [inline] ubi_read_volume_table+0x67b/0x288a drivers/mtd/ubi/vtbl.c:812 ubi_attach+0xf34/0x1603 drivers/mtd/ubi/attach.c:1601 ubi_attach_mtd_dev+0x6f3/0x185e drivers/mtd/ubi/build.c:965 ctrl_cdev_ioctl+0x2db/0x347 drivers/mtd/ubi/cdev.c:1043 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x193/0x213 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3e/0x86 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0x0 The buggy address belongs to the object at ffff88802bb36e00 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 0 bytes to the right of 256-byte region [ffff88802bb36e00, ffff88802bb36f00) The buggy address belongs to the physical page: page:00000000ea4d1263 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x2bb36 head:00000000ea4d1263 order:1 compound_mapcount:0 compound_pincount:0 flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0010200 ffffea000066c300 dead000000000003 ffff888100042b40 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88802bb36e00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff88802bb36e80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff88802bb36f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff88802bb36f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88802bb37000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Fixes: 801c135ce73d ("UBI: Unsorted Block Images") Reported-by: syzkaller Signed-off-by: George Kennedy Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- drivers/mtd/ubi/build.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 4153e0d15c5f..8747569e793d 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -664,6 +664,12 @@ static int io_init(struct ubi_device *ubi, int max_beb_per1024) ubi->ec_hdr_alsize = ALIGN(UBI_EC_HDR_SIZE, ubi->hdrs_min_io_size); ubi->vid_hdr_alsize = ALIGN(UBI_VID_HDR_SIZE, ubi->hdrs_min_io_size); + if (ubi->vid_hdr_offset && ((ubi->vid_hdr_offset + UBI_VID_HDR_SIZE) > + ubi->vid_hdr_alsize)) { + ubi_err(ubi, "VID header offset %d too large.", ubi->vid_hdr_offset); + return -EINVAL; + } + dbg_gen("min_io_size %d", ubi->min_io_size); dbg_gen("max_write_size %d", ubi->max_write_size); dbg_gen("hdrs_min_io_size %d", ubi->hdrs_min_io_size); From 93e748ba517426912cfec83439fb64e2703083f1 Mon Sep 17 00:00:00 2001 From: Li Hua Date: Mon, 21 Nov 2022 19:18:47 +0800 Subject: [PATCH 1940/4345] ubifs: Fix build errors as symbol undefined [ Upstream commit aa6d148e6d6270274e3d5a529b71c54cd329d17f ] With CONFIG_UBIFS_FS_AUTHENTICATION not set, the compiler can assume that ubifs_node_check_hash() is never true and drops the call to ubifs_bad_hash(). Is CONFIG_CC_OPTIMIZE_FOR_SIZE enabled this optimization does not happen anymore. So When CONFIG_UBIFS_FS and CONFIG_CC_OPTIMIZE_FOR_SIZE is enabled but CONFIG_UBIFS_FS_AUTHENTICATION is not set, the build errors is as followd: ERROR: modpost: "ubifs_bad_hash" [fs/ubifs/ubifs.ko] undefined! Fix it by add no-op ubifs_bad_hash() for the CONFIG_UBIFS_FS_AUTHENTICATION=n case. Fixes: 16a26b20d2af ("ubifs: authentication: Add hashes to index nodes") Signed-off-by: Li Hua Reviewed-by: Sascha Hauer Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/ubifs.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index e7e48f3b179a..b66ebab5c5de 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1594,8 +1594,13 @@ static inline int ubifs_check_hmac(const struct ubifs_info *c, return crypto_memneq(expected, got, c->hmac_desc_len); } +#ifdef CONFIG_UBIFS_FS_AUTHENTICATION void ubifs_bad_hash(const struct ubifs_info *c, const void *node, const u8 *hash, int lnum, int offs); +#else +static inline void ubifs_bad_hash(const struct ubifs_info *c, const void *node, + const u8 *hash, int lnum, int offs) {}; +#endif int __ubifs_node_check_hash(const struct ubifs_info *c, const void *buf, const u8 *expected); From ffebd804c7ab22175fa14b74599c00e161dc1bfd Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 11 Oct 2022 11:47:27 +0800 Subject: [PATCH 1941/4345] ubifs: Rectify space budget for ubifs_symlink() if symlink is encrypted [ Upstream commit c2c36cc6ca23e614f9e4238d0ecf48549ee9002a ] Fix bad space budget when symlink file is encrypted. Bad space budget may let make_reservation() return with -ENOSPC, which could turn ubifs to read-only mode in do_writepage() process. Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216490 Fixes: ca7f85be8d6cf9 ("ubifs: Add support for encrypted symlinks") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 9257ee893bdb..7dceca1be9b5 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1117,7 +1117,6 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, int err, sz_change, len = strlen(symname); struct fscrypt_str disk_link; struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, - .new_ino_d = ALIGN(len, 8), .dirtied_ino = 1 }; struct fscrypt_name nm; @@ -1133,6 +1132,7 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, * Budget request settings: new inode, new direntry and changing parent * directory inode. */ + req.new_ino_d = ALIGN(disk_link.len - 1, 8); err = ubifs_budget_space(c, &req); if (err) return err; From 9e07ee28c20d1507d9c4b649932561fe583930eb Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 11 Oct 2022 11:47:28 +0800 Subject: [PATCH 1942/4345] ubifs: Rectify space budget for ubifs_xrename() [ Upstream commit 1b2ba09060e41adb356b9ae58ef94a7390928004 ] There is no space budget for ubifs_xrename(). It may let make_reservation() return with -ENOSPC, which could turn ubifs to read-only mode in do_writepage() process. Fix it by adding space budget for ubifs_xrename(). Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216569 Fixes: 9ec64962afb170 ("ubifs: Implement RENAME_EXCHANGE") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/dir.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 7dceca1be9b5..15b5664fd5c9 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1530,6 +1530,10 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, return err; } + err = ubifs_budget_space(c, &req); + if (err) + goto out; + lock_4_inodes(old_dir, new_dir, NULL, NULL); time = current_time(old_dir); @@ -1555,6 +1559,7 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, unlock_4_inodes(old_dir, new_dir, NULL, NULL); ubifs_release_budget(c, &req); +out: fscrypt_free_filename(&fst_nm); fscrypt_free_filename(&snd_nm); return err; From 495ea59a24a391bd0401c6442982ee29dca0a7e6 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 11 Oct 2022 11:47:30 +0800 Subject: [PATCH 1943/4345] ubifs: Fix wrong dirty space budget for dirty inode [ Upstream commit b248eaf049d9cdc5eb76b59399e4d3de233f02ac ] Each dirty inode should reserve 'c->bi.inode_budget' bytes in space budget calculation. Currently, space budget for dirty inode reports more space than what UBIFS actually needs to write. Fixes: 1e51764a3c2ac0 ("UBIFS: add new flash file system") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/budget.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index c0b84e960b20..bdb79be6dc0e 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -403,7 +403,7 @@ static int calc_dd_growth(const struct ubifs_info *c, dd_growth = req->dirtied_page ? c->bi.page_budget : 0; if (req->dirtied_ino) - dd_growth += c->bi.inode_budget << (req->dirtied_ino - 1); + dd_growth += c->bi.inode_budget * req->dirtied_ino; if (req->mod_dent) dd_growth += c->bi.dent_budget; dd_growth += req->dirtied_ino_d; From 38a097dce1842ffca3ce007496c8e992215a120b Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 11 Oct 2022 11:47:31 +0800 Subject: [PATCH 1944/4345] ubifs: do_rename: Fix wrong space budget when target inode's nlink > 1 [ Upstream commit 25fce616a61fc2f1821e4a9ce212d0e064707093 ] If target inode is a special file (eg. block/char device) with nlink count greater than 1, the inode with ui->data will be re-written on disk. However, UBIFS losts target inode's data_len while doing space budget. Bad space budget may let make_reservation() return with -ENOSPC, which could turn ubifs to read-only mode in do_writepage() process. Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216494 Fixes: 1e51764a3c2ac0 ("UBIFS: add new flash file system") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/dir.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 15b5664fd5c9..6039943877e1 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1288,6 +1288,8 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlink) { ubifs_assert(c, inode_is_locked(new_inode)); + /* Budget for old inode's data when its nlink > 1. */ + req.dirtied_ino_d = ALIGN(ubifs_inode(new_inode)->data_len, 8); err = ubifs_purge_xattrs(new_inode); if (err) return err; From 38fd7acdc1d2c650e8d8ef4343fc306103ca75d9 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 11 Oct 2022 11:47:32 +0800 Subject: [PATCH 1945/4345] ubifs: Reserve one leb for each journal head while doing budget [ Upstream commit e874dcde1cbf82c786c0e7f2899811c02630cc52 ] UBIFS calculates available space by c->main_bytes - c->lst.total_used (which means non-index lebs' free and dirty space is accounted into total available), then index lebs and four lebs (one for gc_lnum, one for deletions, two for journal heads) are deducted. In following situation, ubifs may get -ENOSPC from make_reservation(): LEB 84: DATAHD free 122880 used 1920 dirty 2176 dark 6144 LEB 110:DELETION free 126976 used 0 dirty 0 dark 6144 (empty) LEB 201:gc_lnum free 126976 used 0 dirty 0 dark 6144 LEB 272:GCHD free 77824 used 47672 dirty 1480 dark 6144 LEB 356:BASEHD free 0 used 39776 dirty 87200 dark 6144 OTHERS: index lebs, zero-available non-index lebs UBIFS calculates the available bytes is 6888 (How to calculate it: 126976 * 5[remain main bytes] - 1920[used] - 47672[used] - 39776[used] - 126976 * 1[deletions] - 126976 * 1[gc_lnum] - 126976 * 2[journal heads] - 6144 * 5[dark] = 6888) after doing budget, however UBIFS cannot use BASEHD's dirty space(87200), because UBIFS cannot find next BASEHD to reclaim current BASEHD. (c->bi.min_idx_lebs equals to c->lst.idx_lebs, the empty leb won't be found by ubifs_find_free_space(), and dirty index lebs won't be picked as gced lebs. All non-index lebs has dirty space less then c->dead_wm, non-index lebs won't be picked as gced lebs either. So new free lebs won't be produced.). See more details in Link. To fix it, reserve one leb for each journal head while doing budget. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216562 Fixes: 1e51764a3c2ac0 ("UBIFS: add new flash file system") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/budget.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index bdb79be6dc0e..9cb05ef9b9dd 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -212,11 +212,10 @@ long long ubifs_calc_available(const struct ubifs_info *c, int min_idx_lebs) subtract_lebs += 1; /* - * The GC journal head LEB is not really accessible. And since - * different write types go to different heads, we may count only on - * one head's space. + * Since different write types go to different heads, we should + * reserve one leb for each head. */ - subtract_lebs += c->jhead_cnt - 1; + subtract_lebs += c->jhead_cnt; /* We also reserve one LEB for deletions, which bypass budgeting */ subtract_lebs += 1; From 35f8d4064e54c18424db2997059d4c0b1d13d093 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Fri, 21 Oct 2022 18:21:56 +0800 Subject: [PATCH 1946/4345] ubi: Fix use-after-free when volume resizing failed [ Upstream commit 9af31d6ec1a4be4caab2550096c6bd2ba8fba472 ] There is an use-after-free problem reported by KASAN: ================================================================== BUG: KASAN: use-after-free in ubi_eba_copy_table+0x11f/0x1c0 [ubi] Read of size 8 at addr ffff888101eec008 by task ubirsvol/4735 CPU: 2 PID: 4735 Comm: ubirsvol Not tainted 6.1.0-rc1-00003-g84fa3304a7fc-dirty #14 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc33 04/01/2014 Call Trace: dump_stack_lvl+0x34/0x44 print_report+0x171/0x472 kasan_report+0xad/0x130 ubi_eba_copy_table+0x11f/0x1c0 [ubi] ubi_resize_volume+0x4f9/0xbc0 [ubi] ubi_cdev_ioctl+0x701/0x1850 [ubi] __x64_sys_ioctl+0x11d/0x170 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 When ubi_change_vtbl_record() returns an error in ubi_resize_volume(), "new_eba_tbl" will be freed on error handing path, but it is holded by "vol->eba_tbl" in ubi_eba_replace_table(). It means that the liftcycle of "vol->eba_tbl" and "vol" are different, so when resizing volume in next time, it causing an use-after-free fault. Fix it by not freeing "new_eba_tbl" after it replaced in ubi_eba_replace_table(), while will be freed in next volume resizing. Fixes: 801c135ce73d ("UBI: Unsorted Block Images") Signed-off-by: Li Zetao Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- drivers/mtd/ubi/vmt.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 6ea95ade4ca6..6c7822c1cc45 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -464,7 +464,7 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) for (i = 0; i < -pebs; i++) { err = ubi_eba_unmap_leb(ubi, vol, reserved_pebs + i); if (err) - goto out_acc; + goto out_free; } spin_lock(&ubi->volumes_lock); ubi->rsvd_pebs += pebs; @@ -512,6 +512,8 @@ out_acc: ubi->avail_pebs += pebs; spin_unlock(&ubi->volumes_lock); } + return err; + out_free: kfree(new_eba_tbl); return err; From 31d60afe2cc2b712dbefcaab6b7d6a47036f844e Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Fri, 21 Oct 2022 18:21:57 +0800 Subject: [PATCH 1947/4345] ubi: Fix unreferenced object reported by kmemleak in ubi_resize_volume() [ Upstream commit 1e591ea072df7211f64542a09482b5f81cb3ad27 ] There is a memory leaks problem reported by kmemleak: unreferenced object 0xffff888102007a00 (size 128): comm "ubirsvol", pid 32090, jiffies 4298464136 (age 2361.231s) hex dump (first 32 bytes): ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ................ ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ................ backtrace: [] __kmalloc+0x4d/0x150 [] ubi_eba_create_table+0x76/0x170 [ubi] [] ubi_resize_volume+0x1be/0xbc0 [ubi] [] ubi_cdev_ioctl+0x701/0x1850 [ubi] [] __x64_sys_ioctl+0x11d/0x170 [] do_syscall_64+0x35/0x80 [] entry_SYSCALL_64_after_hwframe+0x46/0xb0 This is due to a mismatch between create and destroy interfaces, and in detail that "new_eba_tbl" created by ubi_eba_create_table() but destroyed by kfree(), while will causing "new_eba_tbl->entries" not freed. Fix it by replacing kfree(new_eba_tbl) with ubi_eba_destroy_table(new_eba_tbl) Fixes: 799dca34ac54 ("UBI: hide EBA internals") Signed-off-by: Li Zetao Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- drivers/mtd/ubi/vmt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 6c7822c1cc45..2e5bd473e5e2 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -515,7 +515,7 @@ out_acc: return err; out_free: - kfree(new_eba_tbl); + ubi_eba_destroy_table(new_eba_tbl); return err; } From bf50229494f0443b3f08427d7df63e5a7e2a796a Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Sat, 22 Oct 2022 19:52:11 +0800 Subject: [PATCH 1948/4345] ubifs: Fix memory leak in alloc_wbufs() [ Upstream commit 4a1ff3c5d04b9079b4f768d9a71b51c4af578dd2 ] kmemleak reported a sequence of memory leaks, and show them as following: unreferenced object 0xffff8881575f8400 (size 1024): comm "mount", pid 19625, jiffies 4297119604 (age 20.383s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] __kmalloc+0x4d/0x150 [] ubifs_mount+0x307b/0x7170 [ubifs] [] legacy_get_tree+0xed/0x1d0 [] vfs_get_tree+0x7d/0x230 [] path_mount+0xdd4/0x17b0 [] __x64_sys_mount+0x1fa/0x270 [] do_syscall_64+0x35/0x80 [] entry_SYSCALL_64_after_hwframe+0x46/0xb0 unreferenced object 0xffff8881798a6e00 (size 512): comm "mount", pid 19677, jiffies 4297121912 (age 37.816s) hex dump (first 32 bytes): 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk backtrace: [] __kmalloc+0x4d/0x150 [] ubifs_wbuf_init+0x52/0x480 [ubifs] [] ubifs_mount+0x31f5/0x7170 [ubifs] [] legacy_get_tree+0xed/0x1d0 [] vfs_get_tree+0x7d/0x230 [] path_mount+0xdd4/0x17b0 [] __x64_sys_mount+0x1fa/0x270 [] do_syscall_64+0x35/0x80 [] entry_SYSCALL_64_after_hwframe+0x46/0xb0 The problem is that the ubifs_wbuf_init() returns an error in the loop which in the alloc_wbufs(), then the wbuf->buf and wbuf->inodes that were successfully alloced before are not freed. Fix it by adding error hanging path in alloc_wbufs() which frees the memory alloced before when ubifs_wbuf_init() returns an error. Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Signed-off-by: Li Zetao Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/super.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 6a8f9efc2e2f..1df193c87e92 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -833,7 +833,7 @@ static int alloc_wbufs(struct ubifs_info *c) INIT_LIST_HEAD(&c->jheads[i].buds_list); err = ubifs_wbuf_init(c, &c->jheads[i].wbuf); if (err) - return err; + goto out_wbuf; c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback; c->jheads[i].wbuf.jhead = i; @@ -841,7 +841,7 @@ static int alloc_wbufs(struct ubifs_info *c) c->jheads[i].log_hash = ubifs_hash_get_desc(c); if (IS_ERR(c->jheads[i].log_hash)) { err = PTR_ERR(c->jheads[i].log_hash); - goto out; + goto out_log_hash; } } @@ -854,9 +854,18 @@ static int alloc_wbufs(struct ubifs_info *c) return 0; -out: - while (i--) +out_log_hash: + kfree(c->jheads[i].wbuf.buf); + kfree(c->jheads[i].wbuf.inodes); + +out_wbuf: + while (i--) { + kfree(c->jheads[i].wbuf.buf); + kfree(c->jheads[i].wbuf.inodes); kfree(c->jheads[i].log_hash); + } + kfree(c->jheads); + c->jheads = NULL; return err; } From fcbc795abe7897da4b5d2a6ab5010e36774b00c2 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 14 Nov 2022 18:26:24 +0800 Subject: [PATCH 1949/4345] ubi: Fix possible null-ptr-deref in ubi_free_volume() [ Upstream commit c15859bfd326c10230f09cb48a17f8a35f190342 ] It willl cause null-ptr-deref in the following case: uif_init() ubi_add_volume() cdev_add() -> if it fails, call kill_volumes() device_register() kill_volumes() -> if ubi_add_volume() fails call this function ubi_free_volume() cdev_del() device_unregister() -> trying to delete a not added device, it causes null-ptr-deref So in ubi_free_volume(), it delete devices whether they are added or not, it will causes null-ptr-deref. Handle the error case whlie calling ubi_add_volume() to fix this problem. If add volume fails, set the corresponding vol to null, so it can not be accessed in kill_volumes() and release the resource in ubi_add_volume() error path. Fixes: 801c135ce73d ("UBI: Unsorted Block Images") Suggested-by: Zhihao Cheng Signed-off-by: Yang Yingliang Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- drivers/mtd/ubi/build.c | 1 + drivers/mtd/ubi/vmt.c | 12 ++++++------ 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 8747569e793d..e45fdc1bf66a 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -467,6 +467,7 @@ static int uif_init(struct ubi_device *ubi) err = ubi_add_volume(ubi, ubi->volumes[i]); if (err) { ubi_err(ubi, "cannot add volume %d", i); + ubi->volumes[i] = NULL; goto out_volumes; } } diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 2e5bd473e5e2..d79323e8ea29 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -582,6 +582,7 @@ int ubi_add_volume(struct ubi_device *ubi, struct ubi_volume *vol) if (err) { ubi_err(ubi, "cannot add character device for volume %d, error %d", vol_id, err); + vol_release(&vol->dev); return err; } @@ -592,15 +593,14 @@ int ubi_add_volume(struct ubi_device *ubi, struct ubi_volume *vol) vol->dev.groups = volume_dev_groups; dev_set_name(&vol->dev, "%s_%d", ubi->ubi_name, vol->vol_id); err = device_register(&vol->dev); - if (err) - goto out_cdev; + if (err) { + cdev_del(&vol->cdev); + put_device(&vol->dev); + return err; + } self_check_volumes(ubi); return err; - -out_cdev: - cdev_del(&vol->cdev); - return err; } /** From 343d273d5fd06b6c065d4015506ae9ebbf6c64e6 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Fri, 18 Nov 2022 17:02:35 +0800 Subject: [PATCH 1950/4345] ubifs: Re-statistic cleaned znode count if commit failed [ Upstream commit 944e096aa24071d3fe22822f6249d3ae309e39ea ] Dirty znodes will be written on flash in committing process with following states: process A | znode state ------------------------------------------------------ do_commit | DIRTY_ZNODE ubifs_tnc_start_commit | DIRTY_ZNODE get_znodes_to_commit | DIRTY_ZNODE | COW_ZNODE layout_commit | DIRTY_ZNODE | COW_ZNODE fill_gap | 0 write master | 0 or OBSOLETE_ZNODE process B | znode state ------------------------------------------------------ do_commit | DIRTY_ZNODE[1] ubifs_tnc_start_commit | DIRTY_ZNODE get_znodes_to_commit | DIRTY_ZNODE | COW_ZNODE ubifs_tnc_end_commit | DIRTY_ZNODE | COW_ZNODE write_index | 0 write master | 0 or OBSOLETE_ZNODE[2] or | DIRTY_ZNODE[3] [1] znode is dirtied without concurrent committing process [2] znode is copied up (re-dirtied by other process) before cleaned up in committing process [3] znode is re-dirtied after cleaned up in committing process Currently, the clean znode count is updated in free_obsolete_znodes(), which is called only in normal path. If do_commit failed, clean znode count won't be updated, which triggers a failure ubifs assertion[4] in ubifs_tnc_close(): ubifs_assert_failed [ubifs]: UBIFS assert failed: freed == n [4] Commit 380347e9ca7682 ("UBIFS: Add an assertion for clean_zn_cnt"). Fix it by re-statisticing cleaned znode count in tnc_destroy_cnext(). Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216704 Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/tnc.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 894f1ab14616..7c36b6677430 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -3053,6 +3053,21 @@ static void tnc_destroy_cnext(struct ubifs_info *c) cnext = cnext->cnext; if (ubifs_zn_obsolete(znode)) kfree(znode); + else if (!ubifs_zn_cow(znode)) { + /* + * Don't forget to update clean znode count after + * committing failed, because ubifs will check this + * count while closing tnc. Non-obsolete znode could + * be re-dirtied during committing process, so dirty + * flag is untrustable. The flag 'COW_ZNODE' is set + * for each dirty znode before committing, and it is + * cleared as long as the znode become clean, so we + * can statistic clean znode count according to this + * flag. + */ + atomic_long_inc(&c->clean_zn_cnt); + atomic_long_inc(&ubifs_clean_zn_cnt); + } } while (cnext && cnext != c->cnext); } From 9d4768523b092bfb9a9bfa6b1d903b968c8008cf Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Fri, 18 Nov 2022 17:02:36 +0800 Subject: [PATCH 1951/4345] ubifs: dirty_cow_znode: Fix memleak in error handling path [ Upstream commit 122deabfe1428bffe95e2bf364ff8a5059bdf089 ] Following process will cause a memleak for copied up znode: dirty_cow_znode zn = copy_znode(c, znode); err = insert_old_idx(c, zbr->lnum, zbr->offs); if (unlikely(err)) return ERR_PTR(err); // No one refers to zn. Fix it by adding copied znode back to tnc, then it will be freed by ubifs_destroy_tnc_subtree() while closing tnc. Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216705 Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/tnc.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 7c36b6677430..07470449b960 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -267,11 +267,18 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c, if (zbr->len) { err = insert_old_idx(c, zbr->lnum, zbr->offs); if (unlikely(err)) - return ERR_PTR(err); + /* + * Obsolete znodes will be freed by tnc_destroy_cnext() + * or free_obsolete_znodes(), copied up znodes should + * be added back to tnc and freed by + * ubifs_destroy_tnc_subtree(). + */ + goto out; err = add_idx_dirt(c, zbr->lnum, zbr->len); } else err = 0; +out: zbr->znode = zn; zbr->lnum = 0; zbr->offs = 0; From f09a84548c379d4257368aa05cb5273c42aa829d Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 1 Jun 2022 10:59:59 +0800 Subject: [PATCH 1952/4345] ubifs: ubifs_writepage: Mark page dirty after writing inode failed [ Upstream commit fb8bc4c74ae4526d9489362ab2793a936d072b84 ] There are two states for ubifs writing pages: 1. Dirty, Private 2. Not Dirty, Not Private There is a third possibility which maybe related to [1] that page is private but not dirty caused by following process: PA lock(page) ubifs_write_end attach_page_private // set Private __set_page_dirty_nobuffers // set Dirty unlock(page) write_cache_pages lock(page) clear_page_dirty_for_io(page) // clear Dirty ubifs_writepage write_inode // fail, goto out, following codes are not executed // do_writepage // set_page_writeback // set Writeback // detach_page_private // clear Private // end_page_writeback // clear Writeback out: unlock(page) // Private, Not Dirty PB ksys_fadvise64_64 generic_fadvise invalidate_inode_page // page is neither Dirty nor Writeback invalidate_complete_page // page_has_private is true try_to_release_page ubifs_releasepage ubifs_assert(c, 0) !!! Then we may get following assertion failed: UBIFS error (ubi0:0 pid 1492): ubifs_assert_failed [ubifs]: UBIFS assert failed: 0, in fs/ubifs/file.c:1499 UBIFS warning (ubi0:0 pid 1492): ubifs_ro_mode [ubifs]: switched to read-only mode, error -22 CPU: 2 PID: 1492 Comm: aa Not tainted 5.16.0-rc2-00012-g7bb767dee0ba-dirty Call Trace: dump_stack+0x13/0x1b ubifs_ro_mode+0x54/0x60 [ubifs] ubifs_assert_failed+0x4b/0x80 [ubifs] ubifs_releasepage+0x7e/0x1e0 [ubifs] try_to_release_page+0x57/0xe0 invalidate_inode_page+0xfb/0x130 invalidate_mapping_pagevec+0x12/0x20 generic_fadvise+0x303/0x3c0 vfs_fadvise+0x35/0x40 ksys_fadvise64_64+0x4c/0xb0 Jump [2] to find a reproducer. [1] https://linux-mtd.infradead.narkive.com/NQoBeT1u/patch-rfc-ubifs-fix-assert-failed-in-ubifs-set-page-dirty [2] https://bugzilla.kernel.org/show_bug.cgi?id=215357 Fixes: 1e51764a3c2ac0 ("UBIFS: add new flash file system") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/ubifs/file.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 354457e846cd..19fdcda04589 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1031,7 +1031,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) if (page->index >= synced_i_size >> PAGE_SHIFT) { err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) - goto out_unlock; + goto out_redirty; /* * The inode has been written, but the write-buffer has * not been synchronized, so in case of an unclean @@ -1059,11 +1059,17 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) if (i_size > synced_i_size) { err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) - goto out_unlock; + goto out_redirty; } return do_writepage(page, len); - +out_redirty: + /* + * redirty_page_for_writepage() won't call ubifs_dirty_inode() because + * it passes I_DIRTY_PAGES flag while calling __mark_inode_dirty(), so + * there is no need to do space budget for dirty inode. + */ + redirty_page_for_writepage(wbc, page); out_unlock: unlock_page(page); return err; From 0aa0253f6c99cf9b4fd2ec4e8591cba8dae4e88f Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 9 Aug 2022 15:06:19 +0800 Subject: [PATCH 1953/4345] ubi: fastmap: Fix missed fm_anchor PEB in wear-leveling after disabling fastmap [ Upstream commit 76f9476ece445a07aeb72df9d896cd563fb5b50f ] After disabling fastmap(ubi->fm_disabled = 1), fastmap won't be updated, fm_anchor PEB is missed being scheduled for erasing. Besides, fm_anchor PEB may have smallest erase count, it doesn't participate wear-leveling. The difference of erase count between fm_anchor PEB and other PEBs will be larger and larger later on. In which situation fastmap can be disabled? Initially, we have an UBI image with fastmap. Then the image will be atttached without module parameter 'fm_autoconvert', ubi turns to full scanning mode in one random attaching process(eg. bad fastmap caused by powercut), ubi fastmap is disabled since then. Fix it by not getting fm_anchor if fastmap is disabled in ubi_refill_pools(). Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216341 Fixes: 4b68bf9a69d22d ("ubi: Select fastmap anchor PEBs considering ...") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- drivers/mtd/ubi/fastmap-wl.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/ubi/fastmap-wl.c b/drivers/mtd/ubi/fastmap-wl.c index 053ab52668e8..69592be33adf 100644 --- a/drivers/mtd/ubi/fastmap-wl.c +++ b/drivers/mtd/ubi/fastmap-wl.c @@ -146,13 +146,15 @@ void ubi_refill_pools(struct ubi_device *ubi) if (ubi->fm_anchor) { wl_tree_add(ubi->fm_anchor, &ubi->free); ubi->free_count++; + ubi->fm_anchor = NULL; } - /* - * All available PEBs are in ubi->free, now is the time to get - * the best anchor PEBs. - */ - ubi->fm_anchor = ubi_wl_get_fm_peb(ubi, 1); + if (!ubi->fm_disabled) + /* + * All available PEBs are in ubi->free, now is the time to get + * the best anchor PEBs. + */ + ubi->fm_anchor = ubi_wl_get_fm_peb(ubi, 1); for (;;) { enough = 0; From 9d448dd6bcb61a508204b57ea1f454ba9bac2f24 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Sat, 30 Jul 2022 19:28:37 +0800 Subject: [PATCH 1954/4345] ubi: Fix UAF wear-leveling entry in eraseblk_count_seq_show() [ Upstream commit a240bc5c43130c6aa50831d7caaa02a1d84e1bce ] Wear-leveling entry could be freed in error path, which may be accessed again in eraseblk_count_seq_show(), for example: __erase_worker eraseblk_count_seq_show wl = ubi->lookuptbl[*block_number] if (wl) wl_entry_destroy ubi->lookuptbl[e->pnum] = NULL kmem_cache_free(ubi_wl_entry_slab, e) erase_count = wl->ec // UAF! Wear-leveling entry updating/accessing in ubi->lookuptbl should be protected by ubi->wl_lock, fix it by adding ubi->wl_lock to serialize wl entry accessing between wl_entry_destroy() and eraseblk_count_seq_show(). Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216305 Fixes: 7bccd12d27b7e3 ("ubi: Add debugfs file for tracking PEB state") Fixes: 801c135ce73d5d ("UBI: Unsorted Block Images") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- drivers/mtd/ubi/wl.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 820b5c1c8e8e..7406bc96affb 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -885,8 +885,11 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, err = do_sync_erase(ubi, e1, vol_id, lnum, 0); if (err) { - if (e2) + if (e2) { + spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e2); + spin_unlock(&ubi->wl_lock); + } goto out_ro; } @@ -1121,14 +1124,18 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) /* Re-schedule the LEB for erasure */ err1 = schedule_erase(ubi, e, vol_id, lnum, 0, false); if (err1) { + spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e); + spin_unlock(&ubi->wl_lock); err = err1; goto out_ro; } return err; } + spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e); + spin_unlock(&ubi->wl_lock); if (err != -EIO) /* * If this is not %-EIO, we have no idea what to do. Scheduling From 8a18856e074479bd050b01e688c58defadce7ab0 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Mon, 13 Jun 2022 14:59:04 +0800 Subject: [PATCH 1955/4345] ubi: ubi_wl_put_peb: Fix infinite loop when wear-leveling work failed [ Upstream commit 4d57a7333e26040f2b583983e1970d9d460e56b0 ] Following process will trigger an infinite loop in ubi_wl_put_peb(): ubifs_bgt ubi_bgt ubifs_leb_unmap ubi_leb_unmap ubi_eba_unmap_leb ubi_wl_put_peb wear_leveling_worker e1 = rb_entry(rb_first(&ubi->used) e2 = get_peb_for_wl(ubi) ubi_io_read_vid_hdr // return err (flash fault) out_error: ubi->move_from = ubi->move_to = NULL wl_entry_destroy(ubi, e1) ubi->lookuptbl[e->pnum] = NULL retry: e = ubi->lookuptbl[pnum]; // return NULL if (e == ubi->move_from) { // NULL == NULL gets true goto retry; // infinite loop !!! $ top PID USER PR NI VIRT RES SHR S %CPU %MEM COMMAND 7676 root 20 0 0 0 0 R 100.0 0.0 ubifs_bgt0_0 Fix it by: 1) Letting ubi_wl_put_peb() returns directly if wearl leveling entry has been removed from 'ubi->lookuptbl'. 2) Using 'ubi->wl_lock' protecting wl entry deletion to preventing an use-after-free problem for wl entry in ubi_wl_put_peb(). Fetch a reproducer in [Link]. Fixes: 43f9b25a9cdd7b1 ("UBI: bugfix: protect from volume removal") Fixes: ee59ba8b064f692 ("UBI: Fix stale pointers in ubi->lookuptbl") Link: https://bugzilla.kernel.org/show_bug.cgi?id=216111 Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- drivers/mtd/ubi/wl.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 7406bc96affb..6da09263e0b9 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -971,11 +971,11 @@ out_error: spin_lock(&ubi->wl_lock); ubi->move_from = ubi->move_to = NULL; ubi->move_to_put = ubi->wl_scheduled = 0; + wl_entry_destroy(ubi, e1); + wl_entry_destroy(ubi, e2); spin_unlock(&ubi->wl_lock); ubi_free_vid_buf(vidb); - wl_entry_destroy(ubi, e1); - wl_entry_destroy(ubi, e2); out_ro: ubi_ro_mode(ubi); @@ -1251,6 +1251,18 @@ int ubi_wl_put_peb(struct ubi_device *ubi, int vol_id, int lnum, retry: spin_lock(&ubi->wl_lock); e = ubi->lookuptbl[pnum]; + if (!e) { + /* + * This wl entry has been removed for some errors by other + * process (eg. wear leveling worker), corresponding process + * (except __erase_worker, which cannot concurrent with + * ubi_wl_put_peb) will set ubi ro_mode at the same time, + * just ignore this wl entry. + */ + spin_unlock(&ubi->wl_lock); + up_read(&ubi->fm_protect); + return 0; + } if (e == ubi->move_from) { /* * User is putting the physical eraseblock which was selected to From 7cb46fa16b96ff197eb84a33b23a8448fe0c1e8d Mon Sep 17 00:00:00 2001 From: Ammar Faizi Date: Sat, 24 Dec 2022 00:23:38 +0700 Subject: [PATCH 1956/4345] x86: um: vdso: Add '%rcx' and '%r11' to the syscall clobber list [ Upstream commit 5541992e512de8c9133110809f767bd1b54ee10d ] The 'syscall' instruction clobbers '%rcx' and '%r11', but they are not listed in the inline Assembly that performs the syscall instruction. No real bug is found. It wasn't buggy by luck because '%rcx' and '%r11' are caller-saved registers, and not used in the functions, and the functions are never inlined. Add them to the clobber list for code correctness. Fixes: f1c2bb8b9964ed31de988910f8b1cfb586d30091 ("um: implement a x86_64 vDSO") Signed-off-by: Ammar Faizi Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- arch/x86/um/vdso/um_vdso.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c index 2112b8d14668..ff0f3b4b6c45 100644 --- a/arch/x86/um/vdso/um_vdso.c +++ b/arch/x86/um/vdso/um_vdso.c @@ -17,8 +17,10 @@ int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + asm("syscall" + : "=a" (ret) + : "0" (__NR_clock_gettime), "D" (clock), "S" (ts) + : "rcx", "r11", "memory"); return ret; } @@ -29,8 +31,10 @@ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + asm("syscall" + : "=a" (ret) + : "0" (__NR_gettimeofday), "D" (tv), "S" (tz) + : "rcx", "r11", "memory"); return ret; } From 273559f58f71512e4be929b78d4e05f60d48a60c Mon Sep 17 00:00:00 2001 From: ruanjinjie Date: Wed, 16 Nov 2022 17:49:50 +0800 Subject: [PATCH 1957/4345] watchdog: at91sam9_wdt: use devm_request_irq to avoid missing free_irq() in error path [ Upstream commit 07bec0e09c1afbab4c5674fd2341f4f52d594f30 ] free_irq() is missing in case of error in at91_wdt_init(), use devm_request_irq to fix that. Fixes: 5161b31dc39a ("watchdog: at91sam9_wdt: better watchdog support") Signed-off-by: ruanjinjie Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20221116094950.3141943-1-ruanjinjie@huawei.com [groeck: Adjust multi-line alignment] Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Signed-off-by: Sasha Levin --- drivers/watchdog/at91sam9_wdt.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/at91sam9_wdt.c b/drivers/watchdog/at91sam9_wdt.c index 292b5a1ca831..fed7be246442 100644 --- a/drivers/watchdog/at91sam9_wdt.c +++ b/drivers/watchdog/at91sam9_wdt.c @@ -206,10 +206,9 @@ static int at91_wdt_init(struct platform_device *pdev, struct at91wdt *wdt) "min heartbeat and max heartbeat might be too close for the system to handle it correctly\n"); if ((tmp & AT91_WDT_WDFIEN) && wdt->irq) { - err = request_irq(wdt->irq, wdt_interrupt, - IRQF_SHARED | IRQF_IRQPOLL | - IRQF_NO_SUSPEND, - pdev->name, wdt); + err = devm_request_irq(dev, wdt->irq, wdt_interrupt, + IRQF_SHARED | IRQF_IRQPOLL | IRQF_NO_SUSPEND, + pdev->name, wdt); if (err) return err; } From c5a21a5501508ae3afa2fe6d5a3e74a37fa48df3 Mon Sep 17 00:00:00 2001 From: Chen Jun Date: Wed, 16 Nov 2022 01:27:14 +0000 Subject: [PATCH 1958/4345] watchdog: Fix kmemleak in watchdog_cdev_register [ Upstream commit 13721a2ac66b246f5802ba1b75ad8637e53eeecc ] kmemleak reports memory leaks in watchdog_dev_register, as follows: unreferenced object 0xffff888116233000 (size 2048): comm ""modprobe"", pid 28147, jiffies 4353426116 (age 61.741s) hex dump (first 32 bytes): 80 fa b9 05 81 88 ff ff 08 30 23 16 81 88 ff ff .........0#..... 08 30 23 16 81 88 ff ff 00 00 00 00 00 00 00 00 .0#............. backtrace: [<000000007f001ffd>] __kmem_cache_alloc_node+0x157/0x220 [<000000006a389304>] kmalloc_trace+0x21/0x110 [<000000008d640eea>] watchdog_dev_register+0x4e/0x780 [watchdog] [<0000000053c9f248>] __watchdog_register_device+0x4f0/0x680 [watchdog] [<00000000b2979824>] watchdog_register_device+0xd2/0x110 [watchdog] [<000000001f730178>] 0xffffffffc10880ae [<000000007a1a8bcc>] do_one_initcall+0xcb/0x4d0 [<00000000b98be325>] do_init_module+0x1ca/0x5f0 [<0000000046d08e7c>] load_module+0x6133/0x70f0 ... unreferenced object 0xffff888105b9fa80 (size 16): comm ""modprobe"", pid 28147, jiffies 4353426116 (age 61.741s) hex dump (first 16 bytes): 77 61 74 63 68 64 6f 67 31 00 b9 05 81 88 ff ff watchdog1....... backtrace: [<000000007f001ffd>] __kmem_cache_alloc_node+0x157/0x220 [<00000000486ab89b>] __kmalloc_node_track_caller+0x44/0x1b0 [<000000005a39aab0>] kvasprintf+0xb5/0x140 [<0000000024806f85>] kvasprintf_const+0x55/0x180 [<000000009276cb7f>] kobject_set_name_vargs+0x56/0x150 [<00000000a92e820b>] dev_set_name+0xab/0xe0 [<00000000cec812c6>] watchdog_dev_register+0x285/0x780 [watchdog] [<0000000053c9f248>] __watchdog_register_device+0x4f0/0x680 [watchdog] [<00000000b2979824>] watchdog_register_device+0xd2/0x110 [watchdog] [<000000001f730178>] 0xffffffffc10880ae [<000000007a1a8bcc>] do_one_initcall+0xcb/0x4d0 [<00000000b98be325>] do_init_module+0x1ca/0x5f0 [<0000000046d08e7c>] load_module+0x6133/0x70f0 ... The reason is that put_device is not be called if cdev_device_add fails and wdd->id != 0. watchdog_cdev_register wd_data = kzalloc [1] err = dev_set_name [2] .. err = cdev_device_add if (err) { if (wdd->id == 0) { // wdd->id != 0 .. } return err; // [1],[2] would be leaked To fix it, call put_device in all wdd->id cases. Fixes: 72139dfa2464 ("watchdog: Fix the race between the release of watchdog_core_data and cdev") Signed-off-by: Chen Jun Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20221116012714.102066-1-chenjun102@huawei.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Signed-off-by: Sasha Levin --- drivers/watchdog/watchdog_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index 2ee017442dfc..f37255cd75fd 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -1037,8 +1037,8 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) if (wdd->id == 0) { misc_deregister(&watchdog_miscdev); old_wd_data = NULL; - put_device(&wd_data->dev); } + put_device(&wd_data->dev); return err; } From 9f7abdd500269d044388593654a85afc3e174b91 Mon Sep 17 00:00:00 2001 From: Li Hua Date: Wed, 16 Nov 2022 10:07:06 +0800 Subject: [PATCH 1959/4345] watchdog: pcwd_usb: Fix attempting to access uninitialized memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7d06c07c67100fd0f8e6b3ab7145ce789f788117 ] The stack variable msb and lsb may be used uninitialized in function usb_pcwd_get_temperature and usb_pcwd_get_timeleft when usb card no response. The build waring is: drivers/watchdog/pcwd_usb.c:336:22: error: ‘lsb’ is used uninitialized in this function [-Werror=uninitialized] *temperature = (lsb * 9 / 5) + 32; ~~~~^~~ drivers/watchdog/pcwd_usb.c:328:21: note: ‘lsb’ was declared here unsigned char msb, lsb; ^~~ cc1: all warnings being treated as errors scripts/Makefile.build:250: recipe for target 'drivers/watchdog/pcwd_usb.o' failed make[3]: *** [drivers/watchdog/pcwd_usb.o] Error 1 Fixes: b7e04f8c61a4 ("mv watchdog tree under drivers") Signed-off-by: Li Hua Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20221116020706.70847-1-hucool.lihua@huawei.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Signed-off-by: Sasha Levin --- drivers/watchdog/pcwd_usb.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c index 1bdaf17c1d38..8202f0a6b093 100644 --- a/drivers/watchdog/pcwd_usb.c +++ b/drivers/watchdog/pcwd_usb.c @@ -325,7 +325,8 @@ static int usb_pcwd_set_heartbeat(struct usb_pcwd_private *usb_pcwd, int t) static int usb_pcwd_get_temperature(struct usb_pcwd_private *usb_pcwd, int *temperature) { - unsigned char msb, lsb; + unsigned char msb = 0x00; + unsigned char lsb = 0x00; usb_pcwd_send_command(usb_pcwd, CMD_READ_TEMP, &msb, &lsb); @@ -341,7 +342,8 @@ static int usb_pcwd_get_temperature(struct usb_pcwd_private *usb_pcwd, static int usb_pcwd_get_timeleft(struct usb_pcwd_private *usb_pcwd, int *time_left) { - unsigned char msb, lsb; + unsigned char msb = 0x00; + unsigned char lsb = 0x00; /* Read the time that's left before rebooting */ /* Note: if the board is not yet armed then we will read 0xFFFF */ From 1ff0b87df98b93e10ced45773aa7d35377355421 Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Fri, 10 Feb 2023 15:17:30 +0800 Subject: [PATCH 1960/4345] netfilter: ctnetlink: fix possible refcount leak in ctnetlink_create_conntrack() [ Upstream commit ac4893980bbe79ce383daf9a0885666a30fe4c83 ] nf_ct_put() needs to be called to put the refcount got by nf_conntrack_find_get() to avoid refcount leak when nf_conntrack_hash_check_insert() fails. Fixes: 7d367e06688d ("netfilter: ctnetlink: fix soft lockup when netlink adds new entries (v2)") Signed-off-by: Hangyu Hua Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_netlink.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 2efdc50f978b..f8ba3bc25cf3 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2359,12 +2359,15 @@ ctnetlink_create_conntrack(struct net *net, err = nf_conntrack_hash_check_insert(ct); if (err < 0) - goto err2; + goto err3; rcu_read_unlock(); return ct; +err3: + if (ct->master) + nf_ct_put(ct->master); err2: rcu_read_unlock(); err1: From 9060abce3305ab2354c892c09d5689df51486df5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Feb 2023 23:20:06 +0100 Subject: [PATCH 1961/4345] netfilter: ebtables: fix table blob use-after-free [ Upstream commit e58a171d35e32e6e8c37cfe0e8a94406732a331f ] We are not allowed to return an error at this point. Looking at the code it looks like ret is always 0 at this point, but its not. t = find_table_lock(net, repl->name, &ret, &ebt_mutex); ... this can return a valid table, with ret != 0. This bug causes update of table->private with the new blob, but then frees the blob right away in the caller. Syzbot report: BUG: KASAN: vmalloc-out-of-bounds in __ebt_unregister_table+0xc00/0xcd0 net/bridge/netfilter/ebtables.c:1168 Read of size 4 at addr ffffc90005425000 by task kworker/u4:4/74 Workqueue: netns cleanup_net Call Trace: kasan_report+0xbf/0x1f0 mm/kasan/report.c:517 __ebt_unregister_table+0xc00/0xcd0 net/bridge/netfilter/ebtables.c:1168 ebt_unregister_table+0x35/0x40 net/bridge/netfilter/ebtables.c:1372 ops_exit_list+0xb0/0x170 net/core/net_namespace.c:169 cleanup_net+0x4ee/0xb10 net/core/net_namespace.c:613 ... ip(6)tables appears to be ok (ret should be 0 at this point) but make this more obvious. Fixes: c58dd2dd443c ("netfilter: Can't fail and free after table replacement") Reported-by: syzbot+f61594de72d6705aea03@syzkaller.appspotmail.com Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/bridge/netfilter/ebtables.c | 2 +- net/ipv4/netfilter/ip_tables.c | 3 +-- net/ipv6/netfilter/ip6_tables.c | 3 +-- 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 06b80b584381..8335b7e4bcf6 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1049,7 +1049,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries, AUDIT_XT_OP_REPLACE, GFP_KERNEL); - return ret; + return 0; free_unlock: mutex_unlock(&ebt_mutex); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index f77ea0dbe656..ec981618b7b2 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1044,7 +1044,6 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_counters *counters; struct ipt_entry *iter; - ret = 0; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; @@ -1090,7 +1089,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n"); } vfree(counters); - return ret; + return 0; put_module: module_put(t->me); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index d36168baf677..99bb11d16712 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1062,7 +1062,6 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_counters *counters; struct ip6t_entry *iter; - ret = 0; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; @@ -1108,7 +1107,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); } vfree(counters); - return ret; + return 0; put_module: module_put(t->me); From da26369377f0b671c14692e2d65ceb38131053e1 Mon Sep 17 00:00:00 2001 From: Lu Wei Date: Wed, 22 Feb 2023 16:36:28 +0800 Subject: [PATCH 1962/4345] ipv6: Add lwtunnel encap size of all siblings in nexthop calculation [ Upstream commit 4cc59f386991ec9374cb4bc83dbe1c0b5a95033f ] In function rt6_nlmsg_size(), the length of nexthop is calculated by multipling the nexthop length of fib6_info and the number of siblings. However if the fib6_info has no lwtunnel but the siblings have lwtunnels, the nexthop length is less than it should be, and it will trigger a warning in inet6_rt_notify() as follows: WARNING: CPU: 0 PID: 6082 at net/ipv6/route.c:6180 inet6_rt_notify+0x120/0x130 ...... Call Trace: fib6_add_rt2node+0x685/0xa30 fib6_add+0x96/0x1b0 ip6_route_add+0x50/0xd0 inet6_rtm_newroute+0x97/0xa0 rtnetlink_rcv_msg+0x156/0x3d0 netlink_rcv_skb+0x5a/0x110 netlink_unicast+0x246/0x350 netlink_sendmsg+0x250/0x4c0 sock_sendmsg+0x66/0x70 ___sys_sendmsg+0x7c/0xd0 __sys_sendmsg+0x5d/0xb0 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc This bug can be reproduced by script: ip -6 addr add 2002::2/64 dev ens2 ip -6 route add 100::/64 via 2002::1 dev ens2 metric 100 for i in 10 20 30 40 50 60 70; do ip link add link ens2 name ipv_$i type ipvlan ip -6 addr add 2002::$i/64 dev ipv_$i ifconfig ipv_$i up done for i in 10 20 30 40 50 60; do ip -6 route append 100::/64 encap ip6 dst 2002::$i via 2002::1 dev ipv_$i metric 100 done ip -6 route append 100::/64 via 2002::1 dev ipv_70 metric 100 This patch fixes it by adding nexthop_len of every siblings using rt6_nh_nlmsg_size(). Fixes: beb1afac518d ("net: ipv6: Add support to dump multipath routes via RTA_MULTIPATH attribute") Signed-off-by: Lu Wei Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230222083629.335683-2-luwei32@huawei.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/ipv6/route.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 803d1aa83140..a6d5c99f65a3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5444,16 +5444,17 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i) nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); } else { + struct fib6_info *sibling, *next_sibling; struct fib6_nh *nh = f6i->fib6_nh; nexthop_len = 0; if (f6i->fib6_nsiblings) { - nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */ - + NLA_ALIGN(sizeof(struct rtnexthop)) - + nla_total_size(16) /* RTA_GATEWAY */ - + lwtunnel_get_encap_size(nh->fib_nh_lws); + rt6_nh_nlmsg_size(nh, &nexthop_len); - nexthop_len *= f6i->fib6_nsiblings; + list_for_each_entry_safe(sibling, next_sibling, + &f6i->fib6_siblings, fib6_siblings) { + rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); + } } nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } From 8ee401f89cdb10f39098c0656d695b2bc4052100 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 22 Feb 2023 12:07:21 -0500 Subject: [PATCH 1963/4345] sctp: add a refcnt in sctp_stream_priorities to avoid a nested loop [ Upstream commit 68ba44639537de6f91fe32783766322d41848127 ] With this refcnt added in sctp_stream_priorities, we don't need to traverse all streams to check if the prio is used by other streams when freeing one stream's prio in sctp_sched_prio_free_sid(). This can avoid a nested loop (up to 65535 * 65535), which may cause a stuck as Ying reported: watchdog: BUG: soft lockup - CPU#23 stuck for 26s! [ksoftirqd/23:136] Call Trace: sctp_sched_prio_free_sid+0xab/0x100 [sctp] sctp_stream_free_ext+0x64/0xa0 [sctp] sctp_stream_free+0x31/0x50 [sctp] sctp_association_free+0xa5/0x200 [sctp] Note that it doesn't need to use refcount_t type for this counter, as its accessing is always protected under the sock lock. v1->v2: - add a check in sctp_sched_prio_set to avoid the possible prio_head refcnt overflow. Fixes: 9ed7bfc79542 ("sctp: fix memory leak in sctp_stream_outq_migrate()") Reported-by: Ying Xu Acked-by: Marcelo Ricardo Leitner Signed-off-by: Xin Long Link: https://lore.kernel.org/r/825eb0c905cb864991eba335f4a2b780e543f06b.1677085641.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/sctp/structs.h | 1 + net/sctp/stream_sched_prio.c | 52 +++++++++++++++--------------------- 2 files changed, 22 insertions(+), 31 deletions(-) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index be9ff0422c16..be59e8df0bff 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1394,6 +1394,7 @@ struct sctp_stream_priorities { /* The next stream in line */ struct sctp_stream_out_ext *next; __u16 prio; + __u16 users; }; struct sctp_stream_out_ext { diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c index 4fc9f2923ed1..7dd9f8b387cc 100644 --- a/net/sctp/stream_sched_prio.c +++ b/net/sctp/stream_sched_prio.c @@ -25,6 +25,18 @@ static void sctp_sched_prio_unsched_all(struct sctp_stream *stream); +static struct sctp_stream_priorities *sctp_sched_prio_head_get(struct sctp_stream_priorities *p) +{ + p->users++; + return p; +} + +static void sctp_sched_prio_head_put(struct sctp_stream_priorities *p) +{ + if (p && --p->users == 0) + kfree(p); +} + static struct sctp_stream_priorities *sctp_sched_prio_new_head( struct sctp_stream *stream, int prio, gfp_t gfp) { @@ -38,6 +50,7 @@ static struct sctp_stream_priorities *sctp_sched_prio_new_head( INIT_LIST_HEAD(&p->active); p->next = NULL; p->prio = prio; + p->users = 1; return p; } @@ -53,7 +66,7 @@ static struct sctp_stream_priorities *sctp_sched_prio_get_head( */ list_for_each_entry(p, &stream->prio_list, prio_sched) { if (p->prio == prio) - return p; + return sctp_sched_prio_head_get(p); if (p->prio > prio) break; } @@ -70,7 +83,7 @@ static struct sctp_stream_priorities *sctp_sched_prio_get_head( */ break; if (p->prio == prio) - return p; + return sctp_sched_prio_head_get(p); } /* If not even there, allocate a new one. */ @@ -154,32 +167,21 @@ static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, struct sctp_stream_out_ext *soute = sout->ext; struct sctp_stream_priorities *prio_head, *old; bool reschedule = false; - int i; + + old = soute->prio_head; + if (old && old->prio == prio) + return 0; prio_head = sctp_sched_prio_get_head(stream, prio, gfp); if (!prio_head) return -ENOMEM; reschedule = sctp_sched_prio_unsched(soute); - old = soute->prio_head; soute->prio_head = prio_head; if (reschedule) sctp_sched_prio_sched(stream, soute); - if (!old) - /* Happens when we set the priority for the first time */ - return 0; - - for (i = 0; i < stream->outcnt; i++) { - soute = SCTP_SO(stream, i)->ext; - if (soute && soute->prio_head == old) - /* It's still in use, nothing else to do here. */ - return 0; - } - - /* No hits, we are good to free it. */ - kfree(old); - + sctp_sched_prio_head_put(old); return 0; } @@ -206,20 +208,8 @@ static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, static void sctp_sched_prio_free_sid(struct sctp_stream *stream, __u16 sid) { - struct sctp_stream_priorities *prio = SCTP_SO(stream, sid)->ext->prio_head; - int i; - - if (!prio) - return; - + sctp_sched_prio_head_put(SCTP_SO(stream, sid)->ext->prio_head); SCTP_SO(stream, sid)->ext->prio_head = NULL; - for (i = 0; i < stream->outcnt; i++) { - if (SCTP_SO(stream, i)->ext && - SCTP_SO(stream, i)->ext->prio_head == prio) - return; - } - - kfree(prio); } static void sctp_sched_prio_free(struct sctp_stream *stream) From 82a0c1fe1fe0a0b9957e8f6a0b99884f64ba0ba4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Feb 2023 08:38:45 +0000 Subject: [PATCH 1964/4345] net: fix __dev_kfree_skb_any() vs drop monitor [ Upstream commit ac3ad19584b26fae9ac86e4faebe790becc74491 ] dev_kfree_skb() is aliased to consume_skb(). When a driver is dropping a packet by calling dev_kfree_skb_any() we should propagate the drop reason instead of pretending the packet was consumed. Note: Now we have enum skb_drop_reason we could remove enum skb_free_reason (for linux-6.4) v2: added an unlikely(), suggested by Yunsheng Lin. Fixes: e6247027e517 ("net: introduce dev_consume_skb_any()") Signed-off-by: Eric Dumazet Cc: Yunsheng Lin Reviewed-by: Yunsheng Lin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index b7646d4e079b..8cbcb6a104f2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3119,8 +3119,10 @@ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { if (in_irq() || irqs_disabled()) __dev_kfree_skb_irq(skb, reason); + else if (unlikely(reason == SKB_REASON_DROPPED)) + kfree_skb(skb); else - dev_kfree_skb(skb); + consume_skb(skb); } EXPORT_SYMBOL(__dev_kfree_skb_any); From c959a53b62a6d5bdcf6f2c4295714f68a2381f6a Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 30 Jan 2023 12:30:35 +0100 Subject: [PATCH 1965/4345] 9p/xen: fix version parsing [ Upstream commit f1956f4ec15195ec60976d9b5625326285ab102e ] When connecting the Xen 9pfs frontend to the backend, the "versions" Xenstore entry written by the backend is parsed in a wrong way. The "versions" entry is defined to contain the versions supported by the backend separated by commas (e.g. "1,2"). Today only version "1" is defined. Unfortunately the frontend doesn't look for "1" being listed in the entry, but it is expecting the entry to have the value "1". This will result in failure as soon as the backend will support e.g. versions "1" and "2". Fix that by scanning the entry correctly. Link: https://lkml.kernel.org/r/20230130113036.7087-2-jgross@suse.com Fixes: 71ebd71921e4 ("xen/9pfs: connect to the backend") Signed-off-by: Juergen Gross Reviewed-by: Simon Horman Signed-off-by: Dominique Martinet Signed-off-by: Eric Van Hensbergen Signed-off-by: Sasha Levin --- net/9p/trans_xen.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 6c8a33f98f09..d8ed75e8dbb1 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -399,13 +399,19 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, int ret, i; struct xenbus_transaction xbt; struct xen_9pfs_front_priv *priv = NULL; - char *versions; + char *versions, *v; unsigned int max_rings, max_ring_order, len = 0; versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len); if (IS_ERR(versions)) return PTR_ERR(versions); - if (strcmp(versions, "1")) { + for (v = versions; *v; v++) { + if (simple_strtoul(v, &v, 10) == 1) { + v = NULL; + break; + } + } + if (v) { kfree(versions); return -EINVAL; } From 3e0359f151ac151abe3fa71040e450ed69cb824b Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 30 Jan 2023 12:30:36 +0100 Subject: [PATCH 1966/4345] 9p/xen: fix connection sequence [ Upstream commit c15fe55d14b3b4ded5af2a3260877460a6ffb8ad ] Today the connection sequence of the Xen 9pfs frontend doesn't match the documented sequence. It can work reliably only for a PV 9pfs device having been added at boot time already, as the frontend is not waiting for the backend to have set its state to "XenbusStateInitWait" before reading the backend properties from Xenstore. Fix that by following the documented sequence [1] (the documentation has a bug, so the reference is for the patch fixing that). [1]: https://lore.kernel.org/xen-devel/20230130090937.31623-1-jgross@suse.com/T/#u Link: https://lkml.kernel.org/r/20230130113036.7087-3-jgross@suse.com Fixes: 868eb122739a ("xen/9pfs: introduce Xen 9pfs transport driver") Signed-off-by: Juergen Gross Reviewed-by: Simon Horman Signed-off-by: Dominique Martinet Signed-off-by: Eric Van Hensbergen Signed-off-by: Sasha Levin --- net/9p/trans_xen.c | 38 +++++++++++++++++++++++--------------- 1 file changed, 23 insertions(+), 15 deletions(-) diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index d8ed75e8dbb1..220e8f4ac0cf 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -393,12 +393,11 @@ out: return ret; } -static int xen_9pfs_front_probe(struct xenbus_device *dev, - const struct xenbus_device_id *id) +static int xen_9pfs_front_init(struct xenbus_device *dev) { int ret, i; struct xenbus_transaction xbt; - struct xen_9pfs_front_priv *priv = NULL; + struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev); char *versions, *v; unsigned int max_rings, max_ring_order, len = 0; @@ -426,11 +425,6 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, if (p9_xen_trans.maxsize > XEN_FLEX_RING_SIZE(max_ring_order)) p9_xen_trans.maxsize = XEN_FLEX_RING_SIZE(max_ring_order) / 2; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - - priv->dev = dev; priv->num_rings = XEN_9PFS_NUM_RINGS; priv->rings = kcalloc(priv->num_rings, sizeof(*priv->rings), GFP_KERNEL); @@ -489,23 +483,35 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, goto error; } - write_lock(&xen_9pfs_lock); - list_add_tail(&priv->list, &xen_9pfs_devs); - write_unlock(&xen_9pfs_lock); - dev_set_drvdata(&dev->dev, priv); - xenbus_switch_state(dev, XenbusStateInitialised); - return 0; error_xenbus: xenbus_transaction_end(xbt, 1); xenbus_dev_fatal(dev, ret, "writing xenstore"); error: - dev_set_drvdata(&dev->dev, NULL); xen_9pfs_front_free(priv); return ret; } +static int xen_9pfs_front_probe(struct xenbus_device *dev, + const struct xenbus_device_id *id) +{ + struct xen_9pfs_front_priv *priv = NULL; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = dev; + dev_set_drvdata(&dev->dev, priv); + + write_lock(&xen_9pfs_lock); + list_add_tail(&priv->list, &xen_9pfs_devs); + write_unlock(&xen_9pfs_lock); + + return 0; +} + static int xen_9pfs_front_resume(struct xenbus_device *dev) { dev_warn(&dev->dev, "suspend/resume unsupported\n"); @@ -524,6 +530,8 @@ static void xen_9pfs_front_changed(struct xenbus_device *dev, break; case XenbusStateInitWait: + if (!xen_9pfs_front_init(dev)) + xenbus_switch_state(dev, XenbusStateInitialised); break; case XenbusStateConnected: From 0ac65fab2b3f121e4d606b3729cf06da0bfc8885 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 4 Jan 2023 10:04:24 +0800 Subject: [PATCH 1967/4345] 9p/rdma: unmap receive dma buffer in rdma_request()/post_recv() [ Upstream commit 74a25e6e916cb57dab4267a96fbe8864ed21abdb ] When down_interruptible() or ib_post_send() failed in rdma_request(), receive dma buffer is not unmapped. Add unmap action to error path. Also if ib_post_recv() failed in post_recv(), dma buffer is not unmapped. Add unmap action to error path. Link: https://lkml.kernel.org/r/20230104020424.611926-1-shaozhengchao@huawei.com Fixes: fc79d4b104f0 ("9p: rdma: RDMA Transport Support for 9P") Signed-off-by: Zhengchao Shao Reviewed-by: Leon Romanovsky Signed-off-by: Dominique Martinet Signed-off-by: Eric Van Hensbergen Signed-off-by: Sasha Levin --- net/9p/trans_rdma.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 2885ff9c76f0..7217bd9886e3 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -386,6 +386,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c) struct p9_trans_rdma *rdma = client->trans; struct ib_recv_wr wr; struct ib_sge sge; + int ret; c->busa = ib_dma_map_single(rdma->cm_id->device, c->rc.sdata, client->msize, @@ -403,7 +404,12 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c) wr.wr_cqe = &c->cqe; wr.sg_list = &sge; wr.num_sge = 1; - return ib_post_recv(rdma->qp, &wr, NULL); + + ret = ib_post_recv(rdma->qp, &wr, NULL); + if (ret) + ib_dma_unmap_single(rdma->cm_id->device, c->busa, + client->msize, DMA_FROM_DEVICE); + return ret; error: p9_debug(P9_DEBUG_ERROR, "EIO\n"); @@ -500,7 +506,7 @@ dont_need_post_recv: if (down_interruptible(&rdma->sq_sem)) { err = -EINTR; - goto send_error; + goto dma_unmap; } /* Mark request as `sent' *before* we actually send it, @@ -510,11 +516,14 @@ dont_need_post_recv: req->status = REQ_STATUS_SENT; err = ib_post_send(rdma->qp, &wr, NULL); if (err) - goto send_error; + goto dma_unmap; /* Success */ return 0; +dma_unmap: + ib_dma_unmap_single(rdma->cm_id->device, c->busa, + c->req->tc.size, DMA_TO_DEVICE); /* Handle errors that happened during or while preparing the send: */ send_error: req->status = REQ_STATUS_ERROR; From 8817602cffe0107834865b5d2c2fb7f77132d7dc Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Wed, 8 Feb 2023 17:44:06 +0200 Subject: [PATCH 1968/4345] net/mlx5: Geneve, Fix handling of Geneve object id as error code [ Upstream commit d28a06d7dbedc598a06bd1e53a28125f87ca5d0c ] On success, mlx5_geneve_tlv_option_create returns non negative Geneve object id. In case the object id is positive value the caller functions will handle it as an error (non zero) and will fail to offload the Geneve rule. Fix this by changing caller function ,mlx5_geneve_tlv_option_add, to return 0 in case valid non negative object id was provided. Fixes: 0ccc171ea6a2 ("net/mlx5: Geneve, Manage Geneve TLV options") Signed-off-by: Maor Dickman Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c index 23361a9ae4fa..6dc83e871cd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c @@ -105,6 +105,7 @@ int mlx5_geneve_tlv_option_add(struct mlx5_geneve *geneve, struct geneve_opt *op geneve->opt_type = opt->type; geneve->obj_id = res; geneve->refcount++; + res = 0; } unlock: From 8978315cb4bf8878c9c8ec05dafd8f7ff539860d Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Sat, 25 Feb 2023 13:56:14 +0300 Subject: [PATCH 1969/4345] nfc: fix memory leak of se_io context in nfc_genl_se_io [ Upstream commit 25ff6f8a5a3b8dc48e8abda6f013e8cc4b14ffea ] The callback context for sending/receiving APDUs to/from the selected secure element is allocated inside nfc_genl_se_io and supposed to be eventually freed in se_io_cb callback function. However, there are several error paths where the bwi_timer is not charged to call se_io_cb later, and the cb_context is leaked. The patch proposes to free the cb_context explicitly on those error paths. At the moment we can't simply check 'dev->ops->se_io()' return value as it may be negative in both cases: when the timer was charged and was not. Fixes: 5ce3f32b5264 ("NFC: netlink: SE API implementation") Reported-by: syzbot+df64c0a2e8d68e78a4fa@syzkaller.appspotmail.com Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/nfc/st-nci/se.c | 6 ++++++ drivers/nfc/st21nfca/se.c | 6 ++++++ net/nfc/netlink.c | 4 ++++ 3 files changed, 16 insertions(+) diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 37d397aae9b9..a14afceaf5e9 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -664,6 +664,12 @@ int st_nci_se_io(struct nci_dev *ndev, u32 se_idx, ST_NCI_EVT_TRANSMIT_DATA, apdu, apdu_length); default: + /* Need to free cb_context here as at the moment we can't + * clearly indicate to the caller if the callback function + * would be called (and free it) or not. In both cases a + * negative value may be returned to the caller. + */ + kfree(cb_context); return -ENODEV; } } diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index d41636504246..6a1d3b2752fb 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -236,6 +236,12 @@ int st21nfca_hci_se_io(struct nfc_hci_dev *hdev, u32 se_idx, ST21NFCA_EVT_TRANSMIT_DATA, apdu, apdu_length); default: + /* Need to free cb_context here as at the moment we can't + * clearly indicate to the caller if the callback function + * would be called (and free it) or not. In both cases a + * negative value may be returned to the caller. + */ + kfree(cb_context); return -ENODEV; } } diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 610caea4feec..3f4785be066a 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1442,7 +1442,11 @@ static int nfc_se_io(struct nfc_dev *dev, u32 se_idx, rc = dev->ops->se_io(dev, se_idx, apdu, apdu_length, cb, cb_context); + device_unlock(&dev->dev); + return rc; + error: + kfree(cb_context); device_unlock(&dev->dev); return rc; } From 2f935409cd82f45205b597cd93efbd7cfb10d54c Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Fri, 24 Feb 2023 12:00:58 -0300 Subject: [PATCH 1970/4345] net/sched: act_sample: fix action bind logic [ Upstream commit 4a20056a49a1854966562241922f68197f950539 ] The TC architecture allows filters and actions to be created independently. In filters the user can reference action objects using: tc action add action sample ... index 1 tc filter add ... action pedit index 1 In the current code for act_sample this is broken as it checks netlink attributes for create/update before actually checking if we are binding to an existing action. tdc results: 1..29 ok 1 9784 - Add valid sample action with mandatory arguments ok 2 5c91 - Add valid sample action with mandatory arguments and continue control action ok 3 334b - Add valid sample action with mandatory arguments and drop control action ok 4 da69 - Add valid sample action with mandatory arguments and reclassify control action ok 5 13ce - Add valid sample action with mandatory arguments and pipe control action ok 6 1886 - Add valid sample action with mandatory arguments and jump control action ok 7 7571 - Add sample action with invalid rate ok 8 b6d4 - Add sample action with mandatory arguments and invalid control action ok 9 a874 - Add invalid sample action without mandatory arguments ok 10 ac01 - Add invalid sample action without mandatory argument rate ok 11 4203 - Add invalid sample action without mandatory argument group ok 12 14a7 - Add invalid sample action without mandatory argument group ok 13 8f2e - Add valid sample action with trunc argument ok 14 45f8 - Add sample action with maximum rate argument ok 15 ad0c - Add sample action with maximum trunc argument ok 16 83a9 - Add sample action with maximum group argument ok 17 ed27 - Add sample action with invalid rate argument ok 18 2eae - Add sample action with invalid group argument ok 19 6ff3 - Add sample action with invalid trunc size ok 20 2b2a - Add sample action with invalid index ok 21 dee2 - Add sample action with maximum allowed index ok 22 560e - Add sample action with cookie ok 23 704a - Replace existing sample action with new rate argument ok 24 60eb - Replace existing sample action with new group argument ok 25 2cce - Replace existing sample action with new trunc argument ok 26 59d1 - Replace existing sample action with new control argument ok 27 0a6e - Replace sample action with invalid goto chain control ok 28 3872 - Delete sample action with valid index ok 29 a394 - Delete sample action with invalid index Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action") Reviewed-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/act_sample.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 2f0e98bcf494..6988a9cf4080 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -54,8 +54,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, sample_policy, NULL); if (ret < 0) return ret; - if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] || - !tb[TCA_SAMPLE_PSAMPLE_GROUP]) + + if (!tb[TCA_SAMPLE_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_SAMPLE_PARMS]); @@ -79,6 +79,13 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } + + if (!tb[TCA_SAMPLE_RATE] || !tb[TCA_SAMPLE_PSAMPLE_GROUP]) { + NL_SET_ERR_MSG(extack, "sample rate and group are required"); + err = -EINVAL; + goto release_idr; + } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; From 4d08ed4651a105224b97f53f6a586a3efa175498 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 25 Feb 2023 17:22:37 +0100 Subject: [PATCH 1971/4345] ARM: dts: spear320-hmi: correct STMPE GPIO compatible [ Upstream commit 33a0c1b850c8c85f400531dab3a0b022cdb164b1 ] The compatible is st,stmpe-gpio. Fixes: e2eb69183ec4 ("ARM: SPEAr320: DT: Add SPEAr 320 HMI board support") Signed-off-by: Krzysztof Kozlowski Acked-by: Viresh Kumar Link: https://lore.kernel.org/r/20230225162237.40242-1-krzysztof.kozlowski@linaro.org Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- arch/arm/boot/dts/spear320-hmi.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/spear320-hmi.dts b/arch/arm/boot/dts/spear320-hmi.dts index 367ba48aac3e..5c562fb4886f 100644 --- a/arch/arm/boot/dts/spear320-hmi.dts +++ b/arch/arm/boot/dts/spear320-hmi.dts @@ -242,7 +242,7 @@ irq-trigger = <0x1>; stmpegpio: stmpe-gpio { - compatible = "stmpe,gpio"; + compatible = "st,stmpe-gpio"; reg = <0>; gpio-controller; #gpio-cells = <2>; From ac73d8f6a64a9be3ab1c9e8d9ed66d81aebc82f5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 27 Feb 2023 08:33:36 +0000 Subject: [PATCH 1972/4345] tcp: tcp_check_req() can be called from process context [ Upstream commit 580f98cc33a260bb8c6a39ae2921b29586b84fdf ] This is a follow up of commit 0a375c822497 ("tcp: tcp_rtx_synack() can be called from process context"). Frederick Lawler reported another "__this_cpu_add() in preemptible" warning caused by the same reason. In my former patch I took care of tcp_rtx_synack() but forgot that tcp_check_req() also contained some SNMP updates. Note that some parts of tcp_check_req() always run in BH context, I added a comment to clarify this. Fixes: 8336886f786f ("tcp: TCP Fast Open Server - support TFO listeners") Link: https://lore.kernel.org/netdev/8cd33923-a21d-397c-e46b-2a068c287b03@cloudflare.com/T/ Signed-off-by: Eric Dumazet Reported-by: Frederick Lawler Tested-by: Frederick Lawler Link: https://lore.kernel.org/r/20230227083336.4153089-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_minisocks.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e42312321191..8d854feebdb0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -565,6 +565,9 @@ EXPORT_SYMBOL(tcp_create_openreq_child); * validation and inside tcp_v4_reqsk_send_ack(). Can we do better? * * We don't need to initialize tmp_opt.sack_ok as we don't use the results + * + * Note: If @fastopen is true, this can be called from process context. + * Otherwise, this is from BH context. */ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, @@ -717,7 +720,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, &tcp_rsk(req)->last_oow_ack_time)) req->rsk_ops->send_ack(sk, skb, req); if (paws_reject) - __NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); return NULL; } @@ -736,7 +739,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * "fourth, check the SYN bit" */ if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) { - __TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); goto embryonic_reset; } From 3e734e694181b27687ce17da3229aa8edfd21760 Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Mon, 27 Feb 2023 15:21:41 -0500 Subject: [PATCH 1973/4345] vc_screen: modify vcs_size() handling in vcs_read() [ Upstream commit 46d733d0efc79bc8430d63b57ab88011806d5180 ] Restore the vcs_size() handling in vcs_read() to what it had been in previous version. Fixes: 226fae124b2d ("vc_screen: move load of struct vc_data pointer in vcs_read() to avoid UAF") Suggested-by: Jiri Slaby Signed-off-by: George Kennedy Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- drivers/tty/vt/vc_screen.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 71e091f879f0..1dc07f9214d5 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -415,10 +415,8 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) */ size = vcs_size(vc, attr, uni_mode); if (size < 0) { - if (read) - break; ret = size; - goto unlock_out; + break; } if (pos >= size) break; From 555f315832ecc4ab9ffc94fbaea77ad3b5e98dd5 Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Thu, 29 Dec 2022 15:53:19 -0600 Subject: [PATCH 1974/4345] rtc: sun6i: Always export the internal oscillator [ Upstream commit 344f4030f6c50a9db2d03021884c4bf36191b53a ] On all variants of the hardware, the internal oscillator is one possible parent for the AR100 clock. It needs to be exported so we can model that relationship correctly in the devicetree. Fixes: c56afc1844d6 ("rtc: sun6i: Expose internal oscillator through device tree") Signed-off-by: Samuel Holland Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20221229215319.14145-1-samuel@sholland.org Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-sun6i.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index 52b36b7c6129..a72856fb5252 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -128,7 +128,6 @@ struct sun6i_rtc_clk_data { unsigned int fixed_prescaler : 16; unsigned int has_prescaler : 1; unsigned int has_out_clk : 1; - unsigned int export_iosc : 1; unsigned int has_losc_en : 1; unsigned int has_auto_swt : 1; }; @@ -260,10 +259,8 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, /* Yes, I know, this is ugly. */ sun6i_rtc = rtc; - /* Only read IOSC name from device tree if it is exported */ - if (rtc->data->export_iosc) - of_property_read_string_index(node, "clock-output-names", 2, - &iosc_name); + of_property_read_string_index(node, "clock-output-names", 2, + &iosc_name); rtc->int_osc = clk_hw_register_fixed_rate_with_accuracy(NULL, iosc_name, @@ -304,13 +301,10 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, goto err_register; } - clk_data->num = 2; + clk_data->num = 3; clk_data->hws[0] = &rtc->hw; clk_data->hws[1] = __clk_get_hw(rtc->ext_losc); - if (rtc->data->export_iosc) { - clk_data->hws[2] = rtc->int_osc; - clk_data->num = 3; - } + clk_data->hws[2] = rtc->int_osc; of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); return; @@ -350,7 +344,6 @@ static const struct sun6i_rtc_clk_data sun8i_h3_rtc_data = { .fixed_prescaler = 32, .has_prescaler = 1, .has_out_clk = 1, - .export_iosc = 1, }; static void __init sun8i_h3_rtc_clk_init(struct device_node *node) @@ -368,7 +361,6 @@ static const struct sun6i_rtc_clk_data sun50i_h6_rtc_data = { .fixed_prescaler = 32, .has_prescaler = 1, .has_out_clk = 1, - .export_iosc = 1, .has_losc_en = 1, .has_auto_swt = 1, }; From af5f9a47614755023d615f0ba4fd35e9e490f0fc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 14 Feb 2023 14:28:08 +0100 Subject: [PATCH 1975/4345] scsi: ipr: Work around fortify-string warning [ Upstream commit ee4e7dfe4ffc9ca50c6875757bd119abfe22b5c5 ] The ipr_log_vpd_compact() function triggers a fortified memcpy() warning about a potential string overflow with all versions of clang: In file included from drivers/scsi/ipr.c:43: In file included from include/linux/string.h:254: include/linux/fortify-string.h:520:4: error: call to '__write_overflow_field' declared with 'warning' attribute: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror,-Wattribute-warning] __write_overflow_field(p_size_field, size); ^ include/linux/fortify-string.h:520:4: error: call to '__write_overflow_field' declared with 'warning' attribute: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror,-Wattribute-warning] 2 errors generated. I don't see anything actually wrong with the function, but this is the only instance I can reproduce of the fortification going wrong in the kernel at the moment, so the easiest solution may be to rewrite the function into something that does not trigger the warning. Instead of having a combined buffer for vendor/device/serial strings, use three separate local variables and just truncate the whitespace individually. Link: https://lore.kernel.org/r/20230214132831.2118392-1-arnd@kernel.org Cc: Kees Cook Fixes: 8cf093e275d0 ("[SCSI] ipr: Improved dual adapter errors") Signed-off-by: Arnd Bergmann Reviewed-by: Damien Le Moal Reviewed-by: Kees Cook Acked-by: Brian King Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/ipr.c | 41 +++++++++++++++++++++-------------------- 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index a5e6fbd86ad4..8c376736a8f5 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -1516,23 +1516,22 @@ static void ipr_process_ccn(struct ipr_cmnd *ipr_cmd) } /** - * strip_and_pad_whitespace - Strip and pad trailing whitespace. - * @i: index into buffer - * @buf: string to modify + * strip_whitespace - Strip and pad trailing whitespace. + * @i: size of buffer + * @buf: string to modify * - * This function will strip all trailing whitespace, pad the end - * of the string with a single space, and NULL terminate the string. + * This function will strip all trailing whitespace and + * NUL terminate the string. * - * Return value: - * new length of string **/ -static int strip_and_pad_whitespace(int i, char *buf) +static void strip_whitespace(int i, char *buf) { + if (i < 1) + return; + i--; while (i && buf[i] == ' ') i--; - buf[i+1] = ' '; - buf[i+2] = '\0'; - return i + 2; + buf[i+1] = '\0'; } /** @@ -1547,19 +1546,21 @@ static int strip_and_pad_whitespace(int i, char *buf) static void ipr_log_vpd_compact(char *prefix, struct ipr_hostrcb *hostrcb, struct ipr_vpd *vpd) { - char buffer[IPR_VENDOR_ID_LEN + IPR_PROD_ID_LEN + IPR_SERIAL_NUM_LEN + 3]; - int i = 0; + char vendor_id[IPR_VENDOR_ID_LEN + 1]; + char product_id[IPR_PROD_ID_LEN + 1]; + char sn[IPR_SERIAL_NUM_LEN + 1]; - memcpy(buffer, vpd->vpids.vendor_id, IPR_VENDOR_ID_LEN); - i = strip_and_pad_whitespace(IPR_VENDOR_ID_LEN - 1, buffer); + memcpy(vendor_id, vpd->vpids.vendor_id, IPR_VENDOR_ID_LEN); + strip_whitespace(IPR_VENDOR_ID_LEN, vendor_id); - memcpy(&buffer[i], vpd->vpids.product_id, IPR_PROD_ID_LEN); - i = strip_and_pad_whitespace(i + IPR_PROD_ID_LEN - 1, buffer); + memcpy(product_id, vpd->vpids.product_id, IPR_PROD_ID_LEN); + strip_whitespace(IPR_PROD_ID_LEN, product_id); - memcpy(&buffer[i], vpd->sn, IPR_SERIAL_NUM_LEN); - buffer[IPR_SERIAL_NUM_LEN + i] = '\0'; + memcpy(sn, vpd->sn, IPR_SERIAL_NUM_LEN); + strip_whitespace(IPR_SERIAL_NUM_LEN, sn); - ipr_hcam_err(hostrcb, "%s VPID/SN: %s\n", prefix, buffer); + ipr_hcam_err(hostrcb, "%s VPID/SN: %s %s %s\n", prefix, + vendor_id, product_id, sn); } /** From c79a924ed6afac1708dfd370ba66bcf6a852ced6 Mon Sep 17 00:00:00 2001 From: Zhong Jinghua Date: Tue, 21 Feb 2023 17:50:27 +0800 Subject: [PATCH 1976/4345] loop: loop_set_status_from_info() check before assignment [ Upstream commit 9f6ad5d533d1c71e51bdd06a5712c4fbc8768dfa ] In loop_set_status_from_info(), lo->lo_offset and lo->lo_sizelimit should be checked before reassignment, because if an overflow error occurs, the original correct value will be changed to the wrong value, and it will not be changed back. More, the original patch did not solve the problem, the value was set and ioctl returned an error, but the subsequent io used the value in the loop driver, which still caused an alarm: loop_handle_cmd do_req_filebacked loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; lo_rw_aio cmd->iocb.ki_pos = pos Fixes: c490a0b5a4f3 ("loop: Check for overflow while configuring loop") Signed-off-by: Zhong Jinghua Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20230221095027.3656193-1-zhongjinghua@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/loop.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index b10410585a74..d86fbea54652 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1029,13 +1029,13 @@ loop_set_status_from_info(struct loop_device *lo, if (err) return err; + /* Avoid assigning overflow values */ + if (info->lo_offset > LLONG_MAX || info->lo_sizelimit > LLONG_MAX) + return -EOVERFLOW; + lo->lo_offset = info->lo_offset; lo->lo_sizelimit = info->lo_sizelimit; - /* loff_t vars have been assigned __u64 */ - if (lo->lo_offset < 0 || lo->lo_sizelimit < 0) - return -EOVERFLOW; - memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE); lo->lo_file_name[LO_NAME_SIZE-1] = 0; From c8e7c0ec458c677d2c55635c22a7118d5b303abe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Fri, 24 Feb 2023 11:45:51 +0100 Subject: [PATCH 1977/4345] ASoC: adau7118: don't disable regulators on device unbind MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b5bfa7277ee7d944421e0ef193586c6e34d7492c ] The regulators are supposed to be controlled through the set_bias_level() component callback. Moreover, the regulators are not enabled during probe and so, this would lead to a regulator unbalanced use count. Fixes: ca514c0f12b02 ("ASOC: Add ADAU7118 8 Channel PDM-to-I2S/TDM Converter driver") Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20230224104551.1139981-1-nuno.sa@analog.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/adau7118.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) diff --git a/sound/soc/codecs/adau7118.c b/sound/soc/codecs/adau7118.c index 841229dcbca1..305f294b7710 100644 --- a/sound/soc/codecs/adau7118.c +++ b/sound/soc/codecs/adau7118.c @@ -445,22 +445,6 @@ static const struct snd_soc_component_driver adau7118_component_driver = { .non_legacy_dai_naming = 1, }; -static void adau7118_regulator_disable(void *data) -{ - struct adau7118_data *st = data; - int ret; - /* - * If we fail to disable DVDD, don't bother in trying IOVDD. We - * actually don't want to be left in the situation where DVDD - * is enabled and IOVDD is disabled. - */ - ret = regulator_disable(st->dvdd); - if (ret) - return; - - regulator_disable(st->iovdd); -} - static int adau7118_regulator_setup(struct adau7118_data *st) { st->iovdd = devm_regulator_get(st->dev, "iovdd"); @@ -482,8 +466,7 @@ static int adau7118_regulator_setup(struct adau7118_data *st) regcache_cache_only(st->map, true); } - return devm_add_action_or_reset(st->dev, adau7118_regulator_disable, - st); + return 0; } static int adau7118_parset_dt(const struct adau7118_data *st) From 2bc1f260ede1274a59db706768b6292a24d45128 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 2 Feb 2022 19:23:32 +0000 Subject: [PATCH 1978/4345] ASoC: zl38060: Remove spurious gpiolib select [ Upstream commit 8e70aaae32b72d3088d18a3447b67112b3f5979a ] The usage of GPIOs is optional in the code so don't force on gpiolib when building it, avoiding warnings in randconfigs. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20220202192333.3655269-6-broonie@kernel.org Signed-off-by: Mark Brown Stable-dep-of: 0de2cc3707b6 ("ASoC: zl38060 add gpiolib dependency") Signed-off-by: Sasha Levin --- sound/soc/codecs/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 25f331551f68..a96f18a9479e 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1701,7 +1701,6 @@ config SND_SOC_WSA881X config SND_SOC_ZL38060 tristate "Microsemi ZL38060 Connected Home Audio Processor" depends on SPI_MASTER - select GPIOLIB select REGMAP help Support for ZL38060 Connected Home Audio Processor from Microsemi, From 01829cb8708912ab0a2ae50b35c04a929045c5bf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 27 Feb 2023 09:58:26 +0100 Subject: [PATCH 1979/4345] ASoC: zl38060 add gpiolib dependency [ Upstream commit 0de2cc3707b6b6e2ad40bd24ce09a5c1f65d01e1 ] Without gpiolib, this driver fails to link: arm-linux-gnueabi-ld: sound/soc/codecs/zl38060.o: in function `chip_gpio_get': zl38060.c:(.text+0x30): undefined reference to `gpiochip_get_data' arm-linux-gnueabi-ld: sound/soc/codecs/zl38060.o: in function `zl38_spi_probe': zl38060.c:(.text+0xa18): undefined reference to `devm_gpiochip_add_data_with_key' This appears to have been in the driver since the start, but is hard to hit in randconfig testing since gpiolib is almost always selected by something else. Fixes: 52e8a94baf90 ("ASoC: Add initial ZL38060 driver") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230227085850.2503725-1-arnd@kernel.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index a96f18a9479e..f1c9e563994b 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1701,6 +1701,7 @@ config SND_SOC_WSA881X config SND_SOC_ZL38060 tristate "Microsemi ZL38060 Connected Home Audio Processor" depends on SPI_MASTER + depends on GPIOLIB select REGMAP help Support for ZL38060 Connected Home Audio Processor from Microsemi, From f73134231fa23e0856c15010db5f5c03693c1e92 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 27 Feb 2023 13:06:50 +0300 Subject: [PATCH 1980/4345] thermal: intel: quark_dts: fix error pointer dereference [ Upstream commit f1b930e740811d416de4d2074da48b6633a672c8 ] If alloc_soc_dts() fails, then we can just return. Trying to free "soc_dts" will lead to an Oops. Fixes: 8c1876939663 ("thermal: intel Quark SoC X1000 DTS thermal driver") Signed-off-by: Dan Carpenter Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/thermal/intel/intel_quark_dts_thermal.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/drivers/thermal/intel/intel_quark_dts_thermal.c b/drivers/thermal/intel/intel_quark_dts_thermal.c index 3eafc6b0e6c3..b43fbd5eaa6b 100644 --- a/drivers/thermal/intel/intel_quark_dts_thermal.c +++ b/drivers/thermal/intel/intel_quark_dts_thermal.c @@ -415,22 +415,14 @@ MODULE_DEVICE_TABLE(x86cpu, qrk_thermal_ids); static int __init intel_quark_thermal_init(void) { - int err = 0; - if (!x86_match_cpu(qrk_thermal_ids) || !iosf_mbi_available()) return -ENODEV; soc_dts = alloc_soc_dts(); - if (IS_ERR(soc_dts)) { - err = PTR_ERR(soc_dts); - goto err_free; - } + if (IS_ERR(soc_dts)) + return PTR_ERR(soc_dts); return 0; - -err_free: - free_soc_dts(soc_dts); - return err; } static void __exit intel_quark_thermal_exit(void) From e30b26e746175a775921b948479308644336b796 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 25 Feb 2023 21:39:52 -0800 Subject: [PATCH 1981/4345] thermal: intel: BXT_PMIC: select REGMAP instead of depending on it [ Upstream commit 1467fb960349dfa5e300658f1a409dde2cfb0c51 ] REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it. Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues. Therefore, change the use of "depends on REGMAP" to "select REGMAP". Fixes: b474303ffd57 ("thermal: add Intel BXT WhiskeyCove PMIC thermal driver") Signed-off-by: Randy Dunlap Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/thermal/intel/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig index 8025b21f43fa..b5427579fae5 100644 --- a/drivers/thermal/intel/Kconfig +++ b/drivers/thermal/intel/Kconfig @@ -60,7 +60,8 @@ endmenu config INTEL_BXT_PMIC_THERMAL tristate "Intel Broxton PMIC thermal driver" - depends on X86 && INTEL_SOC_PMIC_BXTWC && REGMAP + depends on X86 && INTEL_SOC_PMIC_BXTWC + select REGMAP help Select this driver for Intel Broxton PMIC with ADC channels monitoring system temperature measurements and alerts. From 25c9fba724bdfa66e4f0d19e8b3d331eca798be9 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Fri, 13 Jan 2023 20:55:01 +0800 Subject: [PATCH 1982/4345] tracing: Add NULL checks for buffer in ring_buffer_free_read_page() [ Upstream commit 3e4272b9954094907f16861199728f14002fcaf6 ] In a previous commit 7433632c9ff6, buffer, buffer->buffers and buffer->buffers[cpu] in ring_buffer_wake_waiters() can be NULL, and thus the related checks are added. However, in the same call stack, these variables are also used in ring_buffer_free_read_page(): tracing_buffers_release() ring_buffer_wake_waiters(iter->array_buffer->buffer) cpu_buffer = buffer->buffers[cpu] -> Add checks by previous commit ring_buffer_free_read_page(iter->array_buffer->buffer) cpu_buffer = buffer->buffers[cpu] -> No check Thus, to avod possible null-pointer derefernces, the related checks should be added. These results are reported by a static tool designed by myself. Link: https://lkml.kernel.org/r/20230113125501.760324-1-baijiaju1990@gmail.com Reported-by: TOTE Robot Signed-off-by: Jia-Ju Bai Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/ring_buffer.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c00463613eab..70da6f3212bc 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5302,11 +5302,16 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); */ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data) { - struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_per_cpu *cpu_buffer; struct buffer_data_page *bpage = data; struct page *page = virt_to_page(bpage); unsigned long flags; + if (!buffer || !buffer->buffers || !buffer->buffers[cpu]) + return; + + cpu_buffer = buffer->buffers[cpu]; + /* If the page is still in use someplace else, we can't reuse it */ if (page_ref_count(page) > 1) goto out; From 07fb5653366c86fad87d84bad9d5c3f6fbc1e307 Mon Sep 17 00:00:00 2001 From: Darrell Kavanagh Date: Wed, 15 Feb 2023 11:50:45 +0000 Subject: [PATCH 1983/4345] firmware/efi sysfb_efi: Add quirk for Lenovo IdeaPad Duet 3 [ Upstream commit e1d447157f232c650e6f32c9fb89ff3d0207c69a ] Another Lenovo convertable which reports a landscape resolution of 1920x1200 with a pitch of (1920 * 4) bytes, while the actual framebuffer has a resolution of 1200x1920 with a pitch of (1200 * 4) bytes. Signed-off-by: Darrell Kavanagh Reviewed-by: Hans de Goede Signed-off-by: Ard Biesheuvel Signed-off-by: Sasha Levin --- arch/x86/kernel/sysfb_efi.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index 653b7f617b61..9ea65611fba0 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -264,6 +264,14 @@ static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { "Lenovo ideapad D330-10IGM"), }, }, + { + /* Lenovo IdeaPad Duet 3 10IGL5 with 1200x1920 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "IdeaPad Duet 3 10IGL5"), + }, + }, {}, }; From 903b91cea77acc79a6b58553023d6ea4d0aa3dd7 Mon Sep 17 00:00:00 2001 From: Souradeep Chowdhury Date: Wed, 22 Feb 2023 08:27:49 +0900 Subject: [PATCH 1984/4345] bootconfig: Increase max nodes of bootconfig from 1024 to 8192 for DCC support [ Upstream commit 6c40624930c58529185a257380442547580ed837 ] The Data Capture and Compare(DCC) is a debugging tool that uses the bootconfig for configuring the register values during boot-time. Increase the max nodes supported by bootconfig to cater to the requirements of the Data Capture and Compare Driver. Link: https://lore.kernel.org/all/1674536682-18404-1-git-send-email-quic_schowdhu@quicinc.com/ Signed-off-by: Souradeep Chowdhury Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Sasha Levin --- include/linux/bootconfig.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 2696eb0fc149..df9cbf02d030 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -29,7 +29,7 @@ struct xbc_node { /* Maximum size of boot config is 32KB - 1 */ #define XBC_DATA_MAX (XBC_VALUE - 1) -#define XBC_NODE_MAX 1024 +#define XBC_NODE_MAX 8192 #define XBC_KEYLEN_MAX 256 #define XBC_DEPTH_MAX 16 From 754e81ff44061dda68da0fd4ef51bd1aa9fbf2cf Mon Sep 17 00:00:00 2001 From: Liang He Date: Thu, 5 Jan 2023 14:10:55 +0800 Subject: [PATCH 1985/4345] mfd: arizona: Use pm_runtime_resume_and_get() to prevent refcnt leak [ Upstream commit 4414a7ab80cebf715045e3c4d465feefbad21139 ] In arizona_clk32k_enable(), we should use pm_runtime_resume_and_get() as pm_runtime_get_sync() will increase the refcnt even when it returns an error. Signed-off-by: Liang He Acked-by: Charles Keepax Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230105061055.1509261-1-windhl@126.com Signed-off-by: Sasha Levin --- drivers/mfd/arizona-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index 000cb82023e3..afdc49083625 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -45,7 +45,7 @@ int arizona_clk32k_enable(struct arizona *arizona) if (arizona->clk32k_ref == 1) { switch (arizona->pdata.clk32k_src) { case ARIZONA_32KZ_MCLK1: - ret = pm_runtime_get_sync(arizona->dev); + ret = pm_runtime_resume_and_get(arizona->dev); if (ret != 0) goto err_ref; ret = clk_prepare_enable(arizona->mclk[ARIZONA_MCLK1]); From 76752888edcc3d01dbdf8886bc65af6767803471 Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Mon, 9 Jan 2023 14:04:29 -0500 Subject: [PATCH 1986/4345] IB/hfi1: Update RMT size calculation [ Upstream commit 892ede5a77f337831609fb9c248ac60948061894 ] Fix possible RMT overflow: Use the correct netdev size. Don't allow adjusted user contexts to go negative. Fix QOS calculation: Send kernel context count as an argument since dd->n_krcv_queues is not yet set up in earliest call. Do not include the control context in the QOS calculation. Use the same sized variable to find the max of krcvq[] entries. Update the RMT count explanation to make more sense. Signed-off-by: Dean Luick Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/167329106946.1472990.18385495251650939054.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/chip.c | 59 +++++++++++++++++-------------- 1 file changed, 32 insertions(+), 27 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 88476a1a601a..4b41f35668b2 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -1097,7 +1097,7 @@ static void read_link_down_reason(struct hfi1_devdata *dd, u8 *ldr); static void handle_temp_err(struct hfi1_devdata *dd); static void dc_shutdown(struct hfi1_devdata *dd); static void dc_start(struct hfi1_devdata *dd); -static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp, +static int qos_rmt_entries(unsigned int n_krcv_queues, unsigned int *mp, unsigned int *np); static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd); static int wait_link_transfer_active(struct hfi1_devdata *dd, int wait_ms); @@ -13403,7 +13403,6 @@ static int set_up_context_variables(struct hfi1_devdata *dd) int ret; unsigned ngroups; int rmt_count; - int user_rmt_reduced; u32 n_usr_ctxts; u32 send_contexts = chip_send_contexts(dd); u32 rcv_contexts = chip_rcv_contexts(dd); @@ -13462,28 +13461,34 @@ static int set_up_context_variables(struct hfi1_devdata *dd) (num_kernel_contexts + n_usr_ctxts), &node_affinity.real_cpu_mask); /* - * The RMT entries are currently allocated as shown below: - * 1. QOS (0 to 128 entries); - * 2. FECN (num_kernel_context - 1 + num_user_contexts + - * num_netdev_contexts); - * 3. netdev (num_netdev_contexts). - * It should be noted that FECN oversubscribe num_netdev_contexts - * entries of RMT because both netdev and PSM could allocate any receive - * context between dd->first_dyn_alloc_text and dd->num_rcv_contexts, - * and PSM FECN must reserve an RMT entry for each possible PSM receive - * context. + * RMT entries are allocated as follows: + * 1. QOS (0 to 128 entries) + * 2. FECN (num_kernel_context - 1 [a] + num_user_contexts + + * num_netdev_contexts [b]) + * 3. netdev (NUM_NETDEV_MAP_ENTRIES) + * + * Notes: + * [a] Kernel contexts (except control) are included in FECN if kernel + * TID_RDMA is active. + * [b] Netdev and user contexts are randomly allocated from the same + * context pool, so FECN must cover all contexts in the pool. */ - rmt_count = qos_rmt_entries(dd, NULL, NULL) + (num_netdev_contexts * 2); - if (HFI1_CAP_IS_KSET(TID_RDMA)) - rmt_count += num_kernel_contexts - 1; - if (rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) { - user_rmt_reduced = NUM_MAP_ENTRIES - rmt_count; - dd_dev_err(dd, - "RMT size is reducing the number of user receive contexts from %u to %d\n", - n_usr_ctxts, - user_rmt_reduced); - /* recalculate */ - n_usr_ctxts = user_rmt_reduced; + rmt_count = qos_rmt_entries(num_kernel_contexts - 1, NULL, NULL) + + (HFI1_CAP_IS_KSET(TID_RDMA) ? num_kernel_contexts - 1 + : 0) + + n_usr_ctxts + + num_netdev_contexts + + NUM_NETDEV_MAP_ENTRIES; + if (rmt_count > NUM_MAP_ENTRIES) { + int over = rmt_count - NUM_MAP_ENTRIES; + /* try to squish user contexts, minimum of 1 */ + if (over >= n_usr_ctxts) { + dd_dev_err(dd, "RMT overflow: reduce the requested number of contexts\n"); + return -EINVAL; + } + dd_dev_err(dd, "RMT overflow: reducing # user contexts from %u to %u\n", + n_usr_ctxts, n_usr_ctxts - over); + n_usr_ctxts -= over; } /* the first N are kernel contexts, the rest are user/netdev contexts */ @@ -14340,15 +14345,15 @@ static void clear_rsm_rule(struct hfi1_devdata *dd, u8 rule_index) } /* return the number of RSM map table entries that will be used for QOS */ -static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp, +static int qos_rmt_entries(unsigned int n_krcv_queues, unsigned int *mp, unsigned int *np) { int i; unsigned int m, n; - u8 max_by_vl = 0; + uint max_by_vl = 0; /* is QOS active at all? */ - if (dd->n_krcv_queues <= MIN_KERNEL_KCTXTS || + if (n_krcv_queues < MIN_KERNEL_KCTXTS || num_vls == 1 || krcvqsset <= 1) goto no_qos; @@ -14406,7 +14411,7 @@ static void init_qos(struct hfi1_devdata *dd, struct rsm_map_table *rmt) if (!rmt) goto bail; - rmt_entries = qos_rmt_entries(dd, &m, &n); + rmt_entries = qos_rmt_entries(dd->n_krcv_queues - 1, &m, &n); if (rmt_entries == 0) goto bail; qpns_per_vl = 1 << m; From d8aa2e1ae6426d7cbddf1735aed1a63ddf0e6909 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Tue, 20 Sep 2022 16:04:55 +0200 Subject: [PATCH 1987/4345] media: uvcvideo: Handle cameras with invalid descriptors [ Upstream commit 41ddb251c68ac75c101d3a50a68c4629c9055e4c ] If the source entity does not contain any pads, do not create a link. Reported-by: syzbot Signed-off-by: Ricardo Ribalda Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/media/usb/uvc/uvc_entity.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/usb/uvc/uvc_entity.c b/drivers/media/usb/uvc/uvc_entity.c index ca3a9c2eec27..7c9895377118 100644 --- a/drivers/media/usb/uvc/uvc_entity.c +++ b/drivers/media/usb/uvc/uvc_entity.c @@ -37,7 +37,7 @@ static int uvc_mc_create_links(struct uvc_video_chain *chain, continue; remote = uvc_entity_by_id(chain->dev, entity->baSourceID[i]); - if (remote == NULL) + if (remote == NULL || remote->num_pads == 0) return -EINVAL; source = (UVC_ENTITY_TYPE(remote) == UVC_TT_STREAMING) From 23f9bead358de7a25c815e81c62243b48a186fc0 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 25 Oct 2022 16:41:01 +0200 Subject: [PATCH 1988/4345] media: uvcvideo: Handle errors from calls to usb_string [ Upstream commit 4867bb590ae445bcfaa711a86b603c97e94574b3 ] On a Webcam from Quanta, we see the following error. usb 3-5: New USB device found, idVendor=0408, idProduct=30d2, bcdDevice= 0.03 usb 3-5: New USB device strings: Mfr=3, Product=1, SerialNumber=2 usb 3-5: Product: USB2.0 HD UVC WebCam usb 3-5: Manufacturer: Quanta usb 3-5: SerialNumber: 0x0001 ... uvcvideo: Found UVC 1.10 device USB2.0 HD UVC WebCam (0408:30d2) uvcvideo: Failed to initialize entity for entity 5 uvcvideo: Failed to register entities (-22). The Webcam reports an entity of type UVC_VC_EXTENSION_UNIT. It reports a string index of '7' associated with that entity. The attempt to read that string from the camera fails with error -32 (-EPIPE). usb_string() returns that error, but it is ignored. As result, the entity name is empty. This later causes v4l2_device_register_subdev() to return -EINVAL, and no entities are registered as result. While this appears to be a firmware problem with the camera, the kernel should still handle the situation gracefully. To do that, check the return value from usb_string(). If it reports an error, assign the entity's default name. Signed-off-by: Guenter Roeck Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/media/usb/uvc/uvc_driver.c | 48 ++++++++++++------------------ 1 file changed, 19 insertions(+), 29 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 282f3d2388cc..2be18fa7982d 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -1121,10 +1121,8 @@ static int uvc_parse_vendor_control(struct uvc_device *dev, + n; memcpy(unit->extension.bmControls, &buffer[23+p], 2*n); - if (buffer[24+p+2*n] != 0) - usb_string(udev, buffer[24+p+2*n], unit->name, - sizeof(unit->name)); - else + if (buffer[24+p+2*n] == 0 || + usb_string(udev, buffer[24+p+2*n], unit->name, sizeof(unit->name)) < 0) sprintf(unit->name, "Extension %u", buffer[3]); list_add_tail(&unit->list, &dev->entities); @@ -1249,15 +1247,15 @@ static int uvc_parse_standard_control(struct uvc_device *dev, memcpy(term->media.bmTransportModes, &buffer[10+n], p); } - if (buffer[7] != 0) - usb_string(udev, buffer[7], term->name, - sizeof(term->name)); - else if (UVC_ENTITY_TYPE(term) == UVC_ITT_CAMERA) - sprintf(term->name, "Camera %u", buffer[3]); - else if (UVC_ENTITY_TYPE(term) == UVC_ITT_MEDIA_TRANSPORT_INPUT) - sprintf(term->name, "Media %u", buffer[3]); - else - sprintf(term->name, "Input %u", buffer[3]); + if (buffer[7] == 0 || + usb_string(udev, buffer[7], term->name, sizeof(term->name)) < 0) { + if (UVC_ENTITY_TYPE(term) == UVC_ITT_CAMERA) + sprintf(term->name, "Camera %u", buffer[3]); + if (UVC_ENTITY_TYPE(term) == UVC_ITT_MEDIA_TRANSPORT_INPUT) + sprintf(term->name, "Media %u", buffer[3]); + else + sprintf(term->name, "Input %u", buffer[3]); + } list_add_tail(&term->list, &dev->entities); break; @@ -1289,10 +1287,8 @@ static int uvc_parse_standard_control(struct uvc_device *dev, memcpy(term->baSourceID, &buffer[7], 1); - if (buffer[8] != 0) - usb_string(udev, buffer[8], term->name, - sizeof(term->name)); - else + if (buffer[8] == 0 || + usb_string(udev, buffer[8], term->name, sizeof(term->name)) < 0) sprintf(term->name, "Output %u", buffer[3]); list_add_tail(&term->list, &dev->entities); @@ -1314,10 +1310,8 @@ static int uvc_parse_standard_control(struct uvc_device *dev, memcpy(unit->baSourceID, &buffer[5], p); - if (buffer[5+p] != 0) - usb_string(udev, buffer[5+p], unit->name, - sizeof(unit->name)); - else + if (buffer[5+p] == 0 || + usb_string(udev, buffer[5+p], unit->name, sizeof(unit->name)) < 0) sprintf(unit->name, "Selector %u", buffer[3]); list_add_tail(&unit->list, &dev->entities); @@ -1347,10 +1341,8 @@ static int uvc_parse_standard_control(struct uvc_device *dev, if (dev->uvc_version >= 0x0110) unit->processing.bmVideoStandards = buffer[9+n]; - if (buffer[8+n] != 0) - usb_string(udev, buffer[8+n], unit->name, - sizeof(unit->name)); - else + if (buffer[8+n] == 0 || + usb_string(udev, buffer[8+n], unit->name, sizeof(unit->name)) < 0) sprintf(unit->name, "Processing %u", buffer[3]); list_add_tail(&unit->list, &dev->entities); @@ -1378,10 +1370,8 @@ static int uvc_parse_standard_control(struct uvc_device *dev, unit->extension.bmControls = (u8 *)unit + sizeof(*unit); memcpy(unit->extension.bmControls, &buffer[23+p], n); - if (buffer[23+p+n] != 0) - usb_string(udev, buffer[23+p+n], unit->name, - sizeof(unit->name)); - else + if (buffer[23+p+n] == 0 || + usb_string(udev, buffer[23+p+n], unit->name, sizeof(unit->name)) < 0) sprintf(unit->name, "Extension %u", buffer[3]); list_add_tail(&unit->list, &dev->entities); From 78b1fdc47e4e0a1ea1846f9b5913bfec0be00bea Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Wed, 4 Jan 2023 11:45:23 +0100 Subject: [PATCH 1989/4345] media: uvcvideo: Quirk for autosuspend in Logitech B910 and C910 [ Upstream commit 136effa754b57632f99574fc4a3433e0cfc031d9 ] Logitech B910 and C910 firmware are unable to recover from a USB autosuspend. When it resumes, the device is in a state where it only produces invalid frames. Eg: $ echo 0xFFFF > /sys/module/uvcvideo/parameters/trace # enable verbose log $ yavta -c1 -n1 --file='frame#.jpg' --format MJPEG --size=1920x1080 /dev/video1 [350438.435219] uvcvideo: uvc_v4l2_open [350438.529794] uvcvideo: Resuming interface 2 [350438.529801] uvcvideo: Resuming interface 3 [350438.529991] uvcvideo: Trying format 0x47504a4d (MJPG): 1920x1080. [350438.529996] uvcvideo: Using default frame interval 33333.3 us (30.0 fps). [350438.551496] uvcvideo: uvc_v4l2_mmap [350438.555890] uvcvideo: Device requested 3060 B/frame bandwidth. [350438.555896] uvcvideo: Selecting alternate setting 11 (3060 B/frame bandwidth). [350438.556362] uvcvideo: Allocated 5 URB buffers of 32x3060 bytes each. [350439.316468] uvcvideo: Marking buffer as bad (error bit set). [350439.316475] uvcvideo: Frame complete (EOF found). [350439.316477] uvcvideo: EOF in empty payload. [350439.316484] uvcvideo: frame 1 stats: 149/261/417 packets, 1/149/417 pts (early initial), 416/417 scr, last pts/stc/sof 2976325734/2978107243/249 [350439.384510] uvcvideo: Marking buffer as bad (error bit set). [350439.384516] uvcvideo: Frame complete (EOF found). [350439.384518] uvcvideo: EOF in empty payload. [350439.384525] uvcvideo: frame 2 stats: 265/379/533 packets, 1/265/533 pts (early initial), 532/533 scr, last pts/stc/sof 2979524454/2981305193/316 [350439.448472] uvcvideo: Marking buffer as bad (error bit set). [350439.448478] uvcvideo: Frame complete (EOF found). [350439.448480] uvcvideo: EOF in empty payload. [350439.448487] uvcvideo: frame 3 stats: 265/377/533 packets, 1/265/533 pts (early initial), 532/533 scr, last pts/stc/sof 2982723174/2984503144/382 ...(loop)... The devices can leave this invalid state if the alternate setting of the streaming interface is toggled. This patch adds a quirk for this device so it can be autosuspended properly. lsusb -v: Bus 001 Device 049: ID 046d:0821 Logitech, Inc. HD Webcam C910 Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 239 Miscellaneous Device bDeviceSubClass 2 bDeviceProtocol 1 Interface Association bMaxPacketSize0 64 idVendor 0x046d Logitech, Inc. idProduct 0x0821 HD Webcam C910 bcdDevice 0.10 iManufacturer 0 iProduct 0 iSerial 1 390022B0 bNumConfigurations 1 Signed-off-by: Ricardo Ribalda Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/media/usb/uvc/uvc_driver.c | 18 ++++++++++++++++++ drivers/media/usb/uvc/uvc_video.c | 11 +++++++++++ drivers/media/usb/uvc/uvcvideo.h | 1 + 3 files changed, 30 insertions(+) diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 2be18fa7982d..6334f99f1854 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -2555,6 +2555,24 @@ static const struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = (kernel_ulong_t)&uvc_quirk_probe_minmax }, + /* Logitech, Webcam C910 */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x046d, + .idProduct = 0x0821, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_WAKE_AUTOSUSPEND)}, + /* Logitech, Webcam B910 */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x046d, + .idProduct = 0x0823, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_WAKE_AUTOSUSPEND)}, /* Logitech Quickcam Fusion */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index f6373d678d25..d5a4e967883c 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -1903,6 +1903,17 @@ static int uvc_video_start_transfer(struct uvc_streaming *stream, uvc_trace(UVC_TRACE_VIDEO, "Selecting alternate setting %u " "(%u B/frame bandwidth).\n", altsetting, best_psize); + /* + * Some devices, namely the Logitech C910 and B910, are unable + * to recover from a USB autosuspend, unless the alternate + * setting of the streaming interface is toggled. + */ + if (stream->dev->quirks & UVC_QUIRK_WAKE_AUTOSUSPEND) { + usb_set_interface(stream->dev->udev, intfnum, + altsetting); + usb_set_interface(stream->dev->udev, intfnum, 0); + } + ret = usb_set_interface(stream->dev->udev, intfnum, altsetting); if (ret < 0) return ret; diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index c884020b2878..284200becbbd 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -203,6 +203,7 @@ #define UVC_QUIRK_RESTORE_CTRLS_ON_INIT 0x00000400 #define UVC_QUIRK_FORCE_Y8 0x00000800 #define UVC_QUIRK_FORCE_BPP 0x00001000 +#define UVC_QUIRK_WAKE_AUTOSUSPEND 0x00002000 /* Format flags */ #define UVC_FMT_FLAG_COMPRESSED 0x00000001 From c4d96503d67b2c4de9772521cac84e5f25218c7c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 5 Jan 2023 22:17:04 -0800 Subject: [PATCH 1990/4345] media: uvcvideo: Silence memcpy() run-time false positive warnings [ Upstream commit b839212988575c701aab4d3d9ca15e44c87e383c ] The memcpy() in uvc_video_decode_meta() intentionally copies across the length and flags members and into the trailing buf flexible array. Split the copy so that the compiler can better reason about (the lack of) buffer overflows here. Avoid the run-time false positive warning: memcpy: detected field-spanning write (size 12) of single field "&meta->length" at drivers/media/usb/uvc/uvc_video.c:1355 (size 1) Additionally fix a typo in the documentation for struct uvc_meta_buf. Reported-by: ionut_n2001@yahoo.com Link: https://bugzilla.kernel.org/show_bug.cgi?id=216810 Signed-off-by: Kees Cook Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Sasha Levin --- drivers/media/usb/uvc/uvc_video.c | 4 +++- include/uapi/linux/uvcvideo.h | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index d5a4e967883c..03dfe96bceba 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -1308,7 +1308,9 @@ static void uvc_video_decode_meta(struct uvc_streaming *stream, if (has_scr) memcpy(stream->clock.last_scr, scr, 6); - memcpy(&meta->length, mem, length); + meta->length = mem[0]; + meta->flags = mem[1]; + memcpy(meta->buf, &mem[2], length - 2); meta_buf->bytesused += length + sizeof(meta->ns) + sizeof(meta->sof); uvc_trace(UVC_TRACE_FRAME, diff --git a/include/uapi/linux/uvcvideo.h b/include/uapi/linux/uvcvideo.h index f80f05b3c423..214092366193 100644 --- a/include/uapi/linux/uvcvideo.h +++ b/include/uapi/linux/uvcvideo.h @@ -86,7 +86,7 @@ struct uvc_xu_control_query { * struct. The first two fields are added by the driver, they can be used for * clock synchronisation. The rest is an exact copy of a UVC payload header. * Only complete objects with complete buffers are included. Therefore it's - * always sizeof(meta->ts) + sizeof(meta->sof) + meta->length bytes large. + * always sizeof(meta->ns) + sizeof(meta->sof) + meta->length bytes large. */ struct uvc_meta_buf { __u64 ns; From e8a5efd5aefcc7de0f06983dd6038e4ce3a57632 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Thu, 19 Jan 2023 08:31:19 +0000 Subject: [PATCH 1991/4345] staging: emxx_udc: Add checks for dma_alloc_coherent() [ Upstream commit f6510a93cfd8c6c79b4dda0f2967cdc6df42eff4 ] As the dma_alloc_coherent may return NULL, the return value needs to be checked to avoid NULL poineter dereference. Signed-off-by: Yuan Can Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230119083119.16956-1-yuancan@huawei.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/staging/emxx_udc/emxx_udc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/staging/emxx_udc/emxx_udc.c b/drivers/staging/emxx_udc/emxx_udc.c index 3897f8e8f5e0..6870a33d4ccf 100644 --- a/drivers/staging/emxx_udc/emxx_udc.c +++ b/drivers/staging/emxx_udc/emxx_udc.c @@ -2591,10 +2591,15 @@ static int nbu2ss_ep_queue(struct usb_ep *_ep, req->unaligned = false; if (req->unaligned) { - if (!ep->virt_buf) + if (!ep->virt_buf) { ep->virt_buf = dma_alloc_coherent(udc->dev, PAGE_SIZE, &ep->phys_buf, GFP_ATOMIC | GFP_DMA); + if (!ep->virt_buf) { + spin_unlock_irqrestore(&udc->lock, flags); + return -ENOMEM; + } + } if (ep->epnum > 0) { if (ep->direct == USB_DIR_IN) memcpy(ep->virt_buf, req->req.buf, From 84ea44dc3e4ecb2632586238014bf6722aa5843b Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Fri, 9 Dec 2022 12:27:36 +0100 Subject: [PATCH 1992/4345] tty: fix out-of-bounds access in tty_driver_lookup_tty() [ Upstream commit db4df8e9d79e7d37732c1a1b560958e8dadfefa1 ] When specifying an invalid console= device like console=tty3270, tty_driver_lookup_tty() returns the tty struct without checking whether index is a valid number. To reproduce: qemu-system-x86_64 -enable-kvm -nographic -serial mon:stdio \ -kernel ../linux-build-x86/arch/x86/boot/bzImage \ -append "console=ttyS0 console=tty3270" This crashes with: [ 0.770599] BUG: kernel NULL pointer dereference, address: 00000000000000ef [ 0.771265] #PF: supervisor read access in kernel mode [ 0.771773] #PF: error_code(0x0000) - not-present page [ 0.772609] Oops: 0000 [#1] PREEMPT SMP PTI [ 0.774878] RIP: 0010:tty_open+0x268/0x6f0 [ 0.784013] chrdev_open+0xbd/0x230 [ 0.784444] ? cdev_device_add+0x80/0x80 [ 0.784920] do_dentry_open+0x1e0/0x410 [ 0.785389] path_openat+0xca9/0x1050 [ 0.785813] do_filp_open+0xaa/0x150 [ 0.786240] file_open_name+0x133/0x1b0 [ 0.786746] filp_open+0x27/0x50 [ 0.787244] console_on_rootfs+0x14/0x4d [ 0.787800] kernel_init_freeable+0x1e4/0x20d [ 0.788383] ? rest_init+0xc0/0xc0 [ 0.788881] kernel_init+0x11/0x120 [ 0.789356] ret_from_fork+0x22/0x30 Signed-off-by: Sven Schnelle Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/20221209112737.3222509-2-svens@linux.ibm.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/tty_io.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 669aef77a0bd..c37d2657308c 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1237,14 +1237,16 @@ static struct tty_struct *tty_driver_lookup_tty(struct tty_driver *driver, { struct tty_struct *tty; - if (driver->ops->lookup) + if (driver->ops->lookup) { if (!file) tty = ERR_PTR(-EIO); else tty = driver->ops->lookup(driver, file, idx); - else + } else { + if (idx >= driver->num) + return ERR_PTR(-EINVAL); tty = driver->ttys[idx]; - + } if (!IS_ERR(tty)) tty_kref_get(tty); return tty; From 0cb1f78d886bc3da43c714029ab35027c4e3208d Mon Sep 17 00:00:00 2001 From: Sherry Sun Date: Wed, 14 Dec 2022 11:11:35 +0800 Subject: [PATCH 1993/4345] tty: serial: fsl_lpuart: disable the CTS when send break signal [ Upstream commit c4c81db5cf8bc53d6160c3abf26d382c841aa434 ] LPUART IP has a bug that it treats the CTS as higher priority than the break signal, which cause the break signal sending through UARTCTRL_SBK may impacted by the CTS input if the HW flow control is enabled. Add this workaround patch to fix the IP bug, we can disable CTS before asserting SBK to avoid any interference from CTS, and re-enable it when break off. Such as for the bluetooth chip power save feature, host can let the BT chip get into sleep state by sending a UART break signal, and wake it up by turning off the UART break. If the BT chip enters the sleep mode successfully, it will pull up the CTS line, if the BT chip is woken up, it will pull down the CTS line. If without this workaround patch, the UART TX pin cannot send the break signal successfully as it affected by the BT CTS pin. After adding this patch, the BT power save feature can work well. Signed-off-by: Sherry Sun Link: https://lore.kernel.org/r/20221214031137.28815-2-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/fsl_lpuart.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 223695947b65..9cb0e8673f82 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1448,12 +1448,32 @@ static void lpuart_break_ctl(struct uart_port *port, int break_state) static void lpuart32_break_ctl(struct uart_port *port, int break_state) { - unsigned long temp; + unsigned long temp, modem; + struct tty_struct *tty; + unsigned int cflag = 0; + + tty = tty_port_tty_get(&port->state->port); + if (tty) { + cflag = tty->termios.c_cflag; + tty_kref_put(tty); + } temp = lpuart32_read(port, UARTCTRL) & ~UARTCTRL_SBK; + modem = lpuart32_read(port, UARTMODIR); - if (break_state != 0) + if (break_state != 0) { temp |= UARTCTRL_SBK; + /* + * LPUART CTS has higher priority than SBK, need to disable CTS before + * asserting SBK to avoid any interference if flow control is enabled. + */ + if (cflag & CRTSCTS && modem & UARTMODIR_TXCTSE) + lpuart32_write(port, modem & ~UARTMODIR_TXCTSE, UARTMODIR); + } else { + /* Re-enable the CTS when break off. */ + if (cflag & CRTSCTS && !(modem & UARTMODIR_TXCTSE)) + lpuart32_write(port, modem | UARTMODIR_TXCTSE, UARTMODIR); + } lpuart32_write(port, temp, UARTCTRL); } From 17b96b5c19bec791b433890549e44ca523dc82aa Mon Sep 17 00:00:00 2001 From: Isaac True Date: Wed, 30 Nov 2022 11:55:30 +0100 Subject: [PATCH 1994/4345] serial: sc16is7xx: setup GPIO controller later in probe [ Upstream commit c8f71b49ee4d28930c4a6798d1969fa91dc4ef3e ] The GPIO controller component of the sc16is7xx driver is setup too early, which can result in a race condition where another device tries to utilise the GPIO lines before the sc16is7xx device has finished initialising. This issue manifests itself as an Oops when the GPIO lines are configured: Unable to handle kernel read from unreadable memory at virtual address ... pc : sc16is7xx_gpio_direction_output+0x68/0x108 [sc16is7xx] lr : sc16is7xx_gpio_direction_output+0x4c/0x108 [sc16is7xx] ... Call trace: sc16is7xx_gpio_direction_output+0x68/0x108 [sc16is7xx] gpiod_direction_output_raw_commit+0x64/0x318 gpiod_direction_output+0xb0/0x170 create_gpio_led+0xec/0x198 gpio_led_probe+0x16c/0x4f0 platform_drv_probe+0x5c/0xb0 really_probe+0xe8/0x448 driver_probe_device+0xe8/0x138 __device_attach_driver+0x94/0x118 bus_for_each_drv+0x8c/0xe0 __device_attach+0x100/0x1b8 device_initial_probe+0x28/0x38 bus_probe_device+0xa4/0xb0 deferred_probe_work_func+0x90/0xe0 process_one_work+0x1c4/0x480 worker_thread+0x54/0x430 kthread+0x138/0x150 ret_from_fork+0x10/0x1c This patch moves the setup of the GPIO controller functions to later in the probe function, ensuring the sc16is7xx device has already finished initialising by the time other devices try to make use of the GPIO lines. The error handling has also been reordered to reflect the new initialisation order. Co-developed-by: Wen-chien Jesse Sung Signed-off-by: Wen-chien Jesse Sung Signed-off-by: Isaac True Link: https://lore.kernel.org/r/20221130105529.698385-1-isaac.true@canonical.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/sc16is7xx.c | 51 +++++++++++++++++----------------- 1 file changed, 26 insertions(+), 25 deletions(-) diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 04b4ed5d0634..7ece8d1a23cb 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1243,25 +1243,6 @@ static int sc16is7xx_probe(struct device *dev, } sched_set_fifo(s->kworker_task); -#ifdef CONFIG_GPIOLIB - if (devtype->nr_gpio) { - /* Setup GPIO cotroller */ - s->gpio.owner = THIS_MODULE; - s->gpio.parent = dev; - s->gpio.label = dev_name(dev); - s->gpio.direction_input = sc16is7xx_gpio_direction_input; - s->gpio.get = sc16is7xx_gpio_get; - s->gpio.direction_output = sc16is7xx_gpio_direction_output; - s->gpio.set = sc16is7xx_gpio_set; - s->gpio.base = -1; - s->gpio.ngpio = devtype->nr_gpio; - s->gpio.can_sleep = 1; - ret = gpiochip_add_data(&s->gpio, s); - if (ret) - goto out_thread; - } -#endif - /* reset device, purging any pending irq / data */ regmap_write(s->regmap, SC16IS7XX_IOCONTROL_REG << SC16IS7XX_REG_SHIFT, SC16IS7XX_IOCONTROL_SRESET_BIT); @@ -1327,6 +1308,25 @@ static int sc16is7xx_probe(struct device *dev, s->p[u].irda_mode = true; } +#ifdef CONFIG_GPIOLIB + if (devtype->nr_gpio) { + /* Setup GPIO cotroller */ + s->gpio.owner = THIS_MODULE; + s->gpio.parent = dev; + s->gpio.label = dev_name(dev); + s->gpio.direction_input = sc16is7xx_gpio_direction_input; + s->gpio.get = sc16is7xx_gpio_get; + s->gpio.direction_output = sc16is7xx_gpio_direction_output; + s->gpio.set = sc16is7xx_gpio_set; + s->gpio.base = -1; + s->gpio.ngpio = devtype->nr_gpio; + s->gpio.can_sleep = 1; + ret = gpiochip_add_data(&s->gpio, s); + if (ret) + goto out_thread; + } +#endif + /* * Setup interrupt. We first try to acquire the IRQ line as level IRQ. * If that succeeds, we can allow sharing the interrupt as well. @@ -1346,18 +1346,19 @@ static int sc16is7xx_probe(struct device *dev, if (!ret) return 0; -out_ports: - for (i--; i >= 0; i--) { - uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port); - clear_bit(s->p[i].port.line, &sc16is7xx_lines); - } - #ifdef CONFIG_GPIOLIB if (devtype->nr_gpio) gpiochip_remove(&s->gpio); out_thread: #endif + +out_ports: + for (i--; i >= 0; i--) { + uart_remove_one_port(&sc16is7xx_uart, &s->p[i].port); + clear_bit(s->p[i].port.line, &sc16is7xx_lines); + } + kthread_stop(s->kworker_task); out_clk: From 160494b66fe09577f30cf454f785f364c8c70c5d Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Mon, 12 Dec 2022 23:49:33 +0200 Subject: [PATCH 1995/4345] mei: bus-fixup:upon error print return values of send and receive [ Upstream commit 4b8659e2c258e4fdac9ccdf06cc20c0677894ef9 ] For easier debugging, upon error, print also return values from __mei_cl_recv() and __mei_cl_send() functions. Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler Link: https://lore.kernel.org/r/20221212214933.275434-1-tomas.winkler@intel.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/mei/bus-fixup.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c index 4e30fa98fe7d..c4c1275581ec 100644 --- a/drivers/misc/mei/bus-fixup.c +++ b/drivers/misc/mei/bus-fixup.c @@ -172,7 +172,7 @@ static int mei_fwver(struct mei_cl_device *cldev) ret = __mei_cl_send(cldev->cl, (u8 *)&req, sizeof(req), MEI_CL_IO_TX_BLOCKING); if (ret < 0) { - dev_err(&cldev->dev, "Could not send ReqFWVersion cmd\n"); + dev_err(&cldev->dev, "Could not send ReqFWVersion cmd ret = %d\n", ret); return ret; } @@ -184,7 +184,7 @@ static int mei_fwver(struct mei_cl_device *cldev) * Should be at least one version block, * error out if nothing found */ - dev_err(&cldev->dev, "Could not read FW version\n"); + dev_err(&cldev->dev, "Could not read FW version ret = %d\n", bytes_recv); return -EIO; } @@ -332,7 +332,7 @@ static int mei_nfc_if_version(struct mei_cl *cl, ret = __mei_cl_send(cl, (u8 *)&cmd, sizeof(cmd), MEI_CL_IO_TX_BLOCKING); if (ret < 0) { - dev_err(bus->dev, "Could not send IF version cmd\n"); + dev_err(bus->dev, "Could not send IF version cmd ret = %d\n", ret); return ret; } @@ -346,7 +346,7 @@ static int mei_nfc_if_version(struct mei_cl *cl, ret = 0; bytes_recv = __mei_cl_recv(cl, (u8 *)reply, if_version_length, 0, 0); if (bytes_recv < 0 || (size_t)bytes_recv < if_version_length) { - dev_err(bus->dev, "Could not read IF version\n"); + dev_err(bus->dev, "Could not read IF version ret = %d\n", bytes_recv); ret = -EIO; goto err; } From 8db64cea4788d972dcc9e064ad93c935ed67e4a8 Mon Sep 17 00:00:00 2001 From: Yulong Zhang Date: Tue, 17 Jan 2023 10:51:47 +0800 Subject: [PATCH 1996/4345] tools/iio/iio_utils:fix memory leak [ Upstream commit f2edf0c819a4823cd6c288801ce737e8d4fcde06 ] 1. fopen sysfs without fclose. 2. asprintf filename without free. 3. if asprintf return error,do not need to free the buffer. Signed-off-by: Yulong Zhang Link: https://lore.kernel.org/r/20230117025147.69890-1-yulong.zhang@metoak.net Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- tools/iio/iio_utils.c | 23 ++++++----------------- 1 file changed, 6 insertions(+), 17 deletions(-) diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index d66b18c54606..48360994c2a1 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -262,6 +262,7 @@ int iioutils_get_param_float(float *output, const char *param_name, if (fscanf(sysfsfp, "%f", output) != 1) ret = errno ? -errno : -ENODATA; + fclose(sysfsfp); break; } error_free_filename: @@ -342,9 +343,9 @@ int build_channel_array(const char *device_dir, } sysfsfp = fopen(filename, "r"); + free(filename); if (!sysfsfp) { ret = -errno; - free(filename); goto error_close_dir; } @@ -354,7 +355,6 @@ int build_channel_array(const char *device_dir, if (fclose(sysfsfp)) perror("build_channel_array(): Failed to close file"); - free(filename); goto error_close_dir; } if (ret == 1) @@ -362,11 +362,9 @@ int build_channel_array(const char *device_dir, if (fclose(sysfsfp)) { ret = -errno; - free(filename); goto error_close_dir; } - free(filename); } *ci_array = malloc(sizeof(**ci_array) * (*counter)); @@ -392,9 +390,9 @@ int build_channel_array(const char *device_dir, } sysfsfp = fopen(filename, "r"); + free(filename); if (!sysfsfp) { ret = -errno; - free(filename); count--; goto error_cleanup_array; } @@ -402,20 +400,17 @@ int build_channel_array(const char *device_dir, errno = 0; if (fscanf(sysfsfp, "%i", ¤t_enabled) != 1) { ret = errno ? -errno : -ENODATA; - free(filename); count--; goto error_cleanup_array; } if (fclose(sysfsfp)) { ret = -errno; - free(filename); count--; goto error_cleanup_array; } if (!current_enabled) { - free(filename); count--; continue; } @@ -426,7 +421,6 @@ int build_channel_array(const char *device_dir, strlen(ent->d_name) - strlen("_en")); if (!current->name) { - free(filename); ret = -ENOMEM; count--; goto error_cleanup_array; @@ -436,7 +430,6 @@ int build_channel_array(const char *device_dir, ret = iioutils_break_up_name(current->name, ¤t->generic_name); if (ret) { - free(filename); free(current->name); count--; goto error_cleanup_array; @@ -447,17 +440,16 @@ int build_channel_array(const char *device_dir, scan_el_dir, current->name); if (ret < 0) { - free(filename); ret = -ENOMEM; goto error_cleanup_array; } sysfsfp = fopen(filename, "r"); + free(filename); if (!sysfsfp) { ret = -errno; - fprintf(stderr, "failed to open %s\n", - filename); - free(filename); + fprintf(stderr, "failed to open %s/%s_index\n", + scan_el_dir, current->name); goto error_cleanup_array; } @@ -467,17 +459,14 @@ int build_channel_array(const char *device_dir, if (fclose(sysfsfp)) perror("build_channel_array(): Failed to close file"); - free(filename); goto error_cleanup_array; } if (fclose(sysfsfp)) { ret = -errno; - free(filename); goto error_cleanup_array; } - free(filename); /* Find the scale */ ret = iioutils_get_param_float(¤t->scale, "scale", From 3357e90d3c3648807b317b8948bd400cb56fc255 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Thu, 26 Jan 2023 07:21:46 -0800 Subject: [PATCH 1997/4345] iio: accel: mma9551_core: Prevent uninitialized variable in mma9551_read_status_word() [ Upstream commit e56d2c34ce9dc122b1a618172ec0e05e50adb9e9 ] Smatch Warns: drivers/iio/accel/mma9551_core.c:357 mma9551_read_status_word() error: uninitialized symbol 'v'. When (offset >= 1 << 12) is true mma9551_transfer() will return -EINVAL without 'v' being initialized, so check for the error and return. Note: Not a bug as such because the caller checks return value and doesn't not use this parameter in the problem case. Signed-off-by: Harshit Mogalapalli Link: https://lore.kernel.org/r/20230126152147.3585874-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/accel/mma9551_core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/iio/accel/mma9551_core.c b/drivers/iio/accel/mma9551_core.c index 666e7a04a7d7..aa16d6678494 100644 --- a/drivers/iio/accel/mma9551_core.c +++ b/drivers/iio/accel/mma9551_core.c @@ -354,9 +354,12 @@ int mma9551_read_status_word(struct i2c_client *client, u8 app_id, ret = mma9551_transfer(client, app_id, MMA9551_CMD_READ_STATUS, reg, NULL, 0, (u8 *)&v, 2); + if (ret < 0) + return ret; + *val = be16_to_cpu(v); - return ret; + return 0; } EXPORT_SYMBOL(mma9551_read_status_word); From 09ca779ac04cd50ee0d27acd6faf7b2224a6b65a Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Thu, 26 Jan 2023 07:36:09 -0800 Subject: [PATCH 1998/4345] iio: accel: mma9551_core: Prevent uninitialized variable in mma9551_read_config_word() [ Upstream commit 64a68158738ec8f520347144352f7a09bdb9e169 ] Smatch Warns: drivers/iio/accel/mma9551_core.c:299 mma9551_read_config_word() error: uninitialized symbol 'v'. When (offset >= 1 << 12) is true mma9551_transfer() will return -EINVAL without 'v' being initialized, so check for the error and return. Note: No actual bug as caller checks the return value and does not use the parameter in the problem case. Signed-off-by: Harshit Mogalapalli Link: https://lore.kernel.org/r/20230126153610.3586243-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/accel/mma9551_core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/iio/accel/mma9551_core.c b/drivers/iio/accel/mma9551_core.c index aa16d6678494..9bb5c2fea08c 100644 --- a/drivers/iio/accel/mma9551_core.c +++ b/drivers/iio/accel/mma9551_core.c @@ -296,9 +296,12 @@ int mma9551_read_config_word(struct i2c_client *client, u8 app_id, ret = mma9551_transfer(client, app_id, MMA9551_CMD_READ_CONFIG, reg, NULL, 0, (u8 *)&v, 2); + if (ret < 0) + return ret; + *val = be16_to_cpu(v); - return ret; + return 0; } EXPORT_SYMBOL(mma9551_read_config_word); From 654ae539254d10042869fdc77ad04c09e7eff1fd Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 1 Feb 2023 12:30:18 +0800 Subject: [PATCH 1999/4345] PCI: loongson: Prevent LS7A MRRS increases [ Upstream commit 8b3517f88ff2983f52698893519227c10aac90b2 ] Except for isochronous-configured devices, software may set Max_Read_Request_Size (MRRS) to any value up to 4096. If a device issues a read request with size greater than the completer's Max_Payload_Size (MPS), the completer is required to break the response into multiple completions. Instead of correctly responding with multiple completions to a large read request, some LS7A Root Ports respond with a Completer Abort. To prevent this, the MRRS must be limited to an implementation-specific value. The OS cannot detect that value, so rely on BIOS to configure MRRS before booting, and quirk the Root Ports so we never set an MRRS larger than that BIOS value for any downstream device. N.B. Hot-added devices are not configured by BIOS, and they power up with MRRS = 512 bytes, so these devices will be limited to 512 bytes. If the LS7A limit is smaller, those hot-added devices may not work correctly, but per [1], hotplug is not supported with this chipset revision. [1] https://lore.kernel.org/r/073638a7-ae68-2847-ac3d-29e5e760d6af@loongson.cn [bhelgaas: commit log] Link: https://bugzilla.kernel.org/show_bug.cgi?id=216884 Link: https://lore.kernel.org/r/20230201043018.778499-3-chenhuacai@loongson.cn Signed-off-by: Huacai Chen Signed-off-by: Bjorn Helgaas Signed-off-by: Sasha Levin --- drivers/pci/controller/pci-loongson.c | 42 +++++++++------------------ drivers/pci/pci.c | 10 +++++++ include/linux/pci.h | 1 + 3 files changed, 25 insertions(+), 28 deletions(-) diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c index 48169b1e3817..dc7b4e4293ce 100644 --- a/drivers/pci/controller/pci-loongson.c +++ b/drivers/pci/controller/pci-loongson.c @@ -60,37 +60,23 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DEV_LS7A_LPC, system_bus_quirk); -static void loongson_mrrs_quirk(struct pci_dev *dev) +static void loongson_mrrs_quirk(struct pci_dev *pdev) { - struct pci_bus *bus = dev->bus; - struct pci_dev *bridge; - static const struct pci_device_id bridge_devids[] = { - { PCI_VDEVICE(LOONGSON, DEV_PCIE_PORT_0) }, - { PCI_VDEVICE(LOONGSON, DEV_PCIE_PORT_1) }, - { PCI_VDEVICE(LOONGSON, DEV_PCIE_PORT_2) }, - { 0, }, - }; + /* + * Some Loongson PCIe ports have h/w limitations of maximum read + * request size. They can't handle anything larger than this. So + * force this limit on any devices attached under these ports. + */ + struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); - /* look for the matching bridge */ - while (!pci_is_root_bus(bus)) { - bridge = bus->self; - bus = bus->parent; - /* - * Some Loongson PCIe ports have a h/w limitation of - * 256 bytes maximum read request size. They can't handle - * anything larger than this. So force this limit on - * any devices attached under these ports. - */ - if (pci_match_id(bridge_devids, bridge)) { - if (pcie_get_readrq(dev) > 256) { - pci_info(dev, "limiting MRRS to 256\n"); - pcie_set_readrq(dev, 256); - } - break; - } - } + bridge->no_inc_mrrs = 1; } -DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_PCIE_PORT_0, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_PCIE_PORT_1, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_PCIE_PORT_2, loongson_mrrs_quirk); static void __iomem *cfg1_map(struct loongson_pci *priv, int bus, unsigned int devfn, int where) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 845851e23352..744a2e05635b 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5739,6 +5739,7 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) { u16 v; int ret; + struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus); if (rq < 128 || rq > 4096 || !is_power_of_2(rq)) return -EINVAL; @@ -5757,6 +5758,15 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) v = (ffs(rq) - 8) << 12; + if (bridge->no_inc_mrrs) { + int max_mrrs = pcie_get_readrq(dev); + + if (rq > max_mrrs) { + pci_info(dev, "can't set Max_Read_Request_Size to %d; max is %d\n", rq, max_mrrs); + return -EINVAL; + } + } + ret = pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_READRQ, v); diff --git a/include/linux/pci.h b/include/linux/pci.h index 692ce678c5f1..4cc42ad2f6c5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -539,6 +539,7 @@ struct pci_host_bridge { struct msi_controller *msi; unsigned int ignore_reset_delay:1; /* For entire hierarchy */ unsigned int no_ext_tags:1; /* No Extended Tags */ + unsigned int no_inc_mrrs:1; /* No Increase MRRS */ unsigned int native_aer:1; /* OS may use PCIe AER */ unsigned int native_pcie_hotplug:1; /* OS may use PCIe hotplug */ unsigned int native_shpc_hotplug:1; /* OS may use SHPC hotplug */ From 426cbe9a0a688533eb286e1298bd9e66be7f806f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 4 Feb 2023 10:36:52 -0800 Subject: [PATCH 2000/4345] usb: host: xhci: mvebu: Iterate over array indexes instead of using pointer math [ Upstream commit 0fbd2cda92cdb00f72080665554a586f88bca821 ] Walking the dram->cs array was seen as accesses beyond the first array item by the compiler. Instead, use the array index directly. This allows for run-time bounds checking under CONFIG_UBSAN_BOUNDS as well. Seen with GCC 13 with -fstrict-flex-arrays: In function 'xhci_mvebu_mbus_config', inlined from 'xhci_mvebu_mbus_init_quirk' at ../drivers/usb/host/xhci-mvebu.c:66:2: ../drivers/usb/host/xhci-mvebu.c:37:28: warning: array subscript 0 is outside array bounds of 'const struct mbus_dram_window[0]' [-Warray-bounds=] 37 | writel(((cs->size - 1) & 0xffff0000) | (cs->mbus_attr << 8) | | ~~^~~~~~ Cc: Mathias Nyman Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230204183651.never.663-kees@kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-mvebu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-mvebu.c b/drivers/usb/host/xhci-mvebu.c index 8ca1a235d164..eabccf25796b 100644 --- a/drivers/usb/host/xhci-mvebu.c +++ b/drivers/usb/host/xhci-mvebu.c @@ -33,7 +33,7 @@ static void xhci_mvebu_mbus_config(void __iomem *base, /* Program each DRAM CS in a seperate window */ for (win = 0; win < dram->num_cs; win++) { - const struct mbus_dram_window *cs = dram->cs + win; + const struct mbus_dram_window *cs = &dram->cs[win]; writel(((cs->size - 1) & 0xffff0000) | (cs->mbus_attr << 8) | (dram->mbus_dram_target_id << 4) | 1, From 961f93d63da72f5fcaa6793fb2dcbc995c119a8e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 4 Feb 2023 10:35:46 -0800 Subject: [PATCH 2001/4345] USB: ene_usb6250: Allocate enough memory for full object [ Upstream commit ce33e64c1788912976b61314b56935abd4bc97ef ] The allocation of PageBuffer is 512 bytes in size, but the dereferencing of struct ms_bootblock_idi (also size 512) happens at a calculated offset within the allocation, which means the object could potentially extend beyond the end of the allocation. Avoid this case by just allocating enough space to catch any accesses beyond the end. Seen with GCC 13: ../drivers/usb/storage/ene_ub6250.c: In function 'ms_lib_process_bootblock': ../drivers/usb/storage/ene_ub6250.c:1050:44: warning: array subscript 'struct ms_bootblock_idi[0]' is partly outside array bounds of 'unsigned char[512]' [-Warray-bounds=] 1050 | if (le16_to_cpu(idi->wIDIgeneralConfiguration) != MS_IDI_GENERAL_CONF) | ^~ ../include/uapi/linux/byteorder/little_endian.h:37:51: note: in definition of macro '__le16_to_cpu' 37 | #define __le16_to_cpu(x) ((__force __u16)(__le16)(x)) | ^ ../drivers/usb/storage/ene_ub6250.c:1050:29: note: in expansion of macro 'le16_to_cpu' 1050 | if (le16_to_cpu(idi->wIDIgeneralConfiguration) != MS_IDI_GENERAL_CONF) | ^~~~~~~~~~~ In file included from ../drivers/usb/storage/ene_ub6250.c:5: In function 'kmalloc', inlined from 'ms_lib_process_bootblock' at ../drivers/usb/storage/ene_ub6250.c:942:15: ../include/linux/slab.h:580:24: note: at offset [256, 512] into object of size 512 allocated by 'kmalloc_trace' 580 | return kmalloc_trace( | ^~~~~~~~~~~~~~ 581 | kmalloc_caches[kmalloc_type(flags)][index], | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 582 | flags, size); | ~~~~~~~~~~~~ Cc: Alan Stern Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230204183546.never.849-kees@kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/storage/ene_ub6250.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/storage/ene_ub6250.c b/drivers/usb/storage/ene_ub6250.c index c9ce1c25c80c..737398f1b896 100644 --- a/drivers/usb/storage/ene_ub6250.c +++ b/drivers/usb/storage/ene_ub6250.c @@ -938,7 +938,7 @@ static int ms_lib_process_bootblock(struct us_data *us, u16 PhyBlock, u8 *PageDa struct ms_lib_type_extdat ExtraData; struct ene_ub6250_info *info = (struct ene_ub6250_info *) us->extra; - PageBuffer = kmalloc(MS_BYTES_PER_PAGE, GFP_KERNEL); + PageBuffer = kzalloc(MS_BYTES_PER_PAGE * 2, GFP_KERNEL); if (PageBuffer == NULL) return (u32)-1; From 56495e8d3cb4522b8e72347755d5c02e64ac30df Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Thu, 2 Feb 2023 11:41:37 +0000 Subject: [PATCH 2002/4345] usb: uvc: Enumerate valid values for color matching [ Upstream commit e16cab9c1596e251761d2bfb5e1467950d616963 ] The color matching descriptors defined in the UVC Specification contain 3 fields with discrete numeric values representing particular settings. Enumerate those values so that later code setting them can be more readable. Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Scally Link: https://lore.kernel.org/r/20230202114142.300858-2-dan.scally@ideasonboard.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- include/uapi/linux/usb/video.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/include/uapi/linux/usb/video.h b/include/uapi/linux/usb/video.h index bfdae12cdacf..c58854fb7d94 100644 --- a/include/uapi/linux/usb/video.h +++ b/include/uapi/linux/usb/video.h @@ -179,6 +179,36 @@ #define UVC_CONTROL_CAP_AUTOUPDATE (1 << 3) #define UVC_CONTROL_CAP_ASYNCHRONOUS (1 << 4) +/* 3.9.2.6 Color Matching Descriptor Values */ +enum uvc_color_primaries_values { + UVC_COLOR_PRIMARIES_UNSPECIFIED, + UVC_COLOR_PRIMARIES_BT_709_SRGB, + UVC_COLOR_PRIMARIES_BT_470_2_M, + UVC_COLOR_PRIMARIES_BT_470_2_B_G, + UVC_COLOR_PRIMARIES_SMPTE_170M, + UVC_COLOR_PRIMARIES_SMPTE_240M, +}; + +enum uvc_transfer_characteristics_values { + UVC_TRANSFER_CHARACTERISTICS_UNSPECIFIED, + UVC_TRANSFER_CHARACTERISTICS_BT_709, + UVC_TRANSFER_CHARACTERISTICS_BT_470_2_M, + UVC_TRANSFER_CHARACTERISTICS_BT_470_2_B_G, + UVC_TRANSFER_CHARACTERISTICS_SMPTE_170M, + UVC_TRANSFER_CHARACTERISTICS_SMPTE_240M, + UVC_TRANSFER_CHARACTERISTICS_LINEAR, + UVC_TRANSFER_CHARACTERISTICS_SRGB, +}; + +enum uvc_matrix_coefficients { + UVC_MATRIX_COEFFICIENTS_UNSPECIFIED, + UVC_MATRIX_COEFFICIENTS_BT_709, + UVC_MATRIX_COEFFICIENTS_FCC, + UVC_MATRIX_COEFFICIENTS_BT_470_2_B_G, + UVC_MATRIX_COEFFICIENTS_SMPTE_170M, + UVC_MATRIX_COEFFICIENTS_SMPTE_240M, +}; + /* ------------------------------------------------------------------------ * UVC structures */ From 877aacda14698b6217951c30eb4033ce53f50a33 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Mon, 6 Feb 2023 16:17:52 +0000 Subject: [PATCH 2003/4345] usb: gadget: uvc: Make bSourceID read/write [ Upstream commit b3c839bd8a07d303bc59a900d55dd35c7826562c ] At the moment, the UVC function graph is hardcoded IT -> PU -> OT. To add XU support we need the ability to insert the XU descriptors into the chain. To facilitate that, make the output terminal's bSourceID attribute writeable so that we can configure its source. Signed-off-by: Daniel Scally Link: https://lore.kernel.org/r/20230206161802.892954-2-dan.scally@ideasonboard.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- .../ABI/testing/configfs-usb-gadget-uvc | 2 +- drivers/usb/gadget/function/uvc_configfs.c | 59 ++++++++++++++++++- 2 files changed, 59 insertions(+), 2 deletions(-) diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uvc b/Documentation/ABI/testing/configfs-usb-gadget-uvc index ac5e11af79a8..4b1813994bd0 100644 --- a/Documentation/ABI/testing/configfs-usb-gadget-uvc +++ b/Documentation/ABI/testing/configfs-usb-gadget-uvc @@ -51,7 +51,7 @@ Date: Dec 2014 KernelVersion: 4.0 Description: Default output terminal descriptors - All attributes read only: + All attributes read only except bSourceID: ============== ============================================= iTerminal index of string descriptor diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 00fb58e50a15..7bb11d532b19 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -505,11 +505,68 @@ UVC_ATTR_RO(uvcg_default_output_, cname, aname) UVCG_DEFAULT_OUTPUT_ATTR(b_terminal_id, bTerminalID, 8); UVCG_DEFAULT_OUTPUT_ATTR(w_terminal_type, wTerminalType, 16); UVCG_DEFAULT_OUTPUT_ATTR(b_assoc_terminal, bAssocTerminal, 8); -UVCG_DEFAULT_OUTPUT_ATTR(b_source_id, bSourceID, 8); UVCG_DEFAULT_OUTPUT_ATTR(i_terminal, iTerminal, 8); #undef UVCG_DEFAULT_OUTPUT_ATTR +static ssize_t uvcg_default_output_b_source_id_show(struct config_item *item, + char *page) +{ + struct config_group *group = to_config_group(item); + struct f_uvc_opts *opts; + struct config_item *opts_item; + struct mutex *su_mutex = &group->cg_subsys->su_mutex; + struct uvc_output_terminal_descriptor *cd; + int result; + + mutex_lock(su_mutex); /* for navigating configfs hierarchy */ + + opts_item = group->cg_item.ci_parent->ci_parent-> + ci_parent->ci_parent; + opts = to_f_uvc_opts(opts_item); + cd = &opts->uvc_output_terminal; + + mutex_lock(&opts->lock); + result = sprintf(page, "%u\n", le8_to_cpu(cd->bSourceID)); + mutex_unlock(&opts->lock); + + mutex_unlock(su_mutex); + + return result; +} + +static ssize_t uvcg_default_output_b_source_id_store(struct config_item *item, + const char *page, size_t len) +{ + struct config_group *group = to_config_group(item); + struct f_uvc_opts *opts; + struct config_item *opts_item; + struct mutex *su_mutex = &group->cg_subsys->su_mutex; + struct uvc_output_terminal_descriptor *cd; + int result; + u8 num; + + mutex_lock(su_mutex); /* for navigating configfs hierarchy */ + + opts_item = group->cg_item.ci_parent->ci_parent-> + ci_parent->ci_parent; + opts = to_f_uvc_opts(opts_item); + cd = &opts->uvc_output_terminal; + + result = kstrtou8(page, 0, &num); + if (result) + return result; + + mutex_lock(&opts->lock); + cd->bSourceID = num; + mutex_unlock(&opts->lock); + + mutex_unlock(su_mutex); + + return len; +} +UVC_ATTR(uvcg_default_output_, b_source_id, bSourceID); + static struct configfs_attribute *uvcg_default_output_attrs[] = { &uvcg_default_output_attr_b_terminal_id, &uvcg_default_output_attr_w_terminal_type, From fdca189e522850ee122a409ed7e693795e31fb58 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 31 Jan 2023 11:24:03 +0200 Subject: [PATCH 2004/4345] PCI: Align extra resources for hotplug bridges properly [ Upstream commit 08f0a15ee8adb4846b08ca5d5c175fbf0f652bc9 ] After division the extra resource space per hotplug bridge may not be aligned according to the window alignment, so align it before passing it down for further distribution. Link: https://lore.kernel.org/r/20230131092405.29121-2-mika.westerberg@linux.intel.com Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas Signed-off-by: Sasha Levin --- drivers/pci/setup-bus.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 2ce636937c6e..4a6b698b5dd1 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -2004,6 +2004,7 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus, * resource space between hotplug bridges. */ for_each_pci_bridge(dev, bus) { + struct resource *res; struct pci_bus *b; b = dev->subordinate; @@ -2015,16 +2016,28 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus, * hotplug-capable downstream ports taking alignment into * account. */ - io.end = io.start + io_per_hp - 1; - mmio.end = mmio.start + mmio_per_hp - 1; - mmio_pref.end = mmio_pref.start + mmio_pref_per_hp - 1; + res = &dev->resource[PCI_BRIDGE_IO_WINDOW]; + align = pci_resource_alignment(dev, res); + io.end = align ? io.start + ALIGN_DOWN(io_per_hp, align) - 1 + : io.start + io_per_hp - 1; + + res = &dev->resource[PCI_BRIDGE_MEM_WINDOW]; + align = pci_resource_alignment(dev, res); + mmio.end = align ? mmio.start + ALIGN_DOWN(mmio_per_hp, align) - 1 + : mmio.start + mmio_per_hp - 1; + + res = &dev->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; + align = pci_resource_alignment(dev, res); + mmio_pref.end = align ? mmio_pref.start + + ALIGN_DOWN(mmio_pref_per_hp, align) - 1 + : mmio_pref.start + mmio_pref_per_hp - 1; pci_bus_distribute_available_resources(b, add_list, io, mmio, mmio_pref); - io.start += io_per_hp; - mmio.start += mmio_per_hp; - mmio_pref.start += mmio_pref_per_hp; + io.start += io.end + 1; + mmio.start += mmio.end + 1; + mmio_pref.start += mmio_pref.end + 1; } } From b2301851e7e3f5935f317a840763fb4ccaac55cb Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 31 Jan 2023 11:24:04 +0200 Subject: [PATCH 2005/4345] PCI: Take other bus devices into account when distributing resources [ Upstream commit 9db0b9b6a14249ef65a5f1e5e3b37762af96f425 ] A PCI bridge may reside on a bus with other devices as well. The resource distribution code does not take this into account and therefore it expands the bridge resource windows too much, not leaving space for the other devices (or functions of a multifunction device). This leads to an issue that Jonathan reported when running QEMU with the following topology (QEMU parameters): -device pcie-root-port,port=0,id=root_port13,chassis=0,slot=2 \ -device x3130-upstream,id=sw1,bus=root_port13,multifunction=on \ -device e1000,bus=root_port13,addr=0.1 \ -device xio3130-downstream,id=fun1,bus=sw1,chassis=0,slot=3 \ -device e1000,bus=fun1 The first e1000 NIC here is another function in the switch upstream port. This leads to following errors: pci 0000:00:04.0: bridge window [mem 0x10200000-0x103fffff] to [bus 02-04] pci 0000:02:00.0: bridge window [mem 0x10200000-0x103fffff] to [bus 03-04] pci 0000:02:00.1: BAR 0: failed to assign [mem size 0x00020000] e1000 0000:02:00.1: can't ioremap BAR 0: [??? 0x00000000 flags 0x0] Fix this by taking into account bridge windows, device BARs and SR-IOV PF BARs on the bus (PF BARs include space for VF BARS so only account PF BARs), including the ones belonging to bridges themselves if it has any. Link: https://lore.kernel.org/linux-pci/20221014124553.0000696f@huawei.com/ Link: https://lore.kernel.org/linux-pci/6053736d-1923-41e7-def9-7585ce1772d9@ixsystems.com/ Link: https://lore.kernel.org/r/20230131092405.29121-3-mika.westerberg@linux.intel.com Reported-by: Jonathan Cameron Reported-by: Alexander Motin Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas Signed-off-by: Sasha Levin --- drivers/pci/setup-bus.c | 178 ++++++++++++++++++++++++---------------- 1 file changed, 107 insertions(+), 71 deletions(-) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 4a6b698b5dd1..16d291e10627 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1878,12 +1878,67 @@ static void adjust_bridge_window(struct pci_dev *bridge, struct resource *res, add_size = size - new_size; pci_dbg(bridge, "bridge window %pR shrunken by %pa\n", res, &add_size); + } else { + return; } res->end = res->start + new_size - 1; remove_from_list(add_list, res); } +static void remove_dev_resource(struct resource *avail, struct pci_dev *dev, + struct resource *res) +{ + resource_size_t size, align, tmp; + + size = resource_size(res); + if (!size) + return; + + align = pci_resource_alignment(dev, res); + align = align ? ALIGN(avail->start, align) - avail->start : 0; + tmp = align + size; + avail->start = min(avail->start + tmp, avail->end + 1); +} + +static void remove_dev_resources(struct pci_dev *dev, struct resource *io, + struct resource *mmio, + struct resource *mmio_pref) +{ + int i; + + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + struct resource *res = &dev->resource[i]; + + if (resource_type(res) == IORESOURCE_IO) { + remove_dev_resource(io, dev, res); + } else if (resource_type(res) == IORESOURCE_MEM) { + + /* + * Make sure prefetchable memory is reduced from + * the correct resource. Specifically we put 32-bit + * prefetchable memory in non-prefetchable window + * if there is an 64-bit pretchable window. + * + * See comments in __pci_bus_size_bridges() for + * more information. + */ + if ((res->flags & IORESOURCE_PREFETCH) && + ((res->flags & IORESOURCE_MEM_64) == + (mmio_pref->flags & IORESOURCE_MEM_64))) + remove_dev_resource(mmio_pref, dev, res); + else + remove_dev_resource(mmio, dev, res); + } + } +} + +/* + * io, mmio and mmio_pref contain the total amount of bridge window space + * available. This includes the minimal space needed to cover all the + * existing devices on the bus and the possible extra space that can be + * shared with the bridges. + */ static void pci_bus_distribute_available_resources(struct pci_bus *bus, struct list_head *add_list, struct resource io, @@ -1893,7 +1948,7 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus, unsigned int normal_bridges = 0, hotplug_bridges = 0; struct resource *io_res, *mmio_res, *mmio_pref_res; struct pci_dev *dev, *bridge = bus->self; - resource_size_t io_per_hp, mmio_per_hp, mmio_pref_per_hp, align; + resource_size_t io_per_b, mmio_per_b, mmio_pref_per_b, align; io_res = &bridge->resource[PCI_BRIDGE_IO_WINDOW]; mmio_res = &bridge->resource[PCI_BRIDGE_MEM_WINDOW]; @@ -1937,100 +1992,81 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus, normal_bridges++; } - /* - * There is only one bridge on the bus so it gets all available - * resources which it can then distribute to the possible hotplug - * bridges below. - */ - if (hotplug_bridges + normal_bridges == 1) { - dev = list_first_entry(&bus->devices, struct pci_dev, bus_list); - if (dev->subordinate) - pci_bus_distribute_available_resources(dev->subordinate, - add_list, io, mmio, mmio_pref); - return; - } - - if (hotplug_bridges == 0) + if (!(hotplug_bridges + normal_bridges)) return; /* - * Calculate the total amount of extra resource space we can - * pass to bridges below this one. This is basically the - * extra space reduced by the minimal required space for the - * non-hotplug bridges. + * Calculate the amount of space we can forward from "bus" to any + * downstream buses, i.e., the space left over after assigning the + * BARs and windows on "bus". */ - for_each_pci_bridge(dev, bus) { - resource_size_t used_size; - struct resource *res; - - if (dev->is_hotplug_bridge) - continue; - - /* - * Reduce the available resource space by what the - * bridge and devices below it occupy. - */ - res = &dev->resource[PCI_BRIDGE_IO_WINDOW]; - align = pci_resource_alignment(dev, res); - align = align ? ALIGN(io.start, align) - io.start : 0; - used_size = align + resource_size(res); - if (!res->parent) - io.start = min(io.start + used_size, io.end + 1); - - res = &dev->resource[PCI_BRIDGE_MEM_WINDOW]; - align = pci_resource_alignment(dev, res); - align = align ? ALIGN(mmio.start, align) - mmio.start : 0; - used_size = align + resource_size(res); - if (!res->parent) - mmio.start = min(mmio.start + used_size, mmio.end + 1); - - res = &dev->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; - align = pci_resource_alignment(dev, res); - align = align ? ALIGN(mmio_pref.start, align) - - mmio_pref.start : 0; - used_size = align + resource_size(res); - if (!res->parent) - mmio_pref.start = min(mmio_pref.start + used_size, - mmio_pref.end + 1); + list_for_each_entry(dev, &bus->devices, bus_list) { + if (!dev->is_virtfn) + remove_dev_resources(dev, &io, &mmio, &mmio_pref); } - io_per_hp = div64_ul(resource_size(&io), hotplug_bridges); - mmio_per_hp = div64_ul(resource_size(&mmio), hotplug_bridges); - mmio_pref_per_hp = div64_ul(resource_size(&mmio_pref), - hotplug_bridges); - /* - * Go over devices on this bus and distribute the remaining - * resource space between hotplug bridges. + * If there is at least one hotplug bridge on this bus it gets all + * the extra resource space that was left after the reductions + * above. + * + * If there are no hotplug bridges the extra resource space is + * split between non-hotplug bridges. This is to allow possible + * hotplug bridges below them to get the extra space as well. */ + if (hotplug_bridges) { + io_per_b = div64_ul(resource_size(&io), hotplug_bridges); + mmio_per_b = div64_ul(resource_size(&mmio), hotplug_bridges); + mmio_pref_per_b = div64_ul(resource_size(&mmio_pref), + hotplug_bridges); + } else { + io_per_b = div64_ul(resource_size(&io), normal_bridges); + mmio_per_b = div64_ul(resource_size(&mmio), normal_bridges); + mmio_pref_per_b = div64_ul(resource_size(&mmio_pref), + normal_bridges); + } + for_each_pci_bridge(dev, bus) { struct resource *res; struct pci_bus *b; b = dev->subordinate; - if (!b || !dev->is_hotplug_bridge) + if (!b) + continue; + if (hotplug_bridges && !dev->is_hotplug_bridge) continue; - /* - * Distribute available extra resources equally between - * hotplug-capable downstream ports taking alignment into - * account. - */ res = &dev->resource[PCI_BRIDGE_IO_WINDOW]; + + /* + * Make sure the split resource space is properly aligned + * for bridge windows (align it down to avoid going above + * what is available). + */ align = pci_resource_alignment(dev, res); - io.end = align ? io.start + ALIGN_DOWN(io_per_hp, align) - 1 - : io.start + io_per_hp - 1; + io.end = align ? io.start + ALIGN_DOWN(io_per_b, align) - 1 + : io.start + io_per_b - 1; + + /* + * The x_per_b holds the extra resource space that can be + * added for each bridge but there is the minimal already + * reserved as well so adjust x.start down accordingly to + * cover the whole space. + */ + io.start -= resource_size(res); res = &dev->resource[PCI_BRIDGE_MEM_WINDOW]; align = pci_resource_alignment(dev, res); - mmio.end = align ? mmio.start + ALIGN_DOWN(mmio_per_hp, align) - 1 - : mmio.start + mmio_per_hp - 1; + mmio.end = align ? mmio.start + ALIGN_DOWN(mmio_per_b, align) - 1 + : mmio.start + mmio_per_b - 1; + mmio.start -= resource_size(res); res = &dev->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; align = pci_resource_alignment(dev, res); mmio_pref.end = align ? mmio_pref.start + - ALIGN_DOWN(mmio_pref_per_hp, align) - 1 - : mmio_pref.start + mmio_pref_per_hp - 1; + ALIGN_DOWN(mmio_pref_per_b, align) - 1 + : mmio_pref.start + mmio_pref_per_b - 1; + mmio_pref.start -= resource_size(res); pci_bus_distribute_available_resources(b, add_list, io, mmio, mmio_pref); From dd9981a11d74ff2eb253bb5c459876f8bd3c6c36 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 2 Feb 2023 16:16:33 +0100 Subject: [PATCH 2006/4345] kernel/fail_function: fix memory leak with using debugfs_lookup() [ Upstream commit 2bb3669f576559db273efe49e0e69f82450efbca ] When calling debugfs_lookup() the result must have dput() called on it, otherwise the memory will leak over time. To make things simpler, just call debugfs_lookup_and_remove() instead which handles all of the logic at once. Cc: Andrew Morton Reviewed-by: Yang Yingliang Link: https://lore.kernel.org/r/20230202151633.2310897-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- kernel/fail_function.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/fail_function.c b/kernel/fail_function.c index b0b1ad93fa95..8f3795d8ac5b 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -163,10 +163,7 @@ static void fei_debugfs_add_attr(struct fei_attr *attr) static void fei_debugfs_remove_attr(struct fei_attr *attr) { - struct dentry *dir; - - dir = debugfs_lookup(attr->kp.symbol_name, fei_debugfs_dir); - debugfs_remove_recursive(dir); + debugfs_lookup_and_remove(attr->kp.symbol_name, fei_debugfs_dir); } static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs) From faa050d2ff8820f450b69b84645e74b6934ed5ad Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sat, 11 Feb 2023 10:33:21 +0800 Subject: [PATCH 2007/4345] PCI: loongson: Add more devices that need MRRS quirk [ Upstream commit c768f8c5f40fcdc6f058cc2f02592163d6c6716c ] Loongson-2K SOC and LS7A2000 chipset add new PCI IDs that need MRRS quirk. Add them. Link: https://lore.kernel.org/r/20230211023321.3530080-1-chenhuacai@loongson.cn Signed-off-by: Huacai Chen Signed-off-by: Bjorn Helgaas Signed-off-by: Sasha Levin --- drivers/pci/controller/pci-loongson.c | 33 +++++++++++++++++++-------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c index dc7b4e4293ce..e73e18a73833 100644 --- a/drivers/pci/controller/pci-loongson.c +++ b/drivers/pci/controller/pci-loongson.c @@ -13,9 +13,14 @@ #include "../pci.h" /* Device IDs */ -#define DEV_PCIE_PORT_0 0x7a09 -#define DEV_PCIE_PORT_1 0x7a19 -#define DEV_PCIE_PORT_2 0x7a29 +#define DEV_LS2K_PCIE_PORT0 0x1a05 +#define DEV_LS7A_PCIE_PORT0 0x7a09 +#define DEV_LS7A_PCIE_PORT1 0x7a19 +#define DEV_LS7A_PCIE_PORT2 0x7a29 +#define DEV_LS7A_PCIE_PORT3 0x7a39 +#define DEV_LS7A_PCIE_PORT4 0x7a49 +#define DEV_LS7A_PCIE_PORT5 0x7a59 +#define DEV_LS7A_PCIE_PORT6 0x7a69 #define DEV_LS2K_APB 0x7a02 #define DEV_LS7A_CONF 0x7a10 @@ -38,11 +43,11 @@ static void bridge_class_quirk(struct pci_dev *dev) dev->class = PCI_CLASS_BRIDGE_PCI << 8; } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_PCIE_PORT_0, bridge_class_quirk); + DEV_LS7A_PCIE_PORT0, bridge_class_quirk); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_PCIE_PORT_1, bridge_class_quirk); + DEV_LS7A_PCIE_PORT1, bridge_class_quirk); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_PCIE_PORT_2, bridge_class_quirk); + DEV_LS7A_PCIE_PORT2, bridge_class_quirk); static void system_bus_quirk(struct pci_dev *pdev) { @@ -72,11 +77,21 @@ static void loongson_mrrs_quirk(struct pci_dev *pdev) bridge->no_inc_mrrs = 1; } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_PCIE_PORT_0, loongson_mrrs_quirk); + DEV_LS2K_PCIE_PORT0, loongson_mrrs_quirk); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_PCIE_PORT_1, loongson_mrrs_quirk); + DEV_LS7A_PCIE_PORT0, loongson_mrrs_quirk); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_PCIE_PORT_2, loongson_mrrs_quirk); + DEV_LS7A_PCIE_PORT1, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT2, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT3, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT4, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT5, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT6, loongson_mrrs_quirk); static void __iomem *cfg1_map(struct loongson_pci *priv, int bus, unsigned int devfn, int where) From 01923e3196ee60b9357624c120b8426c7261ae15 Mon Sep 17 00:00:00 2001 From: Mengyuan Lou Date: Tue, 7 Feb 2023 18:24:19 +0800 Subject: [PATCH 2008/4345] PCI: Add ACS quirk for Wangxun NICs [ Upstream commit a2b9b123ccac913e9f9b80337d687a2fe786a634 ] Wangxun has verified there is no peer-to-peer between functions for the below selection of SFxxx, RP1000 and RP2000 NICS. They may be multi-function devices, but the hardware does not advertise ACS capability. Add an ACS quirk for these devices so the functions can be in independent IOMMU groups. Link: https://lore.kernel.org/r/20230207102419.44326-1-mengyuanlou@net-swift.com Signed-off-by: Mengyuan Lou Signed-off-by: Bjorn Helgaas Signed-off-by: Sasha Levin --- drivers/pci/quirks.c | 22 ++++++++++++++++++++++ include/linux/pci_ids.h | 2 ++ 2 files changed, 24 insertions(+) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index f30c42f0ac31..c1ebd5e12b06 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4797,6 +4797,26 @@ static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags) PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); } +/* + * Wangxun 10G/1G NICs have no ACS capability, and on multi-function + * devices, peer-to-peer transactions are not be used between the functions. + * So add an ACS quirk for below devices to isolate functions. + * SFxxx 1G NICs(em). + * RP1000/RP2000 10G NICs(sp). + */ +static int pci_quirk_wangxun_nic_acs(struct pci_dev *dev, u16 acs_flags) +{ + switch (dev->device) { + case 0x0100 ... 0x010F: + case 0x1001: + case 0x2001: + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); + } + + return false; +} + static const struct pci_dev_acs_enabled { u16 vendor; u16 device; @@ -4942,6 +4962,8 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_NXP, 0x8d9b, pci_quirk_nxp_rp_acs }, /* Zhaoxin Root/Downstream Ports */ { PCI_VENDOR_ID_ZHAOXIN, PCI_ANY_ID, pci_quirk_zhaoxin_pcie_ports_acs }, + /* Wangxun nics */ + { PCI_VENDOR_ID_WANGXUN, PCI_ANY_ID, pci_quirk_wangxun_nic_acs }, { 0 } }; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 69e310173fbc..2e1935917c24 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3033,6 +3033,8 @@ #define PCI_DEVICE_ID_INTEL_VMD_9A0B 0x9a0b #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 +#define PCI_VENDOR_ID_WANGXUN 0x8088 + #define PCI_VENDOR_ID_SCALEMP 0x8686 #define PCI_DEVICE_ID_SCALEMP_VSMP_CTL 0x1010 From 4d2423f15b36a7a11075faa46ce7327c4375fd63 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Mon, 13 Feb 2023 11:57:09 +0800 Subject: [PATCH 2009/4345] phy: rockchip-typec: Fix unsigned comparison with less than zero [ Upstream commit f765c59c5a72546a2d74a92ae5d0eb0329d8e247 ] The dp and ufp are defined as bool type, the return value type of function extcon_get_state should be int, so the type of dp and ufp are modified to int. ./drivers/phy/rockchip/phy-rockchip-typec.c:827:12-14: WARNING: Unsigned expression compared with zero: dp > 0. Reported-by: Abaci Robot Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=3962 Signed-off-by: Jiapeng Chong Link: https://lore.kernel.org/r/20230213035709.99027-1-jiapeng.chong@linux.alibaba.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/rockchip/phy-rockchip-typec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c index 70a31251b202..20f787d5ec58 100644 --- a/drivers/phy/rockchip/phy-rockchip-typec.c +++ b/drivers/phy/rockchip/phy-rockchip-typec.c @@ -808,9 +808,8 @@ static int tcphy_get_mode(struct rockchip_typec_phy *tcphy) struct extcon_dev *edev = tcphy->extcon; union extcon_property_value property; unsigned int id; - bool ufp, dp; u8 mode; - int ret; + int ret, ufp, dp; if (!edev) return MODE_DFP_USB; From e5ca5b71363a0a4902f8968191e8ddf939b5018e Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Fri, 2 Dec 2022 16:18:11 +0000 Subject: [PATCH 2010/4345] soundwire: cadence: Remove wasted space in response_buf [ Upstream commit 827c32d0df4bbe0d1c47d79f6a5eabfe9ac75216 ] The response_buf was declared much larger (128 entries) than the number of responses that could ever be written into it. The Cadence IP is configurable up to a maximum of 32 entries, and the datasheet says that RX_FIFO_AVAIL can be 2 larger than this. So allow up to 34 responses. Also add checking in cdns_read_response() to prevent overflowing reponse_buf if RX_FIFO_AVAIL contains an unexpectedly large number. Signed-off-by: Richard Fitzgerald Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20221202161812.4186897-3-rf@opensource.cirrus.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/soundwire/cadence_master.c | 7 +++++++ drivers/soundwire/cadence_master.h | 13 ++++++++++++- 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index a3247692ddc0..292c4460eaaa 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -725,8 +725,15 @@ static void cdns_read_response(struct sdw_cdns *cdns) u32 num_resp, cmd_base; int i; + /* RX_FIFO_AVAIL can be 2 entries more than the FIFO size */ + BUILD_BUG_ON(ARRAY_SIZE(cdns->response_buf) < CDNS_MCP_CMD_LEN + 2); + num_resp = cdns_readl(cdns, CDNS_MCP_FIFOSTAT); num_resp &= CDNS_MCP_RX_FIFO_AVAIL; + if (num_resp > ARRAY_SIZE(cdns->response_buf)) { + dev_warn(cdns->dev, "RX AVAIL %d too long\n", num_resp); + num_resp = ARRAY_SIZE(cdns->response_buf); + } cmd_base = CDNS_MCP_CMD_BASE; diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h index 4d1aab5b5ec2..e7f0108d417c 100644 --- a/drivers/soundwire/cadence_master.h +++ b/drivers/soundwire/cadence_master.h @@ -8,6 +8,12 @@ #define SDW_CADENCE_GSYNC_KHZ 4 /* 4 kHz */ #define SDW_CADENCE_GSYNC_HZ (SDW_CADENCE_GSYNC_KHZ * 1000) +/* + * The Cadence IP supports up to 32 entries in the FIFO, though implementations + * can configure the IP to have a smaller FIFO. + */ +#define CDNS_MCP_IP_MAX_CMD_LEN 32 + /** * struct sdw_cdns_pdi: PDI (Physical Data Interface) instance * @@ -119,7 +125,12 @@ struct sdw_cdns { struct sdw_bus bus; unsigned int instance; - u32 response_buf[0x80]; + /* + * The datasheet says the RX FIFO AVAIL can be 2 entries more + * than the FIFO capacity, so allow for this. + */ + u32 response_buf[CDNS_MCP_IP_MAX_CMD_LEN + 2]; + struct completion tx_complete; struct sdw_defer *defer; From a6549336f574658433e10a34e72f7669cac6afbe Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Fri, 2 Dec 2022 16:18:12 +0000 Subject: [PATCH 2011/4345] soundwire: cadence: Drain the RX FIFO after an IO timeout [ Upstream commit 0603a47bd3a8f439d7844b841eee1819353063e0 ] If wait_for_completion_timeout() times-out in _cdns_xfer_msg() it is possible that something could have been written to the RX FIFO. In this case, we should drain the RX FIFO so that anything in it doesn't carry over and mess up the next transfer. Obviously, if we got to this state something went wrong, and we don't really know the state of everything. The cleanup in this situation cannot be bullet-proof but we should attempt to avoid breaking future transaction, if only to reduce the amount of error noise when debugging the failure from a kernel log. Note that this patch only implements the draining for blocking (non-deferred) transfers. The deferred API doesn't have any proper handling of error conditions and would need some re-design before implementing cleanup. That is a task for a separate patch... Signed-off-by: Richard Fitzgerald Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20221202161812.4186897-4-rf@opensource.cirrus.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/soundwire/cadence_master.c | 50 ++++++++++++++++-------------- 1 file changed, 27 insertions(+), 23 deletions(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 292c4460eaaa..18e7d158fcca 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -511,6 +511,29 @@ cdns_fill_msg_resp(struct sdw_cdns *cdns, return SDW_CMD_OK; } +static void cdns_read_response(struct sdw_cdns *cdns) +{ + u32 num_resp, cmd_base; + int i; + + /* RX_FIFO_AVAIL can be 2 entries more than the FIFO size */ + BUILD_BUG_ON(ARRAY_SIZE(cdns->response_buf) < CDNS_MCP_CMD_LEN + 2); + + num_resp = cdns_readl(cdns, CDNS_MCP_FIFOSTAT); + num_resp &= CDNS_MCP_RX_FIFO_AVAIL; + if (num_resp > ARRAY_SIZE(cdns->response_buf)) { + dev_warn(cdns->dev, "RX AVAIL %d too long\n", num_resp); + num_resp = ARRAY_SIZE(cdns->response_buf); + } + + cmd_base = CDNS_MCP_CMD_BASE; + + for (i = 0; i < num_resp; i++) { + cdns->response_buf[i] = cdns_readl(cdns, cmd_base); + cmd_base += CDNS_MCP_CMD_WORD_LEN; + } +} + static enum sdw_command_response _cdns_xfer_msg(struct sdw_cdns *cdns, struct sdw_msg *msg, int cmd, int offset, int count, bool defer) @@ -552,6 +575,10 @@ _cdns_xfer_msg(struct sdw_cdns *cdns, struct sdw_msg *msg, int cmd, dev_err(cdns->dev, "IO transfer timed out, cmd %d device %d addr %x len %d\n", cmd, msg->dev_num, msg->addr, msg->len); msg->len = 0; + + /* Drain anything in the RX_FIFO */ + cdns_read_response(cdns); + return SDW_CMD_TIMEOUT; } @@ -720,29 +747,6 @@ EXPORT_SYMBOL(cdns_reset_page_addr); * IRQ handling */ -static void cdns_read_response(struct sdw_cdns *cdns) -{ - u32 num_resp, cmd_base; - int i; - - /* RX_FIFO_AVAIL can be 2 entries more than the FIFO size */ - BUILD_BUG_ON(ARRAY_SIZE(cdns->response_buf) < CDNS_MCP_CMD_LEN + 2); - - num_resp = cdns_readl(cdns, CDNS_MCP_FIFOSTAT); - num_resp &= CDNS_MCP_RX_FIFO_AVAIL; - if (num_resp > ARRAY_SIZE(cdns->response_buf)) { - dev_warn(cdns->dev, "RX AVAIL %d too long\n", num_resp); - num_resp = ARRAY_SIZE(cdns->response_buf); - } - - cmd_base = CDNS_MCP_CMD_BASE; - - for (i = 0; i < num_resp; i++) { - cdns->response_buf[i] = cdns_readl(cdns, cmd_base); - cmd_base += CDNS_MCP_CMD_WORD_LEN; - } -} - static int cdns_update_slave_status(struct sdw_cdns *cdns, u32 slave0, u32 slave1) { From 7123a4337bf73132bbfb5437e4dc83ba864a9a1e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 28 Feb 2023 16:28:57 -0800 Subject: [PATCH 2012/4345] net: tls: avoid hanging tasks on the tx_lock commit f3221361dc85d4de22586ce8441ec2c67b454f5d upstream. syzbot sent a hung task report and Eric explains that adversarial receiver may keep RWIN at 0 for a long time, so we are not guaranteed to make forward progress. Thread which took tx_lock and went to sleep may not release tx_lock for hours. Use interruptible sleep where possible and reschedule the work if it can't take the lock. Testing: existing selftest passes Reported-by: syzbot+9c0268252b8ef967c62e@syzkaller.appspotmail.com Fixes: 79ffe6087e91 ("net/tls: add a TX lock") Link: https://lore.kernel.org/all/000000000000e412e905f5b46201@google.com/ Cc: stable@vger.kernel.org # wait 4 weeks Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230301002857.2101894-1-kuba@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/tls/tls_sw.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 21f20c3cda97..ac7feadb4390 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -949,7 +949,9 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) MSG_CMSG_COMPAT)) return -EOPNOTSUPP; - mutex_lock(&tls_ctx->tx_lock); + ret = mutex_lock_interruptible(&tls_ctx->tx_lock); + if (ret) + return ret; lock_sock(sk); if (unlikely(msg->msg_controllen)) { @@ -1283,7 +1285,9 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) return -EOPNOTSUPP; - mutex_lock(&tls_ctx->tx_lock); + ret = mutex_lock_interruptible(&tls_ctx->tx_lock); + if (ret) + return ret; lock_sock(sk); ret = tls_sw_do_sendpage(sk, page, offset, size, flags); release_sock(sk); @@ -2266,11 +2270,19 @@ static void tx_work_handler(struct work_struct *work) if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) return; - mutex_lock(&tls_ctx->tx_lock); - lock_sock(sk); - tls_tx_records(sk, -1); - release_sock(sk); - mutex_unlock(&tls_ctx->tx_lock); + + if (mutex_trylock(&tls_ctx->tx_lock)) { + lock_sock(sk); + tls_tx_records(sk, -1); + release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); + } else if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) { + /* Someone is holding the tx_lock, they will likely run Tx + * and cancel the work on their way out of the lock section. + * Schedule a long delay just in case. + */ + schedule_delayed_work(&ctx->tx_work.work, msecs_to_jiffies(10)); + } } void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) From 9554af98018cc29aea9a9b277ae10061e7e625f2 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 17 Dec 2020 14:31:21 -0800 Subject: [PATCH 2013/4345] x86/resctrl: Apply READ_ONCE/WRITE_ONCE to task_struct.{rmid,closid} commit 6d3b47ddffed70006cf4ba360eef61e9ce097d8f upstream. A CPU's current task can have its {closid, rmid} fields read locally while they are being concurrently written to from another CPU. This can happen anytime __resctrl_sched_in() races with either __rdtgroup_move_task() or rdt_move_group_tasks(). Prevent load / store tearing for those accesses by giving them the READ_ONCE() / WRITE_ONCE() treatment. Signed-off-by: Valentin Schneider Signed-off-by: Reinette Chatre Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/9921fda88ad81afb9885b517fbe864a2bc7c35a9.1608243147.git.reinette.chatre@intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/resctrl.h | 11 +++++++---- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 10 +++++----- 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 07603064df8f..d60ed0668a59 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -56,19 +56,22 @@ static void __resctrl_sched_in(void) struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); u32 closid = state->default_closid; u32 rmid = state->default_rmid; + u32 tmp; /* * If this task has a closid/rmid assigned, use it. * Else use the closid/rmid assigned to this cpu. */ if (static_branch_likely(&rdt_alloc_enable_key)) { - if (current->closid) - closid = current->closid; + tmp = READ_ONCE(current->closid); + if (tmp) + closid = tmp; } if (static_branch_likely(&rdt_mon_enable_key)) { - if (current->rmid) - rmid = current->rmid; + tmp = READ_ONCE(current->rmid); + if (tmp) + rmid = tmp; } if (closid != state->cur_closid || rmid != state->cur_rmid) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index ff26de11b3f1..296647930251 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -563,11 +563,11 @@ static int __rdtgroup_move_task(struct task_struct *tsk, */ if (rdtgrp->type == RDTCTRL_GROUP) { - tsk->closid = rdtgrp->closid; - tsk->rmid = rdtgrp->mon.rmid; + WRITE_ONCE(tsk->closid, rdtgrp->closid); + WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); } else if (rdtgrp->type == RDTMON_GROUP) { if (rdtgrp->mon.parent->closid == tsk->closid) { - tsk->rmid = rdtgrp->mon.rmid; + WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); } else { rdt_last_cmd_puts("Can't move task to different control group\n"); return -EINVAL; @@ -2312,8 +2312,8 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, for_each_process_thread(p, t) { if (!from || is_closid_match(t, from) || is_rmid_match(t, from)) { - t->closid = to->closid; - t->rmid = to->mon.rmid; + WRITE_ONCE(t->closid, to->closid); + WRITE_ONCE(t->rmid, to->mon.rmid); /* * Order the closid/rmid stores above before the loads From 411b8ad505f7686de182749cb293a8e887c2dd49 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 7 Mar 2023 13:06:29 -0800 Subject: [PATCH 2014/4345] x86/resctl: fix scheduler confusion with 'current' commit 7fef099702527c3b2c5234a2ea6a24411485a13a upstream. The implementation of 'current' on x86 is very intentionally special: it is a very common thing to look up, and it uses 'this_cpu_read_stable()' to get the current thread pointer efficiently from per-cpu storage. And the keyword in there is 'stable': the current thread pointer never changes as far as a single thread is concerned. Even if when a thread is preempted, or moved to another CPU, or even across an explicit call 'schedule()' that thread will still have the same value for 'current'. It is, after all, the kernel base pointer to thread-local storage. That's why it's stable to begin with, but it's also why it's important enough that we have that special 'this_cpu_read_stable()' access for it. So this is all done very intentionally to allow the compiler to treat 'current' as a value that never visibly changes, so that the compiler can do CSE and combine multiple different 'current' accesses into one. However, there is obviously one very special situation when the currently running thread does actually change: inside the scheduler itself. So the scheduler code paths are special, and do not have a 'current' thread at all. Instead there are _two_ threads: the previous and the next thread - typically called 'prev' and 'next' (or prev_p/next_p) internally. So this is all actually quite straightforward and simple, and not all that complicated. Except for when you then have special code that is run in scheduler context, that code then has to be aware that 'current' isn't really a valid thing. Did you mean 'prev'? Did you mean 'next'? In fact, even if then look at the code, and you use 'current' after the new value has been assigned to the percpu variable, we have explicitly told the compiler that 'current' is magical and always stable. So the compiler is quite free to use an older (or newer) value of 'current', and the actual assignment to the percpu storage is not relevant even if it might look that way. Which is exactly what happened in the resctl code, that blithely used 'current' in '__resctrl_sched_in()' when it really wanted the new process state (as implied by the name: we're scheduling 'into' that new resctl state). And clang would end up just using the old thread pointer value at least in some configurations. This could have happened with gcc too, and purely depends on random compiler details. Clang just seems to have been more aggressive about moving the read of the per-cpu current_task pointer around. The fix is trivial: just make the resctl code adhere to the scheduler rules of using the prev/next thread pointer explicitly, instead of using 'current' in a situation where it just wasn't valid. That same code is then also used outside of the scheduler context (when a thread resctl state is explicitly changed), and then we will just pass in 'current' as that pointer, of course. There is no ambiguity in that case. The fix may be trivial, but noticing and figuring out what went wrong was not. The credit for that goes to Stephane Eranian. Reported-by: Stephane Eranian Link: https://lore.kernel.org/lkml/20230303231133.1486085-1-eranian@google.com/ Link: https://lore.kernel.org/lkml/alpine.LFD.2.01.0908011214330.3304@localhost.localdomain/ Reviewed-by: Nick Desaulniers Tested-by: Tony Luck Tested-by: Stephane Eranian Tested-by: Babu Moger Cc: stable@kernel.org Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/resctrl.h | 12 ++++++------ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 4 ++-- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index d60ed0668a59..b9ccdf5ea98b 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -51,7 +51,7 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); * simple as possible. * Must be called with preemption disabled. */ -static void __resctrl_sched_in(void) +static inline void __resctrl_sched_in(struct task_struct *tsk) { struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); u32 closid = state->default_closid; @@ -63,13 +63,13 @@ static void __resctrl_sched_in(void) * Else use the closid/rmid assigned to this cpu. */ if (static_branch_likely(&rdt_alloc_enable_key)) { - tmp = READ_ONCE(current->closid); + tmp = READ_ONCE(tsk->closid); if (tmp) closid = tmp; } if (static_branch_likely(&rdt_mon_enable_key)) { - tmp = READ_ONCE(current->rmid); + tmp = READ_ONCE(tsk->rmid); if (tmp) rmid = tmp; } @@ -81,17 +81,17 @@ static void __resctrl_sched_in(void) } } -static inline void resctrl_sched_in(void) +static inline void resctrl_sched_in(struct task_struct *tsk) { if (static_branch_likely(&rdt_enable_key)) - __resctrl_sched_in(); + __resctrl_sched_in(tsk); } void resctrl_cpu_detect(struct cpuinfo_x86 *c); #else -static inline void resctrl_sched_in(void) {} +static inline void resctrl_sched_in(struct task_struct *tsk) {} static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {} #endif /* CONFIG_X86_CPU_RESCTRL */ diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 296647930251..1a943743cfe4 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -311,7 +311,7 @@ static void update_cpu_closid_rmid(void *info) * executing task might have its own closid selected. Just reuse * the context switch code. */ - resctrl_sched_in(); + resctrl_sched_in(current); } /* @@ -532,7 +532,7 @@ static void _update_task_closid_rmid(void *task) * Otherwise, the MSR is updated when the task is scheduled in. */ if (task == current) - resctrl_sched_in(); + resctrl_sched_in(task); } static void update_task_closid_rmid(struct task_struct *t) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 98bf8fd18902..3b4c394a1a76 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -214,7 +214,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) switch_fpu_finish(next_p); /* Load the Intel cache allocation PQR MSR. */ - resctrl_sched_in(); + resctrl_sched_in(next_p); return prev_p; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ad3f82a18de9..1d8bc4736fb7 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -629,7 +629,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) } /* Load the Intel cache allocation PQR MSR. */ - resctrl_sched_in(); + resctrl_sched_in(next_p); return prev_p; } From ee4a4282d78d96e07e714c28ca54679713fa2157 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Wed, 14 Dec 2022 20:42:56 +0200 Subject: [PATCH 2015/4345] drm/display/dp_mst: Fix down/up message handling after sink disconnect commit 1d082618bbf3b6755b8cc68c0a8122af2842d593 upstream. If the sink gets disconnected during receiving a multi-packet DP MST AUX down-reply/up-request sideband message, the state keeping track of which packets have been received already is not reset. This results in a failed sanity check for the subsequent message packet received after a sink is reconnected (due to the pending message not yet completed with an end-of-message-transfer packet), indicated by the "sideband msg set header failed" error. Fix the above by resetting the up/down message reception state after a disconnect event. Cc: Lyude Paul Cc: # v3.17+ Signed-off-by: Imre Deak Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20221214184258.2869417-1-imre.deak@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_dp_mst_topology.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 0feeac52e4eb..9f40437ee252 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -3769,6 +3769,9 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms set_bit(0, &mgr->payload_mask); mgr->vcpi_mask = 0; mgr->payload_id_table_cleared = false; + + memset(&mgr->down_rep_recv, 0, sizeof(mgr->down_rep_recv)); + memset(&mgr->up_req_recv, 0, sizeof(mgr->up_req_recv)); } out_unlock: From d90967f850b1f2ff600d2dcc4261487ffd23e523 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Wed, 14 Dec 2022 20:42:57 +0200 Subject: [PATCH 2016/4345] drm/display/dp_mst: Fix down message handling after a packet reception error commit 1241aedb6b5c7a5a8ad73e5eb3a41cfe18a3e00e upstream. After an error during receiving a packet for a multi-packet DP MST sideband message, the state tracking which packets have been received already is not reset. This prevents the reception of subsequent down messages (due to the pending message not yet completed with an end-of-message-transfer packet). Fix the above by resetting the reception state after a packet error. Cc: Lyude Paul Cc: # v3.17+ Signed-off-by: Imre Deak Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20221214184258.2869417-2-imre.deak@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_dp_mst_topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 9f40437ee252..b5e15933cb5f 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -3988,7 +3988,7 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) struct drm_dp_sideband_msg_rx *msg = &mgr->down_rep_recv; if (!drm_dp_get_one_sb_msg(mgr, false, &mstb)) - goto out; + goto out_clear_reply; /* Multi-packet message transmission, don't clear the reply */ if (!msg->have_eomt) From 7474be26b032f682b2166beb4a92c533f4de6a76 Mon Sep 17 00:00:00 2001 From: Nguyen Dinh Phi Date: Fri, 8 Oct 2021 03:04:24 +0800 Subject: [PATCH 2017/4345] Bluetooth: hci_sock: purge socket queues in the destruct() callback commit 709fca500067524381e28a5f481882930eebac88 upstream. The receive path may take the socket right before hci_sock_release(), but it may enqueue the packets to the socket queues after the call to skb_queue_purge(), therefore the socket can be destroyed without clear its queues completely. Moving these skb_queue_purge() to the hci_sock_destruct() will fix this issue, because nothing is referencing the socket at this point. Signed-off-by: Nguyen Dinh Phi Reported-by: syzbot+4c4ffd1e1094dae61035@syzkaller.appspotmail.com Signed-off-by: Marcel Holtmann Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/hci_sock.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 71d18d3295f5..73779af2fed6 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -888,10 +888,6 @@ static int hci_sock_release(struct socket *sock) } sock_orphan(sk); - - skb_queue_purge(&sk->sk_receive_queue); - skb_queue_purge(&sk->sk_write_queue); - release_sock(sk); sock_put(sk); return 0; @@ -2012,6 +2008,12 @@ done: return err; } +static void hci_sock_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge(&sk->sk_write_queue); +} + static const struct proto_ops hci_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, @@ -2065,6 +2067,7 @@ static int hci_sock_create(struct net *net, struct socket *sock, int protocol, sock->state = SS_UNCONNECTED; sk->sk_state = BT_OPEN; + sk->sk_destruct = hci_sock_destruct; bt_sock_link(&hci_sk_list, sk); return 0; From 0a1d0c79eaec745b6e9cafa0a55a2c762e93eeb9 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 13 Feb 2023 20:45:48 +0000 Subject: [PATCH 2018/4345] tcp: Fix listen() regression in 5.10.163 commit fdaf88531cfd17b2a710cceb3141ef6f9085ff40 upstream. When we backport dadd0dcaa67d ("net/ulp: prevent ULP without clone op from entering the LISTEN status"), we have accidentally backported a part of 7a7160edf1bf ("net: Return errno in sk->sk_prot->get_port().") and removed err = -EADDRINUSE in inet_csk_listen_start(). Thus, listen() no longer returns -EADDRINUSE even if ->get_port() failed as reported in [0]. We set -EADDRINUSE to err just before ->get_port() to fix the regression. [0]: https://lore.kernel.org/stable/EF8A45D0-768A-4CD5-9A8A-0FA6E610ABF7@winter.cafe/ Reported-by: Winter Signed-off-by: Kuniyuki Iwashima Signed-off-by: Greg Kroah-Hartman --- net/ipv4/inet_connection_sock.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 9ed59147ef66..e05dd87848f7 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -946,6 +946,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog) * It is OK, because this socket enters to hash table only * after validation is complete. */ + err = -EADDRINUSE; inet_sk_state_store(sk, TCP_LISTEN); if (!sk->sk_prot->get_port(sk, inet->inet_num)) { inet->inet_sport = htons(inet->inet_num); From c5fe3fba1b7bfecb6f17f93a433782b8500fe377 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Thu, 2 Mar 2023 09:28:16 -0800 Subject: [PATCH 2019/4345] drm/virtio: Fix error code in virtio_gpu_object_shmem_init() In virtio_gpu_object_shmem_init() we are passing NULL to PTR_ERR, which is returning 0/success. Fix this by storing error value in 'ret' variable before assigning shmem->pages to NULL. Found using static analysis with Smatch. Fixes: 64b88afbd92f ("drm/virtio: Correct drm_gem_shmem_get_sg_table() error handling") Signed-off-by: Harshit Mogalapalli Reviewed-by: Dmitry Osipenko Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/virtio/virtgpu_object.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 168148686001..49fa59e09187 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -159,8 +159,9 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, shmem->pages = drm_gem_shmem_get_sg_table(&bo->base.base); if (IS_ERR(shmem->pages)) { drm_gem_shmem_unpin(&bo->base.base); + ret = PTR_ERR(shmem->pages); shmem->pages = NULL; - return PTR_ERR(shmem->pages); + return ret; } if (use_dma_api) { From 9d83b69e934db163fa60456dab1f01fd23f579ec Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Wed, 23 Dec 2020 14:35:20 +0100 Subject: [PATCH 2020/4345] media: uvcvideo: Provide sync and async uvc_ctrl_status_event commit d9c8763e61295be0a21dc04ad9c379d5d17c3d86 upstream. Split the functionality of void uvc_ctrl_status_event_work in two, so it can be called by functions outside interrupt context and not part of an URB. Signed-off-by: Ricardo Ribalda Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/uvc/uvc_ctrl.c | 25 +++++++++++++++---------- drivers/media/usb/uvc/uvc_status.c | 3 ++- drivers/media/usb/uvc/uvcvideo.h | 4 +++- 3 files changed, 20 insertions(+), 12 deletions(-) diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index f479d8971dfb..327ffc232993 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -1275,17 +1275,12 @@ static void uvc_ctrl_send_slave_event(struct uvc_video_chain *chain, uvc_ctrl_send_event(chain, handle, ctrl, mapping, val, changes); } -static void uvc_ctrl_status_event_work(struct work_struct *work) +void uvc_ctrl_status_event(struct uvc_video_chain *chain, + struct uvc_control *ctrl, const u8 *data) { - struct uvc_device *dev = container_of(work, struct uvc_device, - async_ctrl.work); - struct uvc_ctrl_work *w = &dev->async_ctrl; - struct uvc_video_chain *chain = w->chain; struct uvc_control_mapping *mapping; - struct uvc_control *ctrl = w->ctrl; struct uvc_fh *handle; unsigned int i; - int ret; mutex_lock(&chain->ctrl_mutex); @@ -1293,7 +1288,7 @@ static void uvc_ctrl_status_event_work(struct work_struct *work) ctrl->handle = NULL; list_for_each_entry(mapping, &ctrl->info.mappings, list) { - s32 value = __uvc_ctrl_get_value(mapping, w->data); + s32 value = __uvc_ctrl_get_value(mapping, data); /* * handle may be NULL here if the device sends auto-update @@ -1312,6 +1307,16 @@ static void uvc_ctrl_status_event_work(struct work_struct *work) } mutex_unlock(&chain->ctrl_mutex); +} + +static void uvc_ctrl_status_event_work(struct work_struct *work) +{ + struct uvc_device *dev = container_of(work, struct uvc_device, + async_ctrl.work); + struct uvc_ctrl_work *w = &dev->async_ctrl; + int ret; + + uvc_ctrl_status_event(w->chain, w->ctrl, w->data); /* Resubmit the URB. */ w->urb->interval = dev->int_ep->desc.bInterval; @@ -1321,8 +1326,8 @@ static void uvc_ctrl_status_event_work(struct work_struct *work) ret); } -bool uvc_ctrl_status_event(struct urb *urb, struct uvc_video_chain *chain, - struct uvc_control *ctrl, const u8 *data) +bool uvc_ctrl_status_event_async(struct urb *urb, struct uvc_video_chain *chain, + struct uvc_control *ctrl, const u8 *data) { struct uvc_device *dev = chain->dev; struct uvc_ctrl_work *w = &dev->async_ctrl; diff --git a/drivers/media/usb/uvc/uvc_status.c b/drivers/media/usb/uvc/uvc_status.c index 2bdb0ff203f8..3e26d82a906d 100644 --- a/drivers/media/usb/uvc/uvc_status.c +++ b/drivers/media/usb/uvc/uvc_status.c @@ -179,7 +179,8 @@ static bool uvc_event_control(struct urb *urb, switch (status->bAttribute) { case UVC_CTRL_VALUE_CHANGE: - return uvc_ctrl_status_event(urb, chain, ctrl, status->bValue); + return uvc_ctrl_status_event_async(urb, chain, ctrl, + status->bValue); case UVC_CTRL_INFO_CHANGE: case UVC_CTRL_FAILURE_CHANGE: diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index 284200becbbd..8a590e0895fb 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -839,7 +839,9 @@ int uvc_ctrl_add_mapping(struct uvc_video_chain *chain, int uvc_ctrl_init_device(struct uvc_device *dev); void uvc_ctrl_cleanup_device(struct uvc_device *dev); int uvc_ctrl_restore_values(struct uvc_device *dev); -bool uvc_ctrl_status_event(struct urb *urb, struct uvc_video_chain *chain, +bool uvc_ctrl_status_event_async(struct urb *urb, struct uvc_video_chain *chain, + struct uvc_control *ctrl, const u8 *data); +void uvc_ctrl_status_event(struct uvc_video_chain *chain, struct uvc_control *ctrl, const u8 *data); int uvc_ctrl_begin(struct uvc_video_chain *chain); From 331c18e8ac810eec0058834a3a5fd35b54d7a7f9 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Thu, 5 Jan 2023 15:31:29 +0100 Subject: [PATCH 2021/4345] media: uvcvideo: Fix race condition with usb_kill_urb commit 619d9b710cf06f7a00a17120ca92333684ac45a8 upstream. usb_kill_urb warranties that all the handlers are finished when it returns, but does not protect against threads that might be handling asynchronously the urb. For UVC, the function uvc_ctrl_status_event_async() takes care of control changes asynchronously. If the code is executed in the following order: CPU 0 CPU 1 ===== ===== uvc_status_complete() uvc_status_stop() uvc_ctrl_status_event_work() uvc_status_start() -> FAIL Then uvc_status_start will keep failing and this error will be shown: <4>[ 5.540139] URB 0000000000000000 submitted while active drivers/usb/core/urb.c:378 usb_submit_urb+0x4c3/0x528 Let's improve the current situation, by not re-submiting the urb if we are stopping the status event. Also process the queued work (if any) during stop. CPU 0 CPU 1 ===== ===== uvc_status_complete() uvc_status_stop() uvc_status_start() uvc_ctrl_status_event_work() -> FAIL Hopefully, with the usb layer protection this should be enough to cover all the cases. Cc: stable@vger.kernel.org Fixes: e5225c820c05 ("media: uvcvideo: Send a control event when a Control Change interrupt arrives") Reviewed-by: Yunke Cao Signed-off-by: Ricardo Ribalda Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/uvc/uvc_ctrl.c | 5 ++++ drivers/media/usb/uvc/uvc_status.c | 37 ++++++++++++++++++++++++++++++ drivers/media/usb/uvc/uvcvideo.h | 1 + 3 files changed, 43 insertions(+) diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index 327ffc232993..5e0acabed37a 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -6,6 +6,7 @@ * Laurent Pinchart (laurent.pinchart@ideasonboard.com) */ +#include #include #include #include @@ -1318,6 +1319,10 @@ static void uvc_ctrl_status_event_work(struct work_struct *work) uvc_ctrl_status_event(w->chain, w->ctrl, w->data); + /* The barrier is needed to synchronize with uvc_status_stop(). */ + if (smp_load_acquire(&dev->flush_status)) + return; + /* Resubmit the URB. */ w->urb->interval = dev->int_ep->desc.bInterval; ret = usb_submit_urb(w->urb, GFP_KERNEL); diff --git a/drivers/media/usb/uvc/uvc_status.c b/drivers/media/usb/uvc/uvc_status.c index 3e26d82a906d..73725051cc16 100644 --- a/drivers/media/usb/uvc/uvc_status.c +++ b/drivers/media/usb/uvc/uvc_status.c @@ -6,6 +6,7 @@ * Laurent Pinchart (laurent.pinchart@ideasonboard.com) */ +#include #include #include #include @@ -310,5 +311,41 @@ int uvc_status_start(struct uvc_device *dev, gfp_t flags) void uvc_status_stop(struct uvc_device *dev) { + struct uvc_ctrl_work *w = &dev->async_ctrl; + + /* + * Prevent the asynchronous control handler from requeing the URB. The + * barrier is needed so the flush_status change is visible to other + * CPUs running the asynchronous handler before usb_kill_urb() is + * called below. + */ + smp_store_release(&dev->flush_status, true); + + /* + * Cancel any pending asynchronous work. If any status event was queued, + * process it synchronously. + */ + if (cancel_work_sync(&w->work)) + uvc_ctrl_status_event(w->chain, w->ctrl, w->data); + + /* Kill the urb. */ usb_kill_urb(dev->int_urb); + + /* + * The URB completion handler may have queued asynchronous work. This + * won't resubmit the URB as flush_status is set, but it needs to be + * cancelled before returning or it could then race with a future + * uvc_status_start() call. + */ + if (cancel_work_sync(&w->work)) + uvc_ctrl_status_event(w->chain, w->ctrl, w->data); + + /* + * From this point, there are no events on the queue and the status URB + * is dead. No events will be queued until uvc_status_start() is called. + * The barrier is needed to make sure that flush_status is visible to + * uvc_ctrl_status_event_work() when uvc_status_start() will be called + * again. + */ + smp_store_release(&dev->flush_status, false); } diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index 8a590e0895fb..c75990c0957e 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -670,6 +670,7 @@ struct uvc_device { /* Status Interrupt Endpoint */ struct usb_host_endpoint *int_ep; struct urb *int_urb; + bool flush_status; u8 *status; struct input_dev *input; char input_phys[64]; From f73bbfb47ff10d8a6288bd37a833fb987cc5a6f2 Mon Sep 17 00:00:00 2001 From: Salvatore Bonaccorso Date: Wed, 8 Mar 2023 17:14:56 +0100 Subject: [PATCH 2022/4345] Revert "scsi: mpt3sas: Fix return value check of dma_get_required_mask()" This reverts commit e0e0747de0ea3dd87cdbb0393311e17471a9baf1. As noted in 1a2dcbdde82e ("scsi: mpt3sas: re-do lost mpt3sas DMA mask fix") in mainline there was a mis-merge in commit 62e6e5940c0c ("Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi"). causing that the fix needed to be redone later on again. To make series of patches apply cleanly to the stable series where e0e0747de0ea ("scsi: mpt3sas: Fix return value check of dma_get_required_mask()") was backported, revert the aforementioned commit. No upstream commit exists for this commit. Link: https://lore.kernel.org/regressions/yq1sfehmjnb.fsf@ca-mkp.ca.oracle.com/ Signed-off-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/mpt3sas/mpt3sas_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 2ad75c9a9088..c7830f7ad19d 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2825,7 +2825,7 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 || ioc->use_32bit_dma || - dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) + dma_get_required_mask(&pdev->dev) <= 32) ioc->dma_mask = 32; /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */ else if (ioc->hba_mpi_version_belonged > MPI2_VERSION) From 2392303df240e7d036df8872ada176734e108036 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Thu, 25 Aug 2022 13:24:54 +0530 Subject: [PATCH 2023/4345] scsi: mpt3sas: Don't change DMA mask while reallocating pools commit 9df650963bf6d6c2c3fcd325d8c44ca2b99554fe upstream. When a pool crosses the 4GB boundary region then before reallocating pools change the coherent DMA mask to 32 bits and keep the normal DMA mask set to 63/64 bits. Link: https://lore.kernel.org/r/20220825075457.16422-2-sreekanth.reddy@broadcom.com Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen Signed-off-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/mpt3sas/mpt3sas_base.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index c7830f7ad19d..eb37460ce109 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2822,19 +2822,26 @@ static int _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) { struct sysinfo s; + u64 coherent_dma_mask, dma_mask; - if (ioc->is_mcpu_endpoint || - sizeof(dma_addr_t) == 4 || ioc->use_32bit_dma || - dma_get_required_mask(&pdev->dev) <= 32) + if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 || + dma_get_required_mask(&pdev->dev) <= 32) { ioc->dma_mask = 32; + coherent_dma_mask = dma_mask = DMA_BIT_MASK(32); /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */ - else if (ioc->hba_mpi_version_belonged > MPI2_VERSION) + } else if (ioc->hba_mpi_version_belonged > MPI2_VERSION) { ioc->dma_mask = 63; - else + coherent_dma_mask = dma_mask = DMA_BIT_MASK(63); + } else { ioc->dma_mask = 64; + coherent_dma_mask = dma_mask = DMA_BIT_MASK(64); + } - if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(ioc->dma_mask)) || - dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(ioc->dma_mask))) + if (ioc->use_32bit_dma) + coherent_dma_mask = DMA_BIT_MASK(32); + + if (dma_set_mask(&pdev->dev, dma_mask) || + dma_set_coherent_mask(&pdev->dev, coherent_dma_mask)) return -ENODEV; if (ioc->dma_mask > 32) { From 747652f9c5037cc27544c1fe44c4125876e4ef34 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Tue, 13 Sep 2022 17:35:38 +0530 Subject: [PATCH 2024/4345] scsi: mpt3sas: re-do lost mpt3sas DMA mask fix commit 1a2dcbdde82e3a5f1db9b2f4c48aa1aeba534fb2 upstream. This is a re-do of commit e0e0747de0ea ("scsi: mpt3sas: Fix return value check of dma_get_required_mask()"), which I ended up undoing in a mis-merge in commit 62e6e5940c0c ("Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi"). The original commit message was scsi: mpt3sas: Fix return value check of dma_get_required_mask() Fix the incorrect return value check of dma_get_required_mask(). Due to this incorrect check, the driver was always setting the DMA mask to 63 bit. Link: https://lore.kernel.org/r/20220913120538.18759-2-sreekanth.reddy@broadcom.com Fixes: ba27c5cf286d ("scsi: mpt3sas: Don't change the DMA coherent mask after allocations") Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen and this fix was lost when I mis-merged the conflict with commit 9df650963bf6 ("scsi: mpt3sas: Don't change DMA mask while reallocating pools"). Reported-by: Juergen Gross Fixes: 62e6e5940c0c ("Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi") Link: https://lore.kernel.org/all/CAHk-=wjaK-TxrNaGtFDpL9qNHL1MVkWXO1TT6vObD5tXMSC4Zg@mail.gmail.com Signed-off-by: Linus Torvalds Signed-off-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/mpt3sas/mpt3sas_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index eb37460ce109..2ab72f8818ee 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2825,7 +2825,7 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) u64 coherent_dma_mask, dma_mask; if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 || - dma_get_required_mask(&pdev->dev) <= 32) { + dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) { ioc->dma_mask = 32; coherent_dma_mask = dma_mask = DMA_BIT_MASK(32); /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */ From 1dfc0a52f768d481de6bb672904cd382ead7ca0e Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Fri, 28 Oct 2022 14:46:55 +0530 Subject: [PATCH 2025/4345] scsi: mpt3sas: Remove usage of dma_get_required_mask() API commit 06e472acf964649a58b7de35fc9cdc3151acb970 upstream. Remove the usage of dma_get_required_mask() API. Directly set the DMA mask to 63/64 if the system is a 64bit machine. Signed-off-by: Sreekanth Reddy Link: https://lore.kernel.org/r/20221028091655.17741-2-sreekanth.reddy@broadcom.com Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen Signed-off-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/mpt3sas/mpt3sas_base.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 2ab72f8818ee..26b15a24300e 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2824,8 +2824,7 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) struct sysinfo s; u64 coherent_dma_mask, dma_mask; - if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 || - dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) { + if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4) { ioc->dma_mask = 32; coherent_dma_mask = dma_mask = DMA_BIT_MASK(32); /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */ From a5bbea50d622b8f49ab8ee3b0eb283107febcf1a Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Mon, 13 Dec 2021 07:21:15 +0000 Subject: [PATCH 2026/4345] malidp: Fix NULL vs IS_ERR() checking commit 15342f930ebebcfe36f2415049736a77d7d2e045 upstream. The get_sg_table() function does not return NULL. It returns error pointers. Signed-off-by: Miaoqian Lin Signed-off-by: Liviu Dudau Link: https://lore.kernel.org/dri-devel/20211213072115.18098-1-linmq006@gmail.com/ Signed-off-by: Stefan Ghinea Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/arm/malidp_planes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c index f1e8bc39b16d..24604b410372 100644 --- a/drivers/gpu/drm/arm/malidp_planes.c +++ b/drivers/gpu/drm/arm/malidp_planes.c @@ -348,7 +348,7 @@ static bool malidp_check_pages_threshold(struct malidp_plane_state *ms, else sgt = obj->funcs->get_sg_table(obj); - if (!sgt) + if (IS_ERR(sgt)) return false; sgl = sgt->sgl; From 8ecd5dabddc0b70d82ca45e8c664e31fd04eaa92 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 13 Feb 2023 15:09:26 +0800 Subject: [PATCH 2027/4345] usb: gadget: uvc: fix missing mutex_unlock() if kstrtou8() fails commit 7ebb605d2283fb2647b4fa82030307ce00bee436 upstream. If kstrtou8() fails, the mutex_unlock() is missed, move kstrtou8() before mutex_lock() to fix it up. Fixes: 0525210c9840 ("usb: gadget: uvc: Allow definition of XUs in configfs") Fixes: b3c839bd8a07 ("usb: gadget: uvc: Make bSourceID read/write") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20230213070926.776447-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/uvc_configfs.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 7bb11d532b19..2db01170d096 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -546,6 +546,10 @@ static ssize_t uvcg_default_output_b_source_id_store(struct config_item *item, int result; u8 num; + result = kstrtou8(page, 0, &num); + if (result) + return result; + mutex_lock(su_mutex); /* for navigating configfs hierarchy */ opts_item = group->cg_item.ci_parent->ci_parent-> @@ -553,10 +557,6 @@ static ssize_t uvcg_default_output_b_source_id_store(struct config_item *item, opts = to_f_uvc_opts(opts_item); cd = &opts->uvc_output_terminal; - result = kstrtou8(page, 0, &num); - if (result) - return result; - mutex_lock(&opts->lock); cd->bSourceID = num; mutex_unlock(&opts->lock); From e5f315b55f8e09ac17c968da42f9345f64efcdd2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 11 Mar 2023 16:40:21 +0100 Subject: [PATCH 2028/4345] Linux 5.10.173 Link: https://lore.kernel.org/r/20230310133804.978589368@linuxfoundation.org Tested-by: Jon Hunter Tested-by: Salvatore Bonaccorso Tested-by: Shuah Khan Tested-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20230311091908.975813595@linuxfoundation.org Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5ca862041b71..1a6ea7994079 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 172 +SUBLEVEL = 173 EXTRAVERSION = NAME = Dare mighty things From decf73066f7eae34e434f707698c2c8b3bc62902 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Sat, 11 Mar 2023 23:19:14 +0900 Subject: [PATCH 2029/4345] wifi: cfg80211: Partial revert "wifi: cfg80211: Fix use after free for wext" commit 79d1ed5ca7db67d48e870c979f0e0f6b0947944a upstream. This reverts part of commit 015b8cc5e7c4 ("wifi: cfg80211: Fix use after free for wext") This commit broke WPA offload by unconditionally clearing the crypto modes for non-WEP connections. Drop that part of the patch. Signed-off-by: Hector Martin Reported-by: Ilya Reported-and-tested-by: Janne Grunau Reviewed-by: Eric Curtin Fixes: 015b8cc5e7c4 ("wifi: cfg80211: Fix use after free for wext") Cc: stable@kernel.org Link: https://lore.kernel.org/linux-wireless/ZAx0TWRBlGfv7pNl@kroah.com/T/#m11e6e0915ab8fa19ce8bc9695ab288c0fe018edf Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- net/wireless/sme.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f4d98ed8fa31..f7e2e172a68d 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1264,8 +1264,6 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, connect->key = NULL; connect->key_len = 0; connect->key_idx = 0; - connect->crypto.cipher_group = 0; - connect->crypto.n_ciphers_pairwise = 0; } wdev->connect_keys = connkeys; From 1afff6203a734f9e6eacdc356c29b2fabd82f1b6 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 28 Feb 2023 21:28:57 +0100 Subject: [PATCH 2030/4345] staging: rtl8192e: Remove function ..dm_check_ac_dc_power calling a script commit a98fc23cc2c1e4382a79ff137ca1a93d6a73b451 upstream. Remove function _rtl92e_dm_check_ac_dc_power calling a script /etc/acpi/wireless-rtl-ac-dc-power.sh that is not available. This script is not part of the kernel and it is not available on the www. The result is that this function is just dead code. Signed-off-by: Philipp Hortmann Cc: stable Link: https://lore.kernel.org/r/20230228202857.GA16442@matrix-ESPRIMO-P710 Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 27 ---------------------- 1 file changed, 27 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index 462835684e8b..9a02330864de 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -185,7 +185,6 @@ static void _rtl92e_dm_init_fsync(struct net_device *dev); static void _rtl92e_dm_deinit_fsync(struct net_device *dev); static void _rtl92e_dm_check_txrateandretrycount(struct net_device *dev); -static void _rtl92e_dm_check_ac_dc_power(struct net_device *dev); static void _rtl92e_dm_check_fsync(struct net_device *dev); static void _rtl92e_dm_check_rf_ctrl_gpio(void *data); static void _rtl92e_dm_fsync_timer_callback(struct timer_list *t); @@ -238,8 +237,6 @@ void rtl92e_dm_watchdog(struct net_device *dev) if (priv->being_init_adapter) return; - _rtl92e_dm_check_ac_dc_power(dev); - _rtl92e_dm_check_txrateandretrycount(dev); _rtl92e_dm_check_edca_turbo(dev); @@ -257,30 +254,6 @@ void rtl92e_dm_watchdog(struct net_device *dev) _rtl92e_dm_cts_to_self(dev); } -static void _rtl92e_dm_check_ac_dc_power(struct net_device *dev) -{ - struct r8192_priv *priv = rtllib_priv(dev); - static char const ac_dc_script[] = "/etc/acpi/wireless-rtl-ac-dc-power.sh"; - char *argv[] = {(char *)ac_dc_script, DRV_NAME, NULL}; - static char *envp[] = {"HOME=/", - "TERM=linux", - "PATH=/usr/bin:/bin", - NULL}; - - if (priv->ResetProgress == RESET_TYPE_SILENT) { - RT_TRACE((COMP_INIT | COMP_POWER | COMP_RF), - "GPIOChangeRFWorkItemCallBack(): Silent Reset!!!!!!!\n"); - return; - } - - if (priv->rtllib->state != RTLLIB_LINKED) - return; - call_usermodehelper(ac_dc_script, argv, envp, UMH_WAIT_PROC); - - return; -}; - - void rtl92e_init_adaptive_rate(struct net_device *dev) { From c036dae0367852ac08d0810478d7276e47ebc0c6 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Wed, 1 Mar 2023 22:54:41 +0100 Subject: [PATCH 2031/4345] staging: rtl8192e: Remove call_usermodehelper starting RadioPower.sh commit fe413a074a93d56f89e322c786aad8639afe76b4 upstream. Remove call_usermodehelper starting /etc/acpi/events/RadioPower.sh that is not available. This script is not part of the kernel and it is not officially available on the www. The result is that this lines are just dead code. Signed-off-by: Philipp Hortmann Cc: stable Link: https://lore.kernel.org/r/20230301215441.GA14049@matrix-ESPRIMO-P710 Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index 9a02330864de..916ff5058ae7 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -1773,10 +1773,6 @@ static void _rtl92e_dm_check_rf_ctrl_gpio(void *data) u8 tmp1byte; enum rt_rf_power_state eRfPowerStateToSet; bool bActuallySet = false; - char *argv[3]; - static char const RadioPowerPath[] = "/etc/acpi/events/RadioPower.sh"; - static char *envp[] = {"HOME=/", "TERM=linux", "PATH=/usr/bin:/bin", - NULL}; bActuallySet = false; @@ -1808,14 +1804,6 @@ static void _rtl92e_dm_check_rf_ctrl_gpio(void *data) mdelay(1000); priv->bHwRfOffAction = 1; rtl92e_set_rf_state(dev, eRfPowerStateToSet, RF_CHANGE_BY_HW); - if (priv->bHwRadioOff) - argv[1] = "RFOFF"; - else - argv[1] = "RFON"; - - argv[0] = (char *)RadioPowerPath; - argv[2] = NULL; - call_usermodehelper(RadioPowerPath, argv, envp, UMH_WAIT_PROC); } } From 955623617f2f505ac08d0efda2bb50c1a52e2c96 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 10:19:37 +0100 Subject: [PATCH 2032/4345] Linux 5.10.174 Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 1a6ea7994079..92accf2ddc08 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 173 +SUBLEVEL = 174 EXTRAVERSION = NAME = Dare mighty things From 09e5cc649d39f80e913043099b465374ceef4faf Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 8 Dec 2022 10:32:31 +0800 Subject: [PATCH 2033/4345] UPSTREAM: ext4: allocate extended attribute value in vmalloc area commit cc12a6f25e07ed05d5825a1664b67a970842b2ca upstream. Now, extended attribute value maximum length is 64K. The memory requested here does not need continuous physical addresses, so it is appropriate to use kvmalloc to request memory. At the same time, it can also cope with the situation that the extended attribute will become longer in the future. Signed-off-by: Ye Bin Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221208023233.1231330-3-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman Bug: 262267471 Change-Id: I92a4a66d8220f46f26a89100ba41c659559443a7 Signed-off-by: Tudor Ambarus --- fs/ext4/xattr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 38531c5e16c6..02fc067474f6 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2556,7 +2556,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); - buffer = kmalloc(value_size, GFP_NOFS); + buffer = kvmalloc(value_size, GFP_NOFS); b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS); if (!is || !bs || !buffer || !b_entry_name) { error = -ENOMEM; @@ -2608,7 +2608,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, error = 0; out: kfree(b_entry_name); - kfree(buffer); + kvfree(buffer); if (is) brelse(is->iloc.bh); if (bs) From 33245a0eac85b8512ea4f28d3ff761c5b139ea3b Mon Sep 17 00:00:00 2001 From: Jun Nie Date: Tue, 3 Jan 2023 09:45:16 +0800 Subject: [PATCH 2034/4345] UPSTREAM: ext4: optimize ea_inode block expansion commit 1e9d62d252812575ded7c620d8fc67c32ff06c16 upstream. Copy ea data from inode entry when expanding ea block if possible. Then remove the ea entry if expansion success. Thus memcpy to a temporary buffer may be avoided. If the expansion fails, we do not need to recovery the removed ea entry neither in this way. Reported-by: syzbot+2dacb8f015bf1420155f@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=3613786cb88c93aa1c6a279b1df6a7b201347d08 Link: https://lore.kernel.org/r/20230103014517.495275-2-jun.nie@linaro.org Cc: stable@kernel.org Signed-off-by: Jun Nie Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman Bug: 262267471 Change-Id: I26e7d45ab21bcf9e38eeb66601067f42b01c11f5 Signed-off-by: Tudor Ambarus --- fs/ext4/xattr.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 02fc067474f6..96f14c3ef6be 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2556,9 +2556,8 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); - buffer = kvmalloc(value_size, GFP_NOFS); b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS); - if (!is || !bs || !buffer || !b_entry_name) { + if (!is || !bs || !b_entry_name) { error = -ENOMEM; goto out; } @@ -2570,12 +2569,18 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, /* Save the entry name and the entry value */ if (entry->e_value_inum) { + buffer = kvmalloc(value_size, GFP_NOFS); + if (!buffer) { + error = -ENOMEM; + goto out; + } + error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; } else { size_t value_offs = le16_to_cpu(entry->e_value_offs); - memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size); + buffer = (void *)IFIRST(header) + value_offs; } memcpy(b_entry_name, entry->e_name, entry->e_name_len); @@ -2590,25 +2595,26 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, if (error) goto out; - /* Remove the chosen entry from the inode */ - error = ext4_xattr_ibody_set(handle, inode, &i, is); - if (error) - goto out; - i.value = buffer; i.value_len = value_size; error = ext4_xattr_block_find(inode, &i, bs); if (error) goto out; - /* Add entry which was removed from the inode into the block */ + /* Move ea entry from the inode into the block */ error = ext4_xattr_block_set(handle, inode, &i, bs); if (error) goto out; - error = 0; + + /* Remove the chosen entry from the inode */ + i.value = NULL; + i.value_len = 0; + error = ext4_xattr_ibody_set(handle, inode, &i, is); + out: kfree(b_entry_name); - kvfree(buffer); + if (entry->e_value_inum && buffer) + kvfree(buffer); if (is) brelse(is->iloc.bh); if (bs) From 62f5fae173d8afb19749a1b78d8f11fb23d92164 Mon Sep 17 00:00:00 2001 From: Jun Nie Date: Tue, 3 Jan 2023 09:45:17 +0800 Subject: [PATCH 2035/4345] UPSTREAM: ext4: refuse to create ea block when umounted commit f31173c19901a96bb2ebf6bcfec8a08df7095c91 upstream. The ea block expansion need to access s_root while it is already set as NULL when umount is triggered. Refuse this request to avoid panic. Reported-by: syzbot+2dacb8f015bf1420155f@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=3613786cb88c93aa1c6a279b1df6a7b201347d08 Link: https://lore.kernel.org/r/20230103014517.495275-3-jun.nie@linaro.org Cc: stable@kernel.org Signed-off-by: Jun Nie Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman Bug: 262267471 Change-Id: I0a5c974e696cf7a132f3cbb8acbe066edba4660f Signed-off-by: Tudor Ambarus --- fs/ext4/xattr.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 96f14c3ef6be..a0b59db17120 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1406,6 +1406,13 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle, uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) }; int err; + if (inode->i_sb->s_root == NULL) { + ext4_warning(inode->i_sb, + "refuse to create EA inode when umounting"); + WARN_ON(1); + return ERR_PTR(-EINVAL); + } + /* * Let the next inode be the goal, so we try and allocate the EA inode * in the same group, or nearby one. From a759905de9cd6ec9ca08ceadf0920272772ed830 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 6 Mar 2023 13:54:50 -0500 Subject: [PATCH 2036/4345] fs: prevent out-of-bounds array speculation when closing a file descriptor commit 609d54441493c99f21c1823dfd66fa7f4c512ff4 upstream. Google-Bug-Id: 114199369 Signed-off-by: Theodore Ts'o Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- fs/file.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/file.c b/fs/file.c index 97a0cd31faec..173d318208b8 100644 --- a/fs/file.c +++ b/fs/file.c @@ -677,6 +677,7 @@ static struct file *pick_file(struct files_struct *files, unsigned fd) fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; + fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (!file) goto out_unlock; From a1eb8bf1e35f5d274efcfd55e91361a91d85e327 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Wed, 8 Mar 2023 11:51:26 +0100 Subject: [PATCH 2037/4345] fork: allow CLONE_NEWTIME in clone3 flags commit a402f1e35313fc7ce2ca60f543c4402c2c7c3544 upstream. Currently, calling clone3() with CLONE_NEWTIME in clone_args->flags fails with -EINVAL. This is because CLONE_NEWTIME intersects with CSIGNAL. However, CSIGNAL was deprecated when clone3 was introduced in commit 7f192e3cd316 ("fork: add clone3"), allowing re-use of that part of clone flags. Fix this by explicitly allowing CLONE_NEWTIME in clone3_args_valid. This is also in line with the respective check in check_unshare_flags which allow CLONE_NEWTIME for unshare(). Fixes: 769071ac9f20 ("ns: Introduce Time Namespace") Cc: Andrey Vagin Cc: Christian Brauner Cc: stable@vger.kernel.org Signed-off-by: Tobias Klauser Reviewed-by: Christian Brauner Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Greg Kroah-Hartman --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/fork.c b/kernel/fork.c index 68efe2a0b4fb..a5bc0c6a00fd 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2726,7 +2726,7 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs) * - make the CLONE_DETACHED bit reuseable for clone3 * - make the CSIGNAL bits reuseable for clone3 */ - if (kargs->flags & (CLONE_DETACHED | CSIGNAL)) + if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == From 5462843dc40f23fcdacac0460b75ec4916ef6ae6 Mon Sep 17 00:00:00 2001 From: Andrew Cooper Date: Tue, 7 Mar 2023 17:46:43 +0000 Subject: [PATCH 2038/4345] x86/CPU/AMD: Disable XSAVES on AMD family 0x17 commit b0563468eeac88ebc70559d52a0b66efc37e4e9d upstream. AMD Erratum 1386 is summarised as: XSAVES Instruction May Fail to Save XMM Registers to the Provided State Save Area This piece of accidental chronomancy causes the %xmm registers to occasionally reset back to an older value. Ignore the XSAVES feature on all AMD Zen1/2 hardware. The XSAVEC instruction (which works fine) is equivalent on affected parts. [ bp: Typos, move it into the F17h-specific function. ] Reported-by: Tavis Ormandy Signed-off-by: Andrew Cooper Signed-off-by: Borislav Petkov (AMD) Cc: Link: https://lore.kernel.org/r/20230307174643.1240184-1-andrew.cooper3@citrix.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/amd.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ec3fa4dc9031..89a9b7754476 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -932,6 +932,15 @@ void init_spectral_chicken(struct cpuinfo_x86 *c) } } #endif + /* + * Work around Erratum 1386. The XSAVES instruction malfunctions in + * certain circumstances on Zen1/2 uarch, and not all parts have had + * updated microcode at the time of writing (March 2023). + * + * Affected parts all have no supervisor XSAVE states, meaning that + * the XSAVEC instruction (which works fine) is equivalent. + */ + clear_cpu_cap(c, X86_FEATURE_XSAVES); } static void init_amd_zn(struct cpuinfo_x86 *c) From 4279e87da6c88d63796904184b6f027321e370ab Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 6 Mar 2023 10:34:20 -0500 Subject: [PATCH 2039/4345] drm/amdgpu: fix error checking in amdgpu_read_mm_registers for soc15 commit 0dcdf8498eae2727bb33cef3576991dc841d4343 upstream. Properly skip non-existent registers as well. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2442 Reviewed-by: Hawking Zhang Reviewed-by: Evan Quan Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/soc15.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 7212b9900e0a..994e6635b834 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -382,8 +382,9 @@ static int soc15_read_register(struct amdgpu_device *adev, u32 se_num, *value = 0; for (i = 0; i < ARRAY_SIZE(soc15_allowed_read_registers); i++) { en = &soc15_allowed_read_registers[i]; - if (adev->reg_offset[en->hwip][en->inst] && - reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + if (!adev->reg_offset[en->hwip][en->inst]) + continue; + else if (reg_offset != (adev->reg_offset[en->hwip][en->inst][en->seg] + en->reg_offset)) continue; From 3106cb47cded559a8937b26d6cf4740f6f5de76f Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Fri, 13 Jan 2023 11:24:09 -0500 Subject: [PATCH 2040/4345] drm/connector: print max_requested_bpc in state debugfs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 7d386975f6a495902e679a3a250a7456d7e54765 upstream. This is useful to understand the bpc defaults and support of a driver. Signed-off-by: Harry Wentland Cc: Pekka Paalanen Cc: Sebastian Wick Cc: Vitaly.Prosyak@amd.com Cc: Uma Shankar Cc: Ville Syrjälä Cc: Joshua Ashton Cc: Jani Nikula Cc: dri-devel@lists.freedesktop.org Cc: amd-gfx@lists.freedesktop.org Reviewed-By: Joshua Ashton Link: https://patchwork.freedesktop.org/patch/msgid/20230113162428.33874-3-harry.wentland@amd.com Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_atomic.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 58527f151984..98b659981f1a 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1010,6 +1010,7 @@ static void drm_atomic_connector_print_state(struct drm_printer *p, drm_printf(p, "connector[%u]: %s\n", connector->base.id, connector->name); drm_printf(p, "\tcrtc=%s\n", state->crtc ? state->crtc->name : "(null)"); drm_printf(p, "\tself_refresh_aware=%d\n", state->self_refresh_aware); + drm_printf(p, "\tmax_requested_bpc=%d\n", state->max_requested_bpc); if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) if (state->writeback_job && state->writeback_job->fb) From d0632ff49bd1a7d56f33ef2b935acbb6d00c9310 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 2 Feb 2023 16:55:03 -0800 Subject: [PATCH 2041/4345] ext4: fix cgroup writeback accounting with fs-layer encryption commit ffec85d53d0f39ee4680a2cf0795255e000e1feb upstream. When writing a page from an encrypted file that is using filesystem-layer encryption (not inline encryption), ext4 encrypts the pagecache page into a bounce page, then writes the bounce page. It also passes the bounce page to wbc_account_cgroup_owner(). That's incorrect, because the bounce page is a newly allocated temporary page that doesn't have the memory cgroup of the original pagecache page. This makes wbc_account_cgroup_owner() not account the I/O to the owner of the pagecache page as it should. Fix this by always passing the pagecache page to wbc_account_cgroup_owner(). Fixes: 001e4a8775f6 ("ext4: implement cgroup writeback support") Cc: stable@vger.kernel.org Reported-by: Matthew Wilcox (Oracle) Signed-off-by: Eric Biggers Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20230203005503.141557-1-ebiggers@kernel.org Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/page-io.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 4569075a7da0..a94cc7b22d7e 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -416,7 +416,8 @@ static void io_submit_init_bio(struct ext4_io_submit *io, static void io_submit_add_bh(struct ext4_io_submit *io, struct inode *inode, - struct page *page, + struct page *pagecache_page, + struct page *bounce_page, struct buffer_head *bh) { int ret; @@ -430,10 +431,11 @@ submit_and_retry: io_submit_init_bio(io, bh); io->io_bio->bi_write_hint = inode->i_write_hint; } - ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); + ret = bio_add_page(io->io_bio, bounce_page ?: pagecache_page, + bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; - wbc_account_cgroup_owner(io->io_wbc, page, bh->b_size); + wbc_account_cgroup_owner(io->io_wbc, pagecache_page, bh->b_size); io->io_next_block++; } @@ -551,8 +553,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, do { if (!buffer_async_write(bh)) continue; - io_submit_add_bh(io, inode, - bounce_page ? bounce_page : page, bh); + io_submit_add_bh(io, inode, page, bounce_page, bh); nr_submitted++; clear_buffer_dirty(bh); } while ((bh = bh->b_this_page) != head); From 8706c972fcfa8c9533f37989c808a18bfa058ccd Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Fri, 10 Feb 2023 12:32:44 -0500 Subject: [PATCH 2042/4345] ext4: fix RENAME_WHITEOUT handling for inline directories commit c9f62c8b2dbf7240536c0cc9a4529397bb8bf38e upstream. A significant number of xfstests can cause ext4 to log one or more warning messages when they are run on a test file system where the inline_data feature has been enabled. An example: "EXT4-fs warning (device vdc): ext4_dirblock_csum_set:425: inode #16385: comm fsstress: No space for directory leaf checksum. Please run e2fsck -D." The xfstests include: ext4/057, 058, and 307; generic/013, 051, 068, 070, 076, 078, 083, 232, 269, 270, 390, 461, 475, 476, 482, 579, 585, 589, 626, 631, and 650. In this situation, the warning message indicates a bug in the code that performs the RENAME_WHITEOUT operation on a directory entry that has been stored inline. It doesn't detect that the directory is stored inline, and incorrectly attempts to compute a dirent block checksum on the whiteout inode when creating it. This attempt fails as a result of the integrity checking in get_dirent_tail (usually due to a failure to match the EXT4_FT_DIR_CSUM magic cookie), and the warning message is then emitted. Fix this by simply collecting the inlined data state at the time the search for the source directory entry is performed. Existing code handles the rest, and this is sufficient to eliminate all spurious warning messages produced by the tests above. Go one step further and do the same in the code that resets the source directory entry in the event of failure. The inlined state should be present in the "old" struct, but given the possibility of a race there's no harm in taking a conservative approach and getting that information again since the directory entry is being reread anyway. Fixes: b7ff91fd030d ("ext4: find old entry again if failed to rename whiteout") Cc: stable@kernel.org Signed-off-by: Eric Whitney Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230210173244.679890-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/namei.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 7ec7c9c16a39..6f335d58183e 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1512,11 +1512,10 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir, int has_inline_data = 1; ret = ext4_find_inline_entry(dir, fname, res_dir, &has_inline_data); - if (has_inline_data) { - if (inlined) - *inlined = 1; + if (inlined) + *inlined = has_inline_data; + if (has_inline_data) goto cleanup_and_exit; - } } if ((namelen <= 2) && (name[0] == '.') && @@ -3698,7 +3697,8 @@ static void ext4_resetent(handle_t *handle, struct ext4_renament *ent, * so the old->de may no longer valid and need to find it again * before reset old inode info. */ - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, + &old.inlined); if (IS_ERR(old.bh)) retval = PTR_ERR(old.bh); if (!old.bh) @@ -3863,7 +3863,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, return retval; } - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, + &old.inlined); if (IS_ERR(old.bh)) return PTR_ERR(old.bh); /* From 1d2366624b4c19a2ba6baf67fe57f4a1b0f67c05 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 16 Feb 2023 10:55:48 -0800 Subject: [PATCH 2043/4345] ext4: fix another off-by-one fsmap error on 1k block filesystems commit c993799baf9c5861f8df91beb80e1611b12efcbd upstream. Apparently syzbot figured out that issuing this FSMAP call: struct fsmap_head cmd = { .fmh_count = ...; .fmh_keys = { { .fmr_device = /* ext4 dev */, .fmr_physical = 0, }, { .fmr_device = /* ext4 dev */, .fmr_physical = 0, }, }, ... }; ret = ioctl(fd, FS_IOC_GETFSMAP, &cmd); Produces this crash if the underlying filesystem is a 1k-block ext4 filesystem: kernel BUG at fs/ext4/ext4.h:3331! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 3 PID: 3227965 Comm: xfs_io Tainted: G W O 6.2.0-rc8-achx Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 RIP: 0010:ext4_mb_load_buddy_gfp+0x47c/0x570 [ext4] RSP: 0018:ffffc90007c03998 EFLAGS: 00010246 RAX: ffff888004978000 RBX: ffffc90007c03a20 RCX: ffff888041618000 RDX: 0000000000000000 RSI: 00000000000005a4 RDI: ffffffffa0c99b11 RBP: ffff888012330000 R08: ffffffffa0c2b7d0 R09: 0000000000000400 R10: ffffc90007c03950 R11: 0000000000000000 R12: 0000000000000001 R13: 00000000ffffffff R14: 0000000000000c40 R15: ffff88802678c398 FS: 00007fdf2020c880(0000) GS:ffff88807e100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffd318a5fe8 CR3: 000000007f80f001 CR4: 00000000001706e0 Call Trace: ext4_mballoc_query_range+0x4b/0x210 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] ext4_getfsmap_datadev+0x713/0x890 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] ext4_getfsmap+0x2b7/0x330 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] ext4_ioc_getfsmap+0x153/0x2b0 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] __ext4_ioctl+0x2a7/0x17e0 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] __x64_sys_ioctl+0x82/0xa0 do_syscall_64+0x2b/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fdf20558aff RSP: 002b:00007ffd318a9e30 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00000000000200c0 RCX: 00007fdf20558aff RDX: 00007fdf1feb2010 RSI: 00000000c0c0583b RDI: 0000000000000003 RBP: 00005625c0634be0 R08: 00005625c0634c40 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fdf1feb2010 R13: 00005625be70d994 R14: 0000000000000800 R15: 0000000000000000 For GETFSMAP calls, the caller selects a physical block device by writing its block number into fsmap_head.fmh_keys[01].fmr_device. To query mappings for a subrange of the device, the starting byte of the range is written to fsmap_head.fmh_keys[0].fmr_physical and the last byte of the range goes in fsmap_head.fmh_keys[1].fmr_physical. IOWs, to query what mappings overlap with bytes 3-14 of /dev/sda, you'd set the inputs as follows: fmh_keys[0] = { .fmr_device = major(8, 0), .fmr_physical = 3}, fmh_keys[1] = { .fmr_device = major(8, 0), .fmr_physical = 14}, Which would return you whatever is mapped in the 12 bytes starting at physical offset 3. The crash is due to insufficient range validation of keys[1] in ext4_getfsmap_datadev. On 1k-block filesystems, block 0 is not part of the filesystem, which means that s_first_data_block is nonzero. ext4_get_group_no_and_offset subtracts this quantity from the blocknr argument before cracking it into a group number and a block number within a group. IOWs, block group 0 spans blocks 1-8192 (1-based) instead of 0-8191 (0-based) like what happens with larger blocksizes. The net result of this encoding is that blocknr < s_first_data_block is not a valid input to this function. The end_fsb variable is set from the keys that are copied from userspace, which means that in the above example, its value is zero. That leads to an underflow here: blocknr = blocknr - le32_to_cpu(es->s_first_data_block); The division then operates on -1: offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)) >> EXT4_SB(sb)->s_cluster_bits; Leaving an impossibly large group number (2^32-1) in blocknr. ext4_getfsmap_check_keys checked that keys[0].fmr_physical and keys[1].fmr_physical are in increasing order, but ext4_getfsmap_datadev adjusts keys[0].fmr_physical to be at least s_first_data_block. This implies that we have to check it again after the adjustment, which is the piece that I forgot. Reported-by: syzbot+6be2b977c89f79b6b153@syzkaller.appspotmail.com Fixes: 4a4956249dac ("ext4: fix off-by-one fsmap error on 1k block filesystems") Link: https://syzkaller.appspot.com/bug?id=79d5768e9bfe362911ac1a5057a36fc6b5c30002 Cc: stable@vger.kernel.org Signed-off-by: Darrick J. Wong Link: https://lore.kernel.org/r/Y+58NPTH7VNGgzdd@magnolia Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/fsmap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 4493ef0c715e..cdf9bfe10137 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -486,6 +486,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb, keys[0].fmr_physical = bofs; if (keys[1].fmr_physical >= eofs) keys[1].fmr_physical = eofs - 1; + if (keys[1].fmr_physical < keys[0].fmr_physical) + return 0; start_fsb = keys[0].fmr_physical; end_fsb = keys[1].fmr_physical; From d72a6c31393da918c8004233f53b601efd732be5 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Tue, 7 Mar 2023 09:52:52 +0800 Subject: [PATCH 2044/4345] ext4: move where set the MAY_INLINE_DATA flag is set commit 1dcdce5919115a471bf4921a57f20050c545a236 upstream. The only caller of ext4_find_inline_data_nolock() that needs setting of EXT4_STATE_MAY_INLINE_DATA flag is ext4_iget_extra_inode(). In ext4_write_inline_data_end() we just need to update inode->i_inline_off. Since we are going to add one more caller that does not need to set EXT4_STATE_MAY_INLINE_DATA, just move setting of EXT4_STATE_MAY_INLINE_DATA out to ext4_iget_extra_inode(). Signed-off-by: Ye Bin Cc: stable@kernel.org Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230307015253.2232062-2-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inline.c | 1 - fs/ext4/inode.c | 7 ++++++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 77377befbb1c..61cb50e8fcb7 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -157,7 +157,6 @@ int ext4_find_inline_data_nolock(struct inode *inode) (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); - ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); } out: brelse(is.iloc.bh); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 355343cf4609..1a654a1f3f46 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4639,8 +4639,13 @@ static inline int ext4_iget_extra_inode(struct inode *inode, if (EXT4_INODE_HAS_XATTR_SPACE(inode) && *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { + int err; + ext4_set_inode_state(inode, EXT4_STATE_XATTR); - return ext4_find_inline_data_nolock(inode); + err = ext4_find_inline_data_nolock(inode); + if (!err && ext4_has_inline_data(inode)) + ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + return err; } else EXT4_I(inode)->i_inline_off = 0; return 0; From a9bd94f67b27739bbe8583c52256502bd4cc7e83 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Tue, 7 Mar 2023 09:52:53 +0800 Subject: [PATCH 2045/4345] ext4: fix WARNING in ext4_update_inline_data commit 2b96b4a5d9443ca4cad58b0040be455803c05a42 upstream. Syzbot found the following issue: EXT4-fs (loop0): mounted filesystem 00000000-0000-0000-0000-000000000000 without journal. Quota mode: none. fscrypt: AES-256-CTS-CBC using implementation "cts-cbc-aes-aesni" fscrypt: AES-256-XTS using implementation "xts-aes-aesni" ------------[ cut here ]------------ WARNING: CPU: 0 PID: 5071 at mm/page_alloc.c:5525 __alloc_pages+0x30a/0x560 mm/page_alloc.c:5525 Modules linked in: CPU: 1 PID: 5071 Comm: syz-executor263 Not tainted 6.2.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 RIP: 0010:__alloc_pages+0x30a/0x560 mm/page_alloc.c:5525 RSP: 0018:ffffc90003c2f1c0 EFLAGS: 00010246 RAX: ffffc90003c2f220 RBX: 0000000000000014 RCX: 0000000000000000 RDX: 0000000000000028 RSI: 0000000000000000 RDI: ffffc90003c2f248 RBP: ffffc90003c2f2d8 R08: dffffc0000000000 R09: ffffc90003c2f220 R10: fffff52000785e49 R11: 1ffff92000785e44 R12: 0000000000040d40 R13: 1ffff92000785e40 R14: dffffc0000000000 R15: 1ffff92000785e3c FS: 0000555556c0d300(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f95d5e04138 CR3: 00000000793aa000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __alloc_pages_node include/linux/gfp.h:237 [inline] alloc_pages_node include/linux/gfp.h:260 [inline] __kmalloc_large_node+0x95/0x1e0 mm/slab_common.c:1113 __do_kmalloc_node mm/slab_common.c:956 [inline] __kmalloc+0xfe/0x190 mm/slab_common.c:981 kmalloc include/linux/slab.h:584 [inline] kzalloc include/linux/slab.h:720 [inline] ext4_update_inline_data+0x236/0x6b0 fs/ext4/inline.c:346 ext4_update_inline_dir fs/ext4/inline.c:1115 [inline] ext4_try_add_inline_entry+0x328/0x990 fs/ext4/inline.c:1307 ext4_add_entry+0x5a4/0xeb0 fs/ext4/namei.c:2385 ext4_add_nondir+0x96/0x260 fs/ext4/namei.c:2772 ext4_create+0x36c/0x560 fs/ext4/namei.c:2817 lookup_open fs/namei.c:3413 [inline] open_last_lookups fs/namei.c:3481 [inline] path_openat+0x12ac/0x2dd0 fs/namei.c:3711 do_filp_open+0x264/0x4f0 fs/namei.c:3741 do_sys_openat2+0x124/0x4e0 fs/open.c:1310 do_sys_open fs/open.c:1326 [inline] __do_sys_openat fs/open.c:1342 [inline] __se_sys_openat fs/open.c:1337 [inline] __x64_sys_openat+0x243/0x290 fs/open.c:1337 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Above issue happens as follows: ext4_iget ext4_find_inline_data_nolock ->i_inline_off=164 i_inline_size=60 ext4_try_add_inline_entry __ext4_mark_inode_dirty ext4_expand_extra_isize_ea ->i_extra_isize=32 s_want_extra_isize=44 ext4_xattr_shift_entries ->after shift i_inline_off is incorrect, actually is change to 176 ext4_try_add_inline_entry ext4_update_inline_dir get_max_inline_xattr_value_size if (EXT4_I(inode)->i_inline_off) entry = (struct ext4_xattr_entry *)((void *)raw_inode + EXT4_I(inode)->i_inline_off); free += EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)); ->As entry is incorrect, then 'free' may be negative ext4_update_inline_data value = kzalloc(len, GFP_NOFS); -> len is unsigned int, maybe very large, then trigger warning when 'kzalloc()' To resolve the above issue we need to update 'i_inline_off' after 'ext4_xattr_shift_entries()'. We do not need to set EXT4_STATE_MAY_INLINE_DATA flag here, since ext4_mark_inode_dirty() already sets this flag if needed. Setting EXT4_STATE_MAY_INLINE_DATA when it is needed may trigger a BUG_ON in ext4_writepages(). Reported-by: syzbot+d30838395804afc2fa6f@syzkaller.appspotmail.com Cc: stable@kernel.org Signed-off-by: Ye Bin Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230307015253.2232062-3-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index b80ad5a7b05c..60e122761352 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2804,6 +2804,9 @@ shift: (void *)header, total_ino); EXT4_I(inode)->i_extra_isize = new_extra_isize; + if (ext4_has_inline_data(inode)) + error = ext4_find_inline_data_nolock(inode); + cleanup: if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) { ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.", From 3f00c476da8fe7c4c34ea16abb55d74127120413 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 8 Mar 2023 11:26:43 +0800 Subject: [PATCH 2046/4345] ext4: zero i_disksize when initializing the bootloader inode commit f5361da1e60d54ec81346aee8e3d8baf1be0b762 upstream. If the boot loader inode has never been used before, the EXT4_IOC_SWAP_BOOT inode will initialize it, including setting the i_size to 0. However, if the "never before used" boot loader has a non-zero i_size, then i_disksize will be non-zero, and the inconsistency between i_size and i_disksize can trigger a kernel warning: WARNING: CPU: 0 PID: 2580 at fs/ext4/file.c:319 CPU: 0 PID: 2580 Comm: bb Not tainted 6.3.0-rc1-00004-g703695902cfa RIP: 0010:ext4_file_write_iter+0xbc7/0xd10 Call Trace: vfs_write+0x3b1/0x5c0 ksys_write+0x77/0x160 __x64_sys_write+0x22/0x30 do_syscall_64+0x39/0x80 Reproducer: 1. create corrupted image and mount it: mke2fs -t ext4 /tmp/foo.img 200 debugfs -wR "sif <5> size 25700" /tmp/foo.img mount -t ext4 /tmp/foo.img /mnt cd /mnt echo 123 > file 2. Run the reproducer program: posix_memalign(&buf, 1024, 1024) fd = open("file", O_RDWR | O_DIRECT); ioctl(fd, EXT4_IOC_SWAP_BOOT); write(fd, buf, 1024); Fix this by setting i_disksize as well as i_size to zero when initiaizing the boot loader inode. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217159 Cc: stable@kernel.org Signed-off-by: Zhihao Cheng Link: https://lore.kernel.org/r/20230308032643.641113-1-chengzhihao1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ioctl.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 240d792db9f7..53bdc67a815f 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -180,6 +180,7 @@ static long swap_inode_boot_loader(struct super_block *sb, ei_bl->i_flags = 0; inode_set_iversion(inode_bl, 1); i_size_write(inode_bl, 0); + EXT4_I(inode_bl)->i_disksize = inode_bl->i_size; inode_bl->i_mode = S_IFREG; if (ext4_has_feature_extents(sb)) { ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); From 7786bfd8f7ab94f5c1ceb3e721aeccb76e24f414 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Tue, 7 Mar 2023 00:26:50 +0300 Subject: [PATCH 2047/4345] nfc: change order inside nfc_se_io error path commit 7d834b4d1ab66c48e8c0810fdeadaabb80fa2c81 upstream. cb_context should be freed on the error path in nfc_se_io as stated by commit 25ff6f8a5a3b ("nfc: fix memory leak of se_io context in nfc_genl_se_io"). Make the error path in nfc_se_io unwind everything in reverse order, i.e. free the cb_context after unlocking the device. Suggested-by: Krzysztof Kozlowski Signed-off-by: Fedor Pchelkin Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230306212650.230322-1-pchelkin@ispras.ru Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/nfc/netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 3f4785be066a..e0e116865511 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1446,8 +1446,8 @@ static int nfc_se_io(struct nfc_dev *dev, u32 se_idx, return rc; error: - kfree(cb_context); device_unlock(&dev->dev); + kfree(cb_context); return rc; } From fe80a53eabdb256a0610c7681ca8823435c963ac Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 23 Jan 2023 14:29:15 +0100 Subject: [PATCH 2048/4345] udf: Fix off-by-one error when discarding preallocation [ Upstream commit f54aa97fb7e5329a373f9df4e5e213ced4fc8759 ] The condition determining whether the preallocation can be used had an off-by-one error so we didn't discard preallocation when new allocation was just following it. This can then confuse code in inode_getblk(). CC: stable@vger.kernel.org Fixes: 16d055656814 ("udf: Discard preallocation before extending file with a hole") Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/udf/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 81876284a83c..d114774ecdea 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -442,7 +442,7 @@ static int udf_get_block(struct inode *inode, sector_t block, * Block beyond EOF and prealloc extents? Just discard preallocation * as it is not useful and complicates things. */ - if (((loff_t)block) << inode->i_blkbits > iinfo->i_lenExtents) + if (((loff_t)block) << inode->i_blkbits >= iinfo->i_lenExtents) udf_discard_prealloc(inode); udf_clear_extent_cache(inode); phys = inode_getblk(inode, block, &err, &new); From 6414597815d57c15cc083df1ad0d043b724b7418 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 22 Mar 2021 04:21:30 +0100 Subject: [PATCH 2049/4345] irq: Fix typos in comments [ Upstream commit a359f757965aafd0f58570de95dc6bc06cf12a9c ] Fix ~36 single-word typos in the IRQ, irqchip and irqdomain code comments. Signed-off-by: Ingo Molnar Cc: Thomas Gleixner Cc: Marc Zyngier Cc: Borislav Petkov Cc: Peter Zijlstra Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar Stable-dep-of: 6e6f75c9c98d ("irqdomain: Look for existing mapping only once") Signed-off-by: Sasha Levin --- drivers/irqchip/irq-aspeed-vic.c | 4 ++-- drivers/irqchip/irq-bcm7120-l2.c | 2 +- drivers/irqchip/irq-csky-apb-intc.c | 2 +- drivers/irqchip/irq-gic-v2m.c | 2 +- drivers/irqchip/irq-gic-v3-its.c | 10 +++++----- drivers/irqchip/irq-gic-v3.c | 2 +- drivers/irqchip/irq-loongson-pch-pic.c | 2 +- drivers/irqchip/irq-meson-gpio.c | 2 +- drivers/irqchip/irq-mtk-cirq.c | 2 +- drivers/irqchip/irq-mxs.c | 4 ++-- drivers/irqchip/irq-sun4i.c | 2 +- drivers/irqchip/irq-ti-sci-inta.c | 2 +- drivers/irqchip/irq-vic.c | 4 ++-- drivers/irqchip/irq-xilinx-intc.c | 2 +- include/linux/irq.h | 4 ++-- include/linux/irqdesc.h | 2 +- kernel/irq/chip.c | 2 +- kernel/irq/dummychip.c | 2 +- kernel/irq/irqdesc.c | 2 +- kernel/irq/irqdomain.c | 8 ++++---- kernel/irq/manage.c | 6 +++--- kernel/irq/msi.c | 2 +- kernel/irq/timings.c | 2 +- 23 files changed, 36 insertions(+), 36 deletions(-) diff --git a/drivers/irqchip/irq-aspeed-vic.c b/drivers/irqchip/irq-aspeed-vic.c index 6567ed782f82..58717cd44f99 100644 --- a/drivers/irqchip/irq-aspeed-vic.c +++ b/drivers/irqchip/irq-aspeed-vic.c @@ -71,7 +71,7 @@ static void vic_init_hw(struct aspeed_vic *vic) writel(0, vic->base + AVIC_INT_SELECT); writel(0, vic->base + AVIC_INT_SELECT + 4); - /* Some interrupts have a programable high/low level trigger + /* Some interrupts have a programmable high/low level trigger * (4 GPIO direct inputs), for now we assume this was configured * by firmware. We read which ones are edge now. */ @@ -203,7 +203,7 @@ static int __init avic_of_init(struct device_node *node, } vic->base = regs; - /* Initialize soures, all masked */ + /* Initialize sources, all masked */ vic_init_hw(vic); /* Ready to receive interrupts */ diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c index 7d776c905b7d..1c2c5bd5a9fc 100644 --- a/drivers/irqchip/irq-bcm7120-l2.c +++ b/drivers/irqchip/irq-bcm7120-l2.c @@ -310,7 +310,7 @@ static int __init bcm7120_l2_intc_probe(struct device_node *dn, if (data->can_wake) { /* This IRQ chip can wake the system, set all - * relevant child interupts in wake_enabled mask + * relevant child interrupts in wake_enabled mask */ gc->wake_enabled = 0xffffffff; gc->wake_enabled &= ~gc->unused; diff --git a/drivers/irqchip/irq-csky-apb-intc.c b/drivers/irqchip/irq-csky-apb-intc.c index 5a2ec43b7ddd..ab91afa86755 100644 --- a/drivers/irqchip/irq-csky-apb-intc.c +++ b/drivers/irqchip/irq-csky-apb-intc.c @@ -176,7 +176,7 @@ gx_intc_init(struct device_node *node, struct device_node *parent) writel(0x0, reg_base + GX_INTC_NEN63_32); /* - * Initial mask reg with all unmasked, because we only use enalbe reg + * Initial mask reg with all unmasked, because we only use enable reg */ writel(0x0, reg_base + GX_INTC_NMASK31_00); writel(0x0, reg_base + GX_INTC_NMASK63_32); diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index fbec07d634ad..4116b48e60af 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -371,7 +371,7 @@ static int __init gicv2m_init_one(struct fwnode_handle *fwnode, * the MSI data is the absolute value within the range from * spi_start to (spi_start + num_spis). * - * Broadom NS2 GICv2m implementation has an erratum where the MSI data + * Broadcom NS2 GICv2m implementation has an erratum where the MSI data * is 'spi_number - 32' * * Reading that register fails on the Graviton implementation diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index d8cb5bcd6b10..5ec091c64d47 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1492,7 +1492,7 @@ static void its_vlpi_set_doorbell(struct irq_data *d, bool enable) * * Ideally, we'd issue a VMAPTI to set the doorbell to its LPI * value or to 1023, depending on the enable bit. But that - * would be issueing a mapping for an /existing/ DevID+EventID + * would be issuing a mapping for an /existing/ DevID+EventID * pair, which is UNPREDICTABLE. Instead, let's issue a VMOVI * to the /same/ vPE, using this opportunity to adjust the * doorbell. Mouahahahaha. We loves it, Precious. @@ -3122,7 +3122,7 @@ static void its_cpu_init_lpis(void) /* * It's possible for CPU to receive VLPIs before it is - * sheduled as a vPE, especially for the first CPU, and the + * scheduled as a vPE, especially for the first CPU, and the * VLPI with INTID larger than 2^(IDbits+1) will be considered * as out of range and dropped by GIC. * So we initialize IDbits to known value to avoid VLPI drop. @@ -3613,7 +3613,7 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, /* * If all interrupts have been freed, start mopping the - * floor. This is conditionned on the device not being shared. + * floor. This is conditioned on the device not being shared. */ if (!its_dev->shared && bitmap_empty(its_dev->event_map.lpi_map, @@ -4187,7 +4187,7 @@ static int its_sgi_set_affinity(struct irq_data *d, { /* * There is no notion of affinity for virtual SGIs, at least - * not on the host (since they can only be targetting a vPE). + * not on the host (since they can only be targeting a vPE). * Tell the kernel we've done whatever it asked for. */ irq_data_update_effective_affinity(d, mask_val); @@ -4232,7 +4232,7 @@ static int its_sgi_get_irqchip_state(struct irq_data *d, /* * Locking galore! We can race against two different events: * - * - Concurent vPE affinity change: we must make sure it cannot + * - Concurrent vPE affinity change: we must make sure it cannot * happen, or we'll talk to the wrong redistributor. This is * identical to what happens with vLPIs. * diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 4c8f18f0cecf..2805969e4f15 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -1456,7 +1456,7 @@ static int gic_irq_domain_translate(struct irq_domain *d, /* * Make it clear that broken DTs are... broken. - * Partitionned PPIs are an unfortunate exception. + * Partitioned PPIs are an unfortunate exception. */ WARN_ON(*type == IRQ_TYPE_NONE && fwspec->param[0] != GIC_IRQ_TYPE_PARTITION); diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c index 90e1ad6e3612..a4eb8a2181c7 100644 --- a/drivers/irqchip/irq-loongson-pch-pic.c +++ b/drivers/irqchip/irq-loongson-pch-pic.c @@ -180,7 +180,7 @@ static void pch_pic_reset(struct pch_pic *priv) int i; for (i = 0; i < PIC_COUNT; i++) { - /* Write vectore ID */ + /* Write vectored ID */ writeb(priv->ht_vec_base + i, priv->base + PCH_INT_HTVEC(i)); /* Hardcode route to HT0 Lo */ writeb(1, priv->base + PCH_INT_ROUTE(i)); diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index bc7aebcc96e9..e50676ce2ec8 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -227,7 +227,7 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl, /* * Get the hwirq number assigned to this channel through - * a pointer the channel_irq table. The added benifit of this + * a pointer the channel_irq table. The added benefit of this * method is that we can also retrieve the channel index with * it, using the table base. */ diff --git a/drivers/irqchip/irq-mtk-cirq.c b/drivers/irqchip/irq-mtk-cirq.c index 69ba8ce3c178..9bca0918078e 100644 --- a/drivers/irqchip/irq-mtk-cirq.c +++ b/drivers/irqchip/irq-mtk-cirq.c @@ -217,7 +217,7 @@ static void mtk_cirq_resume(void) { u32 value; - /* flush recored interrupts, will send signals to parent controller */ + /* flush recorded interrupts, will send signals to parent controller */ value = readl_relaxed(cirq_data->base + CIRQ_CONTROL); writel_relaxed(value | CIRQ_FLUSH, cirq_data->base + CIRQ_CONTROL); diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c index a671938fd97f..d1f5740cd575 100644 --- a/drivers/irqchip/irq-mxs.c +++ b/drivers/irqchip/irq-mxs.c @@ -58,7 +58,7 @@ struct icoll_priv { static struct icoll_priv icoll_priv; static struct irq_domain *icoll_domain; -/* calculate bit offset depending on number of intterupt per register */ +/* calculate bit offset depending on number of interrupt per register */ static u32 icoll_intr_bitshift(struct irq_data *d, u32 bit) { /* @@ -68,7 +68,7 @@ static u32 icoll_intr_bitshift(struct irq_data *d, u32 bit) return bit << ((d->hwirq & 3) << 3); } -/* calculate mem offset depending on number of intterupt per register */ +/* calculate mem offset depending on number of interrupt per register */ static void __iomem *icoll_intr_reg(struct irq_data *d) { /* offset = hwirq / intr_per_reg * 0x10 */ diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c index fb78d6623556..9ea94456b178 100644 --- a/drivers/irqchip/irq-sun4i.c +++ b/drivers/irqchip/irq-sun4i.c @@ -189,7 +189,7 @@ static void __exception_irq_entry sun4i_handle_irq(struct pt_regs *regs) * 3) spurious irq * So if we immediately get a reading of 0, check the irq-pending reg * to differentiate between 2 and 3. We only do this once to avoid - * the extra check in the common case of 1 hapening after having + * the extra check in the common case of 1 happening after having * read the vector-reg once. */ hwirq = readl(irq_ic_data->irq_base + SUN4I_IRQ_VECTOR_REG) >> 2; diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index 532d0ae172d9..ca1f593f4d13 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -78,7 +78,7 @@ struct ti_sci_inta_vint_desc { * struct ti_sci_inta_irq_domain - Structure representing a TISCI based * Interrupt Aggregator IRQ domain. * @sci: Pointer to TISCI handle - * @vint: TISCI resource pointer representing IA inerrupts. + * @vint: TISCI resource pointer representing IA interrupts. * @global_event: TISCI resource pointer representing global events. * @vint_list: List of the vints active in the system * @vint_mutex: Mutex to protect vint_list diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c index e46036374227..62f3d29f9042 100644 --- a/drivers/irqchip/irq-vic.c +++ b/drivers/irqchip/irq-vic.c @@ -163,7 +163,7 @@ static struct syscore_ops vic_syscore_ops = { }; /** - * vic_pm_init - initicall to register VIC pm + * vic_pm_init - initcall to register VIC pm * * This is called via late_initcall() to register * the resources for the VICs due to the early @@ -397,7 +397,7 @@ static void __init vic_clear_interrupts(void __iomem *base) /* * The PL190 cell from ARM has been modified by ST to handle 64 interrupts. * The original cell has 32 interrupts, while the modified one has 64, - * replocating two blocks 0x00..0x1f in 0x20..0x3f. In that case + * replicating two blocks 0x00..0x1f in 0x20..0x3f. In that case * the probe function is called twice, with base set to offset 000 * and 020 within the page. We call this "second block". */ diff --git a/drivers/irqchip/irq-xilinx-intc.c b/drivers/irqchip/irq-xilinx-intc.c index 1d3d273309bd..8cd1bfc73057 100644 --- a/drivers/irqchip/irq-xilinx-intc.c +++ b/drivers/irqchip/irq-xilinx-intc.c @@ -210,7 +210,7 @@ static int __init xilinx_intc_of_init(struct device_node *intc, /* * Disable all external interrupts until they are - * explicity requested. + * explicitly requested. */ xintc_write(irqc, IER, 0); diff --git a/include/linux/irq.h b/include/linux/irq.h index 607bee9271bd..b89a8ac83d1b 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -116,7 +116,7 @@ enum { * IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to * support stacked irqchips, which indicates skipping - * all descendent irqchips. + * all descendant irqchips. */ enum { IRQ_SET_MASK_OK = 0, @@ -302,7 +302,7 @@ static inline bool irqd_is_level_type(struct irq_data *d) /* * Must only be called of irqchip.irq_set_affinity() or low level - * hieararchy domain allocation functions. + * hierarchy domain allocation functions. */ static inline void irqd_set_single_target(struct irq_data *d) { diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 5745491303e0..fdb22e0f9a91 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -32,7 +32,7 @@ struct pt_regs; * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts * @threads_handled: stats field for deferred spurious detection of threaded handlers - * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers + * @threads_handled_last: comparator field for deferred spurious detection of threaded handlers * @lock: locking for SMP * @affinity_hint: hint to user space for preferred irq affinity * @affinity_notify: context for notification of affinity changes diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 621d8dd157bc..e7d284261d45 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -811,7 +811,7 @@ void handle_edge_irq(struct irq_desc *desc) /* * When another irq arrived while we were handling * one, we could have masked the irq. - * Renable it, if it was not disabled in meantime. + * Reenable it, if it was not disabled in meantime. */ if (unlikely(desc->istate & IRQS_PENDING)) { if (!irqd_irq_disabled(&desc->irq_data) && diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c index 0b0cdf206dc4..7fe6cffe7d0d 100644 --- a/kernel/irq/dummychip.c +++ b/kernel/irq/dummychip.c @@ -13,7 +13,7 @@ /* * What should we do if we get a hw irq event on an illegal vector? - * Each architecture has to answer this themself. + * Each architecture has to answer this themselves. */ static void ack_bad(struct irq_data *data) { diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 9b0914a063f9..6c009a033c73 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -31,7 +31,7 @@ static int __init irq_affinity_setup(char *str) cpulist_parse(str, irq_default_affinity); /* * Set at least the boot cpu. We don't want to end up with - * bugreports caused by random comandline masks + * bugreports caused by random commandline masks */ cpumask_set_cpu(smp_processor_id(), irq_default_affinity); return 1; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 1720998933f8..fe07888a7d96 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -53,7 +53,7 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops); * @name: Optional user provided domain name * @pa: Optional user-provided physical address * - * Allocate a struct irqchip_fwid, and return a poiner to the embedded + * Allocate a struct irqchip_fwid, and return a pointer to the embedded * fwnode_handle (or NULL on failure). * * Note: The types IRQCHIP_FWNODE_NAMED and IRQCHIP_FWNODE_NAMED_ID are @@ -657,7 +657,7 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain, pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); - /* Look for default domain if nececssary */ + /* Look for default domain if necessary */ if (domain == NULL) domain = irq_default_domain; if (domain == NULL) { @@ -893,7 +893,7 @@ unsigned int irq_find_mapping(struct irq_domain *domain, { struct irq_data *data; - /* Look for default domain if nececssary */ + /* Look for default domain if necessary */ if (domain == NULL) domain = irq_default_domain; if (domain == NULL) @@ -1423,7 +1423,7 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, * The whole process to setup an IRQ has been split into two steps. * The first step, __irq_domain_alloc_irqs(), is to allocate IRQ * descriptor and required hardware resources. The second step, - * irq_domain_activate_irq(), is to program hardwares with preallocated + * irq_domain_activate_irq(), is to program the hardware with preallocated * resources. In this way, it's easier to rollback when failing to * allocate resources. */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 437b073dc487..0159925054fa 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -341,7 +341,7 @@ static bool irq_set_affinity_deactivated(struct irq_data *data, * If the interrupt is not yet activated, just store the affinity * mask and do not call the chip driver at all. On activation the * driver has to make sure anyway that the interrupt is in a - * useable state so startup works. + * usable state so startup works. */ if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || irqd_is_activated(data) || !irqd_affinity_on_activate(data)) @@ -999,7 +999,7 @@ again: * to IRQS_INPROGRESS and the irq line is masked forever. * * This also serializes the state of shared oneshot handlers - * versus "desc->threads_onehsot |= action->thread_mask;" in + * versus "desc->threads_oneshot |= action->thread_mask;" in * irq_wake_thread(). See the comment there which explains the * serialization. */ @@ -1877,7 +1877,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) /* Last action releases resources */ if (!desc->action) { /* - * Reaquire bus lock as irq_release_resources() might + * Reacquire bus lock as irq_release_resources() might * require it to deallocate resources over the slow bus. */ chip_bus_lock(desc); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index b47d95b68ac1..4457f3e966d0 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -5,7 +5,7 @@ * * This file is licensed under GPLv2. * - * This file contains common code to support Message Signalled Interrupt for + * This file contains common code to support Message Signaled Interrupts for * PCI compatible and non PCI compatible devices. */ #include diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index 1f981162648a..00d45b6bd8f8 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -490,7 +490,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts) /* * The interrupt triggered more than one second apart, that - * ends the sequence as predictible for our purpose. In this + * ends the sequence as predictable for our purpose. In this * case, assume we have the beginning of a sequence and the * timestamp is the first value. As it is impossible to * predict anything at this point, return. From ff762cdbf0c8c9bf0b97684f39af13b3332e77e8 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 13 Feb 2023 11:42:46 +0100 Subject: [PATCH 2050/4345] irqdomain: Look for existing mapping only once [ Upstream commit 6e6f75c9c98d2d246d90411ff2b6f0cd271f4cba ] Avoid looking for an existing mapping twice when creating a new mapping using irq_create_fwspec_mapping() by factoring out the actual allocation which is shared with irq_create_mapping_affinity(). The new helper function will also be used to fix a shared-interrupt mapping race, hence the Fixes tag. Fixes: b62b2cf5759b ("irqdomain: Fix handling of type settings for existing mappings") Cc: stable@vger.kernel.org # 4.8 Tested-by: Hsin-Yi Wang Tested-by: Mark-PK Tsai Signed-off-by: Johan Hovold Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230213104302.17307-5-johan+linaro@kernel.org Signed-off-by: Sasha Levin --- kernel/irq/irqdomain.c | 74 +++++++++++++++++++++++------------------- 1 file changed, 40 insertions(+), 34 deletions(-) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index fe07888a7d96..d18c25a41673 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -637,44 +637,15 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) } EXPORT_SYMBOL_GPL(irq_create_direct_mapping); -/** - * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space - * @domain: domain owning this hardware interrupt or NULL for default domain - * @hwirq: hardware irq number in that domain space - * @affinity: irq affinity - * - * Only one mapping per hardware interrupt is permitted. Returns a linux - * irq number. - * If the sense/trigger is to be specified, set_irq_type() should be called - * on the number returned from that call. - */ -unsigned int irq_create_mapping_affinity(struct irq_domain *domain, - irq_hw_number_t hwirq, - const struct irq_affinity_desc *affinity) +static unsigned int __irq_create_mapping_affinity(struct irq_domain *domain, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity) { - struct device_node *of_node; + struct device_node *of_node = irq_domain_get_of_node(domain); int virq; pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); - /* Look for default domain if necessary */ - if (domain == NULL) - domain = irq_default_domain; - if (domain == NULL) { - WARN(1, "%s(, %lx) called with NULL domain\n", __func__, hwirq); - return 0; - } - pr_debug("-> using domain @%p\n", domain); - - of_node = irq_domain_get_of_node(domain); - - /* Check if mapping already exists */ - virq = irq_find_mapping(domain, hwirq); - if (virq) { - pr_debug("-> existing mapping on virq %d\n", virq); - return virq; - } - /* Allocate a virtual interrupt number */ virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), affinity); @@ -693,6 +664,41 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain, return virq; } + +/** + * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space + * @domain: domain owning this hardware interrupt or NULL for default domain + * @hwirq: hardware irq number in that domain space + * @affinity: irq affinity + * + * Only one mapping per hardware interrupt is permitted. Returns a linux + * irq number. + * If the sense/trigger is to be specified, set_irq_type() should be called + * on the number returned from that call. + */ +unsigned int irq_create_mapping_affinity(struct irq_domain *domain, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity) +{ + int virq; + + /* Look for default domain if necessary */ + if (domain == NULL) + domain = irq_default_domain; + if (domain == NULL) { + WARN(1, "%s(, %lx) called with NULL domain\n", __func__, hwirq); + return 0; + } + + /* Check if mapping already exists */ + virq = irq_find_mapping(domain, hwirq); + if (virq) { + pr_debug("existing mapping on virq %d\n", virq); + return virq; + } + + return __irq_create_mapping_affinity(domain, hwirq, affinity); +} EXPORT_SYMBOL_GPL(irq_create_mapping_affinity); /** @@ -831,7 +837,7 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) return 0; } else { /* Create mapping */ - virq = irq_create_mapping(domain, hwirq); + virq = __irq_create_mapping_affinity(domain, hwirq, NULL); if (!virq) return virq; } From 8617599c646f8c4623fe8c998fc4f9303c2967d4 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 13 Feb 2023 11:42:47 +0100 Subject: [PATCH 2051/4345] irqdomain: Refactor __irq_domain_alloc_irqs() [ Upstream commit d55f7f4c58c07beb5050a834bf57ae2ede599c7e ] Refactor __irq_domain_alloc_irqs() so that it can be called internally while holding the irq_domain_mutex. This will be used to fix a shared-interrupt mapping race, hence the Fixes tag. Fixes: b62b2cf5759b ("irqdomain: Fix handling of type settings for existing mappings") Cc: stable@vger.kernel.org # 4.8 Tested-by: Hsin-Yi Wang Tested-by: Mark-PK Tsai Signed-off-by: Johan Hovold Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230213104302.17307-6-johan+linaro@kernel.org Signed-off-by: Sasha Levin --- kernel/irq/irqdomain.c | 90 +++++++++++++++++++++++------------------- 1 file changed, 49 insertions(+), 41 deletions(-) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index d18c25a41673..a1e1433a0775 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1411,6 +1411,52 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, return domain->ops->alloc(domain, irq_base, nr_irqs, arg); } +static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc, const struct irq_affinity_desc *affinity) +{ + int i, ret, virq; + + if (realloc && irq_base >= 0) { + virq = irq_base; + } else { + virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node, + affinity); + if (virq < 0) { + pr_debug("cannot allocate IRQ(base %d, count %d)\n", + irq_base, nr_irqs); + return virq; + } + } + + if (irq_domain_alloc_irq_data(domain, virq, nr_irqs)) { + pr_debug("cannot allocate memory for IRQ%d\n", virq); + ret = -ENOMEM; + goto out_free_desc; + } + + ret = irq_domain_alloc_irqs_hierarchy(domain, virq, nr_irqs, arg); + if (ret < 0) + goto out_free_irq_data; + + for (i = 0; i < nr_irqs; i++) { + ret = irq_domain_trim_hierarchy(virq + i); + if (ret) + goto out_free_irq_data; + } + + for (i = 0; i < nr_irqs; i++) + irq_domain_insert_irq(virq + i); + + return virq; + +out_free_irq_data: + irq_domain_free_irq_data(virq, nr_irqs); +out_free_desc: + irq_free_descs(virq, nr_irqs); + return ret; +} + /** * __irq_domain_alloc_irqs - Allocate IRQs from domain * @domain: domain to allocate from @@ -1437,7 +1483,7 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, unsigned int nr_irqs, int node, void *arg, bool realloc, const struct irq_affinity_desc *affinity) { - int i, ret, virq; + int ret; if (domain == NULL) { domain = irq_default_domain; @@ -1445,49 +1491,11 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, return -EINVAL; } - if (realloc && irq_base >= 0) { - virq = irq_base; - } else { - virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node, - affinity); - if (virq < 0) { - pr_debug("cannot allocate IRQ(base %d, count %d)\n", - irq_base, nr_irqs); - return virq; - } - } - - if (irq_domain_alloc_irq_data(domain, virq, nr_irqs)) { - pr_debug("cannot allocate memory for IRQ%d\n", virq); - ret = -ENOMEM; - goto out_free_desc; - } - mutex_lock(&irq_domain_mutex); - ret = irq_domain_alloc_irqs_hierarchy(domain, virq, nr_irqs, arg); - if (ret < 0) { - mutex_unlock(&irq_domain_mutex); - goto out_free_irq_data; - } - - for (i = 0; i < nr_irqs; i++) { - ret = irq_domain_trim_hierarchy(virq + i); - if (ret) { - mutex_unlock(&irq_domain_mutex); - goto out_free_irq_data; - } - } - - for (i = 0; i < nr_irqs; i++) - irq_domain_insert_irq(virq + i); + ret = irq_domain_alloc_irqs_locked(domain, irq_base, nr_irqs, node, arg, + realloc, affinity); mutex_unlock(&irq_domain_mutex); - return virq; - -out_free_irq_data: - irq_domain_free_irq_data(virq, nr_irqs); -out_free_desc: - irq_free_descs(virq, nr_irqs); return ret; } From 4ab311d51cd99ddc48e828e70fbdf9c076416cf2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 13 Feb 2023 11:42:48 +0100 Subject: [PATCH 2052/4345] irqdomain: Fix mapping-creation race [ Upstream commit 601363cc08da25747feb87c55573dd54de91d66a ] Parallel probing of devices that share interrupts (e.g. when a driver uses asynchronous probing) can currently result in two mappings for the same hardware interrupt to be created due to missing serialisation. Make sure to hold the irq_domain_mutex when creating mappings so that looking for an existing mapping before creating a new one is done atomically. Fixes: 765230b5f084 ("driver-core: add asynchronous probing support for drivers") Fixes: b62b2cf5759b ("irqdomain: Fix handling of type settings for existing mappings") Link: https://lore.kernel.org/r/YuJXMHoT4ijUxnRb@hovoldconsulting.com Cc: stable@vger.kernel.org # 4.8 Cc: Dmitry Torokhov Cc: Jon Hunter Tested-by: Hsin-Yi Wang Tested-by: Mark-PK Tsai Signed-off-by: Johan Hovold Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230213104302.17307-7-johan+linaro@kernel.org Signed-off-by: Sasha Levin --- kernel/irq/irqdomain.c | 64 ++++++++++++++++++++++++++++++------------ 1 file changed, 46 insertions(+), 18 deletions(-) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index a1e1433a0775..245e317c7290 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -25,6 +25,9 @@ static DEFINE_MUTEX(irq_domain_mutex); static struct irq_domain *irq_default_domain; +static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc, const struct irq_affinity_desc *affinity); static void irq_domain_check_hierarchy(struct irq_domain *domain); struct irqchip_fwid { @@ -637,9 +640,9 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) } EXPORT_SYMBOL_GPL(irq_create_direct_mapping); -static unsigned int __irq_create_mapping_affinity(struct irq_domain *domain, - irq_hw_number_t hwirq, - const struct irq_affinity_desc *affinity) +static unsigned int irq_create_mapping_affinity_locked(struct irq_domain *domain, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity) { struct device_node *of_node = irq_domain_get_of_node(domain); int virq; @@ -654,7 +657,7 @@ static unsigned int __irq_create_mapping_affinity(struct irq_domain *domain, return 0; } - if (irq_domain_associate(domain, virq, hwirq)) { + if (irq_domain_associate_locked(domain, virq, hwirq)) { irq_free_desc(virq); return 0; } @@ -690,14 +693,20 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain, return 0; } + mutex_lock(&irq_domain_mutex); + /* Check if mapping already exists */ virq = irq_find_mapping(domain, hwirq); if (virq) { pr_debug("existing mapping on virq %d\n", virq); - return virq; + goto out; } - return __irq_create_mapping_affinity(domain, hwirq, affinity); + virq = irq_create_mapping_affinity_locked(domain, hwirq, affinity); +out: + mutex_unlock(&irq_domain_mutex); + + return virq; } EXPORT_SYMBOL_GPL(irq_create_mapping_affinity); @@ -799,6 +808,8 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) if (WARN_ON(type & ~IRQ_TYPE_SENSE_MASK)) type &= IRQ_TYPE_SENSE_MASK; + mutex_lock(&irq_domain_mutex); + /* * If we've already configured this interrupt, * don't do it again, or hell will break loose. @@ -811,7 +822,7 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) * interrupt number. */ if (type == IRQ_TYPE_NONE || type == irq_get_trigger_type(virq)) - return virq; + goto out; /* * If the trigger type has not been set yet, then set @@ -819,35 +830,45 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) */ if (irq_get_trigger_type(virq) == IRQ_TYPE_NONE) { irq_data = irq_get_irq_data(virq); - if (!irq_data) - return 0; + if (!irq_data) { + virq = 0; + goto out; + } irqd_set_trigger_type(irq_data, type); - return virq; + goto out; } pr_warn("type mismatch, failed to map hwirq-%lu for %s!\n", hwirq, of_node_full_name(to_of_node(fwspec->fwnode))); - return 0; + virq = 0; + goto out; } if (irq_domain_is_hierarchy(domain)) { - virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, fwspec); - if (virq <= 0) - return 0; + virq = irq_domain_alloc_irqs_locked(domain, -1, 1, NUMA_NO_NODE, + fwspec, false, NULL); + if (virq <= 0) { + virq = 0; + goto out; + } } else { /* Create mapping */ - virq = __irq_create_mapping_affinity(domain, hwirq, NULL); + virq = irq_create_mapping_affinity_locked(domain, hwirq, NULL); if (!virq) - return virq; + goto out; } irq_data = irq_get_irq_data(virq); - if (WARN_ON(!irq_data)) - return 0; + if (WARN_ON(!irq_data)) { + virq = 0; + goto out; + } /* Store trigger type */ irqd_set_trigger_type(irq_data, type); +out: + mutex_unlock(&irq_domain_mutex); return virq; } @@ -1856,6 +1877,13 @@ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, irq_set_handler_data(virq, handler_data); } +static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc, const struct irq_affinity_desc *affinity) +{ + return -EINVAL; +} + static void irq_domain_check_hierarchy(struct irq_domain *domain) { } From bb7597777c134a6229f74843d307866643a792ed Mon Sep 17 00:00:00 2001 From: Bixuan Cui Date: Thu, 16 Sep 2021 10:52:03 +0800 Subject: [PATCH 2053/4345] irqdomain: Change the type of 'size' in __irq_domain_add() to be consistent [ Upstream commit 20c36ce2164f1774b487d443ece99b754bc6ad43 ] The 'size' is used in struct_size(domain, revmap, size) and its input parameter type is 'size_t'(unsigned int). Changing the size to 'unsigned int' to make the type consistent. Signed-off-by: Bixuan Cui Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210916025203.44841-1-cuibixuan@huawei.com Stable-dep-of: 8932c32c3053 ("irqdomain: Fix domain registration race") Signed-off-by: Sasha Levin --- include/linux/irqdomain.h | 2 +- kernel/irq/irqdomain.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index ea5a337e0f8b..9b9743f7538c 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -256,7 +256,7 @@ static inline struct fwnode_handle *irq_domain_alloc_fwnode(phys_addr_t *pa) } void irq_domain_free_fwnode(struct fwnode_handle *fwnode); -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 245e317c7290..426242c8903d 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -130,7 +130,7 @@ EXPORT_SYMBOL_GPL(irq_domain_free_fwnode); * Allocates and initializes an irq_domain structure. * Returns pointer to IRQ domain, or NULL on failure. */ -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data) From aeab1f1a60ae19ab7bc509f2b6c9ae5a60761ca9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 13 Feb 2023 11:42:49 +0100 Subject: [PATCH 2054/4345] irqdomain: Fix domain registration race [ Upstream commit 8932c32c3053accd50702b36e944ac2016cd103c ] Hierarchical domains created using irq_domain_create_hierarchy() are currently added to the domain list before having been fully initialised. This specifically means that a racing allocation request might fail to allocate irq data for the inner domains of a hierarchy in case the parent domain pointer has not yet been set up. Note that this is not really any issue for irqchip drivers that are registered early (e.g. via IRQCHIP_DECLARE() or IRQCHIP_ACPI_DECLARE()) but could potentially cause trouble with drivers that are registered later (e.g. modular drivers using IRQCHIP_PLATFORM_DRIVER_BEGIN(), gpiochip drivers, etc.). Fixes: afb7da83b9f4 ("irqdomain: Introduce helper function irq_domain_add_hierarchy()") Cc: stable@vger.kernel.org # 3.19 Signed-off-by: Marc Zyngier [ johan: add commit message ] Signed-off-by: Johan Hovold Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230213104302.17307-8-johan+linaro@kernel.org Signed-off-by: Sasha Levin --- kernel/irq/irqdomain.c | 62 +++++++++++++++++++++++++++++------------- 1 file changed, 43 insertions(+), 19 deletions(-) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 426242c8903d..fd3f7c16c299 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -117,23 +117,12 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode) } EXPORT_SYMBOL_GPL(irq_domain_free_fwnode); -/** - * __irq_domain_add() - Allocate a new irq_domain data structure - * @fwnode: firmware node for the interrupt controller - * @size: Size of linear map; 0 for radix mapping only - * @hwirq_max: Maximum number of interrupts supported by controller - * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no - * direct mapping - * @ops: domain callbacks - * @host_data: Controller private data pointer - * - * Allocates and initializes an irq_domain structure. - * Returns pointer to IRQ domain, or NULL on failure. - */ -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, - irq_hw_number_t hwirq_max, int direct_max, - const struct irq_domain_ops *ops, - void *host_data) +static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode, + unsigned int size, + irq_hw_number_t hwirq_max, + int direct_max, + const struct irq_domain_ops *ops, + void *host_data) { struct irqchip_fwid *fwid; struct irq_domain *domain; @@ -210,12 +199,44 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int s domain->revmap_direct_max_irq = direct_max; irq_domain_check_hierarchy(domain); + return domain; +} + +static void __irq_domain_publish(struct irq_domain *domain) +{ mutex_lock(&irq_domain_mutex); debugfs_add_domain_dir(domain); list_add(&domain->link, &irq_domain_list); mutex_unlock(&irq_domain_mutex); pr_debug("Added domain %s\n", domain->name); +} + +/** + * __irq_domain_add() - Allocate a new irq_domain data structure + * @fwnode: firmware node for the interrupt controller + * @size: Size of linear map; 0 for radix mapping only + * @hwirq_max: Maximum number of interrupts supported by controller + * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no + * direct mapping + * @ops: domain callbacks + * @host_data: Controller private data pointer + * + * Allocates and initializes an irq_domain structure. + * Returns pointer to IRQ domain, or NULL on failure. + */ +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, + irq_hw_number_t hwirq_max, int direct_max, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + domain = __irq_domain_create(fwnode, size, hwirq_max, direct_max, + ops, host_data); + if (domain) + __irq_domain_publish(domain); + return domain; } EXPORT_SYMBOL_GPL(__irq_domain_add); @@ -1110,12 +1131,15 @@ struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, struct irq_domain *domain; if (size) - domain = irq_domain_create_linear(fwnode, size, ops, host_data); + domain = __irq_domain_create(fwnode, size, size, 0, ops, host_data); else - domain = irq_domain_create_tree(fwnode, ops, host_data); + domain = __irq_domain_create(fwnode, 0, ~0, 0, ops, host_data); + if (domain) { domain->parent = parent; domain->flags |= flags; + + __irq_domain_publish(domain); } return domain; From c424b1819120093d34852c5893c507a4bc0b5a98 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 20 Mar 2021 10:09:16 +0800 Subject: [PATCH 2055/4345] iommu/vt-d: Fix lockdep splat in intel_pasid_get_entry() [ Upstream commit 803766cbf85fb8edbf896729bbefc2d38dcf1e0a ] The pasid_lock is used to synchronize different threads from modifying a same pasid directory entry at the same time. It causes below lockdep splat. [ 83.296538] ======================================================== [ 83.296538] WARNING: possible irq lock inversion dependency detected [ 83.296539] 5.12.0-rc3+ #25 Tainted: G W [ 83.296539] -------------------------------------------------------- [ 83.296540] bash/780 just changed the state of lock: [ 83.296540] ffffffff82b29c98 (device_domain_lock){..-.}-{2:2}, at: iommu_flush_dev_iotlb.part.0+0x32/0x110 [ 83.296547] but this lock took another, SOFTIRQ-unsafe lock in the past: [ 83.296547] (pasid_lock){+.+.}-{2:2} [ 83.296548] and interrupts could create inverse lock ordering between them. [ 83.296549] other info that might help us debug this: [ 83.296549] Chain exists of: device_domain_lock --> &iommu->lock --> pasid_lock [ 83.296551] Possible interrupt unsafe locking scenario: [ 83.296551] CPU0 CPU1 [ 83.296552] ---- ---- [ 83.296552] lock(pasid_lock); [ 83.296553] local_irq_disable(); [ 83.296553] lock(device_domain_lock); [ 83.296554] lock(&iommu->lock); [ 83.296554] [ 83.296554] lock(device_domain_lock); [ 83.296555] *** DEADLOCK *** Fix it by replacing the pasid_lock with an atomic exchange operation. Reported-and-tested-by: Dave Jiang Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210320020916.640115-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel Stable-dep-of: 194b3348bdbb ("iommu/vt-d: Fix PASID directory pointer coherency") Signed-off-by: Sasha Levin --- drivers/iommu/intel/pasid.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 86fd49ae7f61..f821153390e5 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -24,7 +24,6 @@ /* * Intel IOMMU system wide PASID name space: */ -static DEFINE_SPINLOCK(pasid_lock); u32 intel_pasid_max_id = PASID_MAX; int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid) @@ -259,19 +258,25 @@ struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid) dir_index = pasid >> PASID_PDE_SHIFT; index = pasid & PASID_PTE_MASK; - spin_lock(&pasid_lock); +retry: entries = get_pasid_table_from_pde(&dir[dir_index]); if (!entries) { entries = alloc_pgtable_page(info->iommu->node); - if (!entries) { - spin_unlock(&pasid_lock); + if (!entries) return NULL; - } - WRITE_ONCE(dir[dir_index].val, - (u64)virt_to_phys(entries) | PASID_PTE_PRESENT); + /* + * The pasid directory table entry won't be freed after + * allocation. No worry about the race with free and + * clear. However, this entry might be populated by others + * while we are preparing it. Use theirs with a retry. + */ + if (cmpxchg64(&dir[dir_index].val, 0ULL, + (u64)virt_to_phys(entries) | PASID_PTE_PRESENT)) { + free_pgtable_page(entries); + goto retry; + } } - spin_unlock(&pasid_lock); return &entries[index]; } From 7e00b52c8cdd9d3a985d63d72ecae7bde6314883 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Thu, 16 Feb 2023 21:08:15 +0800 Subject: [PATCH 2056/4345] iommu/vt-d: Fix PASID directory pointer coherency [ Upstream commit 194b3348bdbb7db65375c72f3f774aee4cc6614e ] On platforms that do not support IOMMU Extended capability bit 0 Page-walk Coherency, CPU caches are not snooped when IOMMU is accessing any translation structures. IOMMU access goes only directly to memory. Intel IOMMU code was missing a flush for the PASID table directory that resulted in the unrecoverable fault as shown below. This patch adds clflush calls whenever allocating and updating a PASID table directory to ensure cache coherency. On the reverse direction, there's no need to clflush the PASID directory pointer when we deactivate a context entry in that IOMMU hardware will not see the old PASID directory pointer after we clear the context entry. PASID directory entries are also never freed once allocated. DMAR: DRHD: handling fault status reg 3 DMAR: [DMA Read NO_PASID] Request device [00:0d.2] fault addr 0x1026a4000 [fault reason 0x51] SM: Present bit in Directory Entry is clear DMAR: Dump dmar1 table entries for IOVA 0x1026a4000 DMAR: scalable mode root entry: hi 0x0000000102448001, low 0x0000000101b3e001 DMAR: context entry: hi 0x0000000000000000, low 0x0000000101b4d401 DMAR: pasid dir entry: 0x0000000101b4e001 DMAR: pasid table entry[0]: 0x0000000000000109 DMAR: pasid table entry[1]: 0x0000000000000001 DMAR: pasid table entry[2]: 0x0000000000000000 DMAR: pasid table entry[3]: 0x0000000000000000 DMAR: pasid table entry[4]: 0x0000000000000000 DMAR: pasid table entry[5]: 0x0000000000000000 DMAR: pasid table entry[6]: 0x0000000000000000 DMAR: pasid table entry[7]: 0x0000000000000000 DMAR: PTE not present at level 4 Cc: Fixes: 0bbeb01a4faf ("iommu/vt-d: Manage scalalble mode PASID tables") Reviewed-by: Kevin Tian Reported-by: Sukumar Ghorai Signed-off-by: Ashok Raj Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230209212843.1788125-1-jacob.jun.pan@linux.intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/intel/pasid.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index f821153390e5..80d6412e2c54 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -186,6 +186,9 @@ int intel_pasid_alloc_table(struct device *dev) attach_out: device_attach_pasid_table(info, pasid_table); + if (!ecap_coherent(info->iommu->ecap)) + clflush_cache_range(pasid_table->table, size); + return 0; } @@ -276,6 +279,10 @@ retry: free_pgtable_page(entries); goto retry; } + if (!ecap_coherent(info->iommu->ecap)) { + clflush_cache_range(entries, VTD_PAGE_SIZE); + clflush_cache_range(&dir[dir_index].val, sizeof(*dir)); + } } return &entries[index]; From 030b1c4217a4f504c7d0795a2bd86b7181e56f11 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 15 Feb 2023 17:10:47 +0100 Subject: [PATCH 2057/4345] arm64: efi: Make efi_rt_lock a raw_spinlock [ Upstream commit 0e68b5517d3767562889f1d83fdb828c26adb24f ] Running a rt-kernel base on 6.2.0-rc3-rt1 on an Ampere Altra outputs the following: BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9, name: kworker/u320:0 preempt_count: 2, expected: 0 RCU nest depth: 0, expected: 0 3 locks held by kworker/u320:0/9: #0: ffff3fff8c27d128 ((wq_completion)efi_rts_wq){+.+.}-{0:0}, at: process_one_work (./include/linux/atomic/atomic-long.h:41) #1: ffff80000861bdd0 ((work_completion)(&efi_rts_work.work)){+.+.}-{0:0}, at: process_one_work (./include/linux/atomic/atomic-long.h:41) #2: ffffdf7e1ed3e460 (efi_rt_lock){+.+.}-{3:3}, at: efi_call_rts (drivers/firmware/efi/runtime-wrappers.c:101) Preemption disabled at: efi_virtmap_load (./arch/arm64/include/asm/mmu_context.h:248) CPU: 0 PID: 9 Comm: kworker/u320:0 Tainted: G W 6.2.0-rc3-rt1 Hardware name: WIWYNN Mt.Jade Server System B81.03001.0005/Mt.Jade Motherboard, BIOS 1.08.20220218 (SCP: 1.08.20220218) 2022/02/18 Workqueue: efi_rts_wq efi_call_rts Call trace: dump_backtrace (arch/arm64/kernel/stacktrace.c:158) show_stack (arch/arm64/kernel/stacktrace.c:165) dump_stack_lvl (lib/dump_stack.c:107 (discriminator 4)) dump_stack (lib/dump_stack.c:114) __might_resched (kernel/sched/core.c:10134) rt_spin_lock (kernel/locking/rtmutex.c:1769 (discriminator 4)) efi_call_rts (drivers/firmware/efi/runtime-wrappers.c:101) [...] This seems to come from commit ff7a167961d1 ("arm64: efi: Execute runtime services from a dedicated stack") which adds a spinlock. This spinlock is taken through: efi_call_rts() \-efi_call_virt() \-efi_call_virt_pointer() \-arch_efi_call_virt_setup() Make 'efi_rt_lock' a raw_spinlock to avoid being preempted. [ardb: The EFI runtime services are called with a different set of translation tables, and are permitted to use the SIMD registers. The context switch code preserves/restores neither, and so EFI calls must be made with preemption disabled, rather than only disabling migration.] Fixes: ff7a167961d1 ("arm64: efi: Execute runtime services from a dedicated stack") Signed-off-by: Pierre Gondois Cc: # v6.1+ Signed-off-by: Ard Biesheuvel Signed-off-by: Sasha Levin --- arch/arm64/include/asm/efi.h | 6 +++--- arch/arm64/kernel/efi.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 16892f0d05ad..538b6a1b198b 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -25,7 +25,7 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); ({ \ efi_virtmap_load(); \ __efi_fpsimd_begin(); \ - spin_lock(&efi_rt_lock); \ + raw_spin_lock(&efi_rt_lock); \ }) #define arch_efi_call_virt(p, f, args...) \ @@ -37,12 +37,12 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); #define arch_efi_call_virt_teardown() \ ({ \ - spin_unlock(&efi_rt_lock); \ + raw_spin_unlock(&efi_rt_lock); \ __efi_fpsimd_end(); \ efi_virtmap_unload(); \ }) -extern spinlock_t efi_rt_lock; +extern raw_spinlock_t efi_rt_lock; efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...); #define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 72f432d23ec5..3ee3b3daca47 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -144,7 +144,7 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f) return s; } -DEFINE_SPINLOCK(efi_rt_lock); +DEFINE_RAW_SPINLOCK(efi_rt_lock); asmlinkage u64 *efi_rt_stack_top __ro_after_init; From f9fdb3e7b0758516fbc5ae12e3ec23d9060f7035 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Tue, 20 Sep 2022 13:00:37 -0700 Subject: [PATCH 2058/4345] RISC-V: Avoid dereferening NULL regs in die() [ Upstream commit f2913d006fcdb61719635e093d1b5dd0dafecac7 ] I don't think we can actually die() without a regs pointer, but the compiler was warning about a NULL check after a dereference. It seems prudent to just avoid the possibly-NULL dereference, given that when die()ing the system is already toast so who knows how we got there. Reported-by: kernel test robot Reported-by: Dan Carpenter Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220920200037.6727-1-palmer@rivosinc.com Signed-off-by: Palmer Dabbelt Stable-dep-of: 130aee3fd998 ("riscv: Avoid enabling interrupts in die()") Signed-off-by: Sasha Levin --- arch/riscv/kernel/traps.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 23fe03ca7ec7..bc6b30f3add8 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -31,6 +31,7 @@ void die(struct pt_regs *regs, const char *str) { static int die_counter; int ret; + long cause; oops_enter(); @@ -40,11 +41,13 @@ void die(struct pt_regs *regs, const char *str) pr_emerg("%s [#%d]\n", str, ++die_counter); print_modules(); - show_regs(regs); + if (regs) + show_regs(regs); - ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV); + cause = regs ? regs->cause : -1; + ret = notify_die(DIE_OOPS, str, regs, 0, cause, SIGSEGV); - if (regs && kexec_should_crash(current)) + if (kexec_should_crash(current)) crash_kexec(regs); bust_spinlocks(0); From 713c335e5a8f1e65dbe9980ed77d8ae4c0364c34 Mon Sep 17 00:00:00 2001 From: Mattias Nissler Date: Wed, 15 Feb 2023 14:48:28 +0000 Subject: [PATCH 2059/4345] riscv: Avoid enabling interrupts in die() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 130aee3fd9981297ff9354e5d5609cd59aafbbea ] While working on something else, I noticed that the kernel would start accepting interrupts again after crashing in an interrupt handler. Since the kernel is already in inconsistent state, enabling interrupts is dangerous and opens up risk of kernel state deteriorating further. Interrupts do get enabled via what looks like an unintended side effect of spin_unlock_irq, so switch to the more cautious spin_lock_irqsave/spin_unlock_irqrestore instead. Fixes: 76d2a0493a17 ("RISC-V: Init and Halt Code") Signed-off-by: Mattias Nissler Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20230215144828.3370316-1-mnissler@rivosinc.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/kernel/traps.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index bc6b30f3add8..227253fde33c 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -32,10 +32,11 @@ void die(struct pt_regs *regs, const char *str) static int die_counter; int ret; long cause; + unsigned long flags; oops_enter(); - spin_lock_irq(&die_lock); + spin_lock_irqsave(&die_lock, flags); console_verbose(); bust_spinlocks(1); @@ -52,7 +53,7 @@ void die(struct pt_regs *regs, const char *str) bust_spinlocks(0); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irq(&die_lock); + spin_unlock_irqrestore(&die_lock, flags); oops_exit(); if (in_interrupt()) From e993e3ea9550d5b604748ada728386ca25372aae Mon Sep 17 00:00:00 2001 From: Liao Chang Date: Sun, 29 Jan 2023 17:42:42 +0800 Subject: [PATCH 2060/4345] riscv: Add header include guards to insn.h [ Upstream commit 8ac6e619d9d51b3eb5bae817db8aa94e780a0db4 ] Add header include guards to insn.h to prevent repeating declaration of any identifiers in insn.h. Fixes: edde5584c7ab ("riscv: Add SW single-step support for KDB") Signed-off-by: Liao Chang Reviewed-by: Andrew Jones Fixes: c9c1af3f186a ("RISC-V: rename parse_asm.h to insn.h") Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230129094242.282620-1-liaochang1@huawei.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/include/asm/parse_asm.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/riscv/include/asm/parse_asm.h b/arch/riscv/include/asm/parse_asm.h index 7fee806805c1..ad254da85e61 100644 --- a/arch/riscv/include/asm/parse_asm.h +++ b/arch/riscv/include/asm/parse_asm.h @@ -3,6 +3,9 @@ * Copyright (C) 2020 SiFive */ +#ifndef _ASM_RISCV_INSN_H +#define _ASM_RISCV_INSN_H + #include /* The bit field of immediate value in I-type instruction */ @@ -217,3 +220,5 @@ static inline bool is_ ## INSN_NAME ## _insn(long insn) \ (RVC_X(x_, RVC_B_IMM_5_OPOFF, RVC_B_IMM_5_MASK) << RVC_B_IMM_5_OFF) | \ (RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \ (RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); }) + +#endif /* _ASM_RISCV_INSN_H */ From 6b223e32d66ca9db1f252f433514783d8b22a8e1 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 10 Feb 2023 12:52:00 -0800 Subject: [PATCH 2061/4345] scsi: core: Remove the /proc/scsi/${proc_name} directory earlier [ Upstream commit fc663711b94468f4e1427ebe289c9f05669699c9 ] Remove the /proc/scsi/${proc_name} directory earlier to fix a race condition between unloading and reloading kernel modules. This fixes a bug introduced in 2009 by commit 77c019768f06 ("[SCSI] fix /proc memory leak in the SCSI core"). Fix the following kernel warning: proc_dir_entry 'scsi/scsi_debug' already registered WARNING: CPU: 19 PID: 27986 at fs/proc/generic.c:376 proc_register+0x27d/0x2e0 Call Trace: proc_mkdir+0xb5/0xe0 scsi_proc_hostdir_add+0xb5/0x170 scsi_host_alloc+0x683/0x6c0 sdebug_driver_probe+0x6b/0x2d0 [scsi_debug] really_probe+0x159/0x540 __driver_probe_device+0xdc/0x230 driver_probe_device+0x4f/0x120 __device_attach_driver+0xef/0x180 bus_for_each_drv+0xe5/0x130 __device_attach+0x127/0x290 device_initial_probe+0x17/0x20 bus_probe_device+0x110/0x130 device_add+0x673/0xc80 device_register+0x1e/0x30 sdebug_add_host_helper+0x1a7/0x3b0 [scsi_debug] scsi_debug_init+0x64f/0x1000 [scsi_debug] do_one_initcall+0xd7/0x470 do_init_module+0xe7/0x330 load_module+0x122a/0x12c0 __do_sys_finit_module+0x124/0x1a0 __x64_sys_finit_module+0x46/0x50 do_syscall_64+0x38/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Link: https://lore.kernel.org/r/20230210205200.36973-3-bvanassche@acm.org Cc: Alan Stern Cc: Yi Zhang Cc: stable@vger.kernel.org Fixes: 77c019768f06 ("[SCSI] fix /proc memory leak in the SCSI core") Reported-by: Yi Zhang Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hosts.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index d664c4650b2d..fae032324210 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -180,6 +180,7 @@ void scsi_remove_host(struct Scsi_Host *shost) scsi_forget_host(shost); mutex_unlock(&shost->scan_mutex); scsi_proc_host_rm(shost); + scsi_proc_hostdir_rm(shost->hostt); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_DEL)) @@ -321,6 +322,7 @@ static void scsi_host_dev_release(struct device *dev) struct Scsi_Host *shost = dev_to_shost(dev); struct device *parent = dev->parent; + /* In case scsi_remove_host() has not been called. */ scsi_proc_hostdir_rm(shost->hostt); /* Wait for functions invoked through call_rcu(&shost->rcu, ...) */ From 0c440f14558bfacd22c6935ae1fd4b2a09e96b5d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 26 Jan 2023 12:22:21 +0100 Subject: [PATCH 2062/4345] ext4: Fix possible corruption when moving a directory [ Upstream commit 0813299c586b175d7edb25f56412c54b812d0379 ] When we are renaming a directory to a different directory, we need to update '..' entry in the moved directory. However nothing prevents moved directory from being modified and even converted from the inline format to the normal format. When such race happens the rename code gets confused and we crash. Fix the problem by locking the moved directory. CC: stable@vger.kernel.org Fixes: 32f7f22c0b52 ("ext4: let ext4_rename handle inline dir") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230126112221.11866-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/namei.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 6f335d58183e..17590bb76914 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3923,9 +3923,16 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, if (new.dir != old.dir && EXT4_DIR_LINK_MAX(new.dir)) goto end_rename; } + /* + * We need to protect against old.inode directory getting + * converted from inline directory format into a normal one. + */ + inode_lock_nested(old.inode, I_MUTEX_NONDIR2); retval = ext4_rename_dir_prepare(handle, &old); - if (retval) + if (retval) { + inode_unlock(old.inode); goto end_rename; + } } /* * If we're renaming a file within an inline_data dir and adding or @@ -4050,6 +4057,8 @@ end_rename: } else { ext4_journal_stop(handle); } + if (old.dir_bh) + inode_unlock(old.inode); release_bh: brelse(old.dir_bh); brelse(old.bh); From 9ca74e5e75ea29399cbec3102bb195a1d899fa4a Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Wed, 1 Jun 2022 20:46:06 +1000 Subject: [PATCH 2063/4345] drm/nouveau/kms/nv50-: remove unused functions [ Upstream commit 89ed996b888faaf11c69bb4cbc19f21475c9050e ] Signed-off-by: Ben Skeggs Reviewed-by: Dave Airlie Signed-off-by: Dave Airlie Stable-dep-of: 3638a820c5c3 ("drm/nouveau/kms/nv50: fix nv50_wndw_new_ prototype") Signed-off-by: Sasha Levin --- drivers/gpu/drm/nouveau/dispnv50/disp.c | 16 ---------------- drivers/gpu/drm/nouveau/dispnv50/wndw.c | 12 ------------ drivers/gpu/drm/nouveau/dispnv50/wndw.h | 2 -- 3 files changed, 30 deletions(-) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index c2d34c91e840..804ea035fa46 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2555,14 +2555,6 @@ nv50_display_fini(struct drm_device *dev, bool runtime, bool suspend) { struct nouveau_drm *drm = nouveau_drm(dev); struct drm_encoder *encoder; - struct drm_plane *plane; - - drm_for_each_plane(plane, dev) { - struct nv50_wndw *wndw = nv50_wndw(plane); - if (plane->funcs != &nv50_wndw) - continue; - nv50_wndw_fini(wndw); - } list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) @@ -2578,7 +2570,6 @@ nv50_display_init(struct drm_device *dev, bool resume, bool runtime) { struct nv50_core *core = nv50_disp(dev)->core; struct drm_encoder *encoder; - struct drm_plane *plane; if (resume || runtime) core->func->init(core); @@ -2591,13 +2582,6 @@ nv50_display_init(struct drm_device *dev, bool resume, bool runtime) } } - drm_for_each_plane(plane, dev) { - struct nv50_wndw *wndw = nv50_wndw(plane); - if (plane->funcs != &nv50_wndw) - continue; - nv50_wndw_init(wndw); - } - return 0; } diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index f07916ffe42c..831125b4453d 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -690,18 +690,6 @@ nv50_wndw_notify(struct nvif_notify *notify) return NVIF_NOTIFY_KEEP; } -void -nv50_wndw_fini(struct nv50_wndw *wndw) -{ - nvif_notify_put(&wndw->notify); -} - -void -nv50_wndw_init(struct nv50_wndw *wndw) -{ - nvif_notify_get(&wndw->notify); -} - static const u64 nv50_cursor_format_modifiers[] = { DRM_FORMAT_MOD_LINEAR, DRM_FORMAT_MOD_INVALID, diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h index 3278e2880034..8bed195ae098 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.h +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h @@ -40,8 +40,6 @@ int nv50_wndw_new_(const struct nv50_wndw_func *, struct drm_device *, enum drm_plane_type, const char *name, int index, const u32 *format, enum nv50_disp_interlock_type, u32 interlock_data, u32 heads, struct nv50_wndw **); -void nv50_wndw_init(struct nv50_wndw *); -void nv50_wndw_fini(struct nv50_wndw *); void nv50_wndw_flush_set(struct nv50_wndw *, u32 *interlock, struct nv50_wndw_atom *); void nv50_wndw_flush_clr(struct nv50_wndw *, u32 *interlock, bool flush, From 8b4a6dd1571783a3129ea5697bb2f16104d1ee13 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 31 Oct 2022 12:42:29 +0100 Subject: [PATCH 2064/4345] drm/nouveau/kms/nv50: fix nv50_wndw_new_ prototype [ Upstream commit 3638a820c5c3b52f327cebb174fd4274bee08aa7 ] gcc-13 warns about mismatching types for enums. That revealed switched arguments of nv50_wndw_new_(): drivers/gpu/drm/nouveau/dispnv50/wndw.c:696:1: error: conflicting types for 'nv50_wndw_new_' due to enum/integer mismatch; have 'int(const struct nv50_wndw_func *, struct drm_device *, enum drm_plane_type, const char *, int, const u32 *, u32, enum nv50_disp_interlock_type, u32, struct nv50_wndw **)' drivers/gpu/drm/nouveau/dispnv50/wndw.h:36:5: note: previous declaration of 'nv50_wndw_new_' with type 'int(const struct nv50_wndw_func *, struct drm_device *, enum drm_plane_type, const char *, int, const u32 *, enum nv50_disp_interlock_type, u32, u32, struct nv50_wndw **)' It can be barely visible, but the declaration says about the parameters in the middle: enum nv50_disp_interlock_type, u32 interlock_data, u32 heads, While the definition states differently: u32 heads, enum nv50_disp_interlock_type interlock_type, u32 interlock_data, Unify/fix the declaration to match the definition. Fixes: 53e0a3e70de6 ("drm/nouveau/kms/nv50-: simplify tracking of channel interlocks") Cc: Martin Liska Cc: Ben Skeggs Cc: Karol Herbst Cc: Lyude Paul Cc: David Airlie Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Cc: nouveau@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Jiri Slaby (SUSE) Signed-off-by: Karol Herbst Link: https://patchwork.freedesktop.org/patch/msgid/20221031114229.10289-1-jirislaby@kernel.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/nouveau/dispnv50/wndw.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h index 8bed195ae098..77bf124319fb 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.h +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h @@ -38,8 +38,9 @@ struct nv50_wndw { int nv50_wndw_new_(const struct nv50_wndw_func *, struct drm_device *, enum drm_plane_type, const char *name, int index, - const u32 *format, enum nv50_disp_interlock_type, - u32 interlock_data, u32 heads, struct nv50_wndw **); + const u32 *format, u32 heads, + enum nv50_disp_interlock_type, u32 interlock_data, + struct nv50_wndw **); void nv50_wndw_flush_set(struct nv50_wndw *, u32 *interlock, struct nv50_wndw_atom *); void nv50_wndw_flush_clr(struct nv50_wndw *, u32 *interlock, bool flush, From 08c0b54bef78eb74b9e1df32616fc85d5492c66f Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 15 Feb 2023 15:50:48 -0800 Subject: [PATCH 2065/4345] drm/msm: Fix potential invalid ptr free [ Upstream commit 8a86f213f4426f19511a16d886871805b35c3acf ] The error path cleanup expects that chain and syncobj are either NULL or valid pointers. But post_deps was not allocated with __GFP_ZERO. Fixes: ab723b7a992a ("drm/msm: Add syncobj support.") Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Reviewed-by: Dmitry Osipenko Patchwork: https://patchwork.freedesktop.org/patch/523051/ Link: https://lore.kernel.org/r/20230215235048.1166484-1-robdclark@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/msm_gem_submit.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index aa5c60a7132d..c4e5037512b9 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -494,8 +494,8 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, int ret = 0; uint32_t i, j; - post_deps = kmalloc_array(nr_syncobjs, sizeof(*post_deps), - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + post_deps = kcalloc(nr_syncobjs, sizeof(*post_deps), + GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); if (!post_deps) return ERR_PTR(-ENOMEM); @@ -510,7 +510,6 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, } post_deps[i].point = syncobj_desc.point; - post_deps[i].chain = NULL; if (syncobj_desc.flags) { ret = -EINVAL; From 00c2020b8bb8914f08b5df63992a7ea3c87cdb45 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 14 Feb 2023 05:09:53 +0300 Subject: [PATCH 2066/4345] drm/msm/a5xx: fix setting of the CP_PREEMPT_ENABLE_LOCAL register [ Upstream commit a7a4c19c36de1e4b99b06e4060ccc8ab837725bc ] Rather than writing CP_PREEMPT_ENABLE_GLOBAL twice, follow the vendor kernel and set CP_PREEMPT_ENABLE_LOCAL register instead. a5xx_submit() will override it during submission, but let's get the sequence correct. Fixes: b1fc2839d2f9 ("drm/msm: Implement preemption for A5XX targets") Signed-off-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/522638/ Link: https://lore.kernel.org/r/20230214020956.164473-2-dmitry.baryshkov@linaro.org Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 0ca7e53db112..64da65ae6d67 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -144,8 +144,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, 1); /* Enable local preemption for finegrain preemption */ - OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1); - OUT_RING(ring, 0x02); + OUT_PKT7(ring, CP_PREEMPT_ENABLE_LOCAL, 1); + OUT_RING(ring, 0x1); /* Allow CP_CONTEXT_SWITCH_YIELD packets in the IB2 */ OUT_PKT7(ring, CP_YIELD_ENABLE, 1); From 8dde1d9d6f065ea4c03c1d77182ba9e122d516d3 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Fri, 23 Oct 2020 09:51:15 -0700 Subject: [PATCH 2067/4345] drm/msm: Document and rename preempt_lock [ Upstream commit 77c406038e830a4b6219b14a116cd2a6ac9f4908 ] Before adding another lock, give ring->lock a more descriptive name. Signed-off-by: Rob Clark Reviewed-by: Jordan Crouse Reviewed-by: Kristian H. Kristensen Signed-off-by: Rob Clark Stable-dep-of: b4fb748f0b73 ("drm/msm/a5xx: fix the emptyness check in the preempt code") Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 4 ++-- drivers/gpu/drm/msm/adreno/a5xx_preempt.c | 12 ++++++------ drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 4 ++-- drivers/gpu/drm/msm/msm_ringbuffer.c | 2 +- drivers/gpu/drm/msm/msm_ringbuffer.h | 7 ++++++- 5 files changed, 17 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 64da65ae6d67..6f84db97e20e 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -36,7 +36,7 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring, OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring))); } - spin_lock_irqsave(&ring->lock, flags); + spin_lock_irqsave(&ring->preempt_lock, flags); /* Copy the shadow to the actual register */ ring->cur = ring->next; @@ -44,7 +44,7 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring, /* Make sure to wrap wptr if we need to */ wptr = get_wptr(ring); - spin_unlock_irqrestore(&ring->lock, flags); + spin_unlock_irqrestore(&ring->preempt_lock, flags); /* Make sure everything is posted before making a decision */ mb(); diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 7e04509c4e1f..183de1139eeb 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -45,9 +45,9 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) if (!ring) return; - spin_lock_irqsave(&ring->lock, flags); + spin_lock_irqsave(&ring->preempt_lock, flags); wptr = get_wptr(ring); - spin_unlock_irqrestore(&ring->lock, flags); + spin_unlock_irqrestore(&ring->preempt_lock, flags); gpu_write(gpu, REG_A5XX_CP_RB_WPTR, wptr); } @@ -62,9 +62,9 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) bool empty; struct msm_ringbuffer *ring = gpu->rb[i]; - spin_lock_irqsave(&ring->lock, flags); + spin_lock_irqsave(&ring->preempt_lock, flags); empty = (get_wptr(ring) == ring->memptrs->rptr); - spin_unlock_irqrestore(&ring->lock, flags); + spin_unlock_irqrestore(&ring->preempt_lock, flags); if (!empty) return ring; @@ -132,9 +132,9 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) } /* Make sure the wptr doesn't update while we're in motion */ - spin_lock_irqsave(&ring->lock, flags); + spin_lock_irqsave(&ring->preempt_lock, flags); a5xx_gpu->preempt[ring->id]->wptr = get_wptr(ring); - spin_unlock_irqrestore(&ring->lock, flags); + spin_unlock_irqrestore(&ring->preempt_lock, flags); /* Set the address of the incoming preemption record */ gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_LO, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index dffc133b8b1c..29b40acedb38 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -65,7 +65,7 @@ static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) OUT_RING(ring, upper_32_bits(shadowptr(a6xx_gpu, ring))); } - spin_lock_irqsave(&ring->lock, flags); + spin_lock_irqsave(&ring->preempt_lock, flags); /* Copy the shadow to the actual register */ ring->cur = ring->next; @@ -73,7 +73,7 @@ static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) /* Make sure to wrap wptr if we need to */ wptr = get_wptr(ring); - spin_unlock_irqrestore(&ring->lock, flags); + spin_unlock_irqrestore(&ring->preempt_lock, flags); /* Make sure everything is posted before making a decision */ mb(); diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 935bf9b1d941..1b6958e908dc 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -46,7 +46,7 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, ring->memptrs_iova = memptrs_iova; INIT_LIST_HEAD(&ring->submits); - spin_lock_init(&ring->lock); + spin_lock_init(&ring->preempt_lock); snprintf(name, sizeof(name), "gpu-ring-%d", ring->id); diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h index 0987d6bf848c..4956d1bc5d0e 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.h +++ b/drivers/gpu/drm/msm/msm_ringbuffer.h @@ -46,7 +46,12 @@ struct msm_ringbuffer { struct msm_rbmemptrs *memptrs; uint64_t memptrs_iova; struct msm_fence_context *fctx; - spinlock_t lock; + + /* + * preempt_lock protects preemption and serializes wptr updates against + * preemption. Can be aquired from irq context. + */ + spinlock_t preempt_lock; }; struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, From 34e71ca0a0068f9d7e12c59dc997ae5725fa181f Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 14 Feb 2023 05:09:55 +0300 Subject: [PATCH 2068/4345] drm/msm/a5xx: fix the emptyness check in the preempt code [ Upstream commit b4fb748f0b734ce1d2e7834998cc599fcbd25d67 ] Quoting Yassine: ring->memptrs->rptr is never updated and stays 0, so the comparison always evaluates to false and get_next_ring always returns ring 0 thinking it isn't empty. Fix this by calling get_rptr() instead of reading rptr directly. Reported-by: Yassine Oudjana Fixes: b1fc2839d2f9 ("drm/msm: Implement preemption for A5XX targets") Signed-off-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/522642/ Link: https://lore.kernel.org/r/20230214020956.164473-4-dmitry.baryshkov@linaro.org Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/a5xx_preempt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 183de1139eeb..9da0aff0072d 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -63,7 +63,7 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) struct msm_ringbuffer *ring = gpu->rb[i]; spin_lock_irqsave(&ring->preempt_lock, flags); - empty = (get_wptr(ring) == ring->memptrs->rptr); + empty = (get_wptr(ring) == gpu->funcs->get_rptr(gpu, ring)); spin_unlock_irqrestore(&ring->preempt_lock, flags); if (!empty) From 4c43a0291f878bf194061b34e367f521f7066e25 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 14 Feb 2023 05:09:56 +0300 Subject: [PATCH 2069/4345] drm/msm/a5xx: fix context faults during ring switch [ Upstream commit 32e7083429d46f29080626fe387ff90c086b1fbe ] The rptr_addr is set in the preempt_init_ring(), which is called from a5xx_gpu_init(). It uses shadowptr() to set the address, however the shadow_iova is not yet initialized at that time. Move the rptr_addr setting to the a5xx_preempt_hw_init() which is called after setting the shadow_iova, getting the correct value for the address. Fixes: 8907afb476ac ("drm/msm: Allow a5xx to mark the RPTR shadow as privileged") Suggested-by: Rob Clark Signed-off-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/522640/ Link: https://lore.kernel.org/r/20230214020956.164473-5-dmitry.baryshkov@linaro.org Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/a5xx_preempt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 9da0aff0072d..b8e71ad6f8d8 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -210,6 +210,7 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu) a5xx_gpu->preempt[i]->wptr = 0; a5xx_gpu->preempt[i]->rptr = 0; a5xx_gpu->preempt[i]->rbase = gpu->rb[i]->iova; + a5xx_gpu->preempt[i]->rptr_addr = shadowptr(a5xx_gpu, gpu->rb[i]); } /* Write a 0 to signal that we aren't switching pagetables */ @@ -261,7 +262,6 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, ptr->data = 0; ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE; - ptr->rptr_addr = shadowptr(a5xx_gpu, ring); ptr->counter = counters_iova; return 0; From cbf11ff3708ff163387da924f80a47ce7c721e9b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Mon, 27 Feb 2023 10:11:56 +0100 Subject: [PATCH 2070/4345] bgmac: fix *initial* chip reset to support BCM5358 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f99e6d7c4ed3be2531bd576425a5bd07fb133bd7 ] While bringing hardware up we should perform a full reset including the switch bit (BGMAC_BCMA_IOCTL_SW_RESET aka SICF_SWRST). It's what specification says and what reference driver does. This seems to be critical for the BCM5358. Without this hardware doesn't get initialized properly and doesn't seem to transmit or receive any packets. Originally bgmac was calling bgmac_chip_reset() before setting "has_robosw" property which resulted in expected behaviour. That has changed as a side effect of adding platform device support which regressed BCM5358 support. Fixes: f6a95a24957a ("net: ethernet: bgmac: Add platform device support") Cc: Jon Mason Signed-off-by: Rafał Miłecki Reviewed-by: Leon Romanovsky Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20230227091156.19509-1-zajec5@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bgmac.c | 8 ++++++-- drivers/net/ethernet/broadcom/bgmac.h | 2 ++ 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 9960127f612e..bb999e67d773 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -890,13 +890,13 @@ static void bgmac_chip_reset_idm_config(struct bgmac *bgmac) if (iost & BGMAC_BCMA_IOST_ATTACHED) { flags = BGMAC_BCMA_IOCTL_SW_CLKEN; - if (!bgmac->has_robosw) + if (bgmac->in_init || !bgmac->has_robosw) flags |= BGMAC_BCMA_IOCTL_SW_RESET; } bgmac_clk_enable(bgmac, flags); } - if (iost & BGMAC_BCMA_IOST_ATTACHED && !bgmac->has_robosw) + if (iost & BGMAC_BCMA_IOST_ATTACHED && (bgmac->in_init || !bgmac->has_robosw)) bgmac_idm_write(bgmac, BCMA_IOCTL, bgmac_idm_read(bgmac, BCMA_IOCTL) & ~BGMAC_BCMA_IOCTL_SW_RESET); @@ -1490,6 +1490,8 @@ int bgmac_enet_probe(struct bgmac *bgmac) struct net_device *net_dev = bgmac->net_dev; int err; + bgmac->in_init = true; + bgmac_chip_intrs_off(bgmac); net_dev->irq = bgmac->irq; @@ -1542,6 +1544,8 @@ int bgmac_enet_probe(struct bgmac *bgmac) /* Omit FCS from max MTU size */ net_dev->max_mtu = BGMAC_RX_MAX_FRAME_SIZE - ETH_FCS_LEN; + bgmac->in_init = false; + err = register_netdev(bgmac->net_dev); if (err) { dev_err(bgmac->dev, "Cannot register net device\n"); diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index 351c598a3ec6..d1200b27af1e 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -512,6 +512,8 @@ struct bgmac { int irq; u32 int_mask; + bool in_init; + /* Current MAC state */ int mac_speed; int mac_duplex; From 80be62358fa5507cefbaa067c7e6648401f2c3da Mon Sep 17 00:00:00 2001 From: Kang Chen Date: Mon, 27 Feb 2023 17:30:37 +0800 Subject: [PATCH 2071/4345] nfc: fdp: add null check of devm_kmalloc_array in fdp_nci_i2c_read_device_properties [ Upstream commit 11f180a5d62a51b484e9648f9b310e1bd50b1a57 ] devm_kmalloc_array may fails, *fw_vsc_cfg might be null and cause out-of-bounds write in device_property_read_u8_array later. Fixes: a06347c04c13 ("NFC: Add Intel Fields Peak NFC solution driver") Signed-off-by: Kang Chen Reviewed-by: Krzysztof Kozlowski Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230227093037.907654-1-void0red@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/nfc/fdp/i2c.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 5e300788be52..808d73050afd 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -249,6 +249,9 @@ static void fdp_nci_i2c_read_device_properties(struct device *dev, len, sizeof(**fw_vsc_cfg), GFP_KERNEL); + if (!*fw_vsc_cfg) + goto alloc_err; + r = device_property_read_u8_array(dev, FDP_DP_FW_VSC_CFG_NAME, *fw_vsc_cfg, len); @@ -262,6 +265,7 @@ vsc_read_err: *fw_vsc_cfg = NULL; } +alloc_err: dev_dbg(dev, "Clock type: %d, clock frequency: %d, VSC: %s", *clock_type, *clock_freq, *fw_vsc_cfg != NULL ? "yes" : "no"); } From 6f0cc879c889596c7ea0cddc86ca19fcf540a1c4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 24 Feb 2023 17:59:39 +0200 Subject: [PATCH 2072/4345] powerpc: dts: t1040rdb: fix compatible string for Rev A boards [ Upstream commit ae44f1c9d1fc54aeceb335fedb1e73b2c3ee4561 ] It looks like U-Boot fails to start the kernel properly when the compatible string of the board isn't fsl,T1040RDB, so stop overriding it from the rev-a.dts. Fixes: 5ebb74749202 ("powerpc: dts: t1040rdb: fix ports names for Seville Ethernet switch") Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts index 73f8c998c64d..d4f5f159d6f2 100644 --- a/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts +++ b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts @@ -10,7 +10,6 @@ / { model = "fsl,T1040RDB-REV-A"; - compatible = "fsl,T1040RDB-REV-A"; }; &seville_port0 { From 42d9ed4e5dc5f87fbd67c232e2e4a9b88ceeb47f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 27 Feb 2023 15:30:24 +0000 Subject: [PATCH 2073/4345] ila: do not generate empty messages in ila_xlat_nl_cmd_get_mapping() [ Upstream commit 693aa2c0d9b6d5b1f2745d31b6e70d09dbbaf06e ] ila_xlat_nl_cmd_get_mapping() generates an empty skb, triggerring a recent sanity check [1]. Instead, return an error code, so that user space can get it. [1] skb_assert_len WARNING: CPU: 0 PID: 5923 at include/linux/skbuff.h:2527 skb_assert_len include/linux/skbuff.h:2527 [inline] WARNING: CPU: 0 PID: 5923 at include/linux/skbuff.h:2527 __dev_queue_xmit+0x1bc0/0x3488 net/core/dev.c:4156 Modules linked in: CPU: 0 PID: 5923 Comm: syz-executor269 Not tainted 6.2.0-syzkaller-18300-g2ebd1fbb946d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/21/2023 pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : skb_assert_len include/linux/skbuff.h:2527 [inline] pc : __dev_queue_xmit+0x1bc0/0x3488 net/core/dev.c:4156 lr : skb_assert_len include/linux/skbuff.h:2527 [inline] lr : __dev_queue_xmit+0x1bc0/0x3488 net/core/dev.c:4156 sp : ffff80001e0d6c40 x29: ffff80001e0d6e60 x28: dfff800000000000 x27: ffff0000c86328c0 x26: dfff800000000000 x25: ffff0000c8632990 x24: ffff0000c8632a00 x23: 0000000000000000 x22: 1fffe000190c6542 x21: ffff0000c8632a10 x20: ffff0000c8632a00 x19: ffff80001856e000 x18: ffff80001e0d5fc0 x17: 0000000000000000 x16: ffff80001235d16c x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000001 x12: 0000000000000001 x11: ff80800008353a30 x10: 0000000000000000 x9 : 21567eaf25bfb600 x8 : 21567eaf25bfb600 x7 : 0000000000000001 x6 : 0000000000000001 x5 : ffff80001e0d6558 x4 : ffff800015c74760 x3 : ffff800008596744 x2 : 0000000000000001 x1 : 0000000100000000 x0 : 000000000000000e Call trace: skb_assert_len include/linux/skbuff.h:2527 [inline] __dev_queue_xmit+0x1bc0/0x3488 net/core/dev.c:4156 dev_queue_xmit include/linux/netdevice.h:3033 [inline] __netlink_deliver_tap_skb net/netlink/af_netlink.c:307 [inline] __netlink_deliver_tap+0x45c/0x6f8 net/netlink/af_netlink.c:325 netlink_deliver_tap+0xf4/0x174 net/netlink/af_netlink.c:338 __netlink_sendskb net/netlink/af_netlink.c:1283 [inline] netlink_sendskb+0x6c/0x154 net/netlink/af_netlink.c:1292 netlink_unicast+0x334/0x8d4 net/netlink/af_netlink.c:1380 nlmsg_unicast include/net/netlink.h:1099 [inline] genlmsg_unicast include/net/genetlink.h:433 [inline] genlmsg_reply include/net/genetlink.h:443 [inline] ila_xlat_nl_cmd_get_mapping+0x620/0x7d0 net/ipv6/ila/ila_xlat.c:493 genl_family_rcv_msg_doit net/netlink/genetlink.c:968 [inline] genl_family_rcv_msg net/netlink/genetlink.c:1048 [inline] genl_rcv_msg+0x938/0xc1c net/netlink/genetlink.c:1065 netlink_rcv_skb+0x214/0x3c4 net/netlink/af_netlink.c:2574 genl_rcv+0x38/0x50 net/netlink/genetlink.c:1076 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x660/0x8d4 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x800/0xae0 net/netlink/af_netlink.c:1942 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0x558/0x844 net/socket.c:2479 ___sys_sendmsg net/socket.c:2533 [inline] __sys_sendmsg+0x26c/0x33c net/socket.c:2562 __do_sys_sendmsg net/socket.c:2571 [inline] __se_sys_sendmsg net/socket.c:2569 [inline] __arm64_sys_sendmsg+0x80/0x94 net/socket.c:2569 __invoke_syscall arch/arm64/kernel/syscall.c:38 [inline] invoke_syscall+0x98/0x2c0 arch/arm64/kernel/syscall.c:52 el0_svc_common+0x138/0x258 arch/arm64/kernel/syscall.c:142 do_el0_svc+0x64/0x198 arch/arm64/kernel/syscall.c:193 el0_svc+0x58/0x168 arch/arm64/kernel/entry-common.c:637 el0t_64_sync_handler+0x84/0xf0 arch/arm64/kernel/entry-common.c:655 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:591 irq event stamp: 136484 hardirqs last enabled at (136483): [] __up_console_sem+0x60/0xb4 kernel/printk/printk.c:345 hardirqs last disabled at (136484): [] el1_dbg+0x24/0x80 arch/arm64/kernel/entry-common.c:405 softirqs last enabled at (136418): [] softirq_handle_end kernel/softirq.c:414 [inline] softirqs last enabled at (136418): [] __do_softirq+0xd4c/0xfa4 kernel/softirq.c:600 softirqs last disabled at (136371): [] ____do_softirq+0x14/0x20 arch/arm64/kernel/irq.c:80 ---[ end trace 0000000000000000 ]--- skb len=0 headroom=0 headlen=0 tailroom=192 mac=(0,0) net=(0,-1) trans=-1 shinfo(txflags=0 nr_frags=0 gso(size=0 type=0 segs=0)) csum(0x0 ip_summed=0 complete_sw=0 valid=0 level=0) hash(0x0 sw=0 l4=0) proto=0x0010 pkttype=6 iif=0 dev name=nlmon0 feat=0x0000000000005861 Fixes: 7f00feaf1076 ("ila: Add generic ILA translation facility") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/ila/ila_xlat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index a1ac0e3d8c60..163668531a57 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -477,6 +477,7 @@ int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info) rcu_read_lock(); + ret = -ESRCH; ila = ila_lookup_by_params(&xp, ilan); if (ila) { ret = ila_dump_info(ila, From 374cbffe7d6fd93ee22db7783a0205a0f7d5dccf Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 27 Feb 2023 17:36:46 +0800 Subject: [PATCH 2074/4345] selftests: nft_nat: ensuring the listening side is up before starting the client [ Upstream commit 2067e7a00aa604b94de31d64f29b8893b1696f26 ] The test_local_dnat_portonly() function initiates the client-side as soon as it sets the listening side to the background. This could lead to a race condition where the server may not be ready to listen. To ensure that the server-side is up and running before initiating the client-side, a delay is introduced to the test_local_dnat_portonly() function. Before the fix: # ./nft_nat.sh PASS: netns routing/connectivity: ns0-rthlYrBU can reach ns1-rthlYrBU and ns2-rthlYrBU PASS: ping to ns1-rthlYrBU was ip NATted to ns2-rthlYrBU PASS: ping to ns1-rthlYrBU OK after ip nat output chain flush PASS: ipv6 ping to ns1-rthlYrBU was ip6 NATted to ns2-rthlYrBU 2023/02/27 04:11:03 socat[6055] E connect(5, AF=2 10.0.1.99:2000, 16): Connection refused ERROR: inet port rewrite After the fix: # ./nft_nat.sh PASS: netns routing/connectivity: ns0-9sPJV6JJ can reach ns1-9sPJV6JJ and ns2-9sPJV6JJ PASS: ping to ns1-9sPJV6JJ was ip NATted to ns2-9sPJV6JJ PASS: ping to ns1-9sPJV6JJ OK after ip nat output chain flush PASS: ipv6 ping to ns1-9sPJV6JJ was ip6 NATted to ns2-9sPJV6JJ PASS: inet port rewrite without l3 address Fixes: 282e5f8fe907 ("netfilter: nat: really support inet nat without l3 address") Signed-off-by: Hangbin Liu Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- tools/testing/selftests/netfilter/nft_nat.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 4e15e8167310..67697d8ea59a 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -404,6 +404,8 @@ EOF echo SERVER-$family | ip netns exec "$ns1" timeout 5 socat -u STDIN TCP-LISTEN:2000 & sc_s=$! + sleep 1 + result=$(ip netns exec "$ns0" timeout 1 socat TCP:$daddr:2000 STDOUT) if [ "$result" = "SERVER-inet" ];then From d5e8f7edc2ac6b2fddeeaadf4930dea4c65da03d Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 2 Nov 2020 11:45:06 +0000 Subject: [PATCH 2075/4345] net: usb: lan78xx: Remove lots of set but unused 'ret' variables MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 06cd7c46b3ab3f2252c61bf85b191236cf0254e1 ] Fixes the following W=1 kernel build warning(s): drivers/net/usb/lan78xx.c: In function ‘lan78xx_read_raw_otp’: drivers/net/usb/lan78xx.c:825:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_write_raw_otp’: drivers/net/usb/lan78xx.c:879:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_deferred_multicast_write’: drivers/net/usb/lan78xx.c:1041:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_update_flowcontrol’: drivers/net/usb/lan78xx.c:1127:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_init_mac_address’: drivers/net/usb/lan78xx.c:1666:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_link_status_change’: drivers/net/usb/lan78xx.c:1841:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_irq_bus_sync_unlock’: drivers/net/usb/lan78xx.c:1920:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan8835_fixup’: drivers/net/usb/lan78xx.c:1994:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_set_rx_max_frame_length’: drivers/net/usb/lan78xx.c:2192:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_change_mtu’: drivers/net/usb/lan78xx.c:2270:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_set_mac_addr’: drivers/net/usb/lan78xx.c:2299:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_set_features’: drivers/net/usb/lan78xx.c:2333:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] drivers/net/usb/lan78xx.c: In function ‘lan78xx_set_suspend’: drivers/net/usb/lan78xx.c:3807:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20201102114512.1062724-25-lee.jones@linaro.org Signed-off-by: Jakub Kicinski Stable-dep-of: e57cf3639c32 ("net: lan78xx: fix accessing the LAN7800's internal phy specific registers from the MAC driver") Signed-off-by: Sasha Levin --- drivers/net/usb/lan78xx.c | 168 ++++++++++++++++++-------------------- 1 file changed, 78 insertions(+), 90 deletions(-) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 6f7b70522d92..0b5b4f9c7c5b 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -824,20 +824,19 @@ static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { int i; - int ret; u32 buf; unsigned long timeout; - ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (buf & OTP_PWR_DN_PWRDN_N_) { /* clear it and wait to be cleared */ - ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0); + lan78xx_write_reg(dev, OTP_PWR_DN, 0); timeout = jiffies + HZ; do { usleep_range(1, 10); - ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_PWR_DN"); @@ -847,18 +846,18 @@ static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, } for (i = 0; i < length; i++) { - ret = lan78xx_write_reg(dev, OTP_ADDR1, + lan78xx_write_reg(dev, OTP_ADDR1, ((offset + i) >> 8) & OTP_ADDR1_15_11); - ret = lan78xx_write_reg(dev, OTP_ADDR2, + lan78xx_write_reg(dev, OTP_ADDR2, ((offset + i) & OTP_ADDR2_10_3)); - ret = lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_); - ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); + lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_); + lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); timeout = jiffies + HZ; do { udelay(1); - ret = lan78xx_read_reg(dev, OTP_STATUS, &buf); + lan78xx_read_reg(dev, OTP_STATUS, &buf); if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_STATUS"); @@ -866,7 +865,7 @@ static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, } } while (buf & OTP_STATUS_BUSY_); - ret = lan78xx_read_reg(dev, OTP_RD_DATA, &buf); + lan78xx_read_reg(dev, OTP_RD_DATA, &buf); data[i] = (u8)(buf & 0xFF); } @@ -878,20 +877,19 @@ static int lan78xx_write_raw_otp(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { int i; - int ret; u32 buf; unsigned long timeout; - ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (buf & OTP_PWR_DN_PWRDN_N_) { /* clear it and wait to be cleared */ - ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0); + lan78xx_write_reg(dev, OTP_PWR_DN, 0); timeout = jiffies + HZ; do { udelay(1); - ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_PWR_DN completion"); @@ -901,21 +899,21 @@ static int lan78xx_write_raw_otp(struct lan78xx_net *dev, u32 offset, } /* set to BYTE program mode */ - ret = lan78xx_write_reg(dev, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_); + lan78xx_write_reg(dev, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_); for (i = 0; i < length; i++) { - ret = lan78xx_write_reg(dev, OTP_ADDR1, + lan78xx_write_reg(dev, OTP_ADDR1, ((offset + i) >> 8) & OTP_ADDR1_15_11); - ret = lan78xx_write_reg(dev, OTP_ADDR2, + lan78xx_write_reg(dev, OTP_ADDR2, ((offset + i) & OTP_ADDR2_10_3)); - ret = lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]); - ret = lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_); - ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); + lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]); + lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_); + lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); timeout = jiffies + HZ; do { udelay(1); - ret = lan78xx_read_reg(dev, OTP_STATUS, &buf); + lan78xx_read_reg(dev, OTP_STATUS, &buf); if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "Timeout on OTP_STATUS completion"); @@ -1040,7 +1038,6 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param) container_of(param, struct lan78xx_priv, set_multicast); struct lan78xx_net *dev = pdata->dev; int i; - int ret; netif_dbg(dev, drv, dev->net, "deferred multicast write 0x%08x\n", pdata->rfe_ctl); @@ -1049,14 +1046,14 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param) DP_SEL_VHF_HASH_LEN, pdata->mchash_table); for (i = 1; i < NUM_OF_MAF; i++) { - ret = lan78xx_write_reg(dev, MAF_HI(i), 0); - ret = lan78xx_write_reg(dev, MAF_LO(i), + lan78xx_write_reg(dev, MAF_HI(i), 0); + lan78xx_write_reg(dev, MAF_LO(i), pdata->pfilter_table[i][1]); - ret = lan78xx_write_reg(dev, MAF_HI(i), + lan78xx_write_reg(dev, MAF_HI(i), pdata->pfilter_table[i][0]); } - ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); + lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); } static void lan78xx_set_multicast(struct net_device *netdev) @@ -1126,7 +1123,6 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex, u16 lcladv, u16 rmtadv) { u32 flow = 0, fct_flow = 0; - int ret; u8 cap; if (dev->fc_autoneg) @@ -1149,10 +1145,10 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex, (cap & FLOW_CTRL_RX ? "enabled" : "disabled"), (cap & FLOW_CTRL_TX ? "enabled" : "disabled")); - ret = lan78xx_write_reg(dev, FCT_FLOW, fct_flow); + lan78xx_write_reg(dev, FCT_FLOW, fct_flow); /* threshold value should be set before enabling flow */ - ret = lan78xx_write_reg(dev, FLOW, flow); + lan78xx_write_reg(dev, FLOW, flow); return 0; } @@ -1673,11 +1669,10 @@ static const struct ethtool_ops lan78xx_ethtool_ops = { static void lan78xx_init_mac_address(struct lan78xx_net *dev) { u32 addr_lo, addr_hi; - int ret; u8 addr[6]; - ret = lan78xx_read_reg(dev, RX_ADDRL, &addr_lo); - ret = lan78xx_read_reg(dev, RX_ADDRH, &addr_hi); + lan78xx_read_reg(dev, RX_ADDRL, &addr_lo); + lan78xx_read_reg(dev, RX_ADDRH, &addr_hi); addr[0] = addr_lo & 0xFF; addr[1] = (addr_lo >> 8) & 0xFF; @@ -1710,12 +1705,12 @@ static void lan78xx_init_mac_address(struct lan78xx_net *dev) (addr[2] << 16) | (addr[3] << 24); addr_hi = addr[4] | (addr[5] << 8); - ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); - ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + lan78xx_write_reg(dev, RX_ADDRL, addr_lo); + lan78xx_write_reg(dev, RX_ADDRH, addr_hi); } - ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); - ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); + lan78xx_write_reg(dev, MAF_LO(0), addr_lo); + lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); ether_addr_copy(dev->net->dev_addr, addr); } @@ -1848,7 +1843,7 @@ static void lan78xx_remove_mdio(struct lan78xx_net *dev) static void lan78xx_link_status_change(struct net_device *net) { struct phy_device *phydev = net->phydev; - int ret, temp; + int temp; /* At forced 100 F/H mode, chip may fail to set mode correctly * when cable is switched between long(~50+m) and short one. @@ -1859,7 +1854,7 @@ static void lan78xx_link_status_change(struct net_device *net) /* disable phy interrupt */ temp = phy_read(phydev, LAN88XX_INT_MASK); temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_; - ret = phy_write(phydev, LAN88XX_INT_MASK, temp); + phy_write(phydev, LAN88XX_INT_MASK, temp); temp = phy_read(phydev, MII_BMCR); temp &= ~(BMCR_SPEED100 | BMCR_SPEED1000); @@ -1873,7 +1868,7 @@ static void lan78xx_link_status_change(struct net_device *net) /* enable phy interrupt back */ temp = phy_read(phydev, LAN88XX_INT_MASK); temp |= LAN88XX_INT_MASK_MDINTPIN_EN_; - ret = phy_write(phydev, LAN88XX_INT_MASK, temp); + phy_write(phydev, LAN88XX_INT_MASK, temp); } } @@ -1927,14 +1922,13 @@ static void lan78xx_irq_bus_sync_unlock(struct irq_data *irqd) struct lan78xx_net *dev = container_of(data, struct lan78xx_net, domain_data); u32 buf; - int ret; /* call register access here because irq_bus_lock & irq_bus_sync_unlock * are only two callbacks executed in non-atomic contex. */ - ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf); + lan78xx_read_reg(dev, INT_EP_CTL, &buf); if (buf != data->irqenable) - ret = lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable); + lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable); mutex_unlock(&data->irq_lock); } @@ -2001,7 +1995,6 @@ static void lan78xx_remove_irq_domain(struct lan78xx_net *dev) static int lan8835_fixup(struct phy_device *phydev) { int buf; - int ret; struct lan78xx_net *dev = netdev_priv(phydev->attached_dev); /* LED2/PME_N/IRQ_N/RGMII_ID pin to IRQ_N mode */ @@ -2011,11 +2004,11 @@ static int lan8835_fixup(struct phy_device *phydev) phy_write_mmd(phydev, MDIO_MMD_PCS, 0x8010, buf); /* RGMII MAC TXC Delay Enable */ - ret = lan78xx_write_reg(dev, MAC_RGMII_ID, + lan78xx_write_reg(dev, MAC_RGMII_ID, MAC_RGMII_ID_TXC_DELAY_EN_); /* RGMII TX DLL Tune Adjust */ - ret = lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00); + lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00); dev->interface = PHY_INTERFACE_MODE_RGMII_TXID; @@ -2199,28 +2192,27 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) static int lan78xx_set_rx_max_frame_length(struct lan78xx_net *dev, int size) { - int ret = 0; u32 buf; bool rxenabled; - ret = lan78xx_read_reg(dev, MAC_RX, &buf); + lan78xx_read_reg(dev, MAC_RX, &buf); rxenabled = ((buf & MAC_RX_RXEN_) != 0); if (rxenabled) { buf &= ~MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); } /* add 4 to size for FCS */ buf &= ~MAC_RX_MAX_SIZE_MASK_; buf |= (((size + 4) << MAC_RX_MAX_SIZE_SHIFT_) & MAC_RX_MAX_SIZE_MASK_); - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); if (rxenabled) { buf |= MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); } return 0; @@ -2277,13 +2269,12 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) int ll_mtu = new_mtu + netdev->hard_header_len; int old_hard_mtu = dev->hard_mtu; int old_rx_urb_size = dev->rx_urb_size; - int ret; /* no second zero-length packet read wanted after mtu-sized packets */ if ((ll_mtu % dev->maxpacket) == 0) return -EDOM; - ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN); + lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN); netdev->mtu = new_mtu; @@ -2306,7 +2297,6 @@ static int lan78xx_set_mac_addr(struct net_device *netdev, void *p) struct lan78xx_net *dev = netdev_priv(netdev); struct sockaddr *addr = p; u32 addr_lo, addr_hi; - int ret; if (netif_running(netdev)) return -EBUSY; @@ -2323,12 +2313,12 @@ static int lan78xx_set_mac_addr(struct net_device *netdev, void *p) addr_hi = netdev->dev_addr[4] | netdev->dev_addr[5] << 8; - ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); - ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + lan78xx_write_reg(dev, RX_ADDRL, addr_lo); + lan78xx_write_reg(dev, RX_ADDRH, addr_hi); /* Added to support MAC address changes */ - ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); - ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); + lan78xx_write_reg(dev, MAF_LO(0), addr_lo); + lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); return 0; } @@ -2340,7 +2330,6 @@ static int lan78xx_set_features(struct net_device *netdev, struct lan78xx_net *dev = netdev_priv(netdev); struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); unsigned long flags; - int ret; spin_lock_irqsave(&pdata->rfe_ctl_lock, flags); @@ -2364,7 +2353,7 @@ static int lan78xx_set_features(struct net_device *netdev, spin_unlock_irqrestore(&pdata->rfe_ctl_lock, flags); - ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); + lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); return 0; } @@ -3820,7 +3809,6 @@ static u16 lan78xx_wakeframe_crc16(const u8 *buf, int len) static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) { u32 buf; - int ret; int mask_index; u16 crc; u32 temp_wucsr; @@ -3829,26 +3817,26 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) const u8 ipv6_multicast[3] = { 0x33, 0x33 }; const u8 arp_type[2] = { 0x08, 0x06 }; - ret = lan78xx_read_reg(dev, MAC_TX, &buf); + lan78xx_read_reg(dev, MAC_TX, &buf); buf &= ~MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); + lan78xx_write_reg(dev, MAC_TX, buf); + lan78xx_read_reg(dev, MAC_RX, &buf); buf &= ~MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); - ret = lan78xx_write_reg(dev, WUCSR, 0); - ret = lan78xx_write_reg(dev, WUCSR2, 0); - ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + lan78xx_write_reg(dev, WUCSR, 0); + lan78xx_write_reg(dev, WUCSR2, 0); + lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); temp_wucsr = 0; temp_pmt_ctl = 0; - ret = lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl); + lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl); temp_pmt_ctl &= ~PMT_CTL_RES_CLR_WKP_EN_; temp_pmt_ctl |= PMT_CTL_RES_CLR_WKP_STS_; for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++) - ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), 0); + lan78xx_write_reg(dev, WUF_CFG(mask_index), 0); mask_index = 0; if (wol & WAKE_PHY) { @@ -3877,30 +3865,30 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) /* set WUF_CFG & WUF_MASK for IPv4 Multicast */ crc = lan78xx_wakeframe_crc16(ipv4_multicast, 3); - ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), + lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); - ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7); - ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7); + lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; /* for IPv6 Multicast */ crc = lan78xx_wakeframe_crc16(ipv6_multicast, 2); - ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), + lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); - ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3); - ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3); + lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; @@ -3921,16 +3909,16 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) * for packettype (offset 12,13) = ARP (0x0806) */ crc = lan78xx_wakeframe_crc16(arp_type, 2); - ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), + lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_ALL_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); - ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000); - ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000); + lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; @@ -3938,7 +3926,7 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } - ret = lan78xx_write_reg(dev, WUCSR, temp_wucsr); + lan78xx_write_reg(dev, WUCSR, temp_wucsr); /* when multiple WOL bits are set */ if (hweight_long((unsigned long)wol) > 1) { @@ -3946,16 +3934,16 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } - ret = lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl); + lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl); /* clear WUPS */ - ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + lan78xx_read_reg(dev, PMT_CTL, &buf); buf |= PMT_CTL_WUPS_MASK_; - ret = lan78xx_write_reg(dev, PMT_CTL, buf); + lan78xx_write_reg(dev, PMT_CTL, buf); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); + lan78xx_read_reg(dev, MAC_RX, &buf); buf |= MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); return 0; } From db16d6567402754300059b99f137844ca3fe532a Mon Sep 17 00:00:00 2001 From: Yuiko Oshino Date: Wed, 1 Mar 2023 08:43:07 -0700 Subject: [PATCH 2076/4345] net: lan78xx: fix accessing the LAN7800's internal phy specific registers from the MAC driver [ Upstream commit e57cf3639c323eeed05d3725fd82f91b349adca8 ] Move the LAN7800 internal phy (phy ID 0x0007c132) specific register accesses to the phy driver (microchip.c). Fix the error reported by Enguerrand de Ribaucourt in December 2022, "Some operations during the cable switch workaround modify the register LAN88XX_INT_MASK of the PHY. However, this register is specific to the LAN8835 PHY. For instance, if a DP8322I PHY is connected to the LAN7801, that register (0x19), corresponds to the LED and MAC address configuration, resulting in unapropriate behavior." I did not test with the DP8322I PHY, but I tested with an EVB-LAN7800 with the internal PHY. Fixes: 14437e3fa284 ("lan78xx: workaround of forced 100 Full/Half duplex mode error") Signed-off-by: Yuiko Oshino Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230301154307.30438-1-yuiko.oshino@microchip.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/microchip.c | 32 ++++++++++++++++++++++++++++++++ drivers/net/usb/lan78xx.c | 27 +-------------------------- 2 files changed, 33 insertions(+), 26 deletions(-) diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index a644e8e5071c..375bbd60b38a 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -326,6 +326,37 @@ static int lan88xx_config_aneg(struct phy_device *phydev) return genphy_config_aneg(phydev); } +static void lan88xx_link_change_notify(struct phy_device *phydev) +{ + int temp; + + /* At forced 100 F/H mode, chip may fail to set mode correctly + * when cable is switched between long(~50+m) and short one. + * As workaround, set to 10 before setting to 100 + * at forced 100 F/H mode. + */ + if (!phydev->autoneg && phydev->speed == 100) { + /* disable phy interrupt */ + temp = phy_read(phydev, LAN88XX_INT_MASK); + temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_; + phy_write(phydev, LAN88XX_INT_MASK, temp); + + temp = phy_read(phydev, MII_BMCR); + temp &= ~(BMCR_SPEED100 | BMCR_SPEED1000); + phy_write(phydev, MII_BMCR, temp); /* set to 10 first */ + temp |= BMCR_SPEED100; + phy_write(phydev, MII_BMCR, temp); /* set to 100 later */ + + /* clear pending interrupt generated while workaround */ + temp = phy_read(phydev, LAN88XX_INT_STS); + + /* enable phy interrupt back */ + temp = phy_read(phydev, LAN88XX_INT_MASK); + temp |= LAN88XX_INT_MASK_MDINTPIN_EN_; + phy_write(phydev, LAN88XX_INT_MASK, temp); + } +} + static struct phy_driver microchip_phy_driver[] = { { .phy_id = 0x0007c130, @@ -339,6 +370,7 @@ static struct phy_driver microchip_phy_driver[] = { .config_init = lan88xx_config_init, .config_aneg = lan88xx_config_aneg, + .link_change_notify = lan88xx_link_change_notify, .ack_interrupt = lan88xx_phy_ack_interrupt, .config_intr = lan88xx_phy_config_intr, diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 0b5b4f9c7c5b..667984efeb3b 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1843,33 +1843,8 @@ static void lan78xx_remove_mdio(struct lan78xx_net *dev) static void lan78xx_link_status_change(struct net_device *net) { struct phy_device *phydev = net->phydev; - int temp; - /* At forced 100 F/H mode, chip may fail to set mode correctly - * when cable is switched between long(~50+m) and short one. - * As workaround, set to 10 before setting to 100 - * at forced 100 F/H mode. - */ - if (!phydev->autoneg && (phydev->speed == 100)) { - /* disable phy interrupt */ - temp = phy_read(phydev, LAN88XX_INT_MASK); - temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_; - phy_write(phydev, LAN88XX_INT_MASK, temp); - - temp = phy_read(phydev, MII_BMCR); - temp &= ~(BMCR_SPEED100 | BMCR_SPEED1000); - phy_write(phydev, MII_BMCR, temp); /* set to 10 first */ - temp |= BMCR_SPEED100; - phy_write(phydev, MII_BMCR, temp); /* set to 100 later */ - - /* clear pending interrupt generated while workaround */ - temp = phy_read(phydev, LAN88XX_INT_STS); - - /* enable phy interrupt back */ - temp = phy_read(phydev, LAN88XX_INT_MASK); - temp |= LAN88XX_INT_MASK_MDINTPIN_EN_; - phy_write(phydev, LAN88XX_INT_MASK, temp); - } + phy_print_status(phydev); } static int irq_map(struct irq_domain *d, unsigned int irq, From c3aaec463a632cf4187dc017e421bfa69d7834a9 Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Thu, 2 Mar 2023 01:39:13 +0900 Subject: [PATCH 2077/4345] net: caif: Fix use-after-free in cfusbl_device_notify() [ Upstream commit 9781e98a97110f5e76999058368b4be76a788484 ] syzbot reported use-after-free in cfusbl_device_notify() [1]. This causes a stack trace like below: BUG: KASAN: use-after-free in cfusbl_device_notify+0x7c9/0x870 net/caif/caif_usb.c:138 Read of size 8 at addr ffff88807ac4e6f0 by task kworker/u4:6/1214 CPU: 0 PID: 1214 Comm: kworker/u4:6 Not tainted 5.19.0-rc3-syzkaller-00146-g92f20ff72066 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: netns cleanup_net Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0xeb/0x467 mm/kasan/report.c:313 print_report mm/kasan/report.c:429 [inline] kasan_report.cold+0xf4/0x1c6 mm/kasan/report.c:491 cfusbl_device_notify+0x7c9/0x870 net/caif/caif_usb.c:138 notifier_call_chain+0xb5/0x200 kernel/notifier.c:87 call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:1945 call_netdevice_notifiers_extack net/core/dev.c:1983 [inline] call_netdevice_notifiers net/core/dev.c:1997 [inline] netdev_wait_allrefs_any net/core/dev.c:10227 [inline] netdev_run_todo+0xbc0/0x10f0 net/core/dev.c:10341 default_device_exit_batch+0x44e/0x590 net/core/dev.c:11334 ops_exit_list+0x125/0x170 net/core/net_namespace.c:167 cleanup_net+0x4ea/0xb00 net/core/net_namespace.c:594 process_one_work+0x996/0x1610 kernel/workqueue.c:2289 worker_thread+0x665/0x1080 kernel/workqueue.c:2436 kthread+0x2e9/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:302 When unregistering a net device, unregister_netdevice_many_notify() sets the device's reg_state to NETREG_UNREGISTERING, calls notifiers with NETDEV_UNREGISTER, and adds the device to the todo list. Later on, devices in the todo list are processed by netdev_run_todo(). netdev_run_todo() waits devices' reference count become 1 while rebdoadcasting NETDEV_UNREGISTER notification. When cfusbl_device_notify() is called with NETDEV_UNREGISTER multiple times, the parent device might be freed. This could cause UAF. Processing NETDEV_UNREGISTER multiple times also causes inbalance of reference count for the module. This patch fixes the issue by accepting only first NETDEV_UNREGISTER notification. Fixes: 7ad65bf68d70 ("caif: Add support for CAIF over CDC NCM USB interface") CC: sjur.brandeland@stericsson.com Reported-by: syzbot+b563d33852b893653a9e@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=c3bfd8e2450adab3bffe4d80821fbbced600407f [1] Signed-off-by: Shigeru Yoshida Link: https://lore.kernel.org/r/20230301163913.391304-1-syoshida@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/caif/caif_usb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index b02e1292f7f1..24488a4e2d26 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -134,6 +134,9 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, struct usb_device *usbdev; int res; + if (what == NETDEV_UNREGISTER && dev->reg_state >= NETREG_UNREGISTERED) + return 0; + /* Check whether we have a NCM device, and find its VID/PID. */ if (!(dev->dev.parent && dev->dev.parent->driver && strcmp(dev->dev.parent->driver->name, "cdc_ncm") == 0)) From d2a5a9cdc5d6a33008c508d592f9847e7ff347cd Mon Sep 17 00:00:00 2001 From: Rongguang Wei Date: Thu, 2 Mar 2023 14:21:43 +0800 Subject: [PATCH 2078/4345] net: stmmac: add to set device wake up flag when stmmac init phy [ Upstream commit a9334b702a03b693f54ebd3b98f67bf722b74870 ] When MAC is not support PMT, driver will check PHY's WoL capability and set device wakeup capability in stmmac_init_phy(). We can enable the WoL through ethtool, the driver would enable the device wake up flag. Now the device_may_wakeup() return true. But if there is a way which enable the PHY's WoL capability derectly, like in BIOS. The driver would not know the enable thing and would not set the device wake up flag. The phy_suspend may failed like this: [ 32.409063] PM: dpm_run_callback(): mdio_bus_phy_suspend+0x0/0x50 returns -16 [ 32.409065] PM: Device stmmac-1:00 failed to suspend: error -16 [ 32.409067] PM: Some devices failed to suspend, or early wake event detected Add to set the device wakeup enable flag according to the get_wol function result in PHY can fix the error in this scene. v2: add a Fixes tag. Fixes: 1d8e5b0f3f2c ("net: stmmac: Support WOL with phy") Signed-off-by: Rongguang Wei Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1ec000d4c770..04c59102a286 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1145,6 +1145,7 @@ static int stmmac_init_phy(struct net_device *dev) phylink_ethtool_get_wol(priv->phylink, &wol); device_set_wakeup_capable(priv->device, !!wol.supported); + device_set_wakeup_enable(priv->device, !!wol.wolopts); } return ret; From c0df4e5c247d73f80925a62e7f0f9f8ae84bf691 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 3 Mar 2023 16:37:54 +0000 Subject: [PATCH 2079/4345] net: phylib: get rid of unnecessary locking [ Upstream commit f4b47a2e9463950df3e7c8b70e017877c1d4eb11 ] The locking in phy_probe() and phy_remove() does very little to prevent any races with e.g. phy_attach_direct(), but instead causes lockdep ABBA warnings. Remove it. ====================================================== WARNING: possible circular locking dependency detected 6.2.0-dirty #1108 Tainted: G W E ------------------------------------------------------ ip/415 is trying to acquire lock: ffff5c268f81ef50 (&dev->lock){+.+.}-{3:3}, at: phy_attach_direct+0x17c/0x3a0 [libphy] but task is already holding lock: ffffaef6496cb518 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x154/0x560 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (rtnl_mutex){+.+.}-{3:3}: __lock_acquire+0x35c/0x6c0 lock_acquire.part.0+0xcc/0x220 lock_acquire+0x68/0x84 __mutex_lock+0x8c/0x414 mutex_lock_nested+0x34/0x40 rtnl_lock+0x24/0x30 sfp_bus_add_upstream+0x34/0x150 phy_sfp_probe+0x4c/0x94 [libphy] mv3310_probe+0x148/0x184 [marvell10g] phy_probe+0x8c/0x200 [libphy] call_driver_probe+0xbc/0x15c really_probe+0xc0/0x320 __driver_probe_device+0x84/0x120 driver_probe_device+0x44/0x120 __device_attach_driver+0xc4/0x160 bus_for_each_drv+0x80/0xe0 __device_attach+0xb0/0x1f0 device_initial_probe+0x1c/0x2c bus_probe_device+0xa4/0xb0 device_add+0x360/0x53c phy_device_register+0x60/0xa4 [libphy] fwnode_mdiobus_phy_device_register+0xc0/0x190 [fwnode_mdio] fwnode_mdiobus_register_phy+0x160/0xd80 [fwnode_mdio] of_mdiobus_register+0x140/0x340 [of_mdio] orion_mdio_probe+0x298/0x3c0 [mvmdio] platform_probe+0x70/0xe0 call_driver_probe+0x34/0x15c really_probe+0xc0/0x320 __driver_probe_device+0x84/0x120 driver_probe_device+0x44/0x120 __driver_attach+0x104/0x210 bus_for_each_dev+0x78/0xdc driver_attach+0x2c/0x3c bus_add_driver+0x184/0x240 driver_register+0x80/0x13c __platform_driver_register+0x30/0x3c xt_compat_calc_jump+0x28/0xa4 [x_tables] do_one_initcall+0x50/0x1b0 do_init_module+0x50/0x1fc load_module+0x684/0x744 __do_sys_finit_module+0xc4/0x140 __arm64_sys_finit_module+0x28/0x34 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0x6c/0x1b0 do_el0_svc+0x34/0x44 el0_svc+0x48/0xf0 el0t_64_sync_handler+0xb8/0xc0 el0t_64_sync+0x1a0/0x1a4 -> #0 (&dev->lock){+.+.}-{3:3}: check_prev_add+0xb4/0xc80 validate_chain+0x414/0x47c __lock_acquire+0x35c/0x6c0 lock_acquire.part.0+0xcc/0x220 lock_acquire+0x68/0x84 __mutex_lock+0x8c/0x414 mutex_lock_nested+0x34/0x40 phy_attach_direct+0x17c/0x3a0 [libphy] phylink_fwnode_phy_connect.part.0+0x70/0xe4 [phylink] phylink_fwnode_phy_connect+0x48/0x60 [phylink] mvpp2_open+0xec/0x2e0 [mvpp2] __dev_open+0x104/0x214 __dev_change_flags+0x1d4/0x254 dev_change_flags+0x2c/0x7c do_setlink+0x254/0xa50 __rtnl_newlink+0x430/0x514 rtnl_newlink+0x58/0x8c rtnetlink_rcv_msg+0x17c/0x560 netlink_rcv_skb+0x64/0x150 rtnetlink_rcv+0x20/0x30 netlink_unicast+0x1d4/0x2b4 netlink_sendmsg+0x1a4/0x400 ____sys_sendmsg+0x228/0x290 ___sys_sendmsg+0x88/0xec __sys_sendmsg+0x70/0xd0 __arm64_sys_sendmsg+0x2c/0x40 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0x6c/0x1b0 do_el0_svc+0x34/0x44 el0_svc+0x48/0xf0 el0t_64_sync_handler+0xb8/0xc0 el0t_64_sync+0x1a0/0x1a4 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(rtnl_mutex); lock(&dev->lock); lock(rtnl_mutex); lock(&dev->lock); *** DEADLOCK *** Fixes: 298e54fa810e ("net: phy: add core phylib sfp support") Reported-by: Marc Zyngier Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/phy/phy_device.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 3ef5aa6b72a7..e771e0e8a9bc 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2833,8 +2833,6 @@ static int phy_probe(struct device *dev) if (phydrv->flags & PHY_IS_INTERNAL) phydev->is_internal = true; - mutex_lock(&phydev->lock); - /* Deassert the reset signal */ phy_device_reset(phydev, 0); @@ -2903,12 +2901,10 @@ static int phy_probe(struct device *dev) phydev->state = PHY_READY; out: - /* Assert the reset signal */ + /* Re-assert the reset signal on error */ if (err) phy_device_reset(phydev, 1); - mutex_unlock(&phydev->lock); - return err; } @@ -2918,9 +2914,7 @@ static int phy_remove(struct device *dev) cancel_delayed_work_sync(&phydev->state_queue); - mutex_lock(&phydev->lock); phydev->state = PHY_DOWN; - mutex_unlock(&phydev->lock); sfp_bus_del_upstream(phydev->sfp_bus); phydev->sfp_bus = NULL; From d16701a385b54f44bf41ff1d7485e7a11080deb3 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 3 Mar 2023 18:43:57 -0800 Subject: [PATCH 2080/4345] bnxt_en: Avoid order-5 memory allocation for TPA data [ Upstream commit accd7e23693aaaa9aa0d3e9eca0ae77d1be80ab3 ] The driver needs to keep track of all the possible concurrent TPA (GRO/LRO) completions on the aggregation ring. On P5 chips, the maximum number of concurrent TPA is 256 and the amount of memory we allocate is order-5 on systems using 4K pages. Memory allocation failure has been reported: NetworkManager: page allocation failure: order:5, mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null),cpuset=/,mems_allowed=0-1 CPU: 15 PID: 2995 Comm: NetworkManager Kdump: loaded Not tainted 5.10.156 #1 Hardware name: Dell Inc. PowerEdge R660/0M1CC5, BIOS 0.2.25 08/12/2022 Call Trace: dump_stack+0x57/0x6e warn_alloc.cold.120+0x7b/0xdd ? _cond_resched+0x15/0x30 ? __alloc_pages_direct_compact+0x15f/0x170 __alloc_pages_slowpath.constprop.108+0xc58/0xc70 __alloc_pages_nodemask+0x2d0/0x300 kmalloc_order+0x24/0xe0 kmalloc_order_trace+0x19/0x80 bnxt_alloc_mem+0x1150/0x15c0 [bnxt_en] ? bnxt_get_func_stat_ctxs+0x13/0x60 [bnxt_en] __bnxt_open_nic+0x12e/0x780 [bnxt_en] bnxt_open+0x10b/0x240 [bnxt_en] __dev_open+0xe9/0x180 __dev_change_flags+0x1af/0x220 dev_change_flags+0x21/0x60 do_setlink+0x35c/0x1100 Instead of allocating this big chunk of memory and dividing it up for the concurrent TPA instances, allocate each small chunk separately for each TPA instance. This will reduce it to order-0 allocations. Fixes: 79632e9ba386 ("bnxt_en: Expand bnxt_tpa_info struct to support 57500 chips.") Reviewed-by: Somnath Kotur Reviewed-by: Damodharam Ammepalli Reviewed-by: Pavan Chebbi Signed-off-by: Michael Chan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c4a768ce8c99..6928c0b578ab 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2854,7 +2854,7 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem) static void bnxt_free_tpa_info(struct bnxt *bp) { - int i; + int i, j; for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; @@ -2862,8 +2862,10 @@ static void bnxt_free_tpa_info(struct bnxt *bp) kfree(rxr->rx_tpa_idx_map); rxr->rx_tpa_idx_map = NULL; if (rxr->rx_tpa) { - kfree(rxr->rx_tpa[0].agg_arr); - rxr->rx_tpa[0].agg_arr = NULL; + for (j = 0; j < bp->max_tpa; j++) { + kfree(rxr->rx_tpa[j].agg_arr); + rxr->rx_tpa[j].agg_arr = NULL; + } } kfree(rxr->rx_tpa); rxr->rx_tpa = NULL; @@ -2872,14 +2874,13 @@ static void bnxt_free_tpa_info(struct bnxt *bp) static int bnxt_alloc_tpa_info(struct bnxt *bp) { - int i, j, total_aggs = 0; + int i, j; bp->max_tpa = MAX_TPA; if (bp->flags & BNXT_FLAG_CHIP_P5) { if (!bp->max_tpa_v2) return 0; bp->max_tpa = max_t(u16, bp->max_tpa_v2, MAX_TPA_P5); - total_aggs = bp->max_tpa * MAX_SKB_FRAGS; } for (i = 0; i < bp->rx_nr_rings; i++) { @@ -2893,12 +2894,12 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp) if (!(bp->flags & BNXT_FLAG_CHIP_P5)) continue; - agg = kcalloc(total_aggs, sizeof(*agg), GFP_KERNEL); - rxr->rx_tpa[0].agg_arr = agg; - if (!agg) - return -ENOMEM; - for (j = 1; j < bp->max_tpa; j++) - rxr->rx_tpa[j].agg_arr = agg + j * MAX_SKB_FRAGS; + for (j = 0; j < bp->max_tpa; j++) { + agg = kcalloc(MAX_SKB_FRAGS, sizeof(*agg), GFP_KERNEL); + if (!agg) + return -ENOMEM; + rxr->rx_tpa[j].agg_arr = agg; + } rxr->rx_tpa_idx_map = kzalloc(sizeof(*rxr->rx_tpa_idx_map), GFP_KERNEL); if (!rxr->rx_tpa_idx_map) From 26fa059cc92477c5fb16ef5bdca3b75997ddf95c Mon Sep 17 00:00:00 2001 From: Ivan Delalande Date: Thu, 2 Mar 2023 17:48:31 -0800 Subject: [PATCH 2081/4345] netfilter: ctnetlink: revert to dumping mark regardless of event type [ Upstream commit 9f7dd42f0db1dc6915a52d4a8a96ca18dd8cc34e ] It seems that change was unintentional, we have userspace code that needs the mark while listening for events like REPLY, DESTROY, etc. Also include 0-marks in requested dumps, as they were before that fix. Fixes: 1feeae071507 ("netfilter: ctnetlink: fix compilation warning after data race fixes in ct mark") Signed-off-by: Ivan Delalande Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_netlink.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index f8ba3bc25cf3..c9ca857f1068 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -317,11 +317,12 @@ nla_put_failure: } #ifdef CONFIG_NF_CONNTRACK_MARK -static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) +static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct, + bool dump) { u32 mark = READ_ONCE(ct->mark); - if (!mark) + if (!mark && !dump) return 0; if (nla_put_be32(skb, CTA_MARK, htonl(mark))) @@ -332,7 +333,7 @@ nla_put_failure: return -1; } #else -#define ctnetlink_dump_mark(a, b) (0) +#define ctnetlink_dump_mark(a, b, c) (0) #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK @@ -537,7 +538,7 @@ static int ctnetlink_dump_extinfo(struct sk_buff *skb, static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || - ctnetlink_dump_mark(skb, ct) < 0 || + ctnetlink_dump_mark(skb, ct, true) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || @@ -816,8 +817,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) } #ifdef CONFIG_NF_CONNTRACK_MARK - if (events & (1 << IPCT_MARK) && - ctnetlink_dump_mark(skb, ct) < 0) + if (ctnetlink_dump_mark(skb, ct, events & (1 << IPCT_MARK))) goto nla_put_failure; #endif nlmsg_end(skb, nlh); @@ -2734,7 +2734,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK - if (ctnetlink_dump_mark(skb, ct) < 0) + if (ctnetlink_dump_mark(skb, ct, true) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) From 065c1ed5c4cec2ae676f2b6b35fd13acf85a11eb Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 3 Mar 2023 10:58:56 +0100 Subject: [PATCH 2082/4345] netfilter: tproxy: fix deadlock due to missing BH disable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4a02426787bf024dafdb79b362285ee325de3f5e ] The xtables packet traverser performs an unconditional local_bh_disable(), but the nf_tables evaluation loop does not. Functions that are called from either xtables or nftables must assume that they can be called in process context. inet_twsk_deschedule_put() assumes that no softirq interrupt can occur. If tproxy is used from nf_tables its possible that we'll deadlock trying to aquire a lock already held in process context. Add a small helper that takes care of this and use it. Link: https://lore.kernel.org/netfilter-devel/401bd6ed-314a-a196-1cdc-e13c720cc8f2@balasys.hu/ Fixes: 4ed8eb6570a4 ("netfilter: nf_tables: Add native tproxy support") Reported-and-tested-by: Major Dávid Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/net/netfilter/nf_tproxy.h | 7 +++++++ net/ipv4/netfilter/nf_tproxy_ipv4.c | 2 +- net/ipv6/netfilter/nf_tproxy_ipv6.c | 2 +- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h index 82d0e41b76f2..faa108b1ba67 100644 --- a/include/net/netfilter/nf_tproxy.h +++ b/include/net/netfilter/nf_tproxy.h @@ -17,6 +17,13 @@ static inline bool nf_tproxy_sk_is_transparent(struct sock *sk) return false; } +static inline void nf_tproxy_twsk_deschedule_put(struct inet_timewait_sock *tw) +{ + local_bh_disable(); + inet_twsk_deschedule_put(tw); + local_bh_enable(); +} + /* assign a socket to the skb -- consumes sk */ static inline void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) { diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index b2bae0b0e42a..61cb2341f50f 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -38,7 +38,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, hp->source, lport ? lport : hp->dest, skb->dev, NF_TPROXY_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule_put(inet_twsk(sk)); + nf_tproxy_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c index 6bac68fb27a3..3fe4f15e01dc 100644 --- a/net/ipv6/netfilter/nf_tproxy_ipv6.c +++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c @@ -63,7 +63,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, lport ? lport : hp->dest, skb->dev, NF_TPROXY_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule_put(inet_twsk(sk)); + nf_tproxy_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } From 01a1e98109056dd8c760283f618a8d5fa97d26f9 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 6 Mar 2023 11:21:37 +0000 Subject: [PATCH 2083/4345] btf: fix resolving BTF_KIND_VAR after ARRAY, STRUCT, UNION, PTR [ Upstream commit 9b459804ff9973e173fabafba2a1319f771e85fa ] btf_datasec_resolve contains a bug that causes the following BTF to fail loading: [1] DATASEC a size=2 vlen=2 type_id=4 offset=0 size=1 type_id=7 offset=1 size=1 [2] INT (anon) size=1 bits_offset=0 nr_bits=8 encoding=(none) [3] PTR (anon) type_id=2 [4] VAR a type_id=3 linkage=0 [5] INT (anon) size=1 bits_offset=0 nr_bits=8 encoding=(none) [6] TYPEDEF td type_id=5 [7] VAR b type_id=6 linkage=0 This error message is printed during btf_check_all_types: [1] DATASEC a size=2 vlen=2 type_id=7 offset=1 size=1 Invalid type By tracing btf_*_resolve we can pinpoint the problem: btf_datasec_resolve(depth: 1, type_id: 1, mode: RESOLVE_TBD) = 0 btf_var_resolve(depth: 2, type_id: 4, mode: RESOLVE_TBD) = 0 btf_ptr_resolve(depth: 3, type_id: 3, mode: RESOLVE_PTR) = 0 btf_var_resolve(depth: 2, type_id: 4, mode: RESOLVE_PTR) = 0 btf_datasec_resolve(depth: 1, type_id: 1, mode: RESOLVE_PTR) = -22 The last invocation of btf_datasec_resolve should invoke btf_var_resolve by means of env_stack_push, instead it returns EINVAL. The reason is that env_stack_push is never executed for the second VAR. if (!env_type_is_resolve_sink(env, var_type) && !env_type_is_resolved(env, var_type_id)) { env_stack_set_next_member(env, i + 1); return env_stack_push(env, var_type, var_type_id); } env_type_is_resolve_sink() changes its behaviour based on resolve_mode. For RESOLVE_PTR, we can simplify the if condition to the following: (btf_type_is_modifier() || btf_type_is_ptr) && !env_type_is_resolved() Since we're dealing with a VAR the clause evaluates to false. This is not sufficient to trigger the bug however. The log output and EINVAL are only generated if btf_type_id_size() fails. if (!btf_type_id_size(btf, &type_id, &type_size)) { btf_verifier_log_vsi(env, v->t, vsi, "Invalid type"); return -EINVAL; } Most types are sized, so for example a VAR referring to an INT is not a problem. The bug is only triggered if a VAR points at a modifier. Since we skipped btf_var_resolve that modifier was also never resolved, which means that btf_resolved_type_id returns 0 aka VOID for the modifier. This in turn causes btf_type_id_size to return NULL, triggering EINVAL. To summarise, the following conditions are necessary: - VAR pointing at PTR, STRUCT, UNION or ARRAY - Followed by a VAR pointing at TYPEDEF, VOLATILE, CONST, RESTRICT or TYPE_TAG The fix is to reset resolve_mode to RESOLVE_TBD before attempting to resolve a VAR from a DATASEC. Fixes: 1dc92851849c ("bpf: kernel side support for BTF Var and DataSec") Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230306112138.155352-2-lmb@isovalent.com Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- kernel/bpf/btf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 11b612e94e4e..cb80d18a49b5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3541,6 +3541,7 @@ static int btf_datasec_resolve(struct btf_verifier_env *env, struct btf *btf = env->btf; u16 i; + env->resolve_mode = RESOLVE_TBD; for_each_vsi_from(i, v->next_member, v->t, vsi) { u32 var_type_id = vsi->type, type_id, type_size = 0; const struct btf_type *var_type = btf_type_by_id(env->btf, From f4eae84f575492e18bd71176ad1a084bf837252d Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Sat, 4 Mar 2023 13:43:20 +0000 Subject: [PATCH 2084/4345] net: ethernet: mtk_eth_soc: fix RX data corruption issue MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 193250ace270fecd586dd2d0dfbd9cbd2ade977f ] Fix data corruption issue with SerDes connected PHYs operating at 1.25 Gbps speed where we could previously observe about 30% packet loss while the bad packet counter was increasing. As almost all boards with MediaTek MT7622 or MT7986 use either the MT7531 switch IC operating at 3.125Gbps SerDes rate or single-port PHYs using rate-adaptation to 2500Base-X mode, this issue only got exposed now when we started trying to use SFP modules operating with 1.25 Gbps with the BananaPi R3 board. The fix is to set bit 12 which disables the RX FIFO clear function when setting up MAC MCR, MediaTek SDK did the same change stating: "If without this patch, kernel might receive invalid packets that are corrupted by GMAC."[1] [1]: https://git01.mediatek.com/plugins/gitiles/openwrt/feeds/mtk-openwrt-feeds/+/d8a2975939a12686c4a95c40db21efdc3f821f63 Fixes: 42c03844e93d ("net-next: mediatek: add support for MediaTek MT7622 SoC") Tested-by: Bjørn Mork Signed-off-by: Daniel Golle Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/138da2735f92c8b6f8578ec2e5a794ee515b665f.1677937317.git.daniel@makrotopia.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 3 ++- drivers/net/ethernet/mediatek/mtk_eth_soc.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 217dc67c48fa..a8319295f1ab 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -354,7 +354,8 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode, mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); mcr_new = mcr_cur; mcr_new |= MAC_MCR_MAX_RX_1536 | MAC_MCR_IPG_CFG | MAC_MCR_FORCE_MODE | - MAC_MCR_BACKOFF_EN | MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_LINK; + MAC_MCR_BACKOFF_EN | MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_LINK | + MAC_MCR_RX_FIFO_CLR_DIS; /* Only update control register when needed! */ if (mcr_new != mcr_cur) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 54a7cd93cc0f..0ca3223ad545 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -339,6 +339,7 @@ #define MAC_MCR_FORCE_MODE BIT(15) #define MAC_MCR_TX_EN BIT(14) #define MAC_MCR_RX_EN BIT(13) +#define MAC_MCR_RX_FIFO_CLR_DIS BIT(12) #define MAC_MCR_BACKOFF_EN BIT(9) #define MAC_MCR_BACKPR_EN BIT(8) #define MAC_MCR_FORCE_RX_FC BIT(5) From 0fe672336d69c56d0656e705158311618f627aba Mon Sep 17 00:00:00 2001 From: Chandrakanth Patil Date: Thu, 2 Mar 2023 16:23:40 +0530 Subject: [PATCH 2085/4345] scsi: megaraid_sas: Update max supported LD IDs to 240 [ Upstream commit bfa659177dcba48cf13f2bd88c1972f12a60bf1c ] The firmware only supports Logical Disk IDs up to 240 and LD ID 255 (0xFF) is reserved for deleted LDs. However, in some cases, firmware was assigning LD ID 254 (0xFE) to deleted LDs and this was causing the driver to mark the wrong disk as deleted. This in turn caused the wrong disk device to be taken offline by the SCSI midlayer. To address this issue, limit the LD ID range from 255 to 240. This ensures the deleted LD ID is properly identified and removed by the driver without accidently deleting any valid LDs. Fixes: ae6874ba4b43 ("scsi: megaraid_sas: Early detection of VD deletion through RaidMap update") Reported-by: Martin K. Petersen Signed-off-by: Chandrakanth Patil Signed-off-by: Sumit Saxena Link: https://lore.kernel.org/r/20230302105342.34933-2-chandrakanth.patil@broadcom.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/megaraid/megaraid_sas.h | 2 ++ drivers/scsi/megaraid/megaraid_sas_fp.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h index c088a848776e..2d5b1d597866 100644 --- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -1517,6 +1517,8 @@ struct megasas_ctrl_info { #define MEGASAS_MAX_LD_IDS (MEGASAS_MAX_LD_CHANNELS * \ MEGASAS_MAX_DEV_PER_CHANNEL) +#define MEGASAS_MAX_SUPPORTED_LD_IDS 240 + #define MEGASAS_MAX_SECTORS (2*1024) #define MEGASAS_MAX_SECTORS_IEEE (2*128) #define MEGASAS_DBG_LVL 1 diff --git a/drivers/scsi/megaraid/megaraid_sas_fp.c b/drivers/scsi/megaraid/megaraid_sas_fp.c index 83f69c33b01a..ec10d35b4685 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fp.c +++ b/drivers/scsi/megaraid/megaraid_sas_fp.c @@ -358,7 +358,7 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance, u64 map_id) ld = MR_TargetIdToLdGet(i, drv_map); /* For non existing VDs, iterate to next VD*/ - if (ld >= (MAX_LOGICAL_DRIVES_EXT - 1)) + if (ld >= MEGASAS_MAX_SUPPORTED_LD_IDS) continue; raid = MR_LdRaidGet(ld, drv_map); From 93367126f68cd66359bbc81c3e9f6fda93701099 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 25 Feb 2023 21:39:51 -0800 Subject: [PATCH 2086/4345] platform: x86: MLX_PLATFORM: select REGMAP instead of depending on it [ Upstream commit 7e7e1541c91615e9950d0b96bcd1806d297e970e ] REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it. Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues. Therefore, change the use of "depends on REGMAP" to "select REGMAP". Fixes: ef0f62264b2a ("platform/x86: mlx-platform: Add physical bus number auto detection") Signed-off-by: Randy Dunlap Cc: Vadim Pasternak Cc: Darren Hart Cc: Hans de Goede Cc: Mark Gross Cc: platform-driver-x86@vger.kernel.org Link: https://lore.kernel.org/r/20230226053953.4681-7-rdunlap@infradead.org Signed-off-by: Hans de Goede Reviewed-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index a1858689d6e1..84c5b922f245 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -1195,7 +1195,8 @@ config I2C_MULTI_INSTANTIATE config MLX_PLATFORM tristate "Mellanox Technologies platform support" - depends on I2C && REGMAP + depends on I2C + select REGMAP help This option enables system support for the Mellanox Technologies platform. The Mellanox systems provide data center networking From e1b8342a85289d0d3411744c4fc1e0fc46fc9d5c Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Tue, 7 Mar 2023 11:23:46 +0800 Subject: [PATCH 2087/4345] net/smc: fix fallback failed while sendmsg with fastopen [ Upstream commit ce7ca794712f186da99719e8b4e97bd5ddbb04c3 ] Before determining whether the msg has unsupported options, it has been prematurely terminated by the wrong status check. For the application, the general usages of MSG_FASTOPEN likes fd = socket(...) /* rather than connect */ sendto(fd, data, len, MSG_FASTOPEN) Hence, We need to check the flag before state check, because the sock state here is always SMC_INIT when applications tries MSG_FASTOPEN. Once we found unsupported options, fallback it to TCP. Fixes: ee9dfbef02d1 ("net/smc: handle sockopts forcing fallback") Signed-off-by: D. Wythe Signed-off-by: Simon Horman v2 -> v1: Optimize code style Reviewed-by: Tony Lu Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/smc/af_smc.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 41cbc7c89c9d..8ab84926816f 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1988,16 +1988,14 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct smc_sock *smc; - int rc = -EPIPE; + int rc; smc = smc_sk(sk); lock_sock(sk); - if ((sk->sk_state != SMC_ACTIVE) && - (sk->sk_state != SMC_APPCLOSEWAIT1) && - (sk->sk_state != SMC_INIT)) - goto out; + /* SMC does not support connect with fastopen */ if (msg->msg_flags & MSG_FASTOPEN) { + /* not connected yet, fallback */ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; @@ -2005,6 +2003,11 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) rc = -EINVAL; goto out; } + } else if ((sk->sk_state != SMC_ACTIVE) && + (sk->sk_state != SMC_APPCLOSEWAIT1) && + (sk->sk_state != SMC_INIT)) { + rc = -EPIPE; + goto out; } if (smc->use_fallback) From ce7dd61e004002bc1c48d1ca47c887f3f3cc7370 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Fri, 3 Mar 2023 16:08:32 -0500 Subject: [PATCH 2088/4345] SUNRPC: Fix a server shutdown leak [ Upstream commit 9ca6705d9d609441d34f8b853e1e4a6369b3b171 ] Fix a race where kthread_stop() may prevent the threadfn from ever getting called. If that happens the svc_rqst will not be cleaned up. Fixes: ed6473ddc704 ("NFSv4: Fix callback server shutdown") Signed-off-by: Benjamin Coddington Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- net/sunrpc/svc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d38788cd9433..af657a482ad2 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -800,6 +800,7 @@ EXPORT_SYMBOL_GPL(svc_set_num_threads); static int svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { + struct svc_rqst *rqstp; struct task_struct *task; unsigned int state = serv->sv_nrthreads-1; @@ -808,7 +809,10 @@ svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) task = choose_victim(serv, pool, &state); if (task == NULL) break; - kthread_stop(task); + rqstp = kthread_data(task); + /* Did we lose a race to svo_function threadfn? */ + if (kthread_stop(task) == -EINTR) + svc_exit_thread(rqstp); nrservs++; } while (nrservs < 0); return 0; From 3de277af481ab931fab9e295ad8762692920732a Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 8 Mar 2023 10:16:39 +0100 Subject: [PATCH 2089/4345] riscv: Use READ_ONCE_NOCHECK in imprecise unwinding stack mode [ Upstream commit 76950340cf03b149412fe0d5f0810e52ac1df8cb ] When CONFIG_FRAME_POINTER is unset, the stack unwinding function walk_stackframe randomly reads the stack and then, when KASAN is enabled, it can lead to the following backtrace: [ 0.000000] ================================================================== [ 0.000000] BUG: KASAN: stack-out-of-bounds in walk_stackframe+0xa6/0x11a [ 0.000000] Read of size 8 at addr ffffffff81807c40 by task swapper/0 [ 0.000000] [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 6.2.0-12919-g24203e6db61f #43 [ 0.000000] Hardware name: riscv-virtio,qemu (DT) [ 0.000000] Call Trace: [ 0.000000] [] walk_stackframe+0x0/0x11a [ 0.000000] [] init_param_lock+0x26/0x2a [ 0.000000] [] walk_stackframe+0xa2/0x11a [ 0.000000] [] dump_stack_lvl+0x22/0x36 [ 0.000000] [] print_report+0x198/0x4a8 [ 0.000000] [] init_param_lock+0x26/0x2a [ 0.000000] [] walk_stackframe+0xa2/0x11a [ 0.000000] [] kasan_report+0x9a/0xc8 [ 0.000000] [] walk_stackframe+0xa2/0x11a [ 0.000000] [] walk_stackframe+0xa2/0x11a [ 0.000000] [] desc_make_final+0x80/0x84 [ 0.000000] [] stack_trace_save+0x88/0xa6 [ 0.000000] [] filter_irq_stacks+0x72/0x76 [ 0.000000] [] devkmsg_read+0x32a/0x32e [ 0.000000] [] kasan_save_stack+0x28/0x52 [ 0.000000] [] desc_make_final+0x7c/0x84 [ 0.000000] [] stack_trace_save+0x84/0xa6 [ 0.000000] [] kasan_set_track+0x12/0x20 [ 0.000000] [] __kasan_slab_alloc+0x58/0x5e [ 0.000000] [] __kmem_cache_create+0x21e/0x39a [ 0.000000] [] create_boot_cache+0x70/0x9c [ 0.000000] [] kmem_cache_init+0x6c/0x11e [ 0.000000] [] mm_init+0xd8/0xfe [ 0.000000] [] start_kernel+0x190/0x3ca [ 0.000000] [ 0.000000] The buggy address belongs to stack of task swapper/0 [ 0.000000] and is located at offset 0 in frame: [ 0.000000] stack_trace_save+0x0/0xa6 [ 0.000000] [ 0.000000] This frame has 1 object: [ 0.000000] [32, 56) 'c' [ 0.000000] [ 0.000000] The buggy address belongs to the physical page: [ 0.000000] page:(____ptrval____) refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x81a07 [ 0.000000] flags: 0x1000(reserved|zone=0) [ 0.000000] raw: 0000000000001000 ff600003f1e3d150 ff600003f1e3d150 0000000000000000 [ 0.000000] raw: 0000000000000000 0000000000000000 00000001ffffffff [ 0.000000] page dumped because: kasan: bad access detected [ 0.000000] [ 0.000000] Memory state around the buggy address: [ 0.000000] ffffffff81807b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 0.000000] ffffffff81807b80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 0.000000] >ffffffff81807c00: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 f3 [ 0.000000] ^ [ 0.000000] ffffffff81807c80: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 [ 0.000000] ffffffff81807d00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 0.000000] ================================================================== Fix that by using READ_ONCE_NOCHECK when reading the stack in imprecise mode. Fixes: 5d8544e2d007 ("RISC-V: Generic library routines and assembly") Reported-by: Chathura Rajapaksha Link: https://lore.kernel.org/all/CAD7mqryDQCYyJ1gAmtMm8SASMWAQ4i103ptTb0f6Oda=tPY2=A@mail.gmail.com/ Suggested-by: Dmitry Vyukov Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230308091639.602024-1-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/kernel/stacktrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 1e53fbe5eb78..9c34735c1e77 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -96,7 +96,7 @@ void notrace walk_stackframe(struct task_struct *task, while (!kstack_end(ksp)) { if (__kernel_text_address(pc) && unlikely(fn(pc, arg))) break; - pc = (*ksp++) - 0x4; + pc = READ_ONCE_NOCHECK(*ksp++) - 0x4; } } From ab89b8a67fbbc37c34c2ecb3ed0d7d2ea4bc4c3d Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Fri, 3 Mar 2023 14:37:55 +0000 Subject: [PATCH 2090/4345] RISC-V: Don't check text_mutex during stop_machine [ Upstream commit 2a8db5ec4a28a0fce822d10224db9471a44b6925 ] We're currently using stop_machine() to update ftrace & kprobes, which means that the thread that takes text_mutex during may not be the same as the thread that eventually patches the code. This isn't actually a race because the lock is still held (preventing any other concurrent accesses) and there is only one thread running during stop_machine(), but it does trigger a lockdep failure. This patch just elides the lockdep check during stop_machine. Fixes: c15ac4fd60d5 ("riscv/ftrace: Add dynamic function tracer support") Suggested-by: Steven Rostedt Reported-by: Changbin Du Signed-off-by: Palmer Dabbelt Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20230303143754.4005217-1-conor.dooley@microchip.com Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/include/asm/ftrace.h | 2 +- arch/riscv/include/asm/patch.h | 2 ++ arch/riscv/kernel/ftrace.c | 14 ++++++++++++-- arch/riscv/kernel/patch.c | 28 +++++++++++++++++++++++++--- 4 files changed, 40 insertions(+), 6 deletions(-) diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 04dad3380041..bc745900c163 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -83,6 +83,6 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); #define ftrace_init_nop ftrace_init_nop #endif -#endif +#endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/patch.h index 9a7d7346001e..98d9de07cba1 100644 --- a/arch/riscv/include/asm/patch.h +++ b/arch/riscv/include/asm/patch.h @@ -9,4 +9,6 @@ int patch_text_nosync(void *addr, const void *insns, size_t len); int patch_text(void *addr, u32 insn); +extern int riscv_patch_in_stop_machine; + #endif /* _ASM_RISCV_PATCH_H */ diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 765b62434f30..8693dfcffb02 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -15,11 +15,21 @@ int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) { mutex_lock(&text_mutex); + + /* + * The code sequences we use for ftrace can't be patched while the + * kernel is running, so we need to use stop_machine() to modify them + * for now. This doesn't play nice with text_mutex, we use this flag + * to elide the check. + */ + riscv_patch_in_stop_machine = true; + return 0; } int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) { + riscv_patch_in_stop_machine = false; mutex_unlock(&text_mutex); return 0; } @@ -109,9 +119,9 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) { int out; - ftrace_arch_code_modify_prepare(); + mutex_lock(&text_mutex); out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); - ftrace_arch_code_modify_post_process(); + mutex_unlock(&text_mutex); return out; } diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 1612e11f7bf6..c3fced410e74 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -11,6 +11,7 @@ #include #include #include +#include #include struct patch_insn { @@ -19,6 +20,8 @@ struct patch_insn { atomic_t cpu_count; }; +int riscv_patch_in_stop_machine = false; + #ifdef CONFIG_MMU static void *patch_map(void *addr, int fixmap) { @@ -55,8 +58,15 @@ static int patch_insn_write(void *addr, const void *insn, size_t len) * Before reaching here, it was expected to lock the text_mutex * already, so we don't need to give another lock here and could * ensure that it was safe between each cores. + * + * We're currently using stop_machine() for ftrace & kprobes, and while + * that ensures text_mutex is held before installing the mappings it + * does not ensure text_mutex is held by the calling thread. That's + * safe but triggers a lockdep failure, so just elide it for that + * specific case. */ - lockdep_assert_held(&text_mutex); + if (!riscv_patch_in_stop_machine) + lockdep_assert_held(&text_mutex); if (across_pages) patch_map(addr + len, FIX_TEXT_POKE1); @@ -117,13 +127,25 @@ NOKPROBE_SYMBOL(patch_text_cb); int patch_text(void *addr, u32 insn) { + int ret; struct patch_insn patch = { .addr = addr, .insn = insn, .cpu_count = ATOMIC_INIT(0), }; - return stop_machine_cpuslocked(patch_text_cb, - &patch, cpu_online_mask); + /* + * kprobes takes text_mutex, before calling patch_text(), but as we call + * calls stop_machine(), the lockdep assertion in patch_insn_write() + * gets confused by the context in which the lock is taken. + * Instead, ensure the lock is held before calling stop_machine(), and + * set riscv_patch_in_stop_machine to skip the check in + * patch_insn_write(). + */ + lockdep_assert_held(&text_mutex); + riscv_patch_in_stop_machine = true; + ret = stop_machine_cpuslocked(patch_text_cb, &patch, cpu_online_mask); + riscv_patch_in_stop_machine = false; + return ret; } NOKPROBE_SYMBOL(patch_text); From b113f90204479f55a17295bedf0cc966a60c7a56 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 1 Mar 2023 15:10:04 +0100 Subject: [PATCH 2091/4345] ext4: Fix deadlock during directory rename [ Upstream commit 3c92792da8506a295afb6d032b4476e46f979725 ] As lockdep properly warns, we should not be locking i_rwsem while having transactions started as the proper lock ordering used by all directory handling operations is i_rwsem -> transaction start. Fix the lock ordering by moving the locking of the directory earlier in ext4_rename(). Reported-by: syzbot+9d16c39efb5fade84574@syzkaller.appspotmail.com Fixes: 0813299c586b ("ext4: Fix possible corruption when moving a directory") Link: https://syzkaller.appspot.com/bug?extid=9d16c39efb5fade84574 Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230301141004.15087-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/namei.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 17590bb76914..1f47aeca7142 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3863,10 +3863,20 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, return retval; } + /* + * We need to protect against old.inode directory getting converted + * from inline directory format into a normal one. + */ + if (S_ISDIR(old.inode->i_mode)) + inode_lock_nested(old.inode, I_MUTEX_NONDIR2); + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, &old.inlined); - if (IS_ERR(old.bh)) - return PTR_ERR(old.bh); + if (IS_ERR(old.bh)) { + retval = PTR_ERR(old.bh); + goto unlock_moved_dir; + } + /* * Check for inode number is _not_ due to possible IO errors. * We might rmdir the source, keep it as pwd of some process @@ -3923,11 +3933,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, if (new.dir != old.dir && EXT4_DIR_LINK_MAX(new.dir)) goto end_rename; } - /* - * We need to protect against old.inode directory getting - * converted from inline directory format into a normal one. - */ - inode_lock_nested(old.inode, I_MUTEX_NONDIR2); retval = ext4_rename_dir_prepare(handle, &old); if (retval) { inode_unlock(old.inode); @@ -4057,12 +4062,15 @@ end_rename: } else { ext4_journal_stop(handle); } - if (old.dir_bh) - inode_unlock(old.inode); release_bh: brelse(old.dir_bh); brelse(old.bh); brelse(new.bh); + +unlock_moved_dir: + if (S_ISDIR(old.inode->i_mode)) + inode_unlock(old.inode); + return retval; } From f2a5ec7f7b28f9b9cd5fac232ff51019a7f7b9e9 Mon Sep 17 00:00:00 2001 From: Gavrilov Ilia Date: Thu, 2 Feb 2023 08:26:56 +0000 Subject: [PATCH 2092/4345] iommu/amd: Add a length limitation for the ivrs_acpihid command-line parameter [ Upstream commit b6b26d86c61c441144c72f842f7469bb686e1211 ] The 'acpiid' buffer in the parse_ivrs_acpihid function may overflow, because the string specifier in the format string sscanf() has no width limitation. Found by InfoTeCS on behalf of Linux Verification Center (linuxtesting.org) with SVACE. Fixes: ca3bf5d47cec ("iommu/amd: Introduces ivrs_acpihid kernel parameter") Cc: stable@vger.kernel.org Signed-off-by: Ilia.Gavrilov Reviewed-by: Kim Phillips Link: https://lore.kernel.org/r/20230202082719.1513849-1-Ilia.Gavrilov@infotecs.ru Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/amd/init.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index ce822347f747..603f625a74e5 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3124,15 +3124,26 @@ found: return 1; } +#define ACPIID_LEN (ACPIHID_UID_LEN + ACPIHID_HID_LEN) + static int __init parse_ivrs_acpihid(char *str) { u32 seg = 0, bus, dev, fn; char *hid, *uid, *p, *addr; - char acpiid[ACPIHID_UID_LEN + ACPIHID_HID_LEN] = {0}; + char acpiid[ACPIID_LEN] = {0}; int i; addr = strchr(str, '@'); if (!addr) { + addr = strchr(str, '='); + if (!addr) + goto not_found; + + ++addr; + + if (strlen(addr) > ACPIID_LEN) + goto not_found; + if (sscanf(str, "[%x:%x.%x]=%s", &bus, &dev, &fn, acpiid) == 4 || sscanf(str, "[%x:%x:%x.%x]=%s", &seg, &bus, &dev, &fn, acpiid) == 5) { pr_warn("ivrs_acpihid%s option format deprecated; use ivrs_acpihid=%s@%04x:%02x:%02x.%d instead\n", @@ -3145,6 +3156,9 @@ static int __init parse_ivrs_acpihid(char *str) /* We have the '@', make it the terminator to get just the acpiid */ *addr++ = 0; + if (strlen(str) > ACPIID_LEN + 1) + goto not_found; + if (sscanf(str, "=%s", acpiid) != 1) goto not_found; From b1fddddf58acd6d9618a2e3e974f3a2629b2ebf5 Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Tue, 7 Mar 2023 16:21:06 +0100 Subject: [PATCH 2093/4345] watch_queue: fix IOC_WATCH_QUEUE_SET_SIZE alloc error paths [ Upstream commit 03e1d60e177eedbd302b77af4ea5e21b5a7ade31 ] The watch_queue_set_size() allocation error paths return the ret value set via the prior pipe_resize_ring() call, which will always be zero. As a result, IOC_WATCH_QUEUE_SET_SIZE callers such as "keyctl watch" fail to detect kernel wqueue->notes allocation failures and proceed to KEYCTL_WATCH_KEY, with any notifications subsequently lost. Fixes: c73be61cede58 ("pipe: Add general notification queue support") Signed-off-by: David Disseldorp Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Sasha Levin --- kernel/watch_queue.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index d29731a30b8e..73717917d816 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -274,6 +274,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) if (ret < 0) goto error; + ret = -ENOMEM; pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL); if (!pages) goto error; From c660e024bc681fdd0bd839a94834be216afd30d5 Mon Sep 17 00:00:00 2001 From: Morten Linderud Date: Wed, 15 Feb 2023 10:25:52 +0100 Subject: [PATCH 2094/4345] tpm/eventlog: Don't abort tpm_read_log on faulty ACPI address [ Upstream commit 80a6c216b16d7f5c584d2148c2e4345ea4eb06ce ] tpm_read_log_acpi() should return -ENODEV when no eventlog from the ACPI table is found. If the firmware vendor includes an invalid log address we are unable to map from the ACPI memory and tpm_read_log() returns -EIO which would abort discovery of the eventlog. Change the return value from -EIO to -ENODEV when acpi_os_map_iomem() fails to map the event log. The following hardware was used to test this issue: Framework Laptop (Pre-production) BIOS: INSYDE Corp, Revision: 3.2 TPM Device: NTC, Firmware Revision: 7.2 Dump of the faulty ACPI TPM2 table: [000h 0000 4] Signature : "TPM2" [Trusted Platform Module hardware interface Table] [004h 0004 4] Table Length : 0000004C [008h 0008 1] Revision : 04 [009h 0009 1] Checksum : 2B [00Ah 0010 6] Oem ID : "INSYDE" [010h 0016 8] Oem Table ID : "TGL-ULT" [018h 0024 4] Oem Revision : 00000002 [01Ch 0028 4] Asl Compiler ID : "ACPI" [020h 0032 4] Asl Compiler Revision : 00040000 [024h 0036 2] Platform Class : 0000 [026h 0038 2] Reserved : 0000 [028h 0040 8] Control Address : 0000000000000000 [030h 0048 4] Start Method : 06 [Memory Mapped I/O] [034h 0052 12] Method Parameters : 00 00 00 00 00 00 00 00 00 00 00 00 [040h 0064 4] Minimum Log Length : 00010000 [044h 0068 8] Log Address : 000000004053D000 Fixes: 0cf577a03f21 ("tpm: Fix handling of missing event log") Tested-by: Erkki Eilonen Signed-off-by: Morten Linderud Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Sasha Levin --- drivers/char/tpm/eventlog/acpi.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c index 0913d3eb8d51..cd266021d010 100644 --- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -143,8 +143,12 @@ int tpm_read_log_acpi(struct tpm_chip *chip) ret = -EIO; virt = acpi_os_map_iomem(start, len); - if (!virt) + if (!virt) { + dev_warn(&chip->dev, "%s: Failed to map ACPI memory\n", __func__); + /* try EFI log next */ + ret = -ENODEV; goto err; + } memcpy_fromio(log->bios_event_log, virt, len); From 5533742c7cb1bc9b1f0bf401cc397d44a3a9e07a Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 13 Mar 2023 15:27:53 -0700 Subject: [PATCH 2095/4345] block, bfq: fix possible uaf for 'bfqq->bic' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 64dc8c732f5c2b406cc752e6aaa1bd5471159cab ] Our test report a uaf for 'bfqq->bic' in 5.10: ================================================================== BUG: KASAN: use-after-free in bfq_select_queue+0x378/0xa30 CPU: 6 PID: 2318352 Comm: fsstress Kdump: loaded Not tainted 5.10.0-60.18.0.50.h602.kasan.eulerosv2r11.x86_64 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-20220320_160524-szxrtosci10000 04/01/2014 Call Trace: bfq_select_queue+0x378/0xa30 bfq_dispatch_request+0xe8/0x130 blk_mq_do_dispatch_sched+0x62/0xb0 __blk_mq_sched_dispatch_requests+0x215/0x2a0 blk_mq_sched_dispatch_requests+0x8f/0xd0 __blk_mq_run_hw_queue+0x98/0x180 __blk_mq_delay_run_hw_queue+0x22b/0x240 blk_mq_run_hw_queue+0xe3/0x190 blk_mq_sched_insert_requests+0x107/0x200 blk_mq_flush_plug_list+0x26e/0x3c0 blk_finish_plug+0x63/0x90 __iomap_dio_rw+0x7b5/0x910 iomap_dio_rw+0x36/0x80 ext4_dio_read_iter+0x146/0x190 [ext4] ext4_file_read_iter+0x1e2/0x230 [ext4] new_sync_read+0x29f/0x400 vfs_read+0x24e/0x2d0 ksys_read+0xd5/0x1b0 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x61/0xc6 Commit 3bc5e683c67d ("bfq: Split shared queues on move between cgroups") changes that move process to a new cgroup will allocate a new bfqq to use, however, the old bfqq and new bfqq can point to the same bic: 1) Initial state, two process with io in the same cgroup. Process 1 Process 2 (BIC1) (BIC2) | Λ | Λ | | | | V | V | bfqq1 bfqq2 2) bfqq1 is merged to bfqq2. Process 1 Process 2 (BIC1) (BIC2) | | \-------------\| V bfqq1 bfqq2(coop) 3) Process 1 exit, then issue new io(denoce IOA) from Process 2. (BIC2) | Λ | | V | bfqq2(coop) 4) Before IOA is completed, move Process 2 to another cgroup and issue io. Process 2 (BIC2) Λ |\--------------\ | V bfqq2 bfqq3 Now that BIC2 points to bfqq3, while bfqq2 and bfqq3 both point to BIC2. If all the requests are completed, and Process 2 exit, BIC2 will be freed while there is no guarantee that bfqq2 will be freed before BIC2. Fix the problem by clearing bfqq->bic while bfqq is detached from bic. Fixes: 3bc5e683c67d ("bfq: Split shared queues on move between cgroups") Suggested-by: Jan Kara Signed-off-by: Yu Kuai Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221214030430.3304151-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Khazhismel Kumykov Signed-off-by: Sasha Levin --- block/bfq-iosched.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 7c4b8d0635eb..afaededb3c49 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -373,6 +373,12 @@ struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync) void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync) { + struct bfq_queue *old_bfqq = bic->bfqq[is_sync]; + + /* Clear bic pointer if bfqq is detached from this bic */ + if (old_bfqq && old_bfqq->bic == bic) + old_bfqq->bic = NULL; + bic->bfqq[is_sync] = bfqq; } @@ -4977,7 +4983,6 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync) unsigned long flags; spin_lock_irqsave(&bfqd->lock, flags); - bfqq->bic = NULL; bfq_exit_bfqq(bfqd, bfqq); bic_set_bfqq(bic, NULL, is_sync); spin_unlock_irqrestore(&bfqd->lock, flags); From 1425f1bb5df5239021fd09ebc2a5e8070e705d36 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 13 Mar 2023 15:27:54 -0700 Subject: [PATCH 2096/4345] block, bfq: fix uaf for bfqq in bfq_exit_icq_bfqq [ Upstream commit 246cf66e300b76099b5dbd3fdd39e9a5dbc53f02 ] Commit 64dc8c732f5c ("block, bfq: fix possible uaf for 'bfqq->bic'") will access 'bic->bfqq' in bic_set_bfqq(), however, bfq_exit_icq_bfqq() can free bfqq first, and then call bic_set_bfqq(), which will cause uaf. Fix the problem by moving bfq_exit_bfqq() behind bic_set_bfqq(). Fixes: 64dc8c732f5c ("block, bfq: fix possible uaf for 'bfqq->bic'") Reported-by: Yi Zhang Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20221226030605.1437081-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Khazhismel Kumykov Signed-off-by: Sasha Levin --- block/bfq-iosched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index afaededb3c49..0a53b653a7e2 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4983,8 +4983,8 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync) unsigned long flags; spin_lock_irqsave(&bfqd->lock, flags); - bfq_exit_bfqq(bfqd, bfqq); bic_set_bfqq(bic, NULL, is_sync); + bfq_exit_bfqq(bfqd, bfqq); spin_unlock_irqrestore(&bfqd->lock, flags); } } From e6f03decf5b77214602ba2a1a6e33f1fb789bae3 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 13 Mar 2023 15:27:55 -0700 Subject: [PATCH 2097/4345] block/bfq-iosched.c: use "false" rather than "BLK_RW_ASYNC" [ Upstream commit f6bad159f5d5e5b33531aba3d9b860ad8618afe0 ] bfq_get_queue() expects a "bool" for the third arg, so pass "false" rather than "BLK_RW_ASYNC" which will soon be removed. Link: https://lkml.kernel.org/r/164549983746.9187.7949730109246767909.stgit@noble.brown Signed-off-by: NeilBrown Acked-by: Jens Axboe Cc: Anna Schumaker Cc: Chao Yu Cc: Darrick J. Wong Cc: Ilya Dryomov Cc: Jaegeuk Kim Cc: Jan Kara Cc: Jeff Layton Cc: Lars Ellenberg Cc: Miklos Szeredi Cc: Paolo Valente Cc: Philipp Reisner Cc: Ryusuke Konishi Cc: Trond Myklebust Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Stable-dep-of: b600de2d7d3a ("block, bfq: fix uaf for bfqq in bic_set_bfqq()") Signed-off-by: Sasha Levin Signed-off-by: Khazhismel Kumykov Signed-off-by: Sasha Levin --- block/bfq-iosched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 0a53b653a7e2..35b240cba092 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5071,7 +5071,7 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) bfqq = bic_to_bfqq(bic, false); if (bfqq) { bfq_release_process_ref(bfqd, bfqq); - bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic); + bfqq = bfq_get_queue(bfqd, bio, false, bic); bic_set_bfqq(bic, bfqq, false); } From 6291281f15e147428c95f0e053108086eba78f6e Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 13 Mar 2023 15:27:56 -0700 Subject: [PATCH 2098/4345] block, bfq: replace 0/1 with false/true in bic apis [ Upstream commit 337366e02b370d2800110fbc99940f6ddddcbdfa ] Just to make the code a litter cleaner, there are no functional changes. Signed-off-by: Yu Kuai Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20221214033155.3455754-3-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Stable-dep-of: b600de2d7d3a ("block, bfq: fix uaf for bfqq in bic_set_bfqq()") Signed-off-by: Sasha Levin Signed-off-by: Khazhismel Kumykov Signed-off-by: Sasha Levin --- block/bfq-cgroup.c | 8 ++++---- block/bfq-iosched.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index badb90352bf3..2f440b79183d 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -705,15 +705,15 @@ static void *__bfq_bic_change_cgroup(struct bfq_data *bfqd, struct bfq_io_cq *bic, struct bfq_group *bfqg) { - struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0); - struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1); + struct bfq_queue *async_bfqq = bic_to_bfqq(bic, false); + struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true); struct bfq_entity *entity; if (async_bfqq) { entity = &async_bfqq->entity; if (entity->sched_data != &bfqg->sched_data) { - bic_set_bfqq(bic, NULL, 0); + bic_set_bfqq(bic, NULL, false); bfq_release_process_ref(bfqd, async_bfqq); } } @@ -749,7 +749,7 @@ static void *__bfq_bic_change_cgroup(struct bfq_data *bfqd, */ bfq_put_cooperator(sync_bfqq); bfq_release_process_ref(bfqd, sync_bfqq); - bic_set_bfqq(bic, NULL, 1); + bic_set_bfqq(bic, NULL, true); } } } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 35b240cba092..016d7f32af9f 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2816,7 +2816,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, /* * Merge queues (that is, let bic redirect its requests to new_bfqq) */ - bic_set_bfqq(bic, new_bfqq, 1); + bic_set_bfqq(bic, new_bfqq, true); bfq_mark_bfqq_coop(new_bfqq); /* * new_bfqq now belongs to at least two bics (it is a shared queue): @@ -6014,7 +6014,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) return bfqq; } - bic_set_bfqq(bic, NULL, 1); + bic_set_bfqq(bic, NULL, true); bfq_put_cooperator(bfqq); From 7f77f3dab5066a7c9da73d72d1eee895ff84a8d5 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 13 Mar 2023 15:27:57 -0700 Subject: [PATCH 2099/4345] block, bfq: fix uaf for bfqq in bic_set_bfqq() [ Upstream commit b600de2d7d3a16f9007fad1bdae82a3951a26af2 ] After commit 64dc8c732f5c ("block, bfq: fix possible uaf for 'bfqq->bic'"), bic->bfqq will be accessed in bic_set_bfqq(), however, in some context bic->bfqq will be freed, and bic_set_bfqq() is called with the freed bic->bfqq. Fix the problem by always freeing bfqq after bic_set_bfqq(). Fixes: 64dc8c732f5c ("block, bfq: fix possible uaf for 'bfqq->bic'") Reported-and-tested-by: Shinichiro Kawasaki Signed-off-by: Yu Kuai Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230130014136.591038-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Khazhismel Kumykov Signed-off-by: Sasha Levin --- block/bfq-cgroup.c | 2 +- block/bfq-iosched.c | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 2f440b79183d..1f9ccc661d57 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -748,8 +748,8 @@ static void *__bfq_bic_change_cgroup(struct bfq_data *bfqd, * request from the old cgroup. */ bfq_put_cooperator(sync_bfqq); - bfq_release_process_ref(bfqd, sync_bfqq); bic_set_bfqq(bic, NULL, true); + bfq_release_process_ref(bfqd, sync_bfqq); } } } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 016d7f32af9f..6687b805bab3 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5070,9 +5070,11 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) bfqq = bic_to_bfqq(bic, false); if (bfqq) { - bfq_release_process_ref(bfqd, bfqq); + struct bfq_queue *old_bfqq = bfqq; + bfqq = bfq_get_queue(bfqd, bio, false, bic); bic_set_bfqq(bic, bfqq, false); + bfq_release_process_ref(bfqd, old_bfqq); } bfqq = bic_to_bfqq(bic, true); From 5ddcb0a348194b372e9f0d027ba7eedb6b5bd1e0 Mon Sep 17 00:00:00 2001 From: xurui Date: Wed, 18 Jan 2023 16:59:12 +0800 Subject: [PATCH 2100/4345] MIPS: Fix a compilation issue MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 109d587a4b4d7ccca2200ab1f808f43ae23e2585 ] arch/mips/include/asm/mach-rc32434/pci.h:377: cc1: error: result of ‘-117440512 << 16’ requires 44 bits to represent, but ‘int’ only has 32 bits [-Werror=shift-overflow=] All bits in KORINA_STAT are already at the correct position, so there is no addtional shift needed. Signed-off-by: xurui Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/include/asm/mach-rc32434/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/mach-rc32434/pci.h b/arch/mips/include/asm/mach-rc32434/pci.h index 9a6eefd12757..3eb767c8a4ee 100644 --- a/arch/mips/include/asm/mach-rc32434/pci.h +++ b/arch/mips/include/asm/mach-rc32434/pci.h @@ -374,7 +374,7 @@ struct pci_msu { PCI_CFG04_STAT_SSE | \ PCI_CFG04_STAT_PE) -#define KORINA_CNFG1 ((KORINA_STAT<<16)|KORINA_CMD) +#define KORINA_CNFG1 (KORINA_STAT | KORINA_CMD) #define KORINA_REVID 0 #define KORINA_CLASS_CODE 0 From 9a61a3a6ec660915b641dacc6ac40bb52cc9e06b Mon Sep 17 00:00:00 2001 From: Rohan McLure Date: Mon, 6 Feb 2023 13:17:58 +1100 Subject: [PATCH 2101/4345] powerpc/kcsan: Exclude udelay to prevent recursive instrumentation [ Upstream commit 2a7ce82dc46c591c9244057d89a6591c9639b9b9 ] In order for KCSAN to increase its likelihood of observing a data race, it sets a watchpoint on memory accesses and stalls, allowing for detection of conflicting accesses by other kernel threads or interrupts. Stalls are implemented by injecting a call to udelay in instrumented code. To prevent recursive instrumentation, exclude udelay from being instrumented. Signed-off-by: Rohan McLure Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230206021801.105268-3-rmclure@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/time.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 1d20f0f77a92..ba9b54d35f57 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -436,7 +436,7 @@ void vtime_flush(struct task_struct *tsk) #define calc_cputime_factors() #endif -void __delay(unsigned long loops) +void __no_kcsan __delay(unsigned long loops) { unsigned long start; @@ -457,7 +457,7 @@ void __delay(unsigned long loops) } EXPORT_SYMBOL(__delay); -void udelay(unsigned long usecs) +void __no_kcsan udelay(unsigned long usecs) { __delay(tb_ticks_per_usec * usecs); } From 9cff3f106a4cc59454c764eb3eff7c6237d649ab Mon Sep 17 00:00:00 2001 From: Edward Humes Date: Sat, 27 Aug 2022 02:49:39 -0400 Subject: [PATCH 2102/4345] alpha: fix R_ALPHA_LITERAL reloc for large modules [ Upstream commit b6b17a8b3ecd878d98d5472a9023ede9e669ca72 ] Previously, R_ALPHA_LITERAL relocations would overflow for large kernel modules. This was because the Alpha's apply_relocate_add was relying on the kernel's module loader to have sorted the GOT towards the very end of the module as it was mapped into memory in order to correctly assign the global pointer. While this behavior would mostly work fine for small kernel modules, this approach would overflow on kernel modules with large GOT's since the global pointer would be very far away from the GOT, and thus, certain entries would be out of range. This patch fixes this by instead using the Tru64 behavior of assigning the global pointer to be 32KB away from the start of the GOT. The change made in this patch won't work for multi-GOT kernel modules as it makes the assumption the module only has one GOT located at the beginning of .got, although for the vast majority kernel modules, this should be fine. Of the kernel modules that would previously result in a relocation error, none of them, even modules like nouveau, have even come close to filling up a single GOT, and they've all worked fine under this patch. Signed-off-by: Edward Humes Signed-off-by: Matt Turner Signed-off-by: Sasha Levin --- arch/alpha/kernel/module.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c index 5b60c248de9e..cbefa5a77384 100644 --- a/arch/alpha/kernel/module.c +++ b/arch/alpha/kernel/module.c @@ -146,10 +146,8 @@ apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, base = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr; symtab = (Elf64_Sym *)sechdrs[symindex].sh_addr; - /* The small sections were sorted to the end of the segment. - The following should definitely cover them. */ - gp = (u64)me->core_layout.base + me->core_layout.size - 0x8000; got = sechdrs[me->arch.gotsecindex].sh_addr; + gp = got + 0x8000; for (i = 0; i < n; i++) { unsigned long r_sym = ELF64_R_SYM (rela[i].r_info); From d47d364f6671d8794a89e4972b1fd3284d213c96 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 15 Feb 2023 10:12:12 -0700 Subject: [PATCH 2103/4345] macintosh: windfarm: Use unsigned type for 1-bit bitfields [ Upstream commit 748ea32d2dbd813d3bd958117bde5191182f909a ] Clang warns: drivers/macintosh/windfarm_lm75_sensor.c:63:14: error: implicit truncation from 'int' to a one-bit wide bit-field changes value from 1 to -1 [-Werror,-Wsingle-bit-bitfield-constant-conversion] lm->inited = 1; ^ ~ drivers/macintosh/windfarm_smu_sensors.c:356:19: error: implicit truncation from 'int' to a one-bit wide bit-field changes value from 1 to -1 [-Werror,-Wsingle-bit-bitfield-constant-conversion] pow->fake_volts = 1; ^ ~ drivers/macintosh/windfarm_smu_sensors.c:368:18: error: implicit truncation from 'int' to a one-bit wide bit-field changes value from 1 to -1 [-Werror,-Wsingle-bit-bitfield-constant-conversion] pow->quadratic = 1; ^ ~ There is no bug here since no code checks the actual value of these fields, just whether or not they are zero (boolean context), but this can be easily fixed by switching to an unsigned type. Signed-off-by: Nathan Chancellor Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230215-windfarm-wsingle-bit-bitfield-constant-conversion-v1-1-26415072e855@kernel.org Signed-off-by: Sasha Levin --- drivers/macintosh/windfarm_lm75_sensor.c | 4 ++-- drivers/macintosh/windfarm_smu_sensors.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/macintosh/windfarm_lm75_sensor.c b/drivers/macintosh/windfarm_lm75_sensor.c index 29f48c2028b6..e90ad1b78e93 100644 --- a/drivers/macintosh/windfarm_lm75_sensor.c +++ b/drivers/macintosh/windfarm_lm75_sensor.c @@ -34,8 +34,8 @@ #endif struct wf_lm75_sensor { - int ds1775 : 1; - int inited : 1; + unsigned int ds1775 : 1; + unsigned int inited : 1; struct i2c_client *i2c; struct wf_sensor sens; }; diff --git a/drivers/macintosh/windfarm_smu_sensors.c b/drivers/macintosh/windfarm_smu_sensors.c index c8706cfb83fd..714c1e14074e 100644 --- a/drivers/macintosh/windfarm_smu_sensors.c +++ b/drivers/macintosh/windfarm_smu_sensors.c @@ -273,8 +273,8 @@ struct smu_cpu_power_sensor { struct list_head link; struct wf_sensor *volts; struct wf_sensor *amps; - int fake_volts : 1; - int quadratic : 1; + unsigned int fake_volts : 1; + unsigned int quadratic : 1; struct wf_sensor sens; }; #define to_smu_cpu_power(c) container_of(c, struct smu_cpu_power_sensor, sens) From be658aa43a47c9a8e3462b01c7eb1420ba74d433 Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Tue, 10 Jan 2023 18:56:36 +0200 Subject: [PATCH 2104/4345] PCI: Add SolidRun vendor ID [ Upstream commit db6c4dee4c104f50ed163af71c53bfdb878a8318 ] Add SolidRun vendor ID to pci_ids.h The vendor ID is used in 2 different source files, the SNET vDPA driver and PCI quirks. Signed-off-by: Alvaro Karsz Acked-by: Bjorn Helgaas Message-Id: <20230110165638.123745-2-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 2e1935917c24..4b34a5c12599 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3115,6 +3115,8 @@ #define PCI_VENDOR_ID_3COM_2 0xa727 +#define PCI_VENDOR_ID_SOLIDRUN 0xd063 + #define PCI_VENDOR_ID_DIGIUM 0xd161 #define PCI_DEVICE_ID_DIGIUM_HFC4S 0xb410 From 42bb1e6b7fe8f826851eb4c5f1bac2b22a06a80b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 12 Jan 2023 11:30:06 +0900 Subject: [PATCH 2105/4345] scripts: handle BrokenPipeError for python scripts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 87c7ee67deb7fce9951a5f9d80641138694aad17 ] In the follow-up of commit fb3041d61f68 ("kbuild: fix SIGPIPE error message for AR=gcc-ar and AR=llvm-ar"), Kees Cook pointed out that tools should _not_ catch their own SIGPIPEs [1] [2]. Based on his feedback, LLVM was fixed [3]. However, Python's default behavior is to show noisy bracktrace when SIGPIPE is sent. So, scripts written in Python are basically in the same situation as the buggy llvm tools. Example: $ make -s allnoconfig $ make -s allmodconfig $ scripts/diffconfig .config.old .config | head -n1 -ALIX n Traceback (most recent call last): File "/home/masahiro/linux/scripts/diffconfig", line 132, in main() File "/home/masahiro/linux/scripts/diffconfig", line 130, in main print_config("+", config, None, b[config]) File "/home/masahiro/linux/scripts/diffconfig", line 64, in print_config print("+%s %s" % (config, new_value)) BrokenPipeError: [Errno 32] Broken pipe Python documentation [4] notes how to make scripts die immediately and silently: """ Piping output of your program to tools like head(1) will cause a SIGPIPE signal to be sent to your process when the receiver of its standard output closes early. This results in an exception like BrokenPipeError: [Errno 32] Broken pipe. To handle this case, wrap your entry point to catch this exception as follows: import os import sys def main(): try: # simulate large output (your code replaces this loop) for x in range(10000): print("y") # flush output here to force SIGPIPE to be triggered # while inside this try block. sys.stdout.flush() except BrokenPipeError: # Python flushes standard streams on exit; redirect remaining output # to devnull to avoid another BrokenPipeError at shutdown devnull = os.open(os.devnull, os.O_WRONLY) os.dup2(devnull, sys.stdout.fileno()) sys.exit(1) # Python exits with error code 1 on EPIPE if __name__ == '__main__': main() Do not set SIGPIPE’s disposition to SIG_DFL in order to avoid BrokenPipeError. Doing that would cause your program to exit unexpectedly whenever any socket connection is interrupted while your program is still writing to it. """ Currently, tools/perf/scripts/python/intel-pt-events.py seems to be the only script that fixes the issue that way. tools/perf/scripts/python/compaction-times.py uses another approach signal.signal(signal.SIGPIPE, signal.SIG_DFL) but the Python documentation clearly says "Don't do it". I cannot fix all Python scripts since there are so many. I fixed some in the scripts/ directory. [1]: https://lore.kernel.org/all/202211161056.1B9611A@keescook/ [2]: https://github.com/llvm/llvm-project/issues/59037 [3]: https://github.com/llvm/llvm-project/commit/4787efa38066adb51e2c049499d25b3610c0877b [4]: https://docs.python.org/3/library/signal.html#note-on-sigpipe Signed-off-by: Masahiro Yamada Reviewed-by: Nick Desaulniers Reviewed-by: Nicolas Schier Signed-off-by: Sasha Levin --- scripts/checkkconfigsymbols.py | 13 ++++++++++++- scripts/clang-tools/run-clang-tools.py | 21 ++++++++++++++------- scripts/diffconfig | 16 ++++++++++++++-- 3 files changed, 40 insertions(+), 10 deletions(-) diff --git a/scripts/checkkconfigsymbols.py b/scripts/checkkconfigsymbols.py index 1548f9ce4682..697972432bbe 100755 --- a/scripts/checkkconfigsymbols.py +++ b/scripts/checkkconfigsymbols.py @@ -113,7 +113,7 @@ def parse_options(): return args -def main(): +def print_undefined_symbols(): """Main function of this module.""" args = parse_options() @@ -472,5 +472,16 @@ def parse_kconfig_file(kfile): return defined, references +def main(): + try: + print_undefined_symbols() + except BrokenPipeError: + # Python flushes standard streams on exit; redirect remaining output + # to devnull to avoid another BrokenPipeError at shutdown + devnull = os.open(os.devnull, os.O_WRONLY) + os.dup2(devnull, sys.stdout.fileno()) + sys.exit(1) # Python exits with error code 1 on EPIPE + + if __name__ == "__main__": main() diff --git a/scripts/clang-tools/run-clang-tools.py b/scripts/clang-tools/run-clang-tools.py index f754415af398..f42699134f1c 100755 --- a/scripts/clang-tools/run-clang-tools.py +++ b/scripts/clang-tools/run-clang-tools.py @@ -60,14 +60,21 @@ def run_analysis(entry): def main(): - args = parse_arguments() + try: + args = parse_arguments() - lock = multiprocessing.Lock() - pool = multiprocessing.Pool(initializer=init, initargs=(lock, args)) - # Read JSON data into the datastore variable - with open(args.path, "r") as f: - datastore = json.load(f) - pool.map(run_analysis, datastore) + lock = multiprocessing.Lock() + pool = multiprocessing.Pool(initializer=init, initargs=(lock, args)) + # Read JSON data into the datastore variable + with open(args.path, "r") as f: + datastore = json.load(f) + pool.map(run_analysis, datastore) + except BrokenPipeError: + # Python flushes standard streams on exit; redirect remaining output + # to devnull to avoid another BrokenPipeError at shutdown + devnull = os.open(os.devnull, os.O_WRONLY) + os.dup2(devnull, sys.stdout.fileno()) + sys.exit(1) # Python exits with error code 1 on EPIPE if __name__ == "__main__": diff --git a/scripts/diffconfig b/scripts/diffconfig index d5da5fa05d1d..43f0f3d273ae 100755 --- a/scripts/diffconfig +++ b/scripts/diffconfig @@ -65,7 +65,7 @@ def print_config(op, config, value, new_value): else: print(" %s %s -> %s" % (config, value, new_value)) -def main(): +def show_diff(): global merge_style # parse command line args @@ -129,4 +129,16 @@ def main(): for config in new: print_config("+", config, None, b[config]) -main() +def main(): + try: + show_diff() + except BrokenPipeError: + # Python flushes standard streams on exit; redirect remaining output + # to devnull to avoid another BrokenPipeError at shutdown + devnull = os.open(os.devnull, os.O_WRONLY) + os.dup2(devnull, sys.stdout.fileno()) + sys.exit(1) # Python exits with error code 1 on EPIPE + + +if __name__ == '__main__': + main() From 13b04efb5bd011570a392a912df3e6109e414a9c Mon Sep 17 00:00:00 2001 From: Paul Elder Date: Mon, 28 Nov 2022 09:02:01 +0100 Subject: [PATCH 2106/4345] media: ov5640: Fix analogue gain control [ Upstream commit afa4805799c1d332980ad23339fdb07b5e0cf7e0 ] Gain control is badly documented in publicly available (including leaked) documentation. There is an AGC pre-gain in register 0x3a13, expressed as a 6-bit value (plus an enable bit in bit 6). The driver hardcodes it to 0x43, which one application note states is equal to x1.047. The documentation also states that 0x40 is equel to x1.000. The pre-gain thus seems to be expressed as in 1/64 increments, and thus ranges from x1.00 to x1.984. What the pre-gain does is however unspecified. There is then an AGC gain limit, in registers 0x3a18 and 0x3a19, expressed as a 10-bit "real gain format" value. One application note sets it to 0x00f8 and states it is equal to x15.5, so it appears to be expressed in 1/16 increments, up to x63.9375. The manual gain is stored in registers 0x350a and 0x350b, also as a 10-bit "real gain format" value. It is documented in the application note as a Q6.4 values, up to x63.9375. One version of the datasheet indicates that the sensor supports a digital gain: The OV5640 supports 1/2/4 digital gain. Normally, the gain is controlled automatically by the automatic gain control (AGC) block. It isn't clear how that would be controlled manually. There appears to be no indication regarding whether the gain controlled through registers 0x350a and 0x350b is an analogue gain only or also includes digital gain. The words "real gain" don't necessarily mean "combined analogue and digital gains". Some OmniVision sensors (such as the OV8858) are documented as supoprting different formats for the gain values, selectable through a register bit, and they are called "real gain format" and "sensor gain format". For that sensor, we have (one of) the gain registers documented as 0x3503[2]=0, gain[7:0] is real gain format, where low 4 bits are fraction bits, for example, 0x10 is 1x gain, 0x28 is 2.5x gain If 0x3503[2]=1, gain[7:0] is sensor gain format, gain[7:4] is coarse gain, 00000: 1x, 00001: 2x, 00011: 4x, 00111: 8x, gain[7] is 1, gain[3:0] is fine gain. For example, 0x10 is 1x gain, 0x30 is 2x gain, 0x70 is 4x gain (The second part of the text makes little sense) "Real gain" may thus refer to the combination of the coarse and fine analogue gains as a single value. The OV5640 0x350a and 0x350b registers thus appear to control analogue gain. The driver incorrectly uses V4L2_CID_GAIN as V4L2 has a specific control for analogue gain, V4L2_CID_ANALOGUE_GAIN. Use it. If registers 0x350a and 0x350b are later found to control digital gain as well, the driver could then restrict the range of the analogue gain control value to lower than x64 and add a separate digital gain control. Signed-off-by: Paul Elder Signed-off-by: Laurent Pinchart Reviewed-by: Jacopo Mondi Reviewed-by: Jai Luthra Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/ov5640.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c index 8f0812e85901..92a5f9aff9b5 100644 --- a/drivers/media/i2c/ov5640.c +++ b/drivers/media/i2c/ov5640.c @@ -2748,7 +2748,7 @@ static int ov5640_init_controls(struct ov5640_dev *sensor) /* Auto/manual gain */ ctrls->auto_gain = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_AUTOGAIN, 0, 1, 1, 1); - ctrls->gain = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_GAIN, + ctrls->gain = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_ANALOGUE_GAIN, 0, 1023, 1, 0); ctrls->saturation = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_SATURATION, From a5c140d88a69eb43de2a030f1d7ff7b16bff3b1a Mon Sep 17 00:00:00 2001 From: Li Jun Date: Wed, 11 Jan 2023 10:39:21 +0100 Subject: [PATCH 2107/4345] media: rc: gpio-ir-recv: add remove function [ Upstream commit 30040818b338b8ebc956ce0ebd198f8d593586a6 ] In case runtime PM is enabled, do runtime PM clean up to remove cpu latency qos request, otherwise driver removal may have below kernel dump: [ 19.463299] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000048 [ 19.472161] Mem abort info: [ 19.474985] ESR = 0x0000000096000004 [ 19.478754] EC = 0x25: DABT (current EL), IL = 32 bits [ 19.484081] SET = 0, FnV = 0 [ 19.487149] EA = 0, S1PTW = 0 [ 19.490361] FSC = 0x04: level 0 translation fault [ 19.495256] Data abort info: [ 19.498149] ISV = 0, ISS = 0x00000004 [ 19.501997] CM = 0, WnR = 0 [ 19.504977] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000049f81000 [ 19.511432] [0000000000000048] pgd=0000000000000000, p4d=0000000000000000 [ 19.518245] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP [ 19.524520] Modules linked in: gpio_ir_recv(+) rc_core [last unloaded: rc_core] [ 19.531845] CPU: 0 PID: 445 Comm: insmod Not tainted 6.2.0-rc1-00028-g2c397a46d47c #72 [ 19.531854] Hardware name: FSL i.MX8MM EVK board (DT) [ 19.531859] pstate: 80000005 (Nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 19.551777] pc : cpu_latency_qos_remove_request+0x20/0x110 [ 19.557277] lr : gpio_ir_recv_runtime_suspend+0x18/0x30 [gpio_ir_recv] [ 19.557294] sp : ffff800008ce3740 [ 19.557297] x29: ffff800008ce3740 x28: 0000000000000000 x27: ffff800008ce3d50 [ 19.574270] x26: ffffc7e3e9cea100 x25: 00000000000f4240 x24: ffffc7e3f9ef0e30 [ 19.574284] x23: 0000000000000000 x22: ffff0061803820f4 x21: 0000000000000008 [ 19.574296] x20: ffffc7e3fa75df30 x19: 0000000000000020 x18: ffffffffffffffff [ 19.588570] x17: 0000000000000000 x16: ffffc7e3f9efab70 x15: ffffffffffffffff [ 19.595712] x14: ffff800008ce37b8 x13: ffff800008ce37aa x12: 0000000000000001 [ 19.602853] x11: 0000000000000001 x10: ffffcbe3ec0dff87 x9 : 0000000000000008 [ 19.609991] x8 : 0101010101010101 x7 : 0000000000000000 x6 : 000000000f0bfe9f [ 19.624261] x5 : 00ffffffffffffff x4 : 0025ab8e00000000 x3 : ffff006180382010 [ 19.631405] x2 : ffffc7e3e9ce8030 x1 : ffffc7e3fc3eb810 x0 : 0000000000000020 [ 19.638548] Call trace: [ 19.640995] cpu_latency_qos_remove_request+0x20/0x110 [ 19.646142] gpio_ir_recv_runtime_suspend+0x18/0x30 [gpio_ir_recv] [ 19.652339] pm_generic_runtime_suspend+0x2c/0x44 [ 19.657055] __rpm_callback+0x48/0x1dc [ 19.660807] rpm_callback+0x6c/0x80 [ 19.664301] rpm_suspend+0x10c/0x640 [ 19.667880] rpm_idle+0x250/0x2d0 [ 19.671198] update_autosuspend+0x38/0xe0 [ 19.675213] pm_runtime_set_autosuspend_delay+0x40/0x60 [ 19.680442] gpio_ir_recv_probe+0x1b4/0x21c [gpio_ir_recv] [ 19.685941] platform_probe+0x68/0xc0 [ 19.689610] really_probe+0xc0/0x3dc [ 19.693189] __driver_probe_device+0x7c/0x190 [ 19.697550] driver_probe_device+0x3c/0x110 [ 19.701739] __driver_attach+0xf4/0x200 [ 19.705578] bus_for_each_dev+0x70/0xd0 [ 19.709417] driver_attach+0x24/0x30 [ 19.712998] bus_add_driver+0x17c/0x240 [ 19.716834] driver_register+0x78/0x130 [ 19.720676] __platform_driver_register+0x28/0x34 [ 19.725386] gpio_ir_recv_driver_init+0x20/0x1000 [gpio_ir_recv] [ 19.731404] do_one_initcall+0x44/0x2ac [ 19.735243] do_init_module+0x48/0x1d0 [ 19.739003] load_module+0x19fc/0x2034 [ 19.742759] __do_sys_finit_module+0xac/0x12c [ 19.747124] __arm64_sys_finit_module+0x20/0x30 [ 19.751664] invoke_syscall+0x48/0x114 [ 19.755420] el0_svc_common.constprop.0+0xcc/0xec [ 19.760132] do_el0_svc+0x38/0xb0 [ 19.763456] el0_svc+0x2c/0x84 [ 19.766516] el0t_64_sync_handler+0xf4/0x120 [ 19.770789] el0t_64_sync+0x190/0x194 [ 19.774460] Code: 910003fd a90153f3 aa0003f3 91204021 (f9401400) [ 19.780556] ---[ end trace 0000000000000000 ]--- Signed-off-by: Li Jun Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/rc/gpio-ir-recv.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/media/rc/gpio-ir-recv.c b/drivers/media/rc/gpio-ir-recv.c index 22e524b69806..a56c844d7f81 100644 --- a/drivers/media/rc/gpio-ir-recv.c +++ b/drivers/media/rc/gpio-ir-recv.c @@ -130,6 +130,23 @@ static int gpio_ir_recv_probe(struct platform_device *pdev) "gpio-ir-recv-irq", gpio_dev); } +static int gpio_ir_recv_remove(struct platform_device *pdev) +{ + struct gpio_rc_dev *gpio_dev = platform_get_drvdata(pdev); + struct device *pmdev = gpio_dev->pmdev; + + if (pmdev) { + pm_runtime_get_sync(pmdev); + cpu_latency_qos_remove_request(&gpio_dev->qos); + + pm_runtime_disable(pmdev); + pm_runtime_put_noidle(pmdev); + pm_runtime_set_suspended(pmdev); + } + + return 0; +} + #ifdef CONFIG_PM static int gpio_ir_recv_suspend(struct device *dev) { @@ -189,6 +206,7 @@ MODULE_DEVICE_TABLE(of, gpio_ir_recv_of_match); static struct platform_driver gpio_ir_recv_driver = { .probe = gpio_ir_recv_probe, + .remove = gpio_ir_recv_remove, .driver = { .name = KBUILD_MODNAME, .of_match_table = of_match_ptr(gpio_ir_recv_of_match), From 7aa5a495cbf8a33cd9fec892c180dedf14292b76 Mon Sep 17 00:00:00 2001 From: Yejune Deng Date: Mon, 16 Nov 2020 15:30:07 +0800 Subject: [PATCH 2108/4345] ipmi/watchdog: replace atomic_add() and atomic_sub() commit a01a89b1db1066a6af23ae08b9a0c345b7966f0b upstream. atomic_inc() and atomic_dec() looks better Signed-off-by: Yejune Deng Message-Id: <1605511807-7135-1-git-send-email-yejune.deng@gmail.com> Signed-off-by: Corey Minyard Signed-off-by: Greg Kroah-Hartman --- drivers/char/ipmi/ipmi_watchdog.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 92eda5b2f134..7f71471c7a46 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -503,7 +503,7 @@ static void panic_halt_ipmi_heartbeat(void) msg.cmd = IPMI_WDOG_RESET_TIMER; msg.data = NULL; msg.data_len = 0; - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = ipmi_request_supply_msgs(watchdog_user, (struct ipmi_addr *) &addr, 0, @@ -513,7 +513,7 @@ static void panic_halt_ipmi_heartbeat(void) &panic_halt_heartbeat_recv_msg, 1); if (rv) - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); } static struct ipmi_smi_msg panic_halt_smi_msg = { @@ -537,12 +537,12 @@ static void panic_halt_ipmi_set_timeout(void) /* Wait for the messages to be free. */ while (atomic_read(&panic_done_count) != 0) ipmi_poll_interface(watchdog_user); - atomic_add(1, &panic_done_count); + atomic_inc(&panic_done_count); rv = __ipmi_set_timeout(&panic_halt_smi_msg, &panic_halt_recv_msg, &send_heartbeat_now); if (rv) { - atomic_sub(1, &panic_done_count); + atomic_dec(&panic_done_count); pr_warn("Unable to extend the watchdog timeout\n"); } else { if (send_heartbeat_now) From a4932a2c544607640ddab7f3275726e364a897bf Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Mon, 20 Sep 2021 06:25:37 -0500 Subject: [PATCH 2109/4345] ipmi:watchdog: Set panic count to proper value on a panic commit db05ddf7f321634c5659a0cf7ea56594e22365f7 upstream. You will get two decrements when the messages on a panic are sent, not one, since commit 2033f6858970 ("ipmi: Free receive messages when in an oops") was added, but the watchdog code had a bug where it didn't set the value properly. Reported-by: Anton Lundin Cc: # v5.4+ Fixes: 2033f6858970 ("ipmi: Free receive messages when in an oops") Signed-off-by: Corey Minyard Signed-off-by: Greg Kroah-Hartman --- drivers/char/ipmi/ipmi_watchdog.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 7f71471c7a46..883b4a341012 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -503,7 +503,7 @@ static void panic_halt_ipmi_heartbeat(void) msg.cmd = IPMI_WDOG_RESET_TIMER; msg.data = NULL; msg.data_len = 0; - atomic_inc(&panic_done_count); + atomic_add(2, &panic_done_count); rv = ipmi_request_supply_msgs(watchdog_user, (struct ipmi_addr *) &addr, 0, @@ -513,7 +513,7 @@ static void panic_halt_ipmi_heartbeat(void) &panic_halt_heartbeat_recv_msg, 1); if (rv) - atomic_dec(&panic_done_count); + atomic_sub(2, &panic_done_count); } static struct ipmi_smi_msg panic_halt_smi_msg = { @@ -537,12 +537,12 @@ static void panic_halt_ipmi_set_timeout(void) /* Wait for the messages to be free. */ while (atomic_read(&panic_done_count) != 0) ipmi_poll_interface(watchdog_user); - atomic_inc(&panic_done_count); + atomic_add(2, &panic_done_count); rv = __ipmi_set_timeout(&panic_halt_smi_msg, &panic_halt_recv_msg, &send_heartbeat_now); if (rv) { - atomic_dec(&panic_done_count); + atomic_sub(2, &panic_done_count); pr_warn("Unable to extend the watchdog timeout\n"); } else { if (send_heartbeat_now) From c53d50d8081a49ba21f866a51277a012b9efad8e Mon Sep 17 00:00:00 2001 From: Tao Liu Date: Tue, 14 Mar 2023 20:10:17 +0800 Subject: [PATCH 2110/4345] skbuff: Fix nfct leak on napi stolen Upstream commit [0] had fixed this issue, and backported to kernel 5.10.54. However, nf_reset_ct() added in skb_release_head_state() instead of napi_skb_free_stolen_head(), which lead to leakage still exist in 5.10. [0] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=8550ff8d8c75416e984d9c4b082845e57e560984 Fixes: 570341f10ecc ("skbuff: Release nfct refcount on napi stolen or re-used skbs")) Signed-off-by: Tao Liu Signed-off-by: Greg Kroah-Hartman --- net/core/dev.c | 1 + net/core/skbuff.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 8cbcb6a104f2..413c2a08d79d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6111,6 +6111,7 @@ EXPORT_SYMBOL(gro_find_complete_by_type); static void napi_skb_free_stolen_head(struct sk_buff *skb) { + nf_reset_ct(skb); skb_dst_drop(skb); skb_ext_put(skb); kmem_cache_free(skbuff_head_cache, skb); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 668a9d0fbbc6..09cdefe5e1c8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -659,7 +659,6 @@ fastpath: void skb_release_head_state(struct sk_buff *skb) { - nf_reset_ct(skb); skb_dst_drop(skb); if (skb->destructor) { WARN_ON(in_irq()); From b5005605013d30ab27c303cbaeff60b7872234a3 Mon Sep 17 00:00:00 2001 From: John Harrison Date: Wed, 15 Feb 2023 17:11:01 -0800 Subject: [PATCH 2111/4345] drm/i915: Don't use BAR mappings for ring buffers with LLC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 85636167e3206c3fbd52254fc432991cc4e90194 upstream. Direction from hardware is that ring buffers should never be mapped via the BAR on systems with LLC. There are too many caching pitfalls due to the way BAR accesses are routed. So it is safest to just not use it. Signed-off-by: John Harrison Fixes: 9d80841ea4c9 ("drm/i915: Allow ringbuffers to be bound anywhere") Cc: Chris Wilson Cc: Joonas Lahtinen Cc: Jani Nikula Cc: Rodrigo Vivi Cc: Tvrtko Ursulin Cc: intel-gfx@lists.freedesktop.org Cc: # v4.9+ Tested-by: Jouni Högander Reviewed-by: Daniele Ceraolo Spurio Link: https://patchwork.freedesktop.org/patch/msgid/20230216011101.1909009-3-John.C.Harrison@Intel.com (cherry picked from commit 65c08339db1ada87afd6cfe7db8e60bb4851d919) Signed-off-by: Jani Nikula Signed-off-by: John Harrison Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gt/intel_ring.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c index 4034a4bac7f0..69b2e5509d67 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.c +++ b/drivers/gpu/drm/i915/gt/intel_ring.c @@ -49,7 +49,7 @@ int intel_ring_pin(struct intel_ring *ring, struct i915_gem_ww_ctx *ww) if (unlikely(ret)) goto err_unpin; - if (i915_vma_is_map_and_fenceable(vma)) + if (i915_vma_is_map_and_fenceable(vma) && !HAS_LLC(vma->vm->i915)) addr = (void __force *)i915_vma_pin_iomap(vma); else addr = i915_gem_object_pin_map(vma->obj, @@ -91,7 +91,7 @@ void intel_ring_unpin(struct intel_ring *ring) return; i915_vma_unset_ggtt_write(vma); - if (i915_vma_is_map_and_fenceable(vma)) + if (i915_vma_is_map_and_fenceable(vma) && !HAS_LLC(vma->vm->i915)) i915_vma_unpin_iomap(vma); else i915_gem_object_unpin_map(vma->obj); From 9cd21f5babb51e0eccb4bd18db890419971fe9d3 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 16 Feb 2022 12:32:45 +0530 Subject: [PATCH 2112/4345] ext4: refactor ext4_free_blocks() to pull out ext4_mb_clear_bb() commit 8ac3939db99f99667b8eb670cf4baf292896e72d upstream. ext4_free_blocks() function became too long and confusing, this patch just pulls out the ext4_mb_clear_bb() function logic from it which clears the block bitmap and frees it. No functionality change in this patch Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/22c30fbb26ba409cf8aa5f0c7912970272c459e8.1644992610.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- fs/ext4/mballoc.c | 180 ++++++++++++++++++++++++++-------------------- 1 file changed, 102 insertions(+), 78 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index d5ca02a7766e..0870f0436946 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5303,7 +5303,8 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, } /** - * ext4_free_blocks() -- Free given blocks and update quota + * ext4_mb_clear_bb() -- helper function for freeing blocks. + * Used by ext4_free_blocks() * @handle: handle for this transaction * @inode: inode * @bh: optional buffer of the block to be freed @@ -5311,9 +5312,9 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ -void ext4_free_blocks(handle_t *handle, struct inode *inode, - struct buffer_head *bh, ext4_fsblk_t block, - unsigned long count, int flags) +static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, + ext4_fsblk_t block, unsigned long count, + int flags) { struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; @@ -5330,80 +5331,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); - if (sbi->s_mount_state & EXT4_FC_REPLAY) { - ext4_free_blocks_simple(inode, block, count); - return; - } - - might_sleep(); - if (bh) { - if (block) - BUG_ON(block != bh->b_blocknr); - else - block = bh->b_blocknr; - } - - if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && - !ext4_inode_block_valid(inode, block, count)) { - ext4_error(sb, "Freeing blocks not in datazone - " - "block = %llu, count = %lu", block, count); - goto error_return; - } - - ext4_debug("freeing block %llu\n", block); - trace_ext4_free_blocks(inode, block, count, flags); - - if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { - BUG_ON(count > 1); - - ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, - inode, bh, block); - } - - /* - * If the extent to be freed does not begin on a cluster - * boundary, we need to deal with partial clusters at the - * beginning and end of the extent. Normally we will free - * blocks at the beginning or the end unless we are explicitly - * requested to avoid doing so. - */ - overflow = EXT4_PBLK_COFF(sbi, block); - if (overflow) { - if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { - overflow = sbi->s_cluster_ratio - overflow; - block += overflow; - if (count > overflow) - count -= overflow; - else - return; - } else { - block -= overflow; - count += overflow; - } - } - overflow = EXT4_LBLK_COFF(sbi, count); - if (overflow) { - if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { - if (count > overflow) - count -= overflow; - else - return; - } else - count += sbi->s_cluster_ratio - overflow; - } - - if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { - int i; - int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; - - for (i = 0; i < count; i++) { - cond_resched(); - if (is_metadata) - bh = sb_find_get_block(inode->i_sb, block + i); - ext4_forget(handle, is_metadata, inode, bh, block + i); - } - } - do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -5570,6 +5497,103 @@ error_return: return; } +/** + * ext4_free_blocks() -- Free given blocks and update quota + * @handle: handle for this transaction + * @inode: inode + * @bh: optional buffer of the block to be freed + * @block: starting physical block to be freed + * @count: number of blocks to be freed + * @flags: flags used by ext4_free_blocks + */ +void ext4_free_blocks(handle_t *handle, struct inode *inode, + struct buffer_head *bh, ext4_fsblk_t block, + unsigned long count, int flags) +{ + struct super_block *sb = inode->i_sb; + unsigned int overflow; + struct ext4_sb_info *sbi; + + sbi = EXT4_SB(sb); + + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + ext4_free_blocks_simple(inode, block, count); + return; + } + + might_sleep(); + if (bh) { + if (block) + BUG_ON(block != bh->b_blocknr); + else + block = bh->b_blocknr; + } + + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { + ext4_error(sb, "Freeing blocks not in datazone - " + "block = %llu, count = %lu", block, count); + return; + } + + ext4_debug("freeing block %llu\n", block); + trace_ext4_free_blocks(inode, block, count, flags); + + if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + BUG_ON(count > 1); + + ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, + inode, bh, block); + } + + /* + * If the extent to be freed does not begin on a cluster + * boundary, we need to deal with partial clusters at the + * beginning and end of the extent. Normally we will free + * blocks at the beginning or the end unless we are explicitly + * requested to avoid doing so. + */ + overflow = EXT4_PBLK_COFF(sbi, block); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { + overflow = sbi->s_cluster_ratio - overflow; + block += overflow; + if (count > overflow) + count -= overflow; + else + return; + } else { + block -= overflow; + count += overflow; + } + } + overflow = EXT4_LBLK_COFF(sbi, count); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { + if (count > overflow) + count -= overflow; + else + return; + } else + count += sbi->s_cluster_ratio - overflow; + } + + if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + int i; + int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; + + for (i = 0; i < count; i++) { + cond_resched(); + if (is_metadata) + bh = sb_find_get_block(inode->i_sb, block + i); + ext4_forget(handle, is_metadata, inode, bh, block + i); + } + } + + ext4_mb_clear_bb(handle, inode, block, count, flags); + return; +} + /** * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction From 65061f49a50f8a303af61e9328e94a6c51ea4ab1 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 16 Feb 2022 12:32:49 +0530 Subject: [PATCH 2113/4345] ext4: add ext4_sb_block_valid() refactored out of ext4_inode_block_valid() commit 6bc6c2bdf1baca6522b8d9ba976257d722423085 upstream. This API will be needed at places where we don't have an inode for e.g. while freeing blocks in ext4_group_add_blocks() Suggested-by: Jan Kara Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/dd34a236543ad5ae7123eeebe0cb69e6bdd44f34.1644992610.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- fs/ext4/block_validity.c | 26 +++++++++++++++++--------- fs/ext4/ext4.h | 3 +++ 2 files changed, 20 insertions(+), 9 deletions(-) diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 8e6ca23ed172..eed5b855dd94 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -294,15 +294,10 @@ void ext4_release_system_zone(struct super_block *sb) call_rcu(&system_blks->rcu, ext4_destroy_system_zone); } -/* - * Returns 1 if the passed-in block region (start_blk, - * start_blk+count) is valid; 0 if some part of the block region - * overlaps with some other filesystem metadata blocks. - */ -int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, - unsigned int count) +int ext4_sb_block_valid(struct super_block *sb, struct inode *inode, + ext4_fsblk_t start_blk, unsigned int count) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_system_blocks *system_blks; struct ext4_system_zone *entry; struct rb_node *n; @@ -331,7 +326,9 @@ int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, else if (start_blk >= (entry->start_blk + entry->count)) n = n->rb_right; else { - ret = (entry->ino == inode->i_ino); + ret = 0; + if (inode) + ret = (entry->ino == inode->i_ino); break; } } @@ -340,6 +337,17 @@ out_rcu: return ret; } +/* + * Returns 1 if the passed-in block region (start_blk, + * start_blk+count) is valid; 0 if some part of the block region + * overlaps with some other filesystem metadata blocks. + */ +int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, + unsigned int count) +{ + return ext4_sb_block_valid(inode->i_sb, inode, start_blk, count); +} + int ext4_check_blockref(const char *function, unsigned int line, struct inode *inode, __le32 *p, unsigned int max) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 81dc61f1c557..246573a4e804 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3536,6 +3536,9 @@ extern int ext4_inode_block_valid(struct inode *inode, unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); +extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode, + ext4_fsblk_t start_blk, unsigned int count); + /* extents.c */ struct ext4_ext_path; From c3fd717b58f0a3e2461c16e2360ee6a949b47940 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 16 Feb 2022 12:32:50 +0530 Subject: [PATCH 2114/4345] ext4: add strict range checks while freeing blocks commit a00b482b82fb098956a5bed22bd7873e56f152f1 upstream. Currently ext4_mb_clear_bb() & ext4_group_add_blocks() only checks whether the given block ranges (which is to be freed) belongs to any FS metadata blocks or not, of the block's respective block group. But to detect any FS error early, it is better to add more strict checkings in those functions which checks whether the given blocks belongs to any critical FS metadata or not within system-zone. Suggested-by: Jan Kara Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/ddd9143d064774e32d6364a99667817c6e8bfdc0.1644992610.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- fs/ext4/mballoc.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 0870f0436946..b98d77c8b002 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5361,13 +5361,7 @@ do_more: goto error_return; } - if (in_range(ext4_block_bitmap(sb, gdp), block, count) || - in_range(ext4_inode_bitmap(sb, gdp), block, count) || - in_range(block, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group) || - in_range(block + count - 1, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group)) { - + if (!ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ @@ -5437,7 +5431,7 @@ do_more: NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" - " group:%d block:%d count:%lu failed" + " group:%u block:%d count:%lu failed" " with %d", block_group, bit, count, err); } else @@ -5650,11 +5644,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, goto error_return; } - if (in_range(ext4_block_bitmap(sb, desc), block, count) || - in_range(ext4_inode_bitmap(sb, desc), block, count) || - in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) || - in_range(block + count - 1, ext4_inode_table(sb, desc), - sbi->s_itb_per_group)) { + if (!ext4_sb_block_valid(sb, NULL, block, count)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); From 7550aade978371ac582f6d43b14c4cb89ca54463 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Thu, 14 Jul 2022 18:59:03 +0200 Subject: [PATCH 2115/4345] ext4: block range must be validated before use in ext4_mb_clear_bb() commit 1e1c2b86ef86a8477fd9b9a4f48a6bfe235606f6 upstream. Block range to free is validated in ext4_free_blocks() using ext4_inode_block_valid() and then it's passed to ext4_mb_clear_bb(). However in some situations on bigalloc file system the range might be adjusted after the validation in ext4_free_blocks() which can lead to troubles on corrupted file systems such as one found by syzkaller that resulted in the following BUG kernel BUG at fs/ext4/ext4.h:3319! PREEMPT SMP NOPTI CPU: 28 PID: 4243 Comm: repro Kdump: loaded Not tainted 5.19.0-rc6+ #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1.fc35 04/01/2014 RIP: 0010:ext4_free_blocks+0x95e/0xa90 Call Trace: ? lock_timer_base+0x61/0x80 ? __es_remove_extent+0x5a/0x760 ? __mod_timer+0x256/0x380 ? ext4_ind_truncate_ensure_credits+0x90/0x220 ext4_clear_blocks+0x107/0x1b0 ext4_free_data+0x15b/0x170 ext4_ind_truncate+0x214/0x2c0 ? _raw_spin_unlock+0x15/0x30 ? ext4_discard_preallocations+0x15a/0x410 ? ext4_journal_check_start+0xe/0x90 ? __ext4_journal_start_sb+0x2f/0x110 ext4_truncate+0x1b5/0x460 ? __ext4_journal_start_sb+0x2f/0x110 ext4_evict_inode+0x2b4/0x6f0 evict+0xd0/0x1d0 ext4_enable_quotas+0x11f/0x1f0 ext4_orphan_cleanup+0x3de/0x430 ? proc_create_seq_private+0x43/0x50 ext4_fill_super+0x295f/0x3ae0 ? snprintf+0x39/0x40 ? sget_fc+0x19c/0x330 ? ext4_reconfigure+0x850/0x850 get_tree_bdev+0x16d/0x260 vfs_get_tree+0x25/0xb0 path_mount+0x431/0xa70 __x64_sys_mount+0xe2/0x120 do_syscall_64+0x5b/0x80 ? do_user_addr_fault+0x1e2/0x670 ? exc_page_fault+0x70/0x170 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fdf4e512ace Fix it by making sure that the block range is properly validated before used every time it changes in ext4_free_blocks() or ext4_mb_clear_bb(). Link: https://syzkaller.appspot.com/bug?id=5266d464285a03cee9dbfda7d2452a72c3c2ae7c Reported-by: syzbot+15cd994e273307bf5cfa@syzkaller.appspotmail.com Signed-off-by: Lukas Czerner Cc: Tadeusz Struk Tested-by: Tadeusz Struk Link: https://lore.kernel.org/r/20220714165903.58260-1-lczerner@redhat.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- fs/ext4/mballoc.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index b98d77c8b002..843840c2aced 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5331,6 +5331,15 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { + ext4_error(sb, "Freeing blocks in system zone - " + "Block = %llu, count = %lu", block, count); + /* err = 0. ext4_std_error should be a no op */ + goto error_return; + } + flags |= EXT4_FREE_BLOCKS_VALIDATED; + do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -5347,6 +5356,8 @@ do_more: overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); bitmap_bh = ext4_read_block_bitmap(sb, block_group); @@ -5361,7 +5372,8 @@ do_more: goto error_return; } - if (!ext4_inode_block_valid(inode, block, count)) { + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ @@ -5483,6 +5495,8 @@ do_more: block += count; count = overflow; put_bh(bitmap_bh); + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } error_return: @@ -5529,6 +5543,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, "block = %llu, count = %lu", block, count); return; } + flags |= EXT4_FREE_BLOCKS_VALIDATED; ext4_debug("freeing block %llu\n", block); trace_ext4_free_blocks(inode, block, count, flags); @@ -5560,6 +5575,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, block -= overflow; count += overflow; } + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { @@ -5570,6 +5587,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, return; } else count += sbi->s_cluster_ratio - overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { From d367c5ebe94359b0ac38c0d91c4c10654460bb03 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 1 Mar 2023 19:04:52 -0700 Subject: [PATCH 2116/4345] arch: fix broken BuildID for arm64 and riscv commit 99cb0d917ffa1ab628bb67364ca9b162c07699b1 upstream. Dennis Gilmore reports that the BuildID is missing in the arm64 vmlinux since commit 994b7ac1697b ("arm64: remove special treatment for the link order of head.o"). The issue is that the type of .notes section, which contains the BuildID, changed from NOTES to PROGBITS. Ard Biesheuvel figured out that whichever object gets linked first gets to decide the type of a section. The PROGBITS type is the result of the compiler emitting .note.GNU-stack as PROGBITS rather than NOTE. While Ard provided a fix for arm64, I want to fix this globally because the same issue is happening on riscv since commit 2348e6bf4421 ("riscv: remove special treatment for the link order of head.o"). This problem will happen in general for other architectures if they start to drop unneeded entries from scripts/head-object-list.txt. Discard .note.GNU-stack in include/asm-generic/vmlinux.lds.h. Link: https://lore.kernel.org/lkml/CAABkxwuQoz1CTbyb57n0ZX65eSYiTonFCU8-LCQc=74D=xE=rA@mail.gmail.com/ Fixes: 994b7ac1697b ("arm64: remove special treatment for the link order of head.o") Fixes: 2348e6bf4421 ("riscv: remove special treatment for the link order of head.o") Reported-by: Dennis Gilmore Suggested-by: Ard Biesheuvel Signed-off-by: Masahiro Yamada Acked-by: Palmer Dabbelt [Tom: stable backport 5.15.y, 5.10.y, 5.4.y] Though the above "Fixes:" commits are not in this kernel, the conditions which lead to a missing Build ID in arm64 vmlinux are similar. Evidence points to these conditions: 1. ld version > 2.36 (exact binutils commit documented in a494398bde27) 2. first object which gets linked (head.o) has a PROGBITS .note.GNU-stack segment These conditions can be observed when: - 5.15.60+ OR 5.10.136+ OR 5.4.210+ - AND ld version > 2.36 - AND arch=arm64 - AND CONFIG_MODVERSIONS=y There are notable differences in the vmlinux elf files produced before(bad) and after(good) applying this series. Good: p_type:PT_NOTE segment exists. Bad: p_type:PT_NOTE segment is missing. Good: sh_name_str:.notes section has sh_type:SHT_NOTE Bad: sh_name_str:.notes section has sh_type:SHT_PROGBITS `readelf -n` (as of v2.40) searches for Build Id by processing only the very first note in sh_type:SHT_NOTE sections. This was previously bisected to the stable backport of 0d362be5b142. Follow-up experiments were discussed here: https://lore.kernel.org/all/20221221235413.xaisboqmr7dkqwn6@oracle.com/ which strongly hints at condition 2. Signed-off-by: Tom Saeger Signed-off-by: Greg Kroah-Hartman --- include/asm-generic/vmlinux.lds.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index d233f9e4b9c6..44103f9487c9 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -906,7 +906,12 @@ #define TRACEDATA #endif +/* + * Discard .note.GNU-stack, which is emitted as PROGBITS by the compiler. + * Otherwise, the type of .notes section would become PROGBITS instead of NOTES. + */ #define NOTES \ + /DISCARD/ : { *(.note.GNU-stack) } \ .notes : AT(ADDR(.notes) - LOAD_OFFSET) { \ __start_notes = .; \ KEEP(*(.note.*)) \ From af560685bad5f182a2ca00b82774081f71939c86 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 1 Mar 2023 19:04:53 -0700 Subject: [PATCH 2117/4345] powerpc/vmlinux.lds: Define RUNTIME_DISCARD_EXIT commit 4b9880dbf3bdba3a7c56445137c3d0e30aaa0a40 upstream. The powerpc linker script explicitly includes .exit.text, because otherwise the link fails due to references from __bug_table and __ex_table. The code is freed (discarded) at runtime along with .init.text and data. That has worked in the past despite powerpc not defining RUNTIME_DISCARD_EXIT because DISCARDS appears late in the powerpc linker script (line 410), and the explicit inclusion of .exit.text earlier (line 280) supersedes the discard. However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") introduced an earlier use of DISCARD as part of the RO_DATA macro (line 136). With binutils < 2.36 that causes the DISCARD directives later in the script to be applied earlier [1], causing .exit.text to actually be discarded at link time, leading to build errors: '.exit.text' referenced in section '__bug_table' of crypto/algboss.o: defined in discarded section '.exit.text' of crypto/algboss.o '.exit.text' referenced in section '__ex_table' of drivers/nvdimm/core.o: defined in discarded section '.exit.text' of drivers/nvdimm/core.o Fix it by defining RUNTIME_DISCARD_EXIT, which causes the generic DISCARDS macro to not include .exit.text at all. 1: https://lore.kernel.org/lkml/87fscp2v7k.fsf@igel.home/ Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230105132349.384666-1-mpe@ellerman.id.au Signed-off-by: Tom Saeger Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/vmlinux.lds.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 4a1f494ef03f..e3984389f8ef 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -8,6 +8,7 @@ #define BSS_FIRST_SECTIONS *(.bss.prominit) #define EMITS_PT_NOTE #define RO_EXCEPTION_TABLE_ALIGN 0 +#define RUNTIME_DISCARD_EXIT #include #include From 6af633e7782c85d6522fe44ef8a97632725fa5fe Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 1 Mar 2023 19:04:54 -0700 Subject: [PATCH 2118/4345] powerpc/vmlinux.lds: Don't discard .rela* for relocatable builds commit 07b050f9290ee012a407a0f64151db902a1520f5 upstream. Relocatable kernels must not discard relocations, they need to be processed at runtime. As such they are included for CONFIG_RELOCATABLE builds in the powerpc linker script (line 340). However they are also unconditionally discarded later in the script (line 414). Previously that worked because the earlier inclusion superseded the discard. However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") introduced an earlier use of DISCARD as part of the RO_DATA macro (line 137). With binutils < 2.36 that causes the DISCARD directives later in the script to be applied earlier, causing .rela* to actually be discarded at link time, leading to build warnings and a kernel that doesn't boot: ld: warning: discarding dynamic section .rela.init.rodata Fix it by conditionally discarding .rela* only when CONFIG_RELOCATABLE is disabled. Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20230105132349.384666-2-mpe@ellerman.id.au Signed-off-by: Tom Saeger Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/vmlinux.lds.S | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index e3984389f8ef..fabe6cf10bd2 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -379,9 +379,12 @@ SECTIONS DISCARDS /DISCARD/ : { *(*.EMB.apuinfo) - *(.glink .iplt .plt .rela* .comment) + *(.glink .iplt .plt .comment) *(.gnu.version*) *(.gnu.attributes) *(.eh_frame) +#ifndef CONFIG_RELOCATABLE + *(.rela*) +#endif } } From bfef72d2fc62c194a36f271917ff1240f45d0f2f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 1 Mar 2023 19:04:55 -0700 Subject: [PATCH 2119/4345] s390: define RUNTIME_DISCARD_EXIT to fix link error with GNU ld < 2.36 commit a494398bde273143c2352dd373cad8211f7d94b2 upstream. Nathan Chancellor reports that the s390 vmlinux fails to link with GNU ld < 2.36 since commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv"). It happens for defconfig, or more specifically for CONFIG_EXPOLINE=y. $ s390x-linux-gnu-ld --version | head -n1 GNU ld (GNU Binutils for Debian) 2.35.2 $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- allnoconfig $ ./scripts/config -e CONFIG_EXPOLINE $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- olddefconfig $ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- `.exit.text' referenced in section `.s390_return_reg' of drivers/base/dd.o: defined in discarded section `.exit.text' of drivers/base/dd.o make[1]: *** [scripts/Makefile.vmlinux:34: vmlinux] Error 1 make: *** [Makefile:1252: vmlinux] Error 2 arch/s390/kernel/vmlinux.lds.S wants to keep EXIT_TEXT: .exit.text : { EXIT_TEXT } But, at the same time, EXIT_TEXT is thrown away by DISCARD because s390 does not define RUNTIME_DISCARD_EXIT. I still do not understand why the latter wins after 99cb0d917ffa, but defining RUNTIME_DISCARD_EXIT seems correct because the comment line in arch/s390/kernel/vmlinux.lds.S says: /* * .exit.text is discarded at runtime, not link time, * to deal with references from __bug_table */ Nathan also found that binutils commit 21401fc7bf67 ("Duplicate output sections in scripts") cured this issue, so we cannot reproduce it with binutils 2.36+, but it is better to not rely on it. Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Link: https://lore.kernel.org/all/Y7Jal56f6UBh1abE@dev-arch.thelio-3990X/ Reported-by: Nathan Chancellor Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20230105031306.1455409-1-masahiroy@kernel.org Signed-off-by: Heiko Carstens Signed-off-by: Tom Saeger Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/vmlinux.lds.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index d7291eb0d0c0..1c65c38ec9a3 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -15,6 +15,8 @@ /* Handle ro_after_init data on our own. */ #define RO_AFTER_INIT_DATA +#define RUNTIME_DISCARD_EXIT + #define EMITS_PT_NOTE #include From 5c425eb9da8ace13cecd18e705b0ed65923927f4 Mon Sep 17 00:00:00 2001 From: Tom Saeger Date: Wed, 1 Mar 2023 19:04:56 -0700 Subject: [PATCH 2120/4345] sh: define RUNTIME_DISCARD_EXIT commit c1c551bebf928889e7a8fef7415b44f9a64975f4 upstream. sh vmlinux fails to link with GNU ld < 2.40 (likely < 2.36) since commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv"). This is similar to fixes for powerpc and s390: commit 4b9880dbf3bd ("powerpc/vmlinux.lds: Define RUNTIME_DISCARD_EXIT"). commit a494398bde27 ("s390: define RUNTIME_DISCARD_EXIT to fix link error with GNU ld < 2.36"). $ sh4-linux-gnu-ld --version | head -n1 GNU ld (GNU Binutils for Debian) 2.35.2 $ make ARCH=sh CROSS_COMPILE=sh4-linux-gnu- microdev_defconfig $ make ARCH=sh CROSS_COMPILE=sh4-linux-gnu- `.exit.text' referenced in section `__bug_table' of crypto/algboss.o: defined in discarded section `.exit.text' of crypto/algboss.o `.exit.text' referenced in section `__bug_table' of drivers/char/hw_random/core.o: defined in discarded section `.exit.text' of drivers/char/hw_random/core.o make[2]: *** [scripts/Makefile.vmlinux:34: vmlinux] Error 1 make[1]: *** [Makefile:1252: vmlinux] Error 2 arch/sh/kernel/vmlinux.lds.S keeps EXIT_TEXT: /* * .exit.text is discarded at runtime, not link time, to deal with * references from __bug_table */ .exit.text : AT(ADDR(.exit.text)) { EXIT_TEXT } However, EXIT_TEXT is thrown away by DISCARD(include/asm-generic/vmlinux.lds.h) because sh does not define RUNTIME_DISCARD_EXIT. GNU ld 2.40 does not have this issue and builds fine. This corresponds with Masahiro's comments in a494398bde27: "Nathan [Chancellor] also found that binutils commit 21401fc7bf67 ("Duplicate output sections in scripts") cured this issue, so we cannot reproduce it with binutils 2.36+, but it is better to not rely on it." Link: https://lkml.kernel.org/r/9166a8abdc0f979e50377e61780a4bba1dfa2f52.1674518464.git.tom.saeger@oracle.com Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Link: https://lore.kernel.org/all/Y7Jal56f6UBh1abE@dev-arch.thelio-3990X/ Link: https://lore.kernel.org/all/20230123194218.47ssfzhrpnv3xfez@oracle.com/ Signed-off-by: Tom Saeger Tested-by: John Paul Adrian Glaubitz Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Dennis Gilmore Cc: Greg Kroah-Hartman Cc: Masahiro Yamada Cc: Naresh Kamboju Cc: Nathan Chancellor Cc: Palmer Dabbelt Cc: Rich Felker Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Tom Saeger Signed-off-by: Greg Kroah-Hartman --- arch/sh/kernel/vmlinux.lds.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 3161b9ccd2a5..b6276a3521d7 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -4,6 +4,7 @@ * Written by Niibe Yutaka and Paul Mundt */ OUTPUT_ARCH(sh) +#define RUNTIME_DISCARD_EXIT #include #include #include From 9da269bee7ead0922dc091475e525cbe21cbdfa8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 8 Feb 2023 01:41:56 +0900 Subject: [PATCH 2121/4345] UML: define RUNTIME_DISCARD_EXIT commit b99ddbe8336ee680257c8ab479f75051eaa49dcf upstream. With CONFIG_VIRTIO_UML=y, GNU ld < 2.36 fails to link UML vmlinux (w/wo CONFIG_LD_SCRIPT_STATIC). `.exit.text' referenced in section `.uml.exitcall.exit' of arch/um/drivers/virtio_uml.o: defined in discarded section `.exit.text' of arch/um/drivers/virtio_uml.o collect2: error: ld returned 1 exit status This fix is similar to the following commits: - 4b9880dbf3bd ("powerpc/vmlinux.lds: Define RUNTIME_DISCARD_EXIT") - a494398bde27 ("s390: define RUNTIME_DISCARD_EXIT to fix link error with GNU ld < 2.36") - c1c551bebf92 ("sh: define RUNTIME_DISCARD_EXIT") Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Reported-by: SeongJae Park Signed-off-by: Masahiro Yamada Tested-by: SeongJae Park Signed-off-by: Richard Weinberger Signed-off-by: Greg Kroah-Hartman --- arch/um/kernel/vmlinux.lds.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/kernel/vmlinux.lds.S b/arch/um/kernel/vmlinux.lds.S index 16e49bfa2b42..53d719c04ba9 100644 --- a/arch/um/kernel/vmlinux.lds.S +++ b/arch/um/kernel/vmlinux.lds.S @@ -1,4 +1,4 @@ - +#define RUNTIME_DISCARD_EXIT KERNEL_STACK_SIZE = 4096 * (1 << CONFIG_KERNEL_STACK_ORDER); #ifdef CONFIG_LD_SCRIPT_STATIC From 0ef55bafabb9ebf45bf5cdfaeabdc37d206e7624 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 29 Nov 2021 10:47:01 +0100 Subject: [PATCH 2122/4345] KVM: nVMX: Don't use Enlightened MSR Bitmap for L3 commit 250552b925ce400c17d166422fde9bb215958481 upstream. When KVM runs as a nested hypervisor on top of Hyper-V it uses Enlightened VMCS and enables Enlightened MSR Bitmap feature for its L1s and L2s (which are actually L2s and L3s from Hyper-V's perspective). When MSR bitmap is updated, KVM has to reset HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP from clean fields to make Hyper-V aware of the change. For KVM's L1s, this is done in vmx_disable_intercept_for_msr()/vmx_enable_intercept_for_msr(). MSR bitmap for L2 is build in nested_vmx_prepare_msr_bitmap() by blending MSR bitmap for L1 and L1's idea of MSR bitmap for L2. KVM, however, doesn't check if the resulting bitmap is different and never cleans HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP in eVMCS02. This is incorrect and may result in Hyper-V missing the update. The issue could've been solved by calling evmcs_touch_msr_bitmap() for eVMCS02 from nested_vmx_prepare_msr_bitmap() unconditionally but doing so would not give any performance benefits (compared to not using Enlightened MSR Bitmap at all). 3-level nesting is also not a very common setup nowadays. Don't enable 'Enlightened MSR Bitmap' feature for KVM's L2s (real L3s) for now. Signed-off-by: Vitaly Kuznetsov Message-Id: <20211129094704.326635-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini Signed-off-by: Alexandru Matei Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx/vmx.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c37cbd3fdd85..eefd6387a99d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2725,15 +2725,6 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); - - if (IS_ENABLED(CONFIG_HYPERV) && - static_branch_unlikely(&enable_evmcs) && - (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { - struct hv_enlightened_vmcs *evmcs = - (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs; - - evmcs->hv_enlightenments_control.msr_bitmap = 1; - } } memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); @@ -7029,6 +7020,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) if (err < 0) goto free_pml; + /* + * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a + * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the + * feature only for vmcs01, KVM currently isn't equipped to realize any + * performance benefits from enabling it for vmcs02. + */ + if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) && + (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + evmcs->hv_enlightenments_control.msr_bitmap = 1; + } + /* The MSR bitmap starts with all ones */ bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS); bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); From 685ed0a277f16881090891988b4d93257f8caf3c Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 29 Nov 2021 10:47:02 +0100 Subject: [PATCH 2123/4345] KVM: VMX: Introduce vmx_msr_bitmap_l01_changed() helper commit b84155c38076b36d625043a06a2f1c90bde62903 upstream. In preparation to enabling 'Enlightened MSR Bitmap' feature for Hyper-V guests move MSR bitmap update tracking to a dedicated helper. Note: vmx_msr_bitmap_l01_changed() is called when MSR bitmap might be updated. KVM doesn't check if the bit we're trying to set is already set (or the bit it's trying to clear is already cleared). Such situations should not be common and a few false positives should not be a problem. No functional change intended. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Maxim Levitsky Reviewed-by: Sean Christopherson Message-Id: <20211129094704.326635-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini Signed-off-by: Alexandru Matei Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx/vmx.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index eefd6387a99d..ee05c0e1cb2a 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -3785,6 +3785,17 @@ static void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr) __set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); } +static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) +{ + /* + * When KVM is a nested hypervisor on top of Hyper-V and uses + * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR + * bitmap has changed. + */ + if (static_branch_unlikely(&enable_evmcs)) + evmcs_touch_msr_bitmap(); +} + static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { @@ -3794,8 +3805,7 @@ static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed @@ -3840,8 +3850,7 @@ static __always_inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, if (!cpu_has_vmx_msr_bitmap()) return; - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed From 6baebcecf09acd19e2bab1c2911dcdba5d48a1dc Mon Sep 17 00:00:00 2001 From: Alexandru Matei Date: Tue, 24 Jan 2023 00:12:08 +0200 Subject: [PATCH 2124/4345] KVM: VMX: Fix crash due to uninitialized current_vmcs commit 93827a0a36396f2fd6368a54a020f420c8916e9b upstream. KVM enables 'Enlightened VMCS' and 'Enlightened MSR Bitmap' when running as a nested hypervisor on top of Hyper-V. When MSR bitmap is updated, evmcs_touch_msr_bitmap function uses current_vmcs per-cpu variable to mark that the msr bitmap was changed. vmx_vcpu_create() modifies the msr bitmap via vmx_disable_intercept_for_msr -> vmx_msr_bitmap_l01_changed which in the end calls this function. The function checks for current_vmcs if it is null but the check is insufficient because current_vmcs is not initialized. Because of this, the code might incorrectly write to the structure pointed by current_vmcs value left by another task. Preemption is not disabled, the current task can be preempted and moved to another CPU while current_vmcs is accessed multiple times from evmcs_touch_msr_bitmap() which leads to crash. The manipulation of MSR bitmaps by callers happens only for vmcs01 so the solution is to use vmx->vmcs01.vmcs instead of current_vmcs. BUG: kernel NULL pointer dereference, address: 0000000000000338 PGD 4e1775067 P4D 0 Oops: 0002 [#1] PREEMPT SMP NOPTI ... RIP: 0010:vmx_msr_bitmap_l01_changed+0x39/0x50 [kvm_intel] ... Call Trace: vmx_disable_intercept_for_msr+0x36/0x260 [kvm_intel] vmx_vcpu_create+0xe6/0x540 [kvm_intel] kvm_arch_vcpu_create+0x1d1/0x2e0 [kvm] kvm_vm_ioctl_create_vcpu+0x178/0x430 [kvm] kvm_vm_ioctl+0x53f/0x790 [kvm] __x64_sys_ioctl+0x8a/0xc0 do_syscall_64+0x5c/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: ceef7d10dfb6 ("KVM: x86: VMX: hyper-v: Enlightened MSR-Bitmap support") Cc: stable@vger.kernel.org Suggested-by: Sean Christopherson Signed-off-by: Alexandru Matei Link: https://lore.kernel.org/r/20230123221208.4964-1-alexandru.matei@uipath.com Signed-off-by: Sean Christopherson [manual backport: evmcs.h got renamed to hyperv.h in a later version, modified in evmcs.h instead] Signed-off-by: Alexandru Matei Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx/evmcs.h | 11 ----------- arch/x86/kvm/vmx/vmx.c | 9 +++++++-- 2 files changed, 7 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 011929a63823..9180155d5d89 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -166,16 +166,6 @@ static inline u16 evmcs_read16(unsigned long field) return *(u16 *)((char *)current_evmcs + offset); } -static inline void evmcs_touch_msr_bitmap(void) -{ - if (unlikely(!current_evmcs)) - return; - - if (current_evmcs->hv_enlightenments_control.msr_bitmap) - current_evmcs->hv_clean_fields &= - ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; -} - static inline void evmcs_load(u64 phys_addr) { struct hv_vp_assist_page *vp_ap = @@ -196,7 +186,6 @@ static inline u64 evmcs_read64(unsigned long field) { return 0; } static inline u32 evmcs_read32(unsigned long field) { return 0; } static inline u16 evmcs_read16(unsigned long field) { return 0; } static inline void evmcs_load(u64 phys_addr) {} -static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ enum nested_evmptrld_status { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ee05c0e1cb2a..2c5d8b9f9873 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -3792,8 +3792,13 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR * bitmap has changed. */ - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs)) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + if (evmcs->hv_enlightenments_control.msr_bitmap) + evmcs->hv_clean_fields &= + ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + } } static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, From aa8579bc084673c651204f7cd0d6308a47dffc16 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Tue, 25 May 2021 14:50:06 +0200 Subject: [PATCH 2125/4345] s390/dasd: add missing discipline function commit c0c8a8397fa8a74d04915f4d3d28cb4a5d401427 upstream. Fix crash with illegal operation exception in dasd_device_tasklet. Commit b72949328869 ("s390/dasd: Prepare for additional path event handling") renamed the verify_path function for ECKD but not for FBA and DIAG. This leads to a panic when the path verification function is called for a FBA or DIAG device. Fix by defining a wrapper function for dasd_generic_verify_path(). Fixes: b72949328869 ("s390/dasd: Prepare for additional path event handling") Cc: #5.11 Reviewed-by: Jan Hoeppner Signed-off-by: Stefan Haberland Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/r/20210525125006.157531-2-sth@linux.ibm.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/s390/block/dasd_diag.c | 7 ++++++- drivers/s390/block/dasd_fba.c | 7 ++++++- drivers/s390/block/dasd_int.h | 1 - 3 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index 1b9e1442e6a5..d5c7b70bd4de 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -642,12 +642,17 @@ static void dasd_diag_setup_blk_queue(struct dasd_block *block) blk_queue_segment_boundary(q, PAGE_SIZE - 1); } +static int dasd_diag_pe_handler(struct dasd_device *device, __u8 tbvpm) +{ + return dasd_generic_verify_path(device, tbvpm); +} + static struct dasd_discipline dasd_diag_discipline = { .owner = THIS_MODULE, .name = "DIAG", .ebcname = "DIAG", .check_device = dasd_diag_check_device, - .verify_path = dasd_generic_verify_path, + .pe_handler = dasd_diag_pe_handler, .fill_geometry = dasd_diag_fill_geometry, .setup_blk_queue = dasd_diag_setup_blk_queue, .start_IO = dasd_start_diag, diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index 1a44e321b54e..b159575a2760 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -803,13 +803,18 @@ static void dasd_fba_setup_blk_queue(struct dasd_block *block) blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } +static int dasd_fba_pe_handler(struct dasd_device *device, __u8 tbvpm) +{ + return dasd_generic_verify_path(device, tbvpm); +} + static struct dasd_discipline dasd_fba_discipline = { .owner = THIS_MODULE, .name = "FBA ", .ebcname = "FBA ", .check_device = dasd_fba_check_characteristics, .do_analysis = dasd_fba_do_analysis, - .verify_path = dasd_generic_verify_path, + .pe_handler = dasd_fba_pe_handler, .setup_blk_queue = dasd_fba_setup_blk_queue, .fill_geometry = dasd_fba_fill_geometry, .start_IO = dasd_start_IO, diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index e8a06d85d6f7..5d7d35ca5eb4 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -298,7 +298,6 @@ struct dasd_discipline { * e.g. verify that new path is compatible with the current * configuration. */ - int (*verify_path)(struct dasd_device *, __u8); int (*pe_handler)(struct dasd_device *, __u8); /* From de26e1b2103b1f56451f6ad77f0190c9066c87dc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 17 Mar 2023 08:45:17 +0100 Subject: [PATCH 2126/4345] Linux 5.10.175 Link: https://lore.kernel.org/r/20230315115731.942692602@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Salvatore Bonaccorso Tested-by: Shuah Khan Link: https://lore.kernel.org/r/20230316083430.973448646@linuxfoundation.org Tested-by: Chris Paterson (CIP) Tested-by: Florian Fainelli Tested-by: Tom Saeger Tested-by: Guenter Roeck Tested-by: Linux Kernel Functional Testing Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 92accf2ddc08..e6b09052f222 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 174 +SUBLEVEL = 175 EXTRAVERSION = NAME = Dare mighty things From afff17f58386f569c7bd324ee4a39b4cd840bf22 Mon Sep 17 00:00:00 2001 From: Seiya Wang Date: Fri, 17 Mar 2023 15:39:05 +0800 Subject: [PATCH 2127/4345] ANDROID: GKI: Update symbol list for mtk 6 Added functions: [A] 'function int of_get_pci_domain_nr(device_node*)' [A] 'function int pci_generic_config_read32(pci_bus*, unsigned int, int, int, u32*)' [A] 'function int pci_generic_config_write32(pci_bus*, unsigned int, int, int, u32)' [A] 'function void pci_lock_rescan_remove()' [A] 'function phys_addr_t pci_pio_to_address(unsigned long int)' [A] 'function void pci_unlock_rescan_remove()' Bug: 274051294 Signed-off-by: Seiya Wang Change-Id: I30fe96d94e3a371a44a977e696bafda4b23e7e63 --- android/abi_gki_aarch64.xml | 89 ++++++++++++++++++------------------- android/abi_gki_aarch64_mtk | 6 +++ 2 files changed, 49 insertions(+), 46 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 8b3cf2d10c07..3e0e10b5d0e6 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -3839,6 +3839,7 @@ + @@ -4008,7 +4009,9 @@ + + @@ -4021,6 +4024,7 @@ + @@ -4029,6 +4033,7 @@ + @@ -4055,6 +4060,7 @@ + @@ -44513,23 +44519,7 @@ - - - - - - - - - - - - - - - - - + @@ -48859,7 +48849,6 @@ - @@ -53803,13 +53792,6 @@ - - - - - - - @@ -66469,13 +66451,6 @@ - - - - - - - @@ -91224,7 +91199,6 @@ - @@ -102991,12 +102965,6 @@ - - - - - - @@ -111242,7 +111210,6 @@ - @@ -137471,6 +137438,10 @@ + + + + @@ -138393,6 +138364,14 @@ + + + + + + + + @@ -138401,6 +138380,14 @@ + + + + + + + + @@ -138465,6 +138452,9 @@ + + + @@ -138500,6 +138490,10 @@ + + + + @@ -138629,6 +138623,9 @@ + + + @@ -147295,16 +147292,16 @@ - - + + - - + + - - + + diff --git a/android/abi_gki_aarch64_mtk b/android/abi_gki_aarch64_mtk index 69e3dcacf161..630e18957ea8 100644 --- a/android/abi_gki_aarch64_mtk +++ b/android/abi_gki_aarch64_mtk @@ -1401,6 +1401,7 @@ of_get_next_child of_get_next_parent of_get_parent + of_get_pci_domain_nr of_get_phy_mode of_get_property of_get_regulator_init_data @@ -1473,6 +1474,11 @@ param_set_ulong pause_cpus pci_bus_type + pci_generic_config_read32 + pci_generic_config_write32 + pci_lock_rescan_remove + pci_pio_to_address + pci_unlock_rescan_remove PDE_DATA __per_cpu_offset perf_event_create_kernel_counter From eddac455460f9a21db796000b807872f28fefe7d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 14 Jan 2022 16:16:55 -0800 Subject: [PATCH 2128/4345] UPSTREAM: rcu: Remove __read_mostly annotations from rcu_scheduler_active externs Remove the __read_mostly attributes from the rcu_scheduler_active extern declarations, because these attributes are ignored for prototypes and we'd have to include the full header to gain this functionally pointless attribute defined. BUG: 274028827 Change-Id: Ib9c1d34ad2325b8cf939f5df0b35ebe4b281e9ec Signed-off-by: Ingo Molnar Signed-off-by: Paul E. McKenney (cherry picked from commit e6339d3b443c436c3b8f45eefec2212a8c07065d) Signed-off-by: Srinivasarao Pathipati --- include/linux/rcupdate.h | 2 +- include/linux/rcutree.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 095b3b39bd03..3190ba568096 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -83,7 +83,7 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); -extern int rcu_scheduler_active __read_mostly; +extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 59eb5cd567d7..a4567b25e158 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -60,7 +60,7 @@ static inline void rcu_irq_exit_check_preempt(void) { } void exit_rcu(void); void rcu_scheduler_starting(void); -extern int rcu_scheduler_active __read_mostly; +extern int rcu_scheduler_active; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); From a13e8447e8c6d29b36f2977c9350740b8fee5d01 Mon Sep 17 00:00:00 2001 From: Evgenii Stepanov Date: Wed, 7 Sep 2022 15:34:08 -0700 Subject: [PATCH 2129/4345] BACKPORT: arm64: mte: move register initialization to C If FEAT_MTE2 is disabled via the arm64.nomte command line argument on a CPU that claims to support FEAT_MTE2, the kernel will use Tagged Normal in the MAIR. If we interpret arm64.nomte to mean that the CPU does not in fact implement FEAT_MTE2, setting the system register like this may lead to UNSPECIFIED behavior. Fix it by arranging for MAIR to be set in the C function cpu_enable_mte which is called based on the sanitized version of the system register. There is no need for the rest of the MTE-related system register initialization to happen from assembly, with the exception of TCR_EL1, which must be set to include at least TBI1 because the secondary CPUs access KASan-allocated data structures early. Therefore, make the TCR_EL1 initialization unconditional and move the rest of the initialization to cpu_enable_mte so that we no longer have a dependency on the unsanitized ID register value. Signed-off-by: Peter Collingbourne Signed-off-by: Evgenii Stepanov Signed-off-by: Qun-Wei Lin Suggested-by: Catalin Marinas Reported-by: kernel test robot Link: https://lore.kernel.org/linux-arm-kernel/20220907003630.1115439-1-eugenis@google.com/ Bug: 239834217 Change-Id: I7bd247ae5802295c198bac42df86fab9e9e9cefd (cherry picked from commit 6a2905d35289caeeecbafa93ae4ff7cefafd02ed) --- arch/arm64/include/asm/mte.h | 5 ++++ arch/arm64/kernel/cpufeature.c | 3 +- arch/arm64/kernel/mte.c | 51 ++++++++++++++++++++++++++++++++ arch/arm64/kernel/suspend.c | 2 ++ arch/arm64/mm/proc.S | 54 ++++------------------------------ 5 files changed, 66 insertions(+), 49 deletions(-) diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index c0857e61e9e8..b63efcff7c74 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -40,7 +40,9 @@ void mte_sync_tags(pte_t *ptep, pte_t pte); void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); +void mte_cpu_setup(void); void mte_suspend_enter(void); +void mte_suspend_exit(void); long set_mte_ctrl(struct task_struct *task, unsigned long arg); long get_mte_ctrl(struct task_struct *task); int mte_ptrace_copy_tags(struct task_struct *child, long request, @@ -69,6 +71,9 @@ static inline void mte_thread_switch(struct task_struct *next) static inline void mte_suspend_enter(void) { } +static inline void mte_suspend_exit(void) +{ +} static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg) { return 0; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 4be4d5410a7b..0c17b2601003 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1870,7 +1870,8 @@ static void bti_enable(const struct arm64_cpu_capabilities *__unused) static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) { sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ATA | SCTLR_EL1_ATA0); - isb(); + + mte_cpu_setup(); /* * Clear the tags in the zero page. This needs to be done via the diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index c6a37d93539b..8bb8b67140d9 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -242,6 +242,49 @@ void mte_thread_switch(struct task_struct *next) mte_check_tfsr_el1(); } +void mte_cpu_setup(void) +{ + u64 rgsr; + + /* + * CnP must be enabled only after the MAIR_EL1 register has been set + * up. Inconsistent MAIR_EL1 between CPUs sharing the same TLB may + * lead to the wrong memory type being used for a brief window during + * CPU power-up. + * + * CnP is not a boot feature so MTE gets enabled before CnP, but let's + * make sure that is the case. + */ + BUG_ON(read_sysreg(ttbr0_el1) & TTBR_CNP_BIT); + BUG_ON(read_sysreg(ttbr1_el1) & TTBR_CNP_BIT); + + /* Normal Tagged memory type at the corresponding MAIR index */ + sysreg_clear_set(mair_el1, + MAIR_ATTRIDX(MAIR_ATTR_MASK, MT_NORMAL_TAGGED), + MAIR_ATTRIDX(MAIR_ATTR_NORMAL_TAGGED, + MT_NORMAL_TAGGED)); + + write_sysreg_s(KERNEL_GCR_EL1, SYS_GCR_EL1); + + /* + * If GCR_EL1.RRND=1 is implemented the same way as RRND=0, then + * RGSR_EL1.SEED must be non-zero for IRG to produce + * pseudorandom numbers. As RGSR_EL1 is UNKNOWN out of reset, we + * must initialize it. + */ + rgsr = (read_sysreg(CNTVCT_EL0) & SYS_RGSR_EL1_SEED_MASK) << + SYS_RGSR_EL1_SEED_SHIFT; + if (rgsr == 0) + rgsr = 1 << SYS_RGSR_EL1_SEED_SHIFT; + write_sysreg_s(rgsr, SYS_RGSR_EL1); + + /* clear any pending tag check faults in TFSR*_EL1 */ + write_sysreg_s(0, SYS_TFSR_EL1); + write_sysreg_s(0, SYS_TFSRE0_EL1); + + local_flush_tlb_all(); +} + void mte_suspend_enter(void) { if (!system_supports_mte()) @@ -258,6 +301,14 @@ void mte_suspend_enter(void) mte_check_tfsr_el1(); } +void mte_suspend_exit(void) +{ + if (!system_supports_mte()) + return; + + mte_cpu_setup(); +} + long set_mte_ctrl(struct task_struct *task, unsigned long arg) { u64 mte_ctrl = (~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) & diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index ea019a852adc..ae59fddb4f97 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -42,6 +42,8 @@ void notrace __cpu_suspend_exit(void) { unsigned int cpu = smp_processor_id(); + mte_suspend_exit(); + /* * We are resuming from reset with the idmap active in TTBR0_EL1. * We must uninstall the idmap and restore the expected MMU diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index c188a9eb3ea6..ee43c3cf5bf6 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -47,17 +47,19 @@ #ifdef CONFIG_KASAN_HW_TAGS #define TCR_MTE_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1 -#else +#elif defined(CONFIG_ARM64_MTE) /* * The mte_zero_clear_page_tags() implementation uses DC GZVA, which relies on * TBI being enabled at EL1. */ #define TCR_MTE_FLAGS TCR_TBI1 | TCR_TBID1 +#else +#define TCR_MTE_FLAGS 0 #endif /* * Default MAIR_EL1. MT_NORMAL_TAGGED is initially mapped as Normal memory and - * changed during __cpu_setup to Normal Tagged if the system supports MTE. + * changed during mte_cpu_setup to Normal Tagged if the system supports MTE. */ #define MAIR_EL1_SET \ (MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRnE) | \ @@ -427,47 +429,6 @@ SYM_FUNC_START(__cpu_setup) * Memory region attributes */ mov_q x5, MAIR_EL1_SET -#ifdef CONFIG_ARM64_MTE - mte_tcr .req x20 - - mov mte_tcr, #0 - - /* - * Update MAIR_EL1, GCR_EL1 and TFSR*_EL1 if MTE is supported - * (ID_AA64PFR1_EL1[11:8] > 1). - */ - mrs x10, ID_AA64PFR1_EL1 - ubfx x10, x10, #ID_AA64PFR1_MTE_SHIFT, #4 - cmp x10, #ID_AA64PFR1_MTE - b.lt 1f - - /* Normal Tagged memory type at the corresponding MAIR index */ - mov x10, #MAIR_ATTR_NORMAL_TAGGED - bfi x5, x10, #(8 * MT_NORMAL_TAGGED), #8 - - mov x10, #KERNEL_GCR_EL1 - msr_s SYS_GCR_EL1, x10 - - /* - * If GCR_EL1.RRND=1 is implemented the same way as RRND=0, then - * RGSR_EL1.SEED must be non-zero for IRG to produce - * pseudorandom numbers. As RGSR_EL1 is UNKNOWN out of reset, we - * must initialize it. - */ - mrs x10, CNTVCT_EL0 - ands x10, x10, #SYS_RGSR_EL1_SEED_MASK - csinc x10, x10, xzr, ne - lsl x10, x10, #SYS_RGSR_EL1_SEED_SHIFT - msr_s SYS_RGSR_EL1, x10 - - /* clear any pending tag check faults in TFSR*_EL1 */ - msr_s SYS_TFSR_EL1, xzr - msr_s SYS_TFSRE0_EL1, xzr - - /* set the TCR_EL1 bits */ - mov_q mte_tcr, TCR_MTE_FLAGS -1: -#endif msr mair_el1, x5 /* * Set/prepare TCR and TTBR. TCR_EL1.T1SZ gets further @@ -475,11 +436,8 @@ SYM_FUNC_START(__cpu_setup) */ mov_q x10, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ - TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS -#ifdef CONFIG_ARM64_MTE - orr x10, x10, mte_tcr - .unreq mte_tcr -#endif + TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS + tcr_clear_errata_bits x10, x9, x5 #ifdef CONFIG_ARM64_VA_BITS_52 From eb53a59b4d305c7502edef8ce30b23674de76eeb Mon Sep 17 00:00:00 2001 From: Kever Yang Date: Mon, 20 Mar 2023 08:59:35 +0800 Subject: [PATCH 2130/4345] ANDROID: GKI: rockchip: Add symbols for clk api Leaf changes summary: 2 artifacts changed (2 filtered out) Changed leaf types summary: 0 (1 filtered out) leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 2 Added functions Removed/Changed/Added variables summary: 0 Removed, 0 Changed (1 filtered out), 0 Added variable 2 Added functions: [A] 'function bool clk_has_parent(clk*, clk*)' [A] 'function int of_clk_parent_fill(device_node*, const char**, unsigned int)' Bug: 239396464 Signed-off-by: Kever Yang Change-Id: I51511f8736dc992ebe8cf85d9c0d41f588c66e24 --- android/abi_gki_aarch64.xml | 13 +++++++++++++ android/abi_gki_aarch64_rockchip | 5 +++++ 2 files changed, 18 insertions(+) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 3e0e10b5d0e6..58b441616537 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -1176,6 +1176,7 @@ + @@ -3778,6 +3779,7 @@ + @@ -123622,6 +123624,11 @@ + + + + + @@ -137134,6 +137141,12 @@ + + + + + + diff --git a/android/abi_gki_aarch64_rockchip b/android/abi_gki_aarch64_rockchip index aabe57eaca5f..205db1464b83 100644 --- a/android/abi_gki_aarch64_rockchip +++ b/android/abi_gki_aarch64_rockchip @@ -1638,6 +1638,10 @@ of_clk_add_hw_provider of_clk_hw_simple_get +# required by clk-out.ko + __clk_hw_register_gate + of_clk_parent_fill + # required by clk-rk628.ko devm_reset_controller_register @@ -2705,6 +2709,7 @@ snd_soc_dapm_new_widgets # required by snd-soc-rockchip-i2s-tdm.ko + clk_has_parent clk_is_match pm_runtime_forbid snd_pcm_stop_xrun From 370cb1c2705474c128447fed72eb3f63c1783409 Mon Sep 17 00:00:00 2001 From: Bin Yang Date: Mon, 28 Feb 2022 08:56:56 -0500 Subject: [PATCH 2131/4345] UPSTREAM: usb: dwc3: core: do not use 3.0 clock when operating in 2.0 mode In the 3.0 device core, if the core is programmed to operate in 2.0 only, then setting the GUCTL1.DEV_FORCE_20_CLK_FOR_30_CLK makes the internal 2.0(utmi/ulpi) clock to be routed as the 3.0 (pipe) clock. Enabling this feature allows the pipe3 clock to be not-running when forcibly operating in 2.0 device mode. Tested-by: Michael Riesch Signed-off-by: Bin Yang Signed-off-by: Peter Geis Link: https://lore.kernel.org/r/20220228135700.1089526-6-pgwipeout@gmail.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 62b20e6e0dde8d5633e3d94b028f86fb24b31d22) Signed-off-by: Kever Yang Change-Id: I7e53aaa54dd247f399a16406acb832a9f9a5a5eb --- drivers/usb/dwc3/core.c | 5 +++++ drivers/usb/dwc3/core.h | 1 + 2 files changed, 6 insertions(+) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 4806b415d237..fdadab536347 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1067,6 +1067,11 @@ static int dwc3_core_init(struct dwc3 *dwc) if (dwc->parkmode_disable_ss_quirk) reg |= DWC3_GUCTL1_PARKMODE_DISABLE_SS; + if (DWC3_VER_IS_WITHIN(DWC3, 290A, ANY) && + (dwc->maximum_speed == USB_SPEED_HIGH || + dwc->maximum_speed == USB_SPEED_FULL)) + reg |= DWC3_GUCTL1_DEV_FORCE_20_CLK_FOR_30_CLK; + dwc3_writel(dwc->regs, DWC3_GUCTL1, reg); } diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index b6f71aed4f82..98bd917a44d1 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -259,6 +259,7 @@ /* Global User Control 1 Register */ #define DWC3_GUCTL1_DEV_DECOUPLE_L1L2_EVT BIT(31) #define DWC3_GUCTL1_TX_IPGAP_LINECHECK_DIS BIT(28) +#define DWC3_GUCTL1_DEV_FORCE_20_CLK_FOR_30_CLK BIT(26) #define DWC3_GUCTL1_DEV_L1_EXIT_BY_HW BIT(24) #define DWC3_GUCTL1_PARKMODE_DISABLE_SS BIT(17) From 8ddbd3df9314d82afc0881dca4aef0c736422dd2 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 16 Feb 2022 12:32:45 +0530 Subject: [PATCH 2132/4345] UPSTREAM: ext4: refactor ext4_free_blocks() to pull out ext4_mb_clear_bb() commit 8ac3939db99f99667b8eb670cf4baf292896e72d upstream. ext4_free_blocks() function became too long and confusing, this patch just pulls out the ext4_mb_clear_bb() function logic from it which clears the block bitmap and frees it. No functionality change in this patch Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/22c30fbb26ba409cf8aa5f0c7912970272c459e8.1644992610.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman Bug: 237951970 Change-Id: Ib8c113a85e620eff6d4561a38c97f875a476ab7b Signed-off-by: Tudor Ambarus --- fs/ext4/mballoc.c | 180 ++++++++++++++++++++++++++-------------------- 1 file changed, 102 insertions(+), 78 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index d5ca02a7766e..0870f0436946 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5303,7 +5303,8 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, } /** - * ext4_free_blocks() -- Free given blocks and update quota + * ext4_mb_clear_bb() -- helper function for freeing blocks. + * Used by ext4_free_blocks() * @handle: handle for this transaction * @inode: inode * @bh: optional buffer of the block to be freed @@ -5311,9 +5312,9 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ -void ext4_free_blocks(handle_t *handle, struct inode *inode, - struct buffer_head *bh, ext4_fsblk_t block, - unsigned long count, int flags) +static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, + ext4_fsblk_t block, unsigned long count, + int flags) { struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; @@ -5330,80 +5331,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); - if (sbi->s_mount_state & EXT4_FC_REPLAY) { - ext4_free_blocks_simple(inode, block, count); - return; - } - - might_sleep(); - if (bh) { - if (block) - BUG_ON(block != bh->b_blocknr); - else - block = bh->b_blocknr; - } - - if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && - !ext4_inode_block_valid(inode, block, count)) { - ext4_error(sb, "Freeing blocks not in datazone - " - "block = %llu, count = %lu", block, count); - goto error_return; - } - - ext4_debug("freeing block %llu\n", block); - trace_ext4_free_blocks(inode, block, count, flags); - - if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { - BUG_ON(count > 1); - - ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, - inode, bh, block); - } - - /* - * If the extent to be freed does not begin on a cluster - * boundary, we need to deal with partial clusters at the - * beginning and end of the extent. Normally we will free - * blocks at the beginning or the end unless we are explicitly - * requested to avoid doing so. - */ - overflow = EXT4_PBLK_COFF(sbi, block); - if (overflow) { - if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { - overflow = sbi->s_cluster_ratio - overflow; - block += overflow; - if (count > overflow) - count -= overflow; - else - return; - } else { - block -= overflow; - count += overflow; - } - } - overflow = EXT4_LBLK_COFF(sbi, count); - if (overflow) { - if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { - if (count > overflow) - count -= overflow; - else - return; - } else - count += sbi->s_cluster_ratio - overflow; - } - - if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { - int i; - int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; - - for (i = 0; i < count; i++) { - cond_resched(); - if (is_metadata) - bh = sb_find_get_block(inode->i_sb, block + i); - ext4_forget(handle, is_metadata, inode, bh, block + i); - } - } - do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -5570,6 +5497,103 @@ error_return: return; } +/** + * ext4_free_blocks() -- Free given blocks and update quota + * @handle: handle for this transaction + * @inode: inode + * @bh: optional buffer of the block to be freed + * @block: starting physical block to be freed + * @count: number of blocks to be freed + * @flags: flags used by ext4_free_blocks + */ +void ext4_free_blocks(handle_t *handle, struct inode *inode, + struct buffer_head *bh, ext4_fsblk_t block, + unsigned long count, int flags) +{ + struct super_block *sb = inode->i_sb; + unsigned int overflow; + struct ext4_sb_info *sbi; + + sbi = EXT4_SB(sb); + + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + ext4_free_blocks_simple(inode, block, count); + return; + } + + might_sleep(); + if (bh) { + if (block) + BUG_ON(block != bh->b_blocknr); + else + block = bh->b_blocknr; + } + + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { + ext4_error(sb, "Freeing blocks not in datazone - " + "block = %llu, count = %lu", block, count); + return; + } + + ext4_debug("freeing block %llu\n", block); + trace_ext4_free_blocks(inode, block, count, flags); + + if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + BUG_ON(count > 1); + + ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, + inode, bh, block); + } + + /* + * If the extent to be freed does not begin on a cluster + * boundary, we need to deal with partial clusters at the + * beginning and end of the extent. Normally we will free + * blocks at the beginning or the end unless we are explicitly + * requested to avoid doing so. + */ + overflow = EXT4_PBLK_COFF(sbi, block); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { + overflow = sbi->s_cluster_ratio - overflow; + block += overflow; + if (count > overflow) + count -= overflow; + else + return; + } else { + block -= overflow; + count += overflow; + } + } + overflow = EXT4_LBLK_COFF(sbi, count); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { + if (count > overflow) + count -= overflow; + else + return; + } else + count += sbi->s_cluster_ratio - overflow; + } + + if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + int i; + int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; + + for (i = 0; i < count; i++) { + cond_resched(); + if (is_metadata) + bh = sb_find_get_block(inode->i_sb, block + i); + ext4_forget(handle, is_metadata, inode, bh, block + i); + } + } + + ext4_mb_clear_bb(handle, inode, block, count, flags); + return; +} + /** * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction From 1d4b2a4ad77b9ce10fe2c38be501823515f29080 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 16 Feb 2022 12:32:49 +0530 Subject: [PATCH 2133/4345] UPSTREAM: ext4: add ext4_sb_block_valid() refactored out of ext4_inode_block_valid() commit 6bc6c2bdf1baca6522b8d9ba976257d722423085 upstream. This API will be needed at places where we don't have an inode for e.g. while freeing blocks in ext4_group_add_blocks() Suggested-by: Jan Kara Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/dd34a236543ad5ae7123eeebe0cb69e6bdd44f34.1644992610.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman Bug: 237951970 Change-Id: I4a63d1f1c720bce9612600c9c6034ddeda389d01 Signed-off-by: Tudor Ambarus --- fs/ext4/block_validity.c | 26 +++++++++++++++++--------- fs/ext4/ext4.h | 3 +++ 2 files changed, 20 insertions(+), 9 deletions(-) diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 8e6ca23ed172..eed5b855dd94 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -294,15 +294,10 @@ void ext4_release_system_zone(struct super_block *sb) call_rcu(&system_blks->rcu, ext4_destroy_system_zone); } -/* - * Returns 1 if the passed-in block region (start_blk, - * start_blk+count) is valid; 0 if some part of the block region - * overlaps with some other filesystem metadata blocks. - */ -int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, - unsigned int count) +int ext4_sb_block_valid(struct super_block *sb, struct inode *inode, + ext4_fsblk_t start_blk, unsigned int count) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_system_blocks *system_blks; struct ext4_system_zone *entry; struct rb_node *n; @@ -331,7 +326,9 @@ int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, else if (start_blk >= (entry->start_blk + entry->count)) n = n->rb_right; else { - ret = (entry->ino == inode->i_ino); + ret = 0; + if (inode) + ret = (entry->ino == inode->i_ino); break; } } @@ -340,6 +337,17 @@ out_rcu: return ret; } +/* + * Returns 1 if the passed-in block region (start_blk, + * start_blk+count) is valid; 0 if some part of the block region + * overlaps with some other filesystem metadata blocks. + */ +int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, + unsigned int count) +{ + return ext4_sb_block_valid(inode->i_sb, inode, start_blk, count); +} + int ext4_check_blockref(const char *function, unsigned int line, struct inode *inode, __le32 *p, unsigned int max) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 666ea80b3cf3..ac1f9f237c75 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3574,6 +3574,9 @@ extern int ext4_inode_block_valid(struct inode *inode, unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); +extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode, + ext4_fsblk_t start_blk, unsigned int count); + /* extents.c */ struct ext4_ext_path; From 0301fe419a1ef8b2d5b1297aef44cbc663f00a6b Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 16 Feb 2022 12:32:50 +0530 Subject: [PATCH 2134/4345] UPSTREAM: ext4: add strict range checks while freeing blocks commit a00b482b82fb098956a5bed22bd7873e56f152f1 upstream. Currently ext4_mb_clear_bb() & ext4_group_add_blocks() only checks whether the given block ranges (which is to be freed) belongs to any FS metadata blocks or not, of the block's respective block group. But to detect any FS error early, it is better to add more strict checkings in those functions which checks whether the given blocks belongs to any critical FS metadata or not within system-zone. Suggested-by: Jan Kara Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/ddd9143d064774e32d6364a99667817c6e8bfdc0.1644992610.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman Bug: 237951970 Change-Id: Ibab39a43f13af206af8c384e7c5590925a089f00 Signed-off-by: Tudor Ambarus --- fs/ext4/mballoc.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 0870f0436946..b98d77c8b002 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5361,13 +5361,7 @@ do_more: goto error_return; } - if (in_range(ext4_block_bitmap(sb, gdp), block, count) || - in_range(ext4_inode_bitmap(sb, gdp), block, count) || - in_range(block, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group) || - in_range(block + count - 1, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group)) { - + if (!ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ @@ -5437,7 +5431,7 @@ do_more: NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" - " group:%d block:%d count:%lu failed" + " group:%u block:%d count:%lu failed" " with %d", block_group, bit, count, err); } else @@ -5650,11 +5644,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, goto error_return; } - if (in_range(ext4_block_bitmap(sb, desc), block, count) || - in_range(ext4_inode_bitmap(sb, desc), block, count) || - in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) || - in_range(block + count - 1, ext4_inode_table(sb, desc), - sbi->s_itb_per_group)) { + if (!ext4_sb_block_valid(sb, NULL, block, count)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); From b0d829f27f26d683c8b9878a8df2da48a1bebdfe Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Thu, 14 Jul 2022 18:59:03 +0200 Subject: [PATCH 2135/4345] UPSTREAM: ext4: block range must be validated before use in ext4_mb_clear_bb() commit 1e1c2b86ef86a8477fd9b9a4f48a6bfe235606f6 upstream. Block range to free is validated in ext4_free_blocks() using ext4_inode_block_valid() and then it's passed to ext4_mb_clear_bb(). However in some situations on bigalloc file system the range might be adjusted after the validation in ext4_free_blocks() which can lead to troubles on corrupted file systems such as one found by syzkaller that resulted in the following BUG kernel BUG at fs/ext4/ext4.h:3319! PREEMPT SMP NOPTI CPU: 28 PID: 4243 Comm: repro Kdump: loaded Not tainted 5.19.0-rc6+ #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1.fc35 04/01/2014 RIP: 0010:ext4_free_blocks+0x95e/0xa90 Call Trace: ? lock_timer_base+0x61/0x80 ? __es_remove_extent+0x5a/0x760 ? __mod_timer+0x256/0x380 ? ext4_ind_truncate_ensure_credits+0x90/0x220 ext4_clear_blocks+0x107/0x1b0 ext4_free_data+0x15b/0x170 ext4_ind_truncate+0x214/0x2c0 ? _raw_spin_unlock+0x15/0x30 ? ext4_discard_preallocations+0x15a/0x410 ? ext4_journal_check_start+0xe/0x90 ? __ext4_journal_start_sb+0x2f/0x110 ext4_truncate+0x1b5/0x460 ? __ext4_journal_start_sb+0x2f/0x110 ext4_evict_inode+0x2b4/0x6f0 evict+0xd0/0x1d0 ext4_enable_quotas+0x11f/0x1f0 ext4_orphan_cleanup+0x3de/0x430 ? proc_create_seq_private+0x43/0x50 ext4_fill_super+0x295f/0x3ae0 ? snprintf+0x39/0x40 ? sget_fc+0x19c/0x330 ? ext4_reconfigure+0x850/0x850 get_tree_bdev+0x16d/0x260 vfs_get_tree+0x25/0xb0 path_mount+0x431/0xa70 __x64_sys_mount+0xe2/0x120 do_syscall_64+0x5b/0x80 ? do_user_addr_fault+0x1e2/0x670 ? exc_page_fault+0x70/0x170 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fdf4e512ace Fix it by making sure that the block range is properly validated before used every time it changes in ext4_free_blocks() or ext4_mb_clear_bb(). Link: https://syzkaller.appspot.com/bug?id=5266d464285a03cee9dbfda7d2452a72c3c2ae7c Reported-by: syzbot+15cd994e273307bf5cfa@syzkaller.appspotmail.com Signed-off-by: Lukas Czerner Cc: Tadeusz Struk Tested-by: Tadeusz Struk Link: https://lore.kernel.org/r/20220714165903.58260-1-lczerner@redhat.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman Bug: 237951970 Change-Id: I2a45df5fe3f47c9408bed79f83a61b68c00efa22 Signed-off-by: Tudor Ambarus --- fs/ext4/mballoc.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index b98d77c8b002..843840c2aced 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5331,6 +5331,15 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { + ext4_error(sb, "Freeing blocks in system zone - " + "Block = %llu, count = %lu", block, count); + /* err = 0. ext4_std_error should be a no op */ + goto error_return; + } + flags |= EXT4_FREE_BLOCKS_VALIDATED; + do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -5347,6 +5356,8 @@ do_more: overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); bitmap_bh = ext4_read_block_bitmap(sb, block_group); @@ -5361,7 +5372,8 @@ do_more: goto error_return; } - if (!ext4_inode_block_valid(inode, block, count)) { + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ @@ -5483,6 +5495,8 @@ do_more: block += count; count = overflow; put_bh(bitmap_bh); + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } error_return: @@ -5529,6 +5543,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, "block = %llu, count = %lu", block, count); return; } + flags |= EXT4_FREE_BLOCKS_VALIDATED; ext4_debug("freeing block %llu\n", block); trace_ext4_free_blocks(inode, block, count, flags); @@ -5560,6 +5575,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, block -= overflow; count += overflow; } + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { @@ -5570,6 +5587,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, return; } else count += sbi->s_cluster_ratio - overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { From 989d4c69a92313db22b70fdc4876069e0ba11313 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 16 Feb 2023 10:55:48 -0800 Subject: [PATCH 2136/4345] UPSTREAM: ext4: fix another off-by-one fsmap error on 1k block filesystems commit c993799baf9c5861f8df91beb80e1611b12efcbd upstream. Apparently syzbot figured out that issuing this FSMAP call: struct fsmap_head cmd = { .fmh_count = ...; .fmh_keys = { { .fmr_device = /* ext4 dev */, .fmr_physical = 0, }, { .fmr_device = /* ext4 dev */, .fmr_physical = 0, }, }, ... }; ret = ioctl(fd, FS_IOC_GETFSMAP, &cmd); Produces this crash if the underlying filesystem is a 1k-block ext4 filesystem: kernel BUG at fs/ext4/ext4.h:3331! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 3 PID: 3227965 Comm: xfs_io Tainted: G W O 6.2.0-rc8-achx Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 RIP: 0010:ext4_mb_load_buddy_gfp+0x47c/0x570 [ext4] RSP: 0018:ffffc90007c03998 EFLAGS: 00010246 RAX: ffff888004978000 RBX: ffffc90007c03a20 RCX: ffff888041618000 RDX: 0000000000000000 RSI: 00000000000005a4 RDI: ffffffffa0c99b11 RBP: ffff888012330000 R08: ffffffffa0c2b7d0 R09: 0000000000000400 R10: ffffc90007c03950 R11: 0000000000000000 R12: 0000000000000001 R13: 00000000ffffffff R14: 0000000000000c40 R15: ffff88802678c398 FS: 00007fdf2020c880(0000) GS:ffff88807e100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffd318a5fe8 CR3: 000000007f80f001 CR4: 00000000001706e0 Call Trace: ext4_mballoc_query_range+0x4b/0x210 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] ext4_getfsmap_datadev+0x713/0x890 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] ext4_getfsmap+0x2b7/0x330 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] ext4_ioc_getfsmap+0x153/0x2b0 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] __ext4_ioctl+0x2a7/0x17e0 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] __x64_sys_ioctl+0x82/0xa0 do_syscall_64+0x2b/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fdf20558aff RSP: 002b:00007ffd318a9e30 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00000000000200c0 RCX: 00007fdf20558aff RDX: 00007fdf1feb2010 RSI: 00000000c0c0583b RDI: 0000000000000003 RBP: 00005625c0634be0 R08: 00005625c0634c40 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fdf1feb2010 R13: 00005625be70d994 R14: 0000000000000800 R15: 0000000000000000 For GETFSMAP calls, the caller selects a physical block device by writing its block number into fsmap_head.fmh_keys[01].fmr_device. To query mappings for a subrange of the device, the starting byte of the range is written to fsmap_head.fmh_keys[0].fmr_physical and the last byte of the range goes in fsmap_head.fmh_keys[1].fmr_physical. IOWs, to query what mappings overlap with bytes 3-14 of /dev/sda, you'd set the inputs as follows: fmh_keys[0] = { .fmr_device = major(8, 0), .fmr_physical = 3}, fmh_keys[1] = { .fmr_device = major(8, 0), .fmr_physical = 14}, Which would return you whatever is mapped in the 12 bytes starting at physical offset 3. The crash is due to insufficient range validation of keys[1] in ext4_getfsmap_datadev. On 1k-block filesystems, block 0 is not part of the filesystem, which means that s_first_data_block is nonzero. ext4_get_group_no_and_offset subtracts this quantity from the blocknr argument before cracking it into a group number and a block number within a group. IOWs, block group 0 spans blocks 1-8192 (1-based) instead of 0-8191 (0-based) like what happens with larger blocksizes. The net result of this encoding is that blocknr < s_first_data_block is not a valid input to this function. The end_fsb variable is set from the keys that are copied from userspace, which means that in the above example, its value is zero. That leads to an underflow here: blocknr = blocknr - le32_to_cpu(es->s_first_data_block); The division then operates on -1: offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)) >> EXT4_SB(sb)->s_cluster_bits; Leaving an impossibly large group number (2^32-1) in blocknr. ext4_getfsmap_check_keys checked that keys[0].fmr_physical and keys[1].fmr_physical are in increasing order, but ext4_getfsmap_datadev adjusts keys[0].fmr_physical to be at least s_first_data_block. This implies that we have to check it again after the adjustment, which is the piece that I forgot. Reported-by: syzbot+6be2b977c89f79b6b153@syzkaller.appspotmail.com Fixes: 4a4956249dac ("ext4: fix off-by-one fsmap error on 1k block filesystems") Link: https://syzkaller.appspot.com/bug?id=79d5768e9bfe362911ac1a5057a36fc6b5c30002 Cc: stable@vger.kernel.org Signed-off-by: Darrick J. Wong Link: https://lore.kernel.org/r/Y+58NPTH7VNGgzdd@magnolia Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman Bug: 260486287 Change-Id: I07ac9fcb91671016f4b6a10ef5c8711eea74fb26 Signed-off-by: Tudor Ambarus --- fs/ext4/fsmap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 4c2a9fe30067..0b2e4d3f5699 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -486,6 +486,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb, keys[0].fmr_physical = bofs; if (keys[1].fmr_physical >= eofs) keys[1].fmr_physical = eofs - 1; + if (keys[1].fmr_physical < keys[0].fmr_physical) + return 0; start_fsb = keys[0].fmr_physical; end_fsb = keys[1].fmr_physical; From 0da0b816972a88dc82431586cb2c1e85876f9c77 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 21 Feb 2023 13:54:00 +0800 Subject: [PATCH 2137/4345] xfrm: Allow transport-mode states with AF_UNSPEC selector [ Upstream commit c276a706ea1f51cf9723ed8484feceaf961b8f89 ] xfrm state selectors are matched against the inner-most flow which can be of any address family. Therefore middle states in nested configurations need to carry a wildcard selector in order to work at all. However, this is currently forbidden for transport-mode states. Fix this by removing the unnecessary check. Fixes: 13996378e658 ("[IPSEC]: Rename mode to outer_mode and add inner_mode") Reported-by: David George Signed-off-by: Herbert Xu Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_state.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index fdbd56ed4bd5..ba73014805a4 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2611,9 +2611,6 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) if (inner_mode == NULL) goto error; - if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL)) - goto error; - x->inner_mode = *inner_mode; if (x->props.family == AF_INET) From a3c502218cd34992dabbfe0b5385a2ece5864f82 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 17 Nov 2022 04:40:38 +0300 Subject: [PATCH 2138/4345] drm/panfrost: Don't sync rpm suspension after mmu flushing [ Upstream commit ba3be66f11c3c49afaa9f49b99e21d88756229ef ] Lockdep warns about potential circular locking dependency of devfreq with the fs_reclaim caused by immediate device suspension when mapping is released by shrinker. Fix it by doing the suspension asynchronously. Reviewed-by: Steven Price Fixes: ec7eba47da86 ("drm/panfrost: Rework page table flushing and runtime PM interaction") Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/all/20230108210445.3948344-3-dmitry.osipenko@collabora.com/ Signed-off-by: Sasha Levin --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 13596961ae17..5ff856ef7d88 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -236,7 +236,7 @@ static void panfrost_mmu_flush_range(struct panfrost_device *pfdev, if (pm_runtime_active(pfdev->dev)) mmu_hw_do_operation(pfdev, mmu, iova, size, AS_COMMAND_FLUSH_PT); - pm_runtime_put_sync_autosuspend(pfdev->dev); + pm_runtime_put_autosuspend(pfdev->dev); } static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu, From ed9ed2f58cebfa4894efaee43986e1e96e8ca850 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Wed, 16 Nov 2022 11:11:36 +0800 Subject: [PATCH 2139/4345] cifs: Move the in_send statistic to __smb_send_rqst() [ Upstream commit d0dc41119905f740e8d5594adce277f7c0de8c92 ] When send SMB_COM_NT_CANCEL and RFC1002_SESSION_REQUEST, the in_send statistic was lost. Let's move the in_send statistic to the send function to avoid this scenario. Fixes: 7ee1af765dfa ("[CIFS]") Signed-off-by: Zhang Xiaoxu Signed-off-by: Steve French Signed-off-by: Sasha Levin --- fs/cifs/transport.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index b137006f0fd2..4409f56fc37e 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -312,7 +312,7 @@ static int __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, struct smb_rqst *rqst) { - int rc = 0; + int rc; struct kvec *iov; int n_vec; unsigned int send_length = 0; @@ -323,6 +323,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, struct msghdr smb_msg = {}; __be32 rfc1002_marker; + cifs_in_send_inc(server); if (cifs_rdma_enabled(server)) { /* return -EAGAIN when connecting or reconnecting */ rc = -EAGAIN; @@ -331,14 +332,17 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, goto smbd_done; } + rc = -EAGAIN; if (ssocket == NULL) - return -EAGAIN; + goto out; + rc = -ERESTARTSYS; if (fatal_signal_pending(current)) { cifs_dbg(FYI, "signal pending before send request\n"); - return -ERESTARTSYS; + goto out; } + rc = 0; /* cork the socket */ tcp_sock_set_cork(ssocket->sk, true); @@ -449,7 +453,8 @@ smbd_done: rc); else if (rc > 0) rc = 0; - +out: + cifs_in_send_dec(server); return rc; } @@ -826,9 +831,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, * I/O response may come back and free the mid entry on another thread. */ cifs_save_when_sent(mid); - cifs_in_send_inc(server); rc = smb_send_rqst(server, 1, rqst, flags); - cifs_in_send_dec(server); if (rc < 0) { revert_current_mid(server, mid->credits); @@ -1117,9 +1120,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, else midQ[i]->callback = cifs_compound_last_callback; } - cifs_in_send_inc(server); rc = smb_send_rqst(server, num_rqst, rqst, flags); - cifs_in_send_dec(server); for (i = 0; i < num_rqst; i++) cifs_save_when_sent(midQ[i]); @@ -1356,9 +1357,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, midQ->mid_state = MID_REQUEST_SUBMITTED; - cifs_in_send_inc(server); rc = smb_send(server, in_buf, len); - cifs_in_send_dec(server); cifs_save_when_sent(midQ); if (rc < 0) @@ -1495,9 +1494,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, } midQ->mid_state = MID_REQUEST_SUBMITTED; - cifs_in_send_inc(server); rc = smb_send(server, in_buf, len); - cifs_in_send_dec(server); cifs_save_when_sent(midQ); if (rc < 0) From 081893e254f1369b64f4427911d4fd7b48d651aa Mon Sep 17 00:00:00 2001 From: Christian Hewitt Date: Fri, 3 Mar 2023 12:33:12 +0000 Subject: [PATCH 2140/4345] drm/meson: fix 1px pink line on GXM when scaling video overlay [ Upstream commit 5c8cf1664f288098a971a1d1e65716a2b6a279e1 ] Playing media with a resolution smaller than the crtc size requires the video overlay to be scaled for output and GXM boards display a 1px pink line on the bottom of the scaled overlay. Comparing with the downstream vendor driver revealed VPP_DUMMY_DATA not being set [0]. Setting VPP_DUMMY_DATA prevents the 1px pink line from being seen. [0] https://github.com/endlessm/linux-s905x/blob/master/drivers/amlogic/amports/video.c#L7869 Fixes: bbbe775ec5b5 ("drm: Add support for Amlogic Meson Graphic Controller") Suggested-by: Martin Blumenstingl Signed-off-by: Christian Hewitt Acked-by: Martin Blumenstingl Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230303123312.155164-1-christianshewitt@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/meson/meson_vpp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/meson/meson_vpp.c b/drivers/gpu/drm/meson/meson_vpp.c index 154837688ab0..5df1957c8e41 100644 --- a/drivers/gpu/drm/meson/meson_vpp.c +++ b/drivers/gpu/drm/meson/meson_vpp.c @@ -100,6 +100,8 @@ void meson_vpp_init(struct meson_drm *priv) priv->io_base + _REG(VPP_DOLBY_CTRL)); writel_relaxed(0x1020080, priv->io_base + _REG(VPP_DUMMY_DATA1)); + writel_relaxed(0x42020, + priv->io_base + _REG(VPP_DUMMY_DATA)); } else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) writel_relaxed(0xf, priv->io_base + _REG(DOLBY_PATH_CTRL)); From ea1e21d38a8d78f22c6cd87d2df89ac08705c1e8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 25 Feb 2023 21:39:47 -0800 Subject: [PATCH 2141/4345] clk: HI655X: select REGMAP instead of depending on it [ Upstream commit 0ffad67784a097beccf34d297ddd1b0773b3b8a3 ] REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it. Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues. Therefore, change the use of "depends on REGMAP" to "select REGMAP". Fixes: 3a49afb84ca0 ("clk: enable hi655x common clk automatically") Signed-off-by: Randy Dunlap Cc: Riku Voipio Cc: Stephen Boyd Cc: Michael Turquette Cc: linux-clk@vger.kernel.org Link: https://lore.kernel.org/r/20230226053953.4681-3-rdunlap@infradead.org Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index c715d4681a0b..4ae49eae4586 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -79,7 +79,7 @@ config COMMON_CLK_RK808 config COMMON_CLK_HI655X tristate "Clock driver for Hi655x" if EXPERT depends on (MFD_HI655X_PMIC || COMPILE_TEST) - depends on REGMAP + select REGMAP default MFD_HI655X_PMIC help This driver supports the hi655x PMIC clock. This From 79fe786dab5c10b1d5cb40aa3b4cdcc4489626ad Mon Sep 17 00:00:00 2001 From: Glenn Washburn Date: Mon, 27 Feb 2023 12:40:42 -0600 Subject: [PATCH 2142/4345] docs: Correct missing "d_" prefix for dentry_operations member d_weak_revalidate [ Upstream commit 74596085796fae0cfce3e42ee46bf4f8acbdac55 ] The details for struct dentry_operations member d_weak_revalidate is missing a "d_" prefix. Fixes: af96c1e304f7 ("docs: filesystems: vfs: Convert vfs.txt to RST") Signed-off-by: Glenn Washburn Reviewed-by: Matthew Wilcox (Oracle) Link: https://lore.kernel.org/r/20230227184042.2375235-1-development@efficientek.com Signed-off-by: Jonathan Corbet Signed-off-by: Sasha Levin --- Documentation/filesystems/vfs.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index ca52c82e5bb5..f7b69a0e71e1 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -1188,7 +1188,7 @@ defined: return -ECHILD and it will be called again in ref-walk mode. -``_weak_revalidate`` +``d_weak_revalidate`` called when the VFS needs to revalidate a "jumped" dentry. This is called when a path-walk ends at dentry that was not acquired by doing a lookup in the parent directory. This includes "/", From 6f0c2f70d9929208d8427ec72c3ed91e2251e289 Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Sat, 25 Feb 2023 18:01:36 +0800 Subject: [PATCH 2143/4345] scsi: mpt3sas: Fix NULL pointer access in mpt3sas_transport_port_add() [ Upstream commit d3c57724f1569311e4b81e98fad0931028b9bdcd ] Port is allocated by sas_port_alloc_num() and rphy is allocated by either sas_end_device_alloc() or sas_expander_alloc(), all of which may return NULL. So we need to check the rphy to avoid possible NULL pointer access. If sas_rphy_add() returned with failure, rphy is set to NULL. We would access the rphy in the following lines which would also result NULL pointer access. Fixes: 78316e9dfc24 ("scsi: mpt3sas: Fix possible resource leaks in mpt3sas_transport_port_add()") Signed-off-by: Wenchao Hao Link: https://lore.kernel.org/r/20230225100135.2109330-1-haowenchao2@huawei.com Acked-by: Sathya Prakash Veerichetty Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/mpt3sas/mpt3sas_transport.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c index b58f4d9c296a..326265fd7f91 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_transport.c +++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c @@ -670,7 +670,7 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle, goto out_fail; } port = sas_port_alloc_num(sas_node->parent_dev); - if ((sas_port_add(port))) { + if (!port || (sas_port_add(port))) { ioc_err(ioc, "failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); goto out_fail; @@ -695,6 +695,12 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle, rphy = sas_expander_alloc(port, mpt3sas_port->remote_identify.device_type); + if (!rphy) { + ioc_err(ioc, "failure at %s:%d/%s()!\n", + __FILE__, __LINE__, __func__); + goto out_delete_port; + } + rphy->identify = mpt3sas_port->remote_identify; if (mpt3sas_port->remote_identify.device_type == SAS_END_DEVICE) { @@ -714,6 +720,7 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle, __FILE__, __LINE__, __func__); sas_rphy_free(rphy); rphy = NULL; + goto out_delete_port; } if (mpt3sas_port->remote_identify.device_type == SAS_END_DEVICE) { @@ -740,7 +747,10 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle, rphy_to_expander_device(rphy)); return mpt3sas_port; - out_fail: +out_delete_port: + sas_port_delete(port); + +out_fail: list_for_each_entry_safe(mpt3sas_phy, next, &mpt3sas_port->phy_list, port_siblings) list_del(&mpt3sas_phy->port_siblings); From 0c6c5abeb471fead787ab12d8cafb9850cf66de2 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 15:40:54 -0600 Subject: [PATCH 2144/4345] ALSA: hda: Match only Intel devices with CONTROLLER_IN_GPU() [ Upstream commit ff447886e675979d66b2bc01810035d3baea1b3a ] CONTROLLER_IN_GPU() is clearly intended to match only Intel devices, but previously it checked only the PCI Device ID, not the Vendor ID, so it could match devices from other vendors that happened to use the same Device ID. Update CONTROLLER_IN_GPU() so it matches only Intel devices. Fixes: 535115b5ff51 ("ALSA: hda - Abort the probe without i915 binding for HSW/B") Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20230307214054.886721-1-helgaas@kernel.org Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/hda_intel.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 494bfd2135a9..de1fe604905f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -365,14 +365,15 @@ enum { #define needs_eld_notify_link(chip) false #endif -#define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \ +#define CONTROLLER_IN_GPU(pci) (((pci)->vendor == 0x8086) && \ + (((pci)->device == 0x0a0c) || \ ((pci)->device == 0x0c0c) || \ ((pci)->device == 0x0d0c) || \ ((pci)->device == 0x160c) || \ ((pci)->device == 0x490d) || \ ((pci)->device == 0x4f90) || \ ((pci)->device == 0x4f91) || \ - ((pci)->device == 0x4f92)) + ((pci)->device == 0x4f92))) #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) From eff050d83eee162a88d52b421f55ea9fad0bb826 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Tue, 7 Mar 2023 23:22:56 +0000 Subject: [PATCH 2145/4345] netfilter: nft_nat: correct length for loading protocol registers [ Upstream commit 068d82e75d537b444303b8c449a11e51ea659565 ] The values in the protocol registers are two bytes wide. However, when parsing the register loads, the code currently uses the larger 16-byte size of a `union nf_inet_addr`. Change it to use the (correct) size of a `union nf_conntrack_man_proto` instead. Fixes: d07db9884a5f ("netfilter: nf_tables: introduce nft_validate_register_load()") Signed-off-by: Jeremy Sowden Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_nat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index db8f9116eeb4..cd4eb4996aff 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -226,7 +226,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->flags |= NF_NAT_RANGE_MAP_IPS; } - plen = sizeof_field(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MIN], &priv->sreg_proto_min, plen); From 3a0f8ea35ddc9b205dbc04f6e848890ec983065e Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Tue, 7 Mar 2023 23:22:57 +0000 Subject: [PATCH 2146/4345] netfilter: nft_masq: correct length for loading protocol registers [ Upstream commit ec2c5917eb858428b2083d1c74f445aabbe8316b ] The values in the protocol registers are two bytes wide. However, when parsing the register loads, the code currently uses the larger 16-byte size of a `union nf_inet_addr`. Change it to use the (correct) size of a `union nf_conntrack_man_proto` instead. Fixes: 8a6bf5da1aef ("netfilter: nft_masq: support port range") Signed-off-by: Jeremy Sowden Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_masq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 9953e8053753..1818dbf089ca 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -43,7 +43,7 @@ static int nft_masq_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { - u32 plen = sizeof_field(struct nf_nat_range, min_addr.all); + u32 plen = sizeof_field(struct nf_nat_range, min_proto.all); struct nft_masq *priv = nft_expr_priv(expr); int err; From c144dff64ea9c924c1a85714d4fcf420c2df3213 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Tue, 7 Mar 2023 23:22:58 +0000 Subject: [PATCH 2147/4345] netfilter: nft_redir: correct length for loading protocol registers [ Upstream commit 1f617b6b4c7a3d5ea7a56abb83a4c27733b60c2f ] The values in the protocol registers are two bytes wide. However, when parsing the register loads, the code currently uses the larger 16-byte size of a `union nf_inet_addr`. Change it to use the (correct) size of a `union nf_conntrack_man_proto` instead. Fixes: d07db9884a5f ("netfilter: nf_tables: introduce nft_validate_register_load()") Signed-off-by: Jeremy Sowden Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_redir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index ba09890dddb5..deb7e65c8d82 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -48,7 +48,7 @@ static int nft_redir_init(const struct nft_ctx *ctx, unsigned int plen; int err; - plen = sizeof_field(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MIN], &priv->sreg_proto_min, plen); From 0fac20b1806b211fc38fa8778208bc1cad7a5df1 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Tue, 7 Mar 2023 23:22:59 +0000 Subject: [PATCH 2148/4345] netfilter: nft_redir: correct value of inet type `.maxattrs` [ Upstream commit 493924519b1fe3faab13ee621a43b0d0939abab1 ] `nft_redir_inet_type.maxattrs` was being set, presumably because of a cut-and-paste error, to `NFTA_MASQ_MAX`, instead of `NFTA_REDIR_MAX`. Fixes: 63ce3940f3ab ("netfilter: nft_redir: add inet support") Signed-off-by: Jeremy Sowden Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_redir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index deb7e65c8d82..e64f531d66cf 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -232,7 +232,7 @@ static struct nft_expr_type nft_redir_inet_type __read_mostly = { .name = "redir", .ops = &nft_redir_inet_ops, .policy = nft_redir_policy, - .maxattr = NFTA_MASQ_MAX, + .maxattr = NFTA_REDIR_MAX, .owner = THIS_MODULE, }; From be5aa2534188ab5df96508b532bcd59181650e5f Mon Sep 17 00:00:00 2001 From: Xiang Chen Date: Mon, 10 May 2021 19:35:26 +0800 Subject: [PATCH 2149/4345] scsi: core: Fix a comment in function scsi_host_dev_release() [ Upstream commit 2dde5c8d912efea43be94d6a83ac9cb74879fa12 ] Commit 3be8828fc507 ("scsi: core: Avoid that ATA error handling can trigger a kernel hang or oops") moved rcu to scsi_cmnd instead of shost. Modify "shost->rcu" to "scmd->rcu" in a comment. Link: https://lore.kernel.org/r/1620646526-193154-1-git-send-email-chenxiang66@hisilicon.com Signed-off-by: Xiang Chen Signed-off-by: Martin K. Petersen Stable-dep-of: be03df3d4bfe ("scsi: core: Fix a procfs host directory removal regression") Signed-off-by: Sasha Levin --- drivers/scsi/hosts.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index fae032324210..0fd2487203ff 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -325,7 +325,7 @@ static void scsi_host_dev_release(struct device *dev) /* In case scsi_remove_host() has not been called. */ scsi_proc_hostdir_rm(shost->hostt); - /* Wait for functions invoked through call_rcu(&shost->rcu, ...) */ + /* Wait for functions invoked through call_rcu(&scmd->rcu, ...) */ rcu_barrier(); if (shost->tmf_work_q) From 68c665bb185037e7eb66fb792c61da9d7151e99c Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 7 Mar 2023 13:44:28 -0800 Subject: [PATCH 2150/4345] scsi: core: Fix a procfs host directory removal regression [ Upstream commit be03df3d4bfe7e8866d4aa43d62e648ffe884f5f ] scsi_proc_hostdir_rm() decreases a reference counter and hence must only be called once per host that is removed. This change does not require a scsi_add_host_with_dma() change since scsi_add_host_with_dma() will return 0 (success) if scsi_proc_host_add() is called. Fixes: fc663711b944 ("scsi: core: Remove the /proc/scsi/${proc_name} directory earlier") Cc: John Garry Reported-by: John Garry Link: https://lore.kernel.org/all/ed6b8027-a9d9-1b45-be8e-df4e8c6c4605@oracle.com/ Reported-by: syzbot+645a4616b87a2f10e398@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-scsi/000000000000890fab05f65342b6@google.com/ Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230307214428.3703498-1-bvanassche@acm.org Tested-by: John Garry Tested-by: Shin'ichiro Kawasaki Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hosts.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 0fd2487203ff..18321cf9db5d 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -322,9 +322,6 @@ static void scsi_host_dev_release(struct device *dev) struct Scsi_Host *shost = dev_to_shost(dev); struct device *parent = dev->parent; - /* In case scsi_remove_host() has not been called. */ - scsi_proc_hostdir_rm(shost->hostt); - /* Wait for functions invoked through call_rcu(&scmd->rcu, ...) */ rcu_barrier(); From 77ad58bca0119e8cc3e0e9d91a3f22caa66e4dfa Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 8 Mar 2023 11:07:45 -0800 Subject: [PATCH 2151/4345] tcp: tcp_make_synack() can be called from process context [ Upstream commit bced3f7db95ff2e6ca29dc4d1c9751ab5e736a09 ] tcp_rtx_synack() now could be called in process context as explained in 0a375c822497 ("tcp: tcp_rtx_synack() can be called from process context"). tcp_rtx_synack() might call tcp_make_synack(), which will touch per-CPU variables with preemption enabled. This causes the following BUG: BUG: using __this_cpu_add() in preemptible [00000000] code: ThriftIO1/5464 caller is tcp_make_synack+0x841/0xac0 Call Trace: dump_stack_lvl+0x10d/0x1a0 check_preemption_disabled+0x104/0x110 tcp_make_synack+0x841/0xac0 tcp_v6_send_synack+0x5c/0x450 tcp_rtx_synack+0xeb/0x1f0 inet_rtx_syn_ack+0x34/0x60 tcp_check_req+0x3af/0x9e0 tcp_rcv_state_process+0x59b/0x2030 tcp_v6_do_rcv+0x5f5/0x700 release_sock+0x3a/0xf0 tcp_sendmsg+0x33/0x40 ____sys_sendmsg+0x2f2/0x490 __sys_sendmsg+0x184/0x230 do_syscall_64+0x3d/0x90 Avoid calling __TCP_INC_STATS() with will touch per-cpu variables. Use TCP_INC_STATS() which is safe to be called from context switch. Fixes: 8336886f786f ("tcp: TCP Fast Open Server - support TFO listeners") Signed-off-by: Breno Leitao Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230308190745.780221-1-leitao@debian.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index eefd032bc6db..e4ad274ec7a3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3609,7 +3609,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, th->window = htons(min(req->rsk_rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), NULL, &opts); th->doff = (tcp_header_size >> 2); - __TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ From 2703da78849c47b6b5b4471edb35fc7b7f91dead Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Thu, 9 Mar 2023 19:50:50 +0300 Subject: [PATCH 2152/4345] nfc: pn533: initialize struct pn533_out_arg properly [ Upstream commit 484b7059796e3bc1cb527caa61dfc60da649b4f6 ] struct pn533_out_arg used as a temporary context for out_urb is not initialized properly. Its uninitialized 'phy' field can be dereferenced in error cases inside pn533_out_complete() callback function. It causes the following failure: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.2.0-rc3-next-20230110-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 RIP: 0010:pn533_out_complete.cold+0x15/0x44 drivers/nfc/pn533/usb.c:441 Call Trace: __usb_hcd_giveback_urb+0x2b6/0x5c0 drivers/usb/core/hcd.c:1671 usb_hcd_giveback_urb+0x384/0x430 drivers/usb/core/hcd.c:1754 dummy_timer+0x1203/0x32d0 drivers/usb/gadget/udc/dummy_hcd.c:1988 call_timer_fn+0x1da/0x800 kernel/time/timer.c:1700 expire_timers+0x234/0x330 kernel/time/timer.c:1751 __run_timers kernel/time/timer.c:2022 [inline] __run_timers kernel/time/timer.c:1995 [inline] run_timer_softirq+0x326/0x910 kernel/time/timer.c:2035 __do_softirq+0x1fb/0xaf6 kernel/softirq.c:571 invoke_softirq kernel/softirq.c:445 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:650 irq_exit_rcu+0x9/0x20 kernel/softirq.c:662 sysvec_apic_timer_interrupt+0x97/0xc0 arch/x86/kernel/apic/apic.c:1107 Initialize the field with the pn533_usb_phy currently used. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: 9dab880d675b ("nfc: pn533: Wait for out_urb's completion in pn533_usb_send_frame()") Reported-by: syzbot+1e608ba4217c96d1952f@syzkaller.appspotmail.com Signed-off-by: Fedor Pchelkin Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230309165050.207390-1-pchelkin@ispras.ru Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/nfc/pn533/usb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index 57b07446bb76..68eb1253f888 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -175,6 +175,7 @@ static int pn533_usb_send_frame(struct pn533 *dev, print_hex_dump_debug("PN533 TX: ", DUMP_PREFIX_NONE, 16, 1, out->data, out->len, false); + arg.phy = phy; init_completion(&arg.done); cntx = phy->out_urb->context; phy->out_urb->context = &arg; From 91eb59240150f2b5907a88be3fc7ebb7f636cdfd Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Thu, 9 Mar 2023 10:03:36 +0800 Subject: [PATCH 2153/4345] ipvlan: Make skb->skb_iif track skb->dev for l3s mode [ Upstream commit 59a0b022aa249e3f5735d93de0849341722c4754 ] For l3s mode, skb->dev is set to ipvlan interface in ipvlan_nf_input(): skb->dev = addr->master->dev but, skb->skb_iif remain unchanged, this will cause socket lookup failed if a target socket is bound to a interface, like the following example: ip link add ipvlan0 link eth0 type ipvlan mode l3s ip addr add dev ipvlan0 192.168.124.111/24 ip link set ipvlan0 up ping -c 1 -I ipvlan0 8.8.8.8 100% packet loss This is because there is no match sk in __raw_v4_lookup() as sk->sk_bound_dev_if != dif(skb->skb_iif). Fix this by make skb->skb_iif track skb->dev in ipvlan_nf_input(). Fixes: c675e06a98a4 ("ipvlan: decouple l3s mode dependencies from other modes") Signed-off-by: Jianguo Wu Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/29865b1f-6db7-c07a-de89-949d3721ea30@163.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ipvlan/ipvlan_l3s.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c index 943d26cbf39f..71712ea25403 100644 --- a/drivers/net/ipvlan/ipvlan_l3s.c +++ b/drivers/net/ipvlan/ipvlan_l3s.c @@ -101,6 +101,7 @@ static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, goto out; skb->dev = addr->master->dev; + skb->skb_iif = skb->dev->ifindex; len = skb->len + ETH_HLEN; ipvlan_count_rx(addr->master, len, true, false); out: From 3cbecb1c9085a00155639404f7addbcbfc987ba3 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Thu, 9 Mar 2023 10:45:09 -0800 Subject: [PATCH 2154/4345] i40e: Fix kernel crash during reboot when adapter is in recovery mode [ Upstream commit 7e4f8a0c495413a50413e8c9f1032ce1bc633bae ] If the driver detects during probe that firmware is in recovery mode then i40e_init_recovery_mode() is called and the rest of probe function is skipped including pci_set_drvdata(). Subsequent i40e_shutdown() called during shutdown/reboot dereferences NULL pointer as pci_get_drvdata() returns NULL. To fix call pci_set_drvdata() also during entering to recovery mode. Reproducer: 1) Lets have i40e NIC with firmware in recovery mode 2) Run reboot Result: [ 139.084698] i40e: Intel(R) Ethernet Connection XL710 Network Driver [ 139.090959] i40e: Copyright (c) 2013 - 2019 Intel Corporation. [ 139.108438] i40e 0000:02:00.0: Firmware recovery mode detected. Limiting functionality. [ 139.116439] i40e 0000:02:00.0: Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode. [ 139.129499] i40e 0000:02:00.0: fw 8.3.64775 api 1.13 nvm 8.30 0x8000b78d 1.3106.0 [8086:1583] [15d9:084a] [ 139.215932] i40e 0000:02:00.0 enp2s0f0: renamed from eth0 [ 139.223292] i40e 0000:02:00.1: Firmware recovery mode detected. Limiting functionality. [ 139.231292] i40e 0000:02:00.1: Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode. [ 139.244406] i40e 0000:02:00.1: fw 8.3.64775 api 1.13 nvm 8.30 0x8000b78d 1.3106.0 [8086:1583] [15d9:084a] [ 139.329209] i40e 0000:02:00.1 enp2s0f1: renamed from eth0 ... [ 156.311376] BUG: kernel NULL pointer dereference, address: 00000000000006c2 [ 156.318330] #PF: supervisor write access in kernel mode [ 156.323546] #PF: error_code(0x0002) - not-present page [ 156.328679] PGD 0 P4D 0 [ 156.331210] Oops: 0002 [#1] PREEMPT SMP NOPTI [ 156.335567] CPU: 26 PID: 15119 Comm: reboot Tainted: G E 6.2.0+ #1 [ 156.343126] Hardware name: Abacus electric, s.r.o. - servis@abacus.cz Super Server/H12SSW-iN, BIOS 2.4 04/13/2022 [ 156.353369] RIP: 0010:i40e_shutdown+0x15/0x130 [i40e] [ 156.358430] Code: c1 fc ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 55 48 89 fd 53 48 8b 9f 48 01 00 00 80 8b c2 06 00 00 04 f0 80 8b c0 06 00 00 08 48 8d bb 08 08 00 [ 156.377168] RSP: 0018:ffffb223c8447d90 EFLAGS: 00010282 [ 156.382384] RAX: ffffffffc073ee70 RBX: 0000000000000000 RCX: 0000000000000001 [ 156.389510] RDX: 0000000080000001 RSI: 0000000000000246 RDI: ffff95db49988000 [ 156.396634] RBP: ffff95db49988000 R08: ffffffffffffffff R09: ffffffff8bd17d40 [ 156.403759] R10: 0000000000000001 R11: ffffffff8a5e3d28 R12: ffff95db49988000 [ 156.410882] R13: ffffffff89a6fe17 R14: ffff95db49988150 R15: 0000000000000000 [ 156.418007] FS: 00007fe7c0cc3980(0000) GS:ffff95ea8ee80000(0000) knlGS:0000000000000000 [ 156.426083] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 156.431819] CR2: 00000000000006c2 CR3: 00000003092fc005 CR4: 0000000000770ee0 [ 156.438944] PKRU: 55555554 [ 156.441647] Call Trace: [ 156.444096] [ 156.446199] pci_device_shutdown+0x38/0x60 [ 156.450297] device_shutdown+0x163/0x210 [ 156.454215] kernel_restart+0x12/0x70 [ 156.457872] __do_sys_reboot+0x1ab/0x230 [ 156.461789] ? vfs_writev+0xa6/0x1a0 [ 156.465362] ? __pfx_file_free_rcu+0x10/0x10 [ 156.469635] ? __call_rcu_common.constprop.85+0x109/0x5a0 [ 156.475034] do_syscall_64+0x3e/0x90 [ 156.478611] entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 156.483658] RIP: 0033:0x7fe7bff37ab7 Fixes: 4ff0ee1af016 ("i40e: Introduce recovery mode support") Signed-off-by: Ivan Vecera Tested-by: Arpana Arland (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20230309184509.984639-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 9e8a20a94862..76481ff7074b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -14851,6 +14851,7 @@ static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw) int err; int v_idx; + pci_set_drvdata(pf->pdev, pf); pci_save_state(pf->pdev); /* set up periodic task facility */ From 31817c530768b0199771ec6019571b4f0ddbf230 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Wed, 8 Mar 2023 16:17:12 +0800 Subject: [PATCH 2155/4345] net/smc: fix NULL sndbuf_desc in smc_cdc_tx_handler() [ Upstream commit 22a825c541d775c1dbe7b2402786025acad6727b ] When performing a stress test on SMC-R by rmmod mlx5_ib driver during the wrk/nginx test, we found that there is a probability of triggering a panic while terminating all link groups. This issue dues to the race between smc_smcr_terminate_all() and smc_buf_create(). smc_smcr_terminate_all smc_buf_create /* init */ conn->sndbuf_desc = NULL; ... __smc_lgr_terminate smc_conn_kill smc_close_abort smc_cdc_get_slot_and_msg_send __softirqentry_text_start smc_wr_tx_process_cqe smc_cdc_tx_handler READ(conn->sndbuf_desc->len); /* panic dues to NULL sndbuf_desc */ conn->sndbuf_desc = xxx; This patch tries to fix the issue by always to check the sndbuf_desc before send any cdc msg, to make sure that no null pointer is seen during cqe processing. Fixes: 0b29ec643613 ("net/smc: immediate termination for SMCR link groups") Signed-off-by: D. Wythe Reviewed-by: Tony Lu Reviewed-by: Wenjia Zhang Link: https://lore.kernel.org/r/1678263432-17329-1-git-send-email-alibuda@linux.alibaba.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/smc/smc_cdc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 94503f36b9a6..9125d28d9ff5 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -104,6 +104,9 @@ int smc_cdc_msg_send(struct smc_connection *conn, union smc_host_cursor cfed; int rc; + if (unlikely(!READ_ONCE(conn->sndbuf_desc))) + return -ENOBUFS; + smc_cdc_add_pending_send(conn, pend); conn->tx_cdc_seq++; From 281e86e3fab69294e0a7467d0447d1b0468aa1fd Mon Sep 17 00:00:00 2001 From: Daniil Tatianin Date: Thu, 9 Mar 2023 23:15:56 +0300 Subject: [PATCH 2156/4345] qed/qed_dev: guard against a possible division by zero [ Upstream commit 1a9dc5610ef89d807acdcfbff93a558f341a44da ] Previously we would divide total_left_rate by zero if num_vports happened to be 1 because non_requested_count is calculated as num_vports - req_count. Guard against this by validating num_vports at the beginning and returning an error otherwise. Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Fixes: bcd197c81f63 ("qed: Add vport WFQ configuration APIs") Signed-off-by: Daniil Tatianin Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230309201556.191392-1-d-tatianin@yandex-team.ru Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_dev.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index d2f5855b2ea7..895b6f0a3984 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -4986,6 +4986,11 @@ static int qed_init_wfq_param(struct qed_hwfn *p_hwfn, num_vports = p_hwfn->qm_info.num_vports; + if (num_vports < 2) { + DP_NOTICE(p_hwfn, "Unexpected num_vports: %d\n", num_vports); + return -EINVAL; + } + /* Accounting for the vports which are configured for WFQ explicitly */ for (i = 0; i < num_vports; i++) { u32 tmp_speed; From be59b87ee4aed81db7c10e44f603866a0ac3ca5d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 10 Mar 2023 19:11:09 +0000 Subject: [PATCH 2157/4345] net: tunnels: annotate lockless accesses to dev->needed_headroom [ Upstream commit 4b397c06cb987935b1b097336532aa6b4210e091 ] IP tunnels can apparently update dev->needed_headroom in their xmit path. This patch takes care of three tunnels xmit, and also the core LL_RESERVED_SPACE() and LL_RESERVED_SPACE_EXTRA() helpers. More changes might be needed for completeness. BUG: KCSAN: data-race in ip_tunnel_xmit / ip_tunnel_xmit read to 0xffff88815b9da0ec of 2 bytes by task 888 on cpu 1: ip_tunnel_xmit+0x1270/0x1730 net/ipv4/ip_tunnel.c:803 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 write to 0xffff88815b9da0ec of 2 bytes by task 2379 on cpu 0: ip_tunnel_xmit+0x1294/0x1730 net/ipv4/ip_tunnel.c:804 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip6_finish_output2+0x9bc/0xc50 net/ipv6/ip6_output.c:134 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x39a/0x4e0 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip6_output+0xeb/0x220 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:444 [inline] NF_HOOK include/linux/netfilter.h:302 [inline] mld_sendpack+0x438/0x6a0 net/ipv6/mcast.c:1820 mld_send_cr net/ipv6/mcast.c:2121 [inline] mld_ifc_work+0x519/0x7b0 net/ipv6/mcast.c:2653 process_one_work+0x3e6/0x750 kernel/workqueue.c:2390 worker_thread+0x5f2/0xa10 kernel/workqueue.c:2537 kthread+0x1ac/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x0dd4 -> 0x0e14 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 2379 Comm: kworker/0:0 Not tainted 6.3.0-rc1-syzkaller-00002-g8ca09d5fa354-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 Workqueue: mld mld_ifc_work Fixes: 8eb30be0352d ("ipv6: Create ip6_tnl_xmit") Reported-by: syzbot Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230310191109.2384387-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/linux/netdevice.h | 6 ++++-- net/ipv4/ip_tunnel.c | 12 ++++++------ net/ipv6/ip6_tunnel.c | 4 ++-- 3 files changed, 12 insertions(+), 10 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b478a16ef284..9ef63bc14b00 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -270,9 +270,11 @@ struct hh_cache { * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ - ((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index be75b409445c..99f70b990eb1 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -613,10 +613,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > dev->needed_headroom) - dev->needed_headroom = headroom; + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); goto tx_dropped; } @@ -797,10 +797,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 0d4cab94c5dd..a03a322e0cc1 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1267,8 +1267,8 @@ route_lookup: */ max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) From 194248138f8da8a74cbdc359fb5e5a7b116f35da Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 11 Mar 2023 19:34:45 +0100 Subject: [PATCH 2158/4345] net: phy: smsc: bail out in lan87xx_read_status if genphy_read_status fails [ Upstream commit c22c3bbf351e4ce905f082649cffa1ff893ea8c1 ] If genphy_read_status fails then further access to the PHY may result in unpredictable behavior. To prevent this bail out immediately if genphy_read_status fails. Fixes: 4223dbffed9f ("net: phy: smsc: Re-enable EDPD mode for LAN87xx") Signed-off-by: Heiner Kallweit Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/026aa4f2-36f5-1c10-ab9f-cdb17dda6ac4@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/smsc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index caf7291ffaf8..b67de3f9ef18 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -181,8 +181,11 @@ static int lan95xx_config_aneg_ext(struct phy_device *phydev) static int lan87xx_read_status(struct phy_device *phydev) { struct smsc_phy_priv *priv = phydev->priv; + int err; - int err = genphy_read_status(phydev); + err = genphy_read_status(phydev); + if (err) + return err; if (!phydev->link && priv->energy_enable) { /* Disable EDPD to wake up PHY */ From 43aa468df246175207a7d5d7d6d31b231f15b49c Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Mon, 13 Mar 2023 00:08:37 +0800 Subject: [PATCH 2159/4345] nfc: st-nci: Fix use after free bug in ndlc_remove due to race condition [ Upstream commit 5000fe6c27827a61d8250a7e4a1d26c3298ef4f6 ] This bug influences both st_nci_i2c_remove and st_nci_spi_remove. Take st_nci_i2c_remove as an example. In st_nci_i2c_probe, it called ndlc_probe and bound &ndlc->sm_work with llt_ndlc_sm_work. When it calls ndlc_recv or timeout handler, it will finally call schedule_work to start the work. When we call st_nci_i2c_remove to remove the driver, there may be a sequence as follows: Fix it by finishing the work before cleanup in ndlc_remove CPU0 CPU1 |llt_ndlc_sm_work st_nci_i2c_remove | ndlc_remove | st_nci_remove | nci_free_device| kfree(ndev) | //free ndlc->ndev | |llt_ndlc_rcv_queue |nci_recv_frame |//use ndlc->ndev Fixes: 35630df68d60 ("NFC: st21nfcb: Add driver for STMicroelectronics ST21NFCB NFC chip") Signed-off-by: Zheng Wang Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312160837.2040857-1-zyytlz.wz@163.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/nfc/st-nci/ndlc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/nfc/st-nci/ndlc.c b/drivers/nfc/st-nci/ndlc.c index 5d74c674368a..8ccf5a86ad1b 100644 --- a/drivers/nfc/st-nci/ndlc.c +++ b/drivers/nfc/st-nci/ndlc.c @@ -286,13 +286,15 @@ EXPORT_SYMBOL(ndlc_probe); void ndlc_remove(struct llt_ndlc *ndlc) { - st_nci_remove(ndlc->ndev); - /* cancel timers */ del_timer_sync(&ndlc->t1_timer); del_timer_sync(&ndlc->t2_timer); ndlc->t2_active = false; ndlc->t1_active = false; + /* cancel work */ + cancel_work_sync(&ndlc->sm_work); + + st_nci_remove(ndlc->ndev); skb_queue_purge(&ndlc->rcv_q); skb_queue_purge(&ndlc->send_q); From 9708efad9ba5095b9bb7916e11a135b3bd66c071 Mon Sep 17 00:00:00 2001 From: Wenjia Zhang Date: Mon, 13 Mar 2023 11:08:28 +0100 Subject: [PATCH 2160/4345] net/smc: fix deadlock triggered by cancel_delayed_work_syn() [ Upstream commit 13085e1b5cab8ad802904d72e6a6dae85ae0cd20 ] The following LOCKDEP was detected: Workqueue: events smc_lgr_free_work [smc] WARNING: possible circular locking dependency detected 6.1.0-20221027.rc2.git8.56bc5b569087.300.fc36.s390x+debug #1 Not tainted ------------------------------------------------------ kworker/3:0/176251 is trying to acquire lock: 00000000f1467148 ((wq_completion)smc_tx_wq-00000000#2){+.+.}-{0:0}, at: __flush_workqueue+0x7a/0x4f0 but task is already holding lock: 0000037fffe97dc8 ((work_completion)(&(&lgr->free_work)->work)){+.+.}-{0:0}, at: process_one_work+0x232/0x730 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #4 ((work_completion)(&(&lgr->free_work)->work)){+.+.}-{0:0}: __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 __flush_work+0x76/0xf0 __cancel_work_timer+0x170/0x220 __smc_lgr_terminate.part.0+0x34/0x1c0 [smc] smc_connect_rdma+0x15e/0x418 [smc] __smc_connect+0x234/0x480 [smc] smc_connect+0x1d6/0x230 [smc] __sys_connect+0x90/0xc0 __do_sys_socketcall+0x186/0x370 __do_syscall+0x1da/0x208 system_call+0x82/0xb0 -> #3 (smc_client_lgr_pending){+.+.}-{3:3}: __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 __mutex_lock+0x96/0x8e8 mutex_lock_nested+0x32/0x40 smc_connect_rdma+0xa4/0x418 [smc] __smc_connect+0x234/0x480 [smc] smc_connect+0x1d6/0x230 [smc] __sys_connect+0x90/0xc0 __do_sys_socketcall+0x186/0x370 __do_syscall+0x1da/0x208 system_call+0x82/0xb0 -> #2 (sk_lock-AF_SMC){+.+.}-{0:0}: __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 lock_sock_nested+0x46/0xa8 smc_tx_work+0x34/0x50 [smc] process_one_work+0x30c/0x730 worker_thread+0x62/0x420 kthread+0x138/0x150 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 -> #1 ((work_completion)(&(&smc->conn.tx_work)->work)){+.+.}-{0:0}: __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 process_one_work+0x2bc/0x730 worker_thread+0x62/0x420 kthread+0x138/0x150 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 -> #0 ((wq_completion)smc_tx_wq-00000000#2){+.+.}-{0:0}: check_prev_add+0xd8/0xe88 validate_chain+0x70c/0xb20 __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 __flush_workqueue+0xaa/0x4f0 drain_workqueue+0xaa/0x158 destroy_workqueue+0x44/0x2d8 smc_lgr_free+0x9e/0xf8 [smc] process_one_work+0x30c/0x730 worker_thread+0x62/0x420 kthread+0x138/0x150 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 other info that might help us debug this: Chain exists of: (wq_completion)smc_tx_wq-00000000#2 --> smc_client_lgr_pending --> (work_completion)(&(&lgr->free_work)->work) Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((work_completion)(&(&lgr->free_work)->work)); lock(smc_client_lgr_pending); lock((work_completion) (&(&lgr->free_work)->work)); lock((wq_completion)smc_tx_wq-00000000#2); *** DEADLOCK *** 2 locks held by kworker/3:0/176251: #0: 0000000080183548 ((wq_completion)events){+.+.}-{0:0}, at: process_one_work+0x232/0x730 #1: 0000037fffe97dc8 ((work_completion) (&(&lgr->free_work)->work)){+.+.}-{0:0}, at: process_one_work+0x232/0x730 stack backtrace: CPU: 3 PID: 176251 Comm: kworker/3:0 Not tainted Hardware name: IBM 8561 T01 701 (z/VM 7.2.0) Call Trace: [<000000002983c3e4>] dump_stack_lvl+0xac/0x100 [<0000000028b477ae>] check_noncircular+0x13e/0x160 [<0000000028b48808>] check_prev_add+0xd8/0xe88 [<0000000028b49cc4>] validate_chain+0x70c/0xb20 [<0000000028b4bd26>] __lock_acquire+0x58e/0xbd8 [<0000000028b4cf6a>] lock_acquire.part.0+0xe2/0x248 [<0000000028b4d17c>] lock_acquire+0xac/0x1c8 [<0000000028addaaa>] __flush_workqueue+0xaa/0x4f0 [<0000000028addf9a>] drain_workqueue+0xaa/0x158 [<0000000028ae303c>] destroy_workqueue+0x44/0x2d8 [<000003ff8029af26>] smc_lgr_free+0x9e/0xf8 [smc] [<0000000028adf3d4>] process_one_work+0x30c/0x730 [<0000000028adf85a>] worker_thread+0x62/0x420 [<0000000028aeac50>] kthread+0x138/0x150 [<0000000028a63914>] __ret_from_fork+0x3c/0x58 [<00000000298503da>] ret_from_fork+0xa/0x40 INFO: lockdep is turned off. =================================================================== This deadlock occurs because cancel_delayed_work_sync() waits for the work(&lgr->free_work) to finish, while the &lgr->free_work waits for the work(lgr->tx_wq), which needs the sk_lock-AF_SMC, that is already used under the mutex_lock. The solution is to use cancel_delayed_work() instead, which kills off a pending work. Fixes: a52bcc919b14 ("net/smc: improve termination processing") Signed-off-by: Wenjia Zhang Reviewed-by: Jan Karcher Reviewed-by: Karsten Graul Reviewed-by: Tony Lu Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/smc/smc_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index bf485a2017a4..e84241ff4ac4 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -912,7 +912,7 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) if (lgr->terminating) return; /* lgr already terminating */ /* cancel free_work sync, will terminate when lgr->freeing is set */ - cancel_delayed_work_sync(&lgr->free_work); + cancel_delayed_work(&lgr->free_work); lgr->terminating = 1; /* kill remaining link group connections */ From e294f0aa47e4844f3d3c8766c02accd5a76a7d4e Mon Sep 17 00:00:00 2001 From: Szymon Heidrich Date: Mon, 13 Mar 2023 23:00:45 +0100 Subject: [PATCH 2161/4345] net: usb: smsc75xx: Limit packet length to skb->len [ Upstream commit d8b228318935044dafe3a5bc07ee71a1f1424b8d ] Packet length retrieved from skb data may be larger than the actual socket buffer length (up to 9026 bytes). In such case the cloned skb passed up the network stack will leak kernel memory contents. Fixes: d0cad871703b ("smsc75xx: SMSC LAN75xx USB gigabit ethernet adapter driver") Signed-off-by: Szymon Heidrich Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/usb/smsc75xx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 378a12ae2d95..0b3d11e28faa 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2211,7 +2211,8 @@ static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) dev->net->stats.rx_frame_errors++; } else { /* MAX_SINGLE_PACKET_SIZE + 4(CRC) + 2(COE) + 4(Vlan) */ - if (unlikely(size > (MAX_SINGLE_PACKET_SIZE + ETH_HLEN + 12))) { + if (unlikely(size > (MAX_SINGLE_PACKET_SIZE + ETH_HLEN + 12) || + size > skb->len)) { netif_dbg(dev, rx_err, dev->net, "size err rx_cmd_a=0x%08x\n", rx_cmd_a); From d5e61a859a8aeed4300ce4d067c3440770d9e728 Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Tue, 14 Mar 2023 13:50:35 +0800 Subject: [PATCH 2162/4345] drm/bridge: Fix returned array size name for atomic_get_input_bus_fmts kdoc [ Upstream commit 0d3c9333d976af41d7dbc6bf4d9d2e95fbdf9c89 ] The returned array size for input formats is set through atomic_get_input_bus_fmts()'s 'num_input_fmts' argument, so use 'num_input_fmts' to represent the array size in the function's kdoc, not 'num_output_fmts'. Fixes: 91ea83306bfa ("drm/bridge: Fix the bridge kernel doc") Fixes: f32df58acc68 ("drm/bridge: Add the necessary bits to support bus format negotiation") Signed-off-by: Liu Ying Reviewed-by: Robert Foss Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230314055035.3731179-1-victor.liu@nxp.com Signed-off-by: Sasha Levin --- include/drm/drm_bridge.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 2195daa289d2..055486e35e68 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -427,11 +427,11 @@ struct drm_bridge_funcs { * * The returned array must be allocated with kmalloc() and will be * freed by the caller. If the allocation fails, NULL should be - * returned. num_output_fmts must be set to the returned array size. + * returned. num_input_fmts must be set to the returned array size. * Formats listed in the returned array should be listed in decreasing * preference order (the core will try all formats until it finds one * that works). When the format is not supported NULL should be - * returned and num_output_fmts should be set to 0. + * returned and num_input_fmts should be set to 0. * * This method is called on all elements of the bridge chain as part of * the bus format negotiation process that happens in From d14d2574a54c2ee7ae6c44a5507973972ecce7f5 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 20 Nov 2020 10:55:19 +0900 Subject: [PATCH 2163/4345] null_blk: Move driver into its own directory [ Upstream commit eebf34a85c8c724676eba502d15202854f199b05 ] Move null_blk driver code into the new sub-directory drivers/block/null_blk. Suggested-by: Bart Van Assche Signed-off-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe Stable-dep-of: 63f886597085 ("block: null_blk: Fix handling of fake timeout request") Signed-off-by: Sasha Levin --- drivers/block/Kconfig | 8 +------- drivers/block/Makefile | 7 +------ drivers/block/null_blk/Kconfig | 12 ++++++++++++ drivers/block/null_blk/Makefile | 11 +++++++++++ drivers/block/{null_blk_main.c => null_blk/main.c} | 0 drivers/block/{ => null_blk}/null_blk.h | 0 drivers/block/{null_blk_trace.c => null_blk/trace.c} | 2 +- drivers/block/{null_blk_trace.h => null_blk/trace.h} | 2 +- drivers/block/{null_blk_zoned.c => null_blk/zoned.c} | 2 +- 9 files changed, 28 insertions(+), 16 deletions(-) create mode 100644 drivers/block/null_blk/Kconfig create mode 100644 drivers/block/null_blk/Makefile rename drivers/block/{null_blk_main.c => null_blk/main.c} (100%) rename drivers/block/{ => null_blk}/null_blk.h (100%) rename drivers/block/{null_blk_trace.c => null_blk/trace.c} (93%) rename drivers/block/{null_blk_trace.h => null_blk/trace.h} (97%) rename drivers/block/{null_blk_zoned.c => null_blk/zoned.c} (99%) diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 40c53632512b..9617688b58b3 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -16,13 +16,7 @@ menuconfig BLK_DEV if BLK_DEV -config BLK_DEV_NULL_BLK - tristate "Null test block driver" - select CONFIGFS_FS - -config BLK_DEV_NULL_BLK_FAULT_INJECTION - bool "Support fault injection for Null test block driver" - depends on BLK_DEV_NULL_BLK && FAULT_INJECTION +source "drivers/block/null_blk/Kconfig" config BLK_DEV_FD tristate "Normal floppy disk support" diff --git a/drivers/block/Makefile b/drivers/block/Makefile index e1f63117ee94..a3170859e01d 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -41,12 +41,7 @@ obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/ obj-$(CONFIG_ZRAM) += zram/ obj-$(CONFIG_BLK_DEV_RNBD) += rnbd/ -obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk.o -null_blk-objs := null_blk_main.o -ifeq ($(CONFIG_BLK_DEV_ZONED), y) -null_blk-$(CONFIG_TRACING) += null_blk_trace.o -endif -null_blk-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o +obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk/ skd-y := skd_main.o swim_mod-y := swim.o swim_asm.o diff --git a/drivers/block/null_blk/Kconfig b/drivers/block/null_blk/Kconfig new file mode 100644 index 000000000000..6bf1f8ca20a2 --- /dev/null +++ b/drivers/block/null_blk/Kconfig @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Null block device driver configuration +# + +config BLK_DEV_NULL_BLK + tristate "Null test block driver" + select CONFIGFS_FS + +config BLK_DEV_NULL_BLK_FAULT_INJECTION + bool "Support fault injection for Null test block driver" + depends on BLK_DEV_NULL_BLK && FAULT_INJECTION diff --git a/drivers/block/null_blk/Makefile b/drivers/block/null_blk/Makefile new file mode 100644 index 000000000000..84c36e512ab8 --- /dev/null +++ b/drivers/block/null_blk/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 + +# needed for trace events +ccflags-y += -I$(src) + +obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk.o +null_blk-objs := main.o +ifeq ($(CONFIG_BLK_DEV_ZONED), y) +null_blk-$(CONFIG_TRACING) += trace.o +endif +null_blk-$(CONFIG_BLK_DEV_ZONED) += zoned.o diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk/main.c similarity index 100% rename from drivers/block/null_blk_main.c rename to drivers/block/null_blk/main.c diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk/null_blk.h similarity index 100% rename from drivers/block/null_blk.h rename to drivers/block/null_blk/null_blk.h diff --git a/drivers/block/null_blk_trace.c b/drivers/block/null_blk/trace.c similarity index 93% rename from drivers/block/null_blk_trace.c rename to drivers/block/null_blk/trace.c index f246e7bff698..3711cba16071 100644 --- a/drivers/block/null_blk_trace.c +++ b/drivers/block/null_blk/trace.c @@ -4,7 +4,7 @@ * * Copyright (C) 2020 Western Digital Corporation or its affiliates. */ -#include "null_blk_trace.h" +#include "trace.h" /* * Helper to use for all null_blk traces to extract disk name. diff --git a/drivers/block/null_blk_trace.h b/drivers/block/null_blk/trace.h similarity index 97% rename from drivers/block/null_blk_trace.h rename to drivers/block/null_blk/trace.h index 4f83032eb544..ce3b430e88c5 100644 --- a/drivers/block/null_blk_trace.h +++ b/drivers/block/null_blk/trace.h @@ -73,7 +73,7 @@ TRACE_EVENT(nullb_report_zones, #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE null_blk_trace +#define TRACE_INCLUDE_FILE trace /* This part must be outside protection */ #include diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk/zoned.c similarity index 99% rename from drivers/block/null_blk_zoned.c rename to drivers/block/null_blk/zoned.c index f5df82c26c16..41220ce59659 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -4,7 +4,7 @@ #include "null_blk.h" #define CREATE_TRACE_POINTS -#include "null_blk_trace.h" +#include "trace.h" #define MB_TO_SECTS(mb) (((sector_t)mb * SZ_1M) >> SECTOR_SHIFT) From 4cf15887a41be1e8c723788846c3c412ed856df0 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 14 Mar 2023 13:11:05 +0900 Subject: [PATCH 2164/4345] block: null_blk: Fix handling of fake timeout request [ Upstream commit 63f886597085f346276e3b3c8974de0100d65f32 ] When injecting a fake timeout into the null_blk driver using fail_io_timeout, the request timeout handler does not execute blk_mq_complete_request(), so the complete callback is never executed for a timedout request. The null_blk driver also has a driver-specific fake timeout mechanism which does not have this problem. Fix the problem with fail_io_timeout by using the same meachanism as null_blk internal timeout feature, using the fake_timeout field of null_blk commands. Reported-by: Akinobu Mita Fixes: de3510e52b0a ("null_blk: fix command timeout completion handling") Signed-off-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20230314041106.19173-2-damien.lemoal@opensource.wdc.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/null_blk/main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index c6ba8f9f3f31..25db095e943b 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1309,8 +1309,7 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd) case NULL_IRQ_SOFTIRQ: switch (cmd->nq->dev->queue_mode) { case NULL_Q_MQ: - if (likely(!blk_should_fake_timeout(cmd->rq->q))) - blk_mq_complete_request(cmd->rq); + blk_mq_complete_request(cmd->rq); break; case NULL_Q_BIO: /* @@ -1486,7 +1485,8 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, cmd->rq = bd->rq; cmd->error = BLK_STS_OK; cmd->nq = nq; - cmd->fake_timeout = should_timeout_request(bd->rq); + cmd->fake_timeout = should_timeout_request(bd->rq) || + blk_should_fake_timeout(bd->rq->q); blk_mq_start_request(bd->rq); From 9ebc344ce547206de488215eaaa96e5f007548b2 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 4 Mar 2023 07:13:45 +0800 Subject: [PATCH 2165/4345] nvme: fix handling single range discard request [ Upstream commit 37f0dc2ec78af0c3f35dd05578763de059f6fe77 ] When investigating one customer report on warning in nvme_setup_discard, we observed the controller(nvme/tcp) actually exposes queue_max_discard_segments(req->q) == 1. Obviously the current code can't handle this situation, since contiguity merge like normal RW request is taken. Fix the issue by building range from request sector/nr_sectors directly. Fixes: b35ba01ea697 ("nvme: support ranged discard requests") Signed-off-by: Ming Lei Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/core.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e162f1dfbafe..a4b6aa932a8f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -723,16 +723,26 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, range = page_address(ns->ctrl->discard_page); } - __rq_for_each_bio(bio, req) { - u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector); - u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift; + if (queue_max_discard_segments(req->q) == 1) { + u64 slba = nvme_sect_to_lba(ns, blk_rq_pos(req)); + u32 nlb = blk_rq_sectors(req) >> (ns->lba_shift - 9); - if (n < segments) { - range[n].cattr = cpu_to_le32(0); - range[n].nlb = cpu_to_le32(nlb); - range[n].slba = cpu_to_le64(slba); + range[0].cattr = cpu_to_le32(0); + range[0].nlb = cpu_to_le32(nlb); + range[0].slba = cpu_to_le64(slba); + n = 1; + } else { + __rq_for_each_bio(bio, req) { + u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector); + u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift; + + if (n < segments) { + range[n].cattr = cpu_to_le32(0); + range[n].nlb = cpu_to_le32(nlb); + range[n].slba = cpu_to_le64(slba); + } + n++; } - n++; } if (WARN_ON_ONCE(n != segments)) { From a6317235da8aa7cb97529ebc8121cc2a4c4c437a Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 6 Mar 2023 10:13:13 +0900 Subject: [PATCH 2166/4345] nvmet: avoid potential UAF in nvmet_req_complete() [ Upstream commit 6173a77b7e9d3e202bdb9897b23f2a8afe7bf286 ] An nvme target ->queue_response() operation implementation may free the request passed as argument. Such implementation potentially could result in a use after free of the request pointer when percpu_ref_put() is called in nvmet_req_complete(). Avoid such problem by using a local variable to save the sq pointer before calling __nvmet_req_complete(), thus avoiding dereferencing the req pointer after that function call. Fixes: a07b4970f464 ("nvmet: add a generic NVMe target") Signed-off-by: Damien Le Moal Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/target/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index bc88ff2912f5..a82a0796a614 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -749,8 +749,10 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) void nvmet_req_complete(struct nvmet_req *req, u16 status) { + struct nvmet_sq *sq = req->sq; + __nvmet_req_complete(req, status); - percpu_ref_put(&req->sq->ref); + percpu_ref_put(&sq->ref); } EXPORT_SYMBOL_GPL(nvmet_req_complete); From 2f28cb5c2a510185fec4a52e9ca20d78ce72f57d Mon Sep 17 00:00:00 2001 From: Liang He Date: Wed, 15 Mar 2023 14:20:32 +0800 Subject: [PATCH 2167/4345] block: sunvdc: add check for mdesc_grab() returning NULL [ Upstream commit 6030363199e3a6341afb467ddddbed56640cbf6a ] In vdc_port_probe(), we should check the return value of mdesc_grab() as it may return NULL, which can cause potential NPD bug. Fixes: 43fdf27470b2 ("[SPARC64]: Abstract out mdesc accesses for better MD update handling.") Signed-off-by: Liang He Link: https://lore.kernel.org/r/20230315062032.1741692-1-windhl@126.com [axboe: style cleanup] Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/sunvdc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 39aeebc6837d..d9e41d3bbe71 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -984,6 +984,8 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) print_version(); hp = mdesc_grab(); + if (!hp) + return -ENODEV; err = -ENODEV; if ((vdev->dev_no << PARTITION_SHIFT) & ~(u64)MINORMASK) { From cccba1ff0798a27f7b8d0c06762ef977400a2afb Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Tue, 14 Mar 2023 10:45:43 -0700 Subject: [PATCH 2168/4345] ice: xsk: disable txq irq before flushing hw [ Upstream commit b830c9642386867863ac64295185f896ff2928ac ] ice_qp_dis() intends to stop a given queue pair that is a target of xsk pool attach/detach. One of the steps is to disable interrupts on these queues. It currently is broken in a way that txq irq is turned off *after* HW flush which in turn takes no effect. ice_qp_dis(): -> ice_qvec_dis_irq() --> disable rxq irq --> flush hw -> ice_vsi_stop_tx_ring() -->disable txq irq Below splat can be triggered by following steps: - start xdpsock WITHOUT loading xdp prog - run xdp_rxq_info with XDP_TX action on this interface - start traffic - terminate xdpsock [ 256.312485] BUG: kernel NULL pointer dereference, address: 0000000000000018 [ 256.319560] #PF: supervisor read access in kernel mode [ 256.324775] #PF: error_code(0x0000) - not-present page [ 256.329994] PGD 0 P4D 0 [ 256.332574] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 256.337006] CPU: 3 PID: 32 Comm: ksoftirqd/3 Tainted: G OE 6.2.0-rc5+ #51 [ 256.345218] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [ 256.355807] RIP: 0010:ice_clean_rx_irq_zc+0x9c/0x7d0 [ice] [ 256.361423] Code: b7 8f 8a 00 00 00 66 39 ca 0f 84 f1 04 00 00 49 8b 47 40 4c 8b 24 d0 41 0f b7 45 04 66 25 ff 3f 66 89 04 24 0f 84 85 02 00 00 <49> 8b 44 24 18 0f b7 14 24 48 05 00 01 00 00 49 89 04 24 49 89 44 [ 256.380463] RSP: 0018:ffffc900088bfd20 EFLAGS: 00010206 [ 256.385765] RAX: 000000000000003c RBX: 0000000000000035 RCX: 000000000000067f [ 256.393012] RDX: 0000000000000775 RSI: 0000000000000000 RDI: ffff8881deb3ac80 [ 256.400256] RBP: 000000000000003c R08: ffff889847982710 R09: 0000000000010000 [ 256.407500] R10: ffffffff82c060c0 R11: 0000000000000004 R12: 0000000000000000 [ 256.414746] R13: ffff88811165eea0 R14: ffffc9000d255000 R15: ffff888119b37600 [ 256.421990] FS: 0000000000000000(0000) GS:ffff8897e0cc0000(0000) knlGS:0000000000000000 [ 256.430207] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 256.436036] CR2: 0000000000000018 CR3: 0000000005c0a006 CR4: 00000000007706e0 [ 256.443283] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 256.450527] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 256.457770] PKRU: 55555554 [ 256.460529] Call Trace: [ 256.463015] [ 256.465157] ? ice_xmit_zc+0x6e/0x150 [ice] [ 256.469437] ice_napi_poll+0x46d/0x680 [ice] [ 256.473815] ? _raw_spin_unlock_irqrestore+0x1b/0x40 [ 256.478863] __napi_poll+0x29/0x160 [ 256.482409] net_rx_action+0x136/0x260 [ 256.486222] __do_softirq+0xe8/0x2e5 [ 256.489853] ? smpboot_thread_fn+0x2c/0x270 [ 256.494108] run_ksoftirqd+0x2a/0x50 [ 256.497747] smpboot_thread_fn+0x1c1/0x270 [ 256.501907] ? __pfx_smpboot_thread_fn+0x10/0x10 [ 256.506594] kthread+0xea/0x120 [ 256.509785] ? __pfx_kthread+0x10/0x10 [ 256.513597] ret_from_fork+0x29/0x50 [ 256.517238] In fact, irqs were not disabled and napi managed to be scheduled and run while xsk_pool pointer was still valid, but SW ring of xdp_buff pointers was already freed. To fix this, call ice_qvec_dis_irq() after ice_vsi_stop_tx_ring(). Also while at it, remove redundant ice_clean_rx_ring() call - this is handled in ice_qp_clean_rings(). Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Signed-off-by: Maciej Fijalkowski Reviewed-by: Larysa Zaremba Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Acked-by: John Fastabend Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ice/ice_xsk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 59963b901be0..e0790df700e2 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -169,8 +169,6 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) } netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); - ice_qvec_dis_irq(vsi, rx_ring, q_vector); - ice_fill_txq_meta(vsi, tx_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta); if (err) @@ -185,6 +183,8 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } + ice_qvec_dis_irq(vsi, rx_ring, q_vector); + err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; From 1f0586dcc0768e95006c99598fe101302f78fac1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 14 Mar 2023 20:24:05 +0200 Subject: [PATCH 2169/4345] net: dsa: mv88e6xxx: fix max_mtu of 1492 on 6165, 6191, 6220, 6250, 6290 [ Upstream commit 7e9517375a14f44ee830ca1c3278076dd65fcc8f ] There are 3 classes of switch families that the driver is aware of, as far as mv88e6xxx_change_mtu() is concerned: - MTU configuration is available per port. Here, the chip->info->ops->port_set_jumbo_size() method will be present. - MTU configuration is global to the switch. Here, the chip->info->ops->set_max_frame_size() method will be present. - We don't know how to change the MTU. Here, none of the above methods will be present. Switch families MV88E6165, MV88E6191, MV88E6220, MV88E6250 and MV88E6290 fall in category 3. The blamed commit has adjusted the MTU for all 3 categories by EDSA_HLEN (8 bytes), resulting in a new maximum MTU of 1492 being reported by the driver for these switches. I don't have the hardware to test, but I do have a MV88E6390 switch on which I can simulate this by commenting out its .port_set_jumbo_size definition from mv88e6390_ops. The result is this set of messages at probe time: mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 1 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 2 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 3 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 4 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 5 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 6 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 7 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 8 It is highly implausible that there exist Ethernet switches which don't support the standard MTU of 1500 octets, and this is what the DSA framework says as well - the error comes from dsa_slave_create() -> dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN). But the error messages are alarming, and it would be good to suppress them. As a consequence of this unlikeliness, we reimplement mv88e6xxx_get_max_mtu() and mv88e6xxx_change_mtu() on switches from the 3rd category as follows: the maximum supported MTU is 1500, and any request to set the MTU to a value larger than that fails in dev_validate_mtu(). Fixes: b9c587fed61c ("dsa: mv88e6xxx: Include tagger overhead when setting MTU for DSA and CPU ports") Signed-off-by: Vladimir Oltean Reviewed-by: Simon Horman Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/mv88e6xxx/chip.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 371b345635e6..a253476a52b0 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2734,7 +2734,7 @@ static int mv88e6xxx_get_max_mtu(struct dsa_switch *ds, int port) return 10240 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; else if (chip->info->ops->set_max_frame_size) return 1632 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; - return 1522 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; + return ETH_DATA_LEN; } static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) @@ -2742,6 +2742,17 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) struct mv88e6xxx_chip *chip = ds->priv; int ret = 0; + /* For families where we don't know how to alter the MTU, + * just accept any value up to ETH_DATA_LEN + */ + if (!chip->info->ops->port_set_jumbo_size && + !chip->info->ops->set_max_frame_size) { + if (new_mtu > ETH_DATA_LEN) + return -EINVAL; + + return 0; + } + if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) new_mtu += EDSA_HLEN; @@ -2750,9 +2761,6 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) ret = chip->info->ops->port_set_jumbo_size(chip, port, new_mtu); else if (chip->info->ops->set_max_frame_size) ret = chip->info->ops->set_max_frame_size(chip, new_mtu); - else - if (new_mtu > 1522) - ret = -EINVAL; mv88e6xxx_reg_unlock(chip); return ret; From 013fae04b8ff8b00ad7c60633b4d3ae2c22d1086 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 15 Mar 2023 14:40:09 +0200 Subject: [PATCH 2170/4345] ipv4: Fix incorrect table ID in IOCTL path [ Upstream commit 8a2618e14f81604a9b6ad305d57e0c8da939cd65 ] Commit f96a3d74554d ("ipv4: Fix incorrect route flushing when source address is deleted") started to take the table ID field in the FIB info structure into account when determining if two structures are identical or not. This field is initialized using the 'fc_table' field in the route configuration structure, which is not set when adding a route via IOCTL. The above can result in user space being able to install two identical routes that only differ in the table ID field of their associated FIB info. Fix by initializing the table ID field in the route configuration structure in the IOCTL path. Before the fix: # ip route add default via 192.0.2.2 # route add default gw 192.0.2.2 # ip -4 r show default # default via 192.0.2.2 dev dummy10 # default via 192.0.2.2 dev dummy10 After the fix: # ip route add default via 192.0.2.2 # route add default gw 192.0.2.2 SIOCADDRT: File exists # ip -4 r show default default via 192.0.2.2 dev dummy10 Audited the code paths to ensure there are no other paths that do not properly initialize the route configuration structure when installing a route. Fixes: 5a56a0b3a45d ("net: Don't delete routes in different VRFs") Fixes: f96a3d74554d ("ipv4: Fix incorrect route flushing when source address is deleted") Reported-by: gaoxingwang Link: https://lore.kernel.org/netdev/20230314144159.2354729-1-gaoxingwang1@huawei.com/ Tested-by: gaoxingwang Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230315124009.4015212-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/fib_frontend.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 5f786ef662ea..41f890bf9d4c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -573,6 +573,9 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, cfg->fc_scope = RT_SCOPE_UNIVERSE; } + if (!cfg->fc_table) + cfg->fc_table = RT_TABLE_MAIN; + if (cmd == SIOCDELRT) return 0; From 2cc46ed406bb325f10a251b03d9a83ae67b3d3d8 Mon Sep 17 00:00:00 2001 From: Szymon Heidrich Date: Thu, 16 Mar 2023 12:05:40 +0100 Subject: [PATCH 2171/4345] net: usb: smsc75xx: Move packet length check to prevent kernel panic in skb_pull [ Upstream commit 43ffe6caccc7a1bb9d7442fbab521efbf6c1378c ] Packet length check needs to be located after size and align_count calculation to prevent kernel panic in skb_pull() in case rx_cmd_a & RX_CMD_A_RED evaluates to true. Fixes: d8b228318935 ("net: usb: smsc75xx: Limit packet length to skb->len") Signed-off-by: Szymon Heidrich Link: https://lore.kernel.org/r/20230316110540.77531-1-szymon.heidrich@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/usb/smsc75xx.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 0b3d11e28faa..fb1389bd0939 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2199,6 +2199,13 @@ static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) size = (rx_cmd_a & RX_CMD_A_LEN) - RXW_PADDING; align_count = (4 - ((size + RXW_PADDING) % 4)) % 4; + if (unlikely(size > skb->len)) { + netif_dbg(dev, rx_err, dev->net, + "size err rx_cmd_a=0x%08x\n", + rx_cmd_a); + return 0; + } + if (unlikely(rx_cmd_a & RX_CMD_A_RED)) { netif_dbg(dev, rx_err, dev->net, "Error rx_cmd_a=0x%08x\n", rx_cmd_a); @@ -2211,8 +2218,7 @@ static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) dev->net->stats.rx_frame_errors++; } else { /* MAX_SINGLE_PACKET_SIZE + 4(CRC) + 2(COE) + 4(Vlan) */ - if (unlikely(size > (MAX_SINGLE_PACKET_SIZE + ETH_HLEN + 12) || - size > skb->len)) { + if (unlikely(size > (MAX_SINGLE_PACKET_SIZE + ETH_HLEN + 12))) { netif_dbg(dev, rx_err, dev->net, "size err rx_cmd_a=0x%08x\n", rx_cmd_a); From bd2e78462ae18484e55ae4d285df2c86b86bdd12 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Wed, 15 Mar 2023 14:14:35 +0100 Subject: [PATCH 2172/4345] net/iucv: Fix size of interrupt data [ Upstream commit 3d87debb8ed2649608ff432699e7c961c0c6f03b ] iucv_irq_data needs to be 4 bytes larger. These bytes are not used by the iucv module, but written by the z/VM hypervisor in case a CPU is deconfigured. Reported as: BUG dma-kmalloc-64 (Not tainted): kmalloc Redzone overwritten ----------------------------------------------------------------------------- 0x0000000000400564-0x0000000000400567 @offset=1380. First byte 0x80 instead of 0xcc Allocated in iucv_cpu_prepare+0x44/0xd0 age=167839 cpu=2 pid=1 __kmem_cache_alloc_node+0x166/0x450 kmalloc_node_trace+0x3a/0x70 iucv_cpu_prepare+0x44/0xd0 cpuhp_invoke_callback+0x156/0x2f0 cpuhp_issue_call+0xf0/0x298 __cpuhp_setup_state_cpuslocked+0x136/0x338 __cpuhp_setup_state+0xf4/0x288 iucv_init+0xf4/0x280 do_one_initcall+0x78/0x390 do_initcalls+0x11a/0x140 kernel_init_freeable+0x25e/0x2a0 kernel_init+0x2e/0x170 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 Freed in iucv_init+0x92/0x280 age=167839 cpu=2 pid=1 __kmem_cache_free+0x308/0x358 iucv_init+0x92/0x280 do_one_initcall+0x78/0x390 do_initcalls+0x11a/0x140 kernel_init_freeable+0x25e/0x2a0 kernel_init+0x2e/0x170 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 Slab 0x0000037200010000 objects=32 used=30 fp=0x0000000000400640 flags=0x1ffff00000010200(slab|head|node=0|zone=0| Object 0x0000000000400540 @offset=1344 fp=0x0000000000000000 Redzone 0000000000400500: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Redzone 0000000000400510: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Redzone 0000000000400520: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Redzone 0000000000400530: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Object 0000000000400540: 00 01 00 03 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object 0000000000400550: f3 86 81 f2 f4 82 f8 82 f0 f0 f0 f0 f0 f0 f0 f2 ................ Object 0000000000400560: 00 00 00 00 80 00 00 00 cc cc cc cc cc cc cc cc ................ Object 0000000000400570: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Redzone 0000000000400580: cc cc cc cc cc cc cc cc ........ Padding 00000000004005d4: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZZZZZ Padding 00000000004005e4: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZZZZZ Padding 00000000004005f4: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZ CPU: 6 PID: 121030 Comm: 116-pai-crypto. Not tainted 6.3.0-20230221.rc0.git4.99b8246b2d71.300.fc37.s390x+debug #1 Hardware name: IBM 3931 A01 704 (z/VM 7.3.0) Call Trace: [<000000032aa034ec>] dump_stack_lvl+0xac/0x100 [<0000000329f5a6cc>] check_bytes_and_report+0x104/0x140 [<0000000329f5aa78>] check_object+0x370/0x3c0 [<0000000329f5ede6>] free_debug_processing+0x15e/0x348 [<0000000329f5f06a>] free_to_partial_list+0x9a/0x2f0 [<0000000329f5f4a4>] __slab_free+0x1e4/0x3a8 [<0000000329f61768>] __kmem_cache_free+0x308/0x358 [<000000032a91465c>] iucv_cpu_dead+0x6c/0x88 [<0000000329c2fc66>] cpuhp_invoke_callback+0x156/0x2f0 [<000000032aa062da>] _cpu_down.constprop.0+0x22a/0x5e0 [<0000000329c3243e>] cpu_device_down+0x4e/0x78 [<000000032a61dee0>] device_offline+0xc8/0x118 [<000000032a61e048>] online_store+0x60/0xe0 [<000000032a08b6b0>] kernfs_fop_write_iter+0x150/0x1e8 [<0000000329fab65c>] vfs_write+0x174/0x360 [<0000000329fab9fc>] ksys_write+0x74/0x100 [<000000032aa03a5a>] __do_syscall+0x1da/0x208 [<000000032aa177b2>] system_call+0x82/0xb0 INFO: lockdep is turned off. FIX dma-kmalloc-64: Restoring kmalloc Redzone 0x0000000000400564-0x0000000000400567=0xcc FIX dma-kmalloc-64: Object at 0x0000000000400540 not freed Fixes: 2356f4cb1911 ("[S390]: Rewrite of the IUCV base code, part 2") Signed-off-by: Alexandra Winter Link: https://lore.kernel.org/r/20230315131435.4113889-1-wintera@linux.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/iucv/iucv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 349c6ac3313f..6f84978a7726 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -83,7 +83,7 @@ struct iucv_irq_data { u16 ippathid; u8 ipflags1; u8 iptype; - u32 res2[8]; + u32 res2[9]; }; struct iucv_irq_list { From 1c06d12237282200566a556be965f4d7801d6ec8 Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Thu, 16 Mar 2023 00:53:53 +0800 Subject: [PATCH 2173/4345] selftests: net: devlink_port_split.py: skip test if no suitable device available [ Upstream commit 24994513ad13ff2c47ba91d2b5df82c3d496c370 ] The `devlink -j port show` command output may not contain the "flavour" key, an example from Ubuntu 22.10 s390x LPAR(5.19.0-37-generic), with mlx4 driver and iproute2-5.15.0: {"port":{"pci/0001:00:00.0/1":{"type":"eth","netdev":"ens301"}, "pci/0001:00:00.0/2":{"type":"eth","netdev":"ens301d1"}, "pci/0002:00:00.0/1":{"type":"eth","netdev":"ens317"}, "pci/0002:00:00.0/2":{"type":"eth","netdev":"ens317d1"}}} This will cause a KeyError exception. Create a validate_devlink_output() to check for this "flavour" from devlink command output to avoid this KeyError exception. Also let it handle the check for `devlink -j dev show` output in main(). Apart from this, if the test was not started because the max lanes of the designated device is 0. The script will still return 0 and thus causing a false-negative test result. Use a found_max_lanes flag to determine if these tests were skipped due to this reason and return KSFT_SKIP to make it more clear. Link: https://bugs.launchpad.net/bugs/1937133 Fixes: f3348a82e727 ("selftests: net: Add port split test") Signed-off-by: Po-Hsu Lin Link: https://lore.kernel.org/r/20230315165353.229590-1-po-hsu.lin@canonical.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- .../selftests/net/devlink_port_split.py | 30 +++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py index 834066d465fc..f0fbd7367f4f 100755 --- a/tools/testing/selftests/net/devlink_port_split.py +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -57,6 +57,8 @@ class devlink_ports(object): assert stderr == "" ports = json.loads(stdout)['port'] + validate_devlink_output(ports, 'flavour') + for port in ports: if dev in port: if ports[port]['flavour'] == 'physical': @@ -218,6 +220,27 @@ def split_splittable_port(port, k, lanes, dev): unsplit(port.bus_info) +def validate_devlink_output(devlink_data, target_property=None): + """ + Determine if test should be skipped by checking: + 1. devlink_data contains values + 2. The target_property exist in devlink_data + """ + skip_reason = None + if any(devlink_data.values()): + if target_property: + skip_reason = "{} not found in devlink output, test skipped".format(target_property) + for key in devlink_data: + if target_property in devlink_data[key]: + skip_reason = None + else: + skip_reason = 'devlink output is empty, test skipped' + + if skip_reason: + print(skip_reason) + sys.exit(KSFT_SKIP) + + def make_parser(): parser = argparse.ArgumentParser(description='A test for port splitting.') parser.add_argument('--dev', @@ -238,6 +261,7 @@ def main(cmdline=None): stdout, stderr = run_command(cmd) assert stderr == "" + validate_devlink_output(json.loads(stdout)) devs = json.loads(stdout)['dev'] dev = list(devs.keys())[0] @@ -249,6 +273,7 @@ def main(cmdline=None): ports = devlink_ports(dev) + found_max_lanes = False for port in ports.if_names: max_lanes = get_max_lanes(port.name) @@ -271,6 +296,11 @@ def main(cmdline=None): split_splittable_port(port, lane, max_lanes, dev) lane //= 2 + found_max_lanes = True + + if not found_max_lanes: + print(f"Test not started, no port of device {dev} reports max_lanes") + sys.exit(KSFT_SKIP) if __name__ == "__main__": From eb80cb66a2c5e94794bcb52fc6272a7ab20152f4 Mon Sep 17 00:00:00 2001 From: Daniil Tatianin Date: Wed, 15 Mar 2023 22:46:18 +0300 Subject: [PATCH 2174/4345] qed/qed_mng_tlv: correctly zero out ->min instead of ->hour [ Upstream commit 470efd68a4653d9819d391489886432cd31bcd0b ] This fixes an issue where ->hour would erroneously get zeroed out instead of ->min because of a bad copy paste. Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Fixes: f240b6882211 ("qed: Add support for processing fcoe tlv request.") Signed-off-by: Daniil Tatianin Link: https://lore.kernel.org/r/20230315194618.579286-1-d-tatianin@yandex-team.ru Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c index 3e3192a3ad9b..fdbd5f07a185 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c @@ -422,7 +422,7 @@ qed_mfw_get_tlv_time_value(struct qed_mfw_tlv_time *p_time, if (p_time->hour > 23) p_time->hour = 0; if (p_time->min > 59) - p_time->hour = 0; + p_time->min = 0; if (p_time->msec > 999) p_time->msec = 0; if (p_time->usec > 999) From d4dbd26f985c1cb9a36610708beb01cf0ed95741 Mon Sep 17 00:00:00 2001 From: Liang He Date: Wed, 15 Mar 2023 14:00:21 +0800 Subject: [PATCH 2175/4345] ethernet: sun: add check for the mdesc_grab() [ Upstream commit 90de546d9a0b3c771667af18bb3f80567eabb89b ] In vnet_port_probe() and vsw_port_probe(), we should check the return value of mdesc_grab() as it may return NULL which can caused NPD bugs. Fixes: 5d01fa0c6bd8 ("ldmvsw: Add ldmvsw.c driver code") Fixes: 43fdf27470b2 ("[SPARC64]: Abstract out mdesc accesses for better MD update handling.") Signed-off-by: Liang He Reviewed-by: Piotr Raczynski Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/sun/ldmvsw.c | 3 +++ drivers/net/ethernet/sun/sunvnet.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 01ea0d6f8819..934a4b54784b 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -290,6 +290,9 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) hp = mdesc_grab(); + if (!hp) + return -ENODEV; + rmac = mdesc_get_property(hp, vdev->mp, remote_macaddr_prop, &len); err = -ENODEV; if (!rmac) { diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 96b883f965f6..b6c03adf1e76 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -431,6 +431,9 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) hp = mdesc_grab(); + if (!hp) + return -ENODEV; + vp = vnet_find_parent(hp, vdev->mp, vdev); if (IS_ERR(vp)) { pr_err("Cannot find port parent vnet\n"); From aff84fadba53befed494a28c84544c87fce908c4 Mon Sep 17 00:00:00 2001 From: Tony O'Brien Date: Wed, 22 Feb 2023 13:52:27 +1300 Subject: [PATCH 2176/4345] hwmon: (adt7475) Display smoothing attributes in correct order [ Upstream commit 5f8d1e3b6f9b5971f9c06d5846ce00c49e3a8d94 ] Throughout the ADT7475 driver, attributes relating to the temperature sensors are displayed in the order Remote 1, Local, Remote 2. Make temp_st_show() conform to this expectation so that values set by temp_st_store() can be displayed using the correct attribute. Fixes: 8f05bcc33e74 ("hwmon: (adt7475) temperature smoothing") Signed-off-by: Tony O'Brien Link: https://lore.kernel.org/r/20230222005228.158661-2-tony.obrien@alliedtelesis.co.nz Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/adt7475.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 9d5b019651f2..c7f19a1ca0a5 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -554,11 +554,11 @@ static ssize_t temp_st_show(struct device *dev, struct device_attribute *attr, val = data->enh_acoustics[0] & 0xf; break; case 1: - val = (data->enh_acoustics[1] >> 4) & 0xf; + val = data->enh_acoustics[1] & 0xf; break; case 2: default: - val = data->enh_acoustics[1] & 0xf; + val = (data->enh_acoustics[1] >> 4) & 0xf; break; } From 4a8c3ad12c9dd6456ae3fade707166935bf29ba5 Mon Sep 17 00:00:00 2001 From: Tony O'Brien Date: Wed, 22 Feb 2023 13:52:28 +1300 Subject: [PATCH 2177/4345] hwmon: (adt7475) Fix masking of hysteresis registers [ Upstream commit 48e8186870d9d0902e712d601ccb7098cb220688 ] The wrong bits are masked in the hysteresis register; indices 0 and 2 should zero bits [7:4] and preserve bits [3:0], and index 1 should zero bits [3:0] and preserve bits [7:4]. Fixes: 1c301fc5394f ("hwmon: Add a driver for the ADT7475 hardware monitoring chip") Signed-off-by: Tony O'Brien Link: https://lore.kernel.org/r/20230222005228.158661-3-tony.obrien@alliedtelesis.co.nz Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/adt7475.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index c7f19a1ca0a5..6b84822e7d93 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -486,10 +486,10 @@ static ssize_t temp_store(struct device *dev, struct device_attribute *attr, val = (temp - val) / 1000; if (sattr->index != 1) { - data->temp[HYSTERSIS][sattr->index] &= 0xF0; + data->temp[HYSTERSIS][sattr->index] &= 0x0F; data->temp[HYSTERSIS][sattr->index] |= (val & 0xF) << 4; } else { - data->temp[HYSTERSIS][sattr->index] &= 0x0F; + data->temp[HYSTERSIS][sattr->index] &= 0xF0; data->temp[HYSTERSIS][sattr->index] |= (val & 0xF); } From 0a73c8b3cc99d214dff83c51805c844240c4f749 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Fri, 10 Mar 2023 16:40:07 +0800 Subject: [PATCH 2178/4345] hwmon: (xgene) Fix use after free bug in xgene_hwmon_remove due to race condition [ Upstream commit cb090e64cf25602b9adaf32d5dfc9c8bec493cd1 ] In xgene_hwmon_probe, &ctx->workq is bound with xgene_hwmon_evt_work. Then it will be started. If we remove the driver which will call xgene_hwmon_remove to clean up, there may be unfinished work. The possible sequence is as follows: Fix it by finishing the work before cleanup in xgene_hwmon_remove. CPU0 CPU1 |xgene_hwmon_evt_work xgene_hwmon_remove | kfifo_free(&ctx->async_msg_fifo);| | |kfifo_out_spinlocked |//use &ctx->async_msg_fifo Fixes: 2ca492e22cb7 ("hwmon: (xgene) Fix crash when alarm occurs before driver probe") Signed-off-by: Zheng Wang Link: https://lore.kernel.org/r/20230310084007.1403388-1-zyytlz.wz@163.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/xgene-hwmon.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c index f2a5af239c95..f5d3cf86753f 100644 --- a/drivers/hwmon/xgene-hwmon.c +++ b/drivers/hwmon/xgene-hwmon.c @@ -768,6 +768,7 @@ static int xgene_hwmon_remove(struct platform_device *pdev) { struct xgene_hwmon_dev *ctx = platform_get_drvdata(pdev); + cancel_work_sync(&ctx->workq); hwmon_device_unregister(ctx->hwmon_dev); kfifo_free(&ctx->async_msg_fifo); if (acpi_disabled) From 663c3afee81ea56952293b869c623e7dd20548ec Mon Sep 17 00:00:00 2001 From: Marcus Folkesson Date: Fri, 10 Mar 2023 08:50:35 +0100 Subject: [PATCH 2179/4345] hwmon: (ina3221) return prober error code [ Upstream commit c93f5e2ab53243b17febabb9422a697017d3d49a ] ret is set to 0 which do not indicate an error. Return -EINVAL instead. Fixes: a9e9dd9c6de5 ("hwmon: (ina3221) Read channel input source info from DT") Signed-off-by: Marcus Folkesson Link: https://lore.kernel.org/r/20230310075035.246083-1-marcus.folkesson@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/ina3221.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/ina3221.c b/drivers/hwmon/ina3221.c index d3c98115042b..836e7579e166 100644 --- a/drivers/hwmon/ina3221.c +++ b/drivers/hwmon/ina3221.c @@ -772,7 +772,7 @@ static int ina3221_probe_child_from_dt(struct device *dev, return ret; } else if (val > INA3221_CHANNEL3) { dev_err(dev, "invalid reg %d of %pOFn\n", val, child); - return ret; + return -EINVAL; } input = &ina->inputs[val]; From c5bd9719b53be9afe872bc03a88ba5df3a5fd00e Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 12 Mar 2023 09:03:12 -0700 Subject: [PATCH 2180/4345] hwmon: (ucd90320) Add minimum delay between bus accesses [ Upstream commit 8d655e65237643c48ada2c131b83679bf1105373 ] When probing the ucd90320 access to some of the registers randomly fails. Sometimes it NACKs a transfer, sometimes it returns just random data and the PEC check fails. Experimentation shows that this seems to be triggered by a register access directly back to back with a previous register write. Experimentation also shows that inserting a small delay after register writes makes the issue go away. Use a similar solution to what the max15301 driver does to solve the same problem. Create a custom set of bus read and write functions that make sure that the delay is added. Fixes: a470f11c5ba2 ("hwmon: (pmbus/ucd9000) Add support for UCD90320 Power Sequencer") Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230312160312.2227405-1-lars@metafoo.de Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/pmbus/ucd9000.c | 75 +++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c index f8017993e2b4..9e26cc084a17 100644 --- a/drivers/hwmon/pmbus/ucd9000.c +++ b/drivers/hwmon/pmbus/ucd9000.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -16,6 +17,7 @@ #include #include #include +#include #include "pmbus.h" enum chips { ucd9000, ucd90120, ucd90124, ucd90160, ucd90320, ucd9090, @@ -65,6 +67,7 @@ struct ucd9000_data { struct gpio_chip gpio; #endif struct dentry *debugfs; + ktime_t write_time; }; #define to_ucd9000_data(_info) container_of(_info, struct ucd9000_data, info) @@ -73,6 +76,73 @@ struct ucd9000_debugfs_entry { u8 index; }; +/* + * It has been observed that the UCD90320 randomly fails register access when + * doing another access right on the back of a register write. To mitigate this + * make sure that there is a minimum delay between a write access and the + * following access. The 250us is based on experimental data. At a delay of + * 200us the issue seems to go away. Add a bit of extra margin to allow for + * system to system differences. + */ +#define UCD90320_WAIT_DELAY_US 250 + +static inline void ucd90320_wait(const struct ucd9000_data *data) +{ + s64 delta = ktime_us_delta(ktime_get(), data->write_time); + + if (delta < UCD90320_WAIT_DELAY_US) + udelay(UCD90320_WAIT_DELAY_US - delta); +} + +static int ucd90320_read_word_data(struct i2c_client *client, int page, + int phase, int reg) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct ucd9000_data *data = to_ucd9000_data(info); + + if (reg >= PMBUS_VIRT_BASE) + return -ENXIO; + + ucd90320_wait(data); + return pmbus_read_word_data(client, page, phase, reg); +} + +static int ucd90320_read_byte_data(struct i2c_client *client, int page, int reg) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct ucd9000_data *data = to_ucd9000_data(info); + + ucd90320_wait(data); + return pmbus_read_byte_data(client, page, reg); +} + +static int ucd90320_write_word_data(struct i2c_client *client, int page, + int reg, u16 word) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct ucd9000_data *data = to_ucd9000_data(info); + int ret; + + ucd90320_wait(data); + ret = pmbus_write_word_data(client, page, reg, word); + data->write_time = ktime_get(); + + return ret; +} + +static int ucd90320_write_byte(struct i2c_client *client, int page, u8 value) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct ucd9000_data *data = to_ucd9000_data(info); + int ret; + + ucd90320_wait(data); + ret = pmbus_write_byte(client, page, value); + data->write_time = ktime_get(); + + return ret; +} + static int ucd9000_get_fan_config(struct i2c_client *client, int fan) { int fan_config = 0; @@ -598,6 +668,11 @@ static int ucd9000_probe(struct i2c_client *client) info->read_byte_data = ucd9000_read_byte_data; info->func[0] |= PMBUS_HAVE_FAN12 | PMBUS_HAVE_STATUS_FAN12 | PMBUS_HAVE_FAN34 | PMBUS_HAVE_STATUS_FAN34; + } else if (mid->driver_data == ucd90320) { + info->read_byte_data = ucd90320_read_byte_data; + info->read_word_data = ucd90320_read_word_data; + info->write_byte = ucd90320_write_byte; + info->write_word_data = ucd90320_write_word_data; } ucd9000_probe_gpio(client, mid, data); From a4c3e1132422b8cdb515fbe64162419c3c761a9f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 20:37:23 +0100 Subject: [PATCH 2181/4345] hwmon: tmp512: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 00d85e81796b17a29a0e096c5a4735daa47adef8 ] The driver will match mostly by DT table (even thought there is regular ID table) so there is little benefit in of_match_ptr (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/hwmon/tmp513.c:610:34: error: ‘tmp51x_of_match’ defined but not used [-Werror=unused-const-variable=] Fixes: 59dfa75e5d82 ("hwmon: Add driver for Texas Instruments TMP512/513 sensor chips.") Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312193723.478032-2-krzysztof.kozlowski@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/tmp513.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/tmp513.c b/drivers/hwmon/tmp513.c index 47bbe47e062f..7d5f7441aceb 100644 --- a/drivers/hwmon/tmp513.c +++ b/drivers/hwmon/tmp513.c @@ -758,7 +758,7 @@ static int tmp51x_probe(struct i2c_client *client) static struct i2c_driver tmp51x_driver = { .driver = { .name = "tmp51x", - .of_match_table = of_match_ptr(tmp51x_of_match), + .of_match_table = tmp51x_of_match, }, .probe_new = tmp51x_probe, .id_table = tmp51x_id, From a4c048d502eb24fd8040f88031a493b1f10cd4e9 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 14 Mar 2023 02:31:45 -0700 Subject: [PATCH 2182/4345] hwmon: (adm1266) Set `can_sleep` flag for GPIO chip [ Upstream commit a5bb73b3f5db1a4e91402ad132b59b13d2651ed9 ] The adm1266 driver uses I2C bus access in its GPIO chip `set` and `get` implementation. This means these functions can sleep and the GPIO chip should set the `can_sleep` property to true. This will ensure that a warning is printed when trying to set or get the GPIO value from a context that potentially can't sleep. Fixes: d98dfad35c38 ("hwmon: (pmbus/adm1266) Add support for GPIOs") Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230314093146.2443845-1-lars@metafoo.de Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/pmbus/adm1266.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwmon/pmbus/adm1266.c b/drivers/hwmon/pmbus/adm1266.c index c7b373ba92f2..d1b2e936546f 100644 --- a/drivers/hwmon/pmbus/adm1266.c +++ b/drivers/hwmon/pmbus/adm1266.c @@ -301,6 +301,7 @@ static int adm1266_config_gpio(struct adm1266_data *data) data->gc.label = name; data->gc.parent = &data->client->dev; data->gc.owner = THIS_MODULE; + data->gc.can_sleep = true; data->gc.base = -1; data->gc.names = data->gpio_names; data->gc.ngpio = ARRAY_SIZE(data->gpio_names); From 04eaeaa2f79fa5a4df421d24492e241ac5e0fb28 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 17 Mar 2023 13:51:17 -0700 Subject: [PATCH 2183/4345] media: m5mols: fix off-by-one loop termination error [ Upstream commit efbcbb12ee99f750c9f25c873b55ad774871de2a ] The __find_restype() function loops over the m5mols_default_ffmt[] array, and the termination condition ends up being wrong: instead of stopping when the iterator becomes the size of the array it traverses, it stops after it has already overshot the array. Now, in practice this doesn't likely matter, because the code will always find the entry it looks for, and will thus return early and never hit that last extra iteration. But it turns out that clang will unroll the loop fully, because it has only two iterations (well, three due to the off-by-one bug), and then clang will end up just giving up in the middle of the loop unrolling when it notices that the code walks past the end of the array. And that made 'objtool' very unhappy indeed, because the generated code just falls off the edge of the universe, and ends up falling through to the next function, causing this warning: drivers/media/i2c/m5mols/m5mols.o: warning: objtool: m5mols_set_fmt() falls through to next function m5mols_get_frame_desc() Fix the loop ending condition. Reported-by: Jens Axboe Analyzed-by: Miguel Ojeda Analyzed-by: Nick Desaulniers Link: https://lore.kernel.org/linux-block/CAHk-=wgTSdKYbmB1JYM5vmHMcD9J9UZr0mn7BOYM_LudrP+Xvw@mail.gmail.com/ Fixes: bc125106f8af ("[media] Add support for M-5MOLS 8 Mega Pixel camera ISP") Cc: HeungJun, Kim Cc: Sylwester Nawrocki Cc: Kyungmin Park Cc: Mauro Carvalho Chehab Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- drivers/media/i2c/m5mols/m5mols_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/m5mols/m5mols_core.c b/drivers/media/i2c/m5mols/m5mols_core.c index 21666d705e37..dcf9e4d4ee6b 100644 --- a/drivers/media/i2c/m5mols/m5mols_core.c +++ b/drivers/media/i2c/m5mols/m5mols_core.c @@ -488,7 +488,7 @@ static enum m5mols_restype __find_restype(u32 code) do { if (code == m5mols_default_ffmt[type].code) return type; - } while (type++ != SIZE_DEFAULT_FFMT); + } while (++type != SIZE_DEFAULT_FFMT); return 0; } From 980d4e70c7085351623ad6c5ff104ea0c5f0abc4 Mon Sep 17 00:00:00 2001 From: Tobias Schramm Date: Fri, 30 Dec 2022 20:43:15 +0100 Subject: [PATCH 2184/4345] mmc: atmel-mci: fix race between stop command and start of next command [ Upstream commit eca5bd666b0aa7dc0bca63292e4778968241134e ] This commit fixes a race between completion of stop command and start of a new command. Previously the command ready interrupt was enabled before stop command was written to the command register. This caused the command ready interrupt to fire immediately since the CMDRDY flag is asserted constantly while there is no command in progress. Consequently the command state machine will immediately advance to the next state when the tasklet function is executed again, no matter actual completion state of the stop command. Thus a new command can then be dispatched immediately, interrupting and corrupting the stop command on the CMD line. Fix that by dropping the command ready interrupt enable before calling atmci_send_stop_cmd. atmci_send_stop_cmd does already enable the command ready interrupt, no further writes to ATMCI_IER are necessary. Signed-off-by: Tobias Schramm Acked-by: Ludovic Desroches Link: https://lore.kernel.org/r/20221230194315.809903-2-t.schramm@manjaro.org Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/atmel-mci.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index af85b32c6c1c..c468f9a02ef6 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -1818,7 +1818,6 @@ static void atmci_tasklet_func(unsigned long priv) atmci_writel(host, ATMCI_IER, ATMCI_NOTBUSY); state = STATE_WAITING_NOTBUSY; } else if (host->mrq->stop) { - atmci_writel(host, ATMCI_IER, ATMCI_CMDRDY); atmci_send_stop_cmd(host, data); state = STATE_SENDING_STOP; } else { @@ -1851,8 +1850,6 @@ static void atmci_tasklet_func(unsigned long priv) * command to send. */ if (host->mrq->stop) { - atmci_writel(host, ATMCI_IER, - ATMCI_CMDRDY); atmci_send_stop_cmd(host, data); state = STATE_SENDING_STOP; } else { From 8e7f26b9565a83e6116ce24512191e21f13c7a7f Mon Sep 17 00:00:00 2001 From: Yifei Liu Date: Wed, 3 Aug 2022 15:53:12 +0000 Subject: [PATCH 2185/4345] jffs2: correct logic when creating a hole in jffs2_write_begin [ Upstream commit 23892d383bee15b64f5463bd7195615734bb2415 ] Bug description and fix: 1. Write data to a file, say all 1s from offset 0 to 16. 2. Truncate the file to a smaller size, say 8 bytes. 3. Write new bytes (say 2s) from an offset past the original size of the file, say at offset 20, for 4 bytes. This is supposed to create a "hole" in the file, meaning that the bytes from offset 8 (where it was truncated above) up to the new write at offset 20, should all be 0s (zeros). 4. Flush all caches using "echo 3 > /proc/sys/vm/drop_caches" (or unmount and remount) the f/s. 5. Check the content of the file. It is wrong. The 1s that used to be between bytes 9 and 16, before the truncation, have REAPPEARED (they should be 0s). We wrote a script and helper C program to reproduce the bug (reproduce_jffs2_write_begin_issue.sh, write_file.c, and Makefile). We can make them available to anyone. The above example is shown when writing a small file within the same first page. But the bug happens for larger files, as long as steps 1, 2, and 3 above all happen within the same page. The problem was traced to the jffs2_write_begin code, where it goes into an 'if' statement intended to handle writes past the current EOF (i.e., writes that may create a hole). The code computes a 'pageofs' that is the floor of the write position (pos), aligned to the page size boundary. In other words, 'pageofs' will never be larger than 'pos'. The code then sets the internal jffs2_raw_inode->isize to the size of max(current inode size, pageofs) but that is wrong: the new file size should be the 'pos', which is larger than both the current inode size and pageofs. Similarly, the code incorrectly sets the internal jffs2_raw_inode->dsize to the difference between the pageofs minus current inode size; instead it should be the current pos minus the current inode size. Finally, inode->i_size was also set incorrectly. The patch below fixes this bug. The bug was discovered using a new tool for finding f/s bugs using model checking, called MCFS (Model Checking File Systems). Signed-off-by: Yifei Liu Signed-off-by: Erez Zadok Signed-off-by: Manish Adkar Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- fs/jffs2/file.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index bd7d58d27bfc..97a3c09fd96b 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -138,19 +138,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); pgoff_t index = pos >> PAGE_SHIFT; - uint32_t pageofs = index << PAGE_SHIFT; int ret = 0; jffs2_dbg(1, "%s()\n", __func__); - if (pageofs > inode->i_size) { - /* Make new hole frag from old EOF to new page */ + if (pos > inode->i_size) { + /* Make new hole frag from old EOF to new position */ struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; uint32_t alloc_len; - jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", - (unsigned int)inode->i_size, pageofs); + jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new position\n", + (unsigned int)inode->i_size, (uint32_t)pos); ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); @@ -170,10 +169,10 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, ri.mode = cpu_to_jemode(inode->i_mode); ri.uid = cpu_to_je16(i_uid_read(inode)); ri.gid = cpu_to_je16(i_gid_read(inode)); - ri.isize = cpu_to_je32(max((uint32_t)inode->i_size, pageofs)); + ri.isize = cpu_to_je32((uint32_t)pos); ri.atime = ri.ctime = ri.mtime = cpu_to_je32(JFFS2_NOW()); ri.offset = cpu_to_je32(inode->i_size); - ri.dsize = cpu_to_je32(pageofs - inode->i_size); + ri.dsize = cpu_to_je32((uint32_t)pos - inode->i_size); ri.csize = cpu_to_je32(0); ri.compr = JFFS2_COMPR_ZERO; ri.node_crc = cpu_to_je32(crc32(0, &ri, sizeof(ri)-8)); @@ -203,7 +202,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, goto out_err; } jffs2_complete_reservation(c); - inode->i_size = pageofs; + inode->i_size = pos; mutex_unlock(&f->sem); } From 0bf15bc393a15dbb723c28d571326e727c60f298 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Sat, 7 Jan 2023 11:21:25 +0800 Subject: [PATCH 2186/4345] ext4: fail ext4_iget if special inode unallocated MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5cd740287ae5e3f9d1c46f5bfe8778972fd6d3fe ] In ext4_fill_super(), EXT4_ORPHAN_FS flag is cleared after ext4_orphan_cleanup() is executed. Therefore, when __ext4_iget() is called to get an inode whose i_nlink is 0 when the flag exists, no error is returned. If the inode is a special inode, a null pointer dereference may occur. If the value of i_nlink is 0 for any inodes (except boot loader inodes) got by using the EXT4_IGET_SPECIAL flag, the current file system is corrupted. Therefore, make the ext4_iget() function return an error if it gets such an abnormal special inode. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199179 Link: https://bugzilla.kernel.org/show_bug.cgi?id=216541 Link: https://bugzilla.kernel.org/show_bug.cgi?id=216539 Reported-by: Luís Henriques Suggested-by: Theodore Ts'o Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230107032126.4165860-2-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/inode.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1a654a1f3f46..6ba185b46ba3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4721,13 +4721,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, goto bad_inode; raw_inode = ext4_raw_inode(&iloc); - if ((ino == EXT4_ROOT_INO) && (raw_inode->i_links_count == 0)) { - ext4_error_inode(inode, function, line, 0, - "iget: root inode unallocated"); - ret = -EFSCORRUPTED; - goto bad_inode; - } - if ((flags & EXT4_IGET_HANDLE) && (raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) { ret = -ESTALE; @@ -4800,11 +4793,16 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, * NeilBrown 1999oct15 */ if (inode->i_nlink == 0) { - if ((inode->i_mode == 0 || + if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL || !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) && ino != EXT4_BOOT_LOADER_INO) { - /* this inode is deleted */ - ret = -ESTALE; + /* this inode is deleted or unallocated */ + if (flags & EXT4_IGET_SPECIAL) { + ext4_error_inode(inode, function, line, 0, + "iget: special inode unallocated"); + ret = -EFSCORRUPTED; + } else + ret = -ESTALE; goto bad_inode; } /* The only unlinked inodes we let through here have From a98160d8f3e6242ca9b7f443f26e7ef3a61ba684 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Tue, 10 Jan 2023 21:34:36 +0800 Subject: [PATCH 2187/4345] ext4: fix task hung in ext4_xattr_delete_inode [ Upstream commit 0f7bfd6f8164be32dbbdf36aa1e5d00485c53cd7 ] Syzbot reported a hung task problem: ================================================================== INFO: task syz-executor232:5073 blocked for more than 143 seconds. Not tainted 6.2.0-rc2-syzkaller-00024-g512dee0c00ad #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-exec232 state:D stack:21024 pid:5073 ppid:5072 flags:0x00004004 Call Trace: context_switch kernel/sched/core.c:5244 [inline] __schedule+0x995/0xe20 kernel/sched/core.c:6555 schedule+0xcb/0x190 kernel/sched/core.c:6631 __wait_on_freeing_inode fs/inode.c:2196 [inline] find_inode_fast+0x35a/0x4c0 fs/inode.c:950 iget_locked+0xb1/0x830 fs/inode.c:1273 __ext4_iget+0x22e/0x3ed0 fs/ext4/inode.c:4861 ext4_xattr_inode_iget+0x68/0x4e0 fs/ext4/xattr.c:389 ext4_xattr_inode_dec_ref_all+0x1a7/0xe50 fs/ext4/xattr.c:1148 ext4_xattr_delete_inode+0xb04/0xcd0 fs/ext4/xattr.c:2880 ext4_evict_inode+0xd7c/0x10b0 fs/ext4/inode.c:296 evict+0x2a4/0x620 fs/inode.c:664 ext4_orphan_cleanup+0xb60/0x1340 fs/ext4/orphan.c:474 __ext4_fill_super fs/ext4/super.c:5516 [inline] ext4_fill_super+0x81cd/0x8700 fs/ext4/super.c:5644 get_tree_bdev+0x400/0x620 fs/super.c:1282 vfs_get_tree+0x88/0x270 fs/super.c:1489 do_new_mount+0x289/0xad0 fs/namespace.c:3145 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x2d3/0x3c0 fs/namespace.c:3674 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fa5406fd5ea RSP: 002b:00007ffc7232f968 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007fa5406fd5ea RDX: 0000000020000440 RSI: 0000000020000000 RDI: 00007ffc7232f970 RBP: 00007ffc7232f970 R08: 00007ffc7232f9b0 R09: 0000000000000432 R10: 0000000000804a03 R11: 0000000000000202 R12: 0000000000000004 R13: 0000555556a7a2c0 R14: 00007ffc7232f9b0 R15: 0000000000000000 ================================================================== The problem is that the inode contains an xattr entry with ea_inum of 15 when cleaning up an orphan inode <15>. When evict inode <15>, the reference counting of the corresponding EA inode is decreased. When EA inode <15> is found by find_inode_fast() in __ext4_iget(), it is found that the EA inode holds the I_FREEING flag and waits for the EA inode to complete deletion. As a result, when inode <15> is being deleted, we wait for inode <15> to complete the deletion, resulting in an infinite loop and triggering Hung Task. To solve this problem, we only need to check whether the ino of EA inode and parent is the same before getting EA inode. Link: https://syzkaller.appspot.com/bug?extid=77d6fcc37bbb92f26048 Reported-by: syzbot+77d6fcc37bbb92f26048@syzkaller.appspotmail.com Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230110133436.996350-1-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/xattr.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 60e122761352..f3da1f2d4cb9 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -386,6 +386,17 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, struct inode *inode; int err; + /* + * We have to check for this corruption early as otherwise + * iget_locked() could wait indefinitely for the state of our + * parent inode. + */ + if (parent->i_ino == ea_ino) { + ext4_error(parent->i_sb, + "Parent and EA inode have the same ino %lu", ea_ino); + return -EFSCORRUPTED; + } + inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); From 6936525142a015e854d0a23e9ad9ea0a28b3843d Mon Sep 17 00:00:00 2001 From: Qu Huang Date: Tue, 21 Feb 2023 11:35:16 +0000 Subject: [PATCH 2188/4345] drm/amdkfd: Fix an illegal memory access [ Upstream commit 4fc8fff378b2f2039f2a666d9f8c570f4e58352c ] In the kfd_wait_on_events() function, the kfd_event_waiter structure is allocated by alloc_event_waiters(), but the event field of the waiter structure is not initialized; When copy_from_user() fails in the kfd_wait_on_events() function, it will enter exception handling to release the previously allocated memory of the waiter structure; Due to the event field of the waiters structure being accessed in the free_waiters() function, this results in illegal memory access and system crash, here is the crash log: localhost kernel: RIP: 0010:native_queued_spin_lock_slowpath+0x185/0x1e0 localhost kernel: RSP: 0018:ffffaa53c362bd60 EFLAGS: 00010082 localhost kernel: RAX: ff3d3d6bff4007cb RBX: 0000000000000282 RCX: 00000000002c0000 localhost kernel: RDX: ffff9e855eeacb80 RSI: 000000000000279c RDI: ffffe7088f6a21d0 localhost kernel: RBP: ffffe7088f6a21d0 R08: 00000000002c0000 R09: ffffaa53c362be64 localhost kernel: R10: ffffaa53c362bbd8 R11: 0000000000000001 R12: 0000000000000002 localhost kernel: R13: ffff9e7ead15d600 R14: 0000000000000000 R15: ffff9e7ead15d698 localhost kernel: FS: 0000152a3d111700(0000) GS:ffff9e855ee80000(0000) knlGS:0000000000000000 localhost kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 localhost kernel: CR2: 0000152938000010 CR3: 000000044d7a4000 CR4: 00000000003506e0 localhost kernel: Call Trace: localhost kernel: _raw_spin_lock_irqsave+0x30/0x40 localhost kernel: remove_wait_queue+0x12/0x50 localhost kernel: kfd_wait_on_events+0x1b6/0x490 [hydcu] localhost kernel: ? ftrace_graph_caller+0xa0/0xa0 localhost kernel: kfd_ioctl+0x38c/0x4a0 [hydcu] localhost kernel: ? kfd_ioctl_set_trap_handler+0x70/0x70 [hydcu] localhost kernel: ? kfd_ioctl_create_queue+0x5a0/0x5a0 [hydcu] localhost kernel: ? ftrace_graph_caller+0xa0/0xa0 localhost kernel: __x64_sys_ioctl+0x8e/0xd0 localhost kernel: ? syscall_trace_enter.isra.18+0x143/0x1b0 localhost kernel: do_syscall_64+0x33/0x80 localhost kernel: entry_SYSCALL_64_after_hwframe+0x44/0xa9 localhost kernel: RIP: 0033:0x152a4dff68d7 Allocate the structure with kcalloc, and remove redundant 0-initialization and a redundant loop condition check. Signed-off-by: Qu Huang Signed-off-by: Felix Kuehling Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdkfd/kfd_events.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 159be13ef20b..2c19b3775179 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -528,16 +528,13 @@ static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events) struct kfd_event_waiter *event_waiters; uint32_t i; - event_waiters = kmalloc_array(num_events, - sizeof(struct kfd_event_waiter), - GFP_KERNEL); + event_waiters = kcalloc(num_events, sizeof(struct kfd_event_waiter), + GFP_KERNEL); if (!event_waiters) return NULL; - for (i = 0; (event_waiters) && (i < num_events) ; i++) { + for (i = 0; i < num_events; i++) init_wait(&event_waiters[i].wait); - event_waiters[i].activated = false; - } return event_waiters; } From ab7da8d93a6ff68a921b6dffbfb8c463e606517c Mon Sep 17 00:00:00 2001 From: Michael Karcher Date: Tue, 24 Jan 2023 22:48:16 +0100 Subject: [PATCH 2189/4345] sh: intc: Avoid spurious sizeof-pointer-div warning [ Upstream commit 250870824c1cf199b032b1ef889c8e8d69d9123a ] GCC warns about the pattern sizeof(void*)/sizeof(void), as it looks like the abuse of a pattern to calculate the array size. This pattern appears in the unevaluated part of the ternary operator in _INTC_ARRAY if the parameter is NULL. The replacement uses an alternate approach to return 0 in case of NULL which does not generate the pattern sizeof(void*)/sizeof(void), but still emits the warning if _INTC_ARRAY is called with a nonarray parameter. This patch is required for successful compilation with -Werror enabled. The idea to use _Generic for type distinction is taken from Comment #7 in https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108483 by Jakub Jelinek Signed-off-by: Michael Karcher Acked-by: Randy Dunlap # build-tested Link: https://lore.kernel.org/r/619fa552-c988-35e5-b1d7-fe256c46a272@mkarcher.dialup.fu-berlin.de Signed-off-by: John Paul Adrian Glaubitz Signed-off-by: Sasha Levin --- include/linux/sh_intc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/include/linux/sh_intc.h b/include/linux/sh_intc.h index c255273b0281..37ad81058d6a 100644 --- a/include/linux/sh_intc.h +++ b/include/linux/sh_intc.h @@ -97,7 +97,10 @@ struct intc_hw_desc { unsigned int nr_subgroups; }; -#define _INTC_ARRAY(a) a, __same_type(a, NULL) ? 0 : sizeof(a)/sizeof(*a) +#define _INTC_SIZEOF_OR_ZERO(a) (_Generic(a, \ + typeof(NULL): 0, \ + default: sizeof(a))) +#define _INTC_ARRAY(a) a, _INTC_SIZEOF_OR_ZERO(a)/sizeof(*a) #define INTC_HW_DESC(vectors, groups, mask_regs, \ prio_regs, sense_regs, ack_regs) \ From 7257070be70e19a9138f39009c1a26c83a8a7cfa Mon Sep 17 00:00:00 2001 From: Alex Hung Date: Wed, 11 Jan 2023 09:54:11 -0700 Subject: [PATCH 2190/4345] drm/amd/display: fix shift-out-of-bounds in CalculateVMAndRowBytes [ Upstream commit 031f196d1b1b6d5dfcb0533b431e3ab1750e6189 ] [WHY] When PTEBufferSizeInRequests is zero, UBSAN reports the following warning because dml_log2 returns an unexpected negative value: shift exponent 4294966273 is too large for 32-bit type 'int' [HOW] In the case PTEBufferSizeInRequests is zero, skip the dml_log2() and assign the result directly. Reviewed-by: Jun Lei Acked-by: Qingqing Zhuo Signed-off-by: Alex Hung Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- .../gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index e427f4ffa080..e5b1002d7f3f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -1868,7 +1868,10 @@ static unsigned int CalculateVMAndRowBytes( } if (SurfaceTiling == dm_sw_linear) { - *dpte_row_height = dml_min(128, 1 << (unsigned int) dml_floor(dml_log2(PTEBufferSizeInRequests * *PixelPTEReqWidth / Pitch), 1)); + if (PTEBufferSizeInRequests == 0) + *dpte_row_height = 1; + else + *dpte_row_height = dml_min(128, 1 << (unsigned int) dml_floor(dml_log2(PTEBufferSizeInRequests * *PixelPTEReqWidth / Pitch), 1)); *dpte_row_width_ub = (dml_ceil(((double) SwathWidth - 1) / *PixelPTEReqWidth, 1) + 1) * *PixelPTEReqWidth; *PixelPTEBytesPerRow = *dpte_row_width_ub / *PixelPTEReqWidth * *PTERequestSize; } else if (ScanDirection != dm_vert) { From 020166bc6669ca9fb267ebd96bd88c4fb64a5d46 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 17 Mar 2023 21:53:52 -0400 Subject: [PATCH 2191/4345] ext4: fix possible double unlock when moving a directory commit 70e42feab2e20618ddd0cbfc4ab4b08628236ecd upstream. Fixes: 0813299c586b ("ext4: Fix possible corruption when moving a directory") Link: https://lore.kernel.org/r/5efbe1b9-ad8b-4a4f-b422-24824d2b775c@kili.mountain Reported-by: Dan Carpenter Reported-by: syzbot+0c73d1d8b952c5f3d714@syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/namei.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 1f47aeca7142..45f719c1e002 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3934,10 +3934,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; } retval = ext4_rename_dir_prepare(handle, &old); - if (retval) { - inode_unlock(old.inode); + if (retval) goto end_rename; - } } /* * If we're renaming a file within an inline_data dir and adding or From f5a5150c7066c6fc5d617e277cd432ebbb8f97b4 Mon Sep 17 00:00:00 2001 From: Sherry Sun Date: Thu, 23 Feb 2023 17:39:41 +0800 Subject: [PATCH 2192/4345] tty: serial: fsl_lpuart: skip waiting for transmission complete when UARTCTRL_SBK is asserted commit 2411fd94ceaa6e11326e95d6ebf876cbfed28d23 upstream. According to LPUART RM, Transmission Complete Flag becomes 0 if queuing a break character by writing 1 to CTRL[SBK], so here need to skip waiting for transmission complete when UARTCTRL_SBK is asserted, otherwise the kernel may stuck here. And actually set_termios() adds transmission completion waiting to avoid data loss or data breakage when changing the baud rate, but we don't need to worry about this when queuing break characters. Signed-off-by: Sherry Sun Cc: stable Link: https://lore.kernel.org/r/20230223093941.31790-1-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 9cb0e8673f82..32cce52800a7 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2159,9 +2159,15 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios, /* update the per-port timeout */ uart_update_timeout(port, termios->c_cflag, baud); - /* wait transmit engin complete */ - lpuart32_write(&sport->port, 0, UARTMODIR); - lpuart32_wait_bit_set(&sport->port, UARTSTAT, UARTSTAT_TC); + /* + * LPUART Transmission Complete Flag may never be set while queuing a break + * character, so skip waiting for transmission complete when UARTCTRL_SBK is + * asserted. + */ + if (!(old_ctrl & UARTCTRL_SBK)) { + lpuart32_write(&sport->port, 0, UARTMODIR); + lpuart32_wait_bit_set(&sport->port, UARTSTAT, UARTSTAT_TC); + } /* disable transmit and receive */ lpuart32_write(&sport->port, old_ctrl & ~(UARTCTRL_TE | UARTCTRL_RE), From 0c16c20b87873801d6eaa79e5a150eadab9145b3 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Mon, 27 Feb 2023 11:41:46 +0000 Subject: [PATCH 2193/4345] serial: 8250_em: Fix UART port type commit 32e293be736b853f168cd065d9cbc1b0c69f545d upstream. As per HW manual for EMEV2 "R19UH0040EJ0400 Rev.4.00", the UART IP found on EMMA mobile SoC is Register-compatible with the general-purpose 16750 UART chip. Fix UART port type as 16750 and enable 64-bytes fifo support. Fixes: 22886ee96895 ("serial8250-em: Emma Mobile UART driver V2") Cc: stable@vger.kernel.org Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230227114152.22265-2-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_em.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index f8e99995eee9..d94c3811a8f7 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -106,8 +106,8 @@ static int serial8250_em_probe(struct platform_device *pdev) memset(&up, 0, sizeof(up)); up.port.mapbase = regs->start; up.port.irq = irq; - up.port.type = PORT_UNKNOWN; - up.port.flags = UPF_BOOT_AUTOCONF | UPF_FIXED_PORT | UPF_IOREMAP; + up.port.type = PORT_16750; + up.port.flags = UPF_FIXED_PORT | UPF_IOREMAP | UPF_FIXED_TYPE; up.port.dev = &pdev->dev; up.port.private_data = priv; From b37d3ccbd549494890672136a0e623eb010d46a7 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 8 Mar 2023 14:26:02 -0800 Subject: [PATCH 2194/4345] firmware: xilinx: don't make a sleepable memory allocation from an atomic context commit 38ed310c22e7a0fc978b1f8292136a4a4a8b3051 upstream. The following issue was discovered using lockdep: [ 6.691371] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:209 [ 6.694602] in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 1, name: swapper/0 [ 6.702431] 2 locks held by swapper/0/1: [ 6.706300] #0: ffffff8800f6f188 (&dev->mutex){....}-{3:3}, at: __device_driver_lock+0x4c/0x90 [ 6.714900] #1: ffffffc009a2abb8 (enable_lock){....}-{2:2}, at: clk_enable_lock+0x4c/0x140 [ 6.723156] irq event stamp: 304030 [ 6.726596] hardirqs last enabled at (304029): [] _raw_spin_unlock_irqrestore+0xc0/0xd0 [ 6.736142] hardirqs last disabled at (304030): [] clk_enable_lock+0xfc/0x140 [ 6.744742] softirqs last enabled at (303958): [] _stext+0x4f0/0x894 [ 6.752655] softirqs last disabled at (303951): [] irq_exit+0x238/0x280 [ 6.760744] CPU: 1 PID: 1 Comm: swapper/0 Tainted: G U 5.15.36 #2 [ 6.768048] Hardware name: xlnx,zynqmp (DT) [ 6.772179] Call trace: [ 6.774584] dump_backtrace+0x0/0x300 [ 6.778197] show_stack+0x18/0x30 [ 6.781465] dump_stack_lvl+0xb8/0xec [ 6.785077] dump_stack+0x1c/0x38 [ 6.788345] ___might_sleep+0x1a8/0x2a0 [ 6.792129] __might_sleep+0x6c/0xd0 [ 6.795655] kmem_cache_alloc_trace+0x270/0x3d0 [ 6.800127] do_feature_check_call+0x100/0x220 [ 6.804513] zynqmp_pm_invoke_fn+0x8c/0xb0 [ 6.808555] zynqmp_pm_clock_getstate+0x90/0xe0 [ 6.813027] zynqmp_pll_is_enabled+0x8c/0x120 [ 6.817327] zynqmp_pll_enable+0x38/0xc0 [ 6.821197] clk_core_enable+0x144/0x400 [ 6.825067] clk_core_enable+0xd4/0x400 [ 6.828851] clk_core_enable+0xd4/0x400 [ 6.832635] clk_core_enable+0xd4/0x400 [ 6.836419] clk_core_enable+0xd4/0x400 [ 6.840203] clk_core_enable+0xd4/0x400 [ 6.843987] clk_core_enable+0xd4/0x400 [ 6.847771] clk_core_enable+0xd4/0x400 [ 6.851555] clk_core_enable_lock+0x24/0x50 [ 6.855683] clk_enable+0x24/0x40 [ 6.858952] fclk_probe+0x84/0xf0 [ 6.862220] platform_probe+0x8c/0x110 [ 6.865918] really_probe+0x110/0x5f0 [ 6.869530] __driver_probe_device+0xcc/0x210 [ 6.873830] driver_probe_device+0x64/0x140 [ 6.877958] __driver_attach+0x114/0x1f0 [ 6.881828] bus_for_each_dev+0xe8/0x160 [ 6.885698] driver_attach+0x34/0x50 [ 6.889224] bus_add_driver+0x228/0x300 [ 6.893008] driver_register+0xc0/0x1e0 [ 6.896792] __platform_driver_register+0x44/0x60 [ 6.901436] fclk_driver_init+0x1c/0x28 [ 6.905220] do_one_initcall+0x104/0x590 [ 6.909091] kernel_init_freeable+0x254/0x2bc [ 6.913390] kernel_init+0x24/0x130 [ 6.916831] ret_from_fork+0x10/0x20 Fix it by passing the GFP_ATOMIC gfp flag for the corresponding memory allocation. Fixes: acfdd18591ea ("firmware: xilinx: Use hash-table for api feature check") Cc: stable Signed-off-by: Roman Gushchin Cc: Amit Sunil Dhamne Cc: Michal Simek Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Link: https://lore.kernel.org/r/20230308222602.123866-1-roman.gushchin@linux.dev Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/xilinx/zynqmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 9e6504592646..300ba2991936 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -171,7 +171,7 @@ static int zynqmp_pm_feature(u32 api_id) } /* Add new entry if not present */ - feature_data = kmalloc(sizeof(*feature_data), GFP_KERNEL); + feature_data = kmalloc(sizeof(*feature_data), GFP_ATOMIC); if (!feature_data) return -ENOMEM; From efae80ca13faa94457208852825731da44a788ad Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 08:56:29 +0100 Subject: [PATCH 2195/4345] interconnect: fix mem leak when freeing nodes commit a5904f415e1af72fa8fe6665aa4f554dc2099a95 upstream. The node link array is allocated when adding links to a node but is not deallocated when nodes are destroyed. Fixes: 11f1ceca7031 ("interconnect: Add generic on-chip interconnect API") Cc: stable@vger.kernel.org # 5.1 Reviewed-by: Konrad Dybcio Signed-off-by: Johan Hovold Tested-by: Luca Ceresoli # i.MX8MP MSC SM2-MB-EP1 Board Link: https://lore.kernel.org/r/20230306075651.2449-2-johan+linaro@kernel.org Signed-off-by: Georgi Djakov Signed-off-by: Greg Kroah-Hartman --- drivers/interconnect/core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index ceb6cdc20484..7db6d0fc6ec2 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -850,6 +850,10 @@ void icc_node_destroy(int id) mutex_unlock(&icc_lock); + if (!node) + return; + + kfree(node->links); kfree(node); } EXPORT_SYMBOL_GPL(icc_node_destroy); From de3170bd41dee29039e8a87efa960759ad256a5a Mon Sep 17 00:00:00 2001 From: Sung-hun Kim Date: Tue, 14 Mar 2023 10:37:07 +0900 Subject: [PATCH 2196/4345] tracing: Make splice_read available again commit e400be674a1a40e9dcb2e95f84d6c1fd2d88f31d upstream. Since the commit 36e2c7421f02 ("fs: don't allow splice read/write without explicit ops") is applied to the kernel, splice() and sendfile() calls on the trace file (/sys/kernel/debug/tracing /trace) return EINVAL. This patch restores these system calls by initializing splice_read in file_operations of the trace file. This patch only enables such functionalities for the read case. Link: https://lore.kernel.org/linux-trace-kernel/20230314013707.28814-1-sfoon.kim@samsung.com Cc: stable@vger.kernel.org Fixes: 36e2c7421f02 ("fs: don't allow splice read/write without explicit ops") Signed-off-by: Sung-hun Kim Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8637eab2986e..ce45bdd9077d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4705,6 +4705,8 @@ loff_t tracing_lseek(struct file *file, loff_t offset, int whence) static const struct file_operations tracing_fops = { .open = tracing_open, .read = seq_read, + .read_iter = seq_read_iter, + .splice_read = generic_file_splice_read, .write = tracing_write_stub, .llseek = tracing_lseek, .release = tracing_release, From 8ae86ef7a0580135ac6d0afce3e16e2c9e4b8e96 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 1 Mar 2023 20:00:53 -0500 Subject: [PATCH 2197/4345] tracing: Check field value in hist_field_name() commit 9f116f76fa8c04c81aef33ad870dbf9a158e5b70 upstream. The function hist_field_name() cannot handle being passed a NULL field parameter. It should never be NULL, but due to a previous bug, NULL was passed to the function and the kernel crashed due to a NULL dereference. Mark Rutland reported this to me on IRC. The bug was fixed, but to prevent future bugs from crashing the kernel, check the field and add a WARN_ON() if it is NULL. Link: https://lkml.kernel.org/r/20230302020810.762384440@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Andrew Morton Reported-by: Mark Rutland Fixes: c6afad49d127f ("tracing: Add hist trigger 'sym' and 'sym-offset' modifiers") Tested-by: Mark Rutland Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_events_hist.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index ccc99cd23f3c..9ed65191888e 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1087,6 +1087,9 @@ static const char *hist_field_name(struct hist_field *field, { const char *field_name = ""; + if (WARN_ON_ONCE(!field)) + return field_name; + if (level > 1) return field_name; From ec663c410ce0023e13f56a95e096be9cd6d471c2 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 10 Mar 2023 17:28:56 -0500 Subject: [PATCH 2198/4345] tracing: Make tracepoint lockdep check actually test something commit c2679254b9c9980d9045f0f722cf093a2b1f7590 upstream. A while ago where the trace events had the following: rcu_read_lock_sched_notrace(); rcu_dereference_sched(...); rcu_read_unlock_sched_notrace(); If the tracepoint is enabled, it could trigger RCU issues if called in the wrong place. And this warning was only triggered if lockdep was enabled. If the tracepoint was never enabled with lockdep, the bug would not be caught. To handle this, the above sequence was done when lockdep was enabled regardless if the tracepoint was enabled or not (although the always enabled code really didn't do anything, it would still trigger a warning). But a lot has changed since that lockdep code was added. One is, that sequence no longer triggers any warning. Another is, the tracepoint when enabled doesn't even do that sequence anymore. The main check we care about today is whether RCU is "watching" or not. So if lockdep is enabled, always check if rcu_is_watching() which will trigger a warning if it is not (tracepoints require RCU to be watching). Note, that old sequence did add a bit of overhead when lockdep was enabled, and with the latest kernel updates, would cause the system to slow down enough to trigger kernel "stalled" warnings. Link: http://lore.kernel.org/lkml/20140806181801.GA4605@redhat.com Link: http://lore.kernel.org/lkml/20140807175204.C257CAC5@viggo.jf.intel.com Link: https://lore.kernel.org/lkml/20230307184645.521db5c9@gandalf.local.home/ Link: https://lore.kernel.org/linux-trace-kernel/20230310172856.77406446@gandalf.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Dave Hansen Cc: "Paul E. McKenney" Cc: Mathieu Desnoyers Cc: Joel Fernandes Acked-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- include/linux/tracepoint.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index e4c5df71f0e7..4e1356c35fe6 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -234,12 +234,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. * - * When lockdep is enabled, we make sure to always do the RCU portions of - * the tracepoint code, regardless of whether tracing is on. However, - * don't check if the condition is false, due to interaction with idle - * instrumentation. This lets us find RCU issues triggered with tracepoints - * even when this tracepoint is off. This code has no purpose other than - * poking RCU a bit. + * When lockdep is enabled, we make sure to always test if RCU is + * "watching" regardless if the tracepoint is enabled or not. Tracepoints + * require RCU to be active, and it should always warn at the tracepoint + * site if it is not watching, as it will need to be active when the + * tracepoint is enabled. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ extern int __traceiter_##name(data_proto); \ @@ -253,9 +252,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) TP_ARGS(data_args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ - rcu_read_lock_sched_notrace(); \ - rcu_dereference_sched(__tracepoint_##name.funcs);\ - rcu_read_unlock_sched_notrace(); \ + WARN_ON_ONCE(!rcu_is_watching()); \ } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ From 7b18dea697e400dd91c2a0447cebf1f5fe9f5d1c Mon Sep 17 00:00:00 2001 From: Volker Lendecke Date: Mon, 13 Mar 2023 16:09:54 +0100 Subject: [PATCH 2199/4345] cifs: Fix smb2_set_path_size() commit 211baef0eabf4169ce4f73ebd917749d1a7edd74 upstream. If cifs_get_writable_path() finds a writable file, smb2_compound_op() must use that file's FID and not the COMPOUND_FID. Cc: stable@vger.kernel.org Signed-off-by: Volker Lendecke Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/smb2inode.c | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 97cd4df04060..e11818801148 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -236,15 +236,32 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, size[0] = 8; /* sizeof __le64 */ data[0] = ptr; - rc = SMB2_set_info_init(tcon, server, - &rqst[num_rqst], COMPOUND_FID, - COMPOUND_FID, current->tgid, - FILE_END_OF_FILE_INFORMATION, - SMB2_O_INFO_FILE, 0, data, size); + if (cfile) { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + current->tgid, + FILE_END_OF_FILE_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + } else { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + COMPOUND_FID, + COMPOUND_FID, + current->tgid, + FILE_END_OF_FILE_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + if (!rc) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } + } if (rc) goto finished; - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst++]); + num_rqst++; trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_SET_INFO: From c54974ccaff73525462e278602dfe4069877cfaa Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 10 Mar 2023 11:10:56 -0500 Subject: [PATCH 2200/4345] KVM: nVMX: add missing consistency checks for CR0 and CR4 commit 112e66017bff7f2837030f34c2bc19501e9212d5 upstream. The effective values of the guest CR0 and CR4 registers may differ from those included in the VMCS12. In particular, disabling EPT forces CR4.PAE=1 and disabling unrestricted guest mode forces CR0.PG=CR0.PE=1. Therefore, checks on these bits cannot be delegated to the processor and must be performed by KVM. Reported-by: Reima ISHII Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx/nested.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 91371b01eae0..c165ddbb672f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2998,7 +2998,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, enum vm_entry_failure_code *entry_failure_code) { - bool ia32e; + bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE); *entry_failure_code = ENTRY_FAIL_DEFAULT; @@ -3024,6 +3024,13 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, vmcs12->guest_ia32_perf_global_ctrl))) return -EINVAL; + if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG)) + return -EINVAL; + + if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) || + CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG))) + return -EINVAL; + /* * If the load IA32_EFER VM-entry control is 1, the following checks * are performed on the field for the IA32_EFER MSR: @@ -3035,7 +3042,6 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, */ if (to_vmx(vcpu)->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { - ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) || CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) || CC(((vmcs12->guest_cr0 & X86_CR0_PG) && From 9addf5e1050abb5c63cd7d9d40f6b004f2b45cfc Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Mon, 6 Mar 2023 15:41:01 +0800 Subject: [PATCH 2201/4345] ALSA: hda: intel-dsp-config: add MTL PCI id commit bbdf904b13a62bb8b1272d92a7dde082dff86fbb upstream. Use SOF as default audio driver. Signed-off-by: Bard Liao Reviewed-by: Gongjun Song Reviewed-by: Kai Vehmanen Cc: Link: https://lore.kernel.org/r/20230306074101.3906707-1-yung-chuan.liao@linux.intel.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/hda/intel-dsp-config.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 2a5ba9dca6b0..f96e70c85f84 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -359,6 +359,15 @@ static const struct config_entry config_table[] = { }, #endif +/* Meteor Lake */ +#if IS_ENABLED(CONFIG_SND_SOC_SOF_METEORLAKE) + /* Meteorlake-P */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x7e28, + }, +#endif + }; static const struct config_entry *snd_intel_dsp_find_config From fbc5ffcce72be7805a1c0da19e86d8e3fddc7399 Mon Sep 17 00:00:00 2001 From: "Hamidreza H. Fard" Date: Tue, 7 Mar 2023 16:37:41 +0000 Subject: [PATCH 2202/4345] ALSA: hda/realtek: Fix the speaker output on Samsung Galaxy Book2 Pro commit a86e79e3015f5dd8e1b01ccfa49bd5c6e41047a1 upstream. Samsung Galaxy Book2 Pro (13" 2022 NP930XED-KA1DE) with codec SSID 144d:c868 requires the same workaround for enabling the speaker amp like other Samsung models with ALC298 code. Signed-off-by: Hamidreza H. Fard Cc: Link: https://lore.kernel.org/r/20230307163741.3878-1-nitocris@posteo.net Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f2ef75c8de42..2cf6600c9ca8 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9091,6 +9091,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc832, "Samsung Galaxy Book Flex Alpha (NP730QCJ)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xca03, "Samsung Galaxy Book2 Pro 360 (NP930QED)", ALC298_FIXUP_SAMSUNG_AMP), + SND_PCI_QUIRK(0x144d, 0xc868, "Samsung Galaxy Book2 Pro (NP930XED)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), From 684c7372bbd6447c2e86a2a84e97a1478604d21f Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 9 Jan 2023 00:13:11 +0300 Subject: [PATCH 2203/4345] drm/shmem-helper: Remove another errant put in error path commit ee9adb7a45516cfa536ca92253d7ae59d56db9e4 upstream. drm_gem_shmem_mmap() doesn't own reference in error code path, resulting in the dma-buf shmem GEM object getting prematurely freed leading to a later use-after-free. Fixes: f49a51bfdc8e ("drm/shme-helpers: Fix dma_buf_mmap forwarding bug") Cc: stable@vger.kernel.org Signed-off-by: Dmitry Osipenko Reviewed-by: Rob Clark Link: https://patchwork.freedesktop.org/patch/msgid/20230108211311.3950107-1-dmitry.osipenko@collabora.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_gem_shmem_helper.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index c56656a95cf9..b7bb5610dfe2 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -614,11 +614,14 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) int ret; if (obj->import_attach) { - /* Drop the reference drm_gem_mmap_obj() acquired.*/ - drm_gem_object_put(obj); vma->vm_private_data = NULL; + ret = dma_buf_mmap(obj->dma_buf, vma, 0); - return dma_buf_mmap(obj->dma_buf, vma, 0); + /* Drop the reference drm_gem_mmap_obj() acquired.*/ + if (!ret) + drm_gem_object_put(obj); + + return ret; } shmem = to_drm_gem_shmem_obj(obj); From f9a98b8dde09330c238cbb556a9f75bd965b91aa Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Thu, 9 Mar 2023 15:50:03 +0100 Subject: [PATCH 2204/4345] mptcp: avoid setting TCP_CLOSE state twice commit 3ba14528684f528566fb7d956bfbfb958b591d86 upstream. tcp_set_state() is called from tcp_done() already. There is then no need to first set the state to TCP_CLOSE, then call tcp_done(). Fixes: d582484726c4 ("mptcp: fix fallback for MP_JOIN subflows") Cc: stable@vger.kernel.org Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/362 Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/mptcp/subflow.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3b154ad4945c..607519246bf2 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -275,7 +275,6 @@ void mptcp_subflow_reset(struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; - tcp_set_state(ssk, TCP_CLOSE); tcp_send_active_reset(ssk, GFP_ATOMIC); tcp_done(ssk); if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) && From 83c3b2f4e7c61367c7b24551f4c6eb94bbdda283 Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Thu, 9 Mar 2023 16:02:30 +0800 Subject: [PATCH 2205/4345] ftrace: Fix invalid address access in lookup_rec() when index is 0 commit ee92fa443358f4fc0017c1d0d325c27b37802504 upstream. KASAN reported follow problem: BUG: KASAN: use-after-free in lookup_rec Read of size 8 at addr ffff000199270ff0 by task modprobe CPU: 2 Comm: modprobe Call trace: kasan_report __asan_load8 lookup_rec ftrace_location arch_check_ftrace_location check_kprobe_address_safe register_kprobe When checking pg->records[pg->index - 1].ip in lookup_rec(), it can get a pg which is newly added to ftrace_pages_start in ftrace_process_locs(). Before the first pg->index++, index is 0 and accessing pg->records[-1].ip will cause this problem. Don't check the ip when pg->index is 0. Link: https://lore.kernel.org/linux-trace-kernel/20230309080230.36064-1-chenzhongjin@huawei.com Cc: stable@vger.kernel.org Fixes: 9644302e3315 ("ftrace: Speed up search by skipping pages by address") Suggested-by: Steven Rostedt (Google) Signed-off-by: Chen Zhongjin Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ftrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d97c189695cb..67829b6e07bd 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1538,7 +1538,8 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) key.flags = end; /* overload flags, as it is unsigned long */ for (pg = ftrace_pages_start; pg; pg = pg->next) { - if (end < pg->records[0].ip || + if (pg->index == 0 || + end < pg->records[0].ip || start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) continue; rec = bsearch(&key, pg->records, pg->index, From b2747b690cb911263fa6e2cbe32a85446f259165 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 2 Mar 2023 18:54:23 +0100 Subject: [PATCH 2206/4345] mm/userfaultfd: propagate uffd-wp bit when PTE-mapping the huge zeropage commit 42b2af2c9b7eede8ef21d0943f84d135e21a32a3 upstream. Currently, we'd lose the userfaultfd-wp marker when PTE-mapping a huge zeropage, resulting in the next write faults in the PMD range not triggering uffd-wp events. Various actions (partial MADV_DONTNEED, partial mremap, partial munmap, partial mprotect) could trigger this. However, most importantly, un-protecting a single sub-page from the userfaultfd-wp handler when processing a uffd-wp event will PTE-map the shared huge zeropage and lose the uffd-wp bit for the remainder of the PMD. Let's properly propagate the uffd-wp bit to the PMDs. #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include #include #include #include #include static size_t pagesize; static int uffd; static volatile bool uffd_triggered; #define barrier() __asm__ __volatile__("": : :"memory") static void uffd_wp_range(char *start, size_t size, bool wp) { struct uffdio_writeprotect uffd_writeprotect; uffd_writeprotect.range.start = (unsigned long) start; uffd_writeprotect.range.len = size; if (wp) { uffd_writeprotect.mode = UFFDIO_WRITEPROTECT_MODE_WP; } else { uffd_writeprotect.mode = 0; } if (ioctl(uffd, UFFDIO_WRITEPROTECT, &uffd_writeprotect)) { fprintf(stderr, "UFFDIO_WRITEPROTECT failed: %d\n", errno); exit(1); } } static void *uffd_thread_fn(void *arg) { static struct uffd_msg msg; ssize_t nread; while (1) { struct pollfd pollfd; int nready; pollfd.fd = uffd; pollfd.events = POLLIN; nready = poll(&pollfd, 1, -1); if (nready == -1) { fprintf(stderr, "poll() failed: %d\n", errno); exit(1); } nread = read(uffd, &msg, sizeof(msg)); if (nread <= 0) continue; if (msg.event != UFFD_EVENT_PAGEFAULT || !(msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP)) { printf("FAIL: wrong uffd-wp event fired\n"); exit(1); } /* un-protect the single page. */ uffd_triggered = true; uffd_wp_range((char *)(uintptr_t)msg.arg.pagefault.address, pagesize, false); } return arg; } static int setup_uffd(char *map, size_t size) { struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; pthread_t thread; uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY); if (uffd < 0) { fprintf(stderr, "syscall() failed: %d\n", errno); return -errno; } uffdio_api.api = UFFD_API; uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP; if (ioctl(uffd, UFFDIO_API, &uffdio_api) < 0) { fprintf(stderr, "UFFDIO_API failed: %d\n", errno); return -errno; } if (!(uffdio_api.features & UFFD_FEATURE_PAGEFAULT_FLAG_WP)) { fprintf(stderr, "UFFD_FEATURE_WRITEPROTECT missing\n"); return -ENOSYS; } uffdio_register.range.start = (unsigned long) map; uffdio_register.range.len = size; uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) < 0) { fprintf(stderr, "UFFDIO_REGISTER failed: %d\n", errno); return -errno; } pthread_create(&thread, NULL, uffd_thread_fn, NULL); return 0; } int main(void) { const size_t size = 4 * 1024 * 1024ull; char *map, *cur; pagesize = getpagesize(); map = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0); if (map == MAP_FAILED) { fprintf(stderr, "mmap() failed\n"); return -errno; } if (madvise(map, size, MADV_HUGEPAGE)) { fprintf(stderr, "MADV_HUGEPAGE failed\n"); return -errno; } if (setup_uffd(map, size)) return 1; /* Read the whole range, populating zeropages. */ madvise(map, size, MADV_POPULATE_READ); /* Write-protect the whole range. */ uffd_wp_range(map, size, true); /* Make sure uffd-wp triggers on each page. */ for (cur = map; cur < map + size; cur += pagesize) { uffd_triggered = false; barrier(); /* Trigger a write fault. */ *cur = 1; barrier(); if (!uffd_triggered) { printf("FAIL: uffd-wp did not trigger\n"); return 1; } } printf("PASS: uffd-wp triggered\n"); return 0; } Link: https://lkml.kernel.org/r/20230302175423.589164-1-david@redhat.com Fixes: e06f1e1dd499 ("userfaultfd: wp: enabled write protection in userfaultfd API") Signed-off-by: David Hildenbrand Acked-by: Peter Xu Cc: Mike Rapoport Cc: Andrea Arcangeli Cc: Jerome Glisse Cc: Shaohua Li Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/huge_memory.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9b15760e0541..e4c690c21fc9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1994,7 +1994,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; pgtable_t pgtable; - pmd_t _pmd; + pmd_t _pmd, old_pmd; int i; /* @@ -2005,7 +2005,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, * * See Documentation/vm/mmu_notifier.rst */ - pmdp_huge_clear_flush(vma, haddr, pmd); + old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); @@ -2014,6 +2014,8 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, pte_t *pte, entry; entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot); entry = pte_mkspecial(entry); + if (pmd_uffd_wp(old_pmd)) + entry = pte_mkuffd_wp(entry); pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte_none(*pte)); set_pte_at(mm, haddr, pte, entry); From 03fc29e75e44bac3108068a9403ff1b316f3f0fa Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Mon, 6 Mar 2023 17:27:51 +0100 Subject: [PATCH 2207/4345] mmc: sdhci_am654: lower power-on failed message severity commit 11440da77d6020831ee6f9ce4551b545dea789ee upstream. Lower the power-on failed message severity from warn to info when the controller does not power-up. It's normal to have this situation when the SD card slot is empty, therefore we should not warn the user about it. Fixes: 7ca0f166f5b2 ("mmc: sdhci_am654: Add workaround for card detect debounce timer") Signed-off-by: Francesco Dolcini Acked-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230306162751.163369-1-francesco@dolcini.it Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/sdhci_am654.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index 24cd6d3dc647..bf2592774165 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -369,7 +369,7 @@ static void sdhci_am654_write_b(struct sdhci_host *host, u8 val, int reg) MAX_POWER_ON_TIMEOUT, false, host, val, reg); if (ret) - dev_warn(mmc_dev(host->mmc), "Power on failed\n"); + dev_info(mmc_dev(host->mmc), "Power on failed\n"); } } From 38742635eda98fb5d3304d921cddaaa62d656814 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Thu, 16 Mar 2023 11:38:19 +0100 Subject: [PATCH 2208/4345] fbdev: stifb: Provide valid pixelclock and add fb_check_var() checks commit 203873a535d627c668f293be0cb73e26c30f9cc7 upstream. Find a valid modeline depending on the machine graphic card configuration and add the fb_check_var() function to validate Xorg provided graphics settings. Signed-off-by: Helge Deller Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/stifb.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 3feb6e40d56d..ef8a4c5fc687 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -921,6 +921,28 @@ SETUP_HCRX(struct stifb_info *fb) /* ------------------- driver specific functions --------------------------- */ +static int +stifb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) +{ + struct stifb_info *fb = container_of(info, struct stifb_info, info); + + if (var->xres != fb->info.var.xres || + var->yres != fb->info.var.yres || + var->bits_per_pixel != fb->info.var.bits_per_pixel) + return -EINVAL; + + var->xres_virtual = var->xres; + var->yres_virtual = var->yres; + var->xoffset = 0; + var->yoffset = 0; + var->grayscale = fb->info.var.grayscale; + var->red.length = fb->info.var.red.length; + var->green.length = fb->info.var.green.length; + var->blue.length = fb->info.var.blue.length; + + return 0; +} + static int stifb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, u_int transp, struct fb_info *info) @@ -1145,6 +1167,7 @@ stifb_init_display(struct stifb_info *fb) static const struct fb_ops stifb_ops = { .owner = THIS_MODULE, + .fb_check_var = stifb_check_var, .fb_setcolreg = stifb_setcolreg, .fb_blank = stifb_blank, .fb_fillrect = stifb_fillrect, @@ -1164,6 +1187,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) struct stifb_info *fb; struct fb_info *info; unsigned long sti_rom_address; + char modestr[32]; char *dev_name; int bpp, xres, yres; @@ -1342,6 +1366,9 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) info->flags = FBINFO_HWACCEL_COPYAREA | FBINFO_HWACCEL_FILLRECT; info->pseudo_palette = &fb->pseudo_palette; + scnprintf(modestr, sizeof(modestr), "%dx%d-%d", xres, yres, bpp); + fb_find_mode(&info->var, info, modestr, NULL, 0, NULL, bpp); + /* This has to be done !!! */ if (fb_alloc_cmap(&info->cmap, NR_PALETTE, 0)) goto out_err1; From 15e926dfd82081e759754ac3917817d427ec2889 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Sat, 4 Mar 2023 15:41:07 +0800 Subject: [PATCH 2209/4345] cpuidle: psci: Iterate backwards over list in psci_pd_remove() commit 6b0313c2fa3d2cf991c9ffef6fae6e7ef592ce6d upstream. In case that psci_pd_init_topology() fails for some reason, psci_pd_remove() will be responsible for deleting provider and removing genpd from psci_pd_providers list. There will be a failure when removing the cluster PD, because the cpu (child) PDs haven't been removed. [ 0.050232] CPUidle PSCI: init PM domain cpu0 [ 0.050278] CPUidle PSCI: init PM domain cpu1 [ 0.050329] CPUidle PSCI: init PM domain cpu2 [ 0.050370] CPUidle PSCI: init PM domain cpu3 [ 0.050422] CPUidle PSCI: init PM domain cpu-cluster0 [ 0.050475] PM: genpd_remove: unable to remove cpu-cluster0 [ 0.051412] PM: genpd_remove: removed cpu3 [ 0.051449] PM: genpd_remove: removed cpu2 [ 0.051499] PM: genpd_remove: removed cpu1 [ 0.051546] PM: genpd_remove: removed cpu0 Fix the problem by iterating the provider list reversely, so that parent PD gets removed after child's PDs like below. [ 0.029052] CPUidle PSCI: init PM domain cpu0 [ 0.029076] CPUidle PSCI: init PM domain cpu1 [ 0.029103] CPUidle PSCI: init PM domain cpu2 [ 0.029124] CPUidle PSCI: init PM domain cpu3 [ 0.029151] CPUidle PSCI: init PM domain cpu-cluster0 [ 0.029647] PM: genpd_remove: removed cpu0 [ 0.029666] PM: genpd_remove: removed cpu1 [ 0.029690] PM: genpd_remove: removed cpu2 [ 0.029714] PM: genpd_remove: removed cpu3 [ 0.029738] PM: genpd_remove: removed cpu-cluster0 Fixes: a65a397f2451 ("cpuidle: psci: Add support for PM domains by using genpd") Reviewed-by: Sudeep Holla Reviewed-by: Ulf Hansson Signed-off-by: Shawn Guo Cc: 5.10+ # 5.10+ Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/cpuidle/cpuidle-psci-domain.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c index 4a031c62f92a..5098639d41f1 100644 --- a/drivers/cpuidle/cpuidle-psci-domain.c +++ b/drivers/cpuidle/cpuidle-psci-domain.c @@ -182,7 +182,8 @@ static void psci_pd_remove(void) struct psci_pd_provider *pd_provider, *it; struct generic_pm_domain *genpd; - list_for_each_entry_safe(pd_provider, it, &psci_pd_providers, link) { + list_for_each_entry_safe_reverse(pd_provider, it, + &psci_pd_providers, link) { of_genpd_del_provider(pd_provider->node); genpd = of_genpd_remove_last(pd_provider->node); From 764217184f9ef1fe2c8e1f6abed010dda4a53a94 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Wed, 1 Mar 2023 22:14:20 +0000 Subject: [PATCH 2210/4345] x86/mce: Make sure logged MCEs are processed after sysfs update commit 4783b9cb374af02d49740e00e2da19fd4ed6dec4 upstream. A recent change introduced a flag to queue up errors found during boot-time polling. These errors will be processed during late init once the MCE subsystem is fully set up. A number of sysfs updates call mce_restart() which goes through a subset of the CPU init flow. This includes polling MCA banks and logging any errors found. Since the same function is used as boot-time polling, errors will be queued. However, the system is now past late init, so the errors will remain queued until another error is found and the workqueue is triggered. Call mce_schedule_work() at the end of mce_restart() so that queued errors are processed. Fixes: 3bff147b187d ("x86/mce: Defer processing of early errors") Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Tony Luck Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230301221420.2203184-1-yazen.ghannam@amd.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/mce/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 1906387a0faf..0b7c81389c50 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2309,6 +2309,7 @@ static void mce_restart(void) { mce_timer_delete_all(); on_each_cpu(mce_cpu_restart, NULL, 1); + mce_schedule_work(); } /* Toggle features for corrected errors */ From b4a798374f2d269af00886616386beea7388a8ea Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Mon, 6 Mar 2023 08:06:56 -0800 Subject: [PATCH 2211/4345] x86/mm: Fix use of uninitialized buffer in sme_enable() commit cbebd68f59f03633469f3ecf9bea99cd6cce3854 upstream. cmdline_find_option() may fail before doing any initialization of the buffer array. This may lead to unpredictable results when the same buffer is used later in calls to strncmp() function. Fix the issue by returning early if cmdline_find_option() returns an error. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: aca20d546214 ("x86/mm: Add support to make use of Secure Memory Encryption") Signed-off-by: Nikita Zhandarovich Signed-off-by: Borislav Petkov (AMD) Acked-by: Tom Lendacky Cc: Link: https://lore.kernel.org/r/20230306160656.14844-1-n.zhandarovich@fintech.ru Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/mem_encrypt_identity.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 011e042b47ba..5ec47af786dd 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -586,7 +586,8 @@ void __init sme_enable(struct boot_params *bp) cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | ((u64)bp->ext_cmd_line_ptr << 32)); - cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)); + if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0) + return; if (!strncmp(buffer, cmdline_on, sizeof(buffer))) sme_me_mask = me_mask; From 8f27d432170068709654da9ce7e9e8f3aa2f6b8d Mon Sep 17 00:00:00 2001 From: John Harrison Date: Wed, 15 Feb 2023 17:11:00 -0800 Subject: [PATCH 2212/4345] drm/i915: Don't use stolen memory for ring buffers with LLC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 690e0ec8e63da9a29b39fedc6ed5da09c7c82651 upstream. Direction from hardware is that stolen memory should never be used for ring buffer allocations on platforms with LLC. There are too many caching pitfalls due to the way stolen memory accesses are routed. So it is safest to just not use it. Signed-off-by: John Harrison Fixes: c58b735fc762 ("drm/i915: Allocate rings from stolen") Cc: Chris Wilson Cc: Joonas Lahtinen Cc: Jani Nikula Cc: Rodrigo Vivi Cc: Tvrtko Ursulin Cc: intel-gfx@lists.freedesktop.org Cc: # v4.9+ Tested-by: Jouni Högander Reviewed-by: Daniele Ceraolo Spurio Link: https://patchwork.freedesktop.org/patch/msgid/20230216011101.1909009-2-John.C.Harrison@Intel.com (cherry picked from commit f54c1f6c697c4297f7ed94283c184acc338a5cf8) Signed-off-by: Jani Nikula Signed-off-by: John Harrison Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gt/intel_ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c index 69b2e5509d67..de67b2745258 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.c +++ b/drivers/gpu/drm/i915/gt/intel_ring.c @@ -108,7 +108,7 @@ static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size) struct i915_vma *vma; obj = ERR_PTR(-ENODEV); - if (i915_ggtt_has_aperture(ggtt)) + if (i915_ggtt_has_aperture(ggtt) && !HAS_LLC(i915)) obj = i915_gem_object_create_stolen(i915, size); if (IS_ERR(obj)) obj = i915_gem_object_create_internal(i915, size); From 5e784a7d07af42057c0576fb647b482f4cb0dc2c Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Thu, 2 Mar 2023 13:08:20 +0100 Subject: [PATCH 2213/4345] drm/i915/active: Fix misuse of non-idle barriers as fence trackers commit e0e6b416b25ee14716f3549e0cbec1011b193809 upstream. Users reported oopses on list corruptions when using i915 perf with a number of concurrently running graphics applications. Root cause analysis pointed at an issue in barrier processing code -- a race among perf open / close replacing active barriers with perf requests on kernel context and concurrent barrier preallocate / acquire operations performed during user context first pin / last unpin. When adding a request to a composite tracker, we try to reuse an existing fence tracker, already allocated and registered with that composite. The tracker we obtain may already track another fence, may be an idle barrier, or an active barrier. If the tracker we get occurs a non-idle barrier then we try to delete that barrier from a list of barrier tasks it belongs to. However, while doing that we don't respect return value from a function that performs the barrier deletion. Should the deletion ever fail, we would end up reusing the tracker still registered as a barrier task. Since the same structure field is reused with both fence callback lists and barrier tasks list, list corruptions would likely occur. Barriers are now deleted from a barrier tasks list by temporarily removing the list content, traversing that content with skip over the node to be deleted, then populating the list back with the modified content. Should that intentionally racy concurrent deletion attempts be not serialized, one or more of those may fail because of the list being temporary empty. Related code that ignores the results of barrier deletion was initially introduced in v5.4 by commit d8af05ff38ae ("drm/i915: Allow sharing the idle-barrier from other kernel requests"). However, all users of the barrier deletion routine were apparently serialized at that time, then the issue didn't exhibit itself. Results of git bisect with help of a newly developed igt@gem_barrier_race@remote-request IGT test indicate that list corruptions might start to appear after commit 311770173fac ("drm/i915/gt: Schedule request retirement when timeline idles"), introduced in v5.5. Respect results of barrier deletion attempts -- mark the barrier as idle only if successfully deleted from the list. Then, before proceeding with setting our fence as the one currently tracked, make sure that the tracker we've got is not a non-idle barrier. If that check fails then don't use that tracker but go back and try to acquire a new, usable one. v3: use unlikely() to document what outcome we expect (Andi), - fix bad grammar in commit description. v2: no code changes, - blame commit 311770173fac ("drm/i915/gt: Schedule request retirement when timeline idles"), v5.5, not commit d8af05ff38ae ("drm/i915: Allow sharing the idle-barrier from other kernel requests"), v5.4, - reword commit description. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/6333 Fixes: 311770173fac ("drm/i915/gt: Schedule request retirement when timeline idles") Cc: Chris Wilson Cc: stable@vger.kernel.org # v5.5 Cc: Andi Shyti Signed-off-by: Janusz Krzysztofik Reviewed-by: Andi Shyti Signed-off-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20230302120820.48740-1-janusz.krzysztofik@linux.intel.com (cherry picked from commit 506006055769b10d1b2b4e22f636f3b45e0e9fc7) Signed-off-by: Jani Nikula Signed-off-by: Janusz Krzysztofik Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_active.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index c4c2d24dc509..0532a5069c04 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -432,8 +432,7 @@ replace_barrier(struct i915_active *ref, struct i915_active_fence *active) * we can use it to substitute for the pending idle-barrer * request that we want to emit on the kernel_context. */ - __active_del_barrier(ref, node_from_active(active)); - return true; + return __active_del_barrier(ref, node_from_active(active)); } int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence) @@ -446,16 +445,19 @@ int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence) if (err) return err; - active = active_instance(ref, idx); - if (!active) { - err = -ENOMEM; - goto out; - } + do { + active = active_instance(ref, idx); + if (!active) { + err = -ENOMEM; + goto out; + } + + if (replace_barrier(ref, active)) { + RCU_INIT_POINTER(active->fence, NULL); + atomic_dec(&ref->count); + } + } while (unlikely(is_barrier(active))); - if (replace_barrier(ref, active)) { - RCU_INIT_POINTER(active->fence, NULL); - atomic_dec(&ref->count); - } if (!__i915_active_fence_set(active, fence)) __i915_active_acquire(ref); From 84e2e393bf9fa47d134eddaeb8319c755e646f30 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Thu, 16 Mar 2023 21:56:16 +0300 Subject: [PATCH 2214/4345] io_uring: avoid null-ptr-deref in io_arm_poll_handler No upstream commit exists for this commit. The issue was introduced with backporting upstream commit c16bda37594f ("io_uring/poll: allow some retries for poll triggering spuriously"). Memory allocation can possibly fail causing invalid pointer be dereferenced just before comparing it to NULL value. Move the pointer check in proper place (upstream has the similar location of the check). In case the request has REQ_F_POLLED flag up, apoll can't be NULL so no need to check there. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 445afda927f4..fd799567fc23 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5792,10 +5792,10 @@ static int io_arm_poll_handler(struct io_kiocb *req) } } else { apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); + if (unlikely(!apoll)) + return IO_APOLL_ABORTED; apoll->poll.retries = APOLL_MAX_RETRY; } - if (unlikely(!apoll)) - return IO_APOLL_ABORTED; apoll->double_poll = NULL; req->apoll = apoll; req->flags |= REQ_F_POLLED; From b5e0b3d74285f7b5491e7fa5c3c1e0860f924edf Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Tue, 7 Mar 2023 14:35:23 +0100 Subject: [PATCH 2215/4345] s390/ipl: add missing intersection check to ipl_report handling commit a52e5cdbe8016d4e3e6322fd93d71afddb9a5af9 upstream. The code which handles the ipl report is searching for a free location in memory where it could copy the component and certificate entries to. It checks for intersection between the sections required for the kernel and the component/certificate data area, but fails to check whether the data structures linking these data areas together intersect. This might cause the iplreport copy code to overwrite the iplreport itself. Fix this by adding two addtional intersection checks. Cc: Fixes: 9641b8cc733f ("s390/ipl: read IPL report at early boot") Signed-off-by: Sven Schnelle Reviewed-by: Vasily Gorbik Signed-off-by: Vasily Gorbik Signed-off-by: Sven Schnelle Signed-off-by: Greg Kroah-Hartman --- arch/s390/boot/ipl_report.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/s390/boot/ipl_report.c b/arch/s390/boot/ipl_report.c index 0b4965573656..88bacf4999c4 100644 --- a/arch/s390/boot/ipl_report.c +++ b/arch/s390/boot/ipl_report.c @@ -57,11 +57,19 @@ repeat: if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE && intersects(INITRD_START, INITRD_SIZE, safe_addr, size)) safe_addr = INITRD_START + INITRD_SIZE; + if (intersects(safe_addr, size, (unsigned long)comps, comps->len)) { + safe_addr = (unsigned long)comps + comps->len; + goto repeat; + } for_each_rb_entry(comp, comps) if (intersects(safe_addr, size, comp->addr, comp->len)) { safe_addr = comp->addr + comp->len; goto repeat; } + if (intersects(safe_addr, size, (unsigned long)certs, certs->len)) { + safe_addr = (unsigned long)certs + certs->len; + goto repeat; + } for_each_rb_entry(cert, certs) if (intersects(safe_addr, size, cert->addr, cert->len)) { safe_addr = cert->addr + cert->len; From 337aa99f76ea07a0cd9eebe694fd21760c343330 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sun, 15 Jan 2023 09:20:32 +0100 Subject: [PATCH 2216/4345] PCI: Unify delay handling for reset and resume commit ac91e6980563ed53afadd925fa6585ffd2bc4a2c upstream. Sheng Bi reports that pci_bridge_secondary_bus_reset() may fail to wait for devices on the secondary bus to become accessible after reset: Although it does call pci_dev_wait(), it erroneously passes the bridge's pci_dev rather than that of a child. The bridge of course is always accessible while its secondary bus is reset, so pci_dev_wait() returns immediately. Sheng Bi proposes introducing a new pci_bridge_secondary_bus_wait() function which is called from pci_bridge_secondary_bus_reset(): https://lore.kernel.org/linux-pci/20220523171517.32407-1-windy.bi.enflame@gmail.com/ However we already have pci_bridge_wait_for_secondary_bus() which does almost exactly what we need. So far it's only called on resume from D3cold (which implies a Fundamental Reset per PCIe r6.0 sec 5.8). Re-using it for Secondary Bus Resets is a leaner and more rational approach than introducing a new function. That only requires a few minor tweaks: - Amend pci_bridge_wait_for_secondary_bus() to await accessibility of the first device on the secondary bus by calling pci_dev_wait() after performing the prescribed delays. pci_dev_wait() needs two parameters, a reset reason and a timeout, which callers must now pass to pci_bridge_wait_for_secondary_bus(). The timeout is 1 sec for resume (PCIe r6.0 sec 6.6.1) and 60 sec for reset (commit 821cdad5c46c ("PCI: Wait up to 60 seconds for device to become ready after FLR")). Introduce a PCI_RESET_WAIT macro for the 1 sec timeout. - Amend pci_bridge_wait_for_secondary_bus() to return 0 on success or -ENOTTY on error for consumption by pci_bridge_secondary_bus_reset(). - Drop an unnecessary 1 sec delay from pci_reset_secondary_bus() which is now performed by pci_bridge_wait_for_secondary_bus(). A static delay this long is only necessary for Conventional PCI, so modern PCIe systems benefit from shorter reset times as a side effect. Fixes: 6b2f1351af56 ("PCI: Wait for device to become ready after secondary bus reset") Link: https://lore.kernel.org/r/da77c92796b99ec568bd070cbe4725074a117038.1673769517.git.lukas@wunner.de Reported-by: Sheng Bi Tested-by: Ravi Kishore Koppuravuri Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg Reviewed-by: Kuppuswamy Sathyanarayanan Cc: stable@vger.kernel.org # v4.17+ Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci-driver.c | 4 +-- drivers/pci/pci.c | 54 ++++++++++++++++++---------------------- drivers/pci/pci.h | 10 +++++++- 3 files changed, 35 insertions(+), 33 deletions(-) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 8b587fc97f7b..c22cc20db1a7 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -911,7 +911,7 @@ static int pci_pm_resume_noirq(struct device *dev) pcie_pme_root_status_cleanup(pci_dev); if (!skip_bus_pm && prev_state == PCI_D3cold) - pci_bridge_wait_for_secondary_bus(pci_dev); + pci_bridge_wait_for_secondary_bus(pci_dev, "resume", PCI_RESET_WAIT); if (pci_has_legacy_pm_support(pci_dev)) return 0; @@ -1298,7 +1298,7 @@ static int pci_pm_runtime_resume(struct device *dev) pci_pm_default_resume(pci_dev); if (prev_state == PCI_D3cold) - pci_bridge_wait_for_secondary_bus(pci_dev); + pci_bridge_wait_for_secondary_bus(pci_dev, "resume", PCI_RESET_WAIT); if (pm && pm->runtime_resume) error = pm->runtime_resume(dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 744a2e05635b..f1a3f165f88a 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1221,7 +1221,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) return -ENOTTY; } - if (delay > 1000) + if (delay > PCI_RESET_WAIT) pci_info(dev, "not ready %dms after %s; waiting\n", delay - 1, reset_type); @@ -1230,7 +1230,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) pci_read_config_dword(dev, PCI_COMMAND, &id); } - if (delay > 1000) + if (delay > PCI_RESET_WAIT) pci_info(dev, "ready %dms after %s\n", delay - 1, reset_type); @@ -4792,24 +4792,31 @@ static int pci_bus_max_d3cold_delay(const struct pci_bus *bus) /** * pci_bridge_wait_for_secondary_bus - Wait for secondary bus to be accessible * @dev: PCI bridge + * @reset_type: reset type in human-readable form + * @timeout: maximum time to wait for devices on secondary bus (milliseconds) * * Handle necessary delays before access to the devices on the secondary - * side of the bridge are permitted after D3cold to D0 transition. + * side of the bridge are permitted after D3cold to D0 transition + * or Conventional Reset. * * For PCIe this means the delays in PCIe 5.0 section 6.6.1. For * conventional PCI it means Tpvrh + Trhfa specified in PCI 3.0 section * 4.3.2. + * + * Return 0 on success or -ENOTTY if the first device on the secondary bus + * failed to become accessible. */ -void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) +int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type, + int timeout) { struct pci_dev *child; int delay; if (pci_dev_is_disconnected(dev)) - return; + return 0; if (!pci_is_bridge(dev)) - return; + return 0; down_read(&pci_bus_sem); @@ -4821,14 +4828,14 @@ void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) */ if (!dev->subordinate || list_empty(&dev->subordinate->devices)) { up_read(&pci_bus_sem); - return; + return 0; } /* Take d3cold_delay requirements into account */ delay = pci_bus_max_d3cold_delay(dev->subordinate); if (!delay) { up_read(&pci_bus_sem); - return; + return 0; } child = list_first_entry(&dev->subordinate->devices, struct pci_dev, @@ -4837,14 +4844,12 @@ void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) /* * Conventional PCI and PCI-X we need to wait Tpvrh + Trhfa before - * accessing the device after reset (that is 1000 ms + 100 ms). In - * practice this should not be needed because we don't do power - * management for them (see pci_bridge_d3_possible()). + * accessing the device after reset (that is 1000 ms + 100 ms). */ if (!pci_is_pcie(dev)) { pci_dbg(dev, "waiting %d ms for secondary bus\n", 1000 + delay); msleep(1000 + delay); - return; + return 0; } /* @@ -4861,11 +4866,11 @@ void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) * configuration requests if we only wait for 100 ms (see * https://bugzilla.kernel.org/show_bug.cgi?id=203885). * - * Therefore we wait for 100 ms and check for the device presence. - * If it is still not present give it an additional 100 ms. + * Therefore we wait for 100 ms and check for the device presence + * until the timeout expires. */ if (!pcie_downstream_port(dev)) - return; + return 0; if (pcie_get_speed_cap(dev) <= PCIE_SPEED_5_0GT) { pci_dbg(dev, "waiting %d ms for downstream link\n", delay); @@ -4876,14 +4881,11 @@ void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) if (!pcie_wait_for_link_delay(dev, true, delay)) { /* Did not train, no need to wait any further */ pci_info(dev, "Data Link Layer Link Active not set in 1000 msec\n"); - return; + return -ENOTTY; } } - if (!pci_device_is_present(child)) { - pci_dbg(child, "waiting additional %d ms to become accessible\n", delay); - msleep(delay); - } + return pci_dev_wait(child, reset_type, timeout - delay); } void pci_reset_secondary_bus(struct pci_dev *dev) @@ -4902,15 +4904,6 @@ void pci_reset_secondary_bus(struct pci_dev *dev) ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); - - /* - * Trhfa for conventional PCI is 2^25 clock cycles. - * Assuming a minimum 33MHz clock this results in a 1s - * delay before we can consider subordinate devices to - * be re-initialized. PCIe has some ways to shorten this, - * but we don't make use of them yet. - */ - ssleep(1); } void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) @@ -4929,7 +4922,8 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) { pcibios_reset_secondary_bus(dev); - return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS); + return pci_bridge_wait_for_secondary_bus(dev, "bus reset", + PCIE_RESET_READY_POLL_MS); } EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 9197d7362731..77dd7bbe861d 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -47,6 +47,13 @@ int pci_bus_error_reset(struct pci_dev *dev); #define PCI_PM_D3HOT_WAIT 10 /* msec */ #define PCI_PM_D3COLD_WAIT 100 /* msec */ +/* + * Following exit from Conventional Reset, devices must be ready within 1 sec + * (PCIe r6.0 sec 6.6.1). A D3cold to D0 transition implies a Conventional + * Reset (PCIe r6.0 sec 5.8). + */ +#define PCI_RESET_WAIT 1000 /* msec */ + /** * struct pci_platform_pm_ops - Firmware PM callbacks * @@ -108,7 +115,8 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev); void pci_free_cap_save_buffers(struct pci_dev *dev); bool pci_bridge_d3_possible(struct pci_dev *dev); void pci_bridge_d3_update(struct pci_dev *dev); -void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev); +int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type, + int timeout); static inline void pci_wakeup_event(struct pci_dev *dev) { From d0292124bb5787a2f1ab1316509e801ca89c10fb Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sun, 15 Jan 2023 09:20:33 +0100 Subject: [PATCH 2217/4345] PCI/DPC: Await readiness of secondary bus after reset commit 53b54ad074de1896f8b021615f65b27f557ce874 upstream. pci_bridge_wait_for_secondary_bus() is called after a Secondary Bus Reset, but not after a DPC-induced Hot Reset. As a result, the delays prescribed by PCIe r6.0 sec 6.6.1 are not observed and devices on the secondary bus may be accessed before they're ready. One affected device is Intel's Ponte Vecchio HPC GPU. It comprises a PCIe switch whose upstream port is not immediately ready after reset. Because its config space is restored too early, it remains in D0uninitialized, its subordinate devices remain inaccessible and DPC recovery fails with messages such as: i915 0000:8c:00.0: can't change power state from D3cold to D0 (config space inaccessible) intel_vsec 0000:8e:00.1: can't change power state from D3cold to D0 (config space inaccessible) pcieport 0000:89:02.0: AER: device recovery failed Fix it. Link: https://lore.kernel.org/r/9f5ff00e1593d8d9a4b452398b98aa14d23fca11.1673769517.git.lukas@wunner.de Tested-by: Ravi Kishore Koppuravuri Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci.c | 3 --- drivers/pci/pci.h | 6 ++++++ drivers/pci/pcie/dpc.c | 4 ++-- 3 files changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index f1a3f165f88a..d37013d007b6 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -157,9 +157,6 @@ static int __init pcie_port_pm_setup(char *str) } __setup("pcie_port_pm=", pcie_port_pm_setup); -/* Time to wait after a reset for device to become responsive */ -#define PCIE_RESET_READY_POLL_MS 60000 - /** * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children * @bus: pointer to PCI bus structure to search diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 77dd7bbe861d..72436000ff25 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -53,6 +53,12 @@ int pci_bus_error_reset(struct pci_dev *dev); * Reset (PCIe r6.0 sec 5.8). */ #define PCI_RESET_WAIT 1000 /* msec */ +/* + * Devices may extend the 1 sec period through Request Retry Status completions + * (PCIe r6.0 sec 2.3.1). The spec does not provide an upper limit, but 60 sec + * ought to be enough for any device to become responsive. + */ +#define PCIE_RESET_READY_POLL_MS 60000 /* msec */ /** * struct pci_platform_pm_ops - Firmware PM callbacks diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index c556e7beafe3..f21d64ae4ffc 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -170,8 +170,8 @@ pci_ers_result_t dpc_reset_link(struct pci_dev *pdev) pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS, PCI_EXP_DPC_STATUS_TRIGGER); - if (!pcie_wait_for_link(pdev, true)) { - pci_info(pdev, "Data Link Layer Link Active not set in 1000 msec\n"); + if (pci_bridge_wait_for_secondary_bus(pdev, "DPC", + PCIE_RESET_READY_POLL_MS)) { clear_bit(PCI_DPC_RECOVERED, &pdev->priv_flags); ret = PCI_ERS_RESULT_DISCONNECT; } else { From d6f223cfef322d92305a697b848852ba4c2caecc Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Sat, 18 Mar 2023 12:15:15 +0200 Subject: [PATCH 2218/4345] xfs: don't assert fail on perag references on teardown commit 5b55cbc2d72632e874e50d2e36bce608e55aaaea upstream. [backport for 5.10.y, prior to perag refactoring in v5.14] Not fatal, the assert is there to catch developer attention. I'm seeing this occasionally during recoveryloop testing after a shutdown, and I don't want this to stop an overnight recoveryloop run as it is currently doing. Convert the ASSERT to a XFS_IS_CORRUPT() check so it will dump a corruption report into the log and cause a test failure that way, but it won't stop the machine dead. Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_mount.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index a2a5a0fd9233..402cf828cc91 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -126,7 +126,6 @@ __xfs_free_perag( { struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head); - ASSERT(atomic_read(&pag->pag_ref) == 0); kmem_free(pag); } @@ -145,7 +144,7 @@ xfs_free_perag( pag = radix_tree_delete(&mp->m_perag_tree, agno); spin_unlock(&mp->m_perag_lock); ASSERT(pag); - ASSERT(atomic_read(&pag->pag_ref) == 0); + XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0); xfs_iunlink_destroy(pag); xfs_buf_hash_destroy(pag); call_rcu(&pag->rcu_head, __xfs_free_perag); From be60f08c03dedb2e78d4c472de92b812ac2e5dca Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sat, 18 Mar 2023 12:15:16 +0200 Subject: [PATCH 2219/4345] xfs: purge dquots after inode walk fails during quotacheck commit 86d40f1e49e9a909d25c35ba01bea80dbcd758cb upstream. [add XFS_QMOPT_QUOTALL flag to xfs_qm_dqpurge_all() for 5.10.y backport] xfs/434 and xfs/436 have been reporting occasional memory leaks of xfs_dquot objects. These tests themselves were the messenger, not the culprit, since they unload the xfs module, which trips the slub debugging code while tearing down all the xfs slab caches: ============================================================================= BUG xfs_dquot (Tainted: G W ): Objects remaining in xfs_dquot on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Slab 0xffffea000606de00 objects=30 used=5 fp=0xffff888181b78a78 flags=0x17ff80000010200(slab|head|node=0|zone=2|lastcpupid=0xfff) CPU: 0 PID: 3953166 Comm: modprobe Tainted: G W 5.18.0-rc6-djwx #rc6 d5824be9e46a2393677bda868f9b154d917ca6a7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20171121_152543-x86-ol7-builder-01.us.oracle.com-4.el7.1 04/01/2014 Since we don't generally rmmod the xfs module between fstests, this means that xfs/434 is really just the canary in the coal mine -- something leaked a dquot, but we don't know who. After days of pounding on fstests with kmemleak enabled, I finally got it to spit this out: unreferenced object 0xffff8880465654c0 (size 536): comm "u10:4", pid 88, jiffies 4294935810 (age 29.512s) hex dump (first 32 bytes): 60 4a 56 46 80 88 ff ff 58 ea e4 5c 80 88 ff ff `JVF....X..\.... 00 e0 52 49 80 88 ff ff 01 00 01 00 00 00 00 00 ..RI............ backtrace: [] xfs_dquot_alloc+0x2c/0x530 [xfs] [] xfs_qm_dqread+0x6f/0x330 [xfs] [] xfs_qm_dqget+0x132/0x4e0 [xfs] [] xfs_qm_quotacheck_dqadjust+0xa0/0x3e0 [xfs] [] xfs_qm_dqusage_adjust+0x35d/0x4f0 [xfs] [] xfs_iwalk_ag_recs+0x348/0x5d0 [xfs] [] xfs_iwalk_run_callbacks+0x273/0x540 [xfs] [] xfs_iwalk_ag+0x5ed/0x890 [xfs] [] xfs_iwalk_ag_work+0xff/0x170 [xfs] [] xfs_pwork_work+0x79/0x130 [xfs] [] process_one_work+0x672/0x1040 [] worker_thread+0x59b/0xec0 [] kthread+0x29e/0x340 [] ret_from_fork+0x1f/0x30 Now we know that quotacheck is at fault, but even this report was canaryish -- it was triggered by xfs/494, which doesn't actually mount any filesystems. (kmemleak can be a little slow to notice leaks, even with fstests repeatedly whacking it to look for them.) Looking at the *previous* fstest, however, showed that the test run before xfs/494 was xfs/117. The tipoff to the problem is in this excerpt from dmesg: XFS (sda4): Quotacheck needed: Please wait. XFS (sda4): Metadata corruption detected at xfs_dinode_verify.part.0+0xdb/0x7b0 [xfs], inode 0x119 dinode XFS (sda4): Unmount and run xfs_repair XFS (sda4): First 128 bytes of corrupted metadata buffer: 00000000: 49 4e 81 a4 03 02 00 00 00 00 00 00 00 00 00 00 IN.............. 00000010: 00 00 00 01 00 00 00 00 00 90 57 54 54 1a 4c 68 ..........WTT.Lh 00000020: 81 f9 7d e1 6d ee 16 00 34 bd 7d e1 6d ee 16 00 ..}.m...4.}.m... 00000030: 34 bd 7d e1 6d ee 16 00 00 00 00 00 00 00 00 00 4.}.m........... 00000040: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000050: 00 00 00 02 00 00 00 00 00 00 00 00 96 80 f3 ab ................ 00000060: ff ff ff ff da 57 7b 11 00 00 00 00 00 00 00 03 .....W{......... 00000070: 00 00 00 01 00 00 00 10 00 00 00 00 00 00 00 08 ................ XFS (sda4): Quotacheck: Unsuccessful (Error -117): Disabling quotas. The dinode verifier decided that the inode was corrupt, which causes iget to return with EFSCORRUPTED. Since this happened during quotacheck, it is obvious that the kernel aborted the inode walk on account of the corruption error and disabled quotas. Unfortunately, we neglect to purge the dquot cache before doing that, which is how the dquots leaked. The problems started 10 years ago in commit b84a3a, when the dquot lists were converted to a radix tree, but the error handling behavior was not correctly preserved -- in that commit, if the bulkstat failed and usrquota was enabled, the bulkstat failure code would be overwritten by the result of flushing all the dquots to disk. As long as that succeeds, we'd continue the quota mount as if everything were ok, but instead we're now operating with a corrupt inode and incorrect quota usage counts. I didn't notice this bug in 2019 when I wrote commit ebd126a, which changed quotacheck to skip the dqflush when the scan doesn't complete due to inode walk failures. Introduced-by: b84a3a96751f ("xfs: remove the per-filesystem list of dquots") Fixes: ebd126a651f8 ("xfs: convert quotacheck to use the new iwalk functions") Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_qm.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 64e5da33733b..3c17e0c0f816 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1318,8 +1318,15 @@ xfs_qm_quotacheck( error = xfs_iwalk_threaded(mp, 0, 0, xfs_qm_dqusage_adjust, 0, true, NULL); - if (error) + if (error) { + /* + * The inode walk may have partially populated the dquot + * caches. We must purge them before disabling quota and + * tearing down the quotainfo, or else the dquots will leak. + */ + xfs_qm_dqpurge_all(mp, XFS_QMOPT_QUOTALL); goto error_return; + } /* * We've made all the changes that we need to make incore. Flush them From c84fb2962680fa85d9916d67026e4f01ea4cadca Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sat, 18 Mar 2023 12:15:17 +0200 Subject: [PATCH 2220/4345] xfs: don't leak btree cursor when insrec fails after a split commit a54f78def73d847cb060b18c4e4a3d1d26c9ca6d upstream. The recent patch to improve btree cycle checking caused a regression when I rebased the in-memory btree branch atop the 5.19 for-next branch, because in-memory short-pointer btrees do not have AG numbers. This produced the following complaint from kmemleak: unreferenced object 0xffff88803d47dde8 (size 264): comm "xfs_io", pid 4889, jiffies 4294906764 (age 24.072s) hex dump (first 32 bytes): 90 4d 0b 0f 80 88 ff ff 00 a0 bd 05 80 88 ff ff .M.............. e0 44 3a a0 ff ff ff ff 00 df 08 06 80 88 ff ff .D:............. backtrace: [] xfbtree_dup_cursor+0x49/0xc0 [xfs] [] xfs_btree_dup_cursor+0x3b/0x200 [xfs] [] __xfs_btree_split+0x6ad/0x820 [xfs] [] xfs_btree_split+0x60/0x110 [xfs] [] xfs_btree_make_block_unfull+0x19a/0x1f0 [xfs] [] xfs_btree_insrec+0x3aa/0x810 [xfs] [] xfs_btree_insert+0xb3/0x240 [xfs] [] xfs_rmap_insert+0x99/0x200 [xfs] [] xfs_rmap_map_shared+0x192/0x5f0 [xfs] [] xfs_rmap_map_raw+0x6b/0x90 [xfs] [] xrep_rmap_stash+0xd5/0x1d0 [xfs] [] xrep_rmap_visit_bmbt+0xa0/0xf0 [xfs] [] xrep_rmap_scan_iext+0x56/0xa0 [xfs] [] xrep_rmap_scan_ifork+0xd8/0x160 [xfs] [] xrep_rmap_scan_inode+0x35/0x80 [xfs] [] xrep_rmap_find_rmaps+0x10e/0x270 [xfs] I noticed that xfs_btree_insrec has a bunch of debug code that return out of the function immediately, without freeing the "new" btree cursor that can be returned when _make_block_unfull calls xfs_btree_split. Fix the error return in this function to free the btree cursor. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/xfs/libxfs/xfs_btree.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 24c7d30e41df..0926363179a7 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -3190,7 +3190,7 @@ xfs_btree_insrec( struct xfs_btree_block *block; /* btree block */ struct xfs_buf *bp; /* buffer for block */ union xfs_btree_ptr nptr; /* new block ptr */ - struct xfs_btree_cur *ncur; /* new btree cursor */ + struct xfs_btree_cur *ncur = NULL; /* new btree cursor */ union xfs_btree_key nkey; /* new block key */ union xfs_btree_key *lkey; int optr; /* old key/record index */ @@ -3270,7 +3270,7 @@ xfs_btree_insrec( #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) - return error; + goto error0; #endif /* @@ -3290,7 +3290,7 @@ xfs_btree_insrec( for (i = numrecs - ptr; i >= 0; i--) { error = xfs_btree_debug_check_ptr(cur, pp, i, level); if (error) - return error; + goto error0; } xfs_btree_shift_keys(cur, kp, 1, numrecs - ptr + 1); @@ -3375,6 +3375,8 @@ xfs_btree_insrec( return 0; error0: + if (ncur) + xfs_btree_del_cursor(ncur, error); return error; } From 35f049abbae3954fe2c3d57d62fe6624d9b29df6 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Sat, 18 Mar 2023 12:15:18 +0200 Subject: [PATCH 2221/4345] xfs: remove XFS_PREALLOC_SYNC commit 472c6e46f589c26057596dcba160712a5b3e02c5 upstream. [partial backport for dependency - xfs_ioc_space() still uses XFS_PREALLOC_SYNC] Callers can acheive the same thing by calling xfs_log_force_inode() after making their modifications. There is no need for xfs_update_prealloc_flags() to do this. Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_file.c | 13 +++++++------ fs/xfs/xfs_pnfs.c | 6 ++++-- 2 files changed, 11 insertions(+), 8 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 4d6bf8d4974f..630525b1da77 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -94,8 +94,6 @@ xfs_update_prealloc_flags( ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (flags & XFS_PREALLOC_SYNC) - xfs_trans_set_sync(tp); return xfs_trans_commit(tp); } @@ -1000,9 +998,6 @@ xfs_file_fallocate( } } - if (file->f_flags & O_DSYNC) - flags |= XFS_PREALLOC_SYNC; - error = xfs_update_prealloc_flags(ip, flags); if (error) goto out_unlock; @@ -1024,8 +1019,14 @@ xfs_file_fallocate( * leave shifted extents past EOF and hence losing access to * the data that is contained within them. */ - if (do_file_insert) + if (do_file_insert) { error = xfs_insert_file_space(ip, offset, len); + if (error) + goto out_unlock; + } + + if (file->f_flags & O_DSYNC) + error = xfs_log_force_inode(ip); out_unlock: xfs_iunlock(ip, iolock); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index f3082a957d5e..64ab54f2fe81 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -164,10 +164,12 @@ xfs_fs_map_blocks( * that the blocks allocated and handed out to the client are * guaranteed to be present even after a server crash. */ - error = xfs_update_prealloc_flags(ip, - XFS_PREALLOC_SET | XFS_PREALLOC_SYNC); + error = xfs_update_prealloc_flags(ip, XFS_PREALLOC_SET); + if (!error) + error = xfs_log_force_inode(ip); if (error) goto out_unlock; + } else { xfs_iunlock(ip, lock_flags); } From 308dfe49eb753d7263fa4e001251d733c710ed14 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Sat, 18 Mar 2023 12:15:19 +0200 Subject: [PATCH 2222/4345] xfs: fallocate() should call file_modified() commit fbe7e520036583a783b13ff9744e35c2a329d9a4 upstream. In XFS, we always update the inode change and modification time when any fallocate() operation succeeds. Furthermore, as various fallocate modes can change the file contents (extending EOF, punching holes, zeroing things, shifting extents), we should drop file privileges like suid just like we do for a regular write(). There's already a VFS helper that figures all this out for us, so use that. The net effect of this is that we no longer drop suid/sgid if the caller is root, but we also now drop file capabilities. We also move the xfs_update_prealloc_flags() function so that it now is only called by the scope that needs to set the the prealloc flag. Based on a patch from Darrick Wong. Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_file.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 630525b1da77..a95af57a59a7 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -895,6 +895,10 @@ xfs_file_fallocate( goto out_unlock; } + error = file_modified(file); + if (error) + goto out_unlock; + if (mode & FALLOC_FL_PUNCH_HOLE) { error = xfs_free_file_space(ip, offset, len); if (error) @@ -996,11 +1000,12 @@ xfs_file_fallocate( if (error) goto out_unlock; } - } - error = xfs_update_prealloc_flags(ip, flags); - if (error) - goto out_unlock; + error = xfs_update_prealloc_flags(ip, XFS_PREALLOC_SET); + if (error) + goto out_unlock; + + } /* Change file size if needed */ if (new_size) { From 8cf9400f8948781cc9175f94666421e77622d639 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Sat, 18 Mar 2023 12:15:20 +0200 Subject: [PATCH 2223/4345] xfs: set prealloc flag in xfs_alloc_file_space() commit 0b02c8c0d75a738c98c35f02efb36217c170d78c upstream. [backport for 5.10.y] Now that we only call xfs_update_prealloc_flags() from xfs_file_fallocate() in the case where we need to set the preallocation flag, do this in xfs_alloc_file_space() where we already have the inode joined into a transaction and get rid of the call to xfs_update_prealloc_flags() from the fallocate code. This also means that we now correctly avoid setting the XFS_DIFLAG_PREALLOC flag when xfs_is_always_cow_inode() is true, as these inodes will never have preallocated extents. Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_bmap_util.c | 9 +++------ fs/xfs/xfs_file.c | 8 -------- 2 files changed, 3 insertions(+), 14 deletions(-) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 7371a7f7c652..fbab1042bc90 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -800,9 +800,6 @@ xfs_alloc_file_space( quota_flag = XFS_QMOPT_RES_REGBLKS; } - /* - * Allocate and setup the transaction. - */ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, resrtextents, 0, &tp); @@ -830,9 +827,9 @@ xfs_alloc_file_space( if (error) goto error0; - /* - * Complete the transaction - */ + ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); if (error) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index a95af57a59a7..9b6c5ba5fdfb 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -850,7 +850,6 @@ xfs_file_fallocate( struct inode *inode = file_inode(file); struct xfs_inode *ip = XFS_I(inode); long error; - enum xfs_prealloc_flags flags = 0; uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; loff_t new_size = 0; bool do_file_insert = false; @@ -948,8 +947,6 @@ xfs_file_fallocate( } do_file_insert = true; } else { - flags |= XFS_PREALLOC_SET; - if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > i_size_read(inode)) { new_size = offset + len; @@ -1000,11 +997,6 @@ xfs_file_fallocate( if (error) goto out_unlock; } - - error = xfs_update_prealloc_flags(ip, XFS_PREALLOC_SET); - if (error) - goto out_unlock; - } /* Change file size if needed */ From f60b68c46444e4e9321a4313efd5ea0eddd77fb7 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sat, 18 Mar 2023 12:15:21 +0200 Subject: [PATCH 2224/4345] xfs: use setattr_copy to set vfs inode attributes commit e014f37db1a2d109afa750042ac4d69cf3e3d88e upstream. [remove userns argument of setattr_copy() for 5.10.y backport] Filipe Manana pointed out that XFS' behavior w.r.t. setuid/setgid revocation isn't consistent with btrfs[1] or ext4. Those two filesystems use the VFS function setattr_copy to convey certain attributes from struct iattr into the VFS inode structure. Andrey Zhadchenko reported[2] that XFS uses the wrong user namespace to decide if it should clear setgid and setuid on a file attribute update. This is a second symptom of the problem that Filipe noticed. XFS, on the other hand, open-codes setattr_copy in xfs_setattr_mode, xfs_setattr_nonsize, and xfs_setattr_time. Regrettably, setattr_copy is /not/ a simple copy function; it contains additional logic to clear the setgid bit when setting the mode, and XFS' version no longer matches. The VFS implements its own setuid/setgid stripping logic, which establishes consistent behavior. It's a tad unfortunate that it's scattered across notify_change, should_remove_suid, and setattr_copy but XFS should really follow the Linux VFS. Adapt XFS to use the VFS functions and get rid of the old functions. [1] https://lore.kernel.org/fstests/CAL3q7H47iNQ=Wmk83WcGB-KBJVOEtR9+qGczzCeXJ9Y2KCV25Q@mail.gmail.com/ [2] https://lore.kernel.org/linux-xfs/20220221182218.748084-1-andrey.zhadchenko@virtuozzo.com/ Fixes: 7fa294c8991c ("userns: Allow chown and setgid preservation") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Christian Brauner Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_iops.c | 56 +++-------------------------------------------- fs/xfs/xfs_pnfs.c | 3 ++- 2 files changed, 5 insertions(+), 54 deletions(-) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 6a3026e78a9b..69fef29df428 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -595,37 +595,6 @@ xfs_vn_getattr( return 0; } -static void -xfs_setattr_mode( - struct xfs_inode *ip, - struct iattr *iattr) -{ - struct inode *inode = VFS_I(ip); - umode_t mode = iattr->ia_mode; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - - inode->i_mode &= S_IFMT; - inode->i_mode |= mode & ~S_IFMT; -} - -void -xfs_setattr_time( - struct xfs_inode *ip, - struct iattr *iattr) -{ - struct inode *inode = VFS_I(ip); - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - - if (iattr->ia_valid & ATTR_ATIME) - inode->i_atime = iattr->ia_atime; - if (iattr->ia_valid & ATTR_CTIME) - inode->i_ctime = iattr->ia_ctime; - if (iattr->ia_valid & ATTR_MTIME) - inode->i_mtime = iattr->ia_mtime; -} - static int xfs_vn_change_ok( struct dentry *dentry, @@ -740,16 +709,6 @@ xfs_setattr_nonsize( goto out_cancel; } - /* - * CAP_FSETID overrides the following restrictions: - * - * The set-user-ID and set-group-ID bits of a file will be - * cleared upon successful return from chown() - */ - if ((inode->i_mode & (S_ISUID|S_ISGID)) && - !capable(CAP_FSETID)) - inode->i_mode &= ~(S_ISUID|S_ISGID); - /* * Change the ownerships and register quota modifications * in the transaction. @@ -761,7 +720,6 @@ xfs_setattr_nonsize( olddquot1 = xfs_qm_vop_chown(tp, ip, &ip->i_udquot, udqp); } - inode->i_uid = uid; } if (!gid_eq(igid, gid)) { if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) { @@ -772,15 +730,10 @@ xfs_setattr_nonsize( olddquot2 = xfs_qm_vop_chown(tp, ip, &ip->i_gdquot, gdqp); } - inode->i_gid = gid; } } - if (mask & ATTR_MODE) - xfs_setattr_mode(ip, iattr); - if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) - xfs_setattr_time(ip, iattr); - + setattr_copy(inode, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); XFS_STATS_INC(mp, xs_ig_attrchg); @@ -1025,11 +978,8 @@ xfs_setattr_size( xfs_inode_clear_eofblocks_tag(ip); } - if (iattr->ia_valid & ATTR_MODE) - xfs_setattr_mode(ip, iattr); - if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) - xfs_setattr_time(ip, iattr); - + ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID))); + setattr_copy(inode, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); XFS_STATS_INC(mp, xs_ig_attrchg); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 64ab54f2fe81..053b99929f83 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -285,7 +285,8 @@ xfs_fs_commit_blocks( xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - xfs_setattr_time(ip, iattr); + ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID))); + setattr_copy(inode, iattr); if (update_isize) { i_size_write(inode, iattr->ia_size); ip->i_d.di_size = iattr->ia_size; From 347750e1b69cef62966fbc5bd7dc579b4c00688a Mon Sep 17 00:00:00 2001 From: Yang Xu Date: Sat, 18 Mar 2023 12:15:22 +0200 Subject: [PATCH 2225/4345] fs: add mode_strip_sgid() helper commit 2b3416ceff5e6bd4922f6d1c61fb68113dd82302 upstream. [remove userns argument of helper for 5.10.y backport] Add a dedicated helper to handle the setgid bit when creating a new file in a setgid directory. This is a preparatory patch for moving setgid stripping into the vfs. The patch contains no functional changes. Currently the setgid stripping logic is open-coded directly in inode_init_owner() and the individual filesystems are responsible for handling setgid inheritance. Since this has proven to be brittle as evidenced by old issues we uncovered over the last months (see [1] to [3] below) we will try to move this logic into the vfs. Link: e014f37db1a2 ("xfs: use setattr_copy to set vfs inode attributes") [1] Link: 01ea173e103e ("xfs: fix up non-directory creation in SGID directories") [2] Link: fd84bfdddd16 ("ceph: fix up non-directory creation in SGID directories") [3] Link: https://lore.kernel.org/r/1657779088-2242-1-git-send-email-xuyang2018.jy@fujitsu.com Reviewed-by: Darrick J. Wong Reviewed-by: Christian Brauner (Microsoft) Reviewed-and-Tested-by: Jeff Layton Signed-off-by: Yang Xu Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/inode.c | 34 ++++++++++++++++++++++++++++++---- include/linux/fs.h | 1 + 2 files changed, 31 insertions(+), 4 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 9f49e0bdc2f7..23d03abcb0ff 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2147,10 +2147,8 @@ void inode_init_owner(struct inode *inode, const struct inode *dir, /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; - else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && - !in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(dir, CAP_FSETID)) - mode &= ~S_ISGID; + else + mode = mode_strip_sgid(dir, mode); } else inode->i_gid = current_fsgid(); inode->i_mode = mode; @@ -2382,3 +2380,31 @@ int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa, return 0; } EXPORT_SYMBOL(vfs_ioc_fssetxattr_check); + +/** + * mode_strip_sgid - handle the sgid bit for non-directories + * @dir: parent directory inode + * @mode: mode of the file to be created in @dir + * + * If the @mode of the new file has both the S_ISGID and S_IXGRP bit + * raised and @dir has the S_ISGID bit raised ensure that the caller is + * either in the group of the parent directory or they have CAP_FSETID + * in their user namespace and are privileged over the parent directory. + * In all other cases, strip the S_ISGID bit from @mode. + * + * Return: the new mode to use for the file + */ +umode_t mode_strip_sgid(const struct inode *dir, umode_t mode) +{ + if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) + return mode; + if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) + return mode; + if (in_group_p(dir->i_gid)) + return mode; + if (capable_wrt_inode_uidgid(dir, CAP_FSETID)) + return mode; + + return mode & ~S_ISGID; +} +EXPORT_SYMBOL(mode_strip_sgid); diff --git a/include/linux/fs.h b/include/linux/fs.h index 74e19bccbf73..527791e4860b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1768,6 +1768,7 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, extern void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); +umode_t mode_strip_sgid(const struct inode *dir, umode_t mode); /* * This is the "filldir" function type, used by readdir() to let From 94ac142c19f1016283a1860b07de7fa555385d31 Mon Sep 17 00:00:00 2001 From: Yang Xu Date: Sat, 18 Mar 2023 12:15:23 +0200 Subject: [PATCH 2226/4345] fs: move S_ISGID stripping into the vfs_*() helpers commit 1639a49ccdce58ea248841ed9b23babcce6dbb0b upstream. [remove userns argument of helpers for 5.10.y backport] Move setgid handling out of individual filesystems and into the VFS itself to stop the proliferation of setgid inheritance bugs. Creating files that have both the S_IXGRP and S_ISGID bit raised in directories that themselves have the S_ISGID bit set requires additional privileges to avoid security issues. When a filesystem creates a new inode it needs to take care that the caller is either in the group of the newly created inode or they have CAP_FSETID in their current user namespace and are privileged over the parent directory of the new inode. If any of these two conditions is true then the S_ISGID bit can be raised for an S_IXGRP file and if not it needs to be stripped. However, there are several key issues with the current implementation: * S_ISGID stripping logic is entangled with umask stripping. If a filesystem doesn't support or enable POSIX ACLs then umask stripping is done directly in the vfs before calling into the filesystem. If the filesystem does support POSIX ACLs then unmask stripping may be done in the filesystem itself when calling posix_acl_create(). Since umask stripping has an effect on S_ISGID inheritance, e.g., by stripping the S_IXGRP bit from the file to be created and all relevant filesystems have to call posix_acl_create() before inode_init_owner() where we currently take care of S_ISGID handling S_ISGID handling is order dependent. IOW, whether or not you get a setgid bit depends on POSIX ACLs and umask and in what order they are called. Note that technically filesystems are free to impose their own ordering between posix_acl_create() and inode_init_owner() meaning that there's additional ordering issues that influence S_SIGID inheritance. * Filesystems that don't rely on inode_init_owner() don't get S_ISGID stripping logic. While that may be intentional (e.g. network filesystems might just defer setgid stripping to a server) it is often just a security issue. This is not just ugly it's unsustainably messy especially since we do still have bugs in this area years after the initial round of setgid bugfixes. So the current state is quite messy and while we won't be able to make it completely clean as posix_acl_create() is still a filesystem specific call we can improve the S_SIGD stripping situation quite a bit by hoisting it out of inode_init_owner() and into the vfs creation operations. This means we alleviate the burden for filesystems to handle S_ISGID stripping correctly and can standardize the ordering between S_ISGID and umask stripping in the vfs. We add a new helper vfs_prepare_mode() so S_ISGID handling is now done in the VFS before umask handling. This has S_ISGID handling is unaffected unaffected by whether umask stripping is done by the VFS itself (if no POSIX ACLs are supported or enabled) or in the filesystem in posix_acl_create() (if POSIX ACLs are supported). The vfs_prepare_mode() helper is called directly in vfs_*() helpers that create new filesystem objects. We need to move them into there to make sure that filesystems like overlayfs hat have callchains like: sys_mknod() -> do_mknodat(mode) -> .mknod = ovl_mknod(mode) -> ovl_create(mode) -> vfs_mknod(mode) get S_ISGID stripping done when calling into lower filesystems via vfs_*() creation helpers. Moving vfs_prepare_mode() into e.g. vfs_mknod() takes care of that. This is in any case semantically cleaner because S_ISGID stripping is VFS security requirement. Security hooks so far have seen the mode with the umask applied but without S_ISGID handling done. The relevant hooks are called outside of vfs_*() creation helpers so by calling vfs_prepare_mode() from vfs_*() helpers the security hooks would now see the mode without umask stripping applied. For now we fix this by passing the mode with umask settings applied to not risk any regressions for LSM hooks. IOW, nothing changes for LSM hooks. It is worth pointing out that security hooks never saw the mode that is seen by the filesystem when actually creating the file. They have always been completely misplaced for that to work. The following filesystems use inode_init_owner() and thus relied on S_ISGID stripping: spufs, 9p, bfs, btrfs, ext2, ext4, f2fs, hfsplus, hugetlbfs, jfs, minix, nilfs2, ntfs3, ocfs2, omfs, overlayfs, ramfs, reiserfs, sysv, ubifs, udf, ufs, xfs, zonefs, bpf, tmpfs. All of the above filesystems end up calling inode_init_owner() when new filesystem objects are created through the ->mkdir(), ->mknod(), ->create(), ->tmpfile(), ->rename() inode operations. Since directories always inherit the S_ISGID bit with the exception of xfs when irix_sgid_inherit mode is turned on S_ISGID stripping doesn't apply. The ->symlink() and ->link() inode operations trivially inherit the mode from the target and the ->rename() inode operation inherits the mode from the source inode. All other creation inode operations will get S_ISGID handling via vfs_prepare_mode() when called from their relevant vfs_*() helpers. In addition to this there are filesystems which allow the creation of filesystem objects through ioctl()s or - in the case of spufs - circumventing the vfs in other ways. If filesystem objects are created through ioctl()s the vfs doesn't know about it and can't apply regular permission checking including S_ISGID logic. Therfore, a filesystem relying on S_ISGID stripping in inode_init_owner() in their ioctl() callpath will be affected by moving this logic into the vfs. We audited those filesystems: * btrfs allows the creation of filesystem objects through various ioctls(). Snapshot creation literally takes a snapshot and so the mode is fully preserved and S_ISGID stripping doesn't apply. Creating a new subvolum relies on inode_init_owner() in btrfs_new_subvol_inode() but only creates directories and doesn't raise S_ISGID. * ocfs2 has a peculiar implementation of reflinks. In contrast to e.g. xfs and btrfs FICLONE/FICLONERANGE ioctl() that is only concerned with the actual extents ocfs2 uses a separate ioctl() that also creates the target file. Iow, ocfs2 circumvents the vfs entirely here and did indeed rely on inode_init_owner() to strip the S_ISGID bit. This is the only place where a filesystem needs to call mode_strip_sgid() directly but this is self-inflicted pain. * spufs doesn't go through the vfs at all and doesn't use ioctl()s either. Instead it has a dedicated system call spufs_create() which allows the creation of filesystem objects. But spufs only creates directories and doesn't allo S_SIGID bits, i.e. it specifically only allows 0777 bits. * bpf uses vfs_mkobj() but also doesn't allow S_ISGID bits to be created. The patch will have an effect on ext2 when the EXT2_MOUNT_GRPID mount option is used, on ext4 when the EXT4_MOUNT_GRPID mount option is used, and on xfs when the XFS_FEAT_GRPID mount option is used. When any of these filesystems are mounted with their respective GRPID option then newly created files inherit the parent directories group unconditionally. In these cases non of the filesystems call inode_init_owner() and thus did never strip the S_ISGID bit for newly created files. Moving this logic into the VFS means that they now get the S_ISGID bit stripped. This is a user visible change. If this leads to regressions we will either need to figure out a better way or we need to revert. However, given the various setgid bugs that we found just in the last two years this is a regression risk we should take. Associated with this change is a new set of fstests to enforce the semantics for all new filesystems. Link: https://lore.kernel.org/ceph-devel/20220427092201.wvsdjbnc7b4dttaw@wittgenstein [1] Link: e014f37db1a2 ("xfs: use setattr_copy to set vfs inode attributes") [2] Link: 01ea173e103e ("xfs: fix up non-directory creation in SGID directories") [3] Link: fd84bfdddd16 ("ceph: fix up non-directory creation in SGID directories") [4] Link: https://lore.kernel.org/r/1657779088-2242-3-git-send-email-xuyang2018.jy@fujitsu.com Suggested-by: Dave Chinner Suggested-by: Christian Brauner (Microsoft) Reviewed-by: Darrick J. Wong Reviewed-and-Tested-by: Jeff Layton Signed-off-by: Yang Xu [: rewrote commit message] Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/inode.c | 2 -- fs/namei.c | 80 ++++++++++++++++++++++++++++++++++++++++-------- fs/ocfs2/namei.c | 1 + 3 files changed, 68 insertions(+), 15 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 23d03abcb0ff..52f834b6a3ad 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2147,8 +2147,6 @@ void inode_init_owner(struct inode *inode, const struct inode *dir, /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; - else - mode = mode_strip_sgid(dir, mode); } else inode->i_gid = current_fsgid(); inode->i_mode = mode; diff --git a/fs/namei.c b/fs/namei.c index 4159c140fa47..3d98db9802a7 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2798,6 +2798,63 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) } EXPORT_SYMBOL(unlock_rename); +/** + * mode_strip_umask - handle vfs umask stripping + * @dir: parent directory of the new inode + * @mode: mode of the new inode to be created in @dir + * + * Umask stripping depends on whether or not the filesystem supports POSIX + * ACLs. If the filesystem doesn't support it umask stripping is done directly + * in here. If the filesystem does support POSIX ACLs umask stripping is + * deferred until the filesystem calls posix_acl_create(). + * + * Returns: mode + */ +static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) +{ + if (!IS_POSIXACL(dir)) + mode &= ~current_umask(); + return mode; +} + +/** + * vfs_prepare_mode - prepare the mode to be used for a new inode + * @dir: parent directory of the new inode + * @mode: mode of the new inode + * @mask_perms: allowed permission by the vfs + * @type: type of file to be created + * + * This helper consolidates and enforces vfs restrictions on the @mode of a new + * object to be created. + * + * Umask stripping depends on whether the filesystem supports POSIX ACLs (see + * the kernel documentation for mode_strip_umask()). Moving umask stripping + * after setgid stripping allows the same ordering for both non-POSIX ACL and + * POSIX ACL supporting filesystems. + * + * Note that it's currently valid for @type to be 0 if a directory is created. + * Filesystems raise that flag individually and we need to check whether each + * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a + * non-zero type. + * + * Returns: mode to be passed to the filesystem + */ +static inline umode_t vfs_prepare_mode(const struct inode *dir, umode_t mode, + umode_t mask_perms, umode_t type) +{ + mode = mode_strip_sgid(dir, mode); + mode = mode_strip_umask(dir, mode); + + /* + * Apply the vfs mandated allowed permission mask and set the type of + * file to be created before we call into the filesystem. + */ + mode &= (mask_perms & ~S_IFMT); + mode |= (type & S_IFMT); + + return mode; +} + int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) { @@ -2807,8 +2864,8 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ - mode &= S_IALLUGO; - mode |= S_IFREG; + + mode = vfs_prepare_mode(dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; @@ -3072,8 +3129,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current_umask(); + mode = vfs_prepare_mode(dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(&nd->path, dentry, mode); else @@ -3286,8 +3342,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; - if (!IS_POSIXACL(dir)) - mode &= ~current_umask(); + mode = vfs_prepare_mode(dir, mode, mode, mode); error = dir->i_op->tmpfile(dir, child, mode); if (error) goto out_err; @@ -3548,6 +3603,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) if (!dir->i_op->mknod) return -EPERM; + mode = vfs_prepare_mode(dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; @@ -3596,9 +3652,8 @@ retry: if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mknod(&path, dentry, mode, dev); + error = security_path_mknod(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out; switch (mode & S_IFMT) { @@ -3646,7 +3701,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (!dir->i_op->mkdir) return -EPERM; - mode &= (S_IRWXUGO|S_ISVTX); + mode = vfs_prepare_mode(dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; @@ -3673,9 +3728,8 @@ retry: if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mkdir(&path, dentry, mode); + error = security_path_mkdir(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode)); if (!error) error = vfs_mkdir(path.dentry->d_inode, dentry, mode); done_path_create(&path, dentry); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 856474b0a1ae..df1f6b7aa797 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -198,6 +198,7 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode) * callers. */ if (S_ISDIR(mode)) set_nlink(inode, 2); + mode = mode_strip_sgid(dir, mode); inode_init_owner(inode, dir, mode); status = dquot_initialize(inode); if (status) From 24378d6f748649060f4d0c3eea8a1efe5bccfd1d Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 18 Mar 2023 12:15:24 +0200 Subject: [PATCH 2227/4345] attr: add in_group_or_capable() commit 11c2a8700cdcabf9b639b7204a1e38e2a0b6798e upstream. [backported to 5.10.y, prior to idmapped mounts] In setattr_{copy,prepare}() we need to perform the same permission checks to determine whether we need to drop the setgid bit or not. Instead of open-coding it twice add a simple helper the encapsulates the logic. We will reuse this helpers to make dropping the setgid bit during write operations more consistent in a follow up patch. Reviewed-by: Amir Goldstein Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/attr.c | 11 +++++------ fs/inode.c | 25 +++++++++++++++++++++---- fs/internal.h | 1 + 3 files changed, 27 insertions(+), 10 deletions(-) diff --git a/fs/attr.c b/fs/attr.c index 848ffe6e3c24..300ba5153868 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -18,6 +18,8 @@ #include #include +#include "internal.h" + static bool chown_ok(const struct inode *inode, kuid_t uid) { if (uid_eq(current_fsuid(), inode->i_uid) && @@ -90,9 +92,8 @@ int setattr_prepare(struct dentry *dentry, struct iattr *attr) if (!inode_owner_or_capable(inode)) return -EPERM; /* Also check the setgid bit! */ - if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : - inode->i_gid) && - !capable_wrt_inode_uidgid(inode, CAP_FSETID)) + if (!in_group_or_capable(inode, (ia_valid & ATTR_GID) ? + attr->ia_gid : inode->i_gid)) attr->ia_mode &= ~S_ISGID; } @@ -193,9 +194,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr) inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; - - if (!in_group_p(inode->i_gid) && - !capable_wrt_inode_uidgid(inode, CAP_FSETID)) + if (!in_group_or_capable(inode, inode->i_gid)) mode &= ~S_ISGID; inode->i_mode = mode; } diff --git a/fs/inode.c b/fs/inode.c index 52f834b6a3ad..63f86aeda7fd 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2379,6 +2379,26 @@ int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa, } EXPORT_SYMBOL(vfs_ioc_fssetxattr_check); +/** + * in_group_or_capable - check whether caller is CAP_FSETID privileged + * @inode: inode to check + * @gid: the new/current gid of @inode + * + * Check wether @gid is in the caller's group list or if the caller is + * privileged with CAP_FSETID over @inode. This can be used to determine + * whether the setgid bit can be kept or must be dropped. + * + * Return: true if the caller is sufficiently privileged, false if not. + */ +bool in_group_or_capable(const struct inode *inode, kgid_t gid) +{ + if (in_group_p(gid)) + return true; + if (capable_wrt_inode_uidgid(inode, CAP_FSETID)) + return true; + return false; +} + /** * mode_strip_sgid - handle the sgid bit for non-directories * @dir: parent directory inode @@ -2398,11 +2418,8 @@ umode_t mode_strip_sgid(const struct inode *dir, umode_t mode) return mode; if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) return mode; - if (in_group_p(dir->i_gid)) + if (in_group_or_capable(dir, dir->i_gid)) return mode; - if (capable_wrt_inode_uidgid(dir, CAP_FSETID)) - return mode; - return mode & ~S_ISGID; } EXPORT_SYMBOL(mode_strip_sgid); diff --git a/fs/internal.h b/fs/internal.h index 06d313b9beec..0fe920d9f393 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -149,6 +149,7 @@ extern int vfs_open(const struct path *, struct file *); extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); extern void inode_add_lru(struct inode *inode); extern int dentry_needs_remove_privs(struct dentry *dentry); +bool in_group_or_capable(const struct inode *inode, kgid_t gid); /* * fs-writeback.c From baea3ae425fb3d65a3aef15e58724e717a746a0b Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 18 Mar 2023 12:15:25 +0200 Subject: [PATCH 2228/4345] fs: move should_remove_suid() commit e243e3f94c804ecca9a8241b5babe28f35258ef4 upstream. Move the helper from inode.c to attr.c. This keeps the the core of the set{g,u}id stripping logic in one place when we add follow-up changes. It is the better place anyway, since should_remove_suid() returns ATTR_KILL_S{G,U}ID flags. Reviewed-by: Amir Goldstein Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/attr.c | 29 +++++++++++++++++++++++++++++ fs/inode.c | 29 ----------------------------- 2 files changed, 29 insertions(+), 29 deletions(-) diff --git a/fs/attr.c b/fs/attr.c index 300ba5153868..666489157978 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -20,6 +20,35 @@ #include "internal.h" +/* + * The logic we want is + * + * if suid or (sgid and xgrp) + * remove privs + */ +int should_remove_suid(struct dentry *dentry) +{ + umode_t mode = d_inode(dentry)->i_mode; + int kill = 0; + + /* suid always must be killed */ + if (unlikely(mode & S_ISUID)) + kill = ATTR_KILL_SUID; + + /* + * sgid without any exec bits is just a mandatory locking mark; leave + * it alone. If some exec bits are set, it's a real sgid; kill it. + */ + if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) + kill |= ATTR_KILL_SGID; + + if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) + return kill; + + return 0; +} +EXPORT_SYMBOL(should_remove_suid); + static bool chown_ok(const struct inode *inode, kuid_t uid) { if (uid_eq(current_fsuid(), inode->i_uid) && diff --git a/fs/inode.c b/fs/inode.c index 63f86aeda7fd..f52dd6feea98 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1854,35 +1854,6 @@ skip_update: } EXPORT_SYMBOL(touch_atime); -/* - * The logic we want is - * - * if suid or (sgid and xgrp) - * remove privs - */ -int should_remove_suid(struct dentry *dentry) -{ - umode_t mode = d_inode(dentry)->i_mode; - int kill = 0; - - /* suid always must be killed */ - if (unlikely(mode & S_ISUID)) - kill = ATTR_KILL_SUID; - - /* - * sgid without any exec bits is just a mandatory locking mark; leave - * it alone. If some exec bits are set, it's a real sgid; kill it. - */ - if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) - kill |= ATTR_KILL_SGID; - - if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) - return kill; - - return 0; -} -EXPORT_SYMBOL(should_remove_suid); - /* * Return mask of changes for notify_change() that need to be done as a * response to write or truncate. Return 0 if nothing has to be changed. From 240b96ffece8fc959c1b7d8647b178503a51255b Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 18 Mar 2023 12:15:26 +0200 Subject: [PATCH 2229/4345] attr: add setattr_should_drop_sgid() commit 72ae017c5451860443a16fb2a8c243bff3e396b8 upstream. [backported to 5.10.y, prior to idmapped mounts] The current setgid stripping logic during write and ownership change operations is inconsistent and strewn over multiple places. In order to consolidate it and make more consistent we'll add a new helper setattr_should_drop_sgid(). The function retains the old behavior where we remove the S_ISGID bit unconditionally when S_IXGRP is set but also when it isn't set and the caller is neither in the group of the inode nor privileged over the inode. We will use this helper both in write operation permission removal such as file_remove_privs() as well as in ownership change operations. Reviewed-by: Amir Goldstein Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/attr.c | 25 +++++++++++++++++++++++++ fs/internal.h | 5 +++++ 2 files changed, 30 insertions(+) diff --git a/fs/attr.c b/fs/attr.c index 666489157978..c8049ae34a2e 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -20,6 +20,31 @@ #include "internal.h" +/** + * setattr_should_drop_sgid - determine whether the setgid bit needs to be + * removed + * @inode: inode to check + * + * This function determines whether the setgid bit needs to be removed. + * We retain backwards compatibility and require setgid bit to be removed + * unconditionally if S_IXGRP is set. Otherwise we have the exact same + * requirements as setattr_prepare() and setattr_copy(). + * + * Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise. + */ +int setattr_should_drop_sgid(const struct inode *inode) +{ + umode_t mode = inode->i_mode; + + if (!(mode & S_ISGID)) + return 0; + if (mode & S_IXGRP) + return ATTR_KILL_SGID; + if (!in_group_or_capable(inode, inode->i_gid)) + return ATTR_KILL_SGID; + return 0; +} + /* * The logic we want is * diff --git a/fs/internal.h b/fs/internal.h index 0fe920d9f393..d5d9fcdae10c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -197,3 +197,8 @@ int sb_init_dio_done_wq(struct super_block *sb); */ int do_statx(int dfd, const char __user *filename, unsigned flags, unsigned int mask, struct statx __user *buffer); + +/* + * fs/attr.c + */ +int setattr_should_drop_sgid(const struct inode *inode); From 0e9dbde96cacd0e95e05e862b50f3079146917f2 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 18 Mar 2023 12:15:27 +0200 Subject: [PATCH 2230/4345] attr: use consistent sgid stripping checks commit ed5a7047d2011cb6b2bf84ceb6680124cc6a7d95 upstream. [backported to 5.10.y, prior to idmapped mounts] Currently setgid stripping in file_remove_privs()'s should_remove_suid() helper is inconsistent with other parts of the vfs. Specifically, it only raises ATTR_KILL_SGID if the inode is S_ISGID and S_IXGRP but not if the inode isn't in the caller's groups and the caller isn't privileged over the inode although we require this already in setattr_prepare() and setattr_copy() and so all filesystem implement this requirement implicitly because they have to use setattr_{prepare,copy}() anyway. But the inconsistency shows up in setgid stripping bugs for overlayfs in xfstests (e.g., generic/673, generic/683, generic/685, generic/686, generic/687). For example, we test whether suid and setgid stripping works correctly when performing various write-like operations as an unprivileged user (fallocate, reflink, write, etc.): echo "Test 1 - qa_user, non-exec file $verb" setup_testfile chmod a+rws $junk_file commit_and_check "$qa_user" "$verb" 64k 64k The test basically creates a file with 6666 permissions. While the file has the S_ISUID and S_ISGID bits set it does not have the S_IXGRP set. On a regular filesystem like xfs what will happen is: sys_fallocate() -> vfs_fallocate() -> xfs_file_fallocate() -> file_modified() -> __file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = ATTR_FORCE | kill; -> notify_change() -> setattr_copy() In should_remove_suid() we can see that ATTR_KILL_SUID is raised unconditionally because the file in the test has S_ISUID set. But we also see that ATTR_KILL_SGID won't be set because while the file is S_ISGID it is not S_IXGRP (see above) which is a condition for ATTR_KILL_SGID being raised. So by the time we call notify_change() we have attr->ia_valid set to ATTR_KILL_SUID | ATTR_FORCE. Now notify_change() sees that ATTR_KILL_SUID is set and does: ia_valid = attr->ia_valid |= ATTR_MODE attr->ia_mode = (inode->i_mode & ~S_ISUID); which means that when we call setattr_copy() later we will definitely update inode->i_mode. Note that attr->ia_mode still contains S_ISGID. Now we call into the filesystem's ->setattr() inode operation which will end up calling setattr_copy(). Since ATTR_MODE is set we will hit: if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); if (!vfsgid_in_group_p(vfsgid) && !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) mode &= ~S_ISGID; inode->i_mode = mode; } and since the caller in the test is neither capable nor in the group of the inode the S_ISGID bit is stripped. But assume the file isn't suid then ATTR_KILL_SUID won't be raised which has the consequence that neither the setgid nor the suid bits are stripped even though it should be stripped because the inode isn't in the caller's groups and the caller isn't privileged over the inode. If overlayfs is in the mix things become a bit more complicated and the bug shows up more clearly. When e.g., ovl_setattr() is hit from ovl_fallocate()'s call to file_remove_privs() then ATTR_KILL_SUID and ATTR_KILL_SGID might be raised but because the check in notify_change() is questioning the ATTR_KILL_SGID flag again by requiring S_IXGRP for it to be stripped the S_ISGID bit isn't removed even though it should be stripped: sys_fallocate() -> vfs_fallocate() -> ovl_fallocate() -> file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = ATTR_FORCE | kill; -> notify_change() -> ovl_setattr() // TAKE ON MOUNTER'S CREDS -> ovl_do_notify_change() -> notify_change() // GIVE UP MOUNTER'S CREDS // TAKE ON MOUNTER'S CREDS -> vfs_fallocate() -> xfs_file_fallocate() -> file_modified() -> __file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = attr_force | kill; -> notify_change() The fix for all of this is to make file_remove_privs()'s should_remove_suid() helper to perform the same checks as we already require in setattr_prepare() and setattr_copy() and have notify_change() not pointlessly requiring S_IXGRP again. It doesn't make any sense in the first place because the caller must calculate the flags via should_remove_suid() anyway which would raise ATTR_KILL_SGID. While we're at it we move should_remove_suid() from inode.c to attr.c where it belongs with the rest of the iattr helpers. Especially since it returns ATTR_KILL_S{G,U}ID flags. We also rename it to setattr_should_drop_suidgid() to better reflect that it indicates both setuid and setgid bit removal and also that it returns attr flags. Running xfstests with this doesn't report any regressions. We should really try and use consistent checks. Reviewed-by: Amir Goldstein Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- Documentation/trace/ftrace.rst | 2 +- fs/attr.c | 31 +++++++++++++++++-------------- fs/inode.c | 2 +- fs/ocfs2/file.c | 4 ++-- fs/open.c | 6 +++--- include/linux/fs.h | 2 +- 6 files changed, 25 insertions(+), 22 deletions(-) diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index 87cf5c010d5d..ed2e45f9b762 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -2923,7 +2923,7 @@ Produces:: bash-1994 [000] .... 4342.324898: ima_get_action <-process_measurement bash-1994 [000] .... 4342.324898: ima_match_policy <-ima_get_action bash-1994 [000] .... 4342.324899: do_truncate <-do_last - bash-1994 [000] .... 4342.324899: should_remove_suid <-do_truncate + bash-1994 [000] .... 4342.324899: setattr_should_drop_suidgid <-do_truncate bash-1994 [000] .... 4342.324899: notify_change <-do_truncate bash-1994 [000] .... 4342.324900: current_fs_time <-notify_change bash-1994 [000] .... 4342.324900: current_kernel_time <-current_fs_time diff --git a/fs/attr.c b/fs/attr.c index c8049ae34a2e..326a0db3296d 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -45,34 +45,37 @@ int setattr_should_drop_sgid(const struct inode *inode) return 0; } -/* - * The logic we want is +/** + * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to + * be dropped + * @inode: inode to check * - * if suid or (sgid and xgrp) - * remove privs + * This function determines whether the set{g,u}id bits need to be removed. + * If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the + * setgid bit needs to be removed ATTR_KILL_SGID is returned. If both + * set{g,u}id bits need to be removed the corresponding mask of both flags is + * returned. + * + * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits + * to remove, 0 otherwise. */ -int should_remove_suid(struct dentry *dentry) +int setattr_should_drop_suidgid(struct inode *inode) { - umode_t mode = d_inode(dentry)->i_mode; + umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; - /* - * sgid without any exec bits is just a mandatory locking mark; leave - * it alone. If some exec bits are set, it's a real sgid; kill it. - */ - if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) - kill |= ATTR_KILL_SGID; + kill |= setattr_should_drop_sgid(inode); if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; return 0; } -EXPORT_SYMBOL(should_remove_suid); +EXPORT_SYMBOL(setattr_should_drop_suidgid); static bool chown_ok(const struct inode *inode, kuid_t uid) { @@ -350,7 +353,7 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de } } if (ia_valid & ATTR_KILL_SGID) { - if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { + if (mode & S_ISGID) { if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = inode->i_mode; diff --git a/fs/inode.c b/fs/inode.c index f52dd6feea98..7ec90788d8be 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1868,7 +1868,7 @@ int dentry_needs_remove_privs(struct dentry *dentry) if (IS_NOSEC(inode)) return 0; - mask = should_remove_suid(dentry); + mask = setattr_should_drop_suidgid(inode); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 1470b49adb2d..ca00cac5a12f 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1994,7 +1994,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, } } - if (file && should_remove_suid(file->f_path.dentry)) { + if (file && setattr_should_drop_suidgid(file_inode(file))) { ret = __ocfs2_write_remove_suid(inode, di_bh); if (ret) { mlog_errno(ret); @@ -2282,7 +2282,7 @@ static int ocfs2_prepare_inode_for_write(struct file *file, * inode. There's also the dinode i_size state which * can be lost via setattr during extending writes (we * set inode->i_size at the end of a write. */ - if (should_remove_suid(dentry)) { + if (setattr_should_drop_suidgid(inode)) { if (meta_level == 0) { ocfs2_inode_unlock_for_extent_tree(inode, &di_bh, diff --git a/fs/open.c b/fs/open.c index b3fbb4300fc9..1ca4b236fdbe 100644 --- a/fs/open.c +++ b/fs/open.c @@ -665,10 +665,10 @@ retry_deleg: newattrs.ia_valid |= ATTR_GID; newattrs.ia_gid = gid; } - if (!S_ISDIR(inode->i_mode)) - newattrs.ia_valid |= - ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; inode_lock(inode); + if (!S_ISDIR(inode->i_mode)) + newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | + setattr_should_drop_sgid(inode); error = security_path_chown(path, uid, gid); if (!error) error = notify_change(path->dentry, &newattrs, &delegated_inode); diff --git a/include/linux/fs.h b/include/linux/fs.h index 527791e4860b..57afa4fa5e7b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2960,7 +2960,7 @@ extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); -extern int should_remove_suid(struct dentry *); +extern int setattr_should_drop_suidgid(struct inode *); extern int file_remove_privs(struct file *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); From 183ca919544c898dfbb40f6b26d33bfe8765a986 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sat, 18 Mar 2023 12:15:28 +0200 Subject: [PATCH 2231/4345] fs: use consistent setgid checks in is_sxid() commit 8d84e39d76bd83474b26cb44f4b338635676e7e8 upstream. Now that we made the VFS setgid checking consistent an inode can't be marked security irrelevant even if the setgid bit is still set. Make this function consistent with all other helpers. Note that enforcing consistent setgid stripping checks for file modification and mode- and ownership changes will cause the setgid bit to be lost in more cases than useed to be the case. If an unprivileged user wrote to a non-executable setgid file that they don't have privilege over the setgid bit will be dropped. This will lead to temporary failures in some xfstests until they have been updated. Reported-by: Miklos Szeredi Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/fs.h b/include/linux/fs.h index 57afa4fa5e7b..8ce9e5c61ede 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3408,7 +3408,7 @@ int __init get_filesystem_list(char *buf); static inline bool is_sxid(umode_t mode) { - return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); + return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct inode *dir, struct inode *inode) From daa97e770e780b5e74d85afd236849359711a8d0 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Sat, 18 Mar 2023 12:15:29 +0200 Subject: [PATCH 2232/4345] xfs: remove xfs_setattr_time() declaration commit b0463b9dd7030a766133ad2f1571f97f204d7bdf upstream. xfs_setattr_time() has been removed since commit e014f37db1a2 ("xfs: use setattr_copy to set vfs inode attributes"), so remove it. Signed-off-by: Gaosheng Cui Reviewed-by: Carlos Maiolino Signed-off-by: Dave Chinner Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_iops.h | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index 4d24ff309f59..dd1bd0332f8e 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -18,7 +18,6 @@ extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size); */ #define XFS_ATTR_NOACL 0x01 /* Don't call posix_acl_chmod */ -extern void xfs_setattr_time(struct xfs_inode *ip, struct iattr *iattr); extern int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap, int flags); extern int xfs_vn_setattr_nonsize(struct dentry *dentry, struct iattr *vap); From 9bc878756b017f2e1d8dc4f261faa64f69c4c2ee Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 20 Mar 2023 13:06:31 +0000 Subject: [PATCH 2233/4345] HID: core: Provide new max_buffer_size attribute to over-ride the default commit b1a37ed00d7908a991c1d0f18a8cba3c2aa99bdc upstream. Presently, when a report is processed, its proposed size, provided by the user of the API (as Report Size * Report Count) is compared against the subsystem default HID_MAX_BUFFER_SIZE (16k). However, some low-level HID drivers allocate a reduced amount of memory to their buffers (e.g. UHID only allocates UHID_DATA_MAX (4k) buffers), rending this check inadequate in some cases. In these circumstances, if the received report ends up being smaller than the proposed report size, the remainder of the buffer is zeroed. That is, the space between sizeof(csize) (size of the current report) and the rsize (size proposed i.e. Report Size * Report Count), which can be handled up to HID_MAX_BUFFER_SIZE (16k). Meaning that memset() shoots straight past the end of the buffer boundary and starts zeroing out in-use values, often resulting in calamity. This patch introduces a new variable into 'struct hid_ll_driver' where individual low-level drivers can over-ride the default maximum value of HID_MAX_BUFFER_SIZE (16k) with something more sympathetic to the interface. Signed-off-by: Lee Jones Signed-off-by: Jiri Kosina [Lee: Backported to v5.10.y] Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-core.c | 18 +++++++++++++----- include/linux/hid.h | 3 +++ 2 files changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 5f9ec1d1464a..524d6d712e72 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -258,6 +258,7 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign { struct hid_report *report; struct hid_field *field; + unsigned int max_buffer_size = HID_MAX_BUFFER_SIZE; unsigned int usages; unsigned int offset; unsigned int i; @@ -288,8 +289,11 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign offset = report->size; report->size += parser->global.report_size * parser->global.report_count; + if (parser->device->ll_driver->max_buffer_size) + max_buffer_size = parser->device->ll_driver->max_buffer_size; + /* Total size check: Allow for possible report index byte */ - if (report->size > (HID_MAX_BUFFER_SIZE - 1) << 3) { + if (report->size > (max_buffer_size - 1) << 3) { hid_err(parser->device, "report is too long\n"); return -1; } @@ -1752,6 +1756,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, struct hid_report_enum *report_enum = hid->report_enum + type; struct hid_report *report; struct hid_driver *hdrv; + int max_buffer_size = HID_MAX_BUFFER_SIZE; unsigned int a; u32 rsize, csize = size; u8 *cdata = data; @@ -1768,10 +1773,13 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, rsize = hid_compute_report_size(report); - if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) - rsize = HID_MAX_BUFFER_SIZE - 1; - else if (rsize > HID_MAX_BUFFER_SIZE) - rsize = HID_MAX_BUFFER_SIZE; + if (hid->ll_driver->max_buffer_size) + max_buffer_size = hid->ll_driver->max_buffer_size; + + if (report_enum->numbered && rsize >= max_buffer_size) + rsize = max_buffer_size - 1; + else if (rsize > max_buffer_size) + rsize = max_buffer_size; if (csize < rsize) { dbg_hid("report %d is too short, (%d < %d)\n", report->id, diff --git a/include/linux/hid.h b/include/linux/hid.h index 2ba33d708942..256f34f49167 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -798,6 +798,7 @@ struct hid_driver { * @raw_request: send raw report request to device (e.g. feature report) * @output_report: send output report to device * @idle: send idle request to device + * @max_buffer_size: over-ride maximum data buffer size (default: HID_MAX_BUFFER_SIZE) */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); @@ -822,6 +823,8 @@ struct hid_ll_driver { int (*output_report) (struct hid_device *hdev, __u8 *buf, size_t len); int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); + + unsigned int max_buffer_size; }; extern struct hid_ll_driver i2c_hid_ll_driver; From e57f797e3ffafb09eafb9be69d065d1e0331da61 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 20 Mar 2023 13:06:32 +0000 Subject: [PATCH 2234/4345] HID: uhid: Over-ride the default maximum data buffer value with our own commit 1c5d4221240a233df2440fe75c881465cdf8da07 upstream. The default maximum data buffer size for this interface is UHID_DATA_MAX (4k). When data buffers are being processed, ensure this value is used when ensuring the sanity, rather than a value between the user provided value and HID_MAX_BUFFER_SIZE (16k). Signed-off-by: Lee Jones Signed-off-by: Jiri Kosina Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- drivers/hid/uhid.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c index fc06d8bb42e0..ba0ca652b9da 100644 --- a/drivers/hid/uhid.c +++ b/drivers/hid/uhid.c @@ -395,6 +395,7 @@ struct hid_ll_driver uhid_hid_driver = { .parse = uhid_hid_parse, .raw_request = uhid_hid_raw_request, .output_report = uhid_hid_output_report, + .max_buffer_size = UHID_DATA_MAX, }; EXPORT_SYMBOL_GPL(uhid_hid_driver); From ca9787bdecfa2174b0a169a54916e22b89b0ef5b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 22 Mar 2023 13:30:08 +0100 Subject: [PATCH 2235/4345] Linux 5.10.176 Link: https://lore.kernel.org/r/20230320145443.333824603@linuxfoundation.org Tested-by: Chris Paterson (CIP) Tested-by: Florian Fainelli Tested-by: Linux Kernel Functional Testing Tested-by: Shuah Khan Tested-by: Jon Hunter Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e6b09052f222..71caf5938361 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 175 +SUBLEVEL = 176 EXTRAVERSION = NAME = Dare mighty things From a880d7ebc53ec8595200175f860f35ef8755e91f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 15:39:31 +0000 Subject: [PATCH 2236/4345] ANDROID: remove CONFIG_NET_CLS_TCINDEX from gki_defconfig The tcindex code was removed from the tree in 5.10.173, so remove the config option from the gki_defconfig files to fix up the build. Fixes: 18c3fa7a7fdb ("net/sched: Retire tcindex classifier") Change-Id: Id4927815ec2fd0ebc8065d891dfb721551f3dbc6 Signed-off-by: Greg Kroah-Hartman --- arch/arm64/configs/gki_defconfig | 1 - arch/x86/configs/gki_defconfig | 1 - 2 files changed, 2 deletions(-) diff --git a/arch/arm64/configs/gki_defconfig b/arch/arm64/configs/gki_defconfig index 2ff6b13c9fe6..89281967589c 100644 --- a/arch/arm64/configs/gki_defconfig +++ b/arch/arm64/configs/gki_defconfig @@ -244,7 +244,6 @@ CONFIG_NET_SCH_FQ_CODEL=y CONFIG_NET_SCH_FQ=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_CLS_BASIC=y -CONFIG_NET_CLS_TCINDEX=y CONFIG_NET_CLS_FW=y CONFIG_NET_CLS_U32=y CONFIG_CLS_U32_MARK=y diff --git a/arch/x86/configs/gki_defconfig b/arch/x86/configs/gki_defconfig index 8c486248e3dd..a317546d3098 100644 --- a/arch/x86/configs/gki_defconfig +++ b/arch/x86/configs/gki_defconfig @@ -220,7 +220,6 @@ CONFIG_NET_SCH_FQ_CODEL=y CONFIG_NET_SCH_FQ=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_CLS_BASIC=y -CONFIG_NET_CLS_TCINDEX=y CONFIG_NET_CLS_FW=y CONFIG_NET_CLS_U32=y CONFIG_CLS_U32_MARK=y From 1aaaa18b4a4abab3b5643bee9093f9cc32d4e581 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 23 Mar 2023 14:40:28 +0000 Subject: [PATCH 2237/4345] Revert "PCI: loongson: Add more devices that need MRRS quirk" This reverts commit faa050d2ff8820f450b69b84645e74b6934ed5ad which is commit c768f8c5f40fcdc6f058cc2f02592163d6c6716c upstream. It breaks the Android kernel abi and it not needed for any Android devices at this time. If it is needed, it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: I0d81c2395d7e4e42c81631040b40e936f2ccdf6a Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pci-loongson.c | 33 ++++++++------------------- 1 file changed, 9 insertions(+), 24 deletions(-) diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c index e73e18a73833..dc7b4e4293ce 100644 --- a/drivers/pci/controller/pci-loongson.c +++ b/drivers/pci/controller/pci-loongson.c @@ -13,14 +13,9 @@ #include "../pci.h" /* Device IDs */ -#define DEV_LS2K_PCIE_PORT0 0x1a05 -#define DEV_LS7A_PCIE_PORT0 0x7a09 -#define DEV_LS7A_PCIE_PORT1 0x7a19 -#define DEV_LS7A_PCIE_PORT2 0x7a29 -#define DEV_LS7A_PCIE_PORT3 0x7a39 -#define DEV_LS7A_PCIE_PORT4 0x7a49 -#define DEV_LS7A_PCIE_PORT5 0x7a59 -#define DEV_LS7A_PCIE_PORT6 0x7a69 +#define DEV_PCIE_PORT_0 0x7a09 +#define DEV_PCIE_PORT_1 0x7a19 +#define DEV_PCIE_PORT_2 0x7a29 #define DEV_LS2K_APB 0x7a02 #define DEV_LS7A_CONF 0x7a10 @@ -43,11 +38,11 @@ static void bridge_class_quirk(struct pci_dev *dev) dev->class = PCI_CLASS_BRIDGE_PCI << 8; } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT0, bridge_class_quirk); + DEV_PCIE_PORT_0, bridge_class_quirk); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT1, bridge_class_quirk); + DEV_PCIE_PORT_1, bridge_class_quirk); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT2, bridge_class_quirk); + DEV_PCIE_PORT_2, bridge_class_quirk); static void system_bus_quirk(struct pci_dev *pdev) { @@ -77,21 +72,11 @@ static void loongson_mrrs_quirk(struct pci_dev *pdev) bridge->no_inc_mrrs = 1; } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS2K_PCIE_PORT0, loongson_mrrs_quirk); + DEV_PCIE_PORT_0, loongson_mrrs_quirk); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT0, loongson_mrrs_quirk); + DEV_PCIE_PORT_1, loongson_mrrs_quirk); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT1, loongson_mrrs_quirk); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT2, loongson_mrrs_quirk); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT3, loongson_mrrs_quirk); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT4, loongson_mrrs_quirk); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT5, loongson_mrrs_quirk); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_LS7A_PCIE_PORT6, loongson_mrrs_quirk); + DEV_PCIE_PORT_2, loongson_mrrs_quirk); static void __iomem *cfg1_map(struct loongson_pci *priv, int bus, unsigned int devfn, int where) From 04d892b6169308165b25d962be72f85de26c039d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 23 Mar 2023 14:40:41 +0000 Subject: [PATCH 2238/4345] Revert "PCI: loongson: Prevent LS7A MRRS increases" This reverts commit 654ae539254d10042869fdc77ad04c09e7eff1fd which is commit 8b3517f88ff2983f52698893519227c10aac90b2 upstream. It breaks the Android kernel abi and it not needed for any Android devices at this time. If it is needed, it can be brought back in an ABI-safe way. Bug: 161946584 Signed-off-by: Greg Kroah-Hartman Change-Id: I8543def5fb03133f4772ba1976f882d182bba677 --- drivers/pci/controller/pci-loongson.c | 42 ++++++++++++++++++--------- drivers/pci/pci.c | 10 ------- include/linux/pci.h | 1 - 3 files changed, 28 insertions(+), 25 deletions(-) diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c index dc7b4e4293ce..48169b1e3817 100644 --- a/drivers/pci/controller/pci-loongson.c +++ b/drivers/pci/controller/pci-loongson.c @@ -60,23 +60,37 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DEV_LS7A_LPC, system_bus_quirk); -static void loongson_mrrs_quirk(struct pci_dev *pdev) +static void loongson_mrrs_quirk(struct pci_dev *dev) { - /* - * Some Loongson PCIe ports have h/w limitations of maximum read - * request size. They can't handle anything larger than this. So - * force this limit on any devices attached under these ports. - */ - struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); + struct pci_bus *bus = dev->bus; + struct pci_dev *bridge; + static const struct pci_device_id bridge_devids[] = { + { PCI_VDEVICE(LOONGSON, DEV_PCIE_PORT_0) }, + { PCI_VDEVICE(LOONGSON, DEV_PCIE_PORT_1) }, + { PCI_VDEVICE(LOONGSON, DEV_PCIE_PORT_2) }, + { 0, }, + }; - bridge->no_inc_mrrs = 1; + /* look for the matching bridge */ + while (!pci_is_root_bus(bus)) { + bridge = bus->self; + bus = bus->parent; + /* + * Some Loongson PCIe ports have a h/w limitation of + * 256 bytes maximum read request size. They can't handle + * anything larger than this. So force this limit on + * any devices attached under these ports. + */ + if (pci_match_id(bridge_devids, bridge)) { + if (pcie_get_readrq(dev) > 256) { + pci_info(dev, "limiting MRRS to 256\n"); + pcie_set_readrq(dev, 256); + } + break; + } + } } -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_PCIE_PORT_0, loongson_mrrs_quirk); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_PCIE_PORT_1, loongson_mrrs_quirk); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, - DEV_PCIE_PORT_2, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_mrrs_quirk); static void __iomem *cfg1_map(struct loongson_pci *priv, int bus, unsigned int devfn, int where) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 8faf263f0d11..da01b31c29ef 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5746,7 +5746,6 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) { u16 v; int ret; - struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus); if (rq < 128 || rq > 4096 || !is_power_of_2(rq)) return -EINVAL; @@ -5765,15 +5764,6 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) v = (ffs(rq) - 8) << 12; - if (bridge->no_inc_mrrs) { - int max_mrrs = pcie_get_readrq(dev); - - if (rq > max_mrrs) { - pci_info(dev, "can't set Max_Read_Request_Size to %d; max is %d\n", rq, max_mrrs); - return -EINVAL; - } - } - ret = pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_READRQ, v); diff --git a/include/linux/pci.h b/include/linux/pci.h index 62a7a1c25166..3abe5ddb5c03 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -545,7 +545,6 @@ struct pci_host_bridge { struct msi_controller *msi; unsigned int ignore_reset_delay:1; /* For entire hierarchy */ unsigned int no_ext_tags:1; /* No Extended Tags */ - unsigned int no_inc_mrrs:1; /* No Increase MRRS */ unsigned int native_aer:1; /* OS may use PCIe AER */ unsigned int native_pcie_hotplug:1; /* OS may use PCIe hotplug */ unsigned int native_shpc_hotplug:1; /* OS may use SHPC hotplug */ From 78a559e2a9be34380399d49020ba3248265607cb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 Feb 2021 06:41:44 -0800 Subject: [PATCH 2239/4345] UPSTREAM: net: initialize net->net_cookie at netns setup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is simpler to make net->net_cookie a plain u64 written once in setup_net() instead of looping and using atomic64 helpers. Lorenz Bauer wants to add SO_NETNS_COOKIE socket option and this patch would makes his patch series simpler. Signed-off-by: Eric Dumazet Cc: Daniel Borkmann Cc: Lorenz Bauer Acked-by: Daniel Borkmann Tested-by: Lorenz Bauer Signed-off-by: David S. Miller (cherry picked from commit 3d368ab87cf6681f928de1ddf804d69600671bb2) Bug: 274789652 Tested: builds, net_test passes Signed-off-by: Maciej Żenczykowski Change-Id: Ia4d018b37af2792f0a21de028f724193797c5138 --- include/net/net_namespace.h | 4 +--- net/core/filter.c | 8 +++----- net/core/net_namespace.c | 19 +++---------------- 3 files changed, 7 insertions(+), 24 deletions(-) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index eb0e7731f3b1..007a9fda9a48 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -171,7 +171,7 @@ struct net { struct netns_xfrm xfrm; #endif - atomic64_t net_cookie; /* written once */ + u64 net_cookie; /* written once */ #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; @@ -237,8 +237,6 @@ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); struct net *get_net_ns_by_fd(int fd); -u64 __net_gen_cookie(struct net *net); - #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); void ipx_unregister_sysctl(void); diff --git a/net/core/filter.c b/net/core/filter.c index 52646107d4e5..16af230341ad 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4636,11 +4636,9 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { static u64 __bpf_get_netns_cookie(struct sock *sk) { -#ifdef CONFIG_NET_NS - return __net_gen_cookie(sk ? sk->sk_net.net : &init_net); -#else - return 0; -#endif + const struct net *net = sk ? sock_net(sk) : &init_net; + + return net->net_cookie; } BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index e05dd4f3279a..20a0fc4d059b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -72,18 +72,6 @@ static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; DEFINE_COOKIE(net_cookie); -u64 __net_gen_cookie(struct net *net) -{ - while (1) { - u64 res = atomic64_read(&net->net_cookie); - - if (res) - return res; - res = gen_cookie_next(&net_cookie); - atomic64_cmpxchg(&net->net_cookie, 0, res); - } -} - static struct net_generic *net_alloc_generic(void) { struct net_generic *ng; @@ -341,6 +329,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) refcount_set(&net->count, 1); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); + preempt_disable(); + net->net_cookie = gen_cookie_next(&net_cookie); + preempt_enable(); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); @@ -1128,10 +1119,6 @@ static int __init net_ns_init(void) rcu_assign_pointer(init_net.gen, ng); - preempt_disable(); - __net_gen_cookie(&init_net); - preempt_enable(); - down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); From cda90416c039b2cfabf0ea2c4905995fd0fa3d1a Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Wed, 23 Jun 2021 15:56:45 +0200 Subject: [PATCH 2240/4345] UPSTREAM: net: retrieve netns cookie via getsocketopt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's getting more common to run nested container environments for testing cloud software. One of such examples is Kind [1] which runs a Kubernetes cluster in Docker containers on a single host. Each container acts as a Kubernetes node, and thus can run any Pod (aka container) inside the former. This approach simplifies testing a lot, as it eliminates complicated VM setups. Unfortunately, such a setup breaks some functionality when cgroupv2 BPF programs are used for load-balancing. The load-balancer BPF program needs to detect whether a request originates from the host netns or a container netns in order to allow some access, e.g. to a service via a loopback IP address. Typically, the programs detect this by comparing netns cookies with the one of the init ns via a call to bpf_get_netns_cookie(NULL). However, in nested environments the latter cannot be used given the Kubernetes node's netns is outside the init ns. To fix this, we need to pass the Kubernetes node netns cookie to the program in a different way: by extending getsockopt() with a SO_NETNS_COOKIE option, the orchestrator which runs in the Kubernetes node netns can retrieve the cookie and pass it to the program instead. Thus, this is following up on Eric's commit 3d368ab87cf6 ("net: initialize net->net_cookie at netns setup") to allow retrieval via SO_NETNS_COOKIE. This is also in line in how we retrieve socket cookie via SO_COOKIE. [1] https://kind.sigs.k8s.io/ Signed-off-by: Lorenz Bauer Signed-off-by: Martynas Pumputis Cc: Eric Dumazet Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller (cherry picked from commit e8b9eab99232c4e62ada9d7976c80fd5e8118289) Bug: 274789652 Tested: builds, net_test passes Signed-off-by: Maciej Żenczykowski Change-Id: If784a592450af38d70f16da61e36cbbaff80ebca --- arch/alpha/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ include/uapi/asm-generic/socket.h | 2 ++ net/core/sock.c | 7 +++++++ 6 files changed, 17 insertions(+) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index de6c4df61082..d033d3f92d6d 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -124,6 +124,8 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_NETNS_COOKIE 71 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index d0a9ed2ca2d6..ff3ab771e769 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -135,6 +135,8 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_NETNS_COOKIE 71 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 10173c32195e..1a8ec3838c9b 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -116,6 +116,8 @@ #define SO_DETACH_REUSEPORT_BPF 0x4042 +#define SO_NETNS_COOKIE 0x4045 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 8029b681fc7c..08f9bbbf5bf2 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -117,6 +117,8 @@ #define SO_DETACH_REUSEPORT_BPF 0x0047 +#define SO_NETNS_COOKIE 0x0050 + #if !defined(__KERNEL__) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 77f7c1638eb1..645606824258 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -119,6 +119,8 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_NETNS_COOKIE 71 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/net/core/sock.c b/net/core/sock.c index 0506590b016b..fe7799499963 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1613,6 +1613,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_bound_dev_if; break; + case SO_NETNS_COOKIE: + lv = sizeof(u64); + if (len != lv) + return -EINVAL; + v.val64 = sock_net(sk)->net_cookie; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). From 05fa7d8eee9ed5eaba4f7ea32472765fd8a7a9e9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Wed, 22 Mar 2023 16:13:37 -0700 Subject: [PATCH 2241/4345] ANDROID: fix ABI by undoing atomic64_t -> u64 type conversion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is pretty much a no-op, but avoids changing struct net ABI. Bug: 274789652 Test: builds, net_test Signed-off-by: Maciej Żenczykowski Change-Id: Ia744bdf0a026adccaef8382aaecc771a8d0763a6 --- include/net/net_namespace.h | 2 +- net/core/filter.c | 2 +- net/core/net_namespace.c | 2 +- net/core/sock.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 007a9fda9a48..9764f4cc1d94 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -171,7 +171,7 @@ struct net { struct netns_xfrm xfrm; #endif - u64 net_cookie; /* written once */ + atomic64_t net_cookie; /* written once */ #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; diff --git a/net/core/filter.c b/net/core/filter.c index 16af230341ad..bca0002228cd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4638,7 +4638,7 @@ static u64 __bpf_get_netns_cookie(struct sock *sk) { const struct net *net = sk ? sock_net(sk) : &init_net; - return net->net_cookie; + return atomic64_read(&net->net_cookie); } BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 20a0fc4d059b..f1258afa1475 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -330,7 +330,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); preempt_disable(); - net->net_cookie = gen_cookie_next(&net_cookie); + atomic64_set(&net->net_cookie, gen_cookie_next(&net_cookie)); preempt_enable(); net->dev_base_seq = 1; net->user_ns = user_ns; diff --git a/net/core/sock.c b/net/core/sock.c index fe7799499963..64e2f9fb6552 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1617,7 +1617,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, lv = sizeof(u64); if (len != lv) return -EINVAL; - v.val64 = sock_net(sk)->net_cookie; + v.val64 = atomic64_read(&sock_net(sk)->net_cookie); break; default: From cd1d9c42a26bb1a043ba6642d24feca8d9c27b6d Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Thu, 28 Oct 2021 12:11:08 +0200 Subject: [PATCH 2242/4345] UPSTREAM: hwrng: virtio - add an internal buffer hwrng core uses two buffers that can be mixed in the virtio-rng queue. If the buffer is provided with wait=0 it is enqueued in the virtio-rng queue but unused by the caller. On the next call, core provides another buffer but the first one is filled instead and the new one queued. And the caller reads the data from the new one that is not updated, and the data in the first one are lost. To avoid this mix, virtio-rng needs to use its own unique internal buffer at a cost of a data copy to the caller buffer. Signed-off-by: Laurent Vivier Link: https://lore.kernel.org/r/20211028101111.128049-2-lvivier@redhat.com Signed-off-by: Michael S. Tsirkin (cherry picked from commit bf3175bc50a3754dc427e2f5046e17a9fafc8be7) Bug: 249566340 Change-Id: Ica2fd680de4bb359923b94dae48c00f6207a6876 Signed-off-by: Alistair Delva --- drivers/char/hw_random/virtio-rng.c | 43 ++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 10 deletions(-) diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index a90001e02bf7..208c547dcac1 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -18,13 +18,20 @@ static DEFINE_IDA(rng_index_ida); struct virtrng_info { struct hwrng hwrng; struct virtqueue *vq; - struct completion have_data; char name[25]; - unsigned int data_avail; int index; bool busy; bool hwrng_register_done; bool hwrng_removed; + /* data transfer */ + struct completion have_data; + unsigned int data_avail; + /* minimal size returned by rng_buffer_size() */ +#if SMP_CACHE_BYTES < 32 + u8 data[32]; +#else + u8 data[SMP_CACHE_BYTES]; +#endif }; static void random_recv_done(struct virtqueue *vq) @@ -39,14 +46,14 @@ static void random_recv_done(struct virtqueue *vq) } /* The host will fill any buffer we give it with sweet, sweet randomness. */ -static void register_buffer(struct virtrng_info *vi, u8 *buf, size_t size) +static void register_buffer(struct virtrng_info *vi) { struct scatterlist sg; - sg_init_one(&sg, buf, size); + sg_init_one(&sg, vi->data, sizeof(vi->data)); /* There should always be room for one buffer. */ - virtqueue_add_inbuf(vi->vq, &sg, 1, buf, GFP_KERNEL); + virtqueue_add_inbuf(vi->vq, &sg, 1, vi->data, GFP_KERNEL); virtqueue_kick(vi->vq); } @@ -55,6 +62,8 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) { int ret; struct virtrng_info *vi = (struct virtrng_info *)rng->priv; + unsigned int chunk; + size_t read; if (vi->hwrng_removed) return -ENODEV; @@ -62,19 +71,33 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) if (!vi->busy) { vi->busy = true; reinit_completion(&vi->have_data); - register_buffer(vi, buf, size); + register_buffer(vi); } if (!wait) return 0; - ret = wait_for_completion_killable(&vi->have_data); - if (ret < 0) - return ret; + read = 0; + while (size != 0) { + ret = wait_for_completion_killable(&vi->have_data); + if (ret < 0) + return ret; + + chunk = min_t(unsigned int, size, vi->data_avail); + memcpy(buf + read, vi->data, chunk); + read += chunk; + size -= chunk; + vi->data_avail = 0; + + if (size != 0) { + reinit_completion(&vi->have_data); + register_buffer(vi); + } + } vi->busy = false; - return vi->data_avail; + return read; } static void virtio_cleanup(struct hwrng *rng) From 16c2b1d94f1b6e409d2f33612afc37b4b03b07d3 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Sun, 27 Nov 2022 10:30:33 -0800 Subject: [PATCH 2243/4345] ANDROID: page_pinner: prevent pp_buffer access before initialization If page_pinner is configured with page_pinner_enabled=false and failure_tracking=true, pp_buffer will be accessed without being initialized. Prevent this by adding page_pinner_inited checks in functions that access it. Fixes: 898cfbf094a2 ("ANDROID: mm: introduce page_pinner") Bug: 259024332 Bug: 260179017 Change-Id: I8f612cae3e74d36e8a4eee5edec25281246cbe5e Signed-off-by: Suren Baghdasaryan (cherry picked from commit 23fb3111f63e5fe239a769668275c20493a5849c) --- include/linux/page_pinner.h | 6 ++++++ mm/page_pinner.c | 1 + 2 files changed, 7 insertions(+) diff --git a/include/linux/page_pinner.h b/include/linux/page_pinner.h index ba14d7636dc0..6dd0f9d3b394 100644 --- a/include/linux/page_pinner.h +++ b/include/linux/page_pinner.h @@ -41,6 +41,9 @@ static inline void dump_page_pinner(struct page *page) static inline void page_pinner_put_page(struct page *page) { + if (!static_branch_unlikely(&page_pinner_inited)) + return; + if (!static_branch_unlikely(&failure_tracking)) return; @@ -49,6 +52,9 @@ static inline void page_pinner_put_page(struct page *page) static inline void page_pinner_failure_detect(struct page *page) { + if (!static_branch_unlikely(&page_pinner_inited)) + return; + if (!static_branch_unlikely(&failure_tracking)) return; diff --git a/mm/page_pinner.c b/mm/page_pinner.c index a444584103ad..74543cefce4f 100644 --- a/mm/page_pinner.c +++ b/mm/page_pinner.c @@ -57,6 +57,7 @@ static struct longterm_pinner acf_pinner = { static bool page_pinner_enabled; DEFINE_STATIC_KEY_FALSE(page_pinner_inited); +EXPORT_SYMBOL(page_pinner_inited); DEFINE_STATIC_KEY_TRUE(failure_tracking); EXPORT_SYMBOL(failure_tracking); From 976d98e9aa2111f2614159559b2dfa5ff070a96e Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 23 Mar 2023 13:36:33 -0700 Subject: [PATCH 2244/4345] ANDROID: ABI: Add page_pinner_inited into symbols list Leaf changes summary: 1 artifact changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 0 Added function Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 1 Added variable 1 Added variable: [A] 'static_key_false page_pinner_inited' Bug: 273138535 Change-Id: I0de904601a8b99029b6deb06833fd1570860031d Signed-off-by: Suren Baghdasaryan --- android/abi_gki_aarch64.xml | 4562 ++++++++++++++++--------------- android/abi_gki_aarch64_generic | 1 + 2 files changed, 2283 insertions(+), 2280 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 58b441616537..291958b75232 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -6891,6 +6891,7 @@ + @@ -7353,7 +7354,7 @@ - + @@ -8232,7 +8233,7 @@ - + @@ -10634,9 +10635,9 @@ - + - + @@ -12132,18 +12133,18 @@ - + - + - + - + - + @@ -13658,12 +13659,12 @@ - + - + - + @@ -17260,69 +17261,69 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -18554,36 +18555,36 @@ - + - + - + - + - + - + - + - + - + - + - + @@ -21610,7 +21611,7 @@ - + @@ -22013,12 +22014,12 @@ - + - + - + @@ -22341,7 +22342,7 @@ - + @@ -22965,7 +22966,7 @@ - + @@ -24710,42 +24711,42 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -25185,7 +25186,7 @@ - + @@ -25329,66 +25330,66 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -26718,12 +26719,12 @@ - + - + - + @@ -27315,12 +27316,12 @@ - + - + - + @@ -31943,7 +31944,7 @@ - + @@ -34594,60 +34595,60 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -38612,18 +38613,18 @@ - + - + - + - + - + @@ -39929,12 +39930,12 @@ - + - + - + @@ -40637,7 +40638,7 @@ - + @@ -41212,21 +41213,21 @@ - + - + - + - + - + - + @@ -43818,7 +43819,7 @@ - + @@ -44593,81 +44594,81 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -45224,15 +45225,15 @@ - + - + - + - + @@ -46717,21 +46718,21 @@ - + - + - + - + - + - + @@ -48956,27 +48957,27 @@ - + - + - + - + - + - + - + - + @@ -51709,18 +51710,18 @@ - + - + - + - + - + @@ -51801,24 +51802,24 @@ - + - + - + - + - + - + - + @@ -51843,12 +51844,12 @@ - + - + - + @@ -53853,45 +53854,45 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -55795,24 +55796,24 @@ - + - + - + - + - + - + - + @@ -57264,114 +57265,114 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -58421,390 +58422,390 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -61211,12 +61212,12 @@ - + - + - + @@ -61443,96 +61444,96 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -63702,12 +63703,12 @@ - + - + - + @@ -66442,12 +66443,12 @@ - + - + - + @@ -68418,7 +68419,7 @@ - + @@ -70489,7 +70490,7 @@ - + @@ -70609,12 +70610,12 @@ - + - + - + @@ -75019,12 +75020,12 @@ - + - + - + @@ -76387,18 +76388,18 @@ - + - + - + - + - + @@ -77116,15 +77117,15 @@ - + - + - + - + @@ -77727,9 +77728,9 @@ - + - + @@ -78535,234 +78536,234 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -80248,108 +80249,108 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -80396,12 +80397,12 @@ - + - + - + @@ -81001,21 +81002,21 @@ - + - + - + - + - + - + @@ -81528,12 +81529,12 @@ - + - + - + @@ -83642,12 +83643,12 @@ - + - + - + @@ -84221,12 +84222,12 @@ - + - + - + @@ -84611,213 +84612,213 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -87490,24 +87491,24 @@ - + - + - + - + - + - + - + @@ -91976,7 +91977,7 @@ - + @@ -92534,12 +92535,12 @@ - + - + - + @@ -95046,12 +95047,12 @@ - + - + - + @@ -96721,12 +96722,12 @@ - + - + - + @@ -98905,15 +98906,15 @@ - + - + - + - + @@ -100289,78 +100290,78 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -101360,18 +101361,18 @@ - + - + - + - + - + @@ -105709,33 +105710,33 @@ - + - + - + - + - + - + - + - + - + - + @@ -107308,12 +107309,12 @@ - + - + - + @@ -114246,15 +114247,15 @@ - + - + - + - + @@ -114587,18 +114588,18 @@ - + - + - + - + - + @@ -115426,15 +115427,15 @@ - + - + - + - + @@ -116484,10 +116485,10 @@ - - - - + + + + @@ -116605,10 +116606,10 @@ - - - - + + + + @@ -116786,11 +116787,11 @@ - - - - - + + + + + @@ -117187,13 +117188,13 @@ - - - - - - - + + + + + + + @@ -117326,22 +117327,22 @@ - - - - + + + + - - - + + + - - - - - + + + + + @@ -117459,11 +117460,11 @@ - - - - - + + + + + @@ -117472,35 +117473,35 @@ - - - - - - - - + + + + + + + + - - - - - - - + + + + + + + - - - - - - - + + + + + + + - + @@ -117510,25 +117511,25 @@ - - + + - - + + - - - + + + - - + + @@ -117592,34 +117593,34 @@ - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + @@ -117642,8 +117643,8 @@ - - + + @@ -117723,12 +117724,12 @@ - - - - - - + + + + + + @@ -117776,12 +117777,12 @@ - - - - - - + + + + + + @@ -117860,12 +117861,12 @@ - - + + - - + + @@ -117936,7 +117937,7 @@ - + @@ -121385,8 +121386,8 @@ - - + + @@ -121445,22 +121446,22 @@ - - - - + + + + - - - - + + + + - - - - + + + + @@ -121695,16 +121696,16 @@ - - - - - + + + + + - - - + + + @@ -121745,9 +121746,9 @@ - - - + + + @@ -121809,8 +121810,8 @@ - - + + @@ -121871,17 +121872,17 @@ - - - + + + - - - - - - + + + + + + @@ -121909,9 +121910,9 @@ - - - + + + @@ -122016,8 +122017,8 @@ - - + + @@ -122190,13 +122191,13 @@ - - + + - - - + + + @@ -122204,9 +122205,9 @@ - - - + + + @@ -122353,10 +122354,10 @@ - - - - + + + + @@ -122378,8 +122379,8 @@ - - + + @@ -122396,9 +122397,9 @@ - - - + + + @@ -122797,8 +122798,8 @@ - - + + @@ -122818,10 +122819,10 @@ - - - - + + + + @@ -122834,17 +122835,17 @@ - - - + + + - - + + - - + + @@ -122932,10 +122933,10 @@ - - - - + + + + @@ -122953,12 +122954,87 @@ - - - + + + - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -122966,13 +123042,9 @@ - - - - - + @@ -122981,13 +123053,9 @@ - - - - - + @@ -122997,90 +123065,23 @@ - - - - - - - - + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + @@ -123205,9 +123206,9 @@ - - - + + + @@ -123494,26 +123495,26 @@ - - + + - - - - - + + + + + - - - - - + + + + + - - + + @@ -123522,8 +123523,8 @@ - - + + @@ -123954,9 +123955,9 @@ - - - + + + @@ -124015,8 +124016,8 @@ - - + + @@ -124043,12 +124044,12 @@ - - + + - - + + @@ -124089,10 +124090,10 @@ - - - - + + + + @@ -125044,39 +125045,39 @@ - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + @@ -125109,18 +125110,18 @@ - - - - - + + + + + - - - - - + + + + + @@ -125129,60 +125130,60 @@ - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + @@ -125198,12 +125199,12 @@ - - - - - - + + + + + + @@ -125228,11 +125229,11 @@ - - - - - + + + + + @@ -126050,8 +126051,8 @@ - - + + @@ -126165,31 +126166,31 @@ - - - - + + + + - - - + + + - - - - + + + + - - - + + + - - - + + + @@ -126204,9 +126205,9 @@ - - - + + + @@ -126331,10 +126332,10 @@ - - - - + + + + @@ -126722,10 +126723,10 @@ - - - - + + + + @@ -126860,17 +126861,17 @@ - - - + + + - - - - - - + + + + + + @@ -126997,14 +126998,14 @@ - - + + - - - - + + + + @@ -127013,10 +127014,10 @@ - - - - + + + + @@ -127077,17 +127078,17 @@ - - + + - - + + - - - + + + @@ -127314,13 +127315,13 @@ - - - + + + - - + + @@ -127427,13 +127428,13 @@ - - + + - - - + + + @@ -127478,8 +127479,8 @@ - - + + @@ -127520,9 +127521,9 @@ - - - + + + @@ -127567,18 +127568,18 @@ - - - - + + + + - - + + - - + + @@ -127608,8 +127609,8 @@ - - + + @@ -127750,16 +127751,16 @@ - - - - + + + + - - - - + + + + @@ -127767,9 +127768,9 @@ - - - + + + @@ -127780,11 +127781,11 @@ - - - - - + + + + + @@ -127796,39 +127797,39 @@ - - - - - + + + + + - - - - - + + + + + - - - + + + - - - - + + + + - - - - + + + + @@ -127845,8 +127846,8 @@ - - + + @@ -128382,8 +128383,8 @@ - - + + @@ -128395,10 +128396,10 @@ - - - - + + + + @@ -128425,48 +128426,48 @@ - - - + + + - - + + - - + + - - + + - - - + + + - - - + + + - - + + - - + + - - - + + + @@ -128660,10 +128661,10 @@ - - - - + + + + @@ -129023,14 +129024,14 @@ - - + + - - - - + + + + @@ -129377,8 +129378,8 @@ - - + + @@ -129390,9 +129391,9 @@ - - - + + + @@ -129601,27 +129602,27 @@ - - + + - - + + - - + + - - - + + + - - - - + + + + @@ -129661,9 +129662,9 @@ - - - + + + @@ -130321,10 +130322,10 @@ - - - - + + + + @@ -130430,47 +130431,47 @@ - - + + - - - - - - - - - - + + + + + + + + + + - + - - + + - - + + - - - - - - + + + + + + - - - - - - + + + + + + @@ -130573,9 +130574,9 @@ - - - + + + @@ -130804,7 +130805,7 @@ - + @@ -131111,32 +131112,32 @@ - - - + + + - - - + + + - - - + + + - - - + + + @@ -131439,8 +131440,8 @@ - - + + @@ -131478,12 +131479,12 @@ - - - - - - + + + + + + @@ -131550,8 +131551,8 @@ - - + + @@ -131684,20 +131685,20 @@ - - - - - - + + + + + + - - - - - - + + + + + + @@ -131747,8 +131748,8 @@ - - + + @@ -131776,8 +131777,8 @@ - - + + @@ -131933,12 +131934,12 @@ - - + + - - + + @@ -132000,7 +132001,7 @@ - + @@ -132172,188 +132173,188 @@ - - - - - + + + + + - - - - - - + + + + + + - - - + + + - - - - + + + + - - - + + + - - - + + + - - + + - - - - - - - - - + + + + + + + + + - - - + + + - - - + + + - - - - + + + + - - + + - - - - + + + + - - - + + + - - + + - - - + + + - - + + - - - + + + - - - + + + - - + + - - - - + + + + - - + + - - + + - - + + - - + + - - + + - - + + - - - - - + + + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + - - + + @@ -132457,37 +132458,37 @@ - + - - - - - - + + + + + + - - + + - - - + + + - - - + + + - - + + - - + + @@ -133411,13 +133412,13 @@ - - - - - - - + + + + + + + @@ -133466,9 +133467,9 @@ - - - + + + @@ -133742,11 +133743,11 @@ - + - - + + @@ -133990,28 +133991,28 @@ - - - + + + - - + + - - - - - - + + + + + + - - - - - + + + + + @@ -134019,24 +134020,24 @@ - - - - - - + + + + + + - - - - - - + + + + + + - - + + @@ -134344,10 +134345,10 @@ - - - - + + + + @@ -134409,10 +134410,10 @@ - - - - + + + + @@ -134421,8 +134422,8 @@ - - + + @@ -134923,13 +134924,13 @@ - - - + + + - - + + @@ -135238,9 +135239,9 @@ - - - + + + @@ -135389,13 +135390,13 @@ - - - + + + - - + + @@ -135592,12 +135593,12 @@ - - + + - - + + @@ -135605,26 +135606,26 @@ - - - + + + - - - - + + + + - - + + - - - - - + + + + + @@ -135733,7 +135734,7 @@ - + @@ -136491,12 +136492,12 @@ - - - - - - + + + + + + @@ -136807,48 +136808,48 @@ - - - - - + + + + + - - - - - - + + + + + + - - - + + + - - - + + + - - + + - - + + - - - - - + + + + + - - + + @@ -136892,62 +136893,62 @@ - - - - + + + + - - - - + + + + - - - - + + + + - - - - - + + + + + - - - - - - + + + + + + - - - - + + + + - - - - + + + + - - - - - + + + + + - - - - + + + + @@ -137246,8 +137247,8 @@ - - + + @@ -137947,14 +137948,14 @@ - - - - + + + + - - + + @@ -137975,6 +137976,7 @@ + @@ -138067,13 +138069,13 @@ - - + + - - + + @@ -138153,16 +138155,16 @@ - - - - + + + + - - - - + + + + @@ -138359,10 +138361,10 @@ - - - - + + + + @@ -138811,12 +138813,12 @@ - - - - - - + + + + + + @@ -138860,20 +138862,20 @@ - - - - + + + + - - - - + + + + - - + + @@ -139373,10 +139375,10 @@ - - - - + + + + @@ -139791,50 +139793,50 @@ - - + + - - + + - - + + - - + + - - + + - - + + - - - + + + - - + + - - + + - - - + + + @@ -139898,10 +139900,10 @@ - - - - + + + + @@ -139925,68 +139927,68 @@ - - + + - - - - + + + + - - - - + + + + - - - + + + - - + + - - - - + + + + - - - - + + + + - - - - + + + + - - - - + + + + - - + + - - + + @@ -139997,10 +139999,10 @@ - + - + @@ -140154,13 +140156,13 @@ - - - + + + - - + + @@ -140487,7 +140489,7 @@ - + @@ -140504,7 +140506,7 @@ - + @@ -140556,24 +140558,24 @@ - - + + - - + + - - + + - - + + - - + + @@ -140749,12 +140751,12 @@ - - + + - - + + @@ -140781,13 +140783,13 @@ - - - + + + - - + + @@ -140952,29 +140954,29 @@ - - - + + + - - - + + + - - - + + + - - - - + + + + - - + + @@ -140982,34 +140984,34 @@ - - + + - - - + + + - - + + - - + + - - - + + + @@ -141017,60 +141019,60 @@ - - + + - - + + - - + + - - + + - - - + + + - - + + - - + + - - + + - - - - + + + + - - - + + + @@ -141112,24 +141114,24 @@ - - - - + + + + - - + + - - - + + + - - - + + + @@ -141142,10 +141144,10 @@ - - - - + + + + @@ -141154,24 +141156,24 @@ - - - + + + - - - + + + - - - - + + + + @@ -141179,34 +141181,34 @@ - - - - + + + + - - - - + + + + - - - + + + - - + + - - + + - - - + + + @@ -141218,8 +141220,8 @@ - - + + @@ -141268,12 +141270,12 @@ - - - - - - + + + + + + @@ -141306,13 +141308,13 @@ - - - - - - - + + + + + + + @@ -141503,7 +141505,7 @@ - + @@ -141583,8 +141585,8 @@ - - + + @@ -141592,21 +141594,21 @@ - - - + + + - - - - - - + + + + + + - - + + @@ -141648,8 +141650,8 @@ - - + + @@ -141677,16 +141679,16 @@ - - + + - - + + - - + + @@ -141707,27 +141709,27 @@ - - + + - - - + + + - - - + + + - - - + + + - - + + @@ -141736,8 +141738,8 @@ - - + + @@ -141970,81 +141972,81 @@ - - + + - - + + - - - + + + - - - + + + - - - + + + - - - - + + + + - - - - + + + + - - + + - - + + - - + + - - - - + + + + - - + + - - + + - - + + - - + + - - + + - + @@ -142115,8 +142117,8 @@ - - + + @@ -142158,10 +142160,10 @@ - - - - + + + + @@ -142225,13 +142227,13 @@ - - - + + + - - + + @@ -142885,9 +142887,9 @@ - - - + + + @@ -143105,15 +143107,15 @@ - + - - + + - - + + @@ -143142,11 +143144,11 @@ - - - - - + + + + + @@ -143169,7 +143171,7 @@ - + @@ -143187,7 +143189,7 @@ - + @@ -143219,16 +143221,16 @@ - - - - - - + + + + + + - - + + @@ -143240,18 +143242,18 @@ - - - - - + + + + + - - - - - + + + + + @@ -143263,8 +143265,8 @@ - - + + @@ -143274,9 +143276,9 @@ - - - + + + @@ -143284,11 +143286,11 @@ - - - - - + + + + + @@ -143317,12 +143319,12 @@ - - + + - - + + @@ -143331,9 +143333,9 @@ - - - + + + @@ -143341,16 +143343,16 @@ - - - - + + + + - - - - + + + + @@ -143358,9 +143360,9 @@ - - - + + + @@ -143373,18 +143375,18 @@ - - - + + + - - + + - - - + + + @@ -143399,23 +143401,23 @@ - - - + + + - - - - - + + + + + - - - - - + + + + + @@ -143423,14 +143425,14 @@ - - - + + + - - - + + + @@ -143894,15 +143896,15 @@ - - - - + + + + - - - + + + @@ -143949,11 +143951,11 @@ - - - - - + + + + + @@ -143965,8 +143967,8 @@ - - + + @@ -143988,13 +143990,13 @@ - - - + + + - - + + @@ -144633,7 +144635,7 @@ - + @@ -144652,20 +144654,20 @@ - - - - - - - + + + + + + + - - - - - + + + + + @@ -144676,60 +144678,60 @@ - - + + - - - - - + + + + + - - + + - - - + + + - - - - - + + + + + - - - + + + - - - - + + + + - - - - - - + + + + + + - - - + + + - - - + + + @@ -144763,8 +144765,8 @@ - - + + @@ -145246,12 +145248,12 @@ - - + + - - + + @@ -145276,9 +145278,9 @@ - - - + + + @@ -145287,8 +145289,8 @@ - - + + @@ -145327,7 +145329,7 @@ - + @@ -145380,7 +145382,7 @@ - + @@ -145532,7 +145534,7 @@ - + @@ -145649,8 +145651,8 @@ - - + + @@ -145890,8 +145892,8 @@ - - + + @@ -146610,14 +146612,14 @@ - - - + + + - - - + + + @@ -146640,26 +146642,26 @@ - - + + - - - + + + - - - + + + - - - - - - + + + + + + @@ -146670,18 +146672,18 @@ - - + + - - - + + + - - - + + + @@ -146698,13 +146700,13 @@ - - - + + + - - + + @@ -147094,12 +147096,12 @@ - - + + - - + + @@ -147130,8 +147132,8 @@ - - + + @@ -147400,8 +147402,8 @@ - - + + @@ -147697,13 +147699,13 @@ - - + + - - - + + + @@ -147810,8 +147812,8 @@ - - + + @@ -147842,33 +147844,33 @@ - - + + - - + + - - + + - - + + - - + + - - - + + + @@ -147876,21 +147878,21 @@ - - + + - - + + - - - + + + @@ -147951,13 +147953,13 @@ - - + + - - - + + + @@ -149545,7 +149547,7 @@ - + @@ -149851,13 +149853,13 @@ - + - - - - + + + + @@ -149921,15 +149923,15 @@ - - - - + + + + - - - + + + @@ -149953,19 +149955,19 @@ - - - + + + - - - - + + + + @@ -149978,13 +149980,13 @@ - - - + + + - - + + @@ -149998,13 +150000,13 @@ - - + + - - - + + + @@ -150019,22 +150021,22 @@ - - - - - - + + + + + + - - - + + + - - - + + + @@ -150064,9 +150066,9 @@ - - - + + + @@ -150074,13 +150076,13 @@ - - - + + + - - + + diff --git a/android/abi_gki_aarch64_generic b/android/abi_gki_aarch64_generic index cc8edfd0d35e..cd7ca5f41b8b 100644 --- a/android/abi_gki_aarch64_generic +++ b/android/abi_gki_aarch64_generic @@ -1294,6 +1294,7 @@ of_usb_host_tpl_support page_endio page_mapping + page_pinner_inited __page_pinner_migration_failed panic panic_notifier_list From 9b0fcb1986c55b90c8676bb175e3200d3c6b9806 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 22 Mar 2023 10:38:59 +0000 Subject: [PATCH 2245/4345] ANDROID: preserve CRC for __irq_domain_add() The __irq_domain_add() function changed in commit bb7597777c13 ("irqdomain: Change the type of 'size' in __irq_domain_add() to be consistent") in order to make later commits in the series able to be applied easier. The commit does not actually change any functionality, but the CRC is now changed, so trick the CRC tools to think all is still the same. function symbol changed from 'struct irq_domain * __irq_domain_add(struct fwnode_handle *, int, irq_hw_number_t, int, const struct irq_domain_ops *, void *)' to 'struct irq_domain * __irq_domain_add(struct fwnode_handle *, unsigned int, irq_hw_number_t, int, const struct irq_domain_ops *, void *)' type changed from 'struct irq_domain *(struct fwnode_handle *, int, irq_hw_number_t, int, const struct irq_domain_ops *, void *)' to 'struct irq_domain *(struct fwnode_handle *, unsigned int, irq_hw_number_t, int, const struct irq_domain_ops *, void *)' parameter 2 ('size') type changed from 'int' to 'unsigned int' encoding changed from signed integer to unsigned integer Bug: 161946584 Fixes: bb7597777c13 ("irqdomain: Change the type of 'size' in __irq_domain_add() to be consistent") Change-Id: I3065753600072c4ab4def2c3b1d6420e1946bdeb Signed-off-by: Greg Kroah-Hartman --- android/abi_gki_aarch64.xml | 2104 +++++++++++++++++------------------ include/linux/irqdomain.h | 4 + 2 files changed, 1056 insertions(+), 1052 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 291958b75232..5acd11e5aec7 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -7478,15 +7478,15 @@ - + - + - + - + @@ -22344,9 +22344,9 @@ - + - + @@ -25186,7 +25186,7 @@ - + @@ -35379,21 +35379,21 @@ - + - + - + - + - + - + @@ -38599,18 +38599,18 @@ - + - + - + - + - + @@ -43819,7 +43819,7 @@ - + @@ -48886,7 +48886,7 @@ - + @@ -67722,39 +67722,39 @@ - + - + - + - + - + - + - + - + - + - + - + - + @@ -70490,7 +70490,7 @@ - + @@ -77728,9 +77728,9 @@ - + - + @@ -82189,30 +82189,30 @@ - + - + - + - + - + - + - + - + - + @@ -109974,7 +109974,7 @@ - + @@ -112428,120 +112428,120 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -115875,15 +115875,15 @@ - + - + - + - + @@ -116291,9 +116291,9 @@ - - - + + + @@ -116411,9 +116411,9 @@ - - - + + + @@ -116504,17 +116504,17 @@ - - - + + + - - + + - - + + @@ -116577,18 +116577,18 @@ - - + + - - - + + + - - - + + + @@ -116597,9 +116597,9 @@ - - - + + + @@ -116664,9 +116664,9 @@ - - - + + + @@ -116757,19 +116757,19 @@ - - - - - + + + + + - - - - - - + + + + + + @@ -116850,9 +116850,9 @@ - - - + + + @@ -116937,8 +116937,8 @@ - - + + @@ -117044,16 +117044,16 @@ - - - - + + + + - - - - + + + + @@ -117208,13 +117208,13 @@ - - - - - - - + + + + + + + @@ -117267,8 +117267,8 @@ - - + + @@ -117426,21 +117426,21 @@ - - + + - - + + - - - + + + @@ -117449,8 +117449,8 @@ - - + + @@ -117631,16 +117631,16 @@ - - - - - + + + + + - - - + + + @@ -117861,12 +117861,12 @@ - - + + - - + + @@ -117885,16 +117885,16 @@ - - - - + + + + - - - - + + + + @@ -121230,10 +121230,10 @@ - - - - + + + + @@ -121857,13 +121857,13 @@ - - - - - - - + + + + + + + @@ -121877,12 +121877,12 @@ - - - - - - + + + + + + @@ -122437,16 +122437,16 @@ - - + + - - + + - - + + @@ -122454,22 +122454,22 @@ - - - + + + - - - + + + - - + + - - + + @@ -122485,15 +122485,15 @@ - - + + - - - - - + + + + + @@ -122506,44 +122506,44 @@ - - + + - - - + + + - - + + - - - + + + - - - + + + - - + + - - + + - - - + + + @@ -122553,22 +122553,22 @@ - - + + - - - + + + - - + + - - - + + + @@ -122593,9 +122593,9 @@ - - - + + + @@ -122608,10 +122608,10 @@ - - - - + + + + @@ -122953,7 +122953,7 @@ - + @@ -123211,14 +123211,14 @@ - - - + + + - - - + + + @@ -123484,9 +123484,9 @@ - - - + + + @@ -123594,14 +123594,14 @@ - - + + - - + + @@ -123613,59 +123613,59 @@ - - + + - - + + - - + + - - - + + + - - + + - - + + - - + + - - + + - - - + + + - - + + - - + + - - + + - - - + + + @@ -123691,24 +123691,24 @@ - - - + + + - - - + + + - - - - + + + + - - + + @@ -123727,9 +123727,9 @@ - - - + + + @@ -123740,27 +123740,27 @@ - - - + + + - - - + + + - - + + - - - + + + @@ -123838,42 +123838,42 @@ - - - + + + - - - - + + + + - - - + + + - - - + + + - - - + + + - - + + - - + + - - + + @@ -124073,8 +124073,8 @@ - - + + @@ -125292,16 +125292,16 @@ - - - - + + + + - - - - + + + + @@ -125336,9 +125336,9 @@ - - - + + + @@ -125370,9 +125370,9 @@ - - - + + + @@ -125716,19 +125716,19 @@ - - + + - - - - + + + + - - - + + + @@ -126193,9 +126193,9 @@ - - - + + + @@ -126210,9 +126210,9 @@ - - - + + + @@ -126551,15 +126551,15 @@ - - - - + + + + - - - + + + @@ -126589,25 +126589,25 @@ - - - + + + - - - + + + - - - + + + - - - - + + + + @@ -127605,8 +127605,8 @@ - - + + @@ -127886,14 +127886,14 @@ - - - + + + - - - + + + @@ -127906,8 +127906,8 @@ - - + + @@ -127920,9 +127920,9 @@ - - - + + + @@ -128207,8 +128207,8 @@ - - + + @@ -128683,18 +128683,18 @@ - - - - - - + + + + + + - - - - + + + + @@ -128713,10 +128713,10 @@ - - - - + + + + @@ -128724,8 +128724,8 @@ - - + + @@ -128769,9 +128769,9 @@ - - - + + + @@ -128805,66 +128805,66 @@ - - - - - + + + + + - - - + + + - - - - - + + + + + - - - + + + - - - - + + + + - - - - + + + + - - - + + + - - + + - - - - - - - + + + + + + + @@ -129024,14 +129024,14 @@ - - + + - - - - + + + + @@ -129391,9 +129391,9 @@ - - - + + + @@ -129417,22 +129417,22 @@ - - - + + + - - - - + + + + - - - - - + + + + + @@ -129440,10 +129440,10 @@ - - - - + + + + @@ -129566,8 +129566,8 @@ - - + + @@ -130171,9 +130171,9 @@ - - - + + + @@ -130555,16 +130555,16 @@ - - + + - - - - - - + + + + + + @@ -130823,8 +130823,8 @@ - - + + @@ -131117,8 +131117,8 @@ - - + + @@ -132567,41 +132567,41 @@ - - + + - + - - + + - - + + - - + + - - - + + + - - + + - - - - - - + + + + + + @@ -132614,16 +132614,16 @@ - - - - - - + + + + + + - - + + @@ -133480,8 +133480,8 @@ - - + + @@ -134173,22 +134173,22 @@ - - + + - - - - + + + + - - + + - - + + @@ -134197,125 +134197,125 @@ - - - - - - - + + + + + + + - - - - - - + + + + + + - - - - - + + + + + - - - - - - - + + + + + + + - - - + + + - - - - + + + + - - - - + + + + - - - + + + - - + + - - - - - - + + + + + + - - - - - - - - - + + + + + + + + + - - - - + + + + - - - - - - - + + + + + + + - - - - - - - + + + + + + + - - - - - - - + + + + + + + - - - + + + - - - + + + @@ -134477,11 +134477,11 @@ - - - - - + + + + + @@ -134706,12 +134706,12 @@ - - + + - - + + @@ -134742,9 +134742,9 @@ - - - + + + @@ -135260,14 +135260,14 @@ - - - - + + + + - - + + @@ -135390,9 +135390,9 @@ - - - + + + @@ -135730,11 +135730,11 @@ - - + + - + @@ -135762,7 +135762,7 @@ - + @@ -136055,13 +136055,13 @@ - - - + + + - - + + @@ -136570,55 +136570,55 @@ - - - + + + - - - + + + - - + + - - - + + + - - - + + + - - + + - - + + - - - - + + + + - - - + + + - - - - - + + + + + @@ -136626,9 +136626,9 @@ - - - + + + @@ -136636,44 +136636,44 @@ - - + + - - - - - - - - - - - - - + - - - + + + + + + + + + + - - - - - - + + + + + + + + + + + - - - + + + @@ -136681,10 +136681,10 @@ - - - - + + + + @@ -136692,43 +136692,43 @@ - - - - + + + + - - + + - - - + + + - - + + - - - - + + + + - - - + + + - - - + + + @@ -136740,39 +136740,39 @@ - - + + - - + + - - - - - + + + + + - - + + - - + + - - + + - - + + - - + + @@ -136795,13 +136795,13 @@ - - - + + + - - + + @@ -137021,61 +137021,61 @@ - - - + + + - - + + - - - + + + - - - - + + + + - - - - + + + + - - - + + + - - + + - - - - - + + + + + - - - - - + + + + + - - + + @@ -137093,59 +137093,59 @@ - - - - + + + + - - - - + + + + - - + + - - - + + + - - - + + + - - + + - - + + - - - + + + - - - + + + - - - + + + - - - - + + + + @@ -137153,14 +137153,14 @@ - - - + + + - - - + + + @@ -137620,14 +137620,14 @@ - - - + + + - - - + + + @@ -138167,10 +138167,10 @@ - - - - + + + + @@ -138198,8 +138198,8 @@ - - + + @@ -138936,15 +138936,15 @@ - - - - + + + + - - - + + + @@ -139330,9 +139330,9 @@ - - - + + + @@ -140156,13 +140156,13 @@ - - - + + + - - + + @@ -140215,11 +140215,11 @@ - - - - - + + + + + @@ -140264,8 +140264,8 @@ - - + + @@ -140492,10 +140492,10 @@ - + - + @@ -140544,9 +140544,9 @@ - - - + + + @@ -140731,12 +140731,12 @@ - - + + - - + + @@ -141220,8 +141220,8 @@ - - + + @@ -141737,7 +141737,7 @@ - + @@ -142049,9 +142049,9 @@ - - - + + + @@ -142099,10 +142099,10 @@ - - - - + + + + @@ -142166,17 +142166,17 @@ - - - + + + - - + + - - + + @@ -142191,8 +142191,8 @@ - - + + @@ -143171,7 +143171,7 @@ - + @@ -143189,7 +143189,7 @@ - + @@ -143242,31 +143242,31 @@ - - - - - + + + + + - - - - - + + + + + - - + + - - - + + + - - + + @@ -143276,21 +143276,21 @@ - - - + + + - - - + + + - - - - - + + + + + @@ -143307,35 +143307,35 @@ - - - - - + + + + + - - - + + + - - + + - - + + - - - - + + + + - - - + + + @@ -143349,49 +143349,49 @@ - - - - + + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + - - + + - - - + + + - - - + + + @@ -143406,33 +143406,33 @@ - - - - - + + + + + - - - - - + + + + + - - - + + + - - - + + + - - - + + + @@ -144635,7 +144635,7 @@ - + @@ -144682,20 +144682,20 @@ - - - - - + + + + + - - - + + + @@ -145326,19 +145326,19 @@ - + - + - + - + @@ -146363,8 +146363,8 @@ - - + + @@ -146421,8 +146421,8 @@ - - + + @@ -146430,14 +146430,14 @@ - - - + + + - - - + + + @@ -146456,13 +146456,13 @@ - - - + + + - - + + @@ -147071,21 +147071,21 @@ - - + + - - + + - - - + + + @@ -147402,8 +147402,8 @@ - - + + @@ -147703,9 +147703,9 @@ - - - + + + @@ -147812,8 +147812,8 @@ - - + + @@ -147844,8 +147844,8 @@ - - + + @@ -147882,8 +147882,8 @@ - - + + @@ -147953,8 +147953,8 @@ - - + + @@ -149547,7 +149547,7 @@ - + diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 7e90612af3ac..1d62f241cd87 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -262,7 +262,11 @@ static inline struct fwnode_handle *irq_domain_alloc_fwnode(phys_addr_t *pa) } void irq_domain_free_fwnode(struct fwnode_handle *fwnode); +#ifdef __GENKSYMS__ /* Android KABI hack to preserve CRC checker */ +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, +#else struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, +#endif irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data); From f1b6325b25bd4fbd37b60ee67dd9814710446b9c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 23 Mar 2023 07:05:52 +0000 Subject: [PATCH 2246/4345] Revert "HID: uhid: Over-ride the default maximum data buffer value with our own" This reverts commit e57f797e3ffafb09eafb9be69d065d1e0331da61 which is commit 1c5d4221240a233df2440fe75c881465cdf8da07 upstream. It breaks the Android KABI and if needed, should come back in an abi-safe way. Bug: 161946584 Cc: Lee Jones Change-Id: I9a460d9dbc41512ee71ff607e875f2da9be7f9f6 Signed-off-by: Greg Kroah-Hartman --- drivers/hid/uhid.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c index ba0ca652b9da..fc06d8bb42e0 100644 --- a/drivers/hid/uhid.c +++ b/drivers/hid/uhid.c @@ -395,7 +395,6 @@ struct hid_ll_driver uhid_hid_driver = { .parse = uhid_hid_parse, .raw_request = uhid_hid_raw_request, .output_report = uhid_hid_output_report, - .max_buffer_size = UHID_DATA_MAX, }; EXPORT_SYMBOL_GPL(uhid_hid_driver); From 90eb02302b5e03f83d83287f5486e754b7c15826 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 23 Mar 2023 07:05:58 +0000 Subject: [PATCH 2247/4345] Revert "HID: core: Provide new max_buffer_size attribute to over-ride the default" This reverts commit 9bc878756b017f2e1d8dc4f261faa64f69c4c2ee which is commit b1a37ed00d7908a991c1d0f18a8cba3c2aa99bdc upstream. It breaks the Android KABI and if needed, should come back in an abi-safe way. Bug: 161946584 Cc: Lee Jones Change-Id: I1f160797720e8bdf4960542e711fd17940a975d9 Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-core.c | 18 +++++------------- include/linux/hid.h | 3 --- 2 files changed, 5 insertions(+), 16 deletions(-) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 524d6d712e72..5f9ec1d1464a 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -258,7 +258,6 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign { struct hid_report *report; struct hid_field *field; - unsigned int max_buffer_size = HID_MAX_BUFFER_SIZE; unsigned int usages; unsigned int offset; unsigned int i; @@ -289,11 +288,8 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign offset = report->size; report->size += parser->global.report_size * parser->global.report_count; - if (parser->device->ll_driver->max_buffer_size) - max_buffer_size = parser->device->ll_driver->max_buffer_size; - /* Total size check: Allow for possible report index byte */ - if (report->size > (max_buffer_size - 1) << 3) { + if (report->size > (HID_MAX_BUFFER_SIZE - 1) << 3) { hid_err(parser->device, "report is too long\n"); return -1; } @@ -1756,7 +1752,6 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, struct hid_report_enum *report_enum = hid->report_enum + type; struct hid_report *report; struct hid_driver *hdrv; - int max_buffer_size = HID_MAX_BUFFER_SIZE; unsigned int a; u32 rsize, csize = size; u8 *cdata = data; @@ -1773,13 +1768,10 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, rsize = hid_compute_report_size(report); - if (hid->ll_driver->max_buffer_size) - max_buffer_size = hid->ll_driver->max_buffer_size; - - if (report_enum->numbered && rsize >= max_buffer_size) - rsize = max_buffer_size - 1; - else if (rsize > max_buffer_size) - rsize = max_buffer_size; + if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) + rsize = HID_MAX_BUFFER_SIZE - 1; + else if (rsize > HID_MAX_BUFFER_SIZE) + rsize = HID_MAX_BUFFER_SIZE; if (csize < rsize) { dbg_hid("report %d is too short, (%d < %d)\n", report->id, diff --git a/include/linux/hid.h b/include/linux/hid.h index 256f34f49167..2ba33d708942 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -798,7 +798,6 @@ struct hid_driver { * @raw_request: send raw report request to device (e.g. feature report) * @output_report: send output report to device * @idle: send idle request to device - * @max_buffer_size: over-ride maximum data buffer size (default: HID_MAX_BUFFER_SIZE) */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); @@ -823,8 +822,6 @@ struct hid_ll_driver { int (*output_report) (struct hid_device *hdev, __u8 *buf, size_t len); int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); - - unsigned int max_buffer_size; }; extern struct hid_ll_driver i2c_hid_ll_driver; From d1d2d17fe95dbc0627be11cc8d29ae5cf549842f Mon Sep 17 00:00:00 2001 From: Jiantao Zhang Date: Mon, 21 Nov 2022 13:08:05 +0000 Subject: [PATCH 2248/4345] BACKPORT: USB: gadget: Fix use-after-free during usb config switch In the process of switching USB config from rndis to other config, if the hardware does not support the ->pullup callback, or the hardware encounters a low probability fault, both of them may cause the ->pullup callback to fail, which will then cause a system panic (use after free). The gadget drivers sometimes need to be unloaded regardless of the hardware's behavior. Analysis as follows: ======================================================================= (1) write /config/usb_gadget/g1/UDC "none" gether_disconnect+0x2c/0x1f8 rndis_disable+0x4c/0x74 composite_disconnect+0x74/0xb0 configfs_composite_disconnect+0x60/0x7c usb_gadget_disconnect+0x70/0x124 usb_gadget_unregister_driver+0xc8/0x1d8 gadget_dev_desc_UDC_store+0xec/0x1e4 (2) rm /config/usb_gadget/g1/configs/b.1/f1 rndis_deregister+0x28/0x54 rndis_free+0x44/0x7c usb_put_function+0x14/0x1c config_usb_cfg_unlink+0xc4/0xe0 configfs_unlink+0x124/0x1c8 vfs_unlink+0x114/0x1dc (3) rmdir /config/usb_gadget/g1/functions/rndis.gs4 panic+0x1fc/0x3d0 do_page_fault+0xa8/0x46c do_mem_abort+0x3c/0xac el1_sync_handler+0x40/0x78 0xffffff801138f880 rndis_close+0x28/0x34 eth_stop+0x74/0x110 dev_close_many+0x48/0x194 rollback_registered_many+0x118/0x814 unregister_netdev+0x20/0x30 gether_cleanup+0x1c/0x38 rndis_attr_release+0xc/0x14 kref_put+0x74/0xb8 configfs_rmdir+0x314/0x374 If gadget->ops->pullup() return an error, function rndis_close() will be called, then it will causes a use-after-free problem. ======================================================================= Fixes: 0a55187a1ec8 ("USB: gadget core: Issue ->disconnect() callback from usb_gadget_disconnect()") Signed-off-by: Jiantao Zhang Signed-off-by: TaoXue Link: https://lore.kernel.org/r/20221121130805.10735-1-water.zhangjiantao@huawei.com Signed-off-by: Greg Kroah-Hartman Bug: 273510696 Bug: 275027942 Change-Id: I702f324c5852d3b2448081b092fef464f8691989 (cherry picked from commit afdc12887f2b2ecf20d065a7d81ad29824155083) [ray: Resolved minor conflict in drivers/usb/gadget/udc/core.c] Signed-off-by: Ray Chi --- drivers/usb/gadget/udc/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index e1e243e52a2d..7a00af1f9624 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -730,10 +730,11 @@ int usb_gadget_disconnect(struct usb_gadget *gadget) } ret = gadget->ops->pullup(gadget, 0); - if (!ret) { + if (!ret) gadget->connected = 0; + + if (gadget->udc->driver) gadget->udc->driver->disconnect(gadget); - } out: trace_usb_gadget_disconnect(gadget, ret); From aaffce1ef448015e4f946a53384686839147cf9e Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 18:59:59 +0000 Subject: [PATCH 2249/4345] UPSTREAM: HID: bigben: use spinlock to protect concurrent accesses [ Upstream commit 9fefb6201c4f8dd9f58c581b2a66e5cde2895ea2 ] bigben driver has a worker that may access data concurrently. Proct the accesses using a spinlock. Bug: 268589017 Fixes: 256a90ed9e46 ("HID: hid-bigbenff: driver for BigBen Interactive PS3OFMINIPAD gamepad") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230125-hid-unregister-leds-v4-1-7860c5763c38@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin Signed-off-by: Lee Jones Change-Id: I8b7a34cba4c79c26f3d1912c97a83820d88bd5a4 --- drivers/hid/hid-bigbenff.c | 52 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 50 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index e8b16665860d..ed3d2d7bc1dd 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -174,6 +174,7 @@ static __u8 pid0902_rdesc_fixed[] = { struct bigben_device { struct hid_device *hid; struct hid_report *report; + spinlock_t lock; bool removed; u8 led_state; /* LED1 = 1 .. LED4 = 8 */ u8 right_motor_on; /* right motor off/on 0/1 */ @@ -190,12 +191,27 @@ static void bigben_worker(struct work_struct *work) struct bigben_device *bigben = container_of(work, struct bigben_device, worker); struct hid_field *report_field = bigben->report->field[0]; + bool do_work_led = false; + bool do_work_ff = false; + u8 *buf; + u32 len; + unsigned long flags; if (bigben->removed || !report_field) return; + buf = hid_alloc_report_buf(bigben->report, GFP_KERNEL); + if (!buf) + return; + + len = hid_report_len(bigben->report); + + /* LED work */ + spin_lock_irqsave(&bigben->lock, flags); + if (bigben->work_led) { bigben->work_led = false; + do_work_led = true; report_field->value[0] = 0x01; /* 1 = led message */ report_field->value[1] = 0x08; /* reserved value, always 8 */ report_field->value[2] = bigben->led_state; @@ -204,11 +220,22 @@ static void bigben_worker(struct work_struct *work) report_field->value[5] = 0x00; /* padding */ report_field->value[6] = 0x00; /* padding */ report_field->value[7] = 0x00; /* padding */ - hid_hw_request(bigben->hid, bigben->report, HID_REQ_SET_REPORT); + hid_output_report(bigben->report, buf); } + spin_unlock_irqrestore(&bigben->lock, flags); + + if (do_work_led) { + hid_hw_raw_request(bigben->hid, bigben->report->id, buf, len, + bigben->report->type, HID_REQ_SET_REPORT); + } + + /* FF work */ + spin_lock_irqsave(&bigben->lock, flags); + if (bigben->work_ff) { bigben->work_ff = false; + do_work_ff = true; report_field->value[0] = 0x02; /* 2 = rumble effect message */ report_field->value[1] = 0x08; /* reserved value, always 8 */ report_field->value[2] = bigben->right_motor_on; @@ -217,8 +244,17 @@ static void bigben_worker(struct work_struct *work) report_field->value[5] = 0x00; /* padding */ report_field->value[6] = 0x00; /* padding */ report_field->value[7] = 0x00; /* padding */ - hid_hw_request(bigben->hid, bigben->report, HID_REQ_SET_REPORT); + hid_output_report(bigben->report, buf); } + + spin_unlock_irqrestore(&bigben->lock, flags); + + if (do_work_ff) { + hid_hw_raw_request(bigben->hid, bigben->report->id, buf, len, + bigben->report->type, HID_REQ_SET_REPORT); + } + + kfree(buf); } static int hid_bigben_play_effect(struct input_dev *dev, void *data, @@ -228,6 +264,7 @@ static int hid_bigben_play_effect(struct input_dev *dev, void *data, struct bigben_device *bigben = hid_get_drvdata(hid); u8 right_motor_on; u8 left_motor_force; + unsigned long flags; if (!bigben) { hid_err(hid, "no device data\n"); @@ -242,9 +279,12 @@ static int hid_bigben_play_effect(struct input_dev *dev, void *data, if (right_motor_on != bigben->right_motor_on || left_motor_force != bigben->left_motor_force) { + spin_lock_irqsave(&bigben->lock, flags); bigben->right_motor_on = right_motor_on; bigben->left_motor_force = left_motor_force; bigben->work_ff = true; + spin_unlock_irqrestore(&bigben->lock, flags); + schedule_work(&bigben->worker); } @@ -259,6 +299,7 @@ static void bigben_set_led(struct led_classdev *led, struct bigben_device *bigben = hid_get_drvdata(hid); int n; bool work; + unsigned long flags; if (!bigben) { hid_err(hid, "no device data\n"); @@ -267,6 +308,7 @@ static void bigben_set_led(struct led_classdev *led, for (n = 0; n < NUM_LEDS; n++) { if (led == bigben->leds[n]) { + spin_lock_irqsave(&bigben->lock, flags); if (value == LED_OFF) { work = (bigben->led_state & BIT(n)); bigben->led_state &= ~BIT(n); @@ -274,6 +316,7 @@ static void bigben_set_led(struct led_classdev *led, work = !(bigben->led_state & BIT(n)); bigben->led_state |= BIT(n); } + spin_unlock_irqrestore(&bigben->lock, flags); if (work) { bigben->work_led = true; @@ -307,8 +350,12 @@ static enum led_brightness bigben_get_led(struct led_classdev *led) static void bigben_remove(struct hid_device *hid) { struct bigben_device *bigben = hid_get_drvdata(hid); + unsigned long flags; + spin_lock_irqsave(&bigben->lock, flags); bigben->removed = true; + spin_unlock_irqrestore(&bigben->lock, flags); + cancel_work_sync(&bigben->worker); hid_hw_stop(hid); } @@ -362,6 +409,7 @@ static int bigben_probe(struct hid_device *hid, set_bit(FF_RUMBLE, hidinput->input->ffbit); INIT_WORK(&bigben->worker, bigben_worker); + spin_lock_init(&bigben->lock); error = input_ff_create_memless(hidinput->input, NULL, hid_bigben_play_effect); From 1bba06f3e83a3bb076f5cd9c9de9c158d556836b Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 19:00:00 +0000 Subject: [PATCH 2250/4345] UPSTREAM: HID: bigben_worker() remove unneeded check on report_field [ Upstream commit 27d2a2fd844ec7da70d19fabb482304fd1e0595b ] bigben_worker() checks report_field to be non-NULL. The check has been added in commit 918aa1ef104d ("HID: bigbenff: prevent null pointer dereference") to prevent a NULL pointer crash. However, the true root cause was a missing check for output reports, patched in commit c7bf714f8755 ("HID: check empty report_list in bigben_probe()"), where the type-confused report list_entry was overlapping with a NULL pointer, which was then causing the crash. Bug: 268589017 Fixes: 918aa1ef104d ("HID: bigbenff: prevent null pointer dereference") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230125-hid-unregister-leds-v4-2-7860c5763c38@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin Signed-off-by: Lee Jones Change-Id: Ide36490e2e4482f6cf9af931bef052f172419e31 --- drivers/hid/hid-bigbenff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index ed3d2d7bc1dd..b98c5f31c184 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -197,7 +197,7 @@ static void bigben_worker(struct work_struct *work) u32 len; unsigned long flags; - if (bigben->removed || !report_field) + if (bigben->removed) return; buf = hid_alloc_report_buf(bigben->report, GFP_KERNEL); From 7fd7972fc1f6a6c05ff8fb859b5a8ed77be3dd1d Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 19:00:01 +0000 Subject: [PATCH 2251/4345] UPSTREAM: HID: bigben: use spinlock to safely schedule workers [ Upstream commit 76ca8da989c7d97a7f76c75d475fe95a584439d7 ] Use spinlocks to deal with workers introducing a wrapper bigben_schedule_work(), and several spinlock checks. Otherwise, bigben_set_led() may schedule bigben->worker after the structure has been freed, causing a use-after-free. Bug: 268589017 Fixes: 4eb1b01de5b9 ("HID: hid-bigbenff: fix race condition for scheduled work during removal") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230125-hid-unregister-leds-v4-3-7860c5763c38@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin Signed-off-by: Lee Jones Change-Id: Ia3f47b68264f6c492597b0b0603f6822dc624f2b --- drivers/hid/hid-bigbenff.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index b98c5f31c184..9d6560db762b 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -185,6 +185,15 @@ struct bigben_device { struct work_struct worker; }; +static inline void bigben_schedule_work(struct bigben_device *bigben) +{ + unsigned long flags; + + spin_lock_irqsave(&bigben->lock, flags); + if (!bigben->removed) + schedule_work(&bigben->worker); + spin_unlock_irqrestore(&bigben->lock, flags); +} static void bigben_worker(struct work_struct *work) { @@ -197,9 +206,6 @@ static void bigben_worker(struct work_struct *work) u32 len; unsigned long flags; - if (bigben->removed) - return; - buf = hid_alloc_report_buf(bigben->report, GFP_KERNEL); if (!buf) return; @@ -285,7 +291,7 @@ static int hid_bigben_play_effect(struct input_dev *dev, void *data, bigben->work_ff = true; spin_unlock_irqrestore(&bigben->lock, flags); - schedule_work(&bigben->worker); + bigben_schedule_work(bigben); } return 0; @@ -320,7 +326,7 @@ static void bigben_set_led(struct led_classdev *led, if (work) { bigben->work_led = true; - schedule_work(&bigben->worker); + bigben_schedule_work(bigben); } return; } @@ -450,7 +456,7 @@ static int bigben_probe(struct hid_device *hid, bigben->left_motor_force = 0; bigben->work_led = true; bigben->work_ff = true; - schedule_work(&bigben->worker); + bigben_schedule_work(bigben); hid_info(hid, "LED and force feedback support for BigBen gamepad\n"); From e0d8206f5d42f33854f7111ed1cb9cfc6f7820a4 Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sun, 12 Feb 2023 00:01:44 +0000 Subject: [PATCH 2252/4345] UPSTREAM: hid: bigben_probe(): validate report count [ Upstream commit b94335f899542a0da5fafc38af8edcaf90195843 ] bigben_probe() does not validate that the output report has the needed report values in the first field. A malicious device registering a report with one field and a single value causes an head OOB write in bigben_worker() when accessing report_field->value[1] to report_field->value[7]. Use hid_validate_values() which takes care of all the needed checks. Bug: 268589017 Fixes: 256a90ed9e46 ("HID: hid-bigbenff: driver for BigBen Interactive PS3OFMINIPAD gamepad") Signed-off-by: Pietro Borrello Link: https://lore.kernel.org/r/20230211-bigben-oob-v1-1-d2849688594c@diag.uniroma1.it Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin Signed-off-by: Lee Jones Change-Id: I575c5d4c8a63a2065752a45c47b23cf725cc57ae --- drivers/hid/hid-bigbenff.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index 9d6560db762b..a02cb517b4c4 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -371,7 +371,6 @@ static int bigben_probe(struct hid_device *hid, { struct bigben_device *bigben; struct hid_input *hidinput; - struct list_head *report_list; struct led_classdev *led; char *name; size_t name_sz; @@ -396,14 +395,12 @@ static int bigben_probe(struct hid_device *hid, return error; } - report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; - if (list_empty(report_list)) { + bigben->report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 8); + if (!bigben->report) { hid_err(hid, "no output report found\n"); error = -ENODEV; goto error_hw_stop; } - bigben->report = list_entry(report_list->next, - struct hid_report, list); if (list_empty(&hid->inputs)) { hid_err(hid, "no inputs found\n"); From 469e02cc6d3977c02378547e0e28cc537bd5d7b1 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Wed, 29 Mar 2023 11:58:43 +0530 Subject: [PATCH 2253/4345] BACKPORT: of: base: Skip CPU nodes with "fail"/"fail-..." status Allow fully disabling CPU nodes using status = "fail". This allows a bootloader to change the number of available CPUs (for example when a common DTS is used for SoC variants with different numbers of cores) without deleting the nodes altogether, which could require additional fixups to avoid dangling phandle references. Unknown status values (everything that is not "okay"/"ok", "disabled" or "fail"/"fail-...") will continue to be interpreted like "disabled", meaning that the CPU can be enabled during boot. References: - https://www.spinics.net/lists/devicetree-spec/msg01007.html - https://github.com/devicetree-org/dt-schema/pull/61 Bug: 275500667 Change-Id: I0d0028c1d5f529c43f184556ac661c50fe026741 Link: https://lore.kernel.org/all/CAL_Jsq+1LsTBdVaODVfmB0eme2jMpNL4VgKk-OM7rQWyyF0Jbw@mail.gmail.com/ Signed-off-by: Matthias Schiffer Tested-by: Sai Prakash Ranjan Reviewed-by: Frank Rowand Link: https://lore.kernel.org/r/20211122114536.2981-1-matthias.schiffer@ew.tq-group.com Signed-off-by: Rob Herring (cherry picked from commit 4fdd0736a3b1634613d1d2eeb3328d27522052fb) Signed-off-by: Komal Bajaj --- drivers/of/base.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/drivers/of/base.c b/drivers/of/base.c index bcc88cbbbead..bcb37c3a13b0 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -627,6 +627,28 @@ bool of_device_is_available(const struct device_node *device) } EXPORT_SYMBOL(of_device_is_available); +/** + * __of_device_is_fail - check if a device has status "fail" or "fail-..." + * + * @device: Node to check status for, with locks already held + * + * Return: True if the status property is set to "fail" or "fail-..." (for any + * error code suffix), false otherwise + */ +static bool __of_device_is_fail(const struct device_node *device) +{ + const char *status; + + if (!device) + return false; + + status = __of_get_property(device, "status", NULL); + if (status == NULL) + return false; + + return !strcmp(status, "fail") || !strncmp(status, "fail-", 5); +} + /** * of_device_is_big_endian - check if a device has BE registers * @@ -775,6 +797,9 @@ EXPORT_SYMBOL(of_get_next_available_child); * of_get_next_cpu_node - Iterate on cpu nodes * @prev: previous child of the /cpus node, or NULL to get first * + * Unusable CPUs (those with the status property set to "fail" or "fail-...") + * will be skipped. + * * Returns a cpu node pointer with refcount incremented, use of_node_put() * on it when done. Returns NULL when prev is the last child. Decrements * the refcount of prev. @@ -796,6 +821,8 @@ struct device_node *of_get_next_cpu_node(struct device_node *prev) of_node_put(node); } for (; next; next = next->sibling) { + if (__of_device_is_fail(next)) + continue; if (!(of_node_name_eq(next, "cpu") || __of_node_is_type(next, "cpu"))) continue; From e7bfca167067d02471b615c246c7a5a6a4b0b151 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 15 Mar 2023 11:39:02 -0700 Subject: [PATCH 2254/4345] BACKPORT: FROMGIT: blk-mq: release crypto keyslot before reporting I/O complete Once all I/O using a blk_crypto_key has completed, filesystems can call blk_crypto_evict_key(). However, the block layer currently doesn't call blk_crypto_put_keyslot() until the request is being freed, which happens after upper layers have been told (via bio_endio()) the I/O has completed. This causes a race condition where blk_crypto_evict_key() can see 'slot_refs != 0' without there being an actual bug. This makes __blk_crypto_evict_key() hit the 'WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)' and return without doing anything, eventually causing a use-after-free in blk_crypto_reprogram_all_keys(). (This is a very rare bug and has only been seen when per-file keys are being used with fscrypt.) There are two options to fix this: either release the keyslot before bio_endio() is called on the request's last bio, or make __blk_crypto_evict_key() ignore slot_refs. Let's go with the first solution, since it preserves the ability to report bugs (via WARN_ON_ONCE) where a key is evicted while still in-use. Fixes: a892c8d52c02 ("block: Inline encryption support for blk-mq") Cc: stable@vger.kernel.org Reviewed-by: Nathan Huckleberry Reviewed-by: Christoph Hellwig Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20230315183907.53675-2-ebiggers@kernel.org Signed-off-by: Jens Axboe Bug: 270098322 (cherry picked from commit 9cd1e566676bbcb8a126acd921e4e194e6339603 https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git/log/?h=for-next) Change-Id: Ic2c2426db7693a06901c7893d481471f30de03b2 Signed-off-by: Eric Biggers --- block/blk-core.c | 7 +++++++ block/blk-crypto-internal.h | 25 +++++++++++++++++++++---- block/blk-crypto.c | 24 ++++++++++++------------ block/blk-merge.c | 2 ++ block/blk-mq.c | 2 +- 5 files changed, 43 insertions(+), 17 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index a5edfc114221..3f8c1457eadb 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1450,6 +1450,13 @@ bool blk_update_request(struct request *req, blk_status_t error, req->q->integrity.profile->complete_fn(req, nr_bytes); #endif + /* + * Upper layers may call blk_crypto_evict_key() anytime after the last + * bio_endio(). Therefore, the keyslot must be released before that. + */ + if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req)) + __blk_crypto_rq_put_keyslot(req); + if (unlikely(error && !blk_rq_is_passthrough(req) && !(req->rq_flags & RQF_QUIET))) print_req_error(req, error, __func__); diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h index 0d36aae538d7..8e0834557620 100644 --- a/block/blk-crypto-internal.h +++ b/block/blk-crypto-internal.h @@ -60,6 +60,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq) return rq->crypt_ctx; } +static inline bool blk_crypto_rq_has_keyslot(struct request *rq) +{ + return rq->crypt_keyslot; +} + #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool bio_crypt_rq_ctx_compatible(struct request *rq, @@ -93,6 +98,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq) return false; } +static inline bool blk_crypto_rq_has_keyslot(struct request *rq) +{ + return false; +} + #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ void __bio_crypt_advance(struct bio *bio, unsigned int bytes); @@ -127,14 +137,21 @@ static inline bool blk_crypto_bio_prep(struct bio **bio_ptr) return true; } -blk_status_t __blk_crypto_init_request(struct request *rq); -static inline blk_status_t blk_crypto_init_request(struct request *rq) +blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq); +static inline blk_status_t blk_crypto_rq_get_keyslot(struct request *rq) { if (blk_crypto_rq_is_encrypted(rq)) - return __blk_crypto_init_request(rq); + return __blk_crypto_rq_get_keyslot(rq); return BLK_STS_OK; } +void __blk_crypto_rq_put_keyslot(struct request *rq); +static inline void blk_crypto_rq_put_keyslot(struct request *rq) +{ + if (blk_crypto_rq_has_keyslot(rq)) + __blk_crypto_rq_put_keyslot(rq); +} + void __blk_crypto_free_request(struct request *rq); static inline void blk_crypto_free_request(struct request *rq) { @@ -173,7 +190,7 @@ static inline blk_status_t blk_crypto_insert_cloned_request(struct request *rq) { if (blk_crypto_rq_is_encrypted(rq)) - return blk_crypto_init_request(rq); + return blk_crypto_rq_get_keyslot(rq); return BLK_STS_OK; } diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 722868e016ed..84abf970c40c 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -217,26 +217,26 @@ static bool bio_crypt_check_alignment(struct bio *bio) return true; } -blk_status_t __blk_crypto_init_request(struct request *rq) +blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq) { return blk_ksm_get_slot_for_key(rq->q->ksm, rq->crypt_ctx->bc_key, &rq->crypt_keyslot); } -/** - * __blk_crypto_free_request - Uninitialize the crypto fields of a request. - * - * @rq: The request whose crypto fields to uninitialize. - * - * Completely uninitializes the crypto fields of a request. If a keyslot has - * been programmed into some inline encryption hardware, that keyslot is - * released. The rq->crypt_ctx is also freed. - */ -void __blk_crypto_free_request(struct request *rq) +void __blk_crypto_rq_put_keyslot(struct request *rq) { blk_ksm_put_slot(rq->crypt_keyslot); + rq->crypt_keyslot = NULL; +} + +void __blk_crypto_free_request(struct request *rq) +{ + /* The keyslot, if one was needed, should have been released earlier. */ + if (WARN_ON_ONCE(rq->crypt_keyslot)) + __blk_crypto_rq_put_keyslot(rq); + mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool); - blk_crypto_rq_set_defaults(rq); + rq->crypt_ctx = NULL; } /** diff --git a/block/blk-merge.c b/block/blk-merge.c index 087e422a65a8..4512ba4e0a67 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -803,6 +803,8 @@ static struct request *attempt_merge(struct request_queue *q, if (!blk_discard_mergable(req)) elv_merge_requests(q, req, next); + blk_crypto_rq_put_keyslot(next); + /* * 'next' is going away, so update stats accordingly */ diff --git a/block/blk-mq.c b/block/blk-mq.c index 5d520b187555..0c9631d42ee7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2247,7 +2247,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) blk_mq_bio_to_request(rq, bio, nr_segs); - ret = blk_crypto_init_request(rq); + ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) { bio->bi_status = ret; bio_endio(bio); From b3926f1a34c6aa2b456e2e357e533cb4470d0ec6 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 15 Mar 2023 11:39:03 -0700 Subject: [PATCH 2255/4345] BACKPORT: FROMGIT: blk-crypto: make blk_crypto_evict_key() return void blk_crypto_evict_key() is only called in contexts such as inode eviction where failure is not an option. So there is nothing the caller can do with errors except log them. (dm-table.c does "use" the error code, but only to pass on to upper layers, so it doesn't really count.) Just make blk_crypto_evict_key() return void and log errors itself. Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230315183907.53675-2-ebiggers@kernel.org Signed-off-by: Jens Axboe Bug: 270098322 (cherry picked from commit 70493a63ba04f754f7a7dd53a4fcc82700181490 https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git/log/?h=for-next) Change-Id: I8b9c7a74473e21fb740f021ac9f2fff95f986aa4 Signed-off-by: Eric Biggers --- block/blk-crypto.c | 22 ++++++++++------------ drivers/md/dm-table.c | 19 +++++-------------- include/linux/blk-crypto.h | 4 ++-- 3 files changed, 17 insertions(+), 28 deletions(-) diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 84abf970c40c..26956813a7bf 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "blk-crypto-internal.h" @@ -418,20 +419,17 @@ EXPORT_SYMBOL_GPL(blk_crypto_start_using_key); * Upper layers (filesystems) must call this function to ensure that a key is * evicted from any hardware that it might have been programmed into. The key * must not be in use by any in-flight IO when this function is called. - * - * Return: 0 on success or if key is not present in the q's ksm, -err on error. */ -int blk_crypto_evict_key(struct request_queue *q, - const struct blk_crypto_key *key) +void blk_crypto_evict_key(struct request_queue *q, + const struct blk_crypto_key *key) { - if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg)) - return blk_ksm_evict_key(q->ksm, key); + int err; - /* - * If the request queue's associated inline encryption hardware didn't - * have support for the key, then the key might have been programmed - * into the fallback keyslot manager, so try to evict from there. - */ - return blk_crypto_fallback_evict_key(key); + if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg)) + err = blk_ksm_evict_key(q->ksm, key); + else + err = blk_crypto_fallback_evict_key(key); + if (err) + pr_warn_ratelimited("error %d evicting key\n", err); } EXPORT_SYMBOL_GPL(blk_crypto_evict_key); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index ade798f92817..743bdb157b3e 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1221,21 +1221,12 @@ struct dm_keyslot_manager { struct mapped_device *md; }; -struct dm_keyslot_evict_args { - const struct blk_crypto_key *key; - int err; -}; - static int dm_keyslot_evict_callback(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct dm_keyslot_evict_args *args = data; - int err; + const struct blk_crypto_key *key = data; - err = blk_crypto_evict_key(bdev_get_queue(dev->bdev), args->key); - if (!args->err) - args->err = err; - /* Always try to evict the key from all devices. */ + blk_crypto_evict_key(bdev_get_queue(dev->bdev), key); return 0; } @@ -1250,7 +1241,6 @@ static int dm_keyslot_evict(struct blk_keyslot_manager *ksm, struct dm_keyslot_manager, ksm); struct mapped_device *md = dksm->md; - struct dm_keyslot_evict_args args = { key }; struct dm_table *t; int srcu_idx; int i; @@ -1263,10 +1253,11 @@ static int dm_keyslot_evict(struct blk_keyslot_manager *ksm, ti = dm_table_get_target(t, i); if (!ti->type->iterate_devices) continue; - ti->type->iterate_devices(ti, dm_keyslot_evict_callback, &args); + ti->type->iterate_devices(ti, dm_keyslot_evict_callback, + (void *)key); } dm_put_live_table(md, srcu_idx); - return args.err; + return 0; } struct dm_derive_raw_secret_args { diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index c495572a3c46..d89f521d8310 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -104,8 +104,8 @@ int blk_crypto_init_key(struct blk_crypto_key *blk_key, int blk_crypto_start_using_key(const struct blk_crypto_key *key, struct request_queue *q); -int blk_crypto_evict_key(struct request_queue *q, - const struct blk_crypto_key *key); +void blk_crypto_evict_key(struct request_queue *q, + const struct blk_crypto_key *key); bool blk_crypto_config_supported(struct request_queue *q, const struct blk_crypto_config *cfg); From 0dad2818cb64e44d28bed2927463cc1c7832cb8d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 15 Mar 2023 11:39:04 -0700 Subject: [PATCH 2256/4345] BACKPORT: FROMGIT: blk-crypto: make blk_crypto_evict_key() more robust If blk_crypto_evict_key() sees that the key is still in-use (due to a bug) or that ->keyslot_evict failed, it currently just returns while leaving the key linked into the keyslot management structures. However, blk_crypto_evict_key() is only called in contexts such as inode eviction where failure is not an option. So actually the caller proceeds with freeing the blk_crypto_key regardless of the return value of blk_crypto_evict_key(). These two assumptions don't match, and the result is that there can be a use-after-free in blk_crypto_reprogram_all_keys() after one of these errors occurs. (Note, these errors *shouldn't* happen; we're just talking about what happens if they do anyway.) Fix this by making blk_crypto_evict_key() unlink the key from the keyslot management structures even on failure. Also improve some comments. Fixes: 1b2628397058 ("block: Keyslot Manager for Inline Encryption") Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230315183907.53675-2-ebiggers@kernel.org Signed-off-by: Jens Axboe Bug: 270098322 (cherry picked from commit 5c7cb94452901a93e90c2230632e2c12a681bc92 https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git/log/?h=for-next) Change-Id: I4e8983ad7db94ea8cd422743196da8854adda552 Signed-off-by: Eric Biggers --- block/blk-crypto.c | 29 +++++++++++++++++++-------- block/keyslot-manager.c | 43 ++++++++++++++++++++--------------------- 2 files changed, 42 insertions(+), 30 deletions(-) diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 26956813a7bf..ccb2dc5a3939 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -410,15 +410,20 @@ int blk_crypto_start_using_key(const struct blk_crypto_key *key, EXPORT_SYMBOL_GPL(blk_crypto_start_using_key); /** - * blk_crypto_evict_key() - Evict a key from any inline encryption hardware - * it may have been programmed into - * @q: The request queue who's associated inline encryption hardware this key - * might have been programmed into - * @key: The key to evict + * blk_crypto_evict_key() - Evict a blk_crypto_key from a request_queue + * @q: a request_queue on which I/O using the key may have been done + * @key: the key to evict * - * Upper layers (filesystems) must call this function to ensure that a key is - * evicted from any hardware that it might have been programmed into. The key - * must not be in use by any in-flight IO when this function is called. + * For a given request_queue, this function removes the given blk_crypto_key + * from the keyslot management structures and evicts it from any underlying + * hardware keyslot(s) or blk-crypto-fallback keyslot it may have been + * programmed into. + * + * Upper layers must call this before freeing the blk_crypto_key. It must be + * called for every request_queue the key may have been used on. The key must + * no longer be in use by any I/O when this function is called. + * + * Context: May sleep. */ void blk_crypto_evict_key(struct request_queue *q, const struct blk_crypto_key *key) @@ -429,6 +434,14 @@ void blk_crypto_evict_key(struct request_queue *q, err = blk_ksm_evict_key(q->ksm, key); else err = blk_crypto_fallback_evict_key(key); + /* + * An error can only occur here if the key failed to be evicted from a + * keyslot (due to a hardware or driver issue) or is allegedly still in + * use by I/O (due to a kernel bug). Even in these cases, the key is + * still unlinked from the keyslot management structures, and the caller + * is allowed and expected to free it right away. There's nothing + * callers can do to handle errors, so just log them and return void. + */ if (err) pr_warn_ratelimited("error %d evicting key\n", err); } diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c index 7ba541f73ce8..94704774352a 100644 --- a/block/keyslot-manager.c +++ b/block/keyslot-manager.c @@ -350,25 +350,16 @@ bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, return true; } -/** - * blk_ksm_evict_key() - Evict a key from the lower layer device. - * @ksm: The keyslot manager to evict from - * @key: The key to evict - * - * Find the keyslot that the specified key was programmed into, and evict that - * slot from the lower layer device. The slot must not be in use by any - * in-flight IO when this function is called. - * - * Context: Process context. Takes and releases ksm->lock. - * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY - * if the keyslot is still in use, or another -errno value on other - * error. +/* + * This is an internal function that evicts a key from an inline encryption + * device that can be either a real device or the blk-crypto-fallback "device". + * It is used only by blk_crypto_evict_key(); see that function for details. */ int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, const struct blk_crypto_key *key) { struct blk_ksm_keyslot *slot; - int err = 0; + int err; if (blk_ksm_is_passthrough(ksm)) { if (ksm->ksm_ll_ops.keyslot_evict) { @@ -382,22 +373,30 @@ int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, blk_ksm_hw_enter(ksm); slot = blk_ksm_find_keyslot(ksm, key); - if (!slot) - goto out_unlock; + if (!slot) { + /* + * Not an error, since a key not in use by I/O is not guaranteed + * to be in a keyslot. There can be more keys than keyslots. + */ + err = 0; + goto out; + } if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) { + /* BUG: key is still in use by I/O */ err = -EBUSY; - goto out_unlock; + goto out_remove; } err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, blk_ksm_get_slot_idx(slot)); - if (err) - goto out_unlock; - +out_remove: + /* + * Callers free the key even on error, so unlink the key from the hash + * table and clear slot->key even on error. + */ hlist_del(&slot->hash_node); slot->key = NULL; - err = 0; -out_unlock: +out: blk_ksm_hw_exit(ksm); return err; } From 2a7aed72981a25f653be09cba5d0b4248e70268c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 16 Mar 2023 22:47:27 +0000 Subject: [PATCH 2257/4345] ANDROID: dm-default-key: update for blk_crypto_evict_key() returning void blk_crypto_evict_key() now returns void, so update default_key_dtr() accordingly. Bug: 270098322 Change-Id: I6add49a8f792c51f33e7adb189a9e7ed5ff410b0 Signed-off-by: Eric Biggers --- drivers/md/dm-default-key.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/md/dm-default-key.c b/drivers/md/dm-default-key.c index e8e9b72d30c5..eaa83298858c 100644 --- a/drivers/md/dm-default-key.c +++ b/drivers/md/dm-default-key.c @@ -67,13 +67,9 @@ lookup_cipher(const char *cipher_string) static void default_key_dtr(struct dm_target *ti) { struct default_key_c *dkc = ti->private; - int err; if (dkc->dev) { - err = blk_crypto_evict_key(bdev_get_queue(dkc->dev->bdev), - &dkc->key); - if (err && err != -ENOKEY) - DMWARN("Failed to evict crypto key: %d", err); + blk_crypto_evict_key(bdev_get_queue(dkc->dev->bdev), &dkc->key); dm_put_device(ti, dkc->dev); } kfree_sensitive(dkc->cipher_string); From d88cd5c7f07842144cf3493b43a96cb198d76704 Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Fri, 31 Mar 2023 19:16:49 +0000 Subject: [PATCH 2258/4345] ANDROID: Fix kernelci break: eventfd_signal_mask redefined MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix a merge issue where eventfd_signal_mask() was added twice which resulted in kernelci issues when !CONFIG_EVENTFD: include/linux/eventfd.h:76:19: error: redefinition of ‘eventfd_signal_mask’ Fixes: 4ef66581d7fd ("eventfd: provide a eventfd_signal_mask() helper") Signed-off-by: Todd Kjos Change-Id: Ifdd212e857c2ff76c75283e77b9978e51a96d178 --- include/linux/eventfd.h | 6 ------ 1 file changed, 6 deletions(-) diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index e8c5dd9c3dac..6cd2a92daf20 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -73,12 +73,6 @@ static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, return -ENOSYS; } -static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, - unsigned mask) -{ - return -ENOSYS; -} - static inline void eventfd_ctx_put(struct eventfd_ctx *ctx) { From 3ea370605ab59fa7f4c328e4341cda5b70399f44 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Tue, 24 Jan 2023 08:55:33 +0100 Subject: [PATCH 2259/4345] UPSTREAM: media: rc: Fix use-after-free bugs caused by ene_tx_irqsim() [ Upstream commit 29b0589a865b6f66d141d79b2dd1373e4e50fe17 ] When the ene device is detaching, function ene_remove() will be called. But there is no function to cancel tx_sim_timer in ene_remove(), the timer handler ene_tx_irqsim() could race with ene_remove(). As a result, the UAF bugs could happen, the process is shown below. (cleanup routine) | (timer routine) | mod_timer(&dev->tx_sim_timer, ..) ene_remove() | (wait a time) | ene_tx_irqsim() | dev->hw_lock //USE | ene_tx_sample(dev) //USE Fix by adding del_timer_sync(&dev->tx_sim_timer) in ene_remove(), The tx_sim_timer could stop before ene device is deallocated. What's more, The rc_unregister_device() and del_timer_sync() should be called first in ene_remove() and the deallocated functions such as free_irq(), release_region() and so on should be called behind them. Because the rc_unregister_device() is well synchronized. Otherwise, race conditions may happen. The situations that may lead to race conditions are shown below. Firstly, the rx receiver is disabled with ene_rx_disable() before rc_unregister_device() in ene_remove(), which means it can be enabled again if a process opens /dev/lirc0 between ene_rx_disable() and rc_unregister_device(). Secondly, the irqaction descriptor is freed by free_irq() before the rc device is unregistered, which means irqaction descriptor may be accessed again after it is deallocated. Thirdly, the timer can call ene_tx_sample() that can write to the io ports, which means the io ports could be accessed again after they are deallocated by release_region(). Therefore, the rc_unregister_device() and del_timer_sync() should be called first in ene_remove(). Suggested by: Sean Young Bug: 272747251 Fixes: 9ea53b74df9c ("V4L/DVB: STAGING: remove lirc_ene0100 driver") Signed-off-by: Duoming Zhou Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin Signed-off-by: Lee Jones Change-Id: I0076055ed3336b6f2ef4afe8afe68620dc6c2a0a --- drivers/media/rc/ene_ir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/rc/ene_ir.c b/drivers/media/rc/ene_ir.c index 6049e5c95394..5aa3953cab82 100644 --- a/drivers/media/rc/ene_ir.c +++ b/drivers/media/rc/ene_ir.c @@ -1106,6 +1106,8 @@ static void ene_remove(struct pnp_dev *pnp_dev) struct ene_device *dev = pnp_get_drvdata(pnp_dev); unsigned long flags; + rc_unregister_device(dev->rdev); + del_timer_sync(&dev->tx_sim_timer); spin_lock_irqsave(&dev->hw_lock, flags); ene_rx_disable(dev); ene_rx_restore_hw_buffer(dev); @@ -1113,7 +1115,6 @@ static void ene_remove(struct pnp_dev *pnp_dev) free_irq(dev->irq, dev); release_region(dev->hw_io, ENE_IO_SIZE); - rc_unregister_device(dev->rdev); kfree(dev); } From b7b3a636ada7be8414ce01a6c721b6abdd8ac816 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 2 Sep 2021 14:55:53 -0700 Subject: [PATCH 2260/4345] UPSTREAM: mm: memcontrol: set the correct memcg swappiness restriction Since commit c843966c556d ("mm: allow swappiness that prefers reclaiming anon over the file workingset") has expended the swappiness value to make swap to be preferred in some systems. We should also change the memcg swappiness restriction to allow memcg swap-preferred. Link: https://lkml.kernel.org/r/d77469b90c45c49953ccbc51e54a1d465bc18f70.1627626255.git.baolin.wang@linux.alibaba.com Fixes: c843966c556d ("mm: allow swappiness that prefers reclaiming anon over the file workingset") Signed-off-by: Baolin Wang Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Bug: 275726149 (cherry picked from commit 37bc3cb9bbef86d1ddbbc789e55b588c8a2cac26) Change-Id: If6a46ebe5313ae0f5e75917adb6ca852c8daa6e6 Signed-off-by: Carlos Galo --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0501a27be6f1..645688340f71 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4206,7 +4206,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css, { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - if (val > 100) + if (val > 200) return -EINVAL; if (css->parent) From faf3626b8e34df3dfff3a99e6582a9abd24410ce Mon Sep 17 00:00:00 2001 From: Paul Lawrence Date: Thu, 23 Feb 2023 08:59:38 -0800 Subject: [PATCH 2261/4345] ANDROID: incremental fs: Evict inodes before freeing mount data Since evicting inodes triggers writes to the backing file, which uses the mi_owner field from the mount_info struct, make sure inodes are evicted before we free the mount_info data Test: incfs_test Bug: 270117845 Change-Id: I673b2e0e04b5adc3998caf6f22443598a30338af Signed-off-by: Paul Lawrence (cherry picked from commit 7899985277527b29c47929a6d6a89c5c89b406ad) --- fs/incfs/sysfs.c | 2 ++ fs/incfs/vfs.c | 8 +++++++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/incfs/sysfs.c b/fs/incfs/sysfs.c index 5c7e0fd4496c..ba91c07d2887 100644 --- a/fs/incfs/sysfs.c +++ b/fs/incfs/sysfs.c @@ -34,12 +34,14 @@ DECLARE_FEATURE_FLAG(corefs); DECLARE_FEATURE_FLAG(zstd); DECLARE_FEATURE_FLAG(v2); DECLARE_FEATURE_FLAG(bugfix_throttling); +DECLARE_FEATURE_FLAG(bugfix_inode_eviction); static struct attribute *attributes[] = { &corefs_attr.attr, &zstd_attr.attr, &v2_attr.attr, &bugfix_throttling_attr.attr, + &bugfix_inode_eviction_attr.attr, NULL, }; diff --git a/fs/incfs/vfs.c b/fs/incfs/vfs.c index a0726a505e6c..f393f17435d3 100644 --- a/fs/incfs/vfs.c +++ b/fs/incfs/vfs.c @@ -1928,6 +1928,13 @@ void incfs_kill_sb(struct super_block *sb) pr_debug("incfs: unmount\n"); + /* + * We must kill the super before freeing mi, since killing the super + * triggers inode eviction, which triggers the final update of the + * backing file, which uses certain information for mi + */ + kill_anon_super(sb); + if (mi) { if (mi->mi_backing_dir_path.dentry) dinode = d_inode(mi->mi_backing_dir_path.dentry); @@ -1943,7 +1950,6 @@ void incfs_kill_sb(struct super_block *sb) incfs_free_mount_info(mi); sb->s_fs_info = NULL; } - kill_anon_super(sb); } static int show_options(struct seq_file *m, struct dentry *root) From 08ccb44bfffb80dfbbe0a1fb93f699a17f45dd0a Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Mon, 3 Apr 2023 15:32:19 +0800 Subject: [PATCH 2262/4345] ANDROID: GKI: Update symbols to symbol list Update symbols to symbol list externed by oppo network group. 2 Added functions: [A] 'function sock* __udp4_lib_lookup(net*, __be32, __be16, __be32, __be16, int, int, udp_table*, sk_buff*)' [A] 'function sock* __udp6_lib_lookup(net*, const in6_addr*, __be16, const in6_addr*, __be16, int, int, udp_table*, sk_buff*)' 1 Added variable: [A] 'udp_table udp_table' Bug: 193384408 Change-Id: I11069764b442ce935facb5283f0b3b3494e2846c Signed-off-by: Wei Liu --- android/abi_gki_aarch64.xml | 434 +++++++++++++++++++++------------- android/abi_gki_aarch64_oplus | 3 + 2 files changed, 271 insertions(+), 166 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 291958b75232..f67fa1192d73 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -737,6 +737,8 @@ + + @@ -6956,6 +6958,7 @@ + @@ -38661,7 +38664,14 @@ - + + + + + + + + @@ -44522,7 +44532,23 @@ - + + + + + + + + + + + + + + + + + @@ -48852,6 +48878,7 @@ + @@ -53795,6 +53822,13 @@ + + + + + + + @@ -66454,6 +66488,13 @@ + + + + + + + @@ -69763,7 +69804,20 @@ - + + + + + + + + + + + + + + @@ -70665,6 +70719,7 @@ + @@ -75654,6 +75709,9 @@ + + + @@ -91202,6 +91260,7 @@ + @@ -102968,6 +103027,12 @@ + + + + + + @@ -111213,6 +111278,7 @@ + @@ -113557,6 +113623,17 @@ + + + + + + + + + + + @@ -116335,10 +116412,10 @@ - - - - + + + + @@ -121251,6 +121328,30 @@ + + + + + + + + + + + + + + + + + + + + + + + + @@ -122210,11 +122311,11 @@ - - - - - + + + + + @@ -122347,17 +122448,17 @@ - - - - - + + + + + - - - - + + + + @@ -122379,8 +122480,8 @@ - - + + @@ -122411,17 +122512,17 @@ - - + + - - - + + + - - + + @@ -122546,11 +122647,11 @@ - - - - - + + + + + @@ -122798,8 +122899,8 @@ - - + + @@ -137084,13 +137185,13 @@ - - + + - - - + + + @@ -137163,10 +137264,10 @@ - - - - + + + + @@ -137206,8 +137307,8 @@ - - + + @@ -137282,10 +137383,10 @@ - - - - + + + + @@ -137300,38 +137401,38 @@ - - - - + + + + - - - + + + - - + + - - - + + + - - - + + + - - - + + + @@ -137378,14 +137479,14 @@ - - - + + + - - - + + + @@ -137434,22 +137535,22 @@ - - - + + + - - - + + + - - + + - - + + @@ -137591,9 +137692,9 @@ - - - + + + @@ -137601,10 +137702,10 @@ - - - - + + + + @@ -137630,42 +137731,42 @@ - - - - + + + + - - - - - - + + + + + + - - - - - - + + + + + + - - - - - - + + + + + + - - + + @@ -137824,9 +137925,9 @@ - - - + + + @@ -141738,8 +141839,8 @@ - - + + @@ -146768,6 +146869,7 @@ + @@ -147183,13 +147285,13 @@ - - + + - - - + + + @@ -147358,8 +147460,8 @@ - - + + @@ -147505,55 +147607,55 @@ - - - + + + - - - - + + + + - - - - + + + + - - + + - - - + + + - - - + + + - - - - + + + + - - - - + + + + - - + + @@ -147593,7 +147695,7 @@ - + @@ -147713,10 +147815,10 @@ - - - - + + + + @@ -147927,9 +148029,9 @@ - - - + + + diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index eb8aba0710d9..5693bb828b42 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -3262,6 +3262,9 @@ ucsi_set_drvdata ucsi_unregister __udelay + __udp4_lib_lookup + __udp6_lib_lookup + udp_table ufshcd_auto_hibern8_update ufshcd_delay_us ufshcd_dme_get_attr From 29ee1495e8577d2433b294417f29a3c4d65b4d9e Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Thu, 5 Jan 2023 02:22:19 +0200 Subject: [PATCH 2263/4345] interconnect: qcom: osm-l3: fix icc_onecell_data allocation [ Upstream commit f77ebdda0ee652124061c2ac42399bb6c367e729 ] This is a struct with a trailing zero-length array of icc_node pointers but it's allocated as if it were a single array of icc_nodes instead. Fortunately this overallocates memory rather then allocating less memory than required. Fix by replacing devm_kcalloc() with devm_kzalloc() and struct_size() macro. Fixes: 5bc9900addaf ("interconnect: qcom: Add OSM L3 interconnect provider support") Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230105002221.1416479-2-dmitry.baryshkov@linaro.org Signed-off-by: Georgi Djakov Signed-off-by: Sasha Levin --- drivers/interconnect/qcom/osm-l3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c index 695f28789e98..08a282d57320 100644 --- a/drivers/interconnect/qcom/osm-l3.c +++ b/drivers/interconnect/qcom/osm-l3.c @@ -258,7 +258,7 @@ static int qcom_osm_l3_probe(struct platform_device *pdev) qnodes = desc->nodes; num_nodes = desc->num_nodes; - data = devm_kcalloc(&pdev->dev, num_nodes, sizeof(*node), GFP_KERNEL); + data = devm_kzalloc(&pdev->dev, struct_size(data, nodes, num_nodes), GFP_KERNEL); if (!data) return -ENOMEM; From ddcf8320003638a06eb1e46412e045d0c5701575 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 14 Mar 2023 04:47:35 +0000 Subject: [PATCH 2264/4345] perf/core: Fix perf_output_begin parameter is incorrectly invoked in perf_event_bpf_output [ Upstream commit eb81a2ed4f52be831c9fb879752d89645a312c13 ] syzkaller reportes a KASAN issue with stack-out-of-bounds. The call trace is as follows: dump_stack+0x9c/0xd3 print_address_description.constprop.0+0x19/0x170 __kasan_report.cold+0x6c/0x84 kasan_report+0x3a/0x50 __perf_event_header__init_id+0x34/0x290 perf_event_header__init_id+0x48/0x60 perf_output_begin+0x4a4/0x560 perf_event_bpf_output+0x161/0x1e0 perf_iterate_sb_cpu+0x29e/0x340 perf_iterate_sb+0x4c/0xc0 perf_event_bpf_event+0x194/0x2c0 __bpf_prog_put.constprop.0+0x55/0xf0 __cls_bpf_delete_prog+0xea/0x120 [cls_bpf] cls_bpf_delete_prog_work+0x1c/0x30 [cls_bpf] process_one_work+0x3c2/0x730 worker_thread+0x93/0x650 kthread+0x1b8/0x210 ret_from_fork+0x1f/0x30 commit 267fb27352b6 ("perf: Reduce stack usage of perf_output_begin()") use on-stack struct perf_sample_data of the caller function. However, perf_event_bpf_output uses incorrect parameter to convert small-sized data (struct perf_bpf_event) into large-sized data (struct perf_sample_data), which causes memory overwriting occurs in __perf_event_header__init_id. Fixes: 267fb27352b6 ("perf: Reduce stack usage of perf_output_begin()") Signed-off-by: Yang Jihong Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230314044735.56551-1-yangjihong1@huawei.com Signed-off-by: Sasha Levin --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index d7b61116f15b..eb8660ed1abb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8710,7 +8710,7 @@ static void perf_event_bpf_output(struct perf_event *event, void *data) perf_event_header__init_id(&bpf_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, data, event, + ret = perf_output_begin(&handle, &sample, event, bpf_event->event_id.header.size); if (ret) return; From 18dd825b865117db0e0e5557ddb3f7e0322739db Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 13 Mar 2023 10:16:08 -0700 Subject: [PATCH 2265/4345] perf: fix perf_event_context->time [ Upstream commit baf1b12a67f5b24f395baca03e442ce27cab0c18 ] Time readers rely on perf_event_context->[time|timestamp|timeoffset] to get accurate time_enabled and time_running for an event. The difference between ctx->timestamp and ctx->time is the among of time when the context is not enabled. __update_context_time(ctx, false) is used to increase timestamp, but not time. Therefore, it should only be called in ctx_sched_in() when EVENT_TIME was not enabled. Fixes: 09f5e7dc7ad7 ("perf: Fix perf_event_read_local() time") Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Acked-by: Namhyung Kim Link: https://lkml.kernel.org/r/20230313171608.298734-1-song@kernel.org Signed-off-by: Sasha Levin --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index eb8660ed1abb..e2e1371fbb9d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3817,7 +3817,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (likely(!ctx->nr_events)) return; - if (is_active ^ EVENT_TIME) { + if (!(is_active & EVENT_TIME)) { /* start ctx time */ __update_context_time(ctx, false); perf_cgroup_set_timestamp(task, ctx); From 4d57c90f24e1f197faa8bc472a6082fbbdbed259 Mon Sep 17 00:00:00 2001 From: Liguang Zhang Date: Mon, 1 Mar 2021 22:05:15 +0800 Subject: [PATCH 2266/4345] ipmi:ssif: make ssif_i2c_send() void [ Upstream commit dcd10526ac5a0d6cc94ce60b9acfca458163277b ] This function actually needs no return value. So remove the unneeded check and make it void. Signed-off-by: Liguang Zhang Message-Id: <20210301140515.18951-1-zhangliguang@linux.alibaba.com> Signed-off-by: Corey Minyard Stable-dep-of: 00bb7e763ec9 ("ipmi:ssif: Add a timer between request retries") Signed-off-by: Sasha Levin --- drivers/char/ipmi/ipmi_ssif.c | 81 +++++++++-------------------------- 1 file changed, 20 insertions(+), 61 deletions(-) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 0f2bac24e564..e9775b17dc92 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -510,7 +510,7 @@ static int ipmi_ssif_thread(void *data) return 0; } -static int ssif_i2c_send(struct ssif_info *ssif_info, +static void ssif_i2c_send(struct ssif_info *ssif_info, ssif_i2c_done handler, int read_write, int command, unsigned char *data, unsigned int size) @@ -522,7 +522,6 @@ static int ssif_i2c_send(struct ssif_info *ssif_info, ssif_info->i2c_data = data; ssif_info->i2c_size = size; complete(&ssif_info->wake_thread); - return 0; } @@ -531,22 +530,12 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, static void start_get(struct ssif_info *ssif_info) { - int rv; - ssif_info->rtc_us_timer = 0; ssif_info->multi_pos = 0; - rv = ssif_i2c_send(ssif_info, msg_done_handler, I2C_SMBUS_READ, - SSIF_IPMI_RESPONSE, - ssif_info->recv, I2C_SMBUS_BLOCK_DATA); - if (rv < 0) { - /* request failed, just return the error. */ - if (ssif_info->ssif_debug & SSIF_DEBUG_MSG) - dev_dbg(&ssif_info->client->dev, - "Error from i2c_non_blocking_op(5)\n"); - - msg_done_handler(ssif_info, -EIO, NULL, 0); - } + ssif_i2c_send(ssif_info, msg_done_handler, I2C_SMBUS_READ, + SSIF_IPMI_RESPONSE, + ssif_info->recv, I2C_SMBUS_BLOCK_DATA); } static void retry_timeout(struct timer_list *t) @@ -620,7 +609,6 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, { struct ipmi_smi_msg *msg; unsigned long oflags, *flags; - int rv; /* * We are single-threaded here, so no need for a lock until we @@ -666,17 +654,10 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, ssif_info->multi_len = len; ssif_info->multi_pos = 1; - rv = ssif_i2c_send(ssif_info, msg_done_handler, I2C_SMBUS_READ, - SSIF_IPMI_MULTI_PART_RESPONSE_MIDDLE, - ssif_info->recv, I2C_SMBUS_BLOCK_DATA); - if (rv < 0) { - if (ssif_info->ssif_debug & SSIF_DEBUG_MSG) - dev_dbg(&ssif_info->client->dev, - "Error from i2c_non_blocking_op(1)\n"); - - result = -EIO; - } else - return; + ssif_i2c_send(ssif_info, msg_done_handler, I2C_SMBUS_READ, + SSIF_IPMI_MULTI_PART_RESPONSE_MIDDLE, + ssif_info->recv, I2C_SMBUS_BLOCK_DATA); + return; } else if (ssif_info->multi_pos) { /* Middle of multi-part read. Start the next transaction. */ int i; @@ -738,19 +719,12 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, ssif_info->multi_pos++; - rv = ssif_i2c_send(ssif_info, msg_done_handler, - I2C_SMBUS_READ, - SSIF_IPMI_MULTI_PART_RESPONSE_MIDDLE, - ssif_info->recv, - I2C_SMBUS_BLOCK_DATA); - if (rv < 0) { - if (ssif_info->ssif_debug & SSIF_DEBUG_MSG) - dev_dbg(&ssif_info->client->dev, - "Error from ssif_i2c_send\n"); - - result = -EIO; - } else - return; + ssif_i2c_send(ssif_info, msg_done_handler, + I2C_SMBUS_READ, + SSIF_IPMI_MULTI_PART_RESPONSE_MIDDLE, + ssif_info->recv, + I2C_SMBUS_BLOCK_DATA); + return; } } @@ -931,8 +905,6 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, static void msg_written_handler(struct ssif_info *ssif_info, int result, unsigned char *data, unsigned int len) { - int rv; - /* We are single-threaded here, so no need for a lock. */ if (result < 0) { ssif_info->retries_left--; @@ -995,18 +967,9 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, ssif_info->multi_data = NULL; } - rv = ssif_i2c_send(ssif_info, msg_written_handler, - I2C_SMBUS_WRITE, cmd, - data_to_send, I2C_SMBUS_BLOCK_DATA); - if (rv < 0) { - /* request failed, just return the error. */ - ssif_inc_stat(ssif_info, send_errors); - - if (ssif_info->ssif_debug & SSIF_DEBUG_MSG) - dev_dbg(&ssif_info->client->dev, - "Error from i2c_non_blocking_op(3)\n"); - msg_done_handler(ssif_info, -EIO, NULL, 0); - } + ssif_i2c_send(ssif_info, msg_written_handler, + I2C_SMBUS_WRITE, cmd, + data_to_send, I2C_SMBUS_BLOCK_DATA); } else { /* Ready to request the result. */ unsigned long oflags, *flags; @@ -1035,7 +998,6 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, static int start_resend(struct ssif_info *ssif_info) { - int rv; int command; ssif_info->got_alert = false; @@ -1057,12 +1019,9 @@ static int start_resend(struct ssif_info *ssif_info) ssif_info->data[0] = ssif_info->data_len; } - rv = ssif_i2c_send(ssif_info, msg_written_handler, I2C_SMBUS_WRITE, - command, ssif_info->data, I2C_SMBUS_BLOCK_DATA); - if (rv && (ssif_info->ssif_debug & SSIF_DEBUG_MSG)) - dev_dbg(&ssif_info->client->dev, - "Error from i2c_non_blocking_op(4)\n"); - return rv; + ssif_i2c_send(ssif_info, msg_written_handler, I2C_SMBUS_WRITE, + command, ssif_info->data, I2C_SMBUS_BLOCK_DATA); + return 0; } static int start_send(struct ssif_info *ssif_info, From cd35cbde00786872b473b01abd6c3ef97b837480 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Thu, 3 Nov 2022 15:03:11 -0500 Subject: [PATCH 2267/4345] ipmi:ssif: Increase the message retry time [ Upstream commit 39721d62bbc16ebc9bb2bdc2c163658f33da3b0b ] The spec states that the minimum message retry time is 60ms, but it was set to 20ms. Correct it. Reported by: Tony Camuso Signed-off-by: Corey Minyard Stable-dep-of: 00bb7e763ec9 ("ipmi:ssif: Add a timer between request retries") Signed-off-by: Sasha Levin --- drivers/char/ipmi/ipmi_ssif.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index e9775b17dc92..167ca54d186c 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -74,7 +74,7 @@ /* * Timer values */ -#define SSIF_MSG_USEC 20000 /* 20ms between message tries. */ +#define SSIF_MSG_USEC 60000 /* 60ms between message tries. */ #define SSIF_MSG_PART_USEC 5000 /* 5ms for a message part */ /* How many times to we retry sending/receiving the message. */ From c94de7f85d99eef7bcab665da1d5888ad05fa4bc Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 25 Jan 2023 10:11:06 -0600 Subject: [PATCH 2268/4345] ipmi:ssif: resend_msg() cannot fail [ Upstream commit 95767ed78a181d5404202627499f9cde56053b96 ] The resend_msg() function cannot fail, but there was error handling around using it. Rework the handling of the error, and fix the out of retries debug reporting that was wrong around this, too. Cc: stable@vger.kernel.org Signed-off-by: Corey Minyard Stable-dep-of: 00bb7e763ec9 ("ipmi:ssif: Add a timer between request retries") Signed-off-by: Sasha Levin --- drivers/char/ipmi/ipmi_ssif.c | 28 +++++++--------------------- 1 file changed, 7 insertions(+), 21 deletions(-) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 167ca54d186c..cae21632cf07 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -602,7 +602,7 @@ static void ssif_alert(struct i2c_client *client, enum i2c_alert_protocol type, start_get(ssif_info); } -static int start_resend(struct ssif_info *ssif_info); +static void start_resend(struct ssif_info *ssif_info); static void msg_done_handler(struct ssif_info *ssif_info, int result, unsigned char *data, unsigned int len) @@ -909,31 +909,17 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, if (result < 0) { ssif_info->retries_left--; if (ssif_info->retries_left > 0) { - if (!start_resend(ssif_info)) { - ssif_inc_stat(ssif_info, send_retries); - return; - } - /* request failed, just return the error. */ - ssif_inc_stat(ssif_info, send_errors); - - if (ssif_info->ssif_debug & SSIF_DEBUG_MSG) - dev_dbg(&ssif_info->client->dev, - "%s: Out of retries\n", __func__); - msg_done_handler(ssif_info, -EIO, NULL, 0); + start_resend(ssif_info); return; } ssif_inc_stat(ssif_info, send_errors); - /* - * Got an error on transmit, let the done routine - * handle it. - */ if (ssif_info->ssif_debug & SSIF_DEBUG_MSG) dev_dbg(&ssif_info->client->dev, - "%s: Error %d\n", __func__, result); + "%s: Out of retries\n", __func__); - msg_done_handler(ssif_info, result, NULL, 0); + msg_done_handler(ssif_info, -EIO, NULL, 0); return; } @@ -996,7 +982,7 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, } } -static int start_resend(struct ssif_info *ssif_info) +static void start_resend(struct ssif_info *ssif_info) { int command; @@ -1021,7 +1007,6 @@ static int start_resend(struct ssif_info *ssif_info) ssif_i2c_send(ssif_info, msg_written_handler, I2C_SMBUS_WRITE, command, ssif_info->data, I2C_SMBUS_BLOCK_DATA); - return 0; } static int start_send(struct ssif_info *ssif_info, @@ -1036,7 +1021,8 @@ static int start_send(struct ssif_info *ssif_info, ssif_info->retries_left = SSIF_SEND_RETRIES; memcpy(ssif_info->data + 1, data, len); ssif_info->data_len = len; - return start_resend(ssif_info); + start_resend(ssif_info); + return 0; } /* Must be called with the message lock held. */ From 8f9ae017dd3571659b3f1f2dde6db6371a248821 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 25 Jan 2023 10:34:47 -0600 Subject: [PATCH 2269/4345] ipmi:ssif: Add a timer between request retries [ Upstream commit 00bb7e763ec9f384cb382455cb6ba5588b5375cf ] The IPMI spec has a time (T6) specified between request retries. Add the handling for that. Reported by: Tony Camuso Cc: stable@vger.kernel.org Signed-off-by: Corey Minyard Signed-off-by: Sasha Levin --- drivers/char/ipmi/ipmi_ssif.c | 34 +++++++++++++++++++++++++++------- 1 file changed, 27 insertions(+), 7 deletions(-) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index cae21632cf07..20dc2452815c 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -74,7 +74,8 @@ /* * Timer values */ -#define SSIF_MSG_USEC 60000 /* 60ms between message tries. */ +#define SSIF_MSG_USEC 60000 /* 60ms between message tries (T3). */ +#define SSIF_REQ_RETRY_USEC 60000 /* 60ms between send retries (T6). */ #define SSIF_MSG_PART_USEC 5000 /* 5ms for a message part */ /* How many times to we retry sending/receiving the message. */ @@ -82,7 +83,9 @@ #define SSIF_RECV_RETRIES 250 #define SSIF_MSG_MSEC (SSIF_MSG_USEC / 1000) +#define SSIF_REQ_RETRY_MSEC (SSIF_REQ_RETRY_USEC / 1000) #define SSIF_MSG_JIFFIES ((SSIF_MSG_USEC * 1000) / TICK_NSEC) +#define SSIF_REQ_RETRY_JIFFIES ((SSIF_REQ_RETRY_USEC * 1000) / TICK_NSEC) #define SSIF_MSG_PART_JIFFIES ((SSIF_MSG_PART_USEC * 1000) / TICK_NSEC) /* @@ -229,6 +232,9 @@ struct ssif_info { bool got_alert; bool waiting_alert; + /* Used to inform the timeout that it should do a resend. */ + bool do_resend; + /* * If set to true, this will request events the next time the * state machine is idle. @@ -538,22 +544,28 @@ static void start_get(struct ssif_info *ssif_info) ssif_info->recv, I2C_SMBUS_BLOCK_DATA); } +static void start_resend(struct ssif_info *ssif_info); + static void retry_timeout(struct timer_list *t) { struct ssif_info *ssif_info = from_timer(ssif_info, t, retry_timer); unsigned long oflags, *flags; - bool waiting; + bool waiting, resend; if (ssif_info->stopping) return; flags = ipmi_ssif_lock_cond(ssif_info, &oflags); + resend = ssif_info->do_resend; + ssif_info->do_resend = false; waiting = ssif_info->waiting_alert; ssif_info->waiting_alert = false; ipmi_ssif_unlock_cond(ssif_info, flags); if (waiting) start_get(ssif_info); + if (resend) + start_resend(ssif_info); } static void watch_timeout(struct timer_list *t) @@ -602,8 +614,6 @@ static void ssif_alert(struct i2c_client *client, enum i2c_alert_protocol type, start_get(ssif_info); } -static void start_resend(struct ssif_info *ssif_info); - static void msg_done_handler(struct ssif_info *ssif_info, int result, unsigned char *data, unsigned int len) { @@ -909,7 +919,13 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result, if (result < 0) { ssif_info->retries_left--; if (ssif_info->retries_left > 0) { - start_resend(ssif_info); + /* + * Wait the retry timeout time per the spec, + * then redo the send. + */ + ssif_info->do_resend = true; + mod_timer(&ssif_info->retry_timer, + jiffies + SSIF_REQ_RETRY_JIFFIES); return; } @@ -1322,8 +1338,10 @@ static int do_cmd(struct i2c_client *client, int len, unsigned char *msg, ret = i2c_smbus_write_block_data(client, SSIF_IPMI_REQUEST, len, msg); if (ret) { retry_cnt--; - if (retry_cnt > 0) + if (retry_cnt > 0) { + msleep(SSIF_REQ_RETRY_MSEC); goto retry1; + } return -ENODEV; } @@ -1464,8 +1482,10 @@ retry_write: 32, msg); if (ret) { retry_cnt--; - if (retry_cnt > 0) + if (retry_cnt > 0) { + msleep(SSIF_REQ_RETRY_MSEC); goto retry_write; + } dev_err(&client->dev, "Could not write multi-part start, though the BMC said it could handle it. Just limit sends to one part.\n"); return ret; } From 4cc54f6ae5351dd883120751b75405c9e38aeecc Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 27 Aug 2021 11:25:09 +0200 Subject: [PATCH 2270/4345] KVM: Clean up benign vcpu->cpu data races when kicking vCPUs [ Upstream commit 85b640450ddcfa09cf72771b69a9c3daf0ddc772 ] Fix a benign data race reported by syzbot+KCSAN[*] by ensuring vcpu->cpu is read exactly once, and by ensuring the vCPU is booted from guest mode if kvm_arch_vcpu_should_kick() returns true. Fix a similar race in kvm_make_vcpus_request_mask() by ensuring the vCPU is interrupted if kvm_request_needs_ipi() returns true. Reading vcpu->cpu before vcpu->mode (via kvm_arch_vcpu_should_kick() or kvm_request_needs_ipi()) means the target vCPU could get migrated (change vcpu->cpu) and enter !OUTSIDE_GUEST_MODE between reading vcpu->cpud and reading vcpu->mode. If that happens, the kick/IPI will be sent to the old pCPU, not the new pCPU that is now running the vCPU or reading SPTEs. Although failing to kick the vCPU is not exactly ideal, practically speaking it cannot cause a functional issue unless there is also a bug in the caller, and any such bug would exist regardless of kvm_vcpu_kick()'s behavior. The purpose of sending an IPI is purely to get a vCPU into the host (or out of reading SPTEs) so that the vCPU can recognize a change in state, e.g. a KVM_REQ_* request. If vCPU's handling of the state change is required for correctness, KVM must ensure either the vCPU sees the change before entering the guest, or that the sender sees the vCPU as running in guest mode. All architectures handle this by (a) sending the request before calling kvm_vcpu_kick() and (b) checking for requests _after_ setting vcpu->mode. x86's READING_SHADOW_PAGE_TABLES has similar requirements; KVM needs to ensure it kicks and waits for vCPUs that started reading SPTEs _before_ MMU changes were finalized, but any vCPU that starts reading after MMU changes were finalized will see the new state and can continue on uninterrupted. For uses of kvm_vcpu_kick() that are not paired with a KVM_REQ_*, e.g. x86's kvm_arch_sync_dirty_log(), the order of the kick must not be relied upon for functional correctness, e.g. in the dirty log case, userspace cannot assume it has a 100% complete log if vCPUs are still running. All that said, eliminate the benign race since the cost of doing so is an "extra" atomic cmpxchg() in the case where the target vCPU is loaded by the current pCPU or is not loaded at all. I.e. the kick will be skipped due to kvm_vcpu_exiting_guest_mode() seeing a compatible vcpu->mode as opposed to the kick being skipped because of the cpu checks. Keep the "cpu != me" checks even though they appear useless/impossible at first glance. x86 processes guest IPI writes in a fast path that runs in IN_GUEST_MODE, i.e. can call kvm_vcpu_kick() from IN_GUEST_MODE. And calling kvm_vm_bugged()->kvm_make_vcpus_request_mask() from IN_GUEST or READING_SHADOW_PAGE_TABLES is perfectly reasonable. Note, a race with the cpu_online() check in kvm_vcpu_kick() likely persists, e.g. the vCPU could exit guest mode and get offlined between the cpu_online() check and the sending of smp_send_reschedule(). But, the online check appears to exist only to avoid a WARN in x86's native_smp_send_reschedule() that fires if the target CPU is not online. The reschedule WARN exists because CPU offlining takes the CPU out of the scheduling pool, i.e. the WARN is intended to detect the case where the kernel attempts to schedule a task on an offline CPU. The actual sending of the IPI is a non-issue as at worst it will simpy be dropped on the floor. In other words, KVM's usurping of the reschedule IPI could theoretically trigger a WARN if the stars align, but there will be no loss of functionality. [*] https://syzkaller.appspot.com/bug?extid=cd4154e502f43f10808a Cc: Venkatesh Srinivas Cc: Vitaly Kuznetsov Fixes: 97222cc83163 ("KVM: Emulate local APIC in kernel") Signed-off-by: Sean Christopherson Signed-off-by: Vitaly Kuznetsov Message-Id: <20210827092516.1027264-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini Stable-dep-of: 2b0128127373 ("KVM: Register /dev/kvm as the _very_ last thing during initialization") Signed-off-by: Sasha Levin --- virt/kvm/kvm_main.c | 36 ++++++++++++++++++++++++++++-------- 1 file changed, 28 insertions(+), 8 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 564d5c145fbe..b5134f304648 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -276,14 +276,26 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, continue; kvm_make_request(req, vcpu); - cpu = vcpu->cpu; if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) continue; - if (tmp != NULL && cpu != -1 && cpu != me && - kvm_request_needs_ipi(vcpu, req)) - __cpumask_set_cpu(cpu, tmp); + /* + * Note, the vCPU could get migrated to a different pCPU at any + * point after kvm_request_needs_ipi(), which could result in + * sending an IPI to the previous pCPU. But, that's ok because + * the purpose of the IPI is to ensure the vCPU returns to + * OUTSIDE_GUEST_MODE, which is satisfied if the vCPU migrates. + * Entering READING_SHADOW_PAGE_TABLES after this point is also + * ok, as the requirement is only that KVM wait for vCPUs that + * were reading SPTEs _before_ any changes were finalized. See + * kvm_vcpu_kick() for more details on handling requests. + */ + if (tmp != NULL && kvm_request_needs_ipi(vcpu, req)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != -1 && cpu != me) + __cpumask_set_cpu(cpu, tmp); + } } called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT)); @@ -2937,16 +2949,24 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up); */ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { - int me; - int cpu = vcpu->cpu; + int me, cpu; if (kvm_vcpu_wake_up(vcpu)) return; + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_arch_vcpu_should_kick(), which could result in sending an + * IPI to the previous pCPU. But, that's ok because the purpose of the + * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the + * vCPU also requires it to leave IN_GUEST_MODE. + */ me = get_cpu(); - if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - if (kvm_arch_vcpu_should_kick(vcpu)) + if (kvm_arch_vcpu_should_kick(vcpu)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); + } put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick); From ad120bc8693028ed400bc3b9ec349cfaf7bfef3b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 27 Aug 2021 11:25:10 +0200 Subject: [PATCH 2271/4345] KVM: KVM: Use cpumask_available() to check for NULL cpumask when kicking vCPUs [ Upstream commit 0bbc2ca8515f9cdf11df84ccb63dc7c44bc3d8f4 ] Check for a NULL cpumask_var_t when kicking multiple vCPUs via cpumask_available(), which performs a !NULL check if and only if cpumasks are configured to be allocated off-stack. This is a meaningless optimization, e.g. avoids a TEST+Jcc and TEST+CMOV on x86, but more importantly helps document that the NULL check is necessary even though all callers pass in a local variable. No functional change intended. Cc: Lai Jiangshan Signed-off-by: Sean Christopherson Signed-off-by: Vitaly Kuznetsov Message-Id: <20210827092516.1027264-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini Stable-dep-of: 2b0128127373 ("KVM: Register /dev/kvm as the _very_ last thing during initialization") Signed-off-by: Sasha Levin --- virt/kvm/kvm_main.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b5134f304648..f379398b43d5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -248,9 +248,13 @@ static void ack_flush(void *_completed) { } -static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) +static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait) { - if (unlikely(!cpus)) + const struct cpumask *cpus; + + if (likely(cpumask_available(tmp))) + cpus = tmp; + else cpus = cpu_online_mask; if (cpumask_empty(cpus)) @@ -280,6 +284,14 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) continue; + /* + * tmp can be "unavailable" if cpumasks are allocated off stack + * as allocation of the mask is deliberately not fatal and is + * handled by falling back to kicking all online CPUs. + */ + if (!cpumask_available(tmp)) + continue; + /* * Note, the vCPU could get migrated to a different pCPU at any * point after kvm_request_needs_ipi(), which could result in @@ -291,7 +303,7 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, * were reading SPTEs _before_ any changes were finalized. See * kvm_vcpu_kick() for more details on handling requests. */ - if (tmp != NULL && kvm_request_needs_ipi(vcpu, req)) { + if (kvm_request_needs_ipi(vcpu, req)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != -1 && cpu != me) __cpumask_set_cpu(cpu, tmp); From 6100066358ee1bc5f2d329a7d8eb32bf8e3ee74d Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 3 Sep 2021 09:51:37 +0200 Subject: [PATCH 2272/4345] KVM: Optimize kvm_make_vcpus_request_mask() a bit [ Upstream commit ae0946cd3601752dc58f86d84258e5361e9c8cd4 ] Iterating over set bits in 'vcpu_bitmap' should be faster than going through all vCPUs, especially when just a few bits are set. Drop kvm_make_vcpus_request_mask() call from kvm_make_all_cpus_request_except() to avoid handling the special case when 'vcpu_bitmap' is NULL, move the code to kvm_make_all_cpus_request_except() itself. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini Message-Id: <20210903075141.403071-5-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini Stable-dep-of: 2b0128127373 ("KVM: Register /dev/kvm as the _very_ last thing during initialization") Signed-off-by: Sasha Levin --- virt/kvm/kvm_main.c | 88 +++++++++++++++++++++++++++------------------ 1 file changed, 53 insertions(+), 35 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f379398b43d5..34931443dafa 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -264,50 +264,57 @@ static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait) return true; } +static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu, + unsigned int req, cpumask_var_t tmp, + int current_cpu) +{ + int cpu; + + kvm_make_request(req, vcpu); + + if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) + return; + + /* + * tmp can be "unavailable" if cpumasks are allocated off stack as + * allocation of the mask is deliberately not fatal and is handled by + * falling back to kicking all online CPUs. + */ + if (!cpumask_available(tmp)) + return; + + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_request_needs_ipi(), which could result in sending an IPI + * to the previous pCPU. But, that's OK because the purpose of the IPI + * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is + * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES + * after this point is also OK, as the requirement is only that KVM wait + * for vCPUs that were reading SPTEs _before_ any changes were + * finalized. See kvm_vcpu_kick() for more details on handling requests. + */ + if (kvm_request_needs_ipi(vcpu, req)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != -1 && cpu != current_cpu) + __cpumask_set_cpu(cpu, tmp); + } +} + bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, struct kvm_vcpu *except, unsigned long *vcpu_bitmap, cpumask_var_t tmp) { - int i, cpu, me; struct kvm_vcpu *vcpu; + int i, me; bool called; me = get_cpu(); - kvm_for_each_vcpu(i, vcpu, kvm) { - if ((vcpu_bitmap && !test_bit(i, vcpu_bitmap)) || - vcpu == except) + for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) { + vcpu = kvm_get_vcpu(kvm, i); + if (!vcpu || vcpu == except) continue; - - kvm_make_request(req, vcpu); - - if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) - continue; - - /* - * tmp can be "unavailable" if cpumasks are allocated off stack - * as allocation of the mask is deliberately not fatal and is - * handled by falling back to kicking all online CPUs. - */ - if (!cpumask_available(tmp)) - continue; - - /* - * Note, the vCPU could get migrated to a different pCPU at any - * point after kvm_request_needs_ipi(), which could result in - * sending an IPI to the previous pCPU. But, that's ok because - * the purpose of the IPI is to ensure the vCPU returns to - * OUTSIDE_GUEST_MODE, which is satisfied if the vCPU migrates. - * Entering READING_SHADOW_PAGE_TABLES after this point is also - * ok, as the requirement is only that KVM wait for vCPUs that - * were reading SPTEs _before_ any changes were finalized. See - * kvm_vcpu_kick() for more details on handling requests. - */ - if (kvm_request_needs_ipi(vcpu, req)) { - cpu = READ_ONCE(vcpu->cpu); - if (cpu != -1 && cpu != me) - __cpumask_set_cpu(cpu, tmp); - } + kvm_make_vcpu_request(kvm, vcpu, req, tmp, me); } called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT)); @@ -319,12 +326,23 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, struct kvm_vcpu *except) { + struct kvm_vcpu *vcpu; cpumask_var_t cpus; bool called; + int i, me; zalloc_cpumask_var(&cpus, GFP_ATOMIC); - called = kvm_make_vcpus_request_mask(kvm, req, except, NULL, cpus); + me = get_cpu(); + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu == except) + continue; + kvm_make_vcpu_request(kvm, vcpu, req, cpus, me); + } + + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); + put_cpu(); free_cpumask_var(cpus); return called; From 7958663668ef0ffe49c294ee55c83770b532c685 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 3 Sep 2021 09:51:40 +0200 Subject: [PATCH 2273/4345] KVM: Pre-allocate cpumasks for kvm_make_all_cpus_request_except() [ Upstream commit baff59ccdc657d290be51b95b38ebe5de40036b4 ] Allocating cpumask dynamically in zalloc_cpumask_var() is not ideal. Allocation is somewhat slow and can (in theory and when CPUMASK_OFFSTACK) fail. kvm_make_all_cpus_request_except() already disables preemption so we can use pre-allocated per-cpu cpumasks instead. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini Message-Id: <20210903075141.403071-8-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini Stable-dep-of: 2b0128127373 ("KVM: Register /dev/kvm as the _very_ last thing during initialization") Signed-off-by: Sasha Levin --- virt/kvm/kvm_main.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 34931443dafa..d96a076aef0d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -154,6 +154,8 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); static unsigned long long kvm_createvm_count; static unsigned long long kvm_active_vms; +static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask); + __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end) { @@ -327,14 +329,15 @@ bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, struct kvm_vcpu *except) { struct kvm_vcpu *vcpu; - cpumask_var_t cpus; + struct cpumask *cpus; bool called; int i, me; - zalloc_cpumask_var(&cpus, GFP_ATOMIC); - me = get_cpu(); + cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); + cpumask_clear(cpus); + kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu == except) continue; @@ -344,7 +347,6 @@ bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); - free_cpumask_var(cpus); return called; } @@ -5002,9 +5004,17 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, goto out_free_3; } + for_each_possible_cpu(cpu) { + if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), + GFP_KERNEL, cpu_to_node(cpu))) { + r = -ENOMEM; + goto out_free_4; + } + } + r = kvm_async_pf_init(); if (r) - goto out_free; + goto out_free_5; kvm_chardev_ops.owner = module; kvm_vm_fops.owner = module; @@ -5030,7 +5040,10 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, out_unreg: kvm_async_pf_deinit(); -out_free: +out_free_5: + for_each_possible_cpu(cpu) + free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); +out_free_4: kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); @@ -5050,8 +5063,12 @@ EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { + int cpu; + debugfs_remove_recursive(kvm_debugfs_dir); misc_deregister(&kvm_dev); + for_each_possible_cpu(cpu) + free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); From a43f7d0628e4f5cdb60c771a74d391c77ce87baf Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:08:45 +0000 Subject: [PATCH 2274/4345] KVM: Register /dev/kvm as the _very_ last thing during initialization [ Upstream commit 2b01281273738bf2d6551da48d65db2df3f28998 ] Register /dev/kvm, i.e. expose KVM to userspace, only after all other setup has completed. Once /dev/kvm is exposed, userspace can start invoking KVM ioctls, creating VMs, etc... If userspace creates a VM before KVM is done with its configuration, bad things may happen, e.g. KVM will fail to properly migrate vCPU state if a VM is created before KVM has registered preemption notifiers. Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20221130230934.1014142-2-seanjc@google.com> Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- virt/kvm/kvm_main.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d96a076aef0d..d2df08102171 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5020,12 +5020,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, kvm_vm_fops.owner = module; kvm_vcpu_fops.owner = module; - r = misc_register(&kvm_dev); - if (r) { - pr_err("kvm: misc device register failed\n"); - goto out_unreg; - } - register_syscore_ops(&kvm_syscore_ops); kvm_preempt_ops.sched_in = kvm_sched_in; @@ -5034,11 +5028,24 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, kvm_init_debug(); r = kvm_vfio_ops_init(); - WARN_ON(r); + if (WARN_ON_ONCE(r)) + goto err_vfio; + + /* + * Registration _must_ be the very last thing done, as this exposes + * /dev/kvm to userspace, i.e. all infrastructure must be setup! + */ + r = misc_register(&kvm_dev); + if (r) { + pr_err("kvm: misc device register failed\n"); + goto err_register; + } return 0; -out_unreg: +err_register: + kvm_vfio_ops_exit(); +err_vfio: kvm_async_pf_deinit(); out_free_5: for_each_possible_cpu(cpu) @@ -5065,8 +5072,14 @@ void kvm_exit(void) { int cpu; - debugfs_remove_recursive(kvm_debugfs_dir); + /* + * Note, unregistering /dev/kvm doesn't strictly need to come first, + * fops_get(), a.k.a. try_module_get(), prevents acquiring references + * to KVM while the module is being stopped. + */ misc_deregister(&kvm_dev); + + debugfs_remove_recursive(kvm_debugfs_dir); for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); From ae12308c7d5516891e616bdddfe20a303ac5b2d8 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 3 Aug 2022 18:42:08 +0800 Subject: [PATCH 2275/4345] serial: fsl_lpuart: Fix comment typo [ Upstream commit 374e01fa1304e1eabd2cd16f750da3ecaeab069b ] The double `as' is duplicated in the comment, remove one. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20220803104208.4127-1-wangborong@cdjrlc.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 1be6f2b15f90 ("tty: serial: fsl_lpuart: fix race on RX DMA shutdown") Signed-off-by: Sasha Levin --- drivers/tty/serial/fsl_lpuart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 32cce52800a7..bab296c5a021 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2766,7 +2766,7 @@ static int __maybe_unused lpuart_suspend(struct device *dev) * EDMA driver during suspend will forcefully release any * non-idle DMA channels. If port wakeup is enabled or if port * is console port or 'no_console_suspend' is set the Rx DMA - * cannot resume as as expected, hence gracefully release the + * cannot resume as expected, hence gracefully release the * Rx DMA path before suspend and start Rx DMA path on resume. */ if (irq_wake) { From 19a98d56dfedafb25652bdb9cd48a4e73ceba702 Mon Sep 17 00:00:00 2001 From: Alexander Sverdlin Date: Thu, 9 Mar 2023 14:43:02 +0100 Subject: [PATCH 2276/4345] tty: serial: fsl_lpuart: fix race on RX DMA shutdown [ Upstream commit 1be6f2b15f902c02e055ae0b419ca789200473c9 ] From time to time DMA completion can come in the middle of DMA shutdown: : : lpuart32_shutdown() lpuart_dma_shutdown() del_timer_sync() lpuart_dma_rx_complete() lpuart_copy_rx_to_tty() mod_timer() lpuart_dma_rx_free() When the timer fires a bit later, sport->dma_rx_desc is NULL: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000004 pc : lpuart_copy_rx_to_tty+0xcc/0x5bc lr : lpuart_timer_func+0x1c/0x2c Call trace: lpuart_copy_rx_to_tty lpuart_timer_func call_timer_fn __run_timers.part.0 run_timer_softirq __do_softirq __irq_exit_rcu irq_exit handle_domain_irq gic_handle_irq call_on_irq_stack do_interrupt_handler ... To fix this fold del_timer_sync() into lpuart_dma_rx_free() after dmaengine_terminate_sync() to make sure timer will not be re-started in lpuart_copy_rx_to_tty() <= lpuart_dma_rx_complete(). Fixes: 4a8588a1cf86 ("serial: fsl_lpuart: delete timer on shutdown") Cc: stable Signed-off-by: Alexander Sverdlin Link: https://lore.kernel.org/r/20230309134302.74940-2-alexander.sverdlin@siemens.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/fsl_lpuart.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index bab296c5a021..99f29bd930bd 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1278,6 +1278,7 @@ static void lpuart_dma_rx_free(struct uart_port *port) struct dma_chan *chan = sport->dma_rx_chan; dmaengine_terminate_all(chan); + del_timer_sync(&sport->lpuart_timer); dma_unmap_sg(chan->device->dev, &sport->rx_sgl, 1, DMA_FROM_DEVICE); kfree(sport->rx_ring.buf); sport->rx_ring.tail = 0; @@ -1743,7 +1744,6 @@ static int lpuart32_startup(struct uart_port *port) static void lpuart_dma_shutdown(struct lpuart_port *sport) { if (sport->lpuart_dma_rx_use) { - del_timer_sync(&sport->lpuart_timer); lpuart_dma_rx_free(&sport->port); sport->lpuart_dma_rx_use = false; } @@ -1894,10 +1894,8 @@ lpuart_set_termios(struct uart_port *port, struct ktermios *termios, * Since timer function acqures sport->port.lock, need to stop before * acquring same lock because otherwise del_timer_sync() can deadlock. */ - if (old && sport->lpuart_dma_rx_use) { - del_timer_sync(&sport->lpuart_timer); + if (old && sport->lpuart_dma_rx_use) lpuart_dma_rx_free(&sport->port); - } spin_lock_irqsave(&sport->port.lock, flags); @@ -2129,10 +2127,8 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios, * Since timer function acqures sport->port.lock, need to stop before * acquring same lock because otherwise del_timer_sync() can deadlock. */ - if (old && sport->lpuart_dma_rx_use) { - del_timer_sync(&sport->lpuart_timer); + if (old && sport->lpuart_dma_rx_use) lpuart_dma_rx_free(&sport->port); - } spin_lock_irqsave(&sport->port.lock, flags); @@ -2770,7 +2766,6 @@ static int __maybe_unused lpuart_suspend(struct device *dev) * Rx DMA path before suspend and start Rx DMA path on resume. */ if (irq_wake) { - del_timer_sync(&sport->lpuart_timer); lpuart_dma_rx_free(&sport->port); } From 5fcb12f00a05241089449d7d7bdb22b66803e4ce Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 11 Jul 2022 10:42:52 +0200 Subject: [PATCH 2277/4345] serial: 8250: SERIAL_8250_ASPEED_VUART should depend on ARCH_ASPEED [ Upstream commit 806a449725cbd679a7f52c394d3c87b451d66bd5 ] The Aspeed Virtual UART is only present on Aspeed BMC platforms. Hence add a dependency on ARCH_ASPEED, to prevent asking the user about this driver when configuring a kernel without Aspeed BMC support. Reviewed-by: Jeremy Kerr Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/259138c372d433005b4871789ef9ee8d15320307.1657528861.git.geert+renesas@glider.be Signed-off-by: Greg Kroah-Hartman Stable-dep-of: f8086d1a65ac ("serial: 8250: ASPEED_VUART: select REGMAP instead of depending on it") Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index 136f2b1460f9..dcf89db183df 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -255,6 +255,7 @@ config SERIAL_8250_ASPEED_VUART depends on SERIAL_8250 depends on OF depends on REGMAP && MFD_SYSCON + depends on ARCH_ASPEED || COMPILE_TEST help If you want to use the virtual UART (VUART) device on Aspeed BMC platforms, enable this option. This enables the 16550A- From b5131ed83c8309d3005ce4a4c5dbbb98362dc696 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 25 Feb 2023 21:39:53 -0800 Subject: [PATCH 2278/4345] serial: 8250: ASPEED_VUART: select REGMAP instead of depending on it [ Upstream commit f8086d1a65ac693e3fd863128352b4b11ee7324d ] REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it. Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues. Therefore, change the use of "depends on REGMAP" to "select REGMAP". Fixes: 8d310c9107a2 ("drivers/tty/serial/8250: Make Aspeed VUART SIRQ polarity configurable") Cc: stable Signed-off-by: Randy Dunlap Cc: Greg Kroah-Hartman Cc: Oskar Senft Cc: linux-serial@vger.kernel.org Link: https://lore.kernel.org/r/20230226053953.4681-9-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index dcf89db183df..b7922c8da1e6 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -254,8 +254,9 @@ config SERIAL_8250_ASPEED_VUART tristate "Aspeed Virtual UART" depends on SERIAL_8250 depends on OF - depends on REGMAP && MFD_SYSCON + depends on MFD_SYSCON depends on ARCH_ASPEED || COMPILE_TEST + select REGMAP help If you want to use the virtual UART (VUART) device on Aspeed BMC platforms, enable this option. This enables the 16550A- From cfeda9432c1dd0b33d006fc3cca21d69ff47c49b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 11:32:42 +0100 Subject: [PATCH 2279/4345] drm/sun4i: fix missing component unbind on bind errors [ Upstream commit c22f2ff8724b49dce2ae797e9fbf4bc0fa91112f ] Make sure to unbind all subcomponents when binding the aggregate device fails. Fixes: 9026e0d122ac ("drm: Add Allwinner A10 Display Engine support") Cc: stable@vger.kernel.org # 4.7 Cc: Maxime Ripard Signed-off-by: Johan Hovold Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20230306103242.4775-1-johan+linaro@kernel.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/sun4i/sun4i_drv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index c5912fd53772..9c6ae8cfa0b2 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -93,7 +93,7 @@ static int sun4i_drv_bind(struct device *dev) /* drm_vblank_init calls kcalloc, which can fail */ ret = drm_vblank_init(drm, drm->mode_config.num_crtc); if (ret) - goto cleanup_mode_config; + goto unbind_all; drm->irq_enabled = true; @@ -117,6 +117,8 @@ static int sun4i_drv_bind(struct device *dev) finish_poll: drm_kms_helper_poll_fini(drm); +unbind_all: + component_unbind_all(dev, NULL); cleanup_mode_config: drm_mode_config_cleanup(drm); of_reserved_mem_device_release(dev); From 1fde5782f187daa05919d2bebd872df8ebcc00d1 Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Thu, 23 Mar 2023 05:03:22 +0000 Subject: [PATCH 2280/4345] net: tls: fix possible race condition between do_tls_getsockopt_conf() and do_tls_setsockopt_conf() commit 49c47cc21b5b7a3d8deb18fc57b0aa2ab1286962 upstream. ctx->crypto_send.info is not protected by lock_sock in do_tls_getsockopt_conf(). A race condition between do_tls_getsockopt_conf() and error paths of do_tls_setsockopt_conf() may lead to a use-after-free or null-deref. More discussion: https://lore.kernel.org/all/Y/ht6gQL+u6fj3dG@hog/ Fixes: 3c4d7559159b ("tls: kernel TLS support") Signed-off-by: Hangyu Hua Link: https://lore.kernel.org/r/20230228023344.9623-1-hbh25y@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Meena Shanmugam Signed-off-by: Sasha Levin --- net/tls/tls_main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index e537085b184f..54863e68f304 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -386,13 +386,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(crypto_info_aes_gcm_128->iv, cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); memcpy(crypto_info_aes_gcm_128->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, crypto_info_aes_gcm_128, sizeof(*crypto_info_aes_gcm_128))) @@ -410,13 +408,11 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(crypto_info_aes_gcm_256->iv, cctx->iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, TLS_CIPHER_AES_GCM_256_IV_SIZE); memcpy(crypto_info_aes_gcm_256->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, crypto_info_aes_gcm_256, sizeof(*crypto_info_aes_gcm_256))) @@ -436,6 +432,8 @@ static int do_tls_getsockopt(struct sock *sk, int optname, { int rc = 0; + lock_sock(sk); + switch (optname) { case TLS_TX: case TLS_RX: @@ -446,6 +444,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname, rc = -ENOPROTOOPT; break; } + + release_sock(sk); + return rc; } From 18359b8e30c4f190398ae2bf41c9f07c78e4367a Mon Sep 17 00:00:00 2001 From: Minghao Chi Date: Tue, 12 Apr 2022 08:30:44 +0000 Subject: [PATCH 2281/4345] power: supply: bq24190_charger: using pm_runtime_resume_and_get instead of pm_runtime_get_sync [ Upstream commit d96a89407e5f682d1cb22569d91784506c784863 ] Using pm_runtime_resume_and_get is more appropriate for simplifing code Reported-by: Zeal Robot Signed-off-by: Minghao Chi Signed-off-by: Sebastian Reichel Stable-dep-of: 47c29d692129 ("power: supply: bq24190: Fix use after free bug in bq24190_remove due to race condition") Signed-off-by: Sasha Levin --- drivers/power/supply/bq24190_charger.c | 63 +++++++++----------------- 1 file changed, 21 insertions(+), 42 deletions(-) diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index 8c3c378dce0d..81389fcc73e1 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -448,11 +448,9 @@ static ssize_t bq24190_sysfs_show(struct device *dev, if (!info) return -EINVAL; - ret = pm_runtime_get_sync(bdi->dev); - if (ret < 0) { - pm_runtime_put_noidle(bdi->dev); + ret = pm_runtime_resume_and_get(bdi->dev); + if (ret < 0) return ret; - } ret = bq24190_read_mask(bdi, info->reg, info->mask, info->shift, &v); if (ret) @@ -483,11 +481,9 @@ static ssize_t bq24190_sysfs_store(struct device *dev, if (ret < 0) return ret; - ret = pm_runtime_get_sync(bdi->dev); - if (ret < 0) { - pm_runtime_put_noidle(bdi->dev); + ret = pm_runtime_resume_and_get(bdi->dev); + if (ret < 0) return ret; - } ret = bq24190_write_mask(bdi, info->reg, info->mask, info->shift, v); if (ret) @@ -506,10 +502,9 @@ static int bq24190_set_charge_mode(struct regulator_dev *dev, u8 val) struct bq24190_dev_info *bdi = rdev_get_drvdata(dev); int ret; - ret = pm_runtime_get_sync(bdi->dev); + ret = pm_runtime_resume_and_get(bdi->dev); if (ret < 0) { dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", ret); - pm_runtime_put_noidle(bdi->dev); return ret; } @@ -539,10 +534,9 @@ static int bq24190_vbus_is_enabled(struct regulator_dev *dev) int ret; u8 val; - ret = pm_runtime_get_sync(bdi->dev); + ret = pm_runtime_resume_and_get(bdi->dev); if (ret < 0) { dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", ret); - pm_runtime_put_noidle(bdi->dev); return ret; } @@ -1083,11 +1077,9 @@ static int bq24190_charger_get_property(struct power_supply *psy, dev_dbg(bdi->dev, "prop: %d\n", psp); - ret = pm_runtime_get_sync(bdi->dev); - if (ret < 0) { - pm_runtime_put_noidle(bdi->dev); + ret = pm_runtime_resume_and_get(bdi->dev); + if (ret < 0) return ret; - } switch (psp) { case POWER_SUPPLY_PROP_CHARGE_TYPE: @@ -1157,11 +1149,9 @@ static int bq24190_charger_set_property(struct power_supply *psy, dev_dbg(bdi->dev, "prop: %d\n", psp); - ret = pm_runtime_get_sync(bdi->dev); - if (ret < 0) { - pm_runtime_put_noidle(bdi->dev); + ret = pm_runtime_resume_and_get(bdi->dev); + if (ret < 0) return ret; - } switch (psp) { case POWER_SUPPLY_PROP_ONLINE: @@ -1420,11 +1410,9 @@ static int bq24190_battery_get_property(struct power_supply *psy, dev_warn(bdi->dev, "warning: /sys/class/power_supply/bq24190-battery is deprecated\n"); dev_dbg(bdi->dev, "prop: %d\n", psp); - ret = pm_runtime_get_sync(bdi->dev); - if (ret < 0) { - pm_runtime_put_noidle(bdi->dev); + ret = pm_runtime_resume_and_get(bdi->dev); + if (ret < 0) return ret; - } switch (psp) { case POWER_SUPPLY_PROP_STATUS: @@ -1468,11 +1456,9 @@ static int bq24190_battery_set_property(struct power_supply *psy, dev_warn(bdi->dev, "warning: /sys/class/power_supply/bq24190-battery is deprecated\n"); dev_dbg(bdi->dev, "prop: %d\n", psp); - ret = pm_runtime_get_sync(bdi->dev); - if (ret < 0) { - pm_runtime_put_noidle(bdi->dev); + ret = pm_runtime_resume_and_get(bdi->dev); + if (ret < 0) return ret; - } switch (psp) { case POWER_SUPPLY_PROP_ONLINE: @@ -1626,10 +1612,9 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data) int error; bdi->irq_event = true; - error = pm_runtime_get_sync(bdi->dev); + error = pm_runtime_resume_and_get(bdi->dev); if (error < 0) { dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error); - pm_runtime_put_noidle(bdi->dev); return IRQ_NONE; } bq24190_check_status(bdi); @@ -1849,11 +1834,9 @@ static int bq24190_remove(struct i2c_client *client) struct bq24190_dev_info *bdi = i2c_get_clientdata(client); int error; - error = pm_runtime_get_sync(bdi->dev); - if (error < 0) { + error = pm_runtime_resume_and_get(bdi->dev); + if (error < 0) dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error); - pm_runtime_put_noidle(bdi->dev); - } bq24190_register_reset(bdi); if (bdi->battery) @@ -1902,11 +1885,9 @@ static __maybe_unused int bq24190_pm_suspend(struct device *dev) struct bq24190_dev_info *bdi = i2c_get_clientdata(client); int error; - error = pm_runtime_get_sync(bdi->dev); - if (error < 0) { + error = pm_runtime_resume_and_get(bdi->dev); + if (error < 0) dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error); - pm_runtime_put_noidle(bdi->dev); - } bq24190_register_reset(bdi); @@ -1927,11 +1908,9 @@ static __maybe_unused int bq24190_pm_resume(struct device *dev) bdi->f_reg = 0; bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */ - error = pm_runtime_get_sync(bdi->dev); - if (error < 0) { + error = pm_runtime_resume_and_get(bdi->dev); + if (error < 0) dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error); - pm_runtime_put_noidle(bdi->dev); - } bq24190_register_reset(bdi); bq24190_set_config(bdi); From 2b346876b93168541a45551d5f9abd1d26102e89 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Fri, 10 Mar 2023 01:47:28 +0800 Subject: [PATCH 2282/4345] power: supply: bq24190: Fix use after free bug in bq24190_remove due to race condition [ Upstream commit 47c29d69212911f50bdcdd0564b5999a559010d4 ] In bq24190_probe, &bdi->input_current_limit_work is bound with bq24190_input_current_limit_work. When external power changed, it will call bq24190_charger_external_power_changed to start the work. If we remove the module which will call bq24190_remove to make cleanup, there may be a unfinished work. The possible sequence is as follows: CPU0 CPUc1 |bq24190_input_current_limit_work bq24190_remove | power_supply_unregister | device_unregister | power_supply_dev_release| kfree(psy) | | | power_supply_get_property_from_supplier | //use Fix it by finishing the work before cleanup in the bq24190_remove Fixes: 97774672573a ("power_supply: Initialize changed_work before calling device_add") Signed-off-by: Zheng Wang Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/bq24190_charger.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index 81389fcc73e1..338dd82007e4 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -1834,6 +1834,7 @@ static int bq24190_remove(struct i2c_client *client) struct bq24190_dev_info *bdi = i2c_get_clientdata(client); int error; + cancel_delayed_work_sync(&bdi->input_current_limit_work); error = pm_runtime_resume_and_get(bdi->dev); if (error < 0) dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error); From 75e2144291e847009fbc0350e10ec588ff96e05a Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Sun, 12 Mar 2023 01:46:50 +0800 Subject: [PATCH 2283/4345] power: supply: da9150: Fix use after free bug in da9150_charger_remove due to race condition [ Upstream commit 06615d11cc78162dfd5116efb71f29eb29502d37 ] In da9150_charger_probe, &charger->otg_work is bound with da9150_charger_otg_work. da9150_charger_otg_ncb may be called to start the work. If we remove the module which will call da9150_charger_remove to make cleanup, there may be a unfinished work. The possible sequence is as follows: Fix it by canceling the work before cleanup in the da9150_charger_remove CPU0 CPUc1 |da9150_charger_otg_work da9150_charger_remove | power_supply_unregister | device_unregister | power_supply_dev_release| kfree(psy) | | | power_supply_changed(charger->usb); | //use Fixes: c1a281e34dae ("power: Add support for DA9150 Charger") Signed-off-by: Zheng Wang Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/da9150-charger.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/power/supply/da9150-charger.c b/drivers/power/supply/da9150-charger.c index f9314cc0cd75..6b987da58655 100644 --- a/drivers/power/supply/da9150-charger.c +++ b/drivers/power/supply/da9150-charger.c @@ -662,6 +662,7 @@ static int da9150_charger_remove(struct platform_device *pdev) if (!IS_ERR_OR_NULL(charger->usb_phy)) usb_unregister_notifier(charger->usb_phy, &charger->otg_nb); + cancel_work_sync(&charger->otg_work); power_supply_unregister(charger->battery); power_supply_unregister(charger->usb); From 35a49d27585ccafb8d449c666f9620a739538a0f Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Sun, 26 Feb 2023 21:12:13 +0800 Subject: [PATCH 2284/4345] ARM: dts: imx6sll: e60k02: fix usbotg1 pinctrl [ Upstream commit 957c04e9784c7c757e8cc293d7fb2a60cdf461b6 ] usb@2184000: 'pinctrl-0' is a dependency of 'pinctrl-names' Signed-off-by: Peng Fan Fixes: c100ea86e6ab ("ARM: dts: add Netronix E60K02 board common file") Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/e60k02.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/e60k02.dtsi b/arch/arm/boot/dts/e60k02.dtsi index 3af1ab4458ef..bd1f58ae2374 100644 --- a/arch/arm/boot/dts/e60k02.dtsi +++ b/arch/arm/boot/dts/e60k02.dtsi @@ -296,6 +296,7 @@ &usbotg1 { pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usbotg1>; disable-over-current; srp-disable; hnp-disable; From 7b5dffe048f925a528c83e12331ebe635c12562d Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Sun, 26 Feb 2023 21:12:14 +0800 Subject: [PATCH 2285/4345] ARM: dts: imx6sl: tolino-shine2hd: fix usbotg1 pinctrl [ Upstream commit 1cd489e1ada1cffa56bd06fd4609f5a60a985d43 ] usb@2184000: 'pinctrl-0' is a dependency of 'pinctrl-names' Signed-off-by: Peng Fan Fixes: 9c7016f1ca6d ("ARM: dts: imx: add devicetree for Tolino Shine 2 HD") Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm/boot/dts/imx6sl-tolino-shine2hd.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/imx6sl-tolino-shine2hd.dts b/arch/arm/boot/dts/imx6sl-tolino-shine2hd.dts index caa279608803..0fd126db4e5d 100644 --- a/arch/arm/boot/dts/imx6sl-tolino-shine2hd.dts +++ b/arch/arm/boot/dts/imx6sl-tolino-shine2hd.dts @@ -580,6 +580,7 @@ &usbotg1 { pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usbotg1>; disable-over-current; srp-disable; hnp-disable; From 580634b03a55f04a3c1968bcbd97736c079c6601 Mon Sep 17 00:00:00 2001 From: Kal Conley Date: Wed, 8 Mar 2023 18:40:13 +0100 Subject: [PATCH 2286/4345] xsk: Add missing overflow check in xdp_umem_reg [ Upstream commit c7df4813b149362248d6ef7be41a311e27bf75fe ] The number of chunks can overflow u32. Make sure to return -EINVAL on overflow. Also remove a redundant u32 cast assigning umem->npgs. Fixes: bbff2f321a86 ("xsk: new descriptor addressing scheme") Signed-off-by: Kal Conley Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/20230308174013.1114745-1-kal.conley@dectris.com Signed-off-by: Sasha Levin --- net/xdp/xdp_umem.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 56a28a686988..42b19feb2b6e 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -153,10 +153,11 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { - u32 npgs_rem, chunk_size = mr->chunk_size, headroom = mr->headroom; bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; - u64 npgs, addr = mr->addr, size = mr->len; - unsigned int chunks, chunks_rem; + u32 chunk_size = mr->chunk_size, headroom = mr->headroom; + u64 addr = mr->addr, size = mr->len; + u32 chunks_rem, npgs_rem; + u64 chunks, npgs; int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { @@ -191,8 +192,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (npgs > U32_MAX) return -EINVAL; - chunks = (unsigned int)div_u64_rem(size, chunk_size, &chunks_rem); - if (chunks == 0) + chunks = div_u64_rem(size, chunk_size, &chunks_rem); + if (!chunks || chunks > U32_MAX) return -EINVAL; if (!unaligned_chunks && chunks_rem) @@ -205,7 +206,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->headroom = headroom; umem->chunk_size = chunk_size; umem->chunks = chunks; - umem->npgs = (u32)npgs; + umem->npgs = npgs; umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; From 15dcb57eba09ca3f84033af1e961dde24e2dcb14 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Wed, 1 Mar 2023 12:59:07 +0100 Subject: [PATCH 2287/4345] iavf: fix inverted Rx hash condition leading to disabled hash [ Upstream commit 32d57f667f871bc5a8babbe27ea4c5e668ee0ea8 ] Condition, which checks whether the netdev has hashing enabled is inverted. Basically, the tagged commit effectively disabled passing flow hash from descriptor to skb, unless user *disables* it via Ethtool. Commit a876c3ba59a6 ("i40e/i40evf: properly report Rx packet hash") fixed this problem, but only for i40e. Invert the condition now in iavf and unblock passing hash to skbs again. Fixes: 857942fd1aa1 ("i40e: Fix Rx hash reported to the stack by our driver") Reviewed-by: Larysa Zaremba Reviewed-by: Michal Kubiak Signed-off-by: Alexander Lobakin Tested-by: Rafal Romanowski Reviewed-by: Leon Romanovsky Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index d481a922f018..f411e683eb15 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1061,7 +1061,7 @@ static inline void iavf_rx_hash(struct iavf_ring *ring, cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); - if (ring->netdev->features & NETIF_F_RXHASH) + if (!(ring->netdev->features & NETIF_F_RXHASH)) return; if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { From 155d6d434f86bcbae985171c1c398c11f393950d Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Wed, 1 Mar 2023 12:59:08 +0100 Subject: [PATCH 2288/4345] iavf: fix non-tunneled IPv6 UDP packet type and hashing [ Upstream commit de58647b4301fe181f9c38e8b46f7021584ae427 ] Currently, IAVF's decode_rx_desc_ptype() correctly reports payload type of L4 for IPv4 UDP packets and IPv{4,6} TCP, but only L3 for IPv6 UDP. Originally, i40e, ice and iavf were affected. Commit 73df8c9e3e3d ("i40e: Correct UDP packet header for non_tunnel-ipv6") fixed that in i40e, then commit 638a0c8c8861 ("ice: fix incorrect payload indicator on PTYPE") fixed that for ice. IPv6 UDP is L4 obviously. Fix it and make iavf report correct L4 hash type for such packets, so that the stack won't calculate it on CPU when needs it. Fixes: 206812b5fccb ("i40e/i40evf: i40e implementation for skb_set_hash") Reviewed-by: Larysa Zaremba Reviewed-by: Michal Kubiak Signed-off-by: Alexander Lobakin Tested-by: Rafal Romanowski Reviewed-by: Leon Romanovsky Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c index 8547fc8fdfd6..78423ca401b2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_common.c +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -662,7 +662,7 @@ struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = { /* Non Tunneled IPv6 */ IAVF_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), IAVF_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), + IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), IAVF_PTT_UNUSED_ENTRY(91), IAVF_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), IAVF_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), From fe3850c72a722e9efe18b4ec384b0fa0c09ac053 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 22 Nov 2022 10:28:52 +0800 Subject: [PATCH 2289/4345] intel/igbvf: free irq on the error path in igbvf_request_msix() [ Upstream commit 85eb39bb39cbb5c086df1e19ba67cc1366693a77 ] In igbvf_request_msix(), irqs have not been freed on the err path, we need to free it. Fix it. Fixes: d4e0fe01a38a ("igbvf: add new driver to support 82576 virtual functions") Signed-off-by: Gaosheng Cui Reviewed-by: Maciej Fijalkowski Tested-by: Marek Szlosek Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igbvf/netdev.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index fe8c0a26b720..037ec90ed56c 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1074,7 +1074,7 @@ static int igbvf_request_msix(struct igbvf_adapter *adapter) igbvf_intr_msix_rx, 0, adapter->rx_ring->name, netdev); if (err) - goto out; + goto free_irq_tx; adapter->rx_ring->itr_register = E1000_EITR(vector); adapter->rx_ring->itr_val = adapter->current_itr; @@ -1083,10 +1083,14 @@ static int igbvf_request_msix(struct igbvf_adapter *adapter) err = request_irq(adapter->msix_entries[vector].vector, igbvf_msix_other, 0, netdev->name, netdev); if (err) - goto out; + goto free_irq_rx; igbvf_configure_msix(adapter); return 0; +free_irq_rx: + free_irq(adapter->msix_entries[--vector].vector, netdev); +free_irq_tx: + free_irq(adapter->msix_entries[--vector].vector, netdev); out: return err; } From d3e4844c1829646a0945318bf342f18b64715509 Mon Sep 17 00:00:00 2001 From: Akihiko Odaki Date: Thu, 1 Dec 2022 19:20:03 +0900 Subject: [PATCH 2290/4345] igbvf: Regard vf reset nack as success [ Upstream commit 02c83791ef969c6a8a150b4927193d0d0e50fb23 ] vf reset nack actually represents the reset operation itself is performed but no address is assigned. Therefore, e1000_reset_hw_vf should fill the "perm_addr" with the zero address and return success on such an occasion. This prevents its callers in netdev.c from saying PF still resetting, and instead allows them to correctly report that no address is assigned. Fixes: 6ddbc4cf1f4d ("igb: Indicate failure on vf reset for empty mac address") Signed-off-by: Akihiko Odaki Reviewed-by: Leon Romanovsky Tested-by: Marek Szlosek Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igbvf/vf.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/igbvf/vf.c b/drivers/net/ethernet/intel/igbvf/vf.c index b8ba3f94c363..a47a2e3e548c 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.c +++ b/drivers/net/ethernet/intel/igbvf/vf.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2009 - 2018 Intel Corporation. */ +#include + #include "vf.h" static s32 e1000_check_for_link_vf(struct e1000_hw *hw); @@ -131,11 +133,16 @@ static s32 e1000_reset_hw_vf(struct e1000_hw *hw) /* set our "perm_addr" based on info provided by PF */ ret_val = mbx->ops.read_posted(hw, msgbuf, 3); if (!ret_val) { - if (msgbuf[0] == (E1000_VF_RESET | - E1000_VT_MSGTYPE_ACK)) + switch (msgbuf[0]) { + case E1000_VF_RESET | E1000_VT_MSGTYPE_ACK: memcpy(hw->mac.perm_addr, addr, ETH_ALEN); - else + break; + case E1000_VF_RESET | E1000_VT_MSGTYPE_NACK: + eth_zero_addr(hw->mac.perm_addr); + break; + default: ret_val = -E1000_ERR_MAC_INIT; + } } } From bde2e73d5232cb52003197a5c5e05b61f720d000 Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Tue, 7 Mar 2023 15:45:31 +0900 Subject: [PATCH 2291/4345] igc: fix the validation logic for taprio's gate list [ Upstream commit 2b4cc3d3f4d8ec42961e98568a0afeee96a943ab ] The check introduced in the commit a5fd39464a40 ("igc: Lift TAPRIO schedule restriction") can detect a false positive error in some corner case. For instance, tc qdisc replace ... taprio num_tc 4 ... sched-entry S 0x01 100000 # slot#1 sched-entry S 0x03 100000 # slot#2 sched-entry S 0x04 100000 # slot#3 sched-entry S 0x08 200000 # slot#4 flags 0x02 # hardware offload Here the queue#0 (the first queue) is on at the slot#1 and #2, and off at the slot#3 and #4. Under the current logic, when the slot#4 is examined, validate_schedule() returns *false* since the enablement count for the queue#0 is two and it is already off at the previous slot (i.e. #3). But this definition is truely correct. Let's fix the logic to enforce a strict validation for consecutively-opened slots. Fixes: a5fd39464a40 ("igc: Lift TAPRIO schedule restriction") Signed-off-by: AKASHI Takahiro Reviewed-by: Kurt Kanzenbach Acked-by: Vinicius Costa Gomes Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 1a0aae7b128d..3aa0efb542aa 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4874,18 +4874,18 @@ static bool validate_schedule(struct igc_adapter *adapter, if (e->command != TC_TAPRIO_CMD_SET_GATES) return false; - for (i = 0; i < adapter->num_tx_queues; i++) { - if (e->gate_mask & BIT(i)) + for (i = 0; i < adapter->num_tx_queues; i++) + if (e->gate_mask & BIT(i)) { queue_uses[i]++; - /* There are limitations: A single queue cannot be - * opened and closed multiple times per cycle unless the - * gate stays open. Check for it. - */ - if (queue_uses[i] > 1 && - !(prev->gate_mask & BIT(i))) - return false; - } + /* There are limitations: A single queue cannot + * be opened and closed multiple times per cycle + * unless the gate stays open. Check for it. + */ + if (queue_uses[i] > 1 && + !(prev->gate_mask & BIT(i))) + return false; + } } return true; From a3ada13f20fd018fce7b5867e9805ee69ee01b83 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Mon, 30 Jan 2023 16:32:47 +0100 Subject: [PATCH 2292/4345] i2c: imx-lpi2c: check only for enabled interrupt flags [ Upstream commit 1c7885004567e8951d65a983be095f254dd20bef ] When reading from I2C, the Tx watermark is set to 0. Unfortunately the TDF (transmit data flag) is enabled when Tx FIFO entries is equal or less than watermark. So it is set in every case, hence the reset default of 1. This results in the MSR_RDF _and_ MSR_TDF flags to be set thus trying to send Tx data on a read message. Mask the IRQ status to filter for wanted flags only. Fixes: a55fa9d0e42e ("i2c: imx-lpi2c: add low power i2c bus driver") Signed-off-by: Alexander Stein Tested-by: Emanuele Ghidoli Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-imx-lpi2c.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 8b9ba055c418..2018dbcf241e 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -502,10 +502,14 @@ disable: static irqreturn_t lpi2c_imx_isr(int irq, void *dev_id) { struct lpi2c_imx_struct *lpi2c_imx = dev_id; + unsigned int enabled; unsigned int temp; + enabled = readl(lpi2c_imx->base + LPI2C_MIER); + lpi2c_imx_intctrl(lpi2c_imx, 0); temp = readl(lpi2c_imx->base + LPI2C_MSR); + temp &= enabled; if (temp & MSR_RDF) lpi2c_imx_read_rxfifo(lpi2c_imx); From c09cdf6eb815ee35e55d6c50ac7f63db58bd20b8 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Wed, 15 Mar 2023 14:21:54 +0800 Subject: [PATCH 2293/4345] scsi: scsi_dh_alua: Fix memleak for 'qdata' in alua_activate() [ Upstream commit a13faca032acbf2699293587085293bdfaafc8ae ] If alua_rtpg_queue() failed from alua_activate(), then 'qdata' is not freed, which will cause following memleak: unreferenced object 0xffff88810b2c6980 (size 32): comm "kworker/u16:2", pid 635322, jiffies 4355801099 (age 1216426.076s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 40 39 24 c1 ff ff ff ff 00 f8 ea 0a 81 88 ff ff @9$............. backtrace: [<0000000098f3a26d>] alua_activate+0xb0/0x320 [<000000003b529641>] scsi_dh_activate+0xb2/0x140 [<000000007b296db3>] activate_path_work+0xc6/0xe0 [dm_multipath] [<000000007adc9ace>] process_one_work+0x3c5/0x730 [<00000000c457a985>] worker_thread+0x93/0x650 [<00000000cb80e628>] kthread+0x1ba/0x210 [<00000000a1e61077>] ret_from_fork+0x22/0x30 Fix the problem by freeing 'qdata' in error path. Fixes: 625fe857e4fa ("scsi: scsi_dh_alua: Check scsi_device_get() return value") Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20230315062154.668812-1-yukuai1@huaweicloud.com Reviewed-by: Benjamin Block Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/device_handler/scsi_dh_alua.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index fe8a5e5c0df8..bf0b3178f84d 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -1036,10 +1036,12 @@ static int alua_activate(struct scsi_device *sdev, rcu_read_unlock(); mutex_unlock(&h->init_mutex); - if (alua_rtpg_queue(pg, sdev, qdata, true)) + if (alua_rtpg_queue(pg, sdev, qdata, true)) { fn = NULL; - else + } else { + kfree(qdata); err = SCSI_DH_DEV_OFFLINED; + } kref_put(&pg->kref, release_port_group); out: if (fn) From 33d1603a38e05886c538129ddfe00bd52d347e7b Mon Sep 17 00:00:00 2001 From: Szymon Heidrich Date: Thu, 16 Mar 2023 11:19:54 +0100 Subject: [PATCH 2294/4345] net: usb: smsc95xx: Limit packet length to skb->len [ Upstream commit ff821092cf02a70c2bccd2d19269f01e29aa52cf ] Packet length retrieved from descriptor may be larger than the actual socket buffer length. In such case the cloned skb passed up the network stack will leak kernel memory contents. Fixes: 2f7ca802bdae ("net: Add SMSC LAN9500 USB2.0 10/100 ethernet adapter driver") Signed-off-by: Szymon Heidrich Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230316101954.75836-1-szymon.heidrich@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/usb/smsc95xx.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index e1cd4c2de2d3..975f52605867 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1824,6 +1824,12 @@ static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) size = (u16)((header & RX_STS_FL_) >> 16); align_count = (4 - ((size + NET_IP_ALIGN) % 4)) % 4; + if (unlikely(size > skb->len)) { + netif_dbg(dev, rx_err, dev->net, + "size err header=0x%08x\n", header); + return 0; + } + if (unlikely(header & RX_STS_ES_)) { netif_dbg(dev, rx_err, dev->net, "Error header=0x%08x\n", header); From 39c3b9dd481c3afce9439b29bafe00444cb4406b Mon Sep 17 00:00:00 2001 From: Daniil Tatianin Date: Thu, 16 Mar 2023 13:29:21 +0300 Subject: [PATCH 2295/4345] qed/qed_sriov: guard against NULL derefs from qed_iov_get_vf_info [ Upstream commit 25143b6a01d0cc5319edd3de22ffa2578b045550 ] We have to make sure that the info returned by the helper is valid before using it. Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Fixes: f990c82c385b ("qed*: Add support for ndo_set_vf_trust") Fixes: 733def6a04bf ("qed*: IOV link control") Signed-off-by: Daniil Tatianin Reviewed-by: Michal Swiatkowski Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_sriov.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 3541bc95493f..b2a2beb84e54 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -4378,6 +4378,9 @@ qed_iov_configure_min_tx_rate(struct qed_dev *cdev, int vfid, u32 rate) } vf = qed_iov_get_vf_info(QED_LEADING_HWFN(cdev), (u16)vfid, true); + if (!vf) + return -EINVAL; + vport_id = vf->vport_id; return qed_configure_vport_wfq(cdev, vport_id, rate); @@ -5123,7 +5126,7 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) /* Validate that the VF has a configured vport */ vf = qed_iov_get_vf_info(hwfn, i, true); - if (!vf->vport_instance) + if (!vf || !vf->vport_instance) continue; memset(¶ms, 0, sizeof(params)); From bfeeb3aaad4ee8eaaefe5d9edd9b2ccb5d9b7505 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Fri, 17 Mar 2023 00:15:26 +0800 Subject: [PATCH 2296/4345] xirc2ps_cs: Fix use after free bug in xirc2ps_detach [ Upstream commit e8d20c3ded59a092532513c9bd030d1ea66f5f44 ] In xirc2ps_probe, the local->tx_timeout_task was bounded with xirc2ps_tx_timeout_task. When timeout occurs, it will call xirc_tx_timeout->schedule_work to start the work. When we call xirc2ps_detach to remove the driver, there may be a sequence as follows: Stop responding to timeout tasks and complete scheduled tasks before cleanup in xirc2ps_detach, which will fix the problem. CPU0 CPU1 |xirc2ps_tx_timeout_task xirc2ps_detach | free_netdev | kfree(dev); | | | do_reset | //use dev Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Zheng Wang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/xircom/xirc2ps_cs.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index 3e337142b516..56cef59c1c87 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -503,6 +503,11 @@ static void xirc2ps_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; + struct local_info *local = netdev_priv(dev); + + netif_carrier_off(dev); + netif_tx_disable(dev); + cancel_work_sync(&local->tx_timeout_task); dev_dbg(&link->dev, "detach\n"); From 1b333766ea7a65ee779dd7b91ad3325d1526db7e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 16 Mar 2023 13:33:24 -0700 Subject: [PATCH 2297/4345] net: phy: Ensure state transitions are processed from phy_stop() [ Upstream commit 4203d84032e28f893594a453bd8bc9c3b15c7334 ] In the phy_disconnect() -> phy_stop() path, we will be forcibly setting the PHY state machine to PHY_HALTED. This invalidates the old_state != phydev->state condition in phy_state_machine() such that we will neither display the state change for debugging, nor will we invoke the link_change_notify() callback. Factor the code by introducing phy_process_state_change(), and ensure that we process the state change from phy_stop() as well. Fixes: 5c5f626bcace ("net: phy: improve handling link_change_notify callback") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/phy/phy.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 18e67eb6d8b4..f3e606b6617e 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -56,6 +56,18 @@ static const char *phy_state_to_str(enum phy_state st) return NULL; } +static void phy_process_state_change(struct phy_device *phydev, + enum phy_state old_state) +{ + if (old_state != phydev->state) { + phydev_dbg(phydev, "PHY state change %s -> %s\n", + phy_state_to_str(old_state), + phy_state_to_str(phydev->state)); + if (phydev->drv && phydev->drv->link_change_notify) + phydev->drv->link_change_notify(phydev); + } +} + static void phy_link_up(struct phy_device *phydev) { phydev->phy_link_change(phydev, true); @@ -1110,6 +1122,7 @@ EXPORT_SYMBOL(phy_free_interrupt); void phy_stop(struct phy_device *phydev) { struct net_device *dev = phydev->attached_dev; + enum phy_state old_state; if (!phy_is_started(phydev) && phydev->state != PHY_DOWN) { WARN(1, "called from state %s\n", @@ -1118,6 +1131,7 @@ void phy_stop(struct phy_device *phydev) } mutex_lock(&phydev->lock); + old_state = phydev->state; if (phydev->state == PHY_CABLETEST) { phy_abort_cable_test(phydev); @@ -1128,6 +1142,7 @@ void phy_stop(struct phy_device *phydev) sfp_upstream_stop(phydev->sfp_bus); phydev->state = PHY_HALTED; + phy_process_state_change(phydev, old_state); mutex_unlock(&phydev->lock); @@ -1242,13 +1257,7 @@ void phy_state_machine(struct work_struct *work) if (err < 0) phy_error(phydev); - if (old_state != phydev->state) { - phydev_dbg(phydev, "PHY state change %s -> %s\n", - phy_state_to_str(old_state), - phy_state_to_str(phydev->state)); - if (phydev->drv && phydev->drv->link_change_notify) - phydev->drv->link_change_notify(phydev); - } + phy_process_state_change(phydev, old_state); /* Only re-schedule a PHY state machine change if we are polling the * PHY, if PHY_IGNORE_INTERRUPT is set, then we will be moving From d04dac7fae7580dce0cd9b55db6e1ad4e8d26157 Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Thu, 16 Mar 2023 16:33:16 -0700 Subject: [PATCH 2298/4345] net: mdio: fix owner field for mdio buses registered using device-tree [ Upstream commit 99669259f3361d759219811e670b7e0742668556 ] Bus ownership is wrong when using of_mdiobus_register() to register an mdio bus. That function is not inline, so when it calls mdiobus_register() the wrong THIS_MODULE value is captured. Signed-off-by: Maxime Bizon Fixes: 90eff9096c01 ("net: phy: Allow splitting MDIO bus/device support from PHYs") [florian: fix kdoc, added Fixes tag] Signed-off-by: Florian Fainelli Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/mdio/of_mdio.c | 12 +++++++----- drivers/net/phy/mdio_devres.c | 11 ++++++----- include/linux/of_mdio.h | 22 +++++++++++++++++++--- 3 files changed, 32 insertions(+), 13 deletions(-) diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 5bae47f3da40..b254127cea50 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -238,21 +238,23 @@ bool of_mdiobus_child_is_phy(struct device_node *child) EXPORT_SYMBOL(of_mdiobus_child_is_phy); /** - * of_mdiobus_register - Register mii_bus and create PHYs from the device tree + * __of_mdiobus_register - Register mii_bus and create PHYs from the device tree * @mdio: pointer to mii_bus structure * @np: pointer to device_node of MDIO bus. + * @owner: module owning the @mdio object. * * This function registers the mii_bus structure and registers a phy_device * for each child node of @np. */ -int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) +int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, + struct module *owner) { struct device_node *child; bool scanphys = false; int addr, rc; if (!np) - return mdiobus_register(mdio); + return __mdiobus_register(mdio, owner); /* Do not continue if the node is disabled */ if (!of_device_is_available(np)) @@ -272,7 +274,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) of_property_read_u32(np, "reset-post-delay-us", &mdio->reset_post_delay_us); /* Register the MDIO bus */ - rc = mdiobus_register(mdio); + rc = __mdiobus_register(mdio, owner); if (rc) return rc; @@ -336,7 +338,7 @@ unregister: mdiobus_unregister(mdio); return rc; } -EXPORT_SYMBOL(of_mdiobus_register); +EXPORT_SYMBOL(__of_mdiobus_register); /** * of_mdio_find_device - Given a device tree node, find the mdio_device diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c index b560e99695df..69b829e6ab35 100644 --- a/drivers/net/phy/mdio_devres.c +++ b/drivers/net/phy/mdio_devres.c @@ -98,13 +98,14 @@ EXPORT_SYMBOL(__devm_mdiobus_register); #if IS_ENABLED(CONFIG_OF_MDIO) /** - * devm_of_mdiobus_register - Resource managed variant of of_mdiobus_register() + * __devm_of_mdiobus_register - Resource managed variant of of_mdiobus_register() * @dev: Device to register mii_bus for * @mdio: MII bus structure to register * @np: Device node to parse + * @owner: Owning module */ -int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, - struct device_node *np) +int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np, struct module *owner) { struct mdiobus_devres *dr; int ret; @@ -117,7 +118,7 @@ int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, if (!dr) return -ENOMEM; - ret = of_mdiobus_register(mdio, np); + ret = __of_mdiobus_register(mdio, np, owner); if (ret) { devres_free(dr); return ret; @@ -127,7 +128,7 @@ int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, devres_add(dev, dr); return 0; } -EXPORT_SYMBOL(devm_of_mdiobus_register); +EXPORT_SYMBOL(__devm_of_mdiobus_register); #endif /* CONFIG_OF_MDIO */ MODULE_LICENSE("GPL"); diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index f56c6a9230ac..8cc6522ee43a 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -14,9 +14,25 @@ #if IS_ENABLED(CONFIG_OF_MDIO) bool of_mdiobus_child_is_phy(struct device_node *child); -int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); -int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, - struct device_node *np); +int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, + struct module *owner); + +static inline int of_mdiobus_register(struct mii_bus *mdio, + struct device_node *np) +{ + return __of_mdiobus_register(mdio, np, THIS_MODULE); +} + +int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np, struct module *owner); + +static inline int devm_of_mdiobus_register(struct device *dev, + struct mii_bus *mdio, + struct device_node *np) +{ + return __devm_of_mdiobus_register(dev, mdio, np, THIS_MODULE); +} + struct mdio_device *of_mdio_find_device(struct device_node *np); struct phy_device *of_phy_find_device(struct device_node *phy_np); struct phy_device * From cb5879efde4f9b4de4248b835890df7b6c49ffbc Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Sat, 18 Mar 2023 16:05:26 +0800 Subject: [PATCH 2299/4345] net: qcom/emac: Fix use after free bug in emac_remove due to race condition [ Upstream commit 6b6bc5b8bd2d4ca9e1efa9ae0f98a0b0687ace75 ] In emac_probe, &adpt->work_thread is bound with emac_work_thread. Then it will be started by timeout handler emac_tx_timeout or a IRQ handler emac_isr. If we remove the driver which will call emac_remove to make cleanup, there may be a unfinished work. The possible sequence is as follows: Fix it by finishing the work before cleanup in the emac_remove and disable timeout response. CPU0 CPU1 |emac_work_thread emac_remove | free_netdev | kfree(netdev); | |emac_reinit_locked |emac_mac_down |//use netdev Fixes: b9b17debc69d ("net: emac: emac gigabit ethernet controller driver") Signed-off-by: Zheng Wang Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qualcomm/emac/emac.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index ad655f0a4965..e1aa56be9cc0 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -728,9 +728,15 @@ static int emac_remove(struct platform_device *pdev) struct net_device *netdev = dev_get_drvdata(&pdev->dev); struct emac_adapter *adpt = netdev_priv(netdev); + netif_carrier_off(netdev); + netif_tx_disable(netdev); + unregister_netdev(netdev); netif_napi_del(&adpt->rx_q.napi); + free_irq(adpt->irq.irq, &adpt->irq); + cancel_work_sync(&adpt->work_thread); + emac_clks_teardown(adpt); put_device(&adpt->phydev->mdio.dev); From 3d5a97283e2aa00687399afef2a19e310081e202 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Sat, 18 Mar 2023 17:39:16 +0000 Subject: [PATCH 2300/4345] net/ps3_gelic_net: Fix RX sk_buff length [ Upstream commit 19b3bb51c3bc288b3f2c6f8c4450b0f548320625 ] The Gelic Ethernet device needs to have the RX sk_buffs aligned to GELIC_NET_RXBUF_ALIGN, and also the length of the RX sk_buffs must be a multiple of GELIC_NET_RXBUF_ALIGN. The current Gelic Ethernet driver was not allocating sk_buffs large enough to allow for this alignment. Also, correct the maximum and minimum MTU sizes, and add a new preprocessor macro for the maximum frame size, GELIC_NET_MAX_FRAME. Fixes various randomly occurring runtime network errors. Fixes: 02c1889166b4 ("ps3: gigabit ethernet driver for PS3, take3") Signed-off-by: Geoff Levand Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/toshiba/ps3_gelic_net.c | 19 ++++++++++--------- drivers/net/ethernet/toshiba/ps3_gelic_net.h | 5 +++-- 2 files changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c index d9a5722f561b..013011285dd0 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c @@ -365,26 +365,27 @@ iommu_error: * * allocates a new rx skb, iommu-maps it and attaches it to the descriptor. * Activate the descriptor state-wise + * + * Gelic RX sk_buffs must be aligned to GELIC_NET_RXBUF_ALIGN and the length + * must be a multiple of GELIC_NET_RXBUF_ALIGN. */ static int gelic_descr_prepare_rx(struct gelic_card *card, struct gelic_descr *descr) { + static const unsigned int rx_skb_size = + ALIGN(GELIC_NET_MAX_FRAME, GELIC_NET_RXBUF_ALIGN) + + GELIC_NET_RXBUF_ALIGN - 1; int offset; - unsigned int bufsize; if (gelic_descr_get_status(descr) != GELIC_DESCR_DMA_NOT_IN_USE) dev_info(ctodev(card), "%s: ERROR status\n", __func__); - /* we need to round up the buffer size to a multiple of 128 */ - bufsize = ALIGN(GELIC_NET_MAX_MTU, GELIC_NET_RXBUF_ALIGN); - /* and we need to have it 128 byte aligned, therefore we allocate a - * bit more */ - descr->skb = dev_alloc_skb(bufsize + GELIC_NET_RXBUF_ALIGN - 1); + descr->skb = netdev_alloc_skb(*card->netdev, rx_skb_size); if (!descr->skb) { descr->buf_addr = 0; /* tell DMAC don't touch memory */ return -ENOMEM; } - descr->buf_size = cpu_to_be32(bufsize); + descr->buf_size = cpu_to_be32(rx_skb_size); descr->dmac_cmd_status = 0; descr->result_size = 0; descr->valid_size = 0; @@ -397,7 +398,7 @@ static int gelic_descr_prepare_rx(struct gelic_card *card, /* io-mmu-map the skb */ descr->buf_addr = cpu_to_be32(dma_map_single(ctodev(card), descr->skb->data, - GELIC_NET_MAX_MTU, + GELIC_NET_MAX_FRAME, DMA_FROM_DEVICE)); if (!descr->buf_addr) { dev_kfree_skb_any(descr->skb); @@ -915,7 +916,7 @@ static void gelic_net_pass_skb_up(struct gelic_descr *descr, data_error = be32_to_cpu(descr->data_error); /* unmap skb buffer */ dma_unmap_single(ctodev(card), be32_to_cpu(descr->buf_addr), - GELIC_NET_MAX_MTU, + GELIC_NET_MAX_FRAME, DMA_FROM_DEVICE); skb_put(skb, be32_to_cpu(descr->valid_size)? diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h index 68f324ed4eaf..0d98defb011e 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h @@ -19,8 +19,9 @@ #define GELIC_NET_RX_DESCRIPTORS 128 /* num of descriptors */ #define GELIC_NET_TX_DESCRIPTORS 128 /* num of descriptors */ -#define GELIC_NET_MAX_MTU VLAN_ETH_FRAME_LEN -#define GELIC_NET_MIN_MTU VLAN_ETH_ZLEN +#define GELIC_NET_MAX_FRAME 2312 +#define GELIC_NET_MAX_MTU 2294 +#define GELIC_NET_MIN_MTU 64 #define GELIC_NET_RXBUF_ALIGN 128 #define GELIC_CARD_RX_CSUM_DEFAULT 1 /* hw chksum */ #define GELIC_NET_WATCHDOG_TIMEOUT 5*HZ From 56e0bc4a72a09761ce438c0b38f5263a51582660 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Sat, 18 Mar 2023 17:39:16 +0000 Subject: [PATCH 2301/4345] net/ps3_gelic_net: Use dma_mapping_error [ Upstream commit bebe933d35a63d4f042fbf4dce4f22e689ba0fcd ] The current Gelic Etherenet driver was checking the return value of its dma_map_single call, and not using the dma_mapping_error() routine. Fixes runtime problems like these: DMA-API: ps3_gelic_driver sb_05: device driver failed to check map error WARNING: CPU: 0 PID: 0 at kernel/dma/debug.c:1027 .check_unmap+0x888/0x8dc Fixes: 02c1889166b4 ("ps3: gigabit ethernet driver for PS3, take3") Reviewed-by: Alexander Duyck Signed-off-by: Geoff Levand Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/toshiba/ps3_gelic_net.c | 26 +++++++++++--------- 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c index 013011285dd0..524098a7b658 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c @@ -317,15 +317,17 @@ static int gelic_card_init_chain(struct gelic_card *card, /* set up the hardware pointers in each descriptor */ for (i = 0; i < no; i++, descr++) { - gelic_descr_set_status(descr, GELIC_DESCR_DMA_NOT_IN_USE); - descr->bus_addr = - dma_map_single(ctodev(card), descr, - GELIC_DESCR_SIZE, - DMA_BIDIRECTIONAL); + dma_addr_t cpu_addr; - if (!descr->bus_addr) + gelic_descr_set_status(descr, GELIC_DESCR_DMA_NOT_IN_USE); + + cpu_addr = dma_map_single(ctodev(card), descr, + GELIC_DESCR_SIZE, DMA_BIDIRECTIONAL); + + if (dma_mapping_error(ctodev(card), cpu_addr)) goto iommu_error; + descr->bus_addr = cpu_to_be32(cpu_addr); descr->next = descr + 1; descr->prev = descr - 1; } @@ -375,6 +377,7 @@ static int gelic_descr_prepare_rx(struct gelic_card *card, static const unsigned int rx_skb_size = ALIGN(GELIC_NET_MAX_FRAME, GELIC_NET_RXBUF_ALIGN) + GELIC_NET_RXBUF_ALIGN - 1; + dma_addr_t cpu_addr; int offset; if (gelic_descr_get_status(descr) != GELIC_DESCR_DMA_NOT_IN_USE) @@ -396,11 +399,10 @@ static int gelic_descr_prepare_rx(struct gelic_card *card, if (offset) skb_reserve(descr->skb, GELIC_NET_RXBUF_ALIGN - offset); /* io-mmu-map the skb */ - descr->buf_addr = cpu_to_be32(dma_map_single(ctodev(card), - descr->skb->data, - GELIC_NET_MAX_FRAME, - DMA_FROM_DEVICE)); - if (!descr->buf_addr) { + cpu_addr = dma_map_single(ctodev(card), descr->skb->data, + GELIC_NET_MAX_FRAME, DMA_FROM_DEVICE); + descr->buf_addr = cpu_to_be32(cpu_addr); + if (dma_mapping_error(ctodev(card), cpu_addr)) { dev_kfree_skb_any(descr->skb); descr->skb = NULL; dev_info(ctodev(card), @@ -780,7 +782,7 @@ static int gelic_descr_prepare_tx(struct gelic_card *card, buf = dma_map_single(ctodev(card), skb->data, skb->len, DMA_TO_DEVICE); - if (!buf) { + if (dma_mapping_error(ctodev(card), buf)) { dev_err(ctodev(card), "dma map 2 failed (%p, %i). Dropping packet\n", skb->data, skb->len); From ec23a669decaef2d9531b8c5e1f5d2ea5b85c55e Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Wed, 15 Mar 2023 22:54:08 +0900 Subject: [PATCH 2302/4345] bootconfig: Fix testcase to increase max node [ Upstream commit b69245126a48e50882021180fa5d264dc7149ccc ] Since commit 6c40624930c5 ("bootconfig: Increase max nodes of bootconfig from 1024 to 8192 for DCC support") increased the max number of bootconfig node to 8192, the bootconfig testcase of the max number of nodes fails. To fix this issue, we can not simply increase the number in the test script because the test bootconfig file becomes too big (>32KB). To fix that, we can use a combination of three alphabets (26^3 = 17576). But with that, we can not express the 8193 (just one exceed from the limitation) because it also exceeds the max size of bootconfig. So, the first 26 nodes will just use one alphabet. With this fix, test-bootconfig.sh passes all tests. Link: https://lore.kernel.org/all/167888844790.791176.670805252426835131.stgit@devnote2/ Reported-by: Heinz Wiesinger Link: https://lore.kernel.org/all/2463802.XAFRqVoOGU@amaterasu.liwjatan.org Fixes: 6c40624930c5 ("bootconfig: Increase max nodes of bootconfig from 1024 to 8192 for DCC support") Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- tools/bootconfig/test-bootconfig.sh | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index baed891d0ba4..e36f178f7dcb 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -87,10 +87,14 @@ xfail grep -i "error" $OUTFILE echo "Max node number check" -echo -n > $TEMPCONF -for i in `seq 1 1024` ; do - echo "node$i" >> $TEMPCONF -done +awk ' +BEGIN { + for (i = 0; i < 26; i += 1) + printf("%c\n", 65 + i % 26) + for (i = 26; i < 8192; i += 1) + printf("%c%c%c\n", 65 + i % 26, 65 + (i / 26) % 26, 65 + (i / 26 / 26)) +} +' > $TEMPCONF xpass $BOOTCONF -a $TEMPCONF $INITRD echo "badnode" >> $TEMPCONF From a44e98abcca49e3d6af4f0c9b6fcfc0e98039d99 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Mar 2023 15:15:18 +0000 Subject: [PATCH 2303/4345] keys: Do not cache key in task struct if key is requested from kernel thread [ Upstream commit 47f9e4c924025c5be87959d3335e66fcbb7f6b5c ] The key which gets cached in task structure from a kernel thread does not get invalidated even after expiry. Due to which, a new key request from kernel thread will be served with the cached key if it's present in task struct irrespective of the key validity. The change is to not cache key in task_struct when key requested from kernel thread so that kernel thread gets a valid key on every key request. The problem has been seen with the cifs module doing DNS lookups from a kernel thread and the results getting pinned by being attached to that kernel thread's cache - and thus not something that can be easily got rid of. The cache would ordinarily be cleared by notify-resume, but kernel threads don't do that. This isn't seen with AFS because AFS is doing request_key() within the kernel half of a user thread - which will do notify-resume. Fixes: 7743c48e54ee ("keys: Cache result of request_key*() temporarily in task_struct") Signed-off-by: Bharath SM Signed-off-by: David Howells Reviewed-by: Jarkko Sakkinen cc: Shyam Prasad N cc: Steve French cc: keyrings@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/CAGypqWw951d=zYRbdgNR4snUDvJhWL=q3=WOyh7HhSJupjz2vA@mail.gmail.com/ Signed-off-by: Sasha Levin --- security/keys/request_key.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 2da4404276f0..07a0ef2baacd 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -38,9 +38,12 @@ static void cache_requested_key(struct key *key) #ifdef CONFIG_KEYS_REQUEST_CACHE struct task_struct *t = current; - key_put(t->cached_requested_key); - t->cached_requested_key = key_get(key); - set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); + /* Do not cache key if it is a kernel thread */ + if (!(t->flags & PF_KTHREAD)) { + key_put(t->cached_requested_key); + t->cached_requested_key = key_get(key); + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); + } #endif } From a4bbab27c4bf69486f5846d44134eb31c37e9b22 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 20 Mar 2023 15:37:25 +0100 Subject: [PATCH 2304/4345] bpf: Adjust insufficient default bpf_jit_limit [ Upstream commit 10ec8ca8ec1a2f04c4ed90897225231c58c124a7 ] We've seen recent AWS EKS (Kubernetes) user reports like the following: After upgrading EKS nodes from v20230203 to v20230217 on our 1.24 EKS clusters after a few days a number of the nodes have containers stuck in ContainerCreating state or liveness/readiness probes reporting the following error: Readiness probe errored: rpc error: code = Unknown desc = failed to exec in container: failed to start exec "4a11039f730203ffc003b7[...]": OCI runtime exec failed: exec failed: unable to start container process: unable to init seccomp: error loading seccomp filter into kernel: error loading seccomp filter: errno 524: unknown However, we had not been seeing this issue on previous AMIs and it only started to occur on v20230217 (following the upgrade from kernel 5.4 to 5.10) with no other changes to the underlying cluster or workloads. We tried the suggestions from that issue (sysctl net.core.bpf_jit_limit=452534528) which helped to immediately allow containers to be created and probes to execute but after approximately a day the issue returned and the value returned by cat /proc/vmallocinfo | grep bpf_jit | awk '{s+=$2} END {print s}' was steadily increasing. I tested bpf tree to observe bpf_jit_charge_modmem, bpf_jit_uncharge_modmem their sizes passed in as well as bpf_jit_current under tcpdump BPF filter, seccomp BPF and native (e)BPF programs, and the behavior all looks sane and expected, that is nothing "leaking" from an upstream perspective. The bpf_jit_limit knob was originally added in order to avoid a situation where unprivileged applications loading BPF programs (e.g. seccomp BPF policies) consuming all the module memory space via BPF JIT such that loading of kernel modules would be prevented. The default limit was defined back in 2018 and while good enough back then, we are generally seeing far more BPF consumers today. Adjust the limit for the BPF JIT pool from originally 1/4 to now 1/2 of the module memory space to better reflect today's needs and avoid more users running into potentially hard to debug issues. Fixes: fdadd04931c2 ("bpf: fix bpf_jit_limit knob for PAGE_SIZE >= 64K") Reported-by: Stephen Haynes Reported-by: Lefteris Alexakis Signed-off-by: Daniel Borkmann Link: https://github.com/awslabs/amazon-eks-ami/issues/1179 Link: https://github.com/awslabs/amazon-eks-ami/issues/1219 Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230320143725.8394-1-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 73d4b1e32fbd..d3f6a070875c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -826,7 +826,7 @@ static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); - bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2, + bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1, PAGE_SIZE), LONG_MAX); return 0; } From 18cead61e437f4c7898acca0a5f3df12f801d97f Mon Sep 17 00:00:00 2001 From: Lama Kayal Date: Tue, 31 Jan 2023 14:07:03 +0200 Subject: [PATCH 2305/4345] net/mlx5: Fix steering rules cleanup [ Upstream commit 922f56e9a795d6f3dd72d3428ebdd7ee040fa855 ] vport's mc, uc and multicast rules are not deleted in teardown path when EEH happens. Since the vport's promisc settings(uc, mc and all) in firmware are reset after EEH, mlx5 driver will try to delete the above rules in the initialization path. This cause kernel crash because these software rules are no longer valid. Fix by nullifying these rules right after delete to avoid accessing any dangling pointers. Call Trace: __list_del_entry_valid+0xcc/0x100 (unreliable) tree_put_node+0xf4/0x1b0 [mlx5_core] tree_remove_node+0x30/0x70 [mlx5_core] mlx5_del_flow_rules+0x14c/0x1f0 [mlx5_core] esw_apply_vport_rx_mode+0x10c/0x200 [mlx5_core] esw_update_vport_rx_mode+0xb4/0x180 [mlx5_core] esw_vport_change_handle_locked+0x1ec/0x230 [mlx5_core] esw_enable_vport+0x130/0x260 [mlx5_core] mlx5_eswitch_enable_sriov+0x2a0/0x2f0 [mlx5_core] mlx5_device_enable_sriov+0x74/0x440 [mlx5_core] mlx5_load_one+0x114c/0x1550 [mlx5_core] mlx5_pci_resume+0x68/0xf0 [mlx5_core] eeh_report_resume+0x1a4/0x230 eeh_pe_dev_traverse+0x98/0x170 eeh_handle_normal_event+0x3e4/0x640 eeh_handle_event+0x4c/0x370 eeh_event_handler+0x14c/0x210 kthread+0x168/0x1b0 ret_from_kernel_thread+0x5c/0x84 Fixes: a35f71f27a61 ("net/mlx5: E-Switch, Implement promiscuous rx modes vf request handling") Signed-off-by: Huy Nguyen Signed-off-by: Lama Kayal Reviewed-by: Tariq Toukan Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 78cc6f0bbc72..3ae082c72a2b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1339,6 +1339,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, u16 vport_num) */ esw_vport_change_handle_locked(vport); vport->enabled_events = 0; + esw_apply_vport_rx_mode(esw, vport, false, false); esw_vport_cleanup(esw, vport); esw->enabled_vports--; From 265101aea4c0939f4f916412d0c5469a088f2b7c Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Wed, 15 Mar 2023 11:04:38 +0200 Subject: [PATCH 2306/4345] net/mlx5: Read the TC mapping of all priorities on ETS query [ Upstream commit 44d553188c38ac74b799dfdcebafef2f7bb70942 ] When ETS configurations are queried by the user to get the mapping assignment between packet priority and traffic class, only priorities up to maximum TCs are queried from QTCT register in FW to retrieve their assigned TC, leaving the rest of the priorities mapped to the default TC #0 which might be misleading. Fix by querying the TC mapping of all priorities on each ETS query, regardless of the maximum number of TCs configured in FW. Fixes: 820c2c5e773d ("net/mlx5e: Read ETS settings directly from firmware") Signed-off-by: Maher Sanalla Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 7c0ae7c38eef..c25fb0cbde27 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -117,12 +117,14 @@ static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, if (!MLX5_CAP_GEN(priv->mdev, ets)) return -EOPNOTSUPP; - ets->ets_cap = mlx5_max_tc(priv->mdev) + 1; - for (i = 0; i < ets->ets_cap; i++) { + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { err = mlx5_query_port_prio_tc(mdev, i, &ets->prio_tc[i]); if (err) return err; + } + ets->ets_cap = mlx5_max_tc(priv->mdev) + 1; + for (i = 0; i < ets->ets_cap; i++) { err = mlx5_query_port_tc_group(mdev, i, &tc_group[i]); if (err) return err; From 5eadc80328298ef7beaaf0cd96791667d3b485ca Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 27 Feb 2023 14:16:10 +0300 Subject: [PATCH 2307/4345] net/mlx5: E-Switch, Fix an Oops in error handling code [ Upstream commit 640fcdbcf27fc62de9223f958ceb4e897a00e791 ] The error handling dereferences "vport". There is nothing we can do if it is an error pointer except returning the error code. Fixes: 133dcfc577ea ("net/mlx5: E-Switch, Alloc and free unique metadata for match") Signed-off-by: Dan Carpenter Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c index 548c005ea633..90a10230bf0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c @@ -301,8 +301,7 @@ int mlx5_esw_acl_ingress_vport_bond_update(struct mlx5_eswitch *esw, u16 vport_n if (WARN_ON_ONCE(IS_ERR(vport))) { esw_warn(esw->dev, "vport(%d) invalid!\n", vport_num); - err = PTR_ERR(vport); - goto out; + return PTR_ERR(vport); } esw_acl_ingress_ofld_rules_destroy(esw, vport); From 19aa85b9df487801bfb2d14281797d72d1830e6f Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Mon, 20 Mar 2023 14:33:18 +0000 Subject: [PATCH 2308/4345] atm: idt77252: fix kmemleak when rmmod idt77252 [ Upstream commit 4fe3c88552a3fbe1944426a4506a18cdeb457b5a ] There are memory leaks reported by kmemleak: unreferenced object 0xffff888106500800 (size 128): comm "modprobe", pid 1017, jiffies 4297787785 (age 67.152s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000970ce626>] __kmem_cache_alloc_node+0x20c/0x380 [<00000000fb5f78d9>] kmalloc_trace+0x2f/0xb0 [<000000000e947e2a>] idt77252_init_one+0x2847/0x3c90 [idt77252] [<000000006efb048e>] local_pci_probe+0xeb/0x1a0 ... unreferenced object 0xffff888106500b00 (size 128): comm "modprobe", pid 1017, jiffies 4297787785 (age 67.152s) hex dump (first 32 bytes): 00 20 3d 01 80 88 ff ff 00 20 3d 01 80 88 ff ff . =...... =..... f0 23 3d 01 80 88 ff ff 00 20 3d 01 00 00 00 00 .#=...... =..... backtrace: [<00000000970ce626>] __kmem_cache_alloc_node+0x20c/0x380 [<00000000fb5f78d9>] kmalloc_trace+0x2f/0xb0 [<00000000f451c5be>] alloc_scq.constprop.0+0x4a/0x400 [idt77252] [<00000000e6313849>] idt77252_init_one+0x28cf/0x3c90 [idt77252] The root cause is traced to the vc_maps which alloced in open_card_oam() are not freed in close_card_oam(). The vc_maps are used to record open connections, so when close a vc_map in close_card_oam(), the memory should be freed. Moreover, the ubr0 is not closed when close a idt77252 device, leading to the memory leak of vc_map and scq_info. Fix them by adding kfree in close_card_oam() and implementing new close_card_ubr0() to close ubr0. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Li Zetao Reviewed-by: Francois Romieu Link: https://lore.kernel.org/r/20230320143318.2644630-1-lizetao1@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/atm/idt77252.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 82f6f1fbe9e7..a217b50439e7 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -2915,6 +2915,7 @@ close_card_oam(struct idt77252_dev *card) recycle_rx_pool_skb(card, &vc->rcv.rx_pool); } + kfree(vc); } } } @@ -2958,6 +2959,15 @@ open_card_ubr0(struct idt77252_dev *card) return 0; } +static void +close_card_ubr0(struct idt77252_dev *card) +{ + struct vc_map *vc = card->vcs[0]; + + free_scq(card, vc->scq); + kfree(vc); +} + static int idt77252_dev_open(struct idt77252_dev *card) { @@ -3007,6 +3017,7 @@ static void idt77252_dev_close(struct atm_dev *dev) struct idt77252_dev *card = dev->dev_data; u32 conf; + close_card_ubr0(card); close_card_oam(card); conf = SAR_CFG_RXPTH | /* enable receive path */ From f8cec30541f5c5cc218e9a32138d45d227727f2f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 20 Mar 2023 16:34:27 +0000 Subject: [PATCH 2309/4345] erspan: do not use skb_mac_header() in ndo_start_xmit() [ Upstream commit 8e50ed774554f93d55426039b27b1e38d7fa64d8 ] Drivers should not assume skb_mac_header(skb) == skb->data in their ndo_start_xmit(). Use skb_network_offset() and skb_transport_offset() which better describe what is needed in erspan_fb_xmit() and ip6erspan_tunnel_xmit() syzbot reported: WARNING: CPU: 0 PID: 5083 at include/linux/skbuff.h:2873 skb_mac_header include/linux/skbuff.h:2873 [inline] WARNING: CPU: 0 PID: 5083 at include/linux/skbuff.h:2873 ip6erspan_tunnel_xmit+0x1d9c/0x2d90 net/ipv6/ip6_gre.c:962 Modules linked in: CPU: 0 PID: 5083 Comm: syz-executor406 Not tainted 6.3.0-rc2-syzkaller-00866-gd4671cb96fa3 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 RIP: 0010:skb_mac_header include/linux/skbuff.h:2873 [inline] RIP: 0010:ip6erspan_tunnel_xmit+0x1d9c/0x2d90 net/ipv6/ip6_gre.c:962 Code: 04 02 41 01 de 84 c0 74 08 3c 03 0f 8e 1c 0a 00 00 45 89 b4 24 c8 00 00 00 c6 85 77 fe ff ff 01 e9 33 e7 ff ff e8 b4 27 a1 f8 <0f> 0b e9 b6 e7 ff ff e8 a8 27 a1 f8 49 8d bf f0 0c 00 00 48 b8 00 RSP: 0018:ffffc90003b2f830 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 000000000000ffff RCX: 0000000000000000 RDX: ffff888021273a80 RSI: ffffffff88e1bd4c RDI: 0000000000000003 RBP: ffffc90003b2f9d8 R08: 0000000000000003 R09: 000000000000ffff R10: 000000000000ffff R11: 0000000000000000 R12: ffff88802b28da00 R13: 00000000000000d0 R14: ffff88807e25b6d0 R15: ffff888023408000 FS: 0000555556a61300(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055e5b11eb6e8 CR3: 0000000027c1b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __netdev_start_xmit include/linux/netdevice.h:4900 [inline] netdev_start_xmit include/linux/netdevice.h:4914 [inline] __dev_direct_xmit+0x504/0x730 net/core/dev.c:4300 dev_direct_xmit include/linux/netdevice.h:3088 [inline] packet_xmit+0x20a/0x390 net/packet/af_packet.c:285 packet_snd net/packet/af_packet.c:3075 [inline] packet_sendmsg+0x31a0/0x5150 net/packet/af_packet.c:3107 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0xde/0x190 net/socket.c:747 __sys_sendto+0x23a/0x340 net/socket.c:2142 __do_sys_sendto net/socket.c:2154 [inline] __se_sys_sendto net/socket.c:2150 [inline] __x64_sys_sendto+0xe1/0x1b0 net/socket.c:2150 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f123aaa1039 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 b1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc15d12058 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f123aaa1039 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000020000040 R09: 0000000000000014 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f123aa648c0 R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000 Fixes: 1baf5ebf8954 ("erspan: auto detect truncated packets.") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230320163427.8096-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/ip_gre.c | 4 ++-- net/ipv6/ip6_gre.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 65ead8a74933..9d1a50657104 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -547,7 +547,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) truncate = true; } - nhoff = skb_network_header(skb) - skb_mac_header(skb); + nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; @@ -556,7 +556,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) int thoff; if (skb_transport_header_was_set(skb)) - thoff = skb_transport_header(skb) - skb_mac_header(skb); + thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 0010f9e54f13..2332b5b81c55 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -959,7 +959,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, truncate = true; } - nhoff = skb_network_header(skb) - skb_mac_header(skb); + nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; @@ -968,7 +968,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, int thoff; if (skb_transport_header_was_set(skb)) - thoff = skb_transport_header(skb) - skb_mac_header(skb); + thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) From 73db80dcdc20aceda0c6251f6b1289d7ae297b0d Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Tue, 21 Mar 2023 14:45:43 +1100 Subject: [PATCH 2310/4345] net/sonic: use dma_mapping_error() for error check [ Upstream commit 4107b8746d93ace135b8c4da4f19bbae81db785f ] The DMA address returned by dma_map_single() should be checked with dma_mapping_error(). Fix it accordingly. Fixes: efcce839360f ("[PATCH] macsonic/jazzsonic network drivers update") Signed-off-by: Zhang Changzhong Tested-by: Stan Johnson Signed-off-by: Finn Thain Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/6645a4b5c1e364312103f48b7b36783b94e197a2.1679370343.git.fthain@linux-m68k.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/natsemi/sonic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c index d17d1b4f2585..825356ee3492 100644 --- a/drivers/net/ethernet/natsemi/sonic.c +++ b/drivers/net/ethernet/natsemi/sonic.c @@ -292,7 +292,7 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) */ laddr = dma_map_single(lp->device, skb->data, length, DMA_TO_DEVICE); - if (!laddr) { + if (dma_mapping_error(lp->device, laddr)) { pr_err_ratelimited("%s: failed to map tx DMA buffer.\n", dev->name); dev_kfree_skb_any(skb); return NETDEV_TX_OK; @@ -509,7 +509,7 @@ static bool sonic_alloc_rb(struct net_device *dev, struct sonic_local *lp, *new_addr = dma_map_single(lp->device, skb_put(*new_skb, SONIC_RBSIZE), SONIC_RBSIZE, DMA_FROM_DEVICE); - if (!*new_addr) { + if (dma_mapping_error(lp->device, *new_addr)) { dev_kfree_skb(*new_skb); *new_skb = NULL; return false; From 3c72445dadc33fd5ab44b3987a8c59b62da6f3b1 Mon Sep 17 00:00:00 2001 From: Caleb Sander Date: Mon, 20 Mar 2023 09:57:36 -0600 Subject: [PATCH 2311/4345] nvme-tcp: fix nvme_tcp_term_pdu to match spec [ Upstream commit aa01c67de5926fdb276793180564f172c55fb0d7 ] The FEI field of C2HTermReq/H2CTermReq is 4 bytes but not 4-byte-aligned in the NVMe/TCP specification (it is located at offset 10 in the PDU). Split it into two 16-bit integers in struct nvme_tcp_term_pdu so no padding is inserted. There should also be 10 reserved bytes after. There are currently no users of this type. Fixes: fc221d05447aa6db ("nvme-tcp: Add protocol header") Reported-by: Geert Uytterhoeven Signed-off-by: Caleb Sander Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- include/linux/nvme-tcp.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index 959e0bd9a913..73364ae91689 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -114,8 +114,9 @@ struct nvme_tcp_icresp_pdu { struct nvme_tcp_term_pdu { struct nvme_tcp_hdr hdr; __le16 fes; - __le32 fei; - __u8 rsvd[8]; + __le16 feil; + __le16 feiu; + __u8 rsvd[10]; }; /** From 94ef1715d263ba3b19c55effc22e890af6bd262b Mon Sep 17 00:00:00 2001 From: Joshua Washington Date: Tue, 21 Mar 2023 10:23:32 -0700 Subject: [PATCH 2312/4345] gve: Cache link_speed value from device [ Upstream commit 68c3e4fc8628b1487c965aabb29207249657eb5f ] The link speed is never changed for the uptime of a VM, and the current implementation sends an admin queue command for each call. Admin queue command invocations have nontrivial overhead (e.g., VM exits), which can be disruptive to users if triggered frequently. Our telemetry data shows that there are VMs that make frequent calls to this admin queue command. Caching the result of the original admin queue command would eliminate the need to send multiple admin queue commands on subsequent calls to retrieve link speed. Fixes: 7e074d5a76ca ("gve: Enable Link Speed Reporting in the driver.") Signed-off-by: Joshua Washington Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230321172332.91678-1-joshwash@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/google/gve/gve_ethtool.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index c53a04313944..e0449cc24fbd 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -510,7 +510,10 @@ static int gve_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { struct gve_priv *priv = netdev_priv(netdev); - int err = gve_adminq_report_link_speed(priv); + int err = 0; + + if (priv->link_speed == 0) + err = gve_adminq_report_link_speed(priv); cmd->base.speed = priv->link_speed; return err; From 7aa3d03e1b308b4e8d640d11f516741bc4e81c99 Mon Sep 17 00:00:00 2001 From: Liang He Date: Wed, 22 Mar 2023 14:20:57 +0800 Subject: [PATCH 2313/4345] net: mdio: thunder: Add missing fwnode_handle_put() [ Upstream commit b1de5c78ebe9858ccec9d49af2f76724f1d47e3e ] In device_for_each_child_node(), we should add fwnode_handle_put() when break out of the iteration device_for_each_child_node() as it will automatically increase and decrease the refcounter. Fixes: 379d7ac7ca31 ("phy: mdio-thunder: Add driver for Cavium Thunder SoC MDIO buses.") Signed-off-by: Liang He Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/mdio/mdio-thunder.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/mdio/mdio-thunder.c b/drivers/net/mdio/mdio-thunder.c index 822d2cdd2f35..394b864aaa37 100644 --- a/drivers/net/mdio/mdio-thunder.c +++ b/drivers/net/mdio/mdio-thunder.c @@ -104,6 +104,7 @@ static int thunder_mdiobus_pci_probe(struct pci_dev *pdev, if (i >= ARRAY_SIZE(nexus->buses)) break; } + fwnode_handle_put(fwn); return 0; err_release_regions: From 65ceb170749b65292bb70406c74cd6dd6afcc013 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Wed, 8 Mar 2023 14:31:55 +0100 Subject: [PATCH 2314/4345] Bluetooth: btqcomsmd: Fix command timeout after setting BD address [ Upstream commit 5d44ab9e204200a78ad55cdf185aa2bb109b5950 ] On most devices using the btqcomsmd driver (e.g. the DragonBoard 410c and other devices based on the Qualcomm MSM8916/MSM8909/... SoCs) the Bluetooth firmware seems to become unresponsive for a while after setting the BD address. On recent kernel versions (at least 5.17+) this often causes timeouts for subsequent commands, e.g. the HCI reset sent by the Bluetooth core during initialization: Bluetooth: hci0: Opcode 0x c03 failed: -110 Unfortunately this behavior does not seem to be documented anywhere. Experimentation suggests that the minimum necessary delay to avoid the problem is ~150us. However, to be sure add a sleep for > 1ms in case it is a bit longer on other firmware versions. Older kernel versions are likely also affected, although perhaps with slightly different errors or less probability. Side effects can easily hide the issue in most cases, e.g. unrelated incoming interrupts that cause the necessary delay. Fixes: 1511cc750c3d ("Bluetooth: Introduce Qualcomm WCNSS SMD based HCI driver") Signed-off-by: Stephan Gerhold Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/btqcomsmd.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/btqcomsmd.c b/drivers/bluetooth/btqcomsmd.c index 2acb719e596f..11c7e04bf394 100644 --- a/drivers/bluetooth/btqcomsmd.c +++ b/drivers/bluetooth/btqcomsmd.c @@ -122,6 +122,21 @@ static int btqcomsmd_setup(struct hci_dev *hdev) return 0; } +static int btqcomsmd_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) +{ + int ret; + + ret = qca_set_bdaddr_rome(hdev, bdaddr); + if (ret) + return ret; + + /* The firmware stops responding for a while after setting the bdaddr, + * causing timeouts for subsequent commands. Sleep a bit to avoid this. + */ + usleep_range(1000, 10000); + return 0; +} + static int btqcomsmd_probe(struct platform_device *pdev) { struct btqcomsmd *btq; @@ -162,7 +177,7 @@ static int btqcomsmd_probe(struct platform_device *pdev) hdev->close = btqcomsmd_close; hdev->send = btqcomsmd_send; hdev->setup = btqcomsmd_setup; - hdev->set_bdaddr = qca_set_bdaddr_rome; + hdev->set_bdaddr = btqcomsmd_set_bdaddr; ret = hci_register_dev(hdev); if (ret < 0) From 77a61df0a0e6cf9495b5524e65ffb32e06000871 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 15 Mar 2021 13:04:37 -0700 Subject: [PATCH 2315/4345] Bluetooth: L2CAP: Fix not checking for maximum number of DCID [ Upstream commit 7cf3b1dd6aa603fd80969e9e7160becf1455a0eb ] When receiving L2CAP_CREDIT_BASED_CONNECTION_REQ the remote may request more channels than allowed by the spec (10 octecs = 5 CIDs) so this checks if the number of channels is bigger than the maximum allowed and respond with an error. Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann Stable-dep-of: 9aa9d9473f15 ("Bluetooth: L2CAP: Fix responding with wrong PDU type") Signed-off-by: Sasha Levin --- include/net/bluetooth/l2cap.h | 1 + net/bluetooth/l2cap_core.c | 12 +++++++++--- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 9b8000869b07..7f9d0ab76b14 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -493,6 +493,7 @@ struct l2cap_le_credits { #define L2CAP_ECRED_MIN_MTU 64 #define L2CAP_ECRED_MIN_MPS 64 +#define L2CAP_ECRED_MAX_CID 5 struct l2cap_ecred_conn_req { __le16 psm; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index bde90df6b497..b01677882e38 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -5952,7 +5952,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, struct l2cap_ecred_conn_req *req = (void *) data; struct { struct l2cap_ecred_conn_rsp rsp; - __le16 dcid[5]; + __le16 dcid[L2CAP_ECRED_MAX_CID]; } __packed pdu; struct l2cap_chan *chan, *pchan; u16 mtu, mps; @@ -5969,6 +5969,14 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, goto response; } + cmd_len -= sizeof(*req); + num_scid = cmd_len / sizeof(u16); + + if (num_scid > ARRAY_SIZE(pdu.dcid)) { + result = L2CAP_CR_LE_INVALID_PARAMS; + goto response; + } + mtu = __le16_to_cpu(req->mtu); mps = __le16_to_cpu(req->mps); @@ -6013,8 +6021,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, } result = L2CAP_CR_LE_SUCCESS; - cmd_len -= sizeof(*req); - num_scid = cmd_len / sizeof(u16); for (i = 0; i < num_scid; i++) { u16 scid = __le16_to_cpu(req->scid[i]); From fce0e47e9ec5afa6123ca403bf2112dae59a9b84 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 8 Mar 2023 14:20:34 -0800 Subject: [PATCH 2316/4345] Bluetooth: L2CAP: Fix responding with wrong PDU type [ Upstream commit 9aa9d9473f1550d1936c31259720b3f1f4690576 ] L2CAP_ECRED_CONN_REQ shall be responded with L2CAP_ECRED_CONN_RSP not L2CAP_LE_CONN_RSP: L2CAP LE EATT Server - Reject - run Listening for connections New client connection with handle 0x002a Sending L2CAP Request from client Client received response code 0x15 Unexpected L2CAP response code (expected 0x18) L2CAP LE EATT Server - Reject - test failed > ACL Data RX: Handle 42 flags 0x02 dlen 26 LE L2CAP: Enhanced Credit Connection Request (0x17) ident 1 len 18 PSM: 39 (0x0027) MTU: 64 MPS: 64 Credits: 5 Source CID: 65 Source CID: 66 Source CID: 67 Source CID: 68 Source CID: 69 < ACL Data TX: Handle 42 flags 0x00 dlen 16 LE L2CAP: LE Connection Response (0x15) ident 1 len 8 invalid size 00 00 00 00 00 00 06 00 L2CAP LE EATT Server - Reject - run Listening for connections New client connection with handle 0x002a Sending L2CAP Request from client Client received response code 0x18 L2CAP LE EATT Server - Reject - test passed Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode") Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 133 ++++++++++++++++++++++++------------- 1 file changed, 87 insertions(+), 46 deletions(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b01677882e38..367b1dec2e75 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -710,6 +710,17 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) } EXPORT_SYMBOL_GPL(l2cap_chan_del); +static void __l2cap_chan_list_id(struct l2cap_conn *conn, u16 id, + l2cap_chan_func_t func, void *data) +{ + struct l2cap_chan *chan, *l; + + list_for_each_entry_safe(chan, l, &conn->chan_l, list) { + if (chan->ident == id) + func(chan, data); + } +} + static void __l2cap_chan_list(struct l2cap_conn *conn, l2cap_chan_func_t func, void *data) { @@ -777,23 +788,9 @@ static void l2cap_chan_le_connect_reject(struct l2cap_chan *chan) static void l2cap_chan_ecred_connect_reject(struct l2cap_chan *chan) { - struct l2cap_conn *conn = chan->conn; - struct l2cap_ecred_conn_rsp rsp; - u16 result; - - if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) - result = L2CAP_CR_LE_AUTHORIZATION; - else - result = L2CAP_CR_LE_BAD_PSM; - l2cap_state_change(chan, BT_DISCONN); - memset(&rsp, 0, sizeof(rsp)); - - rsp.result = cpu_to_le16(result); - - l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CONN_RSP, sizeof(rsp), - &rsp); + __l2cap_ecred_conn_rsp_defer(chan); } static void l2cap_chan_connect_reject(struct l2cap_chan *chan) @@ -848,7 +845,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) break; case L2CAP_MODE_EXT_FLOWCTL: l2cap_chan_ecred_connect_reject(chan); - break; + return; } } } @@ -3934,43 +3931,86 @@ void __l2cap_le_connect_rsp_defer(struct l2cap_chan *chan) &rsp); } -void __l2cap_ecred_conn_rsp_defer(struct l2cap_chan *chan) +static void l2cap_ecred_list_defer(struct l2cap_chan *chan, void *data) { - struct { - struct l2cap_ecred_conn_rsp rsp; - __le16 dcid[5]; - } __packed pdu; - struct l2cap_conn *conn = chan->conn; - u16 ident = chan->ident; - int i = 0; + int *result = data; - if (!ident) + if (*result || test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) return; - BT_DBG("chan %p ident %d", chan, ident); - - pdu.rsp.mtu = cpu_to_le16(chan->imtu); - pdu.rsp.mps = cpu_to_le16(chan->mps); - pdu.rsp.credits = cpu_to_le16(chan->rx_credits); - pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_SUCCESS); - - mutex_lock(&conn->chan_lock); - - list_for_each_entry(chan, &conn->chan_l, list) { - if (chan->ident != ident) - continue; - - /* Reset ident so only one response is sent */ - chan->ident = 0; - - /* Include all channels pending with the same ident */ - pdu.dcid[i++] = cpu_to_le16(chan->scid); + switch (chan->state) { + case BT_CONNECT2: + /* If channel still pending accept add to result */ + (*result)++; + return; + case BT_CONNECTED: + return; + default: + /* If not connected or pending accept it has been refused */ + *result = -ECONNREFUSED; + return; } +} - mutex_unlock(&conn->chan_lock); +struct l2cap_ecred_rsp_data { + struct { + struct l2cap_ecred_conn_rsp rsp; + __le16 scid[L2CAP_ECRED_MAX_CID]; + } __packed pdu; + int count; +}; - l2cap_send_cmd(conn, ident, L2CAP_ECRED_CONN_RSP, - sizeof(pdu.rsp) + i * sizeof(__le16), &pdu); +static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) +{ + struct l2cap_ecred_rsp_data *rsp = data; + + if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) + return; + + /* Reset ident so only one response is sent */ + chan->ident = 0; + + /* Include all channels pending with the same ident */ + if (!rsp->pdu.rsp.result) + rsp->pdu.rsp.dcid[rsp->count++] = cpu_to_le16(chan->scid); + else + l2cap_chan_del(chan, ECONNRESET); +} + +void __l2cap_ecred_conn_rsp_defer(struct l2cap_chan *chan) +{ + struct l2cap_conn *conn = chan->conn; + struct l2cap_ecred_rsp_data data; + u16 id = chan->ident; + int result = 0; + + if (!id) + return; + + BT_DBG("chan %p id %d", chan, id); + + memset(&data, 0, sizeof(data)); + + data.pdu.rsp.mtu = cpu_to_le16(chan->imtu); + data.pdu.rsp.mps = cpu_to_le16(chan->mps); + data.pdu.rsp.credits = cpu_to_le16(chan->rx_credits); + data.pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_SUCCESS); + + /* Verify that all channels are ready */ + __l2cap_chan_list_id(conn, id, l2cap_ecred_list_defer, &result); + + if (result > 0) + return; + + if (result < 0) + data.pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_AUTHORIZATION); + + /* Build response */ + __l2cap_chan_list_id(conn, id, l2cap_ecred_rsp_defer, &data); + + l2cap_send_cmd(conn, id, L2CAP_ECRED_CONN_RSP, + sizeof(data.pdu.rsp) + (data.count * sizeof(__le16)), + &data.pdu); } void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) @@ -6073,6 +6113,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); chan->ident = cmd->ident; + chan->mode = L2CAP_MODE_EXT_FLOWCTL; if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { l2cap_state_change(chan, BT_CONNECT2); From da3d3fdfb4d523c5da30e35a8dd90e04f0fd8962 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Thu, 9 Mar 2023 16:07:39 +0800 Subject: [PATCH 2317/4345] Bluetooth: btsdio: fix use after free bug in btsdio_remove due to unfinished work [ Upstream commit 1e9ac114c4428fdb7ff4635b45d4f46017e8916f ] In btsdio_probe, &data->work was bound with btsdio_work.In btsdio_send_frame, it was started by schedule_work. If we call btsdio_remove with an unfinished job, there may be a race condition and cause UAF bug on hdev. Fixes: ddbaf13e3609 ("[Bluetooth] Add generic driver for Bluetooth SDIO devices") Signed-off-by: Zheng Wang Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/btsdio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 199e8f7d426d..7050a16e7efe 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -352,6 +352,7 @@ static void btsdio_remove(struct sdio_func *func) BT_DBG("func %p", func); + cancel_work_sync(&data->work); if (!data) return; From f86ff88a1548ccf5a13960c0e7625ca787ea0993 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Fri, 24 Mar 2023 09:06:58 +0800 Subject: [PATCH 2318/4345] platform/chrome: cros_ec_chardev: fix kernel data leak from ioctl [ Upstream commit b20cf3f89c56b5f6a38b7f76a8128bf9f291bbd3 ] It is possible to peep kernel page's data by providing larger `insize` in struct cros_ec_command[1] when invoking EC host commands. Fix it by using zeroed memory. [1]: https://elixir.bootlin.com/linux/v6.2/source/include/linux/platform_data/cros_ec_proto.h#L74 Fixes: eda2e30c6684 ("mfd / platform: cros_ec: Miscellaneous character device to talk with the EC") Signed-off-by: Tzung-Bi Shih Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230324010658.1082361-1-tzungbi@kernel.org Signed-off-by: Sasha Levin --- drivers/platform/chrome/cros_ec_chardev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/chrome/cros_ec_chardev.c b/drivers/platform/chrome/cros_ec_chardev.c index 0de7c255254e..d6de5a294128 100644 --- a/drivers/platform/chrome/cros_ec_chardev.c +++ b/drivers/platform/chrome/cros_ec_chardev.c @@ -284,7 +284,7 @@ static long cros_ec_chardev_ioctl_xcmd(struct cros_ec_dev *ec, void __user *arg) u_cmd.insize > EC_MAX_MSG_BYTES) return -EINVAL; - s_cmd = kmalloc(sizeof(*s_cmd) + max(u_cmd.outsize, u_cmd.insize), + s_cmd = kzalloc(sizeof(*s_cmd) + max(u_cmd.outsize, u_cmd.insize), GFP_KERNEL); if (!s_cmd) return -ENOMEM; From 33c2fa39fb9e7b3346e53fba055d5cacf9af6dce Mon Sep 17 00:00:00 2001 From: Phinex Hung Date: Tue, 21 Mar 2023 14:02:23 +0800 Subject: [PATCH 2319/4345] hwmon: fix potential sensor registration fail if of_node is missing [ Upstream commit 2315332efcbe7124252f080e03b57d3d2f1f4771 ] It is not sufficient to check of_node in current device. In some cases, this would cause the sensor registration to fail. This patch looks for device's ancestors to find a valid of_node if any. Fixes: d560168b5d0f ("hwmon: (core) New hwmon registration API") Signed-off-by: Phinex Hung Link: https://lore.kernel.org/r/20230321060224.3819-1-phinex@realtek.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/hwmon.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index d649fea82999..045dc3fd7953 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -700,6 +700,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, { struct hwmon_device *hwdev; struct device *hdev; + struct device *tdev = dev; int i, err, id; /* Complain about invalid characters in hwmon name attribute */ @@ -757,7 +758,9 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, hwdev->name = name; hdev->class = &hwmon_class; hdev->parent = dev; - hdev->of_node = dev ? dev->of_node : NULL; + while (tdev && !tdev->of_node) + tdev = tdev->parent; + hdev->of_node = tdev ? tdev->of_node : NULL; hwdev->chip = chip; dev_set_drvdata(hdev, drvdata); dev_set_name(hdev, HWMON_ID_FORMAT, id); @@ -769,7 +772,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, INIT_LIST_HEAD(&hwdev->tzdata); - if (dev && dev->of_node && chip && chip->ops->read && + if (hdev->of_node && chip && chip->ops->read && chip->info[0]->type == hwmon_chip && (chip->info[0]->config[0] & HWMON_C_REGISTER_TZ)) { err = hwmon_thermal_register_sensors(hdev); From f73a88df19b7997829fd05ae9bbc62f86541d789 Mon Sep 17 00:00:00 2001 From: Frank Crawford Date: Sat, 18 Mar 2023 19:05:42 +1100 Subject: [PATCH 2320/4345] hwmon (it87): Fix voltage scaling for chips with 10.9mV ADCs [ Upstream commit 968b66ffeb7956acc72836a7797aeb7b2444ec51 ] Fix voltage scaling for chips that have 10.9mV ADCs, where scaling was not performed. Fixes: ead8080351c9 ("hwmon: (it87) Add support for IT8732F") Signed-off-by: Frank Crawford Link: https://lore.kernel.org/r/20230318080543.1226700-2-frank@crawford.emu.id.au [groeck: Update subject and description to focus on bug fix] Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/it87.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index fac9b5c68a6a..85413d3dc394 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -486,6 +486,8 @@ static const struct it87_devices it87_devices[] = { #define has_pwm_freq2(data) ((data)->features & FEAT_PWM_FREQ2) #define has_six_temp(data) ((data)->features & FEAT_SIX_TEMP) #define has_vin3_5v(data) ((data)->features & FEAT_VIN3_5V) +#define has_scaling(data) ((data)->features & (FEAT_12MV_ADC | \ + FEAT_10_9MV_ADC)) struct it87_sio_data { int sioaddr; @@ -3098,7 +3100,7 @@ static int it87_probe(struct platform_device *pdev) "Detected broken BIOS defaults, disabling PWM interface\n"); /* Starting with IT8721F, we handle scaling of internal voltages */ - if (has_12mv_adc(data)) { + if (has_scaling(data)) { if (sio_data->internal & BIT(0)) data->in_scaled |= BIT(3); /* in3 is AVCC */ if (sio_data->internal & BIT(1)) From 231cfa78ec5badd84a1a2b09465bfad1a926aba1 Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Sun, 12 Mar 2023 21:37:10 -0700 Subject: [PATCH 2321/4345] scsi: qla2xxx: Perform lockless command completion in abort path commit 0367076b0817d5c75dfb83001ce7ce5c64d803a9 upstream. While adding and removing the controller, the following call trace was observed: WARNING: CPU: 3 PID: 623596 at kernel/dma/mapping.c:532 dma_free_attrs+0x33/0x50 CPU: 3 PID: 623596 Comm: sh Kdump: loaded Not tainted 5.14.0-96.el9.x86_64 #1 RIP: 0010:dma_free_attrs+0x33/0x50 Call Trace: qla2x00_async_sns_sp_done+0x107/0x1b0 [qla2xxx] qla2x00_abort_srb+0x8e/0x250 [qla2xxx] ? ql_dbg+0x70/0x100 [qla2xxx] __qla2x00_abort_all_cmds+0x108/0x190 [qla2xxx] qla2x00_abort_all_cmds+0x24/0x70 [qla2xxx] qla2x00_abort_isp_cleanup+0x305/0x3e0 [qla2xxx] qla2x00_remove_one+0x364/0x400 [qla2xxx] pci_device_remove+0x36/0xa0 __device_release_driver+0x17a/0x230 device_release_driver+0x24/0x30 pci_stop_bus_device+0x68/0x90 pci_stop_and_remove_bus_device_locked+0x16/0x30 remove_store+0x75/0x90 kernfs_fop_write_iter+0x11c/0x1b0 new_sync_write+0x11f/0x1b0 vfs_write+0x1eb/0x280 ksys_write+0x5f/0xe0 do_syscall_64+0x5c/0x80 ? do_user_addr_fault+0x1d8/0x680 ? do_syscall_64+0x69/0x80 ? exc_page_fault+0x62/0x140 ? asm_exc_page_fault+0x8/0x30 entry_SYSCALL_64_after_hwframe+0x44/0xae The command was completed in the abort path during driver unload with a lock held, causing the warning in abort path. Hence complete the command without any lock held. Reported-by: Lin Li Tested-by: Lin Li Cc: stable@vger.kernel.org Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230313043711.13500-2-njavali@marvell.com Reviewed-by: Himanshu Madhani Reviewed-by: John Meneghini Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_os.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index e1132970f189..38b8ff87ec0a 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1762,6 +1762,17 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) { sp = req->outstanding_cmds[cnt]; if (sp) { + /* + * perform lockless completion during driver unload + */ + if (qla2x00_chip_is_down(vha)) { + req->outstanding_cmds[cnt] = NULL; + spin_unlock_irqrestore(qp->qp_lock_ptr, flags); + sp->done(sp, res); + spin_lock_irqsave(qp->qp_lock_ptr, flags); + continue; + } + switch (sp->cmd_type) { case TYPE_SRB: qla2x00_abort_srb(qp, sp, res, &flags); From 32fa53c27ea36b62e4444e7e859a5d03f6189d9e Mon Sep 17 00:00:00 2001 From: Yaroslav Furman Date: Sun, 12 Mar 2023 11:07:45 +0200 Subject: [PATCH 2322/4345] uas: Add US_FL_NO_REPORT_OPCODES for JMicron JMS583Gen 2 commit a37eb61b6ec064ac794b8a1e89fd33eb582fe51d upstream. Just like other JMicron JMS5xx enclosures, it chokes on report-opcodes, let's avoid them. Signed-off-by: Yaroslav Furman Cc: stable Link: https://lore.kernel.org/r/20230312090745.47962-1-yaro330@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/unusual_uas.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index c7b763d6d102..1f8c9b16a0fb 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -111,6 +111,13 @@ UNUSUAL_DEV(0x152d, 0x0578, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_BROKEN_FUA), +/* Reported by: Yaroslav Furman */ +UNUSUAL_DEV(0x152d, 0x0583, 0x0000, 0x9999, + "JMicron", + "JMS583Gen 2", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_OPCODES), + /* Reported-by: Thinh Nguyen */ UNUSUAL_DEV(0x154b, 0xf00b, 0x0000, 0x9999, "PNY", From 06e04b450bb49f34d859f49c50d6609dd2008f2f Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 27 Dec 2022 11:55:26 +0200 Subject: [PATCH 2323/4345] thunderbolt: Use scale field when allocating USB3 bandwidth commit c82510b1d87bdebfe916048857d2ef46f1778aa5 upstream. When tunneling aggregated USB3 (20 Gb/s) the bandwidth values that are programmed to the ADP_USB3_CS_2 go higher than 4096 and that does not fit anymore to the 12-bit field. Fix this by scaling the value using the scale field accordingly. Fixes: 3b1d8d577ca8 ("thunderbolt: Implement USB3 bandwidth negotiation routines") Cc: stable@vger.kernel.org Signed-off-by: Mika Westerberg Signed-off-by: Greg Kroah-Hartman --- drivers/thunderbolt/usb4.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 0b3a77ade04d..5b45c45e7c5b 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -1636,18 +1636,30 @@ static int usb4_usb3_port_write_allocated_bandwidth(struct tb_port *port, int downstream_bw) { u32 val, ubw, dbw, scale; - int ret; + int ret, max_bw; - /* Read the used scale, hardware default is 0 */ - ret = tb_port_read(port, &scale, TB_CFG_PORT, - port->cap_adap + ADP_USB3_CS_3, 1); + /* Figure out suitable scale */ + scale = 0; + max_bw = max(upstream_bw, downstream_bw); + while (scale < 64) { + if (mbps_to_usb3_bw(max_bw, scale) < 4096) + break; + scale++; + } + + if (WARN_ON(scale >= 64)) + return -EINVAL; + + ret = tb_port_write(port, &scale, TB_CFG_PORT, + port->cap_adap + ADP_USB3_CS_3, 1); if (ret) return ret; - scale &= ADP_USB3_CS_3_SCALE_MASK; ubw = mbps_to_usb3_bw(upstream_bw, scale); dbw = mbps_to_usb3_bw(downstream_bw, scale); + tb_port_dbg(port, "scaled bandwidth %u/%u, scale %u\n", ubw, dbw, scale); + ret = tb_port_read(port, &val, TB_CFG_PORT, port->cap_adap + ADP_USB3_CS_2, 1); if (ret) From 2d6c2dee59a396b22fff6d708db4b167281e78c2 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 10 Mar 2023 11:20:49 -0600 Subject: [PATCH 2324/4345] thunderbolt: Use const qualifier for `ring_interrupt_index` commit 1716efdb07938bd6510e1127d02012799112c433 upstream. `ring_interrupt_index` doesn't change the data for `ring` so mark it as const. This is needed by the following patch that disables interrupt auto clear for rings. Cc: Sanju Mehta Cc: stable@vger.kernel.org Signed-off-by: Mario Limonciello Signed-off-by: Mika Westerberg Signed-off-by: Greg Kroah-Hartman --- drivers/thunderbolt/nhi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index db80dc5dfeba..fd1b59397c70 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -36,7 +36,7 @@ #define NHI_MAILBOX_TIMEOUT 500 /* ms */ -static int ring_interrupt_index(struct tb_ring *ring) +static int ring_interrupt_index(const struct tb_ring *ring) { int bit = ring->hop; if (!ring->is_tx) From 082b8240a66af84dd837e48751689e9176feb146 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Tue, 16 Mar 2021 15:34:20 -0400 Subject: [PATCH 2325/4345] riscv: Bump COMMAND_LINE_SIZE value to 1024 [ Upstream commit 61fc1ee8be26bc192d691932b0a67eabee45d12f ] Increase COMMAND_LINE_SIZE as the current default value is too low for syzbot kernel command line. There has been considerable discussion on this patch that has led to a larger patch set removing COMMAND_LINE_SIZE from the uapi headers on all ports. That's not quite done yet, but it's gotten far enough we're confident this is not a uABI change so this is safe. Reported-by: Dmitry Vyukov Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20210316193420.904-1-alex@ghiti.fr [Palmer: it's not uabi] Link: https://lore.kernel.org/linux-riscv/874b8076-b0d1-4aaa-bcd8-05d523060152@app.fastmail.com/#t Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/include/uapi/asm/setup.h | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 arch/riscv/include/uapi/asm/setup.h diff --git a/arch/riscv/include/uapi/asm/setup.h b/arch/riscv/include/uapi/asm/setup.h new file mode 100644 index 000000000000..66b13a522880 --- /dev/null +++ b/arch/riscv/include/uapi/asm/setup.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ + +#ifndef _UAPI_ASM_RISCV_SETUP_H +#define _UAPI_ASM_RISCV_SETUP_H + +#define COMMAND_LINE_SIZE 1024 + +#endif /* _UAPI_ASM_RISCV_SETUP_H */ From 3d8fafc5308f7657f93b9514556960936c79917c Mon Sep 17 00:00:00 2001 From: Danny Kaehn Date: Fri, 10 Feb 2023 11:00:44 -0600 Subject: [PATCH 2326/4345] HID: cp2112: Fix driver not registering GPIO IRQ chip as threaded [ Upstream commit 37f5b858a66543b2b67c0288280af623985abc29 ] The CP2112 generates interrupts from a polling routine on a thread, and can only support threaded interrupts. This patch configures the gpiochip irq chip with this flag, disallowing consumers to request a hard IRQ from this driver, which resulted in a segfault previously. Signed-off-by: Danny Kaehn Link: https://lore.kernel.org/r/20230210170044.11835-1-kaehndan@gmail.com Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-cp2112.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c index 172f20e88c6c..d902fe43cb81 100644 --- a/drivers/hid/hid-cp2112.c +++ b/drivers/hid/hid-cp2112.c @@ -1352,6 +1352,7 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id) girq->parents = NULL; girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_simple_irq; + girq->threaded = true; ret = gpiochip_add_data(&dev->gc, dev); if (ret < 0) { From 7df72bedbdd1d02bb216e1f6eca0a16900238c4e Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 16 Feb 2023 23:25:04 -0500 Subject: [PATCH 2327/4345] ca8210: fix mac_len negative array access [ Upstream commit 6c993779ea1d0cccdb3a5d7d45446dd229e610a3 ] This patch fixes a buffer overflow access of skb->data if ieee802154_hdr_peek_addrs() fails. Reported-by: lianhui tang Signed-off-by: Alexander Aring Link: https://lore.kernel.org/r/20230217042504.3303396-1-aahringo@redhat.com Signed-off-by: Stefan Schmidt Signed-off-by: Sasha Levin --- drivers/net/ieee802154/ca8210.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 95ef3b6f98dd..5beb447529f9 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -1956,6 +1956,8 @@ static int ca8210_skb_tx( * packet */ mac_len = ieee802154_hdr_peek_addrs(skb, &header); + if (mac_len < 0) + return mac_len; secspec.security_level = header.sec.level; secspec.key_id_mode = header.sec.key_id_mode; From df1da53a7e98f0b2a0eb2241c154f148f2f2c1d8 Mon Sep 17 00:00:00 2001 From: Michael Schmitz Date: Wed, 1 Mar 2023 15:11:07 +1300 Subject: [PATCH 2328/4345] m68k: Only force 030 bus error if PC not in exception table [ Upstream commit e36a82bebbf7da814530d5a179bef9df5934b717 ] __get_kernel_nofault() does copy data in supervisor mode when forcing a task backtrace log through /proc/sysrq_trigger. This is expected cause a bus error exception on e.g. NULL pointer dereferencing when logging a kernel task has no workqueue associated. This bus error ought to be ignored. Our 030 bus error handler is ill equipped to deal with this: Whenever ssw indicates a kernel mode access on a data fault, we don't even attempt to handle the fault and instead always send a SEGV signal (or panic). As a result, the check for exception handling at the fault PC (buried in send_sig_fault() which gets called from do_page_fault() eventually) is never used. In contrast, both 040 and 060 access error handlers do not care whether a fault happened on supervisor mode access, and will call do_page_fault() on those, ultimately honoring the exception table. Add a check in bus_error030 to call do_page_fault() in case we do have an entry for the fault PC in our exception table. I had attempted a fix for this earlier in 2019 that did rely on testing pagefault_disabled() (see link below) to achieve the same thing, but this patch should be more generic. Tested on 030 Atari Falcon. Reported-by: Eero Tamminen Link: https://lore.kernel.org/r/alpine.LNX.2.21.1904091023540.25@nippy.intranet Link: https://lore.kernel.org/r/63130691-1984-c423-c1f2-73bfd8d3dcd3@gmail.com Signed-off-by: Michael Schmitz Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230301021107.26307-1-schmitzmic@gmail.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- arch/m68k/kernel/traps.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index b2a31afb998c..7d42c84649ac 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -549,7 +550,8 @@ static inline void bus_error030 (struct frame *fp) errorcode |= 2; if (mmusr & (MMU_I | MMU_WP)) { - if (ssw & 4) { + /* We might have an exception table for this PC */ + if (ssw & 4 && !search_exception_tables(fp->ptregs.pc)) { pr_err("Data %s fault at %#010lx in %s (pc=%#lx)\n", ssw & RW ? "read" : "write", fp->un.fmtb.daddr, From 8c42442887db59ac4b67aeaf8825d1192bc783d6 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 6 Mar 2023 11:21:38 +0000 Subject: [PATCH 2329/4345] selftests/bpf: check that modifier resolves after pointer [ Upstream commit dfdd608c3b365f0fd49d7e13911ebcde06b9865b ] Add a regression test that ensures that a VAR pointing at a modifier which follows a PTR (or STRUCT or ARRAY) is resolved correctly by the datasec validator. Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230306112138.155352-3-lmb@isovalent.com Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/prog_tests/btf.c | 28 ++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 48b01150e703..28d22265b825 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -882,6 +882,34 @@ static struct btf_raw_test raw_tests[] = { .btf_load_err = true, .err_str = "Invalid elem", }, +{ + .descr = "var after datasec, ptr followed by modifier", + .raw_types = { + /* .bss section */ /* [1] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), + sizeof(void*)+4), + BTF_VAR_SECINFO_ENC(4, 0, sizeof(void*)), + BTF_VAR_SECINFO_ENC(6, sizeof(void*), 4), + /* int */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int* */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), + BTF_VAR_ENC(NAME_TBD, 3, 0), /* [4] */ + /* const int */ /* [5] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 2), + BTF_VAR_ENC(NAME_TBD, 5, 0), /* [6] */ + BTF_END_RAW, + }, + .str_sec = "\0a\0b\0c\0", + .str_sec_size = sizeof("\0a\0b\0c\0"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = ".bss", + .key_size = sizeof(int), + .value_size = sizeof(void*)+4, + .key_type_id = 0, + .value_type_id = 1, + .max_entries = 1, +}, /* Test member exceeds the size of struct. * * struct A { From 799d29a447dc2461a537fc8edeb44f9cfd630936 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Tue, 14 Feb 2023 15:15:56 +0100 Subject: [PATCH 2330/4345] scsi: target: iscsi: Fix an error message in iscsi_check_key() [ Upstream commit 6cc55c969b7ce8d85e09a636693d4126c3676c11 ] The first half of the error message is printed by pr_err(), the second half is printed by pr_debug(). The user will therefore see only the first part of the message and will miss some useful information. Link: https://lore.kernel.org/r/20230214141556.762047-1-mlombard@redhat.com Signed-off-by: Maurizio Lombardi Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/iscsi/iscsi_target_parameters.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index 7a461fbb1566..31cd3c02e517 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -1262,18 +1262,20 @@ static struct iscsi_param *iscsi_check_key( return param; if (!(param->phase & phase)) { - pr_err("Key \"%s\" may not be negotiated during ", - param->name); + char *phase_name; + switch (phase) { case PHASE_SECURITY: - pr_debug("Security phase.\n"); + phase_name = "Security"; break; case PHASE_OPERATIONAL: - pr_debug("Operational phase.\n"); + phase_name = "Operational"; break; default: - pr_debug("Unknown phase.\n"); + phase_name = "Unknown"; } + pr_err("Key \"%s\" may not be negotiated during %s phase.\n", + param->name, phase_name); return NULL; } From 522314863f7820f49ea80a8fb9d9e5526a578d9a Mon Sep 17 00:00:00 2001 From: Kang Chen Date: Mon, 27 Feb 2023 11:10:30 +0800 Subject: [PATCH 2331/4345] scsi: hisi_sas: Check devm_add_action() return value [ Upstream commit 06d1a90de60208054cca15ef200138cfdbb642a9 ] In case devm_add_action() fails, check it in the caller of interrupt_preinit_v3_hw(). Link: https://lore.kernel.org/r/20230227031030.893324-1-void0red@gmail.com Signed-off-by: Kang Chen Acked-by: Xiang Chen Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index cd41dc061d87..65971bd80186 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2402,8 +2402,7 @@ static int interrupt_preinit_v3_hw(struct hisi_hba *hisi_hba) hisi_hba->cq_nvecs = vectors - BASE_VECTORS_V3_HW; shost->nr_hw_queues = hisi_hba->cq_nvecs; - devm_add_action(&pdev->dev, hisi_sas_v3_free_vectors, pdev); - return 0; + return devm_add_action(&pdev->dev, hisi_sas_v3_free_vectors, pdev); } static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba) From f9a937f75ba2faf41b5acb1603f5ccf3c64b1e82 Mon Sep 17 00:00:00 2001 From: Adrien Thierry Date: Mon, 20 Feb 2023 09:07:40 -0500 Subject: [PATCH 2332/4345] scsi: ufs: core: Add soft dependency on governor_simpleondemand [ Upstream commit 2ebe16155dc8bd4e602cad5b5f65458d2eaa1a75 ] The ufshcd driver uses simpleondemand governor for devfreq. Add it to the list of ufshcd softdeps to allow userspace initramfs tools like dracut to automatically pull the governor module into the initramfs together with UFS drivers. Link: https://lore.kernel.org/r/20230220140740.14379-1-athierry@redhat.com Signed-off-by: Adrien Thierry Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/ufs/ufshcd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index ea6ceab1a1b2..f3389e913179 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -9311,5 +9311,6 @@ EXPORT_SYMBOL_GPL(ufshcd_init); MODULE_AUTHOR("Santosh Yaragnavi "); MODULE_AUTHOR("Vinayak Holikatti "); MODULE_DESCRIPTION("Generic UFS host controller driver Core"); +MODULE_SOFTDEP("pre: governor_simpleondemand"); MODULE_LICENSE("GPL"); MODULE_VERSION(UFSHCD_DRIVER_VERSION); From 3e0a423a55a75a27537084ab9b2edae32b3df2b8 Mon Sep 17 00:00:00 2001 From: Jakob Koschel Date: Wed, 1 Mar 2023 18:19:14 +0100 Subject: [PATCH 2333/4345] scsi: lpfc: Avoid usage of list iterator variable after loop [ Upstream commit 2850b23e9f9ae3696e472d2883ea1b43aafa884e ] If the &epd_pool->list is empty when executing lpfc_get_io_buf_from_expedite_pool() the function would return an invalid pointer. Even in the case if the list is guaranteed to be populated, the iterator variable should not be used after the loop to be more robust for future changes. Linus proposed to avoid any use of the list iterator variable after the loop, in the attempt to move the list iterator variable declaration into the macro to avoid any potential misuse after the loop [1]. Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ [1] Signed-off-by: Jakob Koschel Link: https://lore.kernel.org/r/20230301-scsi-lpfc-avoid-list-iterator-after-loop-v1-1-325578ae7561@gmail.com Reviewed-by: Justin Tee Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_sli.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 755d68b98160..923ceaba0bf3 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -20816,20 +20816,20 @@ lpfc_get_io_buf_from_private_pool(struct lpfc_hba *phba, static struct lpfc_io_buf * lpfc_get_io_buf_from_expedite_pool(struct lpfc_hba *phba) { - struct lpfc_io_buf *lpfc_ncmd; + struct lpfc_io_buf *lpfc_ncmd = NULL, *iter; struct lpfc_io_buf *lpfc_ncmd_next; unsigned long iflag; struct lpfc_epd_pool *epd_pool; epd_pool = &phba->epd_pool; - lpfc_ncmd = NULL; spin_lock_irqsave(&epd_pool->lock, iflag); if (epd_pool->count > 0) { - list_for_each_entry_safe(lpfc_ncmd, lpfc_ncmd_next, + list_for_each_entry_safe(iter, lpfc_ncmd_next, &epd_pool->list, list) { - list_del(&lpfc_ncmd->list); + list_del(&iter->list); epd_pool->count--; + lpfc_ncmd = iter; break; } } From ddfc061793385d7342997c6868a5c9638f1550c8 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 27 Feb 2023 08:48:34 -0800 Subject: [PATCH 2334/4345] scsi: storvsc: Handle BlockSize change in Hyper-V VHD/VHDX file [ Upstream commit 11d9874c4204a785f43d899a1ab12f9dc8d9de3e ] Hyper-V uses a VHD or VHDX file on the host as the underlying storage for a virtual disk. The VHD/VHDX file format is a sparse format where real disk space on the host is assigned in chunks that the VHD/VHDX file format calls the BlockSize. This BlockSize is not to be confused with the 512-byte (or 4096-byte) sector size of the underlying storage device. The default block size for a new VHD/VHDX file is 32 Mbytes. When a guest VM touches any disk space within a 32 Mbyte chunk of the VHD/VHDX file, Hyper-V allocates 32 Mbytes of real disk space for that section of the VHD/VHDX. Similarly, if a discard operation is done that covers an entire 32 Mbyte chunk, Hyper-V will free the real disk space for that portion of the VHD/VHDX. This BlockSize is surfaced in Linux as the "discard_granularity" in /sys/block/sd/queue, which makes sense. Hyper-V also has differencing disks that can overlay a VHD/VHDX file to capture changes to the VHD/VHDX while preserving the original VHD/VHDX. One example of this differencing functionality is for VM snapshots. When a snapshot is created, a differencing disk is created. If the snapshot is rolled back, Hyper-V can just delete the differencing disk, and the VM will see the original disk contents at the time the snapshot was taken. Differencing disks are used in other scenarios as well. The BlockSize for a differencing disk defaults to 2 Mbytes, not 32 Mbytes. The smaller default is used because changes to differencing disks are typically scattered all over, and Hyper-V doesn't want to allocate 32 Mbytes of real disk space for a stray write here or there. The smaller BlockSize provides more efficient use of real disk space. When a differencing disk is added to a VHD/VHDX, Hyper-V reports UNIT_ATTENTION with a sense code indicating "Operating parameters have changed", because the value of discard_granularity should be changed to 2 Mbytes. When the differencing disk is removed, discard_granularity should be changed back to 32 Mbytes. However, current code simply reports a message from scsi_report_sense() and the value of /sys/block/sd/queue/discard_granularity is not updated. The message isn't very actionable by a sysadmin. Fix this by having the storvsc driver check for the sense code indicating that the underly VHD/VHDX block size has changed, and do a rescan of the device to pick up the new discard_granularity. With this change the entire transition to/from differencing disks is handled automatically and transparently, with no confusing messages being output. Link: https://lore.kernel.org/r/1677516514-86060-1-git-send-email-mikelley@microsoft.com Signed-off-by: Michael Kelley Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/storvsc_drv.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 3fa8a0c94bdc..e38aebcabb26 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1013,6 +1013,22 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, goto do_work; } + /* + * Check for "Operating parameters have changed" + * due to Hyper-V changing the VHD/VHDX BlockSize + * when adding/removing a differencing disk. This + * causes discard_granularity to change, so do a + * rescan to pick up the new granularity. We don't + * want scsi_report_sense() to output a message + * that a sysadmin wouldn't know what to do with. + */ + if ((asc == 0x3f) && (ascq != 0x03) && + (ascq != 0x0e)) { + process_err_fn = storvsc_device_scan; + set_host_byte(scmnd, DID_REQUEUE); + goto do_work; + } + /* * Otherwise, let upper layer deal with the * error when sense message is present From 27d4ce4aa3bbf02e839f812843d0c183ac20061d Mon Sep 17 00:00:00 2001 From: Enrico Sau Date: Mon, 6 Mar 2023 12:59:33 +0100 Subject: [PATCH 2335/4345] net: usb: cdc_mbim: avoid altsetting toggling for Telit FE990 [ Upstream commit 418383e6ed6b4624a54ec05c535f13d184fbf33b ] Add quirk CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE for Telit FE990 0x1081 composition in order to avoid bind error. Signed-off-by: Enrico Sau Link: https://lore.kernel.org/r/20230306115933.198259-1-enrico.sau@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/usb/cdc_mbim.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index 414341c9cf5a..6ad1fb00a35c 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -663,6 +663,11 @@ static const struct usb_device_id mbim_devs[] = { .driver_info = (unsigned long)&cdc_mbim_info_avoid_altsetting_toggle, }, + /* Telit FE990 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1bc7, 0x1081, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&cdc_mbim_info_avoid_altsetting_toggle, + }, + /* default entry */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info_zlp, From 87e800e3dc77e3a2b48f105e97bb75f864c65b71 Mon Sep 17 00:00:00 2001 From: Enrico Sau Date: Mon, 6 Mar 2023 13:05:28 +0100 Subject: [PATCH 2336/4345] net: usb: qmi_wwan: add Telit 0x1080 composition [ Upstream commit 382e363d5bed0cec5807b35761d14e55955eee63 ] Add the following Telit FE990 composition: 0x1080: tty, adb, rmnet, tty, tty, tty, tty Signed-off-by: Enrico Sau Link: https://lore.kernel.org/r/20230306120528.198842-1-enrico.sau@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index bce151e3706a..070910567c44 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1297,6 +1297,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ From 8beb18c25beff12f27ffeb78f4e1de31a0e7cad0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 6 Mar 2023 01:20:30 +0000 Subject: [PATCH 2337/4345] sh: sanitize the flags on sigreturn [ Upstream commit 573b22ccb7ce9ab7f0539a2e11a9d3609a8783f5 ] We fetch %SR value from sigframe; it might have been modified by signal handler, so we can't trust it with any bits that are not modifiable in user mode. Signed-off-by: Al Viro Cc: Rich Felker Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- arch/sh/include/asm/processor_32.h | 1 + arch/sh/kernel/signal_32.c | 3 +++ 2 files changed, 4 insertions(+) diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index aa92cc933889..6c7966e62775 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -50,6 +50,7 @@ #define SR_FD 0x00008000 #define SR_MD 0x40000000 +#define SR_USER_MASK 0x00000303 // M, Q, S, T bits /* * DSP structure and data */ diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index dd3092911efa..dc13702003f0 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -115,6 +115,7 @@ static int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *r0_p) { unsigned int err = 0; + unsigned int sr = regs->sr & ~SR_USER_MASK; #define COPY(x) err |= __get_user(regs->x, &sc->sc_##x) COPY(regs[1]); @@ -130,6 +131,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *r0_p COPY(sr); COPY(pc); #undef COPY + regs->sr = (regs->sr & SR_USER_MASK) | sr; + #ifdef CONFIG_SH_FPU if (boot_cpu_data.flags & CPU_HAS_FPU) { int owned_fp; From f7a4ce3514262777f1a43b793d5a7daf24d517bc Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Thu, 9 Mar 2023 13:23:29 +0000 Subject: [PATCH 2338/4345] cifs: empty interface list when server doesn't support query interfaces commit 896cd316b841053f6df95ab77b5f1322c16a8e18 upstream. When querying server interfaces returns -EOPNOTSUPP, clear the list of interfaces. Assumption is that multichannel would be disabled too. Signed-off-by: Shyam Prasad N Reviewed-by: Paulo Alcantara (SUSE) Cc: stable@vger.kernel.org Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/smb2ops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 8fdd34ff20ef..120c7cb11b02 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -593,7 +593,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) if (rc == -EOPNOTSUPP) { cifs_dbg(FYI, "server does not support query network interfaces\n"); - goto out; + ret_data_len = 0; } else if (rc != 0) { cifs_tcon_dbg(VFS, "error %d on ioctl to get interface list\n", rc); goto out; From dce128421554c7ad7c1f25a972b49c355ac2199e Mon Sep 17 00:00:00 2001 From: Joel Selvaraj Date: Sun, 12 Mar 2023 23:14:02 -0500 Subject: [PATCH 2339/4345] scsi: core: Add BLIST_SKIP_VPD_PAGES for SKhynix H28U74301AMR commit a204b490595de71016b2360a1886ec8c12d0afac upstream. Xiaomi Poco F1 (qcom/sdm845-xiaomi-beryllium*.dts) comes with a SKhynix H28U74301AMR UFS. The sd_read_cpr() operation leads to a 120 second timeout, making the device bootup very slow: [ 121.457736] sd 0:0:0:1: [sdb] tag#23 timing out command, waited 120s Setting the BLIST_SKIP_VPD_PAGES allows the device to skip the failing sd_read_cpr operation and boot normally. Signed-off-by: Joel Selvaraj Link: https://lore.kernel.org/r/20230313041402.39330-1-joelselvaraj.oss@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/scsi_devinfo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 9a8f9f902f3b..f5e121f0ee52 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -232,6 +232,7 @@ static struct { {"SGI", "RAID5", "*", BLIST_SPARSELUN}, {"SGI", "TP9100", "*", BLIST_REPORTLUN2}, {"SGI", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, + {"SKhynix", "H28U74301AMR", NULL, BLIST_SKIP_VPD_PAGES}, {"IBM", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"SUN", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"DELL", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, From 1f01027c51eb16145e8e07fafea3ca07ef102d06 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Thu, 16 Mar 2023 09:41:27 +0100 Subject: [PATCH 2340/4345] usb: dwc2: fix a devres leak in hw_enable upon suspend resume commit f747313249b74f323ddf841a9c8db14d989f296a upstream. Each time the platform goes to low power, PM suspend / resume routines call: __dwc2_lowlevel_hw_enable -> devm_add_action_or_reset(). This adds a new devres each time. This may also happen at runtime, as dwc2_lowlevel_hw_enable() can be called from udc_start(). This can be seen with tracing: - echo 1 > /sys/kernel/debug/tracing/events/dev/devres_log/enable - go to low power - cat /sys/kernel/debug/tracing/trace A new "ADD" entry is found upon each low power cycle: ... devres_log: 49000000.usb-otg ADD 82a13bba devm_action_release (8 bytes) ... devres_log: 49000000.usb-otg ADD 49889daf devm_action_release (8 bytes) ... A second issue is addressed here: - regulator_bulk_enable() is called upon each PM cycle (suspend/resume). - regulator_bulk_disable() never gets called. So the reference count for these regulators constantly increase, by one upon each low power cycle, due to missing regulator_bulk_disable() call in __dwc2_lowlevel_hw_disable(). The original fix that introduced the devm_add_action_or_reset() call, fixed an issue during probe, that happens due to other errors in dwc2_driver_probe() -> dwc2_core_reset(). Then the probe fails without disabling regulators, when dr_mode == USB_DR_MODE_PERIPHERAL. Rather fix the error path: disable all the low level hardware in the error path, by using the "hsotg->ll_hw_enabled" flag. Checking dr_mode has been introduced to avoid a dual call to dwc2_lowlevel_hw_disable(). "ll_hw_enabled" should achieve the same (and is used currently in the remove() routine). Fixes: 54c196060510 ("usb: dwc2: Always disable regulators on driver teardown") Fixes: 33a06f1300a7 ("usb: dwc2: Fix error path in gadget registration") Cc: stable Signed-off-by: Fabrice Gasnier Link: https://lore.kernel.org/r/20230316084127.126084-1-fabrice.gasnier@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/platform.c | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 8851db646ef5..9d0dd09a2015 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -121,13 +121,6 @@ static int dwc2_get_dr_mode(struct dwc2_hsotg *hsotg) return 0; } -static void __dwc2_disable_regulators(void *data) -{ - struct dwc2_hsotg *hsotg = data; - - regulator_bulk_disable(ARRAY_SIZE(hsotg->supplies), hsotg->supplies); -} - static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg) { struct platform_device *pdev = to_platform_device(hsotg->dev); @@ -138,11 +131,6 @@ static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg) if (ret) return ret; - ret = devm_add_action_or_reset(&pdev->dev, - __dwc2_disable_regulators, hsotg); - if (ret) - return ret; - if (hsotg->clk) { ret = clk_prepare_enable(hsotg->clk); if (ret) @@ -198,7 +186,7 @@ static int __dwc2_lowlevel_hw_disable(struct dwc2_hsotg *hsotg) if (hsotg->clk) clk_disable_unprepare(hsotg->clk); - return 0; + return regulator_bulk_disable(ARRAY_SIZE(hsotg->supplies), hsotg->supplies); } /** @@ -625,7 +613,7 @@ error_init: if (hsotg->params.activate_stm_id_vb_detection) regulator_disable(hsotg->usb33d); error: - if (hsotg->dr_mode != USB_DR_MODE_PERIPHERAL) + if (hsotg->ll_hw_enabled) dwc2_lowlevel_hw_disable(hsotg); return retval; } From 33f341c1fc60e172a3515c51bdabee11e83d1ee9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alvin=20=C5=A0ipraga?= Date: Thu, 2 Mar 2023 17:36:47 +0100 Subject: [PATCH 2341/4345] usb: gadget: u_audio: don't let userspace block driver unbind MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6c67ed9ad9b83e453e808f9b31a931a20a25629b upstream. In the unbind callback for f_uac1 and f_uac2, a call to snd_card_free() via g_audio_cleanup() will disconnect the card and then wait for all resources to be released, which happens when the refcount falls to zero. Since userspace can keep the refcount incremented by not closing the relevant file descriptor, the call to unbind may block indefinitely. This can cause a deadlock during reboot, as evidenced by the following blocked task observed on my machine: task:reboot state:D stack:0 pid:2827 ppid:569 flags:0x0000000c Call trace: __switch_to+0xc8/0x140 __schedule+0x2f0/0x7c0 schedule+0x60/0xd0 schedule_timeout+0x180/0x1d4 wait_for_completion+0x78/0x180 snd_card_free+0x90/0xa0 g_audio_cleanup+0x2c/0x64 afunc_unbind+0x28/0x60 ... kernel_restart+0x4c/0xac __do_sys_reboot+0xcc/0x1ec __arm64_sys_reboot+0x28/0x30 invoke_syscall+0x4c/0x110 ... The issue can also be observed by opening the card with arecord and then stopping the process through the shell before unbinding: # arecord -D hw:UAC2Gadget -f S32_LE -c 2 -r 48000 /dev/null Recording WAVE '/dev/null' : Signed 32 bit Little Endian, Rate 48000 Hz, Stereo ^Z[1]+ Stopped arecord -D hw:UAC2Gadget -f S32_LE -c 2 -r 48000 /dev/null # echo gadget.0 > /sys/bus/gadget/drivers/configfs-gadget/unbind (observe that the unbind command never finishes) Fix the problem by using snd_card_free_when_closed() instead, which will still disconnect the card as desired, but defer the task of freeing the resources to the core once userspace closes its file descriptor. Fixes: 132fcb460839 ("usb: gadget: Add Audio Class 2.0 Driver") Cc: stable@vger.kernel.org Signed-off-by: Alvin Šipraga Reviewed-by: Ruslan Bilovol Reviewed-by: John Keeping Link: https://lore.kernel.org/r/20230302163648.3349669-1-alvin@pqrs.dk Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_audio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index 95605b1ef4eb..6c8b8f5b7e0f 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -613,7 +613,7 @@ void g_audio_cleanup(struct g_audio *g_audio) uac = g_audio->uac; card = uac->card; if (card) - snd_card_free(card); + snd_card_free_when_closed(card); kfree(uac->p_prm.ureq); kfree(uac->c_prm.ureq); From e66f3039c7922cc76ec555363f3e2a4cd224397d Mon Sep 17 00:00:00 2001 From: Nathan Huckleberry Date: Fri, 10 Mar 2023 11:33:25 -0800 Subject: [PATCH 2342/4345] fsverity: Remove WQ_UNBOUND from fsverity read workqueue commit f959325e6ac3f499450088b8d9c626d1177be160 upstream. WQ_UNBOUND causes significant scheduler latency on ARM64/Android. This is problematic for latency sensitive workloads, like I/O post-processing. Removing WQ_UNBOUND gives a 96% reduction in fsverity workqueue related scheduler latency and improves app cold startup times by ~30ms. WQ_UNBOUND was also removed from the dm-verity workqueue for the same reason [1]. This code was tested by running Android app startup benchmarks and measuring how long the fsverity workqueue spent in the runnable state. Before Total workqueue scheduler latency: 553800us After Total workqueue scheduler latency: 18962us [1]: https://lore.kernel.org/all/20230202012348.885402-1-nhuck@google.com/ Signed-off-by: Nathan Huckleberry Fixes: 8a1d0f9cacc9 ("fs-verity: add data verification hooks for ->readpages()") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230310193325.620493-1-nhuck@google.com Signed-off-by: Eric Biggers Signed-off-by: Greg Kroah-Hartman --- fs/verity/verify.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/verity/verify.c b/fs/verity/verify.c index a8b68c6f663d..d3a3a359d815 100644 --- a/fs/verity/verify.c +++ b/fs/verity/verify.c @@ -279,15 +279,15 @@ EXPORT_SYMBOL_GPL(fsverity_enqueue_verify_work); int __init fsverity_init_workqueue(void) { /* - * Use an unbound workqueue to allow bios to be verified in parallel - * even when they happen to complete on the same CPU. This sacrifices - * locality, but it's worthwhile since hashing is CPU-intensive. + * Use a high-priority workqueue to prioritize verification work, which + * blocks reads from completing, over regular application tasks. * - * Also use a high-priority workqueue to prioritize verification work, - * which blocks reads from completing, over regular application tasks. + * For performance reasons, don't use an unbound workqueue. Using an + * unbound workqueue for crypto operations causes excessive scheduler + * latency on ARM64. */ fsverity_read_workqueue = alloc_workqueue("fsverity_read_queue", - WQ_UNBOUND | WQ_HIGHPRI, + WQ_HIGHPRI, num_online_cpus()); if (!fsverity_read_workqueue) return -ENOMEM; From 4d2626e10709ff8474ffd1a9db3cf4647569e89c Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Tue, 7 Mar 2023 23:29:17 +0800 Subject: [PATCH 2343/4345] igb: revert rtnl_lock() that causes deadlock commit 65f69851e44d71248b952a687e44759a7abb5016 upstream. The commit 6faee3d4ee8b ("igb: Add lock to avoid data race") adds rtnl_lock to eliminate a false data race shown below (FREE from device detaching) | (USE from netdev core) igb_remove | igb_ndo_get_vf_config igb_disable_sriov | vf >= adapter->vfs_allocated_count? kfree(adapter->vf_data) | adapter->vfs_allocated_count = 0 | | memcpy(... adapter->vf_data[vf] The above race will never happen and the extra rtnl_lock causes deadlock below [ 141.420169] [ 141.420672] __schedule+0x2dd/0x840 [ 141.421427] schedule+0x50/0xc0 [ 141.422041] schedule_preempt_disabled+0x11/0x20 [ 141.422678] __mutex_lock.isra.13+0x431/0x6b0 [ 141.423324] unregister_netdev+0xe/0x20 [ 141.423578] igbvf_remove+0x45/0xe0 [igbvf] [ 141.423791] pci_device_remove+0x36/0xb0 [ 141.423990] device_release_driver_internal+0xc1/0x160 [ 141.424270] pci_stop_bus_device+0x6d/0x90 [ 141.424507] pci_stop_and_remove_bus_device+0xe/0x20 [ 141.424789] pci_iov_remove_virtfn+0xba/0x120 [ 141.425452] sriov_disable+0x2f/0xf0 [ 141.425679] igb_disable_sriov+0x4e/0x100 [igb] [ 141.426353] igb_remove+0xa0/0x130 [igb] [ 141.426599] pci_device_remove+0x36/0xb0 [ 141.426796] device_release_driver_internal+0xc1/0x160 [ 141.427060] driver_detach+0x44/0x90 [ 141.427253] bus_remove_driver+0x55/0xe0 [ 141.427477] pci_unregister_driver+0x2a/0xa0 [ 141.428296] __x64_sys_delete_module+0x141/0x2b0 [ 141.429126] ? mntput_no_expire+0x4a/0x240 [ 141.429363] ? syscall_trace_enter.isra.19+0x126/0x1a0 [ 141.429653] do_syscall_64+0x5b/0x80 [ 141.429847] ? exit_to_user_mode_prepare+0x14d/0x1c0 [ 141.430109] ? syscall_exit_to_user_mode+0x12/0x30 [ 141.430849] ? do_syscall_64+0x67/0x80 [ 141.431083] ? syscall_exit_to_user_mode_prepare+0x183/0x1b0 [ 141.431770] ? syscall_exit_to_user_mode+0x12/0x30 [ 141.432482] ? do_syscall_64+0x67/0x80 [ 141.432714] ? exc_page_fault+0x64/0x140 [ 141.432911] entry_SYSCALL_64_after_hwframe+0x72/0xdc Since the igb_disable_sriov() will call pci_disable_sriov() before releasing any resources, the netdev core will synchronize the cleanup to avoid any races. This patch removes the useless rtnl_(un)lock to guarantee correctness. CC: stable@vger.kernel.org Fixes: 6faee3d4ee8b ("igb: Add lock to avoid data race") Reported-by: Corinna Vinschen Link: https://lore.kernel.org/intel-wired-lan/ZAcJvkEPqWeJHO2r@calimero.vinschen.de/ Signed-off-by: Lin Ma Tested-by: Corinna Vinschen Reviewed-by: Jacob Keller Reviewed-by: Simon Horman Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/igb/igb_main.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 0ea8e4024d63..c5f465814dec 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3821,9 +3821,7 @@ static void igb_remove(struct pci_dev *pdev) igb_release_hw_control(adapter); #ifdef CONFIG_PCI_IOV - rtnl_lock(); igb_disable_sriov(pdev); - rtnl_unlock(); #endif unregister_netdev(netdev); From aae6d1bf4d8e66d566b77a44b5bef2cad11ec02c Mon Sep 17 00:00:00 2001 From: Coly Li Date: Mon, 27 Feb 2023 23:23:17 +0800 Subject: [PATCH 2344/4345] dm thin: fix deadlock when swapping to thin device commit 9bbf5feecc7eab2c370496c1c161bbfe62084028 upstream. This is an already known issue that dm-thin volume cannot be used as swap, otherwise a deadlock may happen when dm-thin internal memory demand triggers swap I/O on the dm-thin volume itself. But thanks to commit a666e5c05e7c ("dm: fix deadlock when swapping to encrypted device"), the limit_swap_bios target flag can also be used for dm-thin to avoid the recursive I/O when it is used as swap. Fix is to simply set ti->limit_swap_bios to true in both pool_ctr() and thin_ctr(). In my test, I create a dm-thin volume /dev/vg/swap and use it as swap device. Then I run fio on another dm-thin volume /dev/vg/main and use large --blocksize to trigger swap I/O onto /dev/vg/swap. The following fio command line is used in my test, fio --name recursive-swap-io --lockmem 1 --iodepth 128 \ --ioengine libaio --filename /dev/vg/main --rw randrw \ --blocksize 1M --numjobs 32 --time_based --runtime=12h Without this fix, the whole system can be locked up within 15 seconds. With this fix, there is no any deadlock or hung task observed after 2 hours of running fio. Furthermore, if blocksize is changed from 1M to 128M, after around 30 seconds fio has no visible I/O, and the out-of-memory killer message shows up in kernel message. After around 20 minutes all fio processes are killed and the whole system is back to being alive. This is exactly what is expected when recursive I/O happens on dm-thin volume when it is used as swap. Depends-on: a666e5c05e7c ("dm: fix deadlock when swapping to encrypted device") Cc: stable@vger.kernel.org Signed-off-by: Coly Li Acked-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-thin.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index c890bb3e5185..93140743a999 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3383,6 +3383,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) pt->low_water_blocks = low_water_blocks; pt->adjusted_pf = pt->requested_pf = pf; ti->num_flush_bios = 1; + ti->limit_swap_bios = true; /* * Only need to enable discards if the pool should pass @@ -4259,6 +4260,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; ti->num_flush_bios = 1; + ti->limit_swap_bios = true; ti->flush_supported = true; ti->per_io_data_size = sizeof(struct dm_thin_endio_hook); From 5a36b601aff3f22e9504763c6d9779f099d3f1bd Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Wed, 8 Mar 2023 07:44:27 -0500 Subject: [PATCH 2345/4345] usb: cdns3: Fix issue with using incorrect PCI device function commit 1272fd652a226ccb34e9f47371b6121948048438 upstream. PCI based platform can have more than two PCI functions. USBSS PCI Glue driver during initialization should consider only DRD/HOST/DEVICE PCI functions and all other should be ignored. This patch adds additional condition which causes that only DRD and HOST/DEVICE function will be accepted. cc: Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver") Signed-off-by: Pawel Laszczak Link: https://lore.kernel.org/r/20230308124427.311245-1-pawell@cadence.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/cdns3/cdns3-pci-wrap.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/cdns3/cdns3-pci-wrap.c b/drivers/usb/cdns3/cdns3-pci-wrap.c index deeea618ba33..1f6320d98a76 100644 --- a/drivers/usb/cdns3/cdns3-pci-wrap.c +++ b/drivers/usb/cdns3/cdns3-pci-wrap.c @@ -60,6 +60,11 @@ static struct pci_dev *cdns3_get_second_fun(struct pci_dev *pdev) return NULL; } + if (func->devfn != PCI_DEV_FN_HOST_DEVICE && + func->devfn != PCI_DEV_FN_OTG) { + return NULL; + } + return func; } From 073ce98aa3a6be039a7e17b87945dfea3b4d2b66 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Fri, 17 Mar 2023 14:15:15 +0800 Subject: [PATCH 2346/4345] usb: chipdea: core: fix return -EINVAL if request role is the same with current role commit 3670de80678961eda7fa2220883fc77c16868951 upstream. It should not return -EINVAL if the request role is the same with current role, return non-error and without do anything instead. Fixes: a932a8041ff9 ("usb: chipidea: core: add sysfs group") cc: Acked-by: Peter Chen Signed-off-by: Xu Yang Link: https://lore.kernel.org/r/20230317061516.2451728-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 127b1a62b1bf..0b7e5ab23457 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -966,9 +966,12 @@ static ssize_t role_store(struct device *dev, strlen(ci->roles[role]->name))) break; - if (role == CI_ROLE_END || role == ci->role) + if (role == CI_ROLE_END) return -EINVAL; + if (role == ci->role) + return n; + pm_runtime_get_sync(dev); disable_irq(ci->irq); ci_role_stop(ci); From 09671cfc2b22fa1a4cec29464205d9ac62f821e5 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Fri, 17 Mar 2023 14:15:16 +0800 Subject: [PATCH 2347/4345] usb: chipidea: core: fix possible concurrent when switch role commit 451b15ed138ec15bffbebb58a00ebdd884c3e659 upstream. The user may call role_store() when driver is handling ci_handle_id_switch() which is triggerred by otg event or power lost event. Unfortunately, the controller may go into chaos in this case. Fix this by protecting it with mutex lock. Fixes: a932a8041ff9 ("usb: chipidea: core: add sysfs group") cc: Acked-by: Peter Chen Signed-off-by: Xu Yang Link: https://lore.kernel.org/r/20230317061516.2451728-2-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/ci.h | 2 ++ drivers/usb/chipidea/core.c | 8 +++++++- drivers/usb/chipidea/otg.c | 5 ++++- 3 files changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h index 0697eb980e5f..7b00b93dad9b 100644 --- a/drivers/usb/chipidea/ci.h +++ b/drivers/usb/chipidea/ci.h @@ -204,6 +204,7 @@ struct hw_bank { * @in_lpm: if the core in low power mode * @wakeup_int: if wakeup interrupt occur * @rev: The revision number for controller + * @mutex: protect code from concorrent running when doing role switch */ struct ci_hdrc { struct device *dev; @@ -257,6 +258,7 @@ struct ci_hdrc { bool in_lpm; bool wakeup_int; enum ci_revision rev; + struct mutex mutex; }; static inline struct ci_role_driver *ci_role(struct ci_hdrc *ci) diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 0b7e5ab23457..f26dd1f054f2 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -969,8 +969,12 @@ static ssize_t role_store(struct device *dev, if (role == CI_ROLE_END) return -EINVAL; - if (role == ci->role) + mutex_lock(&ci->mutex); + + if (role == ci->role) { + mutex_unlock(&ci->mutex); return n; + } pm_runtime_get_sync(dev); disable_irq(ci->irq); @@ -980,6 +984,7 @@ static ssize_t role_store(struct device *dev, ci_handle_vbus_change(ci); enable_irq(ci->irq); pm_runtime_put_sync(dev); + mutex_unlock(&ci->mutex); return (ret == 0) ? n : ret; } @@ -1015,6 +1020,7 @@ static int ci_hdrc_probe(struct platform_device *pdev) return -ENOMEM; spin_lock_init(&ci->lock); + mutex_init(&ci->mutex); ci->dev = dev; ci->platdata = dev_get_platdata(dev); ci->imx28_write_fix = !!(ci->platdata->flags & diff --git a/drivers/usb/chipidea/otg.c b/drivers/usb/chipidea/otg.c index d3aada3ce7ec..9a12868ea9b6 100644 --- a/drivers/usb/chipidea/otg.c +++ b/drivers/usb/chipidea/otg.c @@ -166,8 +166,10 @@ static int hw_wait_vbus_lower_bsv(struct ci_hdrc *ci) static void ci_handle_id_switch(struct ci_hdrc *ci) { - enum ci_role role = ci_otg_role(ci); + enum ci_role role; + mutex_lock(&ci->mutex); + role = ci_otg_role(ci); if (role != ci->role) { dev_dbg(ci->dev, "switching from %s to %s\n", ci_role(ci)->name, ci->roles[role]->name); @@ -197,6 +199,7 @@ static void ci_handle_id_switch(struct ci_hdrc *ci) if (role == CI_ROLE_GADGET) ci_handle_vbus_change(ci); } + mutex_unlock(&ci->mutex); } /** * ci_otg_work - perform otg (vbus/id) event handle From a6adfe9bbd6ac11e398b54ccd99a0f8eea09f3c0 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 8 Mar 2023 16:42:42 +0100 Subject: [PATCH 2348/4345] usb: ucsi: Fix NULL pointer deref in ucsi_connector_change() commit f87fb985452ab2083967103ac00bfd68fb182764 upstream. When ucsi_init() fails, ucsi->connector is NULL, yet in case of ucsi_acpi we may still get events which cause the ucs_acpi code to call ucsi_connector_change(), which then derefs the NULL ucsi->connector pointer. Fix this by not setting ucsi->ntfy inside ucsi_init() until ucsi_init() has succeeded, so that ucsi_connector_change() ignores the events because UCSI_ENABLE_NTFY_CONNECTOR_CHANGE is not set in the ntfy mask. Fixes: bdc62f2bae8f ("usb: typec: ucsi: Simplified registration and I/O API") Link: https://bugzilla.kernel.org/show_bug.cgi?id=217106 Cc: stable@vger.kernel.org Reviewed-by: Heikki Krogerus Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230308154244.722337-2-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/ucsi/ucsi.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 4cd5c291cdf3..cd3689005c31 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1152,7 +1152,7 @@ out_unlock: static int ucsi_init(struct ucsi *ucsi) { struct ucsi_connector *con; - u64 command; + u64 command, ntfy; int ret; int i; @@ -1164,8 +1164,8 @@ static int ucsi_init(struct ucsi *ucsi) } /* Enable basic notifications */ - ucsi->ntfy = UCSI_ENABLE_NTFY_CMD_COMPLETE | UCSI_ENABLE_NTFY_ERROR; - command = UCSI_SET_NOTIFICATION_ENABLE | ucsi->ntfy; + ntfy = UCSI_ENABLE_NTFY_CMD_COMPLETE | UCSI_ENABLE_NTFY_ERROR; + command = UCSI_SET_NOTIFICATION_ENABLE | ntfy; ret = ucsi_send_command(ucsi, command, NULL, 0); if (ret < 0) goto err_reset; @@ -1197,12 +1197,13 @@ static int ucsi_init(struct ucsi *ucsi) } /* Enable all notifications */ - ucsi->ntfy = UCSI_ENABLE_NTFY_ALL; - command = UCSI_SET_NOTIFICATION_ENABLE | ucsi->ntfy; + ntfy = UCSI_ENABLE_NTFY_ALL; + command = UCSI_SET_NOTIFICATION_ENABLE | ntfy; ret = ucsi_send_command(ucsi, command, NULL, 0); if (ret < 0) goto err_unregister; + ucsi->ntfy = ntfy; return 0; err_unregister: From 560437bba14d0546de72e3e9d0a2f78d88e8cd91 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 14 Mar 2023 10:59:50 +0100 Subject: [PATCH 2349/4345] wifi: mac80211: fix qos on mesh interfaces commit 4e348c6c6e23491ae6eb5e077848a42d0562339c upstream. When ieee80211_select_queue is called for mesh, the sta pointer is usually NULL, since the nexthop is looked up much later in the tx path. Explicitly check for unicast address in that case in order to make qos work again. Cc: stable@vger.kernel.org Fixes: 50e2ab392919 ("wifi: mac80211: fix queue selection for mesh/OCB interfaces") Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20230314095956.62085-1-nbd@nbd.name Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- net/mac80211/wme.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index b9404b056087..eb79f6844466 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -141,12 +141,14 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata, u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct sk_buff *skb) { + const struct ethhdr *eth = (void *)skb->data; struct mac80211_qos_map *qos_map; bool qos; /* all mesh/ocb stations are required to support WME */ - if (sta && (sdata->vif.type == NL80211_IFTYPE_MESH_POINT || - sdata->vif.type == NL80211_IFTYPE_OCB)) + if ((sdata->vif.type == NL80211_IFTYPE_MESH_POINT && + !is_multicast_ether_addr(eth->h_dest)) || + (sdata->vif.type == NL80211_IFTYPE_OCB && sta)) qos = true; else if (sta) qos = sta->sta.wme; From d18db946cc6a394291539e030df32324285648f7 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Tue, 7 Mar 2023 17:55:48 +0900 Subject: [PATCH 2350/4345] nilfs2: fix kernel-infoleak in nilfs_ioctl_wrap_copy() commit 003587000276f81d0114b5ce773d80c119d8cb30 upstream. The ioctl helper function nilfs_ioctl_wrap_copy(), which exchanges a metadata array to/from user space, may copy uninitialized buffer regions to user space memory for read-only ioctl commands NILFS_IOCTL_GET_SUINFO and NILFS_IOCTL_GET_CPINFO. This can occur when the element size of the user space metadata given by the v_size member of the argument nilfs_argv structure is larger than the size of the metadata element (nilfs_suinfo structure or nilfs_cpinfo structure) on the file system side. KMSAN-enabled kernels detect this issue as follows: BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_user+0xc0/0x100 lib/usercopy.c:33 instrument_copy_to_user include/linux/instrumented.h:121 [inline] _copy_to_user+0xc0/0x100 lib/usercopy.c:33 copy_to_user include/linux/uaccess.h:169 [inline] nilfs_ioctl_wrap_copy+0x6fa/0xc10 fs/nilfs2/ioctl.c:99 nilfs_ioctl_get_info fs/nilfs2/ioctl.c:1173 [inline] nilfs_ioctl+0x2402/0x4450 fs/nilfs2/ioctl.c:1290 nilfs_compat_ioctl+0x1b8/0x200 fs/nilfs2/ioctl.c:1343 __do_compat_sys_ioctl fs/ioctl.c:968 [inline] __se_compat_sys_ioctl+0x7dd/0x1000 fs/ioctl.c:910 __ia32_compat_sys_ioctl+0x93/0xd0 fs/ioctl.c:910 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246 entry_SYSENTER_compat_after_hwframe+0x70/0x82 Uninit was created at: __alloc_pages+0x9f6/0xe90 mm/page_alloc.c:5572 alloc_pages+0xab0/0xd80 mm/mempolicy.c:2287 __get_free_pages+0x34/0xc0 mm/page_alloc.c:5599 nilfs_ioctl_wrap_copy+0x223/0xc10 fs/nilfs2/ioctl.c:74 nilfs_ioctl_get_info fs/nilfs2/ioctl.c:1173 [inline] nilfs_ioctl+0x2402/0x4450 fs/nilfs2/ioctl.c:1290 nilfs_compat_ioctl+0x1b8/0x200 fs/nilfs2/ioctl.c:1343 __do_compat_sys_ioctl fs/ioctl.c:968 [inline] __se_compat_sys_ioctl+0x7dd/0x1000 fs/ioctl.c:910 __ia32_compat_sys_ioctl+0x93/0xd0 fs/ioctl.c:910 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246 entry_SYSENTER_compat_after_hwframe+0x70/0x82 Bytes 16-127 of 3968 are uninitialized ... This eliminates the leak issue by initializing the page allocated as buffer using get_zeroed_page(). Link: https://lkml.kernel.org/r/20230307085548.6290-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+132fdd2f1e1805fdc591@syzkaller.appspotmail.com Link: https://lkml.kernel.org/r/000000000000a5bd2d05f63f04ae@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 3a1dea5d1448..01235fac5971 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -70,7 +70,7 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs, if (argv->v_index > ~(__u64)0 - argv->v_nmembs) return -EINVAL; - buf = (void *)__get_free_pages(GFP_NOFS, 0); + buf = (void *)get_zeroed_page(GFP_NOFS); if (unlikely(!buf)) return -ENOMEM; maxmembs = PAGE_SIZE / argv->v_size; From d5329a06b4cb8bb79117c5ccb0bd3f1463881d21 Mon Sep 17 00:00:00 2001 From: Nirmoy Das Date: Tue, 14 Mar 2023 15:29:14 +0100 Subject: [PATCH 2351/4345] drm/i915/active: Fix missing debug object activation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit e92eb246feb9019b0b137706c934b8891cdfe3c2 upstream. debug_active_activate() expected ref->count to be zero which is not true anymore as __i915_active_activate() calls debug_active_activate() after incrementing the count. v2: No need to check for "ref->count == 1" as __i915_active_activate() already make sure of that(Janusz). References: https://gitlab.freedesktop.org/drm/intel/-/issues/6733 Fixes: 04240e30ed06 ("drm/i915: Skip taking acquire mutex for no ref->active callback") Cc: Chris Wilson Cc: Tvrtko Ursulin Cc: Thomas Hellström Cc: Andi Shyti Cc: intel-gfx@lists.freedesktop.org Cc: Janusz Krzysztofik Cc: # v5.10+ Signed-off-by: Nirmoy Das Reviewed-by: Janusz Krzysztofik Reviewed-by: Andrzej Hajda Link: https://patchwork.freedesktop.org/patch/msgid/20230313114613.9874-1-nirmoy.das@intel.com (cherry picked from commit bfad380c542438a9b642f8190b7fd37bc77e2723) Signed-off-by: Jani Nikula Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_active.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 0532a5069c04..cae9ac6379a5 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -96,8 +96,7 @@ static void debug_active_init(struct i915_active *ref) static void debug_active_activate(struct i915_active *ref) { lockdep_assert_held(&ref->tree_lock); - if (!atomic_read(&ref->count)) /* before the first inc */ - debug_object_activate(ref, &active_debug_desc); + debug_object_activate(ref, &active_debug_desc); } static void debug_active_deactivate(struct i915_active *ref) From 4ede0da36c2fcd1f315c93719d9f3b7c7a807512 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Thu, 23 Feb 2023 17:20:48 +0200 Subject: [PATCH 2352/4345] drm/i915: Preserve crtc_state->inherited during state clearing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 3a84f2c6c9558c554a90ec26ad25df92fc5e05b7 upstream. intel_crtc_prepare_cleared_state() is unintentionally losing the "inherited" flag. This will happen if intel_initial_commit() is forced to go through the full modeset calculations for whatever reason. Afterwards the first real commit from userspace will not get forced to the full modeset path, and thus eg. audio state may not get recomputed properly. So if the monitor was already enabled during boot audio will not work until userspace itself does an explicit full modeset. Cc: stable@vger.kernel.org Tested-by: Lee Shawn C Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20230223152048.20878-1-ville.syrjala@linux.intel.com Reviewed-by: Uma Shankar (cherry picked from commit 2553bacaf953b48c59357f5a622282bc0c45adae) Signed-off-by: Jani Nikula Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/display/intel_display.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 45c2556d6395..d46011f7a838 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -13335,6 +13335,7 @@ intel_crtc_prepare_cleared_state(struct intel_crtc_state *crtc_state) * only fields that are know to not cause problems are preserved. */ saved_state->uapi = crtc_state->uapi; + saved_state->inherited = crtc_state->inherited; saved_state->scaler_state = crtc_state->scaler_state; saved_state->shared_dpll = crtc_state->shared_dpll; saved_state->dpll_hw_state = crtc_state->dpll_hw_state; From f632a90f8e39db39b322107b9a8d438b826a7f4f Mon Sep 17 00:00:00 2001 From: Rijo Thomas Date: Tue, 28 Feb 2023 15:11:20 +0530 Subject: [PATCH 2353/4345] tee: amdtee: fix race condition in amdtee_open_session commit f8502fba45bd30e1a6a354d9d898bc99d1a11e6d upstream. There is a potential race condition in amdtee_open_session that may lead to use-after-free. For instance, in amdtee_open_session() after sess->sess_mask is set, and before setting: sess->session_info[i] = session_info; if amdtee_close_session() closes this same session, then 'sess' data structure will be released, causing kernel panic when 'sess' is accessed within amdtee_open_session(). The solution is to set the bit sess->sess_mask as the last step in amdtee_open_session(). Fixes: 757cc3e9ff1d ("tee: add AMD-TEE driver") Cc: stable@vger.kernel.org Signed-off-by: Rijo Thomas Acked-by: Sumit Garg Signed-off-by: Jens Wiklander Signed-off-by: Greg Kroah-Hartman --- drivers/tee/amdtee/core.c | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c index 297dc62bca29..372d64756ed6 100644 --- a/drivers/tee/amdtee/core.c +++ b/drivers/tee/amdtee/core.c @@ -267,35 +267,34 @@ int amdtee_open_session(struct tee_context *ctx, goto out; } + /* Open session with loaded TA */ + handle_open_session(arg, &session_info, param); + if (arg->ret != TEEC_SUCCESS) { + pr_err("open_session failed %d\n", arg->ret); + handle_unload_ta(ta_handle); + kref_put(&sess->refcount, destroy_session); + goto out; + } + /* Find an empty session index for the given TA */ spin_lock(&sess->lock); i = find_first_zero_bit(sess->sess_mask, TEE_NUM_SESSIONS); - if (i < TEE_NUM_SESSIONS) + if (i < TEE_NUM_SESSIONS) { + sess->session_info[i] = session_info; + set_session_id(ta_handle, i, &arg->session); set_bit(i, sess->sess_mask); + } spin_unlock(&sess->lock); if (i >= TEE_NUM_SESSIONS) { pr_err("reached maximum session count %d\n", TEE_NUM_SESSIONS); + handle_close_session(ta_handle, session_info); handle_unload_ta(ta_handle); kref_put(&sess->refcount, destroy_session); rc = -ENOMEM; goto out; } - /* Open session with loaded TA */ - handle_open_session(arg, &session_info, param); - if (arg->ret != TEEC_SUCCESS) { - pr_err("open_session failed %d\n", arg->ret); - spin_lock(&sess->lock); - clear_bit(i, sess->sess_mask); - spin_unlock(&sess->lock); - handle_unload_ta(ta_handle); - kref_put(&sess->refcount, destroy_session); - goto out; - } - - sess->session_info[i] = session_info; - set_session_id(ta_handle, i, &arg->session); out: free_pages((u64)ta, get_order(ta_size)); return rc; From 85b637feee1e60e2dce3a8e9041ccfee202fbb4c Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Tue, 7 Mar 2023 16:23:24 +0000 Subject: [PATCH 2354/4345] firmware: arm_scmi: Fix device node validation for mailbox transport commit 2ab4f4018cb6b8010ca5002c3bdc37783b5d28c2 upstream. When mailboxes are used as a transport it is possible to setup the SCMI transport layer, depending on the underlying channels configuration, to use one or two mailboxes, associated, respectively, to one or two, distinct, shared memory areas: any other combination should be treated as invalid. Add more strict checking of SCMI mailbox transport device node descriptors. Fixes: 5c8a47a5a91d ("firmware: arm_scmi: Make scmi core independent of the transport type") Cc: # 4.19 Signed-off-by: Cristian Marussi Link: https://lore.kernel.org/r/20230307162324.891866-1-cristian.marussi@arm.com Signed-off-by: Sudeep Holla Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/arm_scmi/mailbox.c | 37 +++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index 4626404be541..ad773a657ed2 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -52,6 +52,39 @@ static bool mailbox_chan_available(struct device *dev, int idx) "#mbox-cells", idx, NULL); } +static int mailbox_chan_validate(struct device *cdev) +{ + int num_mb, num_sh, ret = 0; + struct device_node *np = cdev->of_node; + + num_mb = of_count_phandle_with_args(np, "mboxes", "#mbox-cells"); + num_sh = of_count_phandle_with_args(np, "shmem", NULL); + /* Bail out if mboxes and shmem descriptors are inconsistent */ + if (num_mb <= 0 || num_sh > 2 || num_mb != num_sh) { + dev_warn(cdev, "Invalid channel descriptor for '%s'\n", + of_node_full_name(np)); + return -EINVAL; + } + + if (num_sh > 1) { + struct device_node *np_tx, *np_rx; + + np_tx = of_parse_phandle(np, "shmem", 0); + np_rx = of_parse_phandle(np, "shmem", 1); + /* SCMI Tx and Rx shared mem areas have to be distinct */ + if (!np_tx || !np_rx || np_tx == np_rx) { + dev_warn(cdev, "Invalid shmem descriptor for '%s'\n", + of_node_full_name(np)); + ret = -EINVAL; + } + + of_node_put(np_tx); + of_node_put(np_rx); + } + + return ret; +} + static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, bool tx) { @@ -64,6 +97,10 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, resource_size_t size; struct resource res; + ret = mailbox_chan_validate(cdev); + if (ret) + return ret; + smbox = devm_kzalloc(dev, sizeof(*smbox), GFP_KERNEL); if (!smbox) return -ENOMEM; From 1eaa2b7ae90c5a5e05586df310d804de250747d3 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Tue, 14 Mar 2023 16:54:21 +0000 Subject: [PATCH 2355/4345] i2c: xgene-slimpro: Fix out-of-bounds bug in xgene_slimpro_i2c_xfer() commit 92fbb6d1296f81f41f65effd7f5f8c0f74943d15 upstream. The data->block[0] variable comes from user and is a number between 0-255. Without proper check, the variable may be very large to cause an out-of-bounds when performing memcpy in slimpro_i2c_blkwr. Fix this bug by checking the value of writelen. Fixes: f6505fbabc42 ("i2c: add SLIMpro I2C device driver on APM X-Gene platform") Signed-off-by: Wei Chen Cc: stable@vger.kernel.org Reviewed-by: Andi Shyti Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-xgene-slimpro.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c index 63cbb9c7c1b0..76e9dcd63856 100644 --- a/drivers/i2c/busses/i2c-xgene-slimpro.c +++ b/drivers/i2c/busses/i2c-xgene-slimpro.c @@ -308,6 +308,9 @@ static int slimpro_i2c_blkwr(struct slimpro_i2c_dev *ctx, u32 chip, u32 msg[3]; int rc; + if (writelen > I2C_SMBUS_BLOCK_MAX) + return -EINVAL; + memcpy(ctx->dma_buffer, data, writelen); paddr = dma_map_single(ctx->dev, ctx->dma_buffer, writelen, DMA_TO_DEVICE); From c68f08cc745675a17894e1b4a5b5b9700ace6da4 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Thu, 16 Mar 2023 14:55:06 +0800 Subject: [PATCH 2356/4345] dm stats: check for and propagate alloc_percpu failure commit d3aa3e060c4a80827eb801fc448debc9daa7c46b upstream. Check alloc_precpu()'s return value and return an error from dm_stats_init() if it fails. Update alloc_dev() to fail if dm_stats_init() does. Otherwise, a NULL pointer dereference will occur in dm_stats_cleanup() even if dm-stats isn't being actively used. Fixes: fd2ed4d25270 ("dm: add statistics support") Cc: stable@vger.kernel.org Signed-off-by: Jiasheng Jiang Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-stats.c | 7 ++++++- drivers/md/dm-stats.h | 2 +- drivers/md/dm.c | 4 +++- 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 55443a6598fa..4029281ca383 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -188,7 +188,7 @@ static int dm_stat_in_flight(struct dm_stat_shared *shared) atomic_read(&shared->in_flight[WRITE]); } -void dm_stats_init(struct dm_stats *stats) +int dm_stats_init(struct dm_stats *stats) { int cpu; struct dm_stats_last_position *last; @@ -196,11 +196,16 @@ void dm_stats_init(struct dm_stats *stats) mutex_init(&stats->mutex); INIT_LIST_HEAD(&stats->list); stats->last = alloc_percpu(struct dm_stats_last_position); + if (!stats->last) + return -ENOMEM; + for_each_possible_cpu(cpu) { last = per_cpu_ptr(stats->last, cpu); last->last_sector = (sector_t)ULLONG_MAX; last->last_rw = UINT_MAX; } + + return 0; } void dm_stats_cleanup(struct dm_stats *stats) diff --git a/drivers/md/dm-stats.h b/drivers/md/dm-stats.h index 2ddfae678f32..dcac11fce03b 100644 --- a/drivers/md/dm-stats.h +++ b/drivers/md/dm-stats.h @@ -22,7 +22,7 @@ struct dm_stats_aux { unsigned long long duration_ns; }; -void dm_stats_init(struct dm_stats *st); +int dm_stats_init(struct dm_stats *st); void dm_stats_cleanup(struct dm_stats *st); struct mapped_device; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c60febd14be1..9029c1004b93 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1910,7 +1910,9 @@ static struct mapped_device *alloc_dev(int minor) if (!md->bdev) goto bad; - dm_stats_init(&md->stats); + r = dm_stats_init(&md->stats); + if (r < 0) + goto bad; /* Populate the mapping, nobody knows we exist yet */ spin_lock(&_minor_lock); From 66ff37993dd7e9954b6446237fe2453b380ce40d Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 6 Mar 2023 11:17:58 -0500 Subject: [PATCH 2357/4345] dm crypt: add cond_resched() to dmcrypt_write() commit fb294b1c0ba982144ca467a75e7d01ff26304e2b upstream. The loop in dmcrypt_write may be running for unbounded amount of time, thus we need cond_resched() in it. This commit fixes the following warning: [ 3391.153255][ C12] watchdog: BUG: soft lockup - CPU#12 stuck for 23s! [dmcrypt_write/2:2897] ... [ 3391.387210][ C12] Call trace: [ 3391.390338][ C12] blk_attempt_bio_merge.part.6+0x38/0x158 [ 3391.395970][ C12] blk_attempt_plug_merge+0xc0/0x1b0 [ 3391.401085][ C12] blk_mq_submit_bio+0x398/0x550 [ 3391.405856][ C12] submit_bio_noacct+0x308/0x380 [ 3391.410630][ C12] dmcrypt_write+0x1e4/0x208 [dm_crypt] [ 3391.416005][ C12] kthread+0x130/0x138 [ 3391.419911][ C12] ret_from_fork+0x10/0x18 Reported-by: yangerkun Fixes: dc2676210c42 ("dm crypt: offload writes to thread") Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-crypt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 3d975db86434..17ddca293965 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1934,6 +1934,7 @@ pop_from_list: io = crypt_io_from_node(rb_first(&write_tree)); rb_erase(&io->rb_node, &write_tree); kcryptd_io_write(io); + cond_resched(); } while (!RB_EMPTY_ROOT(&write_tree)); blk_finish_plug(&plug); } From dfdcda25fb5e3c09394a28173f24b22e7c7e4731 Mon Sep 17 00:00:00 2001 From: Zhang Qiao Date: Mon, 30 Jan 2023 13:22:16 +0100 Subject: [PATCH 2358/4345] sched/fair: sanitize vruntime of entity being placed commit 829c1651e9c4a6f78398d3e67651cef9bb6b42cc upstream. When a scheduling entity is placed onto cfs_rq, its vruntime is pulled to the base level (around cfs_rq->min_vruntime), so that the entity doesn't gain extra boost when placed backwards. However, if the entity being placed wasn't executed for a long time, its vruntime may get too far behind (e.g. while cfs_rq was executing a low-weight hog), which can inverse the vruntime comparison due to s64 overflow. This results in the entity being placed with its original vruntime way forwards, so that it will effectively never get to the cpu. To prevent that, ignore the vruntime of the entity being placed if it didn't execute for much longer than the characteristic sheduler time scale. [rkagan: formatted, adjusted commit log, comments, cutoff value] Signed-off-by: Zhang Qiao Co-developed-by: Roman Kagan Signed-off-by: Roman Kagan Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230130122216.3555094-1-rkagan@amazon.de Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c39d2fc3f994..68166c599a35 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4278,6 +4278,7 @@ static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) { u64 vruntime = cfs_rq->min_vruntime; + u64 sleep_time; /* * The 'current' period is already promised to the current tasks, @@ -4302,8 +4303,18 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) vruntime -= thresh; } - /* ensure we never gain time by being placed backwards. */ - se->vruntime = max_vruntime(se->vruntime, vruntime); + /* + * Pull vruntime of the entity being placed to the base level of + * cfs_rq, to prevent boosting it if placed backwards. If the entity + * slept for a long time, don't even try to compare its vruntime with + * the base as it may be too far off and the comparison may get + * inversed due to s64 overflow. + */ + sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start; + if ((s64)sleep_time > 60LL * NSEC_PER_SEC) + se->vruntime = vruntime; + else + se->vruntime = max_vruntime(se->vruntime, vruntime); } static void check_enqueue_throttle(struct cfs_rq *cfs_rq); From d4a5181ba1b1165b8607fa4e738ce7b4be68eb24 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 17 Mar 2023 17:08:10 +0100 Subject: [PATCH 2359/4345] sched/fair: Sanitize vruntime of entity being migrated commit a53ce18cacb477dd0513c607f187d16f0fa96f71 upstream. Commit 829c1651e9c4 ("sched/fair: sanitize vruntime of entity being placed") fixes an overflowing bug, but ignore a case that se->exec_start is reset after a migration. For fixing this case, we delay the reset of se->exec_start after placing the entity which se->exec_start to detect long sleeping task. In order to take into account a possible divergence between the clock_task of 2 rqs, we increase the threshold to around 104 days. Fixes: 829c1651e9c4 ("sched/fair: sanitize vruntime of entity being placed") Originally-by: Zhang Qiao Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Tested-by: Zhang Qiao Link: https://lore.kernel.org/r/20230317160810.107988-1-vincent.guittot@linaro.org Signed-off-by: Greg Kroah-Hartman --- kernel/sched/core.c | 3 +++ kernel/sched/fair.c | 53 ++++++++++++++++++++++++++++++++++++--------- 2 files changed, 46 insertions(+), 10 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1303a2607f1f..abea8fb7bdd1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1601,6 +1601,9 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) void activate_task(struct rq *rq, struct task_struct *p, int flags) { + if (task_on_rq_migrating(p)) + flags |= ENQUEUE_MIGRATED; + enqueue_task(rq, p, flags); p->on_rq = TASK_ON_RQ_QUEUED; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 68166c599a35..bb70a7856277 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4274,11 +4274,33 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) #endif } +static inline bool entity_is_long_sleeper(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq; + u64 sleep_time; + + if (se->exec_start == 0) + return false; + + cfs_rq = cfs_rq_of(se); + + sleep_time = rq_clock_task(rq_of(cfs_rq)); + + /* Happen while migrating because of clock task divergence */ + if (sleep_time <= se->exec_start) + return false; + + sleep_time -= se->exec_start; + if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD))) + return true; + + return false; +} + static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) { u64 vruntime = cfs_rq->min_vruntime; - u64 sleep_time; /* * The 'current' period is already promised to the current tasks, @@ -4305,13 +4327,24 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) /* * Pull vruntime of the entity being placed to the base level of - * cfs_rq, to prevent boosting it if placed backwards. If the entity - * slept for a long time, don't even try to compare its vruntime with - * the base as it may be too far off and the comparison may get - * inversed due to s64 overflow. + * cfs_rq, to prevent boosting it if placed backwards. + * However, min_vruntime can advance much faster than real time, with + * the extreme being when an entity with the minimal weight always runs + * on the cfs_rq. If the waking entity slept for a long time, its + * vruntime difference from min_vruntime may overflow s64 and their + * comparison may get inversed, so ignore the entity's original + * vruntime in that case. + * The maximal vruntime speedup is given by the ratio of normal to + * minimal weight: scale_load_down(NICE_0_LOAD) / MIN_SHARES. + * When placing a migrated waking entity, its exec_start has been set + * from a different rq. In order to take into account a possible + * divergence between new and prev rq's clocks task because of irq and + * stolen time, we take an additional margin. + * So, cutting off on the sleep time of + * 2^63 / scale_load_down(NICE_0_LOAD) ~ 104 days + * should be safe. */ - sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start; - if ((s64)sleep_time > 60LL * NSEC_PER_SEC) + if (entity_is_long_sleeper(se)) se->vruntime = vruntime; else se->vruntime = max_vruntime(se->vruntime, vruntime); @@ -4410,6 +4443,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (flags & ENQUEUE_WAKEUP) place_entity(cfs_rq, se, 0); + /* Entity has migrated, no longer consider this task hot */ + if (flags & ENQUEUE_MIGRATED) + se->exec_start = 0; check_schedstat_required(); update_stats_enqueue(cfs_rq, se, flags); @@ -6995,9 +7031,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) /* Tell new CPU we are migrated */ p->se.avg.last_update_time = 0; - /* We have migrated, no longer consider this task hot */ - p->se.exec_start = 0; - update_scan_period(p, new_cpu); } From 91d7a4bd5656552d6259e2d0f8859f9e8cc5ef68 Mon Sep 17 00:00:00 2001 From: Jan Kara via Ocfs2-devel Date: Thu, 2 Mar 2023 16:38:43 +0100 Subject: [PATCH 2360/4345] ocfs2: fix data corruption after failed write commit 90410bcf873cf05f54a32183afff0161f44f9715 upstream. When buffered write fails to copy data into underlying page cache page, ocfs2_write_end_nolock() just zeroes out and dirties the page. This can leave dirty page beyond EOF and if page writeback tries to write this page before write succeeds and expands i_size, page gets into inconsistent state where page dirty bit is clear but buffer dirty bits stay set resulting in page data never getting written and so data copied to the page is lost. Fix the problem by invalidating page beyond EOF after failed write. Link: https://lkml.kernel.org/r/20230302153843.18499-1-jack@suse.cz Fixes: 6dbf7bb55598 ("fs: Don't invalidate page buffers in block_write_full_page()") Signed-off-by: Jan Kara Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton [ replace block_invalidate_folio to block_invalidatepage ] Signed-off-by: Joseph Qi Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/aops.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index ad20403b383f..9b23e74036eb 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1981,11 +1981,25 @@ int ocfs2_write_end_nolock(struct address_space *mapping, } if (unlikely(copied < len) && wc->w_target_page) { + loff_t new_isize; + if (!PageUptodate(wc->w_target_page)) copied = 0; - ocfs2_zero_new_buffers(wc->w_target_page, start+copied, - start+len); + new_isize = max_t(loff_t, i_size_read(inode), pos + copied); + if (new_isize > page_offset(wc->w_target_page)) + ocfs2_zero_new_buffers(wc->w_target_page, start+copied, + start+len); + else { + /* + * When page is fully beyond new isize (data copy + * failed), do not bother zeroing the page. Invalidate + * it instead so that writeback does not get confused + * put page & buffer dirty bits into inconsistent + * state. + */ + block_invalidatepage(wc->w_target_page, 0, PAGE_SIZE); + } } if (wc->w_target_page) flush_dcache_page(wc->w_target_page); From cb61e1e36fb379228d41b6413487e8a33077828c Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 28 Mar 2023 10:35:11 +0300 Subject: [PATCH 2361/4345] xfs: shut down the filesystem if we screw up quota reservation commit 2a4bdfa8558ca2904dc17b83497dc82aa7fc05e9 upstream. If we ever screw up the quota reservations enough to trip the assertions, something's wrong with the quota code. Shut down the filesystem when this happens, because this is corruption. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Brian Foster Signed-off-by: Amir Goldstein Acked-by: Darrick J. Wong Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_trans_dquot.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 288ea38c43ad..5ca210e6626c 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -16,6 +16,7 @@ #include "xfs_quota.h" #include "xfs_qm.h" #include "xfs_trace.h" +#include "xfs_error.h" STATIC void xfs_trans_alloc_dqinfo(xfs_trans_t *); @@ -708,9 +709,11 @@ xfs_trans_dqresv( XFS_TRANS_DQ_RES_INOS, ninos); } - ASSERT(dqp->q_blk.reserved >= dqp->q_blk.count); - ASSERT(dqp->q_rtb.reserved >= dqp->q_rtb.count); - ASSERT(dqp->q_ino.reserved >= dqp->q_ino.count); + + if (XFS_IS_CORRUPT(mp, dqp->q_blk.reserved < dqp->q_blk.count) || + XFS_IS_CORRUPT(mp, dqp->q_rtb.reserved < dqp->q_rtb.count) || + XFS_IS_CORRUPT(mp, dqp->q_ino.reserved < dqp->q_ino.count)) + goto error_corrupt; xfs_dqunlock(dqp); return 0; @@ -720,6 +723,10 @@ error_return: if (xfs_dquot_type(dqp) == XFS_DQTYPE_PROJ) return -ENOSPC; return -EDQUOT; +error_corrupt: + xfs_dqunlock(dqp); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return -EFSCORRUPTED; } From a6d345c3a31e1eaef6dbccfd57166a4da97c6dfe Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Tue, 28 Mar 2023 10:35:12 +0300 Subject: [PATCH 2362/4345] xfs: don't reuse busy extents on extent trim commit 06058bc40534530e617e5623775c53bb24f032cb upstream. Freed extents are marked busy from the point the freeing transaction commits until the associated CIL context is checkpointed to the log. This prevents reuse and overwrite of recently freed blocks before the changes are committed to disk, which can lead to corruption after a crash. The exception to this rule is that metadata allocation is allowed to reuse busy extents because metadata changes are also logged. As of commit 97d3ac75e5e0 ("xfs: exact busy extent tracking"), XFS has allowed modification or complete invalidation of outstanding busy extents for metadata allocations. This implementation assumes that use of the associated extent is imminent, which is not always the case. For example, the trimmed extent might not satisfy the minimum length of the allocation request, or the allocation algorithm might be involved in a search for the optimal result based on locality. generic/019 reproduces a corruption caused by this scenario. First, a metadata block (usually a bmbt or symlink block) is freed from an inode. A subsequent bmbt split on an unrelated inode attempts a near mode allocation request that invalidates the busy block during the search, but does not ultimately allocate it. Due to the busy state invalidation, the block is no longer considered busy to subsequent allocation. A direct I/O write request immediately allocates the block and writes to it. Finally, the filesystem crashes while in a state where the initial metadata block free had not committed to the on-disk log. After recovery, the original metadata block is in its original location as expected, but has been corrupted by the aforementioned dio. This demonstrates that it is fundamentally unsafe to modify busy extent state for extents that are not guaranteed to be allocated. This applies to pretty much all of the code paths that currently trim busy extents for one reason or another. Therefore to address this problem, drop the reuse mechanism from the busy extent trim path. This code already knows how to return partial non-busy ranges of the targeted free extent and higher level code tracks the busy state of the allocation attempt. If a block allocation fails where one or more candidate extents is busy, we force the log and retry the allocation. Signed-off-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Chandan Babu R Reviewed-by: Christoph Hellwig Signed-off-by: Amir Goldstein Acked-by: Darrick J. Wong Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_extent_busy.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 5c2695a42de1..a4075685d9eb 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -344,7 +344,6 @@ xfs_extent_busy_trim( ASSERT(*len > 0); spin_lock(&args->pag->pagb_lock); -restart: fbno = *bno; flen = *len; rbp = args->pag->pagb_tree.rb_node; @@ -363,19 +362,6 @@ restart: continue; } - /* - * If this is a metadata allocation, try to reuse the busy - * extent instead of trimming the allocation. - */ - if (!(args->datatype & XFS_ALLOC_USERDATA) && - !(busyp->flags & XFS_EXTENT_BUSY_DISCARDED)) { - if (!xfs_extent_busy_update_extent(args->mp, args->pag, - busyp, fbno, flen, - false)) - goto restart; - continue; - } - if (bbno <= fbno) { /* start overlap */ From 34ef9cd887d573babd5b7f689fc188eff14aa8ed Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 23 Aug 2022 14:34:14 +0800 Subject: [PATCH 2363/4345] KVM: fix memoryleak in kvm_init() commit 5a2a961be2ad6a16eb388a80442443b353c11d16 upstream. When alloc_cpumask_var_node() fails for a certain cpu, there might be some allocated cpumasks for percpu cpu_kick_mask. We should free these cpumasks or memoryleak will occur. Fixes: baff59ccdc65 ("KVM: Pre-allocate cpumasks for kvm_make_all_cpus_request_except()") Signed-off-by: Miaohe Lin Link: https://lore.kernel.org/r/20220823063414.59778-1-linmiaohe@huawei.com Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- virt/kvm/kvm_main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d2df08102171..356fd5d1a428 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5014,7 +5014,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, r = kvm_async_pf_init(); if (r) - goto out_free_5; + goto out_free_4; kvm_chardev_ops.owner = module; kvm_vm_fops.owner = module; @@ -5047,10 +5047,9 @@ err_register: kvm_vfio_ops_exit(); err_vfio: kvm_async_pf_deinit(); -out_free_5: +out_free_4: for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); -out_free_4: kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); From 01e4c9c03de8a9f8839cb7342bc4bccf9104efe5 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Mon, 12 Dec 2022 14:50:11 -0800 Subject: [PATCH 2364/4345] NFSD: fix use-after-free in __nfs42_ssc_open() commit 75333d48f92256a0dec91dbf07835e804fc411c0 upstream. Problem caused by source's vfsmount being unmounted but remains on the delayed unmount list. This happens when nfs42_ssc_open() return errors. Fixed by removing nfsd4_interssc_connect(), leave the vfsmount for the laundromat to unmount when idle time expires. We don't need to call nfs_do_sb_deactive when nfs42_ssc_open return errors since the file was not opened so nfs_server->active was not incremented. Same as in nfsd4_copy, if we fail to launch nfsd4_do_async_copy thread then there's no need to call nfs_do_sb_deactive Reported-by: Xingyuan Mo Signed-off-by: Dai Ngo Tested-by: Xingyuan Mo Signed-off-by: Chuck Lever Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman --- fs/nfsd/nfs4proc.c | 22 ++++++---------------- 1 file changed, 6 insertions(+), 16 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f82cfe843b99..3c651cbcf897 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1248,13 +1248,6 @@ out_err: return status; } -static void -nfsd4_interssc_disconnect(struct vfsmount *ss_mnt) -{ - nfs_do_sb_deactive(ss_mnt->mnt_sb); - mntput(ss_mnt); -} - /* * Verify COPY destination stateid. * @@ -1325,11 +1318,6 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, { } -static void -nfsd4_interssc_disconnect(struct vfsmount *ss_mnt) -{ -} - static struct file *nfs42_ssc_open(struct vfsmount *ss_mnt, struct nfs_fh *src_fh, nfs4_stateid *stateid) @@ -1471,14 +1459,14 @@ static int nfsd4_do_async_copy(void *data) copy->nf_src = kzalloc(sizeof(struct nfsd_file), GFP_KERNEL); if (!copy->nf_src) { copy->nfserr = nfserr_serverfault; - nfsd4_interssc_disconnect(copy->ss_mnt); + /* ss_mnt will be unmounted by the laundromat */ goto do_callback; } copy->nf_src->nf_file = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, ©->stateid); if (IS_ERR(copy->nf_src->nf_file)) { copy->nfserr = nfserr_offload_denied; - nfsd4_interssc_disconnect(copy->ss_mnt); + /* ss_mnt will be unmounted by the laundromat */ goto do_callback; } } @@ -1561,8 +1549,10 @@ out_err: if (async_copy) cleanup_async_copy(async_copy); status = nfserrno(-ENOMEM); - if (!copy->cp_intra) - nfsd4_interssc_disconnect(copy->ss_mnt); + /* + * source's vfsmount of inter-copy will be unmounted + * by the laundromat + */ goto out; } From ddb1973e67650dfdc66179b07895b20568a3b251 Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Sun, 6 Mar 2022 22:12:51 +0100 Subject: [PATCH 2365/4345] usb: dwc3: gadget: move cmd_endtransfer to extra function [ Upstream commit e192cc7b52399d1b073f88cd3ba128b74d3a57f1 ] This patch adds the extra function __dwc3_stop_active_transfer to consolidate the same codepath. Signed-off-by: Michael Grzeschik Link: https://lore.kernel.org/r/20220306211251.2281335-3-m.grzeschik@pengutronix.de Signed-off-by: Greg Kroah-Hartman Stable-dep-of: d8a2bb4eb758 ("usb: dwc3: gadget: Add 1ms delay after end transfer command without IOC") Signed-off-by: Sasha Levin --- drivers/usb/dwc3/gadget.c | 69 +++++++++++++++++++++------------------ 1 file changed, 37 insertions(+), 32 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 28a1194f849f..ce5131ccd60a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1440,6 +1440,40 @@ static int __dwc3_gadget_get_frame(struct dwc3 *dwc) return DWC3_DSTS_SOFFN(reg); } +/** + * __dwc3_stop_active_transfer - stop the current active transfer + * @dep: isoc endpoint + * @force: set forcerm bit in the command + * @interrupt: command complete interrupt after End Transfer command + * + * When setting force, the ForceRM bit will be set. In that case + * the controller won't update the TRB progress on command + * completion. It also won't clear the HWO bit in the TRB. + * The command will also not complete immediately in that case. + */ +static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt) +{ + struct dwc3_gadget_ep_cmd_params params; + u32 cmd; + int ret; + + cmd = DWC3_DEPCMD_ENDTRANSFER; + cmd |= force ? DWC3_DEPCMD_HIPRI_FORCERM : 0; + cmd |= interrupt ? DWC3_DEPCMD_CMDIOC : 0; + cmd |= DWC3_DEPCMD_PARAM(dep->resource_index); + memset(¶ms, 0, sizeof(params)); + ret = dwc3_send_gadget_ep_cmd(dep, cmd, ¶ms); + WARN_ON_ONCE(ret); + dep->resource_index = 0; + + if (!interrupt) + dep->flags &= ~DWC3_EP_TRANSFER_STARTED; + else if (!ret) + dep->flags |= DWC3_EP_END_TRANSFER_PENDING; + + return ret; +} + /** * dwc3_gadget_start_isoc_quirk - workaround invalid frame number * @dep: isoc endpoint @@ -1609,21 +1643,8 @@ static int __dwc3_gadget_start_isoc(struct dwc3_ep *dep) * status, issue END_TRANSFER command and retry on the next XferNotReady * event. */ - if (ret == -EAGAIN) { - struct dwc3_gadget_ep_cmd_params params; - u32 cmd; - - cmd = DWC3_DEPCMD_ENDTRANSFER | - DWC3_DEPCMD_CMDIOC | - DWC3_DEPCMD_PARAM(dep->resource_index); - - dep->resource_index = 0; - memset(¶ms, 0, sizeof(params)); - - ret = dwc3_send_gadget_ep_cmd(dep, cmd, ¶ms); - if (!ret) - dep->flags |= DWC3_EP_END_TRANSFER_PENDING; - } + if (ret == -EAGAIN) + ret = __dwc3_stop_active_transfer(dep, false, true); return ret; } @@ -3250,10 +3271,6 @@ static void dwc3_reset_gadget(struct dwc3 *dwc) static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt) { - struct dwc3_gadget_ep_cmd_params params; - u32 cmd; - int ret; - if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) || (dep->flags & DWC3_EP_END_TRANSFER_PENDING)) return; @@ -3285,19 +3302,7 @@ static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, * This mode is NOT available on the DWC_usb31 IP. */ - cmd = DWC3_DEPCMD_ENDTRANSFER; - cmd |= force ? DWC3_DEPCMD_HIPRI_FORCERM : 0; - cmd |= interrupt ? DWC3_DEPCMD_CMDIOC : 0; - cmd |= DWC3_DEPCMD_PARAM(dep->resource_index); - memset(¶ms, 0, sizeof(params)); - ret = dwc3_send_gadget_ep_cmd(dep, cmd, ¶ms); - WARN_ON_ONCE(ret); - dep->resource_index = 0; - - if (!interrupt) - dep->flags &= ~DWC3_EP_TRANSFER_STARTED; - else - dep->flags |= DWC3_EP_END_TRANSFER_PENDING; + __dwc3_stop_active_transfer(dep, force, interrupt); } static void dwc3_clear_stall_all_ep(struct dwc3 *dwc) From a5ce0a559b66b001120af4dfacb75dce4c498c0b Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Mon, 6 Mar 2023 12:05:57 -0800 Subject: [PATCH 2366/4345] usb: dwc3: gadget: Add 1ms delay after end transfer command without IOC [ Upstream commit d8a2bb4eb75866275b5cf7de2e593ac3449643e2 ] Previously, there was a 100uS delay inserted after issuing an end transfer command for specific controller revisions. This was due to the fact that there was a GUCTL2 bit field which enabled synchronous completion of the end transfer command once the CMDACT bit was cleared in the DEPCMD register. Since this bit does not exist for all controller revisions and the current implementation heavily relies on utizling the EndTransfer command completion interrupt, add the delay back in for uses where the interrupt on completion bit is not set, and increase the duration to 1ms for the controller to complete the command. An issue was seen where the USB request buffer was unmapped while the DWC3 controller was still accessing the TRB. However, it was confirmed that the end transfer command was successfully submitted. (no end transfer timeout) In situations, such as dwc3_gadget_soft_disconnect() and __dwc3_gadget_ep_disable(), the dwc3_remove_request() is utilized, which will issue the end transfer command, and follow up with dwc3_gadget_giveback(). At least for the USB ep disable path, it is required for any pending and started requests to be completed and returned to the function driver in the same context of the disable call. Without the GUCTL2 bit, it is not ensured that the end transfer is completed before the buffers are unmapped. Fixes: cf2f8b63f7f1 ("usb: dwc3: gadget: Remove END_TRANSFER delay") Cc: stable Signed-off-by: Wesley Cheng Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230306200557.29387-1-quic_wcheng@quicinc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/dwc3/gadget.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index ce5131ccd60a..01cecde76140 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1453,6 +1453,7 @@ static int __dwc3_gadget_get_frame(struct dwc3 *dwc) */ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt) { + struct dwc3 *dwc = dep->dwc; struct dwc3_gadget_ep_cmd_params params; u32 cmd; int ret; @@ -1466,10 +1467,13 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int WARN_ON_ONCE(ret); dep->resource_index = 0; - if (!interrupt) + if (!interrupt) { + if (!DWC3_IP_IS(DWC3) || DWC3_VER_IS_PRIOR(DWC3, 310A)) + mdelay(1); dep->flags &= ~DWC3_EP_TRANSFER_STARTED; - else if (!ret) + } else if (!ret) { dep->flags |= DWC3_EP_END_TRANSFER_PENDING; + } return ret; } @@ -3299,7 +3303,11 @@ static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, * enabled, the EndTransfer command will have completed upon * returning from this function. * - * This mode is NOT available on the DWC_usb31 IP. + * This mode is NOT available on the DWC_usb31 IP. In this + * case, if the IOC bit is not set, then delay by 1ms + * after issuing the EndTransfer command. This allows for the + * controller to handle the command completely before DWC3 + * remove requests attempts to unmap USB request buffers. */ __dwc3_stop_active_transfer(dep, force, interrupt); From 46ae204069e7d09b36413e71228820153419150e Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Mon, 28 Nov 2022 11:43:58 +0100 Subject: [PATCH 2367/4345] kernel: kcsan: kcsan_test: build without structleak plugin [ Upstream commit 6fcd4267a840d0536b8e5334ad5f31e4105fce85 ] Building kcsan_test with structleak plugin enabled makes the stack frame size to grow. kernel/kcsan/kcsan_test.c:704:1: error: the frame size of 3296 bytes is larger than 2048 bytes [-Werror=frame-larger-than=] Turn off the structleak plugin checks for kcsan_test. Link: https://lkml.kernel.org/r/20221128104358.2660634-1-anders.roxell@linaro.org Signed-off-by: Anders Roxell Suggested-by: Arnd Bergmann Acked-by: Marco Elver Cc: Arnd Bergmann Cc: David Gow Cc: Jason A. Donenfeld Cc: Kees Cook Signed-off-by: Andrew Morton Stable-dep-of: 5eb39cde1e24 ("kcsan: avoid passing -g for test") Signed-off-by: Sasha Levin --- kernel/kcsan/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile index 65ca5539c470..c95957741d36 100644 --- a/kernel/kcsan/Makefile +++ b/kernel/kcsan/Makefile @@ -14,4 +14,5 @@ obj-y := core.o debugfs.o report.o obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o CFLAGS_kcsan-test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer +CFLAGS_kcsan_test.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_KCSAN_TEST) += kcsan-test.o From f7385e0886cda36050e84b15cae2cdbf61415f3d Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 16 Mar 2023 23:47:05 +0100 Subject: [PATCH 2368/4345] kcsan: avoid passing -g for test [ Upstream commit 5eb39cde1e2487ba5ec1802dc5e58a77e700d99e ] Nathan reported that when building with GNU as and a version of clang that defaults to DWARF5, the assembler will complain with: Error: non-constant .uleb128 is not supported This is because `-g` defaults to the compiler debug info default. If the assembler does not support some of the directives used, the above errors occur. To fix, remove the explicit passing of `-g`. All the test wants is that stack traces print valid function names, and debug info is not required for that. (I currently cannot recall why I added the explicit `-g`.) Link: https://lkml.kernel.org/r/20230316224705.709984-2-elver@google.com Fixes: 1fe84fd4a402 ("kcsan: Add test suite") Signed-off-by: Marco Elver Reported-by: Nathan Chancellor Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- kernel/kcsan/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile index c95957741d36..a9b0ee63b697 100644 --- a/kernel/kcsan/Makefile +++ b/kernel/kcsan/Makefile @@ -13,6 +13,6 @@ CFLAGS_core.o := $(call cc-option,-fno-conserve-stack) \ obj-y := core.o debugfs.o report.o obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o -CFLAGS_kcsan-test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer +CFLAGS_kcsan-test.o := $(CFLAGS_KCSAN) -fno-omit-frame-pointer CFLAGS_kcsan_test.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_KCSAN_TEST) += kcsan-test.o From 794a6cea22688db942ee10c258c5f353e7e1649d Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Fri, 31 Dec 2021 00:55:15 +0100 Subject: [PATCH 2369/4345] drm/meson: Fix error handling when afbcd.ops->init fails [ Upstream commit fa747d75f65d1b1cbc3f4691fa67b695e8a399c8 ] When afbcd.ops->init fails we need to free the struct drm_device. Also all errors which come after afbcd.ops->init was successful need to exit the AFBCD, just like meson_drv_unbind() does. Fixes: d1b5e41e13a7e9 ("drm/meson: Add AFBCD module driver") Signed-off-by: Martin Blumenstingl Acked-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20211230235515.1627522-3-martin.blumenstingl@googlemail.com Stable-dep-of: ba98413bf45e ("drm/meson: fix missing component unbind on bind errors") Signed-off-by: Sasha Levin --- drivers/gpu/drm/meson/meson_drv.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index b0bfe85f5f6a..090878bd74f6 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -320,38 +320,38 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) if (priv->afbcd.ops) { ret = priv->afbcd.ops->init(priv); if (ret) - return ret; + goto free_drm; } /* Encoder Initialization */ ret = meson_venc_cvbs_create(priv); if (ret) - goto free_drm; + goto exit_afbcd; if (has_components) { ret = component_bind_all(drm->dev, drm); if (ret) { dev_err(drm->dev, "Couldn't bind all components\n"); - goto free_drm; + goto exit_afbcd; } } ret = meson_plane_create(priv); if (ret) - goto free_drm; + goto exit_afbcd; ret = meson_overlay_create(priv); if (ret) - goto free_drm; + goto exit_afbcd; ret = meson_crtc_create(priv); if (ret) - goto free_drm; + goto exit_afbcd; ret = drm_irq_install(drm, priv->vsync_irq); if (ret) - goto free_drm; + goto exit_afbcd; drm_mode_config_reset(drm); @@ -369,6 +369,9 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) uninstall_irq: drm_irq_uninstall(drm); +exit_afbcd: + if (priv->afbcd.ops) + priv->afbcd.ops->exit(priv); free_drm: drm_dev_put(drm); From 1635a062fa0e045fe9e0eddabdbeff2e66f038d2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 11:35:33 +0100 Subject: [PATCH 2370/4345] drm/meson: fix missing component unbind on bind errors [ Upstream commit ba98413bf45edbf33672e2539e321b851b2cfbd1 ] Make sure to unbind all subcomponents when binding the aggregate device fails. Fixes: a41e82e6c457 ("drm/meson: Add support for components") Cc: stable@vger.kernel.org # 4.12 Cc: Neil Armstrong Signed-off-by: Johan Hovold Acked-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230306103533.4915-1-johan+linaro@kernel.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/meson/meson_drv.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 090878bd74f6..5c29ddf93eb3 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -339,19 +339,19 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) ret = meson_plane_create(priv); if (ret) - goto exit_afbcd; + goto unbind_all; ret = meson_overlay_create(priv); if (ret) - goto exit_afbcd; + goto unbind_all; ret = meson_crtc_create(priv); if (ret) - goto exit_afbcd; + goto unbind_all; ret = drm_irq_install(drm, priv->vsync_irq); if (ret) - goto exit_afbcd; + goto unbind_all; drm_mode_config_reset(drm); @@ -369,6 +369,9 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) uninstall_irq: drm_irq_uninstall(drm); +unbind_all: + if (has_components) + component_unbind_all(drm->dev, drm); exit_afbcd: if (priv->afbcd.ops) priv->afbcd.ops->exit(priv); From b2d19565478f45b3055b70b034014a8bc10fdbfc Mon Sep 17 00:00:00 2001 From: Ivan Bornyakov Date: Mon, 6 Mar 2023 16:25:26 +0300 Subject: [PATCH 2371/4345] bus: imx-weim: fix branch condition evaluates to a garbage value [ Upstream commit 1adab2922c58e7ff4fa9f0b43695079402cce876 ] If bus type is other than imx50_weim_devtype and have no child devices, variable 'ret' in function weim_parse_dt() will not be initialized, but will be used as branch condition and return value. Fix this by initializing 'ret' with 0. This was discovered with help of clang-analyzer, but the situation is quite possible in real life. Fixes: 52c47b63412b ("bus: imx-weim: improve error handling upon child probe-failure") Signed-off-by: Ivan Bornyakov Cc: stable@vger.kernel.org Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- drivers/bus/imx-weim.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index 28bb65a5613f..201767823edb 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -192,8 +192,8 @@ static int weim_parse_dt(struct platform_device *pdev, void __iomem *base) const struct of_device_id *of_id = of_match_device(weim_id_table, &pdev->dev); const struct imx_weim_devtype *devtype = of_id->data; + int ret = 0, have_child = 0; struct device_node *child; - int ret, have_child = 0; struct cs_timing_state ts = {}; u32 reg; From 0b9493b504fc15c63ec9c7d5b47e669a287837e6 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 8 Mar 2023 14:39:54 -0500 Subject: [PATCH 2372/4345] dm crypt: avoid accessing uninitialized tasklet [ Upstream commit d9a02e016aaf5a57fb44e9a5e6da8ccd3b9e2e70 ] When neither "no_read_workqueue" nor "no_write_workqueue" are enabled, tasklet_trylock() in crypt_dec_pending() may still return false due to an uninitialized state, and dm-crypt will unnecessarily do io completion in io_queue workqueue instead of current context. Fix this by adding an 'in_tasklet' flag to dm_crypt_io struct and initialize it to false in crypt_io_init(). Set this flag to true in kcryptd_queue_crypt() before calling tasklet_schedule(). If set crypt_dec_pending() will punt io completion to a workqueue. This also nicely avoids the tasklet_trylock/unlock hack when tasklets aren't in use. Fixes: 8e14f610159d ("dm crypt: do not call bio_endio() from the dm-crypt tasklet") Cc: stable@vger.kernel.org Reported-by: Hou Tao Suggested-by: Ignat Korchagin Reviewed-by: Ignat Korchagin Signed-off-by: Mike Snitzer Signed-off-by: Sasha Levin --- drivers/md/dm-crypt.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 17ddca293965..5d772f322a24 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -67,7 +67,9 @@ struct dm_crypt_io { struct crypt_config *cc; struct bio *base_bio; u8 *integrity_metadata; - bool integrity_metadata_from_pool; + bool integrity_metadata_from_pool:1; + bool in_tasklet:1; + struct work_struct work; struct tasklet_struct tasklet; @@ -1722,6 +1724,7 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc, io->ctx.r.req = NULL; io->integrity_metadata = NULL; io->integrity_metadata_from_pool = false; + io->in_tasklet = false; atomic_set(&io->io_pending, 0); } @@ -1767,14 +1770,13 @@ static void crypt_dec_pending(struct dm_crypt_io *io) * our tasklet. In this case we need to delay bio_endio() * execution to after the tasklet is done and dequeued. */ - if (tasklet_trylock(&io->tasklet)) { - tasklet_unlock(&io->tasklet); - bio_endio(base_bio); + if (io->in_tasklet) { + INIT_WORK(&io->work, kcryptd_io_bio_endio); + queue_work(cc->io_queue, &io->work); return; } - INIT_WORK(&io->work, kcryptd_io_bio_endio); - queue_work(cc->io_queue, &io->work); + bio_endio(base_bio); } /* @@ -2228,6 +2230,7 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io) * it is being executed with irqs disabled. */ if (in_irq() || irqs_disabled()) { + io->in_tasklet = true; tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work); tasklet_schedule(&io->tasklet); return; From 10941fd5c3e18e7958f2bca3904f6972d29b362a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 14 Mar 2023 16:31:32 -0700 Subject: [PATCH 2373/4345] fsverity: don't drop pagecache at end of FS_IOC_ENABLE_VERITY [ Upstream commit a075bacde257f755bea0e53400c9f1cdd1b8e8e6 ] The full pagecache drop at the end of FS_IOC_ENABLE_VERITY is causing performance problems and is hindering adoption of fsverity. It was intended to solve a race condition where unverified pages might be left in the pagecache. But actually it doesn't solve it fully. Since the incomplete solution for this race condition has too much performance impact for it to be worth it, let's remove it for now. Fixes: 3fda4c617e84 ("fs-verity: implement FS_IOC_ENABLE_VERITY ioctl") Cc: stable@vger.kernel.org Reviewed-by: Victor Hsieh Link: https://lore.kernel.org/r/20230314235332.50270-1-ebiggers@kernel.org Signed-off-by: Eric Biggers Signed-off-by: Sasha Levin --- fs/verity/enable.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/fs/verity/enable.c b/fs/verity/enable.c index 734862e608fd..5ceae66e1ae0 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -391,25 +391,27 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *uarg) goto out_drop_write; err = enable_verity(filp, &arg); - if (err) - goto out_allow_write_access; /* - * Some pages of the file may have been evicted from pagecache after - * being used in the Merkle tree construction, then read into pagecache - * again by another process reading from the file concurrently. Since - * these pages didn't undergo verification against the file measurement - * which fs-verity now claims to be enforcing, we have to wipe the - * pagecache to ensure that all future reads are verified. + * We no longer drop the inode's pagecache after enabling verity. This + * used to be done to try to avoid a race condition where pages could be + * evicted after being used in the Merkle tree construction, then + * re-instantiated by a concurrent read. Such pages are unverified, and + * the backing storage could have filled them with different content, so + * they shouldn't be used to fulfill reads once verity is enabled. + * + * But, dropping the pagecache has a big performance impact, and it + * doesn't fully solve the race condition anyway. So for those reasons, + * and also because this race condition isn't very important relatively + * speaking (especially for small-ish files, where the chance of a page + * being used, evicted, *and* re-instantiated all while enabling verity + * is quite small), we no longer drop the inode's pagecache. */ - filemap_write_and_wait(inode->i_mapping); - invalidate_inode_pages2(inode->i_mapping); /* * allow_write_access() is needed to pair with deny_write_access(). * Regardless, the filesystem won't allow writing to verity files. */ -out_allow_write_access: allow_write_access(filp); out_drop_write: mnt_drop_write_file(filp); From 74d6d33f3695070850cc15d3058d1315fb94d380 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 6 Mar 2023 09:36:25 +1100 Subject: [PATCH 2374/4345] md: avoid signed overflow in slot_store() [ Upstream commit 3bc57292278a0b6ac4656cad94c14f2453344b57 ] slot_store() uses kstrtouint() to get a slot number, but stores the result in an "int" variable (by casting a pointer). This can result in a negative slot number if the unsigned int value is very large. A negative number means that the slot is empty, but setting a negative slot number this way will not remove the device from the array. I don't think this is a serious problem, but it could cause confusion and it is best to fix it. Reported-by: Dan Carpenter Signed-off-by: NeilBrown Signed-off-by: Song Liu Signed-off-by: Sasha Levin --- drivers/md/md.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index c0b34637bd66..1553c2495841 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3207,6 +3207,9 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) err = kstrtouint(buf, 10, (unsigned int *)&slot); if (err < 0) return err; + if (slot < 0) + /* overflow */ + return -ENOSPC; } if (rdev->mddev->pers && slot == -1) { /* Setting 'slot' on an active array requires also From b94ffa287415e3950b2fd846c9a10420533f7ef1 Mon Sep 17 00:00:00 2001 From: Kristian Overskeid Date: Tue, 7 Mar 2023 14:32:29 +0100 Subject: [PATCH 2375/4345] net: hsr: Don't log netdev_err message on unknown prp dst node [ Upstream commit 28e8cabe80f3e6e3c98121576eda898eeb20f1b1 ] If no frames has been exchanged with a node for HSR_NODE_FORGET_TIME, the node will be deleted from the node_db list. If a frame is sent to the node after it is deleted, a netdev_err message for each slave interface is produced. This should not happen with dan nodes because of supervision frames, but can happen often with san nodes, which clutters the kernel log. Since the hsr protocol does not support sans, this is only relevant for the prp protocol. Signed-off-by: Kristian Overskeid Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/hsr/hsr_framereg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 20cb6b7dbc69..08627c836884 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -380,7 +380,7 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); if (!node_dst) { - if (net_ratelimit()) + if (net_ratelimit() && port->hsr->prot_version != PRP_V1) netdev_err(skb->dev, "%s: Unknown node\n", __func__); return; } From fcf80111a4f69c85e5b393870f7fc4374d383334 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 13 Mar 2023 00:49:24 +0000 Subject: [PATCH 2376/4345] ALSA: asihpi: check pao in control_message() [ Upstream commit 9026c0bf233db53b86f74f4c620715e94eb32a09 ] control_message() might be called with pao = NULL. Here indicates control_message() as sample. (B) static void control_message(struct hpi_adapter_obj *pao, ...) { ^^^ struct hpi_hw_obj *phw = pao->priv; ... ^^^ } (A) void _HPI_6205(struct hpi_adapter_obj *pao, ...) { ^^^ ... case HPI_OBJ_CONTROL: (B) control_message(pao, phm, phr); break; ^^^ ... } void HPI_6205(...) { ... (A) _HPI_6205(NULL, phm, phr); ... ^^^^ } Therefore, We will get too many warning via cppcheck, like below sound/pci/asihpi/hpi6205.c:238:27: warning: Possible null pointer dereference: pao [nullPointer] struct hpi_hw_obj *phw = pao->priv; ^ sound/pci/asihpi/hpi6205.c:433:13: note: Calling function '_HPI_6205', 1st argument 'NULL' value is 0 _HPI_6205(NULL, phm, phr); ^ sound/pci/asihpi/hpi6205.c:401:20: note: Calling function 'control_message', 1st argument 'pao' value is 0 control_message(pao, phm, phr); ^ Set phr->error like many functions doing, and don't call _HPI_6205() with NULL. Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/87ttypeaqz.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/asihpi/hpi6205.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/asihpi/hpi6205.c b/sound/pci/asihpi/hpi6205.c index 3d6914c64c4a..4cdaeefeb688 100644 --- a/sound/pci/asihpi/hpi6205.c +++ b/sound/pci/asihpi/hpi6205.c @@ -430,7 +430,7 @@ void HPI_6205(struct hpi_message *phm, struct hpi_response *phr) pao = hpi_find_adapter(phm->adapter_index); } else { /* subsys messages don't address an adapter */ - _HPI_6205(NULL, phm, phr); + phr->error = HPI_ERROR_INVALID_OBJ_INDEX; return; } From baef27176ea5fdc7ad0947e2dc7733855e35db71 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 13 Mar 2023 00:50:28 +0000 Subject: [PATCH 2377/4345] ALSA: hda/ca0132: fixup buffer overrun at tuning_ctl_set() [ Upstream commit 98e5eb110095ec77cb6d775051d181edbf9cd3cf ] tuning_ctl_set() might have buffer overrun at (X) if it didn't break from loop by matching (A). static int tuning_ctl_set(...) { for (i = 0; i < TUNING_CTLS_COUNT; i++) (A) if (nid == ca0132_tuning_ctls[i].nid) break; snd_hda_power_up(...); (X) dspio_set_param(..., ca0132_tuning_ctls[i].mid, ...); snd_hda_power_down(...); ^ return 1; } We will get below error by cppcheck sound/pci/hda/patch_ca0132.c:4229:2: note: After for loop, i has value 12 for (i = 0; i < TUNING_CTLS_COUNT; i++) ^ sound/pci/hda/patch_ca0132.c:4234:43: note: Array index out of bounds dspio_set_param(codec, ca0132_tuning_ctls[i].mid, 0x20, ^ This patch cares non match case. Signed-off-by: Kuninori Morimoto Link: https://lore.kernel.org/r/87sfe9eap7.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_ca0132.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 24c2638cde37..6057084da4cf 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -4108,8 +4108,10 @@ static int tuning_ctl_set(struct hda_codec *codec, hda_nid_t nid, for (i = 0; i < TUNING_CTLS_COUNT; i++) if (nid == ca0132_tuning_ctls[i].nid) - break; + goto found; + return -EINVAL; +found: snd_hda_power_up(codec); dspio_set_param(codec, ca0132_tuning_ctls[i].mid, 0x20, ca0132_tuning_ctls[i].req, From 6eaa2254cc5ed8fbc583186083fc87e8aece759a Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Tue, 7 Mar 2023 13:08:56 +0000 Subject: [PATCH 2378/4345] fbdev: tgafb: Fix potential divide by zero [ Upstream commit f90bd245de82c095187d8c2cabb8b488a39eaecc ] fb_set_var would by called when user invokes ioctl with cmd FBIOPUT_VSCREENINFO. User-provided data would finally reach tgafb_check_var. In case var->pixclock is assigned to zero, divide by zero would occur when checking whether reciprocal of var->pixclock is too high. Similar crashes have happened in other fbdev drivers. There is no check and modification on var->pixclock along the call chain to tgafb_check_var. We believe it could also be triggered in driver tgafb from user site. Signed-off-by: Wei Chen Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/tgafb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/video/fbdev/tgafb.c b/drivers/video/fbdev/tgafb.c index 666fbe2f671c..98a2977fd427 100644 --- a/drivers/video/fbdev/tgafb.c +++ b/drivers/video/fbdev/tgafb.c @@ -166,6 +166,9 @@ tgafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { struct tga_par *par = (struct tga_par *)info->par; + if (!var->pixclock) + return -EINVAL; + if (par->tga_type == TGA_TYPE_8PLANE) { if (var->bits_per_pixel != 8) return -EINVAL; From 1f2a94baee431c73b7e2a3230b1adafef6128000 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 14 Mar 2023 19:32:38 -0700 Subject: [PATCH 2379/4345] sched_getaffinity: don't assume 'cpumask_size()' is fully initialized [ Upstream commit 6015b1aca1a233379625385feb01dd014aca60b5 ] The getaffinity() system call uses 'cpumask_size()' to decide how big the CPU mask is - so far so good. It is indeed the allocation size of a cpumask. But the code also assumes that the whole allocation is initialized without actually doing so itself. That's wrong, because we might have fixed-size allocations (making copying and clearing more efficient), but not all of it is then necessarily used if 'nr_cpu_ids' is smaller. Having checked other users of 'cpumask_size()', they all seem to be ok, either using it purely for the allocation size, or explicitly zeroing the cpumask before using the size in bytes to copy it. See for example the ublk_ctrl_get_queue_affinity() function that uses the proper 'zalloc_cpumask_var()' to make sure that the whole mask is cleared, whether the storage is on the stack or if it was an external allocation. Fix this by just zeroing the allocation before using it. Do the same for the compat version of sched_getaffinity(), which had the same logic. Also, for consistency, make sched_getaffinity() use 'cpumask_bits()' to access the bits. For a cpumask_var_t, it ends up being a pointer to the same data either way, but it's just a good idea to treat it like you would a 'cpumask_t'. The compat case already did that. Reported-by: Ryan Roberts Link: https://lore.kernel.org/lkml/7d026744-6bd6-6827-0471-b5e8eae0be3f@arm.com/ Cc: Yury Norov Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- kernel/compat.c | 2 +- kernel/sched/core.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/compat.c b/kernel/compat.c index 05adfd6fa8bf..f9f7a79e07c5 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -152,7 +152,7 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, if (len & (sizeof(compat_ulong_t)-1)) return -EINVAL; - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; ret = sched_getaffinity(pid, mask); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index abea8fb7bdd1..b4bd02d68185 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6067,14 +6067,14 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, if (len & (sizeof(unsigned long)-1)) return -EINVAL; - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; ret = sched_getaffinity(pid, mask); if (ret == 0) { unsigned int retlen = min(len, cpumask_size()); - if (copy_to_user(user_mask_ptr, mask, retlen)) + if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen)) ret = -EFAULT; else ret = retlen; From 78eb964805f9ed40270a3c9339d68d7715cea18f Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Wed, 15 Mar 2023 07:18:31 +0000 Subject: [PATCH 2380/4345] fbdev: nvidia: Fix potential divide by zero [ Upstream commit 92e2a00f2987483e1f9253625828622edd442e61 ] variable var->pixclock can be set by user. In case it equals to zero, divide by zero would occur in nvidiafb_set_par. Similar crashes have happened in other fbdev drivers. There is no check and modification on var->pixclock along the call chain to nvidia_check_var and nvidiafb_set_par. We believe it could also be triggered in driver nvidia from user site. Signed-off-by: Wei Chen Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/nvidia/nvidia.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/fbdev/nvidia/nvidia.c b/drivers/video/fbdev/nvidia/nvidia.c index a372a183c1f0..f9c388a8c10e 100644 --- a/drivers/video/fbdev/nvidia/nvidia.c +++ b/drivers/video/fbdev/nvidia/nvidia.c @@ -763,6 +763,8 @@ static int nvidiafb_check_var(struct fb_var_screeninfo *var, int pitch, err = 0; NVTRACE_ENTER(); + if (!var->pixclock) + return -EINVAL; var->transp.offset = 0; var->transp.length = 0; From c2be7f80562dcc82382857cecc97d4c23c1140cf Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Wed, 15 Mar 2023 08:33:47 +0000 Subject: [PATCH 2381/4345] fbdev: intelfb: Fix potential divide by zero [ Upstream commit d823685486a3446d061fed7c7d2f80af984f119a ] Variable var->pixclock is controlled by user and can be assigned to zero. Without proper check, divide by zero would occur in intelfbhw_validate_mode and intelfbhw_mode_to_hw. Error out if var->pixclock is zero. Signed-off-by: Wei Chen Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/intelfb/intelfbdrv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/video/fbdev/intelfb/intelfbdrv.c b/drivers/video/fbdev/intelfb/intelfbdrv.c index a9579964eaba..8a703adfa936 100644 --- a/drivers/video/fbdev/intelfb/intelfbdrv.c +++ b/drivers/video/fbdev/intelfb/intelfbdrv.c @@ -1214,6 +1214,9 @@ static int intelfb_check_var(struct fb_var_screeninfo *var, dinfo = GET_DINFO(info); + if (!var->pixclock) + return -EINVAL; + /* update the pitch */ if (intelfbhw_validate_mode(dinfo, var) != 0) return -EINVAL; From ce5551db36294764bdbda7d2bf794d13d5dd352c Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Wed, 15 Mar 2023 09:05:18 +0000 Subject: [PATCH 2382/4345] fbdev: lxfb: Fix potential divide by zero [ Upstream commit 61ac4b86a4c047c20d5cb423ddd87496f14d9868 ] var->pixclock can be assigned to zero by user. Without proper check, divide by zero would occur in lx_set_clock. Error out if var->pixclock is zero. Signed-off-by: Wei Chen Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/geode/lxfb_core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/video/fbdev/geode/lxfb_core.c b/drivers/video/fbdev/geode/lxfb_core.c index 66c81262d18f..6c6b6efb49f6 100644 --- a/drivers/video/fbdev/geode/lxfb_core.c +++ b/drivers/video/fbdev/geode/lxfb_core.c @@ -234,6 +234,9 @@ static void get_modedb(struct fb_videomode **modedb, unsigned int *size) static int lxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { + if (!var->pixclock) + return -EINVAL; + if (var->xres > 1920 || var->yres > 1440) return -EINVAL; From 5ec5680dc656c80e4004969299bc6f27e2291434 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Wed, 15 Mar 2023 09:22:54 +0000 Subject: [PATCH 2383/4345] fbdev: au1200fb: Fix potential divide by zero [ Upstream commit 44a3b36b42acfc433aaaf526191dd12fbb919fdb ] var->pixclock can be assigned to zero by user. Without proper check, divide by zero would occur when invoking macro PICOS2KHZ in au1200fb_fb_check_var. Error out if var->pixclock is zero. Signed-off-by: Wei Chen Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/au1200fb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c index c00e01a17368..a8a0a448cdb5 100644 --- a/drivers/video/fbdev/au1200fb.c +++ b/drivers/video/fbdev/au1200fb.c @@ -1040,6 +1040,9 @@ static int au1200fb_fb_check_var(struct fb_var_screeninfo *var, u32 pixclock; int screen_size, plane; + if (!var->pixclock) + return -EINVAL; + plane = fbdev->plane; /* Make sure that the mode respect all LCD controller and From 038765a095fd6dc13128c0d350c53d89ace690dc Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Thu, 15 Dec 2022 10:18:16 -0500 Subject: [PATCH 2384/4345] tools/power turbostat: Fix /dev/cpu_dma_latency warnings [ Upstream commit 40aafc7d58d3544f152a863a0e9863014b6d5d8c ] When running as non-root the following error is seen in turbostat: turbostat: fopen /dev/cpu_dma_latency : Permission denied turbostat and the man page have information on how to avoid other permission errors, so these can be fixed the same way. Provide better /dev/cpu_dma_latency warnings that provide instructions on how to avoid the error, and update the man page. Signed-off-by: Prarit Bhargava Cc: linux-pm@vger.kernel.org Signed-off-by: Len Brown Signed-off-by: Sasha Levin --- tools/power/x86/turbostat/turbostat.8 | 2 ++ tools/power/x86/turbostat/turbostat.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index f6b7e85b121c..71e3f3a68b9d 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -294,6 +294,8 @@ Alternatively, non-root users can be enabled to run turbostat this way: # chmod +r /dev/cpu/*/msr +# chmod +r /dev/cpu_dma_latency + .B "turbostat " reads hardware counters, but doesn't write them. So it will not interfere with the OS or other programs, including diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index ef65f7eed1ec..d33c9d427e57 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -5004,7 +5004,7 @@ void print_dev_latency(void) retval = read(fd, (void *)&value, sizeof(int)); if (retval != sizeof(int)) { - warn("read %s\n", path); + warn("read failed %s\n", path); close(fd); return; } From 8b1269b709c9d3314cb2c6283474c4e5340621b7 Mon Sep 17 00:00:00 2001 From: Anton Gusev Date: Tue, 31 Jan 2023 10:58:18 +0300 Subject: [PATCH 2385/4345] tracing: Fix wrong return in kprobe_event_gen_test.c [ Upstream commit bc4f359b3b607daac0290d0038561237a86b38cb ] Overwriting the error code with the deletion result may cause the function to return 0 despite encountering an error. Commit b111545d26c0 ("tracing: Remove the useless value assignment in test_create_synth_event()") solves a similar issue by returning the original error code, so this patch does the same. Found by Linux Verification Center (linuxtesting.org) with SVACE. Link: https://lore.kernel.org/linux-trace-kernel/20230131075818.5322-1-aagusev@ispras.ru Signed-off-by: Anton Gusev Reviewed-by: Steven Rostedt (Google) Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/kprobe_event_gen_test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c index c736487fc0e4..e0c420eb0b2b 100644 --- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -146,7 +146,7 @@ static int __init test_gen_kprobe_cmd(void) if (trace_event_file_is_valid(gen_kprobe_test)) gen_kprobe_test = NULL; /* We got an error after creating the event, delete it */ - ret = kprobe_event_delete("gen_kprobe_test"); + kprobe_event_delete("gen_kprobe_test"); goto out; } @@ -211,7 +211,7 @@ static int __init test_gen_kretprobe_cmd(void) if (trace_event_file_is_valid(gen_kretprobe_test)) gen_kretprobe_test = NULL; /* We got an error after creating the event, delete it */ - ret = kprobe_event_delete("gen_kretprobe_test"); + kprobe_event_delete("gen_kretprobe_test"); goto out; } From ac63f78d9aca3cd10802b2d9e6c12a3f03b262c7 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Mon, 6 Mar 2023 11:18:24 -0800 Subject: [PATCH 2386/4345] ca8210: Fix unsigned mac_len comparison with zero in ca8210_skb_tx() [ Upstream commit 748b2f5e82d17480404b3e2895388fc2925f7caf ] mac_len is of type unsigned, which can never be less than zero. mac_len = ieee802154_hdr_peek_addrs(skb, &header); if (mac_len < 0) return mac_len; Change this to type int as ieee802154_hdr_peek_addrs() can return negative integers, this is found by static analysis with smatch. Fixes: 6c993779ea1d ("ca8210: fix mac_len negative array access") Signed-off-by: Harshit Mogalapalli Acked-by: Alexander Aring Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230306191824.4115839-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Stefan Schmidt Signed-off-by: Sasha Levin --- drivers/net/ieee802154/ca8210.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 5beb447529f9..1c5d70c60354 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -1945,10 +1945,9 @@ static int ca8210_skb_tx( struct ca8210_priv *priv ) { - int status; struct ieee802154_hdr header = { }; struct secspec secspec; - unsigned int mac_len; + int mac_len, status; dev_dbg(&priv->spi->dev, "%s called\n", __func__); From 47a449ec09b4479b89dcc6b27ec3829fc82ffafb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Fri, 17 Mar 2023 11:20:04 +0100 Subject: [PATCH 2387/4345] mips: bmips: BCM6358: disable RAC flush for TP1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ab327f8acdf8d06601fbf058859a539a9422afff ] RAC flush causes kernel panics on BCM6358 with EHCI/OHCI when booting from TP1: [ 3.881739] usb 1-1: new high-speed USB device number 2 using ehci-platform [ 3.895011] Reserved instruction in kernel code[#1]: [ 3.900113] CPU: 0 PID: 1 Comm: init Not tainted 5.10.16 #0 [ 3.905829] $ 0 : 00000000 10008700 00000000 77d94060 [ 3.911238] $ 4 : 7fd1f088 00000000 81431cac 81431ca0 [ 3.916641] $ 8 : 00000000 ffffefff 8075cd34 00000000 [ 3.922043] $12 : 806f8d40 f3e812b7 00000000 000d9aaa [ 3.927446] $16 : 7fd1f068 7fd1f080 7ff559b8 81428470 [ 3.932848] $20 : 00000000 00000000 55590000 77d70000 [ 3.938251] $24 : 00000018 00000010 [ 3.943655] $28 : 81430000 81431e60 81431f28 800157fc [ 3.949058] Hi : 00000000 [ 3.952013] Lo : 00000000 [ 3.955019] epc : 80015808 setup_sigcontext+0x54/0x24c [ 3.960464] ra : 800157fc setup_sigcontext+0x48/0x24c [ 3.965913] Status: 10008703 KERNEL EXL IE [ 3.970216] Cause : 00800028 (ExcCode 0a) [ 3.974340] PrId : 0002a010 (Broadcom BMIPS4350) [ 3.979170] Modules linked in: ohci_platform ohci_hcd fsl_mph_dr_of ehci_platform ehci_fsl ehci_hcd gpio_button_hotplug usbcore nls_base usb_common [ 3.992907] Process init (pid: 1, threadinfo=(ptrval), task=(ptrval), tls=77e22ec8) [ 4.000776] Stack : 81431ef4 7fd1f080 81431f28 81428470 7fd1f068 81431edc 7ff559b8 81428470 [ 4.009467] 81431f28 7fd1f080 55590000 77d70000 77d5498c 80015c70 806f0000 8063ae74 [ 4.018149] 08100002 81431f28 0000000a 08100002 81431f28 0000000a 77d6b418 00000003 [ 4.026831] ffffffff 80016414 80080734 81431ecc 81431ecc 00000001 00000000 04000000 [ 4.035512] 77d54874 00000000 00000000 00000000 00000000 00000012 00000002 00000000 [ 4.044196] ... [ 4.046706] Call Trace: [ 4.049238] [<80015808>] setup_sigcontext+0x54/0x24c [ 4.054356] [<80015c70>] setup_frame+0xdc/0x124 [ 4.059015] [<80016414>] do_notify_resume+0x1dc/0x288 [ 4.064207] [<80011b50>] work_notifysig+0x10/0x18 [ 4.069036] [ 4.070538] Code: 8fc300b4 00001025 26240008 ac830004 3c048063 0c0228aa 24846a00 26240010 [ 4.080686] [ 4.082517] ---[ end trace 22a8edb41f5f983b ]--- [ 4.087374] Kernel panic - not syncing: Fatal exception [ 4.092753] Rebooting in 1 seconds.. Because the bootloader (CFE) is not initializing the Read-ahead cache properly on the second thread (TP1). Since the RAC was not initialized properly, we should avoid flushing it at the risk of corrupting the instruction stream as seen in the trace above. Fixes: d59098a0e9cb ("MIPS: bmips: use generic dma noncoherent ops") Signed-off-by: Álvaro Fernández Rojas Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/bmips/dma.c | 5 +++++ arch/mips/bmips/setup.c | 8 ++++++++ 2 files changed, 13 insertions(+) diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c index 49061b870680..daef44f68298 100644 --- a/arch/mips/bmips/dma.c +++ b/arch/mips/bmips/dma.c @@ -64,6 +64,8 @@ phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr) return dma_addr; } +bool bmips_rac_flush_disable; + void arch_sync_dma_for_cpu_all(void) { void __iomem *cbr = BMIPS_GET_CBR(); @@ -74,6 +76,9 @@ void arch_sync_dma_for_cpu_all(void) boot_cpu_type() != CPU_BMIPS4380) return; + if (unlikely(bmips_rac_flush_disable)) + return; + /* Flush stale data out of the readahead cache */ cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG); __raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG); diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index 1b06b25aea87..16063081d61e 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -34,6 +34,8 @@ #define REG_BCM6328_OTP ((void __iomem *)CKSEG1ADDR(0x1000062c)) #define BCM6328_TP1_DISABLED BIT(9) +extern bool bmips_rac_flush_disable; + static const unsigned long kbase = VMLINUX_LOAD_ADDRESS & 0xfff00000; struct bmips_quirk { @@ -103,6 +105,12 @@ static void bcm6358_quirks(void) * disable SMP for now */ bmips_smp_enabled = 0; + + /* + * RAC flush causes kernel panics on BCM6358 when booting from TP1 + * because the bootloader is not initializing it properly. + */ + bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)); } static void bcm6368_quirks(void) From 4a81e2da7297f0518e27308f8fcc41db380d4fbc Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Mon, 13 Mar 2023 10:32:44 +0300 Subject: [PATCH 2388/4345] mtd: rawnand: meson: invalidate cache on polling ECC bit [ Upstream commit e732e39ed9929c05fd219035bc9653ba4100d4fa ] 'info_buf' memory is cached and driver polls ECC bit in it. This bit is set by the NAND controller. If 'usleep_range()' returns before device sets this bit, 'info_buf' will be cached and driver won't see update of this bit and will loop forever. Fixes: 8fae856c5350 ("mtd: rawnand: meson: add support for Amlogic NAND flash controller") Signed-off-by: Arseniy Krasnov Reviewed-by: Neil Armstrong Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/d4ef0bd6-816e-f6fa-9385-f05f775f0ae2@sberdevices.ru Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/meson_nand.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 38f490088d76..dc631c514318 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -172,6 +172,7 @@ struct meson_nfc { dma_addr_t daddr; dma_addr_t iaddr; + u32 info_bytes; unsigned long assigned_cs; }; @@ -499,6 +500,7 @@ static int meson_nfc_dma_buffer_setup(struct nand_chip *nand, void *databuf, nfc->daddr, datalen, dir); return ret; } + nfc->info_bytes = infolen; cmd = GENCMDIADDRL(NFC_CMD_AIL, nfc->iaddr); writel(cmd, nfc->reg_base + NFC_REG_CMD); @@ -516,8 +518,10 @@ static void meson_nfc_dma_buffer_release(struct nand_chip *nand, struct meson_nfc *nfc = nand_get_controller_data(nand); dma_unmap_single(nfc->dev, nfc->daddr, datalen, dir); - if (infolen) + if (infolen) { dma_unmap_single(nfc->dev, nfc->iaddr, infolen, dir); + nfc->info_bytes = 0; + } } static int meson_nfc_read_buf(struct nand_chip *nand, u8 *buf, int len) @@ -706,6 +710,8 @@ static void meson_nfc_check_ecc_pages_valid(struct meson_nfc *nfc, usleep_range(10, 15); /* info is updated by nfc dma engine*/ smp_rmb(); + dma_sync_single_for_cpu(nfc->dev, nfc->iaddr, nfc->info_bytes, + DMA_FROM_DEVICE); ret = *info & ECC_COMPLETE; } while (!ret); } From 059c3a7a3d6ddc48f6b93c21bdfb6585bc2a6888 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Thu, 23 Mar 2023 09:34:17 +0100 Subject: [PATCH 2389/4345] sfc: ef10: don't overwrite offload features at NIC reset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ca4a80e4bb7e87daf33b27d2ab9e4f5311018a89 ] At NIC reset, some offload features related to encapsulated traffic might have changed (this mainly happens if the firmware-variant is changed with the sfboot userspace tool). Because of this, features are checked and set again at reset time. However, this was not done right, and some features were improperly overwritten at NIC reset: - Tunneled IPv6 segmentation was always disabled - Features disabled with ethtool were reenabled - Features that becomes unsupported after the reset were not disabled Also, checking if the device supports IPV6_CSUM to enable TSO6 is no longer necessary because all currently supported devices support it. Additionally, move the assignment of some other features to the EF10_OFFLOAD_FEATURES macro, like it is done in ef100, leaving the selection of features in efx_pci_probe_post_io a bit cleaner. Fixes: ffffd2454a7a ("sfc: correctly advertise tunneled IPv6 segmentation") Fixes: 24b2c3751aa3 ("sfc: advertise encapsulated offloads on EF10") Reported-by: Tianhao Zhao Suggested-by: Jonathan Cooper Tested-by: Jonathan Cooper Signed-off-by: Íñigo Huguet Acked-by: Edward Cree Link: https://lore.kernel.org/r/20230323083417.7345-1-ihuguet@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/sfc/ef10.c | 40 ++++++++++++++++++++++----------- drivers/net/ethernet/sfc/efx.c | 17 ++++++-------- 2 files changed, 34 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index eb1be7302082..32654fe1f8b5 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1304,7 +1304,8 @@ static void efx_ef10_fini_nic(struct efx_nic *efx) static int efx_ef10_init_nic(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; - netdev_features_t hw_enc_features = 0; + struct net_device *net_dev = efx->net_dev; + netdev_features_t tun_feats, tso_feats; int rc; if (nic_data->must_check_datapath_caps) { @@ -1349,20 +1350,30 @@ static int efx_ef10_init_nic(struct efx_nic *efx) nic_data->must_restore_piobufs = false; } - /* add encapsulated checksum offload features */ + /* encap features might change during reset if fw variant changed */ if (efx_has_cap(efx, VXLAN_NVGRE) && !efx_ef10_is_vf(efx)) - hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - /* add encapsulated TSO features */ + net_dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + else + net_dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); + + tun_feats = NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | + NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM; + tso_feats = NETIF_F_TSO | NETIF_F_TSO6; + if (efx_has_cap(efx, TX_TSO_V2_ENCAP)) { - netdev_features_t encap_tso_features; - - encap_tso_features = NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | - NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM; - - hw_enc_features |= encap_tso_features | NETIF_F_TSO; - efx->net_dev->features |= encap_tso_features; + /* If this is first nic_init, or if it is a reset and a new fw + * variant has added new features, enable them by default. + * If the features are not new, maintain their current value. + */ + if (!(net_dev->hw_features & tun_feats)) + net_dev->features |= tun_feats; + net_dev->hw_enc_features |= tun_feats | tso_feats; + net_dev->hw_features |= tun_feats; + } else { + net_dev->hw_enc_features &= ~(tun_feats | tso_feats); + net_dev->hw_features &= ~tun_feats; + net_dev->features &= ~tun_feats; } - efx->net_dev->hw_enc_features = hw_enc_features; /* don't fail init if RSS setup doesn't work */ rc = efx->type->rx_push_rss_config(efx, false, @@ -3977,7 +3988,10 @@ static unsigned int ef10_check_caps(const struct efx_nic *efx, NETIF_F_HW_VLAN_CTAG_FILTER | \ NETIF_F_IPV6_CSUM | \ NETIF_F_RXHASH | \ - NETIF_F_NTUPLE) + NETIF_F_NTUPLE | \ + NETIF_F_SG | \ + NETIF_F_RXCSUM | \ + NETIF_F_RXALL) const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .is_vf = true, diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 29c8d2c99004..c069659c9e2d 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1045,21 +1045,18 @@ static int efx_pci_probe_post_io(struct efx_nic *efx) } /* Determine netdevice features */ - net_dev->features |= (efx->type->offload_features | NETIF_F_SG | - NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_RXALL); - if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) { - net_dev->features |= NETIF_F_TSO6; - if (efx_has_cap(efx, TX_TSO_V2_ENCAP)) - net_dev->hw_enc_features |= NETIF_F_TSO6; - } - /* Check whether device supports TSO */ - if (!efx->type->tso_versions || !efx->type->tso_versions(efx)) - net_dev->features &= ~NETIF_F_ALL_TSO; + net_dev->features |= efx->type->offload_features; + + /* Add TSO features */ + if (efx->type->tso_versions && efx->type->tso_versions(efx)) + net_dev->features |= NETIF_F_TSO | NETIF_F_TSO6; + /* Mask for features that also apply to VLAN devices */ net_dev->vlan_features |= (NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_ALL_TSO | NETIF_F_RXCSUM); + /* Determine user configurable features */ net_dev->hw_features |= net_dev->features & ~efx->fixed_features; /* Disable receiving frames with bad FCS, by default. */ From 6ff4a54c0218a2e23b808648a3c0689589d0c502 Mon Sep 17 00:00:00 2001 From: Tomas Henzl Date: Fri, 24 Mar 2023 16:01:34 +0100 Subject: [PATCH 2390/4345] scsi: megaraid_sas: Fix crash after a double completion [ Upstream commit 2309df27111a51734cb9240b4d3c25f2f3c6ab06 ] When a physical disk is attached directly "without JBOD MAP support" (see megasas_get_tm_devhandle()) then there is no real error handling in the driver. Return FAILED instead of SUCCESS. Fixes: 18365b138508 ("megaraid_sas: Task management support") Signed-off-by: Tomas Henzl Link: https://lore.kernel.org/r/20230324150134.14696-1-thenzl@redhat.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/megaraid/megaraid_sas_fusion.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index 7838c7911add..8eb126d48462 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -4656,7 +4656,7 @@ int megasas_task_abort_fusion(struct scsi_cmnd *scmd) devhandle = megasas_get_tm_devhandle(scmd->device); if (devhandle == (u16)ULONG_MAX) { - ret = SUCCESS; + ret = FAILED; sdev_printk(KERN_INFO, scmd->device, "task abort issued for invalid devhandle\n"); mutex_unlock(&instance->reset_mutex); @@ -4726,7 +4726,7 @@ int megasas_reset_target_fusion(struct scsi_cmnd *scmd) devhandle = megasas_get_tm_devhandle(scmd->device); if (devhandle == (u16)ULONG_MAX) { - ret = SUCCESS; + ret = FAILED; sdev_printk(KERN_INFO, scmd->device, "target reset issued for invalid devhandle\n"); mutex_unlock(&instance->reset_mutex); From 3907fcb5a439933cf8c10d6dc300bc11eba30de3 Mon Sep 17 00:00:00 2001 From: SongJingyi Date: Fri, 24 Mar 2023 11:14:06 +0800 Subject: [PATCH 2391/4345] ptp_qoriq: fix memory leak in probe() [ Upstream commit f33642224e38d7e0d59336e10e7b4e370b1c4506 ] Smatch complains that: drivers/ptp/ptp_qoriq.c ptp_qoriq_probe() warn: 'base' from ioremap() not released. Fix this by revising the parameter from 'ptp_qoriq->base' to 'base'. This is only a bug if ptp_qoriq_init() returns on the first -ENODEV error path. For other error paths ptp_qoriq->base and base are the same. And this change makes the code more readable. Fixes: 7f4399ba405b ("ptp_qoriq: fix NULL access if ptp dt node missing") Signed-off-by: SongJingyi Reviewed-by: Dan Carpenter Reviewed-by: Dongliang Mu Link: https://lore.kernel.org/r/20230324031406.1895159-1-u201912584@hust.edu.cn Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/ptp/ptp_qoriq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index 08f4cf0ad9e3..8fa9772acf79 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -601,7 +601,7 @@ static int ptp_qoriq_probe(struct platform_device *dev) return 0; no_clock: - iounmap(ptp_qoriq->base); + iounmap(base); no_ioremap: release_resource(ptp_qoriq->rsrc); no_resource: From 69ed49a7b881ffe6588058411b0205f49b81071a Mon Sep 17 00:00:00 2001 From: ChunHao Lin Date: Thu, 23 Mar 2023 22:33:09 +0800 Subject: [PATCH 2392/4345] r8169: fix RTL8168H and RTL8107E rx crc error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 33189f0a94b9639c058781fcf82e4ea3803b1682 ] When link speed is 10 Mbps and temperature is under -20°C, RTL8168H and RTL8107E may have rx crc error. Disable phy 10 Mbps pll off to fix this issue. Fixes: 6e1d0b898818 ("r8169:add support for RTL8168H and RTL8107E") Signed-off-by: ChunHao Lin Reviewed-by: Heiner Kallweit Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/realtek/r8169_phy_config.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index 913d030d73eb..e18a76f5049f 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -970,6 +970,9 @@ static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp, /* disable phy pfm mode */ phy_modify_paged(phydev, 0x0a44, 0x11, BIT(7), 0); + /* disable 10m pll off */ + phy_modify_paged(phydev, 0x0a43, 0x10, BIT(0), 0); + rtl8168g_disable_aldps(phydev); rtl8168g_config_eee_phy(phydev); } From 1025c471517bba5a43ded0f37be6f6ea2dbb5f29 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 26 Mar 2023 10:29:33 +0200 Subject: [PATCH 2393/4345] regulator: Handle deferred clk [ Upstream commit 02bcba0b9f9da706d5bd1e8cbeb83493863e17b5 ] devm_clk_get() can return -EPROBE_DEFER. So it is better to return the error code from devm_clk_get(), instead of a hard coded -ENOENT. This gives more opportunities to successfully probe the driver. Fixes: 8959e5324485 ("regulator: fixed: add possibility to enable by clock") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/18459fae3d017a66313699c7c8456b28158b2dd0.1679819354.git.christophe.jaillet@wanadoo.fr Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/fixed.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index 3de7709bdcd4..4acfff190807 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -175,7 +175,7 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev) drvdata->enable_clock = devm_clk_get(dev, NULL); if (IS_ERR(drvdata->enable_clock)) { dev_err(dev, "Can't get enable-clock from devicetree\n"); - return -ENOENT; + return PTR_ERR(drvdata->enable_clock); } } else { drvdata->desc.ops = &fixed_voltage_ops; From f032e125149d914e542548c17ebd613851031368 Mon Sep 17 00:00:00 2001 From: Faicker Mo Date: Fri, 24 Mar 2023 17:19:54 +0800 Subject: [PATCH 2394/4345] net/net_failover: fix txq exceeding warning [ Upstream commit e3cbdcb0fbb61045ef3ce0e072927cc41737f787 ] The failover txq is inited as 16 queues. when a packet is transmitted from the failover device firstly, the failover device will select the queue which is returned from the primary device if the primary device is UP and running. If the primary device txq is bigger than the default 16, it can lead to the following warning: eth0 selects TX queue 18, but real number of TX queues is 16 The warning backtrace is: [ 32.146376] CPU: 18 PID: 9134 Comm: chronyd Tainted: G E 6.2.8-1.el7.centos.x86_64 #1 [ 32.147175] Hardware name: Red Hat KVM, BIOS 1.10.2-3.el7_4.1 04/01/2014 [ 32.147730] Call Trace: [ 32.147971] [ 32.148183] dump_stack_lvl+0x48/0x70 [ 32.148514] dump_stack+0x10/0x20 [ 32.148820] netdev_core_pick_tx+0xb1/0xe0 [ 32.149180] __dev_queue_xmit+0x529/0xcf0 [ 32.149533] ? __check_object_size.part.0+0x21c/0x2c0 [ 32.149967] ip_finish_output2+0x278/0x560 [ 32.150327] __ip_finish_output+0x1fe/0x2f0 [ 32.150690] ip_finish_output+0x2a/0xd0 [ 32.151032] ip_output+0x7a/0x110 [ 32.151337] ? __pfx_ip_finish_output+0x10/0x10 [ 32.151733] ip_local_out+0x5e/0x70 [ 32.152054] ip_send_skb+0x19/0x50 [ 32.152366] udp_send_skb.isra.0+0x163/0x3a0 [ 32.152736] udp_sendmsg+0xba8/0xec0 [ 32.153060] ? __folio_memcg_unlock+0x25/0x60 [ 32.153445] ? __pfx_ip_generic_getfrag+0x10/0x10 [ 32.153854] ? sock_has_perm+0x85/0xa0 [ 32.154190] inet_sendmsg+0x6d/0x80 [ 32.154508] ? inet_sendmsg+0x6d/0x80 [ 32.154838] sock_sendmsg+0x62/0x70 [ 32.155152] ____sys_sendmsg+0x134/0x290 [ 32.155499] ___sys_sendmsg+0x81/0xc0 [ 32.155828] ? _get_random_bytes.part.0+0x79/0x1a0 [ 32.156240] ? ip4_datagram_release_cb+0x5f/0x1e0 [ 32.156649] ? get_random_u16+0x69/0xf0 [ 32.156989] ? __fget_light+0xcf/0x110 [ 32.157326] __sys_sendmmsg+0xc4/0x210 [ 32.157657] ? __sys_connect+0xb7/0xe0 [ 32.157995] ? __audit_syscall_entry+0xce/0x140 [ 32.158388] ? syscall_trace_enter.isra.0+0x12c/0x1a0 [ 32.158820] __x64_sys_sendmmsg+0x24/0x30 [ 32.159171] do_syscall_64+0x38/0x90 [ 32.159493] entry_SYSCALL_64_after_hwframe+0x72/0xdc Fix that by reducing txq number as the non-existent primary-dev does. Fixes: cfc80d9a1163 ("net: Introduce net_failover driver") Signed-off-by: Faicker Mo Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/net_failover.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index fb182bec8f06..6b7bba720d8c 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -130,14 +130,10 @@ static u16 net_failover_select_queue(struct net_device *dev, txq = ops->ndo_select_queue(primary_dev, skb, sb_dev); else txq = netdev_pick_tx(primary_dev, skb, NULL); - - qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; - - return txq; + } else { + txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; } - txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; - /* Save the original txq to restore before passing to the driver */ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; From 9b22e0cfc4d737b4cf70debbbb835abd71c8121e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 25 Mar 2023 13:28:15 +0200 Subject: [PATCH 2395/4345] net: stmmac: don't reject VLANs when IFF_PROMISC is set [ Upstream commit a7602e7332b97cfbec7bacb0f1ade99a575fe104 ] The blamed commit has introduced the following tests to dwmac4_add_hw_vlan_rx_fltr(), called from stmmac_vlan_rx_add_vid(): if (hw->promisc) { netdev_err(dev, "Adding VLAN in promisc mode not supported\n"); return -EPERM; } "VLAN promiscuous" mode is keyed in this driver to IFF_PROMISC, and so, vlan_vid_add() and vlan_vid_del() calls cannot take place in IFF_PROMISC mode. I have the following 2 arguments that this restriction is.... hm, how shall I put it nicely... unproductive :) First, take the case of a Linux bridge. If the kernel is compiled with CONFIG_BRIDGE_VLAN_FILTERING=y, then this bridge shall have a VLAN database. The bridge shall try to call vlan_add_vid() on its bridge ports for each VLAN in the VLAN table. It will do this irrespectively of whether that port is *currently* VLAN-aware or not. So it will do this even when the bridge was created with vlan_filtering 0. But the Linux bridge, in VLAN-unaware mode, configures its ports in promiscuous (IFF_PROMISC) mode, so that they accept packets with any MAC DA (a switch must do this in order to forward those packets which are not directly targeted to its MAC address). As a result, the stmmac driver does not work as a bridge port, when the kernel is compiled with CONFIG_BRIDGE_VLAN_FILTERING=y. $ ip link add br0 type bridge && ip link set br0 up $ ip link set eth0 master br0 && ip link set eth0 up [ 2333.943296] br0: port 1(eth0) entered blocking state [ 2333.943381] br0: port 1(eth0) entered disabled state [ 2333.943782] device eth0 entered promiscuous mode [ 2333.944080] 4033c000.ethernet eth0: Adding VLAN in promisc mode not supported [ 2333.976509] 4033c000.ethernet eth0: failed to initialize vlan filtering on this port RTNETLINK answers: Operation not permitted Secondly, take the case of stmmac as DSA master. Some switch tagging protocols are based on 802.1Q VLANs (tag_sja1105.c), and as such, tag_8021q.c uses vlan_vid_add() to work with VLAN-filtering DSA masters. But also, when a DSA port becomes promiscuous (for example when it joins a bridge), the DSA framework also makes the DSA master promiscuous. Moreover, for every VLAN that a DSA switch sends to the CPU, DSA also programs a VLAN filter on the DSA master, because if the the DSA switch uses a tail tag, then the hardware frame parser of the DSA master will see VLAN as VLAN, and might filter them out, for being unknown. Due to the above 2 reasons, my belief is that the stmmac driver does not get to choose to not accept vlan_vid_add() calls while IFF_PROMISC is enabled, because the 2 are completely independent and there are code paths in the network stack which directly lead to this situation occurring, without the user's direct input. In fact, my belief is that "VLAN promiscuous" mode should have never been keyed on IFF_PROMISC in the first place, but rather, on the NETIF_F_HW_VLAN_CTAG_FILTER feature flag which can be toggled by the user through ethtool -k, when present in netdev->hw_features. In the stmmac driver, NETIF_F_HW_VLAN_CTAG_FILTER is only present in "features", making this feature "on [fixed]". I have this belief because I am unaware of any definition of promiscuity which implies having an effect on anything other than MAC DA (therefore not VLAN). However, I seem to be rather alone in having this opinion, looking back at the disagreements from this discussion: https://lore.kernel.org/netdev/20201110153958.ci5ekor3o2ekg3ky@ipetronik.com/ In any case, to remove the vlan_vid_add() dependency on !IFF_PROMISC, one would need to remove the check and see what fails. I guess the test was there because of the way in which dwmac4_vlan_promisc_enable() is implemented. For context, the dwmac4 supports Perfect Filtering for a limited number of VLANs - dwmac4_get_num_vlan(), priv->hw->num_vlan, with a fallback on Hash Filtering - priv->dma_cap.vlhash - see stmmac_vlan_update(), also visible in cat /sys/kernel/debug/stmmaceth/eth0/dma_cap | grep 'VLAN Hash Filtering'. The perfect filtering is based on MAC_VLAN_Tag_Filter/MAC_VLAN_Tag_Data registers, accessed in the driver through dwmac4_write_vlan_filter(). The hash filtering is based on the MAC_VLAN_Hash_Table register, named GMAC_VLAN_HASH_TABLE in the driver and accessed by dwmac4_update_vlan_hash(). The control bit for enabling hash filtering is GMAC_VLAN_VTHM (MAC_VLAN_Tag_Ctrl bit VTHM: VLAN Tag Hash Table Match Enable). Now, the description of dwmac4_vlan_promisc_enable() is that it iterates through the driver's cache of perfect filter entries (hw->vlan_filter[i], added by dwmac4_add_hw_vlan_rx_fltr()), and evicts them from hardware by unsetting their GMAC_VLAN_TAG_DATA_VEN (MAC_VLAN_Tag_Data bit VEN - VLAN Tag Enable) bit. Then it unsets the GMAC_VLAN_VTHM bit, which disables hash matching. This leaves the MAC, according to table "VLAN Match Status" from the documentation, to always enter these data paths: VID |VLAN Perfect Filter |VTHM Bit |VLAN Hash Filter |Final VLAN Match |Match Result | |Match Result |Status -------|--------------------|---------|-----------------|---------------- VID!=0 |Fail |0 |don't care |Pass So, dwmac4_vlan_promisc_enable() does its job, but by unsetting GMAC_VLAN_VTHM, it conflicts with the other code path which controls this bit: dwmac4_update_vlan_hash(), called through stmmac_update_vlan_hash() from stmmac_vlan_rx_add_vid() and from stmmac_vlan_rx_kill_vid(). This is, I guess, why dwmac4_add_hw_vlan_rx_fltr() is not allowed to run after dwmac4_vlan_promisc_enable() has unset GMAC_VLAN_VTHM: because if it did, then dwmac4_update_vlan_hash() would set GMAC_VLAN_VTHM again, breaking the "VLAN promiscuity". It turns out that dwmac4_vlan_promisc_enable() is way too complicated for what needs to be done. The MAC_Packet_Filter register also has the VTFE bit (VLAN Tag Filter Enable), which simply controls whether VLAN tagged packets which don't match the filtering tables (either perfect or hash) are dropped or not. At the moment, this driver unconditionally sets GMAC_PACKET_FILTER_VTFE if NETIF_F_HW_VLAN_CTAG_FILTER was detected through the priv->dma_cap.vlhash capability bits of the device, in stmmac_dvr_probe(). I would suggest deleting the unnecessarily complex logic from dwmac4_vlan_promisc_enable(), and simply unsetting GMAC_PACKET_FILTER_VTFE when becoming IFF_PROMISC, which has the same effect of allowing packets with any VLAN tags, but has the additional benefit of being able to run concurrently with stmmac_vlan_rx_add_vid() and stmmac_vlan_rx_kill_vid(). As much as I believe that the VTFE bit should have been exclusively controlled by NETIF_F_HW_VLAN_CTAG_FILTER through ethtool, and not by IFF_PROMISC, changing that is not a punctual fix to the problem, and it would probably break the VFFQ feature added by the later commit e0f9956a3862 ("net: stmmac: Add option for VLAN filter fail queue enable"). From the commit description, VFFQ needs IFF_PROMISC=on and VTFE=off in order to work (and this change respects that). But if VTFE was changed to be controlled through ethtool -k, then a user-visible change would have been introduced in Intel's scripts (a need to run "ethtool -k eth0 rx-vlan-filter off" which did not exist before). The patch was tested with this set of commands: ip link set eth0 up ip link add link eth0 name eth0.100 type vlan id 100 ip addr add 192.168.100.2/24 dev eth0.100 && ip link set eth0.100 up ip link set eth0 promisc on ip link add link eth0 name eth0.101 type vlan id 101 ip addr add 192.168.101.2/24 dev eth0.101 && ip link set eth0.101 up ip link set eth0 promisc off ping -c 5 192.168.100.1 ping -c 5 192.168.101.1 ip link set eth0 promisc on ping -c 5 192.168.100.1 ping -c 5 192.168.101.1 ip link del eth0.100 ip link del eth0.101 # Wait for VLAN-tagged pings from the other end... # Check with "tcpdump -i eth0 -e -n -p" and we should see them ip link set eth0 promisc off # Wait for VLAN-tagged pings from the other end... # Check with "tcpdump -i eth0 -e -n -p" and we shouldn't see them # anymore, but remove the "-p" argument from tcpdump and they're there. Fixes: c89f44ff10fd ("net: stmmac: Add support for VLAN promiscuous mode") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/common.h | 1 - .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 61 +------------------ 2 files changed, 3 insertions(+), 59 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index df7de50497a0..af4303523929 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -480,7 +480,6 @@ struct mac_device_info { unsigned int xlgmac; unsigned int num_vlan; u32 vlan_filter[32]; - unsigned int promisc; bool vlan_fail_q_en; u8 vlan_fail_q; }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 5b052fdd2696..cd11be005390 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -453,12 +453,6 @@ static int dwmac4_add_hw_vlan_rx_fltr(struct net_device *dev, if (vid > 4095) return -EINVAL; - if (hw->promisc) { - netdev_err(dev, - "Adding VLAN in promisc mode not supported\n"); - return -EPERM; - } - /* Single Rx VLAN Filter */ if (hw->num_vlan == 1) { /* For single VLAN filter, VID 0 means VLAN promiscuous */ @@ -508,12 +502,6 @@ static int dwmac4_del_hw_vlan_rx_fltr(struct net_device *dev, { int i, ret = 0; - if (hw->promisc) { - netdev_err(dev, - "Deleting VLAN in promisc mode not supported\n"); - return -EPERM; - } - /* Single Rx VLAN Filter */ if (hw->num_vlan == 1) { if ((hw->vlan_filter[0] & GMAC_VLAN_TAG_VID) == vid) { @@ -538,39 +526,6 @@ static int dwmac4_del_hw_vlan_rx_fltr(struct net_device *dev, return ret; } -static void dwmac4_vlan_promisc_enable(struct net_device *dev, - struct mac_device_info *hw) -{ - void __iomem *ioaddr = hw->pcsr; - u32 value; - u32 hash; - u32 val; - int i; - - /* Single Rx VLAN Filter */ - if (hw->num_vlan == 1) { - dwmac4_write_single_vlan(dev, 0); - return; - } - - /* Extended Rx VLAN Filter Enable */ - for (i = 0; i < hw->num_vlan; i++) { - if (hw->vlan_filter[i] & GMAC_VLAN_TAG_DATA_VEN) { - val = hw->vlan_filter[i] & ~GMAC_VLAN_TAG_DATA_VEN; - dwmac4_write_vlan_filter(dev, hw, i, val); - } - } - - hash = readl(ioaddr + GMAC_VLAN_HASH_TABLE); - if (hash & GMAC_VLAN_VLHT) { - value = readl(ioaddr + GMAC_VLAN_TAG); - if (value & GMAC_VLAN_VTHM) { - value &= ~GMAC_VLAN_VTHM; - writel(value, ioaddr + GMAC_VLAN_TAG); - } - } -} - static void dwmac4_restore_hw_vlan_rx_fltr(struct net_device *dev, struct mac_device_info *hw) { @@ -690,22 +645,12 @@ static void dwmac4_set_filter(struct mac_device_info *hw, } /* VLAN filtering */ - if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER) + if (dev->flags & IFF_PROMISC && !hw->vlan_fail_q_en) + value &= ~GMAC_PACKET_FILTER_VTFE; + else if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER) value |= GMAC_PACKET_FILTER_VTFE; writel(value, ioaddr + GMAC_PACKET_FILTER); - - if (dev->flags & IFF_PROMISC && !hw->vlan_fail_q_en) { - if (!hw->promisc) { - hw->promisc = 1; - dwmac4_vlan_promisc_enable(dev, hw); - } - } else { - if (hw->promisc) { - hw->promisc = 0; - dwmac4_restore_hw_vlan_rx_fltr(dev, hw); - } - } } static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, From ab2a55907823f0bca56b6d03ea05e4071ba8535f Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Tue, 14 Mar 2023 16:04:45 +0400 Subject: [PATCH 2396/4345] can: bcm: bcm_tx_setup(): fix KMSAN uninit-value in vfs_write [ Upstream commit 2b4c99f7d9a57ecd644eda9b1fb0a1072414959f ] Syzkaller reported the following issue: ===================================================== BUG: KMSAN: uninit-value in aio_rw_done fs/aio.c:1520 [inline] BUG: KMSAN: uninit-value in aio_write+0x899/0x950 fs/aio.c:1600 aio_rw_done fs/aio.c:1520 [inline] aio_write+0x899/0x950 fs/aio.c:1600 io_submit_one+0x1d1c/0x3bf0 fs/aio.c:2019 __do_sys_io_submit fs/aio.c:2078 [inline] __se_sys_io_submit+0x293/0x770 fs/aio.c:2048 __x64_sys_io_submit+0x92/0xd0 fs/aio.c:2048 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook mm/slab.h:766 [inline] slab_alloc_node mm/slub.c:3452 [inline] __kmem_cache_alloc_node+0x71f/0xce0 mm/slub.c:3491 __do_kmalloc_node mm/slab_common.c:967 [inline] __kmalloc+0x11d/0x3b0 mm/slab_common.c:981 kmalloc_array include/linux/slab.h:636 [inline] bcm_tx_setup+0x80e/0x29d0 net/can/bcm.c:930 bcm_sendmsg+0x3a2/0xce0 net/can/bcm.c:1351 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] sock_write_iter+0x495/0x5e0 net/socket.c:1108 call_write_iter include/linux/fs.h:2189 [inline] aio_write+0x63a/0x950 fs/aio.c:1600 io_submit_one+0x1d1c/0x3bf0 fs/aio.c:2019 __do_sys_io_submit fs/aio.c:2078 [inline] __se_sys_io_submit+0x293/0x770 fs/aio.c:2048 __x64_sys_io_submit+0x92/0xd0 fs/aio.c:2048 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd CPU: 1 PID: 5034 Comm: syz-executor350 Not tainted 6.2.0-rc6-syzkaller-80422-geda666ff2276 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 ===================================================== We can follow the call chain and find that 'bcm_tx_setup' function calls 'memcpy_from_msg' to copy some content to the newly allocated frame of 'op->frames'. After that the 'len' field of copied structure being compared with some constant value (64 or 8). However, if 'memcpy_from_msg' returns an error, we will compare some uninitialized memory. This triggers 'uninit-value' issue. This patch will add 'memcpy_from_msg' possible errors processing to avoid uninit-value issue. Tested via syzkaller Reported-by: syzbot+c9bfd85eca611ebf5db1@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=47f897f8ad958bbde5790ebf389b5e7e0a345089 Signed-off-by: Ivan Orlov Fixes: 6f3b911d5f29b ("can: bcm: add support for CAN FD frames") Acked-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20230314120445.12407-1-ivan.orlov0322@gmail.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- net/can/bcm.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/net/can/bcm.c b/net/can/bcm.c index afa82adaf6cd..ddba4e12da78 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -936,6 +936,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); + if (err < 0) + goto free_op; if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) @@ -945,12 +947,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, err = -EINVAL; } - if (err < 0) { - if (op->frames != &op->sframe) - kfree(op->frames); - kfree(op); - return err; - } + if (err < 0) + goto free_op; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ @@ -1021,6 +1019,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_tx_start_timer(op); return msg_head->nframes * op->cfsiz + MHSIZ; + +free_op: + if (op->frames != &op->sframe) + kfree(op->frames); + kfree(op); + return err; } /* From ee17dea3072dec0bc34399a32fa884e26342e4ea Mon Sep 17 00:00:00 2001 From: Tony Krowiak Date: Mon, 20 Mar 2023 11:04:47 -0400 Subject: [PATCH 2397/4345] s390/vfio-ap: fix memory leak in vfio_ap device driver [ Upstream commit 8f8cf767589f2131ae5d40f3758429095c701c84 ] The device release callback function invoked to release the matrix device uses the dev_get_drvdata(device *dev) function to retrieve the pointer to the vfio_matrix_dev object in order to free its storage. The problem is, this object is not stored as drvdata with the device; since the kfree function will accept a NULL pointer, the memory for the vfio_matrix_dev object is never freed. Since the device being released is contained within the vfio_matrix_dev object, the container_of macro will be used to retrieve its pointer. Fixes: 1fde573413b5 ("s390: vfio-ap: base implementation of VFIO AP device driver") Signed-off-by: Tony Krowiak Reviewed-by: Harald Freudenberger Link: https://lore.kernel.org/r/20230320150447.34557-1-akrowiak@linux.ibm.com Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Sasha Levin --- drivers/s390/crypto/vfio_ap_drv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index 7dc72cb718b0..22128eb44f7f 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -82,8 +82,9 @@ static void vfio_ap_queue_dev_remove(struct ap_device *apdev) static void vfio_ap_matrix_dev_release(struct device *dev) { - struct ap_matrix_dev *matrix_dev = dev_get_drvdata(dev); + struct ap_matrix_dev *matrix_dev; + matrix_dev = container_of(dev, struct ap_matrix_dev, device); kfree(matrix_dev); } From 688b1178c443fd1bac47bfc5beb90f356f02569d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 8 Jun 2021 16:05:26 +0200 Subject: [PATCH 2398/4345] ALSA: ymfpci: Fix assignment in if condition [ Upstream commit e7daaeedb4f270126792ae216f406c1ba2b8f4d9 ] PCI YMFPCI driver code contains lots of assignments in if condition, which is a bad coding style that may confuse readers and occasionally lead to bugs. This patch is merely for coding-style fixes, no functional changes. Link: https://lore.kernel.org/r/20210608140540.17885-53-tiwai@suse.de Signed-off-by: Takashi Iwai Stable-dep-of: 6be2e7522eb5 ("ALSA: ymfpci: Fix BUG_ON in probe function") Signed-off-by: Sasha Levin --- sound/pci/ymfpci/ymfpci.c | 71 +++++++++++++++++++-------------- sound/pci/ymfpci/ymfpci_main.c | 72 +++++++++++++++++++++++----------- 2 files changed, 91 insertions(+), 52 deletions(-) diff --git a/sound/pci/ymfpci/ymfpci.c b/sound/pci/ymfpci/ymfpci.c index 9b0d18a7bf35..27fd10b976f7 100644 --- a/sound/pci/ymfpci/ymfpci.c +++ b/sound/pci/ymfpci/ymfpci.c @@ -78,7 +78,8 @@ static int snd_ymfpci_create_gameport(struct snd_ymfpci *chip, int dev, if (io_port == 1) { /* auto-detect */ - if (!(io_port = pci_resource_start(chip->pci, 2))) + io_port = pci_resource_start(chip->pci, 2); + if (!io_port) return -ENODEV; } } else { @@ -87,7 +88,8 @@ static int snd_ymfpci_create_gameport(struct snd_ymfpci *chip, int dev, for (io_port = 0x201; io_port <= 0x205; io_port++) { if (io_port == 0x203) continue; - if ((r = request_region(io_port, 1, "YMFPCI gameport")) != NULL) + r = request_region(io_port, 1, "YMFPCI gameport"); + if (r) break; } if (!r) { @@ -108,10 +110,13 @@ static int snd_ymfpci_create_gameport(struct snd_ymfpci *chip, int dev, } } - if (!r && !(r = request_region(io_port, 1, "YMFPCI gameport"))) { - dev_err(chip->card->dev, - "joystick port %#x is in use.\n", io_port); - return -EBUSY; + if (!r) { + r = request_region(io_port, 1, "YMFPCI gameport"); + if (!r) { + dev_err(chip->card->dev, + "joystick port %#x is in use.\n", io_port); + return -EBUSY; + } } chip->gameport = gp = gameport_allocate_port(); @@ -199,8 +204,9 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, /* auto-detect */ fm_port[dev] = pci_resource_start(pci, 1); } - if (fm_port[dev] > 0 && - (fm_res = request_region(fm_port[dev], 4, "YMFPCI OPL3")) != NULL) { + if (fm_port[dev] > 0) + fm_res = request_region(fm_port[dev], 4, "YMFPCI OPL3"); + if (fm_res) { legacy_ctrl |= YMFPCI_LEGACY_FMEN; pci_write_config_word(pci, PCIR_DSXG_FMBASE, fm_port[dev]); } @@ -208,8 +214,9 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, /* auto-detect */ mpu_port[dev] = pci_resource_start(pci, 1) + 0x20; } - if (mpu_port[dev] > 0 && - (mpu_res = request_region(mpu_port[dev], 2, "YMFPCI MPU401")) != NULL) { + if (mpu_port[dev] > 0) + mpu_res = request_region(mpu_port[dev], 2, "YMFPCI MPU401"); + if (mpu_res) { legacy_ctrl |= YMFPCI_LEGACY_MEN; pci_write_config_word(pci, PCIR_DSXG_MPU401BASE, mpu_port[dev]); } @@ -221,8 +228,9 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, case 0x3a8: legacy_ctrl2 |= 3; break; default: fm_port[dev] = 0; break; } - if (fm_port[dev] > 0 && - (fm_res = request_region(fm_port[dev], 4, "YMFPCI OPL3")) != NULL) { + if (fm_port[dev] > 0) + fm_res = request_region(fm_port[dev], 4, "YMFPCI OPL3"); + if (fm_res) { legacy_ctrl |= YMFPCI_LEGACY_FMEN; } else { legacy_ctrl2 &= ~YMFPCI_LEGACY2_FMIO; @@ -235,8 +243,9 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, case 0x334: legacy_ctrl2 |= 3 << 4; break; default: mpu_port[dev] = 0; break; } - if (mpu_port[dev] > 0 && - (mpu_res = request_region(mpu_port[dev], 2, "YMFPCI MPU401")) != NULL) { + if (mpu_port[dev] > 0) + mpu_res = request_region(mpu_port[dev], 2, "YMFPCI MPU401"); + if (mpu_res) { legacy_ctrl |= YMFPCI_LEGACY_MEN; } else { legacy_ctrl2 &= ~YMFPCI_LEGACY2_MPUIO; @@ -250,9 +259,8 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, pci_read_config_word(pci, PCIR_DSXG_LEGACY, &old_legacy_ctrl); pci_write_config_word(pci, PCIR_DSXG_LEGACY, legacy_ctrl); pci_write_config_word(pci, PCIR_DSXG_ELEGACY, legacy_ctrl2); - if ((err = snd_ymfpci_create(card, pci, - old_legacy_ctrl, - &chip)) < 0) { + err = snd_ymfpci_create(card, pci, old_legacy_ctrl, &chip); + if (err < 0) { release_and_free_resource(mpu_res); release_and_free_resource(fm_res); goto free_card; @@ -293,11 +301,12 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, goto free_card; if (chip->mpu_res) { - if ((err = snd_mpu401_uart_new(card, 0, MPU401_HW_YMFPCI, - mpu_port[dev], - MPU401_INFO_INTEGRATED | - MPU401_INFO_IRQ_HOOK, - -1, &chip->rawmidi)) < 0) { + err = snd_mpu401_uart_new(card, 0, MPU401_HW_YMFPCI, + mpu_port[dev], + MPU401_INFO_INTEGRATED | + MPU401_INFO_IRQ_HOOK, + -1, &chip->rawmidi); + if (err < 0) { dev_warn(card->dev, "cannot initialize MPU401 at 0x%lx, skipping...\n", mpu_port[dev]); @@ -306,18 +315,22 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, } } if (chip->fm_res) { - if ((err = snd_opl3_create(card, - fm_port[dev], - fm_port[dev] + 2, - OPL3_HW_OPL3, 1, &opl3)) < 0) { + err = snd_opl3_create(card, + fm_port[dev], + fm_port[dev] + 2, + OPL3_HW_OPL3, 1, &opl3); + if (err < 0) { dev_warn(card->dev, "cannot initialize FM OPL3 at 0x%lx, skipping...\n", fm_port[dev]); legacy_ctrl &= ~YMFPCI_LEGACY_FMEN; pci_write_config_word(pci, PCIR_DSXG_LEGACY, legacy_ctrl); - } else if ((err = snd_opl3_hwdep_new(opl3, 0, 1, NULL)) < 0) { - dev_err(card->dev, "cannot create opl3 hwdep\n"); - goto free_card; + } else { + err = snd_opl3_hwdep_new(opl3, 0, 1, NULL); + if (err < 0) { + dev_err(card->dev, "cannot create opl3 hwdep\n"); + goto free_card; + } } } diff --git a/sound/pci/ymfpci/ymfpci_main.c b/sound/pci/ymfpci/ymfpci_main.c index cacc6a9d14c8..8fd060769882 100644 --- a/sound/pci/ymfpci/ymfpci_main.c +++ b/sound/pci/ymfpci/ymfpci_main.c @@ -292,7 +292,8 @@ static void snd_ymfpci_pcm_interrupt(struct snd_ymfpci *chip, struct snd_ymfpci_ struct snd_ymfpci_pcm *ypcm; u32 pos, delta; - if ((ypcm = voice->ypcm) == NULL) + ypcm = voice->ypcm; + if (!ypcm) return; if (ypcm->substream == NULL) return; @@ -628,7 +629,8 @@ static int snd_ymfpci_playback_hw_params(struct snd_pcm_substream *substream, struct snd_ymfpci_pcm *ypcm = runtime->private_data; int err; - if ((err = snd_ymfpci_pcm_voice_alloc(ypcm, params_channels(hw_params))) < 0) + err = snd_ymfpci_pcm_voice_alloc(ypcm, params_channels(hw_params)); + if (err < 0) return err; return 0; } @@ -932,7 +934,8 @@ static int snd_ymfpci_playback_open(struct snd_pcm_substream *substream) struct snd_ymfpci_pcm *ypcm; int err; - if ((err = snd_ymfpci_playback_open_1(substream)) < 0) + err = snd_ymfpci_playback_open_1(substream); + if (err < 0) return err; ypcm = runtime->private_data; ypcm->output_front = 1; @@ -954,7 +957,8 @@ static int snd_ymfpci_playback_spdif_open(struct snd_pcm_substream *substream) struct snd_ymfpci_pcm *ypcm; int err; - if ((err = snd_ymfpci_playback_open_1(substream)) < 0) + err = snd_ymfpci_playback_open_1(substream); + if (err < 0) return err; ypcm = runtime->private_data; ypcm->output_front = 0; @@ -982,7 +986,8 @@ static int snd_ymfpci_playback_4ch_open(struct snd_pcm_substream *substream) struct snd_ymfpci_pcm *ypcm; int err; - if ((err = snd_ymfpci_playback_open_1(substream)) < 0) + err = snd_ymfpci_playback_open_1(substream); + if (err < 0) return err; ypcm = runtime->private_data; ypcm->output_front = 0; @@ -1124,7 +1129,8 @@ int snd_ymfpci_pcm(struct snd_ymfpci *chip, int device) struct snd_pcm *pcm; int err; - if ((err = snd_pcm_new(chip->card, "YMFPCI", device, 32, 1, &pcm)) < 0) + err = snd_pcm_new(chip->card, "YMFPCI", device, 32, 1, &pcm); + if (err < 0) return err; pcm->private_data = chip; @@ -1157,7 +1163,8 @@ int snd_ymfpci_pcm2(struct snd_ymfpci *chip, int device) struct snd_pcm *pcm; int err; - if ((err = snd_pcm_new(chip->card, "YMFPCI - PCM2", device, 0, 1, &pcm)) < 0) + err = snd_pcm_new(chip->card, "YMFPCI - PCM2", device, 0, 1, &pcm); + if (err < 0) return err; pcm->private_data = chip; @@ -1190,7 +1197,8 @@ int snd_ymfpci_pcm_spdif(struct snd_ymfpci *chip, int device) struct snd_pcm *pcm; int err; - if ((err = snd_pcm_new(chip->card, "YMFPCI - IEC958", device, 1, 0, &pcm)) < 0) + err = snd_pcm_new(chip->card, "YMFPCI - IEC958", device, 1, 0, &pcm); + if (err < 0) return err; pcm->private_data = chip; @@ -1230,7 +1238,8 @@ int snd_ymfpci_pcm_4ch(struct snd_ymfpci *chip, int device) struct snd_pcm *pcm; int err; - if ((err = snd_pcm_new(chip->card, "YMFPCI - Rear", device, 1, 0, &pcm)) < 0) + err = snd_pcm_new(chip->card, "YMFPCI - Rear", device, 1, 0, &pcm); + if (err < 0) return err; pcm->private_data = chip; @@ -1785,7 +1794,8 @@ int snd_ymfpci_mixer(struct snd_ymfpci *chip, int rear_switch) .read = snd_ymfpci_codec_read, }; - if ((err = snd_ac97_bus(chip->card, 0, &ops, chip, &chip->ac97_bus)) < 0) + err = snd_ac97_bus(chip->card, 0, &ops, chip, &chip->ac97_bus); + if (err < 0) return err; chip->ac97_bus->private_free = snd_ymfpci_mixer_free_ac97_bus; chip->ac97_bus->no_vra = 1; /* YMFPCI doesn't need VRA */ @@ -1793,7 +1803,8 @@ int snd_ymfpci_mixer(struct snd_ymfpci *chip, int rear_switch) memset(&ac97, 0, sizeof(ac97)); ac97.private_data = chip; ac97.private_free = snd_ymfpci_mixer_free_ac97; - if ((err = snd_ac97_mixer(chip->ac97_bus, &ac97, &chip->ac97)) < 0) + err = snd_ac97_mixer(chip->ac97_bus, &ac97, &chip->ac97); + if (err < 0) return err; /* to be sure */ @@ -1801,7 +1812,8 @@ int snd_ymfpci_mixer(struct snd_ymfpci *chip, int rear_switch) AC97_EA_VRA|AC97_EA_VRM, 0); for (idx = 0; idx < ARRAY_SIZE(snd_ymfpci_controls); idx++) { - if ((err = snd_ctl_add(chip->card, snd_ctl_new1(&snd_ymfpci_controls[idx], chip))) < 0) + err = snd_ctl_add(chip->card, snd_ctl_new1(&snd_ymfpci_controls[idx], chip)); + if (err < 0) return err; } if (chip->ac97->ext_id & AC97_EI_SDAC) { @@ -1814,27 +1826,37 @@ int snd_ymfpci_mixer(struct snd_ymfpci *chip, int rear_switch) /* add S/PDIF control */ if (snd_BUG_ON(!chip->pcm_spdif)) return -ENXIO; - if ((err = snd_ctl_add(chip->card, kctl = snd_ctl_new1(&snd_ymfpci_spdif_default, chip))) < 0) + kctl = snd_ctl_new1(&snd_ymfpci_spdif_default, chip); + err = snd_ctl_add(chip->card, kctl); + if (err < 0) return err; kctl->id.device = chip->pcm_spdif->device; - if ((err = snd_ctl_add(chip->card, kctl = snd_ctl_new1(&snd_ymfpci_spdif_mask, chip))) < 0) + kctl = snd_ctl_new1(&snd_ymfpci_spdif_mask, chip); + err = snd_ctl_add(chip->card, kctl); + if (err < 0) return err; kctl->id.device = chip->pcm_spdif->device; - if ((err = snd_ctl_add(chip->card, kctl = snd_ctl_new1(&snd_ymfpci_spdif_stream, chip))) < 0) + kctl = snd_ctl_new1(&snd_ymfpci_spdif_stream, chip); + err = snd_ctl_add(chip->card, kctl); + if (err < 0) return err; kctl->id.device = chip->pcm_spdif->device; chip->spdif_pcm_ctl = kctl; /* direct recording source */ - if (chip->device_id == PCI_DEVICE_ID_YAMAHA_754 && - (err = snd_ctl_add(chip->card, kctl = snd_ctl_new1(&snd_ymfpci_drec_source, chip))) < 0) - return err; + if (chip->device_id == PCI_DEVICE_ID_YAMAHA_754) { + kctl = snd_ctl_new1(&snd_ymfpci_drec_source, chip); + err = snd_ctl_add(chip->card, kctl); + if (err < 0) + return err; + } /* * shared rear/line-in */ if (rear_switch) { - if ((err = snd_ctl_add(chip->card, snd_ctl_new1(&snd_ymfpci_rear_shared, chip))) < 0) + err = snd_ctl_add(chip->card, snd_ctl_new1(&snd_ymfpci_rear_shared, chip)); + if (err < 0) return err; } @@ -1847,7 +1869,8 @@ int snd_ymfpci_mixer(struct snd_ymfpci *chip, int rear_switch) kctl->id.device = chip->pcm->device; kctl->id.subdevice = idx; kctl->private_value = (unsigned long)substream; - if ((err = snd_ctl_add(chip->card, kctl)) < 0) + err = snd_ctl_add(chip->card, kctl); + if (err < 0) return err; chip->pcm_mixer[idx].left = 0x8000; chip->pcm_mixer[idx].right = 0x8000; @@ -1928,7 +1951,8 @@ int snd_ymfpci_timer(struct snd_ymfpci *chip, int device) tid.card = chip->card->number; tid.device = device; tid.subdevice = 0; - if ((err = snd_timer_new(chip->card, "YMFPCI", &tid, &timer)) >= 0) { + err = snd_timer_new(chip->card, "YMFPCI", &tid, &timer); + if (err >= 0) { strcpy(timer->name, "YMFPCI timer"); timer->private_data = chip; timer->hw = snd_ymfpci_timer_hw; @@ -2334,7 +2358,8 @@ int snd_ymfpci_create(struct snd_card *card, *rchip = NULL; /* enable PCI device */ - if ((err = pci_enable_device(pci)) < 0) + err = pci_enable_device(pci); + if (err < 0) return err; chip = kzalloc(sizeof(*chip), GFP_KERNEL); @@ -2357,7 +2382,8 @@ int snd_ymfpci_create(struct snd_card *card, pci_set_master(pci); chip->src441_used = -1; - if ((chip->res_reg_area = request_mem_region(chip->reg_area_phys, 0x8000, "YMFPCI")) == NULL) { + chip->res_reg_area = request_mem_region(chip->reg_area_phys, 0x8000, "YMFPCI"); + if (!chip->res_reg_area) { dev_err(chip->card->dev, "unable to grab memory region 0x%lx-0x%lx\n", chip->reg_area_phys, chip->reg_area_phys + 0x8000 - 1); From 96e34c88000febc83e41aa7db0b0a41676314818 Mon Sep 17 00:00:00 2001 From: Tasos Sahanidis Date: Wed, 29 Mar 2023 06:28:08 +0300 Subject: [PATCH 2399/4345] ALSA: ymfpci: Fix BUG_ON in probe function [ Upstream commit 6be2e7522eb529b41c16d459f33bbdbcddbf5c15 ] The snd_dma_buffer.bytes field now contains the aligned size, which this snd_BUG_ON() did not account for, resulting in the following: [ 9.625915] ------------[ cut here ]------------ [ 9.633440] WARNING: CPU: 0 PID: 126 at sound/pci/ymfpci/ymfpci_main.c:2168 snd_ymfpci_create+0x681/0x698 [snd_ymfpci] [ 9.648926] Modules linked in: snd_ymfpci(+) snd_intel_dspcfg kvm(+) snd_intel_sdw_acpi snd_ac97_codec snd_mpu401_uart snd_opl3_lib irqbypass snd_hda_codec gameport snd_rawmidi crct10dif_pclmul crc32_pclmul cfg80211 snd_hda_core polyval_clmulni polyval_generic gf128mul snd_seq_device ghash_clmulni_intel snd_hwdep ac97_bus sha512_ssse3 rfkill snd_pcm aesni_intel tg3 snd_timer crypto_simd snd mxm_wmi libphy cryptd k10temp fam15h_power pcspkr soundcore sp5100_tco wmi acpi_cpufreq mac_hid dm_multipath sg loop fuse dm_mod bpf_preload ip_tables x_tables ext4 crc32c_generic crc16 mbcache jbd2 sr_mod cdrom ata_generic pata_acpi firewire_ohci crc32c_intel firewire_core xhci_pci crc_itu_t pata_via xhci_pci_renesas floppy [ 9.711849] CPU: 0 PID: 126 Comm: kworker/0:2 Not tainted 6.1.21-1-lts #1 08d2e5ece03136efa7c6aeea9a9c40916b1bd8da [ 9.722200] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./990FX Extreme4, BIOS P2.70 06/05/2014 [ 9.732204] Workqueue: events work_for_cpu_fn [ 9.736580] RIP: 0010:snd_ymfpci_create+0x681/0x698 [snd_ymfpci] [ 9.742594] Code: 8c c0 4c 89 e2 48 89 df 48 c7 c6 92 c6 8c c0 e8 15 d0 e9 ff 48 83 c4 08 44 89 e8 5b 5d 41 5c 41 5d 41 5e 41 5f e9 d3 7a 33 e3 <0f> 0b e9 cb fd ff ff 41 bd fb ff ff ff eb db 41 bd f4 ff ff ff eb [ 9.761358] RSP: 0018:ffffab64804e7da0 EFLAGS: 00010287 [ 9.766594] RAX: ffff8fa2df06c400 RBX: ffff8fa3073a8000 RCX: ffff8fa303fbc4a8 [ 9.773734] RDX: ffff8fa2df06d000 RSI: 0000000000000010 RDI: 0000000000000020 [ 9.780876] RBP: ffff8fa300b5d0d0 R08: ffff8fa3073a8e50 R09: 00000000df06bf00 [ 9.788018] R10: ffff8fa2df06bf00 R11: 00000000df068200 R12: ffff8fa3073a8918 [ 9.795159] R13: 0000000000000000 R14: 0000000000000080 R15: ffff8fa2df068200 [ 9.802317] FS: 0000000000000000(0000) GS:ffff8fa9fec00000(0000) knlGS:0000000000000000 [ 9.810414] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 9.816158] CR2: 000055febaf66500 CR3: 0000000101a2e000 CR4: 00000000000406f0 [ 9.823301] Call Trace: [ 9.825747] [ 9.827889] snd_card_ymfpci_probe+0x194/0x950 [snd_ymfpci b78a5fe64b5663a6390a909c67808567e3e73615] [ 9.837030] ? finish_task_switch.isra.0+0x90/0x2d0 [ 9.841918] local_pci_probe+0x45/0x80 [ 9.845680] work_for_cpu_fn+0x1a/0x30 [ 9.849431] process_one_work+0x1c7/0x380 [ 9.853464] worker_thread+0x1af/0x390 [ 9.857225] ? rescuer_thread+0x3b0/0x3b0 [ 9.861254] kthread+0xde/0x110 [ 9.864414] ? kthread_complete_and_exit+0x20/0x20 [ 9.869210] ret_from_fork+0x22/0x30 [ 9.872792] [ 9.874985] ---[ end trace 0000000000000000 ]--- Fixes: 5c1733e33c88 ("ALSA: memalloc: Align buffer allocations in page size") Signed-off-by: Tasos Sahanidis Link: https://lore.kernel.org/r/20230329032808.170403-1-tasos@tasossah.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/ymfpci/ymfpci_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/ymfpci/ymfpci_main.c b/sound/pci/ymfpci/ymfpci_main.c index 8fd060769882..0cd9b4029dab 100644 --- a/sound/pci/ymfpci/ymfpci_main.c +++ b/sound/pci/ymfpci/ymfpci_main.c @@ -2164,7 +2164,7 @@ static int snd_ymfpci_memalloc(struct snd_ymfpci *chip) chip->work_base = ptr; chip->work_base_addr = ptr_addr; - snd_BUG_ON(ptr + chip->work_size != + snd_BUG_ON(ptr + PAGE_ALIGN(chip->work_size) != chip->work_ptr.area + chip->work_ptr.bytes); snd_ymfpci_writel(chip, YDSXGR_PLAYCTRLBASE, chip->bank_base_playback_addr); From fa7fafedc9fddfbc715132fdf35f6c2fa9c43e02 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 28 Mar 2023 11:27:51 -0500 Subject: [PATCH 2400/4345] net: ipa: compute DMA pool size properly [ Upstream commit 6c75dc94f2b27fff57b305af9236eea181a00b6c ] In gsi_trans_pool_init_dma(), the total size of a pool of memory used for DMA transactions is calculated. However the calculation is done incorrectly. For 4KB pages, this total size is currently always more than one page, and as a result, the calculation produces a positive (though incorrect) total size. The code still works in this case; we just end up with fewer DMA pool entries than we intended. Bjorn Andersson tested booting a kernel with 16KB pages, and hit a null pointer derereference in sg_alloc_append_table_from_pages(), descending from gsi_trans_pool_init_dma(). The cause of this was that a 16KB total size was going to be allocated, and with 16KB pages the order of that allocation is 0. The total_size calculation yielded 0, which eventually led to the crash. Correcting the total_size calculation fixes the problem. Reported-by: Bjorn Andersson Tested-by: Bjorn Andersson Fixes: 9dd441e4ed57 ("soc: qcom: ipa: GSI transactions") Reviewed-by: Mark Bloch Signed-off-by: Alex Elder Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230328162751.2861791-1-elder@linaro.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ipa/gsi_trans.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 70c2b585f98d..1e0d62639301 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -159,7 +159,7 @@ int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool, * gsi_trans_pool_exit_dma() can assume the total allocated * size is exactly (count * size). */ - total_size = get_order(total_size) << PAGE_SHIFT; + total_size = PAGE_SIZE << get_order(total_size); virt = dma_alloc_coherent(dev, total_size, &addr, GFP_KERNEL); if (!virt) From f524d1e55013b64ec14be012d839b919d65d2481 Mon Sep 17 00:00:00 2001 From: Radoslaw Tyl Date: Tue, 28 Mar 2023 10:26:59 -0700 Subject: [PATCH 2401/4345] i40e: fix registers dump after run ethtool adapter self test [ Upstream commit c5cff16f461a4a434a9915a7be7ac9ced861a8a4 ] Fix invalid registers dump from ethtool -d ethX after adapter self test by ethtool -t ethY. It causes invalid data display. The problem was caused by overwriting i40e_reg_list[].elements which is common for ethtool self test and dump. Fixes: 22dd9ae8afcc ("i40e: Rework register diagnostic") Signed-off-by: Radoslaw Tyl Reviewed-by: Michal Swiatkowski Tested-by: Arpana Arland (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20230328172659.3906413-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/i40e/i40e_diag.c | 11 ++++++----- drivers/net/ethernet/intel/i40e/i40e_diag.h | 2 +- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c index ef4d3762bf37..ca229b0efeb6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.c +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c @@ -44,7 +44,7 @@ static i40e_status i40e_diag_reg_pattern_test(struct i40e_hw *hw, return 0; } -struct i40e_diag_reg_test_info i40e_reg_list[] = { +const struct i40e_diag_reg_test_info i40e_reg_list[] = { /* offset mask elements stride */ {I40E_QTX_CTL(0), 0x0000FFBF, 1, I40E_QTX_CTL(1) - I40E_QTX_CTL(0)}, @@ -78,27 +78,28 @@ i40e_status i40e_diag_reg_test(struct i40e_hw *hw) { i40e_status ret_code = 0; u32 reg, mask; + u32 elements; u32 i, j; for (i = 0; i40e_reg_list[i].offset != 0 && !ret_code; i++) { + elements = i40e_reg_list[i].elements; /* set actual reg range for dynamically allocated resources */ if (i40e_reg_list[i].offset == I40E_QTX_CTL(0) && hw->func_caps.num_tx_qp != 0) - i40e_reg_list[i].elements = hw->func_caps.num_tx_qp; + elements = hw->func_caps.num_tx_qp; if ((i40e_reg_list[i].offset == I40E_PFINT_ITRN(0, 0) || i40e_reg_list[i].offset == I40E_PFINT_ITRN(1, 0) || i40e_reg_list[i].offset == I40E_PFINT_ITRN(2, 0) || i40e_reg_list[i].offset == I40E_QINT_TQCTL(0) || i40e_reg_list[i].offset == I40E_QINT_RQCTL(0)) && hw->func_caps.num_msix_vectors != 0) - i40e_reg_list[i].elements = - hw->func_caps.num_msix_vectors - 1; + elements = hw->func_caps.num_msix_vectors - 1; /* test register access */ mask = i40e_reg_list[i].mask; - for (j = 0; j < i40e_reg_list[i].elements && !ret_code; j++) { + for (j = 0; j < elements && !ret_code; j++) { reg = i40e_reg_list[i].offset + (j * i40e_reg_list[i].stride); ret_code = i40e_diag_reg_pattern_test(hw, reg, mask); diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h index c3340f320a18..1db7c6d57231 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.h +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h @@ -20,7 +20,7 @@ struct i40e_diag_reg_test_info { u32 stride; /* bytes between each element */ }; -extern struct i40e_diag_reg_test_info i40e_reg_list[]; +extern const struct i40e_diag_reg_test_info i40e_reg_list[]; i40e_status i40e_diag_reg_test(struct i40e_hw *hw); i40e_status i40e_diag_eeprom_test(struct i40e_hw *hw); From 62850a076353cafcb17adc8fa2dc67cc0aced58d Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Tue, 28 Mar 2023 18:30:20 -0700 Subject: [PATCH 2402/4345] bnxt_en: Fix typo in PCI id to device description string mapping [ Upstream commit 62aad36ed31abc80f35db11e187e690448a79f7d ] Fix 57502 and 57508 NPAR description string entries. The typos caused these devices to not match up with lspci output. Fixes: 49c98421e6ab ("bnxt_en: Add PCI IDs for 57500 series NPAR devices.") Reviewed-by: Pavan Chebbi Signed-off-by: Kalesh AP Signed-off-by: Michael Chan Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6928c0b578ab..3a9fcf942a6d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -219,12 +219,12 @@ static const struct pci_device_id bnxt_pci_tbl[] = { { PCI_VDEVICE(BROADCOM, 0x1750), .driver_data = BCM57508 }, { PCI_VDEVICE(BROADCOM, 0x1751), .driver_data = BCM57504 }, { PCI_VDEVICE(BROADCOM, 0x1752), .driver_data = BCM57502 }, - { PCI_VDEVICE(BROADCOM, 0x1800), .driver_data = BCM57508_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1800), .driver_data = BCM57502_NPAR }, { PCI_VDEVICE(BROADCOM, 0x1801), .driver_data = BCM57504_NPAR }, - { PCI_VDEVICE(BROADCOM, 0x1802), .driver_data = BCM57502_NPAR }, - { PCI_VDEVICE(BROADCOM, 0x1803), .driver_data = BCM57508_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1802), .driver_data = BCM57508_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1803), .driver_data = BCM57502_NPAR }, { PCI_VDEVICE(BROADCOM, 0x1804), .driver_data = BCM57504_NPAR }, - { PCI_VDEVICE(BROADCOM, 0x1805), .driver_data = BCM57502_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1805), .driver_data = BCM57508_NPAR }, { PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 }, { PCI_VDEVICE(BROADCOM, 0xd804), .driver_data = BCM58804 }, #ifdef CONFIG_BNXT_SRIOV From 8104c795517c2f10e2720c16b216abb9a68746ee Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Tue, 28 Mar 2023 18:30:21 -0700 Subject: [PATCH 2403/4345] bnxt_en: Add missing 200G link speed reporting [ Upstream commit 581bce7bcb7e7f100908728e7b292e266c76895b ] bnxt_fw_to_ethtool_speed() is missing the case statement for 200G link speed reported by firmware. As a result, ethtool will report unknown speed when the firmware reports 200G link speed. Fixes: 532262ba3b84 ("bnxt_en: ethtool: support PAM4 link speeds up to 200G") Signed-off-by: Michael Chan Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 34affd1de91d..b7b07beb17ff 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1198,6 +1198,7 @@ struct bnxt_link_info { #define BNXT_LINK_SPEED_40GB PORT_PHY_QCFG_RESP_LINK_SPEED_40GB #define BNXT_LINK_SPEED_50GB PORT_PHY_QCFG_RESP_LINK_SPEED_50GB #define BNXT_LINK_SPEED_100GB PORT_PHY_QCFG_RESP_LINK_SPEED_100GB +#define BNXT_LINK_SPEED_200GB PORT_PHY_QCFG_RESP_LINK_SPEED_200GB u16 support_speeds; u16 support_pam4_speeds; u16 auto_link_speeds; /* fw adv setting */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 81b63d1c2391..1e67e86fc334 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1653,6 +1653,8 @@ u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed) return SPEED_50000; case BNXT_LINK_SPEED_100GB: return SPEED_100000; + case BNXT_LINK_SPEED_200GB: + return SPEED_200000; default: return SPEED_UNKNOWN; } From ed3439a8c4fe7fc7d8c20b9e89aa16d45f8e0a70 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Steffen=20B=C3=A4tz?= Date: Wed, 29 Mar 2023 12:01:40 -0300 Subject: [PATCH 2404/4345] net: dsa: mv88e6xxx: Enable IGMP snooping on user ports only MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7bcad0f0e6fbc1d613e49e0ee35c8e5f2e685bb0 ] Do not set the MV88E6XXX_PORT_CTL0_IGMP_MLD_SNOOP bit on CPU or DSA ports. This allows the host CPU port to be a regular IGMP listener by sending out IGMP Membership Reports, which would otherwise not be forwarded by the mv88exxx chip, but directly looped back to the CPU port itself. Fixes: 54d792f257c6 ("net: dsa: Centralise global and port setup code into mv88e6xxx.") Signed-off-by: Steffen Bätz Signed-off-by: Fabio Estevam Reviewed-by: Andrew Lunn Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20230329150140.701559-1-festevam@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/mv88e6xxx/chip.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index a253476a52b0..0b104a90c0d8 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2611,9 +2611,14 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) * If this is the upstream port for this switch, enable * forwarding of unknown unicasts and multicasts. */ - reg = MV88E6XXX_PORT_CTL0_IGMP_MLD_SNOOP | - MV88E6185_PORT_CTL0_USE_TAG | MV88E6185_PORT_CTL0_USE_IP | + reg = MV88E6185_PORT_CTL0_USE_TAG | MV88E6185_PORT_CTL0_USE_IP | MV88E6XXX_PORT_CTL0_STATE_FORWARDING; + /* Forward any IPv4 IGMP or IPv6 MLD frames received + * by a USER port to the CPU port to allow snooping. + */ + if (dsa_is_user_port(ds, port)) + reg |= MV88E6XXX_PORT_CTL0_IGMP_MLD_SNOOP; + err = mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_CTL0, reg); if (err) return err; From 988061d09972dba1374426924531a85e6d306f47 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Mon, 6 Feb 2023 21:37:20 +0100 Subject: [PATCH 2405/4345] pinctrl: ocelot: Fix alt mode for ocelot [ Upstream commit 657fd9da2d4b4aa0a384105b236baa22fa0233bf ] In case the driver was trying to set an alternate mode for gpio 0 or 32 then the mode was not set correctly. The reason is that there is computation error inside the function ocelot_pinmux_set_mux because in this case it was trying to shift to left by -1. Fix this by actually shifting the function bits and not the position. Fixes: 4b36082e2e09 ("pinctrl: ocelot: fix pinmuxing for pins after 31") Signed-off-by: Horatiu Vultur Link: https://lore.kernel.org/r/20230206203720.1177718-1-horatiu.vultur@microchip.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-ocelot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c index a4a1b00f7f0d..c42a5b0bc4f0 100644 --- a/drivers/pinctrl/pinctrl-ocelot.c +++ b/drivers/pinctrl/pinctrl-ocelot.c @@ -575,7 +575,7 @@ static int ocelot_pinmux_set_mux(struct pinctrl_dev *pctldev, regmap_update_bits(info->map, REG_ALT(0, info, pin->pin), BIT(p), f << p); regmap_update_bits(info->map, REG_ALT(1, info, pin->pin), - BIT(p), f << (p - 1)); + BIT(p), (f >> 1) << p); return 0; } From 449a1a61f7f148aed285cd098e940ae6bc19246a Mon Sep 17 00:00:00 2001 From: msizanoen Date: Sun, 19 Mar 2023 23:02:56 -0700 Subject: [PATCH 2406/4345] Input: alps - fix compatibility with -funsigned-char commit 754ff5060daf5a1cf4474eff9b4edeb6c17ef7ab upstream. The AlpsPS/2 code previously relied on the assumption that `char` is a signed type, which was true on x86 platforms (the only place where this driver is used) before kernel 6.2. However, on 6.2 and later, this assumption is broken due to the introduction of -funsigned-char as a new global compiler flag. Fix this by explicitly specifying the signedness of `char` when sign extending the values received from the device. Fixes: f3f33c677699 ("Input: alps - Rushmore and v7 resolution support") Signed-off-by: msizanoen Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230320045228.182259-1-msizanoen@qtmlabs.xyz Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/mouse/alps.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index b067bfd2699c..0b10c466659e 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -852,8 +852,8 @@ static void alps_process_packet_v6(struct psmouse *psmouse) x = y = z = 0; /* Divide 4 since trackpoint's speed is too fast */ - input_report_rel(dev2, REL_X, (char)x / 4); - input_report_rel(dev2, REL_Y, -((char)y / 4)); + input_report_rel(dev2, REL_X, (s8)x / 4); + input_report_rel(dev2, REL_Y, -((s8)y / 4)); psmouse_report_standard_buttons(dev2, packet[3]); @@ -1104,8 +1104,8 @@ static void alps_process_trackstick_packet_v7(struct psmouse *psmouse) ((packet[3] & 0x20) << 1); z = (packet[5] & 0x3f) | ((packet[3] & 0x80) >> 1); - input_report_rel(dev2, REL_X, (char)x); - input_report_rel(dev2, REL_Y, -((char)y)); + input_report_rel(dev2, REL_X, (s8)x); + input_report_rel(dev2, REL_Y, -((s8)y)); input_report_abs(dev2, ABS_PRESSURE, z); psmouse_report_standard_buttons(dev2, packet[1]); @@ -2294,20 +2294,20 @@ static int alps_get_v3_v7_resolution(struct psmouse *psmouse, int reg_pitch) if (reg < 0) return reg; - x_pitch = (char)(reg << 4) >> 4; /* sign extend lower 4 bits */ + x_pitch = (s8)(reg << 4) >> 4; /* sign extend lower 4 bits */ x_pitch = 50 + 2 * x_pitch; /* In 0.1 mm units */ - y_pitch = (char)reg >> 4; /* sign extend upper 4 bits */ + y_pitch = (s8)reg >> 4; /* sign extend upper 4 bits */ y_pitch = 36 + 2 * y_pitch; /* In 0.1 mm units */ reg = alps_command_mode_read_reg(psmouse, reg_pitch + 1); if (reg < 0) return reg; - x_electrode = (char)(reg << 4) >> 4; /* sign extend lower 4 bits */ + x_electrode = (s8)(reg << 4) >> 4; /* sign extend lower 4 bits */ x_electrode = 17 + x_electrode; - y_electrode = (char)reg >> 4; /* sign extend upper 4 bits */ + y_electrode = (s8)reg >> 4; /* sign extend upper 4 bits */ y_electrode = 13 + y_electrode; x_phys = x_pitch * (x_electrode - 1); /* In 0.1 mm units */ From 8b3d7ad3e8f13a90d56c4d6b3b4eee78634615ab Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 19 Mar 2023 21:36:36 -0700 Subject: [PATCH 2407/4345] Input: focaltech - use explicitly signed char type commit 8980f190947ba29f23110408e712444884b74251 upstream. The recent change of -funsigned-char causes additions of negative numbers to become additions of large positive numbers, leading to wrong calculations of mouse movement. Change these casts to be explicitly signed, to take into account negative offsets. Fixes: 3bc753c06dd0 ("kbuild: treat char as always unsigned") Signed-off-by: Jason A. Donenfeld Reviewed-by: Hans de Goede Cc: stable@vger.kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=217211 Link: https://lore.kernel.org/r/20230318133010.1285202-1-Jason@zx2c4.com Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/mouse/focaltech.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/input/mouse/focaltech.c b/drivers/input/mouse/focaltech.c index 6fd5fff0cbff..c74b99077d16 100644 --- a/drivers/input/mouse/focaltech.c +++ b/drivers/input/mouse/focaltech.c @@ -202,8 +202,8 @@ static void focaltech_process_rel_packet(struct psmouse *psmouse, state->pressed = packet[0] >> 7; finger1 = ((packet[0] >> 4) & 0x7) - 1; if (finger1 < FOC_MAX_FINGERS) { - state->fingers[finger1].x += (char)packet[1]; - state->fingers[finger1].y += (char)packet[2]; + state->fingers[finger1].x += (s8)packet[1]; + state->fingers[finger1].y += (s8)packet[2]; } else { psmouse_err(psmouse, "First finger in rel packet invalid: %d\n", finger1); @@ -218,8 +218,8 @@ static void focaltech_process_rel_packet(struct psmouse *psmouse, */ finger2 = ((packet[3] >> 4) & 0x7) - 1; if (finger2 < FOC_MAX_FINGERS) { - state->fingers[finger2].x += (char)packet[4]; - state->fingers[finger2].y += (char)packet[5]; + state->fingers[finger2].x += (s8)packet[4]; + state->fingers[finger2].y += (s8)packet[5]; } } From 63bbe24b99f9187584be28a3a2336dddb5524c95 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Wed, 29 Mar 2023 17:14:22 -0300 Subject: [PATCH 2408/4345] cifs: prevent infinite recursion in CIFSGetDFSRefer() commit 09ba47b44d26b475bbdf9c80db9e0193d2b58956 upstream. We can't call smb_init() in CIFSGetDFSRefer() as cifs_reconnect_tcon() may end up calling CIFSGetDFSRefer() again to get new DFS referrals and thus causing an infinite recursion. Signed-off-by: Paulo Alcantara (SUSE) Reviewed-by: Ronnie Sahlberg Cc: stable@vger.kernel.org # 6.2 Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/cifssmb.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index c279527aae92..95992c93bbe3 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -4859,8 +4859,13 @@ CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses, return -ENODEV; getDFSRetry: - rc = smb_init(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, (void **) &pSMB, - (void **) &pSMBr); + /* + * Use smb_init_no_reconnect() instead of smb_init() as + * CIFSGetDFSRefer() may be called from cifs_reconnect_tcon() and thus + * causing an infinite recursion. + */ + rc = smb_init_no_reconnect(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, + (void **)&pSMB, (void **)&pSMBr); if (rc) return rc; From 26a32a212bc540f4773cd6af8cf73e967d72569c Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Wed, 29 Mar 2023 22:24:06 +0200 Subject: [PATCH 2409/4345] cifs: fix DFS traversal oops without CONFIG_CIFS_DFS_UPCALL commit 179a88a8558bbf42991d361595281f3e45d7edfc upstream. When compiled with CONFIG_CIFS_DFS_UPCALL disabled, cifs_dfs_d_automount is NULL. cifs.ko logic for mapping CIFS_FATTR_DFS_REFERRAL attributes to S_AUTOMOUNT and corresponding dentry flags is retained regardless of CONFIG_CIFS_DFS_UPCALL, leading to a NULL pointer dereference in VFS follow_automount() when traversing a DFS referral link: BUG: kernel NULL pointer dereference, address: 0000000000000000 ... Call Trace: __traverse_mounts+0xb5/0x220 ? cifs_revalidate_mapping+0x65/0xc0 [cifs] step_into+0x195/0x610 ? lookup_fast+0xe2/0xf0 path_lookupat+0x64/0x140 filename_lookup+0xc2/0x140 ? __create_object+0x299/0x380 ? kmem_cache_alloc+0x119/0x220 ? user_path_at_empty+0x31/0x50 user_path_at_empty+0x31/0x50 __x64_sys_chdir+0x2a/0xd0 ? exit_to_user_mode_prepare+0xca/0x100 do_syscall_64+0x42/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc This fix adds an inline cifs_dfs_d_automount() {return -EREMOTE} handler when CONFIG_CIFS_DFS_UPCALL is disabled. An alternative would be to avoid flagging S_AUTOMOUNT, etc. without CONFIG_CIFS_DFS_UPCALL. This approach was chosen as it provides more control over the error path. Signed-off-by: David Disseldorp Cc: stable@vger.kernel.org Reviewed-by: Paulo Alcantara (SUSE) Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/cifsfs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index e996f0bef414..59c41412ebaf 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -126,7 +126,10 @@ extern const struct dentry_operations cifs_ci_dentry_ops; #ifdef CONFIG_CIFS_DFS_UPCALL extern struct vfsmount *cifs_dfs_d_automount(struct path *path); #else -#define cifs_dfs_d_automount NULL +static inline struct vfsmount *cifs_dfs_d_automount(struct path *path) +{ + return ERR_PTR(-EREMOTE); +} #endif /* Functions related to symlinks */ From ba5deb64ddde2cb68b981f4d108b5cbed2633cfb Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 17 Mar 2023 03:13:12 -0700 Subject: [PATCH 2410/4345] Input: goodix - add Lenovo Yoga Book X90F to nine_bytes_report DMI table commit 8a0432bab6ea3203d220785da7ab3c7677f70ecb upstream. The Android Lenovo Yoga Book X90F / X90L uses the same goodix touchscreen with 9 bytes touch reports for its touch keyboard as the already supported Windows Lenovo Yoga Book X91F/L, add a DMI match for this to the nine_bytes_report DMI table. When the quirk for the X91F/L was initially added it was written to also apply to the X90F/L but this does not work because the Android version of the Yoga Book uses completely different DMI strings. Also adjust the X91F/L quirk to reflect that it only applies to the X91F/L models. Signed-off-by: Hans de Goede Reviewed-by: Bastien Nocera Link: https://lore.kernel.org/r/20230315134442.71787-1-hdegoede@redhat.com Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/touchscreen/goodix.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index b7f87ad4b9a9..098115eb8084 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -183,10 +183,18 @@ static const unsigned long goodix_irq_flags[] = { static const struct dmi_system_id nine_bytes_report[] = { #if defined(CONFIG_DMI) && defined(CONFIG_X86) { - .ident = "Lenovo YogaBook", - /* YB1-X91L/F and YB1-X90L/F */ + /* Lenovo Yoga Book X90F / X90L */ .matches = { - DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9") + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"), + } + }, + { + /* Lenovo Yoga Book X91F / X91L */ + .matches = { + /* Non exact match to match F + L versions */ + DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X91"), } }, #endif From 5f6347034341bf45056ca1ec3fa72040152ecf83 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 22 Mar 2023 10:33:28 +0000 Subject: [PATCH 2411/4345] btrfs: fix race between quota disable and quota assign ioctls commit 2f1a6be12ab6c8470d5776e68644726c94257c54 upstream. The quota assign ioctl can currently run in parallel with a quota disable ioctl call. The assign ioctl uses the quota root, while the disable ioctl frees that root, and therefore we can have a use-after-free triggered in the assign ioctl, leading to a trace like the following when KASAN is enabled: [672.723][T736] BUG: KASAN: slab-use-after-free in btrfs_search_slot+0x2962/0x2db0 [672.723][T736] Read of size 8 at addr ffff888022ec0208 by task btrfs_search_sl/27736 [672.724][T736] [672.725][T736] CPU: 1 PID: 27736 Comm: btrfs_search_sl Not tainted 6.3.0-rc3 #37 [672.723][T736] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [672.727][T736] Call Trace: [672.728][T736] [672.728][T736] dump_stack_lvl+0xd9/0x150 [672.725][T736] print_report+0xc1/0x5e0 [672.720][T736] ? __virt_addr_valid+0x61/0x2e0 [672.727][T736] ? __phys_addr+0xc9/0x150 [672.725][T736] ? btrfs_search_slot+0x2962/0x2db0 [672.722][T736] kasan_report+0xc0/0xf0 [672.729][T736] ? btrfs_search_slot+0x2962/0x2db0 [672.724][T736] btrfs_search_slot+0x2962/0x2db0 [672.723][T736] ? fs_reclaim_acquire+0xba/0x160 [672.722][T736] ? split_leaf+0x13d0/0x13d0 [672.726][T736] ? rcu_is_watching+0x12/0xb0 [672.723][T736] ? kmem_cache_alloc+0x338/0x3c0 [672.722][T736] update_qgroup_status_item+0xf7/0x320 [672.724][T736] ? add_qgroup_rb+0x3d0/0x3d0 [672.739][T736] ? do_raw_spin_lock+0x12d/0x2b0 [672.730][T736] ? spin_bug+0x1d0/0x1d0 [672.737][T736] btrfs_run_qgroups+0x5de/0x840 [672.730][T736] ? btrfs_qgroup_rescan_worker+0xa70/0xa70 [672.738][T736] ? __del_qgroup_relation+0x4ba/0xe00 [672.738][T736] btrfs_ioctl+0x3d58/0x5d80 [672.735][T736] ? tomoyo_path_number_perm+0x16a/0x550 [672.737][T736] ? tomoyo_execute_permission+0x4a0/0x4a0 [672.731][T736] ? btrfs_ioctl_get_supported_features+0x50/0x50 [672.737][T736] ? __sanitizer_cov_trace_switch+0x54/0x90 [672.734][T736] ? do_vfs_ioctl+0x132/0x1660 [672.730][T736] ? vfs_fileattr_set+0xc40/0xc40 [672.730][T736] ? _raw_spin_unlock_irq+0x2e/0x50 [672.732][T736] ? sigprocmask+0xf2/0x340 [672.737][T736] ? __fget_files+0x26a/0x480 [672.732][T736] ? bpf_lsm_file_ioctl+0x9/0x10 [672.738][T736] ? btrfs_ioctl_get_supported_features+0x50/0x50 [672.736][T736] __x64_sys_ioctl+0x198/0x210 [672.736][T736] do_syscall_64+0x39/0xb0 [672.731][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.739][T736] RIP: 0033:0x4556ad [672.742][T736] [672.743][T736] [672.748][T736] Allocated by task 27677: [672.743][T736] kasan_save_stack+0x22/0x40 [672.741][T736] kasan_set_track+0x25/0x30 [672.741][T736] __kasan_kmalloc+0xa4/0xb0 [672.749][T736] btrfs_alloc_root+0x48/0x90 [672.746][T736] btrfs_create_tree+0x146/0xa20 [672.744][T736] btrfs_quota_enable+0x461/0x1d20 [672.743][T736] btrfs_ioctl+0x4a1c/0x5d80 [672.747][T736] __x64_sys_ioctl+0x198/0x210 [672.749][T736] do_syscall_64+0x39/0xb0 [672.744][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.756][T736] [672.757][T736] Freed by task 27677: [672.759][T736] kasan_save_stack+0x22/0x40 [672.759][T736] kasan_set_track+0x25/0x30 [672.756][T736] kasan_save_free_info+0x2e/0x50 [672.751][T736] ____kasan_slab_free+0x162/0x1c0 [672.758][T736] slab_free_freelist_hook+0x89/0x1c0 [672.752][T736] __kmem_cache_free+0xaf/0x2e0 [672.752][T736] btrfs_put_root+0x1ff/0x2b0 [672.759][T736] btrfs_quota_disable+0x80a/0xbc0 [672.752][T736] btrfs_ioctl+0x3e5f/0x5d80 [672.756][T736] __x64_sys_ioctl+0x198/0x210 [672.753][T736] do_syscall_64+0x39/0xb0 [672.765][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.769][T736] [672.768][T736] The buggy address belongs to the object at ffff888022ec0000 [672.768][T736] which belongs to the cache kmalloc-4k of size 4096 [672.769][T736] The buggy address is located 520 bytes inside of [672.769][T736] freed 4096-byte region [ffff888022ec0000, ffff888022ec1000) [672.760][T736] [672.764][T736] The buggy address belongs to the physical page: [672.761][T736] page:ffffea00008bb000 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x22ec0 [672.766][T736] head:ffffea00008bb000 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [672.779][T736] flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) [672.770][T736] raw: 00fff00000010200 ffff888012842140 ffffea000054ba00 dead000000000002 [672.770][T736] raw: 0000000000000000 0000000000040004 00000001ffffffff 0000000000000000 [672.771][T736] page dumped because: kasan: bad access detected [672.778][T736] page_owner tracks the page as allocated [672.777][T736] page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd2040(__GFP_IO|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 88 [672.779][T736] get_page_from_freelist+0x119c/0x2d50 [672.779][T736] __alloc_pages+0x1cb/0x4a0 [672.776][T736] alloc_pages+0x1aa/0x270 [672.773][T736] allocate_slab+0x260/0x390 [672.771][T736] ___slab_alloc+0xa9a/0x13e0 [672.778][T736] __slab_alloc.constprop.0+0x56/0xb0 [672.771][T736] __kmem_cache_alloc_node+0x136/0x320 [672.789][T736] __kmalloc+0x4e/0x1a0 [672.783][T736] tomoyo_realpath_from_path+0xc3/0x600 [672.781][T736] tomoyo_path_perm+0x22f/0x420 [672.782][T736] tomoyo_path_unlink+0x92/0xd0 [672.780][T736] security_path_unlink+0xdb/0x150 [672.788][T736] do_unlinkat+0x377/0x680 [672.788][T736] __x64_sys_unlink+0xca/0x110 [672.789][T736] do_syscall_64+0x39/0xb0 [672.783][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.784][T736] page last free stack trace: [672.787][T736] free_pcp_prepare+0x4e5/0x920 [672.787][T736] free_unref_page+0x1d/0x4e0 [672.784][T736] __unfreeze_partials+0x17c/0x1a0 [672.797][T736] qlist_free_all+0x6a/0x180 [672.796][T736] kasan_quarantine_reduce+0x189/0x1d0 [672.797][T736] __kasan_slab_alloc+0x64/0x90 [672.793][T736] kmem_cache_alloc+0x17c/0x3c0 [672.799][T736] getname_flags.part.0+0x50/0x4e0 [672.799][T736] getname_flags+0x9e/0xe0 [672.792][T736] vfs_fstatat+0x77/0xb0 [672.791][T736] __do_sys_newlstat+0x84/0x100 [672.798][T736] do_syscall_64+0x39/0xb0 [672.796][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.790][T736] [672.791][T736] Memory state around the buggy address: [672.799][T736] ffff888022ec0100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.805][T736] ffff888022ec0180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.802][T736] >ffff888022ec0200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.809][T736] ^ [672.809][T736] ffff888022ec0280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.809][T736] ffff888022ec0300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fix this by having the qgroup assign ioctl take the qgroup ioctl mutex before calling btrfs_run_qgroups(), which is what all qgroup ioctls should call. Reported-by: butt3rflyh4ck Link: https://lore.kernel.org/linux-btrfs/CAFcO6XN3VD8ogmHwqRk4kbiwtpUSNySu2VAxN8waEPciCHJvMA@mail.gmail.com/ CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/ioctl.c | 2 ++ fs/btrfs/qgroup.c | 11 ++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fc335b5e44df..10686b494f0a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4254,7 +4254,9 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) } /* update qgroup status and info */ + mutex_lock(&fs_info->qgroup_ioctl_lock); err = btrfs_run_qgroups(trans); + mutex_unlock(&fs_info->qgroup_ioctl_lock); if (err < 0) btrfs_handle_fs_error(fs_info, err, "failed to update qgroup status and info"); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 9fe6a01ea8b8..3fc689154bb5 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2762,13 +2762,22 @@ cleanup: } /* - * called from commit_transaction. Writes all changed qgroups to disk. + * Writes all changed qgroups to disk. + * Called by the transaction commit path and the qgroup assign ioctl. */ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret = 0; + /* + * In case we are called from the qgroup assign ioctl, assert that we + * are holding the qgroup_ioctl_lock, otherwise we can race with a quota + * disable operation (ioctl) and access a freed quota root. + */ + if (trans->transaction->state != TRANS_STATE_COMMIT_DOING) + lockdep_assert_held(&fs_info->qgroup_ioctl_lock); + if (!fs_info->quota_root) return ret; From b3d7a4478ce0a32bccef6631d3330e3bbc4090a9 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 27 Mar 2023 10:36:45 +0200 Subject: [PATCH 2412/4345] xen/netback: don't do grant copy across page boundary commit 05310f31ca74673a96567fb14637b7d5d6c82ea5 upstream. Fix xenvif_get_requests() not to do grant copy operations across local page boundaries. This requires to double the maximum number of copy operations per queue, as each copy could now be split into 2. Make sure that struct xenvif_tx_cb doesn't grow too large. Cc: stable@vger.kernel.org Fixes: ad7f402ae4f4 ("xen/netback: Ensure protocol headers don't fall in the non-linear area") Signed-off-by: Juergen Gross Reviewed-by: Paul Durrant Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- drivers/net/xen-netback/common.h | 2 +- drivers/net/xen-netback/netback.c | 25 +++++++++++++++++++++++-- 2 files changed, 24 insertions(+), 3 deletions(-) diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 1ba974969216..fe99439ad5fb 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -166,7 +166,7 @@ struct xenvif_queue { /* Per-queue data for xenvif */ struct pending_tx_info pending_tx_info[MAX_PENDING_REQS]; grant_handle_t grant_tx_handle[MAX_PENDING_REQS]; - struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS]; + struct gnttab_copy tx_copy_ops[2 * MAX_PENDING_REQS]; struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS]; struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS]; /* passed to gnttab_[un]map_refs with pages under (un)mapping */ diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index f9373a88cf37..67614e7166ac 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -334,6 +334,7 @@ static int xenvif_count_requests(struct xenvif_queue *queue, struct xenvif_tx_cb { u16 copy_pending_idx[XEN_NETBK_LEGACY_SLOTS_MAX + 1]; u8 copy_count; + u32 split_mask; }; #define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) @@ -361,6 +362,8 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) struct sk_buff *skb = alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN, GFP_ATOMIC | __GFP_NOWARN); + + BUILD_BUG_ON(sizeof(*XENVIF_TX_CB(skb)) > sizeof(skb->cb)); if (unlikely(skb == NULL)) return NULL; @@ -396,11 +399,13 @@ static void xenvif_get_requests(struct xenvif_queue *queue, nr_slots = shinfo->nr_frags + 1; copy_count(skb) = 0; + XENVIF_TX_CB(skb)->split_mask = 0; /* Create copy ops for exactly data_len bytes into the skb head. */ __skb_put(skb, data_len); while (data_len > 0) { int amount = data_len > txp->size ? txp->size : data_len; + bool split = false; cop->source.u.ref = txp->gref; cop->source.domid = queue->vif->domid; @@ -413,6 +418,13 @@ static void xenvif_get_requests(struct xenvif_queue *queue, cop->dest.u.gmfn = virt_to_gfn(skb->data + skb_headlen(skb) - data_len); + /* Don't cross local page boundary! */ + if (cop->dest.offset + amount > XEN_PAGE_SIZE) { + amount = XEN_PAGE_SIZE - cop->dest.offset; + XENVIF_TX_CB(skb)->split_mask |= 1U << copy_count(skb); + split = true; + } + cop->len = amount; cop->flags = GNTCOPY_source_gref; @@ -420,7 +432,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, pending_idx = queue->pending_ring[index]; callback_param(queue, pending_idx).ctx = NULL; copy_pending_idx(skb, copy_count(skb)) = pending_idx; - copy_count(skb)++; + if (!split) + copy_count(skb)++; cop++; data_len -= amount; @@ -441,7 +454,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, nr_slots--; } else { /* The copy op partially covered the tx_request. - * The remainder will be mapped. + * The remainder will be mapped or copied in the next + * iteration. */ txp->offset += amount; txp->size -= amount; @@ -539,6 +553,13 @@ static int xenvif_tx_check_gop(struct xenvif_queue *queue, pending_idx = copy_pending_idx(skb, i); newerr = (*gopp_copy)->status; + + /* Split copies need to be handled together. */ + if (XENVIF_TX_CB(skb)->split_mask & (1U << i)) { + (*gopp_copy)++; + if (!newerr) + newerr = (*gopp_copy)->status; + } if (likely(!newerr)) { /* The first frag might still have this slot mapped */ if (i < copy_count(skb) - 1 || !sharedslot) From fbf3fe7f7bc3713ef191c1edcc30a46e90c1ea09 Mon Sep 17 00:00:00 2001 From: Josua Mayer Date: Thu, 23 Mar 2023 12:25:36 +0200 Subject: [PATCH 2413/4345] net: phy: dp83869: fix default value for tx-/rx-internal-delay commit 82e2c39f9ef78896e9b634dfd82dc042e6956bb7 upstream. dp83869 internally uses a look-up table for mapping supported delays in nanoseconds to register values. When specific delays are defined in device-tree, phy_get_internal_delay does the lookup automatically returning an index. The default case wrongly assigns the nanoseconds value from the lookup table, resulting in numeric value 2000 applied to delay configuration register, rather than the expected index values 0-7 (7 for 2000). Ultimately this issue broke RX for 1Gbps links. Fix default delay configuration by assigning the intended index value directly. Cc: stable@vger.kernel.org Fixes: 736b25afe284 ("net: dp83869: Add RGMII internal delay configuration") Co-developed-by: Yazan Shhady Signed-off-by: Yazan Shhady Signed-off-by: Josua Mayer Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230323102536.31988-1-josua@solid-run.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/dp83869.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index a9daff88006b..65b69ff35e40 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -553,15 +553,13 @@ static int dp83869_of_init(struct phy_device *phydev) &dp83869_internal_delay[0], delay_size, true); if (dp83869->rx_int_delay < 0) - dp83869->rx_int_delay = - dp83869_internal_delay[DP83869_CLK_DELAY_DEF]; + dp83869->rx_int_delay = DP83869_CLK_DELAY_DEF; dp83869->tx_int_delay = phy_get_internal_delay(phydev, dev, &dp83869_internal_delay[0], delay_size, false); if (dp83869->tx_int_delay < 0) - dp83869->tx_int_delay = - dp83869_internal_delay[DP83869_CLK_DELAY_DEF]; + dp83869->tx_int_delay = DP83869_CLK_DELAY_DEF; return ret; } From 25065ed83b5ffaada1768e0416c6e96fdb8da032 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Kornel=20Dul=C4=99ba?= Date: Mon, 20 Mar 2023 09:32:59 +0000 Subject: [PATCH 2414/4345] pinctrl: amd: Disable and mask interrupts on resume MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit b26cd9325be4c1fcd331b77f10acb627c560d4d7 upstream. This fixes a similar problem to the one observed in: commit 4e5a04be88fe ("pinctrl: amd: disable and mask interrupts on probe"). On some systems, during suspend/resume cycle firmware leaves an interrupt enabled on a pin that is not used by the kernel. This confuses the AMD pinctrl driver and causes spurious interrupts. The driver already has logic to detect if a pin is used by the kernel. Leverage it to re-initialize interrupt fields of a pin only if it's not used by us. Cc: stable@vger.kernel.org Fixes: dbad75dd1f25 ("pinctrl: add AMD GPIO driver support.") Signed-off-by: Kornel Dulęba Link: https://lore.kernel.org/r/20230320093259.845178-1-korneld@chromium.org Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-amd.c | 36 +++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 16 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 82b658a3c220..7bfdf5ad77c4 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -764,32 +764,34 @@ static const struct pinconf_ops amd_pinconf_ops = { .pin_config_group_set = amd_pinconf_group_set, }; -static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) +static void amd_gpio_irq_init_pin(struct amd_gpio *gpio_dev, int pin) { - struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + const struct pin_desc *pd; unsigned long flags; u32 pin_reg, mask; - int i; mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | BIT(INTERRUPT_MASK_OFF) | BIT(INTERRUPT_ENABLE_OFF) | BIT(WAKE_CNTRL_OFF_S4); - for (i = 0; i < desc->npins; i++) { - int pin = desc->pins[i].number; - const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin); + pd = pin_desc_get(gpio_dev->pctrl, pin); + if (!pd) + return; - if (!pd) - continue; + raw_spin_lock_irqsave(&gpio_dev->lock, flags); + pin_reg = readl(gpio_dev->base + pin * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + pin * 4); + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); +} - raw_spin_lock_irqsave(&gpio_dev->lock, flags); +static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) +{ + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + int i; - pin_reg = readl(gpio_dev->base + i * 4); - pin_reg &= ~mask; - writel(pin_reg, gpio_dev->base + i * 4); - - raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); - } + for (i = 0; i < desc->npins; i++) + amd_gpio_irq_init_pin(gpio_dev, i); } #ifdef CONFIG_PM_SLEEP @@ -842,8 +844,10 @@ static int amd_gpio_resume(struct device *dev) for (i = 0; i < desc->npins; i++) { int pin = desc->pins[i].number; - if (!amd_gpio_should_save(gpio_dev, pin)) + if (!amd_gpio_should_save(gpio_dev, pin)) { + amd_gpio_irq_init_pin(gpio_dev, pin); continue; + } raw_spin_lock_irqsave(&gpio_dev->lock, flags); gpio_dev->saved_regs[i] |= readl(gpio_dev->base + pin * 4) & PIN_IRQ_PENDING; From 12c2612e18cabec2320b7068e829f0101d0254f2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 24 Feb 2023 14:08:28 +0100 Subject: [PATCH 2415/4345] pinctrl: at91-pio4: fix domain name assignment commit 7bb97e360acdd38b68ad0a1defb89c6e89c85596 upstream. Since commit d59f6617eef0 ("genirq: Allow fwnode to carry name information only") an IRQ domain is always given a name during allocation (e.g. used for the debugfs entry). Drop the no longer valid name assignment, which would lead to an attempt to free a string constant when removing the domain on late probe failures (e.g. probe deferral). Fixes: d59f6617eef0 ("genirq: Allow fwnode to carry name information only") Cc: stable@vger.kernel.org # 4.13 Signed-off-by: Johan Hovold Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea # on SAMA7G5 Link: https://lore.kernel.org/r/20230224130828.27985-1-johan+linaro@kernel.org Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-at91-pio4.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index d2e2b101978f..315a6c4d9ade 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1139,7 +1139,6 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) dev_err(dev, "can't add the irq domain\n"); return -ENODEV; } - atmel_pioctrl->irq_domain->name = "atmel gpio"; for (i = 0; i < atmel_pioctrl->npins; i++) { int irq = irq_create_mapping(atmel_pioctrl->irq_domain, i); From 80a4200d51e5a7e046f4a90f5faa5bafd5a60c58 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 26 Mar 2023 16:15:57 -0600 Subject: [PATCH 2416/4345] powerpc: Don't try to copy PPR for task with NULL pt_regs commit fd7276189450110ed835eb0a334e62d2f1c4e3be upstream. powerpc sets up PF_KTHREAD and PF_IO_WORKER with a NULL pt_regs, which from my (arguably very short) checking is not commonly done for other archs. This is fine, except when PF_IO_WORKER's have been created and the task does something that causes a coredump to be generated. Then we get this crash: Kernel attempted to read user page (160) - exploit attempt? (uid: 1000) BUG: Kernel NULL pointer dereference on read at 0x00000160 Faulting instruction address: 0xc0000000000c3a60 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=32 NUMA pSeries Modules linked in: bochs drm_vram_helper drm_kms_helper xts binfmt_misc ecb ctr syscopyarea sysfillrect cbc sysimgblt drm_ttm_helper aes_generic ttm sg libaes evdev joydev virtio_balloon vmx_crypto gf128mul drm dm_mod fuse loop configfs drm_panel_orientation_quirks ip_tables x_tables autofs4 hid_generic usbhid hid xhci_pci xhci_hcd usbcore usb_common sd_mod CPU: 1 PID: 1982 Comm: ppc-crash Not tainted 6.3.0-rc2+ #88 Hardware name: IBM pSeries (emulated by qemu) POWER9 (raw) 0x4e1202 0xf000005 of:SLOF,HEAD hv:linux,kvm pSeries NIP: c0000000000c3a60 LR: c000000000039944 CTR: c0000000000398e0 REGS: c0000000041833b0 TRAP: 0300 Not tainted (6.3.0-rc2+) MSR: 800000000280b033 CR: 88082828 XER: 200400f8 ... NIP memcpy_power7+0x200/0x7d0 LR ppr_get+0x64/0xb0 Call Trace: ppr_get+0x40/0xb0 (unreliable) __regset_get+0x180/0x1f0 regset_get_alloc+0x64/0x90 elf_core_dump+0xb98/0x1b60 do_coredump+0x1c34/0x24a0 get_signal+0x71c/0x1410 do_notify_resume+0x140/0x6f0 interrupt_exit_user_prepare_main+0x29c/0x320 interrupt_exit_user_prepare+0x6c/0xa0 interrupt_return_srr_user+0x8/0x138 Because ppr_get() is trying to copy from a PF_IO_WORKER with a NULL pt_regs. Check for a valid pt_regs in both ppc_get/ppr_set, and return an error if not set. The actual error value doesn't seem to be important here, so just pick -EINVAL. Fixes: fa439810cc1b ("powerpc/ptrace: Enable support for NT_PPPC_TAR, NT_PPC_PPR, NT_PPC_DSCR") Cc: stable@vger.kernel.org # v4.8+ Signed-off-by: Jens Axboe [mpe: Trim oops in change log, add Fixes & Cc stable] Signed-off-by: Michael Ellerman Link: https://msgid.link/d9f63344-fe7c-56ae-b420-4a1a04a2ae4c@kernel.dk Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/ptrace/ptrace-view.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index 7e6478e7ed07..67c126d4f431 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -298,6 +298,9 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, static int ppr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { + if (!target->thread.regs) + return -EINVAL; + return membuf_write(&to, &target->thread.regs->ppr, sizeof(u64)); } @@ -305,6 +308,9 @@ static int ppr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { + if (!target->thread.regs) + return -EINVAL; + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.regs->ppr, 0, sizeof(u64)); } From 3d328a17c8cb4117cfa8d711d91faeb7c7819484 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 21 Mar 2023 00:17:36 -0400 Subject: [PATCH 2417/4345] NFSv4: Fix hangs when recovering open state after a server reboot commit 6165a16a5ad9b237bb3131cff4d3c601ccb8f9a3 upstream. When we're using a cached open stateid or a delegation in order to avoid sending a CLAIM_PREVIOUS open RPC call to the server, we don't have a new open stateid to present to update_open_stateid(). Instead rely on nfs4_try_open_cached(), just as if we were doing a normal open. Fixes: d2bfda2e7aa0 ("NFSv4: don't reprocess cached open CLAIM_PREVIOUS") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Greg Kroah-Hartman --- fs/nfs/nfs4proc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8653335c17b6..bca5d1bdd79b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1975,8 +1975,7 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (!data->rpc_done) { if (data->rpc_status) return ERR_PTR(data->rpc_status); - /* cached opens have already been processed */ - goto update; + return nfs4_try_open_cached(data); } ret = nfs_refresh_inode(inode, &data->f_attr); @@ -1985,7 +1984,7 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); -update: + if (!update_open_stateid(state, &data->o_res.stateid, NULL, data->o_arg.fmode)) return ERR_PTR(-EAGAIN); From 0044721f4f9553f4001f5a469ac45d2a10e17139 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 20 Mar 2023 15:09:54 +0100 Subject: [PATCH 2418/4345] ALSA: hda/conexant: Partial revert of a quirk for Lenovo commit b871cb971c683f7f212e7ca3c9a6709a75785116 upstream. The recent commit f83bb2592482 ("ALSA: hda/conexant: Add quirk for LENOVO 20149 Notebook model") introduced a quirk for the device with 17aa:3977, but this caused a regression on another model (Lenovo Ideadpad U31) with the very same PCI SSID. And, through skimming over the net, it seems that this PCI SSID is used for multiple different models, so it's no good idea to apply the quirk with the SSID. Although we may take a different ID check (e.g. the codec SSID instead of the PCI SSID), unfortunately, the original patch author couldn't identify the hardware details any longer as the machine was returned, and we can't develop the further proper fix. In this patch, instead, we partially revert the change so that the quirk won't be applied as default for addressing the regression. Meanwhile, the quirk function itself is kept, and it's now made to be applicable via the explicit model=lenovo-20149 option. Fixes: f83bb2592482 ("ALSA: hda/conexant: Add quirk for LENOVO 20149 Notebook model") Reported-by: Jetro Jormalainen Link: https://lore.kernel.org/r/20230308215009.4d3e58a6@mopti Cc: Link: https://lore.kernel.org/r/20230320140954.31154-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_conexant.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 48b802563c2d..e35c470eb481 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -973,7 +973,10 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x17aa, 0x3905, "Lenovo G50-30", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x390b, "Lenovo G50-80", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3975, "Lenovo U300s", CXT_FIXUP_STEREO_DMIC), - SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_PINCFG_LENOVO_NOTEBOOK), + /* NOTE: we'd need to extend the quirk for 17aa:3977 as the same + * PCI SSID is used on multiple Lenovo models + */ + SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo G50-70", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x397b, "Lenovo S205", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", CXT_FIXUP_THINKPAD_ACPI), @@ -996,6 +999,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = { { .id = CXT_FIXUP_MUTE_LED_GPIO, .name = "mute-led-gpio" }, { .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" }, { .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" }, + { .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" }, {} }; From 3b6992bdf09d7e46e9bfb92a98c4ca1f2779466a Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 24 Mar 2023 08:50:05 +0100 Subject: [PATCH 2419/4345] ALSA: usb-audio: Fix regression on detection of Roland VS-100 commit fa4e7a6fa12b1132340785e14bd439cbe95b7a5a upstream. It's been reported that the recent kernel can't probe the PCM devices on Roland VS-100 properly, and it turned out to be a regression by the recent addition of the bit shift range check for the format bits. In the old code, we just did bit-shift and it resulted in zero, which is then corrected to the standard PCM format, while the new code explicitly returns an error in such a case. For addressing the regression, relax the check and fallback to the standard PCM type (with the info output). Fixes: 43d5ca88dfcd ("ALSA: usb-audio: Fix potential out-of-bounds shift") Cc: Link: https://bugzilla.kernel.org/show_bug.cgi?id=217084 Link: https://lore.kernel.org/r/20230324075005.19403-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/format.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/sound/usb/format.c b/sound/usb/format.c index e8a63ea2189d..e0fda244a942 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -40,8 +40,12 @@ static u64 parse_audio_format_i_type(struct snd_usb_audio *chip, case UAC_VERSION_1: default: { struct uac_format_type_i_discrete_descriptor *fmt = _fmt; - if (format >= 64) - return 0; /* invalid format */ + if (format >= 64) { + usb_audio_info(chip, + "%u:%d: invalid format type 0x%llx is detected, processed as PCM\n", + fp->iface, fp->altsetting, format); + format = UAC_FORMAT_TYPE_I_PCM; + } sample_width = fmt->bBitResolution; sample_bytes = fmt->bSubframeSize; format = 1ULL << format; From 8ada1b5c8b43222d962231c58aebe4c72e5bf90c Mon Sep 17 00:00:00 2001 From: huangwenhui Date: Tue, 28 Mar 2023 15:46:44 +0800 Subject: [PATCH 2420/4345] ALSA: hda/realtek: Add quirk for Lenovo ZhaoYang CF4620Z commit 52aad39385e1bfdb34a1b405f699a8ef302c58b0 upstream. Fix headset microphone detection on Lenovo ZhaoYang CF4620Z. [ adjusted to be applicable to the latest tree -- tiwai ] Signed-off-by: huangwenhui Cc: Link: https://lore.kernel.org/r/20230328074644.30142-1-huangwenhuia@uniontech.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2cf6600c9ca8..2af9cd7b7999 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9253,6 +9253,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x511e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), + SND_PCI_QUIRK(0x17aa, 0x9e56, "Lenovo ZhaoYang CF4620Z", ALC286_FIXUP_SONY_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1849, 0x1233, "ASRock NUC Box 1100", ALC233_FIXUP_NO_AUDIO_JACK), SND_PCI_QUIRK(0x1849, 0xa233, "Positivo Master C6300", ALC269_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS), From 08bfd05987df2756aaf7b2b8f014c4cdcc6bcb39 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Thu, 16 Mar 2023 23:00:21 -0700 Subject: [PATCH 2421/4345] xtensa: fix KASAN report for show_stack commit 1d3b7a788ca7435156809a6bd5b20c95b2370d45 upstream. show_stack dumps raw stack contents which may trigger an unnecessary KASAN report. Fix it by copying stack contents to a temporary buffer with __memcpy and then printing that buffer instead of passing stack pointer directly to the print_hex_dump. Cc: stable@vger.kernel.org Signed-off-by: Max Filippov Signed-off-by: Greg Kroah-Hartman --- arch/xtensa/kernel/traps.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 129f23c0ab55..6af68305b795 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -503,7 +503,7 @@ static size_t kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH; void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) { - size_t len; + size_t len, off = 0; if (!sp) sp = stack_pointer(task); @@ -512,9 +512,17 @@ void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) kstack_depth_to_print * STACK_DUMP_ENTRY_SIZE); printk("%sStack:\n", loglvl); - print_hex_dump(loglvl, " ", DUMP_PREFIX_NONE, - STACK_DUMP_LINE_SIZE, STACK_DUMP_ENTRY_SIZE, - sp, len, false); + while (off < len) { + u8 line[STACK_DUMP_LINE_SIZE]; + size_t line_len = len - off > STACK_DUMP_LINE_SIZE ? + STACK_DUMP_LINE_SIZE : len - off; + + __memcpy(line, (u8 *)sp + off, line_len); + print_hex_dump(loglvl, " ", DUMP_PREFIX_NONE, + STACK_DUMP_LINE_SIZE, STACK_DUMP_ENTRY_SIZE, + line, line_len, false); + off += STACK_DUMP_LINE_SIZE; + } show_trace(task, sp, loglvl); } From a484f8bec8ee33e596d6936241bb397e76144ef8 Mon Sep 17 00:00:00 2001 From: Douglas Raillard Date: Mon, 6 Mar 2023 12:27:43 +0000 Subject: [PATCH 2422/4345] rcu: Fix rcu_torture_read ftrace event commit d18a04157fc171fd48075e3dc96471bd3b87f0dd upstream. Fix the rcutorturename field so that its size is correctly reported in the text format embedded in trace.dat files. As it stands, it is reported as being of size 1: field:char rcutorturename[8]; offset:8; size:1; signed:0; Signed-off-by: Douglas Raillard Reviewed-by: Mukesh Ojha Cc: stable@vger.kernel.org Fixes: 04ae87a52074e ("ftrace: Rework event_create_dir()") Reviewed-by: Steven Rostedt (Google) [ boqun: Add "Cc" and "Fixes" tags per Steven ] Signed-off-by: Boqun Feng Signed-off-by: Paul E. McKenney Signed-off-by: Greg Kroah-Hartman --- include/trace/events/rcu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 155b5cb43cfd..2d8790e40901 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -713,7 +713,7 @@ TRACE_EVENT_RCU(rcu_torture_read, TP_ARGS(rcutorturename, rhp, secs, c_old, c), TP_STRUCT__entry( - __field(char, rcutorturename[RCUTORTURENAME_LEN]) + __array(char, rcutorturename, RCUTORTURENAME_LEN) __field(struct rcu_head *, rhp) __field(unsigned long, secs) __field(unsigned long, c_old) From 79815326a516f70af8a79f1a49e50f3efd11a1db Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 24 Feb 2023 18:21:54 +0100 Subject: [PATCH 2423/4345] drm/etnaviv: fix reference leak when mmaping imported buffer commit 963b2e8c428f79489ceeb058e8314554ec9cbe6f upstream. drm_gem_prime_mmap() takes a reference on the GEM object, but before that drm_gem_mmap_obj() already takes a reference, which will be leaked as only one reference is dropped when the mapping is closed. Drop the extra reference when dma_buf_mmap() succeeds. Cc: stable@vger.kernel.org Signed-off-by: Lucas Stach Reviewed-by: Christian Gmeiner Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c index 4aa3426a9ba4..33974cc57e32 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c @@ -93,7 +93,15 @@ static void *etnaviv_gem_prime_vmap_impl(struct etnaviv_gem_object *etnaviv_obj) static int etnaviv_gem_prime_mmap_obj(struct etnaviv_gem_object *etnaviv_obj, struct vm_area_struct *vma) { - return dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0); + int ret; + + ret = dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0); + if (!ret) { + /* Drop the reference acquired by drm_gem_mmap_obj(). */ + drm_gem_object_put(&etnaviv_obj->base); + } + + return ret; } static const struct etnaviv_gem_ops etnaviv_gem_prime_ops = { From 7051d51f1241d02a9db159485bddfe508427ab01 Mon Sep 17 00:00:00 2001 From: Fangzhi Zuo Date: Fri, 24 Feb 2023 13:45:21 -0500 Subject: [PATCH 2424/4345] drm/amd/display: Add DSC Support for Synaptics Cascaded MST Hub commit f4f3b7dedbe849e780c779ba67365bb1db0d8637 upstream. Traditional synaptics hub has one MST branch device without virtual dpcd. Synaptics cascaded hub has two chained MST branch devices. DSC decoding is performed via root MST branch device, instead of the second MST branch device. Reviewed-by: Hersen Wu Acked-by: Qingqing Zhuo Signed-off-by: Fangzhi Zuo Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- .../display/amdgpu_dm/amdgpu_dm_mst_types.c | 19 +++++++++++++++++++ .../display/amdgpu_dm/amdgpu_dm_mst_types.h | 12 ++++++++++++ 2 files changed, 31 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index d617e98afb76..767b3d31c720 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -164,6 +164,21 @@ static bool needs_dsc_aux_workaround(struct dc_link *link) return false; } +bool is_synaptics_cascaded_panamera(struct dc_link *link, struct drm_dp_mst_port *port) +{ + u8 branch_vendor_data[4] = { 0 }; // Vendor data 0x50C ~ 0x50F + + if (drm_dp_dpcd_read(port->mgr->aux, DP_BRANCH_VENDOR_SPECIFIC_START, &branch_vendor_data, 4) == 4) { + if (link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 && + IS_SYNAPTICS_CASCADED_PANAMERA(link->dpcd_caps.branch_dev_name, branch_vendor_data)) { + DRM_INFO("Synaptics Cascaded MST hub\n"); + return true; + } + } + + return false; +} + static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector) { struct dc_sink *dc_sink = aconnector->dc_sink; @@ -185,6 +200,10 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto needs_dsc_aux_workaround(aconnector->dc_link)) aconnector->dsc_aux = &aconnector->mst_port->dm_dp_aux.aux; + /* synaptics cascaded MST hub case */ + if (!aconnector->dsc_aux && is_synaptics_cascaded_panamera(aconnector->dc_link, port)) + aconnector->dsc_aux = port->mgr->aux; + if (!aconnector->dsc_aux) return false; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index b38bd68121ce..5d60e2bf0bd8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -26,6 +26,18 @@ #ifndef __DAL_AMDGPU_DM_MST_TYPES_H__ #define __DAL_AMDGPU_DM_MST_TYPES_H__ +#define DP_BRANCH_VENDOR_SPECIFIC_START 0x50C + +/** + * Panamera MST Hub detection + * Offset DPCD 050Eh == 0x5A indicates cascaded MST hub case + * Check from beginning of branch device vendor specific field (050Ch) + */ +#define IS_SYNAPTICS_PANAMERA(branchDevName) (((int)branchDevName[4] & 0xF0) == 0x50 ? 1 : 0) +#define BRANCH_HW_REVISION_PANAMERA_A2 0x10 +#define SYNAPTICS_CASCADED_HUB_ID 0x5A +#define IS_SYNAPTICS_CASCADED_PANAMERA(devName, data) ((IS_SYNAPTICS_PANAMERA(devName) && ((int)data[2] == SYNAPTICS_CASCADED_HUB_ID)) ? 1 : 0) + struct amdgpu_display_manager; struct amdgpu_dm_connector; From 3eeff8d26c6dceeaf10b552e8a5ce9010d818f41 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 23 Mar 2023 13:09:16 +0100 Subject: [PATCH 2425/4345] s390/uaccess: add missing earlyclobber annotations to __clear_user() commit 89aba4c26fae4e459f755a18912845c348ee48f3 upstream. Add missing earlyclobber annotation to size, to, and tmp2 operands of the __clear_user() inline assembly since they are modified or written to before the last usage of all input operands. This can lead to incorrect register allocation for the inline assembly. Fixes: 6c2a9e6df604 ("[S390] Use alternative user-copy operations for new hardware.") Reported-by: Mark Rutland Link: https://lore.kernel.org/all/20230321122514.1743889-3-mark.rutland@arm.com/ Cc: stable@vger.kernel.org Reviewed-by: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Greg Kroah-Hartman --- arch/s390/lib/uaccess.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index 0267405ab7c6..fcfd78f99cb4 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -339,7 +339,7 @@ static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size "4: slgr %0,%0\n" "5:\n" EX_TABLE(0b,2b) EX_TABLE(3b,5b) - : "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2) + : "+&a" (size), "+&a" (to), "+a" (tmp1), "=&a" (tmp2) : "a" (empty_zero_page), "d" (reg0) : "cc", "memory"); return size; } From b51e4422952b5c98dad46caa017c233ac783679f Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Thu, 23 Mar 2023 15:56:48 +0800 Subject: [PATCH 2426/4345] btrfs: scan device in non-exclusive mode commit 50d281fc434cb8e2497f5e70a309ccca6b1a09f0 upstream. This fixes mkfs/mount/check failures due to race with systemd-udevd scan. During the device scan initiated by systemd-udevd, other user space EXCL operations such as mkfs, mount, or check may get blocked and result in a "Device or resource busy" error. This is because the device scan process opens the device with the EXCL flag in the kernel. Two reports were received: - btrfs/179 test case, where the fsck command failed with the -EBUSY error - LTP pwritev03 test case, where mkfs.vfs failed with the -EBUSY error, when mkfs.vfs tried to overwrite old btrfs filesystem on the device. In both cases, fsck and mkfs (respectively) were racing with a systemd-udevd device scan, and systemd-udevd won, resulting in the -EBUSY error for fsck and mkfs. Reproducing the problem has been difficult because there is a very small window during which these userspace threads can race to acquire the exclusive device open. Even on the system where the problem was observed, the problem occurrences were anywhere between 10 to 400 iterations and chances of reproducing decreases with debug printk()s. However, an exclusive device open is unnecessary for the scan process, as there are no write operations on the device during scan. Furthermore, during the mount process, the superblock is re-read in the below function call chain: btrfs_mount_root btrfs_open_devices open_fs_devices btrfs_open_one_device btrfs_get_bdev_and_sb So, to fix this issue, removes the FMODE_EXCL flag from the scan operation, and add a comment. The case where mkfs may still write to the device and a scan is running, the btrfs signature is not written at that time so scan will not recognize such device. Reported-by: Sherry Yang Reported-by: kernel test robot Link: https://lore.kernel.org/oe-lkp/202303170839.fdf23068-oliver.sang@intel.com CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Anand Jain Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/volumes.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 15435f983180..83dca79ff042 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1411,8 +1411,17 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, * later supers, using BTRFS_SUPER_MIRROR_MAX instead */ bytenr = btrfs_sb_offset(0); - flags |= FMODE_EXCL; + /* + * Avoid using flag |= FMODE_EXCL here, as the systemd-udev may + * initiate the device scan which may race with the user's mount + * or mkfs command, resulting in failure. + * Since the device scan is solely for reading purposes, there is + * no need for FMODE_EXCL. Additionally, the devices are read again + * during the mount process. It is ok to get some inconsistent + * values temporarily, as the device paths of the fsid are the only + * required information for assembling the volume. + */ bdev = blkdev_get_by_path(path, flags, holder); if (IS_ERR(bdev)) return ERR_CAST(bdev); From f1c17475a9dcb947dafcebc1c4940750ddf495bb Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 20 Mar 2023 22:49:15 +0900 Subject: [PATCH 2427/4345] zonefs: Fix error message in zonefs_file_dio_append() commit 88b170088ad2c3e27086fe35769aa49f8a512564 upstream. Since the expected write location in a sequential file is always at the end of the file (append write), when an invalid write append location is detected in zonefs_file_dio_append(), print the invalid written location instead of the expected write location. Fixes: a608da3bd730 ("zonefs: Detect append writes at invalid locations") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Himanshu Madhani Signed-off-by: Greg Kroah-Hartman --- fs/zonefs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 66a089a62c39..b9522eee1257 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -789,7 +789,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) if (bio->bi_iter.bi_sector != wpsector) { zonefs_warn(inode->i_sb, "Corrupted write pointer %llu for zone at %llu\n", - wpsector, zi->i_zsector); + bio->bi_iter.bi_sector, zi->i_zsector); ret = -EIO; } } From b9f7422dd94a6ec5572a3e895157ec1dad2952a7 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Sat, 1 Oct 2022 13:44:25 +0300 Subject: [PATCH 2428/4345] selftests/bpf: Test btf dump for struct with padding only fields [ Upstream commit d503f1176b14f722a40ea5110312614982f9a80b ] Structures with zero regular fields but some padding constitute a special case in btf_dump.c:btf_dump_emit_struct_def with regards to newline before closing '}'. Signed-off-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20221001104425.415768-2-eddyz87@gmail.com Stable-dep-of: ea2ce1ba99aa ("libbpf: Fix BTF-to-C converter's padding logic") Signed-off-by: Sasha Levin --- .../selftests/bpf/progs/btf_dump_test_case_padding.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c index 35c512818a56..db5458da6182 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -102,12 +102,21 @@ struct zone { struct zone_padding __pad__; }; +/* ----- START-EXPECTED-OUTPUT ----- */ +struct padding_wo_named_members { + long: 64; + long: 64; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + int f(struct { struct padded_implicitly _1; struct padded_explicitly _2; struct padded_a_lot _3; struct padded_cache_line _4; struct zone _5; + struct padding_wo_named_members _6; } *_) { return 0; From e5a16bcb131c969befc4ede5542a1c2bd3ecf11b Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 12 Dec 2022 13:15:04 -0800 Subject: [PATCH 2429/4345] libbpf: Fix BTF-to-C converter's padding logic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ea2ce1ba99aa6a60c8d8a706e3abadf3de372163 ] Turns out that btf_dump API doesn't handle a bunch of tricky corner cases, as reported by Per, and further discovered using his testing Python script ([0]). This patch revamps btf_dump's padding logic significantly, making it more correct and also avoiding unnecessary explicit padding, where compiler would pad naturally. This overall topic turned out to be very tricky and subtle, there are lots of subtle corner cases. The comments in the code tries to give some clues, but comments themselves are supposed to be paired with good understanding of C alignment and padding rules. Plus some experimentation to figure out subtle things like whether `long :0;` means that struct is now forced to be long-aligned (no, it's not, turns out). Anyways, Per's script, while not completely correct in some known situations, doesn't show any obvious cases where this logic breaks, so this is a nice improvement over the previous state of this logic. Some selftests had to be adjusted to accommodate better use of natural alignment rules, eliminating some unnecessary padding, or changing it to `type: 0;` alignment markers. Note also that for when we are in between bitfields, we emit explicit bit size, while otherwise we use `: 0`, this feels much more natural in practice. Next patch will add few more test cases, found through randomized Per's script. [0] https://lore.kernel.org/bpf/85f83c333f5355c8ac026f835b18d15060725fcb.camel@ericsson.com/ Reported-by: Per Sundström XP Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20221212211505.558851-6-andrii@kernel.org Signed-off-by: Sasha Levin --- tools/lib/bpf/btf_dump.c | 167 +++++++++++++----- .../bpf/progs/btf_dump_test_case_bitfields.c | 2 +- .../bpf/progs/btf_dump_test_case_padding.c | 58 ++++-- 3 files changed, 163 insertions(+), 64 deletions(-) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 0e2d63da24e9..4d27b08074a5 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -788,6 +788,25 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } } +static int btf_natural_align_of(const struct btf *btf, __u32 id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + int i, align, vlen; + const struct btf_member *m; + + if (!btf_is_composite(t)) + return btf__align_of(btf, id); + + align = 1; + m = btf_members(t); + vlen = btf_vlen(t); + for (i = 0; i < vlen; i++, m++) { + align = max(align, btf__align_of(btf, m->type)); + } + + return align; +} + static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_type *t) { @@ -795,16 +814,16 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, int align, i, bit_sz; __u16 vlen; - align = btf__align_of(btf, id); - /* size of a non-packed struct has to be a multiple of its alignment*/ - if (align && t->size % align) + align = btf_natural_align_of(btf, id); + /* size of a non-packed struct has to be a multiple of its alignment */ + if (align && (t->size % align) != 0) return true; m = btf_members(t); vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ for (i = 0; i < vlen; i++, m++) { - align = btf__align_of(btf, m->type); + align = btf_natural_align_of(btf, m->type); bit_sz = btf_member_bitfield_size(t, i); if (align && bit_sz == 0 && m->offset % (8 * align) != 0) return true; @@ -817,44 +836,97 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, return false; } -static int chip_away_bits(int total, int at_most) -{ - return total % at_most ? : at_most; -} - static void btf_dump_emit_bit_padding(const struct btf_dump *d, - int cur_off, int m_off, int m_bit_sz, - int align, int lvl) + int cur_off, int next_off, int next_align, + bool in_bitfield, int lvl) { - int off_diff = m_off - cur_off; - int ptr_bits = d->ptr_sz * 8; + const struct { + const char *name; + int bits; + } pads[] = { + {"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8} + }; + int new_off, pad_bits, bits, i; + const char *pad_type; - if (off_diff <= 0) - /* no gap */ - return; - if (m_bit_sz == 0 && off_diff < align * 8) - /* natural padding will take care of a gap */ - return; + if (cur_off >= next_off) + return; /* no gap */ - while (off_diff > 0) { - const char *pad_type; - int pad_bits; + /* For filling out padding we want to take advantage of + * natural alignment rules to minimize unnecessary explicit + * padding. First, we find the largest type (among long, int, + * short, or char) that can be used to force naturally aligned + * boundary. Once determined, we'll use such type to fill in + * the remaining padding gap. In some cases we can rely on + * compiler filling some gaps, but sometimes we need to force + * alignment to close natural alignment with markers like + * `long: 0` (this is always the case for bitfields). Note + * that even if struct itself has, let's say 4-byte alignment + * (i.e., it only uses up to int-aligned types), using `long: + * X;` explicit padding doesn't actually change struct's + * overall alignment requirements, but compiler does take into + * account that type's (long, in this example) natural + * alignment requirements when adding implicit padding. We use + * this fact heavily and don't worry about ruining correct + * struct alignment requirement. + */ + for (i = 0; i < ARRAY_SIZE(pads); i++) { + pad_bits = pads[i].bits; + pad_type = pads[i].name; - if (ptr_bits > 32 && off_diff > 32) { - pad_type = "long"; - pad_bits = chip_away_bits(off_diff, ptr_bits); - } else if (off_diff > 16) { - pad_type = "int"; - pad_bits = chip_away_bits(off_diff, 32); - } else if (off_diff > 8) { - pad_type = "short"; - pad_bits = chip_away_bits(off_diff, 16); - } else { - pad_type = "char"; - pad_bits = chip_away_bits(off_diff, 8); + new_off = roundup(cur_off, pad_bits); + if (new_off <= next_off) + break; + } + + if (new_off > cur_off && new_off <= next_off) { + /* We need explicit `: 0` aligning mark if next + * field is right on alignment offset and its + * alignment requirement is less strict than 's + * alignment (so compiler won't naturally align to the + * offset we expect), or if subsequent `: X`, + * will actually completely fit in the remaining hole, + * making compiler basically ignore `: X` + * completely. + */ + if (in_bitfield || + (new_off == next_off && roundup(cur_off, next_align * 8) != new_off) || + (new_off != next_off && next_off - new_off <= new_off - cur_off)) + /* but for bitfields we'll emit explicit bit count */ + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, + in_bitfield ? new_off - cur_off : 0); + cur_off = new_off; + } + + /* Now we know we start at naturally aligned offset for a chosen + * padding type (long, int, short, or char), and so the rest is just + * a straightforward filling of remaining padding gap with full + * `: sizeof();` markers, except for the last one, which + * might need smaller than sizeof() padding. + */ + while (cur_off != next_off) { + bits = min(next_off - cur_off, pad_bits); + if (bits == pad_bits) { + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits); + cur_off += bits; + continue; + } + /* For the remainder padding that doesn't cover entire + * pad_type bit length, we pick the smallest necessary type. + * This is pure aesthetics, we could have just used `long`, + * but having smallest necessary one communicates better the + * scale of the padding gap. + */ + for (i = ARRAY_SIZE(pads) - 1; i >= 0; i--) { + pad_type = pads[i].name; + pad_bits = pads[i].bits; + if (pad_bits < bits) + continue; + + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, bits); + cur_off += bits; + break; } - btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits); - off_diff -= pad_bits; } } @@ -873,9 +945,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, { const struct btf_member *m = btf_members(t); bool is_struct = btf_is_struct(t); - int align, i, packed, off = 0; + bool packed, prev_bitfield = false; + int align, i, off = 0; __u16 vlen = btf_vlen(t); + align = btf__align_of(d->btf, id); packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; btf_dump_printf(d, "%s%s%s {", @@ -885,33 +959,36 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, for (i = 0; i < vlen; i++, m++) { const char *fname; - int m_off, m_sz; + int m_off, m_sz, m_align; + bool in_bitfield; fname = btf_name_of(d, m->name_off); m_sz = btf_member_bitfield_size(t, i); m_off = btf_member_bit_offset(t, i); - align = packed ? 1 : btf__align_of(d->btf, m->type); + m_align = packed ? 1 : btf__align_of(d->btf, m->type); - btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); + in_bitfield = prev_bitfield && m_sz != 0; + + btf_dump_emit_bit_padding(d, off, m_off, m_align, in_bitfield, lvl + 1); btf_dump_printf(d, "\n%s", pfx(lvl + 1)); btf_dump_emit_type_decl(d, m->type, fname, lvl + 1); if (m_sz) { btf_dump_printf(d, ": %d", m_sz); off = m_off + m_sz; + prev_bitfield = true; } else { m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type)); off = m_off + m_sz * 8; + prev_bitfield = false; } + btf_dump_printf(d, ";"); } /* pad at the end, if necessary */ - if (is_struct) { - align = packed ? 1 : btf__align_of(d->btf, id); - btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align, - lvl + 1); - } + if (is_struct) + btf_dump_emit_bit_padding(d, off, t->size * 8, align, false, lvl + 1); if (vlen) btf_dump_printf(d, "\n"); diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c index 8f44767a75fa..22a7cd8fd9ac 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c @@ -53,7 +53,7 @@ struct bitfields_only_mixed_types { */ /* ------ END-EXPECTED-OUTPUT ------ */ struct bitfield_mixed_with_others { - long: 4; /* char is enough as a backing field */ + char: 4; /* char is enough as a backing field */ int a: 4; /* 8-bit implicit padding */ short b; /* combined with previous bitfield */ diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c index db5458da6182..28833f2694e9 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -19,7 +19,7 @@ struct padded_implicitly { /* *struct padded_explicitly { * int a; - * int: 32; + * long: 0; * int b; *}; * @@ -28,41 +28,28 @@ struct padded_implicitly { struct padded_explicitly { int a; - int: 1; /* algo will explicitly pad with full 32 bits here */ + int: 1; /* algo will emit aligning `long: 0;` here */ int b; }; /* ----- START-EXPECTED-OUTPUT ----- */ -/* - *struct padded_a_lot { - * int a; - * long: 32; - * long: 64; - * long: 64; - * int b; - *}; - * - */ -/* ------ END-EXPECTED-OUTPUT ------ */ - struct padded_a_lot { int a; - /* 32 bit of implicit padding here, which algo will make explicit */ long: 64; long: 64; int b; }; +/* ------ END-EXPECTED-OUTPUT ------ */ + /* ----- START-EXPECTED-OUTPUT ----- */ /* *struct padded_cache_line { * int a; - * long: 32; * long: 64; * long: 64; * long: 64; * int b; - * long: 32; * long: 64; * long: 64; * long: 64; @@ -85,7 +72,7 @@ struct padded_cache_line { *struct zone { * int a; * short b; - * short: 16; + * long: 0; * struct zone_padding __pad__; *}; * @@ -108,6 +95,39 @@ struct padding_wo_named_members { long: 64; }; +struct padding_weird_1 { + int a; + long: 64; + short: 16; + short b; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct padding_weird_2 { + * long: 56; + * char a; + * long: 56; + * char b; + * char: 8; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ +struct padding_weird_2 { + int: 32; /* these paddings will be collapsed into `long: 56;` */ + short: 16; + char: 8; + char a; + int: 32; /* these paddings will be collapsed into `long: 56;` */ + short: 16; + char: 8; + char b; + char: 8; +}; + /* ------ END-EXPECTED-OUTPUT ------ */ int f(struct { @@ -117,6 +137,8 @@ int f(struct { struct padded_cache_line _4; struct zone _5; struct padding_wo_named_members _6; + struct padding_weird_1 _7; + struct padding_weird_2 _8; } *_) { return 0; From 7ad30ad8c684362364e629574ab02eec3b9bb1bc Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 12 Dec 2022 13:15:05 -0800 Subject: [PATCH 2430/4345] selftests/bpf: Add few corner cases to test padding handling of btf_dump [ Upstream commit b148c8b9b926e257a59c8eb2cd6fa3adfd443254 ] Add few hand-crafted cases and few randomized cases found using script from [0] that tests btf_dump's padding logic. [0] https://lore.kernel.org/bpf/85f83c333f5355c8ac026f835b18d15060725fcb.camel@ericsson.com/ Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20221212211505.558851-7-andrii@kernel.org Stable-dep-of: 4fb877aaa179 ("libbpf: Fix btf_dump's packed struct determination") Signed-off-by: Sasha Levin --- .../bpf/progs/btf_dump_test_case_packing.c | 61 +++++++++- .../bpf/progs/btf_dump_test_case_padding.c | 104 ++++++++++++++++++ 2 files changed, 164 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c index 1cef3bec1dc7..3f7755247591 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c @@ -58,7 +58,64 @@ union jump_code_union { } __attribute__((packed)); }; -/*------ END-EXPECTED-OUTPUT ------ */ +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct nested_packed_but_aligned_struct { + * int x1; + * int x2; + *}; + * + *struct outer_implicitly_packed_struct { + * char y1; + * struct nested_packed_but_aligned_struct y2; + *} __attribute__((packed)); + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct nested_packed_but_aligned_struct { + int x1; + int x2; +} __attribute__((packed)); + +struct outer_implicitly_packed_struct { + char y1; + struct nested_packed_but_aligned_struct y2; +}; +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct usb_ss_ep_comp_descriptor { + * char: 8; + * char bDescriptorType; + * char bMaxBurst; + * short wBytesPerInterval; + *}; + * + *struct usb_host_endpoint { + * long: 64; + * char: 8; + * struct usb_ss_ep_comp_descriptor ss_ep_comp; + * long: 0; + *} __attribute__((packed)); + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct usb_ss_ep_comp_descriptor { + char: 8; + char bDescriptorType; + char bMaxBurst; + int: 0; + short wBytesPerInterval; +} __attribute__((packed)); + +struct usb_host_endpoint { + long: 64; + char: 8; + struct usb_ss_ep_comp_descriptor ss_ep_comp; + long: 0; +}; + int f(struct { struct packed_trailing_space _1; @@ -69,6 +126,8 @@ int f(struct { union union_is_never_packed _6; union union_does_not_need_packing _7; union jump_code_union _8; + struct outer_implicitly_packed_struct _9; + struct usb_host_endpoint _10; } *_) { return 0; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c index 28833f2694e9..0b3cdffbfcf7 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -128,6 +128,98 @@ struct padding_weird_2 { char: 8; }; +/* ----- START-EXPECTED-OUTPUT ----- */ +struct exact_1byte { + char x; +}; + +struct padded_1byte { + char: 8; +}; + +struct exact_2bytes { + short x; +}; + +struct padded_2bytes { + short: 16; +}; + +struct exact_4bytes { + int x; +}; + +struct padded_4bytes { + int: 32; +}; + +struct exact_8bytes { + long x; +}; + +struct padded_8bytes { + long: 64; +}; + +struct ff_periodic_effect { + int: 32; + short magnitude; + long: 0; + short phase; + long: 0; + int: 32; + int custom_len; + short *custom_data; +}; + +struct ib_wc { + long: 64; + long: 64; + int: 32; + int byte_len; + void *qp; + union {} ex; + long: 64; + int slid; + int wc_flags; + long: 64; + char smac[6]; + long: 0; + char network_hdr_type; +}; + +struct acpi_object_method { + long: 64; + char: 8; + char type; + short reference_count; + char flags; + short: 0; + char: 8; + char sync_level; + long: 64; + void *node; + void *aml_start; + union {} dispatch; + long: 64; + int aml_length; +}; + +struct nested_unpacked { + int x; +}; + +struct nested_packed { + struct nested_unpacked a; + char c; +} __attribute__((packed)); + +struct outer_mixed_but_unpacked { + struct nested_packed b1; + short a1; + struct nested_packed b2; +}; + /* ------ END-EXPECTED-OUTPUT ------ */ int f(struct { @@ -139,6 +231,18 @@ int f(struct { struct padding_wo_named_members _6; struct padding_weird_1 _7; struct padding_weird_2 _8; + struct exact_1byte _100; + struct padded_1byte _101; + struct exact_2bytes _102; + struct padded_2bytes _103; + struct exact_4bytes _104; + struct padded_4bytes _105; + struct exact_8bytes _106; + struct padded_8bytes _107; + struct ff_periodic_effect _200; + struct ib_wc _201; + struct acpi_object_method _202; + struct outer_mixed_but_unpacked _203; } *_) { return 0; From b4781477f397a9e10f36d035ffc76bfb67aa1639 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 15 Dec 2022 10:36:05 -0800 Subject: [PATCH 2431/4345] libbpf: Fix btf_dump's packed struct determination [ Upstream commit 4fb877aaa179dcdb1676d55216482febaada457e ] Fix bug in btf_dump's logic of determining if a given struct type is packed or not. The notion of "natural alignment" is not needed and is even harmful in this case, so drop it altogether. The biggest difference in btf_is_struct_packed() compared to its original implementation is that we don't really use btf__align_of() to determine overall alignment of a struct type (because it could be 1 for both packed and non-packed struct, depending on specifci field definitions), and just use field's actual alignment to calculate whether any field is requiring packing or struct's size overall necessitates packing. Add two simple test cases that demonstrate the difference this change would make. Fixes: ea2ce1ba99aa ("libbpf: Fix BTF-to-C converter's padding logic") Reported-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20221215183605.4149488-1-andrii@kernel.org Signed-off-by: Sasha Levin --- tools/lib/bpf/btf_dump.c | 33 ++++--------------- .../bpf/progs/btf_dump_test_case_packing.c | 19 +++++++++++ 2 files changed, 25 insertions(+), 27 deletions(-) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 4d27b08074a5..558d34fbd331 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -788,47 +788,26 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } } -static int btf_natural_align_of(const struct btf *btf, __u32 id) -{ - const struct btf_type *t = btf__type_by_id(btf, id); - int i, align, vlen; - const struct btf_member *m; - - if (!btf_is_composite(t)) - return btf__align_of(btf, id); - - align = 1; - m = btf_members(t); - vlen = btf_vlen(t); - for (i = 0; i < vlen; i++, m++) { - align = max(align, btf__align_of(btf, m->type)); - } - - return align; -} - static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_type *t) { const struct btf_member *m; - int align, i, bit_sz; + int max_align = 1, align, i, bit_sz; __u16 vlen; - align = btf_natural_align_of(btf, id); - /* size of a non-packed struct has to be a multiple of its alignment */ - if (align && (t->size % align) != 0) - return true; - m = btf_members(t); vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ for (i = 0; i < vlen; i++, m++) { - align = btf_natural_align_of(btf, m->type); + align = btf__align_of(btf, m->type); bit_sz = btf_member_bitfield_size(t, i); if (align && bit_sz == 0 && m->offset % (8 * align) != 0) return true; + max_align = max(align, max_align); } - + /* size of a non-packed struct has to be a multiple of its alignment */ + if (t->size % max_align != 0) + return true; /* * if original struct was marked as packed, but its layout is * naturally aligned, we'll detect that it's not packed diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c index 3f7755247591..22dbd1213434 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c @@ -116,6 +116,23 @@ struct usb_host_endpoint { long: 0; }; +/* ----- START-EXPECTED-OUTPUT ----- */ +struct nested_packed_struct { + int a; + char b; +} __attribute__((packed)); + +struct outer_nonpacked_struct { + short a; + struct nested_packed_struct b; +}; + +struct outer_packed_struct { + short a; + struct nested_packed_struct b; +} __attribute__((packed)); + +/* ------ END-EXPECTED-OUTPUT ------ */ int f(struct { struct packed_trailing_space _1; @@ -128,6 +145,8 @@ int f(struct { union jump_code_union _8; struct outer_implicitly_packed_struct _9; struct usb_host_endpoint _10; + struct outer_nonpacked_struct _11; + struct outer_packed_struct _12; } *_) { return 0; From 3392d67af0a4bf13e7f6ef0cddfc622bc2e8c95e Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Tue, 6 Dec 2022 22:41:34 +0800 Subject: [PATCH 2432/4345] ext4: fix kernel BUG in 'ext4_write_inline_data_end()' commit 5c099c4fdc438014d5893629e70a8ba934433ee8 upstream. Syzbot report follow issue: ------------[ cut here ]------------ kernel BUG at fs/ext4/inline.c:227! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 3629 Comm: syz-executor212 Not tainted 6.1.0-rc5-syzkaller-00018-g59d0d52c30d4 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 RIP: 0010:ext4_write_inline_data+0x344/0x3e0 fs/ext4/inline.c:227 RSP: 0018:ffffc90003b3f368 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8880704e16c0 RCX: 0000000000000000 RDX: ffff888021763a80 RSI: ffffffff821e31a4 RDI: 0000000000000006 RBP: 000000000006818e R08: 0000000000000006 R09: 0000000000068199 R10: 0000000000000079 R11: 0000000000000000 R12: 000000000000000b R13: 0000000000068199 R14: ffffc90003b3f408 R15: ffff8880704e1c82 FS: 000055555723e3c0(0000) GS:ffff8880b9b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fffe8ac9080 CR3: 0000000079f81000 CR4: 0000000000350ee0 Call Trace: ext4_write_inline_data_end+0x2a3/0x12f0 fs/ext4/inline.c:768 ext4_write_end+0x242/0xdd0 fs/ext4/inode.c:1313 ext4_da_write_end+0x3ed/0xa30 fs/ext4/inode.c:3063 generic_perform_write+0x316/0x570 mm/filemap.c:3764 ext4_buffered_write_iter+0x15b/0x460 fs/ext4/file.c:285 ext4_file_write_iter+0x8bc/0x16e0 fs/ext4/file.c:700 call_write_iter include/linux/fs.h:2191 [inline] do_iter_readv_writev+0x20b/0x3b0 fs/read_write.c:735 do_iter_write+0x182/0x700 fs/read_write.c:861 vfs_iter_write+0x74/0xa0 fs/read_write.c:902 iter_file_splice_write+0x745/0xc90 fs/splice.c:686 do_splice_from fs/splice.c:764 [inline] direct_splice_actor+0x114/0x180 fs/splice.c:931 splice_direct_to_actor+0x335/0x8a0 fs/splice.c:886 do_splice_direct+0x1ab/0x280 fs/splice.c:974 do_sendfile+0xb19/0x1270 fs/read_write.c:1255 __do_sys_sendfile64 fs/read_write.c:1323 [inline] __se_sys_sendfile64 fs/read_write.c:1309 [inline] __x64_sys_sendfile64+0x1d0/0x210 fs/read_write.c:1309 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd ---[ end trace 0000000000000000 ]--- Above issue may happens as follows: ext4_da_write_begin ext4_da_write_inline_data_begin ext4_da_convert_inline_data_to_extent ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); ext4_da_write_end ext4_run_li_request ext4_mb_prefetch ext4_read_block_bitmap_nowait ext4_validate_block_bitmap ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT) percpu_counter_sub(&sbi->s_freeclusters_counter,grp->bb_free); -> sbi->s_freeclusters_counter become zero ext4_da_write_begin if (ext4_nonda_switch(inode->i_sb)) -> As freeclusters_counter is zero will return true *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; ext4_write_begin ext4_da_write_end if (write_mode == FALL_BACK_TO_NONDELALLOC) ext4_write_end if (inline_data) ext4_write_inline_data_end ext4_write_inline_data BUG_ON(pos + len > EXT4_I(inode)->i_inline_size); -> As inode is already convert to extent, so 'pos + len' > inline_size -> then trigger BUG. To solve this issue, instead of checking ext4_has_inline_data() which is only cleared after data has been written back, check the EXT4_STATE_MAY_INLINE_DATA flag in ext4_write_end(). Fixes: f19d5870cbf7 ("ext4: add normal write support for inline data") Reported-by: syzbot+4faa160fa96bfba639f8@syzkaller.appspotmail.com Reported-by: Jun Nie Signed-off-by: Ye Bin Link: https://lore.kernel.org/r/20221206144134.1919987-1-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org [ta: Fix conflict in if expression and use the local variable inline_data as it is initialized with ext4_has_inline_data(inode) anyway.] Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6ba185b46ba3..9bd5f8b0511b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1303,7 +1303,8 @@ static int ext4_write_end(struct file *file, bool verity = ext4_verity_in_progress(inode); trace_ext4_write_end(inode, pos, len, copied); - if (inline_data) { + if (inline_data && + ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { From 7c414f6f06e9a3934901b6edc3177ae5a1e07094 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sun, 4 Dec 2022 17:00:04 +0100 Subject: [PATCH 2433/4345] gfs2: Always check inode size of inline inodes commit 70376c7ff31221f1d21db5611d8209e677781d3a upstream. Check if the inode size of stuffed (inline) inodes is within the allowed range when reading inodes from disk (gfs2_dinode_in()). This prevents us from on-disk corruption. The two checks in stuffed_readpage() and gfs2_unstuffer_page() that just truncate inline data to the maximum allowed size don't actually make sense, and they can be removed now as well. Reported-by: syzbot+7bb81dfa9cda07d9cd9d@syzkaller.appspotmail.com Signed-off-by: Andreas Gruenbacher [pchelkin@ispras.ru: adjust the inode variable inside gfs2_dinode_in with the format used before upstream commit 7db354444ad8 ("gfs2: Cosmetic gfs2_dinode_{in,out} cleanup")] Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- fs/gfs2/aops.c | 2 -- fs/gfs2/bmap.c | 3 --- fs/gfs2/glops.c | 3 +++ 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 530659554870..a0430da033b3 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -451,8 +451,6 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) return error; kaddr = kmap_atomic(page); - if (dsize > gfs2_max_stuffed_size(ip)) - dsize = gfs2_max_stuffed_size(ip); memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); memset(kaddr + dsize, 0, PAGE_SIZE - dsize); kunmap_atomic(kaddr); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index b4fde3a8eeb4..eaee95d2ad14 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -69,9 +69,6 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, void *kaddr = kmap(page); u64 dsize = i_size_read(inode); - if (dsize > gfs2_max_stuffed_size(ip)) - dsize = gfs2_max_stuffed_size(ip); - memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); memset(kaddr + dsize, 0, PAGE_SIZE - dsize); kunmap(page); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index bf539eab92c6..db28c240dae3 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -454,6 +454,9 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) ip->i_depth = (u8)depth; ip->i_entries = be32_to_cpu(str->di_entries); + if (gfs2_is_stuffed(ip) && ip->i_inode.i_size > gfs2_max_stuffed_size(ip)) + goto corrupt; + if (S_ISREG(ip->i_inode.i_mode)) gfs2_set_aops(&ip->i_inode); From 34a02011c5d1b9de0085e6e004f20abf0a9cbf42 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Wed, 15 Mar 2023 21:25:17 +0100 Subject: [PATCH 2434/4345] hsr: ratelimit only when errors are printed commit 1b0120e4db0bf2838d1ce741195ce4b7cc100b91 upstream. Recently, when automatically merging -net and net-next in MPTCP devel tree, our CI reported [1] a conflict in hsr, the same as the one reported by Stephen in netdev [2]. When looking at the conflict, I noticed it is in fact the v1 [3] that has been applied in -net and the v2 [4] in net-next. Maybe the v1 was applied by accident. As mentioned by Jakub Kicinski [5], the new condition makes more sense before the net_ratelimit(), not to update net_ratelimit's state which is unnecessary if we're not going to print either way. Here, this modification applies the v2 but in -net. Link: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/4423171069 [1] Link: https://lore.kernel.org/netdev/20230315100914.53fc1760@canb.auug.org.au/ [2] Link: https://lore.kernel.org/netdev/20230307133229.127442-1-koverskeid@gmail.com/ [3] Link: https://lore.kernel.org/netdev/20230309092302.179586-1-koverskeid@gmail.com/ [4] Link: https://lore.kernel.org/netdev/20230308232001.2fb62013@kernel.org/ [5] Fixes: 28e8cabe80f3 ("net: hsr: Don't log netdev_err message on unknown prp dst node") Signed-off-by: Matthieu Baerts Reviewed-by: Steen Hegelund Link: https://lore.kernel.org/r/20230315-net-20230315-hsr_framereg-ratelimit-v1-1-61d2ef176d11@tessares.net Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/hsr/hsr_framereg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 08627c836884..afc97d65cf2d 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -380,7 +380,7 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); if (!node_dst) { - if (net_ratelimit() && port->hsr->prot_version != PRP_V1) + if (port->hsr->prot_version != PRP_V1 && net_ratelimit()) netdev_err(skb->dev, "%s: Unknown node\n", __func__); return; } From 387078f9030cf336cd9fef521540db75b61615e0 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 5 Apr 2023 11:23:52 +0200 Subject: [PATCH 2435/4345] Linux 5.10.177 Link: https://lore.kernel.org/r/20230403140414.174516815@linuxfoundation.org Tested-by: Shuah Khan Tested-by: Florian Fainelli Tested-by: Linux Kernel Functional Testing Tested-by: Jon Hunter Tested-by: Chris Paterson (CIP) Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 71caf5938361..ae202cc53158 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 176 +SUBLEVEL = 177 EXTRAVERSION = NAME = Dare mighty things From d55931c1cccc790de1b688afbee837019dd9065b Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Tue, 6 Dec 2022 22:41:34 +0800 Subject: [PATCH 2436/4345] UPSTREAM: ext4: fix kernel BUG in 'ext4_write_inline_data_end()' commit 5c099c4fdc438014d5893629e70a8ba934433ee8 upstream. Syzbot report follow issue: ------------[ cut here ]------------ kernel BUG at fs/ext4/inline.c:227! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 3629 Comm: syz-executor212 Not tainted 6.1.0-rc5-syzkaller-00018-g59d0d52c30d4 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 RIP: 0010:ext4_write_inline_data+0x344/0x3e0 fs/ext4/inline.c:227 RSP: 0018:ffffc90003b3f368 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8880704e16c0 RCX: 0000000000000000 RDX: ffff888021763a80 RSI: ffffffff821e31a4 RDI: 0000000000000006 RBP: 000000000006818e R08: 0000000000000006 R09: 0000000000068199 R10: 0000000000000079 R11: 0000000000000000 R12: 000000000000000b R13: 0000000000068199 R14: ffffc90003b3f408 R15: ffff8880704e1c82 FS: 000055555723e3c0(0000) GS:ffff8880b9b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fffe8ac9080 CR3: 0000000079f81000 CR4: 0000000000350ee0 Call Trace: ext4_write_inline_data_end+0x2a3/0x12f0 fs/ext4/inline.c:768 ext4_write_end+0x242/0xdd0 fs/ext4/inode.c:1313 ext4_da_write_end+0x3ed/0xa30 fs/ext4/inode.c:3063 generic_perform_write+0x316/0x570 mm/filemap.c:3764 ext4_buffered_write_iter+0x15b/0x460 fs/ext4/file.c:285 ext4_file_write_iter+0x8bc/0x16e0 fs/ext4/file.c:700 call_write_iter include/linux/fs.h:2191 [inline] do_iter_readv_writev+0x20b/0x3b0 fs/read_write.c:735 do_iter_write+0x182/0x700 fs/read_write.c:861 vfs_iter_write+0x74/0xa0 fs/read_write.c:902 iter_file_splice_write+0x745/0xc90 fs/splice.c:686 do_splice_from fs/splice.c:764 [inline] direct_splice_actor+0x114/0x180 fs/splice.c:931 splice_direct_to_actor+0x335/0x8a0 fs/splice.c:886 do_splice_direct+0x1ab/0x280 fs/splice.c:974 do_sendfile+0xb19/0x1270 fs/read_write.c:1255 __do_sys_sendfile64 fs/read_write.c:1323 [inline] __se_sys_sendfile64 fs/read_write.c:1309 [inline] __x64_sys_sendfile64+0x1d0/0x210 fs/read_write.c:1309 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd ---[ end trace 0000000000000000 ]--- Above issue may happens as follows: ext4_da_write_begin ext4_da_write_inline_data_begin ext4_da_convert_inline_data_to_extent ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); ext4_da_write_end ext4_run_li_request ext4_mb_prefetch ext4_read_block_bitmap_nowait ext4_validate_block_bitmap ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT) percpu_counter_sub(&sbi->s_freeclusters_counter,grp->bb_free); -> sbi->s_freeclusters_counter become zero ext4_da_write_begin if (ext4_nonda_switch(inode->i_sb)) -> As freeclusters_counter is zero will return true *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; ext4_write_begin ext4_da_write_end if (write_mode == FALL_BACK_TO_NONDELALLOC) ext4_write_end if (inline_data) ext4_write_inline_data_end ext4_write_inline_data BUG_ON(pos + len > EXT4_I(inode)->i_inline_size); -> As inode is already convert to extent, so 'pos + len' > inline_size -> then trigger BUG. To solve this issue, instead of checking ext4_has_inline_data() which is only cleared after data has been written back, check the EXT4_STATE_MAY_INLINE_DATA flag in ext4_write_end(). Fixes: f19d5870cbf7 ("ext4: add normal write support for inline data") Reported-by: syzbot+4faa160fa96bfba639f8@syzkaller.appspotmail.com Reported-by: Jun Nie Signed-off-by: Ye Bin Link: https://lore.kernel.org/r/20221206144134.1919987-1-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org [ta: Fix conflict in if expression and use the local variable inline_data as it is initialized with ext4_has_inline_data(inode) anyway.] Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman Bug: 257756238 Change-Id: Ifc77db2f12db2270a2f7100e548e113dee3ee492 Signed-off-by: Tudor Ambarus --- fs/ext4/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 961c75280eb4..b5b763c30268 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1315,7 +1315,8 @@ static int ext4_write_end(struct file *file, trace_android_fs_datawrite_end(inode, pos, len); trace_ext4_write_end(inode, pos, len, copied); - if (inline_data) { + if (inline_data && + ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { From 61344663df420c35b7d70ac37c28880ffea72f51 Mon Sep 17 00:00:00 2001 From: Peifeng Li Date: Tue, 11 Apr 2023 14:59:40 +0800 Subject: [PATCH 2437/4345] ANDROID: clear memory trylock-bit when page_locked. Clearing trylock-bit of page shrinked by shrnk_page_list in advance which avoids page in other scene with the trylock-bit. The page with trylock-bit will be added ret_pages and handled in trace_android_vh_handle_failed_page_trylock. In the progress[unlock_page, handled], the page carried with trylock-bit will cause some error-issues in other scene, so clear trylock-bit here. trace_android_vh_page_trylock_get_result will clear trylock-bit and return if page tyrlock failed in reclaim-process. Here we just want to clear trylock-bit so that ignore page_trylock_result. Fixes: 309a6bf81a20 ("ANDROID: vendor_hook: Add hook to not be stuck ro rmap lock in kswapd or direct_reclaim") Bug: 240003372 Signed-off-by: Peifeng Li Change-Id: Ifecd308573ef37a51e33856a0b3bb93cd67289ac --- mm/vmscan.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/mm/vmscan.c b/mm/vmscan.c index 4a11800e1b8f..f94f52e98868 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1128,6 +1128,7 @@ static unsigned int shrink_page_list(struct list_head *page_list, LIST_HEAD(free_pages); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; + bool page_trylock_result; memset(stat, 0, sizeof(*stat)); cond_resched(); @@ -1527,6 +1528,18 @@ activate_locked: count_memcg_page_event(page, PGACTIVATE); } keep_locked: + /* + * The page with trylock-bit will be added ret_pages and + * handled in trace_android_vh_handle_failed_page_trylock. + * In the progress[unlock_page, handled], the page carried + * with trylock-bit will cause some error-issues in other + * scene, so clear trylock-bit here. + * trace_android_vh_page_trylock_get_result will clear + * trylock-bit and return if page tyrlock failed in + * reclaim-process. Here we just want to clear trylock-bit + * so that ignore page_trylock_result. + */ + trace_android_vh_page_trylock_get_result(page, &page_trylock_result); unlock_page(page); keep: list_add(&page->lru, &ret_pages); From 3fafe0740e17185f477a3332bba443f51f15a7e7 Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Tue, 7 Sep 2021 19:40:06 -0400 Subject: [PATCH 2438/4345] BACKPORT: drm/amd/display: Pass display_pipe_params_st as const in DML MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [Why] This neither needs to be on the stack nor passed by value to each function call. In fact, when building with clang it seems to break the Linux's default 1024 byte stack frame limit. [How] We can simply pass this as a const pointer. This patch fixes these Coverity IDs Addresses-Coverity-ID: 1424031: ("Big parameter passed by value") Addresses-Coverity-ID: 1423970: ("Big parameter passed by value") Addresses-Coverity-ID: 1423941: ("Big parameter passed by value") Addresses-Coverity-ID: 1451742: ("Big parameter passed by value") Addresses-Coverity-ID: 1451887: ("Big parameter passed by value") Addresses-Coverity-ID: 1454146: ("Big parameter passed by value") Addresses-Coverity-ID: 1454152: ("Big parameter passed by value") Addresses-Coverity-ID: 1454413: ("Big parameter passed by value") Addresses-Coverity-ID: 1466144: ("Big parameter passed by value") Addresses-Coverity-ID: 1487237: ("Big parameter passed by value") Bug: 254441685 Signed-off-by: Harry Wentland Fixes: 3fe617ccafd6 ("Enable '-Werror' by default for all kernel builds") Cc: Nick Desaulniers Cc: Linus Torvalds Cc: amd-gfx@lists.freedesktop.org Cc: Linux Kernel Mailing List Cc: Arnd Bergmann Cc: Leo Li Cc: Alex Deucher Cc: Christian König Cc: Xinhui Pan Cc: Nathan Chancellor Cc: Guenter Roeck Cc: llvm@lists.linux.dev Acked-by: Christian König Build-tested-by: Nathan Chancellor Reviewed-by: Leo Li Signed-off-by: Alex Deucher (cherry picked from commit 22667e6ec6b2ce9ca706e9061660b059725d009c) Signed-off-by: Lee Jones Change-Id: Ie9846bf0e5dd330cafa811afbb896f0bdb70c85d --- .../drm/amd/display/dc/dcn20/dcn20_resource.c | 2 +- .../dc/dml/dcn20/display_rq_dlg_calc_20.c | 6 +- .../dc/dml/dcn20/display_rq_dlg_calc_20.h | 4 +- .../dc/dml/dcn20/display_rq_dlg_calc_20v2.c | 6 +- .../dc/dml/dcn20/display_rq_dlg_calc_20v2.h | 4 +- .../dc/dml/dcn21/display_rq_dlg_calc_21.c | 62 ++++++++-------- .../dc/dml/dcn21/display_rq_dlg_calc_21.h | 4 +- .../dc/dml/dcn30/display_rq_dlg_calc_30.c | 72 +++++++++---------- .../dc/dml/dcn30/display_rq_dlg_calc_30.h | 4 +- .../drm/amd/display/dc/dml/display_mode_lib.h | 4 +- 10 files changed, 84 insertions(+), 84 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 53ac82693532..3346074047f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3130,7 +3130,7 @@ void dcn20_calculate_dlg_params( context->bw_ctx.dml.funcs.rq_dlg_get_rq_reg(&context->bw_ctx.dml, &context->res_ctx.pipe_ctx[i].rq_regs, - pipes[pipe_idx].pipe); + &pipes[pipe_idx].pipe); pipe_idx++; } } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c index 799bae229e67..ed1625d331ae 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c @@ -768,12 +768,12 @@ static void dml20_rq_dlg_get_rq_params(struct display_mode_lib *mode_lib, void dml20_rq_dlg_get_rq_reg(struct display_mode_lib *mode_lib, display_rq_regs_st *rq_regs, - const display_pipe_params_st pipe_param) + const display_pipe_params_st *pipe_param) { display_rq_params_st rq_param = {0}; memset(rq_regs, 0, sizeof(*rq_regs)); - dml20_rq_dlg_get_rq_params(mode_lib, &rq_param, pipe_param.src); + dml20_rq_dlg_get_rq_params(mode_lib, &rq_param, pipe_param->src); extract_rq_regs(mode_lib, rq_regs, rq_param); print__rq_regs_st(mode_lib, *rq_regs); @@ -1549,7 +1549,7 @@ static void dml20_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib, void dml20_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib, display_dlg_regs_st *dlg_regs, display_ttu_regs_st *ttu_regs, - display_e2e_pipe_params_st *e2e_pipe_param, + const display_e2e_pipe_params_st *e2e_pipe_param, const unsigned int num_pipes, const unsigned int pipe_idx, const bool cstate_en, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h index d0b90947f540..8b23867e97c1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h @@ -43,7 +43,7 @@ struct display_mode_lib; void dml20_rq_dlg_get_rq_reg( struct display_mode_lib *mode_lib, display_rq_regs_st *rq_regs, - const display_pipe_params_st pipe_param); + const display_pipe_params_st *pipe_param); // Function: dml_rq_dlg_get_dlg_reg @@ -61,7 +61,7 @@ void dml20_rq_dlg_get_dlg_reg( struct display_mode_lib *mode_lib, display_dlg_regs_st *dlg_regs, display_ttu_regs_st *ttu_regs, - display_e2e_pipe_params_st *e2e_pipe_param, + const display_e2e_pipe_params_st *e2e_pipe_param, const unsigned int num_pipes, const unsigned int pipe_idx, const bool cstate_en, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c index 6a6d5970d1d5..b1208088a1df 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c @@ -768,12 +768,12 @@ static void dml20v2_rq_dlg_get_rq_params(struct display_mode_lib *mode_lib, void dml20v2_rq_dlg_get_rq_reg(struct display_mode_lib *mode_lib, display_rq_regs_st *rq_regs, - const display_pipe_params_st pipe_param) + const display_pipe_params_st *pipe_param) { display_rq_params_st rq_param = {0}; memset(rq_regs, 0, sizeof(*rq_regs)); - dml20v2_rq_dlg_get_rq_params(mode_lib, &rq_param, pipe_param.src); + dml20v2_rq_dlg_get_rq_params(mode_lib, &rq_param, pipe_param->src); extract_rq_regs(mode_lib, rq_regs, rq_param); print__rq_regs_st(mode_lib, *rq_regs); @@ -1550,7 +1550,7 @@ static void dml20v2_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib, void dml20v2_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib, display_dlg_regs_st *dlg_regs, display_ttu_regs_st *ttu_regs, - display_e2e_pipe_params_st *e2e_pipe_param, + const display_e2e_pipe_params_st *e2e_pipe_param, const unsigned int num_pipes, const unsigned int pipe_idx, const bool cstate_en, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h index 27cf8bed9376..2b4e46ea1c3d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h @@ -43,7 +43,7 @@ struct display_mode_lib; void dml20v2_rq_dlg_get_rq_reg( struct display_mode_lib *mode_lib, display_rq_regs_st *rq_regs, - const display_pipe_params_st pipe_param); + const display_pipe_params_st *pipe_param); // Function: dml_rq_dlg_get_dlg_reg @@ -61,7 +61,7 @@ void dml20v2_rq_dlg_get_dlg_reg( struct display_mode_lib *mode_lib, display_dlg_regs_st *dlg_regs, display_ttu_regs_st *ttu_regs, - display_e2e_pipe_params_st *e2e_pipe_param, + const display_e2e_pipe_params_st *e2e_pipe_param, const unsigned int num_pipes, const unsigned int pipe_idx, const bool cstate_en, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index dc1c81a6e377..bca9406b03b3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -694,7 +694,7 @@ static void get_surf_rq_param( display_data_rq_sizing_params_st *rq_sizing_param, display_data_rq_dlg_params_st *rq_dlg_param, display_data_rq_misc_params_st *rq_misc_param, - const display_pipe_params_st pipe_param, + const display_pipe_params_st *pipe_param, bool is_chroma) { bool mode_422 = false; @@ -706,30 +706,30 @@ static void get_surf_rq_param( // FIXME check if ppe apply for both luma and chroma in 422 case if (is_chroma) { - vp_width = pipe_param.src.viewport_width_c / ppe; - vp_height = pipe_param.src.viewport_height_c; - data_pitch = pipe_param.src.data_pitch_c; - meta_pitch = pipe_param.src.meta_pitch_c; + vp_width = pipe_param->src.viewport_width_c / ppe; + vp_height = pipe_param->src.viewport_height_c; + data_pitch = pipe_param->src.data_pitch_c; + meta_pitch = pipe_param->src.meta_pitch_c; } else { - vp_width = pipe_param.src.viewport_width / ppe; - vp_height = pipe_param.src.viewport_height; - data_pitch = pipe_param.src.data_pitch; - meta_pitch = pipe_param.src.meta_pitch; + vp_width = pipe_param->src.viewport_width / ppe; + vp_height = pipe_param->src.viewport_height; + data_pitch = pipe_param->src.data_pitch; + meta_pitch = pipe_param->src.meta_pitch; } - if (pipe_param.dest.odm_combine) { + if (pipe_param->dest.odm_combine) { unsigned int access_dir; unsigned int full_src_vp_width; unsigned int hactive_half; unsigned int src_hactive_half; - access_dir = (pipe_param.src.source_scan == dm_vert); // vp access direction: horizontal or vertical accessed - hactive_half = pipe_param.dest.hactive / 2; + access_dir = (pipe_param->src.source_scan == dm_vert); // vp access direction: horizontal or vertical accessed + hactive_half = pipe_param->dest.hactive / 2; if (is_chroma) { - full_src_vp_width = pipe_param.scale_ratio_depth.hscl_ratio_c * pipe_param.dest.full_recout_width; - src_hactive_half = pipe_param.scale_ratio_depth.hscl_ratio_c * hactive_half; + full_src_vp_width = pipe_param->scale_ratio_depth.hscl_ratio_c * pipe_param->dest.full_recout_width; + src_hactive_half = pipe_param->scale_ratio_depth.hscl_ratio_c * hactive_half; } else { - full_src_vp_width = pipe_param.scale_ratio_depth.hscl_ratio * pipe_param.dest.full_recout_width; - src_hactive_half = pipe_param.scale_ratio_depth.hscl_ratio * hactive_half; + full_src_vp_width = pipe_param->scale_ratio_depth.hscl_ratio * pipe_param->dest.full_recout_width; + src_hactive_half = pipe_param->scale_ratio_depth.hscl_ratio * hactive_half; } if (access_dir == 0) { @@ -754,7 +754,7 @@ static void get_surf_rq_param( rq_sizing_param->meta_chunk_bytes = 2048; rq_sizing_param->min_meta_chunk_bytes = 256; - if (pipe_param.src.hostvm) + if (pipe_param->src.hostvm) rq_sizing_param->mpte_group_bytes = 512; else rq_sizing_param->mpte_group_bytes = 2048; @@ -768,23 +768,23 @@ static void get_surf_rq_param( vp_height, data_pitch, meta_pitch, - pipe_param.src.source_format, - pipe_param.src.sw_mode, - pipe_param.src.macro_tile_size, - pipe_param.src.source_scan, - pipe_param.src.hostvm, + pipe_param->src.source_format, + pipe_param->src.sw_mode, + pipe_param->src.macro_tile_size, + pipe_param->src.source_scan, + pipe_param->src.hostvm, is_chroma); } static void dml_rq_dlg_get_rq_params( struct display_mode_lib *mode_lib, display_rq_params_st *rq_param, - const display_pipe_params_st pipe_param) + const display_pipe_params_st *pipe_param) { // get param for luma surface - rq_param->yuv420 = pipe_param.src.source_format == dm_420_8 - || pipe_param.src.source_format == dm_420_10; - rq_param->yuv420_10bpc = pipe_param.src.source_format == dm_420_10; + rq_param->yuv420 = pipe_param->src.source_format == dm_420_8 + || pipe_param->src.source_format == dm_420_10; + rq_param->yuv420_10bpc = pipe_param->src.source_format == dm_420_10; get_surf_rq_param( mode_lib, @@ -794,7 +794,7 @@ static void dml_rq_dlg_get_rq_params( pipe_param, 0); - if (is_dual_plane((enum source_format_class) (pipe_param.src.source_format))) { + if (is_dual_plane((enum source_format_class) (pipe_param->src.source_format))) { // get param for chroma surface get_surf_rq_param( mode_lib, @@ -806,14 +806,14 @@ static void dml_rq_dlg_get_rq_params( } // calculate how to split the det buffer space between luma and chroma - handle_det_buf_split(mode_lib, rq_param, pipe_param.src); + handle_det_buf_split(mode_lib, rq_param, pipe_param->src); print__rq_params_st(mode_lib, *rq_param); } void dml21_rq_dlg_get_rq_reg( struct display_mode_lib *mode_lib, display_rq_regs_st *rq_regs, - const display_pipe_params_st pipe_param) + const display_pipe_params_st *pipe_param) { display_rq_params_st rq_param = {0}; @@ -1658,7 +1658,7 @@ void dml21_rq_dlg_get_dlg_reg( struct display_mode_lib *mode_lib, display_dlg_regs_st *dlg_regs, display_ttu_regs_st *ttu_regs, - display_e2e_pipe_params_st *e2e_pipe_param, + const display_e2e_pipe_params_st *e2e_pipe_param, const unsigned int num_pipes, const unsigned int pipe_idx, const bool cstate_en, @@ -1696,7 +1696,7 @@ void dml21_rq_dlg_get_dlg_reg( // system parameter calculation done dml_print("DML_DLG: Calculation for pipe[%d] start\n\n", pipe_idx); - dml_rq_dlg_get_rq_params(mode_lib, &rq_param, e2e_pipe_param[pipe_idx].pipe); + dml_rq_dlg_get_rq_params(mode_lib, &rq_param, &e2e_pipe_param[pipe_idx].pipe); dml_rq_dlg_get_dlg_params( mode_lib, e2e_pipe_param, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.h b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.h index e8f7785e3fc6..af6ad0ca9cf8 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.h @@ -44,7 +44,7 @@ struct display_mode_lib; void dml21_rq_dlg_get_rq_reg( struct display_mode_lib *mode_lib, display_rq_regs_st *rq_regs, - const display_pipe_params_st pipe_param); + const display_pipe_params_st *pipe_param); // Function: dml_rq_dlg_get_dlg_reg // Calculate and return DLG and TTU register struct given the system setting @@ -61,7 +61,7 @@ void dml21_rq_dlg_get_dlg_reg( struct display_mode_lib *mode_lib, display_dlg_regs_st *dlg_regs, display_ttu_regs_st *ttu_regs, - display_e2e_pipe_params_st *e2e_pipe_param, + const display_e2e_pipe_params_st *e2e_pipe_param, const unsigned int num_pipes, const unsigned int pipe_idx, const bool cstate_en, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c index 58c312f80a07..f4d6acad0b6c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c @@ -747,7 +747,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib, display_data_rq_sizing_params_st *rq_sizing_param, display_data_rq_dlg_params_st *rq_dlg_param, display_data_rq_misc_params_st *rq_misc_param, - const display_pipe_params_st pipe_param, + const display_pipe_params_st *pipe_param, bool is_chroma, bool is_alpha) { @@ -761,32 +761,32 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib, // FIXME check if ppe apply for both luma and chroma in 422 case if (is_chroma | is_alpha) { - vp_width = pipe_param.src.viewport_width_c / ppe; - vp_height = pipe_param.src.viewport_height_c; - data_pitch = pipe_param.src.data_pitch_c; - meta_pitch = pipe_param.src.meta_pitch_c; - surface_height = pipe_param.src.surface_height_y / 2.0; + vp_width = pipe_param->src.viewport_width_c / ppe; + vp_height = pipe_param->src.viewport_height_c; + data_pitch = pipe_param->src.data_pitch_c; + meta_pitch = pipe_param->src.meta_pitch_c; + surface_height = pipe_param->src.surface_height_y / 2.0; } else { - vp_width = pipe_param.src.viewport_width / ppe; - vp_height = pipe_param.src.viewport_height; - data_pitch = pipe_param.src.data_pitch; - meta_pitch = pipe_param.src.meta_pitch; - surface_height = pipe_param.src.surface_height_y; + vp_width = pipe_param->src.viewport_width / ppe; + vp_height = pipe_param->src.viewport_height; + data_pitch = pipe_param->src.data_pitch; + meta_pitch = pipe_param->src.meta_pitch; + surface_height = pipe_param->src.surface_height_y; } - if (pipe_param.dest.odm_combine) { + if (pipe_param->dest.odm_combine) { unsigned int access_dir = 0; unsigned int full_src_vp_width = 0; unsigned int hactive_odm = 0; unsigned int src_hactive_odm = 0; - access_dir = (pipe_param.src.source_scan == dm_vert); // vp access direction: horizontal or vertical accessed - hactive_odm = pipe_param.dest.hactive / ((unsigned int)pipe_param.dest.odm_combine*2); + access_dir = (pipe_param->src.source_scan == dm_vert); // vp access direction: horizontal or vertical accessed + hactive_odm = pipe_param->dest.hactive / ((unsigned int) pipe_param->dest.odm_combine*2); if (is_chroma) { - full_src_vp_width = pipe_param.scale_ratio_depth.hscl_ratio_c * pipe_param.dest.full_recout_width; - src_hactive_odm = pipe_param.scale_ratio_depth.hscl_ratio_c * hactive_odm; + full_src_vp_width = pipe_param->scale_ratio_depth.hscl_ratio_c * pipe_param->dest.full_recout_width; + src_hactive_odm = pipe_param->scale_ratio_depth.hscl_ratio_c * hactive_odm; } else { - full_src_vp_width = pipe_param.scale_ratio_depth.hscl_ratio * pipe_param.dest.full_recout_width; - src_hactive_odm = pipe_param.scale_ratio_depth.hscl_ratio * hactive_odm; + full_src_vp_width = pipe_param->scale_ratio_depth.hscl_ratio * pipe_param->dest.full_recout_width; + src_hactive_odm = pipe_param->scale_ratio_depth.hscl_ratio * hactive_odm; } if (access_dir == 0) { @@ -815,7 +815,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib, rq_sizing_param->meta_chunk_bytes = 2048; rq_sizing_param->min_meta_chunk_bytes = 256; - if (pipe_param.src.hostvm) + if (pipe_param->src.hostvm) rq_sizing_param->mpte_group_bytes = 512; else rq_sizing_param->mpte_group_bytes = 2048; @@ -828,28 +828,28 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib, vp_height, data_pitch, meta_pitch, - pipe_param.src.source_format, - pipe_param.src.sw_mode, - pipe_param.src.macro_tile_size, - pipe_param.src.source_scan, - pipe_param.src.hostvm, + pipe_param->src.source_format, + pipe_param->src.sw_mode, + pipe_param->src.macro_tile_size, + pipe_param->src.source_scan, + pipe_param->src.hostvm, is_chroma, surface_height); } static void dml_rq_dlg_get_rq_params(struct display_mode_lib *mode_lib, display_rq_params_st *rq_param, - const display_pipe_params_st pipe_param) + const display_pipe_params_st *pipe_param) { // get param for luma surface - rq_param->yuv420 = pipe_param.src.source_format == dm_420_8 - || pipe_param.src.source_format == dm_420_10 - || pipe_param.src.source_format == dm_rgbe_alpha - || pipe_param.src.source_format == dm_420_12; + rq_param->yuv420 = pipe_param->src.source_format == dm_420_8 + || pipe_param->src.source_format == dm_420_10 + || pipe_param->src.source_format == dm_rgbe_alpha + || pipe_param->src.source_format == dm_420_12; - rq_param->yuv420_10bpc = pipe_param.src.source_format == dm_420_10; + rq_param->yuv420_10bpc = pipe_param->src.source_format == dm_420_10; - rq_param->rgbe_alpha = (pipe_param.src.source_format == dm_rgbe_alpha)?1:0; + rq_param->rgbe_alpha = (pipe_param->src.source_format == dm_rgbe_alpha)?1:0; get_surf_rq_param(mode_lib, &(rq_param->sizing.rq_l), @@ -859,7 +859,7 @@ static void dml_rq_dlg_get_rq_params(struct display_mode_lib *mode_lib, 0, 0); - if (is_dual_plane((enum source_format_class)(pipe_param.src.source_format))) { + if (is_dual_plane((enum source_format_class)(pipe_param->src.source_format))) { // get param for chroma surface get_surf_rq_param(mode_lib, &(rq_param->sizing.rq_c), @@ -871,13 +871,13 @@ static void dml_rq_dlg_get_rq_params(struct display_mode_lib *mode_lib, } // calculate how to split the det buffer space between luma and chroma - handle_det_buf_split(mode_lib, rq_param, pipe_param.src); + handle_det_buf_split(mode_lib, rq_param, pipe_param->src); print__rq_params_st(mode_lib, *rq_param); } void dml30_rq_dlg_get_rq_reg(struct display_mode_lib *mode_lib, display_rq_regs_st *rq_regs, - const display_pipe_params_st pipe_param) + const display_pipe_params_st *pipe_param) { display_rq_params_st rq_param = { 0 }; @@ -1831,7 +1831,7 @@ static void dml_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib, void dml30_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib, display_dlg_regs_st *dlg_regs, display_ttu_regs_st *ttu_regs, - display_e2e_pipe_params_st *e2e_pipe_param, + const display_e2e_pipe_params_st *e2e_pipe_param, const unsigned int num_pipes, const unsigned int pipe_idx, const bool cstate_en, @@ -1866,7 +1866,7 @@ void dml30_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib, // system parameter calculation done dml_print("DML_DLG: Calculation for pipe[%d] start\n\n", pipe_idx); - dml_rq_dlg_get_rq_params(mode_lib, &rq_param, e2e_pipe_param[pipe_idx].pipe); + dml_rq_dlg_get_rq_params(mode_lib, &rq_param, &e2e_pipe_param[pipe_idx].pipe); dml_rq_dlg_get_dlg_params(mode_lib, e2e_pipe_param, num_pipes, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h index c04965cceff3..625e41f8d575 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.h @@ -41,7 +41,7 @@ struct display_mode_lib; // See also: void dml30_rq_dlg_get_rq_reg(struct display_mode_lib *mode_lib, display_rq_regs_st *rq_regs, - const display_pipe_params_st pipe_param); + const display_pipe_params_st *pipe_param); // Function: dml_rq_dlg_get_dlg_reg // Calculate and return DLG and TTU register struct given the system setting @@ -57,7 +57,7 @@ void dml30_rq_dlg_get_rq_reg(struct display_mode_lib *mode_lib, void dml30_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib, display_dlg_regs_st *dlg_regs, display_ttu_regs_st *ttu_regs, - display_e2e_pipe_params_st *e2e_pipe_param, + const display_e2e_pipe_params_st *e2e_pipe_param, const unsigned int num_pipes, const unsigned int pipe_idx, const bool cstate_en, diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h index 6adee8a9ee56..0be31ea15f44 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h @@ -49,7 +49,7 @@ struct dml_funcs { struct display_mode_lib *mode_lib, display_dlg_regs_st *dlg_regs, display_ttu_regs_st *ttu_regs, - display_e2e_pipe_params_st *e2e_pipe_param, + const display_e2e_pipe_params_st *e2e_pipe_param, const unsigned int num_pipes, const unsigned int pipe_idx, const bool cstate_en, @@ -60,7 +60,7 @@ struct dml_funcs { void (*rq_dlg_get_rq_reg)( struct display_mode_lib *mode_lib, display_rq_regs_st *rq_regs, - const display_pipe_params_st pipe_param); + const display_pipe_params_st *pipe_param); void (*recalculate)(struct display_mode_lib *mode_lib); void (*validate)(struct display_mode_lib *mode_lib); }; From 1b3cfadf63b5d793a2480689dcf38814178c4ea6 Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Tue, 7 Sep 2021 20:22:13 -0400 Subject: [PATCH 2439/4345] BACKPORT: drm/amd/display: Allocate structs needed by dcn_bw_calc_rq_dlg_ttu in pipe_ctx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [Why & How] dcn_bw_calc_rq_dlg_ttu uses a stack frame great than 1024. To solve this we could allocate the rq_param, dlg_sys_param, and input structs dynamically. Since this function is inside a kernel_fpu_begin()/end() call we want to avoid memory allocation. Instead it's much safer to pre-allocate these on the pipe_ctx. Bug: 254441685 Signed-off-by: Harry Wentland Fixes: 3fe617ccafd6 ("Enable '-Werror' by default for all kernel builds") Cc: Nick Desaulniers Cc: Linus Torvalds Cc: amd-gfx@lists.freedesktop.org Cc: Linux Kernel Mailing List Cc: Arnd Bergmann Cc: Leo Li Cc: Alex Deucher Cc: Christian König Cc: Xinhui Pan Cc: Nathan Chancellor Cc: Guenter Roeck Cc: llvm@lists.linux.dev Acked-by: Christian König Build-tested-by: Nathan Chancellor Reviewed-by: Leo Li Signed-off-by: Alex Deucher (cherry picked from commit 1f2fcc8183e372b5d8f0e00d3e42e5d6a4a6a336) Signed-off-by: Lee Jones Change-Id: I667857207b3bdcdc8eebb87a043fc4d5bf008d4d --- .../gpu/drm/amd/display/dc/calcs/dcn_calcs.c | 51 ++++++++++--------- .../gpu/drm/amd/display/dc/inc/core_types.h | 3 ++ 2 files changed, 30 insertions(+), 24 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c index 51397b565ddf..93280dca7cd0 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c @@ -459,9 +459,9 @@ static void dcn_bw_calc_rq_dlg_ttu( struct _vcs_dpi_display_dlg_regs_st *dlg_regs = &pipe->dlg_regs; struct _vcs_dpi_display_ttu_regs_st *ttu_regs = &pipe->ttu_regs; struct _vcs_dpi_display_rq_regs_st *rq_regs = &pipe->rq_regs; - struct _vcs_dpi_display_rq_params_st rq_param = {0}; - struct _vcs_dpi_display_dlg_sys_params_st dlg_sys_param = {0}; - struct _vcs_dpi_display_e2e_pipe_params_st input = { { { 0 } } }; + struct _vcs_dpi_display_rq_params_st *rq_param = &pipe->dml_rq_param; + struct _vcs_dpi_display_dlg_sys_params_st *dlg_sys_param = &pipe->dml_dlg_sys_param; + struct _vcs_dpi_display_e2e_pipe_params_st *input = &pipe->dml_input; float total_active_bw = 0; float total_prefetch_bw = 0; int total_flip_bytes = 0; @@ -470,45 +470,48 @@ static void dcn_bw_calc_rq_dlg_ttu( memset(dlg_regs, 0, sizeof(*dlg_regs)); memset(ttu_regs, 0, sizeof(*ttu_regs)); memset(rq_regs, 0, sizeof(*rq_regs)); + memset(rq_param, 0, sizeof(*rq_param)); + memset(dlg_sys_param, 0, sizeof(*dlg_sys_param)); + memset(input, 0, sizeof(*input)); for (i = 0; i < number_of_planes; i++) { total_active_bw += v->read_bandwidth[i]; total_prefetch_bw += v->prefetch_bandwidth[i]; total_flip_bytes += v->total_immediate_flip_bytes[i]; } - dlg_sys_param.total_flip_bw = v->return_bw - dcn_bw_max2(total_active_bw, total_prefetch_bw); - if (dlg_sys_param.total_flip_bw < 0.0) - dlg_sys_param.total_flip_bw = 0; + dlg_sys_param->total_flip_bw = v->return_bw - dcn_bw_max2(total_active_bw, total_prefetch_bw); + if (dlg_sys_param->total_flip_bw < 0.0) + dlg_sys_param->total_flip_bw = 0; - dlg_sys_param.t_mclk_wm_us = v->dram_clock_change_watermark; - dlg_sys_param.t_sr_wm_us = v->stutter_enter_plus_exit_watermark; - dlg_sys_param.t_urg_wm_us = v->urgent_watermark; - dlg_sys_param.t_extra_us = v->urgent_extra_latency; - dlg_sys_param.deepsleep_dcfclk_mhz = v->dcf_clk_deep_sleep; - dlg_sys_param.total_flip_bytes = total_flip_bytes; + dlg_sys_param->t_mclk_wm_us = v->dram_clock_change_watermark; + dlg_sys_param->t_sr_wm_us = v->stutter_enter_plus_exit_watermark; + dlg_sys_param->t_urg_wm_us = v->urgent_watermark; + dlg_sys_param->t_extra_us = v->urgent_extra_latency; + dlg_sys_param->deepsleep_dcfclk_mhz = v->dcf_clk_deep_sleep; + dlg_sys_param->total_flip_bytes = total_flip_bytes; - pipe_ctx_to_e2e_pipe_params(pipe, &input.pipe); - input.clks_cfg.dcfclk_mhz = v->dcfclk; - input.clks_cfg.dispclk_mhz = v->dispclk; - input.clks_cfg.dppclk_mhz = v->dppclk; - input.clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; - input.clks_cfg.socclk_mhz = v->socclk; - input.clks_cfg.voltage = v->voltage_level; + pipe_ctx_to_e2e_pipe_params(pipe, &input->pipe); + input->clks_cfg.dcfclk_mhz = v->dcfclk; + input->clks_cfg.dispclk_mhz = v->dispclk; + input->clks_cfg.dppclk_mhz = v->dppclk; + input->clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; + input->clks_cfg.socclk_mhz = v->socclk; + input->clks_cfg.voltage = v->voltage_level; // dc->dml.logger = pool->base.logger; - input.dout.output_format = (v->output_format[in_idx] == dcn_bw_420) ? dm_420 : dm_444; - input.dout.output_type = (v->output[in_idx] == dcn_bw_hdmi) ? dm_hdmi : dm_dp; + input->dout.output_format = (v->output_format[in_idx] == dcn_bw_420) ? dm_420 : dm_444; + input->dout.output_type = (v->output[in_idx] == dcn_bw_hdmi) ? dm_hdmi : dm_dp; //input[in_idx].dout.output_standard; /*todo: soc->sr_enter_plus_exit_time??*/ - dlg_sys_param.t_srx_delay_us = dc->dcn_ip->dcfclk_cstate_latency / v->dcf_clk_deep_sleep; + dlg_sys_param->t_srx_delay_us = dc->dcn_ip->dcfclk_cstate_latency / v->dcf_clk_deep_sleep; - dml1_rq_dlg_get_rq_params(dml, &rq_param, input.pipe.src); + dml1_rq_dlg_get_rq_params(dml, rq_param, input.pipe.src); dml1_extract_rq_regs(dml, rq_regs, rq_param); dml1_rq_dlg_get_dlg_params( dml, dlg_regs, ttu_regs, - rq_param.dlg, + rq_param->dlg, dlg_sys_param, input, true, diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 6e6bc66e49f0..e40a1d5d5528 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -328,6 +328,9 @@ struct pipe_ctx { struct _vcs_dpi_display_ttu_regs_st ttu_regs; struct _vcs_dpi_display_rq_regs_st rq_regs; struct _vcs_dpi_display_pipe_dest_params_st pipe_dlg_param; + struct _vcs_dpi_display_rq_params_st dml_rq_param; + struct _vcs_dpi_display_dlg_sys_params_st dml_dlg_sys_param; + struct _vcs_dpi_display_e2e_pipe_params_st dml_input; #endif union pipe_update_flags update_flags; struct dwbc *dwbc; From 3815eca894ad79cc6faadb4bb17757d1ae8d78cd Mon Sep 17 00:00:00 2001 From: Lv Ruyi Date: Sat, 9 Oct 2021 08:59:00 +0000 Subject: [PATCH 2440/4345] UPSTREAM: firmware: tegra: Fix error application of sizeof() to pointer Application of sizeof() to pointer yields the number of bytes of the pointer, but it should use the length of buffer in the code. Bug: 254441685 Fixes: 06c2d9a078ab ("firmware: tegra: Reduce stack usage") Reported-by: Zeal Robot Signed-off-by: Lv Ruyi Reviewed-by: Jon Hunter Tested-by: Jon Hunter Signed-off-by: Thierry Reding (cherry picked from commit 711e26c00e4c7b7cef0420c76a61e6d818e12687) Signed-off-by: Lee Jones Change-Id: Ide1f9cbc31fea6fbb1d74f7ad4bbb6bef7caa0a9 --- drivers/firmware/tegra/bpmp-debugfs.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/tegra/bpmp-debugfs.c b/drivers/firmware/tegra/bpmp-debugfs.c index 286fe1257961..fbc0d661060b 100644 --- a/drivers/firmware/tegra/bpmp-debugfs.c +++ b/drivers/firmware/tegra/bpmp-debugfs.c @@ -77,13 +77,14 @@ static const char *get_filename(struct tegra_bpmp *bpmp, const char *root_path, *filename = NULL; char *root_path_buf; size_t root_len; + size_t root_path_buf_len = 512; - root_path_buf = kzalloc(512, GFP_KERNEL); + root_path_buf = kzalloc(root_path_buf_len, GFP_KERNEL); if (!root_path_buf) goto out; root_path = dentry_path(bpmp->debugfs_mirror, root_path_buf, - sizeof(root_path_buf)); + root_path_buf_len); if (IS_ERR(root_path)) goto out; From 37b3a6153f703925678d4ca6e59c72f440ade088 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 27 May 2022 21:15:41 +1000 Subject: [PATCH 2441/4345] UPSTREAM: powerpc/64: Include cache.h directly in paca.h paca.h uses ____cacheline_aligned without directly including cache.h, where it's defined. For Book3S builds that's OK because paca.h includes lppaca.h, and it does include cache.h. But Book3E builds have been getting cache.h indirectly via printk.h, which is dicey, and in fact that include was recently removed, leading to build errors such as: ld: fs/isofs/dir.o:(.bss+0x0): multiple definition of `____cacheline_aligned'; fs/isofs/namei.o:(.bss+0x0): first defined here So include cache.h directly to fix the build error. Bug: 254441685 Fixes: 534aa1dc975a ("printk: stop including cache.h from printk.h") Reported-by: Guenter Roeck Signed-off-by: Michael Ellerman (cherry picked from commit dcf280e6f80be280ca7dd1b058f038654e4a18dd) Signed-off-by: Lee Jones Change-Id: Id94536f14e3705b90bf12f6c61f59b96de3c994a --- arch/powerpc/include/asm/paca.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 9454d29ff4b4..bf8da58c393e 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -12,6 +12,7 @@ #ifdef CONFIG_PPC64 +#include #include #include #include From f74be4424642f5ff8bd34d5711f030c45710c348 Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Tue, 18 Oct 2022 19:39:01 -0700 Subject: [PATCH 2442/4345] UPSTREAM: usb: dwc3: gadget: Don't delay End Transfer on delayed_status The gadget driver may wait on the request completion when it sets the USB_GADGET_DELAYED_STATUS. Make sure that the End Transfer command can go through if the dwc->delayed_status is set so that the request can complete. When the delayed_status is set, the Setup packet is already processed, and the next phase should be either Data or Status. It's unlikely that the host would cancel the control transfer and send a new Setup packet during End Transfer command. But if that's the case, we can try again when ep0state returns to EP0_SETUP_PHASE. Bug: 254441685 Fixes: e1ee843488d5 ("usb: dwc3: gadget: Force sending delayed status during soft disconnect") Cc: stable@vger.kernel.org Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/3f9f59e5d74efcbaee444cf4b30ef639cc7b124e.1666146954.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 4db0fbb601361767144e712beb96704b966339f5) Signed-off-by: Lee Jones Change-Id: I308536a4d5482c838a1b75c84a1e1127e43f3b95 --- drivers/usb/dwc3/gadget.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 0ed907e7aaef..091ec8002efa 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1683,6 +1683,16 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int cmd |= DWC3_DEPCMD_PARAM(dep->resource_index); memset(¶ms, 0, sizeof(params)); ret = dwc3_send_gadget_ep_cmd(dep, cmd, ¶ms); + /* + * If the End Transfer command was timed out while the device is + * not in SETUP phase, it's possible that an incoming Setup packet + * may prevent the command's completion. Let's retry when the + * ep0state returns to EP0_SETUP_PHASE. + */ + if (ret == -ETIMEDOUT && dep->dwc->ep0state != EP0_SETUP_PHASE) { + dep->flags |= DWC3_EP_DELAY_STOP; + return 0; + } WARN_ON_ONCE(ret); dep->resource_index = 0; @@ -3710,7 +3720,7 @@ void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, * timeout. Delay issuing the End Transfer command until the Setup TRB is * prepared. */ - if (dwc->ep0state != EP0_SETUP_PHASE) { + if (dwc->ep0state != EP0_SETUP_PHASE && !dwc->delayed_status) { dep->flags |= DWC3_EP_DELAY_STOP; return; } From 8eb30a41f5017f084a530c7ace5e8bdbf90c1e9e Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 2 Nov 2022 14:41:52 -0400 Subject: [PATCH 2443/4345] UPSTREAM: mm/shmem: use page_mapping() to detect page cache for uffd continue mfill_atomic_install_pte() checks page->mapping to detect whether one page is used in the page cache. However as pointed out by Matthew, the page can logically be a tail page rather than always the head in the case of uffd minor mode with UFFDIO_CONTINUE. It means we could wrongly install one pte with shmem thp tail page assuming it's an anonymous page. It's not that clear even for anonymous page, since normally anonymous pages also have page->mapping being setup with the anon vma. It's safe here only because the only such caller to mfill_atomic_install_pte() is always passing in a newly allocated page (mcopy_atomic_pte()), whose page->mapping is not yet setup. However that's not extremely obvious either. For either of above, use page_mapping() instead. Bug: 254441685 Link: https://lkml.kernel.org/r/Y2K+y7wnhC4vbnP2@x1n Fixes: 153132571f02 ("userfaultfd/shmem: support UFFDIO_CONTINUE for shmem") Signed-off-by: Peter Xu Reported-by: Matthew Wilcox Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Axel Rasmussen Cc: Signed-off-by: Andrew Morton (cherry picked from commit 93b0d9178743a68723babe8448981f658aebc58e) Signed-off-by: Lee Jones Change-Id: I5635ee1a81087e8022169ad1bda1e6d98fe5835f --- mm/userfaultfd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 80da102e4c36..fa707e50b102 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -63,7 +63,7 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, pte_t _dst_pte, *dst_pte; bool writable = dst_vma->vm_flags & VM_WRITE; bool vm_shared = dst_vma->vm_flags & VM_SHARED; - bool page_in_cache = page->mapping; + bool page_in_cache = page_mapping(page); spinlock_t *ptl; struct inode *inode; pgoff_t offset, max_off; From d11c3f780c87198ac9d94f954e66d651677b532a Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 7 Nov 2022 16:50:00 +0000 Subject: [PATCH 2444/4345] UPSTREAM: mm/damon/dbgfs: check if rm_contexts input is for a real context A user could write a name of a file under 'damon/' debugfs directory, which is not a user-created context, to 'rm_contexts' file. In the case, 'dbgfs_rm_context()' just assumes it's the valid DAMON context directory only if a file of the name exist. As a result, invalid memory access could happen as below. Fix the bug by checking if the given input is for a directory. This check can filter out non-context inputs because directories under 'damon/' debugfs directory can be created via only 'mk_contexts' file. This bug has found by syzbot[1]. [1] https://lore.kernel.org/damon/000000000000ede3ac05ec4abf8e@google.com/ Bug: 254441685 Link: https://lkml.kernel.org/r/20221107165001.5717-2-sj@kernel.org Fixes: 75c1c2b53c78 ("mm/damon/dbgfs: support multiple contexts") Signed-off-by: SeongJae Park Reported-by: syzbot+6087eafb76a94c4ac9eb@syzkaller.appspotmail.com Cc: [5.15.x] Signed-off-by: Andrew Morton (cherry picked from commit 1de09a7281edecfdba19b3a07417f6d65243ab5f) Signed-off-by: Lee Jones Change-Id: I038612db15c0a46089a5e1a52a4750fff6ba3bf6 --- mm/damon/dbgfs.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index f2772fc740c0..819c337c22ff 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -785,6 +785,7 @@ out: static int dbgfs_rm_context(char *name) { struct dentry *root, *dir, **new_dirs; + struct inode *inode; struct damon_ctx **new_ctxs; int i, j; int ret = 0; @@ -800,6 +801,12 @@ static int dbgfs_rm_context(char *name) if (!dir) return -ENOENT; + inode = d_inode(dir); + if (!S_ISDIR(inode->i_mode)) { + ret = -EINVAL; + goto out_dput; + } + new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs), GFP_KERNEL); if (!new_dirs) { From 8adfaec1546ce4bf3444584fdf7e96f52e71044a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 14 Nov 2022 10:44:11 +0000 Subject: [PATCH 2445/4345] BACKPORT: arm64: mm: kfence: only handle translation faults Alexander noted that KFENCE only expects to handle faults from invalid page table entries (i.e. translation faults), but arm64's fault handling logic will call kfence_handle_page_fault() for other types of faults, including alignment faults caused by unaligned atomics. This has the unfortunate property of causing those other faults to be reported as "KFENCE: use-after-free", which is misleading and hinders debugging. Fix this by only forwarding unhandled translation faults to the KFENCE code, similar to what x86 does already. Alexander has verified that this passes all the tests in the KFENCE test suite and avoids bogus reports on misaligned atomics. Bug: 254441685 Link: https://lore.kernel.org/all/20221102081620.1465154-1-zhongbaisong@huawei.com/ Fixes: 840b23986344 ("arm64, kfence: enable KFENCE for ARM64") Signed-off-by: Mark Rutland Reviewed-by: Alexander Potapenko Tested-by: Alexander Potapenko Cc: Catalin Marinas Cc: Marco Elver Cc: Will Deacon Link: https://lore.kernel.org/r/20221114104411.2853040-1-mark.rutland@arm.com Signed-off-by: Will Deacon (cherry picked from commit 0bb1fbffc631064db567ccaeb9ed6b6df6342b66) Signed-off-by: Lee Jones Change-Id: I317bb3ca1db362f3a3befa2e97c76d71f1edc770 --- arch/arm64/mm/fault.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index fa59cfb4696b..6c962463064b 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -361,6 +361,11 @@ static bool is_el1_mte_sync_tag_check_fault(unsigned int esr) return false; } +static bool is_translation_fault(unsigned long esr) +{ + return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT; +} + static void __do_kernel_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -393,7 +398,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) + if (is_translation_fault(esr) && + kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; msg = "paging request"; From 9a595405c4ab45f276bb82531745ee6d5317a946 Mon Sep 17 00:00:00 2001 From: Charan Teja Kalla Date: Tue, 8 Nov 2022 10:46:22 +0530 Subject: [PATCH 2446/4345] UPSTREAM: mm/page_exit: fix kernel doc warning in page_ext_put() Fix the below compiler warnings reported with 'make W=1 mm/'. mm/page_ext.c:178: warning: Function parameter or member 'page_ext' not described in 'page_ext_put'. Bug: 254441685 [quic_pkondeti@quicinc.com: better patch title] Link: https://lkml.kernel.org/r/1667884582-2465-1-git-send-email-quic_charante@quicinc.com Fixes: b1d5488a252dc9 ("mm: fix use-after free of page_ext after race with memory-offline") Signed-off-by: Charan Teja Kalla Reported-by: Vlastimil Babka Tested-by: Vlastimil Babka Cc: Pavan Kondeti Signed-off-by: Andrew Morton (cherry picked from commit ed86b74874f839f0e579bdf92ea0a5aabdfabebb) Signed-off-by: Lee Jones Change-Id: Ia1facd5591e04a41d03f9c9a65ea2ef506db2b3f --- mm/page_ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_ext.c b/mm/page_ext.c index e5b56394e2b4..fca6a09cdcfe 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -148,7 +148,7 @@ struct page_ext *page_ext_get(struct page *page) /** * page_ext_put() - Working with page extended information is done. - * @page_ext - Page extended information received from page_ext_get(). + * @page_ext: Page extended information received from page_ext_get(). * * The page extended information of the page may not be valid after this * function is called. From 73c8565a9eb474481b15a7b2ab4dbf955f8a4c6e Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 24 Nov 2022 11:12:07 +0900 Subject: [PATCH 2447/4345] UPSTREAM: block: mq-deadline: Fix dd_finish_request() for zoned devices dd_finish_request() tests if the per prio fifo_list is not empty to determine if request dispatching must be restarted for handling blocked write requests to zoned devices with a call to blk_mq_sched_mark_restart_hctx(). While simple, this implementation has 2 problems: 1) Only the priority level of the completed request is considered. However, writes to a zone may be blocked due to other writes to the same zone using a different priority level. While this is unlikely to happen in practice, as writing a zone with different IO priorirites does not make sense, nothing in the code prevents this from happening. 2) The use of list_empty() is dangerous as dd_finish_request() does not take dd->lock and may run concurrently with the insert and dispatch code. Fix these 2 problems by testing the write fifo list of all priority levels using the new helper dd_has_write_work(), and by testing each fifo list using list_empty_careful(). Bug: 254441685 Fixes: c807ab520fc3 ("block/mq-deadline: Add I/O priority support") Cc: Signed-off-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20221124021208.242541-2-damien.lemoal@opensource.wdc.com Signed-off-by: Jens Axboe (cherry picked from commit 2820e5d0820ac4daedff1272616a53d9c7682fd2) Signed-off-by: Lee Jones Change-Id: I0b56fae549938312d0c8fda1bc193e3a47e4fff4 --- block/mq-deadline-main.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/block/mq-deadline-main.c b/block/mq-deadline-main.c index cdcf72e72d98..560752ad8677 100644 --- a/block/mq-deadline-main.c +++ b/block/mq-deadline-main.c @@ -793,6 +793,18 @@ static void dd_prepare_request(struct request *rq) rq->elv.priv[0] = NULL; } +static bool dd_has_write_work(struct blk_mq_hw_ctx *hctx) +{ + struct deadline_data *dd = hctx->queue->elevator->elevator_data; + enum dd_prio p; + + for (p = 0; p <= DD_PRIO_MAX; p++) + if (!list_empty_careful(&dd->per_prio[p].fifo_list[DD_WRITE])) + return true; + + return false; +} + /* * Callback from inside blk_mq_free_request(). * @@ -816,7 +828,6 @@ static void dd_finish_request(struct request *rq) struct dd_blkcg *blkcg = rq->elv.priv[0]; const u8 ioprio_class = dd_rq_ioclass(rq); const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; - struct dd_per_prio *per_prio = &dd->per_prio[prio]; dd_count(dd, completed, prio); ddcg_count(blkcg, completed, ioprio_class); @@ -826,9 +837,10 @@ static void dd_finish_request(struct request *rq) spin_lock_irqsave(&dd->zone_lock, flags); blk_req_zone_write_unlock(rq); - if (!list_empty(&per_prio->fifo_list[DD_WRITE])) - blk_mq_sched_mark_restart_hctx(rq->mq_hctx); spin_unlock_irqrestore(&dd->zone_lock, flags); + + if (dd_has_write_work(rq->mq_hctx)) + blk_mq_sched_mark_restart_hctx(rq->mq_hctx); } } From 2f9858326dea00b90551eff8d1822cf218007ab9 Mon Sep 17 00:00:00 2001 From: Yang Shen Date: Tue, 22 Nov 2022 17:03:55 +0800 Subject: [PATCH 2448/4345] UPSTREAM: coresight: trbe: remove cpuhp instance node before remove cpuhp state cpuhp_state_add_instance() and cpuhp_state_remove_instance() should be used in pairs. Or there will lead to the warn on cpuhp_remove_multi_state() since the cpuhp_step list is not empty. The following is the error log with 'rmmod coresight-trbe': Error: Removing state 215 which has instances left. Call trace: __cpuhp_remove_state_cpuslocked+0x144/0x160 __cpuhp_remove_state+0xac/0x100 arm_trbe_device_remove+0x2c/0x60 [coresight_trbe] platform_remove+0x34/0x70 device_remove+0x54/0x90 device_release_driver_internal+0x1e4/0x250 driver_detach+0x5c/0xb0 bus_remove_driver+0x64/0xc0 driver_unregister+0x3c/0x70 platform_driver_unregister+0x20/0x30 arm_trbe_exit+0x1c/0x658 [coresight_trbe] __arm64_sys_delete_module+0x1ac/0x24c invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0x58/0x1a0 do_el0_svc+0x38/0xd0 el0_svc+0x2c/0xc0 el0t_64_sync_handler+0x1ac/0x1b0 el0t_64_sync+0x19c/0x1a0 ---[ end trace 0000000000000000 ]--- Bug: 254441685 Fixes: 3fbf7f011f24 ("coresight: sink: Add TRBE driver") Reviewed-by: Anshuman Khandual Signed-off-by: Yang Shen Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20221122090355.23533-1-shenyang39@huawei.com (cherry picked from commit 20ee8c223f792947378196307d8e707c9cdc2d61) Signed-off-by: Lee Jones Change-Id: Ie0a1bece2f5a1c54291c11cef3afb23aedcd0750 --- drivers/hwtracing/coresight/coresight-trbe.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c index 7dddb85b9059..fac63d092c7b 100644 --- a/drivers/hwtracing/coresight/coresight-trbe.c +++ b/drivers/hwtracing/coresight/coresight-trbe.c @@ -1030,6 +1030,7 @@ static int arm_trbe_probe_cpuhp(struct trbe_drvdata *drvdata) static void arm_trbe_remove_cpuhp(struct trbe_drvdata *drvdata) { + cpuhp_state_remove_instance(drvdata->trbe_online, &drvdata->hotplug_node); cpuhp_remove_multi_state(drvdata->trbe_online); } From 391c34feedcff11a5639a636ebbd72226d9cf407 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 30 Nov 2022 23:09:01 +0000 Subject: [PATCH 2449/4345] UPSTREAM: KVM: arm64: Free hypervisor allocations if vector slot init fails Teardown hypervisor mode if vector slot setup fails in order to avoid leaking any allocations done by init_hyp_mode(). Bug: 254441685 Fixes: b881cdce77b4 ("KVM: arm64: Allocate hyp vectors statically") Signed-off-by: Sean Christopherson Message-Id: <20221130230934.1014142-18-seanjc@google.com> Signed-off-by: Paolo Bonzini (cherry picked from commit 6baaeda878445dc7b9e86f614ac39bf137c385af) Signed-off-by: Lee Jones Change-Id: Id20a219325d0ae7882b7e910f460fc8b5c05f839 --- arch/arm64/kvm/arm.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 67c20d4d6ade..0470ebad9bdb 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2098,18 +2098,18 @@ int kvm_arch_init(void *opaque) err = kvm_init_vector_slots(); if (err) { kvm_err("Cannot initialise vector slots\n"); - goto out_err; + goto out_hyp; } err = init_subsystems(); if (err) - goto out_hyp; + goto out_subs; if (!in_hyp_mode) { err = finalize_hyp_mode(); if (err) { kvm_err("Failed to finalize Hyp protection\n"); - goto out_hyp; + goto out_subs; } } @@ -2123,8 +2123,9 @@ int kvm_arch_init(void *opaque) return 0; -out_hyp: +out_subs: hyp_cpu_pm_exit(); +out_hyp: if (!in_hyp_mode) teardown_hyp_mode(); out_err: From 43390f1621406d56277757a6602cd148b9a5024f Mon Sep 17 00:00:00 2001 From: James Houghton Date: Wed, 4 Jan 2023 23:19:10 +0000 Subject: [PATCH 2450/4345] BACKPORT: hugetlb: unshare some PMDs when splitting VMAs PMD sharing can only be done in PUD_SIZE-aligned pieces of VMAs; however, it is possible that HugeTLB VMAs are split without unsharing the PMDs first. Without this fix, it is possible to hit the uffd-wp-related WARN_ON_ONCE in hugetlb_change_protection [1]. The key there is that hugetlb_unshare_all_pmds will not attempt to unshare PMDs in non-PUD_SIZE-aligned sections of the VMA. It might seem ideal to unshare in hugetlb_vm_op_open, but we need to unshare in both the new and old VMAs, so unsharing in hugetlb_vm_op_split seems natural. [1]: https://lore.kernel.org/linux-mm/CADrL8HVeOkj0QH5VZZbRzybNE8CG-tEGFshnA+bG9nMgcWtBSg@mail.gmail.com/ Bug: 254441685 Link: https://lkml.kernel.org/r/20230104231910.1464197-1-jthoughton@google.com Fixes: 6dfeaff93be1 ("hugetlb/userfaultfd: unshare all pmds for hugetlbfs when register wp") Signed-off-by: James Houghton Reviewed-by: Mike Kravetz Acked-by: Peter Xu Cc: Axel Rasmussen Cc: Muchun Song Cc: Signed-off-by: Andrew Morton (cherry picked from commit b30c14cd61025eeea2f2e8569606cd167ba9ad2d) Signed-off-by: Lee Jones Change-Id: Ic7b61e7fd00369f17d26164c187a148d09ffd9ae --- mm/hugetlb.c | 45 ++++++++++++++++++++++++++++++++++++--------- 1 file changed, 36 insertions(+), 9 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7be2c9241cee..a4682bbdf352 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -78,6 +78,9 @@ DEFINE_SPINLOCK(hugetlb_lock); static int num_fault_mutexes; struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; +static void hugetlb_unshare_pmds(struct vm_area_struct *vma, + unsigned long start, unsigned long end); + static inline bool PageHugeFreed(struct page *head) { return page_private(head + 4) == -1UL; @@ -3698,6 +3701,25 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; + + /* + * PMD sharing is only possible for PUD_SIZE-aligned address ranges + * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this + * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. + */ + if (addr & ~PUD_MASK) { + /* + * hugetlb_vm_op_split is called right before we attempt to + * split the VMA. We will need to unshare PMDs in the old and + * new VMAs, so let's unshare before we split. + */ + unsigned long floor = addr & PUD_MASK; + unsigned long ceil = floor + PUD_SIZE; + + if (floor >= vma->vm_start && ceil <= vma->vm_end) + hugetlb_unshare_pmds(vma, floor, ceil); + } + return 0; } @@ -5756,26 +5778,21 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) } } -/* - * This function will unconditionally remove all the shared pmd pgtable entries - * within the specific vma for a hugetlbfs memory range. - */ -void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) +static void hugetlb_unshare_pmds(struct vm_area_struct *vma, + unsigned long start, + unsigned long end) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; - unsigned long address, start, end; + unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; - start = ALIGN(vma->vm_start, PUD_SIZE); - end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); - if (start >= end) return; @@ -5808,6 +5825,16 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) mmu_notifier_invalidate_range_end(&range); } +/* + * This function will unconditionally remove all the shared pmd pgtable entries + * within the specific vma for a hugetlbfs memory range. + */ +void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) +{ + hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), + ALIGN_DOWN(vma->vm_end, PUD_SIZE)); +} + #ifdef CONFIG_CMA static bool cma_reserve_called __initdata; From 1b307b685cca4f0fc72b69b5f86f4fbdf532780b Mon Sep 17 00:00:00 2001 From: Pratham Pratap Date: Wed, 25 Jan 2023 12:57:25 +0530 Subject: [PATCH 2451/4345] UPSTREAM: usb: gadget: f_uac2: Fix incorrect increment of bNumEndpoints Currently connect/disconnect of USB cable calls afunc_bind and eventually increments the bNumEndpoints. Performing multiple plugin/plugout will increment bNumEndpoints incorrectly, and on the next plug-in it leads to invalid configuration of descriptor and hence enumeration fails. Fix this by resetting the value of bNumEndpoints to 1 on every afunc_bind call. Bug: 254441685 Fixes: 40c73b30546e ("usb: gadget: f_uac2: add adaptive sync support for capture") Cc: stable Signed-off-by: Pratham Pratap Signed-off-by: Prashanth K Link: https://lore.kernel.org/r/1674631645-28888-1-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2fa89458af9993fab8054daf827f38881e2ad473) Signed-off-by: Lee Jones Change-Id: Ibbc0b098b7fc4d2d8e07dc4aa9be2917dc57bd64 --- drivers/usb/gadget/function/f_uac2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 91affe8babb8..3f4edfa73250 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -1097,6 +1097,7 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) } std_as_out_if0_desc.bInterfaceNumber = ret; std_as_out_if1_desc.bInterfaceNumber = ret; + std_as_out_if1_desc.bNumEndpoints = 1; uac2->as_out_intf = ret; uac2->as_out_alt = 0; From 0334ff98b9dd42b4dd73644f11c50f72871ac8c4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 17 Apr 2023 11:36:33 +0000 Subject: [PATCH 2452/4345] Revert "net: mdio: fix owner field for mdio buses registered using device-tree" This reverts commit d04dac7fae7580dce0cd9b55db6e1ad4e8d26157. It removes of_mdiobus_register() from the symbol list, which Android drivers are using, and they don't care about module owners as kernel modules are not allowed to be removed on Android systems, so revert it to preserve the ABI. Bug: 161946584 Change-Id: I5bb5d4261bab07c3a4eeb7a41ae09d4a41d56e7e Signed-off-by: Greg Kroah-Hartman --- drivers/net/mdio/of_mdio.c | 12 +++++------- drivers/net/phy/mdio_devres.c | 11 +++++------ include/linux/of_mdio.h | 22 +++------------------- 3 files changed, 13 insertions(+), 32 deletions(-) diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index b254127cea50..5bae47f3da40 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -238,23 +238,21 @@ bool of_mdiobus_child_is_phy(struct device_node *child) EXPORT_SYMBOL(of_mdiobus_child_is_phy); /** - * __of_mdiobus_register - Register mii_bus and create PHYs from the device tree + * of_mdiobus_register - Register mii_bus and create PHYs from the device tree * @mdio: pointer to mii_bus structure * @np: pointer to device_node of MDIO bus. - * @owner: module owning the @mdio object. * * This function registers the mii_bus structure and registers a phy_device * for each child node of @np. */ -int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, - struct module *owner) +int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) { struct device_node *child; bool scanphys = false; int addr, rc; if (!np) - return __mdiobus_register(mdio, owner); + return mdiobus_register(mdio); /* Do not continue if the node is disabled */ if (!of_device_is_available(np)) @@ -274,7 +272,7 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, of_property_read_u32(np, "reset-post-delay-us", &mdio->reset_post_delay_us); /* Register the MDIO bus */ - rc = __mdiobus_register(mdio, owner); + rc = mdiobus_register(mdio); if (rc) return rc; @@ -338,7 +336,7 @@ unregister: mdiobus_unregister(mdio); return rc; } -EXPORT_SYMBOL(__of_mdiobus_register); +EXPORT_SYMBOL(of_mdiobus_register); /** * of_mdio_find_device - Given a device tree node, find the mdio_device diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c index 69b829e6ab35..b560e99695df 100644 --- a/drivers/net/phy/mdio_devres.c +++ b/drivers/net/phy/mdio_devres.c @@ -98,14 +98,13 @@ EXPORT_SYMBOL(__devm_mdiobus_register); #if IS_ENABLED(CONFIG_OF_MDIO) /** - * __devm_of_mdiobus_register - Resource managed variant of of_mdiobus_register() + * devm_of_mdiobus_register - Resource managed variant of of_mdiobus_register() * @dev: Device to register mii_bus for * @mdio: MII bus structure to register * @np: Device node to parse - * @owner: Owning module */ -int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, - struct device_node *np, struct module *owner) +int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np) { struct mdiobus_devres *dr; int ret; @@ -118,7 +117,7 @@ int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, if (!dr) return -ENOMEM; - ret = __of_mdiobus_register(mdio, np, owner); + ret = of_mdiobus_register(mdio, np); if (ret) { devres_free(dr); return ret; @@ -128,7 +127,7 @@ int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, devres_add(dev, dr); return 0; } -EXPORT_SYMBOL(__devm_of_mdiobus_register); +EXPORT_SYMBOL(devm_of_mdiobus_register); #endif /* CONFIG_OF_MDIO */ MODULE_LICENSE("GPL"); diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 8cc6522ee43a..f56c6a9230ac 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -14,25 +14,9 @@ #if IS_ENABLED(CONFIG_OF_MDIO) bool of_mdiobus_child_is_phy(struct device_node *child); -int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, - struct module *owner); - -static inline int of_mdiobus_register(struct mii_bus *mdio, - struct device_node *np) -{ - return __of_mdiobus_register(mdio, np, THIS_MODULE); -} - -int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, - struct device_node *np, struct module *owner); - -static inline int devm_of_mdiobus_register(struct device *dev, - struct mii_bus *mdio, - struct device_node *np) -{ - return __devm_of_mdiobus_register(dev, mdio, np, THIS_MODULE); -} - +int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); +int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np); struct mdio_device *of_mdio_find_device(struct device_node *np); struct phy_device *of_phy_find_device(struct device_node *phy_np); struct phy_device * From 6f485880624b7f1c919780ad992c09ab0c5d64c3 Mon Sep 17 00:00:00 2001 From: Sandeep Dhavale Date: Wed, 8 Feb 2023 17:33:22 +0800 Subject: [PATCH 2453/4345] BACKPORT: erofs: add per-cpu threads for decompression as an option Using per-cpu thread pool we can reduce the scheduling latency compared to workqueue implementation. With this patch scheduling latency and variation is reduced as per-cpu threads are high priority kthread_workers. The results were evaluated on arm64 Android devices running 5.10 kernel. The table below shows resulting improvements of total scheduling latency for the same app launch benchmark runs with 50 iterations. Scheduling latency is the latency between when the task (workqueue kworker vs kthread_worker) became eligible to run to when it actually started running. +-------------------------+-----------+----------------+---------+ | | workqueue | kthread_worker | diff | +-------------------------+-----------+----------------+---------+ | Average (us) | 15253 | 2914 | -80.89% | | Median (us) | 14001 | 2912 | -79.20% | | Minimum (us) | 3117 | 1027 | -67.05% | | Maximum (us) | 30170 | 3805 | -87.39% | | Standard deviation (us) | 7166 | 359 | | +-------------------------+-----------+----------------+---------+ Background: Boot times and cold app launch benchmarks are very important to the Android ecosystem as they directly translate to responsiveness from user point of view. While EROFS provides a lot of important features like space savings, we saw some performance penalty in cold app launch benchmarks in few scenarios. Analysis showed that the significant variance was coming from the scheduling cost while decompression cost was more or less the same. Having per-cpu thread pool we can see from the above table that this variation is reduced by ~80% on average. This problem was discussed at LPC 2022. Link to LPC 2022 slides and talk at [1] [1] https://lpc.events/event/16/contributions/1338/ [ Gao Xiang: At least, we have to add this until WQ_UNBOUND workqueue issue [2] on many arm64 devices is resolved. ] [2] https://lore.kernel.org/r/CAJkfWY490-m6wNubkxiTPsW59sfsQs37Wey279LmiRxKt7aQYg@mail.gmail.com Bug: 271636421 Bug: 278520205 Test: launch_cvd Change-Id: I9dce2bfd6f40ec6a210161b80cee7c0417b4edb3 Signed-off-by: Sandeep Dhavale Signed-off-by: Gao Xiang Link: https://lore.kernel.org/r/20230208093322.75816-1-hsiangkao@linux.alibaba.com (cherry picked from commit 3fffb589b9a6e331e39cb75373ee7691acd7b109) [dhavale: Fixed minor conflict as upstream now has zdata.h folded in zdata.c] Signed-off-by: Sandeep Dhavale (cherry picked from commit 566a7f6c6b3f5f13b766fe749bbdb45918b029ac) [dhavale: Fixed minor conflicts in Kconfig and zdata.c] (cherry picked from commit 2de95f5d183c2174c9380a902919c8e59e380293) --- fs/erofs/Kconfig | 17 +++++ fs/erofs/zdata.c | 185 ++++++++++++++++++++++++++++++++++++++++++----- fs/erofs/zdata.h | 2 + 3 files changed, 186 insertions(+), 18 deletions(-) diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 858b3339f381..662660852397 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -76,3 +76,20 @@ config EROFS_FS_ZIP If you don't want to enable compression feature, say N. +config EROFS_FS_PCPU_KTHREAD + bool "EROFS per-cpu decompression kthread workers" + depends on EROFS_FS_ZIP + help + Saying Y here enables per-CPU kthread workers pool to carry out + async decompression for low latencies on some architectures. + + If unsure, say N. + +config EROFS_FS_PCPU_KTHREAD_HIPRI + bool "EROFS high priority per-CPU kthread workers" + depends on EROFS_FS_ZIP && EROFS_FS_PCPU_KTHREAD + help + This permits EROFS to configure per-CPU kthread workers to run + at higher priority. + + If unsure, say N. diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 7596db389201..9a7318251445 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -7,7 +7,7 @@ #include "zdata.h" #include "compress.h" #include - +#include #include /* @@ -125,24 +125,128 @@ typedef tagptr1_t compressed_page_t; static struct workqueue_struct *z_erofs_workqueue __read_mostly; -void z_erofs_exit_zip_subsystem(void) +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD +static struct kthread_worker __rcu **z_erofs_pcpu_workers; + +static void erofs_destroy_percpu_workers(void) { - destroy_workqueue(z_erofs_workqueue); - z_erofs_destroy_pcluster_pool(); + struct kthread_worker *worker; + unsigned int cpu; + + for_each_possible_cpu(cpu) { + worker = rcu_dereference_protected( + z_erofs_pcpu_workers[cpu], 1); + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], NULL); + if (worker) + kthread_destroy_worker(worker); + } + kfree(z_erofs_pcpu_workers); } -static inline int z_erofs_init_workqueue(void) +static struct kthread_worker *erofs_init_percpu_worker(int cpu) { - const unsigned int onlinecpus = num_possible_cpus(); + struct kthread_worker *worker = + kthread_create_worker_on_cpu(cpu, 0, "erofs_worker/%u", cpu); - /* - * no need to spawn too many threads, limiting threads could minimum - * scheduling overhead, perhaps per-CPU threads should be better? - */ - z_erofs_workqueue = alloc_workqueue("erofs_unzipd", - WQ_UNBOUND | WQ_HIGHPRI, - onlinecpus + onlinecpus / 4); - return z_erofs_workqueue ? 0 : -ENOMEM; + if (IS_ERR(worker)) + return worker; + if (IS_ENABLED(CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI)) + sched_set_fifo_low(worker->task); + else + sched_set_normal(worker->task, 0); + return worker; +} + +static int erofs_init_percpu_workers(void) +{ + struct kthread_worker *worker; + unsigned int cpu; + + z_erofs_pcpu_workers = kcalloc(num_possible_cpus(), + sizeof(struct kthread_worker *), GFP_ATOMIC); + if (!z_erofs_pcpu_workers) + return -ENOMEM; + + for_each_online_cpu(cpu) { /* could miss cpu{off,on}line? */ + worker = erofs_init_percpu_worker(cpu); + if (!IS_ERR(worker)) + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], worker); + } + return 0; +} +#else +static inline void erofs_destroy_percpu_workers(void) {} +static inline int erofs_init_percpu_workers(void) { return 0; } +#endif + +#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_EROFS_FS_PCPU_KTHREAD) +static DEFINE_SPINLOCK(z_erofs_pcpu_worker_lock); +static enum cpuhp_state erofs_cpuhp_state; + +static int erofs_cpu_online(unsigned int cpu) +{ + struct kthread_worker *worker, *old; + + worker = erofs_init_percpu_worker(cpu); + if (IS_ERR(worker)) + return PTR_ERR(worker); + + spin_lock(&z_erofs_pcpu_worker_lock); + old = rcu_dereference_protected(z_erofs_pcpu_workers[cpu], + lockdep_is_held(&z_erofs_pcpu_worker_lock)); + if (!old) + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], worker); + spin_unlock(&z_erofs_pcpu_worker_lock); + if (old) + kthread_destroy_worker(worker); + return 0; +} + +static int erofs_cpu_offline(unsigned int cpu) +{ + struct kthread_worker *worker; + + spin_lock(&z_erofs_pcpu_worker_lock); + worker = rcu_dereference_protected(z_erofs_pcpu_workers[cpu], + lockdep_is_held(&z_erofs_pcpu_worker_lock)); + rcu_assign_pointer(z_erofs_pcpu_workers[cpu], NULL); + spin_unlock(&z_erofs_pcpu_worker_lock); + + synchronize_rcu(); + if (worker) + kthread_destroy_worker(worker); + return 0; +} + +static int erofs_cpu_hotplug_init(void) +{ + int state; + + state = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "fs/erofs:online", erofs_cpu_online, erofs_cpu_offline); + if (state < 0) + return state; + + erofs_cpuhp_state = state; + return 0; +} + +static void erofs_cpu_hotplug_destroy(void) +{ + if (erofs_cpuhp_state) + cpuhp_remove_state_nocalls(erofs_cpuhp_state); +} +#else /* !CONFIG_HOTPLUG_CPU || !CONFIG_EROFS_FS_PCPU_KTHREAD */ +static inline int erofs_cpu_hotplug_init(void) { return 0; } +static inline void erofs_cpu_hotplug_destroy(void) {} +#endif + +void z_erofs_exit_zip_subsystem(void) +{ + erofs_cpu_hotplug_destroy(); + erofs_destroy_percpu_workers(); + destroy_workqueue(z_erofs_workqueue); + z_erofs_destroy_pcluster_pool(); } int __init z_erofs_init_zip_subsystem(void) @@ -150,10 +254,29 @@ int __init z_erofs_init_zip_subsystem(void) int err = z_erofs_create_pcluster_pool(); if (err) - return err; - err = z_erofs_init_workqueue(); + goto out_error_pcluster_pool; + + z_erofs_workqueue = alloc_workqueue("erofs_worker", + WQ_UNBOUND | WQ_HIGHPRI, num_possible_cpus()); + if (!z_erofs_workqueue) + goto out_error_workqueue_init; + + err = erofs_init_percpu_workers(); if (err) - z_erofs_destroy_pcluster_pool(); + goto out_error_pcpu_worker; + + err = erofs_cpu_hotplug_init(); + if (err < 0) + goto out_error_cpuhp_init; + return err; + +out_error_cpuhp_init: + erofs_destroy_percpu_workers(); +out_error_pcpu_worker: + destroy_workqueue(z_erofs_workqueue); +out_error_workqueue_init: + z_erofs_destroy_pcluster_pool(); +out_error_pcluster_pool: return err; } @@ -782,6 +905,12 @@ err_out: } static void z_erofs_decompressqueue_work(struct work_struct *work); +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD +static void z_erofs_decompressqueue_kthread_work(struct kthread_work *work) +{ + z_erofs_decompressqueue_work((struct work_struct *)work); +} +#endif static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, bool sync, int bios) { @@ -799,7 +928,22 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, return; /* Use workqueue and sync decompression for atomic contexts only */ if (in_atomic() || irqs_disabled()) { +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD + struct kthread_worker *worker; + + rcu_read_lock(); + worker = rcu_dereference( + z_erofs_pcpu_workers[raw_smp_processor_id()]); + if (!worker) { + INIT_WORK(&io->u.work, z_erofs_decompressqueue_work); + queue_work(z_erofs_workqueue, &io->u.work); + } else { + kthread_queue_work(worker, &io->u.kthread_work); + } + rcu_read_unlock(); +#else queue_work(z_erofs_workqueue, &io->u.work); +#endif sbi->ctx.readahead_sync_decompress = true; return; } @@ -1207,7 +1351,12 @@ jobqueue_init(struct super_block *sb, *fg = true; goto fg_out; } +#ifdef CONFIG_EROFS_FS_PCPU_KTHREAD + kthread_init_work(&q->u.kthread_work, + z_erofs_decompressqueue_kthread_work); +#else INIT_WORK(&q->u.work, z_erofs_decompressqueue_work); +#endif } else { fg_out: q = fgq; @@ -1348,7 +1497,7 @@ submit_bio_retry: /* * although background is preferred, no one is pending for submission. - * don't issue workqueue for decompression but drop it directly instead. + * don't issue decompression but drop it directly instead. */ if (!*force_fg && !nr_bios) { kvfree(q[JQ_SUBMIT]); diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index 60bf396164ec..f2118ce60e46 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -7,6 +7,7 @@ #ifndef __EROFS_FS_ZDATA_H #define __EROFS_FS_ZDATA_H +#include #include "internal.h" #include "zpvec.h" @@ -92,6 +93,7 @@ struct z_erofs_decompressqueue { union { struct completion done; struct work_struct work; + struct kthread_work kthread_work; } u; }; From 76e536328f69114bf4e08d65554924b483b01224 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 16 Feb 2023 15:13:04 +0300 Subject: [PATCH 2454/4345] UPSTREAM: erofs: fix an error code in z_erofs_init_zip_subsystem() Return -ENOMEM if alloc_workqueue() fails. Don't return success. Fixes: d8a650adf429 ("erofs: add per-cpu threads for decompression as an option") Bug: 271636421 Bug: 278520205 Tests: launch_cvd Change-Id: I49dcf8094655db47ac71ae8967b5402373fc7adc Signed-off-by: Dan Carpenter Reviewed-by: Gao Xiang Link: https://lore.kernel.org/r/Y+4d0FRsUq8jPoOu@kili Signed-off-by: Gao Xiang (cherry picked from commit 8d1b80a79452630f157bf634ae9cfcd9f4eed161) Signed-off-by: Sandeep Dhavale (cherry picked from commit 5004cc655730355d681b333ff5eafd62a4ee02f2) (cherry picked from commit b7f5039f59d8bee886f584c65ca30f14be4b642c) --- fs/erofs/zdata.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 9a7318251445..d4eb0e96b9ac 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -258,8 +258,10 @@ int __init z_erofs_init_zip_subsystem(void) z_erofs_workqueue = alloc_workqueue("erofs_worker", WQ_UNBOUND | WQ_HIGHPRI, num_possible_cpus()); - if (!z_erofs_workqueue) + if (!z_erofs_workqueue) { + err = -ENOMEM; goto out_error_workqueue_init; + } err = erofs_init_percpu_workers(); if (err) From 4078681792c3fc0b0e896ee0b53909a5f3595c48 Mon Sep 17 00:00:00 2001 From: Sandeep Dhavale Date: Wed, 1 Mar 2023 19:03:41 +0000 Subject: [PATCH 2455/4345] ANDROID: Enable percpu high priority kthreads for erofs This change enables 2 configs CONFIG_EROFS_FS_PCPU_KTHREAD CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI With these changes scheduling latency is reduced by ~80% Bug: 271636421 Bug: 278520205 Tests: launch_cvd Change-Id: I91076edd3c7dcbb3497ca0accf98af28c43f4ffb Signed-off-by: Sandeep Dhavale (cherry picked from commit f8e756a6f7019d6c367844ecc449e052c2173f93) (cherry picked from commit ff1fcec189e004540d2abc41bc20102b126e4d7f) --- arch/arm64/configs/gki_defconfig | 2 ++ arch/x86/configs/gki_defconfig | 2 ++ 2 files changed, 4 insertions(+) diff --git a/arch/arm64/configs/gki_defconfig b/arch/arm64/configs/gki_defconfig index d6adcfbd974d..d82e363ddff8 100644 --- a/arch/arm64/configs/gki_defconfig +++ b/arch/arm64/configs/gki_defconfig @@ -591,6 +591,8 @@ CONFIG_PSTORE_CONSOLE=y CONFIG_PSTORE_PMSG=y CONFIG_PSTORE_RAM=y CONFIG_EROFS_FS=y +CONFIG_EROFS_FS_PCPU_KTHREAD=y +CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_CODEPAGE_737=y CONFIG_NLS_CODEPAGE_775=y diff --git a/arch/x86/configs/gki_defconfig b/arch/x86/configs/gki_defconfig index 8c486248e3dd..63419263e5ac 100644 --- a/arch/x86/configs/gki_defconfig +++ b/arch/x86/configs/gki_defconfig @@ -523,6 +523,8 @@ CONFIG_PSTORE_CONSOLE=y CONFIG_PSTORE_PMSG=y CONFIG_PSTORE_RAM=y CONFIG_EROFS_FS=y +CONFIG_EROFS_FS_PCPU_KTHREAD=y +CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_CODEPAGE_737=y CONFIG_NLS_CODEPAGE_775=y From c51b336bd9516e67f3f5b7e4d9706a380e587d24 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 25 Feb 2023 21:39:48 -0800 Subject: [PATCH 2456/4345] gpio: GPIO_REGMAP: select REGMAP instead of depending on it [ Upstream commit d49765b5f4320a402fbc4ed5edfd73d87640f27c ] REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it. Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues. Therefore, change the use of "depends on REGMAP" to "select REGMAP". Fixes: ebe363197e52 ("gpio: add a reusable generic gpio_chip using regmap") Signed-off-by: Randy Dunlap Cc: Michael Walle Cc: Linus Walleij Cc: Bartosz Golaszewski Cc: linux-gpio@vger.kernel.org Acked-by: Michael Walle Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index d1300fc003ed..39f3e1366409 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -99,7 +99,7 @@ config GPIO_GENERIC tristate config GPIO_REGMAP - depends on REGMAP + select REGMAP tristate # put drivers in the right section, in alphabetical order From 176c6b4889195fbe7016d9401175b48c5c9edf68 Mon Sep 17 00:00:00 2001 From: Mohammed Gamal Date: Fri, 17 Feb 2023 22:44:11 +0200 Subject: [PATCH 2457/4345] Drivers: vmbus: Check for channel allocation before looking up relids [ Upstream commit 1eb65c8687316c65140b48fad27133d583178e15 ] relid2channel() assumes vmbus channel array to be allocated when called. However, in cases such as kdump/kexec, not all relids will be reset by the host. When the second kernel boots and if the guest receives a vmbus interrupt during vmbus driver initialization before vmbus_connect() is called, before it finishes, or if it fails, the vmbus interrupt service routine is called which in turn calls relid2channel() and can cause a null pointer dereference. Print a warning and error out in relid2channel() for a channel id that's invalid in the second kernel. Fixes: 8b6a877c060e ("Drivers: hv: vmbus: Replace the per-CPU channel lists with a global array of channels") Signed-off-by: Mohammed Gamal Reviewed-by: Dexuan Cui Link: https://lore.kernel.org/r/20230217204411.212709-1-mgamal@redhat.com Signed-off-by: Wei Liu Signed-off-by: Sasha Levin --- drivers/hv/connection.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index bfd7f00a59ec..683fdfa3e723 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -305,6 +305,10 @@ void vmbus_disconnect(void) */ struct vmbus_channel *relid2channel(u32 relid) { + if (vmbus_connection.channels == NULL) { + pr_warn_once("relid2channel: relid=%d: No channels mapped!\n", relid); + return NULL; + } if (WARN_ON(relid >= MAX_CHANNEL_RELIDS)) return NULL; return READ_ONCE(vmbus_connection.channels[relid]); From d59b83494d1b2d02dcd1226c560f957c19df708f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 22 Mar 2023 22:45:41 +0100 Subject: [PATCH 2458/4345] pwm: cros-ec: Explicitly set .polarity in .get_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 30006b77c7e130e01d1ab2148cc8abf73dfcc4bf ] The driver only supports normal polarity. Complete the implementation of .get_state() by setting .polarity accordingly. Reviewed-by: Guenter Roeck Fixes: 1f0d3bb02785 ("pwm: Add ChromeOS EC PWM driver") Link: https://lore.kernel.org/r/20230228135508.1798428-3-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-cros-ec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c index c1c337969e4e..d4f4a133656c 100644 --- a/drivers/pwm/pwm-cros-ec.c +++ b/drivers/pwm/pwm-cros-ec.c @@ -154,6 +154,7 @@ static void cros_ec_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, state->enabled = (ret > 0); state->period = EC_PWM_MAX_DUTY; + state->polarity = PWM_POLARITY_NORMAL; /* * Note that "disabled" and "duty cycle == 0" are treated the same. If From b43a8939f1e125923fe10492b9ce13133fea0775 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 22 Mar 2023 22:45:43 +0100 Subject: [PATCH 2459/4345] pwm: sprd: Explicitly set .polarity in .get_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2be4dcf6627e1bcbbef8e6ba1811f5127d39202c ] The driver only supports normal polarity. Complete the implementation of .get_state() by setting .polarity accordingly. Fixes: 8aae4b02e8a6 ("pwm: sprd: Add Spreadtrum PWM support") Link: https://lore.kernel.org/r/20230228135508.1798428-5-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-sprd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pwm/pwm-sprd.c b/drivers/pwm/pwm-sprd.c index 9eeb59cb81b6..b23456d38bd2 100644 --- a/drivers/pwm/pwm-sprd.c +++ b/drivers/pwm/pwm-sprd.c @@ -109,6 +109,7 @@ static void sprd_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, duty = val & SPRD_PWM_DUTY_MSK; tmp = (prescale + 1) * NSEC_PER_SEC * duty; state->duty_cycle = DIV_ROUND_CLOSEST_ULL(tmp, chn->clk_rate); + state->polarity = PWM_POLARITY_NORMAL; /* Disable PWM clocks if the PWM channel is not in enable state. */ if (!state->enabled) From 2951229ee7d0f44e252e306dc6f8c13fe987bd21 Mon Sep 17 00:00:00 2001 From: Nico Boehr Date: Mon, 13 Feb 2023 09:55:20 +0100 Subject: [PATCH 2460/4345] KVM: s390: pv: fix external interruption loop not always detected [ Upstream commit 21f27df854008b86349a203bf97fef79bb11f53e ] To determine whether the guest has caused an external interruption loop upon code 20 (external interrupt) intercepts, the ext_new_psw needs to be inspected to see whether external interrupts are enabled. Under non-PV, ext_new_psw can simply be taken from guest lowcore. Under PV, KVM can only access the encrypted guest lowcore and hence the ext_new_psw must not be taken from guest lowcore. handle_external_interrupt() incorrectly did that and hence was not able to reliably tell whether an external interruption loop is happening or not. False negatives cause spurious failures of my kvm-unit-test for extint loops[1] under PV. Since code 20 is only caused under PV if and only if the guest's ext_new_psw is enabled for external interrupts, false positive detection of a external interruption loop can not happen. Fix this issue by instead looking at the guest PSW in the state description. Since the PSW swap for external interrupt is done by the ultravisor before the intercept is caused, this reliably tells whether the guest is enabled for external interrupts in the ext_new_psw. Also update the comments to explain better what is happening. [1] https://lore.kernel.org/kvm/20220812062151.1980937-4-nrb@linux.ibm.com/ Signed-off-by: Nico Boehr Reviewed-by: Janosch Frank Reviewed-by: Christian Borntraeger Fixes: 201ae986ead7 ("KVM: s390: protvirt: Implement interrupt injection") Link: https://lore.kernel.org/r/20230213085520.100756-2-nrb@linux.ibm.com Message-Id: <20230213085520.100756-2-nrb@linux.ibm.com> Signed-off-by: Janosch Frank Signed-off-by: Sasha Levin --- arch/s390/kvm/intercept.c | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 77909d362b78..5be68190901f 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -270,10 +270,18 @@ static int handle_prog(struct kvm_vcpu *vcpu) /** * handle_external_interrupt - used for external interruption interceptions * - * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if - * the new PSW does not have external interrupts disabled. In the first case, - * we've got to deliver the interrupt manually, and in the second case, we - * drop to userspace to handle the situation there. + * This interception occurs if: + * - the CPUSTAT_EXT_INT bit was already set when the external interrupt + * occurred. In this case, the interrupt needs to be injected manually to + * preserve interrupt priority. + * - the external new PSW has external interrupts enabled, which will cause an + * interruption loop. We drop to userspace in this case. + * + * The latter case can be detected by inspecting the external mask bit in the + * external new psw. + * + * Under PV, only the latter case can occur, since interrupt priorities are + * handled in the ultravisor. */ static int handle_external_interrupt(struct kvm_vcpu *vcpu) { @@ -284,10 +292,18 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu) vcpu->stat.exit_external_interrupt++; - rc = read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &newpsw, sizeof(psw_t)); - if (rc) - return rc; - /* We can not handle clock comparator or timer interrupt with bad PSW */ + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + newpsw = vcpu->arch.sie_block->gpsw; + } else { + rc = read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &newpsw, sizeof(psw_t)); + if (rc) + return rc; + } + + /* + * Clock comparator or timer interrupt with external interrupt enabled + * will cause interrupt loop. Drop to userspace. + */ if ((eic == EXT_IRQ_CLK_COMP || eic == EXT_IRQ_CPU_TIMER) && (newpsw.mask & PSW_MASK_EXT)) return -EOPNOTSUPP; From 3fe20515449a80a177526d2ecd13b43f6ee41aeb Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 24 Mar 2023 13:09:24 +0100 Subject: [PATCH 2461/4345] wifi: mac80211: fix invalid drv_sta_pre_rcu_remove calls for non-uploaded sta [ Upstream commit 12b220a6171faf10638ab683a975cadcf1a352d6 ] Avoid potential data corruption issues caused by uninitialized driver private data structures. Reported-by: Brian Coverstone Fixes: 6a9d1b91f34d ("mac80211: add pre-RCU-sync sta removal driver operation") Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20230324120924.38412-3-nbd@nbd.name Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/sta_info.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index d572478c4d68..2e84360990f0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1040,7 +1040,8 @@ static int __must_check __sta_info_destroy_part1(struct sta_info *sta) list_del_rcu(&sta->list); sta->removed = true; - drv_sta_pre_rcu_remove(local, sta->sdata, sta); + if (sta->uploaded) + drv_sta_pre_rcu_remove(local, sta->sdata, sta); if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN && rcu_access_pointer(sdata->u.vlan.sta) == sta) From 94c53d294944d873a922dac151496619a2684af7 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Tue, 28 Sep 2021 19:11:57 +0200 Subject: [PATCH 2462/4345] net: qrtr: combine nameservice into main module [ Upstream commit a365023a76f231cc2fc6e33797e66f3bcaa9f9a9 ] Previously with CONFIG_QRTR=m a separate ns.ko would be built which wasn't done on purpose and should be included in qrtr.ko. Rename qrtr.c to af_qrtr.c so we can build a qrtr.ko with both af_qrtr.c and ns.c. Signed-off-by: Luca Weiss Reviewed-by: Bjorn Andersson Tested-By: Steev Klimaszewski Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20210928171156.6353-1-luca@z3ntu.xyz Signed-off-by: Jakub Kicinski Stable-dep-of: 44d807320000 ("net: qrtr: Fix a refcount bug in qrtr_recvmsg()") Signed-off-by: Sasha Levin --- net/qrtr/Makefile | 3 ++- net/qrtr/{qrtr.c => af_qrtr.c} | 0 2 files changed, 2 insertions(+), 1 deletion(-) rename net/qrtr/{qrtr.c => af_qrtr.c} (100%) diff --git a/net/qrtr/Makefile b/net/qrtr/Makefile index 1b1411d158a7..8e0605f88a73 100644 --- a/net/qrtr/Makefile +++ b/net/qrtr/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_QRTR) := qrtr.o ns.o +obj-$(CONFIG_QRTR) += qrtr.o +qrtr-y := af_qrtr.o ns.o obj-$(CONFIG_QRTR_SMD) += qrtr-smd.o qrtr-smd-y := smd.o diff --git a/net/qrtr/qrtr.c b/net/qrtr/af_qrtr.c similarity index 100% rename from net/qrtr/qrtr.c rename to net/qrtr/af_qrtr.c From 98a9cd82c541ef6cbdb829cd6c05cbbb471e373c Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Thu, 30 Mar 2023 09:25:32 +0800 Subject: [PATCH 2463/4345] net: qrtr: Fix a refcount bug in qrtr_recvmsg() [ Upstream commit 44d807320000db0d0013372ad39b53e12d52f758 ] Syzbot reported a bug as following: refcount_t: addition on 0; use-after-free. ... RIP: 0010:refcount_warn_saturate+0x17c/0x1f0 lib/refcount.c:25 ... Call Trace: __refcount_add include/linux/refcount.h:199 [inline] __refcount_inc include/linux/refcount.h:250 [inline] refcount_inc include/linux/refcount.h:267 [inline] kref_get include/linux/kref.h:45 [inline] qrtr_node_acquire net/qrtr/af_qrtr.c:202 [inline] qrtr_node_lookup net/qrtr/af_qrtr.c:398 [inline] qrtr_send_resume_tx net/qrtr/af_qrtr.c:1003 [inline] qrtr_recvmsg+0x85f/0x990 net/qrtr/af_qrtr.c:1070 sock_recvmsg_nosec net/socket.c:1017 [inline] sock_recvmsg+0xe2/0x160 net/socket.c:1038 qrtr_ns_worker+0x170/0x1700 net/qrtr/ns.c:688 process_one_work+0x991/0x15c0 kernel/workqueue.c:2390 worker_thread+0x669/0x1090 kernel/workqueue.c:2537 It occurs in the concurrent scenario of qrtr_recvmsg() and qrtr_endpoint_unregister() as following: cpu0 cpu1 qrtr_recvmsg qrtr_endpoint_unregister qrtr_send_resume_tx qrtr_node_release qrtr_node_lookup mutex_lock(&qrtr_node_lock) spin_lock_irqsave(&qrtr_nodes_lock, ) refcount_dec_and_test(&node->ref) [node->ref == 0] radix_tree_lookup [node != NULL] __qrtr_node_release qrtr_node_acquire spin_lock_irqsave(&qrtr_nodes_lock, ) kref_get(&node->ref) [WARNING] ... mutex_unlock(&qrtr_node_lock) Use qrtr_node_lock to protect qrtr_node_lookup() implementation, this is actually improving the protection of node reference. Fixes: 0a7e0d0ef054 ("net: qrtr: Migrate node lookup tree to spinlock") Reported-by: syzbot+a7492efaa5d61b51db23@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=a7492efaa5d61b51db23 Signed-off-by: Ziyang Xuan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/qrtr/af_qrtr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 13448ca5aeff..d0f0b2b8dce2 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -388,10 +388,12 @@ static struct qrtr_node *qrtr_node_lookup(unsigned int nid) struct qrtr_node *node; unsigned long flags; + mutex_lock(&qrtr_node_lock); spin_lock_irqsave(&qrtr_nodes_lock, flags); node = radix_tree_lookup(&qrtr_nodes, nid); node = qrtr_node_acquire(node); spin_unlock_irqrestore(&qrtr_nodes_lock, flags); + mutex_unlock(&qrtr_node_lock); return node; } From ec81049f0957b2539ec2f449874c2392add01b2a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 30 Mar 2023 17:45:02 +0000 Subject: [PATCH 2464/4345] icmp: guard against too small mtu [ Upstream commit 7d63b67125382ff0ffdfca434acbc94a38bd092b ] syzbot was able to trigger a panic [1] in icmp_glue_bits(), or more exactly in skb_copy_and_csum_bits() There is no repro yet, but I think the issue is that syzbot manages to lower device mtu to a small value, fooling __icmp_send() __icmp_send() must make sure there is enough room for the packet to include at least the headers. We might in the future refactor skb_copy_and_csum_bits() and its callers to no longer crash when something bad happens. [1] kernel BUG at net/core/skbuff.c:3343 ! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 15766 Comm: syz-executor.0 Not tainted 6.3.0-rc4-syzkaller-00039-gffe78bbd5121 #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-2 04/01/2014 RIP: 0010:skb_copy_and_csum_bits+0x798/0x860 net/core/skbuff.c:3343 Code: f0 c1 c8 08 41 89 c6 e9 73 ff ff ff e8 61 48 d4 f9 e9 41 fd ff ff 48 8b 7c 24 48 e8 52 48 d4 f9 e9 c3 fc ff ff e8 c8 27 84 f9 <0f> 0b 48 89 44 24 28 e8 3c 48 d4 f9 48 8b 44 24 28 e9 9d fb ff ff RSP: 0018:ffffc90000007620 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 00000000000001e8 RCX: 0000000000000100 RDX: ffff8880276f6280 RSI: ffffffff87fdd138 RDI: 0000000000000005 RBP: 0000000000000000 R08: 0000000000000005 R09: 0000000000000000 R10: 00000000000001e8 R11: 0000000000000001 R12: 000000000000003c R13: 0000000000000000 R14: ffff888028244868 R15: 0000000000000b0e FS: 00007fbc81f1c700(0000) GS:ffff88802ca00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2df43000 CR3: 00000000744db000 CR4: 0000000000150ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: icmp_glue_bits+0x7b/0x210 net/ipv4/icmp.c:353 __ip_append_data+0x1d1b/0x39f0 net/ipv4/ip_output.c:1161 ip_append_data net/ipv4/ip_output.c:1343 [inline] ip_append_data+0x115/0x1a0 net/ipv4/ip_output.c:1322 icmp_push_reply+0xa8/0x440 net/ipv4/icmp.c:370 __icmp_send+0xb80/0x1430 net/ipv4/icmp.c:765 ipv4_send_dest_unreach net/ipv4/route.c:1239 [inline] ipv4_link_failure+0x5a9/0x9e0 net/ipv4/route.c:1246 dst_link_failure include/net/dst.h:423 [inline] arp_error_report+0xcb/0x1c0 net/ipv4/arp.c:296 neigh_invalidate+0x20d/0x560 net/core/neighbour.c:1079 neigh_timer_handler+0xc77/0xff0 net/core/neighbour.c:1166 call_timer_fn+0x1a0/0x580 kernel/time/timer.c:1700 expire_timers+0x29b/0x4b0 kernel/time/timer.c:1751 __run_timers kernel/time/timer.c:2022 [inline] Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+d373d60fddbdc915e666@syzkaller.appspotmail.com Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230330174502.1915328-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/icmp.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index a1aacf5e75a6..0bbc047e8f6e 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -755,6 +755,11 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, room = 576; room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen; room -= sizeof(struct icmphdr); + /* Guard against tiny mtu. We need to include at least one + * IP network header for this message to make any sense. + */ + if (room <= (int)sizeof(struct iphdr)) + goto ende; icmp_param.data_len = skb_in->len - icmp_param.offset; if (icmp_param.data_len > room) From efda95cebfdd72f66c3d927641538eeaa0e7ace6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 30 Mar 2023 19:21:44 -0700 Subject: [PATCH 2465/4345] net: don't let netpoll invoke NAPI if in xmit context [ Upstream commit 275b471e3d2daf1472ae8fa70dc1b50c9e0b9e75 ] Commit 0db3dc73f7a3 ("[NETPOLL]: tx lock deadlock fix") narrowed down the region under netif_tx_trylock() inside netpoll_send_skb(). (At that point in time netif_tx_trylock() would lock all queues of the device.) Taking the tx lock was problematic because driver's cleanup method may take the same lock. So the change made us hold the xmit lock only around xmit, and expected the driver to take care of locking within ->ndo_poll_controller(). Unfortunately this only works if netpoll isn't itself called with the xmit lock already held. Netpoll code is careful and uses trylock(). The drivers, however, may be using plain lock(). Printing while holding the xmit lock is going to result in rare deadlocks. Luckily we record the xmit lock owners, so we can scan all the queues, the same way we scan NAPI owners. If any of the xmit locks is held by the local CPU we better not attempt any polling. It would be nice if we could narrow down the check to only the NAPIs and the queue we're trying to use. I don't see a way to do that now. Reported-by: Roman Gushchin Fixes: 0db3dc73f7a3 ("[NETPOLL]: tx lock deadlock fix") Signed-off-by: Jakub Kicinski Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/netpoll.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 960948290001..2ad22511b9c6 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -137,6 +137,20 @@ static void queue_process(struct work_struct *work) } } +static int netif_local_xmit_active(struct net_device *dev) +{ + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) + return 1; + } + + return 0; +} + static void poll_one_napi(struct napi_struct *napi) { int work; @@ -183,7 +197,10 @@ void netpoll_poll_dev(struct net_device *dev) if (!ni || down_trylock(&ni->dev_lock)) return; - if (!netif_running(dev)) { + /* Some drivers will take the same locks in poll and xmit, + * we can't poll if local CPU is already in xmit. + */ + if (!netif_running(dev) || netif_local_xmit_active(dev)) { up(&ni->dev_lock); return; } From b4b6dfad41aaae9e36e44327b18d5cf4b20dd2ce Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 1 Apr 2023 19:09:57 -0400 Subject: [PATCH 2466/4345] sctp: check send stream number after wait_for_sndbuf [ Upstream commit 2584024b23552c00d95b50255e47bd18d306d31a ] This patch fixes a corner case where the asoc out stream count may change after wait_for_sndbuf. When the main thread in the client starts a connection, if its out stream count is set to N while the in stream count in the server is set to N - 2, another thread in the client keeps sending the msgs with stream number N - 1, and waits for sndbuf before processing INIT_ACK. However, after processing INIT_ACK, the out stream count in the client is shrunk to N - 2, the same to the in stream count in the server. The crash occurs when the thread waiting for sndbuf is awake and sends the msg in a non-existing stream(N - 1), the call trace is as below: KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] Call Trace: sctp_cmd_send_msg net/sctp/sm_sideeffect.c:1114 [inline] sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1777 [inline] sctp_side_effects net/sctp/sm_sideeffect.c:1199 [inline] sctp_do_sm+0x197d/0x5310 net/sctp/sm_sideeffect.c:1170 sctp_primitive_SEND+0x9f/0xc0 net/sctp/primitive.c:163 sctp_sendmsg_to_asoc+0x10eb/0x1a30 net/sctp/socket.c:1868 sctp_sendmsg+0x8d4/0x1d90 net/sctp/socket.c:2026 inet_sendmsg+0x9d/0xe0 net/ipv4/af_inet.c:825 sock_sendmsg_nosec net/socket.c:722 [inline] sock_sendmsg+0xde/0x190 net/socket.c:745 The fix is to add an unlikely check for the send stream number after the thread wakes up from the wait_for_sndbuf. Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations") Reported-by: syzbot+47c24ca20a2fa01f082e@syzkaller.appspotmail.com Signed-off-by: Xin Long Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sctp/socket.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e9b4ea3d934f..3a68d65f7d15 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1831,6 +1831,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) goto err; + if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { + err = -EINVAL; + goto err; + } } if (sctp_state(asoc, CLOSED)) { From ff2565fb8f19a0904e6f72af576294443fdd7f0d Mon Sep 17 00:00:00 2001 From: Sricharan Ramabadhran Date: Mon, 3 Apr 2023 12:28:51 +0530 Subject: [PATCH 2467/4345] net: qrtr: Do not do DEL_SERVER broadcast after DEL_CLIENT [ Upstream commit 839349d13905927d8a567ca4d21d88c82028e31d ] On the remote side, when QRTR socket is removed, af_qrtr will call qrtr_port_remove() which broadcasts the DEL_CLIENT packet to all neighbours including local NS. NS upon receiving the DEL_CLIENT packet, will remove the lookups associated with the node:port and broadcasts the DEL_SERVER packet. But on the host side, due to the arrival of the DEL_CLIENT packet, the NS would've already deleted the server belonging to that port. So when the remote's NS again broadcasts the DEL_SERVER for that port, it throws below error message on the host: "failed while handling packet from 2:-2" So fix this error by not broadcasting the DEL_SERVER packet when the DEL_CLIENT packet gets processed." Fixes: 0c2204a4ad71 ("net: qrtr: Migrate nameservice to kernel from userspace") Reviewed-by: Manivannan Sadhasivam Signed-off-by: Ram Kumar Dharuman Signed-off-by: Sricharan Ramabadhran Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/qrtr/ns.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index fe81e0385168..713e9940d88b 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -273,7 +273,7 @@ err: return NULL; } -static int server_del(struct qrtr_node *node, unsigned int port) +static int server_del(struct qrtr_node *node, unsigned int port, bool bcast) { struct qrtr_lookup *lookup; struct qrtr_server *srv; @@ -286,7 +286,7 @@ static int server_del(struct qrtr_node *node, unsigned int port) radix_tree_delete(&node->servers, port); /* Broadcast the removal of local servers */ - if (srv->node == qrtr_ns.local_node) + if (srv->node == qrtr_ns.local_node && bcast) service_announce_del(&qrtr_ns.bcast_sq, srv); /* Announce the service's disappearance to observers */ @@ -372,7 +372,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) } slot = radix_tree_iter_resume(slot, &iter); rcu_read_unlock(); - server_del(node, srv->port); + server_del(node, srv->port, true); rcu_read_lock(); } rcu_read_unlock(); @@ -458,10 +458,13 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, kfree(lookup); } - /* Remove the server belonging to this port */ + /* Remove the server belonging to this port but don't broadcast + * DEL_SERVER. Neighbours would've already removed the server belonging + * to this port due to the DEL_CLIENT broadcast from qrtr_port_remove(). + */ node = node_get(node_id); if (node) - server_del(node, port); + server_del(node, port, false); /* Advertise the removal of this client to all local servers */ local_node = node_get(qrtr_ns.local_node); @@ -574,7 +577,7 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from, if (!node) return -ENOENT; - return server_del(node, port); + return server_del(node, port, true); } static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, From 605b056d63302ae84eb136e88d4df49124bd5e0d Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Mon, 3 Apr 2023 15:34:17 +0800 Subject: [PATCH 2468/4345] ipv6: Fix an uninit variable access bug in __ip6_make_skb() [ Upstream commit ea30388baebcce37fd594d425a65037ca35e59e8 ] Syzbot reported a bug as following: ===================================================== BUG: KMSAN: uninit-value in arch_atomic64_inc arch/x86/include/asm/atomic64_64.h:88 [inline] BUG: KMSAN: uninit-value in arch_atomic_long_inc include/linux/atomic/atomic-long.h:161 [inline] BUG: KMSAN: uninit-value in atomic_long_inc include/linux/atomic/atomic-instrumented.h:1429 [inline] BUG: KMSAN: uninit-value in __ip6_make_skb+0x2f37/0x30f0 net/ipv6/ip6_output.c:1956 arch_atomic64_inc arch/x86/include/asm/atomic64_64.h:88 [inline] arch_atomic_long_inc include/linux/atomic/atomic-long.h:161 [inline] atomic_long_inc include/linux/atomic/atomic-instrumented.h:1429 [inline] __ip6_make_skb+0x2f37/0x30f0 net/ipv6/ip6_output.c:1956 ip6_finish_skb include/net/ipv6.h:1122 [inline] ip6_push_pending_frames+0x10e/0x550 net/ipv6/ip6_output.c:1987 rawv6_push_pending_frames+0xb12/0xb90 net/ipv6/raw.c:579 rawv6_sendmsg+0x297e/0x2e60 net/ipv6/raw.c:922 inet_sendmsg+0x101/0x180 net/ipv4/af_inet.c:827 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0xa8e/0xe70 net/socket.c:2476 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2530 __sys_sendmsg net/socket.c:2559 [inline] __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x367/0x540 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook mm/slab.h:766 [inline] slab_alloc_node mm/slub.c:3452 [inline] __kmem_cache_alloc_node+0x71f/0xce0 mm/slub.c:3491 __do_kmalloc_node mm/slab_common.c:967 [inline] __kmalloc_node_track_caller+0x114/0x3b0 mm/slab_common.c:988 kmalloc_reserve net/core/skbuff.c:492 [inline] __alloc_skb+0x3af/0x8f0 net/core/skbuff.c:565 alloc_skb include/linux/skbuff.h:1270 [inline] __ip6_append_data+0x51c1/0x6bb0 net/ipv6/ip6_output.c:1684 ip6_append_data+0x411/0x580 net/ipv6/ip6_output.c:1854 rawv6_sendmsg+0x2882/0x2e60 net/ipv6/raw.c:915 inet_sendmsg+0x101/0x180 net/ipv4/af_inet.c:827 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0xa8e/0xe70 net/socket.c:2476 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2530 __sys_sendmsg net/socket.c:2559 [inline] __do_sys_sendmsg net/socket.c:2568 [inline] __se_sys_sendmsg net/socket.c:2566 [inline] __x64_sys_sendmsg+0x367/0x540 net/socket.c:2566 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd It is because icmp6hdr does not in skb linear region under the scenario of SOCK_RAW socket. Access icmp6_hdr(skb)->icmp6_type directly will trigger the uninit variable access bug. Use a local variable icmp6_type to carry the correct value in different scenarios. Fixes: 14878f75abd5 ("[IPV6]: Add ICMPMsgStats MIB (RFC 4293) [rev 2]") Reported-by: syzbot+8257f4dcef79de670baf@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=3d605ec1d0a7f2a269a1a6936ac7f2b85975ee9c Signed-off-by: Ziyang Xuan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/ip6_output.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e427f5040a08..c62e44224bf8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1925,8 +1925,13 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + u8 icmp6_type; - ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + icmp6_type = fl6->fl6_icmp_type; + else + icmp6_type = icmp6_hdr(skb)->icmp6_type; + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } From d8c8476c14330cf0e12cd42a8e3c5943d95d81ef Mon Sep 17 00:00:00 2001 From: Dhruva Gole Date: Mon, 3 Apr 2023 12:54:43 +0530 Subject: [PATCH 2469/4345] gpio: davinci: Add irq chip flag to skip set wake [ Upstream commit 7b75c4703609a3ebaf67271813521bc0281e1ec1 ] Add the IRQCHIP_SKIP_SET_WAKE flag since there are no special IRQ Wake bits that can be set to enable wakeup IRQ. Fixes: 3d9edf09d452 ("[ARM] 4457/2: davinci: GPIO support") Signed-off-by: Dhruva Gole Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpio-davinci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 6f2138503726..80597e90de9c 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -326,7 +326,7 @@ static struct irq_chip gpio_irqchip = { .irq_enable = gpio_irq_enable, .irq_disable = gpio_irq_disable, .irq_set_type = gpio_irq_type, - .flags = IRQCHIP_SET_TYPE_MASKED, + .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE, }; static void gpio_irq_handler(struct irq_desc *desc) From bdbbd3fa58f8e9292905a4a10b1da55b2f27e979 Mon Sep 17 00:00:00 2001 From: Siddharth Vadapalli Date: Mon, 3 Apr 2023 14:33:21 +0530 Subject: [PATCH 2470/4345] net: ethernet: ti: am65-cpsw: Fix mdio cleanup in probe [ Upstream commit c6b486fb33680ad5a3a6390ce693c835caaae3f7 ] In the am65_cpsw_nuss_probe() function's cleanup path, the call to of_platform_device_destroy() for the common->mdio_dev device is invoked unconditionally. It is possible that either the MDIO node is not present in the device-tree, or the MDIO node is disabled in the device-tree. In both these cases, the MDIO device is not created, resulting in a NULL pointer dereference when the of_platform_device_destroy() function is invoked on the common->mdio_dev device on the cleanup path. Fix this by ensuring that the common->mdio_dev device exists, before attempting to invoke of_platform_device_destroy(). Fixes: a45cfcc69a25 ("net: ethernet: ti: am65-cpsw-nuss: use of_platform_device_create() for mdio") Signed-off-by: Siddharth Vadapalli Reviewed-by: Roger Quadros Link: https://lore.kernel.org/r/20230403090321.835877-1-s-vadapalli@ti.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 4074310abcff..e4af1f506b83 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2153,7 +2153,8 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) return 0; err_of_clear: - of_platform_device_destroy(common->mdio_dev, NULL); + if (common->mdio_dev) + of_platform_device_destroy(common->mdio_dev, NULL); err_pm_clear: pm_runtime_put_sync(dev); pm_runtime_disable(dev); @@ -2179,7 +2180,8 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev) */ am65_cpsw_nuss_cleanup_ndev(common); - of_platform_device_destroy(common->mdio_dev, NULL); + if (common->mdio_dev) + of_platform_device_destroy(common->mdio_dev, NULL); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); From 890517a4a2550a28a33c73f38ea4958f46faaf0d Mon Sep 17 00:00:00 2001 From: Corinna Vinschen Date: Mon, 3 Apr 2023 14:11:20 +0200 Subject: [PATCH 2471/4345] net: stmmac: fix up RX flow hash indirection table when setting channels [ Upstream commit 218c597325f4faf7b7a6049233a30d7842b5b2dc ] stmmac_reinit_queues() fails to fix up the RX hash. Even if the number of channels gets restricted, the output of `ethtool -x' indicates that all RX queues are used: $ ethtool -l enp0s29f2 Channel parameters for enp0s29f2: Pre-set maximums: RX: 8 TX: 8 Other: n/a Combined: n/a Current hardware settings: RX: 8 TX: 8 Other: n/a Combined: n/a $ ethtool -x enp0s29f2 RX flow hash indirection table for enp0s29f2 with 8 RX ring(s): 0: 0 1 2 3 4 5 6 7 8: 0 1 2 3 4 5 6 7 [...] $ ethtool -L enp0s29f2 rx 3 $ ethtool -x enp0s29f2 RX flow hash indirection table for enp0s29f2 with 3 RX ring(s): 0: 0 1 2 3 4 5 6 7 8: 0 1 2 3 4 5 6 7 [...] Fix this by setting the indirection table according to the number of specified queues. The result is now as expected: $ ethtool -L enp0s29f2 rx 3 $ ethtool -x enp0s29f2 RX flow hash indirection table for enp0s29f2 with 3 RX ring(s): 0: 0 1 2 0 1 2 0 1 8: 2 0 1 2 0 1 2 0 [...] Tested on Intel Elkhart Lake. Fixes: 0366f7e06a6b ("net: stmmac: add ethtool support for get/set channels") Signed-off-by: Corinna Vinschen Link: https://lore.kernel.org/r/20230403121120.489138-1-vinschen@redhat.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 04c59102a286..de66406c5057 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4940,7 +4940,7 @@ static void stmmac_napi_del(struct net_device *dev) int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) { struct stmmac_priv *priv = netdev_priv(dev); - int ret = 0; + int ret = 0, i; if (netif_running(dev)) stmmac_release(dev); @@ -4949,6 +4949,10 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) priv->plat->rx_queues_to_use = rx_cnt; priv->plat->tx_queues_to_use = tx_cnt; + if (!netif_is_rxfh_configured(dev)) + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = ethtool_rxfh_indir_default(i, + rx_cnt); stmmac_napi_add(dev); From a3c4aa48e5f2214326878692e6cbaca23d919c1b Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 30 Mar 2023 14:24:27 -0400 Subject: [PATCH 2472/4345] sunrpc: only free unix grouplist after RCU settles [ Upstream commit 5085e41f9e83a1bec51da1f20b54f2ec3a13a3fe ] While the unix_gid object is rcu-freed, the group_info list that it contains is not. Ensure that we only put the group list reference once we are really freeing the unix_gid object. Reported-by: Zhi Li Link: https://bugzilla.redhat.com/show_bug.cgi?id=2183056 Signed-off-by: Jeff Layton Fixes: fd5d2f78261b ("SUNRPC: Make server side AUTH_UNIX use lockless lookups") Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- net/sunrpc/svcauth_unix.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 97c0bddba7a3..60754a292589 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -424,14 +424,23 @@ static int unix_gid_hash(kuid_t uid) return hash_long(from_kuid(&init_user_ns, uid), GID_HASHBITS); } +static void unix_gid_free(struct rcu_head *rcu) +{ + struct unix_gid *ug = container_of(rcu, struct unix_gid, rcu); + struct cache_head *item = &ug->h; + + if (test_bit(CACHE_VALID, &item->flags) && + !test_bit(CACHE_NEGATIVE, &item->flags)) + put_group_info(ug->gi); + kfree(ug); +} + static void unix_gid_put(struct kref *kref) { struct cache_head *item = container_of(kref, struct cache_head, ref); struct unix_gid *ug = container_of(item, struct unix_gid, h); - if (test_bit(CACHE_VALID, &item->flags) && - !test_bit(CACHE_NEGATIVE, &item->flags)) - put_group_info(ug->gi); - kfree_rcu(ug, rcu); + + call_rcu(&ug->rcu, unix_gid_free); } static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew) From 07216da8fb1d48351fe6ae2c3f7bef297b20ba7b Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Sat, 1 Apr 2023 13:22:08 -0700 Subject: [PATCH 2473/4345] NFSD: callback request does not use correct credential for AUTH_SYS [ Upstream commit 7de82c2f36fb26aa78440bbf0efcf360b691d98b ] Currently callback request does not use the credential specified in CREATE_SESSION if the security flavor for the back channel is AUTH_SYS. Problem was discovered by pynfs 4.1 DELEG5 and DELEG7 test with error: DELEG5 st_delegation.testCBSecParms : FAILURE expected callback with uid, gid == 17, 19, got 0, 0 Signed-off-by: Dai Ngo Reviewed-by: Jeff Layton Fixes: 8276c902bbe9 ("SUNRPC: remove uid and gid from struct auth_cred") Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- fs/nfsd/nfs4callback.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index af2064e36ac6..f5b7ad0847f2 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -875,8 +875,8 @@ static const struct cred *get_backchannel_cred(struct nfs4_client *clp, struct r if (!kcred) return NULL; - kcred->uid = ses->se_cb_sec.uid; - kcred->gid = ses->se_cb_sec.gid; + kcred->fsuid = ses->se_cb_sec.uid; + kcred->fsgid = ses->se_cb_sec.gid; return kcred; } } From b4b4f17aa46c025da77aed5133b08971959c9684 Mon Sep 17 00:00:00 2001 From: Wayne Chang Date: Mon, 27 Mar 2023 17:55:48 +0800 Subject: [PATCH 2474/4345] usb: xhci: tegra: fix sleep in atomic call commit 4c7f9d2e413dc06a157c4e5dccde84aaf4655eb3 upstream. When we set the dual-role port to Host mode, we observed the following splat: [ 167.057718] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:229 [ 167.057872] Workqueue: events tegra_xusb_usb_phy_work [ 167.057954] Call trace: [ 167.057962] dump_backtrace+0x0/0x210 [ 167.057996] show_stack+0x30/0x50 [ 167.058020] dump_stack_lvl+0x64/0x84 [ 167.058065] dump_stack+0x14/0x34 [ 167.058100] __might_resched+0x144/0x180 [ 167.058140] __might_sleep+0x64/0xd0 [ 167.058171] slab_pre_alloc_hook.constprop.0+0xa8/0x110 [ 167.058202] __kmalloc_track_caller+0x74/0x2b0 [ 167.058233] kvasprintf+0xa4/0x190 [ 167.058261] kasprintf+0x58/0x90 [ 167.058285] tegra_xusb_find_port_node.isra.0+0x58/0xd0 [ 167.058334] tegra_xusb_find_port+0x38/0xa0 [ 167.058380] tegra_xusb_padctl_get_usb3_companion+0x38/0xd0 [ 167.058430] tegra_xhci_id_notify+0x8c/0x1e0 [ 167.058473] notifier_call_chain+0x88/0x100 [ 167.058506] atomic_notifier_call_chain+0x44/0x70 [ 167.058537] tegra_xusb_usb_phy_work+0x60/0xd0 [ 167.058581] process_one_work+0x1dc/0x4c0 [ 167.058618] worker_thread+0x54/0x410 [ 167.058650] kthread+0x188/0x1b0 [ 167.058672] ret_from_fork+0x10/0x20 The function tegra_xusb_padctl_get_usb3_companion eventually calls tegra_xusb_find_port and this in turn calls kasprintf which might sleep and so cannot be called from an atomic context. Fix this by moving the call to tegra_xusb_padctl_get_usb3_companion to the tegra_xhci_id_work function where it is really needed. Fixes: f836e7843036 ("usb: xhci-tegra: Add OTG support") Cc: stable@vger.kernel.org Signed-off-by: Wayne Chang Signed-off-by: Haotien Hsu Link: https://lore.kernel.org/r/20230327095548.1599470-1-haotienh@nvidia.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-tegra.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 246a3d274142..9fa4f8f39830 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1175,6 +1175,9 @@ static void tegra_xhci_id_work(struct work_struct *work) mutex_unlock(&tegra->lock); + tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl, + tegra->otg_usb2_port); + if (tegra->host_mode) { /* switch to host mode */ if (tegra->otg_usb3_port >= 0) { @@ -1243,9 +1246,6 @@ static int tegra_xhci_id_notify(struct notifier_block *nb, } tegra->otg_usb2_port = tegra_xusb_get_usb2_port(tegra, usbphy); - tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion( - tegra->padctl, - tegra->otg_usb2_port); tegra->host_mode = (usbphy->last_event == USB_EVENT_ID) ? true : false; From ec20260950afe22189fab8c92a241ac641b03f8f Mon Sep 17 00:00:00 2001 From: D Scott Phillips Date: Thu, 30 Mar 2023 17:30:54 +0300 Subject: [PATCH 2475/4345] xhci: also avoid the XHCI_ZERO_64B_REGS quirk with a passthrough iommu commit ecaa4902439298f6b0e29f47424a86b310a9ff4f upstream. Previously the quirk was skipped when no iommu was present. The same rationale for skipping the quirk also applies in the iommu.passthrough=1 case. Skip applying the XHCI_ZERO_64B_REGS quirk if the device's iommu domain is passthrough. Fixes: 12de0a35c996 ("xhci: Add quirk to zero 64bit registers on Renesas PCIe controllers") Cc: stable Signed-off-by: D Scott Phillips Acked-by: Marc Zyngier Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230330143056.1390020-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 473b0b64dd57..b069fe3f8ab0 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -226,6 +227,7 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us) static void xhci_zero_64b_regs(struct xhci_hcd *xhci) { struct device *dev = xhci_to_hcd(xhci)->self.sysdev; + struct iommu_domain *domain; int err, i; u64 val; u32 intrs; @@ -244,7 +246,9 @@ static void xhci_zero_64b_regs(struct xhci_hcd *xhci) * an iommu. Doing anything when there is no iommu is definitely * unsafe... */ - if (!(xhci->quirks & XHCI_ZERO_64B_REGS) || !device_iommu_mapped(dev)) + domain = iommu_get_domain_for_dev(dev); + if (!(xhci->quirks & XHCI_ZERO_64B_REGS) || !domain || + domain->type == IOMMU_DOMAIN_IDENTITY) return; xhci_info(xhci, "Zeroing 64bit base registers, expecting fault\n"); From 4be2b71e9d368d5b0aca390a576465de14d401a7 Mon Sep 17 00:00:00 2001 From: Kees Jan Koster Date: Sat, 18 Feb 2023 15:18:30 +0100 Subject: [PATCH 2476/4345] USB: serial: cp210x: add Silicon Labs IFS-USB-DATACABLE IDs commit 71f8afa2b66e356f435b6141b4a9ccf953e18356 upstream. The Silicon Labs IFS-USB-DATACABLE is used in conjunction with for example the Quint UPSes. It is used to enable Modbus communication with the UPS to query configuration, power and battery status. Signed-off-by: Kees Jan Koster Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 9ee0fa775612..045e24174e1a 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -124,6 +124,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */ { USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */ { USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */ + { USB_DEVICE(0x10C4, 0x82AA) }, /* Silicon Labs IFS-USB-DATACABLE used with Quint UPS */ { USB_DEVICE(0x10C4, 0x82EF) }, /* CESINEL FALCO 6105 AC Power Supply */ { USB_DEVICE(0x10C4, 0x82F1) }, /* CESINEL MEDCAL EFD Earth Fault Detector */ { USB_DEVICE(0x10C4, 0x82F2) }, /* CESINEL MEDCAL ST Network Analyzer */ From 9d1f2a6b8d9a3fab2611e5bedeeb21da5b4bd032 Mon Sep 17 00:00:00 2001 From: RD Babiera Date: Wed, 29 Mar 2023 21:51:59 +0000 Subject: [PATCH 2477/4345] usb: typec: altmodes/displayport: Fix configure initial pin assignment commit eddebe39602efe631b83ff8d03f26eba12cfd760 upstream. While determining the initial pin assignment to be sent in the configure message, using the DP_PIN_ASSIGN_DP_ONLY_MASK mask causes the DFP_U to send both Pin Assignment C and E when both are supported by the DFP_U and UFP_U. The spec (Table 5-7 DFP_U Pin Assignment Selection Mandates, VESA DisplayPort Alt Mode Standard v2.0) indicates that the DFP_U never selects Pin Assignment E when Pin Assignment C is offered. Update the DP_PIN_ASSIGN_DP_ONLY_MASK conditional to intially select only Pin Assignment C if it is available. Fixes: 0e3bb7d6894d ("usb: typec: Add driver for DisplayPort alternate mode") Cc: stable@vger.kernel.org Signed-off-by: RD Babiera Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230329215159.2046932-1-rdbabiera@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index e8eaca5a84db..07b656172068 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -101,8 +101,12 @@ static int dp_altmode_configure(struct dp_altmode *dp, u8 con) if (dp->data.status & DP_STATUS_PREFER_MULTI_FUNC && pin_assign & DP_PIN_ASSIGN_MULTI_FUNC_MASK) pin_assign &= DP_PIN_ASSIGN_MULTI_FUNC_MASK; - else if (pin_assign & DP_PIN_ASSIGN_DP_ONLY_MASK) + else if (pin_assign & DP_PIN_ASSIGN_DP_ONLY_MASK) { pin_assign &= DP_PIN_ASSIGN_DP_ONLY_MASK; + /* Default to pin assign C if available */ + if (pin_assign & BIT(DP_PIN_ASSIGN_C)) + pin_assign = BIT(DP_PIN_ASSIGN_C); + } if (!pin_assign) return -EINVAL; From e6655d483766d31e22f32b8f37c09588b22d2adc Mon Sep 17 00:00:00 2001 From: Enrico Sau Date: Tue, 14 Mar 2023 10:00:59 +0100 Subject: [PATCH 2478/4345] USB: serial: option: add Telit FE990 compositions commit 773e8e7d07b753474b2ccd605ff092faaa9e65b9 upstream. Add the following Telit FE990 compositions: 0x1080: tty, adb, rmnet, tty, tty, tty, tty 0x1081: tty, adb, mbim, tty, tty, tty, tty 0x1082: rndis, tty, adb, tty, tty, tty, tty 0x1083: tty, adb, ecm, tty, tty, tty, tty Signed-off-by: Enrico Sau Link: https://lore.kernel.org/r/20230314090059.77876-1-enrico.sau@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 14a7af7f3bcd..7c6740d667a5 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1300,6 +1300,14 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990 (PCIe) */ .driver_info = RSVD(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff), /* Telit FE990 (rmnet) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff), /* Telit FE990 (MBIM) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1082, 0xff), /* Telit FE990 (RNDIS) */ + .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff), /* Telit FE990 (ECM) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), From 52a003870ee273d79d0768fb4fdc1585d880199d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Tue, 28 Mar 2023 20:41:31 +0200 Subject: [PATCH 2479/4345] USB: serial: option: add Quectel RM500U-CN modem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 7708a3858e69db91a8b69487994f33b96d20192a upstream. This modem supports several modes with a class network function and a number of serial functions, all using ff/00/00 The device ID is the same in all modes. RNDIS mode ---------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0 D: Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0900 Rev= 4.04 S: Manufacturer=Quectel S: Product=RM500U-CN S: SerialNumber=0123456789ABCDEF C:* #Ifs= 7 Cfg#= 1 Atr=c0 MxPwr=500mA A: FirstIf#= 0 IfCount= 2 Cls=e0(wlcon) Sub=01 Prot=03 I:* If#= 0 Alt= 0 #EPs= 1 Cls=e0(wlcon) Sub=01 Prot=03 Driver=rndis_host E: Ad=82(I) Atr=03(Int.) MxPS= 8 Ivl=32ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=rndis_host E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms ECM mode -------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0 D: Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0900 Rev= 4.04 S: Manufacturer=Quectel S: Product=RM500U-CN S: SerialNumber=0123456789ABCDEF C:* #Ifs= 7 Cfg#= 1 Atr=c0 MxPwr=500mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=06 Prot=00 I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=06 Prot=00 Driver=cdc_ether E: Ad=82(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms NCM mode -------- T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 5 Spd=480 MxCh= 0 D: Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=0900 Rev= 4.04 S: Manufacturer=Quectel S: Product=RM500U-CN S: SerialNumber=0123456789ABCDEF C:* #Ifs= 7 Cfg#= 1 Atr=c0 MxPwr=500mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0d Prot=00 I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0d Prot=00 Driver=cdc_ncm E: Ad=82(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms Reported-by: Andrew Green Cc: stable@vger.kernel.org Signed-off-by: Bjørn Mork Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 7c6740d667a5..da8b7bd39703 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1198,6 +1198,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, 0x0900, 0xff, 0, 0), /* RM500U-CN */ + .driver_info = ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, From f47659f1e942cd7bf63a6b1db13002c7097f3516 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 12 Mar 2023 14:09:33 -0700 Subject: [PATCH 2480/4345] iio: adc: ti-ads7950: Set `can_sleep` flag for GPIO chip commit 363c7dc72f79edd55bf1c4380e0fbf7f1bbc2c86 upstream. The ads7950 uses a mutex as well as SPI transfers in its GPIO callbacks. This means these callbacks can sleep and the `can_sleep` flag should be set. Having the flag set will make sure that warnings are generated when calling any of the callbacks from a potentially non-sleeping context. Fixes: c97dce792dc8 ("iio: adc: ti-ads7950: add GPIO support") Signed-off-by: Lars-Peter Clausen Acked-by: David Lechner Link: https://lore.kernel.org/r/20230312210933.2275376-1-lars@metafoo.de Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/ti-ads7950.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c index a2b83f0bd526..d4583b76f1fe 100644 --- a/drivers/iio/adc/ti-ads7950.c +++ b/drivers/iio/adc/ti-ads7950.c @@ -634,6 +634,7 @@ static int ti_ads7950_probe(struct spi_device *spi) st->chip.label = dev_name(&st->spi->dev); st->chip.parent = &st->spi->dev; st->chip.owner = THIS_MODULE; + st->chip.can_sleep = true; st->chip.base = -1; st->chip.ngpio = TI_ADS7950_NUM_GPIOS; st->chip.get_direction = ti_ads7950_get_direction; From 58bf30479a2e472200430f78dfeca2a5c0cfed3d Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Fri, 10 Mar 2023 19:22:48 -0500 Subject: [PATCH 2481/4345] iio: dac: cio-dac: Fix max DAC write value check for 12-bit commit c3701185ee1973845db088d8b0fc443397ab0eb2 upstream. The CIO-DAC series of devices only supports DAC values up to 12-bit rather than 16-bit. Trying to write a 16-bit value results in only the lower 12 bits affecting the DAC output which is not what the user expects. Instead, adjust the DAC write value check to reject values larger than 12-bit so that they fail explicitly as invalid for the user. Fixes: 3b8df5fd526e ("iio: Add IIO support for the Measurement Computing CIO-DAC family") Cc: stable@vger.kernel.org Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/20230311002248.8548-1-william.gray@linaro.org Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/dac/cio-dac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/dac/cio-dac.c b/drivers/iio/dac/cio-dac.c index 95813569f394..77a6916b3d6c 100644 --- a/drivers/iio/dac/cio-dac.c +++ b/drivers/iio/dac/cio-dac.c @@ -66,8 +66,8 @@ static int cio_dac_write_raw(struct iio_dev *indio_dev, if (mask != IIO_CHAN_INFO_RAW) return -EINVAL; - /* DAC can only accept up to a 16-bit value */ - if ((unsigned int)val > 65535) + /* DAC can only accept up to a 12-bit value */ + if ((unsigned int)val > 4095) return -EINVAL; priv->chan_out_states[chan->channel] = val; From 741d73fc573c15c4fc3fcbf4bd3a711e825d8ea9 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Thu, 23 Feb 2023 10:00:59 +0800 Subject: [PATCH 2482/4345] iio: light: cm32181: Unregister second I2C client if present commit 099cc90a5a62e68b2fe3a42da011ab929b98bf73 upstream. If a second dummy client that talks to the actual I2C address was created in probe(), there should be a proper cleanup on driver and device removal to avoid leakage. So unregister the dummy client via another callback. Reviewed-by: Hans de Goede Suggested-by: Hans de Goede Fixes: c1e62062ff54 ("iio: light: cm32181: Handle CM3218 ACPI devices with 2 I2C resources") Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2152281 Signed-off-by: Kai-Heng Feng Link: https://lore.kernel.org/r/20230223020059.2013993-1-kai.heng.feng@canonical.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/light/cm32181.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c index 97649944f1df..c14a630dd683 100644 --- a/drivers/iio/light/cm32181.c +++ b/drivers/iio/light/cm32181.c @@ -429,6 +429,14 @@ static const struct iio_info cm32181_info = { .attrs = &cm32181_attribute_group, }; +static void cm32181_unregister_dummy_client(void *data) +{ + struct i2c_client *client = data; + + /* Unregister the dummy client */ + i2c_unregister_device(client); +} + static int cm32181_probe(struct i2c_client *client) { struct device *dev = &client->dev; @@ -458,6 +466,10 @@ static int cm32181_probe(struct i2c_client *client) client = i2c_acpi_new_device(dev, 1, &board_info); if (IS_ERR(client)) return PTR_ERR(client); + + ret = devm_add_action_or_reset(dev, cm32181_unregister_dummy_client, client); + if (ret) + return ret; } cm32181 = iio_priv(indio_dev); From 72a3e4fa882db70a10558bfabea4be7fe50a3033 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Fri, 17 Mar 2023 15:04:03 +0000 Subject: [PATCH 2483/4345] tty: serial: sh-sci: Fix transmit end interrupt handler commit b43a18647f03c87e77d50d6fe74904b61b96323e upstream. The fourth interrupt on SCI port is transmit end interrupt compared to the break interrupt on other port types. So, shuffle the interrupts to fix the transmit end interrupt handler. Fixes: e1d0be616186 ("sh-sci: Add h8300 SCI") Cc: stable Suggested-by: Geert Uytterhoeven Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230317150403.154094-1-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 8d924727d6f0..9981da007c8a 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -2923,6 +2924,13 @@ static int sci_init_single(struct platform_device *dev, sci_port->irqs[i] = platform_get_irq(dev, i); } + /* + * The fourth interrupt on SCI port is transmit end interrupt, so + * shuffle the interrupts. + */ + if (p->type == PORT_SCI) + swap(sci_port->irqs[SCIx_BRI_IRQ], sci_port->irqs[SCIx_TEI_IRQ]); + /* The SCI generates several interrupts. They can be muxed together or * connected to different interrupt lines. In the muxed case only one * interrupt resource is specified as there is only one interrupt ID. From 25eff5e7f743b68e23da7d33a8a455cf05d5e22c Mon Sep 17 00:00:00 2001 From: Biju Das Date: Tue, 21 Mar 2023 11:47:50 +0000 Subject: [PATCH 2484/4345] tty: serial: sh-sci: Fix Rx on RZ/G2L SCI commit f92ed0cd9328aed918ebb0ebb64d259eccbcc6e7 upstream. SCI IP on RZ/G2L alike SoCs do not need regshift compared to other SCI IPs on the SH platform. Currently, it does regshift and configuring Rx wrongly. Drop adding regshift for RZ/G2L alike SoCs. Fixes: dfc80387aefb ("serial: sh-sci: Compute the regshift value for SCI ports") Cc: stable@vger.kernel.org Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230321114753.75038-3-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 9981da007c8a..a7c28543c6f7 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -2996,7 +2996,7 @@ static int sci_init_single(struct platform_device *dev, port->flags = UPF_FIXED_PORT | UPF_BOOT_AUTOCONF | p->flags; port->fifosize = sci_port->params->fifosize; - if (port->type == PORT_SCI) { + if (port->type == PORT_SCI && !dev->dev.of_node) { if (sci_port->reg_size >= 0x20) port->regshift = 2; else From a17bed82c0d38d0444c6586543dff5d9c30987d5 Mon Sep 17 00:00:00 2001 From: Sherry Sun Date: Thu, 23 Mar 2023 13:44:15 +0800 Subject: [PATCH 2485/4345] tty: serial: fsl_lpuart: avoid checking for transfer complete when UARTCTRL_SBK is asserted in lpuart32_tx_empty commit 9425914f3de6febbd6250395f56c8279676d9c3c upstream. According to LPUART RM, Transmission Complete Flag becomes 0 if queuing a break character by writing 1 to CTRL[SBK], so here need to avoid checking for transmission complete when UARTCTRL_SBK is asserted, otherwise the lpuart32_tx_empty may never get TIOCSER_TEMT. Commit 2411fd94ceaa("tty: serial: fsl_lpuart: skip waiting for transmission complete when UARTCTRL_SBK is asserted") only fix it in lpuart32_set_termios(), here also fix it in lpuart32_tx_empty(). Fixes: 380c966c093e ("tty: serial: fsl_lpuart: add 32-bit register interface support") Cc: stable Signed-off-by: Sherry Sun Link: https://lore.kernel.org/r/20230323054415.20363-1-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 99f29bd930bd..f481c260b704 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -809,11 +809,17 @@ static unsigned int lpuart32_tx_empty(struct uart_port *port) struct lpuart_port, port); unsigned long stat = lpuart32_read(port, UARTSTAT); unsigned long sfifo = lpuart32_read(port, UARTFIFO); + unsigned long ctrl = lpuart32_read(port, UARTCTRL); if (sport->dma_tx_in_progress) return 0; - if (stat & UARTSTAT_TC && sfifo & UARTFIFO_TXEMPT) + /* + * LPUART Transmission Complete Flag may never be set while queuing a break + * character, so avoid checking for transmission complete when UARTCTRL_SBK + * is asserted. + */ + if ((stat & UARTSTAT_TC && sfifo & UARTFIFO_TXEMPT) || ctrl & UARTCTRL_SBK) return TIOCSER_TEMT; return 0; From f32297dba338dc06d62286dedb3cdbd5175b1719 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Tue, 28 Mar 2023 02:53:18 +0900 Subject: [PATCH 2486/4345] nilfs2: fix potential UAF of struct nilfs_sc_info in nilfs_segctor_thread() commit 6be49d100c22ffea3287a4b19d7639d259888e33 upstream. The finalization of nilfs_segctor_thread() can race with nilfs_segctor_kill_thread() which terminates that thread, potentially causing a use-after-free BUG as KASAN detected. At the end of nilfs_segctor_thread(), it assigns NULL to "sc_task" member of "struct nilfs_sc_info" to indicate the thread has finished, and then notifies nilfs_segctor_kill_thread() of this using waitqueue "sc_wait_task" on the struct nilfs_sc_info. However, here, immediately after the NULL assignment to "sc_task", it is possible that nilfs_segctor_kill_thread() will detect it and return to continue the deallocation, freeing the nilfs_sc_info structure before the thread does the notification. This fixes the issue by protecting the NULL assignment to "sc_task" and its notification, with spinlock "sc_state_lock" of the struct nilfs_sc_info. Since nilfs_segctor_kill_thread() does a final check to see if "sc_task" is NULL with "sc_state_lock" locked, this can eliminate the race. Link: https://lkml.kernel.org/r/20230327175318.8060-1-konishi.ryusuke@gmail.com Reported-by: syzbot+b08ebcc22f8f3e6be43a@syzkaller.appspotmail.com Link: https://lkml.kernel.org/r/00000000000000660d05f7dfa877@google.com Signed-off-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/segment.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 5ee4973525f0..5e835bbf1ffb 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2614,11 +2614,10 @@ static int nilfs_segctor_thread(void *arg) goto loop; end_thread: - spin_unlock(&sci->sc_state_lock); - /* end sync. */ sci->sc_task = NULL; wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ + spin_unlock(&sci->sc_state_lock); return 0; } From 3dbee84bf9e3273c4bb9ca6fc18ff22fba23dd24 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 31 Mar 2023 05:55:15 +0900 Subject: [PATCH 2487/4345] nilfs2: fix sysfs interface lifetime commit 42560f9c92cc43dce75dbf06cc0d840dced39b12 upstream. The current nilfs2 sysfs support has issues with the timing of creation and deletion of sysfs entries, potentially leading to null pointer dereferences, use-after-free, and lockdep warnings. Some of the sysfs attributes for nilfs2 per-filesystem instance refer to metadata file "cpfile", "sufile", or "dat", but nilfs_sysfs_create_device_group that creates those attributes is executed before the inodes for these metadata files are loaded, and nilfs_sysfs_delete_device_group which deletes these sysfs entries is called after releasing their metadata file inodes. Therefore, access to some of these sysfs attributes may occur outside of the lifetime of these metadata files, resulting in inode NULL pointer dereferences or use-after-free. In addition, the call to nilfs_sysfs_create_device_group() is made during the locking period of the semaphore "ns_sem" of nilfs object, so the shrinker call caused by the memory allocation for the sysfs entries, may derive lock dependencies "ns_sem" -> (shrinker) -> "locks acquired in nilfs_evict_inode()". Since nilfs2 may acquire "ns_sem" deep in the call stack holding other locks via its error handler __nilfs_error(), this causes lockdep to report circular locking. This is a false positive and no circular locking actually occurs as no inodes exist yet when nilfs_sysfs_create_device_group() is called. Fortunately, the lockdep warnings can be resolved by simply moving the call to nilfs_sysfs_create_device_group() out of "ns_sem". This fixes these sysfs issues by revising where the device's sysfs interface is created/deleted and keeping its lifetime within the lifetime of the metadata files above. Link: https://lkml.kernel.org/r/20230330205515.6167-1-konishi.ryusuke@gmail.com Fixes: dd70edbde262 ("nilfs2: integrate sysfs support into driver") Signed-off-by: Ryusuke Konishi Reported-by: syzbot+979fa7f9c0d086fdc282@syzkaller.appspotmail.com Link: https://lkml.kernel.org/r/0000000000003414b505f7885f7e@google.com Reported-by: syzbot+5b7d542076d9bddc3c6a@syzkaller.appspotmail.com Link: https://lkml.kernel.org/r/0000000000006ac86605f5f44eb9@google.com Cc: Viacheslav Dubeyko Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/super.c | 2 ++ fs/nilfs2/the_nilfs.c | 12 +++++++----- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 775184868763..9aae60d9a32e 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -482,6 +482,7 @@ static void nilfs_put_super(struct super_block *sb) up_write(&nilfs->ns_sem); } + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); @@ -1105,6 +1106,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) nilfs_put_root(fsroot); failed_unload: + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 38a1206cf948..d8d08fa5c340 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -87,7 +87,6 @@ void destroy_nilfs(struct the_nilfs *nilfs) { might_sleep(); if (nilfs_init(nilfs)) { - nilfs_sysfs_delete_device_group(nilfs); brelse(nilfs->ns_sbh[0]); brelse(nilfs->ns_sbh[1]); } @@ -305,6 +304,10 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; } + err = nilfs_sysfs_create_device_group(sb); + if (unlikely(err)) + goto sysfs_error; + if (valid_fs) goto skip_recovery; @@ -366,6 +369,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; failed_unload: + nilfs_sysfs_delete_device_group(nilfs); + + sysfs_error: iput(nilfs->ns_cpfile); iput(nilfs->ns_sufile); iput(nilfs->ns_dat); @@ -697,10 +703,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) if (err) goto failed_sbh; - err = nilfs_sysfs_create_device_group(sb); - if (err) - goto failed_sbh; - set_nilfs_init(nilfs); err = 0; out: From 1f3b8c3b047a554664be772db61fb3c7210ad0a9 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 17 Mar 2023 10:46:57 +0100 Subject: [PATCH 2488/4345] dt-bindings: serial: renesas,scif: Fix 4th IRQ for 4-IRQ SCIFs commit 7b21f329ae0ab6361c0aebfc094db95821490cd1 upstream. The fourth interrupt on SCIF variants with four interrupts (RZ/A1) is the Break interrupt, not the Transmit End interrupt (like on SCI(g)). Update the description and interrupt name to fix this. Fixes: 384d00fae8e51f8f ("dt-bindings: serial: sh-sci: Convert to json-schema") Cc: stable Signed-off-by: Geert Uytterhoeven Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/719d1582e0ebbe3d674e3a48fc26295e1475a4c3.1679046394.git.geert+renesas@glider.be Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/serial/renesas,scif.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/serial/renesas,scif.yaml b/Documentation/devicetree/bindings/serial/renesas,scif.yaml index eda3d2c6bdd3..dbaa04380209 100644 --- a/Documentation/devicetree/bindings/serial/renesas,scif.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,scif.yaml @@ -74,7 +74,7 @@ properties: - description: Error interrupt - description: Receive buffer full interrupt - description: Transmit buffer empty interrupt - - description: Transmit End interrupt + - description: Break interrupt - items: - description: Error interrupt - description: Receive buffer full interrupt @@ -89,7 +89,7 @@ properties: - const: eri - const: rxi - const: txi - - const: tei + - const: bri - items: - const: eri - const: rxi From 14f9ff7857e7429932fc5549daf6ad187859a8a1 Mon Sep 17 00:00:00 2001 From: Jeremy Soller Date: Fri, 31 Mar 2023 10:23:17 -0600 Subject: [PATCH 2489/4345] ALSA: hda/realtek: Add quirk for Clevo X370SNW commit 36d4d213c6d4fffae2645a601e8ae996de4c3645 upstream. Fixes speaker output and headset detection on Clevo X370SNW. Signed-off-by: Jeremy Soller Signed-off-by: Tim Crawford Cc: Link: https://lore.kernel.org/r/20230331162317.14992-1-tcrawford@system76.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2af9cd7b7999..18309fa17fb8 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2632,6 +2632,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), + SND_PCI_QUIRK(0x1558, 0x3702, "Clevo X370SN[VW]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), From 4bfdead174438b815677c7fa2ebdf6139b5462ca Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Fri, 20 Jan 2023 13:46:45 +0100 Subject: [PATCH 2490/4345] iio: adc: ad7791: fix IRQ flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0c6ef985a1fd8a74dcb5cad941ddcadd55cb8697 ] The interrupt is triggered on the falling edge rather than being a level low interrupt. Fixes: da4d3d6bb9f6 ("iio: adc: ad-sigma-delta: Allow custom IRQ flags") Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20230120124645.819910-1-nuno.sa@analog.com Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/adc/ad7791.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/ad7791.c b/drivers/iio/adc/ad7791.c index d57ad966e17c..f3502f12653b 100644 --- a/drivers/iio/adc/ad7791.c +++ b/drivers/iio/adc/ad7791.c @@ -253,7 +253,7 @@ static const struct ad_sigma_delta_info ad7791_sigma_delta_info = { .has_registers = true, .addr_shift = 4, .read_mask = BIT(3), - .irq_flags = IRQF_TRIGGER_LOW, + .irq_flags = IRQF_TRIGGER_FALLING, }; static int ad7791_read_raw(struct iio_dev *indio_dev, From 499757ad3332e2527254f9ab68dec1da087b1d96 Mon Sep 17 00:00:00 2001 From: Zhong Jinghua Date: Wed, 29 Mar 2023 15:17:39 +0800 Subject: [PATCH 2491/4345] scsi: iscsi_tcp: Check that sock is valid before iscsi_set_param() [ Upstream commit 48b19b79cfa37b1e50da3b5a8af529f994c08901 ] The validity of sock should be checked before assignment to avoid incorrect values. Commit 57569c37f0ad ("scsi: iscsi: iscsi_tcp: Fix null-ptr-deref while calling getpeername()") introduced this change which may lead to inconsistent values of tcp_sw_conn->sendpage and conn->datadgst_en. Fix the issue by moving the position of the assignment. Fixes: 57569c37f0ad ("scsi: iscsi: iscsi_tcp: Fix null-ptr-deref while calling getpeername()") Signed-off-by: Zhong Jinghua Link: https://lore.kernel.org/r/20230329071739.2175268-1-zhongjinghua@huaweicloud.com Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/iscsi_tcp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 252d7881f99c..def9fac7aa4f 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -721,13 +721,12 @@ static int iscsi_sw_tcp_conn_set_param(struct iscsi_cls_conn *cls_conn, iscsi_set_param(cls_conn, param, buf, buflen); break; case ISCSI_PARAM_DATADGST_EN: - iscsi_set_param(cls_conn, param, buf, buflen); - mutex_lock(&tcp_sw_conn->sock_lock); if (!tcp_sw_conn->sock) { mutex_unlock(&tcp_sw_conn->sock_lock); return -ENOTCONN; } + iscsi_set_param(cls_conn, param, buf, buflen); tcp_sw_conn->sendpage = conn->datadgst_en ? sock_no_sendpage : tcp_sw_conn->sock->ops->sendpage; mutex_unlock(&tcp_sw_conn->sock_lock); From 9470fc63ab42c66b3d9495b75d2e8a3341d35a12 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 22 Mar 2023 13:24:49 -0700 Subject: [PATCH 2492/4345] perf/core: Fix the same task check in perf_event_set_output MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 24d3ae2f37d8bc3c14b31d353c5d27baf582b6a6 ] The same task check in perf_event_set_output has some potential issues for some usages. For the current perf code, there is a problem if using of perf_event_open() to have multiple samples getting into the same mmap’d memory when they are both attached to the same process. https://lore.kernel.org/all/92645262-D319-4068-9C44-2409EF44888E@gmail.com/ Because the event->ctx is not ready when the perf_event_set_output() is invoked in the perf_event_open(). Besides the above issue, before the commit bd2756811766 ("perf: Rewrite core context handling"), perf record can errors out when sampling with a hardware event and a software event as below. $ perf record -e cycles,dummy --per-thread ls failed to mmap with 22 (Invalid argument) That's because that prior to the commit a hardware event and a software event are from different task context. The problem should be a long time issue since commit c3f00c70276d ("perk: Separate find_get_context() from event initialization"). The task struct is stored in the event->hw.target for each per-thread event. It is a more reliable way to determine whether two events are attached to the same task. The event->hw.target was also introduced several years ago by the commit 50f16a8bf9d7 ("perf: Remove type specific target pointers"). It can not only be used to fix the issue with the current code, but also back port to fix the issues with an older kernel. Note: The event->hw.target was introduced later than commit c3f00c70276d. The patch may cannot be applied between the commit c3f00c70276d and commit 50f16a8bf9d7. Anybody that wants to back-port this at that period may have to find other solutions. Fixes: c3f00c70276d ("perf: Separate find_get_context() from event initialization") Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Zhengjun Xing Link: https://lkml.kernel.org/r/20230322202449.512091-1-kan.liang@linux.intel.com Signed-off-by: Sasha Levin --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index e2e1371fbb9d..f0df3bc0e641 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11622,7 +11622,7 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) /* * If its not a per-cpu rb, it must be the same task. */ - if (output_event->cpu == -1 && output_event->ctx != event->ctx) + if (output_event->cpu == -1 && output_event->hw.target != event->hw.target) goto out; /* From eadcad0a47bfeeba9fac06047f3141eb725420b2 Mon Sep 17 00:00:00 2001 From: John Keeping Date: Mon, 27 Mar 2023 18:36:46 +0100 Subject: [PATCH 2493/4345] ftrace: Mark get_lock_parent_ip() __always_inline commit ea65b41807a26495ff2a73dd8b1bab2751940887 upstream. If the compiler decides not to inline this function then preemption tracing will always show an IP inside the preemption disabling path and never the function actually calling preempt_{enable,disable}. Link: https://lore.kernel.org/linux-trace-kernel/20230327173647.1690849-1-john@metanate.com Cc: Masami Hiramatsu Cc: Mark Rutland Cc: stable@vger.kernel.org Fixes: f904f58263e1d ("sched/debug: Fix preempt_disable_ip recording for preempt_disable()") Signed-off-by: John Keeping Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- include/linux/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 1bd3a0356ae4..b9dd113599eb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -811,7 +811,7 @@ static inline void __ftrace_enabled_restore(int enabled) #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) -static inline unsigned long get_lock_parent_ip(void) +static __always_inline unsigned long get_lock_parent_ip(void) { unsigned long addr = CALLER_ADDR0; From f018ef34c44b50be56ffaac14e34c135199e2f5a Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Thu, 30 Mar 2023 10:52:23 +0800 Subject: [PATCH 2494/4345] ftrace: Fix issue that 'direct->addr' not restored in modify_ftrace_direct() commit 2a2d8c51defb446e8d89a83f42f8e5cd529111e9 upstream. Syzkaller report a WARNING: "WARN_ON(!direct)" in modify_ftrace_direct(). Root cause is 'direct->addr' was changed from 'old_addr' to 'new_addr' but not restored if error happened on calling ftrace_modify_direct_caller(). Then it can no longer find 'direct' by that 'old_addr'. To fix it, restore 'direct->addr' to 'old_addr' explicitly in error path. Link: https://lore.kernel.org/linux-trace-kernel/20230330025223.1046087-1-zhengyejian1@huawei.com Cc: stable@vger.kernel.org Cc: Cc: Cc: Cc: Fixes: 8a141dd7f706 ("ftrace: Fix modify_ftrace_direct.") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ftrace.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 67829b6e07bd..3dab978c156d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5390,12 +5390,15 @@ int modify_ftrace_direct(unsigned long ip, ret = 0; } - if (unlikely(ret && new_direct)) { - direct->count++; - list_del_rcu(&new_direct->next); - synchronize_rcu_tasks(); - kfree(new_direct); - ftrace_direct_func_count--; + if (ret) { + direct->addr = old_addr; + if (unlikely(new_direct)) { + direct->count++; + list_del_rcu(&new_direct->next); + synchronize_rcu_tasks(); + kfree(new_direct); + ftrace_direct_func_count--; + } } out_unlock: From 70caa596d158a5d84b117f722d58f3ea503a5ba9 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 4 Apr 2023 09:31:28 +0200 Subject: [PATCH 2495/4345] can: j1939: j1939_tp_tx_dat_new(): fix out-of-bounds memory access commit b45193cb4df556fe6251b285a5ce44046dd36b4a upstream. In the j1939_tp_tx_dat_new() function, an out-of-bounds memory access could occur during the memcpy() operation if the size of skb->cb is larger than the size of struct j1939_sk_buff_cb. This is because the memcpy() operation uses the size of skb->cb, leading to a read beyond the struct j1939_sk_buff_cb. Updated the memcpy() operation to use the size of struct j1939_sk_buff_cb instead of the size of skb->cb. This ensures that the memcpy() operation only reads the memory within the bounds of struct j1939_sk_buff_cb, preventing out-of-bounds memory access. Additionally, add a BUILD_BUG_ON() to check that the size of skb->cb is greater than or equal to the size of struct j1939_sk_buff_cb. This ensures that the skb->cb buffer is large enough to hold the j1939_sk_buff_cb structure. Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Reported-by: Shuangpeng Bai Tested-by: Shuangpeng Bai Signed-off-by: Oleksij Rempel Link: https://groups.google.com/g/syzkaller/c/G_LL-C3plRs/m/-8xCi6dCAgAJ Link: https://lore.kernel.org/all/20230404073128.3173900-1-o.rempel@pengutronix.de Cc: stable@vger.kernel.org [mkl: rephrase commit message] Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/j1939/transport.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 57d6aac7f435..5dcbb0b7d123 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -600,7 +600,10 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv, /* reserve CAN header */ skb_reserve(skb, offsetof(struct can_frame, data)); - memcpy(skb->cb, re_skcb, sizeof(skb->cb)); + /* skb->cb must be large enough to hold a j1939_sk_buff_cb structure */ + BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*re_skcb)); + + memcpy(skb->cb, re_skcb, sizeof(*re_skcb)); skcb = j1939_skb_to_cb(skb); if (swap_src_dst) j1939_skbcb_swap(skcb); From 9c5df2f14ee351d0ff4c589ad7b416ae6a680742 Mon Sep 17 00:00:00 2001 From: Michal Sojka Date: Fri, 31 Mar 2023 14:55:11 +0200 Subject: [PATCH 2496/4345] can: isotp: isotp_ops: fix poll() to not report false EPOLLOUT events commit 79e19fa79cb5d5f1b3bf3e3ae24989ccb93c7b7b upstream. When using select()/poll()/epoll() with a non-blocking ISOTP socket to wait for when non-blocking write is possible, a false EPOLLOUT event is sometimes returned. This can happen at least after sending a message which must be split to multiple CAN frames. The reason is that isotp_sendmsg() returns -EAGAIN when tx.state is not equal to ISOTP_IDLE and this behavior is not reflected in datagram_poll(), which is used in isotp_ops. This is fixed by introducing ISOTP-specific poll function, which suppresses the EPOLLOUT events in that case. v2: https://lore.kernel.org/all/20230302092812.320643-1-michal.sojka@cvut.cz v1: https://lore.kernel.org/all/20230224010659.48420-1-michal.sojka@cvut.cz https://lore.kernel.org/all/b53a04a2-ba1f-3858-84c1-d3eb3301ae15@hartkopp.net Signed-off-by: Michal Sojka Reported-by: Jakub Jira Tested-by: Oliver Hartkopp Acked-by: Oliver Hartkopp Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol") Link: https://lore.kernel.org/all/20230331125511.372783-1-michal.sojka@cvut.cz Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/isotp.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/net/can/isotp.c b/net/can/isotp.c index f2f0bc7f0cb4..4360f33278c1 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1480,6 +1480,21 @@ static int isotp_init(struct sock *sk) return 0; } +static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *wait) +{ + struct sock *sk = sock->sk; + struct isotp_sock *so = isotp_sk(sk); + + __poll_t mask = datagram_poll(file, sock, wait); + poll_wait(file, &so->wait, wait); + + /* Check for false positives due to TX state */ + if ((mask & EPOLLWRNORM) && (so->tx.state != ISOTP_IDLE)) + mask &= ~(EPOLLOUT | EPOLLWRNORM); + + return mask; +} + static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { @@ -1495,7 +1510,7 @@ static const struct proto_ops isotp_ops = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = isotp_getname, - .poll = datagram_poll, + .poll = isotp_poll, .ioctl = isotp_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, From 6e36373aa5ffa8e00fe7c71b3209f6f17081e552 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 4 Apr 2023 19:45:04 -0400 Subject: [PATCH 2497/4345] tracing: Free error logs of tracing instances commit 3357c6e429643231e60447b52ffbb7ac895aca22 upstream. When a tracing instance is removed, the error messages that hold errors that occurred in the instance needs to be freed. The following reports a memory leak: # cd /sys/kernel/tracing # mkdir instances/foo # echo 'hist:keys=x' > instances/foo/events/sched/sched_switch/trigger # cat instances/foo/error_log [ 117.404795] hist:sched:sched_switch: error: Couldn't find field Command: hist:keys=x ^ # rmdir instances/foo Then check for memory leaks: # echo scan > /sys/kernel/debug/kmemleak # cat /sys/kernel/debug/kmemleak unreferenced object 0xffff88810d8ec700 (size 192): comm "bash", pid 869, jiffies 4294950577 (age 215.752s) hex dump (first 32 bytes): 60 dd 68 61 81 88 ff ff 60 dd 68 61 81 88 ff ff `.ha....`.ha.... a0 30 8c 83 ff ff ff ff 26 00 0a 00 00 00 00 00 .0......&....... backtrace: [<00000000dae26536>] kmalloc_trace+0x2a/0xa0 [<00000000b2938940>] tracing_log_err+0x277/0x2e0 [<000000004a0e1b07>] parse_atom+0x966/0xb40 [<0000000023b24337>] parse_expr+0x5f3/0xdb0 [<00000000594ad074>] event_hist_trigger_parse+0x27f8/0x3560 [<00000000293a9645>] trigger_process_regex+0x135/0x1a0 [<000000005c22b4f2>] event_trigger_write+0x87/0xf0 [<000000002cadc509>] vfs_write+0x162/0x670 [<0000000059c3b9be>] ksys_write+0xca/0x170 [<00000000f1cddc00>] do_syscall_64+0x3e/0xc0 [<00000000868ac68c>] entry_SYSCALL_64_after_hwframe+0x72/0xdc unreferenced object 0xffff888170c35a00 (size 32): comm "bash", pid 869, jiffies 4294950577 (age 215.752s) hex dump (first 32 bytes): 0a 20 20 43 6f 6d 6d 61 6e 64 3a 20 68 69 73 74 . Command: hist 3a 6b 65 79 73 3d 78 0a 00 00 00 00 00 00 00 00 :keys=x......... backtrace: [<000000006a747de5>] __kmalloc+0x4d/0x160 [<000000000039df5f>] tracing_log_err+0x29b/0x2e0 [<000000004a0e1b07>] parse_atom+0x966/0xb40 [<0000000023b24337>] parse_expr+0x5f3/0xdb0 [<00000000594ad074>] event_hist_trigger_parse+0x27f8/0x3560 [<00000000293a9645>] trigger_process_regex+0x135/0x1a0 [<000000005c22b4f2>] event_trigger_write+0x87/0xf0 [<000000002cadc509>] vfs_write+0x162/0x670 [<0000000059c3b9be>] ksys_write+0xca/0x170 [<00000000f1cddc00>] do_syscall_64+0x3e/0xc0 [<00000000868ac68c>] entry_SYSCALL_64_after_hwframe+0x72/0xdc The problem is that the error log needs to be freed when the instance is removed. Link: https://lore.kernel.org/lkml/76134d9f-a5ba-6a0d-37b3-28310b4a1e91@alu.unizg.hr/ Link: https://lore.kernel.org/linux-trace-kernel/20230404194504.5790b95f@gandalf.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Andrew Morton Cc: Mark Rutland Cc: Thorsten Leemhuis Cc: Ulf Hansson Cc: Eric Biggers Fixes: 2f754e771b1a6 ("tracing: Have the error logs show up in the proper instances") Reported-by: Mirsad Goran Todorovac Tested-by: Mirsad Todorovac Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ce45bdd9077d..482ec6606b7b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8895,6 +8895,7 @@ static int __remove_instance(struct trace_array *tr) ftrace_destroy_function_files(tr); tracefs_remove(tr->dir); free_trace_buffers(tr); + clear_tracing_err_log(tr); for (i = 0; i < tr->nr_topts; i++) { kfree(tr->topts[i].topts); From acbbfdba9ca67ef6bc174a0a42666004aee4d931 Mon Sep 17 00:00:00 2001 From: Jason Montleon Date: Fri, 24 Mar 2023 13:07:11 -0400 Subject: [PATCH 2498/4345] ASoC: hdac_hdmi: use set_stream() instead of set_tdm_slots() commit f6887a71bdd2f0dcba9b8180dd2223cfa8637e85 upstream. hdac_hdmi was not updated to use set_stream() instead of set_tdm_slots() in the original commit so HDMI no longer produces audio. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/regressions/CAJD_bPKQdtaExvVEKxhQ47G-ZXDA=k+gzhMJRHLBe=mysPnuKA@mail.gmail.com/ Fixes: 636110411ca7 ("ASoC: Intel/SOF: use set_stream() instead of set_tdm_slots() for HDAudio") Signed-off-by: Jason Montleon Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20230324170711.2526-1-jmontleo@redhat.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/codecs/hdac_hdmi.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index 2c1305bf0572..6de3e47b92d8 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -436,23 +436,28 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_device *hdev, return 0; } -static int hdac_hdmi_set_tdm_slot(struct snd_soc_dai *dai, - unsigned int tx_mask, unsigned int rx_mask, - int slots, int slot_width) +static int hdac_hdmi_set_stream(struct snd_soc_dai *dai, + void *stream, int direction) { struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai); struct hdac_device *hdev = hdmi->hdev; struct hdac_hdmi_dai_port_map *dai_map; struct hdac_hdmi_pcm *pcm; + struct hdac_stream *hstream; - dev_dbg(&hdev->dev, "%s: strm_tag: %d\n", __func__, tx_mask); + if (!stream) + return -EINVAL; + + hstream = (struct hdac_stream *)stream; + + dev_dbg(&hdev->dev, "%s: strm_tag: %d\n", __func__, hstream->stream_tag); dai_map = &hdmi->dai_map[dai->id]; pcm = hdac_hdmi_get_pcm_from_cvt(hdmi, dai_map->cvt); if (pcm) - pcm->stream_tag = (tx_mask << 4); + pcm->stream_tag = (hstream->stream_tag << 4); return 0; } @@ -1544,7 +1549,7 @@ static const struct snd_soc_dai_ops hdmi_dai_ops = { .startup = hdac_hdmi_pcm_open, .shutdown = hdac_hdmi_pcm_close, .hw_params = hdac_hdmi_set_hw_params, - .set_tdm_slot = hdac_hdmi_set_tdm_slot, + .set_stream = hdac_hdmi_set_stream, }; /* From 8250f7f7ae21a67104e1c8c15ed250b2d01c122d Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 21 May 2021 11:38:11 +0200 Subject: [PATCH 2499/4345] drm/panfrost: Fix the panfrost_mmu_map_fault_addr() error path commit 764a2ab9eb56e1200083e771aab16186836edf1d upstream. Make sure all bo->base.pages entries are either NULL or pointing to a valid page before calling drm_gem_shmem_put_pages(). Reported-by: Tomeu Vizoso Cc: Fixes: 187d2929206e ("drm/panfrost: Add support for GPU heap allocations") Signed-off-by: Boris Brezillon Reviewed-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20210521093811.1018992-1-boris.brezillon@collabora.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 5ff856ef7d88..c81f3ac22cdd 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -458,6 +458,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, if (IS_ERR(pages[i])) { mutex_unlock(&bo->base.pages_lock); ret = PTR_ERR(pages[i]); + pages[i] = NULL; goto err_pages; } } From c1bbe926a1c75a81df58cdb8b68fb213068ca6f1 Mon Sep 17 00:00:00 2001 From: Karol Herbst Date: Fri, 31 Mar 2023 00:39:38 +0200 Subject: [PATCH 2500/4345] drm/nouveau/disp: Support more modes by checking with lower bpc commit 7f67aa097e875c87fba024e850cf405342300059 upstream. This allows us to advertise more modes especially on HDR displays. Fixes using 4K@60 modes on my TV and main display both using a HDMI to DP adapter. Also fixes similar issues for users running into this. Cc: stable@vger.kernel.org # 5.10+ Signed-off-by: Karol Herbst Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20230330223938.4025569-1-kherbst@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/nouveau/dispnv50/disp.c | 32 +++++++++++++++++++++++++ drivers/gpu/drm/nouveau/nouveau_dp.c | 8 ++++--- 2 files changed, 37 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 804ea035fa46..0ac120225b4d 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -396,6 +396,35 @@ nv50_outp_atomic_check_view(struct drm_encoder *encoder, return 0; } +static void +nv50_outp_atomic_fix_depth(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state) +{ + struct nv50_head_atom *asyh = nv50_head_atom(crtc_state); + struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); + struct drm_display_mode *mode = &asyh->state.adjusted_mode; + unsigned int max_rate, mode_rate; + + switch (nv_encoder->dcb->type) { + case DCB_OUTPUT_DP: + max_rate = nv_encoder->dp.link_nr * nv_encoder->dp.link_bw; + + /* we don't support more than 10 anyway */ + asyh->or.bpc = min_t(u8, asyh->or.bpc, 10); + + /* reduce the bpc until it works out */ + while (asyh->or.bpc > 6) { + mode_rate = DIV_ROUND_UP(mode->clock * asyh->or.bpc * 3, 8); + if (mode_rate <= max_rate) + break; + + asyh->or.bpc -= 2; + } + break; + default: + break; + } +} + static int nv50_outp_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, @@ -414,6 +443,9 @@ nv50_outp_atomic_check(struct drm_encoder *encoder, if (crtc_state->mode_changed || crtc_state->connectors_changed) asyh->or.bpc = connector->display_info.bpc; + /* We might have to reduce the bpc */ + nv50_outp_atomic_fix_depth(encoder, crtc_state); + return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index 040ed88d362d..447b7594b35a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -220,8 +220,6 @@ void nouveau_dp_irq(struct nouveau_drm *drm, } /* TODO: - * - Use the minimum possible BPC here, once we add support for the max bpc - * property. * - Validate against the DP caps advertised by the GPU (we don't check these * yet) */ @@ -233,7 +231,11 @@ nv50_dp_mode_valid(struct drm_connector *connector, { const unsigned int min_clock = 25000; unsigned int max_rate, mode_rate, ds_max_dotclock, clock = mode->clock; - const u8 bpp = connector->display_info.bpc * 3; + /* Check with the minmum bpc always, so we can advertise better modes. + * In particlar not doing this causes modes to be dropped on HDR + * displays as we might check with a bpc of 16 even. + */ + const u8 bpp = 6 * 3; if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace) return MODE_NO_INTERLACE; From 5a74837809ccfa8180cbdd2f242ebfd6c3b106a0 Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Sat, 25 Mar 2023 10:12:47 +0800 Subject: [PATCH 2501/4345] ring-buffer: Fix race while reader and writer are on the same page commit 6455b6163d8c680366663cdb8c679514d55fc30c upstream. When user reads file 'trace_pipe', kernel keeps printing following logs that warn at "cpu_buffer->reader_page->read > rb_page_size(reader)" in rb_get_reader_page(). It just looks like there's an infinite loop in tracing_read_pipe(). This problem occurs several times on arm64 platform when testing v5.10 and below. Call trace: rb_get_reader_page+0x248/0x1300 rb_buffer_peek+0x34/0x160 ring_buffer_peek+0xbc/0x224 peek_next_entry+0x98/0xbc __find_next_entry+0xc4/0x1c0 trace_find_next_entry_inc+0x30/0x94 tracing_read_pipe+0x198/0x304 vfs_read+0xb4/0x1e0 ksys_read+0x74/0x100 __arm64_sys_read+0x24/0x30 el0_svc_common.constprop.0+0x7c/0x1bc do_el0_svc+0x2c/0x94 el0_svc+0x20/0x30 el0_sync_handler+0xb0/0xb4 el0_sync+0x160/0x180 Then I dump the vmcore and look into the problematic per_cpu ring_buffer, I found that tail_page/commit_page/reader_page are on the same page while reader_page->read is obviously abnormal: tail_page == commit_page == reader_page == { .write = 0x100d20, .read = 0x8f9f4805, // Far greater than 0xd20, obviously abnormal!!! .entries = 0x10004c, .real_end = 0x0, .page = { .time_stamp = 0x857257416af0, .commit = 0xd20, // This page hasn't been full filled. // .data[0...0xd20] seems normal. } } The root cause is most likely the race that reader and writer are on the same page while reader saw an event that not fully committed by writer. To fix this, add memory barriers to make sure the reader can see the content of what is committed. Since commit a0fcaaed0c46 ("ring-buffer: Fix race between reset page and reading page") has added the read barrier in rb_get_reader_page(), here we just need to add the write barrier. Link: https://lore.kernel.org/linux-trace-kernel/20230325021247.2923907-1-zhengyejian1@huawei.com Cc: stable@vger.kernel.org Fixes: 77ae365eca89 ("ring-buffer: make lockless") Suggested-by: Steven Rostedt (Google) Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ring_buffer.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 70da6f3212bc..21b07c7c6ee5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2962,6 +2962,10 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) if (RB_WARN_ON(cpu_buffer, rb_is_reader_page(cpu_buffer->tail_page))) return; + /* + * No need for a memory barrier here, as the update + * of the tail_page did it for this page. + */ local_set(&cpu_buffer->commit_page->page->commit, rb_page_write(cpu_buffer->commit_page)); rb_inc_page(cpu_buffer, &cpu_buffer->commit_page); @@ -2971,6 +2975,8 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) while (rb_commit_index(cpu_buffer) != rb_page_write(cpu_buffer->commit_page)) { + /* Make sure the readers see the content of what is committed. */ + smp_wmb(); local_set(&cpu_buffer->commit_page->page->commit, rb_page_write(cpu_buffer->commit_page)); RB_WARN_ON(cpu_buffer, @@ -4390,7 +4396,12 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) /* * Make sure we see any padding after the write update - * (see rb_reset_tail()) + * (see rb_reset_tail()). + * + * In addition, a writer may be writing on the reader page + * if the page has not been fully filled, so the read barrier + * is also needed to make sure we see the content of what is + * committed by the writer (see rb_set_commit_to_write()). */ smp_rmb(); From ea8c42b3b6d95ced3a4f555f04686d00ef0bb206 Mon Sep 17 00:00:00 2001 From: Rongwei Wang Date: Tue, 4 Apr 2023 23:47:16 +0800 Subject: [PATCH 2502/4345] mm/swap: fix swap_info_struct race between swapoff and get_swap_pages() commit 6fe7d6b992113719e96744d974212df3fcddc76c upstream. The si->lock must be held when deleting the si from the available list. Otherwise, another thread can re-add the si to the available list, which can lead to memory corruption. The only place we have found where this happens is in the swapoff path. This case can be described as below: core 0 core 1 swapoff del_from_avail_list(si) waiting try lock si->lock acquire swap_avail_lock and re-add si into swap_avail_head acquire si->lock but missing si already being added again, and continuing to clear SWP_WRITEOK, etc. It can be easily found that a massive warning messages can be triggered inside get_swap_pages() by some special cases, for example, we call madvise(MADV_PAGEOUT) on blocks of touched memory concurrently, meanwhile, run much swapon-swapoff operations (e.g. stress-ng-swap). However, in the worst case, panic can be caused by the above scene. In swapoff(), the memory used by si could be kept in swap_info[] after turning off a swap. This means memory corruption will not be caused immediately until allocated and reset for a new swap in the swapon path. A panic message caused: (with CONFIG_PLIST_DEBUG enabled) ------------[ cut here ]------------ top: 00000000e58a3003, n: 0000000013e75cda, p: 000000008cd4451a prev: 0000000035b1e58a, n: 000000008cd4451a, p: 000000002150ee8d next: 000000008cd4451a, n: 000000008cd4451a, p: 000000008cd4451a WARNING: CPU: 21 PID: 1843 at lib/plist.c:60 plist_check_prev_next_node+0x50/0x70 Modules linked in: rfkill(E) crct10dif_ce(E)... CPU: 21 PID: 1843 Comm: stress-ng Kdump: ... 5.10.134+ Hardware name: Alibaba Cloud ECS, BIOS 0.0.0 02/06/2015 pstate: 60400005 (nZCv daif +PAN -UAO -TCO BTYPE=--) pc : plist_check_prev_next_node+0x50/0x70 lr : plist_check_prev_next_node+0x50/0x70 sp : ffff0018009d3c30 x29: ffff0018009d3c40 x28: ffff800011b32a98 x27: 0000000000000000 x26: ffff001803908000 x25: ffff8000128ea088 x24: ffff800011b32a48 x23: 0000000000000028 x22: ffff001800875c00 x21: ffff800010f9e520 x20: ffff001800875c00 x19: ffff001800fdc6e0 x18: 0000000000000030 x17: 0000000000000000 x16: 0000000000000000 x15: 0736076307640766 x14: 0730073007380731 x13: 0736076307640766 x12: 0730073007380731 x11: 000000000004058d x10: 0000000085a85b76 x9 : ffff8000101436e4 x8 : ffff800011c8ce08 x7 : 0000000000000000 x6 : 0000000000000001 x5 : ffff0017df9ed338 x4 : 0000000000000001 x3 : ffff8017ce62a000 x2 : ffff0017df9ed340 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: plist_check_prev_next_node+0x50/0x70 plist_check_head+0x80/0xf0 plist_add+0x28/0x140 add_to_avail_list+0x9c/0xf0 _enable_swap_info+0x78/0xb4 __do_sys_swapon+0x918/0xa10 __arm64_sys_swapon+0x20/0x30 el0_svc_common+0x8c/0x220 do_el0_svc+0x2c/0x90 el0_svc+0x1c/0x30 el0_sync_handler+0xa8/0xb0 el0_sync+0x148/0x180 irq event stamp: 2082270 Now, si->lock locked before calling 'del_from_avail_list()' to make sure other thread see the si had been deleted and SWP_WRITEOK cleared together, will not reinsert again. This problem exists in versions after stable 5.10.y. Link: https://lkml.kernel.org/r/20230404154716.23058-1-rongwei.wang@linux.alibaba.com Fixes: a2468cc9bfdff ("swap: choose swap device according to numa node") Tested-by: Yongchen Yin Signed-off-by: Rongwei Wang Cc: Bagas Sanjaya Cc: Matthew Wilcox (Oracle) Cc: Aaron Lu Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/swapfile.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index d87d6971afc9..86ade667a7af 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -666,6 +666,7 @@ static void __del_from_avail_list(struct swap_info_struct *p) { int nid; + assert_spin_locked(&p->lock); for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } @@ -2611,8 +2612,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - del_from_avail_list(p); spin_lock(&p->lock); + del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; From a2773afc81fc6ce2c164979ecd7635a70e17e88b Mon Sep 17 00:00:00 2001 From: Tommi Rantala Date: Mon, 2 Nov 2020 09:39:18 +0200 Subject: [PATCH 2503/4345] selftests: intel_pstate: ftime() is deprecated MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit fc4a3a1bf9ad799181e4d4ec9c2598c0405bc27d upstream. Use clock_gettime() instead of deprecated ftime(). aperf.c: In function ‘main’: aperf.c:58:2: warning: ‘ftime’ is deprecated [-Wdeprecated-declarations] 58 | ftime(&before); | ^~~~~ In file included from aperf.c:9: /usr/include/sys/timeb.h:39:12: note: declared here 39 | extern int ftime (struct timeb *__timebuf) | ^~~~~ Signed-off-by: Tommi Rantala Signed-off-by: Shuah Khan Signed-off-by: Ricardo Cañuelo Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304060514.ELO1BqLI-lkp@intel.com/ Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/intel_pstate/aperf.c | 22 ++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/intel_pstate/aperf.c b/tools/testing/selftests/intel_pstate/aperf.c index f6cd03a87493..a8acf3996973 100644 --- a/tools/testing/selftests/intel_pstate/aperf.c +++ b/tools/testing/selftests/intel_pstate/aperf.c @@ -10,8 +10,12 @@ #include #include #include +#include #include "../kselftest.h" +#define MSEC_PER_SEC 1000L +#define NSEC_PER_MSEC 1000000L + void usage(char *name) { printf ("Usage: %s cpunum\n", name); } @@ -22,7 +26,7 @@ int main(int argc, char **argv) { long long tsc, old_tsc, new_tsc; long long aperf, old_aperf, new_aperf; long long mperf, old_mperf, new_mperf; - struct timeb before, after; + struct timespec before, after; long long int start, finish, total; cpu_set_t cpuset; @@ -55,7 +59,10 @@ int main(int argc, char **argv) { return 1; } - ftime(&before); + if (clock_gettime(CLOCK_MONOTONIC, &before) < 0) { + perror("clock_gettime"); + return 1; + } pread(fd, &old_tsc, sizeof(old_tsc), 0x10); pread(fd, &old_aperf, sizeof(old_mperf), 0xe7); pread(fd, &old_mperf, sizeof(old_aperf), 0xe8); @@ -64,7 +71,10 @@ int main(int argc, char **argv) { sqrt(i); } - ftime(&after); + if (clock_gettime(CLOCK_MONOTONIC, &after) < 0) { + perror("clock_gettime"); + return 1; + } pread(fd, &new_tsc, sizeof(new_tsc), 0x10); pread(fd, &new_aperf, sizeof(new_mperf), 0xe7); pread(fd, &new_mperf, sizeof(new_aperf), 0xe8); @@ -73,11 +83,11 @@ int main(int argc, char **argv) { aperf = new_aperf-old_aperf; mperf = new_mperf-old_mperf; - start = before.time*1000 + before.millitm; - finish = after.time*1000 + after.millitm; + start = before.tv_sec*MSEC_PER_SEC + before.tv_nsec/NSEC_PER_MSEC; + finish = after.tv_sec*MSEC_PER_SEC + after.tv_nsec/NSEC_PER_MSEC; total = finish - start; - printf("runTime: %4.2f\n", 1.0*total/1000); + printf("runTime: %4.2f\n", 1.0*total/MSEC_PER_SEC); printf("freq: %7.0f\n", tsc / (1.0*aperf / (1.0 * mperf)) / total); return 0; } From 2d96c8dca9467b60f93bf3ac72a6588cc438ac1e Mon Sep 17 00:00:00 2001 From: Robert Foss Date: Tue, 13 Dec 2022 16:03:04 +0100 Subject: [PATCH 2504/4345] drm/bridge: lt9611: Fix PLL being unable to lock commit 2a9df204be0bbb896e087f00b9ee3fc559d5a608 upstream. This fixes PLL being unable to lock, and is derived from an equivalent downstream commit. Available LT9611 documentation does not list this register, neither does LT9611UXC (which is a different chip). This commit has been confirmed to fix HDMI output on DragonBoard 845c. Suggested-by: Amit Pundir Reviewed-by: Amit Pundir Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20221213150304.4189760-1-robert.foss@linaro.org Signed-off-by: Amit Pundir Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/bridge/lontium-lt9611.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 0c6dea9ccb72..660e05fa4a70 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -256,6 +256,7 @@ static int lt9611_pll_setup(struct lt9611 *lt9611, const struct drm_display_mode { 0x8126, 0x55 }, { 0x8127, 0x66 }, { 0x8128, 0x88 }, + { 0x812a, 0x20 }, }; regmap_multi_reg_write(lt9611->regmap, reg_cfg, ARRAY_SIZE(reg_cfg)); From a412ba6b6cc643991f154fa2799aafb957b5fc9e Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 4 Apr 2023 09:25:02 +0800 Subject: [PATCH 2505/4345] Revert "media: ti: cal: fix possible memory leak in cal_ctx_create()" This reverts commit c7a218cbf67fffcd99b76ae3b5e9c2e8bef17c8c. The memory of ctx is allocated by devm_kzalloc in cal_ctx_create, it should not be freed by kfree when cal_ctx_v4l2_init() fails, otherwise kfree() will cause double free, so revert this patch. The memory of ctx is allocated by kzalloc since commit 9e67f24e4d9 ("media: ti-vpe: cal: fix ctx uninitialization"), so the fixes tag of patch c7a218cbf67fis not entirely accurate, mainline should merge this patch, but it should not be merged into 5.10, so we just revert this patch for this branch. Fixes: c7a218cbf67f ("media: ti: cal: fix possible memory leak in cal_ctx_create()") Signed-off-by: Gaosheng Cui Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/ti-vpe/cal.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c index 93121c90d76a..2eef245c31a1 100644 --- a/drivers/media/platform/ti-vpe/cal.c +++ b/drivers/media/platform/ti-vpe/cal.c @@ -624,10 +624,8 @@ static struct cal_ctx *cal_ctx_create(struct cal_dev *cal, int inst) ctx->cport = inst; ret = cal_ctx_v4l2_init(ctx); - if (ret) { - kfree(ctx); + if (ret) return NULL; - } return ctx; } From 2765aca637761db530d7a285bdb85ea1a10318af Mon Sep 17 00:00:00 2001 From: Heming Zhao Date: Mon, 15 Aug 2022 16:57:54 +0800 Subject: [PATCH 2506/4345] ocfs2: fix freeing uninitialized resource on ocfs2_dlm_shutdown commit 550842cc60987b269e31b222283ade3e1b6c7fc8 upstream. After commit 0737e01de9c4 ("ocfs2: ocfs2_mount_volume does cleanup job before return error"), any procedure after ocfs2_dlm_init() fails will trigger crash when calling ocfs2_dlm_shutdown(). ie: On local mount mode, no dlm resource is initialized. If ocfs2_mount_volume() fails in ocfs2_find_slot(), error handling will call ocfs2_dlm_shutdown(), then does dlm resource cleanup job, which will trigger kernel crash. This solution should bypass uninitialized resources in ocfs2_dlm_shutdown(). Link: https://lkml.kernel.org/r/20220815085754.20417-1-heming.zhao@suse.com Fixes: 0737e01de9c4 ("ocfs2: ocfs2_mount_volume does cleanup job before return error") Signed-off-by: Heming Zhao Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/dlmglue.c | 8 +++++--- fs/ocfs2/super.c | 3 +-- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 3e06e9a8cf59..42465693dbdc 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3396,10 +3396,12 @@ void ocfs2_dlm_shutdown(struct ocfs2_super *osb, ocfs2_lock_res_free(&osb->osb_nfs_sync_lockres); ocfs2_lock_res_free(&osb->osb_orphan_scan.os_lockres); - ocfs2_cluster_disconnect(osb->cconn, hangup_pending); - osb->cconn = NULL; + if (osb->cconn) { + ocfs2_cluster_disconnect(osb->cconn, hangup_pending); + osb->cconn = NULL; - ocfs2_dlm_shutdown_debug(osb); + ocfs2_dlm_shutdown_debug(osb); + } } static int ocfs2_drop_lock(struct ocfs2_super *osb, diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 3e0b2e3e00ad..04ce30ae4404 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1922,8 +1922,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) !ocfs2_is_hard_readonly(osb)) hangup_needed = 1; - if (osb->cconn) - ocfs2_dlm_shutdown(osb, hangup_needed); + ocfs2_dlm_shutdown(osb, hangup_needed); ocfs2_blockcheck_stats_debugfs_remove(&osb->osb_ecc_stats); debugfs_remove_recursive(osb->osb_debug_root); From 59dc9767cefbe4b931054bfab39d6aab0bb040f5 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Sat, 1 Oct 2022 13:44:24 +0300 Subject: [PATCH 2507/4345] bpftool: Print newline before '}' for struct with padding only fields [ Upstream commit 44a726c3f23cf762ef4ce3c1709aefbcbe97f62c ] btf_dump_emit_struct_def attempts to print empty structures at a single line, e.g. `struct empty {}`. However, it has to account for a case when there are no regular but some padding fields in the struct. In such case `vlen` would be zero, but size would be non-zero. E.g. here is struct bpf_timer from vmlinux.h before this patch: struct bpf_timer { long: 64; long: 64;}; And after this patch: struct bpf_dynptr { long: 64; long: 64; }; Signed-off-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20221001104425.415768-1-eddyz87@gmail.com Signed-off-by: Sasha Levin --- tools/lib/bpf/btf_dump.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 558d34fbd331..6a8d8ed34b76 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -969,7 +969,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, if (is_struct) btf_dump_emit_bit_padding(d, off, t->size * 8, align, false, lvl + 1); - if (vlen) + /* + * Keep `struct empty {}` on a single line, + * only print newline when there are regular or padding fields. + */ + if (vlen || t->size) btf_dump_printf(d, "\n"); btf_dump_printf(d, "%s}", pfx(lvl)); if (packed) From 14e90335bc7312ae8859e583e8395895a6fe76b9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Kornel=20Dul=C4=99ba?= Date: Tue, 11 Apr 2023 13:49:32 +0000 Subject: [PATCH 2508/4345] Revert "pinctrl: amd: Disable and mask interrupts on resume" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 534e465845ebfb4a97eb5459d3931a0b35e3b9a5 upstream. This reverts commit b26cd9325be4c1fcd331b77f10acb627c560d4d7. This patch introduces a regression on Lenovo Z13, which can't wake from the lid with it applied; and some unspecified AMD based Dell platforms are unable to wake from hitting the power button Signed-off-by: Kornel Dulęba Reviewed-by: Mario Limonciello Link: https://lore.kernel.org/r/20230411134932.292287-1-korneld@chromium.org Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-amd.c | 36 ++++++++++++++++------------------- 1 file changed, 16 insertions(+), 20 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 7bfdf5ad77c4..82b658a3c220 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -764,34 +764,32 @@ static const struct pinconf_ops amd_pinconf_ops = { .pin_config_group_set = amd_pinconf_group_set, }; -static void amd_gpio_irq_init_pin(struct amd_gpio *gpio_dev, int pin) +static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) { - const struct pin_desc *pd; + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; unsigned long flags; u32 pin_reg, mask; + int i; mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | BIT(INTERRUPT_MASK_OFF) | BIT(INTERRUPT_ENABLE_OFF) | BIT(WAKE_CNTRL_OFF_S4); - pd = pin_desc_get(gpio_dev->pctrl, pin); - if (!pd) - return; + for (i = 0; i < desc->npins; i++) { + int pin = desc->pins[i].number; + const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin); - raw_spin_lock_irqsave(&gpio_dev->lock, flags); - pin_reg = readl(gpio_dev->base + pin * 4); - pin_reg &= ~mask; - writel(pin_reg, gpio_dev->base + pin * 4); - raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); -} + if (!pd) + continue; -static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) -{ - struct pinctrl_desc *desc = gpio_dev->pctrl->desc; - int i; + raw_spin_lock_irqsave(&gpio_dev->lock, flags); - for (i = 0; i < desc->npins; i++) - amd_gpio_irq_init_pin(gpio_dev, i); + pin_reg = readl(gpio_dev->base + i * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + i * 4); + + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + } } #ifdef CONFIG_PM_SLEEP @@ -844,10 +842,8 @@ static int amd_gpio_resume(struct device *dev) for (i = 0; i < desc->npins; i++) { int pin = desc->pins[i].number; - if (!amd_gpio_should_save(gpio_dev, pin)) { - amd_gpio_irq_init_pin(gpio_dev, pin); + if (!amd_gpio_should_save(gpio_dev, pin)) continue; - } raw_spin_lock_irqsave(&gpio_dev->lock, flags); gpio_dev->saved_regs[i] |= readl(gpio_dev->base + pin * 4) & PIN_IRQ_PENDING; From df4af0ddf7f0e22ed0ceb8dec222bb96c88af98d Mon Sep 17 00:00:00 2001 From: Oswald Buddenhagen Date: Wed, 5 Apr 2023 22:12:20 +0200 Subject: [PATCH 2509/4345] ALSA: emu10k1: fix capture interrupt handler unlinking commit b09c551c77c7e01dc6e4f3c8bf06b5ffa7b06db5 upstream. Due to two copy/pastos, closing the MIC or EFX capture device would make a running ADC capture hang due to unsetting its interrupt handler. In principle, this would have also allowed dereferencing dangling pointers, but we're actually rather thorough at disabling and flushing the ints. While it may sound like one, this actually wasn't a hypothetical bug: PortAudio will open a capture stream at startup (and close it right away) even if not asked to. If the first device is busy, it will just proceed with the next one ... thus killing a concurrent capture. Signed-off-by: Oswald Buddenhagen Cc: Link: https://lore.kernel.org/r/20230405201220.2197923-1-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/emu10k1/emupcm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index 8d2c101d66a2..1c4388b847d1 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -1232,7 +1232,7 @@ static int snd_emu10k1_capture_mic_close(struct snd_pcm_substream *substream) { struct snd_emu10k1 *emu = snd_pcm_substream_chip(substream); - emu->capture_interrupt = NULL; + emu->capture_mic_interrupt = NULL; emu->pcm_capture_mic_substream = NULL; return 0; } @@ -1340,7 +1340,7 @@ static int snd_emu10k1_capture_efx_close(struct snd_pcm_substream *substream) { struct snd_emu10k1 *emu = snd_pcm_substream_chip(substream); - emu->capture_interrupt = NULL; + emu->capture_efx_interrupt = NULL; emu->pcm_capture_efx_substream = NULL; return 0; } From e63a515d11de1002747187d327f6734ddd6a6f49 Mon Sep 17 00:00:00 2001 From: Oswald Buddenhagen Date: Wed, 5 Apr 2023 22:12:19 +0200 Subject: [PATCH 2510/4345] ALSA: hda/sigmatel: add pin overrides for Intel DP45SG motherboard commit c17f8fd31700392b1bb9e7b66924333568cb3700 upstream. Like the other boards from the D*45* series, this one sets up the outputs not quite correctly. Signed-off-by: Oswald Buddenhagen Cc: Link: https://lore.kernel.org/r/20230405201220.2197826-1-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- Documentation/sound/hd-audio/models.rst | 2 +- sound/pci/hda/patch_sigmatel.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst index 9b52f50a6854..120430450014 100644 --- a/Documentation/sound/hd-audio/models.rst +++ b/Documentation/sound/hd-audio/models.rst @@ -704,7 +704,7 @@ ref no-jd BIOS setup but without jack-detection intel - Intel DG45* mobos + Intel D*45* mobos dell-m6-amic Dell desktops/laptops with analog mics dell-m6-dmic diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 6fc0c4e77cd1..57262fe9a132 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -1955,6 +1955,8 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = { "DFI LanParty", STAC_92HD73XX_REF), SND_PCI_QUIRK(PCI_VENDOR_ID_DFI, 0x3101, "DFI LanParty", STAC_92HD73XX_REF), + SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x5001, + "Intel DP45SG", STAC_92HD73XX_INTEL), SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x5002, "Intel DG45ID", STAC_92HD73XX_INTEL), SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x5003, From 69108a8a45c61461bddca06e084ad5b2e7111612 Mon Sep 17 00:00:00 2001 From: Oswald Buddenhagen Date: Wed, 5 Apr 2023 22:12:19 +0200 Subject: [PATCH 2511/4345] ALSA: i2c/cs8427: fix iec958 mixer control deactivation commit e98e7a82bca2b6dce3e03719cff800ec913f9af7 upstream. snd_cs8427_iec958_active() would always delete SNDRV_CTL_ELEM_ACCESS_INACTIVE, even though the function has an argument `active`. Signed-off-by: Oswald Buddenhagen Cc: Link: https://lore.kernel.org/r/20230405201219.2197811-1-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/i2c/cs8427.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/sound/i2c/cs8427.c b/sound/i2c/cs8427.c index 8634d4f466b3..e8c4c39cea12 100644 --- a/sound/i2c/cs8427.c +++ b/sound/i2c/cs8427.c @@ -553,10 +553,13 @@ int snd_cs8427_iec958_active(struct snd_i2c_device *cs8427, int active) if (snd_BUG_ON(!cs8427)) return -ENXIO; chip = cs8427->private_data; - if (active) + if (active) { memcpy(chip->playback.pcm_status, chip->playback.def_status, 24); - chip->playback.pcm_ctl->vd[0].access &= ~SNDRV_CTL_ELEM_ACCESS_INACTIVE; + chip->playback.pcm_ctl->vd[0].access &= ~SNDRV_CTL_ELEM_ACCESS_INACTIVE; + } else { + chip->playback.pcm_ctl->vd[0].access |= SNDRV_CTL_ELEM_ACCESS_INACTIVE; + } snd_ctl_notify(cs8427->bus->card, SNDRV_CTL_EVENT_MASK_VALUE | SNDRV_CTL_EVENT_MASK_INFO, &chip->playback.pcm_ctl->id); From 8f6a20a4f4ce25391cf5afe941f2e0db95148113 Mon Sep 17 00:00:00 2001 From: Xu Biang Date: Thu, 6 Apr 2023 06:28:01 -0700 Subject: [PATCH 2512/4345] ALSA: firewire-tascam: add missing unwind goto in snd_tscm_stream_start_duplex() commit fb4a624f88f658c7b7ae124452bd42eaa8ac7168 upstream. Smatch Warns: sound/firewire/tascam/tascam-stream.c:493 snd_tscm_stream_start_duplex() warn: missing unwind goto? The direct return will cause the stream list of "&tscm->domain" unemptied and the session in "tscm" unfinished if amdtp_domain_start() returns with an error. Fix this by changing the direct return to a goto which will empty the stream list of "&tscm->domain" and finish the session in "tscm". The snd_tscm_stream_start_duplex() function is called in the prepare callback of PCM. According to "ALSA Kernel API Documentation", the prepare callback of PCM will be called many times at each setup. So, if the "&d->streams" list is not emptied, when the prepare callback is called next time, snd_tscm_stream_start_duplex() will receive -EBUSY from amdtp_domain_add_stream() that tries to add an existing stream to the domain. The error handling code after the "error" label will be executed in this case, and the "&d->streams" list will be emptied. So not emptying the "&d->streams" list will not cause an issue. But it is more efficient and readable to empty it on the first error by changing the direct return to a goto statement. The session in "tscm" has been begun before amdtp_domain_start(), so it needs to be finished when amdtp_domain_start() fails. Fixes: c281d46a51e3 ("ALSA: firewire-tascam: support AMDTP domain") Signed-off-by: Xu Biang Reviewed-by: Dan Carpenter Acked-by: Takashi Sakamoto Cc: Link: https://lore.kernel.org/r/20230406132801.105108-1-xubiang@hust.edu.cn Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/firewire/tascam/tascam-stream.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/firewire/tascam/tascam-stream.c b/sound/firewire/tascam/tascam-stream.c index eb07e1decf9b..47de9727ac73 100644 --- a/sound/firewire/tascam/tascam-stream.c +++ b/sound/firewire/tascam/tascam-stream.c @@ -475,7 +475,7 @@ int snd_tscm_stream_start_duplex(struct snd_tscm *tscm, unsigned int rate) err = amdtp_domain_start(&tscm->domain, 0); if (err < 0) - return err; + goto error; if (!amdtp_stream_wait_callback(&tscm->rx_stream, CALLBACK_TIMEOUT) || From 8533fe864574c4fbaf62d1bc392929a025df122a Mon Sep 17 00:00:00 2001 From: Oswald Buddenhagen Date: Wed, 5 Apr 2023 22:12:20 +0200 Subject: [PATCH 2513/4345] ALSA: hda/sigmatel: fix S/PDIF out on Intel D*45* motherboards commit f342ac00da1064eb4f94b1f4bcacbdfea955797a upstream. The BIOS botches this one completely - it says the 2nd S/PDIF output is used, while in fact it's the 1st one. This is tested on DP45SG, but I'm assuming it's valid for the other boards in the series as well. Also add some comments regarding the pins. FWIW, the codec is apparently still sold by Tempo Semiconductor, Inc., where one can download the documentation. Signed-off-by: Oswald Buddenhagen Cc: Link: https://lore.kernel.org/r/20230405201220.2197826-2-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_sigmatel.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 57262fe9a132..76c5a2b64ef5 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -1707,6 +1707,7 @@ static const struct snd_pci_quirk stac925x_fixup_tbl[] = { }; static const struct hda_pintbl ref92hd73xx_pin_configs[] = { + // Port A-H { 0x0a, 0x02214030 }, { 0x0b, 0x02a19040 }, { 0x0c, 0x01a19020 }, @@ -1715,9 +1716,12 @@ static const struct hda_pintbl ref92hd73xx_pin_configs[] = { { 0x0f, 0x01014010 }, { 0x10, 0x01014020 }, { 0x11, 0x01014030 }, + // CD in { 0x12, 0x02319040 }, + // Digial Mic ins { 0x13, 0x90a000f0 }, { 0x14, 0x90a000f0 }, + // Digital outs { 0x22, 0x01452050 }, { 0x23, 0x01452050 }, {} @@ -1758,6 +1762,7 @@ static const struct hda_pintbl alienware_m17x_pin_configs[] = { }; static const struct hda_pintbl intel_dg45id_pin_configs[] = { + // Analog outputs { 0x0a, 0x02214230 }, { 0x0b, 0x02A19240 }, { 0x0c, 0x01013214 }, @@ -1765,6 +1770,9 @@ static const struct hda_pintbl intel_dg45id_pin_configs[] = { { 0x0e, 0x01A19250 }, { 0x0f, 0x01011212 }, { 0x10, 0x01016211 }, + // Digital output + { 0x22, 0x01451380 }, + { 0x23, 0x40f000f0 }, {} }; From d9ba36c22a7bb09d6bac4cc2f243eff05da53f43 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 6 Apr 2023 09:33:09 -0700 Subject: [PATCH 2514/4345] Bluetooth: L2CAP: Fix use-after-free in l2cap_disconnect_{req,rsp} commit a2a9339e1c9deb7e1e079e12e27a0265aea8421a upstream. Similar to commit d0be8347c623 ("Bluetooth: L2CAP: Fix use-after-free caused by l2cap_chan_put"), just use l2cap_chan_hold_unless_zero to prevent referencing a channel that is about to be destroyed. Cc: stable@kernel.org Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Min Li Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/l2cap_core.c | 24 ++++++------------------ 1 file changed, 6 insertions(+), 18 deletions(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 367b1dec2e75..f9d2ce9cee36 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4647,33 +4647,27 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, BT_DBG("scid 0x%4.4x dcid 0x%4.4x", scid, dcid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, dcid); + chan = l2cap_get_chan_by_scid(conn, dcid); if (!chan) { - mutex_unlock(&conn->chan_lock); cmd_reject_invalid_cid(conn, cmd->ident, dcid, scid); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - rsp.dcid = cpu_to_le16(chan->scid); rsp.scid = cpu_to_le16(chan->dcid); l2cap_send_cmd(conn, cmd->ident, L2CAP_DISCONN_RSP, sizeof(rsp), &rsp); chan->ops->set_shutdown(chan); + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, ECONNRESET); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } @@ -4693,33 +4687,27 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, BT_DBG("dcid 0x%4.4x scid 0x%4.4x", dcid, scid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, scid); + chan = l2cap_get_chan_by_scid(conn, scid); if (!chan) { mutex_unlock(&conn->chan_lock); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); return 0; } + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, 0); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } From f7ec5ca433ceead8d9d78fd2febff094f289441d Mon Sep 17 00:00:00 2001 From: Min Li Date: Sat, 4 Mar 2023 22:23:30 +0800 Subject: [PATCH 2515/4345] Bluetooth: Fix race condition in hidp_session_thread commit c95930abd687fcd1aa040dc4fe90dff947916460 upstream. There is a potential race condition in hidp_session_thread that may lead to use-after-free. For instance, the timer is active while hidp_del_timer is called in hidp_session_thread(). After hidp_session_put, then 'session' will be freed, causing kernel panic when hidp_idle_timeout is running. The solution is to use del_timer_sync instead of del_timer. Here is the call trace: ? hidp_session_probe+0x780/0x780 call_timer_fn+0x2d/0x1e0 __run_timers.part.0+0x569/0x940 hidp_session_probe+0x780/0x780 call_timer_fn+0x1e0/0x1e0 ktime_get+0x5c/0xf0 lapic_next_deadline+0x2c/0x40 clockevents_program_event+0x205/0x320 run_timer_softirq+0xa9/0x1b0 __do_softirq+0x1b9/0x641 __irq_exit_rcu+0xdc/0x190 irq_exit_rcu+0xe/0x20 sysvec_apic_timer_interrupt+0xa1/0xc0 Cc: stable@vger.kernel.org Signed-off-by: Min Li Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/hidp/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 0db48c812662..b946a6379433 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -433,7 +433,7 @@ static void hidp_set_timer(struct hidp_session *session) static void hidp_del_timer(struct hidp_session *session) { if (session->idle_to > 0) - del_timer(&session->timer); + del_timer_sync(&session->timer); } static void hidp_process_report(struct hidp_session *session, int type, From 3576e08f19dce249581ab5fb54fc6ef2ead4a105 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 22 Jun 2022 20:45:18 +0200 Subject: [PATCH 2516/4345] btrfs: print checksum type and implementation at mount time commit c8a5f8ca9a9c7d5c5bc31d54f47ea9d86f93ed69 upstream. Per user request, print the checksum type and implementation at mount time among the messages. The checksum is user configurable and the actual crypto implementation is useful to see for performance reasons. The same information is also available after mount in /sys/fs/FSID/checksum file. Example: [25.323662] BTRFS info (device vdb): using sha256 (sha256-generic) checksum algorithm Link: https://github.com/kdave/btrfs-progs/issues/483 Reviewed-by: Johannes Thumshirn Reviewed-by: Nikolay Borisov Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f2abd8bfd4a0..217509678e8f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2246,6 +2246,9 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) fs_info->csum_shash = csum_shash; + btrfs_info(fs_info, "using %s (%s) checksum algorithm", + btrfs_super_csum_name(csum_type), + crypto_shash_driver_name(csum_shash)); return 0; } From 5635e69406565f3a15cf99b539138b22835ffe3f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 29 Mar 2023 09:13:05 +0900 Subject: [PATCH 2517/4345] btrfs: fix fast csum implementation detection commit 68d99ab0e9221ef54506f827576c5a914680eeaf upstream. The BTRFS_FS_CSUM_IMPL_FAST flag is currently set whenever a non-generic crc32c is detected, which is the incorrect check if the file system uses a different checksumming algorithm. Refactor the code to only check this if crc32c is actually used. Note that in an ideal world the information if an algorithm is hardware accelerated or not should be provided by the crypto API instead, but that's left for another day. CC: stable@vger.kernel.org # 5.4.x: c8a5f8ca9a9c: btrfs: print checksum type and implementation at mount time CC: stable@vger.kernel.org # 5.4.x Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 14 ++++++++++++++ fs/btrfs/super.c | 2 -- 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 217509678e8f..2a7778a88f03 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2246,6 +2246,20 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) fs_info->csum_shash = csum_shash; + /* + * Check if the checksum implementation is a fast accelerated one. + * As-is this is a bit of a hack and should be replaced once the csum + * implementations provide that information themselves. + */ + switch (csum_type) { + case BTRFS_CSUM_TYPE_CRC32: + if (!strstr(crypto_shash_driver_name(csum_shash), "generic")) + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; + default: + break; + } + btrfs_info(fs_info, "using %s (%s) checksum algorithm", btrfs_super_csum_name(csum_type), crypto_shash_driver_name(csum_shash)); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8bf8cdb62a3a..b33505330e33 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1692,8 +1692,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, } else { snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); btrfs_sb(s)->bdev_holder = fs_type; - if (!strstr(crc32c_impl(), "generic")) - set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); error = btrfs_fill_super(s, fs_devices, data); } if (!error) From 0d07ea8d385cb24c03f13b661e8e8954c9c76467 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 4 Apr 2023 21:39:34 +0200 Subject: [PATCH 2518/4345] fbmem: Reject FB_ACTIVATE_KD_TEXT from userspace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6fd33a3333c7916689b8f051a185defe4dd515b0 upstream. This is an oversight from dc5bdb68b5b3 ("drm/fb-helper: Fix vt restore") - I failed to realize that nasty userspace could set this. It's not pretty to mix up kernel-internal and userspace uapi flags like this, but since the entire fb_var_screeninfo structure is uapi we'd need to either add a new parameter to the ->fb_set_par callback and fb_set_par() function, which has a _lot_ of users. Or some other fairly ugly side-channel int fb_info. Neither is a pretty prospect. Instead just correct the issue at hand by filtering out this kernel-internal flag in the ioctl handling code. Reviewed-by: Javier Martinez Canillas Acked-by: Maarten Lankhorst Signed-off-by: Daniel Vetter Fixes: dc5bdb68b5b3 ("drm/fb-helper: Fix vt restore") Cc: Alex Deucher Cc: shlomo@fastmail.com Cc: Michel Dänzer Cc: Noralf Trønnes Cc: Thomas Zimmermann Cc: Daniel Vetter Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: David Airlie Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Cc: # v5.7+ Cc: Bartlomiej Zolnierkiewicz Cc: Geert Uytterhoeven Cc: Nathan Chancellor Cc: Qiujun Huang Cc: Peter Rosin Cc: linux-fbdev@vger.kernel.org Cc: Helge Deller Cc: Sam Ravnborg Cc: Geert Uytterhoeven Cc: Samuel Thibault Cc: Tetsuo Handa Cc: Shigeru Yoshida Link: https://patchwork.freedesktop.org/patch/msgid/20230404193934.472457-1-daniel.vetter@ffwll.ch Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/core/fbmem.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index d787a344b3b8..1704deaf4152 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1117,6 +1117,8 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd, case FBIOPUT_VSCREENINFO: if (copy_from_user(&var, argp, sizeof(var))) return -EFAULT; + /* only for kernel-internal use */ + var.activate &= ~FB_ACTIVATE_KD_TEXT; console_lock(); lock_fb_info(info); ret = fbcon_modechange_possible(info, &var); From 441e57ff87c273de0152a0ee896e89772618f924 Mon Sep 17 00:00:00 2001 From: Bang Li Date: Wed, 29 Mar 2023 00:30:12 +0800 Subject: [PATCH 2519/4345] mtdblock: tolerate corrected bit-flips commit 0c3089601f064d80b3838eceb711fcac04bceaad upstream. mtd_read() may return -EUCLEAN in case of corrected bit-flips.This particular condition should not be treated like an error. Signed-off-by: Bang Li Fixes: e47f68587b82 ("mtd: check for max_bitflips in mtd_read_oob()") Cc: # v3.7 Acked-by: Richard Weinberger Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230328163012.4264-1-libang.linuxer@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/mtdblock.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c index 32e52d83b961..9e5bbb545702 100644 --- a/drivers/mtd/mtdblock.c +++ b/drivers/mtd/mtdblock.c @@ -153,7 +153,7 @@ static int do_cached_write (struct mtdblk_dev *mtdblk, unsigned long pos, mtdblk->cache_state = STATE_EMPTY; ret = mtd_read(mtd, sect_start, sect_size, &retlen, mtdblk->cache_data); - if (ret) + if (ret && !mtd_is_bitflip(ret)) return ret; if (retlen != sect_size) return -EIO; @@ -188,8 +188,12 @@ static int do_cached_read (struct mtdblk_dev *mtdblk, unsigned long pos, pr_debug("mtdblock: read on \"%s\" at 0x%lx, size 0x%x\n", mtd->name, pos, len); - if (!sect_size) - return mtd_read(mtd, pos, len, &retlen, buf); + if (!sect_size) { + ret = mtd_read(mtd, pos, len, &retlen, buf); + if (ret && !mtd_is_bitflip(ret)) + return ret; + return 0; + } while (len > 0) { unsigned long sect_start = (pos/sect_size)*sect_size; @@ -209,7 +213,7 @@ static int do_cached_read (struct mtdblk_dev *mtdblk, unsigned long pos, memcpy (buf, mtdblk->cache_data + offset, size); } else { ret = mtd_read(mtd, pos, size, &retlen, buf); - if (ret) + if (ret && !mtd_is_bitflip(ret)) return ret; if (retlen != size) return -EIO; From 6b0e719192647351b112a9d43cfd83b55d44ec75 Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Wed, 29 Mar 2023 10:47:26 +0300 Subject: [PATCH 2520/4345] mtd: rawnand: meson: fix bitmask for length in command word commit 93942b70461574ca7fc3d91494ca89b16a4c64c7 upstream. Valid mask is 0x3FFF, without this patch the following problems were found: 1) [ 0.938914] Could not find a valid ONFI parameter page, trying bit-wise majority to recover it [ 0.947384] ONFI parameter recovery failed, aborting 2) Read with disabled ECC mode was broken. Fixes: 8fae856c5350 ("mtd: rawnand: meson: add support for Amlogic NAND flash controller") Cc: Signed-off-by: Arseniy Krasnov Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/3794ffbf-dfea-e96f-1f97-fe235b005e19@sberdevices.ru Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/raw/meson_nand.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index dc631c514318..228612d82f31 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -276,7 +276,7 @@ static void meson_nfc_cmd_access(struct nand_chip *nand, int raw, bool dir, if (raw) { len = mtd->writesize + mtd->oobsize; - cmd = (len & GENMASK(5, 0)) | scrambler | DMA_DIR(dir); + cmd = (len & GENMASK(13, 0)) | scrambler | DMA_DIR(dir); writel(cmd, nfc->reg_base + NFC_REG_CMD); return; } @@ -540,7 +540,7 @@ static int meson_nfc_read_buf(struct nand_chip *nand, u8 *buf, int len) if (ret) goto out; - cmd = NFC_CMD_N2M | (len & GENMASK(5, 0)); + cmd = NFC_CMD_N2M | (len & GENMASK(13, 0)); writel(cmd, nfc->reg_base + NFC_REG_CMD); meson_nfc_drain_cmd(nfc); @@ -564,7 +564,7 @@ static int meson_nfc_write_buf(struct nand_chip *nand, u8 *buf, int len) if (ret) return ret; - cmd = NFC_CMD_M2N | (len & GENMASK(5, 0)); + cmd = NFC_CMD_M2N | (len & GENMASK(13, 0)); writel(cmd, nfc->reg_base + NFC_REG_CMD); meson_nfc_drain_cmd(nfc); From 9e946e4e8c3d5ce85ab002459e31c8e39c1ff195 Mon Sep 17 00:00:00 2001 From: Christophe Kerello Date: Tue, 28 Mar 2023 17:58:18 +0200 Subject: [PATCH 2521/4345] mtd: rawnand: stm32_fmc2: remove unsupported EDO mode commit f71e0e329c152c7f11ddfd97ffc62aba152fad3f upstream. Remove the EDO mode support from as the FMC2 controller does not support the feature. Signed-off-by: Christophe Kerello Fixes: 2cd457f328c1 ("mtd: rawnand: stm32_fmc2: add STM32 FMC2 NAND flash controller driver") Cc: stable@vger.kernel.org #v5.4+ Reviewed-by: Tudor Ambarus Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230328155819.225521-2-christophe.kerello@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/raw/stm32_fmc2_nand.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index 550bda4d1415..87d12ebe6283 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -1525,6 +1525,9 @@ static int stm32_fmc2_nfc_setup_interface(struct nand_chip *chip, int chipnr, if (IS_ERR(sdrt)) return PTR_ERR(sdrt); + if (sdrt->tRC_min < 30000) + return -EOPNOTSUPP; + if (chipnr == NAND_DATA_IFACE_CHECK_ONLY) return 0; From 6e2845284b129eee875cdaf66e1670d2dd684ebb Mon Sep 17 00:00:00 2001 From: Christophe Kerello Date: Tue, 28 Mar 2023 17:58:19 +0200 Subject: [PATCH 2522/4345] mtd: rawnand: stm32_fmc2: use timings.mode instead of checking tRC_min commit ddbb664b6ab8de7dffa388ae0c88cd18616494e5 upstream. Use timings.mode value instead of checking tRC_min timing for EDO mode support. Signed-off-by: Christophe Kerello Fixes: 2cd457f328c1 ("mtd: rawnand: stm32_fmc2: add STM32 FMC2 NAND flash controller driver") Cc: stable@vger.kernel.org #v5.10+ Reviewed-by: Tudor Ambarus Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230328155819.225521-3-christophe.kerello@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/raw/stm32_fmc2_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index 87d12ebe6283..c0c47f31c100 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -1525,7 +1525,7 @@ static int stm32_fmc2_nfc_setup_interface(struct nand_chip *chip, int chipnr, if (IS_ERR(sdrt)) return PTR_ERR(sdrt); - if (sdrt->tRC_min < 30000) + if (conf->timings.mode > 3) return -EOPNOTSUPP; if (chipnr == NAND_DATA_IFACE_CHECK_ONLY) From 8a886f01b85d9575c6a197dd2e8f90d18e303d0a Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Thu, 16 Mar 2023 10:36:24 +0800 Subject: [PATCH 2523/4345] clk: sprd: set max_register according to mapping range [ Upstream commit 47d43086531f10539470a63e8ad92803e686a3dd ] In sprd clock driver, regmap_config.max_register was set to a fixed value which is likely larger than the address range configured in device tree, when reading registers through debugfs it would cause access violation. Fixes: d41f59fd92f2 ("clk: sprd: Add common infrastructure") Signed-off-by: Chunyan Zhang Link: https://lore.kernel.org/r/20230316023624.758204-1-chunyan.zhang@unisoc.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/sprd/common.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/clk/sprd/common.c b/drivers/clk/sprd/common.c index ce81e4087a8f..2bfbab8db94b 100644 --- a/drivers/clk/sprd/common.c +++ b/drivers/clk/sprd/common.c @@ -17,7 +17,6 @@ static const struct regmap_config sprdclk_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0xffff, .fast_io = true, }; @@ -43,6 +42,8 @@ int sprd_clk_regmap_init(struct platform_device *pdev, struct device *dev = &pdev->dev; struct device_node *node = dev->of_node, *np; struct regmap *regmap; + struct resource *res; + struct regmap_config reg_config = sprdclk_regmap_config; if (of_find_property(node, "sprd,syscon", NULL)) { regmap = syscon_regmap_lookup_by_phandle(node, "sprd,syscon"); @@ -59,12 +60,14 @@ int sprd_clk_regmap_init(struct platform_device *pdev, return PTR_ERR(regmap); } } else { - base = devm_platform_ioremap_resource(pdev, 0); + base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(base)) return PTR_ERR(base); + reg_config.max_register = resource_size(res) - reg_config.reg_stride; + regmap = devm_regmap_init_mmio(&pdev->dev, base, - &sprdclk_regmap_config); + ®_config); if (IS_ERR(regmap)) { pr_err("failed to init regmap\n"); return PTR_ERR(regmap); From a1d2fb5d13c98acf9d3398e77affeae9fda3e5fa Mon Sep 17 00:00:00 2001 From: Meir Lichtinger Date: Mon, 26 Oct 2020 15:37:38 +0200 Subject: [PATCH 2524/4345] IB/mlx5: Add support for NDR link speed [ Upstream commit f946e45f59ef01ff54ffb3b1eba3a8e7915e7326 ] The IBTA specification has new speed - NDR. That speed supports signaling rate of 100Gb. mlx5 IB driver translates link modes reported by ConnectX device to IB speed and width. Added translation of new 100Gb, 200Gb and 400Gb link modes to NDR IB type and width of x1, x2 or x4 respectively. Link: https://lore.kernel.org/r/20201026133738.1340432-3-leon@kernel.org Signed-off-by: Meir Lichtinger Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe Stable-dep-of: 88c9483faf15 ("IB/mlx5: Add support for 400G_8X lane speed") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx5/main.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index eb69bec77e5d..638da09ff838 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -425,10 +425,22 @@ static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u16 *active_speed, *active_width = IB_WIDTH_2X; *active_speed = IB_SPEED_HDR; break; + case MLX5E_PROT_MASK(MLX5E_100GAUI_1_100GBASE_CR_KR): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_NDR; + break; case MLX5E_PROT_MASK(MLX5E_200GAUI_4_200GBASE_CR4_KR4): *active_width = IB_WIDTH_4X; *active_speed = IB_SPEED_HDR; break; + case MLX5E_PROT_MASK(MLX5E_200GAUI_2_200GBASE_CR2_KR2): + *active_width = IB_WIDTH_2X; + *active_speed = IB_SPEED_NDR; + break; + case MLX5E_PROT_MASK(MLX5E_400GAUI_4_400GBASE_CR4_KR4): + *active_width = IB_WIDTH_4X; + *active_speed = IB_SPEED_NDR; + break; default: return -EINVAL; } From 5e567fd2961135f45c82dfca3867c49ede3cdd85 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Thu, 16 Mar 2023 15:40:49 +0200 Subject: [PATCH 2525/4345] IB/mlx5: Add support for 400G_8X lane speed [ Upstream commit 88c9483faf15ada14eca82714114656893063458 ] Currently, when driver queries PTYS to report which link speed is being used on its RoCE ports, it does not check the case of having 400Gbps transmitted over 8 lanes. Thus it fails to report the said speed and instead it defaults to report 10G over 4 lanes. Add a check for the said speed when querying PTYS and report it back correctly when needed. Fixes: 08e8676f1607 ("IB/mlx5: Add support for 50Gbps per lane link modes") Signed-off-by: Maher Sanalla Reviewed-by: Aya Levin Reviewed-by: Saeed Mahameed Link: https://lore.kernel.org/r/ec9040548d119d22557d6a4b4070d6f421701fd4.1678973994.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx5/main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 638da09ff838..5ef37902e96b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -437,6 +437,10 @@ static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u16 *active_speed, *active_width = IB_WIDTH_2X; *active_speed = IB_SPEED_NDR; break; + case MLX5E_PROT_MASK(MLX5E_400GAUI_8): + *active_width = IB_WIDTH_8X; + *active_speed = IB_SPEED_HDR; + break; case MLX5E_PROT_MASK(MLX5E_400GAUI_4_400GBASE_CR4_KR4): *active_width = IB_WIDTH_4X; *active_speed = IB_SPEED_NDR; From ae11498851423d6de27aebfe12a5ee85060ab1d5 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Mon, 20 Mar 2023 12:59:55 +0200 Subject: [PATCH 2526/4345] RDMA/cma: Allow UD qp_type to join multicast only [ Upstream commit 58e84f6b3e84e46524b7e5a916b53c1ad798bc8f ] As for multicast: - The SIDR is the only mode that makes sense; - Besides PS_UDP, other port spaces like PS_IB is also allowed, as it is UD compatible. In this case qkey also needs to be set [1]. This patch allows only UD qp_type to join multicast, and set qkey to default if it's not set, to fix an uninit-value error: the ib->rec.qkey field is accessed without being initialized. ===================================================== BUG: KMSAN: uninit-value in cma_set_qkey drivers/infiniband/core/cma.c:510 [inline] BUG: KMSAN: uninit-value in cma_make_mc_event+0xb73/0xe00 drivers/infiniband/core/cma.c:4570 cma_set_qkey drivers/infiniband/core/cma.c:510 [inline] cma_make_mc_event+0xb73/0xe00 drivers/infiniband/core/cma.c:4570 cma_iboe_join_multicast drivers/infiniband/core/cma.c:4782 [inline] rdma_join_multicast+0x2b83/0x30a0 drivers/infiniband/core/cma.c:4814 ucma_process_join+0xa76/0xf60 drivers/infiniband/core/ucma.c:1479 ucma_join_multicast+0x1e3/0x250 drivers/infiniband/core/ucma.c:1546 ucma_write+0x639/0x6d0 drivers/infiniband/core/ucma.c:1732 vfs_write+0x8ce/0x2030 fs/read_write.c:588 ksys_write+0x28c/0x520 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __ia32_sys_write+0xdb/0x120 fs/read_write.c:652 do_syscall_32_irqs_on arch/x86/entry/common.c:114 [inline] __do_fast_syscall_32+0x96/0xf0 arch/x86/entry/common.c:180 do_fast_syscall_32+0x34/0x70 arch/x86/entry/common.c:205 do_SYSENTER_32+0x1b/0x20 arch/x86/entry/common.c:248 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c Local variable ib.i created at: cma_iboe_join_multicast drivers/infiniband/core/cma.c:4737 [inline] rdma_join_multicast+0x586/0x30a0 drivers/infiniband/core/cma.c:4814 ucma_process_join+0xa76/0xf60 drivers/infiniband/core/ucma.c:1479 CPU: 0 PID: 29874 Comm: syz-executor.3 Not tainted 5.16.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ===================================================== [1] https://lore.kernel.org/linux-rdma/20220117183832.GD84788@nvidia.com/ Fixes: b5de0c60cc30 ("RDMA/cma: Fix use after free race in roce multicast join") Reported-by: syzbot+8fcbb77276d43cc8b693@syzkaller.appspotmail.com Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/58a4a98323b5e6b1282e83f6b76960d06e43b9fa.1679309909.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/cma.c | 60 ++++++++++++++++++++--------------- 1 file changed, 34 insertions(+), 26 deletions(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 9ed5de38e372..fdcad8d6a5a0 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -505,22 +505,11 @@ static inline unsigned short cma_family(struct rdma_id_private *id_priv) return id_priv->id.route.addr.src_addr.ss_family; } -static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) +static int cma_set_default_qkey(struct rdma_id_private *id_priv) { struct ib_sa_mcmember_rec rec; int ret = 0; - if (id_priv->qkey) { - if (qkey && id_priv->qkey != qkey) - return -EINVAL; - return 0; - } - - if (qkey) { - id_priv->qkey = qkey; - return 0; - } - switch (id_priv->id.ps) { case RDMA_PS_UDP: case RDMA_PS_IB: @@ -540,6 +529,16 @@ static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) return ret; } +static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) +{ + if (!qkey || + (id_priv->qkey && (id_priv->qkey != qkey))) + return -EINVAL; + + id_priv->qkey = qkey; + return 0; +} + static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) { dev_addr->dev_type = ARPHRD_INFINIBAND; @@ -1107,7 +1106,7 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT; if (id_priv->id.qp_type == IB_QPT_UD) { - ret = cma_set_qkey(id_priv, 0); + ret = cma_set_default_qkey(id_priv); if (ret) return ret; @@ -4312,7 +4311,10 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv, memset(&rep, 0, sizeof rep); rep.status = status; if (status == IB_SIDR_SUCCESS) { - ret = cma_set_qkey(id_priv, qkey); + if (qkey) + ret = cma_set_qkey(id_priv, qkey); + else + ret = cma_set_default_qkey(id_priv); if (ret) return ret; rep.qp_num = id_priv->qp_num; @@ -4516,9 +4518,7 @@ static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, enum ib_gid_type gid_type; struct net_device *ndev; - if (!status) - status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); - else + if (status) pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status); @@ -4546,7 +4546,7 @@ static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, } event->param.ud.qp_num = 0xFFFFFF; - event->param.ud.qkey = be32_to_cpu(multicast->rec.qkey); + event->param.ud.qkey = id_priv->qkey; out: if (ndev) @@ -4565,8 +4565,11 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING) goto out; - cma_make_mc_event(status, id_priv, multicast, &event, mc); - ret = cma_cm_event_handler(id_priv, &event); + ret = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); + if (!ret) { + cma_make_mc_event(status, id_priv, multicast, &event, mc); + ret = cma_cm_event_handler(id_priv, &event); + } rdma_destroy_ah_attr(&event.param.ud.ah_attr); WARN_ON(ret); @@ -4619,9 +4622,11 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv, if (ret) return ret; - ret = cma_set_qkey(id_priv, 0); - if (ret) - return ret; + if (!id_priv->qkey) { + ret = cma_set_default_qkey(id_priv); + if (ret) + return ret; + } cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid); rec.qkey = cpu_to_be32(id_priv->qkey); @@ -4709,9 +4714,6 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, cma_iboe_set_mgid(addr, &ib.rec.mgid, gid_type); ib.rec.pkey = cpu_to_be16(0xffff); - if (id_priv->id.ps == RDMA_PS_UDP) - ib.rec.qkey = cpu_to_be32(RDMA_UDP_QKEY); - if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!ndev) @@ -4737,6 +4739,9 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, if (err || !ib.rec.mtu) return err ?: -EINVAL; + if (!id_priv->qkey) + cma_set_default_qkey(id_priv); + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &ib.rec.port_gid); INIT_WORK(&mc->iboe_join.work, cma_iboe_join_work_handler); @@ -4762,6 +4767,9 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, READ_ONCE(id_priv->state) != RDMA_CM_ADDR_RESOLVED)) return -EINVAL; + if (id_priv->id.qp_type != IB_QPT_UD) + return -EINVAL; + mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return -ENOMEM; From 9266e939d76279d8710196d86215ba2be6345041 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Mon, 13 Mar 2023 22:43:25 +0800 Subject: [PATCH 2527/4345] 9p/xen : Fix use after free bug in xen_9pfs_front_remove due to race condition [ Upstream commit ea4f1009408efb4989a0f139b70fb338e7f687d0 ] In xen_9pfs_front_probe, it calls xen_9pfs_front_alloc_dataring to init priv->rings and bound &ring->work with p9_xen_response. When it calls xen_9pfs_front_event_handler to handle IRQ requests, it will finally call schedule_work to start the work. When we call xen_9pfs_front_remove to remove the driver, there may be a sequence as follows: Fix it by finishing the work before cleanup in xen_9pfs_front_free. Note that, this bug is found by static analysis, which might be false positive. CPU0 CPU1 |p9_xen_response xen_9pfs_front_remove| xen_9pfs_front_free| kfree(priv) | //free priv | |p9_tag_lookup |//use priv->client Fixes: 71ebd71921e4 ("xen/9pfs: connect to the backend") Signed-off-by: Zheng Wang Reviewed-by: Michal Swiatkowski Signed-off-by: Eric Van Hensbergen Signed-off-by: Sasha Levin --- net/9p/trans_xen.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 220e8f4ac0cf..da056170849b 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -300,6 +300,10 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) write_unlock(&xen_9pfs_lock); for (i = 0; i < priv->num_rings; i++) { + struct xen_9pfs_dataring *ring = &priv->rings[i]; + + cancel_work_sync(&ring->work); + if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) From 8a1fdb35459d5738cd362c8bb33c2ba743c29c17 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Wed, 5 Apr 2023 23:31:18 -0700 Subject: [PATCH 2528/4345] niu: Fix missing unwind goto in niu_alloc_channels() [ Upstream commit 8ce07be703456acb00e83d99f3b8036252c33b02 ] Smatch reports: drivers/net/ethernet/sun/niu.c:4525 niu_alloc_channels() warn: missing unwind goto? If niu_rbr_fill() fails, then we are directly returning 'err' without freeing the channels. Fix this by changing direct return to a goto 'out_err'. Fixes: a3138df9f20e ("[NIU]: Add Sun Neptune ethernet driver.") Signed-off-by: Harshit Mogalapalli Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/sun/niu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 860644d182ab..1a269fa8c1a0 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -4503,7 +4503,7 @@ static int niu_alloc_channels(struct niu *np) err = niu_rbr_fill(np, rp, GFP_KERNEL); if (err) - return err; + goto out_err; } tx_rings = kcalloc(num_tx_rings, sizeof(struct tx_ring_info), From 389dab6142d742f91010f38de0f1f2f440b97e1b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 25 Mar 2021 11:08:13 -0700 Subject: [PATCH 2529/4345] sysctl: add proc_dou8vec_minmax() [ Upstream commit cb9444130662c6c13022579c861098f212db2562 ] Networking has many sysctls that could fit in one u8. This patch adds proc_dou8vec_minmax() for this purpose. Note that the .extra1 and .extra2 fields are pointing to integers, because it makes conversions easier. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Stable-dep-of: dc5110c2d959 ("tcp: restrict net.ipv4.tcp_app_win") Signed-off-by: Sasha Levin --- fs/proc/proc_sysctl.c | 6 ++++ include/linux/sysctl.h | 2 ++ kernel/sysctl.c | 65 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 73 insertions(+) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index cd7c6c4af83a..1655b7b2a5ab 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1106,6 +1106,11 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table) err |= sysctl_err(path, table, "array not allowed"); } + if (table->proc_handler == proc_dou8vec_minmax) { + if (table->maxlen != sizeof(u8)) + err |= sysctl_err(path, table, "array not allowed"); + } + return err; } @@ -1121,6 +1126,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) (table->proc_handler == proc_douintvec) || (table->proc_handler == proc_douintvec_minmax) || (table->proc_handler == proc_dointvec_minmax) || + (table->proc_handler == proc_dou8vec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || (table->proc_handler == proc_dointvec_userhz_jiffies) || (table->proc_handler == proc_dointvec_ms_jiffies) || diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 161eba9fd912..4393de94cb32 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -53,6 +53,8 @@ int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *); int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); +int proc_dou8vec_minmax(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d8b7b2846313..43e907f4cac7 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1061,6 +1061,65 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, do_proc_douintvec_minmax_conv, ¶m); } +/** + * proc_dou8vec_minmax - read a vector of unsigned chars with min/max values + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(u8) unsigned chars + * values from/to the user buffer, treated as an ASCII string. Negative + * strings are not allowed. + * + * This routine will ensure the values are within the range specified by + * table->extra1 (min) and table->extra2 (max). + * + * Returns 0 on success or an error on write when the range check fails. + */ +int proc_dou8vec_minmax(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table tmp; + unsigned int min = 0, max = 255U, val; + u8 *data = table->data; + struct do_proc_douintvec_minmax_conv_param param = { + .min = &min, + .max = &max, + }; + int res; + + /* Do not support arrays yet. */ + if (table->maxlen != sizeof(u8)) + return -EINVAL; + + if (table->extra1) { + min = *(unsigned int *) table->extra1; + if (min > 255U) + return -EINVAL; + } + if (table->extra2) { + max = *(unsigned int *) table->extra2; + if (max > 255U) + return -EINVAL; + } + + tmp = *table; + + tmp.maxlen = sizeof(val); + tmp.data = &val; + val = *data; + res = do_proc_douintvec(&tmp, write, buffer, lenp, ppos, + do_proc_douintvec_minmax_conv, ¶m); + if (res) + return res; + if (write) + *data = val; + return 0; +} +EXPORT_SYMBOL_GPL(proc_dou8vec_minmax); + static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) @@ -1612,6 +1671,12 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, return -ENOSYS; } +int proc_dou8vec_minmax(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_jiffies(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { From f662a0786dfd404db0b6595302500156719eeaa3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 25 Mar 2021 11:08:14 -0700 Subject: [PATCH 2530/4345] ipv4: shrink netns_ipv4 with sysctl conversions [ Upstream commit 4b6bbf17d4e1939afa72821879fc033d725e9491 ] These sysctls that can fit in one byte instead of one int are converted to save space and thus reduce cache line misses. - icmp_echo_ignore_all, icmp_echo_ignore_broadcasts, - icmp_ignore_bogus_error_responses, icmp_errors_use_inbound_ifaddr - tcp_ecn, tcp_ecn_fallback - ip_default_ttl, ip_no_pmtu_disc, ip_fwd_use_pmtu - ip_nonlocal_bind, ip_autobind_reuse - ip_dynaddr, ip_early_demux, raw_l3mdev_accept - nexthop_compat_mode, fwmark_reflect Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Stable-dep-of: dc5110c2d959 ("tcp: restrict net.ipv4.tcp_app_win") Signed-off-by: Sasha Levin --- include/net/netns/ipv4.h | 32 +++++++++---------- net/ipv4/sysctl_net_ipv4.c | 64 +++++++++++++++++++------------------- 2 files changed, 48 insertions(+), 48 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 75484f425e55..92e3d8fe954a 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -84,36 +84,36 @@ struct netns_ipv4 { struct xt_table *nat_table; #endif - int sysctl_icmp_echo_ignore_all; - int sysctl_icmp_echo_ignore_broadcasts; - int sysctl_icmp_ignore_bogus_error_responses; + u8 sysctl_icmp_echo_ignore_all; + u8 sysctl_icmp_echo_ignore_broadcasts; + u8 sysctl_icmp_ignore_bogus_error_responses; + u8 sysctl_icmp_errors_use_inbound_ifaddr; int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; - int sysctl_icmp_errors_use_inbound_ifaddr; struct local_ports ip_local_ports; - int sysctl_tcp_ecn; - int sysctl_tcp_ecn_fallback; + u8 sysctl_tcp_ecn; + u8 sysctl_tcp_ecn_fallback; - int sysctl_ip_default_ttl; - int sysctl_ip_no_pmtu_disc; - int sysctl_ip_fwd_use_pmtu; + u8 sysctl_ip_default_ttl; + u8 sysctl_ip_no_pmtu_disc; + u8 sysctl_ip_fwd_use_pmtu; int sysctl_ip_fwd_update_priority; - int sysctl_ip_nonlocal_bind; - int sysctl_ip_autobind_reuse; + u8 sysctl_ip_nonlocal_bind; + u8 sysctl_ip_autobind_reuse; /* Shall we try to damage output packets if routing dev changes? */ - int sysctl_ip_dynaddr; - int sysctl_ip_early_demux; + u8 sysctl_ip_dynaddr; + u8 sysctl_ip_early_demux; #ifdef CONFIG_NET_L3_MASTER_DEV - int sysctl_raw_l3mdev_accept; + u8 sysctl_raw_l3mdev_accept; #endif int sysctl_tcp_early_demux; int sysctl_udp_early_demux; - int sysctl_nexthop_compat_mode; + u8 sysctl_nexthop_compat_mode; - int sysctl_fwmark_reflect; + u8 sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; #ifdef CONFIG_NET_L3_MASTER_DEV int sysctl_tcp_l3mdev_accept; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 439970e02ac6..cb587bdd683a 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -540,30 +540,30 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "icmp_echo_ignore_all", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_all, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "icmp_echo_ignore_broadcasts", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_broadcasts, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "icmp_ignore_bogus_error_responses", .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "icmp_errors_use_inbound_ifaddr", .data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "icmp_ratelimit", @@ -590,9 +590,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "raw_l3mdev_accept", .data = &init_net.ipv4.sysctl_raw_l3mdev_accept, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -600,30 +600,30 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_ecn", .data = &init_net.ipv4.sysctl_tcp_ecn, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_ecn_fallback", .data = &init_net.ipv4.sysctl_tcp_ecn_fallback, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_dynaddr", .data = &init_net.ipv4.sysctl_ip_dynaddr, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_early_demux", .data = &init_net.ipv4.sysctl_ip_early_demux, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "udp_early_demux", @@ -642,18 +642,18 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "nexthop_compat_mode", .data = &init_net.ipv4.sysctl_nexthop_compat_mode, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "ip_default_ttl", .data = &init_net.ipv4.sysctl_ip_default_ttl, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = &ip_ttl_min, .extra2 = &ip_ttl_max, }, @@ -674,16 +674,16 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "ip_no_pmtu_disc", .data = &init_net.ipv4.sysctl_ip_no_pmtu_disc, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_forward_use_pmtu", .data = &init_net.ipv4.sysctl_ip_fwd_use_pmtu, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_forward_update_priority", @@ -697,25 +697,25 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "ip_nonlocal_bind", .data = &init_net.ipv4.sysctl_ip_nonlocal_bind, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_autobind_reuse", .data = &init_net.ipv4.sysctl_ip_autobind_reuse, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "fwmark_reflect", .data = &init_net.ipv4.sysctl_fwmark_reflect, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_fwmark_accept", From cc9f9a49f5b3b7bd70e8f7edd10b4f9be196aff3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 25 Mar 2021 11:08:17 -0700 Subject: [PATCH 2531/4345] tcp: convert elligible sysctls to u8 [ Upstream commit 4ecc1baf362c5df2dcabe242511e38ee28486545 ] Many tcp sysctls are either bools or small ints that can fit into u8. Reducing space taken by sysctls can save few cache line misses when sending/receiving data while cpu caches are empty, for example after cpu idle period. This is hard to measure with typical network performance tests, but after this patch, struct netns_ipv4 has shrunk by three cache lines. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Stable-dep-of: dc5110c2d959 ("tcp: restrict net.ipv4.tcp_app_win") Signed-off-by: Sasha Levin --- include/net/netns/ipv4.h | 68 +++++++++---------- net/ipv4/sysctl_net_ipv4.c | 136 ++++++++++++++++++------------------- 2 files changed, 102 insertions(+), 102 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 92e3d8fe954a..d8b320cf54ba 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -114,11 +114,11 @@ struct netns_ipv4 { u8 sysctl_nexthop_compat_mode; u8 sysctl_fwmark_reflect; - int sysctl_tcp_fwmark_accept; + u8 sysctl_tcp_fwmark_accept; #ifdef CONFIG_NET_L3_MASTER_DEV - int sysctl_tcp_l3mdev_accept; + u8 sysctl_tcp_l3mdev_accept; #endif - int sysctl_tcp_mtu_probing; + u8 sysctl_tcp_mtu_probing; int sysctl_tcp_mtu_probe_floor; int sysctl_tcp_base_mss; int sysctl_tcp_min_snd_mss; @@ -126,46 +126,47 @@ struct netns_ipv4 { u32 sysctl_tcp_probe_interval; int sysctl_tcp_keepalive_time; - int sysctl_tcp_keepalive_probes; int sysctl_tcp_keepalive_intvl; + u8 sysctl_tcp_keepalive_probes; - int sysctl_tcp_syn_retries; - int sysctl_tcp_synack_retries; - int sysctl_tcp_syncookies; + u8 sysctl_tcp_syn_retries; + u8 sysctl_tcp_synack_retries; + u8 sysctl_tcp_syncookies; int sysctl_tcp_reordering; - int sysctl_tcp_retries1; - int sysctl_tcp_retries2; - int sysctl_tcp_orphan_retries; + u8 sysctl_tcp_retries1; + u8 sysctl_tcp_retries2; + u8 sysctl_tcp_orphan_retries; + u8 sysctl_tcp_tw_reuse; int sysctl_tcp_fin_timeout; unsigned int sysctl_tcp_notsent_lowat; - int sysctl_tcp_tw_reuse; - int sysctl_tcp_sack; - int sysctl_tcp_window_scaling; - int sysctl_tcp_timestamps; - int sysctl_tcp_early_retrans; - int sysctl_tcp_recovery; - int sysctl_tcp_thin_linear_timeouts; - int sysctl_tcp_slow_start_after_idle; - int sysctl_tcp_retrans_collapse; - int sysctl_tcp_stdurg; - int sysctl_tcp_rfc1337; - int sysctl_tcp_abort_on_overflow; - int sysctl_tcp_fack; + u8 sysctl_tcp_sack; + u8 sysctl_tcp_window_scaling; + u8 sysctl_tcp_timestamps; + u8 sysctl_tcp_early_retrans; + u8 sysctl_tcp_recovery; + u8 sysctl_tcp_thin_linear_timeouts; + u8 sysctl_tcp_slow_start_after_idle; + u8 sysctl_tcp_retrans_collapse; + u8 sysctl_tcp_stdurg; + u8 sysctl_tcp_rfc1337; + u8 sysctl_tcp_abort_on_overflow; + u8 sysctl_tcp_fack; /* obsolete */ int sysctl_tcp_max_reordering; - int sysctl_tcp_dsack; - int sysctl_tcp_app_win; int sysctl_tcp_adv_win_scale; - int sysctl_tcp_frto; - int sysctl_tcp_nometrics_save; - int sysctl_tcp_no_ssthresh_metrics_save; - int sysctl_tcp_moderate_rcvbuf; - int sysctl_tcp_tso_win_divisor; - int sysctl_tcp_workaround_signed_windows; + u8 sysctl_tcp_dsack; + u8 sysctl_tcp_app_win; + u8 sysctl_tcp_frto; + u8 sysctl_tcp_nometrics_save; + u8 sysctl_tcp_no_ssthresh_metrics_save; + u8 sysctl_tcp_moderate_rcvbuf; + u8 sysctl_tcp_tso_win_divisor; + u8 sysctl_tcp_workaround_signed_windows; int sysctl_tcp_limit_output_bytes; int sysctl_tcp_challenge_ack_limit; - int sysctl_tcp_min_tso_segs; int sysctl_tcp_min_rtt_wlen; - int sysctl_tcp_autocorking; + u8 sysctl_tcp_min_tso_segs; + u8 sysctl_tcp_autocorking; + u8 sysctl_tcp_reflect_tos; int sysctl_tcp_invalid_ratelimit; int sysctl_tcp_pacing_ss_ratio; int sysctl_tcp_pacing_ca_ratio; @@ -183,7 +184,6 @@ struct netns_ipv4 { unsigned int sysctl_tcp_fastopen_blackhole_timeout; atomic_t tfo_active_disable_times; unsigned long tfo_active_disable_stamp; - int sysctl_tcp_reflect_tos; int sysctl_udp_wmem_min; int sysctl_udp_rmem_min; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index cb587bdd683a..1a2506f795d4 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -720,17 +720,17 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_fwmark_accept", .data = &init_net.ipv4.sysctl_tcp_fwmark_accept, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, }, #ifdef CONFIG_NET_L3_MASTER_DEV { .procname = "tcp_l3mdev_accept", .data = &init_net.ipv4.sysctl_tcp_l3mdev_accept, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -738,9 +738,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_mtu_probing", .data = &init_net.ipv4.sysctl_tcp_mtu_probing, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_base_mss", @@ -842,9 +842,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_keepalive_probes", .data = &init_net.ipv4.sysctl_tcp_keepalive_probes, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_keepalive_intvl", @@ -856,26 +856,26 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_syn_retries", .data = &init_net.ipv4.sysctl_tcp_syn_retries, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = &tcp_syn_retries_min, .extra2 = &tcp_syn_retries_max }, { .procname = "tcp_synack_retries", .data = &init_net.ipv4.sysctl_tcp_synack_retries, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, #ifdef CONFIG_SYN_COOKIES { .procname = "tcp_syncookies", .data = &init_net.ipv4.sysctl_tcp_syncookies, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, #endif { @@ -888,24 +888,24 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_retries1", .data = &init_net.ipv4.sysctl_tcp_retries1, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra2 = &tcp_retr1_max }, { .procname = "tcp_retries2", .data = &init_net.ipv4.sysctl_tcp_retries2, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_orphan_retries", .data = &init_net.ipv4.sysctl_tcp_orphan_retries, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_fin_timeout", @@ -924,9 +924,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_tw_reuse", .data = &init_net.ipv4.sysctl_tcp_tw_reuse, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &two, }, @@ -1012,88 +1012,88 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_sack", .data = &init_net.ipv4.sysctl_tcp_sack, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_window_scaling", .data = &init_net.ipv4.sysctl_tcp_window_scaling, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_timestamps", .data = &init_net.ipv4.sysctl_tcp_timestamps, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_early_retrans", .data = &init_net.ipv4.sysctl_tcp_early_retrans, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &four, }, { .procname = "tcp_recovery", .data = &init_net.ipv4.sysctl_tcp_recovery, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_thin_linear_timeouts", .data = &init_net.ipv4.sysctl_tcp_thin_linear_timeouts, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_slow_start_after_idle", .data = &init_net.ipv4.sysctl_tcp_slow_start_after_idle, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_retrans_collapse", .data = &init_net.ipv4.sysctl_tcp_retrans_collapse, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_stdurg", .data = &init_net.ipv4.sysctl_tcp_stdurg, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_rfc1337", .data = &init_net.ipv4.sysctl_tcp_rfc1337, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_abort_on_overflow", .data = &init_net.ipv4.sysctl_tcp_abort_on_overflow, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_fack", .data = &init_net.ipv4.sysctl_tcp_fack, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_max_reordering", @@ -1105,16 +1105,16 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_dsack", .data = &init_net.ipv4.sysctl_tcp_dsack, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_app_win", .data = &init_net.ipv4.sysctl_tcp_app_win, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_adv_win_scale", @@ -1128,46 +1128,46 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_frto", .data = &init_net.ipv4.sysctl_tcp_frto, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_no_metrics_save", .data = &init_net.ipv4.sysctl_tcp_nometrics_save, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_no_ssthresh_metrics_save", .data = &init_net.ipv4.sysctl_tcp_no_ssthresh_metrics_save, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_moderate_rcvbuf", .data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_tso_win_divisor", .data = &init_net.ipv4.sysctl_tcp_tso_win_divisor, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_workaround_signed_windows", .data = &init_net.ipv4.sysctl_tcp_workaround_signed_windows, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_limit_output_bytes", @@ -1186,9 +1186,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_min_tso_segs", .data = &init_net.ipv4.sysctl_tcp_min_tso_segs, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &gso_max_segs, }, @@ -1204,9 +1204,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_autocorking", .data = &init_net.ipv4.sysctl_tcp_autocorking, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -1277,9 +1277,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_reflect_tos", .data = &init_net.ipv4.sysctl_tcp_reflect_tos, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, From a069d4d98cd271a70b561cb757485efe5f5e5a7e Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 6 Apr 2023 14:34:50 +0800 Subject: [PATCH 2532/4345] tcp: restrict net.ipv4.tcp_app_win [ Upstream commit dc5110c2d959c1707e12df5f792f41d90614adaa ] UBSAN: shift-out-of-bounds in net/ipv4/tcp_input.c:555:23 shift exponent 255 is too large for 32-bit type 'int' CPU: 1 PID: 7907 Comm: ssh Not tainted 6.3.0-rc4-00161-g62bad54b26db-dirty #206 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Call Trace: dump_stack_lvl+0x136/0x150 __ubsan_handle_shift_out_of_bounds+0x21f/0x5a0 tcp_init_transfer.cold+0x3a/0xb9 tcp_finish_connect+0x1d0/0x620 tcp_rcv_state_process+0xd78/0x4d60 tcp_v4_do_rcv+0x33d/0x9d0 __release_sock+0x133/0x3b0 release_sock+0x58/0x1b0 'maxwin' is int, shifting int for 32 or more bits is undefined behaviour. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: YueHaibing Reviewed-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- Documentation/networking/ip-sysctl.rst | 2 ++ net/ipv4/sysctl_net_ipv4.c | 3 +++ 2 files changed, 5 insertions(+) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 0158dff63887..df26cf4110ef 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -272,6 +272,8 @@ tcp_app_win - INTEGER Reserve max(window/2^tcp_app_win, mss) of window for application buffer. Value 0 is special, it means that nothing is reserved. + Possible values are [0, 31], inclusive. + Default: 31 tcp_autocorking - BOOLEAN diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1a2506f795d4..3a34e9768bff 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -37,6 +37,7 @@ static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; +static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int ip_privileged_port_min; @@ -1115,6 +1116,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_app_win_max, }, { .procname = "tcp_adv_win_scale", From 4a519731ece83d0884fa12595206f1d12f7fe4e5 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 26 Dec 2021 17:34:16 +0100 Subject: [PATCH 2533/4345] drm/armada: Fix a potential double free in an error handling path [ Upstream commit b89ce1177d42d5c124e83f3858818cd4e6a2c46f ] 'priv' is a managed resource, so there is no need to free it explicitly or there will be a double free(). Fixes: 90ad200b4cbc ("drm/armada: Use devm_drm_dev_alloc") Signed-off-by: Christophe JAILLET Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/c4f3c9207a9fce35cb6dd2cc60e755275961588a.1640536364.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/gpu/drm/armada/armada_drv.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 980d3f1f8f16..2d1e1e48f0ee 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -102,7 +102,6 @@ static int armada_drm_bind(struct device *dev) if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); - kfree(priv); return ret; } From dad92d8ada07f1a700d7ac83358e1682d6f98f9e Mon Sep 17 00:00:00 2001 From: Denis Plotnikov Date: Fri, 7 Apr 2023 10:18:49 +0300 Subject: [PATCH 2534/4345] qlcnic: check pci_reset_function result [ Upstream commit 7573099e10ca69c3be33995c1fcd0d241226816d ] Static code analyzer complains to unchecked return value. The result of pci_reset_function() is unchecked. Despite, the issue is on the FLR supported code path and in that case reset can be done with pcie_flr(), the patch uses less invasive approach by adding the result check of pci_reset_function(). Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 7e2cf4feba05 ("qlcnic: change driver hardware interface mechanism") Signed-off-by: Denis Plotnikov Reviewed-by: Simon Horman Reviewed-by: Bjorn Helgaas Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c index 87f76bac2e46..eb827b86ecae 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c @@ -628,7 +628,13 @@ int qlcnic_fw_create_ctx(struct qlcnic_adapter *dev) int i, err, ring; if (dev->flags & QLCNIC_NEED_FLR) { - pci_reset_function(dev->pdev); + err = pci_reset_function(dev->pdev); + if (err) { + dev_err(&dev->pdev->dev, + "Adapter reset failed (%d). Please reboot\n", + err); + return err; + } dev->flags &= ~QLCNIC_NEED_FLR; } From 3814d211ff13ee35f2d9437439a6c7df58524137 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Mon, 10 Apr 2023 09:23:52 +0800 Subject: [PATCH 2535/4345] net: qrtr: Fix an uninit variable access bug in qrtr_tx_resume() [ Upstream commit 6417070918de3bcdbe0646e7256dae58fd8083ba ] Syzbot reported a bug as following: ===================================================== BUG: KMSAN: uninit-value in qrtr_tx_resume+0x185/0x1f0 net/qrtr/af_qrtr.c:230 qrtr_tx_resume+0x185/0x1f0 net/qrtr/af_qrtr.c:230 qrtr_endpoint_post+0xf85/0x11b0 net/qrtr/af_qrtr.c:519 qrtr_tun_write_iter+0x270/0x400 net/qrtr/tun.c:108 call_write_iter include/linux/fs.h:2189 [inline] aio_write+0x63a/0x950 fs/aio.c:1600 io_submit_one+0x1d1c/0x3bf0 fs/aio.c:2019 __do_sys_io_submit fs/aio.c:2078 [inline] __se_sys_io_submit+0x293/0x770 fs/aio.c:2048 __x64_sys_io_submit+0x92/0xd0 fs/aio.c:2048 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook mm/slab.h:766 [inline] slab_alloc_node mm/slub.c:3452 [inline] __kmem_cache_alloc_node+0x71f/0xce0 mm/slub.c:3491 __do_kmalloc_node mm/slab_common.c:967 [inline] __kmalloc_node_track_caller+0x114/0x3b0 mm/slab_common.c:988 kmalloc_reserve net/core/skbuff.c:492 [inline] __alloc_skb+0x3af/0x8f0 net/core/skbuff.c:565 __netdev_alloc_skb+0x120/0x7d0 net/core/skbuff.c:630 qrtr_endpoint_post+0xbd/0x11b0 net/qrtr/af_qrtr.c:446 qrtr_tun_write_iter+0x270/0x400 net/qrtr/tun.c:108 call_write_iter include/linux/fs.h:2189 [inline] aio_write+0x63a/0x950 fs/aio.c:1600 io_submit_one+0x1d1c/0x3bf0 fs/aio.c:2019 __do_sys_io_submit fs/aio.c:2078 [inline] __se_sys_io_submit+0x293/0x770 fs/aio.c:2048 __x64_sys_io_submit+0x92/0xd0 fs/aio.c:2048 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd It is because that skb->len requires at least sizeof(struct qrtr_ctrl_pkt) in qrtr_tx_resume(). And skb->len equals to size in qrtr_endpoint_post(). But size is less than sizeof(struct qrtr_ctrl_pkt) when qrtr_cb->type equals to QRTR_TYPE_RESUME_TX in qrtr_endpoint_post() under the syzbot scenario. This triggers the uninit variable access bug. Add size check when qrtr_cb->type equals to QRTR_TYPE_RESUME_TX in qrtr_endpoint_post() to fix the bug. Fixes: 5fdeb0d372ab ("net: qrtr: Implement outgoing flow control") Reported-by: syzbot+4436c9630a45820fda76@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=c14607f0963d27d5a3d5f4c8639b500909e43540 Suggested-by: Manivannan Sadhasivam Signed-off-by: Ziyang Xuan Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230410012352.3997823-1-william.xuanziyang@huawei.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/qrtr/af_qrtr.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index d0f0b2b8dce2..71c2295d4a57 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -492,6 +492,11 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!size || len != ALIGN(size, 4) + hdrlen) goto err; + if ((cb->type == QRTR_TYPE_NEW_SERVER || + cb->type == QRTR_TYPE_RESUME_TX) && + size < sizeof(struct qrtr_ctrl_pkt)) + goto err; + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && cb->type != QRTR_TYPE_RESUME_TX) goto err; @@ -500,6 +505,14 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) qrtr_node_assign(node, cb->src_node); + if (cb->type == QRTR_TYPE_NEW_SERVER) { + /* Remote node endpoint can bridge other distant nodes */ + const struct qrtr_ctrl_pkt *pkt; + + pkt = data + hdrlen; + qrtr_node_assign(node, le32_to_cpu(pkt->server.node)); + } + if (cb->type == QRTR_TYPE_RESUME_TX) { qrtr_tx_resume(node, skb); } else { From 79b28f42214a3d0d6a8c514db3602260bd5d6cb5 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 10 Apr 2023 15:43:30 -0400 Subject: [PATCH 2536/4345] sctp: fix a potential overflow in sctp_ifwdtsn_skip [ Upstream commit 32832a2caf82663870126c5186cf8f86c8b2a649 ] Currently, when traversing ifwdtsn skips with _sctp_walk_ifwdtsn, it only checks the pos against the end of the chunk. However, the data left for the last pos may be < sizeof(struct sctp_ifwdtsn_skip), and dereference it as struct sctp_ifwdtsn_skip may cause coverflow. This patch fixes it by checking the pos against "the end of the chunk - sizeof(struct sctp_ifwdtsn_skip)" in sctp_ifwdtsn_skip, similar to sctp_fwdtsn_skip. Fixes: 0fc2ea922c8a ("sctp: implement validate_ftsn for sctp_stream_interleave") Signed-off-by: Xin Long Link: https://lore.kernel.org/r/2a71bffcd80b4f2c61fac6d344bb2f11c8fd74f7.1681155810.git.lucien.xin@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sctp/stream_interleave.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 6b13f737ebf2..e3aad75cb11d 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -1162,7 +1162,8 @@ static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) #define _sctp_walk_ifwdtsn(pos, chunk, end) \ for (pos = chunk->subh.ifwdtsn_hdr->skip; \ - (void *)pos < (void *)chunk->subh.ifwdtsn_hdr->skip + (end); pos++) + (void *)pos <= (void *)chunk->subh.ifwdtsn_hdr->skip + (end) - \ + sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ From d1b9b3191697a80aca8e247320eba46f24d41d18 Mon Sep 17 00:00:00 2001 From: Saravanan Vajravel Date: Fri, 31 Mar 2023 23:34:24 -0700 Subject: [PATCH 2537/4345] RDMA/core: Fix GID entry ref leak when create_ah fails [ Upstream commit aca3b0fa3d04b40c96934d86cc224cccfa7ea8e0 ] If AH create request fails, release sgid_attr to avoid GID entry referrence leak reported while releasing GID table Fixes: 1a1f460ff151 ("RDMA: Hold the sgid_attr inside the struct ib_ah/qp") Link: https://lore.kernel.org/r/20230401063424.342204-1-saravanan.vajravel@broadcom.com Reviewed-by: Selvin Xavier Signed-off-by: Saravanan Vajravel Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/core/verbs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 5123be0ab02f..4fcabe5a84be 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -535,6 +535,8 @@ static struct ib_ah *_rdma_create_ah(struct ib_pd *pd, ret = device->ops.create_ah(ah, &init_attr, udata); if (ret) { + if (ah->sgid_attr) + rdma_put_gid_attr(ah->sgid_attr); kfree(ah); return ERR_PTR(ret); } From 7d8c844b337d245c64158138828644c99f28d28c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 12 Apr 2023 13:03:08 +0000 Subject: [PATCH 2538/4345] udp6: fix potential access to stale information MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1c5950fc6fe996235f1d18539b9c6b64b597f50f ] lena wang reported an issue caused by udpv6_sendmsg() mangling msg->msg_name and msg->msg_namelen, which are later read from ____sys_sendmsg() : /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. */ if (used_address && err >= 0) { used_address->name_len = msg_sys->msg_namelen; if (msg_sys->msg_name) memcpy(&used_address->name, msg_sys->msg_name, used_address->name_len); } udpv6_sendmsg() wants to pretend the remote address family is AF_INET in order to call udp_sendmsg(). A fix would be to modify the address in-place, instead of using a local variable, but this could have other side effects. Instead, restore initial values before we return from udpv6_sendmsg(). Fixes: c71d8ebe7a44 ("net: Fix security_socket_sendmsg() bypass problem.") Reported-by: lena wang Signed-off-by: Eric Dumazet Reviewed-by: Maciej Żenczykowski Link: https://lore.kernel.org/r/20230412130308.1202254-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv6/udp.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1805cc5f7418..20cc08210c70 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1340,9 +1340,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (__ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(sk, msg, len); + err = __ipv6_only_sock(sk) ? + -ENETUNREACH : udp_sendmsg(sk, msg, len); + msg->msg_name = sin6; + msg->msg_namelen = addr_len; + return err; } } From 1bec9da233f779e7b6954ee07ad7e6d8f2a4dd83 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 12 Apr 2023 16:21:44 -0700 Subject: [PATCH 2539/4345] net: macb: fix a memory corruption in extended buffer descriptor mode [ Upstream commit e8b74453555872851bdd7ea43a7c0ec39659834f ] For quite some time we were chasing a bug which looked like a sudden permanent failure of networking and mmc on some of our devices. The bug was very sensitive to any software changes and even more to any kernel debug options. Finally we got a setup where the problem was reproducible with CONFIG_DMA_API_DEBUG=y and it revealed the issue with the rx dma: [ 16.992082] ------------[ cut here ]------------ [ 16.996779] DMA-API: macb ff0b0000.ethernet: device driver tries to free DMA memory it has not allocated [device address=0x0000000875e3e244] [size=1536 bytes] [ 17.011049] WARNING: CPU: 0 PID: 85 at kernel/dma/debug.c:1011 check_unmap+0x6a0/0x900 [ 17.018977] Modules linked in: xxxxx [ 17.038823] CPU: 0 PID: 85 Comm: irq/55-8000f000 Not tainted 5.4.0 #28 [ 17.045345] Hardware name: xxxxx [ 17.049528] pstate: 60000005 (nZCv daif -PAN -UAO) [ 17.054322] pc : check_unmap+0x6a0/0x900 [ 17.058243] lr : check_unmap+0x6a0/0x900 [ 17.062163] sp : ffffffc010003c40 [ 17.065470] x29: ffffffc010003c40 x28: 000000004000c03c [ 17.070783] x27: ffffffc010da7048 x26: ffffff8878e38800 [ 17.076095] x25: ffffff8879d22810 x24: ffffffc010003cc8 [ 17.081407] x23: 0000000000000000 x22: ffffffc010a08750 [ 17.086719] x21: ffffff8878e3c7c0 x20: ffffffc010acb000 [ 17.092032] x19: 0000000875e3e244 x18: 0000000000000010 [ 17.097343] x17: 0000000000000000 x16: 0000000000000000 [ 17.102647] x15: ffffff8879e4a988 x14: 0720072007200720 [ 17.107959] x13: 0720072007200720 x12: 0720072007200720 [ 17.113261] x11: 0720072007200720 x10: 0720072007200720 [ 17.118565] x9 : 0720072007200720 x8 : 000000000000022d [ 17.123869] x7 : 0000000000000015 x6 : 0000000000000098 [ 17.129173] x5 : 0000000000000000 x4 : 0000000000000000 [ 17.134475] x3 : 00000000ffffffff x2 : ffffffc010a1d370 [ 17.139778] x1 : b420c9d75d27bb00 x0 : 0000000000000000 [ 17.145082] Call trace: [ 17.147524] check_unmap+0x6a0/0x900 [ 17.151091] debug_dma_unmap_page+0x88/0x90 [ 17.155266] gem_rx+0x114/0x2f0 [ 17.158396] macb_poll+0x58/0x100 [ 17.161705] net_rx_action+0x118/0x400 [ 17.165445] __do_softirq+0x138/0x36c [ 17.169100] irq_exit+0x98/0xc0 [ 17.172234] __handle_domain_irq+0x64/0xc0 [ 17.176320] gic_handle_irq+0x5c/0xc0 [ 17.179974] el1_irq+0xb8/0x140 [ 17.183109] xiic_process+0x5c/0xe30 [ 17.186677] irq_thread_fn+0x28/0x90 [ 17.190244] irq_thread+0x208/0x2a0 [ 17.193724] kthread+0x130/0x140 [ 17.196945] ret_from_fork+0x10/0x20 [ 17.200510] ---[ end trace 7240980785f81d6f ]--- [ 237.021490] ------------[ cut here ]------------ [ 237.026129] DMA-API: exceeded 7 overlapping mappings of cacheline 0x0000000021d79e7b [ 237.033886] WARNING: CPU: 0 PID: 0 at kernel/dma/debug.c:499 add_dma_entry+0x214/0x240 [ 237.041802] Modules linked in: xxxxx [ 237.061637] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G W 5.4.0 #28 [ 237.068941] Hardware name: xxxxx [ 237.073116] pstate: 80000085 (Nzcv daIf -PAN -UAO) [ 237.077900] pc : add_dma_entry+0x214/0x240 [ 237.081986] lr : add_dma_entry+0x214/0x240 [ 237.086072] sp : ffffffc010003c30 [ 237.089379] x29: ffffffc010003c30 x28: ffffff8878a0be00 [ 237.094683] x27: 0000000000000180 x26: ffffff8878e387c0 [ 237.099987] x25: 0000000000000002 x24: 0000000000000000 [ 237.105290] x23: 000000000000003b x22: ffffffc010a0fa00 [ 237.110594] x21: 0000000021d79e7b x20: ffffffc010abe600 [ 237.115897] x19: 00000000ffffffef x18: 0000000000000010 [ 237.121201] x17: 0000000000000000 x16: 0000000000000000 [ 237.126504] x15: ffffffc010a0fdc8 x14: 0720072007200720 [ 237.131807] x13: 0720072007200720 x12: 0720072007200720 [ 237.137111] x11: 0720072007200720 x10: 0720072007200720 [ 237.142415] x9 : 0720072007200720 x8 : 0000000000000259 [ 237.147718] x7 : 0000000000000001 x6 : 0000000000000000 [ 237.153022] x5 : ffffffc010003a20 x4 : 0000000000000001 [ 237.158325] x3 : 0000000000000006 x2 : 0000000000000007 [ 237.163628] x1 : 8ac721b3a7dc1c00 x0 : 0000000000000000 [ 237.168932] Call trace: [ 237.171373] add_dma_entry+0x214/0x240 [ 237.175115] debug_dma_map_page+0xf8/0x120 [ 237.179203] gem_rx_refill+0x190/0x280 [ 237.182942] gem_rx+0x224/0x2f0 [ 237.186075] macb_poll+0x58/0x100 [ 237.189384] net_rx_action+0x118/0x400 [ 237.193125] __do_softirq+0x138/0x36c [ 237.196780] irq_exit+0x98/0xc0 [ 237.199914] __handle_domain_irq+0x64/0xc0 [ 237.204000] gic_handle_irq+0x5c/0xc0 [ 237.207654] el1_irq+0xb8/0x140 [ 237.210789] arch_cpu_idle+0x40/0x200 [ 237.214444] default_idle_call+0x18/0x30 [ 237.218359] do_idle+0x200/0x280 [ 237.221578] cpu_startup_entry+0x20/0x30 [ 237.225493] rest_init+0xe4/0xf0 [ 237.228713] arch_call_rest_init+0xc/0x14 [ 237.232714] start_kernel+0x47c/0x4a8 [ 237.236367] ---[ end trace 7240980785f81d70 ]--- Lars was fast to find an explanation: according to the datasheet bit 2 of the rx buffer descriptor entry has a different meaning in the extended mode: Address [2] of beginning of buffer, or in extended buffer descriptor mode (DMA configuration register [28] = 1), indicates a valid timestamp in the buffer descriptor entry. The macb driver didn't mask this bit while getting an address and it eventually caused a memory corruption and a dma failure. The problem is resolved by explicitly clearing the problematic bit if hw timestamping is used. Fixes: 7b4296148066 ("net: macb: Add support for PTP timestamps in DMA descriptors") Signed-off-by: Roman Gushchin Co-developed-by: Lars-Peter Clausen Signed-off-by: Lars-Peter Clausen Acked-by: Nicolas Ferre Reviewed-by: Jacob Keller Link: https://lore.kernel.org/r/20230412232144.770336-1-roman.gushchin@linux.dev Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/cadence/macb_main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index e0d62e251387..70d57ef95fb1 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -884,6 +884,10 @@ static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc) } #endif addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr)); +#ifdef CONFIG_MACB_USE_HWSTAMP + if (bp->hw_dma_cap & HW_DMA_CAP_PTP) + addr &= ~GEM_BIT(DMA_RXVALID); +#endif return addr; } From 6de0d0699f5c732e94540b5af41ad841f3a7fe83 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 12 Dec 2022 13:15:00 -0800 Subject: [PATCH 2540/4345] libbpf: Fix single-line struct definition output in btf_dump [ Upstream commit 872aec4b5f635d94111d48ec3c57fbe078d64e7d ] btf_dump APIs emit unnecessary tabs when emitting struct/union definition that fits on the single line. Before this patch we'd get: struct blah {}; This patch fixes this and makes sure that we get more natural: struct blah {}; Fixes: 44a726c3f23c ("bpftool: Print newline before '}' for struct with padding only fields") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20221212211505.558851-2-andrii@kernel.org Signed-off-by: Sasha Levin --- tools/lib/bpf/btf_dump.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 6a8d8ed34b76..61aa2c47fbd5 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -973,9 +973,12 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, * Keep `struct empty {}` on a single line, * only print newline when there are regular or padding fields. */ - if (vlen || t->size) + if (vlen || t->size) { btf_dump_printf(d, "\n"); - btf_dump_printf(d, "%s}", pfx(lvl)); + btf_dump_printf(d, "%s}", pfx(lvl)); + } else { + btf_dump_printf(d, "}"); + } if (packed) btf_dump_printf(d, " __attribute__((packed))"); } From ab39582f3081540c2bf5b21e9eeb441b1bf2171e Mon Sep 17 00:00:00 2001 From: Grant Grundler Date: Mon, 12 Dec 2022 13:38:57 -0800 Subject: [PATCH 2541/4345] power: supply: cros_usbpd: reclassify "default case!" as debug [ Upstream commit 14c76b2e75bca4d96e2b85a0c12aa43e84fe3f74 ] This doesn't need to be printed every second as an error: ... <3>[17438.628385] cros-usbpd-charger cros-usbpd-charger.3.auto: Port 1: default case! <3>[17439.634176] cros-usbpd-charger cros-usbpd-charger.3.auto: Port 1: default case! <3>[17440.640298] cros-usbpd-charger cros-usbpd-charger.3.auto: Port 1: default case! ... Reduce priority from ERROR to DEBUG. Signed-off-by: Grant Grundler Reviewed-by: Guenter Roeck Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/cros_usbpd-charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c index d89e08efd2ad..0a4f02e4ae7b 100644 --- a/drivers/power/supply/cros_usbpd-charger.c +++ b/drivers/power/supply/cros_usbpd-charger.c @@ -276,7 +276,7 @@ static int cros_usbpd_charger_get_power_info(struct port_data *port) port->psy_current_max = 0; break; default: - dev_err(dev, "Port %d: default case!\n", port->port_number); + dev_dbg(dev, "Port %d: default case!\n", port->port_number); port->psy_usb_type = POWER_SUPPLY_USB_TYPE_SDP; } From 81c30f89b9c3293b5b53e96b97fd71bc2d052c57 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 14:25:23 +0100 Subject: [PATCH 2542/4345] wifi: mwifiex: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 139f6973bf140c65d4d1d4bde5485badb4454d7a ] The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/net/wireless/marvell/mwifiex/sdio.c:498:34: error: ‘mwifiex_sdio_of_match_table’ defined but not used [-Werror=unused-const-variable=] drivers/net/wireless/marvell/mwifiex/pcie.c:175:34: error: ‘mwifiex_pcie_of_match_table’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230312132523.352182-1-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/pcie.c | 2 +- drivers/net/wireless/marvell/mwifiex/sdio.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c index b0024893a1cb..50c34630ca30 100644 --- a/drivers/net/wireless/marvell/mwifiex/pcie.c +++ b/drivers/net/wireless/marvell/mwifiex/pcie.c @@ -183,7 +183,7 @@ static const struct mwifiex_pcie_device mwifiex_pcie8997 = { .can_ext_scan = true, }; -static const struct of_device_id mwifiex_pcie_of_match_table[] = { +static const struct of_device_id mwifiex_pcie_of_match_table[] __maybe_unused = { { .compatible = "pci11ab,2b42" }, { .compatible = "pci1b4b,2b42" }, { } diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index 7fb6eef40928..b09e60fedeb1 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -484,7 +484,7 @@ static struct memory_type_mapping mem_type_mapping_tbl[] = { {"EXTLAST", NULL, 0, 0xFE}, }; -static const struct of_device_id mwifiex_sdio_of_match_table[] = { +static const struct of_device_id mwifiex_sdio_of_match_table[] __maybe_unused = { { .compatible = "marvell,sd8787" }, { .compatible = "marvell,sd8897" }, { .compatible = "marvell,sd8997" }, From e1f80b4dfad966638f5c65ae9f98d599c4be8cf2 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Mon, 30 Jan 2023 16:32:46 +0100 Subject: [PATCH 2543/4345] i2c: imx-lpi2c: clean rx/tx buffers upon new message [ Upstream commit 987dd36c0141f6ab9f0fbf14d6b2ec3342dedb2f ] When start sending a new message clear the Rx & Tx buffer pointers in order to avoid using stale pointers. Signed-off-by: Alexander Stein Tested-by: Emanuele Ghidoli Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-imx-lpi2c.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 2018dbcf241e..d45ec26d51cb 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -462,6 +462,8 @@ static int lpi2c_imx_xfer(struct i2c_adapter *adapter, if (num == 1 && msgs[0].len == 0) goto stop; + lpi2c_imx->rx_buf = NULL; + lpi2c_imx->tx_buf = NULL; lpi2c_imx->delivered = 0; lpi2c_imx->msglen = msgs[i].len; init_completion(&lpi2c_imx->complete); From 9f0ee9ed54e1eb2aa40f1d8f95d7e17a12682324 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 14 Mar 2023 13:31:03 +0100 Subject: [PATCH 2544/4345] efi: sysfb_efi: Add quirk for Lenovo Yoga Book X91F/L [ Upstream commit 5ed213dd64681f84a01ceaa82fb336cf7d59ddcf ] Another Lenovo convertable which reports a landscape resolution of 1920x1200 with a pitch of (1920 * 4) bytes, while the actual framebuffer has a resolution of 1200x1920 with a pitch of (1200 * 4) bytes. Signed-off-by: Hans de Goede Reviewed-by: Javier Martinez Canillas Signed-off-by: Ard Biesheuvel Signed-off-by: Sasha Levin --- arch/x86/kernel/sysfb_efi.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index 9ea65611fba0..fff04d285976 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -272,6 +272,14 @@ static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { "IdeaPad Duet 3 10IGL5"), }, }, + { + /* Lenovo Yoga Book X91F / X91L */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + /* Non exact match to match F + L versions */ + DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X91"), + }, + }, {}, }; From e4b9f0bf91a30cc3d6745c163e98b6be53762143 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 1 Mar 2023 10:52:18 +0100 Subject: [PATCH 2545/4345] drm: panel-orientation-quirks: Add quirk for Lenovo Yoga Book X90F [ Upstream commit 03aecb1acbcd7a660f97d645ca6c09d9de27ff9d ] Like the Windows Lenovo Yoga Book X91F/L the Android Lenovo Yoga Book X90F/L has a portrait 1200x1920 screen used in landscape mode, add a quirk for this. When the quirk for the X91F/L was initially added it was written to also apply to the X90F/L but this does not work because the Android version of the Yoga Book uses completely different DMI strings. Also adjust the X91F/L quirk to reflect that it only applies to the X91F/L models. Signed-off-by: Hans de Goede Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20230301095218.28457-1-hdegoede@redhat.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_panel_orientation_quirks.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 8768073794fb..6106fa7c4302 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -284,10 +284,17 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Duet 3 10IGL5"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, - }, { /* Lenovo Yoga Book X90F / X91F / X91L */ + }, { /* Lenovo Yoga Book X90F / X90L */ .matches = { - /* Non exact match to match all versions */ - DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9"), + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"), + }, + .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Lenovo Yoga Book X91F / X91L */ + .matches = { + /* Non exact match to match F + L versions */ + DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X91"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, }, { /* OneGX1 Pro */ From 5de2e1f5e26f340f314884d2b68d21a70e6d0160 Mon Sep 17 00:00:00 2001 From: Robbie Harwood Date: Mon, 20 Feb 2023 12:12:53 -0500 Subject: [PATCH 2546/4345] verify_pefile: relax wrapper length check [ Upstream commit 4fc5c74dde69a7eda172514aaeb5a7df3600adb3 ] The PE Format Specification (section "The Attribute Certificate Table (Image Only)") states that `dwLength` is to be rounded up to 8-byte alignment when used for traversal. Therefore, the field is not required to be an 8-byte multiple in the first place. Accordingly, pesign has not performed this alignment since version 0.110. This causes kexec failure on pesign'd binaries with "PEFILE: Signature wrapper len wrong". Update the comment and relax the check. Signed-off-by: Robbie Harwood Signed-off-by: David Howells cc: Jarkko Sakkinen cc: Eric Biederman cc: Herbert Xu cc: keyrings@vger.kernel.org cc: linux-crypto@vger.kernel.org cc: kexec@lists.infradead.org Link: https://learn.microsoft.com/en-us/windows/win32/debug/pe-format#the-attribute-certificate-table-image-only Link: https://github.com/rhboot/pesign Link: https://lore.kernel.org/r/20230220171254.592347-2-rharwood@redhat.com/ # v2 Signed-off-by: Sasha Levin --- crypto/asymmetric_keys/verify_pefile.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/crypto/asymmetric_keys/verify_pefile.c b/crypto/asymmetric_keys/verify_pefile.c index 7553ab18db89..fe1bb374239d 100644 --- a/crypto/asymmetric_keys/verify_pefile.c +++ b/crypto/asymmetric_keys/verify_pefile.c @@ -135,11 +135,15 @@ static int pefile_strip_sig_wrapper(const void *pebuf, pr_debug("sig wrapper = { %x, %x, %x }\n", wrapper.length, wrapper.revision, wrapper.cert_type); - /* Both pesign and sbsign round up the length of certificate table - * (in optional header data directories) to 8 byte alignment. + /* sbsign rounds up the length of certificate table (in optional + * header data directories) to 8 byte alignment. However, the PE + * specification states that while entries are 8-byte aligned, this is + * not included in their length, and as a result, pesign has not + * rounded up since 0.110. */ - if (round_up(wrapper.length, 8) != ctx->sig_len) { - pr_debug("Signature wrapper len wrong\n"); + if (wrapper.length > ctx->sig_len) { + pr_debug("Signature wrapper bigger than sig len (%x > %x)\n", + ctx->sig_len, wrapper.length); return -ELIBBAD; } if (wrapper.revision != WIN_CERT_REVISION_2_0) { From c76e79e526cdfc71a73ce20d5e228da00139cb27 Mon Sep 17 00:00:00 2001 From: Robbie Harwood Date: Mon, 20 Feb 2023 12:12:54 -0500 Subject: [PATCH 2547/4345] asymmetric_keys: log on fatal failures in PE/pkcs7 [ Upstream commit 3584c1dbfffdabf8e3dc1dd25748bb38dd01cd43 ] These particular errors can be encountered while trying to kexec when secureboot lockdown is in place. Without this change, even with a signed debug build, one still needs to reboot the machine to add the appropriate dyndbg parameters (since lockdown blocks debugfs). Accordingly, upgrade all pr_debug() before fatal error into pr_warn(). Signed-off-by: Robbie Harwood Signed-off-by: David Howells cc: Jarkko Sakkinen cc: Eric Biederman cc: Herbert Xu cc: keyrings@vger.kernel.org cc: linux-crypto@vger.kernel.org cc: kexec@lists.infradead.org Link: https://lore.kernel.org/r/20230220171254.592347-3-rharwood@redhat.com/ # v2 Signed-off-by: Sasha Levin --- crypto/asymmetric_keys/pkcs7_verify.c | 10 +++++----- crypto/asymmetric_keys/verify_pefile.c | 24 ++++++++++++------------ 2 files changed, 17 insertions(+), 17 deletions(-) diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c index ce49820caa97..01e54450c846 100644 --- a/crypto/asymmetric_keys/pkcs7_verify.c +++ b/crypto/asymmetric_keys/pkcs7_verify.c @@ -79,16 +79,16 @@ static int pkcs7_digest(struct pkcs7_message *pkcs7, } if (sinfo->msgdigest_len != sig->digest_size) { - pr_debug("Sig %u: Invalid digest size (%u)\n", - sinfo->index, sinfo->msgdigest_len); + pr_warn("Sig %u: Invalid digest size (%u)\n", + sinfo->index, sinfo->msgdigest_len); ret = -EBADMSG; goto error; } if (memcmp(sig->digest, sinfo->msgdigest, sinfo->msgdigest_len) != 0) { - pr_debug("Sig %u: Message digest doesn't match\n", - sinfo->index); + pr_warn("Sig %u: Message digest doesn't match\n", + sinfo->index); ret = -EKEYREJECTED; goto error; } @@ -488,7 +488,7 @@ int pkcs7_supply_detached_data(struct pkcs7_message *pkcs7, const void *data, size_t datalen) { if (pkcs7->data) { - pr_debug("Data already supplied\n"); + pr_warn("Data already supplied\n"); return -EINVAL; } pkcs7->data = data; diff --git a/crypto/asymmetric_keys/verify_pefile.c b/crypto/asymmetric_keys/verify_pefile.c index fe1bb374239d..22beaf2213a2 100644 --- a/crypto/asymmetric_keys/verify_pefile.c +++ b/crypto/asymmetric_keys/verify_pefile.c @@ -74,7 +74,7 @@ static int pefile_parse_binary(const void *pebuf, unsigned int pelen, break; default: - pr_debug("Unknown PEOPT magic = %04hx\n", pe32->magic); + pr_warn("Unknown PEOPT magic = %04hx\n", pe32->magic); return -ELIBBAD; } @@ -95,7 +95,7 @@ static int pefile_parse_binary(const void *pebuf, unsigned int pelen, ctx->certs_size = ddir->certs.size; if (!ddir->certs.virtual_address || !ddir->certs.size) { - pr_debug("Unsigned PE binary\n"); + pr_warn("Unsigned PE binary\n"); return -ENODATA; } @@ -127,7 +127,7 @@ static int pefile_strip_sig_wrapper(const void *pebuf, unsigned len; if (ctx->sig_len < sizeof(wrapper)) { - pr_debug("Signature wrapper too short\n"); + pr_warn("Signature wrapper too short\n"); return -ELIBBAD; } @@ -142,16 +142,16 @@ static int pefile_strip_sig_wrapper(const void *pebuf, * rounded up since 0.110. */ if (wrapper.length > ctx->sig_len) { - pr_debug("Signature wrapper bigger than sig len (%x > %x)\n", - ctx->sig_len, wrapper.length); + pr_warn("Signature wrapper bigger than sig len (%x > %x)\n", + ctx->sig_len, wrapper.length); return -ELIBBAD; } if (wrapper.revision != WIN_CERT_REVISION_2_0) { - pr_debug("Signature is not revision 2.0\n"); + pr_warn("Signature is not revision 2.0\n"); return -ENOTSUPP; } if (wrapper.cert_type != WIN_CERT_TYPE_PKCS_SIGNED_DATA) { - pr_debug("Signature certificate type is not PKCS\n"); + pr_warn("Signature certificate type is not PKCS\n"); return -ENOTSUPP; } @@ -164,7 +164,7 @@ static int pefile_strip_sig_wrapper(const void *pebuf, ctx->sig_offset += sizeof(wrapper); ctx->sig_len -= sizeof(wrapper); if (ctx->sig_len < 4) { - pr_debug("Signature data missing\n"); + pr_warn("Signature data missing\n"); return -EKEYREJECTED; } @@ -198,7 +198,7 @@ check_len: return 0; } not_pkcs7: - pr_debug("Signature data not PKCS#7\n"); + pr_warn("Signature data not PKCS#7\n"); return -ELIBBAD; } @@ -341,8 +341,8 @@ static int pefile_digest_pe(const void *pebuf, unsigned int pelen, digest_size = crypto_shash_digestsize(tfm); if (digest_size != ctx->digest_len) { - pr_debug("Digest size mismatch (%zx != %x)\n", - digest_size, ctx->digest_len); + pr_warn("Digest size mismatch (%zx != %x)\n", + digest_size, ctx->digest_len); ret = -EBADMSG; goto error_no_desc; } @@ -373,7 +373,7 @@ static int pefile_digest_pe(const void *pebuf, unsigned int pelen, * PKCS#7 certificate. */ if (memcmp(digest, ctx->digest, ctx->digest_len) != 0) { - pr_debug("Digest mismatch\n"); + pr_warn("Digest mismatch\n"); ret = -EKEYREJECTED; } else { pr_debug("The digests match!\n"); From 2a4835b8ede001ce88a34f6f0295f4ece2212174 Mon Sep 17 00:00:00 2001 From: Mathis Salmen Date: Thu, 6 Apr 2023 12:11:31 +0200 Subject: [PATCH 2548/4345] riscv: add icache flush for nommu sigreturn trampoline commit 8d736482749f6d350892ef83a7a11d43cd49981e upstream. In a NOMMU kernel, sigreturn trampolines are generated on the user stack by setup_rt_frame. Currently, these trampolines are not instruction fenced, thus their visibility to ifetch is not guaranteed. This patch adds a flush_icache_range in setup_rt_frame to fix this problem. Signed-off-by: Mathis Salmen Fixes: 6bd33e1ece52 ("riscv: add nommu support") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230406101130.82304-1-mathis.salmen@matsal.de Signed-off-by: Palmer Dabbelt Signed-off-by: Greg Kroah-Hartman --- arch/riscv/kernel/signal.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 50a8225c58bc..dd63407e8294 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -16,6 +16,7 @@ #include #include #include +#include extern u32 __user_rt_sigreturn[2]; @@ -178,6 +179,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, { struct rt_sigframe __user *frame; long err = 0; + unsigned long __maybe_unused addr; frame = get_sigframe(ksig, regs, sizeof(*frame)); if (!access_ok(frame, sizeof(*frame))) @@ -206,7 +208,12 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, if (copy_to_user(&frame->sigreturn_code, __user_rt_sigreturn, sizeof(frame->sigreturn_code))) return -EFAULT; - regs->ra = (unsigned long)&frame->sigreturn_code; + + addr = (unsigned long)&frame->sigreturn_code; + /* Make sure the two instructions are pushed to icache. */ + flush_icache_range(addr, addr + sizeof(frame->sigreturn_code)); + + regs->ra = addr; #endif /* CONFIG_MMU */ /* From cf22c98bcbf8fc0660a1f09fe324fd4f45ae179a Mon Sep 17 00:00:00 2001 From: Ivan Bornyakov Date: Thu, 6 Apr 2023 16:08:32 +0300 Subject: [PATCH 2549/4345] net: sfp: initialize sfp->i2c_block_size at sfp allocation commit 813c2dd78618f108fdcf9cd726ea90f081ee2881 upstream. sfp->i2c_block_size is initialized at SFP module insertion in sfp_sm_mod_probe(). Because of that, if SFP module was never inserted since boot, sfp_read() call will lead to zero-length I2C read attempt, and not all I2C controllers are happy with zero-length reads. One way to issue sfp_read() on empty SFP cage is to execute ethtool -m. If SFP module was never plugged since boot, there will be a zero-length I2C read attempt. # ethtool -m xge0 i2c i2c-3: adapter quirk: no zero length (addr 0x0050, size 0, read) Cannot get Module EEPROM data: Operation not supported If SFP module was plugged then removed at least once, sfp->i2c_block_size will be initialized and ethtool -m will fail with different exit code and without I2C error # ethtool -m xge0 Cannot get Module EEPROM data: Remote I/O error Fix this by initializing sfp->i2_block_size at struct sfp allocation stage so no wild sfp_read() could issue zero-length I2C read. Signed-off-by: Ivan Bornyakov Fixes: 0d035bed2a4a ("net: sfp: VSOL V2801F / CarlitoxxPro CPGOS03-0490 v2.0 workaround") Cc: stable@vger.kernel.org Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/sfp.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index dcbe278086dc..6a5f40f11db3 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -207,6 +207,12 @@ static const enum gpiod_flags gpio_flags[] = { */ #define SFP_PHY_ADDR 22 +/* SFP_EEPROM_BLOCK_SIZE is the size of data chunk to read the EEPROM + * at a time. Some SFP modules and also some Linux I2C drivers do not like + * reads longer than 16 bytes. + */ +#define SFP_EEPROM_BLOCK_SIZE 16 + struct sff_data { unsigned int gpios; bool (*module_supported)(const struct sfp_eeprom_id *id); @@ -1754,11 +1760,7 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) u8 check; int ret; - /* Some SFP modules and also some Linux I2C drivers do not like reads - * longer than 16 bytes, so read the EEPROM in chunks of 16 bytes at - * a time. - */ - sfp->i2c_block_size = 16; + sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE; ret = sfp_read(sfp, false, 0, &id.base, sizeof(id.base)); if (ret < 0) { @@ -2385,6 +2387,7 @@ static struct sfp *sfp_alloc(struct device *dev) return ERR_PTR(-ENOMEM); sfp->dev = dev; + sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE; mutex_init(&sfp->sm_mutex); mutex_init(&sfp->st_mutex); From 176d7345b89ced72020a313bfa4e7f345d1c3aed Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 4 Apr 2023 21:23:42 +0200 Subject: [PATCH 2550/4345] scsi: ses: Handle enclosure with just a primary component gracefully commit c8e22b7a1694bb8d025ea636816472739d859145 upstream. This reverts commit 3fe97ff3d949 ("scsi: ses: Don't attach if enclosure has no components") and introduces proper handling of case where there are no detected secondary components, but primary component (enumerated in num_enclosures) does exist. That fix was originally proposed by Ding Hui . Completely ignoring devices that have one primary enclosure and no secondary one results in ses_intf_add() bailing completely scsi 2:0:0:254: enclosure has no enumerated components scsi 2:0:0:254: Failed to bind enclosure -12ven in valid configurations such even on valid configurations with 1 primary and 0 secondary enclosures as below: # sg_ses /dev/sg0 3PARdata SES 3321 Supported diagnostic pages: Supported Diagnostic Pages [sdp] [0x0] Configuration (SES) [cf] [0x1] Short Enclosure Status (SES) [ses] [0x8] # sg_ses -p cf /dev/sg0 3PARdata SES 3321 Configuration diagnostic page: number of secondary subenclosures: 0 generation code: 0x0 enclosure descriptor list Subenclosure identifier: 0 [primary] relative ES process id: 0, number of ES processes: 1 number of type descriptor headers: 1 enclosure logical identifier (hex): 20000002ac02068d enclosure vendor: 3PARdata product: VV rev: 3321 type descriptor header and text list Element type: Unspecified, subenclosure id: 0 number of possible elements: 1 The changelog for the original fix follows ===== We can get a crash when disconnecting the iSCSI session, the call trace like this: [ffff00002a00fb70] kfree at ffff00000830e224 [ffff00002a00fba0] ses_intf_remove at ffff000001f200e4 [ffff00002a00fbd0] device_del at ffff0000086b6a98 [ffff00002a00fc50] device_unregister at ffff0000086b6d58 [ffff00002a00fc70] __scsi_remove_device at ffff00000870608c [ffff00002a00fca0] scsi_remove_device at ffff000008706134 [ffff00002a00fcc0] __scsi_remove_target at ffff0000087062e4 [ffff00002a00fd10] scsi_remove_target at ffff0000087064c0 [ffff00002a00fd70] __iscsi_unbind_session at ffff000001c872c4 [ffff00002a00fdb0] process_one_work at ffff00000810f35c [ffff00002a00fe00] worker_thread at ffff00000810f648 [ffff00002a00fe70] kthread at ffff000008116e98 In ses_intf_add, components count could be 0, and kcalloc 0 size scomp, but not saved in edev->component[i].scratch In this situation, edev->component[0].scratch is an invalid pointer, when kfree it in ses_intf_remove_enclosure, a crash like above would happen The call trace also could be other random cases when kfree cannot catch the invalid pointer We should not use edev->component[] array when the components count is 0 We also need check index when use edev->component[] array in ses_enclosure_data_process ===== Reported-by: Michal Kolar Originally-by: Ding Hui Cc: stable@vger.kernel.org Fixes: 3fe97ff3d949 ("scsi: ses: Don't attach if enclosure has no components") Signed-off-by: Jiri Kosina Link: https://lore.kernel.org/r/nycvar.YFH.7.76.2304042122270.29760@cbobk.fhfr.pm Tested-by: Michal Kolar Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/ses.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 1707d6d144d2..6a1428d453f3 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -503,9 +503,6 @@ static int ses_enclosure_find_by_addr(struct enclosure_device *edev, int i; struct ses_component *scomp; - if (!edev->component[0].scratch) - return 0; - for (i = 0; i < edev->components; i++) { scomp = edev->component[i].scratch; if (scomp->addr != efd->addr) @@ -596,8 +593,10 @@ static void ses_enclosure_data_process(struct enclosure_device *edev, components++, type_ptr[0], name); - else + else if (components < edev->components) ecomp = &edev->component[components++]; + else + ecomp = ERR_PTR(-EINVAL); if (!IS_ERR(ecomp)) { if (addl_desc_ptr) { @@ -728,11 +727,6 @@ static int ses_intf_add(struct device *cdev, components += type_ptr[1]; } - if (components == 0) { - sdev_printk(KERN_WARNING, sdev, "enclosure has no enumerated components\n"); - goto err_free; - } - ses_dev->page1 = buf; ses_dev->page1_len = len; buf = NULL; @@ -774,9 +768,11 @@ static int ses_intf_add(struct device *cdev, buf = NULL; } page2_not_supported: - scomp = kcalloc(components, sizeof(struct ses_component), GFP_KERNEL); - if (!scomp) - goto err_free; + if (components > 0) { + scomp = kcalloc(components, sizeof(struct ses_component), GFP_KERNEL); + if (!scomp) + goto err_free; + } edev = enclosure_register(cdev->parent, dev_name(&sdev->sdev_gendev), components, &ses_enclosure_callbacks); From 10bda0ec316020ae6d8d389d0a48f901826f8d59 Mon Sep 17 00:00:00 2001 From: Basavaraj Natikar Date: Wed, 29 Mar 2023 22:58:59 +0530 Subject: [PATCH 2551/4345] x86/PCI: Add quirk for AMD XHCI controller that loses MSI-X state in D3hot commit f195fc1e9715ba826c3b62d58038f760f66a4fe9 upstream. The AMD [1022:15b8] USB controller loses some internal functional MSI-X context when transitioning from D0 to D3hot. BIOS normally traps D0->D3hot and D3hot->D0 transitions so it can save and restore that internal context, but some firmware in the field can't do this because it fails to clear the AMD_15B8_RCC_DEV2_EPF0_STRAP2 NO_SOFT_RESET bit. Clear AMD_15B8_RCC_DEV2_EPF0_STRAP2 NO_SOFT_RESET bit before USB controller initialization during boot. Link: https://lore.kernel.org/linux-usb/Y%2Fz9GdHjPyF2rNG3@glanzmann.de/T/#u Link: https://lore.kernel.org/r/20230329172859.699743-1-Basavaraj.Natikar@amd.com Reported-by: Thomas Glanzmann Tested-by: Thomas Glanzmann Signed-off-by: Basavaraj Natikar Signed-off-by: Bjorn Helgaas Reviewed-by: Mario Limonciello Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/pci/fixup.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 9b0e771302ce..3f3411b882f5 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -824,3 +825,23 @@ static void rs690_fix_64bit_dma(struct pci_dev *pdev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma); #endif + +#ifdef CONFIG_AMD_NB + +#define AMD_15B8_RCC_DEV2_EPF0_STRAP2 0x10136008 +#define AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK 0x00000080L + +static void quirk_clear_strap_no_soft_reset_dev2_f0(struct pci_dev *dev) +{ + u32 data; + + if (!amd_smn_read(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, &data)) { + data &= ~AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK; + if (amd_smn_write(0, AMD_15B8_RCC_DEV2_EPF0_STRAP2, data)) + pci_err(dev, "Failed to write data 0x%x\n", data); + } else { + pci_err(dev, "Failed to read data\n"); + } +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15b8, quirk_clear_strap_no_soft_reset_dev2_f0); +#endif From 37a3cf4abc5ae4ac690554f8b6b562101d37379e Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 11 Apr 2023 09:35:57 -0400 Subject: [PATCH 2552/4345] cgroup/cpuset: Wake up cpuset_attach_wq tasks in cpuset_cancel_attach() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ba9182a89626d5f83c2ee4594f55cb9c1e60f0e2 upstream. After a successful cpuset_can_attach() call which increments the attach_in_progress flag, either cpuset_cancel_attach() or cpuset_attach() will be called later. In cpuset_attach(), tasks in cpuset_attach_wq, if present, will be woken up at the end. That is not the case in cpuset_cancel_attach(). So missed wakeup is possible if the attach operation is somehow cancelled. Fix that by doing the wakeup in cpuset_cancel_attach() as well. Fixes: e44193d39e8d ("cpuset: let hotplug propagation work wait for task attaching") Signed-off-by: Waiman Long Reviewed-by: Michal Koutný Cc: stable@vger.kernel.org # v3.11+ Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- kernel/cgroup/cpuset.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 43270b07b2e0..b476591168dc 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2188,11 +2188,15 @@ out_unlock: static void cpuset_cancel_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; + struct cpuset *cs; cgroup_taskset_first(tset, &css); + cs = css_cs(css); percpu_down_write(&cpuset_rwsem); - css_cs(css)->attach_in_progress--; + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); } From 0279e82e148407feec88466990de14bcba9e12c0 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Mon, 6 Mar 2023 09:33:08 +0800 Subject: [PATCH 2553/4345] ubi: Fix failure attaching when vid_hdr offset equals to (sub)page size commit 1e020e1b96afdecd20680b5b5be2a6ffc3d27628 upstream. Following process will make ubi attaching failed since commit 1b42b1a36fc946 ("ubi: ensure that VID header offset ... size"): ID="0xec,0xa1,0x00,0x15" # 128M 128KB 2KB modprobe nandsim id_bytes=$ID flash_eraseall /dev/mtd0 modprobe ubi mtd="0,2048" # set vid_hdr offset as 2048 (one page) (dmesg): ubi0 error: ubi_attach_mtd_dev [ubi]: VID header offset 2048 too large. UBI error: cannot attach mtd0 UBI error: cannot initialize UBI, error -22 Rework original solution, the key point is making sure 'vid_hdr_shift + UBI_VID_HDR_SIZE < ubi->vid_hdr_alsize', so we should check vid_hdr_shift rather not vid_hdr_offset. Then, ubi still support (sub)page aligined VID header offset. Fixes: 1b42b1a36fc946 ("ubi: ensure that VID header offset ... size") Signed-off-by: Zhihao Cheng Tested-by: Nicolas Schichan Tested-by: Miquel Raynal # v5.10, v4.19 Signed-off-by: Richard Weinberger Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/ubi/build.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index e45fdc1bf66a..929ce489b062 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -665,12 +665,6 @@ static int io_init(struct ubi_device *ubi, int max_beb_per1024) ubi->ec_hdr_alsize = ALIGN(UBI_EC_HDR_SIZE, ubi->hdrs_min_io_size); ubi->vid_hdr_alsize = ALIGN(UBI_VID_HDR_SIZE, ubi->hdrs_min_io_size); - if (ubi->vid_hdr_offset && ((ubi->vid_hdr_offset + UBI_VID_HDR_SIZE) > - ubi->vid_hdr_alsize)) { - ubi_err(ubi, "VID header offset %d too large.", ubi->vid_hdr_offset); - return -EINVAL; - } - dbg_gen("min_io_size %d", ubi->min_io_size); dbg_gen("max_write_size %d", ubi->max_write_size); dbg_gen("hdrs_min_io_size %d", ubi->hdrs_min_io_size); @@ -688,6 +682,21 @@ static int io_init(struct ubi_device *ubi, int max_beb_per1024) ubi->vid_hdr_aloffset; } + /* + * Memory allocation for VID header is ubi->vid_hdr_alsize + * which is described in comments in io.c. + * Make sure VID header shift + UBI_VID_HDR_SIZE not exceeds + * ubi->vid_hdr_alsize, so that all vid header operations + * won't access memory out of bounds. + */ + if ((ubi->vid_hdr_shift + UBI_VID_HDR_SIZE) > ubi->vid_hdr_alsize) { + ubi_err(ubi, "Invalid VID header offset %d, VID header shift(%d)" + " + VID header size(%zu) > VID header aligned size(%d).", + ubi->vid_hdr_offset, ubi->vid_hdr_shift, + UBI_VID_HDR_SIZE, ubi->vid_hdr_alsize); + return -EINVAL; + } + /* Similar for the data offset */ ubi->leb_start = ubi->vid_hdr_offset + UBI_VID_HDR_SIZE; ubi->leb_start = ALIGN(ubi->leb_start, ubi->min_io_size); From 33611d4a8181fdac99489cc16cb05796e23d533c Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 9 Nov 2020 18:21:55 +0000 Subject: [PATCH 2554/4345] mtd: ubi: wl: Fix a couple of kernel-doc issues [ Upstream commit ab4e4de9fd8b469823a645f05f2c142e9270b012 ] Fixes the following W=1 kernel build warning(s): drivers/mtd/ubi/wl.c:584: warning: Function parameter or member 'nested' not described in 'schedule_erase' drivers/mtd/ubi/wl.c:1075: warning: Excess function parameter 'shutdown' description in '__erase_worker' Cc: Richard Weinberger Cc: Miquel Raynal Cc: Vignesh Raghavendra Cc: linux-mtd@lists.infradead.org Signed-off-by: Lee Jones Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20201109182206.3037326-13-lee.jones@linaro.org Stable-dep-of: f773f0a331d6 ("ubi: Fix deadlock caused by recursively holding work_sem") Signed-off-by: Sasha Levin --- drivers/mtd/ubi/wl.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 6da09263e0b9..2ee0e60c43c2 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -575,6 +575,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, * @vol_id: the volume ID that last used this PEB * @lnum: the last used logical eraseblock number for the PEB * @torture: if the physical eraseblock has to be tortured + * @nested: denotes whether the work_sem is already held in read mode * * This function returns zero in case of success and a %-ENOMEM in case of * failure. @@ -1066,8 +1067,6 @@ out_unlock: * __erase_worker - physical eraseblock erase worker function. * @ubi: UBI device description object * @wl_wrk: the work object - * @shutdown: non-zero if the worker has to free memory and exit - * because the WL sub-system is shutting down * * This function erases a physical eraseblock and perform torture testing if * needed. It also takes care about marking the physical eraseblock bad if From 5abf8af8df97d1c57ebf66ed3d8a20ac8661407f Mon Sep 17 00:00:00 2001 From: ZhaoLong Wang Date: Sat, 4 Mar 2023 09:41:41 +0800 Subject: [PATCH 2555/4345] ubi: Fix deadlock caused by recursively holding work_sem [ Upstream commit f773f0a331d6c41733b17bebbc1b6cae12e016f5 ] During the processing of the bgt, if the sync_erase() return -EBUSY or some other error code in __erase_worker(),schedule_erase() called again lead to the down_read(ubi->work_sem) hold twice and may get block by down_write(ubi->work_sem) in ubi_update_fastmap(), which cause deadlock. ubi bgt other task do_work down_read(&ubi->work_sem) ubi_update_fastmap erase_worker # Blocked by down_read __erase_worker down_write(&ubi->work_sem) schedule_erase schedule_ubi_work down_read(&ubi->work_sem) Fix this by changing input parameter @nested of the schedule_erase() to 'true' to avoid recursively acquiring the down_read(&ubi->work_sem). Also, fix the incorrect comment about @nested parameter of the schedule_erase() because when down_write(ubi->work_sem) is held, the @nested is also need be true. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217093 Fixes: 2e8f08deabbc ("ubi: Fix races around ubi_refill_pools()") Signed-off-by: ZhaoLong Wang Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Sasha Levin --- drivers/mtd/ubi/wl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 2ee0e60c43c2..4427018ad4d9 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -575,7 +575,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, * @vol_id: the volume ID that last used this PEB * @lnum: the last used logical eraseblock number for the PEB * @torture: if the physical eraseblock has to be tortured - * @nested: denotes whether the work_sem is already held in read mode + * @nested: denotes whether the work_sem is already held * * This function returns zero in case of success and a %-ENOMEM in case of * failure. @@ -1121,7 +1121,7 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) int err1; /* Re-schedule the LEB for erasure */ - err1 = schedule_erase(ubi, e, vol_id, lnum, 0, false); + err1 = schedule_erase(ubi, e, vol_id, lnum, 0, true); if (err1) { spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e); From f6d8a3a2eaab376e184846d0f8e3937644f353a1 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 12 Aug 2021 18:52:19 +0530 Subject: [PATCH 2556/4345] powerpc/pseries: rename min_common_depth to primary_domain_index [ Upstream commit 7e35ef662ca05c42dbc2f401bb76d9219dd7fd02 ] No functional change in this patch. Signed-off-by: Aneesh Kumar K.V Reviewed-by: David Gibson Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210812132223.225214-2-aneesh.kumar@linux.ibm.com Stable-dep-of: b277fc793daf ("powerpc/papr_scm: Update the NUMA distance table for the target node") Signed-off-by: Sasha Levin --- arch/powerpc/mm/numa.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 275c60f92a7c..a21f62fcda1e 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -51,7 +51,7 @@ EXPORT_SYMBOL(numa_cpu_lookup_table); EXPORT_SYMBOL(node_to_cpumask_map); EXPORT_SYMBOL(node_data); -static int min_common_depth; +static int primary_domain_index; static int n_mem_addr_cells, n_mem_size_cells; static int form1_affinity; @@ -232,8 +232,8 @@ static int associativity_to_nid(const __be32 *associativity) if (!numa_enabled) goto out; - if (of_read_number(associativity, 1) >= min_common_depth) - nid = of_read_number(&associativity[min_common_depth], 1); + if (of_read_number(associativity, 1) >= primary_domain_index) + nid = of_read_number(&associativity[primary_domain_index], 1); /* POWER4 LPAR uses 0xffff as invalid node */ if (nid == 0xffff || nid >= nr_node_ids) @@ -284,9 +284,9 @@ int of_node_to_nid(struct device_node *device) } EXPORT_SYMBOL(of_node_to_nid); -static int __init find_min_common_depth(void) +static int __init find_primary_domain_index(void) { - int depth; + int index; struct device_node *root; if (firmware_has_feature(FW_FEATURE_OPAL)) @@ -326,7 +326,7 @@ static int __init find_min_common_depth(void) } if (form1_affinity) { - depth = of_read_number(distance_ref_points, 1); + index = of_read_number(distance_ref_points, 1); } else { if (distance_ref_points_depth < 2) { printk(KERN_WARNING "NUMA: " @@ -334,7 +334,7 @@ static int __init find_min_common_depth(void) goto err; } - depth = of_read_number(&distance_ref_points[1], 1); + index = of_read_number(&distance_ref_points[1], 1); } /* @@ -348,7 +348,7 @@ static int __init find_min_common_depth(void) } of_node_put(root); - return depth; + return index; err: of_node_put(root); @@ -437,16 +437,16 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb) int nid = default_nid; int rc, index; - if ((min_common_depth < 0) || !numa_enabled) + if ((primary_domain_index < 0) || !numa_enabled) return default_nid; rc = of_get_assoc_arrays(&aa); if (rc) return default_nid; - if (min_common_depth <= aa.array_sz && + if (primary_domain_index <= aa.array_sz && !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) { - index = lmb->aa_index * aa.array_sz + min_common_depth - 1; + index = lmb->aa_index * aa.array_sz + primary_domain_index - 1; nid = of_read_number(&aa.arrays[index], 1); if (nid == 0xffff || nid >= nr_node_ids) @@ -708,18 +708,18 @@ static int __init parse_numa_properties(void) return -1; } - min_common_depth = find_min_common_depth(); + primary_domain_index = find_primary_domain_index(); - if (min_common_depth < 0) { + if (primary_domain_index < 0) { /* - * if we fail to parse min_common_depth from device tree + * if we fail to parse primary_domain_index from device tree * mark the numa disabled, boot with numa disabled. */ numa_enabled = false; - return min_common_depth; + return primary_domain_index; } - dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth); + dbg("NUMA associativity depth for CPU/Memory: %d\n", primary_domain_index); /* * Even though we connect cpus to numa domains later in SMP @@ -926,7 +926,7 @@ static void __init find_possible_nodes(void) goto out; } - max_nodes = of_read_number(&domains[min_common_depth], 1); + max_nodes = of_read_number(&domains[primary_domain_index], 1); pr_info("Partition configured for %d NUMA nodes.\n", max_nodes); for (i = 0; i < max_nodes; i++) { @@ -935,7 +935,7 @@ static void __init find_possible_nodes(void) } prop_length /= sizeof(int); - if (prop_length > min_common_depth + 2) + if (prop_length > primary_domain_index + 2) coregroup_enabled = 1; out: @@ -1268,7 +1268,7 @@ int cpu_to_coregroup_id(int cpu) goto out; index = of_read_number(associativity, 1); - if (index > min_common_depth + 1) + if (index > primary_domain_index + 1) return of_read_number(&associativity[index - 1], 1); out: From f2ae0eb96bfbd03b9ff3a8901f35b506787c6c62 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 12 Aug 2021 18:52:20 +0530 Subject: [PATCH 2557/4345] powerpc/pseries: Rename TYPE1_AFFINITY to FORM1_AFFINITY [ Upstream commit 0eacd06bb8adea8dd9edb0a30144166d9f227e64 ] Also make related code cleanup that will allow adding FORM2_AFFINITY in later patches. No functional change in this patch. Signed-off-by: Aneesh Kumar K.V Reviewed-by: David Gibson Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210812132223.225214-3-aneesh.kumar@linux.ibm.com Stable-dep-of: b277fc793daf ("powerpc/papr_scm: Update the NUMA distance table for the target node") Signed-off-by: Sasha Levin --- arch/powerpc/include/asm/firmware.h | 4 +-- arch/powerpc/include/asm/prom.h | 2 +- arch/powerpc/kernel/prom_init.c | 2 +- arch/powerpc/mm/numa.c | 35 ++++++++++++++--------- arch/powerpc/platforms/pseries/firmware.c | 2 +- 5 files changed, 26 insertions(+), 19 deletions(-) diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index aa6a5ef5d483..0cf648d829f1 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -44,7 +44,7 @@ #define FW_FEATURE_OPAL ASM_CONST(0x0000000010000000) #define FW_FEATURE_SET_MODE ASM_CONST(0x0000000040000000) #define FW_FEATURE_BEST_ENERGY ASM_CONST(0x0000000080000000) -#define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000) +#define FW_FEATURE_FORM1_AFFINITY ASM_CONST(0x0000000100000000) #define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) #define FW_FEATURE_DRMEM_V2 ASM_CONST(0x0000000400000000) #define FW_FEATURE_DRC_INFO ASM_CONST(0x0000000800000000) @@ -69,7 +69,7 @@ enum { FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO | FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | - FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN | + FW_FEATURE_FORM1_AFFINITY | FW_FEATURE_PRRN | FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 | FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE | FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR | diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 324a13351749..df9fec9d232c 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -147,7 +147,7 @@ extern int of_read_drc_info_cell(struct property **prop, #define OV5_MSI 0x0201 /* PCIe/MSI support */ #define OV5_CMO 0x0480 /* Cooperative Memory Overcommitment */ #define OV5_XCMO 0x0440 /* Page Coalescing */ -#define OV5_TYPE1_AFFINITY 0x0580 /* Type 1 NUMA affinity */ +#define OV5_FORM1_AFFINITY 0x0580 /* FORM1 NUMA affinity */ #define OV5_PRRN 0x0540 /* Platform Resource Reassignment */ #define OV5_HP_EVT 0x0604 /* Hot Plug Event support */ #define OV5_RESIZE_HPT 0x0601 /* Hash Page Table resizing */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 9e71c0739f08..a3bf3587a416 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1069,7 +1069,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = { #else 0, #endif - .associativity = OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN), + .associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN), .bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT), .micro_checkpoint = 0, .reserved0 = 0, diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index a21f62fcda1e..415cd3d258ff 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -53,7 +53,10 @@ EXPORT_SYMBOL(node_data); static int primary_domain_index; static int n_mem_addr_cells, n_mem_size_cells; -static int form1_affinity; + +#define FORM0_AFFINITY 0 +#define FORM1_AFFINITY 1 +static int affinity_form; #define MAX_DISTANCE_REF_POINTS 4 static int distance_ref_points_depth; @@ -190,7 +193,7 @@ int __node_distance(int a, int b) int i; int distance = LOCAL_DISTANCE; - if (!form1_affinity) + if (affinity_form == FORM0_AFFINITY) return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE); for (i = 0; i < distance_ref_points_depth; i++) { @@ -210,7 +213,7 @@ static void initialize_distance_lookup_table(int nid, { int i; - if (!form1_affinity) + if (affinity_form != FORM1_AFFINITY) return; for (i = 0; i < distance_ref_points_depth; i++) { @@ -289,6 +292,17 @@ static int __init find_primary_domain_index(void) int index; struct device_node *root; + /* + * Check for which form of affinity. + */ + if (firmware_has_feature(FW_FEATURE_OPAL)) { + affinity_form = FORM1_AFFINITY; + } else if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY)) { + dbg("Using form 1 affinity\n"); + affinity_form = FORM1_AFFINITY; + } else + affinity_form = FORM0_AFFINITY; + if (firmware_has_feature(FW_FEATURE_OPAL)) root = of_find_node_by_path("/ibm,opal"); else @@ -318,23 +332,16 @@ static int __init find_primary_domain_index(void) } distance_ref_points_depth /= sizeof(int); - - if (firmware_has_feature(FW_FEATURE_OPAL) || - firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) { - dbg("Using form 1 affinity\n"); - form1_affinity = 1; - } - - if (form1_affinity) { - index = of_read_number(distance_ref_points, 1); - } else { + if (affinity_form == FORM0_AFFINITY) { if (distance_ref_points_depth < 2) { printk(KERN_WARNING "NUMA: " - "short ibm,associativity-reference-points\n"); + "short ibm,associativity-reference-points\n"); goto err; } index = of_read_number(&distance_ref_points[1], 1); + } else { + index = of_read_number(distance_ref_points, 1); } /* diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 4c7b7f5a2ebc..5d4c2bc20bba 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -119,7 +119,7 @@ struct vec5_fw_feature { static __initdata struct vec5_fw_feature vec5_fw_features_table[] = { - {FW_FEATURE_TYPE1_AFFINITY, OV5_TYPE1_AFFINITY}, + {FW_FEATURE_FORM1_AFFINITY, OV5_FORM1_AFFINITY}, {FW_FEATURE_PRRN, OV5_PRRN}, {FW_FEATURE_DRMEM_V2, OV5_DRMEM_V2}, {FW_FEATURE_DRC_INFO, OV5_DRC_INFO}, From 18ce785effd986f8e4270b4fe160eeb759c7aea6 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 12 Aug 2021 18:52:21 +0530 Subject: [PATCH 2558/4345] powerpc/pseries: Consolidate different NUMA distance update code paths [ Upstream commit 8ddc6448ec5a5ef50eaa581a7dec0e12a02850ff ] The associativity details of the newly added resourced are collected from the hypervisor via "ibm,configure-connector" rtas call. Update the numa distance details of the newly added numa node after the above call. Instead of updating NUMA distance every time we lookup a node id from the associativity property, add helpers that can be used during boot which does this only once. Also remove the distance update from node id lookup helpers. Currently, we duplicate parsing code for ibm,associativity and ibm,associativity-lookup-arrays in the kernel. The associativity array provided by these device tree properties are very similar and hence can use a helper to parse the node id and numa distance details. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210812132223.225214-4-aneesh.kumar@linux.ibm.com Stable-dep-of: b277fc793daf ("powerpc/papr_scm: Update the NUMA distance table for the target node") Signed-off-by: Sasha Levin --- arch/powerpc/include/asm/topology.h | 2 + arch/powerpc/mm/numa.c | 212 +++++++++++++----- arch/powerpc/platforms/pseries/hotplug-cpu.c | 2 + .../platforms/pseries/hotplug-memory.c | 2 + 4 files changed, 161 insertions(+), 57 deletions(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 3beeb030cd78..1604920d8d2d 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -64,6 +64,7 @@ static inline int early_cpu_to_node(int cpu) } int of_drconf_to_nid_single(struct drmem_lmb *lmb); +void update_numa_distance(struct device_node *node); #else @@ -93,6 +94,7 @@ static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb) return first_online_node; } +static inline void update_numa_distance(struct device_node *node) {} #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 415cd3d258ff..e61593ae25c9 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -208,50 +208,35 @@ int __node_distance(int a, int b) } EXPORT_SYMBOL(__node_distance); -static void initialize_distance_lookup_table(int nid, - const __be32 *associativity) +static int __associativity_to_nid(const __be32 *associativity, + int max_array_sz) { - int i; + int nid; + /* + * primary_domain_index is 1 based array index. + */ + int index = primary_domain_index - 1; - if (affinity_form != FORM1_AFFINITY) - return; + if (!numa_enabled || index >= max_array_sz) + return NUMA_NO_NODE; - for (i = 0; i < distance_ref_points_depth; i++) { - const __be32 *entry; + nid = of_read_number(&associativity[index], 1); - entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1]; - distance_lookup_table[nid][i] = of_read_number(entry, 1); - } + /* POWER4 LPAR uses 0xffff as invalid node */ + if (nid == 0xffff || nid >= nr_node_ids) + nid = NUMA_NO_NODE; + return nid; } - /* * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA * info is found. */ static int associativity_to_nid(const __be32 *associativity) { - int nid = NUMA_NO_NODE; + int array_sz = of_read_number(associativity, 1); - if (!numa_enabled) - goto out; - - if (of_read_number(associativity, 1) >= primary_domain_index) - nid = of_read_number(&associativity[primary_domain_index], 1); - - /* POWER4 LPAR uses 0xffff as invalid node */ - if (nid == 0xffff || nid >= nr_node_ids) - nid = NUMA_NO_NODE; - - if (nid > 0 && - of_read_number(associativity, 1) >= distance_ref_points_depth) { - /* - * Skip the length field and send start of associativity array - */ - initialize_distance_lookup_table(nid, associativity + 1); - } - -out: - return nid; + /* Skip the first element in the associativity array */ + return __associativity_to_nid((associativity + 1), array_sz); } /* Returns the nid associated with the given device tree node, @@ -287,6 +272,60 @@ int of_node_to_nid(struct device_node *device) } EXPORT_SYMBOL(of_node_to_nid); +static void __initialize_form1_numa_distance(const __be32 *associativity, + int max_array_sz) +{ + int i, nid; + + if (affinity_form != FORM1_AFFINITY) + return; + + nid = __associativity_to_nid(associativity, max_array_sz); + if (nid != NUMA_NO_NODE) { + for (i = 0; i < distance_ref_points_depth; i++) { + const __be32 *entry; + int index = be32_to_cpu(distance_ref_points[i]) - 1; + + /* + * broken hierarchy, return with broken distance table + */ + if (WARN(index >= max_array_sz, "Broken ibm,associativity property")) + return; + + entry = &associativity[index]; + distance_lookup_table[nid][i] = of_read_number(entry, 1); + } + } +} + +static void initialize_form1_numa_distance(const __be32 *associativity) +{ + int array_sz; + + array_sz = of_read_number(associativity, 1); + /* Skip the first element in the associativity array */ + __initialize_form1_numa_distance(associativity + 1, array_sz); +} + +/* + * Used to update distance information w.r.t newly added node. + */ +void update_numa_distance(struct device_node *node) +{ + if (affinity_form == FORM0_AFFINITY) + return; + else if (affinity_form == FORM1_AFFINITY) { + const __be32 *associativity; + + associativity = of_get_associativity(node); + if (!associativity) + return; + + initialize_form1_numa_distance(associativity); + return; + } +} + static int __init find_primary_domain_index(void) { int index; @@ -433,6 +472,38 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa) return 0; } +static int get_nid_and_numa_distance(struct drmem_lmb *lmb) +{ + struct assoc_arrays aa = { .arrays = NULL }; + int default_nid = NUMA_NO_NODE; + int nid = default_nid; + int rc, index; + + if ((primary_domain_index < 0) || !numa_enabled) + return default_nid; + + rc = of_get_assoc_arrays(&aa); + if (rc) + return default_nid; + + if (primary_domain_index <= aa.array_sz && + !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) { + const __be32 *associativity; + + index = lmb->aa_index * aa.array_sz; + associativity = &aa.arrays[index]; + nid = __associativity_to_nid(associativity, aa.array_sz); + if (nid > 0 && affinity_form == FORM1_AFFINITY) { + /* + * lookup array associativity entries have + * no length of the array as the first element. + */ + __initialize_form1_numa_distance(associativity, aa.array_sz); + } + } + return nid; +} + /* * This is like of_node_to_nid_single() for memory represented in the * ibm,dynamic-reconfiguration-memory node. @@ -453,26 +524,19 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb) if (primary_domain_index <= aa.array_sz && !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) { - index = lmb->aa_index * aa.array_sz + primary_domain_index - 1; - nid = of_read_number(&aa.arrays[index], 1); + const __be32 *associativity; - if (nid == 0xffff || nid >= nr_node_ids) - nid = default_nid; - - if (nid > 0) { - index = lmb->aa_index * aa.array_sz; - initialize_distance_lookup_table(nid, - &aa.arrays[index]); - } + index = lmb->aa_index * aa.array_sz; + associativity = &aa.arrays[index]; + nid = __associativity_to_nid(associativity, aa.array_sz); } - return nid; } #ifdef CONFIG_PPC_SPLPAR -static int vphn_get_nid(long lcpu) + +static int __vphn_get_associativity(long lcpu, __be32 *associativity) { - __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0}; long rc, hwid; /* @@ -492,12 +556,30 @@ static int vphn_get_nid(long lcpu) rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity); if (rc == H_SUCCESS) - return associativity_to_nid(associativity); + return 0; } + return -1; +} + +static int vphn_get_nid(long lcpu) +{ + __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0}; + + + if (!__vphn_get_associativity(lcpu, associativity)) + return associativity_to_nid(associativity); + return NUMA_NO_NODE; + } #else + +static int __vphn_get_associativity(long lcpu, __be32 *associativity) +{ + return -1; +} + static int vphn_get_nid(long unused) { return NUMA_NO_NODE; @@ -692,7 +774,7 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb, size = read_n_cells(n_mem_size_cells, usm); } - nid = of_drconf_to_nid_single(lmb); + nid = get_nid_and_numa_distance(lmb); fake_numa_create_new_node(((base + size) >> PAGE_SHIFT), &nid); node_set_online(nid); @@ -709,6 +791,7 @@ static int __init parse_numa_properties(void) struct device_node *memory; int default_nid = 0; unsigned long i; + const __be32 *associativity; if (numa_enabled == 0) { printk(KERN_WARNING "NUMA disabled by user\n"); @@ -734,18 +817,30 @@ static int __init parse_numa_properties(void) * each node to be onlined must have NODE_DATA etc backing it. */ for_each_present_cpu(i) { + __be32 vphn_assoc[VPHN_ASSOC_BUFSIZE]; struct device_node *cpu; - int nid = vphn_get_nid(i); + int nid = NUMA_NO_NODE; - /* - * Don't fall back to default_nid yet -- we will plug - * cpus into nodes once the memory scan has discovered - * the topology. - */ - if (nid == NUMA_NO_NODE) { + memset(vphn_assoc, 0, VPHN_ASSOC_BUFSIZE * sizeof(__be32)); + + if (__vphn_get_associativity(i, vphn_assoc) == 0) { + nid = associativity_to_nid(vphn_assoc); + initialize_form1_numa_distance(vphn_assoc); + } else { + + /* + * Don't fall back to default_nid yet -- we will plug + * cpus into nodes once the memory scan has discovered + * the topology. + */ cpu = of_get_cpu_node(i, NULL); BUG_ON(!cpu); - nid = of_node_to_nid_single(cpu); + + associativity = of_get_associativity(cpu); + if (associativity) { + nid = associativity_to_nid(associativity); + initialize_form1_numa_distance(associativity); + } of_node_put(cpu); } @@ -783,8 +878,11 @@ new_range: * have associativity properties. If none, then * everything goes to default_nid. */ - nid = of_node_to_nid_single(memory); - if (nid < 0) + associativity = of_get_associativity(memory); + if (associativity) { + nid = associativity_to_nid(associativity); + initialize_form1_numa_distance(associativity); + } else nid = default_nid; fake_numa_create_new_node(((start + size) >> PAGE_SHIFT), &nid); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 325f3b220f36..1f8f97210d14 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -484,6 +484,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index) return saved_rc; } + update_numa_distance(dn); + rc = dlpar_online_cpu(dn); if (rc) { saved_rc = rc; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 7efe6ec5d14a..a5f968b5fa3a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -180,6 +180,8 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb) return -ENODEV; } + update_numa_distance(lmb_node); + dr_node = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (!dr_node) { dlpar_free_cc_nodes(lmb_node); From 498618e0a1e779f22cfa3bcf2497244bc7bace5a Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 12 Aug 2021 18:52:22 +0530 Subject: [PATCH 2559/4345] powerpc/pseries: Add a helper for form1 cpu distance [ Upstream commit ef31cb83d19c4c589d650747cd5a7e502be9f665 ] This helper is only used with the dispatch trace log collection. A later patch will add Form2 affinity support and this change helps in keeping that simpler. Also add a comment explaining we don't expect the code to be called with FORM0 Signed-off-by: Aneesh Kumar K.V Reviewed-by: David Gibson Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210812132223.225214-5-aneesh.kumar@linux.ibm.com Stable-dep-of: b277fc793daf ("powerpc/papr_scm: Update the NUMA distance table for the target node") Signed-off-by: Sasha Levin --- arch/powerpc/include/asm/topology.h | 4 ++-- arch/powerpc/mm/numa.c | 10 +++++++++- arch/powerpc/platforms/pseries/lpar.c | 4 ++-- 3 files changed, 13 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 1604920d8d2d..b239ef589ae0 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -36,7 +36,7 @@ static inline int pcibus_to_node(struct pci_bus *bus) cpu_all_mask : \ cpumask_of_node(pcibus_to_node(bus))) -extern int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc); +int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc); extern int __node_distance(int, int); #define node_distance(a, b) __node_distance(a, b) @@ -84,7 +84,7 @@ static inline void sysfs_remove_device_from_node(struct device *dev, static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} -static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) +static inline int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) { return 0; } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index e61593ae25c9..010476abec34 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -166,7 +166,7 @@ static void unmap_cpu_from_node(unsigned long cpu) } #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */ -int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) +static int __cpu_form1_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) { int dist = 0; @@ -182,6 +182,14 @@ int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) return dist; } +int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) +{ + /* We should not get called with FORM0 */ + VM_WARN_ON(affinity_form == FORM0_AFFINITY); + + return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc); +} + /* must hold reference to node during call */ static const __be32 *of_get_associativity(struct device_node *dev) { diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 115d196560b8..28396a7e77d6 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -261,7 +261,7 @@ static int cpu_relative_dispatch_distance(int last_disp_cpu, int cur_disp_cpu) if (!last_disp_cpu_assoc || !cur_disp_cpu_assoc) return -EIO; - return cpu_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc); + return cpu_relative_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc); } static int cpu_home_node_dispatch_distance(int disp_cpu) @@ -281,7 +281,7 @@ static int cpu_home_node_dispatch_distance(int disp_cpu) if (!disp_cpu_assoc || !vcpu_assoc) return -EIO; - return cpu_distance(disp_cpu_assoc, vcpu_assoc); + return cpu_relative_distance(disp_cpu_assoc, vcpu_assoc); } static void update_vcpu_disp_stat(int disp_cpu) From 453b3188be89a413efd7bad4ceb1f78a4716475b Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 12 Aug 2021 18:52:23 +0530 Subject: [PATCH 2560/4345] powerpc/pseries: Add support for FORM2 associativity [ Upstream commit 1c6b5a7e74052768977855f95d6b8812f6e7772c ] PAPR interface currently supports two different ways of communicating resource grouping details to the OS. These are referred to as Form 0 and Form 1 associativity grouping. Form 0 is the older format and is now considered deprecated. This patch adds another resource grouping named FORM2. Signed-off-by: Daniel Henrique Barboza Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210812132223.225214-6-aneesh.kumar@linux.ibm.com Stable-dep-of: b277fc793daf ("powerpc/papr_scm: Update the NUMA distance table for the target node") Signed-off-by: Sasha Levin --- Documentation/powerpc/associativity.rst | 104 ++++++++++ arch/powerpc/include/asm/firmware.h | 3 +- arch/powerpc/include/asm/prom.h | 1 + arch/powerpc/kernel/prom_init.c | 3 +- arch/powerpc/mm/numa.c | 219 +++++++++++++++++----- arch/powerpc/platforms/pseries/firmware.c | 1 + 6 files changed, 278 insertions(+), 53 deletions(-) create mode 100644 Documentation/powerpc/associativity.rst diff --git a/Documentation/powerpc/associativity.rst b/Documentation/powerpc/associativity.rst new file mode 100644 index 000000000000..07e7dd3d6c87 --- /dev/null +++ b/Documentation/powerpc/associativity.rst @@ -0,0 +1,104 @@ +============================ +NUMA resource associativity +============================= + +Associativity represents the groupings of the various platform resources into +domains of substantially similar mean performance relative to resources outside +of that domain. Resources subsets of a given domain that exhibit better +performance relative to each other than relative to other resources subsets +are represented as being members of a sub-grouping domain. This performance +characteristic is presented in terms of NUMA node distance within the Linux kernel. +From the platform view, these groups are also referred to as domains. + +PAPR interface currently supports different ways of communicating these resource +grouping details to the OS. These are referred to as Form 0, Form 1 and Form2 +associativity grouping. Form 0 is the oldest format and is now considered deprecated. + +Hypervisor indicates the type/form of associativity used via "ibm,architecture-vec-5 property". +Bit 0 of byte 5 in the "ibm,architecture-vec-5" property indicates usage of Form 0 or Form 1. +A value of 1 indicates the usage of Form 1 associativity. For Form 2 associativity +bit 2 of byte 5 in the "ibm,architecture-vec-5" property is used. + +Form 0 +----- +Form 0 associativity supports only two NUMA distances (LOCAL and REMOTE). + +Form 1 +----- +With Form 1 a combination of ibm,associativity-reference-points, and ibm,associativity +device tree properties are used to determine the NUMA distance between resource groups/domains. + +The “ibm,associativity” property contains a list of one or more numbers (domainID) +representing the resource’s platform grouping domains. + +The “ibm,associativity-reference-points” property contains a list of one or more numbers +(domainID index) that represents the 1 based ordinal in the associativity lists. +The list of domainID indexes represents an increasing hierarchy of resource grouping. + +ex: +{ primary domainID index, secondary domainID index, tertiary domainID index.. } + +Linux kernel uses the domainID at the primary domainID index as the NUMA node id. +Linux kernel computes NUMA distance between two domains by recursively comparing +if they belong to the same higher-level domains. For mismatch at every higher +level of the resource group, the kernel doubles the NUMA distance between the +comparing domains. + +Form 2 +------- +Form 2 associativity format adds separate device tree properties representing NUMA node distance +thereby making the node distance computation flexible. Form 2 also allows flexible primary +domain numbering. With numa distance computation now detached from the index value in +"ibm,associativity-reference-points" property, Form 2 allows a large number of primary domain +ids at the same domainID index representing resource groups of different performance/latency +characteristics. + +Hypervisor indicates the usage of FORM2 associativity using bit 2 of byte 5 in the +"ibm,architecture-vec-5" property. + +"ibm,numa-lookup-index-table" property contains a list of one or more numbers representing +the domainIDs present in the system. The offset of the domainID in this property is +used as an index while computing numa distance information via "ibm,numa-distance-table". + +prop-encoded-array: The number N of the domainIDs encoded as with encode-int, followed by +N domainID encoded as with encode-int + +For ex: +"ibm,numa-lookup-index-table" = {4, 0, 8, 250, 252}. The offset of domainID 8 (2) is used when +computing the distance of domain 8 from other domains present in the system. For the rest of +this document, this offset will be referred to as domain distance offset. + +"ibm,numa-distance-table" property contains a list of one or more numbers representing the NUMA +distance between resource groups/domains present in the system. + +prop-encoded-array: The number N of the distance values encoded as with encode-int, followed by +N distance values encoded as with encode-bytes. The max distance value we could encode is 255. +The number N must be equal to the square of m where m is the number of domainIDs in the +numa-lookup-index-table. + +For ex: +ibm,numa-lookup-index-table = <3 0 8 40>; +ibm,numa-distace-table = <9>, /bits/ 8 < 10 20 80 + 20 10 160 + 80 160 10>; + | 0 8 40 +--|------------ + | +0 | 10 20 80 + | +8 | 20 10 160 + | +40| 80 160 10 + +A possible "ibm,associativity" property for resources in node 0, 8 and 40 + +{ 3, 6, 7, 0 } +{ 3, 6, 9, 8 } +{ 3, 6, 7, 40} + +With "ibm,associativity-reference-points" { 0x3 } + +"ibm,lookup-index-table" helps in having a compact representation of distance matrix. +Since domainID can be sparse, the matrix of distances can also be effectively sparse. +With "ibm,lookup-index-table" we can achieve a compact representation of +distance information. diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 0cf648d829f1..89a31f1c7b11 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -53,6 +53,7 @@ #define FW_FEATURE_ULTRAVISOR ASM_CONST(0x0000004000000000) #define FW_FEATURE_STUFF_TCE ASM_CONST(0x0000008000000000) #define FW_FEATURE_RPT_INVALIDATE ASM_CONST(0x0000010000000000) +#define FW_FEATURE_FORM2_AFFINITY ASM_CONST(0x0000020000000000) #ifndef __ASSEMBLY__ @@ -73,7 +74,7 @@ enum { FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 | FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE | FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR | - FW_FEATURE_RPT_INVALIDATE, + FW_FEATURE_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR, FW_FEATURE_POWERNV_ALWAYS = 0, diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index df9fec9d232c..5c80152e8f18 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -149,6 +149,7 @@ extern int of_read_drc_info_cell(struct property **prop, #define OV5_XCMO 0x0440 /* Page Coalescing */ #define OV5_FORM1_AFFINITY 0x0580 /* FORM1 NUMA affinity */ #define OV5_PRRN 0x0540 /* Platform Resource Reassignment */ +#define OV5_FORM2_AFFINITY 0x0520 /* Form2 NUMA affinity */ #define OV5_HP_EVT 0x0604 /* Hot Plug Event support */ #define OV5_RESIZE_HPT 0x0601 /* Hash Page Table resizing */ #define OV5_PFO_HW_RNG 0x1180 /* PFO Random Number Generator */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a3bf3587a416..6f7ad8076315 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1069,7 +1069,8 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = { #else 0, #endif - .associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN), + .associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN) | + OV5_FEAT(OV5_FORM2_AFFINITY), .bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT), .micro_checkpoint = 0, .reserved0 = 0, diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 010476abec34..cfc170935a58 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -56,12 +56,17 @@ static int n_mem_addr_cells, n_mem_size_cells; #define FORM0_AFFINITY 0 #define FORM1_AFFINITY 1 +#define FORM2_AFFINITY 2 static int affinity_form; #define MAX_DISTANCE_REF_POINTS 4 static int distance_ref_points_depth; static const __be32 *distance_ref_points; static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS]; +static int numa_distance_table[MAX_NUMNODES][MAX_NUMNODES] = { + [0 ... MAX_NUMNODES - 1] = { [0 ... MAX_NUMNODES - 1] = -1 } +}; +static int numa_id_index_table[MAX_NUMNODES] = { [0 ... MAX_NUMNODES - 1] = NUMA_NO_NODE }; /* * Allocate node_to_cpumask_map based on number of available nodes @@ -166,56 +171,6 @@ static void unmap_cpu_from_node(unsigned long cpu) } #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */ -static int __cpu_form1_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) -{ - int dist = 0; - - int i, index; - - for (i = 0; i < distance_ref_points_depth; i++) { - index = be32_to_cpu(distance_ref_points[i]); - if (cpu1_assoc[index] == cpu2_assoc[index]) - break; - dist++; - } - - return dist; -} - -int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) -{ - /* We should not get called with FORM0 */ - VM_WARN_ON(affinity_form == FORM0_AFFINITY); - - return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc); -} - -/* must hold reference to node during call */ -static const __be32 *of_get_associativity(struct device_node *dev) -{ - return of_get_property(dev, "ibm,associativity", NULL); -} - -int __node_distance(int a, int b) -{ - int i; - int distance = LOCAL_DISTANCE; - - if (affinity_form == FORM0_AFFINITY) - return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE); - - for (i = 0; i < distance_ref_points_depth; i++) { - if (distance_lookup_table[a][i] == distance_lookup_table[b][i]) - break; - - /* Double the distance for each NUMA level */ - distance *= 2; - } - - return distance; -} -EXPORT_SYMBOL(__node_distance); - static int __associativity_to_nid(const __be32 *associativity, int max_array_sz) { @@ -247,6 +202,76 @@ static int associativity_to_nid(const __be32 *associativity) return __associativity_to_nid((associativity + 1), array_sz); } +static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) +{ + int dist; + int node1, node2; + + node1 = associativity_to_nid(cpu1_assoc); + node2 = associativity_to_nid(cpu2_assoc); + + dist = numa_distance_table[node1][node2]; + if (dist <= LOCAL_DISTANCE) + return 0; + else if (dist <= REMOTE_DISTANCE) + return 1; + else + return 2; +} + +static int __cpu_form1_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) +{ + int dist = 0; + + int i, index; + + for (i = 0; i < distance_ref_points_depth; i++) { + index = be32_to_cpu(distance_ref_points[i]); + if (cpu1_assoc[index] == cpu2_assoc[index]) + break; + dist++; + } + + return dist; +} + +int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) +{ + /* We should not get called with FORM0 */ + VM_WARN_ON(affinity_form == FORM0_AFFINITY); + if (affinity_form == FORM1_AFFINITY) + return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc); + return __cpu_form2_relative_distance(cpu1_assoc, cpu2_assoc); +} + +/* must hold reference to node during call */ +static const __be32 *of_get_associativity(struct device_node *dev) +{ + return of_get_property(dev, "ibm,associativity", NULL); +} + +int __node_distance(int a, int b) +{ + int i; + int distance = LOCAL_DISTANCE; + + if (affinity_form == FORM2_AFFINITY) + return numa_distance_table[a][b]; + else if (affinity_form == FORM0_AFFINITY) + return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE); + + for (i = 0; i < distance_ref_points_depth; i++) { + if (distance_lookup_table[a][i] == distance_lookup_table[b][i]) + break; + + /* Double the distance for each NUMA level */ + distance *= 2; + } + + return distance; +} +EXPORT_SYMBOL(__node_distance); + /* Returns the nid associated with the given device tree node, * or -1 if not found. */ @@ -320,6 +345,8 @@ static void initialize_form1_numa_distance(const __be32 *associativity) */ void update_numa_distance(struct device_node *node) { + int nid; + if (affinity_form == FORM0_AFFINITY) return; else if (affinity_form == FORM1_AFFINITY) { @@ -332,6 +359,84 @@ void update_numa_distance(struct device_node *node) initialize_form1_numa_distance(associativity); return; } + + /* FORM2 affinity */ + nid = of_node_to_nid_single(node); + if (nid == NUMA_NO_NODE) + return; + + /* + * With FORM2 we expect NUMA distance of all possible NUMA + * nodes to be provided during boot. + */ + WARN(numa_distance_table[nid][nid] == -1, + "NUMA distance details for node %d not provided\n", nid); +} + +/* + * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN} + * ibm,numa-distance-table = { N, 1, 2, 4, 5, 1, 6, .... N elements} + */ +static void initialize_form2_numa_distance_lookup_table(void) +{ + int i, j; + struct device_node *root; + const __u8 *numa_dist_table; + const __be32 *numa_lookup_index; + int numa_dist_table_length; + int max_numa_index, distance_index; + + if (firmware_has_feature(FW_FEATURE_OPAL)) + root = of_find_node_by_path("/ibm,opal"); + else + root = of_find_node_by_path("/rtas"); + if (!root) + root = of_find_node_by_path("/"); + + numa_lookup_index = of_get_property(root, "ibm,numa-lookup-index-table", NULL); + max_numa_index = of_read_number(&numa_lookup_index[0], 1); + + /* first element of the array is the size and is encode-int */ + numa_dist_table = of_get_property(root, "ibm,numa-distance-table", NULL); + numa_dist_table_length = of_read_number((const __be32 *)&numa_dist_table[0], 1); + /* Skip the size which is encoded int */ + numa_dist_table += sizeof(__be32); + + pr_debug("numa_dist_table_len = %d, numa_dist_indexes_len = %d\n", + numa_dist_table_length, max_numa_index); + + for (i = 0; i < max_numa_index; i++) + /* +1 skip the max_numa_index in the property */ + numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1); + + + if (numa_dist_table_length != max_numa_index * max_numa_index) { + WARN(1, "Wrong NUMA distance information\n"); + /* consider everybody else just remote. */ + for (i = 0; i < max_numa_index; i++) { + for (j = 0; j < max_numa_index; j++) { + int nodeA = numa_id_index_table[i]; + int nodeB = numa_id_index_table[j]; + + if (nodeA == nodeB) + numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE; + else + numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE; + } + } + } + + distance_index = 0; + for (i = 0; i < max_numa_index; i++) { + for (j = 0; j < max_numa_index; j++) { + int nodeA = numa_id_index_table[i]; + int nodeB = numa_id_index_table[j]; + + numa_distance_table[nodeA][nodeB] = numa_dist_table[distance_index++]; + pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, numa_distance_table[nodeA][nodeB]); + } + } + of_node_put(root); } static int __init find_primary_domain_index(void) @@ -344,6 +449,9 @@ static int __init find_primary_domain_index(void) */ if (firmware_has_feature(FW_FEATURE_OPAL)) { affinity_form = FORM1_AFFINITY; + } else if (firmware_has_feature(FW_FEATURE_FORM2_AFFINITY)) { + dbg("Using form 2 affinity\n"); + affinity_form = FORM2_AFFINITY; } else if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY)) { dbg("Using form 1 affinity\n"); affinity_form = FORM1_AFFINITY; @@ -388,9 +496,12 @@ static int __init find_primary_domain_index(void) index = of_read_number(&distance_ref_points[1], 1); } else { + /* + * Both FORM1 and FORM2 affinity find the primary domain details + * at the same offset. + */ index = of_read_number(distance_ref_points, 1); } - /* * Warn and cap if the hardware supports more than * MAX_DISTANCE_REF_POINTS domains. @@ -819,6 +930,12 @@ static int __init parse_numa_properties(void) dbg("NUMA associativity depth for CPU/Memory: %d\n", primary_domain_index); + /* + * If it is FORM2 initialize the distance table here. + */ + if (affinity_form == FORM2_AFFINITY) + initialize_form2_numa_distance_lookup_table(); + /* * Even though we connect cpus to numa domains later in SMP * init, we need to know the node ids now. This is because diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 5d4c2bc20bba..f162156b7b68 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -123,6 +123,7 @@ vec5_fw_features_table[] = { {FW_FEATURE_PRRN, OV5_PRRN}, {FW_FEATURE_DRMEM_V2, OV5_DRMEM_V2}, {FW_FEATURE_DRC_INFO, OV5_DRC_INFO}, + {FW_FEATURE_FORM2_AFFINITY, OV5_FORM2_AFFINITY}, }; static void __init fw_vec5_feature_init(const char *vec5, unsigned long len) From ccbec01cc99ce0d3a6851a5cea2fa1c05e536236 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 4 Apr 2023 09:44:33 +0530 Subject: [PATCH 2561/4345] powerpc/papr_scm: Update the NUMA distance table for the target node [ Upstream commit b277fc793daf258877b4c0744b52f69d6e6ba22e ] Platform device helper routines won't update the NUMA distance table while creating a platform device, even if the device is present on a NUMA node that doesn't have memory or CPU. This is especially true for pmem devices. If the target node of the pmem device is not online, we find the nearest online node to the device and associate the pmem device with that online node. To find the nearest online node, we should have the numa distance table updated correctly. Update the distance information during the device probe. For a papr scm device on NUMA node 3 distance_lookup_table value for distance_ref_points_depth = 2 before and after fix is below: Before fix: node 3 distance depth 0 - 0 node 3 distance depth 1 - 0 node 4 distance depth 0 - 4 node 4 distance depth 1 - 2 node 5 distance depth 0 - 5 node 5 distance depth 1 - 1 After fix node 3 distance depth 0 - 3 node 3 distance depth 1 - 1 node 4 distance depth 0 - 4 node 4 distance depth 1 - 2 node 5 distance depth 0 - 5 node 5 distance depth 1 - 1 Without the fix, the nearest numa node to the pmem device (NUMA node 3) will be picked as 4. After the fix, we get the correct numa node which is 5. Fixes: da1115fdbd6e ("powerpc/nvdimm: Pick nearby online node if the device node is not online") Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://msgid.link/20230404041433.1781804-1-aneesh.kumar@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/mm/numa.c | 1 + arch/powerpc/platforms/pseries/papr_scm.c | 7 +++++++ 2 files changed, 8 insertions(+) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index cfc170935a58..ce8569e16f0c 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -372,6 +372,7 @@ void update_numa_distance(struct device_node *node) WARN(numa_distance_table[nid][nid] == -1, "NUMA distance details for node %d not provided\n", nid); } +EXPORT_SYMBOL_GPL(update_numa_distance); /* * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN} diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 057acbb9116d..e3b7698b4762 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -1079,6 +1079,13 @@ static int papr_scm_probe(struct platform_device *pdev) return -ENODEV; } + /* + * open firmware platform device create won't update the NUMA + * distance table. For PAPR SCM devices we use numa_map_to_online_node() + * to find the nearest online NUMA node and that requires correct + * distance table information. + */ + update_numa_distance(dn); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) From 68387ae3b63e7bd1723767ce1bc2186e82490208 Mon Sep 17 00:00:00 2001 From: zgpeng Date: Wed, 6 Apr 2022 17:57:05 +0800 Subject: [PATCH 2562/4345] sched/fair: Move calculate of avg_load to a better location [ Upstream commit 06354900787f25bf5be3c07a68e3cdbc5bf0fa69 ] In calculate_imbalance function, when the value of local->avg_load is greater than or equal to busiest->avg_load, the calculated sds->avg_load is not used. So this calculation can be placed in a more appropriate position. Signed-off-by: zgpeng Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Samuel Liao Reviewed-by: Vincent Guittot Link: https://lore.kernel.org/r/1649239025-10010-1-git-send-email-zgpeng@tencent.com Stable-dep-of: 91dcf1e8068e ("sched/fair: Fix imbalance overflow") Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bb70a7856277..22139e97b2a8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9342,8 +9342,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s local->avg_load = (local->group_load * SCHED_CAPACITY_SCALE) / local->group_capacity; - sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) / - sds->total_capacity; /* * If the local group is more loaded than the selected * busiest group don't try to pull any tasks. @@ -9352,6 +9350,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s env->imbalance = 0; return; } + + sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) / + sds->total_capacity; } /* From ba4a2f6d99fcfce62f7f768d9cfe1c839079191b Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Tue, 11 Apr 2023 11:06:11 +0200 Subject: [PATCH 2563/4345] sched/fair: Fix imbalance overflow [ Upstream commit 91dcf1e8068e9a8823e419a7a34ff4341275fb70 ] When local group is fully busy but its average load is above system load, computing the imbalance will overflow and local group is not the best target for pulling this load. Fixes: 0b0695f2b34a ("sched/fair: Rework load_balance()") Reported-by: Tingjia Cao Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Tested-by: Tingjia Cao Link: https://lore.kernel.org/lkml/CABcWv9_DAhVBOq2=W=2ypKE9dKM5s2DvoV8-U0+GDwwuKZ89jQ@mail.gmail.com/T/ Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 22139e97b2a8..57a58bc48021 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9353,6 +9353,16 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) / sds->total_capacity; + + /* + * If the local group is more loaded than the average system + * load, don't try to pull any tasks. + */ + if (local->avg_load >= sds->avg_load) { + env->imbalance = 0; + return; + } + } /* From b4210b10dc7ed1439c45c0f840a16d9542868c53 Mon Sep 17 00:00:00 2001 From: Matija Glavinic Pecotic Date: Thu, 6 Apr 2023 08:26:52 +0200 Subject: [PATCH 2564/4345] x86/rtc: Remove __init for runtime functions [ Upstream commit 775d3c514c5b2763a50ab7839026d7561795924d ] set_rtc_noop(), get_rtc_noop() are after booting, therefore their __init annotation is wrong. A crash was observed on an x86 platform where CMOS RTC is unused and disabled via device tree. set_rtc_noop() was invoked from ntp: sync_hw_clock(), although CONFIG_RTC_SYSTOHC=n, however sync_cmos_clock() doesn't honour that. Workqueue: events_power_efficient sync_hw_clock RIP: 0010:set_rtc_noop Call Trace: update_persistent_clock64 sync_hw_clock Fix this by dropping the __init annotation from set/get_rtc_noop(). Fixes: c311ed6183f4 ("x86/init: Allow DT configured systems to disable RTC at boot time") Signed-off-by: Matija Glavinic Pecotic Signed-off-by: Thomas Gleixner Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/59f7ceb1-446b-1d3d-0bc8-1f0ee94b1e18@nokia.com Signed-off-by: Sasha Levin --- arch/x86/kernel/x86_init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a3038d8deb6a..b758eeea6090 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -32,8 +32,8 @@ static int __init iommu_init_noop(void) { return 0; } static void iommu_shutdown_noop(void) { } bool __init bool_x86_init_noop(void) { return false; } void x86_op_int_noop(int cpu) { } -static __init int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } -static __init void get_rtc_noop(struct timespec64 *now) { } +static int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } +static void get_rtc_noop(struct timespec64 *now) { } static __initconst const struct of_device_id of_cmos_match[] = { { .compatible = "motorola,mc146818" }, From 10b7a33c5de3c3de27d497060d0a8b5da5b69546 Mon Sep 17 00:00:00 2001 From: Gregor Herburger Date: Thu, 13 Apr 2023 11:37:37 +0200 Subject: [PATCH 2565/4345] i2c: ocores: generate stop condition after timeout in polling mode [ Upstream commit f8160d3b35fc94491bb0cb974dbda310ef96c0e2 ] In polling mode, no stop condition is generated after a timeout. This causes SCL to remain low and thereby block the bus. If this happens during a transfer it can cause slaves to misinterpret the subsequent transfer and return wrong values. To solve this, pass the ETIMEDOUT error up from ocores_process_polling() instead of setting STATE_ERROR directly. The caller is adjusted to call ocores_process_timeout() on error both in polling and in IRQ mode, which will set STATE_ERROR and generate a stop condition. Fixes: 69c8c0c0efa8 ("i2c: ocores: add polling interface") Signed-off-by: Gregor Herburger Signed-off-by: Matthias Schiffer Acked-by: Peter Korsgaard Reviewed-by: Andrew Lunn Reviewed-by: Federico Vaga Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-ocores.c | 35 ++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 16 deletions(-) diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index f5fc75b65a19..71e26aa6bd8f 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -343,18 +343,18 @@ static int ocores_poll_wait(struct ocores_i2c *i2c) * ocores_isr(), we just add our polling code around it. * * It can run in atomic context + * + * Return: 0 on success, -ETIMEDOUT on timeout */ -static void ocores_process_polling(struct ocores_i2c *i2c) +static int ocores_process_polling(struct ocores_i2c *i2c) { - while (1) { - irqreturn_t ret; - int err; + irqreturn_t ret; + int err = 0; + while (1) { err = ocores_poll_wait(i2c); - if (err) { - i2c->state = STATE_ERROR; + if (err) break; /* timeout */ - } ret = ocores_isr(-1, i2c); if (ret == IRQ_NONE) @@ -365,13 +365,15 @@ static void ocores_process_polling(struct ocores_i2c *i2c) break; } } + + return err; } static int ocores_xfer_core(struct ocores_i2c *i2c, struct i2c_msg *msgs, int num, bool polling) { - int ret; + int ret = 0; u8 ctrl; ctrl = oc_getreg(i2c, OCI2C_CONTROL); @@ -389,15 +391,16 @@ static int ocores_xfer_core(struct ocores_i2c *i2c, oc_setreg(i2c, OCI2C_CMD, OCI2C_CMD_START); if (polling) { - ocores_process_polling(i2c); + ret = ocores_process_polling(i2c); } else { - ret = wait_event_timeout(i2c->wait, - (i2c->state == STATE_ERROR) || - (i2c->state == STATE_DONE), HZ); - if (ret == 0) { - ocores_process_timeout(i2c); - return -ETIMEDOUT; - } + if (wait_event_timeout(i2c->wait, + (i2c->state == STATE_ERROR) || + (i2c->state == STATE_DONE), HZ) == 0) + ret = -ETIMEDOUT; + } + if (ret) { + ocores_process_timeout(i2c); + return ret; } return (i2c->state == STATE_DONE) ? num : -EIO; From 7b78445bce52ec0345cb7da1a9beaf47ffa8e9ea Mon Sep 17 00:00:00 2001 From: George Cherian Date: Thu, 9 Feb 2023 02:11:17 +0000 Subject: [PATCH 2566/4345] watchdog: sbsa_wdog: Make sure the timeout programming is within the limits commit 000987a38b53c172f435142a4026dd71378ca464 upstream. Make sure to honour the max_hw_heartbeat_ms while programming the timeout value to WOR. Clamp the timeout passed to sbsa_gwdt_set_timeout() to make sure the programmed value is within the permissible range. Fixes: abd3ac7902fb ("watchdog: sbsa: Support architecture version 1") Signed-off-by: George Cherian Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230209021117.1512097-1-george.cherian@marvell.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Signed-off-by: Tyler Hicks (Microsoft) Signed-off-by: Greg Kroah-Hartman --- drivers/watchdog/sbsa_gwdt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c index f0f1e3b2e463..4cbe6ba52754 100644 --- a/drivers/watchdog/sbsa_gwdt.c +++ b/drivers/watchdog/sbsa_gwdt.c @@ -121,6 +121,7 @@ static int sbsa_gwdt_set_timeout(struct watchdog_device *wdd, struct sbsa_gwdt *gwdt = watchdog_get_drvdata(wdd); wdd->timeout = timeout; + timeout = clamp_t(unsigned int, timeout, 1, wdd->max_hw_heartbeat_ms / 1000); if (action) writel(gwdt->clk * timeout, From 6facabb4d0695ca7d4a2ebab6db460be388c9dc8 Mon Sep 17 00:00:00 2001 From: Steve Clevenger Date: Mon, 27 Feb 2023 16:54:32 -0700 Subject: [PATCH 2567/4345] coresight-etm4: Fix for() loop drvdata->nr_addr_cmp range bug commit bf84937e882009075f57fd213836256fc65d96bc upstream. In etm4_enable_hw, fix for() loop range to represent address comparator pairs. Fixes: 2e1cdfe184b5 ("coresight-etm4x: Adding CoreSight ETM4x driver") Cc: stable@vger.kernel.org Signed-off-by: Steve Clevenger Reviewed-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/4a4ee61ce8ef402615a4528b21a051de3444fb7b.1677540079.git.scclevenger@os.amperecomputing.com Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etm4x-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 99df453575f5..059c09a925cc 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -179,7 +179,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) writel_relaxed(config->ss_pe_cmp[i], drvdata->base + TRCSSPCICRn(i)); } - for (i = 0; i < drvdata->nr_addr_cmp; i++) { + for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { writeq_relaxed(config->addr_val[i], drvdata->base + TRCACVRn(i)); writeq_relaxed(config->addr_acc[i], From 83f55e6f298e9e79a38b92d771179090ff0ac771 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 28 Mar 2023 17:08:29 -0700 Subject: [PATCH 2568/4345] kbuild: check the minimum assembler version in Kconfig commit ba64beb17493a4bfec563100c86a462a15926f24 upstream. Documentation/process/changes.rst defines the minimum assembler version (binutils version), but we have never checked it in the build time. Kbuild never invokes 'as' directly because all assembly files in the kernel tree are *.S, hence must be preprocessed. I do not expect raw assembly source files (*.s) would be added to the kernel tree. Therefore, we always use $(CC) as the assembler driver, and commit aa824e0c962b ("kbuild: remove AS variable") removed 'AS'. However, we are still interested in the version of the assembler acting behind. As usual, the --version option prints the version string. $ as --version | head -n 1 GNU assembler (GNU Binutils for Ubuntu) 2.35.1 But, we do not have $(AS). So, we can add the -Wa prefix so that $(CC) passes --version down to the backing assembler. $ gcc -Wa,--version | head -n 1 gcc: fatal error: no input files compilation terminated. OK, we need to input something to satisfy gcc. $ gcc -Wa,--version -c -x assembler /dev/null -o /dev/null | head -n 1 GNU assembler (GNU Binutils for Ubuntu) 2.35.1 The combination of Clang and GNU assembler works in the same way: $ clang -no-integrated-as -Wa,--version -c -x assembler /dev/null -o /dev/null | head -n 1 GNU assembler (GNU Binutils for Ubuntu) 2.35.1 Clang with the integrated assembler fails like this: $ clang -integrated-as -Wa,--version -c -x assembler /dev/null -o /dev/null | head -n 1 clang: error: unsupported argument '--version' to option 'Wa,' For the last case, checking the error message is fragile. If the proposal for -Wa,--version support [1] is accepted, this may not be even an error in the future. One easy way is to check if -integrated-as is present in the passed arguments. We did not pass -integrated-as to CLANG_FLAGS before, but we can make it explicit. Nathan pointed out -integrated-as is the default for all of the architectures/targets that the kernel cares about, but it goes along with "explicit is better than implicit" policy. [2] With all this in my mind, I implemented scripts/as-version.sh to check the assembler version in Kconfig time. $ scripts/as-version.sh gcc GNU 23501 $ scripts/as-version.sh clang -no-integrated-as GNU 23501 $ scripts/as-version.sh clang -integrated-as LLVM 0 [1]: https://github.com/ClangBuiltLinux/linux/issues/1320 [2]: https://lore.kernel.org/linux-kbuild/20210307044253.v3h47ucq6ng25iay@archlinux-ax161/ Signed-off-by: Masahiro Yamada Reviewed-by: Nathan Chancellor [nathan: Backport to 5.10. Drop minimum version checking, as it is not required in 5.10] Signed-off-by: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- Makefile | 4 ++- init/Kconfig | 12 +++++++ scripts/Kconfig.include | 6 ++++ scripts/as-version.sh | 69 +++++++++++++++++++++++++++++++++++++++++ scripts/dummy-tools/gcc | 6 ++++ 5 files changed, 96 insertions(+), 1 deletion(-) create mode 100755 scripts/as-version.sh diff --git a/Makefile b/Makefile index ae202cc53158..32d1e6e2f755 100644 --- a/Makefile +++ b/Makefile @@ -580,7 +580,9 @@ endif ifneq ($(GCC_TOOLCHAIN),) CLANG_FLAGS += --gcc-toolchain=$(GCC_TOOLCHAIN) endif -ifneq ($(LLVM_IAS),1) +ifeq ($(LLVM_IAS),1) +CLANG_FLAGS += -integrated-as +else CLANG_FLAGS += -no-integrated-as endif CLANG_FLAGS += -Werror=unknown-warning-option diff --git a/init/Kconfig b/init/Kconfig index eba883d6d9ed..9807c66b24bb 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -47,6 +47,18 @@ config CLANG_VERSION int default $(shell,$(srctree)/scripts/clang-version.sh $(CC)) +config AS_IS_GNU + def_bool $(success,test "$(as-name)" = GNU) + +config AS_IS_LLVM + def_bool $(success,test "$(as-name)" = LLVM) + +config AS_VERSION + int + # Use clang version if this is the integrated assembler + default CLANG_VERSION if AS_IS_LLVM + default $(as-version) + config LLD_VERSION int default $(shell,$(srctree)/scripts/lld-version.sh $(LD)) diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index a5fe72c504ff..6d37cb780452 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -42,6 +42,12 @@ $(error-if,$(failure,command -v $(LD)),linker '$(LD)' not found) # Fail if the linker is gold as it's not capable of linking the kernel proper $(error-if,$(success, $(LD) -v | grep -q gold), gold linker '$(LD)' not supported) +# Get the assembler name, version, and error out if it is not supported. +as-info := $(shell,$(srctree)/scripts/as-version.sh $(CC) $(CLANG_FLAGS)) +$(error-if,$(success,test -z "$(as-info)"),Sorry$(comma) this assembler is not supported.) +as-name := $(shell,set -- $(as-info) && echo $1) +as-version := $(shell,set -- $(as-info) && echo $2) + # machine bit flags # $(m32-flag): -m32 if the compiler supports it, or an empty string otherwise. # $(m64-flag): -m64 if the compiler supports it, or an empty string otherwise. diff --git a/scripts/as-version.sh b/scripts/as-version.sh new file mode 100755 index 000000000000..851dcb8a0e68 --- /dev/null +++ b/scripts/as-version.sh @@ -0,0 +1,69 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-only +# +# Print the assembler name and its version in a 5 or 6-digit form. +# Also, perform the minimum version check. +# (If it is the integrated assembler, return 0 as the version, and +# skip the version check.) + +set -e + +# Convert the version string x.y.z to a canonical 5 or 6-digit form. +get_canonical_version() +{ + IFS=. + set -- $1 + + # If the 2nd or 3rd field is missing, fill it with a zero. + # + # The 4th field, if present, is ignored. + # This occurs in development snapshots as in 2.35.1.20201116 + echo $((10000 * $1 + 100 * ${2:-0} + ${3:-0})) +} + +# Clang fails to handle -Wa,--version unless -no-integrated-as is given. +# We check -(f)integrated-as, expecting it is explicitly passed in for the +# integrated assembler case. +check_integrated_as() +{ + while [ $# -gt 0 ]; do + if [ "$1" = -integrated-as -o "$1" = -fintegrated-as ]; then + # For the intergrated assembler, we do not check the + # version here. It is the same as the clang version, and + # it has been already checked by scripts/cc-version.sh. + echo LLVM 0 + exit 0 + fi + shift + done +} + +check_integrated_as "$@" + +orig_args="$@" + +# Get the first line of the --version output. +IFS=' +' +set -- $(LC_ALL=C "$@" -Wa,--version -c -x assembler /dev/null -o /dev/null 2>/dev/null) + +# Split the line on spaces. +IFS=' ' +set -- $1 + +if [ "$1" = GNU -a "$2" = assembler ]; then + shift $(($# - 1)) + version=$1 + name=GNU +else + echo "$orig_args: unknown assembler invoked" >&2 + exit 1 +fi + +# Some distributions append a package release number, as in 2.34-4.fc32 +# Trim the hyphen and any characters that follow. +version=${version%-*} + +cversion=$(get_canonical_version $version) + +echo $name $cversion diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc index 346757a87dbc..485427f40dba 100755 --- a/scripts/dummy-tools/gcc +++ b/scripts/dummy-tools/gcc @@ -67,6 +67,12 @@ if arg_contain -E "$@"; then fi fi +# To set CONFIG_AS_IS_GNU +if arg_contain -Wa,--version "$@"; then + echo "GNU assembler (scripts/dummy-tools) 2.50" + exit 0 +fi + if arg_contain -S "$@"; then # For scripts/gcc-x86-*-has-stack-protector.sh if arg_contain -fstack-protector "$@"; then From d5f67f6d4ec4aaf8bcef95c35a70d7e537239cb1 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 28 Mar 2023 17:08:30 -0700 Subject: [PATCH 2569/4345] kbuild: Switch to 'f' variants of integrated assembler flag commit 2185a7e4b0ade86c2c57fc63d4a7535c40254bd0 upstream. It has been brought up a few times in various code reviews that clang 3.5 introduced -f{,no-}integrated-as as the preferred way to enable and disable the integrated assembler, mentioning that -{no-,}integrated-as are now considered legacy flags. Switch the kernel over to using those variants in case there is ever a time where clang decides to remove the non-'f' variants of the flag. Also, fix a typo in a comment ("intergrated" -> "integrated"). Link: https://releases.llvm.org/3.5.0/tools/clang/docs/ReleaseNotes.html#new-compiler-flags Reviewed-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Signed-off-by: Masahiro Yamada [nathan: Backport to 5.10] Signed-off-by: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- Makefile | 4 ++-- scripts/as-version.sh | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/Makefile b/Makefile index 32d1e6e2f755..a9cabe5b9dfd 100644 --- a/Makefile +++ b/Makefile @@ -581,9 +581,9 @@ ifneq ($(GCC_TOOLCHAIN),) CLANG_FLAGS += --gcc-toolchain=$(GCC_TOOLCHAIN) endif ifeq ($(LLVM_IAS),1) -CLANG_FLAGS += -integrated-as +CLANG_FLAGS += -fintegrated-as else -CLANG_FLAGS += -no-integrated-as +CLANG_FLAGS += -fno-integrated-as endif CLANG_FLAGS += -Werror=unknown-warning-option KBUILD_CFLAGS += $(CLANG_FLAGS) diff --git a/scripts/as-version.sh b/scripts/as-version.sh index 851dcb8a0e68..532270bd4b7e 100755 --- a/scripts/as-version.sh +++ b/scripts/as-version.sh @@ -21,14 +21,14 @@ get_canonical_version() echo $((10000 * $1 + 100 * ${2:-0} + ${3:-0})) } -# Clang fails to handle -Wa,--version unless -no-integrated-as is given. -# We check -(f)integrated-as, expecting it is explicitly passed in for the +# Clang fails to handle -Wa,--version unless -fno-integrated-as is given. +# We check -fintegrated-as, expecting it is explicitly passed in for the # integrated assembler case. check_integrated_as() { while [ $# -gt 0 ]; do - if [ "$1" = -integrated-as -o "$1" = -fintegrated-as ]; then - # For the intergrated assembler, we do not check the + if [ "$1" = -fintegrated-as ]; then + # For the integrated assembler, we do not check the # version here. It is the same as the clang version, and # it has been already checked by scripts/cc-version.sh. echo LLVM 0 From c36a251011793e1c86ab7c7a0e79ce6794a9bd2c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 28 Mar 2023 17:08:31 -0700 Subject: [PATCH 2570/4345] kbuild: check CONFIG_AS_IS_LLVM instead of LLVM_IAS commit 52cc02b910284d6bddba46cce402044ab775f314 upstream. LLVM_IAS is the user interface to set the -(no-)integrated-as flag, and it should be used only for that purpose. LLVM_IAS is checked in some places to determine the assembler type, but it is not precise. For example, $ make CC=gcc LLVM_IAS=1 ... will use the GNU assembler (i.e. binutils) since LLVM_IAS=1 is effective only when $(CC) is clang. Of course, 'CC=gcc LLVM_IAS=1' is an odd combination, but the build system can be more robust against such insane input. Commit ba64beb17493a ("kbuild: check the minimum assembler version in Kconfig") introduced CONFIG_AS_IS_GNU/LLVM, which is more precise because Kconfig checks the version string from the assembler in use. Signed-off-by: Masahiro Yamada Reviewed-by: Nick Desaulniers Reviewed-by: Nathan Chancellor [nathan: Backport to 5.10] Signed-off-by: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- arch/riscv/Makefile | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index a9cabe5b9dfd..ee1fe4842e10 100644 --- a/Makefile +++ b/Makefile @@ -851,7 +851,7 @@ else DEBUG_CFLAGS += -g endif -ifeq ($(LLVM_IAS),1) +ifdef CONFIG_AS_IS_LLVM KBUILD_AFLAGS += -g else KBUILD_AFLAGS += -Wa,-gdwarf-2 diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 9446282b52ba..14cdeaa2bb32 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -40,7 +40,7 @@ ifeq ($(CONFIG_LD_IS_LLD),y) ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 150000; echo $$?),0) KBUILD_CFLAGS += -mno-relax KBUILD_AFLAGS += -mno-relax -ifneq ($(LLVM_IAS),1) +ifndef CONFIG_AS_IS_LLVM KBUILD_CFLAGS += -Wa,-mno-relax KBUILD_AFLAGS += -Wa,-mno-relax endif From 0b077b22ea9ff698840ff9305d9382935fb41540 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 28 Mar 2023 17:08:32 -0700 Subject: [PATCH 2571/4345] riscv: Handle zicsr/zifencei issues between clang and binutils commit e89c2e815e76471cb507bd95728bf26da7976430 upstream. There are two related issues that appear in certain combinations with clang and GNU binutils. The first occurs when a version of clang that supports zicsr or zifencei via '-march=' [1] (i.e, >= 17.x) is used in combination with a version of GNU binutils that do not recognize zicsr and zifencei in the '-march=' value (i.e., < 2.36): riscv64-linux-gnu-ld: -march=rv64i2p0_m2p0_a2p0_c2p0_zicsr2p0_zifencei2p0: Invalid or unknown z ISA extension: 'zifencei' riscv64-linux-gnu-ld: failed to merge target specific data of file fs/efivarfs/file.o riscv64-linux-gnu-ld: -march=rv64i2p0_m2p0_a2p0_c2p0_zicsr2p0_zifencei2p0: Invalid or unknown z ISA extension: 'zifencei' riscv64-linux-gnu-ld: failed to merge target specific data of file fs/efivarfs/super.o The second occurs when a version of clang that does not support zicsr or zifencei via '-march=' (i.e., <= 16.x) is used in combination with a version of GNU as that defaults to a newer ISA base spec, which requires specifying zicsr and zifencei in the '-march=' value explicitly (i.e, >= 2.38): ../arch/riscv/kernel/kexec_relocate.S: Assembler messages: ../arch/riscv/kernel/kexec_relocate.S:147: Error: unrecognized opcode `fence.i', extension `zifencei' required clang-12: error: assembler command failed with exit code 1 (use -v to see invocation) This is the same issue addressed by commit 6df2a016c0c8 ("riscv: fix build with binutils 2.38") (see [2] for additional information) but older versions of clang miss out on it because the cc-option check fails: clang-12: error: invalid arch name 'rv64imac_zicsr_zifencei', unsupported standard user-level extension 'zicsr' clang-12: error: invalid arch name 'rv64imac_zicsr_zifencei', unsupported standard user-level extension 'zicsr' To resolve the first issue, only attempt to add zicsr and zifencei to the march string when using the GNU assembler 2.38 or newer, which is when the default ISA spec was updated, requiring these extensions to be specified explicitly. LLVM implements an older version of the base specification for all currently released versions, so these instructions are available as part of the 'i' extension. If LLVM's implementation is updated in the future, a CONFIG_AS_IS_LLVM condition can be added to CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI. To resolve the second issue, use version 2.2 of the base ISA spec when using an older version of clang that does not support zicsr or zifencei via '-march=', as that is the spec version most compatible with the one clang/LLVM implements and avoids the need to specify zicsr and zifencei explicitly due to still being a part of 'i'. [1]: https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e15bf8a16 [2]: https://lore.kernel.org/ZAxT7T9Xy1Fo3d5W@aurel32.net/ Cc: stable@vger.kernel.org Link: https://github.com/ClangBuiltLinux/linux/issues/1808 Co-developed-by: Conor Dooley Signed-off-by: Conor Dooley Signed-off-by: Nathan Chancellor Acked-by: Conor Dooley Link: https://lore.kernel.org/r/20230313-riscv-zicsr-zifencei-fiasco-v1-1-dd1b7840a551@kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman --- arch/riscv/Kconfig | 22 ++++++++++++++++++++++ arch/riscv/Makefile | 10 ++++++---- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 557c4a8c4087..c192bd7305dc 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -331,6 +331,28 @@ config RISCV_BASE_PMU endmenu +config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + def_bool y + # https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc + depends on AS_IS_GNU && AS_VERSION >= 23800 + help + Newer binutils versions default to ISA spec version 20191213 which + moves some instructions from the I extension to the Zicsr and Zifencei + extensions. + +config TOOLCHAIN_NEEDS_OLD_ISA_SPEC + def_bool y + depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + # https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e15bf8a16 + depends on CC_IS_CLANG && CLANG_VERSION < 170000 + help + Certain versions of clang do not support zicsr and zifencei via -march + but newer versions of binutils require it for the reasons noted in the + help text of CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI. This + option causes an older ISA spec compatible with these older versions + of clang to be passed to GAS, which has the same result as passing zicsr + and zifencei to -march. + config FPU bool "FPU support" default y diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 14cdeaa2bb32..daa679440000 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -53,10 +53,12 @@ riscv-march-$(CONFIG_ARCH_RV64I) := rv64ima riscv-march-$(CONFIG_FPU) := $(riscv-march-y)fd riscv-march-$(CONFIG_RISCV_ISA_C) := $(riscv-march-y)c -# Newer binutils versions default to ISA spec version 20191213 which moves some -# instructions from the I extension to the Zicsr and Zifencei extensions. -toolchain-need-zicsr-zifencei := $(call cc-option-yn, -march=$(riscv-march-y)_zicsr_zifencei) -riscv-march-$(toolchain-need-zicsr-zifencei) := $(riscv-march-y)_zicsr_zifencei +ifdef CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC +KBUILD_CFLAGS += -Wa,-misa-spec=2.2 +KBUILD_AFLAGS += -Wa,-misa-spec=2.2 +else +riscv-march-$(CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI) := $(riscv-march-y)_zicsr_zifencei +endif KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y)) KBUILD_AFLAGS += -march=$(riscv-march-y) From 784b6ba15eb27f3abb800dbfbc5706625f83b418 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Sep 2021 15:18:10 -0700 Subject: [PATCH 2572/4345] kexec: move locking into do_kexec_load commit 4b692e861619353ce069e547a67c8d0e32d9ef3d upstream. Patch series "compat: remove compat_alloc_user_space", v5. Going through compat_alloc_user_space() to convert indirect system call arguments tends to add complexity compared to handling the native and compat logic in the same code. This patch (of 6): The locking is the same between the native and compat version of sys_kexec_load(), so it can be done in the common implementation to reduce duplication. Link: https://lkml.kernel.org/r/20210727144859.4150043-1-arnd@kernel.org Link: https://lkml.kernel.org/r/20210727144859.4150043-2-arnd@kernel.org Signed-off-by: Arnd Bergmann Co-developed-by: Eric Biederman Co-developed-by: Christoph Hellwig Acked-by: "Eric W. Biederman" Cc: Catalin Marinas Cc: Will Deacon Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Al Viro Cc: Feng Tang Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Wen Yang Signed-off-by: Greg Kroah-Hartman --- kernel/kexec.c | 44 ++++++++++++++++---------------------------- 1 file changed, 16 insertions(+), 28 deletions(-) diff --git a/kernel/kexec.c b/kernel/kexec.c index c82c6c06f051..9c7aef8f4bb6 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -110,6 +110,17 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, unsigned long i; int ret; + /* + * Because we write directly to the reserved memory region when loading + * crash kernels we need a mutex here to prevent multiple crash kernels + * from attempting to load simultaneously, and to prevent a crash kernel + * from loading over the top of a in use crash kernel. + * + * KISS: always take the mutex. + */ + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + if (flags & KEXEC_ON_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) @@ -121,7 +132,8 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, if (nr_segments == 0) { /* Uninstall image */ kimage_free(xchg(dest_image, NULL)); - return 0; + ret = 0; + goto out_unlock; } if (flags & KEXEC_ON_CRASH) { /* @@ -134,7 +146,7 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, ret = kimage_alloc_init(&image, entry, nr_segments, segments, flags); if (ret) - return ret; + goto out_unlock; if (flags & KEXEC_PRESERVE_CONTEXT) image->preserve_context = 1; @@ -171,6 +183,8 @@ out: arch_kexec_protect_crashkres(); kimage_free(image); +out_unlock: + mutex_unlock(&kexec_mutex); return ret; } @@ -247,21 +261,8 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, ((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT)) return -EINVAL; - /* Because we write directly to the reserved memory - * region when loading crash kernels we need a mutex here to - * prevent multiple crash kernels from attempting to load - * simultaneously, and to prevent a crash kernel from loading - * over the top of a in use crash kernel. - * - * KISS: always take the mutex. - */ - if (!mutex_trylock(&kexec_mutex)) - return -EBUSY; - result = do_kexec_load(entry, nr_segments, segments, flags); - mutex_unlock(&kexec_mutex); - return result; } @@ -301,21 +302,8 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry, return -EFAULT; } - /* Because we write directly to the reserved memory - * region when loading crash kernels we need a mutex here to - * prevent multiple crash kernels from attempting to load - * simultaneously, and to prevent a crash kernel from loading - * over the top of a in use crash kernel. - * - * KISS: always take the mutex. - */ - if (!mutex_trylock(&kexec_mutex)) - return -EBUSY; - result = do_kexec_load(entry, nr_segments, ksegments, flags); - mutex_unlock(&kexec_mutex); - return result; } #endif From d425f348211ffb387587dc65113852767240d023 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 30 Jun 2022 23:32:57 +0100 Subject: [PATCH 2573/4345] kexec: turn all kexec_mutex acquisitions into trylocks commit 7bb5da0d490b2d836c5218f5186ee588d2145310 upstream. Patch series "kexec, panic: Making crash_kexec() NMI safe", v4. This patch (of 2): Most acquistions of kexec_mutex are done via mutex_trylock() - those were a direct "translation" from: 8c5a1cf0ad3a ("kexec: use a mutex for locking rather than xchg()") there have however been two additions since then that use mutex_lock(): crash_get_memory_size() and crash_shrink_memory(). A later commit will replace said mutex with an atomic variable, and locking operations will become atomic_cmpxchg(). Rather than having those mutex_lock() become while (atomic_cmpxchg(&lock, 0, 1)), turn them into trylocks that can return -EBUSY on acquisition failure. This does halve the printable size of the crash kernel, but that's still neighbouring 2G for 32bit kernels which should be ample enough. Link: https://lkml.kernel.org/r/20220630223258.4144112-1-vschneid@redhat.com Link: https://lkml.kernel.org/r/20220630223258.4144112-2-vschneid@redhat.com Signed-off-by: Valentin Schneider Cc: Arnd Bergmann Cc: "Eric W . Biederman" Cc: Juri Lelli Cc: Luis Claudio R. Goncalves Cc: Miaohe Lin Cc: Petr Mladek Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Wen Yang Signed-off-by: Greg Kroah-Hartman --- include/linux/kexec.h | 2 +- kernel/kexec_core.c | 12 ++++++++---- kernel/ksysfs.c | 7 ++++++- 3 files changed, 15 insertions(+), 6 deletions(-) diff --git a/include/linux/kexec.h b/include/linux/kexec.h index a1f12e959bba..3c1deba496c9 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -380,8 +380,8 @@ extern note_buf_t __percpu *crash_notes; extern bool kexec_in_progress; int crash_shrink_memory(unsigned long new_size); -size_t crash_get_memory_size(void); void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); +ssize_t crash_get_memory_size(void); void arch_kexec_protect_crashkres(void); void arch_kexec_unprotect_crashkres(void); diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index c589c7a9562c..e47870f30728 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -989,13 +989,16 @@ void crash_kexec(struct pt_regs *regs) } } -size_t crash_get_memory_size(void) +ssize_t crash_get_memory_size(void) { - size_t size = 0; + ssize_t size = 0; + + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; - mutex_lock(&kexec_mutex); if (crashk_res.end != crashk_res.start) size = resource_size(&crashk_res); + mutex_unlock(&kexec_mutex); return size; } @@ -1016,7 +1019,8 @@ int crash_shrink_memory(unsigned long new_size) unsigned long old_size; struct resource *ram_res; - mutex_lock(&kexec_mutex); + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; if (kexec_crash_image) { ret = -ENOENT; diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 35859da8bd4f..e20c19e3ba49 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -106,7 +106,12 @@ KERNEL_ATTR_RO(kexec_crash_loaded); static ssize_t kexec_crash_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%zu\n", crash_get_memory_size()); + ssize_t size = crash_get_memory_size(); + + if (size < 0) + return size; + + return sprintf(buf, "%zd\n", size); } static ssize_t kexec_crash_size_store(struct kobject *kobj, struct kobj_attribute *attr, From 56314b90fd43bd2444942bc14a7c5c768ce8ec57 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 30 Jun 2022 23:32:58 +0100 Subject: [PATCH 2574/4345] panic, kexec: make __crash_kexec() NMI safe commit 05c6257433b7212f07a7e53479a8ab038fc1666a upstream. Attempting to get a crash dump out of a debug PREEMPT_RT kernel via an NMI panic() doesn't work. The cause of that lies in the PREEMPT_RT definition of mutex_trylock(): if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task())) return 0; This prevents an nmi_panic() from executing the main body of __crash_kexec() which does the actual kexec into the kdump kernel. The warning and return are explained by: 6ce47fd961fa ("rtmutex: Warn if trylock is called from hard/softirq context") [...] The reasons for this are: 1) There is a potential deadlock in the slowpath 2) Another cpu which blocks on the rtmutex will boost the task which allegedly locked the rtmutex, but that cannot work because the hard/softirq context borrows the task context. Furthermore, grabbing the lock isn't NMI safe, so do away with kexec_mutex and replace it with an atomic variable. This is somewhat overzealous as *some* callsites could keep using a mutex (e.g. the sysfs-facing ones like crash_shrink_memory()), but this has the benefit of involving a single unified lock and preventing any future NMI-related surprises. Tested by triggering NMI panics via: $ echo 1 > /proc/sys/kernel/panic_on_unrecovered_nmi $ echo 1 > /proc/sys/kernel/unknown_nmi_panic $ echo 1 > /proc/sys/kernel/panic $ ipmitool power diag Link: https://lkml.kernel.org/r/20220630223258.4144112-3-vschneid@redhat.com Fixes: 6ce47fd961fa ("rtmutex: Warn if trylock is called from hard/softirq context") Signed-off-by: Valentin Schneider Cc: Arnd Bergmann Cc: Baoquan He Cc: "Eric W . Biederman" Cc: Juri Lelli Cc: Luis Claudio R. Goncalves Cc: Miaohe Lin Cc: Petr Mladek Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Wen Yang Signed-off-by: Greg Kroah-Hartman --- kernel/kexec.c | 11 ++++------- kernel/kexec_core.c | 20 ++++++++++---------- kernel/kexec_file.c | 4 ++-- kernel/kexec_internal.h | 15 ++++++++++++++- 4 files changed, 30 insertions(+), 20 deletions(-) diff --git a/kernel/kexec.c b/kernel/kexec.c index 9c7aef8f4bb6..f0f0c6555454 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -112,13 +112,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, /* * Because we write directly to the reserved memory region when loading - * crash kernels we need a mutex here to prevent multiple crash kernels - * from attempting to load simultaneously, and to prevent a crash kernel - * from loading over the top of a in use crash kernel. - * - * KISS: always take the mutex. + * crash kernels we need a serialization here to prevent multiple crash + * kernels from attempting to load simultaneously. */ - if (!mutex_trylock(&kexec_mutex)) + if (!kexec_trylock()) return -EBUSY; if (flags & KEXEC_ON_CRASH) { @@ -184,7 +181,7 @@ out: kimage_free(image); out_unlock: - mutex_unlock(&kexec_mutex); + kexec_unlock(); return ret; } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index e47870f30728..7a8104d48997 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -45,7 +45,7 @@ #include #include "kexec_internal.h" -DEFINE_MUTEX(kexec_mutex); +atomic_t __kexec_lock = ATOMIC_INIT(0); /* Per cpu memory for storing cpu states in case of system crash. */ note_buf_t __percpu *crash_notes; @@ -943,7 +943,7 @@ int kexec_load_disabled; */ void __noclone __crash_kexec(struct pt_regs *regs) { - /* Take the kexec_mutex here to prevent sys_kexec_load + /* Take the kexec_lock here to prevent sys_kexec_load * running on one cpu from replacing the crash kernel * we are using after a panic on a different cpu. * @@ -951,7 +951,7 @@ void __noclone __crash_kexec(struct pt_regs *regs) * of memory the xchg(&kexec_crash_image) would be * sufficient. But since I reuse the memory... */ - if (mutex_trylock(&kexec_mutex)) { + if (kexec_trylock()) { if (kexec_crash_image) { struct pt_regs fixed_regs; @@ -960,7 +960,7 @@ void __noclone __crash_kexec(struct pt_regs *regs) machine_crash_shutdown(&fixed_regs); machine_kexec(kexec_crash_image); } - mutex_unlock(&kexec_mutex); + kexec_unlock(); } } STACK_FRAME_NON_STANDARD(__crash_kexec); @@ -993,13 +993,13 @@ ssize_t crash_get_memory_size(void) { ssize_t size = 0; - if (!mutex_trylock(&kexec_mutex)) + if (!kexec_trylock()) return -EBUSY; if (crashk_res.end != crashk_res.start) size = resource_size(&crashk_res); - mutex_unlock(&kexec_mutex); + kexec_unlock(); return size; } @@ -1019,7 +1019,7 @@ int crash_shrink_memory(unsigned long new_size) unsigned long old_size; struct resource *ram_res; - if (!mutex_trylock(&kexec_mutex)) + if (!kexec_trylock()) return -EBUSY; if (kexec_crash_image) { @@ -1058,7 +1058,7 @@ int crash_shrink_memory(unsigned long new_size) insert_resource(&iomem_resource, ram_res); unlock: - mutex_unlock(&kexec_mutex); + kexec_unlock(); return ret; } @@ -1130,7 +1130,7 @@ int kernel_kexec(void) { int error = 0; - if (!mutex_trylock(&kexec_mutex)) + if (!kexec_trylock()) return -EBUSY; if (!kexec_image) { error = -EINVAL; @@ -1205,7 +1205,7 @@ int kernel_kexec(void) #endif Unlock: - mutex_unlock(&kexec_mutex); + kexec_unlock(); return error; } diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index fff11916aba3..b9c857782ada 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -343,7 +343,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, image = NULL; - if (!mutex_trylock(&kexec_mutex)) + if (!kexec_trylock()) return -EBUSY; dest_image = &kexec_image; @@ -415,7 +415,7 @@ out: if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image) arch_kexec_protect_crashkres(); - mutex_unlock(&kexec_mutex); + kexec_unlock(); kimage_free(image); return ret; } diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 39d30ccf8d87..49d4e3ab9c96 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -15,7 +15,20 @@ int kimage_is_destination_range(struct kimage *image, int machine_kexec_post_load(struct kimage *image); -extern struct mutex kexec_mutex; +/* + * Whatever is used to serialize accesses to the kexec_crash_image needs to be + * NMI safe, as __crash_kexec() can happen during nmi_panic(), so here we use a + * "simple" atomic variable that is acquired with a cmpxchg(). + */ +extern atomic_t __kexec_lock; +static inline bool kexec_trylock(void) +{ + return atomic_cmpxchg_acquire(&__kexec_lock, 0, 1) == 0; +} +static inline void kexec_unlock(void) +{ + atomic_set_release(&__kexec_lock, 0); +} #ifdef CONFIG_KEXEC_FILE #include From f177b382c33900d0e5a9766493c11a1074076f78 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 11 Jul 2022 17:15:19 -0700 Subject: [PATCH 2575/4345] sysctl: Fix data-races in proc_dou8vec_minmax(). commit 7dee5d7747a69aa2be41f04c6a7ecfe3ac8cdf18 upstream. A sysctl variable is accessed concurrently, and there is always a chance of data-race. So, all readers and writers need some basic protection to avoid load/store-tearing. This patch changes proc_dou8vec_minmax() to use READ_ONCE() and WRITE_ONCE() internally to fix data-races on the sysctl side. For now, proc_dou8vec_minmax() itself is tolerant to a data-race, but we still need to add annotations on the other subsystem's side. Fixes: cb9444130662 ("sysctl: add proc_dou8vec_minmax()") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- kernel/sysctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 43e907f4cac7..d981abea0358 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1109,13 +1109,13 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write, tmp.maxlen = sizeof(val); tmp.data = &val; - val = *data; + val = READ_ONCE(*data); res = do_proc_douintvec(&tmp, write, buffer, lenp, ppos, do_proc_douintvec_minmax_conv, ¶m); if (res) return res; if (write) - *data = val; + WRITE_ONCE(*data, val); return 0; } EXPORT_SYMBOL_GPL(proc_dou8vec_minmax); From 791a854ae5a5f5988f1291ae91168a149bd5ba57 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 20 Apr 2023 12:10:29 +0200 Subject: [PATCH 2576/4345] Linux 5.10.178 Link: https://lore.kernel.org/r/20230418120309.539243408@linuxfoundation.org Tested-by: Florian Fainelli Link: https://lore.kernel.org/r/20230419072207.996418578@linuxfoundation.org Tested-by: Chris Paterson (CIP) Tested-by: Jon Hunter Tested-by: Salvatore Bonaccorso Tested-by: Florian Fainelli Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index ee1fe4842e10..3bde04cc7f04 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 177 +SUBLEVEL = 178 EXTRAVERSION = NAME = Dare mighty things From 7b7cd1158649be7a6488bcecb0009ea6e8d54f98 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Sun, 20 Mar 2022 23:11:17 +0800 Subject: [PATCH 2577/4345] BACKPORT: f2fs: check pinfile in gc_data_segment() in advance In order to skip migrating section which contains data of pinned file in advance. Bug: 278486610 Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Chao Yu (cherry picked from commit 3c4b4e198e7723f00c0f3a078144173fd591d6d8) Change-Id: Ia5d0fa83376afd60cb9dec1ef2e377fedfd905f5 --- fs/f2fs/gc.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 63f7a7238442..00a69b555daf 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1476,6 +1476,13 @@ next_step: if (IS_ERR(inode) || is_bad_inode(inode)) continue; + if (is_inode_flag_set(inode, FI_PIN_FILE) && + gc_type == FG_GC) { + f2fs_pin_file_control(inode, true); + iput(inode); + return submitted; + } + if (!f2fs_down_write_trylock( &F2FS_I(inode)->i_gc_rwsem[WRITE])) { iput(inode); From 7771fe887f137d6a1340922ffe0ce65fa44cf8eb Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 6 May 2022 18:30:31 +0800 Subject: [PATCH 2578/4345] BACKPORT: f2fs: give priority to select unpinned section for foreground GC Previously, during foreground GC, if victims contain data of pinned file, it will fail migration of the data, and meanwhile i_gc_failures of that pinned file may increase, and when it exceeds threshold, GC will unpin the file, result in breaking pinfile's semantics. In order to mitigate such condition, let's record and skip section which has pinned file's data and give priority to select unpinned one. Bug: 278486610 Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Chao Yu (cherry picked from commit 8f84484a0696aa9be41e8e5c1f299f3b5788e5ad) Change-Id: I5477ba502254e3109c01e118301c99f6332c1da5 --- fs/f2fs/gc.c | 85 +++++++++++++++++++++++++++++++++++++++-------- fs/f2fs/segment.c | 8 +++++ fs/f2fs/segment.h | 3 ++ 3 files changed, 82 insertions(+), 14 deletions(-) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 00a69b555daf..71f969a8023f 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -627,6 +627,54 @@ static void release_victim_entry(struct f2fs_sb_info *sbi) f2fs_bug_on(sbi, !list_empty(&am->victim_list)); } +static bool f2fs_pin_section(struct f2fs_sb_info *sbi, unsigned int segno) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); + + if (!dirty_i->enable_pin_section) + return false; + if (!test_and_set_bit(secno, dirty_i->pinned_secmap)) + dirty_i->pinned_secmap_cnt++; + return true; +} + +static bool f2fs_pinned_section_exists(struct dirty_seglist_info *dirty_i) +{ + return dirty_i->pinned_secmap_cnt; +} + +static bool f2fs_section_is_pinned(struct dirty_seglist_info *dirty_i, + unsigned int secno) +{ + return dirty_i->enable_pin_section && + f2fs_pinned_section_exists(dirty_i) && + test_bit(secno, dirty_i->pinned_secmap); +} + +static void f2fs_unpin_all_sections(struct f2fs_sb_info *sbi, bool enable) +{ + unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); + + if (f2fs_pinned_section_exists(DIRTY_I(sbi))) { + memset(DIRTY_I(sbi)->pinned_secmap, 0, bitmap_size); + DIRTY_I(sbi)->pinned_secmap_cnt = 0; + } + DIRTY_I(sbi)->enable_pin_section = enable; +} + +static int f2fs_gc_pinned_control(struct inode *inode, int gc_type, + unsigned int segno) +{ + if (!f2fs_is_pinned_file(inode)) + return 0; + if (gc_type != FG_GC) + return -EBUSY; + if (!f2fs_pin_section(F2FS_I_SB(inode), segno)) + f2fs_pin_file_control(inode, true); + return -EAGAIN; +} + /* * This function is called from two paths. * One is garbage collection and the other is SSR segment selection. @@ -768,6 +816,9 @@ retry: if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) goto next; + if (gc_type == FG_GC && f2fs_section_is_pinned(dirty_i, secno)) + goto next; + if (is_atgc) { add_victim_entry(sbi, &p, segno); goto next; @@ -1196,12 +1247,9 @@ static int move_data_block(struct inode *inode, block_t bidx, goto out; } - if (f2fs_is_pinned_file(inode)) { - if (gc_type == FG_GC) - f2fs_pin_file_control(inode, true); - err = -EAGAIN; + err = f2fs_gc_pinned_control(inode, gc_type, segno); + if (err) goto out; - } set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_get_dnode_of_data(&dn, bidx, LOOKUP_NODE); @@ -1346,12 +1394,9 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type, err = -EAGAIN; goto out; } - if (f2fs_is_pinned_file(inode)) { - if (gc_type == FG_GC) - f2fs_pin_file_control(inode, true); - err = -EAGAIN; + err = f2fs_gc_pinned_control(inode, gc_type, segno); + if (err) goto out; - } if (gc_type == BG_GC) { if (PageWriteback(page)) { @@ -1472,13 +1517,14 @@ next_step: ofs_in_node = le16_to_cpu(entry->ofs_in_node); if (phase == 3) { + int err; + inode = f2fs_iget(sb, dni.ino); if (IS_ERR(inode) || is_bad_inode(inode)) continue; - if (is_inode_flag_set(inode, FI_PIN_FILE) && - gc_type == FG_GC) { - f2fs_pin_file_control(inode, true); + err = f2fs_gc_pinned_control(inode, gc_type, segno); + if (err == -EAGAIN) { iput(inode); return submitted; } @@ -1763,9 +1809,17 @@ gc_more: ret = -EINVAL; goto stop; } +retry: ret = __get_victim(sbi, &segno, gc_type); - if (ret) + if (ret) { + /* allow to search victim from sections has pinned data */ + if (ret == -ENODATA && gc_type == FG_GC && + f2fs_pinned_section_exists(DIRTY_I(sbi))) { + f2fs_unpin_all_sections(sbi, false); + goto retry; + } goto stop; + } seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type, force); if (gc_type == FG_GC && @@ -1816,6 +1870,9 @@ stop: SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0; SIT_I(sbi)->last_victim[FLUSH_DEVICE] = init_segno; + if (gc_type == FG_GC) + f2fs_unpin_all_sections(sbi, true); + trace_f2fs_gc_end(sbi->sb, ret, total_freed, sec_freed, get_pages(sbi, F2FS_DIRTY_NODES), get_pages(sbi, F2FS_DIRTY_DENTS), diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index a02220f208a0..e01387477f04 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -4713,6 +4713,13 @@ static int init_victim_secmap(struct f2fs_sb_info *sbi) dirty_i->victim_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); if (!dirty_i->victim_secmap) return -ENOMEM; + + dirty_i->pinned_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); + if (!dirty_i->pinned_secmap) + return -ENOMEM; + + dirty_i->pinned_secmap_cnt = 0; + dirty_i->enable_pin_section = true; return 0; } @@ -5301,6 +5308,7 @@ static void destroy_victim_secmap(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + kvfree(dirty_i->pinned_secmap); kvfree(dirty_i->victim_secmap); } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index d31eb2f2019c..d7e8eaddc2ec 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -295,6 +295,9 @@ struct dirty_seglist_info { struct mutex seglist_lock; /* lock for segment bitmaps */ int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */ unsigned long *victim_secmap; /* background GC victims */ + unsigned long *pinned_secmap; /* pinned victims from foreground GC */ + unsigned int pinned_secmap_cnt; /* count of victims which has pinned data */ + bool enable_pin_section; /* enable pinning section */ }; /* victim selection function for cleaning and SSR */ From 8c9c56dbe5284f8680f15ccc1c77435532181108 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Mon, 6 Mar 2023 12:05:57 -0800 Subject: [PATCH 2579/4345] FROMGIT: usb: dwc3: gadget: Add 1ms delay after end transfer command without IOC Previously, there was a 100uS delay inserted after issuing an end transfer command for specific controller revisions. This was due to the fact that there was a GUCTL2 bit field which enabled synchronous completion of the end transfer command once the CMDACT bit was cleared in the DEPCMD register. Since this bit does not exist for all controller revisions and the current implementation heavily relies on utizling the EndTransfer command completion interrupt, add the delay back in for uses where the interrupt on completion bit is not set, and increase the duration to 1ms for the controller to complete the command. An issue was seen where the USB request buffer was unmapped while the DWC3 controller was still accessing the TRB. However, it was confirmed that the end transfer command was successfully submitted. (no end transfer timeout) In situations, such as dwc3_gadget_soft_disconnect() and __dwc3_gadget_ep_disable(), the dwc3_remove_request() is utilized, which will issue the end transfer command, and follow up with dwc3_gadget_giveback(). At least for the USB ep disable path, it is required for any pending and started requests to be completed and returned to the function driver in the same context of the disable call. Without the GUCTL2 bit, it is not ensured that the end transfer is completed before the buffers are unmapped. Fixes: cf2f8b63f7f1 ("usb: dwc3: gadget: Remove END_TRANSFER delay") Cc: stable Signed-off-by: Wesley Cheng Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230306200557.29387-1-quic_wcheng@quicinc.com Signed-off-by: Greg Kroah-Hartman Bug: 271815733 Bug: 279141860 Change-Id: I9e06d4810e7052717c7b8e16facd7b765b1ce414 (cherry picked from commit d8a2bb4eb75866275b5cf7de2e593ac3449643e2 https://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git usb-linus) Signed-off-by: Wesley Cheng (cherry picked from commit 35a0e36ee86b9328e6d4e7b353638df730d7bb2e) --- drivers/usb/dwc3/gadget.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 091ec8002efa..7224cb6e6b78 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1673,6 +1673,7 @@ static int __dwc3_gadget_get_frame(struct dwc3 *dwc) */ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt) { + struct dwc3 *dwc = dep->dwc; struct dwc3_gadget_ep_cmd_params params; u32 cmd; int ret; @@ -1696,10 +1697,13 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int WARN_ON_ONCE(ret); dep->resource_index = 0; - if (!interrupt) + if (!interrupt) { + if (!DWC3_IP_IS(DWC3) || DWC3_VER_IS_PRIOR(DWC3, 310A)) + mdelay(1); dep->flags &= ~DWC3_EP_TRANSFER_STARTED; - else if (!ret) + } else if (!ret) { dep->flags |= DWC3_EP_END_TRANSFER_PENDING; + } return ret; } @@ -3749,7 +3753,11 @@ void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, * enabled, the EndTransfer command will have completed upon * returning from this function. * - * This mode is NOT available on the DWC_usb31 IP. + * This mode is NOT available on the DWC_usb31 IP. In this + * case, if the IOC bit is not set, then delay by 1ms + * after issuing the EndTransfer command. This allows for the + * controller to handle the command completely before DWC3 + * remove requests attempts to unmap USB request buffers. */ __dwc3_stop_active_transfer(dep, force, interrupt); } From 5bbc750d9eb8a5f275e4df5a23ff1c96ae890b58 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 9 Apr 2021 15:40:31 +0200 Subject: [PATCH 2580/4345] UPSTREAM: usb: typec: Add typec_port_register_altmodes() This can be used by Type-C controller drivers which use a standard usb-connector fwnode, with altmodes sub-node, to describe the available altmodes. Note there are is no devicetree bindings documentation for the altmodes node, this is deliberate. ATM the fwnodes used to register the altmodes are only used internally to pass platform info from a drivers/platform/x86 driver to the type-c subsystem. When a devicetree user of this functionally comes up and the dt-bindings have been hashed out the internal use can be adjusted to match the dt-bindings. Currently the typec_port_register_altmodes() function expects an "altmodes" child fwnode on port->dev with this "altmodes" fwnode having child fwnodes itself with each child containing 2 integer properties: 1. A "svid" property, which sets the id of the altmode, e.g. displayport altmode has a svid of 0xff01. 2. A "vdo" property, typically used as a bitmask describing the capabilities of the altmode, the bits in the vdo are specified in the specification of the altmode. Bug: 279314285 Reviewed-by: Heikki Krogerus Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210409134033.105834-2-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman Change-Id: Ib78f0b67b985751a32b6f42e79c7976f5515f6b2 Signed-off-by: yubing.zhang (cherry picked from commit 7b458a4c5d7302947556e12c83cfe4da769665d0) Signed-off-by: Kever Yang --- drivers/usb/typec/class.c | 54 +++++++++++++++++++++++++++++++++++++++ include/linux/usb/typec.h | 6 +++++ 2 files changed, 60 insertions(+) diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 4375aa843000..50247e9f3016 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1984,6 +1984,60 @@ typec_port_register_altmode(struct typec_port *port, } EXPORT_SYMBOL_GPL(typec_port_register_altmode); +void typec_port_register_altmodes(struct typec_port *port, + const struct typec_altmode_ops *ops, void *drvdata, + struct typec_altmode **altmodes, size_t n) +{ + struct fwnode_handle *altmodes_node, *child; + struct typec_altmode_desc desc; + struct typec_altmode *alt; + size_t index = 0; + u32 svid, vdo; + int ret; + + altmodes_node = device_get_named_child_node(&port->dev, "altmodes"); + if (!altmodes_node) + return; /* No altmodes specified */ + + fwnode_for_each_child_node(altmodes_node, child) { + ret = fwnode_property_read_u32(child, "svid", &svid); + if (ret) { + dev_err(&port->dev, "Error reading svid for altmode %s\n", + fwnode_get_name(child)); + continue; + } + + ret = fwnode_property_read_u32(child, "vdo", &vdo); + if (ret) { + dev_err(&port->dev, "Error reading vdo for altmode %s\n", + fwnode_get_name(child)); + continue; + } + + if (index >= n) { + dev_err(&port->dev, "Error not enough space for altmode %s\n", + fwnode_get_name(child)); + continue; + } + + desc.svid = svid; + desc.vdo = vdo; + desc.mode = index + 1; + alt = typec_port_register_altmode(port, &desc); + if (IS_ERR(alt)) { + dev_err(&port->dev, "Error registering altmode %s\n", + fwnode_get_name(child)); + continue; + } + + alt->ops = ops; + typec_altmode_set_drvdata(alt, drvdata); + altmodes[index] = alt; + index++; + } +} +EXPORT_SYMBOL_GPL(typec_port_register_altmodes); + /** * typec_register_port - Register a USB Type-C Port * @parent: Parent device diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index b2e2c302caa6..88594260074d 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -18,6 +18,7 @@ struct typec_partner; struct typec_cable; struct typec_plug; struct typec_port; +struct typec_altmode_ops; struct fwnode_handle; struct device; @@ -139,6 +140,11 @@ struct typec_altmode struct typec_altmode *typec_port_register_altmode(struct typec_port *port, const struct typec_altmode_desc *desc); + +void typec_port_register_altmodes(struct typec_port *port, + const struct typec_altmode_ops *ops, void *drvdata, + struct typec_altmode **altmodes, size_t n); + void typec_unregister_altmode(struct typec_altmode *altmode); struct typec_port *typec_altmode2port(struct typec_altmode *alt); From 7513f3e148e2b247ed49cbb8c4cac2ed5b72460d Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 9 Apr 2021 15:40:32 +0200 Subject: [PATCH 2581/4345] UPSTREAM: usb: typec: tcpm: Add support for altmodes Add support for altmodes described in the usb-connector fwnode associated with the Type-C controller by calling the new typec_port_register_altmodes_from_fwnode() helper for this. Bug: 279314285 Reviewed-by: Heikki Krogerus Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210409134033.105834-3-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman Change-Id: I0d7de11b08f1c297e78c7f4cbea90b6d85f8abe5 Signed-off-by: yubing.zhang (cherry picked from commit 55d8b34772e0728a224198ba605eed8cfc570aa0) Signed-off-by: Kever Yang --- drivers/usb/typec/tcpm/tcpm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index dc0d3a48894a..b15a461bec34 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -6521,6 +6521,10 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) goto out_role_sw_put; } + typec_port_register_altmodes(port->typec_port, + &tcpm_altmode_ops, port, + port->port_altmode, ALTMODE_DISCOVERY_MAX); + mutex_lock(&port->lock); tcpm_init(port); mutex_unlock(&port->lock); From 004c4693705a2e3c52257929809fc387a36733b9 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 4 Aug 2022 14:53:07 -0400 Subject: [PATCH 2582/4345] UPSTREAM: dm verity: remove WQ_CPU_INTENSIVE flag since using WQ_UNBOUND The documentation [1] says that WQ_CPU_INTENSIVE is "meaningless" for unbound wq. So remove WQ_CPU_INTENSIVE from the verify_wq allocation. 1. https://www.kernel.org/doc/html/latest/core-api/workqueue.html#flags Suggested-by: Maksym Planeta Signed-off-by: Mike Snitzer Bug: 233247259 (cherry picked from commit 43fa47cb116daa48f731fa5c00d781200addb2ae) Signed-off-by: Nathan Huckleberry (cherry picked from https://android-review.googlesource.com/q/commit:407f5e1a1ddada4de7085798973bbf9135e3bfc5) Merged-In: I13c8916a24274d586a5f462541345d149c602ca3 Bug: 279521578 Change-Id: Ic4d07ccdbd017c4f89e3de5805c9e733a3df9de6 --- drivers/md/dm-verity-target.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 1c8038c665ec..0d4596f100bf 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1220,7 +1220,7 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) } /* WQ_UNBOUND greatly improves performance when running on ramdisk */ - v->verify_wq = alloc_workqueue("kverityd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus()); + v->verify_wq = alloc_workqueue("kverityd", WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus()); if (!v->verify_wq) { ti->error = "Cannot allocate workqueue"; r = -ENOMEM; From 3de420d372f0b81505b5d32f605681b38baddc18 Mon Sep 17 00:00:00 2001 From: Nathan Huckleberry Date: Tue, 30 Aug 2022 18:44:44 +0000 Subject: [PATCH 2583/4345] BACKPORT: dm verity: enable WQ_HIGHPRI on verify_wq WQ_HIGHPRI increases throughput and decreases disk latency when using dm-verity. This is important in Android for camera startup speed. The following tests were run by doing 60 seconds of random reads using a dm-verity device backed by two ramdisks. Without WQ_HIGHPRI lat (usec): min=13, max=3947, avg=69.53, stdev=50.55 READ: bw=51.1MiB/s (53.6MB/s), 51.1MiB/s-51.1MiB/s (53.6MB/s-53.6MB/s) With WQ_HIGHPRI: lat (usec): min=13, max=7854, avg=31.15, stdev=30.42 READ: bw=116MiB/s (121MB/s), 116MiB/s-116MiB/s (121MB/s-121MB/s) Further testing was done by measuring how long it takes to open a camera on an Android device. Without WQ_HIGHPRI Total verity work queue wait times (ms): 880.960, 789.517, 898.852 With WQ_HIGHPRI: Total verity work queue wait times (ms): 528.824, 439.191, 433.300 The average time to open the camera is reduced by 350ms (or 40-50%). Signed-off-by: Nathan Huckleberry Signed-off-by: Mike Snitzer Bug: 233247259 (cherry picked from commit afd41fff9c73ccc3757e94ad727d2a9ac4d7f6cb) [nhuck: Resolved minor conflict in drivers/md/dm-verity-target.c ] (cherry picked from https://android-review.googlesource.com/q/commit:fd4631f8568f5bf16ac5c8b0686d40fad6e4e047) Merged-In: I7d600c924b4a3e793b9a26c2852139683061a831 Bug: 279521578 Change-Id: Ib858d388aa24e4a625085804c097ad66aa179a14 --- drivers/md/dm-verity-target.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 0d4596f100bf..a43c2f78a848 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -993,6 +993,7 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) struct dm_verity_sig_opts verify_args = {0}; struct dm_arg_set as; unsigned int num; + unsigned int wq_flags; unsigned long long num_ll; int r; int i; @@ -1220,7 +1221,18 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) } /* WQ_UNBOUND greatly improves performance when running on ramdisk */ - v->verify_wq = alloc_workqueue("kverityd", WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus()); + wq_flags = WQ_MEM_RECLAIM | WQ_UNBOUND; + /* + * Using WQ_HIGHPRI improves throughput and completion latency by + * reducing wait times when reading from a dm-verity device. + * + * Also as required for the "try_verify_in_tasklet" feature: WQ_HIGHPRI + * allows verify_wq to preempt softirq since verification in tasklet + * will fall-back to using it for error handling (or if the bufio cache + * doesn't have required hashes). + */ + wq_flags |= WQ_HIGHPRI; + v->verify_wq = alloc_workqueue("kverityd", wq_flags, num_online_cpus()); if (!v->verify_wq) { ti->error = "Cannot allocate workqueue"; r = -ENOMEM; From 306223f885fa9cf355deeb84be0e6594cf4a1680 Mon Sep 17 00:00:00 2001 From: Nathan Huckleberry Date: Wed, 1 Feb 2023 17:23:48 -0800 Subject: [PATCH 2584/4345] UPSTREAM: dm verity: stop using WQ_UNBOUND for verify_wq Setting WQ_UNBOUND increases scheduler latency on ARM64. This is likely due to the asymmetric architecture of ARM64 processors. I've been unable to reproduce the results that claim WQ_UNBOUND gives a performance boost on x86-64. This flag is causing performance issues for multiple subsystems within Android. Notably, the same slowdown exists for decompression with EROFS. | open-prebuilt-camera | WQ_UNBOUND | ~WQ_UNBOUND | |-----------------------|------------|---------------| | verity wait time (us) | 11746 | 119 (-98%) | | erofs wait time (us) | 357805 | 174205 (-51%) | | sha256 ramdisk random read | WQ_UNBOUND | ~WQ_UNBOUND | |----------------------------|-----------=---|-------------| | arm64 (accelerated) | bw=42.4MiB/s | bw=212MiB/s | | arm64 (generic) | bw=16.5MiB/s | bw=48MiB/s | | x86_64 (generic) | bw=233MiB/s | bw=230MiB/s | Using a alloc_workqueue() @max_active arg of num_online_cpus() only made sense with WQ_UNBOUND. Switch the @max_active arg to 0 (aka default, which is 256 per-cpu). Also, eliminate 'wq_flags' since it really doesn't serve a purpose. Cc: Sami Tolvanen Cc: Eric Biggers Signed-off-by: Nathan Huckleberry Reviewed-by: Mikulas Patocka Signed-off-by: Mike Snitzer Bug: 233247259 (cherry picked from commit c25da5b7baf1d243e6612ba2b97e2a2c4a1376f6) (cherry picked from https://android-review.googlesource.com/q/commit:0b8c60f03740004a9693d63a2d31618b00469107) Merged-In: Iea437fcfaa978a1389a57ef4d4adcb976d89089c Bug: 279521578 Change-Id: Iecdc2ef25cc59ca53bfe3bca775f93cfda57f9d7 --- drivers/md/dm-verity-target.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index a43c2f78a848..fb1902f2b60a 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -993,7 +993,6 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) struct dm_verity_sig_opts verify_args = {0}; struct dm_arg_set as; unsigned int num; - unsigned int wq_flags; unsigned long long num_ll; int r; int i; @@ -1220,8 +1219,6 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } - /* WQ_UNBOUND greatly improves performance when running on ramdisk */ - wq_flags = WQ_MEM_RECLAIM | WQ_UNBOUND; /* * Using WQ_HIGHPRI improves throughput and completion latency by * reducing wait times when reading from a dm-verity device. @@ -1231,8 +1228,7 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) * will fall-back to using it for error handling (or if the bufio cache * doesn't have required hashes). */ - wq_flags |= WQ_HIGHPRI; - v->verify_wq = alloc_workqueue("kverityd", wq_flags, num_online_cpus()); + v->verify_wq = alloc_workqueue("kverityd", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); if (!v->verify_wq) { ti->error = "Cannot allocate workqueue"; r = -ENOMEM; From 2e61d90c44df342d2493ef407ada126ee8c8cb61 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Wed, 26 Apr 2023 02:16:25 +0000 Subject: [PATCH 2585/4345] ANDROID: fix use of plain integer as NULL pointer This patch fixes the following sparse issues: drivers/android/binder.c:1373:70: sparse: sparse: Using plain integer as NULL pointer drivers/android/binder.c:2508:41: sparse: sparse: Using plain integer as NULL pointer Fixes: e107ea9e4dd1 ("ANDROID: vendor_hooks: Add hooks for binder proc transaction") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304150607.IuUhkfxB-lkp@intel.com/ Cc: zhengding chen Change-Id: I272b3239e2d81bfdd28d1fe412f2c3d0731ec50f Signed-off-by: Carlos Llamas --- drivers/android/binder.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 16e0ba315abf..66152cc321a9 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1399,7 +1399,8 @@ err_no_ref: */ static void binder_free_ref(struct binder_ref *ref) { - trace_android_vh_binder_del_ref(ref->proc ? ref->proc->tsk : 0, ref->data.desc); + trace_android_vh_binder_del_ref(ref->proc ? ref->proc->tsk : NULL, + ref->data.desc); if (ref->node) binder_free_node(ref->node); kfree(ref->death); @@ -2871,7 +2872,8 @@ static int binder_proc_transaction(struct binder_transaction *t, thread = binder_select_thread_ilocked(proc); trace_android_vh_binder_proc_transaction(current, proc->tsk, - thread ? thread->task : 0, node->debug_id, t->code, pending_async); + thread ? thread->task : NULL, node->debug_id, t->code, + pending_async); if (thread) { binder_transaction_priority(thread->task, t, node_prio, From e662521ec73993cc90b1a57a0f12ddd19ca6ac79 Mon Sep 17 00:00:00 2001 From: Jianqun Xu Date: Wed, 8 Feb 2023 17:14:11 +0800 Subject: [PATCH 2586/4345] ARM: dts: rockchip: fix a typo error for rk3288 spdif node [ Upstream commit 02c84f91adb9a64b75ec97d772675c02a3e65ed7 ] Fix the address in the spdif node name. Fixes: 874e568e500a ("ARM: dts: rockchip: Add SPDIF transceiver for RK3288") Signed-off-by: Jianqun Xu Reviewed-by: Sjoerd Simons Link: https://lore.kernel.org/r/20230208091411.1603142-1-jay.xu@rock-chips.com Signed-off-by: Heiko Stuebner Signed-off-by: Sasha Levin --- arch/arm/boot/dts/rk3288.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index aab28161b9ae..250a03a066a1 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -959,7 +959,7 @@ status = "disabled"; }; - spdif: sound@ff88b0000 { + spdif: sound@ff8b0000 { compatible = "rockchip,rk3288-spdif", "rockchip,rk3066-spdif"; reg = <0x0 0xff8b0000 0x0 0x10000>; #sound-dai-cells = <0>; From b33dbd06ac5f23e69c1336df9d5315ad3655a0ad Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 24 Mar 2023 05:16:50 +0300 Subject: [PATCH 2587/4345] arm64: dts: qcom: ipq8074-hk01: enable QMP device, not the PHY node [ Upstream commit 72630ba422b70ea0874fc90d526353cf71c72488 ] Correct PCIe PHY enablement to refer the QMP device nodes rather than PHY device nodes. QMP nodes have 'status = "disabled"' property in the ipq8074.dtsi, while PHY nodes do not correspond to the actual device and do not have the status property. Fixes: e8a7fdc505bb ("arm64: dts: ipq8074: qcom: Re-arrange dts nodes based on address") Signed-off-by: Dmitry Baryshkov Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230324021651.1799969-1-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq8074-hk01.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts b/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts index cc08dc4eb56a..68698cdf56c4 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts +++ b/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts @@ -60,11 +60,11 @@ perst-gpio = <&tlmm 58 0x1>; }; -&pcie_phy0 { +&pcie_qmp0 { status = "okay"; }; -&pcie_phy1 { +&pcie_qmp1 { status = "okay"; }; From 2c06e904c2b730c3c2289fffb3eec601b8d0ec1b Mon Sep 17 00:00:00 2001 From: Marc Gonzalez Date: Mon, 27 Mar 2023 14:09:30 +0200 Subject: [PATCH 2588/4345] arm64: dts: meson-g12-common: specify full DMC range [ Upstream commit aec4353114a408b3a831a22ba34942d05943e462 ] According to S905X2 Datasheet - Revision 07: DRAM Memory Controller (DMC) register area spans ff638000-ff63a000. According to DeviceTree Specification - Release v0.4-rc1: simple-bus nodes do not require reg property. Fixes: 1499218c80c99a ("arm64: dts: move common G12A & G12B modes to meson-g12-common.dtsi") Signed-off-by: Marc Gonzalez Reviewed-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20230327120932.2158389-2-mgonzalez@freebox.fr Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index c0defb36592d..9dd9f7715fbe 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -1604,10 +1604,9 @@ dmc: bus@38000 { compatible = "simple-bus"; - reg = <0x0 0x38000 0x0 0x400>; #address-cells = <2>; #size-cells = <2>; - ranges = <0x0 0x0 0x0 0x38000 0x0 0x400>; + ranges = <0x0 0x0 0x0 0x38000 0x0 0x2000>; canvas: video-lut@48 { compatible = "amlogic,canvas"; From 08b78037c4f1476f5537b4e900ea0f151ea219e8 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 27 Mar 2023 18:03:21 +0800 Subject: [PATCH 2589/4345] arm64: dts: imx8mm-evk: correct pmic clock source [ Upstream commit 85af7ffd24da38e416a14bd6bf207154d94faa83 ] The osc_32k supports #clock-cells as 0, using an id is wrong, drop it. Fixes: a6a355ede574 ("arm64: dts: imx8mm-evk: Add 32.768 kHz clock to PMIC") Signed-off-by: Peng Fan Reviewed-by: Marco Felsch Signed-off-by: Shawn Guo Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi index 521eb3a5a12e..ed6d296bd664 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi @@ -128,7 +128,7 @@ rohm,reset-snvs-powered; #clock-cells = <0>; - clocks = <&osc_32k 0>; + clocks = <&osc_32k>; clock-output-names = "clk-32k-out"; regulators { From 3224458030a2b44eeaeed5af9d1824c2ae0eb30e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 3 Apr 2023 13:54:37 +0200 Subject: [PATCH 2590/4345] netfilter: br_netfilter: fix recent physdev match breakage [ Upstream commit 94623f579ce338b5fa61b5acaa5beb8aa657fb9e ] Recent attempt to ensure PREROUTING hook is executed again when a decrypted ipsec packet received on a bridge passes through the network stack a second time broke the physdev match in INPUT hook. We can't discard the nf_bridge info strct from sabotage_in hook, as this is needed by the physdev match. Keep the struct around and handle this with another conditional instead. Fixes: 2b272bb558f1 ("netfilter: br_netfilter: disable sabotage_in hook after first suppression") Reported-and-tested-by: Farid BENAMROUCHE Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/linux/skbuff.h | 1 + net/bridge/br_netfilter_hooks.c | 17 +++++++++++------ 2 files changed, 12 insertions(+), 6 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 39636fe7e8f0..287999eedef4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -258,6 +258,7 @@ struct nf_bridge_info { u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; + u8 sabotage_in_done:1; __u16 frag_max_size; struct net_device *physindev; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index f3c7cfba31e1..f14beb9a62ed 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -868,12 +868,17 @@ static unsigned int ip_sabotage_in(void *priv, { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - if (nf_bridge && !nf_bridge->in_prerouting && - !netif_is_l3_master(skb->dev) && - !netif_is_l3_slave(skb->dev)) { - nf_bridge_info_free(skb); - state->okfn(state->net, state->sk, skb); - return NF_STOLEN; + if (nf_bridge) { + if (nf_bridge->sabotage_in_done) + return NF_ACCEPT; + + if (!nf_bridge->in_prerouting && + !netif_is_l3_master(skb->dev) && + !netif_is_l3_slave(skb->dev)) { + nf_bridge->sabotage_in_done = 1; + state->okfn(state->net, state->sk, skb); + return NF_STOLEN; + } } return NF_ACCEPT; From 8e73952957a3de4d611a8c2ec82b39b8f25d7c4c Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Thu, 6 Apr 2023 20:18:00 +0300 Subject: [PATCH 2591/4345] regulator: fan53555: Explicitly include bits header [ Upstream commit 4fb9a5060f73627303bc531ceaab1b19d0a24aef ] Since commit f2a9eb975ab2 ("regulator: fan53555: Add support for FAN53526") the driver makes use of the BIT() macro, but relies on the bits header being implicitly included. Explicitly pull the header in to avoid potential build failures in some configurations. While here, reorder include directives alphabetically. Fixes: f2a9eb975ab2 ("regulator: fan53555: Add support for FAN53526") Signed-off-by: Cristian Ciocaltea Link: https://lore.kernel.org/r/20230406171806.948290-3-cristian.ciocaltea@collabora.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/fan53555.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c index aa426183b6a1..1af12074a75a 100644 --- a/drivers/regulator/fan53555.c +++ b/drivers/regulator/fan53555.c @@ -8,18 +8,19 @@ // Copyright (c) 2012 Marvell Technology Ltd. // Yunfan Zhang -#include -#include +#include #include +#include +#include +#include +#include #include +#include #include +#include #include #include -#include -#include #include -#include -#include /* Voltage setting */ #define FAN53555_VSEL0 0x00 From ddcf35deb8f2a1d9addc74b586cf4c5a1f5d6020 Mon Sep 17 00:00:00 2001 From: Gwangun Jung Date: Thu, 13 Apr 2023 19:35:54 +0900 Subject: [PATCH 2592/4345] net: sched: sch_qfq: prevent slab-out-of-bounds in qfq_activate_agg [ Upstream commit 3037933448f60f9acb705997eae62013ecb81e0d ] If the TCA_QFQ_LMAX value is not offered through nlattr, lmax is determined by the MTU value of the network device. The MTU of the loopback device can be set up to 2^31-1. As a result, it is possible to have an lmax value that exceeds QFQ_MIN_LMAX. Due to the invalid lmax value, an index is generated that exceeds the QFQ_MAX_INDEX(=24) value, causing out-of-bounds read/write errors. The following reports a oob access: [ 84.582666] BUG: KASAN: slab-out-of-bounds in qfq_activate_agg.constprop.0 (net/sched/sch_qfq.c:1027 net/sched/sch_qfq.c:1060 net/sched/sch_qfq.c:1313) [ 84.583267] Read of size 4 at addr ffff88810f676948 by task ping/301 [ 84.583686] [ 84.583797] CPU: 3 PID: 301 Comm: ping Not tainted 6.3.0-rc5 #1 [ 84.584164] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [ 84.584644] Call Trace: [ 84.584787] [ 84.584906] dump_stack_lvl (lib/dump_stack.c:107 (discriminator 1)) [ 84.585108] print_report (mm/kasan/report.c:320 mm/kasan/report.c:430) [ 84.585570] kasan_report (mm/kasan/report.c:538) [ 84.585988] qfq_activate_agg.constprop.0 (net/sched/sch_qfq.c:1027 net/sched/sch_qfq.c:1060 net/sched/sch_qfq.c:1313) [ 84.586599] qfq_enqueue (net/sched/sch_qfq.c:1255) [ 84.587607] dev_qdisc_enqueue (net/core/dev.c:3776) [ 84.587749] __dev_queue_xmit (./include/net/sch_generic.h:186 net/core/dev.c:3865 net/core/dev.c:4212) [ 84.588763] ip_finish_output2 (./include/net/neighbour.h:546 net/ipv4/ip_output.c:228) [ 84.589460] ip_output (net/ipv4/ip_output.c:430) [ 84.590132] ip_push_pending_frames (./include/net/dst.h:444 net/ipv4/ip_output.c:126 net/ipv4/ip_output.c:1586 net/ipv4/ip_output.c:1606) [ 84.590285] raw_sendmsg (net/ipv4/raw.c:649) [ 84.591960] sock_sendmsg (net/socket.c:724 net/socket.c:747) [ 84.592084] __sys_sendto (net/socket.c:2142) [ 84.593306] __x64_sys_sendto (net/socket.c:2150) [ 84.593779] do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) [ 84.593902] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) [ 84.594070] RIP: 0033:0x7fe568032066 [ 84.594192] Code: 0e 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 41 89 ca 64 8b 04 25 18 00 00 00 85 c09[ 84.594796] RSP: 002b:00007ffce388b4e8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c Code starting with the faulting instruction =========================================== [ 84.595047] RAX: ffffffffffffffda RBX: 00007ffce388cc70 RCX: 00007fe568032066 [ 84.595281] RDX: 0000000000000040 RSI: 00005605fdad6d10 RDI: 0000000000000003 [ 84.595515] RBP: 00005605fdad6d10 R08: 00007ffce388eeec R09: 0000000000000010 [ 84.595749] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040 [ 84.595984] R13: 00007ffce388cc30 R14: 00007ffce388b4f0 R15: 0000001d00000001 [ 84.596218] [ 84.596295] [ 84.596351] Allocated by task 291: [ 84.596467] kasan_save_stack (mm/kasan/common.c:46) [ 84.596597] kasan_set_track (mm/kasan/common.c:52) [ 84.596725] __kasan_kmalloc (mm/kasan/common.c:384) [ 84.596852] __kmalloc_node (./include/linux/kasan.h:196 mm/slab_common.c:967 mm/slab_common.c:974) [ 84.596979] qdisc_alloc (./include/linux/slab.h:610 ./include/linux/slab.h:731 net/sched/sch_generic.c:938) [ 84.597100] qdisc_create (net/sched/sch_api.c:1244) [ 84.597222] tc_modify_qdisc (net/sched/sch_api.c:1680) [ 84.597357] rtnetlink_rcv_msg (net/core/rtnetlink.c:6174) [ 84.597495] netlink_rcv_skb (net/netlink/af_netlink.c:2574) [ 84.597627] netlink_unicast (net/netlink/af_netlink.c:1340 net/netlink/af_netlink.c:1365) [ 84.597759] netlink_sendmsg (net/netlink/af_netlink.c:1942) [ 84.597891] sock_sendmsg (net/socket.c:724 net/socket.c:747) [ 84.598016] ____sys_sendmsg (net/socket.c:2501) [ 84.598147] ___sys_sendmsg (net/socket.c:2557) [ 84.598275] __sys_sendmsg (./include/linux/file.h:31 net/socket.c:2586) [ 84.598399] do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) [ 84.598520] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) [ 84.598688] [ 84.598744] The buggy address belongs to the object at ffff88810f674000 [ 84.598744] which belongs to the cache kmalloc-8k of size 8192 [ 84.599135] The buggy address is located 2664 bytes to the right of [ 84.599135] allocated 7904-byte region [ffff88810f674000, ffff88810f675ee0) [ 84.599544] [ 84.599598] The buggy address belongs to the physical page: [ 84.599777] page:00000000e638567f refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10f670 [ 84.600074] head:00000000e638567f order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 84.600330] flags: 0x200000000010200(slab|head|node=0|zone=2) [ 84.600517] raw: 0200000000010200 ffff888100043180 dead000000000122 0000000000000000 [ 84.600764] raw: 0000000000000000 0000000080020002 00000001ffffffff 0000000000000000 [ 84.601009] page dumped because: kasan: bad access detected [ 84.601187] [ 84.601241] Memory state around the buggy address: [ 84.601396] ffff88810f676800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 84.601620] ffff88810f676880: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 84.601845] >ffff88810f676900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 84.602069] ^ [ 84.602243] ffff88810f676980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 84.602468] ffff88810f676a00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 84.602693] ================================================================== [ 84.602924] Disabling lock debugging due to kernel taint Fixes: 3015f3d2a3cd ("pkt_sched: enable QFQ to support TSO/GSO") Reported-by: Gwangun Jung Signed-off-by: Gwangun Jung Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/sch_qfq.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 1d1d81aeb389..cad7deacf60a 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -421,15 +421,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } else weight = 1; - if (tb[TCA_QFQ_LMAX]) { + if (tb[TCA_QFQ_LMAX]) lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); - return -EINVAL; - } - } else + else lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { + pr_notice("qfq: invalid max length %u\n", lmax); + return -EINVAL; + } + inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; From b6dd232f6350778a6ba440ea52bdfc4571b62a06 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Fri, 14 Apr 2023 14:08:35 +0800 Subject: [PATCH 2593/4345] virtio_net: bugfix overflow inside xdp_linearize_page() [ Upstream commit 853618d5886bf94812f31228091cd37d308230f7 ] Here we copy the data from the original buf to the new page. But we not check that it may be overflow. As long as the size received(including vnethdr) is greater than 3840 (PAGE_SIZE -VIRTIO_XDP_HEADROOM). Then the memcpy will overflow. And this is completely possible, as long as the MTU is large, such as 4096. In our test environment, this will cause crash. Since crash is caused by the written memory, it is meaningless, so I do not include it. Fixes: 72979a6c3590 ("virtio_net: xdp, add slowpath case for non contiguous buffers") Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/virtio_net.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d53321116136..47c9118cc92a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -646,8 +646,13 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, int page_off, unsigned int *len) { - struct page *page = alloc_page(GFP_ATOMIC); + int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + struct page *page; + if (page_off + *len + tailroom > PAGE_SIZE) + return NULL; + + page = alloc_page(GFP_ATOMIC); if (!page) return NULL; @@ -655,7 +660,6 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, page_off += *len; while (--*num_buf) { - int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); unsigned int buflen; void *buf; int off; From 06a72bbf0d9834fde7e12b2039fbc929fc8eb220 Mon Sep 17 00:00:00 2001 From: Jonathan Cooper Date: Tue, 28 Jun 2022 14:58:55 +0100 Subject: [PATCH 2594/4345] sfc: Split STATE_READY in to STATE_NET_DOWN and STATE_NET_UP. [ Upstream commit 813cf9d1e753e1e0a247d3d685212a06141b483e ] This patch splits the READY state in to NET_UP and NET_DOWN. This is to prepare for future work to delay resource allocation until interface up so that we can use resources more efficiently in SRIOV environments, and also to lay the ground work for an extra PROBED state where we don't create a network interface, for VDPA operation. Signed-off-by: Jonathan Cooper Acked-by: Martin Habets Signed-off-by: David S. Miller Stable-dep-of: a80bb8e7233b ("sfc: Fix use-after-free due to selftest_work") Signed-off-by: Sasha Levin --- drivers/net/ethernet/sfc/ef100_netdev.c | 6 ++- drivers/net/ethernet/sfc/efx.c | 29 ++++++------- drivers/net/ethernet/sfc/efx_common.c | 10 ++--- drivers/net/ethernet/sfc/efx_common.h | 6 +-- drivers/net/ethernet/sfc/ethtool_common.c | 2 +- drivers/net/ethernet/sfc/net_driver.h | 50 +++++++++++++++++++++-- 6 files changed, 72 insertions(+), 31 deletions(-) diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index 63a44ee763be..b9429e8faba1 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -96,6 +96,8 @@ static int ef100_net_stop(struct net_device *net_dev) efx_mcdi_free_vis(efx); efx_remove_interrupts(efx); + efx->state = STATE_NET_DOWN; + return 0; } @@ -172,6 +174,8 @@ static int ef100_net_open(struct net_device *net_dev) efx_link_status_changed(efx); mutex_unlock(&efx->mac_lock); + efx->state = STATE_NET_UP; + return 0; fail: @@ -272,7 +276,7 @@ int ef100_register_netdev(struct efx_nic *efx) /* Always start with carrier off; PHY events will detect the link */ netif_carrier_off(net_dev); - efx->state = STATE_READY; + efx->state = STATE_NET_DOWN; rtnl_unlock(); efx_init_mcdi_logging(efx); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index c069659c9e2d..5f064f185d55 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -105,14 +105,6 @@ static int efx_xdp(struct net_device *dev, struct netdev_bpf *xdp); static int efx_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **xdpfs, u32 flags); -#define EFX_ASSERT_RESET_SERIALISED(efx) \ - do { \ - if ((efx->state == STATE_READY) || \ - (efx->state == STATE_RECOVERY) || \ - (efx->state == STATE_DISABLED)) \ - ASSERT_RTNL(); \ - } while (0) - /************************************************************************** * * Port handling @@ -377,6 +369,8 @@ static int efx_probe_all(struct efx_nic *efx) if (rc) goto fail5; + efx->state = STATE_NET_DOWN; + return 0; fail5: @@ -543,6 +537,9 @@ int efx_net_open(struct net_device *net_dev) efx_start_all(efx); if (efx->state == STATE_DISABLED || efx->reset_pending) netif_device_detach(efx->net_dev); + else + efx->state = STATE_NET_UP; + efx_selftest_async_start(efx); return 0; } @@ -721,8 +718,6 @@ static int efx_register_netdev(struct efx_nic *efx) * already requested. If so, the NIC is probably hosed so we * abort. */ - efx->state = STATE_READY; - smp_mb(); /* ensure we change state before checking reset_pending */ if (efx->reset_pending) { netif_err(efx, probe, efx->net_dev, "aborting probe due to scheduled reset\n"); @@ -750,6 +745,8 @@ static int efx_register_netdev(struct efx_nic *efx) efx_associate(efx); + efx->state = STATE_NET_DOWN; + rtnl_unlock(); rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_type); @@ -851,7 +848,7 @@ static void efx_pci_remove_main(struct efx_nic *efx) /* Flush reset_work. It can no longer be scheduled since we * are not READY. */ - BUG_ON(efx->state == STATE_READY); + WARN_ON(efx_net_active(efx->state)); efx_flush_reset_workqueue(efx); efx_disable_interrupts(efx); @@ -1196,13 +1193,13 @@ static int efx_pm_freeze(struct device *dev) rtnl_lock(); - if (efx->state != STATE_DISABLED) { - efx->state = STATE_UNINIT; - + if (efx_net_active(efx->state)) { efx_device_detach_sync(efx); efx_stop_all(efx); efx_disable_interrupts(efx); + + efx->state = efx_freeze(efx->state); } rtnl_unlock(); @@ -1217,7 +1214,7 @@ static int efx_pm_thaw(struct device *dev) rtnl_lock(); - if (efx->state != STATE_DISABLED) { + if (efx_frozen(efx->state)) { rc = efx_enable_interrupts(efx); if (rc) goto fail; @@ -1230,7 +1227,7 @@ static int efx_pm_thaw(struct device *dev) efx_device_attach_if_not_resetting(efx); - efx->state = STATE_READY; + efx->state = efx_thaw(efx->state); efx->type->resume_wol(efx); } diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index de797e1ac5a9..1527678b241c 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -897,7 +897,7 @@ static void efx_reset_work(struct work_struct *data) * have changed by now. Now that we have the RTNL lock, * it cannot change again. */ - if (efx->state == STATE_READY) + if (efx_net_active(efx->state)) (void)efx_reset(efx, method); rtnl_unlock(); @@ -907,7 +907,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) { enum reset_type method; - if (efx->state == STATE_RECOVERY) { + if (efx_recovering(efx->state)) { netif_dbg(efx, drv, efx->net_dev, "recovering: skip scheduling %s reset\n", RESET_TYPE(type)); @@ -942,7 +942,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) /* If we're not READY then just leave the flags set as the cue * to abort probing or reschedule the reset later. */ - if (READ_ONCE(efx->state) != STATE_READY) + if (!efx_net_active(READ_ONCE(efx->state))) return; /* efx_process_channel() will no longer read events once a @@ -1214,7 +1214,7 @@ static pci_ers_result_t efx_io_error_detected(struct pci_dev *pdev, rtnl_lock(); if (efx->state != STATE_DISABLED) { - efx->state = STATE_RECOVERY; + efx->state = efx_recover(efx->state); efx->reset_pending = 0; efx_device_detach_sync(efx); @@ -1268,7 +1268,7 @@ static void efx_io_resume(struct pci_dev *pdev) netif_err(efx, hw, efx->net_dev, "efx_reset failed after PCI error (%d)\n", rc); } else { - efx->state = STATE_READY; + efx->state = efx_recovered(efx->state); netif_dbg(efx, hw, efx->net_dev, "Done resetting and resuming IO after PCI error.\n"); } diff --git a/drivers/net/ethernet/sfc/efx_common.h b/drivers/net/ethernet/sfc/efx_common.h index 65513fd0cf6c..c72e819da8fd 100644 --- a/drivers/net/ethernet/sfc/efx_common.h +++ b/drivers/net/ethernet/sfc/efx_common.h @@ -45,9 +45,7 @@ int efx_reconfigure_port(struct efx_nic *efx); #define EFX_ASSERT_RESET_SERIALISED(efx) \ do { \ - if ((efx->state == STATE_READY) || \ - (efx->state == STATE_RECOVERY) || \ - (efx->state == STATE_DISABLED)) \ + if (efx->state != STATE_UNINIT) \ ASSERT_RTNL(); \ } while (0) @@ -64,7 +62,7 @@ void efx_port_dummy_op_void(struct efx_nic *efx); static inline int efx_check_disabled(struct efx_nic *efx) { - if (efx->state == STATE_DISABLED || efx->state == STATE_RECOVERY) { + if (efx->state == STATE_DISABLED || efx_recovering(efx->state)) { netif_err(efx, drv, efx->net_dev, "device is disabled due to earlier errors\n"); return -EIO; diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c index bd552c7dffcb..3846b76b8972 100644 --- a/drivers/net/ethernet/sfc/ethtool_common.c +++ b/drivers/net/ethernet/sfc/ethtool_common.c @@ -137,7 +137,7 @@ void efx_ethtool_self_test(struct net_device *net_dev, if (!efx_tests) goto fail; - if (efx->state != STATE_READY) { + if (!efx_net_active(efx->state)) { rc = -EBUSY; goto out; } diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 8aecb4bd2c0d..39f97929b3ff 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -627,12 +627,54 @@ enum efx_int_mode { #define EFX_INT_MODE_USE_MSI(x) (((x)->interrupt_mode) <= EFX_INT_MODE_MSI) enum nic_state { - STATE_UNINIT = 0, /* device being probed/removed or is frozen */ - STATE_READY = 1, /* hardware ready and netdev registered */ - STATE_DISABLED = 2, /* device disabled due to hardware errors */ - STATE_RECOVERY = 3, /* device recovering from PCI error */ + STATE_UNINIT = 0, /* device being probed/removed */ + STATE_NET_DOWN, /* hardware probed and netdev registered */ + STATE_NET_UP, /* ready for traffic */ + STATE_DISABLED, /* device disabled due to hardware errors */ + + STATE_RECOVERY = 0x100,/* recovering from PCI error */ + STATE_FROZEN = 0x200, /* frozen by power management */ }; +static inline bool efx_net_active(enum nic_state state) +{ + return state == STATE_NET_DOWN || state == STATE_NET_UP; +} + +static inline bool efx_frozen(enum nic_state state) +{ + return state & STATE_FROZEN; +} + +static inline bool efx_recovering(enum nic_state state) +{ + return state & STATE_RECOVERY; +} + +static inline enum nic_state efx_freeze(enum nic_state state) +{ + WARN_ON(!efx_net_active(state)); + return state | STATE_FROZEN; +} + +static inline enum nic_state efx_thaw(enum nic_state state) +{ + WARN_ON(!efx_frozen(state)); + return state & ~STATE_FROZEN; +} + +static inline enum nic_state efx_recover(enum nic_state state) +{ + WARN_ON(!efx_net_active(state)); + return state | STATE_RECOVERY; +} + +static inline enum nic_state efx_recovered(enum nic_state state) +{ + WARN_ON(!efx_recovering(state)); + return state & ~STATE_RECOVERY; +} + /* Forward declaration */ struct efx_nic; From 6758a51ef36ac78962db2f421a8e4d85fd23853a Mon Sep 17 00:00:00 2001 From: Ding Hui Date: Fri, 14 Apr 2023 23:23:06 +0800 Subject: [PATCH 2595/4345] sfc: Fix use-after-free due to selftest_work [ Upstream commit a80bb8e7233b2ad6ff119646b6e33fb3edcec37b ] There is a use-after-free scenario that is: When the NIC is down, user set mac address or vlan tag to VF, the xxx_set_vf_mac() or xxx_set_vf_vlan() will invoke efx_net_stop() and efx_net_open(), since netif_running() is false, the port will not start and keep port_enabled false, but selftest_work is scheduled in efx_net_open(). If we remove the device before selftest_work run, the efx_stop_port() will not be called since the NIC is down, and then efx is freed, we will soon get a UAF in run_timer_softirq() like this: [ 1178.907941] ================================================================== [ 1178.907948] BUG: KASAN: use-after-free in run_timer_softirq+0xdea/0xe90 [ 1178.907950] Write of size 8 at addr ff11001f449cdc80 by task swapper/47/0 [ 1178.907950] [ 1178.907953] CPU: 47 PID: 0 Comm: swapper/47 Kdump: loaded Tainted: G O --------- -t - 4.18.0 #1 [ 1178.907954] Hardware name: SANGFOR X620G40/WI2HG-208T1061A, BIOS SPYH051032-U01 04/01/2022 [ 1178.907955] Call Trace: [ 1178.907956] [ 1178.907960] dump_stack+0x71/0xab [ 1178.907963] print_address_description+0x6b/0x290 [ 1178.907965] ? run_timer_softirq+0xdea/0xe90 [ 1178.907967] kasan_report+0x14a/0x2b0 [ 1178.907968] run_timer_softirq+0xdea/0xe90 [ 1178.907971] ? init_timer_key+0x170/0x170 [ 1178.907973] ? hrtimer_cancel+0x20/0x20 [ 1178.907976] ? sched_clock+0x5/0x10 [ 1178.907978] ? sched_clock_cpu+0x18/0x170 [ 1178.907981] __do_softirq+0x1c8/0x5fa [ 1178.907985] irq_exit+0x213/0x240 [ 1178.907987] smp_apic_timer_interrupt+0xd0/0x330 [ 1178.907989] apic_timer_interrupt+0xf/0x20 [ 1178.907990] [ 1178.907991] RIP: 0010:mwait_idle+0xae/0x370 If the NIC is not actually brought up, there is no need to schedule selftest_work, so let's move invoking efx_selftest_async_start() into efx_start_all(), and it will be canceled by broughting down. Fixes: dd40781e3a4e ("sfc: Run event/IRQ self-test asynchronously when interface is brought up") Fixes: e340be923012 ("sfc: add ndo_set_vf_mac() function for EF10") Debugged-by: Huang Cun Cc: Donglin Peng Suggested-by: Martin Habets Signed-off-by: Ding Hui Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/sfc/efx.c | 1 - drivers/net/ethernet/sfc/efx_common.c | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 5f064f185d55..7cf52fcdb307 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -540,7 +540,6 @@ int efx_net_open(struct net_device *net_dev) else efx->state = STATE_NET_UP; - efx_selftest_async_start(efx); return 0; } diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index 1527678b241c..476ef1c97637 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -542,6 +542,8 @@ void efx_start_all(struct efx_nic *efx) /* Start the hardware monitor if there is one */ efx_start_monitor(efx); + efx_selftest_async_start(efx); + /* Link state detection is normally event-driven; we have * to poll now because we could have missed a change */ From 381110d061926f738d3220feb5580f1f1409cbd7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 17 Apr 2023 10:21:36 +0200 Subject: [PATCH 2596/4345] netfilter: nf_tables: fix ifdef to also consider nf_tables=m [ Upstream commit c55c0e91c813589dc55bea6bf9a9fbfaa10ae41d ] nftables can be built as a module, so fix the preprocessor conditional accordingly. Fixes: 478b360a47b7 ("netfilter: nf_tables: fix nf_trace always-on with XT_TRACE=n") Reported-by: Florian Fainelli Reported-by: Jakub Kicinski Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 287999eedef4..a210f1995862 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4277,7 +4277,7 @@ static inline void nf_reset_ct(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -4297,7 +4297,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif From 72df55d3dc96aa5784254e2d86c0802ebe09cf5d Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Fri, 24 Mar 2023 18:16:38 +0100 Subject: [PATCH 2597/4345] i40e: fix accessing vsi->active_filters without holding lock [ Upstream commit 8485d093b076e59baff424552e8aecfc5bd2d261 ] Fix accessing vsi->active_filters without holding the mac_filter_hash_lock. Move vsi->active_filters = 0 inside critical section and move clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) after the critical section to ensure the new filters from other threads can be added only after filters cleaning in the critical section is finished. Fixes: 278e7d0b9d68 ("i40e: store MAC/VLAN filters in a hash with the MAC Address as key") Signed-off-by: Aleksandr Loktionov Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 76481ff7074b..3a93d538b2d7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13458,15 +13458,15 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) vsi->id = ctxt.vsi_number; } - vsi->active_filters = 0; - clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); spin_lock_bh(&vsi->mac_filter_hash_lock); + vsi->active_filters = 0; /* If macvlan filters already exist, force them to get loaded */ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { f->state = I40E_FILTER_NEW; f_count++; } spin_unlock_bh(&vsi->mac_filter_hash_lock); + clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); if (f_count) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; From 880c09bc2f0b6d0f3f3d995508a1c06177eb7d73 Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Mon, 3 Apr 2023 07:13:18 +0200 Subject: [PATCH 2598/4345] i40e: fix i40e_setup_misc_vector() error handling [ Upstream commit c86c00c6935505929cc9adb29ddb85e48c71f828 ] Add error handling of i40e_setup_misc_vector() in i40e_rebuild(). In case interrupt vectors setup fails do not re-open vsi-s and do not bring up vf-s, we have no interrupts to serve a traffic anyway. Fixes: 41c445ff0f48 ("i40e: main driver core") Signed-off-by: Aleksandr Loktionov Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/i40e/i40e_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3a93d538b2d7..d23a467d0d20 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -10448,8 +10448,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) pf->hw.aq.asq_last_status)); } /* reinit the misc interrupt */ - if (pf->flags & I40E_FLAG_MSIX_ENABLED) + if (pf->flags & I40E_FLAG_MSIX_ENABLED) { ret = i40e_setup_misc_vector(pf); + if (ret) + goto end_unlock; + } /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out From b6b06c5ee333ff9ccaf4c54005263daba5673b2f Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Mon, 17 Apr 2023 05:07:18 -0700 Subject: [PATCH 2599/4345] mlxfw: fix null-ptr-deref in mlxfw_mfa2_tlv_next() [ Upstream commit c0e73276f0fcbbd3d4736ba975d7dc7a48791b0c ] Function mlxfw_mfa2_tlv_multi_get() returns NULL if 'tlv' in question does not pass checks in mlxfw_mfa2_tlv_payload_get(). This behaviour may lead to NULL pointer dereference in 'multi->total_len'. Fix this issue by testing mlxfw_mfa2_tlv_multi_get()'s return value against NULL. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: 410ed13cae39 ("Add the mlxfw module for Mellanox firmware flash process") Co-developed-by: Natalia Petrova Signed-off-by: Nikita Zhandarovich Reviewed-by: Ido Schimmel Link: https://lore.kernel.org/r/20230417120718.52325-1-n.zhandarovich@fintech.ru Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c index 017d68f1e123..972c571b4158 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c @@ -31,6 +31,8 @@ mlxfw_mfa2_tlv_next(const struct mlxfw_mfa2_file *mfa2_file, if (tlv->type == MLXFW_MFA2_TLV_MULTI_PART) { multi = mlxfw_mfa2_tlv_multi_get(mfa2_file, tlv); + if (!multi) + return NULL; tlv_len = NLA_ALIGN(tlv_len + be16_to_cpu(multi->total_len)); } From c972851d3848647f57cd8d5625c48663410c3f96 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 17 Apr 2023 09:00:52 -0400 Subject: [PATCH 2600/4345] net: rpl: fix rpl header size calculation [ Upstream commit 4e006c7a6dac0ead4c1bf606000aa90a372fc253 ] This patch fixes a missing 8 byte for the header size calculation. The ipv6_rpl_srh_size() is used to check a skb_pull() on skb->data which points to skb_transport_header(). Currently we only check on the calculated addresses fields using CmprI and CmprE fields, see: https://www.rfc-editor.org/rfc/rfc6554#section-3 there is however a missing 8 byte inside the calculation which stands for the fields before the addresses field. Those 8 bytes are represented by sizeof(struct ipv6_rpl_sr_hdr) expression. Fixes: 8610c7c6e3bd ("net: ipv6: add support for rpl sr exthdr") Signed-off-by: Alexander Aring Reported-by: maxpl0it Reviewed-by: David Ahern Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/rpl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c index 307f336b5353..3b0386437f69 100644 --- a/net/ipv6/rpl.c +++ b/net/ipv6/rpl.c @@ -32,7 +32,8 @@ static void *ipv6_rpl_segdata_pos(const struct ipv6_rpl_sr_hdr *hdr, int i) size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre) { - return (n * IPV6_PFXTAIL_LEN(cmpri)) + IPV6_PFXTAIL_LEN(cmpre); + return sizeof(struct ipv6_rpl_sr_hdr) + (n * IPV6_PFXTAIL_LEN(cmpri)) + + IPV6_PFXTAIL_LEN(cmpre); } void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr, From b085b5787b4a83755e7bf485d44c00217f04ba44 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 17 Apr 2023 18:52:51 +0200 Subject: [PATCH 2601/4345] mlxsw: pci: Fix possible crash during initialization [ Upstream commit 1f64757ee2bb22a93ec89b4c71707297e8cca0ba ] During initialization the driver issues a reset command via its command interface in order to remove previous configuration from the device. After issuing the reset, the driver waits for 200ms before polling on the "system_status" register using memory-mapped IO until the device reaches a ready state (0x5E). The wait is necessary because the reset command only triggers the reset, but the reset itself happens asynchronously. If the driver starts polling too soon, the read of the "system_status" register will never return and the system will crash [1]. The issue was discovered when the device was flashed with a development firmware version where the reset routine took longer to complete. The issue was fixed in the firmware, but it exposed the fact that the current wait time is borderline. Fix by increasing the wait time from 200ms to 400ms. With this patch and the buggy firmware version, the issue did not reproduce in 10 reboots whereas without the patch the issue is reproduced quite consistently. [1] mce: CPUs not responding to MCE broadcast (may include false positives): 0,4 mce: CPUs not responding to MCE broadcast (may include false positives): 0,4 Kernel panic - not syncing: Timeout: Not all CPUs entered broadcast exception handler Shutting down cpus with NMI Kernel Offset: 0x12000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) Fixes: ac004e84164e ("mlxsw: pci: Wait longer before accessing the device after reset") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Petr Machata Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index a2c1fbd3e0d1..0225c8f1e5ea 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -26,7 +26,7 @@ #define MLXSW_PCI_CIR_TIMEOUT_MSECS 1000 #define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 -#define MLXSW_PCI_SW_RESET_WAIT_MSECS 200 +#define MLXSW_PCI_SW_RESET_WAIT_MSECS 400 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF #define MLXSW_PCI_FW_READY_MAGIC 0x5E From b1281d008845ae9a4de9ef7510dcc1667557a67a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 11 Apr 2023 15:24:13 +0000 Subject: [PATCH 2602/4345] bpf: Fix incorrect verifier pruning due to missing register precision taints [ Upstream commit 71b547f561247897a0a14f3082730156c0533fed ] Juan Jose et al reported an issue found via fuzzing where the verifier's pruning logic prematurely marks a program path as safe. Consider the following program: 0: (b7) r6 = 1024 1: (b7) r7 = 0 2: (b7) r8 = 0 3: (b7) r9 = -2147483648 4: (97) r6 %= 1025 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 7: (97) r6 %= 1 8: (b7) r9 = 0 9: (bd) if r6 <= r9 goto pc+1 10: (b7) r6 = 0 11: (b7) r0 = 0 12: (63) *(u32 *)(r10 -4) = r0 13: (18) r4 = 0xffff888103693400 // map_ptr(ks=4,vs=48) 15: (bf) r1 = r4 16: (bf) r2 = r10 17: (07) r2 += -4 18: (85) call bpf_map_lookup_elem#1 19: (55) if r0 != 0x0 goto pc+1 20: (95) exit 21: (77) r6 >>= 10 22: (27) r6 *= 8192 23: (bf) r1 = r0 24: (0f) r0 += r6 25: (79) r3 = *(u64 *)(r0 +0) 26: (7b) *(u64 *)(r1 +0) = r3 27: (95) exit The verifier treats this as safe, leading to oob read/write access due to an incorrect verifier conclusion: func#0 @0 0: R1=ctx(off=0,imm=0) R10=fp0 0: (b7) r6 = 1024 ; R6_w=1024 1: (b7) r7 = 0 ; R7_w=0 2: (b7) r8 = 0 ; R8_w=0 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 4: (97) r6 %= 1025 ; R6_w=scalar() 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff00000000; 0xffffffff)) R9_w=-2147483648 7: (97) r6 %= 1 ; R6_w=scalar() 8: (b7) r9 = 0 ; R9=0 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 10: (b7) r6 = 0 ; R6_w=0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 9 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 20: (95) exit from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=0 22: (27) r6 *= 8192 ; R6_w=0 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 19 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? last_idx 18 first_idx 9 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 regs=40 stack=0 before 10: (b7) r6 = 0 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 27: (95) exit from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 frame 0: propagating r6 last_idx 19 first_idx 11 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 last_idx 9 first_idx 9 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=0 R10=fp0 last_idx 8 first_idx 0 regs=40 stack=0 before 8: (b7) r9 = 0 regs=40 stack=0 before 7: (97) r6 %= 1 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=40 stack=0 before 5: (05) goto pc+0 regs=40 stack=0 before 4: (97) r6 %= 1025 regs=40 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 19: safe frame 0: propagating r6 last_idx 9 first_idx 0 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=40 stack=0 before 5: (05) goto pc+0 regs=40 stack=0 before 4: (97) r6 %= 1025 regs=40 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 from 6 to 9: safe verification time 110 usec stack depth 4 processed 36 insns (limit 1000000) max_states_per_insn 0 total_states 3 peak_states 3 mark_read 2 The verifier considers this program as safe by mistakenly pruning unsafe code paths. In the above func#0, code lines 0-10 are of interest. In line 0-3 registers r6 to r9 are initialized with known scalar values. In line 4 the register r6 is reset to an unknown scalar given the verifier does not track modulo operations. Due to this, the verifier can also not determine precisely which branches in line 6 and 9 are taken, therefore it needs to explore them both. As can be seen, the verifier starts with exploring the false/fall-through paths first. The 'from 19 to 21' path has both r6=0 and r9=0 and the pointer arithmetic on r0 += r6 is therefore considered safe. Given the arithmetic, r6 is correctly marked for precision tracking where backtracking kicks in where it walks back the current path all the way where r6 was set to 0 in the fall-through branch. Next, the pruning logics pops the path 'from 9 to 11' from the stack. Also here, the state of the registers is the same, that is, r6=0 and r9=0, so that at line 19 the path can be pruned as it is considered safe. It is interesting to note that the conditional in line 9 turned r6 into a more precise state, that is, in the fall-through path at the beginning of line 10, it is R6=scalar(umin=1), and in the branch-taken path (which is analyzed here) at the beginning of line 11, r6 turned into a known const r6=0 as r9=0 prior to that and therefore (unsigned) r6 <= 0 concludes that r6 must be 0 (**): [...] ; R6_w=scalar() 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 [...] from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 [...] The next path is 'from 6 to 9'. The verifier considers the old and current state equivalent, and therefore prunes the search incorrectly. Looking into the two states which are being compared by the pruning logic at line 9, the old state consists of R6_rwD=Pscalar() R9_rwD=0 R10=fp0 and the new state consists of R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0. While r6 had the reg->precise flag correctly set in the old state, r9 did not. Both r6'es are considered as equivalent given the old one is a superset of the current, more precise one, however, r9's actual values (0 vs 0x80000000) mismatch. Given the old r9 did not have reg->precise flag set, the verifier does not consider the register as contributing to the precision state of r6, and therefore it considered both r9 states as equivalent. However, for this specific pruned path (which is also the actual path taken at runtime), register r6 will be 0x400 and r9 0x80000000 when reaching line 21, thus oob-accessing the map. The purpose of precision tracking is to initially mark registers (including spilled ones) as imprecise to help verifier's pruning logic finding equivalent states it can then prune if they don't contribute to the program's safety aspects. For example, if registers are used for pointer arithmetic or to pass constant length to a helper, then the verifier sets reg->precise flag and backtracks the BPF program instruction sequence and chain of verifier states to ensure that the given register or stack slot including their dependencies are marked as precisely tracked scalar. This also includes any other registers and slots that contribute to a tracked state of given registers/stack slot. This backtracking relies on recorded jmp_history and is able to traverse entire chain of parent states. This process ends only when all the necessary registers/slots and their transitive dependencies are marked as precise. The backtrack_insn() is called from the current instruction up to the first instruction, and its purpose is to compute a bitmask of registers and stack slots that need precision tracking in the parent's verifier state. For example, if a current instruction is r6 = r7, then r6 needs precision after this instruction and r7 needs precision before this instruction, that is, in the parent state. Hence for the latter r7 is marked and r6 unmarked. For the class of jmp/jmp32 instructions, backtrack_insn() today only looks at call and exit instructions and for all other conditionals the masks remain as-is. However, in the given situation register r6 has a dependency on r9 (as described above in **), so also that one needs to be marked for precision tracking. In other words, if an imprecise register influences a precise one, then the imprecise register should also be marked precise. Meaning, in the parent state both dest and src register need to be tracked for precision and therefore the marking must be more conservative by setting reg->precise flag for both. The precision propagation needs to cover both for the conditional: if the src reg was marked but not the dst reg and vice versa. After the fix the program is correctly rejected: func#0 @0 0: R1=ctx(off=0,imm=0) R10=fp0 0: (b7) r6 = 1024 ; R6_w=1024 1: (b7) r7 = 0 ; R7_w=0 2: (b7) r8 = 0 ; R8_w=0 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 4: (97) r6 %= 1025 ; R6_w=scalar() 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff80000000; 0x7fffffff),u32_min=-2147483648) R9_w=-2147483648 7: (97) r6 %= 1 ; R6_w=scalar() 8: (b7) r9 = 0 ; R9=0 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 10: (b7) r6 = 0 ; R6_w=0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 9 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 20: (95) exit from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=0 22: (27) r6 *= 8192 ; R6_w=0 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 19 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? last_idx 18 first_idx 9 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 regs=40 stack=0 before 10: (b7) r6 = 0 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 27: (95) exit from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 frame 0: propagating r6 last_idx 19 first_idx 11 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 last_idx 9 first_idx 9 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 parent didn't have regs=240 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=P0 R10=fp0 last_idx 8 first_idx 0 regs=240 stack=0 before 8: (b7) r9 = 0 regs=40 stack=0 before 7: (97) r6 %= 1 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 19: safe from 6 to 9: R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 9: (bd) if r6 <= r9 goto pc+1 last_idx 9 first_idx 0 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 last_idx 9 first_idx 0 regs=200 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 11: R6=scalar(umax=18446744071562067968) R9=-2147483648 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0_w=map_value_or_null(id=3,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0_w=0 20: (95) exit from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=scalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=scalar(umax=18014398507384832,var_off=(0x0; 0x3fffffffffffff)) 22: (27) r6 *= 8192 ; R6_w=scalar(smax=9223372036854767616,umax=18446744073709543424,var_off=(0x0; 0xffffffffffffe000),s32_max=2147475456,u32_max=-8192) 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 21 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 parent didn't have regs=40 stack=0 marks: R0_rw=map_value(off=0,ks=4,vs=48,imm=0) R6_r=Pscalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? last_idx 19 first_idx 11 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 last_idx 9 first_idx 0 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 regs=240 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 math between map_value pointer and register with unbounded min value is not allowed verification time 886 usec stack depth 4 processed 49 insns (limit 1000000) max_states_per_insn 1 total_states 5 peak_states 5 mark_read 2 Fixes: b5dc0163d8fd ("bpf: precise scalar_value tracking") Reported-by: Juan Jose Lopez Jaimez Reported-by: Meador Inge Reported-by: Simon Scannell Reported-by: Nenad Stojanovski Signed-off-by: Daniel Borkmann Co-developed-by: Andrii Nakryiko Signed-off-by: Andrii Nakryiko Reviewed-by: John Fastabend Reviewed-by: Juan Jose Lopez Jaimez Reviewed-by: Meador Inge Reviewed-by: Simon Scannell Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e5f1ebe67d7..5a96a9dd51e4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1931,6 +1931,21 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, } } else if (opcode == BPF_EXIT) { return -ENOTSUPP; + } else if (BPF_SRC(insn->code) == BPF_X) { + if (!(*reg_mask & (dreg | sreg))) + return 0; + /* dreg sreg + * Both dreg and sreg need precision before + * this insn. If only sreg was marked precise + * before it would be equally necessary to + * propagate it to dreg. + */ + *reg_mask |= (sreg | dreg); + /* else dreg K + * Only dreg still needs precision before + * this insn, so for the K-based conditional + * there is nothing new to be marked. + */ } } else if (class == BPF_LD) { if (!(*reg_mask & dreg)) From 9a8dbfd7f3e5c3066b2a4fb0eab13b852b087e9b Mon Sep 17 00:00:00 2001 From: Sebastian Basierski Date: Mon, 17 Apr 2023 13:53:45 -0700 Subject: [PATCH 2603/4345] e1000e: Disable TSO on i219-LM card to increase speed [ Upstream commit 67d47b95119ad589b0a0b16b88b1dd9a04061ced ] While using i219-LM card currently it was only possible to achieve about 60% of maximum speed due to regression introduced in Linux 5.8. This was caused by TSO not being disabled by default despite commit f29801030ac6 ("e1000e: Disable TSO for buffer overrun workaround"). Fix that by disabling TSO during driver probe. Fixes: f29801030ac6 ("e1000e: Disable TSO for buffer overrun workaround") Signed-off-by: Sebastian Basierski Signed-off-by: Mateusz Palczewski Tested-by: Naama Meir Signed-off-by: Tony Nguyen Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230417205345.1030801-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/e1000e/netdev.c | 51 +++++++++++----------- 1 file changed, 26 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index ae0c9aaab48d..b700663a634d 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5294,31 +5294,6 @@ static void e1000_watchdog_task(struct work_struct *work) ew32(TARC(0), tarc0); } - /* disable TSO for pcie and 10/100 speeds, to avoid - * some hardware issues - */ - if (!(adapter->flags & FLAG_TSO_FORCE)) { - switch (adapter->link_speed) { - case SPEED_10: - case SPEED_100: - e_info("10/100 speed: disabling TSO\n"); - netdev->features &= ~NETIF_F_TSO; - netdev->features &= ~NETIF_F_TSO6; - break; - case SPEED_1000: - netdev->features |= NETIF_F_TSO; - netdev->features |= NETIF_F_TSO6; - break; - default: - /* oops */ - break; - } - if (hw->mac.type == e1000_pch_spt) { - netdev->features &= ~NETIF_F_TSO; - netdev->features &= ~NETIF_F_TSO6; - } - } - /* enable transmits in the hardware, need to do this * after setting TARC(0) */ @@ -7477,6 +7452,32 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_RXCSUM | NETIF_F_HW_CSUM); + /* disable TSO for pcie and 10/100 speeds to avoid + * some hardware issues and for i219 to fix transfer + * speed being capped at 60% + */ + if (!(adapter->flags & FLAG_TSO_FORCE)) { + switch (adapter->link_speed) { + case SPEED_10: + case SPEED_100: + e_info("10/100 speed: disabling TSO\n"); + netdev->features &= ~NETIF_F_TSO; + netdev->features &= ~NETIF_F_TSO6; + break; + case SPEED_1000: + netdev->features |= NETIF_F_TSO; + netdev->features |= NETIF_F_TSO6; + break; + default: + /* oops */ + break; + } + if (hw->mac.type == e1000_pch_spt) { + netdev->features &= ~NETIF_F_TSO; + netdev->features &= ~NETIF_F_TSO6; + } + } + /* Set user-changeable features (subset of all device features) */ netdev->hw_features = netdev->features; netdev->hw_features |= NETIF_F_RXFCS; From 37882b203a2d206cfab4fb9e1ade4374d0db0540 Mon Sep 17 00:00:00 2001 From: Douglas Raillard Date: Mon, 6 Mar 2023 12:25:49 +0000 Subject: [PATCH 2604/4345] f2fs: Fix f2fs_truncate_partial_nodes ftrace event [ Upstream commit 0b04d4c0542e8573a837b1d81b94209e48723b25 ] Fix the nid_t field so that its size is correctly reported in the text format embedded in trace.dat files. As it stands, it is reported as being of size 4: field:nid_t nid[3]; offset:24; size:4; signed:0; Instead of 12: field:nid_t nid[3]; offset:24; size:12; signed:0; This also fixes the reported offset of subsequent fields so that they match with the actual struct layout. Signed-off-by: Douglas Raillard Reviewed-by: Mukesh Ojha Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- include/trace/events/f2fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index df293bc7f03b..e8cd19e91de1 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -513,7 +513,7 @@ TRACE_EVENT(f2fs_truncate_partial_nodes, TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) - __field(nid_t, nid[3]) + __array(nid_t, nid, 3) __field(int, depth) __field(int, err) ), From 8b44a83a16806f4cc4330562648e10c5ae0eb706 Mon Sep 17 00:00:00 2001 From: Jonathan Denose Date: Fri, 17 Mar 2023 03:19:51 -0700 Subject: [PATCH 2605/4345] Input: i8042 - add quirk for Fujitsu Lifebook A574/H [ Upstream commit f5bad62f9107b701a6def7cac1f5f65862219b83 ] Fujitsu Lifebook A574/H requires the nomux option to properly probe the touchpad, especially when waking from sleep. Signed-off-by: Jonathan Denose Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20230303152623.45859-1-jdenose@google.com Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/serio/i8042-x86ia64io.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 65c0081838e3..9dcdf21c50bd 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -601,6 +601,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, + { + /* Fujitsu Lifebook A574/H */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "FMVA0501PZ"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, { /* Gigabyte M912 */ .matches = { From 01bd481b1b9430bb16cbb05b25b7c87eb2514111 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Wed, 8 Mar 2023 11:59:33 -0800 Subject: [PATCH 2606/4345] selftests: sigaltstack: fix -Wuninitialized [ Upstream commit 05107edc910135d27fe557267dc45be9630bf3dd ] Building sigaltstack with clang via: $ ARCH=x86 make LLVM=1 -C tools/testing/selftests/sigaltstack/ produces the following warning: warning: variable 'sp' is uninitialized when used here [-Wuninitialized] if (sp < (unsigned long)sstack || ^~ Clang expects these to be declared at global scope; we've fixed this in the kernel proper by using the macro `current_stack_pointer`. This is defined in different headers for different target architectures, so just create a new header that defines the arch-specific register names for the stack pointer register, and define it for more targets (at least the ones that support current_stack_pointer/ARCH_HAS_CURRENT_STACK_POINTER). Reported-by: Linux Kernel Functional Testing Link: https://lore.kernel.org/lkml/CA+G9fYsi3OOu7yCsMutpzKDnBMAzJBCPimBp86LhGBa0eCnEpA@mail.gmail.com/ Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Tested-by: Linux Kernel Functional Testing Tested-by: Anders Roxell Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- .../sigaltstack/current_stack_pointer.h | 23 +++++++++++++++++++ tools/testing/selftests/sigaltstack/sas.c | 7 +----- 2 files changed, 24 insertions(+), 6 deletions(-) create mode 100644 tools/testing/selftests/sigaltstack/current_stack_pointer.h diff --git a/tools/testing/selftests/sigaltstack/current_stack_pointer.h b/tools/testing/selftests/sigaltstack/current_stack_pointer.h new file mode 100644 index 000000000000..ea9bdf3a90b1 --- /dev/null +++ b/tools/testing/selftests/sigaltstack/current_stack_pointer.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#if __alpha__ +register unsigned long sp asm("$30"); +#elif __arm__ || __aarch64__ || __csky__ || __m68k__ || __mips__ || __riscv +register unsigned long sp asm("sp"); +#elif __i386__ +register unsigned long sp asm("esp"); +#elif __loongarch64 +register unsigned long sp asm("$sp"); +#elif __ppc__ +register unsigned long sp asm("r1"); +#elif __s390x__ +register unsigned long sp asm("%15"); +#elif __sh__ +register unsigned long sp asm("r15"); +#elif __x86_64__ +register unsigned long sp asm("rsp"); +#elif __XTENSA__ +register unsigned long sp asm("a1"); +#else +#error "implement current_stack_pointer equivalent" +#endif diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index 8934a3766d20..41646c22384a 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -19,6 +19,7 @@ #include #include "../kselftest.h" +#include "current_stack_pointer.h" #ifndef SS_AUTODISARM #define SS_AUTODISARM (1U << 31) @@ -40,12 +41,6 @@ void my_usr1(int sig, siginfo_t *si, void *u) stack_t stk; struct stk_data *p; -#if __s390x__ - register unsigned long sp asm("%15"); -#else - register unsigned long sp asm("sp"); -#endif - if (sp < (unsigned long)sstack || sp >= (unsigned long)sstack + SIGSTKSZ) { ksft_exit_fail_msg("SP is not on sigaltstack\n"); From 24ddcc6a635b01a8fa2f320461011e67c0ea5abc Mon Sep 17 00:00:00 2001 From: Tomas Henzl Date: Fri, 24 Mar 2023 14:52:49 +0100 Subject: [PATCH 2607/4345] scsi: megaraid_sas: Fix fw_crash_buffer_show() [ Upstream commit 0808ed6ebbc292222ca069d339744870f6d801da ] If crash_dump_buf is not allocated then crash dump can't be available. Replace logical 'and' with 'or'. Signed-off-by: Tomas Henzl Link: https://lore.kernel.org/r/20230324135249.9733-1-thenzl@redhat.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/megaraid/megaraid_sas_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 84a2e9292fd0..b5a74b237fd2 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3248,7 +3248,7 @@ fw_crash_buffer_show(struct device *cdev, spin_lock_irqsave(&instance->crashdump_lock, flags); buff_offset = instance->fw_crash_buffer_offset; - if (!instance->crash_dump_buf && + if (!instance->crash_dump_buf || !((instance->fw_crash_state == AVAILABLE) || (instance->fw_crash_state == COPYING))) { dev_err(&instance->pdev->dev, From b33f28ea45e9eb0f84e7bcc0ddc0d2d06a9acedb Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 22 Mar 2023 11:22:11 +0900 Subject: [PATCH 2608/4345] scsi: core: Improve scsi_vpd_inquiry() checks [ Upstream commit f0aa59a33d2ac2267d260fe21eaf92500df8e7b4 ] Some USB-SATA adapters have broken behavior when an unsupported VPD page is probed: Depending on the VPD page number, a 4-byte header with a valid VPD page number but with a 0 length is returned. Currently, scsi_vpd_inquiry() only checks that the page number is valid to determine if the page is valid, which results in receiving only the 4-byte header for the non-existent page. This error manifests itself very often with page 0xb9 for the Concurrent Positioning Ranges detection done by sd_read_cpr(), resulting in the following error message: sd 0:0:0:0: [sda] Invalid Concurrent Positioning Ranges VPD page Prevent such misleading error message by adding a check in scsi_vpd_inquiry() to verify that the page length is not 0. Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20230322022211.116327-1-damien.lemoal@opensource.wdc.com Reviewed-by: Benjamin Block Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 6ad834d61d4c..d6c25a88cebc 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -317,11 +317,18 @@ static int scsi_vpd_inquiry(struct scsi_device *sdev, unsigned char *buffer, if (result) return -EIO; - /* Sanity check that we got the page back that we asked for */ + /* + * Sanity check that we got the page back that we asked for and that + * the page size is not 0. + */ if (buffer[1] != page) return -EIO; - return get_unaligned_be16(&buffer[2]) + 4; + result = get_unaligned_be16(&buffer[2]); + if (!result) + return -EIO; + + return result + 4; } /** From a36246a7480d9590b9b790a6b5b3ac95f6e41833 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Thu, 23 Mar 2023 20:48:41 +0100 Subject: [PATCH 2609/4345] net: dsa: b53: mmap: add phy ops MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 45977e58ce65ed0459edc9a0466d9dfea09463f5 ] Implement phy_read16() and phy_write16() ops for B53 MMAP to avoid accessing B53_PORT_MII_PAGE registers which hangs the device. This access should be done through the MDIO Mux bus controller. Signed-off-by: Álvaro Fernández Rojas Acked-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/b53/b53_mmap.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c index c628d0980c0b..1d52cb3e46d5 100644 --- a/drivers/net/dsa/b53/b53_mmap.c +++ b/drivers/net/dsa/b53/b53_mmap.c @@ -215,6 +215,18 @@ static int b53_mmap_write64(struct b53_device *dev, u8 page, u8 reg, return 0; } +static int b53_mmap_phy_read16(struct b53_device *dev, int addr, int reg, + u16 *value) +{ + return -EIO; +} + +static int b53_mmap_phy_write16(struct b53_device *dev, int addr, int reg, + u16 value) +{ + return -EIO; +} + static const struct b53_io_ops b53_mmap_ops = { .read8 = b53_mmap_read8, .read16 = b53_mmap_read16, @@ -226,6 +238,8 @@ static const struct b53_io_ops b53_mmap_ops = { .write32 = b53_mmap_write32, .write48 = b53_mmap_write48, .write64 = b53_mmap_write64, + .phy_read16 = b53_mmap_phy_read16, + .phy_write16 = b53_mmap_phy_write16, }; static int b53_mmap_probe(struct platform_device *pdev) From 8c746b665089f9da50c34fc0369aa7d7f7c5e609 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 6 Mar 2023 12:31:30 +0100 Subject: [PATCH 2610/4345] s390/ptrace: fix PTRACE_GET_LAST_BREAK error handling [ Upstream commit f9bbf25e7b2b74b52b2f269216a92657774f239c ] Return -EFAULT if put_user() for the PTRACE_GET_LAST_BREAK request fails, instead of silently ignoring it. Reviewed-by: Sven Schnelle Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Sasha Levin --- arch/s390/kernel/ptrace.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index a76dd27fb2e8..3009bb527252 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -500,9 +500,7 @@ long arch_ptrace(struct task_struct *child, long request, } return 0; case PTRACE_GET_LAST_BREAK: - put_user(child->thread.last_break, - (unsigned long __user *) data); - return 0; + return put_user(child->thread.last_break, (unsigned long __user *)data); case PTRACE_ENABLE_TE: if (!MACHINE_HAS_TE) return -EIO; @@ -854,9 +852,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, } return 0; case PTRACE_GET_LAST_BREAK: - put_user(child->thread.last_break, - (unsigned int __user *) data); - return 0; + return put_user(child->thread.last_break, (unsigned int __user *)data); } return compat_ptrace_request(child, request, addr, data); } From 0c9cbfc951c4c4f686df1aee2aceb93935eea729 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 20 Mar 2023 15:33:34 +0200 Subject: [PATCH 2611/4345] nvme-tcp: fix a possible UAF when failing to allocate an io queue [ Upstream commit 88eaba80328b31ef81813a1207b4056efd7006a6 ] When we allocate a nvme-tcp queue, we set the data_ready callback before we actually need to use it. This creates the potential that if a stray controller sends us data on the socket before we connect, we can trigger the io_work and start consuming the socket. In this case reported: we failed to allocate one of the io queues, and as we start releasing the queues that we already allocated, we get a UAF [1] from the io_work which is running before it should really. Fix this by setting the socket ops callbacks only before we start the queue, so that we can't accidentally schedule the io_work in the initialization phase before the queue started. While we are at it, rename nvme_tcp_restore_sock_calls to pair with nvme_tcp_setup_sock_ops. [1]: [16802.107284] nvme nvme4: starting error recovery [16802.109166] nvme nvme4: Reconnecting in 10 seconds... [16812.173535] nvme nvme4: failed to connect socket: -111 [16812.173745] nvme nvme4: Failed reconnect attempt 1 [16812.173747] nvme nvme4: Reconnecting in 10 seconds... [16822.413555] nvme nvme4: failed to connect socket: -111 [16822.413762] nvme nvme4: Failed reconnect attempt 2 [16822.413765] nvme nvme4: Reconnecting in 10 seconds... [16832.661274] nvme nvme4: creating 32 I/O queues. [16833.919887] BUG: kernel NULL pointer dereference, address: 0000000000000088 [16833.920068] nvme nvme4: Failed reconnect attempt 3 [16833.920094] #PF: supervisor write access in kernel mode [16833.920261] nvme nvme4: Reconnecting in 10 seconds... [16833.920368] #PF: error_code(0x0002) - not-present page [16833.921086] Workqueue: nvme_tcp_wq nvme_tcp_io_work [nvme_tcp] [16833.921191] RIP: 0010:_raw_spin_lock_bh+0x17/0x30 ... [16833.923138] Call Trace: [16833.923271] [16833.923402] lock_sock_nested+0x1e/0x50 [16833.923545] nvme_tcp_try_recv+0x40/0xa0 [nvme_tcp] [16833.923685] nvme_tcp_io_work+0x68/0xa0 [nvme_tcp] [16833.923824] process_one_work+0x1e8/0x390 [16833.923969] worker_thread+0x53/0x3d0 [16833.924104] ? process_one_work+0x390/0x390 [16833.924240] kthread+0x124/0x150 [16833.924376] ? set_kthread_struct+0x50/0x50 [16833.924518] ret_from_fork+0x1f/0x30 [16833.924655] Reported-by: Yanjun Zhang Signed-off-by: Sagi Grimberg Tested-by: Yanjun Zhang Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/tcp.c | 46 +++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 20 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 57df87def8c3..e6147a9220f9 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1535,22 +1535,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, if (ret) goto err_init_connect; - queue->rd_enabled = true; set_bit(NVME_TCP_Q_ALLOCATED, &queue->flags); - nvme_tcp_init_recv_ctx(queue); - - write_lock_bh(&queue->sock->sk->sk_callback_lock); - queue->sock->sk->sk_user_data = queue; - queue->state_change = queue->sock->sk->sk_state_change; - queue->data_ready = queue->sock->sk->sk_data_ready; - queue->write_space = queue->sock->sk->sk_write_space; - queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; - queue->sock->sk->sk_state_change = nvme_tcp_state_change; - queue->sock->sk->sk_write_space = nvme_tcp_write_space; -#ifdef CONFIG_NET_RX_BUSY_POLL - queue->sock->sk->sk_ll_usec = 1; -#endif - write_unlock_bh(&queue->sock->sk->sk_callback_lock); return 0; @@ -1569,7 +1554,7 @@ err_destroy_mutex: return ret; } -static void nvme_tcp_restore_sock_calls(struct nvme_tcp_queue *queue) +static void nvme_tcp_restore_sock_ops(struct nvme_tcp_queue *queue) { struct socket *sock = queue->sock; @@ -1584,7 +1569,7 @@ static void nvme_tcp_restore_sock_calls(struct nvme_tcp_queue *queue) static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue) { kernel_sock_shutdown(queue->sock, SHUT_RDWR); - nvme_tcp_restore_sock_calls(queue); + nvme_tcp_restore_sock_ops(queue); cancel_work_sync(&queue->io_work); } @@ -1599,21 +1584,42 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) mutex_unlock(&queue->queue_lock); } +static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue) +{ + write_lock_bh(&queue->sock->sk->sk_callback_lock); + queue->sock->sk->sk_user_data = queue; + queue->state_change = queue->sock->sk->sk_state_change; + queue->data_ready = queue->sock->sk->sk_data_ready; + queue->write_space = queue->sock->sk->sk_write_space; + queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; + queue->sock->sk->sk_state_change = nvme_tcp_state_change; + queue->sock->sk->sk_write_space = nvme_tcp_write_space; +#ifdef CONFIG_NET_RX_BUSY_POLL + queue->sock->sk->sk_ll_usec = 1; +#endif + write_unlock_bh(&queue->sock->sk->sk_callback_lock); +} + static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct nvme_tcp_queue *queue = &ctrl->queues[idx]; int ret; + queue->rd_enabled = true; + nvme_tcp_init_recv_ctx(queue); + nvme_tcp_setup_sock_ops(queue); + if (idx) ret = nvmf_connect_io_queue(nctrl, idx, false); else ret = nvmf_connect_admin_queue(nctrl); if (!ret) { - set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags); + set_bit(NVME_TCP_Q_LIVE, &queue->flags); } else { - if (test_bit(NVME_TCP_Q_ALLOCATED, &ctrl->queues[idx].flags)) - __nvme_tcp_stop_queue(&ctrl->queues[idx]); + if (test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) + __nvme_tcp_stop_queue(queue); dev_err(nctrl->device, "failed to connect queue: %d ret=%d\n", idx, ret); } From c215c636819ce09c336f8c27f1495e3b958208f3 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 29 Mar 2023 10:02:59 +0200 Subject: [PATCH 2612/4345] xen/netback: use same error messages for same errors [ Upstream commit 2eca98e5b24d01c02b46c67be05a5f98cc9789b1 ] Issue the same error message in case an illegal page boundary crossing has been detected in both cases where this is tested. Suggested-by: Jan Beulich Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Link: https://lore.kernel.org/r/20230329080259.14823-1-jgross@suse.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/xen-netback/netback.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 67614e7166ac..379ac9ca60b7 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -996,10 +996,8 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, /* No crossing a page as the payload mustn't fragment. */ if (unlikely((txreq.offset + txreq.size) > XEN_PAGE_SIZE)) { - netdev_err(queue->vif->dev, - "txreq.offset: %u, size: %u, end: %lu\n", - txreq.offset, txreq.size, - (unsigned long)(txreq.offset&~XEN_PAGE_MASK) + txreq.size); + netdev_err(queue->vif->dev, "Cross page boundary, txreq.offset: %u, size: %u\n", + txreq.offset, txreq.size); xenvif_fatal_tx_err(queue->vif); break; } From a4e800a7bd67490722c8466472c7ad03e3754902 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 25 Aug 2021 09:54:47 +0530 Subject: [PATCH 2613/4345] powerpc/doc: Fix htmldocs errors commit f50da6edbf1ebf35dd8070847bfab5cb988d472b upstream. Fix make htmldocs related errors with the newly added associativity.rst doc file. Reported-by: Stephen Rothwell Tested-by: Stephen Rothwell # build test Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210825042447.106219-1-aneesh.kumar@linux.ibm.com Cc: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- Documentation/powerpc/associativity.rst | 29 +++++++++++++------------ Documentation/powerpc/index.rst | 1 + 2 files changed, 16 insertions(+), 14 deletions(-) diff --git a/Documentation/powerpc/associativity.rst b/Documentation/powerpc/associativity.rst index 07e7dd3d6c87..4d01c7368561 100644 --- a/Documentation/powerpc/associativity.rst +++ b/Documentation/powerpc/associativity.rst @@ -1,6 +1,6 @@ ============================ NUMA resource associativity -============================= +============================ Associativity represents the groupings of the various platform resources into domains of substantially similar mean performance relative to resources outside @@ -20,11 +20,11 @@ A value of 1 indicates the usage of Form 1 associativity. For Form 2 associativi bit 2 of byte 5 in the "ibm,architecture-vec-5" property is used. Form 0 ------ +------ Form 0 associativity supports only two NUMA distances (LOCAL and REMOTE). Form 1 ------ +------ With Form 1 a combination of ibm,associativity-reference-points, and ibm,associativity device tree properties are used to determine the NUMA distance between resource groups/domains. @@ -78,17 +78,18 @@ numa-lookup-index-table. For ex: ibm,numa-lookup-index-table = <3 0 8 40>; -ibm,numa-distace-table = <9>, /bits/ 8 < 10 20 80 - 20 10 160 - 80 160 10>; - | 0 8 40 ---|------------ - | -0 | 10 20 80 - | -8 | 20 10 160 - | -40| 80 160 10 +ibm,numa-distace-table = <9>, /bits/ 8 < 10 20 80 20 10 160 80 160 10>; + +:: + + | 0 8 40 + --|------------ + | + 0 | 10 20 80 + | + 8 | 20 10 160 + | + 40| 80 160 10 A possible "ibm,associativity" property for resources in node 0, 8 and 40 diff --git a/Documentation/powerpc/index.rst b/Documentation/powerpc/index.rst index 6ec64b0d5257..4663b72caab8 100644 --- a/Documentation/powerpc/index.rst +++ b/Documentation/powerpc/index.rst @@ -7,6 +7,7 @@ powerpc .. toctree:: :maxdepth: 1 + associativity booting bootwrapper cpu_families From 77ac8f2ad4adcddfba0d539030bbeb53b35f6099 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 9 Apr 2021 10:27:43 -0700 Subject: [PATCH 2614/4345] xfs: drop submit side trans alloc for append ioends commit 7cd3099f4925d7c15887d1940ebd65acd66100f5 upstream. Per-inode ioend completion batching has a log reservation deadlock vector between preallocated append transactions and transactions that are acquired at completion time for other purposes (i.e., unwritten extent conversion or COW fork remaps). For example, if the ioend completion workqueue task executes on a batch of ioends that are sorted such that an append ioend sits at the tail, it's possible for the outstanding append transaction reservation to block allocation of transactions required to process preceding ioends in the list. Append ioend completion is historically the common path for on-disk inode size updates. While file extending writes may have completed sometime earlier, the on-disk inode size is only updated after successful writeback completion. These transactions are preallocated serially from writeback context to mitigate concurrency and associated log reservation pressure across completions processed by multi-threaded workqueue tasks. However, now that delalloc blocks unconditionally map to unwritten extents at physical block allocation time, size updates via append ioends are relatively rare. This means that inode size updates most commonly occur as part of the preexisting completion time transaction to convert unwritten extents. As a result, there is no longer a strong need to preallocate size update transactions. Remove the preallocation of inode size update transactions to avoid the ioend completion processing log reservation deadlock. Instead, continue to send all potential size extending ioends to workqueue context for completion and allocate the transaction from that context. This ensures that no outstanding log reservation is owned by the ioend completion worker task when it begins to process ioends. Signed-off-by: Brian Foster Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reported-by: Christian Theune Link: https://lore.kernel.org/linux-xfs/CAOQ4uxjj2UqA0h4Y31NbmpHksMhVrXfXjLG4Tnz3zq_UR-3gSA@mail.gmail.com/ Signed-off-by: Amir Goldstein Acked-by: Darrick J. Wong Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_aops.c | 45 +++------------------------------------------ 1 file changed, 3 insertions(+), 42 deletions(-) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 953de843d9c3..e341d6531e68 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -39,33 +39,6 @@ static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) XFS_I(ioend->io_inode)->i_d.di_size; } -STATIC int -xfs_setfilesize_trans_alloc( - struct iomap_ioend *ioend) -{ - struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount; - struct xfs_trans *tp; - int error; - - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp); - if (error) - return error; - - ioend->io_private = tp; - - /* - * We may pass freeze protection with a transaction. So tell lockdep - * we released it. - */ - __sb_writers_release(ioend->io_inode->i_sb, SB_FREEZE_FS); - /* - * We hand off the transaction to the completion thread now, so - * clear the flag here. - */ - xfs_trans_clear_context(tp); - return 0; -} - /* * Update on-disk file size now that data has been written to disk. */ @@ -191,12 +164,10 @@ xfs_end_ioend( error = xfs_reflink_end_cow(ip, offset, size); else if (ioend->io_type == IOMAP_UNWRITTEN) error = xfs_iomap_write_unwritten(ip, offset, size, false); - else - ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_private); + if (!error && xfs_ioend_is_append(ioend)) + error = xfs_setfilesize(ip, ioend->io_offset, ioend->io_size); done: - if (ioend->io_private) - error = xfs_setfilesize_ioend(ioend, error); iomap_finish_ioends(ioend, error); memalloc_nofs_restore(nofs_flag); } @@ -246,7 +217,7 @@ xfs_end_io( static inline bool xfs_ioend_needs_workqueue(struct iomap_ioend *ioend) { - return ioend->io_private || + return xfs_ioend_is_append(ioend) || ioend->io_type == IOMAP_UNWRITTEN || (ioend->io_flags & IOMAP_F_SHARED); } @@ -259,8 +230,6 @@ xfs_end_bio( struct xfs_inode *ip = XFS_I(ioend->io_inode); unsigned long flags; - ASSERT(xfs_ioend_needs_workqueue(ioend)); - spin_lock_irqsave(&ip->i_ioend_lock, flags); if (list_empty(&ip->i_ioend_list)) WARN_ON_ONCE(!queue_work(ip->i_mount->m_unwritten_workqueue, @@ -510,14 +479,6 @@ xfs_prepare_ioend( ioend->io_offset, ioend->io_size); } - /* Reserve log space if we might write beyond the on-disk inode size. */ - if (!status && - ((ioend->io_flags & IOMAP_F_SHARED) || - ioend->io_type != IOMAP_UNWRITTEN) && - xfs_ioend_is_append(ioend) && - !ioend->io_private) - status = xfs_setfilesize_trans_alloc(ioend); - memalloc_nofs_restore(nofs_flag); if (xfs_ioend_needs_workqueue(ioend)) From 09daff9c3cd77c4c2e195de82a2082ee956db0e0 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Mon, 3 Apr 2023 21:14:55 -0400 Subject: [PATCH 2615/4345] iio: light: tsl2772: fix reading proximity-diodes from device tree commit b1cb00d51e361cf5af93649917d9790e1623647e upstream. tsl2772_read_prox_diodes() will correctly parse the properties from device tree to determine which proximity diode(s) to read from, however it didn't actually set this value on the struct tsl2772_settings. Let's go ahead and fix that. Reported-by: Tom Rix Link: https://lore.kernel.org/lkml/20230327120823.1369700-1-trix@redhat.com/ Fixes: 94cd1113aaa0 ("iio: tsl2772: add support for reading proximity led settings from device tree") Signed-off-by: Brian Masney Link: https://lore.kernel.org/r/20230404011455.339454-1-bmasney@redhat.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/light/tsl2772.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/light/tsl2772.c b/drivers/iio/light/tsl2772.c index d79205361dfa..ff33ad371420 100644 --- a/drivers/iio/light/tsl2772.c +++ b/drivers/iio/light/tsl2772.c @@ -606,6 +606,7 @@ static int tsl2772_read_prox_diodes(struct tsl2772_chip *chip) return -EINVAL; } } + chip->settings.prox_diode = prox_diode_mask; return 0; } From 2c90ef37151f9143c1bd18d8f76563f817632dbd Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Tue, 18 Apr 2023 02:35:13 +0900 Subject: [PATCH 2616/4345] nilfs2: initialize unused bytes in segment summary blocks commit ef832747a82dfbc22a3702219cc716f449b24e4a upstream. Syzbot still reports uninit-value in nilfs_add_checksums_on_logs() for KMSAN enabled kernels after applying commit 7397031622e0 ("nilfs2: initialize "struct nilfs_binfo_dat"->bi_pad field"). This is because the unused bytes at the end of each block in segment summaries are not initialized. So this fixes the issue by padding the unused bytes with null bytes. Link: https://lkml.kernel.org/r/20230417173513.12598-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Reported-by: syzbot+048585f3f4227bb2b49b@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=048585f3f4227bb2b49b Cc: Alexander Potapenko Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/segment.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 5e835bbf1ffb..fff2cdc69e5e 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -435,6 +435,23 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci) return 0; } +/** + * nilfs_segctor_zeropad_segsum - zero pad the rest of the segment summary area + * @sci: segment constructor object + * + * nilfs_segctor_zeropad_segsum() zero-fills unallocated space at the end of + * the current segment summary block. + */ +static void nilfs_segctor_zeropad_segsum(struct nilfs_sc_info *sci) +{ + struct nilfs_segsum_pointer *ssp; + + ssp = sci->sc_blk_cnt > 0 ? &sci->sc_binfo_ptr : &sci->sc_finfo_ptr; + if (ssp->offset < ssp->bh->b_size) + memset(ssp->bh->b_data + ssp->offset, 0, + ssp->bh->b_size - ssp->offset); +} + static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) { sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks; @@ -443,6 +460,7 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) * The current segment is filled up * (internal code) */ + nilfs_segctor_zeropad_segsum(sci); sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg); return nilfs_segctor_reset_segment_buffer(sci); } @@ -547,6 +565,7 @@ static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci, goto retry; } if (unlikely(required)) { + nilfs_segctor_zeropad_segsum(sci); err = nilfs_segbuf_extend_segsum(segbuf); if (unlikely(err)) goto failed; @@ -1536,6 +1555,7 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA); sci->sc_stage = prev_stage; } + nilfs_segctor_zeropad_segsum(sci); nilfs_segctor_truncate_segments(sci, sci->sc_curseg, nilfs->ns_sufile); return 0; From e10a6d88ae9b81413da6a6d415c2b705100dd872 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 1 Apr 2023 22:03:27 +0200 Subject: [PATCH 2617/4345] memstick: fix memory leak if card device is never registered commit 4b6d621c9d859ff89e68cebf6178652592676013 upstream. When calling dev_set_name() memory is allocated for the name for the struct device. Once that structure device is registered, or attempted to be registerd, with the driver core, the driver core will handle cleaning up that memory when the device is removed from the system. Unfortunatly for the memstick code, there is an error path that causes the struct device to never be registered, and so the memory allocated in dev_set_name will be leaked. Fix that leak by manually freeing it right before the memory for the device is freed. Cc: Maxim Levitsky Cc: Alex Dubov Cc: Ulf Hansson Cc: "Rafael J. Wysocki" Cc: Hans de Goede Cc: Kay Sievers Cc: linux-mmc@vger.kernel.org Fixes: 0252c3b4f018 ("memstick: struct device - replace bus_id with dev_name(), dev_set_name()") Cc: stable Co-developed-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman Co-developed-by: Mirsad Goran Todorovac Signed-off-by: Mirsad Goran Todorovac Link: https://lore.kernel.org/r/20230401200327.16800-1-gregkh@linuxfoundation.org Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/memstick/core/memstick.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index 12bc3f5a6cbb..1c7a9dcfed65 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -412,6 +412,7 @@ static struct memstick_dev *memstick_alloc_card(struct memstick_host *host) return card; err_out: host->card = old_card; + kfree_const(card->dev.kobj.name); kfree(card); return NULL; } @@ -470,8 +471,10 @@ static void memstick_check(struct work_struct *work) put_device(&card->dev); host->card = NULL; } - } else + } else { + kfree_const(card->dev.kobj.name); kfree(card); + } } out_power_off: From c61928fcca27a5ed5b3dde9930023182015de2ae Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Fri, 17 Feb 2023 17:21:54 +0100 Subject: [PATCH 2618/4345] kernel/sys.c: fix and improve control flow in __sys_setres[ug]id() commit 659c0ce1cb9efc7f58d380ca4bb2a51ae9e30553 upstream. Linux Security Modules (LSMs) that implement the "capable" hook will usually emit an access denial message to the audit log whenever they "block" the current task from using the given capability based on their security policy. The occurrence of a denial is used as an indication that the given task has attempted an operation that requires the given access permission, so the callers of functions that perform LSM permission checks must take care to avoid calling them too early (before it is decided if the permission is actually needed to perform the requested operation). The __sys_setres[ug]id() functions violate this convention by first calling ns_capable_setid() and only then checking if the operation requires the capability or not. It means that any caller that has the capability granted by DAC (task's capability set) but not by MAC (LSMs) will generate a "denied" audit record, even if is doing an operation for which the capability is not required. Fix this by reordering the checks such that ns_capable_setid() is checked last and -EPERM is returned immediately if it returns false. While there, also do two small optimizations: * move the capability check before prepare_creds() and * bail out early in case of a no-op. Link: https://lkml.kernel.org/r/20230217162154.837549-1-omosnace@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Ondrej Mosnacek Cc: Eric W. Biederman Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- kernel/sys.c | 69 ++++++++++++++++++++++++++++++---------------------- 1 file changed, 40 insertions(+), 29 deletions(-) diff --git a/kernel/sys.c b/kernel/sys.c index 9f59cc8ab8f8..bff14910b926 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -634,6 +634,7 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) struct cred *new; int retval; kuid_t kruid, keuid, ksuid; + bool ruid_new, euid_new, suid_new; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); @@ -648,25 +649,29 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) if ((suid != (uid_t) -1) && !uid_valid(ksuid)) return -EINVAL; + old = current_cred(); + + /* check for no-op */ + if ((ruid == (uid_t) -1 || uid_eq(kruid, old->uid)) && + (euid == (uid_t) -1 || (uid_eq(keuid, old->euid) && + uid_eq(keuid, old->fsuid))) && + (suid == (uid_t) -1 || uid_eq(ksuid, old->suid))) + return 0; + + ruid_new = ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && + !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid); + euid_new = euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && + !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid); + suid_new = suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && + !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid); + if ((ruid_new || euid_new || suid_new) && + !ns_capable_setid(old->user_ns, CAP_SETUID)) + return -EPERM; + new = prepare_creds(); if (!new) return -ENOMEM; - old = current_cred(); - - retval = -EPERM; - if (!ns_capable_setid(old->user_ns, CAP_SETUID)) { - if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && - !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) - goto error; - if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && - !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) - goto error; - if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && - !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) - goto error; - } - if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(kruid, old->uid)) { @@ -726,6 +731,7 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) struct cred *new; int retval; kgid_t krgid, kegid, ksgid; + bool rgid_new, egid_new, sgid_new; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); @@ -738,23 +744,28 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) return -EINVAL; + old = current_cred(); + + /* check for no-op */ + if ((rgid == (gid_t) -1 || gid_eq(krgid, old->gid)) && + (egid == (gid_t) -1 || (gid_eq(kegid, old->egid) && + gid_eq(kegid, old->fsgid))) && + (sgid == (gid_t) -1 || gid_eq(ksgid, old->sgid))) + return 0; + + rgid_new = rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && + !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid); + egid_new = egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && + !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid); + sgid_new = sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && + !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid); + if ((rgid_new || egid_new || sgid_new) && + !ns_capable_setid(old->user_ns, CAP_SETGID)) + return -EPERM; + new = prepare_creds(); if (!new) return -ENOMEM; - old = current_cred(); - - retval = -EPERM; - if (!ns_capable_setid(old->user_ns, CAP_SETGID)) { - if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && - !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) - goto error; - if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && - !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) - goto error; - if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && - !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) - goto error; - } if (rgid != (gid_t) -1) new->gid = krgid; From 651b0bf43d6706496c993312c3e86cb858606eba Mon Sep 17 00:00:00 2001 From: Bhavya Kapoor Date: Fri, 17 Mar 2023 14:57:11 +0530 Subject: [PATCH 2619/4345] mmc: sdhci_am654: Set HIGH_SPEED_ENA for SDR12 and SDR25 commit 2265098fd6a6272fde3fd1be5761f2f5895bd99a upstream. Timing Information in Datasheet assumes that HIGH_SPEED_ENA=1 should be set for SDR12 and SDR25 modes. But sdhci_am654 driver clears HIGH_SPEED_ENA register. Thus, Modify sdhci_am654 to not clear HIGH_SPEED_ENA (HOST_CONTROL[2]) bit for SDR12 and SDR25 speed modes. Fixes: e374e87538f4 ("mmc: sdhci_am654: Clear HISPD_ENA in some lower speed modes") Signed-off-by: Bhavya Kapoor Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230317092711.660897-1-b-kapoor@ti.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/sdhci_am654.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index bf2592774165..8e52905458f9 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -351,8 +351,6 @@ static void sdhci_am654_write_b(struct sdhci_host *host, u8 val, int reg) */ case MMC_TIMING_SD_HS: case MMC_TIMING_MMC_HS: - case MMC_TIMING_UHS_SDR12: - case MMC_TIMING_UHS_SDR25: val &= ~SDHCI_CTRL_HISPD; } } From 2523d9d7bb5ca7986ee29b5e0fb66d1221bffbc1 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 5 Apr 2023 11:51:20 -0400 Subject: [PATCH 2620/4345] mm/khugepaged: check again on anon uffd-wp during isolation commit dd47ac428c3f5f3bcabe845f36be870fe6c20784 upstream. Khugepaged collapse an anonymous thp in two rounds of scans. The 2nd round done in __collapse_huge_page_isolate() after hpage_collapse_scan_pmd(), during which all the locks will be released temporarily. It means the pgtable can change during this phase before 2nd round starts. It's logically possible some ptes got wr-protected during this phase, and we can errornously collapse a thp without noticing some ptes are wr-protected by userfault. e1e267c7928f wanted to avoid it but it only did that for the 1st phase, not the 2nd phase. Since __collapse_huge_page_isolate() happens after a round of small page swapins, we don't need to worry on any !present ptes - if it existed khugepaged will already bail out. So we only need to check present ptes with uffd-wp bit set there. This is something I found only but never had a reproducer, I thought it was one caused a bug in Muhammad's recent pagemap new ioctl work, but it turns out it's not the cause of that but an userspace bug. However this seems to still be a real bug even with a very small race window, still worth to have it fixed and copy stable. Link: https://lkml.kernel.org/r/20230405155120.3608140-1-peterx@redhat.com Fixes: e1e267c7928f ("khugepaged: skip collapse if uffd-wp detected") Signed-off-by: Peter Xu Reviewed-by: David Hildenbrand Reviewed-by: Yang Shi Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Mike Rapoport Cc: Nadav Amit Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/khugepaged.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index b77186ec70e9..28e18777ec51 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -622,6 +622,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, result = SCAN_PTE_NON_PRESENT; goto out; } + if (pte_uffd_wp(pteval)) { + result = SCAN_PTE_UFFD_WP; + goto out; + } page = vm_normal_page(vma, address, pteval); if (unlikely(!page)) { result = SCAN_PAGE_NULL; From 5cb1a56ced3080f78da539a7addfa95f25c60fd8 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:34 +0100 Subject: [PATCH 2621/4345] sched/uclamp: Make task_fits_capacity() use util_fits_cpu() commit b48e16a69792b5dc4a09d6807369d11b2970cc36 upstream. So that the new uclamp rules in regard to migration margin and capacity pressure are taken into account correctly. Fixes: a7008c07a568 ("sched/fair: Make task_fits_capacity() consider uclamp restrictions") Co-developed-by: Vincent Guittot Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220804143609.515789-3-qais.yousef@arm.com (cherry picked from commit b48e16a69792b5dc4a09d6807369d11b2970cc36) Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 26 ++++++++++++++++---------- kernel/sched/sched.h | 9 +++++++++ 2 files changed, 25 insertions(+), 10 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 57a58bc48021..89d962e90d1a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4197,10 +4197,12 @@ static inline int util_fits_cpu(unsigned long util, return fits; } -static inline int task_fits_capacity(struct task_struct *p, - unsigned long capacity) +static inline int task_fits_cpu(struct task_struct *p, int cpu) { - return fits_capacity(uclamp_task_util(p), capacity); + unsigned long uclamp_min = uclamp_eff_value(p, UCLAMP_MIN); + unsigned long uclamp_max = uclamp_eff_value(p, UCLAMP_MAX); + unsigned long util = task_util_est(p); + return util_fits_cpu(util, uclamp_min, uclamp_max, cpu); } static inline void update_misfit_status(struct task_struct *p, struct rq *rq) @@ -4213,7 +4215,7 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) return; } - if (task_fits_capacity(p, capacity_of(cpu_of(rq)))) { + if (task_fits_cpu(p, cpu_of(rq))) { rq->misfit_task_load = 0; return; } @@ -7942,7 +7944,7 @@ static int detach_tasks(struct lb_env *env) case migrate_misfit: /* This is not a misfit task */ - if (task_fits_capacity(p, capacity_of(env->src_cpu))) + if (task_fits_cpu(p, env->src_cpu)) goto next; env->imbalance = 0; @@ -8884,6 +8886,10 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd, memset(sgs, 0, sizeof(*sgs)); + /* Assume that task can't fit any CPU of the group */ + if (sd->flags & SD_ASYM_CPUCAPACITY) + sgs->group_misfit_task_load = 1; + for_each_cpu(i, sched_group_span(group)) { struct rq *rq = cpu_rq(i); unsigned int local; @@ -8903,12 +8909,12 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd, if (!nr_running && idle_cpu_without(i, p)) sgs->idle_cpus++; - } + /* Check if task fits in the CPU */ + if (sd->flags & SD_ASYM_CPUCAPACITY && + sgs->group_misfit_task_load && + task_fits_cpu(p, i)) + sgs->group_misfit_task_load = 0; - /* Check if task fits in the group */ - if (sd->flags & SD_ASYM_CPUCAPACITY && - !task_fits_capacity(p, group->sgc->max_capacity)) { - sgs->group_misfit_task_load = 1; } sgs->group_capacity = group->sgc->capacity; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 12c65628801c..3758f98c068c 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2468,6 +2468,15 @@ static inline bool uclamp_is_used(void) return static_branch_likely(&sched_uclamp_used); } #else /* CONFIG_UCLAMP_TASK */ +static inline unsigned long uclamp_eff_value(struct task_struct *p, + enum uclamp_id clamp_id) +{ + if (clamp_id == UCLAMP_MIN) + return 0; + + return SCHED_CAPACITY_SCALE; +} + static inline unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, struct task_struct *p) From 8ca2bf63d946bf443fa0b86a2eaefdf952f8cc29 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:35 +0100 Subject: [PATCH 2622/4345] sched/uclamp: Fix fits_capacity() check in feec() commit 244226035a1f9b2b6c326e55ae5188fab4f428cb upstream. As reported by Yun Hsiang [1], if a task has its uclamp_min >= 0.8 * 1024, it'll always pick the previous CPU because fits_capacity() will always return false in this case. The new util_fits_cpu() logic should handle this correctly for us beside more corner cases where similar failures could occur, like when using UCLAMP_MAX. We open code uclamp_rq_util_with() except for the clamp() part, util_fits_cpu() needs the 'raw' values to be passed to it. Also introduce uclamp_rq_{set, get}() shorthand accessors to get uclamp value for the rq. Makes the code more readable and ensures the right rules (use READ_ONCE/WRITE_ONCE) are respected transparently. [1] https://lists.linaro.org/pipermail/eas-dev/2020-July/001488.html Fixes: 1d42509e475c ("sched/fair: Make EAS wakeup placement consider uclamp restrictions") Reported-by: Yun Hsiang Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220804143609.515789-4-qais.yousef@arm.com (cherry picked from commit 244226035a1f9b2b6c326e55ae5188fab4f428cb) [Fix trivial conflict in kernel/sched/fair.c due to new automatic variables in master vs 5.10] Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/core.c | 10 +++++----- kernel/sched/fair.c | 26 ++++++++++++++++++++++++-- kernel/sched/sched.h | 42 +++++++++++++++++++++++++++++++++++++++--- 3 files changed, 68 insertions(+), 10 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b4bd02d68185..9d6dd14cfd26 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -980,7 +980,7 @@ static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id, if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE)) return; - WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value); + uclamp_rq_set(rq, clamp_id, clamp_value); } static inline @@ -1158,8 +1158,8 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, if (bucket->tasks == 1 || uc_se->value > bucket->value) bucket->value = uc_se->value; - if (uc_se->value > READ_ONCE(uc_rq->value)) - WRITE_ONCE(uc_rq->value, uc_se->value); + if (uc_se->value > uclamp_rq_get(rq, clamp_id)) + uclamp_rq_set(rq, clamp_id, uc_se->value); } /* @@ -1225,7 +1225,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, if (likely(bucket->tasks)) return; - rq_clamp = READ_ONCE(uc_rq->value); + rq_clamp = uclamp_rq_get(rq, clamp_id); /* * Defensive programming: this should never happen. If it happens, * e.g. due to future modification, warn and fixup the expected value. @@ -1233,7 +1233,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, SCHED_WARN_ON(bucket->value > rq_clamp); if (bucket->value >= rq_clamp) { bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value); - WRITE_ONCE(uc_rq->value, bkt_clamp); + uclamp_rq_set(rq, clamp_id, bkt_clamp); } } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 89d962e90d1a..d29fda240ca4 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6802,6 +6802,8 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) { unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; + unsigned long p_util_min = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MIN) : 0; + unsigned long p_util_max = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MAX) : 1024; struct root_domain *rd = cpu_rq(smp_processor_id())->rd; unsigned long cpu_cap, util, base_energy = 0; int cpu, best_energy_cpu = prev_cpu; @@ -6829,6 +6831,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) for (; pd; pd = pd->next) { unsigned long cur_delta, spare_cap, max_spare_cap = 0; + unsigned long rq_util_min, rq_util_max; + unsigned long util_min, util_max; unsigned long base_energy_pd; int max_spare_cap_cpu = -1; @@ -6852,8 +6856,26 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) * much capacity we can get out of the CPU; this is * aligned with schedutil_cpu_util(). */ - util = uclamp_rq_util_with(cpu_rq(cpu), util, p); - if (!fits_capacity(util, cpu_cap)) + if (uclamp_is_used()) { + if (uclamp_rq_is_idle(cpu_rq(cpu))) { + util_min = p_util_min; + util_max = p_util_max; + } else { + /* + * Open code uclamp_rq_util_with() except for + * the clamp() part. Ie: apply max aggregation + * only. util_fits_cpu() logic requires to + * operate on non clamped util but must use the + * max-aggregated uclamp_{min, max}. + */ + rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); + rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + + util_min = max(rq_util_min, p_util_min); + util_max = max(rq_util_max, p_util_max); + } + } + if (!util_fits_cpu(util, util_min, util_max, cpu)) continue; /* Always use prev_cpu as a candidate. */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 3758f98c068c..d4632e50d8b3 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2402,6 +2402,23 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #ifdef CONFIG_UCLAMP_TASK unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); +static inline unsigned long uclamp_rq_get(struct rq *rq, + enum uclamp_id clamp_id) +{ + return READ_ONCE(rq->uclamp[clamp_id].value); +} + +static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id, + unsigned int value) +{ + WRITE_ONCE(rq->uclamp[clamp_id].value, value); +} + +static inline bool uclamp_rq_is_idle(struct rq *rq) +{ + return rq->uclamp_flags & UCLAMP_FLAG_IDLE; +} + /** * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values. * @rq: The rq to clamp against. Must not be NULL. @@ -2437,12 +2454,12 @@ unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, * Ignore last runnable task's max clamp, as this task will * reset it. Similarly, no need to read the rq's min clamp. */ - if (rq->uclamp_flags & UCLAMP_FLAG_IDLE) + if (uclamp_rq_is_idle(rq)) goto out; } - min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value)); - max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value)); + min_util = max_t(unsigned long, min_util, uclamp_rq_get(rq, UCLAMP_MIN)); + max_util = max_t(unsigned long, max_util, uclamp_rq_get(rq, UCLAMP_MAX)); out: /* * Since CPU's {min,max}_util clamps are MAX aggregated considering @@ -2488,6 +2505,25 @@ static inline bool uclamp_is_used(void) { return false; } + +static inline unsigned long uclamp_rq_get(struct rq *rq, + enum uclamp_id clamp_id) +{ + if (clamp_id == UCLAMP_MIN) + return 0; + + return SCHED_CAPACITY_SCALE; +} + +static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id, + unsigned int value) +{ +} + +static inline bool uclamp_rq_is_idle(struct rq *rq) +{ + return false; +} #endif /* CONFIG_UCLAMP_TASK */ #ifdef arch_scale_freq_capacity From 2fd1c194e688484e65c2a428bd343107d2a753c2 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:36 +0100 Subject: [PATCH 2623/4345] sched/uclamp: Make select_idle_capacity() use util_fits_cpu() commit b759caa1d9f667b94727b2ad12589cbc4ce13a82 upstream. Use the new util_fits_cpu() to ensure migration margin and capacity pressure are taken into account correctly when uclamp is being used otherwise we will fail to consider CPUs as fitting in scenarios where they should. Fixes: b4c9c9f15649 ("sched/fair: Prefer prev cpu in asymmetric wakeup path") Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220804143609.515789-5-qais.yousef@arm.com (cherry picked from commit b759caa1d9f667b94727b2ad12589cbc4ce13a82) Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d29fda240ca4..70d1036c969b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6394,21 +6394,23 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t static int select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) { - unsigned long task_util, best_cap = 0; + unsigned long task_util, util_min, util_max, best_cap = 0; int cpu, best_cpu = -1; struct cpumask *cpus; cpus = this_cpu_cpumask_var_ptr(select_idle_mask); cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); - task_util = uclamp_task_util(p); + task_util = task_util_est(p); + util_min = uclamp_eff_value(p, UCLAMP_MIN); + util_max = uclamp_eff_value(p, UCLAMP_MAX); for_each_cpu_wrap(cpu, cpus, target) { unsigned long cpu_cap = capacity_of(cpu); if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu)) continue; - if (fits_capacity(task_util, cpu_cap)) + if (util_fits_cpu(task_util, util_min, util_max, cpu)) return cpu; if (cpu_cap > best_cap) { From 07750955e9a241f6c8d5f0ed4eab2b26fb8cd53d Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:37 +0100 Subject: [PATCH 2624/4345] sched/uclamp: Make asym_fits_capacity() use util_fits_cpu() commit a2e7f03ed28fce26c78b985f87913b6ce3accf9d upstream. Use the new util_fits_cpu() to ensure migration margin and capacity pressure are taken into account correctly when uclamp is being used otherwise we will fail to consider CPUs as fitting in scenarios where they should. s/asym_fits_capacity/asym_fits_cpu/ to better reflect what it does now. Fixes: b4c9c9f15649 ("sched/fair: Prefer prev cpu in asymmetric wakeup path") Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220804143609.515789-6-qais.yousef@arm.com (cherry picked from commit a2e7f03ed28fce26c78b985f87913b6ce3accf9d) [Conflict in kernel/sched/fair.c due different name of static key wrapper function and slightly different if condition block in one of the asym_fits_cpu() call sites] Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 70d1036c969b..754dbedf6de4 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6422,10 +6422,13 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) return best_cpu; } -static inline bool asym_fits_capacity(unsigned long task_util, int cpu) +static inline bool asym_fits_cpu(unsigned long util, + unsigned long util_min, + unsigned long util_max, + int cpu) { if (static_branch_unlikely(&sched_asym_cpucapacity)) - return fits_capacity(task_util, capacity_of(cpu)); + return util_fits_cpu(util, util_min, util_max, cpu); return true; } @@ -6436,7 +6439,7 @@ static inline bool asym_fits_capacity(unsigned long task_util, int cpu) static int select_idle_sibling(struct task_struct *p, int prev, int target) { struct sched_domain *sd; - unsigned long task_util; + unsigned long task_util, util_min, util_max; int i, recent_used_cpu; /* @@ -6445,11 +6448,13 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) */ if (static_branch_unlikely(&sched_asym_cpucapacity)) { sync_entity_load_avg(&p->se); - task_util = uclamp_task_util(p); + task_util = task_util_est(p); + util_min = uclamp_eff_value(p, UCLAMP_MIN); + util_max = uclamp_eff_value(p, UCLAMP_MAX); } if ((available_idle_cpu(target) || sched_idle_cpu(target)) && - asym_fits_capacity(task_util, target)) + asym_fits_cpu(task_util, util_min, util_max, target)) return target; /* @@ -6457,7 +6462,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) */ if (prev != target && cpus_share_cache(prev, target) && (available_idle_cpu(prev) || sched_idle_cpu(prev)) && - asym_fits_capacity(task_util, prev)) + asym_fits_cpu(task_util, util_min, util_max, prev)) return prev; /* @@ -6472,7 +6477,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) in_task() && prev == smp_processor_id() && this_rq()->nr_running <= 1 && - asym_fits_capacity(task_util, prev)) { + asym_fits_cpu(task_util, util_min, util_max, prev)) { return prev; } @@ -6483,7 +6488,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) cpus_share_cache(recent_used_cpu, target) && (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) && - asym_fits_capacity(task_util, recent_used_cpu)) { + asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) { /* * Replace recent_used_cpu with prev as it is a potential * candidate for the next wake: From 41a880740c9f3a7da983c67a2ae8f70085fd2c00 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:38 +0100 Subject: [PATCH 2625/4345] sched/uclamp: Make cpu_overutilized() use util_fits_cpu() commit c56ab1b3506ba0e7a872509964b100912bde165d upstream. So that it is now uclamp aware. This fixes a major problem of busy tasks capped with UCLAMP_MAX keeping the system in overutilized state which disables EAS and leads to wasting energy in the long run. Without this patch running a busy background activity like JIT compilation on Pixel 6 causes the system to be in overutilized state 74.5% of the time. With this patch this goes down to 9.79%. It also fixes another problem when long running tasks that have their UCLAMP_MIN changed while running such that they need to upmigrate to honour the new UCLAMP_MIN value. The upmigration doesn't get triggered because overutilized state never gets set in this state, hence misfit migration never happens at tick in this case until the task wakes up again. Fixes: af24bde8df202 ("sched/uclamp: Add uclamp support to energy_compute()") Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220804143609.515789-7-qais.yousef@arm.com (cherry picked from commit c56ab1b3506ba0e7a872509964b100912bde165d) [Conflict in kernel/sched/fair.c: use cpu_util() instead of cpu_util_cfs()] Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 754dbedf6de4..7acc21d639b2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5657,7 +5657,10 @@ static inline unsigned long cpu_util(int cpu); static inline bool cpu_overutilized(int cpu) { - return !fits_capacity(cpu_util(cpu), capacity_of(cpu)); + unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); + unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + + return !util_fits_cpu(cpu_util(cpu), rq_util_min, rq_util_max, cpu); } static inline void update_overutilized_status(struct rq *rq) From b18cbd359d7216a57af9409a177fa58e7db827fb Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:39 +0100 Subject: [PATCH 2626/4345] sched/uclamp: Cater for uclamp in find_energy_efficient_cpu()'s early exit condition commit d81304bc6193554014d4372a01debdf65e1e9a4d upstream. If the utilization of the woken up task is 0, we skip the energy calculation because it has no impact. But if the task is boosted (uclamp_min != 0) will have an impact on task placement and frequency selection. Only skip if the util is truly 0 after applying uclamp values. Change uclamp_task_cpu() signature to avoid unnecessary additional calls to uclamp_eff_get(). feec() is the only user now. Fixes: 732cd75b8c920 ("sched/fair: Select an energy-efficient CPU on task wake-up") Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220804143609.515789-8-qais.yousef@arm.com (cherry picked from commit d81304bc6193554014d4372a01debdf65e1e9a4d) Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7acc21d639b2..40ed005ed46c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3928,14 +3928,16 @@ static inline unsigned long task_util_est(struct task_struct *p) } #ifdef CONFIG_UCLAMP_TASK -static inline unsigned long uclamp_task_util(struct task_struct *p) +static inline unsigned long uclamp_task_util(struct task_struct *p, + unsigned long uclamp_min, + unsigned long uclamp_max) { - return clamp(task_util_est(p), - uclamp_eff_value(p, UCLAMP_MIN), - uclamp_eff_value(p, UCLAMP_MAX)); + return clamp(task_util_est(p), uclamp_min, uclamp_max); } #else -static inline unsigned long uclamp_task_util(struct task_struct *p) +static inline unsigned long uclamp_task_util(struct task_struct *p, + unsigned long uclamp_min, + unsigned long uclamp_max) { return task_util_est(p); } @@ -6836,7 +6838,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) goto fail; sync_entity_load_avg(&p->se); - if (!task_util_est(p)) + if (!uclamp_task_util(p, p_util_min, p_util_max)) goto unlock; for (; pd; pd = pd->next) { From 30f04dd56dfddfc58cd7fe9b45728ba9c1682a94 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:40 +0100 Subject: [PATCH 2627/4345] sched/fair: Detect capacity inversion commit: 44c7b80bffc3a657a36857098d5d9c49d94e652b upstream. Check each performance domain to see if thermal pressure is causing its capacity to be lower than another performance domain. We assume that each performance domain has CPUs with the same capacities, which is similar to an assumption made in energy_model.c We also assume that thermal pressure impacts all CPUs in a performance domain equally. If there're multiple performance domains with the same capacity_orig, we will trigger a capacity inversion if the domain is under thermal pressure. The new cpu_in_capacity_inversion() should help users to know when information about capacity_orig are not reliable and can opt in to use the inverted capacity as the 'actual' capacity_orig. Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220804143609.515789-9-qais.yousef@arm.com (cherry picked from commit 44c7b80bffc3a657a36857098d5d9c49d94e652b) [Trivial conflict in kernel/sched/fair.c and sched.h due to code shuffling] Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 63 +++++++++++++++++++++++++++++++++++++++++--- kernel/sched/sched.h | 19 +++++++++++++ 2 files changed, 79 insertions(+), 3 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 40ed005ed46c..999cee9f57c1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8376,16 +8376,73 @@ static unsigned long scale_rt_capacity(int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { + unsigned long capacity_orig = arch_scale_cpu_capacity(cpu); unsigned long capacity = scale_rt_capacity(cpu); struct sched_group *sdg = sd->groups; + struct rq *rq = cpu_rq(cpu); - cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu); + rq->cpu_capacity_orig = capacity_orig; if (!capacity) capacity = 1; - cpu_rq(cpu)->cpu_capacity = capacity; - trace_sched_cpu_capacity_tp(cpu_rq(cpu)); + rq->cpu_capacity = capacity; + + /* + * Detect if the performance domain is in capacity inversion state. + * + * Capacity inversion happens when another perf domain with equal or + * lower capacity_orig_of() ends up having higher capacity than this + * domain after subtracting thermal pressure. + * + * We only take into account thermal pressure in this detection as it's + * the only metric that actually results in *real* reduction of + * capacity due to performance points (OPPs) being dropped/become + * unreachable due to thermal throttling. + * + * We assume: + * * That all cpus in a perf domain have the same capacity_orig + * (same uArch). + * * Thermal pressure will impact all cpus in this perf domain + * equally. + */ + if (static_branch_unlikely(&sched_asym_cpucapacity)) { + unsigned long inv_cap = capacity_orig - thermal_load_avg(rq); + struct perf_domain *pd = rcu_dereference(rq->rd->pd); + + rq->cpu_capacity_inverted = 0; + + for (; pd; pd = pd->next) { + struct cpumask *pd_span = perf_domain_span(pd); + unsigned long pd_cap_orig, pd_cap; + + cpu = cpumask_any(pd_span); + pd_cap_orig = arch_scale_cpu_capacity(cpu); + + if (capacity_orig < pd_cap_orig) + continue; + + /* + * handle the case of multiple perf domains have the + * same capacity_orig but one of them is under higher + * thermal pressure. We record it as capacity + * inversion. + */ + if (capacity_orig == pd_cap_orig) { + pd_cap = pd_cap_orig - thermal_load_avg(cpu_rq(cpu)); + + if (pd_cap > inv_cap) { + rq->cpu_capacity_inverted = inv_cap; + break; + } + } else if (pd_cap_orig > inv_cap) { + rq->cpu_capacity_inverted = inv_cap; + break; + } + } + } + + trace_sched_cpu_capacity_tp(rq); sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = capacity; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d4632e50d8b3..852e856eed48 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -973,6 +973,7 @@ struct rq { unsigned long cpu_capacity; unsigned long cpu_capacity_orig; + unsigned long cpu_capacity_inverted; struct callback_head *balance_callback; @@ -2539,6 +2540,24 @@ static inline unsigned long capacity_orig_of(int cpu) { return cpu_rq(cpu)->cpu_capacity_orig; } + +/* + * Returns inverted capacity if the CPU is in capacity inversion state. + * 0 otherwise. + * + * Capacity inversion detection only considers thermal impact where actual + * performance points (OPPs) gets dropped. + * + * Capacity inversion state happens when another performance domain that has + * equal or lower capacity_orig_of() becomes effectively larger than the perf + * domain this CPU belongs to due to thermal pressure throttling it hard. + * + * See comment in update_cpu_capacity(). + */ +static inline unsigned long cpu_in_capacity_inversion(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity_inverted; +} #endif /** From 09129798a608eee34c0e53e5cb4974023628944f Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:41 +0100 Subject: [PATCH 2628/4345] sched/fair: Consider capacity inversion in util_fits_cpu() commit: aa69c36f31aadc1669bfa8a3de6a47b5e6c98ee8 upstream. We do consider thermal pressure in util_fits_cpu() for uclamp_min only. With the exception of the biggest cores which by definition are the max performance point of the system and all tasks by definition should fit. Even under thermal pressure, the capacity of the biggest CPU is the highest in the system and should still fit every task. Except when it reaches capacity inversion point, then this is no longer true. We can handle this by using the inverted capacity as capacity_orig in util_fits_cpu(). Which not only addresses the problem above, but also ensure uclamp_max now considers the inverted capacity. Force fitting a task when a CPU is in this adverse state will contribute to making the thermal throttling last longer. Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220804143609.515789-10-qais.yousef@arm.com (cherry picked from commit aa69c36f31aadc1669bfa8a3de6a47b5e6c98ee8) Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 999cee9f57c1..2527c790749b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4113,12 +4113,16 @@ static inline int util_fits_cpu(unsigned long util, * For uclamp_max, we can tolerate a drop in performance level as the * goal is to cap the task. So it's okay if it's getting less. * - * In case of capacity inversion, which is not handled yet, we should - * honour the inverted capacity for both uclamp_min and uclamp_max all - * the time. + * In case of capacity inversion we should honour the inverted capacity + * for both uclamp_min and uclamp_max all the time. */ - capacity_orig = capacity_orig_of(cpu); - capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); + capacity_orig = cpu_in_capacity_inversion(cpu); + if (capacity_orig) { + capacity_orig_thermal = capacity_orig; + } else { + capacity_orig = capacity_orig_of(cpu); + capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); + } /* * We want to force a task to fit a cpu as implied by uclamp_max. From 89ad8a672f57fb119e1743901ed129d4b0a2dc2b Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:42 +0100 Subject: [PATCH 2629/4345] sched/uclamp: Fix a uninitialized variable warnings commit e26fd28db82899be71b4b949527373d0a6be1e65 upstream. Addresses the following warnings: > config: riscv-randconfig-m031-20221111 > compiler: riscv64-linux-gcc (GCC) 12.1.0 > > smatch warnings: > kernel/sched/fair.c:7263 find_energy_efficient_cpu() error: uninitialized symbol 'util_min'. > kernel/sched/fair.c:7263 find_energy_efficient_cpu() error: uninitialized symbol 'util_max'. Fixes: 244226035a1f ("sched/uclamp: Fix fits_capacity() check in feec()") Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Qais Yousef (Google) Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot Link: https://lore.kernel.org/r/20230112122708.330667-2-qyousef@layalina.io (cherry picked from commit e26fd28db82899be71b4b949527373d0a6be1e65) [Conflict in kernel/sched/fair.c due to new automatic variable in master vs 5.10 and new code around for loop] Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2527c790749b..a2426604e4ac 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6846,9 +6846,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) goto unlock; for (; pd; pd = pd->next) { + unsigned long util_min = p_util_min, util_max = p_util_max; unsigned long cur_delta, spare_cap, max_spare_cap = 0; unsigned long rq_util_min, rq_util_max; - unsigned long util_min, util_max; unsigned long base_energy_pd; int max_spare_cap_cpu = -1; @@ -6857,6 +6857,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) base_energy += base_energy_pd; for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { + struct rq *rq = cpu_rq(cpu); + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; @@ -6872,24 +6874,19 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) * much capacity we can get out of the CPU; this is * aligned with schedutil_cpu_util(). */ - if (uclamp_is_used()) { - if (uclamp_rq_is_idle(cpu_rq(cpu))) { - util_min = p_util_min; - util_max = p_util_max; - } else { - /* - * Open code uclamp_rq_util_with() except for - * the clamp() part. Ie: apply max aggregation - * only. util_fits_cpu() logic requires to - * operate on non clamped util but must use the - * max-aggregated uclamp_{min, max}. - */ - rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); - rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) { + /* + * Open code uclamp_rq_util_with() except for + * the clamp() part. Ie: apply max aggregation + * only. util_fits_cpu() logic requires to + * operate on non clamped util but must use the + * max-aggregated uclamp_{min, max}. + */ + rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN); + rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX); - util_min = max(rq_util_min, p_util_min); - util_max = max(rq_util_max, p_util_max); - } + util_min = max(rq_util_min, p_util_min); + util_max = max(rq_util_max, p_util_max); } if (!util_fits_cpu(util, util_min, util_max, cpu)) continue; From 4735b6f74f25e5e869ef1e199064c4f4cd31aa68 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 18 Apr 2023 15:09:43 +0100 Subject: [PATCH 2630/4345] sched/fair: Fixes for capacity inversion detection commit da07d2f9c153e457e845d4dcfdd13568d71d18a4 upstream. Traversing the Perf Domains requires rcu_read_lock() to be held and is conditional on sched_energy_enabled(). Ensure right protections applied. Also skip capacity inversion detection for our own pd; which was an error. Fixes: 44c7b80bffc3 ("sched/fair: Detect capacity inversion") Reported-by: Dietmar Eggemann Signed-off-by: Qais Yousef (Google) Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot Link: https://lore.kernel.org/r/20230112122708.330667-3-qyousef@layalina.io (cherry picked from commit da07d2f9c153e457e845d4dcfdd13568d71d18a4) Signed-off-by: Qais Yousef (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a2426604e4ac..45c1d03aff73 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8407,16 +8407,23 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) * * Thermal pressure will impact all cpus in this perf domain * equally. */ - if (static_branch_unlikely(&sched_asym_cpucapacity)) { + if (sched_energy_enabled()) { unsigned long inv_cap = capacity_orig - thermal_load_avg(rq); - struct perf_domain *pd = rcu_dereference(rq->rd->pd); + struct perf_domain *pd; + rcu_read_lock(); + + pd = rcu_dereference(rq->rd->pd); rq->cpu_capacity_inverted = 0; for (; pd; pd = pd->next) { struct cpumask *pd_span = perf_domain_span(pd); unsigned long pd_cap_orig, pd_cap; + /* We can't be inverted against our own pd */ + if (cpumask_test_cpu(cpu_of(rq), pd_span)) + continue; + cpu = cpumask_any(pd_span); pd_cap_orig = arch_scale_cpu_capacity(cpu); @@ -8441,6 +8448,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) break; } } + + rcu_read_unlock(); } trace_sched_cpu_capacity_tp(rq); From 77748b0a047e7962c66cd9864ddfe87432571a52 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Sat, 8 Apr 2023 21:33:48 +0100 Subject: [PATCH 2631/4345] MIPS: Define RUNTIME_DISCARD_EXIT in LD script commit 6dcbd0a69c84a8ae7a442840a8cf6b1379dc8f16 upstream. MIPS's exit sections are discarded at runtime as well. Fixes link error: `.exit.text' referenced in section `__jump_table' of fs/fuse/inode.o: defined in discarded section `.exit.text' of fs/fuse/inode.o Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv") Reported-by: "kernelci.org bot" Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Greg Kroah-Hartman --- arch/mips/kernel/vmlinux.lds.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 09fa4705ce8e..64afe075df08 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -15,6 +15,8 @@ #define EMITS_PT_NOTE #endif +#define RUNTIME_DISCARD_EXIT + #include #undef mips From 37df709706ae71de4dca8fe338625a643543fd9a Mon Sep 17 00:00:00 2001 From: Salvatore Bonaccorso Date: Sat, 22 Apr 2023 00:17:42 +0200 Subject: [PATCH 2632/4345] docs: futex: Fix kernel-doc references after code split-up preparation In upstream commit 77e52ae35463 ("futex: Move to kernel/futex/") the futex code from kernel/futex.c was moved into kernel/futex/core.c in preparation of the split-up of the implementation in various files. Point kernel-doc references to the new files as otherwise the documentation shows errors on build: [...] Error: Cannot open file ./kernel/futex.c Error: Cannot open file ./kernel/futex.c [...] WARNING: kernel-doc './scripts/kernel-doc -rst -enable-lineno -sphinx-version 3.4.3 -internal ./kernel/futex.c' failed with return code 2 There is no direct upstream commit for this change. It is made in analogy to commit bc67f1c454fb ("docs: futex: Fix kernel-doc references") applied as consequence of the restructuring of the futex code. Fixes: 77e52ae35463 ("futex: Move to kernel/futex/") Signed-off-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-hacking/locking.rst | 2 +- Documentation/translations/it_IT/kernel-hacking/locking.rst | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/kernel-hacking/locking.rst b/Documentation/kernel-hacking/locking.rst index 6ed806e6061b..a6d89efede79 100644 --- a/Documentation/kernel-hacking/locking.rst +++ b/Documentation/kernel-hacking/locking.rst @@ -1358,7 +1358,7 @@ Mutex API reference Futex API reference =================== -.. kernel-doc:: kernel/futex.c +.. kernel-doc:: kernel/futex/core.c :internal: Further reading diff --git a/Documentation/translations/it_IT/kernel-hacking/locking.rst b/Documentation/translations/it_IT/kernel-hacking/locking.rst index bf1acd6204ef..192ab8e28125 100644 --- a/Documentation/translations/it_IT/kernel-hacking/locking.rst +++ b/Documentation/translations/it_IT/kernel-hacking/locking.rst @@ -1400,7 +1400,7 @@ Riferimento per l'API dei Mutex Riferimento per l'API dei Futex =============================== -.. kernel-doc:: kernel/futex.c +.. kernel-doc:: kernel/futex/core.c :internal: Approfondimenti From e220438d1e33170313a295cd797919228c638953 Mon Sep 17 00:00:00 2001 From: Alyssa Ross Date: Sun, 26 Mar 2023 18:21:21 +0000 Subject: [PATCH 2633/4345] purgatory: fix disabling debug info commit d83806c4c0cccc0d6d3c3581a11983a9c186a138 upstream. Since 32ef9e5054ec, -Wa,-gdwarf-2 is no longer used in KBUILD_AFLAGS. Instead, it includes -g, the appropriate -gdwarf-* flag, and also the -Wa versions of both of those if building with Clang and GNU as. As a result, debug info was being generated for the purgatory objects, even though the intention was that it not be. Fixes: 32ef9e5054ec ("Makefile.debug: re-enable debug info for .S files") Signed-off-by: Alyssa Ross Cc: stable@vger.kernel.org Acked-by: Nick Desaulniers Signed-off-by: Masahiro Yamada Signed-off-by: Greg Kroah-Hartman --- arch/x86/purgatory/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 95ea17a9d20c..ebaf329a2368 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -64,8 +64,7 @@ CFLAGS_sha256.o += $(PURGATORY_CFLAGS) CFLAGS_REMOVE_string.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_string.o += $(PURGATORY_CFLAGS) -AFLAGS_REMOVE_setup-x86_$(BITS).o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_entry64.o += -Wa,-gdwarf-2 +asflags-remove-y += -g -Wa,-gdwarf-2 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) From cf08dc79168a80a7cf4dad14a3cc0f2f87561d11 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 11 Nov 2020 17:22:32 +0100 Subject: [PATCH 2634/4345] virtiofs: clean up error handling in virtio_fs_get_tree() commit 833c5a42e28beeefa1f9bd476a63fe8050c1e8ca upstream. Avoid duplicating error cleanup. Signed-off-by: Miklos Szeredi Signed-off-by: Yang Bo Signed-off-by: Greg Kroah-Hartman --- fs/fuse/virtio_fs.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index b9cfb1165ff4..22d2145ce08d 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -1440,22 +1440,14 @@ static int virtio_fs_get_tree(struct fs_context *fsc) return -EINVAL; } + err = -ENOMEM; fc = kzalloc(sizeof(struct fuse_conn), GFP_KERNEL); - if (!fc) { - mutex_lock(&virtio_fs_mutex); - virtio_fs_put(fs); - mutex_unlock(&virtio_fs_mutex); - return -ENOMEM; - } + if (!fc) + goto out_err; fm = kzalloc(sizeof(struct fuse_mount), GFP_KERNEL); - if (!fm) { - mutex_lock(&virtio_fs_mutex); - virtio_fs_put(fs); - mutex_unlock(&virtio_fs_mutex); - kfree(fc); - return -ENOMEM; - } + if (!fm) + goto out_err; fuse_conn_init(fc, fm, fsc->user_ns, &virtio_fs_fiq_ops, fs); fc->release = fuse_free_conn; @@ -1483,6 +1475,13 @@ static int virtio_fs_get_tree(struct fs_context *fsc) WARN_ON(fsc->root); fsc->root = dget(sb->s_root); return 0; + +out_err: + kfree(fc); + mutex_lock(&virtio_fs_mutex); + virtio_fs_put(fs); + mutex_unlock(&virtio_fs_mutex); + return err; } static const struct fs_context_operations virtio_fs_context_ops = { From 6d0d67b05f7b42f638aae31af558e72ce7c5836a Mon Sep 17 00:00:00 2001 From: Connor Kuehl Date: Thu, 18 Mar 2021 08:52:22 -0500 Subject: [PATCH 2635/4345] virtiofs: split requests that exceed virtqueue size commit a7f0d7aab0b4f3f0780b1f77356e2fe7202ac0cb upstream. If an incoming FUSE request can't fit on the virtqueue, the request is placed onto a workqueue so a worker can try to resubmit it later where there will (hopefully) be space for it next time. This is fine for requests that aren't larger than a virtqueue's maximum capacity. However, if a request's size exceeds the maximum capacity of the virtqueue (even if the virtqueue is empty), it will be doomed to a life of being placed on the workqueue, removed, discovered it won't fit, and placed on the workqueue yet again. Furthermore, from section 2.6.5.3.1 (Driver Requirements: Indirect Descriptors) of the virtio spec: "A driver MUST NOT create a descriptor chain longer than the Queue Size of the device." To fix this, limit the number of pages FUSE will use for an overall request. This way, each request can realistically fit on the virtqueue when it is decomposed into a scattergather list and avoid violating section 2.6.5.3.1 of the virtio spec. Signed-off-by: Connor Kuehl Reviewed-by: Vivek Goyal Signed-off-by: Miklos Szeredi Signed-off-by: Yang Bo Signed-off-by: Greg Kroah-Hartman --- fs/fuse/fuse_i.h | 3 +++ fs/fuse/inode.c | 3 ++- fs/fuse/virtio_fs.c | 19 +++++++++++++++++-- 3 files changed, 22 insertions(+), 3 deletions(-) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index b10cddd72355..ceaa6868386e 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -556,6 +556,9 @@ struct fuse_conn { /** Maxmum number of pages that can be used in a single request */ unsigned int max_pages; + /** Constrain ->max_pages to this value during feature negotiation */ + unsigned int max_pages_limit; + /** Input queue */ struct fuse_iqueue iq; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2ede05df7d06..058bb82dee40 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -710,6 +710,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm, fc->pid_ns = get_pid_ns(task_active_pid_ns(current)); fc->user_ns = get_user_ns(user_ns); fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; + fc->max_pages_limit = FUSE_MAX_MAX_PAGES; INIT_LIST_HEAD(&fc->mounts); list_add(&fm->fc_entry, &fc->mounts); @@ -1056,7 +1057,7 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, fc->abort_err = 1; if (arg->flags & FUSE_MAX_PAGES) { fc->max_pages = - min_t(unsigned int, FUSE_MAX_MAX_PAGES, + min_t(unsigned int, fc->max_pages_limit, max_t(unsigned int, arg->max_pages, 1)); } if (IS_ENABLED(CONFIG_FUSE_DAX) && diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 22d2145ce08d..6aaaa74438f3 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -18,6 +18,12 @@ #include #include "fuse_i.h" +/* Used to help calculate the FUSE connection's max_pages limit for a request's + * size. Parts of the struct fuse_req are sliced into scattergather lists in + * addition to the pages used, so this can help account for that overhead. + */ +#define FUSE_HEADER_OVERHEAD 4 + /* List of virtio-fs device instances and a lock for the list. Also provides * mutual exclusion in device removal and mounting path */ @@ -1426,9 +1432,10 @@ static int virtio_fs_get_tree(struct fs_context *fsc) { struct virtio_fs *fs; struct super_block *sb; - struct fuse_conn *fc; + struct fuse_conn *fc = NULL; struct fuse_mount *fm; - int err; + unsigned int virtqueue_size; + int err = -EIO; /* This gets a reference on virtio_fs object. This ptr gets installed * in fc->iq->priv. Once fuse_conn is going away, it calls ->put() @@ -1440,6 +1447,10 @@ static int virtio_fs_get_tree(struct fs_context *fsc) return -EINVAL; } + virtqueue_size = virtqueue_get_vring_size(fs->vqs[VQ_REQUEST].vq); + if (WARN_ON(virtqueue_size <= FUSE_HEADER_OVERHEAD)) + goto out_err; + err = -ENOMEM; fc = kzalloc(sizeof(struct fuse_conn), GFP_KERNEL); if (!fc) @@ -1454,6 +1465,10 @@ static int virtio_fs_get_tree(struct fs_context *fsc) fc->delete_stale = true; fc->auto_submounts = true; + /* Tell FUSE to split requests that exceed the virtqueue's size */ + fc->max_pages_limit = min_t(unsigned int, fc->max_pages_limit, + virtqueue_size - FUSE_HEADER_OVERHEAD); + fsc->s_fs_info = fm; sb = sget_fc(fsc, virtio_fs_test_super, virtio_fs_set_super); fuse_mount_put(fm); From 0078a1667cbf7e674430186837698503f0ef4272 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 21 Oct 2021 10:01:38 +0200 Subject: [PATCH 2636/4345] fuse: check s_root when destroying sb commit d534d31d6a45d71de61db22090b4820afb68fddc upstream. Checking "fm" works because currently sb->s_fs_info is cleared on error paths; however, sb->s_root is what generic_shutdown_super() checks to determine whether the sb was fully initialized or not. This change will allow cleanup of sb setup error paths. Signed-off-by: Miklos Szeredi Signed-off-by: Yang Bo Signed-off-by: Greg Kroah-Hartman --- fs/fuse/inode.c | 2 +- fs/fuse/virtio_fs.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 058bb82dee40..9ea175ff9c8e 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1596,7 +1596,7 @@ static void fuse_kill_sb_blk(struct super_block *sb) struct fuse_mount *fm = get_fuse_mount_super(sb); bool last; - if (fm) { + if (sb->s_root) { last = fuse_mount_remove(fm); if (last) fuse_conn_destroy(fm); diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 6aaaa74438f3..faadc80485e7 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -1399,7 +1399,7 @@ static void virtio_kill_sb(struct super_block *sb) bool last; /* If mount failed, we can still be called without any fc */ - if (fm) { + if (sb->s_root) { last = fuse_mount_remove(fm); if (last) virtio_fs_conn_destroy(fm); From 42dfdbd4dcfa021d50af9f6a4c4a09eb086cc29d Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 22 Oct 2021 17:03:03 +0200 Subject: [PATCH 2637/4345] fuse: fix attr version comparison in fuse_read_update_size() commit 484ce65715b06aead8c4901f01ca32c5a240bc71 upstream. A READ request returning a short count is taken as indication of EOF, and the cached file size is modified accordingly. Fix the attribute version checking to allow for changes to fc->attr_version on other inodes. Signed-off-by: Miklos Szeredi Signed-off-by: Yang Bo Signed-off-by: Greg Kroah-Hartman --- fs/fuse/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 504389568dac..94fe2c690676 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -782,7 +782,7 @@ static void fuse_read_update_size(struct inode *inode, loff_t size, struct fuse_inode *fi = get_fuse_inode(inode); spin_lock(&fi->lock); - if (attr_ver == fi->attr_version && size < inode->i_size && + if (attr_ver >= fi->attr_version && size < inode->i_size && !test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) { fi->attr_version = atomic64_inc_return(&fc->attr_version); i_size_write(inode, size); From 03cefde986f1504fb84c92403c2b6c133fc9bdb0 Mon Sep 17 00:00:00 2001 From: Jiachen Zhang Date: Wed, 28 Sep 2022 20:19:34 +0800 Subject: [PATCH 2638/4345] fuse: always revalidate rename target dentry commit ccc031e26afe60d2a5a3d93dabd9c978210825fb upstream. The previous commit df8629af2934 ("fuse: always revalidate if exclusive create") ensures that the dentries are revalidated on O_EXCL creates. This commit complements it by also performing revalidation for rename target dentries. Otherwise, a rename target file that only exists in kernel dentry cache but not in the filesystem will result in EEXIST if RENAME_NOREPLACE flag is used. Signed-off-by: Jiachen Zhang Signed-off-by: Zhang Tianci Signed-off-by: Miklos Szeredi Signed-off-by: Yang Bo Signed-off-by: Greg Kroah-Hartman --- fs/fuse/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 80a9e50392a0..bdb04bea0da9 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -205,7 +205,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) if (inode && fuse_is_bad(inode)) goto invalid; else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) || - (flags & (LOOKUP_EXCL | LOOKUP_REVAL))) { + (flags & (LOOKUP_EXCL | LOOKUP_REVAL | LOOKUP_RENAME_TARGET))) { struct fuse_entry_out outarg; FUSE_ARGS(args); struct fuse_forget_link *forget; From 81775ab858b4236c52c5da7e25cec6e49dd91b46 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 22 Apr 2022 15:48:53 +0200 Subject: [PATCH 2639/4345] fuse: fix deadlock between atomic O_TRUNC and page invalidation commit 2fdbb8dd01556e1501132b5ad3826e8f71e24a8b upstream. fuse_finish_open() will be called with FUSE_NOWRITE set in case of atomic O_TRUNC open(), so commit 76224355db75 ("fuse: truncate pagecache on atomic_o_trunc") replaced invalidate_inode_pages2() by truncate_pagecache() in such a case to avoid the A-A deadlock. However, we found another A-B-B-A deadlock related to the case above, which will cause the xfstests generic/464 testcase hung in our virtio-fs test environment. For example, consider two processes concurrently open one same file, one with O_TRUNC and another without O_TRUNC. The deadlock case is described below, if open(O_TRUNC) is already set_nowrite(acquired A), and is trying to lock a page (acquiring B), open() could have held the page lock (acquired B), and waiting on the page writeback (acquiring A). This would lead to deadlocks. open(O_TRUNC) ---------------------------------------------------------------- fuse_open_common inode_lock [C acquire] fuse_set_nowrite [A acquire] fuse_finish_open truncate_pagecache lock_page [B acquire] truncate_inode_page unlock_page [B release] fuse_release_nowrite [A release] inode_unlock [C release] ---------------------------------------------------------------- open() ---------------------------------------------------------------- fuse_open_common fuse_finish_open invalidate_inode_pages2 lock_page [B acquire] fuse_launder_page fuse_wait_on_page_writeback [A acquire & release] unlock_page [B release] ---------------------------------------------------------------- Besides this case, all calls of invalidate_inode_pages2() and invalidate_inode_pages2_range() in fuse code also can deadlock with open(O_TRUNC). Fix by moving the truncate_pagecache() call outside the nowrite protected region. The nowrite protection is only for delayed writeback (writeback_cache) case, where inode lock does not protect against truncation racing with writes on the server. Write syscalls racing with page cache truncation still get the inode lock protection. This patch also changes the order of filemap_invalidate_lock() vs. fuse_set_nowrite() in fuse_open_common(). This new order matches the order found in fuse_file_fallocate() and fuse_do_setattr(). Reported-by: Jiachen Zhang Tested-by: Jiachen Zhang Fixes: e4648309b85a ("fuse: truncate pending writes on O_TRUNC") Cc: Signed-off-by: Miklos Szeredi Signed-off-by: Yang Bo Signed-off-by: Greg Kroah-Hartman --- fs/fuse/dir.c | 5 +++++ fs/fuse/file.c | 29 +++++++++++++++++------------ 2 files changed, 22 insertions(+), 12 deletions(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index bdb04bea0da9..e3b9b7d188e6 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -537,6 +537,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, struct fuse_entry_out outentry; struct fuse_inode *fi; struct fuse_file *ff; + bool trunc = flags & O_TRUNC; /* Userspace expects S_IFREG in create mode */ BUG_ON((mode & S_IFMT) != S_IFREG); @@ -604,6 +605,10 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, } else { file->private_data = ff; fuse_finish_open(inode, file); + if (fm->fc->atomic_o_trunc && trunc) + truncate_pagecache(inode, 0); + else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); } return err; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 94fe2c690676..13d97547eaf6 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -206,14 +206,10 @@ void fuse_finish_open(struct inode *inode, struct file *file) fi->attr_version = atomic64_inc_return(&fc->attr_version); i_size_write(inode, 0); spin_unlock(&fi->lock); - truncate_pagecache(inode, 0); fuse_invalidate_attr(inode); if (fc->writeback_cache) file_update_time(file); - } else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) { - invalidate_inode_pages2(inode->i_mapping); } - if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache) fuse_link_write_file(file); } @@ -236,30 +232,39 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) if (err) return err; - if (is_wb_truncate || dax_truncate) { + if (is_wb_truncate || dax_truncate) inode_lock(inode); - fuse_set_nowrite(inode); - } if (dax_truncate) { down_write(&get_fuse_inode(inode)->i_mmap_sem); err = fuse_dax_break_layouts(inode, 0, 0); if (err) - goto out; + goto out_inode_unlock; } + if (is_wb_truncate || dax_truncate) + fuse_set_nowrite(inode); + err = fuse_do_open(fm, get_node_id(inode), file, isdir); if (!err) fuse_finish_open(inode, file); -out: + if (is_wb_truncate || dax_truncate) + fuse_release_nowrite(inode); + if (!err) { + struct fuse_file *ff = file->private_data; + + if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) + truncate_pagecache(inode, 0); + else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); + } if (dax_truncate) up_write(&get_fuse_inode(inode)->i_mmap_sem); - if (is_wb_truncate | dax_truncate) { - fuse_release_nowrite(inode); +out_inode_unlock: + if (is_wb_truncate || dax_truncate) inode_unlock(inode); - } return err; } From 9400206d9d5eebc0317da4151364ade32d28944f Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 19 Apr 2023 06:46:08 +0000 Subject: [PATCH 2640/4345] Revert "ext4: fix use-after-free in ext4_xattr_set_entry" This reverts commit bb8592efcf8ef2f62947745d3182ea05b5256a15 which is commit 67d7d8ad99beccd9fe92d585b87f1760dc9018e3 upstream. The order in which patches are queued to stable matters. This patch has a logical dependency on commit 310c097c2bdbea253d6ee4e064f3e65580ef93ac upstream, and failing to queue the latter results in a null-ptr-deref reported at the Link below. In order to avoid conflicts on stable, revert the commit just so that we can queue its prerequisite patch first and then queue the same after. Link: https://syzkaller.appspot.com/bug?extid=d5ebf56f3b1268136afd Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index f3da1f2d4cb9..948da799abab 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2193,9 +2193,8 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_inode *raw_inode; int error; - if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) + if (EXT4_I(inode)->i_extra_isize == 0) return 0; - raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); @@ -2223,9 +2222,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, struct ext4_xattr_search *s = &is->s; int error; - if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) + if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; - error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; From c75711396c04a77cb614f49d37e7385e984c0cb7 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 19 Apr 2023 06:46:09 +0000 Subject: [PATCH 2641/4345] ext4: remove duplicate definition of ext4_xattr_ibody_inline_set() [ Upstream commit 310c097c2bdbea253d6ee4e064f3e65580ef93ac ] ext4_xattr_ibody_inline_set() & ext4_xattr_ibody_set() have the exact same definition. Hence remove ext4_xattr_ibody_inline_set() and all its call references. Convert the callers of it to call ext4_xattr_ibody_set() instead. [ Modified to preserve ext4_xattr_ibody_set() and remove ext4_xattr_ibody_inline_set() instead. -- TYT ] Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/fd566b799bbbbe9b668eb5eecde5b5e319e3694f.1622685482.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inline.c | 11 +++++------ fs/ext4/xattr.c | 26 +------------------------- fs/ext4/xattr.h | 6 +++--- 3 files changed, 9 insertions(+), 34 deletions(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 61cb50e8fcb7..0758f606f006 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -206,7 +206,7 @@ out: /* * write the buffer to the inline inode. * If 'create' is set, we don't need to do the extra copy in the xattr - * value since it is already handled by ext4_xattr_ibody_inline_set. + * value since it is already handled by ext4_xattr_ibody_set. * That saves us one memcpy. */ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, @@ -288,7 +288,7 @@ static int ext4_create_inline_data(handle_t *handle, BUG_ON(!is.s.not_found); - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) { if (error == -ENOSPC) ext4_clear_inode_state(inode, @@ -360,7 +360,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, i.value = value; i.value_len = len; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -433,7 +433,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle, if (error) goto out; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -1930,8 +1930,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) i.value = value; i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ? i_size - EXT4_MIN_INLINE_DATA_SIZE : 0; - err = ext4_xattr_ibody_inline_set(handle, inode, - &i, &is); + err = ext4_xattr_ibody_set(handle, inode, &i, &is); if (err) goto out_error; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 948da799abab..71e83e815258 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2214,31 +2214,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, return 0; } -int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is) -{ - struct ext4_xattr_ibody_header *header; - struct ext4_xattr_search *s = &is->s; - int error; - - if (EXT4_I(inode)->i_extra_isize == 0) - return -ENOSPC; - error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); - if (error) - return error; - header = IHDR(inode, ext4_raw_inode(&is->iloc)); - if (!IS_LAST_ENTRY(s->first)) { - header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); - ext4_set_inode_state(inode, EXT4_STATE_XATTR); - } else { - header->h_magic = cpu_to_le32(0); - ext4_clear_inode_state(inode, EXT4_STATE_XATTR); - } - return 0; -} - -static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, +int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index b357872ab83b..e5e36bd11f05 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -200,9 +200,9 @@ extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, extern int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size); -extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is); +extern int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is); extern struct mb_cache *ext4_xattr_create_cache(void); extern void ext4_xattr_destroy_cache(struct mb_cache *); From 05cf34a2b6414a1172552d16159b3e17e9da36a3 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 19 Apr 2023 06:46:10 +0000 Subject: [PATCH 2642/4345] ext4: fix use-after-free in ext4_xattr_set_entry [ Upstream commit 67d7d8ad99beccd9fe92d585b87f1760dc9018e3 ] Hulk Robot reported a issue: ================================================================== BUG: KASAN: use-after-free in ext4_xattr_set_entry+0x18ab/0x3500 Write of size 4105 at addr ffff8881675ef5f4 by task syz-executor.0/7092 CPU: 1 PID: 7092 Comm: syz-executor.0 Not tainted 4.19.90-dirty #17 Call Trace: [...] memcpy+0x34/0x50 mm/kasan/kasan.c:303 ext4_xattr_set_entry+0x18ab/0x3500 fs/ext4/xattr.c:1747 ext4_xattr_ibody_inline_set+0x86/0x2a0 fs/ext4/xattr.c:2205 ext4_xattr_set_handle+0x940/0x1300 fs/ext4/xattr.c:2386 ext4_xattr_set+0x1da/0x300 fs/ext4/xattr.c:2498 __vfs_setxattr+0x112/0x170 fs/xattr.c:149 __vfs_setxattr_noperm+0x11b/0x2a0 fs/xattr.c:180 __vfs_setxattr_locked+0x17b/0x250 fs/xattr.c:238 vfs_setxattr+0xed/0x270 fs/xattr.c:255 setxattr+0x235/0x330 fs/xattr.c:520 path_setxattr+0x176/0x190 fs/xattr.c:539 __do_sys_lsetxattr fs/xattr.c:561 [inline] __se_sys_lsetxattr fs/xattr.c:557 [inline] __x64_sys_lsetxattr+0xc2/0x160 fs/xattr.c:557 do_syscall_64+0xdf/0x530 arch/x86/entry/common.c:298 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x459fe9 RSP: 002b:00007fa5e54b4c08 EFLAGS: 00000246 ORIG_RAX: 00000000000000bd RAX: ffffffffffffffda RBX: 000000000051bf60 RCX: 0000000000459fe9 RDX: 00000000200003c0 RSI: 0000000020000180 RDI: 0000000020000140 RBP: 000000000051bf60 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000001009 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffc73c93fc0 R14: 000000000051bf60 R15: 00007fa5e54b4d80 [...] ================================================================== Above issue may happen as follows: ------------------------------------- ext4_xattr_set ext4_xattr_set_handle ext4_xattr_ibody_find >> s->end < s->base >> no EXT4_STATE_XATTR >> xattr_check_inode is not executed ext4_xattr_ibody_set ext4_xattr_set_entry >> size_t min_offs = s->end - s->base >> UAF in memcpy we can easily reproduce this problem with the following commands: mkfs.ext4 -F /dev/sda mount -o debug_want_extra_isize=128 /dev/sda /mnt touch /mnt/file setfattr -n user.cat -v `seq -s z 4096|tr -d '[:digit:]'` /mnt/file In ext4_xattr_ibody_find, we have the following assignment logic: header = IHDR(inode, raw_inode) = raw_inode + EXT4_GOOD_OLD_INODE_SIZE + i_extra_isize is->s.base = IFIRST(header) = header + sizeof(struct ext4_xattr_ibody_header) is->s.end = raw_inode + s_inode_size In ext4_xattr_set_entry min_offs = s->end - s->base = s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - i_extra_isize - sizeof(struct ext4_xattr_ibody_header) last = s->first free = min_offs - ((void *)last - s->base) - sizeof(__u32) = s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - i_extra_isize - sizeof(struct ext4_xattr_ibody_header) - sizeof(__u32) In the calculation formula, all values except s_inode_size and i_extra_size are fixed values. When i_extra_size is the maximum value s_inode_size - EXT4_GOOD_OLD_INODE_SIZE, min_offs is -4 and free is -8. The value overflows. As a result, the preceding issue is triggered when memcpy is executed. Therefore, when finding xattr or setting xattr, check whether there is space for storing xattr in the inode to resolve this issue. Cc: stable@kernel.org Reported-by: Hulk Robot Signed-off-by: Baokun Li Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20220616021358.2504451-3-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 71e83e815258..28fa9a64dc4b 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2193,8 +2193,9 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_inode *raw_inode; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0; + raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); @@ -2222,8 +2223,9 @@ int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_search *s = &is->s; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return -ENOSPC; + error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; From 0e7b5e1020aad24e63d1231065af92c701629327 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 6 Oct 2022 11:53:46 -0700 Subject: [PATCH 2643/4345] udp: Call inet6_destroy_sock() in setsockopt(IPV6_ADDRFORM). commit 21985f43376cee092702d6cb963ff97a9d2ede68 upstream. Commit 4b340ae20d0e ("IPv6: Complete IPV6_DONTFRAG support") forgot to add a change to free inet6_sk(sk)->rxpmtu while converting an IPv6 socket into IPv4 with IPV6_ADDRFORM. After conversion, sk_prot is changed to udp_prot and ->destroy() never cleans it up, resulting in a memory leak. This is due to the discrepancy between inet6_destroy_sock() and IPV6_ADDRFORM, so let's call inet6_destroy_sock() from IPV6_ADDRFORM to remove the difference. However, this is not enough for now because rxpmtu can be changed without lock_sock() after commit 03485f2adcde ("udpv6: Add lockless sendmsg() support"). We will fix this case in the following patch. Note we will rename inet6_destroy_sock() to inet6_cleanup_sock() and remove unnecessary inet6_destroy_sock() calls in sk_prot->destroy() in the future. Fixes: 4b340ae20d0e ("IPv6: Complete IPV6_DONTFRAG support") Signed-off-by: Kuniyuki Iwashima Signed-off-by: Jakub Kicinski Signed-off-by: Ziyang Xuan Signed-off-by: Greg Kroah-Hartman --- include/net/ipv6.h | 1 + net/ipv6/af_inet6.c | 6 ++++++ net/ipv6/ipv6_sockglue.c | 20 ++++++++------------ 3 files changed, 15 insertions(+), 12 deletions(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 89ce8a50f236..5ab7616ce711 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1109,6 +1109,7 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); +void inet6_cleanup_sock(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 4df9dc9375c8..68d456c7abf9 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -503,6 +503,12 @@ void inet6_destroy_sock(struct sock *sk) } EXPORT_SYMBOL_GPL(inet6_destroy_sock); +void inet6_cleanup_sock(struct sock *sk) +{ + inet6_destroy_sock(sk); +} +EXPORT_SYMBOL_GPL(inet6_cleanup_sock); + /* * This does both peername and sockname. */ diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 2017257cb278..7b4b457a8b87 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -429,9 +429,6 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optlen < sizeof(int)) goto e_inval; if (val == PF_INET) { - struct ipv6_txoptions *opt; - struct sk_buff *pktopt; - if (sk->sk_type == SOCK_RAW) break; @@ -462,7 +459,6 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, break; } - fl6_free_socklist(sk); __ipv6_sock_mc_close(sk); __ipv6_sock_ac_close(sk); @@ -497,14 +493,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sk->sk_socket->ops = &inet_dgram_ops; sk->sk_family = PF_INET; } - opt = xchg((__force struct ipv6_txoptions **)&np->opt, - NULL); - if (opt) { - atomic_sub(opt->tot_len, &sk->sk_omem_alloc); - txopt_put(opt); - } - pktopt = xchg(&np->pktoptions, NULL); - kfree_skb(pktopt); + + /* Disable all options not to allocate memory anymore, + * but there is still a race. See the lockless path + * in udpv6_sendmsg() and ipv6_local_rxpmtu(). + */ + np->rxopt.all = 0; + + inet6_cleanup_sock(sk); /* * ... and add it to the refcnt debug socks count From b1f06ab985efd3456c8bbf96bdc52c53a125b4b3 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 6 Oct 2022 11:53:47 -0700 Subject: [PATCH 2644/4345] tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct(). commit d38afeec26ed4739c640bf286c270559aab2ba5f upstream. Originally, inet6_sk(sk)->XXX were changed under lock_sock(), so we were able to clean them up by calling inet6_destroy_sock() during the IPv6 -> IPv4 conversion by IPV6_ADDRFORM. However, commit 03485f2adcde ("udpv6: Add lockless sendmsg() support") added a lockless memory allocation path, which could cause a memory leak: setsockopt(IPV6_ADDRFORM) sendmsg() +-----------------------+ +-------+ - do_ipv6_setsockopt(sk, ...) - udpv6_sendmsg(sk, ...) - sockopt_lock_sock(sk) ^._ called via udpv6_prot - lock_sock(sk) before WRITE_ONCE() - WRITE_ONCE(sk->sk_prot, &tcp_prot) - inet6_destroy_sock() - if (!corkreq) - sockopt_release_sock(sk) - ip6_make_skb(sk, ...) - release_sock(sk) ^._ lockless fast path for the non-corking case - __ip6_append_data(sk, ...) - ipv6_local_rxpmtu(sk, ...) - xchg(&np->rxpmtu, skb) ^._ rxpmtu is never freed. - goto out_no_dst; - lock_sock(sk) For now, rxpmtu is only the case, but not to miss the future change and a similar bug fixed in commit e27326009a3d ("net: ping6: Fix memleak in ipv6_renew_options()."), let's set a new function to IPv6 sk->sk_destruct() and call inet6_cleanup_sock() there. Since the conversion does not change sk->sk_destruct(), we can guarantee that we can clean up IPv6 resources finally. We can now remove all inet6_destroy_sock() calls from IPv6 protocol specific ->destroy() functions, but such changes are invasive to backport. So they can be posted as a follow-up later for net-next. Fixes: 03485f2adcde ("udpv6: Add lockless sendmsg() support") Signed-off-by: Kuniyuki Iwashima Signed-off-by: Jakub Kicinski Signed-off-by: Ziyang Xuan Signed-off-by: Greg Kroah-Hartman --- include/net/ipv6.h | 1 + include/net/udp.h | 2 +- include/net/udplite.h | 8 -------- net/ipv4/udp.c | 9 ++++++--- net/ipv4/udplite.c | 8 ++++++++ net/ipv6/af_inet6.c | 8 +++++++- net/ipv6/udp.c | 15 ++++++++++++++- net/ipv6/udp_impl.h | 1 + net/ipv6/udplite.c | 9 ++++++++- 9 files changed, 46 insertions(+), 15 deletions(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 5ab7616ce711..8879c0ab0b89 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1110,6 +1110,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); void inet6_cleanup_sock(struct sock *sk); +void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, diff --git a/include/net/udp.h b/include/net/udp.h index 388e68c7bca0..e2550a4547a7 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -268,7 +268,7 @@ static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, } /* net/ipv4/udp.c */ -void udp_destruct_sock(struct sock *sk); +void udp_destruct_common(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); diff --git a/include/net/udplite.h b/include/net/udplite.h index 9185e45b997f..c59ba86668af 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -24,14 +24,6 @@ static __inline__ int udplite_getfrag(void *from, char *to, int offset, return copy_from_iter_full(to, len, &msg->msg_iter) ? 0 : -EFAULT; } -/* Designate sk as UDP-Lite socket */ -static inline int udplite_sk_init(struct sock *sk) -{ - udp_init_sock(sk); - udp_sk(sk)->pcflag = UDPLITE_BIT; - return 0; -} - /* * Checksumming routines */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b093daaa3deb..f0db66e415bd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1582,7 +1582,7 @@ drop: } EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); -void udp_destruct_sock(struct sock *sk) +void udp_destruct_common(struct sock *sk) { /* reclaim completely the forward allocated memory */ struct udp_sock *up = udp_sk(sk); @@ -1595,10 +1595,14 @@ void udp_destruct_sock(struct sock *sk) kfree_skb(skb); } udp_rmem_release(sk, total, 0, true); +} +EXPORT_SYMBOL_GPL(udp_destruct_common); +static void udp_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); inet_sock_destruct(sk); } -EXPORT_SYMBOL_GPL(udp_destruct_sock); int udp_init_sock(struct sock *sk) { @@ -1606,7 +1610,6 @@ int udp_init_sock(struct sock *sk) sk->sk_destruct = udp_destruct_sock; return 0; } -EXPORT_SYMBOL_GPL(udp_init_sock); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index bd8773b49e72..cfb36655a5fd 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -17,6 +17,14 @@ struct udp_table udplite_table __read_mostly; EXPORT_SYMBOL(udplite_table); +/* Designate sk as UDP-Lite socket */ +static int udplite_sk_init(struct sock *sk) +{ + udp_init_sock(sk); + udp_sk(sk)->pcflag = UDPLITE_BIT; + return 0; +} + static int udplite_rcv(struct sk_buff *skb) { return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 68d456c7abf9..5846e386221f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -107,6 +107,12 @@ static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } +void inet6_sock_destruct(struct sock *sk) +{ + inet6_cleanup_sock(sk); + inet_sock_destruct(sk); +} + static int inet6_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -199,7 +205,7 @@ lookup_protocol: inet->hdrincl = 1; } - sk->sk_destruct = inet_sock_destruct; + sk->sk_destruct = inet6_sock_destruct; sk->sk_family = PF_INET6; sk->sk_protocol = protocol; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 20cc08210c70..bd3140f69b82 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -54,6 +54,19 @@ #include #include "udp_impl.h" +static void udpv6_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); + inet6_sock_destruct(sk); +} + +int udpv6_init_sock(struct sock *sk) +{ + skb_queue_head_init(&udp_sk(sk)->reader_queue); + sk->sk_destruct = udpv6_destruct_sock; + return 0; +} + static u32 udp6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, @@ -1702,7 +1715,7 @@ struct proto udpv6_prot = { .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, - .init = udp_init_sock, + .init = udpv6_init_sock, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index b2fcc46c1630..e49776819441 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -12,6 +12,7 @@ int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int); int __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int, __be32, struct udp_table *); +int udpv6_init_sock(struct sock *sk); int udp_v6_get_port(struct sock *sk, unsigned short snum); void udp_v6_rehash(struct sock *sk); diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index fbb700d3f437..b6482e04dad0 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -12,6 +12,13 @@ #include #include "udp_impl.h" +static int udplitev6_sk_init(struct sock *sk) +{ + udpv6_init_sock(sk); + udp_sk(sk)->pcflag = UDPLITE_BIT; + return 0; +} + static int udplitev6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); @@ -38,7 +45,7 @@ struct proto udplitev6_prot = { .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, - .init = udplite_sk_init, + .init = udplitev6_sk_init, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, From 04d393c4bbf5b906329fd40449c1c660a3affa37 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Oct 2022 15:35:59 -0700 Subject: [PATCH 2645/4345] inet6: Remove inet6_destroy_sock() in sk->sk_prot->destroy(). commit b5fc29233d28be7a3322848ebe73ac327559cdb9 upstream. After commit d38afeec26ed ("tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct()."), we call inet6_destroy_sock() in sk->sk_destruct() by setting inet6_sock_destruct() to it to make sure we do not leak inet6-specific resources. Now we can remove unnecessary inet6_destroy_sock() calls in sk->sk_prot->destroy(). DCCP and SCTP have their own sk->sk_destruct() function, so we change them separately in the following patches. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Matthieu Baerts Signed-off-by: David S. Miller Signed-off-by: Ziyang Xuan Signed-off-by: Greg Kroah-Hartman --- net/ipv6/ping.c | 6 ------ net/ipv6/raw.c | 2 -- net/ipv6/tcp_ipv6.c | 8 +------- net/ipv6/udp.c | 2 -- net/l2tp/l2tp_ip6.c | 2 -- net/mptcp/protocol.c | 7 ------- 6 files changed, 1 insertion(+), 26 deletions(-) diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 135e3a060caa..6ac88fe24a8e 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -22,11 +22,6 @@ #include #include -static void ping_v6_destroy(struct sock *sk) -{ - inet6_destroy_sock(sk); -} - /* Compatibility glue so we can support IPv6 when it's compiled as a module */ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) @@ -171,7 +166,6 @@ struct proto pingv6_prot = { .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, - .destroy = ping_v6_destroy, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .setsockopt = ipv6_setsockopt, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 110254f44a46..69f0f9c05d02 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1211,8 +1211,6 @@ static void raw6_destroy(struct sock *sk) lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - - inet6_destroy_sock(sk); } static int rawv6_init_sk(struct sock *sk) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e4ae5362cb51..2347740d3cc7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1936,12 +1936,6 @@ static int tcp_v6_init_sock(struct sock *sk) return 0; } -static void tcp_v6_destroy_sock(struct sock *sk) -{ - tcp_v4_destroy_sock(sk); - inet6_destroy_sock(sk); -} - #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, @@ -2134,7 +2128,7 @@ struct proto tcpv6_prot = { .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v6_init_sock, - .destroy = tcp_v6_destroy_sock, + .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index bd3140f69b82..19c0721399d9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1630,8 +1630,6 @@ void udpv6_destroy_sock(struct sock *sk) udp_encap_disable(); } } - - inet6_destroy_sock(sk); } /* diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index d54dbd01d86f..382124d6f764 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -255,8 +255,6 @@ static void l2tp_ip6_destroy_sock(struct sock *sk) if (tunnel) l2tp_tunnel_delete(tunnel); - - inet6_destroy_sock(sk); } static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e61c85873ea2..72d944e6a641 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2863,12 +2863,6 @@ static const struct proto_ops mptcp_v6_stream_ops = { static struct proto mptcp_v6_prot; -static void mptcp_v6_destroy(struct sock *sk) -{ - mptcp_destroy(sk); - inet6_destroy_sock(sk); -} - static struct inet_protosw mptcp_v6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_MPTCP, @@ -2884,7 +2878,6 @@ int __init mptcp_proto_v6_init(void) mptcp_v6_prot = mptcp_prot; strcpy(mptcp_v6_prot.name, "MPTCPv6"); mptcp_v6_prot.slab = NULL; - mptcp_v6_prot.destroy = mptcp_v6_destroy; mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock); err = proto_register(&mptcp_v6_prot, 1); From 7da54ddc04e6cef3c016b87dbaae574abc73fa94 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Oct 2022 15:36:00 -0700 Subject: [PATCH 2646/4345] dccp: Call inet6_destroy_sock() via sk->sk_destruct(). commit 1651951ebea54970e0bda60c638fc2eee7a6218f upstream. After commit d38afeec26ed ("tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct()."), we call inet6_destroy_sock() in sk->sk_destruct() by setting inet6_sock_destruct() to it to make sure we do not leak inet6-specific resources. DCCP sets its own sk->sk_destruct() in the dccp_init_sock(), and DCCPv6 socket shares it by calling the same init function via dccp_v6_init_sock(). To call inet6_sock_destruct() from DCCPv6 sk->sk_destruct(), we export it and set dccp_v6_sk_destruct() in the init function. Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Ziyang Xuan Signed-off-by: Greg Kroah-Hartman --- net/dccp/dccp.h | 1 + net/dccp/ipv6.c | 15 ++++++++------- net/dccp/proto.c | 8 +++++++- net/ipv6/af_inet6.c | 1 + 4 files changed, 17 insertions(+), 8 deletions(-) diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 5183e627468d..0218eb169891 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -283,6 +283,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, const unsigned int len); +void dccp_destruct_common(struct sock *sk); int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); void dccp_destroy_sock(struct sock *sk); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index c563f9b325d0..64e91783860d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -992,6 +992,12 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .sockaddr_len = sizeof(struct sockaddr_in6), }; +static void dccp_v6_sk_destruct(struct sock *sk) +{ + dccp_destruct_common(sk); + inet6_sock_destruct(sk); +} + /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ @@ -1004,17 +1010,12 @@ static int dccp_v6_init_sock(struct sock *sk) if (unlikely(!dccp_v6_ctl_sock_initialized)) dccp_v6_ctl_sock_initialized = 1; inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; + sk->sk_destruct = dccp_v6_sk_destruct; } return err; } -static void dccp_v6_destroy_sock(struct sock *sk) -{ - dccp_destroy_sock(sk); - inet6_destroy_sock(sk); -} - static struct timewait_sock_ops dccp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct dccp6_timewait_sock), }; @@ -1037,7 +1038,7 @@ static struct proto dccp_v6_prot = { .accept = inet_csk_accept, .get_port = inet_csk_get_port, .shutdown = dccp_shutdown, - .destroy = dccp_v6_destroy_sock, + .destroy = dccp_destroy_sock, .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp6_sock), diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 65e81e0199b0..e946211758c0 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -171,12 +171,18 @@ const char *dccp_packet_name(const int type) EXPORT_SYMBOL_GPL(dccp_packet_name); -static void dccp_sk_destruct(struct sock *sk) +void dccp_destruct_common(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); dp->dccps_hc_tx_ccid = NULL; +} +EXPORT_SYMBOL_GPL(dccp_destruct_common); + +static void dccp_sk_destruct(struct sock *sk) +{ + dccp_destruct_common(sk); inet_sock_destruct(sk); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 5846e386221f..4247997077bf 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -112,6 +112,7 @@ void inet6_sock_destruct(struct sock *sk) inet6_cleanup_sock(sk); inet_sock_destruct(sk); } +EXPORT_SYMBOL_GPL(inet6_sock_destruct); static int inet6_create(struct net *net, struct socket *sock, int protocol, int kern) From f69112de70a0c876a42532daab9962e36c2f3fed Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Oct 2022 15:36:01 -0700 Subject: [PATCH 2647/4345] sctp: Call inet6_destroy_sock() via sk->sk_destruct(). commit 6431b0f6ff1633ae598667e4cdd93830074a03e8 upstream. After commit d38afeec26ed ("tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct()."), we call inet6_destroy_sock() in sk->sk_destruct() by setting inet6_sock_destruct() to it to make sure we do not leak inet6-specific resources. SCTP sets its own sk->sk_destruct() in the sctp_init_sock(), and SCTPv6 socket reuses it as the init function. To call inet6_sock_destruct() from SCTPv6 sk->sk_destruct(), we set sctp_v6_destruct_sock() in a new init function. Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Ziyang Xuan Signed-off-by: Greg Kroah-Hartman --- net/sctp/socket.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3a68d65f7d15..35d3eee26ea5 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4995,13 +4995,17 @@ static void sctp_destroy_sock(struct sock *sk) } /* Triggered when there are no references on the socket anymore */ -static void sctp_destruct_sock(struct sock *sk) +static void sctp_destruct_common(struct sock *sk) { struct sctp_sock *sp = sctp_sk(sk); /* Free up the HMAC transform. */ crypto_free_shash(sp->hmac); +} +static void sctp_destruct_sock(struct sock *sk) +{ + sctp_destruct_common(sk); inet_sock_destruct(sk); } @@ -9195,7 +9199,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, sctp_sk(newsk)->reuse = sp->reuse; newsk->sk_shutdown = sk->sk_shutdown; - newsk->sk_destruct = sctp_destruct_sock; + newsk->sk_destruct = sk->sk_destruct; newsk->sk_family = sk->sk_family; newsk->sk_protocol = IPPROTO_SCTP; newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; @@ -9427,11 +9431,20 @@ struct proto sctp_prot = { #if IS_ENABLED(CONFIG_IPV6) -#include -static void sctp_v6_destroy_sock(struct sock *sk) +static void sctp_v6_destruct_sock(struct sock *sk) { - sctp_destroy_sock(sk); - inet6_destroy_sock(sk); + sctp_destruct_common(sk); + inet6_sock_destruct(sk); +} + +static int sctp_v6_init_sock(struct sock *sk) +{ + int ret = sctp_init_sock(sk); + + if (!ret) + sk->sk_destruct = sctp_v6_destruct_sock; + + return ret; } struct proto sctpv6_prot = { @@ -9441,8 +9454,8 @@ struct proto sctpv6_prot = { .disconnect = sctp_disconnect, .accept = sctp_accept, .ioctl = sctp_ioctl, - .init = sctp_init_sock, - .destroy = sctp_v6_destroy_sock, + .init = sctp_v6_init_sock, + .destroy = sctp_destroy_sock, .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, From b28079807de2144ca88d4f2a5cf039c58e48654d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 22 Mar 2023 22:45:44 +0100 Subject: [PATCH 2648/4345] pwm: meson: Explicitly set .polarity in .get_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8caa81eb950cb2e9d2d6959b37d853162d197f57 upstream. The driver only supports normal polarity. Complete the implementation of .get_state() by setting .polarity accordingly. This fixes a regression that was possible since commit c73a3107624d ("pwm: Handle .get_state() failures") which stopped to zero-initialize the state passed to the .get_state() callback. This was reported at https://forum.odroid.com/viewtopic.php?f=177&t=46360 . While this was an unintended side effect, the real issue is the driver's callback not setting the polarity. There is a complicating fact, that the .apply() callback fakes support for inversed polarity. This is not (and cannot) be matched by .get_state(). As fixing this isn't easy, only point it out in a comment to prevent authors of other drivers from copying that approach. Fixes: c375bcbaabdb ("pwm: meson: Read the full hardware state in meson_pwm_get_state()") Reported-by: Munehisa Kamata Acked-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20230310191405.2606296-1-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding Signed-off-by: Uwe Kleine-König Signed-off-by: Greg Kroah-Hartman --- drivers/pwm/pwm-meson.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index bd0d7336b898..237bb8e06593 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -168,6 +168,12 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm, duty = state->duty_cycle; period = state->period; + /* + * Note this is wrong. The result is an output wave that isn't really + * inverted and so is wrongly identified by .get_state as normal. + * Fixing this needs some care however as some machines might rely on + * this. + */ if (state->polarity == PWM_POLARITY_INVERSED) duty = period - duty; @@ -366,6 +372,7 @@ static void meson_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, state->period = 0; state->duty_cycle = 0; } + state->polarity = PWM_POLARITY_NORMAL; } static const struct pwm_ops meson_pwm_ops = { From 1c3a1211370dcaf509bac72ff258c813cc42a6eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 24 Apr 2023 07:31:04 +0200 Subject: [PATCH 2649/4345] pwm: iqs620a: Explicitly set .polarity in .get_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b20b097128d9145fadcea1cbb45c4d186cb57466 ] The driver only supports normal polarity. Complete the implementation of .get_state() by setting .polarity accordingly. Fixes: 6f0841a8197b ("pwm: Add support for Azoteq IQS620A PWM generator") Reviewed-by: Jeff LaBundy Link: https://lore.kernel.org/r/20230228135508.1798428-4-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding Signed-off-by: Uwe Kleine-König Signed-off-by: Greg Kroah-Hartman --- drivers/pwm/pwm-iqs620a.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pwm/pwm-iqs620a.c b/drivers/pwm/pwm-iqs620a.c index 3e967a12458c..a2aef006cb71 100644 --- a/drivers/pwm/pwm-iqs620a.c +++ b/drivers/pwm/pwm-iqs620a.c @@ -132,6 +132,7 @@ static void iqs620_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, mutex_unlock(&iqs620_pwm->lock); state->period = IQS620_PWM_PERIOD_NS; + state->polarity = PWM_POLARITY_NORMAL; } static int iqs620_pwm_notifier(struct notifier_block *notifier, From 155b2586de3f171d46c8a1955990d4676487501e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 24 Apr 2023 07:31:05 +0200 Subject: [PATCH 2650/4345] pwm: hibvt: Explicitly set .polarity in .get_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6f57937980142715e927697a6ffd2050f38ed6f6 ] The driver only both polarities. Complete the implementation of .get_state() by setting .polarity according to the configured hardware state. Fixes: d09f00810850 ("pwm: Add PWM driver for HiSilicon BVT SOCs") Link: https://lore.kernel.org/r/20230228135508.1798428-2-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding Signed-off-by: Uwe Kleine-König Signed-off-by: Greg Kroah-Hartman --- drivers/pwm/pwm-hibvt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pwm/pwm-hibvt.c b/drivers/pwm/pwm-hibvt.c index ad205fdad372..286e9b119ee5 100644 --- a/drivers/pwm/pwm-hibvt.c +++ b/drivers/pwm/pwm-hibvt.c @@ -146,6 +146,7 @@ static void hibvt_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, value = readl(base + PWM_CTRL_ADDR(pwm->hwpwm)); state->enabled = (PWM_ENABLE_MASK & value); + state->polarity = (PWM_POLARITY_MASK & value) ? PWM_POLARITY_INVERSED : PWM_POLARITY_NORMAL; } static int hibvt_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, From 42604b4ad5f3289596455c786c04c67a1b5740d9 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 29 Mar 2023 07:35:32 +0300 Subject: [PATCH 2651/4345] iio: adc: at91-sama5d2_adc: fix an error code in at91_adc_allocate_trigger() commit 73a428b37b9b538f8f8fe61caa45e7f243bab87c upstream. The at91_adc_allocate_trigger() function is supposed to return error pointers. Returning a NULL will cause an Oops. Fixes: 5e1a1da0f8c9 ("iio: adc: at91-sama5d2_adc: add hw trigger and buffer support") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/5d728f9d-31d1-410d-a0b3-df6a63a2c8ba@kili.mountain Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/at91-sama5d2_adc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index 250b78ee1625..b806c1ab9b61 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -1002,7 +1002,7 @@ static struct iio_trigger *at91_adc_allocate_trigger(struct iio_dev *indio, trig = devm_iio_trigger_alloc(&indio->dev, "%s-dev%d-%s", indio->name, indio->id, trigger_name); if (!trig) - return NULL; + return ERR_PTR(-ENOMEM); trig->dev.parent = indio->dev.parent; iio_trigger_set_drvdata(trig, indio); From 4ab5f8f9d026bd6e66827c5993179bab42fc8f51 Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Mon, 17 Apr 2023 06:32:42 -0700 Subject: [PATCH 2652/4345] ASoC: fsl_asrc_dma: fix potential null-ptr-deref commit 86a24e99c97234f87d9f70b528a691150e145197 upstream. dma_request_slave_channel() may return NULL which will lead to NULL pointer dereference error in 'tmp_chan->private'. Correct this behaviour by, first, switching from deprecated function dma_request_slave_channel() to dma_request_chan(). Secondly, enable sanity check for the resuling value of dma_request_chan(). Also, fix description that follows the enacted changes and that concerns the use of dma_request_slave_channel(). Fixes: 706e2c881158 ("ASoC: fsl_asrc_dma: Reuse the dma channel if available in Back-End") Co-developed-by: Natalia Petrova Signed-off-by: Nikita Zhandarovich Acked-by: Shengjiu Wang Link: https://lore.kernel.org/r/20230417133242.53339-1-n.zhandarovich@fintech.ru Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/fsl/fsl_asrc_dma.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c index 29f91cdecbc3..9b2a986ce415 100644 --- a/sound/soc/fsl/fsl_asrc_dma.c +++ b/sound/soc/fsl/fsl_asrc_dma.c @@ -207,14 +207,19 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component, be_chan = soc_component_to_pcm(component_be)->chan[substream->stream]; tmp_chan = be_chan; } - if (!tmp_chan) - tmp_chan = dma_request_slave_channel(dev_be, tx ? "tx" : "rx"); + if (!tmp_chan) { + tmp_chan = dma_request_chan(dev_be, tx ? "tx" : "rx"); + if (IS_ERR(tmp_chan)) { + dev_err(dev, "failed to request DMA channel for Back-End\n"); + return -EINVAL; + } + } /* * An EDMA DEV_TO_DEV channel is fixed and bound with DMA event of each * peripheral, unlike SDMA channel that is allocated dynamically. So no * need to configure dma_request and dma_request2, but get dma_chan of - * Back-End device directly via dma_request_slave_channel. + * Back-End device directly via dma_request_chan. */ if (!asrc->use_edma) { /* Get DMA request of Back-End */ From 0367bf3f4a4eb6691e18194beb5792843aecced9 Mon Sep 17 00:00:00 2001 From: Ekaterina Orlova Date: Fri, 21 Apr 2023 15:35:39 +0100 Subject: [PATCH 2653/4345] ASN.1: Fix check for strdup() success commit 5a43001c01691dcbd396541e6faa2c0077378f48 upstream. It seems there is a misprint in the check of strdup() return code that can lead to NULL pointer dereference. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 4520c6a49af8 ("X.509: Add simple ASN.1 grammar compiler") Signed-off-by: Ekaterina Orlova Cc: David Woodhouse Cc: James Bottomley Cc: Jarkko Sakkinen Cc: keyrings@vger.kernel.org Cc: linux-kbuild@vger.kernel.org Link: https://lore.kernel.org/r/20230315172130.140-1-vorobushek.ok@gmail.com/ Signed-off-by: David Howells Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- scripts/asn1_compiler.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/asn1_compiler.c b/scripts/asn1_compiler.c index adabd4145264..985fb81cae79 100644 --- a/scripts/asn1_compiler.c +++ b/scripts/asn1_compiler.c @@ -625,7 +625,7 @@ int main(int argc, char **argv) p = strrchr(argv[1], '/'); p = p ? p + 1 : argv[1]; grammar_name = strdup(p); - if (!p) { + if (!grammar_name) { perror(NULL); exit(1); } From f1b32fda06d2cfb8eea9680b0ba7a8b0d5b81eeb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 26 Apr 2023 11:27:43 +0200 Subject: [PATCH 2654/4345] Linux 5.10.179 Link: https://lore.kernel.org/r/20230424131127.653885914@linuxfoundation.org Tested-by: Salvatore Bonaccorso Tested-by: Guenter Roeck Tested-by: Jon Hunter Tested-by: Linux Kernel Functional Testing Tested-by: Chris Paterson (CIP) Tested-by: Florian Fainelli Tested-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 3bde04cc7f04..3ddcade4be8f 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 178 +SUBLEVEL = 179 EXTRAVERSION = NAME = Dare mighty things From 036fa20734cbcbf2f7472d9062a7ca48f6d3c1f3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 27 Apr 2023 11:32:21 +0000 Subject: [PATCH 2655/4345] Revert "tcp: restrict net.ipv4.tcp_app_win" This reverts commit a069d4d98cd271a70b561cb757485efe5f5e5a7e which is commit dc5110c2d959c1707e12df5f792f41d90614adaa upstream. It breaks the Android kernel abi, and is not needed at this point in time. If it is required, it can come back in an ABI-safe way. Bug: 161946584 Change-Id: I7ef145a192f15df2179150f9f0087746725d27ea Signed-off-by: Greg Kroah-Hartman --- Documentation/networking/ip-sysctl.rst | 2 -- net/ipv4/sysctl_net_ipv4.c | 3 --- 2 files changed, 5 deletions(-) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 705d1ded3a4a..eedce7474ad3 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -272,8 +272,6 @@ tcp_app_win - INTEGER Reserve max(window/2^tcp_app_win, mss) of window for application buffer. Value 0 is special, it means that nothing is reserved. - Possible values are [0, 31], inclusive. - Default: 31 tcp_autocorking - BOOLEAN diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index e7449145318a..8c2a45eb783c 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -37,7 +37,6 @@ static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; -static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int ip_privileged_port_min; @@ -1123,8 +1122,6 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = &tcp_app_win_max, }, { .procname = "tcp_adv_win_scale", From e2f3aab65b37220372ae27928ae896e8660f7348 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 27 Apr 2023 11:32:22 +0000 Subject: [PATCH 2656/4345] Revert "tcp: convert elligible sysctls to u8" This reverts commit cc9f9a49f5b3b7bd70e8f7edd10b4f9be196aff3 which is commit 4ecc1baf362c5df2dcabe242511e38ee28486545 upstream. It breaks the Android kernel abi, and is not needed at this point in time. If it is required, it can come back in an ABI-safe way. Bug: 161946584 Change-Id: Ia44a4d7ef5887b2175038783e918badf464ae51b Signed-off-by: Greg Kroah-Hartman --- include/net/netns/ipv4.h | 68 +++++++++---------- net/ipv4/sysctl_net_ipv4.c | 136 ++++++++++++++++++------------------- 2 files changed, 102 insertions(+), 102 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2e93a00ed126..c58d9f9dbc23 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -115,11 +115,11 @@ struct netns_ipv4 { u8 sysctl_nexthop_compat_mode; u8 sysctl_fwmark_reflect; - u8 sysctl_tcp_fwmark_accept; + int sysctl_tcp_fwmark_accept; #ifdef CONFIG_NET_L3_MASTER_DEV - u8 sysctl_tcp_l3mdev_accept; + int sysctl_tcp_l3mdev_accept; #endif - u8 sysctl_tcp_mtu_probing; + int sysctl_tcp_mtu_probing; int sysctl_tcp_mtu_probe_floor; int sysctl_tcp_base_mss; int sysctl_tcp_min_snd_mss; @@ -127,47 +127,46 @@ struct netns_ipv4 { u32 sysctl_tcp_probe_interval; int sysctl_tcp_keepalive_time; + int sysctl_tcp_keepalive_probes; int sysctl_tcp_keepalive_intvl; - u8 sysctl_tcp_keepalive_probes; - u8 sysctl_tcp_syn_retries; - u8 sysctl_tcp_synack_retries; - u8 sysctl_tcp_syncookies; + int sysctl_tcp_syn_retries; + int sysctl_tcp_synack_retries; + int sysctl_tcp_syncookies; int sysctl_tcp_reordering; - u8 sysctl_tcp_retries1; - u8 sysctl_tcp_retries2; - u8 sysctl_tcp_orphan_retries; - u8 sysctl_tcp_tw_reuse; + int sysctl_tcp_retries1; + int sysctl_tcp_retries2; + int sysctl_tcp_orphan_retries; int sysctl_tcp_fin_timeout; unsigned int sysctl_tcp_notsent_lowat; - u8 sysctl_tcp_sack; - u8 sysctl_tcp_window_scaling; - u8 sysctl_tcp_timestamps; - u8 sysctl_tcp_early_retrans; - u8 sysctl_tcp_recovery; - u8 sysctl_tcp_thin_linear_timeouts; - u8 sysctl_tcp_slow_start_after_idle; - u8 sysctl_tcp_retrans_collapse; - u8 sysctl_tcp_stdurg; - u8 sysctl_tcp_rfc1337; - u8 sysctl_tcp_abort_on_overflow; - u8 sysctl_tcp_fack; /* obsolete */ + int sysctl_tcp_tw_reuse; + int sysctl_tcp_sack; + int sysctl_tcp_window_scaling; + int sysctl_tcp_timestamps; + int sysctl_tcp_early_retrans; + int sysctl_tcp_recovery; + int sysctl_tcp_thin_linear_timeouts; + int sysctl_tcp_slow_start_after_idle; + int sysctl_tcp_retrans_collapse; + int sysctl_tcp_stdurg; + int sysctl_tcp_rfc1337; + int sysctl_tcp_abort_on_overflow; + int sysctl_tcp_fack; int sysctl_tcp_max_reordering; + int sysctl_tcp_dsack; + int sysctl_tcp_app_win; int sysctl_tcp_adv_win_scale; - u8 sysctl_tcp_dsack; - u8 sysctl_tcp_app_win; - u8 sysctl_tcp_frto; - u8 sysctl_tcp_nometrics_save; - u8 sysctl_tcp_no_ssthresh_metrics_save; - u8 sysctl_tcp_moderate_rcvbuf; - u8 sysctl_tcp_tso_win_divisor; - u8 sysctl_tcp_workaround_signed_windows; + int sysctl_tcp_frto; + int sysctl_tcp_nometrics_save; + int sysctl_tcp_no_ssthresh_metrics_save; + int sysctl_tcp_moderate_rcvbuf; + int sysctl_tcp_tso_win_divisor; + int sysctl_tcp_workaround_signed_windows; int sysctl_tcp_limit_output_bytes; int sysctl_tcp_challenge_ack_limit; + int sysctl_tcp_min_tso_segs; int sysctl_tcp_min_rtt_wlen; - u8 sysctl_tcp_min_tso_segs; - u8 sysctl_tcp_autocorking; - u8 sysctl_tcp_reflect_tos; + int sysctl_tcp_autocorking; int sysctl_tcp_invalid_ratelimit; int sysctl_tcp_pacing_ss_ratio; int sysctl_tcp_pacing_ca_ratio; @@ -185,6 +184,7 @@ struct netns_ipv4 { unsigned int sysctl_tcp_fastopen_blackhole_timeout; atomic_t tfo_active_disable_times; unsigned long tfo_active_disable_stamp; + int sysctl_tcp_reflect_tos; int sysctl_udp_wmem_min; int sysctl_udp_rmem_min; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 8c2a45eb783c..d1aa5e294f10 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -727,17 +727,17 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_fwmark_accept", .data = &init_net.ipv4.sysctl_tcp_fwmark_accept, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_NET_L3_MASTER_DEV { .procname = "tcp_l3mdev_accept", .data = &init_net.ipv4.sysctl_tcp_l3mdev_accept, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -745,9 +745,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_mtu_probing", .data = &init_net.ipv4.sysctl_tcp_mtu_probing, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec, }, { .procname = "tcp_base_mss", @@ -849,9 +849,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_keepalive_probes", .data = &init_net.ipv4.sysctl_tcp_keepalive_probes, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_keepalive_intvl", @@ -863,26 +863,26 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_syn_retries", .data = &init_net.ipv4.sysctl_tcp_syn_retries, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = &tcp_syn_retries_min, .extra2 = &tcp_syn_retries_max }, { .procname = "tcp_synack_retries", .data = &init_net.ipv4.sysctl_tcp_synack_retries, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, #ifdef CONFIG_SYN_COOKIES { .procname = "tcp_syncookies", .data = &init_net.ipv4.sysctl_tcp_syncookies, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, #endif { @@ -895,24 +895,24 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_retries1", .data = &init_net.ipv4.sysctl_tcp_retries1, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra2 = &tcp_retr1_max }, { .procname = "tcp_retries2", .data = &init_net.ipv4.sysctl_tcp_retries2, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_orphan_retries", .data = &init_net.ipv4.sysctl_tcp_orphan_retries, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_fin_timeout", @@ -931,9 +931,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_tw_reuse", .data = &init_net.ipv4.sysctl_tcp_tw_reuse, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &two, }, @@ -1019,88 +1019,88 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_sack", .data = &init_net.ipv4.sysctl_tcp_sack, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_window_scaling", .data = &init_net.ipv4.sysctl_tcp_window_scaling, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_timestamps", .data = &init_net.ipv4.sysctl_tcp_timestamps, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_early_retrans", .data = &init_net.ipv4.sysctl_tcp_early_retrans, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &four, }, { .procname = "tcp_recovery", .data = &init_net.ipv4.sysctl_tcp_recovery, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec, }, { .procname = "tcp_thin_linear_timeouts", .data = &init_net.ipv4.sysctl_tcp_thin_linear_timeouts, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_slow_start_after_idle", .data = &init_net.ipv4.sysctl_tcp_slow_start_after_idle, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_retrans_collapse", .data = &init_net.ipv4.sysctl_tcp_retrans_collapse, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_stdurg", .data = &init_net.ipv4.sysctl_tcp_stdurg, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_rfc1337", .data = &init_net.ipv4.sysctl_tcp_rfc1337, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_abort_on_overflow", .data = &init_net.ipv4.sysctl_tcp_abort_on_overflow, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_fack", .data = &init_net.ipv4.sysctl_tcp_fack, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_max_reordering", @@ -1112,16 +1112,16 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_dsack", .data = &init_net.ipv4.sysctl_tcp_dsack, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_app_win", .data = &init_net.ipv4.sysctl_tcp_app_win, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_adv_win_scale", @@ -1135,46 +1135,46 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_frto", .data = &init_net.ipv4.sysctl_tcp_frto, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_no_metrics_save", .data = &init_net.ipv4.sysctl_tcp_nometrics_save, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec, }, { .procname = "tcp_no_ssthresh_metrics_save", .data = &init_net.ipv4.sysctl_tcp_no_ssthresh_metrics_save, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "tcp_moderate_rcvbuf", .data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec, }, { .procname = "tcp_tso_win_divisor", .data = &init_net.ipv4.sysctl_tcp_tso_win_divisor, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec, }, { .procname = "tcp_workaround_signed_windows", .data = &init_net.ipv4.sysctl_tcp_workaround_signed_windows, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_limit_output_bytes", @@ -1193,9 +1193,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_min_tso_segs", .data = &init_net.ipv4.sysctl_tcp_min_tso_segs, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &gso_max_segs, }, @@ -1211,9 +1211,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_autocorking", .data = &init_net.ipv4.sysctl_tcp_autocorking, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -1284,9 +1284,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_reflect_tos", .data = &init_net.ipv4.sysctl_tcp_reflect_tos, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, From a4023d8fc3dc01ec9539acc1cead64c02d4bd38a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 28 Apr 2023 14:29:22 +0000 Subject: [PATCH 2657/4345] Revert "ipv4: shrink netns_ipv4 with sysctl conversions" This reverts commit f662a0786dfd404db0b6595302500156719eeaa3 which is commit 4b6bbf17d4e1939afa72821879fc033d725e9491 upstream. It breaks the Android kernel abi, and is not needed at this point in time. If it is required, it can come back in an ABI-safe way. Bug: 161946584 Signed-off-by: Greg Kroah-Hartman Change-Id: I762a8a7eaee1baa7dbedc9c72854b85cfffbe7d9 --- include/net/netns/ipv4.h | 32 +++++++++---------- net/ipv4/sysctl_net_ipv4.c | 64 +++++++++++++++++++------------------- 2 files changed, 48 insertions(+), 48 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index c58d9f9dbc23..fb94551d03e6 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -85,36 +85,36 @@ struct netns_ipv4 { struct xt_table *nat_table; #endif - u8 sysctl_icmp_echo_ignore_all; - u8 sysctl_icmp_echo_ignore_broadcasts; - u8 sysctl_icmp_ignore_bogus_error_responses; - u8 sysctl_icmp_errors_use_inbound_ifaddr; + int sysctl_icmp_echo_ignore_all; + int sysctl_icmp_echo_ignore_broadcasts; + int sysctl_icmp_ignore_bogus_error_responses; int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; + int sysctl_icmp_errors_use_inbound_ifaddr; struct local_ports ip_local_ports; - u8 sysctl_tcp_ecn; - u8 sysctl_tcp_ecn_fallback; + int sysctl_tcp_ecn; + int sysctl_tcp_ecn_fallback; - u8 sysctl_ip_default_ttl; - u8 sysctl_ip_no_pmtu_disc; - u8 sysctl_ip_fwd_use_pmtu; + int sysctl_ip_default_ttl; + int sysctl_ip_no_pmtu_disc; + int sysctl_ip_fwd_use_pmtu; int sysctl_ip_fwd_update_priority; - u8 sysctl_ip_nonlocal_bind; - u8 sysctl_ip_autobind_reuse; + int sysctl_ip_nonlocal_bind; + int sysctl_ip_autobind_reuse; /* Shall we try to damage output packets if routing dev changes? */ - u8 sysctl_ip_dynaddr; - u8 sysctl_ip_early_demux; + int sysctl_ip_dynaddr; + int sysctl_ip_early_demux; #ifdef CONFIG_NET_L3_MASTER_DEV - u8 sysctl_raw_l3mdev_accept; + int sysctl_raw_l3mdev_accept; #endif int sysctl_tcp_early_demux; int sysctl_udp_early_demux; - u8 sysctl_nexthop_compat_mode; + int sysctl_nexthop_compat_mode; - u8 sysctl_fwmark_reflect; + int sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; #ifdef CONFIG_NET_L3_MASTER_DEV int sysctl_tcp_l3mdev_accept; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d1aa5e294f10..070fd0670d00 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -540,30 +540,30 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "icmp_echo_ignore_all", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_all, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "icmp_echo_ignore_broadcasts", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_broadcasts, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "icmp_ignore_bogus_error_responses", .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "icmp_errors_use_inbound_ifaddr", .data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "icmp_ratelimit", @@ -590,9 +590,9 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "raw_l3mdev_accept", .data = &init_net.ipv4.sysctl_raw_l3mdev_accept, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -600,30 +600,30 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_ecn", .data = &init_net.ipv4.sysctl_tcp_ecn, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "tcp_ecn_fallback", .data = &init_net.ipv4.sysctl_tcp_ecn_fallback, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "ip_dynaddr", .data = &init_net.ipv4.sysctl_ip_dynaddr, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "ip_early_demux", .data = &init_net.ipv4.sysctl_ip_early_demux, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "udp_early_demux", @@ -642,18 +642,18 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "nexthop_compat_mode", .data = &init_net.ipv4.sysctl_nexthop_compat_mode, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "ip_default_ttl", .data = &init_net.ipv4.sysctl_ip_default_ttl, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = &ip_ttl_min, .extra2 = &ip_ttl_max, }, @@ -681,16 +681,16 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "ip_no_pmtu_disc", .data = &init_net.ipv4.sysctl_ip_no_pmtu_disc, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "ip_forward_use_pmtu", .data = &init_net.ipv4.sysctl_ip_fwd_use_pmtu, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec, }, { .procname = "ip_forward_update_priority", @@ -704,25 +704,25 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "ip_nonlocal_bind", .data = &init_net.ipv4.sysctl_ip_nonlocal_bind, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec }, { .procname = "ip_autobind_reuse", .data = &init_net.ipv4.sysctl_ip_autobind_reuse, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "fwmark_reflect", .data = &init_net.ipv4.sysctl_fwmark_reflect, - .maxlen = sizeof(u8), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dou8vec_minmax, + .proc_handler = proc_dointvec, }, { .procname = "tcp_fwmark_accept", From a406acdee08ed1ae27757ead88b9618add6398df Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 18 Apr 2023 08:07:02 +0000 Subject: [PATCH 2658/4345] ANDROID: preserve CRC for xhci symbols In release 5.10.178 a new .h file was included in the xhci code, which caused the CRCs to change as some structures changed into "real" structures instead of anonymous definitions. So preserve the CRCs by commenting out the #include if GENKSYMS is being calculated. Bug: 161946584 Fixes: ec20260950af ("xhci: also avoid the XHCI_ZERO_64B_REGS quirk with a passthrough iommu") Signed-off-by: Greg Kroah-Hartman Change-Id: I59838b0af869d3e17fc73d72eb473190c50281fd --- drivers/usb/host/xhci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index b2960ff34416..972cee01dbb9 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -9,7 +9,9 @@ */ #include +#ifndef __GENKSYMS__ /* ANDROID: KABI CRC preservation hack */ #include +#endif #include #include #include From 49652e1bbd0a2da40de02dd06bbb865fdd70fa4e Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 19 Apr 2023 06:46:08 +0000 Subject: [PATCH 2659/4345] UPSTREAM: Revert "ext4: fix use-after-free in ext4_xattr_set_entry" This reverts commit bb8592efcf8ef2f62947745d3182ea05b5256a15 which is commit 67d7d8ad99beccd9fe92d585b87f1760dc9018e3 upstream. The order in which patches are queued to stable matters. This patch has a logical dependency on commit 310c097c2bdbea253d6ee4e064f3e65580ef93ac upstream, and failing to queue the latter results in a null-ptr-deref reported at the Link below. In order to avoid conflicts on stable, revert the commit just so that we can queue its prerequisite patch first and then queue the same after. Link: https://syzkaller.appspot.com/bug?extid=d5ebf56f3b1268136afd Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman Bug: 253759004 Change-Id: I0e09ac2e68c2b21834ccd620c79f73fadc420170 (cherry picked from commit 9400206d9d5eebc0317da4151364ade32d28944f) Signed-off-by: Tudor Ambarus --- fs/ext4/xattr.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index b80ad5a7b05c..3c570ea4d0a6 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2182,9 +2182,8 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_inode *raw_inode; int error; - if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) + if (EXT4_I(inode)->i_extra_isize == 0) return 0; - raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); @@ -2212,9 +2211,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, struct ext4_xattr_search *s = &is->s; int error; - if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) + if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; - error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; From 3acba5c435917699725890bbc55e96a961b92178 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 19 Apr 2023 06:46:09 +0000 Subject: [PATCH 2660/4345] UPSTREAM: ext4: remove duplicate definition of ext4_xattr_ibody_inline_set() [ Upstream commit 310c097c2bdbea253d6ee4e064f3e65580ef93ac ] ext4_xattr_ibody_inline_set() & ext4_xattr_ibody_set() have the exact same definition. Hence remove ext4_xattr_ibody_inline_set() and all its call references. Convert the callers of it to call ext4_xattr_ibody_set() instead. [ Modified to preserve ext4_xattr_ibody_set() and remove ext4_xattr_ibody_inline_set() instead. -- TYT ] Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/fd566b799bbbbe9b668eb5eecde5b5e319e3694f.1622685482.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman Bug: 253759004 Change-Id: Iaf02894c4f88d79d85ed00363fc83d4b3ba8c575 Signed-off-by: Tudor Ambarus --- fs/ext4/inline.c | 11 +++++------ fs/ext4/xattr.c | 26 +------------------------- fs/ext4/xattr.h | 6 +++--- 3 files changed, 9 insertions(+), 34 deletions(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index cd575062787a..0121484a41d9 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -208,7 +208,7 @@ out: /* * write the buffer to the inline inode. * If 'create' is set, we don't need to do the extra copy in the xattr - * value since it is already handled by ext4_xattr_ibody_inline_set. + * value since it is already handled by ext4_xattr_ibody_set. * That saves us one memcpy. */ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, @@ -290,7 +290,7 @@ static int ext4_create_inline_data(handle_t *handle, BUG_ON(!is.s.not_found); - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) { if (error == -ENOSPC) ext4_clear_inode_state(inode, @@ -362,7 +362,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, i.value = value; i.value_len = len; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -435,7 +435,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle, if (error) goto out; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -1950,8 +1950,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) i.value = value; i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ? i_size - EXT4_MIN_INLINE_DATA_SIZE : 0; - err = ext4_xattr_ibody_inline_set(handle, inode, - &i, &is); + err = ext4_xattr_ibody_set(handle, inode, &i, &is); if (err) goto out_error; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 3c570ea4d0a6..9cca06a7e9dd 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2203,31 +2203,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, return 0; } -int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is) -{ - struct ext4_xattr_ibody_header *header; - struct ext4_xattr_search *s = &is->s; - int error; - - if (EXT4_I(inode)->i_extra_isize == 0) - return -ENOSPC; - error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); - if (error) - return error; - header = IHDR(inode, ext4_raw_inode(&is->iloc)); - if (!IS_LAST_ENTRY(s->first)) { - header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); - ext4_set_inode_state(inode, EXT4_STATE_XATTR); - } else { - header->h_magic = cpu_to_le32(0); - ext4_clear_inode_state(inode, EXT4_STATE_XATTR); - } - return 0; -} - -static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, +int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index b357872ab83b..e5e36bd11f05 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -200,9 +200,9 @@ extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, extern int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size); -extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is); +extern int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is); extern struct mb_cache *ext4_xattr_create_cache(void); extern void ext4_xattr_destroy_cache(struct mb_cache *); From 4d2352ab07ad3dd1f16fd79e50e2815c8daf135f Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 19 Apr 2023 06:46:10 +0000 Subject: [PATCH 2661/4345] UPSTREAM: ext4: fix use-after-free in ext4_xattr_set_entry [ Upstream commit 67d7d8ad99beccd9fe92d585b87f1760dc9018e3 ] Hulk Robot reported a issue: ================================================================== BUG: KASAN: use-after-free in ext4_xattr_set_entry+0x18ab/0x3500 Write of size 4105 at addr ffff8881675ef5f4 by task syz-executor.0/7092 CPU: 1 PID: 7092 Comm: syz-executor.0 Not tainted 4.19.90-dirty #17 Call Trace: [...] memcpy+0x34/0x50 mm/kasan/kasan.c:303 ext4_xattr_set_entry+0x18ab/0x3500 fs/ext4/xattr.c:1747 ext4_xattr_ibody_inline_set+0x86/0x2a0 fs/ext4/xattr.c:2205 ext4_xattr_set_handle+0x940/0x1300 fs/ext4/xattr.c:2386 ext4_xattr_set+0x1da/0x300 fs/ext4/xattr.c:2498 __vfs_setxattr+0x112/0x170 fs/xattr.c:149 __vfs_setxattr_noperm+0x11b/0x2a0 fs/xattr.c:180 __vfs_setxattr_locked+0x17b/0x250 fs/xattr.c:238 vfs_setxattr+0xed/0x270 fs/xattr.c:255 setxattr+0x235/0x330 fs/xattr.c:520 path_setxattr+0x176/0x190 fs/xattr.c:539 __do_sys_lsetxattr fs/xattr.c:561 [inline] __se_sys_lsetxattr fs/xattr.c:557 [inline] __x64_sys_lsetxattr+0xc2/0x160 fs/xattr.c:557 do_syscall_64+0xdf/0x530 arch/x86/entry/common.c:298 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x459fe9 RSP: 002b:00007fa5e54b4c08 EFLAGS: 00000246 ORIG_RAX: 00000000000000bd RAX: ffffffffffffffda RBX: 000000000051bf60 RCX: 0000000000459fe9 RDX: 00000000200003c0 RSI: 0000000020000180 RDI: 0000000020000140 RBP: 000000000051bf60 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000001009 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffc73c93fc0 R14: 000000000051bf60 R15: 00007fa5e54b4d80 [...] ================================================================== Above issue may happen as follows: ------------------------------------- ext4_xattr_set ext4_xattr_set_handle ext4_xattr_ibody_find >> s->end < s->base >> no EXT4_STATE_XATTR >> xattr_check_inode is not executed ext4_xattr_ibody_set ext4_xattr_set_entry >> size_t min_offs = s->end - s->base >> UAF in memcpy we can easily reproduce this problem with the following commands: mkfs.ext4 -F /dev/sda mount -o debug_want_extra_isize=128 /dev/sda /mnt touch /mnt/file setfattr -n user.cat -v `seq -s z 4096|tr -d '[:digit:]'` /mnt/file In ext4_xattr_ibody_find, we have the following assignment logic: header = IHDR(inode, raw_inode) = raw_inode + EXT4_GOOD_OLD_INODE_SIZE + i_extra_isize is->s.base = IFIRST(header) = header + sizeof(struct ext4_xattr_ibody_header) is->s.end = raw_inode + s_inode_size In ext4_xattr_set_entry min_offs = s->end - s->base = s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - i_extra_isize - sizeof(struct ext4_xattr_ibody_header) last = s->first free = min_offs - ((void *)last - s->base) - sizeof(__u32) = s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - i_extra_isize - sizeof(struct ext4_xattr_ibody_header) - sizeof(__u32) In the calculation formula, all values except s_inode_size and i_extra_size are fixed values. When i_extra_size is the maximum value s_inode_size - EXT4_GOOD_OLD_INODE_SIZE, min_offs is -4 and free is -8. The value overflows. As a result, the preceding issue is triggered when memcpy is executed. Therefore, when finding xattr or setting xattr, check whether there is space for storing xattr in the inode to resolve this issue. Cc: stable@kernel.org Reported-by: Hulk Robot Signed-off-by: Baokun Li Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20220616021358.2504451-3-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Tudor Ambarus Signed-off-by: Greg Kroah-Hartman Bug: 253759004 Change-Id: Ib0e74eb2b13884e6ee773748b62cd8a0bcfab3f3 Signed-off-by: Tudor Ambarus --- fs/ext4/xattr.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 9cca06a7e9dd..6fee044fd158 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2182,8 +2182,9 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_inode *raw_inode; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0; + raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); @@ -2211,8 +2212,9 @@ int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_search *s = &is->s; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return -ENOSPC; + error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; From 49df5be9231bc452e7cdee9c797b162a647beab6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 1 May 2023 23:26:19 +0000 Subject: [PATCH 2662/4345] Revert "ASoC: hdac_hdmi: use set_stream() instead of set_tdm_slots()" This reverts commit acbbfdba9ca67ef6bc174a0a42666004aee4d931. The function this uses has been reverted from Android kernels, so revert this to fix the build problems in 5.10.178 Fixes: 791a854ae5a5 ("Linux 5.10.178") Change-Id: Id2c260f023e9e26ab2333a13ecf890f321f28af0 Signed-off-by: Greg Kroah-Hartman --- sound/soc/codecs/hdac_hdmi.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index 6de3e47b92d8..2c1305bf0572 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -436,28 +436,23 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_device *hdev, return 0; } -static int hdac_hdmi_set_stream(struct snd_soc_dai *dai, - void *stream, int direction) +static int hdac_hdmi_set_tdm_slot(struct snd_soc_dai *dai, + unsigned int tx_mask, unsigned int rx_mask, + int slots, int slot_width) { struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai); struct hdac_device *hdev = hdmi->hdev; struct hdac_hdmi_dai_port_map *dai_map; struct hdac_hdmi_pcm *pcm; - struct hdac_stream *hstream; - if (!stream) - return -EINVAL; - - hstream = (struct hdac_stream *)stream; - - dev_dbg(&hdev->dev, "%s: strm_tag: %d\n", __func__, hstream->stream_tag); + dev_dbg(&hdev->dev, "%s: strm_tag: %d\n", __func__, tx_mask); dai_map = &hdmi->dai_map[dai->id]; pcm = hdac_hdmi_get_pcm_from_cvt(hdmi, dai_map->cvt); if (pcm) - pcm->stream_tag = (hstream->stream_tag << 4); + pcm->stream_tag = (tx_mask << 4); return 0; } @@ -1549,7 +1544,7 @@ static const struct snd_soc_dai_ops hdmi_dai_ops = { .startup = hdac_hdmi_pcm_open, .shutdown = hdac_hdmi_pcm_close, .hw_params = hdac_hdmi_set_hw_params, - .set_stream = hdac_hdmi_set_stream, + .set_tdm_slot = hdac_hdmi_set_tdm_slot, }; /* From e2ed7e5048bf80da1604616be758e25fdefab33f Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Tue, 15 Mar 2022 21:14:14 -0700 Subject: [PATCH 2663/4345] BACKPORT: f2fs: introduce gc_urgent_mid mode We need a mid level of gc urgent mode to do GC forcibly in a period of given gc_urgent_sleep_time, but not like using greedy GC approach and switching to SSR mode such as gc urgent high mode. This can be used for more aggressive periodic storage clean up. Signed-off-by: Daeho Jeong Signed-off-by: Jaegeuk Kim BUG: 279706487 Change-Id: I52405f36fcbc0b9ffae1abba3b215ba8506ef6a1 (cherry picked from commit d98af5f4552058a5c22030641ef79cee92c61f54) [Dylan: Resolved minor conflict in fs/f2fs/gc.c ] Signed-off-by: Dylan Chang --- Documentation/ABI/testing/sysfs-fs-f2fs | 17 +++++++++++------ fs/f2fs/debug.c | 4 +++- fs/f2fs/f2fs.h | 4 ++++ fs/f2fs/gc.c | 3 ++- fs/f2fs/sysfs.c | 7 +++++++ 5 files changed, 27 insertions(+), 8 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 75f4bbb06c4d..020284afa78d 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -271,11 +271,16 @@ Description: Shows current reserved blocks in system, it may be temporarily What: /sys/fs/f2fs//gc_urgent Date: August 2017 Contact: "Jaegeuk Kim" -Description: Do background GC agressively when set. When gc_urgent = 1, - background thread starts to do GC by given gc_urgent_sleep_time - interval. When gc_urgent = 2, F2FS will lower the bar of - checking idle in order to process outstanding discard commands - and GC a little bit aggressively. It is set to 0 by default. +Description: Do background GC aggressively when set. Set to 0 by default. + gc urgent high(1): does GC forcibly in a period of given + gc_urgent_sleep_time and ignores I/O idling check. uses greedy + GC approach and turns SSR mode on. + gc urgent low(2): lowers the bar of checking I/O idling in + order to process outstanding discard commands and GC a + little bit aggressively. uses cost benefit GC approach. + gc urgent mid(3): does GC forcibly in a period of given + gc_urgent_sleep_time and executes a mid level of I/O idling check. + uses cost benefit GC approach. What: /sys/fs/f2fs//gc_urgent_sleep_time Date: August 2017 @@ -506,7 +511,7 @@ Date: July 2021 Contact: "Daeho Jeong" Description: Show how many segments have been reclaimed by GC during a specific GC mode (0: GC normal, 1: GC idle CB, 2: GC idle greedy, - 3: GC idle AT, 4: GC urgent high, 5: GC urgent low) + 3: GC idle AT, 4: GC urgent high, 5: GC urgent low 6: GC urgent mid) You can re-initialize this value to "0". What: /sys/fs/f2fs//gc_segment_mode diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index f33e64acaf2b..a549f7b192d1 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -469,12 +469,14 @@ static int stat_show(struct seq_file *s, void *v) si->node_segs, si->bg_node_segs); seq_printf(s, " - Reclaimed segs : Normal (%d), Idle CB (%d), " "Idle Greedy (%d), Idle AT (%d), " - "Urgent High (%d), Urgent Low (%d)\n", + "Urgent High (%d), Urgent Mid (%d), " + "Urgent Low (%d)\n", si->sbi->gc_reclaimed_segs[GC_NORMAL], si->sbi->gc_reclaimed_segs[GC_IDLE_CB], si->sbi->gc_reclaimed_segs[GC_IDLE_GREEDY], si->sbi->gc_reclaimed_segs[GC_IDLE_AT], si->sbi->gc_reclaimed_segs[GC_URGENT_HIGH], + si->sbi->gc_reclaimed_segs[GC_URGENT_MID], si->sbi->gc_reclaimed_segs[GC_URGENT_LOW]); seq_printf(s, "Try to move %d blocks (BG: %d)\n", si->tot_blks, si->bg_data_blks + si->bg_node_blks); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 2e13419f93e8..1e53d000490c 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1286,6 +1286,7 @@ enum { GC_IDLE_AT, GC_URGENT_HIGH, GC_URGENT_LOW, + GC_URGENT_MID, MAX_GC_MODE, }; @@ -2754,6 +2755,9 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type) if (is_inflight_io(sbi, type)) return false; + if (sbi->gc_mode == GC_URGENT_MID) + return true; + if (sbi->gc_mode == GC_URGENT_LOW && (type == DISCARD_TIME || type == GC_TIME)) return true; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 71f969a8023f..2861b99704ff 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -90,7 +90,8 @@ static int gc_thread_func(void *data) * invalidated soon after by user update or deletion. * So, I'd like to wait some time to collect dirty segments. */ - if (sbi->gc_mode == GC_URGENT_HIGH) { + if (sbi->gc_mode == GC_URGENT_HIGH || + sbi->gc_mode == GC_URGENT_MID) { wait_ms = gc_th->urgent_sleep_time; f2fs_down_write(&sbi->gc_lock); goto do_gc; diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index a095919c55ad..07cdf2eef064 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -466,6 +466,13 @@ out: } } else if (t == 2) { sbi->gc_mode = GC_URGENT_LOW; + } else if (t == 3) { + sbi->gc_mode = GC_URGENT_MID; + if (sbi->gc_thread) { + sbi->gc_thread->gc_wake = 1; + wake_up_interruptible_all( + &sbi->gc_thread->gc_wait_queue_head); + } } else { return -EINVAL; } From 00499a5f22b015db989eb07ea02f731143946f7b Mon Sep 17 00:00:00 2001 From: Giuliano Procida Date: Wed, 3 May 2023 09:23:05 +0100 Subject: [PATCH 2664/4345] ANDROID: GKI: reorder symbols within ABI files This matches the extract_symbols ordering. Bug: 280431338 Change-Id: Iec287562393379fa6cf93be9a617deb09ed427fa Signed-off-by: Giuliano Procida --- android/abi_gki_aarch64_asus | 2 +- android/abi_gki_aarch64_exynos | 8 +- android/abi_gki_aarch64_galaxy | 7146 +++++++++++------------ android/abi_gki_aarch64_generic | 8 +- android/abi_gki_aarch64_lenovo | 10 +- android/abi_gki_aarch64_mtk | 6 +- android/abi_gki_aarch64_oplus | 78 +- android/abi_gki_aarch64_qcom | 10 +- android/abi_gki_aarch64_transsion | 110 +- android/abi_gki_aarch64_type_visibility | 2 +- android/abi_gki_aarch64_vivo | 6 +- android/abi_gki_aarch64_xiaomi | 130 +- 12 files changed, 3758 insertions(+), 3758 deletions(-) diff --git a/android/abi_gki_aarch64_asus b/android/abi_gki_aarch64_asus index a44e7e67e0e4..0c3159dcda6f 100644 --- a/android/abi_gki_aarch64_asus +++ b/android/abi_gki_aarch64_asus @@ -265,8 +265,8 @@ up_read up_write vfree vfs_fsync_range -vmalloc __vmalloc +vmalloc vsnprintf vzalloc __wait_on_buffer diff --git a/android/abi_gki_aarch64_exynos b/android/abi_gki_aarch64_exynos index 0b37ab51884c..5f0526297f1c 100644 --- a/android/abi_gki_aarch64_exynos +++ b/android/abi_gki_aarch64_exynos @@ -73,9 +73,9 @@ blocking_notifier_call_chain blocking_notifier_chain_register blocking_notifier_chain_unregister - bpf_trace_run1 bpf_trace_run10 bpf_trace_run12 + bpf_trace_run1 bpf_trace_run2 bpf_trace_run3 bpf_trace_run4 @@ -1044,9 +1044,9 @@ is_dma_buf_file is_vmalloc_addr iterate_fd - jiffies jiffies_64_to_clock_t jiffies64_to_msecs + jiffies jiffies_to_msecs jiffies_to_usecs kasan_flag_enabled @@ -1167,8 +1167,8 @@ memory_read_from_buffer memparse memremap - memset memset64 + memset __memset_io memstart_addr memunmap @@ -1262,8 +1262,8 @@ nla_find nla_memcpy __nla_parse - nla_put nla_put_64bit + nla_put nla_put_nohdr nla_reserve __nla_validate diff --git a/android/abi_gki_aarch64_galaxy b/android/abi_gki_aarch64_galaxy index 7ba5f74f973a..6b921ab3a901 100644 --- a/android/abi_gki_aarch64_galaxy +++ b/android/abi_gki_aarch64_galaxy @@ -1,121 +1,1948 @@ [abi_symbol_list] - PDE_DATA - __ClearPageMovable - __SetPageMovable - ___pskb_trim - ___ratelimit + access_process_vm + ack_all_badblocks + activate_task + add_cpu + add_device_randomness + add_memory + add_memory_subsection + add_taint + add_timer + add_timer_on + add_uevent_var + add_wait_queue + adjust_managed_page_count + alarm_cancel + alarm_init + alarm_start + alarm_start_relative + alarmtimer_get_rtcdev + alarm_try_to_cancel + alloc_anon_inode + alloc_chrdev_region __alloc_disk_node + alloc_etherdev_mqs + alloc_io_pgtable_ops + alloc_netdev_mqs + alloc_page_buffers + alloc_pages_exact __alloc_pages_nodemask __alloc_percpu __alloc_percpu_gfp __alloc_skb + alloc_skb_with_frags + alloc_workqueue + all_vm_events + amba_bustype + amba_driver_register + amba_driver_unregister + amba_release_regions + amba_request_regions + android_debug_per_cpu_symbol + android_debug_symbol + android_rvh_probe_register + anon_inode_getfd + anon_inode_getfile __arch_clear_user __arch_copy_from_user __arch_copy_in_user __arch_copy_to_user + arch_timer_read_counter + argv_free + argv_split + arm64_const_caps_ready + arm64_use_ng_mappings __arm_smccc_hvc __arm_smccc_smc + async_schedule_node + async_schedule_node_domain + async_synchronize_full_domain + _atomic_dec_and_lock + atomic_notifier_call_chain + atomic_notifier_chain_register + atomic_notifier_chain_unregister + autoremove_wake_function + available_idle_cpu + backlight_device_get_by_type + backlight_device_register + backlight_device_set_brightness + backlight_device_unregister + badblocks_clear + badblocks_exit + badblocks_init + badblocks_set + badblocks_show + badblocks_store + balloon_aops + balloon_page_alloc + balloon_page_dequeue + balloon_page_enqueue + bcmp + bdev_check_media_change + bdevname + bdev_read_only + bdget_disk + bd_link_disk_holder + bdput + bd_set_nr_sectors + bd_unlink_disk_holder + bgpio_init + bin2hex + bio_add_page + bio_alloc_bioset + bio_associate_blkg + bio_chain + bio_clone_blkg_association + bio_endio + bio_init + bio_put + bioset_exit + bioset_init + bitmap_allocate_region __bitmap_andnot __bitmap_clear __bitmap_complement + bitmap_find_next_zero_area_off + bitmap_from_arr32 __bitmap_or + bitmap_parse + bitmap_parselist + bitmap_parselist_user + bitmap_print_to_pagebuf + bitmap_release_region __bitmap_set + bitmap_to_arr32 __bitmap_weight __bitmap_xor - __blk_mq_debugfs_rq_show - __blk_mq_end_request - __blk_rq_map_sg + bitmap_zalloc + blk_alloc_queue + blkcg_activate_policy + blkcg_deactivate_policy + blkcg_policy_register + blkcg_policy_unregister + blkcg_root + blk_cleanup_queue + blkdev_fsync + blkdev_get_by_dev + blkdev_get_by_path __blkdev_issue_discard + blkdev_issue_flush __blkdev_issue_zeroout + blkdev_put + blk_execute_rq + blk_execute_rq_nowait + blk_finish_plug + blk_freeze_queue_start + blk_get_queue + blk_get_request + blkg_lookup_slowpath + blk_mq_alloc_request + blk_mq_alloc_request_hctx + blk_mq_alloc_tag_set + blk_mq_complete_request + blk_mq_complete_request_remote + __blk_mq_debugfs_rq_show + blk_mq_debugfs_rq_show + blk_mq_delay_kick_requeue_list + __blk_mq_end_request + blk_mq_end_request + blk_mq_free_request + blk_mq_free_tag_set + blk_mq_freeze_queue + blk_mq_freeze_queue_wait + blk_mq_freeze_queue_wait_timeout + blk_mq_init_queue + blk_mq_map_queues + blk_mq_pci_map_queues + blk_mq_quiesce_queue + blk_mq_requeue_request + blk_mq_rq_cpu + blk_mq_run_hw_queues + blk_mq_sched_request_inserted + blk_mq_sched_try_insert_merge + blk_mq_sched_try_merge + blk_mq_start_request + blk_mq_start_stopped_hw_queues + blk_mq_stop_hw_queue + blk_mq_tagset_busy_iter + blk_mq_tagset_wait_completed_request + blk_mq_tag_to_rq + blk_mq_unfreeze_queue + blk_mq_unique_tag + blk_mq_unquiesce_queue + blk_mq_update_nr_hw_queues + blk_mq_virtio_map_queues + blk_poll + blk_put_queue + blk_put_request + blk_queue_alignment_offset + blk_queue_bounce_limit + blk_queue_can_use_dma_map_merging + blk_queue_chunk_sectors + blk_queue_dma_alignment + blk_queue_flag_clear + blk_queue_flag_set + blk_queue_flag_test_and_set + blk_queue_io_min + blk_queue_io_opt + blk_queue_logical_block_size + blk_queue_max_discard_sectors + blk_queue_max_discard_segments + blk_queue_max_hw_sectors + blk_queue_max_segments + blk_queue_max_segment_size + blk_queue_max_write_zeroes_sectors + blk_queue_physical_block_size + blk_queue_rq_timeout + blk_queue_split + blk_queue_virt_boundary + blk_queue_write_cache + blk_register_region + blk_rq_map_kern + __blk_rq_map_sg + blk_rq_map_user + blk_rq_map_user_iov + blk_rq_unmap_user + blk_set_queue_dying + blk_set_stacking_limits + blk_start_plug + blk_status_to_errno + blk_sync_queue + blk_unregister_region + blk_update_request + blk_verify_command + blocking_notifier_call_chain + blocking_notifier_chain_register + blocking_notifier_chain_unregister + bmap + bpf_dispatcher_xdp_func + bpf_prog_add + bpf_prog_put + bpf_prog_sub + bpf_stats_enabled_key + bpf_trace_run10 + bpf_trace_run11 + bpf_trace_run12 + bpf_trace_run1 + bpf_trace_run2 + bpf_trace_run3 + bpf_trace_run4 + bpf_trace_run5 + bpf_trace_run6 + bpf_trace_run7 + bpf_trace_run8 + bpf_trace_run9 + bpf_warn_invalid_xdp_action + bsearch + bt_err + bt_info + build_skb + bus_find_device + bus_for_each_dev + bus_for_each_drv + bus_register + bus_register_notifier + bus_set_iommu + bus_unregister + bus_unregister_notifier + cache_line_size + call_netdevice_notifiers + call_rcu + call_rcu_tasks + call_rcu_tasks_trace + call_srcu + cancel_delayed_work + cancel_delayed_work_sync + cancel_work_sync + capable + cdc_ncm_bind_common + cdc_ncm_change_mtu + cdc_ncm_fill_tx_frame + cdc_ncm_rx_verify_ndp16 + cdc_ncm_rx_verify_nth16 + cdc_ncm_select_altsetting + cdc_ncm_unbind + cdc_parse_cdc_header + cdev_add + cdev_alloc + cdev_del + cdev_device_add + cdev_device_del + cdev_init + cec_allocate_adapter + cec_delete_adapter + cec_received_msg_ts + cec_register_adapter + cec_s_log_addrs + cec_s_phys_addr + cec_s_phys_addr_from_edid + cec_transmit_attempt_done_ts + cec_transmit_done_ts + cec_unregister_adapter __cfi_slowpath + cgroup_path_ns + cgroup_taskset_first + cgroup_taskset_next __check_object_size + check_preempt_curr + check_zeroed_user __class_create + class_create_file_ns + class_destroy + class_find_device + class_for_each_device + class_interface_unregister __class_register + class_remove_file_ns + class_unregister + cleancache_register_ops + cleanup_srcu_struct + clear_page + __ClearPageMovable + clk_bulk_disable + clk_bulk_enable + clk_bulk_get_all + clk_bulk_prepare + clk_bulk_put_all + clk_bulk_unprepare __clk_determine_rate + clk_disable + clk_enable + clk_fixed_factor_ops + clk_fixed_rate_ops + clk_get __clk_get_hw __clk_get_name + clk_get_parent + clk_get_rate + clk_hw_get_flags + clk_hw_get_name + clk_hw_get_num_parents + clk_hw_get_parent + clk_hw_get_parent_by_index + clk_hw_get_rate + clk_hw_is_enabled + clk_hw_is_prepared + clk_hw_register __clk_hw_register_divider + clk_hw_register_fixed_factor __clk_hw_register_gate __clk_hw_register_mux + clk_hw_round_rate + clk_hw_set_rate_range + clk_hw_unregister + clk_hw_unregister_divider + clk_hw_unregister_fixed_factor + clk_hw_unregister_gate + clk_hw_unregister_mux __clk_is_enabled __clk_mux_determine_rate_closest + clk_notifier_register + clk_notifier_unregister + clk_prepare + clk_put + clk_register + clk_register_clkdev + clk_register_fixed_factor + clk_register_fixed_rate + clk_register_gate + clk_round_rate + clk_set_parent + clk_set_rate + clk_sync_state + clk_unprepare + clk_unregister + clockevents_config_and_register + clocks_calc_mult_shift __clocksource_register_scale __close_fd + cma_alloc + cma_for_each_area + cma_get_name + cma_release + compat_alloc_user_space + compat_only_sysfs_link_entry_to_kobj + compat_ptr_ioctl + complete + complete_all + complete_and_exit + completion_done + component_add + component_bind_all + component_del + component_master_add_with_match + component_master_del + component_match_add_release + component_unbind_all + cond_synchronize_rcu + config_ep_by_speed + configfs_register_subsystem + configfs_unregister_subsystem + config_group_init + config_group_init_type_name + config_item_get + config_item_put + console_drivers + console_printk + console_stop + console_suspend_enabled + console_trylock + console_unlock __const_udelay + consume_skb + contig_page_data + _copy_from_iter + _copy_from_iter_full + copy_from_kernel_nofault + copy_page + _copy_to_iter __cpu_active_mask - __cpu_online_mask - __cpu_possible_mask - __cpu_present_mask + cpu_all_bits + cpu_bit_bitmap + cpufreq_add_update_util_hook + cpufreq_cpu_get + cpufreq_cpu_get_raw + cpufreq_cpu_put + cpufreq_disable_fast_switch + cpufreq_driver_fast_switch + cpufreq_driver_resolve_freq __cpufreq_driver_target + cpufreq_enable_boost_support + cpufreq_enable_fast_switch + cpufreq_freq_attr_scaling_available_freqs + cpufreq_freq_attr_scaling_boost_freqs + cpufreq_freq_transition_begin + cpufreq_freq_transition_end + cpufreq_frequency_table_verify + cpufreq_generic_attr + cpufreq_generic_frequency_table_verify + cpufreq_generic_get + cpufreq_generic_suspend + cpufreq_get_driver_data + cpufreq_get_policy + cpufreq_policy_transition_delay_us + cpufreq_quick_get + cpufreq_quick_get_max + cpufreq_register_driver + cpufreq_register_governor + cpufreq_register_notifier + cpufreq_remove_update_util_hook + cpufreq_table_index_unsorted + cpufreq_this_cpu_can_update + cpufreq_unregister_driver + cpufreq_unregister_notifier + cpufreq_update_policy + cpu_hotplug_disable + cpu_hotplug_enable __cpuhp_remove_state __cpuhp_setup_state __cpuhp_setup_state_cpuslocked __cpuhp_state_add_instance __cpuhp_state_remove_instance + cpuhp_tasks_frozen + cpu_hwcap_keys + cpu_hwcaps + cpuidle_governor_latency_req + cpuidle_register_governor + cpu_irqtime + cpu_is_hotpluggable + cpu_latency_qos_add_request + cpu_latency_qos_remove_request + cpu_latency_qos_request_active + cpu_latency_qos_update_request + cpumask_any_but + cpumask_next + cpumask_next_and + cpumask_next_wrap + cpu_number + __cpu_online_mask + cpu_pm_register_notifier + cpu_pm_unregister_notifier + __cpu_possible_mask + __cpu_present_mask + cpupri_find_fitness + cpu_scale + cpus_read_lock + cpus_read_unlock + cpu_subsys + cpu_topology + crc16 + crc32_le + crc8 + crc8_populate_msb + create_function_device + crypto_aead_encrypt + crypto_aead_setauthsize + crypto_aead_setkey + crypto_alloc_aead + crypto_alloc_base + crypto_alloc_shash + crypto_alloc_skcipher + crypto_cipher_encrypt_one + crypto_cipher_setkey + crypto_comp_compress + crypto_comp_decompress + crypto_destroy_tfm + crypto_has_alg + crypto_register_alg + crypto_register_rngs + crypto_register_scomp + crypto_shash_digest + crypto_shash_final + crypto_shash_setkey + crypto_shash_update + crypto_skcipher_decrypt + crypto_skcipher_encrypt + crypto_skcipher_setkey + crypto_unregister_alg + crypto_unregister_rngs + crypto_unregister_scomp + css_next_child + css_next_descendant_pre + csum_ipv6_magic + csum_partial + csum_tcpudp_nofold + _ctype + current_time + current_work + d_add + d_alloc_name + dapm_pinctrl_event + dapm_regulator_event + datagram_poll + d_delete + deactivate_task + debugfs_attr_read + debugfs_attr_write + debugfs_create_atomic_t + debugfs_create_blob + debugfs_create_bool + debugfs_create_dir + debugfs_create_file + debugfs_create_file_unsafe + debugfs_create_regset32 + debugfs_create_size_t + debugfs_create_symlink + debugfs_create_u16 + debugfs_create_u32 + debugfs_create_u64 + debugfs_create_u8 + debugfs_create_ulong + debugfs_create_x32 + debugfs_create_x64 + debugfs_create_x8 + debugfs_file_get + debugfs_file_put + debugfs_lookup + debugfs_print_regs32 + debugfs_remove + dec_zone_page_state + default_llseek + deferred_free + delayed_work_timer_fn + del_gendisk + del_timer + del_timer_sync + desc_to_gpio + destroy_workqueue + _dev_alert + dev_alloc_name + dev_close + dev_coredumpm + dev_coredumpv + _dev_crit + dev_driver_string + _dev_emerg + _dev_err + dev_err_probe + devfreq_add_device + devfreq_add_governor + devfreq_cooling_unregister + devfreq_get_devfreq_by_phandle + devfreq_monitor_resume + devfreq_monitor_start + devfreq_monitor_stop + devfreq_monitor_suspend + devfreq_recommended_opp + devfreq_register_opp_notifier + devfreq_remove_device + devfreq_remove_governor + devfreq_resume_device + devfreq_suspend_device + devfreq_unregister_opp_notifier + devfreq_update_interval + dev_fwnode __dev_get_by_index + dev_get_by_index + dev_get_by_name + dev_get_regmap + dev_get_stats + device_add + device_add_disk + device_add_groups + device_attach + device_bind_driver + device_create + device_create_bin_file + device_create_file + device_create_with_groups + device_del + device_destroy + device_find_child + device_for_each_child + device_get_child_node_count + device_get_dma_attr + device_get_mac_address + device_get_match_data + device_get_named_child_node + device_get_next_child_node + device_initialize + device_init_wakeup + device_link_add + device_link_del + device_match_fwnode + device_match_name + device_match_of_node + device_property_present + device_property_read_string + device_property_read_string_array + device_property_read_u16_array + device_property_read_u32_array + device_property_read_u8_array + device_register + device_release_driver + device_remove_bin_file + device_remove_file + device_remove_file_self + device_remove_groups + device_set_wakeup_capable + device_set_wakeup_enable + device_show_bool + device_show_int + device_store_bool + device_store_int + device_unregister + device_wakeup_disable + device_wakeup_enable + _dev_info __dev_kfree_skb_any + devm_add_action __devm_alloc_percpu + devm_backlight_device_register + devm_backlight_device_unregister + devm_blk_ksm_init + devm_clk_bulk_get + devm_clk_bulk_get_all + devm_clk_bulk_get_optional + devm_clk_get + devm_clk_get_optional + devm_clk_hw_register + devm_clk_hw_register_clkdev + devm_clk_put + devm_clk_register + dev_mc_sync_multiple + dev_mc_unsync + devm_devfreq_add_device + devm_devfreq_register_notifier + devm_devfreq_unregister_notifier + devm_device_add_group + devm_device_add_groups + devm_device_remove_group __devm_drm_dev_alloc + devm_drm_panel_bridge_add_typed + devm_extcon_dev_allocate + devm_extcon_dev_register + devm_extcon_dev_unregister + devm_extcon_register_notifier + devm_free_irq + devm_free_percpu + devm_gen_pool_create + devm_get_clk_from_child + devm_gpiochip_add_data_with_key + devm_gpiod_get + devm_gpiod_get_array + devm_gpiod_get_index + devm_gpiod_get_optional + devm_gpiod_put_array + devm_gpio_free + devm_gpio_request + devm_gpio_request_one + devm_hwrng_register + devm_hwspin_lock_register + devm_i2c_new_dummy_device + devm_iio_channel_get + devm_iio_device_alloc __devm_iio_device_register + devm_input_allocate_device + devm_ioremap + devm_ioremap_resource + devm_ioremap_wc + devm_iounmap __devm_irq_alloc_descs + devm_kasprintf + devm_kfree + devm_kmalloc + devm_kmemdup + devm_kstrdup + devm_kstrdup_const + devm_kvasprintf + devm_led_classdev_register_ext + devm_mbox_controller_register + devm_memremap + devm_mfd_add_devices + devm_nvmem_cell_get + devm_nvmem_device_get + devm_nvmem_register + devm_of_clk_add_hw_provider + devm_of_icc_get + devm_of_iomap __devm_of_phy_provider_register + devm_of_platform_populate + devm_of_pwm_get + devm_pci_alloc_host_bridge + devm_phy_create + devm_phy_get + devm_phy_put + devm_pinctrl_get + devm_pinctrl_put + devm_pinctrl_register + devm_pinctrl_register_and_init + devm_platform_get_and_ioremap_resource + devm_platform_ioremap_resource + devm_platform_ioremap_resource_byname + devm_power_supply_register + devm_pwm_put + devm_regmap_add_irq_chip + devm_regmap_del_irq_chip + devm_regmap_field_alloc __devm_regmap_init __devm_regmap_init_i2c __devm_regmap_init_mmio_clk __devm_regmap_init_spi + devm_regulator_bulk_get + devm_regulator_get + devm_regulator_get_exclusive + devm_regulator_get_optional + devm_regulator_put + devm_regulator_register + devm_regulator_register_notifier __devm_release_region + devm_request_any_context_irq __devm_request_region + devm_request_threaded_irq + devm_reset_control_array_get __devm_reset_control_get + devm_reset_controller_register + devm_rtc_allocate_device + devm_rtc_device_register + devm_snd_dmaengine_pcm_register + devm_snd_soc_register_card + devm_snd_soc_register_component __devm_spi_alloc_controller + devm_spi_register_controller + devm_thermal_of_cooling_device_register + devm_thermal_zone_of_sensor_register + devm_thermal_zone_of_sensor_unregister + devm_usb_get_phy + devm_usb_get_phy_by_node + devm_usb_get_phy_by_phandle + devm_watchdog_register_device + _dev_notice + dev_open + dev_pm_clear_wake_irq + dev_pm_domain_attach + dev_pm_domain_attach_by_name + dev_pm_domain_detach + dev_pm_genpd_add_notifier + dev_pm_genpd_remove_notifier + dev_pm_genpd_set_next_wakeup + dev_pm_genpd_set_performance_state + dev_pm_opp_add + dev_pm_opp_adjust_voltage + dev_pm_opp_disable + dev_pm_opp_enable + dev_pm_opp_find_freq_ceil + dev_pm_opp_find_freq_ceil_by_volt + dev_pm_opp_find_freq_exact + dev_pm_opp_find_freq_floor + dev_pm_opp_free_cpufreq_table + dev_pm_opp_get_freq + dev_pm_opp_get_level + dev_pm_opp_get_max_transition_latency + dev_pm_opp_get_opp_count + dev_pm_opp_get_opp_table + dev_pm_opp_get_sharing_cpus + dev_pm_opp_get_suspend_opp_freq + dev_pm_opp_get_voltage + dev_pm_opp_init_cpufreq_table + dev_pm_opp_of_add_table + dev_pm_opp_of_cpumask_add_table + dev_pm_opp_of_cpumask_remove_table + dev_pm_opp_of_find_icc_paths + dev_pm_opp_of_get_sharing_cpus + dev_pm_opp_of_register_em + dev_pm_opp_of_remove_table + dev_pm_opp_put + dev_pm_opp_put_clkname + dev_pm_opp_put_opp_table + dev_pm_opp_put_regulators + dev_pm_opp_register_notifier + dev_pm_opp_remove_all_dynamic + dev_pm_opp_set_bw + dev_pm_opp_set_clkname + dev_pm_opp_set_rate + dev_pm_opp_set_regulators + dev_pm_opp_set_sharing_cpus + dev_pm_opp_set_supported_hw + dev_pm_opp_unregister_notifier + dev_pm_qos_add_notifier + dev_pm_qos_add_request + dev_pm_qos_expose_latency_tolerance + dev_pm_qos_hide_latency_tolerance + dev_pm_qos_read_value + dev_pm_qos_remove_notifier + dev_pm_qos_remove_request + dev_pm_qos_update_request + dev_pm_qos_update_user_latency_tolerance + dev_pm_set_dedicated_wake_irq + dev_printk + dev_printk_emit + dev_queue_xmit + devres_add + devres_alloc_node + devres_free + devres_release + dev_set_mtu + dev_set_name + dev_uc_sync_multiple + dev_uc_unsync + _dev_warn + disable_irq + disable_irq_nosync + disable_percpu_irq + disk_end_io_acct + disk_start_io_acct + divider_get_val + divider_recalc_rate + divider_ro_round_rate_parent + divider_round_rate_parent + dma_alloc_attrs + dma_async_device_register + dma_async_device_unregister + dma_async_tx_descriptor_init + dma_buf_attach + dma_buf_begin_cpu_access + dma_buf_begin_cpu_access_partial + dma_buf_detach + dma_buf_dynamic_attach + dma_buf_end_cpu_access + dma_buf_end_cpu_access_partial + dma_buf_export + dma_buf_fd + dma_buf_get + dma_buf_get_flags + dma_buf_map_attachment + dma_buf_mmap + dma_buf_move_notify + dmabuf_page_pool_alloc + dmabuf_page_pool_create + dmabuf_page_pool_destroy + dmabuf_page_pool_free + dma_buf_pin + dma_buf_put + dma_buf_unmap_attachment + dma_buf_unpin + dma_buf_vmap + dma_buf_vunmap + dma_contiguous_default_area + dmaengine_unmap_put + dma_fence_add_callback + dma_fence_array_create + dma_fence_array_ops + dma_fence_context_alloc + dma_fence_default_wait + dma_fence_enable_sw_signaling + dma_fence_free + dma_fence_get_status + dma_fence_get_stub + dma_fence_init + dma_fence_match_context + dma_fence_release + dma_fence_remove_callback + dma_fence_signal + dma_fence_signal_locked + dma_fence_wait_any_timeout + dma_fence_wait_timeout + dma_free_attrs + dma_get_merge_boundary + dma_get_required_mask + dma_get_sgtable_attrs + dma_get_slave_caps + dma_get_slave_channel + dma_heap_add + dma_heap_buffer_alloc + dma_heap_buffer_free + dma_heap_find + dma_heap_get_dev + dma_heap_get_drvdata + dma_heap_get_name + dma_heap_put + d_make_root + dmam_alloc_attrs + dma_map_page_attrs + dma_map_resource + dma_map_sg_attrs + dma_max_mapping_size + dmam_free_coherent + dma_mmap_attrs + dmam_pool_create + dma_pool_alloc + dma_pool_create + dma_pool_destroy + dma_pool_free + dma_release_channel + dma_request_chan __dma_request_channel + dma_resv_add_excl_fence + dma_resv_add_shared_fence + dma_resv_fini + dma_resv_get_fences_rcu + dma_resv_init + dma_resv_reserve_shared + dma_resv_test_signaled_rcu + dma_resv_wait_timeout_rcu + dma_set_coherent_mask + dma_set_mask + dma_sync_sg_for_cpu + dma_sync_sg_for_device + dma_sync_single_for_cpu + dma_sync_single_for_device + dma_unmap_page_attrs + dma_unmap_resource + dma_unmap_sg_attrs + do_exit __do_once_done __do_once_start + do_SAK + do_trace_rcu_torture_read + do_wait_intr + do_wait_intr_irq + down + downgrade_write + down_interruptible + down_read + down_read_killable + down_read_trylock + down_timeout + down_trylock + down_write + d_path + dput + drain_workqueue + driver_attach + driver_create_file + driver_find_device + driver_register + driver_remove_file + driver_unregister + drm_add_edid_modes + drm_add_modes_noedid + drm_atomic_add_affected_connectors + drm_atomic_add_affected_planes + drm_atomic_commit + drm_atomic_get_connector_state + drm_atomic_get_crtc_state + drm_atomic_get_new_connector_for_encoder + drm_atomic_get_plane_state + drm_atomic_get_private_obj_state + drm_atomic_helper_bridge_destroy_state + drm_atomic_helper_bridge_duplicate_state + drm_atomic_helper_bridge_reset + drm_atomic_helper_check + drm_atomic_helper_check_modeset + drm_atomic_helper_check_planes + drm_atomic_helper_check_plane_state + drm_atomic_helper_cleanup_planes + drm_atomic_helper_commit + drm_atomic_helper_commit_cleanup_done + drm_atomic_helper_commit_duplicated_state + drm_atomic_helper_commit_hw_done + drm_atomic_helper_commit_modeset_disables + drm_atomic_helper_commit_modeset_enables + drm_atomic_helper_commit_planes + drm_atomic_helper_commit_tail __drm_atomic_helper_connector_destroy_state + drm_atomic_helper_connector_destroy_state __drm_atomic_helper_connector_duplicate_state + drm_atomic_helper_connector_duplicate_state __drm_atomic_helper_connector_reset + drm_atomic_helper_connector_reset __drm_atomic_helper_crtc_destroy_state + drm_atomic_helper_crtc_destroy_state __drm_atomic_helper_crtc_duplicate_state + drm_atomic_helper_crtc_duplicate_state __drm_atomic_helper_crtc_reset + drm_atomic_helper_crtc_reset + drm_atomic_helper_damage_merged + drm_atomic_helper_dirtyfb + drm_atomic_helper_disable_plane + drm_atomic_helper_disable_planes_on_crtc + drm_atomic_helper_duplicate_state + drm_atomic_helper_fake_vblank + drm_atomic_helper_page_flip __drm_atomic_helper_plane_destroy_state + drm_atomic_helper_plane_destroy_state __drm_atomic_helper_plane_duplicate_state + drm_atomic_helper_plane_duplicate_state + drm_atomic_helper_plane_reset + drm_atomic_helper_prepare_planes __drm_atomic_helper_private_obj_duplicate_state + drm_atomic_helper_set_config + drm_atomic_helper_setup_commit + drm_atomic_helper_shutdown + drm_atomic_helper_swap_state + drm_atomic_helper_update_legacy_modeset_state + drm_atomic_helper_update_plane + drm_atomic_helper_wait_for_dependencies + drm_atomic_helper_wait_for_fences + drm_atomic_helper_wait_for_flip_done + drm_atomic_helper_wait_for_vblanks + drm_atomic_normalize_zpos + drm_atomic_private_obj_fini + drm_atomic_private_obj_init + drm_atomic_set_crtc_for_connector + drm_atomic_set_crtc_for_plane + drm_atomic_set_fb_for_plane + drm_atomic_set_fence_for_plane + drm_atomic_set_mode_for_crtc + drm_atomic_state_alloc + drm_atomic_state_clear + drm_atomic_state_default_clear + drm_atomic_state_default_release __drm_atomic_state_free + drm_atomic_state_init + drm_bridge_add + drm_bridge_attach + drm_bridge_chain_disable + drm_bridge_chain_enable + drm_bridge_chain_mode_set + drm_bridge_chain_post_disable + drm_bridge_chain_pre_enable + drm_bridge_hpd_notify + drm_bridge_remove + drm_client_init + drm_client_modeset_commit_locked + drm_client_register + drm_compat_ioctl + drm_connector_attach_dp_subconnector_property + drm_connector_attach_edid_property + drm_connector_attach_encoder + drm_connector_cleanup + drm_connector_has_possible_encoder + drm_connector_init + drm_connector_init_with_ddc + drm_connector_list_iter_begin + drm_connector_list_iter_end + drm_connector_list_iter_next + drm_connector_register + drm_connector_set_tile_property + drm_connector_unregister + drm_connector_update_edid_property + drm_crtc_arm_vblank_event + drm_crtc_cleanup + drm_crtc_enable_color_mgmt + drm_crtc_from_index + drm_crtc_handle_vblank + drm_crtc_helper_set_config + drm_crtc_helper_set_mode + drm_crtc_init + drm_crtc_init_with_planes + drm_crtc_send_vblank_event + drm_crtc_set_max_vblank_count + drm_crtc_vblank_count + drm_crtc_vblank_count_and_time + drm_crtc_vblank_get + drm_crtc_vblank_helper_get_vblank_timestamp + drm_crtc_vblank_off + drm_crtc_vblank_on + drm_crtc_vblank_put + drm_crtc_vblank_reset + drm_crtc_wait_one_vblank + drm_cvt_mode __drm_dbg __drm_debug + drm_debugfs_create_files + drm_detect_hdmi_monitor + drm_detect_monitor_audio + drm_dev_alloc + drm_dev_dbg + drm_dev_enter + drm_dev_exit + drm_dev_get + drm_dev_printk + drm_dev_put + drm_dev_register + drm_dev_set_unique + drm_dev_unplug + drm_dev_unregister + drm_display_mode_to_videomode + drm_do_get_edid + drm_dp_atomic_find_vcpi_slots + drm_dp_atomic_release_vcpi_slots + drm_dp_aux_init + drm_dp_aux_register + drm_dp_aux_unregister + drm_dp_bw_code_to_link_rate + drm_dp_calc_pbn_mode + drm_dp_channel_eq_ok + drm_dp_check_act_status + drm_dp_clock_recovery_ok + drm_dp_dpcd_read + drm_dp_dpcd_read_link_status + drm_dp_dpcd_write + drm_dp_find_vcpi_slots + drm_dp_get_adjust_request_pre_emphasis + drm_dp_get_adjust_request_voltage + drm_dp_get_edid_quirks + drm_dp_link_rate_to_bw_code + drm_dp_link_train_channel_eq_delay + drm_dp_link_train_clock_recovery_delay + drm_dp_mst_allocate_vcpi + drm_dp_mst_deallocate_vcpi + drm_dp_mst_detect_port + drm_dp_mst_get_edid + drm_dp_mst_get_port_malloc + drm_dp_mst_hpd_irq + drm_dp_mst_put_port_malloc + drm_dp_mst_reset_vcpi_slots + drm_dp_mst_topology_mgr_destroy + drm_dp_mst_topology_mgr_init + drm_dp_mst_topology_mgr_set_mst + drm_dp_send_power_updown_phy + drm_dp_set_subconnector_property + drm_dp_update_payload_part1 + drm_dp_update_payload_part2 + drm_edid_block_valid + drm_edid_duplicate + drm_edid_get_monitor_name + drm_edid_header_is_valid + drm_edid_is_valid + drm_edid_to_sad + drm_edid_to_speaker_allocation + drm_encoder_cleanup + drm_encoder_init __drm_err + drm_event_cancel_free + drm_event_reserve_init + drm_event_reserve_init_locked + drm_fb_cma_get_gem_obj + drm_flip_work_cleanup + drm_flip_work_commit + drm_flip_work_init + drm_flip_work_queue + drm_format_info + drm_framebuffer_cleanup + drm_framebuffer_init + drm_framebuffer_lookup + drm_framebuffer_remove + drm_framebuffer_unregister_private + drm_gem_cma_dumb_create_internal + drm_gem_cma_free_object + drm_gem_cma_mmap + drm_gem_cma_prime_get_sg_table + drm_gem_cma_prime_import_sg_table + drm_gem_cma_prime_mmap + drm_gem_cma_prime_vmap + drm_gem_cma_prime_vunmap + drm_gem_cma_vm_ops + drm_gem_create_mmap_offset + drm_gem_dmabuf_mmap + drm_gem_dmabuf_release + drm_gem_dmabuf_vmap + drm_gem_dmabuf_vunmap + drm_gem_fb_create + drm_gem_fb_create_handle + drm_gem_fb_destroy + drm_gem_fb_get_obj + drm_gem_fb_prepare_fb + drm_gem_free_mmap_offset + drm_gem_get_pages + drm_gem_handle_create + drm_gem_lock_reservations + drm_gem_map_attach + drm_gem_map_detach + drm_gem_map_dma_buf + drm_gem_mmap + drm_gem_mmap_obj + drm_gem_object_free + drm_gem_object_init + drm_gem_object_lookup + drm_gem_object_put_locked + drm_gem_object_release + drm_gem_prime_export + drm_gem_prime_fd_to_handle + drm_gem_prime_handle_to_fd + drm_gem_prime_import + drm_gem_prime_import_dev + drm_gem_prime_mmap + drm_gem_private_object_init + drm_gem_put_pages + drm_gem_shmem_create + drm_gem_shmem_free_object + drm_gem_shmem_get_sg_table + drm_gem_shmem_mmap + drm_gem_shmem_pin + drm_gem_shmem_print_info + drm_gem_shmem_unpin + drm_gem_shmem_vmap + drm_gem_shmem_vunmap + drm_gem_unlock_reservations + drm_gem_unmap_dma_buf + drm_gem_vm_close + drm_gem_vm_open + drm_get_connector_status_name + drm_get_edid + drm_get_format_info + drm_get_format_name + drm_handle_vblank + drm_hdmi_avi_infoframe_from_display_mode + drm_helper_connector_dpms + drm_helper_disable_unused_functions + drm_helper_force_disable_all + drm_helper_hpd_irq_event + drm_helper_mode_fill_fb_struct + drm_helper_probe_single_connector_modes + drm_helper_resume_force_mode + drm_ioctl + drm_irq_install + drm_irq_uninstall + drm_is_current_master + drm_kms_helper_hotplug_event + drm_kms_helper_is_poll_worker + drm_kms_helper_poll_disable + drm_kms_helper_poll_enable + drm_kms_helper_poll_fini + drm_kms_helper_poll_init + drm_match_cea_mode + drmm_kmalloc + drm_mm_init + drm_mm_insert_node_in_range + drmm_mode_config_init + drm_mm_print + drm_mm_remove_node + drm_mm_takedown + drm_mode_config_cleanup + drm_mode_config_helper_resume + drm_mode_config_helper_suspend + drm_mode_config_reset + drm_mode_convert_to_umode + drm_mode_convert_umode + drm_mode_copy + drm_mode_create + drm_mode_create_dp_colorspace_property + drm_mode_create_scaling_mode_property + drm_mode_create_tile_group + drm_mode_crtc_set_gamma_size + drm_mode_debug_printmodeline + drm_mode_destroy + drm_mode_duplicate + drm_mode_equal + drm_mode_equal_no_clocks + drm_mode_get_tile_group + drm_mode_is_420_only + drm_mode_match + drm_mode_object_find + drm_mode_object_get + drm_mode_object_put + drm_mode_probed_add + drm_modeset_acquire_fini + drm_modeset_acquire_init + drm_modeset_backoff + drm_mode_set_crtcinfo + drm_modeset_drop_locks + drm_modeset_lock + drm_modeset_lock_all + drm_modeset_lock_all_ctx + drm_modeset_lock_init + drm_mode_set_name + drm_modeset_unlock + drm_modeset_unlock_all + drm_mode_sort + drm_mode_vrefresh + drm_need_swiotlb + drm_object_attach_property + drm_object_property_set_value + drm_of_component_match_add + drm_of_find_possible_crtcs + drm_open + drm_panel_add + drm_panel_disable + drm_panel_enable + drm_panel_get_modes + drm_panel_init + drm_panel_prepare + drm_panel_remove + drm_panel_unprepare + drm_plane_cleanup + drm_plane_create_alpha_property + drm_plane_create_blend_mode_property + drm_plane_create_rotation_property + drm_plane_create_zpos_property + drm_plane_enable_fb_damage_clips + drm_poll + drm_prime_gem_destroy + drm_prime_pages_to_sg + drm_prime_sg_to_page_addr_arrays + drm_printf __drm_printfn_coredump __drm_printfn_info __drm_printfn_seq_file + drm_property_blob_get + drm_property_blob_put + drm_property_create + drm_property_create_bitmask + drm_property_create_blob + drm_property_create_bool + drm_property_create_enum + drm_property_create_range + drm_property_create_signed_range + drm_property_lookup_blob + drm_property_replace_blob + drm_puts __drm_puts_coredump __drm_puts_seq_file + drm_read + drm_rect_calc_hscale + drm_rect_calc_vscale + drm_rect_clip_scaled + drm_rect_intersect + drm_release + drm_rotation_simplify + drm_send_event + drm_send_event_locked + drm_set_preferred_mode + drm_simple_encoder_init + drm_state_dump + drm_syncobj_add_point + drm_syncobj_create + drm_syncobj_find + drm_syncobj_find_fence + drm_syncobj_free + drm_syncobj_get_fd + drm_syncobj_get_handle + drm_syncobj_replace_fence + drm_sysfs_hotplug_event + drm_universal_plane_init + drm_vblank_init + drm_vma_node_allow + drm_vma_node_is_allowed + drm_vma_node_revoke + drm_wait_one_vblank + drm_writeback_connector_init + drm_writeback_queue_job + drm_writeback_signal_completion + dst_release + dump_align + dump_backtrace + dump_emit + dump_stack + dup_iter + dwc3_send_gadget_ep_cmd + dwc3_stop_active_transfer + dw_handle_msi_irq + dw_pcie_host_init + dw_pcie_msi_init + dw_pcie_own_conf_map_bus + dw_pcie_read + dw_pcie_setup_rc + dw_pcie_write __dynamic_dev_dbg __dynamic_pr_debug + edac_device_add_device + edac_device_alloc_ctl_info + edac_device_alloc_index + edac_device_del_device + edac_device_free_ctl_info + edac_device_handle_ce_count + edac_device_handle_ue_count + efi + efi_tpm_final_log_size + elevator_alloc + elv_bio_merge_ok + elv_rb_add + elv_rb_del + elv_rb_find + elv_rb_former_request + elv_rb_latter_request + elv_register + elv_rqhash_add + elv_rqhash_del + elv_unregister + emergency_restart + enable_irq + enable_percpu_irq + eth_commit_mac_addr_change + ether_setup + eth_mac_addr + eth_platform_get_mac_address + eth_prepare_mac_addr_change __ethtool_get_link_ksettings + ethtool_op_get_link + ethtool_op_get_ts_info + ethtool_virtdev_set_link_ksettings + eth_type_trans + eth_validate_addr + eventfd_ctx_fdget + eventfd_ctx_fileget + eventfd_ctx_put + eventfd_ctx_remove_wait_queue + eventfd_signal + event_triggers_call + extcon_find_edev_by_node + extcon_get_edev_by_phandle + extcon_get_edev_name + extcon_get_extcon_dev + extcon_get_property + extcon_get_state + extcon_register_notifier + extcon_set_property + extcon_set_property_capability + extcon_set_state_sync + extcon_unregister_notifier + fasync_helper __fdget + fd_install + fget + file_path + file_ra_state_init + filp_close + filp_open_block + find_get_pid + find_last_bit + find_next_bit + find_next_zero_bit + find_snd_usb_substream + find_task_by_vpid + find_vma + find_vpid + finish_wait + firmware_request_nowarn + fixed_phy_register + fixed_phy_unregister + fixed_size_llseek + flow_keys_basic_dissector + flush_dcache_page + flush_delayed_work __flush_icache_range + flush_signals + flush_work + flush_workqueue + fput + frame_vector_create + frame_vector_destroy + frame_vector_to_pages + free_buffer_head + free_io_pgtable_ops + free_irq + free_netdev __free_pages + free_pages + free_pages_exact + free_percpu + free_percpu_irq + freezing_slow_path + freq_qos_add_request + freq_qos_remove_request + freq_qos_update_request + freq_scale + fs_bio_set + fsync_bdev + ftrace_dump + full_name_hash + fwnode_find_reference + fwnode_get_name + fwnode_get_named_child_node + fwnode_get_next_child_node + fwnode_gpiod_get_index + fwnode_handle_get + fwnode_handle_put + fwnode_property_present + fwnode_property_read_string + fwnode_property_read_u32_array + fwnode_usb_role_switch_get + gcd + generic_delete_inode + generic_device_group + generic_file_llseek + generic_file_read_iter + generic_handle_irq + generic_iommu_put_resv_regions + generic_mii_ioctl + generic_perform_write + generic_write_checks + genlmsg_put + genl_notify + genl_register_family + genl_unregister_family __genphy_config_aneg + genphy_read_status + genphy_resume + genphy_soft_reset + genphy_suspend + gen_pool_add_owner + gen_pool_alloc_algo_owner + gen_pool_avail + gen_pool_best_fit + gen_pool_create + gen_pool_destroy + gen_pool_dma_alloc_align + gen_pool_dma_zalloc_align + gen_pool_first_fit_align + gen_pool_first_fit_order_align + gen_pool_free_owner + gen_pool_has_addr + gen_pool_set_algo + gen_pool_size + gen_pool_virt_to_phys + getboottime64 + get_cpu_device + get_cpu_idle_time + get_cpu_idle_time_us + get_cpu_iowait_time_us + get_device + get_device_system_crosststamp __get_free_pages + get_governor_parent_kobj + get_next_ino + get_option + get_options + get_pid_task + get_random_bytes + get_random_bytes_arch + get_random_u32 + get_random_u64 + get_sg_io_hdr + get_state_synchronize_rcu __get_task_comm + get_task_exe_file + get_task_mm + get_task_pid + get_thermal_instance + get_tree_single + get_unmapped_area + get_unused_fd_flags + get_user_pages + get_user_pages_fast + get_user_pages_remote + get_vaddr_frames + get_zeroed_page + gfp_zone + gic_nonsecure_priorities + glob_match + gnss_allocate_device + gnss_deregister_device + gnss_insert_raw + gnss_put_device + gnss_register_device + gov_attr_set_get + gov_attr_set_init + gov_attr_set_put + governor_sysfs_ops + gpiochip_add_data_with_key + gpiochip_add_pin_range + gpiochip_find + gpiochip_generic_config + gpiochip_generic_free + gpiochip_generic_request + gpiochip_get_data + gpiochip_irqchip_add_key + gpiochip_line_is_valid + gpiochip_lock_as_irq + gpiochip_populate_parent_fwspec_fourcell + gpiochip_remove + gpiochip_set_nested_irqchip + gpiochip_unlock_as_irq + gpiod_cansleep + gpiod_count + gpiod_direction_input + gpiod_direction_output + gpiod_direction_output_raw + gpiod_get_optional + gpiod_get_raw_value + gpiod_get_raw_value_cansleep + gpiod_get_value + gpiod_get_value_cansleep + gpiod_set_consumer_name + gpiod_set_debounce + gpiod_set_raw_value + gpiod_set_raw_value_cansleep + gpiod_set_value + gpiod_set_value_cansleep + gpiod_to_chip + gpiod_to_irq + gpio_free + gpio_free_array + gpio_request + gpio_request_one + gpio_to_desc + gro_cells_destroy + gro_cells_init + gro_cells_receive + gs_alloc_req + gserial_alloc_line + gserial_connect + gserial_disconnect + gserial_free_line + gserial_resume + gserial_suspend + gs_free_req + guid_gen + handle_bad_irq + handle_edge_irq + handle_fasteoi_ack_irq + handle_fasteoi_irq + handle_level_irq + handle_nested_irq + handle_simple_irq + handle_sysrq + hash_digest_size + hashlen_string + have_governor_per_policy + hci_alloc_dev + hci_free_dev + hci_recv_frame + hci_register_dev + hci_unregister_dev + hdmi_audio_infoframe_init + hdmi_audio_infoframe_pack + hdmi_avi_infoframe_init + hdmi_avi_infoframe_pack + hdmi_infoframe_pack + hex2bin + hex_dump_to_buffer + hex_to_bin + hid_hw_close + hid_hw_open + hid_hw_start + hid_hw_stop + hid_open_report __hid_register_driver + hid_report_raw_event __hid_request + hid_unregister_driver + hmm_range_fault + hrtimer_active + hrtimer_cancel + hrtimer_forward __hrtimer_get_remaining + hrtimer_init + hrtimer_init_sleeper + hrtimer_sleeper_start_expires + hrtimer_start_range_ns + hrtimer_try_to_cancel + hvc_alloc + hvc_instantiate + hvc_kick + hvc_poll + hvc_remove __hvc_resize + hwrng_register + hwrng_unregister + hwspin_lock_free + hwspin_lock_request_specific __hwspin_lock_timeout __hwspin_unlock + hypervisor_kobj + i2c_adapter_type + i2c_add_adapter + i2c_add_numbered_adapter + i2c_bit_add_bus + i2c_bit_add_numbered_bus + i2c_bus_type + i2c_client_type + i2c_del_adapter + i2c_del_driver + i2c_for_each_dev + i2c_generic_scl_recovery + i2c_get_adapter + i2c_get_device_id + i2c_get_dma_safe_msg_buf + i2c_match_id + i2c_new_ancillary_device + i2c_new_client_device + i2c_new_dummy_device + i2c_new_scanned_device + i2c_parse_fw_timings + i2c_put_adapter + i2c_put_dma_safe_msg_buf + i2c_recover_bus + i2c_register_driver + i2c_smbus_read_byte + i2c_smbus_read_byte_data + i2c_smbus_read_i2c_block_data + i2c_smbus_read_word_data + i2c_smbus_write_byte + i2c_smbus_write_byte_data + i2c_smbus_write_i2c_block_data + i2c_smbus_write_word_data __i2c_smbus_xfer + i2c_smbus_xfer __i2c_transfer + i2c_transfer + i2c_transfer_buffer_flags + i2c_unregister_device + i2c_verify_adapter + i2c_verify_client + icc_disable + icc_enable + icc_get + icc_link_create + icc_node_add + icc_node_create + icc_node_del + icc_node_destroy + icc_nodes_remove + icc_provider_add + icc_provider_del + icc_put + icc_set_bw + icc_set_tag + icc_std_aggregate + icc_sync_state + ida_alloc_range + ida_destroy + ida_free + idr_alloc + idr_alloc_cyclic + idr_alloc_u32 + idr_destroy + idr_find + idr_for_each + idr_get_next + idr_preload + idr_remove + idr_replace + ieee802154_alloc_hw + ieee802154_free_hw + ieee802154_register_hw + ieee802154_rx_irqsafe + ieee802154_unregister_hw + ieee802154_wake_queue + ieee802154_xmit_complete + iio_buffer_init + iio_buffer_put + iio_channel_get + iio_channel_get_all + iio_channel_release + iio_device_alloc + iio_device_attach_buffer + iio_device_free __iio_device_register + iio_device_unregister + iio_push_to_buffers + iio_read_channel_processed + iio_read_channel_raw + import_iovec + in4_pton + in6_dev_finish_destroy + in6_pton + in_aton + inc_zone_page_state + in_egroup_p + inet_proto_csum_replace4 + init_dummy_netdev + init_iova_domain + init_net + init_on_free + init_pid_ns + init_pseudo __init_rwsem + init_srcu_struct __init_swait_queue_head + init_task + init_timer_key + init_uts_ns + init_wait_entry __init_waitqueue_head + input_alloc_absinfo + input_allocate_device + input_close_device + input_event + input_ff_create + input_ff_create_memless + input_ff_destroy + input_free_device + input_mt_assign_slots + input_mt_destroy_slots + input_mt_drop_unused + input_mt_init_slots + input_mt_report_finger_count + input_mt_report_pointer_emulation + input_mt_report_slot_state + input_mt_sync_frame + input_open_device + input_register_device + input_register_handle + input_register_handler + input_set_abs_params + input_set_capability + input_set_timestamp + input_unregister_device + input_unregister_handle + input_unregister_handler + interval_tree_insert + interval_tree_iter_first + interval_tree_iter_next + interval_tree_remove + int_pow + int_sqrt + invalidate_bdev + invalidate_mapping_pages + iomem_resource + iommu_alloc_resv_region + iommu_attach_device + iommu_attach_group + iommu_aux_attach_device + iommu_aux_detach_device + iommu_aux_get_pasid + iommu_detach_device + iommu_detach_group + iommu_dev_enable_feature + iommu_dev_feature_enabled + iommu_device_register + iommu_device_sysfs_add + iommu_device_sysfs_remove + iommu_device_unlink + iommu_device_unregister + iommu_dma_enable_best_fit_algo + iommu_dma_get_resv_regions + iommu_dma_reserve_iova + iommu_domain_alloc + iommu_domain_free + iommu_domain_get_attr + iommu_domain_set_attr + iommu_fwspec_add_ids + iommu_fwspec_free + iommu_get_dma_cookie + iommu_get_domain_for_dev + iommu_get_msi_cookie + iommu_group_alloc + iommu_group_for_each_dev + iommu_group_get + iommu_group_get_iommudata + iommu_group_put + iommu_group_ref_get + iommu_group_set_iommudata + iommu_group_set_name + iommu_iova_to_phys + iommu_map + iommu_map_sg + iommu_present + iommu_put_dma_cookie + iommu_register_device_fault_handler + iommu_report_device_fault + iommu_set_fault_handler + iommu_unmap + iommu_unregister_device_fault_handler __ioread32_copy __ioremap + io_schedule_timeout + iounmap + iov_iter_bvec + iov_iter_kvec __iowrite32_copy + ip_compute_csum + ipi_desc_get + ip_send_check + iput __ipv6_addr_type + ipv6_ext_hdr + ipv6_find_hdr + ipv6_skip_exthdr __irq_alloc_descs + irq_chip_ack_parent + irq_chip_disable_parent + irq_chip_enable_parent + irq_chip_eoi_parent + irq_chip_get_parent_state + irq_chip_mask_parent + irq_chip_retrigger_hierarchy + irq_chip_set_affinity_parent + irq_chip_set_parent_state + irq_chip_set_type_parent + irq_chip_set_vcpu_affinity_parent + irq_chip_set_wake_parent + irq_chip_unmask_parent + irq_create_fwspec_mapping + irq_create_mapping_affinity + irq_create_of_mapping + irq_dispose_mapping __irq_domain_add + irq_domain_add_simple + irq_domain_alloc_irqs_parent + irq_domain_create_hierarchy + irq_domain_free_irqs_common + irq_domain_free_irqs_parent + irq_domain_get_irq_data + irq_domain_remove + irq_domain_set_hwirq_and_chip + irq_domain_set_info + irq_domain_simple_ops + irq_domain_update_bus_token + irq_domain_xlate_onecell + irq_domain_xlate_onetwocell + irq_domain_xlate_twocell + irq_find_mapping + irq_find_matching_fwspec + irq_get_irqchip_state + irq_get_irq_data + irq_modify_status + irq_of_parse_and_map + irq_set_affinity_hint + irq_set_affinity_notifier + irq_set_chained_handler_and_data + irq_set_chip + irq_set_chip_and_handler_name + irq_set_chip_data __irq_set_handler + irq_set_handler_data + irq_set_irqchip_state + irq_set_irq_type + irq_set_irq_wake + irq_set_parent + irq_to_desc + irq_work_queue + irq_work_queue_on + irq_work_sync + is_dma_buf_file + is_vmalloc_addr + iwe_stream_add_event + iwe_stream_add_point + iwe_stream_add_value + jiffies_64_to_clock_t + jiffies64_to_msecs + jiffies + jiffies_to_msecs + jiffies_to_usecs + kasan_flag_enabled + kasprintf + kernel_bind + kernel_connect + kernel_cpustat + kernel_getsockname + kernel_kobj + kernel_power_off + kernel_recvmsg + kernel_restart + kernel_sendmsg + kernel_sigaction + kernfs_find_and_get_ns + kernfs_notify + kernfs_path_from_node + kernfs_put + kern_mount + kern_path + kern_unmount __kfifo_alloc __kfifo_free __kfifo_in @@ -123,109 +1950,1767 @@ __kfifo_out __kfifo_out_peek __kfifo_to_user + kfree + kfree_const + kfree_sensitive __kfree_skb + kfree_skb + kick_all_cpus_sync + kill_anon_super + kill_fasync + kill_litter_super + kimage_vaddr + kimage_voffset + kiocb_set_cancel_fn __kmalloc + kmalloc_caches + kmalloc_order + kmalloc_order_trace + kmem_cache_alloc + kmem_cache_alloc_trace + kmem_cache_create + kmem_cache_create_usercopy + kmem_cache_destroy + kmem_cache_free + kmemdup + kmemdup_nul + kmsg_dump_get_line + kmsg_dump_rewind + kobject_add + kobject_create_and_add + kobject_del + kobject_get + kobject_init + kobject_init_and_add + kobject_put + kobject_set_name + kobject_uevent + kobject_uevent_env + kobj_sysfs_ops + krealloc + kset_create_and_add + kset_unregister + ksize + ksoftirqd + kstat + kstat_irqs_cpu + kstat_irqs_usr + kstrdup + kstrdup_const + kstrdup_quotable_cmdline + kstrndup + kstrtobool + kstrtobool_from_user + kstrtoint + kstrtoint_from_user + kstrtol_from_user + kstrtoll + kstrtos16 + kstrtos8 + kstrtos8_from_user + kstrtou16 + kstrtou16_from_user + kstrtou8 + kstrtou8_from_user + kstrtouint + kstrtouint_from_user + kstrtoul_from_user + kstrtoull + kstrtoull_from_user + ksys_sync_helper + kthread_bind + kthread_bind_mask + kthread_blkcg + kthread_cancel_delayed_work_sync + kthread_cancel_work_sync + kthread_create_on_node + kthread_create_worker + kthread_delayed_work_timer_fn + kthread_destroy_worker + kthread_flush_work + kthread_flush_worker __kthread_init_worker + kthread_mod_delayed_work + kthread_park + kthread_parkme + kthread_queue_delayed_work + kthread_queue_work + kthread_should_park + kthread_should_stop + kthread_stop + kthread_unpark + kthread_unuse_mm + kthread_use_mm + kthread_worker_fn + ktime_add_safe + ktime_get + ktime_get_coarse_with_offset + ktime_get_mono_fast_ns + ktime_get_raw + ktime_get_raw_ts64 + ktime_get_real_seconds + ktime_get_real_ts64 + ktime_get_seconds + ktime_get_ts64 + ktime_get_with_offset + kvasprintf + kvfree + kvfree_call_rcu + kvmalloc_node + led_classdev_flash_register_ext + led_classdev_flash_unregister + led_classdev_register_ext + led_classdev_unregister + led_trigger_event + led_trigger_register_simple + led_trigger_unregister_simple __list_add_valid __list_del_entry_valid + list_sort + llist_add_batch + llist_reverse_order __local_bh_enable_ip __lock_page + lock_sock_nested + log_abnormal_wakeup_reason + log_buf_addr_get + log_buf_len_get __log_post_read_mmio __log_read_mmio + log_threaded_irq_wakeup_reason __log_write_mmio + loops_per_jiffy + lzo1x_1_compress + lzo1x_decompress_safe + lzorle1x_1_compress + mac_pton + match_string + mbox_chan_received_data + mbox_chan_txdone + mbox_client_txdone + mbox_controller_register + mbox_controller_unregister + mbox_free_channel + mbox_request_channel + mbox_send_message + mdiobus_alloc_size + mdiobus_free + mdiobus_read __mdiobus_register + mdiobus_unregister + mdiobus_write + media_device_cleanup + media_device_init __media_device_register + media_device_unregister + media_entity_pads_init + memblock_end_of_DRAM + memblock_free __memcat_p + memchr + memchr_inv + memcmp + memcpy __memcpy_fromio __memcpy_toio + memdup_user + memdup_user_nul + memmove + memory_block_size_bytes + memory_read_from_buffer + memparse + mempool_alloc + mempool_alloc_slab + mempool_create + mempool_create_node + mempool_destroy + mempool_exit + mempool_free + mempool_free_slab + mempool_init + mempool_kfree + mempool_kmalloc + memremap + memset64 + memset __memset_io + memstart_addr + memunmap + mfd_add_devices + mfd_remove_devices + migrate_swap + mii_check_media + mii_ethtool_get_link_ksettings + mii_ethtool_gset + mii_ethtool_set_link_ksettings + mii_link_ok + mii_nway_restart + mipi_dsi_attach + mipi_dsi_compression_mode + mipi_dsi_create_packet + mipi_dsi_dcs_read + mipi_dsi_dcs_set_column_address + mipi_dsi_dcs_set_display_brightness + mipi_dsi_dcs_set_page_address + mipi_dsi_dcs_set_tear_off + mipi_dsi_dcs_write_buffer + mipi_dsi_detach + mipi_dsi_device_register_full + mipi_dsi_device_unregister + mipi_dsi_driver_register_full + mipi_dsi_driver_unregister + mipi_dsi_host_register + mipi_dsi_host_unregister + mipi_dsi_packet_format_is_long + mipi_dsi_picture_parameter_set + misc_deregister + misc_register + mktime64 + mmc_add_host + mmc_alloc_host + mmc_app_cmd + mmc_calc_max_discard + mmc_can_erase + mmc_can_gpio_cd + mmc_can_secure_erase_trim + mmc_can_trim __mmc_claim_host + mmc_cmdq_disable + mmc_cmdq_enable + mmc_cqe_post_req + mmc_cqe_recovery + mmc_cqe_request_done + mmc_cqe_start_req + mmc_detect_card_removed + mmc_detect_change + mmc_erase + mmc_erase_group_aligned + mmc_flush_cache + mmc_free_host + mmc_get_card + mmc_get_ext_csd + mmc_gpiod_request_cd + mmc_gpiod_request_cd_irq + mmc_gpiod_request_ro + mmc_gpio_get_cd + mmc_gpio_get_ro + mmc_hw_reset + mmc_of_parse + mmc_of_parse_voltage + mmc_put_card + mmc_register_driver + mmc_regulator_get_supply + mmc_regulator_set_ocr + mmc_regulator_set_vqmmc + mmc_release_host + mmc_remove_host + mmc_request_done + mmc_retune_pause + mmc_retune_release + mmc_retune_unpause + mmc_run_bkops + mmc_sanitize __mmc_send_status + mmc_send_status + mmc_send_tuning + mmc_set_data_timeout + mmc_start_request + mmc_switch + mmc_unregister_driver + mmc_wait_for_cmd + mmc_wait_for_req __mmdrop + mmput + mm_trace_rss_stat + mmu_interval_notifier_insert + mmu_interval_notifier_remove + mmu_interval_read_begin + mmu_notifier_synchronize + mod_delayed_work_on + mod_node_page_state + mod_timer __module_get + module_layout + module_put __msecs_to_jiffies + msleep + msleep_interruptible __mutex_init + mutex_is_locked + mutex_lock + mutex_lock_interruptible + mutex_trylock + mutex_trylock_recursive + mutex_unlock + names_cachep + name_to_dev_t __napi_alloc_skb + napi_complete_done + napi_consume_skb + napi_disable + napi_gro_flush + napi_gro_receive __napi_schedule + napi_schedule_prep __ndelay __netdev_alloc_skb + netdev_change_features + netdev_err + netdev_increment_features + netdev_info + netdev_lower_state_changed + netdev_master_upper_dev_link + netdev_notify_peers + netdev_pick_tx + netdev_rx_handler_register + netdev_rx_handler_unregister + netdev_state_change + netdev_update_features + netdev_upper_dev_link + netdev_upper_dev_unlink + netdev_warn + netif_carrier_off + netif_carrier_on + netif_device_attach + netif_device_detach + netif_napi_add __netif_napi_del + netif_receive_skb + netif_receive_skb_list + netif_rx + netif_rx_ni + netif_schedule_queue + netif_set_real_num_rx_queues + netif_set_real_num_tx_queues __netif_set_xps_queue + netif_stacked_transfer_operstate + netif_tx_stop_all_queues + netif_tx_wake_queue + netlink_ack + netlink_broadcast + netlink_capable + netlink_has_listeners __netlink_kernel_create + netlink_kernel_release + netlink_register_notifier + netlink_unicast + netlink_unregister_notifier + net_namespace_list + net_ratelimit + new_inode __next_zones_zonelist + nf_conntrack_destroy + nla_append + nla_find + nla_memcpy __nla_parse + nla_put_64bit + nla_put + nla_put_nohdr + nla_reserve_64bit + nla_reserve + nla_strlcpy __nla_validate __nlmsg_put + no_llseek + nonseekable_open + noop_llseek + no_seek_end_llseek + nr_cpu_ids + nr_ipi_get + nr_irqs + ns_capable + nsecs_to_jiffies + nsec_to_clock_t + ns_to_timespec64 __num_online_cpus + nvdimm_bus_register + nvdimm_bus_unregister + nvdimm_pmem_region_create + nvmem_cell_get + nvmem_cell_put + nvmem_cell_read + nvmem_cell_read_u32 + nvmem_cell_write + nvmem_device_put + nvmem_device_read + nvmem_device_write + of_address_to_resource + of_alias_get_highest_id + of_alias_get_id + of_clk_add_hw_provider + of_clk_add_provider + of_clk_del_provider + of_clk_get + of_clk_get_by_name + of_clk_get_from_provider + of_clk_get_parent_count + of_clk_get_parent_name + of_clk_hw_onecell_get + of_clk_hw_simple_get + of_clk_set_defaults + of_clk_src_onecell_get + of_clk_src_simple_get + of_count_phandle_with_args + of_cpufreq_cooling_register + of_cpu_node_to_id + of_css + of_devfreq_cooling_register + of_devfreq_cooling_register_power + of_device_get_match_data + of_device_is_available + of_device_is_compatible + of_device_modalias + of_device_request_module + of_device_uevent_modalias + of_dma_configure_id + of_dma_controller_free + of_dma_controller_register + of_dma_is_coherent + of_drm_find_bridge + of_drm_find_panel + of_find_all_nodes + of_find_compatible_node + of_find_device_by_node + of_find_i2c_adapter_by_node + of_find_i2c_device_by_node + of_find_matching_node_and_match + of_find_mipi_dsi_host_by_node + of_find_node_by_name + of_find_node_by_phandle + of_find_node_by_type + of_find_node_opts_by_path + of_find_node_with_property + of_find_property + of_fwnode_ops + of_genpd_add_provider_onecell + of_genpd_add_provider_simple + of_genpd_del_provider + of_get_address + of_get_child_by_name + of_get_compatible_child + of_get_cpu_node + of_get_dma_window + of_get_named_gpio_flags + of_get_next_available_child + of_get_next_child + of_get_next_parent + of_get_parent + of_get_property + of_get_regulator_init_data + of_graph_get_endpoint_by_regs + of_graph_get_next_endpoint + of_graph_get_port_parent + of_graph_get_remote_endpoint + of_graph_get_remote_node + of_graph_get_remote_port + of_graph_get_remote_port_parent + of_graph_is_present + of_graph_parse_endpoint + of_hwspin_lock_get_id + of_i2c_get_board_info + of_icc_get + of_icc_xlate_onecell + of_iomap + of_irq_find_parent + of_irq_get + of_irq_get_byname + of_irq_parse_one + of_machine_is_compatible + of_match_device + of_match_node + of_modalias_node + of_n_addr_cells + of_node_name_eq + of_n_size_cells + of_nvmem_device_get + of_parse_phandle + of_parse_phandle_with_args + of_parse_phandle_with_fixed_args + of_phandle_iterator_init + of_phandle_iterator_next + of_phy_simple_xlate + of_platform_depopulate + of_platform_device_create + of_platform_device_destroy + of_platform_populate + of_property_count_elems_of_size + of_property_match_string + of_property_read_string + of_property_read_string_helper + of_property_read_u32_index + of_property_read_u64 + of_property_read_u64_index + of_property_read_variable_u16_array + of_property_read_variable_u32_array + of_property_read_variable_u64_array + of_property_read_variable_u8_array + of_prop_next_string + of_prop_next_u32 + of_pwm_xlate_with_flags + of_reserved_mem_device_init_by_idx + of_reserved_mem_device_release + of_reserved_mem_lookup + of_reset_control_array_get __of_reset_control_get + of_root + of_thermal_get_ntrips + of_thermal_get_trip_points + of_thermal_is_trip_valid + of_translate_address + of_usb_get_phy_mode + of_usb_host_tpl_support + on_each_cpu + oops_in_progress + orderly_poweroff + overflowuid + page_endio + page_mapping + page_reporting_register + page_reporting_unregister + panic + panic_notifier_list + panic_timeout + param_array_ops + param_get_int + param_get_string + param_get_uint + param_get_ullong + param_ops_bint + param_ops_bool + param_ops_byte + param_ops_charp + param_ops_hexint + param_ops_int + param_ops_long + param_ops_short + param_ops_string + param_ops_uint + param_ops_ullong + param_ops_ulong + param_ops_ushort + param_set_bool + param_set_copystring + param_set_int + param_set_uint + part_end_io_acct + part_start_io_acct + passthru_features_check + path_put + pause_cpus + pci_alloc_irq_vectors_affinity + pci_assign_resource + pci_assign_unassigned_bus_resources + pcibios_resource_to_bus + pci_bus_resource_n + pci_bus_type + pci_clear_master + pci_d3cold_disable + pci_device_group + pci_device_is_present + pci_dev_present + pci_dev_put + pci_disable_device + pci_disable_msi + pcie_aspm_enabled + pcie_bandwidth_available + pcie_capability_read_word + pcie_capability_write_word + pcie_get_mps + pcie_get_speed_cap + pci_enable_atomic_ops_to_root + pci_enable_device + pci_enable_device_mem + pci_enable_msi + pci_enable_wake + pci_find_bus + pci_find_capability + pci_find_ext_capability + pci_find_next_capability + pci_free_irq + pci_free_irq_vectors + pci_generic_config_read + pci_generic_config_write + pci_get_device + pci_get_domain_bus_and_slot + pci_get_slot + pci_host_probe + pci_intx + pci_iomap + pci_iomap_range + pci_ioremap_bar + pci_irq_get_affinity + pci_irq_vector + pci_load_and_free_saved_state + pci_load_saved_state + pci_map_rom + pci_match_id + pcim_enable_device + pci_msi_create_irq_domain + pci_msi_mask_irq + pci_msi_unmask_irq + pci_msix_vec_count + pci_read_config_byte + pci_read_config_dword + pci_read_config_word __pci_register_driver - __per_cpu_offset + pci_release_region + pci_release_regions + pci_release_resource + pci_release_selected_regions + pci_request_irq + pci_request_region + pci_request_regions + pci_request_selected_regions + pci_rescan_bus + pci_resize_resource + pci_restore_msi_state + pci_restore_state + pci_save_state + pci_select_bars + pci_set_master + pci_set_mwi + pci_set_power_state + pci_store_saved_state + pci_unmap_rom + pci_unregister_driver + pci_wake_from_d3 + pci_walk_bus + pci_write_config_byte + pci_write_config_dword + pci_write_config_word + PDE_DATA __percpu_down_read + percpu_down_write __percpu_init_rwsem + __per_cpu_offset + per_cpu_ptr_to_phys + percpu_ref_exit + percpu_ref_init + percpu_ref_is_zero + percpu_ref_kill_and_confirm + percpu_ref_switch_to_atomic_sync + percpu_ref_switch_to_percpu + percpu_up_write + perf_aux_output_begin + perf_aux_output_end + perf_aux_output_flag + perf_event_addr_filters_sync + perf_event_create_kernel_counter + perf_event_disable + perf_event_enable + perf_event_pause + perf_event_read_local + perf_event_read_value + perf_event_release_kernel + perf_event_update_userpage + perf_get_aux + perf_pmu_migrate_context + perf_pmu_register + perf_pmu_unregister + perf_trace_buf_alloc + perf_trace_run_bpf_submit + pfn_valid + phy_attached_info + phy_calibrate + phy_configure + phy_connect + phy_connect_direct + phy_disconnect + phy_do_ioctl_running + phy_drivers_register + phy_drivers_unregister + phy_ethtool_get_link_ksettings + phy_ethtool_nway_reset + phy_ethtool_set_link_ksettings + phy_ethtool_set_wol + phy_exit + phy_find_first + phy_get_pause + phy_init + phy_init_hw + phy_mii_ioctl + phy_pm_runtime_get_sync + phy_pm_runtime_put_sync + phy_power_off + phy_power_on + phy_print_status + phy_register_fixup_for_uid + phy_save_page + phy_set_mode_ext + phy_start + phy_stop + phy_unregister_fixup_for_uid + pick_highest_pushable_task + pid_nr_ns + pid_task + pinconf_generic_dt_free_map + pinconf_generic_dt_node_to_map + pinctrl_add_gpio_range + pinctrl_dev_get_drvdata + pinctrl_enable + pinctrl_force_default + pinctrl_force_sleep + pinctrl_get + pinctrl_lookup_state + pinctrl_pm_select_default_state + pinctrl_pm_select_idle_state + pinctrl_pm_select_sleep_state + pinctrl_put + pinctrl_remove_gpio_range + pinctrl_select_default_state + pinctrl_select_state + pinctrl_utils_free_map + pin_get_name + pin_user_pages + pin_user_pages_fast + pin_user_pages_remote + pipe_lock + pipe_unlock + pktgen_xfrm_outer_mode_output + platform_add_devices + platform_bus_type + platform_device_add + platform_device_add_data + platform_device_add_properties + platform_device_add_resources + platform_device_alloc + platform_device_del + platform_device_put + platform_device_register + platform_device_register_full + platform_device_unregister __platform_driver_probe __platform_driver_register + platform_driver_unregister + platform_find_device_by_driver + platform_get_irq + platform_get_irq_byname + platform_get_irq_byname_optional + platform_get_irq_optional + platform_get_resource + platform_get_resource_byname + platform_irq_count __platform_register_drivers + pm_clk_add + pm_clk_create + pm_clk_destroy + pm_clk_resume + pm_clk_suspend + pm_generic_resume + pm_generic_runtime_resume + pm_generic_runtime_suspend + pm_generic_suspend + pm_genpd_add_subdomain + pm_genpd_init + pm_genpd_remove + pm_genpd_remove_subdomain + pm_power_off __pm_relax + pm_relax + pm_runtime_allow + pm_runtime_autosuspend_expiration + pm_runtime_barrier __pm_runtime_disable + pm_runtime_enable + pm_runtime_forbid + pm_runtime_force_resume + pm_runtime_force_suspend + pm_runtime_get_if_active __pm_runtime_idle + pm_runtime_irq_safe + pm_runtime_no_callbacks __pm_runtime_resume + pm_runtime_set_autosuspend_delay __pm_runtime_set_status __pm_runtime_suspend __pm_runtime_use_autosuspend __pm_stay_awake + pm_stay_awake + pm_suspend_global_flags + pm_system_wakeup + pm_wakeup_dev_event + pm_wakeup_ws_event + policy_has_boost_freq + power_supply_changed + power_supply_get_by_name + power_supply_get_by_phandle_array + power_supply_get_drvdata + power_supply_get_property + power_supply_is_system_supplied + power_supply_put + power_supply_register + power_supply_reg_notifier + power_supply_set_property + power_supply_unregister + power_supply_unreg_notifier + prandom_bytes + prandom_u32 + preempt_schedule + preempt_schedule_notrace + prepare_to_wait + prepare_to_wait_event + print_hex_dump + printk + printk_deferred __printk_ratelimit + printk_timed_ratelimit + proc_create + proc_create_data + proc_create_single_data + proc_dointvec + proc_dointvec_minmax + proc_dostring + proc_douintvec_minmax + proc_mkdir + proc_mkdir_data + proc_remove + proc_set_size + proc_set_user + proc_symlink + proto_register + proto_unregister + ps2_begin_command + ps2_cmd_aborted + ps2_command + ps2_drain + ps2_end_command + ps2_handle_ack + ps2_handle_response + ps2_init + ps2_sendbyte + ps2_sliced_command + pskb_expand_head __pskb_pull_tail + ___pskb_trim + pstore_register + pstore_unregister + public_key_verify_signature + put_device + put_disk + put_iova_domain __put_page + put_pid + put_sg_io_hdr __put_task_struct + put_tty_driver + put_unused_fd + put_vaddr_frames + pwm_apply_state + pwmchip_add + pwmchip_remove + pwm_get_chip_data + pwm_set_chip_data + qcom_smem_state_get + qcom_smem_state_register + qcom_smem_state_unregister + qcom_smem_state_update_bits + qdisc_reset + queue_delayed_work_on + queue_work_on + radix_tree_delete + radix_tree_insert + radix_tree_iter_delete + radix_tree_iter_resume + radix_tree_lookup + radix_tree_maybe_preload + radix_tree_next_chunk + radix_tree_tagged + ___ratelimit + rational_best_approximation + raw_notifier_call_chain + raw_notifier_chain_register + raw_notifier_chain_unregister + _raw_read_lock + _raw_read_lock_bh + _raw_read_lock_irq + _raw_read_lock_irqsave + _raw_read_unlock + _raw_read_unlock_bh + _raw_read_unlock_irq + _raw_read_unlock_irqrestore + _raw_spin_lock + _raw_spin_lock_bh + _raw_spin_lock_irq + _raw_spin_lock_irqsave + _raw_spin_trylock + _raw_spin_trylock_bh + _raw_spin_unlock + _raw_spin_unlock_bh + _raw_spin_unlock_irq + _raw_spin_unlock_irqrestore + _raw_write_lock + _raw_write_lock_bh + _raw_write_lock_irq + _raw_write_lock_irqsave + _raw_write_unlock + _raw_write_unlock_bh + _raw_write_unlock_irq + _raw_write_unlock_irqrestore + rb_erase __rb_erase_color + rb_first + rb_first_postorder __rb_insert_augmented + rb_insert_color + rb_last + rb_next + rb_next_postorder + rb_prev + rb_replace_node + rcu_barrier + rcu_barrier_tasks + rcu_barrier_tasks_trace + rcu_bind_current_to_nocb + rcu_cpu_stall_suppress + rcu_cpu_stall_suppress_at_boot + rcu_expedite_gp + rcu_force_quiescent_state + rcu_fwd_progress_check + rcu_get_gp_kthreads_prio + rcu_get_gp_seq + rcu_gp_is_expedited + rcu_gp_is_normal + rcu_gp_set_torture_wait + rcu_inkernel_boot_has_ended + rcu_is_watching + rcu_jiffies_till_stall_check __rcu_read_lock __rcu_read_unlock + rcu_read_unlock_trace_special + rcutorture_get_gp_data + rcu_unexpedite_gp + rcuwait_wake_up + rdev_get_drvdata + rdev_get_id + reboot_mode + reciprocal_value + refcount_dec_and_lock + refcount_dec_and_mutex_lock + refcount_dec_not_one + refcount_warn_saturate + refresh_frequency_limits __refrigerator + regcache_cache_bypass + regcache_cache_only + regcache_drop_region + regcache_mark_dirty + regcache_sync + regcache_sync_region + register_blkdev __register_chrdev + register_chrdev_region + register_console + register_die_notifier + register_filesystem + register_ftrace_export + register_inet6addr_notifier + register_inetaddr_notifier + register_kernel_break_hook + register_kprobe + register_kretprobe + register_memory_notifier + register_module_notifier + register_netdev + register_netdevice + register_netdevice_notifier + register_netevent_notifier + register_net_sysctl + register_oom_notifier + register_pernet_device + register_pernet_subsys + register_pm_notifier + register_reboot_notifier + register_restart_handler __register_rpmsg_driver + register_shrinker + register_syscore_ops + register_sysctl + register_sysctl_table + register_virtio_device + register_virtio_driver + register_vmap_purge_notifier + regmap_add_irq_chip + regmap_async_complete + regmap_bulk_read + regmap_bulk_write + regmap_check_range_table + regmap_del_irq_chip + regmap_exit + regmap_field_read + regmap_field_update_bits_base + regmap_get_device __regmap_init + regmap_irq_get_domain + regmap_irq_get_virq + regmap_mmio_detach_clk + regmap_multi_reg_write + regmap_multi_reg_write_bypassed + regmap_raw_read + regmap_raw_write + regmap_raw_write_async + regmap_read + regmap_register_patch + regmap_update_bits_base + regmap_write + regulator_allow_bypass + regulator_bulk_disable + regulator_bulk_enable + regulator_bulk_get + regulator_count_voltages + regulator_disable + regulator_disable_deferred + regulator_disable_regmap + regulator_enable + regulator_enable_regmap + regulator_force_disable + regulator_get + regulator_get_current_limit + regulator_get_drvdata + regulator_get_mode + regulator_get_optional + regulator_get_voltage + regulator_get_voltage_rdev + regulator_get_voltage_sel_regmap + regulator_is_enabled + regulator_is_enabled_regmap + regulator_is_supported_voltage + regulator_list_voltage_linear + regulator_list_voltage_linear_range + regulator_list_voltage_table + regulator_map_voltage_ascend + regulator_map_voltage_linear + regulator_notifier_call_chain + regulator_put + regulator_register + regulator_register_notifier + regulator_set_current_limit + regulator_set_load + regulator_set_mode + regulator_set_voltage + regulator_set_voltage_sel_regmap + regulator_unregister + regulator_unregister_notifier + release_firmware + release_pages __release_region + release_sock + remap_pfn_range + remap_vmalloc_range + remove_cpu + remove_memory_subsection + remove_proc_entry + remove_wait_queue + report_iommu_fault + request_any_context_irq + request_firmware + request_firmware_direct + request_firmware_into_buf + request_firmware_nowait __request_module __request_percpu_irq __request_region + request_threaded_irq + resched_curr + reservation_ww_class + reset_control_assert + reset_control_deassert + reset_control_put + reset_control_reset + resume_cpus + return_address + revalidate_disk_size + rfkill_alloc + rfkill_destroy + rfkill_find_type + rfkill_init_sw_state + rfkill_register + rfkill_set_sw_state + rfkill_unregister + rhashtable_destroy + rhashtable_init + rhashtable_insert_slow __rht_bucket_nested + rht_bucket_nested + rht_bucket_nested_insert + rndis_deregister + rndis_free_response + rndis_get_next_response + rndis_msg_parser + rndis_register + rndis_set_host_mac + rndis_set_param_dev + rndis_set_param_medium + rndis_set_param_vendor + rndis_signal_connect + rndis_uninit + root_task_group + round_jiffies_relative + round_jiffies_up + rpmsg_get_signals + rpmsg_poll + rpmsg_register_device + rpmsg_send + rpmsg_set_signals + rpmsg_trysend + rpmsg_unregister_device + rproc_add + rproc_add_subdev + rproc_alloc + rproc_boot + rproc_coredump_add_custom_segment + rproc_coredump_add_segment + rproc_coredump_set_elf_info + rproc_coredump_using_sections + rproc_del + rproc_elf_get_boot_addr + rproc_free + rproc_get_by_child + rproc_get_by_phandle + rproc_put + rproc_remove_subdev + rproc_report_crash + rproc_shutdown + rps_needed + rtc_class_close + rtc_class_open + rtc_read_time __rtc_register_device + rtc_set_time + rtc_time64_to_tm + rtc_tm_to_time64 + rtc_update_irq + rtc_valid_tm + rtc_year_days + rt_mutex_lock + rt_mutex_trylock + rt_mutex_unlock + rtnl_is_locked + rtnl_link_register + rtnl_link_unregister + rtnl_lock + rtnl_register_module + rtnl_trylock + rtnl_unicast + rtnl_unlock + rtnl_unregister + runqueues + sb800_prefetch + sbitmap_queue_min_shallow_depth + sched_clock + sched_feat_keys + sched_feat_names + sched_setattr + sched_setattr_nocheck + sched_set_fifo + sched_set_fifo_low + sched_set_normal + sched_setscheduler + sched_setscheduler_nocheck + sched_show_task + sched_trace_cfs_rq_avg + sched_trace_cfs_rq_cpu + sched_trace_cfs_rq_path + sched_trace_rd_span + sched_trace_rq_avg_dl + sched_trace_rq_avg_irq + sched_trace_rq_avg_rt + sched_trace_rq_cpu + sched_uclamp_used + schedule + schedule_hrtimeout + schedule_timeout + schedule_timeout_interruptible + schedule_timeout_uninterruptible + scnprintf + scsi_autopm_get_device + scsi_autopm_put_device + scsi_block_requests + scsi_block_when_processing_errors + scsi_command_size_tbl + scsi_compat_ioctl + scsi_device_get + scsi_device_put + scsi_device_quiesce + scsi_dma_unmap + scsi_eh_ready_devs __scsi_execute + scsi_ioctl + scsi_ioctl_block_when_processing_errors __scsi_iterate_devices + scsi_normalize_sense __scsi_print_sense + scsi_print_sense_hdr + scsi_register_interface + scsi_remove_device + scsi_unblock_requests + sdev_prefix_printk __sdhci_add_host + sdhci_add_host + sdhci_cleanup_host + sdhci_cqe_disable + sdhci_cqe_enable + sdhci_cqe_irq + sdhci_enable_clk + sdhci_get_property + sdhci_pltfm_free + sdhci_pltfm_init + sdhci_remove_host + sdhci_reset + sdhci_set_bus_width + sdhci_set_power_noreg + sdhci_setup_host + sdio_claim_host + sdio_disable_func + sdio_enable_func + sdio_f0_readb + sdio_f0_writeb + sdio_get_host_pm_caps + sdio_memcpy_fromio + sdio_memcpy_toio + sdio_readsb + sdio_register_driver + sdio_release_host + sdio_set_block_size + sdio_set_host_pm_flags + sdio_signal_irq + sdio_unregister_driver + sdio_writesb + securityfs_create_dir + securityfs_create_file + securityfs_remove + send_sig_info + seq_buf_printf + seq_file_path + seq_hex_dump + seq_list_next + seq_list_start + seq_lseek + seq_open __seq_open_private + seq_printf + seq_putc + seq_puts + seq_read + seq_release + seq_release_private + seq_vprintf + seq_write + serdev_device_close + serdev_device_open + serdev_device_set_baudrate + serdev_device_set_flow_control + serdev_device_wait_until_sent + serdev_device_write + serdev_device_write_wakeup + serio_close + serio_interrupt + serio_open + serio_reconnect __serio_register_driver __serio_register_port + serio_rescan + serio_unregister_child_port + serio_unregister_driver + serio_unregister_port + set_blocksize + set_capacity_revalidate_and_notify + set_cpus_allowed_ptr + set_disk_ro + set_freezable + set_normalized_timespec64 + set_page_dirty + set_page_dirty_lock + __SetPageMovable + set_task_cpu + set_user_nice + sg_alloc_table + sg_alloc_table_from_pages + sg_free_table + sg_init_one + sg_init_table + sgl_alloc + sgl_free + sg_miter_next + sg_miter_start + sg_miter_stop + sg_nents_for_len + sg_next __sg_page_iter_dma_next __sg_page_iter_next __sg_page_iter_start + sg_pcopy_from_buffer + sg_pcopy_to_buffer + sg_scsi_ioctl + sg_zero_buffer + shmem_truncate_range + show_rcu_gp_kthreads + show_regs + sigprocmask + si_mem_available + si_meminfo + simple_attr_open + simple_attr_read + simple_attr_release + simple_attr_write + simple_dir_inode_operations + simple_dir_operations + simple_open + simple_read_from_buffer + simple_statfs + simple_strtol + simple_strtoll + simple_strtoul + simple_strtoull + simple_write_to_buffer + single_open + single_open_size + single_release + si_swapinfo + sk_alloc + skb_add_rx_frag + skb_append_pagefrags + skb_checksum + skb_clone + skb_coalesce_rx_frag + skb_copy + skb_copy_bits + skb_copy_datagram_iter + skb_copy_expand + skb_copy_ubufs + skb_dequeue + skb_dequeue_tail + skb_ensure_writable __skb_ext_put __skb_flow_dissect + skb_free_datagram __skb_get_hash __skb_gso_segment __skb_pad + skb_page_frag_refill + skb_partial_csum_set + skb_pull + skb_push + skb_put + skb_queue_head + skb_queue_purge + skb_queue_tail + skb_realloc_headroom + skb_recv_datagram + skb_set_owner_w + skb_store_bits + skb_to_sgvec + skb_trim + skb_tstamp_tx + skb_unlink + sk_free + skip_spaces + smpboot_register_percpu_thread + smpboot_unregister_percpu_thread + smp_call_function + smp_call_function_any + smp_call_function_many + smp_call_function_single + smp_call_function_single_async + smp_call_on_cpu + snd_card_disconnect + snd_card_free + snd_card_new + snd_card_register + snd_card_rw_proc_new + snd_component_add + snd_compr_stop_error + snd_ctl_add + _snd_ctl_add_follower + snd_ctl_add_vmaster_hook + snd_ctl_apply_vmaster_followers + snd_ctl_boolean_mono_info + snd_ctl_boolean_stereo_info + snd_ctl_enum_info + snd_ctl_find_id + snd_ctl_make_virtual_master + snd_ctl_new1 + snd_ctl_notify + snd_ctl_remove + snd_ctl_remove_id + snd_ctl_sync_vmaster + snd_device_disconnect + snd_device_free + snd_device_new + snd_dma_alloc_pages + snd_dmaengine_pcm_prepare_slave_config + snd_dma_free_pages + snd_hwdep_new + snd_info_create_card_entry + snd_info_create_module_entry + snd_info_free_entry + snd_info_register + snd_interval_refine + snd_jack_new + snd_jack_report + snd_jack_set_key + snd_pci_quirk_lookup + snd_pcm_add_chmap_ctls + snd_pcm_alt_chmaps + snd_pcm_create_iec958_consumer_hw_params + snd_pcm_format_physical_width + snd_pcm_format_width + snd_pcm_hw_constraint_eld + snd_pcm_hw_constraint_integer + snd_pcm_hw_constraint_list + snd_pcm_hw_constraint_minmax + snd_pcm_hw_constraint_msbits + snd_pcm_hw_constraint_step + snd_pcm_hw_limit_rates + snd_pcm_hw_rule_add + snd_pcm_lib_default_mmap + snd_pcm_lib_free_pages + snd_pcm_lib_ioctl + snd_pcm_lib_malloc_pages + snd_pcm_lib_preallocate_free_for_all + snd_pcm_lib_preallocate_pages + snd_pcm_new + snd_pcm_period_elapsed + snd_pcm_rate_range_to_bits + snd_pcm_set_managed_buffer_all + snd_pcm_set_ops + snd_pcm_set_sync + snd_pcm_std_chmaps + snd_pcm_stream_lock + _snd_pcm_stream_lock_irqsave + snd_pcm_stream_unlock + snd_pcm_stream_unlock_irqrestore + snd_soc_add_card_controls + snd_soc_add_component_controls + snd_soc_add_dai_controls + snd_soc_bytes_info_ext + snd_soc_bytes_tlv_callback + snd_soc_card_get_kcontrol + snd_soc_card_jack_new + snd_soc_component_async_complete + snd_soc_component_disable_pin + snd_soc_component_exit_regmap + snd_soc_component_force_enable_pin + snd_soc_component_init_regmap + snd_soc_component_read + snd_soc_component_set_jack + snd_soc_component_set_pll + snd_soc_component_set_sysclk + snd_soc_component_update_bits + snd_soc_component_update_bits_async + snd_soc_component_write + snd_soc_dai_get_channel_map + snd_soc_dai_link_set_capabilities + snd_soc_dai_set_bclk_ratio + snd_soc_dai_set_channel_map + snd_soc_dai_set_fmt + snd_soc_dai_set_pll + snd_soc_dai_set_sysclk + snd_soc_dai_set_tdm_slot + snd_soc_dapm_add_routes + snd_soc_dapm_disable_pin + snd_soc_dapm_disable_pin_unlocked + snd_soc_dapm_enable_pin + snd_soc_dapm_force_enable_pin + snd_soc_dapm_force_enable_pin_unlocked + snd_soc_dapm_get_enum_double + snd_soc_dapm_get_pin_status + snd_soc_dapm_get_pin_switch + snd_soc_dapm_get_volsw + snd_soc_dapm_ignore_suspend + snd_soc_dapm_info_pin_switch + snd_soc_dapm_kcontrol_dapm + snd_soc_dapm_kcontrol_widget + snd_soc_dapm_mixer_update_power + snd_soc_dapm_mux_update_power + snd_soc_dapm_new_control + snd_soc_dapm_new_controls + snd_soc_dapm_new_widgets + snd_soc_dapm_put_enum_double + snd_soc_dapm_put_pin_switch + snd_soc_dapm_put_volsw + snd_soc_dapm_sync + snd_soc_dapm_sync_unlocked + snd_soc_dapm_weak_routes + snd_soc_find_dai + snd_soc_get_enum_double + snd_soc_get_pcm_runtime + snd_soc_get_volsw + snd_soc_get_volsw_range + snd_soc_get_volsw_sx + snd_soc_get_xr_sx + snd_soc_info_enum_double + snd_soc_info_multi_ext + snd_soc_info_volsw + snd_soc_info_volsw_range + snd_soc_info_volsw_sx + snd_soc_info_xr_sx + snd_soc_jack_add_gpios + snd_soc_jack_report + snd_soc_lookup_component + snd_soc_new_compress + snd_soc_of_get_dai_link_codecs + snd_soc_of_get_dai_name + snd_soc_of_parse_audio_routing + snd_soc_of_parse_audio_simple_widgets + snd_soc_of_parse_aux_devs + snd_soc_of_parse_card_name + snd_soc_of_parse_daifmt + snd_soc_of_parse_node_prefix + snd_soc_of_parse_tdm_slot + snd_soc_of_put_dai_link_codecs + snd_soc_params_to_bclk + snd_soc_params_to_frame_size + snd_soc_pm_ops + snd_soc_put_enum_double + snd_soc_put_volsw + snd_soc_put_volsw_range + snd_soc_put_volsw_sx + snd_soc_put_xr_sx + snd_soc_register_card + snd_soc_register_component + snd_soc_rtdcom_lookup + snd_soc_runtime_calc_hw + snd_soc_runtime_set_dai_fmt + snd_soc_set_runtime_hwparams + snd_soc_tplg_component_load + snd_soc_tplg_component_remove + snd_soc_tplg_widget_bind_event + snd_soc_unregister_card + snd_soc_unregister_component + snd_usb_enable_audio_stream + snd_vendor_set_ops + snprintf + soc_device_register + soc_device_unregister + sock_alloc_send_skb + sock_create_kern + sock_gettstamp + sock_init_data + sock_i_uid + sock_no_accept + sock_no_listen + sock_no_mmap + sock_no_sendpage + sock_no_shutdown + sock_no_socketpair + sock_queue_rcv_skb + sock_register + sock_release + sock_setsockopt + sock_unregister + sock_wfree + softnet_data + sort __spi_alloc_controller + spi_bus_lock + spi_bus_type + spi_bus_unlock + spi_controller_resume + spi_controller_suspend + spi_delay_exec + spi_finalize_current_message + spi_finalize_current_transfer + spi_get_next_queued_message + spi_register_controller __spi_register_driver + spi_setup + spi_sync + spi_sync_locked + spi_unregister_controller __splice_from_pipe + split_page + spmi_controller_add + spmi_controller_alloc + spmi_controller_remove __spmi_driver_register + spmi_ext_register_read + spmi_ext_register_readl + spmi_ext_register_write + spmi_ext_register_writel + spmi_register_read + spmi_register_write + spmi_register_zero_write + sprintf + sprint_symbol + sprint_symbol_no_offset + srcu_barrier + srcu_batches_completed + srcu_init_notifier_head + srcu_notifier_call_chain + srcu_notifier_chain_register + srcu_notifier_chain_unregister __srcu_read_lock __srcu_read_unlock + srcutorture_get_gp_data + srcu_torture_stats_print + sscanf __stack_chk_fail __stack_chk_guard + stack_trace_print + stack_trace_save + stack_trace_save_regs + stack_trace_save_tsk + static_key_disable + static_key_disable_cpuslocked + static_key_slow_dec + static_key_slow_inc + stop_machine + stop_one_cpu_nowait + stpcpy + strcasecmp + strcat + strchr + strchrnul + strcmp + strcpy + strcspn + stream_open + strim + string_get_size + strlcat + strlcpy + strlen + strncasecmp + strncat + strnchr + strncmp + strncpy + strncpy_from_user + strndup_user + strnlen + strnstr + strpbrk + strrchr + strreplace + strscpy + strsep + strspn + strstr + submit_bh + submit_bio + submit_bio_wait + subsys_system_register __sw_hweight16 __sw_hweight32 __sw_hweight64 __sw_hweight8 + swiotlb_nr_tbl + sync_blockdev + sync_file_create + sync_file_get_fence + synchronize_irq + synchronize_net + synchronize_rcu + synchronize_rcu_expedited + synchronize_rcu_tasks + synchronize_rcu_tasks_trace + synchronize_srcu + synchronize_srcu_expedited + syscon_node_to_regmap + syscon_regmap_lookup_by_phandle + sysctl_sched_features + sysctl_sched_latency + sysctl_vals + sysfs_add_file_to_group + sysfs_add_link_to_group + sysfs_create_bin_file + sysfs_create_file_ns + sysfs_create_files + sysfs_create_group + sysfs_create_groups + sysfs_create_link + sysfs_emit + sysfs_emit_at __sysfs_match_string + sysfs_notify + sysfs_remove_bin_file + sysfs_remove_file_from_group + sysfs_remove_file_ns + sysfs_remove_files + sysfs_remove_group + sysfs_remove_groups + sysfs_remove_link + sysfs_remove_link_from_group + sysfs_streq + sysfs_update_group + sysrq_mask + system_freezable_wq + system_freezing_cnt + system_highpri_wq + system_long_wq + system_power_efficient_wq + system_state + system_unbound_wq + system_wq + sys_tz + task_active_pid_ns + task_groups + __tasklet_hi_schedule + tasklet_init + tasklet_kill + __tasklet_schedule + tasklet_setup + tasklist_lock + task_may_not_preempt __task_pid_nr_ns __task_rq_lock - __tasklet_hi_schedule - __tasklet_schedule + task_rq_lock + tcpci_get_tcpm_port + tcpci_irq + tcpci_register_port + tcpci_unregister_port + tcpm_cc_change + tcpm_is_toggling + tcpm_pd_hard_reset + tcpm_pd_receive + tcpm_pd_transmit_complete + tcpm_sink_frs + tcpm_sourcing_vbus + tcpm_update_sink_capabilities + tcpm_vbus_change + tcp_register_congestion_control + tcp_reno_cong_avoid + tcp_reno_ssthresh + tcp_reno_undo_cwnd + tcp_slow_start + tcp_unregister_congestion_control + thermal_cdev_update + thermal_cooling_device_register + thermal_cooling_device_unregister + thermal_of_cooling_device_register + thermal_pressure + thermal_zone_device_disable + thermal_zone_device_enable + thermal_zone_device_is_enabled + thermal_zone_device_register + thermal_zone_device_unregister + thermal_zone_device_update + thermal_zone_get_slope + thermal_zone_get_temp + thermal_zone_get_zone_by_name + thermal_zone_of_sensor_register + thermal_zone_of_sensor_unregister + thread_group_cputime_adjusted + tick_nohz_get_idle_calls_cpu + tick_nohz_get_sleep_length + time64_to_tm + timecounter_init + timecounter_read + timer_unstable_counter_workaround + topology_set_thermal_pressure + _totalram_pages + total_swapcache_pages + _trace_android_vh_record_pcpu_rwsem_starttime __trace_bprintk __trace_bputs - __trace_printk + trace_clock_local + trace_event_buffer_commit + trace_event_buffer_reserve + trace_event_ignore_this_pid + trace_event_raw_init + trace_event_reg + trace_handle_return __traceiter_android_rvh_account_irq __traceiter_android_rvh_build_perf_domains __traceiter_android_rvh_can_migrate_task @@ -233,8 +3718,8 @@ __traceiter_android_rvh_cpu_cgroup_attach __traceiter_android_rvh_cpu_cgroup_can_attach __traceiter_android_rvh_cpu_cgroup_online - __traceiter_android_rvh_cpu_overutilized __traceiter_android_rvh_cpufreq_transition + __traceiter_android_rvh_cpu_overutilized __traceiter_android_rvh_dequeue_task __traceiter_android_rvh_die_kernel_fault __traceiter_android_rvh_do_mem_abort @@ -346,6 +3831,7 @@ __traceiter_kfree_skb __traceiter_sched_util_est_se_tp __traceiter_xdp_exception + trace_output_call __tracepoint_android_rvh_account_irq __tracepoint_android_rvh_arm64_serror_panic __tracepoint_android_rvh_bad_mode @@ -355,8 +3841,8 @@ __tracepoint_android_rvh_cpu_cgroup_attach __tracepoint_android_rvh_cpu_cgroup_can_attach __tracepoint_android_rvh_cpu_cgroup_online - __tracepoint_android_rvh_cpu_overutilized __tracepoint_android_rvh_cpufreq_transition + __tracepoint_android_rvh_cpu_overutilized __tracepoint_android_rvh_dequeue_task __tracepoint_android_rvh_dequeue_task_idle __tracepoint_android_rvh_die_kernel_fault @@ -501,6 +3987,9 @@ __tracepoint_pelt_irq_tp __tracepoint_pelt_rt_tp __tracepoint_pelt_se_tp + tracepoint_probe_register + tracepoint_probe_register_prio + tracepoint_probe_unregister __tracepoint_rwmmio_post_read __tracepoint_rwmmio_read __tracepoint_rwmmio_write @@ -513,3523 +4002,14 @@ __tracepoint_workqueue_execute_end __tracepoint_workqueue_execute_start __tracepoint_xdp_exception - __tty_alloc_driver - __tty_insert_flip_char - __udelay - __uio_register_device - __unregister_chrdev - __update_load_avg_blocked_se - __usb_create_hcd - __usb_get_extra_descriptor - __usecs_to_jiffies - __v4l2_device_register_subdev_nodes - __video_register_device - __wait_rcu_gp - __wake_up - __wake_up_locked - __wake_up_locked_key - __wake_up_sync - __warn_printk - __xa_alloc - __xa_insert - __xfrm_state_destroy - _atomic_dec_and_lock - _copy_from_iter - _copy_from_iter_full - _copy_to_iter - _ctype - _dev_alert - _dev_crit - _dev_emerg - _dev_err - _dev_info - _dev_notice - _dev_warn - _raw_read_lock - _raw_read_lock_bh - _raw_read_lock_irq - _raw_read_lock_irqsave - _raw_read_unlock - _raw_read_unlock_bh - _raw_read_unlock_irq - _raw_read_unlock_irqrestore - _raw_spin_lock - _raw_spin_lock_bh - _raw_spin_lock_irq - _raw_spin_lock_irqsave - _raw_spin_trylock - _raw_spin_trylock_bh - _raw_spin_unlock - _raw_spin_unlock_bh - _raw_spin_unlock_irq - _raw_spin_unlock_irqrestore - _raw_write_lock - _raw_write_lock_bh - _raw_write_lock_irq - _raw_write_lock_irqsave - _raw_write_unlock - _raw_write_unlock_bh - _raw_write_unlock_irq - _raw_write_unlock_irqrestore - _snd_ctl_add_follower - _snd_pcm_stream_lock_irqsave - _totalram_pages - _trace_android_vh_record_pcpu_rwsem_starttime - access_process_vm - ack_all_badblocks - activate_task - add_cpu - add_device_randomness - add_memory - add_memory_subsection - add_taint - add_timer - add_timer_on - add_uevent_var - add_wait_queue - adjust_managed_page_count - alarm_cancel - alarm_init - alarm_start - alarm_start_relative - alarm_try_to_cancel - alarmtimer_get_rtcdev - all_vm_events - alloc_anon_inode - alloc_chrdev_region - alloc_etherdev_mqs - alloc_io_pgtable_ops - alloc_netdev_mqs - alloc_page_buffers - alloc_pages_exact - alloc_skb_with_frags - alloc_workqueue - amba_bustype - amba_driver_register - amba_driver_unregister - amba_release_regions - amba_request_regions - android_debug_per_cpu_symbol - android_debug_symbol - android_rvh_probe_register - anon_inode_getfd - anon_inode_getfile - arch_timer_read_counter - argv_free - argv_split - arm64_const_caps_ready - arm64_use_ng_mappings - async_schedule_node - async_schedule_node_domain - async_synchronize_full_domain - atomic_notifier_call_chain - atomic_notifier_chain_register - atomic_notifier_chain_unregister - autoremove_wake_function - available_idle_cpu - backlight_device_get_by_type - backlight_device_register - backlight_device_set_brightness - backlight_device_unregister - badblocks_clear - badblocks_exit - badblocks_init - badblocks_set - badblocks_show - badblocks_store - balloon_aops - balloon_page_alloc - balloon_page_dequeue - balloon_page_enqueue - bcmp - bd_link_disk_holder - bd_set_nr_sectors - bd_unlink_disk_holder - bdev_check_media_change - bdev_read_only - bdevname - bdget_disk - bdput - bgpio_init - bin2hex - bio_add_page - bio_alloc_bioset - bio_associate_blkg - bio_chain - bio_clone_blkg_association - bio_endio - bio_init - bio_put - bioset_exit - bioset_init - bitmap_allocate_region - bitmap_find_next_zero_area_off - bitmap_from_arr32 - bitmap_parse - bitmap_parselist - bitmap_parselist_user - bitmap_print_to_pagebuf - bitmap_release_region - bitmap_to_arr32 - bitmap_zalloc - blk_alloc_queue - blk_cleanup_queue - blk_execute_rq - blk_execute_rq_nowait - blk_finish_plug - blk_freeze_queue_start - blk_get_queue - blk_get_request - blk_mq_alloc_request - blk_mq_alloc_request_hctx - blk_mq_alloc_tag_set - blk_mq_complete_request - blk_mq_complete_request_remote - blk_mq_debugfs_rq_show - blk_mq_delay_kick_requeue_list - blk_mq_end_request - blk_mq_free_request - blk_mq_free_tag_set - blk_mq_freeze_queue - blk_mq_freeze_queue_wait - blk_mq_freeze_queue_wait_timeout - blk_mq_init_queue - blk_mq_map_queues - blk_mq_pci_map_queues - blk_mq_quiesce_queue - blk_mq_requeue_request - blk_mq_rq_cpu - blk_mq_run_hw_queues - blk_mq_sched_request_inserted - blk_mq_sched_try_insert_merge - blk_mq_sched_try_merge - blk_mq_start_request - blk_mq_start_stopped_hw_queues - blk_mq_stop_hw_queue - blk_mq_tag_to_rq - blk_mq_tagset_busy_iter - blk_mq_tagset_wait_completed_request - blk_mq_unfreeze_queue - blk_mq_unique_tag - blk_mq_unquiesce_queue - blk_mq_update_nr_hw_queues - blk_mq_virtio_map_queues - blk_poll - blk_put_queue - blk_put_request - blk_queue_alignment_offset - blk_queue_bounce_limit - blk_queue_can_use_dma_map_merging - blk_queue_chunk_sectors - blk_queue_dma_alignment - blk_queue_flag_clear - blk_queue_flag_set - blk_queue_flag_test_and_set - blk_queue_io_min - blk_queue_io_opt - blk_queue_logical_block_size - blk_queue_max_discard_sectors - blk_queue_max_discard_segments - blk_queue_max_hw_sectors - blk_queue_max_segment_size - blk_queue_max_segments - blk_queue_max_write_zeroes_sectors - blk_queue_physical_block_size - blk_queue_rq_timeout - blk_queue_split - blk_queue_virt_boundary - blk_queue_write_cache - blk_register_region - blk_rq_map_kern - blk_rq_map_user - blk_rq_map_user_iov - blk_rq_unmap_user - blk_set_queue_dying - blk_set_stacking_limits - blk_start_plug - blk_status_to_errno - blk_sync_queue - blk_unregister_region - blk_update_request - blk_verify_command - blkcg_activate_policy - blkcg_deactivate_policy - blkcg_policy_register - blkcg_policy_unregister - blkcg_root - blkdev_fsync - blkdev_get_by_dev - blkdev_get_by_path - blkdev_issue_flush - blkdev_put - blkg_lookup_slowpath - blocking_notifier_call_chain - blocking_notifier_chain_register - blocking_notifier_chain_unregister - bmap - bpf_dispatcher_xdp_func - bpf_prog_add - bpf_prog_put - bpf_prog_sub - bpf_stats_enabled_key - bpf_trace_run1 - bpf_trace_run10 - bpf_trace_run11 - bpf_trace_run12 - bpf_trace_run2 - bpf_trace_run3 - bpf_trace_run4 - bpf_trace_run5 - bpf_trace_run6 - bpf_trace_run7 - bpf_trace_run8 - bpf_trace_run9 - bpf_warn_invalid_xdp_action - bsearch - bt_err - bt_info - build_skb - bus_find_device - bus_for_each_dev - bus_for_each_drv - bus_register - bus_register_notifier - bus_set_iommu - bus_unregister - bus_unregister_notifier - cache_line_size - call_netdevice_notifiers - call_rcu - call_rcu_tasks - call_rcu_tasks_trace - call_srcu - cancel_delayed_work - cancel_delayed_work_sync - cancel_work_sync - capable - cdc_ncm_bind_common - cdc_ncm_change_mtu - cdc_ncm_fill_tx_frame - cdc_ncm_rx_verify_ndp16 - cdc_ncm_rx_verify_nth16 - cdc_ncm_select_altsetting - cdc_ncm_unbind - cdc_parse_cdc_header - cdev_add - cdev_alloc - cdev_del - cdev_device_add - cdev_device_del - cdev_init - cec_allocate_adapter - cec_delete_adapter - cec_received_msg_ts - cec_register_adapter - cec_s_log_addrs - cec_s_phys_addr - cec_s_phys_addr_from_edid - cec_transmit_attempt_done_ts - cec_transmit_done_ts - cec_unregister_adapter - cgroup_path_ns - cgroup_taskset_first - cgroup_taskset_next - check_preempt_curr - check_zeroed_user - class_create_file_ns - class_destroy - class_find_device - class_for_each_device - class_interface_unregister - class_remove_file_ns - class_unregister - cleancache_register_ops - cleanup_srcu_struct - clear_page - clk_bulk_disable - clk_bulk_enable - clk_bulk_get_all - clk_bulk_prepare - clk_bulk_put_all - clk_bulk_unprepare - clk_disable - clk_enable - clk_fixed_factor_ops - clk_fixed_rate_ops - clk_get - clk_get_parent - clk_get_rate - clk_hw_get_flags - clk_hw_get_name - clk_hw_get_num_parents - clk_hw_get_parent - clk_hw_get_parent_by_index - clk_hw_get_rate - clk_hw_is_enabled - clk_hw_is_prepared - clk_hw_register - clk_hw_register_fixed_factor - clk_hw_round_rate - clk_hw_set_rate_range - clk_hw_unregister - clk_hw_unregister_divider - clk_hw_unregister_fixed_factor - clk_hw_unregister_gate - clk_hw_unregister_mux - clk_notifier_register - clk_notifier_unregister - clk_prepare - clk_put - clk_register - clk_register_clkdev - clk_register_fixed_factor - clk_register_fixed_rate - clk_register_gate - clk_round_rate - clk_set_parent - clk_set_rate - clk_sync_state - clk_unprepare - clk_unregister - clockevents_config_and_register - clocks_calc_mult_shift - cma_alloc - cma_for_each_area - cma_get_name - cma_release - compat_alloc_user_space - compat_only_sysfs_link_entry_to_kobj - compat_ptr_ioctl - complete - complete_all - complete_and_exit - completion_done - component_add - component_bind_all - component_del - component_master_add_with_match - component_master_del - component_match_add_release - component_unbind_all - cond_synchronize_rcu - config_ep_by_speed - config_group_init - config_group_init_type_name - config_item_get - config_item_put - configfs_register_subsystem - configfs_unregister_subsystem - console_drivers - console_printk - console_stop - console_suspend_enabled - console_trylock - console_unlock - consume_skb - contig_page_data - copy_from_kernel_nofault - copy_page - cpu_all_bits - cpu_bit_bitmap - cpu_hotplug_disable - cpu_hotplug_enable - cpu_hwcap_keys - cpu_hwcaps - cpu_irqtime - cpu_is_hotpluggable - cpu_latency_qos_add_request - cpu_latency_qos_remove_request - cpu_latency_qos_request_active - cpu_latency_qos_update_request - cpu_number - cpu_pm_register_notifier - cpu_pm_unregister_notifier - cpu_scale - cpu_subsys - cpu_topology - cpufreq_add_update_util_hook - cpufreq_cpu_get - cpufreq_cpu_get_raw - cpufreq_cpu_put - cpufreq_disable_fast_switch - cpufreq_driver_fast_switch - cpufreq_driver_resolve_freq - cpufreq_enable_boost_support - cpufreq_enable_fast_switch - cpufreq_freq_attr_scaling_available_freqs - cpufreq_freq_attr_scaling_boost_freqs - cpufreq_freq_transition_begin - cpufreq_freq_transition_end - cpufreq_frequency_table_verify - cpufreq_generic_attr - cpufreq_generic_frequency_table_verify - cpufreq_generic_get - cpufreq_generic_suspend - cpufreq_get_driver_data - cpufreq_get_policy - cpufreq_policy_transition_delay_us - cpufreq_quick_get - cpufreq_quick_get_max - cpufreq_register_driver - cpufreq_register_governor - cpufreq_register_notifier - cpufreq_remove_update_util_hook - cpufreq_table_index_unsorted - cpufreq_this_cpu_can_update - cpufreq_unregister_driver - cpufreq_unregister_notifier - cpufreq_update_policy - cpuhp_tasks_frozen - cpuidle_governor_latency_req - cpuidle_register_governor - cpumask_any_but - cpumask_next - cpumask_next_and - cpumask_next_wrap - cpupri_find_fitness - cpus_read_lock - cpus_read_unlock - crc16 - crc32_le - crc8 - crc8_populate_msb - create_function_device - crypto_aead_encrypt - crypto_aead_setauthsize - crypto_aead_setkey - crypto_alloc_aead - crypto_alloc_base - crypto_alloc_shash - crypto_alloc_skcipher - crypto_cipher_encrypt_one - crypto_cipher_setkey - crypto_comp_compress - crypto_comp_decompress - crypto_destroy_tfm - crypto_has_alg - crypto_register_alg - crypto_register_rngs - crypto_register_scomp - crypto_shash_digest - crypto_shash_final - crypto_shash_setkey - crypto_shash_update - crypto_skcipher_decrypt - crypto_skcipher_encrypt - crypto_skcipher_setkey - crypto_unregister_alg - crypto_unregister_rngs - crypto_unregister_scomp - css_next_child - css_next_descendant_pre - csum_ipv6_magic - csum_partial - csum_tcpudp_nofold - current_time - current_work - d_add - d_alloc_name - d_delete - d_make_root - d_path - dapm_pinctrl_event - dapm_regulator_event - datagram_poll - deactivate_task - debugfs_attr_read - debugfs_attr_write - debugfs_create_atomic_t - debugfs_create_blob - debugfs_create_bool - debugfs_create_dir - debugfs_create_file - debugfs_create_file_unsafe - debugfs_create_regset32 - debugfs_create_size_t - debugfs_create_symlink - debugfs_create_u16 - debugfs_create_u32 - debugfs_create_u64 - debugfs_create_u8 - debugfs_create_ulong - debugfs_create_x32 - debugfs_create_x64 - debugfs_create_x8 - debugfs_file_get - debugfs_file_put - debugfs_lookup - debugfs_print_regs32 - debugfs_remove - dec_zone_page_state - default_llseek - deferred_free - del_gendisk - del_timer - del_timer_sync - delayed_work_timer_fn - desc_to_gpio - destroy_workqueue - dev_alloc_name - dev_close - dev_coredumpm - dev_coredumpv - dev_driver_string - dev_err_probe - dev_fwnode - dev_get_by_index - dev_get_by_name - dev_get_regmap - dev_get_stats - dev_mc_sync_multiple - dev_mc_unsync - dev_open - dev_pm_clear_wake_irq - dev_pm_domain_attach - dev_pm_domain_attach_by_name - dev_pm_domain_detach - dev_pm_genpd_add_notifier - dev_pm_genpd_remove_notifier - dev_pm_genpd_set_next_wakeup - dev_pm_genpd_set_performance_state - dev_pm_opp_add - dev_pm_opp_adjust_voltage - dev_pm_opp_disable - dev_pm_opp_enable - dev_pm_opp_find_freq_ceil - dev_pm_opp_find_freq_ceil_by_volt - dev_pm_opp_find_freq_exact - dev_pm_opp_find_freq_floor - dev_pm_opp_free_cpufreq_table - dev_pm_opp_get_freq - dev_pm_opp_get_level - dev_pm_opp_get_max_transition_latency - dev_pm_opp_get_opp_count - dev_pm_opp_get_opp_table - dev_pm_opp_get_sharing_cpus - dev_pm_opp_get_suspend_opp_freq - dev_pm_opp_get_voltage - dev_pm_opp_init_cpufreq_table - dev_pm_opp_of_add_table - dev_pm_opp_of_cpumask_add_table - dev_pm_opp_of_cpumask_remove_table - dev_pm_opp_of_find_icc_paths - dev_pm_opp_of_get_sharing_cpus - dev_pm_opp_of_register_em - dev_pm_opp_of_remove_table - dev_pm_opp_put - dev_pm_opp_put_clkname - dev_pm_opp_put_opp_table - dev_pm_opp_put_regulators - dev_pm_opp_register_notifier - dev_pm_opp_remove_all_dynamic - dev_pm_opp_set_bw - dev_pm_opp_set_clkname - dev_pm_opp_set_rate - dev_pm_opp_set_regulators - dev_pm_opp_set_sharing_cpus - dev_pm_opp_set_supported_hw - dev_pm_opp_unregister_notifier - dev_pm_qos_add_notifier - dev_pm_qos_add_request - dev_pm_qos_expose_latency_tolerance - dev_pm_qos_hide_latency_tolerance - dev_pm_qos_read_value - dev_pm_qos_remove_notifier - dev_pm_qos_remove_request - dev_pm_qos_update_request - dev_pm_qos_update_user_latency_tolerance - dev_pm_set_dedicated_wake_irq - dev_printk - dev_printk_emit - dev_queue_xmit - dev_set_mtu - dev_set_name - dev_uc_sync_multiple - dev_uc_unsync - devfreq_add_device - devfreq_add_governor - devfreq_cooling_unregister - devfreq_get_devfreq_by_phandle - devfreq_monitor_resume - devfreq_monitor_start - devfreq_monitor_stop - devfreq_monitor_suspend - devfreq_recommended_opp - devfreq_register_opp_notifier - devfreq_remove_device - devfreq_remove_governor - devfreq_resume_device - devfreq_suspend_device - devfreq_unregister_opp_notifier - devfreq_update_interval - device_add - device_add_disk - device_add_groups - device_attach - device_bind_driver - device_create - device_create_bin_file - device_create_file - device_create_with_groups - device_del - device_destroy - device_find_child - device_for_each_child - device_get_child_node_count - device_get_dma_attr - device_get_mac_address - device_get_match_data - device_get_named_child_node - device_get_next_child_node - device_init_wakeup - device_initialize - device_link_add - device_link_del - device_match_fwnode - device_match_name - device_match_of_node - device_property_present - device_property_read_string - device_property_read_string_array - device_property_read_u16_array - device_property_read_u32_array - device_property_read_u8_array - device_register - device_release_driver - device_remove_bin_file - device_remove_file - device_remove_file_self - device_remove_groups - device_set_wakeup_capable - device_set_wakeup_enable - device_show_bool - device_show_int - device_store_bool - device_store_int - device_unregister - device_wakeup_disable - device_wakeup_enable - devm_add_action - devm_backlight_device_register - devm_backlight_device_unregister - devm_blk_ksm_init - devm_clk_bulk_get - devm_clk_bulk_get_all - devm_clk_bulk_get_optional - devm_clk_get - devm_clk_get_optional - devm_clk_hw_register - devm_clk_hw_register_clkdev - devm_clk_put - devm_clk_register - devm_devfreq_add_device - devm_devfreq_register_notifier - devm_devfreq_unregister_notifier - devm_device_add_group - devm_device_add_groups - devm_device_remove_group - devm_drm_panel_bridge_add_typed - devm_extcon_dev_allocate - devm_extcon_dev_register - devm_extcon_dev_unregister - devm_extcon_register_notifier - devm_free_irq - devm_free_percpu - devm_gen_pool_create - devm_get_clk_from_child - devm_gpio_free - devm_gpio_request - devm_gpio_request_one - devm_gpiochip_add_data_with_key - devm_gpiod_get - devm_gpiod_get_array - devm_gpiod_get_index - devm_gpiod_get_optional - devm_gpiod_put_array - devm_hwrng_register - devm_hwspin_lock_register - devm_i2c_new_dummy_device - devm_iio_channel_get - devm_iio_device_alloc - devm_input_allocate_device - devm_ioremap - devm_ioremap_resource - devm_ioremap_wc - devm_iounmap - devm_kasprintf - devm_kfree - devm_kmalloc - devm_kmemdup - devm_kstrdup - devm_kstrdup_const - devm_kvasprintf - devm_led_classdev_register_ext - devm_mbox_controller_register - devm_memremap - devm_mfd_add_devices - devm_nvmem_cell_get - devm_nvmem_device_get - devm_nvmem_register - devm_of_clk_add_hw_provider - devm_of_icc_get - devm_of_iomap - devm_of_platform_populate - devm_of_pwm_get - devm_pci_alloc_host_bridge - devm_phy_create - devm_phy_get - devm_phy_put - devm_pinctrl_get - devm_pinctrl_put - devm_pinctrl_register - devm_pinctrl_register_and_init - devm_platform_get_and_ioremap_resource - devm_platform_ioremap_resource - devm_platform_ioremap_resource_byname - devm_power_supply_register - devm_pwm_put - devm_regmap_add_irq_chip - devm_regmap_del_irq_chip - devm_regmap_field_alloc - devm_regulator_bulk_get - devm_regulator_get - devm_regulator_get_exclusive - devm_regulator_get_optional - devm_regulator_put - devm_regulator_register - devm_regulator_register_notifier - devm_request_any_context_irq - devm_request_threaded_irq - devm_reset_control_array_get - devm_reset_controller_register - devm_rtc_allocate_device - devm_rtc_device_register - devm_snd_dmaengine_pcm_register - devm_snd_soc_register_card - devm_snd_soc_register_component - devm_spi_register_controller - devm_thermal_of_cooling_device_register - devm_thermal_zone_of_sensor_register - devm_thermal_zone_of_sensor_unregister - devm_usb_get_phy - devm_usb_get_phy_by_node - devm_usb_get_phy_by_phandle - devm_watchdog_register_device - devres_add - devres_alloc_node - devres_free - devres_release - disable_irq - disable_irq_nosync - disable_percpu_irq - disk_end_io_acct - disk_start_io_acct - divider_get_val - divider_recalc_rate - divider_ro_round_rate_parent - divider_round_rate_parent - dma_alloc_attrs - dma_async_device_register - dma_async_device_unregister - dma_async_tx_descriptor_init - dma_buf_attach - dma_buf_begin_cpu_access - dma_buf_begin_cpu_access_partial - dma_buf_detach - dma_buf_dynamic_attach - dma_buf_end_cpu_access - dma_buf_end_cpu_access_partial - dma_buf_export - dma_buf_fd - dma_buf_get - dma_buf_get_flags - dma_buf_map_attachment - dma_buf_mmap - dma_buf_move_notify - dma_buf_pin - dma_buf_put - dma_buf_unmap_attachment - dma_buf_unpin - dma_buf_vmap - dma_buf_vunmap - dma_contiguous_default_area - dma_fence_add_callback - dma_fence_array_create - dma_fence_array_ops - dma_fence_context_alloc - dma_fence_default_wait - dma_fence_enable_sw_signaling - dma_fence_free - dma_fence_get_status - dma_fence_get_stub - dma_fence_init - dma_fence_match_context - dma_fence_release - dma_fence_remove_callback - dma_fence_signal - dma_fence_signal_locked - dma_fence_wait_any_timeout - dma_fence_wait_timeout - dma_free_attrs - dma_get_merge_boundary - dma_get_required_mask - dma_get_sgtable_attrs - dma_get_slave_caps - dma_get_slave_channel - dma_heap_add - dma_heap_buffer_alloc - dma_heap_buffer_free - dma_heap_find - dma_heap_get_dev - dma_heap_get_drvdata - dma_heap_get_name - dma_heap_put - dma_map_page_attrs - dma_map_resource - dma_map_sg_attrs - dma_max_mapping_size - dma_mmap_attrs - dma_pool_alloc - dma_pool_create - dma_pool_destroy - dma_pool_free - dma_release_channel - dma_request_chan - dma_resv_add_excl_fence - dma_resv_add_shared_fence - dma_resv_fini - dma_resv_get_fences_rcu - dma_resv_init - dma_resv_reserve_shared - dma_resv_test_signaled_rcu - dma_resv_wait_timeout_rcu - dma_set_coherent_mask - dma_set_mask - dma_sync_sg_for_cpu - dma_sync_sg_for_device - dma_sync_single_for_cpu - dma_sync_single_for_device - dma_unmap_page_attrs - dma_unmap_resource - dma_unmap_sg_attrs - dmabuf_page_pool_alloc - dmabuf_page_pool_create - dmabuf_page_pool_destroy - dmabuf_page_pool_free - dmaengine_unmap_put - dmam_alloc_attrs - dmam_free_coherent - dmam_pool_create - do_SAK - do_exit - do_trace_rcu_torture_read - do_wait_intr - do_wait_intr_irq - down - down_interruptible - down_read - down_read_killable - down_read_trylock - down_timeout - down_trylock - down_write - downgrade_write - dput - drain_workqueue - driver_attach - driver_create_file - driver_find_device - driver_register - driver_remove_file - driver_unregister - drm_add_edid_modes - drm_add_modes_noedid - drm_atomic_add_affected_connectors - drm_atomic_add_affected_planes - drm_atomic_commit - drm_atomic_get_connector_state - drm_atomic_get_crtc_state - drm_atomic_get_new_connector_for_encoder - drm_atomic_get_plane_state - drm_atomic_get_private_obj_state - drm_atomic_helper_bridge_destroy_state - drm_atomic_helper_bridge_duplicate_state - drm_atomic_helper_bridge_reset - drm_atomic_helper_check - drm_atomic_helper_check_modeset - drm_atomic_helper_check_plane_state - drm_atomic_helper_check_planes - drm_atomic_helper_cleanup_planes - drm_atomic_helper_commit - drm_atomic_helper_commit_cleanup_done - drm_atomic_helper_commit_duplicated_state - drm_atomic_helper_commit_hw_done - drm_atomic_helper_commit_modeset_disables - drm_atomic_helper_commit_modeset_enables - drm_atomic_helper_commit_planes - drm_atomic_helper_commit_tail - drm_atomic_helper_connector_destroy_state - drm_atomic_helper_connector_duplicate_state - drm_atomic_helper_connector_reset - drm_atomic_helper_crtc_destroy_state - drm_atomic_helper_crtc_duplicate_state - drm_atomic_helper_crtc_reset - drm_atomic_helper_damage_merged - drm_atomic_helper_dirtyfb - drm_atomic_helper_disable_plane - drm_atomic_helper_disable_planes_on_crtc - drm_atomic_helper_duplicate_state - drm_atomic_helper_fake_vblank - drm_atomic_helper_page_flip - drm_atomic_helper_plane_destroy_state - drm_atomic_helper_plane_duplicate_state - drm_atomic_helper_plane_reset - drm_atomic_helper_prepare_planes - drm_atomic_helper_set_config - drm_atomic_helper_setup_commit - drm_atomic_helper_shutdown - drm_atomic_helper_swap_state - drm_atomic_helper_update_legacy_modeset_state - drm_atomic_helper_update_plane - drm_atomic_helper_wait_for_dependencies - drm_atomic_helper_wait_for_fences - drm_atomic_helper_wait_for_flip_done - drm_atomic_helper_wait_for_vblanks - drm_atomic_normalize_zpos - drm_atomic_private_obj_fini - drm_atomic_private_obj_init - drm_atomic_set_crtc_for_connector - drm_atomic_set_crtc_for_plane - drm_atomic_set_fb_for_plane - drm_atomic_set_fence_for_plane - drm_atomic_set_mode_for_crtc - drm_atomic_state_alloc - drm_atomic_state_clear - drm_atomic_state_default_clear - drm_atomic_state_default_release - drm_atomic_state_init - drm_bridge_add - drm_bridge_attach - drm_bridge_chain_disable - drm_bridge_chain_enable - drm_bridge_chain_mode_set - drm_bridge_chain_post_disable - drm_bridge_chain_pre_enable - drm_bridge_hpd_notify - drm_bridge_remove - drm_client_init - drm_client_modeset_commit_locked - drm_client_register - drm_compat_ioctl - drm_connector_attach_dp_subconnector_property - drm_connector_attach_edid_property - drm_connector_attach_encoder - drm_connector_cleanup - drm_connector_has_possible_encoder - drm_connector_init - drm_connector_init_with_ddc - drm_connector_list_iter_begin - drm_connector_list_iter_end - drm_connector_list_iter_next - drm_connector_register - drm_connector_set_tile_property - drm_connector_unregister - drm_connector_update_edid_property - drm_crtc_arm_vblank_event - drm_crtc_cleanup - drm_crtc_enable_color_mgmt - drm_crtc_from_index - drm_crtc_handle_vblank - drm_crtc_helper_set_config - drm_crtc_helper_set_mode - drm_crtc_init - drm_crtc_init_with_planes - drm_crtc_send_vblank_event - drm_crtc_set_max_vblank_count - drm_crtc_vblank_count - drm_crtc_vblank_count_and_time - drm_crtc_vblank_get - drm_crtc_vblank_helper_get_vblank_timestamp - drm_crtc_vblank_off - drm_crtc_vblank_on - drm_crtc_vblank_put - drm_crtc_vblank_reset - drm_crtc_wait_one_vblank - drm_cvt_mode - drm_debugfs_create_files - drm_detect_hdmi_monitor - drm_detect_monitor_audio - drm_dev_alloc - drm_dev_dbg - drm_dev_enter - drm_dev_exit - drm_dev_get - drm_dev_printk - drm_dev_put - drm_dev_register - drm_dev_set_unique - drm_dev_unplug - drm_dev_unregister - drm_display_mode_to_videomode - drm_do_get_edid - drm_dp_atomic_find_vcpi_slots - drm_dp_atomic_release_vcpi_slots - drm_dp_aux_init - drm_dp_aux_register - drm_dp_aux_unregister - drm_dp_bw_code_to_link_rate - drm_dp_calc_pbn_mode - drm_dp_channel_eq_ok - drm_dp_check_act_status - drm_dp_clock_recovery_ok - drm_dp_dpcd_read - drm_dp_dpcd_read_link_status - drm_dp_dpcd_write - drm_dp_find_vcpi_slots - drm_dp_get_adjust_request_pre_emphasis - drm_dp_get_adjust_request_voltage - drm_dp_get_edid_quirks - drm_dp_link_rate_to_bw_code - drm_dp_link_train_channel_eq_delay - drm_dp_link_train_clock_recovery_delay - drm_dp_mst_allocate_vcpi - drm_dp_mst_deallocate_vcpi - drm_dp_mst_detect_port - drm_dp_mst_get_edid - drm_dp_mst_get_port_malloc - drm_dp_mst_hpd_irq - drm_dp_mst_put_port_malloc - drm_dp_mst_reset_vcpi_slots - drm_dp_mst_topology_mgr_destroy - drm_dp_mst_topology_mgr_init - drm_dp_mst_topology_mgr_set_mst - drm_dp_send_power_updown_phy - drm_dp_set_subconnector_property - drm_dp_update_payload_part1 - drm_dp_update_payload_part2 - drm_edid_block_valid - drm_edid_duplicate - drm_edid_get_monitor_name - drm_edid_header_is_valid - drm_edid_is_valid - drm_edid_to_sad - drm_edid_to_speaker_allocation - drm_encoder_cleanup - drm_encoder_init - drm_event_cancel_free - drm_event_reserve_init - drm_event_reserve_init_locked - drm_fb_cma_get_gem_obj - drm_flip_work_cleanup - drm_flip_work_commit - drm_flip_work_init - drm_flip_work_queue - drm_format_info - drm_framebuffer_cleanup - drm_framebuffer_init - drm_framebuffer_lookup - drm_framebuffer_remove - drm_framebuffer_unregister_private - drm_gem_cma_dumb_create_internal - drm_gem_cma_free_object - drm_gem_cma_mmap - drm_gem_cma_prime_get_sg_table - drm_gem_cma_prime_import_sg_table - drm_gem_cma_prime_mmap - drm_gem_cma_prime_vmap - drm_gem_cma_prime_vunmap - drm_gem_cma_vm_ops - drm_gem_create_mmap_offset - drm_gem_dmabuf_mmap - drm_gem_dmabuf_release - drm_gem_dmabuf_vmap - drm_gem_dmabuf_vunmap - drm_gem_fb_create - drm_gem_fb_create_handle - drm_gem_fb_destroy - drm_gem_fb_get_obj - drm_gem_fb_prepare_fb - drm_gem_free_mmap_offset - drm_gem_get_pages - drm_gem_handle_create - drm_gem_lock_reservations - drm_gem_map_attach - drm_gem_map_detach - drm_gem_map_dma_buf - drm_gem_mmap - drm_gem_mmap_obj - drm_gem_object_free - drm_gem_object_init - drm_gem_object_lookup - drm_gem_object_put_locked - drm_gem_object_release - drm_gem_prime_export - drm_gem_prime_fd_to_handle - drm_gem_prime_handle_to_fd - drm_gem_prime_import - drm_gem_prime_import_dev - drm_gem_prime_mmap - drm_gem_private_object_init - drm_gem_put_pages - drm_gem_shmem_create - drm_gem_shmem_free_object - drm_gem_shmem_get_sg_table - drm_gem_shmem_mmap - drm_gem_shmem_pin - drm_gem_shmem_print_info - drm_gem_shmem_unpin - drm_gem_shmem_vmap - drm_gem_shmem_vunmap - drm_gem_unlock_reservations - drm_gem_unmap_dma_buf - drm_gem_vm_close - drm_gem_vm_open - drm_get_connector_status_name - drm_get_edid - drm_get_format_info - drm_get_format_name - drm_handle_vblank - drm_hdmi_avi_infoframe_from_display_mode - drm_helper_connector_dpms - drm_helper_disable_unused_functions - drm_helper_force_disable_all - drm_helper_hpd_irq_event - drm_helper_mode_fill_fb_struct - drm_helper_probe_single_connector_modes - drm_helper_resume_force_mode - drm_ioctl - drm_irq_install - drm_irq_uninstall - drm_is_current_master - drm_kms_helper_hotplug_event - drm_kms_helper_is_poll_worker - drm_kms_helper_poll_disable - drm_kms_helper_poll_enable - drm_kms_helper_poll_fini - drm_kms_helper_poll_init - drm_match_cea_mode - drm_mm_init - drm_mm_insert_node_in_range - drm_mm_print - drm_mm_remove_node - drm_mm_takedown - drm_mode_config_cleanup - drm_mode_config_helper_resume - drm_mode_config_helper_suspend - drm_mode_config_reset - drm_mode_convert_to_umode - drm_mode_convert_umode - drm_mode_copy - drm_mode_create - drm_mode_create_dp_colorspace_property - drm_mode_create_scaling_mode_property - drm_mode_create_tile_group - drm_mode_crtc_set_gamma_size - drm_mode_debug_printmodeline - drm_mode_destroy - drm_mode_duplicate - drm_mode_equal - drm_mode_equal_no_clocks - drm_mode_get_tile_group - drm_mode_is_420_only - drm_mode_match - drm_mode_object_find - drm_mode_object_get - drm_mode_object_put - drm_mode_probed_add - drm_mode_set_crtcinfo - drm_mode_set_name - drm_mode_sort - drm_mode_vrefresh - drm_modeset_acquire_fini - drm_modeset_acquire_init - drm_modeset_backoff - drm_modeset_drop_locks - drm_modeset_lock - drm_modeset_lock_all - drm_modeset_lock_all_ctx - drm_modeset_lock_init - drm_modeset_unlock - drm_modeset_unlock_all - drm_need_swiotlb - drm_object_attach_property - drm_object_property_set_value - drm_of_component_match_add - drm_of_find_possible_crtcs - drm_open - drm_panel_add - drm_panel_disable - drm_panel_enable - drm_panel_get_modes - drm_panel_init - drm_panel_prepare - drm_panel_remove - drm_panel_unprepare - drm_plane_cleanup - drm_plane_create_alpha_property - drm_plane_create_blend_mode_property - drm_plane_create_rotation_property - drm_plane_create_zpos_property - drm_plane_enable_fb_damage_clips - drm_poll - drm_prime_gem_destroy - drm_prime_pages_to_sg - drm_prime_sg_to_page_addr_arrays - drm_printf - drm_property_blob_get - drm_property_blob_put - drm_property_create - drm_property_create_bitmask - drm_property_create_blob - drm_property_create_bool - drm_property_create_enum - drm_property_create_range - drm_property_create_signed_range - drm_property_lookup_blob - drm_property_replace_blob - drm_puts - drm_read - drm_rect_calc_hscale - drm_rect_calc_vscale - drm_rect_clip_scaled - drm_rect_intersect - drm_release - drm_rotation_simplify - drm_send_event - drm_send_event_locked - drm_set_preferred_mode - drm_simple_encoder_init - drm_state_dump - drm_syncobj_add_point - drm_syncobj_create - drm_syncobj_find - drm_syncobj_find_fence - drm_syncobj_free - drm_syncobj_get_fd - drm_syncobj_get_handle - drm_syncobj_replace_fence - drm_sysfs_hotplug_event - drm_universal_plane_init - drm_vblank_init - drm_vma_node_allow - drm_vma_node_is_allowed - drm_vma_node_revoke - drm_wait_one_vblank - drm_writeback_connector_init - drm_writeback_queue_job - drm_writeback_signal_completion - drmm_kmalloc - drmm_mode_config_init - dst_release - dump_align - dump_backtrace - dump_emit - dump_stack - dup_iter - dw_handle_msi_irq - dw_pcie_host_init - dw_pcie_msi_init - dw_pcie_own_conf_map_bus - dw_pcie_read - dw_pcie_setup_rc - dw_pcie_write - dwc3_send_gadget_ep_cmd - dwc3_stop_active_transfer - edac_device_add_device - edac_device_alloc_ctl_info - edac_device_alloc_index - edac_device_del_device - edac_device_free_ctl_info - edac_device_handle_ce_count - edac_device_handle_ue_count - efi - efi_tpm_final_log_size - elevator_alloc - elv_bio_merge_ok - elv_rb_add - elv_rb_del - elv_rb_find - elv_rb_former_request - elv_rb_latter_request - elv_register - elv_rqhash_add - elv_rqhash_del - elv_unregister - emergency_restart - enable_irq - enable_percpu_irq - eth_commit_mac_addr_change - eth_mac_addr - eth_platform_get_mac_address - eth_prepare_mac_addr_change - eth_type_trans - eth_validate_addr - ether_setup - ethtool_op_get_link - ethtool_op_get_ts_info - ethtool_virtdev_set_link_ksettings - event_triggers_call - eventfd_ctx_fdget - eventfd_ctx_fileget - eventfd_ctx_put - eventfd_ctx_remove_wait_queue - eventfd_signal - extcon_find_edev_by_node - extcon_get_edev_by_phandle - extcon_get_edev_name - extcon_get_extcon_dev - extcon_get_property - extcon_get_state - extcon_register_notifier - extcon_set_property - extcon_set_property_capability - extcon_set_state_sync - extcon_unregister_notifier - fasync_helper - fd_install - fget - file_path - file_ra_state_init - filp_close - filp_open_block - find_get_pid - find_last_bit - find_next_bit - find_next_zero_bit - find_snd_usb_substream - find_task_by_vpid - find_vma - find_vpid - finish_wait - firmware_request_nowarn - fixed_phy_register - fixed_phy_unregister - fixed_size_llseek - flow_keys_basic_dissector - flush_dcache_page - flush_delayed_work - flush_signals - flush_work - flush_workqueue - fput - frame_vector_create - frame_vector_destroy - frame_vector_to_pages - free_buffer_head - free_io_pgtable_ops - free_irq - free_netdev - free_pages - free_pages_exact - free_percpu - free_percpu_irq - freezing_slow_path - freq_qos_add_request - freq_qos_remove_request - freq_qos_update_request - freq_scale - fs_bio_set - fsync_bdev - ftrace_dump - full_name_hash - fwnode_find_reference - fwnode_get_name - fwnode_get_named_child_node - fwnode_get_next_child_node - fwnode_gpiod_get_index - fwnode_handle_get - fwnode_handle_put - fwnode_property_present - fwnode_property_read_string - fwnode_property_read_u32_array - fwnode_usb_role_switch_get - gcd - gen_pool_add_owner - gen_pool_alloc_algo_owner - gen_pool_avail - gen_pool_best_fit - gen_pool_create - gen_pool_destroy - gen_pool_dma_alloc_align - gen_pool_dma_zalloc_align - gen_pool_first_fit_align - gen_pool_first_fit_order_align - gen_pool_free_owner - gen_pool_has_addr - gen_pool_set_algo - gen_pool_size - gen_pool_virt_to_phys - generic_delete_inode - generic_device_group - generic_file_llseek - generic_file_read_iter - generic_handle_irq - generic_iommu_put_resv_regions - generic_mii_ioctl - generic_perform_write - generic_write_checks - genl_notify - genl_register_family - genl_unregister_family - genlmsg_put - genphy_read_status - genphy_resume - genphy_soft_reset - genphy_suspend - get_cpu_device - get_cpu_idle_time - get_cpu_idle_time_us - get_cpu_iowait_time_us - get_device - get_device_system_crosststamp - get_governor_parent_kobj - get_next_ino - get_option - get_options - get_pid_task - get_random_bytes - get_random_bytes_arch - get_random_u32 - get_random_u64 - get_sg_io_hdr - get_state_synchronize_rcu - get_task_exe_file - get_task_mm - get_task_pid - get_thermal_instance - get_tree_single - get_unmapped_area - get_unused_fd_flags - get_user_pages - get_user_pages_fast - get_user_pages_remote - get_vaddr_frames - get_zeroed_page - getboottime64 - gfp_zone - gic_nonsecure_priorities - glob_match - gnss_allocate_device - gnss_deregister_device - gnss_insert_raw - gnss_put_device - gnss_register_device - gov_attr_set_get - gov_attr_set_init - gov_attr_set_put - governor_sysfs_ops - gpio_free - gpio_free_array - gpio_request - gpio_request_one - gpio_to_desc - gpiochip_add_data_with_key - gpiochip_add_pin_range - gpiochip_find - gpiochip_generic_config - gpiochip_generic_free - gpiochip_generic_request - gpiochip_get_data - gpiochip_irqchip_add_key - gpiochip_line_is_valid - gpiochip_lock_as_irq - gpiochip_populate_parent_fwspec_fourcell - gpiochip_remove - gpiochip_set_nested_irqchip - gpiochip_unlock_as_irq - gpiod_cansleep - gpiod_count - gpiod_direction_input - gpiod_direction_output - gpiod_direction_output_raw - gpiod_get_optional - gpiod_get_raw_value - gpiod_get_raw_value_cansleep - gpiod_get_value - gpiod_get_value_cansleep - gpiod_set_consumer_name - gpiod_set_debounce - gpiod_set_raw_value - gpiod_set_raw_value_cansleep - gpiod_set_value - gpiod_set_value_cansleep - gpiod_to_chip - gpiod_to_irq - gro_cells_destroy - gro_cells_init - gro_cells_receive - gs_alloc_req - gs_free_req - gserial_alloc_line - gserial_connect - gserial_disconnect - gserial_free_line - gserial_resume - gserial_suspend - guid_gen - handle_bad_irq - handle_edge_irq - handle_fasteoi_ack_irq - handle_fasteoi_irq - handle_level_irq - handle_nested_irq - handle_simple_irq - handle_sysrq - hash_digest_size - hashlen_string - have_governor_per_policy - hci_alloc_dev - hci_free_dev - hci_recv_frame - hci_register_dev - hci_unregister_dev - hdmi_audio_infoframe_init - hdmi_audio_infoframe_pack - hdmi_avi_infoframe_init - hdmi_avi_infoframe_pack - hdmi_infoframe_pack - hex2bin - hex_dump_to_buffer - hex_to_bin - hid_hw_close - hid_hw_open - hid_hw_start - hid_hw_stop - hid_open_report - hid_report_raw_event - hid_unregister_driver - hmm_range_fault - hrtimer_active - hrtimer_cancel - hrtimer_forward - hrtimer_init - hrtimer_init_sleeper - hrtimer_sleeper_start_expires - hrtimer_start_range_ns - hrtimer_try_to_cancel - hvc_alloc - hvc_instantiate - hvc_kick - hvc_poll - hvc_remove - hwrng_register - hwrng_unregister - hwspin_lock_free - hwspin_lock_request_specific - hypervisor_kobj - i2c_adapter_type - i2c_add_adapter - i2c_add_numbered_adapter - i2c_bit_add_bus - i2c_bit_add_numbered_bus - i2c_bus_type - i2c_client_type - i2c_del_adapter - i2c_del_driver - i2c_for_each_dev - i2c_generic_scl_recovery - i2c_get_adapter - i2c_get_device_id - i2c_get_dma_safe_msg_buf - i2c_match_id - i2c_new_ancillary_device - i2c_new_client_device - i2c_new_dummy_device - i2c_new_scanned_device - i2c_parse_fw_timings - i2c_put_adapter - i2c_put_dma_safe_msg_buf - i2c_recover_bus - i2c_register_driver - i2c_smbus_read_byte - i2c_smbus_read_byte_data - i2c_smbus_read_i2c_block_data - i2c_smbus_read_word_data - i2c_smbus_write_byte - i2c_smbus_write_byte_data - i2c_smbus_write_i2c_block_data - i2c_smbus_write_word_data - i2c_smbus_xfer - i2c_transfer - i2c_transfer_buffer_flags - i2c_unregister_device - i2c_verify_adapter - i2c_verify_client - icc_disable - icc_enable - icc_get - icc_link_create - icc_node_add - icc_node_create - icc_node_del - icc_node_destroy - icc_nodes_remove - icc_provider_add - icc_provider_del - icc_put - icc_set_bw - icc_set_tag - icc_std_aggregate - icc_sync_state - ida_alloc_range - ida_destroy - ida_free - idr_alloc - idr_alloc_cyclic - idr_alloc_u32 - idr_destroy - idr_find - idr_for_each - idr_get_next - idr_preload - idr_remove - idr_replace - ieee802154_alloc_hw - ieee802154_free_hw - ieee802154_register_hw - ieee802154_rx_irqsafe - ieee802154_unregister_hw - ieee802154_wake_queue - ieee802154_xmit_complete - iio_buffer_init - iio_buffer_put - iio_channel_get - iio_channel_get_all - iio_channel_release - iio_device_alloc - iio_device_attach_buffer - iio_device_free - iio_device_unregister - iio_push_to_buffers - iio_read_channel_processed - iio_read_channel_raw - import_iovec - in4_pton - in6_dev_finish_destroy - in6_pton - in_aton - in_egroup_p - inc_zone_page_state - inet_proto_csum_replace4 - init_dummy_netdev - init_iova_domain - init_net - init_on_free - init_pid_ns - init_pseudo - init_srcu_struct - init_task - init_timer_key - init_uts_ns - init_wait_entry - input_alloc_absinfo - input_allocate_device - input_close_device - input_event - input_ff_create - input_ff_create_memless - input_ff_destroy - input_free_device - input_mt_assign_slots - input_mt_destroy_slots - input_mt_drop_unused - input_mt_init_slots - input_mt_report_finger_count - input_mt_report_pointer_emulation - input_mt_report_slot_state - input_mt_sync_frame - input_open_device - input_register_device - input_register_handle - input_register_handler - input_set_abs_params - input_set_capability - input_set_timestamp - input_unregister_device - input_unregister_handle - input_unregister_handler - int_pow - int_sqrt - interval_tree_insert - interval_tree_iter_first - interval_tree_iter_next - interval_tree_remove - invalidate_bdev - invalidate_mapping_pages - io_schedule_timeout - iomem_resource - iommu_alloc_resv_region - iommu_attach_device - iommu_attach_group - iommu_aux_attach_device - iommu_aux_detach_device - iommu_aux_get_pasid - iommu_detach_device - iommu_detach_group - iommu_dev_enable_feature - iommu_dev_feature_enabled - iommu_device_register - iommu_device_sysfs_add - iommu_device_sysfs_remove - iommu_device_unlink - iommu_device_unregister - iommu_dma_enable_best_fit_algo - iommu_dma_get_resv_regions - iommu_dma_reserve_iova - iommu_domain_alloc - iommu_domain_free - iommu_domain_get_attr - iommu_domain_set_attr - iommu_fwspec_add_ids - iommu_fwspec_free - iommu_get_dma_cookie - iommu_get_domain_for_dev - iommu_get_msi_cookie - iommu_group_alloc - iommu_group_for_each_dev - iommu_group_get - iommu_group_get_iommudata - iommu_group_put - iommu_group_ref_get - iommu_group_set_iommudata - iommu_group_set_name - iommu_iova_to_phys - iommu_map - iommu_map_sg - iommu_present - iommu_put_dma_cookie - iommu_register_device_fault_handler - iommu_report_device_fault - iommu_set_fault_handler - iommu_unmap - iommu_unregister_device_fault_handler - iounmap - iov_iter_bvec - iov_iter_kvec - ip_compute_csum - ip_send_check - ipi_desc_get - iput - ipv6_ext_hdr - ipv6_find_hdr - ipv6_skip_exthdr - irq_chip_ack_parent - irq_chip_disable_parent - irq_chip_enable_parent - irq_chip_eoi_parent - irq_chip_get_parent_state - irq_chip_mask_parent - irq_chip_retrigger_hierarchy - irq_chip_set_affinity_parent - irq_chip_set_parent_state - irq_chip_set_type_parent - irq_chip_set_vcpu_affinity_parent - irq_chip_set_wake_parent - irq_chip_unmask_parent - irq_create_fwspec_mapping - irq_create_mapping_affinity - irq_create_of_mapping - irq_dispose_mapping - irq_domain_add_simple - irq_domain_alloc_irqs_parent - irq_domain_create_hierarchy - irq_domain_free_irqs_common - irq_domain_free_irqs_parent - irq_domain_get_irq_data - irq_domain_remove - irq_domain_set_hwirq_and_chip - irq_domain_set_info - irq_domain_simple_ops - irq_domain_update_bus_token - irq_domain_xlate_onecell - irq_domain_xlate_onetwocell - irq_domain_xlate_twocell - irq_find_mapping - irq_find_matching_fwspec - irq_get_irq_data - irq_get_irqchip_state - irq_modify_status - irq_of_parse_and_map - irq_set_affinity_hint - irq_set_affinity_notifier - irq_set_chained_handler_and_data - irq_set_chip - irq_set_chip_and_handler_name - irq_set_chip_data - irq_set_handler_data - irq_set_irq_type - irq_set_irq_wake - irq_set_irqchip_state - irq_set_parent - irq_to_desc - irq_work_queue - irq_work_queue_on - irq_work_sync - is_dma_buf_file - is_vmalloc_addr - iwe_stream_add_event - iwe_stream_add_point - iwe_stream_add_value - jiffies - jiffies64_to_msecs - jiffies_64_to_clock_t - jiffies_to_msecs - jiffies_to_usecs - kasan_flag_enabled - kasprintf - kern_mount - kern_path - kern_unmount - kernel_bind - kernel_connect - kernel_cpustat - kernel_getsockname - kernel_kobj - kernel_power_off - kernel_recvmsg - kernel_restart - kernel_sendmsg - kernel_sigaction - kernfs_find_and_get_ns - kernfs_notify - kernfs_path_from_node - kernfs_put - kfree - kfree_const - kfree_sensitive - kfree_skb - kick_all_cpus_sync - kill_anon_super - kill_fasync - kill_litter_super - kimage_vaddr - kimage_voffset - kiocb_set_cancel_fn - kmalloc_caches - kmalloc_order - kmalloc_order_trace - kmem_cache_alloc - kmem_cache_alloc_trace - kmem_cache_create - kmem_cache_create_usercopy - kmem_cache_destroy - kmem_cache_free - kmemdup - kmemdup_nul - kmsg_dump_get_line - kmsg_dump_rewind - kobj_sysfs_ops - kobject_add - kobject_create_and_add - kobject_del - kobject_get - kobject_init - kobject_init_and_add - kobject_put - kobject_set_name - kobject_uevent - kobject_uevent_env - krealloc - kset_create_and_add - kset_unregister - ksize - ksoftirqd - kstat - kstat_irqs_cpu - kstat_irqs_usr - kstrdup - kstrdup_const - kstrdup_quotable_cmdline - kstrndup - kstrtobool - kstrtobool_from_user - kstrtoint - kstrtoint_from_user - kstrtol_from_user - kstrtoll - kstrtos16 - kstrtos8 - kstrtos8_from_user - kstrtou16 - kstrtou16_from_user - kstrtou8 - kstrtou8_from_user - kstrtouint - kstrtouint_from_user - kstrtoul_from_user - kstrtoull - kstrtoull_from_user - ksys_sync_helper - kthread_bind - kthread_bind_mask - kthread_blkcg - kthread_cancel_delayed_work_sync - kthread_cancel_work_sync - kthread_create_on_node - kthread_create_worker - kthread_delayed_work_timer_fn - kthread_destroy_worker - kthread_flush_work - kthread_flush_worker - kthread_mod_delayed_work - kthread_park - kthread_parkme - kthread_queue_delayed_work - kthread_queue_work - kthread_should_park - kthread_should_stop - kthread_stop - kthread_unpark - kthread_unuse_mm - kthread_use_mm - kthread_worker_fn - ktime_add_safe - ktime_get - ktime_get_coarse_with_offset - ktime_get_mono_fast_ns - ktime_get_raw - ktime_get_raw_ts64 - ktime_get_real_seconds - ktime_get_real_ts64 - ktime_get_seconds - ktime_get_ts64 - ktime_get_with_offset - kvasprintf - kvfree - kvfree_call_rcu - kvmalloc_node - led_classdev_flash_register_ext - led_classdev_flash_unregister - led_classdev_register_ext - led_classdev_unregister - led_trigger_event - led_trigger_register_simple - led_trigger_unregister_simple - list_sort - llist_add_batch - llist_reverse_order - lock_sock_nested - log_abnormal_wakeup_reason - log_buf_addr_get - log_buf_len_get - log_threaded_irq_wakeup_reason - loops_per_jiffy - lzo1x_1_compress - lzo1x_decompress_safe - lzorle1x_1_compress - mac_pton - match_string - mbox_chan_received_data - mbox_chan_txdone - mbox_client_txdone - mbox_controller_register - mbox_controller_unregister - mbox_free_channel - mbox_request_channel - mbox_send_message - mdiobus_alloc_size - mdiobus_free - mdiobus_read - mdiobus_unregister - mdiobus_write - media_device_cleanup - media_device_init - media_device_unregister - media_entity_pads_init - memblock_end_of_DRAM - memblock_free - memchr - memchr_inv - memcmp - memcpy - memdup_user - memdup_user_nul - memmove - memory_block_size_bytes - memory_read_from_buffer - memparse - mempool_alloc - mempool_alloc_slab - mempool_create - mempool_create_node - mempool_destroy - mempool_exit - mempool_free - mempool_free_slab - mempool_init - mempool_kfree - mempool_kmalloc - memremap - memset - memset64 - memstart_addr - memunmap - mfd_add_devices - mfd_remove_devices - migrate_swap - mii_check_media - mii_ethtool_get_link_ksettings - mii_ethtool_gset - mii_ethtool_set_link_ksettings - mii_link_ok - mii_nway_restart - mipi_dsi_attach - mipi_dsi_compression_mode - mipi_dsi_create_packet - mipi_dsi_dcs_read - mipi_dsi_dcs_set_column_address - mipi_dsi_dcs_set_display_brightness - mipi_dsi_dcs_set_page_address - mipi_dsi_dcs_set_tear_off - mipi_dsi_dcs_write_buffer - mipi_dsi_detach - mipi_dsi_device_register_full - mipi_dsi_device_unregister - mipi_dsi_driver_register_full - mipi_dsi_driver_unregister - mipi_dsi_host_register - mipi_dsi_host_unregister - mipi_dsi_packet_format_is_long - mipi_dsi_picture_parameter_set - misc_deregister - misc_register - mktime64 - mm_trace_rss_stat - mmc_add_host - mmc_alloc_host - mmc_app_cmd - mmc_calc_max_discard - mmc_can_erase - mmc_can_gpio_cd - mmc_can_secure_erase_trim - mmc_can_trim - mmc_cmdq_disable - mmc_cmdq_enable - mmc_cqe_post_req - mmc_cqe_recovery - mmc_cqe_request_done - mmc_cqe_start_req - mmc_detect_card_removed - mmc_detect_change - mmc_erase - mmc_erase_group_aligned - mmc_flush_cache - mmc_free_host - mmc_get_card - mmc_get_ext_csd - mmc_gpio_get_cd - mmc_gpio_get_ro - mmc_gpiod_request_cd - mmc_gpiod_request_cd_irq - mmc_gpiod_request_ro - mmc_hw_reset - mmc_of_parse - mmc_of_parse_voltage - mmc_put_card - mmc_register_driver - mmc_regulator_get_supply - mmc_regulator_set_ocr - mmc_regulator_set_vqmmc - mmc_release_host - mmc_remove_host - mmc_request_done - mmc_retune_pause - mmc_retune_release - mmc_retune_unpause - mmc_run_bkops - mmc_sanitize - mmc_send_status - mmc_send_tuning - mmc_set_data_timeout - mmc_start_request - mmc_switch - mmc_unregister_driver - mmc_wait_for_cmd - mmc_wait_for_req - mmput - mmu_interval_notifier_insert - mmu_interval_notifier_remove - mmu_interval_read_begin - mmu_notifier_synchronize - mod_delayed_work_on - mod_node_page_state - mod_timer - module_layout - module_put - msleep - msleep_interruptible - mutex_is_locked - mutex_lock - mutex_lock_interruptible - mutex_trylock - mutex_trylock_recursive - mutex_unlock - name_to_dev_t - names_cachep - napi_complete_done - napi_consume_skb - napi_disable - napi_gro_flush - napi_gro_receive - napi_schedule_prep - net_namespace_list - net_ratelimit - netdev_change_features - netdev_err - netdev_increment_features - netdev_info - netdev_lower_state_changed - netdev_master_upper_dev_link - netdev_notify_peers - netdev_pick_tx - netdev_rx_handler_register - netdev_rx_handler_unregister - netdev_state_change - netdev_update_features - netdev_upper_dev_link - netdev_upper_dev_unlink - netdev_warn - netif_carrier_off - netif_carrier_on - netif_device_attach - netif_device_detach - netif_napi_add - netif_receive_skb - netif_receive_skb_list - netif_rx - netif_rx_ni - netif_schedule_queue - netif_set_real_num_rx_queues - netif_set_real_num_tx_queues - netif_stacked_transfer_operstate - netif_tx_stop_all_queues - netif_tx_wake_queue - netlink_ack - netlink_broadcast - netlink_capable - netlink_has_listeners - netlink_kernel_release - netlink_register_notifier - netlink_unicast - netlink_unregister_notifier - new_inode - nf_conntrack_destroy - nla_append - nla_find - nla_memcpy - nla_put - nla_put_64bit - nla_put_nohdr - nla_reserve - nla_reserve_64bit - nla_strlcpy - no_llseek - no_seek_end_llseek - nonseekable_open - noop_llseek - nr_cpu_ids - nr_ipi_get - nr_irqs - ns_capable - ns_to_timespec64 - nsec_to_clock_t - nsecs_to_jiffies - nvdimm_bus_register - nvdimm_bus_unregister - nvdimm_pmem_region_create - nvmem_cell_get - nvmem_cell_put - nvmem_cell_read - nvmem_cell_read_u32 - nvmem_cell_write - nvmem_device_put - nvmem_device_read - nvmem_device_write - of_address_to_resource - of_alias_get_highest_id - of_alias_get_id - of_clk_add_hw_provider - of_clk_add_provider - of_clk_del_provider - of_clk_get - of_clk_get_by_name - of_clk_get_from_provider - of_clk_get_parent_count - of_clk_get_parent_name - of_clk_hw_onecell_get - of_clk_hw_simple_get - of_clk_set_defaults - of_clk_src_onecell_get - of_clk_src_simple_get - of_count_phandle_with_args - of_cpu_node_to_id - of_cpufreq_cooling_register - of_css - of_devfreq_cooling_register - of_devfreq_cooling_register_power - of_device_get_match_data - of_device_is_available - of_device_is_compatible - of_device_modalias - of_device_request_module - of_device_uevent_modalias - of_dma_configure_id - of_dma_controller_free - of_dma_controller_register - of_dma_is_coherent - of_drm_find_bridge - of_drm_find_panel - of_find_all_nodes - of_find_compatible_node - of_find_device_by_node - of_find_i2c_adapter_by_node - of_find_i2c_device_by_node - of_find_matching_node_and_match - of_find_mipi_dsi_host_by_node - of_find_node_by_name - of_find_node_by_phandle - of_find_node_by_type - of_find_node_opts_by_path - of_find_node_with_property - of_find_property - of_fwnode_ops - of_genpd_add_provider_onecell - of_genpd_add_provider_simple - of_genpd_del_provider - of_get_address - of_get_child_by_name - of_get_compatible_child - of_get_cpu_node - of_get_dma_window - of_get_named_gpio_flags - of_get_next_available_child - of_get_next_child - of_get_next_parent - of_get_parent - of_get_property - of_get_regulator_init_data - of_graph_get_endpoint_by_regs - of_graph_get_next_endpoint - of_graph_get_port_parent - of_graph_get_remote_endpoint - of_graph_get_remote_node - of_graph_get_remote_port - of_graph_get_remote_port_parent - of_graph_is_present - of_graph_parse_endpoint - of_hwspin_lock_get_id - of_i2c_get_board_info - of_icc_get - of_icc_xlate_onecell - of_iomap - of_irq_find_parent - of_irq_get - of_irq_get_byname - of_irq_parse_one - of_machine_is_compatible - of_match_device - of_match_node - of_modalias_node - of_n_addr_cells - of_n_size_cells - of_node_name_eq - of_nvmem_device_get - of_parse_phandle - of_parse_phandle_with_args - of_parse_phandle_with_fixed_args - of_phandle_iterator_init - of_phandle_iterator_next - of_phy_simple_xlate - of_platform_depopulate - of_platform_device_create - of_platform_device_destroy - of_platform_populate - of_prop_next_string - of_prop_next_u32 - of_property_count_elems_of_size - of_property_match_string - of_property_read_string - of_property_read_string_helper - of_property_read_u32_index - of_property_read_u64 - of_property_read_u64_index - of_property_read_variable_u16_array - of_property_read_variable_u32_array - of_property_read_variable_u64_array - of_property_read_variable_u8_array - of_pwm_xlate_with_flags - of_reserved_mem_device_init_by_idx - of_reserved_mem_device_release - of_reserved_mem_lookup - of_reset_control_array_get - of_root - of_thermal_get_ntrips - of_thermal_get_trip_points - of_thermal_is_trip_valid - of_translate_address - of_usb_get_phy_mode - of_usb_host_tpl_support - on_each_cpu - oops_in_progress - orderly_poweroff - overflowuid - page_endio - page_mapping - page_reporting_register - page_reporting_unregister - panic - panic_notifier_list - panic_timeout - param_array_ops - param_get_int - param_get_string - param_get_uint - param_get_ullong - param_ops_bint - param_ops_bool - param_ops_byte - param_ops_charp - param_ops_hexint - param_ops_int - param_ops_long - param_ops_short - param_ops_string - param_ops_uint - param_ops_ullong - param_ops_ulong - param_ops_ushort - param_set_bool - param_set_copystring - param_set_int - param_set_uint - part_end_io_acct - part_start_io_acct - passthru_features_check - path_put - pause_cpus - pci_alloc_irq_vectors_affinity - pci_assign_resource - pci_assign_unassigned_bus_resources - pci_bus_resource_n - pci_bus_type - pci_clear_master - pci_d3cold_disable - pci_dev_present - pci_dev_put - pci_device_group - pci_device_is_present - pci_disable_device - pci_disable_msi - pci_enable_atomic_ops_to_root - pci_enable_device - pci_enable_device_mem - pci_enable_msi - pci_enable_wake - pci_find_bus - pci_find_capability - pci_find_ext_capability - pci_find_next_capability - pci_free_irq - pci_free_irq_vectors - pci_generic_config_read - pci_generic_config_write - pci_get_device - pci_get_domain_bus_and_slot - pci_get_slot - pci_host_probe - pci_intx - pci_iomap - pci_iomap_range - pci_ioremap_bar - pci_irq_get_affinity - pci_irq_vector - pci_load_and_free_saved_state - pci_load_saved_state - pci_map_rom - pci_match_id - pci_msi_create_irq_domain - pci_msi_mask_irq - pci_msi_unmask_irq - pci_msix_vec_count - pci_read_config_byte - pci_read_config_dword - pci_read_config_word - pci_release_region - pci_release_regions - pci_release_resource - pci_release_selected_regions - pci_request_irq - pci_request_region - pci_request_regions - pci_request_selected_regions - pci_rescan_bus - pci_resize_resource - pci_restore_msi_state - pci_restore_state - pci_save_state - pci_select_bars - pci_set_master - pci_set_mwi - pci_set_power_state - pci_store_saved_state - pci_unmap_rom - pci_unregister_driver - pci_wake_from_d3 - pci_walk_bus - pci_write_config_byte - pci_write_config_dword - pci_write_config_word - pcibios_resource_to_bus - pcie_aspm_enabled - pcie_bandwidth_available - pcie_capability_read_word - pcie_capability_write_word - pcie_get_mps - pcie_get_speed_cap - pcim_enable_device - per_cpu_ptr_to_phys - percpu_down_write - percpu_ref_exit - percpu_ref_init - percpu_ref_is_zero - percpu_ref_kill_and_confirm - percpu_ref_switch_to_atomic_sync - percpu_ref_switch_to_percpu - percpu_up_write - perf_aux_output_begin - perf_aux_output_end - perf_aux_output_flag - perf_event_addr_filters_sync - perf_event_create_kernel_counter - perf_event_disable - perf_event_enable - perf_event_pause - perf_event_read_local - perf_event_read_value - perf_event_release_kernel - perf_event_update_userpage - perf_get_aux - perf_pmu_migrate_context - perf_pmu_register - perf_pmu_unregister - perf_trace_buf_alloc - perf_trace_run_bpf_submit - pfn_valid - phy_attached_info - phy_calibrate - phy_configure - phy_connect - phy_connect_direct - phy_disconnect - phy_do_ioctl_running - phy_drivers_register - phy_drivers_unregister - phy_ethtool_get_link_ksettings - phy_ethtool_nway_reset - phy_ethtool_set_link_ksettings - phy_ethtool_set_wol - phy_exit - phy_find_first - phy_get_pause - phy_init - phy_init_hw - phy_mii_ioctl - phy_pm_runtime_get_sync - phy_pm_runtime_put_sync - phy_power_off - phy_power_on - phy_print_status - phy_register_fixup_for_uid - phy_save_page - phy_set_mode_ext - phy_start - phy_stop - phy_unregister_fixup_for_uid - pick_highest_pushable_task - pid_nr_ns - pid_task - pin_get_name - pin_user_pages - pin_user_pages_fast - pin_user_pages_remote - pinconf_generic_dt_free_map - pinconf_generic_dt_node_to_map - pinctrl_add_gpio_range - pinctrl_dev_get_drvdata - pinctrl_enable - pinctrl_force_default - pinctrl_force_sleep - pinctrl_get - pinctrl_lookup_state - pinctrl_pm_select_default_state - pinctrl_pm_select_idle_state - pinctrl_pm_select_sleep_state - pinctrl_put - pinctrl_remove_gpio_range - pinctrl_select_default_state - pinctrl_select_state - pinctrl_utils_free_map - pipe_lock - pipe_unlock - pktgen_xfrm_outer_mode_output - platform_add_devices - platform_bus_type - platform_device_add - platform_device_add_data - platform_device_add_properties - platform_device_add_resources - platform_device_alloc - platform_device_del - platform_device_put - platform_device_register - platform_device_register_full - platform_device_unregister - platform_driver_unregister - platform_find_device_by_driver - platform_get_irq - platform_get_irq_byname - platform_get_irq_byname_optional - platform_get_irq_optional - platform_get_resource - platform_get_resource_byname - platform_irq_count - pm_clk_add - pm_clk_create - pm_clk_destroy - pm_clk_resume - pm_clk_suspend - pm_generic_resume - pm_generic_runtime_resume - pm_generic_runtime_suspend - pm_generic_suspend - pm_genpd_add_subdomain - pm_genpd_init - pm_genpd_remove - pm_genpd_remove_subdomain - pm_power_off - pm_relax - pm_runtime_allow - pm_runtime_autosuspend_expiration - pm_runtime_barrier - pm_runtime_enable - pm_runtime_forbid - pm_runtime_force_resume - pm_runtime_force_suspend - pm_runtime_get_if_active - pm_runtime_irq_safe - pm_runtime_no_callbacks - pm_runtime_set_autosuspend_delay - pm_stay_awake - pm_suspend_global_flags - pm_system_wakeup - pm_wakeup_dev_event - pm_wakeup_ws_event - policy_has_boost_freq - power_supply_changed - power_supply_get_by_name - power_supply_get_by_phandle_array - power_supply_get_drvdata - power_supply_get_property - power_supply_is_system_supplied - power_supply_put - power_supply_reg_notifier - power_supply_register - power_supply_set_property - power_supply_unreg_notifier - power_supply_unregister - prandom_bytes - prandom_u32 - preempt_schedule - preempt_schedule_notrace - prepare_to_wait - prepare_to_wait_event - print_hex_dump - printk - printk_deferred - printk_timed_ratelimit - proc_create - proc_create_data - proc_create_single_data - proc_dointvec - proc_dointvec_minmax - proc_dostring - proc_douintvec_minmax - proc_mkdir - proc_mkdir_data - proc_remove - proc_set_size - proc_set_user - proc_symlink - proto_register - proto_unregister - ps2_begin_command - ps2_cmd_aborted - ps2_command - ps2_drain - ps2_end_command - ps2_handle_ack - ps2_handle_response - ps2_init - ps2_sendbyte - ps2_sliced_command - pskb_expand_head - pstore_register - pstore_unregister - public_key_verify_signature - put_device - put_disk - put_iova_domain - put_pid - put_sg_io_hdr - put_tty_driver - put_unused_fd - put_vaddr_frames - pwm_apply_state - pwm_get_chip_data - pwm_set_chip_data - pwmchip_add - pwmchip_remove - qcom_smem_state_get - qcom_smem_state_register - qcom_smem_state_unregister - qcom_smem_state_update_bits - qdisc_reset - queue_delayed_work_on - queue_work_on - radix_tree_delete - radix_tree_insert - radix_tree_iter_delete - radix_tree_iter_resume - radix_tree_lookup - radix_tree_maybe_preload - radix_tree_next_chunk - radix_tree_tagged - rational_best_approximation - raw_notifier_call_chain - raw_notifier_chain_register - raw_notifier_chain_unregister - rb_erase - rb_first - rb_first_postorder - rb_insert_color - rb_last - rb_next - rb_next_postorder - rb_prev - rb_replace_node - rcu_barrier - rcu_barrier_tasks - rcu_barrier_tasks_trace - rcu_bind_current_to_nocb - rcu_cpu_stall_suppress - rcu_cpu_stall_suppress_at_boot - rcu_expedite_gp - rcu_force_quiescent_state - rcu_fwd_progress_check - rcu_get_gp_kthreads_prio - rcu_get_gp_seq - rcu_gp_is_expedited - rcu_gp_is_normal - rcu_gp_set_torture_wait - rcu_inkernel_boot_has_ended - rcu_is_watching - rcu_jiffies_till_stall_check - rcu_read_unlock_trace_special - rcu_unexpedite_gp - rcutorture_get_gp_data - rcuwait_wake_up - rdev_get_drvdata - rdev_get_id - reboot_mode - reciprocal_value - refcount_dec_and_lock - refcount_dec_and_mutex_lock - refcount_dec_not_one - refcount_warn_saturate - refresh_frequency_limits - regcache_cache_bypass - regcache_cache_only - regcache_drop_region - regcache_mark_dirty - regcache_sync - regcache_sync_region - register_blkdev - register_chrdev_region - register_console - register_die_notifier - register_filesystem - register_ftrace_export - register_inet6addr_notifier - register_inetaddr_notifier - register_kernel_break_hook - register_kprobe - register_kretprobe - register_memory_notifier - register_module_notifier - register_net_sysctl - register_netdev - register_netdevice - register_netdevice_notifier - register_netevent_notifier - register_oom_notifier - register_pernet_device - register_pernet_subsys - register_pm_notifier - register_reboot_notifier - register_restart_handler - register_shrinker - register_syscore_ops - register_sysctl - register_sysctl_table - register_virtio_device - register_virtio_driver - register_vmap_purge_notifier - regmap_add_irq_chip - regmap_async_complete - regmap_bulk_read - regmap_bulk_write - regmap_check_range_table - regmap_del_irq_chip - regmap_exit - regmap_field_read - regmap_field_update_bits_base - regmap_get_device - regmap_irq_get_domain - regmap_irq_get_virq - regmap_mmio_detach_clk - regmap_multi_reg_write - regmap_multi_reg_write_bypassed - regmap_raw_read - regmap_raw_write - regmap_raw_write_async - regmap_read - regmap_register_patch - regmap_update_bits_base - regmap_write - regulator_allow_bypass - regulator_bulk_disable - regulator_bulk_enable - regulator_bulk_get - regulator_count_voltages - regulator_disable - regulator_disable_deferred - regulator_disable_regmap - regulator_enable - regulator_enable_regmap - regulator_force_disable - regulator_get - regulator_get_current_limit - regulator_get_drvdata - regulator_get_mode - regulator_get_optional - regulator_get_voltage - regulator_get_voltage_rdev - regulator_get_voltage_sel_regmap - regulator_is_enabled - regulator_is_enabled_regmap - regulator_is_supported_voltage - regulator_list_voltage_linear - regulator_list_voltage_linear_range - regulator_list_voltage_table - regulator_map_voltage_ascend - regulator_map_voltage_linear - regulator_notifier_call_chain - regulator_put - regulator_register - regulator_register_notifier - regulator_set_current_limit - regulator_set_load - regulator_set_mode - regulator_set_voltage - regulator_set_voltage_sel_regmap - regulator_unregister - regulator_unregister_notifier - release_firmware - release_pages - release_sock - remap_pfn_range - remap_vmalloc_range - remove_cpu - remove_memory_subsection - remove_proc_entry - remove_wait_queue - report_iommu_fault - request_any_context_irq - request_firmware - request_firmware_direct - request_firmware_into_buf - request_firmware_nowait - request_threaded_irq - resched_curr - reservation_ww_class - reset_control_assert - reset_control_deassert - reset_control_put - reset_control_reset - resume_cpus - return_address - revalidate_disk_size - rfkill_alloc - rfkill_destroy - rfkill_find_type - rfkill_init_sw_state - rfkill_register - rfkill_set_sw_state - rfkill_unregister - rhashtable_destroy - rhashtable_init - rhashtable_insert_slow - rht_bucket_nested - rht_bucket_nested_insert - rndis_deregister - rndis_free_response - rndis_get_next_response - rndis_msg_parser - rndis_register - rndis_set_host_mac - rndis_set_param_dev - rndis_set_param_medium - rndis_set_param_vendor - rndis_signal_connect - rndis_uninit - root_task_group - round_jiffies_relative - round_jiffies_up - rpmsg_get_signals - rpmsg_poll - rpmsg_register_device - rpmsg_send - rpmsg_set_signals - rpmsg_trysend - rpmsg_unregister_device - rproc_add - rproc_add_subdev - rproc_alloc - rproc_boot - rproc_coredump_add_custom_segment - rproc_coredump_add_segment - rproc_coredump_set_elf_info - rproc_coredump_using_sections - rproc_del - rproc_elf_get_boot_addr - rproc_free - rproc_get_by_child - rproc_get_by_phandle - rproc_put - rproc_remove_subdev - rproc_report_crash - rproc_shutdown - rps_needed - rt_mutex_lock - rt_mutex_trylock - rt_mutex_unlock - rtc_class_close - rtc_class_open - rtc_read_time - rtc_set_time - rtc_time64_to_tm - rtc_tm_to_time64 - rtc_update_irq - rtc_valid_tm - rtc_year_days - rtnl_is_locked - rtnl_link_register - rtnl_link_unregister - rtnl_lock - rtnl_register_module - rtnl_trylock - rtnl_unicast - rtnl_unlock - rtnl_unregister - runqueues - sb800_prefetch - sbitmap_queue_min_shallow_depth - sched_clock - sched_feat_keys - sched_feat_names - sched_set_fifo - sched_set_fifo_low - sched_set_normal - sched_setattr - sched_setattr_nocheck - sched_setscheduler - sched_setscheduler_nocheck - sched_show_task - sched_trace_cfs_rq_avg - sched_trace_cfs_rq_cpu - sched_trace_cfs_rq_path - sched_trace_rd_span - sched_trace_rq_avg_dl - sched_trace_rq_avg_irq - sched_trace_rq_avg_rt - sched_trace_rq_cpu - sched_uclamp_used - schedule - schedule_hrtimeout - schedule_timeout - schedule_timeout_interruptible - schedule_timeout_uninterruptible - scnprintf - scsi_autopm_get_device - scsi_autopm_put_device - scsi_block_requests - scsi_block_when_processing_errors - scsi_command_size_tbl - scsi_compat_ioctl - scsi_device_get - scsi_device_put - scsi_device_quiesce - scsi_dma_unmap - scsi_eh_ready_devs - scsi_ioctl - scsi_ioctl_block_when_processing_errors - scsi_normalize_sense - scsi_print_sense_hdr - scsi_register_interface - scsi_remove_device - scsi_unblock_requests - sdev_prefix_printk - sdhci_add_host - sdhci_cleanup_host - sdhci_cqe_disable - sdhci_cqe_enable - sdhci_cqe_irq - sdhci_enable_clk - sdhci_get_property - sdhci_pltfm_free - sdhci_pltfm_init - sdhci_remove_host - sdhci_reset - sdhci_set_bus_width - sdhci_set_power_noreg - sdhci_setup_host - sdio_claim_host - sdio_disable_func - sdio_enable_func - sdio_f0_readb - sdio_f0_writeb - sdio_get_host_pm_caps - sdio_memcpy_fromio - sdio_memcpy_toio - sdio_readsb - sdio_register_driver - sdio_release_host - sdio_set_block_size - sdio_set_host_pm_flags - sdio_signal_irq - sdio_unregister_driver - sdio_writesb - securityfs_create_dir - securityfs_create_file - securityfs_remove - send_sig_info - seq_buf_printf - seq_file_path - seq_hex_dump - seq_list_next - seq_list_start - seq_lseek - seq_open - seq_printf - seq_putc - seq_puts - seq_read - seq_release - seq_release_private - seq_vprintf - seq_write - serdev_device_close - serdev_device_open - serdev_device_set_baudrate - serdev_device_set_flow_control - serdev_device_wait_until_sent - serdev_device_write - serdev_device_write_wakeup - serio_close - serio_interrupt - serio_open - serio_reconnect - serio_rescan - serio_unregister_child_port - serio_unregister_driver - serio_unregister_port - set_blocksize - set_capacity_revalidate_and_notify - set_cpus_allowed_ptr - set_disk_ro - set_freezable - set_normalized_timespec64 - set_page_dirty - set_page_dirty_lock - set_task_cpu - set_user_nice - sg_alloc_table - sg_alloc_table_from_pages - sg_free_table - sg_init_one - sg_init_table - sg_miter_next - sg_miter_start - sg_miter_stop - sg_nents_for_len - sg_next - sg_pcopy_from_buffer - sg_pcopy_to_buffer - sg_scsi_ioctl - sg_zero_buffer - sgl_alloc - sgl_free - shmem_truncate_range - show_rcu_gp_kthreads - show_regs - si_mem_available - si_meminfo - si_swapinfo - sigprocmask - simple_attr_open - simple_attr_read - simple_attr_release - simple_attr_write - simple_dir_inode_operations - simple_dir_operations - simple_open - simple_read_from_buffer - simple_statfs - simple_strtol - simple_strtoll - simple_strtoul - simple_strtoull - simple_write_to_buffer - single_open - single_open_size - single_release - sk_alloc - sk_free - skb_add_rx_frag - skb_append_pagefrags - skb_checksum - skb_clone - skb_coalesce_rx_frag - skb_copy - skb_copy_bits - skb_copy_datagram_iter - skb_copy_expand - skb_copy_ubufs - skb_dequeue - skb_dequeue_tail - skb_ensure_writable - skb_free_datagram - skb_page_frag_refill - skb_partial_csum_set - skb_pull - skb_push - skb_put - skb_queue_head - skb_queue_purge - skb_queue_tail - skb_realloc_headroom - skb_recv_datagram - skb_set_owner_w - skb_store_bits - skb_to_sgvec - skb_trim - skb_tstamp_tx - skb_unlink - skip_spaces - smp_call_function - smp_call_function_any - smp_call_function_many - smp_call_function_single - smp_call_function_single_async - smp_call_on_cpu - smpboot_register_percpu_thread - smpboot_unregister_percpu_thread - snd_card_disconnect - snd_card_free - snd_card_new - snd_card_register - snd_card_rw_proc_new - snd_component_add - snd_compr_stop_error - snd_ctl_add - snd_ctl_add_vmaster_hook - snd_ctl_apply_vmaster_followers - snd_ctl_boolean_mono_info - snd_ctl_boolean_stereo_info - snd_ctl_enum_info - snd_ctl_find_id - snd_ctl_make_virtual_master - snd_ctl_new1 - snd_ctl_notify - snd_ctl_remove - snd_ctl_remove_id - snd_ctl_sync_vmaster - snd_device_disconnect - snd_device_free - snd_device_new - snd_dma_alloc_pages - snd_dma_free_pages - snd_dmaengine_pcm_prepare_slave_config - snd_hwdep_new - snd_info_create_card_entry - snd_info_create_module_entry - snd_info_free_entry - snd_info_register - snd_interval_refine - snd_jack_new - snd_jack_report - snd_jack_set_key - snd_pci_quirk_lookup - snd_pcm_add_chmap_ctls - snd_pcm_alt_chmaps - snd_pcm_create_iec958_consumer_hw_params - snd_pcm_format_physical_width - snd_pcm_format_width - snd_pcm_hw_constraint_eld - snd_pcm_hw_constraint_integer - snd_pcm_hw_constraint_list - snd_pcm_hw_constraint_minmax - snd_pcm_hw_constraint_msbits - snd_pcm_hw_constraint_step - snd_pcm_hw_limit_rates - snd_pcm_hw_rule_add - snd_pcm_lib_default_mmap - snd_pcm_lib_free_pages - snd_pcm_lib_ioctl - snd_pcm_lib_malloc_pages - snd_pcm_lib_preallocate_free_for_all - snd_pcm_lib_preallocate_pages - snd_pcm_new - snd_pcm_period_elapsed - snd_pcm_rate_range_to_bits - snd_pcm_set_managed_buffer_all - snd_pcm_set_ops - snd_pcm_set_sync - snd_pcm_std_chmaps - snd_pcm_stream_lock - snd_pcm_stream_unlock - snd_pcm_stream_unlock_irqrestore - snd_soc_add_card_controls - snd_soc_add_component_controls - snd_soc_add_dai_controls - snd_soc_bytes_info_ext - snd_soc_bytes_tlv_callback - snd_soc_card_get_kcontrol - snd_soc_card_jack_new - snd_soc_component_async_complete - snd_soc_component_disable_pin - snd_soc_component_exit_regmap - snd_soc_component_force_enable_pin - snd_soc_component_init_regmap - snd_soc_component_read - snd_soc_component_set_jack - snd_soc_component_set_pll - snd_soc_component_set_sysclk - snd_soc_component_update_bits - snd_soc_component_update_bits_async - snd_soc_component_write - snd_soc_dai_get_channel_map - snd_soc_dai_link_set_capabilities - snd_soc_dai_set_bclk_ratio - snd_soc_dai_set_channel_map - snd_soc_dai_set_fmt - snd_soc_dai_set_pll - snd_soc_dai_set_sysclk - snd_soc_dai_set_tdm_slot - snd_soc_dapm_add_routes - snd_soc_dapm_disable_pin - snd_soc_dapm_disable_pin_unlocked - snd_soc_dapm_enable_pin - snd_soc_dapm_force_enable_pin - snd_soc_dapm_force_enable_pin_unlocked - snd_soc_dapm_get_enum_double - snd_soc_dapm_get_pin_status - snd_soc_dapm_get_pin_switch - snd_soc_dapm_get_volsw - snd_soc_dapm_ignore_suspend - snd_soc_dapm_info_pin_switch - snd_soc_dapm_kcontrol_dapm - snd_soc_dapm_kcontrol_widget - snd_soc_dapm_mixer_update_power - snd_soc_dapm_mux_update_power - snd_soc_dapm_new_control - snd_soc_dapm_new_controls - snd_soc_dapm_new_widgets - snd_soc_dapm_put_enum_double - snd_soc_dapm_put_pin_switch - snd_soc_dapm_put_volsw - snd_soc_dapm_sync - snd_soc_dapm_sync_unlocked - snd_soc_dapm_weak_routes - snd_soc_find_dai - snd_soc_get_enum_double - snd_soc_get_pcm_runtime - snd_soc_get_volsw - snd_soc_get_volsw_range - snd_soc_get_volsw_sx - snd_soc_get_xr_sx - snd_soc_info_enum_double - snd_soc_info_multi_ext - snd_soc_info_volsw - snd_soc_info_volsw_range - snd_soc_info_volsw_sx - snd_soc_info_xr_sx - snd_soc_jack_add_gpios - snd_soc_jack_report - snd_soc_lookup_component - snd_soc_new_compress - snd_soc_of_get_dai_link_codecs - snd_soc_of_get_dai_name - snd_soc_of_parse_audio_routing - snd_soc_of_parse_audio_simple_widgets - snd_soc_of_parse_aux_devs - snd_soc_of_parse_card_name - snd_soc_of_parse_daifmt - snd_soc_of_parse_node_prefix - snd_soc_of_parse_tdm_slot - snd_soc_of_put_dai_link_codecs - snd_soc_params_to_bclk - snd_soc_params_to_frame_size - snd_soc_pm_ops - snd_soc_put_enum_double - snd_soc_put_volsw - snd_soc_put_volsw_range - snd_soc_put_volsw_sx - snd_soc_put_xr_sx - snd_soc_register_card - snd_soc_register_component - snd_soc_rtdcom_lookup - snd_soc_runtime_calc_hw - snd_soc_runtime_set_dai_fmt - snd_soc_set_runtime_hwparams - snd_soc_tplg_component_load - snd_soc_tplg_component_remove - snd_soc_tplg_widget_bind_event - snd_soc_unregister_card - snd_soc_unregister_component - snd_usb_enable_audio_stream - snd_vendor_set_ops - snprintf - soc_device_register - soc_device_unregister - sock_alloc_send_skb - sock_create_kern - sock_gettstamp - sock_i_uid - sock_init_data - sock_no_accept - sock_no_listen - sock_no_mmap - sock_no_sendpage - sock_no_shutdown - sock_no_socketpair - sock_queue_rcv_skb - sock_register - sock_release - sock_setsockopt - sock_unregister - sock_wfree - softnet_data - sort - spi_bus_lock - spi_bus_type - spi_bus_unlock - spi_controller_resume - spi_controller_suspend - spi_delay_exec - spi_finalize_current_message - spi_finalize_current_transfer - spi_get_next_queued_message - spi_register_controller - spi_setup - spi_sync - spi_sync_locked - spi_unregister_controller - split_page - spmi_controller_add - spmi_controller_alloc - spmi_controller_remove - spmi_ext_register_read - spmi_ext_register_readl - spmi_ext_register_write - spmi_ext_register_writel - spmi_register_read - spmi_register_write - spmi_register_zero_write - sprint_symbol - sprint_symbol_no_offset - sprintf - srcu_barrier - srcu_batches_completed - srcu_init_notifier_head - srcu_notifier_call_chain - srcu_notifier_chain_register - srcu_notifier_chain_unregister - srcu_torture_stats_print - srcutorture_get_gp_data - sscanf - stack_trace_print - stack_trace_save - stack_trace_save_regs - stack_trace_save_tsk - static_key_disable - static_key_disable_cpuslocked - static_key_slow_dec - static_key_slow_inc - stop_machine - stop_one_cpu_nowait - stpcpy - strcasecmp - strcat - strchr - strchrnul - strcmp - strcpy - strcspn - stream_open - strim - string_get_size - strlcat - strlcpy - strlen - strncasecmp - strncat - strnchr - strncmp - strncpy - strncpy_from_user - strndup_user - strnlen - strnstr - strpbrk - strrchr - strreplace - strscpy - strsep - strspn - strstr - submit_bh - submit_bio - submit_bio_wait - subsys_system_register - swiotlb_nr_tbl - sync_blockdev - sync_file_create - sync_file_get_fence - synchronize_irq - synchronize_net - synchronize_rcu - synchronize_rcu_expedited - synchronize_rcu_tasks - synchronize_rcu_tasks_trace - synchronize_srcu - synchronize_srcu_expedited - sys_tz - syscon_node_to_regmap - syscon_regmap_lookup_by_phandle - sysctl_sched_features - sysctl_sched_latency - sysctl_vals - sysfs_add_file_to_group - sysfs_add_link_to_group - sysfs_create_bin_file - sysfs_create_file_ns - sysfs_create_files - sysfs_create_group - sysfs_create_groups - sysfs_create_link - sysfs_emit - sysfs_emit_at - sysfs_notify - sysfs_remove_bin_file - sysfs_remove_file_from_group - sysfs_remove_file_ns - sysfs_remove_files - sysfs_remove_group - sysfs_remove_groups - sysfs_remove_link - sysfs_remove_link_from_group - sysfs_streq - sysfs_update_group - sysrq_mask - system_freezable_wq - system_freezing_cnt - system_highpri_wq - system_long_wq - system_power_efficient_wq - system_state - system_unbound_wq - system_wq - task_active_pid_ns - task_groups - task_may_not_preempt - task_rq_lock - tasklet_init - tasklet_kill - tasklet_setup - tasklist_lock - tcp_register_congestion_control - tcp_reno_cong_avoid - tcp_reno_ssthresh - tcp_reno_undo_cwnd - tcp_slow_start - tcp_unregister_congestion_control - tcpci_get_tcpm_port - tcpci_irq - tcpci_register_port - tcpci_unregister_port - tcpm_cc_change - tcpm_is_toggling - tcpm_pd_hard_reset - tcpm_pd_receive - tcpm_pd_transmit_complete - tcpm_sink_frs - tcpm_sourcing_vbus - tcpm_update_sink_capabilities - tcpm_vbus_change - thermal_cdev_update - thermal_cooling_device_register - thermal_cooling_device_unregister - thermal_of_cooling_device_register - thermal_pressure - thermal_zone_device_disable - thermal_zone_device_enable - thermal_zone_device_is_enabled - thermal_zone_device_register - thermal_zone_device_unregister - thermal_zone_device_update - thermal_zone_get_slope - thermal_zone_get_temp - thermal_zone_get_zone_by_name - thermal_zone_of_sensor_register - thermal_zone_of_sensor_unregister - thread_group_cputime_adjusted - tick_nohz_get_idle_calls_cpu - tick_nohz_get_sleep_length - time64_to_tm - timecounter_init - timecounter_read - timer_unstable_counter_workaround - topology_set_thermal_pressure - total_swapcache_pages - trace_clock_local - trace_event_buffer_commit - trace_event_buffer_reserve - trace_event_ignore_this_pid - trace_event_raw_init - trace_event_reg - trace_handle_return - trace_output_call trace_print_array_seq trace_print_flags_seq trace_print_hex_seq + __trace_printk trace_print_symbols_seq trace_raw_output_prep trace_seq_printf trace_seq_putc - tracepoint_probe_register - tracepoint_probe_register_prio - tracepoint_probe_unregister tracing_off try_module_get try_to_del_timer_sync @@ -4038,8 +4018,8 @@ ttm_bo_device_init ttm_bo_device_release ttm_bo_dma_acc_size - ttm_bo_evict_mm ttm_bo_eviction_valuable + ttm_bo_evict_mm ttm_bo_glob ttm_bo_init_reserved ttm_bo_kmap @@ -4074,8 +4054,10 @@ ttm_tt_populate ttm_tt_set_placement_caching ttm_unmap_and_unpopulate_pages + __tty_alloc_driver tty_encode_baud_rate tty_flip_buffer_push + __tty_insert_flip_char tty_insert_flip_string_fixed_flag tty_kref_put tty_ldisc_deref @@ -4137,6 +4119,7 @@ ucsi_register ucsi_set_drvdata ucsi_unregister + __udelay udp4_hwcsum ufshcd_auto_hibern8_update ufshcd_bkops_ctrl @@ -4168,11 +4151,13 @@ ufshcd_system_suspend ufshcd_uic_hibern8_enter ufshcd_uic_hibern8_exit + __uio_register_device uio_unregister_device unlock_page unmap_mapping_range unpin_user_page unregister_blkdev + __unregister_chrdev unregister_chrdev_region unregister_console unregister_die_notifier @@ -4202,10 +4187,11 @@ unregister_virtio_driver unregister_vmap_purge_notifier up + update_devfreq + __update_load_avg_blocked_se + update_rq_clock up_read up_write - update_devfreq - update_rq_clock usb_add_function usb_add_gadget usb_add_gadget_udc @@ -4233,14 +4219,15 @@ usb_composite_setup_continue usb_control_msg usb_copy_descriptors + __usb_create_hcd usb_create_hcd usb_debug_root usb_decode_ctrl usb_del_gadget_udc usb_deregister usb_deregister_dev - usb_disable_xhci_ports usb_disabled + usb_disable_xhci_ports usb_enable_autosuspend usb_enable_intel_xhci_ports usb_ep_alloc_request @@ -4275,15 +4262,16 @@ usb_gadget_wakeup usb_get_dev usb_get_dr_mode + __usb_get_extra_descriptor usb_get_gadget_udc_name usb_get_intf usb_get_maximum_speed usb_get_urb usb_gstrings_attach - usb_hc_died usb_hcd_check_unlink_urb usb_hcd_end_port_resume usb_hcd_giveback_urb + usb_hc_died usb_hcd_irq usb_hcd_is_primary_hcd usb_hcd_link_urb_to_ep @@ -4295,9 +4283,9 @@ usb_hcd_platform_shutdown usb_hcd_poll_rh_status usb_hcd_resume_root_hub + usb_hcds_loaded usb_hcd_start_port_resume usb_hcd_unlink_urb_from_ep - usb_hcds_loaded usb_hid_driver usb_hub_clear_tt_buffer usb_hub_find_child @@ -4308,6 +4296,36 @@ usb_kill_urb usb_match_id usb_match_one_id + usbnet_cdc_unbind + usbnet_change_mtu + usbnet_defer_kevent + usbnet_disconnect + usbnet_generic_cdc_bind + usbnet_get_drvinfo + usbnet_get_endpoints + usbnet_get_link + usbnet_get_link_ksettings + usbnet_get_msglevel + usbnet_get_stats64 + usbnet_link_change + usbnet_nway_reset + usbnet_open + usbnet_probe + usbnet_read_cmd + usbnet_read_cmd_nopm + usbnet_resume + usbnet_set_link_ksettings + usbnet_set_msglevel + usbnet_skb_return + usbnet_start_xmit + usbnet_stop + usbnet_suspend + usbnet_tx_timeout + usbnet_unlink_rx_urbs + usbnet_update_max_qlen + usbnet_write_cmd + usbnet_write_cmd_async + usbnet_write_cmd_nopm usb_otg_state_string usb_phy_set_charger_current usb_poison_anchored_urbs @@ -4339,36 +4357,7 @@ usb_unpoison_urb usb_unregister_notify usb_wakeup_notification - usbnet_cdc_unbind - usbnet_change_mtu - usbnet_defer_kevent - usbnet_disconnect - usbnet_generic_cdc_bind - usbnet_get_drvinfo - usbnet_get_endpoints - usbnet_get_link - usbnet_get_link_ksettings - usbnet_get_msglevel - usbnet_get_stats64 - usbnet_link_change - usbnet_nway_reset - usbnet_open - usbnet_probe - usbnet_read_cmd - usbnet_read_cmd_nopm - usbnet_resume - usbnet_set_link_ksettings - usbnet_set_msglevel - usbnet_skb_return - usbnet_start_xmit - usbnet_stop - usbnet_suspend - usbnet_tx_timeout - usbnet_unlink_rx_urbs - usbnet_update_max_qlen - usbnet_write_cmd - usbnet_write_cmd_async - usbnet_write_cmd_nopm + __usecs_to_jiffies usleep_range uuid_gen uuid_null @@ -4384,6 +4373,7 @@ v4l2_ctrl_new_std_menu v4l2_device_register v4l2_device_register_subdev + __v4l2_device_register_subdev_nodes v4l2_device_set_name v4l2_device_unregister v4l2_device_unregister_subdev @@ -4476,6 +4466,7 @@ video_device_release video_device_release_empty video_ioctl2 + __video_register_device video_unregister_device virtio_check_driver_offered_feature virtio_config_changed @@ -4532,7 +4523,17 @@ virtqueue_kick_prepare virtqueue_notify virtqueue_poll + vmalloc + vmalloc_nr_pages + vmalloc_to_page + vmalloc_to_pfn + vmalloc_user + vmap + vmemdup_user vm_event_states + vmf_insert_mixed + vmf_insert_pfn + vmf_insert_pfn_prot vm_get_page_prot vm_insert_page vm_iomap_memory @@ -4543,16 +4544,6 @@ vm_node_stat vm_unmap_ram vm_zone_stat - vmalloc - vmalloc_nr_pages - vmalloc_to_page - vmalloc_to_pfn - vmalloc_user - vmap - vmemdup_user - vmf_insert_mixed - vmf_insert_pfn - vmf_insert_pfn_prot vprintk vring_create_virtqueue vring_del_virtqueue @@ -4575,8 +4566,12 @@ wait_for_completion_killable wait_for_completion_killable_timeout wait_for_completion_timeout + __wait_rcu_gp wait_woken + __wake_up wake_up_if_idle + __wake_up_locked + __wake_up_locked_key wake_up_process wakeup_source_add wakeup_source_create @@ -4584,6 +4579,8 @@ wakeup_source_register wakeup_source_remove wakeup_source_unregister + __wake_up_sync + __warn_printk watchdog_init_timeout watchdog_register_device watchdog_set_restart_priority @@ -4594,10 +4591,12 @@ ww_mutex_lock ww_mutex_lock_interruptible ww_mutex_unlock + __xa_alloc xa_destroy xa_erase xa_find xa_find_after + __xa_insert xa_load xa_store xdp_convert_zc_to_xdp_frame @@ -4609,6 +4608,7 @@ xdp_rxq_info_reg_mem_model xdp_rxq_info_unreg xdp_warn + __xfrm_state_destroy xfrm_state_lookup_byspi xfrm_stateonly_find xhci_add_endpoint diff --git a/android/abi_gki_aarch64_generic b/android/abi_gki_aarch64_generic index cd7ca5f41b8b..f0808ba8372e 100644 --- a/android/abi_gki_aarch64_generic +++ b/android/abi_gki_aarch64_generic @@ -87,10 +87,10 @@ blocking_notifier_call_chain blocking_notifier_chain_register blocking_notifier_chain_unregister - bpf_trace_run1 bpf_trace_run10 bpf_trace_run11 bpf_trace_run12 + bpf_trace_run1 bpf_trace_run2 bpf_trace_run3 bpf_trace_run4 @@ -993,8 +993,8 @@ irq_work_queue irq_work_sync is_vmalloc_addr - jiffies jiffies64_to_msecs + jiffies jiffies_to_msecs jiffies_to_usecs kasan_flag_enabled @@ -1123,8 +1123,8 @@ memmove memparse memremap - memset memset64 + memset memstart_addr memunmap mfd_add_devices @@ -1198,8 +1198,8 @@ nla_find nla_memcpy __nla_parse - nla_put nla_put_64bit + nla_put nla_put_nohdr nla_reserve nla_strlcpy diff --git a/android/abi_gki_aarch64_lenovo b/android/abi_gki_aarch64_lenovo index 0049535a4a1f..6815423a1c7c 100644 --- a/android/abi_gki_aarch64_lenovo +++ b/android/abi_gki_aarch64_lenovo @@ -1,10 +1,10 @@ [abi_symbol_list] # required by raid0.ko - __tracepoint_block_bio_remap - disk_stack_limits - blk_queue_max_write_same_sectors - __traceiter_block_bio_remap - submit_bio_noacct bio_split + blk_queue_max_write_same_sectors + disk_stack_limits + submit_bio_noacct + __traceiter_block_bio_remap + __tracepoint_block_bio_remap # required by lenovo-fan.ko clk_set_duty_cycle diff --git a/android/abi_gki_aarch64_mtk b/android/abi_gki_aarch64_mtk index 630e18957ea8..5473f314864b 100644 --- a/android/abi_gki_aarch64_mtk +++ b/android/abi_gki_aarch64_mtk @@ -199,8 +199,8 @@ cpufreq_disable_fast_switch cpufreq_driver_fast_switch cpufreq_driver_resolve_freq - cpufreq_driver_target __cpufreq_driver_target + cpufreq_driver_target cpufreq_enable_fast_switch cpufreq_frequency_table_get_index cpufreq_generic_attr @@ -374,8 +374,8 @@ __dev_kfree_skb_any __dev_kfree_skb_irq devm_add_action - __devm_alloc_percpu devm_alloc_etherdev_mqs + __devm_alloc_percpu devm_blk_ksm_init devm_clk_bulk_get devm_clk_bulk_get_optional @@ -3159,10 +3159,10 @@ __tracepoint_android_rvh_select_task_rq_rt __tracepoint_android_rvh_setscheduler __tracepoint_android_rvh_set_user_nice + __tracepoint_android_rvh_uclamp_eff_get __tracepoint_android_rvh_v4l2subdev_set_fmt __tracepoint_android_rvh_v4l2subdev_set_frame_interval __tracepoint_android_rvh_v4l2subdev_set_selection - __tracepoint_android_rvh_uclamp_eff_get __tracepoint_android_vh_alter_futex_plist_add __tracepoint_android_vh_alter_rwsem_list_add __tracepoint_android_vh_arch_set_freq_scale diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index 5693bb828b42..b1b464d893fe 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -115,9 +115,9 @@ blocking_notifier_call_chain blocking_notifier_chain_register blocking_notifier_chain_unregister - bpf_trace_run1 bpf_trace_run10 bpf_trace_run12 + bpf_trace_run1 bpf_trace_run2 bpf_trace_run3 bpf_trace_run4 @@ -685,8 +685,8 @@ dma_unmap_resource dma_unmap_sg_attrs do_exit - do_wait_intr_irq do_traversal_all_lruvec + do_wait_intr_irq down down_interruptible down_read @@ -1568,8 +1568,8 @@ mempool_free mempool_free_slab memremap - memset memset64 + memset __memset_io memstart_addr memunmap @@ -1670,10 +1670,10 @@ nla_find nla_memcpy __nla_parse - nla_put nla_put_64bit - nla_reserve + nla_put nla_reserve_64bit + nla_reserve __nla_validate __nlmsg_put no_llseek @@ -1810,8 +1810,8 @@ page_endio __page_file_index __page_file_mapping - __page_mapcount page_get_link + __page_mapcount page_mapping __page_pinner_migration_failed page_symlink @@ -2059,8 +2059,8 @@ radix_tree_lookup radix_tree_lookup_slot radix_tree_next_chunk - radix_tree_replace_slot radix_tree_preload + radix_tree_replace_slot ___ratelimit rational_best_approximation raw_notifier_call_chain @@ -2696,8 +2696,8 @@ __traceiter_android_rvh_after_enqueue_task __traceiter_android_rvh_build_perf_domains __traceiter_android_rvh_can_migrate_task - __traceiter_android_rvh_check_preempt_wakeup __traceiter_android_rvh_check_preempt_tick + __traceiter_android_rvh_check_preempt_wakeup __traceiter_android_rvh_cpu_cgroup_attach __traceiter_android_rvh_cpu_cgroup_online __traceiter_android_rvh_cpu_overutilized @@ -2754,6 +2754,9 @@ __traceiter_android_rvh_v4l2subdev_set_selection __traceiter_android_rvh_wake_up_new_task __traceiter_android_vh_account_task_time + __traceiter_android_vh_add_page_to_lrulist + __traceiter_android_vh_alloc_pages_slowpath_begin + __traceiter_android_vh_alloc_pages_slowpath_end __traceiter_android_vh_allow_domain_state __traceiter_android_vh_alter_futex_plist_add __traceiter_android_vh_alter_mutex_list_add @@ -2784,6 +2787,7 @@ __traceiter_android_vh_check_bpf_syscall __traceiter_android_vh_check_file_open __traceiter_android_vh_check_mmap_file + __traceiter_android_vh_check_page_look_around_ref __traceiter_android_vh_check_uninterruptible_tasks __traceiter_android_vh_check_uninterruptible_tasks_dn __traceiter_android_vh_clear_mask_adjust @@ -2797,9 +2801,11 @@ __traceiter_android_vh_cpu_idle_enter __traceiter_android_vh_cpu_idle_exit __traceiter_android_vh_cpu_up - __traceiter_android_vh_check_page_look_around_ref + __traceiter_android_vh_del_page_from_lrulist __traceiter_android_vh_do_futex + __traceiter_android_vh_do_page_trylock __traceiter_android_vh_do_send_sig_info + __traceiter_android_vh_do_traversal_lruvec __traceiter_android_vh_drain_all_pages_bypass __traceiter_android_vh_em_cpu_energy __traceiter_android_vh_exclude_reserved_zone @@ -2833,14 +2839,13 @@ __traceiter_android_vh_logbuf __traceiter_android_vh_look_around __traceiter_android_vh_look_around_migrate_page + __traceiter_android_vh_mark_page_accessed __traceiter_android_vh_mem_cgroup_alloc __traceiter_android_vh_mem_cgroup_css_offline __traceiter_android_vh_mem_cgroup_css_online __traceiter_android_vh_mem_cgroup_free __traceiter_android_vh_mem_cgroup_id_remove __traceiter_android_vh_meminfo_proc_show - __traceiter_android_vh_alloc_pages_slowpath_begin - __traceiter_android_vh_alloc_pages_slowpath_end __traceiter_android_vh_mutex_can_spin_on_owner __traceiter_android_vh_mutex_opt_spin_finish __traceiter_android_vh_mutex_opt_spin_start @@ -2851,25 +2856,19 @@ __traceiter_android_vh_override_creds __traceiter_android_vh_page_referenced_check_bypass __traceiter_android_vh_page_should_be_protected - __traceiter_android_vh_page_trylock_set __traceiter_android_vh_page_trylock_clear __traceiter_android_vh_page_trylock_get_result - __traceiter_android_vh_mark_page_accessed - __traceiter_android_vh_show_mapcount_pages - __traceiter_android_vh_do_traversal_lruvec - __traceiter_android_vh_do_page_trylock - __traceiter_android_vh_update_page_mapcount - __traceiter_android_vh_add_page_to_lrulist - __traceiter_android_vh_del_page_from_lrulist + __traceiter_android_vh_page_trylock_set __traceiter_android_vh_pcplist_add_cma_pages_bypass __traceiter_android_vh_prepare_update_load_avg_se __traceiter_android_vh_printk_hotplug __traceiter_android_vh_process_killed - __traceiter_android_vh_revert_creds __traceiter_android_vh_record_mutex_lock_starttime + __traceiter_android_vh_record_pcpu_rwsem_starttime __traceiter_android_vh_record_rtmutex_lock_starttime __traceiter_android_vh_record_rwsem_lock_starttime - __traceiter_android_vh_record_pcpu_rwsem_starttime + __traceiter_android_vh_remove_vmalloc_stack + __traceiter_android_vh_revert_creds __traceiter_android_vh_rmqueue __traceiter_android_vh_rwsem_can_spin_on_owner __traceiter_android_vh_rwsem_init @@ -2885,7 +2884,6 @@ __traceiter_android_vh_rwsem_write_finished __traceiter_android_vh_save_track_hash __traceiter_android_vh_save_vmalloc_stack - __traceiter_android_vh_remove_vmalloc_stack __traceiter_android_vh_sched_stat_runtime_rt __traceiter_android_vh_scheduler_tick __traceiter_android_vh_selinux_avc_insert @@ -2901,6 +2899,7 @@ __traceiter_android_vh_set_module_permit_before_init __traceiter_android_vh_setscheduler_uclamp __traceiter_android_vh_set_wake_flags + __traceiter_android_vh_show_mapcount_pages __traceiter_android_vh_show_max_freq __traceiter_android_vh_show_resume_epoch_val __traceiter_android_vh_show_stack_hash @@ -2908,6 +2907,7 @@ __traceiter_android_vh_shrink_node_memcgs __traceiter_android_vh_sync_txn_recvd __traceiter_android_vh_syscall_prctl_finished + __traceiter_android_vh_test_clear_look_around_ref __traceiter_android_vh_timer_calc_index __traceiter_android_vh_tune_inactive_ratio __traceiter_android_vh_tune_scan_type @@ -2915,6 +2915,7 @@ __traceiter_android_vh_ufs_compl_command __traceiter_android_vh_ufs_send_command __traceiter_android_vh_ufs_send_tm_command + __traceiter_android_vh_update_page_mapcount __traceiter_android_vh_update_topology_flags_workfn __traceiter_binder_transaction_received __traceiter_cpu_frequency @@ -2940,14 +2941,13 @@ __traceiter_suspend_resume __traceiter_task_newtask __traceiter_task_rename - __traceiter_android_vh_test_clear_look_around_ref __traceiter_xhci_urb_giveback __tracepoint_android_rvh_account_irq __tracepoint_android_rvh_after_enqueue_task __tracepoint_android_rvh_build_perf_domains __tracepoint_android_rvh_can_migrate_task - __tracepoint_android_rvh_check_preempt_wakeup __tracepoint_android_rvh_check_preempt_tick + __tracepoint_android_rvh_check_preempt_wakeup __tracepoint_android_rvh_cpu_cgroup_attach __tracepoint_android_rvh_cpu_cgroup_online __tracepoint_android_rvh_cpu_overutilized @@ -3004,6 +3004,9 @@ __tracepoint_android_rvh_v4l2subdev_set_selection __tracepoint_android_rvh_wake_up_new_task __tracepoint_android_vh_account_task_time + __tracepoint_android_vh_add_page_to_lrulist + __tracepoint_android_vh_alloc_pages_slowpath_begin + __tracepoint_android_vh_alloc_pages_slowpath_end __tracepoint_android_vh_allow_domain_state __tracepoint_android_vh_alter_futex_plist_add __tracepoint_android_vh_alter_mutex_list_add @@ -3034,6 +3037,7 @@ __tracepoint_android_vh_check_bpf_syscall __tracepoint_android_vh_check_file_open __tracepoint_android_vh_check_mmap_file + __tracepoint_android_vh_check_page_look_around_ref __tracepoint_android_vh_check_uninterruptible_tasks __tracepoint_android_vh_check_uninterruptible_tasks_dn __tracepoint_android_vh_clear_mask_adjust @@ -3047,9 +3051,11 @@ __tracepoint_android_vh_cpu_idle_enter __tracepoint_android_vh_cpu_idle_exit __tracepoint_android_vh_cpu_up - __tracepoint_android_vh_check_page_look_around_ref + __tracepoint_android_vh_del_page_from_lrulist __tracepoint_android_vh_do_futex + __tracepoint_android_vh_do_page_trylock __tracepoint_android_vh_do_send_sig_info + __tracepoint_android_vh_do_traversal_lruvec __tracepoint_android_vh_drain_all_pages_bypass __tracepoint_android_vh_em_cpu_energy __tracepoint_android_vh_exclude_reserved_zone @@ -3083,14 +3089,13 @@ __tracepoint_android_vh_logbuf __tracepoint_android_vh_look_around __tracepoint_android_vh_look_around_migrate_page + __tracepoint_android_vh_mark_page_accessed __tracepoint_android_vh_mem_cgroup_alloc __tracepoint_android_vh_mem_cgroup_css_offline __tracepoint_android_vh_mem_cgroup_css_online __tracepoint_android_vh_mem_cgroup_free __tracepoint_android_vh_mem_cgroup_id_remove __tracepoint_android_vh_meminfo_proc_show - __tracepoint_android_vh_alloc_pages_slowpath_begin - __tracepoint_android_vh_alloc_pages_slowpath_end __tracepoint_android_vh_mutex_can_spin_on_owner __tracepoint_android_vh_mutex_opt_spin_finish __tracepoint_android_vh_mutex_opt_spin_start @@ -3101,25 +3106,19 @@ __tracepoint_android_vh_override_creds __tracepoint_android_vh_page_referenced_check_bypass __tracepoint_android_vh_page_should_be_protected - __tracepoint_android_vh_page_trylock_set __tracepoint_android_vh_page_trylock_clear __tracepoint_android_vh_page_trylock_get_result - __tracepoint_android_vh_mark_page_accessed - __tracepoint_android_vh_show_mapcount_pages - __tracepoint_android_vh_do_traversal_lruvec - __tracepoint_android_vh_do_page_trylock - __tracepoint_android_vh_update_page_mapcount - __tracepoint_android_vh_add_page_to_lrulist - __tracepoint_android_vh_del_page_from_lrulist + __tracepoint_android_vh_page_trylock_set __tracepoint_android_vh_pcplist_add_cma_pages_bypass __tracepoint_android_vh_prepare_update_load_avg_se __tracepoint_android_vh_printk_hotplug __tracepoint_android_vh_process_killed - __tracepoint_android_vh_revert_creds __tracepoint_android_vh_record_mutex_lock_starttime + __tracepoint_android_vh_record_pcpu_rwsem_starttime __tracepoint_android_vh_record_rtmutex_lock_starttime __tracepoint_android_vh_record_rwsem_lock_starttime - __tracepoint_android_vh_record_pcpu_rwsem_starttime + __tracepoint_android_vh_remove_vmalloc_stack + __tracepoint_android_vh_revert_creds __tracepoint_android_vh_rmqueue __tracepoint_android_vh_rwsem_can_spin_on_owner __tracepoint_android_vh_rwsem_init @@ -3135,7 +3134,6 @@ __tracepoint_android_vh_rwsem_write_finished __tracepoint_android_vh_save_track_hash __tracepoint_android_vh_save_vmalloc_stack - __tracepoint_android_vh_remove_vmalloc_stack __tracepoint_android_vh_sched_stat_runtime_rt __tracepoint_android_vh_scheduler_tick __tracepoint_android_vh_selinux_avc_insert @@ -3151,6 +3149,7 @@ __tracepoint_android_vh_set_module_permit_before_init __tracepoint_android_vh_setscheduler_uclamp __tracepoint_android_vh_set_wake_flags + __tracepoint_android_vh_show_mapcount_pages __tracepoint_android_vh_show_max_freq __tracepoint_android_vh_show_resume_epoch_val __tracepoint_android_vh_show_stack_hash @@ -3158,14 +3157,15 @@ __tracepoint_android_vh_shrink_node_memcgs __tracepoint_android_vh_sync_txn_recvd __tracepoint_android_vh_syscall_prctl_finished + __tracepoint_android_vh_test_clear_look_around_ref __tracepoint_android_vh_timer_calc_index __tracepoint_android_vh_tune_inactive_ratio __tracepoint_android_vh_tune_scan_type __tracepoint_android_vh_tune_swappiness - __tracepoint_android_vh_test_clear_look_around_ref __tracepoint_android_vh_ufs_compl_command __tracepoint_android_vh_ufs_send_command __tracepoint_android_vh_ufs_send_tm_command + __tracepoint_android_vh_update_page_mapcount __tracepoint_android_vh_update_topology_flags_workfn __tracepoint_binder_transaction_received __tracepoint_cpu_frequency diff --git a/android/abi_gki_aarch64_qcom b/android/abi_gki_aarch64_qcom index 0004b141d673..bc5d94e3630a 100644 --- a/android/abi_gki_aarch64_qcom +++ b/android/abi_gki_aarch64_qcom @@ -93,10 +93,10 @@ blocking_notifier_call_chain blocking_notifier_chain_register blocking_notifier_chain_unregister - bpf_trace_run1 bpf_trace_run10 bpf_trace_run11 bpf_trace_run12 + bpf_trace_run1 bpf_trace_run2 bpf_trace_run3 bpf_trace_run4 @@ -1431,8 +1431,8 @@ mempool_free mempool_free_slab memremap - memset memset64 + memset __memset_io memstart_addr memunmap @@ -1453,8 +1453,8 @@ mmc_regulator_set_ocr mmc_regulator_set_vqmmc mmc_select_bus_width - mmc_select_hs mmc_select_hs400 + mmc_select_hs mmc_select_hs_ddr mmc_select_timing mmc_send_tuning @@ -1524,10 +1524,10 @@ nla_find nla_memcpy __nla_parse - nla_put nla_put_64bit - nla_reserve + nla_put nla_reserve_64bit + nla_reserve __nla_validate __nlmsg_put no_llseek diff --git a/android/abi_gki_aarch64_transsion b/android/abi_gki_aarch64_transsion index 83e28c1e1746..26f1a25320be 100644 --- a/android/abi_gki_aarch64_transsion +++ b/android/abi_gki_aarch64_transsion @@ -1,74 +1,74 @@ [abi_symbol_list] + check_cache_active get_mem_cgroup_from_mm is_swap_slot_cache_enabled - swapcache_free_entries - swap_type_to_swap_info + nr_swap_pages + plist_del + plist_requeue scan_swap_map_slots swap_alloc_cluster - check_cache_active - zero_pfn - nr_swap_pages - plist_requeue - plist_del + swapcache_free_entries + swap_type_to_swap_info + __traceiter_android_rvh_alloc_si + __traceiter_android_rvh_alloc_swap_slot_cache + __traceiter_android_rvh_drain_slots_cache_cpu + __traceiter_android_rvh_free_swap_slot + __traceiter_android_rvh_get_swap_page __traceiter_android_rvh_handle_pte_fault_end - __traceiter_android_vh_handle_pte_fault_end - __traceiter_android_vh_cow_user_page - __traceiter_android_vh_swapin_add_anon_rmap - __traceiter_android_vh_waiting_for_page_migration - __traceiter_android_vh_migrate_page_states - __traceiter_android_vh_page_referenced_one_end + __traceiter_android_vh_account_swap_pages + __traceiter_android_vh_alloc_si + __traceiter_android_vh_alloc_swap_slot_cache __traceiter_android_vh_count_pswpin __traceiter_android_vh_count_pswpout __traceiter_android_vh_count_swpout_vm_event - __traceiter_android_vh_swap_slot_cache_active - __traceiter_android_rvh_drain_slots_cache_cpu + __traceiter_android_vh_cow_user_page __traceiter_android_vh_drain_slots_cache_cpu - __traceiter_android_rvh_alloc_swap_slot_cache - __traceiter_android_vh_alloc_swap_slot_cache - __traceiter_android_rvh_free_swap_slot - __traceiter_android_vh_free_swap_slot - __traceiter_android_rvh_get_swap_page - __traceiter_android_vh_get_swap_page - __traceiter_android_vh_page_isolated_for_reclaim - __traceiter_android_vh_inactive_is_low - __traceiter_android_vh_snapshot_refaults - __traceiter_android_vh_account_swap_pages - __traceiter_android_vh_unuse_swap_page - __traceiter_android_vh_init_swap_info_struct - __traceiter_android_vh_si_swapinfo - __traceiter_android_rvh_alloc_si - __traceiter_android_vh_alloc_si __traceiter_android_vh_free_pages - __traceiter_android_vh_set_shmem_page_flag + __traceiter_android_vh_free_swap_slot + __traceiter_android_vh_get_swap_page + __traceiter_android_vh_handle_pte_fault_end + __traceiter_android_vh_inactive_is_low + __traceiter_android_vh_init_swap_info_struct + __traceiter_android_vh_migrate_page_states + __traceiter_android_vh_page_isolated_for_reclaim + __traceiter_android_vh_page_referenced_one_end __traceiter_android_vh_ra_tuning_max_page + __traceiter_android_vh_set_shmem_page_flag + __traceiter_android_vh_si_swapinfo + __traceiter_android_vh_snapshot_refaults + __traceiter_android_vh_swapin_add_anon_rmap + __traceiter_android_vh_swap_slot_cache_active + __traceiter_android_vh_unuse_swap_page + __traceiter_android_vh_waiting_for_page_migration + __tracepoint_android_rvh_alloc_si + __tracepoint_android_rvh_alloc_swap_slot_cache + __tracepoint_android_rvh_drain_slots_cache_cpu + __tracepoint_android_rvh_free_swap_slot + __tracepoint_android_rvh_get_swap_page __tracepoint_android_rvh_handle_pte_fault_end - __tracepoint_android_vh_handle_pte_fault_end - __tracepoint_android_vh_cow_user_page - __tracepoint_android_vh_swapin_add_anon_rmap - __tracepoint_android_vh_waiting_for_page_migration - __tracepoint_android_vh_migrate_page_states - __tracepoint_android_vh_page_referenced_one_end + __tracepoint_android_vh_account_swap_pages + __tracepoint_android_vh_alloc_si + __tracepoint_android_vh_alloc_swap_slot_cache __tracepoint_android_vh_count_pswpin __tracepoint_android_vh_count_pswpout __tracepoint_android_vh_count_swpout_vm_event - __tracepoint_android_vh_swap_slot_cache_active - __tracepoint_android_rvh_drain_slots_cache_cpu + __tracepoint_android_vh_cow_user_page __tracepoint_android_vh_drain_slots_cache_cpu - __tracepoint_android_rvh_alloc_swap_slot_cache - __tracepoint_android_vh_alloc_swap_slot_cache - __tracepoint_android_rvh_free_swap_slot - __tracepoint_android_vh_free_swap_slot - __tracepoint_android_rvh_get_swap_page - __tracepoint_android_vh_get_swap_page - __tracepoint_android_vh_page_isolated_for_reclaim - __tracepoint_android_vh_inactive_is_low - __tracepoint_android_vh_snapshot_refaults - __tracepoint_android_vh_account_swap_pages - __tracepoint_android_vh_unuse_swap_page - __tracepoint_android_vh_init_swap_info_struct - __tracepoint_android_vh_si_swapinfo - __tracepoint_android_rvh_alloc_si - __tracepoint_android_vh_alloc_si __tracepoint_android_vh_free_pages - __tracepoint_android_vh_set_shmem_page_flag + __tracepoint_android_vh_free_swap_slot + __tracepoint_android_vh_get_swap_page + __tracepoint_android_vh_handle_pte_fault_end + __tracepoint_android_vh_inactive_is_low + __tracepoint_android_vh_init_swap_info_struct + __tracepoint_android_vh_migrate_page_states + __tracepoint_android_vh_page_isolated_for_reclaim + __tracepoint_android_vh_page_referenced_one_end __tracepoint_android_vh_ra_tuning_max_page + __tracepoint_android_vh_set_shmem_page_flag + __tracepoint_android_vh_si_swapinfo + __tracepoint_android_vh_snapshot_refaults + __tracepoint_android_vh_swapin_add_anon_rmap + __tracepoint_android_vh_swap_slot_cache_active + __tracepoint_android_vh_unuse_swap_page + __tracepoint_android_vh_waiting_for_page_migration + zero_pfn diff --git a/android/abi_gki_aarch64_type_visibility b/android/abi_gki_aarch64_type_visibility index 705bf5574222..97a077fdf46e 100644 --- a/android/abi_gki_aarch64_type_visibility +++ b/android/abi_gki_aarch64_type_visibility @@ -1,6 +1,6 @@ [abi_symbol_list] # for type visibility - GKI_struct_selinux_state GKI_struct_gic_chip_data + GKI_struct_selinux_state GKI_struct_swap_slots_cache diff --git a/android/abi_gki_aarch64_vivo b/android/abi_gki_aarch64_vivo index 28c4b05aa43f..9b890ada7ad6 100644 --- a/android/abi_gki_aarch64_vivo +++ b/android/abi_gki_aarch64_vivo @@ -84,9 +84,9 @@ blocking_notifier_call_chain blocking_notifier_chain_register blocking_notifier_chain_unregister - bpf_trace_run1 bpf_trace_run10 bpf_trace_run12 + bpf_trace_run1 bpf_trace_run2 bpf_trace_run3 bpf_trace_run4 @@ -938,8 +938,8 @@ mempool_free mempool_free_slab memremap - memset memset64 + memset __memset_io memstart_addr memunmap @@ -975,8 +975,8 @@ __next_zones_zonelist nla_find nla_put - nla_reserve nla_reserve_64bit + nla_reserve __nla_validate __nlmsg_put no_llseek diff --git a/android/abi_gki_aarch64_xiaomi b/android/abi_gki_aarch64_xiaomi index ded2c5464994..67c83533d643 100644 --- a/android/abi_gki_aarch64_xiaomi +++ b/android/abi_gki_aarch64_xiaomi @@ -2,8 +2,8 @@ # commonly used symbols # required by touch module - proc_mkdir_data proc_create_seq_private + proc_mkdir_data # required by aw8697-haptic.ko devm_gpio_free @@ -11,36 +11,43 @@ i2c_smbus_write_byte_data #required by memory module - blk_execute_rq - blk_rq_map_kern - scsi_device_lookup - scsi_host_lookup - scsi_host_put - ufshcd_read_desc_param - utf16s_to_utf8s async_schedule_node + blk_execute_rq + blk_ksm_get_slot_idx blk_ksm_register blk_ksm_reprogram_all_keys blk_mq_alloc_tag_set + blk_mq_free_tag_set blk_mq_init_queue blk_mq_tagset_busy_iter + blk_queue_update_dma_alignment + blk_queue_update_dma_pad + blk_rq_map_kern bsg_job_done bsg_remove_queue bsg_setup_queue dev_pm_opp_remove + mempool_alloc_pages + mempool_free_pages + mempool_resize + __scsi_add_device scsi_add_host_with_dma scsi_block_requests + scsi_change_queue_depth + scsi_device_lookup + scsi_dma_map scsi_dma_unmap + __scsi_execute + scsi_host_alloc + scsi_host_lookup + scsi_host_put scsi_is_host_device + scsi_normalize_sense + scsi_print_command scsi_remove_host scsi_report_bus_reset scsi_scan_host scsi_unblock_requests - scsi_change_queue_depth - scsi_print_command - scsi_dma_map - scsi_host_alloc - scsi_normalize_sense sg_copy_from_buffer sg_copy_to_buffer ufshcd_alloc_host @@ -51,44 +58,40 @@ ufshcd_map_desc_id_to_length ufshcd_query_attr_retry ufshcd_query_flag_retry + ufshcd_read_desc_param ufshcd_update_evt_hist + utf16s_to_utf8s wait_for_completion_io_timeout - __scsi_add_device - __scsi_execute - blk_mq_free_tag_set - blk_queue_update_dma_alignment - blk_queue_update_dma_pad - blk_ksm_get_slot_idx - mempool_resize - mempool_alloc_pages - mempool_free_pages #required by cs35l41 module - regmap_raw_write_async - snd_soc_bytes_tlv_callback + regcache_drop_region regmap_async_complete + regmap_multi_reg_write + regmap_multi_reg_write_bypassed + regmap_raw_read + regmap_raw_write + regmap_raw_write_async + regulator_bulk_enable snd_compr_stop_error - snd_soc_component_disable_pin - snd_soc_component_force_enable_pin + snd_ctl_boolean_mono_info snd_pcm_format_physical_width snd_pcm_hw_constraint_list - regmap_multi_reg_write_bypassed - snd_ctl_boolean_mono_info - snd_soc_put_volsw_range + snd_soc_bytes_tlv_callback + snd_soc_component_disable_pin + snd_soc_component_force_enable_pin snd_soc_get_volsw_range snd_soc_info_volsw_range - regmap_raw_write - regcache_drop_region - regmap_raw_read - regmap_multi_reg_write - regulator_bulk_enable + snd_soc_put_volsw_range #required by mtd module - __blk_mq_end_request balance_dirty_pages_ratelimited bdi_alloc bdi_put bdi_register + blkdev_get_by_dev + blkdev_get_by_path + blkdev_put + __blk_mq_end_request blk_mq_freeze_queue blk_mq_init_sq_queue blk_mq_quiesce_queue @@ -97,9 +100,6 @@ blk_mq_unquiesce_queue blk_queue_write_cache blk_update_request - blkdev_get_by_dev - blkdev_get_by_path - blkdev_put deactivate_locked_super fixed_size_llseek generic_shutdown_super @@ -126,42 +126,42 @@ #required by millet.ko freezer_cgrp_subsys - __traceiter_android_vh_do_send_sig_info - __traceiter_android_vh_binder_preset - __traceiter_android_vh_binder_wait_for_work - __traceiter_android_vh_binder_trans - __traceiter_android_vh_binder_reply __traceiter_android_vh_binder_alloc_new_buf_locked - __tracepoint_android_vh_do_send_sig_info - __tracepoint_android_vh_binder_preset - __tracepoint_android_vh_binder_wait_for_work - __tracepoint_android_vh_binder_trans - __tracepoint_android_vh_binder_reply + __traceiter_android_vh_binder_preset + __traceiter_android_vh_binder_reply + __traceiter_android_vh_binder_trans + __traceiter_android_vh_binder_wait_for_work + __traceiter_android_vh_do_send_sig_info __tracepoint_android_vh_binder_alloc_new_buf_locked + __tracepoint_android_vh_binder_preset + __tracepoint_android_vh_binder_reply + __tracepoint_android_vh_binder_trans + __tracepoint_android_vh_binder_wait_for_work + __tracepoint_android_vh_do_send_sig_info #required by mi_sched.ko + find_user + free_uid + jiffies_64 __traceiter_android_vh_free_task __tracepoint_android_vh_free_task - jiffies_64 - free_uid - find_user #required by migt.ko - __traceiter_android_rvh_after_enqueue_task __traceiter_android_rvh_after_dequeue_task + __traceiter_android_rvh_after_enqueue_task __traceiter_android_vh_map_util_freq - __tracepoint_android_rvh_after_enqueue_task __tracepoint_android_rvh_after_dequeue_task + __tracepoint_android_rvh_after_enqueue_task __tracepoint_android_vh_map_util_freq #required by turbo.ko + cpuset_cpus_allowed + __traceiter_android_rvh_cpuset_fork __traceiter_android_rvh_set_cpus_allowed_comm __traceiter_android_vh_sched_setaffinity_early - __traceiter_android_rvh_cpuset_fork + __tracepoint_android_rvh_cpuset_fork __tracepoint_android_rvh_set_cpus_allowed_comm __tracepoint_android_vh_sched_setaffinity_early - __tracepoint_android_rvh_cpuset_fork - cpuset_cpus_allowed #required by fas.ko __traceiter_android_rvh_check_preempt_tick @@ -175,15 +175,15 @@ console_printk #required by binderinfo.ko module - __traceiter_android_vh_binder_transaction_init __traceiter_android_vh_binder_print_transaction_info - __tracepoint_android_vh_binder_transaction_init + __traceiter_android_vh_binder_transaction_init __tracepoint_android_vh_binder_print_transaction_info + __tracepoint_android_vh_binder_transaction_init #required by reclaim module __traceiter_android_vh_tune_scan_type - __tracepoint_android_vh_tune_scan_type __traceiter_android_vh_tune_swappiness + __tracepoint_android_vh_tune_scan_type __tracepoint_android_vh_tune_swappiness #required by msm_drm.ko module @@ -198,19 +198,19 @@ ##required by xm_power_debug.ko module wakeup_sources_read_lock wakeup_sources_read_unlock - wakeup_sources_walk_start wakeup_sources_walk_next + wakeup_sources_walk_start #required by mi_mempool.ko module - __traceiter_android_vh_mmput - __tracepoint_android_vh_mmput - __traceiter_android_vh_alloc_pages_reclaim_bypass - __tracepoint_android_vh_alloc_pages_reclaim_bypass __traceiter_android_vh_alloc_pages_failure_bypass + __traceiter_android_vh_alloc_pages_reclaim_bypass + __traceiter_android_vh_mmput __tracepoint_android_vh_alloc_pages_failure_bypass + __tracepoint_android_vh_alloc_pages_reclaim_bypass + __tracepoint_android_vh_mmput #required by us_prox.ko module iio_trigger_alloc - __iio_trigger_register iio_trigger_free + __iio_trigger_register iio_trigger_unregister From 4d70900718765404719e83be71e98ddbe655e1b6 Mon Sep 17 00:00:00 2001 From: Giuliano Procida Date: Wed, 3 May 2023 09:23:36 +0100 Subject: [PATCH 2665/4345] ANDROID: GKI: add missing vendor hook and other ktrace symbols For each traceiter or tracepoint symbol in a section of a symbol list, this change ensures its partner is also present in the same section. 38 function symbol(s) added 'int __traceiter_android_rvh_arm64_serror_panic(void*, struct pt_regs*, unsigned int)' 'int __traceiter_android_rvh_bad_mode(void*, struct pt_regs*, unsigned int, int)' 'int __traceiter_android_rvh_dequeue_task_idle(void*, struct task_struct*)' 'int __traceiter_android_rvh_do_ptrauth_fault(void*, struct pt_regs*, unsigned int, bool)' 'int __traceiter_android_rvh_do_sea(void*, struct pt_regs*, unsigned int, unsigned long int, const char*)' 'int __traceiter_android_rvh_do_undefinstr(void*, struct pt_regs*, bool)' 'int __traceiter_android_rvh_refrigerator(void*, bool)' 'int __traceiter_android_rvh_tcp_recvmsg(void*, struct sock*)' 'int __traceiter_android_rvh_tcp_recvmsg_stat(void*, struct sock*, int)' 'int __traceiter_android_rvh_tcp_sendmsg_locked(void*, struct sock*, int)' 'int __traceiter_android_rvh_udp_recvmsg(void*, struct sock*)' 'int __traceiter_android_rvh_udp_sendmsg(void*, struct sock*)' 'int __traceiter_android_vh_disable_thermal_cooling_stats(void*, struct thermal_cooling_device*, bool*)' 'int __traceiter_android_vh_dup_task_struct(void*, struct task_struct*, struct task_struct*)' 'int __traceiter_android_vh_handle_tlb_conf(void*, unsigned long int, unsigned int, int*)' 'int __traceiter_android_vh_irqtime_account_process_tick(void*, struct task_struct*, struct rq*, int, int)' 'int __traceiter_android_vh_madvise_cold_or_pageout(void*, struct vm_area_struct*, bool*)' 'int __traceiter_android_vh_oom_check_panic(void*, struct oom_control*, int*)' 'int __traceiter_android_vh_psi_event(void*, struct psi_trigger*)' 'int __traceiter_android_vh_psi_group(void*, struct psi_group*)' 'int __traceiter_android_vh_rtmutex_wait_finish(void*, struct rt_mutex*)' 'int __traceiter_android_vh_rtmutex_wait_start(void*, struct rt_mutex*)' 'int __traceiter_android_vh_rwsem_read_wait_finish(void*, struct rw_semaphore*)' 'int __traceiter_android_vh_rwsem_read_wait_start(void*, struct rw_semaphore*)' 'int __traceiter_android_vh_rwsem_write_wait_finish(void*, struct rw_semaphore*)' 'int __traceiter_android_vh_rwsem_write_wait_start(void*, struct rw_semaphore*)' 'int __traceiter_android_vh_sched_show_task(void*, struct task_struct*)' 'int __traceiter_android_vh_shmem_alloc_page(void*, struct page**)' 'int __traceiter_android_vh_subpage_dma_contig_alloc(void*, bool*, struct device*, size_t*)' 'int __traceiter_android_vh_try_to_freeze_todo(void*, unsigned int, unsigned int, bool)' 'int __traceiter_android_vh_try_to_freeze_todo_unfrozen(void*, struct task_struct*)' 'int __traceiter_android_vh_vmpressure(void*, struct mem_cgroup*, bool*)' 'int __traceiter_android_vh_watchdog_timer_softlockup(void*, int, struct pt_regs*, bool)' 'int __traceiter_android_vh_wq_lockup_pool(void*, int, unsigned long int)' 'int __traceiter_net_dev_queue(void*, struct sk_buff*)' 'int __traceiter_net_dev_xmit(void*, struct sk_buff*, int, struct net_device*, unsigned int)' 'int __traceiter_netif_receive_skb(void*, struct sk_buff*)' 'int __traceiter_netif_rx(void*, struct sk_buff*)' Bug: 280431338 Change-Id: Id46fa6a5f9d7923897e29a46d39d9d17c6d2fa9a Signed-off-by: Giuliano Procida --- android/abi_gki_aarch64.xml | 522 ++++++++++++++++++++++++++------- android/abi_gki_aarch64_galaxy | 47 +++ android/abi_gki_aarch64_mtk | 1 + android/abi_gki_aarch64_oplus | 4 + android/abi_gki_aarch64_qcom | 13 + android/abi_gki_aarch64_unisoc | 3 + android/abi_gki_aarch64_vivo | 13 + 7 files changed, 500 insertions(+), 103 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index f67fa1192d73..6a06ed9aaa13 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -307,6 +307,8 @@ + + @@ -322,11 +324,15 @@ + + + + @@ -357,6 +363,7 @@ + @@ -386,6 +393,9 @@ + + + @@ -393,6 +403,8 @@ + + @@ -472,6 +484,7 @@ + @@ -480,6 +493,7 @@ + @@ -514,6 +528,7 @@ + @@ -524,6 +539,7 @@ + @@ -533,6 +549,7 @@ + @@ -558,6 +575,7 @@ + @@ -571,6 +589,8 @@ + + @@ -582,11 +602,15 @@ + + + + @@ -594,10 +618,13 @@ + + + @@ -618,6 +645,7 @@ + @@ -631,6 +659,7 @@ + @@ -639,6 +668,8 @@ + + @@ -666,7 +697,10 @@ + + + @@ -703,6 +737,10 @@ + + + + @@ -9739,6 +9777,41 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -10645,7 +10718,7 @@ - + @@ -13946,7 +14019,7 @@ - + @@ -18720,42 +18793,42 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -25950,6 +26023,7 @@ + @@ -27308,7 +27382,7 @@ - + @@ -29387,18 +29461,18 @@ - + - + - + - + - + @@ -33250,7 +33324,7 @@ - + @@ -40888,18 +40962,18 @@ - + - + - + - + - + @@ -42924,6 +42998,13 @@ + + + + + + + @@ -44532,23 +44613,7 @@ - - - - - - - - - - - - - - - - - + @@ -47445,7 +47510,7 @@ - + @@ -48241,6 +48306,16 @@ + + + + + + + + + + @@ -48878,7 +48953,6 @@ - @@ -52438,6 +52512,20 @@ + + + + + + + + + + + + + + @@ -53822,13 +53910,6 @@ - - - - - - - @@ -62584,7 +62665,7 @@ - + @@ -64249,6 +64330,7 @@ + @@ -66488,13 +66570,6 @@ - - - - - - - @@ -68164,18 +68239,18 @@ - + - + - + - + - + @@ -78094,7 +78169,7 @@ - + @@ -84503,6 +84578,32 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -91260,7 +91361,6 @@ - @@ -95433,6 +95533,7 @@ + @@ -96091,24 +96192,24 @@ - + - + - + - + - + - + - + @@ -103027,12 +103128,6 @@ - - - - - - @@ -104649,7 +104744,7 @@ - + @@ -111181,6 +111276,7 @@ + @@ -111278,7 +111374,6 @@ - @@ -118124,6 +118219,19 @@ + + + + + + + + + + + + + @@ -118228,6 +118336,11 @@ + + + + + @@ -118250,11 +118363,26 @@ + + + + + + + + + + + + + + + @@ -118263,6 +118391,12 @@ + + + + + + @@ -118463,6 +118597,11 @@ + + + + + @@ -118645,6 +118784,23 @@ + + + + + + + + + + + + + + + + + @@ -118689,6 +118845,16 @@ + + + + + + + + + + @@ -119223,6 +119389,12 @@ + + + + + + @@ -119283,6 +119455,12 @@ + + + + + + @@ -119494,6 +119672,13 @@ + + + + + + + @@ -119561,6 +119746,14 @@ + + + + + + + + @@ -119617,6 +119810,12 @@ + + + + + + @@ -119769,6 +119968,12 @@ + + + + + + @@ -119850,6 +120055,16 @@ + + + + + + + + + + @@ -119917,6 +120132,16 @@ + + + + + + + + + + @@ -119950,6 +120175,16 @@ + + + + + + + + + + @@ -119985,6 +120220,16 @@ + + + + + + + + + + @@ -120011,6 +120256,11 @@ + + + + + @@ -120127,6 +120377,11 @@ + + + + + @@ -120205,6 +120460,13 @@ + + + + + + + @@ -120251,6 +120513,18 @@ + + + + + + + + + + + + @@ -120435,11 +120709,30 @@ + + + + + + + + + + + + + + + + + + + @@ -120659,6 +120952,29 @@ + + + + + + + + + + + + + + + + + + + + + + + @@ -123575,8 +123891,8 @@ - - + + @@ -130526,10 +130842,10 @@ - - - - + + + + @@ -140701,8 +141017,8 @@ - - + + @@ -145795,8 +146111,8 @@ - - + + @@ -146172,11 +146488,11 @@ - - - - - + + + + + @@ -146658,9 +146974,9 @@ - - - + + + @@ -146709,8 +147025,8 @@ - - + + diff --git a/android/abi_gki_aarch64_galaxy b/android/abi_gki_aarch64_galaxy index 6b921ab3a901..db5abff44b22 100644 --- a/android/abi_gki_aarch64_galaxy +++ b/android/abi_gki_aarch64_galaxy @@ -3712,6 +3712,8 @@ trace_event_reg trace_handle_return __traceiter_android_rvh_account_irq + __traceiter_android_rvh_arm64_serror_panic + __traceiter_android_rvh_bad_mode __traceiter_android_rvh_build_perf_domains __traceiter_android_rvh_can_migrate_task __traceiter_android_rvh_check_preempt_wakeup @@ -3721,9 +3723,12 @@ __traceiter_android_rvh_cpufreq_transition __traceiter_android_rvh_cpu_overutilized __traceiter_android_rvh_dequeue_task + __traceiter_android_rvh_dequeue_task_idle __traceiter_android_rvh_die_kernel_fault __traceiter_android_rvh_do_mem_abort + __traceiter_android_rvh_do_sea __traceiter_android_rvh_do_sp_pc_abort + __traceiter_android_rvh_do_undefinstr __traceiter_android_rvh_enqueue_task __traceiter_android_rvh_find_busiest_queue __traceiter_android_rvh_find_energy_efficient_cpu @@ -3777,6 +3782,7 @@ __traceiter_android_vh_binder_set_priority __traceiter_android_vh_binder_transaction_init __traceiter_android_vh_binder_wakeup_ilocked + __traceiter_android_vh_cgroup_attach __traceiter_android_vh_cma_alloc_finish __traceiter_android_vh_cma_alloc_start __traceiter_android_vh_cpu_idle_enter @@ -3798,10 +3804,19 @@ __traceiter_android_vh_logbuf __traceiter_android_vh_logbuf_pr_cont __traceiter_android_vh_meminfo_proc_show + __traceiter_android_vh_mutex_wait_finish + __traceiter_android_vh_mutex_wait_start __traceiter_android_vh_pagecache_get_page __traceiter_android_vh_printk_hotplug __traceiter_android_vh_ptype_head __traceiter_android_vh_rmqueue + __traceiter_android_vh_rtmutex_wait_finish + __traceiter_android_vh_rtmutex_wait_start + __traceiter_android_vh_rwsem_read_wait_finish + __traceiter_android_vh_rwsem_read_wait_start + __traceiter_android_vh_rwsem_write_wait_finish + __traceiter_android_vh_rwsem_write_wait_start + __traceiter_android_vh_sched_show_task __traceiter_android_vh_scheduler_tick __traceiter_android_vh_show_max_freq __traceiter_android_vh_show_mem @@ -3809,6 +3824,8 @@ __traceiter_android_vh_show_suspend_epoch_val __traceiter_android_vh_timer_calc_index __traceiter_android_vh_timerfd_create + __traceiter_android_vh_try_to_freeze_todo + __traceiter_android_vh_try_to_freeze_todo_unfrozen __traceiter_android_vh_typec_store_partner_src_caps __traceiter_android_vh_typec_tcpci_override_toggling __traceiter_android_vh_typec_tcpm_adj_current_limit @@ -3822,14 +3839,44 @@ __traceiter_android_vh_ufs_send_uic_command __traceiter_android_vh_ufs_update_sdev __traceiter_android_vh_ufs_update_sysfs + __traceiter_android_vh_watchdog_timer_softlockup + __traceiter_android_vh_wq_lockup_pool + __traceiter_binder_transaction_received __traceiter_clock_set_rate __traceiter_cpu_frequency + __traceiter_cpu_frequency_limits + __traceiter_cpu_idle + __traceiter_device_pm_callback_end + __traceiter_device_pm_callback_start __traceiter_dma_fence_emit + __traceiter_dwc3_ep_queue __traceiter_dwc3_readl __traceiter_dwc3_writel __traceiter_gpu_mem_total + __traceiter_hrtimer_expire_entry + __traceiter_hrtimer_expire_exit + __traceiter_ipi_entry + __traceiter_ipi_exit + __traceiter_ipi_raise + __traceiter_irq_handler_entry + __traceiter_irq_handler_exit __traceiter_kfree_skb + __traceiter_pelt_cfs_tp + __traceiter_pelt_dl_tp + __traceiter_pelt_irq_tp + __traceiter_pelt_rt_tp + __traceiter_pelt_se_tp + __traceiter_rwmmio_post_read + __traceiter_rwmmio_read + __traceiter_rwmmio_write + __traceiter_sched_cpu_capacity_tp + __traceiter_sched_overutilized_tp + __traceiter_sched_switch + __traceiter_sched_util_est_cfs_tp __traceiter_sched_util_est_se_tp + __traceiter_suspend_resume + __traceiter_workqueue_execute_end + __traceiter_workqueue_execute_start __traceiter_xdp_exception trace_output_call __tracepoint_android_rvh_account_irq diff --git a/android/abi_gki_aarch64_mtk b/android/abi_gki_aarch64_mtk index 5473f314864b..2ac7b11faf77 100644 --- a/android/abi_gki_aarch64_mtk +++ b/android/abi_gki_aarch64_mtk @@ -3142,6 +3142,7 @@ __traceiter_android_vh_snd_soc_card_get_comp_chain __traceiter_android_vh_sound_usb_support_cpu_suspend __traceiter_android_vh_syscall_prctl_finished + __traceiter_android_vh_ufs_update_sdev __traceiter_android_vh_v4l2subdev_set_fmt __traceiter_android_vh_v4l2subdev_set_frame_interval __traceiter_android_vh_v4l2subdev_set_selection diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index b1b464d893fe..9544ea84c8f1 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -2925,6 +2925,10 @@ __traceiter_ipi_entry __traceiter_ipi_raise __traceiter_irq_handler_entry + __traceiter_net_dev_queue + __traceiter_net_dev_xmit + __traceiter_netif_receive_skb + __traceiter_netif_rx __traceiter_pelt_se_tp __traceiter_rwmmio_post_read __traceiter_rwmmio_read diff --git a/android/abi_gki_aarch64_qcom b/android/abi_gki_aarch64_qcom index bc5d94e3630a..b269c937101c 100644 --- a/android/abi_gki_aarch64_qcom +++ b/android/abi_gki_aarch64_qcom @@ -2514,6 +2514,7 @@ __traceiter_android_rvh_cpu_cgroup_online __traceiter_android_rvh_cpufreq_transition __traceiter_android_rvh_dequeue_task + __traceiter_android_rvh_do_ptrauth_fault __traceiter_android_rvh_do_sched_yield __traceiter_android_rvh_enqueue_task __traceiter_android_rvh_find_busiest_queue @@ -2561,14 +2562,18 @@ __traceiter_android_rvh_update_misfit_status __traceiter_android_rvh_wake_up_new_task __traceiter_android_vh_allow_domain_state + __traceiter_android_vh_alter_rwsem_list_add __traceiter_android_vh_binder_restore_priority __traceiter_android_vh_binder_set_priority __traceiter_android_vh_binder_transaction_init __traceiter_android_vh_binder_wakeup_ilocked + __traceiter_android_vh_check_uninterruptible_tasks + __traceiter_android_vh_check_uninterruptible_tasks_dn __traceiter_android_vh_cpu_idle_enter __traceiter_android_vh_cpu_idle_exit __traceiter_android_vh_cpuidle_psci_enter __traceiter_android_vh_cpuidle_psci_exit + __traceiter_android_vh_disable_thermal_cooling_stats __traceiter_android_vh_dump_throttled_rt_tasks __traceiter_android_vh_freq_table_limits __traceiter_android_vh_ftrace_dump_buffer @@ -2578,18 +2583,26 @@ __traceiter_android_vh_ftrace_size_check __traceiter_android_vh_gic_resume __traceiter_android_vh_gpio_block_read + __traceiter_android_vh_handle_tlb_conf __traceiter_android_vh_iommu_setup_dma_ops __traceiter_android_vh_ipi_stop __traceiter_android_vh_jiffies_update __traceiter_android_vh_logbuf __traceiter_android_vh_logbuf_pr_cont + __traceiter_android_vh_madvise_cold_or_pageout + __traceiter_android_vh_oom_check_panic __traceiter_android_vh_printk_hotplug + __traceiter_android_vh_process_killed + __traceiter_android_vh_psi_event + __traceiter_android_vh_psi_group __traceiter_android_vh_rproc_recovery __traceiter_android_vh_rproc_recovery_set __traceiter_android_vh_scheduler_tick + __traceiter_android_vh_shmem_alloc_page __traceiter_android_vh_show_max_freq __traceiter_android_vh_show_resume_epoch_val __traceiter_android_vh_show_suspend_epoch_val + __traceiter_android_vh_subpage_dma_contig_alloc __traceiter_android_vh_timer_calc_index __traceiter_android_vh_ufs_check_int_errors __traceiter_android_vh_ufs_clock_scaling diff --git a/android/abi_gki_aarch64_unisoc b/android/abi_gki_aarch64_unisoc index d065398a5fd0..ec061835a335 100644 --- a/android/abi_gki_aarch64_unisoc +++ b/android/abi_gki_aarch64_unisoc @@ -254,6 +254,9 @@ __tasklet_schedule thermal_zone_device_disable thermal_zone_device_enable + __traceiter_rwmmio_post_read + __traceiter_rwmmio_read + __traceiter_rwmmio_write __tracepoint_rwmmio_post_read __tracepoint_rwmmio_read __tracepoint_rwmmio_write diff --git a/android/abi_gki_aarch64_vivo b/android/abi_gki_aarch64_vivo index 9b890ada7ad6..9143afa6c2dc 100644 --- a/android/abi_gki_aarch64_vivo +++ b/android/abi_gki_aarch64_vivo @@ -1687,6 +1687,7 @@ __traceiter_android_rvh_flush_task __traceiter_android_rvh_migrate_queued_task __traceiter_android_rvh_new_task_stats + __traceiter_android_rvh_refrigerator __traceiter_android_rvh_replace_next_task_fair __traceiter_android_rvh_resume_cpus __traceiter_android_rvh_sched_cpu_dying @@ -1704,22 +1705,30 @@ __traceiter_android_rvh_set_readahead_gfp_mask __traceiter_android_rvh_set_skip_swapcache_flags __traceiter_android_rvh_set_task_cpu + __traceiter_android_rvh_tcp_recvmsg + __traceiter_android_rvh_tcp_recvmsg_stat + __traceiter_android_rvh_tcp_sendmsg_locked __traceiter_android_rvh_tick_entry __traceiter_android_rvh_try_to_wake_up __traceiter_android_rvh_try_to_wake_up_success __traceiter_android_rvh_ttwu_cond + __traceiter_android_rvh_udp_recvmsg + __traceiter_android_rvh_udp_sendmsg __traceiter_android_rvh_update_cpu_capacity __traceiter_android_rvh_update_cpus_allowed __traceiter_android_rvh_update_misfit_status __traceiter_android_rvh_wake_up_new_task + __traceiter_android_vh_account_task_time __traceiter_android_vh_allow_domain_state __traceiter_android_vh_binder_restore_priority __traceiter_android_vh_binder_set_priority + __traceiter_android_vh_binder_trans __traceiter_android_vh_binder_wakeup_ilocked __traceiter_android_vh_blk_alloc_rqs __traceiter_android_vh_blk_rq_ctx_init __traceiter_android_vh_cpu_idle_enter __traceiter_android_vh_cpu_idle_exit + __traceiter_android_vh_dup_task_struct __traceiter_android_vh_filemap_fault_cache_page __traceiter_android_vh_filemap_fault_get_page __traceiter_android_vh_ftrace_dump_buffer @@ -1729,6 +1738,7 @@ __traceiter_android_vh_ftrace_size_check __traceiter_android_vh_iommu_setup_dma_ops __traceiter_android_vh_ipi_stop + __traceiter_android_vh_irqtime_account_process_tick __traceiter_android_vh_jiffies_update __traceiter_android_vh_mmap_region __traceiter_android_vh_mmc_attach_sd @@ -1746,10 +1756,13 @@ __traceiter_android_vh_shrink_slab_bypass __traceiter_android_vh_timer_calc_index __traceiter_android_vh_try_to_unmap_one + __traceiter_android_vh_tune_scan_type + __traceiter_android_vh_tune_swappiness __traceiter_android_vh_ufs_check_int_errors __traceiter_android_vh_ufs_compl_command __traceiter_android_vh_ufs_send_command __traceiter_android_vh_ufs_update_sdev + __traceiter_android_vh_vmpressure __traceiter_binder_transaction_received __traceiter_block_bio_complete __traceiter_block_bio_queue From ce88d51c722f26f604abdaa4b105d37172ee51ae Mon Sep 17 00:00:00 2001 From: Alistair Delva Date: Fri, 28 Apr 2023 09:52:58 -0700 Subject: [PATCH 2666/4345] ANDROID: GKI: Increase max 8250 uarts Some boards need more than the default maximum of 4 uarts. This has no impact unless 8250.nr_uarts is specified on the cmdline to increase the number of runtime uarts from the GKI default of 0. Bug: 280015873 Signed-off-by: Alistair Delva Change-Id: I5ba4e1dcce4f4e01b7d306fa3ab05319768eef00 --- arch/arm64/configs/gki_defconfig | 1 + arch/x86/configs/gki_defconfig | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/arm64/configs/gki_defconfig b/arch/arm64/configs/gki_defconfig index d82e363ddff8..8fa037f86347 100644 --- a/arch/arm64/configs/gki_defconfig +++ b/arch/arm64/configs/gki_defconfig @@ -373,6 +373,7 @@ CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_SERIAL_8250_EXAR is not set +CONFIG_SERIAL_8250_NR_UARTS=32 CONFIG_SERIAL_8250_RUNTIME_UARTS=0 CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_AMBA_PL011=y diff --git a/arch/x86/configs/gki_defconfig b/arch/x86/configs/gki_defconfig index 63419263e5ac..9507ff815d82 100644 --- a/arch/x86/configs/gki_defconfig +++ b/arch/x86/configs/gki_defconfig @@ -343,6 +343,7 @@ CONFIG_INPUT_UINPUT=y CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=32 CONFIG_SERIAL_8250_RUNTIME_UARTS=0 CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_SAMSUNG=y From 66cba6260a95c3bfa1f8db0e77b10c0bacfab4b6 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Fri, 5 May 2023 06:48:10 +0000 Subject: [PATCH 2667/4345] FROMLIST: binder: fix UAF caused by faulty buffer cleanup In binder_transaction_buffer_release() the 'failed_at' offset indicates the number of objects to clean up. However, this function was changed by commit 44d8047f1d87 ("binder: use standard functions to allocate fds"), to release all the objects in the buffer when 'failed_at' is zero. This introduced an issue when a transaction buffer is released without any objects having been processed so far. In this case, 'failed_at' is indeed zero yet it is misinterpreted as releasing the entire buffer. This leads to use-after-free errors where nodes are incorrectly freed and subsequently accessed. Such is the case in the following KASAN report: ================================================================== BUG: KASAN: slab-use-after-free in binder_thread_read+0xc40/0x1f30 Read of size 8 at addr ffff4faf037cfc58 by task poc/474 CPU: 6 PID: 474 Comm: poc Not tainted 6.3.0-12570-g7df047b3f0aa #5 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x94/0xec show_stack+0x18/0x24 dump_stack_lvl+0x48/0x60 print_report+0xf8/0x5b8 kasan_report+0xb8/0xfc __asan_load8+0x9c/0xb8 binder_thread_read+0xc40/0x1f30 binder_ioctl+0xd9c/0x1768 __arm64_sys_ioctl+0xd4/0x118 invoke_syscall+0x60/0x188 [...] Allocated by task 474: kasan_save_stack+0x3c/0x64 kasan_set_track+0x2c/0x40 kasan_save_alloc_info+0x24/0x34 __kasan_kmalloc+0xb8/0xbc kmalloc_trace+0x48/0x5c binder_new_node+0x3c/0x3a4 binder_transaction+0x2b58/0x36f0 binder_thread_write+0x8e0/0x1b78 binder_ioctl+0x14a0/0x1768 __arm64_sys_ioctl+0xd4/0x118 invoke_syscall+0x60/0x188 [...] Freed by task 475: kasan_save_stack+0x3c/0x64 kasan_set_track+0x2c/0x40 kasan_save_free_info+0x38/0x5c __kasan_slab_free+0xe8/0x154 __kmem_cache_free+0x128/0x2bc kfree+0x58/0x70 binder_dec_node_tmpref+0x178/0x1fc binder_transaction_buffer_release+0x430/0x628 binder_transaction+0x1954/0x36f0 binder_thread_write+0x8e0/0x1b78 binder_ioctl+0x14a0/0x1768 __arm64_sys_ioctl+0xd4/0x118 invoke_syscall+0x60/0x188 [...] ================================================================== In order to avoid these issues, let's always calculate the intended 'failed_at' offset beforehand. This is renamed and wrapped in a helper function to make it clear and convenient. Fixes: 32e9f56a96d8 ("binder: don't detect sender/target during buffer cleanup") Reported-by: Zi Fan Tan Link: https://b.corp.google.com/issues/275041864 Cc: stable@vger.kernel.org Signed-off-by: Carlos Llamas Bug: 275041864 Link: https://lore.kernel.org/all/20230505203020.4101154-1-cmllamas@google.com Change-Id: I4bcc8bde77a8118872237d100cccb5caf95d99a1 Signed-off-by: Carlos Llamas --- drivers/android/binder.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 66152cc321a9..75072d3bc98c 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2034,24 +2034,23 @@ static void binder_deferred_fd_close(int fd) static void binder_transaction_buffer_release(struct binder_proc *proc, struct binder_thread *thread, struct binder_buffer *buffer, - binder_size_t failed_at, + binder_size_t off_end_offset, bool is_failure) { int debug_id = buffer->debug_id; - binder_size_t off_start_offset, buffer_offset, off_end_offset; + binder_size_t off_start_offset, buffer_offset; binder_debug(BINDER_DEBUG_TRANSACTION, "%d buffer release %d, size %zd-%zd, failed at %llx\n", proc->pid, buffer->debug_id, buffer->data_size, buffer->offsets_size, - (unsigned long long)failed_at); + (unsigned long long)off_end_offset); if (buffer->target_node) binder_dec_node(buffer->target_node, 1, 0); off_start_offset = ALIGN(buffer->data_size, sizeof(void *)); - off_end_offset = is_failure && failed_at ? failed_at : - off_start_offset + buffer->offsets_size; + for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { struct binder_object_header *hdr; @@ -2211,6 +2210,21 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, } } +/* Clean up all the objects in the buffer */ +static inline void binder_release_entire_buffer(struct binder_proc *proc, + struct binder_thread *thread, + struct binder_buffer *buffer, + bool is_failure) +{ + binder_size_t off_end_offset; + + off_end_offset = ALIGN(buffer->data_size, sizeof(void *)); + off_end_offset += buffer->offsets_size; + + binder_transaction_buffer_release(proc, thread, buffer, + off_end_offset, is_failure); +} + static int binder_translate_binder(struct flat_binder_object *fp, struct binder_transaction *t, struct binder_thread *thread) @@ -2916,7 +2930,7 @@ static int binder_proc_transaction(struct binder_transaction *t, t_outdated->buffer = NULL; buffer->transaction = NULL; trace_binder_transaction_update_buffer_release(buffer); - binder_transaction_buffer_release(proc, NULL, buffer, 0, 0); + binder_release_entire_buffer(proc, NULL, buffer, false); binder_alloc_free_buf(&proc->alloc, buffer); kfree(t_outdated); binder_stats_deleted(BINDER_STAT_TRANSACTION); @@ -3830,7 +3844,7 @@ binder_free_buf(struct binder_proc *proc, binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); - binder_transaction_buffer_release(proc, thread, buffer, 0, is_failure); + binder_release_entire_buffer(proc, thread, buffer, is_failure); binder_alloc_free_buf(&proc->alloc, buffer); } From 57f609a261a333f605bd1b07e139c25df3d80c5f Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Mon, 19 Sep 2022 16:12:13 -0700 Subject: [PATCH 2668/4345] BACKPORT: usb: dwc3: gadget: Do not clear ep delayed stop flag during ep disable DWC3_EP_DELAYED_STOP is utilized to defer issuing the end transfer command until the subsequent SETUP stage, in order to avoid end transfer timeouts. During cable disconnect scenarios, __dwc3_gadget_ep_disable() is responsible for ensuring endpoints have no active transfers pending. Since dwc3_remove_request() can now exit early if the EP delayed stop is set, avoid clearing all DEP flags, otherwise the transition back into the SETUP stage won't issue an endxfer command. Bug: 280698396 Bug: 276227797 Fixes: 2b2da6574e77 ("usb: dwc3: Avoid unmapping USB requests if endxfer is not complete") Reviewed-by: Thinh Nguyen Change-Id: I4453c4ddfe7ad15e9c5b1ba2be09d20cac72b0bf Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/20220919231213.21364-1-quic_wcheng@quicinc.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 76bff31c7fba) (cherry picked from commit c0b28ac8b3976be4277de828aefc914ce2741f95) --- drivers/usb/dwc3/gadget.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 7224cb6e6b78..3c471b1d03a4 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1013,6 +1013,7 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) { struct dwc3 *dwc = dep->dwc; u32 reg; + u32 mask; trace_dwc3_gadget_ep_disable(dep); @@ -1028,7 +1029,15 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) dep->stream_capable = false; dep->type = 0; - dep->flags &= DWC3_EP_TXFIFO_RESIZED; + mask = DWC3_EP_TXFIFO_RESIZED; + /* + * dwc3_remove_requests() can exit early if DWC3 EP delayed stop is + * set. Do not clear DEP flags, so that the end transfer command will + * be reattempted during the next SETUP stage. + */ + if (dep->flags & DWC3_EP_DELAY_STOP) + mask |= (DWC3_EP_DELAY_STOP | DWC3_EP_TRANSFER_STARTED); + dep->flags &= mask; /* Clear out the ep descriptors for non-ep0 */ if (dep->number > 1) { From a42b1b61190b3d12b23c1ba568e8b98d0cb70876 Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Thu, 8 Dec 2022 16:50:35 -0800 Subject: [PATCH 2669/4345] BACKPORT: usb: dwc3: gadget: Ignore End Transfer delay on teardown If we delay sending End Transfer for Setup TRB to be prepared, we need to check if the End Transfer was in preparation for a driver teardown/soft-disconnect. In those cases, just send the End Transfer command without delay. In the case of soft-disconnect, there's a very small chance the command may not go through immediately. But should it happen, the Setup TRB will be prepared during the polling of the controller halted state, allowing the command to go through then. In the case of disabling endpoint due to reconfiguration (e.g. set_interface(alt-setting) or usb reset), then it's driven by the host. Typically the host wouldn't immediately cancel the control request and send another control transfer to trigger the End Transfer command timeout. Bug: 280698394 Bug: 276227797 Fixes: 4db0fbb60136 ("usb: dwc3: gadget: Don't delay End Transfer on delayed_status") Cc: stable@vger.kernel.org Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/f1617a323e190b9cc408fb8b65456e32b5814113.1670546756.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit c4e3ef568539) Change-Id: If49c07d3822e8d637f7dca337c895b0fd1a156f2 (cherry picked from commit 2f2c6f2cf0602ca2b82c70c49aa4e3dab0ab8e11) --- drivers/usb/dwc3/gadget.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 3c471b1d03a4..fbceba256317 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1714,6 +1714,7 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int dep->flags |= DWC3_EP_END_TRANSFER_PENDING; } + dep->flags &= ~DWC3_EP_DELAY_STOP; return ret; } @@ -3721,8 +3722,10 @@ void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, if (dep->number <= 1 && dwc->ep0state != EP0_DATA_PHASE) return; + if (interrupt && (dep->flags & DWC3_EP_DELAY_STOP)) + return; + if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) || - (dep->flags & DWC3_EP_DELAY_STOP) || (dep->flags & DWC3_EP_END_TRANSFER_PENDING)) return; From e36eef3783edf177800df2102e6aec784ef4b27f Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 18 Apr 2023 10:35:38 +0100 Subject: [PATCH 2670/4345] Revert "Revert "mm/rmap: Fix anon_vma->degree ambiguity leading to double-reuse"" This reverts commit 4f35cec76058557d9eaec0d501d03c7657eb56b4 and does so in an abi-safe way. This is done by adding the new fields only to the end of the structure and this structure is only passed around to other functions as a pointer, the internal structure layout is only touched by the core kernel, so adding it to the end is safe. Update ABI using The Button: Leaf changes summary: 1 artifact changed Changed leaf types summary: 1 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 0 Added function Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 0 Added variable 'struct anon_vma at rmap.h:33:1' changed: type size changed from 832 to 960 (in bits) 2 data member insertions: 'unsigned long int num_children', at offset 832 (in bits) at rmap.h:74:1 'unsigned long int num_active_vmas', at offset 896 (in bits) at rmap.h:76:1 5406 impacted interfaces Bug: 260678056 Bug: 253167854 Change-Id: Ib1d45625cbc2e0b21330ca3dc2aa7aff34666d31 Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- android/abi_gki_aarch64.xml | 34 ++++++++++++++++++++-------------- include/linux/rmap.h | 27 ++++++++++++++++++++------- mm/rmap.c | 30 +++++++++++++++++------------- 3 files changed, 57 insertions(+), 34 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 6a06ed9aaa13..94f6ea7547dc 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -14860,7 +14860,7 @@ - + @@ -14871,13 +14871,19 @@ - + - + - + + + + + + + @@ -99212,27 +99218,27 @@ - + - + - + - + - + - + - + - + @@ -138389,8 +138395,8 @@ - - + + diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 0a4d49ca8ccf..5a64e48ef207 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -42,13 +42,7 @@ struct anon_vma { */ atomic_t refcount; - /* - * Count of child anon_vmas and VMAs which points to this anon_vma. - * - * This counter is used for making decision about reusing anon_vma - * instead of forking new one. See comments in function anon_vma_clone. - */ - unsigned degree; + unsigned degree; /* ANDROID: KABI preservation, DO NOT USE! */ struct anon_vma *parent; /* Parent of this anon_vma */ @@ -63,6 +57,25 @@ struct anon_vma { /* Interval tree of private "related" vmas */ struct rb_root_cached rb_root; + + /* + * ANDROID: KABI preservation, it's safe to put these at the end of this structure as it's + * only passed by a pointer everywhere, the size and internal structures are local to the + * core kernel. + */ +#ifndef __GENKSYMS__ + /* + * Count of child anon_vmas. Equals to the count of all anon_vmas that + * have ->parent pointing to this one, including itself. + * + * This counter is used for making decision about reusing anon_vma + * instead of forking new one. See comments in function anon_vma_clone. + */ + unsigned long num_children; + /* Count of VMAs whose ->anon_vma pointer points to this object. */ + unsigned long num_active_vmas; +#endif + }; /* diff --git a/mm/rmap.c b/mm/rmap.c index 033b04704b59..422b3d0deb8f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -91,7 +91,8 @@ static inline struct anon_vma *anon_vma_alloc(void) anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); - anon_vma->degree = 1; /* Reference for first vma */ + anon_vma->num_children = 0; + anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called @@ -199,6 +200,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; + anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } @@ -208,8 +210,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); - /* vma reference or self-parent link for new root */ - anon_vma->degree++; + anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } @@ -294,19 +295,19 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) anon_vma_chain_link(dst, avc, anon_vma); /* - * Reuse existing anon_vma if its degree lower than two, - * that means it has no vma and only one anon_vma child. + * Reuse existing anon_vma if it has no vma and only one + * anon_vma child. * - * Do not chose parent anon_vma, otherwise first child - * will always reuse it. Root anon_vma is never reused: + * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && src->anon_vma && - anon_vma != src->anon_vma && anon_vma->degree < 2) + anon_vma->num_children < 2 && + anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) - dst->anon_vma->degree++; + dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; @@ -356,6 +357,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; + anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; @@ -376,7 +378,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); - anon_vma->parent->degree++; + anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; @@ -408,7 +410,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { - anon_vma->parent->degree--; + anon_vma->parent->num_children--; continue; } @@ -416,7 +418,8 @@ void unlink_anon_vmas(struct vm_area_struct *vma) anon_vma_chain_free(avc); } if (vma->anon_vma) - vma->anon_vma->degree--; + vma->anon_vma->num_active_vmas--; + unlock_anon_vma_root(root); /* @@ -427,7 +430,8 @@ void unlink_anon_vmas(struct vm_area_struct *vma) list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; - VM_WARN_ON(anon_vma->degree); + VM_WARN_ON(anon_vma->num_children); + VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); From 368fb8a50c9a26a5632f502310066bb74daa0005 Mon Sep 17 00:00:00 2001 From: "tanghuan@vivo.com" Date: Tue, 9 May 2023 20:55:30 +0800 Subject: [PATCH 2671/4345] BACKPORT: scsi: ufs: fix a race condition related to device management If a device management command completion happens after wait_for_completion_timeout() times out and before ufshcd_clear_cmds() is called, then the completion code may crash on the complete() call in __ufshcd_transfer_req_compl(). Fix the following crash: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 Call trace: complete+0x64/0x178 __ufshcd_transfer_req_compl+0x30c/0x9c0 ufshcd_poll+0xf0/0x208 ufshcd_sl_intr+0xb8/0xf0 ufshcd_intr+0x168/0x2f4 __handle_irq_event_percpu+0xa0/0x30c handle_irq_event+0x84/0x178 handle_fasteoi_irq+0x150/0x2e8 __handle_domain_irq+0x114/0x1e4 gic_handle_irq.31846+0x58/0x300 el1_irq+0xe4/0x1c0 efi_header_end+0x110/0x680 __irq_exit_rcu+0x108/0x124 __handle_domain_irq+0x118/0x1e4 gic_handle_irq.31846+0x58/0x300 el1_irq+0xe4/0x1c0 cpuidle_enter_state+0x3ac/0x8c4 do_idle+0x2fc/0x55c cpu_startup_entry+0x84/0x90 kernel_init+0x0/0x310 start_kernel+0x0/0x608 start_kernel+0x4ec/0x608 Bug:280957963 Change-Id: I317f9a92ddbd38a952328ce132a60228f41651be (cherry picked from commit f5c2976e0cb0f6236013bfb479868531b04f61d4) Link: https://lore.kernel.org/r/20220720170228.1598842-1-bvanassche@acm.org Fixes: 5a0b0cb9bee7 ("[SCSI] ufs: Add support for sending NOP OUT UPIU") Cc: Adrian Hunter Cc: Avri Altman Cc: Bean Huo Cc: Stanley Chu Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: tanghuan@vivo.com --- drivers/scsi/ufs/ufshcd.c | 66 ++++++++++++++++++++++++--------------- 1 file changed, 40 insertions(+), 26 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 1812edbb7d72..625ea25580da 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -730,16 +730,6 @@ static inline void ufshcd_utmrl_clear(struct ufs_hba *hba, u32 pos) ufshcd_writel(hba, ~(1 << pos), REG_UTP_TASK_REQ_LIST_CLEAR); } -/** - * ufshcd_outstanding_req_clear - Clear a bit in outstanding request field - * @hba: per adapter instance - * @tag: position of the bit to be cleared - */ -static inline void ufshcd_outstanding_req_clear(struct ufs_hba *hba, int tag) -{ - clear_bit(tag, &hba->outstanding_reqs); -} - /** * ufshcd_get_lists_status - Check UCRDY, UTRLRDY and UTMRLRDY * @reg: Register value of host controller status @@ -2882,37 +2872,61 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, int max_timeout) { - int err = 0; - unsigned long time_left; + unsigned long time_left = msecs_to_jiffies(max_timeout); unsigned long flags; + bool pending; + int err; +retry: time_left = wait_for_completion_timeout(hba->dev_cmd.complete, - msecs_to_jiffies(max_timeout)); + time_left); /* Make sure descriptors are ready before ringing the doorbell */ wmb(); - spin_lock_irqsave(hba->host->host_lock, flags); - hba->dev_cmd.complete = NULL; if (likely(time_left)) { + /* + * The completion handler called complete() and the caller of + * this function still owns the @lrbp tag so the code below does + * not trigger any race conditions. + */ + hba->dev_cmd.complete = NULL; err = ufshcd_get_tr_ocs(lrbp); if (!err) err = ufshcd_dev_cmd_completion(hba, lrbp); - } - spin_unlock_irqrestore(hba->host->host_lock, flags); - - if (!time_left) { + } else { err = -ETIMEDOUT; dev_dbg(hba->dev, "%s: dev_cmd request timedout, tag %d\n", __func__, lrbp->task_tag); - if (!ufshcd_clear_cmd(hba, lrbp->task_tag)) + if (ufshcd_clear_cmd(hba, lrbp->task_tag) == 0) { /* successfully cleared the command, retry if needed */ err = -EAGAIN; - /* - * in case of an error, after clearing the doorbell, - * we also need to clear the outstanding_request - * field in hba - */ - ufshcd_outstanding_req_clear(hba, lrbp->task_tag); + /* + * Since clearing the command succeeded we also need to + * clear the task tag bit from the outstanding_reqs + * variable. + */ + spin_lock_irqsave(hba->host->host_lock, flags); + pending = test_bit(lrbp->task_tag, + &hba->outstanding_reqs); + if (pending) { + hba->dev_cmd.complete = NULL; + __clear_bit(lrbp->task_tag, + &hba->outstanding_reqs); + } + spin_unlock_irqrestore(hba->host->host_lock, flags); + + if (!pending) { + /* + * The completion handler ran while we tried to + * clear the command. + */ + time_left = 1; + goto retry; + } + } else { + dev_err(hba->dev, "%s: failed to clear tag %d\n", + __func__, lrbp->task_tag); + } } return err; From 694b75e0ce805e65566636aadc093478e6c20c62 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 14 Feb 2023 11:33:04 +0100 Subject: [PATCH 2672/4345] UPSTREAM: kvm: initialize all of the kvm_debugregs structure before sending it to userspace commit 2c10b61421a28e95a46ab489fd56c0f442ff6952 upstream. When calling the KVM_GET_DEBUGREGS ioctl, on some configurations, there might be some unitialized portions of the kvm_debugregs structure that could be copied to userspace. Prevent this as is done in the other kvm ioctls, by setting the whole structure to 0 before copying anything into it. Bonus is that this reduces the lines of code as the explicit flag setting and reserved space zeroing out can be removed. Bug: 276839298 Cc: Sean Christopherson Cc: Paolo Bonzini Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Cc: "H. Peter Anvin" Cc: stable Reported-by: Xingyuan Mo Signed-off-by: Greg Kroah-Hartman Message-Id: <20230214103304.3689213-1-gregkh@linuxfoundation.org> Tested-by: Xingyuan Mo Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman Signed-off-by: Lee Jones Change-Id: Iba91db0bd1b8380584f48b0ca94d8c104afcce29 --- arch/x86/kvm/x86.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 23d7c563e012..554d37873c25 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4455,12 +4455,11 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, { unsigned long val; + memset(dbgregs, 0, sizeof(*dbgregs)); memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); kvm_get_dr(vcpu, 6, &val); dbgregs->dr6 = val; dbgregs->dr7 = vcpu->arch.dr7; - dbgregs->flags = 0; - memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, From 3641f511eed14ab04cb066e4d7bb56d82e4d1908 Mon Sep 17 00:00:00 2001 From: Udipto Goswami Date: Tue, 9 May 2023 20:18:36 +0530 Subject: [PATCH 2673/4345] UPSTREAM: usb: dwc3: debugfs: Resume dwc3 before accessing registers When the dwc3 device is runtime suspended, various required clocks are in disabled state and it is not guaranteed that access to any registers would work. Depending on the SoC glue, a register read could be as benign as returning 0 or be fatal enough to hang the system. In order to prevent such scenarios of fatal errors, make sure to resume dwc3 then allow the function to proceed. Fixes: 72246da40f37 ("usb: Introduce DesignWare USB3 DRD Driver") Cc: stable@vger.kernel.org #3.2: 30332eeefec8: debugfs: regset32: Add Runtime PM support Signed-off-by: Udipto Goswami Reviewed-by: Johan Hovold Tested-by: Johan Hovold Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230509144836.6803-1-quic_ugoswami@quicinc.com Signed-off-by: Greg Kroah-Hartman Bug: 282654910 (cherry picked from commit 614ce6a2ea50068b45339257891e51e639ac9001 usb-linus) Change-Id: Ie89d818b2d77681075cc517184ad1a5fa755dd88 Signed-off-by: Udipto Goswami --- drivers/usb/dwc3/debugfs.c | 109 +++++++++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index 23f4682ad104..9592875ce835 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -327,6 +327,11 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) unsigned int current_mode; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); @@ -345,6 +350,8 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) } spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -390,6 +397,11 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GCTL); @@ -409,6 +421,8 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %08x\n", DWC3_GCTL_PRTCAP(reg)); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -458,6 +472,11 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -488,6 +507,8 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %d\n", reg); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -504,6 +525,7 @@ static ssize_t dwc3_testmode_write(struct file *file, unsigned long flags; u32 testmode = 0; char buf[32]; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -521,10 +543,16 @@ static ssize_t dwc3_testmode_write(struct file *file, else testmode = 0; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); dwc3_gadget_set_test_mode(dwc, testmode); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -543,12 +571,18 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) enum dwc3_link_state state; u32 reg; u8 speed; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { seq_puts(s, "Not available\n"); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return 0; } @@ -561,6 +595,8 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) dwc3_gadget_hs_link_string(state)); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -579,6 +615,7 @@ static ssize_t dwc3_link_state_write(struct file *file, char buf[32]; u32 reg; u8 speed; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -598,10 +635,15 @@ static ssize_t dwc3_link_state_write(struct file *file, else return -EINVAL; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } @@ -611,12 +653,15 @@ static ssize_t dwc3_link_state_write(struct file *file, if (speed < DWC3_DSTS_SUPERSPEED && state != DWC3_LINK_STATE_RECOV) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } dwc3_gadget_set_link_state(dwc, state); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -640,6 +685,11 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXFIFO); @@ -652,6 +702,8 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -662,6 +714,11 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXFIFO); @@ -674,6 +731,8 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -683,12 +742,19 @@ static int dwc3_tx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -698,12 +764,19 @@ static int dwc3_rx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -713,12 +786,19 @@ static int dwc3_rx_info_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXINFOQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -728,12 +808,19 @@ static int dwc3_descriptor_fetch_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_DESCFETCHQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -743,12 +830,19 @@ static int dwc3_event_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_EVENTQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -793,6 +887,11 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; int i; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); if (dep->number <= 1) { @@ -822,6 +921,8 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) out: spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -834,6 +935,11 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) u32 lower_32_bits; u32 upper_32_bits; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = DWC3_GDBGLSPMUX_EPSELECT(dep->number); @@ -846,6 +952,8 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) seq_printf(s, "0x%016llx\n", ep_info); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -907,6 +1015,7 @@ void dwc3_debugfs_init(struct dwc3 *dwc) dwc->regset->regs = dwc3_regs; dwc->regset->nregs = ARRAY_SIZE(dwc3_regs); dwc->regset->base = dwc->regs - DWC3_GLOBALS_REGS_START; + dwc->regset->dev = dwc->dev; root = debugfs_create_dir(dev_name(dwc->dev), usb_debug_root); dwc->root = root; From c28be8ff1dd3084e9e1831add480a884ce4182e5 Mon Sep 17 00:00:00 2001 From: tanghuan Date: Tue, 16 May 2023 17:28:21 +0800 Subject: [PATCH 2674/4345] BACKPORT: scsi: ufs: Fix device management cmd timeout flow In the UFS error handling flow, the host will send a device management cmd(NOP OUT) to the device for link recovery. If this cmd times out and clearing the doorbell fails, ufshcd_wait_for_dev_cmd() will do nothing andreturn. hba->dev_cmd.complete struct is not set to NULL. When this happens, if cmd has been completed by device, then we will call complete() in __ufshcd_transfer_req_compl(). Because the complete struct is allocated on the stack, the following crash will occur: ipanic_die+0x24/0x38 [mrdump] die+0x344/0x748 arm64_notify_die+0x44/0x104 do_debug_exception+0x104/0x1e0 el1_dbg+0x38/0x54 el1_sync_handler+0x40/0x88 el1_sync+0x8c/0x140 queued_spin_lock_slowpath+0x2e4/0x3c0 __ufshcd_transfer_req_compl+0x3b0/0x1164 ufshcd_trc_handler+0x15c/0x308 ufshcd_host_reset_and_restore+0x54/0x260 ufshcd_reset_and_restore+0x28c/0x57c ufshcd_err_handler+0xeb8/0x1b6c process_one_work+0x288/0x964 worker_thread+0x4bc/0xc7c kthread+0x15c/0x264 ret_from_fork+0x10/0x30 Bug:280957963 Change-Id: I1529c332847ace10bf4a6f8c1ec10ea2eb1eea6a (cherry picked from commit 36822124f9de200cedc2f42516301b50d386a6cd) Link: https://lore.kernel.org/r/20221216032532.1280-1-mason.zhang@mediatek.com Signed-off-by: Mason Zhang Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: tanghuan --- drivers/scsi/ufs/ufshcd.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 625ea25580da..a42e4e96a964 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -2926,6 +2926,21 @@ retry: } else { dev_err(hba->dev, "%s: failed to clear tag %d\n", __func__, lrbp->task_tag); + spin_lock_irqsave(hba->host->host_lock, flags); + pending = test_bit(lrbp->task_tag, + &hba->outstanding_reqs); + if (pending) + hba->dev_cmd.complete = NULL; + spin_unlock_irqrestore(hba->host->host_lock, flags); + + if (!pending) { + /* + * The completion handler ran while we tried to + * clear the command. + */ + time_left = 1; + goto retry; + } } } From d4a895e924b486f2a38463114509e1088ef4d7f5 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 23 Aug 2022 08:45:32 -0700 Subject: [PATCH 2675/4345] seccomp: Move copy_seccomp() to no failure path. commit a1140cb215fa13dcec06d12ba0c3ee105633b7c4 upstream. Our syzbot instance reported memory leaks in do_seccomp() [0], similar to the report [1]. It shows that we miss freeing struct seccomp_filter and some objects included in it. We can reproduce the issue with the program below [2] which calls one seccomp() and two clone() syscalls. The first clone()d child exits earlier than its parent and sends a signal to kill it during the second clone(), more precisely before the fatal_signal_pending() test in copy_process(). When the parent receives the signal, it has to destroy the embryonic process and return -EINTR to user space. In the failure path, we have to call seccomp_filter_release() to decrement the filter's refcount. Initially, we called it in free_task() called from the failure path, but the commit 3a15fb6ed92c ("seccomp: release filter after task is fully dead") moved it to release_task() to notify user space as early as possible that the filter is no longer used. To keep the change and current seccomp refcount semantics, let's move copy_seccomp() just after the signal check and add a WARN_ON_ONCE() in free_task() for future debugging. [0]: unreferenced object 0xffff8880063add00 (size 256): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.914s) hex dump (first 32 bytes): 01 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00 ................ ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ................ backtrace: do_seccomp (./include/linux/slab.h:600 ./include/linux/slab.h:733 kernel/seccomp.c:666 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) unreferenced object 0xffffc90000035000 (size 4096): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.915s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 05 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: __vmalloc_node_range (mm/vmalloc.c:3226) __vmalloc_node (mm/vmalloc.c:3261 (discriminator 4)) bpf_prog_alloc_no_stats (kernel/bpf/core.c:91) bpf_prog_alloc (kernel/bpf/core.c:129) bpf_prog_create_from_user (net/core/filter.c:1414) do_seccomp (kernel/seccomp.c:671 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) unreferenced object 0xffff888003fa1000 (size 1024): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.915s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: bpf_prog_alloc_no_stats (./include/linux/slab.h:600 ./include/linux/slab.h:733 kernel/bpf/core.c:95) bpf_prog_alloc (kernel/bpf/core.c:129) bpf_prog_create_from_user (net/core/filter.c:1414) do_seccomp (kernel/seccomp.c:671 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) unreferenced object 0xffff888006360240 (size 16): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.915s) hex dump (first 16 bytes): 01 00 37 00 76 65 72 6c e0 83 01 06 80 88 ff ff ..7.verl........ backtrace: bpf_prog_store_orig_filter (net/core/filter.c:1137) bpf_prog_create_from_user (net/core/filter.c:1428) do_seccomp (kernel/seccomp.c:671 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) unreferenced object 0xffff8880060183e0 (size 8): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.915s) hex dump (first 8 bytes): 06 00 00 00 00 00 ff 7f ........ backtrace: kmemdup (mm/util.c:129) bpf_prog_store_orig_filter (net/core/filter.c:1144) bpf_prog_create_from_user (net/core/filter.c:1428) do_seccomp (kernel/seccomp.c:671 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) [1]: https://syzkaller.appspot.com/bug?id=2809bb0ac77ad9aa3f4afe42d6a610aba594a987 [2]: #define _GNU_SOURCE #include #include #include #include #include #include void main(void) { struct sock_filter filter[] = { BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW), }; struct sock_fprog fprog = { .len = sizeof(filter) / sizeof(filter[0]), .filter = filter, }; long i, pid; syscall(__NR_seccomp, SECCOMP_SET_MODE_FILTER, 0, &fprog); for (i = 0; i < 2; i++) { pid = syscall(__NR_clone, CLONE_NEWNET | SIGKILL, NULL, NULL, 0); if (pid == 0) return; } } Fixes: 3a15fb6ed92c ("seccomp: release filter after task is fully dead") Reported-by: syzbot+ab17848fe269b573eb71@syzkaller.appspotmail.com Reported-by: Ayushman Dutta Suggested-by: Kees Cook Signed-off-by: Kuniyuki Iwashima Reviewed-by: Christian Brauner (Microsoft) Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220823154532.82913-1-kuniyu@amazon.com Signed-off-by: Greg Kroah-Hartman --- kernel/fork.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index a5bc0c6a00fd..c6a289317e89 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -441,6 +441,9 @@ void put_task_stack(struct task_struct *tsk) void free_task(struct task_struct *tsk) { +#ifdef CONFIG_SECCOMP + WARN_ON_ONCE(tsk->seccomp.filter); +#endif scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK @@ -2248,12 +2251,6 @@ static __latent_entropy struct task_struct *copy_process( spin_lock(¤t->sighand->siglock); - /* - * Copy seccomp details explicitly here, in case they were changed - * before holding sighand lock. - */ - copy_seccomp(p); - rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ @@ -2268,6 +2265,14 @@ static __latent_entropy struct task_struct *copy_process( goto bad_fork_cancel_cgroup; } + /* No more failure paths after this point. */ + + /* + * Copy seccomp details explicitly here, in case they were changed + * before holding sighand lock. + */ + copy_seccomp(p); + init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); From 0f29d0e8fc77db0cbf08df3aafb6206b66714277 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Sun, 12 Mar 2023 19:15:49 -0400 Subject: [PATCH 2676/4345] counter: 104-quad-8: Fix race condition between FLAG and CNTR reads commit 4aa3b75c74603c3374877d5fd18ad9cc3a9a62ed upstream. The Counter (CNTR) register is 24 bits wide, but we can have an effective 25-bit count value by setting bit 24 to the XOR of the Borrow flag and Carry flag. The flags can be read from the FLAG register, but a race condition exists: the Borrow flag and Carry flag are instantaneous and could change by the time the count value is read from the CNTR register. Since the race condition could result in an incorrect 25-bit count value, remove support for 25-bit count values from this driver; hard-coded maximum count values are replaced by a LS7267_CNTR_MAX define for consistency and clarity. Fixes: 28e5d3bb0325 ("iio: 104-quad-8: Add IIO support for the ACCES 104-QUAD-8") Cc: # 6.1.x Cc: # 6.2.x Link: https://lore.kernel.org/r/20230312231554.134858-1-william.gray@linaro.org/ Signed-off-by: William Breathitt Gray Signed-off-by: Greg Kroah-Hartman --- drivers/counter/104-quad-8.c | 28 ++++------------------------ 1 file changed, 4 insertions(+), 24 deletions(-) diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index 21bb2bb767a1..89c9cb850a34 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -62,10 +62,6 @@ struct quad8_iio { #define QUAD8_REG_CHAN_OP 0x11 #define QUAD8_REG_INDEX_INPUT_LEVELS 0x16 #define QUAD8_DIFF_ENCODER_CABLE_STATUS 0x17 -/* Borrow Toggle flip-flop */ -#define QUAD8_FLAG_BT BIT(0) -/* Carry Toggle flip-flop */ -#define QUAD8_FLAG_CT BIT(1) /* Error flag */ #define QUAD8_FLAG_E BIT(4) /* Up/Down flag */ @@ -104,9 +100,6 @@ static int quad8_read_raw(struct iio_dev *indio_dev, { struct quad8_iio *const priv = iio_priv(indio_dev); const int base_offset = priv->base + 2 * chan->channel; - unsigned int flags; - unsigned int borrow; - unsigned int carry; int i; switch (mask) { @@ -117,12 +110,7 @@ static int quad8_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; } - flags = inb(base_offset + 1); - borrow = flags & QUAD8_FLAG_BT; - carry = !!(flags & QUAD8_FLAG_CT); - - /* Borrow XOR Carry effectively doubles count range */ - *val = (borrow ^ carry) << 24; + *val = 0; mutex_lock(&priv->lock); @@ -643,17 +631,9 @@ static int quad8_count_read(struct counter_device *counter, { struct quad8_iio *const priv = counter->priv; const int base_offset = priv->base + 2 * count->id; - unsigned int flags; - unsigned int borrow; - unsigned int carry; int i; - flags = inb(base_offset + 1); - borrow = flags & QUAD8_FLAG_BT; - carry = !!(flags & QUAD8_FLAG_CT); - - /* Borrow XOR Carry effectively doubles count range */ - *val = (unsigned long)(borrow ^ carry) << 24; + *val = 0; mutex_lock(&priv->lock); @@ -1198,8 +1178,8 @@ static ssize_t quad8_count_ceiling_read(struct counter_device *counter, mutex_unlock(&priv->lock); - /* By default 0x1FFFFFF (25 bits unsigned) is maximum count */ - return sprintf(buf, "33554431\n"); + /* By default 0xFFFFFF (24 bits unsigned) is maximum count */ + return sprintf(buf, "16777215\n"); } static ssize_t quad8_count_ceiling_write(struct counter_device *counter, From 1dd95b2109de223d98956b54cf8990bb226c285e Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 19 Apr 2023 13:16:13 +0300 Subject: [PATCH 2677/4345] KVM: arm64: Fix buffer overflow in kvm_arm_set_fw_reg() commit a25bc8486f9c01c1af6b6c5657234b2eee2c39d6 upstream. The KVM_REG_SIZE() comes from the ioctl and it can be a power of two between 0-32768 but if it is more than sizeof(long) this will corrupt memory. Fixes: 99adb567632b ("KVM: arm/arm64: Add save/restore support for firmware workaround state") Signed-off-by: Dan Carpenter Reviewed-by: Steven Price Reviewed-by: Eric Auger Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/4efbab8c-640f-43b2-8ac6-6d68e08280fe@kili.mountain Signed-off-by: Oliver Upton [will: kvm_arm_set_fw_reg() lives in psci.c not hypercalls.c] Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kvm/psci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 20ba5136ac3d..32bb26be8a9b 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -499,6 +499,8 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; int wa_level; + if (KVM_REG_SIZE(reg->id) != sizeof(val)) + return -ENOENT; if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) return -EFAULT; From 549825602e3e6449927ca1ea1a08fd89868439df Mon Sep 17 00:00:00 2001 From: Jisoo Jang Date: Thu, 9 Mar 2023 19:44:57 +0900 Subject: [PATCH 2678/4345] wifi: brcmfmac: slab-out-of-bounds read in brcmf_get_assoc_ies() commit 0da40e018fd034d87c9460123fa7f897b69fdee7 upstream. Fix a slab-out-of-bounds read that occurs in kmemdup() called from brcmf_get_assoc_ies(). The bug could occur when assoc_info->req_len, data from a URB provided by a USB device, is bigger than the size of buffer which is defined as WL_EXTRA_BUF_MAX. Add the size check for req_len/resp_len of assoc_info. Found by a modified version of syzkaller. [ 46.592467][ T7] ================================================================== [ 46.594687][ T7] BUG: KASAN: slab-out-of-bounds in kmemdup+0x3e/0x50 [ 46.596572][ T7] Read of size 3014656 at addr ffff888019442000 by task kworker/0:1/7 [ 46.598575][ T7] [ 46.599157][ T7] CPU: 0 PID: 7 Comm: kworker/0:1 Tainted: G O 5.14.0+ #145 [ 46.601333][ T7] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 [ 46.604360][ T7] Workqueue: events brcmf_fweh_event_worker [ 46.605943][ T7] Call Trace: [ 46.606584][ T7] dump_stack_lvl+0x8e/0xd1 [ 46.607446][ T7] print_address_description.constprop.0.cold+0x93/0x334 [ 46.608610][ T7] ? kmemdup+0x3e/0x50 [ 46.609341][ T7] kasan_report.cold+0x79/0xd5 [ 46.610151][ T7] ? kmemdup+0x3e/0x50 [ 46.610796][ T7] kasan_check_range+0x14e/0x1b0 [ 46.611691][ T7] memcpy+0x20/0x60 [ 46.612323][ T7] kmemdup+0x3e/0x50 [ 46.612987][ T7] brcmf_get_assoc_ies+0x967/0xf60 [ 46.613904][ T7] ? brcmf_notify_vif_event+0x3d0/0x3d0 [ 46.614831][ T7] ? lock_chain_count+0x20/0x20 [ 46.615683][ T7] ? mark_lock.part.0+0xfc/0x2770 [ 46.616552][ T7] ? lock_chain_count+0x20/0x20 [ 46.617409][ T7] ? mark_lock.part.0+0xfc/0x2770 [ 46.618244][ T7] ? lock_chain_count+0x20/0x20 [ 46.619024][ T7] brcmf_bss_connect_done.constprop.0+0x241/0x2e0 [ 46.620019][ T7] ? brcmf_parse_configure_security.isra.0+0x2a0/0x2a0 [ 46.620818][ T7] ? __lock_acquire+0x181f/0x5790 [ 46.621462][ T7] brcmf_notify_connect_status+0x448/0x1950 [ 46.622134][ T7] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 46.622736][ T7] ? brcmf_cfg80211_join_ibss+0x7b0/0x7b0 [ 46.623390][ T7] ? find_held_lock+0x2d/0x110 [ 46.623962][ T7] ? brcmf_fweh_event_worker+0x19f/0xc60 [ 46.624603][ T7] ? mark_held_locks+0x9f/0xe0 [ 46.625145][ T7] ? lockdep_hardirqs_on_prepare+0x3e0/0x3e0 [ 46.625871][ T7] ? brcmf_cfg80211_join_ibss+0x7b0/0x7b0 [ 46.626545][ T7] brcmf_fweh_call_event_handler.isra.0+0x90/0x100 [ 46.627338][ T7] brcmf_fweh_event_worker+0x557/0xc60 [ 46.627962][ T7] ? brcmf_fweh_call_event_handler.isra.0+0x100/0x100 [ 46.628736][ T7] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 46.629396][ T7] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 46.629970][ T7] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 46.630649][ T7] process_one_work+0x92b/0x1460 [ 46.631205][ T7] ? pwq_dec_nr_in_flight+0x330/0x330 [ 46.631821][ T7] ? rwlock_bug.part.0+0x90/0x90 [ 46.632347][ T7] worker_thread+0x95/0xe00 [ 46.632832][ T7] ? __kthread_parkme+0x115/0x1e0 [ 46.633393][ T7] ? process_one_work+0x1460/0x1460 [ 46.633957][ T7] kthread+0x3a1/0x480 [ 46.634369][ T7] ? set_kthread_struct+0x120/0x120 [ 46.634933][ T7] ret_from_fork+0x1f/0x30 [ 46.635431][ T7] [ 46.635687][ T7] Allocated by task 7: [ 46.636151][ T7] kasan_save_stack+0x1b/0x40 [ 46.636628][ T7] __kasan_kmalloc+0x7c/0x90 [ 46.637108][ T7] kmem_cache_alloc_trace+0x19e/0x330 [ 46.637696][ T7] brcmf_cfg80211_attach+0x4a0/0x4040 [ 46.638275][ T7] brcmf_attach+0x389/0xd40 [ 46.638739][ T7] brcmf_usb_probe+0x12de/0x1690 [ 46.639279][ T7] usb_probe_interface+0x2aa/0x760 [ 46.639820][ T7] really_probe+0x205/0xb70 [ 46.640342][ T7] __driver_probe_device+0x311/0x4b0 [ 46.640876][ T7] driver_probe_device+0x4e/0x150 [ 46.641445][ T7] __device_attach_driver+0x1cc/0x2a0 [ 46.642000][ T7] bus_for_each_drv+0x156/0x1d0 [ 46.642543][ T7] __device_attach+0x23f/0x3a0 [ 46.643065][ T7] bus_probe_device+0x1da/0x290 [ 46.643644][ T7] device_add+0xb7b/0x1eb0 [ 46.644130][ T7] usb_set_configuration+0xf59/0x16f0 [ 46.644720][ T7] usb_generic_driver_probe+0x82/0xa0 [ 46.645295][ T7] usb_probe_device+0xbb/0x250 [ 46.645786][ T7] really_probe+0x205/0xb70 [ 46.646258][ T7] __driver_probe_device+0x311/0x4b0 [ 46.646804][ T7] driver_probe_device+0x4e/0x150 [ 46.647387][ T7] __device_attach_driver+0x1cc/0x2a0 [ 46.647926][ T7] bus_for_each_drv+0x156/0x1d0 [ 46.648454][ T7] __device_attach+0x23f/0x3a0 [ 46.648939][ T7] bus_probe_device+0x1da/0x290 [ 46.649478][ T7] device_add+0xb7b/0x1eb0 [ 46.649936][ T7] usb_new_device.cold+0x49c/0x1029 [ 46.650526][ T7] hub_event+0x1c98/0x3950 [ 46.650975][ T7] process_one_work+0x92b/0x1460 [ 46.651535][ T7] worker_thread+0x95/0xe00 [ 46.651991][ T7] kthread+0x3a1/0x480 [ 46.652413][ T7] ret_from_fork+0x1f/0x30 [ 46.652885][ T7] [ 46.653131][ T7] The buggy address belongs to the object at ffff888019442000 [ 46.653131][ T7] which belongs to the cache kmalloc-2k of size 2048 [ 46.654669][ T7] The buggy address is located 0 bytes inside of [ 46.654669][ T7] 2048-byte region [ffff888019442000, ffff888019442800) [ 46.656137][ T7] The buggy address belongs to the page: [ 46.656720][ T7] page:ffffea0000651000 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x19440 [ 46.657792][ T7] head:ffffea0000651000 order:3 compound_mapcount:0 compound_pincount:0 [ 46.658673][ T7] flags: 0x100000000010200(slab|head|node=0|zone=1) [ 46.659422][ T7] raw: 0100000000010200 0000000000000000 dead000000000122 ffff888100042000 [ 46.660363][ T7] raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000 [ 46.661236][ T7] page dumped because: kasan: bad access detected [ 46.661956][ T7] page_owner tracks the page as allocated [ 46.662588][ T7] page last allocated via order 3, migratetype Unmovable, gfp_mask 0x52a20(GFP_ATOMIC|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP), pid 7, ts 31136961085, free_ts 0 [ 46.664271][ T7] prep_new_page+0x1aa/0x240 [ 46.664763][ T7] get_page_from_freelist+0x159a/0x27c0 [ 46.665340][ T7] __alloc_pages+0x2da/0x6a0 [ 46.665847][ T7] alloc_pages+0xec/0x1e0 [ 46.666308][ T7] allocate_slab+0x380/0x4e0 [ 46.666770][ T7] ___slab_alloc+0x5bc/0x940 [ 46.667264][ T7] __slab_alloc+0x6d/0x80 [ 46.667712][ T7] kmem_cache_alloc_trace+0x30a/0x330 [ 46.668299][ T7] brcmf_usbdev_qinit.constprop.0+0x50/0x470 [ 46.668885][ T7] brcmf_usb_probe+0xc97/0x1690 [ 46.669438][ T7] usb_probe_interface+0x2aa/0x760 [ 46.669988][ T7] really_probe+0x205/0xb70 [ 46.670487][ T7] __driver_probe_device+0x311/0x4b0 [ 46.671031][ T7] driver_probe_device+0x4e/0x150 [ 46.671604][ T7] __device_attach_driver+0x1cc/0x2a0 [ 46.672192][ T7] bus_for_each_drv+0x156/0x1d0 [ 46.672739][ T7] page_owner free stack trace missing [ 46.673335][ T7] [ 46.673620][ T7] Memory state around the buggy address: [ 46.674213][ T7] ffff888019442700: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 46.675083][ T7] ffff888019442780: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 46.675994][ T7] >ffff888019442800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 46.676875][ T7] ^ [ 46.677323][ T7] ffff888019442880: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 46.678190][ T7] ffff888019442900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 46.679052][ T7] ================================================================== [ 46.679945][ T7] Disabling lock debugging due to kernel taint [ 46.680725][ T7] Kernel panic - not syncing: Reviewed-by: Arend van Spriel Signed-off-by: Jisoo Jang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230309104457.22628-1-jisoo.jang@yonsei.ac.kr Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 0a069bc7f156..df5970619712 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -5834,6 +5834,11 @@ static s32 brcmf_get_assoc_ies(struct brcmf_cfg80211_info *cfg, (struct brcmf_cfg80211_assoc_ielen_le *)cfg->extra_buf; req_len = le32_to_cpu(assoc_info->req_len); resp_len = le32_to_cpu(assoc_info->resp_len); + if (req_len > WL_EXTRA_BUF_MAX || resp_len > WL_EXTRA_BUF_MAX) { + bphy_err(drvr, "invalid lengths in assoc info: req %u resp %u\n", + req_len, resp_len); + return -EINVAL; + } if (req_len) { err = brcmf_fil_iovar_data_get(ifp, "assoc_req_ies", cfg->extra_buf, From dc110b20f4ce752c232ad710a428dd97cf138338 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 4 Apr 2023 21:40:36 +0200 Subject: [PATCH 2679/4345] drm/fb-helper: set x/yres_virtual in drm_fb_helper_check_var commit 1935f0deb6116dd785ea64d8035eab0ff441255b upstream. Drivers are supposed to fix this up if needed if they don't outright reject it. Uncovered by 6c11df58fd1a ("fbmem: Check virtual screen sizes in fb_set_var()"). Reported-by: syzbot+20dcf81733d43ddff661@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=c5faf983bfa4a607de530cd3bb008888bf06cefc Cc: stable@vger.kernel.org # v5.4+ Cc: Daniel Vetter Cc: Javier Martinez Canillas Cc: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20230404194038.472803-1-daniel.vetter@ffwll.ch Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_fb_helper.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index ac5d61e65124..04f2ec2254e9 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1299,6 +1299,9 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, return -EINVAL; } + var->xres_virtual = fb->width; + var->yres_virtual = fb->height; + /* * Workaround for SDL 1.2, which is known to be setting all pixel format * fields values to zero in some cases. We treat this situation as a From 98cfbad52fc286c2a1a75e04bf47b98d6489db1f Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Sun, 16 Apr 2023 16:14:04 +0800 Subject: [PATCH 2680/4345] bluetooth: Perform careful capability checks in hci_sock_ioctl() commit 25c150ac103a4ebeed0319994c742a90634ddf18 upstream. Previously, capability was checked using capable(), which verified that the caller of the ioctl system call had the required capability. In addition, the result of the check would be stored in the HCI_SOCK_TRUSTED flag, making it persistent for the socket. However, malicious programs can abuse this approach by deliberately sharing an HCI socket with a privileged task. The HCI socket will be marked as trusted when the privileged task occasionally makes an ioctl call. This problem can be solved by using sk_capable() to check capability, which ensures that not only the current task but also the socket opener has the specified capability, thus reducing the risk of privilege escalation through the previously identified vulnerability. Cc: stable@vger.kernel.org Fixes: f81f5b2db869 ("Bluetooth: Send control open and close messages for HCI raw sockets") Signed-off-by: Ruihan Li Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/hci_sock.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 73779af2fed6..4dcc1a8a8954 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -996,7 +996,14 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, if (hci_sock_gen_cookie(sk)) { struct sk_buff *skb; - if (capable(CAP_NET_ADMIN)) + /* Perform careful checks before setting the HCI_SOCK_TRUSTED + * flag. Make sure that not only the current task but also + * the socket opener has the required capability, since + * privileged programs can be tricked into making ioctl calls + * on HCI sockets, and the socket should not be marked as + * trusted simply because the ioctl caller is privileged. + */ + if (sk_capable(sk, CAP_NET_ADMIN)) hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); /* Send event to monitor */ From c0e921422359f6796fc0ccf50a66739b919344dd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 1 May 2022 21:31:43 +0200 Subject: [PATCH 2681/4345] x86/fpu: Prevent FPU state corruption commit 59f5ede3bc0f00eb856425f636dab0c10feb06d8 upstream. The FPU usage related to task FPU management is either protected by disabling interrupts (switch_to, return to user) or via fpregs_lock() which is a wrapper around local_bh_disable(). When kernel code wants to use the FPU then it has to check whether it is possible by calling irq_fpu_usable(). But the condition in irq_fpu_usable() is wrong. It allows FPU to be used when: !in_interrupt() || interrupted_user_mode() || interrupted_kernel_fpu_idle() The latter is checking whether some other context already uses FPU in the kernel, but if that's not the case then it allows FPU to be used unconditionally even if the calling context interrupted a fpregs_lock() critical region. If that happens then the FPU state of the interrupted context becomes corrupted. Allow in kernel FPU usage only when no other context has in kernel FPU usage and either the calling context is not hard interrupt context or the hard interrupt did not interrupt a local bottomhalf disabled region. It's hard to find a proper Fixes tag as the condition was broken in one way or the other for a very long time and the eager/lazy FPU changes caused a lot of churn. Picked something remotely connected from the history. This survived undetected for quite some time as FPU usage in interrupt context is rare, but the recent changes to the random code unearthed it at least on a kernel which had FPU debugging enabled. There is probably a higher rate of silent corruption as not all issues can be detected by the FPU debugging code. This will be addressed in a subsequent change. Fixes: 5d2bd7009f30 ("x86, fpu: decouple non-lazy/eager fpu restore from xsave") Reported-by: Filipe Manana Signed-off-by: Thomas Gleixner Tested-by: Filipe Manana Reviewed-by: Borislav Petkov Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220501193102.588689270@linutronix.de Signed-off-by: Can Sun Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/fpu/core.c | 67 +++++++++++++++----------------------- 1 file changed, 26 insertions(+), 41 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 571220ac8bea..835b948095cd 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -25,17 +25,7 @@ */ union fpregs_state init_fpstate __read_mostly; -/* - * Track whether the kernel is using the FPU state - * currently. - * - * This flag is used: - * - * - by IRQ context code to potentially use the FPU - * if it's unused. - * - * - to debug kernel_fpu_begin()/end() correctness - */ +/* Track in-kernel FPU usage */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* @@ -43,42 +33,37 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu); */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); -static bool kernel_fpu_disabled(void) -{ - return this_cpu_read(in_kernel_fpu); -} - -static bool interrupted_kernel_fpu_idle(void) -{ - return !kernel_fpu_disabled(); -} - -/* - * Were we in user mode (or vm86 mode) when we were - * interrupted? - * - * Doing kernel_fpu_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - return regs && user_mode(regs); -} - /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. */ bool irq_fpu_usable(void) { - return !in_interrupt() || - interrupted_user_mode() || - interrupted_kernel_fpu_idle(); + if (WARN_ON_ONCE(in_nmi())) + return false; + + /* In kernel FPU usage already active? */ + if (this_cpu_read(in_kernel_fpu)) + return false; + + /* + * When not in NMI or hard interrupt context, FPU can be used in: + * + * - Task context except from within fpregs_lock()'ed critical + * regions. + * + * - Soft interrupt processing context which cannot happen + * while in a fpregs_lock()'ed critical region. + */ + if (!in_irq()) + return true; + + /* + * In hard interrupt context it's safe when soft interrupts + * are enabled, which means the interrupt did not hit in + * a fpregs_lock()'ed critical region. + */ + return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); From f964a00386ca0b1013357657922c00c1b5e66b07 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Mon, 17 Apr 2023 18:20:03 +0300 Subject: [PATCH 2682/4345] USB: serial: option: add UNISOC vendor and TOZED LT70C product MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit a095edfc15f0832e046ae23964e249ef5c95af87 upstream. Add UNISOC vendor ID and TOZED LT70-C modem which is based from UNISOC SL8563. The modem supports the NCM mode. Interface 0 is used for running the AT commands. Interface 12 is the ADB interface. T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 6 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=1782 ProdID=4055 Rev=04.04 S: Manufacturer=Unisoc Phone S: Product=Unisoc Phone S: SerialNumber= C: #Ifs=14 Cfg#= 1 Atr=c0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0d Prot=00 Driver=cdc_ncm E: Ad=82(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#=10 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#=11 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=08(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8c(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#=12 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) E: Ad=09(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8d(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#=13 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=0a(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 2 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0d Prot=00 Driver=cdc_ncm E: Ad=84(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 3 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 4 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0d Prot=00 Driver=cdc_ncm E: Ad=86(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 5 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 6 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0d Prot=00 Driver=cdc_ncm E: Ad=88(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 7 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 9 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8a(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Arınç ÜNAL Link: https://lore.kernel.org/r/20230417152003.243248-1-arinc.unal@arinc9.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index da8b7bd39703..5b474efeab6a 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -595,6 +595,11 @@ static void option_instat_callback(struct urb *urb); #define SIERRA_VENDOR_ID 0x1199 #define SIERRA_PRODUCT_EM9191 0x90d3 +/* UNISOC (Spreadtrum) products */ +#define UNISOC_VENDOR_ID 0x1782 +/* TOZED LT70-C based on UNISOC SL8563 uses UNISOC's vendor ID */ +#define TOZED_PRODUCT_LT70C 0x4055 + /* Device flags */ /* Highest interface number which can be used with NCTRL() and RSVD() */ @@ -2225,6 +2230,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); From 8aa079c2fdfc1bbf2eb8499e065ab509a2b3eea3 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 12 Apr 2023 15:58:42 -0700 Subject: [PATCH 2683/4345] driver core: Don't require dynamic_debug for initcall_debug probe timing commit e2f06aa885081e1391916367f53bad984714b4db upstream. Don't require the use of dynamic debug (or modification of the kernel to add a #define DEBUG to the top of this file) to get the printk message about driver probe timing. This printk is only emitted when initcall_debug is enabled on the kernel commandline, and it isn't immediately obvious that you have to do something else to debug boot timing issues related to driver probe. Add a comment too so it doesn't get converted back to pr_debug(). Fixes: eb7fbc9fb118 ("driver core: Add missing '\n' in log messages") Cc: stable Cc: Christophe JAILLET Cc: Brian Norris Reviewed-by: Brian Norris Acked-by: Randy Dunlap Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230412225842.3196599-1-swboyd@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 497e3d4255c4..503c01d4015d 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -677,7 +677,12 @@ static int really_probe_debug(struct device *dev, struct device_driver *drv) calltime = ktime_get(); ret = really_probe(dev, drv); rettime = ktime_get(); - pr_debug("probe of %s returned %d after %lld usecs\n", + /* + * Don't change this to pr_debug() because that requires + * CONFIG_DYNAMIC_DEBUG and we want a simple 'initcall_debug' on the + * kernel commandline to print this all the time at the debug level. + */ + printk(KERN_DEBUG "probe of %s returned %d after %lld usecs\n", dev_name(dev), ret, ktime_us_delta(rettime, calltime)); return ret; } From f5e96af71eab491a19fb3926ab42d592118ca52c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Patrik=20Dahlstr=C3=B6m?= Date: Mon, 13 Mar 2023 21:50:29 +0100 Subject: [PATCH 2684/4345] iio: adc: palmas_gpadc: fix NULL dereference on rmmod MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 49f76c499d38bf67803438eee88c8300d0f6ce09 ] Calling dev_to_iio_dev() on a platform device pointer is undefined and will make adc NULL. Signed-off-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230313205029.1881745-1-risca@dalakolonin.se Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/adc/palmas_gpadc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index f4756671cddb..6ed0d151ad21 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -628,7 +628,7 @@ out: static int palmas_gpadc_remove(struct platform_device *pdev) { - struct iio_dev *indio_dev = dev_to_iio_dev(&pdev->dev); + struct iio_dev *indio_dev = dev_get_drvdata(&pdev->dev); struct palmas_gpadc *adc = iio_priv(indio_dev); if (adc->wakeup1_enable || adc->wakeup2_enable) From 925cbb725367b228039c62d35f4c75937463bb44 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 22 Mar 2023 15:53:32 +0100 Subject: [PATCH 2685/4345] ASoC: Intel: bytcr_rt5640: Add quirk for the Acer Iconia One 7 B1-750 [ Upstream commit e38c5e80c3d293a883c6f1d553f2146ec0bda35e ] The Acer Iconia One 7 B1-750 tablet mostly works fine with the defaults for an Bay Trail CR tablet. Except for the internal mic, instead of an analog mic on IN3 a digital mic on DMIC1 is uses. Add a quirk with these settings for this tablet. Acked-by: Pierre-Louis Bossart Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230322145332.131525-1-hdegoede@redhat.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/intel/boards/bytcr_rt5640.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 8a99cb6dfcd6..9a5ab96f917d 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -393,6 +393,18 @@ static int byt_rt5640_aif1_hw_params(struct snd_pcm_substream *substream, /* Please keep this list alphabetically sorted */ static const struct dmi_system_id byt_rt5640_quirk_table[] = { + { /* Acer Iconia One 7 B1-750 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "VESPA2"), + }, + .driver_data = (void *)(BYT_RT5640_DMIC1_MAP | + BYT_RT5640_JD_SRC_JD1_IN4P | + BYT_RT5640_OVCD_TH_1500UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* Acer Iconia Tab 8 W1-810 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"), From 69fdbb334d6e6d33e27b0adc3234607af6135861 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 9 Jan 2023 15:11:52 +0200 Subject: [PATCH 2686/4345] asm-generic/io.h: suppress endianness warnings for readq() and writeq() [ Upstream commit d564fa1ff19e893e2971d66e5c8f49dc1cdc8ffc ] Commit c1d55d50139b ("asm-generic/io.h: Fix sparse warnings on big-endian architectures") missed fixing the 64-bit accessors. Arnd explains in the attached link why the casts are necessary, even if __raw_readq() and __raw_writeq() do not take endian-specific types. Link: https://lore.kernel.org/lkml/9105d6fc-880b-4734-857d-e3d30b87ccf6@app.fastmail.com/ Suggested-by: Arnd Bergmann Signed-off-by: Vladimir Oltean Reviewed-by: Jonathan Cameron Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- include/asm-generic/io.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 9ea83d80eb6f..dcbd41048b4e 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -190,7 +190,7 @@ static inline u64 readq(const volatile void __iomem *addr) u64 val; __io_br(); - val = __le64_to_cpu(__raw_readq(addr)); + val = __le64_to_cpu((__le64 __force)__raw_readq(addr)); __io_ar(val); return val; } @@ -233,7 +233,7 @@ static inline void writel(u32 value, volatile void __iomem *addr) static inline void writeq(u64 value, volatile void __iomem *addr) { __io_bw(); - __raw_writeq(__cpu_to_le64(value), addr); + __raw_writeq((u64 __force)__cpu_to_le64(value), addr); __io_aw(); } #endif From 5434c7019d2308a474ddb8accbb7279f1a327036 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Tue, 13 Dec 2022 15:52:08 -0700 Subject: [PATCH 2687/4345] wireguard: timers: cast enum limits members to int in prints commit 2d4ee16d969c97996e80e4c9cb6de0acaff22c9f upstream. Since gcc13, each member of an enum has the same type as the enum. And that is inherited from its members. Provided "REKEY_AFTER_MESSAGES = 1ULL << 60", the named type is unsigned long. This generates warnings with gcc-13: error: format '%d' expects argument of type 'int', but argument 6 has type 'long unsigned int' Cast those particular enum members to int when printing them. Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=36113 Cc: Martin Liska Signed-off-by: Jiri Slaby (SUSE) Signed-off-by: Jason A. Donenfeld Link: https://lore.kernel.org/all/20221213225208.3343692-2-Jason@zx2c4.com/ Signed-off-by: Jakub Kicinski Cc: Chris Clayton Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireguard/timers.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireguard/timers.c b/drivers/net/wireguard/timers.c index d54d32ac9bc4..91f5d6d2d4e2 100644 --- a/drivers/net/wireguard/timers.c +++ b/drivers/net/wireguard/timers.c @@ -46,7 +46,7 @@ static void wg_expired_retransmit_handshake(struct timer_list *timer) if (peer->timer_handshake_attempts > MAX_TIMER_HANDSHAKES) { pr_debug("%s: Handshake for peer %llu (%pISpfsc) did not complete after %d attempts, giving up\n", peer->device->dev->name, peer->internal_id, - &peer->endpoint.addr, MAX_TIMER_HANDSHAKES + 2); + &peer->endpoint.addr, (int)MAX_TIMER_HANDSHAKES + 2); del_timer(&peer->timer_send_keepalive); /* We drop all packets without a keypair and don't try again, @@ -64,7 +64,7 @@ static void wg_expired_retransmit_handshake(struct timer_list *timer) ++peer->timer_handshake_attempts; pr_debug("%s: Handshake for peer %llu (%pISpfsc) did not complete after %d seconds, retrying (try %d)\n", peer->device->dev->name, peer->internal_id, - &peer->endpoint.addr, REKEY_TIMEOUT, + &peer->endpoint.addr, (int)REKEY_TIMEOUT, peer->timer_handshake_attempts + 1); /* We clear the endpoint address src address, in case this is @@ -94,7 +94,7 @@ static void wg_expired_new_handshake(struct timer_list *timer) pr_debug("%s: Retrying handshake with peer %llu (%pISpfsc) because we stopped hearing back after %d seconds\n", peer->device->dev->name, peer->internal_id, - &peer->endpoint.addr, KEEPALIVE_TIMEOUT + REKEY_TIMEOUT); + &peer->endpoint.addr, (int)(KEEPALIVE_TIMEOUT + REKEY_TIMEOUT)); /* We clear the endpoint address src address, in case this is the cause * of trouble. */ @@ -126,7 +126,7 @@ static void wg_queued_expired_zero_key_material(struct work_struct *work) pr_debug("%s: Zeroing out all keys for peer %llu (%pISpfsc), since we haven't received a new one in %d seconds\n", peer->device->dev->name, peer->internal_id, - &peer->endpoint.addr, REJECT_AFTER_TIME * 3); + &peer->endpoint.addr, (int)REJECT_AFTER_TIME * 3); wg_noise_handshake_clear(&peer->handshake); wg_noise_keypairs_clear(&peer->keypairs); wg_peer_put(peer); From 2f31633da843eb0457f6212eba435ac538c28f58 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 11 Apr 2023 08:21:02 +0200 Subject: [PATCH 2688/4345] PCI: pciehp: Fix AB-BA deadlock between reset_lock and device_lock commit f5eff5591b8f9c5effd25c92c758a127765f74c1 upstream. In 2013, commits 2e35afaefe64 ("PCI: pciehp: Add reset_slot() method") 608c388122c7 ("PCI: Add slot reset option to pci_dev_reset()") amended PCIe hotplug to mask Presence Detect Changed events during a Secondary Bus Reset. The reset thus no longer causes gratuitous slot bringdown and bringup. However the commits neglected to serialize reset with code paths reading slot registers. For instance, a slot bringup due to an earlier hotplug event may see the Presence Detect State bit cleared during a concurrent Secondary Bus Reset. In 2018, commit 5b3f7b7d062b ("PCI: pciehp: Avoid slot access during reset") retrofitted the missing locking. It introduced a reset_lock which serializes a Secondary Bus Reset with other parts of pciehp. Unfortunately the locking turns out to be overzealous: reset_lock is held for the entire enumeration and de-enumeration of hotplugged devices, including driver binding and unbinding. Driver binding and unbinding acquires device_lock while the reset_lock of the ancestral hotplug port is held. A concurrent Secondary Bus Reset acquires the ancestral reset_lock while already holding the device_lock. The asymmetric locking order in the two code paths can lead to AB-BA deadlocks. Michael Haeuptle reports such deadlocks on simultaneous hot-removal and vfio release (the latter implies a Secondary Bus Reset): pciehp_ist() # down_read(reset_lock) pciehp_handle_presence_or_link_change() pciehp_disable_slot() __pciehp_disable_slot() remove_board() pciehp_unconfigure_device() pci_stop_and_remove_bus_device() pci_stop_bus_device() pci_stop_dev() device_release_driver() device_release_driver_internal() __device_driver_lock() # device_lock() SYS_munmap() vfio_device_fops_release() vfio_device_group_close() vfio_device_close() vfio_device_last_close() vfio_pci_core_close_device() vfio_pci_core_disable() # device_lock() __pci_reset_function_locked() pci_reset_bus_function() pci_dev_reset_slot_function() pci_reset_hotplug_slot() pciehp_reset_slot() # down_write(reset_lock) Ian May reports the same deadlock on simultaneous hot-removal and an AER-induced Secondary Bus Reset: aer_recover_work_func() pcie_do_recovery() aer_root_reset() pci_bus_error_reset() pci_slot_reset() pci_slot_lock() # device_lock() pci_reset_hotplug_slot() pciehp_reset_slot() # down_write(reset_lock) Fix by releasing the reset_lock during driver binding and unbinding, thereby splitting and shrinking the critical section. Driver binding and unbinding is protected by the device_lock() and thus serialized with a Secondary Bus Reset. There's no need to additionally protect it with the reset_lock. However, pciehp does not bind and unbind devices directly, but rather invokes PCI core functions which also perform certain enumeration and de-enumeration steps. The reset_lock's purpose is to protect slot registers, not enumeration and de-enumeration of hotplugged devices. That would arguably be the job of the PCI core, not the PCIe hotplug driver. After all, an AER-induced Secondary Bus Reset may as well happen during boot-time enumeration of the PCI hierarchy and there's no locking to prevent that either. Exempting *de-enumeration* from the reset_lock is relatively harmless: A concurrent Secondary Bus Reset may foil config space accesses such as PME interrupt disablement. But if the device is physically gone, those accesses are pointless anyway. If the device is physically present and only logically removed through an Attention Button press or the sysfs "power" attribute, PME interrupts as well as DMA cannot come through because pciehp_unconfigure_device() disables INTx and Bus Master bits. That's still protected by the reset_lock in the present commit. Exempting *enumeration* from the reset_lock also has limited impact: The exempted call to pci_bus_add_device() may perform device accesses through pcibios_bus_add_device() and pci_fixup_device() which are now no longer protected from a concurrent Secondary Bus Reset. Otherwise there should be no impact. In essence, the present commit seeks to fix the AB-BA deadlocks while still retaining a best-effort reset protection for enumeration and de-enumeration of hotplugged devices -- until a general solution is implemented in the PCI core. Link: https://lore.kernel.org/linux-pci/CS1PR8401MB0728FC6FDAB8A35C22BD90EC95F10@CS1PR8401MB0728.NAMPRD84.PROD.OUTLOOK.COM Link: https://lore.kernel.org/linux-pci/20200615143250.438252-1-ian.may@canonical.com Link: https://lore.kernel.org/linux-pci/ce878dab-c0c4-5bd0-a725-9805a075682d@amd.com Link: https://lore.kernel.org/linux-pci/ed831249-384a-6d35-0831-70af191e9bce@huawei.com Link: https://bugzilla.kernel.org/show_bug.cgi?id=215590 Fixes: 5b3f7b7d062b ("PCI: pciehp: Avoid slot access during reset") Link: https://lore.kernel.org/r/fef2b2e9edf245c049a8c5b94743c0f74ff5008a.1681191902.git.lukas@wunner.de Reported-by: Michael Haeuptle Reported-by: Ian May Reported-by: Andrey Grodzovsky Reported-by: Rahul Kumar Reported-by: Jialin Zhang Tested-by: Anatoli Antonovitch Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org # v4.19+ Cc: Dan Stein Cc: Ashok Raj Cc: Alex Michon Cc: Xiongfeng Wang Cc: Alex Williamson Cc: Mika Westerberg Cc: Sathyanarayanan Kuppuswamy Signed-off-by: Greg Kroah-Hartman --- drivers/pci/hotplug/pciehp_pci.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c index d17f3bf36f70..ad12515a4a12 100644 --- a/drivers/pci/hotplug/pciehp_pci.c +++ b/drivers/pci/hotplug/pciehp_pci.c @@ -63,7 +63,14 @@ int pciehp_configure_device(struct controller *ctrl) pci_assign_unassigned_bridge_resources(bridge); pcie_bus_configure_settings(parent); + + /* + * Release reset_lock during driver binding + * to avoid AB-BA deadlock with device_lock. + */ + up_read(&ctrl->reset_lock); pci_bus_add_devices(parent); + down_read_nested(&ctrl->reset_lock, ctrl->depth); out: pci_unlock_rescan_remove(); @@ -104,7 +111,15 @@ void pciehp_unconfigure_device(struct controller *ctrl, bool presence) list_for_each_entry_safe_reverse(dev, temp, &parent->devices, bus_list) { pci_dev_get(dev); + + /* + * Release reset_lock during driver unbinding + * to avoid AB-BA deadlock with device_lock. + */ + up_read(&ctrl->reset_lock); pci_stop_and_remove_bus_device(dev); + down_read_nested(&ctrl->reset_lock, ctrl->depth); + /* * Ensure that no new Requests will be generated from * the device. From b978269ddad4ee2d5d6788eeb0e7e344a7d480e1 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Thu, 16 Mar 2023 13:40:59 +0530 Subject: [PATCH 2689/4345] PCI: qcom: Fix the incorrect register usage in v2.7.0 config commit 2542e16c392508800f1d9037feee881a9c444951 upstream. Qcom PCIe IP version v2.7.0 and its derivatives don't contain the PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT register. Instead, they have the new PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2 register. So fix the incorrect register usage which is modifying a different register. Also in this IP version, this register change doesn't depend on MSI being enabled. So remove that check also. Link: https://lore.kernel.org/r/20230316081117.14288-2-manivannan.sadhasivam@linaro.org Fixes: ed8cc3b1fc84 ("PCI: qcom: Add support for SDM845 PCIe controller") Signed-off-by: Manivannan Sadhasivam Signed-off-by: Lorenzo Pieralisi Cc: # 5.6+ Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/dwc/pcie-qcom.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 5fbd80908a99..c68e14271c02 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -1210,11 +1210,9 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie) val |= BIT(4); writel(val, pcie->parf + PCIE20_PARF_MHI_CLOCK_RESET_CTRL); - if (IS_ENABLED(CONFIG_PCI_MSI)) { - val = readl(pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT); - val |= BIT(31); - writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT); - } + val = readl(pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2); + val |= BIT(31); + writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2); return 0; err_disable_clocks: From 27dc207c386eb6719e9cb695f7afb15e52b07d28 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:14 +0200 Subject: [PATCH 2690/4345] USB: dwc3: fix runtime pm imbalance on probe errors commit 9a8ad10c9f2e0925ff26308ec6756b93fc2f4977 upstream. Make sure not to suspend the device when probe fails to avoid disabling clocks and phys multiple times. Fixes: 328082376aea ("usb: dwc3: fix runtime PM in error path") Cc: stable@vger.kernel.org # 4.8 Cc: Roger Quadros Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-2-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index d73f624ed42a..fc84677635a3 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1567,13 +1567,11 @@ static int dwc3_probe(struct platform_device *pdev) spin_lock_init(&dwc->lock); mutex_init(&dwc->mutex); + pm_runtime_get_noresume(dev); pm_runtime_set_active(dev); pm_runtime_use_autosuspend(dev); pm_runtime_set_autosuspend_delay(dev, DWC3_DEFAULT_AUTOSUSPEND_DELAY); pm_runtime_enable(dev); - ret = pm_runtime_get_sync(dev); - if (ret < 0) - goto err1; pm_runtime_forbid(dev); @@ -1633,12 +1631,10 @@ err3: dwc3_free_event_buffers(dwc); err2: - pm_runtime_allow(&pdev->dev); - -err1: - pm_runtime_put_sync(&pdev->dev); - pm_runtime_disable(&pdev->dev); - + pm_runtime_allow(dev); + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + pm_runtime_put_noidle(dev); disable_clks: clk_bulk_disable_unprepare(dwc->num_clks, dwc->clks); assert_reset: From a71cb92ec4315b7b61983bae35ec00be62901b25 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:15 +0200 Subject: [PATCH 2691/4345] USB: dwc3: fix runtime pm imbalance on unbind commit 44d257e9012ee8040e41d224d0e5bfb5ef5427ea upstream. Make sure to balance the runtime PM usage count on driver unbind by adding back the pm_runtime_allow() call that had been erroneously removed. Fixes: 266d0493900a ("usb: dwc3: core: don't trigger runtime pm when remove driver") Cc: stable@vger.kernel.org # 5.9 Cc: Li Jun Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-3-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index fc84677635a3..5709b959b1d9 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1655,6 +1655,7 @@ static int dwc3_remove(struct platform_device *pdev) dwc3_core_exit(dwc); dwc3_ulpi_exit(dwc); + pm_runtime_allow(&pdev->dev); pm_runtime_disable(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); From b009006887e32bf62ff5c0da73b9bafd18dd996b Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Thu, 13 Apr 2023 16:39:58 -0500 Subject: [PATCH 2692/4345] hwmon: (k10temp) Check range scale when CUR_TEMP register is read-write MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 0c072385348e3ac5229145644055d3e2afb5b3db upstream. Spec says, when CUR_TEMP_TJ_SEL == 3 and CUR_TEMP_RANGE_SEL == 0, it should use RangeUnadjusted is 0, which is (CurTmp*0.125 -49) C. The CUR_TEMP register is read-write when CUR_TEMP_TJ_SEL == 3 (bit 17-16). Add the check to detect it. Sensors command's output before the patch. $sensors k10temp-pci-00c3 Adapter: PCI adapter Tctl: +76.6°C <- Wrong value Tccd1: +26.5°C Tccd2: +27.5°C Tccd3: +27.2°C Tccd4: +27.5°C Tccd5: +26.0°C Tccd6: +26.2°C Tccd7: +25.0°C Tccd8: +26.5°C Sensors command's output after the patch. $sensors k10temp-pci-00c3 Adapter: PCI adapter Tctl: +28.8°C <- corrected value Tccd1: +27.5°C Tccd2: +28.5°C Tccd3: +28.5°C Tccd4: +28.5°C Tccd5: +27.0°C Tccd6: +27.5°C Tccd7: +27.0°C Tccd8: +27.5°C Signed-off-by: Babu Moger Fixes: 1b59788979ac ("hwmon: (k10temp) Add temperature offset for Ryzen 2700X") Link: https://lore.kernel.org/r/20230413213958.847634-1-babu.moger@amd.com Cc: stable@vger.kernel.org Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/k10temp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 3bc2551577a3..74a67089ad07 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -74,6 +74,7 @@ static DEFINE_MUTEX(nb_smu_ind_mutex); #define ZEN_CUR_TEMP_SHIFT 21 #define ZEN_CUR_TEMP_RANGE_SEL_MASK BIT(19) +#define ZEN_CUR_TEMP_TJ_SEL_MASK GENMASK(17, 16) #define ZEN_SVI_BASE 0x0005A000 @@ -173,7 +174,8 @@ static long get_raw_temp(struct k10temp_data *data) data->read_tempreg(data->pdev, ®val); temp = (regval >> ZEN_CUR_TEMP_SHIFT) * 125; - if (regval & data->temp_adjust_mask) + if ((regval & data->temp_adjust_mask) || + (regval & ZEN_CUR_TEMP_TJ_SEL_MASK) == ZEN_CUR_TEMP_TJ_SEL_MASK) temp -= 49000; return temp; } From aed39acf7ed6beb8f671d2b23709a863aed565e8 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Wed, 19 Apr 2023 11:36:55 +1200 Subject: [PATCH 2693/4345] hwmon: (adt7475) Use device_property APIs when configuring polarity MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2a8e41ad337508fc5d598c0f9288890214f8e318 upstream. On DT unaware platforms of_property_read_u32_array() returns -ENOSYS which wasn't handled by the code treating adi,pwm-active-state as optional. Update the code to use device_property_read_u32_array() which deals gracefully with DT unaware platforms. Fixes: 86da28eed4fb ("hwmon: (adt7475) Add support for inverting pwm output") Reported-by: Mariusz Białończyk Link: https://lore.kernel.org/linux-hwmon/52e26a67-9131-2dc0-40cb-db5c07370027@alliedtelesis.co.nz/T/#mdd0505801e0a4e72340de009a47c0fca4f771ed3 Signed-off-by: Chris Packham Link: https://lore.kernel.org/r/20230418233656.869055-2-chris.packham@alliedtelesis.co.nz Cc: stable@vger.kernel.org Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- drivers/hwmon/adt7475.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 6b84822e7d93..22e314725def 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -1515,9 +1515,9 @@ static int adt7475_set_pwm_polarity(struct i2c_client *client) int ret, i; u8 val; - ret = of_property_read_u32_array(client->dev.of_node, - "adi,pwm-active-state", states, - ARRAY_SIZE(states)); + ret = device_property_read_u32_array(&client->dev, + "adi,pwm-active-state", states, + ARRAY_SIZE(states)); if (ret) return ret; From 7c5811b95c573d0e080f9fd8d708fc2a706cf784 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 17 Apr 2023 15:37:55 +0200 Subject: [PATCH 2694/4345] posix-cpu-timers: Implement the missing timer_wait_running callback commit f7abf14f0001a5a47539d9f60bbdca649e43536b upstream. For some unknown reason the introduction of the timer_wait_running callback missed to fixup posix CPU timers, which went unnoticed for almost four years. Marco reported recently that the WARN_ON() in timer_wait_running() triggers with a posix CPU timer test case. Posix CPU timers have two execution models for expiring timers depending on CONFIG_POSIX_CPU_TIMERS_TASK_WORK: 1) If not enabled, the expiry happens in hard interrupt context so spin waiting on the remote CPU is reasonably time bound. Implement an empty stub function for that case. 2) If enabled, the expiry happens in task work before returning to user space or guest mode. The expired timers are marked as firing and moved from the timer queue to a local list head with sighand lock held. Once the timers are moved, sighand lock is dropped and the expiry happens in fully preemptible context. That means the expiring task can be scheduled out, migrated, interrupted etc. So spin waiting on it is more than suboptimal. The timer wheel has a timer_wait_running() mechanism for RT, which uses a per CPU timer-base expiry lock which is held by the expiry code and the task waiting for the timer function to complete blocks on that lock. This does not work in the same way for posix CPU timers as there is no timer base and expiry for process wide timers can run on any task belonging to that process, but the concept of waiting on an expiry lock can be used too in a slightly different way: - Add a mutex to struct posix_cputimers_work. This struct is per task and used to schedule the expiry task work from the timer interrupt. - Add a task_struct pointer to struct cpu_timer which is used to store a the task which runs the expiry. That's filled in when the task moves the expired timers to the local expiry list. That's not affecting the size of the k_itimer union as there are bigger union members already - Let the task take the expiry mutex around the expiry function - Let the waiter acquire a task reference with rcu_read_lock() held and block on the expiry mutex This avoids spin-waiting on a task which might not even be on a CPU and works nicely for RT too. Fixes: ec8f954a40da ("posix-timers: Use a callback for cancel synchronization on PREEMPT_RT") Reported-by: Marco Elver Signed-off-by: Thomas Gleixner Tested-by: Marco Elver Tested-by: Sebastian Andrzej Siewior Reviewed-by: Frederic Weisbecker Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87zg764ojw.ffs@tglx Signed-off-by: Greg Kroah-Hartman --- include/linux/posix-timers.h | 17 ++++--- kernel/time/posix-cpu-timers.c | 81 ++++++++++++++++++++++++++++------ kernel/time/posix-timers.c | 4 ++ 3 files changed, 82 insertions(+), 20 deletions(-) diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 913aa60228b1..8e284161b65e 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -4,6 +4,7 @@ #include #include +#include #include #include #include @@ -63,16 +64,18 @@ static inline int clockid_to_fd(const clockid_t clk) * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig * @head: timerqueue head on which this timer is queued - * @task: Pointer to target task + * @pid: Pointer to target task PID * @elist: List head for the expiry list * @firing: Timer is currently firing + * @handling: Pointer to the task which handles expiry */ struct cpu_timer { - struct timerqueue_node node; - struct timerqueue_head *head; - struct pid *pid; - struct list_head elist; - int firing; + struct timerqueue_node node; + struct timerqueue_head *head; + struct pid *pid; + struct list_head elist; + int firing; + struct task_struct __rcu *handling; }; static inline bool cpu_timer_enqueue(struct timerqueue_head *head, @@ -129,10 +132,12 @@ struct posix_cputimers { /** * posix_cputimers_work - Container for task work based posix CPU timer expiry * @work: The task work to be scheduled + * @mutex: Mutex held around expiry in context of this task work * @scheduled: @work has been scheduled already, no further processing */ struct posix_cputimers_work { struct callback_head work; + struct mutex mutex; unsigned int scheduled; }; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 5d76edd0ad9c..bede1e608d95 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -782,6 +782,8 @@ static u64 collect_timerqueue(struct timerqueue_head *head, return expires; ctmr->firing = 1; + /* See posix_cpu_timer_wait_running() */ + rcu_assign_pointer(ctmr->handling, current); cpu_timer_dequeue(ctmr); list_add_tail(&ctmr->elist, firing); } @@ -1097,7 +1099,49 @@ static void handle_posix_cpu_timers(struct task_struct *tsk); #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK static void posix_cpu_timers_work(struct callback_head *work) { + struct posix_cputimers_work *cw = container_of(work, typeof(*cw), work); + + mutex_lock(&cw->mutex); handle_posix_cpu_timers(current); + mutex_unlock(&cw->mutex); +} + +/* + * Invoked from the posix-timer core when a cancel operation failed because + * the timer is marked firing. The caller holds rcu_read_lock(), which + * protects the timer and the task which is expiring it from being freed. + */ +static void posix_cpu_timer_wait_running(struct k_itimer *timr) +{ + struct task_struct *tsk = rcu_dereference(timr->it.cpu.handling); + + /* Has the handling task completed expiry already? */ + if (!tsk) + return; + + /* Ensure that the task cannot go away */ + get_task_struct(tsk); + /* Now drop the RCU protection so the mutex can be locked */ + rcu_read_unlock(); + /* Wait on the expiry mutex */ + mutex_lock(&tsk->posix_cputimers_work.mutex); + /* Release it immediately again. */ + mutex_unlock(&tsk->posix_cputimers_work.mutex); + /* Drop the task reference. */ + put_task_struct(tsk); + /* Relock RCU so the callsite is balanced */ + rcu_read_lock(); +} + +static void posix_cpu_timer_wait_running_nsleep(struct k_itimer *timr) +{ + /* Ensure that timr->it.cpu.handling task cannot go away */ + rcu_read_lock(); + spin_unlock_irq(&timr->it_lock); + posix_cpu_timer_wait_running(timr); + rcu_read_unlock(); + /* @timr is on stack and is valid */ + spin_lock_irq(&timr->it_lock); } /* @@ -1113,6 +1157,7 @@ void clear_posix_cputimers_work(struct task_struct *p) sizeof(p->posix_cputimers_work.work)); init_task_work(&p->posix_cputimers_work.work, posix_cpu_timers_work); + mutex_init(&p->posix_cputimers_work.mutex); p->posix_cputimers_work.scheduled = false; } @@ -1191,6 +1236,18 @@ static inline void __run_posix_cpu_timers(struct task_struct *tsk) lockdep_posixtimer_exit(); } +static void posix_cpu_timer_wait_running(struct k_itimer *timr) +{ + cpu_relax(); +} + +static void posix_cpu_timer_wait_running_nsleep(struct k_itimer *timr) +{ + spin_unlock_irq(&timr->it_lock); + cpu_relax(); + spin_lock_irq(&timr->it_lock); +} + static inline bool posix_cpu_timers_work_scheduled(struct task_struct *tsk) { return false; @@ -1299,6 +1356,8 @@ static void handle_posix_cpu_timers(struct task_struct *tsk) */ if (likely(cpu_firing >= 0)) cpu_timer_fire(timer); + /* See posix_cpu_timer_wait_running() */ + rcu_assign_pointer(timer->it.cpu.handling, NULL); spin_unlock(&timer->it_lock); } } @@ -1434,23 +1493,16 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, expires = cpu_timer_getexpires(&timer.it.cpu); error = posix_cpu_timer_set(&timer, 0, &zero_it, &it); if (!error) { - /* - * Timer is now unarmed, deletion can not fail. - */ + /* Timer is now unarmed, deletion can not fail. */ posix_cpu_timer_del(&timer); + } else { + while (error == TIMER_RETRY) { + posix_cpu_timer_wait_running_nsleep(&timer); + error = posix_cpu_timer_del(&timer); + } } - spin_unlock_irq(&timer.it_lock); - while (error == TIMER_RETRY) { - /* - * We need to handle case when timer was or is in the - * middle of firing. In other cases we already freed - * resources. - */ - spin_lock_irq(&timer.it_lock); - error = posix_cpu_timer_del(&timer); - spin_unlock_irq(&timer.it_lock); - } + spin_unlock_irq(&timer.it_lock); if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) { /* @@ -1560,6 +1612,7 @@ const struct k_clock clock_posix_cpu = { .timer_del = posix_cpu_timer_del, .timer_get = posix_cpu_timer_get, .timer_rearm = posix_cpu_timer_rearm, + .timer_wait_running = posix_cpu_timer_wait_running, }; const struct k_clock clock_process = { diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 724ca7eb1a6e..d089627f2f2b 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -846,6 +846,10 @@ static struct k_itimer *timer_wait_running(struct k_itimer *timer, rcu_read_lock(); unlock_timer(timer, *flags); + /* + * kc->timer_wait_running() might drop RCU lock. So @timer + * cannot be touched anymore after the function returns! + */ if (!WARN_ON_ONCE(!kc->timer_wait_running)) kc->timer_wait_running(timer); From 68494eb75f1fd1366a969a8374fd72cfb9dacadb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 14 Jul 2021 13:06:38 -0300 Subject: [PATCH 2695/4345] perf sched: Cast PTHREAD_STACK_MIN to int as it may turn into sysconf(__SC_THREAD_STACK_MIN_VALUE) commit d08c84e01afa7a7eee6badab25d5420fa847f783 upstream. In fedora rawhide the PTHREAD_STACK_MIN define may end up expanded to a sysconf() call, and that will return 'long int', breaking the build: 45 fedora:rawhide : FAIL gcc version 11.1.1 20210623 (Red Hat 11.1.1-6) (GCC) builtin-sched.c: In function 'create_tasks': /git/perf-5.14.0-rc1/tools/include/linux/kernel.h:43:24: error: comparison of distinct pointer types lacks a cast [-Werror] 43 | (void) (&_max1 == &_max2); \ | ^~ builtin-sched.c:673:34: note: in expansion of macro 'max' 673 | (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); | ^~~ cc1: all warnings being treated as errors $ grep __sysconf /usr/include/*/*.h /usr/include/bits/pthread_stack_min-dynamic.h:extern long int __sysconf (int __name) __THROW; /usr/include/bits/pthread_stack_min-dynamic.h:# define PTHREAD_STACK_MIN __sysconf (__SC_THREAD_STACK_MIN_VALUE) /usr/include/bits/time.h:extern long int __sysconf (int); /usr/include/bits/time.h:# define CLK_TCK ((__clock_t) __sysconf (2)) /* 2 is _SC_CLK_TCK */ $ So cast it to int to cope with that. Signed-off-by: Arnaldo Carvalho de Melo Cc: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- tools/perf/builtin-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index d3b5f5faf8c1..02e5774cabb6 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -670,7 +670,7 @@ static void create_tasks(struct perf_sched *sched) err = pthread_attr_init(&attr); BUG_ON(err); err = pthread_attr_setstacksize(&attr, - (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); + (size_t) max(16 * 1024, (int)PTHREAD_STACK_MIN)); BUG_ON(err); err = pthread_mutex_lock(&sched->start_work_mutex); BUG_ON(err); From 874bdf43b4a7dc5463c31508f62b3e42eb237b08 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 3 May 2023 21:09:39 -0700 Subject: [PATCH 2696/4345] blk-mq: release crypto keyslot before reporting I/O complete commit 9cd1e566676bbcb8a126acd921e4e194e6339603 upstream. Once all I/O using a blk_crypto_key has completed, filesystems can call blk_crypto_evict_key(). However, the block layer currently doesn't call blk_crypto_put_keyslot() until the request is being freed, which happens after upper layers have been told (via bio_endio()) the I/O has completed. This causes a race condition where blk_crypto_evict_key() can see 'slot_refs != 0' without there being an actual bug. This makes __blk_crypto_evict_key() hit the 'WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)' and return without doing anything, eventually causing a use-after-free in blk_crypto_reprogram_all_keys(). (This is a very rare bug and has only been seen when per-file keys are being used with fscrypt.) There are two options to fix this: either release the keyslot before bio_endio() is called on the request's last bio, or make __blk_crypto_evict_key() ignore slot_refs. Let's go with the first solution, since it preserves the ability to report bugs (via WARN_ON_ONCE) where a key is evicted while still in-use. Fixes: a892c8d52c02 ("block: Inline encryption support for blk-mq") Cc: stable@vger.kernel.org Reviewed-by: Nathan Huckleberry Reviewed-by: Christoph Hellwig Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20230315183907.53675-2-ebiggers@kernel.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/blk-core.c | 7 +++++++ block/blk-crypto-internal.h | 25 +++++++++++++++++++++---- block/blk-crypto.c | 24 ++++++++++++------------ block/blk-merge.c | 2 ++ block/blk-mq.c | 2 +- 5 files changed, 43 insertions(+), 17 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 9afb79b322fb..d0d0dd8151f7 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1444,6 +1444,13 @@ bool blk_update_request(struct request *req, blk_status_t error, req->q->integrity.profile->complete_fn(req, nr_bytes); #endif + /* + * Upper layers may call blk_crypto_evict_key() anytime after the last + * bio_endio(). Therefore, the keyslot must be released before that. + */ + if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req)) + __blk_crypto_rq_put_keyslot(req); + if (unlikely(error && !blk_rq_is_passthrough(req) && !(req->rq_flags & RQF_QUIET))) print_req_error(req, error, __func__); diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h index 0d36aae538d7..8e0834557620 100644 --- a/block/blk-crypto-internal.h +++ b/block/blk-crypto-internal.h @@ -60,6 +60,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq) return rq->crypt_ctx; } +static inline bool blk_crypto_rq_has_keyslot(struct request *rq) +{ + return rq->crypt_keyslot; +} + #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool bio_crypt_rq_ctx_compatible(struct request *rq, @@ -93,6 +98,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq) return false; } +static inline bool blk_crypto_rq_has_keyslot(struct request *rq) +{ + return false; +} + #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ void __bio_crypt_advance(struct bio *bio, unsigned int bytes); @@ -127,14 +137,21 @@ static inline bool blk_crypto_bio_prep(struct bio **bio_ptr) return true; } -blk_status_t __blk_crypto_init_request(struct request *rq); -static inline blk_status_t blk_crypto_init_request(struct request *rq) +blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq); +static inline blk_status_t blk_crypto_rq_get_keyslot(struct request *rq) { if (blk_crypto_rq_is_encrypted(rq)) - return __blk_crypto_init_request(rq); + return __blk_crypto_rq_get_keyslot(rq); return BLK_STS_OK; } +void __blk_crypto_rq_put_keyslot(struct request *rq); +static inline void blk_crypto_rq_put_keyslot(struct request *rq) +{ + if (blk_crypto_rq_has_keyslot(rq)) + __blk_crypto_rq_put_keyslot(rq); +} + void __blk_crypto_free_request(struct request *rq); static inline void blk_crypto_free_request(struct request *rq) { @@ -173,7 +190,7 @@ static inline blk_status_t blk_crypto_insert_cloned_request(struct request *rq) { if (blk_crypto_rq_is_encrypted(rq)) - return blk_crypto_init_request(rq); + return blk_crypto_rq_get_keyslot(rq); return BLK_STS_OK; } diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 5ffa9aab49de..0506adfd9ca6 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -216,26 +216,26 @@ static bool bio_crypt_check_alignment(struct bio *bio) return true; } -blk_status_t __blk_crypto_init_request(struct request *rq) +blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq) { return blk_ksm_get_slot_for_key(rq->q->ksm, rq->crypt_ctx->bc_key, &rq->crypt_keyslot); } -/** - * __blk_crypto_free_request - Uninitialize the crypto fields of a request. - * - * @rq: The request whose crypto fields to uninitialize. - * - * Completely uninitializes the crypto fields of a request. If a keyslot has - * been programmed into some inline encryption hardware, that keyslot is - * released. The rq->crypt_ctx is also freed. - */ -void __blk_crypto_free_request(struct request *rq) +void __blk_crypto_rq_put_keyslot(struct request *rq) { blk_ksm_put_slot(rq->crypt_keyslot); + rq->crypt_keyslot = NULL; +} + +void __blk_crypto_free_request(struct request *rq) +{ + /* The keyslot, if one was needed, should have been released earlier. */ + if (WARN_ON_ONCE(rq->crypt_keyslot)) + __blk_crypto_rq_put_keyslot(rq); + mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool); - blk_crypto_rq_set_defaults(rq); + rq->crypt_ctx = NULL; } /** diff --git a/block/blk-merge.c b/block/blk-merge.c index fbba277364f0..f3b016b31af8 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -801,6 +801,8 @@ static struct request *attempt_merge(struct request_queue *q, if (!blk_discard_mergable(req)) elv_merge_requests(q, req, next); + blk_crypto_rq_put_keyslot(next); + /* * 'next' is going away, so update stats accordingly */ diff --git a/block/blk-mq.c b/block/blk-mq.c index cf66de0f00fd..e153a36c9ba3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2193,7 +2193,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) blk_mq_bio_to_request(rq, bio, nr_segs); - ret = blk_crypto_init_request(rq); + ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) { bio->bi_status = ret; bio_endio(bio); From 5072008bef2386237dab112dd0770bd82b7a46c1 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 3 May 2023 21:09:40 -0700 Subject: [PATCH 2697/4345] blk-crypto: make blk_crypto_evict_key() return void commit 70493a63ba04f754f7a7dd53a4fcc82700181490 upstream. blk_crypto_evict_key() is only called in contexts such as inode eviction where failure is not an option. So there is nothing the caller can do with errors except log them. (dm-table.c does "use" the error code, but only to pass on to upper layers, so it doesn't really count.) Just make blk_crypto_evict_key() return void and log errors itself. Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230315183907.53675-2-ebiggers@kernel.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/blk-crypto.c | 22 ++++++++++------------ include/linux/blk-crypto.h | 4 ++-- 2 files changed, 12 insertions(+), 14 deletions(-) diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 0506adfd9ca6..d8c48ee44ba6 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "blk-crypto-internal.h" @@ -393,19 +394,16 @@ int blk_crypto_start_using_key(const struct blk_crypto_key *key, * Upper layers (filesystems) must call this function to ensure that a key is * evicted from any hardware that it might have been programmed into. The key * must not be in use by any in-flight IO when this function is called. - * - * Return: 0 on success or if key is not present in the q's ksm, -err on error. */ -int blk_crypto_evict_key(struct request_queue *q, - const struct blk_crypto_key *key) +void blk_crypto_evict_key(struct request_queue *q, + const struct blk_crypto_key *key) { - if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg)) - return blk_ksm_evict_key(q->ksm, key); + int err; - /* - * If the request queue's associated inline encryption hardware didn't - * have support for the key, then the key might have been programmed - * into the fallback keyslot manager, so try to evict from there. - */ - return blk_crypto_fallback_evict_key(key); + if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg)) + err = blk_ksm_evict_key(q->ksm, key); + else + err = blk_crypto_fallback_evict_key(key); + if (err) + pr_warn_ratelimited("error %d evicting key\n", err); } diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index 69b24fe92cbf..5e96bad54804 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -97,8 +97,8 @@ int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, int blk_crypto_start_using_key(const struct blk_crypto_key *key, struct request_queue *q); -int blk_crypto_evict_key(struct request_queue *q, - const struct blk_crypto_key *key); +void blk_crypto_evict_key(struct request_queue *q, + const struct blk_crypto_key *key); bool blk_crypto_config_supported(struct request_queue *q, const struct blk_crypto_config *cfg); From 701a8220762ff90615dc91d3543f789391b63298 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 3 May 2023 21:09:41 -0700 Subject: [PATCH 2698/4345] blk-crypto: make blk_crypto_evict_key() more robust commit 5c7cb94452901a93e90c2230632e2c12a681bc92 upstream. If blk_crypto_evict_key() sees that the key is still in-use (due to a bug) or that ->keyslot_evict failed, it currently just returns while leaving the key linked into the keyslot management structures. However, blk_crypto_evict_key() is only called in contexts such as inode eviction where failure is not an option. So actually the caller proceeds with freeing the blk_crypto_key regardless of the return value of blk_crypto_evict_key(). These two assumptions don't match, and the result is that there can be a use-after-free in blk_crypto_reprogram_all_keys() after one of these errors occurs. (Note, these errors *shouldn't* happen; we're just talking about what happens if they do anyway.) Fix this by making blk_crypto_evict_key() unlink the key from the keyslot management structures even on failure. Also improve some comments. Fixes: 1b2628397058 ("block: Keyslot Manager for Inline Encryption") Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230315183907.53675-2-ebiggers@kernel.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/blk-crypto.c | 29 +++++++++++++++++++-------- block/keyslot-manager.c | 43 ++++++++++++++++++++--------------------- 2 files changed, 42 insertions(+), 30 deletions(-) diff --git a/block/blk-crypto.c b/block/blk-crypto.c index d8c48ee44ba6..87ec55d4354f 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -385,15 +385,20 @@ int blk_crypto_start_using_key(const struct blk_crypto_key *key, } /** - * blk_crypto_evict_key() - Evict a key from any inline encryption hardware - * it may have been programmed into - * @q: The request queue who's associated inline encryption hardware this key - * might have been programmed into - * @key: The key to evict + * blk_crypto_evict_key() - Evict a blk_crypto_key from a request_queue + * @q: a request_queue on which I/O using the key may have been done + * @key: the key to evict * - * Upper layers (filesystems) must call this function to ensure that a key is - * evicted from any hardware that it might have been programmed into. The key - * must not be in use by any in-flight IO when this function is called. + * For a given request_queue, this function removes the given blk_crypto_key + * from the keyslot management structures and evicts it from any underlying + * hardware keyslot(s) or blk-crypto-fallback keyslot it may have been + * programmed into. + * + * Upper layers must call this before freeing the blk_crypto_key. It must be + * called for every request_queue the key may have been used on. The key must + * no longer be in use by any I/O when this function is called. + * + * Context: May sleep. */ void blk_crypto_evict_key(struct request_queue *q, const struct blk_crypto_key *key) @@ -404,6 +409,14 @@ void blk_crypto_evict_key(struct request_queue *q, err = blk_ksm_evict_key(q->ksm, key); else err = blk_crypto_fallback_evict_key(key); + /* + * An error can only occur here if the key failed to be evicted from a + * keyslot (due to a hardware or driver issue) or is allegedly still in + * use by I/O (due to a kernel bug). Even in these cases, the key is + * still unlinked from the keyslot management structures, and the caller + * is allowed and expected to free it right away. There's nothing + * callers can do to handle errors, so just log them and return void. + */ if (err) pr_warn_ratelimited("error %d evicting key\n", err); } diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c index 86f8195d8039..17a1f1ba44ef 100644 --- a/block/keyslot-manager.c +++ b/block/keyslot-manager.c @@ -305,44 +305,43 @@ bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, return true; } -/** - * blk_ksm_evict_key() - Evict a key from the lower layer device. - * @ksm: The keyslot manager to evict from - * @key: The key to evict - * - * Find the keyslot that the specified key was programmed into, and evict that - * slot from the lower layer device. The slot must not be in use by any - * in-flight IO when this function is called. - * - * Context: Process context. Takes and releases ksm->lock. - * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY - * if the keyslot is still in use, or another -errno value on other - * error. +/* + * This is an internal function that evicts a key from an inline encryption + * device that can be either a real device or the blk-crypto-fallback "device". + * It is used only by blk_crypto_evict_key(); see that function for details. */ int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, const struct blk_crypto_key *key) { struct blk_ksm_keyslot *slot; - int err = 0; + int err; blk_ksm_hw_enter(ksm); slot = blk_ksm_find_keyslot(ksm, key); - if (!slot) - goto out_unlock; + if (!slot) { + /* + * Not an error, since a key not in use by I/O is not guaranteed + * to be in a keyslot. There can be more keys than keyslots. + */ + err = 0; + goto out; + } if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) { + /* BUG: key is still in use by I/O */ err = -EBUSY; - goto out_unlock; + goto out_remove; } err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, blk_ksm_get_slot_idx(slot)); - if (err) - goto out_unlock; - +out_remove: + /* + * Callers free the key even on error, so unlink the key from the hash + * table and clear slot->key even on error. + */ hlist_del(&slot->hash_node); slot->key = NULL; - err = 0; -out_unlock: +out: blk_ksm_hw_exit(ksm); return err; } From c8714ddf3ccf94a50574ba5db2e2128eb6e77b75 Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Thu, 23 Dec 2021 12:21:37 -0800 Subject: [PATCH 2699/4345] ext4: use ext4_journal_start/stop for fast commit transactions commit 2729cfdcfa1cc49bef5a90d046fa4a187fdfcc69 upstream. This patch drops all calls to ext4_fc_start_update() and ext4_fc_stop_update(). To ensure that there are no ongoing journal updates during fast commit, we also make jbd2_fc_begin_commit() lock journal for updates. This way we don't have to maintain two different transaction start stop APIs for fast commit and full commit. This patch doesn't remove the functions altogether since in future we want to have inode level locking for fast commits. Signed-off-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/20211223202140.2061101-2-harshads@google.com Signed-off-by: Theodore Ts'o Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/ext4/acl.c | 2 -- fs/ext4/extents.c | 2 -- fs/ext4/file.c | 4 ---- fs/ext4/inode.c | 7 +------ fs/ext4/ioctl.c | 8 +------- fs/jbd2/journal.c | 2 ++ 6 files changed, 4 insertions(+), 21 deletions(-) diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 68aaed48315f..76f634d185f1 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -242,7 +242,6 @@ retry: handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) return PTR_ERR(handle); - ext4_fc_start_update(inode); if ((type == ACL_TYPE_ACCESS) && acl) { error = posix_acl_update_mode(inode, &mode, &acl); @@ -260,7 +259,6 @@ retry: } out_stop: ext4_journal_stop(handle); - ext4_fc_stop_update(inode); if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; return error; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index bf0872bb34f6..6c06ce9dd6bd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4694,7 +4694,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; - ext4_fc_start_update(inode); inode_lock(inode); ret = ext4_convert_inline_data(inode); inode_unlock(inode); @@ -4764,7 +4763,6 @@ out: inode_unlock(inode); trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); exit: - ext4_fc_stop_update(inode); return ret; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 0f61e0aa85d6..f42cc1fe0ba1 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -260,7 +260,6 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb, if (iocb->ki_flags & IOCB_NOWAIT) return -EOPNOTSUPP; - ext4_fc_start_update(inode); inode_lock(inode); ret = ext4_write_checks(iocb, from); if (ret <= 0) @@ -272,7 +271,6 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb, out: inode_unlock(inode); - ext4_fc_stop_update(inode); if (likely(ret > 0)) { iocb->ki_pos += ret; ret = generic_write_sync(iocb, ret); @@ -559,9 +557,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; } - ext4_fc_start_update(inode); ret = ext4_orphan_add(handle, inode); - ext4_fc_stop_update(inode); if (ret) { ext4_journal_stop(handle); goto out; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9bd5f8b0511b..a93b93de5a60 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5437,7 +5437,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (error) return error; } - ext4_fc_start_update(inode); + if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { handle_t *handle; @@ -5461,7 +5461,6 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (error) { ext4_journal_stop(handle); - ext4_fc_stop_update(inode); return error; } /* Update corresponding info in inode so that everything is in @@ -5473,7 +5472,6 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) error = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); if (unlikely(error)) { - ext4_fc_stop_update(inode); return error; } } @@ -5488,12 +5486,10 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (attr->ia_size > sbi->s_bitmap_maxbytes) { - ext4_fc_stop_update(inode); return -EFBIG; } } if (!S_ISREG(inode->i_mode)) { - ext4_fc_stop_update(inode); return -EINVAL; } @@ -5619,7 +5615,6 @@ err_out: ext4_std_error(inode->i_sb, error); if (!error) error = rc; - ext4_fc_stop_update(inode); return error; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 53bdc67a815f..1171618f6549 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1322,13 +1322,7 @@ out: long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { - long ret; - - ext4_fc_start_update(file_inode(filp)); - ret = __ext4_ioctl(filp, cmd, arg); - ext4_fc_stop_update(file_inode(filp)); - - return ret; + return __ext4_ioctl(filp, cmd, arg); } #ifdef CONFIG_COMPAT diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 6689d235de8a..fee325d62bfd 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -757,6 +757,7 @@ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) } journal->j_flags |= JBD2_FAST_COMMIT_ONGOING; write_unlock(&journal->j_state_lock); + jbd2_journal_lock_updates(journal); return 0; } @@ -768,6 +769,7 @@ EXPORT_SYMBOL(jbd2_fc_begin_commit); */ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) { + jbd2_journal_unlock_updates(journal); if (journal->j_fc_cleanup_callback) journal->j_fc_cleanup_callback(journal, 0); write_lock(&journal->j_state_lock); From a863ac03fae0c07e9eba8129fc4b8dcabe0ad670 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 27 Mar 2023 16:54:14 +0200 Subject: [PATCH 2700/4345] staging: iio: resolver: ads1210: fix config mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 16313403d873ff17a587818b61f84c8cb4971cef upstream. As stated in the device datasheet [1], bits a0 and a1 have to be set to 1 for the configuration mode. [1]: https://www.analog.com/media/en/technical-documentation/data-sheets/ad2s1210.pdf Fixes: b19e9ad5e2cb9 ("staging:iio:resolver:ad2s1210 general driver cleanup") Cc: stable Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20230327145414.1505537-1-nuno.sa@analog.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/iio/resolver/ad2s1210.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/iio/resolver/ad2s1210.c b/drivers/staging/iio/resolver/ad2s1210.c index 74adb82f37c3..a19cfb2998c9 100644 --- a/drivers/staging/iio/resolver/ad2s1210.c +++ b/drivers/staging/iio/resolver/ad2s1210.c @@ -101,7 +101,7 @@ struct ad2s1210_state { static const int ad2s1210_mode_vals[4][2] = { [MOD_POS] = { 0, 0 }, [MOD_VEL] = { 0, 1 }, - [MOD_CONFIG] = { 1, 0 }, + [MOD_CONFIG] = { 1, 1 }, }; static inline void ad2s1210_set_mode(enum ad2s1210_mode mode, From 29b89908fdd94127e9b6e2f29ecceae82a1314bc Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 5 Apr 2023 11:03:42 +0200 Subject: [PATCH 2701/4345] xhci: fix debugfs register accesses while suspended commit 735baf1b23458f71a8b15cb924af22c9ff9cd125 upstream. Wire up the debugfs regset device pointer so that the controller is resumed before accessing registers to avoid crashing or locking up if it happens to be runtime suspended. Fixes: 02b6fdc2a153 ("usb: xhci: Add debugfs interface for xHCI driver") Cc: stable@vger.kernel.org # 4.15: 30332eeefec8: debugfs: regset32: Add Runtime PM support Cc: stable@vger.kernel.org # 4.15 Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230405090342.7363-1-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-debugfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index dc832ddf7033..bd40caeeb21c 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -133,6 +133,7 @@ static void xhci_debugfs_regset(struct xhci_hcd *xhci, u32 base, regset->regs = regs; regset->nregs = nregs; regset->base = hcd->regs + base; + regset->dev = hcd->self.controller; debugfs_create_regset32((const char *)rgs->name, 0444, parent, regset); } From 2884595932ea07481590b2c10e20fcb729eaaad0 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Tue, 24 Jan 2023 17:31:26 +0000 Subject: [PATCH 2702/4345] tick/nohz: Fix cpu_is_hotpluggable() by checking with nohz subsystem commit 58d7668242647e661a20efe065519abd6454287e upstream. For CONFIG_NO_HZ_FULL systems, the tick_do_timer_cpu cannot be offlined. However, cpu_is_hotpluggable() still returns true for those CPUs. This causes torture tests that do offlining to end up trying to offline this CPU causing test failures. Such failure happens on all architectures. Fix the repeated error messages thrown by this (even if the hotplug errors are harmless) by asking the opinion of the nohz subsystem on whether the CPU can be hotplugged. [ Apply Frederic Weisbecker feedback on refactoring tick_nohz_cpu_down(). ] For drivers/base/ portion: Acked-by: Greg Kroah-Hartman Acked-by: Frederic Weisbecker Cc: Frederic Weisbecker Cc: "Paul E. McKenney" Cc: Zhouyi Zhou Cc: Will Deacon Cc: Marc Zyngier Cc: rcu Cc: stable@vger.kernel.org Fixes: 2987557f52b9 ("driver-core/cpu: Expose hotpluggability to the rest of the kernel") Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- drivers/base/cpu.c | 3 ++- include/linux/tick.h | 2 ++ kernel/time/tick-sched.c | 11 ++++++++--- 3 files changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 24dd532c8e5e..33e0526907eb 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -489,7 +489,8 @@ static const struct attribute_group *cpu_root_attr_groups[] = { bool cpu_is_hotpluggable(unsigned cpu) { struct device *dev = get_cpu_device(cpu); - return dev && container_of(dev, struct cpu, dev)->hotpluggable; + return dev && container_of(dev, struct cpu, dev)->hotpluggable + && tick_nohz_cpu_hotpluggable(cpu); } EXPORT_SYMBOL_GPL(cpu_is_hotpluggable); diff --git a/include/linux/tick.h b/include/linux/tick.h index 7340613c7eff..a90a8f7759a2 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -211,6 +211,7 @@ extern void tick_nohz_dep_set_signal(struct signal_struct *signal, enum tick_dep_bits bit); extern void tick_nohz_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit); +extern bool tick_nohz_cpu_hotpluggable(unsigned int cpu); /* * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases @@ -275,6 +276,7 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { } +static inline bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { return true; } static inline void tick_dep_set(enum tick_dep_bits bit) { } static inline void tick_dep_clear(enum tick_dep_bits bit) { } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 92fb738813f3..e4e0d032126b 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -426,7 +426,7 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask) tick_nohz_full_running = true; } -static int tick_nohz_cpu_down(unsigned int cpu) +bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { /* * The tick_do_timer_cpu CPU handles housekeeping duty (unbound @@ -434,8 +434,13 @@ static int tick_nohz_cpu_down(unsigned int cpu) * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && tick_do_timer_cpu == cpu) - return -EBUSY; - return 0; + return false; + return true; +} + +static int tick_nohz_cpu_down(unsigned int cpu) +{ + return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY; } void __init tick_nohz_init(void) From 6d5993d5696339b2f4fbfbe0f9f940388f3cf636 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 4 Apr 2023 12:09:14 +0000 Subject: [PATCH 2703/4345] ipmi:ssif: Add send_retries increment commit 6ce7995a43febe693d4894033c6e29314970646a upstream. A recent change removed an increment of send_retries, re-add it. Fixes: 95767ed78a18 ipmi:ssif: resend_msg() cannot fail Reported-by: Pavel Machek Cc: stable@vger.kernel.org Signed-off-by: Corey Minyard Signed-off-by: Greg Kroah-Hartman --- drivers/char/ipmi/ipmi_ssif.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 20dc2452815c..3005e95df3be 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -564,8 +564,10 @@ static void retry_timeout(struct timer_list *t) if (waiting) start_get(ssif_info); - if (resend) + if (resend) { start_resend(ssif_info); + ssif_inc_stat(ssif_info, send_retries); + } } static void watch_timeout(struct timer_list *t) From 1b633da2fecf954440cd71d786368a407256a2ee Mon Sep 17 00:00:00 2001 From: Zhang Yuchen Date: Wed, 12 Apr 2023 15:49:07 +0800 Subject: [PATCH 2704/4345] ipmi: fix SSIF not responding under certain cond. commit 6d2555cde2918409b0331560e66f84a0ad4849c6 upstream. The ipmi communication is not restored after a specific version of BMC is upgraded on our server. The ipmi driver does not respond after printing the following log: ipmi_ssif: Invalid response getting flags: 1c 1 I found that after entering this branch, ssif_info->ssif_state always holds SSIF_GETTING_FLAGS and never return to IDLE. As a result, the driver cannot be loaded, because the driver status is checked during the unload process and must be IDLE in shutdown_ssif(): while (ssif_info->ssif_state != SSIF_IDLE) schedule_timeout(1); The process trigger this problem is: 1. One msg timeout and next msg start send, and call ssif_set_need_watch(). 2. ssif_set_need_watch()->watch_timeout()->start_flag_fetch() change ssif_state to SSIF_GETTING_FLAGS. 3. In msg_done_handler() ssif_state == SSIF_GETTING_FLAGS, if an error message is received, the second branch does not modify the ssif_state. 4. All retry action need IS_SSIF_IDLE() == True. Include retry action in watch_timeout(), msg_done_handler(). Sending msg does not work either. SSIF_IDLE is also checked in start_next_msg(). 5. The only thing that can be triggered in the SSIF driver is watch_timeout(), after destory_user(), this timer will stop too. So, if enter this branch, the ssif_state will remain SSIF_GETTING_FLAGS and can't send msg, no timer started, can't unload. We did a comparative test before and after adding this patch, and the result is effective. Fixes: 259307074bfc ("ipmi: Add SMBus interface driver (SSIF)") Cc: stable@vger.kernel.org Signed-off-by: Zhang Yuchen Message-Id: <20230412074907.80046-1-zhangyuchen.lcr@bytedance.com> Signed-off-by: Corey Minyard Signed-off-by: Greg Kroah-Hartman --- drivers/char/ipmi/ipmi_ssif.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 3005e95df3be..a3745fa643f3 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -794,9 +794,9 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, } else if (data[0] != (IPMI_NETFN_APP_REQUEST | 1) << 2 || data[1] != IPMI_GET_MSG_FLAGS_CMD) { /* - * Don't abort here, maybe it was a queued - * response to a previous command. + * Recv error response, give up. */ + ssif_info->ssif_state = SSIF_IDLE; ipmi_ssif_unlock_cond(ssif_info, flags); dev_warn(&ssif_info->client->dev, "Invalid response getting flags: %x %x\n", From fcd2da2e6bf2640a31a2a5b118b50dc3635c707b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 2 Mar 2023 14:49:50 -0800 Subject: [PATCH 2705/4345] kheaders: Use array declaration instead of char commit b69edab47f1da8edd8e7bfdf8c70f51a2a5d89fb upstream. Under CONFIG_FORTIFY_SOURCE, memcpy() will check the size of destination and source buffers. Defining kernel_headers_data as "char" would trip this check. Since these addresses are treated as byte arrays, define them as arrays (as done everywhere else). This was seen with: $ cat /sys/kernel/kheaders.tar.xz >> /dev/null detected buffer overflow in memcpy kernel BUG at lib/string_helpers.c:1027! ... RIP: 0010:fortify_panic+0xf/0x20 [...] Call Trace: ikheaders_read+0x45/0x50 [kheaders] kernfs_fop_read_iter+0x1a4/0x2f0 ... Reported-by: Jakub Kicinski Link: https://lore.kernel.org/bpf/20230302112130.6e402a98@kernel.org/ Acked-by: Joel Fernandes (Google) Reviewed-by: Alexander Lobakin Tested-by: Jakub Kicinski Fixes: 43d8ce9d65a5 ("Provide in-kernel headers to make extending kernel easier") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230302224946.never.243-kees@kernel.org Signed-off-by: Greg Kroah-Hartman --- kernel/kheaders.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/kheaders.c b/kernel/kheaders.c index 8f69772af77b..42163c9e94e5 100644 --- a/kernel/kheaders.c +++ b/kernel/kheaders.c @@ -26,15 +26,15 @@ asm ( " .popsection \n" ); -extern char kernel_headers_data; -extern char kernel_headers_data_end; +extern char kernel_headers_data[]; +extern char kernel_headers_data_end[]; static ssize_t ikheaders_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) { - memcpy(buf, &kernel_headers_data + off, len); + memcpy(buf, &kernel_headers_data[off], len); return len; } @@ -48,8 +48,8 @@ static struct bin_attribute kheaders_attr __ro_after_init = { static int __init ikheaders_init(void) { - kheaders_attr.size = (&kernel_headers_data_end - - &kernel_headers_data); + kheaders_attr.size = (kernel_headers_data_end - + kernel_headers_data); return sysfs_create_bin_file(kernel_kobj, &kheaders_attr); } From c1cabb10e07287019527132a74baa684df77af8b Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 9 Apr 2023 17:15:52 +0200 Subject: [PATCH 2706/4345] pwm: meson: Fix axg ao mux parents commit eb411c0cf59ae6344b34bc6f0d298a22b300627e upstream. This fix is basically the same as 9bce02ef0dfa ("pwm: meson: Fix the G12A AO clock parents order"). Vendor driver referenced there has xtal as first parent also for axg ao. In addition fix the name of the aoclk81 clock. Apparently name aoclk81 as used by the vendor driver was changed when mainlining the axg clock driver. Fixes: bccaa3f917c9 ("pwm: meson: Add clock source configuration for Meson-AXG") Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Reviewed-by: Martin Blumenstingl Signed-off-by: Thierry Reding Signed-off-by: Greg Kroah-Hartman --- drivers/pwm/pwm-meson.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 237bb8e06593..1699d311e860 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -424,7 +424,7 @@ static const struct meson_pwm_data pwm_axg_ee_data = { }; static const char * const pwm_axg_ao_parent_names[] = { - "aoclk81", "xtal", "fclk_div4", "fclk_div5" + "xtal", "axg_ao_clk81", "fclk_div4", "fclk_div5" }; static const struct meson_pwm_data pwm_axg_ao_data = { From dda1372c8d838e389c1a9fc805bdead96fa4d52b Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 11 Apr 2023 07:34:11 +0200 Subject: [PATCH 2707/4345] pwm: meson: Fix g12a ao clk81 name commit 9e4fa80ab7ef9eb4f7b1ea9fc31e0eb040e85e25 upstream. Fix the name of the aoclk81 clock. Apparently name aoclk81 as used by the vendor driver was changed when mainlining the g12a clock driver. Fixes: f41efceb46e6 ("pwm: meson: Add clock source configuration for Meson G12A") Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Reviewed-by: Martin Blumenstingl Signed-off-by: Thierry Reding Signed-off-by: Greg Kroah-Hartman --- drivers/pwm/pwm-meson.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 1699d311e860..0283163ddbe8 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -433,7 +433,7 @@ static const struct meson_pwm_data pwm_axg_ao_data = { }; static const char * const pwm_g12a_ao_ab_parent_names[] = { - "xtal", "aoclk81", "fclk_div4", "fclk_div5" + "xtal", "g12a_ao_clk81", "fclk_div4", "fclk_div5" }; static const struct meson_pwm_data pwm_g12a_ao_ab_data = { @@ -442,7 +442,7 @@ static const struct meson_pwm_data pwm_g12a_ao_ab_data = { }; static const char * const pwm_g12a_ao_cd_parent_names[] = { - "xtal", "aoclk81", + "xtal", "g12a_ao_clk81", }; static const struct meson_pwm_data pwm_g12a_ao_cd_data = { From 1c99f65d6af2a454bfd5207b4f6a97c8474a1191 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 27 Apr 2023 17:59:20 +0200 Subject: [PATCH 2708/4345] ring-buffer: Sync IRQ works before buffer destruction commit 675751bb20634f981498c7d66161584080cc061e upstream. If something was written to the buffer just before destruction, it may be possible (maybe not in a real system, but it did happen in ARCH=um with time-travel) to destroy the ringbuffer before the IRQ work ran, leading this KASAN report (or a crash without KASAN): BUG: KASAN: slab-use-after-free in irq_work_run_list+0x11a/0x13a Read of size 8 at addr 000000006d640a48 by task swapper/0 CPU: 0 PID: 0 Comm: swapper Tainted: G W O 6.3.0-rc1 #7 Stack: 60c4f20f 0c203d48 41b58ab3 60f224fc 600477fa 60f35687 60c4f20f 601273dd 00000008 6101eb00 6101eab0 615be548 Call Trace: [<60047a58>] show_stack+0x25e/0x282 [<60c609e0>] dump_stack_lvl+0x96/0xfd [<60c50d4c>] print_report+0x1a7/0x5a8 [<603078d3>] kasan_report+0xc1/0xe9 [<60308950>] __asan_report_load8_noabort+0x1b/0x1d [<60232844>] irq_work_run_list+0x11a/0x13a [<602328b4>] irq_work_tick+0x24/0x34 [<6017f9dc>] update_process_times+0x162/0x196 [<6019f335>] tick_sched_handle+0x1a4/0x1c3 [<6019fd9e>] tick_sched_timer+0x79/0x10c [<601812b9>] __hrtimer_run_queues.constprop.0+0x425/0x695 [<60182913>] hrtimer_interrupt+0x16c/0x2c4 [<600486a3>] um_timer+0x164/0x183 [...] Allocated by task 411: save_stack_trace+0x99/0xb5 stack_trace_save+0x81/0x9b kasan_save_stack+0x2d/0x54 kasan_set_track+0x34/0x3e kasan_save_alloc_info+0x25/0x28 ____kasan_kmalloc+0x8b/0x97 __kasan_kmalloc+0x10/0x12 __kmalloc+0xb2/0xe8 load_elf_phdrs+0xee/0x182 [...] The buggy address belongs to the object at 000000006d640800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 584 bytes inside of freed 1024-byte region [000000006d640800, 000000006d640c00) Add the appropriate irq_work_sync() so the work finishes before the buffers are destroyed. Prior to the commit in the Fixes tag below, there was only a single global IRQ work, so this issue didn't exist. Link: https://lore.kernel.org/linux-trace-kernel/20230427175920.a76159263122.I8295e405c44362a86c995e9c2c37e3e03810aa56@changeid Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Fixes: 15693458c4bc ("tracing/ring-buffer: Move poll wake ups into ring buffer code") Signed-off-by: Johannes Berg Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ring_buffer.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 21b07c7c6ee5..1fe6b29366f1 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1644,6 +1644,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) struct list_head *head = cpu_buffer->pages; struct buffer_page *bpage, *tmp; + irq_work_sync(&cpu_buffer->irq_work.work); + free_buffer_page(cpu_buffer->reader_page); if (head) { @@ -1750,6 +1752,8 @@ ring_buffer_free(struct trace_buffer *buffer) cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node); + irq_work_sync(&buffer->irq_work.work); + for_each_buffer_cpu(buffer, cpu) rb_free_cpu_buffer(buffer->buffers[cpu]); From ff86deaba1fa15b3035ffe6f0059c2493535124e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Mon, 13 Mar 2023 10:17:24 +0100 Subject: [PATCH 2709/4345] crypto: api - Demote BUG_ON() in crypto_unregister_alg() to a WARN_ON() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit a543ada7db729514ddd3ba4efa45f4c7b802ad85 upstream. The crypto_unregister_alg() function expects callers to ensure that any algorithm that is unregistered has a refcnt of exactly 1, and issues a BUG_ON() if this is not the case. However, there are in fact drivers that will call crypto_unregister_alg() without ensuring that the refcnt has been lowered first, most notably on system shutdown. This causes the BUG_ON() to trigger, which prevents a clean shutdown and hangs the system. To avoid such hangs on shutdown, demote the BUG_ON() in crypto_unregister_alg() to a WARN_ON() with early return. Cc stable because this problem was observed on a 6.2 kernel, cf the link below. Link: https://lore.kernel.org/r/87r0tyq8ph.fsf@toke.dk Cc: stable@vger.kernel.org Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algapi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/crypto/algapi.c b/crypto/algapi.c index 9de27daa98b4..42dca17dc2d9 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -456,7 +456,9 @@ void crypto_unregister_alg(struct crypto_alg *alg) if (WARN(ret, "Algorithm %s is not registered", alg->cra_driver_name)) return; - BUG_ON(refcount_read(&alg->cra_refcnt) != 1); + if (WARN_ON(refcount_read(&alg->cra_refcnt) != 1)) + return; + if (alg->cra_destroy) alg->cra_destroy(alg); From 47e61cadc7a5f3dffd42d2d6fda81be163f1ab82 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 11 Apr 2023 12:14:26 +0100 Subject: [PATCH 2710/4345] MIPS: fw: Allow firmware to pass a empty env commit ee1809ed7bc456a72dc8410b475b73021a3a68d5 upstream. fw_getenv will use env entry to determine style of env, however it is legal for firmware to just pass a empty list. Check if first entry exist before running strchr to avoid null pointer dereference. Cc: stable@vger.kernel.org Link: https://github.com/clbr/n64bootloader/issues/5 Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Greg Kroah-Hartman --- arch/mips/fw/lib/cmdline.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/fw/lib/cmdline.c b/arch/mips/fw/lib/cmdline.c index f24cbb4a39b5..892765b742bb 100644 --- a/arch/mips/fw/lib/cmdline.c +++ b/arch/mips/fw/lib/cmdline.c @@ -53,7 +53,7 @@ char *fw_getenv(char *envname) { char *result = NULL; - if (_fw_envp != NULL) { + if (_fw_envp != NULL && fw_envp(0) != NULL) { /* * Return a pointer to the given environment variable. * YAMON uses "name", "value" pairs, while U-Boot uses From 0a89d4a075524cf1f865cfdbb9cf38ab8e3e5409 Mon Sep 17 00:00:00 2001 From: Jonathan McDowell Date: Tue, 28 Feb 2023 18:28:58 +0000 Subject: [PATCH 2711/4345] crypto: safexcel - Cleanup ring IRQ workqueues on load failure commit ca25c00ccbc5f942c63897ed23584cfc66e8ec81 upstream. A failure loading the safexcel driver results in the following warning on boot, because the IRQ affinity has not been correctly cleaned up. Ensure we clean up the affinity and workqueues on a failure to load the driver. crypto-safexcel: probe of f2800000.crypto failed with error -2 ------------[ cut here ]------------ WARNING: CPU: 1 PID: 232 at kernel/irq/manage.c:1913 free_irq+0x300/0x340 Modules linked in: hwmon mdio_i2c crypto_safexcel(+) md5 sha256_generic libsha256 authenc libdes omap_rng rng_core nft_masq nft_nat nft_chain_nat nf_nat nft_ct nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables libcrc32c nfnetlink fuse autofs4 CPU: 1 PID: 232 Comm: systemd-udevd Tainted: G W 6.1.6-00002-g9d4898824677 #3 Hardware name: MikroTik RB5009 (DT) pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : free_irq+0x300/0x340 lr : free_irq+0x2e0/0x340 sp : ffff800008fa3890 x29: ffff800008fa3890 x28: 0000000000000000 x27: 0000000000000000 x26: ffff8000008e6dc0 x25: ffff000009034cac x24: ffff000009034d50 x23: 0000000000000000 x22: 000000000000004a x21: ffff0000093e0d80 x20: ffff000009034c00 x19: ffff00000615fc00 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 000075f5c1584c5e x14: 0000000000000017 x13: 0000000000000000 x12: 0000000000000040 x11: ffff000000579b60 x10: ffff000000579b62 x9 : ffff800008bbe370 x8 : ffff000000579dd0 x7 : 0000000000000000 x6 : ffff000000579e18 x5 : ffff000000579da8 x4 : ffff800008ca0000 x3 : ffff800008ca0188 x2 : 0000000013033204 x1 : ffff000009034c00 x0 : ffff8000087eadf0 Call trace: free_irq+0x300/0x340 devm_irq_release+0x14/0x20 devres_release_all+0xa0/0x100 device_unbind_cleanup+0x14/0x60 really_probe+0x198/0x2d4 __driver_probe_device+0x74/0xdc driver_probe_device+0x3c/0x110 __driver_attach+0x8c/0x190 bus_for_each_dev+0x6c/0xc0 driver_attach+0x20/0x30 bus_add_driver+0x148/0x1fc driver_register+0x74/0x120 __platform_driver_register+0x24/0x30 safexcel_init+0x48/0x1000 [crypto_safexcel] do_one_initcall+0x4c/0x1b0 do_init_module+0x44/0x1cc load_module+0x1724/0x1be4 __do_sys_finit_module+0xbc/0x110 __arm64_sys_finit_module+0x1c/0x24 invoke_syscall+0x44/0x110 el0_svc_common.constprop.0+0xc0/0xe0 do_el0_svc+0x20/0x80 el0_svc+0x14/0x4c el0t_64_sync_handler+0xb0/0xb4 el0t_64_sync+0x148/0x14c ---[ end trace 0000000000000000 ]--- Fixes: 1b44c5a60c13 ("inside-secure - add SafeXcel EIP197 crypto engine driver") Signed-off-by: Jonathan McDowell Cc: stable@vger.kernel.org Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/inside-secure/safexcel.c | 37 ++++++++++++++++++------- 1 file changed, 27 insertions(+), 10 deletions(-) diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c index fbcf52e46d17..7de9b9d20de0 100644 --- a/drivers/crypto/inside-secure/safexcel.c +++ b/drivers/crypto/inside-secure/safexcel.c @@ -1634,19 +1634,23 @@ static int safexcel_probe_generic(void *pdev, &priv->ring[i].rdr); if (ret) { dev_err(dev, "Failed to initialize rings\n"); - return ret; + goto err_cleanup_rings; } priv->ring[i].rdr_req = devm_kcalloc(dev, EIP197_DEFAULT_RING_SIZE, sizeof(*priv->ring[i].rdr_req), GFP_KERNEL); - if (!priv->ring[i].rdr_req) - return -ENOMEM; + if (!priv->ring[i].rdr_req) { + ret = -ENOMEM; + goto err_cleanup_rings; + } ring_irq = devm_kzalloc(dev, sizeof(*ring_irq), GFP_KERNEL); - if (!ring_irq) - return -ENOMEM; + if (!ring_irq) { + ret = -ENOMEM; + goto err_cleanup_rings; + } ring_irq->priv = priv; ring_irq->ring = i; @@ -1660,7 +1664,8 @@ static int safexcel_probe_generic(void *pdev, ring_irq); if (irq < 0) { dev_err(dev, "Failed to get IRQ ID for ring %d\n", i); - return irq; + ret = irq; + goto err_cleanup_rings; } priv->ring[i].irq = irq; @@ -1672,8 +1677,10 @@ static int safexcel_probe_generic(void *pdev, snprintf(wq_name, 9, "wq_ring%d", i); priv->ring[i].workqueue = create_singlethread_workqueue(wq_name); - if (!priv->ring[i].workqueue) - return -ENOMEM; + if (!priv->ring[i].workqueue) { + ret = -ENOMEM; + goto err_cleanup_rings; + } priv->ring[i].requests = 0; priv->ring[i].busy = false; @@ -1690,16 +1697,26 @@ static int safexcel_probe_generic(void *pdev, ret = safexcel_hw_init(priv); if (ret) { dev_err(dev, "HW init failed (%d)\n", ret); - return ret; + goto err_cleanup_rings; } ret = safexcel_register_algorithms(priv); if (ret) { dev_err(dev, "Failed to register algorithms (%d)\n", ret); - return ret; + goto err_cleanup_rings; } return 0; + +err_cleanup_rings: + for (i = 0; i < priv->config.rings; i++) { + if (priv->ring[i].irq) + irq_set_affinity_hint(priv->ring[i].irq, NULL); + if (priv->ring[i].workqueue) + destroy_workqueue(priv->ring[i].workqueue); + } + + return ret; } static void safexcel_hw_reset_rings(struct safexcel_crypto_priv *priv) From eb18bc5a8678f431c500e6da1b8b5f34478d5bc1 Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Fri, 6 Jan 2023 15:09:34 +0800 Subject: [PATCH 2712/4345] rcu: Avoid stack overflow due to __rcu_irq_enter_check_tick() being kprobe-ed commit 7a29fb4a4771124bc61de397dbfc1554dbbcc19c upstream. Registering a kprobe on __rcu_irq_enter_check_tick() can cause kernel stack overflow as shown below. This issue can be reproduced by enabling CONFIG_NO_HZ_FULL and booting the kernel with argument "nohz_full=", and then giving the following commands at the shell prompt: # cd /sys/kernel/tracing/ # echo 'p:mp1 __rcu_irq_enter_check_tick' >> kprobe_events # echo 1 > events/kprobes/enable This commit therefore adds __rcu_irq_enter_check_tick() to the kprobes blacklist using NOKPROBE_SYMBOL(). Insufficient stack space to handle exception! ESR: 0x00000000f2000004 -- BRK (AArch64) FAR: 0x0000ffffccf3e510 Task stack: [0xffff80000ad30000..0xffff80000ad38000] IRQ stack: [0xffff800008050000..0xffff800008058000] Overflow stack: [0xffff089c36f9f310..0xffff089c36fa0310] CPU: 5 PID: 190 Comm: bash Not tainted 6.2.0-rc2-00320-g1f5abbd77e2c #19 Hardware name: linux,dummy-virt (DT) pstate: 400003c5 (nZcv DAIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __rcu_irq_enter_check_tick+0x0/0x1b8 lr : ct_nmi_enter+0x11c/0x138 sp : ffff80000ad30080 x29: ffff80000ad30080 x28: ffff089c82e20000 x27: 0000000000000000 x26: 0000000000000000 x25: ffff089c02a8d100 x24: 0000000000000000 x23: 00000000400003c5 x22: 0000ffffccf3e510 x21: ffff089c36fae148 x20: ffff80000ad30120 x19: ffffa8da8fcce148 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: ffffa8da8e44ea6c x14: ffffa8da8e44e968 x13: ffffa8da8e03136c x12: 1fffe113804d6809 x11: ffff6113804d6809 x10: 0000000000000a60 x9 : dfff800000000000 x8 : ffff089c026b404f x7 : 00009eec7fb297f7 x6 : 0000000000000001 x5 : ffff80000ad30120 x4 : dfff800000000000 x3 : ffffa8da8e3016f4 x2 : 0000000000000003 x1 : 0000000000000000 x0 : 0000000000000000 Kernel panic - not syncing: kernel stack overflow CPU: 5 PID: 190 Comm: bash Not tainted 6.2.0-rc2-00320-g1f5abbd77e2c #19 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0xf8/0x108 show_stack+0x20/0x30 dump_stack_lvl+0x68/0x84 dump_stack+0x1c/0x38 panic+0x214/0x404 add_taint+0x0/0xf8 panic_bad_stack+0x144/0x160 handle_bad_stack+0x38/0x58 __bad_stack+0x78/0x7c __rcu_irq_enter_check_tick+0x0/0x1b8 arm64_enter_el1_dbg.isra.0+0x14/0x20 el1_dbg+0x2c/0x90 el1h_64_sync_handler+0xcc/0xe8 el1h_64_sync+0x64/0x68 __rcu_irq_enter_check_tick+0x0/0x1b8 arm64_enter_el1_dbg.isra.0+0x14/0x20 el1_dbg+0x2c/0x90 el1h_64_sync_handler+0xcc/0xe8 el1h_64_sync+0x64/0x68 __rcu_irq_enter_check_tick+0x0/0x1b8 arm64_enter_el1_dbg.isra.0+0x14/0x20 el1_dbg+0x2c/0x90 el1h_64_sync_handler+0xcc/0xe8 el1h_64_sync+0x64/0x68 __rcu_irq_enter_check_tick+0x0/0x1b8 [...] el1_dbg+0x2c/0x90 el1h_64_sync_handler+0xcc/0xe8 el1h_64_sync+0x64/0x68 __rcu_irq_enter_check_tick+0x0/0x1b8 arm64_enter_el1_dbg.isra.0+0x14/0x20 el1_dbg+0x2c/0x90 el1h_64_sync_handler+0xcc/0xe8 el1h_64_sync+0x64/0x68 __rcu_irq_enter_check_tick+0x0/0x1b8 arm64_enter_el1_dbg.isra.0+0x14/0x20 el1_dbg+0x2c/0x90 el1h_64_sync_handler+0xcc/0xe8 el1h_64_sync+0x64/0x68 __rcu_irq_enter_check_tick+0x0/0x1b8 el1_interrupt+0x28/0x60 el1h_64_irq_handler+0x18/0x28 el1h_64_irq+0x64/0x68 __ftrace_set_clr_event_nolock+0x98/0x198 __ftrace_set_clr_event+0x58/0x80 system_enable_write+0x144/0x178 vfs_write+0x174/0x738 ksys_write+0xd0/0x188 __arm64_sys_write+0x4c/0x60 invoke_syscall+0x64/0x180 el0_svc_common.constprop.0+0x84/0x160 do_el0_svc+0x48/0xe8 el0_svc+0x34/0xd0 el0t_64_sync_handler+0xb8/0xc0 el0t_64_sync+0x190/0x194 SMP: stopping secondary CPUs Kernel Offset: 0x28da86000000 from 0xffff800008000000 PHYS_OFFSET: 0xfffff76600000000 CPU features: 0x00000,01a00100,0000421b Memory Limit: none Acked-by: Joel Fernandes (Google) Link: https://lore.kernel.org/all/20221119040049.795065-1-zhengyejian1@huawei.com/ Fixes: aaf2bc50df1f ("rcu: Abstract out rcu_irq_enter_check_tick() from rcu_nmi_enter()") Signed-off-by: Zheng Yejian Cc: stable@vger.kernel.org Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/rcu/tree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 9cce4e13af41..30e1d7fedb5f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -964,6 +964,7 @@ void __rcu_irq_enter_check_tick(void) } raw_spin_unlock_rcu_node(rdp->mynode); } +NOKPROBE_SYMBOL(__rcu_irq_enter_check_tick); #endif /* CONFIG_NO_HZ_FULL */ /** From 680c419d0d8a67a3a8601174547aae6a4e26e5f9 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 31 Mar 2023 14:32:18 +0200 Subject: [PATCH 2713/4345] reiserfs: Add security prefix to xattr name in reiserfs_security_write() commit d82dcd9e21b77d338dc4875f3d4111f0db314a7c upstream. Reiserfs sets a security xattr at inode creation time in two stages: first, it calls reiserfs_security_init() to obtain the xattr from active LSMs; then, it calls reiserfs_security_write() to actually write that xattr. Unfortunately, it seems there is a wrong expectation that LSMs provide the full xattr name in the form 'security.'. However, LSMs always provided just the suffix, causing reiserfs to not write the xattr at all (if the suffix is shorter than the prefix), or to write an xattr with the wrong name. Add a temporary buffer in reiserfs_security_write(), and write to it the full xattr name, before passing it to reiserfs_xattr_set_handle(). Also replace the name length check with a check that the full xattr name is not larger than XATTR_NAME_MAX. Cc: stable@vger.kernel.org # v2.6.x Fixes: 57fe60df6241 ("reiserfs: add atomic addition of selinux attributes during inode creation") Signed-off-by: Roberto Sassu Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- fs/reiserfs/xattr_security.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index 59d87f9f72fb..159af6c26f4b 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -81,11 +81,15 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, struct inode *inode, struct reiserfs_security_handle *sec) { + char xattr_name[XATTR_NAME_MAX + 1] = XATTR_SECURITY_PREFIX; int error; - if (strlen(sec->name) < sizeof(XATTR_SECURITY_PREFIX)) + + if (XATTR_SECURITY_PREFIX_LEN + strlen(sec->name) > XATTR_NAME_MAX) return -EINVAL; - error = reiserfs_xattr_set_handle(th, inode, sec->name, sec->value, + strlcat(xattr_name, sec->name, sizeof(xattr_name)); + + error = reiserfs_xattr_set_handle(th, inode, xattr_name, sec->value, sec->length, XATTR_CREATE); if (error == -ENODATA || error == -EOPNOTSUPP) error = 0; From e28df70df0070ab3db25e0e71c47cb465676a7e2 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 Apr 2023 17:23:59 -0700 Subject: [PATCH 2714/4345] KVM: nVMX: Emulate NOPs in L2, and PAUSE if it's not intercepted commit 4984563823f0034d3533854c1b50e729f5191089 upstream. Extend VMX's nested intercept logic for emulated instructions to handle "pause" interception, in quotes because KVM's emulator doesn't filter out NOPs when checking for nested intercepts. Failure to allow emulation of NOPs results in KVM injecting a #UD into L2 on any NOP that collides with the emulator's definition of PAUSE, i.e. on all single-byte NOPs. For PAUSE itself, honor L1's PAUSE-exiting control, but ignore PLE to avoid unnecessarily injecting a #UD into L2. Per the SDM, the first execution of PAUSE after VM-Entry is treated as the beginning of a new loop, i.e. will never trigger a PLE VM-Exit, and so L1 can't expect any given execution of PAUSE to deterministically exit. ... the processor considers this execution to be the first execution of PAUSE in a loop. (It also does so for the first execution of PAUSE at CPL 0 after VM entry.) All that said, the PLE side of things is currently a moot point, as KVM doesn't expose PLE to L1. Note, vmx_check_intercept() is still wildly broken when L1 wants to intercept an instruction, as KVM injects a #UD instead of synthesizing a nested VM-Exit. That issue extends far beyond NOP/PAUSE and needs far more effort to fix, i.e. is a problem for the future. Fixes: 07721feee46b ("KVM: nVMX: Don't emulate instructions in guest mode") Cc: Mathias Krause Cc: stable@vger.kernel.org Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20230405002359.418138-1-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx/vmx.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 2c5d8b9f9873..d65cc9363567 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7536,6 +7536,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ break; + case x86_intercept_pause: + /* + * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides + * with vanilla NOPs in the emulator. Apply the interception + * check only to actual PAUSE instructions. Don't check + * PAUSE-loop-exiting, software can't expect a given PAUSE to + * exit, i.e. KVM is within its rights to allow L2 to execute + * the PAUSE. + */ + if ((info->rep_prefix != REPE_PREFIX) || + !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING)) + return X86EMUL_CONTINUE; + + break; + /* TODO: check more intercepts... */ default: break; From 1b0df44753bf9e45eaf5cee34f87597193f862e8 Mon Sep 17 00:00:00 2001 From: Zhang Zhengming Date: Wed, 19 Apr 2023 12:02:03 +0800 Subject: [PATCH 2715/4345] relayfs: fix out-of-bounds access in relay_file_read commit 43ec16f1450f4936025a9bdf1a273affdb9732c1 upstream. There is a crash in relay_file_read, as the var from point to the end of last subbuf. The oops looks something like: pc : __arch_copy_to_user+0x180/0x310 lr : relay_file_read+0x20c/0x2c8 Call trace: __arch_copy_to_user+0x180/0x310 full_proxy_read+0x68/0x98 vfs_read+0xb0/0x1d0 ksys_read+0x6c/0xf0 __arm64_sys_read+0x20/0x28 el0_svc_common.constprop.3+0x84/0x108 do_el0_svc+0x74/0x90 el0_svc+0x1c/0x28 el0_sync_handler+0x88/0xb0 el0_sync+0x148/0x180 We get the condition by analyzing the vmcore: 1). The last produced byte and last consumed byte both at the end of the last subbuf 2). A softirq calls function(e.g __blk_add_trace) to write relay buffer occurs when an program is calling relay_file_read_avail(). relay_file_read relay_file_read_avail relay_file_read_consume(buf, 0, 0); //interrupted by softirq who will write subbuf .... return 1; //read_start point to the end of the last subbuf read_start = relay_file_read_start_pos //avail is equal to subsize avail = relay_file_read_subbuf_avail //from points to an invalid memory address from = buf->start + read_start //system is crashed copy_to_user(buffer, from, avail) Link: https://lkml.kernel.org/r/20230419040203.37676-1-zhang.zhengming@h3c.com Fixes: 8d62fdebdaf9 ("relay file read: start-pos fix") Signed-off-by: Zhang Zhengming Reviewed-by: Zhao Lei Reviewed-by: Zhou Kete Reviewed-by: Pengcheng Yang Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- kernel/relay.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/relay.c b/kernel/relay.c index 067769b80d4a..f6826dec2103 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1077,7 +1077,8 @@ static size_t relay_file_read_start_pos(struct rchan_buf *buf) size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t consumed = buf->subbufs_consumed % n_subbufs; - size_t read_pos = consumed * subbuf_size + buf->bytes_consumed; + size_t read_pos = (consumed * subbuf_size + buf->bytes_consumed) + % (n_subbufs * subbuf_size); read_subbuf = read_pos / subbuf_size; padding = buf->padding[read_subbuf]; From 2b00b2a0e6425095602a0ba05e36a5b9afe86817 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Mon, 10 Apr 2023 21:08:26 +0800 Subject: [PATCH 2716/4345] writeback, cgroup: fix null-ptr-deref write in bdi_split_work_to_wbs [ Upstream commit 1ba1199ec5747f475538c0d25a32804e5ba1dfde ] KASAN report null-ptr-deref: ================================================================== BUG: KASAN: null-ptr-deref in bdi_split_work_to_wbs+0x5c5/0x7b0 Write of size 8 at addr 0000000000000000 by task sync/943 CPU: 5 PID: 943 Comm: sync Tainted: 6.3.0-rc5-next-20230406-dirty #461 Call Trace: dump_stack_lvl+0x7f/0xc0 print_report+0x2ba/0x340 kasan_report+0xc4/0x120 kasan_check_range+0x1b7/0x2e0 __kasan_check_write+0x24/0x40 bdi_split_work_to_wbs+0x5c5/0x7b0 sync_inodes_sb+0x195/0x630 sync_inodes_one_sb+0x3a/0x50 iterate_supers+0x106/0x1b0 ksys_sync+0x98/0x160 [...] ================================================================== The race that causes the above issue is as follows: cpu1 cpu2 -------------------------|------------------------- inode_switch_wbs INIT_WORK(&isw->work, inode_switch_wbs_work_fn) queue_rcu_work(isw_wq, &isw->work) // queue_work async inode_switch_wbs_work_fn wb_put_many(old_wb, nr_switched) percpu_ref_put_many ref->data->release(ref) cgwb_release queue_work(cgwb_release_wq, &wb->release_work) // queue_work async &wb->release_work cgwb_release_workfn ksys_sync iterate_supers sync_inodes_one_sb sync_inodes_sb bdi_split_work_to_wbs kmalloc(sizeof(*work), GFP_ATOMIC) // alloc memory failed percpu_ref_exit ref->data = NULL kfree(data) wb_get(wb) percpu_ref_get(&wb->refcnt) percpu_ref_get_many(ref, 1) atomic_long_add(nr, &ref->data->count) atomic64_add(i, v) // trigger null-ptr-deref bdi_split_work_to_wbs() traverses &bdi->wb_list to split work into all wbs. If the allocation of new work fails, the on-stack fallback will be used and the reference count of the current wb is increased afterwards. If cgroup writeback membership switches occur before getting the reference count and the current wb is released as old_wd, then calling wb_get() or wb_put() will trigger the null pointer dereference above. This issue was introduced in v4.3-rc7 (see fix tag1). Both sync_inodes_sb() and __writeback_inodes_sb_nr() calls to bdi_split_work_to_wbs() can trigger this issue. For scenarios called via sync_inodes_sb(), originally commit 7fc5854f8c6e ("writeback: synchronize sync(2) against cgroup writeback membership switches") reduced the possibility of the issue by adding wb_switch_rwsem, but in v5.14-rc1 (see fix tag2) removed the "inode_io_list_del_locked(inode, old_wb)" from inode_switch_wbs_work_fn() so that wb->state contains WB_has_dirty_io, thus old_wb is not skipped when traversing wbs in bdi_split_work_to_wbs(), and the issue becomes easily reproducible again. To solve this problem, percpu_ref_exit() is called under RCU protection to avoid race between cgwb_release_workfn() and bdi_split_work_to_wbs(). Moreover, replace wb_get() with wb_tryget() in bdi_split_work_to_wbs(), and skip the current wb if wb_tryget() fails because the wb has already been shutdown. Link: https://lkml.kernel.org/r/20230410130826.1492525-1-libaokun1@huawei.com Fixes: b817525a4a80 ("writeback: bdi_writeback iteration must not skip dying ones") Signed-off-by: Baokun Li Reviewed-by: Jan Kara Acked-by: Tejun Heo Cc: Alexander Viro Cc: Andreas Dilger Cc: Christian Brauner Cc: Dennis Zhou Cc: Hou Tao Cc: yangerkun Cc: Zhang Yi Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- fs/fs-writeback.c | 17 ++++++++++------- mm/backing-dev.c | 11 ++++++++++- 2 files changed, 20 insertions(+), 8 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 46c15dd2405c..6f18459f5e38 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -884,6 +884,16 @@ restart: continue; } + /* + * If wb_tryget fails, the wb has been shutdown, skip it. + * + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + if (!wb_tryget(wb)) + continue; + /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; @@ -892,13 +902,6 @@ restart: work->done = &fallback_work_done; wb_queue_work(wb, work); - - /* - * Pin @wb so that it stays on @bdi->wb_list. This allows - * continuing iteration from @wb after dropping and - * regrabbing rcu read lock. - */ - wb_get(wb); last_wb = wb; rcu_read_unlock(); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index ca770a783a9f..b28f629c3527 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -378,6 +378,15 @@ static void wb_exit(struct bdi_writeback *wb) static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; +static void cgwb_free_rcu(struct rcu_head *rcu_head) +{ + struct bdi_writeback *wb = container_of(rcu_head, + struct bdi_writeback, rcu); + + percpu_ref_exit(&wb->refcnt); + kfree(wb); +} + static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, @@ -397,7 +406,7 @@ static void cgwb_release_workfn(struct work_struct *work) fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); wb_exit(wb); - kfree_rcu(wb, rcu); + call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) From db8b34ffb29bde098cdac8b1da0d6fb47ac7add7 Mon Sep 17 00:00:00 2001 From: Reid Tonking Date: Wed, 26 Apr 2023 14:49:56 -0500 Subject: [PATCH 2717/4345] i2c: omap: Fix standard mode false ACK readings commit c770657bd2611b077ec1e7b1fe6aa92f249399bd upstream. Using standard mode, rare false ACK responses were appearing with i2cdetect tool. This was happening due to NACK interrupt triggering ISR thread before register access interrupt was ready. Removing the NACK interrupt's ability to trigger ISR thread lets register access ready interrupt do this instead. Cc: # v3.7+ Fixes: 3b2f8f82dad7 ("i2c: omap: switch to threaded IRQ support") Signed-off-by: Reid Tonking Acked-by: Vignesh Raghavendra Reviewed-by: Tony Lindgren Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-omap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index d4f6c6d60683..8955f62b497e 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1058,7 +1058,7 @@ omap_i2c_isr(int irq, void *dev_id) u16 stat; stat = omap_i2c_read_reg(omap, OMAP_I2C_STAT_REG); - mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG); + mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG) & ~OMAP_I2C_STAT_NACK; if (stat & mask) ret = IRQ_WAKE_THREAD; From 87d98984b050b98376bccd9bcc7ed0cbfa5a6cfd Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Wed, 5 Apr 2023 13:03:17 +0000 Subject: [PATCH 2718/4345] iommu/amd: Fix "Guest Virtual APIC Table Root Pointer" configuration in IRTE commit ccc62b827775915a9b82db42a29813d04f92df7a upstream. commit b9c6ff94e43a ("iommu/amd: Re-factor guest virtual APIC (de-)activation code") while refactoring guest virtual APIC activation/de-activation code, stored information for activate/de-activate in "struct amd_ir_data". It used 32-bit integer data type for storing the "Guest Virtual APIC Table Root Pointer" (ga_root_ptr), though the "ga_root_ptr" is actually a 40-bit field in IRTE (Interrupt Remapping Table Entry). This causes interrupts from PCIe devices to not reach the guest in the case of PCIe passthrough with SME (Secure Memory Encryption) enabled as _SME_ bit in the "ga_root_ptr" is lost before writing it to the IRTE. Fix it by using 64-bit data type for storing the "ga_root_ptr". While at that also change the data type of "ga_tag" to u32 in order to match the IOMMU spec. Fixes: b9c6ff94e43a ("iommu/amd: Re-factor guest virtual APIC (de-)activation code") Cc: stable@vger.kernel.org # v5.4+ Reported-by: Alejandro Jimenez Reviewed-by: Suravee Suthikulpanit Signed-off-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20230405130317.9351-1-kvijayab@amd.com Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/amd/amd_iommu_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 690c5976575c..4a8791e037b8 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -897,8 +897,8 @@ struct amd_ir_data { */ struct irq_cfg *cfg; int ga_vector; - int ga_root_ptr; - int ga_tag; + u64 ga_root_ptr; + u32 ga_tag; }; struct amd_irte_ops { From a4904c56fc6fa56df1ce7ecab21aaef5ba2b7d36 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 1 Mar 2023 20:29:18 +0800 Subject: [PATCH 2719/4345] Revert "ubifs: dirty_cow_znode: Fix memleak in error handling path" commit 7d01cb27f6aebc54efbe28d8961a973b8f795b13 upstream. This reverts commit 122deabfe1428 (ubifs: dirty_cow_znode: Fix memleak in error handling path). After commit 122deabfe1428 applied, if insert_old_idx() failed, old index neither exists in TNC nor in old-index tree. Which means that old index node could be overwritten in layout_leb_in_gaps(), then ubifs image will be corrupted in power-cut. Fixes: 122deabfe1428 (ubifs: dirty_cow_znode: Fix memleak ... path) Cc: stable@vger.kernel.org Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Greg Kroah-Hartman --- fs/ubifs/tnc.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 07470449b960..7c36b6677430 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -267,18 +267,11 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c, if (zbr->len) { err = insert_old_idx(c, zbr->lnum, zbr->offs); if (unlikely(err)) - /* - * Obsolete znodes will be freed by tnc_destroy_cnext() - * or free_obsolete_znodes(), copied up znodes should - * be added back to tnc and freed by - * ubifs_destroy_tnc_subtree(). - */ - goto out; + return ERR_PTR(err); err = add_idx_dirt(c, zbr->lnum, zbr->len); } else err = 0; -out: zbr->znode = zn; zbr->lnum = 0; zbr->offs = 0; From 66e9f2fb3e753f820bec2a98e8c6387029988320 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 1 Mar 2023 20:29:19 +0800 Subject: [PATCH 2720/4345] ubifs: Fix memleak when insert_old_idx() failed commit b5fda08ef213352ac2df7447611eb4d383cce929 upstream. Following process will cause a memleak for copied up znode: dirty_cow_znode zn = copy_znode(c, znode); err = insert_old_idx(c, zbr->lnum, zbr->offs); if (unlikely(err)) return ERR_PTR(err); // No one refers to zn. Fetch a reproducer in [Link]. Function copy_znode() is split into 2 parts: resource allocation and znode replacement, insert_old_idx() is split in similar way, so resource cleanup could be done in error handling path without corrupting metadata(mem & disk). It's okay that old index inserting is put behind of add_idx_dirt(), old index is used in layout_leb_in_gaps(), so the two processes do not depend on each other. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216705 Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Cc: stable@vger.kernel.org Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Greg Kroah-Hartman --- fs/ubifs/tnc.c | 137 +++++++++++++++++++++++++++++++------------------ 1 file changed, 87 insertions(+), 50 deletions(-) diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 7c36b6677430..2313c7174e3c 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -44,6 +44,33 @@ enum { NOT_ON_MEDIA = 3, }; +static void do_insert_old_idx(struct ubifs_info *c, + struct ubifs_old_idx *old_idx) +{ + struct ubifs_old_idx *o; + struct rb_node **p, *parent = NULL; + + p = &c->old_idx.rb_node; + while (*p) { + parent = *p; + o = rb_entry(parent, struct ubifs_old_idx, rb); + if (old_idx->lnum < o->lnum) + p = &(*p)->rb_left; + else if (old_idx->lnum > o->lnum) + p = &(*p)->rb_right; + else if (old_idx->offs < o->offs) + p = &(*p)->rb_left; + else if (old_idx->offs > o->offs) + p = &(*p)->rb_right; + else { + ubifs_err(c, "old idx added twice!"); + kfree(old_idx); + } + } + rb_link_node(&old_idx->rb, parent, p); + rb_insert_color(&old_idx->rb, &c->old_idx); +} + /** * insert_old_idx - record an index node obsoleted since the last commit start. * @c: UBIFS file-system description object @@ -69,35 +96,15 @@ enum { */ static int insert_old_idx(struct ubifs_info *c, int lnum, int offs) { - struct ubifs_old_idx *old_idx, *o; - struct rb_node **p, *parent = NULL; + struct ubifs_old_idx *old_idx; old_idx = kmalloc(sizeof(struct ubifs_old_idx), GFP_NOFS); if (unlikely(!old_idx)) return -ENOMEM; old_idx->lnum = lnum; old_idx->offs = offs; + do_insert_old_idx(c, old_idx); - p = &c->old_idx.rb_node; - while (*p) { - parent = *p; - o = rb_entry(parent, struct ubifs_old_idx, rb); - if (lnum < o->lnum) - p = &(*p)->rb_left; - else if (lnum > o->lnum) - p = &(*p)->rb_right; - else if (offs < o->offs) - p = &(*p)->rb_left; - else if (offs > o->offs) - p = &(*p)->rb_right; - else { - ubifs_err(c, "old idx added twice!"); - kfree(old_idx); - return 0; - } - } - rb_link_node(&old_idx->rb, parent, p); - rb_insert_color(&old_idx->rb, &c->old_idx); return 0; } @@ -199,23 +206,6 @@ static struct ubifs_znode *copy_znode(struct ubifs_info *c, __set_bit(DIRTY_ZNODE, &zn->flags); __clear_bit(COW_ZNODE, &zn->flags); - ubifs_assert(c, !ubifs_zn_obsolete(znode)); - __set_bit(OBSOLETE_ZNODE, &znode->flags); - - if (znode->level != 0) { - int i; - const int n = zn->child_cnt; - - /* The children now have new parent */ - for (i = 0; i < n; i++) { - struct ubifs_zbranch *zbr = &zn->zbranch[i]; - - if (zbr->znode) - zbr->znode->parent = zn; - } - } - - atomic_long_inc(&c->dirty_zn_cnt); return zn; } @@ -233,6 +223,42 @@ static int add_idx_dirt(struct ubifs_info *c, int lnum, int dirt) return ubifs_add_dirt(c, lnum, dirt); } +/** + * replace_znode - replace old znode with new znode. + * @c: UBIFS file-system description object + * @new_zn: new znode + * @old_zn: old znode + * @zbr: the branch of parent znode + * + * Replace old znode with new znode in TNC. + */ +static void replace_znode(struct ubifs_info *c, struct ubifs_znode *new_zn, + struct ubifs_znode *old_zn, struct ubifs_zbranch *zbr) +{ + ubifs_assert(c, !ubifs_zn_obsolete(old_zn)); + __set_bit(OBSOLETE_ZNODE, &old_zn->flags); + + if (old_zn->level != 0) { + int i; + const int n = new_zn->child_cnt; + + /* The children now have new parent */ + for (i = 0; i < n; i++) { + struct ubifs_zbranch *child = &new_zn->zbranch[i]; + + if (child->znode) + child->znode->parent = new_zn; + } + } + + zbr->znode = new_zn; + zbr->lnum = 0; + zbr->offs = 0; + zbr->len = 0; + + atomic_long_inc(&c->dirty_zn_cnt); +} + /** * dirty_cow_znode - ensure a znode is not being committed. * @c: UBIFS file-system description object @@ -265,21 +291,32 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c, return zn; if (zbr->len) { - err = insert_old_idx(c, zbr->lnum, zbr->offs); - if (unlikely(err)) - return ERR_PTR(err); + struct ubifs_old_idx *old_idx; + + old_idx = kmalloc(sizeof(struct ubifs_old_idx), GFP_NOFS); + if (unlikely(!old_idx)) { + err = -ENOMEM; + goto out; + } + old_idx->lnum = zbr->lnum; + old_idx->offs = zbr->offs; + err = add_idx_dirt(c, zbr->lnum, zbr->len); - } else - err = 0; + if (err) { + kfree(old_idx); + goto out; + } - zbr->znode = zn; - zbr->lnum = 0; - zbr->offs = 0; - zbr->len = 0; + do_insert_old_idx(c, old_idx); + } + + replace_znode(c, zn, znode, zbr); - if (unlikely(err)) - return ERR_PTR(err); return zn; + +out: + kfree(zn); + return ERR_PTR(err); } /** From 5b4b6cb7246efe00ecc6187903af918a360e2300 Mon Sep 17 00:00:00 2001 From: Wang YanQing Date: Tue, 28 Mar 2023 23:35:34 +0800 Subject: [PATCH 2721/4345] ubi: Fix return value overwrite issue in try_write_vid_and_data() commit 31a149d5c13c4cbcf97de3435817263a2d8c9d6e upstream. The commit 2d78aee426d8 ("UBI: simplify LEB write and atomic LEB change code") adds helper function, try_write_vid_and_data(), to simplify the code, but this helper function has bug, it will return 0 (success) when ubi_io_write_vid_hdr() or the ubi_io_write_data() return error number (-EIO, etc), because the return value of ubi_wl_put_peb() will overwrite the original return value. This issue will cause unexpected data loss issue, because the caller of this function and UBIFS willn't know the data is lost. Fixes: 2d78aee426d8 ("UBI: simplify LEB write and atomic LEB change code") Cc: stable@vger.kernel.org Signed-off-by: Wang YanQing Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/ubi/eba.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index 0edecfdbd01f..b4cdf2351cac 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -947,7 +947,7 @@ static int try_write_vid_and_data(struct ubi_volume *vol, int lnum, int offset, int len) { struct ubi_device *ubi = vol->ubi; - int pnum, opnum, err, vol_id = vol->vol_id; + int pnum, opnum, err, err2, vol_id = vol->vol_id; pnum = ubi_wl_get_peb(ubi); if (pnum < 0) { @@ -982,10 +982,19 @@ static int try_write_vid_and_data(struct ubi_volume *vol, int lnum, out_put: up_read(&ubi->fm_eba_sem); - if (err && pnum >= 0) - err = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1); - else if (!err && opnum >= 0) - err = ubi_wl_put_peb(ubi, vol_id, lnum, opnum, 0); + if (err && pnum >= 0) { + err2 = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1); + if (err2) { + ubi_warn(ubi, "failed to return physical eraseblock %d, error %d", + pnum, err2); + } + } else if (!err && opnum >= 0) { + err2 = ubi_wl_put_peb(ubi, vol_id, lnum, opnum, 0); + if (err2) { + ubi_warn(ubi, "failed to return physical eraseblock %d, error %d", + opnum, err2); + } + } return err; } From b8f444a4fadfb5070ed7e298e0a5ceb4a18014f3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=C3=A5rten=20Lindahl?= Date: Thu, 30 Mar 2023 11:32:14 +0200 Subject: [PATCH 2722/4345] ubifs: Free memory for tmpfile name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1fb815b38bb31d6af9bd0540b8652a0d6fe6cfd3 upstream. When opening a ubifs tmpfile on an encrypted directory, function fscrypt_setup_filename allocates memory for the name that is to be stored in the directory entry, but after the name has been copied to the directory entry inode, the memory is not freed. When running kmemleak on it we see that it is registered as a leak. The report below is triggered by a simple program 'tmpfile' just opening a tmpfile: unreferenced object 0xffff88810178f380 (size 32): comm "tmpfile", pid 509, jiffies 4294934744 (age 1524.742s) backtrace: __kmem_cache_alloc_node __kmalloc fscrypt_setup_filename ubifs_tmpfile vfs_tmpfile path_openat Free this memory after it has been copied to the inode. Signed-off-by: Mårten Lindahl Reviewed-by: Zhihao Cheng Cc: stable@vger.kernel.org Signed-off-by: Richard Weinberger Signed-off-by: Greg Kroah-Hartman --- fs/ubifs/dir.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 6039943877e1..bc562b1072d3 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -425,6 +425,7 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry, mutex_unlock(&dir_ui->ui_mutex); ubifs_release_budget(c, &req); + fscrypt_free_filename(&nm); return 0; From be649ea153b04c2ad35c6f32b18f644ab9b192b9 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 5 Apr 2022 16:41:18 -0700 Subject: [PATCH 2723/4345] sound/oss/dmasound: fix build when drivers are mixed =y/=m commit 9dd7c46346ca4390f84a7ea9933005eb1b175c15 upstream. When CONFIG_DMASOUND_ATARI=m and CONFIG_DMASOUND_Q40=y (or vice versa), dmasound_core.o can be built without dmasound_deinit() being defined, causing a build error: ERROR: modpost: "dmasound_deinit" [sound/oss/dmasound/dmasound_atari.ko] undefined! Modify dmasound_core.c and dmasound.h so that dmasound_deinit() is always available. The mixed modes (=y/=m) also mean that several variables and structs have to be declared in all cases. Suggested-by: Arnd Bergmann Suggested-by: Geert Uytterhoeven Signed-off-by: Randy Dunlap Reported-by: kernel test robot Link: lore.kernel.org/r/202204032138.EFT9qGEd-lkp@intel.com Cc: Geert Uytterhoeven Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: alsa-devel@alsa-project.org Link: https://lore.kernel.org/r/20220405234118.24830-1-rdunlap@infradead.org Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/oss/dmasound/dmasound.h | 6 ------ sound/oss/dmasound/dmasound_core.c | 24 +----------------------- 2 files changed, 1 insertion(+), 29 deletions(-) diff --git a/sound/oss/dmasound/dmasound.h b/sound/oss/dmasound/dmasound.h index c1c52b479da2..ad8ce6a1c25c 100644 --- a/sound/oss/dmasound/dmasound.h +++ b/sound/oss/dmasound/dmasound.h @@ -88,11 +88,7 @@ static inline int ioctl_return(int __user *addr, int value) */ extern int dmasound_init(void); -#ifdef MODULE extern void dmasound_deinit(void); -#else -#define dmasound_deinit() do { } while (0) -#endif /* description of the set-up applies to either hard or soft settings */ @@ -114,9 +110,7 @@ typedef struct { void *(*dma_alloc)(unsigned int, gfp_t); void (*dma_free)(void *, unsigned int); int (*irqinit)(void); -#ifdef MODULE void (*irqcleanup)(void); -#endif void (*init)(void); void (*silence)(void); int (*setFormat)(int); diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 38f25e97538f..7a8698ff7f54 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -206,12 +206,10 @@ module_param(writeBufSize, int, 0); MODULE_LICENSE("GPL"); -#ifdef MODULE static int sq_unit = -1; static int mixer_unit = -1; static int state_unit = -1; static int irq_installed; -#endif /* MODULE */ /* control over who can modify resources shared between play/record */ static fmode_t shared_resource_owner; @@ -391,9 +389,6 @@ static const struct file_operations mixer_fops = static void mixer_init(void) { -#ifndef MODULE - int mixer_unit; -#endif mixer_unit = register_sound_mixer(&mixer_fops, -1); if (mixer_unit < 0) return; @@ -1176,9 +1171,6 @@ static const struct file_operations sq_fops = static int sq_init(void) { const struct file_operations *fops = &sq_fops; -#ifndef MODULE - int sq_unit; -#endif sq_unit = register_sound_dsp(fops, -1); if (sq_unit < 0) { @@ -1380,9 +1372,6 @@ static const struct file_operations state_fops = { static int state_init(void) { -#ifndef MODULE - int state_unit; -#endif state_unit = register_sound_special(&state_fops, SND_DEV_STATUS); if (state_unit < 0) return state_unit ; @@ -1400,10 +1389,9 @@ static int state_init(void) int dmasound_init(void) { int res ; -#ifdef MODULE + if (irq_installed) return -EBUSY; -#endif /* Set up sound queue, /dev/audio and /dev/dsp. */ @@ -1422,9 +1410,7 @@ int dmasound_init(void) printk(KERN_ERR "DMA sound driver: Interrupt initialization failed\n"); return -ENODEV; } -#ifdef MODULE irq_installed = 1; -#endif printk(KERN_INFO "%s DMA sound driver rev %03d installed\n", dmasound.mach.name, (DMASOUND_CORE_REVISION<<4) + @@ -1438,8 +1424,6 @@ int dmasound_init(void) return 0; } -#ifdef MODULE - void dmasound_deinit(void) { if (irq_installed) { @@ -1458,8 +1442,6 @@ void dmasound_deinit(void) unregister_sound_dsp(sq_unit); } -#else /* !MODULE */ - static int dmasound_setup(char *str) { int ints[6], size; @@ -1503,8 +1485,6 @@ static int dmasound_setup(char *str) __setup("dmasound=", dmasound_setup); -#endif /* !MODULE */ - /* * Conversion tables */ @@ -1591,9 +1571,7 @@ char dmasound_alaw2dma8[] = { EXPORT_SYMBOL(dmasound); EXPORT_SYMBOL(dmasound_init); -#ifdef MODULE EXPORT_SYMBOL(dmasound_deinit); -#endif EXPORT_SYMBOL(dmasound_write_sq); EXPORT_SYMBOL(dmasound_catchRadius); #ifdef HAS_8BIT_TABLES From e4b526442247fabc92d2ce79a5725ee75c4f7caa Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 3 May 2023 16:39:56 +0200 Subject: [PATCH 2724/4345] parisc: Fix argument pointer in real64_call_asm() commit 6e3220ba3323a2c24be834aebf5d6e9f89d0993f upstream. Fix the argument pointer (ap) to point to real-mode memory instead of virtual memory. It's interesting that this issue hasn't shown up earlier, as this could have happened with any 64-bit PDC ROM code. I just noticed it because I suddenly faced a HPMC while trying to execute the 64-bit STI ROM code of an Visualize-FXe graphics card for the STI text console. Signed-off-by: Helge Deller Cc: Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/real2.S | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/parisc/kernel/real2.S b/arch/parisc/kernel/real2.S index 2b16d8d6598f..c37010a13586 100644 --- a/arch/parisc/kernel/real2.S +++ b/arch/parisc/kernel/real2.S @@ -248,9 +248,6 @@ ENTRY_CFI(real64_call_asm) /* save fn */ copy %arg2, %r31 - /* set up the new ap */ - ldo 64(%arg1), %r29 - /* load up the arg registers from the saved arg area */ /* 32-bit calling convention passes first 4 args in registers */ ldd 0*REG_SZ(%arg1), %arg0 /* note overwriting arg0 */ @@ -262,7 +259,9 @@ ENTRY_CFI(real64_call_asm) ldd 7*REG_SZ(%arg1), %r19 ldd 1*REG_SZ(%arg1), %arg1 /* do this one last! */ + /* set up real-mode stack and real-mode ap */ tophys_r1 %sp + ldo -16(%sp), %r29 /* Reference param save area */ b,l rfi_virt2real,%r2 nop From 7c3e662048053802f6b0db3a78e97f4e1f7edc4f Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 27 Apr 2023 10:15:26 +0900 Subject: [PATCH 2725/4345] nilfs2: do not write dirty data after degenerating to read-only commit 28a65b49eb53e172d23567005465019658bfdb4d upstream. According to syzbot's report, mark_buffer_dirty() called from nilfs_segctor_do_construct() outputs a warning with some patterns after nilfs2 detects metadata corruption and degrades to read-only mode. After such read-only degeneration, page cache data may be cleared through nilfs_clear_dirty_page() which may also clear the uptodate flag for their buffer heads. However, even after the degeneration, log writes are still performed by unmount processing etc., which causes mark_buffer_dirty() to be called for buffer heads without the "uptodate" flag and causes the warning. Since any writes should not be done to a read-only file system in the first place, this fixes the warning in mark_buffer_dirty() by letting nilfs_segctor_do_construct() abort early if in read-only mode. This also changes the retry check of nilfs_segctor_write_out() to avoid unnecessary log write retries if it detects -EROFS that nilfs_segctor_do_construct() returned. Link: https://lkml.kernel.org/r/20230427011526.13457-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Reported-by: syzbot+2af3bc9585be7f23f290@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=2af3bc9585be7f23f290 Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/segment.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index fff2cdc69e5e..cdaca232ac4d 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2044,6 +2044,9 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) struct the_nilfs *nilfs = sci->sc_super->s_fs_info; int err; + if (sb_rdonly(sci->sc_super)) + return -EROFS; + nilfs_sc_cstage_set(sci, NILFS_ST_INIT); sci->sc_cno = nilfs->ns_cno; @@ -2729,7 +2732,7 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) flush_work(&sci->sc_iput_work); - } while (ret && retrycount-- > 0); + } while (ret && ret != -EROFS && retrycount-- > 0); } /** From 8a89d36a07afe1ed4564df51fefa2bb556c85412 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 1 May 2023 04:30:46 +0900 Subject: [PATCH 2726/4345] nilfs2: fix infinite loop in nilfs_mdt_get_block() commit a6a491c048882e7e424d407d32cba0b52d9ef2bf upstream. If the disk image that nilfs2 mounts is corrupted and a virtual block address obtained by block lookup for a metadata file is invalid, nilfs_bmap_lookup_at_level() may return the same internal return code as -ENOENT, meaning the block does not exist in the metadata file. This duplication of return codes confuses nilfs_mdt_get_block(), causing it to read and create a metadata block indefinitely. In particular, if this happens to the inode metadata file, ifile, semaphore i_rwsem can be left held, causing task hangs in lock_mount. Fix this issue by making nilfs_bmap_lookup_at_level() treat virtual block address translation failures with -ENOENT as metadata corruption instead of returning the error code. Link: https://lkml.kernel.org/r/20230430193046.6769-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Reported-by: syzbot+221d75710bde87fa0e97@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=221d75710bde87fa0e97 Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/bmap.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index 5900879d5693..8ebb69c4ad18 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -67,20 +67,28 @@ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level, down_read(&bmap->b_sem); ret = bmap->b_ops->bop_lookup(bmap, key, level, ptrp); - if (ret < 0) { - ret = nilfs_bmap_convert_error(bmap, __func__, ret); + if (ret < 0) goto out; - } + if (NILFS_BMAP_USE_VBN(bmap)) { ret = nilfs_dat_translate(nilfs_bmap_get_dat(bmap), *ptrp, &blocknr); if (!ret) *ptrp = blocknr; + else if (ret == -ENOENT) { + /* + * If there was no valid entry in DAT for the block + * address obtained by b_ops->bop_lookup, then pass + * internal code -EINVAL to nilfs_bmap_convert_error + * to treat it as metadata corruption. + */ + ret = -EINVAL; + } } out: up_read(&bmap->b_sem); - return ret; + return nilfs_bmap_convert_error(bmap, __func__, ret); } int nilfs_bmap_lookup_contig(struct nilfs_bmap *bmap, __u64 key, __u64 *ptrp, From bdbf104b1c91fbf38f82c522ebf75429f094292a Mon Sep 17 00:00:00 2001 From: Li Nan Date: Wed, 22 Feb 2023 12:10:00 +0800 Subject: [PATCH 2727/4345] md/raid10: fix null-ptr-deref in raid10_sync_request commit a405c6f0229526160aa3f177f65e20c86fce84c5 upstream. init_resync() inits mempool and sets conf->have_replacemnt at the beginning of sync, close_sync() frees the mempool when sync is completed. After [1] recovery might be skipped and init_resync() is called but close_sync() is not. null-ptr-deref occurs with r10bio->dev[i].repl_bio. The following is one way to reproduce the issue. 1) create a array, wait for resync to complete, mddev->recovery_cp is set to MaxSector. 2) recovery is woken and it is skipped. conf->have_replacement is set to 0 in init_resync(). close_sync() not called. 3) some io errors and rdev A is set to WantReplacement. 4) a new device is added and set to A's replacement. 5) recovery is woken, A have replacement, but conf->have_replacemnt is 0. r10bio->dev[i].repl_bio will not be alloced and null-ptr-deref occurs. Fix it by not calling init_resync() if recovery skipped. [1] commit 7e83ccbecd60 ("md/raid10: Allow skipping recovery when clean arrays are assembled") Fixes: 7e83ccbecd60 ("md/raid10: Allow skipping recovery when clean arrays are assembled") Cc: stable@vger.kernel.org Signed-off-by: Li Nan Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230222041000.3341651-3-linan666@huaweicloud.com Signed-off-by: Greg Kroah-Hartman --- drivers/md/raid10.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 0e741a8d278d..6f8a7537dcd7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2900,10 +2900,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, sector_t chunk_mask = conf->geo.chunk_mask; int page_idx = 0; - if (!mempool_initialized(&conf->r10buf_pool)) - if (init_resync(conf)) - return 0; - /* * Allow skipping a full rebuild for incremental assembly * of a clean array, like RAID1 does. @@ -2919,6 +2915,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, return mddev->dev_sectors - sector_nr; } + if (!mempool_initialized(&conf->r10buf_pool)) + if (init_resync(conf)) + return 0; + skipped: max_sector = mddev->dev_sectors; if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) || From 63314371ebbf7d036c5b61273cf20e492b4d6945 Mon Sep 17 00:00:00 2001 From: Tanmay Shah Date: Fri, 10 Mar 2023 17:24:05 -0800 Subject: [PATCH 2728/4345] mailbox: zynqmp: Fix IPI isr handling commit 74ad37a30ffee3643bc34f9ca7225b20a66abaaf upstream. Multiple IPI channels are mapped to same interrupt handler. Current isr implementation handles only one channel per isr. Fix this behavior by checking isr status bit of all child mailbox nodes. Fixes: 4981b82ba2ff ("mailbox: ZynqMP IPI mailbox controller") Signed-off-by: Tanmay Shah Acked-by: Michal Simek Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230311012407.1292118-3-tanmay.shah@amd.com Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/mailbox/zynqmp-ipi-mailbox.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c index 527204c6d5cd..05e36229622e 100644 --- a/drivers/mailbox/zynqmp-ipi-mailbox.c +++ b/drivers/mailbox/zynqmp-ipi-mailbox.c @@ -152,7 +152,7 @@ static irqreturn_t zynqmp_ipi_interrupt(int irq, void *data) struct zynqmp_ipi_message *msg; u64 arg0, arg3; struct arm_smccc_res res; - int ret, i; + int ret, i, status = IRQ_NONE; (void)irq; arg0 = SMC_IPI_MAILBOX_STATUS_ENQUIRY; @@ -170,11 +170,11 @@ static irqreturn_t zynqmp_ipi_interrupt(int irq, void *data) memcpy_fromio(msg->data, mchan->req_buf, msg->len); mbox_chan_received_data(chan, (void *)msg); - return IRQ_HANDLED; + status = IRQ_HANDLED; } } } - return IRQ_NONE; + return status; } /** From d1ab8b54b2cee95b306b901da490cd2f09d3d579 Mon Sep 17 00:00:00 2001 From: Quentin Schulz Date: Thu, 17 Nov 2022 13:04:31 +0100 Subject: [PATCH 2729/4345] clk: rockchip: rk3399: allow clk_cifout to force clk_cifout_src to reparent commit 933bf364e152cd60902cf9585c2ba310d593e69f upstream. clk_cifout is derived from clk_cifout_src through an integer divider limited to 32. clk_cifout_src is a child of either cpll, gpll or npll without any possibility of a divider of any sort. The default clock parent is cpll. Let's allow clk_cifout to ask its parent clk_cifout_src to reparent in order to find the real closest possible rate for clk_cifout and not one derived from cpll only. Cc: stable@vger.kernel.org # 4.10+ Fixes: fd8bc829336a ("clk: rockchip: fix the rk3399 cifout clock") Signed-off-by: Quentin Schulz Link: https://lore.kernel.org/r/20221117-rk3399-cifout-set-rate-parent-v1-0-432548d04081@theobroma-systems.com Signed-off-by: Heiko Stuebner Signed-off-by: Greg Kroah-Hartman --- drivers/clk/rockchip/clk-rk3399.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index 7df2f1e00347..a9cacbcc1c2a 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -1261,7 +1261,7 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = { RK3399_CLKSEL_CON(56), 6, 2, MFLAGS, RK3399_CLKGATE_CON(10), 7, GFLAGS), - COMPOSITE_NOGATE(SCLK_CIF_OUT, "clk_cifout", mux_clk_cif_p, 0, + COMPOSITE_NOGATE(SCLK_CIF_OUT, "clk_cifout", mux_clk_cif_p, CLK_SET_RATE_PARENT, RK3399_CLKSEL_CON(56), 5, 1, MFLAGS, 0, 5, DFLAGS), /* gic */ From 0fd9b0f61119a72f987a548447c49d3b4c9eced0 Mon Sep 17 00:00:00 2001 From: Tanmay Shah Date: Fri, 10 Mar 2023 17:24:06 -0800 Subject: [PATCH 2730/4345] mailbox: zynqmp: Fix typo in IPI documentation commit 79963fbfc233759bd8a43462f120d15a1bd4f4fa upstream. Xilinx IPI message buffers allows 32-byte data transfer. Fix documentation that says 12 bytes Fixes: 4981b82ba2ff ("mailbox: ZynqMP IPI mailbox controller") Signed-off-by: Tanmay Shah Acked-by: Michal Simek Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230311012407.1292118-4-tanmay.shah@amd.com Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/mailbox/zynqmp-ipi-message.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/mailbox/zynqmp-ipi-message.h b/include/linux/mailbox/zynqmp-ipi-message.h index 35ce84c8ca02..31d8046d945e 100644 --- a/include/linux/mailbox/zynqmp-ipi-message.h +++ b/include/linux/mailbox/zynqmp-ipi-message.h @@ -9,7 +9,7 @@ * @data: message payload * * This is the structure for data used in mbox_send_message - * the maximum length of data buffer is fixed to 12 bytes. + * the maximum length of data buffer is fixed to 32 bytes. * Client is supposed to be aware of this. */ struct zynqmp_ipi_message { From d0653cc6e0c7f975db13ffd41af3c9f80c3a374b Mon Sep 17 00:00:00 2001 From: Zqiang Date: Tue, 20 Dec 2022 22:16:25 +0800 Subject: [PATCH 2731/4345] rcu: Fix missing TICK_DEP_MASK_RCU_EXP dependency check [ Upstream commit db7b464df9d820186e98a65aa6a10f0d51fbf8ce ] This commit adds checks for the TICK_DEP_MASK_RCU_EXP bit, thus enabling RCU expedited grace periods to actually force-enable scheduling-clock interrupts on holdout CPUs. Fixes: df1e849ae455 ("rcu: Enable tick for nohz_full CPUs slow to provide expedited QS") Signed-off-by: Zqiang Cc: Steven Rostedt Cc: Masami Hiramatsu Cc: Frederic Weisbecker Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Anna-Maria Behnsen Acked-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Sasha Levin --- include/trace/events/timer.h | 3 ++- kernel/time/tick-sched.c | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 19abb6c3eb73..40e9b5a12732 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -368,7 +368,8 @@ TRACE_EVENT(itimer_expire, tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ - tick_dep_name_end(RCU) + tick_dep_name(RCU) \ + tick_dep_name_end(RCU_EXP) #undef tick_dep_name #undef tick_dep_mask_name diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index e4e0d032126b..378096fc8c56 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -213,6 +213,11 @@ static bool check_tick_dependency(atomic_t *dep) return true; } + if (val & TICK_DEP_MASK_RCU_EXP) { + trace_tick_stop(0, TICK_DEP_MASK_RCU_EXP); + return true; + } + return false; } From e0dd13b49da950833709b3fc943721ee1a7e7a26 Mon Sep 17 00:00:00 2001 From: Bitterblue Smith Date: Mon, 13 Mar 2023 15:42:59 +0200 Subject: [PATCH 2732/4345] wifi: rtl8xxxu: RTL8192EU always needs full init commit d46e04ccd40457a0119b76e11ab64a2ad403e138 upstream. Always run the entire init sequence (rtl8xxxu_init_device()) for RTL8192EU. It's what the vendor driver does too. This fixes a bug where the device is unable to connect after rebooting: wlp3s0f3u2: send auth to ... (try 1/3) wlp3s0f3u2: send auth to ... (try 2/3) wlp3s0f3u2: send auth to ... (try 3/3) wlp3s0f3u2: authentication with ... timed out Rebooting leaves the device powered on (partially? at least the firmware is still running), but not really in a working state. Cc: stable@vger.kernel.org Signed-off-by: Bitterblue Smith Acked-by: Jes Sorensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/4eb111a9-d4c4-37d0-b376-4e202de7153c@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c index 3b3cb3a6e2e8..6d13327d690e 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c @@ -1702,6 +1702,7 @@ struct rtl8xxxu_fileops rtl8192eu_fops = { .rx_desc_size = sizeof(struct rtl8xxxu_rxdesc24), .has_s0s1 = 0, .gen2_thermal_meter = 1, + .needs_full_init = 1, .adda_1t_init = 0x0fc01616, .adda_1t_path_on = 0x0fc01616, .adda_2t_path_on_a = 0x0fc01616, From 4075fbcde40f2e12130964abedfb418469238af1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Wed, 15 Feb 2023 15:05:57 +0200 Subject: [PATCH 2733/4345] selftests/resctrl: Return NULL if malloc_and_init_memory() did not alloc mem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 22a8be280383812235131dda18a8212a59fadd2d ] malloc_and_init_memory() in fill_buf isn't checking if memalign() successfully allocated memory or not before accessing the memory. Check the return value of memalign() and return NULL if allocating aligned memory fails. Fixes: a2561b12fe39 ("selftests/resctrl: Add built in benchmark") Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/resctrl/fill_buf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 56ccbeae0638..c20d0a7ecbe6 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -68,6 +68,8 @@ static void *malloc_and_init_memory(size_t s) size_t s64; void *p = memalign(PAGE_SIZE, s); + if (!p) + return NULL; p64 = (uint64_t *)p; s64 = s / sizeof(uint64_t); From 0c29f14cf470ce7e7fe85eb25602bb138b871256 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Wed, 15 Feb 2023 15:06:00 +0200 Subject: [PATCH 2734/4345] selftests/resctrl: Check for return value after write_schemata() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0d45c83b95da414e98ad333e723141a94f6e2c64 ] MBA test case writes schemata but it does not check if the write is successful or not. Add the error check and return error properly. Fixes: 01fee6b4d1f9 ("selftests/resctrl: Add MBA test") Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- tools/testing/selftests/resctrl/mba_test.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index 6449fbd96096..6cfddd1d4355 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -28,6 +28,7 @@ static int mba_setup(int num, ...) struct resctrl_val_param *p; char allocation_str[64]; va_list param; + int ret; va_start(param, num); p = va_arg(param, struct resctrl_val_param *); @@ -45,7 +46,11 @@ static int mba_setup(int num, ...) sprintf(allocation_str, "%d", allocation); - write_schemata(p->ctrlgrp, allocation_str, p->cpu_no, p->resctrl_val); + ret = write_schemata(p->ctrlgrp, allocation_str, p->cpu_no, + p->resctrl_val); + if (ret < 0) + return ret; + allocation -= ALLOCATION_STEP; return 0; From fea3144639269d37923f7a88906b3fa7f1231603 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Wed, 12 Apr 2023 15:59:19 +0200 Subject: [PATCH 2735/4345] selinux: fix Makefile dependencies of flask.h [ Upstream commit bcab1adeaad4b39a1e04cb98979a367d08253f03 ] Make the flask.h target depend on the genheaders binary instead of classmap.h to ensure that it is rebuilt if any of the dependencies of genheaders are changed. Notably this fixes flask.h not being rebuilt when initial_sid_to_string.h is modified. Fixes: 8753f6bec352 ("selinux: generate flask headers during kernel build") Signed-off-by: Ondrej Mosnacek Acked-by: Stephen Smalley Signed-off-by: Paul Moore Signed-off-by: Sasha Levin --- security/selinux/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/security/selinux/Makefile b/security/selinux/Makefile index 4d8e0e8adf0b..47e4aba3a868 100644 --- a/security/selinux/Makefile +++ b/security/selinux/Makefile @@ -21,8 +21,8 @@ ccflags-y := -I$(srctree)/security/selinux -I$(srctree)/security/selinux/include $(addprefix $(obj)/,$(selinux-y)): $(obj)/flask.h quiet_cmd_flask = GEN $(obj)/flask.h $(obj)/av_permissions.h - cmd_flask = scripts/selinux/genheaders/genheaders $(obj)/flask.h $(obj)/av_permissions.h + cmd_flask = $< $(obj)/flask.h $(obj)/av_permissions.h targets += flask.h av_permissions.h -$(obj)/flask.h: $(src)/include/classmap.h FORCE +$(obj)/flask.h: scripts/selinux/genheaders/genheaders FORCE $(call if_changed,flask) From 3ec77043a27d2dc7689cc570bfc9ba5015a76619 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 12 Apr 2023 13:29:11 -0400 Subject: [PATCH 2736/4345] selinux: ensure av_permissions.h is built when needed [ Upstream commit 4ce1f694eb5d8ca607fed8542d32a33b4f1217a5 ] The Makefile rule responsible for building flask.h and av_permissions.h only lists flask.h as a target which means that av_permissions.h is only generated when flask.h needs to be generated. This patch fixes this by adding av_permissions.h as a target to the rule. Fixes: 8753f6bec352 ("selinux: generate flask headers during kernel build") Signed-off-by: Paul Moore Signed-off-by: Sasha Levin --- security/selinux/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/selinux/Makefile b/security/selinux/Makefile index 47e4aba3a868..ee1ddda96447 100644 --- a/security/selinux/Makefile +++ b/security/selinux/Makefile @@ -24,5 +24,5 @@ quiet_cmd_flask = GEN $(obj)/flask.h $(obj)/av_permissions.h cmd_flask = $< $(obj)/flask.h $(obj)/av_permissions.h targets += flask.h av_permissions.h -$(obj)/flask.h: scripts/selinux/genheaders/genheaders FORCE +$(obj)/flask.h $(obj)/av_permissions.h &: scripts/selinux/genheaders/genheaders FORCE $(call if_changed,flask) From c62a2331abfaed811ebbe29ade9774fbbc42683f Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Thu, 24 Nov 2022 14:55:28 +0100 Subject: [PATCH 2737/4345] tpm, tpm_tis: Do not skip reset of original interrupt vector [ Upstream commit ed9be0e6c892a783800d77a41ca4c7255c6af8c5 ] If in tpm_tis_probe_irq_single() an error occurs after the original interrupt vector has been read, restore the interrupts before the error is returned. Since the caller does not check the error value, return -1 in any case that the TPM_CHIP_FLAG_IRQ flag is not set. Since the return value of function tpm_tis_gen_interrupt() is not longer used, make it a void function. Fixes: 1107d065fdf1 ("tpm_tis: Introduce intermediate layer for TPM access") Signed-off-by: Lino Sanfilippo Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_tis_core.c | 29 +++++++++++------------------ 1 file changed, 11 insertions(+), 18 deletions(-) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index dc56b976d816..ae0c773a6041 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -714,7 +714,7 @@ static irqreturn_t tis_int_handler(int dummy, void *dev_id) return IRQ_HANDLED; } -static int tpm_tis_gen_interrupt(struct tpm_chip *chip) +static void tpm_tis_gen_interrupt(struct tpm_chip *chip) { const char *desc = "attempting to generate an interrupt"; u32 cap2; @@ -723,7 +723,7 @@ static int tpm_tis_gen_interrupt(struct tpm_chip *chip) ret = request_locality(chip, 0); if (ret < 0) - return ret; + return; if (chip->flags & TPM_CHIP_FLAG_TPM2) ret = tpm2_get_tpm_pt(chip, 0x100, &cap2, desc); @@ -731,8 +731,6 @@ static int tpm_tis_gen_interrupt(struct tpm_chip *chip) ret = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, 0); release_locality(chip, 0); - - return ret; } /* Register the IRQ and issue a command that will cause an interrupt. If an @@ -762,42 +760,37 @@ static int tpm_tis_probe_irq_single(struct tpm_chip *chip, u32 intmask, rc = tpm_tis_write8(priv, TPM_INT_VECTOR(priv->locality), irq); if (rc < 0) - return rc; + goto restore_irqs; rc = tpm_tis_read32(priv, TPM_INT_STATUS(priv->locality), &int_status); if (rc < 0) - return rc; + goto restore_irqs; /* Clear all existing */ rc = tpm_tis_write32(priv, TPM_INT_STATUS(priv->locality), int_status); if (rc < 0) - return rc; - + goto restore_irqs; /* Turn on */ rc = tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask | TPM_GLOBAL_INT_ENABLE); if (rc < 0) - return rc; + goto restore_irqs; priv->irq_tested = false; /* Generate an interrupt by having the core call through to * tpm_tis_send */ - rc = tpm_tis_gen_interrupt(chip); - if (rc < 0) - return rc; + tpm_tis_gen_interrupt(chip); +restore_irqs: /* tpm_tis_send will either confirm the interrupt is working or it * will call disable_irq which undoes all of the above. */ if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) { - rc = tpm_tis_write8(priv, original_int_vec, - TPM_INT_VECTOR(priv->locality)); - if (rc < 0) - return rc; - - return 1; + tpm_tis_write8(priv, original_int_vec, + TPM_INT_VECTOR(priv->locality)); + return -1; } return 0; From cbb1dd27058eac7327a0c67e450fcac5b828d29d Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Thu, 24 Nov 2022 14:55:26 +0100 Subject: [PATCH 2738/4345] tpm, tpm_tis: Claim locality before writing TPM_INT_ENABLE register MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 282657a8bd7fddcf511b834f43705001668b33a7 ] In disable_interrupts() the TPM_GLOBAL_INT_ENABLE bit is unset in the TPM_INT_ENABLE register to shut the interrupts off. However modifying the register is only possible with a held locality. So claim the locality before disable_interrupts() is called. Signed-off-by: Lino Sanfilippo Tested-by: Michael Niewöhner Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Stable-dep-of: 955df4f87760 ("tpm, tpm_tis: Claim locality when interrupts are reenabled on resume") Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_tis_core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index ae0c773a6041..274096fece3f 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1076,7 +1076,11 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, dev_err(&chip->dev, FW_BUG "TPM interrupt not working, polling instead\n"); + rc = request_locality(chip, 0); + if (rc < 0) + goto out_err; disable_interrupts(chip); + release_locality(chip, 0); } } else { tpm_tis_probe_irq(chip, intmask); From 35ca7f62528320193673678f997998c40119fb44 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Thu, 24 Nov 2022 14:55:27 +0100 Subject: [PATCH 2739/4345] tpm, tpm_tis: Disable interrupts if tpm_tis_probe_irq() failed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6d789ad726950e612a7f31044260337237c5b490 ] Both functions tpm_tis_probe_irq_single() and tpm_tis_probe_irq() may setup the interrupts and then return with an error. This case is indicated by a missing TPM_CHIP_FLAG_IRQ flag in chip->flags. Currently the interrupt setup is only undone if tpm_tis_probe_irq_single() fails. Undo the setup also if tpm_tis_probe_irq() fails. Signed-off-by: Lino Sanfilippo Tested-by: Michael Niewöhner Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Stable-dep-of: 955df4f87760 ("tpm, tpm_tis: Claim locality when interrupts are reenabled on resume") Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_tis_core.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 274096fece3f..99cbf6fb062c 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1069,21 +1069,21 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, goto out_err; } - if (irq) { + if (irq) tpm_tis_probe_irq_single(chip, intmask, IRQF_SHARED, irq); - if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) { - dev_err(&chip->dev, FW_BUG + else + tpm_tis_probe_irq(chip, intmask); + + if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) { + dev_err(&chip->dev, FW_BUG "TPM interrupt not working, polling instead\n"); - rc = request_locality(chip, 0); - if (rc < 0) - goto out_err; - disable_interrupts(chip); - release_locality(chip, 0); - } - } else { - tpm_tis_probe_irq(chip, intmask); + rc = request_locality(chip, 0); + if (rc < 0) + goto out_err; + disable_interrupts(chip); + release_locality(chip, 0); } } From 140735c46d376cd4587ccd4dd6a501ae1076109e Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Thu, 24 Nov 2022 14:55:29 +0100 Subject: [PATCH 2740/4345] tpm, tpm_tis: Claim locality before writing interrupt registers [ Upstream commit 15d7aa4e46eba87242a320f39773aa16faddadee ] In tpm_tis_probe_single_irq() interrupt registers TPM_INT_VECTOR, TPM_INT_STATUS and TPM_INT_ENABLE are modified to setup the interrupts. Currently these modifications are done without holding a locality thus they have no effect. Fix this by claiming the (default) locality before the registers are written. Since now tpm_tis_gen_interrupt() is called with the locality already claimed remove locality request and release from this function. Signed-off-by: Lino Sanfilippo Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Stable-dep-of: 955df4f87760 ("tpm, tpm_tis: Claim locality when interrupts are reenabled on resume") Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_tis_core.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 99cbf6fb062c..52826a7edf80 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -721,16 +721,10 @@ static void tpm_tis_gen_interrupt(struct tpm_chip *chip) cap_t cap; int ret; - ret = request_locality(chip, 0); - if (ret < 0) - return; - if (chip->flags & TPM_CHIP_FLAG_TPM2) ret = tpm2_get_tpm_pt(chip, 0x100, &cap2, desc); else ret = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, 0); - - release_locality(chip, 0); } /* Register the IRQ and issue a command that will cause an interrupt. If an @@ -753,11 +747,17 @@ static int tpm_tis_probe_irq_single(struct tpm_chip *chip, u32 intmask, } priv->irq = irq; - rc = tpm_tis_read8(priv, TPM_INT_VECTOR(priv->locality), - &original_int_vec); + rc = request_locality(chip, 0); if (rc < 0) return rc; + rc = tpm_tis_read8(priv, TPM_INT_VECTOR(priv->locality), + &original_int_vec); + if (rc < 0) { + release_locality(chip, priv->locality); + return rc; + } + rc = tpm_tis_write8(priv, TPM_INT_VECTOR(priv->locality), irq); if (rc < 0) goto restore_irqs; @@ -790,10 +790,12 @@ restore_irqs: if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) { tpm_tis_write8(priv, original_int_vec, TPM_INT_VECTOR(priv->locality)); - return -1; + rc = -1; } - return 0; + release_locality(chip, priv->locality); + + return rc; } /* Try to find the IRQ the TPM is using. This is for legacy x86 systems that From 933bfc5ad2132d4513d714cb596485c76339a5c4 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Thu, 24 Nov 2022 14:55:33 +0100 Subject: [PATCH 2741/4345] tpm, tpm: Implement usage counter for locality MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7a2f55d0be296c4e81fd782f3d6c43ed4ec7e265 ] Implement a usage counter for the (default) locality used by the TPM TIS driver: Request the locality from the TPM if it has not been claimed yet, otherwise only increment the counter. Also release the locality if the counter is 0 otherwise only decrement the counter. Since in case of SPI the register accesses are locked by means of the SPI bus mutex use a sleepable lock (i.e. also a mutex) to ensure thread-safety of the counter which may be accessed by both a userspace thread and the interrupt handler. By doing this refactor the names of the amended functions to use a more appropriate prefix. Signed-off-by: Lino Sanfilippo Tested-by: Michael Niewöhner Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Stable-dep-of: 955df4f87760 ("tpm, tpm_tis: Claim locality when interrupts are reenabled on resume") Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_tis_core.c | 65 +++++++++++++++++++++++---------- drivers/char/tpm/tpm_tis_core.h | 2 + 2 files changed, 48 insertions(+), 19 deletions(-) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 52826a7edf80..3ea0fff30273 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -136,16 +136,27 @@ static bool check_locality(struct tpm_chip *chip, int l) return false; } -static int release_locality(struct tpm_chip *chip, int l) +static int __tpm_tis_relinquish_locality(struct tpm_tis_data *priv, int l) { - struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); - tpm_tis_write8(priv, TPM_ACCESS(l), TPM_ACCESS_ACTIVE_LOCALITY); return 0; } -static int request_locality(struct tpm_chip *chip, int l) +static int tpm_tis_relinquish_locality(struct tpm_chip *chip, int l) +{ + struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); + + mutex_lock(&priv->locality_count_mutex); + priv->locality_count--; + if (priv->locality_count == 0) + __tpm_tis_relinquish_locality(priv, l); + mutex_unlock(&priv->locality_count_mutex); + + return 0; +} + +static int __tpm_tis_request_locality(struct tpm_chip *chip, int l) { struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); unsigned long stop, timeout; @@ -186,6 +197,20 @@ again: return -1; } +static int tpm_tis_request_locality(struct tpm_chip *chip, int l) +{ + struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); + int ret = 0; + + mutex_lock(&priv->locality_count_mutex); + if (priv->locality_count == 0) + ret = __tpm_tis_request_locality(chip, l); + if (!ret) + priv->locality_count++; + mutex_unlock(&priv->locality_count_mutex); + return ret; +} + static u8 tpm_tis_status(struct tpm_chip *chip) { struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); @@ -638,7 +663,7 @@ static int probe_itpm(struct tpm_chip *chip) if (vendor != TPM_VID_INTEL) return 0; - if (request_locality(chip, 0) != 0) + if (tpm_tis_request_locality(chip, 0) != 0) return -EBUSY; rc = tpm_tis_send_data(chip, cmd_getticks, len); @@ -659,7 +684,7 @@ static int probe_itpm(struct tpm_chip *chip) out: tpm_tis_ready(chip); - release_locality(chip, priv->locality); + tpm_tis_relinquish_locality(chip, priv->locality); return rc; } @@ -747,14 +772,14 @@ static int tpm_tis_probe_irq_single(struct tpm_chip *chip, u32 intmask, } priv->irq = irq; - rc = request_locality(chip, 0); + rc = tpm_tis_request_locality(chip, 0); if (rc < 0) return rc; rc = tpm_tis_read8(priv, TPM_INT_VECTOR(priv->locality), &original_int_vec); if (rc < 0) { - release_locality(chip, priv->locality); + tpm_tis_relinquish_locality(chip, priv->locality); return rc; } @@ -793,7 +818,7 @@ restore_irqs: rc = -1; } - release_locality(chip, priv->locality); + tpm_tis_relinquish_locality(chip, priv->locality); return rc; } @@ -909,8 +934,8 @@ static const struct tpm_class_ops tpm_tis = { .req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID, .req_canceled = tpm_tis_req_canceled, - .request_locality = request_locality, - .relinquish_locality = release_locality, + .request_locality = tpm_tis_request_locality, + .relinquish_locality = tpm_tis_relinquish_locality, .clk_enable = tpm_tis_clkrun_enable, }; @@ -944,6 +969,8 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, priv->timeout_min = TPM_TIMEOUT_USECS_MIN; priv->timeout_max = TPM_TIMEOUT_USECS_MAX; priv->phy_ops = phy_ops; + priv->locality_count = 0; + mutex_init(&priv->locality_count_mutex); dev_set_drvdata(&chip->dev, priv); @@ -990,14 +1017,14 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, TPM_INTF_DATA_AVAIL_INT | TPM_INTF_STS_VALID_INT; intmask &= ~TPM_GLOBAL_INT_ENABLE; - rc = request_locality(chip, 0); + rc = tpm_tis_request_locality(chip, 0); if (rc < 0) { rc = -ENODEV; goto out_err; } tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); - release_locality(chip, 0); + tpm_tis_relinquish_locality(chip, 0); rc = tpm_chip_start(chip); if (rc) @@ -1057,13 +1084,13 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, * proper timeouts for the driver. */ - rc = request_locality(chip, 0); + rc = tpm_tis_request_locality(chip, 0); if (rc < 0) goto out_err; rc = tpm_get_timeouts(chip); - release_locality(chip, 0); + tpm_tis_relinquish_locality(chip, 0); if (rc) { dev_err(dev, "Could not get TPM timeouts and durations\n"); @@ -1081,11 +1108,11 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, dev_err(&chip->dev, FW_BUG "TPM interrupt not working, polling instead\n"); - rc = request_locality(chip, 0); + rc = tpm_tis_request_locality(chip, 0); if (rc < 0) goto out_err; disable_interrupts(chip); - release_locality(chip, 0); + tpm_tis_relinquish_locality(chip, 0); } } @@ -1158,13 +1185,13 @@ int tpm_tis_resume(struct device *dev) * an error code but for unknown reason it isn't handled. */ if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { - ret = request_locality(chip, 0); + ret = tpm_tis_request_locality(chip, 0); if (ret < 0) return ret; tpm1_do_selftest(chip); - release_locality(chip, 0); + tpm_tis_relinquish_locality(chip, 0); } return 0; diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index 3be24f221e32..464ed352ab2e 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -90,6 +90,8 @@ enum tpm_tis_flags { struct tpm_tis_data { u16 manufacturer_id; + struct mutex locality_count_mutex; + unsigned int locality_count; int locality; int irq; bool irq_tested; From e5ec129158f3dbcd56b7b9819713c1c0521dbb43 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Thu, 24 Nov 2022 14:55:36 +0100 Subject: [PATCH 2742/4345] tpm, tpm_tis: Claim locality when interrupts are reenabled on resume [ Upstream commit 955df4f87760b3bb2af253d3fbb12fb712b3ffa6 ] In tpm_tis_resume() make sure that the locality has been claimed when tpm_tis_reenable_interrupts() is called. Otherwise the writings to the register might not have any effect. Fixes: 45baa1d1fa39 ("tpm_tis: Re-enable interrupts upon (S3) resume") Signed-off-by: Lino Sanfilippo Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Sasha Levin --- drivers/char/tpm/tpm_tis_core.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 3ea0fff30273..d65fff4e2ebe 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1173,28 +1173,27 @@ int tpm_tis_resume(struct device *dev) struct tpm_chip *chip = dev_get_drvdata(dev); int ret; + ret = tpm_tis_request_locality(chip, 0); + if (ret < 0) + return ret; + if (chip->flags & TPM_CHIP_FLAG_IRQ) tpm_tis_reenable_interrupts(chip); ret = tpm_pm_resume(dev); if (ret) - return ret; + goto out; /* * TPM 1.2 requires self-test on resume. This function actually returns * an error code but for unknown reason it isn't handled. */ - if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { - ret = tpm_tis_request_locality(chip, 0); - if (ret < 0) - return ret; - + if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) tpm1_do_selftest(chip); +out: + tpm_tis_relinquish_locality(chip, 0); - tpm_tis_relinquish_locality(chip, 0); - } - - return 0; + return ret; } EXPORT_SYMBOL_GPL(tpm_tis_resume); #endif From 7a4579cd6e4936de107c82499c3c9ee11b63401e Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Tue, 11 Apr 2023 01:37:14 +0800 Subject: [PATCH 2743/4345] erofs: stop parsing non-compact HEAD index if clusterofs is invalid [ Upstream commit cc4efd3dd2ac9f89143e5d881609747ecff04164 ] Syzbot generated a crafted image [1] with a non-compact HEAD index of clusterofs 33024 while valid numbers should be 0 ~ lclustersize-1, which causes the following unexpected behavior as below: BUG: unable to handle page fault for address: fffff52101a3fff9 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 23ffed067 P4D 23ffed067 PUD 0 Oops: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 4398 Comm: kworker/u5:1 Not tainted 6.3.0-rc6-syzkaller-g09a9639e56c0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023 Workqueue: erofs_worker z_erofs_decompressqueue_work RIP: 0010:z_erofs_decompress_queue+0xb7e/0x2b40 ... Call Trace: z_erofs_decompressqueue_work+0x99/0xe0 process_one_work+0x8f6/0x1170 worker_thread+0xa63/0x1210 kthread+0x270/0x300 ret_from_fork+0x1f/0x30 Note that normal images or images using compact indexes are not impacted. Let's fix this now. [1] https://lore.kernel.org/r/000000000000ec75b005ee97fbaa@google.com Reported-and-tested-by: syzbot+aafb3f37cfeb6534c4ac@syzkaller.appspotmail.com Fixes: 02827e1796b3 ("staging: erofs: add erofs_map_blocks_iter") Fixes: 152a333a5895 ("staging: erofs: add compacted compression indexes support") Signed-off-by: Gao Xiang Reviewed-by: Chao Yu Link: https://lore.kernel.org/r/20230410173714.104604-1-hsiangkao@linux.alibaba.com Signed-off-by: Sasha Levin --- fs/erofs/zmap.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 14d2de35110c..f18194fd8d77 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -179,6 +179,10 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: case Z_EROFS_VLE_CLUSTER_TYPE_HEAD: m->clusterofs = le16_to_cpu(di->di_clusterofs); + if (m->clusterofs >= 1 << vi->z_logical_clusterbits) { + DBG_BUGON(1); + return -EFSCORRUPTED; + } m->pblk = le32_to_cpu(di->di_u.blkaddr); break; default: From 056a1217cffa6af4318f8d0161e78b77a2b32914 Mon Sep 17 00:00:00 2001 From: Jingbo Xu Date: Fri, 14 Apr 2023 14:18:10 +0800 Subject: [PATCH 2744/4345] erofs: fix potential overflow calculating xattr_isize [ Upstream commit 1b3567a1969b26f709d82a874498c0754ea841c3 ] Given on-disk i_xattr_icount is 16 bits and xattr_isize is calculated from i_xattr_icount multiplying 4, xattr_isize has a theoretical maximum of 256K (64K * 4). Thus declare xattr_isize as unsigned int to avoid the potential overflow. Fixes: bfb8674dc044 ("staging: erofs: add erofs in-memory stuffs") Signed-off-by: Jingbo Xu Reviewed-by: Gao Xiang Reviewed-by: Chao Yu Link: https://lore.kernel.org/r/20230414061810.6479-1-jefflexu@linux.alibaba.com Signed-off-by: Gao Xiang Signed-off-by: Sasha Levin --- fs/erofs/internal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 67a7ec945686..ce52f708a403 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -232,7 +232,7 @@ struct erofs_inode { unsigned char datalayout; unsigned char inode_isize; - unsigned short xattr_isize; + unsigned int xattr_isize; unsigned int xattr_shared_count; unsigned int *xattr_shared_xattrs; From ae784c3ed37384210a43529f7842c865581c1258 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 19 Jan 2023 15:17:34 -0800 Subject: [PATCH 2745/4345] drm/rockchip: Drop unbalanced obj unref [ Upstream commit 8ee3b0e85f6ccd9e6c527bc50eaba774c3bb18d0 ] In the error path, rockchip_drm_gem_object_mmap() is dropping an obj reference that it doesn't own. Fixes: 41315b793e13 ("drm/rockchip: use drm_gem_mmap helpers") Signed-off-by: Rob Clark Signed-off-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/20230119231734.2884543-1-robdclark@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/rockchip/rockchip_drm_gem.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index 62e5d0970525..22ff4a592976 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -250,9 +250,6 @@ static int rockchip_drm_gem_object_mmap(struct drm_gem_object *obj, else ret = rockchip_drm_gem_object_mmap_dma(obj, vma); - if (ret) - drm_gem_vm_close(vma); - return ret; } From 67f07215eb8b19cab11dc0929c06c71e069afbcf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ADra=20Canal?= Date: Thu, 2 Feb 2023 09:55:17 -0300 Subject: [PATCH 2746/4345] drm/vgem: add missing mutex_destroy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7c18189b14b33c1fbf76480b1bd217877c086e67 ] vgem_fence_open() instantiates a mutex for a particular fence instance, but never destroys it by calling mutex_destroy() in vgem_fence_close(). So, add the missing mutex_destroy() to guarantee proper resource destruction. Fixes: 407779848445 ("drm/vgem: Attach sw fences to exported vGEM dma-buf (ioctl)") Signed-off-by: Maíra Canal Reviewed-by: Stanislaw Gruszka Signed-off-by: Maíra Canal Link: https://patchwork.freedesktop.org/patch/msgid/20230202125517.427976-1-mcanal@igalia.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/vgem/vgem_fence.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c index 17f32f550dd9..575bc331716e 100644 --- a/drivers/gpu/drm/vgem/vgem_fence.c +++ b/drivers/gpu/drm/vgem/vgem_fence.c @@ -249,4 +249,5 @@ void vgem_fence_close(struct vgem_file *vfile) { idr_for_each(&vfile->fence_idr, __vgem_fence_idr_fini, vfile); idr_destroy(&vfile->fence_idr); + mutex_destroy(&vfile->fence_mutex); } From e33f374d65d9d935a8de1ca95a604230195518a9 Mon Sep 17 00:00:00 2001 From: Dom Cobley Date: Fri, 27 Jan 2023 16:40:52 +0100 Subject: [PATCH 2747/4345] drm/probe-helper: Cancel previous job before starting new one [ Upstream commit a8e47884f1906cd7440fafa056adc8817568e73e ] Currently we schedule a call to output_poll_execute from drm_kms_helper_poll_enable for 10s in future. Later we try to replace that in drm_helper_probe_single_connector_modes with a 0s schedule with delayed_event set. But as there is already a job in the queue this fails, and the immediate job we wanted with delayed_event set doesn't occur until 10s later. And that call acts as if connector state has changed, reprobing modes. This has a side effect of waking up a display that has been blanked. Make sure we cancel the old job before submitting the immediate one. Fixes: 162b6a57ac50 ("drm/probe-helper: don't lose hotplug event") Acked-by: Daniel Vetter Signed-off-by: Dom Cobley [Maxime: Switched to mod_delayed_work] Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20230127154052.452524-1-maxime@cerno.tech Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_probe_helper.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index e5432dcf6999..d3f0d048594e 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -488,8 +488,9 @@ retry: */ dev->mode_config.delayed_event = true; if (dev->mode_config.poll_enabled) - schedule_delayed_work(&dev->mode_config.output_poll_work, - 0); + mod_delayed_work(system_wq, + &dev->mode_config.output_poll_work, + 0); } /* Re-enable polling in case the global poll config changed. */ From a1e6a4161a27533cee2f678b97011f43886f937d Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 16 Nov 2020 12:57:13 +0200 Subject: [PATCH 2748/4345] soc: ti: pm33xx: Enable basic PM runtime support for genpd [ Upstream commit 74033131d2467fda6b76ba10bc80a75fb47e03d1 ] To prepare for moving to use genpd, let's enable basic PM runtime support. Cc: Dave Gerlach Cc: Santosh Shilimkar Cc: Suman Anna Signed-off-by: Tony Lindgren Stable-dep-of: 8f3c307b580a ("soc: ti: pm33xx: Fix refcount leak in am33xx_pm_probe") Signed-off-by: Sasha Levin --- drivers/soc/ti/pm33xx.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/soc/ti/pm33xx.c b/drivers/soc/ti/pm33xx.c index dc21aa855a45..332588de22f3 100644 --- a/drivers/soc/ti/pm33xx.c +++ b/drivers/soc/ti/pm33xx.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -555,16 +556,26 @@ static int am33xx_pm_probe(struct platform_device *pdev) suspend_wfi_flags |= WFI_FLAG_WAKE_M3; #endif /* CONFIG_SUSPEND */ + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + pm_runtime_put_noidle(dev); + goto err_pm_runtime_disable; + } + ret = pm_ops->init(am33xx_do_sram_idle); if (ret) { dev_err(dev, "Unable to call core pm init!\n"); ret = -ENODEV; - goto err_put_wkup_m3_ipc; + goto err_pm_runtime_put; } return 0; -err_put_wkup_m3_ipc: +err_pm_runtime_put: + pm_runtime_put_sync(dev); +err_pm_runtime_disable: + pm_runtime_disable(dev); wkup_m3_ipc_put(m3_ipc); err_unsetup_rtc: iounmap(rtc_base_virt); @@ -577,6 +588,8 @@ err_free_sram: static int am33xx_pm_remove(struct platform_device *pdev) { + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); if (pm_ops->deinit) pm_ops->deinit(); suspend_set_ops(NULL); From 08310f810975c8c9e17c6ffb99fdb76a84e8adb7 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Fri, 6 Jan 2023 09:40:22 +0400 Subject: [PATCH 2749/4345] soc: ti: pm33xx: Fix refcount leak in am33xx_pm_probe [ Upstream commit 8f3c307b580a4a6425896007325bddefc36e8d91 ] wkup_m3_ipc_get() takes refcount, which should be freed by wkup_m3_ipc_put(). Add missing refcount release in the error paths. Fixes: 5a99ae0092fe ("soc: ti: pm33xx: AM437X: Add rtc_only with ddr in self-refresh support") Signed-off-by: Miaoqian Lin Link: https://lore.kernel.org/r/20230106054022.947529-1-linmq006@gmail.com Signed-off-by: Nishanth Menon Signed-off-by: Sasha Levin --- drivers/soc/ti/pm33xx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/soc/ti/pm33xx.c b/drivers/soc/ti/pm33xx.c index 332588de22f3..44ec0048911c 100644 --- a/drivers/soc/ti/pm33xx.c +++ b/drivers/soc/ti/pm33xx.c @@ -529,7 +529,7 @@ static int am33xx_pm_probe(struct platform_device *pdev) ret = am33xx_pm_alloc_sram(); if (ret) - return ret; + goto err_wkup_m3_ipc_put; ret = am33xx_pm_rtc_setup(); if (ret) @@ -576,13 +576,14 @@ err_pm_runtime_put: pm_runtime_put_sync(dev); err_pm_runtime_disable: pm_runtime_disable(dev); - wkup_m3_ipc_put(m3_ipc); err_unsetup_rtc: iounmap(rtc_base_virt); clk_put(rtc_fck); err_free_sram: am33xx_pm_free_sram(); pm33xx_dev = NULL; +err_wkup_m3_ipc_put: + wkup_m3_ipc_put(m3_ipc); return ret; } From fbfca9b8399fe82e5b5c54d74e6d79977a4ecc5e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 16 Feb 2023 16:30:31 +0100 Subject: [PATCH 2750/4345] arm64: dts: renesas: r8a77990: Remove bogus voltages from OPP table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit fb76b0fae3ca880363214e1dcd6513ab8bd529e7 ] According to the R-Car Series, 3rd Generation Hardware User’s Manual Rev. 2.30, the System CPU cores on R-Car E3 do not have their own power supply, but use the common internal power supply (typical 1.03V). Hence remove the "opp-microvolt" properties from the Operating Performance Points table. They are optional, and unused, when none of the CPU nodes is tied to a regulator using the "cpu-supply" property. Fixes: dd7188eb4ed128dc ("arm64: dts: renesas: r8a77990: Add OPPs table for cpu devices") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/9232578d9d395d529f64db3333a371e31327f459.1676560856.git.geert+renesas@glider.be Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/renesas/r8a77990.dtsi | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/boot/dts/renesas/r8a77990.dtsi b/arch/arm64/boot/dts/renesas/r8a77990.dtsi index 37159b9408e8..e91d197a4c0b 100644 --- a/arch/arm64/boot/dts/renesas/r8a77990.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77990.dtsi @@ -60,17 +60,14 @@ opp-shared; opp-800000000 { opp-hz = /bits/ 64 <800000000>; - opp-microvolt = <820000>; clock-latency-ns = <300000>; }; opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; - opp-microvolt = <820000>; clock-latency-ns = <300000>; }; opp-1200000000 { opp-hz = /bits/ 64 <1200000000>; - opp-microvolt = <820000>; clock-latency-ns = <300000>; opp-suspend; }; From 9c4c9010ae80c5f12d78f68b1ddcea70e94cc82d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 16 Feb 2023 16:30:32 +0100 Subject: [PATCH 2751/4345] arm64: dts: renesas: r8a774c0: Remove bogus voltages from OPP table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 554edc3e9239bb81e61be9f0f5dbbeb528a69e72 ] According to the RZ/G Series, 2nd Generation Hardware User’s Manual Rev. 1.11, the System CPU cores on RZ/G2E do not have their own power supply, but use the common internal power supply (typical 1.03V). Hence remove the "opp-microvolt" properties from the Operating Performance Points table. They are optional, and unused, when none of the CPU nodes is tied to a regulator using the "cpu-supply" property. Fixes: 231d8908a66fa98f ("arm64: dts: renesas: r8a774c0: Add OPPs table for cpu devices") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/8348e18a011ded94e35919cd8e17c0be1f9acf2f.1676560856.git.geert+renesas@glider.be Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/renesas/r8a774c0.dtsi | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi index 4c7d7e8f8e28..c4a6dfae93aa 100644 --- a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi @@ -49,17 +49,14 @@ opp-shared; opp-800000000 { opp-hz = /bits/ 64 <800000000>; - opp-microvolt = <820000>; clock-latency-ns = <300000>; }; opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; - opp-microvolt = <820000>; clock-latency-ns = <300000>; }; opp-1200000000 { opp-hz = /bits/ 64 <1200000000>; - opp-microvolt = <820000>; clock-latency-ns = <300000>; opp-suspend; }; From 6e6c27b2fb9df6387ea5e766b29807a048d4c37e Mon Sep 17 00:00:00 2001 From: Vinod Polimera Date: Thu, 2 Mar 2023 22:03:07 +0530 Subject: [PATCH 2752/4345] drm/msm/disp/dpu: check for crtc enable rather than crtc active to release shared resources [ Upstream commit b6975693846b562c4d3e0e60cc884affc5bdac00 ] According to KMS documentation, The driver must not release any shared resources if active is set to false but enable still true. Fixes: ccc862b957c6 ("drm/msm/dpu: Fix reservation failures in modeset") Signed-off-by: Vinod Polimera Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/524726/ Link: https://lore.kernel.org/r/1677774797-31063-5-git-send-email-quic_vpolimer@quicinc.com Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index a0274fcfe9c9..408fc6c8a6df 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -634,7 +634,7 @@ static int dpu_encoder_virt_atomic_check( if (drm_atomic_crtc_needs_modeset(crtc_state)) { dpu_rm_release(global_state, drm_enc); - if (!crtc_state->active_changed || crtc_state->active) + if (!crtc_state->active_changed || crtc_state->enable) ret = dpu_rm_reserve(&dpu_kms->rm, global_state, drm_enc, crtc_state, topology); } From e951bdaa65865a67902d2db6a697178b16f39437 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Sat, 11 Feb 2023 09:17:28 +0800 Subject: [PATCH 2753/4345] EDAC/skx: Fix overflows on the DRAM row address mapping arrays [ Upstream commit 71b1e3ba3fed5a34c5fac6d3a15c2634b04c1eb7 ] The current DRAM row address mapping arrays skx_{open,close}_row[] only support ranks with sizes up to 16G. Decoding a rank address to a DRAM row address for a 32G rank by using either one of the above arrays by the skx_edac driver, will result in an overflow on the array. For a 32G rank, the most significant DRAM row address bit (the bit17) is mapped from the bit34 of the rank address. Add this new mapping item to both arrays to fix the overflow issue. Fixes: 4ec656bdf43a ("EDAC, skx_edac: Add EDAC driver for Skylake") Reported-by: Feng Xu Tested-by: Feng Xu Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Link: https://lore.kernel.org/all/20230211011728.71764-1-qiuxu.zhuo@intel.com Signed-off-by: Sasha Levin --- drivers/edac/skx_base.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c index f887e3166651..ba3e83313938 100644 --- a/drivers/edac/skx_base.c +++ b/drivers/edac/skx_base.c @@ -509,7 +509,7 @@ rir_found: } static u8 skx_close_row[] = { - 15, 16, 17, 18, 20, 21, 22, 28, 10, 11, 12, 13, 29, 30, 31, 32, 33 + 15, 16, 17, 18, 20, 21, 22, 28, 10, 11, 12, 13, 29, 30, 31, 32, 33, 34 }; static u8 skx_close_column[] = { @@ -517,7 +517,7 @@ static u8 skx_close_column[] = { }; static u8 skx_open_row[] = { - 14, 15, 16, 20, 28, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31, 32, 33 + 14, 15, 16, 20, 28, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31, 32, 33, 34 }; static u8 skx_open_column[] = { From 94e6f7e75729d52189b29f20bc1f8fcfe9698f62 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 13 Feb 2023 22:03:31 +0100 Subject: [PATCH 2754/4345] arm64: dts: qcom: msm8998: Fix stm-stimulus-base reg name [ Upstream commit b5d08f08377218b1d2ab4026e427a7788b271c8e ] The name stm-data-base comes from ancient (msm-3.10 or older) downstream kernels. Upstream uses stm-stimulus-base instead. Fix it. Fixes: 783abfa2249a ("arm64: dts: qcom: msm8998: Add Coresight support") Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230213210331.2106877-1-konrad.dybcio@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8998.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 9e04ac3f596d..0ea4c9e7e180 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -1187,7 +1187,7 @@ compatible = "arm,coresight-stm", "arm,primecell"; reg = <0x06002000 0x1000>, <0x16280000 0x180000>; - reg-names = "stm-base", "stm-data-base"; + reg-names = "stm-base", "stm-stimulus-base"; status = "disabled"; clocks = <&rpmcc RPM_SMD_QDSS_CLK>, <&rpmcc RPM_SMD_QDSS_A_CLK>; From eb9c5b383e0317782178310139754ba098ff703e Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 15 Mar 2022 17:11:04 +0300 Subject: [PATCH 2755/4345] arm64: dts: qcom: sdm845: correct dynamic power coefficients MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 0e0a8e35d72533b3eef3365e900baacd7cede8e2 ] Following sm8150/sm8250 update sdm845 capacity-dmips-mhz and dynamic-power-coefficient based on the measurements [1], [2]. The energy model dynamic-power-coefficient values were calculated with DPC = µW / MHz / V^2 for each OPP, and averaged across all OPPs within each cluster for the final coefficient. Voltages were obtained from the qcom-cpufreq-hw driver that reads voltages from the OSM LUT programmed into the SoC. Normalized DMIPS/MHz capacity scale values for each CPU were calculated from CoreMarks/MHz (CoreMark iterations per second per MHz), which serves the same purpose. For each CPU, the final capacity-dmips-mhz value is the C/MHz value of its maximum frequency normalized to SCHED_CAPACITY_SCALE (1024) for the fastest CPU in the system. For more details on measurement process see the commit message for the commit 6aabed5526ee ("arm64: dts: qcom: sm8250: Add CPU capacities and energy model"). [1] https://github.com/kdrag0n/freqbench [2] https://github.com/kdrag0n/freqbench/tree/master/results/sdm845/main Cc: Danny Lin Signed-off-by: Dmitry Baryshkov Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220315141104.730235-1-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845.dtsi | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 9beb3c34fcdb..076b6949a0ee 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -196,8 +196,8 @@ cpu-idle-states = <&LITTLE_CPU_SLEEP_0 &LITTLE_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; - capacity-dmips-mhz = <607>; - dynamic-power-coefficient = <100>; + capacity-dmips-mhz = <611>; + dynamic-power-coefficient = <290>; qcom,freq-domain = <&cpufreq_hw 0>; operating-points-v2 = <&cpu0_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -221,8 +221,8 @@ cpu-idle-states = <&LITTLE_CPU_SLEEP_0 &LITTLE_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; - capacity-dmips-mhz = <607>; - dynamic-power-coefficient = <100>; + capacity-dmips-mhz = <611>; + dynamic-power-coefficient = <290>; qcom,freq-domain = <&cpufreq_hw 0>; operating-points-v2 = <&cpu0_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -243,8 +243,8 @@ cpu-idle-states = <&LITTLE_CPU_SLEEP_0 &LITTLE_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; - capacity-dmips-mhz = <607>; - dynamic-power-coefficient = <100>; + capacity-dmips-mhz = <611>; + dynamic-power-coefficient = <290>; qcom,freq-domain = <&cpufreq_hw 0>; operating-points-v2 = <&cpu0_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -265,8 +265,8 @@ cpu-idle-states = <&LITTLE_CPU_SLEEP_0 &LITTLE_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; - capacity-dmips-mhz = <607>; - dynamic-power-coefficient = <100>; + capacity-dmips-mhz = <611>; + dynamic-power-coefficient = <290>; qcom,freq-domain = <&cpufreq_hw 0>; operating-points-v2 = <&cpu0_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -288,7 +288,7 @@ cpu-idle-states = <&BIG_CPU_SLEEP_0 &BIG_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; - dynamic-power-coefficient = <396>; + dynamic-power-coefficient = <442>; qcom,freq-domain = <&cpufreq_hw 1>; operating-points-v2 = <&cpu4_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -310,7 +310,7 @@ cpu-idle-states = <&BIG_CPU_SLEEP_0 &BIG_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; - dynamic-power-coefficient = <396>; + dynamic-power-coefficient = <442>; qcom,freq-domain = <&cpufreq_hw 1>; operating-points-v2 = <&cpu4_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -332,7 +332,7 @@ cpu-idle-states = <&BIG_CPU_SLEEP_0 &BIG_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; - dynamic-power-coefficient = <396>; + dynamic-power-coefficient = <442>; qcom,freq-domain = <&cpufreq_hw 1>; operating-points-v2 = <&cpu4_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -354,7 +354,7 @@ cpu-idle-states = <&BIG_CPU_SLEEP_0 &BIG_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; - dynamic-power-coefficient = <396>; + dynamic-power-coefficient = <442>; qcom,freq-domain = <&cpufreq_hw 1>; operating-points-v2 = <&cpu4_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, From 212352542d72a39b4c3b1b40734f8911fba961b1 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 28 Feb 2023 22:17:37 +0530 Subject: [PATCH 2756/4345] arm64: dts: qcom: sdm845: Fix the PCI I/O port range [ Upstream commit 67aa109eee654c76dcc100554e637fa64d5aa099 ] For 1MiB of the I/O region, the I/O ports of the legacy PCI devices are located in the range of 0x0 to 0x100000. Hence, fix the bogus PCI addresses (0x60200000, 0x40200000) specified in the ranges property for I/O region. While at it, let's use the missing 0x prefix for the addresses. Fixes: 42ad231338c1 ("arm64: dts: qcom: sdm845: Add second PCIe PHY and controller") Fixes: 5c538e09cb19 ("arm64: dts: qcom: sdm845: Add first PCIe controller and PHY") Reported-by: Arnd Bergmann Link: https://lore.kernel.org/linux-arm-msm/7c5dfa87-41df-4ba7-b0e4-72c8386402a8@app.fastmail.com/ Signed-off-by: Manivannan Sadhasivam Reviewed-by: Arnd Bergmann Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230228164752.55682-2-manivannan.sadhasivam@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/sdm845.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 076b6949a0ee..28fbd728304d 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -1816,8 +1816,8 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x01000000 0x0 0x60200000 0 0x60200000 0x0 0x100000>, - <0x02000000 0x0 0x60300000 0 0x60300000 0x0 0xd00000>; + ranges = <0x01000000 0x0 0x00000000 0x0 0x60200000 0x0 0x100000>, + <0x02000000 0x0 0x60300000 0x0 0x60300000 0x0 0xd00000>; interrupts = ; interrupt-names = "msi"; @@ -1920,7 +1920,7 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x01000000 0x0 0x40200000 0x0 0x40200000 0x0 0x100000>, + ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>, <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>; interrupts = ; From 5f6302ab78f4aabec27219c889c5604e4e6a8625 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 28 Feb 2023 22:17:38 +0530 Subject: [PATCH 2757/4345] arm64: dts: qcom: msm8998: Fix the PCI I/O port range [ Upstream commit c30a27dcfe4545edbda1578b3a63ed6147519cdd ] For 1MiB of the I/O region, the I/O ports of the legacy PCI devices are located in the range of 0x0 to 0x100000. Hence, fix the bogus PCI address (0x1b200000) specified in the ranges property for I/O region. Fixes: b84dfd175c09 ("arm64: dts: qcom: msm8998: Add PCIe PHY and RC nodes") Reported-by: Arnd Bergmann Link: https://lore.kernel.org/linux-arm-msm/7c5dfa87-41df-4ba7-b0e4-72c8386402a8@app.fastmail.com/ Signed-off-by: Manivannan Sadhasivam Reviewed-by: Arnd Bergmann Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230228164752.55682-3-manivannan.sadhasivam@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8998.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 0ea4c9e7e180..7c8d69ca91cf 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -942,7 +942,7 @@ phys = <&pciephy>; phy-names = "pciephy"; - ranges = <0x01000000 0x0 0x1b200000 0x1b200000 0x0 0x100000>, + ranges = <0x01000000 0x0 0x00000000 0x1b200000 0x0 0x100000>, <0x02000000 0x0 0x1b300000 0x1b300000 0x0 0xd00000>; #interrupt-cells = <1>; From b6082e8caad886d34f6d0d0bdc2ea21a7b751eb9 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 28 Feb 2023 22:17:41 +0530 Subject: [PATCH 2758/4345] arm64: dts: qcom: ipq8074: Fix the PCI I/O port range [ Upstream commit e49eafefe5ab325e38dd074f2005076ffc271e54 ] For 64KiB of the I/O region, the I/O ports of the legacy PCI devices are located in the range of 0x0 to 0x10000. Hence, fix the bogus PCI addresses (0x10200000, 0x20200000) specified in the ranges property for I/O region. While at it, let's use the missing 0x prefix for the addresses and align them in a single line. Fixes: 33057e1672fe ("ARM: dts: ipq8074: Add pcie nodes") Reported-by: Arnd Bergmann Link: https://lore.kernel.org/linux-arm-msm/7c5dfa87-41df-4ba7-b0e4-72c8386402a8@app.fastmail.com/ Signed-off-by: Manivannan Sadhasivam Reviewed-by: Arnd Bergmann Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230228164752.55682-6-manivannan.sadhasivam@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index e191a7bc532b..f85fcc7c8676 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -609,10 +609,8 @@ phys = <&pcie_phy1>; phy-names = "pciephy"; - ranges = <0x81000000 0 0x10200000 0x10200000 - 0 0x10000>, /* downstream I/O */ - <0x82000000 0 0x10220000 0x10220000 - 0 0xfde0000>; /* non-prefetchable memory */ + ranges = <0x81000000 0x0 0x00000000 0x10200000 0x0 0x10000>, /* I/O */ + <0x82000000 0x0 0x10220000 0x10220000 0x0 0xfde0000>; /* MEM */ interrupts = ; interrupt-names = "msi"; @@ -673,10 +671,8 @@ phys = <&pcie_phy0>; phy-names = "pciephy"; - ranges = <0x81000000 0 0x20200000 0x20200000 - 0 0x10000>, /* downstream I/O */ - <0x82000000 0 0x20220000 0x20220000 - 0 0xfde0000>; /* non-prefetchable memory */ + ranges = <0x81000000 0x0 0x00000000 0x20200000 0x0 0x10000>, /* I/O */ + <0x82000000 0x0 0x20220000 0x20220000 0x0 0xfde0000>; /* MEM */ interrupts = ; interrupt-names = "msi"; From 45855912958f5500f9ea827bf2866bcf2b8fd80c Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 28 Feb 2023 22:17:43 +0530 Subject: [PATCH 2759/4345] arm64: dts: qcom: msm8996: Fix the PCI I/O port range [ Upstream commit cf0ac10feb17661987d0018eb9475dc03e2a2253 ] For 1MiB of the I/O region, the I/O ports of the legacy PCI devices are located in the range of 0x0 to 0x100000. Hence, fix the bogus PCI addresses (0x0c200000, 0x0d200000, 0x0e200000) specified in the ranges property for I/O region. While at it, let's also align the entries. Fixes: ed965ef89227 ("arm64: dts: qcom: msm8996: add support to pcie") Reported-by: Arnd Bergmann Link: https://lore.kernel.org/linux-arm-msm/7c5dfa87-41df-4ba7-b0e4-72c8386402a8@app.fastmail.com/ Signed-off-by: Manivannan Sadhasivam Reviewed-by: Arnd Bergmann Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230228164752.55682-8-manivannan.sadhasivam@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8996.dtsi | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index bc140269e4cc..02b5f6f1d331 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -744,8 +744,8 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x01000000 0x0 0x0c200000 0x0c200000 0x0 0x100000>, - <0x02000000 0x0 0x0c300000 0x0c300000 0x0 0xd00000>; + ranges = <0x01000000 0x0 0x00000000 0x0c200000 0x0 0x100000>, + <0x02000000 0x0 0x0c300000 0x0c300000 0x0 0xd00000>; interrupts = ; interrupt-names = "msi"; @@ -796,8 +796,8 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x01000000 0x0 0x0d200000 0x0d200000 0x0 0x100000>, - <0x02000000 0x0 0x0d300000 0x0d300000 0x0 0xd00000>; + ranges = <0x01000000 0x0 0x00000000 0x0d200000 0x0 0x100000>, + <0x02000000 0x0 0x0d300000 0x0d300000 0x0 0xd00000>; interrupts = ; interrupt-names = "msi"; @@ -845,8 +845,8 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x01000000 0x0 0x0e200000 0x0e200000 0x0 0x100000>, - <0x02000000 0x0 0x0e300000 0x0e300000 0x0 0x1d00000>; + ranges = <0x01000000 0x0 0x00000000 0x0e200000 0x0 0x100000>, + <0x02000000 0x0 0x0e300000 0x0e300000 0x0 0x1d00000>; device_type = "pci"; From 870644bf1bfcc34337eb190a596185e38aa15673 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 28 Feb 2023 22:17:51 +0530 Subject: [PATCH 2760/4345] ARM: dts: qcom: ipq4019: Fix the PCI I/O port range [ Upstream commit 2540279e9a9e74fc880d1e4c83754ecfcbe290a0 ] For 1MiB of the I/O region, the I/O ports of the legacy PCI devices are located in the range of 0x0 to 0x100000. Hence, fix the bogus PCI address (0x40200000) specified in the ranges property for I/O region. While at it, let's use the missing 0x prefix for the addresses. Fixes: 187519403273 ("ARM: dts: ipq4019: Add a few peripheral nodes") Reported-by: Arnd Bergmann Link: https://lore.kernel.org/linux-arm-msm/7c5dfa87-41df-4ba7-b0e4-72c8386402a8@app.fastmail.com/ Signed-off-by: Manivannan Sadhasivam Reviewed-by: Arnd Bergmann Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230228164752.55682-16-manivannan.sadhasivam@linaro.org Signed-off-by: Sasha Levin --- arch/arm/boot/dts/qcom-ipq4019.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/qcom-ipq4019.dtsi b/arch/arm/boot/dts/qcom-ipq4019.dtsi index 3defd47fd8fa..037bb8a9b01e 100644 --- a/arch/arm/boot/dts/qcom-ipq4019.dtsi +++ b/arch/arm/boot/dts/qcom-ipq4019.dtsi @@ -414,8 +414,8 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x81000000 0 0x40200000 0x40200000 0 0x00100000>, - <0x82000000 0 0x40300000 0x40300000 0 0x00d00000>; + ranges = <0x81000000 0x0 0x00000000 0x40200000 0x0 0x00100000>, + <0x82000000 0x0 0x40300000 0x40300000 0x0 0x00d00000>; interrupts = ; interrupt-names = "msi"; From 7d731faebc8efc6b41f3fbad69318ad5f62c963d Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Thu, 7 Jul 2022 03:09:40 +0200 Subject: [PATCH 2761/4345] ARM: dts: qcom: ipq8064: reduce pci IO size to 64K [ Upstream commit 8fafb7e5c041814876266259e5e439f93571dcef ] The current value for pci IO is problematic for ath10k wifi card commonly connected to ipq8064 SoC. The current value is probably a typo and is actually uncommon to find 1MB IO space even on a x86 arch. Also with recent changes to the pci driver, pci1 and pci2 now fails to function as any connected device fails any reg read/write. Reduce this to 64K as it should be more than enough and 3 * 64K of total IO space doesn't exceed the IO_SPACE_LIMIT hardcoded for the ARM arch. Signed-off-by: Christian Marangi Tested-by: Jonathan McDowell Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220707010943.20857-7-ansuelsmth@gmail.com Stable-dep-of: 0b16b34e4916 ("ARM: dts: qcom: ipq8064: Fix the PCI I/O port range") Signed-off-by: Sasha Levin --- arch/arm/boot/dts/qcom-ipq8064.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom-ipq8064.dtsi index c51481405e7f..f7ed87a35e34 100644 --- a/arch/arm/boot/dts/qcom-ipq8064.dtsi +++ b/arch/arm/boot/dts/qcom-ipq8064.dtsi @@ -465,7 +465,7 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x81000000 0 0x0fe00000 0x0fe00000 0 0x00100000 /* downstream I/O */ + ranges = <0x81000000 0 0x0fe00000 0x0fe00000 0 0x00010000 /* downstream I/O */ 0x82000000 0 0x08000000 0x08000000 0 0x07e00000>; /* non-prefetchable memory */ interrupts = ; @@ -516,7 +516,7 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x81000000 0 0x31e00000 0x31e00000 0 0x00100000 /* downstream I/O */ + ranges = <0x81000000 0 0x31e00000 0x31e00000 0 0x00010000 /* downstream I/O */ 0x82000000 0 0x2e000000 0x2e000000 0 0x03e00000>; /* non-prefetchable memory */ interrupts = ; @@ -567,7 +567,7 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x81000000 0 0x35e00000 0x35e00000 0 0x00100000 /* downstream I/O */ + ranges = <0x81000000 0 0x35e00000 0x35e00000 0 0x00010000 /* downstream I/O */ 0x82000000 0 0x32000000 0x32000000 0 0x03e00000>; /* non-prefetchable memory */ interrupts = ; From a8504f9a1304708290c41e2bf659d227d21e04cb Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 28 Feb 2023 22:17:52 +0530 Subject: [PATCH 2762/4345] ARM: dts: qcom: ipq8064: Fix the PCI I/O port range [ Upstream commit 0b16b34e491629016109e56747ad64588074194b ] For 64KiB of the I/O region, the I/O ports of the legacy PCI devices are located in the range of 0x0 to 0x10000. Hence, fix the bogus PCI addresses (0x0fe00000, 0x31e00000, 0x35e00000) specified in the ranges property for I/O region. While at it, let's use the missing 0x prefix for the addresses. Fixes: 93241840b664 ("ARM: dts: qcom: Add pcie nodes for ipq8064") Reported-by: Arnd Bergmann Link: https://lore.kernel.org/linux-arm-msm/7c5dfa87-41df-4ba7-b0e4-72c8386402a8@app.fastmail.com/ Signed-off-by: Manivannan Sadhasivam Reviewed-by: Arnd Bergmann Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230228164752.55682-17-manivannan.sadhasivam@linaro.org Signed-off-by: Sasha Levin --- arch/arm/boot/dts/qcom-ipq8064.dtsi | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/boot/dts/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom-ipq8064.dtsi index f7ed87a35e34..dca0ed6c8c8d 100644 --- a/arch/arm/boot/dts/qcom-ipq8064.dtsi +++ b/arch/arm/boot/dts/qcom-ipq8064.dtsi @@ -465,8 +465,8 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x81000000 0 0x0fe00000 0x0fe00000 0 0x00010000 /* downstream I/O */ - 0x82000000 0 0x08000000 0x08000000 0 0x07e00000>; /* non-prefetchable memory */ + ranges = <0x81000000 0x0 0x00000000 0x0fe00000 0x0 0x00010000 /* I/O */ + 0x82000000 0x0 0x08000000 0x08000000 0x0 0x07e00000>; /* MEM */ interrupts = ; interrupt-names = "msi"; @@ -516,8 +516,8 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x81000000 0 0x31e00000 0x31e00000 0 0x00010000 /* downstream I/O */ - 0x82000000 0 0x2e000000 0x2e000000 0 0x03e00000>; /* non-prefetchable memory */ + ranges = <0x81000000 0x0 0x00000000 0x31e00000 0x0 0x00010000 /* I/O */ + 0x82000000 0x0 0x2e000000 0x2e000000 0x0 0x03e00000>; /* MEM */ interrupts = ; interrupt-names = "msi"; @@ -567,8 +567,8 @@ #address-cells = <3>; #size-cells = <2>; - ranges = <0x81000000 0 0x35e00000 0x35e00000 0 0x00010000 /* downstream I/O */ - 0x82000000 0 0x32000000 0x32000000 0 0x03e00000>; /* non-prefetchable memory */ + ranges = <0x81000000 0x0 0x00000000 0x35e00000 0x0 0x00010000 /* I/O */ + 0x82000000 0x0 0x32000000 0x32000000 0x0 0x03e00000>; /* MEM */ interrupts = ; interrupt-names = "msi"; From a9b9ea0e63a0ec5e97bf1219ab6dcbd55e362f83 Mon Sep 17 00:00:00 2001 From: Muralidhara M K Date: Fri, 27 Jan 2023 15:16:01 +0000 Subject: [PATCH 2763/4345] x86/MCE/AMD: Use an u64 for bank_map [ Upstream commit 4c1cdec319b9aadb65737c3eb1f5cb74bd6aa156 ] Thee maximum number of MCA banks is 64 (MAX_NR_BANKS), see a0bc32b3cacf ("x86/mce: Increase maximum number of banks to 64"). However, the bank_map which contains a bitfield of which banks to initialize is of type unsigned int and that overflows when those bit numbers are >= 32, leading to UBSAN complaining correctly: UBSAN: shift-out-of-bounds in arch/x86/kernel/cpu/mce/amd.c:1365:38 shift exponent 32 is too large for 32-bit type 'int' Change the bank_map to a u64 and use the proper BIT_ULL() macro when modifying bits in there. [ bp: Rewrite commit message. ] Fixes: a0bc32b3cacf ("x86/mce: Increase maximum number of banks to 64") Signed-off-by: Muralidhara M K Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230127151601.1068324-1-muralimk@amd.com Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/mce/amd.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 4f9b7c1cfc36..cd8db6b9ca2f 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -197,10 +197,10 @@ static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); * A list of the banks enabled on each logical CPU. Controls which respective * descriptors to initialize later in mce_threshold_create_device(). */ -static DEFINE_PER_CPU(unsigned int, bank_map); +static DEFINE_PER_CPU(u64, bank_map); /* Map of banks that have more than MCA_MISC0 available. */ -static DEFINE_PER_CPU(u32, smca_misc_banks_map); +static DEFINE_PER_CPU(u64, smca_misc_banks_map); static void amd_threshold_interrupt(void); static void amd_deferred_error_interrupt(void); @@ -229,7 +229,7 @@ static void smca_set_misc_banks_map(unsigned int bank, unsigned int cpu) return; if (low & MASK_BLKPTR_LO) - per_cpu(smca_misc_banks_map, cpu) |= BIT(bank); + per_cpu(smca_misc_banks_map, cpu) |= BIT_ULL(bank); } @@ -492,7 +492,7 @@ static u32 smca_get_block_address(unsigned int bank, unsigned int block, if (!block) return MSR_AMD64_SMCA_MCx_MISC(bank); - if (!(per_cpu(smca_misc_banks_map, cpu) & BIT(bank))) + if (!(per_cpu(smca_misc_banks_map, cpu) & BIT_ULL(bank))) return 0; return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); @@ -536,7 +536,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, int new; if (!block) - per_cpu(bank_map, cpu) |= (1 << bank); + per_cpu(bank_map, cpu) |= BIT_ULL(bank); memset(&b, 0, sizeof(b)); b.cpu = cpu; @@ -1048,7 +1048,7 @@ static void amd_threshold_interrupt(void) return; for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) { - if (!(per_cpu(bank_map, cpu) & (1 << bank))) + if (!(per_cpu(bank_map, cpu) & BIT_ULL(bank))) continue; first_block = bp[bank]->blocks; @@ -1525,7 +1525,7 @@ int mce_threshold_create_device(unsigned int cpu) return -ENOMEM; for (bank = 0; bank < numbanks; ++bank) { - if (!(this_cpu_read(bank_map) & (1 << bank))) + if (!(this_cpu_read(bank_map) & BIT_ULL(bank))) continue; err = threshold_create_bank(bp, cpu, bank); if (err) { From 4362444dca02ab44ac844feda3cf6238ef953673 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 8 Feb 2023 08:14:42 +0100 Subject: [PATCH 2764/4345] media: bdisp: Add missing check for create_workqueue [ Upstream commit 2371adeab717d8fe32144a84f3491a03c5838cfb ] Add the check for the return value of the create_workqueue in order to avoid NULL pointer dereference. Fixes: 28ffeebbb7bd ("[media] bdisp: 2D blitter driver using v4l2 mem2mem framework") Signed-off-by: Jiasheng Jiang Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/platform/sti/bdisp/bdisp-v4l2.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c index 85288da9d2ae..182e5a4aeb17 100644 --- a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c +++ b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c @@ -1310,6 +1310,8 @@ static int bdisp_probe(struct platform_device *pdev) init_waitqueue_head(&bdisp->irq_queue); INIT_DELAYED_WORK(&bdisp->timeout_work, bdisp_irq_timeout); bdisp->work_queue = create_workqueue(BDISP_NAME); + if (!bdisp->work_queue) + return -ENOMEM; spin_lock_init(&bdisp->slock); mutex_init(&bdisp->lock); From 076cdba34de20515372fe2d8b47649e1d0417580 Mon Sep 17 00:00:00 2001 From: Mukesh Ojha Date: Thu, 16 Mar 2023 20:44:26 +0530 Subject: [PATCH 2765/4345] firmware: qcom_scm: Clear download bit during reboot [ Upstream commit 781d32d1c9709fd25655c4e3e3e15370ae4ae4db ] During normal restart of a system download bit should be cleared irrespective of whether download mode is set or not. Fixes: 8c1b7dc9ba22 ("firmware: qcom: scm: Expose download-mode control") Signed-off-by: Mukesh Ojha Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/1678979666-551-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Sasha Levin --- drivers/firmware/qcom_scm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index d417199f8fe9..96086e7df910 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -1256,8 +1256,7 @@ static int qcom_scm_probe(struct platform_device *pdev) static void qcom_scm_shutdown(struct platform_device *pdev) { /* Clean shutdown, disable download mode to allow normal restart */ - if (download_mode) - qcom_scm_set_download_mode(false); + qcom_scm_set_download_mode(false); } static const struct of_device_id qcom_scm_dt_match[] = { From f8d28cecf2100e2fd0677812a1af70f6cf2e10fb Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Sun, 19 Mar 2023 07:55:24 -0500 Subject: [PATCH 2766/4345] drm/bridge: adv7533: Fix adv7533_mode_valid for adv7533 and adv7535 [ Upstream commit ee0285e13455fdbce5de315bdbe91b5f198a2a06 ] When dynamically switching lanes was removed, the intent of the code was to check to make sure that higher speed items used 4 lanes, but it had the unintended consequence of removing the slower speeds for 4-lane users. This attempts to remedy this by doing a check to see that the max frequency doesn't exceed the chip limit, and a second check to make sure that the max bit-rate doesn't exceed the number of lanes * max bit rate / lane. Fixes: 9a0cdcd6649b ("drm/bridge: adv7533: remove dynamic lane switching from adv7533 bridge") Reviewed-by: Robert Foss Signed-off-by: Adam Ford Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230319125524.58803-1-aford173@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/adv7511/adv7533.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/bridge/adv7511/adv7533.c b/drivers/gpu/drm/bridge/adv7511/adv7533.c index f304a5ff8e59..e0bdedf22390 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7533.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7533.c @@ -103,22 +103,19 @@ void adv7533_dsi_power_off(struct adv7511 *adv) enum drm_mode_status adv7533_mode_valid(struct adv7511 *adv, const struct drm_display_mode *mode) { - int lanes; + unsigned long max_lane_freq; struct mipi_dsi_device *dsi = adv->dsi; + u8 bpp = mipi_dsi_pixel_format_to_bpp(dsi->format); - if (mode->clock > 80000) - lanes = 4; - else - lanes = 3; + /* Check max clock for either 7533 or 7535 */ + if (mode->clock > (adv->type == ADV7533 ? 80000 : 148500)) + return MODE_CLOCK_HIGH; - /* - * TODO: add support for dynamic switching of lanes - * by using the bridge pre_enable() op . Till then filter - * out the modes which shall need different number of lanes - * than what was configured in the device tree. - */ - if (lanes != dsi->lanes) - return MODE_BAD; + /* Check max clock for each lane */ + max_lane_freq = (adv->type == ADV7533 ? 800000 : 891000); + + if (mode->clock * bpp > max_lane_freq * adv->num_dsi_lanes) + return MODE_CLOCK_HIGH; return MODE_OK; } From 9a3a907cf69f804eb41ece5c079720d1a6a15aa1 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sat, 14 Jan 2023 22:46:50 +0100 Subject: [PATCH 2767/4345] media: max9286: Free control handler MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit bfce6a12e5ba1edde95126aa06778027f16115d4 ] The control handler is leaked in some probe-time error paths, as well as in the remove path. Fix it. Fixes: 66d8c9d2422d ("media: i2c: Add MAX9286 driver") Signed-off-by: Laurent Pinchart Reviewed-by: Niklas Söderlund Reviewed-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/i2c/max9286.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/i2c/max9286.c b/drivers/media/i2c/max9286.c index 79a11c0184c6..62ce27552dd3 100644 --- a/drivers/media/i2c/max9286.c +++ b/drivers/media/i2c/max9286.c @@ -899,6 +899,7 @@ err_async: static void max9286_v4l2_unregister(struct max9286_priv *priv) { fwnode_handle_put(priv->sd.fwnode); + v4l2_ctrl_handler_free(&priv->ctrls); v4l2_async_unregister_subdev(&priv->sd); max9286_v4l2_notifier_unregister(priv); } From f9ba5962ccfca9f1d6939333141581105a47ff90 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 13 Jun 2022 11:20:30 -0700 Subject: [PATCH 2768/4345] drm/msm/adreno: Defer enabling runpm until hw_init() [ Upstream commit 4b18299b33655fa9672b774b6df774dc03d6aee8 ] To avoid preventing the display from coming up before the rootfs is mounted, without resorting to packing fw in the initrd, the GPU has this limbo state where the device is probed, but we aren't ready to start sending commands to it. This is particularly problematic for a6xx, since the GMU (which requires fw to be loaded) is the one that is controlling the power/clk/icc votes. So defer enabling runpm until we are ready to call gpu->hw_init(), as that is a point where we know we have all the needed fw and are ready to start sending commands to the coproc's. Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/489337/ Link: https://lore.kernel.org/r/20220613182036.2567963-1-robdclark@gmail.com Stable-dep-of: db7662d076c9 ("drm/msm/adreno: drop bogus pm_runtime_set_active()") Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/adreno_device.c | 6 ++++++ drivers/gpu/drm/msm/adreno/adreno_gpu.c | 1 - 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 58e03b20e1c7..c06202b9243c 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -301,6 +301,12 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev) if (ret) return NULL; + /* + * Now that we have firmware loaded, and are ready to begin + * booting the gpu, go ahead and enable runpm: + */ + pm_runtime_enable(&pdev->dev); + /* Make sure pm runtime is active and reset any previous errors */ pm_runtime_set_active(&pdev->dev); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 78181e2d78a9..11a6a41b4910 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -916,7 +916,6 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, pm_runtime_set_autosuspend_delay(dev, adreno_gpu->info->inactive_period); pm_runtime_use_autosuspend(dev); - pm_runtime_enable(dev); ret = msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base, adreno_gpu->info->name, &adreno_gpu_config); From 00f02bb8cb053997f48ffe7f71b92d674be4676d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 3 Mar 2023 17:48:06 +0100 Subject: [PATCH 2769/4345] drm/msm/adreno: drop bogus pm_runtime_set_active() [ Upstream commit db7662d076c973072d788bd0e8130e04430307a1 ] The runtime PM status can only be updated while runtime PM is disabled. Drop the bogus pm_runtime_set_active() call that was made after enabling runtime PM and which (incidentally but correctly) left the runtime PM status set to 'suspended'. Fixes: 2c087a336676 ("drm/msm/adreno: Load the firmware before bringing up the hardware") Signed-off-by: Johan Hovold Patchwork: https://patchwork.freedesktop.org/patch/524972/ Link: https://lore.kernel.org/r/20230303164807.13124-4-johan+linaro@kernel.org Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/adreno_device.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index c06202b9243c..760687f66ae5 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -307,9 +307,6 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev) */ pm_runtime_enable(&pdev->dev); - /* Make sure pm runtime is active and reset any previous errors */ - pm_runtime_set_active(&pdev->dev); - ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) { pm_runtime_put_sync(&pdev->dev); From f59421334e9448c46a11195c93e8c139430ed321 Mon Sep 17 00:00:00 2001 From: Georgii Kruglov Date: Tue, 21 Mar 2023 23:37:15 +0300 Subject: [PATCH 2770/4345] mmc: sdhci-of-esdhc: fix quirk to ignore command inhibit for data [ Upstream commit 0dd8316037a2a6d85b2be208bef9991de7b42170 ] If spec_reg is equal to 'SDHCI_PRESENT_STATE', esdhc_readl_fixup() fixes up register value and returns it immediately. As a result, the further block (spec_reg == SDHCI_PRESENT_STATE) &&(esdhc->quirk_ignore_data_inhibit == true), is never executed. The patch merges the second block into the first one. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 1f1929f3f2fa ("mmc: sdhci-of-esdhc: add quirk to ignore command inhibit for data") Signed-off-by: Georgii Kruglov Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20230321203715.3975-1-georgy.kruglov@yandex.ru Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/sdhci-of-esdhc.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index d53374991e13..5b853f651b38 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -126,6 +126,7 @@ static u32 esdhc_readl_fixup(struct sdhci_host *host, return ret; } } + /* * The DAT[3:0] line signal levels and the CMD line signal level are * not compatible with standard SDHC register. The line signal levels @@ -137,6 +138,16 @@ static u32 esdhc_readl_fixup(struct sdhci_host *host, ret = value & 0x000fffff; ret |= (value >> 4) & SDHCI_DATA_LVL_MASK; ret |= (value << 1) & SDHCI_CMD_LVL; + + /* + * Some controllers have unreliable Data Line Active + * bit for commands with busy signal. This affects + * Command Inhibit (data) bit. Just ignore it since + * MMC core driver has already polled card status + * with CMD13 after any command with busy siganl. + */ + if (esdhc->quirk_ignore_data_inhibit) + ret &= ~SDHCI_DATA_INHIBIT; return ret; } @@ -151,19 +162,6 @@ static u32 esdhc_readl_fixup(struct sdhci_host *host, return ret; } - /* - * Some controllers have unreliable Data Line Active - * bit for commands with busy signal. This affects - * Command Inhibit (data) bit. Just ignore it since - * MMC core driver has already polled card status - * with CMD13 after any command with busy siganl. - */ - if ((spec_reg == SDHCI_PRESENT_STATE) && - (esdhc->quirk_ignore_data_inhibit == true)) { - ret = value & ~SDHCI_DATA_INHIBIT; - return ret; - } - ret = value; return ret; } From 0fc1a90bcef75f9b65f6476670c35ce232e27990 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Fri, 13 Jan 2023 22:11:51 +0100 Subject: [PATCH 2771/4345] ARM: dts: gta04: fix excess dma channel usage [ Upstream commit a622310f7f0185da02e42cdb06475f533efaae60 ] OMAP processors support 32 channels but there is no check or inspect this except booting a device and looking at dmesg reports of not available channels. Recently some more subsystems with DMA (aes1+2) were added filling the list of dma channels beyond the limit of 32 (even if other parameters indicate 96 or 128 channels). This leads to random subsystem failures i(e.g. mcbsp for audio) after boot or boot messages that DMA can not be initialized. Another symptom is that /sys/kernel/debug/dmaengine/summary has 32 entries and does not show all required channels. Fix by disabling unused (on the GTA04 hardware) mcspi1...4. Each SPI channel allocates 4 DMA channels rapidly filling the available ones. Disabling unused SPI modules on the OMAP3 SoC may also save some energy (has not been checked). Fixes: c312f066314e ("ARM: dts: omap3: Migrate AES from hwmods to sysc-omap2") Signed-off-by: H. Nikolaus Schaller [re-enabled aes2, improved commit subject line] Signed-off-by: Andreas Kemnade Message-Id: <20230113211151.2314874-1-andreas@kemnade.info> Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- arch/arm/boot/dts/omap3-gta04.dtsi | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index cc8a378dd076..e61e5ddbf202 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -609,6 +609,22 @@ clock-frequency = <100000>; }; +&mcspi1 { + status = "disabled"; +}; + +&mcspi2 { + status = "disabled"; +}; + +&mcspi3 { + status = "disabled"; +}; + +&mcspi4 { + status = "disabled"; +}; + &usb_otg_hs { interface-type = <0>; usb-phy = <&usb2_phy>; From e21c93b20a864c1624e3367a5abbc00f43e843e5 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Mon, 13 Mar 2023 22:27:11 -0700 Subject: [PATCH 2772/4345] drm/lima/lima_drv: Add missing unwind goto in lima_pdev_probe() [ Upstream commit c5647cae2704e58d1c4e5fedbf63f11bca6376c9 ] Smatch reports: drivers/gpu/drm/lima/lima_drv.c:396 lima_pdev_probe() warn: missing unwind goto? Store return value in err and goto 'err_out0' which has lima_sched_slab_fini() before returning. Fixes: a1d2a6339961 ("drm/lima: driver for ARM Mali4xx GPUs") Signed-off-by: Harshit Mogalapalli Signed-off-by: Qiang Yu Link: https://patchwork.freedesktop.org/patch/msgid/20230314052711.4061652-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/lima/lima_drv.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/lima/lima_drv.c b/drivers/gpu/drm/lima/lima_drv.c index ab460121fd52..65dc0dc2c119 100644 --- a/drivers/gpu/drm/lima/lima_drv.c +++ b/drivers/gpu/drm/lima/lima_drv.c @@ -392,8 +392,10 @@ static int lima_pdev_probe(struct platform_device *pdev) /* Allocate and initialize the DRM device. */ ddev = drm_dev_alloc(&lima_drm_driver, &pdev->dev); - if (IS_ERR(ddev)) - return PTR_ERR(ddev); + if (IS_ERR(ddev)) { + err = PTR_ERR(ddev); + goto err_out0; + } ddev->dev_private = ldev; ldev->ddev = ddev; From 4c0b98d87c3e0c1ba02c797cc83450938a6deaf5 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Wed, 29 Mar 2023 14:33:53 -0700 Subject: [PATCH 2773/4345] regulator: core: Consistently set mutex_owner when using ww_mutex_lock_slow() [ Upstream commit b83a1772be854f87602de14726737d3e5b06e1f4 ] When a codepath locks a rdev using ww_mutex_lock_slow() directly then that codepath is responsible for incrementing the "ref_cnt" and also setting the "mutex_owner" to "current". The regulator core consistently got that right for "ref_cnt" but didn't always get it right for "mutex_owner". Let's fix this. It's unlikely that this truly matters because the "mutex_owner" is only needed if we're going to do subsequent locking of the same rdev. However, even though it's not truly needed it seems less surprising if we consistently set "mutex_owner" properly. Fixes: f8702f9e4aa7 ("regulator: core: Use ww_mutex for regulators locking") Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20230329143317.RFC.v2.1.I4e9d433ea26360c06dd1381d091c82bb1a4ce843@changeid Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 6dd698b2d0af..bd2a3f44dd6e 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -343,6 +343,7 @@ static void regulator_lock_dependent(struct regulator_dev *rdev, ww_mutex_lock_slow(&new_contended_rdev->mutex, ww_ctx); old_contended_rdev = new_contended_rdev; old_contended_rdev->ref_cnt++; + old_contended_rdev->mutex_owner = current; } err = regulator_lock_recursive(rdev, @@ -5800,6 +5801,7 @@ static void regulator_summary_lock(struct ww_acquire_ctx *ww_ctx) ww_mutex_lock_slow(&new_contended_rdev->mutex, ww_ctx); old_contended_rdev = new_contended_rdev; old_contended_rdev->ref_cnt++; + old_contended_rdev->mutex_owner = current; } err = regulator_summary_lock_all(ww_ctx, From ee22417f829934841b08c351eb2f7ca6ae76a512 Mon Sep 17 00:00:00 2001 From: Adam Skladowski Date: Tue, 14 Mar 2023 23:17:17 +0100 Subject: [PATCH 2774/4345] drm: msm: adreno: Disable preemption on Adreno 510 [ Upstream commit 010c8bbad2cb8c33c47963e29f051f1e917e45a5 ] Downstream driver appears to not support preemption on A510 target, trying to use one make device slow and fill log with rings related errors. Set num_rings to 1 to disable preemption. Suggested-by: Dmitry Baryshkov Fixes: e20c9284c8f2 ("drm/msm/adreno: Add support for Adreno 510 GPU") Signed-off-by: Adam Skladowski Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/526898/ Link: https://lore.kernel.org/r/20230314221757.13096-1-a39.skl@gmail.com Signed-off-by: Rob Clark Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 6f84db97e20e..0fcba2bc26b8 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1569,6 +1569,7 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) struct a5xx_gpu *a5xx_gpu = NULL; struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; + unsigned int nr_rings; int ret; if (!pdev) { @@ -1589,7 +1590,12 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) check_speed_bin(&pdev->dev); - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4); + nr_rings = 4; + + if (adreno_is_a510(adreno_gpu)) + nr_rings = 1; + + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, nr_rings); if (ret) { a5xx_destroy(&(a5xx_gpu->base.base)); return ERR_PTR(ret); From 06140d6dfe720d80566f792b4e28a9cd60a67970 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Wed, 29 Mar 2023 14:33:54 -0700 Subject: [PATCH 2775/4345] regulator: core: Avoid lockdep reports when resolving supplies [ Upstream commit cba6cfdc7c3f1516f0d08ddfb24e689af0932573 ] An automated bot told me that there was a potential lockdep problem with regulators. This was on the chromeos-5.15 kernel, but I see nothing that would be different downstream compared to upstream. The bot said: ============================================ WARNING: possible recursive locking detected 5.15.104-lockdep-17461-gc1e499ed6604 #1 Not tainted -------------------------------------------- kworker/u16:4/115 is trying to acquire lock: ffffff8083110170 (regulator_ww_class_mutex){+.+.}-{3:3}, at: create_regulator+0x398/0x7ec but task is already holding lock: ffffff808378e170 (regulator_ww_class_mutex){+.+.}-{3:3}, at: ww_mutex_trylock+0x3c/0x7b8 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(regulator_ww_class_mutex); lock(regulator_ww_class_mutex); *** DEADLOCK *** May be due to missing lock nesting notation 4 locks held by kworker/u16:4/115: #0: ffffff808006a948 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work+0x520/0x1348 #1: ffffffc00e0a7cc0 ((work_completion)(&entry->work)){+.+.}-{0:0}, at: process_one_work+0x55c/0x1348 #2: ffffff80828a2260 (&dev->mutex){....}-{3:3}, at: __device_attach_async_helper+0xd0/0x2a4 #3: ffffff808378e170 (regulator_ww_class_mutex){+.+.}-{3:3}, at: ww_mutex_trylock+0x3c/0x7b8 stack backtrace: CPU: 2 PID: 115 Comm: kworker/u16:4 Not tainted 5.15.104-lockdep-17461-gc1e499ed6604 #1 9292e52fa83c0e23762b2b3aa1bacf5787a4d5da Hardware name: Google Quackingstick (rev0+) (DT) Workqueue: events_unbound async_run_entry_fn Call trace: dump_backtrace+0x0/0x4ec show_stack+0x34/0x50 dump_stack_lvl+0xdc/0x11c dump_stack+0x1c/0x48 __lock_acquire+0x16d4/0x6c74 lock_acquire+0x208/0x750 __mutex_lock_common+0x11c/0x11f8 ww_mutex_lock+0xc0/0x440 create_regulator+0x398/0x7ec regulator_resolve_supply+0x654/0x7c4 regulator_register_resolve_supply+0x30/0x120 class_for_each_device+0x1b8/0x230 regulator_register+0x17a4/0x1f40 devm_regulator_register+0x60/0xd0 reg_fixed_voltage_probe+0x728/0xaec platform_probe+0x150/0x1c8 really_probe+0x274/0xa20 __driver_probe_device+0x1dc/0x3f4 driver_probe_device+0x78/0x1c0 __device_attach_driver+0x1ac/0x2c8 bus_for_each_drv+0x11c/0x190 __device_attach_async_helper+0x1e4/0x2a4 async_run_entry_fn+0xa0/0x3ac process_one_work+0x638/0x1348 worker_thread+0x4a8/0x9c4 kthread+0x2e4/0x3a0 ret_from_fork+0x10/0x20 The problem was first reported soon after we made many of the regulators probe asynchronously, though nothing I've seen implies that the problems couldn't have also happened even without that. I haven't personally been able to reproduce the lockdep issue, but the issue does look somewhat legitimate. Specifically, it looks like in regulator_resolve_supply() we are holding a "rdev" lock while calling set_supply() -> create_regulator() which grabs the lock of a _different_ "rdev" (the one for our supply). This is not necessarily safe from a lockdep perspective since there is no documented ordering between these two locks. In reality, we should always be locking a regulator before the supplying regulator, so I don't expect there to be any real deadlocks in practice. However, the regulator framework in general doesn't express this to lockdep. Let's fix the issue by simply grabbing the two locks involved in the same way we grab multiple locks elsewhere in the regulator framework: using the "wound/wait" mechanisms. Fixes: eaa7995c529b ("regulator: core: avoid regulator_resolve_supply() race condition") Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20230329143317.RFC.v2.2.I30d8e1ca10cfbe5403884cdd192253a2e063eb9e@changeid Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 91 ++++++++++++++++++++++++++++++++++++---- 1 file changed, 83 insertions(+), 8 deletions(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index bd2a3f44dd6e..47a04c5f7a9b 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -216,6 +216,78 @@ static void regulator_unlock(struct regulator_dev *rdev) mutex_unlock(®ulator_nesting_mutex); } +/** + * regulator_lock_two - lock two regulators + * @rdev1: first regulator + * @rdev2: second regulator + * @ww_ctx: w/w mutex acquire context + * + * Locks both rdevs using the regulator_ww_class. + */ +static void regulator_lock_two(struct regulator_dev *rdev1, + struct regulator_dev *rdev2, + struct ww_acquire_ctx *ww_ctx) +{ + struct regulator_dev *tmp; + int ret; + + ww_acquire_init(ww_ctx, ®ulator_ww_class); + + /* Try to just grab both of them */ + ret = regulator_lock_nested(rdev1, ww_ctx); + WARN_ON(ret); + ret = regulator_lock_nested(rdev2, ww_ctx); + if (ret != -EDEADLOCK) { + WARN_ON(ret); + goto exit; + } + + while (true) { + /* + * Start of loop: rdev1 was locked and rdev2 was contended. + * Need to unlock rdev1, slowly lock rdev2, then try rdev1 + * again. + */ + regulator_unlock(rdev1); + + ww_mutex_lock_slow(&rdev2->mutex, ww_ctx); + rdev2->ref_cnt++; + rdev2->mutex_owner = current; + ret = regulator_lock_nested(rdev1, ww_ctx); + + if (ret == -EDEADLOCK) { + /* More contention; swap which needs to be slow */ + tmp = rdev1; + rdev1 = rdev2; + rdev2 = tmp; + } else { + WARN_ON(ret); + break; + } + } + +exit: + ww_acquire_done(ww_ctx); +} + +/** + * regulator_unlock_two - unlock two regulators + * @rdev1: first regulator + * @rdev2: second regulator + * @ww_ctx: w/w mutex acquire context + * + * The inverse of regulator_lock_two(). + */ + +static void regulator_unlock_two(struct regulator_dev *rdev1, + struct regulator_dev *rdev2, + struct ww_acquire_ctx *ww_ctx) +{ + regulator_unlock(rdev2); + regulator_unlock(rdev1); + ww_acquire_fini(ww_ctx); +} + static bool regulator_supply_is_couple(struct regulator_dev *rdev) { struct regulator_dev *c_rdev; @@ -1460,8 +1532,8 @@ static int set_machine_constraints(struct regulator_dev *rdev) /** * set_supply - set regulator supply regulator - * @rdev: regulator name - * @supply_rdev: supply regulator name + * @rdev: regulator (locked) + * @supply_rdev: supply regulator (locked)) * * Called by platform initialisation code to set the supply regulator for this * regulator. This ensures that a regulators supply will also be enabled by the @@ -1633,6 +1705,8 @@ static struct regulator *create_regulator(struct regulator_dev *rdev, struct regulator *regulator; int err = 0; + lockdep_assert_held_once(&rdev->mutex.base); + if (dev) { char buf[REG_STR_SIZE]; int size; @@ -1660,9 +1734,7 @@ static struct regulator *create_regulator(struct regulator_dev *rdev, regulator->rdev = rdev; regulator->supply_name = supply_name; - regulator_lock(rdev); list_add(®ulator->list, &rdev->consumer_list); - regulator_unlock(rdev); if (dev) { regulator->dev = dev; @@ -1828,6 +1900,7 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) { struct regulator_dev *r; struct device *dev = rdev->dev.parent; + struct ww_acquire_ctx ww_ctx; int ret = 0; /* No supply to resolve? */ @@ -1894,23 +1967,23 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) * between rdev->supply null check and setting rdev->supply in * set_supply() from concurrent tasks. */ - regulator_lock(rdev); + regulator_lock_two(rdev, r, &ww_ctx); /* Supply just resolved by a concurrent task? */ if (rdev->supply) { - regulator_unlock(rdev); + regulator_unlock_two(rdev, r, &ww_ctx); put_device(&r->dev); goto out; } ret = set_supply(rdev, r); if (ret < 0) { - regulator_unlock(rdev); + regulator_unlock_two(rdev, r, &ww_ctx); put_device(&r->dev); goto out; } - regulator_unlock(rdev); + regulator_unlock_two(rdev, r, &ww_ctx); /* * In set_machine_constraints() we may have turned this regulator on @@ -2023,7 +2096,9 @@ struct regulator *_regulator_get(struct device *dev, const char *id, return regulator; } + regulator_lock(rdev); regulator = create_regulator(rdev, dev, id); + regulator_unlock(rdev); if (regulator == NULL) { regulator = ERR_PTR(-ENOMEM); module_put(rdev->owner); From 1487b29030bae2eed159a813d5ae8f540d5eabd9 Mon Sep 17 00:00:00 2001 From: Roger Pau Monne Date: Wed, 22 Mar 2023 12:13:29 +0100 Subject: [PATCH 2776/4345] ACPI: processor: Fix evaluating _PDC method when running as Xen dom0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 073828e954459b883f23e53999d31e4c55ab9654 ] In ACPI systems, the OS can direct power management, as opposed to the firmware. This OS-directed Power Management is called OSPM. Part of telling the firmware that the OS going to direct power management is making ACPI "_PDC" (Processor Driver Capabilities) calls. These _PDC methods must be evaluated for every processor object. If these _PDC calls are not completed for every processor it can lead to inconsistency and later failures in things like the CPU frequency driver. In a Xen system, the dom0 kernel is responsible for system-wide power management. The dom0 kernel is in charge of OSPM. However, the number of CPUs available to dom0 can be different than the number of CPUs physically present on the system. This leads to a problem: the dom0 kernel needs to evaluate _PDC for all the processors, but it can't always see them. In dom0 kernels, ignore the existing ACPI method for determining if a processor is physically present because it might not be accurate. Instead, ask the hypervisor for this information. Fix this by introducing a custom function to use when running as Xen dom0 in order to check whether a processor object matches a CPU that's online. Such checking is done using the existing information fetched by the Xen pCPU subsystem, extending it to also store the ACPI ID. This ensures that _PDC method gets evaluated for all physically online CPUs, regardless of the number of CPUs made available to dom0. Fixes: 5d554a7bb064 ("ACPI: processor: add internal processor_physically_present()") Signed-off-by: Roger Pau Monné Reviewed-by: Juergen Gross Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/processor_pdc.c | 11 +++++++++++ drivers/xen/pcpu.c | 20 ++++++++++++++++++++ include/xen/xen.h | 11 +++++++++++ 3 files changed, 42 insertions(+) diff --git a/drivers/acpi/processor_pdc.c b/drivers/acpi/processor_pdc.c index 813f1b78c16a..c0d2d9a2c0d5 100644 --- a/drivers/acpi/processor_pdc.c +++ b/drivers/acpi/processor_pdc.c @@ -14,6 +14,8 @@ #include #include +#include + #include "internal.h" #define _COMPONENT ACPI_PROCESSOR_COMPONENT @@ -50,6 +52,15 @@ static bool __init processor_physically_present(acpi_handle handle) return false; } + if (xen_initial_domain()) + /* + * When running as a Xen dom0 the number of processors Linux + * sees can be different from the real number of processors on + * the system, and we still need to execute _PDC for all of + * them. + */ + return xen_processor_present(acpi_id); + type = (acpi_type == ACPI_TYPE_DEVICE) ? 1 : 0; cpuid = acpi_get_cpuid(handle, type, acpi_id); diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index 9cf7085a260b..4581217e31fe 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -58,6 +58,7 @@ struct pcpu { struct list_head list; struct device dev; uint32_t cpu_id; + uint32_t acpi_id; uint32_t flags; }; @@ -249,6 +250,7 @@ static struct pcpu *create_and_register_pcpu(struct xenpf_pcpuinfo *info) INIT_LIST_HEAD(&pcpu->list); pcpu->cpu_id = info->xen_cpuid; + pcpu->acpi_id = info->acpi_id; pcpu->flags = info->flags; /* Need hold on xen_pcpu_lock before pcpu list manipulations */ @@ -416,3 +418,21 @@ err1: return ret; } arch_initcall(xen_pcpu_init); + +#ifdef CONFIG_ACPI +bool __init xen_processor_present(uint32_t acpi_id) +{ + const struct pcpu *pcpu; + bool online = false; + + mutex_lock(&xen_pcpu_lock); + list_for_each_entry(pcpu, &xen_pcpus, list) + if (pcpu->acpi_id == acpi_id) { + online = pcpu->flags & XEN_PCPU_FLAGS_ONLINE; + break; + } + mutex_unlock(&xen_pcpu_lock); + + return online; +} +#endif diff --git a/include/xen/xen.h b/include/xen/xen.h index 43efba045acc..5a6a2ab675be 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -61,4 +61,15 @@ void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages); #include #endif +#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI) && defined(CONFIG_X86) +bool __init xen_processor_present(uint32_t acpi_id); +#else +#include +static inline bool xen_processor_present(uint32_t acpi_id) +{ + BUG(); + return false; +} +#endif + #endif /* _XEN_XEN_H */ From 4883f0f7ee448de1e15814497f21177481d03447 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 27 Feb 2023 17:09:17 +0100 Subject: [PATCH 2777/4345] x86/apic: Fix atomic update of offset in reserve_eilvt_offset() [ Upstream commit f96fb2df3eb31ede1b34b0521560967310267750 ] The detection of atomic update failure in reserve_eilvt_offset() is not correct. The value returned by atomic_cmpxchg() should be compared to the old value from the location to be updated. If these two are the same, then atomic update succeeded and "eilvt_offsets[offset]" location is updated to "new" in an atomic way. Otherwise, the atomic update failed and it should be retried with the value from "eilvt_offsets[offset]" - exactly what atomic_try_cmpxchg() does in a correct and more optimal way. Fixes: a68c439b1966c ("apic, x86: Check if EILVT APIC registers are available (AMD only)") Signed-off-by: Uros Bizjak Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230227160917.107820-1-ubizjak@gmail.com Signed-off-by: Sasha Levin --- arch/x86/kernel/apic/apic.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 1c96f2425eaf..25eb69f26e03 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -410,10 +410,9 @@ static unsigned int reserve_eilvt_offset(int offset, unsigned int new) if (vector && !eilvt_entry_is_changeable(vector, new)) /* may not change if vectors are different */ return rsvd; - rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new); - } while (rsvd != new); + } while (!atomic_try_cmpxchg(&eilvt_offsets[offset], &rsvd, new)); - rsvd &= ~APIC_EILVT_MASKED; + rsvd = new & ~APIC_EILVT_MASKED; if (rsvd && rsvd != vector) pr_info("LVT offset %d assigned for vector 0x%02x\n", offset, rsvd); From de19d02d734ef29f5dbd2c12fe810fa960ecd83f Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Mon, 13 Mar 2023 16:42:20 +0000 Subject: [PATCH 2778/4345] media: rkvdec: fix use after free bug in rkvdec_remove [ Upstream commit 3228cec23b8b29215e18090c6ba635840190993d ] In rkvdec_probe, rkvdec->watchdog_work is bound with rkvdec_watchdog_func. Then rkvdec_vp9_run may be called to start the work. If we remove the module which will call rkvdec_remove to make cleanup, there may be a unfinished work. The possible sequence is as follows, which will cause a typical UAF bug. Fix it by canceling the work before cleanup in rkvdec_remove. CPU0 CPU1 |rkvdec_watchdog_func rkvdec_remove | rkvdec_v4l2_cleanup| v4l2_m2m_release | kfree(m2m_dev); | | | v4l2_m2m_get_curr_priv | m2m_dev->curr_ctx //use Fixes: cd33c830448b ("media: rkvdec: Add the rkvdec driver") Signed-off-by: Zheng Wang Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/staging/media/rkvdec/rkvdec.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c index e384ea8d7280..f6a29a707862 100644 --- a/drivers/staging/media/rkvdec/rkvdec.c +++ b/drivers/staging/media/rkvdec/rkvdec.c @@ -1077,6 +1077,8 @@ static int rkvdec_remove(struct platform_device *pdev) { struct rkvdec_dev *rkvdec = platform_get_drvdata(pdev); + cancel_delayed_work_sync(&rkvdec->watchdog_work); + rkvdec_v4l2_cleanup(rkvdec); pm_runtime_disable(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); From e9d64e90a0ada4d00ac6562e351ef10ae7d9b911 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Sat, 18 Mar 2023 16:15:06 +0800 Subject: [PATCH 2779/4345] media: dm1105: Fix use after free bug in dm1105_remove due to race condition [ Upstream commit 5abda7a16698d4d1f47af1168d8fa2c640116b4a ] In dm1105_probe, it called dm1105_ir_init and bound &dm1105->ir.work with dm1105_emit_key. When it handles IRQ request with dm1105_irq, it may call schedule_work to start the work. When we call dm1105_remove to remove the driver, there may be a sequence as follows: Fix it by finishing the work before cleanup in dm1105_remove CPU0 CPU1 |dm1105_emit_key dm1105_remove | dm1105_ir_exit | rc_unregister_device | rc_free_device | rc_dev_release | kfree(dev); | | | rc_keydown | //use Fixes: 34d2f9bf189c ("V4L/DVB: dm1105: use dm1105_dev & dev instead of dm1105dvb") Signed-off-by: Zheng Wang Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/pci/dm1105/dm1105.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/pci/dm1105/dm1105.c b/drivers/media/pci/dm1105/dm1105.c index 9dce31d2b525..d2e194a24e7e 100644 --- a/drivers/media/pci/dm1105/dm1105.c +++ b/drivers/media/pci/dm1105/dm1105.c @@ -1178,6 +1178,7 @@ static void dm1105_remove(struct pci_dev *pdev) struct dvb_demux *dvbdemux = &dev->demux; struct dmx_demux *dmx = &dvbdemux->dmx; + cancel_work_sync(&dev->ir.work); dm1105_ir_exit(dev); dmx->close(dmx); dvb_net_release(&dev->dvbnet); From 7dac96e9cc985328ec1fae92f0c245f559dc0e11 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Sat, 18 Mar 2023 16:50:23 +0800 Subject: [PATCH 2780/4345] media: saa7134: fix use after free bug in saa7134_finidev due to race condition [ Upstream commit 30cf57da176cca80f11df0d9b7f71581fe601389 ] In saa7134_initdev, it will call saa7134_hwinit1. There are three function invoking here: saa7134_video_init1, saa7134_ts_init1 and saa7134_vbi_init1. All of them will init a timer with same function. Take saa7134_video_init1 as an example. It'll bound &dev->video_q.timeout with saa7134_buffer_timeout. In buffer_activate, the timer funtcion is started. If we remove the module or device which will call saa7134_finidev to make cleanup, there may be a unfinished work. The possible sequence is as follows, which will cause a typical UAF bug. Fix it by canceling the timer works accordingly before cleanup in saa7134_finidev. CPU0 CPU1 |saa7134_buffer_timeout saa7134_finidev | kfree(dev); | | | saa7134_buffer_next | //use dev Fixes: 1e7126b4a86a ("media: saa7134: Convert timers to use timer_setup()") Signed-off-by: Zheng Wang Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/pci/saa7134/saa7134-ts.c | 1 + drivers/media/pci/saa7134/saa7134-vbi.c | 1 + drivers/media/pci/saa7134/saa7134-video.c | 1 + 3 files changed, 3 insertions(+) diff --git a/drivers/media/pci/saa7134/saa7134-ts.c b/drivers/media/pci/saa7134/saa7134-ts.c index 6a5053126237..437dbe5e75e2 100644 --- a/drivers/media/pci/saa7134/saa7134-ts.c +++ b/drivers/media/pci/saa7134/saa7134-ts.c @@ -300,6 +300,7 @@ int saa7134_ts_start(struct saa7134_dev *dev) int saa7134_ts_fini(struct saa7134_dev *dev) { + del_timer_sync(&dev->ts_q.timeout); saa7134_pgtable_free(dev->pci, &dev->ts_q.pt); return 0; } diff --git a/drivers/media/pci/saa7134/saa7134-vbi.c b/drivers/media/pci/saa7134/saa7134-vbi.c index 3f0b0933eed6..3e773690468b 100644 --- a/drivers/media/pci/saa7134/saa7134-vbi.c +++ b/drivers/media/pci/saa7134/saa7134-vbi.c @@ -185,6 +185,7 @@ int saa7134_vbi_init1(struct saa7134_dev *dev) int saa7134_vbi_fini(struct saa7134_dev *dev) { /* nothing */ + del_timer_sync(&dev->vbi_q.timeout); return 0; } diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c index 85d082baaadc..df9e3293015a 100644 --- a/drivers/media/pci/saa7134/saa7134-video.c +++ b/drivers/media/pci/saa7134/saa7134-video.c @@ -2153,6 +2153,7 @@ int saa7134_video_init1(struct saa7134_dev *dev) void saa7134_video_fini(struct saa7134_dev *dev) { + del_timer_sync(&dev->video_q.timeout); /* free stuff */ saa7134_pgtable_free(dev->pci, &dev->video_q.pt); saa7134_pgtable_free(dev->pci, &dev->vbi_q.pt); From 21de9d0daab1a98635bfd2b2afb9abe346691d18 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 23 Apr 2021 16:59:34 +0200 Subject: [PATCH 2781/4345] media: rcar_fdp1: simplify error check logic at fdp_open() [ Upstream commit fa9f443f7c962d072d150472e2bb77de39817a9a ] Avoid some code duplication by moving the common error path logic at fdp_open(). Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: c766c90faf93 ("media: rcar_fdp1: Fix refcount leak in probe and remove function") Signed-off-by: Sasha Levin --- drivers/media/platform/rcar_fdp1.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c index c9448de885b6..ac2e7b2c6082 100644 --- a/drivers/media/platform/rcar_fdp1.c +++ b/drivers/media/platform/rcar_fdp1.c @@ -2121,9 +2121,7 @@ static int fdp1_open(struct file *file) if (ctx->hdl.error) { ret = ctx->hdl.error; - v4l2_ctrl_handler_free(&ctx->hdl); - kfree(ctx); - goto done; + goto error_ctx; } ctx->fh.ctrl_handler = &ctx->hdl; @@ -2137,10 +2135,7 @@ static int fdp1_open(struct file *file) if (IS_ERR(ctx->fh.m2m_ctx)) { ret = PTR_ERR(ctx->fh.m2m_ctx); - - v4l2_ctrl_handler_free(&ctx->hdl); - kfree(ctx); - goto done; + goto error_ctx; } /* Perform any power management required */ @@ -2151,6 +2146,12 @@ static int fdp1_open(struct file *file) dprintk(fdp1, "Created instance: %p, m2m_ctx: %p\n", ctx, ctx->fh.m2m_ctx); + mutex_unlock(&fdp1->dev_mutex); + return 0; + +error_ctx: + v4l2_ctrl_handler_free(&ctx->hdl); + kfree(ctx); done: mutex_unlock(&fdp1->dev_mutex); return ret; From bf91fb6c1e9d20d965654f9b13cb23f22559ef12 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 23 Apr 2021 16:59:34 +0200 Subject: [PATCH 2782/4345] media: rcar_fdp1: fix pm_runtime_get_sync() usage count [ Upstream commit 45e75a8c6fa455a5909ac04db76a4b15d6bb8368 ] The pm_runtime_get_sync() internally increments the dev->power.usage_count without decrementing it, even on errors. Replace it by the new pm_runtime_resume_and_get(), introduced by: commit dd8088d5a896 ("PM: runtime: Add pm_runtime_resume_and_get to deal with usage counter") in order to properly decrement the usage counter, avoiding a potential PM usage counter leak. Also, right now, the driver is ignoring any troubles when trying to do PM resume. So, add the proper error handling for the code. Reviewed-by: Jonathan Cameron Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: c766c90faf93 ("media: rcar_fdp1: Fix refcount leak in probe and remove function") Signed-off-by: Sasha Levin --- drivers/media/platform/rcar_fdp1.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c index ac2e7b2c6082..cedae184c6ad 100644 --- a/drivers/media/platform/rcar_fdp1.c +++ b/drivers/media/platform/rcar_fdp1.c @@ -2139,7 +2139,9 @@ static int fdp1_open(struct file *file) } /* Perform any power management required */ - pm_runtime_get_sync(fdp1->dev); + ret = pm_runtime_resume_and_get(fdp1->dev); + if (ret < 0) + goto error_pm; v4l2_fh_add(&ctx->fh); @@ -2149,6 +2151,8 @@ static int fdp1_open(struct file *file) mutex_unlock(&fdp1->dev_mutex); return 0; +error_pm: + v4l2_m2m_ctx_release(ctx->fh.m2m_ctx); error_ctx: v4l2_ctrl_handler_free(&ctx->hdl); kfree(ctx); @@ -2356,7 +2360,9 @@ static int fdp1_probe(struct platform_device *pdev) /* Power up the cells to read HW */ pm_runtime_enable(&pdev->dev); - pm_runtime_get_sync(fdp1->dev); + ret = pm_runtime_resume_and_get(fdp1->dev); + if (ret < 0) + goto disable_pm; hw_version = fdp1_read(fdp1, FD1_IP_INTDATA); switch (hw_version) { @@ -2385,6 +2391,9 @@ static int fdp1_probe(struct platform_device *pdev) return 0; +disable_pm: + pm_runtime_disable(fdp1->dev); + release_m2m: v4l2_m2m_release(fdp1->m2m_dev); From ee24c9e23206aa3e04e5275b500e7b81995ec894 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Wed, 1 Sep 2021 07:55:24 +0200 Subject: [PATCH 2783/4345] media: rcar_fdp1: Make use of the helper function devm_platform_ioremap_resource() [ Upstream commit 736cce12fa630e28705de06570d74f0513d948d5 ] Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Reviewed-by: Kieran Bingham Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: c766c90faf93 ("media: rcar_fdp1: Fix refcount leak in probe and remove function") Signed-off-by: Sasha Levin --- drivers/media/platform/rcar_fdp1.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c index cedae184c6ad..782e805b85da 100644 --- a/drivers/media/platform/rcar_fdp1.c +++ b/drivers/media/platform/rcar_fdp1.c @@ -2260,7 +2260,6 @@ static int fdp1_probe(struct platform_device *pdev) struct fdp1_dev *fdp1; struct video_device *vfd; struct device_node *fcp_node; - struct resource *res; struct clk *clk; unsigned int i; @@ -2287,8 +2286,7 @@ static int fdp1_probe(struct platform_device *pdev) platform_set_drvdata(pdev, fdp1); /* Memory-mapped registers */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - fdp1->regs = devm_ioremap_resource(&pdev->dev, res); + fdp1->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(fdp1->regs)) return PTR_ERR(fdp1->regs); From ccc454881f0953c9bf8201e673d398cc320cdb8b Mon Sep 17 00:00:00 2001 From: Tang Bin Date: Thu, 21 Oct 2021 05:09:38 +0200 Subject: [PATCH 2784/4345] media: rcar_fdp1: Fix the correct variable assignments [ Upstream commit af88c2adbb72a09ab1bb5c37ba388c98fecca69b ] In the function fdp1_probe(), when get irq failed, the function platform_get_irq() log an error message, so remove redundant message here. And the variable type of "ret" is int, the "fdp1->irq" is unsigned int, when irq failed, this place maybe wrong, thus fix it. Signed-off-by: Tang Bin Reviewed-by: Geert Uytterhoeven Reviewed-by: Kieran Bingham Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: c766c90faf93 ("media: rcar_fdp1: Fix refcount leak in probe and remove function") Signed-off-by: Sasha Levin --- drivers/media/platform/rcar_fdp1.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c index 782e805b85da..1dd8bebb66f5 100644 --- a/drivers/media/platform/rcar_fdp1.c +++ b/drivers/media/platform/rcar_fdp1.c @@ -2291,11 +2291,10 @@ static int fdp1_probe(struct platform_device *pdev) return PTR_ERR(fdp1->regs); /* Interrupt service routine registration */ - fdp1->irq = ret = platform_get_irq(pdev, 0); - if (ret < 0) { - dev_err(&pdev->dev, "cannot find IRQ\n"); + ret = platform_get_irq(pdev, 0); + if (ret < 0) return ret; - } + fdp1->irq = ret; ret = devm_request_irq(&pdev->dev, fdp1->irq, fdp1_irq_handler, 0, dev_name(&pdev->dev), fdp1); From 1acb982e3616e70128994fdecf2368a259c8a489 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Fri, 6 Jan 2023 11:58:09 +0400 Subject: [PATCH 2785/4345] media: rcar_fdp1: Fix refcount leak in probe and remove function [ Upstream commit c766c90faf93897b77c9c5daa603cffab85ba907 ] rcar_fcp_get() take reference, which should be balanced with rcar_fcp_put(). Add missing rcar_fcp_put() in fdp1_remove and the error paths of fdp1_probe() to fix this. Fixes: 4710b752e029 ("[media] v4l: Add Renesas R-Car FDP1 Driver") Signed-off-by: Miaoqian Lin Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart [hverkuil: resolve merge conflict, remove() is now void] Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/rcar_fdp1.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c index 1dd8bebb66f5..44a57fa06e74 100644 --- a/drivers/media/platform/rcar_fdp1.c +++ b/drivers/media/platform/rcar_fdp1.c @@ -2317,8 +2317,10 @@ static int fdp1_probe(struct platform_device *pdev) /* Determine our clock rate */ clk = clk_get(&pdev->dev, NULL); - if (IS_ERR(clk)) - return PTR_ERR(clk); + if (IS_ERR(clk)) { + ret = PTR_ERR(clk); + goto put_dev; + } fdp1->clk_rate = clk_get_rate(clk); clk_put(clk); @@ -2327,7 +2329,7 @@ static int fdp1_probe(struct platform_device *pdev) ret = v4l2_device_register(&pdev->dev, &fdp1->v4l2_dev); if (ret) { v4l2_err(&fdp1->v4l2_dev, "Failed to register video device\n"); - return ret; + goto put_dev; } /* M2M registration */ @@ -2397,6 +2399,8 @@ release_m2m: unreg_dev: v4l2_device_unregister(&fdp1->v4l2_dev); +put_dev: + rcar_fcp_put(fdp1->fcp); return ret; } @@ -2408,6 +2412,7 @@ static int fdp1_remove(struct platform_device *pdev) video_unregister_device(&fdp1->vfd); v4l2_device_unregister(&fdp1->v4l2_dev); pm_runtime_disable(&pdev->dev); + rcar_fcp_put(fdp1->fcp); return 0; } From 025a34716c888551a7ffd2a1119f60cb628be7fd Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 24 Mar 2023 13:38:33 -0700 Subject: [PATCH 2786/4345] media: rc: gpio-ir-recv: Fix support for wake-up [ Upstream commit 9c592f8ab114875fdb3b2040f01818e53de44991 ] The driver was intended from the start to be a wake-up source for the system, however due to the absence of a suitable call to device_set_wakeup_capable(), the device_may_wakeup() call used to decide whether to enable the GPIO interrupt as a wake-up source would never happen. Lookup the DT standard "wakeup-source" property and call device_init_wakeup() to ensure the device is flagged as being wakeup capable. Reported-by: Matthew Lear Fixes: fd0f6851eb46 ("[media] rc: Add support for GPIO based IR Receiver driver") Signed-off-by: Florian Fainelli Signed-off-by: Sean Young Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/rc/gpio-ir-recv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/rc/gpio-ir-recv.c b/drivers/media/rc/gpio-ir-recv.c index a56c844d7f81..16795e07dc10 100644 --- a/drivers/media/rc/gpio-ir-recv.c +++ b/drivers/media/rc/gpio-ir-recv.c @@ -107,6 +107,8 @@ static int gpio_ir_recv_probe(struct platform_device *pdev) rcdev->map_name = RC_MAP_EMPTY; gpio_dev->rcdev = rcdev; + if (of_property_read_bool(np, "wakeup-source")) + device_init_wakeup(dev, true); rc = devm_rc_register_device(dev, rcdev); if (rc < 0) { From a30297bff881dd13bd74cfa4c93034e47396011e Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Mon, 28 Sep 2020 18:44:29 +0200 Subject: [PATCH 2787/4345] media: venus: vdec: Fix non reliable setting of LAST flag [ Upstream commit acf8a57d8caf5ceabbe50774953fe04745ad1a50 ] In real use of dynamic-resolution-change it is observed that the LAST buffer flag (which marks the last decoded buffer with the resolution before the resolution-change event) is not reliably set. Fix this by set the LAST buffer flag on next queued capture buffer after the resolution-change event. Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: 50248ad9f190 ("media: venus: dec: Fix handling of the start cmd") Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/venus/core.h | 5 +-- drivers/media/platform/qcom/venus/helpers.c | 6 +++ drivers/media/platform/qcom/venus/vdec.c | 45 ++++++++++++--------- 3 files changed, 33 insertions(+), 23 deletions(-) diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h index f2a0ef9ee884..f78eed2c243a 100644 --- a/drivers/media/platform/qcom/venus/core.h +++ b/drivers/media/platform/qcom/venus/core.h @@ -283,7 +283,6 @@ enum venus_dec_state { VENUS_DEC_STATE_DRAIN = 5, VENUS_DEC_STATE_DECODING = 6, VENUS_DEC_STATE_DRC = 7, - VENUS_DEC_STATE_DRC_FLUSH_DONE = 8, }; struct venus_ts_metadata { @@ -348,7 +347,7 @@ struct venus_ts_metadata { * @priv: a private for HFI operations callbacks * @session_type: the type of the session (decoder or encoder) * @hprop: a union used as a holder by get property - * @last_buf: last capture buffer for dynamic-resoluton-change + * @next_buf_last: a flag to mark next queued capture buffer as last */ struct venus_inst { struct list_head list; @@ -410,7 +409,7 @@ struct venus_inst { union hfi_get_property hprop; unsigned int core_acquired: 1; unsigned int bit_depth; - struct vb2_buffer *last_buf; + bool next_buf_last; }; #define IS_V1(core) ((core)->res->hfi_version == HFI_VERSION_1XX) diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c index 50439eb1ffea..5ca3920237c5 100644 --- a/drivers/media/platform/qcom/venus/helpers.c +++ b/drivers/media/platform/qcom/venus/helpers.c @@ -1347,6 +1347,12 @@ void venus_helper_vb2_buf_queue(struct vb2_buffer *vb) v4l2_m2m_buf_queue(m2m_ctx, vbuf); + /* Skip processing queued capture buffers after LAST flag */ + if (inst->session_type == VIDC_SESSION_TYPE_DEC && + V4L2_TYPE_IS_CAPTURE(vb->vb2_queue->type) && + inst->codec_state == VENUS_DEC_STATE_DRC) + goto unlock; + cache_payload(inst, vb); if (inst->session_type == VIDC_SESSION_TYPE_ENC && diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index de34a87d1130..b6b5ae0a457b 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -916,10 +916,6 @@ static int vdec_start_capture(struct venus_inst *inst) return 0; reconfigure: - ret = hfi_session_flush(inst, HFI_FLUSH_OUTPUT, true); - if (ret) - return ret; - ret = vdec_output_conf(inst); if (ret) return ret; @@ -947,6 +943,8 @@ reconfigure: venus_pm_load_scale(inst); + inst->next_buf_last = false; + ret = hfi_session_continue(inst); if (ret) goto free_dpb_bufs; @@ -987,6 +985,7 @@ static int vdec_start_output(struct venus_inst *inst) venus_helper_init_instance(inst); inst->sequence_out = 0; inst->reconfig = false; + inst->next_buf_last = false; ret = vdec_set_properties(inst); if (ret) @@ -1080,9 +1079,7 @@ static int vdec_stop_capture(struct venus_inst *inst) inst->codec_state = VENUS_DEC_STATE_STOPPED; break; case VENUS_DEC_STATE_DRC: - WARN_ON(1); - fallthrough; - case VENUS_DEC_STATE_DRC_FLUSH_DONE: + ret = hfi_session_flush(inst, HFI_FLUSH_OUTPUT, true); inst->codec_state = VENUS_DEC_STATE_CAPTURE_SETUP; venus_helper_free_dpb_bufs(inst); break; @@ -1206,9 +1203,28 @@ static void vdec_buf_cleanup(struct vb2_buffer *vb) static void vdec_vb2_buf_queue(struct vb2_buffer *vb) { struct venus_inst *inst = vb2_get_drv_priv(vb->vb2_queue); + struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); + static const struct v4l2_event eos = { .type = V4L2_EVENT_EOS }; vdec_pm_get_put(inst); + mutex_lock(&inst->lock); + + if (inst->next_buf_last && V4L2_TYPE_IS_CAPTURE(vb->vb2_queue->type) && + inst->codec_state == VENUS_DEC_STATE_DRC) { + vbuf->flags |= V4L2_BUF_FLAG_LAST; + vbuf->sequence = inst->sequence_cap++; + vbuf->field = V4L2_FIELD_NONE; + vb2_set_plane_payload(vb, 0, 0); + v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_DONE); + v4l2_event_queue_fh(&inst->fh, &eos); + inst->next_buf_last = false; + mutex_unlock(&inst->lock); + return; + } + + mutex_unlock(&inst->lock); + venus_helper_vb2_buf_queue(vb); } @@ -1252,13 +1268,6 @@ static void vdec_buf_done(struct venus_inst *inst, unsigned int buf_type, vb->timestamp = timestamp_us * NSEC_PER_USEC; vbuf->sequence = inst->sequence_cap++; - if (inst->last_buf == vb) { - inst->last_buf = NULL; - vbuf->flags |= V4L2_BUF_FLAG_LAST; - vb2_set_plane_payload(vb, 0, 0); - vb->timestamp = 0; - } - if (vbuf->flags & V4L2_BUF_FLAG_LAST) { const struct v4l2_event ev = { .type = V4L2_EVENT_EOS }; @@ -1343,12 +1352,9 @@ static void vdec_event_change(struct venus_inst *inst, */ if (!sufficient && inst->codec_state == VENUS_DEC_STATE_DRC) { - struct vb2_v4l2_buffer *last; int ret; - last = v4l2_m2m_last_dst_buf(inst->m2m_ctx); - if (last) - inst->last_buf = &last->vb2_buf; + inst->next_buf_last = true; ret = hfi_session_flush(inst, HFI_FLUSH_OUTPUT, false); if (ret) @@ -1397,8 +1403,7 @@ static void vdec_event_notify(struct venus_inst *inst, u32 event, static void vdec_flush_done(struct venus_inst *inst) { - if (inst->codec_state == VENUS_DEC_STATE_DRC) - inst->codec_state = VENUS_DEC_STATE_DRC_FLUSH_DONE; + dev_dbg(inst->core->dev_dec, VDBGH "flush done\n"); } static const struct hfi_inst_ops vdec_hfi_ops = { From 4c1239274f41989d3f2b454f87847a351e3f6ba2 Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Mon, 28 Sep 2020 18:44:30 +0200 Subject: [PATCH 2788/4345] media: venus: vdec: Make decoder return LAST flag for sufficient event [ Upstream commit a4ca67af8b831a781ac53060c5d5c3dccaf7676e ] This makes the decoder to behaives equally for sufficient and insufficient events. After this change the LAST buffer flag will be set when the new resolution (in dynamic-resolution-change state) is smaller then the old bitstream resolution. Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: 50248ad9f190 ("media: venus: dec: Fix handling of the start cmd") Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/venus/vdec.c | 42 ++++++++++++++++-------- 1 file changed, 28 insertions(+), 14 deletions(-) diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index b6b5ae0a457b..3adff10fce6a 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -636,6 +636,7 @@ static int vdec_output_conf(struct venus_inst *inst) { struct venus_core *core = inst->core; struct hfi_enable en = { .enable = 1 }; + struct hfi_buffer_requirements bufreq; u32 width = inst->out_width; u32 height = inst->out_height; u32 out_fmt, out2_fmt; @@ -711,6 +712,23 @@ static int vdec_output_conf(struct venus_inst *inst) } if (IS_V3(core) || IS_V4(core)) { + ret = venus_helper_get_bufreq(inst, HFI_BUFFER_OUTPUT, &bufreq); + if (ret) + return ret; + + if (bufreq.size > inst->output_buf_size) + return -EINVAL; + + if (inst->dpb_fmt) { + ret = venus_helper_get_bufreq(inst, HFI_BUFFER_OUTPUT2, + &bufreq); + if (ret) + return ret; + + if (bufreq.size > inst->output2_buf_size) + return -EINVAL; + } + if (inst->output2_buf_size) { ret = venus_helper_set_bufsize(inst, inst->output2_buf_size, @@ -1330,19 +1348,15 @@ static void vdec_event_change(struct venus_inst *inst, dev_dbg(dev, VDBGM "event %s sufficient resources (%ux%u)\n", sufficient ? "" : "not", ev_data->width, ev_data->height); - if (sufficient) { - hfi_session_continue(inst); - } else { - switch (inst->codec_state) { - case VENUS_DEC_STATE_INIT: - inst->codec_state = VENUS_DEC_STATE_CAPTURE_SETUP; - break; - case VENUS_DEC_STATE_DECODING: - inst->codec_state = VENUS_DEC_STATE_DRC; - break; - default: - break; - } + switch (inst->codec_state) { + case VENUS_DEC_STATE_INIT: + inst->codec_state = VENUS_DEC_STATE_CAPTURE_SETUP; + break; + case VENUS_DEC_STATE_DECODING: + inst->codec_state = VENUS_DEC_STATE_DRC; + break; + default: + break; } /* @@ -1351,7 +1365,7 @@ static void vdec_event_change(struct venus_inst *inst, * itself doesn't mark the last decoder output buffer with HFI EOS flag. */ - if (!sufficient && inst->codec_state == VENUS_DEC_STATE_DRC) { + if (inst->codec_state == VENUS_DEC_STATE_DRC) { int ret; inst->next_buf_last = true; From 5bac3de7f49fe3a21f485d2cf64f847b5b4677dd Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Wed, 2 Dec 2020 06:34:24 +0100 Subject: [PATCH 2789/4345] media: venus: preserve DRC state across seeks [ Upstream commit d5ee32d7e5929592ad9b6e7a919dcdf89d05221b ] DRC events can happen virtually at anytime, including when we are starting a seek. Should this happen, we must make sure to return to the DRC state, otherwise the firmware will expect buffers of the new resolution whereas userspace will still work with the old one. Returning to the DRC state upon resume for seeking makes sure that the client will get the DRC event and will reallocate the buffers to fit the firmware's expectations. Signed-off-by: Alexandre Courbot Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: 50248ad9f190 ("media: venus: dec: Fix handling of the start cmd") Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/venus/vdec.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 3adff10fce6a..1bb2350408cf 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -987,7 +987,10 @@ static int vdec_start_output(struct venus_inst *inst) if (inst->codec_state == VENUS_DEC_STATE_SEEK) { ret = venus_helper_process_initial_out_bufs(inst); - inst->codec_state = VENUS_DEC_STATE_DECODING; + if (inst->next_buf_last) + inst->codec_state = VENUS_DEC_STATE_DRC; + else + inst->codec_state = VENUS_DEC_STATE_DECODING; goto done; } @@ -1093,8 +1096,10 @@ static int vdec_stop_capture(struct venus_inst *inst) ret = hfi_session_flush(inst, HFI_FLUSH_ALL, true); fallthrough; case VENUS_DEC_STATE_DRAIN: - vdec_cancel_dst_buffers(inst); inst->codec_state = VENUS_DEC_STATE_STOPPED; + fallthrough; + case VENUS_DEC_STATE_SEEK: + vdec_cancel_dst_buffers(inst); break; case VENUS_DEC_STATE_DRC: ret = hfi_session_flush(inst, HFI_FLUSH_OUTPUT, true); @@ -1116,6 +1121,7 @@ static int vdec_stop_output(struct venus_inst *inst) case VENUS_DEC_STATE_DECODING: case VENUS_DEC_STATE_DRAIN: case VENUS_DEC_STATE_STOPPED: + case VENUS_DEC_STATE_DRC: ret = hfi_session_flush(inst, HFI_FLUSH_ALL, true); inst->codec_state = VENUS_DEC_STATE_SEEK; break; @@ -1375,6 +1381,7 @@ static void vdec_event_change(struct venus_inst *inst, dev_dbg(dev, VDBGH "flush output error %d\n", ret); } + inst->next_buf_last = true; inst->reconfig = true; v4l2_event_queue_fh(&inst->fh, &ev); wake_up(&inst->reconf_wait); From 3a227dc12b1af9cdca12da9ce486606138ee33b0 Mon Sep 17 00:00:00 2001 From: Fritz Koenig Date: Tue, 1 Dec 2020 05:23:23 +0100 Subject: [PATCH 2790/4345] media: venus: vdec: Handle DRC after drain [ Upstream commit c8e8dabcd1a8c7aaedc514052d383a8152119084 ] If the DRC is near the end of the stream the client may send a V4L2_DEC_CMD_STOP before the DRC occurs. V4L2_DEC_CMD_STOP puts the driver into the VENUS_DEC_STATE_DRAIN state. DRC must be aware so that after the DRC event the state can be restored correctly. Signed-off-by: Fritz Koenig Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab Stable-dep-of: 50248ad9f190 ("media: venus: dec: Fix handling of the start cmd") Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/venus/core.h | 1 + drivers/media/platform/qcom/venus/vdec.c | 14 ++++++++++++-- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h index f78eed2c243a..aebd4c664bfa 100644 --- a/drivers/media/platform/qcom/venus/core.h +++ b/drivers/media/platform/qcom/venus/core.h @@ -410,6 +410,7 @@ struct venus_inst { unsigned int core_acquired: 1; unsigned int bit_depth; bool next_buf_last; + bool drain_active; }; #define IS_V1(core) ((core)->res->hfi_version == HFI_VERSION_1XX) diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 1bb2350408cf..766c29291527 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -518,8 +518,10 @@ vdec_decoder_cmd(struct file *file, void *fh, struct v4l2_decoder_cmd *cmd) ret = hfi_session_process_buf(inst, &fdata); - if (!ret && inst->codec_state == VENUS_DEC_STATE_DECODING) + if (!ret && inst->codec_state == VENUS_DEC_STATE_DECODING) { inst->codec_state = VENUS_DEC_STATE_DRAIN; + inst->drain_active = true; + } } unlock: @@ -969,9 +971,13 @@ reconfigure: inst->codec_state = VENUS_DEC_STATE_DECODING; + if (inst->drain_active) + inst->codec_state = VENUS_DEC_STATE_DRAIN; + inst->streamon_cap = 1; inst->sequence_cap = 0; inst->reconfig = false; + inst->drain_active = false; return 0; @@ -1097,6 +1103,7 @@ static int vdec_stop_capture(struct venus_inst *inst) fallthrough; case VENUS_DEC_STATE_DRAIN: inst->codec_state = VENUS_DEC_STATE_STOPPED; + inst->drain_active = false; fallthrough; case VENUS_DEC_STATE_SEEK: vdec_cancel_dst_buffers(inst); @@ -1297,8 +1304,10 @@ static void vdec_buf_done(struct venus_inst *inst, unsigned int buf_type, v4l2_event_queue_fh(&inst->fh, &ev); - if (inst->codec_state == VENUS_DEC_STATE_DRAIN) + if (inst->codec_state == VENUS_DEC_STATE_DRAIN) { + inst->drain_active = false; inst->codec_state = VENUS_DEC_STATE_STOPPED; + } } if (!bytesused) @@ -1359,6 +1368,7 @@ static void vdec_event_change(struct venus_inst *inst, inst->codec_state = VENUS_DEC_STATE_CAPTURE_SETUP; break; case VENUS_DEC_STATE_DECODING: + case VENUS_DEC_STATE_DRAIN: inst->codec_state = VENUS_DEC_STATE_DRC; break; default: From a6aeba550c5904fba261c92ec8e7bfd715694d52 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Krawczyk?= Date: Mon, 30 Jan 2023 13:54:18 +0000 Subject: [PATCH 2791/4345] media: venus: dec: Fix handling of the start cmd MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 50248ad9f190d527cbd578190ca769729518b703 ] The decoder driver should clear the last_buffer_dequeued flag of the capture queue upon receiving V4L2_DEC_CMD_START. The last_buffer_dequeued flag is set upon receiving EOS (which always happens upon receiving V4L2_DEC_CMD_STOP). Without this patch, after issuing the V4L2_DEC_CMD_STOP and V4L2_DEC_CMD_START, the vb2_dqbuf() function will always fail, even if the buffers are completed by the hardware. Fixes: beac82904a87 ("media: venus: make decoder compliant with stateful codec API") Signed-off-by: Michał Krawczyk Signed-off-by: Stanimir Varbanov Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/venus/vdec.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 766c29291527..c437a929a545 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -495,6 +495,7 @@ static int vdec_decoder_cmd(struct file *file, void *fh, struct v4l2_decoder_cmd *cmd) { struct venus_inst *inst = to_inst(file); + struct vb2_queue *dst_vq; struct hfi_frame_data fdata = {0}; int ret; @@ -522,6 +523,13 @@ vdec_decoder_cmd(struct file *file, void *fh, struct v4l2_decoder_cmd *cmd) inst->codec_state = VENUS_DEC_STATE_DRAIN; inst->drain_active = true; } + } else if (cmd->cmd == V4L2_DEC_CMD_START && + inst->codec_state == VENUS_DEC_STATE_STOPPED) { + dst_vq = v4l2_m2m_get_vq(inst->fh.m2m_ctx, + V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE); + vb2_clear_last_buffer_dequeued(dst_vq); + + inst->codec_state = VENUS_DEC_STATE_DECODING; } unlock: From dfce9bb3517a78507cf96f9b83948d0b81338afa Mon Sep 17 00:00:00 2001 From: YAN SHI Date: Wed, 12 Apr 2023 11:35:29 +0800 Subject: [PATCH 2792/4345] regulator: stm32-pwr: fix of_iomap leak [ Upstream commit c4a413e56d16a2ae84e6d8992f215c4dcc7fac20 ] Smatch reports: drivers/regulator/stm32-pwr.c:166 stm32_pwr_regulator_probe() warn: 'base' from of_iomap() not released on lines: 151,166. In stm32_pwr_regulator_probe(), base is not released when devm_kzalloc() fails to allocate memory or devm_regulator_register() fails to register a new regulator device, which may cause a leak. To fix this issue, replace of_iomap() with devm_platform_ioremap_resource(). devm_platform_ioremap_resource() is a specialized function for platform devices. It allows 'base' to be automatically released whether the probe function succeeds or fails. Besides, use IS_ERR(base) instead of !base as the return value of devm_platform_ioremap_resource() can either be a pointer to the remapped memory or an ERR_PTR() encoded error code if the operation fails. Fixes: dc62f951a6a8 ("regulator: stm32-pwr: Fix return value check in stm32_pwr_regulator_probe()") Signed-off-by: YAN SHI Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304111750.o2643eJN-lkp@intel.com/ Reviewed-by: Dongliang Mu Link: https://lore.kernel.org/r/20230412033529.18890-1-m202071378@hust.edu.cn Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/stm32-pwr.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/regulator/stm32-pwr.c b/drivers/regulator/stm32-pwr.c index 2a42acb7c24e..e5dd4db6403b 100644 --- a/drivers/regulator/stm32-pwr.c +++ b/drivers/regulator/stm32-pwr.c @@ -129,17 +129,16 @@ static const struct regulator_desc stm32_pwr_desc[] = { static int stm32_pwr_regulator_probe(struct platform_device *pdev) { - struct device_node *np = pdev->dev.of_node; struct stm32_pwr_reg *priv; void __iomem *base; struct regulator_dev *rdev; struct regulator_config config = { }; int i, ret = 0; - base = of_iomap(np, 0); - if (!base) { + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) { dev_err(&pdev->dev, "Unable to map IO memory\n"); - return -ENOMEM; + return PTR_ERR(base); } config.dev = &pdev->dev; From 55fc2246c46d8cc2ea56497664eaa4d7412409c8 Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Tue, 28 Mar 2023 00:30:04 -0700 Subject: [PATCH 2793/4345] x86/ioapic: Don't return 0 from arch_dynirq_lower_bound() [ Upstream commit 5af507bef93c09a94fb8f058213b489178f4cbe5 ] arch_dynirq_lower_bound() is invoked by the core interrupt code to retrieve the lowest possible Linux interrupt number for dynamically allocated interrupts like MSI. The x86 implementation uses this to exclude the IO/APIC GSI space. This works correctly as long as there is an IO/APIC registered, but returns 0 if not. This has been observed in VMs where the BIOS does not advertise an IO/APIC. 0 is an invalid interrupt number except for the legacy timer interrupt on x86. The return value is unchecked in the core code, so it ends up to allocate interrupt number 0 which is subsequently considered to be invalid by the caller, e.g. the MSI allocation code. The function has already a check for 0 in the case that an IO/APIC is registered, as ioapic_dynirq_base is 0 in case of device tree setups. Consolidate this and zero check for both ioapic_dynirq_base and gsi_top, which is used in the case that no IO/APIC is registered. Fixes: 3e5bedc2c258 ("x86/apic: Fix arch_dynirq_lower_bound() bug for DT enabled machines") Signed-off-by: Saurabh Sengar Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/1679988604-20308-1-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Sasha Levin --- arch/x86/kernel/apic/io_apic.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 25b1d5c6af96..74794387bf59 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2442,17 +2442,21 @@ static int io_apic_get_redir_entries(int ioapic) unsigned int arch_dynirq_lower_bound(unsigned int from) { + unsigned int ret; + /* * dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use * gsi_top if ioapic_dynirq_base hasn't been initialized yet. */ - if (!ioapic_initialized) - return gsi_top; + ret = ioapic_dynirq_base ? : gsi_top; + /* - * For DT enabled machines ioapic_dynirq_base is irrelevant and not - * updated. So simply return @from if ioapic_dynirq_base == 0. + * For DT enabled machines ioapic_dynirq_base is irrelevant and + * always 0. gsi_top can be 0 if there is no IO/APIC registered. + * 0 is an invalid interrupt number for dynamic allocations. Return + * @from instead. */ - return ioapic_dynirq_base ? : from; + return ret ? : from; } #ifdef CONFIG_X86_32 From f16f065f8ce3651b875cc88fb7a8d048f7beef7a Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Thu, 2 Feb 2023 13:01:48 +0530 Subject: [PATCH 2794/4345] arm64: kgdb: Set PSTATE.SS to 1 to re-enable single-step [ Upstream commit af6c0bd59f4f3ad5daad2f7b777954b1954551d5 ] Currently only the first attempt to single-step has any effect. After that all further stepping remains "stuck" at the same program counter value. Refer to the ARM Architecture Reference Manual (ARM DDI 0487E.a) D2.12, PSTATE.SS=1 should be set at each step before transferring the PE to the 'Active-not-pending' state. The problem here is PSTATE.SS=1 is not set since the second single-step. After the first single-step, the PE transferes to the 'Inactive' state, with PSTATE.SS=0 and MDSCR.SS=1, thus PSTATE.SS won't be set to 1 due to kernel_active_single_step()=true. Then the PE transferes to the 'Active-pending' state when ERET and returns to the debugger by step exception. Before this patch: ================== Entering kdb (current=0xffff3376039f0000, pid 1) on processor 0 due to Keyboard Entry [0]kdb> [0]kdb> [0]kdb> bp write_sysrq_trigger Instruction(i) BP #0 at 0xffffa45c13d09290 (write_sysrq_trigger) is enabled addr at ffffa45c13d09290, hardtype=0 installed=0 [0]kdb> go $ echo h > /proc/sysrq-trigger Entering kdb (current=0xffff4f7e453f8000, pid 175) on processor 1 due to Breakpoint @ 0xffffad651a309290 [1]kdb> ss Entering kdb (current=0xffff4f7e453f8000, pid 175) on processor 1 due to SS trap @ 0xffffad651a309294 [1]kdb> ss Entering kdb (current=0xffff4f7e453f8000, pid 175) on processor 1 due to SS trap @ 0xffffad651a309294 [1]kdb> After this patch: ================= Entering kdb (current=0xffff6851c39f0000, pid 1) on processor 0 due to Keyboard Entry [0]kdb> bp write_sysrq_trigger Instruction(i) BP #0 at 0xffffc02d2dd09290 (write_sysrq_trigger) is enabled addr at ffffc02d2dd09290, hardtype=0 installed=0 [0]kdb> go $ echo h > /proc/sysrq-trigger Entering kdb (current=0xffff6851c53c1840, pid 174) on processor 1 due to Breakpoint @ 0xffffc02d2dd09290 [1]kdb> ss Entering kdb (current=0xffff6851c53c1840, pid 174) on processor 1 due to SS trap @ 0xffffc02d2dd09294 [1]kdb> ss Entering kdb (current=0xffff6851c53c1840, pid 174) on processor 1 due to SS trap @ 0xffffc02d2dd09298 [1]kdb> ss Entering kdb (current=0xffff6851c53c1840, pid 174) on processor 1 due to SS trap @ 0xffffc02d2dd0929c [1]kdb> Fixes: 44679a4f142b ("arm64: KGDB: Add step debugging support") Co-developed-by: Wei Li Signed-off-by: Wei Li Signed-off-by: Sumit Garg Tested-by: Douglas Anderson Acked-by: Daniel Thompson Tested-by: Daniel Thompson Link: https://lore.kernel.org/r/20230202073148.657746-3-sumit.garg@linaro.org Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/include/asm/debug-monitors.h | 1 + arch/arm64/kernel/debug-monitors.c | 5 +++++ arch/arm64/kernel/kgdb.c | 2 ++ 3 files changed, 8 insertions(+) diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 657c921fd784..c16ed5b68768 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -116,6 +116,7 @@ void user_regs_reset_single_step(struct user_pt_regs *regs, void kernel_enable_single_step(struct pt_regs *regs); void kernel_disable_single_step(void); int kernel_active_single_step(void); +void kernel_rewind_single_step(struct pt_regs *regs); #ifdef CONFIG_HAVE_HW_BREAKPOINT int reinstall_suspended_bps(struct pt_regs *regs); diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index fa76151de6ff..38a0213fdbee 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -439,6 +439,11 @@ int kernel_active_single_step(void) } NOKPROBE_SYMBOL(kernel_active_single_step); +void kernel_rewind_single_step(struct pt_regs *regs) +{ + set_regs_spsr_ss(regs); +} + /* ptrace API */ void user_enable_single_step(struct task_struct *task) { diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index 1a157ca33262..e4e95821b1f6 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -223,6 +223,8 @@ int kgdb_arch_handle_exception(int exception_vector, int signo, */ if (!kernel_active_single_step()) kernel_enable_single_step(linux_regs); + else + kernel_rewind_single_step(linux_regs); err = 0; break; default: From 9edf5518db252b7ea2e2e87133c891bad5d8955a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 12 Apr 2023 09:54:39 +0200 Subject: [PATCH 2795/4345] debugobject: Prevent init race with static objects [ Upstream commit 63a759694eed61025713b3e14dd827c8548daadc ] Statically initialized objects are usually not initialized via the init() function of the subsystem. They are special cased and the subsystem provides a function to validate whether an object which is not yet tracked by debugobjects is statically initialized. This means the object is started to be tracked on first use, e.g. activation. This works perfectly fine, unless there are two concurrent operations on that object. Schspa decoded the problem: T0 T1 debug_object_assert_init(addr) lock_hash_bucket() obj = lookup_object(addr); if (!obj) { unlock_hash_bucket(); - > preemption lock_subsytem_object(addr); activate_object(addr) lock_hash_bucket(); obj = lookup_object(addr); if (!obj) { unlock_hash_bucket(); if (is_static_object(addr)) init_and_track(addr); lock_hash_bucket(); obj = lookup_object(addr); obj->state = ACTIVATED; unlock_hash_bucket(); subsys function modifies content of addr, so static object detection does not longer work. unlock_subsytem_object(addr); if (is_static_object(addr)) <- Fails debugobject emits a warning and invokes the fixup function which reinitializes the already active object in the worst case. This race exists forever, but was never observed until mod_timer() got a debug_object_assert_init() added which is outside of the timer base lock held section right at the beginning of the function to cover the lockless early exit points too. Rework the code so that the lookup, the static object check and the tracking object association happens atomically under the hash bucket lock. This prevents the issue completely as all callers are serialized on the hash bucket lock and therefore cannot observe inconsistent state. Fixes: 3ac7fe5a4aab ("infrastructure to debug (dynamic) objects") Reported-by: syzbot+5093ba19745994288b53@syzkaller.appspotmail.com Debugged-by: Schspa Shi Signed-off-by: Thomas Gleixner Reviewed-by: Stephen Boyd Link: https://syzkaller.appspot.com/bug?id=22c8a5938eab640d1c6bcc0e3dc7be519d878462 Link: https://lore.kernel.org/lkml/20230303161906.831686-1-schspa@gmail.com Link: https://lore.kernel.org/r/87zg7dzgao.ffs@tglx Signed-off-by: Sasha Levin --- lib/debugobjects.c | 125 ++++++++++++++++++++++++--------------------- 1 file changed, 66 insertions(+), 59 deletions(-) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 71bdc167a9ee..8282ae37db4e 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -219,10 +219,6 @@ static struct debug_obj *__alloc_object(struct hlist_head *list) return obj; } -/* - * Allocate a new object. If the pool is empty, switch off the debugger. - * Must be called with interrupts disabled. - */ static struct debug_obj * alloc_object(void *addr, struct debug_bucket *b, const struct debug_obj_descr *descr) { @@ -555,11 +551,49 @@ static void debug_object_is_on_stack(void *addr, int onstack) WARN_ON(1); } +static struct debug_obj *lookup_object_or_alloc(void *addr, struct debug_bucket *b, + const struct debug_obj_descr *descr, + bool onstack, bool alloc_ifstatic) +{ + struct debug_obj *obj = lookup_object(addr, b); + enum debug_obj_state state = ODEBUG_STATE_NONE; + + if (likely(obj)) + return obj; + + /* + * debug_object_init() unconditionally allocates untracked + * objects. It does not matter whether it is a static object or + * not. + * + * debug_object_assert_init() and debug_object_activate() allow + * allocation only if the descriptor callback confirms that the + * object is static and considered initialized. For non-static + * objects the allocation needs to be done from the fixup callback. + */ + if (unlikely(alloc_ifstatic)) { + if (!descr->is_static_object || !descr->is_static_object(addr)) + return ERR_PTR(-ENOENT); + /* Statically allocated objects are considered initialized */ + state = ODEBUG_STATE_INIT; + } + + obj = alloc_object(addr, b, descr); + if (likely(obj)) { + obj->state = state; + debug_object_is_on_stack(addr, onstack); + return obj; + } + + /* Out of memory. Do the cleanup outside of the locked region */ + debug_objects_enabled = 0; + return NULL; +} + static void __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack) { enum debug_obj_state state; - bool check_stack = false; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; @@ -570,16 +604,11 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack raw_spin_lock_irqsave(&db->lock, flags); - obj = lookup_object(addr, db); - if (!obj) { - obj = alloc_object(addr, db, descr); - if (!obj) { - debug_objects_enabled = 0; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_objects_oom(); - return; - } - check_stack = true; + obj = lookup_object_or_alloc(addr, db, descr, onstack, false); + if (unlikely(!obj)) { + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_objects_oom(); + return; } switch (obj->state) { @@ -605,8 +634,6 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack } raw_spin_unlock_irqrestore(&db->lock, flags); - if (check_stack) - debug_object_is_on_stack(addr, onstack); } /** @@ -646,14 +673,12 @@ EXPORT_SYMBOL_GPL(debug_object_init_on_stack); */ int debug_object_activate(void *addr, const struct debug_obj_descr *descr) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; enum debug_obj_state state; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; int ret; - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; if (!debug_objects_enabled) return 0; @@ -662,8 +687,8 @@ int debug_object_activate(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags); - obj = lookup_object(addr, db); - if (obj) { + obj = lookup_object_or_alloc(addr, db, descr, false, true); + if (likely(!IS_ERR_OR_NULL(obj))) { bool print_object = false; switch (obj->state) { @@ -696,24 +721,16 @@ int debug_object_activate(void *addr, const struct debug_obj_descr *descr) raw_spin_unlock_irqrestore(&db->lock, flags); - /* - * We are here when a static object is activated. We - * let the type specific code confirm whether this is - * true or not. if true, we just make sure that the - * static object is tracked in the object tracker. If - * not, this must be a bug, so we try to fix it up. - */ - if (descr->is_static_object && descr->is_static_object(addr)) { - /* track this static object */ - debug_object_init(addr, descr); - debug_object_activate(addr, descr); - } else { - debug_print_object(&o, "activate"); - ret = debug_object_fixup(descr->fixup_activate, addr, - ODEBUG_STATE_NOTAVAILABLE); - return ret ? 0 : -EINVAL; + /* If NULL the allocation has hit OOM */ + if (!obj) { + debug_objects_oom(); + return 0; } - return 0; + + /* Object is neither static nor tracked. It's not initialized */ + debug_print_object(&o, "activate"); + ret = debug_object_fixup(descr->fixup_activate, addr, ODEBUG_STATE_NOTAVAILABLE); + return ret ? 0 : -EINVAL; } EXPORT_SYMBOL_GPL(debug_object_activate); @@ -867,6 +884,7 @@ EXPORT_SYMBOL_GPL(debug_object_free); */ void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; @@ -877,31 +895,20 @@ void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr) db = get_bucket((unsigned long) addr); raw_spin_lock_irqsave(&db->lock, flags); + obj = lookup_object_or_alloc(addr, db, descr, false, true); + raw_spin_unlock_irqrestore(&db->lock, flags); + if (likely(!IS_ERR_OR_NULL(obj))) + return; - obj = lookup_object(addr, db); + /* If NULL the allocation has hit OOM */ if (!obj) { - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; - - raw_spin_unlock_irqrestore(&db->lock, flags); - /* - * Maybe the object is static, and we let the type specific - * code confirm. Track this static object if true, else invoke - * fixup. - */ - if (descr->is_static_object && descr->is_static_object(addr)) { - /* Track this static object */ - debug_object_init(addr, descr); - } else { - debug_print_object(&o, "assert_init"); - debug_object_fixup(descr->fixup_assert_init, addr, - ODEBUG_STATE_NOTAVAILABLE); - } + debug_objects_oom(); return; } - raw_spin_unlock_irqrestore(&db->lock, flags); + /* Object is neither tracked nor static. It's not initialized. */ + debug_print_object(&o, "assert_init"); + debug_object_fixup(descr->fixup_assert_init, addr, ODEBUG_STATE_NOTAVAILABLE); } EXPORT_SYMBOL_GPL(debug_object_assert_init); From 780f303233c35eeb5132e3ee1cbc8f4cebe86dd2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Thu, 13 Apr 2023 23:06:02 +0300 Subject: [PATCH 2796/4345] drm/i915: Make intel_get_crtc_new_encoder() less oopsy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 631420b06597a33c72b6dcef78d1c2dea17f452d ] The point of the WARN was to print something, not oops straight up. Currently that is precisely what happens if we can't find the connector for the crtc in the atomic state. Get the dev pointer from the atomic state instead of the potentially NULL encoder to avoid that. Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20230413200602.6037-2-ville.syrjala@linux.intel.com Fixes: 3a47ae201e07 ("drm/i915/display: Make WARN* drm specific where encoder ptr is available") Reviewed-by: Jani Nikula (cherry picked from commit 3b6692357f70498f617ea1b31a0378070a0acf1c) Signed-off-by: Joonas Lahtinen Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/display/intel_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index d46011f7a838..9a06bd8cb200 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -5844,7 +5844,7 @@ intel_get_crtc_new_encoder(const struct intel_atomic_state *state, num_encoders++; } - drm_WARN(encoder->base.dev, num_encoders != 1, + drm_WARN(state->base.dev, num_encoders != 1, "%d encoders for pipe %c\n", num_encoders, pipe_name(crtc->pipe)); From ca721584e9a4492b92972fda884449eb0e38a312 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 17 Nov 2020 14:19:45 +0100 Subject: [PATCH 2797/4345] tick/sched: Use tick_next_period for lockless quick check [ Upstream commit 372acbbaa80940189593f9d69c7c069955f24f7a ] No point in doing calculations. tick_next_period = last_jiffies_update + tick_period Just check whether now is before tick_next_period to figure out whether jiffies need an update. Add a comment why the intentional data race in the quick check is safe or not so safe in a 32bit corner case and why we don't worry about it. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20201117132006.337366695@linutronix.de Stable-dep-of: e9523a0d8189 ("tick/common: Align tick period with the HZ tick.") Signed-off-by: Sasha Levin --- kernel/time/tick-sched.c | 46 ++++++++++++++++++++++++++++------------ 1 file changed, 33 insertions(+), 13 deletions(-) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 378096fc8c56..4f1b6170b3a2 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -57,11 +57,29 @@ static void tick_do_update_jiffies64(ktime_t now) ktime_t delta; /* - * Do a quick check without holding jiffies_lock: - * The READ_ONCE() pairs with two updates done later in this function. + * Do a quick check without holding jiffies_lock. The READ_ONCE() + * pairs with the update done later in this function. + * + * This is also an intentional data race which is even safe on + * 32bit in theory. If there is a concurrent update then the check + * might give a random answer. It does not matter because if it + * returns then the concurrent update is already taking care, if it + * falls through then it will pointlessly contend on jiffies_lock. + * + * Though there is one nasty case on 32bit due to store tearing of + * the 64bit value. If the first 32bit store makes the quick check + * return on all other CPUs and the writing CPU context gets + * delayed to complete the second store (scheduled out on virt) + * then jiffies can become stale for up to ~2^32 nanoseconds + * without noticing. After that point all CPUs will wait for + * jiffies lock. + * + * OTOH, this is not any different than the situation with NOHZ=off + * where one CPU is responsible for updating jiffies and + * timekeeping. If that CPU goes out for lunch then all other CPUs + * will operate on stale jiffies until it decides to come back. */ - delta = ktime_sub(now, READ_ONCE(last_jiffies_update)); - if (delta < tick_period) + if (ktime_before(now, READ_ONCE(tick_next_period))) return; /* Reevaluate with jiffies_lock held */ @@ -72,9 +90,8 @@ static void tick_do_update_jiffies64(ktime_t now) if (delta >= tick_period) { delta = ktime_sub(delta, tick_period); - /* Pairs with the lockless read in this function. */ - WRITE_ONCE(last_jiffies_update, - ktime_add(last_jiffies_update, tick_period)); + last_jiffies_update = ktime_add(last_jiffies_update, + tick_period); /* Slow path for long timeouts */ if (unlikely(delta >= tick_period)) { @@ -82,15 +99,18 @@ static void tick_do_update_jiffies64(ktime_t now) ticks = ktime_divns(delta, incr); - /* Pairs with the lockless read in this function. */ - WRITE_ONCE(last_jiffies_update, - ktime_add_ns(last_jiffies_update, - incr * ticks)); + last_jiffies_update = ktime_add_ns(last_jiffies_update, + incr * ticks); } do_timer(++ticks); - /* Keep the tick_next_period variable up to date */ - tick_next_period = ktime_add(last_jiffies_update, tick_period); + /* + * Keep the tick_next_period variable up to date. + * WRITE_ONCE() pairs with the READ_ONCE() in the lockless + * quick check above. + */ + WRITE_ONCE(tick_next_period, + ktime_add(last_jiffies_update, tick_period)); } else { write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); From 93c43008368d60f2cb11cc239a3219a2f4142c30 Mon Sep 17 00:00:00 2001 From: Yunfeng Ye Date: Tue, 17 Nov 2020 14:19:46 +0100 Subject: [PATCH 2798/4345] tick/sched: Reduce seqcount held scope in tick_do_update_jiffies64() [ Upstream commit 94ad2e3cedb82af034f6d97c58022f162b669f9b ] If jiffies are up to date already (caller lost the race against another CPU) there is no point to change the sequence count. Doing that just forces other CPUs into the seqcount retry loop in tick_nohz_next_event() for nothing. Just bail out early. [ tglx: Rewrote most of it ] Signed-off-by: Yunfeng Ye Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20201117132006.462195901@linutronix.de Stable-dep-of: e9523a0d8189 ("tick/common: Align tick period with the HZ tick.") Signed-off-by: Sasha Levin --- kernel/time/tick-sched.c | 55 +++++++++++++++++++--------------------- 1 file changed, 26 insertions(+), 29 deletions(-) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 4f1b6170b3a2..ac9953f6f92c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -84,38 +84,35 @@ static void tick_do_update_jiffies64(ktime_t now) /* Reevaluate with jiffies_lock held */ raw_spin_lock(&jiffies_lock); - write_seqcount_begin(&jiffies_seq); - - delta = ktime_sub(now, last_jiffies_update); - if (delta >= tick_period) { - - delta = ktime_sub(delta, tick_period); - last_jiffies_update = ktime_add(last_jiffies_update, - tick_period); - - /* Slow path for long timeouts */ - if (unlikely(delta >= tick_period)) { - s64 incr = ktime_to_ns(tick_period); - - ticks = ktime_divns(delta, incr); - - last_jiffies_update = ktime_add_ns(last_jiffies_update, - incr * ticks); - } - do_timer(++ticks); - - /* - * Keep the tick_next_period variable up to date. - * WRITE_ONCE() pairs with the READ_ONCE() in the lockless - * quick check above. - */ - WRITE_ONCE(tick_next_period, - ktime_add(last_jiffies_update, tick_period)); - } else { - write_seqcount_end(&jiffies_seq); + if (ktime_before(now, tick_next_period)) { raw_spin_unlock(&jiffies_lock); return; } + + write_seqcount_begin(&jiffies_seq); + + last_jiffies_update = ktime_add(last_jiffies_update, tick_period); + + delta = ktime_sub(now, tick_next_period); + if (unlikely(delta >= tick_period)) { + /* Slow path for long idle sleep times */ + s64 incr = ktime_to_ns(tick_period); + + ticks = ktime_divns(delta, incr); + + last_jiffies_update = ktime_add_ns(last_jiffies_update, + incr * ticks); + } + + do_timer(++ticks); + + /* + * Keep the tick_next_period variable up to date. WRITE_ONCE() + * pairs with the READ_ONCE() in the lockless quick check above. + */ + WRITE_ONCE(tick_next_period, + ktime_add(last_jiffies_update, tick_period)); + write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); update_wall_time(); From fdc48767461a3ceeb1b6d587740d1430f7eb9c6f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 17 Nov 2020 14:19:47 +0100 Subject: [PATCH 2799/4345] tick/sched: Optimize tick_do_update_jiffies64() further [ Upstream commit 7a35bf2a6a871cd0252cd371d741e7d070b53af9 ] Now that it's clear that there is always one tick to account, simplify the calculations some more. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20201117132006.565663056@linutronix.de Stable-dep-of: e9523a0d8189 ("tick/common: Align tick period with the HZ tick.") Signed-off-by: Sasha Levin --- kernel/time/tick-sched.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index ac9953f6f92c..5c3d4355266d 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -53,7 +53,7 @@ static ktime_t last_jiffies_update; */ static void tick_do_update_jiffies64(ktime_t now) { - unsigned long ticks = 0; + unsigned long ticks = 1; ktime_t delta; /* @@ -91,20 +91,21 @@ static void tick_do_update_jiffies64(ktime_t now) write_seqcount_begin(&jiffies_seq); - last_jiffies_update = ktime_add(last_jiffies_update, tick_period); - delta = ktime_sub(now, tick_next_period); if (unlikely(delta >= tick_period)) { /* Slow path for long idle sleep times */ s64 incr = ktime_to_ns(tick_period); - ticks = ktime_divns(delta, incr); + ticks += ktime_divns(delta, incr); last_jiffies_update = ktime_add_ns(last_jiffies_update, incr * ticks); + } else { + last_jiffies_update = ktime_add(last_jiffies_update, + tick_period); } - do_timer(++ticks); + do_timer(ticks); /* * Keep the tick_next_period variable up to date. WRITE_ONCE() From 107ea1f63b266afcf50b7a9496d04797d149c0cf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 17 Nov 2020 14:19:49 +0100 Subject: [PATCH 2800/4345] tick: Get rid of tick_period [ Upstream commit b996544916429946bf4934c1c01a306d1690972c ] The variable tick_period is initialized to NSEC_PER_TICK / HZ during boot and never updated again. If NSEC_PER_TICK is not an integer multiple of HZ this computation is less accurate than TICK_NSEC which has proper rounding in place. Aside of the inaccuracy there is no reason for having this variable at all. It's just a pointless indirection and all usage sites can just use the TICK_NSEC constant. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20201117132006.766643526@linutronix.de Stable-dep-of: e9523a0d8189 ("tick/common: Align tick period with the HZ tick.") Signed-off-by: Sasha Levin --- kernel/time/tick-broadcast.c | 2 +- kernel/time/tick-common.c | 8 +++----- kernel/time/tick-internal.h | 1 - kernel/time/tick-sched.c | 22 +++++++++++----------- 4 files changed, 15 insertions(+), 18 deletions(-) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 36d7464c8962..a9530e866e5f 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -331,7 +331,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) bc_local = tick_do_periodic_broadcast(); if (clockevent_state_oneshot(dev)) { - ktime_t next = ktime_add(dev->next_event, tick_period); + ktime_t next = ktime_add_ns(dev->next_event, TICK_NSEC); clockevents_program_event(dev, next, true); } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 6c9c342dd0e5..92bf99d558b4 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -30,7 +30,6 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device); * Tick next event: keeps track of the tick time */ ktime_t tick_next_period; -ktime_t tick_period; /* * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR @@ -88,7 +87,7 @@ static void tick_periodic(int cpu) write_seqcount_begin(&jiffies_seq); /* Keep track of the next tick event */ - tick_next_period = ktime_add(tick_next_period, tick_period); + tick_next_period = ktime_add_ns(tick_next_period, TICK_NSEC); do_timer(1); write_seqcount_end(&jiffies_seq); @@ -127,7 +126,7 @@ void tick_handle_periodic(struct clock_event_device *dev) * Setup the next period for devices, which do not have * periodic mode: */ - next = ktime_add(next, tick_period); + next = ktime_add_ns(next, TICK_NSEC); if (!clockevents_program_event(dev, next, false)) return; @@ -173,7 +172,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) for (;;) { if (!clockevents_program_event(dev, next, false)) return; - next = ktime_add(next, tick_period); + next = ktime_add_ns(next, TICK_NSEC); } } } @@ -220,7 +219,6 @@ static void tick_setup_device(struct tick_device *td, tick_do_timer_cpu = cpu; tick_next_period = ktime_get(); - tick_period = NSEC_PER_SEC / HZ; #ifdef CONFIG_NO_HZ_FULL /* * The boot CPU may be nohz_full, in which case set diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 5294f5b1f955..e61c1244e7d4 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -15,7 +15,6 @@ DECLARE_PER_CPU(struct tick_device, tick_cpu_device); extern ktime_t tick_next_period; -extern ktime_t tick_period; extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 5c3d4355266d..17dc3f53efef 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -92,17 +92,17 @@ static void tick_do_update_jiffies64(ktime_t now) write_seqcount_begin(&jiffies_seq); delta = ktime_sub(now, tick_next_period); - if (unlikely(delta >= tick_period)) { + if (unlikely(delta >= TICK_NSEC)) { /* Slow path for long idle sleep times */ - s64 incr = ktime_to_ns(tick_period); + s64 incr = TICK_NSEC; ticks += ktime_divns(delta, incr); last_jiffies_update = ktime_add_ns(last_jiffies_update, incr * ticks); } else { - last_jiffies_update = ktime_add(last_jiffies_update, - tick_period); + last_jiffies_update = ktime_add_ns(last_jiffies_update, + TICK_NSEC); } do_timer(ticks); @@ -112,7 +112,7 @@ static void tick_do_update_jiffies64(ktime_t now) * pairs with the READ_ONCE() in the lockless quick check above. */ WRITE_ONCE(tick_next_period, - ktime_add(last_jiffies_update, tick_period)); + ktime_add_ns(last_jiffies_update, TICK_NSEC)); write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); @@ -688,7 +688,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) hrtimer_set_expires(&ts->sched_timer, ts->last_tick); /* Forward the time to expire in the future */ - hrtimer_forward(&ts->sched_timer, now, tick_period); + hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { hrtimer_start_expires(&ts->sched_timer, @@ -1250,7 +1250,7 @@ static void tick_nohz_handler(struct clock_event_device *dev) if (unlikely(ts->tick_stopped)) return; - hrtimer_forward(&ts->sched_timer, now, tick_period); + hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } @@ -1287,7 +1287,7 @@ static void tick_nohz_switch_to_nohz(void) next = tick_init_jiffy_update(); hrtimer_set_expires(&ts->sched_timer, next); - hrtimer_forward_now(&ts->sched_timer, tick_period); + hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts, NOHZ_MODE_LOWRES); } @@ -1353,7 +1353,7 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) if (unlikely(ts->tick_stopped)) return HRTIMER_NORESTART; - hrtimer_forward(timer, now, tick_period); + hrtimer_forward(timer, now, TICK_NSEC); return HRTIMER_RESTART; } @@ -1387,13 +1387,13 @@ void tick_setup_sched_timer(void) /* Offset the tick to avert jiffies_lock contention. */ if (sched_skew_tick) { - u64 offset = ktime_to_ns(tick_period) >> 1; + u64 offset = TICK_NSEC >> 1; do_div(offset, num_possible_cpus()); offset *= smp_processor_id(); hrtimer_add_expires_ns(&ts->sched_timer, offset); } - hrtimer_forward(&ts->sched_timer, now, tick_period); + hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); tick_nohz_activate(ts, NOHZ_MODE_HIGHRES); } From c4013689269df584efe9e42f7a8e42c871fc32db Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 18 Apr 2023 14:26:39 +0200 Subject: [PATCH 2801/4345] tick/common: Align tick period with the HZ tick. [ Upstream commit e9523a0d81899361214d118ad60ef76f0e92f71d ] With HIGHRES enabled tick_sched_timer() is programmed every jiffy to expire the timer_list timers. This timer is programmed accurate in respect to CLOCK_MONOTONIC so that 0 seconds and nanoseconds is the first tick and the next one is 1000/CONFIG_HZ ms later. For HZ=250 it is every 4 ms and so based on the current time the next tick can be computed. This accuracy broke since the commit mentioned below because the jiffy based clocksource is initialized with higher accuracy in read_persistent_wall_and_boot_offset(). This higher accuracy is inherited during the setup in tick_setup_device(). The timer still fires every 4ms with HZ=250 but timer is no longer aligned with CLOCK_MONOTONIC with 0 as it origin but has an offset in the us/ns part of the timestamp. The offset differs with every boot and makes it impossible for user land to align with the tick. Align the tick period with CLOCK_MONOTONIC ensuring that it is always a multiple of 1000/CONFIG_HZ ms. Fixes: 857baa87b6422 ("sched/clock: Enable sched clock early") Reported-by: Gusenleitner Klaus Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/20230406095735.0_14edn3@linutronix.de Link: https://lore.kernel.org/r/20230418122639.ikgfvu3f@linutronix.de Signed-off-by: Sasha Levin --- kernel/time/tick-common.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 92bf99d558b4..2b7448ae5b47 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -216,9 +216,19 @@ static void tick_setup_device(struct tick_device *td, * this cpu: */ if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { + ktime_t next_p; + u32 rem; + tick_do_timer_cpu = cpu; - tick_next_period = ktime_get(); + next_p = ktime_get(); + div_u64_rem(next_p, TICK_NSEC, &rem); + if (rem) { + next_p -= rem; + next_p += TICK_NSEC; + } + + tick_next_period = next_p; #ifdef CONFIG_NO_HZ_FULL /* * The boot CPU may be nohz_full, in which case set From 129c3fb5795d062eb962453a84a84d6365194c48 Mon Sep 17 00:00:00 2001 From: "Alexey V. Vissarionov" Date: Wed, 15 Feb 2023 20:31:37 +0200 Subject: [PATCH 2802/4345] wifi: ath6kl: minor fix for allocation size [ Upstream commit 778f83f889e7fca37780d9640fcbd0229ae38eaa ] Although the "param" pointer occupies more or equal space compared to "*param", the allocation size should use the size of variable itself. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: bdcd81707973cf8a ("Add ath6kl cleaned up driver") Signed-off-by: Alexey V. Vissarionov Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230117110414.GC12547@altlinux.org Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath6kl/bmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath6kl/bmi.c b/drivers/net/wireless/ath/ath6kl/bmi.c index bde5a10d470c..af98e871199d 100644 --- a/drivers/net/wireless/ath/ath6kl/bmi.c +++ b/drivers/net/wireless/ath/ath6kl/bmi.c @@ -246,7 +246,7 @@ int ath6kl_bmi_execute(struct ath6kl *ar, u32 addr, u32 *param) return -EACCES; } - size = sizeof(cid) + sizeof(addr) + sizeof(param); + size = sizeof(cid) + sizeof(addr) + sizeof(*param); if (size > ar->bmi.max_cmd_size) { WARN_ON(1); return -EINVAL; From 320d760a35273aa815d58b57e4fd9ba5279a3489 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Thu, 16 Feb 2023 22:23:01 +0300 Subject: [PATCH 2803/4345] wifi: ath9k: hif_usb: fix memory leak of remain_skbs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 7654cc03eb699297130b693ec34e25f77b17c947 ] hif_dev->remain_skb is allocated and used exclusively in ath9k_hif_usb_rx_stream(). It is implied that an allocated remain_skb is processed and subsequently freed (in error paths) only during the next call of ath9k_hif_usb_rx_stream(). So, if the urbs are deallocated between those two calls due to the device deinitialization or suspend, it is possible that ath9k_hif_usb_rx_stream() is not called next time and the allocated remain_skb is leaked. Our local Syzkaller instance was able to trigger that. remain_skb makes sense when receiving two consecutive urbs which are logically linked together, i.e. a specific data field from the first skb indicates a cached skb to be allocated, memcpy'd with some data and subsequently processed in the next call to ath9k_hif_usb_rx_stream(). Urbs deallocation supposedly makes that link irrelevant so we need to free the cached skb in those cases. Fix the leak by introducing a function to explicitly free remain_skb (if it is not NULL) when the rx urbs have been deallocated. remain_skb is NULL when it has not been allocated at all (hif_dev struct is kzalloced) or when it has been processed in next call to ath9k_hif_usb_rx_stream(). Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.") Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230216192301.171225-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/hif_usb.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index f521dfa2f194..e0130beb304d 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -534,6 +534,24 @@ static struct ath9k_htc_hif hif_usb = { .send = hif_usb_send, }; +/* Need to free remain_skb allocated in ath9k_hif_usb_rx_stream + * in case ath9k_hif_usb_rx_stream wasn't called next time to + * process the buffer and subsequently free it. + */ +static void ath9k_hif_usb_free_rx_remain_skb(struct hif_device_usb *hif_dev) +{ + unsigned long flags; + + spin_lock_irqsave(&hif_dev->rx_lock, flags); + if (hif_dev->remain_skb) { + dev_kfree_skb_any(hif_dev->remain_skb); + hif_dev->remain_skb = NULL; + hif_dev->rx_remain_len = 0; + RX_STAT_INC(hif_dev, skb_dropped); + } + spin_unlock_irqrestore(&hif_dev->rx_lock, flags); +} + static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, struct sk_buff *skb) { @@ -868,6 +886,7 @@ err: static void ath9k_hif_usb_dealloc_rx_urbs(struct hif_device_usb *hif_dev) { usb_kill_anchored_urbs(&hif_dev->rx_submitted); + ath9k_hif_usb_free_rx_remain_skb(hif_dev); } static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev) From 6c91b3b57b1f5aed73053e8992a6badc907218d3 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 6 Feb 2023 16:15:48 +0300 Subject: [PATCH 2804/4345] wifi: ath5k: fix an off by one check in ath5k_eeprom_read_freq_list() [ Upstream commit 4c856ee12df85aabd437c3836ed9f68d94268358 ] This loop checks that i < max at the start of loop but then it does i++ which could put it past the end of the array. It's harmless to check again and prevent a potential out of bounds. Fixes: 1048643ea94d ("ath5k: Clean up eeprom parsing and add missing calibration data") Signed-off-by: Dan Carpenter Reviewed-by: Luis Chamberlain Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/Y+D9hPQrHfWBJhXz@kili Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath5k/eeprom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath5k/eeprom.c b/drivers/net/wireless/ath/ath5k/eeprom.c index d444b3d70ba2..58d3e86f6256 100644 --- a/drivers/net/wireless/ath/ath5k/eeprom.c +++ b/drivers/net/wireless/ath/ath5k/eeprom.c @@ -529,7 +529,7 @@ ath5k_eeprom_read_freq_list(struct ath5k_hw *ah, int *offset, int max, ee->ee_n_piers[mode]++; freq2 = (val >> 8) & 0xff; - if (!freq2) + if (!freq2 || i >= max) break; pc[i++].freq = ath5k_eeprom_bin2freq(ee, From 1300517e371e4d0acdb0f1237477e1ed223c3a9a Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Fri, 24 Feb 2023 12:28:05 +0200 Subject: [PATCH 2805/4345] wifi: ath6kl: reduce WARN to dev_dbg() in callback [ Upstream commit 75c4a8154cb6c7239fb55d5550f481f6765fb83c ] The warn is triggered on a known race condition, documented in the code above the test, that is correctly handled. Using WARN() hinders automated testing. Reducing severity. Fixes: de2070fc4aa7 ("ath6kl: Fix kernel panic on continuous driver load/unload") Reported-and-tested-by: syzbot+555908813b2ea35dae9a@syzkaller.appspotmail.com Signed-off-by: Oliver Neukum Signed-off-by: Fedor Pchelkin Signed-off-by: Alexey Khoroshilov Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230126182431.867984-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath6kl/htc_pipe.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath6kl/htc_pipe.c b/drivers/net/wireless/ath/ath6kl/htc_pipe.c index c68848819a52..9b88d96bfe96 100644 --- a/drivers/net/wireless/ath/ath6kl/htc_pipe.c +++ b/drivers/net/wireless/ath/ath6kl/htc_pipe.c @@ -960,8 +960,8 @@ static int ath6kl_htc_pipe_rx_complete(struct ath6kl *ar, struct sk_buff *skb, * Thus the possibility of ar->htc_target being NULL * via ath6kl_recv_complete -> ath6kl_usb_io_comp_work. */ - if (WARN_ON_ONCE(!target)) { - ath6kl_err("Target not yet initialized\n"); + if (!target) { + ath6kl_dbg(ATH6KL_DBG_HTC, "Target not yet initialized\n"); status = -EINVAL; goto free_skb; } From 3ab6ec6c485b6a0b8811faa5e6166d67584001cc Mon Sep 17 00:00:00 2001 From: Luis Gerhorst Date: Mon, 27 Feb 2023 16:08:54 +0100 Subject: [PATCH 2806/4345] tools: bpftool: Remove invalid \' json escape [ Upstream commit c679bbd611c08b0559ffae079330bc4e5574696a ] RFC8259 ("The JavaScript Object Notation (JSON) Data Interchange Format") only specifies \", \\, \/, \b, \f, \n, \r, and \r as valid two-character escape sequences. This does not include \', which is not required in JSON because it exclusively uses double quotes as string separators. Solidus (/) may be escaped, but does not have to. Only reverse solidus (\), double quotes ("), and the control characters have to be escaped. Therefore, with this fix, bpftool correctly supports all valid two-character escape sequences (but still does not support characters that require multi-character escape sequences). Witout this fix, attempting to load a JSON file generated by bpftool using Python 3.10.6's default json.load() may fail with the error "Invalid \escape" if the file contains the invalid escaped single quote (\'). Fixes: b66e907cfee2 ("tools: bpftool: copy JSON writer from iproute2 repository") Signed-off-by: Luis Gerhorst Signed-off-by: Andrii Nakryiko Reviewed-by: Quentin Monnet Link: https://lore.kernel.org/bpf/20230227150853.16863-1-gerhorst@cs.fau.de Signed-off-by: Sasha Levin --- tools/bpf/bpftool/json_writer.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c index 7fea83bedf48..bca5dd0a59e3 100644 --- a/tools/bpf/bpftool/json_writer.c +++ b/tools/bpf/bpftool/json_writer.c @@ -80,9 +80,6 @@ static void jsonw_puts(json_writer_t *self, const char *str) case '"': fputs("\\\"", self->out); break; - case '\'': - fputs("\\\'", self->out); - break; default: putc(*str, self->out); } From 1980dd8c53ec6383358645073463e7a155f16f0a Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sun, 26 Feb 2023 23:10:03 +0100 Subject: [PATCH 2807/4345] wifi: rtw88: mac: Return the original error from rtw_pwr_seq_parser() [ Upstream commit b7ed9fa2cb76ca7a3c3cd4a6d35748fe1fbda9f6 ] rtw_pwr_seq_parser() calls rtw_sub_pwr_seq_parser() which can either return -EBUSY, -EINVAL or 0. Propagate the original error code instead of unconditionally returning -EBUSY in case of an error. Fixes: e3037485c68e ("rtw88: new Realtek 802.11ac driver") Signed-off-by: Martin Blumenstingl Reviewed-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230226221004.138331-2-martin.blumenstingl@googlemail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtw88/mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtw88/mac.c b/drivers/net/wireless/realtek/rtw88/mac.c index 59028b121b00..fd427c606fa2 100644 --- a/drivers/net/wireless/realtek/rtw88/mac.c +++ b/drivers/net/wireless/realtek/rtw88/mac.c @@ -233,7 +233,7 @@ static int rtw_pwr_seq_parser(struct rtw_dev *rtwdev, ret = rtw_sub_pwr_seq_parser(rtwdev, intf_mask, cut_mask, cmd); if (ret) - return -EBUSY; + return ret; idx++; } while (1); From 243fab8e37d4aa3ac91f05bd157819f97ab38d88 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sun, 26 Feb 2023 23:10:04 +0100 Subject: [PATCH 2808/4345] wifi: rtw88: mac: Return the original error from rtw_mac_power_switch() [ Upstream commit 15c8e267dfa62f207ee1db666c822324e3362b84 ] rtw_mac_power_switch() calls rtw_pwr_seq_parser() which can return -EINVAL, -EBUSY or 0. Propagate the original error code instead of unconditionally returning -EINVAL in case of an error. Fixes: e3037485c68e ("rtw88: new Realtek 802.11ac driver") Signed-off-by: Martin Blumenstingl Reviewed-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230226221004.138331-3-martin.blumenstingl@googlemail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtw88/mac.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw88/mac.c b/drivers/net/wireless/realtek/rtw88/mac.c index fd427c606fa2..a6d554a9dd99 100644 --- a/drivers/net/wireless/realtek/rtw88/mac.c +++ b/drivers/net/wireless/realtek/rtw88/mac.c @@ -247,6 +247,7 @@ static int rtw_mac_power_switch(struct rtw_dev *rtwdev, bool pwr_on) const struct rtw_pwr_seq_cmd **pwr_seq; u8 rpwm; bool cur_pwr; + int ret; if (rtw_chip_wcpu_11ac(rtwdev)) { rpwm = rtw_read8(rtwdev, rtwdev->hci.rpwm_addr); @@ -270,8 +271,9 @@ static int rtw_mac_power_switch(struct rtw_dev *rtwdev, bool pwr_on) return -EALREADY; pwr_seq = pwr_on ? chip->pwr_on_seq : chip->pwr_off_seq; - if (rtw_pwr_seq_parser(rtwdev, pwr_seq)) - return -EINVAL; + ret = rtw_pwr_seq_parser(rtwdev, pwr_seq); + if (ret) + return ret; return 0; } From 6be8ad4cdcac2fda572dd3b9f2ea064ad8b8a679 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 9 Mar 2023 14:41:31 -0800 Subject: [PATCH 2809/4345] bpf: take into account liveness when propagating precision [ Upstream commit 52c2b005a3c18c565fc70cfd0ca49375f301e952 ] When doing state comparison, if old state has register that is not marked as REG_LIVE_READ, then we just skip comparison, regardless what's the state of corresponing register in current state. This is because not REG_LIVE_READ register is irrelevant for further program execution and correctness. All good here. But when we get to precision propagation, after two states were declared equivalent, we don't take into account old register's liveness, and thus attempt to propagate precision for register in current state even if that register in old state was not REG_LIVE_READ anymore. This is bad, because register in current state could be anything at all and this could cause -EFAULT due to internal logic bugs. Fix by taking into account REG_LIVE_READ liveness mark to keep the logic in state comparison in sync with precision propagation. Fixes: a3ce685dd01a ("bpf: fix precision tracking") Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230309224131.57449-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5a96a9dd51e4..e2488a00efc5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9550,7 +9550,8 @@ static int propagate_precision(struct bpf_verifier_env *env, state_reg = state->regs; for (i = 0; i < BPF_REG_FP; i++, state_reg++) { if (state_reg->type != SCALAR_VALUE || - !state_reg->precise) + !state_reg->precise || + !(state_reg->live & REG_LIVE_READ)) continue; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "frame %d: propagating r%d\n", i, fr); @@ -9564,7 +9565,8 @@ static int propagate_precision(struct bpf_verifier_env *env, continue; state_reg = &state->stack[i].spilled_ptr; if (state_reg->type != SCALAR_VALUE || - !state_reg->precise) + !state_reg->precise || + !(state_reg->live & REG_LIVE_READ)) continue; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "frame %d: propagating fp%d\n", From 10702be8b3732b31ce4d584a23fefbf1a6f8a0f7 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 13 Mar 2023 11:40:17 -0700 Subject: [PATCH 2810/4345] bpf: fix precision propagation verbose logging [ Upstream commit 34f0677e7afd3a292bc1aadda7ce8e35faedb204 ] Fix wrong order of frame index vs register/slot index in precision propagation verbose (level 2) output. It's wrong and very confusing as is. Fixes: 529409ea92d5 ("bpf: propagate precision across all frames, not just the last one") Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230313184017.4083374-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e2488a00efc5..232f720104cd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9554,7 +9554,7 @@ static int propagate_precision(struct bpf_verifier_env *env, !(state_reg->live & REG_LIVE_READ)) continue; if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "frame %d: propagating r%d\n", i, fr); + verbose(env, "frame %d: propagating r%d\n", fr, i); err = mark_chain_precision_frame(env, fr, i); if (err < 0) return err; @@ -9570,7 +9570,7 @@ static int propagate_precision(struct bpf_verifier_env *env, continue; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "frame %d: propagating fp%d\n", - (-i - 1) * BPF_REG_SIZE, fr); + fr, (-i - 1) * BPF_REG_SIZE); err = mark_chain_precision_stack_frame(env, fr, i); if (err < 0) return err; From 10c1051267879ddf3e4aff1d0bd7d2debf28d85a Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Mon, 13 Mar 2023 12:32:11 +0100 Subject: [PATCH 2811/4345] scm: fix MSG_CTRUNC setting condition for SO_PASSSEC [ Upstream commit a02d83f9947d8f71904eda4de046630c3eb6802c ] Currently, kernel would set MSG_CTRUNC flag if msg_control buffer wasn't provided and SO_PASSCRED was set or if there was pending SCM_RIGHTS. For some reason we have no corresponding check for SO_PASSSEC. In the recvmsg(2) doc we have: MSG_CTRUNC indicates that some control data was discarded due to lack of space in the buffer for ancillary data. So, we need to set MSG_CTRUNC flag for all types of SCM. This change can break applications those don't check MSG_CTRUNC flag. Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Leon Romanovsky Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Alexander Mikhalitsyn v2: - commit message was rewritten according to Eric's suggestion Acked-by: Paul Moore Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/scm.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/include/net/scm.h b/include/net/scm.h index 1ce365f4c256..585adc1346bd 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -105,16 +105,27 @@ static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct sc } } } + +static inline bool scm_has_secdata(struct socket *sock) +{ + return test_bit(SOCK_PASSSEC, &sock->flags); +} #else static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm) { } + +static inline bool scm_has_secdata(struct socket *sock) +{ + return false; +} #endif /* CONFIG_SECURITY_NETWORK */ static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm, int flags) { if (!msg->msg_control) { - if (test_bit(SOCK_PASSCRED, &sock->flags) || scm->fp) + if (test_bit(SOCK_PASSCRED, &sock->flags) || scm->fp || + scm_has_secdata(sock)) msg->msg_flags |= MSG_CTRUNC; scm_destroy(scm); return; From 118df5df1b4b046870f166b4b88ee59b94985c93 Mon Sep 17 00:00:00 2001 From: Luis Gerhorst Date: Wed, 15 Mar 2023 17:54:00 +0100 Subject: [PATCH 2812/4345] bpf: Remove misleading spec_v1 check on var-offset stack read [ Upstream commit 082cdc69a4651dd2a77539d69416a359ed1214f5 ] For every BPF_ADD/SUB involving a pointer, adjust_ptr_min_max_vals() ensures that the resulting pointer has a constant offset if bypass_spec_v1 is false. This is ensured by calling sanitize_check_bounds() which in turn calls check_stack_access_for_ptr_arithmetic(). There, -EACCESS is returned if the register's offset is not constant, thereby rejecting the program. In summary, an unprivileged user must never be able to create stack pointers with a variable offset. That is also the case, because a respective check in check_stack_write() is missing. If they were able to create a variable-offset pointer, users could still use it in a stack-write operation to trigger unsafe speculative behavior [1]. Because unprivileged users must already be prevented from creating variable-offset stack pointers, viable options are to either remove this check (replacing it with a clarifying comment), or to turn it into a "verifier BUG"-message, also adding a similar check in check_stack_write() (for consistency, as a second-level defense). This patch implements the first option to reduce verifier bloat. This check was introduced by commit 01f810ace9ed ("bpf: Allow variable-offset stack access") which correctly notes that "variable-offset reads and writes are disallowed (they were already disallowed for the indirect access case) because the speculative execution checking code doesn't support them". However, it does not further discuss why the check in check_stack_read() is necessary. The code which made this check obsolete was also introduced in this commit. I have compiled ~650 programs from the Linux selftests, Linux samples, Cilium, and libbpf/examples projects and confirmed that none of these trigger the check in check_stack_read() [2]. Instead, all of these programs are, as expected, already rejected when constructing the variable-offset pointers. Note that the check in check_stack_access_for_ptr_arithmetic() also prints "off=%d" while the code removed by this patch does not (the error removed does not appear in the "verification_error" values). For reproducibility, the repository linked includes the raw data and scripts used to create the plot. [1] https://arxiv.org/pdf/1807.03757.pdf [2] https://gitlab.cs.fau.de/un65esoq/bpf-spectre/-/raw/53dc19fcf459c186613b1156a81504b39c8d49db/data/plots/23-02-26_23-56_bpftool/bpftool/0004-errors.pdf?inline=false Fixes: 01f810ace9ed ("bpf: Allow variable-offset stack access") Signed-off-by: Luis Gerhorst Signed-off-by: Daniel Borkmann Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230315165358.23701-1-gerhorst@cs.fau.de Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 232f720104cd..6876796a8de0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2775,17 +2775,13 @@ static int check_stack_read(struct bpf_verifier_env *env, } /* Variable offset is prohibited for unprivileged mode for simplicity * since it requires corresponding support in Spectre masking for stack - * ALU. See also retrieve_ptr_limit(). + * ALU. See also retrieve_ptr_limit(). The check in + * check_stack_access_for_ptr_arithmetic() called by + * adjust_ptr_min_max_vals() prevents users from creating stack pointers + * with variable offsets, therefore no check is required here. Further, + * just checking it here would be insufficient as speculative stack + * writes could still lead to unsafe speculative behaviour. */ - if (!env->bypass_spec_v1 && var_off) { - char tn_buf[48]; - - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "R%d variable offset stack access prohibited for !root, var_off=%s\n", - ptr_regno, tn_buf); - return -EACCES; - } - if (!var_off) { off += reg->var_off.value; err = check_stack_read_fixed_off(env, state, off, size, From ba6d56b20e8acb0d83020580ce28b1127e6d4b88 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Wed, 15 Mar 2023 08:33:02 -0700 Subject: [PATCH 2813/4345] vlan: partially enable SIOCSHWTSTAMP in container [ Upstream commit 731b73dba359e3ff00517c13aa0daa82b34ff466 ] Setting timestamp filter was explicitly disabled on vlan devices in containers because it might affect other processes on the host. But it's absolutely legit in case when real device is in the same namespace. Fixes: 873017af7784 ("vlan: disable SIOCSHWTSTAMP in container") Signed-off-by: Vadim Fedorenko Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/8021q/vlan_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 86a1c99025ea..929f85c6cf11 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -365,7 +365,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCSHWTSTAMP: - if (!net_eq(dev_net(dev), &init_net)) + if (!net_eq(dev_net(dev), dev_net(real_dev))) break; fallthrough; case SIOCGMIIPHY: From 8bb81a925a9fd1b14633653146530528ef297ce1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Mar 2023 01:10:06 +0000 Subject: [PATCH 2814/4345] net/packet: annotate accesses to po->xmit [ Upstream commit b9d83ab8a708f23a4001d60e9d8d0b3be3d9f607 ] po->xmit can be set from setsockopt(PACKET_QDISC_BYPASS), while read locklessly. Use READ_ONCE()/WRITE_ONCE() to avoid potential load/store tearing issues. Fixes: d346a3fae3ff ("packet: introduce PACKET_QDISC_BYPASS socket option") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/packet/af_packet.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3716797c5564..2b435d9916e6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -269,7 +269,8 @@ static void packet_cached_dev_reset(struct packet_sock *po) static bool packet_use_direct_xmit(const struct packet_sock *po) { - return po->xmit == packet_direct_xmit; + /* Paired with WRITE_ONCE() in packet_setsockopt() */ + return READ_ONCE(po->xmit) == packet_direct_xmit; } static u16 packet_pick_tx_queue(struct sk_buff *skb) @@ -2825,7 +2826,8 @@ tpacket_error: packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; - err = po->xmit(skb); + /* Paired with WRITE_ONCE() in packet_setsockopt() */ + err = READ_ONCE(po->xmit)(skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); @@ -3028,7 +3030,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) virtio_net_hdr_set_proto(skb, &vnet_hdr); } - err = po->xmit(skb); + /* Paired with WRITE_ONCE() in packet_setsockopt() */ + err = READ_ONCE(po->xmit)(skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); @@ -3979,7 +3982,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; - po->xmit = val ? packet_direct_xmit : dev_queue_xmit; + /* Paired with all lockless reads of po->xmit */ + WRITE_ONCE(po->xmit, val ? packet_direct_xmit : dev_queue_xmit); return 0; } default: From 5ca1be3658cda035ab82cfeeb93c6dadbed502c4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Mar 2023 01:10:07 +0000 Subject: [PATCH 2815/4345] net/packet: convert po->origdev to an atomic flag [ Upstream commit ee5675ecdf7a4e713ed21d98a70c2871d6ebed01 ] syzbot/KCAN reported that po->origdev can be read while another thread is changing its value. We can avoid this splat by converting this field to an actual bit. Following patches will convert remaining 1bit fields. Fixes: 80feaacb8a64 ("[AF_PACKET]: Add option to return orig_dev to userspace.") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/packet/af_packet.c | 10 ++++------ net/packet/diag.c | 2 +- net/packet/internal.h | 22 +++++++++++++++++++++- 3 files changed, 26 insertions(+), 8 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2b435d9916e6..df93f4b09ab9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2146,7 +2146,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, sll = &PACKET_SKB_CB(skb)->sa.ll; sll->sll_hatype = dev->type; sll->sll_pkttype = skb->pkt_type; - if (unlikely(po->origdev)) + if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; @@ -2419,7 +2419,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_hatype = dev->type; sll->sll_protocol = skb->protocol; sll->sll_pkttype = skb->pkt_type; - if (unlikely(po->origdev)) + if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; @@ -3883,9 +3883,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; - lock_sock(sk); - po->origdev = !!val; - release_sock(sk); + packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val); return 0; } case PACKET_VNET_HDR: @@ -4037,7 +4035,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, val = po->auxdata; break; case PACKET_ORIGDEV: - val = po->origdev; + val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); break; case PACKET_VNET_HDR: val = po->has_vnet_hdr; diff --git a/net/packet/diag.c b/net/packet/diag.c index 07812ae5ca07..e1ac9bb375b3 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -25,7 +25,7 @@ static int pdiag_put_info(const struct packet_sock *po, struct sk_buff *nlskb) pinfo.pdi_flags |= PDI_RUNNING; if (po->auxdata) pinfo.pdi_flags |= PDI_AUXDATA; - if (po->origdev) + if (packet_sock_flag(po, PACKET_SOCK_ORIGDEV)) pinfo.pdi_flags |= PDI_ORIGDEV; if (po->has_vnet_hdr) pinfo.pdi_flags |= PDI_VNETHDR; diff --git a/net/packet/internal.h b/net/packet/internal.h index 7af1e9179385..7fea453dc721 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -116,9 +116,9 @@ struct packet_sock { int copy_thresh; spinlock_t bind_lock; struct mutex pg_vec_lock; + unsigned long flags; unsigned int running; /* bind_lock must be held */ unsigned int auxdata:1, /* writer must hold sock lock */ - origdev:1, has_vnet_hdr:1, tp_loss:1, tp_tx_has_off:1; @@ -144,4 +144,24 @@ static struct packet_sock *pkt_sk(struct sock *sk) return (struct packet_sock *)sk; } +enum packet_sock_flags { + PACKET_SOCK_ORIGDEV, +}; + +static inline void packet_sock_flag_set(struct packet_sock *po, + enum packet_sock_flags flag, + bool val) +{ + if (val) + set_bit(flag, &po->flags); + else + clear_bit(flag, &po->flags); +} + +static inline bool packet_sock_flag(const struct packet_sock *po, + enum packet_sock_flags flag) +{ + return test_bit(flag, &po->flags); +} + #endif From 05c6db12aece625cd5de696c8b036c55d4ef8290 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Mar 2023 01:10:08 +0000 Subject: [PATCH 2816/4345] net/packet: convert po->auxdata to an atomic flag [ Upstream commit fd53c297aa7b077ae98a3d3d2d3aa278a1686ba6 ] po->auxdata can be read while another thread is changing its value, potentially raising KCSAN splat. Convert it to PACKET_SOCK_AUXDATA flag. Fixes: 8dc419447415 ("[PACKET]: Add optional checksum computation for recvmsg") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/packet/af_packet.c | 8 +++----- net/packet/diag.c | 2 +- net/packet/internal.h | 4 ++-- 3 files changed, 6 insertions(+), 8 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index df93f4b09ab9..9b6f6a5e0b14 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3485,7 +3485,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } - if (pkt_sk(sk)->auxdata) { + if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) { struct tpacket_auxdata aux; aux.tp_status = TP_STATUS_USER; @@ -3869,9 +3869,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; - lock_sock(sk); - po->auxdata = !!val; - release_sock(sk); + packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val); return 0; } case PACKET_ORIGDEV: @@ -4032,7 +4030,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, break; case PACKET_AUXDATA: - val = po->auxdata; + val = packet_sock_flag(po, PACKET_SOCK_AUXDATA); break; case PACKET_ORIGDEV: val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); diff --git a/net/packet/diag.c b/net/packet/diag.c index e1ac9bb375b3..d704c7bf51b2 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -23,7 +23,7 @@ static int pdiag_put_info(const struct packet_sock *po, struct sk_buff *nlskb) pinfo.pdi_flags = 0; if (po->running) pinfo.pdi_flags |= PDI_RUNNING; - if (po->auxdata) + if (packet_sock_flag(po, PACKET_SOCK_AUXDATA)) pinfo.pdi_flags |= PDI_AUXDATA; if (packet_sock_flag(po, PACKET_SOCK_ORIGDEV)) pinfo.pdi_flags |= PDI_ORIGDEV; diff --git a/net/packet/internal.h b/net/packet/internal.h index 7fea453dc721..3938cb413d5d 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -118,8 +118,7 @@ struct packet_sock { struct mutex pg_vec_lock; unsigned long flags; unsigned int running; /* bind_lock must be held */ - unsigned int auxdata:1, /* writer must hold sock lock */ - has_vnet_hdr:1, + unsigned int has_vnet_hdr:1, /* writer must hold sock lock */ tp_loss:1, tp_tx_has_off:1; int pressure; @@ -146,6 +145,7 @@ static struct packet_sock *pkt_sk(struct sock *sk) enum packet_sock_flags { PACKET_SOCK_ORIGDEV, + PACKET_SOCK_AUXDATA, }; static inline void packet_sock_flag_set(struct packet_sock *po, From 621c89a0216ac227a0fe146b42d60893f256c1fd Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Sun, 1 Nov 2020 00:32:08 +0100 Subject: [PATCH 2817/4345] scsi: target: Rename struct sense_info to sense_detail [ Upstream commit b455233dcc403e3eb955a642dd69b6676e12b245 ] This helps distinguish it from the SCSI sense INFORMATION field. Link: https://lore.kernel.org/r/20201031233211.5207-2-ddiss@suse.de Reviewed-by: Mike Christie Signed-off-by: David Disseldorp Signed-off-by: Martin K. Petersen Stable-dep-of: 673db054d7a2 ("scsi: target: Fix multiple LUN_RESET handling") Signed-off-by: Sasha Levin --- drivers/target/target_core_transport.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index bca3a32a4bfb..ce521d3d3047 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -3131,14 +3131,14 @@ bool transport_wait_for_tasks(struct se_cmd *cmd) } EXPORT_SYMBOL(transport_wait_for_tasks); -struct sense_info { +struct sense_detail { u8 key; u8 asc; u8 ascq; bool add_sector_info; }; -static const struct sense_info sense_info_table[] = { +static const struct sense_detail sense_detail_table[] = { [TCM_NO_SENSE] = { .key = NOT_READY }, @@ -3298,39 +3298,39 @@ static const struct sense_info sense_info_table[] = { */ static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason) { - const struct sense_info *si; + const struct sense_detail *sd; u8 *buffer = cmd->sense_buffer; int r = (__force int)reason; u8 key, asc, ascq; bool desc_format = target_sense_desc_format(cmd->se_dev); - if (r < ARRAY_SIZE(sense_info_table) && sense_info_table[r].key) - si = &sense_info_table[r]; + if (r < ARRAY_SIZE(sense_detail_table) && sense_detail_table[r].key) + sd = &sense_detail_table[r]; else - si = &sense_info_table[(__force int) + sd = &sense_detail_table[(__force int) TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE]; - key = si->key; + key = sd->key; if (reason == TCM_CHECK_CONDITION_UNIT_ATTENTION) { if (!core_scsi3_ua_for_check_condition(cmd, &key, &asc, &ascq)) { cmd->scsi_status = SAM_STAT_BUSY; return; } - } else if (si->asc == 0) { + } else if (sd->asc == 0) { WARN_ON_ONCE(cmd->scsi_asc == 0); asc = cmd->scsi_asc; ascq = cmd->scsi_ascq; } else { - asc = si->asc; - ascq = si->ascq; + asc = sd->asc; + ascq = sd->ascq; } cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE; cmd->scsi_status = SAM_STAT_CHECK_CONDITION; cmd->scsi_sense_length = TRANSPORT_SENSE_BUFFER; scsi_build_sense_buffer(desc_format, buffer, key, asc, ascq); - if (si->add_sector_info) + if (sd->add_sector_info) WARN_ON_ONCE(scsi_set_sense_information(buffer, cmd->scsi_sense_length, cmd->bad_sector) < 0); From 7c8a29f1b22e68978e0449ebb2e30a123074bea1 Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Sun, 1 Nov 2020 00:32:09 +0100 Subject: [PATCH 2818/4345] scsi: target: Rename cmd.bad_sector to cmd.sense_info [ Upstream commit 8dd992fb67f33a0777fb4bee1e22a5ee5530f024 ] cmd.bad_sector currently gets packed into the sense INFORMATION field for TCM_LOGICAL_BLOCK_{GUARD,APP_TAG,REF_TAG}_CHECK_FAILED errors, which carry an .add_sector_info flag in the sense_detail_table to ensure this. In preparation for propagating a byte offset on COMPARE AND WRITE TCM_MISCOMPARE_VERIFY error, rename cmd.bad_sector to cmd.sense_info and sense_detail.add_sector_info to sense_detail.add_sense_info so that it better reflects the sense INFORMATION field destination. [ddiss: update previously overlooked ib_isert] Link: https://lore.kernel.org/r/20201031233211.5207-3-ddiss@suse.de Reviewed-by: Mike Christie Signed-off-by: David Disseldorp Signed-off-by: Martin K. Petersen Stable-dep-of: 673db054d7a2 ("scsi: target: Fix multiple LUN_RESET handling") Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/isert/ib_isert.c | 4 ++-- drivers/target/target_core_sbc.c | 2 +- drivers/target/target_core_transport.c | 12 ++++++------ include/target/target_core_base.h | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index edea37da8a5b..2d0d966fba2c 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -1553,12 +1553,12 @@ isert_check_pi_status(struct se_cmd *se_cmd, struct ib_mr *sig_mr) } sec_offset_err = mr_status.sig_err.sig_err_offset; do_div(sec_offset_err, block_size); - se_cmd->bad_sector = sec_offset_err + se_cmd->t_task_lba; + se_cmd->sense_info = sec_offset_err + se_cmd->t_task_lba; isert_err("PI error found type %d at sector 0x%llx " "expected 0x%x vs actual 0x%x\n", mr_status.sig_err.err_type, - (unsigned long long)se_cmd->bad_sector, + (unsigned long long)se_cmd->sense_info, mr_status.sig_err.expected, mr_status.sig_err.actual); ret = 1; diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index eaf8551ebc61..47c5f26e6012 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -1438,7 +1438,7 @@ sbc_dif_verify(struct se_cmd *cmd, sector_t start, unsigned int sectors, if (rc) { kunmap_atomic(daddr - dsg->offset); kunmap_atomic(paddr - psg->offset); - cmd->bad_sector = sector; + cmd->sense_info = sector; return rc; } next: diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index ce521d3d3047..84d654c14917 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -3135,7 +3135,7 @@ struct sense_detail { u8 key; u8 asc; u8 ascq; - bool add_sector_info; + bool add_sense_info; }; static const struct sense_detail sense_detail_table[] = { @@ -3238,19 +3238,19 @@ static const struct sense_detail sense_detail_table[] = { .key = ABORTED_COMMAND, .asc = 0x10, .ascq = 0x01, /* LOGICAL BLOCK GUARD CHECK FAILED */ - .add_sector_info = true, + .add_sense_info = true, }, [TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED] = { .key = ABORTED_COMMAND, .asc = 0x10, .ascq = 0x02, /* LOGICAL BLOCK APPLICATION TAG CHECK FAILED */ - .add_sector_info = true, + .add_sense_info = true, }, [TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED] = { .key = ABORTED_COMMAND, .asc = 0x10, .ascq = 0x03, /* LOGICAL BLOCK REFERENCE TAG CHECK FAILED */ - .add_sector_info = true, + .add_sense_info = true, }, [TCM_COPY_TARGET_DEVICE_NOT_REACHABLE] = { .key = COPY_ABORTED, @@ -3330,10 +3330,10 @@ static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason) cmd->scsi_status = SAM_STAT_CHECK_CONDITION; cmd->scsi_sense_length = TRANSPORT_SENSE_BUFFER; scsi_build_sense_buffer(desc_format, buffer, key, asc, ascq); - if (sd->add_sector_info) + if (sd->add_sense_info) WARN_ON_ONCE(scsi_set_sense_information(buffer, cmd->scsi_sense_length, - cmd->bad_sector) < 0); + cmd->sense_info) < 0); } int diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 18a5dcd275f8..16992ba455de 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -540,7 +540,7 @@ struct se_cmd { struct scatterlist *t_prot_sg; unsigned int t_prot_nents; sense_reason_t pi_err; - sector_t bad_sector; + u64 sense_info; int cpuid; }; From 008b936bbde3e87a611b3828a0d5d2a4f99026a0 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 1 Nov 2020 12:59:33 -0600 Subject: [PATCH 2819/4345] scsi: target: Make state_list per CPU [ Upstream commit 1526d9f10c6184031e42afad0adbdde1213e8ad1 ] Do a state_list/execute_task_lock per CPU, so we can do submissions from different CPUs without contention with each other. Note: tcm_fc was passing TARGET_SCF_USE_CPUID, but never set cpuid. The assumption is that it wanted to set the cpuid to the CPU it was submitting from so it will get this behavior with this patch. [mkp: s/printk/pr_err/ + resolve COMPARE AND WRITE patch conflict] Link: https://lore.kernel.org/r/1604257174-4524-8-git-send-email-michael.christie@oracle.com Reviewed-by: Himanshu Madhani Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen Stable-dep-of: 673db054d7a2 ("scsi: target: Fix multiple LUN_RESET handling") Signed-off-by: Sasha Levin --- drivers/target/target_core_device.c | 16 ++- drivers/target/target_core_tmr.c | 138 +++++++++++++------------ drivers/target/target_core_transport.c | 27 +++-- drivers/target/tcm_fc/tfc_cmd.c | 2 +- include/target/target_core_base.h | 13 ++- 5 files changed, 112 insertions(+), 84 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 1eded5c4ebda..bd3f1192c75a 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -724,11 +724,24 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) { struct se_device *dev; struct se_lun *xcopy_lun; + int i; dev = hba->backend->ops->alloc_device(hba, name); if (!dev) return NULL; + dev->queues = kcalloc(nr_cpu_ids, sizeof(*dev->queues), GFP_KERNEL); + if (!dev->queues) { + dev->transport->free_device(dev); + return NULL; + } + + dev->queue_cnt = nr_cpu_ids; + for (i = 0; i < dev->queue_cnt; i++) { + INIT_LIST_HEAD(&dev->queues[i].state_list); + spin_lock_init(&dev->queues[i].lock); + } + dev->se_hba = hba; dev->transport = hba->backend->ops; dev->transport_flags = dev->transport->transport_flags_default; @@ -738,9 +751,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) INIT_LIST_HEAD(&dev->dev_sep_list); INIT_LIST_HEAD(&dev->dev_tmr_list); INIT_LIST_HEAD(&dev->delayed_cmd_list); - INIT_LIST_HEAD(&dev->state_list); INIT_LIST_HEAD(&dev->qf_cmd_list); - spin_lock_init(&dev->execute_task_lock); spin_lock_init(&dev->delayed_cmd_lock); spin_lock_init(&dev->dev_reservation_lock); spin_lock_init(&dev->se_port_lock); @@ -1014,6 +1025,7 @@ void target_free_device(struct se_device *dev) if (dev->transport->free_prot) dev->transport->free_prot(dev); + kfree(dev->queues); dev->transport->free_device(dev); } diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 3efd5a3bd69d..5da384bb88c8 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -121,57 +121,61 @@ void core_tmr_abort_task( unsigned long flags; bool rc; u64 ref_tag; + int i; - spin_lock_irqsave(&dev->execute_task_lock, flags); - list_for_each_entry_safe(se_cmd, next, &dev->state_list, state_list) { + for (i = 0; i < dev->queue_cnt; i++) { + spin_lock_irqsave(&dev->queues[i].lock, flags); + list_for_each_entry_safe(se_cmd, next, &dev->queues[i].state_list, + state_list) { + if (se_sess != se_cmd->se_sess) + continue; - if (se_sess != se_cmd->se_sess) - continue; + /* + * skip task management functions, including + * tmr->task_cmd + */ + if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) + continue; - /* skip task management functions, including tmr->task_cmd */ - if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) - continue; + ref_tag = se_cmd->tag; + if (tmr->ref_task_tag != ref_tag) + continue; - ref_tag = se_cmd->tag; - if (tmr->ref_task_tag != ref_tag) - continue; + pr_err("ABORT_TASK: Found referenced %s task_tag: %llu\n", + se_cmd->se_tfo->fabric_name, ref_tag); - printk("ABORT_TASK: Found referenced %s task_tag: %llu\n", - se_cmd->se_tfo->fabric_name, ref_tag); + spin_lock(&se_sess->sess_cmd_lock); + rc = __target_check_io_state(se_cmd, se_sess, 0); + spin_unlock(&se_sess->sess_cmd_lock); + if (!rc) + continue; - spin_lock(&se_sess->sess_cmd_lock); - rc = __target_check_io_state(se_cmd, se_sess, 0); - spin_unlock(&se_sess->sess_cmd_lock); - if (!rc) - continue; + list_move_tail(&se_cmd->state_list, &aborted_list); + se_cmd->state_active = false; + spin_unlock_irqrestore(&dev->queues[i].lock, flags); - list_move_tail(&se_cmd->state_list, &aborted_list); - se_cmd->state_active = false; + /* + * Ensure that this ABORT request is visible to the LU + * RESET code. + */ + if (!tmr->tmr_dev) + WARN_ON_ONCE(transport_lookup_tmr_lun(tmr->task_cmd) < 0); - spin_unlock_irqrestore(&dev->execute_task_lock, flags); + if (dev->transport->tmr_notify) + dev->transport->tmr_notify(dev, TMR_ABORT_TASK, + &aborted_list); - /* - * Ensure that this ABORT request is visible to the LU RESET - * code. - */ - if (!tmr->tmr_dev) - WARN_ON_ONCE(transport_lookup_tmr_lun(tmr->task_cmd) < - 0); + list_del_init(&se_cmd->state_list); + target_put_cmd_and_wait(se_cmd); - if (dev->transport->tmr_notify) - dev->transport->tmr_notify(dev, TMR_ABORT_TASK, - &aborted_list); - - list_del_init(&se_cmd->state_list); - target_put_cmd_and_wait(se_cmd); - - printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for" - " ref_tag: %llu\n", ref_tag); - tmr->response = TMR_FUNCTION_COMPLETE; - atomic_long_inc(&dev->aborts_complete); - return; + pr_err("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for ref_tag: %llu\n", + ref_tag); + tmr->response = TMR_FUNCTION_COMPLETE; + atomic_long_inc(&dev->aborts_complete); + return; + } + spin_unlock_irqrestore(&dev->queues[i].lock, flags); } - spin_unlock_irqrestore(&dev->execute_task_lock, flags); if (dev->transport->tmr_notify) dev->transport->tmr_notify(dev, TMR_ABORT_TASK, &aborted_list); @@ -273,7 +277,7 @@ static void core_tmr_drain_state_list( struct se_session *sess; struct se_cmd *cmd, *next; unsigned long flags; - int rc; + int rc, i; /* * Complete outstanding commands with TASK_ABORTED SAM status. @@ -297,35 +301,39 @@ static void core_tmr_drain_state_list( * Note that this seems to be independent of TAS (Task Aborted Status) * in the Control Mode Page. */ - spin_lock_irqsave(&dev->execute_task_lock, flags); - list_for_each_entry_safe(cmd, next, &dev->state_list, state_list) { - /* - * For PREEMPT_AND_ABORT usage, only process commands - * with a matching reservation key. - */ - if (target_check_cdb_and_preempt(preempt_and_abort_list, cmd)) - continue; + for (i = 0; i < dev->queue_cnt; i++) { + spin_lock_irqsave(&dev->queues[i].lock, flags); + list_for_each_entry_safe(cmd, next, &dev->queues[i].state_list, + state_list) { + /* + * For PREEMPT_AND_ABORT usage, only process commands + * with a matching reservation key. + */ + if (target_check_cdb_and_preempt(preempt_and_abort_list, + cmd)) + continue; - /* - * Not aborting PROUT PREEMPT_AND_ABORT CDB.. - */ - if (prout_cmd == cmd) - continue; + /* + * Not aborting PROUT PREEMPT_AND_ABORT CDB.. + */ + if (prout_cmd == cmd) + continue; - sess = cmd->se_sess; - if (WARN_ON_ONCE(!sess)) - continue; + sess = cmd->se_sess; + if (WARN_ON_ONCE(!sess)) + continue; - spin_lock(&sess->sess_cmd_lock); - rc = __target_check_io_state(cmd, tmr_sess, tas); - spin_unlock(&sess->sess_cmd_lock); - if (!rc) - continue; + spin_lock(&sess->sess_cmd_lock); + rc = __target_check_io_state(cmd, tmr_sess, tas); + spin_unlock(&sess->sess_cmd_lock); + if (!rc) + continue; - list_move_tail(&cmd->state_list, &drain_task_list); - cmd->state_active = false; + list_move_tail(&cmd->state_list, &drain_task_list); + cmd->state_active = false; + } + spin_unlock_irqrestore(&dev->queues[i].lock, flags); } - spin_unlock_irqrestore(&dev->execute_task_lock, flags); if (dev->transport->tmr_notify) dev->transport->tmr_notify(dev, preempt_and_abort_list ? diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 84d654c14917..230fffa993c0 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -650,12 +650,12 @@ static void target_remove_from_state_list(struct se_cmd *cmd) if (!dev) return; - spin_lock_irqsave(&dev->execute_task_lock, flags); + spin_lock_irqsave(&dev->queues[cmd->cpuid].lock, flags); if (cmd->state_active) { list_del(&cmd->state_list); cmd->state_active = false; } - spin_unlock_irqrestore(&dev->execute_task_lock, flags); + spin_unlock_irqrestore(&dev->queues[cmd->cpuid].lock, flags); } /* @@ -866,10 +866,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) INIT_WORK(&cmd->work, success ? target_complete_ok_work : target_complete_failure_work); - if (cmd->se_cmd_flags & SCF_USE_CPUID) - queue_work_on(cmd->cpuid, target_completion_wq, &cmd->work); - else - queue_work(target_completion_wq, &cmd->work); + queue_work_on(cmd->cpuid, target_completion_wq, &cmd->work); } EXPORT_SYMBOL(target_complete_cmd); @@ -904,12 +901,13 @@ static void target_add_to_state_list(struct se_cmd *cmd) struct se_device *dev = cmd->se_dev; unsigned long flags; - spin_lock_irqsave(&dev->execute_task_lock, flags); + spin_lock_irqsave(&dev->queues[cmd->cpuid].lock, flags); if (!cmd->state_active) { - list_add_tail(&cmd->state_list, &dev->state_list); + list_add_tail(&cmd->state_list, + &dev->queues[cmd->cpuid].state_list); cmd->state_active = true; } - spin_unlock_irqrestore(&dev->execute_task_lock, flags); + spin_unlock_irqrestore(&dev->queues[cmd->cpuid].lock, flags); } /* @@ -1397,6 +1395,9 @@ void transport_init_se_cmd( cmd->sense_buffer = sense_buffer; cmd->orig_fe_lun = unpacked_lun; + if (!(cmd->se_cmd_flags & SCF_USE_CPUID)) + cmd->cpuid = smp_processor_id(); + cmd->state_active = false; } EXPORT_SYMBOL(transport_init_se_cmd); @@ -1614,6 +1615,9 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess BUG_ON(!se_tpg); BUG_ON(se_cmd->se_tfo || se_cmd->se_sess); BUG_ON(in_interrupt()); + + if (flags & TARGET_SCF_USE_CPUID) + se_cmd->se_cmd_flags |= SCF_USE_CPUID; /* * Initialize se_cmd for target operation. From this point * exceptions are handled by sending exception status via @@ -1623,11 +1627,6 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess data_length, data_dir, task_attr, sense, unpacked_lun); - if (flags & TARGET_SCF_USE_CPUID) - se_cmd->se_cmd_flags |= SCF_USE_CPUID; - else - se_cmd->cpuid = WORK_CPU_UNBOUND; - if (flags & TARGET_SCF_UNKNOWN_SIZE) se_cmd->unknown_data_length = 1; /* diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index a7ed56602c6c..8936a094f846 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -551,7 +551,7 @@ static void ft_send_work(struct work_struct *work) if (target_submit_cmd(&cmd->se_cmd, cmd->sess->se_sess, fcp->fc_cdb, &cmd->ft_sense_buffer[0], scsilun_to_int(&fcp->fc_lun), ntohl(fcp->fc_dl), task_attr, data_dir, - TARGET_SCF_ACK_KREF | TARGET_SCF_USE_CPUID)) + TARGET_SCF_ACK_KREF)) goto err; pr_debug("r_ctl %x target_submit_cmd %p\n", fh->fh_r_ctl, cmd); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 16992ba455de..0109adcdfa0b 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -541,6 +541,10 @@ struct se_cmd { unsigned int t_prot_nents; sense_reason_t pi_err; u64 sense_info; + /* + * CPU LIO will execute the cmd on. Defaults to the CPU the cmd is + * initialized on. Drivers can override. + */ int cpuid; }; @@ -761,6 +765,11 @@ struct se_dev_stat_grps { struct config_group scsi_lu_group; }; +struct se_device_queue { + struct list_head state_list; + spinlock_t lock; +}; + struct se_device { /* RELATIVE TARGET PORT IDENTIFER Counter */ u16 dev_rpti_counter; @@ -794,7 +803,6 @@ struct se_device { atomic_t dev_qf_count; u32 export_count; spinlock_t delayed_cmd_lock; - spinlock_t execute_task_lock; spinlock_t dev_reservation_lock; unsigned int dev_reservation_flags; #define DRF_SPC2_RESERVATIONS 0x00000001 @@ -814,7 +822,6 @@ struct se_device { struct work_struct qf_work_queue; struct work_struct delayed_cmd_work; struct list_head delayed_cmd_list; - struct list_head state_list; struct list_head qf_cmd_list; /* Pointer to associated SE HBA */ struct se_hba *se_hba; @@ -841,6 +848,8 @@ struct se_device { /* For se_lun->lun_se_dev RCU read-side critical access */ u32 hba_index; struct rcu_head rcu_head; + int queue_cnt; + struct se_device_queue *queues; }; struct se_hba { From e1f59cd18a10969d08a082264b557876ca38766e Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sat, 18 Mar 2023 20:56:18 -0500 Subject: [PATCH 2820/4345] scsi: target: Fix multiple LUN_RESET handling [ Upstream commit 673db054d7a2b5a470d7a25baf65956d005ad729 ] This fixes a bug where an initiator thinks a LUN_RESET has cleaned up running commands when it hasn't. The bug was added in commit 51ec502a3266 ("target: Delete tmr from list before processing"). The problem occurs when: 1. We have N I/O cmds running in the target layer spread over 2 sessions. 2. The initiator sends a LUN_RESET for each session. 3. session1's LUN_RESET loops over all the running commands from both sessions and moves them to its local drain_task_list. 4. session2's LUN_RESET does not see the LUN_RESET from session1 because the commit above has it remove itself. session2 also does not see any commands since the other reset moved them off the state lists. 5. sessions2's LUN_RESET will then complete with a successful response. 6. sessions2's inititor believes the running commands on its session are now cleaned up due to the successful response and cleans up the running commands from its side. It then restarts them. 7. The commands do eventually complete on the backend and the target starts to return aborted task statuses for them. The initiator will either throw a invalid ITT error or might accidentally lookup a new task if the ITT has been reallocated already. Fix the bug by reverting the patch, and serialize the execution of LUN_RESETs and Preempt and Aborts. Also prevent us from waiting on LUN_RESETs in core_tmr_drain_tmr_list, because it turns out the original patch fixed a bug that was not mentioned. For LUN_RESET1 core_tmr_drain_tmr_list can see a second LUN_RESET and wait on it. Then the second reset will run core_tmr_drain_tmr_list and see the first reset and wait on it resulting in a deadlock. Fixes: 51ec502a3266 ("target: Delete tmr from list before processing") Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230319015620.96006-8-michael.christie@oracle.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/target_core_device.c | 1 + drivers/target/target_core_tmr.c | 26 +++++++++++++++++++++++--- include/target/target_core_base.h | 1 + 3 files changed, 25 insertions(+), 3 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index bd3f1192c75a..4664330fb55d 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -770,6 +770,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) spin_lock_init(&dev->t10_alua.lba_map_lock); INIT_WORK(&dev->delayed_cmd_work, target_do_delayed_work); + mutex_init(&dev->lun_reset_mutex); dev->t10_wwn.t10_dev = dev; dev->t10_alua.t10_dev = dev; diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 5da384bb88c8..a2b18a98d671 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -202,14 +202,23 @@ static void core_tmr_drain_tmr_list( * LUN_RESET tmr.. */ spin_lock_irqsave(&dev->se_tmr_lock, flags); - if (tmr) - list_del_init(&tmr->tmr_list); list_for_each_entry_safe(tmr_p, tmr_pp, &dev->dev_tmr_list, tmr_list) { + if (tmr_p == tmr) + continue; + cmd = tmr_p->task_cmd; if (!cmd) { pr_err("Unable to locate struct se_cmd for TMR\n"); continue; } + + /* + * We only execute one LUN_RESET at a time so we can't wait + * on them below. + */ + if (tmr_p->function == TMR_LUN_RESET) + continue; + /* * If this function was called with a valid pr_res_key * parameter (eg: for PROUT PREEMPT_AND_ABORT service action @@ -390,14 +399,25 @@ int core_tmr_lun_reset( tmr_nacl->initiatorname); } } + + + /* + * We only allow one reset or preempt and abort to execute at a time + * to prevent one call from claiming all the cmds causing a second + * call from returning while cmds it should have waited on are still + * running. + */ + mutex_lock(&dev->lun_reset_mutex); + pr_debug("LUN_RESET: %s starting for [%s], tas: %d\n", (preempt_and_abort_list) ? "Preempt" : "TMR", dev->transport->name, tas); - core_tmr_drain_tmr_list(dev, tmr, preempt_and_abort_list); core_tmr_drain_state_list(dev, prout_cmd, tmr_sess, tas, preempt_and_abort_list); + mutex_unlock(&dev->lun_reset_mutex); + /* * Clear any legacy SPC-2 reservation when called during * LOGICAL UNIT RESET diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 0109adcdfa0b..e681c712fcca 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -850,6 +850,7 @@ struct se_device { struct rcu_head rcu_head; int queue_cnt; struct se_device_queue *queues; + struct mutex lun_reset_mutex; }; struct se_hba { From bfe67e05632751e9d904d9addc8f361ea2e6e788 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sat, 18 Mar 2023 20:56:19 -0500 Subject: [PATCH 2821/4345] scsi: target: iscsit: Fix TAS handling during conn cleanup [ Upstream commit cc79da306ebb2edb700c3816b90219223182ac3c ] Fix a bug added in commit f36199355c64 ("scsi: target: iscsi: Fix cmd abort fabric stop race"). If CMD_T_TAS is set on the se_cmd we must call iscsit_free_cmd() to do the last put on the cmd and free it, because the connection is down and we will not up sending the response and doing the put from the normal I/O path. Add a check for CMD_T_TAS in iscsit_release_commands_from_conn() so we now detect this case and run iscsit_free_cmd(). Fixes: f36199355c64 ("scsi: target: iscsi: Fix cmd abort fabric stop race") Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230319015620.96006-9-michael.christie@oracle.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/iscsi/iscsi_target.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index a237f1cf9bd6..6bb840358072 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4084,9 +4084,12 @@ static void iscsit_release_commands_from_conn(struct iscsi_conn *conn) list_for_each_entry_safe(cmd, cmd_tmp, &tmp_list, i_conn_node) { struct se_cmd *se_cmd = &cmd->se_cmd; - if (se_cmd->se_tfo != NULL) { - spin_lock_irq(&se_cmd->t_state_lock); - if (se_cmd->transport_state & CMD_T_ABORTED) { + if (!se_cmd->se_tfo) + continue; + + spin_lock_irq(&se_cmd->t_state_lock); + if (se_cmd->transport_state & CMD_T_ABORTED) { + if (!(se_cmd->transport_state & CMD_T_TAS)) /* * LIO's abort path owns the cleanup for this, * so put it back on the list and let @@ -4094,11 +4097,10 @@ static void iscsit_release_commands_from_conn(struct iscsi_conn *conn) */ list_move_tail(&cmd->i_conn_node, &conn->conn_cmd_list); - } else { - se_cmd->transport_state |= CMD_T_FABRIC_STOP; - } - spin_unlock_irq(&se_cmd->t_state_lock); + } else { + se_cmd->transport_state |= CMD_T_FABRIC_STOP; } + spin_unlock_irq(&se_cmd->t_state_lock); } spin_unlock_bh(&conn->cmd_lock); From 202048ec1ee531bdef179c32d54bb51d26bfff5b Mon Sep 17 00:00:00 2001 From: Danila Chernetsov Date: Fri, 17 Mar 2023 17:51:09 +0000 Subject: [PATCH 2822/4345] scsi: megaraid: Fix mega_cmd_done() CMDID_INT_CMDS [ Upstream commit 75cb113cd43f06aaf4f1bda0069cfd5b98e909eb ] When cmdid == CMDID_INT_CMDS, the 'cmds' pointer is NULL but is dereferenced below. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 0f2bb84d2a68 ("[SCSI] megaraid: simplify internal command handling") Signed-off-by: Danila Chernetsov Link: https://lore.kernel.org/r/20230317175109.18585-1-listdansp@mail.ru Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/megaraid.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index daffa36988ae..810d80340676 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -1443,6 +1443,7 @@ mega_cmd_done(adapter_t *adapter, u8 completed[], int nstatus, int status) */ if (cmdid == CMDID_INT_CMDS) { scb = &adapter->int_scb; + cmd = scb->cmd; list_del_init(&scb->list); scb->state = SCB_FREE; From c3a1914b96784e9c9125732ca036072ef4b948eb Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Tue, 21 Feb 2023 22:45:50 +0800 Subject: [PATCH 2823/4345] f2fs: handle dqget error in f2fs_transfer_project_quota() [ Upstream commit 8051692f5f23260215bfe9a72e712d93606acc5f ] We should set the error code when dqget() failed. Fixes: 2c1d03056991 ("f2fs: support F2FS_IOC_FS{GET,SET}XATTR") Signed-off-by: Yangtao Li Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/file.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index d56fcace1821..a0d8aa52b696 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3013,15 +3013,16 @@ int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid) struct dquot *transfer_to[MAXQUOTAS] = {}; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct super_block *sb = sbi->sb; - int err = 0; + int err; transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); - if (!IS_ERR(transfer_to[PRJQUOTA])) { - err = __dquot_transfer(inode, transfer_to); - if (err) - set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); - dqput(transfer_to[PRJQUOTA]); - } + if (IS_ERR(transfer_to[PRJQUOTA])) + return PTR_ERR(transfer_to[PRJQUOTA]); + + err = __dquot_transfer(inode, transfer_to); + if (err) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + dqput(transfer_to[PRJQUOTA]); return err; } From d420c4a06d8f3dc3dc34ff96cc298125e53dd5ac Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 28 Jun 2022 10:57:24 -0700 Subject: [PATCH 2824/4345] f2fs: enforce single zone capacity [ Upstream commit b771aadc6e4c221a468fe4a2dfcfffec01a06722 ] In order to simplify the complicated per-zone capacity, let's support only one capacity for entire zoned device. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Stable-dep-of: 0b37ed21e336 ("f2fs: apply zone capacity to all zone type") Signed-off-by: Sasha Levin --- fs/f2fs/f2fs.h | 2 +- fs/f2fs/segment.c | 19 ++++++------------- fs/f2fs/segment.h | 3 +++ fs/f2fs/super.c | 33 ++++++++++++--------------------- 4 files changed, 22 insertions(+), 35 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index c03fdda1bddf..62b7848f1f71 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1153,7 +1153,6 @@ struct f2fs_dev_info { #ifdef CONFIG_BLK_DEV_ZONED unsigned int nr_blkz; /* Total number of zones */ unsigned long *blkz_seq; /* Bitmap indicating sequential zones */ - block_t *zone_capacity_blocks; /* Array of zone capacity in blks */ #endif }; @@ -1422,6 +1421,7 @@ struct f2fs_sb_info { unsigned int meta_ino_num; /* meta inode number*/ unsigned int log_blocks_per_seg; /* log2 blocks per segment */ unsigned int blocks_per_seg; /* blocks per segment */ + unsigned int unusable_blocks_per_sec; /* unusable blocks per section */ unsigned int segs_per_sec; /* segments per section */ unsigned int secs_per_zone; /* sections per zone */ unsigned int total_sections; /* total section count */ diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 7c90d93f4e43..5305913fe0d5 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -4982,7 +4982,7 @@ static unsigned int get_zone_idx(struct f2fs_sb_info *sbi, unsigned int secno, static inline unsigned int f2fs_usable_zone_segs_in_sec( struct f2fs_sb_info *sbi, unsigned int segno) { - unsigned int dev_idx, zone_idx, unusable_segs_in_sec; + unsigned int dev_idx, zone_idx; dev_idx = f2fs_target_device_index(sbi, START_BLOCK(sbi, segno)); zone_idx = get_zone_idx(sbi, GET_SEC_FROM_SEG(sbi, segno), dev_idx); @@ -4991,18 +4991,12 @@ static inline unsigned int f2fs_usable_zone_segs_in_sec( if (is_conv_zone(sbi, zone_idx, dev_idx)) return sbi->segs_per_sec; - /* - * If the zone_capacity_blocks array is NULL, then zone capacity - * is equal to the zone size for all zones - */ - if (!FDEV(dev_idx).zone_capacity_blocks) + if (!sbi->unusable_blocks_per_sec) return sbi->segs_per_sec; /* Get the segment count beyond zone capacity block */ - unusable_segs_in_sec = (sbi->blocks_per_blkz - - FDEV(dev_idx).zone_capacity_blocks[zone_idx]) >> - sbi->log_blocks_per_seg; - return sbi->segs_per_sec - unusable_segs_in_sec; + return sbi->segs_per_sec - (sbi->unusable_blocks_per_sec >> + sbi->log_blocks_per_seg); } /* @@ -5031,12 +5025,11 @@ static inline unsigned int f2fs_usable_zone_blks_in_seg( if (is_conv_zone(sbi, zone_idx, dev_idx)) return sbi->blocks_per_seg; - if (!FDEV(dev_idx).zone_capacity_blocks) + if (!sbi->unusable_blocks_per_sec) return sbi->blocks_per_seg; sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno)); - sec_cap_blkaddr = sec_start_blkaddr + - FDEV(dev_idx).zone_capacity_blocks[zone_idx]; + sec_cap_blkaddr = sec_start_blkaddr + CAP_BLKS_PER_SEC(sbi); /* * If segment starts before zone capacity and spans beyond diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index eafd89f0c77e..aca6c9a3aad0 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -101,6 +101,9 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, GET_SEGNO_FROM_SEG0(sbi, blk_addr))) #define BLKS_PER_SEC(sbi) \ ((sbi)->segs_per_sec * (sbi)->blocks_per_seg) +#define CAP_BLKS_PER_SEC(sbi) \ + ((sbi)->segs_per_sec * (sbi)->blocks_per_seg - \ + (sbi)->unusable_blocks_per_sec) #define GET_SEC_FROM_SEG(sbi, segno) \ (((segno) == -1) ? -1: (segno) / (sbi)->segs_per_sec) #define GET_SEG_FROM_SEC(sbi, secno) \ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 0bba5c72fc77..9a74d60f61db 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1242,7 +1242,6 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) blkdev_put(FDEV(i).bdev, FMODE_EXCL); #ifdef CONFIG_BLK_DEV_ZONED kvfree(FDEV(i).blkz_seq); - kfree(FDEV(i).zone_capacity_blocks); #endif } kvfree(sbi->devs); @@ -3199,24 +3198,29 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) #ifdef CONFIG_BLK_DEV_ZONED struct f2fs_report_zones_args { + struct f2fs_sb_info *sbi; struct f2fs_dev_info *dev; - bool zone_cap_mismatch; }; static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct f2fs_report_zones_args *rz_args = data; + block_t unusable_blocks = (zone->len - zone->capacity) >> + F2FS_LOG_SECTORS_PER_BLOCK; if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) return 0; set_bit(idx, rz_args->dev->blkz_seq); - rz_args->dev->zone_capacity_blocks[idx] = zone->capacity >> - F2FS_LOG_SECTORS_PER_BLOCK; - if (zone->len != zone->capacity && !rz_args->zone_cap_mismatch) - rz_args->zone_cap_mismatch = true; - + if (!rz_args->sbi->unusable_blocks_per_sec) { + rz_args->sbi->unusable_blocks_per_sec = unusable_blocks; + return 0; + } + if (rz_args->sbi->unusable_blocks_per_sec != unusable_blocks) { + f2fs_err(rz_args->sbi, "F2FS supports single zone capacity\n"); + return -EINVAL; + } return 0; } @@ -3250,26 +3254,13 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) if (!FDEV(devi).blkz_seq) return -ENOMEM; - /* Get block zones type and zone-capacity */ - FDEV(devi).zone_capacity_blocks = f2fs_kzalloc(sbi, - FDEV(devi).nr_blkz * sizeof(block_t), - GFP_KERNEL); - if (!FDEV(devi).zone_capacity_blocks) - return -ENOMEM; - + rep_zone_arg.sbi = sbi; rep_zone_arg.dev = &FDEV(devi); - rep_zone_arg.zone_cap_mismatch = false; ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, f2fs_report_zone_cb, &rep_zone_arg); if (ret < 0) return ret; - - if (!rep_zone_arg.zone_cap_mismatch) { - kfree(FDEV(devi).zone_capacity_blocks); - FDEV(devi).zone_capacity_blocks = NULL; - } - return 0; } #endif From d11a74577c21cf6dc1db65b6178ef3d03953ccf0 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 21 Mar 2023 15:58:04 -0700 Subject: [PATCH 2825/4345] f2fs: apply zone capacity to all zone type [ Upstream commit 0b37ed21e3367539b79284e0b0af2246ffcf0dca ] If we manage the zone capacity per zone type, it'll break the GC assumption. And, the current logic complains valid block count mismatch. Let's apply zone capacity to all zone type, if specified. Fixes: de881df97768 ("f2fs: support zone capacity less than zone size") Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/segment.c | 65 +++-------------------------------------------- fs/f2fs/segment.h | 3 +++ 2 files changed, 7 insertions(+), 61 deletions(-) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 5305913fe0d5..a27a93429271 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -4957,48 +4957,6 @@ int f2fs_check_write_pointer(struct f2fs_sb_info *sbi) return 0; } -static bool is_conv_zone(struct f2fs_sb_info *sbi, unsigned int zone_idx, - unsigned int dev_idx) -{ - if (!bdev_is_zoned(FDEV(dev_idx).bdev)) - return true; - return !test_bit(zone_idx, FDEV(dev_idx).blkz_seq); -} - -/* Return the zone index in the given device */ -static unsigned int get_zone_idx(struct f2fs_sb_info *sbi, unsigned int secno, - int dev_idx) -{ - block_t sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno)); - - return (sec_start_blkaddr - FDEV(dev_idx).start_blk) >> - sbi->log_blocks_per_blkz; -} - -/* - * Return the usable segments in a section based on the zone's - * corresponding zone capacity. Zone is equal to a section. - */ -static inline unsigned int f2fs_usable_zone_segs_in_sec( - struct f2fs_sb_info *sbi, unsigned int segno) -{ - unsigned int dev_idx, zone_idx; - - dev_idx = f2fs_target_device_index(sbi, START_BLOCK(sbi, segno)); - zone_idx = get_zone_idx(sbi, GET_SEC_FROM_SEG(sbi, segno), dev_idx); - - /* Conventional zone's capacity is always equal to zone size */ - if (is_conv_zone(sbi, zone_idx, dev_idx)) - return sbi->segs_per_sec; - - if (!sbi->unusable_blocks_per_sec) - return sbi->segs_per_sec; - - /* Get the segment count beyond zone capacity block */ - return sbi->segs_per_sec - (sbi->unusable_blocks_per_sec >> - sbi->log_blocks_per_seg); -} - /* * Return the number of usable blocks in a segment. The number of blocks * returned is always equal to the number of blocks in a segment for @@ -5011,23 +4969,13 @@ static inline unsigned int f2fs_usable_zone_blks_in_seg( struct f2fs_sb_info *sbi, unsigned int segno) { block_t seg_start, sec_start_blkaddr, sec_cap_blkaddr; - unsigned int zone_idx, dev_idx, secno; - - secno = GET_SEC_FROM_SEG(sbi, segno); - seg_start = START_BLOCK(sbi, segno); - dev_idx = f2fs_target_device_index(sbi, seg_start); - zone_idx = get_zone_idx(sbi, secno, dev_idx); - - /* - * Conventional zone's capacity is always equal to zone size, - * so, blocks per segment is unchanged. - */ - if (is_conv_zone(sbi, zone_idx, dev_idx)) - return sbi->blocks_per_seg; + unsigned int secno; if (!sbi->unusable_blocks_per_sec) return sbi->blocks_per_seg; + secno = GET_SEC_FROM_SEG(sbi, segno); + seg_start = START_BLOCK(sbi, segno); sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno)); sec_cap_blkaddr = sec_start_blkaddr + CAP_BLKS_PER_SEC(sbi); @@ -5061,11 +5009,6 @@ static inline unsigned int f2fs_usable_zone_blks_in_seg(struct f2fs_sb_info *sbi return 0; } -static inline unsigned int f2fs_usable_zone_segs_in_sec(struct f2fs_sb_info *sbi, - unsigned int segno) -{ - return 0; -} #endif unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, unsigned int segno) @@ -5080,7 +5023,7 @@ unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, unsigned int segno) { if (f2fs_sb_has_blkzoned(sbi)) - return f2fs_usable_zone_segs_in_sec(sbi, segno); + return CAP_SEGS_PER_SEC(sbi); return sbi->segs_per_sec; } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index aca6c9a3aad0..979296b835b5 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -104,6 +104,9 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, #define CAP_BLKS_PER_SEC(sbi) \ ((sbi)->segs_per_sec * (sbi)->blocks_per_seg - \ (sbi)->unusable_blocks_per_sec) +#define CAP_SEGS_PER_SEC(sbi) \ + ((sbi)->segs_per_sec - ((sbi)->unusable_blocks_per_sec >>\ + (sbi)->log_blocks_per_seg)) #define GET_SEC_FROM_SEG(sbi, segno) \ (((segno) == -1) ? -1: (segno) / (sbi)->segs_per_sec) #define GET_SEG_FROM_SEC(sbi, secno) \ From a8226a45b2a9ce83ba7a167a387a00fecc319e71 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Tue, 21 Mar 2023 01:22:18 +0800 Subject: [PATCH 2826/4345] f2fs: compress: fix to call f2fs_wait_on_page_writeback() in f2fs_write_raw_pages() [ Upstream commit babedcbac164cec970872b8097401ca913a80e61 ] BUG_ON() will be triggered when writing files concurrently, because the same page is writtenback multiple times. 1597 void folio_end_writeback(struct folio *folio) 1598 { ...... 1618 if (!__folio_end_writeback(folio)) 1619 BUG(); ...... 1625 } kernel BUG at mm/filemap.c:1619! Call Trace: f2fs_write_end_io+0x1a0/0x370 blk_update_request+0x6c/0x410 blk_mq_end_request+0x15/0x130 blk_complete_reqs+0x3c/0x50 __do_softirq+0xb8/0x29b ? sort_range+0x20/0x20 run_ksoftirqd+0x19/0x20 smpboot_thread_fn+0x10b/0x1d0 kthread+0xde/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 Below is the concurrency scenario: [Process A] [Process B] [Process C] f2fs_write_raw_pages() - redirty_page_for_writepage() - unlock page() f2fs_do_write_data_page() - lock_page() - clear_page_dirty_for_io() - set_page_writeback() [1st writeback] ..... - unlock page() generic_perform_write() - f2fs_write_begin() - wait_for_stable_page() - f2fs_write_end() - set_page_dirty() - lock_page() - f2fs_do_write_data_page() - set_page_writeback() [2st writeback] This problem was introduced by the previous commit 7377e853967b ("f2fs: compress: fix potential deadlock of compress file"). All pagelocks were released in f2fs_write_raw_pages(), but whether the page was in the writeback state was ignored in the subsequent writing process. Let's fix it by waiting for the page to writeback before writing. Cc: Christoph Hellwig Fixes: 4c8ff7095bef ("f2fs: support data compression") Fixes: 7377e853967b ("f2fs: compress: fix potential deadlock of compress file") Signed-off-by: Qi Han Signed-off-by: Yangtao Li Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/compress.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 1541da5ace85..1be9de40f0b5 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1391,6 +1391,12 @@ continue_unlock: if (!PageDirty(cc->rpages[i])) goto continue_unlock; + if (PageWriteback(cc->rpages[i])) { + if (wbc->sync_mode == WB_SYNC_NONE) + goto continue_unlock; + f2fs_wait_on_page_writeback(cc->rpages[i], DATA, true, true); + } + if (!clear_page_dirty_for_io(cc->rpages[i])) goto continue_unlock; From de3908e1515224b0e65cdfbe246eda933be3cdbf Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 21 Mar 2023 07:59:30 +0100 Subject: [PATCH 2827/4345] crypto: caam - Clear some memory in instantiate_rng [ Upstream commit 9c19fb86a8cb2ee82a832c95e139f29ea05c4d08 ] According to the comment at the end of the 'for' loop just a few lines below, it looks needed to clear 'desc'. So it should also be cleared for the first iteration. Move the memset() to the beginning of the loop to be safe. Fixes: 281922a1d4f5 ("crypto: caam - add support for SEC v5.x RNG4") Signed-off-by: Christophe JAILLET Reviewed-by: Gaurav Jain Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/caam/ctrl.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index f87aa2169e5f..f9a1ec3c8485 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -284,6 +284,10 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask, const u32 rdsta_if = RDSTA_IF0 << sh_idx; const u32 rdsta_pr = RDSTA_PR0 << sh_idx; const u32 rdsta_mask = rdsta_if | rdsta_pr; + + /* Clear the contents before using the descriptor */ + memset(desc, 0x00, CAAM_CMD_SZ * 7); + /* * If the corresponding bit is set, this state handle * was initialized by somebody else, so it's left alone. @@ -327,8 +331,6 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask, } dev_info(ctrldev, "Instantiated RNG4 SH%d\n", sh_idx); - /* Clear the contents before recreating the descriptor */ - memset(desc, 0x00, CAAM_CMD_SZ * 7); } kfree(desc); From adc2d82eee221bd9c36e0b17c857652fe27a871b Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 24 Mar 2023 20:28:12 +0530 Subject: [PATCH 2828/4345] crypto: sa2ul - Select CRYPTO_DES [ Upstream commit 8832023efd20966e29944dac92118dfbf1fa1bc0 ] The SA2UL Crypto driver provides support for couple of DES3 algos "cbc(des3_ede)" and "ecb(des3_ede)", and enabling the crypto selftest throws the following errors (as seen on K3 J721E SoCs): saul-crypto 4e00000.crypto: Error allocating fallback algo cbc(des3_ede) alg: skcipher: failed to allocate transform for cbc-des3-sa2ul: -2 saul-crypto 4e00000.crypto: Error allocating fallback algo ecb(des3_ede) alg: skcipher: failed to allocate transform for ecb-des3-sa2ul: -2 Fix this by selecting CRYPTO_DES which was missed while adding base driver support. Fixes: 7694b6ca649f ("crypto: sa2ul - Add crypto driver") Signed-off-by: Suman Anna Signed-off-by: Jayesh Choudhary Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 0a3dd0793f30..dbdee43c6ffc 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -897,6 +897,7 @@ config CRYPTO_DEV_SA2UL select CRYPTO_AES_ARM64 select CRYPTO_ALGAPI select CRYPTO_AUTHENC + select CRYPTO_DES select CRYPTO_SHA1 select CRYPTO_SHA256 select CRYPTO_SHA512 From c621697505b3aa12c261a272eac15a61ce7e643b Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Sun, 26 Mar 2023 05:31:38 +0000 Subject: [PATCH 2829/4345] wifi: rtlwifi: fix incorrect error codes in rtl_debugfs_set_write_rfreg() [ Upstream commit 905a9241e4e8c15d2c084fee916280514848fe35 ] If there is a failure during copy_from_user or user-provided data buffer is invalid, rtl_debugfs_set_write_rfreg should return negative error code instead of a positive value count. Fix this bug by returning correct error code. Moreover, the check of buffer against null is removed since it will be handled by copy_from_user. Fixes: 610247f46feb ("rtlwifi: Improve debugging by using debugfs") Signed-off-by: Wei Chen Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230326053138.91338-1-harperchen1110@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtlwifi/debug.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/debug.c b/drivers/net/wireless/realtek/rtlwifi/debug.c index 0b1bc04cb6ad..602717928887 100644 --- a/drivers/net/wireless/realtek/rtlwifi/debug.c +++ b/drivers/net/wireless/realtek/rtlwifi/debug.c @@ -375,8 +375,8 @@ static ssize_t rtl_debugfs_set_write_rfreg(struct file *filp, tmp_len = (count > sizeof(tmp) - 1 ? sizeof(tmp) - 1 : count); - if (!buffer || copy_from_user(tmp, buffer, tmp_len)) - return count; + if (copy_from_user(tmp, buffer, tmp_len)) + return -EFAULT; tmp[tmp_len] = '\0'; @@ -386,7 +386,7 @@ static ssize_t rtl_debugfs_set_write_rfreg(struct file *filp, if (num != 4) { rtl_dbg(rtlpriv, COMP_ERR, DBG_DMESG, "Format is \n"); - return count; + return -EINVAL; } rtl_set_rfreg(hw, path, addr, bitmask, data); From dc55805db254d7f9990cb5a49dd771e69e70c4ae Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Sun, 26 Mar 2023 05:42:17 +0000 Subject: [PATCH 2830/4345] wifi: rtlwifi: fix incorrect error codes in rtl_debugfs_set_write_reg() [ Upstream commit 5dbe1f8eb8c5ac69394400a5b86fd81775e96c43 ] If there is a failure during copy_from_user or user-provided data buffer is invalid, rtl_debugfs_set_write_reg should return negative error code instead of a positive value count. Fix this bug by returning correct error code. Moreover, the check of buffer against null is removed since it will be handled by copy_from_user. Fixes: 610247f46feb ("rtlwifi: Improve debugging by using debugfs") Signed-off-by: Wei Chen Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230326054217.93492-1-harperchen1110@gmail.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtlwifi/debug.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/debug.c b/drivers/net/wireless/realtek/rtlwifi/debug.c index 602717928887..9eb26dfe4ca9 100644 --- a/drivers/net/wireless/realtek/rtlwifi/debug.c +++ b/drivers/net/wireless/realtek/rtlwifi/debug.c @@ -278,8 +278,8 @@ static ssize_t rtl_debugfs_set_write_reg(struct file *filp, tmp_len = (count > sizeof(tmp) - 1 ? sizeof(tmp) - 1 : count); - if (!buffer || copy_from_user(tmp, buffer, tmp_len)) - return count; + if (copy_from_user(tmp, buffer, tmp_len)) + return -EFAULT; tmp[tmp_len] = '\0'; @@ -287,7 +287,7 @@ static ssize_t rtl_debugfs_set_write_reg(struct file *filp, num = sscanf(tmp, "%x %x %x", &addr, &val, &len); if (num != 3) - return count; + return -EINVAL; switch (len) { case 1: From d64a12eeb4a6316616a7b08fbdab54edb665049f Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 3 Apr 2023 17:43:16 +0200 Subject: [PATCH 2831/4345] net: qrtr: correct types of trace event parameters [ Upstream commit 054fbf7ff8143d35ca7d3bb5414bb44ee1574194 ] The arguments passed to the trace events are of type unsigned int, however the signature of the events used __le32 parameters. I may be missing the point here, but sparse flagged this and it does seem incorrect to me. net/qrtr/ns.c: note: in included file (through include/trace/trace_events.h, include/trace/define_trace.h, include/trace/events/qrtr.h): ./include/trace/events/qrtr.h:11:1: warning: cast to restricted __le32 ./include/trace/events/qrtr.h:11:1: warning: restricted __le32 degrades to integer ./include/trace/events/qrtr.h:11:1: warning: restricted __le32 degrades to integer ... (a lot more similar warnings) net/qrtr/ns.c:115:47: expected restricted __le32 [usertype] service net/qrtr/ns.c:115:47: got unsigned int service net/qrtr/ns.c:115:61: warning: incorrect type in argument 2 (different base types) ... (a lot more similar warnings) Fixes: dfddb54043f0 ("net: qrtr: Add tracepoint support") Reviewed-by: Manivannan Sadhasivam Signed-off-by: Simon Horman Link: https://lore.kernel.org/r/20230402-qrtr-trace-types-v1-1-92ad55008dd3@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/trace/events/qrtr.h | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) diff --git a/include/trace/events/qrtr.h b/include/trace/events/qrtr.h index b1de14c3bb93..441132c67133 100644 --- a/include/trace/events/qrtr.h +++ b/include/trace/events/qrtr.h @@ -10,15 +10,16 @@ TRACE_EVENT(qrtr_ns_service_announce_new, - TP_PROTO(__le32 service, __le32 instance, __le32 node, __le32 port), + TP_PROTO(unsigned int service, unsigned int instance, + unsigned int node, unsigned int port), TP_ARGS(service, instance, node, port), TP_STRUCT__entry( - __field(__le32, service) - __field(__le32, instance) - __field(__le32, node) - __field(__le32, port) + __field(unsigned int, service) + __field(unsigned int, instance) + __field(unsigned int, node) + __field(unsigned int, port) ), TP_fast_assign( @@ -36,15 +37,16 @@ TRACE_EVENT(qrtr_ns_service_announce_new, TRACE_EVENT(qrtr_ns_service_announce_del, - TP_PROTO(__le32 service, __le32 instance, __le32 node, __le32 port), + TP_PROTO(unsigned int service, unsigned int instance, + unsigned int node, unsigned int port), TP_ARGS(service, instance, node, port), TP_STRUCT__entry( - __field(__le32, service) - __field(__le32, instance) - __field(__le32, node) - __field(__le32, port) + __field(unsigned int, service) + __field(unsigned int, instance) + __field(unsigned int, node) + __field(unsigned int, port) ), TP_fast_assign( @@ -62,15 +64,16 @@ TRACE_EVENT(qrtr_ns_service_announce_del, TRACE_EVENT(qrtr_ns_server_add, - TP_PROTO(__le32 service, __le32 instance, __le32 node, __le32 port), + TP_PROTO(unsigned int service, unsigned int instance, + unsigned int node, unsigned int port), TP_ARGS(service, instance, node, port), TP_STRUCT__entry( - __field(__le32, service) - __field(__le32, instance) - __field(__le32, node) - __field(__le32, port) + __field(unsigned int, service) + __field(unsigned int, instance) + __field(unsigned int, node) + __field(unsigned int, port) ), TP_fast_assign( From 072d16abf567d46dc0e9ee62cfad3793ab81ef10 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Wed, 5 Apr 2023 19:33:54 +0000 Subject: [PATCH 2832/4345] selftests/bpf: Wait for receive in cg_storage_multi test [ Upstream commit 5af607a861d43ffff830fc1890033e579ec44799 ] In some cases the loopback latency might be large enough, causing the assertion on invocations to be run before ingress prog getting executed. The assertion would fail and the test would flake. This can be reliably reproduced by arbitrarily increasing the loopback latency (thanks to [1]): tc qdisc add dev lo root handle 1: htb default 12 tc class add dev lo parent 1:1 classid 1:12 htb rate 20kbps ceil 20kbps tc qdisc add dev lo parent 1:12 netem delay 100ms Fix this by waiting on the receive end, instead of instantly returning to the assert. The call to read() will wait for the default SO_RCVTIMEO timeout of 3 seconds provided by start_server(). [1] https://gist.github.com/kstevens715/4598301 Reported-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/9c5c8b7e-1d89-a3af-5400-14fde81f4429@linux.dev/ Fixes: 3573f384014f ("selftests/bpf: Test CGROUP_STORAGE behavior on shared egress + ingress") Acked-by: Stanislav Fomichev Signed-off-by: YiFei Zhu Link: https://lore.kernel.org/r/20230405193354.1956209-1-zhuyifei@google.com Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c index 643dfa35419c..48dc5827daa7 100644 --- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c @@ -56,8 +56,9 @@ static bool assert_storage_noexist(struct bpf_map *map, const void *key) static bool connect_send(const char *cgroup_path) { - bool res = true; int server_fd = -1, client_fd = -1; + char message[] = "message"; + bool res = true; if (join_cgroup(cgroup_path)) goto out_clean; @@ -70,7 +71,10 @@ static bool connect_send(const char *cgroup_path) if (client_fd < 0) goto out_clean; - if (send(client_fd, "message", strlen("message"), 0) < 0) + if (send(client_fd, &message, sizeof(message), 0) < 0) + goto out_clean; + + if (read(server_fd, &message, sizeof(message)) < 0) goto out_clean; res = false; From 27942f477d1069adab3f6c45f59146bc9379dd45 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Wed, 5 Apr 2023 14:21:15 +0100 Subject: [PATCH 2833/4345] bpftool: Fix bug for long instructions in program CFG dumps [ Upstream commit 67cf52cdb6c8fa6365d29106555dacf95c9fd374 ] When dumping the control flow graphs for programs using the 16-byte long load instruction, we need to skip the second part of this instruction when looking for the next instruction to process. Otherwise, we end up printing "BUG_ld_00" from the kernel disassembler in the CFG. Fixes: efcef17a6d65 ("tools: bpftool: generate .dot graph from CFG information") Signed-off-by: Quentin Monnet Link: https://lore.kernel.org/r/20230405132120.59886-3-quentin@isovalent.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- tools/bpf/bpftool/xlated_dumper.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 8608cd68cdd0..13d614b16f6c 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -363,8 +363,15 @@ void dump_xlated_for_graph(struct dump_data *dd, void *buf_start, void *buf_end, struct bpf_insn *insn_start = buf_start; struct bpf_insn *insn_end = buf_end; struct bpf_insn *cur = insn_start; + bool double_insn = false; for (; cur <= insn_end; cur++) { + if (double_insn) { + double_insn = false; + continue; + } + double_insn = cur->code == (BPF_LD | BPF_IMM | BPF_DW); + printf("% 4d: ", (int)(cur - insn_start + start_idx)); print_bpf_insn(&cbs, cur, true); if (cur != insn_end) From 9dbdedd44ff42fbbcd6235f3aa89aeb291f2355c Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Mon, 15 Nov 2021 15:18:08 +0100 Subject: [PATCH 2834/4345] crypto: drbg - make drbg_prepare_hrng() handle jent instantiation errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 559edd47cce4cc407d606b4d7f376822816fd4b8 ] Now that drbg_prepare_hrng() doesn't do anything but to instantiate a jitterentropy crypto_rng instance, it looks a little odd to have the related error handling at its only caller, drbg_instantiate(). Move the handling of jitterentropy allocation failures from drbg_instantiate() close to the allocation itself in drbg_prepare_hrng(). There is no change in behaviour. Signed-off-by: Nicolai Stange Reviewed-by: Stephan Müller Signed-off-by: Herbert Xu Stable-dep-of: 686cd976b6dd ("crypto: drbg - Only fail when jent is unavailable in FIPS mode") Signed-off-by: Sasha Levin --- crypto/drbg.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/crypto/drbg.c b/crypto/drbg.c index a4b5d6dbe99d..ecc6b167b89e 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -1515,6 +1515,14 @@ static int drbg_prepare_hrng(struct drbg_state *drbg) return 0; drbg->jent = crypto_alloc_rng("jitterentropy_rng", 0, 0); + if (IS_ERR(drbg->jent)) { + const int err = PTR_ERR(drbg->jent); + + drbg->jent = NULL; + if (fips_enabled || err != -ENOENT) + return err; + pr_info("DRBG: Continuing without Jitter RNG\n"); + } return 0; } @@ -1570,14 +1578,6 @@ static int drbg_instantiate(struct drbg_state *drbg, struct drbg_string *pers, if (ret) goto free_everything; - if (IS_ERR(drbg->jent)) { - ret = PTR_ERR(drbg->jent); - drbg->jent = NULL; - if (fips_enabled || ret != -ENOENT) - goto free_everything; - pr_info("DRBG: Continuing without Jitter RNG\n"); - } - reseed = false; } From 2a67bc52cd3f0783ac412d8007ae7bdd04911b10 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 28 Mar 2023 11:35:23 +0800 Subject: [PATCH 2835/4345] crypto: drbg - Only fail when jent is unavailable in FIPS mode [ Upstream commit 686cd976b6ddedeeb1a1fb09ba53a891d3cc9a03 ] When jent initialisation fails for any reason other than ENOENT, the entire drbg fails to initialise, even when we're not in FIPS mode. This is wrong because we can still use the kernel RNG when we're not in FIPS mode. Change it so that it only fails when we are in FIPS mode. Fixes: 57225e679788 ("crypto: drbg - Use callback API for random readiness") Signed-off-by: Herbert Xu Reviewed-by: Stephan Mueller Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- crypto/drbg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crypto/drbg.c b/crypto/drbg.c index ecc6b167b89e..ba1fa5cdd90a 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -1519,7 +1519,7 @@ static int drbg_prepare_hrng(struct drbg_state *drbg) const int err = PTR_ERR(drbg->jent); drbg->jent = NULL; - if (fips_enabled || err != -ENOENT) + if (fips_enabled) return err; pr_info("DRBG: Continuing without Jitter RNG\n"); } From 5877980dc2e47119a14cf084159672317d4dd6b7 Mon Sep 17 00:00:00 2001 From: Kal Conley Date: Thu, 6 Apr 2023 01:59:18 +0200 Subject: [PATCH 2836/4345] xsk: Fix unaligned descriptor validation [ Upstream commit d769ccaf957fe7391f357c0a923de71f594b8a2b ] Make sure unaligned descriptors that straddle the end of the UMEM are considered invalid. Currently, descriptor validation is broken for zero-copy mode which only checks descriptors at page granularity. For example, descriptors in zero-copy mode that overrun the end of the UMEM but not a page boundary are (incorrectly) considered valid. The UMEM boundary check needs to happen before the page boundary and contiguity checks in xp_desc_crosses_non_contig_pg(). Do this check in xp_unaligned_validate_desc() instead like xp_check_unaligned() already does. Fixes: 2b43470add8c ("xsk: Introduce AF_XDP buffer allocation API") Signed-off-by: Kal Conley Acked-by: Magnus Karlsson Link: https://lore.kernel.org/r/20230405235920.7305-2-kal.conley@dectris.com Signed-off-by: Martin KaFai Lau Signed-off-by: Sasha Levin --- include/net/xsk_buff_pool.h | 9 ++------- net/xdp/xsk_queue.h | 1 + 2 files changed, 3 insertions(+), 7 deletions(-) diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index c9a47d3d8f50..5a63e3b12335 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -150,13 +150,8 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, if (likely(!cross_pg)) return false; - if (pool->dma_pages_cnt) { - return !(pool->dma_pages[addr >> PAGE_SHIFT] & - XSK_NEXT_PG_CONTIG_MASK); - } - - /* skb path */ - return addr + len > pool->addrs_cnt; + return pool->dma_pages_cnt && + !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr) diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 3c7ce60fe9a5..a76d43787549 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -155,6 +155,7 @@ static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool, return false; if (base_addr >= pool->addrs_cnt || addr >= pool->addrs_cnt || + addr + desc->len > pool->addrs_cnt || xp_desc_crosses_non_contig_pg(pool, addr, desc->len)) return false; From b2f423fda64fb49213aa0ed5056079cf295a5df2 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 10 Apr 2023 10:14:02 +0800 Subject: [PATCH 2837/4345] f2fs: fix to avoid use-after-free for cached IPU bio [ Upstream commit 5cdb422c839134273866208dad5360835ddb9794 ] xfstest generic/019 reports a bug: kernel BUG at mm/filemap.c:1619! RIP: 0010:folio_end_writeback+0x8a/0x90 Call Trace: end_page_writeback+0x1c/0x60 f2fs_write_end_io+0x199/0x420 bio_endio+0x104/0x180 submit_bio_noacct+0xa5/0x510 submit_bio+0x48/0x80 f2fs_submit_write_bio+0x35/0x300 f2fs_submit_merged_ipu_write+0x2a0/0x2b0 f2fs_write_single_data_page+0x838/0x8b0 f2fs_write_cache_pages+0x379/0xa30 f2fs_write_data_pages+0x30c/0x340 do_writepages+0xd8/0x1b0 __writeback_single_inode+0x44/0x370 writeback_sb_inodes+0x233/0x4d0 __writeback_inodes_wb+0x56/0xf0 wb_writeback+0x1dd/0x2d0 wb_workfn+0x367/0x4a0 process_one_work+0x21d/0x430 worker_thread+0x4e/0x3c0 kthread+0x103/0x130 ret_from_fork+0x2c/0x50 The root cause is: after cp_error is set, f2fs_submit_merged_ipu_write() in f2fs_write_single_data_page() tries to flush IPU bio in cache, however f2fs_submit_merged_ipu_write() missed to check validity of @bio parameter, result in submitting random cached bio which belong to other IO context, then it will cause use-after-free issue, fix it by adding additional validity check. Fixes: 0b20fcec8651 ("f2fs: cache global IPU bio") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/data.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index db26e87b8f0d..e9481c940895 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -849,6 +849,8 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, bool found = false; struct bio *target = bio ? *bio : NULL; + f2fs_bug_on(sbi, !target && !page); + for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) { struct f2fs_bio_info *io = sbi->write_io[DATA] + temp; struct list_head *head = &io->bio_list; @@ -2917,7 +2919,8 @@ out: if (unlikely(f2fs_cp_error(sbi))) { f2fs_submit_merged_write(sbi, DATA); - f2fs_submit_merged_ipu_write(sbi, bio, NULL); + if (bio && *bio) + f2fs_submit_merged_ipu_write(sbi, bio, NULL); submitted = NULL; } From bab8dc38b1a0a12bc064fc064269033bdcf5b88e Mon Sep 17 00:00:00 2001 From: Shuchang Li Date: Tue, 4 Apr 2023 15:21:32 +0800 Subject: [PATCH 2838/4345] scsi: lpfc: Fix ioremap issues in lpfc_sli4_pci_mem_setup() [ Upstream commit 91a0c0c1413239d0548b5aac4c82f38f6d53a91e ] When if_type equals zero and pci_resource_start(pdev, PCI_64BIT_BAR4) returns false, drbl_regs_memmap_p is not remapped. This passes a NULL pointer to iounmap(), which can trigger a WARN() on certain arches. When if_type equals six and pci_resource_start(pdev, PCI_64BIT_BAR4) returns true, drbl_regs_memmap_p may has been remapped and ctrl_regs_memmap_p is not remapped. This is a resource leak and passes a NULL pointer to iounmap(). To fix these issues, we need to add null checks before iounmap(), and change some goto labels. Fixes: 1351e69fc6db ("scsi: lpfc: Add push-to-adapter support to sli4") Signed-off-by: Shuchang Li Link: https://lore.kernel.org/r/20230404072133.1022-1-lishuchang@hust.edu.cn Reviewed-by: Justin Tee Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_init.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 17200b453cbb..1bb3c96a04bd 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -10477,7 +10477,7 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) goto out_iounmap_all; } else { error = -ENOMEM; - goto out_iounmap_all; + goto out_iounmap_ctrl; } } @@ -10495,7 +10495,7 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) dev_err(&pdev->dev, "ioremap failed for SLI4 HBA dpp registers.\n"); error = -ENOMEM; - goto out_iounmap_ctrl; + goto out_iounmap_all; } phba->pci_bar4_memmap_p = phba->sli4_hba.dpp_regs_memmap_p; } @@ -10520,9 +10520,11 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) return 0; out_iounmap_all: - iounmap(phba->sli4_hba.drbl_regs_memmap_p); + if (phba->sli4_hba.drbl_regs_memmap_p) + iounmap(phba->sli4_hba.drbl_regs_memmap_p); out_iounmap_ctrl: - iounmap(phba->sli4_hba.ctrl_regs_memmap_p); + if (phba->sli4_hba.ctrl_regs_memmap_p) + iounmap(phba->sli4_hba.ctrl_regs_memmap_p); out_iounmap_conf: iounmap(phba->sli4_hba.conf_regs_memmap_p); From 2be04fa7ee8567ef0d2e1c48b5bcd8d445709a99 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 7 Apr 2023 18:11:29 +0200 Subject: [PATCH 2839/4345] net: ethernet: stmmac: dwmac-rk: fix optional phy regulator handling [ Upstream commit db21973263f8c56750cb610f1d5e8bee00a513b9 ] The usual devm_regulator_get() call already handles "optional" regulators by returning a valid dummy and printing a warning that the dummy regulator should be described properly. This code open coded the same behaviour, but masked any errors that are not -EPROBE_DEFER and is quite noisy. This change effectively unmasks and propagates regulators errors not involving -ENODEV, downgrades the error print to warning level if no regulator is specified and captures the probe defer message for /sys/kernel/debug/devices_deferred. Fixes: 2e12f536635f ("net: stmmac: dwmac-rk: Use standard devicetree property for phy regulator") Signed-off-by: Sebastian Reichel Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index e7fbc9b30bf9..d0d47d91b460 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1194,9 +1194,6 @@ static int phy_power_on(struct rk_priv_data *bsp_priv, bool enable) int ret; struct device *dev = &bsp_priv->pdev->dev; - if (!ldo) - return 0; - if (enable) { ret = regulator_enable(ldo); if (ret) @@ -1227,14 +1224,11 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, of_get_phy_mode(dev->of_node, &bsp_priv->phy_iface); bsp_priv->ops = ops; - bsp_priv->regulator = devm_regulator_get_optional(dev, "phy"); + bsp_priv->regulator = devm_regulator_get(dev, "phy"); if (IS_ERR(bsp_priv->regulator)) { - if (PTR_ERR(bsp_priv->regulator) == -EPROBE_DEFER) { - dev_err(dev, "phy regulator is not available yet, deferred probing\n"); - return ERR_PTR(-EPROBE_DEFER); - } - dev_err(dev, "no regulator found\n"); - bsp_priv->regulator = NULL; + ret = PTR_ERR(bsp_priv->regulator); + dev_err_probe(dev, ret, "failed to get phy regulator\n"); + return ERR_PTR(ret); } ret = of_property_read_string(dev->of_node, "clock_in_out", &strings); From 2f9307222227410453e33654f5d9ed6459351455 Mon Sep 17 00:00:00 2001 From: Xin Liu Date: Thu, 6 Apr 2023 20:26:22 +0800 Subject: [PATCH 2840/4345] bpf, sockmap: fix deadlocks in the sockhash and sockmap [ Upstream commit ed17aa92dc56b6d8883e4b7a8f1c6fbf5ed6cd29 ] When huang uses sched_switch tracepoint, the tracepoint does only one thing in the mounted ebpf program, which deletes the fixed elements in sockhash ([0]) It seems that elements in sockhash are rarely actively deleted by users or ebpf program. Therefore, we do not pay much attention to their deletion. Compared with hash maps, sockhash only provides spin_lock_bh protection. This causes it to appear to have self-locking behavior in the interrupt context. [0]:https://lore.kernel.org/all/CABcoxUayum5oOqFMMqAeWuS8+EzojquSOSyDA3J_2omY=2EeAg@mail.gmail.com/ Reported-by: Hsin-Wei Hung Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Xin Liu Acked-by: John Fastabend Link: https://lore.kernel.org/r/20230406122622.109978-1-liuxin350@huawei.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- net/core/sock_map.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index ee5d3f49b0b5..e21adbbb7461 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -423,8 +423,9 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, { struct sock *sk; int err = 0; + unsigned long flags; - raw_spin_lock_bh(&stab->lock); + raw_spin_lock_irqsave(&stab->lock, flags); sk = *psk; if (!sk_test || sk_test == sk) sk = xchg(psk, NULL); @@ -434,7 +435,7 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, else err = -EINVAL; - raw_spin_unlock_bh(&stab->lock); + raw_spin_unlock_irqrestore(&stab->lock, flags); return err; } @@ -956,11 +957,12 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; int ret = -ENOENT; + unsigned long flags; hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); - raw_spin_lock_bh(&bucket->lock); + raw_spin_lock_irqsave(&bucket->lock, flags); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); if (elem) { hlist_del_rcu(&elem->node); @@ -968,7 +970,7 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) sock_hash_free_elem(htab, elem); ret = 0; } - raw_spin_unlock_bh(&bucket->lock); + raw_spin_unlock_irqrestore(&bucket->lock, flags); return ret; } From a9e3d9bac9633e8ce038b6ed05ab8ebc5ddfbe55 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 8 Jun 2022 11:52:21 -0700 Subject: [PATCH 2841/4345] nvme: handle the persistent internal error AER [ Upstream commit 2c61c97fb12b806e1c8eb15f04c277ad097ec95e ] In the NVM Express Revision 1.4 spec, Figure 145 describes possible values for an AER with event type "Error" (value 000b). For a Persistent Internal Error (value 03h), the host should perform a controller reset. Add support for this error using code that already exists for doing a controller reset. As part of this support, introduce two utility functions for parsing the AER type and subtype. This new support was tested in a lab environment where we can generate the persistent internal error on demand, and observe both the Linux side and NVMe controller side to see that the controller reset has been done. Signed-off-by: Michael Kelley Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe Stable-dep-of: 6622b76fe922 ("nvme: fix async event trace event") Signed-off-by: Sasha Levin --- drivers/nvme/host/core.c | 31 +++++++++++++++++++++++++++++-- include/linux/nvme.h | 4 ++++ 2 files changed, 33 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index a4b6aa932a8f..cb3f807ede1b 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4416,9 +4416,19 @@ static void nvme_fw_act_work(struct work_struct *work) nvme_get_fw_slot_info(ctrl); } +static u32 nvme_aer_type(u32 result) +{ + return result & 0x7; +} + +static u32 nvme_aer_subtype(u32 result) +{ + return (result & 0xff00) >> 8; +} + static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) { - u32 aer_notice_type = (result & 0xff00) >> 8; + u32 aer_notice_type = nvme_aer_subtype(result); trace_nvme_async_event(ctrl, aer_notice_type); @@ -4451,11 +4461,19 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) } } +static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl) +{ + trace_nvme_async_event(ctrl, NVME_AER_ERROR); + dev_warn(ctrl->device, "resetting controller due to AER\n"); + nvme_reset_ctrl(ctrl); +} + void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, volatile union nvme_result *res) { u32 result = le32_to_cpu(res->u32); - u32 aer_type = result & 0x07; + u32 aer_type = nvme_aer_type(result); + u32 aer_subtype = nvme_aer_subtype(result); if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS) return; @@ -4465,6 +4483,15 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, nvme_handle_aen_notice(ctrl, result); break; case NVME_AER_ERROR: + /* + * For a persistent internal error, don't run async_event_work + * to submit a new AER. The controller reset will do it. + */ + if (aer_subtype == NVME_AER_ERROR_PERSIST_INT_ERR) { + nvme_handle_aer_persistent_error(ctrl); + return; + } + fallthrough; case NVME_AER_SMART: case NVME_AER_CSS: case NVME_AER_VS: diff --git a/include/linux/nvme.h b/include/linux/nvme.h index fe39ed9e9303..f454dd100334 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -602,6 +602,10 @@ enum { NVME_AER_VS = 7, }; +enum { + NVME_AER_ERROR_PERSIST_INT_ERR = 0x03, +}; + enum { NVME_AER_NOTICE_NS_CHANGED = 0x00, NVME_AER_NOTICE_FW_ACT_STARTING = 0x01, From e119d1918303505ac9b6dd263a46a7e09d6f1684 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 5 Apr 2023 14:57:20 -0700 Subject: [PATCH 2842/4345] nvme: fix async event trace event [ Upstream commit 6622b76fe922b94189499a90ccdb714a4a8d0773 ] Mixing AER Event Type and Event Info has masking clashes. Just print the event type, but also include the event info of the AER result in the trace. Fixes: 09bd1ff4b15143b ("nvme-core: add async event trace helper") Reported-by: Nate Thornton Reviewed-by: Sagi Grimberg Reviewed-by: Minwoo Im Reviewed-by: Chaitanya Kulkarni Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/core.c | 5 +---- drivers/nvme/host/trace.h | 15 ++++++--------- 2 files changed, 7 insertions(+), 13 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index cb3f807ede1b..07c41a149328 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4430,8 +4430,6 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) { u32 aer_notice_type = nvme_aer_subtype(result); - trace_nvme_async_event(ctrl, aer_notice_type); - switch (aer_notice_type) { case NVME_AER_NOTICE_NS_CHANGED: set_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events); @@ -4463,7 +4461,6 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl) { - trace_nvme_async_event(ctrl, NVME_AER_ERROR); dev_warn(ctrl->device, "resetting controller due to AER\n"); nvme_reset_ctrl(ctrl); } @@ -4478,6 +4475,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS) return; + trace_nvme_async_event(ctrl, result); switch (aer_type) { case NVME_AER_NOTICE: nvme_handle_aen_notice(ctrl, result); @@ -4495,7 +4493,6 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, case NVME_AER_SMART: case NVME_AER_CSS: case NVME_AER_VS: - trace_nvme_async_event(ctrl, aer_type); ctrl->aen_result = result; break; default: diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h index aa8b0f86b2be..b258f7b8788e 100644 --- a/drivers/nvme/host/trace.h +++ b/drivers/nvme/host/trace.h @@ -127,15 +127,12 @@ TRACE_EVENT(nvme_async_event, ), TP_printk("nvme%d: NVME_AEN=%#08x [%s]", __entry->ctrl_id, __entry->result, - __print_symbolic(__entry->result, - aer_name(NVME_AER_NOTICE_NS_CHANGED), - aer_name(NVME_AER_NOTICE_ANA), - aer_name(NVME_AER_NOTICE_FW_ACT_STARTING), - aer_name(NVME_AER_NOTICE_DISC_CHANGED), - aer_name(NVME_AER_ERROR), - aer_name(NVME_AER_SMART), - aer_name(NVME_AER_CSS), - aer_name(NVME_AER_VS)) + __print_symbolic(__entry->result & 0x7, + aer_name(NVME_AER_ERROR), + aer_name(NVME_AER_SMART), + aer_name(NVME_AER_NOTICE), + aer_name(NVME_AER_CSS), + aer_name(NVME_AER_VS)) ) ); From 21f2503d37eeb18e975e494cd09378a38d9d81f0 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 12 Apr 2023 16:49:04 +0800 Subject: [PATCH 2843/4345] nvme-fcloop: fix "inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage" [ Upstream commit 4f86a6ff6fbd891232dda3ca97fd1b9630b59809 ] fcloop_fcp_op() could be called from flush request's ->end_io(flush_end_io) in which the spinlock of fq->mq_flush_lock is grabbed with irq saved/disabled. So fcloop_fcp_op() can't call spin_unlock_irq(&tfcp_req->reqlock) simply which enables irq unconditionally. Fixes the warning by switching to spin_lock_irqsave()/spin_unlock_irqrestore() Fixes: c38dbbfab1bc ("nvme-fcloop: fix inconsistent lock state warnings") Reported-by: Yi Zhang Signed-off-by: Ming Lei Reviewed-by: Ewan D. Milne Tested-by: Yi Zhang Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/target/fcloop.c | 48 ++++++++++++++++++++---------------- 1 file changed, 27 insertions(+), 21 deletions(-) diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 3da067a8311e..80a208fb34f5 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -570,10 +570,11 @@ fcloop_fcp_recv_work(struct work_struct *work) struct fcloop_fcpreq *tfcp_req = container_of(work, struct fcloop_fcpreq, fcp_rcv_work); struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq; + unsigned long flags; int ret = 0; bool aborted = false; - spin_lock_irq(&tfcp_req->reqlock); + spin_lock_irqsave(&tfcp_req->reqlock, flags); switch (tfcp_req->inistate) { case INI_IO_START: tfcp_req->inistate = INI_IO_ACTIVE; @@ -582,11 +583,11 @@ fcloop_fcp_recv_work(struct work_struct *work) aborted = true; break; default: - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); WARN_ON(1); return; } - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); if (unlikely(aborted)) ret = -ECANCELED; @@ -607,8 +608,9 @@ fcloop_fcp_abort_recv_work(struct work_struct *work) container_of(work, struct fcloop_fcpreq, abort_rcv_work); struct nvmefc_fcp_req *fcpreq; bool completed = false; + unsigned long flags; - spin_lock_irq(&tfcp_req->reqlock); + spin_lock_irqsave(&tfcp_req->reqlock, flags); fcpreq = tfcp_req->fcpreq; switch (tfcp_req->inistate) { case INI_IO_ABORTED: @@ -617,11 +619,11 @@ fcloop_fcp_abort_recv_work(struct work_struct *work) completed = true; break; default: - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); WARN_ON(1); return; } - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); if (unlikely(completed)) { /* remove reference taken in original abort downcall */ @@ -633,9 +635,9 @@ fcloop_fcp_abort_recv_work(struct work_struct *work) nvmet_fc_rcv_fcp_abort(tfcp_req->tport->targetport, &tfcp_req->tgt_fcp_req); - spin_lock_irq(&tfcp_req->reqlock); + spin_lock_irqsave(&tfcp_req->reqlock, flags); tfcp_req->fcpreq = NULL; - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); fcloop_call_host_done(fcpreq, tfcp_req, -ECANCELED); /* call_host_done releases reference for abort downcall */ @@ -651,11 +653,12 @@ fcloop_tgt_fcprqst_done_work(struct work_struct *work) struct fcloop_fcpreq *tfcp_req = container_of(work, struct fcloop_fcpreq, tio_done_work); struct nvmefc_fcp_req *fcpreq; + unsigned long flags; - spin_lock_irq(&tfcp_req->reqlock); + spin_lock_irqsave(&tfcp_req->reqlock, flags); fcpreq = tfcp_req->fcpreq; tfcp_req->inistate = INI_IO_COMPLETED; - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); fcloop_call_host_done(fcpreq, tfcp_req, tfcp_req->status); } @@ -759,13 +762,14 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport, u32 rsplen = 0, xfrlen = 0; int fcp_err = 0, active, aborted; u8 op = tgt_fcpreq->op; + unsigned long flags; - spin_lock_irq(&tfcp_req->reqlock); + spin_lock_irqsave(&tfcp_req->reqlock, flags); fcpreq = tfcp_req->fcpreq; active = tfcp_req->active; aborted = tfcp_req->aborted; tfcp_req->active = true; - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); if (unlikely(active)) /* illegal - call while i/o active */ @@ -773,9 +777,9 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport, if (unlikely(aborted)) { /* target transport has aborted i/o prior */ - spin_lock_irq(&tfcp_req->reqlock); + spin_lock_irqsave(&tfcp_req->reqlock, flags); tfcp_req->active = false; - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); tgt_fcpreq->transferred_length = 0; tgt_fcpreq->fcp_error = -ECANCELED; tgt_fcpreq->done(tgt_fcpreq); @@ -832,9 +836,9 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport, break; } - spin_lock_irq(&tfcp_req->reqlock); + spin_lock_irqsave(&tfcp_req->reqlock, flags); tfcp_req->active = false; - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); tgt_fcpreq->transferred_length = xfrlen; tgt_fcpreq->fcp_error = fcp_err; @@ -848,15 +852,16 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *tgt_fcpreq) { struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq); + unsigned long flags; /* * mark aborted only in case there were 2 threads in transport * (one doing io, other doing abort) and only kills ops posted * after the abort request */ - spin_lock_irq(&tfcp_req->reqlock); + spin_lock_irqsave(&tfcp_req->reqlock, flags); tfcp_req->aborted = true; - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); tfcp_req->status = NVME_SC_INTERNAL; @@ -898,6 +903,7 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport, struct fcloop_ini_fcpreq *inireq = fcpreq->private; struct fcloop_fcpreq *tfcp_req; bool abortio = true; + unsigned long flags; spin_lock(&inireq->inilock); tfcp_req = inireq->tfcp_req; @@ -910,7 +916,7 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport, return; /* break initiator/target relationship for io */ - spin_lock_irq(&tfcp_req->reqlock); + spin_lock_irqsave(&tfcp_req->reqlock, flags); switch (tfcp_req->inistate) { case INI_IO_START: case INI_IO_ACTIVE: @@ -920,11 +926,11 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport, abortio = false; break; default: - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); WARN_ON(1); return; } - spin_unlock_irq(&tfcp_req->reqlock); + spin_unlock_irqrestore(&tfcp_req->reqlock, flags); if (abortio) /* leave the reference while the work item is scheduled */ From fcacaa9d0457046ada6da69c0582712b392cc56b Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 13 Apr 2023 20:28:42 +0200 Subject: [PATCH 2844/4345] bpf, sockmap: Revert buggy deadlock fix in the sockhash and sockmap [ Upstream commit 8c5c2a4898e3d6bad86e29d471e023c8a19ba799 ] syzbot reported a splat and bisected it to recent commit ed17aa92dc56 ("bpf, sockmap: fix deadlocks in the sockhash and sockmap"): [...] WARNING: CPU: 1 PID: 9280 at kernel/softirq.c:376 __local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 Modules linked in: CPU: 1 PID: 9280 Comm: syz-executor.1 Not tainted 6.2.0-syzkaller-13249-gd319f344561d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023 RIP: 0010:__local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 [...] Call Trace: spin_unlock_bh include/linux/spinlock.h:395 [inline] sock_map_del_link+0x2ea/0x510 net/core/sock_map.c:165 sock_map_unref+0xb0/0x1d0 net/core/sock_map.c:184 sock_hash_delete_elem+0x1ec/0x2a0 net/core/sock_map.c:945 map_delete_elem kernel/bpf/syscall.c:1536 [inline] __sys_bpf+0x2edc/0x53e0 kernel/bpf/syscall.c:5053 __do_sys_bpf kernel/bpf/syscall.c:5166 [inline] __se_sys_bpf kernel/bpf/syscall.c:5164 [inline] __x64_sys_bpf+0x79/0xc0 kernel/bpf/syscall.c:5164 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fe8f7c8c169 [...] Revert for now until we have a proper solution. Fixes: ed17aa92dc56 ("bpf, sockmap: fix deadlocks in the sockhash and sockmap") Reported-by: syzbot+49f6cef45247ff249498@syzkaller.appspotmail.com Cc: Hsin-Wei Hung Cc: Xin Liu Cc: John Fastabend Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/000000000000f1db9605f939720e@google.com/ Signed-off-by: Sasha Levin --- net/core/sock_map.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index e21adbbb7461..ee5d3f49b0b5 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -423,9 +423,8 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, { struct sock *sk; int err = 0; - unsigned long flags; - raw_spin_lock_irqsave(&stab->lock, flags); + raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) sk = xchg(psk, NULL); @@ -435,7 +434,7 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, else err = -EINVAL; - raw_spin_unlock_irqrestore(&stab->lock, flags); + raw_spin_unlock_bh(&stab->lock); return err; } @@ -957,12 +956,11 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; int ret = -ENOENT; - unsigned long flags; hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); - raw_spin_lock_irqsave(&bucket->lock, flags); + raw_spin_lock_bh(&bucket->lock); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); if (elem) { hlist_del_rcu(&elem->node); @@ -970,7 +968,7 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) sock_hash_free_elem(htab, elem); ret = 0; } - raw_spin_unlock_irqrestore(&bucket->lock, flags); + raw_spin_unlock_bh(&bucket->lock); return ret; } From 1697fb124c6d6c5237e9cbd78890310154738084 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 10 Mar 2023 15:38:53 +0800 Subject: [PATCH 2845/4345] md/raid10: fix leak of 'r10bio->remaining' for recovery [ Upstream commit 26208a7cffd0c7cbf14237ccd20c7270b3ffeb7e ] raid10_sync_request() will add 'r10bio->remaining' for both rdev and replacement rdev. However, if the read io fails, recovery_request_write() returns without issuing the write io, in this case, end_sync_request() is only called once and 'remaining' is leaked, cause an io hang. Fix the problem by decreasing 'remaining' according to if 'bio' and 'repl_bio' is valid. Fixes: 24afd80d99f8 ("md/raid10: handle recovery of replacement devices.") Signed-off-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230310073855.1337560-5-yukuai1@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/raid10.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 6f8a7537dcd7..e2e58a1f7f42 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2212,11 +2212,22 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) { struct r10conf *conf = mddev->private; int d; - struct bio *wbio, *wbio2; + struct bio *wbio = r10_bio->devs[1].bio; + struct bio *wbio2 = r10_bio->devs[1].repl_bio; + + /* Need to test wbio2->bi_end_io before we call + * submit_bio_noacct as if the former is NULL, + * the latter is free to free wbio2. + */ + if (wbio2 && !wbio2->bi_end_io) + wbio2 = NULL; if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) { fix_recovery_read_error(r10_bio); - end_sync_request(r10_bio); + if (wbio->bi_end_io) + end_sync_request(r10_bio); + if (wbio2) + end_sync_request(r10_bio); return; } @@ -2225,14 +2236,6 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) * and submit the write request */ d = r10_bio->devs[1].devnum; - wbio = r10_bio->devs[1].bio; - wbio2 = r10_bio->devs[1].repl_bio; - /* Need to test wbio2->bi_end_io before we call - * submit_bio_noacct as if the former is NULL, - * the latter is free to free wbio2. - */ - if (wbio2 && !wbio2->bi_end_io) - wbio2 = NULL; if (wbio->bi_end_io) { atomic_inc(&conf->mirrors[d].rdev->nr_pending); md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio)); From 6361b0592b46c465ac926c1f3105d66c30d9658b Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 10 Mar 2023 15:38:54 +0800 Subject: [PATCH 2846/4345] md/raid10: fix memleak for 'conf->bio_split' [ Upstream commit c9ac2acde53f5385de185bccf6aaa91cf9ac1541 ] In the error path of raid10_run(), 'conf' need be freed, however, 'conf->bio_split' is missed and memory will be leaked. Since there are 3 places to free 'conf', factor out a helper to fix the problem. Fixes: fc9977dd069e ("md/raid10: simplify the splitting of requests.") Signed-off-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230310073855.1337560-6-yukuai1@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/raid10.c | 37 +++++++++++++++++-------------------- 1 file changed, 17 insertions(+), 20 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index e2e58a1f7f42..4307832062fb 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3618,6 +3618,20 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new) return nc*fc; } +static void raid10_free_conf(struct r10conf *conf) +{ + if (!conf) + return; + + mempool_exit(&conf->r10bio_pool); + kfree(conf->mirrors); + kfree(conf->mirrors_old); + kfree(conf->mirrors_new); + safe_put_page(conf->tmppage); + bioset_exit(&conf->bio_split); + kfree(conf); +} + static struct r10conf *setup_conf(struct mddev *mddev) { struct r10conf *conf = NULL; @@ -3700,13 +3714,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) return conf; out: - if (conf) { - mempool_exit(&conf->r10bio_pool); - kfree(conf->mirrors); - safe_put_page(conf->tmppage); - bioset_exit(&conf->bio_split); - kfree(conf); - } + raid10_free_conf(conf); return ERR_PTR(err); } @@ -3912,10 +3920,7 @@ static int raid10_run(struct mddev *mddev) out_free_conf: md_unregister_thread(&mddev->thread); - mempool_exit(&conf->r10bio_pool); - safe_put_page(conf->tmppage); - kfree(conf->mirrors); - kfree(conf); + raid10_free_conf(conf); mddev->private = NULL; out: return -EIO; @@ -3923,15 +3928,7 @@ out: static void raid10_free(struct mddev *mddev, void *priv) { - struct r10conf *conf = priv; - - mempool_exit(&conf->r10bio_pool); - safe_put_page(conf->tmppage); - kfree(conf->mirrors); - kfree(conf->mirrors_old); - kfree(conf->mirrors_new); - bioset_exit(&conf->bio_split); - kfree(conf); + raid10_free_conf(priv); } static void raid10_quiesce(struct mddev *mddev, int quiesce) From 2a65555f7e0f4a05b663879908a991e6d9f81e51 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 10 Mar 2023 15:38:55 +0800 Subject: [PATCH 2847/4345] md/raid10: fix memleak of md thread [ Upstream commit f0ddb83da3cbbf8a1f9087a642c448ff52ee9abd ] In raid10_run(), if setup_conf() succeed and raid10_run() failed before setting 'mddev->thread', then in the error path 'conf->thread' is not freed. Fix the problem by setting 'mddev->thread' right after setup_conf(). Fixes: 43a521238aca ("md-cluster: choose correct label when clustered layout is not supported") Signed-off-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230310073855.1337560-7-yukuai1@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/raid10.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 4307832062fb..6a0459f9fafb 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3752,6 +3752,9 @@ static int raid10_run(struct mddev *mddev) if (!conf) goto out; + mddev->thread = conf->thread; + conf->thread = NULL; + if (mddev_is_clustered(conf->mddev)) { int fc, fo; @@ -3764,9 +3767,6 @@ static int raid10_run(struct mddev *mddev) } } - mddev->thread = conf->thread; - conf->thread = NULL; - if (mddev->queue) { blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); From c0ca3824190e4046e5e2af127a89a3113f8d71b9 Mon Sep 17 00:00:00 2001 From: Daniel Gabay Date: Thu, 13 Apr 2023 21:40:34 +0300 Subject: [PATCH 2848/4345] wifi: iwlwifi: yoyo: Fix possible division by zero [ Upstream commit ba30415118eee374a08b39a0460a1d1e52c24a25 ] Don't allow buffer allocation TLV with zero req_size since it leads later to division by zero in iwl_dbg_tlv_alloc_fragments(). Also, NPK/SRAM locations are allowed to have zero buffer req_size, don't discard them. Fixes: a9248de42464 ("iwlwifi: dbg_ini: add TLV allocation new API support") Signed-off-by: Daniel Gabay Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230413213309.5d6688ed74d8.I5c2f3a882b50698b708d54f4524dc5bdf11e3d32@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 3c931b1b2a0b..fdf2c6ea41d9 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -191,6 +191,12 @@ static int iwl_dbg_tlv_alloc_buf_alloc(struct iwl_trans *trans, alloc_id != IWL_FW_INI_ALLOCATION_ID_INTERNAL) goto err; + if (buf_location == IWL_FW_INI_LOCATION_DRAM_PATH && + alloc->req_size == 0) { + IWL_ERR(trans, "WRT: Invalid DRAM buffer allocation requested size (0)\n"); + return -EINVAL; + } + trans->dbg.fw_mon_cfg[alloc_id] = *alloc; return 0; From 038cbab5506964cebb5cbedb597c6247f72f066c Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 14 Apr 2023 13:11:58 +0300 Subject: [PATCH 2849/4345] wifi: iwlwifi: fw: move memset before early return [ Upstream commit 8ce437dd5b2e4adef13aa4ecce07392f9966b1ab ] Clang static analysis reports this representative issue dbg.c:1455:6: warning: Branch condition evaluates to a garbage value if (!rxf_data.size) ^~~~~~~~~~~~~~ This check depends on iwl_ini_get_rxf_data() to clear rxf_data but the function can return early without doing the clear. So move the memset before the early return. Fixes: cc9b6012d34b ("iwlwifi: yoyo: use hweight_long instead of bit manipulating") Signed-off-by: Tom Rix Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230414130637.872a7175f1ff.I33802a77a91998276992b088fbe25f61c87c33ac@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index 419eaa5cf0b5..79d08e5d9a81 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -1372,13 +1372,13 @@ static void iwl_ini_get_rxf_data(struct iwl_fw_runtime *fwrt, if (!data) return; + memset(data, 0, sizeof(*data)); + /* make sure only one bit is set in only one fid */ if (WARN_ONCE(hweight_long(fid1) + hweight_long(fid2) != 1, "fid1=%x, fid2=%x\n", fid1, fid2)) return; - memset(data, 0, sizeof(*data)); - if (fid1) { fifo_idx = ffs(fid1) - 1; if (WARN_ONCE(fifo_idx >= MAX_NUM_LMAC, "fifo_idx=%d\n", From 62fde465175921007335c719d780a6ee598c9485 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 29 Mar 2023 17:49:32 +0200 Subject: [PATCH 2850/4345] jdb2: Don't refuse invalidation of already invalidated buffers [ Upstream commit bd159398a2d2234de07d310132865706964aaaa7 ] When invalidating buffers under the partial tail page, jbd2_journal_invalidate_folio() returns -EBUSY if the buffer is part of the committing transaction as we cannot safely modify buffer state. However if the buffer is already invalidated (due to previous invalidation attempts from ext4_wait_for_tail_page_commit()), there's nothing to do and there's no point in returning -EBUSY. This fixes occasional warnings from ext4_journalled_invalidate_folio() triggered by generic/051 fstest when blocksize < pagesize. Fixes: 53e872681fed ("ext4: fix deadlock in journal_unmap_buffer()") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230329154950.19720-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/jbd2/transaction.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 1923528154b5..1baf2d607268 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2378,6 +2378,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); jbd2_journal_put_journal_head(jh); + /* Already zapped buffer? Nothing to do... */ + if (!bh->b_bdev) + return 0; return -EBUSY; } /* From 4ff7c0fbb3fd627fd43a6a554c9bf290df71696d Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 16 Apr 2023 15:47:38 +0300 Subject: [PATCH 2851/4345] wifi: iwlwifi: make the loop for card preparation effective [ Upstream commit 28965ec0b5d9112585f725660e2ff13218505ace ] Since we didn't reset t to 0, only the first iteration of the loop did checked the ready bit several times. From the second iteration and on, we just tested the bit once and continued to the next iteration. Reported-and-tested-by: Lorenzo Zolfanelli Link: https://bugzilla.kernel.org/show_bug.cgi?id=216452 Fixes: 289e5501c314 ("iwlwifi: fix the preparation of the card") Signed-off-by: Emmanuel Grumbach Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230416154301.615b683ab9c8.Ic52c3229d3345b0064fa34263293db095d88daf8@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index daec61a60fec..7f8b7f7697cf 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -620,7 +620,6 @@ static int iwl_pcie_set_hw_ready(struct iwl_trans *trans) int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) { int ret; - int t = 0; int iter; IWL_DEBUG_INFO(trans, "iwl_trans_prepare_card_hw enter\n"); @@ -635,6 +634,8 @@ int iwl_pcie_prepare_card_hw(struct iwl_trans *trans) usleep_range(1000, 2000); for (iter = 0; iter < 10; iter++) { + int t = 0; + /* If HW is not ready, prepare the conditions to check again */ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG, CSR_HW_IF_CONFIG_REG_PREPARE); From f4eb14d2618f28a02c5b1d2183675aa9c9719ec7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 17 Apr 2023 11:41:33 +0300 Subject: [PATCH 2852/4345] wifi: iwlwifi: mvm: check firmware response size [ Upstream commit 13513cec93ac9902d0b896976d8bab3758a9881c ] Check the firmware response size for responses to the memory read/write command in debugfs before using it. Fixes: 2b55f43f8e47 ("iwlwifi: mvm: Add mem debugfs entry") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230417113648.0d56fcaf68ee.I70e9571f3ed7263929b04f8fabad23c9b999e4ea@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index 3395c4675988..36f75d594630 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -1885,6 +1885,11 @@ static ssize_t iwl_dbgfs_mem_read(struct file *file, char __user *user_buf, if (ret < 0) return ret; + if (iwl_rx_packet_payload_len(hcmd.resp_pkt) < sizeof(*rsp)) { + ret = -EIO; + goto out; + } + rsp = (void *)hcmd.resp_pkt->data; if (le32_to_cpu(rsp->status) != DEBUG_MEM_STATUS_SUCCESS) { ret = -ENXIO; @@ -1962,6 +1967,11 @@ static ssize_t iwl_dbgfs_mem_write(struct file *file, if (ret < 0) return ret; + if (iwl_rx_packet_payload_len(hcmd.resp_pkt) < sizeof(*rsp)) { + ret = -EIO; + goto out; + } + rsp = (void *)hcmd.resp_pkt->data; if (rsp->status != DEBUG_MEM_STATUS_SUCCESS) { ret = -ENXIO; From 89496d6cff297c88fe0286a440c380ceb172da2b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 18 Apr 2023 12:28:05 +0300 Subject: [PATCH 2853/4345] wifi: iwlwifi: fw: fix memory leak in debugfs [ Upstream commit 3d90d2f4a018fe8cfd65068bc6350b6222be4852 ] Fix a memory leak that occurs when reading the fw_info file all the way, since we return NULL indicating no more data, but don't free the status tracking object. Fixes: 36dfe9ac6e8b ("iwlwifi: dump api version in yaml format") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230418122405.239e501b3b8d.I4268f87809ef91209cbcd748eee0863195e70fa2@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/fw/debugfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c index 267ad4eddb5c..24d6ed3513ce 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c @@ -344,8 +344,10 @@ static void *iwl_dbgfs_fw_info_seq_next(struct seq_file *seq, const struct iwl_fw *fw = priv->fwrt->fw; *pos = ++state->pos; - if (*pos >= fw->ucode_capa.n_cmd_versions) + if (*pos >= fw->ucode_capa.n_cmd_versions) { + kfree(state); return NULL; + } return state; } From 7a150a5b54681b344b3de3b7e6ab7043cce81eae Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Sun, 16 Apr 2023 19:12:22 +0000 Subject: [PATCH 2854/4345] ixgbe: Allow flow hash to be set via ethtool [ Upstream commit 4f3ed1293feb9502dc254b05802faf1ad3317ac6 ] ixgbe currently returns `EINVAL` whenever the flowhash it set by ethtool because the ethtool code in the kernel passes a non-zero value for hfunc that ixgbe should allow. When ethtool is called with `ETHTOOL_SRXFHINDIR`, `ethtool_set_rxfh_indir` will call ixgbe's set_rxfh function with `ETH_RSS_HASH_NO_CHANGE`. This value should be accepted. When ethtool is called with `ETHTOOL_SRSSH`, `ethtool_set_rxfh` will call ixgbe's set_rxfh function with `rxfh.hfunc`, which appears to be hardcoded in ixgbe to always be `ETH_RSS_HASH_TOP`. This value should also be accepted. Before this patch: $ sudo ethtool -L eth1 combined 10 $ sudo ethtool -X eth1 default Cannot set RX flow hash configuration: Invalid argument After this patch: $ sudo ethtool -L eth1 combined 10 $ sudo ethtool -X eth1 default $ sudo ethtool -x eth1 RX flow hash indirection table for eth1 with 10 RX ring(s): 0: 0 1 2 3 4 5 6 7 8: 8 9 0 1 2 3 4 5 16: 6 7 8 9 0 1 2 3 24: 4 5 6 7 8 9 0 1 ... Fixes: 1c7cf0784e4d ("ixgbe: support for ethtool set_rxfh") Signed-off-by: Joe Damato Reviewed-by: Sridhar Samudrala Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 55983904b6df..472ea068ea7b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3107,8 +3107,8 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir, int i; u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter); - if (hfunc) - return -EINVAL; + if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; /* Fill out the redirection table */ if (indir) { From 80090acb588556ab2b2699d7a1583733ed17d89a Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Sun, 16 Apr 2023 19:12:23 +0000 Subject: [PATCH 2855/4345] ixgbe: Enable setting RSS table to default values [ Upstream commit e85d3d55875f7a1079edfbc4e4e98d6f8aea9ac7 ] ethtool uses `ETHTOOL_GRXRINGS` to compute how many queues are supported by RSS. The driver should return the smaller of either: - The maximum number of RSS queues the device supports, OR - The number of RX queues configured Prior to this change, running `ethtool -X $iface default` fails if the number of queues configured is larger than the number supported by RSS, even though changing the queue count correctly resets the flowhash to use all supported queues. Other drivers (for example, i40e) will succeed but the flow hash will reset to support the maximum number of queues supported by RSS, even if that amount is smaller than the configured amount. Prior to this change: $ sudo ethtool -L eth1 combined 20 $ sudo ethtool -x eth1 RX flow hash indirection table for eth1 with 20 RX ring(s): 0: 0 1 2 3 4 5 6 7 8: 8 9 10 11 12 13 14 15 16: 0 1 2 3 4 5 6 7 24: 8 9 10 11 12 13 14 15 32: 0 1 2 3 4 5 6 7 ... You can see that the flowhash was correctly set to use the maximum number of queues supported by the driver (16). However, asking the NIC to reset to "default" fails: $ sudo ethtool -X eth1 default Cannot set RX flow hash configuration: Invalid argument After this change, the flowhash can be reset to default which will use all of the available RSS queues (16) or the configured queue count, whichever is smaller. Starting with eth1 which has 10 queues and a flowhash distributing to all 10 queues: $ sudo ethtool -x eth1 RX flow hash indirection table for eth1 with 10 RX ring(s): 0: 0 1 2 3 4 5 6 7 8: 8 9 0 1 2 3 4 5 16: 6 7 8 9 0 1 2 3 ... Increasing the queue count to 48 resets the flowhash to distribute to 16 queues, as it did before this patch: $ sudo ethtool -L eth1 combined 48 $ sudo ethtool -x eth1 RX flow hash indirection table for eth1 with 16 RX ring(s): 0: 0 1 2 3 4 5 6 7 8: 8 9 10 11 12 13 14 15 16: 0 1 2 3 4 5 6 7 ... Due to the other bugfix in this series, the flowhash can be set to use queues 0-5: $ sudo ethtool -X eth1 equal 5 $ sudo ethtool -x eth1 RX flow hash indirection table for eth1 with 16 RX ring(s): 0: 0 1 2 3 4 0 1 2 8: 3 4 0 1 2 3 4 0 16: 1 2 3 4 0 1 2 3 ... Due to this bugfix, the flowhash can be reset to default and use 16 queues: $ sudo ethtool -X eth1 default $ sudo ethtool -x eth1 RX flow hash indirection table for eth1 with 16 RX ring(s): 0: 0 1 2 3 4 5 6 7 8: 8 9 10 11 12 13 14 15 16: 0 1 2 3 4 5 6 7 ... Fixes: 91cd94bfe4f0 ("ixgbe: add basic support for setting and getting nfc controls") Signed-off-by: Joe Damato Reviewed-by: Sridhar Samudrala Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- .../net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 472ea068ea7b..2eb133183473 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2641,6 +2641,14 @@ static int ixgbe_get_rss_hash_opts(struct ixgbe_adapter *adapter, return 0; } +static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter) +{ + if (adapter->hw.mac.type < ixgbe_mac_X550) + return 16; + else + return 64; +} + static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { @@ -2649,7 +2657,8 @@ static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = adapter->num_rx_queues; + cmd->data = min_t(int, adapter->num_rx_queues, + ixgbe_rss_indir_tbl_max(adapter)); ret = 0; break; case ETHTOOL_GRXCLSRLCNT: @@ -3051,14 +3060,6 @@ static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return ret; } -static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter) -{ - if (adapter->hw.mac.type < ixgbe_mac_X550) - return 16; - else - return 64; -} - static u32 ixgbe_get_rxfh_key_size(struct net_device *netdev) { return IXGBE_RSS_KEY_SIZE; From f4fc43fde12a1b87b0433a9f8e6ad6fb5fe9cd8a Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 18 Apr 2023 15:53:38 -0700 Subject: [PATCH 2856/4345] bpf: Don't EFAULT for getsockopt with optval=NULL [ Upstream commit 00e74ae0863827d944e36e56a4ce1e77e50edb91 ] Some socket options do getsockopt with optval=NULL to estimate the size of the final buffer (which is returned via optlen). This breaks BPF getsockopt assumptions about permitted optval buffer size. Let's enforce these assumptions only when non-NULL optval is provided. Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks") Reported-by: Martin KaFai Lau Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/ZD7Js4fj5YyI2oLd@google.com/T/#mb68daf700f87a9244a15d01d00c3f0e5b08f49f7 Link: https://lore.kernel.org/bpf/20230418225343.553806-2-sdf@google.com Signed-off-by: Sasha Levin --- kernel/bpf/cgroup.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 6d92e393e1bc..d3593a520bb7 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1516,7 +1516,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (ctx.optlen > max_optlen || ctx.optlen < 0) { + if (optval && (ctx.optlen > max_optlen || ctx.optlen < 0)) { ret = -EFAULT; goto out; } @@ -1530,8 +1530,11 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, } if (ctx.optlen != 0) { - if (copy_to_user(optval, ctx.optval, ctx.optlen) || - put_user(ctx.optlen, optlen)) { + if (optval && copy_to_user(optval, ctx.optval, ctx.optlen)) { + ret = -EFAULT; + goto out; + } + if (put_user(ctx.optlen, optlen)) { ret = -EFAULT; goto out; } From cb71b24a89274d651dd1c569c2c03e3d87d250ec Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Apr 2023 17:13:19 +0200 Subject: [PATCH 2857/4345] netfilter: nf_tables: don't write table validation state without mutex [ Upstream commit 9a32e9850686599ed194ccdceb6cd3dd56b2d9b9 ] The ->cleanup callback needs to be removed, this doesn't work anymore as the transaction mutex is already released in the ->abort function. Just do it after a successful validation pass, this either happens from commit or abort phases where transaction mutex is held. Fixes: f102d66b335a ("netfilter: nf_tables: use dedicated mutex to guard transactions") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/linux/netfilter/nfnetlink.h | 1 - net/netfilter/nf_tables_api.c | 8 ++------ net/netfilter/nfnetlink.c | 2 -- 3 files changed, 2 insertions(+), 9 deletions(-) diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 791d516e1e88..0518ca72b761 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -39,7 +39,6 @@ struct nfnetlink_subsystem { int (*commit)(struct net *net, struct sk_buff *skb); int (*abort)(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action); - void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2143edafba77..7bb716df7afc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7442,6 +7442,8 @@ static int nf_tables_validate(struct net *net) if (nft_table_validate(net, table) < 0) return -EAGAIN; } + + nft_validate_state_update(net, NFT_VALIDATE_SKIP); break; } @@ -8273,11 +8275,6 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) return 0; } -static void nf_tables_cleanup(struct net *net) -{ - nft_validate_state_update(net, NFT_VALIDATE_SKIP); -} - static int nf_tables_abort(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action) { @@ -8309,7 +8306,6 @@ static const struct nfnetlink_subsystem nf_tables_subsys = { .cb = nf_tables_cb, .commit = nf_tables_commit, .abort = nf_tables_abort, - .cleanup = nf_tables_cleanup, .valid_genid = nf_tables_valid_genid, .owner = THIS_MODULE, }; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index d3df66a39b5e..edf386a020b9 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -530,8 +530,6 @@ done: goto replay_abort; } } - if (ss->cleanup) - ss->cleanup(net); nfnl_err_deliver(&err_list, oskb); kfree_skb(skb); From 4b8a05e3801661a0438fcd0cdef181030d966a5a Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 20 Apr 2023 16:59:46 +0200 Subject: [PATCH 2858/4345] net/sched: sch_fq: fix integer overflow of "credit" [ Upstream commit 7041101ff6c3073fd8f2e99920f535b111c929cb ] if sch_fq is configured with "initial quantum" having values greater than INT_MAX, the first assignment of "credit" does signed integer overflow to a very negative value. In this situation, the syzkaller script provided by Cristoph triggers the CPU soft-lockup warning even with few sockets. It's not an infinite loop, but "credit" wasn't probably meant to be minus 2Gb for each new flow. Capping "initial quantum" to INT_MAX proved to fix the issue. v2: validation of "initial quantum" is done in fq_policy, instead of open coding in fq_change() _ suggested by Jakub Kicinski Reported-by: Christoph Paasch Link: https://github.com/multipath-tcp/mptcp_net-next/issues/377 Fixes: afe4fd062416 ("pkt_sched: fq: Fair Queue packet scheduler") Reviewed-by: Eric Dumazet Signed-off-by: Davide Caratti Link: https://lore.kernel.org/r/7b3a3c7e36d03068707a021760a194a8eb5ad41a.1682002300.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_fq.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 2fb76fc0cc31..5a1274199fe3 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -779,13 +779,17 @@ static int fq_resize(struct Qdisc *sch, u32 log) return 0; } +static struct netlink_range_validation iq_range = { + .max = INT_MAX, +}; + static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_UNSPEC] = { .strict_start_type = TCA_FQ_TIMER_SLACK }, [TCA_FQ_PLIMIT] = { .type = NLA_U32 }, [TCA_FQ_FLOW_PLIMIT] = { .type = NLA_U32 }, [TCA_FQ_QUANTUM] = { .type = NLA_U32 }, - [TCA_FQ_INITIAL_QUANTUM] = { .type = NLA_U32 }, + [TCA_FQ_INITIAL_QUANTUM] = NLA_POLICY_FULL_RANGE(NLA_U32, &iq_range), [TCA_FQ_RATE_ENABLE] = { .type = NLA_U32 }, [TCA_FQ_FLOW_DEFAULT_RATE] = { .type = NLA_U32 }, [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, From 566785731c6dd41ef815196ddc36d1ae30a63763 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Thu, 20 Apr 2023 20:40:35 +0800 Subject: [PATCH 2859/4345] ipv4: Fix potential uninit variable access bug in __ip_make_skb() [ Upstream commit 99e5acae193e369b71217efe6f1dad42f3f18815 ] Like commit ea30388baebc ("ipv6: Fix an uninit variable access bug in __ip6_make_skb()"). icmphdr does not in skb linear region under the scenario of SOCK_RAW socket. Access icmp_hdr(skb)->type directly will trigger the uninit variable access bug. Use a local variable icmp_type to carry the correct value in different scenarios. Fixes: 96793b482540 ("[IPV4]: Add ICMPMsgStats MIB (RFC 4293)") Reviewed-by: Willem de Bruijn Signed-off-by: Ziyang Xuan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/ip_output.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 0dbf950de832..1e07df282177 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1564,9 +1564,19 @@ struct sk_buff *__ip_make_skb(struct sock *sk, cork->dst = NULL; skb_dst_set(skb, &rt->dst); - if (iph->protocol == IPPROTO_ICMP) - icmp_out_count(net, ((struct icmphdr *) - skb_transport_header(skb))->type); + if (iph->protocol == IPPROTO_ICMP) { + u8 icmp_type; + + /* For such sockets, transhdrlen is zero when do ip_append_data(), + * so icmphdr does not in skb linear region and can not get icmp_type + * by icmp_hdr(skb)->type. + */ + if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) + icmp_type = fl4->fl4_icmp_type; + else + icmp_type = icmp_hdr(skb)->type; + icmp_out_count(net, icmp_type); + } ip_cork_release(cork); out: From 0837d10f6c37a47a0c73bccf1e39513613a2fcc2 Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Fri, 14 Apr 2023 18:30:06 +0800 Subject: [PATCH 2860/4345] Revert "Bluetooth: btsdio: fix use after free bug in btsdio_remove due to unfinished work" [ Upstream commit db2bf510bd5d57f064d9e1db395ed86a08320c54 ] This reverts commit 1e9ac114c4428fdb7ff4635b45d4f46017e8916f. This patch introduces a possible null-ptr-def problem. Revert it. And the fixed bug by this patch have resolved by commit 73f7b171b7c0 ("Bluetooth: btsdio: fix use after free bug in btsdio_remove due to race condition"). Fixes: 1e9ac114c442 ("Bluetooth: btsdio: fix use after free bug in btsdio_remove due to unfinished work") Signed-off-by: Liu Jian Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/btsdio.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 7050a16e7efe..199e8f7d426d 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -352,7 +352,6 @@ static void btsdio_remove(struct sdio_func *func) BT_DBG("func %p", func); - cancel_work_sync(&data->work); if (!data) return; From b978d22fa122182829be681a5dfebaf4cff592a1 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 21 Apr 2023 11:52:55 -0700 Subject: [PATCH 2861/4345] netlink: Use copy_to_user() for optval in netlink_getsockopt(). [ Upstream commit d913d32cc2707e9cd24fe6fa6d7d470e9c728980 ] Brad Spencer provided a detailed report [0] that when calling getsockopt() for AF_NETLINK, some SOL_NETLINK options set only 1 byte even though such options require at least sizeof(int) as length. The options return a flag value that fits into 1 byte, but such behaviour confuses users who do not initialise the variable before calling getsockopt() and do not strictly check the returned value as char. Currently, netlink_getsockopt() uses put_user() to copy data to optlen and optval, but put_user() casts the data based on the pointer, char *optval. As a result, only 1 byte is set to optval. To avoid this behaviour, we need to use copy_to_user() or cast optval for put_user(). Note that this changes the behaviour on big-endian systems, but we document that the size of optval is int in the man page. $ man 7 netlink ... Socket options To set or get a netlink socket option, call getsockopt(2) to read or setsockopt(2) to write the option with the option level argument set to SOL_NETLINK. Unless otherwise noted, optval is a pointer to an int. Fixes: 9a4595bc7e67 ("[NETLINK]: Add set/getsockopt options to support more than 32 groups") Fixes: be0c22a46cfb ("netlink: add NETLINK_BROADCAST_ERROR socket option") Fixes: 38938bfe3489 ("netlink: add NETLINK_NO_ENOBUFS socket flag") Fixes: 0a6a3a23ea6e ("netlink: add NETLINK_CAP_ACK socket option") Fixes: 2d4bc93368f5 ("netlink: extended ACK reporting") Fixes: 89d35528d17d ("netlink: Add new socket option to enable strict checking on dumps") Reported-by: Brad Spencer Link: https://lore.kernel.org/netdev/ZD7VkNWFfp22kTDt@datsun.rim.net/ Signed-off-by: Kuniyuki Iwashima Reviewed-by: Johannes Berg Link: https://lore.kernel.org/r/20230421185255.94606-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 75 ++++++++++++---------------------------- 1 file changed, 23 insertions(+), 52 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 2104fbdd63d2..eedb16517f16 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1744,7 +1744,8 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); - int len, val, err; + unsigned int flag; + int len, val; if (level != SOL_NETLINK) return -ENOPROTOOPT; @@ -1756,39 +1757,17 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, switch (optname) { case NETLINK_PKTINFO: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_RECV_PKTINFO ? 1 : 0; - if (put_user(len, optlen) || - put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_RECV_PKTINFO; break; case NETLINK_BROADCAST_ERROR: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR ? 1 : 0; - if (put_user(len, optlen) || - put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_RECV_NO_ENOBUFS ? 1 : 0; - if (put_user(len, optlen) || - put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_RECV_NO_ENOBUFS; break; case NETLINK_LIST_MEMBERSHIPS: { - int pos, idx, shift; + int pos, idx, shift, err = 0; - err = 0; netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) @@ -1805,40 +1784,32 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); - break; + return err; } case NETLINK_CAP_ACK: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_CAP_ACK ? 1 : 0; - if (put_user(len, optlen) || - put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_EXT_ACK ? 1 : 0; - if (put_user(len, optlen) || put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_STRICT_CHK ? 1 : 0; - if (put_user(len, optlen) || put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_STRICT_CHK; break; default: - err = -ENOPROTOOPT; + return -ENOPROTOOPT; } - return err; + + if (len < sizeof(int)) + return -EINVAL; + + len = sizeof(int); + val = nlk->flags & flag ? 1 : 0; + + if (put_user(len, optlen) || + copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; } static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) From 0abcb0b0d629fd598c0ab5358ae605cb1d94d88f Mon Sep 17 00:00:00 2001 From: Gencen Gan Date: Mon, 24 Apr 2023 23:28:01 +0800 Subject: [PATCH 2862/4345] net: amd: Fix link leak when verifying config failed [ Upstream commit d325c34d9e7e38d371c0a299d415e9b07f66a1fb ] After failing to verify configuration, it returns directly without releasing link, which may cause memory leak. Paolo Abeni thinks that the whole code of this driver is quite "suboptimal" and looks unmainatained since at least ~15y, so he suggests that we could simply remove the whole driver, please take it into consideration. Simon Horman suggests that the fix label should be set to "Linux-2.6.12-rc2" considering that the problem has existed since the driver was introduced and the commit above doesn't seem to exist in net/net-next. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Gan Gecen Reviewed-by: Dongliang Mu Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/nmclan_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index 11c0b13edd30..f34881637505 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -650,7 +650,7 @@ static int nmclan_config(struct pcmcia_device *link) } else { pr_notice("mace id not found: %x %x should be 0x40 0x?9\n", sig[0], sig[1]); - return -ENODEV; + goto failed; } } From 230a5ed7d813fb516de81d23f09d7506753e41e9 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 24 Apr 2023 15:20:22 -0700 Subject: [PATCH 2863/4345] tcp/udp: Fix memleaks of sk and zerocopy skbs with TX timestamp. [ Upstream commit 50749f2dd6854a41830996ad302aef2ffaf011d8 ] syzkaller reported [0] memory leaks of an UDP socket and ZEROCOPY skbs. We can reproduce the problem with these sequences: sk = socket(AF_INET, SOCK_DGRAM, 0) sk.setsockopt(SOL_SOCKET, SO_TIMESTAMPING, SOF_TIMESTAMPING_TX_SOFTWARE) sk.setsockopt(SOL_SOCKET, SO_ZEROCOPY, 1) sk.sendto(b'', MSG_ZEROCOPY, ('127.0.0.1', 53)) sk.close() sendmsg() calls msg_zerocopy_alloc(), which allocates a skb, sets skb->cb->ubuf.refcnt to 1, and calls sock_hold(). Here, struct ubuf_info_msgzc indirectly holds a refcnt of the socket. When the skb is sent, __skb_tstamp_tx() clones it and puts the clone into the socket's error queue with the TX timestamp. When the original skb is received locally, skb_copy_ubufs() calls skb_unclone(), and pskb_expand_head() increments skb->cb->ubuf.refcnt. This additional count is decremented while freeing the skb, but struct ubuf_info_msgzc still has a refcnt, so __msg_zerocopy_callback() is not called. The last refcnt is not released unless we retrieve the TX timestamped skb by recvmsg(). Since we clear the error queue in inet_sock_destruct() after the socket's refcnt reaches 0, there is a circular dependency. If we close() the socket holding such skbs, we never call sock_put() and leak the count, sk, and skb. TCP has the same problem, and commit e0c8bccd40fc ("net: stream: purge sk_error_queue in sk_stream_kill_queues()") tried to fix it by calling skb_queue_purge() during close(). However, there is a small chance that skb queued in a qdisc or device could be put into the error queue after the skb_queue_purge() call. In __skb_tstamp_tx(), the cloned skb should not have a reference to the ubuf to remove the circular dependency, but skb_clone() does not call skb_copy_ubufs() for zerocopy skb. So, we need to call skb_orphan_frags_rx() for the cloned skb to call skb_copy_ubufs(). [0]: BUG: memory leak unreferenced object 0xffff88800c6d2d00 (size 1152): comm "syz-executor392", pid 264, jiffies 4294785440 (age 13.044s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 cd af e8 81 00 00 00 00 ................ 02 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00 ...@............ backtrace: [<0000000055636812>] sk_prot_alloc+0x64/0x2a0 net/core/sock.c:2024 [<0000000054d77b7a>] sk_alloc+0x3b/0x800 net/core/sock.c:2083 [<0000000066f3c7e0>] inet_create net/ipv4/af_inet.c:319 [inline] [<0000000066f3c7e0>] inet_create+0x31e/0xe40 net/ipv4/af_inet.c:245 [<000000009b83af97>] __sock_create+0x2ab/0x550 net/socket.c:1515 [<00000000b9b11231>] sock_create net/socket.c:1566 [inline] [<00000000b9b11231>] __sys_socket_create net/socket.c:1603 [inline] [<00000000b9b11231>] __sys_socket_create net/socket.c:1588 [inline] [<00000000b9b11231>] __sys_socket+0x138/0x250 net/socket.c:1636 [<000000004fb45142>] __do_sys_socket net/socket.c:1649 [inline] [<000000004fb45142>] __se_sys_socket net/socket.c:1647 [inline] [<000000004fb45142>] __x64_sys_socket+0x73/0xb0 net/socket.c:1647 [<0000000066999e0e>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<0000000066999e0e>] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80 [<0000000017f238c1>] entry_SYSCALL_64_after_hwframe+0x63/0xcd BUG: memory leak unreferenced object 0xffff888017633a00 (size 240): comm "syz-executor392", pid 264, jiffies 4294785440 (age 13.044s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 2d 6d 0c 80 88 ff ff .........-m..... backtrace: [<000000002b1c4368>] __alloc_skb+0x229/0x320 net/core/skbuff.c:497 [<00000000143579a6>] alloc_skb include/linux/skbuff.h:1265 [inline] [<00000000143579a6>] sock_omalloc+0xaa/0x190 net/core/sock.c:2596 [<00000000be626478>] msg_zerocopy_alloc net/core/skbuff.c:1294 [inline] [<00000000be626478>] msg_zerocopy_realloc+0x1ce/0x7f0 net/core/skbuff.c:1370 [<00000000cbfc9870>] __ip_append_data+0x2adf/0x3b30 net/ipv4/ip_output.c:1037 [<0000000089869146>] ip_make_skb+0x26c/0x2e0 net/ipv4/ip_output.c:1652 [<00000000098015c2>] udp_sendmsg+0x1bac/0x2390 net/ipv4/udp.c:1253 [<0000000045e0e95e>] inet_sendmsg+0x10a/0x150 net/ipv4/af_inet.c:819 [<000000008d31bfde>] sock_sendmsg_nosec net/socket.c:714 [inline] [<000000008d31bfde>] sock_sendmsg+0x141/0x190 net/socket.c:734 [<0000000021e21aa4>] __sys_sendto+0x243/0x360 net/socket.c:2117 [<00000000ac0af00c>] __do_sys_sendto net/socket.c:2129 [inline] [<00000000ac0af00c>] __se_sys_sendto net/socket.c:2125 [inline] [<00000000ac0af00c>] __x64_sys_sendto+0xe1/0x1c0 net/socket.c:2125 [<0000000066999e0e>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<0000000066999e0e>] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80 [<0000000017f238c1>] entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY") Fixes: b5947e5d1e71 ("udp: msg_zerocopy") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/skbuff.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 09cdefe5e1c8..fb6b3f2ae192 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4750,6 +4750,9 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, skb = alloc_skb(0, GFP_ATOMIC); } else { skb = skb_clone(orig_skb, GFP_ATOMIC); + + if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) + return; } if (!skb) return; From 7d285c6cfee6ca44979a355e1e2350a9bf90cd35 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 25 Feb 2023 21:39:46 -0800 Subject: [PATCH 2864/4345] ipmi: ASPEED_BT_IPMI_BMC: select REGMAP_MMIO instead of depending on it [ Upstream commit 2a587b9ad052e7e92e508aea90c1e2ae433c1908 ] REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it. Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues. Therefore, change the use of "depends on REGMAP_MMIO" to "select REGMAP_MMIO", which will also set REGMAP. Fixes: eb994594bc22 ("ipmi: bt-bmc: Use a regmap for register access") Signed-off-by: Randy Dunlap Cc: Andrew Jeffery Cc: Corey Minyard Cc: openipmi-developer@lists.sourceforge.net Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Message-Id: <20230226053953.4681-2-rdunlap@infradead.org> Signed-off-by: Corey Minyard Signed-off-by: Sasha Levin --- drivers/char/ipmi/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig index 07847d9a459a..f443186269e1 100644 --- a/drivers/char/ipmi/Kconfig +++ b/drivers/char/ipmi/Kconfig @@ -126,7 +126,8 @@ config NPCM7XX_KCS_IPMI_BMC config ASPEED_BT_IPMI_BMC depends on ARCH_ASPEED || COMPILE_TEST - depends on REGMAP && REGMAP_MMIO && MFD_SYSCON + depends on MFD_SYSCON + select REGMAP_MMIO tristate "BT IPMI bmc driver" help Provides a driver for the BT (Block Transfer) IPMI interface From c76ba917915c0ceb31f8e6523c02cbab5eb0c0fd Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 8 Mar 2023 20:40:43 +0000 Subject: [PATCH 2865/4345] pstore: Revert pmsg_lock back to a normal mutex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5239a89b06d6b199f133bf0ffea421683187f257 ] This reverts commit 76d62f24db07f22ccf9bc18ca793c27d4ebef721. So while priority inversion on the pmsg_lock is an occasional problem that an rt_mutex would help with, in uses where logging is writing to pmsg heavily from multiple threads, the pmsg_lock can be heavily contended. After this change landed, it was reported that cases where the mutex locking overhead was commonly adding on the order of 10s of usecs delay had suddenly jumped to ~msec delay with rtmutex. It seems the slight differences in the locks under this level of contention causes the normal mutexes to utilize the spinning optimizations, while the rtmutexes end up in the sleeping slowpath (which allows additional threads to pile on trying to take the lock). In this case, it devolves to a worse case senerio where the lock acquisition and scheduling overhead dominates, and each thread is waiting on the order of ~ms to do ~us of work. Obviously, having tons of threads all contending on a single lock for logging is non-optimal, so the proper fix is probably reworking pstore pmsg to have per-cpu buffers so we don't have contention. Additionally, Steven Rostedt has provided some furhter optimizations for rtmutexes that improves the rtmutex spinning path, but at least in my testing, I still see the test tripping into the sleeping path on rtmutexes while utilizing the spinning path with mutexes. But in the short term, lets revert the change to the rt_mutex and go back to normal mutexes to avoid a potentially major performance regression. And we can work on optimizations to both rtmutexes and finer-grained locking for pstore pmsg in the future. Cc: Wei Wang Cc: Midas Chien Cc: "Chunhui Li (李春辉)" Cc: Steven Rostedt Cc: Kees Cook Cc: Anton Vorontsov Cc: "Guilherme G. Piccoli" Cc: Tony Luck Cc: kernel-team@android.com Fixes: 76d62f24db07 ("pstore: Switch pmsg_lock to an rt_mutex to avoid priority inversion") Reported-by: "Chunhui Li (李春辉)" Signed-off-by: John Stultz Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230308204043.2061631-1-jstultz@google.com Signed-off-by: Sasha Levin --- fs/pstore/pmsg.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index 18cf94b597e0..d8542ec2f38c 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -7,10 +7,9 @@ #include #include #include -#include #include "internal.h" -static DEFINE_RT_MUTEX(pmsg_lock); +static DEFINE_MUTEX(pmsg_lock); static ssize_t write_pmsg(struct file *file, const char __user *buf, size_t count, loff_t *ppos) @@ -29,9 +28,9 @@ static ssize_t write_pmsg(struct file *file, const char __user *buf, if (!access_ok(buf, count)) return -EFAULT; - rt_mutex_lock(&pmsg_lock); + mutex_lock(&pmsg_lock); ret = psinfo->write_user(&record, buf); - rt_mutex_unlock(&pmsg_lock); + mutex_unlock(&pmsg_lock); return ret ? ret : count; } From 8a859ac86dea6166e03f315a550a1769f57b411e Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 7 Mar 2023 17:30:37 +0100 Subject: [PATCH 2866/4345] usb: host: xhci-rcar: remove leftover quirk handling [ Upstream commit 5d67f4861884762ebc2bddb5d667444e45f25782 ] Loading V3 firmware does not need a quirk anymore, remove the leftover code. Fixes: ed8603e11124 ("usb: host: xhci-rcar: Simplify getting the firmware name for R-Car Gen3") Reviewed-by: Geert Uytterhoeven Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20230307163041.3815-10-wsa+renesas@sang-engineering.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/host/xhci-rcar.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/usb/host/xhci-rcar.c b/drivers/usb/host/xhci-rcar.c index 9888ba7d85b6..cfafa1c50ade 100644 --- a/drivers/usb/host/xhci-rcar.c +++ b/drivers/usb/host/xhci-rcar.c @@ -75,7 +75,6 @@ MODULE_FIRMWARE(XHCI_RCAR_FIRMWARE_NAME_V3); /* For soc_device_attribute */ #define RCAR_XHCI_FIRMWARE_V2 BIT(0) /* FIRMWARE V2 */ -#define RCAR_XHCI_FIRMWARE_V3 BIT(1) /* FIRMWARE V3 */ static const struct soc_device_attribute rcar_quirks_match[] = { { @@ -147,8 +146,6 @@ static int xhci_rcar_download_firmware(struct usb_hcd *hcd) if (quirks & RCAR_XHCI_FIRMWARE_V2) firmware_name = XHCI_RCAR_FIRMWARE_NAME_V2; - else if (quirks & RCAR_XHCI_FIRMWARE_V3) - firmware_name = XHCI_RCAR_FIRMWARE_NAME_V3; else firmware_name = priv->firmware_name; From 98bf98e749e671bec95119a33a3e5a1e9989e717 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Fri, 24 Feb 2023 11:16:58 +0530 Subject: [PATCH 2867/4345] usb: dwc3: gadget: Change condition for processing suspend event [ Upstream commit 4decf4060ecfee1f7a710999fcd421645ac0c419 ] Currently we process the suspend interrupt event only if the device is in configured state. Consider a case where device is not configured and got suspend interrupt, in that case our gadget will still use 100mA as composite_suspend didn't happen. But battery charging specification (BC1.2) expects a downstream device to draw less than 2.5mA when unconnected OR suspended. Fix this by removing the condition for processing suspend event, and thus composite_resume would set vbus draw to 2. Fixes: 72704f876f50 ("dwc3: gadget: Implement the suspend entry event handler") Signed-off-by: Prashanth K Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/1677217619-10261-2-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/dwc3/gadget.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 01cecde76140..4e3b451ed749 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3726,15 +3726,8 @@ static void dwc3_gadget_interrupt(struct dwc3 *dwc, break; case DWC3_DEVICE_EVENT_EOPF: /* It changed to be suspend event for version 2.30a and above */ - if (!DWC3_VER_IS_PRIOR(DWC3, 230A)) { - /* - * Ignore suspend event until the gadget enters into - * USB_STATE_CONFIGURED state. - */ - if (dwc->gadget->state >= USB_STATE_CONFIGURED) - dwc3_gadget_suspend_interrupt(dwc, - event->event_info); - } + if (!DWC3_VER_IS_PRIOR(DWC3, 230A)) + dwc3_gadget_suspend_interrupt(dwc, event->event_info); break; case DWC3_DEVICE_EVENT_SOF: case DWC3_DEVICE_EVENT_ERRATIC_ERROR: From ed1f459af644460a906ca6ed78421df928d24a04 Mon Sep 17 00:00:00 2001 From: Marco Pagani Date: Wed, 1 Mar 2023 15:03:08 +0100 Subject: [PATCH 2868/4345] fpga: bridge: fix kernel-doc parameter description [ Upstream commit 7ef1a2c1c9dffa177ecc3ea50b7f5ee63a621137 ] Fix the kernel-doc description for the "struct fpga_image_info *info" parameter of the fpga_bridge_get() function. Fixes: 060ac5c8fa7b ("fpga: bridge: kernel-doc fixes") Signed-off-by: Marco Pagani Reviewed-by: Tom Rix Acked-by: Xu Yilun Link: https://lore.kernel.org/r/20230301140309.512578-1-marpagan@redhat.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/fpga/fpga-bridge.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c index 2deccacc3aa7..851debe32bf0 100644 --- a/drivers/fpga/fpga-bridge.c +++ b/drivers/fpga/fpga-bridge.c @@ -115,7 +115,7 @@ static int fpga_bridge_dev_match(struct device *dev, const void *data) /** * fpga_bridge_get - get an exclusive reference to a fpga bridge * @dev: parent device that fpga bridge was registered with - * @info: fpga manager info + * @info: fpga image specific information * * Given a device, get an exclusive reference to a fpga bridge. * From f1f3bc9915b2593ddb39d92dbbb33efb3b8dac9e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 16:34:28 +0100 Subject: [PATCH 2869/4345] iio: light: max44009: add missing OF device matching MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b29c49026c3c05a11f845dba17cad0b3ba06836d ] The driver currently matches only via i2c_device_id, but also has of_device_id table: drivers/iio/light/max44009.c:545:34: error: ‘max44009_of_match’ defined but not used [-Werror=unused-const-variable=] Fixes: 6aef699a7d7e ("iio: light: add driver for MAX44009") Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312153429.371702-2-krzysztof.kozlowski@linaro.org Signed-off-by: Jonathan Cameron Signed-off-by: Sasha Levin --- drivers/iio/light/max44009.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/iio/light/max44009.c b/drivers/iio/light/max44009.c index 801e5a0ad496..f3648f20ef2c 100644 --- a/drivers/iio/light/max44009.c +++ b/drivers/iio/light/max44009.c @@ -528,6 +528,12 @@ static int max44009_probe(struct i2c_client *client, return devm_iio_device_register(&client->dev, indio_dev); } +static const struct of_device_id max44009_of_match[] = { + { .compatible = "maxim,max44009" }, + { } +}; +MODULE_DEVICE_TABLE(of, max44009_of_match); + static const struct i2c_device_id max44009_id[] = { { "max44009", 0 }, { } @@ -537,18 +543,13 @@ MODULE_DEVICE_TABLE(i2c, max44009_id); static struct i2c_driver max44009_driver = { .driver = { .name = MAX44009_DRV_NAME, + .of_match_table = max44009_of_match, }, .probe = max44009_probe, .id_table = max44009_id, }; module_i2c_driver(max44009_driver); -static const struct of_device_id max44009_of_match[] = { - { .compatible = "maxim,max44009" }, - { } -}; -MODULE_DEVICE_TABLE(of, max44009_of_match); - MODULE_AUTHOR("Robert Eshleman "); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("MAX44009 ambient light sensor driver"); From c3aba912f40e1755a7423ee83017b9a23cefc62a Mon Sep 17 00:00:00 2001 From: Minghao Chi Date: Thu, 14 Apr 2022 08:53:42 +0000 Subject: [PATCH 2870/4345] spi: spi-imx: using pm_runtime_resume_and_get instead of pm_runtime_get_sync [ Upstream commit 7d34ff58f35c82207698f43af79817a05e1342e5 ] Using pm_runtime_resume_and_get() to replace pm_runtime_get_sync and pm_runtime_put_noidle. This change is just to simplify the code, no actual functional changes. Reported-by: Zeal Robot Signed-off-by: Minghao Chi Link: https://lore.kernel.org/r/20220414085343.2541608-1-chi.minghao@zte.com.cn Signed-off-by: Mark Brown Stable-dep-of: 11951c9e3f36 ("spi: imx: Don't skip cleanup in remove's error path") Signed-off-by: Sasha Levin --- drivers/spi/spi-imx.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 74b3b6ca15ef..66b568de96af 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1554,9 +1554,8 @@ spi_imx_prepare_message(struct spi_master *master, struct spi_message *msg) struct spi_imx_data *spi_imx = spi_master_get_devdata(master); int ret; - ret = pm_runtime_get_sync(spi_imx->dev); + ret = pm_runtime_resume_and_get(spi_imx->dev); if (ret < 0) { - pm_runtime_put_noidle(spi_imx->dev); dev_err(spi_imx->dev, "failed to enable clock\n"); return ret; } @@ -1765,9 +1764,8 @@ static int spi_imx_remove(struct platform_device *pdev) spi_bitbang_stop(&spi_imx->bitbang); - ret = pm_runtime_get_sync(spi_imx->dev); + ret = pm_runtime_resume_and_get(spi_imx->dev); if (ret < 0) { - pm_runtime_put_noidle(spi_imx->dev); dev_err(spi_imx->dev, "failed to enable clock\n"); return ret; } From aa93a46f998a9069368026ac52bba96868c59157 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 6 Mar 2023 07:57:32 +0100 Subject: [PATCH 2871/4345] spi: imx: Don't skip cleanup in remove's error path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 11951c9e3f364d7ae3b568a0e52c8335d43066b5 ] Returning early in a platform driver's remove callback is wrong. In this case the dma resources are not released in the error path. this is never retried later and so this is a permanent leak. To fix this, only skip hardware disabling if waking the device fails. Fixes: d593574aff0a ("spi: imx: do not access registers while clocks disabled") Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230306065733.2170662-2-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-imx.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 66b568de96af..bbc420865f0f 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1764,13 +1764,11 @@ static int spi_imx_remove(struct platform_device *pdev) spi_bitbang_stop(&spi_imx->bitbang); - ret = pm_runtime_resume_and_get(spi_imx->dev); - if (ret < 0) { - dev_err(spi_imx->dev, "failed to enable clock\n"); - return ret; - } - - writel(0, spi_imx->base + MXC_CSPICTRL); + ret = pm_runtime_get_sync(spi_imx->dev); + if (ret >= 0) + writel(0, spi_imx->base + MXC_CSPICTRL); + else + dev_warn(spi_imx->dev, "failed to enable clock, skip hw disable\n"); pm_runtime_dont_use_autosuspend(spi_imx->dev); pm_runtime_put_sync(spi_imx->dev); From 36c237b202a406ba441892eabcf44e60dae7ad73 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Mon, 20 Mar 2023 14:29:31 +0800 Subject: [PATCH 2872/4345] usb: gadget: udc: renesas_usb3: Fix use after free bug in renesas_usb3_remove due to race condition [ Upstream commit 2b947f8769be8b8181dc795fd292d3e7120f5204 ] In renesas_usb3_probe, role_work is bound with renesas_usb3_role_work. renesas_usb3_start will be called to start the work. If we remove the driver which will call usbhs_remove, there may be an unfinished work. The possible sequence is as follows: CPU0 CPU1 renesas_usb3_role_work renesas_usb3_remove usb_role_switch_unregister device_unregister kfree(sw) //free usb3->role_sw usb_role_switch_set_role //use usb3->role_sw The usb3->role_sw could be freed under such circumstance and then used in usb_role_switch_set_role. This bug was found by static analysis. And note that removing a driver is a root-only operation, and should never happen in normal case. But the root user may directly remove the device which will also trigger the remove function. Fix it by canceling the work before cleanup in the renesas_usb3_remove. Fixes: 39facfa01c9f ("usb: gadget: udc: renesas_usb3: Add register of usb role switch") Signed-off-by: Zheng Wang Reviewed-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20230320062931.505170-1-zyytlz.wz@163.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/renesas_usb3.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 601829a6b4ba..a10f41c4a3f2 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -2568,6 +2568,7 @@ static int renesas_usb3_remove(struct platform_device *pdev) debugfs_remove_recursive(usb3->dentry); device_remove_file(&pdev->dev, &dev_attr_role); + cancel_work_sync(&usb3->role_work); usb_role_switch_unregister(usb3->role_sw); usb_del_gadget_udc(&usb3->gadget); From eb971efca7f023563fceb098d6d578d4123a97bd Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Thu, 9 Mar 2023 17:56:31 +0100 Subject: [PATCH 2873/4345] PCI: imx6: Install the fault handler only on compatible match [ Upstream commit 5f5ac460dfe7f4e11f99de9870f240e39189cf72 ] commit bb38919ec56e ("PCI: imx6: Add support for i.MX6 PCIe controller") added a fault hook to this driver in the probe function. So it was only installed if needed. commit bde4a5a00e76 ("PCI: imx6: Allow probe deferral by reset GPIO") moved it from probe to driver init which installs the hook unconditionally as soon as the driver is compiled into a kernel. When this driver is compiled as a module, the hook is not registered until after the driver has been matched with a .compatible and loaded. commit 415b6185c541 ("PCI: imx6: Fix config read timeout handling") extended the fault handling code. commit 2d8ed461dbc9 ("PCI: imx6: Add support for i.MX8MQ") added some protection for non-ARM architectures, but this does not protect non-i.MX ARM architectures. Since fault handlers can be triggered on any architecture for different reasons, there is no guarantee that they will be triggered only for the assumed situation, leading to improper error handling (i.MX6-specific imx6q_pcie_abort_handler) on foreign systems. I had seen strange L3 imprecise external abort messages several times on OMAP4 and OMAP5 devices and couldn't make sense of them until I realized they were related to this unused imx6q driver because I had CONFIG_PCI_IMX6=y. Note that CONFIG_PCI_IMX6=y is useful for kernel binaries that are designed to run on different ARM SoC and be differentiated only by device tree binaries. So turning off CONFIG_PCI_IMX6 is not a solution. Therefore we check the compatible in the init function before registering the fault handler. Link: https://lore.kernel.org/r/e1bcfc3078c82b53aa9b78077a89955abe4ea009.1678380991.git.hns@goldelico.com Fixes: bde4a5a00e76 ("PCI: imx6: Allow probe deferral by reset GPIO") Fixes: 415b6185c541 ("PCI: imx6: Fix config read timeout handling") Fixes: 2d8ed461dbc9 ("PCI: imx6: Add support for i.MX8MQ") Signed-off-by: H. Nikolaus Schaller Signed-off-by: Lorenzo Pieralisi Reviewed-by: Richard Zhu Signed-off-by: Sasha Levin --- drivers/pci/controller/dwc/pci-imx6.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index ceb4815379cd..8117f2dad86c 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -1272,6 +1272,13 @@ DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_SYNOPSYS, 0xabcd, static int __init imx6_pcie_init(void) { #ifdef CONFIG_ARM + struct device_node *np; + + np = of_find_matching_node(NULL, imx6_pcie_of_match); + if (!np) + return -ENODEV; + of_node_put(np); + /* * Since probe() can be deferred we need to make sure that * hook_fault_code is not called after __init memory is freed From 67b6e077fb89ccd5c2fd9dff5682f5b60263a46e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 3 Oct 2021 15:22:54 +0200 Subject: [PATCH 2874/4345] ASoC: es8316: Use IRQF_NO_AUTOEN when requesting the IRQ [ Upstream commit 1cf2aa665901054b140eb71748661ceae99b6b5a ] Use the new IRQF_NO_AUTOEN flag when requesting the IRQ, rather then disabling it immediately after requesting it. This fixes a possible race where the IRQ might trigger between requesting and disabling it; and this also leads to a small code cleanup. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20211003132255.31743-1-hdegoede@redhat.com Signed-off-by: Mark Brown Stable-dep-of: 39db65a0a17b ("ASoC: es8316: Handle optional IRQ assignment") Signed-off-by: Sasha Levin --- sound/soc/codecs/es8316.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c index 609459077f9d..aa23e4e67189 100644 --- a/sound/soc/codecs/es8316.c +++ b/sound/soc/codecs/es8316.c @@ -808,12 +808,9 @@ static int es8316_i2c_probe(struct i2c_client *i2c_client, mutex_init(&es8316->lock); ret = devm_request_threaded_irq(dev, es8316->irq, NULL, es8316_irq, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT | IRQF_NO_AUTOEN, "es8316", es8316); - if (ret == 0) { - /* Gets re-enabled by es8316_set_jack() */ - disable_irq(es8316->irq); - } else { + if (ret) { dev_warn(dev, "Failed to get IRQ %d: %d\n", es8316->irq, ret); es8316->irq = -ENXIO; } From d4a3c912c87b5ce0076b150c6fffd55e1c443e22 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 28 Mar 2023 12:49:01 +0300 Subject: [PATCH 2875/4345] ASoC: es8316: Handle optional IRQ assignment [ Upstream commit 39db65a0a17b54915b269d3685f253a4731f344c ] The driver is able to work fine without relying on a mandatory interrupt being assigned to the I2C device. This is only needed when making use of the jack-detect support. However, the following warning message is always emitted when there is no such interrupt available: es8316 0-0011: Failed to get IRQ 0: -22 Do not attempt to request an IRQ if it is not available/valid. This also ensures the rather misleading message is not displayed anymore. Also note the IRQ validation relies on commit dab472eb931bc291 ("i2c / ACPI: Use 0 to indicate that device does not have interrupt assigned"). Fixes: 822257661031 ("ASoC: es8316: Add jack-detect support") Signed-off-by: Cristian Ciocaltea Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20230328094901.50763-1-cristian.ciocaltea@collabora.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/es8316.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c index aa23e4e67189..bc3d46617a11 100644 --- a/sound/soc/codecs/es8316.c +++ b/sound/soc/codecs/es8316.c @@ -807,12 +807,14 @@ static int es8316_i2c_probe(struct i2c_client *i2c_client, es8316->irq = i2c_client->irq; mutex_init(&es8316->lock); - ret = devm_request_threaded_irq(dev, es8316->irq, NULL, es8316_irq, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT | IRQF_NO_AUTOEN, - "es8316", es8316); - if (ret) { - dev_warn(dev, "Failed to get IRQ %d: %d\n", es8316->irq, ret); - es8316->irq = -ENXIO; + if (es8316->irq > 0) { + ret = devm_request_threaded_irq(dev, es8316->irq, NULL, es8316_irq, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT | IRQF_NO_AUTOEN, + "es8316", es8316); + if (ret) { + dev_warn(dev, "Failed to get IRQ %d: %d\n", es8316->irq, ret); + es8316->irq = -ENXIO; + } } return devm_snd_soc_register_component(&i2c_client->dev, From 00c5b5498bd1910cb2a39277f82637de064a860c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 28 Mar 2023 19:15:29 -0700 Subject: [PATCH 2876/4345] linux/vt_buffer.h: allow either builtin or modular for macros [ Upstream commit 2b76ffe81e32afd6d318dc4547e2ba8c46207b77 ] Fix build errors on ARCH=alpha when CONFIG_MDA_CONSOLE=m. This allows the ARCH macros to be the only ones defined. In file included from ../drivers/video/console/mdacon.c:37: ../arch/alpha/include/asm/vga.h:17:40: error: expected identifier or '(' before 'volatile' 17 | static inline void scr_writew(u16 val, volatile u16 *addr) | ^~~~~~~~ ../include/linux/vt_buffer.h:24:34: note: in definition of macro 'scr_writew' 24 | #define scr_writew(val, addr) (*(addr) = (val)) | ^~~~ ../include/linux/vt_buffer.h:24:40: error: expected ')' before '=' token 24 | #define scr_writew(val, addr) (*(addr) = (val)) | ^ ../arch/alpha/include/asm/vga.h:17:20: note: in expansion of macro 'scr_writew' 17 | static inline void scr_writew(u16 val, volatile u16 *addr) | ^~~~~~~~~~ ../arch/alpha/include/asm/vga.h:25:29: error: expected identifier or '(' before 'volatile' 25 | static inline u16 scr_readw(volatile const u16 *addr) | ^~~~~~~~ Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Randy Dunlap Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Link: https://lore.kernel.org/r/20230329021529.16188-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- include/linux/vt_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index 848db1b1569f..919d999a8c1d 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -16,7 +16,7 @@ #include -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_MDA_CONSOLE) +#if IS_ENABLED(CONFIG_VGA_CONSOLE) || IS_ENABLED(CONFIG_MDA_CONSOLE) #include #endif From bc88243bbe6140d289bb32b4ee4607ba5ce1124a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 30 Mar 2023 23:03:40 +0200 Subject: [PATCH 2877/4345] spi: qup: Don't skip cleanup in remove's error path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 61f49171a43ab1f80c73c5c88c508770c461e0f2 ] Returning early in a platform driver's remove callback is wrong. In this case the dma resources are not released in the error path. this is never retried later and so this is a permanent leak. To fix this, only skip hardware disabling if waking the device fails. Fixes: 64ff247a978f ("spi: Add Qualcomm QUP SPI controller support") Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230330210341.2459548-2-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-qup.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index f3877eeb3da6..8bf58510cca6 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -1276,19 +1276,23 @@ static int spi_qup_remove(struct platform_device *pdev) struct spi_qup *controller = spi_master_get_devdata(master); int ret; - ret = pm_runtime_resume_and_get(&pdev->dev); - if (ret < 0) - return ret; + ret = pm_runtime_get_sync(&pdev->dev); - ret = spi_qup_set_state(controller, QUP_STATE_RESET); - if (ret) - return ret; + if (ret >= 0) { + ret = spi_qup_set_state(controller, QUP_STATE_RESET); + if (ret) + dev_warn(&pdev->dev, "failed to reset controller (%pe)\n", + ERR_PTR(ret)); + + clk_disable_unprepare(controller->cclk); + clk_disable_unprepare(controller->iclk); + } else { + dev_warn(&pdev->dev, "failed to resume, skip hw disable (%pe)\n", + ERR_PTR(ret)); + } spi_qup_release_dma(master); - clk_disable_unprepare(controller->cclk); - clk_disable_unprepare(controller->iclk); - pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); From 4bdae667f91155827e9649083439eab26942613f Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 1 Apr 2023 19:59:46 +0200 Subject: [PATCH 2878/4345] spi: fsl-spi: Fix CPM/QE mode Litte Endian [ Upstream commit c20c57d9868d7f9fd1b2904c7801b07e128f6322 ] CPM has the same problem as QE so for CPM also use the fix added by commit 0398fb70940e ("spi/spi_mpc8xxx: Fix QE mode Litte Endian"): CPM mode uses Little Endian so words > 8 bits are byte swapped. Workaround this by always enforcing wordsize 8 for 16 and 32 bits words. Unfortunately this will not work for LSB transfers where wordsize is > 8 bits so disable these for now. Also limit the workaround to 16 and 32 bits words because it can only work for multiples of 8-bits. Signed-off-by: Christophe Leroy Cc: Joakim Tjernlund Fixes: 0398fb70940e ("spi/spi_mpc8xxx: Fix QE mode Litte Endian") Link: https://lore.kernel.org/r/1b7d3e84b1128f42c1887dd2fb9cdf390f541bc1.1680371809.git.christophe.leroy@csgroup.eu Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-fsl-spi.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index bdf94cc7be1a..1bad0ceac81b 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -207,8 +207,8 @@ static int mspi_apply_qe_mode_quirks(struct spi_mpc8xxx_cs *cs, struct spi_device *spi, int bits_per_word) { - /* QE uses Little Endian for words > 8 - * so transform all words > 8 into 8 bits + /* CPM/QE uses Little Endian for words > 8 + * so transform 16 and 32 bits words into 8 bits * Unfortnatly that doesn't work for LSB so * reject these for now */ /* Note: 32 bits word, LSB works iff @@ -216,9 +216,11 @@ static int mspi_apply_qe_mode_quirks(struct spi_mpc8xxx_cs *cs, if (spi->mode & SPI_LSB_FIRST && bits_per_word > 8) return -EINVAL; - if (bits_per_word > 8) + if (bits_per_word <= 8) + return bits_per_word; + if (bits_per_word == 16 || bits_per_word == 32) return 8; /* pretend its 8 bits */ - return bits_per_word; + return -EINVAL; } static int fsl_spi_setup_transfer(struct spi_device *spi, @@ -248,7 +250,7 @@ static int fsl_spi_setup_transfer(struct spi_device *spi, bits_per_word = mspi_apply_cpu_mode_quirks(cs, spi, mpc8xxx_spi, bits_per_word); - else if (mpc8xxx_spi->flags & SPI_QE) + else bits_per_word = mspi_apply_qe_mode_quirks(cs, spi, bits_per_word); From 85b4aa4eb2e3a0da111fd0a1cdbf00f986ac6b6b Mon Sep 17 00:00:00 2001 From: "Dae R. Jeong" Date: Mon, 27 Mar 2023 21:01:53 +0900 Subject: [PATCH 2879/4345] vmci_host: fix a race condition in vmci_host_poll() causing GPF [ Upstream commit ae13381da5ff0e8e084c0323c3cc0a945e43e9c7 ] During fuzzing, a general protection fault is observed in vmci_host_poll(). general protection fault, probably for non-canonical address 0xdffffc0000000019: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x00000000000000c8-0x00000000000000cf] RIP: 0010:__lock_acquire+0xf3/0x5e00 kernel/locking/lockdep.c:4926 <- omitting registers -> Call Trace: lock_acquire+0x1a4/0x4a0 kernel/locking/lockdep.c:5672 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0xb3/0x100 kernel/locking/spinlock.c:162 add_wait_queue+0x3d/0x260 kernel/sched/wait.c:22 poll_wait include/linux/poll.h:49 [inline] vmci_host_poll+0xf8/0x2b0 drivers/misc/vmw_vmci/vmci_host.c:174 vfs_poll include/linux/poll.h:88 [inline] do_pollfd fs/select.c:873 [inline] do_poll fs/select.c:921 [inline] do_sys_poll+0xc7c/0x1aa0 fs/select.c:1015 __do_sys_ppoll fs/select.c:1121 [inline] __se_sys_ppoll+0x2cc/0x330 fs/select.c:1101 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x4e/0xa0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Example thread interleaving that causes the general protection fault is as follows: CPU1 (vmci_host_poll) CPU2 (vmci_host_do_init_context) ----- ----- // Read uninitialized context context = vmci_host_dev->context; // Initialize context vmci_host_dev->context = vmci_ctx_create(); vmci_host_dev->ct_type = VMCIOBJ_CONTEXT; if (vmci_host_dev->ct_type == VMCIOBJ_CONTEXT) { // Dereferencing the wrong pointer poll_wait(..., &context->host_context); } In this scenario, vmci_host_poll() reads vmci_host_dev->context first, and then reads vmci_host_dev->ct_type to check that vmci_host_dev->context is initialized. However, since these two reads are not atomically executed, there is a chance of a race condition as described above. To fix this race condition, read vmci_host_dev->context after checking the value of vmci_host_dev->ct_type so that vmci_host_poll() always reads an initialized context. Reported-by: Dae R. Jeong Fixes: 8bf503991f87 ("VMCI: host side driver implementation.") Signed-off-by: Dae R. Jeong Link: https://lore.kernel.org/r/ZCGFsdBAU4cYww5l@dragonet Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/misc/vmw_vmci/vmci_host.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c index 2d8328d928d5..4a903770b8e1 100644 --- a/drivers/misc/vmw_vmci/vmci_host.c +++ b/drivers/misc/vmw_vmci/vmci_host.c @@ -165,10 +165,16 @@ static int vmci_host_close(struct inode *inode, struct file *filp) static __poll_t vmci_host_poll(struct file *filp, poll_table *wait) { struct vmci_host_dev *vmci_host_dev = filp->private_data; - struct vmci_ctx *context = vmci_host_dev->context; + struct vmci_ctx *context; __poll_t mask = 0; if (vmci_host_dev->ct_type == VMCIOBJ_CONTEXT) { + /* + * Read context only if ct_type == VMCIOBJ_CONTEXT to make + * sure that context is initialized + */ + context = vmci_host_dev->context; + /* Check for VMCI calls to this VM context. */ if (wait) poll_wait(filp, &context->host_context.wait_queue, From 9e5ee4fa0d06d35addf72ccd537e6abaf8d2fdd4 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:09 +0100 Subject: [PATCH 2880/4345] of: Fix modalias string generation [ Upstream commit b19a4266c52de78496fe40f0b37580a3b762e67d ] The helper generating an OF based modalias (of_device_get_modalias()) works fine, but due to the use of snprintf() internally it needs a buffer one byte longer than what should be needed just for the entire string (excluding the '\0'). Most users of this helper are sysfs hooks providing the modalias string to users. They all provide a PAGE_SIZE buffer which is way above the number of bytes required to fit the modalias string and hence do not suffer from this issue. There is another user though, of_device_request_module(), which is only called by drivers/usb/common/ulpi.c. This request module function is faulty, but maybe because in most cases there is an alternative, ULPI driver users have not noticed it. In this function, of_device_get_modalias() is called twice. The first time without buffer just to get the number of bytes required by the modalias string (excluding the null byte), and a second time, after buffer allocation, to fill the buffer. The allocation asks for an additional byte, in order to store the trailing '\0'. However, the buffer *length* provided to of_device_get_modalias() excludes this extra byte. The internal use of snprintf() with a length that is exactly the number of bytes to be written has the effect of using the last available byte to store a '\0', which then smashes the last character of the modalias string. Provide the actual size of the buffer to of_device_get_modalias() to fix this issue. Note: the "str[size - 1] = '\0';" line is not really needed as snprintf will anyway end the string with a null byte, but there is a possibility that this function might be called on a struct device_node without compatible, in this case snprintf() would not be executed. So we keep it just to avoid possible unbounded strings. Cc: Stephen Boyd Cc: Peter Chen Fixes: 9c829c097f2f ("of: device: Support loading a module with OF based modalias") Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-2-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/of/device.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/of/device.c b/drivers/of/device.c index 1122daa8e273..3a547793135c 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -264,12 +264,15 @@ int of_device_request_module(struct device *dev) if (size < 0) return size; - str = kmalloc(size + 1, GFP_KERNEL); + /* Reserve an additional byte for the trailing '\0' */ + size++; + + str = kmalloc(size, GFP_KERNEL); if (!str) return -ENOMEM; of_device_get_modalias(dev, str, size); - str[size] = '\0'; + str[size - 1] = '\0'; ret = request_module(str); kfree(str); From fd4e45d8d7c85ea154a44c91edc96f35dfa701e1 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Wed, 15 Mar 2023 16:54:49 -0700 Subject: [PATCH 2881/4345] PCI/EDR: Clear Device Status after EDR error recovery [ Upstream commit c441b1e03da6c680a3e12da59c554f454f2ccf5e ] During EDR recovery, the OS must clear error status of the port that triggered DPC even if firmware retains control of DPC and AER (see the implementation note in the PCI Firmware spec r3.3, sec 4.6.12). Prior to 068c29a248b6 ("PCI/ERR: Clear PCIe Device Status errors only if OS owns AER"), the port Device Status was cleared in this path: edr_handle_event dpc_process_error(dev) # "dev" triggered DPC pcie_do_recovery(dev, dpc_reset_link) dpc_reset_link # exit DPC pcie_clear_device_status(dev) # clear Device Status After 068c29a248b6, pcie_do_recovery() no longer clears Device Status when firmware controls AER, so the error bit remains set even after recovery. Per the "Downstream Port Containment configuration control" bit in the returned _OSC Control Field (sec 4.5.1), the OS is allowed to clear error status until it evaluates _OST, so clear Device Status in edr_handle_event() if the error recovery was successful. [bhelgaas: commit log] Fixes: 068c29a248b6 ("PCI/ERR: Clear PCIe Device Status errors only if OS owns AER") Link: https://lore.kernel.org/r/20230315235449.1279209-1-sathyanarayanan.kuppuswamy@linux.intel.com Reported-by: Tsaur Erwin Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas Signed-off-by: Sasha Levin --- drivers/pci/pcie/edr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/pcie/edr.c b/drivers/pci/pcie/edr.c index a6b9b479b97a..87734e4c3c20 100644 --- a/drivers/pci/pcie/edr.c +++ b/drivers/pci/pcie/edr.c @@ -193,6 +193,7 @@ send_ost: */ if (estate == PCI_ERS_RESULT_RECOVERED) { pci_dbg(edev, "DPC port successfully recovered\n"); + pcie_clear_device_status(edev); acpi_send_edr_status(pdev, edev, EDR_OST_SUCCESS); } else { pci_dbg(edev, "DPC port recovery failed\n"); From 65b5b2c5fd86fa602da7f55c6178f1508bef2100 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 19:42:58 -0800 Subject: [PATCH 2882/4345] ia64: mm/contig: fix section mismatch warning/error [ Upstream commit 58deeb4ef3b054498747d0929d94ac53ab90981f ] alloc_per_cpu_data() is called by find_memory(), which is marked as __init. Therefore alloc_per_cpu_data() can also be marked as __init to remedy this modpost problem. WARNING: modpost: vmlinux.o: section mismatch in reference: alloc_per_cpu_data (section: .text) -> memblock_alloc_try_nid (section: .init.text) Link: https://lkml.kernel.org/r/20230223034258.12917-1-rdunlap@infradead.org Fixes: 4b9ddc7cf272 ("[IA64] Fix section mismatch in contig.c version of per_cpu_init()") Signed-off-by: Randy Dunlap Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- arch/ia64/mm/contig.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index e30e360beef8..c638e012ad05 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -79,7 +79,7 @@ skip: return __per_cpu_start + __per_cpu_offset[smp_processor_id()]; } -static inline void +static inline __init void alloc_per_cpu_data(void) { size_t size = PERCPU_PAGE_SIZE * num_possible_cpus(); From b4b4409510a3f4e08247292832a1886ec8d9629f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 19:43:09 -0800 Subject: [PATCH 2883/4345] ia64: salinfo: placate defined-but-not-used warning [ Upstream commit 0de155752b152d6bcd96b5b5bf20af336abd183a ] When CONFIG_PROC_FS is not set, proc_salinfo_show() is not used. Mark the function as __maybe_unused to quieten the warning message. ../arch/ia64/kernel/salinfo.c:584:12: warning: 'proc_salinfo_show' defined but not used [-Wunused-function] 584 | static int proc_salinfo_show(struct seq_file *m, void *v) | ^~~~~~~~~~~~~~~~~ Link: https://lkml.kernel.org/r/20230223034309.13375-1-rdunlap@infradead.org Fixes: 3f3942aca6da ("proc: introduce proc_create_single{,_data}") Signed-off-by: Randy Dunlap Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- arch/ia64/kernel/salinfo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index a25ab9b37953..bb99b543dc67 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -581,7 +581,7 @@ static int salinfo_cpu_pre_down(unsigned int cpu) * 'data' contains an integer that corresponds to the feature we're * testing */ -static int proc_salinfo_show(struct seq_file *m, void *v) +static int __maybe_unused proc_salinfo_show(struct seq_file *m, void *v) { unsigned long data = (unsigned long)v; seq_puts(m, (sal_platform_features & data) ? "1\n" : "0\n"); From 01710564a92a32d0dfedc0d35a68102e76f16d20 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 23 Mar 2023 15:52:45 -0700 Subject: [PATCH 2884/4345] scripts/gdb: bail early if there are no clocks [ Upstream commit 1d7adbc74c009057ed9dc3112f388e91a9c79acc ] Avoid generating an exception if there are no clocks registered: (gdb) lx-clk-summary enable prepare protect clock count count count rate ------------------------------------------------------------------------ Python Exception : No symbol "clk_root_list" in current context. Error occurred in Python: No symbol "clk_root_list" in current context. Link: https://lkml.kernel.org/r/20230323225246.3302977-1-f.fainelli@gmail.com Fixes: d1e9710b63d8 ("scripts/gdb: initial clk support: lx-clk-summary") Signed-off-by: Florian Fainelli Cc: Jan Kiszka Cc: Kieran Bingham Cc: Leonard Crestez Cc: Stephen Boyd Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- scripts/gdb/linux/clk.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/gdb/linux/clk.py b/scripts/gdb/linux/clk.py index 061aecfa294e..7a01fdc3e844 100644 --- a/scripts/gdb/linux/clk.py +++ b/scripts/gdb/linux/clk.py @@ -41,6 +41,8 @@ are cached and potentially out of date""" self.show_subtree(child, level + 1) def invoke(self, arg, from_tty): + if utils.gdb_eval_or_none("clk_root_list") is None: + raise gdb.GdbError("No clocks registered") gdb.write(" enable prepare protect \n") gdb.write(" clock count count count rate \n") gdb.write("------------------------------------------------------------------------\n") From 174d7483f15cbdba114ef04b6d2bc79a7d04c625 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 23 Mar 2023 16:16:57 -0700 Subject: [PATCH 2885/4345] scripts/gdb: bail early if there are no generic PD [ Upstream commit f19c3c2959e465209ade1a7a699e6cbf4359ce78 ] Avoid generating an exception if there are no generic power domain(s) registered: (gdb) lx-genpd-summary domain status children /device runtime status ---------------------------------------------------------------------- Python Exception : No symbol "gpd_list" in current context. Error occurred in Python: No symbol "gpd_list" in current context. (gdb) quit [f.fainelli@gmail.com: correctly invoke gdb_eval_or_none] Link: https://lkml.kernel.org/r/20230327185746.3856407-1-f.fainelli@gmail.com Link: https://lkml.kernel.org/r/20230323231659.3319941-1-f.fainelli@gmail.com Fixes: 8207d4a88e1e ("scripts/gdb: add lx-genpd-summary command") Signed-off-by: Florian Fainelli Cc: Jan Kiszka Cc: Kieran Bingham Cc: Leonard Crestez Cc: Stephen Boyd Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- scripts/gdb/linux/genpd.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/scripts/gdb/linux/genpd.py b/scripts/gdb/linux/genpd.py index 39cd1abd8559..b53649c0a77a 100644 --- a/scripts/gdb/linux/genpd.py +++ b/scripts/gdb/linux/genpd.py @@ -5,7 +5,7 @@ import gdb import sys -from linux.utils import CachedType +from linux.utils import CachedType, gdb_eval_or_none from linux.lists import list_for_each_entry generic_pm_domain_type = CachedType('struct generic_pm_domain') @@ -70,6 +70,8 @@ Output is similar to /sys/kernel/debug/pm_genpd/pm_genpd_summary''' gdb.write(' %-50s %s\n' % (kobj_path, rtpm_status_str(dev))) def invoke(self, arg, from_tty): + if gdb_eval_or_none("&gpd_list") is None: + raise gdb.GdbError("No power domain(s) registered") gdb.write('domain status children\n'); gdb.write(' /device runtime status\n'); gdb.write('----------------------------------------------------------------------\n'); From 5bf2d84074ddf68c21591be61e9bb7e9818f5bd4 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Wed, 5 Apr 2023 10:49:22 +0100 Subject: [PATCH 2886/4345] coresight: etm_pmu: Set the module field [ Upstream commit 18996a113f2567aef3057e300e3193ce2df1684c ] struct pmu::module must be set to the module owning the PMU driver. Set this for the coresight etm_pmu. Fixes: 8e264c52e1dab ("coresight: core: Allow the coresight core driver to be built as a module") Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230405094922.667834-1-suzuki.poulose@arm.com Signed-off-by: Sasha Levin --- drivers/hwtracing/coresight/coresight-etm-perf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index bdc34ca449f7..c5698c62b610 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -619,6 +619,7 @@ int __init etm_perf_init(void) etm_pmu.addr_filters_sync = etm_addr_filters_sync; etm_pmu.addr_filters_validate = etm_addr_filters_validate; etm_pmu.nr_addr_filters = ETM_ADDR_CMP_MAX; + etm_pmu.module = THIS_MODULE; ret = perf_pmu_register(&etm_pmu, CORESIGHT_ETM_PMU_NAME, -1); if (ret == 0) From b5a6930fc6a432e32714c4ed3c597077d999cf6d Mon Sep 17 00:00:00 2001 From: Liliang Ye Date: Mon, 3 Apr 2023 23:26:47 +0800 Subject: [PATCH 2887/4345] ASoC: fsl_mqs: move of_node_put() to the correct location [ Upstream commit 1c34890273a020d61d6127ade3f68ed1cb21c16a ] of_node_put() should have been done directly after mqs_priv->regmap = syscon_node_to_regmap(gpr_np); otherwise it creates a reference leak on the success path. To fix this, of_node_put() is moved to the correct location, and change all the gotos to direct returns. Fixes: a9d273671440 ("ASoC: fsl_mqs: Fix error handling in probe") Signed-off-by: Liliang Ye Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20230403152647.17638-1-yll@hust.edu.cn Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/fsl_mqs.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/sound/soc/fsl/fsl_mqs.c b/sound/soc/fsl/fsl_mqs.c index 0d4efbed41da..c33439650823 100644 --- a/sound/soc/fsl/fsl_mqs.c +++ b/sound/soc/fsl/fsl_mqs.c @@ -204,10 +204,10 @@ static int fsl_mqs_probe(struct platform_device *pdev) } mqs_priv->regmap = syscon_node_to_regmap(gpr_np); + of_node_put(gpr_np); if (IS_ERR(mqs_priv->regmap)) { dev_err(&pdev->dev, "failed to get gpr regmap\n"); - ret = PTR_ERR(mqs_priv->regmap); - goto err_free_gpr_np; + return PTR_ERR(mqs_priv->regmap); } } else { regs = devm_platform_ioremap_resource(pdev, 0); @@ -236,8 +236,7 @@ static int fsl_mqs_probe(struct platform_device *pdev) if (IS_ERR(mqs_priv->mclk)) { dev_err(&pdev->dev, "failed to get the clock: %ld\n", PTR_ERR(mqs_priv->mclk)); - ret = PTR_ERR(mqs_priv->mclk); - goto err_free_gpr_np; + return PTR_ERR(mqs_priv->mclk); } dev_set_drvdata(&pdev->dev, mqs_priv); @@ -246,13 +245,9 @@ static int fsl_mqs_probe(struct platform_device *pdev) ret = devm_snd_soc_register_component(&pdev->dev, &soc_codec_fsl_mqs, &fsl_mqs_dai, 1); if (ret) - goto err_free_gpr_np; + return ret; + return 0; - -err_free_gpr_np: - of_node_put(gpr_np); - - return ret; } static int fsl_mqs_remove(struct platform_device *pdev) From b24f1ecc8fe2ceefc14af02edb1744c246d87bf7 Mon Sep 17 00:00:00 2001 From: Dhruva Gole Date: Mon, 17 Apr 2023 14:40:27 +0530 Subject: [PATCH 2888/4345] spi: cadence-quadspi: fix suspend-resume implementations [ Upstream commit 2087e85bb66ee3652dafe732bb9b9b896229eafc ] The cadence QSPI driver misbehaves after performing a full system suspend resume: ... spi-nor spi0.0: resume() failed ... This results in a flash connected via OSPI interface after system suspend- resume to be unusable. fix these suspend and resume functions. Fixes: 140623410536 ("mtd: spi-nor: Add driver for Cadence Quad SPI Flash Controller") Signed-off-by: Dhruva Gole Link: https://lore.kernel.org/r/20230417091027.966146-3-d-gole@ti.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-cadence-quadspi.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 2e1255bf1b42..23d50a19ae27 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1355,17 +1355,30 @@ static int cqspi_remove(struct platform_device *pdev) static int cqspi_suspend(struct device *dev) { struct cqspi_st *cqspi = dev_get_drvdata(dev); + struct spi_master *master = dev_get_drvdata(dev); + int ret; + ret = spi_master_suspend(master); cqspi_controller_enable(cqspi, 0); - return 0; + + clk_disable_unprepare(cqspi->clk); + + return ret; } static int cqspi_resume(struct device *dev) { struct cqspi_st *cqspi = dev_get_drvdata(dev); + struct spi_master *master = dev_get_drvdata(dev); - cqspi_controller_enable(cqspi, 1); - return 0; + clk_prepare_enable(cqspi->clk); + cqspi_wait_idle(cqspi); + cqspi_controller_init(cqspi); + + cqspi->current_cs = -1; + cqspi->sclk = 0; + + return spi_master_resume(master); } static const struct dev_pm_ops cqspi__dev_pm_ops = { From 95d97e182dbd4d75c44c41ae23f35d99df814acc Mon Sep 17 00:00:00 2001 From: John Paul Adrian Glaubitz Date: Wed, 19 Apr 2023 13:48:52 +0200 Subject: [PATCH 2889/4345] sh: sq: Fix incorrect element size for allocating bitmap buffer [ Upstream commit 80f746e2bd0e1da3fdb49a53570e54a1a225faac ] The Store Queue code allocates a bitmap buffer with the size of multiple of sizeof(long) in sq_api_init(). While the buffer size is calculated correctly, the code uses the wrong element size to allocate the buffer which results in the allocated bitmap buffer being too small. Fix this by allocating the buffer with kcalloc() with element size sizeof(long) instead of kzalloc() whose elements size defaults to sizeof(char). Fixes: d7c30c682a27 ("sh: Store Queue API rework.") Reviewed-by: Geert Uytterhoeven Signed-off-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230419114854.528677-1-glaubitz@physik.fu-berlin.de Signed-off-by: Sasha Levin --- arch/sh/kernel/cpu/sh4/sq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c index d432164b23b7..c31ec0fea300 100644 --- a/arch/sh/kernel/cpu/sh4/sq.c +++ b/arch/sh/kernel/cpu/sh4/sq.c @@ -381,7 +381,7 @@ static int __init sq_api_init(void) if (unlikely(!sq_cache)) return ret; - sq_bitmap = kzalloc(size, GFP_KERNEL); + sq_bitmap = kcalloc(size, sizeof(long), GFP_KERNEL); if (unlikely(!sq_bitmap)) goto out; From 7d667749b3dd8b007880f275272446a637d4a627 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Wed, 5 Apr 2023 19:18:53 +0100 Subject: [PATCH 2890/4345] usb: gadget: tegra-xudc: Fix crash in vbus_draw [ Upstream commit 5629d31955297ca47b9283c64fff70f2f34aa528 ] Commit ac82b56bda5f ("usb: gadget: tegra-xudc: Add vbus_draw support") populated the vbus_draw callback for the Tegra XUDC driver. The function tegra_xudc_gadget_vbus_draw(), that was added by this commit, assumes that the pointer 'curr_usbphy' has been initialised, which is not always the case because this is only initialised when the USB role is updated. Fix this crash, by checking that the 'curr_usbphy' is valid before dereferencing. Fixes: ac82b56bda5f ("usb: gadget: tegra-xudc: Add vbus_draw support") Reviewed-by: Thierry Reding Signed-off-by: Jon Hunter Link: https://lore.kernel.org/r/20230405181854.42355-1-jonathanh@nvidia.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/tegra-xudc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index 3ebc8c5416e3..66d5f6a85c84 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -2154,7 +2154,7 @@ static int tegra_xudc_gadget_vbus_draw(struct usb_gadget *gadget, dev_dbg(xudc->dev, "%s: %u mA\n", __func__, m_a); - if (xudc->curr_usbphy->chg_type == SDP_TYPE) + if (xudc->curr_usbphy && xudc->curr_usbphy->chg_type == SDP_TYPE) ret = usb_phy_set_power(xudc->curr_usbphy, m_a); return ret; From e8f64f3200cdc2b896f4df81cf5b4def62df7484 Mon Sep 17 00:00:00 2001 From: Yinhao Hu Date: Wed, 12 Apr 2023 13:58:52 +0800 Subject: [PATCH 2891/4345] usb: chipidea: fix missing goto in `ci_hdrc_probe` [ Upstream commit d6f712f53b79f5017cdcefafb7a5aea9ec52da5d ] From the comment of ci_usb_phy_init, it returns an error code if usb_phy_init has failed, and it should do some clean up, not just return directly. Fix this by goto the error handling. Fixes: 74475ede784d ("usb: chipidea: move PHY operation to core") Reviewed-by: Dongliang Mu Acked-by: Peter Chen Signed-off-by: Yinhao Hu Link: https://lore.kernel.org/r/20230412055852.971991-1-dddddd@hust.edu.cn Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/chipidea/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index f26dd1f054f2..3d18599c5b9e 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -1090,7 +1090,7 @@ static int ci_hdrc_probe(struct platform_device *pdev) ret = ci_usb_phy_init(ci); if (ret) { dev_err(dev, "unable to init phy: %d\n", ret); - return ret; + goto ulpi_exit; } ci->hw_bank.phys = res->start; From 012936502a9cb7b0604e85bb961eb15e2bb40dd9 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 17 Apr 2023 10:51:59 +0800 Subject: [PATCH 2892/4345] usb: mtu3: fix kernel panic at qmu transfer done irq handler [ Upstream commit d28f4091ea7ec3510fd6a3c6d433234e7a2bef14 ] When handle qmu transfer irq, it will unlock @mtu->lock before give back request, if another thread handle disconnect event at the same time, and try to disable ep, it may lock @mtu->lock and free qmu ring, then qmu irq hanlder may get a NULL gpd, avoid the KE by checking gpd's value before handling it. e.g. qmu done irq on cpu0 thread running on cpu1 qmu_done_tx() handle gpd [0] mtu3_requ_complete() mtu3_gadget_ep_disable() unlock @mtu->lock give back request lock @mtu->lock mtu3_ep_disable() mtu3_gpd_ring_free() unlock @mtu->lock lock @mtu->lock get next gpd [1] [1]: goto [0] to handle next gpd, and next gpd may be NULL. Fixes: 48e0d3735aa5 ("usb: mtu3: supports new QMU format") Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230417025203.18097-3-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/mtu3/mtu3_qmu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/usb/mtu3/mtu3_qmu.c b/drivers/usb/mtu3/mtu3_qmu.c index 2ea3157ddb6e..e65586147965 100644 --- a/drivers/usb/mtu3/mtu3_qmu.c +++ b/drivers/usb/mtu3/mtu3_qmu.c @@ -210,6 +210,7 @@ static struct qmu_gpd *advance_enq_gpd(struct mtu3_gpd_ring *ring) return ring->enqueue; } +/* @dequeue may be NULL if ring is unallocated or freed */ static struct qmu_gpd *advance_deq_gpd(struct mtu3_gpd_ring *ring) { if (ring->dequeue < ring->end) @@ -484,7 +485,7 @@ static void qmu_done_tx(struct mtu3 *mtu, u8 epnum) dev_dbg(mtu->dev, "%s EP%d, last=%p, current=%p, enq=%p\n", __func__, epnum, gpd, gpd_current, ring->enqueue); - while (gpd != gpd_current && !GET_GPD_HWO(gpd)) { + while (gpd && gpd != gpd_current && !GET_GPD_HWO(gpd)) { mreq = next_request(mep); @@ -523,7 +524,7 @@ static void qmu_done_rx(struct mtu3 *mtu, u8 epnum) dev_dbg(mtu->dev, "%s EP%d, last=%p, current=%p, enq=%p\n", __func__, epnum, gpd, gpd_current, ring->enqueue); - while (gpd != gpd_current && !GET_GPD_HWO(gpd)) { + while (gpd && gpd != gpd_current && !GET_GPD_HWO(gpd)) { mreq = next_request(mep); From 5a76bc35cce8aeb7afd335a514156e2cd527380d Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 19 Apr 2023 17:27:03 +0300 Subject: [PATCH 2893/4345] firmware: stratix10-svc: Fix an NULL vs IS_ERR() bug in probe [ Upstream commit e1d6ca042e62c2a69513235f8629eb6e62ca79c5 ] The svc_create_memory_pool() function returns error pointers. It never returns NULL. Fix the check. Fixes: 7ca5ce896524 ("firmware: add Intel Stratix10 service layer driver") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/5f9a8cb4-5a4f-460b-9cdc-2fae6c5b7922@kili.mountain Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/firmware/stratix10-svc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index 7dd0ac1a0cfc..78a446cb4348 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -989,8 +989,8 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) return ret; genpool = svc_create_memory_pool(pdev, sh_memory); - if (!genpool) - return -ENOMEM; + if (IS_ERR(genpool)) + return PTR_ERR(genpool); /* allocate service controller and supporting channel */ controller = devm_kzalloc(dev, sizeof(*controller), GFP_KERNEL); From fde8ffaaacfa47459b538f15b9c79be071ea6e34 Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Mon, 10 Apr 2023 14:55:55 -0500 Subject: [PATCH 2894/4345] tty: serial: fsl_lpuart: adjust buffer length to the intended size [ Upstream commit f73fd750552524b06b5d77ebfdd106ccc8fcac61 ] Based on the fls function definition provided below, we should not subtract 1 to obtain the correct buffer length: fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. Fixes: 5887ad43ee02 ("tty: serial: fsl_lpuart: Use cyclic DMA for Rx") Signed-off-by: Shenwei Wang Link: https://lore.kernel.org/r/20230410195555.1003900-1-shenwei.wang@nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/fsl_lpuart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index f481c260b704..a2efa81471f3 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1220,7 +1220,7 @@ static inline int lpuart_start_rx_dma(struct lpuart_port *sport) * 10ms at any baud rate. */ sport->rx_dma_rng_buf_len = (DMA_RX_TIMEOUT * baud / bits / 1000) * 2; - sport->rx_dma_rng_buf_len = (1 << (fls(sport->rx_dma_rng_buf_len) - 1)); + sport->rx_dma_rng_buf_len = (1 << fls(sport->rx_dma_rng_buf_len)); if (sport->rx_dma_rng_buf_len < 16) sport->rx_dma_rng_buf_len = 16; From fd7bf900c3215c77f6d779d1532faa22b79f2430 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Thu, 13 Apr 2023 19:10:21 -0700 Subject: [PATCH 2895/4345] i2c: cadence: cdns_i2c_master_xfer(): Fix runtime PM leak on error path [ Upstream commit ae1664f04f504a998737f5bb563f16b44357bcca ] The cdns_i2c_master_xfer() function gets a runtime PM reference when the function is entered. This reference is released when the function is exited. There is currently one error path where the function exits directly, which leads to a leak of the runtime PM reference. Make sure that this error path also releases the runtime PM reference. Fixes: 1a351b10b967 ("i2c: cadence: Added slave support") Signed-off-by: Lars-Peter Clausen Reviewed-by: Michal Simek Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-cadence.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index 50928216b3f2..24987902ca59 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -792,8 +792,10 @@ static int cdns_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, #if IS_ENABLED(CONFIG_I2C_SLAVE) /* Check i2c operating mode and switch if possible */ if (id->dev_mode == CDNS_I2C_MODE_SLAVE) { - if (id->slave_state != CDNS_I2C_SLAVE_STATE_IDLE) - return -EAGAIN; + if (id->slave_state != CDNS_I2C_SLAVE_STATE_IDLE) { + ret = -EAGAIN; + goto out; + } /* Set mode to master */ cdns_i2c_set_mode(CDNS_I2C_MODE_MASTER, id); From a69eb1200eb699fb8c07f2b42285dfa291af071b Mon Sep 17 00:00:00 2001 From: Kevin Brodsky Date: Tue, 11 Apr 2023 10:27:47 +0100 Subject: [PATCH 2896/4345] uapi/linux/const.h: prefer ISO-friendly __typeof__ [ Upstream commit 31088f6f7906253ef4577f6a9b84e2d42447dba0 ] typeof is (still) a GNU extension, which means that it cannot be used when building ISO C (e.g. -std=c99). It should therefore be avoided in uapi headers in favour of the ISO-friendly __typeof__. Unfortunately this issue could not be detected by CONFIG_UAPI_HEADER_TEST=y as the __ALIGN_KERNEL() macro is not expanded in any uapi header. This matters from a userspace perspective, not a kernel one. uapi headers and their contents are expected to be usable in a variety of situations, and in particular when building ISO C applications (with -std=c99 or similar). This particular problem can be reproduced by trying to use the __ALIGN_KERNEL macro directly in application code, say: #include int align(int x, int a) { return __KERNEL_ALIGN(x, a); } and trying to build that with -std=c99. Link: https://lkml.kernel.org/r/20230411092747.3759032-1-kevin.brodsky@arm.com Fixes: a79ff731a1b2 ("netfilter: xtables: make XT_ALIGN() usable in exported headers by exporting __ALIGN_KERNEL()") Signed-off-by: Kevin Brodsky Reported-by: Ruben Ayrapetyan Tested-by: Ruben Ayrapetyan Reviewed-by: Petr Vorel Tested-by: Petr Vorel Reviewed-by: Masahiro Yamada Cc: Sam Ravnborg Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- include/uapi/linux/const.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index af2a44c08683..a429381e7ca5 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) From d5d628fea5f6181809a9d61b04de6ade53277684 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 14 Apr 2023 10:02:39 -0700 Subject: [PATCH 2897/4345] serial: 8250: Add missing wakeup event reporting [ Upstream commit 0ba9e3a13c6adfa99e32b2576d20820ab10ad48a ] An 8250 UART configured as a wake-up source would not have reported itself through sysfs as being the source of wake-up, correct that. Fixes: b3b708fa2780 ("wake up from a serial port") Signed-off-by: Florian Fainelli Link: https://lore.kernel.org/r/20230414170241.2016255-1-f.fainelli@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_port.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 1f231fcda657..1f9e4b87387b 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -1889,6 +1890,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) unsigned char status; unsigned long flags; struct uart_8250_port *up = up_to_u8250p(port); + struct tty_port *tport = &port->state->port; bool skip_rx = false; if (iir & UART_IIR_NO_INT) @@ -1912,6 +1914,8 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) skip_rx = true; if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { + if (irqd_is_wakeup_set(irq_get_irq_data(port->irq))) + pm_wakeup_event(tport->tty->dev, 0); if (!up->dma || handle_rx_dma(up, iir)) status = serial8250_rx_chars(up, status); } From 4ca4a3e454368d3714aa3f284caa5b016bbf975f Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 18 Apr 2023 22:02:01 +0200 Subject: [PATCH 2898/4345] staging: rtl8192e: Fix W_DISABLE# does not work after stop/start [ Upstream commit 3fac2397f562eb669ddc2f45867a253f3fc26184 ] When loading the driver for rtl8192e, the W_DISABLE# switch is working as intended. But when the WLAN is turned off in software and then turned on again the W_DISABLE# does not work anymore. Reason for this is that in the function _rtl92e_dm_check_rf_ctrl_gpio() the bfirst_after_down is checked and returned when true. bfirst_after_down is set true when switching the WLAN off in software. But it is not set to false again when WLAN is turned on again. Add bfirst_after_down = false in _rtl92e_sta_up to reset bit and fix above described bug. Fixes: 94a799425eee ("From: wlanfae [PATCH 1/8] rtl8192e: Import new version of driver from realtek") Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/20230418200201.GA17398@matrix-ESPRIMO-P710 Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 99c27d6b4233..291f98251f7f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -770,6 +770,7 @@ static int _rtl92e_sta_up(struct net_device *dev, bool is_silent_reset) else netif_wake_queue(dev); + priv->bfirst_after_down = false; return 0; } From c45ab3ab9c371c9ac22bbe1217e5abb2e55a3d4b Mon Sep 17 00:00:00 2001 From: Jishnu Prakash Date: Thu, 13 Apr 2023 15:38:34 -0700 Subject: [PATCH 2899/4345] spmi: Add a check for remove callback when removing a SPMI driver [ Upstream commit b56eef3e16d888883fefab47425036de80dd38fc ] When removing a SPMI driver, there can be a crash due to NULL pointer dereference if it does not have a remove callback defined. This is one such call trace observed when removing the QCOM SPMI PMIC driver: dump_backtrace.cfi_jt+0x0/0x8 dump_stack_lvl+0xd8/0x16c panic+0x188/0x498 __cfi_slowpath+0x0/0x214 __cfi_slowpath+0x1dc/0x214 spmi_drv_remove+0x16c/0x1e0 device_release_driver_internal+0x468/0x79c driver_detach+0x11c/0x1a0 bus_remove_driver+0xc4/0x124 driver_unregister+0x58/0x84 cleanup_module+0x1c/0xc24 [qcom_spmi_pmic] __do_sys_delete_module+0x3ec/0x53c __arm64_sys_delete_module+0x18/0x28 el0_svc_common+0xdc/0x294 el0_svc+0x38/0x9c el0_sync_handler+0x8c/0xf0 el0_sync+0x1b4/0x1c0 If a driver has all its resources allocated through devm_() APIs and does not need any other explicit cleanup, it would not require a remove callback to be defined. Hence, add a check for remove callback presence before calling it when removing a SPMI driver. Link: https://lore.kernel.org/r/1671601032-18397-2-git-send-email-quic_jprakash@quicinc.com Fixes: 6f00f8c8635f ("mfd: qcom-spmi-pmic: Use devm_of_platform_populate()") Fixes: 5a86bf343976 ("spmi: Linux driver framework for SPMI") Signed-off-by: Jishnu Prakash Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230413223834.4084793-7-sboyd@kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/spmi/spmi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c index c16b60f645a4..8ca7e004a53d 100644 --- a/drivers/spmi/spmi.c +++ b/drivers/spmi/spmi.c @@ -348,7 +348,8 @@ static int spmi_drv_remove(struct device *dev) const struct spmi_driver *sdrv = to_spmi_driver(dev->driver); pm_runtime_get_sync(dev); - sdrv->remove(to_spmi_device(dev)); + if (sdrv->remove) + sdrv->remove(to_spmi_device(dev)); pm_runtime_put_noidle(dev); pm_runtime_disable(dev); From d68265ec0bb1e864a4748407a143875162aa84a1 Mon Sep 17 00:00:00 2001 From: Liang He Date: Thu, 30 Mar 2023 11:35:58 +0800 Subject: [PATCH 2900/4345] macintosh/windfarm_smu_sat: Add missing of_node_put() [ Upstream commit 631cf002826007ab7415258ee647dcaf8845ad5a ] We call of_node_get() in wf_sat_probe() after sat is created, so we need the of_node_put() before *kfree(sat)*. Fixes: ac171c46667c ("[PATCH] powerpc: Thermal control for dual core G5s") Signed-off-by: Liang He Signed-off-by: Michael Ellerman Link: https://msgid.link/20230330033558.2562778-1-windhl@126.com Signed-off-by: Sasha Levin --- drivers/macintosh/windfarm_smu_sat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c index e46e1153a0b4..7d7d6213e32a 100644 --- a/drivers/macintosh/windfarm_smu_sat.c +++ b/drivers/macintosh/windfarm_smu_sat.c @@ -171,6 +171,7 @@ static void wf_sat_release(struct kref *ref) if (sat->nr >= 0) sats[sat->nr] = NULL; + of_node_put(sat->node); kfree(sat); } From 701e3e59991381037606524a9a188443823bb269 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 23:01:13 -0800 Subject: [PATCH 2901/4345] powerpc/mpc512x: fix resource printk format warning [ Upstream commit 7538c97e2b80ff6b7a8ea2ecf16a04355461b439 ] Use "%pa" format specifier for resource_size_t to avoid a compiler printk format warning. ../arch/powerpc/platforms/512x/clock-commonclk.c: In function 'mpc5121_clk_provide_backwards_compat': ../arch/powerpc/platforms/512x/clock-commonclk.c:989:44: error: format '%x' expects argument of type 'unsigned int', but argument 4 has type 'resource_size_t' {aka 'long long unsigned int'} [-Werror=format=] 989 | snprintf(devname, sizeof(devname), "%08x.%s", res.start, np->name); \ | ^~~~~~~~~ ~~~~~~~~~ | | | resource_size_t {aka long long unsigned int} Prevents 24 such warnings. Fixes: 01f25c371658 ("clk: mpc512x: add backwards compat to the CCF code") Signed-off-by: Randy Dunlap Signed-off-by: Michael Ellerman Link: https://msgid.link/20230223070116.660-2-rdunlap@infradead.org Signed-off-by: Sasha Levin --- arch/powerpc/platforms/512x/clock-commonclk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c index 30342b60aa63..42c3d40355d9 100644 --- a/arch/powerpc/platforms/512x/clock-commonclk.c +++ b/arch/powerpc/platforms/512x/clock-commonclk.c @@ -984,7 +984,7 @@ static void mpc5121_clk_provide_migration_support(void) #define NODE_PREP do { \ of_address_to_resource(np, 0, &res); \ - snprintf(devname, sizeof(devname), "%08x.%s", res.start, np->name); \ + snprintf(devname, sizeof(devname), "%pa.%s", &res.start, np->name); \ } while (0) #define NODE_CHK(clkname, clkitem, regnode, regflag) do { \ From 4f41f55d82cb7230973f57deb2f7113e0a41ce50 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 23:01:14 -0800 Subject: [PATCH 2902/4345] powerpc/wii: fix resource printk format warnings [ Upstream commit 7b69600d4da0049244e9be2f5ef5a2f8e04fcd9a ] Use "%pa" format specifier for resource_size_t to avoid compiler printk format warnings. ../arch/powerpc/platforms/embedded6xx/flipper-pic.c: In function 'flipper_pic_init': ../include/linux/kern_levels.h:5:25: error: format '%x' expects argument of type 'unsigned int', but argument 2 has type 'resource_size_t' {aka 'long long unsigned int'} [-Werror=format=] ../arch/powerpc/platforms/embedded6xx/flipper-pic.c:148:9: note: in expansion of macro 'pr_info' 148 | pr_info("controller at 0x%08x mapped to 0x%p\n", res.start, io_base); | ^~~~~~~ ../arch/powerpc/platforms/embedded6xx/hlwd-pic.c: In function 'hlwd_pic_init': ../include/linux/kern_levels.h:5:25: error: format '%x' expects argument of type 'unsigned int', but argument 2 has type 'resource_size_t' {aka 'long long unsigned int'} [-Werror=format=] ../arch/powerpc/platforms/embedded6xx/hlwd-pic.c:174:9: note: in expansion of macro 'pr_info' 174 | pr_info("controller at 0x%08x mapped to 0x%p\n", res.start, io_base); | ^~~~~~~ ../arch/powerpc/platforms/embedded6xx/wii.c: In function 'wii_ioremap_hw_regs': ../include/linux/kern_levels.h:5:25: error: format '%x' expects argument of type 'unsigned int', but argument 3 has type 'resource_size_t' {aka 'long long unsigned int'} [-Werror=format=] ../arch/powerpc/platforms/embedded6xx/wii.c:77:17: note: in expansion of macro 'pr_info' 77 | pr_info("%s at 0x%08x mapped to 0x%p\n", name, | ^~~~~~~ Fixes: 028ee972f032 ("powerpc: gamecube/wii: flipper interrupt controller support") Fixes: 9c21025c7845 ("powerpc: wii: hollywood interrupt controller support") Fixes: 5a7ee3198dfa ("powerpc: wii: platform support") Signed-off-by: Randy Dunlap Signed-off-by: Michael Ellerman Link: https://msgid.link/20230223070116.660-3-rdunlap@infradead.org Signed-off-by: Sasha Levin --- arch/powerpc/platforms/embedded6xx/flipper-pic.c | 2 +- arch/powerpc/platforms/embedded6xx/hlwd-pic.c | 2 +- arch/powerpc/platforms/embedded6xx/wii.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c index d39a9213a3e6..7dd2e2f97aae 100644 --- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c +++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c @@ -144,7 +144,7 @@ static struct irq_domain * __init flipper_pic_init(struct device_node *np) } io_base = ioremap(res.start, resource_size(&res)); - pr_info("controller at 0x%08x mapped to 0x%p\n", res.start, io_base); + pr_info("controller at 0x%pa mapped to 0x%p\n", &res.start, io_base); __flipper_quiesce(io_base); diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c index de10c13de15c..c6b492ebb766 100644 --- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c +++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c @@ -173,7 +173,7 @@ static struct irq_domain *hlwd_pic_init(struct device_node *np) return NULL; } - pr_info("controller at 0x%08x mapped to 0x%p\n", res.start, io_base); + pr_info("controller at 0x%pa mapped to 0x%p\n", &res.start, io_base); __hlwd_quiesce(io_base); diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index a802ef957d63..458a63a30e80 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -89,8 +89,8 @@ static void __iomem *wii_ioremap_hw_regs(char *name, char *compatible) hw_regs = ioremap(res.start, resource_size(&res)); if (hw_regs) { - pr_info("%s at 0x%08x mapped to 0x%p\n", name, - res.start, hw_regs); + pr_info("%s at 0x%pa mapped to 0x%p\n", name, + &res.start, hw_regs); } out_put: From 15f3a811bfde9273a7854e53826b0d707876e7d8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 23:01:16 -0800 Subject: [PATCH 2903/4345] powerpc/sysdev/tsi108: fix resource printk format warnings [ Upstream commit 55d8bd02cc1b9f1063993b5c42c9cabf4af67dea ] Use "%pa" format specifier for resource_size_t to avoid a compiler printk format warning. arch/powerpc/sysdev/tsi108_pci.c: In function 'tsi108_setup_pci': include/linux/kern_levels.h:5:25: error: format '%x' expects argument of type 'unsigned int', but argument 2 has type 'resource_size_t' Fixes: c4342ff92bed ("[POWERPC] Update mpc7448hpc2 board irq support using device tree") Fixes: 2b9d7467a6db ("[POWERPC] Add tsi108 pci and platform device data register function") Signed-off-by: Randy Dunlap [mpe: Use pr_info() and unsplit string] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230223070116.660-5-rdunlap@infradead.org Signed-off-by: Sasha Levin --- arch/powerpc/sysdev/tsi108_pci.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c index 49f9541954f8..3664ffcbb313 100644 --- a/arch/powerpc/sysdev/tsi108_pci.c +++ b/arch/powerpc/sysdev/tsi108_pci.c @@ -216,9 +216,8 @@ int __init tsi108_setup_pci(struct device_node *dev, u32 cfg_phys, int primary) (hose)->ops = &tsi108_direct_pci_ops; - printk(KERN_INFO "Found tsi108 PCI host bridge at 0x%08x. " - "Firmware bus number: %d->%d\n", - rsrc.start, hose->first_busno, hose->last_busno); + pr_info("Found tsi108 PCI host bridge at 0x%pa. Firmware bus number: %d->%d\n", + &rsrc.start, hose->first_busno, hose->last_busno); /* Interpret the "ranges" property */ /* This also maps the I/O region and sets isa_io/mem_base */ From 6339b9dcdba2c4049119caf43b11aa7d1e860a7d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 17:42:41 -0800 Subject: [PATCH 2904/4345] macintosh: via-pmu-led: requires ATA to be set [ Upstream commit 05dce4ba125336875cd3eed3c1503fa81cd2f691 ] LEDS_TRIGGER_DISK depends on ATA, so selecting LEDS_TRIGGER_DISK when ATA is not set/enabled causes a Kconfig warning: WARNING: unmet direct dependencies detected for LEDS_TRIGGER_DISK Depends on [n]: NEW_LEDS [=y] && LEDS_TRIGGERS [=y] && ATA [=n] Selected by [y]: - ADB_PMU_LED_DISK [=y] && MACINTOSH_DRIVERS [=y] && ADB_PMU_LED [=y] && LEDS_CLASS [=y] Fix this by making ADB_PMU_LED_DISK depend on ATA. Seen on both PPC32 and PPC64. Fixes: 0e865a80c135 ("macintosh: Remove dependency on IDE_GD_ATA if ADB_PMU_LED_DISK is selected") Signed-off-by: Randy Dunlap Signed-off-by: Michael Ellerman Link: https://msgid.link/20230223014241.20878-1-rdunlap@infradead.org Signed-off-by: Sasha Levin --- drivers/macintosh/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/macintosh/Kconfig b/drivers/macintosh/Kconfig index 539a2ed4e13d..a0e717a986dc 100644 --- a/drivers/macintosh/Kconfig +++ b/drivers/macintosh/Kconfig @@ -86,6 +86,7 @@ config ADB_PMU_LED config ADB_PMU_LED_DISK bool "Use front LED as DISK LED by default" + depends on ATA depends on ADB_PMU_LED depends on LEDS_CLASS select LEDS_TRIGGERS From 3ea9186a3ef518dc9de60e2db9fb8b976792da3d Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Mon, 6 Mar 2023 15:33:41 -0600 Subject: [PATCH 2905/4345] powerpc/rtas: use memmove for potentially overlapping buffer copy [ Upstream commit 271208ee5e335cb1ad280d22784940daf7ddf820 ] Using memcpy() isn't safe when buf is identical to rtas_err_buf, which can happen during boot before slab is up. Full context which may not be obvious from the diff: if (altbuf) { buf = altbuf; } else { buf = rtas_err_buf; if (slab_is_available()) buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC); } if (buf) memcpy(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX); This was found by inspection and I'm not aware of it causing problems in practice. It appears to have been introduced by commit 033ef338b6e0 ("powerpc: Merge rtas.c into arch/powerpc/kernel"); the old ppc64 version of this code did not have this problem. Use memmove() instead. Fixes: 033ef338b6e0 ("powerpc: Merge rtas.c into arch/powerpc/kernel") Signed-off-by: Nathan Lynch Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220-rtas-queue-for-6-4-v1-2-010e4416f13f@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/kernel/rtas.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index c2e407a112a2..5976a25c6264 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -399,7 +399,7 @@ static char *__fetch_rtas_last_error(char *altbuf) buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC); } if (buf) - memcpy(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX); + memmove(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX); } return buf; From 8f381b249424c19ca155302dabad005160c03258 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Mon, 27 Feb 2023 10:35:08 +0800 Subject: [PATCH 2906/4345] perf/core: Fix hardlockup failure caused by perf throttle [ Upstream commit 15def34e2635ab7e0e96f1bc32e1b69609f14942 ] commit e050e3f0a71bf ("perf: Fix broken interrupt rate throttling") introduces a change in throttling threshold judgment. Before this, compare hwc->interrupts and max_samples_per_tick, then increase hwc->interrupts by 1, but this commit reverses order of these two behaviors, causing the semantics of max_samples_per_tick to change. In literal sense of "max_samples_per_tick", if hwc->interrupts == max_samples_per_tick, it should not be throttled, therefore, the judgment condition should be changed to "hwc->interrupts > max_samples_per_tick". In fact, this may cause the hardlockup to fail, The minimum value of max_samples_per_tick may be 1, in this case, the return value of __perf_event_account_interrupt function is 1. As a result, nmi_watchdog gets throttled, which would stop PMU (Use x86 architecture as an example, see x86_pmu_handle_irq). Fixes: e050e3f0a71b ("perf: Fix broken interrupt rate throttling") Signed-off-by: Yang Jihong Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230227023508.102230-1-yangjihong1@huawei.com Signed-off-by: Sasha Levin --- kernel/events/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index f0df3bc0e641..53f36bbaf0c6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8925,8 +8925,8 @@ __perf_event_account_interrupt(struct perf_event *event, int throttle) hwc->interrupts = 1; } else { hwc->interrupts++; - if (unlikely(throttle - && hwc->interrupts >= max_samples_per_tick)) { + if (unlikely(throttle && + hwc->interrupts > max_samples_per_tick)) { __this_cpu_inc(perf_throttled_count); tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); hwc->interrupts = MAX_INTERRUPTS; From ab8646c9a0b11a0fdb319592f786a64045ae8d25 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Mon, 27 Feb 2023 12:59:31 +0200 Subject: [PATCH 2907/4345] clk: at91: clk-sam9x60-pll: fix return value check [ Upstream commit 1bd8e27fd0db0fe7f489213836dcbab92934f8fa ] sam9x60_frac_pll_compute_mul_frac() can't return zero. Remove the check against zero to reflect this. Fixes: 43b1bb4a9b3e ("clk: at91: clk-sam9x60-pll: re-factor to support plls with multiple outputs") Reported-by: Dan Carpenter Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230227105931.2812412-1-claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/at91/clk-sam9x60-pll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c index 5a9daa3643a7..5fe50ba173a8 100644 --- a/drivers/clk/at91/clk-sam9x60-pll.c +++ b/drivers/clk/at91/clk-sam9x60-pll.c @@ -452,7 +452,7 @@ sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock, ret = sam9x60_frac_pll_compute_mul_frac(&frac->core, FCORE_MIN, parent_rate, true); - if (ret <= 0) { + if (ret < 0) { hw = ERR_PTR(ret); goto free; } From f7790aecb3c7599b61f7a686e173e4b0c005b597 Mon Sep 17 00:00:00 2001 From: Daniil Dulov Date: Mon, 27 Feb 2023 01:17:51 -0800 Subject: [PATCH 2908/4345] RDMA/siw: Fix potential page_array out of range access [ Upstream commit 271bfcfb83a9f77cbae3d6e1a16e3c14132922f0 ] When seg is equal to MAX_ARRAY, the loop should break, otherwise it will result in out of range access. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: b9be6f18cf9e ("rdma/siw: transmit path") Signed-off-by: Daniil Dulov Link: https://lore.kernel.org/r/20230227091751.589612-1-d.dulov@aladdin.ru Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/sw/siw/siw_qp_tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index df8802b4981c..ccc6d5bb1a27 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -548,7 +548,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) data_len -= plen; fp_off = 0; - if (++seg > (int)MAX_ARRAY) { + if (++seg >= (int)MAX_ARRAY) { siw_dbg_qp(tx_qp(c_tx), "to many fragments\n"); siw_unmap_pages(page_array, kmap_mask); wqe->processed -= c_tx->bytes_unsent; From 77d9a64cfbc677169264e961dd36c00b5d7cd63c Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 17 Aug 2021 09:32:34 +0800 Subject: [PATCH 2909/4345] workqueue: Rename "delayed" (delayed by active management) to "inactive" [ Upstream commit f97a4a1a3f8769e3452885967955e21c88f3f263 ] There are two kinds of "delayed" work items in workqueue subsystem. One is for timer-delayed work items which are visible to workqueue users. The other kind is for work items delayed by active management which can not be directly visible to workqueue users. We mixed the word "delayed" for both kinds and caused somewhat ambiguity. This patch renames the later one (delayed by active management) to "inactive", because it is used for workqueue active management and most of its related symbols are named with "active" or "activate". All "delayed" and "DELAYED" are carefully checked and renamed one by one to avoid accidentally changing the name of the other kind for timer-delayed. No functional change intended. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo Stable-dep-of: 335a42ebb0ca ("workqueue: Fix hung time report of worker pools") Signed-off-by: Sasha Levin --- include/linux/workqueue.h | 4 +-- kernel/workqueue.c | 58 +++++++++++++++++++-------------------- 2 files changed, 31 insertions(+), 31 deletions(-) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 26de0cae2a0a..2fa9b311e566 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -29,7 +29,7 @@ void delayed_work_timer_fn(struct timer_list *t); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ + WORK_STRUCT_INACTIVE_BIT= 1, /* work item is inactive */ WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */ WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -42,7 +42,7 @@ enum { WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, - WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, + WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0cc2a62e88f9..7f57fed71995 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -207,7 +207,7 @@ struct pool_workqueue { /* L: nr of in_flight works */ int nr_active; /* L: nr of active works */ int max_active; /* L: max active works */ - struct list_head delayed_works; /* L: delayed works */ + struct list_head inactive_works; /* L: inactive works */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ @@ -1145,7 +1145,7 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) } } -static void pwq_activate_delayed_work(struct work_struct *work) +static void pwq_activate_inactive_work(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); @@ -1153,16 +1153,16 @@ static void pwq_activate_delayed_work(struct work_struct *work) if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); - __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); + __clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work)); pwq->nr_active++; } -static void pwq_activate_first_delayed(struct pool_workqueue *pwq) +static void pwq_activate_first_inactive(struct pool_workqueue *pwq) { - struct work_struct *work = list_first_entry(&pwq->delayed_works, + struct work_struct *work = list_first_entry(&pwq->inactive_works, struct work_struct, entry); - pwq_activate_delayed_work(work); + pwq_activate_inactive_work(work); } /** @@ -1185,10 +1185,10 @@ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color) pwq->nr_in_flight[color]--; pwq->nr_active--; - if (!list_empty(&pwq->delayed_works)) { - /* one down, submit a delayed one */ + if (!list_empty(&pwq->inactive_works)) { + /* one down, submit an inactive one */ if (pwq->nr_active < pwq->max_active) - pwq_activate_first_delayed(pwq); + pwq_activate_first_inactive(pwq); } /* is flush in progress and are we at the flushing tip? */ @@ -1290,14 +1290,14 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, debug_work_deactivate(work); /* - * A delayed work item cannot be grabbed directly because + * An inactive work item cannot be grabbed directly because * it might have linked NO_COLOR work items which, if left - * on the delayed_list, will confuse pwq->nr_active + * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Make sure the work * item is activated before grabbing. */ - if (*work_data_bits(work) & WORK_STRUCT_DELAYED) - pwq_activate_delayed_work(work); + if (*work_data_bits(work) & WORK_STRUCT_INACTIVE) + pwq_activate_inactive_work(work); list_del_init(&work->entry); pwq_dec_nr_in_flight(pwq, get_work_color(work)); @@ -1496,8 +1496,8 @@ retry: if (list_empty(worklist)) pwq->pool->watchdog_ts = jiffies; } else { - work_flags |= WORK_STRUCT_DELAYED; - worklist = &pwq->delayed_works; + work_flags |= WORK_STRUCT_INACTIVE; + worklist = &pwq->inactive_works; } debug_work_activate(work); @@ -2534,7 +2534,7 @@ repeat: /* * The above execution of rescued work items could * have created more to rescue through - * pwq_activate_first_delayed() or chained + * pwq_activate_first_inactive() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't @@ -2960,7 +2960,7 @@ reflush: bool drained; raw_spin_lock_irq(&pwq->pool->lock); - drained = !pwq->nr_active && list_empty(&pwq->delayed_works); + drained = !pwq->nr_active && list_empty(&pwq->inactive_works); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) @@ -3714,7 +3714,7 @@ static void pwq_unbound_release_workfn(struct work_struct *work) * @pwq: target pool_workqueue * * If @pwq isn't freezing, set @pwq->max_active to the associated - * workqueue's saved_max_active and activate delayed work items + * workqueue's saved_max_active and activate inactive work items * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. */ static void pwq_adjust_max_active(struct pool_workqueue *pwq) @@ -3743,9 +3743,9 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq) pwq->max_active = wq->saved_max_active; - while (!list_empty(&pwq->delayed_works) && + while (!list_empty(&pwq->inactive_works) && pwq->nr_active < pwq->max_active) { - pwq_activate_first_delayed(pwq); + pwq_activate_first_inactive(pwq); kick = true; } @@ -3776,7 +3776,7 @@ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; - INIT_LIST_HEAD(&pwq->delayed_works); + INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn); @@ -4363,7 +4363,7 @@ static bool pwq_busy(struct pool_workqueue *pwq) if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1)) return true; - if (pwq->nr_active || !list_empty(&pwq->delayed_works)) + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) return true; return false; @@ -4559,7 +4559,7 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) else pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); - ret = !list_empty(&pwq->delayed_works); + ret = !list_empty(&pwq->inactive_works); preempt_enable(); rcu_read_unlock(); @@ -4755,11 +4755,11 @@ static void show_pwq(struct pool_workqueue *pwq) pr_cont("\n"); } - if (!list_empty(&pwq->delayed_works)) { + if (!list_empty(&pwq->inactive_works)) { bool comma = false; - pr_info(" delayed:"); - list_for_each_entry(work, &pwq->delayed_works, entry) { + pr_info(" inactive:"); + list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } @@ -4789,7 +4789,7 @@ void show_workqueue_state(void) bool idle = true; for_each_pwq(pwq, wq) { - if (pwq->nr_active || !list_empty(&pwq->delayed_works)) { + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { idle = false; break; } @@ -4801,7 +4801,7 @@ void show_workqueue_state(void) for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, flags); - if (pwq->nr_active || !list_empty(&pwq->delayed_works)) + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) show_pwq(pwq); raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); /* @@ -5176,7 +5176,7 @@ EXPORT_SYMBOL_GPL(work_on_cpu_safe); * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable - * workqueues will queue new works to their delayed_works list instead of + * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: From 960167e0e019127891cff4131b5d8d0dccf5466f Mon Sep 17 00:00:00 2001 From: Natalia Petrova Date: Fri, 3 Mar 2023 15:44:08 +0300 Subject: [PATCH 2910/4345] RDMA/rdmavt: Delete unnecessary NULL check [ Upstream commit b73a0b80c69de77d8d4942abb37066531c0169b2 ] There is no need to check 'rdi->qp_dev' for NULL. The field 'qp_dev' is created in rvt_register_device() which will fail if the 'qp_dev' allocation fails in rvt_driver_qp_init(). Overwise this pointer doesn't changed and passed to rvt_qp_exit() by the next step. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 0acb0cc7ecc1 ("IB/rdmavt: Initialize and teardown of qpn table") Signed-off-by: Natalia Petrova Link: https://lore.kernel.org/r/20230303124408.16685-1-n.petrova@fintech.ru Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/sw/rdmavt/qp.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 585a9c76e518..ddc8825d526e 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -505,8 +505,6 @@ void rvt_qp_exit(struct rvt_dev_info *rdi) if (qps_inuse) rvt_pr_err(rdi, "QP memory leak! %u still in use\n", qps_inuse); - if (!rdi->qp_dev) - return; kfree(rdi->qp_dev->qp_table); free_qpn_table(&rdi->qp_dev->qpn_table); From 647781347af925268434c5dc99b04f7077de8e8e Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Tue, 7 Mar 2023 13:53:31 +0100 Subject: [PATCH 2911/4345] workqueue: Fix hung time report of worker pools [ Upstream commit 335a42ebb0ca8ee9997a1731aaaae6dcd704c113 ] The workqueue watchdog prints a warning when there is no progress in a worker pool. Where the progress means that the pool started processing a pending work item. Note that it is perfectly fine to process work items much longer. The progress should be guaranteed by waking up or creating idle workers. show_one_worker_pool() prints state of non-idle worker pool. It shows a delay since the last pool->watchdog_ts. The timestamp is updated when a first pending work is queued in __queue_work(). Also it is updated when a work is dequeued for processing in worker_thread() and rescuer_thread(). The delay is misleading when there is no pending work item. In this case it shows how long the last work item is being proceed. Show zero instead. There is no stall if there is no pending work. Fixes: 82607adcf9cdf40fb7b ("workqueue: implement lockup detector") Signed-off-by: Petr Mladek Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- kernel/workqueue.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 7f57fed71995..b9041ab881bc 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4816,16 +4816,19 @@ void show_workqueue_state(void) for_each_pool(pool, pi) { struct worker *worker; bool first = true; + unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; + /* How long the first pending work is waiting for a worker. */ + if (!list_empty(&pool->worklist)) + hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; + pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); - pr_cont(" hung=%us workers=%d", - jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000, - pool->nr_workers); + pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); From 889a2070dc09e47af5972cd0a3730c9350be4e07 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 10:40:21 +0100 Subject: [PATCH 2912/4345] rtc: omap: include header for omap_rtc_power_off_program prototype MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f69c2b5420497b7a54181ce170d682cbeb1f119f ] Non-static functions should have a prototype: drivers/rtc/rtc-omap.c:410:5: error: no previous prototype for ‘omap_rtc_power_off_program’ [-Werror=missing-prototypes] Fixes: 6256f7f7f217 ("rtc: OMAP: Add support for rtc-only mode") Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311094021.79730-1-krzysztof.kozlowski@linaro.org Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-omap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c index c20fc7937dfa..18ae2a4f26ea 100644 --- a/drivers/rtc/rtc-omap.c +++ b/drivers/rtc/rtc-omap.c @@ -25,6 +25,7 @@ #include #include #include +#include /* * The OMAP RTC is a year/month/day/hours/minutes/seconds BCD clock From 9ad3221c86cc9c6305594b742d4a72dfbd4ea579 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 7 Mar 2023 12:51:27 +0300 Subject: [PATCH 2913/4345] RDMA/mlx4: Prevent shift wrapping in set_user_sq_size() [ Upstream commit d50b3c73f1ac20dabc53dc6e9d64ce9c79a331eb ] The ucmd->log_sq_bb_count variable is controlled by the user so this shift can wrap. Fix it by using check_shl_overflow() in the same way that it was done in commit 515f60004ed9 ("RDMA/hns: Prevent undefined behavior in hns_roce_set_user_sq_size()"). Fixes: 839041329fd3 ("IB/mlx4: Sanity check userspace send queue sizes") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/a8dfbd1d-c019-4556-930b-bab1ded73b10@kili.mountain Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx4/qp.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index c6a815a705fe..255194029e2d 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -412,9 +412,13 @@ static int set_user_sq_size(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, struct mlx4_ib_create_qp *ucmd) { + u32 cnt; + /* Sanity check SQ size before proceeding */ - if ((1 << ucmd->log_sq_bb_count) > dev->dev->caps.max_wqes || - ucmd->log_sq_stride > + if (check_shl_overflow(1, ucmd->log_sq_bb_count, &cnt) || + cnt > dev->dev->caps.max_wqes) + return -EINVAL; + if (ucmd->log_sq_stride > ilog2(roundup_pow_of_two(dev->dev->caps.max_sq_desc_sz)) || ucmd->log_sq_stride < MLX4_IB_MIN_SQ_STRIDE) return -EINVAL; From 9e5a7c110645524accef030e39ffa50ff01dbe86 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Mon, 20 Mar 2023 22:21:42 +0100 Subject: [PATCH 2914/4345] rtc: meson-vrtc: Use ktime_get_real_ts64() to get the current time [ Upstream commit 0e6255fa3f649170da6bd1a544680589cfae1131 ] The VRTC alarm register can be programmed with an amount of seconds after which the SoC will be woken up by the VRTC timer again. We are already converting the alarm time from meson_vrtc_set_alarm() to "seconds since 1970". This means we also need to use "seconds since 1970" for the current time. This fixes a problem where setting the alarm to one minute in the future results in the firmware (which handles wakeup) to output (on the serial console) that the system will be woken up in billions of seconds. ktime_get_raw_ts64() returns the time since boot, not since 1970. Switch to ktime_get_real_ts64() to fix the calculation of the alarm time and to make the SoC wake up at the specified date/time. Also the firmware (which manages suspend) now prints either 59 or 60 seconds until wakeup (depending on how long it takes for the system to enter suspend). Fixes: 6ef35398e827 ("rtc: Add Amlogic Virtual Wake RTC") Signed-off-by: Martin Blumenstingl Reviewed-by: Neil Armstrong Reviewed-by: Kevin Hilman Link: https://lore.kernel.org/r/20230320212142.2355062-1-martin.blumenstingl@googlemail.com Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-meson-vrtc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-meson-vrtc.c b/drivers/rtc/rtc-meson-vrtc.c index e6bd0808a092..18ff8439b5bb 100644 --- a/drivers/rtc/rtc-meson-vrtc.c +++ b/drivers/rtc/rtc-meson-vrtc.c @@ -23,7 +23,7 @@ static int meson_vrtc_read_time(struct device *dev, struct rtc_time *tm) struct timespec64 time; dev_dbg(dev, "%s\n", __func__); - ktime_get_raw_ts64(&time); + ktime_get_real_ts64(&time); rtc_time64_to_tm(time.tv_sec, tm); return 0; @@ -96,7 +96,7 @@ static int __maybe_unused meson_vrtc_suspend(struct device *dev) long alarm_secs; struct timespec64 time; - ktime_get_raw_ts64(&time); + ktime_get_real_ts64(&time); local_time = time.tv_sec; dev_dbg(dev, "alarm_time = %lus, local_time=%lus\n", From 391fbf0d081d23a9919cb7f3a7aa649455991e3f Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:57 +0100 Subject: [PATCH 2915/4345] power: supply: generic-adc-battery: fix unit scaling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 44263f50065969f2344808388bd589740f026167 ] power-supply properties are reported in µV, µA and µW. The IIO API provides mV, mA, mW, so the values need to be multiplied by 1000. Fixes: e60fea794e6e ("power: battery: Generic battery driver using IIO") Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/generic-adc-battery.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index 58f09314741a..09bb4ff291cb 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -138,6 +138,9 @@ static int read_channel(struct gab *adc_bat, enum power_supply_property psp, result); if (ret < 0) pr_err("read channel error\n"); + else + *result *= 1000; + return ret; } From ac7f79ee11c3e965d88fe66bfedaa4a52b624262 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Tue, 31 Jan 2023 09:32:27 +0100 Subject: [PATCH 2916/4345] clk: add missing of_node_put() in "assigned-clocks" property parsing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 27a6e1b09a782517fddac91259970ac466a3f7b6 ] When returning from of_parse_phandle_with_args(), the np member of the of_phandle_args structure should be put after usage. Add missing of_node_put() calls in both __set_clk_parents() and __set_clk_rates(). Fixes: 86be408bfbd8 ("clk: Support for clock parents and rates assigned from device tree") Signed-off-by: Clément Léger Link: https://lore.kernel.org/r/20230131083227.10990-1-clement.leger@bootlin.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/clk-conf.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/clk/clk-conf.c b/drivers/clk/clk-conf.c index 2ef819606c41..1a4e6340f95c 100644 --- a/drivers/clk/clk-conf.c +++ b/drivers/clk/clk-conf.c @@ -33,9 +33,12 @@ static int __set_clk_parents(struct device_node *node, bool clk_supplier) else return rc; } - if (clkspec.np == node && !clk_supplier) + if (clkspec.np == node && !clk_supplier) { + of_node_put(clkspec.np); return 0; + } pclk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); if (IS_ERR(pclk)) { if (PTR_ERR(pclk) != -EPROBE_DEFER) pr_warn("clk: couldn't get parent clock %d for %pOF\n", @@ -48,10 +51,12 @@ static int __set_clk_parents(struct device_node *node, bool clk_supplier) if (rc < 0) goto err; if (clkspec.np == node && !clk_supplier) { + of_node_put(clkspec.np); rc = 0; goto err; } clk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); if (IS_ERR(clk)) { if (PTR_ERR(clk) != -EPROBE_DEFER) pr_warn("clk: couldn't get assigned clock %d for %pOF\n", @@ -93,10 +98,13 @@ static int __set_clk_rates(struct device_node *node, bool clk_supplier) else return rc; } - if (clkspec.np == node && !clk_supplier) + if (clkspec.np == node && !clk_supplier) { + of_node_put(clkspec.np); return 0; + } clk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); if (IS_ERR(clk)) { if (PTR_ERR(clk) != -EPROBE_DEFER) pr_warn("clk: couldn't get clock %d for %pOF\n", From 3ef7a4c0d5cd35ce3d9fa62b28720379604eabdd Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sun, 2 Apr 2023 14:10:13 +0900 Subject: [PATCH 2917/4345] RDMA/siw: Remove namespace check from siw_netdev_event() [ Upstream commit 266e9b3475ba82212062771fdbc40be0e3c06ec8 ] syzbot is reporting that siw_netdev_event(NETDEV_UNREGISTER) cannot destroy siw_device created after unshare(CLONE_NEWNET) due to net namespace check. It seems that this check was by error there and should be removed. Reported-by: syzbot Link: https://syzkaller.appspot.com/bug?extid=5e70d01ee8985ae62a3b Suggested-by: Jason Gunthorpe Suggested-by: Leon Romanovsky Fixes: bdcf26bf9b3a ("rdma/siw: network and RDMA core interface") Signed-off-by: Tetsuo Handa Link: https://lore.kernel.org/r/a44e9ac5-44e2-d575-9e30-02483cc7ffd1@I-love.SAKURA.ne.jp Reviewed-by: Bernard Metzler Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/sw/siw/siw_main.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index 32a553a1b905..5ba0893f1f01 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -458,9 +458,6 @@ static int siw_netdev_event(struct notifier_block *nb, unsigned long event, dev_dbg(&netdev->dev, "siw: event %lu\n", event); - if (dev_net(netdev) != &init_net) - return NOTIFY_OK; - base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (!base_dev) return NOTIFY_OK; From 16f596cfe95602d03513728061177ba7f866506d Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Thu, 30 Mar 2023 10:23:51 +0300 Subject: [PATCH 2918/4345] RDMA/cm: Trace icm_send_rej event before the cm state is reset [ Upstream commit bd9de1badac7e4ff6780365d4aa38983f5e2a436 ] Trace icm_send_rej event before the cm state is reset to idle, so that correct cm state will be logged. For example when an incoming request is rejected, the old trace log was: icm_send_rej: local_id=961102742 remote_id=3829151631 state=IDLE reason=REJ_CONSUMER_DEFINED With this patch: icm_send_rej: local_id=312971016 remote_id=3778819983 state=MRA_REQ_SENT reason=REJ_CONSUMER_DEFINED Fixes: 8dc105befe16 ("RDMA/cm: Add tracepoints to track MAD send operations") Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/20230330072351.481200-1-markzhang@nvidia.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/cm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 3133b6be6cab..db1a25fbe2fa 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -2924,6 +2924,8 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv, (ari && ari_length > IB_CM_REJ_ARI_LENGTH)) return -EINVAL; + trace_icm_send_rej(&cm_id_priv->id, reason); + switch (state) { case IB_CM_REQ_SENT: case IB_CM_MRA_REQ_RCVD: @@ -2954,7 +2956,6 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv, return -EINVAL; } - trace_icm_send_rej(&cm_id_priv->id, reason); ret = ib_post_send_mad(msg, NULL); if (ret) { cm_free_msg(msg); From 8ec6acdb9b6a80eeb13e778dfedb5d72a88f14fe Mon Sep 17 00:00:00 2001 From: Saravanan Vajravel Date: Wed, 5 Apr 2023 21:25:49 -0700 Subject: [PATCH 2919/4345] RDMA/srpt: Add a check for valid 'mad_agent' pointer [ Upstream commit eca5cd9474cd26d62f9756f536e2e656d3f62f3a ] When unregistering MAD agent, srpt module has a non-null check for 'mad_agent' pointer before invoking ib_unregister_mad_agent(). This check can pass if 'mad_agent' variable holds an error value. The 'mad_agent' can have an error value for a short window when srpt_add_one() and srpt_remove_one() is executed simultaneously. In srpt module, added a valid pointer check for 'sport->mad_agent' before unregistering MAD agent. This issue can hit when RoCE driver unregisters ib_device Stack Trace: ------------ BUG: kernel NULL pointer dereference, address: 000000000000004d PGD 145003067 P4D 145003067 PUD 2324fe067 PMD 0 Oops: 0002 [#1] PREEMPT SMP NOPTI CPU: 10 PID: 4459 Comm: kworker/u80:0 Kdump: loaded Tainted: P Hardware name: Dell Inc. PowerEdge R640/06NR82, BIOS 2.5.4 01/13/2020 Workqueue: bnxt_re bnxt_re_task [bnxt_re] RIP: 0010:_raw_spin_lock_irqsave+0x19/0x40 Call Trace: ib_unregister_mad_agent+0x46/0x2f0 [ib_core] IPv6: ADDRCONF(NETDEV_CHANGE): bond0: link becomes ready ? __schedule+0x20b/0x560 srpt_unregister_mad_agent+0x93/0xd0 [ib_srpt] srpt_remove_one+0x20/0x150 [ib_srpt] remove_client_context+0x88/0xd0 [ib_core] bond0: (slave p2p1): link status definitely up, 100000 Mbps full duplex disable_device+0x8a/0x160 [ib_core] bond0: active interface up! ? kernfs_name_hash+0x12/0x80 (NULL device *): Bonding Info Received: rdev: 000000006c0b8247 __ib_unregister_device+0x42/0xb0 [ib_core] (NULL device *): Master: mode: 4 num_slaves:2 ib_unregister_device+0x22/0x30 [ib_core] (NULL device *): Slave: id: 105069936 name:p2p1 link:0 state:0 bnxt_re_stopqps_and_ib_uninit+0x83/0x90 [bnxt_re] bnxt_re_alloc_lag+0x12e/0x4e0 [bnxt_re] Fixes: a42d985bd5b2 ("ib_srpt: Initial SRP Target merge for v3.3-rc1") Reviewed-by: Selvin Xavier Reviewed-by: Kashyap Desai Signed-off-by: Saravanan Vajravel Link: https://lore.kernel.org/r/20230406042549.507328-1-saravanan.vajravel@broadcom.com Reviewed-by: Bart Van Assche Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/srpt/ib_srpt.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index c0ed08fcab48..983f59c87b79 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -549,6 +549,7 @@ static int srpt_format_guid(char *buf, unsigned int size, const __be64 *guid) */ static int srpt_refresh_port(struct srpt_port *sport) { + struct ib_mad_agent *mad_agent; struct ib_mad_reg_req reg_req; struct ib_port_modify port_modify; struct ib_port_attr port_attr; @@ -593,24 +594,26 @@ static int srpt_refresh_port(struct srpt_port *sport) set_bit(IB_MGMT_METHOD_GET, reg_req.method_mask); set_bit(IB_MGMT_METHOD_SET, reg_req.method_mask); - sport->mad_agent = ib_register_mad_agent(sport->sdev->device, - sport->port, - IB_QPT_GSI, - ®_req, 0, - srpt_mad_send_handler, - srpt_mad_recv_handler, - sport, 0); - if (IS_ERR(sport->mad_agent)) { + mad_agent = ib_register_mad_agent(sport->sdev->device, + sport->port, + IB_QPT_GSI, + ®_req, 0, + srpt_mad_send_handler, + srpt_mad_recv_handler, + sport, 0); + if (IS_ERR(mad_agent)) { pr_err("%s-%d: MAD agent registration failed (%ld). Note: this is expected if SR-IOV is enabled.\n", dev_name(&sport->sdev->device->dev), sport->port, - PTR_ERR(sport->mad_agent)); + PTR_ERR(mad_agent)); sport->mad_agent = NULL; memset(&port_modify, 0, sizeof(port_modify)); port_modify.clr_port_cap_mask = IB_PORT_DEVICE_MGMT_SUP; ib_modify_port(sport->sdev->device, sport->port, 0, &port_modify); - + return 0; } + + sport->mad_agent = mad_agent; } return 0; From 823b59fc56170eac408268511c1d6878844f0496 Mon Sep 17 00:00:00 2001 From: Patrick Kelsey Date: Fri, 7 Apr 2023 12:52:39 -0400 Subject: [PATCH 2920/4345] IB/hfi1: Fix SDMA mmu_rb_node not being evicted in LRU order [ Upstream commit 9fe8fec5e43d5a80f43cbf61aaada1b047a1eb61 ] hfi1_mmu_rb_remove_unless_exact() did not move mmu_rb_node objects in mmu_rb_handler->lru_list after getting a cache hit on an mmu_rb_node. As a result, hfi1_mmu_rb_evict() was not guaranteed to evict truly least-recently used nodes. This could be a performance issue for an application when that application: - Uses some long-lived buffers frequently. - Uses a large number of buffers once. - Hits the mmu_rb_handler cache size or pinned-page limits, forcing mmu_rb_handler cache entries to be evicted. In this case, the one-time use buffers cause the long-lived buffer entries to eventually filter to the end of the LRU list where hfi1_mmu_rb_evict() will consider evicting a frequently-used long-lived entry instead of evicting one of the one-time use entries. Fix this by inserting new mmu_rb_node at the tail of mmu_rb_handler->lru_list and move mmu_rb_ndoe to the tail of mmu_rb_handler->lru_list when the mmu_rb_node is a hit in hfi1_mmu_rb_remove_unless_exact(). Change hfi1_mmu_rb_evict() to evict from the head of mmu_rb_handler->lru_list instead of the tail. Fixes: 0636e9ab8355 ("IB/hfi1: Add cache evict LRU list") Signed-off-by: Brendan Cunningham Signed-off-by: Patrick Kelsey Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/168088635931.3027109.10423156330761536044.stgit@252.162.96.66.static.eigbox.net Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/mmu_rb.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index ed8a96ae61ce..d8b6bf271db8 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -171,7 +171,7 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, goto unlock; } __mmu_int_rb_insert(mnode, &handler->root); - list_add(&mnode->list, &handler->lru_list); + list_add_tail(&mnode->list, &handler->lru_list); ret = handler->ops->insert(handler->ops_arg, mnode); if (ret) { @@ -222,8 +222,10 @@ bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, spin_lock_irqsave(&handler->lock, flags); node = __mmu_rb_search(handler, addr, len); if (node) { - if (node->addr == addr && node->len == len) + if (node->addr == addr && node->len == len) { + list_move_tail(&node->list, &handler->lru_list); goto unlock; + } __mmu_int_rb_remove(node, &handler->root); list_del(&node->list); /* remove from LRU list */ ret = true; @@ -247,8 +249,7 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) INIT_LIST_HEAD(&del_list); spin_lock_irqsave(&handler->lock, flags); - list_for_each_entry_safe_reverse(rbnode, ptr, &handler->lru_list, - list) { + list_for_each_entry_safe(rbnode, ptr, &handler->lru_list, list) { if (handler->ops->evict(handler->ops_arg, rbnode, evict_arg, &stop)) { __mmu_int_rb_remove(rbnode, &handler->root); @@ -260,9 +261,7 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) } spin_unlock_irqrestore(&handler->lock, flags); - while (!list_empty(&del_list)) { - rbnode = list_first_entry(&del_list, struct mmu_rb_node, list); - list_del(&rbnode->list); + list_for_each_entry_safe(rbnode, ptr, &del_list, list) { handler->ops->remove(handler->ops_arg, rbnode); } } From 1af73620a191a7721113ed1f8af2dcefc462b1ad Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Mon, 29 Mar 2021 09:54:07 -0400 Subject: [PATCH 2921/4345] IB/hfi1: Add AIP tx traces [ Upstream commit 4bd00b55c978017aad10f0ff3e45525cd62cca07 ] Add traces to allow for debugging issues with AIP tx. Link: https://lore.kernel.org/r/1617026056-50483-2-git-send-email-dennis.dalessandro@cornelisnetworks.com Reviewed-by: Kaike Wan Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe Stable-dep-of: 00cbce5cbf88 ("IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/ipoib_tx.c | 18 ++++- drivers/infiniband/hw/hfi1/trace_tx.h | 104 ++++++++++++++++++++++++++ 2 files changed, 119 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c index ab1eefffc14b..ec187ec74674 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_tx.c +++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c @@ -15,6 +15,7 @@ #include "verbs.h" #include "trace_ibhdrs.h" #include "ipoib.h" +#include "trace_tx.h" /* Add a convenience helper */ #define CIRC_ADD(val, add, size) (((val) + (add)) & ((size) - 1)) @@ -63,12 +64,14 @@ static u64 hfi1_ipoib_used(struct hfi1_ipoib_txq *txq) static void hfi1_ipoib_stop_txq(struct hfi1_ipoib_txq *txq) { + trace_hfi1_txq_stop(txq); if (atomic_inc_return(&txq->stops) == 1) netif_stop_subqueue(txq->priv->netdev, txq->q_idx); } static void hfi1_ipoib_wake_txq(struct hfi1_ipoib_txq *txq) { + trace_hfi1_txq_wake(txq); if (atomic_dec_and_test(&txq->stops)) netif_wake_subqueue(txq->priv->netdev, txq->q_idx); } @@ -89,8 +92,10 @@ static void hfi1_ipoib_check_queue_depth(struct hfi1_ipoib_txq *txq) { ++txq->sent_txreqs; if (hfi1_ipoib_used(txq) >= hfi1_ipoib_ring_hwat(txq) && - !atomic_xchg(&txq->ring_full, 1)) + !atomic_xchg(&txq->ring_full, 1)) { + trace_hfi1_txq_full(txq); hfi1_ipoib_stop_txq(txq); + } } static void hfi1_ipoib_check_queue_stopped(struct hfi1_ipoib_txq *txq) @@ -112,8 +117,10 @@ static void hfi1_ipoib_check_queue_stopped(struct hfi1_ipoib_txq *txq) * to protect against ring overflow. */ if (hfi1_ipoib_used(txq) < hfi1_ipoib_ring_lwat(txq) && - atomic_xchg(&txq->ring_full, 0)) + atomic_xchg(&txq->ring_full, 0)) { + trace_hfi1_txq_xmit_unstopped(txq); hfi1_ipoib_wake_txq(txq); + } } static void hfi1_ipoib_free_tx(struct ipoib_txreq *tx, int budget) @@ -405,6 +412,7 @@ static struct ipoib_txreq *hfi1_ipoib_send_dma_common(struct net_device *dev, sdma_select_engine_sc(priv->dd, txp->flow.tx_queue, txp->flow.sc5); + trace_hfi1_flow_switch(txp->txq); } return tx; @@ -525,6 +533,7 @@ static int hfi1_ipoib_send_dma_list(struct net_device *dev, if (txq->flow.as_int != txp->flow.as_int) { int ret; + trace_hfi1_flow_flush(txq); ret = hfi1_ipoib_flush_tx_list(dev, txq); if (unlikely(ret)) { if (ret == -EBUSY) @@ -635,8 +644,10 @@ static int hfi1_ipoib_sdma_sleep(struct sdma_engine *sde, /* came from non-list submit */ list_add_tail(&txreq->list, &txq->tx_list); if (list_empty(&txq->wait.list)) { - if (!atomic_xchg(&txq->no_desc, 1)) + if (!atomic_xchg(&txq->no_desc, 1)) { + trace_hfi1_txq_queued(txq); hfi1_ipoib_stop_txq(txq); + } iowait_queue(pkts_sent, wait->iow, &sde->dmawait); } @@ -659,6 +670,7 @@ static void hfi1_ipoib_sdma_wakeup(struct iowait *wait, int reason) struct hfi1_ipoib_txq *txq = container_of(wait, struct hfi1_ipoib_txq, wait); + trace_hfi1_txq_wakeup(txq); if (likely(txq->priv->netdev->reg_state == NETREG_REGISTERED)) iowait_schedule(wait, system_highpri_wq, WORK_CPU_UNBOUND); } diff --git a/drivers/infiniband/hw/hfi1/trace_tx.h b/drivers/infiniband/hw/hfi1/trace_tx.h index 769e5e4710c6..847654196dd3 100644 --- a/drivers/infiniband/hw/hfi1/trace_tx.h +++ b/drivers/infiniband/hw/hfi1/trace_tx.h @@ -53,6 +53,7 @@ #include "hfi.h" #include "mad.h" #include "sdma.h" +#include "ipoib.h" const char *parse_sdma_flags(struct trace_seq *p, u64 desc0, u64 desc1); @@ -858,6 +859,109 @@ DEFINE_EVENT( TP_ARGS(qp, flag) ); +DECLARE_EVENT_CLASS(/* AIP */ + hfi1_ipoib_txq_template, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq), + TP_STRUCT__entry(/* entry */ + DD_DEV_ENTRY(txq->priv->dd) + __field(struct hfi1_ipoib_txq *, txq) + __field(struct sdma_engine *, sde) + __field(ulong, head) + __field(ulong, tail) + __field(uint, used) + __field(uint, flow) + __field(int, stops) + __field(int, no_desc) + __field(u8, idx) + __field(u8, stopped) + ), + TP_fast_assign(/* assign */ + DD_DEV_ASSIGN(txq->priv->dd) + __entry->txq = txq; + __entry->sde = txq->sde; + __entry->head = txq->tx_ring.head; + __entry->tail = txq->tx_ring.tail; + __entry->idx = txq->q_idx; + __entry->used = + txq->sent_txreqs - + atomic64_read(&txq->complete_txreqs); + __entry->flow = txq->flow.as_int; + __entry->stops = atomic_read(&txq->stops); + __entry->no_desc = atomic_read(&txq->no_desc); + __entry->stopped = + __netif_subqueue_stopped(txq->priv->netdev, txq->q_idx); + ), + TP_printk(/* print */ + "[%s] txq %llx idx %u sde %llx head %lx tail %lx flow %x used %u stops %d no_desc %d stopped %u", + __get_str(dev), + (unsigned long long)__entry->txq, + __entry->idx, + (unsigned long long)__entry->sde, + __entry->head, + __entry->tail, + __entry->flow, + __entry->used, + __entry->stops, + __entry->no_desc, + __entry->stopped + ) +); + +DEFINE_EVENT(/* queue stop */ + hfi1_ipoib_txq_template, hfi1_txq_stop, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq) +); + +DEFINE_EVENT(/* queue wake */ + hfi1_ipoib_txq_template, hfi1_txq_wake, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq) +); + +DEFINE_EVENT(/* flow flush */ + hfi1_ipoib_txq_template, hfi1_flow_flush, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq) +); + +DEFINE_EVENT(/* flow switch */ + hfi1_ipoib_txq_template, hfi1_flow_switch, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq) +); + +DEFINE_EVENT(/* wakeup */ + hfi1_ipoib_txq_template, hfi1_txq_wakeup, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq) +); + +DEFINE_EVENT(/* full */ + hfi1_ipoib_txq_template, hfi1_txq_full, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq) +); + +DEFINE_EVENT(/* queued */ + hfi1_ipoib_txq_template, hfi1_txq_queued, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq) +); + +DEFINE_EVENT(/* xmit_stopped */ + hfi1_ipoib_txq_template, hfi1_txq_xmit_stopped, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq) +); + +DEFINE_EVENT(/* xmit_unstopped */ + hfi1_ipoib_txq_template, hfi1_txq_xmit_unstopped, + TP_PROTO(struct hfi1_ipoib_txq *txq), + TP_ARGS(txq) +); + #endif /* __HFI1_TRACE_TX_H */ #undef TRACE_INCLUDE_PATH From f84c02597857f6b9db24179f9e3ae65942e993fa Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Mon, 29 Mar 2021 09:54:13 -0400 Subject: [PATCH 2922/4345] IB/hfi1: Add additional usdma traces [ Upstream commit 6b13215df1d37f5be23fc4a01a915a287b25ce15 ] Add traces that were vital in isolating an issue with pq waitlist in commit fa8dac396863 ("IB/hfi1: Fix another case where pq is left on waitlist") Link: https://lore.kernel.org/r/1617026056-50483-8-git-send-email-dennis.dalessandro@cornelisnetworks.com Reviewed-by: Kaike Wan Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe Stable-dep-of: 00cbce5cbf88 ("IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/trace_tx.h | 75 ++++++++++++++++++++++++++ drivers/infiniband/hw/hfi1/user_sdma.c | 12 +++-- drivers/infiniband/hw/hfi1/user_sdma.h | 1 + 3 files changed, 85 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/trace_tx.h b/drivers/infiniband/hw/hfi1/trace_tx.h index 847654196dd3..d44fc54858b9 100644 --- a/drivers/infiniband/hw/hfi1/trace_tx.h +++ b/drivers/infiniband/hw/hfi1/trace_tx.h @@ -54,6 +54,7 @@ #include "mad.h" #include "sdma.h" #include "ipoib.h" +#include "user_sdma.h" const char *parse_sdma_flags(struct trace_seq *p, u64 desc0, u64 desc1); @@ -654,6 +655,80 @@ TRACE_EVENT(hfi1_sdma_user_completion, __entry->code) ); +TRACE_EVENT(hfi1_usdma_defer, + TP_PROTO(struct hfi1_user_sdma_pkt_q *pq, + struct sdma_engine *sde, + struct iowait *wait), + TP_ARGS(pq, sde, wait), + TP_STRUCT__entry(DD_DEV_ENTRY(pq->dd) + __field(struct hfi1_user_sdma_pkt_q *, pq) + __field(struct sdma_engine *, sde) + __field(struct iowait *, wait) + __field(int, engine) + __field(int, empty) + ), + TP_fast_assign(DD_DEV_ASSIGN(pq->dd); + __entry->pq = pq; + __entry->sde = sde; + __entry->wait = wait; + __entry->engine = sde->this_idx; + __entry->empty = list_empty(&__entry->wait->list); + ), + TP_printk("[%s] pq %llx sde %llx wait %llx engine %d empty %d", + __get_str(dev), + (unsigned long long)__entry->pq, + (unsigned long long)__entry->sde, + (unsigned long long)__entry->wait, + __entry->engine, + __entry->empty + ) +); + +TRACE_EVENT(hfi1_usdma_activate, + TP_PROTO(struct hfi1_user_sdma_pkt_q *pq, + struct iowait *wait, + int reason), + TP_ARGS(pq, wait, reason), + TP_STRUCT__entry(DD_DEV_ENTRY(pq->dd) + __field(struct hfi1_user_sdma_pkt_q *, pq) + __field(struct iowait *, wait) + __field(int, reason) + ), + TP_fast_assign(DD_DEV_ASSIGN(pq->dd); + __entry->pq = pq; + __entry->wait = wait; + __entry->reason = reason; + ), + TP_printk("[%s] pq %llx wait %llx reason %d", + __get_str(dev), + (unsigned long long)__entry->pq, + (unsigned long long)__entry->wait, + __entry->reason + ) +); + +TRACE_EVENT(hfi1_usdma_we, + TP_PROTO(struct hfi1_user_sdma_pkt_q *pq, + int we_ret), + TP_ARGS(pq, we_ret), + TP_STRUCT__entry(DD_DEV_ENTRY(pq->dd) + __field(struct hfi1_user_sdma_pkt_q *, pq) + __field(int, state) + __field(int, we_ret) + ), + TP_fast_assign(DD_DEV_ASSIGN(pq->dd); + __entry->pq = pq; + __entry->state = pq->state; + __entry->we_ret = we_ret; + ), + TP_printk("[%s] pq %llx state %d we_ret %d", + __get_str(dev), + (unsigned long long)__entry->pq, + __entry->state, + __entry->we_ret + ) +); + const char *print_u32_array(struct trace_seq *, u32 *, int); #define __print_u32_hex(arr, len) print_u32_array(p, arr, len) diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index 4a4956f96a7e..da5b2e37355a 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -133,6 +133,7 @@ static int defer_packet_queue( container_of(wait->iow, struct hfi1_user_sdma_pkt_q, busy); write_seqlock(&sde->waitlock); + trace_hfi1_usdma_defer(pq, sde, &pq->busy); if (sdma_progress(sde, seq, txreq)) goto eagain; /* @@ -157,7 +158,8 @@ static void activate_packet_queue(struct iowait *wait, int reason) { struct hfi1_user_sdma_pkt_q *pq = container_of(wait, struct hfi1_user_sdma_pkt_q, busy); - pq->busy.lock = NULL; + + trace_hfi1_usdma_activate(pq, wait, reason); xchg(&pq->state, SDMA_PKT_Q_ACTIVE); wake_up(&wait->wait_dma); }; @@ -599,13 +601,17 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, while (req->seqsubmitted != req->info.npkts) { ret = user_sdma_send_pkts(req, pcount); if (ret < 0) { + int we_ret; + if (ret != -EBUSY) goto free_req; - if (wait_event_interruptible_timeout( + we_ret = wait_event_interruptible_timeout( pq->busy.wait_dma, pq->state == SDMA_PKT_Q_ACTIVE, msecs_to_jiffies( - SDMA_IOWAIT_TIMEOUT)) <= 0) + SDMA_IOWAIT_TIMEOUT)); + trace_hfi1_usdma_we(pq, we_ret); + if (we_ret <= 0) flush_pq_iowait(pq); } } diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h index 1e8c02fe8ad1..fabe58139906 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.h +++ b/drivers/infiniband/hw/hfi1/user_sdma.h @@ -53,6 +53,7 @@ #include "common.h" #include "iowait.h" #include "user_exp_rcv.h" +#include "mmu_rb.h" /* The maximum number of Data io vectors per message/request */ #define MAX_VECTORS_PER_REQ 8 From 9c4c6512d7330b743c4ffd18bd999a86ca26db0d Mon Sep 17 00:00:00 2001 From: Patrick Kelsey Date: Fri, 7 Apr 2023 12:52:44 -0400 Subject: [PATCH 2923/4345] IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests [ Upstream commit 00cbce5cbf88459cd1aa1d60d0f1df15477df127 ] hfi1 user SDMA request processing has two bugs that can cause data corruption for user SDMA requests that have multiple payload iovecs where an iovec other than the tail iovec does not run up to the page boundary for the buffer pointed to by that iovec.a Here are the specific bugs: 1. user_sdma_txadd() does not use struct user_sdma_iovec->iov.iov_len. Rather, user_sdma_txadd() will add up to PAGE_SIZE bytes from iovec to the packet, even if some of those bytes are past iovec->iov.iov_len and are thus not intended to be in the packet. 2. user_sdma_txadd() and user_sdma_send_pkts() fail to advance to the next iovec in user_sdma_request->iovs when the current iovec is not PAGE_SIZE and does not contain enough data to complete the packet. The transmitted packet will contain the wrong data from the iovec pages. This has not been an issue with SDMA packets from hfi1 Verbs or PSM2 because they only produce iovecs that end short of PAGE_SIZE as the tail iovec of an SDMA request. Fixing these bugs exposes other bugs with the SDMA pin cache (struct mmu_rb_handler) that get in way of supporting user SDMA requests with multiple payload iovecs whose buffers do not end at PAGE_SIZE. So this commit fixes those issues as well. Here are the mmu_rb_handler bugs that non-PAGE_SIZE-end multi-iovec payload user SDMA requests can hit: 1. Overlapping memory ranges in mmu_rb_handler will result in duplicate pinnings. 2. When extending an existing mmu_rb_handler entry (struct mmu_rb_node), the mmu_rb code (1) removes the existing entry under a lock, (2) releases that lock, pins the new pages, (3) then reacquires the lock to insert the extended mmu_rb_node. If someone else comes in and inserts an overlapping entry between (2) and (3), insert in (3) will fail. The failure path code in this case unpins _all_ pages in either the original mmu_rb_node or the new mmu_rb_node that was inserted between (2) and (3). 3. In hfi1_mmu_rb_remove_unless_exact(), mmu_rb_node->refcount is incremented outside of mmu_rb_handler->lock. As a result, mmu_rb_node could be evicted by another thread that gets mmu_rb_handler->lock and checks mmu_rb_node->refcount before mmu_rb_node->refcount is incremented. 4. Related to #2 above, SDMA request submission failure path does not check mmu_rb_node->refcount before freeing mmu_rb_node object. If there are other SDMA requests in progress whose iovecs have pointers to the now-freed mmu_rb_node(s), those pointers to the now-freed mmu_rb nodes will be dereferenced when those SDMA requests complete. Fixes: 7be85676f1d1 ("IB/hfi1: Don't remove RB entry when not needed.") Fixes: 7724105686e7 ("IB/hfi1: add driver files") Signed-off-by: Brendan Cunningham Signed-off-by: Patrick Kelsey Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/168088636445.3027109.10054635277810177889.stgit@252.162.96.66.static.eigbox.net Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/ipoib_tx.c | 1 + drivers/infiniband/hw/hfi1/mmu_rb.c | 66 +-- drivers/infiniband/hw/hfi1/mmu_rb.h | 8 +- drivers/infiniband/hw/hfi1/sdma.c | 21 +- drivers/infiniband/hw/hfi1/sdma.h | 16 +- drivers/infiniband/hw/hfi1/sdma_txreq.h | 1 + drivers/infiniband/hw/hfi1/trace_mmu.h | 4 - drivers/infiniband/hw/hfi1/user_sdma.c | 600 +++++++++++++++--------- drivers/infiniband/hw/hfi1/user_sdma.h | 5 - drivers/infiniband/hw/hfi1/verbs.c | 4 +- drivers/infiniband/hw/hfi1/vnic_sdma.c | 1 + 11 files changed, 423 insertions(+), 304 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c index ec187ec74674..956fc3fd88b9 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_tx.c +++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c @@ -251,6 +251,7 @@ static int hfi1_ipoib_build_ulp_payload(struct ipoib_txreq *tx, const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; ret = sdma_txadd_page(dd, + NULL, txreq, skb_frag_page(frag), frag->bv_offset, diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index d8b6bf271db8..d331184ded30 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -167,7 +167,7 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, spin_lock_irqsave(&handler->lock, flags); node = __mmu_rb_search(handler, mnode->addr, mnode->len); if (node) { - ret = -EINVAL; + ret = -EEXIST; goto unlock; } __mmu_int_rb_insert(mnode, &handler->root); @@ -184,6 +184,19 @@ unlock: return ret; } +/* Caller must hold handler lock */ +struct mmu_rb_node *hfi1_mmu_rb_get_first(struct mmu_rb_handler *handler, + unsigned long addr, unsigned long len) +{ + struct mmu_rb_node *node; + + trace_hfi1_mmu_rb_search(addr, len); + node = __mmu_int_rb_iter_first(&handler->root, addr, (addr + len) - 1); + if (node) + list_move_tail(&node->list, &handler->lru_list); + return node; +} + /* Caller must hold handler lock */ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, unsigned long addr, @@ -208,34 +221,6 @@ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, return node; } -bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, - unsigned long addr, unsigned long len, - struct mmu_rb_node **rb_node) -{ - struct mmu_rb_node *node; - unsigned long flags; - bool ret = false; - - if (current->mm != handler->mn.mm) - return ret; - - spin_lock_irqsave(&handler->lock, flags); - node = __mmu_rb_search(handler, addr, len); - if (node) { - if (node->addr == addr && node->len == len) { - list_move_tail(&node->list, &handler->lru_list); - goto unlock; - } - __mmu_int_rb_remove(node, &handler->root); - list_del(&node->list); /* remove from LRU list */ - ret = true; - } -unlock: - spin_unlock_irqrestore(&handler->lock, flags); - *rb_node = node; - return ret; -} - void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) { struct mmu_rb_node *rbnode, *ptr; @@ -266,29 +251,6 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) } } -/* - * It is up to the caller to ensure that this function does not race with the - * mmu invalidate notifier which may be calling the users remove callback on - * 'node'. - */ -void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler, - struct mmu_rb_node *node) -{ - unsigned long flags; - - if (current->mm != handler->mn.mm) - return; - - /* Validity of handler and node pointers has been checked by caller. */ - trace_hfi1_mmu_rb_remove(node->addr, node->len); - spin_lock_irqsave(&handler->lock, flags); - __mmu_int_rb_remove(node, &handler->root); - list_del(&node->list); /* remove from LRU list */ - spin_unlock_irqrestore(&handler->lock, flags); - - handler->ops->remove(handler->ops_arg, node); -} - static int mmu_notifier_range_start(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.h b/drivers/infiniband/hw/hfi1/mmu_rb.h index 423aacc67e94..0265d81c6206 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.h +++ b/drivers/infiniband/hw/hfi1/mmu_rb.h @@ -93,10 +93,8 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler); int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, struct mmu_rb_node *mnode); void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg); -void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler, - struct mmu_rb_node *mnode); -bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, - unsigned long addr, unsigned long len, - struct mmu_rb_node **rb_node); +struct mmu_rb_node *hfi1_mmu_rb_get_first(struct mmu_rb_handler *handler, + unsigned long addr, + unsigned long len); #endif /* _HFI1_MMU_RB_H */ diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index a044bee257f9..061562627dae 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -1635,22 +1635,7 @@ static inline void sdma_unmap_desc( struct hfi1_devdata *dd, struct sdma_desc *descp) { - switch (sdma_mapping_type(descp)) { - case SDMA_MAP_SINGLE: - dma_unmap_single( - &dd->pcidev->dev, - sdma_mapping_addr(descp), - sdma_mapping_len(descp), - DMA_TO_DEVICE); - break; - case SDMA_MAP_PAGE: - dma_unmap_page( - &dd->pcidev->dev, - sdma_mapping_addr(descp), - sdma_mapping_len(descp), - DMA_TO_DEVICE); - break; - } + system_descriptor_complete(dd, descp); } /* @@ -3170,7 +3155,7 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx, /* Add descriptor for coalesce buffer */ tx->desc_limit = MAX_DESC; - return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, tx, + return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, NULL, tx, addr, tx->tlen); } @@ -3210,10 +3195,12 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) return rval; } } + /* finish the one just added */ make_tx_sdma_desc( tx, SDMA_MAP_NONE, + NULL, dd->sdma_pad_phys, sizeof(u32) - (tx->packet_len & (sizeof(u32) - 1))); _sdma_close_tx(dd, tx); diff --git a/drivers/infiniband/hw/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h index 7a851191f987..7d4f316ac6e4 100644 --- a/drivers/infiniband/hw/hfi1/sdma.h +++ b/drivers/infiniband/hw/hfi1/sdma.h @@ -635,6 +635,7 @@ static inline dma_addr_t sdma_mapping_addr(struct sdma_desc *d) static inline void make_tx_sdma_desc( struct sdma_txreq *tx, int type, + void *pinning_ctx, dma_addr_t addr, size_t len) { @@ -653,6 +654,7 @@ static inline void make_tx_sdma_desc( << SDMA_DESC0_PHY_ADDR_SHIFT) | (((u64)len & SDMA_DESC0_BYTE_COUNT_MASK) << SDMA_DESC0_BYTE_COUNT_SHIFT); + desc->pinning_ctx = pinning_ctx; } /* helper to extend txreq */ @@ -685,6 +687,7 @@ static inline void _sdma_close_tx(struct hfi1_devdata *dd, static inline int _sdma_txadd_daddr( struct hfi1_devdata *dd, int type, + void *pinning_ctx, struct sdma_txreq *tx, dma_addr_t addr, u16 len) @@ -694,6 +697,7 @@ static inline int _sdma_txadd_daddr( make_tx_sdma_desc( tx, type, + pinning_ctx, addr, len); WARN_ON(len > tx->tlen); tx->tlen -= len; @@ -714,6 +718,7 @@ static inline int _sdma_txadd_daddr( /** * sdma_txadd_page() - add a page to the sdma_txreq * @dd: the device to use for mapping + * @pinning_ctx: context to be released at descriptor retirement * @tx: tx request to which the page is added * @page: page to map * @offset: offset within the page @@ -729,6 +734,7 @@ static inline int _sdma_txadd_daddr( */ static inline int sdma_txadd_page( struct hfi1_devdata *dd, + void *pinning_ctx, struct sdma_txreq *tx, struct page *page, unsigned long offset, @@ -756,8 +762,7 @@ static inline int sdma_txadd_page( return -ENOSPC; } - return _sdma_txadd_daddr( - dd, SDMA_MAP_PAGE, tx, addr, len); + return _sdma_txadd_daddr(dd, SDMA_MAP_PAGE, pinning_ctx, tx, addr, len); } /** @@ -791,7 +796,8 @@ static inline int sdma_txadd_daddr( return rval; } - return _sdma_txadd_daddr(dd, SDMA_MAP_NONE, tx, addr, len); + return _sdma_txadd_daddr(dd, SDMA_MAP_NONE, NULL, tx, + addr, len); } /** @@ -837,8 +843,7 @@ static inline int sdma_txadd_kvaddr( return -ENOSPC; } - return _sdma_txadd_daddr( - dd, SDMA_MAP_SINGLE, tx, addr, len); + return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, NULL, tx, addr, len); } struct iowait_work; @@ -1090,4 +1095,5 @@ extern uint mod_num_sdma; void sdma_update_lmc(struct hfi1_devdata *dd, u64 mask, u32 lid); +void system_descriptor_complete(struct hfi1_devdata *dd, struct sdma_desc *descp); #endif diff --git a/drivers/infiniband/hw/hfi1/sdma_txreq.h b/drivers/infiniband/hw/hfi1/sdma_txreq.h index 514a4784566b..4204650cebc2 100644 --- a/drivers/infiniband/hw/hfi1/sdma_txreq.h +++ b/drivers/infiniband/hw/hfi1/sdma_txreq.h @@ -61,6 +61,7 @@ struct sdma_desc { /* private: don't use directly */ u64 qw[2]; + void *pinning_ctx; }; /** diff --git a/drivers/infiniband/hw/hfi1/trace_mmu.h b/drivers/infiniband/hw/hfi1/trace_mmu.h index 3b7abbc382c2..c3055cff4d6b 100644 --- a/drivers/infiniband/hw/hfi1/trace_mmu.h +++ b/drivers/infiniband/hw/hfi1/trace_mmu.h @@ -78,10 +78,6 @@ DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_rb_search, TP_PROTO(unsigned long addr, unsigned long len), TP_ARGS(addr, len)); -DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_rb_remove, - TP_PROTO(unsigned long addr, unsigned long len), - TP_ARGS(addr, len)); - DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_mem_invalidate, TP_PROTO(unsigned long addr, unsigned long len), TP_ARGS(addr, len)); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index da5b2e37355a..1eb5a44a4ae6 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -65,7 +65,6 @@ #include "hfi.h" #include "sdma.h" -#include "mmu_rb.h" #include "user_sdma.h" #include "verbs.h" /* for the headers */ #include "common.h" /* for struct hfi1_tid_info */ @@ -80,11 +79,7 @@ static unsigned initial_pkt_count = 8; static int user_sdma_send_pkts(struct user_sdma_request *req, u16 maxpkts); static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status); static inline void pq_update(struct hfi1_user_sdma_pkt_q *pq); -static void user_sdma_free_request(struct user_sdma_request *req, bool unpin); -static int pin_vector_pages(struct user_sdma_request *req, - struct user_sdma_iovec *iovec); -static void unpin_vector_pages(struct mm_struct *mm, struct page **pages, - unsigned start, unsigned npages); +static void user_sdma_free_request(struct user_sdma_request *req); static int check_header_template(struct user_sdma_request *req, struct hfi1_pkt_header *hdr, u32 lrhlen, u32 datalen); @@ -122,6 +117,11 @@ static struct mmu_rb_ops sdma_rb_ops = { .invalidate = sdma_rb_invalidate }; +static int add_system_pages_to_sdma_packet(struct user_sdma_request *req, + struct user_sdma_txreq *tx, + struct user_sdma_iovec *iovec, + u32 *pkt_remaining); + static int defer_packet_queue( struct sdma_engine *sde, struct iowait_work *wait, @@ -453,6 +453,7 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, ret = -EINVAL; goto free_req; } + /* Copy the header from the user buffer */ ret = copy_from_user(&req->hdr, iovec[idx].iov_base + sizeof(info), sizeof(req->hdr)); @@ -527,9 +528,8 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, memcpy(&req->iovs[i].iov, iovec + idx++, sizeof(req->iovs[i].iov)); - ret = pin_vector_pages(req, &req->iovs[i]); - if (ret) { - req->data_iovs = i; + if (req->iovs[i].iov.iov_len == 0) { + ret = -EINVAL; goto free_req; } req->data_len += req->iovs[i].iov.iov_len; @@ -627,7 +627,7 @@ free_req: if (req->seqsubmitted) wait_event(pq->busy.wait_dma, (req->seqcomp == req->seqsubmitted - 1)); - user_sdma_free_request(req, true); + user_sdma_free_request(req); pq_update(pq); set_comp_state(pq, cq, info.comp_idx, ERROR, ret); } @@ -739,48 +739,6 @@ static int user_sdma_txadd_ahg(struct user_sdma_request *req, return ret; } -static int user_sdma_txadd(struct user_sdma_request *req, - struct user_sdma_txreq *tx, - struct user_sdma_iovec *iovec, u32 datalen, - u32 *queued_ptr, u32 *data_sent_ptr, - u64 *iov_offset_ptr) -{ - int ret; - unsigned int pageidx, len; - unsigned long base, offset; - u64 iov_offset = *iov_offset_ptr; - u32 queued = *queued_ptr, data_sent = *data_sent_ptr; - struct hfi1_user_sdma_pkt_q *pq = req->pq; - - base = (unsigned long)iovec->iov.iov_base; - offset = offset_in_page(base + iovec->offset + iov_offset); - pageidx = (((iovec->offset + iov_offset + base) - (base & PAGE_MASK)) >> - PAGE_SHIFT); - len = offset + req->info.fragsize > PAGE_SIZE ? - PAGE_SIZE - offset : req->info.fragsize; - len = min((datalen - queued), len); - ret = sdma_txadd_page(pq->dd, &tx->txreq, iovec->pages[pageidx], - offset, len); - if (ret) { - SDMA_DBG(req, "SDMA txreq add page failed %d\n", ret); - return ret; - } - iov_offset += len; - queued += len; - data_sent += len; - if (unlikely(queued < datalen && pageidx == iovec->npages && - req->iov_idx < req->data_iovs - 1)) { - iovec->offset += iov_offset; - iovec = &req->iovs[++req->iov_idx]; - iov_offset = 0; - } - - *queued_ptr = queued; - *data_sent_ptr = data_sent; - *iov_offset_ptr = iov_offset; - return ret; -} - static int user_sdma_send_pkts(struct user_sdma_request *req, u16 maxpkts) { int ret = 0; @@ -812,8 +770,7 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, u16 maxpkts) maxpkts = req->info.npkts - req->seqnum; while (npkts < maxpkts) { - u32 datalen = 0, queued = 0, data_sent = 0; - u64 iov_offset = 0; + u32 datalen = 0; /* * Check whether any of the completions have come back @@ -906,27 +863,17 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, u16 maxpkts) goto free_txreq; } - /* - * If the request contains any data vectors, add up to - * fragsize bytes to the descriptor. - */ - while (queued < datalen && - (req->sent + data_sent) < req->data_len) { - ret = user_sdma_txadd(req, tx, iovec, datalen, - &queued, &data_sent, &iov_offset); - if (ret) - goto free_txreq; - } - /* - * The txreq was submitted successfully so we can update - * the counters. - */ req->koffset += datalen; if (req_opcode(req->info.ctrl) == EXPECTED) req->tidoffset += datalen; - req->sent += data_sent; - if (req->data_len) - iovec->offset += iov_offset; + req->sent += datalen; + while (datalen) { + ret = add_system_pages_to_sdma_packet(req, tx, iovec, + &datalen); + if (ret) + goto free_txreq; + iovec = &req->iovs[req->iov_idx]; + } list_add_tail(&tx->txreq.list, &req->txps); /* * It is important to increment this here as it is used to @@ -963,133 +910,14 @@ free_tx: static u32 sdma_cache_evict(struct hfi1_user_sdma_pkt_q *pq, u32 npages) { struct evict_data evict_data; + struct mmu_rb_handler *handler = pq->handler; evict_data.cleared = 0; evict_data.target = npages; - hfi1_mmu_rb_evict(pq->handler, &evict_data); + hfi1_mmu_rb_evict(handler, &evict_data); return evict_data.cleared; } -static int pin_sdma_pages(struct user_sdma_request *req, - struct user_sdma_iovec *iovec, - struct sdma_mmu_node *node, - int npages) -{ - int pinned, cleared; - struct page **pages; - struct hfi1_user_sdma_pkt_q *pq = req->pq; - - pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL); - if (!pages) - return -ENOMEM; - memcpy(pages, node->pages, node->npages * sizeof(*pages)); - - npages -= node->npages; -retry: - if (!hfi1_can_pin_pages(pq->dd, current->mm, - atomic_read(&pq->n_locked), npages)) { - cleared = sdma_cache_evict(pq, npages); - if (cleared >= npages) - goto retry; - } - pinned = hfi1_acquire_user_pages(current->mm, - ((unsigned long)iovec->iov.iov_base + - (node->npages * PAGE_SIZE)), npages, 0, - pages + node->npages); - if (pinned < 0) { - kfree(pages); - return pinned; - } - if (pinned != npages) { - unpin_vector_pages(current->mm, pages, node->npages, pinned); - return -EFAULT; - } - kfree(node->pages); - node->rb.len = iovec->iov.iov_len; - node->pages = pages; - atomic_add(pinned, &pq->n_locked); - return pinned; -} - -static void unpin_sdma_pages(struct sdma_mmu_node *node) -{ - if (node->npages) { - unpin_vector_pages(mm_from_sdma_node(node), node->pages, 0, - node->npages); - atomic_sub(node->npages, &node->pq->n_locked); - } -} - -static int pin_vector_pages(struct user_sdma_request *req, - struct user_sdma_iovec *iovec) -{ - int ret = 0, pinned, npages; - struct hfi1_user_sdma_pkt_q *pq = req->pq; - struct sdma_mmu_node *node = NULL; - struct mmu_rb_node *rb_node; - struct iovec *iov; - bool extracted; - - extracted = - hfi1_mmu_rb_remove_unless_exact(pq->handler, - (unsigned long) - iovec->iov.iov_base, - iovec->iov.iov_len, &rb_node); - if (rb_node) { - node = container_of(rb_node, struct sdma_mmu_node, rb); - if (!extracted) { - atomic_inc(&node->refcount); - iovec->pages = node->pages; - iovec->npages = node->npages; - iovec->node = node; - return 0; - } - } - - if (!node) { - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (!node) - return -ENOMEM; - - node->rb.addr = (unsigned long)iovec->iov.iov_base; - node->pq = pq; - atomic_set(&node->refcount, 0); - } - - iov = &iovec->iov; - npages = num_user_pages((unsigned long)iov->iov_base, iov->iov_len); - if (node->npages < npages) { - pinned = pin_sdma_pages(req, iovec, node, npages); - if (pinned < 0) { - ret = pinned; - goto bail; - } - node->npages += pinned; - npages = node->npages; - } - iovec->pages = node->pages; - iovec->npages = npages; - iovec->node = node; - - ret = hfi1_mmu_rb_insert(req->pq->handler, &node->rb); - if (ret) { - iovec->node = NULL; - goto bail; - } - return 0; -bail: - unpin_sdma_pages(node); - kfree(node); - return ret; -} - -static void unpin_vector_pages(struct mm_struct *mm, struct page **pages, - unsigned start, unsigned npages) -{ - hfi1_release_user_pages(mm, pages + start, npages, false); - kfree(pages); -} - static int check_header_template(struct user_sdma_request *req, struct hfi1_pkt_header *hdr, u32 lrhlen, u32 datalen) @@ -1431,7 +1259,7 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status) if (req->seqcomp != req->info.npkts - 1) return; - user_sdma_free_request(req, false); + user_sdma_free_request(req); set_comp_state(pq, cq, req->info.comp_idx, state, status); pq_update(pq); } @@ -1442,10 +1270,8 @@ static inline void pq_update(struct hfi1_user_sdma_pkt_q *pq) wake_up(&pq->wait); } -static void user_sdma_free_request(struct user_sdma_request *req, bool unpin) +static void user_sdma_free_request(struct user_sdma_request *req) { - int i; - if (!list_empty(&req->txps)) { struct sdma_txreq *t, *p; @@ -1458,21 +1284,6 @@ static void user_sdma_free_request(struct user_sdma_request *req, bool unpin) } } - for (i = 0; i < req->data_iovs; i++) { - struct sdma_mmu_node *node = req->iovs[i].node; - - if (!node) - continue; - - req->iovs[i].node = NULL; - - if (unpin) - hfi1_mmu_rb_remove(req->pq->handler, - &node->rb); - else - atomic_dec(&node->refcount); - } - kfree(req->tids); clear_bit(req->info.comp_idx, req->pq->req_in_use); } @@ -1490,6 +1301,368 @@ static inline void set_comp_state(struct hfi1_user_sdma_pkt_q *pq, idx, state, ret); } +static void unpin_vector_pages(struct mm_struct *mm, struct page **pages, + unsigned int start, unsigned int npages) +{ + hfi1_release_user_pages(mm, pages + start, npages, false); + kfree(pages); +} + +static void free_system_node(struct sdma_mmu_node *node) +{ + if (node->npages) { + unpin_vector_pages(mm_from_sdma_node(node), node->pages, 0, + node->npages); + atomic_sub(node->npages, &node->pq->n_locked); + } + kfree(node); +} + +static inline void acquire_node(struct sdma_mmu_node *node) +{ + atomic_inc(&node->refcount); + WARN_ON(atomic_read(&node->refcount) < 0); +} + +static inline void release_node(struct mmu_rb_handler *handler, + struct sdma_mmu_node *node) +{ + atomic_dec(&node->refcount); + WARN_ON(atomic_read(&node->refcount) < 0); +} + +static struct sdma_mmu_node *find_system_node(struct mmu_rb_handler *handler, + unsigned long start, + unsigned long end) +{ + struct mmu_rb_node *rb_node; + struct sdma_mmu_node *node; + unsigned long flags; + + spin_lock_irqsave(&handler->lock, flags); + rb_node = hfi1_mmu_rb_get_first(handler, start, (end - start)); + if (!rb_node) { + spin_unlock_irqrestore(&handler->lock, flags); + return NULL; + } + node = container_of(rb_node, struct sdma_mmu_node, rb); + acquire_node(node); + spin_unlock_irqrestore(&handler->lock, flags); + + return node; +} + +static int pin_system_pages(struct user_sdma_request *req, + uintptr_t start_address, size_t length, + struct sdma_mmu_node *node, int npages) +{ + struct hfi1_user_sdma_pkt_q *pq = req->pq; + int pinned, cleared; + struct page **pages; + + pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return -ENOMEM; + +retry: + if (!hfi1_can_pin_pages(pq->dd, current->mm, atomic_read(&pq->n_locked), + npages)) { + SDMA_DBG(req, "Evicting: nlocked %u npages %u", + atomic_read(&pq->n_locked), npages); + cleared = sdma_cache_evict(pq, npages); + if (cleared >= npages) + goto retry; + } + + SDMA_DBG(req, "Acquire user pages start_address %lx node->npages %u npages %u", + start_address, node->npages, npages); + pinned = hfi1_acquire_user_pages(current->mm, start_address, npages, 0, + pages); + + if (pinned < 0) { + kfree(pages); + SDMA_DBG(req, "pinned %d", pinned); + return pinned; + } + if (pinned != npages) { + unpin_vector_pages(current->mm, pages, node->npages, pinned); + SDMA_DBG(req, "npages %u pinned %d", npages, pinned); + return -EFAULT; + } + node->rb.addr = start_address; + node->rb.len = length; + node->pages = pages; + node->npages = npages; + atomic_add(pinned, &pq->n_locked); + SDMA_DBG(req, "done. pinned %d", pinned); + return 0; +} + +static int add_system_pinning(struct user_sdma_request *req, + struct sdma_mmu_node **node_p, + unsigned long start, unsigned long len) + +{ + struct hfi1_user_sdma_pkt_q *pq = req->pq; + struct sdma_mmu_node *node; + int ret; + + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + + node->pq = pq; + ret = pin_system_pages(req, start, len, node, PFN_DOWN(len)); + if (ret == 0) { + ret = hfi1_mmu_rb_insert(pq->handler, &node->rb); + if (ret) + free_system_node(node); + else + *node_p = node; + + return ret; + } + + kfree(node); + return ret; +} + +static int get_system_cache_entry(struct user_sdma_request *req, + struct sdma_mmu_node **node_p, + size_t req_start, size_t req_len) +{ + struct hfi1_user_sdma_pkt_q *pq = req->pq; + u64 start = ALIGN_DOWN(req_start, PAGE_SIZE); + u64 end = PFN_ALIGN(req_start + req_len); + struct mmu_rb_handler *handler = pq->handler; + int ret; + + if ((end - start) == 0) { + SDMA_DBG(req, + "Request for empty cache entry req_start %lx req_len %lx start %llx end %llx", + req_start, req_len, start, end); + return -EINVAL; + } + + SDMA_DBG(req, "req_start %lx req_len %lu", req_start, req_len); + + while (1) { + struct sdma_mmu_node *node = + find_system_node(handler, start, end); + u64 prepend_len = 0; + + SDMA_DBG(req, "node %p start %llx end %llu", node, start, end); + if (!node) { + ret = add_system_pinning(req, node_p, start, + end - start); + if (ret == -EEXIST) { + /* + * Another execution context has inserted a + * conficting entry first. + */ + continue; + } + return ret; + } + + if (node->rb.addr <= start) { + /* + * This entry covers at least part of the region. If it doesn't extend + * to the end, then this will be called again for the next segment. + */ + *node_p = node; + return 0; + } + + SDMA_DBG(req, "prepend: node->rb.addr %lx, node->refcount %d", + node->rb.addr, atomic_read(&node->refcount)); + prepend_len = node->rb.addr - start; + + /* + * This node will not be returned, instead a new node + * will be. So release the reference. + */ + release_node(handler, node); + + /* Prepend a node to cover the beginning of the allocation */ + ret = add_system_pinning(req, node_p, start, prepend_len); + if (ret == -EEXIST) { + /* Another execution context has inserted a conficting entry first. */ + continue; + } + return ret; + } +} + +static int add_mapping_to_sdma_packet(struct user_sdma_request *req, + struct user_sdma_txreq *tx, + struct sdma_mmu_node *cache_entry, + size_t start, + size_t from_this_cache_entry) +{ + struct hfi1_user_sdma_pkt_q *pq = req->pq; + unsigned int page_offset; + unsigned int from_this_page; + size_t page_index; + void *ctx; + int ret; + + /* + * Because the cache may be more fragmented than the memory that is being accessed, + * it's not strictly necessary to have a descriptor per cache entry. + */ + + while (from_this_cache_entry) { + page_index = PFN_DOWN(start - cache_entry->rb.addr); + + if (page_index >= cache_entry->npages) { + SDMA_DBG(req, + "Request for page_index %zu >= cache_entry->npages %u", + page_index, cache_entry->npages); + return -EINVAL; + } + + page_offset = start - ALIGN_DOWN(start, PAGE_SIZE); + from_this_page = PAGE_SIZE - page_offset; + + if (from_this_page < from_this_cache_entry) { + ctx = NULL; + } else { + /* + * In the case they are equal the next line has no practical effect, + * but it's better to do a register to register copy than a conditional + * branch. + */ + from_this_page = from_this_cache_entry; + ctx = cache_entry; + } + + ret = sdma_txadd_page(pq->dd, ctx, &tx->txreq, + cache_entry->pages[page_index], + page_offset, from_this_page); + if (ret) { + /* + * When there's a failure, the entire request is freed by + * user_sdma_send_pkts(). + */ + SDMA_DBG(req, + "sdma_txadd_page failed %d page_index %lu page_offset %u from_this_page %u", + ret, page_index, page_offset, from_this_page); + return ret; + } + start += from_this_page; + from_this_cache_entry -= from_this_page; + } + return 0; +} + +static int add_system_iovec_to_sdma_packet(struct user_sdma_request *req, + struct user_sdma_txreq *tx, + struct user_sdma_iovec *iovec, + size_t from_this_iovec) +{ + struct mmu_rb_handler *handler = req->pq->handler; + + while (from_this_iovec > 0) { + struct sdma_mmu_node *cache_entry; + size_t from_this_cache_entry; + size_t start; + int ret; + + start = (uintptr_t)iovec->iov.iov_base + iovec->offset; + ret = get_system_cache_entry(req, &cache_entry, start, + from_this_iovec); + if (ret) { + SDMA_DBG(req, "pin system segment failed %d", ret); + return ret; + } + + from_this_cache_entry = cache_entry->rb.len - (start - cache_entry->rb.addr); + if (from_this_cache_entry > from_this_iovec) + from_this_cache_entry = from_this_iovec; + + ret = add_mapping_to_sdma_packet(req, tx, cache_entry, start, + from_this_cache_entry); + if (ret) { + /* + * We're guaranteed that there will be no descriptor + * completion callback that releases this node + * because only the last descriptor referencing it + * has a context attached, and a failure means the + * last descriptor was never added. + */ + release_node(handler, cache_entry); + SDMA_DBG(req, "add system segment failed %d", ret); + return ret; + } + + iovec->offset += from_this_cache_entry; + from_this_iovec -= from_this_cache_entry; + } + + return 0; +} + +static int add_system_pages_to_sdma_packet(struct user_sdma_request *req, + struct user_sdma_txreq *tx, + struct user_sdma_iovec *iovec, + u32 *pkt_data_remaining) +{ + size_t remaining_to_add = *pkt_data_remaining; + /* + * Walk through iovec entries, ensure the associated pages + * are pinned and mapped, add data to the packet until no more + * data remains to be added. + */ + while (remaining_to_add > 0) { + struct user_sdma_iovec *cur_iovec; + size_t from_this_iovec; + int ret; + + cur_iovec = iovec; + from_this_iovec = iovec->iov.iov_len - iovec->offset; + + if (from_this_iovec > remaining_to_add) { + from_this_iovec = remaining_to_add; + } else { + /* The current iovec entry will be consumed by this pass. */ + req->iov_idx++; + iovec++; + } + + ret = add_system_iovec_to_sdma_packet(req, tx, cur_iovec, + from_this_iovec); + if (ret) + return ret; + + remaining_to_add -= from_this_iovec; + } + *pkt_data_remaining = remaining_to_add; + + return 0; +} + +void system_descriptor_complete(struct hfi1_devdata *dd, + struct sdma_desc *descp) +{ + switch (sdma_mapping_type(descp)) { + case SDMA_MAP_SINGLE: + dma_unmap_single(&dd->pcidev->dev, sdma_mapping_addr(descp), + sdma_mapping_len(descp), DMA_TO_DEVICE); + break; + case SDMA_MAP_PAGE: + dma_unmap_page(&dd->pcidev->dev, sdma_mapping_addr(descp), + sdma_mapping_len(descp), DMA_TO_DEVICE); + break; + } + + if (descp->pinning_ctx) { + struct sdma_mmu_node *node = descp->pinning_ctx; + + release_node(node->rb.handler, node); + } +} + static bool sdma_rb_filter(struct mmu_rb_node *node, unsigned long addr, unsigned long len) { @@ -1536,8 +1709,7 @@ static void sdma_rb_remove(void *arg, struct mmu_rb_node *mnode) struct sdma_mmu_node *node = container_of(mnode, struct sdma_mmu_node, rb); - unpin_sdma_pages(node); - kfree(node); + free_system_node(node); } static int sdma_rb_invalidate(void *arg, struct mmu_rb_node *mnode) diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h index fabe58139906..9d417aacfa8b 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.h +++ b/drivers/infiniband/hw/hfi1/user_sdma.h @@ -153,16 +153,11 @@ struct sdma_mmu_node { struct user_sdma_iovec { struct list_head list; struct iovec iov; - /* number of pages in this vector */ - unsigned int npages; - /* array of pinned pages for this vector */ - struct page **pages; /* * offset into the virtual address space of the vector at * which we last left off. */ u64 offset; - struct sdma_mmu_node *node; }; /* evict operation argument */ diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 5f3edd255ca3..693922df3543 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -820,8 +820,8 @@ static int build_verbs_tx_desc( /* add icrc, lt byte, and padding to flit */ if (extra_bytes) - ret = sdma_txadd_daddr(sde->dd, &tx->txreq, - sde->dd->sdma_pad_phys, extra_bytes); + ret = sdma_txadd_daddr(sde->dd, &tx->txreq, sde->dd->sdma_pad_phys, + extra_bytes); bail_txadd: return ret; diff --git a/drivers/infiniband/hw/hfi1/vnic_sdma.c b/drivers/infiniband/hw/hfi1/vnic_sdma.c index 7d90b900131b..7658c620a125 100644 --- a/drivers/infiniband/hw/hfi1/vnic_sdma.c +++ b/drivers/infiniband/hw/hfi1/vnic_sdma.c @@ -106,6 +106,7 @@ static noinline int build_vnic_ulp_payload(struct sdma_engine *sde, /* combine physically continuous fragments later? */ ret = sdma_txadd_page(sde->dd, + NULL, &tx->txreq, skb_frag_page(frag), skb_frag_off(frag), From 73a65744c7fd785b3fd9d9541a6f238d0faae0ac Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Mar 2023 18:45:53 -0400 Subject: [PATCH 2924/4345] NFSv4.1: Always send a RECLAIM_COMPLETE after establishing lease [ Upstream commit 40882deb83c29d8df4470d4e5e7f137b6acf7ad1 ] The spec requires that we always at least send a RECLAIM_COMPLETE when we're done establishing the lease and recovering any state. Fixes: fce5c838e133 ("nfs41: RECLAIM_COMPLETE functionality") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- fs/nfs/nfs4state.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 628e030f8e3b..ff6ca05a9d44 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -67,6 +67,8 @@ #define OPENOWNER_POOL_SIZE 8 +static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp); + const nfs4_stateid zero_stateid = { { .data = { 0 } }, .type = NFS4_SPECIAL_STATEID_TYPE, @@ -330,6 +332,8 @@ do_confirm: status = nfs4_proc_create_session(clp, cred); if (status != 0) goto out; + if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)) + nfs4_state_start_reclaim_reboot(clp); nfs41_finish_session_reset(clp); nfs_mark_client_ready(clp, NFS_CS_READY); out: From 3aa2503717ba8b7cf529527d9bad09947f2f65a0 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Mon, 18 Jan 2021 13:32:35 +0100 Subject: [PATCH 2925/4345] firmware: raspberrypi: Introduce devm_rpi_firmware_get() [ Upstream commit f663204c9a1f8d6fcc590667d9d7a9f44e064644 ] It'll simplify the firmware handling for most consumers. Suggested-by: Bartosz Golaszewski Signed-off-by: Nicolas Saenz Julienne Reviewed-by: Florian Fainelli Reviewed-by: Bartosz Golaszewski Stable-dep-of: 5bca3688bdbc ("Input: raspberrypi-ts - fix refcount leak in rpi_ts_probe") Signed-off-by: Sasha Levin --- drivers/firmware/raspberrypi.c | 29 ++++++++++++++++++++++ include/soc/bcm2835/raspberrypi-firmware.h | 8 ++++++ 2 files changed, 37 insertions(+) diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c index 9eef49da47e0..45ff03da234a 100644 --- a/drivers/firmware/raspberrypi.c +++ b/drivers/firmware/raspberrypi.c @@ -243,6 +243,13 @@ void rpi_firmware_put(struct rpi_firmware *fw) } EXPORT_SYMBOL_GPL(rpi_firmware_put); +static void devm_rpi_firmware_put(void *data) +{ + struct rpi_firmware *fw = data; + + rpi_firmware_put(fw); +} + static int rpi_firmware_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -338,6 +345,28 @@ err_put_device: } EXPORT_SYMBOL_GPL(rpi_firmware_get); +/** + * devm_rpi_firmware_get - Get pointer to rpi_firmware structure. + * @firmware_node: Pointer to the firmware Device Tree node. + * + * Returns NULL is the firmware device is not ready. + */ +struct rpi_firmware *devm_rpi_firmware_get(struct device *dev, + struct device_node *firmware_node) +{ + struct rpi_firmware *fw; + + fw = rpi_firmware_get(firmware_node); + if (!fw) + return NULL; + + if (devm_add_action_or_reset(dev, devm_rpi_firmware_put, fw)) + return NULL; + + return fw; +} +EXPORT_SYMBOL_GPL(devm_rpi_firmware_get); + static const struct of_device_id rpi_firmware_of_match[] = { { .compatible = "raspberrypi,bcm2835-firmware", }, {}, diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h index fdfef7fe40df..73ad784fca96 100644 --- a/include/soc/bcm2835/raspberrypi-firmware.h +++ b/include/soc/bcm2835/raspberrypi-firmware.h @@ -142,6 +142,8 @@ int rpi_firmware_property_list(struct rpi_firmware *fw, void *data, size_t tag_size); void rpi_firmware_put(struct rpi_firmware *fw); struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node); +struct rpi_firmware *devm_rpi_firmware_get(struct device *dev, + struct device_node *firmware_node); #else static inline int rpi_firmware_property(struct rpi_firmware *fw, u32 tag, void *data, size_t len) @@ -160,6 +162,12 @@ static inline struct rpi_firmware *rpi_firmware_get(struct device_node *firmware { return NULL; } + +static inline struct rpi_firmware *devm_rpi_firmware_get(struct device *dev, + struct device_node *firmware_node) +{ + return NULL; +} #endif #endif /* __SOC_RASPBERRY_FIRMWARE_H__ */ From 09bfd90d040fca9c0374af9b90f83e0f58e0b600 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Mon, 18 Jan 2021 13:32:41 +0100 Subject: [PATCH 2926/4345] input: raspberrypi-ts: Release firmware handle when not needed [ Upstream commit 3b8ddff780b7d12e99ae39177f84b9003097777a ] There is no use for the firmware interface after getting the touch buffer address, so release it. Signed-off-by: Nicolas Saenz Julienne Acked-by: Dmitry Torokhov Reviewed-by: Florian Fainelli Stable-dep-of: 5bca3688bdbc ("Input: raspberrypi-ts - fix refcount leak in rpi_ts_probe") Signed-off-by: Sasha Levin --- drivers/input/touchscreen/raspberrypi-ts.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/touchscreen/raspberrypi-ts.c b/drivers/input/touchscreen/raspberrypi-ts.c index ef6aaed217cf..5000f5fd9ec3 100644 --- a/drivers/input/touchscreen/raspberrypi-ts.c +++ b/drivers/input/touchscreen/raspberrypi-ts.c @@ -160,7 +160,7 @@ static int rpi_ts_probe(struct platform_device *pdev) touchbuf = (u32)ts->fw_regs_phys; error = rpi_firmware_property(fw, RPI_FIRMWARE_FRAMEBUFFER_SET_TOUCHBUF, &touchbuf, sizeof(touchbuf)); - + rpi_firmware_put(fw); if (error || touchbuf != 0) { dev_warn(dev, "Failed to set touchbuf, %d\n", error); return error; From 0d6a5c9489c8a3d434e685066119c4333476dccd Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Thu, 13 Apr 2023 23:05:20 -0700 Subject: [PATCH 2927/4345] Input: raspberrypi-ts - fix refcount leak in rpi_ts_probe [ Upstream commit 5bca3688bdbc3b58a2894b8671a8e2378efe28bd ] rpi_firmware_get() take reference, we need to release it in error paths as well. Use devm_rpi_firmware_get() helper to handling the resources. Also remove the existing rpi_firmware_put(). Fixes: 0b9f28fed3f7 ("Input: add official Raspberry Pi's touchscreen driver") Fixes: 3b8ddff780b7 ("input: raspberrypi-ts: Release firmware handle when not needed") Signed-off-by: Miaoqian Lin Reviewed-by: Mattijs Korpershoek Link: https://lore.kernel.org/r/20221223074657.810346-1-linmq006@gmail.com Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/touchscreen/raspberrypi-ts.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/input/touchscreen/raspberrypi-ts.c b/drivers/input/touchscreen/raspberrypi-ts.c index 5000f5fd9ec3..45c575df994e 100644 --- a/drivers/input/touchscreen/raspberrypi-ts.c +++ b/drivers/input/touchscreen/raspberrypi-ts.c @@ -134,7 +134,7 @@ static int rpi_ts_probe(struct platform_device *pdev) return -ENOENT; } - fw = rpi_firmware_get(fw_node); + fw = devm_rpi_firmware_get(&pdev->dev, fw_node); of_node_put(fw_node); if (!fw) return -EPROBE_DEFER; @@ -160,7 +160,6 @@ static int rpi_ts_probe(struct platform_device *pdev) touchbuf = (u32)ts->fw_regs_phys; error = rpi_firmware_property(fw, RPI_FIRMWARE_FRAMEBUFFER_SET_TOUCHBUF, &touchbuf, sizeof(touchbuf)); - rpi_firmware_put(fw); if (error || touchbuf != 0) { dev_warn(dev, "Failed to set touchbuf, %d\n", error); return error; From 50440cdb0b4799ddb6b56b41cee7e92443544c76 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Thu, 13 Apr 2023 12:23:09 +0300 Subject: [PATCH 2928/4345] RDMA/mlx5: Fix flow counter query via DEVX [ Upstream commit 3e358ea8614ddfbc59ca7a3f5dff5dde2b350b2c ] Commit cited in "fixes" tag added bulk support for flow counters but it didn't account that's also possible to query a counter using a non-base id if the counter was allocated as bulk. When a user performs a query, validate the flow counter id given in the mailbox is inside the valid range taking bulk value into account. Fixes: 208d70f562e5 ("IB/mlx5: Support flow counters offset for bulk counters") Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Link: https://lore.kernel.org/r/79d7fbe291690128e44672418934256254d93115.1681377114.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx5/devx.c | 31 ++++++++++++++++++++++++++----- include/linux/mlx5/mlx5_ifc.h | 3 ++- 2 files changed, 28 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 2f053f48f1be..a56ebdc15723 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -595,7 +595,21 @@ static bool devx_is_valid_obj_id(struct uverbs_attr_bundle *attrs, obj_id; case MLX5_IB_OBJECT_DEVX_OBJ: - return ((struct devx_obj *)uobj->object)->obj_id == obj_id; + { + u16 opcode = MLX5_GET(general_obj_in_cmd_hdr, in, opcode); + struct devx_obj *devx_uobj = uobj->object; + + if (opcode == MLX5_CMD_OP_QUERY_FLOW_COUNTER && + devx_uobj->flow_counter_bulk_size) { + u64 end; + + end = devx_uobj->obj_id + + devx_uobj->flow_counter_bulk_size; + return devx_uobj->obj_id <= obj_id && end > obj_id; + } + + return devx_uobj->obj_id == obj_id; + } default: return false; @@ -1416,10 +1430,17 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( goto obj_free; if (opcode == MLX5_CMD_OP_ALLOC_FLOW_COUNTER) { - u8 bulk = MLX5_GET(alloc_flow_counter_in, - cmd_in, - flow_counter_bulk); - obj->flow_counter_bulk_size = 128UL * bulk; + u32 bulk = MLX5_GET(alloc_flow_counter_in, + cmd_in, + flow_counter_bulk_log_size); + + if (bulk) + bulk = 1 << bulk; + else + bulk = 128UL * MLX5_GET(alloc_flow_counter_in, + cmd_in, + flow_counter_bulk); + obj->flow_counter_bulk_size = bulk; } uobj->object = obj; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6ca97729b54a..88dbb2009080 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8331,7 +8331,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x38]; + u8 reserved_at_40[0x33]; + u8 flow_counter_bulk_log_size[0x5]; u8 flow_counter_bulk[0x8]; }; From 95468f165d9379d7714d0ca099df5a306deff0e5 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Tue, 18 Apr 2023 13:19:02 -0700 Subject: [PATCH 2929/4345] SUNRPC: remove the maximum number of retries in call_bind_status [ Upstream commit 691d0b782066a6eeeecbfceb7910a8f6184e6105 ] Currently call_bind_status places a hard limit of 3 to the number of retries on EACCES error. This limit was done to prevent NLM unlock requests from being hang forever when the server keeps returning garbage. However this change causes problem for cases when NLM service takes longer than 9 seconds to register with the port mapper after a restart. This patch removes this hard coded limit and let the RPC handles the retry based on the standard hard/soft task semantics. Fixes: 0b760113a3a1 ("NLM: Don't hang forever on NLM unlock requests") Reported-by: Helen Chao Tested-by: Helen Chao Signed-off-by: Dai Ngo Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- include/linux/sunrpc/sched.h | 3 +-- net/sunrpc/clnt.c | 3 --- net/sunrpc/sched.c | 1 - 3 files changed, 1 insertion(+), 6 deletions(-) diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index df696efdd675..256dff36cf72 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -90,8 +90,7 @@ struct rpc_task { #endif unsigned char tk_priority : 2,/* Task priority */ tk_garb_retry : 2, - tk_cred_retry : 2, - tk_rebind_retry : 2; + tk_cred_retry : 2; }; typedef void (*rpc_action)(struct rpc_task *); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index c6e8bd78e35d..e1ce0f261f0b 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1967,9 +1967,6 @@ call_bind_status(struct rpc_task *task) status = -EOPNOTSUPP; break; } - if (task->tk_rebind_retry == 0) - break; - task->tk_rebind_retry--; rpc_delay(task, 3*HZ); goto retry_timeout; case -ENOBUFS: diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index f0f55fbd1375..a00890962e11 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -796,7 +796,6 @@ rpc_init_task_statistics(struct rpc_task *task) /* Initialize retry counters */ task->tk_garb_retry = 2; task->tk_cred_retry = 2; - task->tk_rebind_retry = 2; /* starting timestamp */ task->tk_start = ktime_get(); From 3bc78eddf0a054a24ea977df7add6f8671e456a9 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Thu, 20 Apr 2023 04:39:06 +0300 Subject: [PATCH 2930/4345] RDMA/mlx5: Use correct device num_ports when modify DC [ Upstream commit 746aa3c8cb1a650ff2583497ac646e505831b9b9 ] Just like other QP types, when modify DC, the port_num should be compared with dev->num_ports, instead of HCA_CAP.num_ports. Otherwise Multi-port vHCA on DC may not work. Fixes: 776a3906b692 ("IB/mlx5: Add support for DC target QP") Link: https://lore.kernel.org/r/20230420013906.1244185-1-markzhang@nvidia.com Signed-off-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx5/qp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 0caff276f2c1..0c47e3e24b2a 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4164,7 +4164,7 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr, return -EINVAL; if (attr->port_num == 0 || - attr->port_num > MLX5_CAP_GEN(dev->mdev, num_ports)) { + attr->port_num > dev->num_ports) { mlx5_ib_dbg(dev, "invalid port number %d. number of ports is %d\n", attr->port_num, dev->num_ports); return -EINVAL; From 1fe1580521dddc86d26401e82c44c793e86a7a5f Mon Sep 17 00:00:00 2001 From: Qinrun Dai Date: Thu, 13 Apr 2023 13:50:37 +0000 Subject: [PATCH 2931/4345] clocksource/drivers/davinci: Fix memory leak in davinci_timer_register when init fails [ Upstream commit fb73556386e074e9bee9fa2d253aeaefe4e063e0 ] Smatch reports: drivers/clocksource/timer-davinci.c:332 davinci_timer_register() warn: 'base' from ioremap() not released on lines: 274. Fix this and other potential memory leak problems by adding a set of corresponding exit lables. Fixes: 721154f972aa ("clocksource/drivers/davinci: Add support for clockevents") Signed-off-by: Qinrun Dai Link: https://lore.kernel.org/r/20230413135037.1505799-1-flno@hust.edu.cn Signed-off-by: Daniel Lezcano Signed-off-by: Sasha Levin --- drivers/clocksource/timer-davinci.c | 30 +++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) diff --git a/drivers/clocksource/timer-davinci.c b/drivers/clocksource/timer-davinci.c index bb4eee31ae08..3dc0c6ceed02 100644 --- a/drivers/clocksource/timer-davinci.c +++ b/drivers/clocksource/timer-davinci.c @@ -258,21 +258,25 @@ int __init davinci_timer_register(struct clk *clk, resource_size(&timer_cfg->reg), "davinci-timer")) { pr_err("Unable to request memory region\n"); - return -EBUSY; + rv = -EBUSY; + goto exit_clk_disable; } base = ioremap(timer_cfg->reg.start, resource_size(&timer_cfg->reg)); if (!base) { pr_err("Unable to map the register range\n"); - return -ENOMEM; + rv = -ENOMEM; + goto exit_mem_region; } davinci_timer_init(base); tick_rate = clk_get_rate(clk); clockevent = kzalloc(sizeof(*clockevent), GFP_KERNEL); - if (!clockevent) - return -ENOMEM; + if (!clockevent) { + rv = -ENOMEM; + goto exit_iounmap_base; + } clockevent->dev.name = "tim12"; clockevent->dev.features = CLOCK_EVT_FEAT_ONESHOT; @@ -297,7 +301,7 @@ int __init davinci_timer_register(struct clk *clk, "clockevent/tim12", clockevent); if (rv) { pr_err("Unable to request the clockevent interrupt\n"); - return rv; + goto exit_free_clockevent; } davinci_clocksource.dev.rating = 300; @@ -324,13 +328,27 @@ int __init davinci_timer_register(struct clk *clk, rv = clocksource_register_hz(&davinci_clocksource.dev, tick_rate); if (rv) { pr_err("Unable to register clocksource\n"); - return rv; + goto exit_free_irq; } sched_clock_register(davinci_timer_read_sched_clock, DAVINCI_TIMER_CLKSRC_BITS, tick_rate); return 0; + +exit_free_irq: + free_irq(timer_cfg->irq[DAVINCI_TIMER_CLOCKEVENT_IRQ].start, + clockevent); +exit_free_clockevent: + kfree(clockevent); +exit_iounmap_base: + iounmap(base); +exit_mem_region: + release_mem_region(timer_cfg->reg.start, + resource_size(&timer_cfg->reg)); +exit_clk_disable: + clk_disable_unprepare(clk); + return rv; } static int __init of_davinci_timer_register(struct device_node *np) From 8f009ae90b2bca5da5dbdf818debdbf917628d49 Mon Sep 17 00:00:00 2001 From: Stafford Horne Date: Sat, 11 Feb 2023 19:14:06 +0900 Subject: [PATCH 2932/4345] openrisc: Properly store r31 to pt_regs on unhandled exceptions [ Upstream commit 812489ac4dd91144a74ce65ecf232252a2e406fb ] In commit 91993c8c2ed5 ("openrisc: use shadow registers to save regs on exception") the unhandled exception path was changed to do an early store of r30 instead of r31. The entry code was not updated and r31 is not getting stored to pt_regs. This patch updates the entry handler to store r31 instead of r30. We also remove some misleading commented out store r30 and r31 instructrions. I noticed this while working on adding floating point exception handling, This issue probably would never impact anything since we kill the process or Oops right away on unhandled exceptions. Fixes: 91993c8c2ed5 ("openrisc: use shadow registers to save regs on exception") Signed-off-by: Stafford Horne Signed-off-by: Sasha Levin --- arch/openrisc/kernel/entry.S | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index b42d32d79b2e..7257e942731d 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -173,7 +173,6 @@ handler: ;\ l.sw PT_GPR28(r1),r28 ;\ l.sw PT_GPR29(r1),r29 ;\ /* r30 already save */ ;\ -/* l.sw PT_GPR30(r1),r30*/ ;\ l.sw PT_GPR31(r1),r31 ;\ TRACE_IRQS_OFF_ENTRY ;\ /* Store -1 in orig_gpr11 for non-syscall exceptions */ ;\ @@ -211,9 +210,8 @@ handler: ;\ l.sw PT_GPR27(r1),r27 ;\ l.sw PT_GPR28(r1),r28 ;\ l.sw PT_GPR29(r1),r29 ;\ - /* r31 already saved */ ;\ - l.sw PT_GPR30(r1),r30 ;\ -/* l.sw PT_GPR31(r1),r31 */ ;\ + /* r30 already saved */ ;\ + l.sw PT_GPR31(r1),r31 ;\ /* Store -1 in orig_gpr11 for non-syscall exceptions */ ;\ l.addi r30,r0,-1 ;\ l.sw PT_ORIG_GPR11(r1),r30 ;\ From 770b0613637f59f3091dda1ff0c23671a5326b9c Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 6 Apr 2023 11:16:27 +0000 Subject: [PATCH 2933/4345] ext4: fix use-after-free read in ext4_find_extent for bigalloc + inline [ Upstream commit 835659598c67907b98cd2aa57bb951dfaf675c69 ] Syzbot found the following issue: loop0: detected capacity change from 0 to 2048 EXT4-fs (loop0): mounted filesystem 00000000-0000-0000-0000-000000000000 without journal. Quota mode: none. ================================================================== BUG: KASAN: use-after-free in ext4_ext_binsearch_idx fs/ext4/extents.c:768 [inline] BUG: KASAN: use-after-free in ext4_find_extent+0x76e/0xd90 fs/ext4/extents.c:931 Read of size 4 at addr ffff888073644750 by task syz-executor420/5067 CPU: 0 PID: 5067 Comm: syz-executor420 Not tainted 6.2.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x290 lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:306 print_report+0x107/0x1f0 mm/kasan/report.c:417 kasan_report+0xcd/0x100 mm/kasan/report.c:517 ext4_ext_binsearch_idx fs/ext4/extents.c:768 [inline] ext4_find_extent+0x76e/0xd90 fs/ext4/extents.c:931 ext4_clu_mapped+0x117/0x970 fs/ext4/extents.c:5809 ext4_insert_delayed_block fs/ext4/inode.c:1696 [inline] ext4_da_map_blocks fs/ext4/inode.c:1806 [inline] ext4_da_get_block_prep+0x9e8/0x13c0 fs/ext4/inode.c:1870 ext4_block_write_begin+0x6a8/0x2290 fs/ext4/inode.c:1098 ext4_da_write_begin+0x539/0x760 fs/ext4/inode.c:3082 generic_perform_write+0x2e4/0x5e0 mm/filemap.c:3772 ext4_buffered_write_iter+0x122/0x3a0 fs/ext4/file.c:285 ext4_file_write_iter+0x1d0/0x18f0 call_write_iter include/linux/fs.h:2186 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x7dc/0xc50 fs/read_write.c:584 ksys_write+0x177/0x2a0 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f4b7a9737b9 RSP: 002b:00007ffc5cac3668 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f4b7a9737b9 RDX: 00000000175d9003 RSI: 0000000020000200 RDI: 0000000000000004 RBP: 00007f4b7a933050 R08: 0000000000000000 R09: 0000000000000000 R10: 000000000000079f R11: 0000000000000246 R12: 00007f4b7a9330e0 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Above issue is happens when enable bigalloc and inline data feature. As commit 131294c35ed6 fixed delayed allocation bug in ext4_clu_mapped for bigalloc + inline. But it only resolved issue when has inline data, if inline data has been converted to extent(ext4_da_convert_inline_data_to_extent) before writepages, there is no EXT4_STATE_MAY_INLINE_DATA flag. However i_data is still store inline data in this scene. Then will trigger UAF when find extent. To resolve above issue, there is need to add judge "ext4_has_inline_data(inode)" in ext4_clu_mapped(). Fixes: 131294c35ed6 ("ext4: fix delayed allocation bug in ext4_clu_mapped for bigalloc + inline") Reported-by: syzbot+bf4bb7731ef73b83a3b4@syzkaller.appspotmail.com Reviewed-by: Jan Kara Reviewed-by: Ye Bin Reviewed-by: Tudor Ambarus Tested-by: Tudor Ambarus Link: https://lore.kernel.org/r/20230406111627.1916759-1-tudor.ambarus@linaro.org Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/extents.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 6c06ce9dd6bd..2c2e1cc43e0e 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5805,7 +5805,8 @@ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) * mapped - no physical clusters have been allocated, and the * file has no extents */ - if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) + if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) || + ext4_has_inline_data(inode)) return 0; /* search for the extent closest to the first block in the cluster */ From 198fbdd10620e52424691a5251fd0cefca76784a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 25 Feb 2023 21:39:49 -0800 Subject: [PATCH 2934/4345] leds: TI_LMU_COMMON: select REGMAP instead of depending on it [ Upstream commit a61079efc87888587e463afaed82417b162fbd69 ] REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it. Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues. Therefore, change the use of "depends on REGMAP" to "select REGMAP". Fixes: 3fce8e1eb994 ("leds: TI LMU: Add common code for TI LMU devices") Signed-off-by: Randy Dunlap Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230226053953.4681-5-rdunlap@infradead.org Signed-off-by: Sasha Levin --- drivers/leds/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 56e8198e13d1..ad84be4f6817 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -871,7 +871,7 @@ config LEDS_SPI_BYTE config LEDS_TI_LMU_COMMON tristate "LED driver for TI LMU" depends on LEDS_CLASS - depends on REGMAP + select REGMAP help Say Y to enable the LED driver for TI LMU devices. This supports common features between the TI LM3532, LM3631, LM3632, From 033f00eb8969e99d9a06ac0c77adcab3501ef1fe Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 26 Mar 2023 09:06:37 +0200 Subject: [PATCH 2935/4345] dmaengine: mv_xor_v2: Fix an error code. [ Upstream commit 827026ae2e56ec05ef1155661079badbbfc0b038 ] If the probe is deferred, -EPROBE_DEFER should be returned, not +EPROBE_DEFER. Fixes: 3cd2c313f1d6 ("dmaengine: mv_xor_v2: Fix clock resource by adding a register clock") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/201170dff832a3c496d125772e10070cd834ebf2.1679814350.git.christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/mv_xor_v2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index 4800c596433a..9f3e011fbd91 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -756,7 +756,7 @@ static int mv_xor_v2_probe(struct platform_device *pdev) xor_dev->clk = devm_clk_get(&pdev->dev, NULL); if (PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { - ret = EPROBE_DEFER; + ret = -EPROBE_DEFER; goto disable_reg_clk; } if (!IS_ERR(xor_dev->clk)) { From 795cec288e9c3661caff2b9e28012da9e07ea5e5 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Sun, 2 Apr 2023 13:12:59 +0200 Subject: [PATCH 2936/4345] leds: tca6507: Fix error handling of using fwnode_property_read_string MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c1087c29e96a48e9080377e168d35dcb52fb068b ] Commit 96f524105b9c ("leds: tca6507: use fwnode API instead of OF") changed to fwnode API but did not take into account that a missing property "linux,default-trigger" now seems to return an error and as a side effect sets value to -1. This seems to be different from of_get_property() which always returned NULL in any case of error. Neglecting this side-effect leads to [ 11.201965] Unable to handle kernel paging request at virtual address ffffffff when read in the strcmp() of led_trigger_set_default() if there is no led-trigger defined in the DTS. I don't know if this was recently introduced somewhere in the fwnode lib or if the effect was missed in initial testing. Anyways it seems to be a bug to ignore the error return value of an optional value here in the driver. Fixes: 96f524105b9c ("leds: tca6507: use fwnode API instead of OF") Signed-off-by: H. Nikolaus Schaller Acked-by: Pavel Machek Reviewed-by: Marek Behún Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/cbae7617db83113de726fcc423a805ebaa1bfca6.1680433978.git.hns@goldelico.com Signed-off-by: Sasha Levin --- drivers/leds/leds-tca6507.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c index 225b765830bd..caad9d3e0eac 100644 --- a/drivers/leds/leds-tca6507.c +++ b/drivers/leds/leds-tca6507.c @@ -696,8 +696,9 @@ tca6507_led_dt_init(struct device *dev) if (fwnode_property_read_string(child, "label", &led.name)) led.name = fwnode_get_name(child); - fwnode_property_read_string(child, "linux,default-trigger", - &led.default_trigger); + if (fwnode_property_read_string(child, "linux,default-trigger", + &led.default_trigger)) + led.default_trigger = NULL; led.flags = 0; if (fwnode_property_match_string(child, "compatible", From 060bd30bf70515bd862c6a384de077f0afdcc869 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 7 Jul 2021 18:28:27 +0200 Subject: [PATCH 2937/4345] pwm: mtk-disp: Don't check the return code of pwmchip_remove() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9b7b5736ffd5da6f8f6329ebe5f1829cbcf8afae ] pwmchip_remove() returns always 0. Don't use the value to make it possible to eventually change the function to return void. Also the driver core ignores the return value of mtk_disp_pwm_remove(). Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding Stable-dep-of: 36dd7f530ae7 ("pwm: mtk-disp: Disable shadow registers before setting backlight values") Signed-off-by: Sasha Levin --- drivers/pwm/pwm-mtk-disp.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/pwm/pwm-mtk-disp.c b/drivers/pwm/pwm-mtk-disp.c index 83b8be0209b7..af63aaab8e15 100644 --- a/drivers/pwm/pwm-mtk-disp.c +++ b/drivers/pwm/pwm-mtk-disp.c @@ -240,13 +240,12 @@ disable_clk_main: static int mtk_disp_pwm_remove(struct platform_device *pdev) { struct mtk_disp_pwm *mdp = platform_get_drvdata(pdev); - int ret; - ret = pwmchip_remove(&mdp->chip); + pwmchip_remove(&mdp->chip); clk_unprepare(mdp->clk_mm); clk_unprepare(mdp->clk_main); - return ret; + return 0; } static const struct mtk_pwm_data mt2701_pwm_data = { From 6d13804388d6eb4b74c633a18a3bbd2d609f91bf Mon Sep 17 00:00:00 2001 From: Jitao Shi Date: Sun, 8 Aug 2021 21:24:29 +0800 Subject: [PATCH 2938/4345] pwm: mtk-disp: Adjust the clocks to avoid them mismatch [ Upstream commit d7a4e582587d97a586b1f7709e3bddcf35928e96 ] The clks "main" and "mm" are prepared in .probe() (and unprepared in .remove()). This results in the clocks being on during suspend which results in unnecessarily increased power consumption. Remove the clock operations from .probe() and .remove(). Add the clk_prepare_enable() in .enable() and the clk_disable_unprepare() in .disable(). Signed-off-by: Jitao Shi [thierry.reding@gmail.com: squashed in fixup patch] Signed-off-by: Thierry Reding Stable-dep-of: 36dd7f530ae7 ("pwm: mtk-disp: Disable shadow registers before setting backlight values") Signed-off-by: Sasha Levin --- drivers/pwm/pwm-mtk-disp.c | 95 +++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 52 deletions(-) diff --git a/drivers/pwm/pwm-mtk-disp.c b/drivers/pwm/pwm-mtk-disp.c index af63aaab8e15..a594a0fdddd7 100644 --- a/drivers/pwm/pwm-mtk-disp.c +++ b/drivers/pwm/pwm-mtk-disp.c @@ -74,6 +74,19 @@ static int mtk_disp_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, u64 div, rate; int err; + err = clk_prepare_enable(mdp->clk_main); + if (err < 0) { + dev_err(chip->dev, "Can't enable mdp->clk_main: %pe\n", ERR_PTR(err)); + return err; + } + + err = clk_prepare_enable(mdp->clk_mm); + if (err < 0) { + dev_err(chip->dev, "Can't enable mdp->clk_mm: %pe\n", ERR_PTR(err)); + clk_disable_unprepare(mdp->clk_main); + return err; + } + /* * Find period, high_width and clk_div to suit duty_ns and period_ns. * Calculate proper div value to keep period value in the bound. @@ -87,8 +100,11 @@ static int mtk_disp_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, rate = clk_get_rate(mdp->clk_main); clk_div = div_u64(rate * period_ns, NSEC_PER_SEC) >> PWM_PERIOD_BIT_WIDTH; - if (clk_div > PWM_CLKDIV_MAX) + if (clk_div > PWM_CLKDIV_MAX) { + clk_disable_unprepare(mdp->clk_mm); + clk_disable_unprepare(mdp->clk_main); return -EINVAL; + } div = NSEC_PER_SEC * (clk_div + 1); period = div64_u64(rate * period_ns, div); @@ -98,16 +114,6 @@ static int mtk_disp_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, high_width = div64_u64(rate * duty_ns, div); value = period | (high_width << PWM_HIGH_WIDTH_SHIFT); - err = clk_enable(mdp->clk_main); - if (err < 0) - return err; - - err = clk_enable(mdp->clk_mm); - if (err < 0) { - clk_disable(mdp->clk_main); - return err; - } - mtk_disp_pwm_update_bits(mdp, mdp->data->con0, PWM_CLKDIV_MASK, clk_div << PWM_CLKDIV_SHIFT); @@ -122,10 +128,21 @@ static int mtk_disp_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, mtk_disp_pwm_update_bits(mdp, mdp->data->commit, mdp->data->commit_mask, 0x0); + } else { + /* + * For MT2701, disable double buffer before writing register + * and select manual mode and use PWM_PERIOD/PWM_HIGH_WIDTH. + */ + mtk_disp_pwm_update_bits(mdp, mdp->data->bls_debug, + mdp->data->bls_debug_mask, + mdp->data->bls_debug_mask); + mtk_disp_pwm_update_bits(mdp, mdp->data->con0, + mdp->data->con0_sel, + mdp->data->con0_sel); } - clk_disable(mdp->clk_mm); - clk_disable(mdp->clk_main); + clk_disable_unprepare(mdp->clk_mm); + clk_disable_unprepare(mdp->clk_main); return 0; } @@ -135,13 +152,16 @@ static int mtk_disp_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm) struct mtk_disp_pwm *mdp = to_mtk_disp_pwm(chip); int err; - err = clk_enable(mdp->clk_main); - if (err < 0) - return err; - - err = clk_enable(mdp->clk_mm); + err = clk_prepare_enable(mdp->clk_main); if (err < 0) { - clk_disable(mdp->clk_main); + dev_err(chip->dev, "Can't enable mdp->clk_main: %pe\n", ERR_PTR(err)); + return err; + } + + err = clk_prepare_enable(mdp->clk_mm); + if (err < 0) { + dev_err(chip->dev, "Can't enable mdp->clk_mm: %pe\n", ERR_PTR(err)); + clk_disable_unprepare(mdp->clk_main); return err; } @@ -158,8 +178,8 @@ static void mtk_disp_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm) mtk_disp_pwm_update_bits(mdp, DISP_PWM_EN, mdp->data->enable_mask, 0x0); - clk_disable(mdp->clk_mm); - clk_disable(mdp->clk_main); + clk_disable_unprepare(mdp->clk_mm); + clk_disable_unprepare(mdp->clk_main); } static const struct pwm_ops mtk_disp_pwm_ops = { @@ -194,14 +214,6 @@ static int mtk_disp_pwm_probe(struct platform_device *pdev) if (IS_ERR(mdp->clk_mm)) return PTR_ERR(mdp->clk_mm); - ret = clk_prepare(mdp->clk_main); - if (ret < 0) - return ret; - - ret = clk_prepare(mdp->clk_mm); - if (ret < 0) - goto disable_clk_main; - mdp->chip.dev = &pdev->dev; mdp->chip.ops = &mtk_disp_pwm_ops; mdp->chip.base = -1; @@ -209,32 +221,13 @@ static int mtk_disp_pwm_probe(struct platform_device *pdev) ret = pwmchip_add(&mdp->chip); if (ret < 0) { - dev_err(&pdev->dev, "pwmchip_add() failed: %d\n", ret); - goto disable_clk_mm; + dev_err(&pdev->dev, "pwmchip_add() failed: %pe\n", ERR_PTR(ret)); + return ret; } platform_set_drvdata(pdev, mdp); - /* - * For MT2701, disable double buffer before writing register - * and select manual mode and use PWM_PERIOD/PWM_HIGH_WIDTH. - */ - if (!mdp->data->has_commit) { - mtk_disp_pwm_update_bits(mdp, mdp->data->bls_debug, - mdp->data->bls_debug_mask, - mdp->data->bls_debug_mask); - mtk_disp_pwm_update_bits(mdp, mdp->data->con0, - mdp->data->con0_sel, - mdp->data->con0_sel); - } - return 0; - -disable_clk_mm: - clk_unprepare(mdp->clk_mm); -disable_clk_main: - clk_unprepare(mdp->clk_main); - return ret; } static int mtk_disp_pwm_remove(struct platform_device *pdev) @@ -242,8 +235,6 @@ static int mtk_disp_pwm_remove(struct platform_device *pdev) struct mtk_disp_pwm *mdp = platform_get_drvdata(pdev); pwmchip_remove(&mdp->chip); - clk_unprepare(mdp->clk_mm); - clk_unprepare(mdp->clk_main); return 0; } From 45e4c00940beecc3a81934d8e4d58ce67d9f88c2 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 3 Apr 2023 15:30:53 +0200 Subject: [PATCH 2939/4345] pwm: mtk-disp: Disable shadow registers before setting backlight values MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 36dd7f530ae7d9ce9e853ffb8aa337de65c6600b ] If shadow registers usage is not desired, disable that before performing any write to CON0/1 registers in the .apply() callback, otherwise we may lose clkdiv or period/width updates. Fixes: cd4b45ac449a ("pwm: Add MediaTek MT2701 display PWM driver support") Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Nícolas F. R. A. Prado Tested-by: Nícolas F. R. A. Prado Reviewed-by: Alexandre Mergnat Tested-by: Alexandre Mergnat Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-mtk-disp.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/pwm/pwm-mtk-disp.c b/drivers/pwm/pwm-mtk-disp.c index a594a0fdddd7..327c780d433d 100644 --- a/drivers/pwm/pwm-mtk-disp.c +++ b/drivers/pwm/pwm-mtk-disp.c @@ -114,6 +114,19 @@ static int mtk_disp_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, high_width = div64_u64(rate * duty_ns, div); value = period | (high_width << PWM_HIGH_WIDTH_SHIFT); + if (mdp->data->bls_debug && !mdp->data->has_commit) { + /* + * For MT2701, disable double buffer before writing register + * and select manual mode and use PWM_PERIOD/PWM_HIGH_WIDTH. + */ + mtk_disp_pwm_update_bits(mdp, mdp->data->bls_debug, + mdp->data->bls_debug_mask, + mdp->data->bls_debug_mask); + mtk_disp_pwm_update_bits(mdp, mdp->data->con0, + mdp->data->con0_sel, + mdp->data->con0_sel); + } + mtk_disp_pwm_update_bits(mdp, mdp->data->con0, PWM_CLKDIV_MASK, clk_div << PWM_CLKDIV_SHIFT); @@ -128,17 +141,6 @@ static int mtk_disp_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, mtk_disp_pwm_update_bits(mdp, mdp->data->commit, mdp->data->commit_mask, 0x0); - } else { - /* - * For MT2701, disable double buffer before writing register - * and select manual mode and use PWM_PERIOD/PWM_HIGH_WIDTH. - */ - mtk_disp_pwm_update_bits(mdp, mdp->data->bls_debug, - mdp->data->bls_debug_mask, - mdp->data->bls_debug_mask); - mtk_disp_pwm_update_bits(mdp, mdp->data->con0, - mdp->data->con0_sel, - mdp->data->con0_sel); } clk_disable_unprepare(mdp->clk_mm); From da67d60467dd9308a98c6213213a4c39dd5d2a24 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 29 Nov 2022 19:16:34 +0800 Subject: [PATCH 2940/4345] phy: tegra: xusb: Add missing tegra_xusb_port_unregister for usb2_port and ulpi_port [ Upstream commit e024854048e733391b31fe5a398704b31b9af803 ] The tegra_xusb_port_unregister should be called when usb2_port and ulpi_port map fails in tegra_xusb_add_usb2_port() or in tegra_xusb_add_ulpi_port(), fix it. Fixes: 53d2a715c240 ("phy: Add Tegra XUSB pad controller support") Signed-off-by: Gaosheng Cui Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20221129111634.1547747-1-cuigaosheng1@huawei.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/tegra/xusb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 181a1be5f491..d07f33ec7939 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -775,6 +775,7 @@ static int tegra_xusb_add_usb2_port(struct tegra_xusb_padctl *padctl, usb2->base.lane = usb2->base.ops->map(&usb2->base); if (IS_ERR(usb2->base.lane)) { err = PTR_ERR(usb2->base.lane); + tegra_xusb_port_unregister(&usb2->base); goto out; } @@ -841,6 +842,7 @@ static int tegra_xusb_add_ulpi_port(struct tegra_xusb_padctl *padctl, ulpi->base.lane = ulpi->base.ops->map(&ulpi->base); if (IS_ERR(ulpi->base.lane)) { err = PTR_ERR(ulpi->base.lane); + tegra_xusb_port_unregister(&ulpi->base); goto out; } From b29543194594903242907e490e8e50ec05561aee Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Tue, 11 Apr 2023 19:17:57 +0900 Subject: [PATCH 2941/4345] dmaengine: dw-edma: Fix to change for continuous transfer [ Upstream commit a251994a441ee0a69ba7062c8cd2d08ead3db379 ] The dw-edma driver stops after processing a DMA request even if a request remains in the issued queue, which is not the expected behavior. The DMA engine API requires continuous processing. Add a trigger to start after one processing finished if there are requests remain. Fixes: e63d79d1ffcd ("dmaengine: Add Synopsys eDMA IP core driver") Signed-off-by: Shunsuke Mie Link: https://lore.kernel.org/r/20230411101758.438472-1-mie@igel.co.jp Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/dw-edma/dw-edma-core.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c index d7ed50f8b929..a3790f7b1b53 100644 --- a/drivers/dma/dw-edma/dw-edma-core.c +++ b/drivers/dma/dw-edma/dw-edma-core.c @@ -166,7 +166,7 @@ static void vchan_free_desc(struct virt_dma_desc *vdesc) dw_edma_free_desc(vd2dw_edma_desc(vdesc)); } -static void dw_edma_start_transfer(struct dw_edma_chan *chan) +static int dw_edma_start_transfer(struct dw_edma_chan *chan) { struct dw_edma_chunk *child; struct dw_edma_desc *desc; @@ -174,16 +174,16 @@ static void dw_edma_start_transfer(struct dw_edma_chan *chan) vd = vchan_next_desc(&chan->vc); if (!vd) - return; + return 0; desc = vd2dw_edma_desc(vd); if (!desc) - return; + return 0; child = list_first_entry_or_null(&desc->chunk->list, struct dw_edma_chunk, list); if (!child) - return; + return 0; dw_edma_v0_core_start(child, !desc->xfer_sz); desc->xfer_sz += child->ll_region.sz; @@ -191,6 +191,8 @@ static void dw_edma_start_transfer(struct dw_edma_chan *chan) list_del(&child->list); kfree(child); desc->chunks_alloc--; + + return 1; } static int dw_edma_device_config(struct dma_chan *dchan, @@ -497,14 +499,14 @@ static void dw_edma_done_interrupt(struct dw_edma_chan *chan) switch (chan->request) { case EDMA_REQ_NONE: desc = vd2dw_edma_desc(vd); - if (desc->chunks_alloc) { - chan->status = EDMA_ST_BUSY; - dw_edma_start_transfer(chan); - } else { + if (!desc->chunks_alloc) { list_del(&vd->node); vchan_cookie_complete(vd); - chan->status = EDMA_ST_IDLE; } + + /* Continue transferring if there are remaining chunks or issued requests. + */ + chan->status = dw_edma_start_transfer(chan) ? EDMA_ST_BUSY : EDMA_ST_IDLE; break; case EDMA_REQ_STOP: From 4f6303fd8f907adf4785aaeb6f62e470115f1901 Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Tue, 11 Apr 2023 19:17:58 +0900 Subject: [PATCH 2942/4345] dmaengine: dw-edma: Fix to enable to issue dma request on DMA processing [ Upstream commit 970b17dfe264a9085ba4e593730ecfd496b950ab ] The issue_pending request is ignored while driver is processing a DMA request. Fix to issue the pending requests on any dma channel status. Fixes: e63d79d1ffcd ("dmaengine: Add Synopsys eDMA IP core driver") Signed-off-by: Shunsuke Mie Link: https://lore.kernel.org/r/20230411101758.438472-2-mie@igel.co.jp Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/dw-edma/dw-edma-core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c index a3790f7b1b53..f91dbf43a598 100644 --- a/drivers/dma/dw-edma/dw-edma-core.c +++ b/drivers/dma/dw-edma/dw-edma-core.c @@ -276,9 +276,12 @@ static void dw_edma_device_issue_pending(struct dma_chan *dchan) struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan); unsigned long flags; + if (!chan->configured) + return; + spin_lock_irqsave(&chan->vc.lock, flags); - if (chan->configured && chan->request == EDMA_REQ_NONE && - chan->status == EDMA_ST_IDLE && vchan_issue_pending(&chan->vc)) { + if (vchan_issue_pending(&chan->vc) && chan->request == EDMA_REQ_NONE && + chan->status == EDMA_ST_IDLE) { chan->status = EDMA_ST_BUSY; dw_edma_start_transfer(chan); } From 08012d9edc521e8ed66de6ba7cb49d73862d4b98 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 14 Feb 2023 17:18:25 +0200 Subject: [PATCH 2943/4345] dmaengine: at_xdmac: do not enable all cyclic channels [ Upstream commit f8435befd81dd85b7b610598551fadf675849bc1 ] Do not global enable all the cyclic channels in at_xdmac_resume(). Instead save the global status in at_xdmac_suspend() and re-enable the cyclic channel only if it was active before suspend. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230214151827.1050280-6-claudiu.beznea@microchip.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/at_xdmac.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index b5d691ae45dc..1fe006cc643e 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -212,6 +212,7 @@ struct at_xdmac { int irq; struct clk *clk; u32 save_gim; + u32 save_gs; struct dma_pool *at_xdmac_desc_pool; struct at_xdmac_chan chan[]; }; @@ -1910,6 +1911,7 @@ static int atmel_xdmac_suspend(struct device *dev) } } atxdmac->save_gim = at_xdmac_read(atxdmac, AT_XDMAC_GIM); + atxdmac->save_gs = at_xdmac_read(atxdmac, AT_XDMAC_GS); at_xdmac_off(atxdmac); clk_disable_unprepare(atxdmac->clk); @@ -1946,7 +1948,8 @@ static int atmel_xdmac_resume(struct device *dev) at_xdmac_chan_write(atchan, AT_XDMAC_CNDC, atchan->save_cndc); at_xdmac_chan_write(atchan, AT_XDMAC_CIE, atchan->save_cim); wmb(); - at_xdmac_write(atxdmac, AT_XDMAC_GE, atchan->mask); + if (atxdmac->save_gs & atchan->mask) + at_xdmac_write(atxdmac, AT_XDMAC_GE, atchan->mask); } } return 0; From 15da2acad5156937c5b62444b18c6c20dd20f64d Mon Sep 17 00:00:00 2001 From: Kang Chen Date: Wed, 19 Apr 2023 10:07:48 +0800 Subject: [PATCH 2944/4345] thermal/drivers/mediatek: Use devm_of_iomap to avoid resource leak in mtk_thermal_probe [ Upstream commit f05c7b7d9ea9477fcc388476c6f4ade8c66d2d26 ] Smatch reports: 1. mtk_thermal_probe() warn: 'apmixed_base' from of_iomap() not released. 2. mtk_thermal_probe() warn: 'auxadc_base' from of_iomap() not released. The original code forgets to release iomap resource when handling errors, fix it by switch to devm_of_iomap. Fixes: 89945047b166 ("thermal: mediatek: Add tsensor support for V2 thermal system") Signed-off-by: Kang Chen Reviewed-by: Dongliang Mu Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230419020749.621257-1-void0red@hust.edu.cn Signed-off-by: Sasha Levin --- drivers/thermal/mtk_thermal.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c index 0bd7aa564bc2..9fe169dbed88 100644 --- a/drivers/thermal/mtk_thermal.c +++ b/drivers/thermal/mtk_thermal.c @@ -1026,7 +1026,12 @@ static int mtk_thermal_probe(struct platform_device *pdev) return -ENODEV; } - auxadc_base = of_iomap(auxadc, 0); + auxadc_base = devm_of_iomap(&pdev->dev, auxadc, 0, NULL); + if (IS_ERR(auxadc_base)) { + of_node_put(auxadc); + return PTR_ERR(auxadc_base); + } + auxadc_phys_base = of_get_phys_base(auxadc); of_node_put(auxadc); @@ -1042,7 +1047,12 @@ static int mtk_thermal_probe(struct platform_device *pdev) return -ENODEV; } - apmixed_base = of_iomap(apmixedsys, 0); + apmixed_base = devm_of_iomap(&pdev->dev, apmixedsys, 0, NULL); + if (IS_ERR(apmixed_base)) { + of_node_put(apmixedsys); + return PTR_ERR(apmixed_base); + } + apmixed_phys_base = of_get_phys_base(apmixedsys); of_node_put(apmixedsys); From 6697a3b0ed8397ed7d837c65b82119f8530c0200 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 20 Feb 2023 12:25:44 +0100 Subject: [PATCH 2945/4345] mfd: tqmx86: Do not access I2C_DETECT register through io_base [ Upstream commit 1be1b23696b3d4b0231c694f5e0767b4471d33a9 ] The I2C_DETECT register is at IO port 0x1a7, which is outside the range passed to devm_ioport_map() for io_base, and was only working because there aren't actually any bounds checks for IO port accesses. Extending the range does not seem like a good solution here, as it would then conflict with the IO resource assigned to the I2C controller. As this is just a one-off access during probe, use a simple inb() instead. While we're at it, drop the unused define TQMX86_REG_I2C_INT_EN. Fixes: 2f17dd34ffed ("mfd: tqmx86: IO controller with I2C, Wachdog and GPIO") Signed-off-by: Matthias Schiffer Reviewed-by: Andrew Lunn Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/e8300a30f0791afb67d79db8089fb6004855f378.1676892223.git.matthias.schiffer@ew.tq-group.com Signed-off-by: Sasha Levin --- drivers/mfd/tqmx86.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/mfd/tqmx86.c b/drivers/mfd/tqmx86.c index 732013f40e4e..99a59341e449 100644 --- a/drivers/mfd/tqmx86.c +++ b/drivers/mfd/tqmx86.c @@ -45,9 +45,8 @@ #define TQMX86_REG_IO_EXT_INT_MASK 0x3 #define TQMX86_REG_IO_EXT_INT_GPIO_SHIFT 4 -#define TQMX86_REG_I2C_DETECT 0x47 +#define TQMX86_REG_I2C_DETECT 0x1a7 #define TQMX86_REG_I2C_DETECT_SOFT 0xa5 -#define TQMX86_REG_I2C_INT_EN 0x49 static uint gpio_irq; module_param(gpio_irq, uint, 0); @@ -195,7 +194,12 @@ static int tqmx86_probe(struct platform_device *pdev) "Found %s - Board ID %d, PCB Revision %d, PLD Revision %d\n", board_name, board_id, rev >> 4, rev & 0xf); - i2c_det = ioread8(io_base + TQMX86_REG_I2C_DETECT); + /* + * The I2C_DETECT register is in the range assigned to the I2C driver + * later, so we don't extend TQMX86_IOSIZE. Use inb() for this one-off + * access instead of ioport_map + unmap. + */ + i2c_det = inb(TQMX86_REG_I2C_DETECT); if (gpio_irq_cfg) { io_ext_int_val = From 4be49b7c2457d49ea1f590ce961e2a28e61a479f Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Fri, 16 Jul 2021 12:00:49 +0200 Subject: [PATCH 2946/4345] mfd: tqmx86: Remove incorrect TQMx90UC board ID [ Upstream commit 16b2ad150f74db0eb91f445061f16140b5aaa650 ] No TQMx90UC exists at the moment, and it is undecided whether ID 10 will be used eventually (and if it is, how that SoM will be named). Signed-off-by: Matthias Schiffer Reviewed-by: Andrew Lunn Signed-off-by: Lee Jones Stable-dep-of: 051c69ff4f60 ("mfd: tqmx86: Specify IO port register range more precisely") Signed-off-by: Sasha Levin --- drivers/mfd/tqmx86.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/mfd/tqmx86.c b/drivers/mfd/tqmx86.c index 99a59341e449..c5c5846dcf99 100644 --- a/drivers/mfd/tqmx86.c +++ b/drivers/mfd/tqmx86.c @@ -35,7 +35,6 @@ #define TQMX86_REG_BOARD_ID_E39x 7 #define TQMX86_REG_BOARD_ID_70EB 8 #define TQMX86_REG_BOARD_ID_80UC 9 -#define TQMX86_REG_BOARD_ID_90UC 10 #define TQMX86_REG_BOARD_REV 0x21 #define TQMX86_REG_IO_EXT_INT 0x26 #define TQMX86_REG_IO_EXT_INT_NONE 0 @@ -127,8 +126,6 @@ static const char *tqmx86_board_id_to_name(u8 board_id) return "TQMx70EB"; case TQMX86_REG_BOARD_ID_80UC: return "TQMx80UC"; - case TQMX86_REG_BOARD_ID_90UC: - return "TQMx90UC"; default: return "Unknown"; } @@ -141,7 +138,6 @@ static int tqmx86_board_id_to_clk_rate(u8 board_id) case TQMX86_REG_BOARD_ID_60EB: case TQMX86_REG_BOARD_ID_70EB: case TQMX86_REG_BOARD_ID_80UC: - case TQMX86_REG_BOARD_ID_90UC: return 24000; case TQMX86_REG_BOARD_ID_E39M: case TQMX86_REG_BOARD_ID_E39C: From 640a1f7e36e8b60b94a68bd4525a536647597fec Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Fri, 16 Jul 2021 12:00:51 +0200 Subject: [PATCH 2947/4345] mfd: tqmx86: Add support for TQMx110EB and TQMxE40x [ Upstream commit 3da48ccb1d0f3b53b1e8c9022edbedc2a6e3f50a ] Add the board IDs for the TQMx110EB and the TQMxE40x family. All use a 24MHz LPC clock. Signed-off-by: Matthias Schiffer Reviewed-by: Andrew Lunn Signed-off-by: Lee Jones Stable-dep-of: 051c69ff4f60 ("mfd: tqmx86: Specify IO port register range more precisely") Signed-off-by: Sasha Levin --- drivers/mfd/tqmx86.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/mfd/tqmx86.c b/drivers/mfd/tqmx86.c index c5c5846dcf99..1db95aed5012 100644 --- a/drivers/mfd/tqmx86.c +++ b/drivers/mfd/tqmx86.c @@ -35,6 +35,11 @@ #define TQMX86_REG_BOARD_ID_E39x 7 #define TQMX86_REG_BOARD_ID_70EB 8 #define TQMX86_REG_BOARD_ID_80UC 9 +#define TQMX86_REG_BOARD_ID_110EB 11 +#define TQMX86_REG_BOARD_ID_E40M 12 +#define TQMX86_REG_BOARD_ID_E40S 13 +#define TQMX86_REG_BOARD_ID_E40C1 14 +#define TQMX86_REG_BOARD_ID_E40C2 15 #define TQMX86_REG_BOARD_REV 0x21 #define TQMX86_REG_IO_EXT_INT 0x26 #define TQMX86_REG_IO_EXT_INT_NONE 0 @@ -126,6 +131,16 @@ static const char *tqmx86_board_id_to_name(u8 board_id) return "TQMx70EB"; case TQMX86_REG_BOARD_ID_80UC: return "TQMx80UC"; + case TQMX86_REG_BOARD_ID_110EB: + return "TQMx110EB"; + case TQMX86_REG_BOARD_ID_E40M: + return "TQMxE40M"; + case TQMX86_REG_BOARD_ID_E40S: + return "TQMxE40S"; + case TQMX86_REG_BOARD_ID_E40C1: + return "TQMxE40C1"; + case TQMX86_REG_BOARD_ID_E40C2: + return "TQMxE40C2"; default: return "Unknown"; } @@ -138,6 +153,11 @@ static int tqmx86_board_id_to_clk_rate(u8 board_id) case TQMX86_REG_BOARD_ID_60EB: case TQMX86_REG_BOARD_ID_70EB: case TQMX86_REG_BOARD_ID_80UC: + case TQMX86_REG_BOARD_ID_110EB: + case TQMX86_REG_BOARD_ID_E40M: + case TQMX86_REG_BOARD_ID_E40S: + case TQMX86_REG_BOARD_ID_E40C1: + case TQMX86_REG_BOARD_ID_E40C2: return 24000; case TQMX86_REG_BOARD_ID_E39M: case TQMX86_REG_BOARD_ID_E39C: From cbe060011b561cf4a0d94aa213bc1c97c789de31 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 20 Feb 2023 12:25:45 +0100 Subject: [PATCH 2948/4345] mfd: tqmx86: Specify IO port register range more precisely [ Upstream commit 051c69ff4f607aa114c7bbdd7c41ed881367aeee ] Registers 0x160..0x17f are unassigned. Use 0x180 as base register and update offets accordingly. Also change the size of the range to include 0x19f. While 0x19f is currently reserved for future extensions, so are several of the previous registers up to 0x19e, and it is weird to leave out just the last one. Fixes: 2f17dd34ffed ("mfd: tqmx86: IO controller with I2C, Wachdog and GPIO") Signed-off-by: Matthias Schiffer Reviewed-by: Andrew Lunn Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/db4677ac318b1283c8956f637f409995a30a31c3.1676892223.git.matthias.schiffer@ew.tq-group.com Signed-off-by: Sasha Levin --- drivers/mfd/tqmx86.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/mfd/tqmx86.c b/drivers/mfd/tqmx86.c index 1db95aed5012..c8ec0f92bc10 100644 --- a/drivers/mfd/tqmx86.c +++ b/drivers/mfd/tqmx86.c @@ -16,8 +16,8 @@ #include #include -#define TQMX86_IOBASE 0x160 -#define TQMX86_IOSIZE 0x3f +#define TQMX86_IOBASE 0x180 +#define TQMX86_IOSIZE 0x20 #define TQMX86_IOBASE_I2C 0x1a0 #define TQMX86_IOSIZE_I2C 0xa #define TQMX86_IOBASE_WATCHDOG 0x18b @@ -25,7 +25,7 @@ #define TQMX86_IOBASE_GPIO 0x18d #define TQMX86_IOSIZE_GPIO 0x4 -#define TQMX86_REG_BOARD_ID 0x20 +#define TQMX86_REG_BOARD_ID 0x00 #define TQMX86_REG_BOARD_ID_E38M 1 #define TQMX86_REG_BOARD_ID_50UC 2 #define TQMX86_REG_BOARD_ID_E38C 3 @@ -40,8 +40,8 @@ #define TQMX86_REG_BOARD_ID_E40S 13 #define TQMX86_REG_BOARD_ID_E40C1 14 #define TQMX86_REG_BOARD_ID_E40C2 15 -#define TQMX86_REG_BOARD_REV 0x21 -#define TQMX86_REG_IO_EXT_INT 0x26 +#define TQMX86_REG_BOARD_REV 0x01 +#define TQMX86_REG_IO_EXT_INT 0x06 #define TQMX86_REG_IO_EXT_INT_NONE 0 #define TQMX86_REG_IO_EXT_INT_7 1 #define TQMX86_REG_IO_EXT_INT_9 2 From 3530a795bb07597477fb792f625d645e79c4a45c Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 20 Feb 2023 12:25:46 +0100 Subject: [PATCH 2949/4345] mfd: tqmx86: Correct board names for TQMxE39x [ Upstream commit f376c479668557bcc2fd9e9fbc0f53e7819a11cd ] It seems that this driver was developed based on preliminary documentation. Report the correct names for all TQMxE39x variants, as they are used by the released hardware revisions: - Fix names for TQMxE39C1/C2 board IDs - Distinguish TQMxE39M and TQMxE39S, which use the same board ID The TQMxE39M/S are distinguished using the SAUC (Sanctioned Alternate Uses Configuration) register of the GPIO controller. This also prepares for the correct handling of the differences between the GPIO controllers of our COMe and SMARC modules. Fixes: 2f17dd34ffed ("mfd: tqmx86: IO controller with I2C, Wachdog and GPIO") Signed-off-by: Matthias Schiffer Reviewed-by: Andrew Lunn Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/aca9a7cb42a85181bcb456c437554d2728e708ec.1676892223.git.matthias.schiffer@ew.tq-group.com Signed-off-by: Sasha Levin --- drivers/mfd/tqmx86.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/drivers/mfd/tqmx86.c b/drivers/mfd/tqmx86.c index c8ec0f92bc10..0498f1b7e2e3 100644 --- a/drivers/mfd/tqmx86.c +++ b/drivers/mfd/tqmx86.c @@ -30,9 +30,9 @@ #define TQMX86_REG_BOARD_ID_50UC 2 #define TQMX86_REG_BOARD_ID_E38C 3 #define TQMX86_REG_BOARD_ID_60EB 4 -#define TQMX86_REG_BOARD_ID_E39M 5 -#define TQMX86_REG_BOARD_ID_E39C 6 -#define TQMX86_REG_BOARD_ID_E39x 7 +#define TQMX86_REG_BOARD_ID_E39MS 5 +#define TQMX86_REG_BOARD_ID_E39C1 6 +#define TQMX86_REG_BOARD_ID_E39C2 7 #define TQMX86_REG_BOARD_ID_70EB 8 #define TQMX86_REG_BOARD_ID_80UC 9 #define TQMX86_REG_BOARD_ID_110EB 11 @@ -48,6 +48,7 @@ #define TQMX86_REG_IO_EXT_INT_12 3 #define TQMX86_REG_IO_EXT_INT_MASK 0x3 #define TQMX86_REG_IO_EXT_INT_GPIO_SHIFT 4 +#define TQMX86_REG_SAUC 0x17 #define TQMX86_REG_I2C_DETECT 0x1a7 #define TQMX86_REG_I2C_DETECT_SOFT 0xa5 @@ -110,7 +111,7 @@ static const struct mfd_cell tqmx86_devs[] = { }, }; -static const char *tqmx86_board_id_to_name(u8 board_id) +static const char *tqmx86_board_id_to_name(u8 board_id, u8 sauc) { switch (board_id) { case TQMX86_REG_BOARD_ID_E38M: @@ -121,12 +122,12 @@ static const char *tqmx86_board_id_to_name(u8 board_id) return "TQMxE38C"; case TQMX86_REG_BOARD_ID_60EB: return "TQMx60EB"; - case TQMX86_REG_BOARD_ID_E39M: - return "TQMxE39M"; - case TQMX86_REG_BOARD_ID_E39C: - return "TQMxE39C"; - case TQMX86_REG_BOARD_ID_E39x: - return "TQMxE39x"; + case TQMX86_REG_BOARD_ID_E39MS: + return (sauc == 0xff) ? "TQMxE39M" : "TQMxE39S"; + case TQMX86_REG_BOARD_ID_E39C1: + return "TQMxE39C1"; + case TQMX86_REG_BOARD_ID_E39C2: + return "TQMxE39C2"; case TQMX86_REG_BOARD_ID_70EB: return "TQMx70EB"; case TQMX86_REG_BOARD_ID_80UC: @@ -159,9 +160,9 @@ static int tqmx86_board_id_to_clk_rate(u8 board_id) case TQMX86_REG_BOARD_ID_E40C1: case TQMX86_REG_BOARD_ID_E40C2: return 24000; - case TQMX86_REG_BOARD_ID_E39M: - case TQMX86_REG_BOARD_ID_E39C: - case TQMX86_REG_BOARD_ID_E39x: + case TQMX86_REG_BOARD_ID_E39MS: + case TQMX86_REG_BOARD_ID_E39C1: + case TQMX86_REG_BOARD_ID_E39C2: return 25000; case TQMX86_REG_BOARD_ID_E38M: case TQMX86_REG_BOARD_ID_E38C: @@ -173,7 +174,7 @@ static int tqmx86_board_id_to_clk_rate(u8 board_id) static int tqmx86_probe(struct platform_device *pdev) { - u8 board_id, rev, i2c_det, io_ext_int_val; + u8 board_id, sauc, rev, i2c_det, io_ext_int_val; struct device *dev = &pdev->dev; u8 gpio_irq_cfg, readback; const char *board_name; @@ -203,7 +204,8 @@ static int tqmx86_probe(struct platform_device *pdev) return -ENOMEM; board_id = ioread8(io_base + TQMX86_REG_BOARD_ID); - board_name = tqmx86_board_id_to_name(board_id); + sauc = ioread8(io_base + TQMX86_REG_SAUC); + board_name = tqmx86_board_id_to_name(board_id, sauc); rev = ioread8(io_base + TQMX86_REG_BOARD_REV); dev_info(dev, From 9aabb5f9ef3214fa1e0bc267dbbc00c534ba2b9b Mon Sep 17 00:00:00 2001 From: Marc Dionne Date: Fri, 2 Dec 2022 10:07:01 -0400 Subject: [PATCH 2950/4345] afs: Fix updating of i_size with dv jump from server [ Upstream commit d7f74e9a917503ee78f2b603a456d7227cf38919 ] If the data version returned from the server is larger than expected, the local data is invalidated, but we may still want to note the remote file size. Since we're setting change_size, we have to also set data_changed for the i_size to get updated. Fixes: 3f4aa9818163 ("afs: Fix EOF corruption") Signed-off-by: Marc Dionne Signed-off-by: David Howells cc: linux-afs@lists.infradead.org Signed-off-by: Sasha Levin --- fs/afs/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 826fae22a8cc..fdca4262f806 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -218,6 +218,7 @@ static void afs_apply_status(struct afs_operation *op, set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); } change_size = true; + data_changed = true; } else if (vnode->status.type == AFS_FTYPE_DIR) { /* Expected directory change is handled elsewhere so * that we can locally edit the directory and save on a From f7fd1eed3125e36c8087814af89adef00ee1f7be Mon Sep 17 00:00:00 2001 From: Peng Liu Date: Tue, 21 Mar 2023 14:19:29 +0800 Subject: [PATCH 2951/4345] scripts/gdb: fix lx-timerlist for Python3 commit 7362042f3556528e9e9b1eb5ce8d7a3a6331476b upstream. Below incompatibilities between Python2 and Python3 made lx-timerlist fail to run under Python3. o xrange() is replaced by range() in Python3 o bytes and str are different types in Python3 o the return value of Inferior.read_memory() is memoryview object in Python3 akpm: cc stable so that older kernels are properly debuggable under newer Python. Link: https://lkml.kernel.org/r/TYCP286MB2146EE1180A4D5176CBA8AB2C6819@TYCP286MB2146.JPNP286.PROD.OUTLOOK.COM Signed-off-by: Peng Liu Reviewed-by: Jan Kiszka Cc: Florian Fainelli Cc: Kieran Bingham Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- scripts/gdb/linux/timerlist.py | 4 +++- scripts/gdb/linux/utils.py | 5 ++++- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/scripts/gdb/linux/timerlist.py b/scripts/gdb/linux/timerlist.py index 071d0dd5a634..51def847f1ef 100644 --- a/scripts/gdb/linux/timerlist.py +++ b/scripts/gdb/linux/timerlist.py @@ -73,7 +73,7 @@ def print_cpu(hrtimer_bases, cpu, max_clock_bases): ts = cpus.per_cpu(tick_sched_ptr, cpu) text = "cpu: {}\n".format(cpu) - for i in xrange(max_clock_bases): + for i in range(max_clock_bases): text += " clock {}:\n".format(i) text += print_base(cpu_base['clock_base'][i]) @@ -158,6 +158,8 @@ def pr_cpumask(mask): num_bytes = (nr_cpu_ids + 7) / 8 buf = utils.read_memoryview(inf, bits, num_bytes).tobytes() buf = binascii.b2a_hex(buf) + if type(buf) is not str: + buf=buf.decode() chunks = [] i = num_bytes diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index ff7c1799d588..db59f986c7fd 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -89,7 +89,10 @@ def get_target_endianness(): def read_memoryview(inf, start, length): - return memoryview(inf.read_memory(start, length)) + m = inf.read_memory(start, length) + if type(m) is memoryview: + return m + return memoryview(m) def read_u16(buffer, offset): From c96807a4adbe2906167e8c7020a15a0f38ef060b Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 6 Apr 2023 13:00:34 +0800 Subject: [PATCH 2952/4345] btrfs: scrub: reject unsupported scrub flags commit 604e6681e114d05a2e384c4d1e8ef81918037ef5 upstream. Since the introduction of scrub interface, the only flag that we support is BTRFS_SCRUB_READONLY. Thus there is no sanity checks, if there are some undefined flags passed in, we just ignore them. This is problematic if we want to introduce new scrub flags, as we have no way to determine if such flags are supported. Address the problem by introducing a check for the flags, and if unsupported flags are set, return -EOPNOTSUPP to inform the user space. This check should be backported for all supported kernels before any new scrub flags are introduced. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Anand Jain Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/ioctl.c | 5 +++++ include/uapi/linux/btrfs.h | 1 + 2 files changed, 6 insertions(+) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 10686b494f0a..63bf68e0b006 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3702,6 +3702,11 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg) if (IS_ERR(sa)) return PTR_ERR(sa); + if (sa->flags & ~BTRFS_SCRUB_SUPPORTED_FLAGS) { + ret = -EOPNOTSUPP; + goto out; + } + if (!(sa->flags & BTRFS_SCRUB_READONLY)) { ret = mnt_want_write_file(file); if (ret) diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 2c39d15a2beb..e65300d63d7c 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -181,6 +181,7 @@ struct btrfs_scrub_progress { }; #define BTRFS_SCRUB_READONLY 1 +#define BTRFS_SCRUB_SUPPORTED_FLAGS (BTRFS_SCRUB_READONLY) struct btrfs_ioctl_scrub_args { __u64 devid; /* in */ __u64 start; /* in */ From abb427cb7730a0515ced6b10194fcf843d8787d1 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Wed, 5 Apr 2023 16:20:17 +0200 Subject: [PATCH 2953/4345] s390/dasd: fix hanging blockdevice after request requeue commit d8898ee50edecacdf0141f26fd90acf43d7e9cd7 upstream. The DASD driver does not kick the requeue list when requeuing IO requests to the blocklayer. This might lead to hanging blockdevice when there is no other trigger for this. Fix by automatically kick the requeue list when requeuing DASD requests to the blocklayer. Fixes: e443343e509a ("s390/dasd: blk-mq conversion") CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Reviewed-by: Halil Pasic Link: https://lore.kernel.org/r/20230405142017.2446986-8-sth@linux.ibm.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/s390/block/dasd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 9f26f55e4988..792f8f568808 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -3000,7 +3000,7 @@ static int _dasd_requeue_request(struct dasd_ccw_req *cqr) return 0; spin_lock_irq(&cqr->dq->lock); req = (struct request *) cqr->callback_data; - blk_mq_requeue_request(req, false); + blk_mq_requeue_request(req, true); spin_unlock_irq(&cqr->dq->lock); return 0; From eded3ad80a048deb6668bc44494e830122dcfc3a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 16 Apr 2023 22:17:05 -0700 Subject: [PATCH 2954/4345] ia64: fix an addr to taddr in huge_pte_offset() commit 3647ebcfbfca384840231fe13fae665453238a61 upstream. I know nothing of ia64 htlbpage_to_page(), but guess that the p4d line should be using taddr rather than addr, like everywhere else. Link: https://lkml.kernel.org/r/732eae88-3beb-246-2c72-281de786740@google.com Fixes: c03ab9e32a2c ("ia64: add support for folded p4d page tables") Signed-off-by: Hugh Dickins Acked-by: Mike Rapoport (IBM) Cc: Ard Biesheuvel Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- arch/ia64/mm/hugetlbpage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index b331f94d20ac..292a28a2008f 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -57,7 +57,7 @@ huge_pte_offset (struct mm_struct *mm, unsigned long addr, unsigned long sz) pgd = pgd_offset(mm, taddr); if (pgd_present(*pgd)) { - p4d = p4d_offset(pgd, addr); + p4d = p4d_offset(pgd, taddr); if (p4d_present(*p4d)) { pud = pud_offset(p4d, taddr); if (pud_present(*pud)) { From 717ceb487bc30bc32ccb99fa5966a4f5f4e84686 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 4 Apr 2023 11:59:00 -0400 Subject: [PATCH 2955/4345] dm clone: call kmem_cache_destroy() in dm_clone_init() error path commit 6827af4a9a9f5bb664c42abf7c11af4978d72201 upstream. Otherwise the _hydration_cache will leak if dm_register_target() fails. Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-clone-target.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 0d38ad623534..e3156b30294f 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -2221,6 +2221,7 @@ static int __init dm_clone_init(void) r = dm_register_target(&clone_target); if (r < 0) { DMERR("Failed to register clone target"); + kmem_cache_destroy(_hydration_cache); return r; } From 44f29e93a55b544dc961b6f8b4e93abaeaafb9ee Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 4 Apr 2023 13:34:28 -0400 Subject: [PATCH 2956/4345] dm integrity: call kmem_cache_destroy() in dm_integrity_init() error path commit 6b79a428c02769f2a11f8ae76bf866226d134887 upstream. Otherwise the journal_io_cache will leak if dm_register_target() fails. Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-integrity.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index a1c4cc48bf03..7599a122c956 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -4481,11 +4481,13 @@ static int __init dm_integrity_init(void) } r = dm_register_target(&integrity_target); - - if (r < 0) + if (r < 0) { DMERR("register failed %d", r); + kmem_cache_destroy(journal_io_cache); + return r; + } - return r; + return 0; } static void __exit dm_integrity_exit(void) From 3f225f29c69c13ce1cbdb1d607a42efeef080056 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 9 Jan 2023 18:48:00 +0100 Subject: [PATCH 2957/4345] arm64: Stash shadow stack pointer in the task struct on interrupt commit 59b37fe52f49955791a460752c37145f1afdcad1 upstream. Instead of reloading the shadow call stack pointer from the ordinary stack, which may be vulnerable to the kind of gadget based attacks shadow call stacks were designed to prevent, let's store a task's shadow call stack pointer in the task struct when switching to the shadow IRQ stack. Given that currently, the task_struct::scs_sp field is only used to preserve the shadow call stack pointer while a task is scheduled out or running in user space, reusing this field to preserve and restore it while running off the IRQ stack must be safe, as those occurrences are guaranteed to never overlap. (The stack switching logic only switches stacks when running from the task stack, and so the value being saved here always corresponds to the task mode shadow stack) While at it, fold a mov/add/mov sequence into a single add. Signed-off-by: Ard Biesheuvel Reviewed-by: Kees Cook Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20230109174800.3286265-3-ardb@kernel.org Signed-off-by: Catalin Marinas [ardb: v5.10 backport, which doesn't have call_on_irq_stack() yet *] Signed-off-by: Ard Biesheuvel Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/entry.S | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 28d4cdeee5ae..55e477f73158 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -431,9 +431,7 @@ SYM_CODE_END(__swpan_exit_el0) .macro irq_stack_entry mov x19, sp // preserve the original sp -#ifdef CONFIG_SHADOW_CALL_STACK - mov x24, scs_sp // preserve the original shadow stack -#endif + scs_save tsk // preserve the original shadow stack /* * Compare sp with the base of the task stack. @@ -467,9 +465,7 @@ SYM_CODE_END(__swpan_exit_el0) */ .macro irq_stack_exit mov sp, x19 -#ifdef CONFIG_SHADOW_CALL_STACK - mov scs_sp, x24 -#endif + scs_load_current .endm /* GPRs used by entry code */ From 905f847675cfd9df98b748f9189a2571cc1d489c Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 3 Apr 2023 18:48:30 +0300 Subject: [PATCH 2958/4345] perf auxtrace: Fix address filter entire kernel size commit 1f9f33ccf0320be21703d9195dd2b36a1c9a07cb upstream. kallsyms is not completely in address order. In find_entire_kern_cb(), calculate the kernel end from the maximum address not the last symbol. Example: Before: $ sudo cat /proc/kallsyms | grep ' [twTw] ' | tail -1 ffffffffc00b8bd0 t bpf_prog_6deef7357e7b4530 [bpf] $ sudo cat /proc/kallsyms | grep ' [twTw] ' | sort | tail -1 ffffffffc15e0cc0 t iwl_mvm_exit [iwlmvm] $ perf.d093603a05aa record -v --kcore -e intel_pt// --filter 'filter *' -- uname |& grep filter Address filter: filter 0xffffffff93200000/0x2ceba000 After: $ perf.8fb0f7a01f8e record -v --kcore -e intel_pt// --filter 'filter *' -- uname |& grep filter Address filter: filter 0xffffffff93200000/0x2e3e2000 Fixes: 1b36c03e356936d6 ("perf record: Add support for using symbols in address filters") Signed-off-by: Adrian Hunter Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230403154831.8651-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/auxtrace.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 18452f12510c..41dd4c266cc0 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -2279,6 +2279,7 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused, char type, u64 start) { struct sym_args *args = arg; + u64 size; if (!kallsyms__is_function(type)) return 0; @@ -2288,7 +2289,9 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused, args->start = start; } /* Don't know exactly where the kernel ends, so we add a page */ - args->size = round_up(start, page_size) + page_size - args->start; + size = round_up(start, page_size) + page_size - args->start; + if (size > args->size) + args->size = size; return 0; } From 9079ff34a1ac65c52eb825840960257b68e49d47 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 1 May 2023 17:42:06 +0200 Subject: [PATCH 2959/4345] debugobject: Ensure pool refill (again) commit 0af462f19e635ad522f28981238334620881badc upstream. The recent fix to ensure atomicity of lookup and allocation inadvertently broke the pool refill mechanism. Prior to that change debug_objects_activate() and debug_objecs_assert_init() invoked debug_objecs_init() to set up the tracking object for statically initialized objects. That's not longer the case and debug_objecs_init() is now the only place which does pool refills. Depending on the number of statically initialized objects this can be enough to actually deplete the pool, which was observed by Ido via a debugobjects OOM warning. Restore the old behaviour by adding explicit refill opportunities to debug_objects_activate() and debug_objecs_assert_init(). Fixes: 63a759694eed ("debugobject: Prevent init race with static objects") Reported-by: Ido Schimmel Signed-off-by: Thomas Gleixner Tested-by: Ido Schimmel Link: https://lore.kernel.org/r/871qk05a9d.ffs@tglx Signed-off-by: Greg Kroah-Hartman --- lib/debugobjects.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 8282ae37db4e..824337ec36aa 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -590,6 +590,16 @@ static struct debug_obj *lookup_object_or_alloc(void *addr, struct debug_bucket return NULL; } +static void debug_objects_fill_pool(void) +{ + /* + * On RT enabled kernels the pool refill must happen in preemptible + * context: + */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) + fill_pool(); +} + static void __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack) { @@ -598,7 +608,7 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack struct debug_obj *obj; unsigned long flags; - fill_pool(); + debug_objects_fill_pool(); db = get_bucket((unsigned long) addr); @@ -683,6 +693,8 @@ int debug_object_activate(void *addr, const struct debug_obj_descr *descr) if (!debug_objects_enabled) return 0; + debug_objects_fill_pool(); + db = get_bucket((unsigned long) addr); raw_spin_lock_irqsave(&db->lock, flags); @@ -892,6 +904,8 @@ void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr) if (!debug_objects_enabled) return; + debug_objects_fill_pool(); + db = get_bucket((unsigned long) addr); raw_spin_lock_irqsave(&db->lock, flags); From a1e3fffe02e05c05357af91364ac0fc1ed425b5b Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 18 Apr 2023 15:57:47 -0400 Subject: [PATCH 2960/4345] dm flakey: fix a crash with invalid table line commit 98dba02d9a93eec11bffbb93c7c51624290702d2 upstream. This command will crash with NULL pointer dereference: dmsetup create flakey --table \ "0 `blockdev --getsize /dev/ram0` flakey /dev/ram0 0 0 1 2 corrupt_bio_byte 512" Fix the crash by checking if arg_name is non-NULL before comparing it. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-flakey.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 36a4ef51ecaa..faae360b881b 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -124,9 +124,9 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc, * Direction r or w? */ arg_name = dm_shift_arg(as); - if (!strcasecmp(arg_name, "w")) + if (arg_name && !strcasecmp(arg_name, "w")) fc->corrupt_bio_rw = WRITE; - else if (!strcasecmp(arg_name, "r")) + else if (arg_name && !strcasecmp(arg_name, "r")) fc->corrupt_bio_rw = READ; else { ti->error = "Invalid corrupt bio direction (r or w)"; From ea827627a9249154b34b646b1e1007013402afea Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 17 Apr 2023 11:59:56 -0400 Subject: [PATCH 2961/4345] dm ioctl: fix nested locking in table_clear() to remove deadlock concern commit 3d32aaa7e66d5c1479a3c31d6c2c5d45dd0d3b89 upstream. syzkaller found the following problematic rwsem locking (with write lock already held): down_read+0x9d/0x450 kernel/locking/rwsem.c:1509 dm_get_inactive_table+0x2b/0xc0 drivers/md/dm-ioctl.c:773 __dev_status+0x4fd/0x7c0 drivers/md/dm-ioctl.c:844 table_clear+0x197/0x280 drivers/md/dm-ioctl.c:1537 In table_clear, it first acquires a write lock https://elixir.bootlin.com/linux/v6.2/source/drivers/md/dm-ioctl.c#L1520 down_write(&_hash_lock); Then before the lock is released at L1539, there is a path shown above: table_clear -> __dev_status -> dm_get_inactive_table -> down_read https://elixir.bootlin.com/linux/v6.2/source/drivers/md/dm-ioctl.c#L773 down_read(&_hash_lock); It tries to acquire the same read lock again, resulting in the deadlock problem. Fix this by moving table_clear()'s __dev_status() call to after its up_write(&_hash_lock); Cc: stable@vger.kernel.org Reported-by: Zheng Zhang Signed-off-by: Mike Snitzer Signed-off-by: Greg Kroah-Hartman --- drivers/md/dm-ioctl.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 20171c9d8952..5f9b9178c647 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1435,11 +1435,12 @@ static int table_clear(struct file *filp, struct dm_ioctl *param, size_t param_s hc->new_map = NULL; } - param->flags &= ~DM_INACTIVE_PRESENT_FLAG; - - __dev_status(hc->md, param); md = hc->md; up_write(&_hash_lock); + + param->flags &= ~DM_INACTIVE_PRESENT_FLAG; + __dev_status(md, param); + if (old_map) { dm_sync_table(md); dm_table_destroy(old_map); From a25a403e4b318c005109a0af42113a208206da6c Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 3 Apr 2023 18:48:31 +0300 Subject: [PATCH 2962/4345] perf intel-pt: Fix CYC timestamps after standalone CBR commit 430635a0ef1ce958b7b4311f172694ece2c692b8 upstream. After a standalone CBR (not associated with TSC), update the cycles reference timestamp and reset the cycle count, so that CYC timestamps are calculated relative to that point with the new frequency. Fixes: cc33618619cefc6d ("perf tools: Add Intel PT support for decoding CYC packets") Signed-off-by: Adrian Hunter Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230403154831.8651-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index e4c485f92c02..48fda1a19ab5 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1639,6 +1639,8 @@ static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) decoder->cbr = cbr; decoder->cbr_cyc_to_tsc = decoder->max_non_turbo_ratio_fp / cbr; + decoder->cyc_ref_timestamp = decoder->timestamp; + decoder->cycle_cnt = 0; intel_pt_mtc_cyc_cnt_cbr(decoder); } From 9134b5a4647e46a76dbedb3604f0dd1870e19169 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 9 Jan 2023 18:47:59 +0100 Subject: [PATCH 2963/4345] arm64: Always load shadow stack pointer directly from the task struct commit 2198d07c509f1db4a1185d1f65aaada794c6ea59 upstream. All occurrences of the scs_load macro load the value of the shadow call stack pointer from the task which is current at that point. So instead of taking a task struct register argument in the scs_load macro to specify the task struct to load from, let's always reference the current task directly. This should make it much harder to exploit any instruction sequences reloading the shadow call stack pointer register from memory. Signed-off-by: Ard Biesheuvel Acked-by: Mark Rutland Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20230109174800.3286265-2-ardb@kernel.org Signed-off-by: Catalin Marinas Signed-off-by: Ard Biesheuvel Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/scs.h | 7 ++++--- arch/arm64/kernel/entry.S | 4 ++-- arch/arm64/kernel/head.S | 2 +- 3 files changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index eaa2cd92e4c1..7155055a5beb 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -9,15 +9,16 @@ #ifdef CONFIG_SHADOW_CALL_STACK scs_sp .req x18 - .macro scs_load tsk, tmp - ldr scs_sp, [\tsk, #TSK_TI_SCS_SP] + .macro scs_load_current + get_current_task scs_sp + ldr scs_sp, [scs_sp, #TSK_TI_SCS_SP] .endm .macro scs_save tsk, tmp str scs_sp, [\tsk, #TSK_TI_SCS_SP] .endm #else - .macro scs_load tsk, tmp + .macro scs_load_current .endm .macro scs_save tsk, tmp diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index d5bc1dbdd2fd..28d4cdeee5ae 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -221,7 +221,7 @@ alternative_else_nop_endif ptrauth_keys_install_kernel tsk, x20, x22, x23 - scs_load tsk, x20 + scs_load_current .else add x21, sp, #S_FRAME_SIZE get_current_task tsk @@ -1025,7 +1025,7 @@ SYM_FUNC_START(cpu_switch_to) msr sp_el0, x1 ptrauth_keys_install_kernel x1, x8, x9, x10 scs_save x0, x8 - scs_load x1, x8 + scs_load_current ret SYM_FUNC_END(cpu_switch_to) NOKPROBE(cpu_switch_to) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index e1c25fa3b8e6..351ee64c7deb 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -747,7 +747,7 @@ SYM_FUNC_START_LOCAL(__secondary_switched) ldr x2, [x0, #CPU_BOOT_TASK] cbz x2, __secondary_too_slow msr sp_el0, x2 - scs_load x2, x3 + scs_load_current mov x29, #0 mov x30, #0 From c820c05c5ff6613ad424dce1cddc459ffd2fb96b Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Thu, 14 Apr 2022 17:19:38 +0800 Subject: [PATCH 2964/4345] sound/oss/dmasound: fix 'dmasound_setup' defined but not used commit 357ad4d898286b94aaae0cb7e3f573459e5b98b9 upstream. We observed: 'dmasound_setup' defined but not used error with COMPILER=gcc ARCH=m68k DEFCONFIG=allmodconfig build. Fix it by adding __maybe_unused to dmasound_setup. Error(s): sound/oss/dmasound/dmasound_core.c:1431:12: error: 'dmasound_setup' defined but not used [-Werror=unused-function] Fixes: 9dd7c46346ca ("sound/oss/dmasound: fix build when drivers are mixed =y/=m") Signed-off-by: Miles Chen Acked-by: Randy Dunlap Link: https://lore.kernel.org/r/20220414091940.2216-1-miles.chen@mediatek.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/oss/dmasound/dmasound_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 7a8698ff7f54..7454b058dda5 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -1442,7 +1442,7 @@ void dmasound_deinit(void) unregister_sound_dsp(sq_unit); } -static int dmasound_setup(char *str) +static int __maybe_unused dmasound_setup(char *str) { int ints[6], size; From 14fc6af67b3f54f6d5a02e8066b4981762ea17d1 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 6 Jan 2023 17:46:18 +0100 Subject: [PATCH 2965/4345] arm64: dts: qcom: sdm845: correct dynamic power coefficients commit 44750f153699b6e4f851a399287e5c8df208d696 upstream. While stressing EAS on my dragonboard RB3, I have noticed that LITTLE cores where never selected as the most energy efficient CPU whatever the utilization level of waking task. energy model framework uses its cost field to estimate the energy with the formula: nrg = cost of the selected OPP * utilization / CPU's max capacity which ends up selecting the CPU with lowest cost / max capacity ration as long as the utilization fits in the OPP's capacity. If we compare the cost of a little OPP with similar capacity of a big OPP like : OPP(kHz) OPP capacity cost max capacity cost/max capacity LITTLE 1766400 407 351114 407 863 big 1056000 408 520267 1024 508 This can be interpreted as the LITTLE core consumes 70% more than big core for the same compute capacity. According to [1], LITTLE consumes 10% less than big core for Coremark benchmark at those OPPs. If we consider that everything else stays unchanged, the dynamic-power-coefficient of LITTLE core should be only 53% of the current value: 290 * 53% = 154 Set the dynamic-power-coefficient of CPU0-3 to 154 to fix the energy model. [1] https://github.com/kdrag0n/freqbench/tree/master/results/sdm845/main Fixes: 0e0a8e35d725 ("arm64: dts: qcom: sdm845: correct dynamic power coefficients") Signed-off-by: Vincent Guittot Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230106164618.1845281-1-vincent.guittot@linaro.org Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/qcom/sdm845.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 28fbd728304d..71e5b9fdc9e1 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -197,7 +197,7 @@ &LITTLE_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; capacity-dmips-mhz = <611>; - dynamic-power-coefficient = <290>; + dynamic-power-coefficient = <154>; qcom,freq-domain = <&cpufreq_hw 0>; operating-points-v2 = <&cpu0_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -222,7 +222,7 @@ &LITTLE_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; capacity-dmips-mhz = <611>; - dynamic-power-coefficient = <290>; + dynamic-power-coefficient = <154>; qcom,freq-domain = <&cpufreq_hw 0>; operating-points-v2 = <&cpu0_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -244,7 +244,7 @@ &LITTLE_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; capacity-dmips-mhz = <611>; - dynamic-power-coefficient = <290>; + dynamic-power-coefficient = <154>; qcom,freq-domain = <&cpufreq_hw 0>; operating-points-v2 = <&cpu0_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, @@ -266,7 +266,7 @@ &LITTLE_CPU_SLEEP_1 &CLUSTER_SLEEP_0>; capacity-dmips-mhz = <611>; - dynamic-power-coefficient = <290>; + dynamic-power-coefficient = <154>; qcom,freq-domain = <&cpufreq_hw 0>; operating-points-v2 = <&cpu0_opp_table>; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_EBI1 3>, From a222d2794c53f8165de20aa91b39e35e4b72bce9 Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Sat, 15 May 2021 16:03:15 +0900 Subject: [PATCH 2966/4345] scsi: target: core: Avoid smp_processor_id() in preemptible code commit 70ca3c57ff914113f681e657634f7fbfa68e1ad1 upstream. The BUG message "BUG: using smp_processor_id() in preemptible [00000000] code" was observed for TCMU devices with kernel config DEBUG_PREEMPT. The message was observed when blktests block/005 was run on TCMU devices with fileio backend or user:zbc backend [1]. The commit 1130b499b4a7 ("scsi: target: tcm_loop: Use LIO wq cmd submission helper") triggered the symptom. The commit modified work queue to handle commands and changed 'current->nr_cpu_allowed' at smp_processor_id() call. The message was also observed at system shutdown when TCMU devices were not cleaned up [2]. The function smp_processor_id() was called in SCSI host work queue for abort handling, and triggered the BUG message. This symptom was observed regardless of the commit 1130b499b4a7 ("scsi: target: tcm_loop: Use LIO wq cmd submission helper"). To avoid the preemptible code check at smp_processor_id(), get CPU ID with raw_smp_processor_id() instead. The CPU ID is used for performance improvement then thread move to other CPU will not affect the code. [1] [ 56.468103] run blktests block/005 at 2021-05-12 14:16:38 [ 57.369473] check_preemption_disabled: 85 callbacks suppressed [ 57.369480] BUG: using smp_processor_id() in preemptible [00000000] code: fio/1511 [ 57.369506] BUG: using smp_processor_id() in preemptible [00000000] code: fio/1510 [ 57.369512] BUG: using smp_processor_id() in preemptible [00000000] code: fio/1506 [ 57.369552] caller is __target_init_cmd+0x157/0x170 [target_core_mod] [ 57.369606] CPU: 4 PID: 1506 Comm: fio Not tainted 5.13.0-rc1+ #34 [ 57.369613] Hardware name: System manufacturer System Product Name/PRIME Z270-A, BIOS 1302 03/15/2018 [ 57.369617] Call Trace: [ 57.369621] BUG: using smp_processor_id() in preemptible [00000000] code: fio/1507 [ 57.369628] dump_stack+0x6d/0x89 [ 57.369642] check_preemption_disabled+0xc8/0xd0 [ 57.369628] caller is __target_init_cmd+0x157/0x170 [target_core_mod] [ 57.369655] __target_init_cmd+0x157/0x170 [target_core_mod] [ 57.369695] target_init_cmd+0x76/0x90 [target_core_mod] [ 57.369732] tcm_loop_queuecommand+0x109/0x210 [tcm_loop] [ 57.369744] scsi_queue_rq+0x38e/0xc40 [ 57.369761] __blk_mq_try_issue_directly+0x109/0x1c0 [ 57.369779] blk_mq_try_issue_directly+0x43/0x90 [ 57.369790] blk_mq_submit_bio+0x4e5/0x5d0 [ 57.369812] submit_bio_noacct+0x46e/0x4e0 [ 57.369830] __blkdev_direct_IO_simple+0x1a3/0x2d0 [ 57.369859] ? set_init_blocksize.isra.0+0x60/0x60 [ 57.369880] generic_file_read_iter+0x89/0x160 [ 57.369898] blkdev_read_iter+0x44/0x60 [ 57.369906] new_sync_read+0x102/0x170 [ 57.369929] vfs_read+0xd4/0x160 [ 57.369941] __x64_sys_pread64+0x6e/0xa0 [ 57.369946] ? lockdep_hardirqs_on+0x79/0x100 [ 57.369958] do_syscall_64+0x3a/0x70 [ 57.369965] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 57.369973] RIP: 0033:0x7f7ed4c1399f [ 57.369979] Code: 08 89 3c 24 48 89 4c 24 18 e8 7d f3 ff ff 4c 8b 54 24 18 48 8b 54 24 10 41 89 c0 48 8b 74 24 08 8b 3c 24 b8 11 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 31 44 89 c7 48 89 04 24 e8 cd f3 ff ff 48 8b [ 57.369983] RSP: 002b:00007ffd7918c580 EFLAGS: 00000293 ORIG_RAX: 0000000000000011 [ 57.369990] RAX: ffffffffffffffda RBX: 00000000015b4540 RCX: 00007f7ed4c1399f [ 57.369993] RDX: 0000000000001000 RSI: 00000000015de000 RDI: 0000000000000009 [ 57.369996] RBP: 00000000015b4540 R08: 0000000000000000 R09: 0000000000000001 [ 57.369999] R10: 0000000000e5c000 R11: 0000000000000293 R12: 00007f7eb5269a70 [ 57.370002] R13: 0000000000000000 R14: 0000000000001000 R15: 00000000015b4568 [ 57.370031] CPU: 7 PID: 1507 Comm: fio Not tainted 5.13.0-rc1+ #34 [ 57.370036] Hardware name: System manufacturer System Product Name/PRIME Z270-A, BIOS 1302 03/15/2018 [ 57.370039] Call Trace: [ 57.370045] dump_stack+0x6d/0x89 [ 57.370056] check_preemption_disabled+0xc8/0xd0 [ 57.370068] __target_init_cmd+0x157/0x170 [target_core_mod] [ 57.370121] target_init_cmd+0x76/0x90 [target_core_mod] [ 57.370178] tcm_loop_queuecommand+0x109/0x210 [tcm_loop] [ 57.370197] scsi_queue_rq+0x38e/0xc40 [ 57.370224] __blk_mq_try_issue_directly+0x109/0x1c0 ... [2] [ 117.458597] BUG: using smp_processor_id() in preemptible [00000000] code: kworker/u16:8 [ 117.467279] caller is __target_init_cmd+0x157/0x170 [target_core_mod] [ 117.473893] CPU: 1 PID: 418 Comm: kworker/u16:6 Not tainted 5.13.0-rc1+ #34 [ 117.481150] Hardware name: System manufacturer System Product Name/PRIME Z270-A, BIOS 8 [ 117.481153] Workqueue: scsi_tmf_7 scmd_eh_abort_handler [ 117.481156] Call Trace: [ 117.481158] dump_stack+0x6d/0x89 [ 117.481162] check_preemption_disabled+0xc8/0xd0 [ 117.512575] target_submit_tmr+0x41/0x150 [target_core_mod] [ 117.519705] tcm_loop_issue_tmr+0xa7/0x100 [tcm_loop] [ 117.524913] tcm_loop_abort_task+0x43/0x60 [tcm_loop] [ 117.530137] scmd_eh_abort_handler+0x7b/0x230 [ 117.534681] process_one_work+0x268/0x580 [ 117.538862] worker_thread+0x55/0x3b0 [ 117.542652] ? process_one_work+0x580/0x580 [ 117.548351] kthread+0x143/0x160 [ 117.551675] ? kthread_create_worker_on_cpu+0x40/0x40 [ 117.556873] ret_from_fork+0x1f/0x30 Link: https://lore.kernel.org/r/20210515070315.215801-1-shinichiro.kawasaki@wdc.com Fixes: 1526d9f10c61 ("scsi: target: Make state_list per CPU") Cc: stable@vger.kernel.org # v5.11+ Reviewed-by: Mike Christie Signed-off-by: Shin'ichiro Kawasaki Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/target/target_core_transport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 230fffa993c0..2e97937f005f 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1396,7 +1396,7 @@ void transport_init_se_cmd( cmd->orig_fe_lun = unpacked_lun; if (!(cmd->se_cmd_flags & SCF_USE_CPUID)) - cmd->cpuid = smp_processor_id(); + cmd->cpuid = raw_smp_processor_id(); cmd->state_active = false; } From e044a24447189419c3a7ccc5fa6da7516036dc55 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 2 May 2023 10:25:24 +0200 Subject: [PATCH 2967/4345] netfilter: nf_tables: deactivate anonymous set from preparation phase commit c1592a89942e9678f7d9c8030efa777c0d57edab upstream. Toggle deleted anonymous sets as inactive in the next generation, so users cannot perform any update on it. Clear the generation bitmask in case the transaction is aborted. The following KASAN splat shows a set element deletion for a bound anonymous set that has been already removed in the same transaction. [ 64.921510] ================================================================== [ 64.923123] BUG: KASAN: wild-memory-access in nf_tables_commit+0xa24/0x1490 [nf_tables] [ 64.924745] Write of size 8 at addr dead000000000122 by task test/890 [ 64.927903] CPU: 3 PID: 890 Comm: test Not tainted 6.3.0+ #253 [ 64.931120] Call Trace: [ 64.932699] [ 64.934292] dump_stack_lvl+0x33/0x50 [ 64.935908] ? nf_tables_commit+0xa24/0x1490 [nf_tables] [ 64.937551] kasan_report+0xda/0x120 [ 64.939186] ? nf_tables_commit+0xa24/0x1490 [nf_tables] [ 64.940814] nf_tables_commit+0xa24/0x1490 [nf_tables] [ 64.942452] ? __kasan_slab_alloc+0x2d/0x60 [ 64.944070] ? nf_tables_setelem_notify+0x190/0x190 [nf_tables] [ 64.945710] ? kasan_set_track+0x21/0x30 [ 64.947323] nfnetlink_rcv_batch+0x709/0xd90 [nfnetlink] [ 64.948898] ? nfnetlink_rcv_msg+0x480/0x480 [nfnetlink] Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 1 + net/netfilter/nf_tables_api.c | 12 ++++++++++++ net/netfilter/nft_dynset.c | 2 +- net/netfilter/nft_lookup.c | 2 +- net/netfilter/nft_objref.c | 2 +- 5 files changed, 16 insertions(+), 3 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index e66fee99ed3e..564fbe0c865f 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -507,6 +507,7 @@ struct nft_set_binding { }; enum nft_trans_phase; +void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set); void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7bb716df7afc..fe51cedd9cc3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4479,12 +4479,24 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, } } +void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) +{ + if (nft_set_is_anonymous(set)) + nft_clear(ctx->net, set); + + set->use++; +} +EXPORT_SYMBOL_GPL(nf_tables_activate_set); + void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase) { switch (phase) { case NFT_TRANS_PREPARE: + if (nft_set_is_anonymous(set)) + nft_deactivate_next(ctx->net, set); + set->use--; return; case NFT_TRANS_ABORT: diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 8c45e01fecdd..038588d4d80e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -233,7 +233,7 @@ static void nft_dynset_activate(const struct nft_ctx *ctx, { struct nft_dynset *priv = nft_expr_priv(expr); - priv->set->use++; + nf_tables_activate_set(ctx, priv->set); } static void nft_dynset_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index b0f558b4fea5..8bc008ff00cb 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -132,7 +132,7 @@ static void nft_lookup_activate(const struct nft_ctx *ctx, { struct nft_lookup *priv = nft_expr_priv(expr); - priv->set->use++; + nf_tables_activate_set(ctx, priv->set); } static void nft_lookup_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index bc104d36d3bb..25157d8cc250 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -180,7 +180,7 @@ static void nft_objref_map_activate(const struct nft_ctx *ctx, { struct nft_objref_map *priv = nft_expr_priv(expr); - priv->set->use++; + nf_tables_activate_set(ctx, priv->set); } static void nft_objref_map_destroy(const struct nft_ctx *ctx, From 6a392b806f185dc122761d17138ab3bdc74bb823 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Apr 2021 14:51:22 +0200 Subject: [PATCH 2968/4345] tty: create internal tty.h file [ Upstream commit 98602c010ceba82f2c2384122dbd07bc965fd367 ] There are a number of functions and #defines in include/linux/tty.h that do not belong there as they are private to the tty core code. Create an initial drivers/tty/tty.h file and copy the odd "tty logging" macros into it to seed the file with some initial things that we know nothing outside of the tty core should be calling. Cc: Tetsuo Handa Cc: Jiri Slaby Link: https://lore.kernel.org/r/20210408125134.3016837-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 094fb49a2d0d ("tty: Prevent writing chars during tcsetattr TCSADRAIN/FLUSH") Signed-off-by: Sasha Levin --- drivers/tty/n_tty.c | 1 + drivers/tty/pty.c | 1 + drivers/tty/tty.h | 21 +++++++++++++++++++++ drivers/tty/tty_io.c | 1 + drivers/tty/tty_jobctrl.c | 1 + drivers/tty/tty_ldisc.c | 1 + drivers/tty/tty_port.c | 1 + include/linux/tty.h | 12 ------------ 8 files changed, 27 insertions(+), 12 deletions(-) create mode 100644 drivers/tty/tty.h diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 12dde01e576b..8e7931d93543 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -49,6 +49,7 @@ #include #include #include +#include "tty.h" /* * Until this number of characters is queued in the xmit buffer, select will diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 16498f5fba64..ca3e5a6c1a49 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -29,6 +29,7 @@ #include #include #include +#include "tty.h" #undef TTY_DEBUG_HANGUP #ifdef TTY_DEBUG_HANGUP diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h new file mode 100644 index 000000000000..f4cd20261e91 --- /dev/null +++ b/drivers/tty/tty.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * TTY core internal functions + */ + +#ifndef _TTY_INTERNAL_H +#define _TTY_INTERNAL_H + +#define tty_msg(fn, tty, f, ...) \ + fn("%s %s: " f, tty_driver_name(tty), tty_name(tty), ##__VA_ARGS__) + +#define tty_debug(tty, f, ...) tty_msg(pr_debug, tty, f, ##__VA_ARGS__) +#define tty_info(tty, f, ...) tty_msg(pr_info, tty, f, ##__VA_ARGS__) +#define tty_notice(tty, f, ...) tty_msg(pr_notice, tty, f, ##__VA_ARGS__) +#define tty_warn(tty, f, ...) tty_msg(pr_warn, tty, f, ##__VA_ARGS__) +#define tty_err(tty, f, ...) tty_msg(pr_err, tty, f, ##__VA_ARGS__) + +#define tty_info_ratelimited(tty, f, ...) \ + tty_msg(pr_info_ratelimited, tty, f, ##__VA_ARGS__) + +#endif diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index c37d2657308c..86fbfe42ce0a 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -108,6 +108,7 @@ #include #include +#include "tty.h" #undef TTY_DEBUG_HANGUP #ifdef TTY_DEBUG_HANGUP diff --git a/drivers/tty/tty_jobctrl.c b/drivers/tty/tty_jobctrl.c index aa6d0537b379..95d67613b25b 100644 --- a/drivers/tty/tty_jobctrl.c +++ b/drivers/tty/tty_jobctrl.c @@ -11,6 +11,7 @@ #include #include #include +#include "tty.h" static int is_ignored(int sig) { diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index fe37ec331289..c23938b8628d 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -19,6 +19,7 @@ #include #include #include +#include "tty.h" #undef LDISC_DEBUG_HANGUP diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c index ea80bf872f54..cbb56f725bc4 100644 --- a/drivers/tty/tty_port.c +++ b/drivers/tty/tty_port.c @@ -18,6 +18,7 @@ #include #include #include +#include "tty.h" static int tty_port_default_receive_buf(struct tty_port *port, const unsigned char *p, diff --git a/include/linux/tty.h b/include/linux/tty.h index 5972f43b9d5a..9e3725589214 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -786,16 +786,4 @@ static inline void proc_tty_register_driver(struct tty_driver *d) {} static inline void proc_tty_unregister_driver(struct tty_driver *d) {} #endif -#define tty_msg(fn, tty, f, ...) \ - fn("%s %s: " f, tty_driver_name(tty), tty_name(tty), ##__VA_ARGS__) - -#define tty_debug(tty, f, ...) tty_msg(pr_debug, tty, f, ##__VA_ARGS__) -#define tty_info(tty, f, ...) tty_msg(pr_info, tty, f, ##__VA_ARGS__) -#define tty_notice(tty, f, ...) tty_msg(pr_notice, tty, f, ##__VA_ARGS__) -#define tty_warn(tty, f, ...) tty_msg(pr_warn, tty, f, ##__VA_ARGS__) -#define tty_err(tty, f, ...) tty_msg(pr_err, tty, f, ##__VA_ARGS__) - -#define tty_info_ratelimited(tty, f, ...) \ - tty_msg(pr_info_ratelimited, tty, f, ##__VA_ARGS__) - #endif From f665d81ffad7a3e9af6b22acf16a60ebbdfcef64 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Apr 2021 14:51:29 +0200 Subject: [PATCH 2969/4345] tty: audit: move some local functions out of tty.h [ Upstream commit da5d669e00d2c437b3f508d60add417fc74f4bb6 ] The functions tty_audit_add_data() and tty_audit_tiocsti() are local to the tty core code, and do not need to be in a "kernel-wide" header file so move them to drivers/tty/tty.h Cc: Jiri Slaby Link: https://lore.kernel.org/r/20210408125134.3016837-9-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 094fb49a2d0d ("tty: Prevent writing chars during tcsetattr TCSADRAIN/FLUSH") Signed-off-by: Sasha Levin --- drivers/tty/tty.h | 14 ++++++++++++++ drivers/tty/tty_audit.c | 1 + include/linux/tty.h | 10 ---------- 3 files changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h index f4cd20261e91..f131d538b62b 100644 --- a/drivers/tty/tty.h +++ b/drivers/tty/tty.h @@ -18,4 +18,18 @@ #define tty_info_ratelimited(tty, f, ...) \ tty_msg(pr_info_ratelimited, tty, f, ##__VA_ARGS__) +/* tty_audit.c */ +#ifdef CONFIG_AUDIT +void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size); +void tty_audit_tiocsti(struct tty_struct *tty, char ch); +#else +static inline void tty_audit_add_data(struct tty_struct *tty, const void *data, + size_t size) +{ +} +static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch) +{ +} +#endif + #endif diff --git a/drivers/tty/tty_audit.c b/drivers/tty/tty_audit.c index 9f906a5b8e81..9b30edee71fe 100644 --- a/drivers/tty/tty_audit.c +++ b/drivers/tty/tty_audit.c @@ -10,6 +10,7 @@ #include #include #include +#include "tty.h" struct tty_audit_buf { struct mutex mutex; /* Protects all data below */ diff --git a/include/linux/tty.h b/include/linux/tty.h index 9e3725589214..a1a9c4b8210e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -731,20 +731,10 @@ static inline void n_tty_init(void) { } /* tty_audit.c */ #ifdef CONFIG_AUDIT -extern void tty_audit_add_data(struct tty_struct *tty, const void *data, - size_t size); extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); -extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); extern int tty_audit_push(void); #else -static inline void tty_audit_add_data(struct tty_struct *tty, const void *data, - size_t size) -{ -} -static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch) -{ -} static inline void tty_audit_exit(void) { } From 1924d47a2809e2690fe6414d120d51b2a92ffeae Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Apr 2021 14:51:30 +0200 Subject: [PATCH 2970/4345] tty: move some internal tty lock enums and functions out of tty.h [ Upstream commit 6c80c0b94b94192d9a34b400f8237703c6475f4d ] Move the TTY_LOCK_* enums and tty_ldisc lock functions out of the global tty.h into the local header file to clean things up. Cc: Jiri Slaby Link: https://lore.kernel.org/r/20210408125134.3016837-10-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 094fb49a2d0d ("tty: Prevent writing chars during tcsetattr TCSADRAIN/FLUSH") Signed-off-by: Sasha Levin --- drivers/tty/tty.h | 26 ++++++++++++++++++++++++++ drivers/tty/tty_buffer.c | 2 +- drivers/tty/tty_mutex.c | 1 + include/linux/tty.h | 26 -------------------------- 4 files changed, 28 insertions(+), 27 deletions(-) diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h index f131d538b62b..552e263e02df 100644 --- a/drivers/tty/tty.h +++ b/drivers/tty/tty.h @@ -18,6 +18,32 @@ #define tty_info_ratelimited(tty, f, ...) \ tty_msg(pr_info_ratelimited, tty, f, ##__VA_ARGS__) +/* + * Lock subclasses for tty locks + * + * TTY_LOCK_NORMAL is for normal ttys and master ptys. + * TTY_LOCK_SLAVE is for slave ptys only. + * + * Lock subclasses are necessary for handling nested locking with pty pairs. + * tty locks which use nested locking: + * + * legacy_mutex - Nested tty locks are necessary for releasing pty pairs. + * The stable lock order is master pty first, then slave pty. + * termios_rwsem - The stable lock order is tty_buffer lock->termios_rwsem. + * Subclassing this lock enables the slave pty to hold its + * termios_rwsem when claiming the master tty_buffer lock. + * tty_buffer lock - slave ptys can claim nested buffer lock when handling + * signal chars. The stable lock order is slave pty, then + * master. + */ +enum { + TTY_LOCK_NORMAL = 0, + TTY_LOCK_SLAVE, +}; + +int tty_ldisc_lock(struct tty_struct *tty, unsigned long timeout); +void tty_ldisc_unlock(struct tty_struct *tty); + /* tty_audit.c */ #ifdef CONFIG_AUDIT void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size); diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 5bbc2e010b48..9f2379815557 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -17,7 +17,7 @@ #include #include #include - +#include "tty.h" #define MIN_TTYB_SIZE 256 #define TTYB_ALIGN_MASK 255 diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c index 2640635ee177..393518a24cfe 100644 --- a/drivers/tty/tty_mutex.c +++ b/drivers/tty/tty_mutex.c @@ -4,6 +4,7 @@ #include #include #include +#include "tty.h" /* Legacy tty mutex glue */ diff --git a/include/linux/tty.h b/include/linux/tty.h index a1a9c4b8210e..af398d0aa9fd 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -16,30 +16,6 @@ #include -/* - * Lock subclasses for tty locks - * - * TTY_LOCK_NORMAL is for normal ttys and master ptys. - * TTY_LOCK_SLAVE is for slave ptys only. - * - * Lock subclasses are necessary for handling nested locking with pty pairs. - * tty locks which use nested locking: - * - * legacy_mutex - Nested tty locks are necessary for releasing pty pairs. - * The stable lock order is master pty first, then slave pty. - * termios_rwsem - The stable lock order is tty_buffer lock->termios_rwsem. - * Subclassing this lock enables the slave pty to hold its - * termios_rwsem when claiming the master tty_buffer lock. - * tty_buffer lock - slave ptys can claim nested buffer lock when handling - * signal chars. The stable lock order is slave pty, then - * master. - */ - -enum { - TTY_LOCK_NORMAL = 0, - TTY_LOCK_SLAVE, -}; - /* * (Note: the *_driver.minor_start values 1, 64, 128, 192 are * hardcoded at present.) @@ -419,8 +395,6 @@ extern const char *tty_name(const struct tty_struct *tty); extern struct tty_struct *tty_kopen(dev_t device); extern void tty_kclose(struct tty_struct *tty); extern int tty_dev_name_to_number(const char *name, dev_t *number); -extern int tty_ldisc_lock(struct tty_struct *tty, unsigned long timeout); -extern void tty_ldisc_unlock(struct tty_struct *tty); extern ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *); #else static inline void tty_kref_put(struct tty_struct *tty) From 57b510c7d37717784a5c082c7ec66baecfe6dfff Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Apr 2021 14:51:32 +0200 Subject: [PATCH 2971/4345] tty: move some tty-only functions to drivers/tty/tty.h [ Upstream commit 9f72cab1596327e1011ab4599c07b165e0fb45db ] The flow change and restricted_tty_write() logic is internal to the tty core only, so move it out of the include/linux/tty.h file. Cc: Jiri Slaby Link: https://lore.kernel.org/r/20210408125134.3016837-12-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 094fb49a2d0d ("tty: Prevent writing chars during tcsetattr TCSADRAIN/FLUSH") Signed-off-by: Sasha Levin --- drivers/tty/tty.h | 17 +++++++++++++++++ drivers/tty/tty_ioctl.c | 1 + include/linux/tty.h | 16 ---------------- 3 files changed, 18 insertions(+), 16 deletions(-) diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h index 552e263e02df..9eda9e5f8ad5 100644 --- a/drivers/tty/tty.h +++ b/drivers/tty/tty.h @@ -41,6 +41,21 @@ enum { TTY_LOCK_SLAVE, }; +/* Values for tty->flow_change */ +#define TTY_THROTTLE_SAFE 1 +#define TTY_UNTHROTTLE_SAFE 2 + +static inline void __tty_set_flow_change(struct tty_struct *tty, int val) +{ + tty->flow_change = val; +} + +static inline void tty_set_flow_change(struct tty_struct *tty, int val) +{ + tty->flow_change = val; + smp_mb(); +} + int tty_ldisc_lock(struct tty_struct *tty, unsigned long timeout); void tty_ldisc_unlock(struct tty_struct *tty); @@ -58,4 +73,6 @@ static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch) } #endif +ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *); + #endif diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 803da2d111c8..50e65784fbf7 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -21,6 +21,7 @@ #include #include #include +#include "tty.h" #include #include diff --git a/include/linux/tty.h b/include/linux/tty.h index af398d0aa9fd..a641fc6a7fa8 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -350,21 +350,6 @@ struct tty_file_private { #define TTY_LDISC_CHANGING 20 /* Change pending - non-block IO */ #define TTY_LDISC_HALTED 22 /* Line discipline is halted */ -/* Values for tty->flow_change */ -#define TTY_THROTTLE_SAFE 1 -#define TTY_UNTHROTTLE_SAFE 2 - -static inline void __tty_set_flow_change(struct tty_struct *tty, int val) -{ - tty->flow_change = val; -} - -static inline void tty_set_flow_change(struct tty_struct *tty, int val) -{ - tty->flow_change = val; - smp_mb(); -} - static inline bool tty_io_nonblock(struct tty_struct *tty, struct file *file) { return file->f_flags & O_NONBLOCK || @@ -395,7 +380,6 @@ extern const char *tty_name(const struct tty_struct *tty); extern struct tty_struct *tty_kopen(dev_t device); extern void tty_kclose(struct tty_struct *tty); extern int tty_dev_name_to_number(const char *name, dev_t *number); -extern ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *); #else static inline void tty_kref_put(struct tty_struct *tty) { } From 6c2ee50c9012b926aa298538a347a747e5ce6ba7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Apr 2021 14:51:34 +0200 Subject: [PATCH 2972/4345] tty: clean include/linux/tty.h up [ Upstream commit 5ffa6e344a1c92a27c242f500fc74e6eb361a4bc ] There are a lot of tty-core-only functions that are listed in include/linux/tty.h. Move them to drivers/tty/tty.h so that no one else can accidentally call them or think that they are public functions. Cc: Jiri Slaby Link: https://lore.kernel.org/r/20210408125134.3016837-14-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 094fb49a2d0d ("tty: Prevent writing chars during tcsetattr TCSADRAIN/FLUSH") Signed-off-by: Sasha Levin --- drivers/tty/n_gsm.c | 1 + drivers/tty/n_hdlc.c | 1 + drivers/tty/tty.h | 37 +++++++++++++++++++++++++++++++++++++ drivers/tty/tty_baudrate.c | 1 + include/linux/tty.h | 33 --------------------------------- 5 files changed, 40 insertions(+), 33 deletions(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index f5063499f9cf..23b014b8c919 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -50,6 +50,7 @@ #include #include #include +#include "tty.h" static int debug; module_param(debug, int, 0600); diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index 48c64e68017c..697199a3ca01 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -100,6 +100,7 @@ #include #include +#include "tty.h" /* * Buffers for individual HDLC frames diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h index 9eda9e5f8ad5..74ed99bc5449 100644 --- a/drivers/tty/tty.h +++ b/drivers/tty/tty.h @@ -59,6 +59,43 @@ static inline void tty_set_flow_change(struct tty_struct *tty, int val) int tty_ldisc_lock(struct tty_struct *tty, unsigned long timeout); void tty_ldisc_unlock(struct tty_struct *tty); +int __tty_check_change(struct tty_struct *tty, int sig); +int tty_check_change(struct tty_struct *tty); +void __stop_tty(struct tty_struct *tty); +void __start_tty(struct tty_struct *tty); +void tty_vhangup_session(struct tty_struct *tty); +void tty_open_proc_set_tty(struct file *filp, struct tty_struct *tty); +int tty_signal_session_leader(struct tty_struct *tty, int exit_session); +void session_clear_tty(struct pid *session); +void tty_buffer_free_all(struct tty_port *port); +void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld); +void tty_buffer_init(struct tty_port *port); +void tty_buffer_set_lock_subclass(struct tty_port *port); +bool tty_buffer_restart_work(struct tty_port *port); +bool tty_buffer_cancel_work(struct tty_port *port); +void tty_buffer_flush_work(struct tty_port *port); +speed_t tty_termios_input_baud_rate(struct ktermios *termios); +void tty_ldisc_hangup(struct tty_struct *tty, bool reset); +int tty_ldisc_reinit(struct tty_struct *tty, int disc); +long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +long tty_jobctrl_ioctl(struct tty_struct *tty, struct tty_struct *real_tty, + struct file *file, unsigned int cmd, unsigned long arg); +void tty_default_fops(struct file_operations *fops); +struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx); +int tty_alloc_file(struct file *file); +void tty_add_file(struct tty_struct *tty, struct file *file); +void tty_free_file(struct file *file); +int tty_release(struct inode *inode, struct file *filp); + +#define tty_is_writelocked(tty) (mutex_is_locked(&tty->atomic_write_lock)) + +int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty); +void tty_ldisc_release(struct tty_struct *tty); +int __must_check tty_ldisc_init(struct tty_struct *tty); +void tty_ldisc_deinit(struct tty_struct *tty); + +void tty_sysctl_init(void); + /* tty_audit.c */ #ifdef CONFIG_AUDIT void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size); diff --git a/drivers/tty/tty_baudrate.c b/drivers/tty/tty_baudrate.c index 84fec3c62d6a..9d0093d84e08 100644 --- a/drivers/tty/tty_baudrate.c +++ b/drivers/tty/tty_baudrate.c @@ -8,6 +8,7 @@ #include #include #include +#include "tty.h" /* diff --git a/include/linux/tty.h b/include/linux/tty.h index a641fc6a7fa8..e51d75f5165b 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -432,11 +432,7 @@ static inline struct tty_struct *tty_kref_get(struct tty_struct *tty) extern const char *tty_driver_name(const struct tty_struct *tty); extern void tty_wait_until_sent(struct tty_struct *tty, long timeout); -extern int __tty_check_change(struct tty_struct *tty, int sig); -extern int tty_check_change(struct tty_struct *tty); -extern void __stop_tty(struct tty_struct *tty); extern void stop_tty(struct tty_struct *tty); -extern void __start_tty(struct tty_struct *tty); extern void start_tty(struct tty_struct *tty); extern int tty_register_driver(struct tty_driver *driver); extern int tty_unregister_driver(struct tty_driver *driver); @@ -461,23 +457,11 @@ extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); extern int is_current_pgrp_orphaned(void); extern void tty_hangup(struct tty_struct *tty); extern void tty_vhangup(struct tty_struct *tty); -extern void tty_vhangup_session(struct tty_struct *tty); extern int tty_hung_up_p(struct file *filp); extern void do_SAK(struct tty_struct *tty); extern void __do_SAK(struct tty_struct *tty); -extern void tty_open_proc_set_tty(struct file *filp, struct tty_struct *tty); -extern int tty_signal_session_leader(struct tty_struct *tty, int exit_session); -extern void session_clear_tty(struct pid *session); extern void no_tty(void); -extern void tty_buffer_free_all(struct tty_port *port); -extern void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld); -extern void tty_buffer_init(struct tty_port *port); -extern void tty_buffer_set_lock_subclass(struct tty_port *port); -extern bool tty_buffer_restart_work(struct tty_port *port); -extern bool tty_buffer_cancel_work(struct tty_port *port); -extern void tty_buffer_flush_work(struct tty_port *port); extern speed_t tty_termios_baud_rate(struct ktermios *termios); -extern speed_t tty_termios_input_baud_rate(struct ktermios *termios); extern void tty_termios_encode_baud_rate(struct ktermios *termios, speed_t ibaud, speed_t obaud); extern void tty_encode_baud_rate(struct tty_struct *tty, @@ -505,27 +489,16 @@ extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); extern void tty_ldisc_deref(struct tty_ldisc *); extern struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *); -extern void tty_ldisc_hangup(struct tty_struct *tty, bool reset); -extern int tty_ldisc_reinit(struct tty_struct *tty, int disc); extern const struct seq_operations tty_ldiscs_seq_ops; extern void tty_wakeup(struct tty_struct *tty); extern void tty_ldisc_flush(struct tty_struct *tty); -extern long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg); extern int tty_mode_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); -extern long tty_jobctrl_ioctl(struct tty_struct *tty, struct tty_struct *real_tty, - struct file *file, unsigned int cmd, unsigned long arg); extern int tty_perform_flush(struct tty_struct *tty, unsigned long arg); -extern void tty_default_fops(struct file_operations *fops); -extern struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx); -extern int tty_alloc_file(struct file *file); -extern void tty_add_file(struct tty_struct *tty, struct file *file); -extern void tty_free_file(struct file *file); extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); extern void tty_release_struct(struct tty_struct *tty, int idx); -extern int tty_release(struct inode *inode, struct file *filp); extern void tty_init_termios(struct tty_struct *tty); extern void tty_save_termios(struct tty_struct *tty); extern int tty_standard_install(struct tty_driver *driver, @@ -533,8 +506,6 @@ extern int tty_standard_install(struct tty_driver *driver, extern struct mutex tty_mutex; -#define tty_is_writelocked(tty) (mutex_is_locked(&tty->atomic_write_lock)) - extern void tty_port_init(struct tty_port *port); extern void tty_port_link_device(struct tty_port *port, struct tty_driver *driver, unsigned index); @@ -672,10 +643,6 @@ static inline int tty_port_users(struct tty_port *port) extern int tty_register_ldisc(int disc, struct tty_ldisc_ops *new_ldisc); extern int tty_unregister_ldisc(int disc); extern int tty_set_ldisc(struct tty_struct *tty, int disc); -extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty); -extern void tty_ldisc_release(struct tty_struct *tty); -extern int __must_check tty_ldisc_init(struct tty_struct *tty); -extern void tty_ldisc_deinit(struct tty_struct *tty); extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, char *f, int count); From 2fcb12b3f421f3a26d912744df22dfbd771e0f1d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Fri, 17 Mar 2023 13:33:17 +0200 Subject: [PATCH 2973/4345] tty: Prevent writing chars during tcsetattr TCSADRAIN/FLUSH MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 094fb49a2d0d6827c86d2e0840873e6db0c491d2 ] If userspace races tcsetattr() with a write, the drained condition might not be guaranteed by the kernel. There is a race window after checking Tx is empty before tty_set_termios() takes termios_rwsem for write. During that race window, more characters can be queued by a racing writer. Any ongoing transmission might produce garbage during HW's ->set_termios() call. The intent of TCSADRAIN/FLUSH seems to be preventing such a character corruption. If those flags are set, take tty's write lock to stop any writer before performing the lower layer Tx empty check and wait for the pending characters to be sent (if any). The initial wait for all-writers-done must be placed outside of tty's write lock to avoid deadlock which makes it impossible to use tty_wait_until_sent(). The write lock is retried if a racing write is detected. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230317113318.31327-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/tty.h | 2 ++ drivers/tty/tty_io.c | 4 ++-- drivers/tty/tty_ioctl.c | 47 +++++++++++++++++++++++++++++------------ 3 files changed, 38 insertions(+), 15 deletions(-) diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h index 74ed99bc5449..1908f27a795a 100644 --- a/drivers/tty/tty.h +++ b/drivers/tty/tty.h @@ -63,6 +63,8 @@ int __tty_check_change(struct tty_struct *tty, int sig); int tty_check_change(struct tty_struct *tty); void __stop_tty(struct tty_struct *tty); void __start_tty(struct tty_struct *tty); +void tty_write_unlock(struct tty_struct *tty); +int tty_write_lock(struct tty_struct *tty, int ndelay); void tty_vhangup_session(struct tty_struct *tty); void tty_open_proc_set_tty(struct file *filp, struct tty_struct *tty); int tty_signal_session_leader(struct tty_struct *tty, int exit_session); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 86fbfe42ce0a..094e82a12d29 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -942,13 +942,13 @@ static ssize_t tty_read(struct kiocb *iocb, struct iov_iter *to) return i; } -static void tty_write_unlock(struct tty_struct *tty) +void tty_write_unlock(struct tty_struct *tty) { mutex_unlock(&tty->atomic_write_lock); wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT); } -static int tty_write_lock(struct tty_struct *tty, int ndelay) +int tty_write_lock(struct tty_struct *tty, int ndelay) { if (!mutex_trylock(&tty->atomic_write_lock)) { if (ndelay) diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 50e65784fbf7..68b07250dcb6 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -398,22 +398,43 @@ static int set_termios(struct tty_struct *tty, void __user *arg, int opt) tmp_termios.c_ispeed = tty_termios_input_baud_rate(&tmp_termios); tmp_termios.c_ospeed = tty_termios_baud_rate(&tmp_termios); - ld = tty_ldisc_ref(tty); + if (opt & (TERMIOS_FLUSH|TERMIOS_WAIT)) { +retry_write_wait: + retval = wait_event_interruptible(tty->write_wait, !tty_chars_in_buffer(tty)); + if (retval < 0) + return retval; - if (ld != NULL) { - if ((opt & TERMIOS_FLUSH) && ld->ops->flush_buffer) - ld->ops->flush_buffer(tty); - tty_ldisc_deref(ld); + if (tty_write_lock(tty, 0) < 0) + goto retry_write_wait; + + /* Racing writer? */ + if (tty_chars_in_buffer(tty)) { + tty_write_unlock(tty); + goto retry_write_wait; + } + + ld = tty_ldisc_ref(tty); + if (ld != NULL) { + if ((opt & TERMIOS_FLUSH) && ld->ops->flush_buffer) + ld->ops->flush_buffer(tty); + tty_ldisc_deref(ld); + } + + if ((opt & TERMIOS_WAIT) && tty->ops->wait_until_sent) { + tty->ops->wait_until_sent(tty, 0); + if (signal_pending(current)) { + tty_write_unlock(tty); + return -ERESTARTSYS; + } + } + + tty_set_termios(tty, &tmp_termios); + + tty_write_unlock(tty); + } else { + tty_set_termios(tty, &tmp_termios); } - if (opt & TERMIOS_WAIT) { - tty_wait_until_sent(tty, 0); - if (signal_pending(current)) - return -ERESTARTSYS; - } - - tty_set_termios(tty, &tmp_termios); - /* FIXME: Arguably if tmp_termios == tty->termios AND the actual requested termios was not tmp_termios then we may want to return an error as no user requested change has From 6f60aae72cccb5afe78487560a485e1c75132441 Mon Sep 17 00:00:00 2001 From: Tze-nan Wu Date: Wed, 26 Apr 2023 14:20:23 +0800 Subject: [PATCH 2974/4345] ring-buffer: Ensure proper resetting of atomic variables in ring_buffer_reset_online_cpus [ Upstream commit 7c339fb4d8577792378136c15fde773cfb863cb8 ] In ring_buffer_reset_online_cpus, the buffer_size_kb write operation may permanently fail if the cpu_online_mask changes between two for_each_online_buffer_cpu loops. The number of increases and decreases on both cpu_buffer->resize_disabled and cpu_buffer->record_disabled may be inconsistent, causing some CPUs to have non-zero values for these atomic variables after the function returns. This issue can be reproduced by "echo 0 > trace" while hotplugging cpu. After reproducing success, we can find out buffer_size_kb will not be functional anymore. To prevent leaving 'resize_disabled' and 'record_disabled' non-zero after ring_buffer_reset_online_cpus returns, we ensure that each atomic variable has been set up before atomic_sub() to it. Link: https://lore.kernel.org/linux-trace-kernel/20230426062027.17451-1-Tze-nan.Wu@mediatek.com Cc: stable@vger.kernel.org Cc: Cc: npiggin@gmail.com Fixes: b23d7a5f4a07 ("ring-buffer: speed up buffer resets by avoiding synchronize_rcu for each CPU") Reviewed-by: Cheng-Jui Wang Signed-off-by: Tze-nan Wu Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- kernel/trace/ring_buffer.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1fe6b29366f1..f08904914166 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5051,6 +5051,9 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); +/* Flag to ensure proper resetting of atomic variables */ +#define RESET_BIT (1 << 30) + /** * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer * @buffer: The ring buffer to reset a per cpu buffer of @@ -5067,20 +5070,27 @@ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer) for_each_online_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - atomic_inc(&cpu_buffer->resize_disabled); + atomic_add(RESET_BIT, &cpu_buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); } /* Make sure all commits have finished */ synchronize_rcu(); - for_each_online_buffer_cpu(buffer, cpu) { + for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; + /* + * If a CPU came online during the synchronize_rcu(), then + * ignore it. + */ + if (!(atomic_read(&cpu_buffer->resize_disabled) & RESET_BIT)) + continue; + reset_disabled_cpu_buffer(cpu_buffer); atomic_dec(&cpu_buffer->record_disabled); - atomic_dec(&cpu_buffer->resize_disabled); + atomic_sub(RESET_BIT, &cpu_buffer->resize_disabled); } mutex_unlock(&buffer->mutex); From c4e636f025a14e6d27f144fc0f16f442a4663f39 Mon Sep 17 00:00:00 2001 From: Jeremi Piotrowski Date: Tue, 28 Mar 2023 15:16:36 +0000 Subject: [PATCH 2975/4345] crypto: ccp - Clear PSP interrupt status register before calling handler [ Upstream commit 45121ad4a1750ca47ce3f32bd434bdb0cdbf0043 ] The PSP IRQ is edge-triggered (MSI or MSI-X) in all cases supported by the psp module so clear the interrupt status register early in the handler to prevent missed interrupts. sev_irq_handler() calls wake_up() on a wait queue, which can result in a new command being submitted from a different CPU. This then races with the clearing of isr and can result in missed interrupts. A missed interrupt results in a command waiting until it times out, which results in the psp being declared dead. This is unlikely on bare metal, but has been observed when running virtualized. In the cases where this is observed, sev->cmdresp_reg has PSP_CMDRESP_RESP set which indicates that the command was processed correctly but no interrupt was asserted. The full sequence of events looks like this: CPU 1: submits SEV cmd #1 CPU 1: calls wait_event_timeout() CPU 0: enters psp_irq_handler() CPU 0: calls sev_handler()->wake_up() CPU 1: wakes up; finishes processing cmd #1 CPU 1: submits SEV cmd #2 CPU 1: calls wait_event_timeout() PSP: finishes processing cmd #2; interrupt status is still set; no interrupt CPU 0: clears intsts CPU 0: exits psp_irq_handler() CPU 1: wait_event_timeout() times out; psp_dead=true Fixes: 200664d5237f ("crypto: ccp: Add Secure Encrypted Virtualization (SEV) command support") Cc: stable@vger.kernel.org Signed-off-by: Jeremi Piotrowski Acked-by: Tom Lendacky Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/ccp/psp-dev.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c index ae7b44599914..4bf9eaab4456 100644 --- a/drivers/crypto/ccp/psp-dev.c +++ b/drivers/crypto/ccp/psp-dev.c @@ -42,6 +42,9 @@ static irqreturn_t psp_irq_handler(int irq, void *data) /* Read the interrupt status: */ status = ioread32(psp->io_regs + psp->vdata->intsts_reg); + /* Clear the interrupt status by writing the same value we read. */ + iowrite32(status, psp->io_regs + psp->vdata->intsts_reg); + /* invoke subdevice interrupt handlers */ if (status) { if (psp->sev_irq_handler) @@ -51,9 +54,6 @@ static irqreturn_t psp_irq_handler(int irq, void *data) psp->tee_irq_handler(irq, psp->tee_irq_data, status); } - /* Clear the interrupt status by writing the same value we read. */ - iowrite32(status, psp->io_regs + psp->vdata->intsts_reg); - return IRQ_HANDLED; } From 67fb57f24737ffdbd443eb176fe3fc344c93f491 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 20 Nov 2022 09:25:54 +0100 Subject: [PATCH 2976/4345] mailbox: zynq: Switch to flexible array to simplify code [ Upstream commit 043f85ce81cb1714e14d31c322c5646513dde3fb ] Using flexible array is more straight forward. It - saves 1 pointer in the 'zynqmp_ipi_pdata' structure - saves an indirection when using this array - saves some LoC and avoids some always spurious pointer arithmetic Signed-off-by: Christophe JAILLET Signed-off-by: Jassi Brar Stable-dep-of: f72f805e7288 ("mailbox: zynqmp: Fix counts of child nodes") Signed-off-by: Sasha Levin --- drivers/mailbox/zynqmp-ipi-mailbox.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c index 05e36229622e..136a84ad871c 100644 --- a/drivers/mailbox/zynqmp-ipi-mailbox.c +++ b/drivers/mailbox/zynqmp-ipi-mailbox.c @@ -110,7 +110,7 @@ struct zynqmp_ipi_pdata { unsigned int method; u32 local_id; int num_mboxes; - struct zynqmp_ipi_mbox *ipi_mboxes; + struct zynqmp_ipi_mbox ipi_mboxes[]; }; static struct device_driver zynqmp_ipi_mbox_driver = { @@ -635,7 +635,7 @@ static int zynqmp_ipi_probe(struct platform_device *pdev) int num_mboxes, ret = -EINVAL; num_mboxes = of_get_child_count(np); - pdata = devm_kzalloc(dev, sizeof(*pdata) + (num_mboxes * sizeof(*mbox)), + pdata = devm_kzalloc(dev, struct_size(pdata, ipi_mboxes, num_mboxes), GFP_KERNEL); if (!pdata) return -ENOMEM; @@ -649,8 +649,6 @@ static int zynqmp_ipi_probe(struct platform_device *pdev) } pdata->num_mboxes = num_mboxes; - pdata->ipi_mboxes = (struct zynqmp_ipi_mbox *) - ((char *)pdata + sizeof(*pdata)); mbox = pdata->ipi_mboxes; for_each_available_child_of_node(np, nc) { From 26b1b0d0bebdb45ba1e33590313a4e345e1e18d8 Mon Sep 17 00:00:00 2001 From: Tanmay Shah Date: Fri, 10 Mar 2023 17:24:04 -0800 Subject: [PATCH 2977/4345] mailbox: zynqmp: Fix counts of child nodes [ Upstream commit f72f805e72882c361e2a612c64a6e549f3da7152 ] If child mailbox node status is disabled it causes crash in interrupt handler. Fix this by assigning only available child node during driver probe. Fixes: 4981b82ba2ff ("mailbox: ZynqMP IPI mailbox controller") Signed-off-by: Tanmay Shah Acked-by: Michal Simek Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230311012407.1292118-2-tanmay.shah@amd.com Signed-off-by: Mathieu Poirier Signed-off-by: Sasha Levin --- drivers/mailbox/zynqmp-ipi-mailbox.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/mailbox/zynqmp-ipi-mailbox.c b/drivers/mailbox/zynqmp-ipi-mailbox.c index 136a84ad871c..be06de791c54 100644 --- a/drivers/mailbox/zynqmp-ipi-mailbox.c +++ b/drivers/mailbox/zynqmp-ipi-mailbox.c @@ -634,7 +634,12 @@ static int zynqmp_ipi_probe(struct platform_device *pdev) struct zynqmp_ipi_mbox *mbox; int num_mboxes, ret = -EINVAL; - num_mboxes = of_get_child_count(np); + num_mboxes = of_get_available_child_count(np); + if (num_mboxes == 0) { + dev_err(dev, "mailbox nodes not available\n"); + return -EINVAL; + } + pdata = devm_kzalloc(dev, struct_size(pdata, ipi_mboxes, num_mboxes), GFP_KERNEL); if (!pdata) From fc097cfca0049c46df8f08814b3784780d483b4d Mon Sep 17 00:00:00 2001 From: Akilesh Kailash Date: Mon, 13 Sep 2021 09:26:42 +0000 Subject: [PATCH 2978/4345] dm verity: skip redundant verity_handle_err() on I/O errors [ Upstream commit 2c0468e054c0adb660ac055fc396622ec7235df9 ] Without FEC, dm-verity won't call verity_handle_err() when I/O fails, but with FEC enabled, it currently does even if an I/O error has occurred. If there is an I/O error and FEC correction fails, return the error instead of calling verity_handle_err() again. Suggested-by: Sami Tolvanen Signed-off-by: Akilesh Kailash Reviewed-by: Sami Tolvanen Signed-off-by: Mike Snitzer Stable-dep-of: e8c5d45f82ce ("dm verity: fix error handling for check_at_most_once on FEC") Signed-off-by: Sasha Levin --- drivers/md/dm-verity-target.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index c801f6b93b7b..d9c388e6ce76 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -475,6 +475,7 @@ static int verity_verify_io(struct dm_verity_io *io) struct bvec_iter start; unsigned b; struct crypto_wait wait; + struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); for (b = 0; b < io->n_blocks; b++) { int r; @@ -529,9 +530,17 @@ static int verity_verify_io(struct dm_verity_io *io) else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, cur_block, NULL, &start) == 0) continue; - else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, - cur_block)) - return -EIO; + else { + if (bio->bi_status) { + /* + * Error correction failed; Just return error + */ + return -EIO; + } + if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, + cur_block)) + return -EIO; + } } return 0; From 4285cc0a22d25c6f5363d9cc182d24b516dc6709 Mon Sep 17 00:00:00 2001 From: Yeongjin Gil Date: Mon, 20 Mar 2023 15:59:32 +0900 Subject: [PATCH 2979/4345] dm verity: fix error handling for check_at_most_once on FEC [ Upstream commit e8c5d45f82ce0c238a4817739892fe8897a3dcc3 ] In verity_end_io(), if bi_status is not BLK_STS_OK, it can be return directly. But if FEC configured, it is desired to correct the data page through verity_verify_io. And the return value will be converted to blk_status and passed to verity_finish_io(). BTW, when a bit is set in v->validated_blocks, verity_verify_io() skips verification regardless of I/O error for the corresponding bio. In this case, the I/O error could not be returned properly, and as a result, there is a problem that abnormal data could be read for the corresponding block. To fix this problem, when an I/O error occurs, do not skip verification even if the bit related is set in v->validated_blocks. Fixes: 843f38d382b1 ("dm verity: add 'check_at_most_once' option to only validate hashes once") Cc: stable@vger.kernel.org Reviewed-by: Sungjong Seo Signed-off-by: Yeongjin Gil Signed-off-by: Mike Snitzer Signed-off-by: Sasha Levin --- drivers/md/dm-verity-target.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index d9c388e6ce76..0c2048d2b847 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -482,7 +482,7 @@ static int verity_verify_io(struct dm_verity_io *io) sector_t cur_block = io->block + b; struct ahash_request *req = verity_io_hash_req(v, io); - if (v->validated_blocks && + if (v->validated_blocks && bio->bi_status == BLK_STS_OK && likely(test_bit(cur_block, v->validated_blocks))) { verity_bv_skip_block(v, io, &io->iter); continue; From fa19c533ab19161298f0780bcc6523af88f6fd20 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Thu, 13 Apr 2023 11:34:22 +0800 Subject: [PATCH 2980/4345] scsi: qedi: Fix use after free bug in qedi_remove() [ Upstream commit c5749639f2d0a1f6cbe187d05f70c2e7c544d748 ] In qedi_probe() we call __qedi_probe() which initializes &qedi->recovery_work with qedi_recovery_handler() and &qedi->board_disable_work with qedi_board_disable_work(). When qedi_schedule_recovery_handler() is called, schedule_delayed_work() will finally start the work. In qedi_remove(), which is called to remove the driver, the following sequence may be observed: Fix this by finishing the work before cleanup in qedi_remove(). CPU0 CPU1 |qedi_recovery_handler qedi_remove | __qedi_remove | iscsi_host_free | scsi_host_put | //free shost | |iscsi_host_for_each_session |//use qedi->shost Cancel recovery_work and board_disable_work in __qedi_remove(). Fixes: 4b1068f5d74b ("scsi: qedi: Add MFW error recovery process") Signed-off-by: Zheng Wang Link: https://lore.kernel.org/r/20230413033422.28003-1-zyytlz.wz@163.com Acked-by: Manish Rangankar Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qedi/qedi_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 299d0369e4f0..7df0106f132e 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -2456,6 +2456,9 @@ static void __qedi_remove(struct pci_dev *pdev, int mode) qedi_ops->ll2->stop(qedi->cdev); } + cancel_delayed_work_sync(&qedi->recovery_work); + cancel_delayed_work_sync(&qedi->board_disable_work); + qedi_free_iscsi_pf_param(qedi); rval = qedi_ops->common->update_drv_state(qedi->cdev, false); From cc8efc78c3f6a6fd0f6ff2523a98048c0610499d Mon Sep 17 00:00:00 2001 From: Cosmo Chou Date: Wed, 26 Apr 2023 16:13:50 +0800 Subject: [PATCH 2981/4345] net/ncsi: clear Tx enable mode when handling a Config required AEN [ Upstream commit 6f75cd166a5a3c0bc50441faa8b8304f60522fdd ] ncsi_channel_is_tx() determines whether a given channel should be used for Tx or not. However, when reconfiguring the channel by handling a Configuration Required AEN, there is a misjudgment that the channel Tx has already been enabled, which results in the Enable Channel Network Tx command not being sent. Clear the channel Tx enable flag before reconfiguring the channel to avoid the misjudgment. Fixes: 8d951a75d022 ("net/ncsi: Configure multi-package, multi-channel modes with failover") Signed-off-by: Cosmo Chou Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ncsi/ncsi-aen.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index b635c194f0a8..62fb1031763d 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -165,6 +165,7 @@ static int ncsi_aen_handler_cr(struct ncsi_dev_priv *ndp, nc->state = NCSI_CHANNEL_INACTIVE; list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); + nc->modes[NCSI_MODE_TX_ENABLE].enable = 0; return ncsi_process_next_channel(ndp); } From 7311c8be3755611bf6edea4dfbeb190b4bdd489f Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 26 Apr 2023 14:31:11 +0200 Subject: [PATCH 2982/4345] net/sched: cls_api: remove block_cb from driver_list before freeing [ Upstream commit da94a7781fc3c92e7df7832bc2746f4d39bc624e ] Error handler of tcf_block_bind() frees the whole bo->cb_list on error. However, by that time the flow_block_cb instances are already in the driver list because driver ndo_setup_tc() callback is called before that up the call chain in tcf_block_offload_cmd(). This leaves dangling pointers to freed objects in the list and causes use-after-free[0]. Fix it by also removing flow_block_cb instances from driver_list before deallocating them. [0]: [ 279.868433] ================================================================== [ 279.869964] BUG: KASAN: slab-use-after-free in flow_block_cb_setup_simple+0x631/0x7c0 [ 279.871527] Read of size 8 at addr ffff888147e2bf20 by task tc/2963 [ 279.873151] CPU: 6 PID: 2963 Comm: tc Not tainted 6.3.0-rc6+ #4 [ 279.874273] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 279.876295] Call Trace: [ 279.876882] [ 279.877413] dump_stack_lvl+0x33/0x50 [ 279.878198] print_report+0xc2/0x610 [ 279.878987] ? flow_block_cb_setup_simple+0x631/0x7c0 [ 279.879994] kasan_report+0xae/0xe0 [ 279.880750] ? flow_block_cb_setup_simple+0x631/0x7c0 [ 279.881744] ? mlx5e_tc_reoffload_flows_work+0x240/0x240 [mlx5_core] [ 279.883047] flow_block_cb_setup_simple+0x631/0x7c0 [ 279.884027] tcf_block_offload_cmd.isra.0+0x189/0x2d0 [ 279.885037] ? tcf_block_setup+0x6b0/0x6b0 [ 279.885901] ? mutex_lock+0x7d/0xd0 [ 279.886669] ? __mutex_unlock_slowpath.constprop.0+0x2d0/0x2d0 [ 279.887844] ? ingress_init+0x1c0/0x1c0 [sch_ingress] [ 279.888846] tcf_block_get_ext+0x61c/0x1200 [ 279.889711] ingress_init+0x112/0x1c0 [sch_ingress] [ 279.890682] ? clsact_init+0x2b0/0x2b0 [sch_ingress] [ 279.891701] qdisc_create+0x401/0xea0 [ 279.892485] ? qdisc_tree_reduce_backlog+0x470/0x470 [ 279.893473] tc_modify_qdisc+0x6f7/0x16d0 [ 279.894344] ? tc_get_qdisc+0xac0/0xac0 [ 279.895213] ? mutex_lock+0x7d/0xd0 [ 279.896005] ? __mutex_lock_slowpath+0x10/0x10 [ 279.896910] rtnetlink_rcv_msg+0x5fe/0x9d0 [ 279.897770] ? rtnl_calcit.isra.0+0x2b0/0x2b0 [ 279.898672] ? __sys_sendmsg+0xb5/0x140 [ 279.899494] ? do_syscall_64+0x3d/0x90 [ 279.900302] ? entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 279.901337] ? kasan_save_stack+0x2e/0x40 [ 279.902177] ? kasan_save_stack+0x1e/0x40 [ 279.903058] ? kasan_set_track+0x21/0x30 [ 279.903913] ? kasan_save_free_info+0x2a/0x40 [ 279.904836] ? ____kasan_slab_free+0x11a/0x1b0 [ 279.905741] ? kmem_cache_free+0x179/0x400 [ 279.906599] netlink_rcv_skb+0x12c/0x360 [ 279.907450] ? rtnl_calcit.isra.0+0x2b0/0x2b0 [ 279.908360] ? netlink_ack+0x1550/0x1550 [ 279.909192] ? rhashtable_walk_peek+0x170/0x170 [ 279.910135] ? kmem_cache_alloc_node+0x1af/0x390 [ 279.911086] ? _copy_from_iter+0x3d6/0xc70 [ 279.912031] netlink_unicast+0x553/0x790 [ 279.912864] ? netlink_attachskb+0x6a0/0x6a0 [ 279.913763] ? netlink_recvmsg+0x416/0xb50 [ 279.914627] netlink_sendmsg+0x7a1/0xcb0 [ 279.915473] ? netlink_unicast+0x790/0x790 [ 279.916334] ? iovec_from_user.part.0+0x4d/0x220 [ 279.917293] ? netlink_unicast+0x790/0x790 [ 279.918159] sock_sendmsg+0xc5/0x190 [ 279.918938] ____sys_sendmsg+0x535/0x6b0 [ 279.919813] ? import_iovec+0x7/0x10 [ 279.920601] ? kernel_sendmsg+0x30/0x30 [ 279.921423] ? __copy_msghdr+0x3c0/0x3c0 [ 279.922254] ? import_iovec+0x7/0x10 [ 279.923041] ___sys_sendmsg+0xeb/0x170 [ 279.923854] ? copy_msghdr_from_user+0x110/0x110 [ 279.924797] ? ___sys_recvmsg+0xd9/0x130 [ 279.925630] ? __perf_event_task_sched_in+0x183/0x470 [ 279.926656] ? ___sys_sendmsg+0x170/0x170 [ 279.927529] ? ctx_sched_in+0x530/0x530 [ 279.928369] ? update_curr+0x283/0x4f0 [ 279.929185] ? perf_event_update_userpage+0x570/0x570 [ 279.930201] ? __fget_light+0x57/0x520 [ 279.931023] ? __switch_to+0x53d/0xe70 [ 279.931846] ? sockfd_lookup_light+0x1a/0x140 [ 279.932761] __sys_sendmsg+0xb5/0x140 [ 279.933560] ? __sys_sendmsg_sock+0x20/0x20 [ 279.934436] ? fpregs_assert_state_consistent+0x1d/0xa0 [ 279.935490] do_syscall_64+0x3d/0x90 [ 279.936300] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 279.937311] RIP: 0033:0x7f21c814f887 [ 279.938085] Code: 0a 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 [ 279.941448] RSP: 002b:00007fff11efd478 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 279.942964] RAX: ffffffffffffffda RBX: 0000000064401979 RCX: 00007f21c814f887 [ 279.944337] RDX: 0000000000000000 RSI: 00007fff11efd4e0 RDI: 0000000000000003 [ 279.945660] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 [ 279.947003] R10: 00007f21c8008708 R11: 0000000000000246 R12: 0000000000000001 [ 279.948345] R13: 0000000000409980 R14: 000000000047e538 R15: 0000000000485400 [ 279.949690] [ 279.950706] Allocated by task 2960: [ 279.951471] kasan_save_stack+0x1e/0x40 [ 279.952338] kasan_set_track+0x21/0x30 [ 279.953165] __kasan_kmalloc+0x77/0x90 [ 279.954006] flow_block_cb_setup_simple+0x3dd/0x7c0 [ 279.955001] tcf_block_offload_cmd.isra.0+0x189/0x2d0 [ 279.956020] tcf_block_get_ext+0x61c/0x1200 [ 279.956881] ingress_init+0x112/0x1c0 [sch_ingress] [ 279.957873] qdisc_create+0x401/0xea0 [ 279.958656] tc_modify_qdisc+0x6f7/0x16d0 [ 279.959506] rtnetlink_rcv_msg+0x5fe/0x9d0 [ 279.960392] netlink_rcv_skb+0x12c/0x360 [ 279.961216] netlink_unicast+0x553/0x790 [ 279.962044] netlink_sendmsg+0x7a1/0xcb0 [ 279.962906] sock_sendmsg+0xc5/0x190 [ 279.963702] ____sys_sendmsg+0x535/0x6b0 [ 279.964534] ___sys_sendmsg+0xeb/0x170 [ 279.965343] __sys_sendmsg+0xb5/0x140 [ 279.966132] do_syscall_64+0x3d/0x90 [ 279.966908] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 279.968407] Freed by task 2960: [ 279.969114] kasan_save_stack+0x1e/0x40 [ 279.969929] kasan_set_track+0x21/0x30 [ 279.970729] kasan_save_free_info+0x2a/0x40 [ 279.971603] ____kasan_slab_free+0x11a/0x1b0 [ 279.972483] __kmem_cache_free+0x14d/0x280 [ 279.973337] tcf_block_setup+0x29d/0x6b0 [ 279.974173] tcf_block_offload_cmd.isra.0+0x226/0x2d0 [ 279.975186] tcf_block_get_ext+0x61c/0x1200 [ 279.976080] ingress_init+0x112/0x1c0 [sch_ingress] [ 279.977065] qdisc_create+0x401/0xea0 [ 279.977857] tc_modify_qdisc+0x6f7/0x16d0 [ 279.978695] rtnetlink_rcv_msg+0x5fe/0x9d0 [ 279.979562] netlink_rcv_skb+0x12c/0x360 [ 279.980388] netlink_unicast+0x553/0x790 [ 279.981214] netlink_sendmsg+0x7a1/0xcb0 [ 279.982043] sock_sendmsg+0xc5/0x190 [ 279.982827] ____sys_sendmsg+0x535/0x6b0 [ 279.983703] ___sys_sendmsg+0xeb/0x170 [ 279.984510] __sys_sendmsg+0xb5/0x140 [ 279.985298] do_syscall_64+0x3d/0x90 [ 279.986076] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 279.987532] The buggy address belongs to the object at ffff888147e2bf00 which belongs to the cache kmalloc-192 of size 192 [ 279.989747] The buggy address is located 32 bytes inside of freed 192-byte region [ffff888147e2bf00, ffff888147e2bfc0) [ 279.992367] The buggy address belongs to the physical page: [ 279.993430] page:00000000550f405c refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x147e2a [ 279.995182] head:00000000550f405c order:1 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 279.996713] anon flags: 0x200000000010200(slab|head|node=0|zone=2) [ 279.997878] raw: 0200000000010200 ffff888100042a00 0000000000000000 dead000000000001 [ 279.999384] raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 [ 280.000894] page dumped because: kasan: bad access detected [ 280.002386] Memory state around the buggy address: [ 280.003338] ffff888147e2be00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 280.004781] ffff888147e2be80: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 280.006224] >ffff888147e2bf00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 280.007700] ^ [ 280.008592] ffff888147e2bf80: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 280.010035] ffff888147e2c000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 280.011564] ================================================================== Fixes: 59094b1e5094 ("net: sched: use flow block API") Signed-off-by: Vlad Buslov Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/cls_api.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index c410a736301b..53d315ed9430 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1466,6 +1466,7 @@ static int tcf_block_bind(struct tcf_block *block, err_unroll: list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { + list_del(&block_cb->driver_list); if (i-- > 0) { list_del(&block_cb->list); tcf_block_playback_offloads(block, block_cb->cb, From d6f0687d506d74ff15701823b5223c4d07d91bc1 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Wed, 26 Apr 2023 23:00:06 -0700 Subject: [PATCH 2983/4345] sit: update dev->needed_headroom in ipip6_tunnel_bind_dev() [ Upstream commit c88f8d5cd95fd039cff95d682b8e71100c001df0 ] When a tunnel device is bound with the underlying device, its dev->needed_headroom needs to be updated properly. IPv4 tunnels already do the same in ip_tunnel_bind_dev(). Otherwise we may not have enough header room for skb, especially after commit b17f709a2401 ("gue: TX support for using remote checksum offload option"). Fixes: 32b8a8e59c9c ("sit: add IPv4 over IPv4 support") Reported-by: Palash Oswal Link: https://lore.kernel.org/netdev/CAGyP=7fDcSPKu6nttbGwt7RXzE3uyYxLjCSE97J64pRxJP8jPA@mail.gmail.com/ Cc: Kuniyuki Iwashima Cc: Eric Dumazet Signed-off-by: Cong Wang Reviewed-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/sit.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1ce486a9bc07..9806bd56b95f 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1094,12 +1094,13 @@ tx_err: static void ipip6_tunnel_bind_dev(struct net_device *dev) { + struct ip_tunnel *tunnel = netdev_priv(dev); + int t_hlen = tunnel->hlen + sizeof(struct iphdr); struct net_device *tdev = NULL; - struct ip_tunnel *tunnel; + int hlen = LL_MAX_HEADER; const struct iphdr *iph; struct flowi4 fl4; - tunnel = netdev_priv(dev); iph = &tunnel->parms.iph; if (iph->daddr) { @@ -1122,14 +1123,15 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev && !netif_is_l3_master(tdev)) { - int t_hlen = tunnel->hlen + sizeof(struct iphdr); int mtu; mtu = tdev->mtu - t_hlen; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; WRITE_ONCE(dev->mtu, mtu); + hlen = tdev->hard_header_len + tdev->needed_headroom; } + dev->needed_headroom = t_hlen + hlen; } static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, From f47f0fb5b58b92e0e256fd8e90211fe42093aaad Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Wed, 26 Apr 2023 22:28:15 +0200 Subject: [PATCH 2984/4345] net: dsa: mv88e6xxx: add mv88e6321 rsvd2cpu [ Upstream commit 6686317855c6997671982d4489ccdd946f644957 ] Add rsvd2cpu capability for mv88e6321 model, to allow proper bpdu processing. Signed-off-by: Angelo Dureghello Fixes: 51c901a775621 ("net: dsa: mv88e6xxx: distinguish Global 2 Rsvd2CPU") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/mv88e6xxx/chip.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 0b104a90c0d8..321c821876f6 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -4182,6 +4182,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .set_cpu_port = mv88e6095_g1_set_cpu_port, .set_egress_port = mv88e6095_g1_set_egress_port, .watchdog_ops = &mv88e6390_watchdog_ops, + .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, From 3b7798b42e1da6bbea70e6b09c41829865014f25 Mon Sep 17 00:00:00 2001 From: Maxim Korotkov Date: Thu, 19 Jan 2023 13:44:43 +0300 Subject: [PATCH 2985/4345] writeback: fix call of incorrect macro [ Upstream commit 3e46c89c74f2c38e5337d2cf44b0b551adff1cb4 ] the variable 'history' is of type u16, it may be an error that the hweight32 macro was used for it I guess macro hweight16 should be used Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 2a81490811d0 ("writeback: implement foreign cgroup inode detection") Signed-off-by: Maxim Korotkov Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230119104443.3002-1-korotkov.maxim.s@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- fs/fs-writeback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6f18459f5e38..045a3bd520ca 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -700,7 +700,7 @@ void wbc_detach_inode(struct writeback_control *wbc) * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ - if (hweight32(history) > WB_FRN_HIST_THR_SLOTS) + if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } From f3fae1b1c721edfadf35c85ac9cecc52d71d6f23 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 26 Apr 2023 08:52:48 +0200 Subject: [PATCH 2986/4345] watchdog: dw_wdt: Fix the error handling path of dw_wdt_drv_probe() [ Upstream commit 7f5390750645756bd5da2b24fac285f2654dd922 ] The commit in Fixes has only updated the remove function and missed the error handling path of the probe. Add the missing reset_control_assert() call. Fixes: 65a3b6935d92 ("watchdog: dw_wdt: get reset lines from dt") Signed-off-by: Christophe JAILLET Reviewed-by: Philipp Zabel Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/fbb650650bbb33a8fa2fd028c23157bedeed50e1.1682491863.git.christophe.jaillet@wanadoo.fr Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Signed-off-by: Sasha Levin --- drivers/watchdog/dw_wdt.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c index 32d0e1781e63..3cd118281980 100644 --- a/drivers/watchdog/dw_wdt.c +++ b/drivers/watchdog/dw_wdt.c @@ -638,7 +638,7 @@ static int dw_wdt_drv_probe(struct platform_device *pdev) ret = dw_wdt_init_timeouts(dw_wdt, dev); if (ret) - goto out_disable_clk; + goto out_assert_rst; wdd = &dw_wdt->wdd; wdd->ops = &dw_wdt_ops; @@ -669,12 +669,15 @@ static int dw_wdt_drv_probe(struct platform_device *pdev) ret = watchdog_register_device(wdd); if (ret) - goto out_disable_pclk; + goto out_assert_rst; dw_wdt_dbgfs_init(dw_wdt); return 0; +out_assert_rst: + reset_control_assert(dw_wdt->rst); + out_disable_pclk: clk_disable_unprepare(dw_wdt->pclk); From 774da70521564b3ebbc4d53402a960b1726ae94e Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Wed, 26 Apr 2023 15:19:40 +0000 Subject: [PATCH 2987/4345] net/sched: act_mirred: Add carrier check [ Upstream commit 526f28bd0fbdc699cda31426928802650c1528e5 ] There are cases where the device is adminstratively UP, but operationally down. For example, we have a physical device (Nvidia ConnectX-6 Dx, 25Gbps) who's cable was pulled out, here is its ip link output: 5: ens2f1: mtu 1500 qdisc mq state DOWN mode DEFAULT group default qlen 1000 link/ether b8:ce:f6:4b:68:35 brd ff:ff:ff:ff:ff:ff altname enp179s0f1np1 As you can see, it's administratively UP but operationally down. In this case, sending a packet to this port caused a nasty kernel hang (so nasty that we were unable to capture it). Aborting a transmit based on operational status (in addition to administrative status) fixes the issue. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira v1->v2: Add fixes tag v2->v3: Remove blank line between tags + add change log, suggested by Leon Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/act_mirred.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 24d561d8d9c9..25dad1921baf 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -244,7 +244,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } - if (unlikely(!(dev->flags & IFF_UP))) { + if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); goto out; From 9291aba0ffa0bd15fe3d2677a437328689c15c94 Mon Sep 17 00:00:00 2001 From: Andy Moreton Date: Fri, 28 Apr 2023 12:33:33 +0100 Subject: [PATCH 2988/4345] sfc: Fix module EEPROM reporting for QSFP modules [ Upstream commit 281900a923d4c50df109b52a22ae3cdac150159b ] The sfc driver does not report QSFP module EEPROM contents correctly as only the first page is fetched from hardware. Commit 0e1a2a3e6e7d ("ethtool: Add SFF-8436 and SFF-8636 max EEPROM length definitions") added ETH_MODULE_SFF_8436_MAX_LEN for the overall size of the EEPROM info, so use that to report the full EEPROM contents. Fixes: 9b17010da57a ("sfc: Add ethtool -m support for QSFP modules") Signed-off-by: Andy Moreton Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/sfc/mcdi_port_common.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c index c4fe3c48ac46..eccb97a5d938 100644 --- a/drivers/net/ethernet/sfc/mcdi_port_common.c +++ b/drivers/net/ethernet/sfc/mcdi_port_common.c @@ -974,12 +974,15 @@ static u32 efx_mcdi_phy_module_type(struct efx_nic *efx) /* A QSFP+ NIC may actually have an SFP+ module attached. * The ID is page 0, byte 0. + * QSFP28 is of type SFF_8636, however, this is treated + * the same by ethtool, so we can also treat them the same. */ switch (efx_mcdi_phy_get_module_eeprom_byte(efx, 0, 0)) { - case 0x3: + case 0x3: /* SFP */ return MC_CMD_MEDIA_SFP_PLUS; - case 0xc: - case 0xd: + case 0xc: /* QSFP */ + case 0xd: /* QSFP+ */ + case 0x11: /* QSFP28 */ return MC_CMD_MEDIA_QSFP_PLUS; default: return 0; @@ -1077,7 +1080,7 @@ int efx_mcdi_phy_get_module_info(struct efx_nic *efx, struct ethtool_modinfo *mo case MC_CMD_MEDIA_QSFP_PLUS: modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; break; default: From 15152b8a4bbb8541c8f8c18e972a7c4030da86b3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 28 Apr 2023 21:27:54 +0100 Subject: [PATCH 2989/4345] rxrpc: Fix hard call timeout units [ Upstream commit 0d098d83c5d9e107b2df7f5e11f81492f56d2fe7 ] The hard call timeout is specified in the RXRPC_SET_CALL_TIMEOUT cmsg in seconds, so fix the point at which sendmsg() applies it to the call to convert to jiffies from seconds, not milliseconds. Fixes: a158bdd3247b ("rxrpc: Fix timeout of a call that hasn't yet been granted a channel") Signed-off-by: David Howells cc: Marc Dionne cc: "David S. Miller" cc: Eric Dumazet cc: Jakub Kicinski cc: Paolo Abeni cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/rxrpc/sendmsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index a670553159ab..1882fea71903 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -753,7 +753,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) fallthrough; case 1: if (p.call.timeouts.hard > 0) { - j = msecs_to_jiffies(p.call.timeouts.hard); + j = p.call.timeouts.hard * HZ; now = jiffies; j += now; WRITE_ONCE(call->expect_term_by, j); From ea7453f5e5b6305e3d0e349f7d332aca7ee73465 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 3 May 2023 12:39:43 +0530 Subject: [PATCH 2990/4345] octeontx2-pf: Disable packet I/O for graceful exit [ Upstream commit c926252205c424c4842dbdbe02f8e3296f623204 ] At the stage of enabling packet I/O in otx2_open, If mailbox timeout occurs then interface ends up in down state where as hardware packet I/O is enabled. Hence disable packet I/O also before bailing out. Fixes: 1ea0166da050 ("octeontx2-pf: Fix the device state on error") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 161174be51c3..54aeb276b9a0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1589,11 +1589,20 @@ int otx2_open(struct net_device *netdev) otx2_config_pause_frm(pf); err = otx2_rxtx_enable(pf, true); - if (err) + /* If a mbox communication error happens at this point then interface + * will end up in a state such that it is in down state but hardware + * mcam entries are enabled to receive the packets. Hence disable the + * packet I/O. + */ + if (err == EIO) + goto err_disable_rxtx; + else if (err) goto err_tx_stop_queues; return 0; +err_disable_rxtx: + otx2_rxtx_enable(pf, false); err_tx_stop_queues: netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); From 3605b3318483714f4cda7c7b629d4463bd9ed94e Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 3 May 2023 12:39:44 +0530 Subject: [PATCH 2991/4345] octeontx2-vf: Detach LF resources on probe cleanup [ Upstream commit 99ae1260fdb5f15beab8a3adfb93a9041c87a2c1 ] When a VF device probe fails due to error in MSIX vector allocation then the resources NIX and NPA LFs were not detached. Fix this by detaching the LFs when MSIX vector allocation fails. Fixes: 3184fb5ba96e ("octeontx2-vf: Virtual function driver support") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 67fabf265fe6..5310b71795ec 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -542,7 +542,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) err = otx2vf_realloc_msix_vectors(vf); if (err) - goto err_mbox_destroy; + goto err_detach_rsrc; err = otx2_set_real_num_queues(netdev, qcount, qcount); if (err) From 02359ba526ce4df4fbb1ed03684c1a15c0e6c8da Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 2 May 2023 11:47:40 -0700 Subject: [PATCH 2992/4345] ionic: remove noise from ethtool rxnfc error msg [ Upstream commit 3711d44fac1f80ea69ecb7315fed05b3812a7401 ] It seems that ethtool is calling into .get_rxnfc more often with ETHTOOL_GRXCLSRLCNT which ionic doesn't know about. We don't need to log a message about it, just return not supported. Fixes: aa3198819bea6 ("ionic: Add RSS support") Signed-off-by: Shannon Nelson Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/pensando/ionic/ionic_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index 35c72d4a78b3..8e5b01af85ed 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -693,7 +693,7 @@ static int ionic_get_rxnfc(struct net_device *netdev, info->data = lif->nxqs; break; default: - netdev_err(netdev, "Command parameter %d is not supported\n", + netdev_dbg(netdev, "Command parameter %d is not supported\n", info->cmd); err = -EOPNOTSUPP; } From f00ef2618fa1c941981f3aafb106754377658f30 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 1 May 2023 13:28:57 -0700 Subject: [PATCH 2993/4345] af_packet: Don't send zero-byte data in packet_sendmsg_spkt(). [ Upstream commit 6a341729fb31b4c5df9f74f24b4b1c98410c9b87 ] syzkaller reported a warning below [0]. We can reproduce it by sending 0-byte data from the (AF_PACKET, SOCK_PACKET) socket via some devices whose dev->hard_header_len is 0. struct sockaddr_pkt addr = { .spkt_family = AF_PACKET, .spkt_device = "tun0", }; int fd; fd = socket(AF_PACKET, SOCK_PACKET, 0); sendto(fd, NULL, 0, 0, (struct sockaddr *)&addr, sizeof(addr)); We have a similar fix for the (AF_PACKET, SOCK_RAW) socket as commit dc633700f00f ("net/af_packet: check len when min_header_len equals to 0"). Let's add the same test for the SOCK_PACKET socket. [0]: skb_assert_len WARNING: CPU: 1 PID: 19945 at include/linux/skbuff.h:2552 skb_assert_len include/linux/skbuff.h:2552 [inline] WARNING: CPU: 1 PID: 19945 at include/linux/skbuff.h:2552 __dev_queue_xmit+0x1f26/0x31d0 net/core/dev.c:4159 Modules linked in: CPU: 1 PID: 19945 Comm: syz-executor.0 Not tainted 6.3.0-rc7-02330-gca6270c12e20 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:skb_assert_len include/linux/skbuff.h:2552 [inline] RIP: 0010:__dev_queue_xmit+0x1f26/0x31d0 net/core/dev.c:4159 Code: 89 de e8 1d a2 85 fd 84 db 75 21 e8 64 a9 85 fd 48 c7 c6 80 2a 1f 86 48 c7 c7 c0 06 1f 86 c6 05 23 cf 27 04 01 e8 fa ee 56 fd <0f> 0b e8 43 a9 85 fd 0f b6 1d 0f cf 27 04 31 ff 89 de e8 e3 a1 85 RSP: 0018:ffff8880217af6e0 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffc90001133000 RDX: 0000000000040000 RSI: ffffffff81186922 RDI: 0000000000000001 RBP: ffff8880217af8b0 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff888030045640 R13: ffff8880300456b0 R14: ffff888030045650 R15: ffff888030045718 FS: 00007fc5864da640(0000) GS:ffff88806cd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020005740 CR3: 000000003f856003 CR4: 0000000000770ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: dev_queue_xmit include/linux/netdevice.h:3085 [inline] packet_sendmsg_spkt+0xc4b/0x1230 net/packet/af_packet.c:2066 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b4/0x200 net/socket.c:747 ____sys_sendmsg+0x331/0x970 net/socket.c:2503 ___sys_sendmsg+0x11d/0x1c0 net/socket.c:2557 __sys_sendmmsg+0x18c/0x430 net/socket.c:2643 __do_sys_sendmmsg net/socket.c:2672 [inline] __se_sys_sendmmsg net/socket.c:2669 [inline] __x64_sys_sendmmsg+0x9c/0x100 net/socket.c:2669 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3c/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7fc58791de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 73 9f 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007fc5864d9cc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 00000000004bbf80 RCX: 00007fc58791de5d RDX: 0000000000000001 RSI: 0000000020005740 RDI: 0000000000000004 RBP: 00000000004bbf80 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007fc58797e530 R15: 0000000000000000 ---[ end trace 0000000000000000 ]--- skb len=0 headroom=16 headlen=0 tailroom=304 mac=(16,0) net=(16,-1) trans=-1 shinfo(txflags=0 nr_frags=0 gso(size=0 type=0 segs=0)) csum(0x0 ip_summed=0 complete_sw=0 valid=0 level=0) hash(0x0 sw=0 l4=0) proto=0x0000 pkttype=0 iif=0 dev name=sit0 feat=0x00000006401d7869 sk family=17 type=10 proto=0 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/packet/af_packet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 9b6f6a5e0b14..2e766490a739 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1996,7 +1996,7 @@ retry: goto retry; } - if (!dev_validate_header(dev, skb->data, len)) { + if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } From 7f497a9451d716d8e46a3907996151a23296d49b Mon Sep 17 00:00:00 2001 From: Chia-I Wu Date: Wed, 26 Apr 2023 15:54:55 -0700 Subject: [PATCH 2994/4345] drm/amdgpu: add a missing lock for AMDGPU_SCHED MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2397e3d8d2e120355201a8310b61929f5a8bd2c0 ] mgr->ctx_handles should be protected by mgr->lock. v2: improve commit message v3: add a Fixes tag Signed-off-by: Chia-I Wu Reviewed-by: Christian König Fixes: 52c6a62c64fa ("drm/amdgpu: add interface for editing a foreign process's priority v3") Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c index 0da0a0d98672..15c0a3068eab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c @@ -66,6 +66,7 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev, { struct fd f = fdget(fd); struct amdgpu_fpriv *fpriv; + struct amdgpu_ctx_mgr *mgr; struct amdgpu_ctx *ctx; uint32_t id; int r; @@ -79,8 +80,11 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev, return r; } - idr_for_each_entry(&fpriv->ctx_mgr.ctx_handles, ctx, id) + mgr = &fpriv->ctx_mgr; + mutex_lock(&mgr->lock); + idr_for_each_entry(&mgr->ctx_handles, ctx, id) amdgpu_ctx_priority_override(ctx, priority); + mutex_unlock(&mgr->lock); fdput(f); return 0; From 0f1ad0ef60cc07d94256a39b0c594c0cd94f1716 Mon Sep 17 00:00:00 2001 From: Ruliang Lin Date: Thu, 4 May 2023 14:50:53 +0800 Subject: [PATCH 2995/4345] ALSA: caiaq: input: Add error handling for unsupported input methods in `snd_usb_caiaq_input_init` [ Upstream commit 0d727e1856ef22dd9337199430258cb64cbbc658 ] Smatch complains that: snd_usb_caiaq_input_init() warn: missing error code 'ret' This patch adds a new case to handle the situation where the device does not support any input methods in the `snd_usb_caiaq_input_init` function. It returns an `-EINVAL` error code to indicate that no input methods are supported on the device. Fixes: 523f1dce3743 ("[ALSA] Add Native Instrument usb audio device support") Signed-off-by: Ruliang Lin Reviewed-by: Dongliang Mu Acked-by: Daniel Mack Link: https://lore.kernel.org/r/20230504065054.3309-1-u202112092@hust.edu.cn Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/usb/caiaq/input.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/caiaq/input.c b/sound/usb/caiaq/input.c index 1e2cf2f08eec..84f26dce7f5d 100644 --- a/sound/usb/caiaq/input.c +++ b/sound/usb/caiaq/input.c @@ -804,6 +804,7 @@ int snd_usb_caiaq_input_init(struct snd_usb_caiaqdev *cdev) default: /* no input methods supported on this device */ + ret = -EINVAL; goto exit_free_idev; } From 0773270b131481fb5159bc9d562c3dfac6330d22 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Wed, 3 May 2023 00:09:46 +0300 Subject: [PATCH 2996/4345] net: dsa: mt7530: fix corrupt frames using trgmii on 40 MHz XTAL MT7621 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 37c218d8021e36e226add4bab93d071d30fe0704 ] The multi-chip module MT7530 switch with a 40 MHz oscillator on the MT7621AT, MT7621DAT, and MT7621ST SoCs forwards corrupt frames using trgmii. This is caused by the assumption that MT7621 SoCs have got 150 MHz PLL, hence using the ncpo1 value, 0x0780. My testing shows this value works on Unielec U7621-06, Bartel's testing shows it won't work on Hi-Link HLK-MT7621A and Netgear WAC104. All devices tested have got 40 MHz oscillators. Using the value for 125 MHz PLL, 0x0640, works on all boards at hand. The definitions for 125 MHz PLL exist on the Banana Pi BPI-R2 BSP source code whilst 150 MHz PLL don't. Forwarding frames using trgmii on the MCM MT7530 switch with a 25 MHz oscillator on the said MT7621 SoCs works fine because the ncpo1 value defined for it is for 125 MHz PLL. Change the 150 MHz PLL comment to 125 MHz PLL, and use the 125 MHz PLL ncpo1 values for both oscillator frequencies. Link: https://github.com/BPI-SINOVOIP/BPI-R2-bsp/blob/81d24bbce7d99524d0771a8bdb2d6663e4eb4faa/u-boot-mt/drivers/net/rt2880_eth.c#L2195 Fixes: 7ef6f6f8d237 ("net: dsa: mt7530: Add MT7621 TRGMII mode support") Tested-by: Bartel Eerdekens Signed-off-by: Arınç ÜNAL Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/mt7530.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 70155e996f7d..d3b42adef057 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -404,9 +404,9 @@ mt7530_pad_clk_setup(struct dsa_switch *ds, phy_interface_t interface) case PHY_INTERFACE_MODE_TRGMII: trgint = 1; if (priv->id == ID_MT7621) { - /* PLL frequency: 150MHz: 1.2GBit */ + /* PLL frequency: 125MHz: 1.0GBit */ if (xtal == HWTRAP_XTAL_40MHZ) - ncpo1 = 0x0780; + ncpo1 = 0x0640; if (xtal == HWTRAP_XTAL_25MHZ) ncpo1 = 0x0a00; } else { /* PLL frequency: 250MHz: 2.0Gbit */ From c043714ef230065fd5303307acbd2ca2627cb567 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:59 +0800 Subject: [PATCH 2997/4345] virtio_net: split free_unused_bufs() [ Upstream commit 6e345f8c7cd029ad3aaece15ad4425ac26e4eb63 ] This patch separates two functions for freeing sq buf and rq buf from free_unused_bufs(). When supporting the enable/disable tx/rq queue in the future, it is necessary to support separate recovery of a sq buf or a rq buf. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-40-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin Stable-dep-of: f8bb51043945 ("virtio_net: suppress cpu stall when free_unused_bufs") Signed-off-by: Sasha Levin --- drivers/net/virtio_net.c | 41 ++++++++++++++++++++++++---------------- 1 file changed, 25 insertions(+), 16 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 47c9118cc92a..75219c8f4a63 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2747,6 +2747,27 @@ static void free_receive_page_frags(struct virtnet_info *vi) put_page(vi->rq[i].alloc_frag.page); } +static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf) +{ + if (!is_xdp_frame(buf)) + dev_kfree_skb(buf); + else + xdp_return_frame(ptr_to_xdp(buf)); +} + +static void virtnet_rq_free_unused_buf(struct virtqueue *vq, void *buf) +{ + struct virtnet_info *vi = vq->vdev->priv; + int i = vq2rxq(vq); + + if (vi->mergeable_rx_bufs) + put_page(virt_to_head_page(buf)); + else if (vi->big_packets) + give_pages(&vi->rq[i], buf); + else + put_page(virt_to_head_page(buf)); +} + static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -2754,26 +2775,14 @@ static void free_unused_bufs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->sq[i].vq; - while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { - if (!is_xdp_frame(buf)) - dev_kfree_skb(buf); - else - xdp_return_frame(ptr_to_xdp(buf)); - } + while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) + virtnet_sq_free_unused_buf(vq, buf); } for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->rq[i].vq; - - while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { - if (vi->mergeable_rx_bufs) { - put_page(virt_to_head_page(buf)); - } else if (vi->big_packets) { - give_pages(&vi->rq[i], buf); - } else { - put_page(virt_to_head_page(buf)); - } - } + while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) + virtnet_rq_free_unused_buf(vq, buf); } } From b6b15de5129e9a02c59640cd43fa1955036ed674 Mon Sep 17 00:00:00 2001 From: Wenliang Wang Date: Thu, 4 May 2023 10:27:06 +0800 Subject: [PATCH 2998/4345] virtio_net: suppress cpu stall when free_unused_bufs [ Upstream commit f8bb5104394560e29017c25bcade4c6b7aabd108 ] For multi-queue and large ring-size use case, the following error occurred when free_unused_bufs: rcu: INFO: rcu_sched self-detected stall on CPU. Fixes: 986a4f4d452d ("virtio_net: multiqueue support") Signed-off-by: Wenliang Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/virtio_net.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 75219c8f4a63..119a32f34b53 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2777,12 +2777,14 @@ static void free_unused_bufs(struct virtnet_info *vi) struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_sq_free_unused_buf(vq, buf); + cond_resched(); } for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->rq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_rq_free_unused_buf(vq, buf); + cond_resched(); } } From 796616f216d06269aabc4e7801f251f6f9c1c364 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Thu, 4 May 2023 16:03:59 +0800 Subject: [PATCH 2999/4345] net: enetc: check the index of the SFI rather than the handle [ Upstream commit 299efdc2380aac588557f4d0b2ce7bee05bd0cf2 ] We should check whether the current SFI (Stream Filter Instance) table is full before creating a new SFI entry. However, the previous logic checks the handle by mistake and might lead to unpredictable behavior. Fixes: 888ae5a3952b ("net: enetc: add tc flower psfp offload driver") Signed-off-by: Wei Fang Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/enetc/enetc_qos.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 5841721c8119..8d92dc6bc994 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -1266,7 +1266,7 @@ static int enetc_psfp_parse_clsflower(struct enetc_ndev_priv *priv, int index; index = enetc_get_free_index(priv); - if (sfi->handle < 0) { + if (index < 0) { NL_SET_ERR_MSG_MOD(extack, "No Stream Filter resource!"); err = -ENOSPC; goto free_fmi; From 1ebd0dfb271e023058211e3e6c12a73aa8253982 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Tue, 28 Mar 2023 16:59:08 +0530 Subject: [PATCH 3000/4345] perf vendor events power9: Remove UTF-8 characters from JSON files [ Upstream commit 5d9df8731c0941f3add30f96745a62586a0c9d52 ] Commit 3c22ba5243040c13 ("perf vendor events powerpc: Update POWER9 events") added and updated power9 PMU JSON events. However some of the JSON events which are part of other.json and pipeline.json files, contains UTF-8 characters in their brief description. Having UTF-8 character could breaks the perf build on some distros. Fix this issue by removing the UTF-8 characters from other.json and pipeline.json files. Result without the fix: [command]# file -i pmu-events/arch/powerpc/power9/* pmu-events/arch/powerpc/power9/cache.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/floating-point.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/frontend.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/marked.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/memory.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/metrics.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/nest_metrics.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/other.json: application/json; charset=utf-8 pmu-events/arch/powerpc/power9/pipeline.json: application/json; charset=utf-8 pmu-events/arch/powerpc/power9/pmc.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/translation.json: application/json; charset=us-ascii [command]# Result with the fix: [command]# file -i pmu-events/arch/powerpc/power9/* pmu-events/arch/powerpc/power9/cache.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/floating-point.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/frontend.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/marked.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/memory.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/metrics.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/nest_metrics.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/other.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/pipeline.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/pmc.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/translation.json: application/json; charset=us-ascii [command]# Fixes: 3c22ba5243040c13 ("perf vendor events powerpc: Update POWER9 events") Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Kajol Jain Acked-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Athira Rajeev Cc: Disha Goel Cc: Jiri Olsa Cc: Madhavan Srinivasan Cc: Sukadev Bhattiprolu Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/lkml/ZBxP77deq7ikTxwG@kernel.org/ Link: https://lore.kernel.org/r/20230328112908.113158-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/pmu-events/arch/powerpc/power9/other.json | 4 ++-- tools/perf/pmu-events/arch/powerpc/power9/pipeline.json | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json index 3f69422c21f9..f10bd554521a 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json @@ -1417,7 +1417,7 @@ { "EventCode": "0x45054", "EventName": "PM_FMA_CMPL", - "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. " + "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only." }, { "EventCode": "0x201E8", @@ -2017,7 +2017,7 @@ { "EventCode": "0xC0BC", "EventName": "PM_LSU_FLUSH_OTHER", - "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the “bad dval” back and flush all younger ops)" + "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the 'bad dval' back and flush all younger ops)" }, { "EventCode": "0x5094", diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json index d0265f255de2..723bffa41c44 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json @@ -442,7 +442,7 @@ { "EventCode": "0x4D052", "EventName": "PM_2FLOP_CMPL", - "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg " + "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg" }, { "EventCode": "0x1F142", From 604b650fb5742d8a1e654786372473ca3838f2be Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 10:23:35 -0300 Subject: [PATCH 3001/4345] perf pmu: zfree() expects a pointer to a pointer to zero it after freeing its contents [ Upstream commit 57f14b5ae1a97537f2abd2828ee7212cada7036e ] An audit showed just this one problem with zfree(), fix it. Fixes: 9fbc61f832ebf432 ("perf pmu: Add support for PMU capabilities") Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index ac45da0302a7..d322305bc182 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1670,7 +1670,7 @@ static int perf_pmu__new_caps(struct list_head *list, char *name, char *value) return 0; free_name: - zfree(caps->name); + zfree(&caps->name); free_caps: free(caps); From be3517ae6b8093baa5c7e04cd4c8713c6e6eacaa Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Thu, 13 Apr 2023 14:46:39 +0200 Subject: [PATCH 3002/4345] perf map: Delete two variable initialisations before null pointer checks in sort__sym_from_cmp() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c160118a90d4acf335993d8d59b02ae2147a524e ] Addresses of two data structure members were determined before corresponding null pointer checks in the implementation of the function “sort__sym_from_cmp”. Thus avoid the risk for undefined behaviour by removing extra initialisations for the local variables “from_l” and “from_r” (also because they were already reassigned with the same value behind this pointer check). This issue was detected by using the Coccinelle software. Fixes: 1b9e97a2a95e4941 ("perf tools: Fix report -F symbol_from for data without branch info") Signed-off-by: Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: German Gomez Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Link: https://lore.kernel.org/cocci/54a21fea-64e3-de67-82ef-d61b90ffad05@web.de/ Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/sort.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 5e9e96452b9e..42806102010b 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -873,8 +873,7 @@ static int hist_entry__dso_to_filter(struct hist_entry *he, int type, static int64_t sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) { - struct addr_map_symbol *from_l = &left->branch_info->from; - struct addr_map_symbol *from_r = &right->branch_info->from; + struct addr_map_symbol *from_l, *from_r; if (!left->branch_info || !right->branch_info) return cmp_null(left->branch_info, right->branch_info); From 87a1fa0ad74e844c1801515df94ff0af0a0121b8 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 17 Apr 2023 22:25:09 +0200 Subject: [PATCH 3003/4345] crypto: sun8i-ss - Fix a test in sun8i_ss_setup_ivs() [ Upstream commit 8fd91151ebcb21b3f2f2bf158ac6092192550b2b ] SS_ENCRYPTION is (0 << 7 = 0), so the test can never be true. Use a direct comparison to SS_ENCRYPTION instead. The same king of test is already done the same way in sun8i_ss_run_task(). Fixes: 359e893e8af4 ("crypto: sun8i-ss - rework handling of IV") Signed-off-by: Christophe JAILLET Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c index 49c7a8b464dd..8a94f812e6d2 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c @@ -132,7 +132,7 @@ static int sun8i_ss_setup_ivs(struct skcipher_request *areq) } rctx->p_iv[i] = a; /* we need to setup all others IVs only in the decrypt way */ - if (rctx->op_dir & SS_ENCRYPTION) + if (rctx->op_dir == SS_ENCRYPTION) return 0; todo = min(len, sg_dma_len(sg)); len -= todo; From 7a4db11f00f3412eb4931fcb5e5cc91675b89b6e Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Thu, 27 Apr 2023 01:28:41 +0000 Subject: [PATCH 3004/4345] perf symbols: Fix return incorrect build_id size in elf_read_build_id() [ Upstream commit 1511e4696acb715a4fe48be89e1e691daec91c0e ] In elf_read_build_id(), if gnu build_id is found, should return the size of the actually copied data. If descsz is greater thanBuild_ID_SIZE, write_buildid data access may occur. Fixes: be96ea8ffa788dcc ("perf symbols: Fix issue with binaries using 16-bytes buildids (v2)") Reported-by: Will Ochowicz Signed-off-by: Yang Jihong Tested-by: Will Ochowicz Acked-by: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/lkml/CWLP265MB49702F7BA3D6D8F13E4B1A719C649@CWLP265MB4970.GBRP265.PROD.OUTLOOK.COM/T/ Link: https://lore.kernel.org/r/20230427012841.231729-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/symbol-elf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 5221f272f85c..b171d134ce87 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -548,7 +548,7 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size) size_t sz = min(size, descsz); memcpy(bf, ptr, sz); memset(bf + sz, 0, size - sz); - err = descsz; + err = sz; break; } } From 08fa23adbdccd1dca92e0f6a14debfc8c240ace6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 12 Apr 2023 11:33:09 +0100 Subject: [PATCH 3005/4345] btrfs: fix btrfs_prev_leaf() to not return the same key twice commit 6f932d4ef007d6a4ae03badcb749fbb8f49196f6 upstream. A call to btrfs_prev_leaf() may end up returning a path that points to the same item (key) again. This happens if while btrfs_prev_leaf(), after we release the path, a concurrent insertion happens, which moves items off from a sibling into the front of the previous leaf, and an item with the computed previous key does not exists. For example, suppose we have the two following leaves: Leaf A ------------------------------------------------------------- | ... key (300 96 10) key (300 96 15) key (300 96 16) | ------------------------------------------------------------- slot 20 slot 21 slot 22 Leaf B ------------------------------------------------------------- | key (300 96 20) key (300 96 21) key (300 96 22) ... | ------------------------------------------------------------- slot 0 slot 1 slot 2 If we call btrfs_prev_leaf(), from btrfs_previous_item() for example, with a path pointing to leaf B and slot 0 and the following happens: 1) At btrfs_prev_leaf() we compute the previous key to search as: (300 96 19), which is a key that does not exists in the tree; 2) Then we call btrfs_release_path() at btrfs_prev_leaf(); 3) Some other task inserts a key at leaf A, that sorts before the key at slot 20, for example it has an objectid of 299. In order to make room for the new key, the key at slot 22 is moved to the front of leaf B. This happens at push_leaf_right(), called from split_leaf(). After this leaf B now looks like: -------------------------------------------------------------------------------- | key (300 96 16) key (300 96 20) key (300 96 21) key (300 96 22) ... | -------------------------------------------------------------------------------- slot 0 slot 1 slot 2 slot 3 4) At btrfs_prev_leaf() we call btrfs_search_slot() for the computed previous key: (300 96 19). Since the key does not exists, btrfs_search_slot() returns 1 and with a path pointing to leaf B and slot 1, the item with key (300 96 20); 5) This makes btrfs_prev_leaf() return a path that points to slot 1 of leaf B, the same key as before it was called, since the key at slot 0 of leaf B (300 96 16) is less than the computed previous key, which is (300 96 19); 6) As a consequence btrfs_previous_item() returns a path that points again to the item with key (300 96 20). For some users of btrfs_prev_leaf() or btrfs_previous_item() this may not be functional a problem, despite not making sense to return a new path pointing again to the same item/key. However for a caller such as tree-log.c:log_dir_items(), this has a bad consequence, as it can result in not logging some dir index deletions in case the directory is being logged without holding the inode's VFS lock (logging triggered while logging a child inode for example) - for the example scenario above, in case the dir index keys 17, 18 and 19 were deleted in the current transaction. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/ctree.c | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5addd1e36a8e..3e55245e54e7 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -5160,10 +5160,12 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) { struct btrfs_key key; + struct btrfs_key orig_key; struct btrfs_disk_key found_key; int ret; btrfs_item_key_to_cpu(path->nodes[0], &key, 0); + orig_key = key; if (key.offset > 0) { key.offset--; @@ -5180,8 +5182,36 @@ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) + if (ret <= 0) return ret; + + /* + * Previous key not found. Even if we were at slot 0 of the leaf we had + * before releasing the path and calling btrfs_search_slot(), we now may + * be in a slot pointing to the same original key - this can happen if + * after we released the path, one of more items were moved from a + * sibling leaf into the front of the leaf we had due to an insertion + * (see push_leaf_right()). + * If we hit this case and our slot is > 0 and just decrement the slot + * so that the caller does not process the same key again, which may or + * may not break the caller, depending on its logic. + */ + if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { + btrfs_item_key(path->nodes[0], &found_key, path->slots[0]); + ret = comp_keys(&found_key, &orig_key); + if (ret == 0) { + if (path->slots[0] > 0) { + path->slots[0]--; + return 0; + } + /* + * At slot 0, same key as before, it means orig_key is + * the lowest, leftmost, key in the tree. We're done. + */ + return 1; + } + } + btrfs_item_key(path->nodes[0], &found_key, 0); ret = comp_keys(&found_key, &key); /* From 148b16cd30b202999ec5b534e3e5d8ab4b766f21 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 2 May 2023 16:00:06 -0400 Subject: [PATCH 3006/4345] btrfs: don't free qgroup space unless specified commit d246331b78cbef86237f9c22389205bc9b4e1cc1 upstream. Boris noticed in his simple quotas testing that he was getting a leak with Sweet Tea's change to subvol create that stopped doing a transaction commit. This was just a side effect of that change. In the delayed inode code we have an optimization that will free extra reservations if we think we can pack a dir item into an already modified leaf. Previously this wouldn't be triggered in the subvolume create case because we'd commit the transaction, it was still possible but much harder to trigger. It could actually be triggered if we did a mkdir && subvol create with qgroups enabled. This occurs because in btrfs_insert_delayed_dir_index(), which gets called when we're adding the dir item, we do the following: btrfs_block_rsv_release(fs_info, trans->block_rsv, bytes, NULL); if we're able to skip reserving space. The problem here is that trans->block_rsv points at the temporary block rsv for the subvolume create, which has qgroup reservations in the block rsv. This is a problem because btrfs_block_rsv_release() will do the following: if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) { qgroup_to_release = block_rsv->qgroup_rsv_reserved - block_rsv->qgroup_rsv_size; block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size; } The temporary block rsv just has ->qgroup_rsv_reserved set, ->qgroup_rsv_size == 0. The optimization in btrfs_insert_delayed_dir_index() sets ->qgroup_rsv_reserved = 0. Then later on when we call btrfs_subvolume_release_metadata() which has btrfs_block_rsv_release(fs_info, rsv, (u64)-1, &qgroup_to_release); btrfs_qgroup_convert_reserved_meta(root, qgroup_to_release); qgroup_to_release is set to 0, and we do not convert the reserved metadata space. The problem here is that the block rsv code has been unconditionally messing with ->qgroup_rsv_reserved, because the main place this is used is delalloc, and any time we call btrfs_block_rsv_release() we do it with qgroup_to_release set, and thus do the proper accounting. The subvolume code is the only other code that uses the qgroup reservation stuff, but it's intermingled with the above optimization, and thus was getting its reservation freed out from underneath it and thus leaking the reserved space. The solution is to simply not mess with the qgroup reservations if we don't have qgroup_to_release set. This works with the existing code as anything that messes with the delalloc reservations always have qgroup_to_release set. This fixes the leak that Boris was observing. Reviewed-by: Qu Wenruo CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/block-rsv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index bc920afe23bf..eb41dc2f6b40 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -121,7 +121,8 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info, } else { num_bytes = 0; } - if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) { + if (qgroup_to_release_ret && + block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) { qgroup_to_release = block_rsv->qgroup_rsv_reserved - block_rsv->qgroup_rsv_size; block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size; From 829c20fd7a7b2fe440a1a5261b6f366e7398ba92 Mon Sep 17 00:00:00 2001 From: Anastasia Belova Date: Wed, 26 Apr 2023 14:53:23 +0300 Subject: [PATCH 3007/4345] btrfs: print-tree: parent bytenr must be aligned to sector size commit c87f318e6f47696b4040b58f460d5c17ea0280e6 upstream. Check nodesize to sectorsize in alignment check in print_extent_item. The comment states that and this is correct, similar check is done elsewhere in the functions. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: ea57788eb76d ("btrfs: require only sector size alignment for parent eb bytenr") CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Qu Wenruo Signed-off-by: Anastasia Belova Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/print-tree.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index c62771f3af8c..e98ba4e091b3 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -147,10 +147,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) pr_cont("shared data backref parent %llu count %u\n", offset, btrfs_shared_data_ref_count(eb, sref)); /* - * offset is supposed to be a tree block which - * must be aligned to nodesize. + * Offset is supposed to be a tree block which must be + * aligned to sectorsize. */ - if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) + if (!IS_ALIGNED(offset, eb->fs_info->sectorsize)) pr_info( "\t\t\t(parent %llu not aligned to sectorsize %u)\n", offset, eb->fs_info->sectorsize); From 8c2cdb7326f0672db21d1d114aaf7b2193ca21ae Mon Sep 17 00:00:00 2001 From: Pawel Witek Date: Fri, 5 May 2023 17:14:59 +0200 Subject: [PATCH 3008/4345] cifs: fix pcchunk length type in smb2_copychunk_range commit d66cde50c3c868af7abddafce701bb86e4a93039 upstream. Change type of pcchunk->Length from u32 to u64 to match smb2_copychunk_range arguments type. Fixes the problem where performing server-side copy with CIFS_IOC_COPYCHUNK_FILE ioctl resulted in incomplete copy of large files while returning -EINVAL. Fixes: 9bf0c9cd4314 ("CIFS: Fix SMB2/SMB3 Copy offload support (refcopy) for large files") Cc: Signed-off-by: Pawel Witek Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/smb2ops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 120c7cb11b02..015b7b37edee 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1784,7 +1784,7 @@ smb2_copychunk_range(const unsigned int xid, pcchunk->SourceOffset = cpu_to_le64(src_off); pcchunk->TargetOffset = cpu_to_le64(dest_off); pcchunk->Length = - cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk)); + cpu_to_le32(min_t(u64, len, tcon->max_bytes_chunk)); /* Request server copy to target from src identified by key */ kfree(retbuf); From 4b87eec73e47e70bcafe98c36f32483a033e1688 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 5 May 2023 23:03:23 +0200 Subject: [PATCH 3009/4345] platform/x86: touchscreen_dmi: Add upside-down quirk for GDIX1002 ts on the Juno Tablet commit 6abfa99ce52f61a31bcfc2aaaae09006f5665495 upstream. The Juno Computers Juno Tablet has an upside-down mounted Goodix touchscreen. Add a quirk to invert both axis to correct for this. Link: https://junocomputers.com/us/product/juno-tablet/ Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230505210323.43177-1-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/touchscreen_dmi.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index b96fbc8dba09..0d1356e4e2c3 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -381,6 +381,11 @@ static const struct ts_dmi_data glavey_tm800a550l_data = { .properties = glavey_tm800a550l_props, }; +static const struct ts_dmi_data gdix1002_00_upside_down_data = { + .acpi_name = "GDIX1002:00", + .properties = gdix1001_upside_down_props, +}; + static const struct property_entry gp_electronic_t701_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 960), PROPERTY_ENTRY_U32("touchscreen-size-y", 640), @@ -1227,6 +1232,18 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BIOS_VERSION, "jumperx.T87.KFBNEEA"), }, }, + { + /* Juno Tablet */ + .driver_data = (void *)&gdix1002_00_upside_down_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Default string"), + /* Both product- and board-name being "Default string" is somewhat rare */ + DMI_MATCH(DMI_PRODUCT_NAME, "Default string"), + DMI_MATCH(DMI_BOARD_NAME, "Default string"), + /* Above matches are too generic, add partial bios-version match */ + DMI_MATCH(DMI_BIOS_VERSION, "JP2V1."), + }, + }, { /* Mediacom WinPad 7.0 W700 (same hw as Wintron surftab 7") */ .driver_data = (void *)&trekstor_surftab_wintron70_data, From 73aef14407de964b2a05d08c1f431298c7c3b7b5 Mon Sep 17 00:00:00 2001 From: Andrey Avdeev Date: Sun, 30 Apr 2023 11:01:10 +0300 Subject: [PATCH 3010/4345] platform/x86: touchscreen_dmi: Add info for the Dexp Ursus KX210i commit 4b65f95c87c35699bc6ad540d6b9dd7f950d0924 upstream. Add touchscreen info for the Dexp Ursus KX210i Signed-off-by: Andrey Avdeev Link: https://lore.kernel.org/r/ZE4gRgzRQCjXFYD0@avdeevavpc Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/touchscreen_dmi.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 0d1356e4e2c3..55a18cd0c298 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -327,6 +327,22 @@ static const struct ts_dmi_data dexp_ursus_7w_data = { .properties = dexp_ursus_7w_props, }; +static const struct property_entry dexp_ursus_kx210i_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 5), + PROPERTY_ENTRY_U32("touchscreen-min-y", 2), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1720), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1137), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-dexp-ursus-kx210i.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data dexp_ursus_kx210i_data = { + .acpi_name = "MSSL1680:00", + .properties = dexp_ursus_kx210i_props, +}; + static const struct property_entry digma_citi_e200_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), PROPERTY_ENTRY_U32("touchscreen-size-y", 1500), @@ -1123,6 +1139,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "7W"), }, }, + { + /* DEXP Ursus KX210i */ + .driver_data = (void *)&dexp_ursus_kx210i_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "INSYDE Corp."), + DMI_MATCH(DMI_PRODUCT_NAME, "S107I"), + }, + }, { /* Digma Citi E200 */ .driver_data = (void *)&digma_citi_e200_data, From 2d65c97777e5b4a845637800d5d7b648f5772106 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 24 Apr 2023 18:32:19 +0200 Subject: [PATCH 3011/4345] inotify: Avoid reporting event with invalid wd commit c915d8f5918bea7c3962b09b8884ca128bfd9b0c upstream. When inotify_freeing_mark() races with inotify_handle_inode_event() it can happen that inotify_handle_inode_event() sees that i_mark->wd got already reset to -1 and reports this value to userspace which can confuse the inotify listener. Avoid the problem by validating that wd is sensible (and pretend the mark got removed before the event got generated otherwise). CC: stable@vger.kernel.org Fixes: 7e790dd5fc93 ("inotify: fix error paths in inotify_update_watch") Message-Id: <20230424163219.9250-1-jack@suse.cz> Reported-by: syzbot+4a06d4373fd52f0b2f9c@syzkaller.appspotmail.com Reviewed-by: Amir Goldstein Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/notify/inotify/inotify_fsnotify.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 1901d799909b..66991c7fef9e 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -64,7 +64,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, struct fsnotify_event *fsn_event; struct fsnotify_group *group = inode_mark->group; int ret; - int len = 0; + int len = 0, wd; int alloc_len = sizeof(struct inotify_event_info); struct mem_cgroup *old_memcg; @@ -79,6 +79,13 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, i_mark = container_of(inode_mark, struct inotify_inode_mark, fsn_mark); + /* + * We can be racing with mark being detached. Don't report event with + * invalid wd. + */ + wd = READ_ONCE(i_mark->wd); + if (wd == -1) + return 0; /* * Whoever is interested in the event, pays for the allocation. Do not * trigger OOM killer in the target monitoring memcg as it may have @@ -109,7 +116,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, fsn_event = &event->fse; fsnotify_init_event(fsn_event, 0); event->mask = mask; - event->wd = i_mark->wd; + event->wd = wd; event->sync_cookie = cookie; event->name_len = len; if (len) From bbad64abd610fb007ab0650fe3a953261c0b8998 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:34 -0800 Subject: [PATCH 3012/4345] sh: math-emu: fix macro redefined warning commit 58a49ad90939386a8682e842c474a0d2c00ec39c upstream. Fix a warning that was reported by the kernel test robot: In file included from ../include/math-emu/soft-fp.h:27, from ../arch/sh/math-emu/math.c:22: ../arch/sh/include/asm/sfp-machine.h:17: warning: "__BYTE_ORDER" redefined 17 | #define __BYTE_ORDER __BIG_ENDIAN In file included from ../arch/sh/math-emu/math.c:21: ../arch/sh/math-emu/sfp-util.h:71: note: this is the location of the previous definition 71 | #define __BYTE_ORDER __LITTLE_ENDIAN Fixes: b929926f01f2 ("sh: define __BIG_ENDIAN for math-emu") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Link: lore.kernel.org/r/202111121827.6v6SXtVv-lkp@intel.com Cc: John Paul Adrian Glaubitz Cc: Yoshinori Sato Cc: Rich Felker Cc: linux-sh@vger.kernel.org Reviewed-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-5-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz Signed-off-by: Greg Kroah-Hartman --- arch/sh/math-emu/sfp-util.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/sh/math-emu/sfp-util.h b/arch/sh/math-emu/sfp-util.h index 784f541344f3..bda50762b3d3 100644 --- a/arch/sh/math-emu/sfp-util.h +++ b/arch/sh/math-emu/sfp-util.h @@ -67,7 +67,3 @@ } while (0) #define abort() return 0 - -#define __BYTE_ORDER __LITTLE_ENDIAN - - From f19bc0d2a68c9c4f0e4d177642468d3e0fbb87cf Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:37 -0800 Subject: [PATCH 3013/4345] sh: mcount.S: fix build error when PRINTK is not enabled commit c2bd1e18c6f85c0027da2e5e7753b9bfd9f8e6dc upstream. Fix a build error in mcount.S when CONFIG_PRINTK is not enabled. Fixes this build error: sh2-linux-ld: arch/sh/lib/mcount.o: in function `stack_panic': (.text+0xec): undefined reference to `dump_stack' Fixes: e460ab27b6c3 ("sh: Fix up stack overflow check with ftrace disabled.") Signed-off-by: Randy Dunlap Cc: John Paul Adrian Glaubitz Cc: Yoshinori Sato Cc: Rich Felker Suggested-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-8-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz Signed-off-by: Greg Kroah-Hartman --- arch/sh/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug index 97b0e26cf05a..7bc1b10b81c9 100644 --- a/arch/sh/Kconfig.debug +++ b/arch/sh/Kconfig.debug @@ -18,7 +18,7 @@ config SH_STANDARD_BIOS config STACK_DEBUG bool "Check for stack overflows" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && PRINTK help This option will cause messages to be printed if free stack space drops below a certain limit. Saying Y here will add overhead to From 9245f34029b7c09d40442d20f4056a2ca5b53ae5 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:33 -0800 Subject: [PATCH 3014/4345] sh: init: use OF_EARLY_FLATTREE for early init commit 6cba655543c7959f8a6d2979b9d40a6a66b7ed4f upstream. When CONFIG_OF_EARLY_FLATTREE and CONFIG_SH_DEVICE_TREE are not set, SH3 build fails with a call to early_init_dt_scan(), so in arch/sh/kernel/setup.c and arch/sh/kernel/head_32.S, use CONFIG_OF_EARLY_FLATTREE instead of CONFIG_OF_FLATTREE. Fixes this build error: ../arch/sh/kernel/setup.c: In function 'sh_fdt_init': ../arch/sh/kernel/setup.c:262:26: error: implicit declaration of function 'early_init_dt_scan' [-Werror=implicit-function-declaration] 262 | if (!dt_virt || !early_init_dt_scan(dt_virt)) { Fixes: 03767daa1387 ("sh: fix build regression with CONFIG_OF && !CONFIG_OF_FLATTREE") Fixes: eb6b6930a70f ("sh: fix memory corruption of unflattened device tree") Signed-off-by: Randy Dunlap Suggested-by: Rob Herring Cc: Frank Rowand Cc: devicetree@vger.kernel.org Cc: Rich Felker Cc: Yoshinori Sato Cc: Geert Uytterhoeven Cc: John Paul Adrian Glaubitz Cc: linux-sh@vger.kernel.org Cc: stable@vger.kernel.org Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-4-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz Signed-off-by: Greg Kroah-Hartman --- arch/sh/kernel/head_32.S | 6 +++--- arch/sh/kernel/setup.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/sh/kernel/head_32.S b/arch/sh/kernel/head_32.S index 4adbd4ade319..b603b7968b38 100644 --- a/arch/sh/kernel/head_32.S +++ b/arch/sh/kernel/head_32.S @@ -64,7 +64,7 @@ ENTRY(_stext) ldc r0, r6_bank #endif -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE mov r4, r12 ! Store device tree blob pointer in r12 #endif @@ -315,7 +315,7 @@ ENTRY(_stext) 10: #endif -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE mov.l 8f, r0 ! Make flat device tree available early. jsr @r0 mov r12, r4 @@ -346,7 +346,7 @@ ENTRY(stack_start) 5: .long start_kernel 6: .long cpu_init 7: .long init_thread_union -#if defined(CONFIG_OF_FLATTREE) +#if defined(CONFIG_OF_EARLY_FLATTREE) 8: .long sh_fdt_init #endif diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 4144be650d41..556e463a43d2 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -244,7 +244,7 @@ void __init __weak plat_early_device_setup(void) { } -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE void __ref sh_fdt_init(phys_addr_t dt_phys) { static int done = 0; @@ -329,7 +329,7 @@ void __init setup_arch(char **cmdline_p) /* Let earlyprintk output early console messages */ sh_early_platform_driver_probe("earlyprintk", 1, 1); -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE #ifdef CONFIG_USE_BUILTIN_DTB unflatten_and_copy_device_tree(); #else From 62fe5d74ef7f4cbab25c223f3b894c7d47e8893a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:32 -0800 Subject: [PATCH 3015/4345] sh: nmi_debug: fix return value of __setup handler commit d1155e4132de712a9d3066e2667ceaad39a539c5 upstream. __setup() handlers should return 1 to obsolete_checksetup() in init/main.c to indicate that the boot option has been handled. A return of 0 causes the boot option/value to be listed as an Unknown kernel parameter and added to init's (limited) argument or environment strings. Also, error return codes don't mean anything to obsolete_checksetup() -- only non-zero (usually 1) or zero. So return 1 from nmi_debug_setup(). Fixes: 1e1030dccb10 ("sh: nmi_debug support.") Signed-off-by: Randy Dunlap Reported-by: Igor Zhbanov Link: lore.kernel.org/r/64644a2f-4a20-bab3-1e15-3b2cdd0defe3@omprussia.ru Cc: John Paul Adrian Glaubitz Cc: Yoshinori Sato Cc: Rich Felker Cc: linux-sh@vger.kernel.org Cc: stable@vger.kernel.org Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-3-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz Signed-off-by: Greg Kroah-Hartman --- arch/sh/kernel/nmi_debug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/sh/kernel/nmi_debug.c b/arch/sh/kernel/nmi_debug.c index 11777867c6f5..a212b645b4cf 100644 --- a/arch/sh/kernel/nmi_debug.c +++ b/arch/sh/kernel/nmi_debug.c @@ -49,7 +49,7 @@ static int __init nmi_debug_setup(char *str) register_die_notifier(&nmi_debug_nb); if (*str != '=') - return 0; + return 1; for (p = str + 1; *p; p = sep + 1) { sep = strchr(p, ','); @@ -70,6 +70,6 @@ static int __init nmi_debug_setup(char *str) break; } - return 0; + return 1; } __setup("nmi_debug", nmi_debug_setup); From 30e0834becd8c35781628d3d244bdcd14e57cc31 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Mon, 20 Mar 2023 16:18:22 -0600 Subject: [PATCH 3016/4345] remoteproc: stm32: Call of_node_put() on iteration error commit ccadca5baf5124a880f2bb50ed1ec265415f025b upstream. Function of_phandle_iterator_next() calls of_node_put() on the last device_node it iterated over, but when the loop exits prematurely it has to be called explicitly. Fixes: 13140de09cc2 ("remoteproc: stm32: add an ST stm32_rproc driver") Cc: stable@vger.kernel.org Signed-off-by: Mathieu Poirier Reviewed-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20230320221826.2728078-2-mathieu.poirier@linaro.org Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/remoteproc/stm32_rproc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index d2414cc1d90d..24760d8ea637 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -231,11 +231,13 @@ static int stm32_rproc_parse_memory_regions(struct rproc *rproc) while (of_phandle_iterator_next(&it) == 0) { rmem = of_reserved_mem_lookup(it.node); if (!rmem) { + of_node_put(it.node); dev_err(dev, "unable to acquire memory-region\n"); return -EINVAL; } if (stm32_rproc_pa_to_da(rproc, rmem->base, &da) < 0) { + of_node_put(it.node); dev_err(dev, "memory region not valid %pa\n", &rmem->base); return -EINVAL; @@ -262,8 +264,10 @@ static int stm32_rproc_parse_memory_regions(struct rproc *rproc) it.node->name); } - if (!mem) + if (!mem) { + of_node_put(it.node); return -ENOMEM; + } rproc_add_carveout(rproc, mem); index++; From 777952ce11873c66a2a0bb556258dcbbde320430 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Mon, 20 Mar 2023 16:18:23 -0600 Subject: [PATCH 3017/4345] remoteproc: st: Call of_node_put() on iteration error commit 8a74918948b40317a5b5bab9739d13dcb5de2784 upstream. Function of_phandle_iterator_next() calls of_node_put() on the last device_node it iterated over, but when the loop exits prematurely it has to be called explicitly. Fixes: 3df52ed7f269 ("remoteproc: st: add reserved memory support") Cc: stable@vger.kernel.org Signed-off-by: Mathieu Poirier Reviewed-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20230320221826.2728078-3-mathieu.poirier@linaro.org Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/remoteproc/st_remoteproc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/st_remoteproc.c b/drivers/remoteproc/st_remoteproc.c index a3268d95a50e..e6bd3c7a950a 100644 --- a/drivers/remoteproc/st_remoteproc.c +++ b/drivers/remoteproc/st_remoteproc.c @@ -129,6 +129,7 @@ static int st_rproc_parse_fw(struct rproc *rproc, const struct firmware *fw) while (of_phandle_iterator_next(&it) == 0) { rmem = of_reserved_mem_lookup(it.node); if (!rmem) { + of_node_put(it.node); dev_err(dev, "unable to acquire memory-region\n"); return -EINVAL; } @@ -150,8 +151,10 @@ static int st_rproc_parse_fw(struct rproc *rproc, const struct firmware *fw) it.node->name); } - if (!mem) + if (!mem) { + of_node_put(it.node); return -ENOMEM; + } rproc_add_carveout(rproc, mem); index++; From fed6318e47222c88655b7c3a9b216fa94899a6e2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 17 Feb 2023 16:06:27 +0100 Subject: [PATCH 3018/4345] ARM: dts: exynos: fix WM8960 clock name in Itop Elite commit 6c950c20da38debf1ed531e0b972bd8b53d1c11f upstream. The WM8960 Linux driver expects the clock to be named "mclk". Otherwise the clock will be ignored and not prepared/enabled by the driver. Cc: Fixes: 339b2fb36a67 ("ARM: dts: exynos: Add TOPEET itop elite based board") Link: https://lore.kernel.org/r/20230217150627.779764-3-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/exynos4412-itop-elite.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/exynos4412-itop-elite.dts b/arch/arm/boot/dts/exynos4412-itop-elite.dts index f6d0a5f5d339..9a2a49420d4d 100644 --- a/arch/arm/boot/dts/exynos4412-itop-elite.dts +++ b/arch/arm/boot/dts/exynos4412-itop-elite.dts @@ -179,7 +179,7 @@ compatible = "wlf,wm8960"; reg = <0x1a>; clocks = <&pmu_system_controller 0>; - clock-names = "MCLK1"; + clock-names = "mclk"; wlf,shared-lrclk; #sound-dai-cells = <0>; }; From 4a638a958230748031967662f91d7d14f5077869 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Feb 2023 19:58:18 +0100 Subject: [PATCH 3019/4345] ARM: dts: s5pv210: correct MIPI CSIS clock name commit 665b9459bb53b8f19bd1541567e1fe9782c83c4b upstream. The Samsung S5P/Exynos MIPI CSIS bindings and Linux driver expect first clock name to be "csis". Otherwise the driver fails to probe. Fixes: 94ad0f6d9278 ("ARM: dts: Add Device tree for s5pv210 SoC") Cc: Link: https://lore.kernel.org/r/20230212185818.43503-2-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/s5pv210.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/s5pv210.dtsi b/arch/arm/boot/dts/s5pv210.dtsi index eb7e3660ada7..81ab9fe9897f 100644 --- a/arch/arm/boot/dts/s5pv210.dtsi +++ b/arch/arm/boot/dts/s5pv210.dtsi @@ -583,7 +583,7 @@ interrupts = <29>; clocks = <&clocks CLK_CSIS>, <&clocks SCLK_CSIS>; - clock-names = "clk_csis", + clock-names = "csis", "sclk_csis"; bus-width = <4>; status = "disabled"; From 957904f531fd857a92743b11fbc9c9ffdf7f3207 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 6 Apr 2023 11:18:48 -0700 Subject: [PATCH 3020/4345] f2fs: fix potential corruption when moving a directory commit d94772154e524b329a168678836745d2773a6e02 upstream. F2FS has the same issue in ext4_rename causing crash revealed by xfstests/generic/707. See also commit 0813299c586b ("ext4: Fix possible corruption when moving a directory") CC: stable@vger.kernel.org Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/namei.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 72b109685db4..98263180c0ea 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -969,12 +969,20 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; } + /* + * Copied from ext4_rename: we need to protect against old.inode + * directory getting converted from inline directory format into + * a normal one. + */ + if (S_ISDIR(old_inode->i_mode)) + inode_lock_nested(old_inode, I_MUTEX_NONDIR2); + err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) err = PTR_ERR(old_page); - goto out; + goto out_unlock_old; } if (S_ISDIR(old_inode->i_mode)) { @@ -1082,6 +1090,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_unlock_op(sbi); + if (S_ISDIR(old_inode->i_mode)) + inode_unlock(old_inode); + if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); @@ -1096,6 +1107,9 @@ out_dir: f2fs_put_page(old_dir_page, 0); out_old: f2fs_put_page(old_page, 0); +out_unlock_old: + if (S_ISDIR(old_inode->i_mode)) + inode_unlock(old_inode); out: if (whiteout) iput(whiteout); From c85327c1e93ceef2bef9bb2d367e8d2b08b88a62 Mon Sep 17 00:00:00 2001 From: James Cowgill Date: Wed, 12 Apr 2023 17:35:07 +0000 Subject: [PATCH 3021/4345] drm/panel: otm8009a: Set backlight parent to panel device commit ab4f869fba6119997f7630d600049762a2b014fa upstream. This is the logical place to put the backlight device, and it also fixes a kernel crash if the MIPI host is removed. Previously the backlight device would be unregistered twice when this happened - once as a child of the MIPI host through `mipi_dsi_host_unregister`, and once when the panel device is destroyed. Fixes: 12a6cbd4f3f1 ("drm/panel: otm8009a: Use new backlight API") Signed-off-by: James Cowgill Cc: stable@vger.kernel.org Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230412173450.199592-1-james.cowgill@blaize.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/panel/panel-orisetech-otm8009a.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c index 6ac1accade80..b19597b836e3 100644 --- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c +++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c @@ -458,7 +458,7 @@ static int otm8009a_probe(struct mipi_dsi_device *dsi) DRM_MODE_CONNECTOR_DSI); ctx->bl_dev = devm_backlight_device_register(dev, dev_name(dev), - dsi->host->dev, ctx, + dev, ctx, &otm8009a_backlight_ops, NULL); if (IS_ERR(ctx->bl_dev)) { From eed63477ae065b69ee757e38a1cd48ec51de9719 Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Tue, 2 May 2023 11:59:08 -0400 Subject: [PATCH 3022/4345] drm/amdgpu: fix an amdgpu_irq_put() issue in gmc_v9_0_hw_fini() commit 922a76ba31adf84e72bc947267385be420c689ee upstream. As made mention of in commit 08c677cb0b43 ("drm/amdgpu: fix amdgpu_irq_put call trace in gmc_v10_0_hw_fini") and commit 13af556104fa ("drm/amdgpu: fix amdgpu_irq_put call trace in gmc_v11_0_hw_fini"). It is meaningless to call amdgpu_irq_put() for gmc.ecc_irq. So, remove it from gmc_v9_0_hw_fini(). Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2522 Fixes: 3029c855d79f ("drm/amdgpu: Fix desktop freezed after gpu-reset") Reviewed-by: Mario Limonciello Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 1673bf3bae55..945cbdbc2f99 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1686,7 +1686,6 @@ static int gmc_v9_0_hw_fini(void *handle) return 0; } - amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); return 0; From 20ca90ceda71ed90a4d6960acbe7d5e120b40c0d Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Sat, 6 May 2023 20:06:45 +0800 Subject: [PATCH 3023/4345] drm/amdgpu/gfx: disable gfx9 cp_ecc_error_irq only when enabling legacy gfx ras commit 4a76680311330aefe5074bed8f06afa354b85c48 upstream. gfx9 cp_ecc_error_irq is only enabled when legacy gfx ras is assert. So in gfx_v9_0_hw_fini, interrupt disablement for cp_ecc_error_irq should be executed under such condition, otherwise, an amdgpu_irq_put calltrace will occur. [ 7283.170322] RIP: 0010:amdgpu_irq_put+0x45/0x70 [amdgpu] [ 7283.170964] RSP: 0018:ffff9a5fc3967d00 EFLAGS: 00010246 [ 7283.170967] RAX: ffff98d88afd3040 RBX: ffff98d89da20000 RCX: 0000000000000000 [ 7283.170969] RDX: 0000000000000000 RSI: ffff98d89da2bef8 RDI: ffff98d89da20000 [ 7283.170971] RBP: ffff98d89da20000 R08: ffff98d89da2ca18 R09: 0000000000000006 [ 7283.170973] R10: ffffd5764243c008 R11: 0000000000000000 R12: 0000000000001050 [ 7283.170975] R13: ffff98d89da38978 R14: ffffffff999ae15a R15: ffff98d880130105 [ 7283.170978] FS: 0000000000000000(0000) GS:ffff98d996f00000(0000) knlGS:0000000000000000 [ 7283.170981] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7283.170983] CR2: 00000000f7a9d178 CR3: 00000001c42ea000 CR4: 00000000003506e0 [ 7283.170986] Call Trace: [ 7283.170988] [ 7283.170989] gfx_v9_0_hw_fini+0x1c/0x6d0 [amdgpu] [ 7283.171655] amdgpu_device_ip_suspend_phase2+0x101/0x1a0 [amdgpu] [ 7283.172245] amdgpu_device_suspend+0x103/0x180 [amdgpu] [ 7283.172823] amdgpu_pmops_freeze+0x21/0x60 [amdgpu] [ 7283.173412] pci_pm_freeze+0x54/0xc0 [ 7283.173419] ? __pfx_pci_pm_freeze+0x10/0x10 [ 7283.173425] dpm_run_callback+0x98/0x200 [ 7283.173430] __device_suspend+0x164/0x5f0 v2: drop gfx11 as it's fixed in a different solution by retiring cp_ecc_irq funcs(Hawking) Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2522 Signed-off-by: Guchun Chen Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 38f4c7474487..629671f66b31 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3943,7 +3943,8 @@ static int gfx_v9_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) + amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); From c1420276be7a98df0074584bb9c1709cbc1a9df5 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Sat, 6 May 2023 16:52:59 +0800 Subject: [PATCH 3024/4345] drm/amdgpu: disable sdma ecc irq only when sdma RAS is enabled in suspend commit 8b229ada2669b74fdae06c83fbfda5a5a99fc253 upstream. sdma_v4_0_ip is shared on a few asics, but in sdma_v4_0_hw_fini, driver unconditionally disables ecc_irq which is only enabled on those asics enabling sdma ecc. This will introduce a warning in suspend cycle on those chips with sdma ip v4.0, while without sdma ecc. So this patch correct this. [ 7283.166354] RIP: 0010:amdgpu_irq_put+0x45/0x70 [amdgpu] [ 7283.167001] RSP: 0018:ffff9a5fc3967d08 EFLAGS: 00010246 [ 7283.167019] RAX: ffff98d88afd3770 RBX: 0000000000000001 RCX: 0000000000000000 [ 7283.167023] RDX: 0000000000000000 RSI: ffff98d89da30390 RDI: ffff98d89da20000 [ 7283.167025] RBP: ffff98d89da20000 R08: 0000000000036838 R09: 0000000000000006 [ 7283.167028] R10: ffffd5764243c008 R11: 0000000000000000 R12: ffff98d89da30390 [ 7283.167030] R13: ffff98d89da38978 R14: ffffffff999ae15a R15: ffff98d880130105 [ 7283.167032] FS: 0000000000000000(0000) GS:ffff98d996f00000(0000) knlGS:0000000000000000 [ 7283.167036] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7283.167039] CR2: 00000000f7a9d178 CR3: 00000001c42ea000 CR4: 00000000003506e0 [ 7283.167041] Call Trace: [ 7283.167046] [ 7283.167048] sdma_v4_0_hw_fini+0x38/0xa0 [amdgpu] [ 7283.167704] amdgpu_device_ip_suspend_phase2+0x101/0x1a0 [amdgpu] [ 7283.168296] amdgpu_device_suspend+0x103/0x180 [amdgpu] [ 7283.168875] amdgpu_pmops_freeze+0x21/0x60 [amdgpu] [ 7283.169464] pci_pm_freeze+0x54/0xc0 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2522 Signed-off-by: Guchun Chen Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 1f2e2460e121..dbcaef3f35da 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1979,9 +1979,11 @@ static int sdma_v4_0_hw_fini(void *handle) if (amdgpu_sriov_vf(adev)) return 0; - for (i = 0; i < adev->sdma.num_instances; i++) { - amdgpu_irq_put(adev, &adev->sdma.ecc_irq, - AMDGPU_SDMA_IRQ_INSTANCE0 + i); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) { + for (i = 0; i < adev->sdma.num_instances; i++) { + amdgpu_irq_put(adev, &adev->sdma.ecc_irq, + AMDGPU_SDMA_IRQ_INSTANCE0 + i); + } } sdma_v4_0_ctx_switch_enable(adev, false); From 77fd800d3f1be3fd2ad3465ad0ac774f5b8f8263 Mon Sep 17 00:00:00 2001 From: Ping Cheng Date: Sun, 9 Apr 2023 09:42:29 -0700 Subject: [PATCH 3025/4345] HID: wacom: Set a default resolution for older tablets commit 08a46b4190d345544d04ce4fe2e1844b772b8535 upstream. Some older tablets may not report physical maximum for X/Y coordinates. Set a default to prevent undefined resolution. Signed-off-by: Ping Cheng Link: https://lore.kernel.org/r/20230409164229.29777-1-ping.cheng@wacom.com Signed-off-by: Benjamin Tissoires Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom_wac.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index afb94b89fc4d..b65ed38c45e6 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1853,6 +1853,7 @@ static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage, int fmax = field->logical_maximum; unsigned int equivalent_usage = wacom_equivalent_usage(usage->hid); int resolution_code = code; + int resolution = hidinput_calc_abs_res(field, resolution_code); if (equivalent_usage == HID_DG_TWIST) { resolution_code = ABS_RZ; @@ -1875,8 +1876,15 @@ static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage, switch (type) { case EV_ABS: input_set_abs_params(input, code, fmin, fmax, fuzz, 0); - input_abs_set_res(input, code, - hidinput_calc_abs_res(field, resolution_code)); + + /* older tablet may miss physical usage */ + if ((code == ABS_X || code == ABS_Y) && !resolution) { + resolution = WACOM_INTUOS_RES; + hid_warn(input, + "Wacom usage (%d) missing resolution \n", + code); + } + input_abs_set_res(input, code, resolution); break; case EV_KEY: input_set_capability(input, EV_KEY, code); From 4502ebbdc0e21e44a8a706428e420ae9c1bb9bba Mon Sep 17 00:00:00 2001 From: Ping Cheng Date: Fri, 24 Feb 2023 08:26:43 -0800 Subject: [PATCH 3026/4345] HID: wacom: insert timestamp to packed Bluetooth (BT) events commit 17d793f3ed53080dab6bbeabfc82de890c901001 upstream. To fully utilize the BT polling/refresh rate, a few input events are sent together to reduce event delay. This causes issue to the timestamp generated by input_sync since all the events in the same packet would pretty much have the same timestamp. This patch inserts time interval to the events by averaging the total time used for sending the packet. This decision was mainly based on observing the actual time interval between each BT polling. The interval doesn't seem to be constant, due to the network and system environment. So, using solutions other than averaging doesn't end up with valid timestamps. Signed-off-by: Ping Cheng Reviewed-by: Jason Gerecke Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom_wac.c | 26 ++++++++++++++++++++++++++ drivers/hid/wacom_wac.h | 1 + 2 files changed, 27 insertions(+) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index b65ed38c45e6..6c64165fae13 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1265,6 +1265,9 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) struct input_dev *pen_input = wacom->pen_input; unsigned char *data = wacom->data; + int number_of_valid_frames = 0; + int time_interval = 15000000; + ktime_t time_packet_received = ktime_get(); int i; if (wacom->features.type == INTUOSP2_BT || @@ -1285,12 +1288,30 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) wacom->id[0] |= (wacom->serial[0] >> 32) & 0xFFFFF; } + /* number of valid frames */ for (i = 0; i < pen_frames; i++) { unsigned char *frame = &data[i*pen_frame_len + 1]; bool valid = frame[0] & 0x80; + + if (valid) + number_of_valid_frames++; + } + + if (number_of_valid_frames) { + if (wacom->hid_data.time_delayed) + time_interval = ktime_get() - wacom->hid_data.time_delayed; + time_interval /= number_of_valid_frames; + wacom->hid_data.time_delayed = time_packet_received; + } + + for (i = 0; i < number_of_valid_frames; i++) { + unsigned char *frame = &data[i*pen_frame_len + 1]; + bool valid = frame[0] & 0x80; bool prox = frame[0] & 0x40; bool range = frame[0] & 0x20; bool invert = frame[0] & 0x10; + int frames_number_reversed = number_of_valid_frames - i - 1; + int event_timestamp = time_packet_received - frames_number_reversed * time_interval; if (!valid) continue; @@ -1303,6 +1324,7 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) wacom->tool[0] = 0; wacom->id[0] = 0; wacom->serial[0] = 0; + wacom->hid_data.time_delayed = 0; return; } @@ -1339,6 +1361,7 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) get_unaligned_le16(&frame[11])); } } + if (wacom->tool[0]) { input_report_abs(pen_input, ABS_PRESSURE, get_unaligned_le16(&frame[5])); if (wacom->features.type == INTUOSP2_BT || @@ -1362,6 +1385,9 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) wacom->shared->stylus_in_proximity = prox; + /* add timestamp to unpack the frames */ + input_set_timestamp(pen_input, event_timestamp); + input_sync(pen_input); } } diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index ca172efcf072..88badfbae999 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -320,6 +320,7 @@ struct hid_data { int bat_connected; int ps_connected; bool pad_input_event_flag; + int time_delayed; }; struct wacom_remote_data { From 0cb6e9e7d3f1694ee55227f89a968ea4694db759 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 3 Sep 2021 09:51:36 +0200 Subject: [PATCH 3027/4345] KVM: x86: hyper-v: Avoid calling kvm_make_vcpus_request_mask() with vcpu_mask==NULL commit 6470accc7ba948b0b3aca22b273fe84ec638a116 upstream. In preparation to making kvm_make_vcpus_request_mask() use for_each_set_bit() switch kvm_hv_flush_tlb() to calling kvm_make_all_cpus_request() for 'all cpus' case. Note: kvm_make_all_cpus_request() (unlike kvm_make_vcpus_request_mask()) currently dynamically allocates cpumask on each call and this is suboptimal. Both kvm_make_all_cpus_request() and kvm_make_vcpus_request_mask() are going to be switched to using pre-allocated per-cpu masks. Reviewed-by: Sean Christopherson Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini Message-Id: <20210903075141.403071-4-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini Acked-by: Sean Christopherson Fixes: 6100066358ee ("KVM: Optimize kvm_make_vcpus_request_mask() a bit") Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/hyperv.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 09ec1cda2d68..e03e320847cd 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1562,16 +1562,19 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, cpumask_clear(&hv_vcpu->tlb_flush); - vcpu_mask = all_cpus ? NULL : - sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, - vp_bitmap, vcpu_bitmap); - /* * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't * analyze it here, flush TLB regardless of the specified address space. */ - kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, - NULL, vcpu_mask, &hv_vcpu->tlb_flush); + if (all_cpus) { + kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH_GUEST); + } else { + vcpu_mask = sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, + vp_bitmap, vcpu_bitmap); + + kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, + NULL, vcpu_mask, &hv_vcpu->tlb_flush); + } ret_success: /* We always do full TLB flush, set rep_done = rep_cnt. */ From 529f41f0eb1ef995bfa83c121c3cfe3a0720119a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 7 Jun 2022 10:09:03 -0400 Subject: [PATCH 3028/4345] KVM: x86: do not report a vCPU as preempted outside instruction boundaries commit 6cd88243c7e03845a450795e134b488fc2afb736 upstream. If a vCPU is outside guest mode and is scheduled out, it might be in the process of making a memory access. A problem occurs if another vCPU uses the PV TLB flush feature during the period when the vCPU is scheduled out, and a virtual address has already been translated but has not yet been accessed, because this is equivalent to using a stale TLB entry. To avoid this, only report a vCPU as preempted if sure that the guest is at an instruction boundary. A rescheduling request will be delivered to the host physical CPU as an external interrupt, so for simplicity consider any vmexit *not* instruction boundary except for external interrupts. It would in principle be okay to report the vCPU as preempted also if it is sleeping in kvm_vcpu_block(): a TLB flush IPI will incur the vmentry/vmexit overhead unnecessarily, and optimistic spinning is also unlikely to succeed. However, leave it for later because right now kvm_vcpu_check_block() is doing memory accesses. Even though the TLB flush issue only applies to virtual memory address, it's very much preferrable to be conservative. Reported-by: Jann Horn Signed-off-by: Paolo Bonzini [OP: use VCPU_STAT() for debugfs entries] Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/svm/svm.c | 2 ++ arch/x86/kvm/vmx/vmx.c | 1 + arch/x86/kvm/x86.c | 22 ++++++++++++++++++++++ 4 files changed, 28 insertions(+) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 660012ab7bfa..af4b4d3c6ff6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -553,6 +553,7 @@ struct kvm_vcpu_arch { u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; + bool at_instruction_boundary; bool tpr_access_reporting; bool xsaves_enabled; u64 ia32_xss; @@ -1061,6 +1062,8 @@ struct kvm_vcpu_stat { u64 req_event; u64 halt_poll_success_ns; u64 halt_poll_fail_ns; + u64 preemption_reported; + u64 preemption_other; }; struct x86_instruction_info; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5775983fec56..7b2b61309d8a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3983,6 +3983,8 @@ out: static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + vcpu->arch.at_instruction_boundary = true; } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d65cc9363567..9aedc7b06da7 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6510,6 +6510,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) return; handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + vcpu->arch.at_instruction_boundary = true; } static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0ccc8d1b972c..c1351335d22f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -231,6 +231,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("l1d_flush", l1d_flush), VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), + VCPU_STAT("preemption_reported", preemption_reported), + VCPU_STAT("preemption_other", preemption_other), VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), VM_STAT("mmu_pte_write", mmu_pte_write), VM_STAT("mmu_pde_zapped", mmu_pde_zapped), @@ -4052,6 +4054,19 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) struct kvm_host_map map; struct kvm_steal_time *st; + /* + * The vCPU can be marked preempted if and only if the VM-Exit was on + * an instruction boundary and will not trigger guest emulation of any + * kind (see vcpu_run). Vendor specific code controls (conservatively) + * when this is true, for example allowing the vCPU to be marked + * preempted if and only if the VM-Exit was due to a host interrupt. + */ + if (!vcpu->arch.at_instruction_boundary) { + vcpu->stat.preemption_other++; + return; + } + + vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -9357,6 +9372,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.l1tf_flush_l1d = true; for (;;) { + /* + * If another guest vCPU requests a PV TLB flush in the middle + * of instruction emulation, the rest of the emulation could + * use a stale page translation. Assume that any code after + * this point can start executing an instruction. + */ + vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { From 5d356d902e9d5b1aaaaf2326d365340fa8a90c1b Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Mon, 16 Jan 2023 10:00:15 +0800 Subject: [PATCH 3029/4345] ext4: fix WARNING in mb_find_extent commit fa08a7b61dff8a4df11ff1e84abfc214b487caf7 upstream. Syzbot found the following issue: EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support! EXT4-fs (loop0): orphan cleanup on readonly fs ------------[ cut here ]------------ WARNING: CPU: 1 PID: 5067 at fs/ext4/mballoc.c:1869 mb_find_extent+0x8a1/0xe30 Modules linked in: CPU: 1 PID: 5067 Comm: syz-executor307 Not tainted 6.2.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 RIP: 0010:mb_find_extent+0x8a1/0xe30 fs/ext4/mballoc.c:1869 RSP: 0018:ffffc90003c9e098 EFLAGS: 00010293 RAX: ffffffff82405731 RBX: 0000000000000041 RCX: ffff8880783457c0 RDX: 0000000000000000 RSI: 0000000000000041 RDI: 0000000000000040 RBP: 0000000000000040 R08: ffffffff82405723 R09: ffffed10053c9402 R10: ffffed10053c9402 R11: 1ffff110053c9401 R12: 0000000000000000 R13: ffffc90003c9e538 R14: dffffc0000000000 R15: ffffc90003c9e2cc FS: 0000555556665300(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000056312f6796f8 CR3: 0000000022437000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ext4_mb_complex_scan_group+0x353/0x1100 fs/ext4/mballoc.c:2307 ext4_mb_regular_allocator+0x1533/0x3860 fs/ext4/mballoc.c:2735 ext4_mb_new_blocks+0xddf/0x3db0 fs/ext4/mballoc.c:5605 ext4_ext_map_blocks+0x1868/0x6880 fs/ext4/extents.c:4286 ext4_map_blocks+0xa49/0x1cc0 fs/ext4/inode.c:651 ext4_getblk+0x1b9/0x770 fs/ext4/inode.c:864 ext4_bread+0x2a/0x170 fs/ext4/inode.c:920 ext4_quota_write+0x225/0x570 fs/ext4/super.c:7105 write_blk fs/quota/quota_tree.c:64 [inline] get_free_dqblk+0x34a/0x6d0 fs/quota/quota_tree.c:130 do_insert_tree+0x26b/0x1aa0 fs/quota/quota_tree.c:340 do_insert_tree+0x722/0x1aa0 fs/quota/quota_tree.c:375 do_insert_tree+0x722/0x1aa0 fs/quota/quota_tree.c:375 do_insert_tree+0x722/0x1aa0 fs/quota/quota_tree.c:375 dq_insert_tree fs/quota/quota_tree.c:401 [inline] qtree_write_dquot+0x3b6/0x530 fs/quota/quota_tree.c:420 v2_write_dquot+0x11b/0x190 fs/quota/quota_v2.c:358 dquot_acquire+0x348/0x670 fs/quota/dquot.c:444 ext4_acquire_dquot+0x2dc/0x400 fs/ext4/super.c:6740 dqget+0x999/0xdc0 fs/quota/dquot.c:914 __dquot_initialize+0x3d0/0xcf0 fs/quota/dquot.c:1492 ext4_process_orphan+0x57/0x2d0 fs/ext4/orphan.c:329 ext4_orphan_cleanup+0xb60/0x1340 fs/ext4/orphan.c:474 __ext4_fill_super fs/ext4/super.c:5516 [inline] ext4_fill_super+0x81cd/0x8700 fs/ext4/super.c:5644 get_tree_bdev+0x400/0x620 fs/super.c:1282 vfs_get_tree+0x88/0x270 fs/super.c:1489 do_new_mount+0x289/0xad0 fs/namespace.c:3145 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x2d3/0x3c0 fs/namespace.c:3674 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Add some debug information: mb_find_extent: mb_find_extent block=41, order=0 needed=64 next=0 ex=0/41/1@3735929054 64 64 7 block_bitmap: ff 3f 0c 00 fc 01 00 00 d2 3d 00 00 00 00 00 00 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff Acctually, blocks per group is 64, but block bitmap indicate at least has 128 blocks. Now, ext4_validate_block_bitmap() didn't check invalid block's bitmap if set. To resolve above issue, add check like fsck "Padding at end of block bitmap is not set". Cc: stable@kernel.org Reported-by: syzbot+68223fe9f6c95ad43bed@syzkaller.appspotmail.com Signed-off-by: Ye Bin Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230116020015.1506120-1-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/balloc.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 1afd60fcd772..50a0e90e8af9 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -303,6 +303,22 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, return desc; } +static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, + ext4_group_t block_group, + struct buffer_head *bh) +{ + ext4_grpblk_t next_zero_bit; + unsigned long bitmap_size = sb->s_blocksize * 8; + unsigned int offset = num_clusters_in_group(sb, block_group); + + if (bitmap_size <= offset) + return 0; + + next_zero_bit = ext4_find_next_zero_bit(bh->b_data, bitmap_size, offset); + + return (next_zero_bit < bitmap_size ? next_zero_bit : 0); +} + /* * Return the block number which was discovered to be invalid, or 0 if * the block bitmap is valid. @@ -401,6 +417,15 @@ static int ext4_validate_block_bitmap(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSCORRUPTED; } + blk = ext4_valid_block_bitmap_padding(sb, block_group, bh); + if (unlikely(blk != 0)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: block %llu: padding at end of block bitmap is not set", + block_group, blk); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); + return -EFSCORRUPTED; + } set_buffer_verified(bh); verified: ext4_unlock_group(sb, block_group); From 0dde3141c527b09b96bef1e7eeb18b8127810ce9 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Thu, 4 May 2023 12:15:25 +0000 Subject: [PATCH 3030/4345] ext4: avoid a potential slab-out-of-bounds in ext4_group_desc_csum commit 4f04351888a83e595571de672e0a4a8b74f4fb31 upstream. When modifying the block device while it is mounted by the filesystem, syzbot reported the following: BUG: KASAN: slab-out-of-bounds in crc16+0x206/0x280 lib/crc16.c:58 Read of size 1 at addr ffff888075f5c0a8 by task syz-executor.2/15586 CPU: 1 PID: 15586 Comm: syz-executor.2 Not tainted 6.2.0-rc5-syzkaller-00205-gc96618275234 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x290 lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:306 print_report+0x107/0x1f0 mm/kasan/report.c:417 kasan_report+0xcd/0x100 mm/kasan/report.c:517 crc16+0x206/0x280 lib/crc16.c:58 ext4_group_desc_csum+0x81b/0xb20 fs/ext4/super.c:3187 ext4_group_desc_csum_set+0x195/0x230 fs/ext4/super.c:3210 ext4_mb_clear_bb fs/ext4/mballoc.c:6027 [inline] ext4_free_blocks+0x191a/0x2810 fs/ext4/mballoc.c:6173 ext4_remove_blocks fs/ext4/extents.c:2527 [inline] ext4_ext_rm_leaf fs/ext4/extents.c:2710 [inline] ext4_ext_remove_space+0x24ef/0x46a0 fs/ext4/extents.c:2958 ext4_ext_truncate+0x177/0x220 fs/ext4/extents.c:4416 ext4_truncate+0xa6a/0xea0 fs/ext4/inode.c:4342 ext4_setattr+0x10c8/0x1930 fs/ext4/inode.c:5622 notify_change+0xe50/0x1100 fs/attr.c:482 do_truncate+0x200/0x2f0 fs/open.c:65 handle_truncate fs/namei.c:3216 [inline] do_open fs/namei.c:3561 [inline] path_openat+0x272b/0x2dd0 fs/namei.c:3714 do_filp_open+0x264/0x4f0 fs/namei.c:3741 do_sys_openat2+0x124/0x4e0 fs/open.c:1310 do_sys_open fs/open.c:1326 [inline] __do_sys_creat fs/open.c:1402 [inline] __se_sys_creat fs/open.c:1396 [inline] __x64_sys_creat+0x11f/0x160 fs/open.c:1396 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f72f8a8c0c9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f72f97e3168 EFLAGS: 00000246 ORIG_RAX: 0000000000000055 RAX: ffffffffffffffda RBX: 00007f72f8bac050 RCX: 00007f72f8a8c0c9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000020000280 RBP: 00007f72f8ae7ae9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffd165348bf R14: 00007f72f97e3300 R15: 0000000000022000 Replace le16_to_cpu(sbi->s_es->s_desc_size) with sbi->s_desc_size It reduces ext4's compiled text size, and makes the code more efficient (we remove an extra indirect reference and a potential byte swap on big endian systems), and there is no downside. It also avoids the potential KASAN / syzkaller failure, as a bonus. Reported-by: syzbot+fc51227e7100c9294894@syzkaller.appspotmail.com Reported-by: syzbot+8785e41224a3afd04321@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=70d28d11ab14bd7938f3e088365252aa923cff42 Link: https://syzkaller.appspot.com/bug?id=b85721b38583ecc6b5e72ff524c67302abbc30f3 Link: https://lore.kernel.org/all/000000000000ece18705f3b20934@google.com/ Fixes: 717d50e4971b ("Ext4: Uninitialized Block Groups") Cc: stable@vger.kernel.org Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20230504121525.3275886-1-tudor.ambarus@linaro.org Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/super.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e940fb07ef2e..ba445afbd617 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2831,11 +2831,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ - if (ext4_has_feature_64bit(sb) && - offset < le16_to_cpu(sbi->s_es->s_desc_size)) + if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, - le16_to_cpu(sbi->s_es->s_desc_size) - - offset); + sbi->s_desc_size - offset); out: return cpu_to_le16(crc); From 4aa7f744fa3727818991802ac58331d188389b75 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 4 May 2023 14:55:24 +0200 Subject: [PATCH 3031/4345] ext4: fix data races when using cached status extents commit 492888df0c7b42fc0843631168b0021bc4caee84 upstream. When using cached extent stored in extent status tree in tree->cache_es another process holding ei->i_es_lock for reading can be racing with us setting new value of tree->cache_es. If the compiler would decide to refetch tree->cache_es at an unfortunate moment, it could result in a bogus in_range() check. Fix the possible race by using READ_ONCE() when using tree->cache_es only under ei->i_es_lock for reading. Cc: stable@kernel.org Reported-by: syzbot+4a03518df1e31b537066@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/000000000000d3b33905fa0fd4a6@google.com Suggested-by: Dmitry Vyukov Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230504125524.10802-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/extents_status.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index aa99a3659edf..fee54ab42bba 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -269,14 +269,12 @@ static void __es_find_extent_range(struct inode *inode, /* see if the extent has been cached */ es->es_lblk = es->es_len = es->es_pblk = 0; - if (tree->cache_es) { - es1 = tree->cache_es; - if (in_range(lblk, es1->es_lblk, es1->es_len)) { - es_debug("%u cached by [%u/%u) %llu %x\n", - lblk, es1->es_lblk, es1->es_len, - ext4_es_pblock(es1), ext4_es_status(es1)); - goto out; - } + es1 = READ_ONCE(tree->cache_es); + if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { + es_debug("%u cached by [%u/%u) %llu %x\n", + lblk, es1->es_lblk, es1->es_len, + ext4_es_pblock(es1), ext4_es_status(es1)); + goto out; } es1 = __es_tree_search(&tree->root, lblk); @@ -295,7 +293,7 @@ out: } if (es1 && matching_fn(es1)) { - tree->cache_es = es1; + WRITE_ONCE(tree->cache_es, es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; @@ -934,14 +932,12 @@ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, /* find extent in cache firstly */ es->es_lblk = es->es_len = es->es_pblk = 0; - if (tree->cache_es) { - es1 = tree->cache_es; - if (in_range(lblk, es1->es_lblk, es1->es_len)) { - es_debug("%u cached by [%u/%u)\n", - lblk, es1->es_lblk, es1->es_len); - found = 1; - goto out; - } + es1 = READ_ONCE(tree->cache_es); + if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { + es_debug("%u cached by [%u/%u)\n", + lblk, es1->es_lblk, es1->es_len); + found = 1; + goto out; } node = tree->root.rb_node; From 08838aeefa6fd310cddf8218fddda0a90fdf069e Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Fri, 5 May 2023 21:24:29 +0800 Subject: [PATCH 3032/4345] ext4: check iomap type only if ext4_iomap_begin() does not fail commit fa83c34e3e56b3c672af38059e066242655271b1 upstream. When ext4_iomap_overwrite_begin() calls ext4_iomap_begin() map blocks may fail for some reason (e.g. memory allocation failure, bare disk write), and later because "iomap->type ! = IOMAP_MAPPED" triggers WARN_ON(). When ext4 iomap_begin() returns an error, it is normal that the type of iomap->type may not match the expectation. Therefore, we only determine if iomap->type is as expected when ext4_iomap_begin() is executed successfully. Cc: stable@kernel.org Reported-by: syzbot+08106c4b7d60702dbc14@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/00000000000015760b05f9b4eee9@google.com Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230505132429.714648-1-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a93b93de5a60..735109b9e88d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3564,7 +3564,7 @@ static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset, */ flags &= ~IOMAP_WRITE; ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap); - WARN_ON_ONCE(iomap->type != IOMAP_MAPPED); + WARN_ON_ONCE(!ret && iomap->type != IOMAP_MAPPED); return ret; } From 37c69da3adc45fc34df0b8d07a158a6fa5b2a3f7 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 5 May 2023 22:20:29 -0400 Subject: [PATCH 3033/4345] ext4: improve error recovery code paths in __ext4_remount() commit 4c0b4818b1f636bc96359f7817a2d8bab6370162 upstream. If there are failures while changing the mount options in __ext4_remount(), we need to restore the old mount options. This commit fixes two problem. The first is there is a chance that we will free the old quota file names before a potential failure leading to a use-after-free. The second problem addressed in this commit is if there is a failed read/write to read-only transition, if the quota has already been suspended, we need to renable quota handling. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230506142419.984260-2-tytso@mit.edu Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/super.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ba445afbd617..8694be513241 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6028,9 +6028,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } #ifdef CONFIG_QUOTA - /* Release old quota file names */ - for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(old_opts.s_qf_names[i]); if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); @@ -6040,6 +6037,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } } + /* Release old quota file names */ + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(old_opts.s_qf_names[i]); #endif if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); @@ -6059,6 +6059,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) return 0; restore_opts: + /* + * If there was a failing r/w to ro transition, we may need to + * re-enable quota + */ + if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) && + sb_any_quota_suspended(sb)) + dquot_resume(sb, -1); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; From 5f8b55136ad787aed2c184f7cb3e93772ae637a3 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 6 May 2023 21:04:01 -0400 Subject: [PATCH 3034/4345] ext4: fix deadlock when converting an inline directory in nojournal mode commit f4ce24f54d9cca4f09a395f3eecce20d6bec4663 upstream. In no journal mode, ext4_finish_convert_inline_dir() can self-deadlock by calling ext4_handle_dirty_dirblock() when it already has taken the directory lock. There is a similar self-deadlock in ext4_incvert_inline_data_nolock() for data files which we'll fix at the same time. A simple reproducer demonstrating the problem: mke2fs -Fq -t ext2 -O inline_data -b 4k /dev/vdc 64 mount -t ext4 -o dirsync /dev/vdc /vdc cd /vdc mkdir file0 cd file0 touch file0 touch file1 attr -s BurnSpaceInEA -V abcde . touch supercalifragilisticexpialidocious Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230507021608.1290720-1-tytso@mit.edu Reported-by: syzbot+91dccab7c64e2850a4e5@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=ba84cc80a9491d65416bc7877e1650c87530fe8a Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inline.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 0758f606f006..fd0567d0219c 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1172,6 +1172,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, ext4_initialize_dirent_tail(dir_block, inode->i_sb->s_blocksize); set_buffer_uptodate(dir_block); + unlock_buffer(dir_block); err = ext4_handle_dirty_dirblock(handle, inode, dir_block); if (err) return err; @@ -1245,6 +1246,7 @@ static int ext4_convert_inline_data_nolock(handle_t *handle, if (!S_ISDIR(inode->i_mode)) { memcpy(data_bh->b_data, buf, inline_size); set_buffer_uptodate(data_bh); + unlock_buffer(data_bh); error = ext4_handle_dirty_metadata(handle, inode, data_bh); } else { @@ -1252,7 +1254,6 @@ static int ext4_convert_inline_data_nolock(handle_t *handle, buf, inline_size); } - unlock_buffer(data_bh); out_restore: if (error) ext4_restore_inline_data(handle, inode, iloc, buf, inline_size); From 4597554b4f7b29e7fd78aa449bab648f8da4ee2c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 12 May 2023 15:11:02 -0400 Subject: [PATCH 3035/4345] ext4: add bounds checking in get_max_inline_xattr_value_size() commit 2220eaf90992c11d888fe771055d4de330385f01 upstream. Normally the extended attributes in the inode body would have been checked when the inode is first opened, but if someone is writing to the block device while the file system is mounted, it's possible for the inode table to get corrupted. Add bounds checking to avoid reading beyond the end of allocated memory if this happens. Reported-by: syzbot+1966db24521e5f6e23f7@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=1966db24521e5f6e23f7 Cc: stable@kernel.org Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inline.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index fd0567d0219c..d0bd1046f4a0 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -32,6 +32,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; + void *end; int free, min_offs; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) @@ -55,14 +56,23 @@ static int get_max_inline_xattr_value_size(struct inode *inode, raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); entry = IFIRST(header); + end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; /* Compute min_offs. */ - for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { + while (!IS_LAST_ENTRY(entry)) { + void *next = EXT4_XATTR_NEXT(entry); + + if (next >= end) { + EXT4_ERROR_INODE(inode, + "corrupt xattr in inline inode"); + return 0; + } if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; } + entry = next; } free = min_offs - ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32); From d88fe8e6112696238deeaf09820db183663eabca Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 12 May 2023 15:16:27 -0400 Subject: [PATCH 3036/4345] ext4: bail out of ext4_xattr_ibody_get() fails for any reason commit 2a534e1d0d1591e951f9ece2fb460b2ff92edabd upstream. In ext4_update_inline_data(), if ext4_xattr_ibody_get() fails for any reason, it's best if we just fail as opposed to stumbling on, especially if the failure is EFSCORRUPTED. Cc: stable@kernel.org Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inline.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index d0bd1046f4a0..979935c078fb 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -358,7 +358,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, error = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, len); - if (error == -ENODATA) + if (error < 0) goto out; BUFFER_TRACE(is.iloc.bh, "get_write_access"); From b0fc279de4bf17e1710bb7e83906538ff8f11111 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 29 Apr 2023 16:14:46 -0400 Subject: [PATCH 3037/4345] ext4: remove a BUG_ON in ext4_mb_release_group_pa() commit 463808f237cf73e98a1a45ff7460c2406a150a0b upstream. If a malicious fuzzer overwrites the ext4 superblock while it is mounted such that the s_first_data_block is set to a very large number, the calculation of the block group can underflow, and trigger a BUG_ON check. Change this to be an ext4_warning so that we don't crash the kernel. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230430154311.579720-3-tytso@mit.edu Reported-by: syzbot+e2efa3efc15a1c9e95c3@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=69b28112e098b070f639efb356393af3ffec4220 Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/mballoc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 843840c2aced..a7c42e4bfc5e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4250,7 +4250,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); - BUG_ON(group != e4b->bd_group && pa->pa_len != 0); + if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) { + ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu", + e4b->bd_group, group, pa->pa_pstart); + return 0; + } mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); From 1a8822343e67432b658145d2760a524c884da9d4 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 30 Apr 2023 03:04:13 -0400 Subject: [PATCH 3038/4345] ext4: fix invalid free tracking in ext4_xattr_move_to_block() commit b87c7cdf2bed4928b899e1ce91ef0d147017ba45 upstream. In ext4_xattr_move_to_block(), the value of the extended attribute which we need to move to an external block may be allocated by kvmalloc() if the value is stored in an external inode. So at the end of the function the code tried to check if this was the case by testing entry->e_value_inum. However, at this point, the pointer to the xattr entry is no longer valid, because it was removed from the original location where it had been stored. So we could end up calling kvfree() on a pointer which was not allocated by kvmalloc(); or we could also potentially leak memory by not freeing the buffer when it should be freed. Fix this by storing whether it should be freed in a separate variable. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230430160426.581366-1-tytso@mit.edu Link: https://syzkaller.appspot.com/bug?id=5c2aee8256e30b55ccf57312c16d88417adbd5e1 Link: https://syzkaller.appspot.com/bug?id=41a6b5d4917c0412eb3b3c3c604965bed7d7420b Reported-by: syzbot+64b645917ce07d89bde5@syzkaller.appspotmail.com Reported-by: syzbot+0d042627c4f2ad332195@syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 28fa9a64dc4b..abcba0255109 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2554,6 +2554,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); + int needs_kvfree = 0; int error; is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); @@ -2576,7 +2577,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, error = -ENOMEM; goto out; } - + needs_kvfree = 1; error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; @@ -2615,7 +2616,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, out: kfree(b_entry_name); - if (entry->e_value_inum && buffer) + if (needs_kvfree && buffer) kvfree(buffer); if (is) brelse(is->iloc.bh); From ef77d602e306489fc067a283306d752707ac75e8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Fri, 17 Mar 2023 13:33:18 +0200 Subject: [PATCH 3039/4345] serial: 8250: Fix serial8250_tx_empty() race with DMA Tx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 146a37e05d620cef4ad430e5d1c9c077fe6fa76f upstream. There's a potential race before THRE/TEMT deasserts when DMA Tx is starting up (or the next batch of continuous Tx is being submitted). This can lead to misdetecting Tx empty condition. It is entirely normal for THRE/TEMT to be set for some time after the DMA Tx had been setup in serial8250_tx_dma(). As Tx side is definitely not empty at that point, it seems incorrect for serial8250_tx_empty() claim Tx is empty. Fix the race by also checking in serial8250_tx_empty() whether there's DMA Tx active. Note: This fix only addresses in-kernel race mainly to make using TCSADRAIN/FLUSH robust. Userspace can still cause other races but they seem userspace concurrency control problems. Fixes: 9ee4b83e51f74 ("serial: 8250: Add support for dmaengine") Cc: stable@vger.kernel.org Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230317113318.31327-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250.h | 12 ++++++++++++ drivers/tty/serial/8250/8250_port.c | 12 +++++++++--- 2 files changed, 21 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index b6dc9003b8c4..0771cd226581 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -330,6 +330,13 @@ extern int serial8250_rx_dma(struct uart_8250_port *); extern void serial8250_rx_dma_flush(struct uart_8250_port *); extern int serial8250_request_dma(struct uart_8250_port *); extern void serial8250_release_dma(struct uart_8250_port *); + +static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) +{ + struct uart_8250_dma *dma = p->dma; + + return dma && dma->tx_running; +} #else static inline int serial8250_tx_dma(struct uart_8250_port *p) { @@ -345,6 +352,11 @@ static inline int serial8250_request_dma(struct uart_8250_port *p) return -1; } static inline void serial8250_release_dma(struct uart_8250_port *p) { } + +static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) +{ + return false; +} #endif static inline int ns16550a_goto_highspeed(struct uart_8250_port *up) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 1f9e4b87387b..b19908779e3b 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1971,19 +1971,25 @@ static int serial8250_tx_threshold_handle_irq(struct uart_port *port) static unsigned int serial8250_tx_empty(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); + unsigned int result = 0; unsigned long flags; unsigned int lsr; serial8250_rpm_get(up); spin_lock_irqsave(&port->lock, flags); - lsr = serial_port_in(port, UART_LSR); - up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; + if (!serial8250_tx_dma_running(up)) { + lsr = serial_port_in(port, UART_LSR); + up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; + + if ((lsr & BOTH_EMPTY) == BOTH_EMPTY) + result = TIOCSER_TEMT; + } spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); - return (lsr & BOTH_EMPTY) == BOTH_EMPTY ? TIOCSER_TEMT : 0; + return result; } unsigned int serial8250_do_get_mctrl(struct uart_port *port) From 01c0002ec7bdac9e49458aea6737a9edc0d220da Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christoph=20B=C3=B6hmwalder?= Date: Wed, 3 May 2023 14:19:37 +0200 Subject: [PATCH 3040/4345] drbd: correctly submit flush bio on barrier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 3899d94e3831ee07ea6821c032dc297aec80586a upstream. When we receive a flush command (or "barrier" in DRBD), we currently use a REQ_OP_FLUSH with the REQ_PREFLUSH flag set. The correct way to submit a flush bio is by using a REQ_OP_WRITE without any data, and set the REQ_PREFLUSH flag. Since commit b4a6bb3a67aa ("block: add a sanity check for non-write flush/fua bios"), this triggers a warning in the block layer, but this has been broken for quite some time before that. So use the correct set of flags to actually make the flush happen. Cc: Christoph Hellwig Cc: stable@vger.kernel.org Fixes: f9ff0da56437 ("drbd: allow parallel flushes for multi-volume resources") Reported-by: Thomas Voegtle Signed-off-by: Christoph Böhmwalder Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230503121937.17232-1-christoph.boehmwalder@linbit.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/drbd/drbd_receiver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index dc333dbe5232..405e09575f08 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1299,7 +1299,7 @@ static void submit_one_flush(struct drbd_device *device, struct issue_flush_cont bio_set_dev(bio, device->ldev->backing_bdev); bio->bi_private = octx; bio->bi_end_io = one_flush_endio; - bio->bi_opf = REQ_OP_FLUSH | REQ_PREFLUSH; + bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; device->flush_jif = jiffies; set_bit(FLUSH_PENDING, &device->flags); From 4b19cbdb1dd39874fc530250c588041609bdc11d Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 10 May 2023 18:15:39 +0000 Subject: [PATCH 3041/4345] KVM: x86: Ensure PV TLB flush tracepoint reflects KVM behavior From: Lai Jiangshan commit af3511ff7fa2107d6410831f3d71030f5e8d2b25 upstream. In record_steal_time(), st->preempted is read twice, and trace_kvm_pv_tlb_flush() might output result inconsistent if kvm_vcpu_flush_tlb_guest() see a different st->preempted later. It is a very trivial problem and hardly has actual harm and can be avoided by reseting and reading st->preempted in atomic way via xchg(). Signed-off-by: Lai Jiangshan Message-Id: <20210531174628.10265-1-jiangshanlai@gmail.com> Signed-off-by: Paolo Bonzini Signed-off-by: Rishabh Bhatnagar Tested-by: Allen Pais Acked-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c1351335d22f..d80c89d1971f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3041,9 +3041,11 @@ static void record_steal_time(struct kvm_vcpu *vcpu) * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { + u8 st_preempted = xchg(&st->preempted, 0); + trace_kvm_pv_tlb_flush(vcpu->vcpu_id, - st->preempted & KVM_VCPU_FLUSH_TLB); - if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) + st_preempted & KVM_VCPU_FLUSH_TLB); + if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); } else { st->preempted = 0; From ebd3010d42bad1deefab2990f909d96a774f2921 Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 10 May 2023 18:15:40 +0000 Subject: [PATCH 3042/4345] KVM: x86: Fix recording of guest steal time / preempted status From: David Woodhouse commit 7e2175ebd695f17860c5bd4ad7616cce12ed4591 upstream. In commit b043138246a4 ("x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed") we switched to using a gfn_to_pfn_cache for accessing the guest steal time structure in order to allow for an atomic xchg of the preempted field. This has a couple of problems. Firstly, kvm_map_gfn() doesn't work at all for IOMEM pages when the atomic flag is set, which it is in kvm_steal_time_set_preempted(). So a guest vCPU using an IOMEM page for its steal time would never have its preempted field set. Secondly, the gfn_to_pfn_cache is not invalidated in all cases where it should have been. There are two stages to the GFN->PFN conversion; first the GFN is converted to a userspace HVA, and then that HVA is looked up in the process page tables to find the underlying host PFN. Correct invalidation of the latter would require being hooked up to the MMU notifiers, but that doesn't happen---so it just keeps mapping and unmapping the *wrong* PFN after the userspace page tables change. In the !IOMEM case at least the stale page *is* pinned all the time it's cached, so it won't be freed and reused by anyone else while still receiving the steal time updates. The map/unmap dance only takes care of the KVM administrivia such as marking the page dirty. Until the gfn_to_pfn cache handles the remapping automatically by integrating with the MMU notifiers, we might as well not get a kernel mapping of it, and use the perfectly serviceable userspace HVA that we already have. We just need to implement the atomic xchg on the userspace address with appropriate exception handling, which is fairly trivial. Cc: stable@vger.kernel.org Fixes: b043138246a4 ("x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed") Signed-off-by: David Woodhouse Message-Id: <3645b9b889dac6438394194bb5586a46b68d581f.camel@infradead.org> [I didn't entirely agree with David's assessment of the usefulness of the gfn_to_pfn cache, and integrated the outcome of the discussion in the above commit message. - Paolo] Signed-off-by: Paolo Bonzini [risbhat@amazon.com: Use the older mark_page_dirty_in_slot api without kvm argument] Signed-off-by: Rishabh Bhatnagar Tested-by: Allen Pais Acked-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/x86.c | 105 +++++++++++++++++++++++--------- 2 files changed, 76 insertions(+), 31 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index af4b4d3c6ff6..3e9f1c820edb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -664,7 +664,7 @@ struct kvm_vcpu_arch { u8 preempted; u64 msr_val; u64 last_steal; - struct gfn_to_pfn_cache cache; + struct gfn_to_hva_cache cache; } st; u64 l1_tsc_offset; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d80c89d1971f..119447e31956 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3022,53 +3022,92 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) static void record_steal_time(struct kvm_vcpu *vcpu) { - struct kvm_host_map map; - struct kvm_steal_time *st; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + u64 steal; + u32 version; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - /* -EAGAIN is returned in atomic context so we can just return. */ - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, - &map, &vcpu->arch.st.cache, false)) + if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { + gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; + + /* We rely on the fact that it fits in a single page. */ + BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) || + kvm_is_error_hva(ghc->hva) || !ghc->memslot) + return; + } + + st = (struct kvm_steal_time __user *)ghc->hva; + if (!user_access_begin(st, sizeof(*st))) + return; /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { - u8 st_preempted = xchg(&st->preempted, 0); + u8 st_preempted = 0; + int err = -EFAULT; + + asm volatile("1: xchgb %0, %2\n" + "xor %1, %1\n" + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+r" (st_preempted), + "+&r" (err) + : "m" (st->preempted)); + if (err) + goto out; + + user_access_end(); + + vcpu->arch.st.preempted = 0; trace_kvm_pv_tlb_flush(vcpu->vcpu_id, st_preempted & KVM_VCPU_FLUSH_TLB); if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + + if (!user_access_begin(st, sizeof(*st))) + goto dirty; } else { - st->preempted = 0; + unsafe_put_user(0, &st->preempted, out); + vcpu->arch.st.preempted = 0; } - vcpu->arch.st.preempted = 0; + unsafe_get_user(version, &st->version, out); + if (version & 1) + version += 1; /* first time write, random junk */ - if (st->version & 1) - st->version += 1; /* first time write, random junk */ - - st->version += 1; + version += 1; + unsafe_put_user(version, &st->version, out); smp_wmb(); - st->steal += current->sched_info.run_delay - + unsafe_get_user(steal, &st->steal, out); + steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; + unsafe_put_user(steal, &st->steal, out); - smp_wmb(); + version += 1; + unsafe_put_user(version, &st->version, out); - st->version += 1; - - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); + out: + user_access_end(); + dirty: + mark_page_dirty_in_slot(ghc->memslot, gpa_to_gfn(ghc->gpa)); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -4053,8 +4092,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { - struct kvm_host_map map; - struct kvm_steal_time *st; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + static const u8 preempted = KVM_VCPU_PREEMPTED; /* * The vCPU can be marked preempted if and only if the VM-Exit was on @@ -4075,16 +4116,23 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, - &vcpu->arch.st.cache, true)) + /* This happens on process exit */ + if (unlikely(current->mm != vcpu->kvm->mm)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + slots = kvm_memslots(vcpu->kvm); - st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) + return; - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); + st = (struct kvm_steal_time __user *)ghc->hva; + BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted)); + + if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted))) + vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + + mark_page_dirty_in_slot(ghc->memslot, gpa_to_gfn(ghc->gpa)); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -10266,11 +10314,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; int idx; - kvm_release_pfn(cache->pfn, cache->dirty, cache); - kvmclock_reset(vcpu); kvm_x86_ops.vcpu_free(vcpu); From 8e39c2f407aff06a5968fc5e923e0b080f78f869 Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 10 May 2023 18:15:41 +0000 Subject: [PATCH 3043/4345] KVM: Fix steal time asm constraints From: David Woodhouse commit 964b7aa0b040bdc6ec1c543ee620cda3f8b4c68a upstream. In 64-bit mode, x86 instruction encoding allows us to use the low 8 bits of any GPR as an 8-bit operand. In 32-bit mode, however, we can only use the [abcd] registers. For which, GCC has the "q" constraint instead of the less restrictive "r". Also fix st->preempted, which is an input/output operand rather than an input. Fixes: 7e2175ebd695 ("KVM: x86: Fix recording of guest steal time / preempted status") Reported-by: kernel test robot Signed-off-by: David Woodhouse Message-Id: <89bf72db1b859990355f9c40713a34e0d2d86c98.camel@infradead.org> Signed-off-by: Paolo Bonzini Signed-off-by: Rishabh Bhatnagar Tested-by: Allen Pais Acked-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 119447e31956..40162a8757b2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3064,9 +3064,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu) "xor %1, %1\n" "2:\n" _ASM_EXTABLE_UA(1b, 2b) - : "+r" (st_preempted), - "+&r" (err) - : "m" (st->preempted)); + : "+q" (st_preempted), + "+&r" (err), + "+m" (st->preempted)); if (err) goto out; From 029662004359364428d6cca688acb0441189af1b Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 10 May 2023 18:15:42 +0000 Subject: [PATCH 3044/4345] KVM: x86: Remove obsolete disabling of page faults in kvm_arch_vcpu_put() From: Sean Christopherson commit 19979fba9bfaeab427a8e106d915f0627c952828 upstream. Remove the disabling of page faults across kvm_steal_time_set_preempted() as KVM now accesses the steal time struct (shared with the guest) via a cached mapping (see commit b043138246a4, "x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed".) The cache lookup is flagged as atomic, thus it would be a bug if KVM tried to resolve a new pfn, i.e. we want the splat that would be reached via might_fault(). Signed-off-by: Sean Christopherson Message-Id: <20210123000334.3123628-2-seanjc@google.com> Signed-off-by: Paolo Bonzini Signed-off-by: Rishabh Bhatnagar Tested-by: Allen Pais Acked-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 40162a8757b2..3881bf7d1ac4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4142,15 +4142,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) if (vcpu->preempted) vcpu->arch.preempted_in_kernel = !kvm_x86_ops.get_cpl(vcpu); - /* - * Disable page faults because we're in atomic context here. - * kvm_write_guest_offset_cached() would call might_fault() - * that relies on pagefault_disable() to tell if there's a - * bug. NOTE: the write to guest memory may not go through if - * during postcopy live migration or if there's heavy guest - * paging. - */ - pagefault_disable(); /* * kvm_memslots() will be called by * kvm_write_guest_offset_cached() so take the srcu lock. @@ -4158,7 +4149,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_steal_time_set_preempted(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, idx); - pagefault_enable(); kvm_x86_ops.vcpu_put(vcpu); vcpu->arch.last_host_tsc = rdtsc(); /* From e10a73f5380958629b4ae8d2ecad29f3e82a1b7f Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 10 May 2023 18:15:43 +0000 Subject: [PATCH 3045/4345] KVM: x86: do not set st->preempted when going back to user space From: Paolo Bonzini commit 54aa83c90198e68eee8b0850c749bc70efb548da upstream. Similar to the Xen path, only change the vCPU's reported state if the vCPU was actually preempted. The reason for KVM's behavior is that for example optimistic spinning might not be a good idea if the guest is doing repeated exits to userspace; however, it is confusing and unlikely to make a difference, because well-tuned guests will hardly ever exit KVM_RUN in the first place. Suggested-by: Sean Christopherson Signed-off-by: Paolo Bonzini [risbhat@amazon.com: Don't check for xen msr as support is not available and skip the SEV-ES condition] Signed-off-by: Rishabh Bhatnagar Tested-by: Allen Pais Acked-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3881bf7d1ac4..116a225fb26e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4139,16 +4139,18 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { int idx; - if (vcpu->preempted) + if (vcpu->preempted) { vcpu->arch.preempted_in_kernel = !kvm_x86_ops.get_cpl(vcpu); - /* - * kvm_memslots() will be called by - * kvm_write_guest_offset_cached() so take the srcu lock. - */ - idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_steal_time_set_preempted(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_steal_time_set_preempted(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + } + kvm_x86_ops.vcpu_put(vcpu); vcpu->arch.last_host_tsc = rdtsc(); /* From 4bffae22bec7e035e9d5a0c0db7286b6bd258f56 Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 10 May 2023 18:15:45 +0000 Subject: [PATCH 3046/4345] KVM: x86: revalidate steal time cache if MSR value changes From: Paolo Bonzini commit 901d3765fa804ce42812f1d5b1f3de2dfbb26723 upstream. Commit 7e2175ebd695 ("KVM: x86: Fix recording of guest steal time / preempted status", 2021-11-11) open coded the previous call to kvm_map_gfn, but in doing so it dropped the comparison between the cached guest physical address and the one in the MSR. This cause an incorrect cache hit if the guest modifies the steal time address while the memslots remain the same. This can happen with kexec, in which case the steal time data is written at the address used by the old kernel instead of the old one. While at it, rename the variable from gfn to gpa since it is a plain physical address and not a right-shifted one. Reported-by: Dave Young Reported-by: Xiaoying Yan Analyzed-by: Dr. David Alan Gilbert Cc: David Woodhouse Cc: stable@vger.kernel.org Fixes: 7e2175ebd695 ("KVM: x86: Fix recording of guest steal time / preempted status") Signed-off-by: Paolo Bonzini Signed-off-by: Rishabh Bhatnagar Tested-by: Allen Pais Acked-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 116a225fb26e..0503bb8b64e5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3025,6 +3025,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu) struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; struct kvm_steal_time __user *st; struct kvm_memslots *slots; + gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; u64 steal; u32 version; @@ -3037,13 +3038,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu) slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || + gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { - gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; - /* We rely on the fact that it fits in a single page. */ BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) || + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st)) || kvm_is_error_hva(ghc->hva) || !ghc->memslot) return; } From 85cfbaa575eaa843a15ab2d54b953196c2189b2f Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 10 May 2023 18:15:46 +0000 Subject: [PATCH 3047/4345] KVM: x86: do not report preemption if the steal time cache is stale From: Paolo Bonzini commit c3c28d24d910a746b02f496d190e0e8c6560224b upstream. Commit 7e2175ebd695 ("KVM: x86: Fix recording of guest steal time / preempted status", 2021-11-11) open coded the previous call to kvm_map_gfn, but in doing so it dropped the comparison between the cached guest physical address and the one in the MSR. This cause an incorrect cache hit if the guest modifies the steal time address while the memslots remain the same. This can happen with kexec, in which case the preempted bit is written at the address used by the old kernel instead of the old one. Cc: David Woodhouse Cc: stable@vger.kernel.org Fixes: 7e2175ebd695 ("KVM: x86: Fix recording of guest steal time / preempted status") Signed-off-by: Paolo Bonzini Signed-off-by: Rishabh Bhatnagar Tested-by: Allen Pais Acked-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0503bb8b64e5..8461aa63c251 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4096,6 +4096,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) struct kvm_steal_time __user *st; struct kvm_memslots *slots; static const u8 preempted = KVM_VCPU_PREEMPTED; + gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; /* * The vCPU can be marked preempted if and only if the VM-Exit was on @@ -4123,6 +4124,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || + gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) return; From fcfe05990a5ce95361dbcae308632861d3c40dfd Mon Sep 17 00:00:00 2001 From: Rishabh Bhatnagar Date: Wed, 10 May 2023 18:15:47 +0000 Subject: [PATCH 3048/4345] KVM: x86: move guest_pv_has out of user_access section From: Paolo Bonzini commit 3e067fd8503d6205aa0c1c8f48f6b209c592d19c upstream. When UBSAN is enabled, the code emitted for the call to guest_pv_has includes a call to __ubsan_handle_load_invalid_value. objtool complains that this call happens with UACCESS enabled; to avoid the warning, pull the calls to user_access_begin into both arms of the "if" statement, after the check for guest_pv_has. Reported-by: Stephen Rothwell Cc: David Woodhouse Signed-off-by: Paolo Bonzini Signed-off-by: Rishabh Bhatnagar Tested-by: Allen Pais Acked-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8461aa63c251..5fbae8cc0697 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3049,9 +3049,6 @@ static void record_steal_time(struct kvm_vcpu *vcpu) } st = (struct kvm_steal_time __user *)ghc->hva; - if (!user_access_begin(st, sizeof(*st))) - return; - /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. @@ -3060,6 +3057,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu) u8 st_preempted = 0; int err = -EFAULT; + if (!user_access_begin(st, sizeof(*st))) + return; + asm volatile("1: xchgb %0, %2\n" "xor %1, %1\n" "2:\n" @@ -3082,6 +3082,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu) if (!user_access_begin(st, sizeof(*st))) goto dirty; } else { + if (!user_access_begin(st, sizeof(*st))) + return; + unsafe_put_user(0, &st->preempted, out); vcpu->arch.st.preempted = 0; } From 32232bcd4e5300e678718d5c29da4dfa07ade01e Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sun, 14 May 2023 13:41:27 +0900 Subject: [PATCH 3049/4345] printk: declare printk_deferred_{enter,safe}() in include/linux/printk.h commit 85e3e7fbbb720b9897fba9a99659e31cbd1c082e upstream. [This patch implements subset of original commit 85e3e7fbbb72 ("printk: remove NMI tracking") where commit 1007843a9190 ("mm/page_alloc: fix potential deadlock on zonelist_update_seq seqlock") depends on, for commit 3d36424b3b58 ("mm/page_alloc: fix race condition between build_all_zonelists and page allocation") was backported to stable.] All NMI contexts are handled the same as the safe context: store the message and defer printing. There is no need to have special NMI context tracking for this. Using in_nmi() is enough. There are several parts of the kernel that are manually calling into the printk NMI context tracking in order to cause general printk deferred printing: arch/arm/kernel/smp.c arch/powerpc/kexec/crash.c kernel/trace/trace.c For arm/kernel/smp.c and powerpc/kexec/crash.c, provide a new function pair printk_deferred_enter/exit that explicitly achieves the same objective. For ftrace, remove the printk context manipulation completely. It was added in commit 03fc7f9c99c1 ("printk/nmi: Prevent deadlock when accessing the main log buffer in NMI"). The purpose was to enforce storing messages directly into the ring buffer even in NMI context. It really should have only modified the behavior in NMI context. There is no need for a special behavior any longer. All messages are always stored directly now. The console deferring is handled transparently in vprintk(). Signed-off-by: John Ogness [pmladek@suse.com: Remove special handling in ftrace.c completely. Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20210715193359.25946-5-john.ogness@linutronix.de [penguin-kernel: Copy only printk_deferred_{enter,safe}() definition ] Signed-off-by: Tetsuo Handa Signed-off-by: Greg Kroah-Hartman --- include/linux/printk.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/include/linux/printk.h b/include/linux/printk.h index fe7eb2351610..344f6da3d4c3 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -623,4 +623,23 @@ static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type, #define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \ print_hex_dump_debug(prefix_str, prefix_type, 16, 1, buf, len, true) +#ifdef CONFIG_PRINTK +extern void __printk_safe_enter(void); +extern void __printk_safe_exit(void); +/* + * The printk_deferred_enter/exit macros are available only as a hack for + * some code paths that need to defer all printk console printing. Interrupts + * must be disabled for the deferred duration. + */ +#define printk_deferred_enter __printk_safe_enter +#define printk_deferred_exit __printk_safe_exit +#else +static inline void printk_deferred_enter(void) +{ +} +static inline void printk_deferred_exit(void) +{ +} +#endif + #endif From f2656f437fb1981646d806a314df6eb937feba4f Mon Sep 17 00:00:00 2001 From: Tian Tao Date: Mon, 15 Mar 2021 19:49:37 +0800 Subject: [PATCH 3050/4345] drm/exynos: move to use request_irq by IRQF_NO_AUTOEN flag commit a4e5eed2c6a689ef2b6ad8d7ae86665c69039379 upstream. After this patch cbe16f35bee68 genirq: Add IRQF_NO_AUTOEN for request_irq/nmi() is merged. request_irq() after setting IRQ_NOAUTOEN as below irq_set_status_flags(irq, IRQ_NOAUTOEN); request_irq(dev, irq...); can be replaced by request_irq() with IRQF_NO_AUTOEN flag. v2: Fix the problem of using wrong flags Signed-off-by: Tian Tao Signed-off-by: Inki Dae Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 4 ++-- drivers/gpu/drm/exynos/exynos_drm_dsi.c | 7 +++---- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 1f79bc2a881e..c277d2fc50c6 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -775,8 +775,8 @@ static int decon_conf_irq(struct decon_context *ctx, const char *name, return irq; } } - irq_set_status_flags(irq, IRQ_NOAUTOEN); - ret = devm_request_irq(ctx->dev, irq, handler, flags, "drm_decon", ctx); + ret = devm_request_irq(ctx->dev, irq, handler, + flags | IRQF_NO_AUTOEN, "drm_decon", ctx); if (ret < 0) { dev_err(ctx->dev, "IRQ %s request failed\n", name); return ret; diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 5b9666fc7af1..afb03de2880f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1353,10 +1353,9 @@ static int exynos_dsi_register_te_irq(struct exynos_dsi *dsi, } te_gpio_irq = gpio_to_irq(dsi->te_gpio); - irq_set_status_flags(te_gpio_irq, IRQ_NOAUTOEN); ret = request_threaded_irq(te_gpio_irq, exynos_dsi_te_irq_handler, NULL, - IRQF_TRIGGER_RISING, "TE", dsi); + IRQF_TRIGGER_RISING | IRQF_NO_AUTOEN, "TE", dsi); if (ret) { dev_err(dsi->dev, "request interrupt failed with %d\n", ret); gpio_free(dsi->te_gpio); @@ -1802,9 +1801,9 @@ static int exynos_dsi_probe(struct platform_device *pdev) if (dsi->irq < 0) return dsi->irq; - irq_set_status_flags(dsi->irq, IRQ_NOAUTOEN); ret = devm_request_threaded_irq(dev, dsi->irq, NULL, - exynos_dsi_irq, IRQF_ONESHOT, + exynos_dsi_irq, + IRQF_ONESHOT | IRQF_NO_AUTOEN, dev_name(dev), dsi); if (ret) { dev_err(dev, "failed to request dsi irq\n"); From a992c387b41186ab968fd176ca26b432b05c53ec Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 4 Apr 2023 23:31:58 +0900 Subject: [PATCH 3051/4345] mm/page_alloc: fix potential deadlock on zonelist_update_seq seqlock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1007843a91909a4995ee78a538f62d8665705b66 upstream. syzbot is reporting circular locking dependency which involves zonelist_update_seq seqlock [1], for this lock is checked by memory allocation requests which do not need to be retried. One deadlock scenario is kmalloc(GFP_ATOMIC) from an interrupt handler. CPU0 ---- __build_all_zonelists() { write_seqlock(&zonelist_update_seq); // makes zonelist_update_seq.seqcount odd // e.g. timer interrupt handler runs at this moment some_timer_func() { kmalloc(GFP_ATOMIC) { __alloc_pages_slowpath() { read_seqbegin(&zonelist_update_seq) { // spins forever because zonelist_update_seq.seqcount is odd } } } } // e.g. timer interrupt handler finishes write_sequnlock(&zonelist_update_seq); // makes zonelist_update_seq.seqcount even } This deadlock scenario can be easily eliminated by not calling read_seqbegin(&zonelist_update_seq) from !__GFP_DIRECT_RECLAIM allocation requests, for retry is applicable to only __GFP_DIRECT_RECLAIM allocation requests. But Michal Hocko does not know whether we should go with this approach. Another deadlock scenario which syzbot is reporting is a race between kmalloc(GFP_ATOMIC) from tty_insert_flip_string_and_push_buffer() with port->lock held and printk() from __build_all_zonelists() with zonelist_update_seq held. CPU0 CPU1 ---- ---- pty_write() { tty_insert_flip_string_and_push_buffer() { __build_all_zonelists() { write_seqlock(&zonelist_update_seq); build_zonelists() { printk() { vprintk() { vprintk_default() { vprintk_emit() { console_unlock() { console_flush_all() { console_emit_next_record() { con->write() = serial8250_console_write() { spin_lock_irqsave(&port->lock, flags); tty_insert_flip_string() { tty_insert_flip_string_fixed_flag() { __tty_buffer_request_room() { tty_buffer_alloc() { kmalloc(GFP_ATOMIC | __GFP_NOWARN) { __alloc_pages_slowpath() { zonelist_iter_begin() { read_seqbegin(&zonelist_update_seq); // spins forever because zonelist_update_seq.seqcount is odd spin_lock_irqsave(&port->lock, flags); // spins forever because port->lock is held } } } } } } } } spin_unlock_irqrestore(&port->lock, flags); // message is printed to console spin_unlock_irqrestore(&port->lock, flags); } } } } } } } } } write_sequnlock(&zonelist_update_seq); } } } This deadlock scenario can be eliminated by preventing interrupt context from calling kmalloc(GFP_ATOMIC) and preventing printk() from calling console_flush_all() while zonelist_update_seq.seqcount is odd. Since Petr Mladek thinks that __build_all_zonelists() can become a candidate for deferring printk() [2], let's address this problem by disabling local interrupts in order to avoid kmalloc(GFP_ATOMIC) and disabling synchronous printk() in order to avoid console_flush_all() . As a side effect of minimizing duration of zonelist_update_seq.seqcount being odd by disabling synchronous printk(), latency at read_seqbegin(&zonelist_update_seq) for both !__GFP_DIRECT_RECLAIM and __GFP_DIRECT_RECLAIM allocation requests will be reduced. Although, from lockdep perspective, not calling read_seqbegin(&zonelist_update_seq) (i.e. do not record unnecessary locking dependency) from interrupt context is still preferable, even if we don't allow calling kmalloc(GFP_ATOMIC) inside write_seqlock(&zonelist_update_seq)/write_sequnlock(&zonelist_update_seq) section... Link: https://lkml.kernel.org/r/8796b95c-3da3-5885-fddd-6ef55f30e4d3@I-love.SAKURA.ne.jp Fixes: 3d36424b3b58 ("mm/page_alloc: fix race condition between build_all_zonelists and page allocation") Link: https://lkml.kernel.org/r/ZCrs+1cDqPWTDFNM@alley [2] Reported-by: syzbot Link: https://syzkaller.appspot.com/bug?extid=223c7461c58c58a4cb10 [1] Signed-off-by: Tetsuo Handa Acked-by: Michal Hocko Acked-by: Mel Gorman Cc: Petr Mladek Cc: David Hildenbrand Cc: Ilpo Järvinen Cc: John Ogness Cc: Patrick Daly Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/page_alloc.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1fd41b91a1a8..d85435db35f3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5973,7 +5973,21 @@ static void __build_all_zonelists(void *data) int nid; int __maybe_unused cpu; pg_data_t *self = data; + unsigned long flags; + /* + * Explicitly disable this CPU's interrupts before taking seqlock + * to prevent any IRQ handler from calling into the page allocator + * (e.g. GFP_ATOMIC) that could hit zonelist_iter_begin and livelock. + */ + local_irq_save(flags); + /* + * Explicitly disable this CPU's synchronous printk() before taking + * seqlock to prevent any printk() from trying to hold port->lock, for + * tty_insert_flip_string_and_push_buffer() on other CPU might be + * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held. + */ + printk_deferred_enter(); write_seqlock(&zonelist_update_seq); #ifdef CONFIG_NUMA @@ -6008,6 +6022,8 @@ static void __build_all_zonelists(void *data) } write_sequnlock(&zonelist_update_seq); + printk_deferred_exit(); + local_irq_restore(flags); } static noinline void __init From 3ebe5d6d69ceba8e20b0b74e43192a6c8b49d4f0 Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Fri, 24 Mar 2023 10:42:37 -0400 Subject: [PATCH 3052/4345] drm/amd/display: Fix hang when skipping modeset commit da5e14909776edea4462672fb4a3007802d262e7 upstream. [Why&How] When skipping full modeset since the only state change was a front porch change, the DC commit sequence requires extra checks to handle non existant plane states being asked to be removed from context. Reviewed-by: Alvin Lee Acked-by: Qingqing Zhuo Signed-off-by: Aurabindo Pillai Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 5 ++++- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 3 +++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index dbdf0e210522..3ca1ee396e4c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7248,6 +7248,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, continue; dc_plane = dm_new_plane_state->dc_state; + if (!dc_plane) + continue; bundle->surface_updates[planes_count].surface = dc_plane; if (new_pcrtc_state->color_mgmt_changed) { @@ -8562,8 +8564,9 @@ static int dm_update_plane_state(struct dc *dc, return -EINVAL; } + if (dm_old_plane_state->dc_state) + dc_plane_state_release(dm_old_plane_state->dc_state); - dc_plane_state_release(dm_old_plane_state->dc_state); dm_new_plane_state->dc_state = NULL; *lock_and_validation_needed = true; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 1e47afc4ccc1..f1eda1a6496d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1502,6 +1502,9 @@ bool dc_remove_plane_from_context( struct dc_stream_status *stream_status = NULL; struct resource_pool *pool = dc->res_pool; + if (!plane_state) + return true; + for (i = 0; i < context->stream_count; i++) if (context->streams[i] == stream) { stream_status = &context->stream_status[i]; From 4c893ff55907c61456bcb917781c0dd687a1e123 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 17 May 2023 11:48:20 +0200 Subject: [PATCH 3053/4345] Linux 5.10.180 Link: https://lore.kernel.org/r/20230515161736.775969473@linuxfoundation.org Tested-by: Chris Paterson (CIP) Tested-by: Shuah Khan Tested-by: Sudip Mukherjee Tested-by: Guenter Roeck Tested-by: Jon Hunter Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 3ddcade4be8f..c2f8e1644abd 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 179 +SUBLEVEL = 180 EXTRAVERSION = NAME = Dare mighty things From 97aa93c23f62dff5896c6b1b160c353abfb2be71 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 28 Dec 2022 18:46:51 -0800 Subject: [PATCH 3054/4345] ANDROID: uid_sys_stats: defer process_notifier work if uid_lock is contended process_notifier() is called every time a process exits. When multiple processes exit roughly at the same time, the uid_lock taken from inside of process_notifier() will create contention which slows down process exit. Defer stats accounting in such case to avoid lock contention. Bug: 261537194 Change-Id: Ia1e9a451eab39eb0dda7eb175bfd71c67f3e0a58 Signed-off-by: Suren Baghdasaryan (cherry picked from commit 5d96c24be923d9011762de19bcfbade68b103759) --- drivers/misc/uid_sys_stats.c | 112 ++++++++++++++++++++++++++++------- 1 file changed, 90 insertions(+), 22 deletions(-) diff --git a/drivers/misc/uid_sys_stats.c b/drivers/misc/uid_sys_stats.c index 47336700f687..985e7b02ab3c 100644 --- a/drivers/misc/uid_sys_stats.c +++ b/drivers/misc/uid_sys_stats.c @@ -77,12 +77,12 @@ struct uid_entry { #endif }; -static u64 compute_write_bytes(struct task_struct *task) +static u64 compute_write_bytes(struct task_io_accounting *ioac) { - if (task->ioac.write_bytes <= task->ioac.cancelled_write_bytes) + if (ioac->write_bytes <= ioac->cancelled_write_bytes) return 0; - return task->ioac.write_bytes - task->ioac.cancelled_write_bytes; + return ioac->write_bytes - ioac->cancelled_write_bytes; } static void compute_io_bucket_stats(struct io_stats *io_bucket, @@ -239,17 +239,16 @@ static void set_io_uid_tasks_zero(struct uid_entry *uid_entry) } } -static void add_uid_tasks_io_stats(struct uid_entry *uid_entry, - struct task_struct *task, int slot) +static void add_uid_tasks_io_stats(struct task_entry *task_entry, + struct task_io_accounting *ioac, int slot) { - struct task_entry *task_entry = find_or_register_task(uid_entry, task); struct io_stats *task_io_slot = &task_entry->io[slot]; - task_io_slot->read_bytes += task->ioac.read_bytes; - task_io_slot->write_bytes += compute_write_bytes(task); - task_io_slot->rchar += task->ioac.rchar; - task_io_slot->wchar += task->ioac.wchar; - task_io_slot->fsync += task->ioac.syscfs; + task_io_slot->read_bytes += ioac->read_bytes; + task_io_slot->write_bytes += compute_write_bytes(ioac); + task_io_slot->rchar += ioac->rchar; + task_io_slot->wchar += ioac->wchar; + task_io_slot->fsync += ioac->syscfs; } static void compute_io_uid_tasks(struct uid_entry *uid_entry) @@ -290,8 +289,6 @@ static void show_io_uid_tasks(struct seq_file *m, struct uid_entry *uid_entry) #else static void remove_uid_tasks(struct uid_entry *uid_entry) {}; static void set_io_uid_tasks_zero(struct uid_entry *uid_entry) {}; -static void add_uid_tasks_io_stats(struct uid_entry *uid_entry, - struct task_struct *task, int slot) {}; static void compute_io_uid_tasks(struct uid_entry *uid_entry) {}; static void show_io_uid_tasks(struct seq_file *m, struct uid_entry *uid_entry) {} @@ -446,23 +443,32 @@ static const struct proc_ops uid_remove_fops = { .proc_write = uid_remove_write, }; +static void __add_uid_io_stats(struct uid_entry *uid_entry, + struct task_io_accounting *ioac, int slot) +{ + struct io_stats *io_slot = &uid_entry->io[slot]; + + io_slot->read_bytes += ioac->read_bytes; + io_slot->write_bytes += compute_write_bytes(ioac); + io_slot->rchar += ioac->rchar; + io_slot->wchar += ioac->wchar; + io_slot->fsync += ioac->syscfs; +} static void add_uid_io_stats(struct uid_entry *uid_entry, struct task_struct *task, int slot) { - struct io_stats *io_slot = &uid_entry->io[slot]; + struct task_entry *task_entry __maybe_unused; /* avoid double accounting of dying threads */ if (slot != UID_STATE_DEAD_TASKS && (task->flags & PF_EXITING)) return; - io_slot->read_bytes += task->ioac.read_bytes; - io_slot->write_bytes += compute_write_bytes(task); - io_slot->rchar += task->ioac.rchar; - io_slot->wchar += task->ioac.wchar; - io_slot->fsync += task->ioac.syscfs; - - add_uid_tasks_io_stats(uid_entry, task, slot); +#ifdef CONFIG_UID_SYS_STATS_DEBUG + task_entry = find_or_register_task(uid_entry, task); + add_uid_tasks_io_stats(task_entry, &task->ioac, slot); +#endif + __add_uid_io_stats(uid_entry, &task->ioac, slot); } static void update_io_stats_all_locked(void) @@ -622,6 +628,48 @@ static const struct proc_ops uid_procstat_fops = { .proc_write = uid_procstat_write, }; +struct update_stats_work { + struct work_struct work; + uid_t uid; +#ifdef CONFIG_UID_SYS_STATS_DEBUG + struct task_struct *task; +#endif + struct task_io_accounting ioac; + u64 utime; + u64 stime; +}; + +static void update_stats_workfn(struct work_struct *work) +{ + struct update_stats_work *usw = + container_of(work, struct update_stats_work, work); + struct uid_entry *uid_entry; + struct task_entry *task_entry __maybe_unused; + + rt_mutex_lock(&uid_lock); + uid_entry = find_uid_entry(usw->uid); + if (!uid_entry) + goto exit; + + uid_entry->utime += usw->utime; + uid_entry->stime += usw->stime; + +#ifdef CONFIG_UID_SYS_STATS_DEBUG + task_entry = find_task_entry(uid_entry, usw->task); + if (!task_entry) + goto exit; + add_uid_tasks_io_stats(task_entry, &usw->ioac, + UID_STATE_DEAD_TASKS); +#endif + __add_uid_io_stats(uid_entry, &usw->ioac, UID_STATE_DEAD_TASKS); +exit: + rt_mutex_unlock(&uid_lock); +#ifdef CONFIG_UID_SYS_STATS_DEBUG + put_task_struct(usw->task); +#endif + kfree(usw); +} + static int process_notifier(struct notifier_block *self, unsigned long cmd, void *v) { @@ -633,8 +681,28 @@ static int process_notifier(struct notifier_block *self, if (!task) return NOTIFY_OK; - rt_mutex_lock(&uid_lock); uid = from_kuid_munged(current_user_ns(), task_uid(task)); + if (!rt_mutex_trylock(&uid_lock)) { + struct update_stats_work *usw; + + usw = kmalloc(sizeof(struct update_stats_work), GFP_KERNEL); + if (usw) { + INIT_WORK(&usw->work, update_stats_workfn); + usw->uid = uid; +#ifdef CONFIG_UID_SYS_STATS_DEBUG + usw->task = get_task_struct(task); +#endif + /* + * Copy task->ioac since task might be destroyed before + * the work is later performed. + */ + usw->ioac = task->ioac; + task_cputime_adjusted(task, &usw->utime, &usw->stime); + schedule_work(&usw->work); + } + return NOTIFY_OK; + } + uid_entry = find_or_register_uid(uid); if (!uid_entry) { pr_err("%s: failed to find uid %d\n", __func__, uid); From 9d8c9d868ed9b83913fa5cc890648d5c43c42f2a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 30 Apr 2023 03:04:13 -0400 Subject: [PATCH 3055/4345] UPSTREAM: ext4: fix invalid free tracking in ext4_xattr_move_to_block() commit b87c7cdf2bed4928b899e1ce91ef0d147017ba45 upstream. In ext4_xattr_move_to_block(), the value of the extended attribute which we need to move to an external block may be allocated by kvmalloc() if the value is stored in an external inode. So at the end of the function the code tried to check if this was the case by testing entry->e_value_inum. However, at this point, the pointer to the xattr entry is no longer valid, because it was removed from the original location where it had been stored. So we could end up calling kvfree() on a pointer which was not allocated by kvmalloc(); or we could also potentially leak memory by not freeing the buffer when it should be freed. Fix this by storing whether it should be freed in a separate variable. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230430160426.581366-1-tytso@mit.edu Link: https://syzkaller.appspot.com/bug?id=5c2aee8256e30b55ccf57312c16d88417adbd5e1 Link: https://syzkaller.appspot.com/bug?id=41a6b5d4917c0412eb3b3c3c604965bed7d7420b Reported-by: syzbot+64b645917ce07d89bde5@syzkaller.appspotmail.com Reported-by: syzbot+0d042627c4f2ad332195@syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman Bug: 281332515 Bug: 281333738 Change-Id: Id1fbcc337821d66df53c2826bf3158963f8b0673 Signed-off-by: Tudor Ambarus --- fs/ext4/xattr.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 6fee044fd158..36461b86bd39 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2543,6 +2543,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); + int needs_kvfree = 0; int error; is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); @@ -2565,7 +2566,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, error = -ENOMEM; goto out; } - + needs_kvfree = 1; error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; @@ -2604,7 +2605,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, out: kfree(b_entry_name); - if (entry->e_value_inum && buffer) + if (needs_kvfree && buffer) kvfree(buffer); if (is) brelse(is->iloc.bh); From f03258701de3b1fcb07edeee252d8cd9fe2f9793 Mon Sep 17 00:00:00 2001 From: Seiya Wang Date: Fri, 19 May 2023 10:09:24 +0800 Subject: [PATCH 3056/4345] ANDROID: GKI: Update symbol list for mtk 3 Added functions: [A] 'function int pci_prepare_to_sleep(pci_dev*)' [A] 'function void phy_ethtool_get_wol(phy_device*, ethtool_wolinfo*)' [A] 'function void phy_support_asym_pause(phy_device*)' Bug: 283291448 Signed-off-by: Seiya Wang Change-Id: I73c677c32326f7ab5db7b7cd1c11d3e7311444ab --- android/abi_gki_aarch64.xml | 232 +++++++++++++++++++----------------- android/abi_gki_aarch64_mtk | 3 + 2 files changed, 127 insertions(+), 108 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 94f6ea7547dc..7fd62874c6b4 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -4076,6 +4076,7 @@ + @@ -4165,6 +4166,7 @@ + @@ -4211,6 +4213,7 @@ + @@ -130848,10 +130851,10 @@ - - - - + + + + @@ -138932,6 +138935,10 @@ + + + + @@ -139380,6 +139387,11 @@ + + + + + @@ -139613,6 +139625,10 @@ + + + + @@ -147192,28 +147208,28 @@ - - - + + + - - - + + + - - - + + + - - - + + + - - + + @@ -147221,19 +147237,19 @@ - - - - - + + + + + - - - - - - + + + + + + @@ -147243,13 +147259,13 @@ - - - + + + - - + + @@ -147258,31 +147274,31 @@ - - + + - - + + - - - + + + - - + + - - + + - - - - + + + + @@ -147314,91 +147330,91 @@ - - - - - - - + + + + + + + - - - - - - - + + + + + + + - - - - - - - - + + + + + + + + - - - - - - + + + + + + - - - - - - + + + + + + - - - - - - - + + + + + + + - - + + - - + + - - + + - - + + - - + + - - + + - - + + - - - - + + + + diff --git a/android/abi_gki_aarch64_mtk b/android/abi_gki_aarch64_mtk index 2ac7b11faf77..c27c6a7df54b 100644 --- a/android/abi_gki_aarch64_mtk +++ b/android/abi_gki_aarch64_mtk @@ -1478,6 +1478,7 @@ pci_generic_config_write32 pci_lock_rescan_remove pci_pio_to_address + pci_prepare_to_sleep pci_unlock_rescan_remove PDE_DATA __per_cpu_offset @@ -1499,6 +1500,7 @@ phy_drivers_register phy_drivers_unregister phy_ethtool_get_link_ksettings + phy_ethtool_get_wol phy_ethtool_nway_reset phy_ethtool_set_link_ksettings phy_exit @@ -1518,6 +1520,7 @@ phy_set_mode_ext phy_start phy_stop + phy_support_asym_pause phy_write_paged pid_task pinconf_generic_parse_dt_config From 64c7044d39e4cff7882aa8e2c7c72f624cec9445 Mon Sep 17 00:00:00 2001 From: Peifeng Li Date: Mon, 8 May 2023 14:52:00 +0800 Subject: [PATCH 3057/4345] ANDROID: vendor_hook: add hooks in dm_bufio.c 1. android_vh_dm_bufio_shrink_scan_bypass To adjust dm_bufio-buffer shrinker's policy in some cases. 2. cleanup_old_buffers_bypass To adjust the policy of dm_bufio-buffer periodic eviction in some cases. Bug: 281467813 Signed-off-by: Peifeng Li Change-Id: I29a9d91d18d2e279170533db83b59cfc3b17ebe2 --- drivers/android/vendor_hooks.c | 2 ++ drivers/md/dm-bufio.c | 17 +++++++++++++++++ include/trace/hooks/mm.h | 8 ++++++++ 3 files changed, 27 insertions(+) diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index 5702bf54e0e6..2ce349294f3d 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -275,6 +275,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_commit_creds); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_exit_creds); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_override_creds); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_revert_creds); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_dm_bufio_shrink_scan_bypass); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_cleanup_old_buffers_bypass); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_record_mutex_lock_starttime); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_record_rtmutex_lock_starttime); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_record_rwsem_lock_starttime); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 50f3e673729c..bb0e3ddde093 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -19,6 +19,8 @@ #include #include +#include + #define DM_MSG_PREFIX "bufio" /* @@ -1683,6 +1685,13 @@ static void shrink_work(struct work_struct *w) static unsigned long dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct dm_bufio_client *c; + bool bypass = false; + + trace_android_vh_dm_bufio_shrink_scan_bypass( + dm_bufio_current_allocated, + &bypass); + if (bypass) + return 0; c = container_of(shrink, struct dm_bufio_client, shrinker); atomic_long_add(sc->nr_to_scan, &c->need_shrink); @@ -2009,6 +2018,14 @@ static void cleanup_old_buffers(void) { unsigned long max_age_hz = get_max_age_hz(); struct dm_bufio_client *c; + bool bypass = false; + + trace_android_vh_cleanup_old_buffers_bypass( + dm_bufio_current_allocated, + &max_age_hz, + &bypass); + if (bypass) + return; mutex_lock(&dm_bufio_clients_lock); diff --git a/include/trace/hooks/mm.h b/include/trace/hooks/mm.h index a4b855e0a81a..8fecbc8b3d5b 100644 --- a/include/trace/hooks/mm.h +++ b/include/trace/hooks/mm.h @@ -126,6 +126,14 @@ DECLARE_HOOK(android_vh_save_track_hash, DECLARE_HOOK(android_vh_vmpressure, TP_PROTO(struct mem_cgroup *memcg, bool *bypass), TP_ARGS(memcg, bypass)); +DECLARE_HOOK(android_vh_dm_bufio_shrink_scan_bypass, + TP_PROTO(unsigned long dm_bufio_current_allocated, bool *bypass), + TP_ARGS(dm_bufio_current_allocated, bypass)); +DECLARE_HOOK(android_vh_cleanup_old_buffers_bypass, + TP_PROTO(unsigned long dm_bufio_current_allocated, + unsigned long *max_age_hz, + bool *bypass), + TP_ARGS(dm_bufio_current_allocated, max_age_hz, bypass)); DECLARE_HOOK(android_vh_mem_cgroup_alloc, TP_PROTO(struct mem_cgroup *memcg), TP_ARGS(memcg)); From f60101a030a87da7f9193358ac6c9a386de761de Mon Sep 17 00:00:00 2001 From: Peifeng Li Date: Tue, 23 May 2023 09:29:29 +0800 Subject: [PATCH 3058/4345] ANDROID: GKI: Update symbols to symbol list Leaf changes summary: 4 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 2 Added functions Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 2 Added variables 2 Added functions: [A] 'function int __traceiter_android_vh_cleanup_old_buffers_bypass(void*, unsigned long int, unsigned long int*, bool*)' [A] 'function int __traceiter_android_vh_dm_bufio_shrink_scan_bypass(void*, unsigned long int, bool*)' 2 Added variables: [A] 'tracepoint __tracepoint_android_vh_cleanup_old_buffers_bypass' [A] 'tracepoint __tracepoint_android_vh_dm_bufio_shrink_scan_bypass' Bug: 281467813 Signed-off-by: Peifeng Li Change-Id: I804fcea959bc982934002056e09aaabe26ac1ea0 --- android/abi_gki_aarch64.xml | 631 +++++++++++++++++----------------- android/abi_gki_aarch64_oplus | 4 + 2 files changed, 329 insertions(+), 306 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 7fd62874c6b4..736c2e117d48 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -464,6 +464,7 @@ + @@ -485,6 +486,7 @@ + @@ -6518,6 +6520,7 @@ + @@ -6539,6 +6542,7 @@ + @@ -116456,9 +116460,9 @@ - + - + @@ -118215,17 +118219,17 @@ - - - - + + + + - - - - - + + + + + @@ -118406,12 +118410,12 @@ - - - - - - + + + + + + @@ -118492,19 +118496,19 @@ - - - - - + + + + + - - - - - - + + + + + + @@ -118516,10 +118520,10 @@ - - - - + + + + @@ -118932,10 +118936,10 @@ - - - - + + + + @@ -118945,11 +118949,11 @@ - - - - - + + + + + @@ -118976,22 +118980,22 @@ - - - - - - - + + + + + + + - - - - - - - + + + + + + + @@ -119008,17 +119012,17 @@ - - - - + + + + - - - - - + + + + + @@ -119272,6 +119276,13 @@ + + + + + + + @@ -119299,10 +119310,10 @@ - - - - + + + + @@ -119311,27 +119322,27 @@ - - - + + + - - - + + + - - - - - + + + + + - - - - + + + + @@ -119391,11 +119402,11 @@ - - - - - + + + + + @@ -119404,6 +119415,12 @@ + + + + + + @@ -119411,12 +119428,12 @@ - - - - - - + + + + + + @@ -119426,9 +119443,9 @@ - - - + + + @@ -119437,22 +119454,22 @@ - - - - - - - - + + + + + + + + - - - - - - + + + + + + @@ -119533,17 +119550,17 @@ - - - - + + + + - - - - - + + + + + @@ -119651,12 +119668,12 @@ - - - - - - + + + + + + @@ -119675,10 +119692,10 @@ - - - - + + + + @@ -119703,10 +119720,10 @@ - - - - + + + + @@ -119786,11 +119803,11 @@ - - - - - + + + + + @@ -119805,24 +119822,24 @@ - - - - - - + + + + + + - - - - + + + + - - - - + + + + @@ -119835,9 +119852,9 @@ - - - + + + @@ -119847,31 +119864,31 @@ - - - + + + - - - - + + + + - - - - + + + + - - - + + + - - - + + + @@ -119879,10 +119896,10 @@ - - - - + + + + @@ -119895,10 +119912,10 @@ - - - - + + + + @@ -119989,10 +120006,10 @@ - - - - + + + + @@ -120003,17 +120020,17 @@ - - - - - + + + + + - - - - + + + + @@ -120041,10 +120058,10 @@ - - - - + + + + @@ -120080,10 +120097,10 @@ - - - - + + + + @@ -120110,9 +120127,9 @@ - - - + + + @@ -120360,9 +120377,9 @@ - - - + + + @@ -120391,9 +120408,9 @@ - - - + + + @@ -120440,10 +120457,10 @@ - - - - + + + + @@ -120469,22 +120486,22 @@ - - - - - + + + + + - - - + + + - - - - + + + + @@ -120499,9 +120516,9 @@ - - - + + + @@ -120534,12 +120551,12 @@ - - - - - - + + + + + + @@ -120661,19 +120678,19 @@ - - - - + + + + - - - - - - - + + + + + + + @@ -120724,9 +120741,9 @@ - - - + + + @@ -121166,8 +121183,8 @@ - - + + @@ -121194,7 +121211,7 @@ - + @@ -121207,10 +121224,10 @@ - - + + - + @@ -121276,18 +121293,18 @@ - + - + - - + + - - + + @@ -121325,16 +121342,17 @@ + - + - - - - + + + + @@ -121344,15 +121362,16 @@ - + + - + - + - - + + @@ -121365,8 +121384,8 @@ - - + + @@ -121384,15 +121403,15 @@ - + - + - + @@ -121405,24 +121424,24 @@ - + - - - + + + - + - - - - - + + + + + - + - + @@ -121438,27 +121457,27 @@ - + - - + + - + - + - + @@ -121502,12 +121521,12 @@ - + - + @@ -121515,23 +121534,23 @@ - + - - - + + + - + - + @@ -121550,8 +121569,8 @@ - - + + @@ -121559,7 +121578,7 @@ - + diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index 9544ea84c8f1..bd21cf7d3005 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -2793,6 +2793,7 @@ __traceiter_android_vh_clear_mask_adjust __traceiter_android_vh_clear_reserved_fmt_fields __traceiter_android_vh_cma_drain_all_pages_bypass + __traceiter_android_vh_cleanup_old_buffers_bypass __traceiter_android_vh_commit_creds __traceiter_android_vh_cpufreq_acct_update_power __traceiter_android_vh_cpufreq_fast_switch @@ -2806,6 +2807,7 @@ __traceiter_android_vh_do_page_trylock __traceiter_android_vh_do_send_sig_info __traceiter_android_vh_do_traversal_lruvec + __traceiter_android_vh_dm_bufio_shrink_scan_bypass __traceiter_android_vh_drain_all_pages_bypass __traceiter_android_vh_em_cpu_energy __traceiter_android_vh_exclude_reserved_zone @@ -3047,6 +3049,7 @@ __tracepoint_android_vh_clear_mask_adjust __tracepoint_android_vh_clear_reserved_fmt_fields __tracepoint_android_vh_cma_drain_all_pages_bypass + __tracepoint_android_vh_cleanup_old_buffers_bypass __tracepoint_android_vh_commit_creds __tracepoint_android_vh_cpufreq_acct_update_power __tracepoint_android_vh_cpufreq_fast_switch @@ -3056,6 +3059,7 @@ __tracepoint_android_vh_cpu_idle_exit __tracepoint_android_vh_cpu_up __tracepoint_android_vh_del_page_from_lrulist + __tracepoint_android_vh_dm_bufio_shrink_scan_bypass __tracepoint_android_vh_do_futex __tracepoint_android_vh_do_page_trylock __tracepoint_android_vh_do_send_sig_info From 948b2a120560fe65be16202edf43744e33a61928 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Thu, 4 May 2023 12:15:25 +0000 Subject: [PATCH 3059/4345] UPSTREAM: ext4: avoid a potential slab-out-of-bounds in ext4_group_desc_csum commit 4f04351888a83e595571de672e0a4a8b74f4fb31 upstream. When modifying the block device while it is mounted by the filesystem, syzbot reported the following: BUG: KASAN: slab-out-of-bounds in crc16+0x206/0x280 lib/crc16.c:58 Read of size 1 at addr ffff888075f5c0a8 by task syz-executor.2/15586 CPU: 1 PID: 15586 Comm: syz-executor.2 Not tainted 6.2.0-rc5-syzkaller-00205-gc96618275234 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x290 lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:306 print_report+0x107/0x1f0 mm/kasan/report.c:417 kasan_report+0xcd/0x100 mm/kasan/report.c:517 crc16+0x206/0x280 lib/crc16.c:58 ext4_group_desc_csum+0x81b/0xb20 fs/ext4/super.c:3187 ext4_group_desc_csum_set+0x195/0x230 fs/ext4/super.c:3210 ext4_mb_clear_bb fs/ext4/mballoc.c:6027 [inline] ext4_free_blocks+0x191a/0x2810 fs/ext4/mballoc.c:6173 ext4_remove_blocks fs/ext4/extents.c:2527 [inline] ext4_ext_rm_leaf fs/ext4/extents.c:2710 [inline] ext4_ext_remove_space+0x24ef/0x46a0 fs/ext4/extents.c:2958 ext4_ext_truncate+0x177/0x220 fs/ext4/extents.c:4416 ext4_truncate+0xa6a/0xea0 fs/ext4/inode.c:4342 ext4_setattr+0x10c8/0x1930 fs/ext4/inode.c:5622 notify_change+0xe50/0x1100 fs/attr.c:482 do_truncate+0x200/0x2f0 fs/open.c:65 handle_truncate fs/namei.c:3216 [inline] do_open fs/namei.c:3561 [inline] path_openat+0x272b/0x2dd0 fs/namei.c:3714 do_filp_open+0x264/0x4f0 fs/namei.c:3741 do_sys_openat2+0x124/0x4e0 fs/open.c:1310 do_sys_open fs/open.c:1326 [inline] __do_sys_creat fs/open.c:1402 [inline] __se_sys_creat fs/open.c:1396 [inline] __x64_sys_creat+0x11f/0x160 fs/open.c:1396 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f72f8a8c0c9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f72f97e3168 EFLAGS: 00000246 ORIG_RAX: 0000000000000055 RAX: ffffffffffffffda RBX: 00007f72f8bac050 RCX: 00007f72f8a8c0c9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000020000280 RBP: 00007f72f8ae7ae9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffd165348bf R14: 00007f72f97e3300 R15: 0000000000022000 Replace le16_to_cpu(sbi->s_es->s_desc_size) with sbi->s_desc_size It reduces ext4's compiled text size, and makes the code more efficient (we remove an extra indirect reference and a potential byte swap on big endian systems), and there is no downside. It also avoids the potential KASAN / syzkaller failure, as a bonus. Reported-by: syzbot+fc51227e7100c9294894@syzkaller.appspotmail.com Reported-by: syzbot+8785e41224a3afd04321@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=70d28d11ab14bd7938f3e088365252aa923cff42 Link: https://syzkaller.appspot.com/bug?id=b85721b38583ecc6b5e72ff524c67302abbc30f3 Link: https://lore.kernel.org/all/000000000000ece18705f3b20934@google.com/ Fixes: 717d50e4971b ("Ext4: Uninitialized Block Groups") Cc: stable@vger.kernel.org Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20230504121525.3275886-1-tudor.ambarus@linaro.org Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman Bug: 269155298 Bug: 270466805 Change-Id: Id14192ab0905c36e154d07d461afb56af7b61488 Signed-off-by: Tudor Ambarus --- fs/ext4/super.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 10b9b4421b7f..4bd045296ebf 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2831,11 +2831,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ - if (ext4_has_feature_64bit(sb) && - offset < le16_to_cpu(sbi->s_es->s_desc_size)) + if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, - le16_to_cpu(sbi->s_es->s_desc_size) - - offset); + sbi->s_desc_size - offset); out: return cpu_to_le16(crc); From f27e7efdc69fce98455bde3929fb17a064216b49 Mon Sep 17 00:00:00 2001 From: Udipto Goswami Date: Thu, 23 Mar 2023 18:43:15 +0530 Subject: [PATCH 3060/4345] FROMLIST: usb: xhci: Remove unused udev from xhci_log_ctx trace event xhci_log_ctx event is not utilizing the extracted udev to print out anything, hence removing it. Fixes: 1d27fabec068 ("xhci: add xhci_address_ctx trace event") Signed-off-by: Udipto Goswami Bug: 278637066 Bug: 283906700 Link: https://lore.kernel.org/all/20230323131315.21764-1-quic_ugoswami@quicinc.com/ Change-Id: I359a050ff411ede5bc2c3ba1d1d68550773fa0a6 Signed-off-by: Udipto Goswami (cherry picked from commit d3e95905cee3c94c0d16f392c2e8e7b475540d0e) --- drivers/usb/host/xhci-trace.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/usb/host/xhci-trace.h b/drivers/usb/host/xhci-trace.h index a5da02077297..5daf41ba80a5 100644 --- a/drivers/usb/host/xhci-trace.h +++ b/drivers/usb/host/xhci-trace.h @@ -80,20 +80,16 @@ DECLARE_EVENT_CLASS(xhci_log_ctx, __field(dma_addr_t, ctx_dma) __field(u8 *, ctx_va) __field(unsigned, ctx_ep_num) - __field(int, slot_id) __dynamic_array(u32, ctx_data, ((HCC_64BYTE_CONTEXT(xhci->hcc_params) + 1) * 8) * ((ctx->type == XHCI_CTX_TYPE_INPUT) + ep_num + 1)) ), TP_fast_assign( - struct usb_device *udev; - udev = to_usb_device(xhci_to_hcd(xhci)->self.controller); __entry->ctx_64 = HCC_64BYTE_CONTEXT(xhci->hcc_params); __entry->ctx_type = ctx->type; __entry->ctx_dma = ctx->dma; __entry->ctx_va = ctx->bytes; - __entry->slot_id = udev->slot_id; __entry->ctx_ep_num = ep_num; memcpy(__get_dynamic_array(ctx_data), ctx->bytes, ((HCC_64BYTE_CONTEXT(xhci->hcc_params) + 1) * 32) * From 21a4564a6c763a4af738dd8f04af1e81dcb9e53e Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Tue, 14 Feb 2023 08:49:14 -0500 Subject: [PATCH 3061/4345] BACKPORT: net/sched: Retire tcindex classifier commit 8c710f75256bb3cf05ac7b1672c82b92c43f3d28 upstream. The tcindex classifier has served us well for about a quarter of a century but has not been getting much TLC due to lack of known users. Most recently it has become easy prey to syzkaller. For this reason, we are retiring it. Bug: 274008928 Signed-off-by: Jamal Hadi Salim Acked-by: Jiri Pirko Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman Signed-off-by: Lee Jones Change-Id: I00dac08e63c5cc260c12cfa8934e50913280e898 --- net/sched/Kconfig | 11 - net/sched/Makefile | 1 - net/sched/cls_tcindex.c | 756 ---------------------------------------- 3 files changed, 768 deletions(-) delete mode 100644 net/sched/cls_tcindex.c diff --git a/net/sched/Kconfig b/net/sched/Kconfig index bc4e5da76fa6..697522371914 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -503,17 +503,6 @@ config NET_CLS_BASIC To compile this code as a module, choose M here: the module will be called cls_basic. -config NET_CLS_TCINDEX - tristate "Traffic-Control Index (TCINDEX)" - select NET_CLS - help - Say Y here if you want to be able to classify packets based on - traffic control indices. You will want this feature if you want - to implement Differentiated Services together with DSMARK. - - To compile this code as a module, choose M here: the - module will be called cls_tcindex. - config NET_CLS_ROUTE4 tristate "Routing decision (ROUTE)" depends on INET diff --git a/net/sched/Makefile b/net/sched/Makefile index 66bbf9a98f9e..4311fdb21119 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -69,7 +69,6 @@ obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o -obj-$(CONFIG_NET_CLS_TCINDEX) += cls_tcindex.o obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c deleted file mode 100644 index 50bf7ec4b5b2..000000000000 --- a/net/sched/cls_tcindex.c +++ /dev/null @@ -1,756 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * net/sched/cls_tcindex.c Packet classifier for skb->tc_index - * - * Written 1998,1999 by Werner Almesberger, EPFL ICA - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * Passing parameters to the root seems to be done more awkwardly than really - * necessary. At least, u32 doesn't seem to use such dirty hacks. To be - * verified. FIXME. - */ - -#define PERFECT_HASH_THRESHOLD 64 /* use perfect hash if not bigger */ -#define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */ - - -struct tcindex_data; - -struct tcindex_filter_result { - struct tcf_exts exts; - struct tcf_result res; - struct tcindex_data *p; - struct rcu_work rwork; -}; - -struct tcindex_filter { - u16 key; - struct tcindex_filter_result result; - struct tcindex_filter __rcu *next; - struct rcu_work rwork; -}; - - -struct tcindex_data { - struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */ - struct tcindex_filter __rcu **h; /* imperfect hash; */ - struct tcf_proto *tp; - u16 mask; /* AND key with mask */ - u32 shift; /* shift ANDed key to the right */ - u32 hash; /* hash table size; 0 if undefined */ - u32 alloc_hash; /* allocated size */ - u32 fall_through; /* 0: only classify if explicit match */ - refcount_t refcnt; /* a temporary refcnt for perfect hash */ - struct rcu_work rwork; -}; - -static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) -{ - return tcf_exts_has_actions(&r->exts) || r->res.classid; -} - -static void tcindex_data_get(struct tcindex_data *p) -{ - refcount_inc(&p->refcnt); -} - -static void tcindex_data_put(struct tcindex_data *p) -{ - if (refcount_dec_and_test(&p->refcnt)) { - kfree(p->perfect); - kfree(p->h); - kfree(p); - } -} - -static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p, - u16 key) -{ - if (p->perfect) { - struct tcindex_filter_result *f = p->perfect + key; - - return tcindex_filter_is_set(f) ? f : NULL; - } else if (p->h) { - struct tcindex_filter __rcu **fp; - struct tcindex_filter *f; - - fp = &p->h[key % p->hash]; - for (f = rcu_dereference_bh_rtnl(*fp); - f; - fp = &f->next, f = rcu_dereference_bh_rtnl(*fp)) - if (f->key == key) - return &f->result; - } - - return NULL; -} - - -static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct tcindex_data *p = rcu_dereference_bh(tp->root); - struct tcindex_filter_result *f; - int key = (skb->tc_index & p->mask) >> p->shift; - - pr_debug("tcindex_classify(skb %p,tp %p,res %p),p %p\n", - skb, tp, res, p); - - f = tcindex_lookup(p, key); - if (!f) { - struct Qdisc *q = tcf_block_q(tp->chain->block); - - if (!p->fall_through) - return -1; - res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key); - res->class = 0; - pr_debug("alg 0x%x\n", res->classid); - return 0; - } - *res = f->res; - pr_debug("map 0x%x\n", res->classid); - - return tcf_exts_exec(skb, &f->exts, res); -} - - -static void *tcindex_get(struct tcf_proto *tp, u32 handle) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r; - - pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); - if (p->perfect && handle >= p->alloc_hash) - return NULL; - r = tcindex_lookup(p, handle); - return r && tcindex_filter_is_set(r) ? r : NULL; -} - -static int tcindex_init(struct tcf_proto *tp) -{ - struct tcindex_data *p; - - pr_debug("tcindex_init(tp %p)\n", tp); - p = kzalloc(sizeof(struct tcindex_data), GFP_KERNEL); - if (!p) - return -ENOMEM; - - p->mask = 0xffff; - p->hash = DEFAULT_HASH_SIZE; - p->fall_through = 1; - refcount_set(&p->refcnt, 1); /* Paired with tcindex_destroy_work() */ - - rcu_assign_pointer(tp->root, p); - return 0; -} - -static void __tcindex_destroy_rexts(struct tcindex_filter_result *r) -{ - tcf_exts_destroy(&r->exts); - tcf_exts_put_net(&r->exts); - tcindex_data_put(r->p); -} - -static void tcindex_destroy_rexts_work(struct work_struct *work) -{ - struct tcindex_filter_result *r; - - r = container_of(to_rcu_work(work), - struct tcindex_filter_result, - rwork); - rtnl_lock(); - __tcindex_destroy_rexts(r); - rtnl_unlock(); -} - -static void __tcindex_destroy_fexts(struct tcindex_filter *f) -{ - tcf_exts_destroy(&f->result.exts); - tcf_exts_put_net(&f->result.exts); - kfree(f); -} - -static void tcindex_destroy_fexts_work(struct work_struct *work) -{ - struct tcindex_filter *f = container_of(to_rcu_work(work), - struct tcindex_filter, - rwork); - - rtnl_lock(); - __tcindex_destroy_fexts(f); - rtnl_unlock(); -} - -static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last, - bool rtnl_held, struct netlink_ext_ack *extack) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = arg; - struct tcindex_filter __rcu **walk; - struct tcindex_filter *f = NULL; - - pr_debug("tcindex_delete(tp %p,arg %p),p %p\n", tp, arg, p); - if (p->perfect) { - if (!r->res.class) - return -ENOENT; - } else { - int i; - - for (i = 0; i < p->hash; i++) { - walk = p->h + i; - for (f = rtnl_dereference(*walk); f; - walk = &f->next, f = rtnl_dereference(*walk)) { - if (&f->result == r) - goto found; - } - } - return -ENOENT; - -found: - rcu_assign_pointer(*walk, rtnl_dereference(f->next)); - } - tcf_unbind_filter(tp, &r->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (f) { - if (tcf_exts_get_net(&f->result.exts)) - tcf_queue_work(&f->rwork, tcindex_destroy_fexts_work); - else - __tcindex_destroy_fexts(f); - } else { - tcindex_data_get(p); - - if (tcf_exts_get_net(&r->exts)) - tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work); - else - __tcindex_destroy_rexts(r); - } - - *last = false; - return 0; -} - -static void tcindex_destroy_work(struct work_struct *work) -{ - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); - - tcindex_data_put(p); -} - -static inline int -valid_perfect_hash(struct tcindex_data *p) -{ - return p->hash > (p->mask >> p->shift); -} - -static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { - [TCA_TCINDEX_HASH] = { .type = NLA_U32 }, - [TCA_TCINDEX_MASK] = { .type = NLA_U16 }, - [TCA_TCINDEX_SHIFT] = { .type = NLA_U32 }, - [TCA_TCINDEX_FALL_THROUGH] = { .type = NLA_U32 }, - [TCA_TCINDEX_CLASSID] = { .type = NLA_U32 }, -}; - -static int tcindex_filter_result_init(struct tcindex_filter_result *r, - struct tcindex_data *p, - struct net *net) -{ - memset(r, 0, sizeof(*r)); - r->p = p; - return tcf_exts_init(&r->exts, net, TCA_TCINDEX_ACT, - TCA_TCINDEX_POLICE); -} - -static void tcindex_free_perfect_hash(struct tcindex_data *cp); - -static void tcindex_partial_destroy_work(struct work_struct *work) -{ - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); - - rtnl_lock(); - if (p->perfect) - tcindex_free_perfect_hash(p); - kfree(p); - rtnl_unlock(); -} - -static void tcindex_free_perfect_hash(struct tcindex_data *cp) -{ - int i; - - for (i = 0; i < cp->hash; i++) - tcf_exts_destroy(&cp->perfect[i].exts); - kfree(cp->perfect); -} - -static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) -{ - int i, err = 0; - - cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result), - GFP_KERNEL | __GFP_NOWARN); - if (!cp->perfect) - return -ENOMEM; - - for (i = 0; i < cp->hash; i++) { - err = tcf_exts_init(&cp->perfect[i].exts, net, - TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - goto errout; - cp->perfect[i].p = cp; - } - - return 0; - -errout: - tcindex_free_perfect_hash(cp); - return err; -} - -static int -tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, - u32 handle, struct tcindex_data *p, - struct tcindex_filter_result *r, struct nlattr **tb, - struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) -{ - struct tcindex_filter_result new_filter_result; - struct tcindex_data *cp = NULL, *oldp; - struct tcindex_filter *f = NULL; /* make gcc behave */ - struct tcf_result cr = {}; - int err, balloc = 0; - struct tcf_exts e; - bool update_h = false; - - err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr, true, extack); - if (err < 0) - goto errout; - - err = -ENOMEM; - /* tcindex_data attributes must look atomic to classifier/lookup so - * allocate new tcindex data and RCU assign it onto root. Keeping - * perfect hash and hash pointers from old data. - */ - cp = kzalloc(sizeof(*cp), GFP_KERNEL); - if (!cp) - goto errout; - - cp->mask = p->mask; - cp->shift = p->shift; - cp->hash = p->hash; - cp->alloc_hash = p->alloc_hash; - cp->fall_through = p->fall_through; - cp->tp = tp; - refcount_set(&cp->refcnt, 1); /* Paired with tcindex_destroy_work() */ - - if (tb[TCA_TCINDEX_HASH]) - cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); - - if (tb[TCA_TCINDEX_MASK]) - cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); - - if (tb[TCA_TCINDEX_SHIFT]) { - cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); - if (cp->shift > 16) { - err = -EINVAL; - goto errout; - } - } - if (!cp->hash) { - /* Hash not specified, use perfect hash if the upper limit - * of the hashing index is below the threshold. - */ - if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) - cp->hash = (cp->mask >> cp->shift) + 1; - else - cp->hash = DEFAULT_HASH_SIZE; - } - - if (p->perfect) { - int i; - - if (tcindex_alloc_perfect_hash(net, cp) < 0) - goto errout; - cp->alloc_hash = cp->hash; - for (i = 0; i < min(cp->hash, p->hash); i++) - cp->perfect[i].res = p->perfect[i].res; - balloc = 1; - } - cp->h = p->h; - - err = tcindex_filter_result_init(&new_filter_result, cp, net); - if (err < 0) - goto errout_alloc; - if (r) - cr = r->res; - - err = -EBUSY; - - /* Hash already allocated, make sure that we still meet the - * requirements for the allocated hash. - */ - if (cp->perfect) { - if (!valid_perfect_hash(cp) || - cp->hash > cp->alloc_hash) - goto errout_alloc; - } else if (cp->h && cp->hash != cp->alloc_hash) { - goto errout_alloc; - } - - err = -EINVAL; - if (tb[TCA_TCINDEX_FALL_THROUGH]) - cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]); - - if (!cp->perfect && !cp->h) - cp->alloc_hash = cp->hash; - - /* Note: this could be as restrictive as if (handle & ~(mask >> shift)) - * but then, we'd fail handles that may become valid after some future - * mask change. While this is extremely unlikely to ever matter, - * the check below is safer (and also more backwards-compatible). - */ - if (cp->perfect || valid_perfect_hash(cp)) - if (handle >= cp->alloc_hash) - goto errout_alloc; - - - err = -ENOMEM; - if (!cp->perfect && !cp->h) { - if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(net, cp) < 0) - goto errout_alloc; - balloc = 1; - } else { - struct tcindex_filter __rcu **hash; - - hash = kcalloc(cp->hash, - sizeof(struct tcindex_filter *), - GFP_KERNEL); - - if (!hash) - goto errout_alloc; - - cp->h = hash; - balloc = 2; - } - } - - if (cp->perfect) { - r = cp->perfect + handle; - } else { - /* imperfect area is updated in-place using rcu */ - update_h = !!tcindex_lookup(cp, handle); - r = &new_filter_result; - } - - if (r == &new_filter_result) { - f = kzalloc(sizeof(*f), GFP_KERNEL); - if (!f) - goto errout_alloc; - f->key = handle; - f->next = NULL; - err = tcindex_filter_result_init(&f->result, cp, net); - if (err < 0) { - kfree(f); - goto errout_alloc; - } - } - - if (tb[TCA_TCINDEX_CLASSID]) { - cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr, base); - } - - oldp = p; - r->res = cr; - tcf_exts_change(&r->exts, &e); - - rcu_assign_pointer(tp->root, cp); - - if (update_h) { - struct tcindex_filter __rcu **fp; - struct tcindex_filter *cf; - - f->result.res = r->res; - tcf_exts_change(&f->result.exts, &r->exts); - - /* imperfect area bucket */ - fp = cp->h + (handle % cp->hash); - - /* lookup the filter, guaranteed to exist */ - for (cf = rcu_dereference_bh_rtnl(*fp); cf; - fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp)) - if (cf->key == handle) - break; - - f->next = cf->next; - - cf = rcu_replace_pointer(*fp, f, 1); - tcf_exts_get_net(&cf->result.exts); - tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work); - } else if (r == &new_filter_result) { - struct tcindex_filter *nfp; - struct tcindex_filter __rcu **fp; - - f->result.res = r->res; - tcf_exts_change(&f->result.exts, &r->exts); - - fp = cp->h + (handle % cp->hash); - for (nfp = rtnl_dereference(*fp); - nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) - ; /* nothing */ - - rcu_assign_pointer(*fp, f); - } else { - tcf_exts_destroy(&new_filter_result.exts); - } - - if (oldp) - tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work); - return 0; - -errout_alloc: - if (balloc == 1) - tcindex_free_perfect_hash(cp); - else if (balloc == 2) - kfree(cp->h); - tcf_exts_destroy(&new_filter_result.exts); -errout: - kfree(cp); - tcf_exts_destroy(&e); - return err; -} - -static int -tcindex_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, - bool rtnl_held, struct netlink_ext_ack *extack) -{ - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_TCINDEX_MAX + 1]; - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = *arg; - int err; - - pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p," - "p %p,r %p,*arg %p\n", - tp, handle, tca, arg, opt, p, r, *arg); - - if (!opt) - return 0; - - err = nla_parse_nested_deprecated(tb, TCA_TCINDEX_MAX, opt, - tcindex_policy, NULL); - if (err < 0) - return err; - - return tcindex_set_parms(net, tp, base, handle, p, r, tb, - tca[TCA_RATE], ovr, extack); -} - -static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker, - bool rtnl_held) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter *f, *next; - int i; - - pr_debug("tcindex_walk(tp %p,walker %p),p %p\n", tp, walker, p); - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - if (!p->perfect[i].res.class) - continue; - if (walker->count >= walker->skip) { - if (walker->fn(tp, p->perfect + i, walker) < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } - if (!p->h) - return; - for (i = 0; i < p->hash; i++) { - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - if (walker->count >= walker->skip) { - if (walker->fn(tp, &f->result, walker) < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } -} - -static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - int i; - - pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); - - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - struct tcindex_filter_result *r = p->perfect + i; - - /* tcf_queue_work() does not guarantee the ordering we - * want, so we have to take this refcnt temporarily to - * ensure 'p' is freed after all tcindex_filter_result - * here. Imperfect hash does not need this, because it - * uses linked lists rather than an array. - */ - tcindex_data_get(p); - - tcf_unbind_filter(tp, &r->res); - if (tcf_exts_get_net(&r->exts)) - tcf_queue_work(&r->rwork, - tcindex_destroy_rexts_work); - else - __tcindex_destroy_rexts(r); - } - } - - for (i = 0; p->h && i < p->hash; i++) { - struct tcindex_filter *f, *next; - bool last; - - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - tcindex_delete(tp, &f->result, &last, rtnl_held, NULL); - } - } - - tcf_queue_work(&p->rwork, tcindex_destroy_work); -} - - -static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = fh; - struct nlattr *nest; - - pr_debug("tcindex_dump(tp %p,fh %p,skb %p,t %p),p %p,r %p\n", - tp, fh, skb, t, p, r); - pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h); - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (!fh) { - t->tcm_handle = ~0; /* whatever ... */ - if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) || - nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) || - nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) || - nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through)) - goto nla_put_failure; - nla_nest_end(skb, nest); - } else { - if (p->perfect) { - t->tcm_handle = r - p->perfect; - } else { - struct tcindex_filter *f; - struct tcindex_filter __rcu **fp; - int i; - - t->tcm_handle = 0; - for (i = 0; !t->tcm_handle && i < p->hash; i++) { - fp = &p->h[i]; - for (f = rtnl_dereference(*fp); - !t->tcm_handle && f; - fp = &f->next, f = rtnl_dereference(*fp)) { - if (&f->result == r) - t->tcm_handle = f->key; - } - } - } - pr_debug("handle = %d\n", t->tcm_handle); - if (r->res.class && - nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &r->exts) < 0) - goto nla_put_failure; - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &r->exts) < 0) - goto nla_put_failure; - } - - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl, - void *q, unsigned long base) -{ - struct tcindex_filter_result *r = fh; - - if (r && r->res.classid == classid) { - if (cl) - __tcf_bind_filter(q, &r->res, base); - else - __tcf_unbind_filter(q, &r->res); - } -} - -static struct tcf_proto_ops cls_tcindex_ops __read_mostly = { - .kind = "tcindex", - .classify = tcindex_classify, - .init = tcindex_init, - .destroy = tcindex_destroy, - .get = tcindex_get, - .change = tcindex_change, - .delete = tcindex_delete, - .walk = tcindex_walk, - .dump = tcindex_dump, - .bind_class = tcindex_bind_class, - .owner = THIS_MODULE, -}; - -static int __init init_tcindex(void) -{ - return register_tcf_proto_ops(&cls_tcindex_ops); -} - -static void __exit exit_tcindex(void) -{ - unregister_tcf_proto_ops(&cls_tcindex_ops); -} - -module_init(init_tcindex) -module_exit(exit_tcindex) -MODULE_LICENSE("GPL"); From 7c835be7ec6ea55d7535f2bf8e0cbb1e64b45699 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 15:39:31 +0000 Subject: [PATCH 3062/4345] ANDROID: remove CONFIG_NET_CLS_TCINDEX from gki_defconfig The tcindex code was removed from the tree in 5.10.173, so remove the config option from the gki_defconfig files to fix up the build. Fixes: 18c3fa7a7fdb ("net/sched: Retire tcindex classifier") Change-Id: Id4927815ec2fd0ebc8065d891dfb721551f3dbc6 Signed-off-by: Greg Kroah-Hartman (cherry picked from commit a880d7ebc53ec8595200175f860f35ef8755e91f) Signed-off-by: Lee Jones --- arch/arm64/configs/gki_defconfig | 1 - arch/x86/configs/gki_defconfig | 1 - 2 files changed, 2 deletions(-) diff --git a/arch/arm64/configs/gki_defconfig b/arch/arm64/configs/gki_defconfig index 8fa037f86347..e238ccdcafe1 100644 --- a/arch/arm64/configs/gki_defconfig +++ b/arch/arm64/configs/gki_defconfig @@ -245,7 +245,6 @@ CONFIG_NET_SCH_FQ_CODEL=y CONFIG_NET_SCH_FQ=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_CLS_BASIC=y -CONFIG_NET_CLS_TCINDEX=y CONFIG_NET_CLS_FW=y CONFIG_NET_CLS_U32=y CONFIG_CLS_U32_MARK=y diff --git a/arch/x86/configs/gki_defconfig b/arch/x86/configs/gki_defconfig index 9507ff815d82..9c6d1a0e661d 100644 --- a/arch/x86/configs/gki_defconfig +++ b/arch/x86/configs/gki_defconfig @@ -220,7 +220,6 @@ CONFIG_NET_SCH_FQ_CODEL=y CONFIG_NET_SCH_FQ=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_CLS_BASIC=y -CONFIG_NET_CLS_TCINDEX=y CONFIG_NET_CLS_FW=y CONFIG_NET_CLS_U32=y CONFIG_CLS_U32_MARK=y From 7f9a9a8fe43d84f93726bf3505174b3203b623a8 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 7 Jun 2022 10:09:03 -0400 Subject: [PATCH 3063/4345] UPSTREAM: KVM: x86: do not report a vCPU as preempted outside instruction boundaries commit 6cd88243c7e03845a450795e134b488fc2afb736 upstream. If a vCPU is outside guest mode and is scheduled out, it might be in the process of making a memory access. A problem occurs if another vCPU uses the PV TLB flush feature during the period when the vCPU is scheduled out, and a virtual address has already been translated but has not yet been accessed, because this is equivalent to using a stale TLB entry. To avoid this, only report a vCPU as preempted if sure that the guest is at an instruction boundary. A rescheduling request will be delivered to the host physical CPU as an external interrupt, so for simplicity consider any vmexit *not* instruction boundary except for external interrupts. It would in principle be okay to report the vCPU as preempted also if it is sleeping in kvm_vcpu_block(): a TLB flush IPI will incur the vmentry/vmexit overhead unnecessarily, and optimistic spinning is also unlikely to succeed. However, leave it for later because right now kvm_vcpu_check_block() is doing memory accesses. Even though the TLB flush issue only applies to virtual memory address, it's very much preferrable to be conservative. Bug: 245869446 Bug: 278120352 Reported-by: Jann Horn Signed-off-by: Paolo Bonzini [OP: use VCPU_STAT() for debugfs entries] Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 529f41f0eb1ef995bfa83c121c3cfe3a0720119a) Signed-off-by: Lee Jones Change-Id: Ie9c597eecb619d12a714a0d0722d34e855e97b14 --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/svm/svm.c | 2 ++ arch/x86/kvm/vmx/vmx.c | 1 + arch/x86/kvm/x86.c | 22 ++++++++++++++++++++++ 4 files changed, 28 insertions(+) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 660012ab7bfa..af4b4d3c6ff6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -553,6 +553,7 @@ struct kvm_vcpu_arch { u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; + bool at_instruction_boundary; bool tpr_access_reporting; bool xsaves_enabled; u64 ia32_xss; @@ -1061,6 +1062,8 @@ struct kvm_vcpu_stat { u64 req_event; u64 halt_poll_success_ns; u64 halt_poll_fail_ns; + u64 preemption_reported; + u64 preemption_other; }; struct x86_instruction_info; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index c34ba034ca11..ef5a72d80f54 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3977,6 +3977,8 @@ out: static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + vcpu->arch.at_instruction_boundary = true; } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c37cbd3fdd85..5f6f926b02a9 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6505,6 +6505,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) return; handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + vcpu->arch.at_instruction_boundary = true; } static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 554d37873c25..fb5a10c70beb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -231,6 +231,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("l1d_flush", l1d_flush), VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), + VCPU_STAT("preemption_reported", preemption_reported), + VCPU_STAT("preemption_other", preemption_other), VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), VM_STAT("mmu_pte_write", mmu_pte_write), VM_STAT("mmu_pde_zapped", mmu_pde_zapped), @@ -4052,6 +4054,19 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) struct kvm_host_map map; struct kvm_steal_time *st; + /* + * The vCPU can be marked preempted if and only if the VM-Exit was on + * an instruction boundary and will not trigger guest emulation of any + * kind (see vcpu_run). Vendor specific code controls (conservatively) + * when this is true, for example allowing the vCPU to be marked + * preempted if and only if the VM-Exit was due to a host interrupt. + */ + if (!vcpu->arch.at_instruction_boundary) { + vcpu->stat.preemption_other++; + return; + } + + vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -9355,6 +9370,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.l1tf_flush_l1d = true; for (;;) { + /* + * If another guest vCPU requests a PV TLB flush in the middle + * of instruction emulation, the rest of the emulation could + * use a stale page translation. Assume that any code after + * this point can start executing an instruction. + */ + vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { From 423908e89d7d3185097a144b7c6fe0b3a48f1518 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 17 Jun 2021 15:29:04 +0300 Subject: [PATCH 3064/4345] driver core: add a helper to setup both the of_node and fwnode of a device [ Upstream commit 43e76d463c09a0272b84775bcc727c1eb8b384b2 ] There are many places where both the fwnode_handle and the of_node of a device need to be populated. Add a function which does both so that we have consistency. Suggested-by: Andrew Lunn Signed-off-by: Ioana Ciornei Reviewed-by: Greg Kroah-Hartman Signed-off-by: David S. Miller Stable-dep-of: a26cc2934331 ("drm/mipi-dsi: Set the fwnode for mipi_dsi_device") Signed-off-by: Sasha Levin --- drivers/base/core.c | 7 +++++++ include/linux/device.h | 1 + 2 files changed, 8 insertions(+) diff --git a/drivers/base/core.c b/drivers/base/core.c index 9a874a58d690..cb859febd03c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4352,6 +4352,13 @@ void device_set_of_node_from_dev(struct device *dev, const struct device *dev2) } EXPORT_SYMBOL_GPL(device_set_of_node_from_dev); +void device_set_node(struct device *dev, struct fwnode_handle *fwnode) +{ + dev->fwnode = fwnode; + dev->of_node = to_of_node(fwnode); +} +EXPORT_SYMBOL_GPL(device_set_node); + int device_match_name(struct device *dev, const void *name) { return sysfs_streq(dev_name(dev), name); diff --git a/include/linux/device.h b/include/linux/device.h index 5dc0f81e4f9d..4f7e0c85e11f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -818,6 +818,7 @@ int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); +void device_set_node(struct device *dev, struct fwnode_handle *fwnode); static inline int dev_num_vf(struct device *dev) { From 139c27648f8d3b2283f74715d8e7f0df7f5e55ca Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 9 Mar 2023 22:39:09 -0800 Subject: [PATCH 3065/4345] drm/mipi-dsi: Set the fwnode for mipi_dsi_device [ Upstream commit a26cc2934331b57b5a7164bff344f0a2ec245fc0 ] After commit 3fb16866b51d ("driver core: fw_devlink: Make cycle detection more robust"), fw_devlink prints an error when consumer devices don't have their fwnode set. This used to be ignored silently. Set the fwnode mipi_dsi_device so fw_devlink can find them and properly track their dependencies. This fixes errors like this: [ 0.334054] nwl-dsi 30a00000.mipi-dsi: Failed to create device link with regulator-lcd-1v8 [ 0.346964] nwl-dsi 30a00000.mipi-dsi: Failed to create device link with backlight-dsi Reported-by: Martin Kepplinger Link: https://lore.kernel.org/lkml/2a8e407f4f18c9350f8629a2b5fa18673355b2ae.camel@puri.sm/ Fixes: 068a00233969 ("drm: Add MIPI DSI bus support") Signed-off-by: Saravana Kannan Tested-by: Martin Kepplinger Link: https://lore.kernel.org/r/20230310063910.2474472-1-saravanak@google.com Signed-off-by: Maxime Ripard Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_mipi_dsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 19fb1d93a4f0..0c806e99e869 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -221,7 +221,7 @@ mipi_dsi_device_register_full(struct mipi_dsi_host *host, return dsi; } - dsi->dev.of_node = info->node; + device_set_node(&dsi->dev, of_fwnode_handle(info->node)); dsi->channel = info->channel; strlcpy(dsi->name, info->type, sizeof(dsi->name)); From b882224d73671b77398e235449390e5af84ff6ae Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 23 Apr 2023 06:48:45 +0100 Subject: [PATCH 3066/4345] ARM: 9296/1: HP Jornada 7XX: fix kernel-doc warnings [ Upstream commit 46dd6078dbc7e363a8bb01209da67015a1538929 ] Fix kernel-doc warnings from the kernel test robot: jornada720_ssp.c:24: warning: Function parameter or member 'jornada_ssp_lock' not described in 'DEFINE_SPINLOCK' jornada720_ssp.c:24: warning: expecting prototype for arch/arm/mac(). Prototype was for DEFINE_SPINLOCK() instead jornada720_ssp.c:34: warning: Function parameter or member 'byte' not described in 'jornada_ssp_reverse' jornada720_ssp.c:57: warning: Function parameter or member 'byte' not described in 'jornada_ssp_byte' jornada720_ssp.c:85: warning: Function parameter or member 'byte' not described in 'jornada_ssp_inout' Link: lore.kernel.org/r/202304210535.tWby3jWF-lkp@intel.com Fixes: 69ebb22277a5 ("[ARM] 4506/1: HP Jornada 7XX: Addition of SSP Platform Driver") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Arnd Bergmann Cc: Kristoffer Ericson Cc: patches@armlinux.org.uk Signed-off-by: Russell King (Oracle) Signed-off-by: Sasha Levin --- arch/arm/mach-sa1100/jornada720_ssp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-sa1100/jornada720_ssp.c b/arch/arm/mach-sa1100/jornada720_ssp.c index 1dbe98948ce3..9627c4cf3e41 100644 --- a/arch/arm/mach-sa1100/jornada720_ssp.c +++ b/arch/arm/mach-sa1100/jornada720_ssp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * arch/arm/mac-sa1100/jornada720_ssp.c * * Copyright (C) 2006/2007 Kristoffer Ericson @@ -26,6 +26,7 @@ static unsigned long jornada_ssp_flags; /** * jornada_ssp_reverse - reverses input byte + * @byte: input byte to reverse * * we need to reverse all data we receive from the mcu due to its physical location * returns : 01110111 -> 11101110 @@ -46,6 +47,7 @@ EXPORT_SYMBOL(jornada_ssp_reverse); /** * jornada_ssp_byte - waits for ready ssp bus and sends byte + * @byte: input byte to transmit * * waits for fifo buffer to clear and then transmits, if it doesn't then we will * timeout after rounds. Needs mcu running before its called. @@ -77,6 +79,7 @@ EXPORT_SYMBOL(jornada_ssp_byte); /** * jornada_ssp_inout - decide if input is command or trading byte + * @byte: input byte to send (may be %TXDUMMY) * * returns : (jornada_ssp_byte(byte)) on success * : %-ETIMEDOUT on timeout failure From 4d3ae448e850019449024a02aec814e1c889111c Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 5 May 2023 20:39:33 +0200 Subject: [PATCH 3067/4345] net: mdio: mvusb: Fix an error handling path in mvusb_mdio_probe() [ Upstream commit 27c1eaa07283b0c94becf8241f95368267cf558b ] Should of_mdiobus_register() fail, a previous usb_get_dev() call should be undone as in the .disconnect function. Fixes: 04e37d92fbed ("net: phy: add marvell usb to mdio controller") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/mdio/mdio-mvusb.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/mdio/mdio-mvusb.c b/drivers/net/mdio/mdio-mvusb.c index d5eabddfdf51..11e048136ac2 100644 --- a/drivers/net/mdio/mdio-mvusb.c +++ b/drivers/net/mdio/mdio-mvusb.c @@ -73,6 +73,7 @@ static int mvusb_mdio_probe(struct usb_interface *interface, struct device *dev = &interface->dev; struct mvusb_mdio *mvusb; struct mii_bus *mdio; + int ret; mdio = devm_mdiobus_alloc_size(dev, sizeof(*mvusb)); if (!mdio) @@ -93,7 +94,15 @@ static int mvusb_mdio_probe(struct usb_interface *interface, mdio->write = mvusb_mdio_write; usb_set_intfdata(interface, mvusb); - return of_mdiobus_register(mdio, dev->of_node); + ret = of_mdiobus_register(mdio, dev->of_node); + if (ret) + goto put_dev; + + return 0; + +put_dev: + usb_put_dev(mvusb->udev); + return ret; } static void mvusb_mdio_disconnect(struct usb_interface *interface) From 8eb35b1aca842963182e8e7c70b6238ee6461941 Mon Sep 17 00:00:00 2001 From: Roy Novich Date: Sun, 7 May 2023 16:57:43 +0300 Subject: [PATCH 3068/4345] linux/dim: Do nothing if no time delta between samples [ Upstream commit 162bd18eb55adf464a0fa2b4144b8d61c75ff7c2 ] Add return value for dim_calc_stats. This is an indication for the caller if curr_stats was assigned by the function. Avoid using curr_stats uninitialized over {rdma/net}_dim, when no time delta between samples. Coverity reported this potential use of an uninitialized variable. Fixes: 4c4dbb4a7363 ("net/mlx5e: Move dynamic interrupt coalescing code to include/linux") Fixes: cb3c7fd4f839 ("net/mlx5e: Support adaptive RX coalescing") Signed-off-by: Roy Novich Reviewed-by: Aya Levin Reviewed-by: Saeed Mahameed Signed-off-by: Tariq Toukan Reviewed-by: Leon Romanovsky Reviewed-by: Michal Kubiak Link: https://lore.kernel.org/r/20230507135743.138993-1-tariqt@nvidia.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- include/linux/dim.h | 3 ++- lib/dim/dim.c | 5 +++-- lib/dim/net_dim.c | 3 ++- lib/dim/rdma_dim.c | 3 ++- 4 files changed, 9 insertions(+), 5 deletions(-) diff --git a/include/linux/dim.h b/include/linux/dim.h index 6c5733981563..f343bc9aa2ec 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -236,8 +236,9 @@ void dim_park_tired(struct dim *dim); * * Calculate the delta between two samples (in data rates). * Takes into consideration counter wrap-around. + * Returned boolean indicates whether curr_stats are reliable. */ -void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, struct dim_stats *curr_stats); /** diff --git a/lib/dim/dim.c b/lib/dim/dim.c index 38045d6d0538..e89aaf07bde5 100644 --- a/lib/dim/dim.c +++ b/lib/dim/dim.c @@ -54,7 +54,7 @@ void dim_park_tired(struct dim *dim) } EXPORT_SYMBOL(dim_park_tired); -void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, struct dim_stats *curr_stats) { /* u32 holds up to 71 minutes, should be enough */ @@ -66,7 +66,7 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, start->comp_ctr); if (!delta_us) - return; + return false; curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us); curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us); @@ -79,5 +79,6 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, else curr_stats->cpe_ratio = 0; + return true; } EXPORT_SYMBOL(dim_calc_stats); diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index dae3b51ac3d9..0e4f3a686f1d 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -227,7 +227,8 @@ void net_dim(struct dim *dim, struct dim_sample end_sample) dim->start_sample.event_ctr); if (nevents < DIM_NEVENTS) break; - dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats); + if (!dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats)) + break; if (net_dim_decision(&curr_stats, dim)) { dim->state = DIM_APPLY_NEW_PROFILE; schedule_work(&dim->work); diff --git a/lib/dim/rdma_dim.c b/lib/dim/rdma_dim.c index f7e26c7b4749..d32c8b105adc 100644 --- a/lib/dim/rdma_dim.c +++ b/lib/dim/rdma_dim.c @@ -88,7 +88,8 @@ void rdma_dim(struct dim *dim, u64 completions) nevents = curr_sample->event_ctr - dim->start_sample.event_ctr; if (nevents < DIM_NEVENTS) break; - dim_calc_stats(&dim->start_sample, curr_sample, &curr_stats); + if (!dim_calc_stats(&dim->start_sample, curr_sample, &curr_stats)) + break; if (rdma_dim_decision(&curr_stats, dim)) { dim->state = DIM_APPLY_NEW_PROFILE; schedule_work(&dim->work); From d06f67b2b8dcd00d995c468428b6bccebc5762d8 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 8 May 2023 10:55:43 -0700 Subject: [PATCH 3069/4345] net: Fix load-tearing on sk->sk_stamp in sock_recv_cmsgs(). [ Upstream commit dfd9248c071a3710c24365897459538551cb7167 ] KCSAN found a data race in sock_recv_cmsgs() where the read access to sk->sk_stamp needs READ_ONCE(). BUG: KCSAN: data-race in packet_recvmsg / packet_recvmsg write (marked) to 0xffff88803c81f258 of 8 bytes by task 19171 on cpu 0: sock_write_timestamp include/net/sock.h:2670 [inline] sock_recv_cmsgs include/net/sock.h:2722 [inline] packet_recvmsg+0xb97/0xd00 net/packet/af_packet.c:3489 sock_recvmsg_nosec net/socket.c:1019 [inline] sock_recvmsg+0x11a/0x130 net/socket.c:1040 sock_read_iter+0x176/0x220 net/socket.c:1118 call_read_iter include/linux/fs.h:1845 [inline] new_sync_read fs/read_write.c:389 [inline] vfs_read+0x5e0/0x630 fs/read_write.c:470 ksys_read+0x163/0x1a0 fs/read_write.c:613 __do_sys_read fs/read_write.c:623 [inline] __se_sys_read fs/read_write.c:621 [inline] __x64_sys_read+0x41/0x50 fs/read_write.c:621 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc read to 0xffff88803c81f258 of 8 bytes by task 19183 on cpu 1: sock_recv_cmsgs include/net/sock.h:2721 [inline] packet_recvmsg+0xb64/0xd00 net/packet/af_packet.c:3489 sock_recvmsg_nosec net/socket.c:1019 [inline] sock_recvmsg+0x11a/0x130 net/socket.c:1040 sock_read_iter+0x176/0x220 net/socket.c:1118 call_read_iter include/linux/fs.h:1845 [inline] new_sync_read fs/read_write.c:389 [inline] vfs_read+0x5e0/0x630 fs/read_write.c:470 ksys_read+0x163/0x1a0 fs/read_write.c:613 __do_sys_read fs/read_write.c:623 [inline] __se_sys_read fs/read_write.c:621 [inline] __x64_sys_read+0x41/0x50 fs/read_write.c:621 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc value changed: 0xffffffffc4653600 -> 0x0000000000000000 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 19183 Comm: syz-executor.5 Not tainted 6.3.0-rc7-02330-gca6270c12e20 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 6c7c98bad488 ("sock: avoid dirtying sk_stamp, if possible") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230508175543.55756-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/sock.h b/include/net/sock.h index 1d8529311d6f..651dc0a7bbd5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2535,7 +2535,7 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, __sock_recv_ts_and_drops(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); - else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP)) + else if (unlikely(sock_read_timestamp(sk) == SK_DEFAULT_STAMP)) sock_write_timestamp(sk, 0); } From 26001e75dc5c705b970698adfecc832f29c3a6e8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 4 May 2023 14:55:02 +0200 Subject: [PATCH 3070/4345] netfilter: conntrack: fix possible bug_on with enable_hooks=1 [ Upstream commit e72eeab542dbf4f544e389e64fa13b82a1b6d003 ] I received a bug report (no reproducer so far) where we trip over 712 rcu_read_lock(); 713 ct_hook = rcu_dereference(nf_ct_hook); 714 BUG_ON(ct_hook == NULL); // here In nf_conntrack_destroy(). First turn this BUG_ON into a WARN. I think it was triggered via enable_hooks=1 flag. When this flag is turned on, the conntrack hooks are registered before nf_ct_hook pointer gets assigned. This opens a short window where packets enter the conntrack machinery, can have skb->_nfct set up and a subsequent kfree_skb might occur before nf_ct_hook is set. Call nf_conntrack_init_end() to set nf_ct_hook before we register the pernet ops. Fixes: ba3fbe663635 ("netfilter: nf_conntrack: provide modparam to always register conntrack hooks") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/core.c | 6 ++++-- net/netfilter/nf_conntrack_standalone.c | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 60332fdb6dd4..5b7578adbf0f 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -674,9 +674,11 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); - BUG_ON(ct_hook == NULL); - ct_hook->destroy(nfct); + if (ct_hook) + ct_hook->destroy(nfct); rcu_read_unlock(); + + WARN_ON(!ct_hook); } EXPORT_SYMBOL(nf_conntrack_destroy); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index e12b52019a55..b613de96ad85 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -1170,11 +1170,12 @@ static int __init nf_conntrack_standalone_init(void) nf_conntrack_htable_size_user = nf_conntrack_htable_size; #endif + nf_conntrack_init_end(); + ret = register_pernet_subsys(&nf_conntrack_net_ops); if (ret < 0) goto out_pernet; - nf_conntrack_init_end(); return 0; out_pernet: From f92557f79a60cb142258f5fa7194f327573fadd8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 16:56:34 +0000 Subject: [PATCH 3071/4345] netlink: annotate accesses to nlk->cb_running [ Upstream commit a939d14919b799e6fff8a9c80296ca229ba2f8a4 ] Both netlink_recvmsg() and netlink_native_seq_show() read nlk->cb_running locklessly. Use READ_ONCE() there. Add corresponding WRITE_ONCE() to netlink_dump() and __netlink_dump_start() syzbot reported: BUG: KCSAN: data-race in __netlink_dump_start / netlink_recvmsg write to 0xffff88813ea4db59 of 1 bytes by task 28219 on cpu 0: __netlink_dump_start+0x3af/0x4d0 net/netlink/af_netlink.c:2399 netlink_dump_start include/linux/netlink.h:308 [inline] rtnetlink_rcv_msg+0x70f/0x8c0 net/core/rtnetlink.c:6130 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2577 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6192 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1942 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] sock_write_iter+0x1aa/0x230 net/socket.c:1138 call_write_iter include/linux/fs.h:1851 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x463/0x760 fs/read_write.c:584 ksys_write+0xeb/0x1a0 fs/read_write.c:637 __do_sys_write fs/read_write.c:649 [inline] __se_sys_write fs/read_write.c:646 [inline] __x64_sys_write+0x42/0x50 fs/read_write.c:646 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff88813ea4db59 of 1 bytes by task 28222 on cpu 1: netlink_recvmsg+0x3b4/0x730 net/netlink/af_netlink.c:2022 sock_recvmsg_nosec+0x4c/0x80 net/socket.c:1017 ____sys_recvmsg+0x2db/0x310 net/socket.c:2718 ___sys_recvmsg net/socket.c:2762 [inline] do_recvmmsg+0x2e5/0x710 net/socket.c:2856 __sys_recvmmsg net/socket.c:2935 [inline] __do_sys_recvmmsg net/socket.c:2958 [inline] __se_sys_recvmmsg net/socket.c:2951 [inline] __x64_sys_recvmmsg+0xe2/0x160 net/socket.c:2951 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x00 -> 0x01 Fixes: 16b304f3404f ("netlink: Eliminate kmalloc in netlink dump operation.") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index eedb16517f16..651f8ca912af 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1992,7 +1992,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - if (nlk->cb_running && + if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk); if (ret) { @@ -2304,7 +2304,7 @@ static int netlink_dump(struct sock *sk) if (cb->done) cb->done(cb); - nlk->cb_running = false; + WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; mutex_unlock(nlk->cb_mutex); @@ -2367,7 +2367,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, goto error_put; } - nlk->cb_running = true; + WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; mutex_unlock(nlk->cb_mutex); @@ -2653,7 +2653,7 @@ static int netlink_native_seq_show(struct seq_file *seq, void *v) nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), - nlk->cb_running, + READ_ONCE(nlk->cb_running), refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) From 1b33bdd76635cf4f1de30ef48be87fca309c9e25 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 16:35:53 +0000 Subject: [PATCH 3072/4345] net: annotate sk->sk_err write from do_recvmmsg() [ Upstream commit e05a5f510f26607616fecdd4ac136310c8bea56b ] do_recvmmsg() can write to sk->sk_err from multiple threads. As said before, many other points reading or writing sk_err need annotations. Fixes: 34b88a68f26a ("net: Fix use after free in the recvmmsg exit path") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/socket.c b/net/socket.c index 8657112a687a..84223419da86 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2764,7 +2764,7 @@ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg, * error to return on the next call or if the * app asks about it using getsockopt(SO_ERROR). */ - sock->sk->sk_err = -err; + WRITE_ONCE(sock->sk->sk_err, -err); } out_put: fput_light(sock->file, fput_needed); From 4493914009609d6351b3a41dfe3b0ac5209bd4c6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 18:29:48 +0000 Subject: [PATCH 3073/4345] net: deal with most data-races in sk_wait_event() [ Upstream commit d0ac89f6f9879fae316c155de77b5173b3e2c9c9 ] __condition is evaluated twice in sk_wait_event() macro. First invocation is lockless, and reads can race with writes, as spotted by syzbot. BUG: KCSAN: data-race in sk_stream_wait_connect / tcp_disconnect write to 0xffff88812d83d6a0 of 4 bytes by task 9065 on cpu 1: tcp_disconnect+0x2cd/0xdb0 inet_shutdown+0x19e/0x1f0 net/ipv4/af_inet.c:911 __sys_shutdown_sock net/socket.c:2343 [inline] __sys_shutdown net/socket.c:2355 [inline] __do_sys_shutdown net/socket.c:2363 [inline] __se_sys_shutdown+0xf8/0x140 net/socket.c:2361 __x64_sys_shutdown+0x31/0x40 net/socket.c:2361 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff88812d83d6a0 of 4 bytes by task 9040 on cpu 0: sk_stream_wait_connect+0x1de/0x3a0 net/core/stream.c:75 tcp_sendmsg_locked+0x2e4/0x2120 net/ipv4/tcp.c:1266 tcp_sendmsg+0x30/0x50 net/ipv4/tcp.c:1484 inet6_sendmsg+0x63/0x80 net/ipv6/af_inet6.c:651 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] __sys_sendto+0x246/0x300 net/socket.c:2142 __do_sys_sendto net/socket.c:2154 [inline] __se_sys_sendto net/socket.c:2150 [inline] __x64_sys_sendto+0x78/0x90 net/socket.c:2150 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x00000000 -> 0x00000068 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/stream.c | 12 ++++++------ net/ipv4/tcp_bpf.c | 2 +- net/llc/af_llc.c | 8 +++++--- net/smc/smc_close.c | 4 ++-- net/smc/smc_rx.c | 4 ++-- net/smc/smc_tx.c | 4 ++-- net/tipc/socket.c | 4 ++-- net/tls/tls_main.c | 3 ++- 8 files changed, 22 insertions(+), 19 deletions(-) diff --git a/net/core/stream.c b/net/core/stream.c index cd60746877b1..422ee97e4f2b 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -73,8 +73,8 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending++; done = sk_wait_event(sk, timeo_p, - !sk->sk_err && - !((1 << sk->sk_state) & + !READ_ONCE(sk->sk_err) && + !((1 << READ_ONCE(sk->sk_state)) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending--; @@ -87,9 +87,9 @@ EXPORT_SYMBOL(sk_stream_wait_connect); * sk_stream_closing - Return 1 if we still have things to send in our buffers. * @sk: socket to verify */ -static inline int sk_stream_closing(struct sock *sk) +static int sk_stream_closing(const struct sock *sk) { - return (1 << sk->sk_state) & + return (1 << READ_ONCE(sk->sk_state)) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK); } @@ -142,8 +142,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; - sk_wait_event(sk, ¤t_timeo, sk->sk_err || - (sk->sk_shutdown & SEND_SHUTDOWN) || + sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || + (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || (sk_stream_memory_free(sk) && !vm_wait), &wait); sk->sk_write_pending--; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 926e29e84b40..d0ca1fc325cd 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -262,7 +262,7 @@ static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); ret = sk_wait_event(sk, &timeo, !list_empty(&psock->ingress_msg) || - !skb_queue_empty(&sk->sk_receive_queue), &wait); + !skb_queue_empty_lockless(&sk->sk_receive_queue), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return ret; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 99a37c411323..01e26698285a 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -582,7 +582,8 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout) add_wait_queue(sk_sleep(sk), &wait); while (1) { - if (sk_wait_event(sk, &timeout, sk->sk_state == TCP_CLOSE, &wait)) + if (sk_wait_event(sk, &timeout, + READ_ONCE(sk->sk_state) == TCP_CLOSE, &wait)) break; rc = -ERESTARTSYS; if (signal_pending(current)) @@ -602,7 +603,8 @@ static bool llc_ui_wait_for_conn(struct sock *sk, long timeout) add_wait_queue(sk_sleep(sk), &wait); while (1) { - if (sk_wait_event(sk, &timeout, sk->sk_state != TCP_SYN_SENT, &wait)) + if (sk_wait_event(sk, &timeout, + READ_ONCE(sk->sk_state) != TCP_SYN_SENT, &wait)) break; if (signal_pending(current) || !timeout) break; @@ -621,7 +623,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout) while (1) { rc = 0; if (sk_wait_event(sk, &timeout, - (sk->sk_shutdown & RCV_SHUTDOWN) || + (READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN) || (!llc_data_accept_state(llc->state) && !llc->remote_busy_flag && !llc->p_flag), &wait)) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 84102db5bb31..149a59ecd299 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -64,8 +64,8 @@ static void smc_close_stream_wait(struct smc_sock *smc, long timeout) rc = sk_wait_event(sk, &timeout, !smc_tx_prepared_sends(&smc->conn) || - sk->sk_err == ECONNABORTED || - sk->sk_err == ECONNRESET || + READ_ONCE(sk->sk_err) == ECONNABORTED || + READ_ONCE(sk->sk_err) == ECONNRESET || smc->conn.killed, &wait); if (rc) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 7f7e983e42b1..3757aff6c2f0 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -203,9 +203,9 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); add_wait_queue(sk_sleep(sk), &wait); rc = sk_wait_event(sk, timeo, - sk->sk_err || + READ_ONCE(sk->sk_err) || cflags->peer_conn_abort || - sk->sk_shutdown & RCV_SHUTDOWN || + READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN || conn->killed || fcrit(conn), &wait); diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 52ef1fca0b60..2429f9fc7e0e 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -110,8 +110,8 @@ static int smc_tx_wait(struct smc_sock *smc, int flags) break; /* at least 1 byte of free & no urgent data */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk_wait_event(sk, &timeo, - sk->sk_err || - (sk->sk_shutdown & SEND_SHUTDOWN) || + READ_ONCE(sk->sk_err) || + (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || smc_cdc_rxed_any_close(conn) || (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend), diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 8f3c9fbb9916..7cf9b40b5c73 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -300,9 +300,9 @@ static void tsk_rej_rx_queue(struct sock *sk, int error) tipc_sk_respond(sk, skb, error); } -static bool tipc_sk_connected(struct sock *sk) +static bool tipc_sk_connected(const struct sock *sk) { - return sk->sk_state == TIPC_ESTABLISHED; + return READ_ONCE(sk->sk_state) == TIPC_ESTABLISHED; } /* tipc_sk_type_connectionless - check if the socket is datagram socket diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 54863e68f304..7ee3c8b03a39 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -92,7 +92,8 @@ int wait_on_pending_writer(struct sock *sk, long *timeo) break; } - if (sk_wait_event(sk, timeo, !sk->sk_write_pending, &wait)) + if (sk_wait_event(sk, timeo, + !READ_ONCE(sk->sk_write_pending), &wait)) break; } remove_wait_queue(sk_sleep(sk), &wait); From 9ccf3edbafba96e9619f1196433005fcf7c2937f Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 14 Jan 2021 18:32:38 -0800 Subject: [PATCH 3074/4345] net: tap: check vlan with eth_type_vlan() method [ Upstream commit b69df2608281b71575fbb3b9f426dbcc4be8a700 ] Replace some checks for ETH_P_8021Q and ETH_P_8021AD in drivers/net/tap.c with eth_type_vlan. Signed-off-by: Menglong Dong Link: https://lore.kernel.org/r/20210115023238.4681-1-dong.menglong@zte.com.cn Signed-off-by: Jakub Kicinski Stable-dep-of: 4063384ef762 ("net: add vlan_get_protocol_and_depth() helper") Signed-off-by: Sasha Levin --- drivers/net/tap.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index d9018d9fe310..aed3b1cd80f2 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -713,8 +713,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control, skb_probe_transport_header(skb); /* Move network header to the right position for VLAN tagged packets */ - if ((skb->protocol == htons(ETH_P_8021Q) || - skb->protocol == htons(ETH_P_8021AD)) && + if (eth_type_vlan(skb->protocol) && __vlan_get_protocol(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); @@ -1165,8 +1164,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) } /* Move network header to the right position for VLAN tagged packets */ - if ((skb->protocol == htons(ETH_P_8021Q) || - skb->protocol == htons(ETH_P_8021AD)) && + if (eth_type_vlan(skb->protocol) && __vlan_get_protocol(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); From 34a5ee69ec6273f0aee79e7ce4d14afc83ca8122 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 13:18:57 +0000 Subject: [PATCH 3075/4345] net: add vlan_get_protocol_and_depth() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4063384ef762cc5946fc7a3f89879e76c6ec51e2 ] Before blamed commit, pskb_may_pull() was used instead of skb_header_pointer() in __vlan_get_protocol() and friends. Few callers depended on skb->head being populated with MAC header, syzbot caught one of them (skb_mac_gso_segment()) Add vlan_get_protocol_and_depth() to make the intent clearer and use it where sensible. This is a more generic fix than commit e9d3f80935b6 ("net/af_packet: make sure to pull mac header") which was dealing with a similar issue. kernel BUG at include/linux/skbuff.h:2655 ! invalid opcode: 0000 [#1] SMP KASAN CPU: 0 PID: 1441 Comm: syz-executor199 Not tainted 6.1.24-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023 RIP: 0010:__skb_pull include/linux/skbuff.h:2655 [inline] RIP: 0010:skb_mac_gso_segment+0x68f/0x6a0 net/core/gro.c:136 Code: fd 48 8b 5c 24 10 44 89 6b 70 48 c7 c7 c0 ae 0d 86 44 89 e6 e8 a1 91 d0 00 48 c7 c7 00 af 0d 86 48 89 de 31 d2 e8 d1 4a e9 ff <0f> 0b 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 RSP: 0018:ffffc90001bd7520 EFLAGS: 00010286 RAX: ffffffff8469736a RBX: ffff88810f31dac0 RCX: ffff888115a18b00 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffc90001bd75e8 R08: ffffffff84697183 R09: fffff5200037adf9 R10: 0000000000000000 R11: dffffc0000000001 R12: 0000000000000012 R13: 000000000000fee5 R14: 0000000000005865 R15: 000000000000fed7 FS: 000055555633f300(0000) GS:ffff8881f6a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 0000000116fea000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: [] __skb_gso_segment+0x32d/0x4c0 net/core/dev.c:3419 [] skb_gso_segment include/linux/netdevice.h:4819 [inline] [] validate_xmit_skb+0x3aa/0xee0 net/core/dev.c:3725 [] __dev_queue_xmit+0x1332/0x3300 net/core/dev.c:4313 [] dev_queue_xmit+0x17/0x20 include/linux/netdevice.h:3029 [] packet_snd net/packet/af_packet.c:3111 [inline] [] packet_sendmsg+0x49d2/0x6470 net/packet/af_packet.c:3142 [] sock_sendmsg_nosec net/socket.c:716 [inline] [] sock_sendmsg net/socket.c:736 [inline] [] __sys_sendto+0x472/0x5f0 net/socket.c:2139 [] __do_sys_sendto net/socket.c:2151 [inline] [] __se_sys_sendto net/socket.c:2147 [inline] [] __x64_sys_sendto+0xe5/0x100 net/socket.c:2147 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x2f/0x50 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 469aceddfa3e ("vlan: consolidate VLAN parsing code and limit max parsing depth") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Toke Høiland-Jørgensen Cc: Willem de Bruijn Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/tap.c | 4 ++-- include/linux/if_vlan.h | 17 +++++++++++++++++ net/bridge/br_forward.c | 2 +- net/core/dev.c | 2 +- net/packet/af_packet.c | 6 ++---- 5 files changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index aed3b1cd80f2..f9b3eb2d8d8b 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -714,7 +714,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control, /* Move network header to the right position for VLAN tagged packets */ if (eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); rcu_read_lock(); @@ -1165,7 +1165,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) /* Move network header to the right position for VLAN tagged packets */ if (eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); rcu_read_lock(); diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 41a518336673..4e7e72f3da5b 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -626,6 +626,23 @@ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) return __vlan_get_protocol(skb, skb->protocol, NULL); } +/* This version of __vlan_get_protocol() also pulls mac header in skb->head */ +static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb, + __be16 type, int *depth) +{ + int maclen; + + type = __vlan_get_protocol(skb, type, &maclen); + + if (type) { + if (!pskb_may_pull(skb, maclen)) + type = 0; + else if (depth) + *depth = maclen; + } + return type; +} + /* A getter for the SKB protocol field which will handle VLAN tags consistently * whether VLAN acceleration is enabled or not. */ diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index e28ffadd1371..4610f3a13966 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -43,7 +43,7 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb skb->protocol == htons(ETH_P_8021AD))) { int depth; - if (!__vlan_get_protocol(skb, skb->protocol, &depth)) + if (!vlan_get_protocol_and_depth(skb, skb->protocol, &depth)) goto drop; skb_set_network_header(skb, depth); diff --git a/net/core/dev.c b/net/core/dev.c index 413c2a08d79d..1eaf224a90ce 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3320,7 +3320,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) type = eth->h_proto; } - return __vlan_get_protocol(skb, type, depth); + return vlan_get_protocol_and_depth(skb, type, depth); } /** diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2e766490a739..3c05414cd3f8 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1897,10 +1897,8 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) { - if (pskb_may_pull(skb, depth)) - skb_set_network_header(skb, depth); - } + vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) + skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } From f86568eca4c9808cc5e5aa3759ebba96c40b0131 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 16 Nov 2020 10:48:04 +0100 Subject: [PATCH 3076/4345] tcp: factor out __tcp_close() helper [ Upstream commit 77c3c95637526f1e4330cc9a4b2065f668c2c4fe ] unlocked version of protocol level close, will be used by MPTCP to allow decouple orphaning and subflow level close. Signed-off-by: Paolo Abeni Signed-off-by: Jakub Kicinski Stable-dep-of: e14cadfd80d7 ("tcp: add annotations around sk->sk_shutdown accesses") Signed-off-by: Sasha Levin --- include/net/tcp.h | 1 + net/ipv4/tcp.c | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 9a8d98639b20..d213b86a4822 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -381,6 +381,7 @@ void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); +void __tcp_close(struct sock *sk, long timeout); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6a0560a735ce..3666fa307d0f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2510,13 +2510,12 @@ bool tcp_check_oom(struct sock *sk, int shift) return too_many_orphans || out_of_socket_memory; } -void tcp_close(struct sock *sk, long timeout) +void __tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; int data_was_unread = 0; int state; - lock_sock(sk); sk->sk_shutdown = SHUTDOWN_MASK; if (sk->sk_state == TCP_LISTEN) { @@ -2680,6 +2679,12 @@ adjudge_to_death: out: bh_unlock_sock(sk); local_bh_enable(); +} + +void tcp_close(struct sock *sk, long timeout) +{ + lock_sock(sk); + __tcp_close(sk, timeout); release_sock(sk); sock_put(sk); } From 963fe9ed862697f43ac35e972709fcf76199236f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 20:36:56 +0000 Subject: [PATCH 3077/4345] tcp: add annotations around sk->sk_shutdown accesses [ Upstream commit e14cadfd80d76f01bfaa1a8d745b1db19b57d6be ] Now sk->sk_shutdown is no longer a bitfield, we can add standard READ_ONCE()/WRITE_ONCE() annotations to silence KCSAN reports like the following: BUG: KCSAN: data-race in tcp_disconnect / tcp_poll write to 0xffff88814588582c of 1 bytes by task 3404 on cpu 1: tcp_disconnect+0x4d6/0xdb0 net/ipv4/tcp.c:3121 __inet_stream_connect+0x5dd/0x6e0 net/ipv4/af_inet.c:715 inet_stream_connect+0x48/0x70 net/ipv4/af_inet.c:727 __sys_connect_file net/socket.c:2001 [inline] __sys_connect+0x19b/0x1b0 net/socket.c:2018 __do_sys_connect net/socket.c:2028 [inline] __se_sys_connect net/socket.c:2025 [inline] __x64_sys_connect+0x41/0x50 net/socket.c:2025 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff88814588582c of 1 bytes by task 3374 on cpu 0: tcp_poll+0x2e6/0x7d0 net/ipv4/tcp.c:562 sock_poll+0x253/0x270 net/socket.c:1383 vfs_poll include/linux/poll.h:88 [inline] io_poll_check_events io_uring/poll.c:281 [inline] io_poll_task_func+0x15a/0x820 io_uring/poll.c:333 handle_tw_list io_uring/io_uring.c:1184 [inline] tctx_task_work+0x1fe/0x4d0 io_uring/io_uring.c:1246 task_work_run+0x123/0x160 kernel/task_work.c:179 get_signal+0xe64/0xff0 kernel/signal.c:2635 arch_do_signal_or_restart+0x89/0x2a0 arch/x86/kernel/signal.c:306 exit_to_user_mode_loop+0x6f/0xe0 kernel/entry/common.c:168 exit_to_user_mode_prepare+0x6c/0xb0 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x26/0x140 kernel/entry/common.c:297 do_syscall_64+0x4d/0xc0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x03 -> 0x00 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/af_inet.c | 2 +- net/ipv4/tcp.c | 14 ++++++++------ net/ipv4/tcp_input.c | 4 ++-- 3 files changed, 11 insertions(+), 9 deletions(-) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8dab0d311aba..800c2c7607e1 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -884,7 +884,7 @@ int inet_shutdown(struct socket *sock, int how) EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ fallthrough; default: - sk->sk_shutdown |= how; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how); if (sk->sk_prot->shutdown) sk->sk_prot->shutdown(sk, how); break; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3666fa307d0f..eecce63ba25e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -506,6 +506,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); + u8 shutdown; int state; sock_poll_wait(file, sock, wait); @@ -548,9 +549,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ - if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ @@ -566,7 +568,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tcp_stream_is_readable(tp, target, sk)) mask |= EPOLLIN | EPOLLRDNORM; - if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { + if (!(shutdown & SEND_SHUTDOWN)) { if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ @@ -2516,7 +2518,7 @@ void __tcp_close(struct sock *sk, long timeout) int data_was_unread = 0; int state; - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); @@ -2782,7 +2784,7 @@ int tcp_disconnect(struct sock *sk, int flags) if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); - sk->sk_shutdown = 0; + WRITE_ONCE(sk->sk_shutdown, 0); sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); @@ -4169,7 +4171,7 @@ void tcp_done(struct sock *sk) if (req) reqsk_fastopen_remove(sk, req, false); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 541758cd0b81..b98b7920c402 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4323,7 +4323,7 @@ void tcp_fin(struct sock *sk) inet_csk_schedule_ack(sk); - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); sock_set_flag(sk, SOCK_DONE); switch (sk->sk_state) { @@ -6504,7 +6504,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) break; tcp_set_state(sk, TCP_FIN_WAIT2); - sk->sk_shutdown |= SEND_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN); sk_dst_confirm(sk); From f4a371d3f5a7a71dff1ab48b3122c5cf23cc7ad5 Mon Sep 17 00:00:00 2001 From: "t.feng" Date: Wed, 10 May 2023 11:50:44 +0800 Subject: [PATCH 3078/4345] ipvlan:Fix out-of-bounds caused by unclear skb->cb [ Upstream commit 90cbed5247439a966b645b34eb0a2e037836ea8e ] If skb enqueue the qdisc, fq_skb_cb(skb)->time_to_send is changed which is actually skb->cb, and IPCB(skb_in)->opt will be used in __ip_options_echo. It is possible that memcpy is out of bounds and lead to stack overflow. We should clear skb->cb before ip_local_out or ip6_local_out. v2: 1. clean the stack info 2. use IPCB/IP6CB instead of skb->cb crash on stable-5.10(reproduce in kasan kernel). Stack info: [ 2203.651571] BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0x589/0x800 [ 2203.653327] Write of size 4 at addr ffff88811a388f27 by task swapper/3/0 [ 2203.655460] CPU: 3 PID: 0 Comm: swapper/3 Kdump: loaded Not tainted 5.10.0-60.18.0.50.h856.kasan.eulerosv2r11.x86_64 #1 [ 2203.655466] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-20181220_000000-szxrtosci10000 04/01/2014 [ 2203.655475] Call Trace: [ 2203.655481] [ 2203.655501] dump_stack+0x9c/0xd3 [ 2203.655514] print_address_description.constprop.0+0x19/0x170 [ 2203.655530] __kasan_report.cold+0x6c/0x84 [ 2203.655586] kasan_report+0x3a/0x50 [ 2203.655594] check_memory_region+0xfd/0x1f0 [ 2203.655601] memcpy+0x39/0x60 [ 2203.655608] __ip_options_echo+0x589/0x800 [ 2203.655654] __icmp_send+0x59a/0x960 [ 2203.655755] nf_send_unreach+0x129/0x3d0 [nf_reject_ipv4] [ 2203.655763] reject_tg+0x77/0x1bf [ipt_REJECT] [ 2203.655772] ipt_do_table+0x691/0xa40 [ip_tables] [ 2203.655821] nf_hook_slow+0x69/0x100 [ 2203.655828] __ip_local_out+0x21e/0x2b0 [ 2203.655857] ip_local_out+0x28/0x90 [ 2203.655868] ipvlan_process_v4_outbound+0x21e/0x260 [ipvlan] [ 2203.655931] ipvlan_xmit_mode_l3+0x3bd/0x400 [ipvlan] [ 2203.655967] ipvlan_queue_xmit+0xb3/0x190 [ipvlan] [ 2203.655977] ipvlan_start_xmit+0x2e/0xb0 [ipvlan] [ 2203.655984] xmit_one.constprop.0+0xe1/0x280 [ 2203.655992] dev_hard_start_xmit+0x62/0x100 [ 2203.656000] sch_direct_xmit+0x215/0x640 [ 2203.656028] __qdisc_run+0x153/0x1f0 [ 2203.656069] __dev_queue_xmit+0x77f/0x1030 [ 2203.656173] ip_finish_output2+0x59b/0xc20 [ 2203.656244] __ip_finish_output.part.0+0x318/0x3d0 [ 2203.656312] ip_finish_output+0x168/0x190 [ 2203.656320] ip_output+0x12d/0x220 [ 2203.656357] __ip_queue_xmit+0x392/0x880 [ 2203.656380] __tcp_transmit_skb+0x1088/0x11c0 [ 2203.656436] __tcp_retransmit_skb+0x475/0xa30 [ 2203.656505] tcp_retransmit_skb+0x2d/0x190 [ 2203.656512] tcp_retransmit_timer+0x3af/0x9a0 [ 2203.656519] tcp_write_timer_handler+0x3ba/0x510 [ 2203.656529] tcp_write_timer+0x55/0x180 [ 2203.656542] call_timer_fn+0x3f/0x1d0 [ 2203.656555] expire_timers+0x160/0x200 [ 2203.656562] run_timer_softirq+0x1f4/0x480 [ 2203.656606] __do_softirq+0xfd/0x402 [ 2203.656613] asm_call_irq_on_stack+0x12/0x20 [ 2203.656617] [ 2203.656623] do_softirq_own_stack+0x37/0x50 [ 2203.656631] irq_exit_rcu+0x134/0x1a0 [ 2203.656639] sysvec_apic_timer_interrupt+0x36/0x80 [ 2203.656646] asm_sysvec_apic_timer_interrupt+0x12/0x20 [ 2203.656654] RIP: 0010:default_idle+0x13/0x20 [ 2203.656663] Code: 89 f0 5d 41 5c 41 5d 41 5e c3 cc cc cc cc cc cc cc cc cc cc cc cc cc 0f 1f 44 00 00 0f 1f 44 00 00 0f 00 2d 9f 32 57 00 fb f4 cc cc cc cc 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 41 54 be 08 [ 2203.656668] RSP: 0018:ffff88810036fe78 EFLAGS: 00000256 [ 2203.656676] RAX: ffffffffaf2a87f0 RBX: ffff888100360000 RCX: ffffffffaf290191 [ 2203.656681] RDX: 0000000000098b5e RSI: 0000000000000004 RDI: ffff88811a3c4f60 [ 2203.656686] RBP: 0000000000000000 R08: 0000000000000001 R09: ffff88811a3c4f63 [ 2203.656690] R10: ffffed10234789ec R11: 0000000000000001 R12: 0000000000000003 [ 2203.656695] R13: ffff888100360000 R14: 0000000000000000 R15: 0000000000000000 [ 2203.656729] default_idle_call+0x5a/0x150 [ 2203.656735] cpuidle_idle_call+0x1c6/0x220 [ 2203.656780] do_idle+0xab/0x100 [ 2203.656786] cpu_startup_entry+0x19/0x20 [ 2203.656793] secondary_startup_64_no_verify+0xc2/0xcb [ 2203.657409] The buggy address belongs to the page: [ 2203.658648] page:0000000027a9842f refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x11a388 [ 2203.658665] flags: 0x17ffffc0001000(reserved|node=0|zone=2|lastcpupid=0x1fffff) [ 2203.658675] raw: 0017ffffc0001000 ffffea000468e208 ffffea000468e208 0000000000000000 [ 2203.658682] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 [ 2203.658686] page dumped because: kasan: bad access detected To reproduce(ipvlan with IPVLAN_MODE_L3): Env setting: ======================================================= modprobe ipvlan ipvlan_default_mode=1 sysctl net.ipv4.conf.eth0.forwarding=1 iptables -t nat -A POSTROUTING -s 20.0.0.0/255.255.255.0 -o eth0 -j MASQUERADE ip link add gw link eth0 type ipvlan ip -4 addr add 20.0.0.254/24 dev gw ip netns add net1 ip link add ipv1 link eth0 type ipvlan ip link set ipv1 netns net1 ip netns exec net1 ip link set ipv1 up ip netns exec net1 ip -4 addr add 20.0.0.4/24 dev ipv1 ip netns exec net1 route add default gw 20.0.0.254 ip netns exec net1 tc qdisc add dev ipv1 root netem loss 10% ifconfig gw up iptables -t filter -A OUTPUT -p tcp --dport 8888 -j REJECT --reject-with icmp-port-unreachable ======================================================= And then excute the shell(curl any address of eth0 can reach): for((i=1;i<=100000;i++)) do ip netns exec net1 curl x.x.x.x:8888 done ======================================================= Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.") Signed-off-by: "t.feng" Suggested-by: Florian Westphal Reviewed-by: Paolo Abeni Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ipvlan/ipvlan_core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index a33149ee0ddc..0a5b5ff597c6 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -437,6 +437,9 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) goto err; } skb_dst_set(skb, &rt->dst); + + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + err = ip_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; @@ -475,6 +478,9 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) goto err; } skb_dst_set(skb, dst); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + err = ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; From fb6ac4b5bdfed70b507e500eb903b9c0f03cda3b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 17:31:31 +0000 Subject: [PATCH 3079/4345] net: datagram: fix data-races in datagram_poll() [ Upstream commit 5bca1d081f44c9443e61841842ce4e9179d327b6 ] datagram_poll() runs locklessly, we should add READ_ONCE() annotations while reading sk->sk_err, sk->sk_shutdown and sk->sk_state. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230509173131.3263780-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/datagram.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/net/core/datagram.c b/net/core/datagram.c index bc92683fdcdb..9e77695d1bdc 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -799,18 +799,21 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, { struct sock *sk = sock->sk; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; /* exceptional events? */ - if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) + if (READ_ONCE(sk->sk_err) || + !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (sk->sk_shutdown & RCV_SHUTDOWN) + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* readable? */ @@ -819,10 +822,12 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, /* Connection-based need to check for termination and startup */ if (connection_based(sk)) { - if (sk->sk_state == TCP_CLOSE) + int state = READ_ONCE(sk->sk_state); + + if (state == TCP_CLOSE) mask |= EPOLLHUP; /* connection hasn't started yet? */ - if (sk->sk_state == TCP_SYN_SENT) + if (state == TCP_SYN_SENT) return mask; } From 9b977b0cbb6dd8d8d58f8e41390db9a7986b8e0c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 9 May 2023 17:34:55 -0700 Subject: [PATCH 3080/4345] af_unix: Fix a data race of sk->sk_receive_queue->qlen. [ Upstream commit 679ed006d416ea0cecfe24a99d365d1dea69c683 ] KCSAN found a data race of sk->sk_receive_queue->qlen where recvmsg() updates qlen under the queue lock and sendmsg() checks qlen under unix_state_sock(), not the queue lock, so the reader side needs READ_ONCE(). BUG: KCSAN: data-race in __skb_try_recv_from_queue / unix_wait_for_peer write (marked) to 0xffff888019fe7c68 of 4 bytes by task 49792 on cpu 0: __skb_unlink include/linux/skbuff.h:2347 [inline] __skb_try_recv_from_queue+0x3de/0x470 net/core/datagram.c:197 __skb_try_recv_datagram+0xf7/0x390 net/core/datagram.c:263 __unix_dgram_recvmsg+0x109/0x8a0 net/unix/af_unix.c:2452 unix_dgram_recvmsg+0x94/0xa0 net/unix/af_unix.c:2549 sock_recvmsg_nosec net/socket.c:1019 [inline] ____sys_recvmsg+0x3a3/0x3b0 net/socket.c:2720 ___sys_recvmsg+0xc8/0x150 net/socket.c:2764 do_recvmmsg+0x182/0x560 net/socket.c:2858 __sys_recvmmsg net/socket.c:2937 [inline] __do_sys_recvmmsg net/socket.c:2960 [inline] __se_sys_recvmmsg net/socket.c:2953 [inline] __x64_sys_recvmmsg+0x153/0x170 net/socket.c:2953 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc read to 0xffff888019fe7c68 of 4 bytes by task 49793 on cpu 1: skb_queue_len include/linux/skbuff.h:2127 [inline] unix_recvq_full net/unix/af_unix.c:229 [inline] unix_wait_for_peer+0x154/0x1a0 net/unix/af_unix.c:1445 unix_dgram_sendmsg+0x13bc/0x14b0 net/unix/af_unix.c:2048 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x148/0x160 net/socket.c:747 ____sys_sendmsg+0x20e/0x620 net/socket.c:2503 ___sys_sendmsg+0xc6/0x140 net/socket.c:2557 __sys_sendmmsg+0x11d/0x370 net/socket.c:2643 __do_sys_sendmmsg net/socket.c:2672 [inline] __se_sys_sendmmsg net/socket.c:2669 [inline] __x64_sys_sendmmsg+0x58/0x70 net/socket.c:2669 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc value changed: 0x0000000b -> 0x00000001 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 49793 Comm: syz-executor.0 Not tainted 6.3.0-rc7-02330-gca6270c12e20 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: Michal Kubiak Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 28721e9575b7..a21027536856 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1236,7 +1236,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo) sched = !sock_flag(other, SOCK_DEAD) && !(other->sk_shutdown & RCV_SHUTDOWN) && - unix_recvq_full(other); + unix_recvq_full_lockless(other); unix_state_unlock(other); From 8307e372e7445ec7d3cd2ff107ce5078eaa02815 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 9 May 2023 17:34:56 -0700 Subject: [PATCH 3081/4345] af_unix: Fix data races around sk->sk_shutdown. [ Upstream commit e1d09c2c2f5793474556b60f83900e088d0d366d ] KCSAN found a data race around sk->sk_shutdown where unix_release_sock() and unix_shutdown() update it under unix_state_lock(), OTOH unix_poll() and unix_dgram_poll() read it locklessly. We need to annotate the writes and reads with WRITE_ONCE() and READ_ONCE(). BUG: KCSAN: data-race in unix_poll / unix_release_sock write to 0xffff88800d0f8aec of 1 bytes by task 264 on cpu 0: unix_release_sock+0x75c/0x910 net/unix/af_unix.c:631 unix_release+0x59/0x80 net/unix/af_unix.c:1042 __sock_release+0x7d/0x170 net/socket.c:653 sock_close+0x19/0x30 net/socket.c:1397 __fput+0x179/0x5e0 fs/file_table.c:321 ____fput+0x15/0x20 fs/file_table.c:349 task_work_run+0x116/0x1a0 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x174/0x180 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x1a/0x30 kernel/entry/common.c:297 do_syscall_64+0x4b/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x72/0xdc read to 0xffff88800d0f8aec of 1 bytes by task 222 on cpu 1: unix_poll+0xa3/0x2a0 net/unix/af_unix.c:3170 sock_poll+0xcf/0x2b0 net/socket.c:1385 vfs_poll include/linux/poll.h:88 [inline] ep_item_poll.isra.0+0x78/0xc0 fs/eventpoll.c:855 ep_send_events fs/eventpoll.c:1694 [inline] ep_poll fs/eventpoll.c:1823 [inline] do_epoll_wait+0x6c4/0xea0 fs/eventpoll.c:2258 __do_sys_epoll_wait fs/eventpoll.c:2270 [inline] __se_sys_epoll_wait fs/eventpoll.c:2265 [inline] __x64_sys_epoll_wait+0xcc/0x190 fs/eventpoll.c:2265 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc value changed: 0x00 -> 0x03 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 222 Comm: dbus-broker Not tainted 6.3.0-rc7-02330-gca6270c12e20 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 3c73419c09a5 ("af_unix: fix 'poll for write'/ connected DGRAM sockets") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: Michal Kubiak Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/unix/af_unix.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index a21027536856..2fe0efcbfed1 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -529,7 +529,7 @@ static void unix_release_sock(struct sock *sk, int embrion) /* Clear state */ unix_state_lock(sk); sock_orphan(sk); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); path = u->path; u->path.dentry = NULL; u->path.mnt = NULL; @@ -547,7 +547,7 @@ static void unix_release_sock(struct sock *sk, int embrion) if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); /* No more writes */ - skpair->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); if (!skb_queue_empty(&sk->sk_receive_queue) || embrion) skpair->sk_err = ECONNRESET; unix_state_unlock(skpair); @@ -2581,7 +2581,7 @@ static int unix_shutdown(struct socket *sock, int mode) ++mode; unix_state_lock(sk); - sk->sk_shutdown |= mode; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | mode); other = unix_peer(sk); if (other) sock_hold(other); @@ -2598,7 +2598,7 @@ static int unix_shutdown(struct socket *sock, int mode) if (mode&SEND_SHUTDOWN) peer_mode |= RCV_SHUTDOWN; unix_state_lock(other); - other->sk_shutdown |= peer_mode; + WRITE_ONCE(other->sk_shutdown, other->sk_shutdown | peer_mode); unix_state_unlock(other); other->sk_state_change(other); if (peer_mode == SHUTDOWN_MASK) @@ -2717,16 +2717,18 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa { struct sock *sk = sock->sk; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); /* exceptional events? */ if (sk->sk_err) mask |= EPOLLERR; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; /* readable? */ @@ -2754,18 +2756,20 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk, *other; unsigned int writable; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); /* exceptional events? */ if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* readable? */ From bd6b353671fc4b9b2f9134cf049fa49c21dfed91 Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Tue, 18 Apr 2023 07:04:30 -0700 Subject: [PATCH 3082/4345] drm/i915/dp: prevent potential div-by-zero [ Upstream commit 0ff80028e2702c7c3d78b69705dc47c1ccba8c39 ] drm_dp_dsc_sink_max_slice_count() may return 0 if something goes wrong on the part of the DSC sink and its DPCD register. This null value may be later used as a divisor in intel_dsc_compute_params(), which will lead to an error. In the unlikely event that this issue occurs, fix it by testing the return value of drm_dp_dsc_sink_max_slice_count() against zero. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: a4a157777c80 ("drm/i915/dp: Compute DSC pipe config in atomic check") Signed-off-by: Nikita Zhandarovich Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20230418140430.69902-1-n.zhandarovich@fintech.ru (cherry picked from commit 51f7008239de011370c5067bbba07f0207f06b72) Signed-off-by: Joonas Lahtinen Signed-off-by: Sasha Levin --- drivers/gpu/drm/i915/display/intel_dp.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 1c1931f5c958..7f633f8b3239 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -2281,6 +2281,11 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp, pipe_config->dsc.slice_count = drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd, true); + if (!pipe_config->dsc.slice_count) { + drm_dbg_kms(&dev_priv->drm, "Unsupported Slice Count %d\n", + pipe_config->dsc.slice_count); + return -EINVAL; + } } else { u16 dsc_max_output_bpp; u8 dsc_dp_slice_count; From df1be652a45f0b2d0c60c154aa78ae87687f482c Mon Sep 17 00:00:00 2001 From: Zongjie Li Date: Tue, 9 May 2023 19:27:26 +0800 Subject: [PATCH 3083/4345] fbdev: arcfb: Fix error handling in arcfb_probe() [ Upstream commit 5a6bef734247c7a8c19511664ff77634ab86f45b ] Smatch complains that: arcfb_probe() warn: 'irq' from request_irq() not released on lines: 587. Fix error handling in the arcfb_probe() function. If IO addresses are not provided or framebuffer registration fails, the code will jump to the err_addr or err_register_fb label to release resources. If IRQ request fails, previously allocated resources will be freed. Fixes: 1154ea7dcd8e ("[PATCH] Framebuffer driver for Arc LCD board") Signed-off-by: Zongjie Li Reviewed-by: Dongliang Mu Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/arcfb.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/video/fbdev/arcfb.c b/drivers/video/fbdev/arcfb.c index 1447324ed0b6..08da436265d9 100644 --- a/drivers/video/fbdev/arcfb.c +++ b/drivers/video/fbdev/arcfb.c @@ -523,7 +523,7 @@ static int arcfb_probe(struct platform_device *dev) info = framebuffer_alloc(sizeof(struct arcfb_par), &dev->dev); if (!info) - goto err; + goto err_fb_alloc; info->screen_base = (char __iomem *)videomemory; info->fbops = &arcfb_ops; @@ -535,7 +535,7 @@ static int arcfb_probe(struct platform_device *dev) if (!dio_addr || !cio_addr || !c2io_addr) { printk(KERN_WARNING "no IO addresses supplied\n"); - goto err1; + goto err_addr; } par->dio_addr = dio_addr; par->cio_addr = cio_addr; @@ -551,12 +551,12 @@ static int arcfb_probe(struct platform_device *dev) printk(KERN_INFO "arcfb: Failed req IRQ %d\n", par->irq); retval = -EBUSY; - goto err1; + goto err_addr; } } retval = register_framebuffer(info); if (retval < 0) - goto err1; + goto err_register_fb; platform_set_drvdata(dev, info); fb_info(info, "Arc frame buffer device, using %dK of video memory\n", videomemorysize >> 10); @@ -580,9 +580,12 @@ static int arcfb_probe(struct platform_device *dev) } return 0; -err1: + +err_register_fb: + free_irq(par->irq, info); +err_addr: framebuffer_release(info); -err: +err_fb_alloc: vfree(videomemory); return retval; } From efd18a91c9c246abcbe413e10eeef0a4c4bb22e7 Mon Sep 17 00:00:00 2001 From: Austin Kim Date: Tue, 24 Aug 2021 04:49:29 +0100 Subject: [PATCH 3084/4345] ext4: remove an unused variable warning with CONFIG_QUOTA=n MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3bbef91bdd2180c67407285ba160b023eb4d5306 ] The 'enable_quota' variable is only used in an CONFIG_QUOTA. With CONFIG_QUOTA=n, compiler causes a harmless warning: fs/ext4/super.c: In function ‘ext4_remount’: fs/ext4/super.c:5840:6: warning: variable ‘enable_quota’ set but not used [-Wunused-but-set-variable] int enable_quota = 0; ^~~~~ Move 'enable_quota' into the same #ifdef CONFIG_QUOTA block to remove an unused variable warning. Signed-off-by: Austin Kim Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20210824034929.GA13415@raspberrypi Signed-off-by: Theodore Ts'o Stable-dep-of: a44be64bbecb ("ext4: don't clear SB_RDONLY when remounting r/w until quota is re-enabled") Signed-off-by: Sasha Levin --- fs/ext4/super.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8694be513241..d75aa45a846d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5792,11 +5792,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long old_sb_flags, vfs_flags; struct ext4_mount_options old_opts; - int enable_quota = 0; ext4_group_t g; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; int err = 0; #ifdef CONFIG_QUOTA + int enable_quota = 0; int i, j; char *to_free[EXT4_MAXQUOTAS]; #endif @@ -5994,7 +5994,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) err = -EROFS; goto restore_opts; } +#ifdef CONFIG_QUOTA enable_quota = 1; +#endif } } From 8284c7592d90cb3199597e24bdfd2419ec70a8b6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 27 Apr 2023 22:49:34 -0400 Subject: [PATCH 3085/4345] ext4: reflect error codes from ext4_multi_mount_protect() to its callers [ Upstream commit 3b50d5018ed06a647bb26c44bb5ae74e59c903c7 ] This will allow more fine-grained errno codes to be returned by the mount system call. Cc: Andreas Dilger Signed-off-by: Theodore Ts'o Stable-dep-of: a44be64bbecb ("ext4: don't clear SB_RDONLY when remounting r/w until quota is re-enabled") Signed-off-by: Sasha Levin --- fs/ext4/mmp.c | 9 ++++++++- fs/ext4/super.c | 16 +++++++++------- 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index bc364c119af6..92c863fd9a78 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -290,6 +290,7 @@ int ext4_multi_mount_protect(struct super_block *sb, if (mmp_block < le32_to_cpu(es->s_first_data_block) || mmp_block >= ext4_blocks_count(es)) { ext4_warning(sb, "Invalid MMP block in superblock"); + retval = -EINVAL; goto failed; } @@ -315,6 +316,7 @@ int ext4_multi_mount_protect(struct super_block *sb, if (seq == EXT4_MMP_SEQ_FSCK) { dump_mmp_msg(sb, mmp, "fsck is running on the filesystem"); + retval = -EBUSY; goto failed; } @@ -328,6 +330,7 @@ int ext4_multi_mount_protect(struct super_block *sb, if (schedule_timeout_interruptible(HZ * wait_time) != 0) { ext4_warning(sb, "MMP startup interrupted, failing mount\n"); + retval = -ETIMEDOUT; goto failed; } @@ -338,6 +341,7 @@ int ext4_multi_mount_protect(struct super_block *sb, if (seq != le32_to_cpu(mmp->mmp_seq)) { dump_mmp_msg(sb, mmp, "Device is already active on another node."); + retval = -EBUSY; goto failed; } @@ -357,6 +361,7 @@ skip: */ if (schedule_timeout_interruptible(HZ * wait_time) != 0) { ext4_warning(sb, "MMP startup interrupted, failing mount"); + retval = -ETIMEDOUT; goto failed; } @@ -367,6 +372,7 @@ skip: if (seq != le32_to_cpu(mmp->mmp_seq)) { dump_mmp_msg(sb, mmp, "Device is already active on another node."); + retval = -EBUSY; goto failed; } @@ -383,6 +389,7 @@ skip: EXT4_SB(sb)->s_mmp_tsk = NULL; ext4_warning(sb, "Unable to create kmmpd thread for %s.", sb->s_id); + retval = -ENOMEM; goto failed; } @@ -390,5 +397,5 @@ skip: failed: brelse(bh); - return 1; + return retval; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d75aa45a846d..edd140966393 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4777,9 +4777,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) needs_recovery = (es->s_last_orphan != 0 || ext4_has_feature_journal_needs_recovery(sb)); - if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb)) - if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block))) + if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb)) { + err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); + if (err) goto failed_mount3a; + } /* * The first inode we look at is the journal inode. Don't try @@ -5988,12 +5990,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; sb->s_flags &= ~SB_RDONLY; - if (ext4_has_feature_mmp(sb)) - if (ext4_multi_mount_protect(sb, - le64_to_cpu(es->s_mmp_block))) { - err = -EROFS; + if (ext4_has_feature_mmp(sb)) { + err = ext4_multi_mount_protect(sb, + le64_to_cpu(es->s_mmp_block)); + if (err) goto restore_opts; - } + } #ifdef CONFIG_QUOTA enable_quota = 1; #endif From 5c87115520d2451f5689be7d9a463450d5b1bd96 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 5 May 2023 21:02:30 -0400 Subject: [PATCH 3086/4345] ext4: don't clear SB_RDONLY when remounting r/w until quota is re-enabled [ Upstream commit a44be64bbecb15a452496f60db6eacfee2b59c79 ] When a file system currently mounted read/only is remounted read/write, if we clear the SB_RDONLY flag too early, before the quota is initialized, and there is another process/thread constantly attempting to create a directory, it's possible to trigger the WARN_ON_ONCE(dquot_initialize_needed(inode)); in ext4_xattr_block_set(), with the following stack trace: WARNING: CPU: 0 PID: 5338 at fs/ext4/xattr.c:2141 ext4_xattr_block_set+0x2ef2/0x3680 RIP: 0010:ext4_xattr_block_set+0x2ef2/0x3680 fs/ext4/xattr.c:2141 Call Trace: ext4_xattr_set_handle+0xcd4/0x15c0 fs/ext4/xattr.c:2458 ext4_initxattrs+0xa3/0x110 fs/ext4/xattr_security.c:44 security_inode_init_security+0x2df/0x3f0 security/security.c:1147 __ext4_new_inode+0x347e/0x43d0 fs/ext4/ialloc.c:1324 ext4_mkdir+0x425/0xce0 fs/ext4/namei.c:2992 vfs_mkdir+0x29d/0x450 fs/namei.c:4038 do_mkdirat+0x264/0x520 fs/namei.c:4061 __do_sys_mkdirat fs/namei.c:4076 [inline] __se_sys_mkdirat fs/namei.c:4074 [inline] __x64_sys_mkdirat+0x89/0xa0 fs/namei.c:4074 Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230506142419.984260-1-tytso@mit.edu Reported-by: syzbot+6385d7d3065524c5ca6d@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=6513f6cb5cd6b5fc9f37e3bb70d273b94be9c34c Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/super.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index edd140966393..681efff3af50 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5797,6 +5797,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_group_t g; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; int err = 0; + int enable_rw = 0; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; @@ -5989,7 +5990,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (err) goto restore_opts; - sb->s_flags &= ~SB_RDONLY; + enable_rw = 1; if (ext4_has_feature_mmp(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); @@ -6048,6 +6049,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); + if (enable_rw) + sb->s_flags &= ~SB_RDONLY; + if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); From d48b7eea946905a6a77494909993ac4989017746 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 11 Apr 2023 14:10:19 +0200 Subject: [PATCH 3087/4345] ext4: fix lockdep warning when enabling MMP [ Upstream commit 949f95ff39bf188e594e7ecd8e29b82eb108f5bf ] When we enable MMP in ext4_multi_mount_protect() during mount or remount, we end up calling sb_start_write() from write_mmp_block(). This triggers lockdep warning because freeze protection ranks above s_umount semaphore we are holding during mount / remount. The problem is harmless because we are guaranteed the filesystem is not frozen during mount / remount but still let's fix the warning by not grabbing freeze protection from ext4_multi_mount_protect(). Cc: stable@kernel.org Reported-by: syzbot+6b7df7d5506b32467149@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=ab7e5b6f400b7778d46f01841422e5718fb81843 Signed-off-by: Jan Kara Reviewed-by: Christian Brauner Link: https://lore.kernel.org/r/20230411121019.21940-1-jack@suse.cz Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mmp.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 92c863fd9a78..7a9a8ed1de66 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -39,28 +39,36 @@ static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) * Write the MMP block using REQ_SYNC to try to get the block on-disk * faster. */ -static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) +static int write_mmp_block_thawed(struct super_block *sb, + struct buffer_head *bh) { struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data); - /* - * We protect against freezing so that we don't create dirty buffers - * on frozen filesystem. - */ - sb_start_write(sb); ext4_mmp_csum_set(sb, mmp); lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE, REQ_SYNC | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); - sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) return -EIO; - return 0; } +static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) +{ + int err; + + /* + * We protect against freezing so that we don't create dirty buffers + * on frozen filesystem. + */ + sb_start_write(sb); + err = write_mmp_block_thawed(sb, bh); + sb_end_write(sb); + return err; +} + /* * Read the MMP block. It _must_ be read from disk and hence we clear the * uptodate flag on the buffer. @@ -352,7 +360,11 @@ skip: seq = mmp_new_seq(); mmp->mmp_seq = cpu_to_le32(seq); - retval = write_mmp_block(sb, bh); + /* + * On mount / remount we are protected against fs freezing (by s_umount + * semaphore) and grabbing freeze protection upsets lockdep + */ + retval = write_mmp_block_thawed(sb, bh); if (retval) goto failed; From 0983142c5f17a62055ec851372273c3bc77e4788 Mon Sep 17 00:00:00 2001 From: Chunguang Xu Date: Sat, 7 Nov 2020 23:58:12 +0800 Subject: [PATCH 3088/4345] ext4: remove redundant mb_regenerate_buddy() [ Upstream commit 6bd97bf273bdb4944904e57480f6545bca48ad77 ] After this patch (163a203), if an abnormal bitmap is detected, we will mark the group as corrupt, and we will not use this group in the future. Therefore, it should be meaningless to regenerate the buddy bitmap of this group, It might be better to delete it. Signed-off-by: Chunguang Xu Reviewed-by: Andreas Dilger Link: https://lore.kernel.org/r/1604764698-4269-2-git-send-email-brookxu@tencent.com Signed-off-by: Theodore Ts'o Stable-dep-of: 5354b2af3406 ("ext4: allow ext4_get_group_info() to fail") Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a7c42e4bfc5e..708a5fa3c69f 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -822,24 +822,6 @@ void ext4_mb_generate_buddy(struct super_block *sb, spin_unlock(&sbi->s_bal_lock); } -static void mb_regenerate_buddy(struct ext4_buddy *e4b) -{ - int count; - int order = 1; - void *buddy; - - while ((buddy = mb_find_buddy(e4b, order++, &count))) { - ext4_set_bits(buddy, 0, count); - } - e4b->bd_info->bb_fragments = 0; - memset(e4b->bd_info->bb_counters, 0, - sizeof(*e4b->bd_info->bb_counters) * - (e4b->bd_sb->s_blocksize_bits + 2)); - - ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, - e4b->bd_bitmap, e4b->bd_group); -} - /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1512,7 +1494,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } - mb_regenerate_buddy(e4b); goto done; } From 9b6a0c140e2790b5418560cc3c97bb23773cff8d Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Thu, 1 Apr 2021 10:21:23 -0700 Subject: [PATCH 3089/4345] ext4: drop s_mb_bal_lock and convert protected fields to atomic [ Upstream commit 67d25186046145748d5fe4c5019d832215e01c1e ] s_mb_buddies_generated gets used later in this patch series to determine if the cr 0 and cr 1 optimziations should be performed or not. Currently, s_mb_buddies_generated is protected under a spin_lock. In the allocation path, it is better if we don't depend on the lock and instead read the value atomically. In order to do that, we drop s_bal_lock altogether and we convert the only two protected fields by it s_mb_buddies_generated and s_mb_generation_time to atomic type. Signed-off-by: Harshad Shirwadkar Reviewed-by: Andreas Dilger Reviewed-by: Ritesh Harjani Link: https://lore.kernel.org/r/20210401172129.189766-2-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o Stable-dep-of: 5354b2af3406 ("ext4: allow ext4_get_group_info() to fail") Signed-off-by: Sasha Levin --- fs/ext4/ext4.h | 5 ++--- fs/ext4/mballoc.c | 13 +++++-------- 2 files changed, 7 insertions(+), 11 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 246573a4e804..5efd48d7c9a7 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1538,9 +1538,8 @@ struct ext4_sb_info { atomic_t s_bal_goals; /* goal hits */ atomic_t s_bal_breaks; /* too long searches */ atomic_t s_bal_2orders; /* 2^order hits */ - spinlock_t s_bal_lock; - unsigned long s_mb_buddies_generated; - unsigned long long s_mb_generation_time; + atomic_t s_mb_buddies_generated; /* number of buddies generated */ + atomic64_t s_mb_generation_time; atomic_t s_mb_lost_chunks; atomic_t s_mb_preallocated; atomic_t s_mb_discarded; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 708a5fa3c69f..beee54480562 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -816,10 +816,8 @@ void ext4_mb_generate_buddy(struct super_block *sb, clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; - spin_lock(&sbi->s_bal_lock); - sbi->s_mb_buddies_generated++; - sbi->s_mb_generation_time += period; - spin_unlock(&sbi->s_bal_lock); + atomic_inc(&sbi->s_mb_buddies_generated); + atomic64_add(period, &sbi->s_mb_generation_time); } /* The buddy information is attached the buddy cache inode @@ -2855,7 +2853,6 @@ int ext4_mb_init(struct super_block *sb) } while (i <= sb->s_blocksize_bits + 1); spin_lock_init(&sbi->s_md_lock); - spin_lock_init(&sbi->s_bal_lock); sbi->s_mb_free_pending = 0; INIT_LIST_HEAD(&sbi->s_freed_data_list); @@ -2991,9 +2988,9 @@ int ext4_mb_release(struct super_block *sb) atomic_read(&sbi->s_bal_breaks), atomic_read(&sbi->s_mb_lost_chunks)); ext4_msg(sb, KERN_INFO, - "mballoc: %lu generated and it took %Lu", - sbi->s_mb_buddies_generated, - sbi->s_mb_generation_time); + "mballoc: %u generated and it took %llu", + atomic_read(&sbi->s_mb_buddies_generated), + atomic64_read(&sbi->s_mb_generation_time)); ext4_msg(sb, KERN_INFO, "mballoc: %u preallocated, %u discarded", atomic_read(&sbi->s_mb_preallocated), From 8669fff0d0cd8e1948c2e35fd8a367c809b4452f Mon Sep 17 00:00:00 2001 From: Harshad Shirwadkar Date: Thu, 1 Apr 2021 10:21:25 -0700 Subject: [PATCH 3090/4345] ext4: add mballoc stats proc file [ Upstream commit a6c75eaf11032f4a3d2b3ce2265a194ac6e4a7f0 ] Add new stats for measuring the performance of mballoc. This patch is forked from Artem Blagodarenko's work that can be found here: https://github.com/lustre/lustre-release/blob/master/ldiskfs/kernel_patches/patches/rhel8/ext4-simple-blockalloc.patch This patch reorganizes the stats by cr level. This is how the output looks like: mballoc: reqs: 0 success: 0 groups_scanned: 0 cr0_stats: hits: 0 groups_considered: 0 useless_loops: 0 bad_suggestions: 0 cr1_stats: hits: 0 groups_considered: 0 useless_loops: 0 bad_suggestions: 0 cr2_stats: hits: 0 groups_considered: 0 useless_loops: 0 cr3_stats: hits: 0 groups_considered: 0 useless_loops: 0 extents_scanned: 0 goal_hits: 0 2^n_hits: 0 breaks: 0 lost: 0 buddies_generated: 0/40 buddies_time_used: 0 preallocated: 0 discarded: 0 Signed-off-by: Harshad Shirwadkar Reviewed-by: Andreas Dilger Reviewed-by: Ritesh Harjani Link: https://lore.kernel.org/r/20210401172129.189766-4-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o Stable-dep-of: 5354b2af3406 ("ext4: allow ext4_get_group_info() to fail") Signed-off-by: Sasha Levin --- fs/ext4/ext4.h | 5 ++++ fs/ext4/mballoc.c | 75 +++++++++++++++++++++++++++++++++++++++++++++-- fs/ext4/sysfs.c | 2 ++ 3 files changed, 80 insertions(+), 2 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5efd48d7c9a7..1de55d8e0d35 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1535,9 +1535,13 @@ struct ext4_sb_info { atomic_t s_bal_success; /* we found long enough chunks */ atomic_t s_bal_allocated; /* in blocks */ atomic_t s_bal_ex_scanned; /* total extents scanned */ + atomic_t s_bal_groups_scanned; /* number of groups scanned */ atomic_t s_bal_goals; /* goal hits */ atomic_t s_bal_breaks; /* too long searches */ atomic_t s_bal_2orders; /* 2^order hits */ + atomic64_t s_bal_cX_groups_considered[4]; + atomic64_t s_bal_cX_hits[4]; + atomic64_t s_bal_cX_failed[4]; /* cX loop didn't find blocks */ atomic_t s_mb_buddies_generated; /* number of buddies generated */ atomic64_t s_mb_generation_time; atomic_t s_mb_lost_chunks; @@ -2784,6 +2788,7 @@ int ext4_fc_record_regions(struct super_block *sb, int ino, extern const struct seq_operations ext4_mb_seq_groups_ops; extern long ext4_mb_stats; extern long ext4_mb_max_to_scan; +extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset); extern int ext4_mb_init(struct super_block *); extern int ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index beee54480562..aa51d1b83727 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2151,6 +2151,8 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_grpblk_t free; int ret = 0; + if (sbi->s_mb_stats) + atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]); if (should_lock) ext4_lock_group(sb, group); free = grp->bb_free; @@ -2425,6 +2427,9 @@ repeat: if (ac->ac_status != AC_STATUS_CONTINUE) break; } + /* Processed all groups and haven't found blocks */ + if (sbi->s_mb_stats && i == ngroups) + atomic64_inc(&sbi->s_bal_cX_failed[cr]); } if (ac->ac_b_ex.fe_len > 0 && ac->ac_status != AC_STATUS_FOUND && @@ -2454,6 +2459,9 @@ repeat: goto repeat; } } + + if (sbi->s_mb_stats && ac->ac_status == AC_STATUS_FOUND) + atomic64_inc(&sbi->s_bal_cX_hits[ac->ac_criteria]); out: if (!err && ac->ac_status != AC_STATUS_FOUND && first_err) err = first_err; @@ -2553,6 +2561,67 @@ const struct seq_operations ext4_mb_seq_groups_ops = { .show = ext4_mb_seq_groups_show, }; +int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) +{ + struct super_block *sb = (struct super_block *)seq->private; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + seq_puts(seq, "mballoc:\n"); + if (!sbi->s_mb_stats) { + seq_puts(seq, "\tmb stats collection turned off.\n"); + seq_puts(seq, "\tTo enable, please write \"1\" to sysfs file mb_stats.\n"); + return 0; + } + seq_printf(seq, "\treqs: %u\n", atomic_read(&sbi->s_bal_reqs)); + seq_printf(seq, "\tsuccess: %u\n", atomic_read(&sbi->s_bal_success)); + + seq_printf(seq, "\tgroups_scanned: %u\n", atomic_read(&sbi->s_bal_groups_scanned)); + + seq_puts(seq, "\tcr0_stats:\n"); + seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[0])); + seq_printf(seq, "\t\tgroups_considered: %llu\n", + atomic64_read(&sbi->s_bal_cX_groups_considered[0])); + seq_printf(seq, "\t\tuseless_loops: %llu\n", + atomic64_read(&sbi->s_bal_cX_failed[0])); + + seq_puts(seq, "\tcr1_stats:\n"); + seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[1])); + seq_printf(seq, "\t\tgroups_considered: %llu\n", + atomic64_read(&sbi->s_bal_cX_groups_considered[1])); + seq_printf(seq, "\t\tuseless_loops: %llu\n", + atomic64_read(&sbi->s_bal_cX_failed[1])); + + seq_puts(seq, "\tcr2_stats:\n"); + seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[2])); + seq_printf(seq, "\t\tgroups_considered: %llu\n", + atomic64_read(&sbi->s_bal_cX_groups_considered[2])); + seq_printf(seq, "\t\tuseless_loops: %llu\n", + atomic64_read(&sbi->s_bal_cX_failed[2])); + + seq_puts(seq, "\tcr3_stats:\n"); + seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[3])); + seq_printf(seq, "\t\tgroups_considered: %llu\n", + atomic64_read(&sbi->s_bal_cX_groups_considered[3])); + seq_printf(seq, "\t\tuseless_loops: %llu\n", + atomic64_read(&sbi->s_bal_cX_failed[3])); + seq_printf(seq, "\textents_scanned: %u\n", atomic_read(&sbi->s_bal_ex_scanned)); + seq_printf(seq, "\t\tgoal_hits: %u\n", atomic_read(&sbi->s_bal_goals)); + seq_printf(seq, "\t\t2^n_hits: %u\n", atomic_read(&sbi->s_bal_2orders)); + seq_printf(seq, "\t\tbreaks: %u\n", atomic_read(&sbi->s_bal_breaks)); + seq_printf(seq, "\t\tlost: %u\n", atomic_read(&sbi->s_mb_lost_chunks)); + + seq_printf(seq, "\tbuddies_generated: %u/%u\n", + atomic_read(&sbi->s_mb_buddies_generated), + ext4_get_groups_count(sb)); + seq_printf(seq, "\tbuddies_time_used: %llu\n", + atomic64_read(&sbi->s_mb_generation_time)); + seq_printf(seq, "\tpreallocated: %u\n", + atomic_read(&sbi->s_mb_preallocated)); + seq_printf(seq, "\tdiscarded: %u\n", + atomic_read(&sbi->s_mb_discarded)); + return 0; +} + static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) { int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; @@ -2980,9 +3049,10 @@ int ext4_mb_release(struct super_block *sb) atomic_read(&sbi->s_bal_reqs), atomic_read(&sbi->s_bal_success)); ext4_msg(sb, KERN_INFO, - "mballoc: %u extents scanned, %u goal hits, " + "mballoc: %u extents scanned, %u groups scanned, %u goal hits, " "%u 2^N hits, %u breaks, %u lost", atomic_read(&sbi->s_bal_ex_scanned), + atomic_read(&sbi->s_bal_groups_scanned), atomic_read(&sbi->s_bal_goals), atomic_read(&sbi->s_bal_2orders), atomic_read(&sbi->s_bal_breaks), @@ -3620,12 +3690,13 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - if (sbi->s_mb_stats && ac->ac_g_ex.fe_len > 1) { + if (sbi->s_mb_stats && ac->ac_g_ex.fe_len >= 1) { atomic_inc(&sbi->s_bal_reqs); atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated); if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len) atomic_inc(&sbi->s_bal_success); atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned); + atomic_add(ac->ac_groups_scanned, &sbi->s_bal_groups_scanned); if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start && ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group) atomic_inc(&sbi->s_bal_goals); diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index ce74cde6d8fa..b0bb4a92c9c9 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -539,6 +539,8 @@ int ext4_register_sysfs(struct super_block *sb) ext4_fc_info_show, sb); proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc, &ext4_mb_seq_groups_ops, sb); + proc_create_single_data("mb_stats", 0444, sbi->s_proc, + ext4_seq_mb_stats_show, sb); } return 0; } From 371d8b8ea0cb48de9777aaf7193abd544c200297 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Sat, 4 Mar 2023 01:21:02 +0800 Subject: [PATCH 3091/4345] ext4: allow to find by goal if EXT4_MB_HINT_GOAL_ONLY is set [ Upstream commit 01e4ca29451760b9ac10b4cdc231c52150842643 ] If EXT4_MB_HINT_GOAL_ONLY is set, ext4_mb_regular_allocator will only allocate blocks from ext4_mb_find_by_goal. Allow to find by goal in ext4_mb_find_by_goal if EXT4_MB_HINT_GOAL_ONLY is set or allocation with EXT4_MB_HINT_GOAL_ONLY set will always fail. EXT4_MB_HINT_GOAL_ONLY is not used at all, so the problem is not found for now. Signed-off-by: Kemeng Shi Reviewed-by: Ojaswin Mujoo Link: https://lore.kernel.org/r/20230303172120.3800725-3-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Stable-dep-of: 5354b2af3406 ("ext4: allow ext4_get_group_info() to fail") Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index aa51d1b83727..84d74ba02b37 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1864,7 +1864,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; - if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL)) + if (!(ac->ac_flags & (EXT4_MB_HINT_TRY_GOAL | EXT4_MB_HINT_GOAL_ONLY))) return 0; if (grp->bb_free == 0) return 0; From 100c0ad6c04597fefeaaba2bb1827cc015d95067 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 29 Apr 2023 00:06:28 -0400 Subject: [PATCH 3092/4345] ext4: allow ext4_get_group_info() to fail [ Upstream commit 5354b2af34064a4579be8bc0e2f15a7b70f14b5f ] Previously, ext4_get_group_info() would treat an invalid group number as BUG(), since in theory it should never happen. However, if a malicious attaker (or fuzzer) modifies the superblock via the block device while it is the file system is mounted, it is possible for s_first_data_block to get set to a very large number. In that case, when calculating the block group of some block number (such as the starting block of a preallocation region), could result in an underflow and very large block group number. Then the BUG_ON check in ext4_get_group_info() would fire, resutling in a denial of service attack that can be triggered by root or someone with write access to the block device. For a quality of implementation perspective, it's best that even if the system administrator does something that they shouldn't, that it will not trigger a BUG. So instead of BUG'ing, ext4_get_group_info() will call ext4_error and return NULL. We also add fallback code in all of the callers of ext4_get_group_info() that it might NULL. Also, since ext4_get_group_info() was already borderline to be an inline function, un-inline it. The results in a next reduction of the compiled text size of ext4 by roughly 2k. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230430154311.579720-2-tytso@mit.edu Reported-by: syzbot+e2efa3efc15a1c9e95c3@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=69b28112e098b070f639efb356393af3ffec4220 Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara Signed-off-by: Sasha Levin --- fs/ext4/balloc.c | 18 ++++++++++++- fs/ext4/ext4.h | 15 ++--------- fs/ext4/ialloc.c | 12 ++++++--- fs/ext4/mballoc.c | 64 +++++++++++++++++++++++++++++++++++++++-------- fs/ext4/super.c | 2 ++ 5 files changed, 82 insertions(+), 29 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 50a0e90e8af9..a43167042b6b 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -319,6 +319,22 @@ static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, return (next_zero_bit < bitmap_size ? next_zero_bit : 0); } +struct ext4_group_info *ext4_get_group_info(struct super_block *sb, + ext4_group_t group) +{ + struct ext4_group_info **grp_info; + long indexv, indexh; + + if (unlikely(group >= EXT4_SB(sb)->s_groups_count)) { + ext4_error(sb, "invalid group %u", group); + return NULL; + } + indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); + indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); + grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); + return grp_info[indexh]; +} + /* * Return the block number which was discovered to be invalid, or 0 if * the block bitmap is valid. @@ -393,7 +409,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb, if (buffer_verified(bh)) return 0; - if (EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + if (!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; ext4_lock_group(sb, block_group); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1de55d8e0d35..84a240025aa4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2551,6 +2551,8 @@ extern void ext4_check_blocks_bitmap(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, struct buffer_head ** bh); +extern struct ext4_group_info *ext4_get_group_info(struct super_block *sb, + ext4_group_t group); extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb, @@ -3198,19 +3200,6 @@ static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) raw_inode->i_size_high = cpu_to_le32(i_size >> 32); } -static inline -struct ext4_group_info *ext4_get_group_info(struct super_block *sb, - ext4_group_t group) -{ - struct ext4_group_info **grp_info; - long indexv, indexh; - BUG_ON(group >= EXT4_SB(sb)->s_groups_count); - indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); - indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); - return grp_info[indexh]; -} - /* * Reading s_groups_count requires using smp_rmb() afterwards. See * the locking protocol documented in the comments of ext4_group_add() diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index c53c9b132204..d178543ca13f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -91,7 +91,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, if (buffer_verified(bh)) return 0; - if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) + if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; ext4_lock_group(sb, block_group); @@ -293,7 +293,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) } if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, block_group); - if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) { + if (!grp || unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) { fatal = -EFSCORRUPTED; goto error_return; } @@ -1045,7 +1045,7 @@ got_group: * Skip groups with already-known suspicious inode * tables */ - if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) + if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) goto next_group; } @@ -1180,6 +1180,10 @@ got: if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, group); + if (!grp) { + err = -EFSCORRUPTED; + goto out; + } down_read(&grp->alloc_sem); /* * protect vs itable * lazyinit @@ -1523,7 +1527,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, } gdp = ext4_get_group_desc(sb, group, &group_desc_bh); - if (!gdp) + if (!gdp || !grp) goto out; /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 84d74ba02b37..f18aa35b82b0 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -684,6 +684,8 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments); grp = ext4_get_group_info(sb, e4b->bd_group); + if (!grp) + return NULL; list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; @@ -767,9 +769,9 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) static noinline_for_stack void ext4_mb_generate_buddy(struct super_block *sb, - void *buddy, void *bitmap, ext4_group_t group) + void *buddy, void *bitmap, ext4_group_t group, + struct ext4_group_info *grp) { - struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; @@ -889,6 +891,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) break; grinfo = ext4_get_group_info(sb, group); + if (!grinfo) + continue; /* * If page is uptodate then we came here after online resize * which added some new uninitialized group info structs, so @@ -954,6 +958,10 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) group, page->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); grinfo = ext4_get_group_info(sb, group); + if (!grinfo) { + err = -EFSCORRUPTED; + goto out; + } grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * @@ -964,7 +972,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) ext4_lock_group(sb, group); /* init the buddy */ memset(data, 0xff, blocksize); - ext4_mb_generate_buddy(sb, data, incore, group); + ext4_mb_generate_buddy(sb, data, incore, group, grinfo); ext4_unlock_group(sb, group); incore = NULL; } else { @@ -1078,6 +1086,9 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) might_sleep(); mb_debug(sb, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); + if (!this_grp) + return -EFSCORRUPTED; + /* * This ensures that we don't reinit the buddy cache * page which map to the group from which we are already @@ -1152,6 +1163,8 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, blocks_per_page = PAGE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); + if (!grp) + return -EFSCORRUPTED; e4b->bd_blkbits = sb->s_blocksize_bits; e4b->bd_info = grp; @@ -1864,6 +1877,8 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; + if (!grp) + return -EFSCORRUPTED; if (!(ac->ac_flags & (EXT4_MB_HINT_TRY_GOAL | EXT4_MB_HINT_GOAL_ONLY))) return 0; if (grp->bb_free == 0) @@ -2088,7 +2103,7 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp) || !grp)) return false; free = grp->bb_free; @@ -2151,6 +2166,8 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_grpblk_t free; int ret = 0; + if (!grp) + return -EFSCORRUPTED; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]); if (should_lock) @@ -2223,7 +2240,7 @@ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, * prefetch once, so we avoid getblk() call, which can * be expensive. */ - if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) && + if (gdp && grp && !EXT4_MB_GRP_TEST_AND_SET_READ(grp) && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && @@ -2267,7 +2284,7 @@ void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, group--; grp = ext4_get_group_info(sb, group); - if (EXT4_MB_GRP_NEED_INIT(grp) && + if (grp && gdp && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { @@ -2525,6 +2542,8 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) sizeof(struct ext4_group_info); grinfo = ext4_get_group_info(sb, group); + if (!grinfo) + return 0; /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { err = ext4_mb_load_buddy(sb, group, &e4b); @@ -2535,7 +2554,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) buddy_loaded = 1; } - memcpy(&sg, ext4_get_group_info(sb, group), i); + memcpy(&sg, grinfo, i); if (buddy_loaded) ext4_mb_unload_buddy(&e4b); @@ -2812,8 +2831,12 @@ static int ext4_mb_init_backend(struct super_block *sb) err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); - while (i-- > 0) - kmem_cache_free(cachep, ext4_get_group_info(sb, i)); + while (i-- > 0) { + struct ext4_group_info *grp = ext4_get_group_info(sb, i); + + if (grp) + kmem_cache_free(cachep, grp); + } i = sbi->s_group_info_size; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); @@ -3020,6 +3043,8 @@ int ext4_mb_release(struct super_block *sb) for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); + if (!grinfo) + continue; mb_group_bb_bitmap_free(grinfo); ext4_lock_group(sb, i); count = ext4_mb_cleanup_pa(grinfo); @@ -3933,6 +3958,8 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, struct ext4_free_data *entry; grp = ext4_get_group_info(sb, group); + if (!grp) + return; n = rb_first(&(grp->bb_free_root)); while (n) { @@ -3960,6 +3987,9 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, int preallocated = 0; int len; + if (!grp) + return; + /* all form of preallocation discards first load group, * so the only competing code is preallocation use. * we don't need any locking here @@ -4151,6 +4181,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) ei = EXT4_I(ac->ac_inode); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); + if (!grp) + return; pa->pa_obj_lock = &ei->i_prealloc_lock; pa->pa_inode = ac->ac_inode; @@ -4204,6 +4236,8 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac) atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); + if (!grp) + return; lg = ac->ac_lg; BUG_ON(lg == NULL); @@ -4332,6 +4366,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, int err; int free = 0; + if (!grp) + return 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) goto out_dbg; @@ -4569,6 +4605,9 @@ static inline void ext4_mb_show_pa(struct super_block *sb) struct ext4_prealloc_space *pa; ext4_grpblk_t start; struct list_head *cur; + + if (!grp) + continue; ext4_lock_group(sb, i); list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, @@ -5372,6 +5411,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; struct ext4_group_desc *gdp; + struct ext4_group_info *grp; unsigned int overflow; ext4_grpblk_t bit; struct buffer_head *gd_bh; @@ -5397,8 +5437,8 @@ do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT( - ext4_get_group_info(sb, block_group)))) + grp = ext4_get_group_info(sb, block_group); + if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return; /* @@ -5986,6 +6026,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); + if (!grp) + continue; /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { ret = ext4_mb_init_group(sb, group, GFP_NOFS); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 681efff3af50..d89750e90bc4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1011,6 +1011,8 @@ void ext4_mark_group_bitmap_corrupted(struct super_block *sb, struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; + if (!grp || !gdp) + return; if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); From e4842de4ec13d60e042d915b64c9134e135e0d11 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 31 Jan 2023 16:12:18 -0800 Subject: [PATCH 3093/4345] refscale: Move shutdown from wait_event() to wait_event_idle() [ Upstream commit 6bc6e6b27524304aadb9c04611ddb1c84dd7617a ] The ref_scale_shutdown() kthread/function uses wait_event() to wait for the refscale test to complete. However, although the read-side tests are normally extremely fast, there is no law against specifying a very large value for the refscale.loops module parameter or against having a slow read-side primitive. Either way, this might well trigger the hung-task timeout. This commit therefore replaces those wait_event() calls with calls to wait_event_idle(), which do not trigger the hung-task timeout. Signed-off-by: Paul E. McKenney Signed-off-by: Boqun Feng Signed-off-by: Sasha Levin --- kernel/rcu/refscale.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c index 952595c678b3..4e419ca6d611 100644 --- a/kernel/rcu/refscale.c +++ b/kernel/rcu/refscale.c @@ -625,7 +625,7 @@ ref_scale_cleanup(void) static int ref_scale_shutdown(void *arg) { - wait_event(shutdown_wq, shutdown_start); + wait_event_idle(shutdown_wq, shutdown_start); smp_mb(); // Wake before output. ref_scale_cleanup(); From a7d21b8585894e6fff973f6ddae42f02b13f600f Mon Sep 17 00:00:00 2001 From: Zqiang Date: Sat, 24 Dec 2022 13:25:53 +0800 Subject: [PATCH 3094/4345] rcu: Protect rcu_print_task_exp_stall() ->exp_tasks access [ Upstream commit 3c1566bca3f8349f12b75d0a2d5e4a20ad6262ec ] For kernels built with CONFIG_PREEMPT_RCU=y, the following scenario can result in a NULL-pointer dereference: CPU1 CPU2 rcu_preempt_deferred_qs_irqrestore rcu_print_task_exp_stall if (special.b.blocked) READ_ONCE(rnp->exp_tasks) != NULL raw_spin_lock_rcu_node np = rcu_next_node_entry(t, rnp) if (&t->rcu_node_entry == rnp->exp_tasks) WRITE_ONCE(rnp->exp_tasks, np) .... raw_spin_unlock_irqrestore_rcu_node raw_spin_lock_irqsave_rcu_node t = list_entry(rnp->exp_tasks->prev, struct task_struct, rcu_node_entry) (if rnp->exp_tasks is NULL, this will dereference a NULL pointer) The problem is that CPU2 accesses the rcu_node structure's->exp_tasks field without holding the rcu_node structure's ->lock and CPU2 did not observe CPU1's change to rcu_node structure's ->exp_tasks in time. Therefore, if CPU1 sets rcu_node structure's->exp_tasks pointer to NULL, then CPU2 might dereference that NULL pointer. This commit therefore holds the rcu_node structure's ->lock while accessing that structure's->exp_tasks field. [ paulmck: Apply Frederic Weisbecker feedback. ] Acked-by: Joel Fernandes (Google) Signed-off-by: Zqiang Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Sasha Levin --- kernel/rcu/tree_exp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index ef6570137dcd..401c1f331caf 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -707,9 +707,11 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) int ndetected = 0; struct task_struct *t; - if (!READ_ONCE(rnp->exp_tasks)) - return 0; raw_spin_lock_irqsave_rcu_node(rnp, flags); + if (!rnp->exp_tasks) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return 0; + } t = list_entry(rnp->exp_tasks->prev, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { From c8daee66585897a4c90d937c91e762100237bff9 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 11 Apr 2023 19:57:33 +0900 Subject: [PATCH 3095/4345] fs: hfsplus: remove WARN_ON() from hfsplus_cat_{read,write}_inode() [ Upstream commit 81b21c0f0138ff5a499eafc3eb0578ad2a99622c ] syzbot is hitting WARN_ON() in hfsplus_cat_{read,write}_inode(), for crafted filesystem image can contain bogus length. There conditions are not kernel bugs that can justify kernel to panic. Reported-by: syzbot Link: https://syzkaller.appspot.com/bug?extid=e2787430e752a92b8750 Reported-by: syzbot Link: https://syzkaller.appspot.com/bug?extid=4913dca2ea6e4d43f3f1 Signed-off-by: Tetsuo Handa Reviewed-by: Viacheslav Dubeyko Message-Id: <15308173-5252-d6a3-ae3b-e96d46cb6f41@I-love.SAKURA.ne.jp> Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- fs/hfsplus/inode.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index c60d5ceb0d31..7e1d889dcc07 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -497,7 +497,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) if (type == HFSPLUS_FOLDER) { struct hfsplus_cat_folder *folder = &entry.folder; - WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_folder)); + if (fd->entrylength < sizeof(struct hfsplus_cat_folder)) { + pr_err("bad catalog folder entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_folder)); hfsplus_get_perms(inode, &folder->permissions, 1); @@ -517,7 +521,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) } else if (type == HFSPLUS_FILE) { struct hfsplus_cat_file *file = &entry.file; - WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_file)); + if (fd->entrylength < sizeof(struct hfsplus_cat_file)) { + pr_err("bad catalog file entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_file)); @@ -548,6 +556,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) pr_err("bad catalog entry used to create inode\n"); res = -EIO; } +out: return res; } @@ -556,6 +565,7 @@ int hfsplus_cat_write_inode(struct inode *inode) struct inode *main_inode = inode; struct hfs_find_data fd; hfsplus_cat_entry entry; + int res = 0; if (HFSPLUS_IS_RSRC(inode)) main_inode = HFSPLUS_I(inode)->rsrc_inode; @@ -574,7 +584,11 @@ int hfsplus_cat_write_inode(struct inode *inode) if (S_ISDIR(main_inode->i_mode)) { struct hfsplus_cat_folder *folder = &entry.folder; - WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_folder)); + if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) { + pr_err("bad catalog folder entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_folder)); /* simple node checks? */ @@ -599,7 +613,11 @@ int hfsplus_cat_write_inode(struct inode *inode) } else { struct hfsplus_cat_file *file = &entry.file; - WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_file)); + if (fd.entrylength < sizeof(struct hfsplus_cat_file)) { + pr_err("bad catalog file entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_file)); hfsplus_inode_write_fork(inode, &file->data_fork); @@ -620,5 +638,5 @@ int hfsplus_cat_write_inode(struct inode *inode) set_bit(HFSPLUS_I_CAT_DIRTY, &HFSPLUS_I(inode)->flags); out: hfs_find_exit(&fd); - return 0; + return res; } From d5138ad7ca1d85ceac0cb76961f834b54c1a5549 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 1 Nov 2022 10:20:09 -0400 Subject: [PATCH 3096/4345] drm/amd/display: Use DC_LOG_DC in the trasform pixel function [ Upstream commit 7222f5841ff49709ca666b05ff336776e0664a20 ] [Why & How] DC now uses a new commit sequence which is more robust since it addresses cases where we need to reorganize pipes based on planes and other parameters. As a result, this new commit sequence reset the DC state by cleaning plane states and re-creating them accordingly with the need. For this reason, the dce_transform_set_pixel_storage_depth can be invoked after a plane state is destroyed and before its re-creation. In this situation and on DCE devices, DC will hit a condition that will trigger a dmesg log that looks like this: Console: switching to colour frame buffer device 240x67 ------------[ cut here ]------------ [..] Hardware name: System manufacturer System Product Name/PRIME X370-PRO, BIOS 5603 07/28/2020 RIP: 0010:dce_transform_set_pixel_storage_depth+0x3f8/0x480 [amdgpu] [..] RSP: 0018:ffffc9000202b850 EFLAGS: 00010293 RAX: ffffffffa081d100 RBX: ffff888110790000 RCX: 000000000000000c RDX: ffff888100bedbf8 RSI: 0000000000001a50 RDI: ffff88810463c900 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000007 R10: 0000000000000001 R11: 0000000000000f00 R12: ffff88810f500010 R13: ffff888100bedbf8 R14: ffff88810f515688 R15: 0000000000000000 FS: 00007ff0159249c0(0000) GS:ffff88840e940000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ff01528e550 CR3: 0000000002a10000 CR4: 00000000003506e0 Call Trace: ? dm_write_reg_func+0x21/0x80 [amdgpu 340dadd3f7c8cf4be11cf0bdc850245e99abe0e8] dc_stream_set_dither_option+0xfb/0x130 [amdgpu 340dadd3f7c8cf4be11cf0bdc850245e99abe0e8] amdgpu_dm_crtc_configure_crc_source+0x10b/0x190 [amdgpu 340dadd3f7c8cf4be11cf0bdc850245e99abe0e8] amdgpu_dm_atomic_commit_tail+0x20a8/0x2a90 [amdgpu 340dadd3f7c8cf4be11cf0bdc850245e99abe0e8] ? free_unref_page_commit+0x98/0x170 ? free_unref_page+0xcc/0x150 commit_tail+0x94/0x120 drm_atomic_helper_commit+0x10f/0x140 drm_atomic_commit+0x94/0xc0 ? drm_plane_get_damage_clips.cold+0x1c/0x1c drm_client_modeset_commit_atomic+0x203/0x250 drm_client_modeset_commit_locked+0x56/0x150 drm_client_modeset_commit+0x21/0x40 drm_fb_helper_lastclose+0x42/0x70 amdgpu_driver_lastclose_kms+0xa/0x10 [amdgpu 340dadd3f7c8cf4be11cf0bdc850245e99abe0e8] drm_release+0xda/0x110 __fput+0x89/0x240 task_work_run+0x5c/0x90 do_exit+0x333/0xae0 do_group_exit+0x2d/0x90 __x64_sys_exit_group+0x14/0x20 do_syscall_64+0x5b/0x80 ? exit_to_user_mode_prepare+0x1e/0x140 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7ff016ceaca1 Code: Unable to access opcode bytes at RIP 0x7ff016ceac77. RSP: 002b:00007ffe7a2357e8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 RAX: ffffffffffffffda RBX: 00007ff016e15a00 RCX: 00007ff016ceaca1 RDX: 000000000000003c RSI: 00000000000000e7 RDI: 0000000000000000 RBP: 0000000000000000 R08: ffffffffffffff78 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007ff016e15a00 R13: 0000000000000000 R14: 00007ff016e1aee8 R15: 00007ff016e1af00 Since this issue only happens in a transition state on DC, this commit replace BREAK_TO_DEBUGGER with DC_LOG_DC. Reviewed-by: Harry Wentland Acked-by: Qingqing Zhuo Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dce/dce_transform.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c index e2e79025825f..a54a30987924 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c @@ -1011,7 +1011,7 @@ static void dce_transform_set_pixel_storage_depth( color_depth = COLOR_DEPTH_101010; pixel_depth = 0; expan_mode = 1; - BREAK_TO_DEBUGGER(); + DC_LOG_DC("The pixel depth %d is not valid, set COLOR_DEPTH_101010 instead.", depth); break; } @@ -1025,8 +1025,7 @@ static void dce_transform_set_pixel_storage_depth( if (!(xfm_dce->lb_pixel_depth_supported & depth)) { /*we should use unsupported capabilities * unless it is required by w/a*/ - DC_LOG_WARNING("%s: Capability not supported", - __func__); + DC_LOG_DC("%s: Capability not supported", __func__); } } From bb1616e1057dfbb427f3594111608d7d573c6e1c Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Mon, 13 Mar 2023 08:18:11 +0100 Subject: [PATCH 3097/4345] regmap: cache: Return error in cache sync operations for REGCACHE_NONE [ Upstream commit fd883d79e4dcd2417c2b80756f22a2ff03b0f6e0 ] There is no sense in doing a cache sync on REGCACHE_NONE regmaps. Instead of panicking the kernel due to missing cache_ops, return an error to client driver. Signed-off-by: Alexander Stein Link: https://lore.kernel.org/r/20230313071812.13577-1-alexander.stein@ew.tq-group.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/base/regmap/regcache.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index 7f4b3b62492c..7fdd702e564a 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -343,6 +343,9 @@ int regcache_sync(struct regmap *map) const char *name; bool bypass; + if (WARN_ON(map->cache_type == REGCACHE_NONE)) + return -EINVAL; + BUG_ON(!map->cache_ops); map->lock(map->lock_arg); @@ -412,6 +415,9 @@ int regcache_sync_region(struct regmap *map, unsigned int min, const char *name; bool bypass; + if (WARN_ON(map->cache_type == REGCACHE_NONE)) + return -EINVAL; + BUG_ON(!map->cache_ops); map->lock(map->lock_arg); From ae6769fb939cb148a94efe8c6b0bc68f73349f64 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Thu, 2 Mar 2023 02:18:49 +0100 Subject: [PATCH 3098/4345] arm64: dts: qcom: msm8996: Add missing DWC3 quirks [ Upstream commit d0af0537e28f6eace02deed63b585396de939213 ] Add missing dwc3 quirks from msm-3.18. Unfortunately, none of them make `dwc3-qcom 6af8800.usb: HS-PHY not in L2` go away. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230302011849.1873056-1-konrad.dybcio@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8996.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 02b5f6f1d331..159cdd03e7c0 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -1771,8 +1771,11 @@ interrupts = <0 131 IRQ_TYPE_LEVEL_HIGH>; phys = <&hsusb_phy1>, <&ssusb_phy_0>; phy-names = "usb2-phy", "usb3-phy"; + snps,hird-threshold = /bits/ 8 <0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,is-utmi-l1-suspend; + tx-fifo-resize; }; }; From 5c23f6da62f71ebfeda6ea3960982ccd926ebb09 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Wed, 8 Mar 2023 00:43:38 +0800 Subject: [PATCH 3099/4345] memstick: r592: Fix UAF bug in r592_remove due to race condition [ Upstream commit 63264422785021704c39b38f65a78ab9e4a186d7 ] In r592_probe, dev->detect_timer was bound with r592_detect_timer. In r592_irq function, the timer function will be invoked by mod_timer. If we remove the module which will call hantro_release to make cleanup, there may be a unfinished work. The possible sequence is as follows, which will cause a typical UAF bug. Fix it by canceling the work before cleanup in r592_remove. CPU0 CPU1 |r592_detect_timer r592_remove | memstick_free_host| put_device; | kfree(host); | | | queue_work | &host->media_checker //use Signed-off-by: Zheng Wang Link: https://lore.kernel.org/r/20230307164338.1246287-1-zyytlz.wz@163.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/memstick/host/r592.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/memstick/host/r592.c b/drivers/memstick/host/r592.c index eaa2a94d18be..dd06c18495eb 100644 --- a/drivers/memstick/host/r592.c +++ b/drivers/memstick/host/r592.c @@ -828,7 +828,7 @@ static void r592_remove(struct pci_dev *pdev) /* Stop the processing thread. That ensures that we won't take any more requests */ kthread_stop(dev->io_thread); - + del_timer_sync(&dev->detect_timer); r592_enable_device(dev, false); while (!error && dev->req) { From 7d8f5ccc826b39e05ff252b1fccd808c7a0725e0 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Thu, 16 Feb 2023 09:49:19 +0100 Subject: [PATCH 3100/4345] firmware: arm_sdei: Fix sleep from invalid context BUG [ Upstream commit d2c48b2387eb89e0bf2a2e06e30987cf410acad4 ] Running a preempt-rt (v6.2-rc3-rt1) based kernel on an Ampere Altra triggers: BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46 in_atomic(): 0, irqs_disabled(): 128, non_block: 0, pid: 24, name: cpuhp/0 preempt_count: 0, expected: 0 RCU nest depth: 0, expected: 0 3 locks held by cpuhp/0/24: #0: ffffda30217c70d0 (cpu_hotplug_lock){++++}-{0:0}, at: cpuhp_thread_fun+0x5c/0x248 #1: ffffda30217c7120 (cpuhp_state-up){+.+.}-{0:0}, at: cpuhp_thread_fun+0x5c/0x248 #2: ffffda3021c711f0 (sdei_list_lock){....}-{3:3}, at: sdei_cpuhp_up+0x3c/0x130 irq event stamp: 36 hardirqs last enabled at (35): [] finish_task_switch+0xb4/0x2b0 hardirqs last disabled at (36): [] cpuhp_thread_fun+0x21c/0x248 softirqs last enabled at (0): [] copy_process+0x63c/0x1ac0 softirqs last disabled at (0): [<0000000000000000>] 0x0 CPU: 0 PID: 24 Comm: cpuhp/0 Not tainted 5.19.0-rc3-rt5-[...] Hardware name: WIWYNN Mt.Jade Server [...] Call trace: dump_backtrace+0x114/0x120 show_stack+0x20/0x70 dump_stack_lvl+0x9c/0xd8 dump_stack+0x18/0x34 __might_resched+0x188/0x228 rt_spin_lock+0x70/0x120 sdei_cpuhp_up+0x3c/0x130 cpuhp_invoke_callback+0x250/0xf08 cpuhp_thread_fun+0x120/0x248 smpboot_thread_fn+0x280/0x320 kthread+0x130/0x140 ret_from_fork+0x10/0x20 sdei_cpuhp_up() is called in the STARTING hotplug section, which runs with interrupts disabled. Use a CPUHP_AP_ONLINE_DYN entry instead to execute the cpuhp cb later, with preemption enabled. SDEI originally got its own cpuhp slot to allow interacting with perf. It got superseded by pNMI and this early slot is not relevant anymore. [1] Some SDEI calls (e.g. SDEI_1_0_FN_SDEI_PE_MASK) take actions on the calling CPU. It is checked that preemption is disabled for them. _ONLINE cpuhp cb are executed in the 'per CPU hotplug thread'. Preemption is enabled in those threads, but their cpumask is limited to 1 CPU. Move 'WARN_ON_ONCE(preemptible())' statements so that SDEI cpuhp cb don't trigger them. Also add a check for the SDEI_1_0_FN_SDEI_PRIVATE_RESET SDEI call which acts on the calling CPU. [1]: https://lore.kernel.org/all/5813b8c5-ae3e-87fd-fccc-94c9cd08816d@arm.com/ Suggested-by: James Morse Signed-off-by: Pierre Gondois Reviewed-by: James Morse Link: https://lore.kernel.org/r/20230216084920.144064-1-pierre.gondois@arm.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/firmware/arm_sdei.c | 37 ++++++++++++++++++++----------------- include/linux/cpuhotplug.h | 1 - 2 files changed, 20 insertions(+), 18 deletions(-) diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c index 840754dcc6ca..5a877d76078f 100644 --- a/drivers/firmware/arm_sdei.c +++ b/drivers/firmware/arm_sdei.c @@ -44,6 +44,8 @@ static asmlinkage void (*sdei_firmware_call)(unsigned long function_id, /* entry point from firmware to arch asm code */ static unsigned long sdei_entry_point; +static int sdei_hp_state; + struct sdei_event { /* These three are protected by the sdei_list_lock */ struct list_head list; @@ -302,8 +304,6 @@ int sdei_mask_local_cpu(void) { int err; - WARN_ON_ONCE(preemptible()); - err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_MASK, 0, 0, 0, 0, 0, NULL); if (err && err != -EIO) { pr_warn_once("failed to mask CPU[%u]: %d\n", @@ -316,6 +316,7 @@ int sdei_mask_local_cpu(void) static void _ipi_mask_cpu(void *ignored) { + WARN_ON_ONCE(preemptible()); sdei_mask_local_cpu(); } @@ -323,8 +324,6 @@ int sdei_unmask_local_cpu(void) { int err; - WARN_ON_ONCE(preemptible()); - err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_UNMASK, 0, 0, 0, 0, 0, NULL); if (err && err != -EIO) { pr_warn_once("failed to unmask CPU[%u]: %d\n", @@ -337,6 +336,7 @@ int sdei_unmask_local_cpu(void) static void _ipi_unmask_cpu(void *ignored) { + WARN_ON_ONCE(preemptible()); sdei_unmask_local_cpu(); } @@ -344,6 +344,8 @@ static void _ipi_private_reset(void *ignored) { int err; + WARN_ON_ONCE(preemptible()); + err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PRIVATE_RESET, 0, 0, 0, 0, 0, NULL); if (err && err != -EIO) @@ -390,8 +392,6 @@ static void _local_event_enable(void *data) int err; struct sdei_crosscall_args *arg = data; - WARN_ON_ONCE(preemptible()); - err = sdei_api_event_enable(arg->event->event_num); sdei_cross_call_return(arg, err); @@ -480,8 +480,6 @@ static void _local_event_unregister(void *data) int err; struct sdei_crosscall_args *arg = data; - WARN_ON_ONCE(preemptible()); - err = sdei_api_event_unregister(arg->event->event_num); sdei_cross_call_return(arg, err); @@ -562,8 +560,6 @@ static void _local_event_register(void *data) struct sdei_registered_event *reg; struct sdei_crosscall_args *arg = data; - WARN_ON(preemptible()); - reg = per_cpu_ptr(arg->event->private_registered, smp_processor_id()); err = sdei_api_event_register(arg->event->event_num, sdei_entry_point, reg, 0, 0); @@ -718,6 +714,8 @@ static int sdei_pm_notifier(struct notifier_block *nb, unsigned long action, { int rv; + WARN_ON_ONCE(preemptible()); + switch (action) { case CPU_PM_ENTER: rv = sdei_mask_local_cpu(); @@ -766,7 +764,7 @@ static int sdei_device_freeze(struct device *dev) int err; /* unregister private events */ - cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING); + cpuhp_remove_state(sdei_entry_point); err = sdei_unregister_shared(); if (err) @@ -787,12 +785,15 @@ static int sdei_device_thaw(struct device *dev) return err; } - err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI", + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SDEI", &sdei_cpuhp_up, &sdei_cpuhp_down); - if (err) + if (err < 0) { pr_warn("Failed to re-register CPU hotplug notifier...\n"); + return err; + } - return err; + sdei_hp_state = err; + return 0; } static int sdei_device_restore(struct device *dev) @@ -824,7 +825,7 @@ static int sdei_reboot_notifier(struct notifier_block *nb, unsigned long action, * We are going to reset the interface, after this there is no point * doing work when we take CPUs offline. */ - cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING); + cpuhp_remove_state(sdei_hp_state); sdei_platform_reset(); @@ -1004,13 +1005,15 @@ static int sdei_probe(struct platform_device *pdev) goto remove_cpupm; } - err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI", + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SDEI", &sdei_cpuhp_up, &sdei_cpuhp_down); - if (err) { + if (err < 0) { pr_warn("Failed to register CPU hotplug notifier...\n"); goto remove_reboot; } + sdei_hp_state = err; + return 0; remove_reboot: diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index fc945f9df2c1..cb87247da5ba 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -115,7 +115,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_MIPS_OP_LOONGSON3_STARTING, - CPUHP_AP_ARM_SDEI_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, From 066b90bca755f0b876e7b027b75d1796861d6db0 Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Fri, 24 Mar 2023 21:26:27 +0100 Subject: [PATCH 3101/4345] ACPI: EC: Fix oops when removing custom query handlers [ Upstream commit e5b492c6bb900fcf9722e05f4a10924410e170c1 ] When removing custom query handlers, the handler might still be used inside the EC query workqueue, causing a kernel oops if the module holding the callback function was already unloaded. Fix this by flushing the EC query workqueue when removing custom query handlers. Tested on a Acer Travelmate 4002WLMi Signed-off-by: Armin Wolf Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/ec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 4707d1808ca5..487884420fb0 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1114,6 +1114,7 @@ static void acpi_ec_remove_query_handlers(struct acpi_ec *ec, void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit) { acpi_ec_remove_query_handlers(ec, false, query_bit); + flush_workqueue(ec_query_wq); } EXPORT_SYMBOL_GPL(acpi_ec_remove_query_handler); From f718f1fd3e4cd8e0df912a8a9963ed019c278fb9 Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Fri, 31 Mar 2023 18:06:34 +0200 Subject: [PATCH 3102/4345] remoteproc: stm32_rproc: Add mutex protection for workqueue [ Upstream commit 35bdafda40cc343ad2ba2cce105eba03a70241cc ] The workqueue may execute late even after remoteproc is stopped or stopping, some resources (rpmsg device and endpoint) have been released in rproc_stop_subdevices(), then rproc_vq_interrupt() accessing these resources will cause kernel dump. Call trace: virtqueue_add_inbuf virtqueue_add_inbuf rpmsg_recv_single rpmsg_recv_done vring_interrupt stm32_rproc_mb_vq_work process_one_work worker_thread kthread Suggested-by: Mathieu Poirier Signed-off-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20230331160634.3113031-1-arnaud.pouliquen@foss.st.com Signed-off-by: Mathieu Poirier Signed-off-by: Sasha Levin --- drivers/remoteproc/stm32_rproc.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 24760d8ea637..df784fec124f 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -301,8 +301,16 @@ static void stm32_rproc_mb_vq_work(struct work_struct *work) struct stm32_mbox *mb = container_of(work, struct stm32_mbox, vq_work); struct rproc *rproc = dev_get_drvdata(mb->client.dev); + mutex_lock(&rproc->lock); + + if (rproc->state != RPROC_RUNNING) + goto unlock_mutex; + if (rproc_vq_interrupt(rproc, mb->vq_id) == IRQ_NONE) dev_dbg(&rproc->dev, "no message found in vq%d\n", mb->vq_id); + +unlock_mutex: + mutex_unlock(&rproc->lock); } static void stm32_rproc_mb_callback(struct mbox_client *cl, void *data) From 3f64a0e66469251bdfd0e0f7e97edd15e158a572 Mon Sep 17 00:00:00 2001 From: Nur Hussein Date: Thu, 6 Apr 2023 04:25:59 +0800 Subject: [PATCH 3103/4345] drm/tegra: Avoid potential 32-bit integer overflow [ Upstream commit 2429b3c529da29d4277d519bd66d034842dcd70c ] In tegra_sor_compute_config(), the 32-bit value mode->clock is multiplied by 1000, and assigned to the u64 variable pclk. We can avoid a potential 32-bit integer overflow by casting mode->clock to u64 before we do the arithmetic and assignment. Signed-off-by: Nur Hussein Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/gpu/drm/tegra/sor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index 32c83f2e386c..9d60d1c4cfce 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -1153,7 +1153,7 @@ static int tegra_sor_compute_config(struct tegra_sor *sor, struct drm_dp_link *link) { const u64 f = 100000, link_rate = link->rate * 1000; - const u64 pclk = mode->clock * 1000; + const u64 pclk = (u64)mode->clock * 1000; u64 input, output, watermark, num; struct tegra_sor_params params; u32 num_syms_per_line; From 16359bc02c093b0862e31739c07673340a2106a6 Mon Sep 17 00:00:00 2001 From: Tamir Duberstein Date: Wed, 5 Apr 2023 15:42:43 +0200 Subject: [PATCH 3104/4345] ACPICA: Avoid undefined behavior: applying zero offset to null pointer [ Upstream commit 05bb0167c80b8f93c6a4e0451b7da9b96db990c2 ] ACPICA commit 770653e3ba67c30a629ca7d12e352d83c2541b1e Before this change we see the following UBSAN stack trace in Fuchsia: #0 0x000021e4213b3302 in acpi_ds_init_aml_walk(struct acpi_walk_state*, union acpi_parse_object*, struct acpi_namespace_node*, u8*, u32, struct acpi_evaluate_info*, u8) ../../third_party/acpica/source/components/dispatcher/dswstate.c:682 +0x233302 #1.2 0x000020d0f660777f in ubsan_get_stack_trace() compiler-rt/lib/ubsan/ubsan_diag.cpp:41 +0x3d77f #1.1 0x000020d0f660777f in maybe_print_stack_trace() compiler-rt/lib/ubsan/ubsan_diag.cpp:51 +0x3d77f #1 0x000020d0f660777f in ~scoped_report() compiler-rt/lib/ubsan/ubsan_diag.cpp:387 +0x3d77f #2 0x000020d0f660b96d in handlepointer_overflow_impl() compiler-rt/lib/ubsan/ubsan_handlers.cpp:809 +0x4196d #3 0x000020d0f660b50d in compiler-rt/lib/ubsan/ubsan_handlers.cpp:815 +0x4150d #4 0x000021e4213b3302 in acpi_ds_init_aml_walk(struct acpi_walk_state*, union acpi_parse_object*, struct acpi_namespace_node*, u8*, u32, struct acpi_evaluate_info*, u8) ../../third_party/acpica/source/components/dispatcher/dswstate.c:682 +0x233302 #5 0x000021e4213e2369 in acpi_ds_call_control_method(struct acpi_thread_state*, struct acpi_walk_state*, union acpi_parse_object*) ../../third_party/acpica/source/components/dispatcher/dsmethod.c:605 +0x262369 #6 0x000021e421437fac in acpi_ps_parse_aml(struct acpi_walk_state*) ../../third_party/acpica/source/components/parser/psparse.c:550 +0x2b7fac #7 0x000021e4214464d2 in acpi_ps_execute_method(struct acpi_evaluate_info*) ../../third_party/acpica/source/components/parser/psxface.c:244 +0x2c64d2 #8 0x000021e4213aa052 in acpi_ns_evaluate(struct acpi_evaluate_info*) ../../third_party/acpica/source/components/namespace/nseval.c:250 +0x22a052 #9 0x000021e421413dd8 in acpi_ns_init_one_device(acpi_handle, u32, void*, void**) ../../third_party/acpica/source/components/namespace/nsinit.c:735 +0x293dd8 #10 0x000021e421429e98 in acpi_ns_walk_namespace(acpi_object_type, acpi_handle, u32, u32, acpi_walk_callback, acpi_walk_callback, void*, void**) ../../third_party/acpica/source/components/namespace/nswalk.c:298 +0x2a9e98 #11 0x000021e4214131ac in acpi_ns_initialize_devices(u32) ../../third_party/acpica/source/components/namespace/nsinit.c:268 +0x2931ac #12 0x000021e42147c40d in acpi_initialize_objects(u32) ../../third_party/acpica/source/components/utilities/utxfinit.c:304 +0x2fc40d #13 0x000021e42126d603 in acpi::acpi_impl::initialize_acpi(acpi::acpi_impl*) ../../src/devices/board/lib/acpi/acpi-impl.cc:224 +0xed603 Add a simple check that avoids incrementing a pointer by zero, but otherwise behaves as before. Note that our findings are against ACPICA 20221020, but the same code exists on master. Link: https://github.com/acpica/acpica/commit/770653e3 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/acpica/dswstate.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c index 809a0c0536b5..f9ba7695be14 100644 --- a/drivers/acpi/acpica/dswstate.c +++ b/drivers/acpi/acpica/dswstate.c @@ -576,9 +576,14 @@ acpi_ds_init_aml_walk(struct acpi_walk_state *walk_state, ACPI_FUNCTION_TRACE(ds_init_aml_walk); walk_state->parser_state.aml = - walk_state->parser_state.aml_start = aml_start; - walk_state->parser_state.aml_end = - walk_state->parser_state.pkg_end = aml_start + aml_length; + walk_state->parser_state.aml_start = + walk_state->parser_state.aml_end = + walk_state->parser_state.pkg_end = aml_start; + /* Avoid undefined behavior: applying zero offset to null pointer */ + if (aml_length != 0) { + walk_state->parser_state.aml_end += aml_length; + walk_state->parser_state.pkg_end += aml_length; + } /* The next_op of the next_walk will be the beginning of the method */ From 978e0d05547ae707d51a942fc7e85a34e181ee6f Mon Sep 17 00:00:00 2001 From: void0red <30990023+void0red@users.noreply.github.com> Date: Wed, 5 Apr 2023 15:57:57 +0200 Subject: [PATCH 3105/4345] ACPICA: ACPICA: check null return of ACPI_ALLOCATE_ZEROED in acpi_db_display_objects [ Upstream commit ae5a0eccc85fc960834dd66e3befc2728284b86c ] ACPICA commit 0d5f467d6a0ba852ea3aad68663cbcbd43300fd4 ACPI_ALLOCATE_ZEROED may fails, object_info might be null and will cause null pointer dereference later. Link: https://github.com/acpica/acpica/commit/0d5f467d Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/acpica/dbnames.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c index 3615e1a6efd8..b91155ea9c34 100644 --- a/drivers/acpi/acpica/dbnames.c +++ b/drivers/acpi/acpica/dbnames.c @@ -652,6 +652,9 @@ acpi_status acpi_db_display_objects(char *obj_type_arg, char *display_count_arg) object_info = ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_object_info)); + if (!object_info) + return (AE_NO_MEMORY); + /* Walk the namespace from the root */ (void)acpi_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT, From b8e7589f50b709b647b642531599e70707faf70c Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 23 Mar 2023 14:07:06 -0500 Subject: [PATCH 3106/4345] drm/amd: Fix an out of bounds error in BIOS parser [ Upstream commit d116db180decec1b21bba31d2ff495ac4d8e1b83 ] The array is hardcoded to 8 in atomfirmware.h, but firmware provides a bigger one sometimes. Deferencing the larger array causes an out of bounds error. commit 4fc1ba4aa589 ("drm/amd/display: fix array index out of bound error in bios parser") fixed some of this, but there are two other cases not covered by it. Fix those as well. Reported-by: erhard_f@mailbox.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=214853 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2473 Signed-off-by: Mario Limonciello Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 930d2b7d3448..9dd41eaf32cb 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -406,11 +406,8 @@ static enum bp_result get_gpio_i2c_info( info->i2c_slave_address = record->i2c_slave_addr; /* TODO: check how to get register offset for en, Y, etc. */ - info->gpio_info.clk_a_register_index = - le16_to_cpu( - header->gpio_pin[table_index].data_a_reg_index); - info->gpio_info.clk_a_shift = - header->gpio_pin[table_index].gpio_bitshift; + info->gpio_info.clk_a_register_index = le16_to_cpu(pin->data_a_reg_index); + info->gpio_info.clk_a_shift = pin->gpio_bitshift; return BP_RESULT_OK; } From 30d041c18dfba71b4c11d68abd819d20ab8d93c6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 15 Feb 2023 20:31:38 +0200 Subject: [PATCH 3107/4345] wifi: ath: Silence memcpy run-time false positive warning [ Upstream commit bfcc8ba45eb87bfaaff900bbad2b87b204899d41 ] The memcpy() in ath_key_config() was attempting to write across neighboring struct members in struct ath_keyval. Introduce a wrapping struct_group, kv_values, to be the addressable target of the memcpy without overflowing an individual member. Silences the false positive run-time warning: memcpy: detected field-spanning write (size 32) of single field "hk.kv_val" at drivers/net/wireless/ath/key.c:506 (size 16) Link: https://bbs.archlinux.org/viewtopic.php?id=282254 Cc: Kalle Valo Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230210054310.never.554-kees@kernel.org Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath.h | 12 +++++++----- drivers/net/wireless/ath/key.c | 2 +- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/ath/ath.h b/drivers/net/wireless/ath/ath.h index f083fb9038c3..f02a308a9ffc 100644 --- a/drivers/net/wireless/ath/ath.h +++ b/drivers/net/wireless/ath/ath.h @@ -96,11 +96,13 @@ struct ath_keyval { u8 kv_type; u8 kv_pad; u16 kv_len; - u8 kv_val[16]; /* TK */ - u8 kv_mic[8]; /* Michael MIC key */ - u8 kv_txmic[8]; /* Michael MIC TX key (used only if the hardware - * supports both MIC keys in the same key cache entry; - * in that case, kv_mic is the RX key) */ + struct_group(kv_values, + u8 kv_val[16]; /* TK */ + u8 kv_mic[8]; /* Michael MIC key */ + u8 kv_txmic[8]; /* Michael MIC TX key (used only if the hardware + * supports both MIC keys in the same key cache entry; + * in that case, kv_mic is the RX key) */ + ); }; enum ath_cipher { diff --git a/drivers/net/wireless/ath/key.c b/drivers/net/wireless/ath/key.c index 61b59a804e30..b7b61d4f02ba 100644 --- a/drivers/net/wireless/ath/key.c +++ b/drivers/net/wireless/ath/key.c @@ -503,7 +503,7 @@ int ath_key_config(struct ath_common *common, hk.kv_len = key->keylen; if (key->keylen) - memcpy(hk.kv_val, key->key, key->keylen); + memcpy(&hk.kv_values, key->key, key->keylen); if (!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE)) { switch (vif->type) { From e8d49d1c5968b747c4a0062dc3f97df219bcfb16 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 21 Feb 2023 21:06:42 +0100 Subject: [PATCH 3108/4345] bpf: Annotate data races in bpf_local_storage [ Upstream commit 0a09a2f933c73dc76ab0b72da6855f44342a8903 ] There are a few cases where hlist_node is checked to be unhashed without holding the lock protecting its modification. In this case, one must use hlist_unhashed_lockless to avoid load tearing and KCSAN reports. Fix this by using lockless variant in places not protected by the lock. Since this is not prompted by any actual KCSAN reports but only from code review, I have not included a fixes tag. Cc: Martin KaFai Lau Cc: KP Singh Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20230221200646.2500777-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/bpf_local_storage.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 8aaaaef99f09..f75396572620 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -48,11 +48,21 @@ owner_storage(struct bpf_local_storage_map *smap, void *owner) return map->ops->map_owner_storage_ptr(owner); } +static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed_lockless(&selem->snode); +} + static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); } +static bool selem_linked_to_map_lockless(const struct bpf_local_storage_elem *selem) +{ + return !hlist_unhashed_lockless(&selem->map_node); +} + static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->map_node); @@ -140,7 +150,7 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) struct bpf_local_storage *local_storage; bool free_local_storage = false; - if (unlikely(!selem_linked_to_storage(selem))) + if (unlikely(!selem_linked_to_storage_lockless(selem))) /* selem has already been unlinked from sk */ return; @@ -167,7 +177,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; - if (unlikely(!selem_linked_to_map(selem))) + if (unlikely(!selem_linked_to_map_lockless(selem))) /* selem has already be unlinked from smap */ return; @@ -365,7 +375,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, err = check_flags(old_sdata, map_flags); if (err) return ERR_PTR(err); - if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) { + if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); return old_sdata; From 4e8dc0e5c7636efaadbd7e488acd34b4291c0431 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Tue, 14 Feb 2023 18:24:19 +0900 Subject: [PATCH 3109/4345] wifi: brcmfmac: cfg80211: Pass the PMK in binary instead of hex [ Upstream commit 89b89e52153fda2733562776c7c9d9d3ebf8dd6d ] Apparently the hex passphrase mechanism does not work on newer chips/firmware (e.g. BCM4387). It seems there was a simple way of passing it in binary all along, so use that and avoid the hexification. OpenBSD has been doing it like this from the beginning, so this should work on all chips. Also clear the structure before setting the PMK. This was leaking uninitialized stack contents to the device. Reviewed-by: Linus Walleij Reviewed-by: Arend van Spriel Signed-off-by: Hector Martin Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230214092423.15175-6-marcan@marcan.st Signed-off-by: Sasha Levin --- .../wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index df5970619712..baf5f0afe802 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -1350,13 +1350,14 @@ static int brcmf_set_pmk(struct brcmf_if *ifp, const u8 *pmk_data, u16 pmk_len) { struct brcmf_pub *drvr = ifp->drvr; struct brcmf_wsec_pmk_le pmk; - int i, err; + int err; - /* convert to firmware key format */ - pmk.key_len = cpu_to_le16(pmk_len << 1); - pmk.flags = cpu_to_le16(BRCMF_WSEC_PASSPHRASE); - for (i = 0; i < pmk_len; i++) - snprintf(&pmk.key[2 * i], 3, "%02x", pmk_data[i]); + memset(&pmk, 0, sizeof(pmk)); + + /* pass pmk directly */ + pmk.key_len = cpu_to_le16(pmk_len); + pmk.flags = cpu_to_le16(0); + memcpy(pmk.key, pmk_data, pmk_len); /* store psk in firmware */ err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SET_WSEC_PMK, From 22ab5fed07ad4b206ea910fd0132d1a0d4831584 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 1 Mar 2023 11:59:39 +0100 Subject: [PATCH 3110/4345] ext2: Check block size validity during mount [ Upstream commit 62aeb94433fcec80241754b70d0d1836d5926b0a ] Check that log of block size stored in the superblock has sensible value. Otherwise the shift computing the block size can overflow leading to undefined behavior. Reported-by: syzbot+4fec412f59eba8c01b77@syzkaller.appspotmail.com Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/ext2/ext2.h | 1 + fs/ext2/super.c | 7 +++++++ 2 files changed, 8 insertions(+) diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 5136b7289e8d..f06367cfd764 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -177,6 +177,7 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb) #define EXT2_MIN_BLOCK_SIZE 1024 #define EXT2_MAX_BLOCK_SIZE 4096 #define EXT2_MIN_BLOCK_LOG_SIZE 10 +#define EXT2_MAX_BLOCK_LOG_SIZE 16 #define EXT2_BLOCK_SIZE(s) ((s)->s_blocksize) #define EXT2_ADDR_PER_BLOCK(s) (EXT2_BLOCK_SIZE(s) / sizeof (__u32)) #define EXT2_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 9a6475b2ab28..ab01ec7ac48c 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -950,6 +950,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } + if (le32_to_cpu(es->s_log_block_size) > + (EXT2_MAX_BLOCK_LOG_SIZE - BLOCK_SIZE_BITS)) { + ext2_msg(sb, KERN_ERR, + "Invalid log block size: %u", + le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); if (test_opt(sb, DAX)) { From e0e7faee3a7dd6f51350cda64997116a247eb045 Mon Sep 17 00:00:00 2001 From: Justin Tee Date: Wed, 1 Mar 2023 15:16:17 -0800 Subject: [PATCH 3111/4345] scsi: lpfc: Prevent lpfc_debugfs_lockstat_write() buffer overflow [ Upstream commit c6087b82a9146826564a55c5ca0164cac40348f5 ] A static code analysis tool flagged the possibility of buffer overflow when using copy_from_user() for a debugfs entry. Currently, it is possible that copy_from_user() copies more bytes than what would fit in the mybuf char array. Add a min() restriction check between sizeof(mybuf) - 1 and nbytes passed from the userspace buffer to protect against buffer overflow. Link: https://lore.kernel.org/r/20230301231626.9621-2-justintee8345@gmail.com Signed-off-by: Justin Tee Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/lpfc/lpfc_debugfs.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index fbc76d69ea0b..2b77cbbcdccb 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -2159,10 +2159,13 @@ lpfc_debugfs_lockstat_write(struct file *file, const char __user *buf, char mybuf[64]; char *pbuf; int i; + size_t bsize; memset(mybuf, 0, sizeof(mybuf)); - if (copy_from_user(mybuf, buf, nbytes)) + bsize = min(nbytes, (sizeof(mybuf) - 1)); + + if (copy_from_user(mybuf, buf, bsize)) return -EFAULT; pbuf = &mybuf[0]; @@ -2183,7 +2186,7 @@ lpfc_debugfs_lockstat_write(struct file *file, const char __user *buf, qp->lock_conflict.wq_access = 0; } } - return nbytes; + return bsize; } #endif From 8b61e7ad13f212395c53e68cff10db16be0fc7d7 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Sun, 19 Mar 2023 16:41:08 -0700 Subject: [PATCH 3112/4345] net: pasemi: Fix return type of pasemi_mac_start_tx() [ Upstream commit c8384d4a51e7cb0e6587f3143f29099f202c5de1 ] With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed. A warning in clang aims to catch these at compile time, which reveals: drivers/net/ethernet/pasemi/pasemi_mac.c:1665:21: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict] .ndo_start_xmit = pasemi_mac_start_tx, ^~~~~~~~~~~~~~~~~~~ 1 error generated. ->ndo_start_xmit() in 'struct net_device_ops' expects a return type of 'netdev_tx_t', not 'int'. Adjust the return type of pasemi_mac_start_tx() to match the prototype's to resolve the warning. While PowerPC does not currently implement support for kCFI, it could in the future, which means this warning becomes a fatal CFI failure at run time. Link: https://github.com/ClangBuiltLinux/linux/issues/1750 Signed-off-by: Nathan Chancellor Reviewed-by: Horatiu Vultur Link: https://lore.kernel.org/r/20230319-pasemi-incompatible-pointer-types-strict-v1-1-1b9459d8aef0@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/pasemi/pasemi_mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c index 040a15a828b4..c1d7bd168f1d 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac.c +++ b/drivers/net/ethernet/pasemi/pasemi_mac.c @@ -1423,7 +1423,7 @@ static void pasemi_mac_queue_csdesc(const struct sk_buff *skb, write_dma_reg(PAS_DMA_TXCHAN_INCR(txring->chan.chno), 2); } -static int pasemi_mac_start_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t pasemi_mac_start_tx(struct sk_buff *skb, struct net_device *dev) { struct pasemi_mac * const mac = netdev_priv(dev); struct pasemi_mac_txring * const txring = tx_ring(mac); From 2ea171230a39e50ca6b3d6590a3436a57df8758f Mon Sep 17 00:00:00 2001 From: Nick Child Date: Tue, 21 Mar 2023 10:07:24 -0500 Subject: [PATCH 3113/4345] net: Catch invalid index in XPS mapping [ Upstream commit 5dd0dfd55baec0742ba8f5625a0dd064aca7db16 ] When setting the XPS value of a TX queue, warn the user once if the index of the queue is greater than the number of allocated TX queues. Previously, this scenario went uncaught. In the best case, it resulted in unnecessary allocations. In the worst case, it resulted in out-of-bounds memory references through calls to `netdev_get_tx_queue( dev, index)`. Therefore, it is important to inform the user but not worth returning an error and risk downing the netdevice. Signed-off-by: Nick Child Reviewed-by: Piotr Raczynski Link: https://lore.kernel.org/r/20230321150725.127229-1-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index 1eaf224a90ce..29e6e11c481c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2628,6 +2628,8 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, bool active = false; unsigned int nr_ids; + WARN_ON_ONCE(index >= dev->num_tx_queues); + if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; From 4621e24c9257c6379343bf0c11b473817cf7edcd Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Sat, 18 Mar 2023 20:56:17 -0500 Subject: [PATCH 3114/4345] scsi: target: iscsit: Free cmds before session free [ Upstream commit d8990b5a4d065f38f35d69bcd627ec5a7f8330ca ] Commands from recovery entries are freed after session has been closed. That leads to use-after-free at command free or NPE with such call trace: Time2Retain timer expired for SID: 1, cleaning up iSCSI session. BUG: kernel NULL pointer dereference, address: 0000000000000140 RIP: 0010:sbitmap_queue_clear+0x3a/0xa0 Call Trace: target_release_cmd_kref+0xd1/0x1f0 [target_core_mod] transport_generic_free_cmd+0xd1/0x180 [target_core_mod] iscsit_free_cmd+0x53/0xd0 [iscsi_target_mod] iscsit_free_connection_recovery_entries+0x29d/0x320 [iscsi_target_mod] iscsit_close_session+0x13a/0x140 [iscsi_target_mod] iscsit_check_post_dataout+0x440/0x440 [iscsi_target_mod] call_timer_fn+0x24/0x140 Move cleanup of recovery enrties to before session freeing. Reported-by: Forza Signed-off-by: Dmitry Bogdanov Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20230319015620.96006-7-michael.christie@oracle.com Reviewed-by: Maurizio Lombardi Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/iscsi/iscsi_target.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 6bb840358072..075e2a6fb474 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4385,6 +4385,9 @@ int iscsit_close_session(struct iscsi_session *sess) iscsit_stop_time2retain_timer(sess); spin_unlock_bh(&se_tpg->session_lock); + if (sess->sess_ops->ErrorRecoveryLevel == 2) + iscsit_free_connection_recovery_entries(sess); + /* * transport_deregister_session_configfs() will clear the * struct se_node_acl->nacl_sess pointer now as a iscsi_np process context @@ -4412,9 +4415,6 @@ int iscsit_close_session(struct iscsi_session *sess) transport_deregister_session(sess->se_sess); - if (sess->sess_ops->ErrorRecoveryLevel == 2) - iscsit_free_connection_recovery_entries(sess); - iscsit_free_all_ooo_cmdsns(sess); spin_lock_bh(&se_tpg->session_lock); From f748e15253833b771acbede14ea98f50831ac289 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 8 Feb 2023 07:51:02 +0200 Subject: [PATCH 3115/4345] lib: cpu_rmap: Avoid use after free on rmap->obj array entries [ Upstream commit 4e0473f1060aa49621d40a113afde24818101d37 ] When calling irq_set_affinity_notifier() with NULL at the notify argument, it will cause freeing of the glue pointer in the corresponding array entry but will leave the pointer in the array. A subsequent call to free_irq_cpu_rmap() will try to free this entry again leading to possible use after free. Fix that by setting NULL to the array entry and checking that we have non-zero at the array entry when iterating over the array in free_irq_cpu_rmap(). The current code does not suffer from this since there are no cases where irq_set_affinity_notifier(irq, NULL) (note the NULL passed for the notify arg) is called, followed by a call to free_irq_cpu_rmap() so we don't hit and issue. Subsequent patches in this series excersize this flow, hence the required fix. Cc: Thomas Gleixner Signed-off-by: Eli Cohen Signed-off-by: Saeed Mahameed Reviewed-by: Jacob Keller Signed-off-by: Sasha Levin --- lib/cpu_rmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c index f08d9c56f712..e77f12bb3c77 100644 --- a/lib/cpu_rmap.c +++ b/lib/cpu_rmap.c @@ -232,7 +232,8 @@ void free_irq_cpu_rmap(struct cpu_rmap *rmap) for (index = 0; index < rmap->used; index++) { glue = rmap->obj[index]; - irq_set_affinity_notifier(glue->notify.irq, NULL); + if (glue) + irq_set_affinity_notifier(glue->notify.irq, NULL); } cpu_rmap_put(rmap); @@ -268,6 +269,7 @@ static void irq_cpu_rmap_release(struct kref *ref) container_of(ref, struct irq_glue, notify.kref); cpu_rmap_put(glue->rmap); + glue->rmap->obj[glue->index] = NULL; kfree(glue); } @@ -297,6 +299,7 @@ int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq) rc = irq_set_affinity_notifier(irq, &glue->notify); if (rc) { cpu_rmap_put(glue->rmap); + rmap->obj[glue->index] = NULL; kfree(glue); } return rc; From 697f92f8317e538d8409a0c95d6370eb40b34c05 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Sat, 18 Mar 2023 16:16:35 +0800 Subject: [PATCH 3116/4345] scsi: message: mptlan: Fix use after free bug in mptlan_remove() due to race condition [ Upstream commit f486893288f3e9b171b836f43853a6426515d800 ] mptlan_probe() calls mpt_register_lan_device() which initializes the &priv->post_buckets_task workqueue. A call to mpt_lan_wake_post_buckets_task() will subsequently start the work. During driver unload in mptlan_remove() the following race may occur: CPU0 CPU1 |mpt_lan_post_receive_buckets_work() mptlan_remove() | free_netdev() | kfree(dev); | | | dev->mtu | //use Fix this by finishing the work prior to cleaning up in mptlan_remove(). [mkp: we really should remove mptlan instead of attempting to fix it] Signed-off-by: Zheng Wang Link: https://lore.kernel.org/r/20230318081635.796479-1-zyytlz.wz@163.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/message/fusion/mptlan.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/message/fusion/mptlan.c b/drivers/message/fusion/mptlan.c index 7d3784aa20e5..90cc3cd49a5e 100644 --- a/drivers/message/fusion/mptlan.c +++ b/drivers/message/fusion/mptlan.c @@ -1430,7 +1430,9 @@ mptlan_remove(struct pci_dev *pdev) { MPT_ADAPTER *ioc = pci_get_drvdata(pdev); struct net_device *dev = ioc->netdev; + struct mpt_lan_priv *priv = netdev_priv(dev); + cancel_delayed_work_sync(&priv->post_buckets_task); if(dev != NULL) { unregister_netdev(dev); free_netdev(dev); From 4c2c8f959984e8dbbfdb6441b33fb72609eaefc0 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 28 Mar 2023 00:43:16 +0200 Subject: [PATCH 3117/4345] gfs2: Fix inode height consistency check [ Upstream commit cfcdb5bad34f600aed7613c3c1a5e618111f77b7 ] The maximum allowed height of an inode's metadata tree depends on the filesystem block size; it is lower for bigger-block filesystems. When reading in an inode, make sure that the height doesn't exceed the maximum allowed height. Arrays like sd_heightsize are sized to be big enough for any filesystem block size; they will often be slightly bigger than what's needed for a specific filesystem. Reported-by: syzbot+45d4691b1ed3c48eba05@syzkaller.appspotmail.com Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/glops.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index db28c240dae3..87f811088466 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -405,6 +405,7 @@ static int inode_go_demote_ok(const struct gfs2_glock *gl) static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) { + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); const struct gfs2_dinode *str = buf; struct timespec64 atime; u16 height, depth; @@ -444,7 +445,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) /* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */ gfs2_set_inode_flags(&ip->i_inode); height = be16_to_cpu(str->di_height); - if (unlikely(height > GFS2_MAX_META_HEIGHT)) + if (unlikely(height > sdp->sd_max_height)) goto corrupt; ip->i_height = (u8)height; From 3ca3005b502ca8ea87d6a344323b179b48c4e4a3 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Sat, 4 Mar 2023 01:21:01 +0800 Subject: [PATCH 3118/4345] ext4: set goal start correctly in ext4_mb_normalize_request [ Upstream commit b07ffe6927c75d99af534d685282ea188d9f71a6 ] We need to set ac_g_ex to notify the goal start used in ext4_mb_find_by_goal. Set ac_g_ex instead of ac_f_ex in ext4_mb_normalize_request. Besides we should assure goal start is in range [first_data_block, blocks_count) as ext4_mb_initialize_context does. [ Added a check to make sure size is less than ar->pright; otherwise we could end up passing an underflowed value of ar->pright - size to ext4_get_group_no_and_offset(), which will trigger a BUG_ON later on. - TYT ] Signed-off-by: Kemeng Shi Reviewed-by: Ritesh Harjani (IBM) Link: https://lore.kernel.org/r/20230303172120.3800725-2-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f18aa35b82b0..63c01e068bcb 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3512,6 +3512,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); + struct ext4_super_block *es = sbi->s_es; int bsbits, max; ext4_lblk_t end; loff_t size, start_off; @@ -3692,18 +3693,21 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size); /* define goal start in order to merge */ - if (ar->pright && (ar->lright == (start + size))) { + if (ar->pright && (ar->lright == (start + size)) && + ar->pright >= size && + ar->pright - size >= le32_to_cpu(es->s_first_data_block)) { /* merge to the right */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size, - &ac->ac_f_ex.fe_group, - &ac->ac_f_ex.fe_start); + &ac->ac_g_ex.fe_group, + &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } - if (ar->pleft && (ar->lleft + 1 == start)) { + if (ar->pleft && (ar->lleft + 1 == start) && + ar->pleft + 1 < ext4_blocks_count(es)) { /* merge to the left */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1, - &ac->ac_f_ex.fe_group, - &ac->ac_f_ex.fe_start); + &ac->ac_g_ex.fe_group, + &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } From fc7237e191b99f88e859316fab2b06c2c26c8344 Mon Sep 17 00:00:00 2001 From: Ojaswin Mujoo Date: Sat, 25 Mar 2023 13:43:39 +0530 Subject: [PATCH 3119/4345] ext4: Fix best extent lstart adjustment logic in ext4_mb_new_inode_pa() [ Upstream commit 93cdf49f6eca5e23f6546b8f28457b2e6a6961d9 ] When the length of best extent found is less than the length of goal extent we need to make sure that the best extent atleast covers the start of the original request. This is done by adjusting the ac_b_ex.fe_logical (logical start) of the extent. While doing so, the current logic sometimes results in the best extent's logical range overflowing the goal extent. Since this best extent is later added to the inode preallocation list, we have a possibility of introducing overlapping preallocations. This is discussed in detail here [1]. As per Jan's suggestion, to fix this, replace the existing logic with the below logic for adjusting best extent as it keeps fragmentation in check while ensuring logical range of best extent doesn't overflow out of goal extent: 1. Check if best extent can be kept at end of goal range and still cover original start. 2. Else, check if best extent can be kept at start of goal range and still cover original start. 3. Else, keep the best extent at start of original request. Also, add a few extra BUG_ONs that might help catch errors faster. [1] https://lore.kernel.org/r/Y+OGkVvzPN0RMv0O@li-bb2b2a4c-3307-11b2-a85c-8fa5c3a69313.ibm.com Suggested-by: Jan Kara Signed-off-by: Ojaswin Mujoo Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/f96aca6d415b36d1f90db86c1a8cd7e2e9d7ab0e.1679731817.git.ojaswin@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Sasha Levin --- fs/ext4/mballoc.c | 49 ++++++++++++++++++++++++++++++----------------- 1 file changed, 31 insertions(+), 18 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 63c01e068bcb..8a51448b7670 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3800,6 +3800,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, BUG_ON(start < pa->pa_pstart); BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len)); BUG_ON(pa->pa_free < len); + BUG_ON(ac->ac_b_ex.fe_len <= 0); pa->pa_free -= len; mb_debug(ac->ac_sb, "use %llu/%d from inode pa %p\n", start, len, pa); @@ -4129,10 +4130,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) pa = ac->ac_pa; if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) { - int winl; - int wins; - int win; - int offs; + int new_bex_start; + int new_bex_end; /* we can't allocate as much as normalizer wants. * so, found space must get proper lstart @@ -4140,26 +4139,40 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); - /* we're limited by original request in that - * logical block must be covered any way - * winl is window we can move our chunk within */ - winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical; + /* + * Use the below logic for adjusting best extent as it keeps + * fragmentation in check while ensuring logical range of best + * extent doesn't overflow out of goal extent: + * + * 1. Check if best ex can be kept at end of goal and still + * cover original start + * 2. Else, check if best ex can be kept at start of goal and + * still cover original start + * 3. Else, keep the best ex at start of original request. + */ + new_bex_end = ac->ac_g_ex.fe_logical + + EXT4_C2B(sbi, ac->ac_g_ex.fe_len); + new_bex_start = new_bex_end - EXT4_C2B(sbi, ac->ac_b_ex.fe_len); + if (ac->ac_o_ex.fe_logical >= new_bex_start) + goto adjust_bex; - /* also, we should cover whole original request */ - wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len); + new_bex_start = ac->ac_g_ex.fe_logical; + new_bex_end = + new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); + if (ac->ac_o_ex.fe_logical < new_bex_end) + goto adjust_bex; - /* the smallest one defines real window */ - win = min(winl, wins); + new_bex_start = ac->ac_o_ex.fe_logical; + new_bex_end = + new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - offs = ac->ac_o_ex.fe_logical % - EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (offs && offs < win) - win = offs; +adjust_bex: + ac->ac_b_ex.fe_logical = new_bex_start; - ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical - - EXT4_NUM_B2C(sbi, win); BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); + BUG_ON(new_bex_end > (ac->ac_g_ex.fe_logical + + EXT4_C2B(sbi, ac->ac_g_ex.fe_len))); } /* preallocation can change ac_b_ex, thus we store actually From ad87bd313f70b51e48019d5ce2d02d73152356b3 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 10 Apr 2023 10:12:22 +0800 Subject: [PATCH 3120/4345] f2fs: fix to drop all dirty pages during umount() if cp_error is set [ Upstream commit c9b3649a934d131151111354bcbb638076f03a30 ] xfstest generic/361 reports a bug as below: f2fs_bug_on(sbi, sbi->fsync_node_num); kernel BUG at fs/f2fs/super.c:1627! RIP: 0010:f2fs_put_super+0x3a8/0x3b0 Call Trace: generic_shutdown_super+0x8c/0x1b0 kill_block_super+0x2b/0x60 kill_f2fs_super+0x87/0x110 deactivate_locked_super+0x39/0x80 deactivate_super+0x46/0x50 cleanup_mnt+0x109/0x170 __cleanup_mnt+0x16/0x20 task_work_run+0x65/0xa0 exit_to_user_mode_prepare+0x175/0x190 syscall_exit_to_user_mode+0x25/0x50 do_syscall_64+0x4c/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc During umount(), if cp_error is set, f2fs_wait_on_all_pages() should not stop waiting all F2FS_WB_CP_DATA pages to be writebacked, otherwise, fsync_node_num can be non-zero after f2fs_wait_on_all_pages() causing this bug. In this case, to avoid deadloop in f2fs_wait_on_all_pages(), it needs to drop all dirty pages rather than redirtying them. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/checkpoint.c | 12 ++++++++++-- fs/f2fs/data.c | 3 ++- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index cd46a64ace1b..8ca549cc975e 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -309,8 +309,15 @@ static int __f2fs_write_meta_page(struct page *page, trace_f2fs_writepage(page, META); - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) { + ClearPageUptodate(page); + dec_page_count(sbi, F2FS_DIRTY_META); + unlock_page(page); + return 0; + } goto redirty_out; + } if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0)) @@ -1283,7 +1290,8 @@ void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type) if (!get_pages(sbi, type)) break; - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi) && + !is_sbi_flag_set(sbi, SBI_IS_CLOSE))) break; if (type == F2FS_DIRTY_META) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index e9481c940895..e0533cffbb07 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2814,7 +2814,8 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, * don't drop any dirty dentry pages for keeping lastest * directory structure. */ - if (S_ISDIR(inode->i_mode)) + if (S_ISDIR(inode->i_mode) && + !is_sbi_flag_set(sbi, SBI_IS_CLOSE)) goto redirty_out; goto out; } From 7560ed6592ff4077528c239c71e91b19de985b97 Mon Sep 17 00:00:00 2001 From: Hao Zeng Date: Tue, 11 Apr 2023 16:43:49 +0800 Subject: [PATCH 3121/4345] samples/bpf: Fix fout leak in hbm's run_bpf_prog [ Upstream commit 23acb14af1914010dd0aae1bbb7fab28bf518b8e ] Fix fout being fopen'ed but then not subsequently fclose'd. In the affected branch, fout is otherwise going out of scope. Signed-off-by: Hao Zeng Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230411084349.1999628-1-zenghao@kylinos.cn Signed-off-by: Sasha Levin --- samples/bpf/hbm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index ff4c533dfac2..8e48489b96ae 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -308,6 +308,7 @@ static int run_bpf_prog(char *prog, int cg_id) fout = fopen(fname, "w"); fprintf(fout, "id:%d\n", cg_id); fprintf(fout, "ERROR: Could not lookup queue_stats\n"); + fclose(fout); } else if (stats_flag && qstats.lastPacketTime > qstats.firstPacketTime) { long long delta_us = (qstats.lastPacketTime - From 0fc0d287c1e7dcb39a3b9bb0f8679cd68c2156c7 Mon Sep 17 00:00:00 2001 From: Daniel Gabay Date: Thu, 13 Apr 2023 21:40:32 +0300 Subject: [PATCH 3122/4345] wifi: iwlwifi: pcie: fix possible NULL pointer dereference [ Upstream commit b655b9a9f8467684cfa8906713d33b71ea8c8f54 ] It is possible that iwl_pci_probe() will fail and free the trans, then afterwards iwl_pci_remove() will be called and crash by trying to access trans which is already freed, fix it. iwlwifi 0000:01:00.0: Detected crf-id 0xa5a5a5a2, cnv-id 0xa5a5a5a2 wfpm id 0xa5a5a5a2 iwlwifi 0000:01:00.0: Can't find a correct rfid for crf id 0x5a2 ... BUG: kernel NULL pointer dereference, address: 0000000000000028 ... RIP: 0010:iwl_pci_remove+0x12/0x30 [iwlwifi] pci_device_remove+0x3e/0xb0 device_release_driver_internal+0x103/0x1f0 driver_detach+0x4c/0x90 bus_remove_driver+0x5c/0xd0 driver_unregister+0x31/0x50 pci_unregister_driver+0x40/0x90 iwl_pci_unregister_driver+0x15/0x20 [iwlwifi] __exit_compat+0x9/0x98 [iwlwifi] __x64_sys_delete_module+0x147/0x260 Signed-off-by: Daniel Gabay Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230413213309.082f6e21341b.I0db21d7fa9a828d571ca886713bd0b5d0b6e1e5c@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 4e43efd5d1ea..dc0a507213ca 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -1214,6 +1214,9 @@ static void iwl_pci_remove(struct pci_dev *pdev) { struct iwl_trans *trans = pci_get_drvdata(pdev); + if (!trans) + return; + iwl_drv_stop(trans->drv); iwl_trans_pcie_free(trans); From 059e426d666a41e26b184c177c1ca3ee2d6fa1b6 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Fri, 14 Apr 2023 13:11:59 +0300 Subject: [PATCH 3123/4345] wifi: iwlwifi: pcie: Fix integer overflow in iwl_write_to_user_buf [ Upstream commit 58d1b717879bfeabe09b35e41ad667c79933eb2e ] An integer overflow occurs in the iwl_write_to_user_buf() function, which is called by the iwl_dbgfs_monitor_data_read() function. static bool iwl_write_to_user_buf(char __user *user_buf, ssize_t count, void *buf, ssize_t *size, ssize_t *bytes_copied) { int buf_size_left = count - *bytes_copied; buf_size_left = buf_size_left - (buf_size_left % sizeof(u32)); if (*size > buf_size_left) *size = buf_size_left; If the user passes a SIZE_MAX value to the "ssize_t count" parameter, the ssize_t count parameter is assigned to "int buf_size_left". Then compare "*size" with "buf_size_left" . Here, "buf_size_left" is a negative number, so "*size" is assigned "buf_size_left" and goes into the third argument of the copy_to_user function, causing a heap overflow. This is not a security vulnerability because iwl_dbgfs_monitor_data_read() is a debugfs operation with 0400 privileges. Signed-off-by: Hyunwoo Kim Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230414130637.2d80ace81532.Iecfba549e0e0be21bbb0324675392e42e75bd5ad@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 7f8b7f7697cf..fac7cc75bc31 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -2835,7 +2835,7 @@ static bool iwl_write_to_user_buf(char __user *user_buf, ssize_t count, void *buf, ssize_t *size, ssize_t *bytes_copied) { - int buf_size_left = count - *bytes_copied; + ssize_t buf_size_left = count - *bytes_copied; buf_size_left = buf_size_left - (buf_size_left % sizeof(u32)); if (*size > buf_size_left) From e732a266b973cd4e115e2cc2ea5007119e8a7fbc Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 16 Apr 2023 15:03:39 -0700 Subject: [PATCH 3124/4345] null_blk: Always check queue mode setting from configfs [ Upstream commit 63f8793ee60513a09f110ea460a6ff2c33811cdb ] Make sure to check device queue mode in the null_validate_conf() and return error for NULL_Q_RQ as we don't allow legacy I/O path, without this patch we get OOPs when queue mode is set to 1 from configfs, following are repro steps :- modprobe null_blk nr_devices=0 mkdir config/nullb/nullb0 echo 1 > config/nullb/nullb0/memory_backed echo 4096 > config/nullb/nullb0/blocksize echo 20480 > config/nullb/nullb0/size echo 1 > config/nullb/nullb0/queue_mode echo 1 > config/nullb/nullb0/power Entering kdb (current=0xffff88810acdd080, pid 2372) on processor 42 Oops: (null) due to oops @ 0xffffffffc041c329 CPU: 42 PID: 2372 Comm: sh Tainted: G O N 6.3.0-rc5lblk+ #5 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 RIP: 0010:null_add_dev.part.0+0xd9/0x720 [null_blk] Code: 01 00 00 85 d2 0f 85 a1 03 00 00 48 83 bb 08 01 00 00 00 0f 85 f7 03 00 00 80 bb 62 01 00 00 00 48 8b 75 20 0f 85 6d 02 00 00 <48> 89 6e 60 48 8b 75 20 bf 06 00 00 00 e8 f5 37 2c c1 48 8b 75 20 RSP: 0018:ffffc900052cbde0 EFLAGS: 00010246 RAX: 0000000000000001 RBX: ffff88811084d800 RCX: 0000000000000001 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff888100042e00 RBP: ffff8881053d8200 R08: ffffc900052cbd68 R09: ffff888105db2000 R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000002 R13: ffff888104765200 R14: ffff88810eec1748 R15: ffff88810eec1740 FS: 00007fd445fd1740(0000) GS:ffff8897dfc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000060 CR3: 0000000166a00000 CR4: 0000000000350ee0 DR0: ffffffff8437a488 DR1: ffffffff8437a489 DR2: ffffffff8437a48a DR3: ffffffff8437a48b DR6: 00000000ffff0ff0 DR7: 0000000000000400 Call Trace: nullb_device_power_store+0xd1/0x120 [null_blk] configfs_write_iter+0xb4/0x120 vfs_write+0x2ba/0x3c0 ksys_write+0x5f/0xe0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7fd4460c57a7 Code: 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 RSP: 002b:00007ffd3792a4a8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007fd4460c57a7 RDX: 0000000000000002 RSI: 000055b43c02e4c0 RDI: 0000000000000001 RBP: 000055b43c02e4c0 R08: 000000000000000a R09: 00007fd44615b4e0 R10: 00007fd44615b3e0 R11: 0000000000000246 R12: 0000000000000002 R13: 00007fd446198520 R14: 0000000000000002 R15: 00007fd446198700 Signed-off-by: Chaitanya Kulkarni Reviewed-by: Damien Le Moal Reviewed-by: Ming Lei Reviewed-by: Nitesh Shetty Link: https://lore.kernel.org/r/20230416220339.43845-1-kch@nvidia.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/null_blk/main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 25db095e943b..35b390a785dd 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1738,6 +1738,11 @@ static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set) static int null_validate_conf(struct nullb_device *dev) { + if (dev->queue_mode == NULL_Q_RQ) { + pr_err("legacy IO path is no longer available\n"); + return -EINVAL; + } + dev->blocksize = round_down(dev->blocksize, 512); dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096); From 91ad1ab3cc7e981cb6d6ee100686baed64e1277e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 18 Apr 2023 15:25:46 +0200 Subject: [PATCH 3125/4345] wifi: iwlwifi: dvm: Fix memcpy: detected field-spanning write backtrace [ Upstream commit ef16799640865f937719f0771c93be5dca18adc6 ] A received TKIP key may be up to 32 bytes because it may contain MIC rx/tx keys too. These are not used by iwl and copying these over overflows the iwl_keyinfo.key field. Add a check to not copy more data to iwl_keyinfo.key then will fit. This fixes backtraces like this one: memcpy: detected field-spanning write (size 32) of single field "sta_cmd.key.key" at drivers/net/wireless/intel/iwlwifi/dvm/sta.c:1103 (size 16) WARNING: CPU: 1 PID: 946 at drivers/net/wireless/intel/iwlwifi/dvm/sta.c:1103 iwlagn_send_sta_key+0x375/0x390 [iwldvm] Hardware name: Dell Inc. Latitude E6430/0H3MT5, BIOS A21 05/08/2017 RIP: 0010:iwlagn_send_sta_key+0x375/0x390 [iwldvm] Call Trace: iwl_set_dynamic_key+0x1f0/0x220 [iwldvm] iwlagn_mac_set_key+0x1e4/0x280 [iwldvm] drv_set_key+0xa4/0x1b0 [mac80211] ieee80211_key_enable_hw_accel+0xa8/0x2d0 [mac80211] ieee80211_key_replace+0x22d/0x8e0 [mac80211] Link: https://www.alionet.org/index.php?topic=1469.0 Link: https://lore.kernel.org/linux-wireless/20230218191056.never.374-kees@kernel.org/ Link: https://lore.kernel.org/linux-wireless/68760035-7f75-1b23-e355-bfb758a87d83@redhat.com/ Cc: Kees Cook Suggested-by: Johannes Berg Signed-off-by: Hans de Goede Reviewed-by: Kees Cook Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/dvm/sta.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/sta.c b/drivers/net/wireless/intel/iwlwifi/dvm/sta.c index e622948661fa..b307f0e52777 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/sta.c @@ -1086,6 +1086,7 @@ static int iwlagn_send_sta_key(struct iwl_priv *priv, { __le16 key_flags; struct iwl_addsta_cmd sta_cmd; + size_t to_copy; int i; spin_lock_bh(&priv->sta_lock); @@ -1105,7 +1106,9 @@ static int iwlagn_send_sta_key(struct iwl_priv *priv, sta_cmd.key.tkip_rx_tsc_byte2 = tkip_iv32; for (i = 0; i < 5; i++) sta_cmd.key.tkip_rx_ttak[i] = cpu_to_le16(tkip_p1k[i]); - memcpy(sta_cmd.key.key, keyconf->key, keyconf->keylen); + /* keyconf may contain MIC rx/tx keys which iwl does not use */ + to_copy = min_t(size_t, sizeof(sta_cmd.key.key), keyconf->keylen); + memcpy(sta_cmd.key.key, keyconf->key, to_copy); break; case WLAN_CIPHER_SUITE_WEP104: key_flags |= STA_KEY_FLG_KEY_SIZE_MSK; From 866921dc06b94df91acfcf9359b57da943ed99b3 Mon Sep 17 00:00:00 2001 From: Nagarajan Maran Date: Mon, 17 Apr 2023 13:35:02 +0300 Subject: [PATCH 3126/4345] wifi: ath11k: Fix SKB corruption in REO destination ring [ Upstream commit f9fff67d2d7ca6fa8066132003a3deef654c55b1 ] While running traffics for a long time, randomly an RX descriptor filled with value "0" from REO destination ring is received. This descriptor which is invalid causes the wrong SKB (SKB stored in the IDR lookup with buffer id "0") to be fetched which in turn causes SKB memory corruption issue and the same leads to crash after some time. Changed the start id for idr allocation to "1" and the buffer id "0" is reserved for error validation. Introduced Sanity check to validate the descriptor, before processing the SKB. Crash Signature : Unable to handle kernel paging request at virtual address 3f004900 PC points to "b15_dma_inv_range+0x30/0x50" LR points to "dma_cache_maint_page+0x8c/0x128". The Backtrace obtained is as follows: [<8031716c>] (b15_dma_inv_range) from [<80313a4c>] (dma_cache_maint_page+0x8c/0x128) [<80313a4c>] (dma_cache_maint_page) from [<80313b90>] (__dma_page_dev_to_cpu+0x28/0xcc) [<80313b90>] (__dma_page_dev_to_cpu) from [<7fb5dd68>] (ath11k_dp_process_rx+0x1e8/0x4a4 [ath11k]) [<7fb5dd68>] (ath11k_dp_process_rx [ath11k]) from [<7fb53c20>] (ath11k_dp_service_srng+0xb0/0x2ac [ath11k]) [<7fb53c20>] (ath11k_dp_service_srng [ath11k]) from [<7f67bba4>] (ath11k_pci_ext_grp_napi_poll+0x1c/0x78 [ath11k_pci]) [<7f67bba4>] (ath11k_pci_ext_grp_napi_poll [ath11k_pci]) from [<807d5cf4>] (__napi_poll+0x28/0xb8) [<807d5cf4>] (__napi_poll) from [<807d5f28>] (net_rx_action+0xf0/0x280) [<807d5f28>] (net_rx_action) from [<80302148>] (__do_softirq+0xd0/0x280) [<80302148>] (__do_softirq) from [<80320408>] (irq_exit+0x74/0xd4) [<80320408>] (irq_exit) from [<803638a4>] (__handle_domain_irq+0x90/0xb4) [<803638a4>] (__handle_domain_irq) from [<805bedec>] (gic_handle_irq+0x58/0x90) [<805bedec>] (gic_handle_irq) from [<80301a78>] (__irq_svc+0x58/0x8c) Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1 Signed-off-by: Nagarajan Maran Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230403191533.28114-1-quic_nmaran@quicinc.com Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/dp_rx.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 578fdc446bc0..583bcf148403 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -324,10 +324,10 @@ int ath11k_dp_rxbufs_replenish(struct ath11k_base *ab, int mac_id, goto fail_free_skb; spin_lock_bh(&rx_ring->idr_lock); - buf_id = idr_alloc(&rx_ring->bufs_idr, skb, 0, - rx_ring->bufs_max * 3, GFP_ATOMIC); + buf_id = idr_alloc(&rx_ring->bufs_idr, skb, 1, + (rx_ring->bufs_max * 3) + 1, GFP_ATOMIC); spin_unlock_bh(&rx_ring->idr_lock); - if (buf_id < 0) + if (buf_id <= 0) goto fail_dma_unmap; desc = ath11k_hal_srng_src_get_next_entry(ab, srng); @@ -2564,6 +2564,9 @@ try_again: cookie); mac_id = FIELD_GET(DP_RXDMA_BUF_COOKIE_PDEV_ID, cookie); + if (unlikely(buf_id == 0)) + continue; + ar = ab->pdevs[mac_id].ar; rx_ring = &ar->dp.rx_refill_buf_ring; spin_lock_bh(&rx_ring->idr_lock); From ba66851aba80b42f691f7d4ccad2b45fee19cda5 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 17 Apr 2023 17:10:45 +0200 Subject: [PATCH 3127/4345] ipvs: Update width of source for ip_vs_sync_conn_options [ Upstream commit e3478c68f6704638d08f437cbc552ca5970c151a ] In ip_vs_sync_conn_v0() copy is made to struct ip_vs_sync_conn_options. That structure looks like this: struct ip_vs_sync_conn_options { struct ip_vs_seq in_seq; struct ip_vs_seq out_seq; }; The source of the copy is the in_seq field of struct ip_vs_conn. Whose type is struct ip_vs_seq. Thus we can see that the source - is not as wide as the amount of data copied, which is the width of struct ip_vs_sync_conn_option. The copy is safe because the next field in is another struct ip_vs_seq. Make use of struct_group() to annotate this. Flagged by gcc-13 as: In file included from ./include/linux/string.h:254, from ./include/linux/bitmap.h:11, from ./include/linux/cpumask.h:12, from ./arch/x86/include/asm/paravirt.h:17, from ./arch/x86/include/asm/cpuid.h:62, from ./arch/x86/include/asm/processor.h:19, from ./arch/x86/include/asm/timex.h:5, from ./include/linux/timex.h:67, from ./include/linux/time32.h:13, from ./include/linux/time.h:60, from ./include/linux/stat.h:19, from ./include/linux/module.h:13, from net/netfilter/ipvs/ip_vs_sync.c:38: In function 'fortify_memcpy_chk', inlined from 'ip_vs_sync_conn_v0' at net/netfilter/ipvs/ip_vs_sync.c:606:3: ./include/linux/fortify-string.h:529:25: error: call to '__read_overflow2_field' declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror=attribute-warning] 529 | __read_overflow2_field(q_size_field, size); | Compile tested only. Signed-off-by: Simon Horman Reviewed-by: Horatiu Vultur Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- include/net/ip_vs.h | 6 ++++-- net/netfilter/ipvs/ip_vs_sync.c | 2 +- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d609e957a3ec..c02c3bb0fe09 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -549,8 +549,10 @@ struct ip_vs_conn { */ struct ip_vs_app *app; /* bound ip_vs_app object */ void *app_data; /* Application private data */ - struct ip_vs_seq in_seq; /* incoming seq. struct */ - struct ip_vs_seq out_seq; /* outgoing seq. struct */ + struct_group(sync_conn_opt, + struct ip_vs_seq in_seq; /* incoming seq. struct */ + struct ip_vs_seq out_seq; /* outgoing seq. struct */ + ); const struct ip_vs_pe *pe; char *pe_data; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index daab857c52a8..fc8db03d3efc 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -603,7 +603,7 @@ static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { struct ip_vs_sync_conn_options *opt = (struct ip_vs_sync_conn_options *)&s[1]; - memcpy(opt, &cp->in_seq, sizeof(*opt)); + memcpy(opt, &cp->sync_conn_opt, sizeof(*opt)); } m->nr_conns++; From a2d816f55da14d38218c9bd31748ac9cbae8f66c Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 31 Mar 2023 23:11:21 +0200 Subject: [PATCH 3128/4345] Bluetooth: hci_bcm: Fall back to getting bdaddr from EFI if not set [ Upstream commit 0d218c3642b9ccf71f44987cd03c19320f3bd918 ] On some devices the BCM Bluetooth adapter does not have a valid bdaddr set. btbcm.c currently sets HCI_QUIRK_INVALID_BDADDR to indicate when this is the case. But this requires users to manual setup a btaddr, by doing e.g.: btmgmt -i hci0 public-addr 'B0:F1:EC:82:1D:B3' Which means that Bluetooth will not work out of the box on such devices. To avoid this (where possible) hci_bcm sets: HCI_QUIRK_USE_BDADDR_PROPERTY which tries to get the bdaddr from devicetree. But this only works on devicetree platforms. On UEFI based platforms there is a special Broadcom UEFI variable which when present contains the devices bdaddr, just like how there is another UEFI variable which contains wifi nvram contents including the wifi MAC address. Add support for getting the bdaddr from this Broadcom UEFI variable, so that Bluetooth will work OOTB for users on devices where this UEFI variable is present. This fixes Bluetooth not working on for example Asus T100HA 2-in-1s. Signed-off-by: Hans de Goede Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- drivers/bluetooth/btbcm.c | 47 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 44 insertions(+), 3 deletions(-) diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index d263eac784da..636db3b7e470 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -6,6 +6,7 @@ * Copyright (C) 2015 Intel Corporation */ +#include #include #include #include @@ -32,6 +33,43 @@ /* For kmalloc-ing the fw-name array instead of putting it on the stack */ typedef char bcm_fw_name[BCM_FW_NAME_LEN]; +#ifdef CONFIG_EFI +static int btbcm_set_bdaddr_from_efi(struct hci_dev *hdev) +{ + efi_guid_t guid = EFI_GUID(0x74b00bd9, 0x805a, 0x4d61, 0xb5, 0x1f, + 0x43, 0x26, 0x81, 0x23, 0xd1, 0x13); + bdaddr_t efi_bdaddr, bdaddr; + efi_status_t status; + unsigned long len; + int ret; + + if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) + return -EOPNOTSUPP; + + len = sizeof(efi_bdaddr); + status = efi.get_variable(L"BDADDR", &guid, NULL, &len, &efi_bdaddr); + if (status != EFI_SUCCESS) + return -ENXIO; + + if (len != sizeof(efi_bdaddr)) + return -EIO; + + baswap(&bdaddr, &efi_bdaddr); + + ret = btbcm_set_bdaddr(hdev, &bdaddr); + if (ret) + return ret; + + bt_dev_info(hdev, "BCM: Using EFI device address (%pMR)", &bdaddr); + return 0; +} +#else +static int btbcm_set_bdaddr_from_efi(struct hci_dev *hdev) +{ + return -EOPNOTSUPP; +} +#endif + int btbcm_check_bdaddr(struct hci_dev *hdev) { struct hci_rp_read_bd_addr *bda; @@ -85,9 +123,12 @@ int btbcm_check_bdaddr(struct hci_dev *hdev) !bacmp(&bda->bdaddr, BDADDR_BCM4345C5) || !bacmp(&bda->bdaddr, BDADDR_BCM43430A0) || !bacmp(&bda->bdaddr, BDADDR_BCM43341B)) { - bt_dev_info(hdev, "BCM: Using default device address (%pMR)", - &bda->bdaddr); - set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); + /* Try falling back to BDADDR EFI variable */ + if (btbcm_set_bdaddr_from_efi(hdev) != 0) { + bt_dev_info(hdev, "BCM: Using default device address (%pMR)", + &bda->bdaddr); + set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); + } } kfree_skb(skb); From 55410a9144c76ecda126e6cdec556dfcd8f343b2 Mon Sep 17 00:00:00 2001 From: Min Li Date: Mon, 17 Apr 2023 10:27:54 +0800 Subject: [PATCH 3129/4345] Bluetooth: L2CAP: fix "bad unlock balance" in l2cap_disconnect_rsp [ Upstream commit 25e97f7b1866e6b8503be349eeea44bb52d661ce ] conn->chan_lock isn't acquired before l2cap_get_chan_by_scid, if l2cap_get_chan_by_scid returns NULL, then 'bad unlock balance' is triggered. Reported-by: syzbot+9519d6b5b79cf7787cf3@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/000000000000894f5f05f95e9f4d@google.com/ Signed-off-by: Min Li Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index f9d2ce9cee36..b85ce276e2a3 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4689,7 +4689,6 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, chan = l2cap_get_chan_by_scid(conn, scid); if (!chan) { - mutex_unlock(&conn->chan_lock); return 0; } From bb1313f37e7b267fcf0fe475b974be8de5f39945 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Thu, 23 Feb 2023 07:47:21 +0100 Subject: [PATCH 3130/4345] staging: rtl8192e: Replace macro RTL_PCI_DEVICE with PCI_DEVICE [ Upstream commit fda2093860df4812d69052a8cf4997e53853a340 ] Replace macro RTL_PCI_DEVICE with PCI_DEVICE to get rid of rtl819xp_ops which is empty. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/8b45ee783fa91196b7c9d6fc840a189496afd2f4.1677133271.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 6 +++--- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 5 ----- 2 files changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 291f98251f7f..4c201679fc08 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -50,9 +50,9 @@ static const struct rtl819x_ops rtl819xp_ops = { }; static struct pci_device_id rtl8192_pci_id_tbl[] = { - {RTL_PCI_DEVICE(0x10ec, 0x8192, rtl819xp_ops)}, - {RTL_PCI_DEVICE(0x07aa, 0x0044, rtl819xp_ops)}, - {RTL_PCI_DEVICE(0x07aa, 0x0047, rtl819xp_ops)}, + {PCI_DEVICE(0x10ec, 0x8192)}, + {PCI_DEVICE(0x07aa, 0x0044)}, + {PCI_DEVICE(0x07aa, 0x0047)}, {} }; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 736f1a824cd2..7bbd884aa5f1 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -55,11 +55,6 @@ #define IS_HARDWARE_TYPE_8192SE(_priv) \ (((struct r8192_priv *)rtllib_priv(dev))->card_8192 == NIC_8192SE) -#define RTL_PCI_DEVICE(vend, dev, cfg) \ - .vendor = (vend), .device = (dev), \ - .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, \ - .driver_data = (kernel_ulong_t)&(cfg) - #define TOTAL_CAM_ENTRY 32 #define CAM_CONTENT_COUNT 8 From 958534d4368bc81c170f0508519342558831de8b Mon Sep 17 00:00:00 2001 From: Bastien Nocera Date: Thu, 2 Mar 2023 14:01:16 +0100 Subject: [PATCH 3131/4345] HID: logitech-hidpp: Don't use the USB serial for USB devices [ Upstream commit 7ad1fe0da0fa91bf920b79ab05ae97bfabecc4f4 ] For devices that support the 0x0003 feature (Device Information) version 4, set the serial based on the output of that feature, rather than relying on the usbhid code setting the USB serial. This should allow the serial when connected through USB to (nearly) match the one when connected through a unifying receiver. For example, on the serials on a G903 wired/wireless mouse: - Unifying: 4067-e8-ce-cd-45 - USB before patch: 017C385C3837 - USB after patch: c086-e8-ce-cd-45 Signed-off-by: Bastien Nocera Link: https://lore.kernel.org/r/20230302130117.3975-1-hadess@hadess.net Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-logitech-hidpp.c | 51 ++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index f5ea8e1d8445..4921000d8b09 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -922,6 +922,55 @@ print_version: return 0; } +/* -------------------------------------------------------------------------- */ +/* 0x0003: Device Information */ +/* -------------------------------------------------------------------------- */ + +#define HIDPP_PAGE_DEVICE_INFORMATION 0x0003 + +#define CMD_GET_DEVICE_INFO 0x00 + +static int hidpp_get_serial(struct hidpp_device *hidpp, u32 *serial) +{ + struct hidpp_report response; + u8 feature_type; + u8 feature_index; + int ret; + + ret = hidpp_root_get_feature(hidpp, HIDPP_PAGE_DEVICE_INFORMATION, + &feature_index, + &feature_type); + if (ret) + return ret; + + ret = hidpp_send_fap_command_sync(hidpp, feature_index, + CMD_GET_DEVICE_INFO, + NULL, 0, &response); + if (ret) + return ret; + + /* See hidpp_unifying_get_serial() */ + *serial = *((u32 *)&response.rap.params[1]); + return 0; +} + +static int hidpp_serial_init(struct hidpp_device *hidpp) +{ + struct hid_device *hdev = hidpp->hid_dev; + u32 serial; + int ret; + + ret = hidpp_get_serial(hidpp, &serial); + if (ret) + return ret; + + snprintf(hdev->uniq, sizeof(hdev->uniq), "%04x-%4phD", + hdev->product, &serial); + dbg_hid("HID++ DeviceInformation: Got serial: %s\n", hdev->uniq); + + return 0; +} + /* -------------------------------------------------------------------------- */ /* 0x0005: GetDeviceNameType */ /* -------------------------------------------------------------------------- */ @@ -3855,6 +3904,8 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) if (hidpp->quirks & HIDPP_QUIRK_UNIFYING) hidpp_unifying_init(hidpp); + else if (hid_is_usb(hidpp->hid_dev)) + hidpp_serial_init(hidpp); connected = hidpp_root_get_protocol_version(hidpp) == 0; atomic_set(&hidpp->connected, connected); From 0898a1df72acb2bef7a7b670e5751c8bf3739b0f Mon Sep 17 00:00:00 2001 From: Bastien Nocera Date: Thu, 2 Mar 2023 14:01:17 +0100 Subject: [PATCH 3132/4345] HID: logitech-hidpp: Reconcile USB and Unifying serials [ Upstream commit 5b3691d15e04b6d5a32c915577b8dbc5cfb56382 ] Now that USB HID++ devices can gather a serial number that matches the one that would be gathered when connected through a Unifying receiver, remove the last difference by dropping the product ID as devices usually have different product IDs when connected through USB or Unifying. For example, on the serials on a G903 wired/wireless mouse: - Unifying before patch: 4067-e8-ce-cd-45 - USB before patch: c086-e8-ce-cd-45 - Unifying and USB after patch: e8-ce-cd-45 Signed-off-by: Bastien Nocera Link: https://lore.kernel.org/r/20230302130117.3975-2-hadess@hadess.net Signed-off-by: Benjamin Tissoires Signed-off-by: Sasha Levin --- drivers/hid/hid-logitech-hidpp.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 4921000d8b09..2e32a21bbcbf 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -828,8 +828,7 @@ static int hidpp_unifying_init(struct hidpp_device *hidpp) if (ret) return ret; - snprintf(hdev->uniq, sizeof(hdev->uniq), "%04x-%4phD", - hdev->product, &serial); + snprintf(hdev->uniq, sizeof(hdev->uniq), "%4phD", &serial); dbg_hid("HID++ Unifying: Got serial: %s\n", hdev->uniq); name = hidpp_unifying_get_name(hidpp); @@ -964,8 +963,7 @@ static int hidpp_serial_init(struct hidpp_device *hidpp) if (ret) return ret; - snprintf(hdev->uniq, sizeof(hdev->uniq), "%04x-%4phD", - hdev->product, &serial); + snprintf(hdev->uniq, sizeof(hdev->uniq), "%4phD", &serial); dbg_hid("HID++ DeviceInformation: Got serial: %s\n", hdev->uniq); return 0; From d234de1a924e61dde7a5290d9ead400bb16d5b7f Mon Sep 17 00:00:00 2001 From: Kevin Groeneveld Date: Sat, 18 Mar 2023 18:21:32 -0400 Subject: [PATCH 3133/4345] spi: spi-imx: fix MX51_ECSPI_* macros when cs > 3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 87c614175bbf28d3fd076dc2d166bac759e41427 ] When using gpio based chip select the cs value can go outside the range 0 – 3. The various MX51_ECSPI_* macros did not take this into consideration resulting in possible corruption of the configuration. For example for any cs value over 3 the SCLKPHA bits would not be set and other values in the register possibly corrupted. One way to fix this is to just mask the cs bits to 2 bits. This still allows all 4 native chip selects to work as well as gpio chip selects (which can use any of the 4 chip select configurations). Signed-off-by: Kevin Groeneveld Link: https://lore.kernel.org/r/20230318222132.3373-1-kgroeneveld@lenbrook.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-imx.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index bbc420865f0f..21297cc62571 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -242,6 +242,18 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi, return true; } +/* + * Note the number of natively supported chip selects for MX51 is 4. Some + * devices may have less actual SS pins but the register map supports 4. When + * using gpio chip selects the cs values passed into the macros below can go + * outside the range 0 - 3. We therefore need to limit the cs value to avoid + * corrupting bits outside the allocated locations. + * + * The simplest way to do this is to just mask the cs bits to 2 bits. This + * still allows all 4 native chip selects to work as well as gpio chip selects + * (which can use any of the 4 chip select configurations). + */ + #define MX51_ECSPI_CTRL 0x08 #define MX51_ECSPI_CTRL_ENABLE (1 << 0) #define MX51_ECSPI_CTRL_XCH (1 << 2) @@ -250,16 +262,16 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi, #define MX51_ECSPI_CTRL_DRCTL(drctl) ((drctl) << 16) #define MX51_ECSPI_CTRL_POSTDIV_OFFSET 8 #define MX51_ECSPI_CTRL_PREDIV_OFFSET 12 -#define MX51_ECSPI_CTRL_CS(cs) ((cs) << 18) +#define MX51_ECSPI_CTRL_CS(cs) ((cs & 3) << 18) #define MX51_ECSPI_CTRL_BL_OFFSET 20 #define MX51_ECSPI_CTRL_BL_MASK (0xfff << 20) #define MX51_ECSPI_CONFIG 0x0c -#define MX51_ECSPI_CONFIG_SCLKPHA(cs) (1 << ((cs) + 0)) -#define MX51_ECSPI_CONFIG_SCLKPOL(cs) (1 << ((cs) + 4)) -#define MX51_ECSPI_CONFIG_SBBCTRL(cs) (1 << ((cs) + 8)) -#define MX51_ECSPI_CONFIG_SSBPOL(cs) (1 << ((cs) + 12)) -#define MX51_ECSPI_CONFIG_SCLKCTL(cs) (1 << ((cs) + 20)) +#define MX51_ECSPI_CONFIG_SCLKPHA(cs) (1 << ((cs & 3) + 0)) +#define MX51_ECSPI_CONFIG_SCLKPOL(cs) (1 << ((cs & 3) + 4)) +#define MX51_ECSPI_CONFIG_SBBCTRL(cs) (1 << ((cs & 3) + 8)) +#define MX51_ECSPI_CONFIG_SSBPOL(cs) (1 << ((cs & 3) + 12)) +#define MX51_ECSPI_CONFIG_SCLKCTL(cs) (1 << ((cs & 3) + 20)) #define MX51_ECSPI_INT 0x10 #define MX51_ECSPI_INT_TEEN (1 << 0) From 60fabcba7543ee3dbb9d688f9bb7524a00aa7359 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Thu, 13 Apr 2023 11:17:43 -0700 Subject: [PATCH 3134/4345] HID: wacom: generic: Set battery quirk only when we see battery data [ Upstream commit bea407a427baa019758f29f4d31b26f008bb8cc6 ] Some devices will include battery status usages in the HID descriptor but we won't see that battery data for one reason or another. For example, AES sensors won't send battery data unless an AES pen is in proximity. If a user does not have an AES pen but instead only interacts with the AES touchscreen with their fingers then there is no need for us to create a battery object. Similarly, if a family of peripherals shares the same HID descriptor between wired-only and wireless-capable SKUs, users of the former may never see a battery event and will not want a power_supply object created. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217062 Link: https://gitlab.gnome.org/GNOME/gnome-control-center/-/issues/2354 Signed-off-by: Jason Gerecke Tested-by: Mario Limonciello Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/wacom_wac.c | 33 +++++++++++---------------------- 1 file changed, 11 insertions(+), 22 deletions(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 6c64165fae13..d82df2393d20 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1927,18 +1927,7 @@ static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage, static void wacom_wac_battery_usage_mapping(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage) { - struct wacom *wacom = hid_get_drvdata(hdev); - struct wacom_wac *wacom_wac = &wacom->wacom_wac; - struct wacom_features *features = &wacom_wac->features; - unsigned equivalent_usage = wacom_equivalent_usage(usage->hid); - - switch (equivalent_usage) { - case HID_DG_BATTERYSTRENGTH: - case WACOM_HID_WD_BATTERY_LEVEL: - case WACOM_HID_WD_BATTERY_CHARGING: - features->quirks |= WACOM_QUIRK_BATTERY; - break; - } + return; } static void wacom_wac_battery_event(struct hid_device *hdev, struct hid_field *field, @@ -1959,18 +1948,21 @@ static void wacom_wac_battery_event(struct hid_device *hdev, struct hid_field *f wacom_wac->hid_data.bat_connected = 1; wacom_wac->hid_data.bat_status = WACOM_POWER_SUPPLY_STATUS_AUTO; } + wacom_wac->features.quirks |= WACOM_QUIRK_BATTERY; break; case WACOM_HID_WD_BATTERY_LEVEL: value = value * 100 / (field->logical_maximum - field->logical_minimum); wacom_wac->hid_data.battery_capacity = value; wacom_wac->hid_data.bat_connected = 1; wacom_wac->hid_data.bat_status = WACOM_POWER_SUPPLY_STATUS_AUTO; + wacom_wac->features.quirks |= WACOM_QUIRK_BATTERY; break; case WACOM_HID_WD_BATTERY_CHARGING: wacom_wac->hid_data.bat_charging = value; wacom_wac->hid_data.ps_connected = value; wacom_wac->hid_data.bat_connected = 1; wacom_wac->hid_data.bat_status = WACOM_POWER_SUPPLY_STATUS_AUTO; + wacom_wac->features.quirks |= WACOM_QUIRK_BATTERY; break; } } @@ -1986,18 +1978,15 @@ static void wacom_wac_battery_report(struct hid_device *hdev, { struct wacom *wacom = hid_get_drvdata(hdev); struct wacom_wac *wacom_wac = &wacom->wacom_wac; - struct wacom_features *features = &wacom_wac->features; - if (features->quirks & WACOM_QUIRK_BATTERY) { - int status = wacom_wac->hid_data.bat_status; - int capacity = wacom_wac->hid_data.battery_capacity; - bool charging = wacom_wac->hid_data.bat_charging; - bool connected = wacom_wac->hid_data.bat_connected; - bool powered = wacom_wac->hid_data.ps_connected; + int status = wacom_wac->hid_data.bat_status; + int capacity = wacom_wac->hid_data.battery_capacity; + bool charging = wacom_wac->hid_data.bat_charging; + bool connected = wacom_wac->hid_data.bat_connected; + bool powered = wacom_wac->hid_data.ps_connected; - wacom_notify_battery(wacom_wac, status, capacity, charging, - connected, powered); - } + wacom_notify_battery(wacom_wac, status, capacity, charging, + connected, powered); } static void wacom_wac_pad_usage_mapping(struct hid_device *hdev, From 7ed30db879940822e8a392d402760eff56df0d57 Mon Sep 17 00:00:00 2001 From: Frank Wang Date: Thu, 16 Mar 2023 16:11:49 +0800 Subject: [PATCH 3135/4345] usb: typec: tcpm: fix multiple times discover svids error [ Upstream commit dac3b192107b978198e89ec0f77375738352e0c8 ] PD3.0 Spec 6.4.4.3.2 say that only Responder supports 12 or more SVIDs, the Discover SVIDs Command Shall be executed multiple times until a Discover SVIDs VDO is returned ending either with a SVID value of 0x0000 in the last part of the last VDO or with a VDO containing two SVIDs with values of 0x0000. In the current implementation, if the last VDO does not find that the Discover SVIDs Command would be executed multiple times even if the Responder SVIDs are less than 12, and we found some odd dockers just meet this case. So fix it. Acked-by: Heikki Krogerus Signed-off-by: Frank Wang Link: https://lore.kernel.org/r/20230316081149.24519-1-frank.wang@rock-chips.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/typec/tcpm/tcpm.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 8333c80b5f7c..cf0e6a80815a 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1126,7 +1126,21 @@ static bool svdm_consume_svids(struct tcpm_port *port, const u32 *p, int cnt) pmdata->svids[pmdata->nsvids++] = svid; tcpm_log(port, "SVID %d: 0x%x", pmdata->nsvids, svid); } - return true; + + /* + * PD3.0 Spec 6.4.4.3.2: The SVIDs are returned 2 per VDO (see Table + * 6-43), and can be returned maximum 6 VDOs per response (see Figure + * 6-19). If the Respondersupports 12 or more SVID then the Discover + * SVIDs Command Shall be executed multiple times until a Discover + * SVIDs VDO is returned ending either with a SVID value of 0x0000 in + * the last part of the last VDO or with a VDO containing two SVIDs + * with values of 0x0000. + * + * However, some odd dockers support SVIDs less than 12 but without + * 0x0000 in the last VDO, so we need to break the Discover SVIDs + * request and return false here. + */ + return cnt == 7; abort: tcpm_log(port, "SVID_DISCOVERY_MAX(%d) too low!", SVID_DISCOVERY_MAX); return false; From 2c86a1305c1406f45ea780d06953c484ea1d9e6e Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 18 Apr 2023 13:14:06 +0300 Subject: [PATCH 3136/4345] serial: 8250: Reinit port->pm on port specific driver unbind [ Upstream commit 04e82793f068d2f0ffe62fcea03d007a8cdc16a7 ] When we unbind a serial port hardware specific 8250 driver, the generic serial8250 driver takes over the port. After that we see an oops about 10 seconds later. This can produce the following at least on some TI SoCs: Unhandled fault: imprecise external abort (0x1406) Internal error: : 1406 [#1] SMP ARM Turns out that we may still have the serial port hardware specific driver port->pm in use, and serial8250_pm() tries to call it after the port specific driver is gone: serial8250_pm [8250_base] from uart_change_pm+0x54/0x8c [serial_base] uart_change_pm [serial_base] from uart_hangup+0x154/0x198 [serial_base] uart_hangup [serial_base] from __tty_hangup.part.0+0x328/0x37c __tty_hangup.part.0 from disassociate_ctty+0x154/0x20c disassociate_ctty from do_exit+0x744/0xaac do_exit from do_group_exit+0x40/0x8c do_group_exit from __wake_up_parent+0x0/0x1c Let's fix the issue by calling serial8250_set_defaults() in serial8250_unregister_port(). This will set the port back to using the serial8250 default functions, and sets the port->pm to point to serial8250_pm. Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20230418101407.12403-1-tony@atomide.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 0a7e9491b4d1..43f2eed6df78 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -1165,6 +1165,7 @@ void serial8250_unregister_port(int line) uart->port.type = PORT_UNKNOWN; uart->port.dev = &serial8250_isa_devs->dev; uart->capabilities = 0; + serial8250_init_port(uart); serial8250_apply_quirks(uart); uart_add_one_port(&serial8250_reg, &uart->port); } else { From 158502f790767050bdef4cee5182fbebea56db49 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rodr=C3=ADguez=20Barbarin=2C=20Jos=C3=A9=20Javier?= Date: Tue, 11 Apr 2023 10:33:28 +0200 Subject: [PATCH 3137/4345] mcb-pci: Reallocate memory region to avoid memory overlapping [ Upstream commit 9be24faadd085c284890c3afcec7a0184642315a ] mcb-pci requests a fixed-size memory region to parse the chameleon table, however, if the chameleon table is smaller that the allocated region, it could overlap with the IP Cores' memory regions. After parsing the chameleon table, drop/reallocate the memory region with the actual chameleon table size. Co-developed-by: Jorge Sanjuan Garcia Signed-off-by: Jorge Sanjuan Garcia Signed-off-by: Javier Rodriguez Signed-off-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20230411083329.4506-3-jth@kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/mcb/mcb-pci.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) diff --git a/drivers/mcb/mcb-pci.c b/drivers/mcb/mcb-pci.c index dc88232d9af8..53d9202ff9a7 100644 --- a/drivers/mcb/mcb-pci.c +++ b/drivers/mcb/mcb-pci.c @@ -31,7 +31,7 @@ static int mcb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct resource *res; struct priv *priv; - int ret; + int ret, table_size; unsigned long flags; priv = devm_kzalloc(&pdev->dev, sizeof(struct priv), GFP_KERNEL); @@ -90,7 +90,30 @@ static int mcb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret < 0) goto out_mcb_bus; - dev_dbg(&pdev->dev, "Found %d cells\n", ret); + table_size = ret; + + if (table_size < CHAM_HEADER_SIZE) { + /* Release the previous resources */ + devm_iounmap(&pdev->dev, priv->base); + devm_release_mem_region(&pdev->dev, priv->mapbase, CHAM_HEADER_SIZE); + + /* Then, allocate it again with the actual chameleon table size */ + res = devm_request_mem_region(&pdev->dev, priv->mapbase, + table_size, + KBUILD_MODNAME); + if (!res) { + dev_err(&pdev->dev, "Failed to request PCI memory\n"); + ret = -EBUSY; + goto out_mcb_bus; + } + + priv->base = devm_ioremap(&pdev->dev, priv->mapbase, table_size); + if (!priv->base) { + dev_err(&pdev->dev, "Cannot ioremap\n"); + ret = -ENOMEM; + goto out_mcb_bus; + } + } mcb_bus_add_devices(priv->bus); From cf3e2916017d1d158fba26236b2f791759a2e971 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 10:24:07 -0700 Subject: [PATCH 3138/4345] sched: Fix KCSAN noinstr violation [ Upstream commit e0b081d17a9f4e5c0cbb0e5fbeb1abe3de0f7e4e ] With KCSAN enabled, end_of_stack() can get out-of-lined. Force it inline. Fixes the following warnings: vmlinux.o: warning: objtool: check_stackleak_irqoff+0x2b: call to end_of_stack() leaves .noinstr.text section Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/cc1b4d73d3a428a00d206242a68fdf99a934ca7b.1681320026.git.jpoimboe@kernel.org Signed-off-by: Sasha Levin --- include/linux/sched/task_stack.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index d10150587d81..f24575942dab 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -23,7 +23,7 @@ static inline void *task_stack_page(const struct task_struct *task) #define setup_thread_stack(new,old) do { } while(0) -static inline unsigned long *end_of_stack(const struct task_struct *task) +static __always_inline unsigned long *end_of_stack(const struct task_struct *task) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; From 2d9ca5f62f2ba160ff9c9be4adf401c46c04edef Mon Sep 17 00:00:00 2001 From: Hao Zeng Date: Wed, 26 Apr 2023 09:05:27 +0800 Subject: [PATCH 3139/4345] recordmcount: Fix memory leaks in the uwrite function [ Upstream commit fa359d068574d29e7d2f0fdd0ebe4c6a12b5cfb9 ] Common realloc mistake: 'file_append' nulled but not freed upon failure Link: https://lkml.kernel.org/r/20230426010527.703093-1-zenghao@kylinos.cn Signed-off-by: Hao Zeng Suggested-by: Steven Rostedt Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin --- scripts/recordmcount.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index cce12e1971d8..ec692af8ce9e 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -102,6 +102,7 @@ static ssize_t uwrite(void const *const buf, size_t const count) { size_t cnt = count; off_t idx = 0; + void *p = NULL; file_updated = 1; @@ -109,7 +110,10 @@ static ssize_t uwrite(void const *const buf, size_t const count) off_t aoffset = (file_ptr + count) - file_end; if (aoffset > file_append_size) { - file_append = realloc(file_append, aoffset); + p = realloc(file_append, aoffset); + if (!p) + free(file_append); + file_append = p; file_append_size = aoffset; } if (!file_append) { From 214ae2c1a9ce28435802d010d6b27bad1eeddc97 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 21 Mar 2023 17:47:03 -0600 Subject: [PATCH 3140/4345] RDMA/core: Fix multiple -Warray-bounds warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit aa4d540b4150052ae3b36d286b9c833a961ce291 ] GCC-13 (and Clang)[1] does not like to access a partially allocated object, since it cannot reason about it for bounds checking. In this case 140 bytes are allocated for an object of type struct ib_umad_packet: packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL); However, notice that sizeof(*packet) is only 104 bytes: struct ib_umad_packet { struct ib_mad_send_buf * msg; /* 0 8 */ struct ib_mad_recv_wc * recv_wc; /* 8 8 */ struct list_head list; /* 16 16 */ int length; /* 32 4 */ /* XXX 4 bytes hole, try to pack */ struct ib_user_mad mad __attribute__((__aligned__(8))); /* 40 64 */ /* size: 104, cachelines: 2, members: 5 */ /* sum members: 100, holes: 1, sum holes: 4 */ /* forced alignments: 1, forced holes: 1, sum forced holes: 4 */ /* last cacheline: 40 bytes */ } __attribute__((__aligned__(8))); and 36 bytes extra bytes are allocated for a flexible-array member in struct ib_user_mad: include/rdma/ib_mad.h: 120 enum { ... 123 IB_MGMT_RMPP_HDR = 36, ... } struct ib_user_mad { struct ib_user_mad_hdr hdr; /* 0 64 */ /* --- cacheline 1 boundary (64 bytes) --- */ __u64 data[] __attribute__((__aligned__(8))); /* 64 0 */ /* size: 64, cachelines: 1, members: 2 */ /* forced alignments: 1 */ } __attribute__((__aligned__(8))); So we have sizeof(*packet) + IB_MGMT_RMPP_HDR == 140 bytes Then the address of the flex-array member (for which only 36 bytes were allocated) is casted and copied into a pointer to struct ib_rmpp_mad, which, in turn, is of size 256 bytes: rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data; struct ib_rmpp_mad { struct ib_mad_hdr mad_hdr; /* 0 24 */ struct ib_rmpp_hdr rmpp_hdr; /* 24 12 */ u8 data[220]; /* 36 220 */ /* size: 256, cachelines: 4, members: 3 */ }; The thing is that those 36 bytes allocated for flex-array member data in struct ib_user_mad onlly account for the size of both struct ib_mad_hdr and struct ib_rmpp_hdr, but nothing is left for array u8 data[220]. So, the compiler is legitimately complaining about accessing an object for which not enough memory was allocated. Apparently, the only members of struct ib_rmpp_mad that are relevant (that are actually being used) in function ib_umad_write() are mad_hdr and rmpp_hdr. So, instead of casting packet->mad.data to (struct ib_rmpp_mad *) create a new structure struct ib_rmpp_mad_hdr { struct ib_mad_hdr mad_hdr; struct ib_rmpp_hdr rmpp_hdr; } __packed; and cast packet->mad.data to (struct ib_rmpp_mad_hdr *). Notice that IB_MGMT_RMPP_HDR == sizeof(struct ib_rmpp_mad_hdr) == 36 bytes Refactor the rest of the code, accordingly. Fix the following warnings seen under GCC-13 and -Warray-bounds: drivers/infiniband/core/user_mad.c:564:50: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] drivers/infiniband/core/user_mad.c:566:42: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] drivers/infiniband/core/user_mad.c:618:25: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] drivers/infiniband/core/user_mad.c:622:44: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] Link: https://github.com/KSPP/linux/issues/273 Link: https://godbolt.org/z/oYWaGM4Yb [1] Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/ZBpB91qQcB10m3Fw@work Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/user_mad.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index 4688a6657c87..3bd0dcde8576 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -131,6 +131,11 @@ struct ib_umad_packet { struct ib_user_mad mad; }; +struct ib_rmpp_mad_hdr { + struct ib_mad_hdr mad_hdr; + struct ib_rmpp_hdr rmpp_hdr; +} __packed; + #define CREATE_TRACE_POINTS #include @@ -494,11 +499,11 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_umad_file *file = filp->private_data; + struct ib_rmpp_mad_hdr *rmpp_mad_hdr; struct ib_umad_packet *packet; struct ib_mad_agent *agent; struct rdma_ah_attr ah_attr; struct ib_ah *ah; - struct ib_rmpp_mad *rmpp_mad; __be64 *tid; int ret, data_len, hdr_len, copy_offset, rmpp_active; u8 base_version; @@ -506,7 +511,7 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, if (count < hdr_size(file) + IB_MGMT_RMPP_HDR) return -EINVAL; - packet = kzalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL); + packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL); if (!packet) return -ENOMEM; @@ -560,13 +565,13 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, goto err_up; } - rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data; - hdr_len = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class); + rmpp_mad_hdr = (struct ib_rmpp_mad_hdr *)packet->mad.data; + hdr_len = ib_get_mad_data_offset(rmpp_mad_hdr->mad_hdr.mgmt_class); - if (ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class) + if (ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) && ib_mad_kernel_rmpp_agent(agent)) { copy_offset = IB_MGMT_RMPP_HDR; - rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & + rmpp_active = ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE; } else { copy_offset = IB_MGMT_MAD_HDR; @@ -615,12 +620,12 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, tid = &((struct ib_mad_hdr *) packet->msg->mad)->tid; *tid = cpu_to_be64(((u64) agent->hi_tid) << 32 | (be64_to_cpup(tid) & 0xffffffff)); - rmpp_mad->mad_hdr.tid = *tid; + rmpp_mad_hdr->mad_hdr.tid = *tid; } if (!ib_mad_kernel_rmpp_agent(agent) - && ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class) - && (ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) { + && ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) + && (ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) { spin_lock_irq(&file->send_lock); list_add_tail(&packet->list, &file->send_list); spin_unlock_irq(&file->send_lock); From 8c472e68bea0a8500fe30a101afa3c13c9fbfe67 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 27 Mar 2023 13:30:29 +0530 Subject: [PATCH 3141/4345] iommu/arm-smmu-qcom: Limit the SMR groups to 128 [ Upstream commit 12261134732689b7e30c59db9978f81230965181 ] Some platforms support more than 128 stream matching groups than what is defined by the ARM SMMU architecture specification. But due to some unknown reasons, those additional groups don't exhibit the same behavior as the architecture supported ones. For instance, the additional groups will not detect the quirky behavior of some firmware versions intercepting writes to S2CR register, thus skipping the quirk implemented in the driver and causing boot crash. So let's limit the groups to 128 for now until the issue with those groups are fixed and issue a notice to users in that case. Reviewed-by: Johan Hovold Tested-by: Johan Hovold Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230327080029.11584-1-manivannan.sadhasivam@linaro.org [will: Reworded the comment slightly] Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index 63f7173b241f..1598a1ddbf69 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -32,12 +32,26 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = { static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu) { - unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + unsigned int last_s2cr; u32 reg; u32 smr; int i; + /* + * Some platforms support more than the Arm SMMU architected maximum of + * 128 stream matching groups. For unknown reasons, the additional + * groups don't exhibit the same behavior as the architected registers, + * so limit the groups to 128 until the behavior is fixed for the other + * groups. + */ + if (smmu->num_mapping_groups > 128) { + dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n"); + smmu->num_mapping_groups = 128; + } + + last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); + /* * With some firmware versions writes to S2CR of type FAULT are * ignored, and writing BYPASS will end up written as FAULT in the From cae5f8f4f7a8254be2081332035c11a389f2fd21 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 27 Feb 2023 09:59:10 +0100 Subject: [PATCH 3142/4345] clk: tegra20: fix gcc-7 constant overflow warning [ Upstream commit b4a2adbf3586efa12fe78b9dec047423e01f3010 ] Older gcc versions get confused by comparing a u32 value to a negative constant in a switch()/case block: drivers/clk/tegra/clk-tegra20.c: In function 'tegra20_clk_measure_input_freq': drivers/clk/tegra/clk-tegra20.c:581:2: error: case label does not reduce to an integer constant case OSC_CTRL_OSC_FREQ_12MHZ: ^~~~ drivers/clk/tegra/clk-tegra20.c:593:2: error: case label does not reduce to an integer constant case OSC_CTRL_OSC_FREQ_26MHZ: Make the constants unsigned instead. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230227085914.2560984-1-arnd@kernel.org Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/tegra/clk-tegra20.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index d60ee6e318a5..fb1da5d63f4b 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -18,24 +18,24 @@ #define MISC_CLK_ENB 0x48 #define OSC_CTRL 0x50 -#define OSC_CTRL_OSC_FREQ_MASK (3<<30) -#define OSC_CTRL_OSC_FREQ_13MHZ (0<<30) -#define OSC_CTRL_OSC_FREQ_19_2MHZ (1<<30) -#define OSC_CTRL_OSC_FREQ_12MHZ (2<<30) -#define OSC_CTRL_OSC_FREQ_26MHZ (3<<30) -#define OSC_CTRL_MASK (0x3f2 | OSC_CTRL_OSC_FREQ_MASK) +#define OSC_CTRL_OSC_FREQ_MASK (3u<<30) +#define OSC_CTRL_OSC_FREQ_13MHZ (0u<<30) +#define OSC_CTRL_OSC_FREQ_19_2MHZ (1u<<30) +#define OSC_CTRL_OSC_FREQ_12MHZ (2u<<30) +#define OSC_CTRL_OSC_FREQ_26MHZ (3u<<30) +#define OSC_CTRL_MASK (0x3f2u | OSC_CTRL_OSC_FREQ_MASK) -#define OSC_CTRL_PLL_REF_DIV_MASK (3<<28) -#define OSC_CTRL_PLL_REF_DIV_1 (0<<28) -#define OSC_CTRL_PLL_REF_DIV_2 (1<<28) -#define OSC_CTRL_PLL_REF_DIV_4 (2<<28) +#define OSC_CTRL_PLL_REF_DIV_MASK (3u<<28) +#define OSC_CTRL_PLL_REF_DIV_1 (0u<<28) +#define OSC_CTRL_PLL_REF_DIV_2 (1u<<28) +#define OSC_CTRL_PLL_REF_DIV_4 (2u<<28) #define OSC_FREQ_DET 0x58 -#define OSC_FREQ_DET_TRIG (1<<31) +#define OSC_FREQ_DET_TRIG (1u<<31) #define OSC_FREQ_DET_STATUS 0x5c -#define OSC_FREQ_DET_BUSY (1<<31) -#define OSC_FREQ_DET_CNT_MASK 0xFFFF +#define OSC_FREQ_DET_BUSYu (1<<31) +#define OSC_FREQ_DET_CNT_MASK 0xFFFFu #define TEGRA20_CLK_PERIPH_BANKS 3 From 94ec1a44e843492438226345b8529c651a86ba99 Mon Sep 17 00:00:00 2001 From: Tomas Krcka Date: Wed, 29 Mar 2023 12:34:19 +0000 Subject: [PATCH 3143/4345] iommu/arm-smmu-v3: Acknowledge pri/event queue overflow if any [ Upstream commit 67ea0b7ce41844eae7c10bb04dfe66a23318c224 ] When an overflow occurs in the PRI queue, the SMMU toggles the overflow flag in the PROD register. To exit the overflow condition, the PRI thread is supposed to acknowledge it by toggling this flag in the CONS register. Unacknowledged overflow causes the queue to stop adding anything new. Currently, the priq thread always writes the CONS register back to the SMMU after clearing the queue. The writeback is not necessary if the OVFLG in the PROD register has not been changed, no overflow has occured. This commit checks the difference of the overflow flag between CONS and PROD register. If it's different, toggles the OVACKFLG flag in the CONS register and write it to the SMMU. The situation is similar for the event queue. The acknowledge register is also toggled after clearing the event queue but never propagated to the hardware. This would only be done the next time when executing evtq thread. Unacknowledged event queue overflow doesn't affect the event queue, because the SMMU still adds elements to that queue when the overflow condition is active. But it feel nicer to keep SMMU in sync when possible, so use the same way here as well. Signed-off-by: Tomas Krcka Link: https://lore.kernel.org/r/20230329123420.34641-1-tomas.krcka@gmail.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index bc4cbc7542ce..982c42c87310 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -162,6 +162,18 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q) q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons); } +static void queue_sync_cons_ovf(struct arm_smmu_queue *q) +{ + struct arm_smmu_ll_queue *llq = &q->llq; + + if (likely(Q_OVF(llq->prod) == Q_OVF(llq->cons))) + return; + + llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | + Q_IDX(llq, llq->cons); + queue_sync_cons_out(q); +} + static int queue_sync_prod_in(struct arm_smmu_queue *q) { u32 prod; @@ -1380,8 +1392,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev) } while (!queue_empty(llq)); /* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); + queue_sync_cons_ovf(q); return IRQ_HANDLED; } @@ -1439,9 +1450,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev) } while (!queue_empty(llq)); /* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); - queue_sync_cons_out(q); + queue_sync_cons_ovf(q); return IRQ_HANDLED; } From 3b37bb0d929006f12bdba25ac181036d783ce009 Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Thu, 13 Apr 2023 23:57:42 -0700 Subject: [PATCH 3144/4345] Input: xpad - add constants for GIP interface numbers [ Upstream commit f9b2e603c6216824e34dc9a67205d98ccc9a41ca ] Wired GIP devices present multiple interfaces with the same USB identification other than the interface number. This adds constants for differentiating two of them and uses them where appropriate Signed-off-by: Vicki Pfau Link: https://lore.kernel.org/r/20230411031650.960322-2-vi@endrift.com Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/joystick/xpad.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 70dedc0f7827..0bd55e1fca37 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -489,6 +489,9 @@ struct xboxone_init_packet { } +#define GIP_WIRED_INTF_DATA 0 +#define GIP_WIRED_INTF_AUDIO 1 + /* * This packet is required for all Xbox One pads with 2015 * or later firmware installed (or present from the factory). @@ -1813,7 +1816,7 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id } if (xpad->xtype == XTYPE_XBOXONE && - intf->cur_altsetting->desc.bInterfaceNumber != 0) { + intf->cur_altsetting->desc.bInterfaceNumber != GIP_WIRED_INTF_DATA) { /* * The Xbox One controller lists three interfaces all with the * same interface class, subclass and protocol. Differentiate by From 7d939e367b648b54714ab3e9ab952a4032870cf5 Mon Sep 17 00:00:00 2001 From: Alain Volmat Date: Fri, 10 Feb 2023 23:43:08 +0100 Subject: [PATCH 3145/4345] phy: st: miphy28lp: use _poll_timeout functions for waits [ Upstream commit e3be4dd2c8d8aabfd2c3127d0e2e5754d3ae82d6 ] This commit introduces _poll_timeout functions usage instead of wait loops waiting for a status bit. Signed-off-by: Alain Volmat Reviewed-by: Patrice Chotard Link: https://lore.kernel.org/r/20230210224309.98452-1-avolmat@me.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/st/phy-miphy28lp.c | 42 ++++++++-------------------------- 1 file changed, 10 insertions(+), 32 deletions(-) diff --git a/drivers/phy/st/phy-miphy28lp.c b/drivers/phy/st/phy-miphy28lp.c index 068160a34f5c..e30305b77f0d 100644 --- a/drivers/phy/st/phy-miphy28lp.c +++ b/drivers/phy/st/phy-miphy28lp.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -484,19 +485,11 @@ static inline void miphy28lp_pcie_config_gen(struct miphy28lp_phy *miphy_phy) static inline int miphy28lp_wait_compensation(struct miphy28lp_phy *miphy_phy) { - unsigned long finish = jiffies + 5 * HZ; u8 val; /* Waiting for Compensation to complete */ - do { - val = readb_relaxed(miphy_phy->base + MIPHY_COMP_FSM_6); - - if (time_after_eq(jiffies, finish)) - return -EBUSY; - cpu_relax(); - } while (!(val & COMP_DONE)); - - return 0; + return readb_relaxed_poll_timeout(miphy_phy->base + MIPHY_COMP_FSM_6, + val, val & COMP_DONE, 1, 5 * USEC_PER_SEC); } @@ -805,7 +798,6 @@ static inline void miphy28lp_configure_usb3(struct miphy28lp_phy *miphy_phy) static inline int miphy_is_ready(struct miphy28lp_phy *miphy_phy) { - unsigned long finish = jiffies + 5 * HZ; u8 mask = HFC_PLL | HFC_RDY; u8 val; @@ -816,21 +808,14 @@ static inline int miphy_is_ready(struct miphy28lp_phy *miphy_phy) if (miphy_phy->type == PHY_TYPE_SATA) mask |= PHY_RDY; - do { - val = readb_relaxed(miphy_phy->base + MIPHY_STATUS_1); - if ((val & mask) != mask) - cpu_relax(); - else - return 0; - } while (!time_after_eq(jiffies, finish)); - - return -EBUSY; + return readb_relaxed_poll_timeout(miphy_phy->base + MIPHY_STATUS_1, + val, (val & mask) == mask, 1, + 5 * USEC_PER_SEC); } static int miphy_osc_is_ready(struct miphy28lp_phy *miphy_phy) { struct miphy28lp_dev *miphy_dev = miphy_phy->phydev; - unsigned long finish = jiffies + 5 * HZ; u32 val; if (!miphy_phy->osc_rdy) @@ -839,17 +824,10 @@ static int miphy_osc_is_ready(struct miphy28lp_phy *miphy_phy) if (!miphy_phy->syscfg_reg[SYSCFG_STATUS]) return -EINVAL; - do { - regmap_read(miphy_dev->regmap, - miphy_phy->syscfg_reg[SYSCFG_STATUS], &val); - - if ((val & MIPHY_OSC_RDY) != MIPHY_OSC_RDY) - cpu_relax(); - else - return 0; - } while (!time_after_eq(jiffies, finish)); - - return -EBUSY; + return regmap_read_poll_timeout(miphy_dev->regmap, + miphy_phy->syscfg_reg[SYSCFG_STATUS], + val, val & MIPHY_OSC_RDY, 1, + 5 * USEC_PER_SEC); } static int miphy28lp_get_resource_byname(struct device_node *child, From 6a1a72a8cfdad6911a7167405b63545ad781fbe2 Mon Sep 17 00:00:00 2001 From: Qiang Ning Date: Thu, 30 Mar 2023 10:43:53 +0800 Subject: [PATCH 3146/4345] mfd: dln2: Fix memory leak in dln2_probe() [ Upstream commit 96da8f148396329ba769246cb8ceaa35f1ddfc48 ] When dln2_setup_rx_urbs() in dln2_probe() fails, error out_free forgets to call usb_put_dev() to decrease the refcount of dln2->usb_dev. Fix this by adding usb_put_dev() in the error handling code of dln2_probe(). Signed-off-by: Qiang Ning Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230330024353.4503-1-qning0106@126.com Signed-off-by: Sasha Levin --- drivers/mfd/dln2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mfd/dln2.c b/drivers/mfd/dln2.c index 852129ea0766..fc65f9e25fda 100644 --- a/drivers/mfd/dln2.c +++ b/drivers/mfd/dln2.c @@ -836,6 +836,7 @@ out_stop_rx: dln2_stop_rx_urbs(dln2); out_free: + usb_put_dev(dln2->usb_dev); dln2_free(dln2); return ret; From 9c69a9d05824521e2e3a615283e8158772a1a5f7 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 26 Nov 2020 15:10:37 +0200 Subject: [PATCH 3147/4345] btrfs: move btrfs_find_highest_objectid/btrfs_find_free_objectid to disk-io.c [ Upstream commit ec7d6dfd73b2de1c6bc36f832542061b0ca0e0ff ] Those functions are going to be used even after inode cache is removed so moved them to a more appropriate place. Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 0004ff15ea26 ("btrfs: fix space cache inconsistency after error loading it from disk") Signed-off-by: Sasha Levin --- fs/btrfs/disk-io.c | 55 ++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/disk-io.h | 2 ++ fs/btrfs/inode-map.c | 55 -------------------------------------------- fs/btrfs/inode-map.h | 3 --- 4 files changed, 57 insertions(+), 58 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 2a7778a88f03..095c9e4f9224 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4780,3 +4780,58 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) return 0; } + +int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) +{ + struct btrfs_path *path; + int ret; + struct extent_buffer *l; + struct btrfs_key search_key; + struct btrfs_key found_key; + int slot; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + search_key.objectid = BTRFS_LAST_FREE_OBJECTID; + search_key.type = -1; + search_key.offset = (u64)-1; + ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); + if (ret < 0) + goto error; + BUG_ON(ret == 0); /* Corruption */ + if (path->slots[0] > 0) { + slot = path->slots[0] - 1; + l = path->nodes[0]; + btrfs_item_key_to_cpu(l, &found_key, slot); + *objectid = max_t(u64, found_key.objectid, + BTRFS_FIRST_FREE_OBJECTID - 1); + } else { + *objectid = BTRFS_FIRST_FREE_OBJECTID - 1; + } + ret = 0; +error: + btrfs_free_path(path); + return ret; +} + +int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) +{ + int ret; + mutex_lock(&root->objectid_mutex); + + if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) { + btrfs_warn(root->fs_info, + "the objectid of root %llu reaches its highest value", + root->root_key.objectid); + ret = -ENOSPC; + goto out; + } + + *objectid = ++root->highest_objectid; + ret = 0; +out: + mutex_unlock(&root->objectid_mutex); + return ret; +} diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 182540bdcea0..e3b96944ce10 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -131,6 +131,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, int btree_lock_page_hook(struct page *page, void *data, void (*flush_fn)(void *)); int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags); +int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid); +int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid); int __init btrfs_end_io_wq_init(void); void __cold btrfs_end_io_wq_exit(void); diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 76d2e43817ea..c74340d22624 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -525,58 +525,3 @@ out: extent_changeset_free(data_reserved); return ret; } - -int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) -{ - struct btrfs_path *path; - int ret; - struct extent_buffer *l; - struct btrfs_key search_key; - struct btrfs_key found_key; - int slot; - - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - - search_key.objectid = BTRFS_LAST_FREE_OBJECTID; - search_key.type = -1; - search_key.offset = (u64)-1; - ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); - if (ret < 0) - goto error; - BUG_ON(ret == 0); /* Corruption */ - if (path->slots[0] > 0) { - slot = path->slots[0] - 1; - l = path->nodes[0]; - btrfs_item_key_to_cpu(l, &found_key, slot); - *objectid = max_t(u64, found_key.objectid, - BTRFS_FIRST_FREE_OBJECTID - 1); - } else { - *objectid = BTRFS_FIRST_FREE_OBJECTID - 1; - } - ret = 0; -error: - btrfs_free_path(path); - return ret; -} - -int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) -{ - int ret; - mutex_lock(&root->objectid_mutex); - - if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) { - btrfs_warn(root->fs_info, - "the objectid of root %llu reaches its highest value", - root->root_key.objectid); - ret = -ENOSPC; - goto out; - } - - *objectid = ++root->highest_objectid; - ret = 0; -out: - mutex_unlock(&root->objectid_mutex); - return ret; -} diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h index 7a962811dffe..629baf9aefb1 100644 --- a/fs/btrfs/inode-map.h +++ b/fs/btrfs/inode-map.h @@ -10,7 +10,4 @@ int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid); int btrfs_save_ino_cache(struct btrfs_root *root, struct btrfs_trans_handle *trans); -int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid); -int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid); - #endif From a842fb6038e55c3602f23f5135c753da863b038e Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 26 Nov 2020 15:10:38 +0200 Subject: [PATCH 3148/4345] btrfs: replace calls to btrfs_find_free_ino with btrfs_find_free_objectid [ Upstream commit abadc1fcd72e887a8f875dabe4a07aa8c28ac8af ] The former is going away as part of the inode map removal so switch callers to btrfs_find_free_objectid. No functional changes since with INODE_MAP disabled (default) find_free_objectid was called anyway. Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba Stable-dep-of: 0004ff15ea26 ("btrfs: fix space cache inconsistency after error loading it from disk") Signed-off-by: Sasha Levin --- fs/btrfs/inode.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 779b7745cdc4..c900a39666e3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6273,7 +6273,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6337,7 +6337,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6481,7 +6481,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_fail; @@ -9135,7 +9135,7 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, u64 objectid; u64 index; - ret = btrfs_find_free_ino(root, &objectid); + ret = btrfs_find_free_objectid(root, &objectid); if (ret) return ret; @@ -9631,7 +9631,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -9962,7 +9962,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_find_free_ino(root, &objectid); + ret = btrfs_find_free_objectid(root, &objectid); if (ret) goto out; From 84fdaaf0d76e713d6d2e22f73358667975cfa9fa Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 4 May 2023 12:04:18 +0100 Subject: [PATCH 3149/4345] btrfs: fix space cache inconsistency after error loading it from disk [ Upstream commit 0004ff15ea26015a0a3a6182dca3b9d1df32e2b7 ] When loading a free space cache from disk, at __load_free_space_cache(), if we fail to insert a bitmap entry, we still increment the number of total bitmaps in the btrfs_free_space_ctl structure, which is incorrect since we failed to add the bitmap entry. On error we then empty the cache by calling __btrfs_remove_free_space_cache(), which will result in getting the total bitmaps counter set to 1. A failure to load a free space cache is not critical, so if a failure happens we just rebuild the cache by scanning the extent tree, which happens at block-group.c:caching_thread(). Yet the failure will result in having the total bitmaps of the btrfs_free_space_ctl always bigger by 1 then the number of bitmap entries we have. So fix this by having the total bitmaps counter be incremented only if we successfully added the bitmap entry. Fixes: a67509c30079 ("Btrfs: add a io_ctl struct and helpers for dealing with the space cache") Reviewed-by: Anand Jain CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/free-space-cache.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index ba280707d5ec..4989c60b1df9 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -794,15 +794,16 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, } spin_lock(&ctl->tree_lock); ret = link_free_space(ctl, e); - ctl->total_bitmaps++; - ctl->op->recalc_thresholds(ctl); - spin_unlock(&ctl->tree_lock); if (ret) { + spin_unlock(&ctl->tree_lock); btrfs_err(fs_info, "Duplicate entries in free space cache, dumping"); kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } + ctl->total_bitmaps++; + ctl->op->recalc_thresholds(ctl); + spin_unlock(&ctl->tree_lock); list_add_tail(&e->list, &bitmaps); } From 295e07a76bf30d765303816c7c8a3ff8a0ce5348 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 4 Apr 2023 15:12:16 +0200 Subject: [PATCH 3150/4345] xfrm: don't check the default policy if the policy allows the packet [ Upstream commit 430cac487400494c19a8b85299e979bb07b4671f ] The current code doesn't let a simple "allow" policy counteract a default policy blocking all incoming packets: ip x p setdefault in block ip x p a src 192.168.2.1/32 dst 192.168.2.2/32 dir in action allow At this stage, we have an allow policy (with or without transforms) for this packet. It doesn't matter what the default policy says, since the policy we looked up lets the packet through. The case of a blocking policy is already handled separately, so we can remove this check. Fixes: 2d151d39073a ("xfrm: Add possibility to set the default to block if we have no policy") Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_policy.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d15aa62887de..8ebe305f6ddd 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3677,12 +3677,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_nr = ti; - if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK && - !xfrm_nr) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); - goto reject; - } - if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; From c5449195f86ec02433a9ef8abe01be11d228fca1 Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Tue, 25 Apr 2023 09:46:18 +0200 Subject: [PATCH 3151/4345] Revert "Fix XFRM-I support for nested ESP tunnels" [ Upstream commit 5fc46f94219d1d103ffb5f0832be9da674d85a73 ] This reverts commit b0355dbbf13c0052931dd14c38c789efed64d3de. The reverted commit clears the secpath on packets received via xfrm interfaces to support nested IPsec tunnels. This breaks Netfilter policy matching using xt_policy in the FORWARD chain, as the secpath is missing during forwarding. Additionally, Benedict Wong reports that it breaks Transport-in-Tunnel mode. Fix this regression by reverting the commit until we have a better approach for nested IPsec tunnels. Fixes: b0355dbbf13c ("Fix XFRM-I support for nested ESP tunnels") Link: https://lore.kernel.org/netdev/20230412085615.124791-1-martin@strongswan.org/ Signed-off-by: Martin Willi Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_interface.c | 54 +++------------------------------------ net/xfrm/xfrm_policy.c | 3 --- 2 files changed, 4 insertions(+), 53 deletions(-) diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index e4f21a692415..da518b4ca84c 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -207,52 +207,6 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } -static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type, unsigned short family) -{ - struct sec_path *sp; - - sp = skb_sec_path(skb); - if (sp && (sp->len || sp->olen) && - !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) - goto discard; - - XFRM_SPI_SKB_CB(skb)->family = family; - if (family == AF_INET) { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; - } else { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; - } - - return xfrm_input(skb, nexthdr, spi, encap_type); -discard: - kfree_skb(skb); - return 0; -} - -static int xfrmi4_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); -} - -static int xfrmi6_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], - 0, 0, AF_INET6); -} - -static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); -} - -static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); -} - static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -826,8 +780,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrmi6_rcv, - .input_handler = xfrmi6_input, + .handler = xfrm6_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -877,8 +831,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrmi4_rcv, - .input_handler = xfrmi4_input, + .handler = xfrm4_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 8ebe305f6ddd..295685492853 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3704,9 +3704,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } - if (if_id) - secpath_reset(skb); - xfrm_pols_put(pols, npols); return 1; } From eaf9394ed79c8913322333c627ff63dc56925eb6 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 21 Apr 2023 15:56:57 +0100 Subject: [PATCH 3152/4345] drm/msm/dp: unregister audio driver during unbind [ Upstream commit 85c636284cb63b7740b4ae98881ace92158068d3 ] while binding the code always registers a audio driver, however there is no corresponding unregistration done in unbind. This leads to multiple redundant audio platform devices if dp_display_bind and dp_display_unbind happens multiple times during startup. On X13s platform this resulted in 6 to 9 audio codec device instead of just 3 codec devices for 3 dp ports. Fix this by unregistering codecs on unbind. Signed-off-by: Srinivas Kandagatla Fixes: d13e36d7d222 ("drm/msm/dp: add audio support for Display Port on MSM") Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/533324/ Link: https://lore.kernel.org/r/20230421145657.12186-1-srinivas.kandagatla@linaro.org Signed-off-by: Abhinav Kumar Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dp/dp_audio.c | 12 ++++++++++++ drivers/gpu/drm/msm/dp/dp_audio.h | 2 ++ drivers/gpu/drm/msm/dp/dp_display.c | 1 + 3 files changed, 15 insertions(+) diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index d7e4a39a904e..0eaaaa94563a 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -577,6 +577,18 @@ static struct hdmi_codec_pdata codec_data = { .i2s = 1, }; +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio) +{ + struct dp_audio_private *audio_priv; + + audio_priv = container_of(dp_audio, struct dp_audio_private, dp_audio); + + if (audio_priv->audio_pdev) { + platform_device_unregister(audio_priv->audio_pdev); + audio_priv->audio_pdev = NULL; + } +} + int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio) { diff --git a/drivers/gpu/drm/msm/dp/dp_audio.h b/drivers/gpu/drm/msm/dp/dp_audio.h index 84e5f4a5d26b..4ab78880af82 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.h +++ b/drivers/gpu/drm/msm/dp/dp_audio.h @@ -53,6 +53,8 @@ struct dp_audio *dp_audio_get(struct platform_device *pdev, int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio); +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio); + /** * dp_audio_put() * diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 1c3dcbc6cce8..0bcccf422192 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -276,6 +276,7 @@ static void dp_display_unbind(struct device *dev, struct device *master, kthread_stop(dp->ev_tsk); dp_power_client_deinit(dp->power); + dp_unregister_audio_driver(dev, dp->audio); dp_aux_unregister(dp->aux); priv->dp = NULL; } From dc30fed07ddf9062ccdb19df40bcb2413975a47c Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:22 +0200 Subject: [PATCH 3153/4345] drm/msm/dpu: Remove duplicate register defines from INTF [ Upstream commit 202c044203ac5860e3025169105368d99f9bc6a2 ] The INTF_FRAME_LINE_COUNT_EN, INTF_FRAME_COUNT and INTF_LINE_COUNT registers are already defined higher up, in the right place when sorted numerically. Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Signed-off-by: Marijn Suijten Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534231/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-8-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index 108882bbd2b8..7aa6accb74ad 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -51,11 +51,6 @@ #define INTF_TPG_RGB_MAPPING 0x11C #define INTF_PROG_FETCH_START 0x170 #define INTF_PROG_ROT_START 0x174 - -#define INTF_FRAME_LINE_COUNT_EN 0x0A8 -#define INTF_FRAME_COUNT 0x0AC -#define INTF_LINE_COUNT 0x0B0 - #define INTF_MUX 0x25C static const struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf, From f5cb28a90c8cf230e755ec73f5ce53d17e6d2152 Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Thu, 4 May 2023 06:25:44 +0000 Subject: [PATCH 3154/4345] cpupower: Make TSC read per CPU for Mperf monitor [ Upstream commit c2adb1877b76fc81ae041e1db1a6ed2078c6746b ] System-wide TSC read could cause a drift in C0 percentage calculation. Because if first TSC is read and then one by one mperf is read for all cpus, this introduces drift between mperf reading of later CPUs and TSC reading. To lower this drift read TSC per CPU and also just after mperf read. This technique improves C0 percentage calculation in Mperf monitor. Before fix: (System 100% busy) | Mperf || RAPL || Idle_Stats PKG|CORE| CPU| C0 | Cx | Freq || pack | core || POLL | C1 | C2 0| 0| 0| 87.15| 12.85| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 0| 256| 84.62| 15.38| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 1| 1| 87.15| 12.85| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 1| 257| 84.08| 15.92| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 2| 2| 86.61| 13.39| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 2| 258| 83.26| 16.74| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 3| 3| 86.61| 13.39| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 3| 259| 83.60| 16.40| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 4| 4| 86.33| 13.67| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 4| 260| 83.33| 16.67| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 5| 5| 86.06| 13.94| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 5| 261| 83.05| 16.95| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 6| 6| 85.51| 14.49| 2695||168659003|3970468|| 0.00| 0.00| 0.00 After fix: (System 100% busy) | Mperf || RAPL || Idle_Stats PKG|CORE| CPU| C0 | Cx | Freq || pack | core || POLL | C1 | C2 0| 0| 0| 98.03| 1.97| 2415||163295480|3811189|| 0.00| 0.00| 0.00 0| 0| 256| 98.50| 1.50| 2394||163295480|3811189|| 0.00| 0.00| 0.00 0| 1| 1| 99.99| 0.01| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 1| 257| 99.99| 0.01| 2375||163295480|3811189|| 0.00| 0.00| 0.00 0| 2| 2| 99.99| 0.01| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 2| 258|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 3| 3|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 3| 259| 99.99| 0.01| 2435||163295480|3811189|| 0.00| 0.00| 0.00 0| 4| 4|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 4| 260|100.00| 0.00| 2435||163295480|3811189|| 0.00| 0.00| 0.00 0| 5| 5| 99.99| 0.01| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 5| 261|100.00| 0.00| 2435||163295480|3811189|| 0.00| 0.00| 0.00 0| 6| 6|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 6| 262|100.00| 0.00| 2435||163295480|3811189|| 0.00| 0.00| 0.00 Cc: Thomas Renninger Cc: Shuah Khan Cc: Dominik Brodowski Fixes: 7fe2f6399a84 ("cpupowerutils - cpufrequtils extended with quite some features") Signed-off-by: Wyes Karny Signed-off-by: Shuah Khan Signed-off-by: Sasha Levin --- .../utils/idle_monitor/mperf_monitor.c | 31 +++++++++---------- 1 file changed, 14 insertions(+), 17 deletions(-) diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index e7d48cb563c0..ae6af354a81d 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -70,8 +70,8 @@ static int max_freq_mode; */ static unsigned long max_frequency; -static unsigned long long tsc_at_measure_start; -static unsigned long long tsc_at_measure_end; +static unsigned long long *tsc_at_measure_start; +static unsigned long long *tsc_at_measure_end; static unsigned long long *mperf_previous_count; static unsigned long long *aperf_previous_count; static unsigned long long *mperf_current_count; @@ -169,7 +169,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, aperf_diff = aperf_current_count[cpu] - aperf_previous_count[cpu]; if (max_freq_mode == MAX_FREQ_TSC_REF) { - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; *percent = 100.0 * mperf_diff / tsc_diff; dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); @@ -206,7 +206,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; time_diff = timespec_diff_us(time_start, time_end); max_frequency = tsc_diff / time_diff; } @@ -225,33 +225,27 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, static int mperf_start(void) { int cpu; - unsigned long long dbg; clock_gettime(CLOCK_REALTIME, &time_start); - mperf_get_tsc(&tsc_at_measure_start); - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { + mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); + } - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start); return 0; } static int mperf_stop(void) { - unsigned long long dbg; int cpu; - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); + mperf_get_tsc(&tsc_at_measure_end[cpu]); + } - mperf_get_tsc(&tsc_at_measure_end); clock_gettime(CLOCK_REALTIME, &time_end); - - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end); - return 0; } @@ -353,7 +347,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_previous_count = calloc(cpu_count, sizeof(unsigned long long)); mperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); - + tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); + tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -364,6 +359,8 @@ void mperf_unregister(void) free(aperf_previous_count); free(mperf_current_count); free(aperf_current_count); + free(tsc_at_measure_start); + free(tsc_at_measure_end); free(is_valid); } From 8f57715f8ef6afd75e0d10e70bc970489907e548 Mon Sep 17 00:00:00 2001 From: Tobias Brunner Date: Tue, 9 May 2023 11:00:06 +0200 Subject: [PATCH 3155/4345] af_key: Reject optional tunnel/BEET mode templates in outbound policies [ Upstream commit cf3128a7aca55b2eefb68281d44749c683bdc96f ] xfrm_state_find() uses `encap_family` of the current template with the passed local and remote addresses to find a matching state. If an optional tunnel or BEET mode template is skipped in a mixed-family scenario, there could be a mismatch causing an out-of-bounds read as the addresses were not replaced to match the family of the next template. While there are theoretical use cases for optional templates in outbound policies, the only practical one is to skip IPComp states in inbound policies if uncompressed packets are received that are handled by an implicitly created IPIP state instead. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Tobias Brunner Acked-by: Herbert Xu Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/key/af_key.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/key/af_key.c b/net/key/af_key.c index 8bc7d399987b..fff2bd5f03e3 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1944,7 +1944,8 @@ static u32 gen_reqid(struct net *net) } static int -parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) +parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_policy *pol, + struct sadb_x_ipsecrequest *rq) { struct net *net = xp_net(xp); struct xfrm_tmpl *t = xp->xfrm_vec + xp->xfrm_nr; @@ -1962,9 +1963,12 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; - if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) + if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) { + if ((mode == XFRM_MODE_TUNNEL || mode == XFRM_MODE_BEET) && + pol->sadb_x_policy_dir == IPSEC_DIR_OUTBOUND) + return -EINVAL; t->optional = 1; - else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { + } else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { t->reqid = rq->sadb_x_ipsecrequest_reqid; if (t->reqid > IPSEC_MANUAL_REQID_MAX) t->reqid = 0; @@ -2006,7 +2010,7 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) rq->sadb_x_ipsecrequest_len < sizeof(*rq)) return -EINVAL; - if ((err = parse_ipsecrequest(xp, rq)) < 0) + if ((err = parse_ipsecrequest(xp, pol, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; rq = (void*)((u8*)rq + rq->sadb_x_ipsecrequest_len); From 83996d317b1deddc85006376082e8886f55aa709 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 10 May 2023 22:00:20 +0200 Subject: [PATCH 3156/4345] net: fec: Better handle pm_runtime_get() failing in .remove() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f816b9829b19394d318e01953aa3b2721bca040d ] In the (unlikely) event that pm_runtime_get() (disguised as pm_runtime_resume_and_get()) fails, the remove callback returned an error early. The problem with this is that the driver core ignores the error value and continues removing the device. This results in a resource leak. Worse the devm allocated resources are freed and so if a callback of the driver is called later the register mapping is already gone which probably results in a crash. Fixes: a31eda65ba21 ("net: fec: fix clock count mis-match") Signed-off-by: Uwe Kleine-König Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230510200020.1534610-1-u.kleine-koenig@pengutronix.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/fec_main.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 686bb873125c..e18b3b72fc0d 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3850,9 +3850,11 @@ fec_drv_remove(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; int ret; - ret = pm_runtime_resume_and_get(&pdev->dev); + ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) - return ret; + dev_err(&pdev->dev, + "Failed to resume device in remove callback (%pe)\n", + ERR_PTR(ret)); cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -3865,8 +3867,13 @@ fec_drv_remove(struct platform_device *pdev) of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); - clk_disable_unprepare(fep->clk_ahb); - clk_disable_unprepare(fep->clk_ipg); + /* After pm_runtime_get_sync() failed, the clks are still off, so skip + * disabling them again. + */ + if (ret >= 0) { + clk_disable_unprepare(fep->clk_ahb); + clk_disable_unprepare(fep->clk_ipg); + } pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); From 6fb537895d29559f5586d45090d97a21cb5fcdd7 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Wed, 10 May 2023 18:21:39 +0530 Subject: [PATCH 3157/4345] net: phy: dp83867: add w/a for packet errors seen with short cables [ Upstream commit 0b01db274028f5acd207332686ffc92ac77491ac ] Introduce the W/A for packet errors seen with short cables (<1m) between two DP83867 PHYs. The W/A recommended by DM requires FFE Equalizer Configuration tuning by writing value 0x0E81 to DSP_FFE_CFG register (0x012C), surrounded by hard and soft resets as follows: write_reg(0x001F, 0x8000); //hard reset write_reg(DSP_FFE_CFG, 0x0E81); write_reg(0x001F, 0x4000); //soft reset Since DP83867 PHY DM says "Changing this register to 0x0E81, will not affect Long Cable performance.", enable the W/A by default. Fixes: 2a10154abcb7 ("net: phy: dp83867: Add TI dp83867 phy") Signed-off-by: Grygorii Strashko Signed-off-by: Siddharth Vadapalli Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/phy/dp83867.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index c8031e297faf..5fabcd15ef77 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -41,6 +41,7 @@ #define DP83867_STRAP_STS1 0x006E #define DP83867_STRAP_STS2 0x006f #define DP83867_RGMIIDCTL 0x0086 +#define DP83867_DSP_FFE_CFG 0x012c #define DP83867_RXFCFG 0x0134 #define DP83867_RXFPMD1 0x0136 #define DP83867_RXFPMD2 0x0137 @@ -807,8 +808,27 @@ static int dp83867_phy_reset(struct phy_device *phydev) usleep_range(10, 20); - return phy_modify(phydev, MII_DP83867_PHYCTRL, + err = phy_modify(phydev, MII_DP83867_PHYCTRL, DP83867_PHYCR_FORCE_LINK_GOOD, 0); + if (err < 0) + return err; + + /* Configure the DSP Feedforward Equalizer Configuration register to + * improve short cable (< 1 meter) performance. This will not affect + * long cable performance. + */ + err = phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_DSP_FFE_CFG, + 0x0e81); + if (err < 0) + return err; + + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); + if (err < 0) + return err; + + usleep_range(10, 20); + + return 0; } static void dp83867_link_change_notify(struct phy_device *phydev) From 13c5fa1248bf06e95a25907c1be83948b8c44c50 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 9 May 2023 12:07:11 +0300 Subject: [PATCH 3158/4345] ALSA: firewire-digi00x: prevent potential use after free [ Upstream commit c0e72058d5e21982e61a29de6b098f7c1f0db498 ] This code was supposed to return an error code if init_stream() failed, but it instead freed dg00x->rx_stream and returned success. This potentially leads to a use after free. Fixes: 9a08067ec318 ("ALSA: firewire-digi00x: support AMDTP domain") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/c224cbd5-d9e2-4cd4-9bcf-2138eb1d35c6@kili.mountain Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/firewire/digi00x/digi00x-stream.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/firewire/digi00x/digi00x-stream.c b/sound/firewire/digi00x/digi00x-stream.c index 405d6903bfbc..62a54f5ab84d 100644 --- a/sound/firewire/digi00x/digi00x-stream.c +++ b/sound/firewire/digi00x/digi00x-stream.c @@ -259,8 +259,10 @@ int snd_dg00x_stream_init_duplex(struct snd_dg00x *dg00x) return err; err = init_stream(dg00x, &dg00x->tx_stream); - if (err < 0) + if (err < 0) { destroy_stream(dg00x, &dg00x->rx_stream); + return err; + } err = amdtp_domain_init(&dg00x->domain); if (err < 0) { From b1cf6bd8833b12a7a3dc9f77a61ad901a6c3a8fb Mon Sep 17 00:00:00 2001 From: "Ryan C. Underwood" Date: Thu, 11 May 2023 12:32:21 -0500 Subject: [PATCH 3159/4345] ALSA: hda/realtek: Apply HP B&O top speaker profile to Pavilion 15 [ Upstream commit 92553ee03166ef8fa978e7683f9f4af30c9c4e6b ] The Pavilion 15 line has B&O top speakers similar to the x360 and applying the same profile produces good sound. Without this, the sound would be tinny and underpowered without either applying model=alc295-hp-x360 or booting another OS first. Signed-off-by: Ryan Underwood Fixes: 563785edfcef ("ALSA: hda/realtek - Add quirk entry for HP Pavilion 15") Link: https://lore.kernel.org/r/ZF0mpcMz3ezP9KQw@icequake.net Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 18309fa17fb8..c7e25d19c9d9 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8944,7 +8944,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x802f, "HP Z240", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8077, "HP", ALC256_FIXUP_HP_HEADSET_MIC), SND_PCI_QUIRK(0x103c, 0x8158, "HP", ALC256_FIXUP_HP_HEADSET_MIC), - SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x827f, "HP x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), From 171669917762e3a10c698b0d15b64c20ac11003c Mon Sep 17 00:00:00 2001 From: Zhuang Shengen Date: Thu, 11 May 2023 19:34:30 +0800 Subject: [PATCH 3160/4345] vsock: avoid to close connected socket after the timeout MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 6d4486efe9c69626cab423456169e250a5cd3af5 ] When client and server establish a connection through vsock, the client send a request to the server to initiate the connection, then start a timer to wait for the server's response. When the server's RESPONSE message arrives, the timer also times out and exits. The server's RESPONSE message is processed first, and the connection is established. However, the client's timer also times out, the original processing logic of the client is to directly set the state of this vsock to CLOSE and return ETIMEDOUT. It will not notify the server when the port is released, causing the server port remain. when client's vsock_connect timeout，it should check sk state is ESTABLISHED or not. if sk state is ESTABLISHED, it means the connection is established, the client should not set the sk state to CLOSE Note: I encountered this issue on kernel-4.18, which can be fixed by this patch. Then I checked the latest code in the community and found similar issue. Fixes: d021c344051a ("VSOCK: Introduce VM Sockets") Signed-off-by: Zhuang Shengen Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/vmw_vsock/af_vsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 7829a5018ef9..ce14374bbaca 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1372,7 +1372,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, vsock_transport_cancel_pkt(vsk); vsock_remove_connected(vsk); goto out_wait; - } else if (timeout == 0) { + } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { err = -ETIMEDOUT; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; From a9ef8b2589885851c769982ef34cb01348fb07bb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Jan 2022 12:24:57 -0800 Subject: [PATCH 3161/4345] ipv4/tcp: do not use per netns ctl sockets [ Upstream commit 37ba017dcc3b1123206808979834655ddcf93251 ] TCP ipv4 uses per-cpu/per-netns ctl sockets in order to send RST and some ACK packets (on behalf of TIMEWAIT sockets). This adds memory and cpu costs, which do not seem needed. Now typical servers have 256 or more cores, this adds considerable tax to netns users. tcp sockets are used from BH context, are not receiving packets, and do not store any persistent state but the 'struct net' pointer in order to be able to use IPv4 output functions. Note that I attempted a related change in the past, that had to be hot-fixed in commit bdbbb8527b6f ("ipv4: tcp: get rid of ugly unicast_sock") This patch could very well surface old bugs, on layers not taking care of sk->sk_kern_sock properly. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Stable-dep-of: 1e306ec49a1f ("tcp: fix possible sk_priority leak in tcp_v4_send_reset()") Signed-off-by: Sasha Levin --- include/net/netns/ipv4.h | 1 - net/ipv4/tcp_ipv4.c | 61 ++++++++++++++++++---------------------- 2 files changed, 27 insertions(+), 35 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d8b320cf54ba..4a4a5270ff6f 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -71,7 +71,6 @@ struct netns_ipv4 { struct sock *mc_autojoin_sk; struct inet_peer_base *peers; - struct sock * __percpu *tcp_sk; struct fqdir *fqdir; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 8bd7b1ec3b6a..275ae42be99e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -91,6 +91,8 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); +static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk); + static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, @@ -794,7 +796,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); + ctl_sk = this_cpu_read(ipv4_tcp_sk); + sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; @@ -809,6 +812,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) transmit_time); ctl_sk->sk_mark = 0; + sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_bh_enable(); @@ -892,7 +896,8 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); + ctl_sk = this_cpu_read(ipv4_tcp_sk); + sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? @@ -905,6 +910,7 @@ static void tcp_v4_send_ack(const struct sock *sk, transmit_time); ctl_sk->sk_mark = 0; + sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); } @@ -2828,41 +2834,14 @@ EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { - int cpu; - if (net->ipv4.tcp_congestion_control) bpf_module_put(net->ipv4.tcp_congestion_control, net->ipv4.tcp_congestion_control->owner); - - for_each_possible_cpu(cpu) - inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); - free_percpu(net->ipv4.tcp_sk); } static int __net_init tcp_sk_init(struct net *net) { - int res, cpu, cnt; - - net->ipv4.tcp_sk = alloc_percpu(struct sock *); - if (!net->ipv4.tcp_sk) - return -ENOMEM; - - for_each_possible_cpu(cpu) { - struct sock *sk; - - res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, - IPPROTO_TCP, net); - if (res) - goto fail; - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); - - /* Please enforce IP_DF and IPID==0 for RST and - * ACK sent in SYN-RECV and TIME-WAIT state. - */ - inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; - - *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; - } + int cnt; net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_ecn_fallback = 1; @@ -2947,10 +2926,6 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.tcp_congestion_control = &tcp_reno; return 0; -fail: - tcp_sk_exit(net); - - return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) @@ -3027,6 +3002,24 @@ static void __init bpf_iter_register(void) void __init tcp_v4_init(void) { + int cpu, res; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, &init_net); + if (res) + panic("Failed to create the TCP control socket.\n"); + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + /* Please enforce IP_DF and IPID==0 for RST and + * ACK sent in SYN-RECV and TIME-WAIT state. + */ + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + + per_cpu(ipv4_tcp_sk, cpu) = sk; + } if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); From 788791990d74d3d2140c0f72df0b9218d3984dd8 Mon Sep 17 00:00:00 2001 From: sewookseo Date: Thu, 7 Jul 2022 10:01:39 +0000 Subject: [PATCH 3162/4345] net: Find dst with sk's xfrm policy not ctl_sk MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e22aa14866684f77b4f6b6cae98539e520ddb731 ] If we set XFRM security policy by calling setsockopt with option IPV6_XFRM_POLICY, the policy will be stored in 'sock_policy' in 'sock' struct. However tcp_v6_send_response doesn't look up dst_entry with the actual socket but looks up with tcp control socket. This may cause a problem that a RST packet is sent without ESP encryption & peer's TCP socket can't receive it. This patch will make the function look up dest_entry with actual socket, if the socket has XFRM policy(sock_policy), so that the TCP response packet via this function can be encrypted, & aligned on the encrypted TCP socket. Tested: We encountered this problem when a TCP socket which is encrypted in ESP transport mode encryption, receives challenge ACK at SYN_SENT state. After receiving challenge ACK, TCP needs to send RST to establish the socket at next SYN try. But the RST was not encrypted & peer TCP socket still remains on ESTABLISHED state. So we verified this with test step as below. [Test step] 1. Making a TCP state mismatch between client(IDLE) & server(ESTABLISHED). 2. Client tries a new connection on the same TCP ports(src & dst). 3. Server will return challenge ACK instead of SYN,ACK. 4. Client will send RST to server to clear the SOCKET. 5. Client will retransmit SYN to server on the same TCP ports. [Expected result] The TCP connection should be established. Cc: Maciej Żenczykowski Cc: Eric Dumazet Cc: Steffen Klassert Cc: Sehee Lee Signed-off-by: Sewook Seo Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Stable-dep-of: 1e306ec49a1f ("tcp: fix possible sk_priority leak in tcp_v4_send_reset()") Signed-off-by: Sasha Levin --- include/net/xfrm.h | 2 ++ net/ipv4/ip_output.c | 2 +- net/ipv4/tcp_ipv4.c | 2 ++ net/ipv6/tcp_ipv6.c | 5 ++++- 4 files changed, 9 insertions(+), 2 deletions(-) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 8a9943d935f1..726a2dbb407f 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1198,6 +1198,8 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { + if (!sk_fullsock(osk)) + return 0; sk->sk_policy[0] = NULL; sk->sk_policy[1] = NULL; if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1e07df282177..6fd04f2f8b40 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1723,7 +1723,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, tcp_hdr(skb)->source, tcp_hdr(skb)->dest, arg->uid); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); - rt = ip_route_output_key(net, &fl4); + rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) return; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 275ae42be99e..1995d46afb21 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -804,6 +804,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); + xfrm_sk_clone_policy(ctl_sk, sk); } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -812,6 +813,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) transmit_time); ctl_sk->sk_mark = 0; + xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2347740d3cc7..fe29bc66aeac 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -984,7 +984,10 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 * Underlying function will use this to retrieve the network * namespace */ - dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); + if (sk && sk->sk_state != TCP_TIME_WAIT) + dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/ + else + dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, From e7fd68abbba3409b1c365fe04e7b2c37298954a1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 May 2023 11:47:49 +0000 Subject: [PATCH 3163/4345] tcp: fix possible sk_priority leak in tcp_v4_send_reset() [ Upstream commit 1e306ec49a1f206fd2cc89a42fac6e6f592a8cc1 ] When tcp_v4_send_reset() is called with @sk == NULL, we do not change ctl_sk->sk_priority, which could have been set from a prior invocation. Change tcp_v4_send_reset() to set sk_priority and sk_mark fields before calling ip_send_unicast_reply(). This means tcp_v4_send_reset() and tcp_v4_send_ack() no longer have to clear ctl_sk->sk_mark after their call to ip_send_unicast_reply(). Fixes: f6c0f5d209fa ("tcp: honor SO_PRIORITY in TIME_WAIT state") Signed-off-by: Eric Dumazet Cc: Antoine Tenart Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/tcp_ipv4.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1995d46afb21..270b20e0907c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -805,6 +805,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); + } else { + ctl_sk->sk_mark = 0; + ctl_sk->sk_priority = 0; } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -812,7 +815,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) &arg, arg.iov[0].iov_len, transmit_time); - ctl_sk->sk_mark = 0; xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); @@ -911,7 +913,6 @@ static void tcp_v4_send_ack(const struct sock *sk, &arg, arg.iov[0].iov_len, transmit_time); - ctl_sk->sk_mark = 0; sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); From 153017561d2804cfae87cc9aa377aa84dd906ae1 Mon Sep 17 00:00:00 2001 From: Ke Zhang Date: Fri, 28 Apr 2023 11:16:36 +0800 Subject: [PATCH 3164/4345] serial: arc_uart: fix of_iomap leak in `arc_serial_probe` [ Upstream commit 8ab5fc55d7f65d58a3c3aeadf11bdf60267cd2bd ] Smatch reports: drivers/tty/serial/arc_uart.c:631 arc_serial_probe() warn: 'port->membase' from of_iomap() not released on lines: 631. In arc_serial_probe(), if uart_add_one_port() fails, port->membase is not released, which would cause a resource leak. To fix this, I replace of_iomap with devm_platform_ioremap_resource. Fixes: 8dbe1d5e09a7 ("serial/arc: inline the probe helper") Signed-off-by: Ke Zhang Reviewed-by: Dongliang Mu Link: https://lore.kernel.org/r/20230428031636.44642-1-m202171830@hust.edu.cn Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/arc_uart.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/arc_uart.c b/drivers/tty/serial/arc_uart.c index 17c3fc398fc6..6f7a7d2dcf3a 100644 --- a/drivers/tty/serial/arc_uart.c +++ b/drivers/tty/serial/arc_uart.c @@ -609,10 +609,11 @@ static int arc_serial_probe(struct platform_device *pdev) } uart->baud = val; - port->membase = of_iomap(np, 0); - if (!port->membase) + port->membase = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(port->membase)) { /* No point of dev_err since UART itself is hosed here */ - return -ENXIO; + return PTR_ERR(port->membase); + } port->irq = irq_of_parse_and_map(np, 0); From e1f800be74c188fdad978f8c3353769defcb7760 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 11 May 2023 19:22:11 -0400 Subject: [PATCH 3165/4345] erspan: get the proto with the md version for collect_md [ Upstream commit d80fc101d2eb9b3188c228d61223890aeea480a4 ] In commit 20704bd1633d ("erspan: build the header with the right proto according to erspan_ver"), it gets the proto with t->parms.erspan_ver, but t->parms.erspan_ver is not used by collect_md branch, and instead it should get the proto with md->version for collect_md. Thanks to Kevin for pointing this out. Fixes: 20704bd1633d ("erspan: build the header with the right proto according to erspan_ver") Fixes: 94d7d8f29287 ("ip6_gre: add erspan v2 support") Reported-by: Kevin Traynor Signed-off-by: Xin Long Reviewed-by: Simon Horman Reviewed-by: William Tu Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/ip6_gre.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 2332b5b81c55..7b50e1811678 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1015,12 +1015,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, ntohl(tun_id), ntohl(md->u.index), truncate, false); + proto = htons(ETH_P_ERSPAN); } else if (md->version == 2) { erspan_build_header_v2(skb, ntohl(tun_id), md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + proto = htons(ETH_P_ERSPAN2); } else { goto tx_err; } @@ -1043,24 +1045,25 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, break; } - if (t->parms.erspan_ver == 1) + if (t->parms.erspan_ver == 1) { erspan_build_header(skb, ntohl(t->parms.o_key), t->parms.index, truncate, false); - else if (t->parms.erspan_ver == 2) + proto = htons(ETH_P_ERSPAN); + } else if (t->parms.erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(t->parms.o_key), t->parms.dir, t->parms.hwid, truncate, false); - else + proto = htons(ETH_P_ERSPAN2); + } else { goto tx_err; + } fl6.daddr = t->parms.raddr; } /* Push GRE header. */ - proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) - : htons(ETH_P_ERSPAN2); gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ From aba74ad99870d8b862bc636c17bdf85b72979e37 Mon Sep 17 00:00:00 2001 From: Jijie Shao Date: Fri, 12 May 2023 18:00:12 +0800 Subject: [PATCH 3166/4345] net: hns3: fix sending pfc frames after reset issue [ Upstream commit f14db07064727dd3bc0906c77a6d2759c1bbb395 ] To prevent the system from abnormally sending PFC frames after an abnormal reset. The hns3 driver notifies the firmware to disable pfc before reset. Fixes: 35d93a30040c ("net: hns3: adjust the process of PF reset") Signed-off-by: Jijie Shao Signed-off-by: Hao Lan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 15 +++++++++------ .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 4 ++-- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h | 5 +++++ 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 2070e26a3a35..1ec1709446ba 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -7023,12 +7023,15 @@ static void hclge_ae_stop(struct hnae3_handle *handle) /* If it is not PF reset or FLR, the firmware will disable the MAC, * so it only need to stop phy here. */ - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && - hdev->reset_type != HNAE3_FUNC_RESET && - hdev->reset_type != HNAE3_FLR_RESET) { - hclge_mac_stop_phy(hdev); - hclge_update_link_status(hdev); - return; + if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) { + hclge_pfc_pause_en_cfg(hdev, HCLGE_PFC_TX_RX_DISABLE, + HCLGE_PFC_DISABLE); + if (hdev->reset_type != HNAE3_FUNC_RESET && + hdev->reset_type != HNAE3_FLR_RESET) { + hclge_mac_stop_phy(hdev); + hclge_update_link_status(hdev); + return; + } } for (i = 0; i < handle->kinfo.num_tqps; i++) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 9168e39b6364..b3ceaaaeacae 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -169,8 +169,8 @@ int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx) return hclge_cmd_send(&hdev->hw, &desc, 1); } -static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, - u8 pfc_bitmap) +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap) { struct hclge_desc desc; struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)desc.data; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index bb2a2d8e9259..42932c879b36 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -117,6 +117,9 @@ struct hclge_bp_to_qs_map_cmd { u32 rsvd1; }; +#define HCLGE_PFC_DISABLE 0 +#define HCLGE_PFC_TX_RX_DISABLE 0 + struct hclge_pfc_en_cmd { u8 tx_rx_en_bitmap; u8 pri_en_bitmap; @@ -164,6 +167,8 @@ void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc); void hclge_tm_pfc_info_update(struct hclge_dev *hdev); int hclge_tm_dwrr_cfg(struct hclge_dev *hdev); int hclge_tm_init_hw(struct hclge_dev *hdev, bool init); +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); int hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); From 0cefa42152430bc8896de8c1ae85964b8bb82fdf Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Fri, 12 May 2023 18:00:13 +0800 Subject: [PATCH 3167/4345] net: hns3: fix reset delay time to avoid configuration timeout [ Upstream commit 814d0c786068e858d889ada3153bff82f64223ad ] Currently the hns3 vf function reset delays 5000ms before vf rebuild process. In product applications, this delay is too long for application configurations and causes configuration timeout. According to the tests, 500ms delay is enough for reset process except PF FLR. So this patch modifies delay to 500ms in these scenarios. Fixes: 6988eb2a9b77 ("net: hns3: Add support to reset the enet/ring mgmt layer") Signed-off-by: Jie Wang Signed-off-by: Hao Lan Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index f7f3e4bbc477..7d05915c35e3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1772,7 +1772,10 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) * might happen in case reset assertion was made by PF. Yes, this also * means we might end up waiting bit more even for VF reset. */ - msleep(5000); + if (hdev->reset_type == HNAE3_VF_FULL_RESET) + msleep(5000); + else + msleep(500); return 0; } From f9982db735a8495eee14267cf193c806b957e942 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Wed, 8 Mar 2023 12:55:14 +0000 Subject: [PATCH 3168/4345] media: netup_unidvb: fix use-after-free at del_timer() [ Upstream commit 0f5bb36bf9b39a2a96e730bf4455095b50713f63 ] When Universal DVB card is detaching, netup_unidvb_dma_fini() uses del_timer() to stop dma->timeout timer. But when timer handler netup_unidvb_dma_timeout() is running, del_timer() could not stop it. As a result, the use-after-free bug could happen. The process is shown below: (cleanup routine) | (timer routine) | mod_timer(&dev->tx_sim_timer, ..) netup_unidvb_finidev() | (wait a time) netup_unidvb_dma_fini() | netup_unidvb_dma_timeout() del_timer(&dma->timeout); | | ndev->pci_dev->dev //USE Fix by changing del_timer() to del_timer_sync(). Link: https://lore.kernel.org/linux-media/20230308125514.4208-1-duoming@zju.edu.cn Fixes: 52b1eaf4c59a ("[media] netup_unidvb: NetUP Universal DVB-S/S2/T/T2/C PCI-E card driver") Signed-off-by: Duoming Zhou Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/pci/netup_unidvb/netup_unidvb_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index 77bae1468551..a71814e2772d 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -697,7 +697,7 @@ static void netup_unidvb_dma_fini(struct netup_unidvb_dev *ndev, int num) netup_unidvb_dma_enable(dma, 0); msleep(50); cancel_work_sync(&dma->work); - del_timer(&dma->timeout); + del_timer_sync(&dma->timeout); } static int netup_unidvb_dma_setup(struct netup_unidvb_dev *ndev) From ce97bb60a6e40b365a8c188b4345fbadd5d03958 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 14 May 2023 15:51:48 -0400 Subject: [PATCH 3169/4345] SUNRPC: Fix trace_svc_register() call site [ Upstream commit 07a27305938559fb35f7a46fb90a5e37728bdee6 ] The trace event recorded incorrect values for the registered family, protocol, and port because the arguments are in the wrong order. Fixes: b4af59328c25 ("SUNRPC: Trace server-side rpcbind registration events") Signed-off-by: Chuck Lever Signed-off-by: Sasha Levin --- net/sunrpc/svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index af657a482ad2..495ebe7fad6d 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -995,7 +995,7 @@ static int __svc_register(struct net *net, const char *progname, #endif } - trace_svc_register(progname, version, protocol, port, family, error); + trace_svc_register(progname, version, family, protocol, port, error); return error; } From 01cdda0d27d7c6587e51739a0d6f80d1535b2e4e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 17 Apr 2023 23:04:11 +0200 Subject: [PATCH 3170/4345] drm/exynos: fix g2d_open/close helper function definitions [ Upstream commit 2ef0785b30bd6549ddbc124979f1b6596e065ae2 ] The empty stub functions are defined as global functions, which causes a warning because of missing prototypes: drivers/gpu/drm/exynos/exynos_drm_g2d.h:37:5: error: no previous prototype for 'g2d_open' drivers/gpu/drm/exynos/exynos_drm_g2d.h:42:5: error: no previous prototype for 'g2d_close' Mark them as 'static inline' to avoid the warning and to make them behave as intended. Fixes: eb4d9796fa34 ("drm/exynos: g2d: Convert to driver component API") Signed-off-by: Arnd Bergmann Reviewed-by: Andi Shyti Signed-off-by: Inki Dae Signed-off-by: Sasha Levin --- drivers/gpu/drm/exynos/exynos_drm_g2d.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.h b/drivers/gpu/drm/exynos/exynos_drm_g2d.h index 74ea3c26dead..1a5ae781b56c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.h +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.h @@ -34,11 +34,11 @@ static inline int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data, return -ENODEV; } -int g2d_open(struct drm_device *drm_dev, struct drm_file *file) +static inline int g2d_open(struct drm_device *drm_dev, struct drm_file *file) { return 0; } -void g2d_close(struct drm_device *drm_dev, struct drm_file *file) +static inline void g2d_close(struct drm_device *drm_dev, struct drm_file *file) { } #endif From 02b20e0bc0c2628539e9e518dc342787c3332de2 Mon Sep 17 00:00:00 2001 From: Dong Chenchen Date: Thu, 11 May 2023 20:54:40 +0800 Subject: [PATCH 3171/4345] net: nsh: Use correct mac_offset to unwind gso skb in nsh_gso_segment() [ Upstream commit c83b49383b595be50647f0c764a48c78b5f3c4f8 ] As the call trace shows, skb_panic was caused by wrong skb->mac_header in nsh_gso_segment(): invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 3 PID: 2737 Comm: syz Not tainted 6.3.0-next-20230505 #1 RIP: 0010:skb_panic+0xda/0xe0 call Trace: skb_push+0x91/0xa0 nsh_gso_segment+0x4f3/0x570 skb_mac_gso_segment+0x19e/0x270 __skb_gso_segment+0x1e8/0x3c0 validate_xmit_skb+0x452/0x890 validate_xmit_skb_list+0x99/0xd0 sch_direct_xmit+0x294/0x7c0 __dev_queue_xmit+0x16f0/0x1d70 packet_xmit+0x185/0x210 packet_snd+0xc15/0x1170 packet_sendmsg+0x7b/0xa0 sock_sendmsg+0x14f/0x160 The root cause is: nsh_gso_segment() use skb->network_header - nhoff to reset mac_header in skb_gso_error_unwind() if inner-layer protocol gso fails. However, skb->network_header may be reset by inner-layer protocol gso function e.g. mpls_gso_segment. skb->mac_header reset by the inaccurate network_header will be larger than skb headroom. nsh_gso_segment nhoff = skb->network_header - skb->mac_header; __skb_pull(skb,nsh_len) skb_mac_gso_segment mpls_gso_segment skb_reset_network_header(skb);//skb->network_header+=nsh_len return -EINVAL; skb_gso_error_unwind skb_push(skb, nsh_len); skb->mac_header = skb->network_header - nhoff; // skb->mac_header > skb->headroom, cause skb_push panic Use correct mac_offset to restore mac_header and get rid of nhoff. Fixes: c411ed854584 ("nsh: add GSO support") Reported-by: syzbot+632b5d9964208bfef8c0@syzkaller.appspotmail.com Suggested-by: Eric Dumazet Signed-off-by: Dong Chenchen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/nsh/nsh.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index e9ca007718b7..0f23e5e8e03e 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -77,13 +77,12 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; unsigned int nsh_len, mac_len; __be16 proto; - int nhoff; skb_reset_network_header(skb); - nhoff = skb->network_header - skb->mac_header; mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -108,15 +107,14 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, segs = skb_mac_gso_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, htons(ETH_P_NSH), nsh_len, - skb->network_header - nhoff, - mac_len); + mac_offset, mac_len); goto out; } for (skb = segs; skb; skb = skb->next) { skb->protocol = htons(ETH_P_NSH); __skb_push(skb, nsh_len); - skb_set_mac_header(skb, -nhoff); + skb->mac_header = mac_offset; skb->network_header = skb->mac_header + mac_len; skb->mac_len = mac_len; } From 76ea144a35ba434c641ee1b52579d10415567172 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 29 Nov 2020 10:32:43 -0800 Subject: [PATCH 3172/4345] net/tipc: fix tipc header files for kernel-doc [ Upstream commit ff10527e89826aaf76480ee47e6fd05213189963 ] Fix tipc header files for adding to the networking docbook. Remove some uses of "/**" that were not kernel-doc notation. Fix some source formatting to eliminate Sphinx warnings. Add missing struct member and function argument kernel-doc descriptions. Correct the description of a couple of struct members that were marked as "(FIXME)". Documentation/networking/tipc:18: ../net/tipc/name_table.h:65: WARNING: Unexpected indentation. Documentation/networking/tipc:18: ../net/tipc/name_table.h:66: WARNING: Block quote ends without a blank line; unexpected unindent. ../net/tipc/bearer.h:128: warning: Function parameter or member 'min_win' not described in 'tipc_media' ../net/tipc/bearer.h:128: warning: Function parameter or member 'max_win' not described in 'tipc_media' ../net/tipc/bearer.h:171: warning: Function parameter or member 'min_win' not described in 'tipc_bearer' ../net/tipc/bearer.h:171: warning: Function parameter or member 'max_win' not described in 'tipc_bearer' ../net/tipc/bearer.h:171: warning: Function parameter or member 'disc' not described in 'tipc_bearer' ../net/tipc/bearer.h:171: warning: Function parameter or member 'up' not described in 'tipc_bearer' ../net/tipc/bearer.h:171: warning: Function parameter or member 'refcnt' not described in 'tipc_bearer' ../net/tipc/name_distr.h:68: warning: Function parameter or member 'port' not described in 'distr_item' ../net/tipc/name_table.h:111: warning: Function parameter or member 'services' not described in 'name_table' ../net/tipc/name_table.h:111: warning: Function parameter or member 'cluster_scope_lock' not described in 'name_table' ../net/tipc/name_table.h:111: warning: Function parameter or member 'rc_dests' not described in 'name_table' ../net/tipc/name_table.h:111: warning: Function parameter or member 'snd_nxt' not described in 'name_table' ../net/tipc/subscr.h:67: warning: Function parameter or member 'kref' not described in 'tipc_subscription' ../net/tipc/subscr.h:67: warning: Function parameter or member 'net' not described in 'tipc_subscription' ../net/tipc/subscr.h:67: warning: Function parameter or member 'service_list' not described in 'tipc_subscription' ../net/tipc/subscr.h:67: warning: Function parameter or member 'conid' not described in 'tipc_subscription' ../net/tipc/subscr.h:67: warning: Function parameter or member 'inactive' not described in 'tipc_subscription' ../net/tipc/subscr.h:67: warning: Function parameter or member 'lock' not described in 'tipc_subscription' Signed-off-by: Randy Dunlap Signed-off-by: Jakub Kicinski Stable-dep-of: 56077b56cd3f ("tipc: do not update mtu if msg_max is too small in mtu negotiation") Signed-off-by: Sasha Levin --- net/tipc/bearer.h | 10 +++++++--- net/tipc/crypto.h | 6 +++--- net/tipc/name_distr.h | 2 +- net/tipc/name_table.h | 9 ++++++--- net/tipc/subscr.h | 11 +++++++---- 5 files changed, 24 insertions(+), 14 deletions(-) diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index bc0023119da2..6bf4550aa1ac 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -93,7 +93,8 @@ struct tipc_bearer; * @raw2addr: convert from raw addr format to media addr format * @priority: default link (and bearer) priority * @tolerance: default time (in ms) before declaring link failure - * @window: default window (in packets) before declaring link congestion + * @min_win: minimum window (in packets) before declaring link congestion + * @max_win: maximum window (in packets) before declaring link congestion * @mtu: max packet size bearer can support for media type not dependent on * underlying device MTU * @type_id: TIPC media identifier @@ -138,12 +139,15 @@ struct tipc_media { * @pt: packet type for bearer * @rcu: rcu struct for tipc_bearer * @priority: default link priority for bearer - * @window: default window size for bearer + * @min_win: minimum window (in packets) before declaring link congestion + * @max_win: maximum window (in packets) before declaring link congestion * @tolerance: default link tolerance for bearer * @domain: network domain to which links can be established * @identity: array index of this bearer within TIPC bearer array - * @link_req: ptr to (optional) structure making periodic link setup requests + * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer + * @up: bearer up flag (bit 0) + * @refcnt: tipc_bearer reference counter * * Note: media-specific code is responsible for initialization of the fields * indicated below when a bearer is enabled; TIPC's generic bearer code takes diff --git a/net/tipc/crypto.h b/net/tipc/crypto.h index e71193bd5e36..ce7d4cc8a9e0 100644 --- a/net/tipc/crypto.h +++ b/net/tipc/crypto.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/** +/* * net/tipc/crypto.h: Include file for TIPC crypto * * Copyright (c) 2019, Ericsson AB @@ -53,7 +53,7 @@ #define TIPC_AES_GCM_IV_SIZE 12 #define TIPC_AES_GCM_TAG_SIZE 16 -/** +/* * TIPC crypto modes: * - CLUSTER_KEY: * One single key is used for both TX & RX in all nodes in the cluster. @@ -69,7 +69,7 @@ enum { extern int sysctl_tipc_max_tfms __read_mostly; extern int sysctl_tipc_key_exchange_enabled __read_mostly; -/** +/* * TIPC encryption message format: * * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h index 092323158f06..e231e6964d61 100644 --- a/net/tipc/name_distr.h +++ b/net/tipc/name_distr.h @@ -46,7 +46,7 @@ * @type: name sequence type * @lower: name sequence lower bound * @upper: name sequence upper bound - * @ref: publishing port reference + * @port: publishing port reference * @key: publication key * * ===> All fields are stored in network byte order. <=== diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 8064e1986e2c..5a82a01369d6 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -60,8 +60,8 @@ struct tipc_group; * @key: publication key, unique across the cluster * @id: publication id * @binding_node: all publications from the same node which bound this one - * - Remote publications: in node->publ_list - * Used by node/name distr to withdraw publications when node is lost + * - Remote publications: in node->publ_list; + * Used by node/name distr to withdraw publications when node is lost * - Local/node scope publications: in name_table->node_scope list * - Local/cluster scope publications: in name_table->cluster_scope list * @binding_sock: all publications from the same socket which bound this one @@ -92,13 +92,16 @@ struct publication { /** * struct name_table - table containing all existing port name publications - * @seq_hlist: name sequence hash lists + * @services: name sequence hash lists * @node_scope: all local publications with node scope * - used by name_distr during re-init of name table * @cluster_scope: all local publications with cluster scope * - used by name_distr to send bulk updates to new nodes * - used by name_distr during re-init of name table + * @cluster_scope_lock: lock for accessing @cluster_scope * @local_publ_count: number of publications issued by this node + * @rc_dests: destination node counter + * @snd_nxt: next sequence number to be used */ struct name_table { struct hlist_head services[TIPC_NAMETBL_SIZE]; diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index 6ebbec1bedd1..63bdce9358fe 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -47,12 +47,15 @@ struct tipc_conn; /** * struct tipc_subscription - TIPC network topology subscription object - * @subscriber: pointer to its subscriber - * @seq: name sequence associated with subscription + * @kref: reference count for this subscription + * @net: network namespace associated with subscription * @timer: timer governing subscription duration (optional) - * @nameseq_list: adjacent subscriptions in name sequence's subscription list + * @service_list: adjacent subscriptions in name sequence's subscription list * @sub_list: adjacent subscriptions in subscriber's subscription list * @evt: template for events generated by subscription + * @conid: connection identifier of topology server + * @inactive: true if this subscription is inactive + * @lock: serialize up/down and timer events */ struct tipc_subscription { struct kref kref; @@ -63,7 +66,7 @@ struct tipc_subscription { struct tipc_event evt; int conid; bool inactive; - spinlock_t lock; /* serialize up/down and timer events */ + spinlock_t lock; }; struct tipc_subscription *tipc_sub_subscribe(struct net *net, From 097ea78d8ccaf789eeeb154fdfb6afbd274a2a87 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 14 May 2023 15:52:27 -0400 Subject: [PATCH 3173/4345] tipc: add tipc_bearer_min_mtu to calculate min mtu [ Upstream commit 3ae6d66b605be604644d4bb5708a7ffd9cf1abe8 ] As different media may requires different min mtu, and even the same media with different net family requires different min mtu, add tipc_bearer_min_mtu() to calculate min mtu accordingly. This API will be used to check the new mtu when doing the link mtu negotiation in the next patch. Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller Stable-dep-of: 56077b56cd3f ("tipc: do not update mtu if msg_max is too small in mtu negotiation") Signed-off-by: Sasha Levin --- net/tipc/bearer.c | 13 +++++++++++++ net/tipc/bearer.h | 3 +++ net/tipc/udp_media.c | 5 +++-- 3 files changed, 19 insertions(+), 2 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 72c31ef985eb..c6a9b3446ff8 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -525,6 +525,19 @@ int tipc_bearer_mtu(struct net *net, u32 bearer_id) return mtu; } +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id) +{ + int mtu = TIPC_MIN_BEARER_MTU; + struct tipc_bearer *b; + + rcu_read_lock(); + b = bearer_get(net, bearer_id); + if (b) + mtu += b->encap_hlen; + rcu_read_unlock(); + return mtu; +} + /* tipc_bearer_xmit_skb - sends buffer to destination over bearer */ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 6bf4550aa1ac..711a50f44993 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -146,6 +146,7 @@ struct tipc_media { * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer + * @encap_hlen: encap headers length * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * @@ -170,6 +171,7 @@ struct tipc_bearer { u32 identity; struct tipc_discoverer *disc; char net_plane; + u16 encap_hlen; unsigned long up; refcount_t refcnt; }; @@ -232,6 +234,7 @@ int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index a23628108272..3e47501f024f 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -730,8 +730,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = local.ipv4.s_addr; udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; - if (tipc_mtu_bad(dev, sizeof(struct iphdr) + - sizeof(struct udphdr))) { + b->encap_hlen = sizeof(struct iphdr) + sizeof(struct udphdr); + if (tipc_mtu_bad(dev, b->encap_hlen)) { err = -EINVAL; goto err; } @@ -752,6 +752,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, else udp_conf.local_ip6 = local.ipv6; ub->ifindex = dev->ifindex; + b->encap_hlen = sizeof(struct ipv6hdr) + sizeof(struct udphdr); b->mtu = 1280; #endif } else { From 2bd4ff4ffb92113f8acd04dbaed83269172c24b4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 14 May 2023 15:52:28 -0400 Subject: [PATCH 3174/4345] tipc: do not update mtu if msg_max is too small in mtu negotiation [ Upstream commit 56077b56cd3fb78e1c8619e29581ba25a5c55e86 ] When doing link mtu negotiation, a malicious peer may send Activate msg with a very small mtu, e.g. 4 in Shuang's testing, without checking for the minimum mtu, l->mtu will be set to 4 in tipc_link_proto_rcv(), then n->links[bearer_id].mtu is set to 4294967228, which is a overflow of '4 - INT_H_SIZE - EMSG_OVERHEAD' in tipc_link_mss(). With tipc_link.mtu = 4, tipc_link_xmit() kept printing the warning: tipc: Too large msg, purging xmit list 1 5 0 40 4! tipc: Too large msg, purging xmit list 1 15 0 60 4! And with tipc_link_entry.mtu 4294967228, a huge skb was allocated in named_distribute(), and when purging it in tipc_link_xmit(), a crash was even caused: general protection fault, probably for non-canonical address 0x2100001011000dd: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 0 Comm: swapper/0 Kdump: loaded Not tainted 6.3.0.neta #19 RIP: 0010:kfree_skb_list_reason+0x7e/0x1f0 Call Trace: skb_release_data+0xf9/0x1d0 kfree_skb_reason+0x40/0x100 tipc_link_xmit+0x57a/0x740 [tipc] tipc_node_xmit+0x16c/0x5c0 [tipc] tipc_named_node_up+0x27f/0x2c0 [tipc] tipc_node_write_unlock+0x149/0x170 [tipc] tipc_rcv+0x608/0x740 [tipc] tipc_udp_recv+0xdc/0x1f0 [tipc] udp_queue_rcv_one_skb+0x33e/0x620 udp_unicast_rcv_skb.isra.72+0x75/0x90 __udp4_lib_rcv+0x56d/0xc20 ip_protocol_deliver_rcu+0x100/0x2d0 This patch fixes it by checking the new mtu against tipc_bearer_min_mtu(), and not updating mtu if it is too small. Fixes: ed193ece2649 ("tipc: simplify link mtu negotiation") Reported-by: Shuang Li Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/tipc/link.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index c1e56d1f21b3..dbb1bc722ba9 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2164,7 +2164,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; - u32 dlen = msg_data_sz(hdr), glen = 0; + u32 dlen = msg_data_sz(hdr), glen = 0, msg_max; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); @@ -2203,6 +2203,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG: + msg_max = msg_max_pkt(hdr); + if (msg_max < tipc_bearer_min_mtu(l->net, l->bearer_id)) + break; /* Complete own link name with peer's interface name */ if_name = strrchr(l->name, ':') + 1; if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) @@ -2247,8 +2250,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, l->peer_session = msg_session(hdr); l->in_session = true; l->peer_bearer_id = msg_bearer_id(hdr); - if (l->mtu > msg_max_pkt(hdr)) - l->mtu = msg_max_pkt(hdr); + if (l->mtu > msg_max) + l->mtu = msg_max; break; case STATE_MSG: From 2937127d24ccb83e57ee5dbcd0309995f0fa5386 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 14 May 2023 15:52:29 -0400 Subject: [PATCH 3175/4345] tipc: check the bearer min mtu properly when setting it by netlink [ Upstream commit 35a089b5d793d2bfd2cc7cfa6104545184de2ce7 ] Checking the bearer min mtu with tipc_udp_mtu_bad() only works for IPv4 UDP bearer, and IPv6 UDP bearer has a different value for the min mtu. This patch checks with encap_hlen + TIPC_MIN_BEARER_MTU for min mtu, which works for both IPv4 and IPv6 UDP bearer. Note that tipc_udp_mtu_bad() is still used to check media min mtu in __tipc_nl_media_set(), as m->mtu currently is only used by the IPv4 UDP bearer as its default mtu value. Fixes: 682cd3cf946b ("tipc: confgiure and apply UDP bearer MTU on running links") Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/tipc/bearer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index c6a9b3446ff8..91e678fa3feb 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1135,8 +1135,8 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP - if (tipc_udp_mtu_bad(nla_get_u32 - (props[TIPC_NLA_PROP_MTU]))) { + if (nla_get_u32(props[TIPC_NLA_PROP_MTU]) < + b->encap_hlen + TIPC_MIN_BEARER_MTU) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; From e92727ed9e8b6798efc1e7ae44bbe7c44c453670 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 4 May 2023 16:07:27 -0700 Subject: [PATCH 3176/4345] net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop() [ Upstream commit 93e0401e0fc0c54b0ac05b687cd135c2ac38187c ] The call to phy_stop() races with the later call to phy_disconnect(), resulting in concurrent phy_suspend() calls being run from different CPUs. The final call to phy_disconnect() ensures that the PHY is stopped and suspended, too. Fixes: c96e731c93ff ("net: bcmgenet: connect and disconnect from the PHY state machine") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 7667cbb5adfd..20b161620fee 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3412,7 +3412,6 @@ static void bcmgenet_netif_stop(struct net_device *dev) /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); - phy_stop(dev->phydev); bcmgenet_disable_rx_napi(priv); bcmgenet_intr_disable(priv); From 43f6575004e0bbe0acc5d7a1955f326b22f38121 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sun, 14 May 2023 19:56:07 -0700 Subject: [PATCH 3177/4345] net: bcmgenet: Restore phy_stop() depending upon suspend/close [ Upstream commit 225c657945c4a6307741cb3cc89467eadcc26e9b ] Removing the phy_stop() from bcmgenet_netif_stop() ended up causing warnings from the PHY library that phy_start() is called from the RUNNING state since we are no longer stopping the PHY state machine during bcmgenet_suspend(). Restore the call to phy_stop() but make it conditional on being called from the close or suspend path. Fixes: c96e731c93ff ("net: bcmgenet: connect and disconnect from the PHY state machine") Fixes: 93e0401e0fc0 ("net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop()") Signed-off-by: Florian Fainelli Reviewed-by: Pavan Chebbi Link: https://lore.kernel.org/r/20230515025608.2587012-1-f.fainelli@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 20b161620fee..145488449f13 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3397,7 +3397,7 @@ err_clk_disable: return ret; } -static void bcmgenet_netif_stop(struct net_device *dev) +static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -3412,6 +3412,8 @@ static void bcmgenet_netif_stop(struct net_device *dev) /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); + if (stop_phy) + phy_stop(dev->phydev); bcmgenet_disable_rx_napi(priv); bcmgenet_intr_disable(priv); @@ -3437,7 +3439,7 @@ static int bcmgenet_close(struct net_device *dev) netif_dbg(priv, ifdown, dev, "bcmgenet_close\n"); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, false); /* Really kill the PHY state machine and disconnect from it */ phy_disconnect(dev->phydev); @@ -4239,7 +4241,7 @@ static int bcmgenet_suspend(struct device *d) netif_device_detach(dev); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, true); if (!device_may_wakeup(d)) phy_suspend(dev->phydev); From f9337a41772dbe6d00e2b686c4f4853e4f570e46 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 May 2023 16:45:01 +0300 Subject: [PATCH 3178/4345] wifi: mac80211: fix min center freq offset tracing [ Upstream commit 248e4776514bf70236e6b1a54c65aa5324c8b1eb ] We need to set the correct trace variable, otherwise we're overwriting something else instead and the right one that we print later is not initialized. Fixes: b6011960f392 ("mac80211: handle channel frequency offset") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230504134511.828474-2-gregory.greenman@intel.com Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 89723907a094..5ddaa7c82477 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -67,7 +67,7 @@ __entry->min_freq_offset = (c)->chan ? (c)->chan->freq_offset : 0; \ __entry->min_chan_width = (c)->width; \ __entry->min_center_freq1 = (c)->center_freq1; \ - __entry->freq1_offset = (c)->freq1_offset; \ + __entry->min_freq1_offset = (c)->freq1_offset; \ __entry->min_center_freq2 = (c)->center_freq2; #define MIN_CHANDEF_PR_FMT " min_control:%d.%03d MHz min_width:%d min_center: %d.%03d/%d MHz" #define MIN_CHANDEF_PR_ARG __entry->min_control_freq, __entry->min_freq_offset, \ From d0d39bed9e95f27a246be91c5929254ac043ed30 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:53 +0300 Subject: [PATCH 3179/4345] wifi: iwlwifi: mvm: don't trust firmware n_channels [ Upstream commit 682b6dc29d98e857e6ca4bbc077c7dc2899b7473 ] If the firmware sends us a corrupted MCC response with n_channels much larger than the command response can be, we might copy far too much (uninitialized) memory and even crash if the n_channels is large enough to make it run out of the one page allocated for the FW response. Fix that by checking the lengths. Doing a < comparison would be sufficient, but the firmware should be doing it correctly, so check more strictly. Fixes: dcaf9f5ecb6f ("iwlwifi: mvm: add MCC update FW API") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.d7b233139eb4.I51fd319df8e9d41881fc8450e83d78049518a79a@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/mvm/nvm.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 60296a754af2..34be3f75c2e9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -502,6 +502,11 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, struct iwl_mcc_update_resp *mcc_resp = (void *)pkt->data; n_channels = __le32_to_cpu(mcc_resp->n_channels); + if (iwl_rx_packet_payload_len(pkt) != + struct_size(mcc_resp, channels, n_channels)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } resp_len = sizeof(struct iwl_mcc_update_resp) + n_channels * sizeof(__le32); resp_cp = kmemdup(mcc_resp, resp_len, GFP_KERNEL); @@ -513,6 +518,11 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, struct iwl_mcc_update_resp_v3 *mcc_resp_v3 = (void *)pkt->data; n_channels = __le32_to_cpu(mcc_resp_v3->n_channels); + if (iwl_rx_packet_payload_len(pkt) != + struct_size(mcc_resp_v3, channels, n_channels)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } resp_len = sizeof(struct iwl_mcc_update_resp) + n_channels * sizeof(__le32); resp_cp = kzalloc(resp_len, GFP_KERNEL); From 81139679f4d28c5c2754fd0401f64720fbb1544b Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 15 May 2023 10:20:41 -0700 Subject: [PATCH 3180/4345] scsi: storvsc: Don't pass unused PFNs to Hyper-V host [ Upstream commit 4e81a6cba517cb33584308a331f14f5e3fec369b ] In a SCSI request, storvsc pre-allocates space for up to MAX_PAGE_BUFFER_COUNT physical frame numbers to be passed to Hyper-V. If the size of the I/O request requires more PFNs, a separate memory area of exactly the correct size is dynamically allocated. But when the pre-allocated area is used, current code always passes MAX_PAGE_BUFFER_COUNT PFNs to Hyper-V, even if fewer are needed. While this doesn't break anything because the additional PFNs are always zero, more bytes than necessary are copied into the VMBus channel ring buffer. This takes CPU cycles and wastes space in the ring buffer. For a typical 4 Kbyte I/O that requires only a single PFN, 248 unnecessary bytes are copied. Fix this by setting the payload_sz based on the actual number of PFNs required, not the size of the pre-allocated space. Reported-by: John Starks Fixes: 8f43710543ef ("scsi: storvsc: Support PAGE_SIZE larger than 4K") Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1684171241-16209-1-git-send-email-mikelley@microsoft.com Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/storvsc_drv.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index e38aebcabb26..70b4868fe2f7 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1756,7 +1756,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) length = scsi_bufflen(scmnd); payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb; - payload_sz = sizeof(cmd_request->mpb); + payload_sz = 0; if (sg_count) { unsigned int hvpgoff = 0; @@ -1764,10 +1764,10 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) unsigned int hvpg_count = HVPFN_UP(offset_in_hvpg + length); u64 hvpfn; - if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { + payload_sz = (hvpg_count * sizeof(u64) + + sizeof(struct vmbus_packet_mpb_array)); - payload_sz = (hvpg_count * sizeof(u64) + - sizeof(struct vmbus_packet_mpb_array)); + if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { payload = kzalloc(payload_sz, GFP_ATOMIC); if (!payload) return SCSI_MLQUEUE_DEVICE_BUSY; From dc61f7582cc92d547d02e141cd66f5d1f4ed8012 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 15 May 2023 21:09:11 +0200 Subject: [PATCH 3181/4345] cassini: Fix a memory leak in the error handling path of cas_init_one() [ Upstream commit 412cd77a2c24b191c65ea53025222418db09817c ] cas_saturn_firmware_init() allocates some memory using vmalloc(). This memory is freed in the .remove() function but not it the error handling path of the probe. Add the missing vfree() to avoid a memory leak, should an error occur. Fixes: fcaa40669cd7 ("cassini: use request_firmware") Signed-off-by: Christophe JAILLET Reviewed-by: Pavan Chebbi Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/sun/cassini.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 9ff894ba8d3e..d245f6e21e8c 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -5122,6 +5122,8 @@ err_out_iounmap: cas_shutdown(cp); mutex_unlock(&cp->pm_mutex); + vfree(cp->fw_data); + pci_iounmap(pdev, cp->regs); From 562ec162b04a92986af89dd07586e4fb2a6bb15f Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Tue, 16 May 2023 10:41:46 -0700 Subject: [PATCH 3182/4345] igb: fix bit_shift to be in [1..8] range [ Upstream commit 60d758659f1fb49e0d5b6ac2691ede8c0958795b ] In igb_hash_mc_addr() the expression: "mc_addr[4] >> 8 - bit_shift", right shifting "mc_addr[4]" shift by more than 7 bits always yields zero, so hash becomes not so different. Add initialization with bit_shift = 1 and add a loop condition to ensure bit_shift will be always in [1..8] range. Fixes: 9d5c824399de ("igb: PCI-Express 82575 Gigabit Ethernet driver") Signed-off-by: Aleksandr Loktionov Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igb/e1000_mac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index fd8eb2f9ab9d..57e813405b31 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -426,7 +426,7 @@ void igb_mta_set(struct e1000_hw *hw, u32 hash_value) static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) { u32 hash_value, hash_mask; - u8 bit_shift = 0; + u8 bit_shift = 1; /* Register count multiplied by bits per register */ hash_mask = (hw->mac.mta_reg_count * 32) - 1; @@ -434,7 +434,7 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) /* For a mc_filter_type of 0, bit_shift is the number of left-shifts * where 0xFF would still fall within the hash mask. */ - while (hash_mask >> bit_shift != 0xFF) + while (hash_mask >> bit_shift != 0xFF && bit_shift < 4) bit_shift++; /* The portion of the address that is used for the hash table From 6cfe6f51856b0ef65aabb4423ade43c42ae9d930 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2023 14:23:42 +0000 Subject: [PATCH 3183/4345] vlan: fix a potential uninit-value in vlan_dev_hard_start_xmit() [ Upstream commit dacab578c7c6cd06c50c89dfa36b0e0f10decd4e ] syzbot triggered the following splat [1], sending an empty message through pppoe_sendmsg(). When VLAN_FLAG_REORDER_HDR flag is set, vlan_dev_hard_header() does not push extra bytes for the VLAN header, because vlan is offloaded. Unfortunately vlan_dev_hard_start_xmit() first reads veth->h_vlan_proto before testing (vlan->flags & VLAN_FLAG_REORDER_HDR). We need to swap the two conditions. [1] BUG: KMSAN: uninit-value in vlan_dev_hard_start_xmit+0x171/0x7f0 net/8021q/vlan_dev.c:111 vlan_dev_hard_start_xmit+0x171/0x7f0 net/8021q/vlan_dev.c:111 __netdev_start_xmit include/linux/netdevice.h:4883 [inline] netdev_start_xmit include/linux/netdevice.h:4897 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x253/0xa20 net/core/dev.c:3596 __dev_queue_xmit+0x3c7f/0x5ac0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3053 [inline] pppoe_sendmsg+0xa93/0xb80 drivers/net/ppp/pppoe.c:900 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0xa24/0xe40 net/socket.c:2501 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2555 __sys_sendmmsg+0x411/0xa50 net/socket.c:2641 __do_sys_sendmmsg net/socket.c:2670 [inline] __se_sys_sendmmsg net/socket.c:2667 [inline] __x64_sys_sendmmsg+0xbc/0x120 net/socket.c:2667 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook+0x12d/0xb60 mm/slab.h:774 slab_alloc_node mm/slub.c:3452 [inline] kmem_cache_alloc_node+0x543/0xab0 mm/slub.c:3497 kmalloc_reserve+0x148/0x470 net/core/skbuff.c:520 __alloc_skb+0x3a7/0x850 net/core/skbuff.c:606 alloc_skb include/linux/skbuff.h:1277 [inline] sock_wmalloc+0xfe/0x1a0 net/core/sock.c:2583 pppoe_sendmsg+0x3af/0xb80 drivers/net/ppp/pppoe.c:867 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0xa24/0xe40 net/socket.c:2501 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2555 __sys_sendmmsg+0x411/0xa50 net/socket.c:2641 __do_sys_sendmmsg net/socket.c:2670 [inline] __se_sys_sendmmsg net/socket.c:2667 [inline] __x64_sys_sendmmsg+0xbc/0x120 net/socket.c:2667 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd CPU: 0 PID: 29770 Comm: syz-executor.0 Not tainted 6.3.0-rc6-syzkaller-gc478e5b17829 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/8021q/vlan_dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 929f85c6cf11..8edac9307868 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -108,8 +108,8 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... */ - if (veth->h_vlan_proto != vlan->vlan_proto || - vlan->flags & VLAN_FLAG_REORDER_HDR) { + if (vlan->flags & VLAN_FLAG_REORDER_HDR || + veth->h_vlan_proto != vlan->vlan_proto) { u16 vlan_tci; vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); From 3fa13203b6d90cc3a33af47b058739f92ab82eef Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 11 May 2023 22:39:30 +0200 Subject: [PATCH 3184/4345] netfilter: nft_set_rbtree: fix null deref on element insertion [ Upstream commit 61ae320a29b0540c16931816299eb86bf2b66c08 ] There is no guarantee that rb_prev() will not return NULL in nft_rbtree_gc_elem(): general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] nft_add_set_elem+0x14b0/0x2990 nf_tables_newsetelem+0x528/0xb30 Furthermore, there is a possible use-after-free while iterating, 'node' can be free'd so we need to cache the next value to use. Fixes: c9e6978e2725 ("netfilter: nft_set_rbtree: Switch to node list walk for overlap detection") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nft_set_rbtree.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 4b9a499fe8f4..1ffb24f4c74c 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -220,7 +220,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); - struct nft_rbtree_elem *rbe_prev; + struct nft_rbtree_elem *rbe_prev = NULL; struct nft_set_gc_batch *gcb; gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); @@ -228,17 +228,21 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, return -ENOMEM; /* search for expired end interval coming before this element. */ - do { + while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev)) break; prev = rb_prev(prev); - } while (prev != NULL); + } + + if (rbe_prev) { + rb_erase(&rbe_prev->node, &priv->root); + atomic_dec(&set->nelems); + } - rb_erase(&rbe_prev->node, &priv->root); rb_erase(&rbe->node, &priv->root); - atomic_sub(2, &set->nelems); + atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); nft_set_gc_batch_complete(gcb); @@ -267,7 +271,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_set_ext **ext) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; - struct rb_node *node, *parent, **p, *first = NULL; + struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); int d, err; @@ -306,7 +310,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, * Values stored in the tree are in reversed order, starting from * highest to lowest value. */ - for (node = first; node != NULL; node = rb_next(node)) { + for (node = first; node != NULL; node = next) { + next = rb_next(node); + rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_set_elem_active(&rbe->ext, genmask)) From 3bd6d11e7e630255833d88cb0a95abd483fa8354 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:35 +0200 Subject: [PATCH 3185/4345] bridge: always declare tunnel functions [ Upstream commit 89dcd87ce534a3a7f267cfd58505803006f51301 ] When CONFIG_BRIDGE_VLAN_FILTERING is disabled, two functions are still defined but have no prototype or caller. This causes a W=1 warning for the missing prototypes: net/bridge/br_netlink_tunnel.c:29:6: error: no previous prototype for 'vlan_tunid_inrange' [-Werror=missing-prototypes] net/bridge/br_netlink_tunnel.c:199:5: error: no previous prototype for 'br_vlan_tunnel_info' [-Werror=missing-prototypes] The functions are already contitional on CONFIG_BRIDGE_VLAN_FILTERING, and I coulnd't easily figure out the right set of #ifdefs, so just move the declarations out of the #ifdef to avoid the warning, at a small cost in code size over a more elaborate fix. Fixes: 188c67dd1906 ("net: bridge: vlan options: add support for tunnel id dumping") Fixes: 569da0822808 ("net: bridge: vlan options: add support for tunnel mapping set/del") Signed-off-by: Arnd Bergmann Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230516194625.549249-3-arnd@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/bridge/br_private_tunnel.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h index c54cc26211d7..f6c65dc088d6 100644 --- a/net/bridge/br_private_tunnel.h +++ b/net/bridge/br_private_tunnel.h @@ -27,6 +27,10 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br, int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg); int br_fill_vlan_tunnel_info(struct sk_buff *skb, struct net_bridge_vlan_group *vg); +bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *v_last); +int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, + u16 vid, u32 tun_id, bool *changed); #ifdef CONFIG_BRIDGE_VLAN_FILTERING /* br_vlan_tunnel.c */ @@ -43,10 +47,6 @@ int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan_group *vg); int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan); -bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, - const struct net_bridge_vlan *v_last); -int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, - u16 vid, u32 tun_id, bool *changed); #else static inline int vlan_tunnel_init(struct net_bridge_vlan_group *vg) { From 3b3c6f2d2f1fa8408b8cf050c020815b8a114695 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 12 May 2023 09:58:58 +0200 Subject: [PATCH 3186/4345] ALSA: usb-audio: Add a sample rate workaround for Line6 Pod Go commit 359b4315471181f108723c61612d96e383e56179 upstream. Line6 Pod Go (0e41:424b) requires the similar workaround for the fixed 48k sample rate like other Line6 models. This patch adds the corresponding entry to line6_parse_audio_format_rate_quirk(). Reported-by: John Humlick Cc: Link: https://lore.kernel.org/r/20230512075858.22813-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/format.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/format.c b/sound/usb/format.c index e0fda244a942..29ed301c6f06 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -419,6 +419,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ + case USB_ID(0x0e41, 0x424b): /* Line6 Pod Go */ case USB_ID(0x19f7, 0x0011): /* Rode Rodecaster Pro */ return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); } From 6340e432cf70bf156b19c6f5dd737d940eca02a3 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 1 May 2023 14:22:35 -0400 Subject: [PATCH 3187/4345] USB: usbtmc: Fix direction for 0-length ioctl control messages commit 94d25e9128988c6a1fc9070f6e98215a95795bd8 upstream. The syzbot fuzzer found a problem in the usbtmc driver: When a user submits an ioctl for a 0-length control transfer, the driver does not check that the direction is set to OUT: ------------[ cut here ]------------ usb 3-1: BOGUS control dir, pipe 80000b80 doesn't match bRequestType fd WARNING: CPU: 0 PID: 5100 at drivers/usb/core/urb.c:411 usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 Modules linked in: CPU: 0 PID: 5100 Comm: syz-executor428 Not tainted 6.3.0-syzkaller-12049-g58390c8ce1bd #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023 RIP: 0010:usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 Code: 7c 24 40 e8 1b 13 5c fb 48 8b 7c 24 40 e8 21 1d f0 fe 45 89 e8 44 89 f1 4c 89 e2 48 89 c6 48 c7 c7 e0 b5 fc 8a e8 19 c8 23 fb <0f> 0b e9 9f ee ff ff e8 ed 12 5c fb 0f b6 1d 12 8a 3c 08 31 ff 41 RSP: 0018:ffffc90003d2fb00 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff8880789e9058 RCX: 0000000000000000 RDX: ffff888029593b80 RSI: ffffffff814c1447 RDI: 0000000000000001 RBP: ffff88801ea742f8 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff88802915e528 R13: 00000000000000fd R14: 0000000080000b80 R15: ffff8880222b3100 FS: 0000555556ca63c0(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f9ef4d18150 CR3: 0000000073e5b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: usb_start_wait_urb+0x101/0x4b0 drivers/usb/core/message.c:58 usb_internal_control_msg drivers/usb/core/message.c:102 [inline] usb_control_msg+0x320/0x4a0 drivers/usb/core/message.c:153 usbtmc_ioctl_request drivers/usb/class/usbtmc.c:1954 [inline] usbtmc_ioctl+0x1b3d/0x2840 drivers/usb/class/usbtmc.c:2097 To fix this, we must override the direction in the bRequestType field of the control request structure when the length is 0. Reported-and-tested-by: syzbot+ce77725b89b7bd52425c@syzkaller.appspotmail.com Signed-off-by: Alan Stern Link: https://lore.kernel.org/linux-usb/000000000000716a3705f9adb8ee@google.com/ CC: Link: https://lore.kernel.org/r/ede1ee02-b718-49e7-a44c-51339fec706b@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/usbtmc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 49f59d53b4b2..76ff182427bc 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -1898,6 +1898,8 @@ static int usbtmc_ioctl_request(struct usbtmc_device_data *data, if (request.req.wLength > USBTMC_BUFSIZE) return -EMSGSIZE; + if (request.req.wLength == 0) /* Length-0 requests are never IN */ + request.req.bRequestType &= ~USB_DIR_IN; is_in = request.req.bRequestType & USB_DIR_IN; From 0caed1faf5f68ad8c72230c21a12e17fc00ffd85 Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Fri, 5 May 2023 13:47:59 +0200 Subject: [PATCH 3188/4345] usb-storage: fix deadlock when a scsi command timeouts more than once commit a398d5eac6984316e71474e25b975688f282379b upstream. With faulty usb-storage devices, read/write can timeout, in that case the SCSI layer will abort and re-issue the command. USB storage has no internal timeout, it relies on SCSI layer aborting commands via .eh_abort_handler() for non those responsive devices. After two consecutive timeouts of the same command, SCSI layer calls .eh_device_reset_handler(), without calling .eh_abort_handler() first. With usb-storage, this causes a deadlock: -> .eh_device_reset_handler -> device_reset -> mutex_lock(&(us->dev_mutex)); mutex already by usb_stor_control_thread(), which is waiting for command completion: -> usb_stor_control_thread (mutex taken here) -> usb_stor_invoke_transport -> usb_stor_Bulk_transport -> usb_stor_bulk_srb -> usb_stor_bulk_transfer_sglist -> usb_sg_wait Make sure we cancel any pending command in .eh_device_reset_handler() to avoid this. Signed-off-by: Maxime Bizon Cc: linux-usb@vger.kernel.org Cc: stable Link: https://lore.kernel.org/all/ZEllnjMKT8ulZbJh@sakura/ Reviewed-by: Alan Stern Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230505114759.1189741-1-mbizon@freebox.fr Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/scsiglue.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index e5a971b83e3f..b8e1109f0e0d 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -407,22 +407,25 @@ static DEF_SCSI_QCMD(queuecommand) ***********************************************************************/ /* Command timeout and abort */ -static int command_abort(struct scsi_cmnd *srb) +static int command_abort_matching(struct us_data *us, struct scsi_cmnd *srb_match) { - struct us_data *us = host_to_us(srb->device->host); - - usb_stor_dbg(us, "%s called\n", __func__); - /* * us->srb together with the TIMED_OUT, RESETTING, and ABORTING * bits are protected by the host lock. */ scsi_lock(us_to_host(us)); - /* Is this command still active? */ - if (us->srb != srb) { + /* is there any active pending command to abort ? */ + if (!us->srb) { scsi_unlock(us_to_host(us)); usb_stor_dbg(us, "-- nothing to abort\n"); + return SUCCESS; + } + + /* Does the command match the passed srb if any ? */ + if (srb_match && us->srb != srb_match) { + scsi_unlock(us_to_host(us)); + usb_stor_dbg(us, "-- pending command mismatch\n"); return FAILED; } @@ -445,6 +448,14 @@ static int command_abort(struct scsi_cmnd *srb) return SUCCESS; } +static int command_abort(struct scsi_cmnd *srb) +{ + struct us_data *us = host_to_us(srb->device->host); + + usb_stor_dbg(us, "%s called\n", __func__); + return command_abort_matching(us, srb); +} + /* * This invokes the transport reset mechanism to reset the state of the * device @@ -456,6 +467,9 @@ static int device_reset(struct scsi_cmnd *srb) usb_stor_dbg(us, "%s called\n", __func__); + /* abort any pending command before reset */ + command_abort_matching(us, NULL); + /* lock the device pointers and do the reset */ mutex_lock(&(us->dev_mutex)); result = us->transport_reset(us); From 66070f5b99954793fe1caa568ee3c0a0abccd6c1 Mon Sep 17 00:00:00 2001 From: Weitao Wang Date: Sun, 23 Apr 2023 18:59:52 +0800 Subject: [PATCH 3189/4345] USB: UHCI: adjust zhaoxin UHCI controllers OverCurrent bit value commit dddb342b5b9e482bb213aecc08cbdb201ea4f8da upstream. OverCurrent condition is not standardized in the UHCI spec. Zhaoxin UHCI controllers report OverCurrent bit active off. In order to handle OverCurrent condition correctly, the uhci-hcd driver needs to be told to expect the active-off behavior. Suggested-by: Alan Stern Cc: stable@vger.kernel.org Signed-off-by: Weitao Wang Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230423105952.4526-1-WeitaoWang-oc@zhaoxin.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/uhci-pci.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index 9b88745d247f..3316533b8bc2 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -119,11 +119,13 @@ static int uhci_pci_init(struct usb_hcd *hcd) uhci->rh_numports = uhci_count_ports(hcd); - /* Intel controllers report the OverCurrent bit active on. - * VIA controllers report it active off, so we'll adjust the - * bit value. (It's not standardized in the UHCI spec.) + /* + * Intel controllers report the OverCurrent bit active on. VIA + * and ZHAOXIN controllers report it active off, so we'll adjust + * the bit value. (It's not standardized in the UHCI spec.) */ - if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA) + if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA || + to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_ZHAOXIN) uhci->oc_low = 1; /* HP's server management chip requires a longer port reset delay. */ From e35adb75fda5a6254f7cd232a704dde81206061b Mon Sep 17 00:00:00 2001 From: Udipto Goswami Date: Tue, 9 May 2023 20:18:36 +0530 Subject: [PATCH 3190/4345] usb: dwc3: debugfs: Resume dwc3 before accessing registers commit 614ce6a2ea50068b45339257891e51e639ac9001 upstream. When the dwc3 device is runtime suspended, various required clocks are in disabled state and it is not guaranteed that access to any registers would work. Depending on the SoC glue, a register read could be as benign as returning 0 or be fatal enough to hang the system. In order to prevent such scenarios of fatal errors, make sure to resume dwc3 then allow the function to proceed. Fixes: 72246da40f37 ("usb: Introduce DesignWare USB3 DRD Driver") Cc: stable@vger.kernel.org #3.2: 30332eeefec8: debugfs: regset32: Add Runtime PM support Signed-off-by: Udipto Goswami Reviewed-by: Johan Hovold Tested-by: Johan Hovold Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230509144836.6803-1-quic_ugoswami@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/debugfs.c | 109 +++++++++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index 3ebe3e6c284d..da8b62db49fb 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -327,6 +327,11 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) unsigned int current_mode; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); @@ -345,6 +350,8 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) } spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -390,6 +397,11 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GCTL); @@ -409,6 +421,8 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %08x\n", DWC3_GCTL_PRTCAP(reg)); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -458,6 +472,11 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -488,6 +507,8 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %d\n", reg); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -504,6 +525,7 @@ static ssize_t dwc3_testmode_write(struct file *file, unsigned long flags; u32 testmode = 0; char buf[32]; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -521,10 +543,16 @@ static ssize_t dwc3_testmode_write(struct file *file, else testmode = 0; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); dwc3_gadget_set_test_mode(dwc, testmode); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -543,12 +571,18 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) enum dwc3_link_state state; u32 reg; u8 speed; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { seq_puts(s, "Not available\n"); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return 0; } @@ -561,6 +595,8 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) dwc3_gadget_hs_link_string(state)); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -579,6 +615,7 @@ static ssize_t dwc3_link_state_write(struct file *file, char buf[32]; u32 reg; u8 speed; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -598,10 +635,15 @@ static ssize_t dwc3_link_state_write(struct file *file, else return -EINVAL; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } @@ -611,12 +653,15 @@ static ssize_t dwc3_link_state_write(struct file *file, if (speed < DWC3_DSTS_SUPERSPEED && state != DWC3_LINK_STATE_RECOV) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } dwc3_gadget_set_link_state(dwc, state); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -640,6 +685,11 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; int mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXFIFO); @@ -654,6 +704,8 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -664,6 +716,11 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; int mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXFIFO); @@ -678,6 +735,8 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -687,12 +746,19 @@ static int dwc3_tx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -702,12 +768,19 @@ static int dwc3_rx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -717,12 +790,19 @@ static int dwc3_rx_info_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXINFOQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -732,12 +812,19 @@ static int dwc3_descriptor_fetch_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_DESCFETCHQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -747,12 +834,19 @@ static int dwc3_event_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_EVENTQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -797,6 +891,11 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; int i; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); if (dep->number <= 1) { @@ -826,6 +925,8 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) out: spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -838,6 +939,11 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) u32 lower_32_bits; u32 upper_32_bits; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = DWC3_GDBGLSPMUX_EPSELECT(dep->number); @@ -850,6 +956,8 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) seq_printf(s, "0x%016llx\n", ep_info); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -911,6 +1019,7 @@ void dwc3_debugfs_init(struct dwc3 *dwc) dwc->regset->regs = dwc3_regs; dwc->regset->nregs = ARRAY_SIZE(dwc3_regs); dwc->regset->base = dwc->regs - DWC3_GLOBALS_REGS_START; + dwc->regset->dev = dwc->dev; root = debugfs_create_dir(dev_name(dwc->dev), usb_debug_root); dwc->root = root; From 35e31e1e921c185c48d683bd52438c24916e46f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Konrad=20Gr=C3=A4fe?= Date: Fri, 5 May 2023 16:36:40 +0200 Subject: [PATCH 3191/4345] usb: gadget: u_ether: Fix host MAC address case MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 3c0f4f09c063e143822393d99cb2b19a85451c07 upstream. The CDC-ECM specification [1] requires to send the host MAC address as an uppercase hexadecimal string in chapter "5.4 Ethernet Networking Functional Descriptor": The Unicode character is chosen from the set of values 30h through 39h and 41h through 46h (0-9 and A-F). However, snprintf(.., "%pm", ..) generates a lowercase MAC address string. While most host drivers are tolerant to this, UsbNcm.sys on Windows 10 is not. Instead it uses a different MAC address with all bytes set to zero including and after the first byte containing a lowercase letter. On Windows 11 Microsoft fixed it, but apparently they did not backport the fix. This change fixes the issue by upper-casing the MAC to comply with the specification. [1]: https://www.usb.org/document-library/class-definitions-communication-devices-12, file ECM120.pdf Fixes: bcd4a1c40bee ("usb: gadget: u_ether: construct with default values and add setters/getters") Cc: stable@vger.kernel.org Signed-off-by: Konrad Gräfe Link: https://lore.kernel.org/r/20230505143640.443014-1-k.graefe@gateware.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_ether.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 64ef97ab9274..5e5f699a434f 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "u_ether.h" @@ -974,6 +975,8 @@ int gether_get_host_addr_cdc(struct net_device *net, char *host_addr, int len) dev = netdev_priv(net); snprintf(host_addr, len, "%pm", dev->host_mac); + string_upper(host_addr, host_addr); + return strlen(host_addr); } EXPORT_SYMBOL_GPL(gether_get_host_addr_cdc); From ff466f77d0a56719979c4234abd412abd98eae8f Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Mon, 8 May 2023 21:44:43 +0000 Subject: [PATCH 3192/4345] usb: typec: altmodes/displayport: fix pin_assignment_show commit d8f28269dd4bf9b55c3fb376ae31512730a96fce upstream. This patch fixes negative indexing of buf array in pin_assignment_show when get_current_pin_assignments returns 0 i.e. no compatible pin assignments are found. BUG: KASAN: use-after-free in pin_assignment_show+0x26c/0x33c ... Call trace: dump_backtrace+0x110/0x204 dump_stack_lvl+0x84/0xbc print_report+0x358/0x974 kasan_report+0x9c/0xfc __do_kernel_fault+0xd4/0x2d4 do_bad_area+0x48/0x168 do_tag_check_fault+0x24/0x38 do_mem_abort+0x6c/0x14c el1_abort+0x44/0x68 el1h_64_sync_handler+0x64/0xa4 el1h_64_sync+0x78/0x7c pin_assignment_show+0x26c/0x33c dev_attr_show+0x50/0xc0 Fixes: 0e3bb7d6894d ("usb: typec: Add driver for DisplayPort alternate mode") Cc: stable@vger.kernel.org Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230508214443.893436-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 07b656172068..0d4b1c0eeefb 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -503,6 +503,10 @@ static ssize_t pin_assignment_show(struct device *dev, mutex_unlock(&dp->lock); + /* get_current_pin_assignments can return 0 when no matching pin assignments are found */ + if (len == 0) + len++; + buf[len - 1] = '\n'; return len; } From 546b1f5f45a355ae0d3a8041cdaca597dfcac825 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 May 2023 20:44:12 +0200 Subject: [PATCH 3193/4345] ALSA: hda: Fix Oops by 9.1 surround channel names commit 3b44ec8c5c44790a82f07e90db45643c762878c6 upstream. get_line_out_pfx() may trigger an Oops by overflowing the static array with more than 8 channels. This was reported for MacBookPro 12,1 with Cirrus codec. As a workaround, extend for the 9.1 channels and also fix the potential Oops by unifying the code paths accessing the same array with the proper size check. Reported-by: Olliver Schinagl Cc: Link: https://lore.kernel.org/r/64d95eb0-dbdb-cff8-a8b1-988dc22b24cd@schinagl.nl Link: https://lore.kernel.org/r/20230516184412.24078-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/hda_generic.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 8ee3be7bbd24..35113fa84a0f 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -1153,8 +1153,8 @@ static bool path_has_mixer(struct hda_codec *codec, int path_idx, int ctl_type) return path && path->ctls[ctl_type]; } -static const char * const channel_name[4] = { - "Front", "Surround", "CLFE", "Side" +static const char * const channel_name[] = { + "Front", "Surround", "CLFE", "Side", "Back", }; /* give some appropriate ctl name prefix for the given line out channel */ @@ -1180,7 +1180,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, /* multi-io channels */ if (ch >= cfg->line_outs) - return channel_name[ch]; + goto fixed_name; switch (cfg->line_out_type) { case AUTO_PIN_SPEAKER_OUT: @@ -1232,6 +1232,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, if (cfg->line_outs == 1 && !spec->multi_ios) return "Line Out"; + fixed_name: if (ch >= ARRAY_SIZE(channel_name)) { snd_BUG(); return "PCM"; From 3add6b2a4a693b93a569c7cf84313b7d1a40ff58 Mon Sep 17 00:00:00 2001 From: Nikhil Mahale Date: Wed, 17 May 2023 14:37:36 +0530 Subject: [PATCH 3194/4345] ALSA: hda: Add NVIDIA codec IDs a3 through a7 to patch table commit dc4f2ccaedddb489a83e7b12ebbdc347272aacc9 upstream. These IDs are for AD102, AD103, AD104, AD106, and AD107 gpus with audio functions that are largely similar to the existing ones. Tested audio using gnome-settings, over HDMI, DP-SST and DP-MST connections on AD106 gpu. Signed-off-by: Nikhil Mahale Cc: Link: https://lore.kernel.org/r/20230517090736.15088-1-nmahale@nvidia.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_hdmi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 1afe9cddb69e..e4366fea9e27 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4374,6 +4374,11 @@ HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP", patch_via_hdmi), From 6cebdffba6283a61c37310b82fa5fbcb194ade71 Mon Sep 17 00:00:00 2001 From: Jeremy Soller Date: Fri, 5 May 2023 10:36:51 -0600 Subject: [PATCH 3195/4345] ALSA: hda/realtek: Add quirk for Clevo L140AU commit 0a6b36c5dc3dda0196f4fb65bdb34c38b8d060c3 upstream. Fixes headset detection on Clevo L140AU. Signed-off-by: Jeremy Soller Signed-off-by: Tim Crawford Cc: Link: https://lore.kernel.org/r/20230505163651.21257-1-tcrawford@system76.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c7e25d19c9d9..4c2394a30383 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9136,6 +9136,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x7716, "Clevo NS50PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7717, "Clevo NS70PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7718, "Clevo L140PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x7724, "Clevo L140AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), From b4f770e61230cb47b0c21b01b81e19553d635c83 Mon Sep 17 00:00:00 2001 From: Ai Chao Date: Sat, 6 May 2023 10:26:53 +0800 Subject: [PATCH 3196/4345] ALSA: hda/realtek: Add a quirk for HP EliteDesk 805 commit 90670ef774a8b6700c38ce1222e6aa263be54d5f upstream. Add a quirk for HP EliteDesk 805 to fixup ALC3867 headset MIC no sound. Signed-off-by: Ai Chao Cc: Link: https://lore.kernel.org/r/20230506022653.2074343-1-aichao@kylinos.cn Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4c2394a30383..ab8413dbab1a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11159,6 +11159,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x103c, 0x870c, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB), + SND_PCI_QUIRK(0x103c, 0x872b, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x885f, "HP 288 Pro G8", ALC671_FIXUP_HP_HEADSET_MIC2), From f7f799a6fe38f74ac37a1a4a1786eb3be8b81c81 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Sat, 6 May 2023 11:58:24 +1200 Subject: [PATCH 3197/4345] ALSA: hda/realtek: Add quirk for 2nd ASUS GU603 commit a4671b7fba59775845ee60cfbdfc4ba64300211b upstream. Add quirk for GU603 with 0x1c62 variant of codec. Signed-off-by: Luke D. Jones Cc: Link: https://lore.kernel.org/r/20230505235824.49607-2-luke@ljones.dev Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index ab8413dbab1a..2a72506b77ce 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9044,6 +9044,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), From b4b8294a41ca62d6a3daff24c3448ea51f8bc688 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 6 Apr 2023 13:08:45 +0200 Subject: [PATCH 3198/4345] can: j1939: recvmsg(): allow MSG_CMSG_COMPAT flag commit 1db080cbdbab28752bbb1c86d64daf96253a5da1 upstream. The control message provided by J1939 support MSG_CMSG_COMPAT but blocked recvmsg() syscalls that have set this flag, i.e. on 32bit user space on 64 bit kernels. Link: https://github.com/hartkopp/can-isotp/issues/59 Cc: Oleksij Rempel Suggested-by: Marc Kleine-Budde Signed-off-by: Oliver Hartkopp Tested-by: Oleksij Rempel Acked-by: Oleksij Rempel Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Link: https://lore.kernel.org/20230505110308.81087-3-mkl@pengutronix.de Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/j1939/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 709141abd131..76cd5f43faf7 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -798,7 +798,7 @@ static int j1939_sk_recvmsg(struct socket *sock, struct msghdr *msg, struct j1939_sk_buff_cb *skcb; int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE)) + if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE | MSG_CMSG_COMPAT)) return -EINVAL; if (flags & MSG_ERRQUEUE) From 073a4d750cecd77f1ddf442402123a76ce6602c9 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 6 Apr 2023 13:08:45 +0200 Subject: [PATCH 3199/4345] can: isotp: recvmsg(): allow MSG_CMSG_COMPAT flag commit db2773d65b02aed319a93efdfb958087771d4e19 upstream. The control message provided by isotp support MSG_CMSG_COMPAT but blocked recvmsg() syscalls that have set this flag, i.e. on 32bit user space on 64 bit kernels. Link: https://github.com/hartkopp/can-isotp/issues/59 Cc: Oleksij Rempel Suggested-by: Marc Kleine-Budde Signed-off-by: Oliver Hartkopp Fixes: 42bf50a1795a ("can: isotp: support MSG_TRUNC flag when reading from socket") Link: https://lore.kernel.org/20230505110308.81087-2-mkl@pengutronix.de Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/isotp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/can/isotp.c b/net/can/isotp.c index 4360f33278c1..4fcd8162fad4 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1016,7 +1016,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int noblock = flags & MSG_DONTWAIT; int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK)) + if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK | MSG_CMSG_COMPAT)) return -EINVAL; if (!so->bound) From 3bbeba3ce14d8ecac43fe0b9bb3785b0d86ca055 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:13 +0200 Subject: [PATCH 3200/4345] can: kvaser_pciefd: Set CAN_STATE_STOPPED in kvaser_pciefd_stop() commit aed0e6ca7dbb8fbea9bc69c9ac663d5533c8c5d8 upstream. Set can.state to CAN_STATE_STOPPED in kvaser_pciefd_stop(). Without this fix, wrong CAN state was repported after the interface was brought down. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-2-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/kvaser_pciefd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 9d7445f6ef14..7d8522426777 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -721,6 +721,7 @@ static int kvaser_pciefd_stop(struct net_device *netdev) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); del_timer(&can->bec_poll_timer); } + can->can.state = CAN_STATE_STOPPED; close_candev(netdev); return ret; From 03714e9c04ec96af1c5a6eff3b1e656704962040 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:15 +0200 Subject: [PATCH 3201/4345] can: kvaser_pciefd: Call request_irq() before enabling interrupts commit 84762d8da89d29ba842317eb842973e628c27391 upstream. Make sure the interrupt handler is registered before enabling interrupts. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-4-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/kvaser_pciefd.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 7d8522426777..591435e178d9 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -1825,6 +1825,11 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, if (err) goto err_teardown_can_ctrls; + err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, + IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); + if (err) + goto err_teardown_can_ctrls; + iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1, pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG); @@ -1845,11 +1850,6 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); - err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, - IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); - if (err) - goto err_teardown_can_ctrls; - err = kvaser_pciefd_reg_candev(pcie); if (err) goto err_free_irq; From 0babb3fabf558416757de900ef4e9906d8274f1a Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:16 +0200 Subject: [PATCH 3202/4345] can: kvaser_pciefd: Empty SRB buffer in probe commit c589557dd1426f5adf90c7a919d4fde5a3e4ef64 upstream. Empty the "Shared receive buffer" (SRB) in probe, to assure we start in a known state, and don't process any irrelevant packets. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-5-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/kvaser_pciefd.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 591435e178d9..6d9a9b66d8d6 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -70,10 +70,12 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_SYSID_BUILD_REG (KVASER_PCIEFD_SYSID_BASE + 0x14) /* Shared receive buffer registers */ #define KVASER_PCIEFD_SRB_BASE 0x1f200 +#define KVASER_PCIEFD_SRB_FIFO_LAST_REG (KVASER_PCIEFD_SRB_BASE + 0x1f4) #define KVASER_PCIEFD_SRB_CMD_REG (KVASER_PCIEFD_SRB_BASE + 0x200) #define KVASER_PCIEFD_SRB_IEN_REG (KVASER_PCIEFD_SRB_BASE + 0x204) #define KVASER_PCIEFD_SRB_IRQ_REG (KVASER_PCIEFD_SRB_BASE + 0x20c) #define KVASER_PCIEFD_SRB_STAT_REG (KVASER_PCIEFD_SRB_BASE + 0x210) +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG (KVASER_PCIEFD_SRB_BASE + 0x214) #define KVASER_PCIEFD_SRB_CTRL_REG (KVASER_PCIEFD_SRB_BASE + 0x218) /* EPCS flash controller registers */ #define KVASER_PCIEFD_SPI_BASE 0x1fc00 @@ -110,6 +112,9 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); /* DMA support */ #define KVASER_PCIEFD_SRB_STAT_DMA BIT(24) +/* SRB current packet level */ +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK 0xff + /* DMA Enable */ #define KVASER_PCIEFD_SRB_CTRL_DMA_ENABLE BIT(0) @@ -1055,6 +1060,7 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) { int i; u32 srb_status; + u32 srb_packet_count; dma_addr_t dma_addr[KVASER_PCIEFD_DMA_COUNT]; /* Disable the DMA */ @@ -1082,6 +1088,15 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + /* Empty Rx FIFO */ + srb_packet_count = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG) & + KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK; + while (srb_packet_count) { + /* Drop current packet in FIFO */ + ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_FIFO_LAST_REG); + srb_packet_count--; + } + srb_status = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_STAT_REG); if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DI)) { dev_err(&pcie->pci->dev, "DMA not idle before enabling\n"); From 65e85232ffa6a15f92ead85df236747b0448c960 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:14 +0200 Subject: [PATCH 3203/4345] can: kvaser_pciefd: Clear listen-only bit if not explicitly requested commit bf7ac55e991ca177f1ac16be51152f1ef291a4df upstream. The listen-only bit was never cleared, causing the controller to always use listen-only mode, if previously set. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-3-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/kvaser_pciefd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 6d9a9b66d8d6..f5d0d44c730b 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -561,6 +561,8 @@ static void kvaser_pciefd_setup_controller(struct kvaser_pciefd_can *can) if (can->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) mode |= KVASER_PCIEFD_KCAN_MODE_LOM; + else + mode &= ~KVASER_PCIEFD_KCAN_MODE_LOM; mode |= KVASER_PCIEFD_KCAN_MODE_EEN; mode |= KVASER_PCIEFD_KCAN_MODE_EPEN; From 7a7ec807fe547586e5a26d8027e62aa1c93eccfb Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:17 +0200 Subject: [PATCH 3204/4345] can: kvaser_pciefd: Do not send EFLUSH command on TFD interrupt commit 262d7a52ba27525e3c1203230c9f0524e48bbb34 upstream. Under certain circumstances we send two EFLUSH commands, resulting in two EFLUSH ack packets, while only expecting a single EFLUSH ack. This can cause the driver Tx flush completion to get out of sync. To avoid this problem, don't enable the "Transmit buffer flush done" (TFD) interrupt and remove the code handling it. Now we only send EFLUSH command after receiving status packet with "Init detected" (IDET) bit set. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-6-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/kvaser_pciefd.c | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index f5d0d44c730b..2cfa7edf7059 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -533,7 +533,7 @@ static int kvaser_pciefd_set_tx_irq(struct kvaser_pciefd_can *can) KVASER_PCIEFD_KCAN_IRQ_TOF | KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TAE | KVASER_PCIEFD_KCAN_IRQ_TAL | KVASER_PCIEFD_KCAN_IRQ_FDIC | KVASER_PCIEFD_KCAN_IRQ_BPP | - KVASER_PCIEFD_KCAN_IRQ_TAR | KVASER_PCIEFD_KCAN_IRQ_TFD; + KVASER_PCIEFD_KCAN_IRQ_TAR; iowrite32(msk, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); @@ -581,7 +581,7 @@ static void kvaser_pciefd_start_controller_flush(struct kvaser_pciefd_can *can) spin_lock_irqsave(&can->lock, irq); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); @@ -624,7 +624,7 @@ static int kvaser_pciefd_bus_on(struct kvaser_pciefd_can *can) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); @@ -1011,8 +1011,7 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) SET_NETDEV_DEV(netdev, &pcie->pci->dev); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | - KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); pcie->can[i] = can; @@ -1441,9 +1440,6 @@ static int kvaser_pciefd_handle_status_packet(struct kvaser_pciefd *pcie, cmd = KVASER_PCIEFD_KCAN_CMD_AT; cmd |= ++can->cmd_seq << KVASER_PCIEFD_KCAN_CMD_SEQ_SHIFT; iowrite32(cmd, can->reg_base + KVASER_PCIEFD_KCAN_CMD_REG); - - iowrite32(KVASER_PCIEFD_KCAN_IRQ_TFD, - can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); } else if (p->header[0] & KVASER_PCIEFD_SPACK_IDET && p->header[0] & KVASER_PCIEFD_SPACK_IRM && cmdseq == (p->header[1] & KVASER_PCIEFD_PACKET_SEQ_MSK) && @@ -1732,15 +1728,6 @@ static int kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can) if (irq & KVASER_PCIEFD_KCAN_IRQ_TOF) netdev_err(can->can.dev, "Tx FIFO overflow\n"); - if (irq & KVASER_PCIEFD_KCAN_IRQ_TFD) { - u8 count = ioread32(can->reg_base + - KVASER_PCIEFD_KCAN_TX_NPACKETS_REG) & 0xff; - - if (count == 0) - iowrite32(KVASER_PCIEFD_KCAN_CTRL_EFLUSH, - can->reg_base + KVASER_PCIEFD_KCAN_CTRL_REG); - } - if (irq & KVASER_PCIEFD_KCAN_IRQ_BPP) netdev_err(can->can.dev, "Fail to change bittiming, when not in reset mode\n"); From 845f98af6ae8fd5027aa04c4a1538fe546e7d16b Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:18 +0200 Subject: [PATCH 3205/4345] can: kvaser_pciefd: Disable interrupts in probe error path commit 11164bc39459335ab93c6e99d53b7e4292fba38b upstream. Disable interrupts in error path of probe function. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-7-extja@kvaser.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/kvaser_pciefd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 2cfa7edf7059..197390dfc6ab 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -1861,6 +1861,8 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, return 0; err_free_irq: + /* Disable PCI interrupts */ + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_IEN_REG); free_irq(pcie->pci->irq, pcie); err_teardown_can_ctrls: From ba061afa060ed9fdd1c24788b1de56983ce5a215 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Thu, 4 May 2023 16:40:20 +0200 Subject: [PATCH 3206/4345] statfs: enforce statfs[64] structure initialization commit ed40866ec7d328b3dfb70db7e2011640a16202c3 upstream. s390's struct statfs and struct statfs64 contain padding, which field-by-field copying does not set. Initialize the respective structs with zeros before filling them and copying them to userspace, like it's already done for the compat versions of these structs. Found by KMSAN. [agordeev@linux.ibm.com: fixed typo in patch description] Acked-by: Heiko Carstens Cc: stable@vger.kernel.org # v4.14+ Signed-off-by: Ilya Leoshkevich Reviewed-by: Andrew Morton Link: https://lore.kernel.org/r/20230504144021.808932-2-iii@linux.ibm.com Signed-off-by: Alexander Gordeev Signed-off-by: Greg Kroah-Hartman --- fs/statfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/statfs.c b/fs/statfs.c index 59f33752c131..d42b44dc0e49 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -130,6 +130,7 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); if (sizeof buf.f_blocks == 4) { if ((st->f_blocks | st->f_bfree | st->f_bavail | st->f_bsize | st->f_frsize) & @@ -158,7 +159,6 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; @@ -171,6 +171,7 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; @@ -182,7 +183,6 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; From ea3d5de90bc0601b06c3bf47bc85acfedb79e5a9 Mon Sep 17 00:00:00 2001 From: Vitaliy Tomin Date: Sun, 23 Apr 2023 11:45:12 +0800 Subject: [PATCH 3207/4345] serial: Add support for Advantech PCI-1611U card commit d2b00516de0e1d696724247098f6733a6ea53908 upstream. Add support for Advantech PCI-1611U card Advantech provides opensource drivers for this and many others card based on legacy copy of 8250_pci driver called adv950 https://www.advantech.com/emt/support/details/driver?id=1-TDOIMJ It is hard to maintain to run as out of tree module on newer kernels. Just adding PCI ID to kernel 8250_pci works perfect. Signed-off-by: Vitaliy Tomin Cc: stable Link: https://lore.kernel.org/r/20230423034512.2671157-1-tomin@iszf.irk.ru Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index b6656898699d..9617f7ad332d 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1839,6 +1839,8 @@ pci_moxa_setup(struct serial_private *priv, #define PCI_SUBDEVICE_ID_SIIG_DUAL_30 0x2530 #define PCI_VENDOR_ID_ADVANTECH 0x13fe #define PCI_DEVICE_ID_INTEL_CE4100_UART 0x2e66 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600 0x1600 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600_1611 0x1611 #define PCI_DEVICE_ID_ADVANTECH_PCI3620 0x3620 #define PCI_DEVICE_ID_ADVANTECH_PCI3618 0x3618 #define PCI_DEVICE_ID_ADVANTECH_PCIf618 0xf618 @@ -4185,6 +4187,9 @@ static SIMPLE_DEV_PM_OPS(pciserial_pm_ops, pciserial_suspend_one, pciserial_resume_one); static const struct pci_device_id serial_pci_tbl[] = { + { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI1600, + PCI_DEVICE_ID_ADVANTECH_PCI1600_1611, PCI_ANY_ID, 0, 0, + pbn_b0_4_921600 }, /* Advantech use PCI_DEVICE_ID_ADVANTECH_PCI3620 (0x3620) as 'PCI_SUBVENDOR_ID' */ { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI3620, PCI_DEVICE_ID_ADVANTECH_PCI3620, 0x0001, 0, 0, From 11dddfbb7a4e62489b01074d6c04d9d1b42e4047 Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Fri, 12 May 2023 06:08:48 -0500 Subject: [PATCH 3208/4345] vc_screen: reload load of struct vc_data pointer in vcs_write() to avoid UAF MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8fb9ea65c9d1338b0d2bb0a9122dc942cdd32357 upstream. After a call to console_unlock() in vcs_write() the vc_data struct can be freed by vc_port_destruct(). Because of that, the struct vc_data pointer must be reloaded in the while loop in vcs_write() after console_lock() to avoid a UAF when vcs_size() is called. Syzkaller reported a UAF in vcs_size(). BUG: KASAN: slab-use-after-free in vcs_size (drivers/tty/vt/vc_screen.c:215) Read of size 4 at addr ffff8880beab89a8 by task repro_vcs_size/4119 Call Trace: __asan_report_load4_noabort (mm/kasan/report_generic.c:380) vcs_size (drivers/tty/vt/vc_screen.c:215) vcs_write (drivers/tty/vt/vc_screen.c:664) vfs_write (fs/read_write.c:582 fs/read_write.c:564) ... Allocated by task 1213: kmalloc_trace (mm/slab_common.c:1064) vc_allocate (./include/linux/slab.h:559 ./include/linux/slab.h:680 drivers/tty/vt/vt.c:1078 drivers/tty/vt/vt.c:1058) con_install (drivers/tty/vt/vt.c:3334) tty_init_dev (drivers/tty/tty_io.c:1303 drivers/tty/tty_io.c:1415 drivers/tty/tty_io.c:1392) tty_open (drivers/tty/tty_io.c:2082 drivers/tty/tty_io.c:2128) chrdev_open (fs/char_dev.c:415) do_dentry_open (fs/open.c:921) vfs_open (fs/open.c:1052) ... Freed by task 4116: kfree (mm/slab_common.c:1016) vc_port_destruct (drivers/tty/vt/vt.c:1044) tty_port_destructor (drivers/tty/tty_port.c:296) tty_port_put (drivers/tty/tty_port.c:312) vt_disallocate_all (drivers/tty/vt/vt_ioctl.c:662 (discriminator 2)) vt_ioctl (drivers/tty/vt/vt_ioctl.c:903) tty_ioctl (drivers/tty/tty_io.c:2778) ... The buggy address belongs to the object at ffff8880beab8800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 424 bytes inside of freed 1024-byte region [ffff8880beab8800, ffff8880beab8c00) The buggy address belongs to the physical page: page:00000000afc77580 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xbeab8 head:00000000afc77580 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) page_type: 0xffffffff() raw: 000fffffc0010200 ffff888100042dc0 ffffea000426de00 dead000000000002 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880beab8880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880beab8900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880beab8980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880beab8a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880beab8a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Disabling lock debugging due to kernel taint Fixes: ac751efa6a0d ("console: rename acquire/release_console_sem() to console_lock/unlock()") Cc: stable Reported-by: syzkaller Signed-off-by: George Kennedy Reviewed-by: Thomas Weißschuh Link: https://lore.kernel.org/r/1683889728-10411-1-git-send-email-george.kennedy@oracle.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vc_screen.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 1dc07f9214d5..01c96537fa36 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -656,10 +656,17 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) } } - /* The vcs_size might have changed while we slept to grab - * the user buffer, so recheck. + /* The vc might have been freed or vcs_size might have changed + * while we slept to grab the user buffer, so recheck. * Return data written up to now on failure. */ + vc = vcs_vc(inode, &viewed); + if (!vc) { + if (written) + break; + ret = -ENXIO; + goto unlock_out; + } size = vcs_size(vc, attr, false); if (size < 0) { if (written) From 8c0109d76235543e8520b5e5ad9d71aa7368836e Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 18 May 2023 09:47:23 +0800 Subject: [PATCH 3209/4345] ceph: force updating the msg pointer in non-split case commit 4cafd0400bcb6187c0d4ab4d4b0229a89ac4f8c2 upstream. When the MClientSnap reqeust's op is not CEPH_SNAP_OP_SPLIT the request may still contain a list of 'split_realms', and we need to skip it anyway. Or it will be parsed as a corrupt snaptrace. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/61200 Reported-by: Frank Schilder Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- fs/ceph/snap.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 734873be56a7..8e6fc45ccc9e 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1008,6 +1008,19 @@ skip_inode: continue; adjust_snap_realm_parent(mdsc, child, realm->ino); } + } else { + /* + * In the non-split case both 'num_split_inos' and + * 'num_split_realms' should be 0, making this a no-op. + * However the MDS happens to populate 'split_realms' list + * in one of the UPDATE op cases by mistake. + * + * Skip both lists just in case to ensure that 'p' is + * positioned at the start of realm info, as expected by + * ceph_update_snap_trace(). + */ + p += sizeof(u64) * num_split_inos; + p += sizeof(u64) * num_split_realms; } /* From ae149cdaef4ec680b8145a9dc9674b51d4bfd507 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Wed, 10 May 2023 17:54:03 -0700 Subject: [PATCH 3210/4345] tpm/tpm_tis: Disable interrupts for more Lenovo devices commit e7d3e5c4b1dd50a70b31524c3228c62bb41bbab2 upstream. The P360 Tiny suffers from an irq storm issue like the T490s, so add an entry for it to tpm_tis_dmi_table, and force polling. There also previously was a report from the previous attempt to enable interrupts that involved a ThinkPad L490. So an entry is added for it as well. Cc: stable@vger.kernel.org Reported-by: Peter Zijlstra # P360 Tiny Closes: https://lore.kernel.org/linux-integrity/20230505130731.GO83892@hirez.programming.kicks-ass.net/ Signed-off-by: Jerry Snitselaar Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm_tis.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 14fad16d371f..3e1bb28b7efd 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -83,6 +83,22 @@ static const struct dmi_system_id tpm_tis_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"), }, }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkStation P360 Tiny", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkStation P360 Tiny"), + }, + }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkPad L490", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L490"), + }, + }, {} }; From 710dee57012ed7caebff47d1a7d923eaed4048f3 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 11 May 2023 21:42:24 +1000 Subject: [PATCH 3211/4345] powerpc/64s/radix: Fix soft dirty tracking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 66b2ca086210732954a7790d63d35542936fc664 upstream. It was reported that soft dirty tracking doesn't work when using the Radix MMU. The tracking is supposed to work by clearing the soft dirty bit for a mapping and then write protecting the PTE. If/when the page is written to, a page fault occurs and the soft dirty bit is added back via pte_mkdirty(). For example in wp_page_reuse(): entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); Unfortunately on radix _PAGE_SOFTDIRTY is being dropped by radix__ptep_set_access_flags(), called from ptep_set_access_flags(), meaning the soft dirty bit is not set even though the page has been written to. Fix it by adding _PAGE_SOFTDIRTY to the set of bits that are able to be changed in radix__ptep_set_access_flags(). Fixes: b0b5e9b13047 ("powerpc/mm/radix: Add radix pte #defines") Cc: stable@vger.kernel.org # v4.7+ Reported-by: Dan Horák Link: https://lore.kernel.org/r/20230511095558.56663a50f86bdc4cd97700b7@danny.cz Signed-off-by: Michael Ellerman Link: https://msgid.link/20230511114224.977423-1-mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/mm/book3s64/radix_pgtable.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index ae4ba6a6745d..5f0a2fa611fa 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -1064,8 +1064,8 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { struct mm_struct *mm = vma->vm_mm; - unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | - _PAGE_RW | _PAGE_EXEC); + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY | + _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); unsigned long change = pte_val(entry) ^ pte_val(*ptep); /* From 6b4205ea97901f822004e6c8d59484ccfda03faa Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Wed, 10 May 2023 00:29:56 +0900 Subject: [PATCH 3212/4345] nilfs2: fix use-after-free bug of nilfs_root in nilfs_evict_inode() commit 9b5a04ac3ad9898c4745cba46ea26de74ba56a8e upstream. During unmount process of nilfs2, nothing holds nilfs_root structure after nilfs2 detaches its writer in nilfs_detach_log_writer(). However, since nilfs_evict_inode() uses nilfs_root for some cleanup operations, it may cause use-after-free read if inodes are left in "garbage_list" and released by nilfs_dispose_list() at the end of nilfs_detach_log_writer(). Fix this issue by modifying nilfs_evict_inode() to only clear inode without additional metadata changes that use nilfs_root if the file system is degraded to read-only or the writer is detached. Link: https://lkml.kernel.org/r/20230509152956.8313-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+78d4495558999f55d1da@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/00000000000099e5ac05fb1c3b85@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/inode.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index fb594edc0837..042f4512e47d 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -921,6 +921,7 @@ void nilfs_evict_inode(struct inode *inode) struct nilfs_transaction_info ti; struct super_block *sb = inode->i_sb; struct nilfs_inode_info *ii = NILFS_I(inode); + struct the_nilfs *nilfs; int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { @@ -933,6 +934,23 @@ void nilfs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); + nilfs = sb->s_fs_info; + if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) { + /* + * If this inode is about to be disposed after the file system + * has been degraded to read-only due to file system corruption + * or after the writer has been detached, do not make any + * changes that cause writes, just clear it. + * Do this check after read-locking ns_segctor_sem by + * nilfs_transaction_begin() in order to avoid a race with + * the writer detach operation. + */ + clear_inode(inode); + nilfs_clear_inode(inode); + nilfs_transaction_abort(sb); + return; + } + /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); From 05b1703797443c8c013dd2d16a0756e751114d1d Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Fri, 15 Jul 2022 16:05:19 -0700 Subject: [PATCH 3213/4345] HID: wacom: Force pen out of prox if no events have been received in a while commit 94b179052f95c294d83e9c9c34f7833cf3cd4305 upstream. Prox-out events may not be reliably sent by some AES firmware. This can cause problems for users, particularly due to arbitration logic disabling touch input while the pen is in prox. This commit adds a timer which is reset every time a new prox event is received. When the timer expires we check to see if the pen is still in prox and force it out if necessary. This is patterend off of the same solution used by 'hid-letsketch' driver which has a similar problem. Link: https://github.com/linuxwacom/input-wacom/issues/310 Signed-off-by: Jason Gerecke Signed-off-by: Jiri Kosina Cc: Ping Cheng Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom.h | 3 +++ drivers/hid/wacom_sys.c | 2 ++ drivers/hid/wacom_wac.c | 39 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 44 insertions(+) diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h index 203d27d198b8..3f8b24a57014 100644 --- a/drivers/hid/wacom.h +++ b/drivers/hid/wacom.h @@ -91,6 +91,7 @@ #include #include #include +#include #include /* @@ -167,6 +168,7 @@ struct wacom { struct delayed_work init_work; struct wacom_remote *remote; struct work_struct mode_change_work; + struct timer_list idleprox_timer; bool generic_has_leds; struct wacom_leds { struct wacom_group_leds *groups; @@ -239,4 +241,5 @@ struct wacom_led *wacom_led_find(struct wacom *wacom, unsigned int group, struct wacom_led *wacom_led_next(struct wacom *wacom, struct wacom_led *cur); int wacom_equivalent_usage(int usage); int wacom_initialize_leds(struct wacom *wacom); +void wacom_idleprox_timeout(struct timer_list *list); #endif diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index b42785fdf7ed..a93070f5b214 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2781,6 +2781,7 @@ static int wacom_probe(struct hid_device *hdev, INIT_WORK(&wacom->battery_work, wacom_battery_work); INIT_WORK(&wacom->remote_work, wacom_remote_work); INIT_WORK(&wacom->mode_change_work, wacom_mode_change_work); + timer_setup(&wacom->idleprox_timer, &wacom_idleprox_timeout, TIMER_DEFERRABLE); /* ask for the report descriptor to be loaded by HID */ error = hid_parse(hdev); @@ -2825,6 +2826,7 @@ static void wacom_remove(struct hid_device *hdev) cancel_work_sync(&wacom->battery_work); cancel_work_sync(&wacom->remote_work); cancel_work_sync(&wacom->mode_change_work); + del_timer_sync(&wacom->idleprox_timer); if (hdev->bus == BUS_BLUETOOTH) device_remove_file(&hdev->dev, &dev_attr_speed); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index d82df2393d20..3917939418dc 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -11,6 +11,7 @@ #include "wacom_wac.h" #include "wacom.h" #include +#include /* resolution for penabled devices */ #define WACOM_PL_RES 20 @@ -41,6 +42,43 @@ static int wacom_numbered_button_to_key(int n); static void wacom_update_led(struct wacom *wacom, int button_count, int mask, int group); + +static void wacom_force_proxout(struct wacom_wac *wacom_wac) +{ + struct input_dev *input = wacom_wac->pen_input; + + wacom_wac->shared->stylus_in_proximity = 0; + + input_report_key(input, BTN_TOUCH, 0); + input_report_key(input, BTN_STYLUS, 0); + input_report_key(input, BTN_STYLUS2, 0); + input_report_key(input, BTN_STYLUS3, 0); + input_report_key(input, wacom_wac->tool[0], 0); + if (wacom_wac->serial[0]) { + input_report_abs(input, ABS_MISC, 0); + } + input_report_abs(input, ABS_PRESSURE, 0); + + wacom_wac->tool[0] = 0; + wacom_wac->id[0] = 0; + wacom_wac->serial[0] = 0; + + input_sync(input); +} + +void wacom_idleprox_timeout(struct timer_list *list) +{ + struct wacom *wacom = from_timer(wacom, list, idleprox_timer); + struct wacom_wac *wacom_wac = &wacom->wacom_wac; + + if (!wacom_wac->hid_data.sense_state) { + return; + } + + hid_warn(wacom->hdev, "%s: tool appears to be hung in-prox. forcing it out.\n", __func__); + wacom_force_proxout(wacom_wac); +} + /* * Percent of battery capacity for Graphire. * 8th value means AC online and show 100% capacity. @@ -2328,6 +2366,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field value = field->logical_maximum - value; break; case HID_DG_INRANGE: + mod_timer(&wacom->idleprox_timer, jiffies + msecs_to_jiffies(100)); wacom_wac->hid_data.inrange_state = value; if (!(features->quirks & WACOM_QUIRK_SENSE)) wacom_wac->hid_data.sense_state = value; From dfd419db0391b65d0a711229c07d8a6c4b7b09ac Mon Sep 17 00:00:00 2001 From: Ping Cheng Date: Fri, 26 Aug 2022 14:34:02 -0700 Subject: [PATCH 3214/4345] HID: wacom: Add new Intuos Pro Small (PTH-460) device IDs commit 0627f3df95e1609693f89e7ceb4156ac5db6e358 upstream. Add the new PIDs to wacom_wac.c to support the new model in the Intuos Pro series. Signed-off-by: Ping Cheng Tested-by: Aaron Armstrong Skomra Signed-off-by: Jiri Kosina Cc: Ping Cheng Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom_wac.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 3917939418dc..ad232cafc214 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -4840,6 +4840,10 @@ static const struct wacom_features wacom_features_0x3c6 = static const struct wacom_features wacom_features_0x3c8 = { "Wacom Intuos BT M", 21600, 13500, 4095, 63, INTUOSHT3_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4 }; +static const struct wacom_features wacom_features_0x3dd = + { "Wacom Intuos Pro S", 31920, 19950, 8191, 63, + INTUOSP2S_BT, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 7, + .touch_max = 10 }; static const struct wacom_features wacom_features_HID_ANY_ID = { "Wacom HID", .type = HID_GENERIC, .oVid = HID_ANY_ID, .oPid = HID_ANY_ID }; @@ -5019,6 +5023,7 @@ const struct hid_device_id wacom_ids[] = { { BT_DEVICE_WACOM(0x393) }, { BT_DEVICE_WACOM(0x3c6) }, { BT_DEVICE_WACOM(0x3c8) }, + { BT_DEVICE_WACOM(0x3dd) }, { USB_DEVICE_WACOM(0x4001) }, { USB_DEVICE_WACOM(0x4004) }, { USB_DEVICE_WACOM(0x5000) }, From e266da1656d6d83f41c1880b970f0e4887358f9d Mon Sep 17 00:00:00 2001 From: Ping Cheng Date: Wed, 28 Sep 2022 13:49:29 -0700 Subject: [PATCH 3215/4345] HID: wacom: add three styli to wacom_intuos_get_tool_type commit bfdc750c4cb2f3461b9b00a2755e2145ac195c9a upstream. We forgot to add the 3D pen ID a year ago. There are two new pro pen IDs to be added. Signed-off-by: Ping Cheng Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom_wac.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index ad232cafc214..37754a1f733b 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -713,11 +713,14 @@ static int wacom_intuos_get_tool_type(int tool_id) case 0x802: /* Intuos4/5 13HD/24HD General Pen */ case 0x8e2: /* IntuosHT2 pen */ case 0x022: + case 0x200: /* Pro Pen 3 */ + case 0x04200: /* Pro Pen 3 */ case 0x10842: /* MobileStudio Pro Pro Pen slim */ case 0x14802: /* Intuos4/5 13HD/24HD Classic Pen */ case 0x16802: /* Cintiq 13HD Pro Pen */ case 0x18802: /* DTH2242 Pen */ case 0x10802: /* Intuos4/5 13HD/24HD General Pen */ + case 0x80842: /* Intuos Pro and Cintiq Pro 3D Pen */ tool_type = BTN_TOOL_PEN; break; From 18fbf8cfbb9dcfde8504d23c309ed22bbf616cdf Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 19 Mar 2021 10:01:10 +0000 Subject: [PATCH 3216/4345] KVM: arm64: Link position-independent string routines into .hyp.text commit 7b4a7b5e6fefd15f708f959dd43e188444e252ec upstream Pull clear_page(), copy_page(), memcpy() and memset() into the nVHE hyp code and ensure that we always execute the '__pi_' entry point on the offchance that it changes in future. [ qperret: Commit title nits and added linker script alias ] Signed-off-by: Will Deacon Signed-off-by: Quentin Perret Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210319100146.1149909-3-qperret@google.com [sudip: adjust context] Signed-off-by: Sudip Mukherjee Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/hyp_image.h | 3 +++ arch/arm64/kernel/image-vars.h | 11 +++++++++++ arch/arm64/kvm/hyp/nvhe/Makefile | 4 ++++ 3 files changed, 18 insertions(+) diff --git a/arch/arm64/include/asm/hyp_image.h b/arch/arm64/include/asm/hyp_image.h index daa1a1da539e..e06842756051 100644 --- a/arch/arm64/include/asm/hyp_image.h +++ b/arch/arm64/include/asm/hyp_image.h @@ -31,6 +31,9 @@ */ #define KVM_NVHE_ALIAS(sym) kvm_nvhe_sym(sym) = sym; +/* Defines a linker script alias for KVM nVHE hyp symbols */ +#define KVM_NVHE_ALIAS_HYP(first, sec) kvm_nvhe_sym(first) = kvm_nvhe_sym(sec); + #endif /* LINKER_SCRIPT */ #endif /* __ARM64_HYP_IMAGE_H__ */ diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index c615b285ff5b..48e43b29a2d5 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -103,6 +103,17 @@ KVM_NVHE_ALIAS(gic_nonsecure_priorities); KVM_NVHE_ALIAS(__start___kvm_ex_table); KVM_NVHE_ALIAS(__stop___kvm_ex_table); +/* Position-independent library routines */ +KVM_NVHE_ALIAS_HYP(clear_page, __pi_clear_page); +KVM_NVHE_ALIAS_HYP(copy_page, __pi_copy_page); +KVM_NVHE_ALIAS_HYP(memcpy, __pi_memcpy); +KVM_NVHE_ALIAS_HYP(memset, __pi_memset); + +#ifdef CONFIG_KASAN +KVM_NVHE_ALIAS_HYP(__memcpy, __pi_memcpy); +KVM_NVHE_ALIAS_HYP(__memset, __pi_memset); +#endif + #endif /* CONFIG_KVM */ #endif /* __ARM64_KERNEL_IMAGE_VARS_H */ diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index ddde15fe85f2..230bba1a6716 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -6,9 +6,13 @@ asflags-y := -D__KVM_NVHE_HYPERVISOR__ ccflags-y := -D__KVM_NVHE_HYPERVISOR__ +lib-objs := clear_page.o copy_page.o memcpy.o memset.o +lib-objs := $(addprefix ../../../lib/, $(lib-objs)) + obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o hyp-main.o obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ ../fpsimd.o ../hyp-entry.o +obj-y += $(lib-objs) ## ## Build rules for compiling nVHE hyp code From fb3c5714f5ce2ace7d81ca0315b1171fa5c5fdd4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 27 Jan 2022 20:06:08 +0200 Subject: [PATCH 3217/4345] serial: 8250_exar: derive nr_ports from PCI ID for Acces I/O cards [ Upstream commit 8e4413aaf6a2e3a46e99a0718ca54c0cf8609cb2 ] In the similar way how it's done in 8250_pericom, derive the number of the UART ports from PCI ID for Acces I/O cards. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220127180608.71509-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 95d698869b40 ("serial: 8250_exar: Add support for USR298x PCI Modems") Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_exar.c | 37 ++++++++++------------------- 1 file changed, 13 insertions(+), 24 deletions(-) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 2d0e7c7e408d..3d82902bfe5b 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -596,7 +596,12 @@ exar_pci_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) maxnr = pci_resource_len(pcidev, bar) >> (board->reg_shift + 3); - nr_ports = board->num_ports ? board->num_ports : pcidev->device & 0x0f; + if (pcidev->vendor == PCI_VENDOR_ID_ACCESSIO) + nr_ports = BIT(((pcidev->device & 0x38) >> 3) - 1); + else if (board->num_ports) + nr_ports = board->num_ports; + else + nr_ports = pcidev->device & 0x0f; priv = devm_kzalloc(&pcidev->dev, struct_size(priv, line, nr_ports), GFP_KERNEL); if (!priv) @@ -695,22 +700,6 @@ static int __maybe_unused exar_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(exar_pci_pm, exar_suspend, exar_resume); -static const struct exar8250_board acces_com_2x = { - .num_ports = 2, - .setup = pci_xr17c154_setup, -}; - -static const struct exar8250_board acces_com_4x = { - .num_ports = 4, - .setup = pci_xr17c154_setup, -}; - -static const struct exar8250_board acces_com_8x = { - .num_ports = 8, - .setup = pci_xr17c154_setup, -}; - - static const struct exar8250_board pbn_fastcom335_2 = { .num_ports = 2, .setup = pci_fastcom335_setup, @@ -795,13 +784,13 @@ static const struct exar8250_board pbn_exar_XR17V8358 = { } static const struct pci_device_id exar_pci_tbl[] = { - EXAR_DEVICE(ACCESSIO, COM_2S, acces_com_2x), - EXAR_DEVICE(ACCESSIO, COM_4S, acces_com_4x), - EXAR_DEVICE(ACCESSIO, COM_8S, acces_com_8x), - EXAR_DEVICE(ACCESSIO, COM232_8, acces_com_8x), - EXAR_DEVICE(ACCESSIO, COM_2SM, acces_com_2x), - EXAR_DEVICE(ACCESSIO, COM_4SM, acces_com_4x), - EXAR_DEVICE(ACCESSIO, COM_8SM, acces_com_8x), + EXAR_DEVICE(ACCESSIO, COM_2S, pbn_exar_XR17C15x), + EXAR_DEVICE(ACCESSIO, COM_4S, pbn_exar_XR17C15x), + EXAR_DEVICE(ACCESSIO, COM_8S, pbn_exar_XR17C15x), + EXAR_DEVICE(ACCESSIO, COM232_8, pbn_exar_XR17C15x), + EXAR_DEVICE(ACCESSIO, COM_2SM, pbn_exar_XR17C15x), + EXAR_DEVICE(ACCESSIO, COM_4SM, pbn_exar_XR17C15x), + EXAR_DEVICE(ACCESSIO, COM_8SM, pbn_exar_XR17C15x), CONNECT_DEVICE(XR17C152, UART_2_232, pbn_connect), CONNECT_DEVICE(XR17C154, UART_4_232, pbn_connect), From 1ffa0b8ba928dbbf3cd5adfbc1c189127ec4806b Mon Sep 17 00:00:00 2001 From: Matthew Howell Date: Thu, 19 Jan 2023 14:40:29 -0500 Subject: [PATCH 3218/4345] serial: exar: Add support for Sealevel 7xxxC serial cards [ Upstream commit 14ee78d5932afeb710c8305196a676a715bfdea8 ] Add support for Sealevel 7xxxC serial cards. This patch: * Adds IDs to recognize 7xxxC cards from Sealevel Systems. * Updates exar_pci_probe() to set nr_ports to last two bytes of primary dev ID for these cards. Signed-off-by: Matthew Howell Cc: stable Link: https://lore.kernel.org/r/alpine.DEB.2.21.2301191440010.22558@tstest-VirtualBox Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 95d698869b40 ("serial: 8250_exar: Add support for USR298x PCI Modems") Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_exar.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 3d82902bfe5b..2c9f72109112 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -43,6 +43,12 @@ #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 +#define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001 +#define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002 +#define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004 +#define PCI_DEVICE_ID_SEALEVEL_780xC 0x1008 +#define PCI_DEVICE_ID_SEALEVEL_716xC 0x1010 + #define UART_EXAR_INT0 0x80 #define UART_EXAR_8XMODE 0x88 /* 8X sampling rate select */ #define UART_EXAR_SLEEP 0x8b /* Sleep mode */ @@ -600,6 +606,8 @@ exar_pci_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) nr_ports = BIT(((pcidev->device & 0x38) >> 3) - 1); else if (board->num_ports) nr_ports = board->num_ports; + else if (pcidev->vendor == PCI_VENDOR_ID_SEALEVEL) + nr_ports = pcidev->device & 0xff; else nr_ports = pcidev->device & 0x0f; @@ -826,6 +834,12 @@ static const struct pci_device_id exar_pci_tbl[] = { EXAR_DEVICE(COMMTECH, 4224PCI335, pbn_fastcom335_4), EXAR_DEVICE(COMMTECH, 2324PCI335, pbn_fastcom335_4), EXAR_DEVICE(COMMTECH, 2328PCI335, pbn_fastcom335_8), + + EXAR_DEVICE(SEALEVEL, 710xC, pbn_exar_XR17V35x), + EXAR_DEVICE(SEALEVEL, 720xC, pbn_exar_XR17V35x), + EXAR_DEVICE(SEALEVEL, 740xC, pbn_exar_XR17V35x), + EXAR_DEVICE(SEALEVEL, 780xC, pbn_exar_XR17V35x), + EXAR_DEVICE(SEALEVEL, 716xC, pbn_exar_XR17V35x), { 0, } }; MODULE_DEVICE_TABLE(pci, exar_pci_tbl); From 9c9f253fc60b19ce9d82761bafd7ffb0ac4142b4 Mon Sep 17 00:00:00 2001 From: Andrew Davis Date: Thu, 20 Apr 2023 11:02:09 -0500 Subject: [PATCH 3219/4345] serial: 8250_exar: Add support for USR298x PCI Modems [ Upstream commit 95d698869b404772cc8b72560df71548491c10bc ] Possibly the last PCI controller-based (i.e. not a soft/winmodem) dial-up modem one can still buy. Looks to have a stock XR17C154 PCI UART chip for communication, but for some reason when provisioning the PCI IDs they swapped the vendor and subvendor IDs. Otherwise this card would have worked out of the box. Searching online, some folks seem to not have this issue and others do, so it is possible only some batches of cards have this error. Create a new macro to handle the switched IDs and add support here. Signed-off-by: Andrew Davis Cc: stable Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230420160209.28221-1-afd@ti.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_exar.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 2c9f72109112..5c2adf14049b 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -40,9 +40,13 @@ #define PCI_DEVICE_ID_COMMTECH_4224PCIE 0x0020 #define PCI_DEVICE_ID_COMMTECH_4228PCIE 0x0021 #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 + #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 +#define PCI_SUBDEVICE_ID_USR_2980 0x0128 +#define PCI_SUBDEVICE_ID_USR_2981 0x0129 + #define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001 #define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002 #define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004 @@ -791,6 +795,15 @@ static const struct exar8250_board pbn_exar_XR17V8358 = { (kernel_ulong_t)&bd \ } +#define USR_DEVICE(devid, sdevid, bd) { \ + PCI_DEVICE_SUB( \ + PCI_VENDOR_ID_USR, \ + PCI_DEVICE_ID_EXAR_##devid, \ + PCI_VENDOR_ID_EXAR, \ + PCI_SUBDEVICE_ID_USR_##sdevid), 0, 0, \ + (kernel_ulong_t)&bd \ + } + static const struct pci_device_id exar_pci_tbl[] = { EXAR_DEVICE(ACCESSIO, COM_2S, pbn_exar_XR17C15x), EXAR_DEVICE(ACCESSIO, COM_4S, pbn_exar_XR17C15x), @@ -815,6 +828,10 @@ static const struct pci_device_id exar_pci_tbl[] = { IBM_DEVICE(XR17C152, SATURN_SERIAL_ONE_PORT, pbn_exar_ibm_saturn), + /* USRobotics USR298x-OEM PCI Modems */ + USR_DEVICE(XR17C152, 2980, pbn_exar_XR17C15x), + USR_DEVICE(XR17C152, 2981, pbn_exar_XR17C15x), + /* Exar Corp. XR17C15[248] Dual/Quad/Octal UART */ EXAR_DEVICE(EXAR, XR17C152, pbn_exar_XR17C15x), EXAR_DEVICE(EXAR, XR17C154, pbn_exar_XR17C15x), From 3681a0287a738c1940efe206e43f3c4b06776269 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 22 Jun 2021 15:26:16 +0200 Subject: [PATCH 3220/4345] s390/qdio: get rid of register asm [ Upstream commit d3e2ff5436d6ee38b572ba5c01dc7994769bec54 ] Reviewed-by: Benjamin Block Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik Stable-dep-of: 2862a2fdfae8 ("s390/qdio: fix do_sqbs() inline assembly constraint") Signed-off-by: Sasha Levin --- drivers/s390/cio/qdio.h | 25 ++++++++------- drivers/s390/cio/qdio_main.c | 62 +++++++++++++++++++----------------- 2 files changed, 46 insertions(+), 41 deletions(-) diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index cd2df4ff8e0e..854a21e1d3b7 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -88,15 +88,15 @@ enum qdio_irq_states { static inline int do_sqbs(u64 token, unsigned char state, int queue, int *start, int *count) { - register unsigned long _ccq asm ("0") = *count; - register unsigned long _token asm ("1") = token; unsigned long _queuestart = ((unsigned long)queue << 32) | *start; + unsigned long _ccq = *count; asm volatile( - " .insn rsy,0xeb000000008A,%1,0,0(%2)" - : "+d" (_ccq), "+d" (_queuestart) - : "d" ((unsigned long)state), "d" (_token) - : "memory", "cc"); + " lgr 1,%[token]\n" + " .insn rsy,0xeb000000008a,%[qs],%[ccq],0(%[state])" + : [ccq] "+&d" (_ccq), [qs] "+&d" (_queuestart) + : [state] "d" ((unsigned long)state), [token] "d" (token) + : "memory", "cc", "1"); *count = _ccq & 0xff; *start = _queuestart & 0xff; @@ -106,16 +106,17 @@ static inline int do_sqbs(u64 token, unsigned char state, int queue, static inline int do_eqbs(u64 token, unsigned char *state, int queue, int *start, int *count, int ack) { - register unsigned long _ccq asm ("0") = *count; - register unsigned long _token asm ("1") = token; unsigned long _queuestart = ((unsigned long)queue << 32) | *start; unsigned long _state = (unsigned long)ack << 63; + unsigned long _ccq = *count; asm volatile( - " .insn rrf,0xB99c0000,%1,%2,0,0" - : "+d" (_ccq), "+d" (_queuestart), "+d" (_state) - : "d" (_token) - : "memory", "cc"); + " lgr 1,%[token]\n" + " .insn rrf,0xb99c0000,%[qs],%[state],%[ccq],0" + : [ccq] "+&d" (_ccq), [qs] "+&d" (_queuestart), + [state] "+&d" (_state) + : [token] "d" (token) + : "memory", "cc", "1"); *count = _ccq & 0xff; *start = _queuestart & 0xff; *state = _state & 0xff; diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 3e29c26f0185..e3c55fc2363a 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -31,38 +31,41 @@ MODULE_DESCRIPTION("QDIO base support"); MODULE_LICENSE("GPL"); static inline int do_siga_sync(unsigned long schid, - unsigned int out_mask, unsigned int in_mask, + unsigned long out_mask, unsigned long in_mask, unsigned int fc) { - register unsigned long __fc asm ("0") = fc; - register unsigned long __schid asm ("1") = schid; - register unsigned long out asm ("2") = out_mask; - register unsigned long in asm ("3") = in_mask; int cc; asm volatile( + " lgr 0,%[fc]\n" + " lgr 1,%[schid]\n" + " lgr 2,%[out]\n" + " lgr 3,%[in]\n" " siga 0\n" - " ipm %0\n" - " srl %0,28\n" - : "=d" (cc) - : "d" (__fc), "d" (__schid), "d" (out), "d" (in) : "cc"); + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=&d" (cc) + : [fc] "d" (fc), [schid] "d" (schid), + [out] "d" (out_mask), [in] "d" (in_mask) + : "cc", "0", "1", "2", "3"); return cc; } -static inline int do_siga_input(unsigned long schid, unsigned int mask, - unsigned int fc) +static inline int do_siga_input(unsigned long schid, unsigned long mask, + unsigned long fc) { - register unsigned long __fc asm ("0") = fc; - register unsigned long __schid asm ("1") = schid; - register unsigned long __mask asm ("2") = mask; int cc; asm volatile( + " lgr 0,%[fc]\n" + " lgr 1,%[schid]\n" + " lgr 2,%[mask]\n" " siga 0\n" - " ipm %0\n" - " srl %0,28\n" - : "=d" (cc) - : "d" (__fc), "d" (__schid), "d" (__mask) : "cc"); + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=&d" (cc) + : [fc] "d" (fc), [schid] "d" (schid), [mask] "d" (mask) + : "cc", "0", "1", "2"); return cc; } @@ -78,23 +81,24 @@ static inline int do_siga_input(unsigned long schid, unsigned int mask, * Note: For IQDC unicast queues only the highest priority queue is processed. */ static inline int do_siga_output(unsigned long schid, unsigned long mask, - unsigned int *bb, unsigned int fc, + unsigned int *bb, unsigned long fc, unsigned long aob) { - register unsigned long __fc asm("0") = fc; - register unsigned long __schid asm("1") = schid; - register unsigned long __mask asm("2") = mask; - register unsigned long __aob asm("3") = aob; int cc; asm volatile( + " lgr 0,%[fc]\n" + " lgr 1,%[schid]\n" + " lgr 2,%[mask]\n" + " lgr 3,%[aob]\n" " siga 0\n" - " ipm %0\n" - " srl %0,28\n" - : "=d" (cc), "+d" (__fc), "+d" (__aob) - : "d" (__schid), "d" (__mask) - : "cc"); - *bb = __fc >> 31; + " lgr %[fc],0\n" + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=&d" (cc), [fc] "+&d" (fc) + : [schid] "d" (schid), [mask] "d" (mask), [aob] "d" (aob) + : "cc", "0", "1", "2", "3"); + *bb = fc >> 31; return cc; } From 75258f0838682deaf1b0e2f55f00f56bedbe1b20 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 11 May 2023 17:04:41 +0200 Subject: [PATCH 3221/4345] s390/qdio: fix do_sqbs() inline assembly constraint [ Upstream commit 2862a2fdfae875888e3c1c3634e3422e01d98147 ] Use "a" constraint instead of "d" constraint to pass the state parameter to the do_sqbs() inline assembly. This prevents that general purpose register zero is used for the state parameter. If the compiler would select general purpose register zero this would be problematic for the used instruction in rsy format: the register used for the state parameter is a base register. If the base register is general purpose register zero the contents of the register are unexpectedly ignored when the instruction is executed. This only applies to z/VM guests using QIOASSIST with dedicated (pass through) QDIO-based devices such as FCP [zfcp driver] as well as real OSA or HiperSockets [qeth driver]. A possible symptom for this case using zfcp is the following repeating kernel message pattern: zfcp : A QDIO problem occurred zfcp : A QDIO problem occurred zfcp : qdio: ZFCP on SC using AI:1 QEBSM:1 PRI:1 TDD:1 SIGA: W zfcp : A QDIO problem occurred zfcp : A QDIO problem occurred Each of the qdio problem message can be accompanied by the following entries for the affected subchannel in /sys/kernel/debug/s390dbf/qdio_error/hex_ascii for zfcp or qeth: ccq: 69.... SQBS ERROR. Reviewed-by: Benjamin Block Cc: Steffen Maier Fixes: 8129ee164267 ("[PATCH] s390: qdio V=V pass-through") Cc: Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev Signed-off-by: Sasha Levin --- drivers/s390/cio/qdio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 854a21e1d3b7..919d10614166 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -95,7 +95,7 @@ static inline int do_sqbs(u64 token, unsigned char state, int queue, " lgr 1,%[token]\n" " .insn rsy,0xeb000000008a,%[qs],%[ccq],0(%[state])" : [ccq] "+&d" (_ccq), [qs] "+&d" (_queuestart) - : [state] "d" ((unsigned long)state), [token] "d" (token) + : [state] "a" ((unsigned long)state), [token] "d" (token) : "memory", "cc", "1"); *count = _ccq & 0xff; *start = _queuestart & 0xff; From dbcc95bb510e973c874ecacc170bacfad33e0b89 Mon Sep 17 00:00:00 2001 From: Gregory Oakes Date: Thu, 16 Mar 2023 15:13:12 -0500 Subject: [PATCH 3222/4345] watchdog: sp5100_tco: Immediately trigger upon starting. commit 4eda19cc8a29cde3580ed73bf11dc73b4e757697 upstream. The watchdog countdown is supposed to begin when the device file is opened. Instead, it would begin countdown upon the first write to or close of the device file. Now, the ping operation is called within the start operation which ensures the countdown begins. From experimenation, it does not appear possible to do this with a single write including both the start bit and the trigger bit. So, it is done as two distinct writes. Signed-off-by: Gregory Oakes Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230316201312.17538-1-gregory.oakes@amd.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Cc: Mario Limonciello Signed-off-by: Greg Kroah-Hartman --- drivers/watchdog/sp5100_tco.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c index a730ecbf78cd..0db77c90b4b6 100644 --- a/drivers/watchdog/sp5100_tco.c +++ b/drivers/watchdog/sp5100_tco.c @@ -104,6 +104,10 @@ static int tco_timer_start(struct watchdog_device *wdd) val |= SP5100_WDT_START_STOP_BIT; writel(val, SP5100_WDT_CONTROL(tco->tcobase)); + /* This must be a distinct write. */ + val |= SP5100_WDT_TRIGGER_BIT; + writel(val, SP5100_WDT_CONTROL(tco->tcobase)); + return 0; } From 84fbe6ad0fa3c42925fbf6849d3f2129b4362c5e Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Mon, 24 Jan 2022 16:35:25 +0100 Subject: [PATCH 3223/4345] ARM: dts: stm32: fix AV96 board SAI2 pin muxing on stm32mp15 commit ee2aacb6f3a901a95b1dd68964b69c92cdbbf213 upstream. Replace sai2a-2 node name by sai2a-sleep-2, to avoid name duplication. Fixes: 1a9a9d226f0f ("ARM: dts: stm32: fix AV96 board SAI2 pin muxing on stm32mp15") Signed-off-by: Olivier Moysan Signed-off-by: Alexandre Torgue Cc: Marek Vasut Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/stm32mp15-pinctrl.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/stm32mp15-pinctrl.dtsi b/arch/arm/boot/dts/stm32mp15-pinctrl.dtsi index ccf66adbbf62..07c15c1ce9d4 100644 --- a/arch/arm/boot/dts/stm32mp15-pinctrl.dtsi +++ b/arch/arm/boot/dts/stm32mp15-pinctrl.dtsi @@ -1102,7 +1102,7 @@ }; }; - sai2a_sleep_pins_c: sai2a-2 { + sai2a_sleep_pins_c: sai2a-sleep-2 { pins { pinmux = , /* SAI2_SCK_A */ , /* SAI2_SD_A */ From 047f618d198e4bc7c9ad3844064a15dc90a82094 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Sat, 20 May 2023 12:46:24 -0700 Subject: [PATCH 3224/4345] writeback, cgroup: remove extra percpu_ref_exit() 5.10 stable commit 2b00b2a0e642 ("writeback, cgroup: fix null-ptr-deref write in bdi_split_work_to_wbs") is a backport of upstream 6.3 commit 1ba1199ec574. In the 5.10 stable commit backport percpu_ref_exit() is called twice: first in cgwb_release_workfn() and then in cgwb_free_rcu(). The 2nd call is benign as percpu_ref_exit() internally detects there's nothing to do. This fixes an non-upstream issue that only applies to 5.10.y. Fixes: 2b00b2a0e642 ("writeback, cgroup: fix null-ptr-deref write in bdi_split_work_to_wbs") Signed-off-by: Greg Thelen Signed-off-by: Greg Kroah-Hartman --- mm/backing-dev.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index b28f629c3527..dd08ab928e07 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -404,7 +404,6 @@ static void cgwb_release_workfn(struct work_struct *work) blkcg_unpin_online(blkcg); fprop_local_destroy_percpu(&wb->memcg_completions); - percpu_ref_exit(&wb->refcnt); wb_exit(wb); call_rcu(&wb->rcu, cgwb_free_rcu); } From bba7ebe10baf1d6d59c9a11c3cdc8bd2bc1b1028 Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 16 May 2023 22:00:38 +0300 Subject: [PATCH 3225/4345] net/sched: act_mirred: refactor the handle of xmit [ Upstream commit fa6d639930ee5cd3f932cc314f3407f07a06582d ] This one is prepare for the next patch. Signed-off-by: wenxu Signed-off-by: Jakub Kicinski [DP: adjusted context for linux-5.10.y] Signed-off-by: Dragos-Marian Panait Signed-off-by: Greg Kroah-Hartman --- include/net/sch_generic.h | 5 ----- net/sched/act_mirred.c | 21 +++++++++++++++------ 2 files changed, 15 insertions(+), 11 deletions(-) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 61cd19ee51f4..a62677be7452 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1320,11 +1320,6 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block); -static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res) -{ - return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb); -} - /* Make sure qdisc is no longer in SCHED state. */ static inline void qdisc_synchronize(const struct Qdisc *q) { diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 25dad1921baf..745ce36ffe5b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -206,6 +206,18 @@ release_idr: return err; } +static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) +{ + int err; + + if (!want_ingress) + err = dev_queue_xmit(skb); + else + err = netif_receive_skb(skb); + + return err; +} + static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -295,18 +307,15 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; - if (skb_tc_reinsert(skb, res)) + err = tcf_mirred_forward(res->ingress, skb); + if (err) tcf_action_inc_overlimit_qstats(&m->common); __this_cpu_dec(mirred_rec_level); return TC_ACT_CONSUMED; } } - if (!want_ingress) - err = dev_queue_xmit(skb2); - else - err = netif_receive_skb(skb2); - + err = tcf_mirred_forward(want_ingress, skb2); if (err) { out: tcf_action_inc_overlimit_qstats(&m->common); From f5bf8e3ca13edeee812c2cda6ba52d6cbf85d2b5 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Tue, 16 May 2023 22:00:39 +0300 Subject: [PATCH 3226/4345] net/sched: act_mirred: better wording on protection against excessive stack growth [ Upstream commit 78dcdffe0418ac8f3f057f26fe71ccf4d8ed851f ] with commit e2ca070f89ec ("net: sched: protect against stack overflow in TC act_mirred"), act_mirred protected itself against excessive stack growth using per_cpu counter of nested calls to tcf_mirred_act(), and capping it to MIRRED_RECURSION_LIMIT. However, such protection does not detect recursion/loops in case the packet is enqueued to the backlog (for example, when the mirred target device has RPS or skb timestamping enabled). Change the wording from "recursion" to "nesting" to make it more clear to readers. CC: Jamal Hadi Salim Signed-off-by: Davide Caratti Reviewed-by: Marcelo Ricardo Leitner Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni Stable-dep-of: ca22da2fbd69 ("act_mirred: use the backlog for nested calls to mirred ingress") Signed-off-by: Dragos-Marian Panait Signed-off-by: Greg Kroah-Hartman --- net/sched/act_mirred.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 745ce36ffe5b..cbcbc1d368a5 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -28,8 +28,8 @@ static LIST_HEAD(mirred_list); static DEFINE_SPINLOCK(mirred_list_lock); -#define MIRRED_RECURSION_LIMIT 4 -static DEFINE_PER_CPU(unsigned int, mirred_rec_level); +#define MIRRED_NEST_LIMIT 4 +static DEFINE_PER_CPU(unsigned int, mirred_nest_level); static bool tcf_mirred_is_act_redirect(int action) { @@ -225,7 +225,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, struct sk_buff *skb2 = skb; bool m_mac_header_xmit; struct net_device *dev; - unsigned int rec_level; + unsigned int nest_level; int retval, err = 0; bool use_reinsert; bool want_ingress; @@ -236,11 +236,11 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, int mac_len; bool at_nh; - rec_level = __this_cpu_inc_return(mirred_rec_level); - if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) { + nest_level = __this_cpu_inc_return(mirred_nest_level); + if (unlikely(nest_level > MIRRED_NEST_LIMIT)) { net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", netdev_name(skb->dev)); - __this_cpu_dec(mirred_rec_level); + __this_cpu_dec(mirred_nest_level); return TC_ACT_SHOT; } @@ -310,7 +310,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, err = tcf_mirred_forward(res->ingress, skb); if (err) tcf_action_inc_overlimit_qstats(&m->common); - __this_cpu_dec(mirred_rec_level); + __this_cpu_dec(mirred_nest_level); return TC_ACT_CONSUMED; } } @@ -322,7 +322,7 @@ out: if (tcf_mirred_is_act_redirect(m_eaction)) retval = TC_ACT_SHOT; } - __this_cpu_dec(mirred_rec_level); + __this_cpu_dec(mirred_nest_level); return retval; } From 53245103786312f21fb9785327a4367cf10f0dbb Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Tue, 16 May 2023 22:00:40 +0300 Subject: [PATCH 3227/4345] act_mirred: use the backlog for nested calls to mirred ingress [ Upstream commit ca22da2fbd693b54dc8e3b7b54ccc9f7e9ba3640 ] William reports kernel soft-lockups on some OVS topologies when TC mirred egress->ingress action is hit by local TCP traffic [1]. The same can also be reproduced with SCTP (thanks Xin for verifying), when client and server reach themselves through mirred egress to ingress, and one of the two peers sends a "heartbeat" packet (from within a timer). Enqueueing to backlog proved to fix this soft lockup; however, as Cong noticed [2], we should preserve - when possible - the current mirred behavior that counts as "overlimits" any eventual packet drop subsequent to the mirred forwarding action [3]. A compromise solution might use the backlog only when tcf_mirred_act() has a nest level greater than one: change tcf_mirred_forward() accordingly. Also, add a kselftest that can reproduce the lockup and verifies TC mirred ability to account for further packet drops after TC mirred egress->ingress (when the nest level is 1). [1] https://lore.kernel.org/netdev/33dc43f587ec1388ba456b4915c75f02a8aae226.1663945716.git.dcaratti@redhat.com/ [2] https://lore.kernel.org/netdev/Y0w%2FWWY60gqrtGLp@pop-os.localdomain/ [3] such behavior is not guaranteed: for example, if RPS or skb RX timestamping is enabled on the mirred target device, the kernel can defer receiving the skb and return NET_RX_SUCCESS inside tcf_mirred_forward(). Reported-by: William Zhao CC: Xin Long Signed-off-by: Davide Caratti Reviewed-by: Marcelo Ricardo Leitner Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni [DP: adjusted context for linux-5.10.y] Signed-off-by: Dragos-Marian Panait Signed-off-by: Greg Kroah-Hartman --- net/sched/act_mirred.c | 7 +++ .../selftests/net/forwarding/tc_actions.sh | 48 ++++++++++++++++++- 2 files changed, 54 insertions(+), 1 deletion(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index cbcbc1d368a5..91a19460cb57 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -206,12 +206,19 @@ release_idr: return err; } +static bool is_mirred_nested(void) +{ + return unlikely(__this_cpu_read(mirred_nest_level) > 1); +} + static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) { int err; if (!want_ingress) err = dev_queue_xmit(skb); + else if (is_mirred_nested()) + err = netif_rx(skb); else err = netif_receive_skb(skb); diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index d9eca227136b..1e27031288c8 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -3,7 +3,7 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ - gact_trap_test" + gact_trap_test mirred_egress_to_ingress_tcp_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -153,6 +153,52 @@ gact_trap_test() log_test "trap ($tcflags)" } +mirred_egress_to_ingress_tcp_test() +{ + local tmpfile=$(mktemp) tmpfile1=$(mktemp) + + RET=0 + dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$tmpfile + tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ + $tcflags ip_proto tcp src_ip 192.0.2.1 dst_ip 192.0.2.2 \ + action ct commit nat src addr 192.0.2.2 pipe \ + action ct clear pipe \ + action ct commit nat dst addr 192.0.2.1 pipe \ + action ct clear pipe \ + action skbedit ptype host pipe \ + action mirred ingress redirect dev $h1 + tc filter add dev $h1 protocol ip pref 101 handle 101 egress flower \ + $tcflags ip_proto icmp \ + action mirred ingress redirect dev $h1 + tc filter add dev $h1 protocol ip pref 102 handle 102 ingress flower \ + ip_proto icmp \ + action drop + + ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $tmpfile1 & + local rpid=$! + ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$tmpfile + wait -n $rpid + cmp -s $tmpfile $tmpfile1 + check_err $? "server output check failed" + + $MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \ + -t icmp "ping,id=42,seq=5" -q + tc_check_packets "dev $h1 egress" 101 10 + check_err $? "didn't mirred redirect ICMP" + tc_check_packets "dev $h1 ingress" 102 10 + check_err $? "didn't drop mirred ICMP" + local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits) + test ${overlimits} = 10 + check_err $? "wrong overlimits, expected 10 got ${overlimits}" + + tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower + tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower + tc filter del dev $h1 ingress protocol ip pref 102 handle 102 flower + + rm -f $tmpfile $tmpfile1 + log_test "mirred_egress_to_ingress_tcp ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} From e3674788a86578a403839224ce90355c28ce4562 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 15 May 2023 16:07:16 +0200 Subject: [PATCH 3228/4345] spi: fsl-spi: Re-organise transfer bits_per_word adaptation (backported from upstream 8a5299a1278eadf1e08a598a5345c376206f171e) For different reasons, fsl-spi driver performs bits_per_word modifications for different reasons: - On CPU mode, to minimise amount of interrupts - On CPM/QE mode to work around controller byte order For CPU mode that's done in fsl_spi_prepare_message() while for CPM mode that's done in fsl_spi_setup_transfer(). Reunify all of it in fsl_spi_prepare_message(), and catch impossible cases early through master's bits_per_word_mask instead of returning EINVAL later. Signed-off-by: Christophe Leroy Link: https://lore.kernel.org/r/0ce96fe96e8b07cba0613e4097cfd94d09b8919a.1680371809.git.christophe.leroy@csgroup.eu Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-fsl-spi.c | 50 ++++++++++++++++++--------------------- 1 file changed, 23 insertions(+), 27 deletions(-) diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index 1bad0ceac81b..f1d4aa310233 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -203,26 +203,6 @@ static int mspi_apply_cpu_mode_quirks(struct spi_mpc8xxx_cs *cs, return bits_per_word; } -static int mspi_apply_qe_mode_quirks(struct spi_mpc8xxx_cs *cs, - struct spi_device *spi, - int bits_per_word) -{ - /* CPM/QE uses Little Endian for words > 8 - * so transform 16 and 32 bits words into 8 bits - * Unfortnatly that doesn't work for LSB so - * reject these for now */ - /* Note: 32 bits word, LSB works iff - * tfcr/rfcr is set to CPMFCR_GBL */ - if (spi->mode & SPI_LSB_FIRST && - bits_per_word > 8) - return -EINVAL; - if (bits_per_word <= 8) - return bits_per_word; - if (bits_per_word == 16 || bits_per_word == 32) - return 8; /* pretend its 8 bits */ - return -EINVAL; -} - static int fsl_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t) { @@ -250,9 +230,6 @@ static int fsl_spi_setup_transfer(struct spi_device *spi, bits_per_word = mspi_apply_cpu_mode_quirks(cs, spi, mpc8xxx_spi, bits_per_word); - else - bits_per_word = mspi_apply_qe_mode_quirks(cs, spi, - bits_per_word); if (bits_per_word < 0) return bits_per_word; @@ -370,14 +347,27 @@ static int fsl_spi_do_one_msg(struct spi_master *master, * In CPU mode, optimize large byte transfers to use larger * bits_per_word values to reduce number of interrupts taken. */ - if (!(mpc8xxx_spi->flags & SPI_CPM_MODE)) { - list_for_each_entry(t, &m->transfers, transfer_list) { + list_for_each_entry(t, &m->transfers, transfer_list) { + if (!(mpc8xxx_spi->flags & SPI_CPM_MODE)) { if (t->len < 256 || t->bits_per_word != 8) continue; if ((t->len & 3) == 0) t->bits_per_word = 32; else if ((t->len & 1) == 0) t->bits_per_word = 16; + } else { + /* + * CPM/QE uses Little Endian for words > 8 + * so transform 16 and 32 bits words into 8 bits + * Unfortnatly that doesn't work for LSB so + * reject these for now + * Note: 32 bits word, LSB works iff + * tfcr/rfcr is set to CPMFCR_GBL + */ + if (m->spi->mode & SPI_LSB_FIRST && t->bits_per_word > 8) + return -EINVAL; + if (t->bits_per_word == 16 || t->bits_per_word == 32) + t->bits_per_word = 8; /* pretend its 8 bits */ } } @@ -635,8 +625,14 @@ static struct spi_master *fsl_spi_probe(struct device *dev, if (mpc8xxx_spi->type == TYPE_GRLIB) fsl_spi_grlib_probe(dev); - master->bits_per_word_mask = - (SPI_BPW_RANGE_MASK(4, 16) | SPI_BPW_MASK(32)) & + if (mpc8xxx_spi->flags & SPI_CPM_MODE) + master->bits_per_word_mask = + (SPI_BPW_RANGE_MASK(4, 8) | SPI_BPW_MASK(16) | SPI_BPW_MASK(32)); + else + master->bits_per_word_mask = + (SPI_BPW_RANGE_MASK(4, 16) | SPI_BPW_MASK(32)); + + master->bits_per_word_mask &= SPI_BPW_RANGE_MASK(1, mpc8xxx_spi->max_bits_per_word); if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE) From 60afe299bb541a928ba39bcb4ae8d3e428d1c5a5 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 15 May 2023 16:07:17 +0200 Subject: [PATCH 3229/4345] spi: fsl-cpm: Use 16 bit mode for large transfers with even size (cherry picked from upstream fc96ec826bced75cc6b9c07a4ac44bbf651337ab) On CPM, the RISC core is a lot more efficiant when doing transfers in 16-bits chunks than in 8-bits chunks, but unfortunately the words need to be byte swapped as seen in a previous commit. So, for large tranfers with an even size, allocate a temporary tx buffer and byte-swap data before and after transfer. This change allows setting higher speed for transfer. For instance on an MPC 8xx (CPM1 comms RISC processor), the documentation tells that transfer in byte mode at 1 kbit/s uses 0.200% of CPM load at 25 MHz while a word transfer at the same speed uses 0.032% of CPM load. This means the speed can be 6 times higher in word mode for the same CPM load. For the time being, only do it on CPM1 as there must be a trade-off between the CPM load reduction and the CPU load required to byte swap the data. Signed-off-by: Christophe Leroy Link: https://lore.kernel.org/r/f2e981f20f92dd28983c3949702a09248c23845c.1680371809.git.christophe.leroy@csgroup.eu Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/spi/spi-fsl-cpm.c | 23 +++++++++++++++++++++++ drivers/spi/spi-fsl-spi.c | 3 +++ 2 files changed, 26 insertions(+) diff --git a/drivers/spi/spi-fsl-cpm.c b/drivers/spi/spi-fsl-cpm.c index ee905880769e..7832ce330b29 100644 --- a/drivers/spi/spi-fsl-cpm.c +++ b/drivers/spi/spi-fsl-cpm.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "spi-fsl-cpm.h" #include "spi-fsl-lib.h" @@ -120,6 +121,21 @@ int fsl_spi_cpm_bufs(struct mpc8xxx_spi *mspi, mspi->rx_dma = mspi->dma_dummy_rx; mspi->map_rx_dma = 0; } + if (t->bits_per_word == 16 && t->tx_buf) { + const u16 *src = t->tx_buf; + u16 *dst; + int i; + + dst = kmalloc(t->len, GFP_KERNEL); + if (!dst) + return -ENOMEM; + + for (i = 0; i < t->len >> 1; i++) + dst[i] = cpu_to_le16p(src + i); + + mspi->tx = dst; + mspi->map_tx_dma = 1; + } if (mspi->map_tx_dma) { void *nonconst_tx = (void *)mspi->tx; /* shut up gcc */ @@ -173,6 +189,13 @@ void fsl_spi_cpm_bufs_complete(struct mpc8xxx_spi *mspi) if (mspi->map_rx_dma) dma_unmap_single(dev, mspi->rx_dma, t->len, DMA_FROM_DEVICE); mspi->xfer_in_progress = NULL; + + if (t->bits_per_word == 16 && t->rx_buf) { + int i; + + for (i = 0; i < t->len; i += 2) + le16_to_cpus(t->rx_buf + i); + } } EXPORT_SYMBOL_GPL(fsl_spi_cpm_bufs_complete); diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index f1d4aa310233..63302e21e574 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -368,6 +368,9 @@ static int fsl_spi_do_one_msg(struct spi_master *master, return -EINVAL; if (t->bits_per_word == 16 || t->bits_per_word == 32) t->bits_per_word = 8; /* pretend its 8 bits */ + if (t->bits_per_word == 8 && t->len >= 256 && + (mpc8xxx_spi->flags & SPI_CPM1)) + t->bits_per_word = 16; } } From c41324385aa7c9ac0fc1fa9c2521aacedea24788 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 14 Mar 2023 09:17:16 +0100 Subject: [PATCH 3230/4345] ocfs2: Switch to security_inode_init_security() commit de3004c874e740304cc4f4a83d6200acb511bbda upstream. In preparation for removing security_old_inode_init_security(), switch to security_inode_init_security(). Extend the existing ocfs2_initxattrs() to take the ocfs2_security_xattr_info structure from fs_info, and populate the name/value/len triple with the first xattr provided by LSMs. As fs_info was not used before, ocfs2_initxattrs() can now handle the case of replicating the behavior of security_old_inode_init_security(), i.e. just obtaining the xattr, in addition to setting all xattrs provided by LSMs. Supporting multiple xattrs is not currently supported where security_old_inode_init_security() was called (mknod, symlink), as it requires non-trivial changes that can be done at a later time. Like for reiserfs, even if EVM is invoked, it will not provide an xattr (if it is not the first to set it, its xattr will be discarded; if it is the first, it does not have xattrs to calculate the HMAC on). Finally, since security_inode_init_security(), unlike security_old_inode_init_security(), returns zero instead of -EOPNOTSUPP if no xattrs were provided by LSMs or if inodes are private, additionally check in ocfs2_init_security_get() if the xattr name is set. If not, act as if security_old_inode_init_security() returned -EOPNOTSUPP, and set si->enable to zero to notify to the functions following ocfs2_init_security_get() that no xattrs are available. Signed-off-by: Roberto Sassu Reviewed-by: Casey Schaufler Acked-by: Joseph Qi Reviewed-by: Mimi Zohar Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/namei.c | 2 ++ fs/ocfs2/xattr.c | 30 ++++++++++++++++++++++++++---- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index df1f6b7aa797..d6a0e719b1ad 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -242,6 +242,7 @@ static int ocfs2_mknod(struct inode *dir, int want_meta = 0; int xattr_credits = 0; struct ocfs2_security_xattr_info si = { + .name = NULL, .enable = 1, }; int did_quota_inode = 0; @@ -1801,6 +1802,7 @@ static int ocfs2_symlink(struct inode *dir, int want_clusters = 0; int xattr_credits = 0; struct ocfs2_security_xattr_info si = { + .name = NULL, .enable = 1, }; int did_quota = 0, did_quota_inode = 0; diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 9ccd19d8f7b1..10df2e1dfef7 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7260,9 +7260,21 @@ static int ocfs2_xattr_security_set(const struct xattr_handler *handler, static int ocfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { + struct ocfs2_security_xattr_info *si = fs_info; const struct xattr *xattr; int err = 0; + if (si) { + si->value = kmemdup(xattr_array->value, xattr_array->value_len, + GFP_KERNEL); + if (!si->value) + return -ENOMEM; + + si->name = xattr_array->name; + si->value_len = xattr_array->value_len; + return 0; + } + for (xattr = xattr_array; xattr->name != NULL; xattr++) { err = ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY, xattr->name, xattr->value, @@ -7278,13 +7290,23 @@ int ocfs2_init_security_get(struct inode *inode, const struct qstr *qstr, struct ocfs2_security_xattr_info *si) { + int ret; + /* check whether ocfs2 support feature xattr */ if (!ocfs2_supports_xattr(OCFS2_SB(dir->i_sb))) return -EOPNOTSUPP; - if (si) - return security_old_inode_init_security(inode, dir, qstr, - &si->name, &si->value, - &si->value_len); + if (si) { + ret = security_inode_init_security(inode, dir, qstr, + &ocfs2_initxattrs, si); + /* + * security_inode_init_security() does not return -EOPNOTSUPP, + * we have to check the xattr ourselves. + */ + if (!ret && !si->name) + si->enable = 0; + + return ret; + } return security_inode_init_security(inode, dir, qstr, &ocfs2_initxattrs, NULL); From b0d7e62fd15e46860f9c9157d8e1c95f6ea54973 Mon Sep 17 00:00:00 2001 From: Adam Stylinski Date: Sun, 21 May 2023 10:52:23 -0400 Subject: [PATCH 3231/4345] ALSA: hda/ca0132: add quirk for EVGA X299 DARK commit 7843380d07bbeffd3ce6504e73cf61f840ae76ca upstream. This quirk is necessary for surround and other DSP effects to work with the onboard ca0132 based audio chipset for the EVGA X299 dark mainboard. Signed-off-by: Adam Stylinski Cc: Link: https://bugzilla.kernel.org/show_bug.cgi?id=67071 Link: https://lore.kernel.org/r/ZGopOe19T1QOwizS@eggsbenedict.adamsnet Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_ca0132.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 6057084da4cf..6d67cca4cfa6 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1272,6 +1272,7 @@ static const struct snd_pci_quirk ca0132_quirks[] = { SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI), SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI), SND_PCI_QUIRK(0x3842, 0x1038, "EVGA X99 Classified", QUIRK_R3DI), + SND_PCI_QUIRK(0x3842, 0x104b, "EVGA X299 Dark", QUIRK_R3DI), SND_PCI_QUIRK(0x3842, 0x1055, "EVGA Z390 DARK", QUIRK_R3DI), SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D), SND_PCI_QUIRK(0x1102, 0x0018, "Recon3D", QUIRK_R3D), From 1f57a1b979493b155cea5fa9007f7ce2fc6808f7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 18 May 2023 13:35:20 +0200 Subject: [PATCH 3232/4345] ALSA: hda: Fix unhandled register update during auto-suspend period MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 81302b1c7c997e8a56c1c2fc63a296ebeb0cd2d0 upstream. It's reported that the recording started right after the driver probe doesn't work properly, and it turned out that this is related with the codec auto-suspend. Namely, after the probe phase, the usage count goes zero, and the auto-suspend is programmed, but the codec is kept still active until the auto-suspend expiration. When an application (e.g. alsactl) updates the mixer values at this moment, the values are cached but not actually written. Then, starting arecord thereafter also results in the silence because of the missing unmute. The root cause is the handling of "lazy update" mode; when a mixer value is updated *after* the suspend, it should update only the cache and exits. At the resume, the cached value is written to the device, in turn. The problem is that the current code misinterprets the state of auto-suspend as if it were already suspended. Although we can add the check of the actual device state after pm_runtime_get_if_in_use() for catching the missing state, this won't suffice; the second call of regmap_update_bits_check() will skip writing the register because the cache has been already updated by the first call. So we'd need fixes in two different places. OTOH, a simpler fix is to replace pm_runtime_get_if_in_use() with pm_runtime_get_if_active() (with ign_usage_count=true). This change implies that the driver takes the pm refcount if the device is still in ACTIVE state and continues the processing. A small caveat is that this will leave the auto-suspend timer. But, since the timer callback itself checks the device state and aborts gracefully when it's active, this won't be any substantial problem. Long story short: we address the missing register-write problem just by replacing the pm_runtime_*() call in snd_hda_keep_power_up(). Fixes: fc4f000bf8c0 ("ALSA: hda - Fix unexpected resume through regmap code path") Reported-by: Amadeusz Sławiński Closes: https://lore.kernel.org/r/a7478636-af11-92ab-731c-9b13c582a70d@linux.intel.com Suggested-by: Cezary Rojewski Cc: Link: https://lore.kernel.org/r/20230518113520.15213-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/hda/hdac_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c index b7e5032b61c9..bfd858577676 100644 --- a/sound/hda/hdac_device.c +++ b/sound/hda/hdac_device.c @@ -611,7 +611,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_power_up_pm); int snd_hdac_keep_power_up(struct hdac_device *codec) { if (!atomic_inc_not_zero(&codec->in_pm)) { - int ret = pm_runtime_get_if_in_use(&codec->dev); + int ret = pm_runtime_get_if_active(&codec->dev, true); if (!ret) return -1; if (ret < 0) From 798c1c62cfa5b61868882e2568f0b9308c9d8077 Mon Sep 17 00:00:00 2001 From: Bin Li Date: Wed, 24 May 2023 19:37:55 +0800 Subject: [PATCH 3233/4345] ALSA: hda/realtek: Enable headset onLenovo M70/M90 commit 4ca110cab46561cd74a2acd9b447435acb4bec5f upstream. Lenovo M70/M90 Gen4 are equipped with ALC897, and they need ALC897_FIXUP_HEADSET_MIC_PIN quirk to make its headset mic work. The previous quirk for M70/M90 is for Gen3. Signed-off-by: Bin Li Cc: Link: https://lore.kernel.org/r/20230524113755.1346928-1-bin.li@canonical.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2a72506b77ce..21c8b474a4df 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11187,6 +11187,8 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x3321, "Lenovo ThinkCentre M70 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x331b, "Lenovo ThinkCentre M90 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x3742, "Lenovo TianYi510Pro-14IOB", ALC897_FIXUP_HEADSET_MIC_PIN2), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD), From 42b78c8cc774b47023d6d16d96d54cc7015e4a07 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 17 May 2023 13:38:08 +0000 Subject: [PATCH 3234/4345] net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize commit 7e01c7f7046efc2c7c192c3619db43292b98e997 upstream. Currently in cdc_ncm_check_tx_max(), if dwNtbOutMaxSize is lower than the calculated "min" value, but greater than zero, the logic sets tx_max to dwNtbOutMaxSize. This is then used to allocate a new SKB in cdc_ncm_fill_tx_frame() where all the data is handled. For small values of dwNtbOutMaxSize the memory allocated during alloc_skb(dwNtbOutMaxSize, GFP_ATOMIC) will have the same size, due to how size is aligned at alloc time: size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); Thus we hit the same bug that we tried to squash with commit 2be6d4d16a084 ("net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero") Low values of dwNtbOutMaxSize do not cause an issue presently because at alloc_skb() time more memory (512b) is allocated than required for the SKB headers alone (320b), leaving some space (512b - 320b = 192b) for CDC data (172b). However, if more elements (for example 3 x u64 = [24b]) were added to one of the SKB header structs, say 'struct skb_shared_info', increasing its original size (320b [320b aligned]) to something larger (344b [384b aligned]), then suddenly the CDC data (172b) no longer fits in the spare SKB data area (512b - 384b = 128b). Consequently the SKB bounds checking semantics fails and panics: skbuff: skb_over_panic: text:ffffffff831f755b len:184 put:172 head:ffff88811f1c6c00 data:ffff88811f1c6c00 tail:0xb8 end:0x80 dev: ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:113! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 57 Comm: kworker/0:2 Not tainted 5.15.106-syzkaller-00249-g19c0ed55a470 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023 Workqueue: mld mld_ifc_work RIP: 0010:skb_panic net/core/skbuff.c:113 [inline] RIP: 0010:skb_over_panic+0x14c/0x150 net/core/skbuff.c:118 [snip] Call Trace: skb_put+0x151/0x210 net/core/skbuff.c:2047 skb_put_zero include/linux/skbuff.h:2422 [inline] cdc_ncm_ndp16 drivers/net/usb/cdc_ncm.c:1131 [inline] cdc_ncm_fill_tx_frame+0x11ab/0x3da0 drivers/net/usb/cdc_ncm.c:1308 cdc_ncm_tx_fixup+0xa3/0x100 Deal with too low values of dwNtbOutMaxSize, clamp it in the range [USB_CDC_NCM_NTB_MIN_OUT_SIZE, CDC_NCM_NTB_MAX_SIZE_TX]. We ensure enough data space is allocated to handle CDC data by making sure dwNtbOutMaxSize is not smaller than USB_CDC_NCM_NTB_MIN_OUT_SIZE. Fixes: 289507d3364f ("net: cdc_ncm: use sysfs for rx/tx aggregation tuning") Cc: stable@vger.kernel.org Reported-by: syzbot+9f575a1f15fc0c01ed69@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=b982f1059506db48409d Link: https://lore.kernel.org/all/20211202143437.1411410-1-lee.jones@linaro.org/ Signed-off-by: Tudor Ambarus Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230517133808.1873695-2-tudor.ambarus@linaro.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/cdc_ncm.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index ab91fa5b0194..57b1e6dc62f0 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -180,9 +180,12 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx) else min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32); - max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize)); - if (max == 0) + if (le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) == 0) max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */ + else + max = clamp_t(u32, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize), + USB_CDC_NCM_NTB_MIN_OUT_SIZE, + CDC_NCM_NTB_MAX_SIZE_TX); /* some devices set dwNtbOutMaxSize too low for the above default */ min = min(min, max); @@ -1230,6 +1233,9 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) * further. */ if (skb_out == NULL) { + /* If even the smallest allocation fails, abort. */ + if (ctx->tx_curr_size == USB_CDC_NCM_NTB_MIN_OUT_SIZE) + goto alloc_failed; ctx->tx_low_mem_max_cnt = min(ctx->tx_low_mem_max_cnt + 1, (unsigned)CDC_NCM_LOW_MEM_MAX_CNT); ctx->tx_low_mem_val = ctx->tx_low_mem_max_cnt; @@ -1248,13 +1254,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) skb_out = alloc_skb(ctx->tx_curr_size, GFP_ATOMIC); /* No allocation possible so we will abort */ - if (skb_out == NULL) { - if (skb != NULL) { - dev_kfree_skb_any(skb); - dev->net->stats.tx_dropped++; - } - goto exit_no_skb; - } + if (!skb_out) + goto alloc_failed; ctx->tx_low_mem_val--; } if (ctx->is_ndp16) { @@ -1447,6 +1448,11 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) return skb_out; +alloc_failed: + if (skb) { + dev_kfree_skb_any(skb); + dev->net->stats.tx_dropped++; + } exit_no_skb: /* Start timer, if there is a remaining non-empty skb */ if (ctx->tx_curr_skb != NULL && n > 0) From 89eba5586aa4d308a11b5246f5286abb73c7796d Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Sat, 6 May 2023 19:38:12 +1000 Subject: [PATCH 3235/4345] m68k: Move signal frame following exception on 68020/030 commit b845b574f86dcb6a70dfa698aa87a237b0878d2a upstream. On 68030/020, an instruction such as, moveml %a2-%a3/%a5,%sp@- may cause a stack page fault during instruction execution (i.e. not at an instruction boundary) and produce a format 0xB exception frame. In this situation, the value of USP will be unreliable. If a signal is to be delivered following the exception, this USP value is used to calculate the location for a signal frame. This can result in a corrupted user stack. The corruption was detected in dash (actually in glibc) where it showed up as an intermittent "stack smashing detected" message and crash following signal delivery for SIGCHLD. It was hard to reproduce that failure because delivery of the signal raced with the page fault and because the kernel places an unpredictable gap of up to 7 bytes between the USP and the signal frame. A format 0xB exception frame can be produced by a bus error or an address error. The 68030 Users Manual says that address errors occur immediately upon detection during instruction prefetch. The instruction pipeline allows prefetch to overlap with other instructions, which means an address error can arise during the execution of a different instruction. So it seems likely that this patch may help in the address error case also. Reported-and-tested-by: Stan Johnson Link: https://lore.kernel.org/all/CAMuHMdW3yD22_ApemzW_6me3adq6A458u1_F0v-1EYwK_62jPA@mail.gmail.com/ Cc: Michael Schmitz Cc: Andreas Schwab Cc: stable@vger.kernel.org Co-developed-by: Michael Schmitz Signed-off-by: Michael Schmitz Signed-off-by: Finn Thain Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/9e66262a754fcba50208aa424188896cc52a1dd1.1683365892.git.fthain@linux-m68k.org Signed-off-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman --- arch/m68k/kernel/signal.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 5d12736b4b28..131e87a55cbb 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -882,11 +882,17 @@ static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs * } static inline void __user * -get_sigframe(struct ksignal *ksig, size_t frame_size) +get_sigframe(struct ksignal *ksig, struct pt_regs *tregs, size_t frame_size) { unsigned long usp = sigsp(rdusp(), ksig); + unsigned long gap = 0; - return (void __user *)((usp - frame_size) & -8UL); + if (CPU_IS_020_OR_030 && tregs->format == 0xb) { + /* USP is unreliable so use worst-case value */ + gap = 256; + } + + return (void __user *)((usp - gap - frame_size) & -8UL); } static int setup_frame(struct ksignal *ksig, sigset_t *set, @@ -904,7 +910,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, return -EFAULT; } - frame = get_sigframe(ksig, sizeof(*frame) + fsize); + frame = get_sigframe(ksig, tregs, sizeof(*frame) + fsize); if (fsize) err |= copy_to_user (frame + 1, regs + 1, fsize); @@ -976,7 +982,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, return -EFAULT; } - frame = get_sigframe(ksig, sizeof(*frame)); + frame = get_sigframe(ksig, tregs, sizeof(*frame)); if (fsize) err |= copy_to_user (&frame->uc.uc_extra, regs + 1, fsize); From de0d7dd5efd44515a785d6bdffa4cc04516da6c8 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 24 May 2023 14:34:58 +0200 Subject: [PATCH 3236/4345] parisc: Handle kgdb breakpoints only in kernel context commit 6888ff04e37d01295620a73f3f7efbc79f6ef152 upstream. The kernel kgdb break instructions should only be handled when running in kernel context. Cc: # v5.4+ Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/traps.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 2fad7867af10..bd09050dc0af 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -305,8 +305,8 @@ static void handle_break(struct pt_regs *regs) #endif #ifdef CONFIG_KGDB - if (unlikely(iir == PARISC_KGDB_COMPILED_BREAK_INSN || - iir == PARISC_KGDB_BREAK_INSN)) { + if (unlikely((iir == PARISC_KGDB_COMPILED_BREAK_INSN || + iir == PARISC_KGDB_BREAK_INSN)) && !user_mode(regs)) { kgdb_handle_exception(9, SIGTRAP, 0, regs); return; } From c570dbf279a8d97bf8b60efcb860e664aa0ed072 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Mon, 22 May 2023 22:57:30 +0200 Subject: [PATCH 3237/4345] parisc: Allow to reboot machine after system halt commit 2028315cf59bb899a5ac7e87dc48ecb8fac7ac24 upstream. In case a machine can't power-off itself on system shutdown, allow the user to reboot it by pressing the RETURN key. Cc: # v4.14+ Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/kernel/process.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 5e4381280c97..c14ee40302d8 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -123,13 +123,18 @@ void machine_power_off(void) /* It seems we have no way to power the system off via * software. The user has to press the button himself. */ - printk(KERN_EMERG "System shut down completed.\n" - "Please power this system off now."); + printk("Power off or press RETURN to reboot.\n"); /* prevent soft lockup/stalled CPU messages for endless loop. */ rcu_sysrq_start(); lockup_detector_soft_poweroff(); - for (;;); + while (1) { + /* reboot if user presses RETURN key */ + if (pdc_iodc_getc() == 13) { + printk("Rebooting...\n"); + machine_restart(NULL); + } + } } void (*pm_power_off)(void); From ea50ee0ef9040e87e21165374aa553f410011536 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Tue, 16 May 2023 22:47:56 -0700 Subject: [PATCH 3238/4345] gpio: mockup: Fix mode of debugfs files commit 0a1bb16e0fe6650c3841e611de374bfd5578ad70 upstream. This driver's debugfs files have had a read operation since commit 2a9e27408e12 ("gpio: mockup: rework debugfs interface"), but were still being created with write-only mode bits. Update them to indicate that the files can also be read. Signed-off-by: Zev Weiss Fixes: 2a9e27408e12 ("gpio: mockup: rework debugfs interface") Cc: stable@kernel.org # v5.1+ Signed-off-by: Bartosz Golaszewski Signed-off-by: Greg Kroah-Hartman --- drivers/gpio/gpio-mockup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index 876027fdefc9..e20b60432e01 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -370,7 +370,7 @@ static void gpio_mockup_debugfs_setup(struct device *dev, priv->offset = i; priv->desc = &gc->gpiodev->descs[i]; - debugfs_create_file(name, 0200, chip->dbg_dir, priv, + debugfs_create_file(name, 0600, chip->dbg_dir, priv, &gpio_mockup_debugfs_ops); } } From 139f84c80d9f47a3d8d24b29a56a7ee06e80778e Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 11 May 2023 12:45:59 -0400 Subject: [PATCH 3239/4345] btrfs: use nofs when cleaning up aborted transactions commit 597441b3436a43011f31ce71dc0a6c0bf5ce958a upstream. Our CI system caught a lockdep splat: ====================================================== WARNING: possible circular locking dependency detected 6.3.0-rc7+ #1167 Not tainted ------------------------------------------------------ kswapd0/46 is trying to acquire lock: ffff8c6543abd650 (sb_internal#2){++++}-{0:0}, at: btrfs_commit_inode_delayed_inode+0x5f/0x120 but task is already holding lock: ffffffffabe61b40 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat+0x4aa/0x7a0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (fs_reclaim){+.+.}-{0:0}: fs_reclaim_acquire+0xa5/0xe0 kmem_cache_alloc+0x31/0x2c0 alloc_extent_state+0x1d/0xd0 __clear_extent_bit+0x2e0/0x4f0 try_release_extent_mapping+0x216/0x280 btrfs_release_folio+0x2e/0x90 invalidate_inode_pages2_range+0x397/0x470 btrfs_cleanup_dirty_bgs+0x9e/0x210 btrfs_cleanup_one_transaction+0x22/0x760 btrfs_commit_transaction+0x3b7/0x13a0 create_subvol+0x59b/0x970 btrfs_mksubvol+0x435/0x4f0 __btrfs_ioctl_snap_create+0x11e/0x1b0 btrfs_ioctl_snap_create_v2+0xbf/0x140 btrfs_ioctl+0xa45/0x28f0 __x64_sys_ioctl+0x88/0xc0 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc -> #0 (sb_internal#2){++++}-{0:0}: __lock_acquire+0x1435/0x21a0 lock_acquire+0xc2/0x2b0 start_transaction+0x401/0x730 btrfs_commit_inode_delayed_inode+0x5f/0x120 btrfs_evict_inode+0x292/0x3d0 evict+0xcc/0x1d0 inode_lru_isolate+0x14d/0x1e0 __list_lru_walk_one+0xbe/0x1c0 list_lru_walk_one+0x58/0x80 prune_icache_sb+0x39/0x60 super_cache_scan+0x161/0x1f0 do_shrink_slab+0x163/0x340 shrink_slab+0x1d3/0x290 shrink_node+0x300/0x720 balance_pgdat+0x35c/0x7a0 kswapd+0x205/0x410 kthread+0xf0/0x120 ret_from_fork+0x29/0x50 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(fs_reclaim); lock(sb_internal#2); lock(fs_reclaim); lock(sb_internal#2); *** DEADLOCK *** 3 locks held by kswapd0/46: #0: ffffffffabe61b40 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat+0x4aa/0x7a0 #1: ffffffffabe50270 (shrinker_rwsem){++++}-{3:3}, at: shrink_slab+0x113/0x290 #2: ffff8c6543abd0e0 (&type->s_umount_key#44){++++}-{3:3}, at: super_cache_scan+0x38/0x1f0 stack backtrace: CPU: 0 PID: 46 Comm: kswapd0 Not tainted 6.3.0-rc7+ #1167 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 Call Trace: dump_stack_lvl+0x58/0x90 check_noncircular+0xd6/0x100 ? save_trace+0x3f/0x310 ? add_lock_to_list+0x97/0x120 __lock_acquire+0x1435/0x21a0 lock_acquire+0xc2/0x2b0 ? btrfs_commit_inode_delayed_inode+0x5f/0x120 start_transaction+0x401/0x730 ? btrfs_commit_inode_delayed_inode+0x5f/0x120 btrfs_commit_inode_delayed_inode+0x5f/0x120 btrfs_evict_inode+0x292/0x3d0 ? lock_release+0x134/0x270 ? __pfx_wake_bit_function+0x10/0x10 evict+0xcc/0x1d0 inode_lru_isolate+0x14d/0x1e0 __list_lru_walk_one+0xbe/0x1c0 ? __pfx_inode_lru_isolate+0x10/0x10 ? __pfx_inode_lru_isolate+0x10/0x10 list_lru_walk_one+0x58/0x80 prune_icache_sb+0x39/0x60 super_cache_scan+0x161/0x1f0 do_shrink_slab+0x163/0x340 shrink_slab+0x1d3/0x290 shrink_node+0x300/0x720 balance_pgdat+0x35c/0x7a0 kswapd+0x205/0x410 ? __pfx_autoremove_wake_function+0x10/0x10 ? __pfx_kswapd+0x10/0x10 kthread+0xf0/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x29/0x50 This happens because when we abort the transaction in the transaction commit path we call invalidate_inode_pages2_range on our block group cache inodes (if we have space cache v1) and any delalloc inodes we may have. The plain invalidate_inode_pages2_range() call passes through GFP_KERNEL, which makes sense in most cases, but not here. Wrap these two invalidate callees with memalloc_nofs_save/memalloc_nofs_restore to make sure we don't end up with the fs reclaim dependency under the transaction dependency. CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 095c9e4f9224..60b7a227624d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4535,7 +4535,11 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) */ inode = igrab(&btrfs_inode->vfs_inode); if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); iput(inode); } spin_lock(&root->delalloc_lock); @@ -4640,7 +4644,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) inode = cache->io_ctl.inode; if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); + BTRFS_I(inode)->generation = 0; cache->io_ctl.inode = NULL; iput(inode); From 628d7e4941345611696fff79ebc31444658e3275 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Mon, 15 May 2023 12:20:52 -0400 Subject: [PATCH 3240/4345] dt-binding: cdns,usb3: Fix cdns,on-chip-buff-size type commit 50a1726b148ff30778cb8a6cf3736130b07c93fd upstream. In cdns3-gadget.c, 'cdns,on-chip-buff-size' was read using device_property_read_u16(). It resulted in 0 if a 32bit value was used in dts. This commit fixes the dt binding doc to declare it as u16. Cc: stable@vger.kernel.org Fixes: 68989fe1c39d ("dt-bindings: usb: Convert cdns-usb3.txt to YAML schema") Signed-off-by: Frank Li Reviewed-by: Krzysztof Kozlowski Signed-off-by: Shawn Guo Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/cdns,usb3.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml index d6af2794d444..703921e6bcaf 100644 --- a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml +++ b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml @@ -59,7 +59,7 @@ properties: description: size of memory intended as internal memory for endpoints buffers expressed in KB - $ref: /schemas/types.yaml#/definitions/uint32 + $ref: /schemas/types.yaml#/definitions/uint16 cdns,phyrst-a-enable: description: Enable resetting of PHY if Rx fail is detected From d4a5e6ae996792cdcd20a373a1ceca72253e9bf9 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 16 May 2023 12:24:25 -0700 Subject: [PATCH 3241/4345] x86/mm: Avoid incomplete Global INVLPG flushes commit ce0b15d11ad837fbacc5356941712218e38a0a83 upstream. The INVLPG instruction is used to invalidate TLB entries for a specified virtual address. When PCIDs are enabled, INVLPG is supposed to invalidate TLB entries for the specified address for both the current PCID *and* Global entries. (Note: Only kernel mappings set Global=1.) Unfortunately, some INVLPG implementations can leave Global translations unflushed when PCIDs are enabled. As a workaround, never enable PCIDs on affected processors. I expect there to eventually be microcode mitigations to replace this software workaround. However, the exact version numbers where that will happen are not known today. Once the version numbers are set in stone, the processor list can be tweaked to only disable PCIDs on affected processors with affected microcode. Note: if anyone wants a quick fix that doesn't require patching, just stick 'nopcid' on your kernel command-line. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: stable@vger.kernel.org Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/intel-family.h | 5 +++++ arch/x86/mm/init.c | 25 +++++++++++++++++++++++++ 2 files changed, 30 insertions(+) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 9abe842dbd84..14b52718917f 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -98,6 +98,11 @@ #define INTEL_FAM6_LAKEFIELD 0x8A #define INTEL_FAM6_ALDERLAKE 0x97 #define INTEL_FAM6_ALDERLAKE_L 0x9A +#define INTEL_FAM6_ALDERLAKE_N 0xBE + +#define INTEL_FAM6_RAPTORLAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE_P 0xBA +#define INTEL_FAM6_RAPTORLAKE_S 0xBF /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 63d8c6c7d125..ff3b0d8fe048 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -254,6 +255,24 @@ static void __init probe_page_size_mask(void) } } +#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \ + .family = 6, \ + .model = _model, \ + } +/* + * INVLPG may not properly flush Global entries + * on these CPUs when PCIDs are enabled. + */ +static const struct x86_cpu_id invlpg_miss_ids[] = { + INTEL_MATCH(INTEL_FAM6_ALDERLAKE ), + INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ), + INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S), + {} +}; + static void setup_pcid(void) { if (!IS_ENABLED(CONFIG_X86_64)) @@ -262,6 +281,12 @@ static void setup_pcid(void) if (!boot_cpu_has(X86_FEATURE_PCID)) return; + if (x86_match_cpu(invlpg_miss_ids)) { + pr_info("Incomplete global flushes, disabling PCID"); + setup_clear_cpu_cap(X86_FEATURE_PCID); + return; + } + if (boot_cpu_has(X86_FEATURE_PGE)) { /* * This can't be cr4_set_bits_and_update_boot() -- the From 2d78438c31837471a14cffb63a44a6a99f05247e Mon Sep 17 00:00:00 2001 From: Hardik Garg Date: Fri, 26 May 2023 16:21:36 -0700 Subject: [PATCH 3242/4345] selftests/memfd: Fix unknown type name build failure Partially backport v6.3 commit 11f75a01448f ("selftests/memfd: add tests for MFD_NOEXEC_SEAL MFD_EXEC") to fix an unknown type name build error. In some systems, the __u64 typedef is not present due to differences in system headers, causing compilation errors like this one: fuse_test.c:64:8: error: unknown type name '__u64' 64 | static __u64 mfd_assert_get_seals(int fd) This header includes the __u64 typedef which increases the likelihood of successful compilation on a wider variety of systems. Signed-off-by: Hardik Garg Reviewed-by: Tyler Hicks (Microsoft) Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/memfd/fuse_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c index b018e835737d..cda63164d9d3 100644 --- a/tools/testing/selftests/memfd/fuse_test.c +++ b/tools/testing/selftests/memfd/fuse_test.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include From 518c39fc1ed6d34aa4a6d4a6f48101f88aeda60c Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 24 May 2023 17:07:07 +0200 Subject: [PATCH 3243/4345] parisc: Fix flush_dcache_page() for usage from irq context commit 61e150fb310729c98227a5edf6e4a3619edc3702 upstream. Since at least kernel 6.1, flush_dcache_page() is called with IRQs disabled, e.g. from aio_complete(). But the current implementation for flush_dcache_page() on parisc unintentionally re-enables IRQs, which may lead to deadlocks. Fix it by using xa_lock_irqsave() and xa_unlock_irqrestore() for the flush_dcache_mmap_*lock() macros instead. Cc: linux-parisc@vger.kernel.org Cc: stable@kernel.org # 5.18+ Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/include/asm/cacheflush.h | 5 +++++ arch/parisc/kernel/cache.c | 5 +++-- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 99663fc1f997..cc9d096d5cc4 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -57,6 +57,11 @@ extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) +#define flush_dcache_mmap_lock_irqsave(mapping, flags) \ + xa_lock_irqsave(&mapping->i_pages, flags) +#define flush_dcache_mmap_unlock_irqrestore(mapping, flags) \ + xa_unlock_irqrestore(&mapping->i_pages, flags) + #define flush_icache_page(vma,page) do { \ flush_kernel_dcache_page(page); \ diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index c81ab0cb8925..efa8d2a678a3 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -327,6 +327,7 @@ void flush_dcache_page(struct page *page) struct vm_area_struct *mpnt; unsigned long offset; unsigned long addr, old_addr = 0; + unsigned long flags; pgoff_t pgoff; if (mapping && !mapping_mapped(mapping)) { @@ -346,7 +347,7 @@ void flush_dcache_page(struct page *page) * declared as MAP_PRIVATE or MAP_SHARED), so we only need * to flush one address here for them all to become coherent */ - flush_dcache_mmap_lock(mapping); + flush_dcache_mmap_lock_irqsave(mapping, flags); vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT; addr = mpnt->vm_start + offset; @@ -369,7 +370,7 @@ void flush_dcache_page(struct page *page) old_addr = addr; } } - flush_dcache_mmap_unlock(mapping); + flush_dcache_mmap_unlock_irqrestore(mapping, flags); } EXPORT_SYMBOL(flush_dcache_page); From a12ce786bef647ccd6580fdb1277a36ecb92124d Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Thu, 23 Mar 2023 09:56:40 +0800 Subject: [PATCH 3244/4345] x86/topology: Fix erroneous smp_num_siblings on Intel Hybrid platforms commit edc0a2b5957652f4685ef3516f519f84807087db upstream. Traditionally, all CPUs in a system have identical numbers of SMT siblings. That changes with hybrid processors where some logical CPUs have a sibling and others have none. Today, the CPU boot code sets the global variable smp_num_siblings when every CPU thread is brought up. The last thread to boot will overwrite it with the number of siblings of *that* thread. That last thread to boot will "win". If the thread is a Pcore, smp_num_siblings == 2. If it is an Ecore, smp_num_siblings == 1. smp_num_siblings describes if the *system* supports SMT. It should specify the maximum number of SMT threads among all cores. Ensure that smp_num_siblings represents the system-wide maximum number of siblings by always increasing its value. Never allow it to decrease. On MeteorLake-P platform, this fixes a problem that the Ecore CPUs are not updated in any cpu sibling map because the system is treated as an UP system when probing Ecore CPUs. Below shows part of the CPU topology information before and after the fix, for both Pcore and Ecore CPU (cpu0 is Pcore, cpu 12 is Ecore). ... -/sys/devices/system/cpu/cpu0/topology/package_cpus:000fff -/sys/devices/system/cpu/cpu0/topology/package_cpus_list:0-11 +/sys/devices/system/cpu/cpu0/topology/package_cpus:3fffff +/sys/devices/system/cpu/cpu0/topology/package_cpus_list:0-21 ... -/sys/devices/system/cpu/cpu12/topology/package_cpus:001000 -/sys/devices/system/cpu/cpu12/topology/package_cpus_list:12 +/sys/devices/system/cpu/cpu12/topology/package_cpus:3fffff +/sys/devices/system/cpu/cpu12/topology/package_cpus_list:0-21 Notice that the "before" 'package_cpus_list' has only one CPU. This means that userspace tools like lscpu will see a little laptop like an 11-socket system: -Core(s) per socket: 1 -Socket(s): 11 +Core(s) per socket: 16 +Socket(s): 1 This is also expected to make the scheduler do rather wonky things too. [ dhansen: remove CPUID detail from changelog, add end user effects ] CC: stable@kernel.org Fixes: bbb65d2d365e ("x86: use cpuid vector 0xb when available for detecting cpu topology") Fixes: 95f3d39ccf7a ("x86/cpu/topology: Provide detect_extended_topology_early()") Suggested-by: Len Brown Signed-off-by: Zhang Rui Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230323015640.27906-1-rui.zhang%40intel.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/topology.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 37d48ab3d077..58d17c01d459 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -79,7 +79,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c) * initial apic id, which also represents 32-bit extended x2apic id. */ c->initial_apicid = edx; - smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); #endif return 0; } @@ -109,7 +109,8 @@ int detect_extended_topology(struct cpuinfo_x86 *c) */ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); c->initial_apicid = edx; - core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); From fd673079749bac97bb30f1461df079e6c8e86511 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Thu, 11 May 2023 22:47:32 +0900 Subject: [PATCH 3245/4345] debugobjects: Don't wake up kswapd from fill_pool() commit eb799279fb1f9c63c520fe8c1c41cb9154252db6 upstream. syzbot is reporting a lockdep warning in fill_pool() because the allocation from debugobjects is using GFP_ATOMIC, which is (__GFP_HIGH | __GFP_KSWAPD_RECLAIM) and therefore tries to wake up kswapd, which acquires kswapd_wait::lock. Since fill_pool() might be called with arbitrary locks held, fill_pool() should not assume that acquiring kswapd_wait::lock is safe. Use __GFP_HIGH instead and remove __GFP_NORETRY as it is pointless for !__GFP_DIRECT_RECLAIM allocation. Fixes: 3ac7fe5a4aab ("infrastructure to debug (dynamic) objects") Reported-by: syzbot Signed-off-by: Tetsuo Handa Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/6577e1fa-b6ee-f2be-2414-a2b51b1c5e30@I-love.SAKURA.ne.jp Closes: https://syzkaller.appspot.com/bug?extid=fe0c72f0ccbb93786380 Signed-off-by: Greg Kroah-Hartman --- lib/debugobjects.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 824337ec36aa..4c39678c03ee 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -129,7 +129,7 @@ static const char *obj_states[ODEBUG_STATE_MAX] = { static void fill_pool(void) { - gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; + gfp_t gfp = __GFP_HIGH | __GFP_NOWARN; struct debug_obj *obj; unsigned long flags; From 58ecc165abdaed85447455e6dc396758e8c6f219 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 19 May 2023 15:32:30 -0400 Subject: [PATCH 3246/4345] fbdev: udlfb: Fix endpoint check commit ed9de4ed39875706607fb08118a58344ae6c5f42 upstream. The syzbot fuzzer detected a problem in the udlfb driver, caused by an endpoint not having the expected type: usb 1-1: Read EDID byte 0 failed: -71 usb 1-1: Unable to get valid EDID from device/display ------------[ cut here ]------------ usb 1-1: BOGUS urb xfer, pipe 3 != type 1 WARNING: CPU: 0 PID: 9 at drivers/usb/core/urb.c:504 usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 Modules linked in: CPU: 0 PID: 9 Comm: kworker/0:1 Not tainted 6.4.0-rc1-syzkaller-00016-ga4422ff22142 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/28/2023 Workqueue: usb_hub_wq hub_event RIP: 0010:usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 ... Call Trace: dlfb_submit_urb+0x92/0x180 drivers/video/fbdev/udlfb.c:1980 dlfb_set_video_mode+0x21f0/0x2950 drivers/video/fbdev/udlfb.c:315 dlfb_ops_set_par+0x2a7/0x8d0 drivers/video/fbdev/udlfb.c:1111 dlfb_usb_probe+0x149a/0x2710 drivers/video/fbdev/udlfb.c:1743 The current approach for this issue failed to catch the problem because it only checks for the existence of a bulk-OUT endpoint; it doesn't check whether this endpoint is the one that the driver will actually use. We can fix the problem by instead checking that the endpoint used by the driver does exist and is bulk-OUT. Reported-and-tested-by: syzbot+0e22d63dcebb802b9bc8@syzkaller.appspotmail.com Signed-off-by: Alan Stern CC: Pavel Skripkin Fixes: aaf7dbe07385 ("video: fbdev: udlfb: properly check endpoint type") Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/udlfb.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index d9eec1b60e66..0de7b867714a 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -27,6 +27,8 @@ #include page_pool_put_defragged_page+0x267/0x320 mlx5e_free_xdpsq_desc+0x99/0xd0 mlx5e_poll_xdpsq_cq+0x138/0x3b0 mlx5e_napi_poll+0xc3/0x8b0 netpoll_poll_dev+0xce/0x150 AFAIU page pool takes a BH lock, releases it and since BH is now enabled tries to run softirqs. Reviewed-by: Tariq Toukan Fixes: 60bbf7eeef10 ("mlx5: use page_pool for xdp_return_frame call") Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- .../net/ethernet/mellanox/mlx5/core/en_txrx.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index d5868670f8a5..53ac2383327e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -137,20 +137,22 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) for (i = 0; i < c->num_tc; i++) busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget); + /* budget=0 means we may be in IRQ context, do as little as possible */ + if (unlikely(!budget)) + goto out; + busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq); if (c->xdp) busy |= mlx5e_poll_xdpsq_cq(&c->rq_xdpsq.cq); - if (likely(budget)) { /* budget=0 means: don't poll rx rings */ - if (xsk_open) - work_done = mlx5e_poll_rx_cq(&xskrq->cq, budget); + if (xsk_open) + work_done = mlx5e_poll_rx_cq(&xskrq->cq, budget); - if (likely(budget - work_done)) - work_done += mlx5e_poll_rx_cq(&rq->cq, budget - work_done); + if (likely(budget - work_done)) + work_done += mlx5e_poll_rx_cq(&rq->cq, budget - work_done); - busy |= work_done == budget; - } + busy |= work_done == budget; mlx5e_poll_ico_cq(&c->icosq.cq); if (mlx5e_poll_ico_cq(&c->async_icosq.cq)) From c21862232f6cd1437e2c7531eec196a593c1d9ae Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Thu, 9 Mar 2023 16:43:15 +0200 Subject: [PATCH 3269/4345] net/mlx5: DR, Fix crc32 calculation to work on big-endian (BE) CPUs commit 1e5daf5565b61a96e570865091589afc9156e3d3 upstream. When calculating crc for hash index we use the function crc32 that calculates for little-endian (LE) arch. Then we convert it to network endianness using htonl(), but it's wrong to do the conversion in BE archs since the crc32 value is already LE. The solution is to switch the bytes from the crc result for all types of arc. Fixes: 40416d8ede65 ("net/mlx5: DR, Replace CRC32 implementation to use kernel lib") Signed-off-by: Erez Shitrit Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index b01aaec75622..3b5deb0fe7eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -112,7 +112,8 @@ static u32 dr_ste_crc32_calc(const void *input_data, size_t length) { u32 crc = crc32(0, input_data, length); - return (__force u32)htonl(crc); + return (__force u32)((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) | + ((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000); } u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl) From 8b9c561b9fc186a623982eb9fdd5fa58e48ccf47 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Mon, 1 May 2023 14:37:56 +0300 Subject: [PATCH 3270/4345] net/mlx5: Fix error message when failing to allocate device memory commit a65735148e0328f80c0f72f9f8d2f609bfcf4aff upstream. Fix spacing for the error and also the correct error code pointer. Fixes: c9b9dcb430b3 ("net/mlx5: Move device memory management to mlx5_core") Signed-off-by: Roi Dayan Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 112eaef186e1..da4ca0f67e9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -887,7 +887,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) dev->dm = mlx5_dm_create(dev); if (IS_ERR(dev->dm)) - mlx5_core_warn(dev, "Failed to init device memory%d\n", err); + mlx5_core_warn(dev, "Failed to init device memory %ld\n", PTR_ERR(dev->dm)); dev->tracer = mlx5_fw_tracer_create(dev); dev->hv_vhca = mlx5_hv_vhca_create(dev); From d4d10a6df1529b3f446cdada5c25e065f4712756 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 2 May 2023 13:35:11 +0300 Subject: [PATCH 3271/4345] net/mlx5: Devcom, fix error flow in mlx5_devcom_register_device commit af87194352cad882d787d06fb7efa714acd95427 upstream. In case devcom allocation is failed, mlx5 is always freeing the priv. However, this priv might have been allocated by a different thread, and freeing it might lead to use-after-free bugs. Fix it by freeing the priv only in case it was allocated by the running thread. Fixes: fadd59fc50d0 ("net/mlx5: Introduce inter-device communication mechanism") Signed-off-by: Shay Drory Signed-off-by: Saeed Mahameed Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index bced2efe9bef..abd066e95228 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -110,7 +110,8 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) priv->devs[idx] = dev; devcom = mlx5_devcom_alloc(priv, idx); if (!devcom) { - kfree(priv); + if (new_priv) + kfree(priv); return ERR_PTR(-ENOMEM); } From 6f449e409b75181f5b16302cbd7466649757e014 Mon Sep 17 00:00:00 2001 From: Hugo Villeneuve Date: Mon, 1 May 2023 13:05:32 -0400 Subject: [PATCH 3272/4345] arm64: dts: imx8mn-var-som: fix PHY detection bug by adding deassert delay commit f161cea5a20f3aeeb637a88ad1705fc2720b4d58 upstream. While testing the ethernet interface on a Variscite symphony carrier board using an imx8mn SOM with an onboard ADIN1300 PHY (EC hardware configuration), the ethernet PHY is not detected. The ADIN1300 datasheet indicate that the "Management interface active (t4)" state is reached at most 5ms after the reset signal is deasserted. The device tree in Variscite custom git repository uses the following property: phy-reset-post-delay = <20>; Add a new MDIO property 'reset-deassert-us' of 20ms to have the same delay inside the ethphy node. Adding this property fixes the problem with the PHY detection. Note that this SOM can also have an Atheros AR8033 PHY. In this case, a 1ms deassert delay is sufficient. Add a comment to that effect. Fixes: ade0176dd8a0 ("arm64: dts: imx8mn-var-som: Add Variscite VAR-SOM-MX8MN System on Module") Signed-off-by: Hugo Villeneuve Signed-off-by: Shawn Guo Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index f6287f174355..24f9e8fd0c8b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -98,11 +98,17 @@ #address-cells = <1>; #size-cells = <0>; - ethphy: ethernet-phy@4 { + ethphy: ethernet-phy@4 { /* AR8033 or ADIN1300 */ compatible = "ethernet-phy-ieee802.3-c22"; reg = <4>; reset-gpios = <&gpio1 9 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; + /* + * Deassert delay: + * ADIN1300 requires 5ms. + * AR8033 requires 1ms. + */ + reset-deassert-us = <20000>; }; }; }; From 98cedb991094824e4bc764f86a6716c8c47254bd Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 20 May 2023 11:48:55 +0200 Subject: [PATCH 3273/4345] 3c589_cs: Fix an error handling path in tc589_probe() commit 640bf95b2c7c2981fb471acdafbd3e0458f8390d upstream. Should tc589_config() fail, some resources need to be released as already done in the remove function. Fixes: 15b99ac17295 ("[PATCH] pcmcia: add return value to _config() functions") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/d8593ae867b24c79063646e36f9b18b0790107cb.1684575975.git.christophe.jaillet@wanadoo.fr Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/3com/3c589_cs.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index 09816e84314d..0197ef6f1582 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -195,6 +195,7 @@ static int tc589_probe(struct pcmcia_device *link) { struct el3_private *lp; struct net_device *dev; + int ret; dev_dbg(&link->dev, "3c589_attach()\n"); @@ -218,7 +219,15 @@ static int tc589_probe(struct pcmcia_device *link) dev->ethtool_ops = &netdev_ethtool_ops; - return tc589_config(link); + ret = tc589_config(link); + if (ret) + goto err_free_netdev; + + return 0; + +err_free_netdev: + free_netdev(dev); + return ret; } static void tc589_detach(struct pcmcia_device *link) From cf7ee4b15838afe7b16b5a88e3e8acf4e841e8d3 Mon Sep 17 00:00:00 2001 From: David Epping Date: Tue, 23 May 2023 17:31:05 +0200 Subject: [PATCH 3274/4345] net: phy: mscc: add VSC8502 to MODULE_DEVICE_TABLE commit 57fb54ab9f6945e204740b696bd4cee61ee04e5e upstream. The mscc driver implements support for VSC8502, so its ID should be in the MODULE_DEVICE_TABLE for automatic loading. Signed-off-by: David Epping Fixes: d3169863310d ("net: phy: mscc: add support for VSC8502") Reviewed-by: Vladimir Oltean Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/mscc/mscc_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index e14fa72791b0..ffac713afa55 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -2563,6 +2563,7 @@ static struct phy_driver vsc85xx_driver[] = { module_phy_driver(vsc85xx_driver); static struct mdio_device_id __maybe_unused vsc85xx_tbl[] = { + { PHY_ID_VSC8502, 0xfffffff0, }, { PHY_ID_VSC8504, 0xfffffff0, }, { PHY_ID_VSC8514, 0xfffffff0, }, { PHY_ID_VSC8530, 0xfffffff0, }, From 272d4b8a5b96dda1374b9039a884cce2cd9cb630 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 30 May 2023 12:57:59 +0100 Subject: [PATCH 3275/4345] Linux 5.10.181 Link: https://lore.kernel.org/r/20230528190843.514829708@linuxfoundation.org Tested-by: Guenter Roeck Tested-by: Linux Kernel Functional Testing Tested-by: Jon Hunter Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index c2f8e1644abd..4e8289113a81 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 180 +SUBLEVEL = 181 EXTRAVERSION = NAME = Dare mighty things From a4420dc21f4051ba0584e02535e2bfc6abe52fa9 Mon Sep 17 00:00:00 2001 From: Weichao Guo Date: Sat, 7 May 2022 00:28:14 +0800 Subject: [PATCH 3276/4345] BACKPORT: f2fs: skip GC if possible when checkpoint disabling If the number of unusable blocks is not larger than unusable capacity, we can skip GC when checkpoint disabling. Bug: 278486610 Signed-off-by: Weichao Guo Signed-off-by: Chao Yu [Jaegeuk Kim: Fix missing gc_mode assignment] Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim (cherry picked from commit 2880f47b949f1f49e2d861ffbba91d57416be7d9) [ qixiaoyu1: Resolved minor conflict in fs/f2fs/super.c ] Change-Id: Ic37debb3fbb9d863cb1b0f539cc992dd08ad9f77 --- fs/f2fs/super.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 2c77a2df34a6..268bdd61f2d0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1995,6 +1995,11 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) } sbi->sb->s_flags |= SB_ACTIVE; + /* check if we need more GC first */ + unusable = f2fs_get_unusable_blocks(sbi); + if (!f2fs_disable_cp_again(sbi, unusable)) + goto skip_gc; + f2fs_update_time(sbi, DISABLE_TIME); while (!f2fs_time_over(sbi, DISABLE_TIME)) { @@ -2020,6 +2025,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) goto restore_flag; } +skip_gc: f2fs_down_write(&sbi->gc_lock); cpc.reason = CP_PAUSE; set_sbi_flag(sbi, SBI_CP_DISABLED); From 4a8980cb2a7cb48371af67df4e6d70352b991ab0 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Fri, 12 Nov 2021 10:28:35 -0800 Subject: [PATCH 3277/4345] x86/cpu: Add Raptor Lake to Intel family [ Upstream commit fbdb5e8f2926ae9636c9fa6f42c7426132ddeeb2 ] Add model ID for Raptor Lake. [ dhansen: These get added as soon as possible so that folks doing development can leverage them. ] Signed-off-by: Tony Luck Signed-off-by: Dave Hansen Link: https://lkml.kernel.org/r/20211112182835.924977-1-tony.luck@intel.com Stable-dep-of: ce0b15d11ad8 ("x86/mm: Avoid incomplete Global INVLPG flushes") Signed-off-by: Sasha Levin --- arch/x86/include/asm/intel-family.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 14b52718917f..7a602d79bc38 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -104,6 +104,8 @@ #define INTEL_FAM6_RAPTORLAKE_P 0xBA #define INTEL_FAM6_RAPTORLAKE_S 0xBF +#define INTEL_FAM6_RAPTOR_LAKE 0xB7 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ From 18c9cf46333797d5d71f0fd51611b7af8de99048 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Fri, 19 Nov 2021 09:08:32 -0800 Subject: [PATCH 3278/4345] x86/cpu: Drop spurious underscore from RAPTOR_LAKE #define [ Upstream commit 7d697f0d5737768fa1039b8953b67c08d8d406d1 ] Convention for all the other "lake" CPUs is all one word. So s/RAPTOR_LAKE/RAPTORLAKE/ Fixes: fbdb5e8f2926 ("x86/cpu: Add Raptor Lake to Intel family") Reported-by: Rui Zhang Signed-off-by: Tony Luck Signed-off-by: Dave Hansen Link: https://lkml.kernel.org/r/20211119170832.1034220-1-tony.luck@intel.com Stable-dep-of: ce0b15d11ad8 ("x86/mm: Avoid incomplete Global INVLPG flushes") Signed-off-by: Sasha Levin --- arch/x86/include/asm/intel-family.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 7a602d79bc38..0de49e33d422 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -104,7 +104,7 @@ #define INTEL_FAM6_RAPTORLAKE_P 0xBA #define INTEL_FAM6_RAPTORLAKE_S 0xBF -#define INTEL_FAM6_RAPTOR_LAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE 0xB7 /* "Small Core" Processors (Atom) */ From 14e1a958d9884e15101b42cbdde8e644a04ed7a3 Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Fri, 4 Dec 2020 15:49:50 +0100 Subject: [PATCH 3279/4345] power: supply: bq27xxx: fix polarity of current_now [ Upstream commit cd060b4d0868c806c2738a5e64e8ab9bd0fbec07 ] current_now has to be negative during discharging and positive during charging, the behavior seen is the other way round. Tested on GTA04 with Openmoko battery. Signed-off-by: Andreas Kemnade Signed-off-by: Sebastian Reichel Stable-dep-of: 35092c5819f8 ("power: supply: bq27xxx: Add cache parameter to bq27xxx_battery_current_and_status()") Signed-off-by: Sasha Levin --- drivers/power/supply/bq27xxx_battery.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index c08dd4e6d35a..79eee63a2041 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1773,7 +1773,7 @@ static int bq27xxx_battery_current(struct bq27xxx_device_info *di, if (di->opts & BQ27XXX_O_ZERO) { flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, true); - if (flags & BQ27000_FLAG_CHGS) { + if (!(flags & BQ27000_FLAG_CHGS)) { dev_dbg(di->dev, "negative current!\n"); curr = -curr; } @@ -1781,7 +1781,7 @@ static int bq27xxx_battery_current(struct bq27xxx_device_info *di, val->intval = curr * BQ27XXX_CURRENT_CONSTANT / BQ27XXX_RS; } else { /* Other gauges return signed value */ - val->intval = (int)((s16)curr) * 1000; + val->intval = -(int)((s16)curr) * 1000; } return 0; From 659094e4057ab1b8d3b162b721ea2bd3fe64e30c Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Wed, 3 Mar 2021 10:54:18 +0100 Subject: [PATCH 3280/4345] power: supply: bq27xxx: fix sign of current_now for newer ICs [ Upstream commit b67fdcb7099e9c640bad625c4dd6399debb3376a ] Commit cd060b4d0868 ("power: supply: bq27xxx: fix polarity of current_now") changed the sign of current_now for all bq27xxx variants, but on BQ28Z610 I'm now seeing negated values *with* that patch. The GTA04/Openmoko device that was used for testing uses a BQ27000 or BQ27010 IC, so I assume only the BQ27XXX_O_ZERO code path was incorrect. Revert the behaviour for newer ICs. Fixes: cd060b4d0868 "power: supply: bq27xxx: fix polarity of current_now" Signed-off-by: Matthias Schiffer Signed-off-by: Sebastian Reichel Stable-dep-of: 35092c5819f8 ("power: supply: bq27xxx: Add cache parameter to bq27xxx_battery_current_and_status()") Signed-off-by: Sasha Levin --- drivers/power/supply/bq27xxx_battery.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 79eee63a2041..d34f1fceadbb 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1781,7 +1781,7 @@ static int bq27xxx_battery_current(struct bq27xxx_device_info *di, val->intval = curr * BQ27XXX_CURRENT_CONSTANT / BQ27XXX_RS; } else { /* Other gauges return signed value */ - val->intval = -(int)((s16)curr) * 1000; + val->intval = (int)((s16)curr) * 1000; } return 0; From 432f98c559f20950872a666b1eaba1acc49a833b Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Wed, 3 Mar 2021 10:54:20 +0100 Subject: [PATCH 3281/4345] power: supply: bq27xxx: make status more robust [ Upstream commit c3a6d6a1dfc8a9bf12d79a0b1a30cb24c92a2ddf ] There are multiple issues in bq27xxx_battery_status(): - On BQ28Q610 is was observed that the "full" flag may be set even while the battery is charging or discharging. With the current logic to make "full" override everything else, it look a very long time (>20min) for the status to change from "full" to "discharging" after unplugging the supply on a device with low power consumption - The POWER_SUPPLY_STATUS_NOT_CHARGING check depends on power_supply_am_i_supplied(), which will not work when the supply doesn't exist as a separate device known to Linux We can solve both issues by deriving the status from the current instead of the flags field. The flags are now only used to distinguish "full" from "not charging", and to determine the sign of the current on BQ27XXX_O_ZERO devices. Signed-off-by: Matthias Schiffer Signed-off-by: Sebastian Reichel Stable-dep-of: 35092c5819f8 ("power: supply: bq27xxx: Add cache parameter to bq27xxx_battery_current_and_status()") Signed-off-by: Sasha Levin --- drivers/power/supply/bq27xxx_battery.c | 88 +++++++++++++------------- 1 file changed, 43 insertions(+), 45 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index d34f1fceadbb..681fa81f4dbd 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1754,14 +1754,27 @@ static void bq27xxx_battery_poll(struct work_struct *work) bq27xxx_battery_update(di); } +static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) +{ + if (di->opts & BQ27XXX_O_ZERO) + return (flags & BQ27000_FLAG_FC); + else if (di->opts & BQ27Z561_O_BITS) + return (flags & BQ27Z561_FLAG_FC); + else + return (flags & BQ27XXX_FLAG_FC); +} + /* - * Return the battery average current in µA + * Return the battery average current in µA and the status * Note that current can be negative signed as well * Or 0 if something fails. */ -static int bq27xxx_battery_current(struct bq27xxx_device_info *di, - union power_supply_propval *val) +static int bq27xxx_battery_current_and_status( + struct bq27xxx_device_info *di, + union power_supply_propval *val_curr, + union power_supply_propval *val_status) { + bool single_flags = (di->opts & BQ27XXX_O_ZERO); int curr; int flags; @@ -1771,17 +1784,39 @@ static int bq27xxx_battery_current(struct bq27xxx_device_info *di, return curr; } + flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, single_flags); + if (flags < 0) { + dev_err(di->dev, "error reading flags\n"); + return flags; + } + if (di->opts & BQ27XXX_O_ZERO) { - flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, true); if (!(flags & BQ27000_FLAG_CHGS)) { dev_dbg(di->dev, "negative current!\n"); curr = -curr; } - val->intval = curr * BQ27XXX_CURRENT_CONSTANT / BQ27XXX_RS; + curr = curr * BQ27XXX_CURRENT_CONSTANT / BQ27XXX_RS; } else { /* Other gauges return signed value */ - val->intval = (int)((s16)curr) * 1000; + curr = (int)((s16)curr) * 1000; + } + + if (val_curr) + val_curr->intval = curr; + + if (val_status) { + if (curr > 0) { + val_status->intval = POWER_SUPPLY_STATUS_CHARGING; + } else if (curr < 0) { + val_status->intval = POWER_SUPPLY_STATUS_DISCHARGING; + } else { + if (bq27xxx_battery_is_full(di, flags)) + val_status->intval = POWER_SUPPLY_STATUS_FULL; + else + val_status->intval = + POWER_SUPPLY_STATUS_NOT_CHARGING; + } } return 0; @@ -1813,43 +1848,6 @@ static int bq27xxx_battery_pwr_avg(struct bq27xxx_device_info *di, return 0; } -static int bq27xxx_battery_status(struct bq27xxx_device_info *di, - union power_supply_propval *val) -{ - int status; - - if (di->opts & BQ27XXX_O_ZERO) { - if (di->cache.flags & BQ27000_FLAG_FC) - status = POWER_SUPPLY_STATUS_FULL; - else if (di->cache.flags & BQ27000_FLAG_CHGS) - status = POWER_SUPPLY_STATUS_CHARGING; - else - status = POWER_SUPPLY_STATUS_DISCHARGING; - } else if (di->opts & BQ27Z561_O_BITS) { - if (di->cache.flags & BQ27Z561_FLAG_FC) - status = POWER_SUPPLY_STATUS_FULL; - else if (di->cache.flags & BQ27Z561_FLAG_DIS_CH) - status = POWER_SUPPLY_STATUS_DISCHARGING; - else - status = POWER_SUPPLY_STATUS_CHARGING; - } else { - if (di->cache.flags & BQ27XXX_FLAG_FC) - status = POWER_SUPPLY_STATUS_FULL; - else if (di->cache.flags & BQ27XXX_FLAG_DSC) - status = POWER_SUPPLY_STATUS_DISCHARGING; - else - status = POWER_SUPPLY_STATUS_CHARGING; - } - - if ((status == POWER_SUPPLY_STATUS_DISCHARGING) && - (power_supply_am_i_supplied(di->bat) > 0)) - status = POWER_SUPPLY_STATUS_NOT_CHARGING; - - val->intval = status; - - return 0; -} - static int bq27xxx_battery_capacity_level(struct bq27xxx_device_info *di, union power_supply_propval *val) { @@ -1935,7 +1933,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, switch (psp) { case POWER_SUPPLY_PROP_STATUS: - ret = bq27xxx_battery_status(di, val); + ret = bq27xxx_battery_current_and_status(di, NULL, val); break; case POWER_SUPPLY_PROP_VOLTAGE_NOW: ret = bq27xxx_battery_voltage(di, val); @@ -1944,7 +1942,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, val->intval = di->cache.flags < 0 ? 0 : 1; break; case POWER_SUPPLY_PROP_CURRENT_NOW: - ret = bq27xxx_battery_current(di, val); + ret = bq27xxx_battery_current_and_status(di, val, NULL); break; case POWER_SUPPLY_PROP_CAPACITY: ret = bq27xxx_simple_value(di->cache.capacity, val); From 7ff807d68b5d9db1071986e1043d9a63035053fe Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:35 +0200 Subject: [PATCH 3282/4345] power: supply: bq27xxx: Add cache parameter to bq27xxx_battery_current_and_status() [ Upstream commit 35092c5819f8c5acc7bafe3fdbb13d6307c4f5e1 ] Add a cache parameter to bq27xxx_battery_current_and_status() so that it can optionally use cached flags instead of re-reading them itself. This is a preparation patch for making bq27xxx_battery_update() check the status and have it call power_supply_changed() on status changes. Fixes: 297a533b3e62 ("bq27x00: Cache battery registers") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/bq27xxx_battery.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 681fa81f4dbd..d09ce7d6351d 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1772,7 +1772,8 @@ static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) static int bq27xxx_battery_current_and_status( struct bq27xxx_device_info *di, union power_supply_propval *val_curr, - union power_supply_propval *val_status) + union power_supply_propval *val_status, + struct bq27xxx_reg_cache *cache) { bool single_flags = (di->opts & BQ27XXX_O_ZERO); int curr; @@ -1784,10 +1785,14 @@ static int bq27xxx_battery_current_and_status( return curr; } - flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, single_flags); - if (flags < 0) { - dev_err(di->dev, "error reading flags\n"); - return flags; + if (cache) { + flags = cache->flags; + } else { + flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, single_flags); + if (flags < 0) { + dev_err(di->dev, "error reading flags\n"); + return flags; + } } if (di->opts & BQ27XXX_O_ZERO) { @@ -1933,7 +1938,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, switch (psp) { case POWER_SUPPLY_PROP_STATUS: - ret = bq27xxx_battery_current_and_status(di, NULL, val); + ret = bq27xxx_battery_current_and_status(di, NULL, val, NULL); break; case POWER_SUPPLY_PROP_VOLTAGE_NOW: ret = bq27xxx_battery_voltage(di, val); @@ -1942,7 +1947,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, val->intval = di->cache.flags < 0 ? 0 : 1; break; case POWER_SUPPLY_PROP_CURRENT_NOW: - ret = bq27xxx_battery_current_and_status(di, val, NULL); + ret = bq27xxx_battery_current_and_status(di, val, NULL, NULL); break; case POWER_SUPPLY_PROP_CAPACITY: ret = bq27xxx_simple_value(di->cache.capacity, val); From ed78797a264c9f16b2f836b23abec44498275d29 Mon Sep 17 00:00:00 2001 From: "Sicelo A. Mhlongo" Date: Wed, 20 Apr 2022 14:30:59 +0200 Subject: [PATCH 3283/4345] power: supply: bq27xxx: expose battery data when CI=1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 68fdbe090c362e8be23890a7333d156e18c27781 ] When the Capacity Inaccurate flag is set, the chip still provides data about the battery, albeit inaccurate. Instead of discarding capacity values for CI=1, expose the stale data and use the POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED property to indicate that the values should be used with care. Reviewed-by: Pali Rohár Signed-off-by: Sicelo A. Mhlongo Signed-off-by: Sebastian Reichel Stable-dep-of: ff4c4a2a4437 ("power: supply: bq27xxx: Move bq27xxx_battery_update() down") Signed-off-by: Sasha Levin --- drivers/power/supply/bq27xxx_battery.c | 58 ++++++++++++-------------- 1 file changed, 26 insertions(+), 32 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index d09ce7d6351d..bd6e53525065 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1507,14 +1507,6 @@ static int bq27xxx_battery_read_charge(struct bq27xxx_device_info *di, u8 reg) */ static inline int bq27xxx_battery_read_nac(struct bq27xxx_device_info *di) { - int flags; - - if (di->opts & BQ27XXX_O_ZERO) { - flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, true); - if (flags >= 0 && (flags & BQ27000_FLAG_CI)) - return -ENODATA; - } - return bq27xxx_battery_read_charge(di, BQ27XXX_REG_NAC); } @@ -1668,6 +1660,18 @@ static bool bq27xxx_battery_dead(struct bq27xxx_device_info *di, u16 flags) return flags & (BQ27XXX_FLAG_SOC1 | BQ27XXX_FLAG_SOCF); } +/* + * Returns true if reported battery capacity is inaccurate + */ +static bool bq27xxx_battery_capacity_inaccurate(struct bq27xxx_device_info *di, + u16 flags) +{ + if (di->opts & BQ27XXX_O_HAS_CI) + return (flags & BQ27000_FLAG_CI); + else + return false; +} + static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) { /* Unlikely but important to return first */ @@ -1677,6 +1681,8 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) return POWER_SUPPLY_HEALTH_COLD; if (unlikely(bq27xxx_battery_dead(di, di->cache.flags))) return POWER_SUPPLY_HEALTH_DEAD; + if (unlikely(bq27xxx_battery_capacity_inaccurate(di, di->cache.flags))) + return POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED; return POWER_SUPPLY_HEALTH_GOOD; } @@ -1684,7 +1690,6 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) { struct bq27xxx_reg_cache cache = {0, }; - bool has_ci_flag = di->opts & BQ27XXX_O_HAS_CI; bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); @@ -1692,30 +1697,19 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) cache.flags = -1; /* read error */ if (cache.flags >= 0) { cache.temperature = bq27xxx_battery_read_temperature(di); - if (has_ci_flag && (cache.flags & BQ27000_FLAG_CI)) { - dev_info_once(di->dev, "battery is not calibrated! ignoring capacity values\n"); - cache.capacity = -ENODATA; - cache.energy = -ENODATA; - cache.time_to_empty = -ENODATA; - cache.time_to_empty_avg = -ENODATA; - cache.time_to_full = -ENODATA; - cache.charge_full = -ENODATA; - cache.health = -ENODATA; - } else { - if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) - cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); - if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) - cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); - if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) - cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); + if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) + cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); + if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) + cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); + if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) + cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); - cache.charge_full = bq27xxx_battery_read_fcc(di); - cache.capacity = bq27xxx_battery_read_soc(di); - if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) - cache.energy = bq27xxx_battery_read_energy(di); - di->cache.flags = cache.flags; - cache.health = bq27xxx_battery_read_health(di); - } + cache.charge_full = bq27xxx_battery_read_fcc(di); + cache.capacity = bq27xxx_battery_read_soc(di); + if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) + cache.energy = bq27xxx_battery_read_energy(di); + di->cache.flags = cache.flags; + cache.health = bq27xxx_battery_read_health(di); if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) cache.cycle_count = bq27xxx_battery_read_cyct(di); From 6ed541254f4bdd5aca6ce8993587edecd48086cd Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:36 +0200 Subject: [PATCH 3284/4345] power: supply: bq27xxx: Move bq27xxx_battery_update() down [ Upstream commit ff4c4a2a4437a6d03787c7aafb2617f20c3ef45f ] Move the bq27xxx_battery_update() functions to below the bq27xxx_battery_current_and_status() function. This is just moving a block of text, no functional changes. This is a preparation patch for making bq27xxx_battery_update() check the status and have it call power_supply_changed() on status changes. Fixes: 297a533b3e62 ("bq27x00: Cache battery registers") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/bq27xxx_battery.c | 122 ++++++++++++------------- 1 file changed, 61 insertions(+), 61 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index bd6e53525065..160ab53065f8 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1687,67 +1687,6 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) return POWER_SUPPLY_HEALTH_GOOD; } -static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) -{ - struct bq27xxx_reg_cache cache = {0, }; - bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; - - cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); - if ((cache.flags & 0xff) == 0xff) - cache.flags = -1; /* read error */ - if (cache.flags >= 0) { - cache.temperature = bq27xxx_battery_read_temperature(di); - if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) - cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); - if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) - cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); - if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) - cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); - - cache.charge_full = bq27xxx_battery_read_fcc(di); - cache.capacity = bq27xxx_battery_read_soc(di); - if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) - cache.energy = bq27xxx_battery_read_energy(di); - di->cache.flags = cache.flags; - cache.health = bq27xxx_battery_read_health(di); - if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) - cache.cycle_count = bq27xxx_battery_read_cyct(di); - - /* We only have to read charge design full once */ - if (di->charge_design_full <= 0) - di->charge_design_full = bq27xxx_battery_read_dcap(di); - } - - if ((di->cache.capacity != cache.capacity) || - (di->cache.flags != cache.flags)) - power_supply_changed(di->bat); - - if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) - di->cache = cache; - - di->last_update = jiffies; - - if (!di->removed && poll_interval > 0) - mod_delayed_work(system_wq, &di->work, poll_interval * HZ); -} - -void bq27xxx_battery_update(struct bq27xxx_device_info *di) -{ - mutex_lock(&di->lock); - bq27xxx_battery_update_unlocked(di); - mutex_unlock(&di->lock); -} -EXPORT_SYMBOL_GPL(bq27xxx_battery_update); - -static void bq27xxx_battery_poll(struct work_struct *work) -{ - struct bq27xxx_device_info *di = - container_of(work, struct bq27xxx_device_info, - work.work); - - bq27xxx_battery_update(di); -} - static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) { if (di->opts & BQ27XXX_O_ZERO) @@ -1821,6 +1760,67 @@ static int bq27xxx_battery_current_and_status( return 0; } +static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) +{ + struct bq27xxx_reg_cache cache = {0, }; + bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; + + cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); + if ((cache.flags & 0xff) == 0xff) + cache.flags = -1; /* read error */ + if (cache.flags >= 0) { + cache.temperature = bq27xxx_battery_read_temperature(di); + if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) + cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); + if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) + cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); + if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) + cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); + + cache.charge_full = bq27xxx_battery_read_fcc(di); + cache.capacity = bq27xxx_battery_read_soc(di); + if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) + cache.energy = bq27xxx_battery_read_energy(di); + di->cache.flags = cache.flags; + cache.health = bq27xxx_battery_read_health(di); + if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) + cache.cycle_count = bq27xxx_battery_read_cyct(di); + + /* We only have to read charge design full once */ + if (di->charge_design_full <= 0) + di->charge_design_full = bq27xxx_battery_read_dcap(di); + } + + if ((di->cache.capacity != cache.capacity) || + (di->cache.flags != cache.flags)) + power_supply_changed(di->bat); + + if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) + di->cache = cache; + + di->last_update = jiffies; + + if (!di->removed && poll_interval > 0) + mod_delayed_work(system_wq, &di->work, poll_interval * HZ); +} + +void bq27xxx_battery_update(struct bq27xxx_device_info *di) +{ + mutex_lock(&di->lock); + bq27xxx_battery_update_unlocked(di); + mutex_unlock(&di->lock); +} +EXPORT_SYMBOL_GPL(bq27xxx_battery_update); + +static void bq27xxx_battery_poll(struct work_struct *work) +{ + struct bq27xxx_device_info *di = + container_of(work, struct bq27xxx_device_info, + work.work); + + bq27xxx_battery_update(di); +} + /* * Get the average power in µW * Return < 0 if something fails. From 0949c572d42df8a1b78c5583ed4345e0ff06e06f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:37 +0200 Subject: [PATCH 3285/4345] power: supply: bq27xxx: Ensure power_supply_changed() is called on current sign changes [ Upstream commit 939a116142012926e25de0ea6b7e2f8d86a5f1b6 ] On gauges where the current register is signed, there is no charging flag in the flags register. So only checking flags will not result in power_supply_changed() getting called when e.g. a charger is plugged in and the current sign changes from negative (discharging) to positive (charging). This causes userspace's notion of the status to lag until userspace does a poll. And when a power_supply_leds.c LED trigger is used to indicate charging status with a LED, this LED will lag until the capacity percentage changes, which may take many minutes (because the LED trigger only is updated on power_supply_changed() calls). Fix this by calling bq27xxx_battery_current_and_status() on gauges with a signed current register and checking if the status has changed. Fixes: 297a533b3e62 ("bq27x00: Cache battery registers") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/bq27xxx_battery.c | 13 ++++++++++++- include/linux/power/bq27xxx_battery.h | 3 +++ 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 160ab53065f8..8984f66bd2bc 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1762,6 +1762,7 @@ static int bq27xxx_battery_current_and_status( static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) { + union power_supply_propval status = di->last_status; struct bq27xxx_reg_cache cache = {0, }; bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; @@ -1786,14 +1787,24 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) cache.cycle_count = bq27xxx_battery_read_cyct(di); + /* + * On gauges with signed current reporting the current must be + * checked to detect charging <-> discharging status changes. + */ + if (!(di->opts & BQ27XXX_O_ZERO)) + bq27xxx_battery_current_and_status(di, NULL, &status, &cache); + /* We only have to read charge design full once */ if (di->charge_design_full <= 0) di->charge_design_full = bq27xxx_battery_read_dcap(di); } if ((di->cache.capacity != cache.capacity) || - (di->cache.flags != cache.flags)) + (di->cache.flags != cache.flags) || + (di->last_status.intval != status.intval)) { + di->last_status.intval = status.intval; power_supply_changed(di->bat); + } if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) di->cache = cache; diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 705b94bd091e..63964196a436 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -2,6 +2,8 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__ +#include + enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ @@ -69,6 +71,7 @@ struct bq27xxx_device_info { int charge_design_full; bool removed; unsigned long last_update; + union power_supply_propval last_status; struct delayed_work work; struct power_supply *bat; struct list_head list; From 277b489ad0b70c2ffa6b6805e7f20b54399f8d50 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:38 +0200 Subject: [PATCH 3286/4345] power: supply: bq27xxx: After charger plug in/out wait 0.5s for things to stabilize [ Upstream commit 59a99cd462fbdf71f4e845e09f37783035088b4f ] bq27xxx_external_power_changed() gets called when the charger is plugged in or out. Rather then immediately scheduling an update wait 0.5 seconds for things to stabilize, so that e.g. the (dis)charge current is stable when bq27xxx_battery_update() runs. Fixes: 740b755a3b34 ("bq27x00: Poll battery state") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/bq27xxx_battery.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 8984f66bd2bc..235647b21af7 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -2022,8 +2022,8 @@ static void bq27xxx_external_power_changed(struct power_supply *psy) { struct bq27xxx_device_info *di = power_supply_get_drvdata(psy); - cancel_delayed_work_sync(&di->work); - schedule_delayed_work(&di->work, 0); + /* After charger plug in/out wait 0.5s for things to stabilize */ + mod_delayed_work(system_wq, &di->work, HZ / 2); } int bq27xxx_battery_setup(struct bq27xxx_device_info *di) From 224f7bbf577b21d1f796de825037ae59ef0e0e42 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 1 Feb 2022 14:06:47 +0100 Subject: [PATCH 3287/4345] power: supply: core: Refactor power_supply_set_input_current_limit_from_supplier() [ Upstream commit 2220af8ca61ae67de4ec3deec1c6395a2f65b9fd ] Some (USB) charger ICs have variants with USB D+ and D- pins to do their own builtin charger-type detection, like e.g. the bq24190 and bq25890 and also variants which lack this functionality, e.g. the bq24192 and bq25892. In case the charger-type; and thus the input-current-limit detection is done outside the charger IC then we need some way to communicate this to the charger IC. In the past extcon was used for this, but if the external detection does e.g. full USB PD negotiation then the extcon cable-types do not convey enough information. For these setups it was decided to model the external charging "brick" and the parameters negotiated with it as a power_supply class-device itself; and power_supply_set_input_current_limit_from_supplier() was introduced to allow drivers to get the input-current-limit this way. But in some cases psy drivers may want to know other properties, e.g. the bq25892 can do "quick-charge" negotiation by pulsing its current draw, but this should only be done if the usb_type psy-property of its supplier is set to DCP (and device-properties indicate the board allows higher voltages). Instead of adding extra helper functions for each property which a psy-driver wants to query from its supplier, refactor power_supply_set_input_current_limit_from_supplier() into a more generic power_supply_get_property_from_supplier() function. Reviewed-by: Andy Shevchenko Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel Stable-dep-of: 77c2a3097d70 ("power: supply: bq24190: Call power_supply_changed() after updating input current") Signed-off-by: Sasha Levin --- drivers/power/supply/bq24190_charger.c | 12 ++++- drivers/power/supply/power_supply_core.c | 57 +++++++++++++----------- include/linux/power_supply.h | 5 ++- 3 files changed, 44 insertions(+), 30 deletions(-) diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index 338dd82007e4..7a7b03b09ea6 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -1203,8 +1203,18 @@ static void bq24190_input_current_limit_work(struct work_struct *work) struct bq24190_dev_info *bdi = container_of(work, struct bq24190_dev_info, input_current_limit_work.work); + union power_supply_propval val; + int ret; - power_supply_set_input_current_limit_from_supplier(bdi->charger); + ret = power_supply_get_property_from_supplier(bdi->charger, + POWER_SUPPLY_PROP_CURRENT_MAX, + &val); + if (ret) + return; + + bq24190_charger_set_property(bdi->charger, + POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, + &val); } /* Sync the input-current-limit with our parent supply (if we have one) */ diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 2b644590fa8e..53e5b3e04be1 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -375,46 +375,49 @@ int power_supply_is_system_supplied(void) } EXPORT_SYMBOL_GPL(power_supply_is_system_supplied); -static int __power_supply_get_supplier_max_current(struct device *dev, - void *data) +struct psy_get_supplier_prop_data { + struct power_supply *psy; + enum power_supply_property psp; + union power_supply_propval *val; +}; + +static int __power_supply_get_supplier_property(struct device *dev, void *_data) { - union power_supply_propval ret = {0,}; struct power_supply *epsy = dev_get_drvdata(dev); - struct power_supply *psy = data; + struct psy_get_supplier_prop_data *data = _data; - if (__power_supply_is_supplied_by(epsy, psy)) - if (!epsy->desc->get_property(epsy, - POWER_SUPPLY_PROP_CURRENT_MAX, - &ret)) - return ret.intval; + if (__power_supply_is_supplied_by(epsy, data->psy)) + if (!epsy->desc->get_property(epsy, data->psp, data->val)) + return 1; /* Success */ - return 0; + return 0; /* Continue iterating */ } -int power_supply_set_input_current_limit_from_supplier(struct power_supply *psy) +int power_supply_get_property_from_supplier(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) { - union power_supply_propval val = {0,}; - int curr; - - if (!psy->desc->set_property) - return -EINVAL; + struct psy_get_supplier_prop_data data = { + .psy = psy, + .psp = psp, + .val = val, + }; + int ret; /* * This function is not intended for use with a supply with multiple - * suppliers, we simply pick the first supply to report a non 0 - * max-current. + * suppliers, we simply pick the first supply to report the psp. */ - curr = class_for_each_device(power_supply_class, NULL, psy, - __power_supply_get_supplier_max_current); - if (curr <= 0) - return (curr == 0) ? -ENODEV : curr; + ret = class_for_each_device(power_supply_class, NULL, &data, + __power_supply_get_supplier_property); + if (ret < 0) + return ret; + if (ret == 0) + return -ENODEV; - val.intval = curr; - - return psy->desc->set_property(psy, - POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val); + return 0; } -EXPORT_SYMBOL_GPL(power_supply_set_input_current_limit_from_supplier); +EXPORT_SYMBOL_GPL(power_supply_get_property_from_supplier); int power_supply_set_battery_charged(struct power_supply *psy) { diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 81a55e974feb..e6fe2f581bda 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -413,8 +413,9 @@ power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table int table_len, int temp); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); -extern int power_supply_set_input_current_limit_from_supplier( - struct power_supply *psy); +int power_supply_get_property_from_supplier(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val); extern int power_supply_set_battery_charged(struct power_supply *psy); #ifdef CONFIG_POWER_SUPPLY From b557220d31409eed7bcc5d7f70c3fa5fcd390435 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:41 +0200 Subject: [PATCH 3288/4345] power: supply: bq24190: Call power_supply_changed() after updating input current [ Upstream commit 77c2a3097d7029441e8a91aa0de1b4e5464593da ] The bq24192 model relies on external charger-type detection and once that is done the bq24190_charger code will update the input current. In this case, when the initial power_supply_changed() call is made from the interrupt handler, the input settings are 5V/0.5A which on many devices is not enough power to charge (while the device is on). On many devices the fuel-gauge relies in its external_power_changed callback to timely signal userspace about charging <-> discharging status changes. Add a power_supply_changed() call after updating the input current. This allows the fuel-gauge driver to timely recheck if the battery is charging after the new input current has been applied and then it can immediately notify userspace about this. Fixes: 18f8e6f695ac ("power: supply: bq24190_charger: Get input_current_limit from our supplier") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/bq24190_charger.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index 7a7b03b09ea6..5769b36851c3 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -1215,6 +1215,7 @@ static void bq24190_input_current_limit_work(struct work_struct *work) bq24190_charger_set_property(bdi->charger, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val); + power_supply_changed(bdi->charger); } /* Sync the input-current-limit with our parent supply (if we have one) */ From 12cb97ed85fb8bfc3ef88b66d80b09950d49af91 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 29 Mar 2021 15:59:04 +0300 Subject: [PATCH 3289/4345] regulator: Add regmap helper for ramp-delay setting [ Upstream commit fb8fee9efdcf084d9e31ba14cc4734d97e5dd972 ] Quite a few regulator ICs do support setting ramp-delay by writing a value matching the delay to a ramp-delay register. Provide a simple helper for table-based delay setting. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/f101f1db564cf32cb58719c77af0b00d7236bb89.1617020713.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown Stable-dep-of: d67dada3e252 ("regulator: pca9450: Fix BUCK2 enable_mask") Signed-off-by: Sasha Levin --- drivers/regulator/helpers.c | 65 ++++++++++++++++++++++++++++++++ include/linux/regulator/driver.h | 5 +++ 2 files changed, 70 insertions(+) diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c index e4bb09bbd3fa..a356f84b1285 100644 --- a/drivers/regulator/helpers.c +++ b/drivers/regulator/helpers.c @@ -879,3 +879,68 @@ bool regulator_is_equal(struct regulator *reg1, struct regulator *reg2) return reg1->rdev == reg2->rdev; } EXPORT_SYMBOL_GPL(regulator_is_equal); + +static int find_closest_bigger(unsigned int target, const unsigned int *table, + unsigned int num_sel, unsigned int *sel) +{ + unsigned int s, tmp, max, maxsel = 0; + bool found = false; + + max = table[0]; + + for (s = 0; s < num_sel; s++) { + if (table[s] > max) { + max = table[s]; + maxsel = s; + } + if (table[s] >= target) { + if (!found || table[s] - target < tmp - target) { + tmp = table[s]; + *sel = s; + found = true; + if (tmp == target) + break; + } + } + } + + if (!found) { + *sel = maxsel; + return -EINVAL; + } + + return 0; +} + +/** + * regulator_set_ramp_delay_regmap - set_ramp_delay() helper + * + * @rdev: regulator to operate on + * + * Regulators that use regmap for their register I/O can set the ramp_reg + * and ramp_mask fields in their descriptor and then use this as their + * set_ramp_delay operation, saving some code. + */ +int regulator_set_ramp_delay_regmap(struct regulator_dev *rdev, int ramp_delay) +{ + int ret; + unsigned int sel; + + if (!rdev->desc->n_ramp_values) + return -EINVAL; + + ret = find_closest_bigger(ramp_delay, rdev->desc->ramp_delay_table, + rdev->desc->n_ramp_values, &sel); + + if (ret) { + dev_warn(rdev_get_dev(rdev), + "Can't set ramp-delay %u, setting %u\n", ramp_delay, + rdev->desc->ramp_delay_table[sel]); + } + + sel <<= ffs(rdev->desc->ramp_mask) - 1; + + return regmap_update_bits(rdev->regmap, rdev->desc->ramp_reg, + rdev->desc->ramp_mask, sel); +} +EXPORT_SYMBOL_GPL(regulator_set_ramp_delay_regmap); diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 11cade73726c..633e7a2ab01d 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -370,6 +370,10 @@ struct regulator_desc { unsigned int pull_down_reg; unsigned int pull_down_mask; unsigned int pull_down_val_on; + unsigned int ramp_reg; + unsigned int ramp_mask; + const unsigned int *ramp_delay_table; + unsigned int n_ramp_values; unsigned int enable_time; @@ -532,6 +536,7 @@ int regulator_set_current_limit_regmap(struct regulator_dev *rdev, int min_uA, int max_uA); int regulator_get_current_limit_regmap(struct regulator_dev *rdev); void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data); +int regulator_set_ramp_delay_regmap(struct regulator_dev *rdev, int ramp_delay); /* * Helper functions intended to be used by regulator drivers prior registering From b3a9c4081db956dd383137e55a008f82e1d8bb87 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 26 May 2021 20:24:08 +0800 Subject: [PATCH 3290/4345] regulator: pca9450: Convert to use regulator_set_ramp_delay_regmap [ Upstream commit 4c4fce171c4ca08cd98be7db350e6950630b046a ] Use regulator_set_ramp_delay_regmap instead of open-coded. Signed-off-by: Axel Lin Link: https://lore.kernel.org/r/20210526122408.78156-1-axel.lin@ingics.com Signed-off-by: Mark Brown Stable-dep-of: d67dada3e252 ("regulator: pca9450: Fix BUCK2 enable_mask") Signed-off-by: Sasha Levin --- drivers/regulator/pca9450-regulator.c | 51 +++++++++++++-------------- 1 file changed, 24 insertions(+), 27 deletions(-) diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index d38109cc3a01..fd184c6c7c78 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -65,32 +65,9 @@ static const struct regmap_config pca9450_regmap_config = { * 10: 25mV/4usec * 11: 25mV/8usec */ -static int pca9450_dvs_set_ramp_delay(struct regulator_dev *rdev, - int ramp_delay) -{ - int id = rdev_get_id(rdev); - unsigned int ramp_value; - - switch (ramp_delay) { - case 1 ... 3125: - ramp_value = BUCK1_RAMP_3P125MV; - break; - case 3126 ... 6250: - ramp_value = BUCK1_RAMP_6P25MV; - break; - case 6251 ... 12500: - ramp_value = BUCK1_RAMP_12P5MV; - break; - case 12501 ... 25000: - ramp_value = BUCK1_RAMP_25MV; - break; - default: - ramp_value = BUCK1_RAMP_25MV; - } - - return regmap_update_bits(rdev->regmap, PCA9450_REG_BUCK1CTRL + id * 3, - BUCK1_RAMP_MASK, ramp_value << 6); -} +static const unsigned int pca9450_dvs_buck_ramp_table[] = { + 25000, 12500, 6250, 3125 +}; static const struct regulator_ops pca9450_dvs_buck_regulator_ops = { .enable = regulator_enable_regmap, @@ -100,7 +77,7 @@ static const struct regulator_ops pca9450_dvs_buck_regulator_ops = { .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_time_sel = regulator_set_voltage_time_sel, - .set_ramp_delay = pca9450_dvs_set_ramp_delay, + .set_ramp_delay = regulator_set_ramp_delay_regmap, }; static const struct regulator_ops pca9450_buck_regulator_ops = { @@ -251,6 +228,10 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK1OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK1CTRL, .enable_mask = BUCK1_ENMODE_MASK, + .ramp_reg = PCA9450_REG_BUCK1CTRL, + .ramp_mask = BUCK1_RAMP_MASK, + .ramp_delay_table = pca9450_dvs_buck_ramp_table, + .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, @@ -276,6 +257,10 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, .enable_mask = BUCK1_ENMODE_MASK, + .ramp_reg = PCA9450_REG_BUCK2CTRL, + .ramp_mask = BUCK2_RAMP_MASK, + .ramp_delay_table = pca9450_dvs_buck_ramp_table, + .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, @@ -301,6 +286,10 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK3OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK3CTRL, .enable_mask = BUCK3_ENMODE_MASK, + .ramp_reg = PCA9450_REG_BUCK3CTRL, + .ramp_mask = BUCK3_RAMP_MASK, + .ramp_delay_table = pca9450_dvs_buck_ramp_table, + .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, @@ -477,6 +466,10 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_mask = BUCK1OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK1CTRL, .enable_mask = BUCK1_ENMODE_MASK, + .ramp_reg = PCA9450_REG_BUCK1CTRL, + .ramp_mask = BUCK1_RAMP_MASK, + .ramp_delay_table = pca9450_dvs_buck_ramp_table, + .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, @@ -502,6 +495,10 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, .enable_mask = BUCK1_ENMODE_MASK, + .ramp_reg = PCA9450_REG_BUCK2CTRL, + .ramp_mask = BUCK2_RAMP_MASK, + .ramp_delay_table = pca9450_dvs_buck_ramp_table, + .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, From 860ad704e4506a4716631a46e93c2ed4a6a0e23c Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Fri, 12 May 2023 10:19:34 +0200 Subject: [PATCH 3291/4345] regulator: pca9450: Fix BUCK2 enable_mask [ Upstream commit d67dada3e2524514b09496b9ee1df22d4507a280 ] This fixes a copy & paste error. No functional change intended, BUCK1_ENMODE_MASK equals BUCK2_ENMODE_MASK. Fixes: 0935ff5f1f0a ("regulator: pca9450: add pca9450 pmic driver") Originally-from: Robin Gong --- drivers/regulator/pca9450-regulator.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index fd184c6c7c78..b3d206ebb289 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -256,7 +256,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_reg = PCA9450_REG_BUCK2OUT_DVS0, .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, - .enable_mask = BUCK1_ENMODE_MASK, + .enable_mask = BUCK2_ENMODE_MASK, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, @@ -494,7 +494,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_reg = PCA9450_REG_BUCK2OUT_DVS0, .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, - .enable_mask = BUCK1_ENMODE_MASK, + .enable_mask = BUCK2_ENMODE_MASK, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, From 57dc3c124e7bf2b937086e4b57c4a834b02c0457 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Sun, 27 Feb 2022 12:23:34 +0000 Subject: [PATCH 3292/4345] net/mlx5: devcom only supports 2 ports [ Upstream commit 8a6e75e5f57e9ac82268d9bfca3403598d9d0292 ] Devcom API is intended to be used between 2 devices only add this implied assumption into the code and check when it's no true. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed Stable-dep-of: 1f893f57a3bf ("net/mlx5: Devcom, serialize devcom registration") Signed-off-by: Sasha Levin --- .../net/ethernet/mellanox/mlx5/core/lib/devcom.c | 16 +++++++++------- .../net/ethernet/mellanox/mlx5/core/lib/devcom.h | 2 ++ 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index abd066e95228..617eea1b1701 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -14,7 +14,7 @@ static LIST_HEAD(devcom_list); struct mlx5_devcom_component { struct { void *data; - } device[MLX5_MAX_PORTS]; + } device[MLX5_DEVCOM_PORTS_SUPPORTED]; mlx5_devcom_event_handler_t handler; struct rw_semaphore sem; @@ -25,7 +25,7 @@ struct mlx5_devcom_list { struct list_head list; struct mlx5_devcom_component components[MLX5_DEVCOM_NUM_COMPONENTS]; - struct mlx5_core_dev *devs[MLX5_MAX_PORTS]; + struct mlx5_core_dev *devs[MLX5_DEVCOM_PORTS_SUPPORTED]; }; struct mlx5_devcom { @@ -74,13 +74,15 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (!mlx5_core_is_pf(dev)) return NULL; + if (MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_DEVCOM_PORTS_SUPPORTED) + return NULL; sguid0 = mlx5_query_nic_system_image_guid(dev); list_for_each_entry(iter, &devcom_list, list) { struct mlx5_core_dev *tmp_dev = NULL; idx = -1; - for (i = 0; i < MLX5_MAX_PORTS; i++) { + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) { if (iter->devs[i]) tmp_dev = iter->devs[i]; else @@ -135,11 +137,11 @@ void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom) kfree(devcom); - for (i = 0; i < MLX5_MAX_PORTS; i++) + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) if (priv->devs[i]) break; - if (i != MLX5_MAX_PORTS) + if (i != MLX5_DEVCOM_PORTS_SUPPORTED) return; list_del(&priv->list); @@ -192,7 +194,7 @@ int mlx5_devcom_send_event(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; down_write(&comp->sem); - for (i = 0; i < MLX5_MAX_PORTS; i++) + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) if (i != devcom->idx && comp->device[i].data) { err = comp->handler(event, comp->device[i].data, event_data); @@ -240,7 +242,7 @@ void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, return NULL; } - for (i = 0; i < MLX5_MAX_PORTS; i++) + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) if (i != devcom->idx) break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index 939d5bf1581b..94313c18bb64 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -6,6 +6,8 @@ #include +#define MLX5_DEVCOM_PORTS_SUPPORTED 2 + enum mlx5_devcom_components { MLX5_DEVCOM_ESW_OFFLOADS, From b556990235c33460a9d072b93f8dad3822ce4249 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 2 May 2023 13:36:42 +0300 Subject: [PATCH 3293/4345] net/mlx5: Devcom, serialize devcom registration [ Upstream commit 1f893f57a3bf9fe1f4bcb25b55aea7f7f9712fe7 ] From one hand, mlx5 driver is allowing to probe PFs in parallel. From the other hand, devcom, which is a share resource between PFs, is registered without any lock. This might resulted in memory problems. Hence, use the global mlx5_dev_list_lock in order to serialize devcom registration. Fixes: fadd59fc50d0 ("net/mlx5: Introduce inter-device communication mechanism") Signed-off-by: Shay Drory Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- .../ethernet/mellanox/mlx5/core/lib/devcom.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index 617eea1b1701..438be215bbd4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -3,6 +3,7 @@ #include #include "lib/devcom.h" +#include "mlx5_core.h" static LIST_HEAD(devcom_list); @@ -77,6 +78,7 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_DEVCOM_PORTS_SUPPORTED) return NULL; + mlx5_dev_list_lock(); sguid0 = mlx5_query_nic_system_image_guid(dev); list_for_each_entry(iter, &devcom_list, list) { struct mlx5_core_dev *tmp_dev = NULL; @@ -102,8 +104,10 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (!priv) { priv = mlx5_devcom_list_alloc(); - if (!priv) - return ERR_PTR(-ENOMEM); + if (!priv) { + devcom = ERR_PTR(-ENOMEM); + goto out; + } idx = 0; new_priv = true; @@ -114,12 +118,14 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (!devcom) { if (new_priv) kfree(priv); - return ERR_PTR(-ENOMEM); + devcom = ERR_PTR(-ENOMEM); + goto out; } if (new_priv) list_add(&priv->list, &devcom_list); - +out: + mlx5_dev_list_unlock(); return devcom; } @@ -132,6 +138,7 @@ void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom) if (IS_ERR_OR_NULL(devcom)) return; + mlx5_dev_list_lock(); priv = devcom->priv; priv->devs[devcom->idx] = NULL; @@ -142,10 +149,12 @@ void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom) break; if (i != MLX5_DEVCOM_PORTS_SUPPORTED) - return; + goto out; list_del(&priv->list); kfree(priv); +out: + mlx5_dev_list_unlock(); } void mlx5_devcom_register_component(struct mlx5_devcom *devcom, From 6a0712d9fe46678c65e7844f1b1d4ef9a0bb36de Mon Sep 17 00:00:00 2001 From: David Epping Date: Tue, 23 May 2023 17:31:08 +0200 Subject: [PATCH 3294/4345] net: phy: mscc: enable VSC8501/2 RGMII RX clock [ Upstream commit 71460c9ec5c743e9ffffca3c874d66267c36345e ] By default the VSC8501 and VSC8502 RGMII/GMII/MII RX_CLK output is disabled. To allow packet forwarding towards the MAC it needs to be enabled. For other PHYs supported by this driver the clock output is enabled by default. Fixes: d3169863310d ("net: phy: mscc: add support for VSC8502") Signed-off-by: David Epping Reviewed-by: Russell King (Oracle) Reviewed-by: Vladimir Oltean Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/mscc/mscc.h | 1 + drivers/net/phy/mscc/mscc_main.c | 54 +++++++++++++++++--------------- 2 files changed, 29 insertions(+), 26 deletions(-) diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h index c2023f93c0b2..79117d281c1e 100644 --- a/drivers/net/phy/mscc/mscc.h +++ b/drivers/net/phy/mscc/mscc.h @@ -175,6 +175,7 @@ enum rgmii_clock_delay { #define VSC8502_RGMII_CNTL 20 #define VSC8502_RGMII_RX_DELAY_MASK 0x0070 #define VSC8502_RGMII_TX_DELAY_MASK 0x0007 +#define VSC8502_RGMII_RX_CLK_DISABLE 0x0800 #define MSCC_PHY_WOL_LOWER_MAC_ADDR 21 #define MSCC_PHY_WOL_MID_MAC_ADDR 22 diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index ffac713afa55..c64ac142509a 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -527,14 +527,27 @@ out_unlock: * * 2.0 ns (which causes the data to be sampled at exactly half way between * clock transitions at 1000 Mbps) if delays should be enabled */ -static int vsc85xx_rgmii_set_skews(struct phy_device *phydev, u32 rgmii_cntl, - u16 rgmii_rx_delay_mask, - u16 rgmii_tx_delay_mask) +static int vsc85xx_update_rgmii_cntl(struct phy_device *phydev, u32 rgmii_cntl, + u16 rgmii_rx_delay_mask, + u16 rgmii_tx_delay_mask) { u16 rgmii_rx_delay_pos = ffs(rgmii_rx_delay_mask) - 1; u16 rgmii_tx_delay_pos = ffs(rgmii_tx_delay_mask) - 1; u16 reg_val = 0; - int rc; + u16 mask = 0; + int rc = 0; + + /* For traffic to pass, the VSC8502 family needs the RX_CLK disable bit + * to be unset for all PHY modes, so do that as part of the paged + * register modification. + * For some family members (like VSC8530/31/40/41) this bit is reserved + * and read-only, and the RX clock is enabled by default. + */ + if (rgmii_cntl == VSC8502_RGMII_CNTL) + mask |= VSC8502_RGMII_RX_CLK_DISABLE; + + if (phy_interface_is_rgmii(phydev)) + mask |= rgmii_rx_delay_mask | rgmii_tx_delay_mask; mutex_lock(&phydev->lock); @@ -545,10 +558,9 @@ static int vsc85xx_rgmii_set_skews(struct phy_device *phydev, u32 rgmii_cntl, phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) reg_val |= RGMII_CLK_DELAY_2_0_NS << rgmii_tx_delay_pos; - rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_EXTENDED_2, - rgmii_cntl, - rgmii_rx_delay_mask | rgmii_tx_delay_mask, - reg_val); + if (mask) + rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_EXTENDED_2, + rgmii_cntl, mask, reg_val); mutex_unlock(&phydev->lock); @@ -557,19 +569,11 @@ static int vsc85xx_rgmii_set_skews(struct phy_device *phydev, u32 rgmii_cntl, static int vsc85xx_default_config(struct phy_device *phydev) { - int rc; - phydev->mdix_ctrl = ETH_TP_MDI_AUTO; - if (phy_interface_mode_is_rgmii(phydev->interface)) { - rc = vsc85xx_rgmii_set_skews(phydev, VSC8502_RGMII_CNTL, - VSC8502_RGMII_RX_DELAY_MASK, - VSC8502_RGMII_TX_DELAY_MASK); - if (rc) - return rc; - } - - return 0; + return vsc85xx_update_rgmii_cntl(phydev, VSC8502_RGMII_CNTL, + VSC8502_RGMII_RX_DELAY_MASK, + VSC8502_RGMII_TX_DELAY_MASK); } static int vsc85xx_get_tunable(struct phy_device *phydev, @@ -1646,13 +1650,11 @@ static int vsc8584_config_init(struct phy_device *phydev) if (ret) return ret; - if (phy_interface_is_rgmii(phydev)) { - ret = vsc85xx_rgmii_set_skews(phydev, VSC8572_RGMII_CNTL, - VSC8572_RGMII_RX_DELAY_MASK, - VSC8572_RGMII_TX_DELAY_MASK); - if (ret) - return ret; - } + ret = vsc85xx_update_rgmii_cntl(phydev, VSC8572_RGMII_CNTL, + VSC8572_RGMII_RX_DELAY_MASK, + VSC8572_RGMII_TX_DELAY_MASK); + if (ret) + return ret; ret = genphy_soft_reset(phydev); if (ret) From e4d2e6c3054b974125bdae74ee57017964232c4a Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Sun, 16 Apr 2023 16:02:51 +0800 Subject: [PATCH 3295/4345] bluetooth: Add cmd validity checks at the start of hci_sock_ioctl() commit 000c2fa2c144c499c881a101819cf1936a1f7cf2 upstream. Previously, channel open messages were always sent to monitors on the first ioctl() call for unbound HCI sockets, even if the command and arguments were completely invalid. This can leave an exploitable hole with the abuse of invalid ioctl calls. This commit hardens the ioctl processing logic by first checking if the command is valid, and immediately returning with an ENOIOCTLCMD error code if it is not. This ensures that ioctl calls with invalid commands are free of side effects, and increases the difficulty of further exploitation by forcing exploitation to find a way to pass a valid command first. Signed-off-by: Ruihan Li Co-developed-by: Marcel Holtmann Signed-off-by: Marcel Holtmann Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Dragos-Marian Panait Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/hci_sock.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 4dcc1a8a8954..eafb2bebc12c 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -980,6 +980,34 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, BT_DBG("cmd %x arg %lx", cmd, arg); + /* Make sure the cmd is valid before doing anything */ + switch (cmd) { + case HCIGETDEVLIST: + case HCIGETDEVINFO: + case HCIGETCONNLIST: + case HCIDEVUP: + case HCIDEVDOWN: + case HCIDEVRESET: + case HCIDEVRESTAT: + case HCISETSCAN: + case HCISETAUTH: + case HCISETENCRYPT: + case HCISETPTYPE: + case HCISETLINKPOL: + case HCISETLINKMODE: + case HCISETACLMTU: + case HCISETSCOMTU: + case HCIINQUIRY: + case HCISETRAW: + case HCIGETCONNINFO: + case HCIGETAUTHINFO: + case HCIBLOCKADDR: + case HCIUNBLOCKADDR: + break; + default: + return -ENOIOCTLCMD; + } + lock_sock(sk); if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) { From 2218752325a98861dfb10f59a9b0270d6d4abe21 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Fri, 5 May 2023 20:30:20 +0000 Subject: [PATCH 3296/4345] binder: fix UAF caused by faulty buffer cleanup commit bdc1c5fac982845a58d28690cdb56db8c88a530d upstream. In binder_transaction_buffer_release() the 'failed_at' offset indicates the number of objects to clean up. However, this function was changed by commit 44d8047f1d87 ("binder: use standard functions to allocate fds"), to release all the objects in the buffer when 'failed_at' is zero. This introduced an issue when a transaction buffer is released without any objects having been processed so far. In this case, 'failed_at' is indeed zero yet it is misinterpreted as releasing the entire buffer. This leads to use-after-free errors where nodes are incorrectly freed and subsequently accessed. Such is the case in the following KASAN report: ================================================================== BUG: KASAN: slab-use-after-free in binder_thread_read+0xc40/0x1f30 Read of size 8 at addr ffff4faf037cfc58 by task poc/474 CPU: 6 PID: 474 Comm: poc Not tainted 6.3.0-12570-g7df047b3f0aa #5 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x94/0xec show_stack+0x18/0x24 dump_stack_lvl+0x48/0x60 print_report+0xf8/0x5b8 kasan_report+0xb8/0xfc __asan_load8+0x9c/0xb8 binder_thread_read+0xc40/0x1f30 binder_ioctl+0xd9c/0x1768 __arm64_sys_ioctl+0xd4/0x118 invoke_syscall+0x60/0x188 [...] Allocated by task 474: kasan_save_stack+0x3c/0x64 kasan_set_track+0x2c/0x40 kasan_save_alloc_info+0x24/0x34 __kasan_kmalloc+0xb8/0xbc kmalloc_trace+0x48/0x5c binder_new_node+0x3c/0x3a4 binder_transaction+0x2b58/0x36f0 binder_thread_write+0x8e0/0x1b78 binder_ioctl+0x14a0/0x1768 __arm64_sys_ioctl+0xd4/0x118 invoke_syscall+0x60/0x188 [...] Freed by task 475: kasan_save_stack+0x3c/0x64 kasan_set_track+0x2c/0x40 kasan_save_free_info+0x38/0x5c __kasan_slab_free+0xe8/0x154 __kmem_cache_free+0x128/0x2bc kfree+0x58/0x70 binder_dec_node_tmpref+0x178/0x1fc binder_transaction_buffer_release+0x430/0x628 binder_transaction+0x1954/0x36f0 binder_thread_write+0x8e0/0x1b78 binder_ioctl+0x14a0/0x1768 __arm64_sys_ioctl+0xd4/0x118 invoke_syscall+0x60/0x188 [...] ================================================================== In order to avoid these issues, let's always calculate the intended 'failed_at' offset beforehand. This is renamed and wrapped in a helper function to make it clear and convenient. Fixes: 32e9f56a96d8 ("binder: don't detect sender/target during buffer cleanup") Reported-by: Zi Fan Tan Cc: stable@vger.kernel.org Signed-off-by: Carlos Llamas Acked-by: Todd Kjos Link: https://lore.kernel.org/r/20230505203020.4101154-1-cmllamas@google.com [cmllamas: resolve trivial conflict due to missing commit 9864bb4801331] Signed-off-by: Carlos Llamas Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index b403c7f063b0..dbae98f09658 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2267,24 +2267,23 @@ static void binder_deferred_fd_close(int fd) static void binder_transaction_buffer_release(struct binder_proc *proc, struct binder_thread *thread, struct binder_buffer *buffer, - binder_size_t failed_at, + binder_size_t off_end_offset, bool is_failure) { int debug_id = buffer->debug_id; - binder_size_t off_start_offset, buffer_offset, off_end_offset; + binder_size_t off_start_offset, buffer_offset; binder_debug(BINDER_DEBUG_TRANSACTION, "%d buffer release %d, size %zd-%zd, failed at %llx\n", proc->pid, buffer->debug_id, buffer->data_size, buffer->offsets_size, - (unsigned long long)failed_at); + (unsigned long long)off_end_offset); if (buffer->target_node) binder_dec_node(buffer->target_node, 1, 0); off_start_offset = ALIGN(buffer->data_size, sizeof(void *)); - off_end_offset = is_failure && failed_at ? failed_at : - off_start_offset + buffer->offsets_size; + for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { struct binder_object_header *hdr; @@ -2444,6 +2443,21 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, } } +/* Clean up all the objects in the buffer */ +static inline void binder_release_entire_buffer(struct binder_proc *proc, + struct binder_thread *thread, + struct binder_buffer *buffer, + bool is_failure) +{ + binder_size_t off_end_offset; + + off_end_offset = ALIGN(buffer->data_size, sizeof(void *)); + off_end_offset += buffer->offsets_size; + + binder_transaction_buffer_release(proc, thread, buffer, + off_end_offset, is_failure); +} + static int binder_translate_binder(struct flat_binder_object *fp, struct binder_transaction *t, struct binder_thread *thread) @@ -3926,7 +3940,7 @@ binder_free_buf(struct binder_proc *proc, binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); - binder_transaction_buffer_release(proc, thread, buffer, 0, is_failure); + binder_release_entire_buffer(proc, thread, buffer, is_failure); binder_alloc_free_buf(&proc->alloc, buffer); } From 18c14d3028c001a0be15685a550dbabf67b6382d Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 22 May 2023 14:08:20 +0200 Subject: [PATCH 3297/4345] ipv{4,6}/raw: fix output xfrm lookup wrt protocol commit 3632679d9e4f879f49949bb5b050e0de553e4739 upstream. With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the protocol field of the flow structure, build by raw_sendmsg() / rawv6_sendmsg()), is set to IPPROTO_RAW. This breaks the ipsec policy lookup when some policies are defined with a protocol in the selector. For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to specify the protocol. Just accept all values for IPPROTO_RAW socket. For ipv4, the sin_port field of 'struct sockaddr_in' could not be used without breaking backward compatibility (the value of this field was never checked). Let's add a new kind of control message, so that the userland could specify which protocol is used. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") CC: stable@vger.kernel.org Signed-off-by: Nicolas Dichtel Link: https://lore.kernel.org/r/20230522120820.1319391-1-nicolas.dichtel@6wind.com Signed-off-by: Paolo Abeni Signed-off-by: Nicolas Dichtel Signed-off-by: Greg Kroah-Hartman --- include/net/ip.h | 2 ++ include/uapi/linux/in.h | 2 ++ net/ipv4/ip_sockglue.c | 12 +++++++++++- net/ipv4/raw.c | 5 ++++- net/ipv6/raw.c | 3 ++- 5 files changed, 21 insertions(+), 3 deletions(-) diff --git a/include/net/ip.h b/include/net/ip.h index 4b775af57268..8d1173577fb5 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -75,6 +75,7 @@ struct ipcm_cookie { __be32 addr; int oif; struct ip_options_rcu *opt; + __u8 protocol; __u8 ttl; __s16 tos; char priority; @@ -95,6 +96,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = inet->sk.sk_bound_dev_if; ipcm->addr = inet->inet_saddr; + ipcm->protocol = inet->inet_num; } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index d1b327036ae4..3960bc3da6b3 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -159,6 +159,8 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 4cc39c62af55..1b35afd326b8 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; - + case IP_PROTOCOL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->protocol = val; + break; default: return -EINVAL; } @@ -1724,6 +1731,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MINTTL: val = inet->min_ttl; break; + case IP_PROTOCOL: + val = inet_sk(sk)->inet_num; + break; default: release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 4899ebe569eb..650da4d8f7ad 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -559,6 +559,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); + /* Keep backward compat */ + if (hdrincl) + ipc.protocol = IPPROTO_RAW; if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -626,7 +629,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, - hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 69f0f9c05d02..7ff06fa7ed19 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -828,7 +828,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!proto) proto = inet->inet_num; - else if (proto != inet->inet_num) + else if (proto != inet->inet_num && + inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) From 468bebc426ba19f285ea4d9d9135c7584d123e20 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Wed, 22 Mar 2023 09:35:32 +0200 Subject: [PATCH 3298/4345] netfilter: ctnetlink: Support offloaded conntrack entry deletion commit 9b7c68b3911aef84afa4cbfc31bce20f10570d51 upstream. Currently, offloaded conntrack entries (flows) can only be deleted after they are removed from offload, which is either by timeout, tcp state change or tc ct rule deletion. This can cause issues for users wishing to manually delete or flush existing entries. Support deletion of offloaded conntrack entries. Example usage: # Delete all offloaded (and non offloaded) conntrack entries # whose source address is 1.2.3.4 $ conntrack -D -s 1.2.3.4 # Delete all entries $ conntrack -F Signed-off-by: Paul Blakey Reviewed-by: Simon Horman Acked-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Cc: Demi Marie Obenour Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conntrack_netlink.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c9ca857f1068..6a055a221683 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1493,9 +1493,6 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) { - if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) - return 0; - return ctnetlink_filter_match(ct, data); } @@ -1561,11 +1558,6 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, ct = nf_ct_tuplehash_to_ctrack(h); - if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) { - nf_ct_put(ct); - return -EBUSY; - } - if (cda[CTA_ID]) { __be32 id = nla_get_be32(cda[CTA_ID]); From c7992b6c7f0e2b0a87dd8e3f488250557b077c20 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 5 Jun 2023 09:07:04 +0200 Subject: [PATCH 3299/4345] Linux 5.10.182 Link: https://lore.kernel.org/r/20230601131933.727832920@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Shuah Khan Tested-by: Jon Hunter Tested-by: Linux Kernel Functional Testing Tested-by: Salvatore Bonaccorso Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 4e8289113a81..2f0efde21902 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 181 +SUBLEVEL = 182 EXTRAVERSION = NAME = Dare mighty things From fffb0ae9aac66b147e70d6510b3e59d3addfd161 Mon Sep 17 00:00:00 2001 From: Uttkarsh Aggarwal Date: Tue, 30 May 2023 10:22:46 +0530 Subject: [PATCH 3300/4345] BACKPORT: usb: dwc3: gadget: Bail out in pullup if soft reset timeout happens If the core soft reset timeout happens, avoid setting up event buffers and starting gadget as the writes to these registers may not reflect when in reset and setting the run stop bit can lead the controller to access wrong event buffer address resulting in a crash. Signed-off-by: Krishna Kurapati Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230510075252.31023-2-quic_kriskura@quicinc.com Signed-off-by: Greg Kroah-Hartman Bug: 284900975 (cherry picked from commit 813f44d57e19ccaa7330e829bd913515be42719d https://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git/ usb -next) Change-Id: I01373b098b7e576931d61815fe07373c1185b556 Signed-off-by: Uttkarsh Aggarwal --- drivers/usb/dwc3/gadget.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 905fd2774cb0..35fd2c4fa82f 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2604,13 +2604,16 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) * device-initiated disconnect requires a core soft reset * (DCTL.CSftRst) before enabling the run/stop bit. */ - dwc3_core_soft_reset(dwc); + ret = dwc3_core_soft_reset(dwc); + if (ret) + goto done; dwc3_event_buffers_setup(dwc); __dwc3_gadget_start(dwc); ret = dwc3_gadget_run_stop(dwc, true, false); } +done: pm_runtime_put(dwc->dev); return ret; From 7cc458acf42c60f417156694c4e5a43a99d5cfe1 Mon Sep 17 00:00:00 2001 From: Krishna Kurapati Date: Sun, 21 May 2023 00:03:13 +0530 Subject: [PATCH 3301/4345] BACKPORT: usb: gadget: udc: Handle gadget_connect failure during bind operation In the event, gadget_connect call (which invokes pullup) fails, propagate the error to udc bind operation which inturn sends the error to configfs. The userspace can then retry enumeartion if it chooses to. Signed-off-by: Krishna Kurapati Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230510075252.31023-3-quic_kriskura@quicinc.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit d34f9bafa78da2a561c67d9daf55fc4d1d80edf0 https://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git/ usb- next) Bug: 284900975 Change-Id: I43925bafc6ba7b08e8c501502a0fa58ee40e6526 Signed-off-by: Krishna Kurapati (cherry picked from commit 8faa860f5594a68e5ecf97bb632e59097da23d14) --- drivers/usb/gadget/udc/core.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 7a00af1f9624..237f9cc8bfba 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1047,12 +1047,16 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ -static void usb_udc_connect_control(struct usb_udc *udc) +static int usb_udc_connect_control(struct usb_udc *udc) { + int ret; + if (udc->vbus) - usb_gadget_connect(udc->gadget); + ret = usb_gadget_connect(udc->gadget); else - usb_gadget_disconnect(udc->gadget); + ret = usb_gadget_disconnect(udc->gadget); + + return ret; } /** @@ -1507,15 +1511,26 @@ static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *dri if (ret) goto err1; ret = usb_gadget_udc_start(udc); - if (ret) { - driver->unbind(udc->gadget); - goto err1; - } + if (ret) + goto err_start; + usb_gadget_enable_async_callbacks(udc); - usb_udc_connect_control(udc); + ret = usb_udc_connect_control(udc); + if (ret) + goto err_connect_control; kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; + +err_connect_control: + usb_gadget_disable_async_callbacks(udc); + if (udc->gadget->irq) + synchronize_irq(udc->gadget->irq); + usb_gadget_udc_stop(udc); + +err_start: + driver->unbind(udc->gadget); + err1: if (ret != -EISNAM) dev_err(&udc->dev, "failed to start %s: %d\n", From 2246168a72ec76f45c4b27016be238ba988ea94a Mon Sep 17 00:00:00 2001 From: Dezhi Huang Date: Mon, 22 May 2023 21:24:45 +0800 Subject: [PATCH 3302/4345] ANDROID: fix a race between speculative page walk and unmap operations Speculative page fault walks the page tables under RCU protection and assumes that page tables are stable after ptl lock is taken. Current implementation has three issues: 1. While pmd can't be destroyed while in RCU read section, it can be cleared and result in an invalid ptl lock address. Fix that by rechecking pmd value after obtaining ptl lock. 2. In case of CONFIG_ALLOC_SPLIT_PTLOCKS, ptl lock is separate from the pmd and is destroyed by a synchronous call to pgtable_pmd_page_dtor, which can happen while page walker is in RCU section. Prevent this by adding a dependency for CONFIG_SPECULATIVE_PAGE_FAULT to require !CONIG_ALLOC_SPLIT_PTLOCKS. 3. Below sequence when do_mmap happens after the last mmap_seq check would result in use-after-free issue. __pte_map_lock rcu_read_lock() mmap_seq_read_check() ptl = pte_lockptr(vmf->pmd) spin_trylock(ptl) mmap_seq_read_check() mmap_write_lock() do_mmap() unmap_region() unmap_vmas() free_pgtables() ... free_pte_range pmd_clear pte_free_tlb ... call_rcu(tlb_remove_table_rcu) rcu_read_unlock() tlb_remove_table_rcu spin_unlock(ptl) <-- UAF! To prevent that free_pte_range needs to be blocked if ptl is locked and is in use. [tyler wang: This is a backport from https://android-review.googlesource.com/c/kernel/common/+/2330194. We have adapted the corresponding modifications from 5.15 to 5.10, including the changes made to the function __pte_map_lock in 5.15, which have been adapted to the functions pte_spinlock and __pte_map_lock_speculative in 5.10. Additionally, following surenb's suggestion, we have folded https://android-review.googlesource.com/c/kernel/common/+/2368961 in this patch.] Bug: 278602292 Change-Id: I7b353f0995fc59e92bb2069bcdc7d1ac29b521b9 Signed-off-by: Dezhi Huang --- mm/memory.c | 34 +++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 834078ab6e1c..df62ea2ef8f2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -246,6 +246,16 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT + /* + * Ensure page table destruction is blocked if __pte_map_lock managed + * to take this lock. Without this barrier tlb_remove_table_rcu can + * destroy ptl after __pte_map_lock locked it and during unlock would + * cause a use-after-free. + */ + spinlock_t *ptl = pmd_lock(tlb->mm, pmd); + spin_unlock(ptl); +#endif pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); @@ -2627,9 +2637,7 @@ EXPORT_SYMBOL_GPL(apply_to_page_range); static bool pte_spinlock(struct vm_fault *vmf) { bool ret = false; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t pmdval; -#endif /* Check if vma is still valid */ if (!(vmf->flags & FAULT_FLAG_SPECULATIVE)) { @@ -2644,24 +2652,28 @@ static bool pte_spinlock(struct vm_fault *vmf) goto out; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * We check if the pmd value is still the same to ensure that there * is not a huge collapse operation in progress in our back. + * It also ensures that pmd was not cleared by pmd_clear in + * free_pte_range and ptl is still valid. */ pmdval = READ_ONCE(*vmf->pmd); if (!pmd_same(pmdval, vmf->orig_pmd)) { trace_spf_pmd_changed(_RET_IP_, vmf->vma, vmf->address); goto out; } -#endif - vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); + vmf->ptl = pte_lockptr(vmf->vma->vm_mm, &pmdval); if (unlikely(!spin_trylock(vmf->ptl))) { trace_spf_pte_lock(_RET_IP_, vmf->vma, vmf->address); goto out; } + /* + * The check below will fail if pte_spinlock passed its ptl barrier + * before we took the ptl lock. + */ if (vma_has_changed(vmf)) { spin_unlock(vmf->ptl); trace_spf_vma_changed(_RET_IP_, vmf->vma, vmf->address); @@ -2679,9 +2691,7 @@ static bool __pte_map_lock_speculative(struct vm_fault *vmf, unsigned long addr) bool ret = false; pte_t *pte; spinlock_t *ptl; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t pmdval; -#endif /* * The first vma_has_changed() guarantees the page-tables are still @@ -2696,7 +2706,6 @@ static bool __pte_map_lock_speculative(struct vm_fault *vmf, unsigned long addr) goto out; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * We check if the pmd value is still the same to ensure that there * is not a huge collapse operation in progress in our back. @@ -2706,7 +2715,6 @@ static bool __pte_map_lock_speculative(struct vm_fault *vmf, unsigned long addr) trace_spf_pmd_changed(_RET_IP_, vmf->vma, addr); goto out; } -#endif /* * Same as pte_offset_map_lock() except that we call @@ -2715,14 +2723,18 @@ static bool __pte_map_lock_speculative(struct vm_fault *vmf, unsigned long addr) * to invalidate TLB but this CPU has irq disabled. * Since we are in a speculative patch, accept it could fail */ - ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); - pte = pte_offset_map(vmf->pmd, addr); + ptl = pte_lockptr(vmf->vma->vm_mm, &pmdval); + pte = pte_offset_map(&pmdval, addr); if (unlikely(!spin_trylock(ptl))) { pte_unmap(pte); trace_spf_pte_lock(_RET_IP_, vmf->vma, addr); goto out; } + /* + * The check below will fail if __pte_map_lock_speculative passed its ptl + * barrier before we took the ptl lock. + */ if (vma_has_changed(vmf)) { pte_unmap_unlock(pte, ptl); trace_spf_vma_changed(_RET_IP_, vmf->vma, addr); From 403d5d1318c9b82b70c44a76e3ddbadf42a7838a Mon Sep 17 00:00:00 2001 From: xieliujie Date: Tue, 6 Jun 2023 20:45:12 +0800 Subject: [PATCH 3303/4345] ANDROID: vendor_hook: Avoid clearing protect-flag before waking waiters With hooks below, we can mark a lock-owned thread with an identifiable flag, which can protect it from being preempted by some other unimportant threads, and then waiter will be wakeup more quickly. https://android-review.googlesource.com/c/kernel/common/+/2183353 but now we find an issue like this one: static inline void __up_write(struct rw_semaphore *sem) { ... // Step 1. we clear flag. trace_android_vh_record_rwsem_lock_starttime(current, 0); // Step 2. owner may be preempted by unimportant threads. rwsem_clear_owner(sem); ... // Step 3. wake up waiter, but it's too later. if (unlikely(tmp & RWSEM_FLAG_WAITERS)) rwsem_wake(sem); } This patch will clear protect-flag after waking up waiters. Bug: 286024926 Change-Id: I71f8b6a7d8a01336fd36b8267c2cb5edab65bd11 Signed-off-by: xieliujie --- include/linux/percpu-rwsem.h | 2 +- kernel/locking/mutex.c | 2 +- kernel/locking/percpu-rwsem.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 92d172cfce06..55e80d18628d 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -107,7 +107,6 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) static inline void percpu_up_read(struct percpu_rw_semaphore *sem) { - _trace_android_vh_record_pcpu_rwsem_starttime(current, 0); rwsem_release(&sem->dep_map, _RET_IP_); preempt_disable(); @@ -130,6 +129,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } + _trace_android_vh_record_pcpu_rwsem_starttime(current, 0); preempt_enable(); } diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index b9a10aacb139..be121ed70d7c 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -760,12 +760,12 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne */ void __sched mutex_unlock(struct mutex *lock) { - trace_android_vh_record_mutex_lock_starttime(current, 0); #ifndef CONFIG_DEBUG_LOCK_ALLOC if (__mutex_unlock_fast(lock)) return; #endif __mutex_unlock_slowpath(lock, _RET_IP_); + trace_android_vh_record_mutex_lock_starttime(current, 0); } EXPORT_SYMBOL(mutex_unlock); diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index c8a474aa1b3b..915c045a15f3 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -258,7 +258,6 @@ EXPORT_SYMBOL_GPL(percpu_down_write); void percpu_up_write(struct percpu_rw_semaphore *sem) { - trace_android_vh_record_pcpu_rwsem_starttime(current, 0); rwsem_release(&sem->dep_map, _RET_IP_); /* @@ -284,6 +283,7 @@ void percpu_up_write(struct percpu_rw_semaphore *sem) * exclusive write lock because its counting. */ rcu_sync_exit(&sem->rss); + trace_android_vh_record_pcpu_rwsem_starttime(current, 0); } EXPORT_SYMBOL_GPL(percpu_up_write); From b51c8962853e1f308131b2cbcfbbc7b30fe5fd67 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Thu, 7 Jan 2021 01:43:27 -0800 Subject: [PATCH 3304/4345] RDMA/bnxt_re: Code refactor while populating user MRs [ Upstream commit f6919d56388c95dba2e630670a77c380e4616c50 ] Refactor code that populates MR page buffer list. Instead of allocating a pbl_tbl to hold the buffer list, pass the struct ib_umem directly to bnxt_qplib_alloc_init_hwq() as done for other user space memories. Fix the PBL level to handle the above mentioned change. Also, remove an unwanted flag from the input to bnxt_qplib_reg_mr() function. Link: https://lore.kernel.org/r/1610012608-14528-2-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Devesh Sharma Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Stable-dep-of: 08c7f09356e4 ("RDMA/bnxt_re: Fix the page_size used during the MR creation") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 41 ++++-------------------- drivers/infiniband/hw/bnxt_re/qplib_sp.c | 17 ++++------ drivers/infiniband/hw/bnxt_re/qplib_sp.h | 2 +- 3 files changed, 13 insertions(+), 47 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 10d77f50f818..85fecb432aa0 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -469,7 +469,6 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd) struct bnxt_re_mr *mr = NULL; dma_addr_t dma_addr = 0; struct ib_mw *mw; - u64 pbl_tbl; int rc; dma_addr = dma_map_single(dev, fence->va, BNXT_RE_FENCE_BYTES, @@ -504,9 +503,8 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd) mr->ib_mr.lkey = mr->qplib_mr.lkey; mr->qplib_mr.va = (u64)(unsigned long)fence->va; mr->qplib_mr.total_size = BNXT_RE_FENCE_BYTES; - pbl_tbl = dma_addr; - rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, &pbl_tbl, - BNXT_RE_FENCE_PBL_SIZE, false, PAGE_SIZE); + rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, NULL, + BNXT_RE_FENCE_PBL_SIZE, PAGE_SIZE); if (rc) { ibdev_err(&rdev->ibdev, "Failed to register fence-MR\n"); goto fail; @@ -3588,7 +3586,6 @@ struct ib_mr *bnxt_re_get_dma_mr(struct ib_pd *ib_pd, int mr_access_flags) struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd); struct bnxt_re_dev *rdev = pd->rdev; struct bnxt_re_mr *mr; - u64 pbl = 0; int rc; mr = kzalloc(sizeof(*mr), GFP_KERNEL); @@ -3607,7 +3604,7 @@ struct ib_mr *bnxt_re_get_dma_mr(struct ib_pd *ib_pd, int mr_access_flags) mr->qplib_mr.hwq.level = PBL_LVL_MAX; mr->qplib_mr.total_size = -1; /* Infinte length */ - rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, &pbl, 0, false, + rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, NULL, 0, PAGE_SIZE); if (rc) goto fail_mr; @@ -3778,19 +3775,6 @@ int bnxt_re_dealloc_mw(struct ib_mw *ib_mw) return rc; } -static int fill_umem_pbl_tbl(struct ib_umem *umem, u64 *pbl_tbl_orig, - int page_shift) -{ - u64 *pbl_tbl = pbl_tbl_orig; - u64 page_size = BIT_ULL(page_shift); - struct ib_block_iter biter; - - rdma_umem_for_each_dma_block(umem, &biter, page_size) - *pbl_tbl++ = rdma_block_iter_dma_address(&biter); - - return pbl_tbl - pbl_tbl_orig; -} - /* uverbs */ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags, @@ -3800,7 +3784,6 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length, struct bnxt_re_dev *rdev = pd->rdev; struct bnxt_re_mr *mr; struct ib_umem *umem; - u64 *pbl_tbl = NULL; unsigned long page_size; int umem_pgs, rc; @@ -3854,30 +3837,18 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length, } umem_pgs = ib_umem_num_dma_blocks(umem, page_size); - pbl_tbl = kcalloc(umem_pgs, sizeof(*pbl_tbl), GFP_KERNEL); - if (!pbl_tbl) { - rc = -ENOMEM; - goto free_umem; - } - - /* Map umem buf ptrs to the PBL */ - umem_pgs = fill_umem_pbl_tbl(umem, pbl_tbl, order_base_2(page_size)); - rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, pbl_tbl, - umem_pgs, false, page_size); + rc = bnxt_qplib_reg_mr(&rdev->qplib_res, &mr->qplib_mr, umem, + umem_pgs, page_size); if (rc) { ibdev_err(&rdev->ibdev, "Failed to register user MR"); - goto fail; + goto free_umem; } - kfree(pbl_tbl); - mr->ib_mr.lkey = mr->qplib_mr.lkey; mr->ib_mr.rkey = mr->qplib_mr.lkey; atomic_inc(&rdev->mr_count); return &mr->ib_mr; -fail: - kfree(pbl_tbl); free_umem: ib_umem_release(umem); free_mrw: diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 64d44f51db4b..4afa33f58b10 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -650,16 +650,15 @@ int bnxt_qplib_dereg_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw, } int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, - u64 *pbl_tbl, int num_pbls, bool block, u32 buf_pg_size) + struct ib_umem *umem, int num_pbls, u32 buf_pg_size) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct bnxt_qplib_hwq_attr hwq_attr = {}; struct bnxt_qplib_sg_info sginfo = {}; struct creq_register_mr_resp resp; struct cmdq_register_mr req; - int pg_ptrs, pages, i, rc; u16 cmd_flags = 0, level; - dma_addr_t **pbl_ptr; + int pages, rc, pg_ptrs; u32 pg_size; if (num_pbls) { @@ -683,9 +682,10 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, /* Use system PAGE_SIZE */ hwq_attr.res = res; hwq_attr.depth = pages; - hwq_attr.stride = PAGE_SIZE; + hwq_attr.stride = buf_pg_size; hwq_attr.type = HWQ_TYPE_MR; hwq_attr.sginfo = &sginfo; + hwq_attr.sginfo->umem = umem; hwq_attr.sginfo->npages = pages; hwq_attr.sginfo->pgsize = PAGE_SIZE; hwq_attr.sginfo->pgshft = PAGE_SHIFT; @@ -695,11 +695,6 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, "SP: Reg MR memory allocation failed\n"); return -ENOMEM; } - /* Write to the hwq */ - pbl_ptr = (dma_addr_t **)mr->hwq.pbl_ptr; - for (i = 0; i < num_pbls; i++) - pbl_ptr[PTR_PG(i)][PTR_IDX(i)] = - (pbl_tbl[i] & PAGE_MASK) | PTU_PTE_VALID; } RCFW_CMD_PREP(req, REGISTER_MR, cmd_flags); @@ -711,7 +706,7 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, req.pbl = 0; pg_size = PAGE_SIZE; } else { - level = mr->hwq.level + 1; + level = mr->hwq.level; req.pbl = cpu_to_le64(mr->hwq.pbl[PBL_LVL_0].pg_map_arr[0]); } pg_size = buf_pg_size ? buf_pg_size : PAGE_SIZE; @@ -728,7 +723,7 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, req.mr_size = cpu_to_le64(mr->total_size); rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, block); + (void *)&resp, NULL, false); if (rc) goto fail; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index 967890cd81f2..bc228340684f 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -254,7 +254,7 @@ int bnxt_qplib_alloc_mrw(struct bnxt_qplib_res *res, int bnxt_qplib_dereg_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw, bool block); int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, - u64 *pbl_tbl, int num_pbls, bool block, u32 buf_pg_size); + struct ib_umem *umem, int num_pbls, u32 buf_pg_size); int bnxt_qplib_free_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr); int bnxt_qplib_alloc_fast_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, int max); From 7d6662e4a4b6d6e8ca2a61d7e64841d06a81148a Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Sun, 7 May 2023 11:29:29 -0700 Subject: [PATCH 3305/4345] RDMA/bnxt_re: Fix the page_size used during the MR creation [ Upstream commit 08c7f09356e45d093d1867c7a3c6ac6526e2f98b ] Driver populates the list of pages used for Memory region wrongly when page size is more than system page size. This is causing a failure when some of the applications that creates MR with page size as 2M. Since HW can support multiple page sizes, pass the correct page size while creating the MR. Also, driver need not adjust the number of pages when HW Queues are created with user memory. It should work with the number of dma blocks returned by ib_umem_num_dma_blocks. Fix this calculation also. Fixes: 0c4dcd602817 ("RDMA/bnxt_re: Refactor hardware queue memory allocation") Fixes: f6919d56388c ("RDMA/bnxt_re: Code refactor while populating user MRs") Link: https://lore.kernel.org/r/1683484169-9539-1-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Kalesh AP Signed-off-by: Kashyap Desai Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/qplib_res.c | 12 ++---------- drivers/infiniband/hw/bnxt_re/qplib_sp.c | 7 +++---- 2 files changed, 5 insertions(+), 14 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 754dcebeb4ca..123ea759f282 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -215,17 +215,9 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, return -EINVAL; hwq_attr->sginfo->npages = npages; } else { - unsigned long sginfo_num_pages = ib_umem_num_dma_blocks( - hwq_attr->sginfo->umem, hwq_attr->sginfo->pgsize); - + npages = ib_umem_num_dma_blocks(hwq_attr->sginfo->umem, + hwq_attr->sginfo->pgsize); hwq->is_user = true; - npages = sginfo_num_pages; - npages = (npages * PAGE_SIZE) / - BIT_ULL(hwq_attr->sginfo->pgshft); - if ((sginfo_num_pages * PAGE_SIZE) % - BIT_ULL(hwq_attr->sginfo->pgshft)) - if (!npages) - npages++; } if (npages == MAX_PBL_LVL_0_PGS) { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 4afa33f58b10..f53d94c812ec 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -679,16 +679,15 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, /* Free the hwq if it already exist, must be a rereg */ if (mr->hwq.max_elements) bnxt_qplib_free_hwq(res, &mr->hwq); - /* Use system PAGE_SIZE */ hwq_attr.res = res; hwq_attr.depth = pages; - hwq_attr.stride = buf_pg_size; + hwq_attr.stride = sizeof(dma_addr_t); hwq_attr.type = HWQ_TYPE_MR; hwq_attr.sginfo = &sginfo; hwq_attr.sginfo->umem = umem; hwq_attr.sginfo->npages = pages; - hwq_attr.sginfo->pgsize = PAGE_SIZE; - hwq_attr.sginfo->pgshft = PAGE_SHIFT; + hwq_attr.sginfo->pgsize = buf_pg_size; + hwq_attr.sginfo->pgshft = ilog2(buf_pg_size); rc = bnxt_qplib_alloc_init_hwq(&mr->hwq, &hwq_attr); if (rc) { dev_err(&res->pdev->dev, From 958226b3a6637e3a61fa02412a2014e67034c3c0 Mon Sep 17 00:00:00 2001 From: Yonatan Nachum Date: Thu, 11 May 2023 11:51:03 +0000 Subject: [PATCH 3306/4345] RDMA/efa: Fix unsupported page sizes in device [ Upstream commit 866422cdddcdf59d8c68e9472d49ba1be29b5fcf ] Device uses 4KB size blocks for user pages indirect list while the driver creates those blocks with the size of PAGE_SIZE of the kernel. On kernels with PAGE_SIZE different than 4KB (ARM RHEL), this leads to a failure on register MR with indirect list because of the miss communication between driver and device. Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation") Link: https://lore.kernel.org/r/20230511115103.13876-1-ynachum@amazon.com Reviewed-by: Firas Jahjah Reviewed-by: Michael Margolin Signed-off-by: Yonatan Nachum Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/efa/efa_verbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 2ece682c7835..9cf051818725 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1328,7 +1328,7 @@ static int pbl_continuous_initialize(struct efa_dev *dev, */ static int pbl_indirect_initialize(struct efa_dev *dev, struct pbl_context *pbl) { - u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, PAGE_SIZE); + u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, EFA_CHUNK_PAYLOAD_SIZE); struct scatterlist *sgl; int sg_dma_cnt, err; From 127afc87bb0219bcf1b52a97eed701e7e33d1111 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 15 Dec 2021 13:01:07 +0200 Subject: [PATCH 3307/4345] dmaengine: at_xdmac: Fix concurrency over chan's completed_cookie [ Upstream commit 506875c30fc5bf92246060bc3b4c38799646266b ] Caller of dma_cookie_complete is expected to hold a lock to prevent concurrency over the channel's completed cookie marker. Call dma_cookie_complete() with the lock held. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20211215110115.191749-5-tudor.ambarus@microchip.com Signed-off-by: Vinod Koul Stable-dep-of: 4d43acb145c3 ("dmaengine: at_xdmac: fix potential Oops in at_xdmac_prep_interleaved()") Signed-off-by: Sasha Levin --- drivers/dma/at_xdmac.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 1fe006cc643e..501196d8c488 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1651,11 +1651,10 @@ static void at_xdmac_tasklet(struct tasklet_struct *t) } txd = &desc->tx_dma_desc; - + dma_cookie_complete(txd); at_xdmac_remove_xfer(atchan, desc); spin_unlock_irq(&atchan->lock); - dma_cookie_complete(txd); if (txd->flags & DMA_PREP_INTERRUPT) dmaengine_desc_get_callback_invoke(txd, NULL); From 3041b768cc0f307f0785c3b0fbd819727aae8d26 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 15 Dec 2021 13:01:08 +0200 Subject: [PATCH 3308/4345] dmaengine: at_xdmac: Fix race for the tx desc callback [ Upstream commit b63e5cb94ad6947ab5fe38b5a9417dcfd0bc6122 ] The transfer descriptors were wrongly moved to the free descriptors list before calling the tx desc callback. As the DMA engine drivers drop any locks before calling the callback function, txd could be taken again, resulting in its callback called prematurely. Fix the race for the tx desc callback by moving the xfer desc into the free desc list after the callback is invoked. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20211215110115.191749-6-tudor.ambarus@microchip.com Signed-off-by: Vinod Koul Stable-dep-of: 4d43acb145c3 ("dmaengine: at_xdmac: fix potential Oops in at_xdmac_prep_interleaved()") Signed-off-by: Sasha Levin --- drivers/dma/at_xdmac.c | 25 ++++++++----------------- 1 file changed, 8 insertions(+), 17 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 501196d8c488..8af1c0fd3a73 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1527,20 +1527,6 @@ spin_unlock: return ret; } -/* Call must be protected by lock. */ -static void at_xdmac_remove_xfer(struct at_xdmac_chan *atchan, - struct at_xdmac_desc *desc) -{ - dev_dbg(chan2dev(&atchan->chan), "%s: desc 0x%p\n", __func__, desc); - - /* - * Remove the transfer from the transfer list then move the transfer - * descriptors into the free descriptors list. - */ - list_del(&desc->xfer_node); - list_splice_init(&desc->descs_list, &atchan->free_descs_list); -} - static void at_xdmac_advance_work(struct at_xdmac_chan *atchan) { struct at_xdmac_desc *desc; @@ -1652,7 +1638,8 @@ static void at_xdmac_tasklet(struct tasklet_struct *t) txd = &desc->tx_dma_desc; dma_cookie_complete(txd); - at_xdmac_remove_xfer(atchan, desc); + /* Remove the transfer from the transfer list. */ + list_del(&desc->xfer_node); spin_unlock_irq(&atchan->lock); if (txd->flags & DMA_PREP_INTERRUPT) @@ -1661,6 +1648,8 @@ static void at_xdmac_tasklet(struct tasklet_struct *t) dma_run_dependencies(txd); spin_lock_irq(&atchan->lock); + /* Move the xfer descriptors into the free descriptors list. */ + list_splice_init(&desc->descs_list, &atchan->free_descs_list); at_xdmac_advance_work(atchan); spin_unlock_irq(&atchan->lock); } @@ -1807,8 +1796,10 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan) cpu_relax(); /* Cancel all pending transfers. */ - list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node) - at_xdmac_remove_xfer(atchan, desc); + list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node) { + list_del(&desc->xfer_node); + list_splice_init(&desc->descs_list, &atchan->free_descs_list); + } clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status); clear_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status); From 6b32ed353f44b622c8fbcec60453ade8d17b63f1 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 15 Dec 2021 13:01:09 +0200 Subject: [PATCH 3309/4345] dmaengine: at_xdmac: Move the free desc to the tail of the desc list [ Upstream commit 801db90bf294f647b967e8d99b9ae121bea63d0d ] Move the free desc to the tail of the list, so that the sequence of descriptors is more track-able in case of debug. One would know which descriptor should come next and could easier catch concurrency over descriptors for example. virt-dma uses list_splice_tail_init() as well, follow the core driver. Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20211215110115.191749-7-tudor.ambarus@microchip.com Signed-off-by: Vinod Koul Stable-dep-of: 4d43acb145c3 ("dmaengine: at_xdmac: fix potential Oops in at_xdmac_prep_interleaved()") Signed-off-by: Sasha Levin --- drivers/dma/at_xdmac.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 8af1c0fd3a73..96559c5df944 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -678,7 +678,8 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, if (!desc) { dev_err(chan2dev(chan), "can't get descriptor\n"); if (first) - list_splice_init(&first->descs_list, &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); goto spin_unlock; } @@ -766,7 +767,8 @@ at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, if (!desc) { dev_err(chan2dev(chan), "can't get descriptor\n"); if (first) - list_splice_init(&first->descs_list, &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); spin_unlock_irqrestore(&atchan->lock, irqflags); return NULL; } @@ -998,8 +1000,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, src_addr, dst_addr, xt, chunk); if (!desc) { - list_splice_init(&first->descs_list, - &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } @@ -1077,7 +1079,8 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, if (!desc) { dev_err(chan2dev(chan), "can't get descriptor\n"); if (first) - list_splice_init(&first->descs_list, &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } @@ -1251,8 +1254,8 @@ at_xdmac_prep_dma_memset_sg(struct dma_chan *chan, struct scatterlist *sgl, sg_dma_len(sg), value); if (!desc && first) - list_splice_init(&first->descs_list, - &atchan->free_descs_list); + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); if (!first) first = desc; @@ -1649,7 +1652,8 @@ static void at_xdmac_tasklet(struct tasklet_struct *t) spin_lock_irq(&atchan->lock); /* Move the xfer descriptors into the free descriptors list. */ - list_splice_init(&desc->descs_list, &atchan->free_descs_list); + list_splice_tail_init(&desc->descs_list, + &atchan->free_descs_list); at_xdmac_advance_work(atchan); spin_unlock_irq(&atchan->lock); } @@ -1798,7 +1802,8 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan) /* Cancel all pending transfers. */ list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node) { list_del(&desc->xfer_node); - list_splice_init(&desc->descs_list, &atchan->free_descs_list); + list_splice_tail_init(&desc->descs_list, + &atchan->free_descs_list); } clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status); From ff296fccebcbe0404994879d1ebb4b2d43dea6cd Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 15 May 2023 13:32:10 +0300 Subject: [PATCH 3310/4345] dmaengine: at_xdmac: fix potential Oops in at_xdmac_prep_interleaved() [ Upstream commit 4d43acb145c363626d76f49febb4240c488cd1cf ] There are two place if the at_xdmac_interleaved_queue_desc() fails which could lead to a NULL dereference where "first" is NULL and we call list_add_tail(&first->desc_node, ...). In the first caller, the return is not checked so add a check for that. In the next caller, the return is checked but if it fails on the first iteration through the loop then it will lead to a NULL pointer dereference. Fixes: 4e5385784e69 ("dmaengine: at_xdmac: handle numf > 1") Fixes: 62b5cb757f1d ("dmaengine: at_xdmac: fix memory leak in interleaved mode") Signed-off-by: Dan Carpenter Reviewed-by: Tudor Ambarus Link: https://lore.kernel.org/r/21282b66-9860-410a-83df-39c17fcf2f1b@kili.mountain Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/at_xdmac.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 96559c5df944..861be862a775 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -970,6 +970,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, NULL, src_addr, dst_addr, xt, xt->sgl); + if (!first) + return NULL; /* Length of the block is (BLEN+1) microblocks. */ for (i = 0; i < xt->numf - 1; i++) @@ -1000,8 +1002,9 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, src_addr, dst_addr, xt, chunk); if (!desc) { - list_splice_tail_init(&first->descs_list, - &atchan->free_descs_list); + if (first) + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } From 861868b06304197a0bb81504f26d3ef1b160e797 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Thu, 18 May 2023 01:10:59 -0700 Subject: [PATCH 3311/4345] RDMA/bnxt_re: Fix a possible memory leak [ Upstream commit 349e3c0cf239cc01d58a1e6c749e171de014cd6a ] Inside bnxt_qplib_create_cq(), when the check for NULL DPI fails, driver returns directly without freeing the memory allocated inside bnxt_qplib_alloc_init_hwq() routine. Fixed this by moving the check for NULL DPI before invoking bnxt_qplib_alloc_init_hwq(). Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Link: https://lore.kernel.org/r/1684397461-23082-2-git-send-email-selvin.xavier@broadcom.com Reviewed-by: Kashyap Desai Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index bd153aa7e9ab..b26a89187a19 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -2041,6 +2041,12 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) u32 pg_sz_lvl; int rc; + if (!cq->dpi) { + dev_err(&rcfw->pdev->dev, + "FP: CREATE_CQ failed due to NULL DPI\n"); + return -EINVAL; + } + hwq_attr.res = res; hwq_attr.depth = cq->max_wqe; hwq_attr.stride = sizeof(struct cq_base); @@ -2052,11 +2058,6 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) RCFW_CMD_PREP(req, CREATE_CQ, cmd_flags); - if (!cq->dpi) { - dev_err(&rcfw->pdev->dev, - "FP: CREATE_CQ failed due to NULL DPI\n"); - return -EINVAL; - } req.dpi = cpu_to_le32(cq->dpi->dpi); req.cq_handle = cpu_to_le64(cq->cq_handle); req.cq_size = cpu_to_le32(cq->hwq.max_elements); From 75c60dacf0b49a42faa630b4231600b3495546b3 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Thu, 18 May 2023 01:11:00 -0700 Subject: [PATCH 3312/4345] RDMA/bnxt_re: Fix return value of bnxt_re_process_raw_qp_pkt_rx [ Upstream commit 0fa0d520e2a878cb4c94c4dc84395905d3f14f54 ] bnxt_re_process_raw_qp_pkt_rx() always return 0 and ignores the return value of bnxt_re_post_send_shadow_qp(). Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Link: https://lore.kernel.org/r/1684397461-23082-3-git-send-email-selvin.xavier@broadcom.com Reviewed-by: Hongguang Gao Reviewed-by: Ajit Khaparde Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 85fecb432aa0..2a973a1390a4 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -3247,9 +3247,7 @@ static int bnxt_re_process_raw_qp_pkt_rx(struct bnxt_re_qp *gsi_qp, udwr.remote_qkey = gsi_sqp->qplib_qp.qkey; /* post data received in the send queue */ - rc = bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); - - return 0; + return bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); } static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc, From bd9e61ee3e9ddb756f8c35786e71ab801831af67 Mon Sep 17 00:00:00 2001 From: Chao Wang Date: Mon, 17 Apr 2023 03:04:21 +0000 Subject: [PATCH 3313/4345] iommu/rockchip: Fix unwind goto issue [ Upstream commit ec014683c564fb74fc68e8f5e84691d3b3839d24 ] Smatch complains that drivers/iommu/rockchip-iommu.c:1306 rk_iommu_probe() warn: missing unwind goto? The rk_iommu_probe function, after obtaining the irq value through platform_get_irq, directly returns an error if the returned value is negative, without releasing any resources. Fix this by adding a new error handling label "err_pm_disable" and use a goto statement to redirect to the error handling process. In order to preserve the original semantics, set err to the value of irq. Fixes: 1aa55ca9b14a ("iommu/rockchip: Move irq request past pm_runtime_enable") Signed-off-by: Chao Wang Reviewed-by: Dongliang Mu Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230417030421.2777-1-D202280639@hust.edu.cn Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/rockchip-iommu.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index e5d86b7177de..12551dc11714 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1218,18 +1218,20 @@ static int rk_iommu_probe(struct platform_device *pdev) for (i = 0; i < iommu->num_irq; i++) { int irq = platform_get_irq(pdev, i); - if (irq < 0) - return irq; + if (irq < 0) { + err = irq; + goto err_pm_disable; + } err = devm_request_irq(iommu->dev, irq, rk_iommu_irq, IRQF_SHARED, dev_name(dev), iommu); - if (err) { - pm_runtime_disable(dev); - goto err_remove_sysfs; - } + if (err) + goto err_pm_disable; } return 0; +err_pm_disable: + pm_runtime_disable(dev); err_remove_sysfs: iommu_device_sysfs_remove(&iommu->iommu); err_put_group: From 33d7035dc22490a936229b70502338a0a25ac56c Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Wed, 19 Apr 2023 21:11:53 +0100 Subject: [PATCH 3314/4345] iommu/amd: Don't block updates to GATag if guest mode is on [ Upstream commit ed8a2f4ddef2eaaf864ab1efbbca9788187036ab ] On KVM GSI routing table updates, specially those where they have vIOMMUs with interrupt remapping enabled (to boot >255vcpus setups without relying on KVM_FEATURE_MSI_EXT_DEST_ID), a VMM may update the backing VF MSIs with a new VCPU affinity. On AMD with AVIC enabled, the new vcpu affinity info is updated via: avic_pi_update_irte() irq_set_vcpu_affinity() amd_ir_set_vcpu_affinity() amd_iommu_{de}activate_guest_mode() Where the IRTE[GATag] is updated with the new vcpu affinity. The GATag contains VM ID and VCPU ID, and is used by IOMMU hardware to signal KVM (via GALog) when interrupt cannot be delivered due to vCPU is in blocking state. The issue is that amd_iommu_activate_guest_mode() will essentially only change IRTE fields on transitions from non-guest-mode to guest-mode and otherwise returns *with no changes to IRTE* on already configured guest-mode interrupts. To the guest this means that the VF interrupts remain affined to the first vCPU they were first configured, and guest will be unable to issue VF interrupts and receive messages like this from spurious interrupts (e.g. from waking the wrong vCPU in GALog): [ 167.759472] __common_interrupt: 3.34 No irq handler for vector [ 230.680927] mlx5_core 0000:00:02.0: mlx5_cmd_eq_recover:247:(pid 3122): Recovered 1 EQEs on cmd_eq [ 230.681799] mlx5_core 0000:00:02.0: wait_func_handle_exec_timeout:1113:(pid 3122): cmd[0]: CREATE_CQ(0x400) recovered after timeout [ 230.683266] __common_interrupt: 3.34 No irq handler for vector Given the fact that amd_ir_set_vcpu_affinity() uses amd_iommu_activate_guest_mode() underneath it essentially means that VCPU affinity changes of IRTEs are nops. Fix it by dropping the check for guest-mode at amd_iommu_activate_guest_mode(). Same thing is applicable to amd_iommu_deactivate_guest_mode() although, even if the IRTE doesn't change underlying DestID on the host, the VFIO IRQ handler will still be able to poke at the right guest-vCPU. Fixes: b9c6ff94e43a ("iommu/amd: Re-factor guest virtual APIC (de-)activation code") Signed-off-by: Joao Martins Reviewed-by: Suravee Suthikulpanit Link: https://lore.kernel.org/r/20230419201154.83880-2-joao.m.martins@oracle.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/amd/iommu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index f216a86d9c81..0a061a196b53 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -3914,8 +3914,7 @@ int amd_iommu_activate_guest_mode(void *data) struct irte_ga *entry = (struct irte_ga *) ir_data->entry; u64 valid; - if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || - !entry || entry->lo.fields_vapic.guest_mode) + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry) return 0; valid = entry->lo.fields_vapic.valid; From a864a8543cd5cd542cc397dff4cf4e36e9bab9f2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 23 May 2023 21:53:10 -0700 Subject: [PATCH 3315/4345] dmaengine: pl330: rename _start to prevent build error [ Upstream commit a1a5f2c887252dec161c1e12e04303ca9ba56fa9 ] "_start" is used in several arches and proably should be reserved for ARCH usage. Using it in a driver for a private symbol can cause a build error when it conflicts with ARCH usage of the same symbol. Therefore rename pl330's "_start" to "pl330_start_thread" so that there is no conflict and no build error. drivers/dma/pl330.c:1053:13: error: '_start' redeclared as different kind of symbol 1053 | static bool _start(struct pl330_thread *thrd) | ^~~~~~ In file included from ../include/linux/interrupt.h:21, from ../drivers/dma/pl330.c:18: arch/riscv/include/asm/sections.h:11:13: note: previous declaration of '_start' with type 'char[]' 11 | extern char _start[]; | ^~~~~~ Fixes: b7d861d93945 ("DMA: PL330: Merge PL330 driver into drivers/dma/") Fixes: ae43b3289186 ("ARM: 8202/1: dmaengine: pl330: Add runtime Power Management support v12") Signed-off-by: Randy Dunlap Cc: Jaswinder Singh Cc: Boojin Kim Cc: Krzysztof Kozlowski Cc: Russell King Cc: Vinod Koul Cc: dmaengine@vger.kernel.org Cc: linux-riscv@lists.infradead.org Link: https://lore.kernel.org/r/20230524045310.27923-1-rdunlap@infradead.org Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/dma/pl330.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 5bbae99f2d34..6f697b3f2c18 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1050,7 +1050,7 @@ static bool _trigger(struct pl330_thread *thrd) return true; } -static bool _start(struct pl330_thread *thrd) +static bool pl330_start_thread(struct pl330_thread *thrd) { switch (_state(thrd)) { case PL330_STATE_FAULT_COMPLETING: @@ -1704,7 +1704,7 @@ static int pl330_update(struct pl330_dmac *pl330) thrd->req_running = -1; /* Get going again ASAP */ - _start(thrd); + pl330_start_thread(thrd); /* For now, just make a list of callbacks to be done */ list_add_tail(&descdone->rqd, &pl330->req_done); @@ -2091,7 +2091,7 @@ static void pl330_tasklet(struct tasklet_struct *t) } else { /* Make sure the PL330 Channel thread is active */ spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); } @@ -2109,7 +2109,7 @@ static void pl330_tasklet(struct tasklet_struct *t) if (power_down) { pch->active = true; spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); power_down = false; } From d1b224cb7856e08a8c683dc6c5730bbaad7e241b Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Sat, 29 Apr 2023 20:41:41 +0300 Subject: [PATCH 3316/4345] net/mlx5: fw_tracer, Fix event handling [ Upstream commit 341a80de2468f481b1f771683709b5649cbfe513 ] mlx5 driver needs to parse traces with event_id inside the range of first_string_trace and num_string_trace. However, mlx5 is parsing all events with event_id >= first_string_trace. Fix it by checking for the correct range. Fixes: c71ad41ccb0c ("net/mlx5: FW tracer, events handling") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 0a011a41c039..5273644fb2bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -483,7 +483,7 @@ static void poll_trace(struct mlx5_fw_tracer *tracer, (u64)timestamp_low; break; default: - if (tracer_event->event_id >= tracer->str_db.first_string_trace || + if (tracer_event->event_id >= tracer->str_db.first_string_trace && tracer_event->event_id <= tracer->str_db.first_string_trace + tracer->str_db.num_string_trace) { tracer_event->type = TRACER_EVENT_TYPE_STRING; From 616da05ff8a9aa2e59dc24e70b0a265d48254ded Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 24 May 2023 14:14:56 +0000 Subject: [PATCH 3317/4345] netrom: fix info-leak in nr_write_internal() [ Upstream commit 31642e7089df8fd3f54ca7843f7ee2952978cad1 ] Simon Kapadia reported the following issue: The Online Amateur Radio Community (OARC) has recently been experimenting with building a nationwide packet network in the UK. As part of our experimentation, we have been testing out packet on 300bps HF, and playing with net/rom. For HF packet at this baud rate you really need to make sure that your MTU is relatively low; AX.25 suggests a PACLEN of 60, and a net/rom PACLEN of 40 to go with that. However the Linux net/rom support didn't work with a low PACLEN; the mkiss module would truncate packets if you set the PACLEN below about 200 or so, e.g.: Apr 19 14:00:51 radio kernel: [12985.747310] mkiss: ax1: truncating oversized transmit packet! This didn't make any sense to me (if the packets are smaller why would they be truncated?) so I started investigating. I looked at the packets using ethereal, and found that many were just huge compared to what I would expect. A simple net/rom connection request packet had the request and then a bunch of what appeared to be random data following it: Simon provided a patch that I slightly revised: Not only we must not use skb_tailroom(), we also do not want to count NR_NETWORK_LEN twice. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Co-Developed-by: Simon Kapadia Signed-off-by: Simon Kapadia Signed-off-by: Eric Dumazet Tested-by: Simon Kapadia Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230524141456.1045467-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/netrom/nr_subr.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index 3f99b432ea70..e2d2af924cff 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -123,7 +123,7 @@ void nr_write_internal(struct sock *sk, int frametype) unsigned char *dptr; int len, timeout; - len = NR_NETWORK_LEN + NR_TRANSPORT_LEN; + len = NR_TRANSPORT_LEN; switch (frametype & 0x0F) { case NR_CONNREQ: @@ -141,7 +141,8 @@ void nr_write_internal(struct sock *sk, int frametype) return; } - if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) + skb = alloc_skb(NR_NETWORK_LEN + len, GFP_ATOMIC); + if (!skb) return; /* @@ -149,7 +150,7 @@ void nr_write_internal(struct sock *sk, int frametype) */ skb_reserve(skb, NR_NETWORK_LEN); - dptr = skb_put(skb, skb_tailroom(skb)); + dptr = skb_put(skb, len); switch (frametype & 0x0F) { case NR_CONNREQ: From fa909b138480fceb84aba279a2e5eb018faec20a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 24 May 2023 16:29:34 -0700 Subject: [PATCH 3318/4345] af_packet: Fix data-races of pkt_sk(sk)->num. [ Upstream commit 822b5a1c17df7e338b9f05d1cfe5764e37c7f74f ] syzkaller found a data race of pkt_sk(sk)->num. The value is changed under lock_sock() and po->bind_lock, so we need READ_ONCE() to access pkt_sk(sk)->num without these locks in packet_bind_spkt(), packet_bind(), and sk_diag_fill(). Note that WRITE_ONCE() is already added by commit c7d2ef5dd4b0 ("net/packet: annotate accesses to po->bind"). BUG: KCSAN: data-race in packet_bind / packet_do_bind write (marked) to 0xffff88802ffd1cee of 2 bytes by task 7322 on cpu 0: packet_do_bind+0x446/0x640 net/packet/af_packet.c:3236 packet_bind+0x99/0xe0 net/packet/af_packet.c:3321 __sys_bind+0x19b/0x1e0 net/socket.c:1803 __do_sys_bind net/socket.c:1814 [inline] __se_sys_bind net/socket.c:1812 [inline] __x64_sys_bind+0x40/0x50 net/socket.c:1812 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc read to 0xffff88802ffd1cee of 2 bytes by task 7318 on cpu 1: packet_bind+0xbf/0xe0 net/packet/af_packet.c:3322 __sys_bind+0x19b/0x1e0 net/socket.c:1803 __do_sys_bind net/socket.c:1814 [inline] __se_sys_bind net/socket.c:1812 [inline] __x64_sys_bind+0x40/0x50 net/socket.c:1812 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc value changed: 0x0300 -> 0x0000 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 7318 Comm: syz-executor.4 Not tainted 6.3.0-13380-g7fddb5b5300c #4 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 96ec6327144e ("packet: Diag core and basic socket info dumping") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/r/20230524232934.50950-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/packet/af_packet.c | 4 ++-- net/packet/diag.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3c05414cd3f8..542d5285e99e 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3259,7 +3259,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); name[sizeof(uaddr->sa_data)] = 0; - return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); + return packet_do_bind(sk, name, 0, READ_ONCE(pkt_sk(sk)->num)); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) @@ -3277,7 +3277,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len return -EINVAL; return packet_do_bind(sk, NULL, sll->sll_ifindex, - sll->sll_protocol ? : pkt_sk(sk)->num); + sll->sll_protocol ? : READ_ONCE(pkt_sk(sk)->num)); } static struct proto packet_proto = { diff --git a/net/packet/diag.c b/net/packet/diag.c index d704c7bf51b2..a68a84574c73 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -143,7 +143,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, rp = nlmsg_data(nlh); rp->pdiag_family = AF_PACKET; rp->pdiag_type = sk->sk_type; - rp->pdiag_num = ntohs(po->num); + rp->pdiag_num = ntohs(READ_ONCE(po->num)); rp->pdiag_ino = sk_ino; sock_diag_save_cookie(sk, rp->pdiag_cookie); From 11a1f2561b53be6fba4fd92b2822814bf1f2893c Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Thu, 25 May 2023 23:56:12 +0530 Subject: [PATCH 3319/4345] amd-xgbe: fix the false linkup in xgbe_phy_status [ Upstream commit dc362e20cd6ab7a93d1b09669730c406f0910c35 ] In the event of a change in XGBE mode, the current auto-negotiation needs to be reset and the AN cycle needs to be re-triggerred. However, the current code ignores the return value of xgbe_set_mode(), leading to false information as the link is declared without checking the status register. Fix this by propagating the mode switch status information to xgbe_phy_status(). Fixes: e57f7a3feaef ("amd-xgbe: Prepare for working with more than one type of phy") Co-developed-by: Sudheesh Mavila Signed-off-by: Sudheesh Mavila Reviewed-by: Simon Horman Acked-by: Shyam Sundar S K Signed-off-by: Raju Rangoju Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 43fdd111235a..ca7372369b3e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1312,7 +1312,7 @@ static enum xgbe_mode xgbe_phy_status_aneg(struct xgbe_prv_data *pdata) return pdata->phy_if.phy_impl.an_outcome(pdata); } -static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) +static bool xgbe_phy_status_result(struct xgbe_prv_data *pdata) { struct ethtool_link_ksettings *lks = &pdata->phy.lks; enum xgbe_mode mode; @@ -1347,8 +1347,13 @@ static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) pdata->phy.duplex = DUPLEX_FULL; - if (xgbe_set_mode(pdata, mode) && pdata->an_again) + if (!xgbe_set_mode(pdata, mode)) + return false; + + if (pdata->an_again) xgbe_phy_reconfig_aneg(pdata); + + return true; } static void xgbe_phy_status(struct xgbe_prv_data *pdata) @@ -1378,7 +1383,8 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata) return; } - xgbe_phy_status_result(pdata); + if (xgbe_phy_status_result(pdata)) + return; if (test_bit(XGBE_LINK_INIT, &pdata->dev_state)) clear_bit(XGBE_LINK_INIT, &pdata->dev_state); From 4de3c2c43c6f6c00d9f09276ccc603edfe681fe3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 22:21:24 +0200 Subject: [PATCH 3320/4345] mtd: rawnand: ingenic: fix empty stub helper definitions [ Upstream commit 650a8884a364ff2568b51cde9009cfd43cdae6ad ] A few functions provide an empty interface definition when CONFIG_MTD_NAND_INGENIC_ECC is disabled, but they are accidentally defined as global functions in the header: drivers/mtd/nand/raw/ingenic/ingenic_ecc.h:39:5: error: no previous prototype for 'ingenic_ecc_calculate' drivers/mtd/nand/raw/ingenic/ingenic_ecc.h:46:5: error: no previous prototype for 'ingenic_ecc_correct' drivers/mtd/nand/raw/ingenic/ingenic_ecc.h:53:6: error: no previous prototype for 'ingenic_ecc_release' drivers/mtd/nand/raw/ingenic/ingenic_ecc.h:57:21: error: no previous prototype for 'of_ingenic_ecc_get' Turn them into 'static inline' definitions instead. Fixes: 15de8c6efd0e ("mtd: rawnand: ingenic: Separate top-level and SoC specific code") Signed-off-by: Arnd Bergmann Reviewed-by: Paul Cercueil Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230516202133.559488-1-arnd@kernel.org Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/ingenic/ingenic_ecc.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h b/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h index 2cda439b5e11..017868f59f22 100644 --- a/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h +++ b/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h @@ -36,25 +36,25 @@ int ingenic_ecc_correct(struct ingenic_ecc *ecc, void ingenic_ecc_release(struct ingenic_ecc *ecc); struct ingenic_ecc *of_ingenic_ecc_get(struct device_node *np); #else /* CONFIG_MTD_NAND_INGENIC_ECC */ -int ingenic_ecc_calculate(struct ingenic_ecc *ecc, +static inline int ingenic_ecc_calculate(struct ingenic_ecc *ecc, struct ingenic_ecc_params *params, const u8 *buf, u8 *ecc_code) { return -ENODEV; } -int ingenic_ecc_correct(struct ingenic_ecc *ecc, +static inline int ingenic_ecc_correct(struct ingenic_ecc *ecc, struct ingenic_ecc_params *params, u8 *buf, u8 *ecc_code) { return -ENODEV; } -void ingenic_ecc_release(struct ingenic_ecc *ecc) +static inline void ingenic_ecc_release(struct ingenic_ecc *ecc) { } -struct ingenic_ecc *of_ingenic_ecc_get(struct device_node *np) +static inline struct ingenic_ecc *of_ingenic_ecc_get(struct device_node *np) { return ERR_PTR(-ENODEV); } From 8f0365a3e2862e64be9cb77915f23f1feb31d3e5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 26 May 2023 15:43:42 +0000 Subject: [PATCH 3321/4345] af_packet: do not use READ_ONCE() in packet_bind() [ Upstream commit 6ffc57ea004234d9373c57b204fd10370a69f392 ] A recent patch added READ_ONCE() in packet_bind() and packet_bind_spkt() This is better handled by reading pkt_sk(sk)->num later in packet_do_bind() while appropriate lock is held. READ_ONCE() in writers are often an evidence of something being wrong. Fixes: 822b5a1c17df ("af_packet: Fix data-races of pkt_sk(sk)->num.") Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Reviewed-by: Jiri Pirko Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230526154342.2533026-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/packet/af_packet.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 542d5285e99e..c7129616dd53 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3157,6 +3157,9 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, lock_sock(sk); spin_lock(&po->bind_lock); + if (!proto) + proto = po->num; + rcu_read_lock(); if (po->fanout) { @@ -3259,7 +3262,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); name[sizeof(uaddr->sa_data)] = 0; - return packet_do_bind(sk, name, 0, READ_ONCE(pkt_sk(sk)->num)); + return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) @@ -3276,8 +3279,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len if (sll->sll_family != AF_PACKET) return -EINVAL; - return packet_do_bind(sk, NULL, sll->sll_ifindex, - sll->sll_protocol ? : READ_ONCE(pkt_sk(sk)->num)); + return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { From cccc6209708f59b0d5f0b4853588a720c829a111 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 26 May 2023 16:34:58 +0000 Subject: [PATCH 3322/4345] tcp: deny tcp_disconnect() when threads are waiting [ Upstream commit 4faeee0cf8a5d88d63cdbc3bab124fb0e6aed08c ] Historically connect(AF_UNSPEC) has been abused by syzkaller and other fuzzers to trigger various bugs. A recent one triggers a divide-by-zero [1], and Paolo Abeni was able to diagnose the issue. tcp_recvmsg_locked() has tests about sk_state being not TCP_LISTEN and TCP REPAIR mode being not used. Then later if socket lock is released in sk_wait_data(), another thread can call connect(AF_UNSPEC), then make this socket a TCP listener. When recvmsg() is resumed, it can eventually call tcp_cleanup_rbuf() and attempt a divide by 0 in tcp_rcv_space_adjust() [1] This patch adds a new socket field, counting number of threads blocked in sk_wait_event() and inet_wait_for_connect(). If this counter is not zero, tcp_disconnect() returns an error. This patch adds code in blocking socket system calls, thus should not hurt performance of non blocking ones. Note that we probably could revert commit 499350a5a6e7 ("tcp: initialize rcv_mss to TCP_MIN_MSS instead of 0") to restore original tcpi_rcv_mss meaning (was 0 if no payload was ever received on a socket) [1] divide error: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 13832 Comm: syz-executor.5 Not tainted 6.3.0-rc4-syzkaller-00224-g00c7b5f4ddc5 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 RIP: 0010:tcp_rcv_space_adjust+0x36e/0x9d0 net/ipv4/tcp_input.c:740 Code: 00 00 00 00 fc ff df 4c 89 64 24 48 8b 44 24 04 44 89 f9 41 81 c7 80 03 00 00 c1 e1 04 44 29 f0 48 63 c9 48 01 e9 48 0f af c1 <49> f7 f6 48 8d 04 41 48 89 44 24 40 48 8b 44 24 30 48 c1 e8 03 48 RSP: 0018:ffffc900033af660 EFLAGS: 00010206 RAX: 4a66b76cbade2c48 RBX: ffff888076640cc0 RCX: 00000000c334e4ac RDX: 0000000000000000 RSI: dffffc0000000000 RDI: 0000000000000001 RBP: 00000000c324e86c R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8880766417f8 R13: ffff888028fbb980 R14: 0000000000000000 R15: 0000000000010344 FS: 00007f5bffbfe700(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b32f25000 CR3: 000000007ced0000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcp_recvmsg_locked+0x100e/0x22e0 net/ipv4/tcp.c:2616 tcp_recvmsg+0x117/0x620 net/ipv4/tcp.c:2681 inet6_recvmsg+0x114/0x640 net/ipv6/af_inet6.c:670 sock_recvmsg_nosec net/socket.c:1017 [inline] sock_recvmsg+0xe2/0x160 net/socket.c:1038 ____sys_recvmsg+0x210/0x5a0 net/socket.c:2720 ___sys_recvmsg+0xf2/0x180 net/socket.c:2762 do_recvmmsg+0x25e/0x6e0 net/socket.c:2856 __sys_recvmmsg net/socket.c:2935 [inline] __do_sys_recvmmsg net/socket.c:2958 [inline] __se_sys_recvmmsg net/socket.c:2951 [inline] __x64_sys_recvmmsg+0x20f/0x260 net/socket.c:2951 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f5c0108c0f9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f5bffbfe168 EFLAGS: 00000246 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 00007f5c011ac050 RCX: 00007f5c0108c0f9 RDX: 0000000000000001 RSI: 0000000020000bc0 RDI: 0000000000000003 RBP: 00007f5c010e7b39 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000122 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f5c012cfb1f R14: 00007f5bffbfe300 R15: 0000000000022000 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Reported-by: Paolo Abeni Diagnosed-by: Paolo Abeni Signed-off-by: Eric Dumazet Tested-by: Paolo Abeni Link: https://lore.kernel.org/r/20230526163458.2880232-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/sock.h | 4 ++++ net/ipv4/af_inet.c | 2 ++ net/ipv4/inet_connection_sock.c | 1 + net/ipv4/tcp.c | 6 ++++++ 4 files changed, 13 insertions(+) diff --git a/include/net/sock.h b/include/net/sock.h index 651dc0a7bbd5..3da0601b573e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -326,6 +326,7 @@ struct bpf_local_storage; * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start + * @sk_wait_pending: number of threads blocked on this socket * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available @@ -410,6 +411,7 @@ struct sock { unsigned int sk_napi_id; #endif int sk_rcvbuf; + int sk_wait_pending; struct sk_filter __rcu *sk_filter; union { @@ -1095,6 +1097,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ + __sk->sk_wait_pending++; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ @@ -1104,6 +1107,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } \ sched_annotate_sleep(); \ lock_sock(__sk); \ + __sk->sk_wait_pending--; \ __rc = __condition; \ __rc; \ }) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 800c2c7607e1..acb4887351da 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -584,6 +584,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; + sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -599,6 +600,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; + sk->sk_wait_pending--; return timeo; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e05dd87848f7..406305aaec90 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -839,6 +839,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); + newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index eecce63ba25e..edb743bcbc39 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2748,6 +2748,12 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; + /* Deny disconnect if other threads are blocked in sk_wait_event() + * or inet_wait_for_connect(). + */ + if (sk->sk_wait_pending) + return -EBUSY; + if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); From dfb80ebc3bb450b9eac2c9a90e6cb002b0c1a49f Mon Sep 17 00:00:00 2001 From: Cambda Zhu Date: Sat, 27 May 2023 12:03:17 +0800 Subject: [PATCH 3323/4345] tcp: Return user_mss for TCP_MAXSEG in CLOSE/LISTEN state if user_mss set [ Upstream commit 34dfde4ad87b84d21278a7e19d92b5b2c68e6c4d ] This patch replaces the tp->mss_cache check in getting TCP_MAXSEG with tp->rx_opt.user_mss check for CLOSE/LISTEN sock. Since tp->mss_cache is initialized with TCP_MSS_DEFAULT, checking if it's zero is probably a bug. With this change, getting TCP_MAXSEG before connecting will return default MSS normally, and return user_mss if user_mss is set. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Jack Yang Suggested-by: Eric Dumazet Link: https://lore.kernel.org/netdev/CANn89i+3kL9pYtkxkwxwNMzvC_w3LNUum_2=3u+UyLBmGmifHA@mail.gmail.com/#t Signed-off-by: Cambda Zhu Link: https://lore.kernel.org/netdev/14D45862-36EA-4076-974C-EA67513C92F6@linux.alibaba.com/ Reviewed-by: Jason Xing Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230527040317.68247-1-cambda@linux.alibaba.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index edb743bcbc39..82abbf192985 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3719,7 +3719,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; - if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) + if (tp->rx_opt.user_mss && + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; From 1b0163b2dc3b5b1f20ceecf04f11e2ba6b3066ca Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Mon, 29 May 2023 12:52:55 -0700 Subject: [PATCH 3324/4345] net/sched: sch_ingress: Only create under TC_H_INGRESS [ Upstream commit c7cfbd115001f94de9e4053657946a383147e803 ] ingress Qdiscs are only supposed to be created under TC_H_INGRESS. Return -EOPNOTSUPP if 'parent' is not TC_H_INGRESS, similar to mq_init(). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+b53a9c0d1ea4ad62da8b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/r/0000000000006cf87705f79acf1a@google.com/ Tested-by: Pedro Tammela Acked-by: Jamal Hadi Salim Reviewed-by: Jamal Hadi Salim Reviewed-by: Vlad Buslov Signed-off-by: Peilin Ye Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_ingress.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 84838128b9c5..f9ef6deb2770 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -80,6 +80,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_INGRESS) + return -EOPNOTSUPP; + net_inc_ingress_queue(); mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); @@ -101,6 +104,9 @@ static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_INGRESS) + return; + tcf_block_put_ext(q->block, sch, &q->block_info); net_dec_ingress_queue(); } From 18c76349afdae3318450dd1c5b4add9c5c66390c Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Mon, 29 May 2023 12:53:21 -0700 Subject: [PATCH 3325/4345] net/sched: sch_clsact: Only create under TC_H_CLSACT [ Upstream commit 5eeebfe6c493192b10d516abfd72742900f2a162 ] clsact Qdiscs are only supposed to be created under TC_H_CLSACT (which equals TC_H_INGRESS). Return -EOPNOTSUPP if 'parent' is not TC_H_CLSACT. Fixes: 1f211a1b929c ("net, sched: add clsact qdisc") Tested-by: Pedro Tammela Acked-by: Jamal Hadi Salim Reviewed-by: Jamal Hadi Salim Reviewed-by: Vlad Buslov Signed-off-by: Peilin Ye Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_ingress.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index f9ef6deb2770..35963929e117 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -225,6 +225,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_CLSACT) + return -EOPNOTSUPP; + net_inc_ingress_queue(); net_inc_egress_queue(); @@ -254,6 +257,9 @@ static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_CLSACT) + return; + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); From 676f203803f99a0755d99c2a5ba5bb56e172afbe Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Mon, 29 May 2023 12:54:03 -0700 Subject: [PATCH 3326/4345] net/sched: Reserve TC_H_INGRESS (TC_H_CLSACT) for ingress (clsact) Qdiscs [ Upstream commit f85fa45d4a9408d98c46c8fa45ba2e3b2f4bf219 ] Currently it is possible to add e.g. an HTB Qdisc under ffff:fff1 (TC_H_INGRESS, TC_H_CLSACT): $ ip link add name ifb0 type ifb $ tc qdisc add dev ifb0 parent ffff:fff1 htb $ tc qdisc add dev ifb0 clsact Error: Exclusivity flag on, cannot modify. $ drgn ... >>> ifb0 = netdev_get_by_name(prog, "ifb0") >>> qdisc = ifb0.ingress_queue.qdisc_sleeping >>> print(qdisc.ops.id.string_().decode()) htb >>> qdisc.flags.value_() # TCQ_F_INGRESS 2 Only allow ingress and clsact Qdiscs under ffff:fff1. Return -EINVAL for everything else. Make TCQ_F_INGRESS a static flag of ingress and clsact Qdiscs. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Fixes: 1f211a1b929c ("net, sched: add clsact qdisc") Tested-by: Pedro Tammela Acked-by: Jamal Hadi Salim Reviewed-by: Jamal Hadi Salim Reviewed-by: Vlad Buslov Signed-off-by: Peilin Ye Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_api.c | 7 ++++++- net/sched/sch_ingress.c | 4 ++-- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 54e2309315eb..b665f4ff49a6 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1223,7 +1223,12 @@ static struct Qdisc *qdisc_create(struct net_device *dev, sch->parent = parent; if (handle == TC_H_INGRESS) { - sch->flags |= TCQ_F_INGRESS; + if (!(sch->flags & TCQ_F_INGRESS)) { + NL_SET_ERR_MSG(extack, + "Specified parent ID is reserved for ingress and clsact Qdiscs"); + err = -EINVAL; + goto err_out3; + } handle = TC_H_MAKE(TC_H_INGRESS, 0); } else { if (handle == 0) { diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 35963929e117..e43a45499372 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -140,7 +140,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", .priv_size = sizeof(struct ingress_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -281,7 +281,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", .priv_size = sizeof(struct clsact_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, From a8ad1303b9deeb24edec57b417b9613f8d92711e Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Mon, 29 May 2023 12:54:26 -0700 Subject: [PATCH 3327/4345] net/sched: Prohibit regrafting ingress or clsact Qdiscs [ Upstream commit 9de95df5d15baa956c2b70b9e794842e790a8a13 ] Currently, after creating an ingress (or clsact) Qdisc and grafting it under TC_H_INGRESS (TC_H_CLSACT), it is possible to graft it again under e.g. a TBF Qdisc: $ ip link add ifb0 type ifb $ tc qdisc add dev ifb0 handle 1: root tbf rate 20kbit buffer 1600 limit 3000 $ tc qdisc add dev ifb0 clsact $ tc qdisc link dev ifb0 handle ffff: parent 1:1 $ tc qdisc show dev ifb0 qdisc tbf 1: root refcnt 2 rate 20Kbit burst 1600b lat 560.0ms qdisc clsact ffff: parent ffff:fff1 refcnt 2 ^^^^^^^^ clsact's refcount has increased: it is now grafted under both TC_H_CLSACT and 1:1. ingress and clsact Qdiscs should only be used under TC_H_INGRESS (TC_H_CLSACT). Prohibit regrafting them. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Fixes: 1f211a1b929c ("net, sched: add clsact qdisc") Tested-by: Pedro Tammela Acked-by: Jamal Hadi Salim Reviewed-by: Jamal Hadi Salim Reviewed-by: Vlad Buslov Signed-off-by: Peilin Ye Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_api.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b665f4ff49a6..b330f1192cf8 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1589,6 +1589,11 @@ replay: NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } + if (q->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot regraft ingress or clsact Qdiscs"); + return -EINVAL; + } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); From ae7e941f4dc354ec2aa4642f38c4280493f21302 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Sat, 27 May 2023 17:37:47 +0800 Subject: [PATCH 3328/4345] net: sched: fix NULL pointer dereference in mq_attach [ Upstream commit 36eec020fab668719b541f34d97f44e232ffa165 ] When use the following command to test: 1)ip link add bond0 type bond 2)ip link set bond0 up 3)tc qdisc add dev bond0 root handle ffff: mq 4)tc qdisc replace dev bond0 parent ffff:fff1 handle ffff: mq The kernel reports NULL pointer dereference issue. The stack information is as follows: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 Internal error: Oops: 0000000096000006 [#1] SMP Modules linked in: pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : mq_attach+0x44/0xa0 lr : qdisc_graft+0x20c/0x5cc sp : ffff80000e2236a0 x29: ffff80000e2236a0 x28: ffff0000c0e59d80 x27: ffff0000c0be19c0 x26: ffff0000cae3e800 x25: 0000000000000010 x24: 00000000fffffff1 x23: 0000000000000000 x22: ffff0000cae3e800 x21: ffff0000c9df4000 x20: ffff0000c9df4000 x19: 0000000000000000 x18: ffff80000a934000 x17: ffff8000f5b56000 x16: ffff80000bb08000 x15: 0000000000000000 x14: 0000000000000000 x13: 6b6b6b6b6b6b6b6b x12: 6b6b6b6b00000001 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 x8 : ffff0000c0be0730 x7 : bbbbbbbbbbbbbbbb x6 : 0000000000000008 x5 : ffff0000cae3e864 x4 : 0000000000000000 x3 : 0000000000000001 x2 : 0000000000000001 x1 : ffff8000090bc23c x0 : 0000000000000000 Call trace: mq_attach+0x44/0xa0 qdisc_graft+0x20c/0x5cc tc_modify_qdisc+0x1c4/0x664 rtnetlink_rcv_msg+0x354/0x440 netlink_rcv_skb+0x64/0x144 rtnetlink_rcv+0x28/0x34 netlink_unicast+0x1e8/0x2a4 netlink_sendmsg+0x308/0x4a0 sock_sendmsg+0x64/0xac ____sys_sendmsg+0x29c/0x358 ___sys_sendmsg+0x90/0xd0 __sys_sendmsg+0x7c/0xd0 __arm64_sys_sendmsg+0x2c/0x38 invoke_syscall+0x54/0x114 el0_svc_common.constprop.1+0x90/0x174 do_el0_svc+0x3c/0xb0 el0_svc+0x24/0xec el0t_64_sync_handler+0x90/0xb4 el0t_64_sync+0x174/0x178 This is because when mq is added for the first time, qdiscs in mq is set to NULL in mq_attach(). Therefore, when replacing mq after adding mq, we need to initialize qdiscs in the mq before continuing to graft. Otherwise, it will couse NULL pointer dereference issue in mq_attach(). And the same issue will occur in the attach functions of mqprio, taprio and htb. ffff:fff1 means that the repalce qdisc is ingress. Ingress does not allow any qdisc to be attached. Therefore, ffff:fff1 is incorrectly used, and the command should be dropped. Fixes: 6ec1c69a8f64 ("net_sched: add classful multiqueue dummy scheduler") Signed-off-by: Zhengchao Shao Tested-by: Peilin Ye Acked-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20230527093747.3583502-1-shaozhengchao@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/sch_api.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b330f1192cf8..2084724c36ad 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1599,6 +1599,10 @@ replay: NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; } + if (clid == TC_H_INGRESS) { + NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); + return -EINVAL; + } qdisc_refcount_inc(q); goto graft; } else { From 57e6c54034274ebdcf617bf3eb67fc4a617c09f2 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Mon, 29 May 2023 12:33:35 -0300 Subject: [PATCH 3329/4345] net/netlink: fix NETLINK_LIST_MEMBERSHIPS length report [ Upstream commit f4e4534850a9d18c250a93f8d7fbb51310828110 ] The current code for the length calculation wrongly truncates the reported length of the groups array, causing an under report of the subscribed groups. To fix this, use 'BITS_TO_BYTES()' which rounds up the division by 8. Fixes: b42be38b2778 ("netlink: add API to retrieve all group memberships") Signed-off-by: Pedro Tammela Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230529153335.389815-1-pctammela@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 651f8ca912af..99c869d8d304 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1781,7 +1781,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, break; } } - if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) + if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); return err; From f03bc013604cd367097d19bada4e53848bb42207 Mon Sep 17 00:00:00 2001 From: Vladislav Efanov Date: Tue, 30 May 2023 14:39:41 +0300 Subject: [PATCH 3330/4345] udp6: Fix race condition in udp6_sendmsg & connect [ Upstream commit 448a5ce1120c5bdbce1f1ccdabcd31c7d029f328 ] Syzkaller got the following report: BUG: KASAN: use-after-free in sk_setup_caps+0x621/0x690 net/core/sock.c:2018 Read of size 8 at addr ffff888027f82780 by task syz-executor276/3255 The function sk_setup_caps (called by ip6_sk_dst_store_flow-> ip6_dst_store) referenced already freed memory as this memory was freed by parallel task in udpv6_sendmsg->ip6_sk_dst_lookup_flow-> sk_dst_check. task1 (connect) task2 (udp6_sendmsg) sk_setup_caps->sk_dst_set | | sk_dst_check-> | sk_dst_set | dst_release sk_setup_caps references | to already freed dst_entry| The reason for this race condition is: sk_setup_caps() keeps using the dst after transferring the ownership to the dst cache. Found by Linux Verification Center (linuxtesting.org) with syzkaller. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Vladislav Efanov Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/sock.c b/net/core/sock.c index c5ae520d4a69..9b013d052a72 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2016,7 +2016,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; - sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; @@ -2031,6 +2030,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } } sk->sk_gso_max_segs = max_segs; + sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); From f5c29a9e9146cfe844b881833cd7452244a8384d Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 28 Apr 2023 13:48:13 +0300 Subject: [PATCH 3331/4345] net/mlx5: Read embedded cpu after init bit cleared [ Upstream commit bbfa4b58997e3d38ba629c9f6fc0bd1c163aaf43 ] During driver load it reads embedded_cpu bit from initialization segment, but the initialization segment is readable only after initialization bit is cleared. Move the call to mlx5_read_embedded_cpu() right after initialization bit cleared. Signed-off-by: Moshe Shemesh Fixes: 591905ba9679 ("net/mlx5: Introduce Mellanox SmartNIC and modify page management logic") Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index da4ca0f67e9c..22907f6364f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -783,7 +783,6 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, } mlx5_pci_vsc_init(dev); - dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); return 0; err_clr_master: @@ -978,6 +977,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) goto err_cmd_cleanup; } + dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP); err = mlx5_core_enable_hca(dev, 0); From 7c5c67aa294444b53f697dc3ddce61b33ff8badd Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Wed, 31 May 2023 18:28:04 +0800 Subject: [PATCH 3332/4345] net/sched: flower: fix possible OOB write in fl_set_geneve_opt() [ Upstream commit 4d56304e5827c8cc8cc18c75343d283af7c4825c ] If we send two TCA_FLOWER_KEY_ENC_OPTS_GENEVE packets and their total size is 252 bytes(key->enc_opts.len = 252) then key->enc_opts.len = opt->length = data_len / 4 = 0 when the third TCA_FLOWER_KEY_ENC_OPTS_GENEVE packet enters fl_set_geneve_opt. This bypasses the next bounds check and results in an out-of-bounds. Fixes: 0a6e77784f49 ("net/sched: allow flower to match tunnel options") Signed-off-by: Hangyu Hua Reviewed-by: Simon Horman Reviewed-by: Pieter Jansen van Vuuren Link: https://lore.kernel.org/r/20230531102805.27090-1-hbh25y@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/cls_flower.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 35ee6d8226e6..caf1a05bfbde 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1086,6 +1086,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, if (option_len > sizeof(struct geneve_opt)) data_len = option_len - sizeof(struct geneve_opt); + if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4) + return -ERANGE; + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; memset(opt, 0xff, option_len); opt->length = data_len / 4; From a437d3d25a2753af23cd7f3af5977cbeb7f11bdd Mon Sep 17 00:00:00 2001 From: Andreas Svensson Date: Tue, 30 May 2023 16:52:23 +0200 Subject: [PATCH 3333/4345] net: dsa: mv88e6xxx: Increase wait after reset deactivation [ Upstream commit 3c27f3d53d588618d81d30d6712459a3cc9489b8 ] A switch held in reset by default needs to wait longer until we can reliably detect it. An issue was observed when testing on the Marvell 88E6393X (Link Street). The driver failed to detect the switch on some upstarts. Increasing the wait time after reset deactivation solves this issue. The updated wait time is now also the same as the wait time in the mv88e6xxx_hardware_reset function. Fixes: 7b75e49de424 ("net: dsa: mv88e6xxx: wait after reset deactivation") Signed-off-by: Andreas Svensson Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230530145223.1223993-1-andreas.svensson@axis.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 321c821876f6..8b2c8546f4c9 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -5547,7 +5547,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) goto out; } if (chip->reset) - usleep_range(1000, 2000); + usleep_range(10000, 20000); err = mv88e6xxx_detect(chip); if (err) From e4666d793a2203ecefbe3860842aaf7b740a6a55 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Thu, 25 May 2023 12:31:52 +1200 Subject: [PATCH 3334/4345] mtd: rawnand: marvell: ensure timing values are written [ Upstream commit 8a6f4d346f3bad9c68b4a87701eb3f7978542d57 ] When new timing values are calculated in marvell_nfc_setup_interface() ensure that they will be applied in marvell_nfc_select_target() by clearing the selected_chip pointer. Fixes: b25251414f6e ("mtd: rawnand: marvell: Stop implementing ->select_chip()") Suggested-by: Miquel Raynal Signed-off-by: Chris Packham Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230525003154.2303012-1-chris.packham@alliedtelesis.co.nz Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/marvell_nand.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index dce35f81e0a5..9d437f1566ed 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -2443,6 +2443,12 @@ static int marvell_nfc_setup_interface(struct nand_chip *chip, int chipnr, NDTR1_WAIT_MODE; } + /* + * Reset nfc->selected_chip so the next command will cause the timing + * registers to be updated in marvell_nfc_select_target(). + */ + nfc->selected_chip = NULL; + return 0; } From 9823ac6e7ae19f08e6d2c73bbc3b2d956e823823 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Thu, 25 May 2023 12:31:53 +1200 Subject: [PATCH 3335/4345] mtd: rawnand: marvell: don't set the NAND frequency select [ Upstream commit c4d28e30a8d0b979e4029465ab8f312ab6ce2644 ] marvell_nfc_setup_interface() uses the frequency retrieved from the clock associated with the nand interface to determine the timings that will be used. By changing the NAND frequency select without reflecting this in the clock configuration this means that the timings calculated don't correctly meet the requirements of the NAND chip. This hasn't been an issue up to now because of a different bug that was stopping the timings being updated after they were initially set. Fixes: b25251414f6e ("mtd: rawnand: marvell: Stop implementing ->select_chip()") Signed-off-by: Chris Packham Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230525003154.2303012-2-chris.packham@alliedtelesis.co.nz Signed-off-by: Sasha Levin --- drivers/mtd/nand/raw/marvell_nand.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 9d437f1566ed..2ef1a5adfcfc 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -2891,10 +2891,6 @@ static int marvell_nfc_init(struct marvell_nfc *nfc) regmap_update_bits(sysctrl_base, GENCONF_CLK_GATING_CTRL, GENCONF_CLK_GATING_CTRL_ND_GATE, GENCONF_CLK_GATING_CTRL_ND_GATE); - - regmap_update_bits(sysctrl_base, GENCONF_ND_CLK_CTRL, - GENCONF_ND_CLK_CTRL_EN, - GENCONF_ND_CLK_CTRL_EN); } /* Configure the DMA if appropriate */ From d5fcccfc50100caf62d0ef29032ff892d986d5c0 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 18 Apr 2023 19:25:30 +0200 Subject: [PATCH 3336/4345] watchdog: menz069_wdt: fix watchdog initialisation [ Upstream commit 87b22656ca6a896d0378e9e60ffccb0c82f48b08 ] Doing a 'cat /dev/watchdog0' with menz069_wdt as watchdog0 will result in a NULL pointer dereference. This happens because we're passing the wrong pointer to watchdog_register_device(). Fix this by getting rid of the static watchdog_device structure and use the one embedded into the driver's per-instance private data. Signed-off-by: Johannes Thumshirn Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230418172531.177349-2-jth@kernel.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck Signed-off-by: Sasha Levin --- drivers/watchdog/menz69_wdt.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/drivers/watchdog/menz69_wdt.c b/drivers/watchdog/menz69_wdt.c index 8973f98bc6a5..bca0938f3429 100644 --- a/drivers/watchdog/menz69_wdt.c +++ b/drivers/watchdog/menz69_wdt.c @@ -98,14 +98,6 @@ static const struct watchdog_ops men_z069_ops = { .set_timeout = men_z069_wdt_set_timeout, }; -static struct watchdog_device men_z069_wdt = { - .info = &men_z069_info, - .ops = &men_z069_ops, - .timeout = MEN_Z069_DEFAULT_TIMEOUT, - .min_timeout = 1, - .max_timeout = MEN_Z069_WDT_COUNTER_MAX / MEN_Z069_TIMER_FREQ, -}; - static int men_z069_probe(struct mcb_device *dev, const struct mcb_device_id *id) { @@ -125,15 +117,19 @@ static int men_z069_probe(struct mcb_device *dev, goto release_mem; drv->mem = mem; + drv->wdt.info = &men_z069_info; + drv->wdt.ops = &men_z069_ops; + drv->wdt.timeout = MEN_Z069_DEFAULT_TIMEOUT; + drv->wdt.min_timeout = 1; + drv->wdt.max_timeout = MEN_Z069_WDT_COUNTER_MAX / MEN_Z069_TIMER_FREQ; - drv->wdt = men_z069_wdt; watchdog_init_timeout(&drv->wdt, 0, &dev->dev); watchdog_set_nowayout(&drv->wdt, nowayout); watchdog_set_drvdata(&drv->wdt, drv); drv->wdt.parent = &dev->dev; mcb_set_drvdata(dev, drv); - return watchdog_register_device(&men_z069_wdt); + return watchdog_register_device(&drv->wdt); release_mem: mcb_release_mem(mem); From 0dcf021af4cb3b453d587ee0c6290ab5aaa165d6 Mon Sep 17 00:00:00 2001 From: jasontao Date: Wed, 26 Apr 2023 09:30:59 +0800 Subject: [PATCH 3337/4345] ALSA: hda: Glenfly: add HD Audio PCI IDs and HDMI Codec Vendor IDs. [ Upstream commit c51e431052e2eacfb23fbf6b39bc6c8770d9827a ] Add a set of HD Audio PCI IDS, and the HDMI codec vendor IDs for Glenfly Gpus. - In default_bdl_pos_adj, set bdl to 128 as Glenfly Gpus have hardware limitation, need to increase hdac interrupt interval. - In azx_first_init, enable polling mode for Glenfly Gpu. When the codec complete the command, it sends interrupt and writes response entries to memory, howerver, the write requests sometimes are not actually synchronized to memory when driver handle hdac interrupt on Glenfly Gpus. If the RIRB status is not updated in the interrupt handler, azx_rirb_get_response keeps trying to recevie a response from rirb until 1s timeout. Enabling polling mode for Glenfly Gpu can fix the issue. - In patch_gf_hdmi, set Glenlfy Gpu Codec's no_sticky_stream as it need driver to do actual clean-ups for the linked codec when switch from one codec to another. Signed-off-by: jasontao Signed-off-by: Reaper Li Link: https://lore.kernel.org/r/20230426013059.4329-1-reaperlioc@glenfly.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/hda_intel.c | 21 +++++++++++++++++++++ sound/pci/hda/patch_hdmi.c | 22 ++++++++++++++++++++++ 2 files changed, 43 insertions(+) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index de1fe604905f..1f641712233e 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -264,6 +264,7 @@ enum { AZX_DRIVER_ATI, AZX_DRIVER_ATIHDMI, AZX_DRIVER_ATIHDMI_NS, + AZX_DRIVER_GFHDMI, AZX_DRIVER_VIA, AZX_DRIVER_SIS, AZX_DRIVER_ULI, @@ -386,6 +387,7 @@ static const char * const driver_short_names[] = { [AZX_DRIVER_ATI] = "HDA ATI SB", [AZX_DRIVER_ATIHDMI] = "HDA ATI HDMI", [AZX_DRIVER_ATIHDMI_NS] = "HDA ATI HDMI", + [AZX_DRIVER_GFHDMI] = "HDA GF HDMI", [AZX_DRIVER_VIA] = "HDA VIA VT82xx", [AZX_DRIVER_SIS] = "HDA SIS966", [AZX_DRIVER_ULI] = "HDA ULI M5461", @@ -1783,6 +1785,12 @@ static int default_bdl_pos_adj(struct azx *chip) } switch (chip->driver_type) { + /* + * increase the bdl size for Glenfly Gpus for hardware + * limitation on hdac interrupt interval + */ + case AZX_DRIVER_GFHDMI: + return 128; case AZX_DRIVER_ICH: case AZX_DRIVER_PCH: return 1; @@ -1902,6 +1910,12 @@ static int azx_first_init(struct azx *chip) pci_write_config_dword(pci, PCI_BASE_ADDRESS_1, 0); } #endif + /* + * Fix response write request not synced to memory when handle + * hdac interrupt on Glenfly Gpus + */ + if (chip->driver_type == AZX_DRIVER_GFHDMI) + bus->polling_mode = 1; err = pci_request_regions(pci, "ICH HD audio"); if (err < 0) @@ -2011,6 +2025,7 @@ static int azx_first_init(struct azx *chip) chip->playback_streams = ATIHDMI_NUM_PLAYBACK; chip->capture_streams = ATIHDMI_NUM_CAPTURE; break; + case AZX_DRIVER_GFHDMI: case AZX_DRIVER_GENERIC: default: chip->playback_streams = ICH6_NUM_PLAYBACK; @@ -2756,6 +2771,12 @@ static const struct pci_device_id azx_ids[] = { { PCI_DEVICE(0x1002, 0xab38), .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS | AZX_DCAPS_PM_RUNTIME }, + /* GLENFLY */ + { PCI_DEVICE(0x6766, PCI_ANY_ID), + .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8, + .class_mask = 0xffffff, + .driver_data = AZX_DRIVER_GFHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_NO_64BIT }, /* VIA VT8251/VT8237A */ { PCI_DEVICE(0x1106, 0x3288), .driver_data = AZX_DRIVER_VIA }, /* VIA GFX VT7122/VX900 */ diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index e4366fea9e27..c19afe486194 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4287,6 +4287,22 @@ static int patch_via_hdmi(struct hda_codec *codec) return patch_simple_hdmi(codec, VIAHDMI_CVT_NID, VIAHDMI_PIN_NID); } +static int patch_gf_hdmi(struct hda_codec *codec) +{ + int err; + + err = patch_generic_hdmi(codec); + if (err) + return err; + + /* + * Glenfly GPUs have two codecs, stream switches from one codec to + * another, need to do actual clean-ups in codec_cleanup_stream + */ + codec->no_sticky_stream = 1; + return 0; +} + /* * patch entries */ @@ -4381,6 +4397,12 @@ HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), +HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d83, "Arise 83 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d84, "Arise 84 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d85, "Arise 85 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d86, "Arise 86 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d87, "Arise 87 HDMI/DP", patch_gf_hdmi), HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f81, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f84, "VX11 HDMI/DP", patch_generic_hdmi), From c12c288f1e67b69f516e8ca93a610796f0c7e476 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 20 Apr 2023 08:27:18 +0100 Subject: [PATCH 3338/4345] mailbox: mailbox-test: Fix potential double-free in mbox_test_message_write() [ Upstream commit 2d1e952a2b8e5e92d8d55ac88a7cf7ca5ea591ad ] If a user can make copy_from_user() fail, there is a potential for UAF/DF due to a lack of locking around the allocation, use and freeing of the data buffers. This issue is not theoretical. I managed to author a POC for it: BUG: KASAN: double-free in kfree+0x5c/0xac Free of addr ffff29280be5de00 by task poc/356 CPU: 1 PID: 356 Comm: poc Not tainted 6.1.0-00001-g961aa6552c04-dirty #20 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace.part.0+0xe0/0xf0 show_stack+0x18/0x40 dump_stack_lvl+0x64/0x80 print_report+0x188/0x48c kasan_report_invalid_free+0xa0/0xc0 ____kasan_slab_free+0x174/0x1b0 __kasan_slab_free+0x18/0x24 __kmem_cache_free+0x130/0x2e0 kfree+0x5c/0xac mbox_test_message_write+0x208/0x29c full_proxy_write+0x90/0xf0 vfs_write+0x154/0x440 ksys_write+0xcc/0x180 __arm64_sys_write+0x44/0x60 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x40/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xf4/0x120 el0t_64_sync+0x18c/0x190 Allocated by task 356: kasan_save_stack+0x3c/0x70 kasan_set_track+0x2c/0x40 kasan_save_alloc_info+0x24/0x34 __kasan_kmalloc+0xb8/0xc0 kmalloc_trace+0x58/0x70 mbox_test_message_write+0x6c/0x29c full_proxy_write+0x90/0xf0 vfs_write+0x154/0x440 ksys_write+0xcc/0x180 __arm64_sys_write+0x44/0x60 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x40/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xf4/0x120 el0t_64_sync+0x18c/0x190 Freed by task 357: kasan_save_stack+0x3c/0x70 kasan_set_track+0x2c/0x40 kasan_save_free_info+0x38/0x5c ____kasan_slab_free+0x13c/0x1b0 __kasan_slab_free+0x18/0x24 __kmem_cache_free+0x130/0x2e0 kfree+0x5c/0xac mbox_test_message_write+0x208/0x29c full_proxy_write+0x90/0xf0 vfs_write+0x154/0x440 ksys_write+0xcc/0x180 __arm64_sys_write+0x44/0x60 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x40/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xf4/0x120 el0t_64_sync+0x18c/0x190 Signed-off-by: Lee Jones Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/mailbox-test.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 4555d678fadd..6dd5b9614452 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -38,6 +39,7 @@ struct mbox_test_device { char *signal; char *message; spinlock_t lock; + struct mutex mutex; wait_queue_head_t waitq; struct fasync_struct *async_queue; struct dentry *root_debugfs_dir; @@ -110,6 +112,8 @@ static ssize_t mbox_test_message_write(struct file *filp, return -EINVAL; } + mutex_lock(&tdev->mutex); + tdev->message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); if (!tdev->message) return -ENOMEM; @@ -144,6 +148,8 @@ out: kfree(tdev->message); tdev->signal = NULL; + mutex_unlock(&tdev->mutex); + return ret < 0 ? ret : count; } @@ -392,6 +398,7 @@ static int mbox_test_probe(struct platform_device *pdev) platform_set_drvdata(pdev, tdev); spin_lock_init(&tdev->lock); + mutex_init(&tdev->mutex); if (tdev->rx_channel) { tdev->rx_buffer = devm_kzalloc(&pdev->dev, From a3393eb6fb415300ba860eea8cfcc609368a80ae Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 26 Apr 2023 11:51:35 +0100 Subject: [PATCH 3339/4345] btrfs: abort transaction when sibling keys check fails for leaves [ Upstream commit 9ae5afd02a03d4e22a17a9609b19400b77c36273 ] If the sibling keys check fails before we move keys from one sibling leaf to another, we are not aborting the transaction - we leave that to some higher level caller of btrfs_search_slot() (or anything else that uses it to insert items into a b+tree). This means that the transaction abort will provide a stack trace that omits the b+tree modification call chain. So change this to immediately abort the transaction and therefore get a more useful stack trace that shows us the call chain in the bt+tree modification code. It's also important to immediately abort the transaction just in case some higher level caller is not doing it, as this indicates a very serious corruption and we should stop the possibility of doing further damage. Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/ctree.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 3e55245e54e7..41a7ace9998e 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -3872,6 +3872,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root if (check_sibling_keys(left, right)) { ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); btrfs_tree_unlock(right); free_extent_buffer(right); return ret; @@ -4116,6 +4117,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root if (check_sibling_keys(left, right)) { ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); goto out; } return __push_leaf_left(path, min_data_size, From 16ee4562c7bb9ef0cf814eac12dea55170aca0b5 Mon Sep 17 00:00:00 2001 From: Haibo Li Date: Mon, 17 Apr 2023 10:17:07 +0100 Subject: [PATCH 3340/4345] ARM: 9295/1: unwind:fix unwind abort for uleb128 case [ Upstream commit fa3eeb638de0c1a9d2d860e5b48259facdd65176 ] When unwind instruction is 0xb2,the subsequent instructions are uleb128 bytes. For now,it uses only the first uleb128 byte in code. For vsp increments of 0x204~0x400,use one uleb128 byte like below: 0xc06a00e4 : 0x80b27fac Compact model index: 0 0xb2 0x7f vsp = vsp + 1024 0xac pop {r4, r5, r6, r7, r8, r14} For vsp increments larger than 0x400,use two uleb128 bytes like below: 0xc06a00e4 : @0xc0cc9e0c Compact model index: 1 0xb2 0x81 0x01 vsp = vsp + 1032 0xac pop {r4, r5, r6, r7, r8, r14} The unwind works well since the decoded uleb128 byte is also 0x81. For vsp increments larger than 0x600,use two uleb128 bytes like below: 0xc06a00e4 : @0xc0cc9e0c Compact model index: 1 0xb2 0x81 0x02 vsp = vsp + 1544 0xac pop {r4, r5, r6, r7, r8, r14} In this case,the decoded uleb128 result is 0x101(vsp=0x204+(0x101<<2)). While the uleb128 used in code is 0x81(vsp=0x204+(0x81<<2)). The unwind aborts at this frame since it gets incorrect vsp. To fix this,add uleb128 decode to cover all the above case. Signed-off-by: Haibo Li Reviewed-by: Linus Walleij Reviewed-by: Alexandre Mergnat Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Russell King (Oracle) Signed-off-by: Sasha Levin --- arch/arm/kernel/unwind.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c index d2bd0df2318d..7e90f17a0676 100644 --- a/arch/arm/kernel/unwind.c +++ b/arch/arm/kernel/unwind.c @@ -300,6 +300,29 @@ static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl, return URC_OK; } +static unsigned long unwind_decode_uleb128(struct unwind_ctrl_block *ctrl) +{ + unsigned long bytes = 0; + unsigned long insn; + unsigned long result = 0; + + /* + * unwind_get_byte() will advance `ctrl` one instruction at a time, so + * loop until we get an instruction byte where bit 7 is not set. + * + * Note: This decodes a maximum of 4 bytes to output 28 bits data where + * max is 0xfffffff: that will cover a vsp increment of 1073742336, hence + * it is sufficient for unwinding the stack. + */ + do { + insn = unwind_get_byte(ctrl); + result |= (insn & 0x7f) << (bytes * 7); + bytes++; + } while (!!(insn & 0x80) && (bytes != sizeof(result))); + + return result; +} + /* * Execute the current unwind instruction. */ @@ -353,7 +376,7 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl) if (ret) goto error; } else if (insn == 0xb2) { - unsigned long uleb128 = unwind_get_byte(ctrl); + unsigned long uleb128 = unwind_decode_uleb128(ctrl); ctrl->vrs[SP] += 0x204 + (uleb128 << 2); } else { From fe4f6e159b9ab54a30d18d81b08b6b2fd68a06bf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Sat, 11 Feb 2023 21:55:34 +0100 Subject: [PATCH 3341/4345] media: rcar-vin: Select correct interrupt mode for V4L2_FIELD_ALTERNATE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e10707d5865c90d3dfe4ef589ce02ff4287fef85 ] When adding proper support for V4L2_FIELD_ALTERNATE it was missed that this field format should trigger an interrupt for each field, not just for the whole frame. Fix this by marking it as progressive in the capture setup, which will then select the correct interrupt mode. Tested on both Gen2 and Gen3 with the result of a doubling of the frame rate for V4L2_FIELD_ALTERNATE. From a PAL video source the frame rate is now 50, which is expected for alternate field capture. Signed-off-by: Niklas Söderlund Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/platform/rcar-vin/rcar-dma.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c index 692dea300b0d..63c61c704446 100644 --- a/drivers/media/platform/rcar-vin/rcar-dma.c +++ b/drivers/media/platform/rcar-vin/rcar-dma.c @@ -645,11 +645,9 @@ static int rvin_setup(struct rvin_dev *vin) case V4L2_FIELD_SEQ_TB: case V4L2_FIELD_SEQ_BT: case V4L2_FIELD_NONE: - vnmc = VNMC_IM_ODD_EVEN; - progressive = true; - break; case V4L2_FIELD_ALTERNATE: vnmc = VNMC_IM_ODD_EVEN; + progressive = true; break; default: vnmc = VNMC_IM_ODD; From d03d31d3a206093b9b8759dddf0ba9bd843606ba Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Fri, 28 Apr 2023 12:07:46 -0400 Subject: [PATCH 3342/4345] gfs2: Don't deref jdesc in evict [ Upstream commit 504a10d9e46bc37b23d0a1ae2f28973c8516e636 ] On corrupt gfs2 file systems the evict code can try to reference the journal descriptor structure, jdesc, after it has been freed and set to NULL. The sequence of events is: init_journal() ... fail_jindex: gfs2_jindex_free(sdp); <------frees journals, sets jdesc = NULL if (gfs2_holder_initialized(&ji_gh)) gfs2_glock_dq_uninit(&ji_gh); fail: iput(sdp->sd_jindex); <--references jdesc in evict_linked_inode evict() gfs2_evict_inode() evict_linked_inode() ret = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); <------references the now freed/zeroed sd_jdesc pointer. The call to gfs2_trans_begin is done because the truncate_inode_pages call can cause gfs2 events that require a transaction, such as removing journaled data (jdata) blocks from the journal. This patch fixes the problem by adding a check for sdp->sd_jdesc to function gfs2_evict_inode. In theory, this should only happen to corrupt gfs2 file systems, when gfs2 detects the problem, reports it, then tries to evict all the system inodes it has read in up to that point. Reported-by: Yang Lan Signed-off-by: Bob Peterson Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin --- fs/gfs2/super.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 5cb7e771b57a..e01b6a2d12d3 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1416,6 +1416,14 @@ static void gfs2_evict_inode(struct inode *inode) if (inode->i_nlink || sb_rdonly(sb)) goto out; + /* + * In case of an incomplete mount, gfs2_evict_inode() may be called for + * system files without having an active journal to write to. In that + * case, skip the filesystem evict. + */ + if (!sdp->sd_jdesc) + goto out; + gfs2_holder_mark_uninitialized(&gh); ret = evict_should_delete(inode, &gh); if (ret == SHOULD_DEFER_EVICTION) From 742dab42d70e29b89bb09f23b748da6f4f529ab8 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 22 Apr 2023 23:24:26 +0200 Subject: [PATCH 3343/4345] fbdev: modedb: Add 1920x1080 at 60 Hz video mode [ Upstream commit c8902258b2b8ecaa1b8d88c312853c5b14c2553d ] Add typical resolution for Full-HD monitors. Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/core/modedb.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c index 6473e0dfe146..e78ec7f72846 100644 --- a/drivers/video/fbdev/core/modedb.c +++ b/drivers/video/fbdev/core/modedb.c @@ -257,6 +257,11 @@ static const struct fb_videomode modedb[] = { { NULL, 72, 480, 300, 33386, 40, 24, 11, 19, 80, 3, 0, FB_VMODE_DOUBLE }, + /* 1920x1080 @ 60 Hz, 67.3 kHz hsync */ + { NULL, 60, 1920, 1080, 6734, 148, 88, 36, 4, 44, 5, 0, + FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, + FB_VMODE_NONINTERLACED }, + /* 1920x1200 @ 60 Hz, 74.5 Khz hsync */ { NULL, 60, 1920, 1200, 5177, 128, 336, 1, 38, 208, 3, FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, From 29f6b42a73b3bfe6f877cf99168b64da03fab7e8 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 12 May 2023 11:50:33 +0200 Subject: [PATCH 3344/4345] fbdev: stifb: Fix info entry in sti_struct on error path [ Upstream commit 0bdf1ad8d10bd4e50a8b1a2c53d15984165f7fea ] Minor fix to reset the info field to NULL in case of error. Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/stifb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index ef8a4c5fc687..63f51783352d 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1413,6 +1413,7 @@ out_err1: iounmap(info->screen_base); out_err0: kfree(fb); + sti->info = NULL; return -ENXIO; } From 01c3d3064975944a2edefef6e2f99db3244ca999 Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Fri, 12 May 2023 17:05:32 +0400 Subject: [PATCH 3345/4345] nbd: Fix debugfs_create_dir error checking [ Upstream commit 4913cfcf014c95f0437db2df1734472fd3e15098 ] The debugfs_create_dir function returns ERR_PTR in case of error, and the only correct way to check if an error occurred is 'IS_ERR' inline function. This patch will replace the null-comparison with IS_ERR. Signed-off-by: Ivan Orlov Link: https://lore.kernel.org/r/20230512130533.98709-1-ivan.orlov0322@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/nbd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index dbcd903ba128..b6940f0a9c90 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1624,7 +1624,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd) return -EIO; dir = debugfs_create_dir(nbd_name(nbd), nbd_dbg_dir); - if (!dir) { + if (IS_ERR(dir)) { dev_err(nbd_to_dev(nbd), "Failed to create debugfs dir for '%s'\n", nbd_name(nbd)); return -EIO; @@ -1650,7 +1650,7 @@ static int nbd_dbg_init(void) struct dentry *dbg_dir; dbg_dir = debugfs_create_dir("nbd", NULL); - if (!dbg_dir) + if (IS_ERR(dbg_dir)) return -EIO; nbd_dbg_dir = dbg_dir; From 32f6f1bf1befec1ae7743b5b77ed1027ebe20e7c Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Fri, 12 May 2023 11:46:31 +0800 Subject: [PATCH 3346/4345] block/rnbd: replace REQ_OP_FLUSH with REQ_OP_WRITE [ Upstream commit 5e6e08087a4acb4ee3574cea32dbff0f63c7f608 ] Since flush bios are implemented as writes with no data and the preflush flag per Christoph's comment [1]. And we need to change it in rnbd accordingly. Otherwise, I got splatting when create fs from rnbd client. [ 464.028545] ------------[ cut here ]------------ [ 464.028553] WARNING: CPU: 0 PID: 65 at block/blk-core.c:751 submit_bio_noacct+0x32c/0x5d0 [ ... ] [ 464.028668] CPU: 0 PID: 65 Comm: kworker/0:1H Tainted: G OE 6.4.0-rc1 #9 [ 464.028671] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.15.0-0-g2dd4b9b-rebuilt.opensuse.org 04/01/2014 [ 464.028673] Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] [ 464.028717] RIP: 0010:submit_bio_noacct+0x32c/0x5d0 [ 464.028720] Code: 03 0f 85 51 fe ff ff 48 8b 43 18 8b 88 04 03 00 00 85 c9 0f 85 3f fe ff ff e9 be fd ff ff 0f b6 d0 3c 0d 74 26 83 fa 01 74 21 <0f> 0b b8 0a 00 00 00 e9 56 fd ff ff 4c 89 e7 e8 70 a1 03 00 84 c0 [ 464.028722] RSP: 0018:ffffaf3680b57c68 EFLAGS: 00010202 [ 464.028724] RAX: 0000000000060802 RBX: ffffa09dcc18bf00 RCX: 0000000000000000 [ 464.028726] RDX: 0000000000000002 RSI: 0000000000000000 RDI: ffffa09dde081d00 [ 464.028727] RBP: ffffaf3680b57c98 R08: ffffa09dde081d00 R09: ffffa09e38327200 [ 464.028729] R10: 0000000000000000 R11: 0000000000000000 R12: ffffa09dde081d00 [ 464.028730] R13: ffffa09dcb06e1e8 R14: 0000000000000000 R15: 0000000000200000 [ 464.028733] FS: 0000000000000000(0000) GS:ffffa09e3bc00000(0000) knlGS:0000000000000000 [ 464.028735] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 464.028736] CR2: 000055a4e8206c40 CR3: 0000000119f06000 CR4: 00000000003506f0 [ 464.028738] Call Trace: [ 464.028740] [ 464.028746] submit_bio+0x1b/0x80 [ 464.028748] rnbd_srv_rdma_ev+0x50d/0x10c0 [rnbd_server] [ 464.028754] ? percpu_ref_get_many.constprop.0+0x55/0x140 [rtrs_server] [ 464.028760] ? __this_cpu_preempt_check+0x13/0x20 [ 464.028769] process_io_req+0x1dc/0x450 [rtrs_server] [ 464.028775] rtrs_srv_inv_rkey_done+0x67/0xb0 [rtrs_server] [ 464.028780] __ib_process_cq+0xbc/0x1f0 [ib_core] [ 464.028793] ib_cq_poll_work+0x2b/0xa0 [ib_core] [ 464.028804] process_one_work+0x2a9/0x580 [1]. https://lore.kernel.org/all/ZFHgefWofVt24tRl@infradead.org/ Signed-off-by: Guoqing Jiang Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20230512034631.28686-1-guoqing.jiang@linux.dev Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/rnbd/rnbd-proto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h index ca166241452c..cb11855455dd 100644 --- a/drivers/block/rnbd/rnbd-proto.h +++ b/drivers/block/rnbd/rnbd-proto.h @@ -234,7 +234,7 @@ static inline u32 rnbd_to_bio_flags(u32 rnbd_opf) bio_opf = REQ_OP_WRITE; break; case RNBD_OP_FLUSH: - bio_opf = REQ_OP_FLUSH | REQ_PREFLUSH; + bio_opf = REQ_OP_WRITE | REQ_PREFLUSH; break; case RNBD_OP_DISCARD: bio_opf = REQ_OP_DISCARD; From 5ee83fef0c24469a69a03bf3075fe23c9f7feb14 Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Fri, 5 May 2023 09:28:20 +0300 Subject: [PATCH 3347/4345] ASoC: dwc: limit the number of overrun messages [ Upstream commit ab6ecfbf40fccf74b6ec2ba7ed6dd2fc024c3af2 ] On slow CPU (FPGA/QEMU emulated) printing overrun messages from interrupt handler to uart console may leads to more overrun errors. So use dev_err_ratelimited to limit the number of error messages. Signed-off-by: Maxim Kochetkov --- sound/soc/dwc/dwc-i2s.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/dwc/dwc-i2s.c b/sound/soc/dwc/dwc-i2s.c index 36da0f01571a..5469399abcb4 100644 --- a/sound/soc/dwc/dwc-i2s.c +++ b/sound/soc/dwc/dwc-i2s.c @@ -132,13 +132,13 @@ static irqreturn_t i2s_irq_handler(int irq, void *dev_id) /* Error Handling: TX */ if (isr[i] & ISR_TXFO) { - dev_err(dev->dev, "TX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "TX overrun (ch_id=%d)\n", i); irq_valid = true; } /* Error Handling: TX */ if (isr[i] & ISR_RXFO) { - dev_err(dev->dev, "RX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "RX overrun (ch_id=%d)\n", i); irq_valid = true; } } From bd99da647262d2765db7364eafbb2e42e3c3ccf0 Mon Sep 17 00:00:00 2001 From: Benedict Wong Date: Wed, 10 May 2023 01:14:14 +0000 Subject: [PATCH 3348/4345] xfrm: Check if_id in inbound policy/secpath match [ Upstream commit 8680407b6f8f5fba59e8f1d63c869abc280f04df ] This change ensures that if configured in the policy, the if_id set in the policy and secpath states match during the inbound policy check. Without this, there is potential for ambiguity where entries in the secpath differing by only the if_id could be mismatched. Notably, this is checked in the outbound direction when resolving templates to SAs, but not on the inbound path when matching SAs and policies. Test: Tested against Android kernel unit tests & CTS Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_policy.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 295685492853..d3b128b74a38 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3240,7 +3240,7 @@ xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, - unsigned short family) + unsigned short family, u32 if_id) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); @@ -3251,7 +3251,8 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, (tmpl->allalgs || (tmpl->aalgos & (1<props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && - xfrm_state_addr_cmp(tmpl, x, family)); + xfrm_state_addr_cmp(tmpl, x, family)) && + (if_id == 0 || if_id == x->if_id); } /* @@ -3263,7 +3264,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, - unsigned short family) + unsigned short family, u32 if_id) { int idx = start; @@ -3273,7 +3274,7 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star } else start = -1; for (; idx < sp->len; idx++) { - if (xfrm_state_ok(tmpl, sp->xvec[idx], family)) + if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (start == -1) @@ -3689,7 +3690,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * are implied between each two transformations. */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { - k = xfrm_policy_ok(tpp[i], sp, k, family); + k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ From beee708cccccbd23944129c592a69bd344379923 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Povi=C5=A1er?= Date: Tue, 9 May 2023 17:34:12 +0200 Subject: [PATCH 3349/4345] ASoC: dt-bindings: Adjust #sound-dai-cells on TI's single-DAI codecs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit efb2bfd7b3d210c479b9361c176d7426e5eb8663 ] A bunch of TI's codecs have binding schemas which force #sound-dai-cells to one despite those codecs only having a single DAI. Allow for bindings with zero DAI cells and deprecate the former non-zero value. Signed-off-by: Martin Povišer --- Documentation/devicetree/bindings/sound/tas2562.yaml | 6 ++++-- Documentation/devicetree/bindings/sound/tas2764.yaml | 6 ++++-- Documentation/devicetree/bindings/sound/tas2770.yaml | 6 ++++-- 3 files changed, 12 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/sound/tas2562.yaml b/Documentation/devicetree/bindings/sound/tas2562.yaml index 27f7132ba2ef..6ccb346d4a4d 100644 --- a/Documentation/devicetree/bindings/sound/tas2562.yaml +++ b/Documentation/devicetree/bindings/sound/tas2562.yaml @@ -50,7 +50,9 @@ properties: description: TDM TX current sense time slot. '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -67,7 +69,7 @@ examples: codec: codec@4c { compatible = "ti,tas2562"; reg = <0x4c>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; shutdown-gpios = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas2764.yaml b/Documentation/devicetree/bindings/sound/tas2764.yaml index 5bf8c76ecda1..1ffe1a01668f 100644 --- a/Documentation/devicetree/bindings/sound/tas2764.yaml +++ b/Documentation/devicetree/bindings/sound/tas2764.yaml @@ -46,7 +46,9 @@ properties: description: TDM TX voltage sense time slot. '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -63,7 +65,7 @@ examples: codec: codec@38 { compatible = "ti,tas2764"; reg = <0x38>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpios = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas2770.yaml b/Documentation/devicetree/bindings/sound/tas2770.yaml index 07e7f9951d2e..f3d0ca067bea 100644 --- a/Documentation/devicetree/bindings/sound/tas2770.yaml +++ b/Documentation/devicetree/bindings/sound/tas2770.yaml @@ -52,7 +52,9 @@ properties: - 1 # Falling edge '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -69,7 +71,7 @@ examples: codec: codec@41 { compatible = "ti,tas2770"; reg = <0x41>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpio = <&gpio1 15 0>; From 204e9082f6af2e5b10fa2548c6f5bcebc93ec199 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pawe=C5=82=20Anikiel?= Date: Mon, 8 May 2023 13:30:37 +0200 Subject: [PATCH 3350/4345] ASoC: ssm2602: Add workaround for playback distortions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f63550e2b165208a2f382afcaf5551df9569e1d4 ] Apply a workaround for what appears to be a hardware quirk. The problem seems to happen when enabling "whole chip power" (bit D7 register R6) for the very first time after the chip receives power. If either "output" (D4) or "DAC" (D3) aren't powered on at that time, playback becomes very distorted later on. This happens on the Google Chameleon v3, as well as on a ZYBO Z7-10: https://ez.analog.com/audio/f/q-a/543726/solved-ssm2603-right-output-offset-issue/480229 I suspect this happens only when using an external MCLK signal (which is the case for both of these boards). Here are some experiments run on a Google Chameleon v3. These were run in userspace using a wrapper around the i2cset utility: ssmset() { i2cset -y 0 0x1a $(($1*2)) $2 } For each of the following sequences, we apply power to the ssm2603 chip, set the configuration registers R0-R5 and R7-R8, run the selected sequence, and check for distortions on playback. ssmset 0x09 0x01 # core ssmset 0x06 0x07 # chip, out, dac OK ssmset 0x09 0x01 # core ssmset 0x06 0x87 # out, dac ssmset 0x06 0x07 # chip OK (disable MCLK) ssmset 0x09 0x01 # core ssmset 0x06 0x1f # chip ssmset 0x06 0x07 # out, dac (enable MCLK) OK ssmset 0x09 0x01 # core ssmset 0x06 0x1f # chip ssmset 0x06 0x07 # out, dac NOT OK ssmset 0x06 0x1f # chip ssmset 0x09 0x01 # core ssmset 0x06 0x07 # out, dac NOT OK ssmset 0x09 0x01 # core ssmset 0x06 0x0f # chip, out ssmset 0x06 0x07 # dac NOT OK ssmset 0x09 0x01 # core ssmset 0x06 0x17 # chip, dac ssmset 0x06 0x07 # out NOT OK For each of the following sequences, we apply power to the ssm2603 chip, run the selected sequence, issue a reset with R15, configure R0-R5 and R7-R8, run one of the NOT OK sequences from above, and check for distortions. ssmset 0x09 0x01 # core ssmset 0x06 0x07 # chip, out, dac OK (disable MCLK) ssmset 0x09 0x01 # core ssmset 0x06 0x07 # chip, out, dac (enable MCLK after reset) NOT OK ssmset 0x09 0x01 # core ssmset 0x06 0x17 # chip, dac NOT OK ssmset 0x09 0x01 # core ssmset 0x06 0x0f # chip, out NOT OK ssmset 0x06 0x07 # chip, out, dac NOT OK Signed-off-by: Paweł Anikiel --- sound/soc/codecs/ssm2602.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/sound/soc/codecs/ssm2602.c b/sound/soc/codecs/ssm2602.c index 905160246614..c7a90c34d8f0 100644 --- a/sound/soc/codecs/ssm2602.c +++ b/sound/soc/codecs/ssm2602.c @@ -53,6 +53,18 @@ static const struct reg_default ssm2602_reg[SSM2602_CACHEREGNUM] = { { .reg = 0x09, .def = 0x0000 } }; +/* + * ssm2602 register patch + * Workaround for playback distortions after power up: activates digital + * core, and then powers on output, DAC, and whole chip at the same time + */ + +static const struct reg_sequence ssm2602_patch[] = { + { SSM2602_ACTIVE, 0x01 }, + { SSM2602_PWR, 0x07 }, + { SSM2602_RESET, 0x00 }, +}; + /*Appending several "None"s just for OSS mixer use*/ static const char *ssm2602_input_select[] = { @@ -589,6 +601,9 @@ static int ssm260x_component_probe(struct snd_soc_component *component) return ret; } + regmap_register_patch(ssm2602->regmap, ssm2602_patch, + ARRAY_SIZE(ssm2602_patch)); + /* set the update bits */ regmap_update_bits(ssm2602->regmap, SSM2602_LINVOL, LINVOL_LRIN_BOTH, LINVOL_LRIN_BOTH); From a81280cf3343bd49f62a599b3528dbf304945dbb Mon Sep 17 00:00:00 2001 From: YongSu Yoo Date: Sun, 5 Mar 2023 21:25:19 +0000 Subject: [PATCH 3351/4345] media: dvb_demux: fix a bug for the continuity counter [ Upstream commit 7efb10d8dc70ea3000cc70dca53407c52488acd1 ] In dvb_demux.c, some logics exist which compare the expected continuity counter and the real continuity counter. If they are not matched each other, both of the expected continuity counter and the real continuity counter should be printed. But there exists a bug that the expected continuity counter is not correctly printed. The expected continuity counter is replaced with the real countinuity counter + 1 so that the epected continuity counter is not correclty printed. This is wrong. This bug is fixed. Link: https://lore.kernel.org/linux-media/20230305212519.499-1-yongsuyoo0215@gmail.com Signed-off-by: YongSu Yoo Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/dvb-core/dvb_demux.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c index 5fde1d38b3e3..80b495982f63 100644 --- a/drivers/media/dvb-core/dvb_demux.c +++ b/drivers/media/dvb-core/dvb_demux.c @@ -125,12 +125,12 @@ static inline int dvb_dmx_swfilter_payload(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (!ccok) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("missed packet: %d instead of %d!\n", cc, (feed->cc + 1) & 0x0f); } + feed->cc = cc; if (buf[1] & 0x40) // PUSI ? feed->peslen = 0xfffa; @@ -310,7 +310,6 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (buf[3] & 0x20) { /* adaption field present, check for discontinuity_indicator */ @@ -346,6 +345,7 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, feed->pusi_seen = false; dvb_dmx_swfilter_section_new(feed); } + feed->cc = cc; if (buf[1] & 0x40) { /* PUSI=1 (is set), section boundary is here */ From 084e43d9a4c19defff5af848a697be8964704103 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Fri, 10 Mar 2023 16:56:04 +0000 Subject: [PATCH 3352/4345] media: dvb-usb: az6027: fix three null-ptr-deref in az6027_i2c_xfer() [ Upstream commit 858e97d7956d17a2cb56a9413468704a4d5abfe1 ] In az6027_i2c_xfer, msg is controlled by user. When msg[i].buf is null, commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") fix the null-ptr-deref bug when msg[i].addr is 0x99. However, null-ptr-deref also happens when msg[i].addr is 0xd0 and 0xc0. We add check on msg[i].len to prevent null-ptr-deref. Link: https://lore.kernel.org/linux-media/20230310165604.3093483-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb/az6027.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/media/usb/dvb-usb/az6027.c b/drivers/media/usb/dvb-usb/az6027.c index 32b4ee65c280..991f4510aaeb 100644 --- a/drivers/media/usb/dvb-usb/az6027.c +++ b/drivers/media/usb/dvb-usb/az6027.c @@ -988,6 +988,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* write/read request */ if (i + 1 < num && (msg[i + 1].flags & I2C_M_RD)) { req = 0xB9; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (msg[i].len << 8); length = msg[i + 1].len + 6; @@ -1001,6 +1005,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* demod 16bit addr */ req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (2 << 8); length = msg[i].len - 2; @@ -1026,6 +1034,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n } else { req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = msg[i].buf[0] & 0x00FF; value = msg[i].addr + (1 << 8); length = msg[i].len - 1; From 647da51e4da72208cfbb1d59d160bbf8e24b82a6 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Mon, 13 Mar 2023 08:58:53 +0000 Subject: [PATCH 3353/4345] media: dvb-usb-v2: ec168: fix null-ptr-deref in ec168_i2c_xfer() [ Upstream commit a6dcefcc08eca1bf4e3d213c97c3cfb75f377935 ] In ec168_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. If accessing msg[i].buf[0] without sanity check, null pointer deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/20230313085853.3252349-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb-v2/ec168.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/ec168.c b/drivers/media/usb/dvb-usb-v2/ec168.c index 7ed0ab9e429b..0e4773fc025c 100644 --- a/drivers/media/usb/dvb-usb-v2/ec168.c +++ b/drivers/media/usb/dvb-usb-v2/ec168.c @@ -115,6 +115,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], while (i < num) { if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = READ_DEMOD; req.value = 0; req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -131,6 +135,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], } } else { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_DEMOD; req.value = msg[i].buf[1]; /* val */ req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -139,6 +147,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = ec168_ctrl_msg(d, &req); i += 1; } else { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_I2C; req.value = msg[i].buf[0]; /* val */ req.index = 0x0100 + msg[i].addr; /* I2C addr */ From 2d47867a6b3c07af69e2996af409c3464e2206a6 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Mon, 13 Mar 2023 09:27:51 +0000 Subject: [PATCH 3354/4345] media: dvb-usb-v2: ce6230: fix null-ptr-deref in ce6230_i2c_master_xfer() [ Upstream commit dff919090155fb22679869e8469168f270dcd97f ] In ce6230_i2c_master_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach ce6230_i2c_master_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/20230313092751.209496-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb-v2/ce6230.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/ce6230.c b/drivers/media/usb/dvb-usb-v2/ce6230.c index 44540de1a206..d3b5cb4a24da 100644 --- a/drivers/media/usb/dvb-usb-v2/ce6230.c +++ b/drivers/media/usb/dvb-usb-v2/ce6230.c @@ -101,6 +101,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_READ; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; @@ -117,6 +121,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, } else { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_WRITE; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; From 7945c13c9b7fd7cc0725e6a8cd30480b08eed858 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sun, 7 May 2023 15:52:47 +0100 Subject: [PATCH 3355/4345] media: dvb-usb-v2: rtl28xxu: fix null-ptr-deref in rtl28xxu_i2c_xfer [ Upstream commit aa4a447b81b84f69c1a89ad899df157f386d7636 ] In rtl28xxu_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach rtl28xxu_i2c_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/tencent_3623572106754AC2F266B316798B0F6CCA05@qq.com Signed-off-by: Zhang Shurong Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index c278b9b0f102..70a2f0494216 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -176,6 +176,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1 || msg[1].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { /* return demod page from driver cache */ @@ -189,6 +193,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if (msg[0].len < 2) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_RD; @@ -217,8 +225,16 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { + if (msg[0].len < 2) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* save demod page for later demod access */ dev->page = msg[0].buf[1]; ret = 0; @@ -231,6 +247,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if ((msg[0].len < 23) && (!dev->new_i2c_write)) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_WR; From fcbb72b041d901c78e21a407929b2795046572d4 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Mon, 13 Mar 2023 09:50:08 +0000 Subject: [PATCH 3356/4345] media: dvb-usb: digitv: fix null-ptr-deref in digitv_i2c_xfer() [ Upstream commit 9ded5bd2a49ce3015b7c936743eec0a0e6e11f0c ] In digitv_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach digitv_i2c_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/20230313095008.1039689-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb/digitv.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c index 4e3b3c064bcf..e56efebd4f0a 100644 --- a/drivers/media/usb/dvb-usb/digitv.c +++ b/drivers/media/usb/dvb-usb/digitv.c @@ -63,6 +63,10 @@ static int digitv_i2c_xfer(struct i2c_adapter *adap,struct i2c_msg msg[],int num warn("more than 2 i2c messages at a time is not handled yet. TODO."); for (i = 0; i < num; i++) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } /* write/read request */ if (i+1 < num && (msg[i+1].flags & I2C_M_RD)) { if (digitv_ctrl_msg(d, USB_READ_COFDM, msg[i].buf[0], NULL, 0, From 74c80d2024d99fb01a7b0d898ad7ac8380d45aab Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Tue, 28 Mar 2023 13:44:16 +0100 Subject: [PATCH 3357/4345] media: dvb-usb: dw2102: fix uninit-value in su3000_read_mac_address [ Upstream commit a3fd1ef27aa686d871cefe207bd6168c4b0cd29e ] In su3000_read_mac_address, if i2c_transfer fails to execute two messages, array mac address will not be initialized. Without handling such error, later in function dvb_usb_adapter_dvb_init, proposed_mac is accessed before initialization. Fix this error by returning a negative value if message execution fails. Link: https://lore.kernel.org/linux-media/20230328124416.560889-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb/dw2102.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index aa929db56db1..3c4ac998d040 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -946,7 +946,7 @@ static int su3000_read_mac_address(struct dvb_usb_device *d, u8 mac[6]) for (i = 0; i < 6; i++) { obuf[1] = 0xf0 + i; if (i2c_transfer(&d->i2c_adap, msg, 2) != 2) - break; + return -1; else mac[i] = ibuf[0]; } From b85233ab5335e338c1f0d6d3c39ae9e4afd0a7ff Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Wed, 15 Mar 2023 13:45:18 +0000 Subject: [PATCH 3358/4345] media: netup_unidvb: fix irq init by register it at the end of probe [ Upstream commit e6ad6233592593079db5c8fa592c298e51bc1356 ] IRQ handler netup_spi_interrupt() takes spinlock spi->lock. The lock is initialized in netup_spi_init(). However, irq handler is registered before initializing the lock. Spinlock dma->lock and i2c->lock suffer from the same problem. Fix this by registering the irq at the end of probe. Link: https://lore.kernel.org/linux-media/20230315134518.1074497-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- .../media/pci/netup_unidvb/netup_unidvb_core.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index a71814e2772d..7c5061953ee8 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -887,12 +887,7 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, ndev->lmmio0, (u32)pci_resource_len(pci_dev, 0), ndev->lmmio1, (u32)pci_resource_len(pci_dev, 1), pci_dev->irq); - if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, - "netup_unidvb", pci_dev) < 0) { - dev_err(&pci_dev->dev, - "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); - goto irq_request_err; - } + ndev->dma_size = 2 * 188 * NETUP_DMA_BLOCKS_COUNT * NETUP_DMA_PACKETS_COUNT; ndev->dma_virt = dma_alloc_coherent(&pci_dev->dev, @@ -933,6 +928,14 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, dev_err(&pci_dev->dev, "netup_unidvb: DMA setup failed\n"); goto dma_setup_err; } + + if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, + "netup_unidvb", pci_dev) < 0) { + dev_err(&pci_dev->dev, + "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); + goto dma_setup_err; + } + dev_info(&pci_dev->dev, "netup_unidvb: device has been initialized\n"); return 0; @@ -951,8 +954,6 @@ spi_setup_err: dma_free_coherent(&pci_dev->dev, ndev->dma_size, ndev->dma_virt, ndev->dma_phys); dma_alloc_err: - free_irq(pci_dev->irq, pci_dev); -irq_request_err: iounmap(ndev->lmmio1); pci_bar1_error: iounmap(ndev->lmmio0); From 1995e714725fe7ccd6751277f87421dc5d22ff51 Mon Sep 17 00:00:00 2001 From: YongSu Yoo Date: Thu, 18 Aug 2022 13:50:27 +0100 Subject: [PATCH 3359/4345] media: dvb_ca_en50221: fix a size write bug [ Upstream commit a4315e5be7020aac9b24a8151caf4bb85224cd0e ] The function of "dvb_ca_en50221_write_data" at source/drivers/media /dvb-core/dvb_ca_en50221.c is used for two cases. The first case is for writing APDU data in the function of "dvb_ca_en50221_io_write" at source/drivers/media/dvb-core/ dvb_ca_en50221.c. The second case is for writing the host link buf size on the Command Register in the function of "dvb_ca_en50221_link_init" at source/drivers/media/dvb-core/dvb_ca_en50221.c. In the second case, there exists a bug like following. In the function of the "dvb_ca_en50221_link_init", after a TV host calculates the host link buf_size, the TV host writes the calculated host link buf_size on the Size Register. Accroding to the en50221 Spec (the page 60 of https://dvb.org/wp-content/uploads/2020/02/En50221.V1.pdf), before this writing operation, the "SW(CMDREG_SW)" flag in the Command Register should be set. We can see this setting operation in the function of the "dvb_ca_en50221_link_init" like below. ... if ((ret = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN | CMDREG_SW)) != 0) return ret; ... But, after that, the real writing operation is implemented using the function of the "dvb_ca_en50221_write_data" in the function of "dvb_ca_en50221_link_init", and the "dvb_ca_en50221_write_data" includes the function of "ca->pub->write_cam_control", and the function of the "ca->pub->write_cam_control" in the function of the "dvb_ca_en50221_wrte_data" does not include "CMDREG_SW" flag like below. ... if ((status = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN | CMDREG_HC)) != 0) ... In the above source code, we can see only the "IRQEN | CMDREG_HC", but we cannot see the "CMDREG_SW". The "CMDREG_SW" flag which was set in the function of the "dvb_ca_en50221_link_init" was rollbacked by the follwoing function of the "dvb_ca_en50221_write_data". This is a bug. and this bug causes that the calculated host link buf_size is not properly written in the CI module. Through this patch, we fix this bug. Link: https://lore.kernel.org/linux-media/20220818125027.1131-1-yongsuyoo0215@gmail.com Signed-off-by: YongSu Yoo Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/dvb-core/dvb_ca_en50221.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index fd476536d32e..b1a7b5f8b9aa 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -187,7 +187,7 @@ static void dvb_ca_en50221_thread_wakeup(struct dvb_ca_private *ca); static int dvb_ca_en50221_read_data(struct dvb_ca_private *ca, int slot, u8 *ebuf, int ecount); static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *ebuf, int ecount); + u8 *ebuf, int ecount, int size_write_flag); /** * Safely find needle in haystack. @@ -370,7 +370,7 @@ static int dvb_ca_en50221_link_init(struct dvb_ca_private *ca, int slot) ret = dvb_ca_en50221_wait_if_status(ca, slot, STATUSREG_FR, HZ / 10); if (ret) return ret; - ret = dvb_ca_en50221_write_data(ca, slot, buf, 2); + ret = dvb_ca_en50221_write_data(ca, slot, buf, 2, CMDREG_SW); if (ret != 2) return -EIO; ret = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN); @@ -778,11 +778,13 @@ exit: * @buf: The data in this buffer is treated as a complete link-level packet to * be written. * @bytes_write: Size of ebuf. + * @size_write_flag: A flag on Command Register which says whether the link size + * information will be writen or not. * * return: Number of bytes written, or < 0 on error. */ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *buf, int bytes_write) + u8 *buf, int bytes_write, int size_write_flag) { struct dvb_ca_slot *sl = &ca->slot_info[slot]; int status; @@ -817,7 +819,7 @@ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, /* OK, set HC bit */ status = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, - IRQEN | CMDREG_HC); + IRQEN | CMDREG_HC | size_write_flag); if (status) goto exit; @@ -1505,7 +1507,7 @@ static ssize_t dvb_ca_en50221_io_write(struct file *file, mutex_lock(&sl->slot_lock); status = dvb_ca_en50221_write_data(ca, slot, fragbuf, - fraglen + 2); + fraglen + 2, 0); mutex_unlock(&sl->slot_lock); if (status == (fraglen + 2)) { written = 1; From eb37fef417a246fe54530901a3ea9c0abc914fc2 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:25 +0000 Subject: [PATCH 3360/4345] media: ttusb-dec: fix memory leak in ttusb_dec_exit_dvb() [ Upstream commit 517a281338322ff8293f988771c98aaa7205e457 ] Since dvb_frontend_detach() is not called in ttusb_dec_exit_dvb(), which is called when the device is disconnected, dvb_frontend_free() is not finally called. This causes a memory leak just by repeatedly plugging and unplugging the device. Fix this issue by adding dvb_frontend_detach() to ttusb_dec_exit_dvb(). Link: https://lore.kernel.org/linux-media/20221117045925.14297-5-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/usb/ttusb-dec/ttusb_dec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/usb/ttusb-dec/ttusb_dec.c b/drivers/media/usb/ttusb-dec/ttusb_dec.c index df6c5e4a0f05..68f88143c8a6 100644 --- a/drivers/media/usb/ttusb-dec/ttusb_dec.c +++ b/drivers/media/usb/ttusb-dec/ttusb_dec.c @@ -1551,8 +1551,7 @@ static void ttusb_dec_exit_dvb(struct ttusb_dec *dec) dvb_dmx_release(&dec->demux); if (dec->fe) { dvb_unregister_frontend(dec->fe); - if (dec->fe->ops.release) - dec->fe->ops.release(dec->fe); + dvb_frontend_detach(dec->fe); } dvb_unregister_adapter(&dec->adapter); } From 415651c8f468d5f15f7f1cb6f3d0fd379341735e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 13:13:18 +0000 Subject: [PATCH 3361/4345] media: mn88443x: fix !CONFIG_OF error by drop of_match_ptr from ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ae11c0efaec32fb45130ee9886689f467232eebc ] The driver will match mostly by DT table (even thought there is regular ID table) so there is little benefit in of_match_ptr (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/media/dvb-frontends/mn88443x.c:782:34: error: ‘mn88443x_of_match’ defined but not used [-Werror=unused-const-variable=] Link: https://lore.kernel.org/linux-media/20230312131318.351173-28-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/dvb-frontends/mn88443x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/dvb-frontends/mn88443x.c b/drivers/media/dvb-frontends/mn88443x.c index fff212c0bf3b..05894deb8a19 100644 --- a/drivers/media/dvb-frontends/mn88443x.c +++ b/drivers/media/dvb-frontends/mn88443x.c @@ -800,7 +800,7 @@ MODULE_DEVICE_TABLE(i2c, mn88443x_i2c_id); static struct i2c_driver mn88443x_driver = { .driver = { .name = "mn88443x", - .of_match_table = of_match_ptr(mn88443x_of_match), + .of_match_table = mn88443x_of_match, }, .probe = mn88443x_probe, .remove = mn88443x_remove, From 2ea7d26ed851db7176e4bfa8174c8a1380255bbe Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:23 +0000 Subject: [PATCH 3362/4345] media: dvb-core: Fix use-after-free due on race condition at dvb_net [ Upstream commit 4172385b0c9ac366dcab78eda48c26814b87ed1a ] A race condition may occur between the .disconnect function, which is called when the device is disconnected, and the dvb_device_open() function, which is called when the device node is open()ed. This results in several types of UAFs. The root cause of this is that you use the dvb_device_open() function, which does not implement a conditional statement that checks 'dvbnet->exit'. So, add 'remove_mutex` to protect 'dvbnet->exit' and use locked_dvb_net_open() function to check 'dvbnet->exit'. [mchehab: fix a checkpatch warning] Link: https://lore.kernel.org/linux-media/20221117045925.14297-3-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/dvb-core/dvb_net.c | 38 +++++++++++++++++++++++++++++--- include/media/dvb_net.h | 4 ++++ 2 files changed, 39 insertions(+), 3 deletions(-) diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index dddebea644bb..c594b1bdfcaa 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -1564,15 +1564,43 @@ static long dvb_net_ioctl(struct file *file, return dvb_usercopy(file, cmd, arg, dvb_net_do_ioctl); } +static int locked_dvb_net_open(struct inode *inode, struct file *file) +{ + struct dvb_device *dvbdev = file->private_data; + struct dvb_net *dvbnet = dvbdev->priv; + int ret; + + if (mutex_lock_interruptible(&dvbnet->remove_mutex)) + return -ERESTARTSYS; + + if (dvbnet->exit) { + mutex_unlock(&dvbnet->remove_mutex); + return -ENODEV; + } + + ret = dvb_generic_open(inode, file); + + mutex_unlock(&dvbnet->remove_mutex); + + return ret; +} + static int dvb_net_close(struct inode *inode, struct file *file) { struct dvb_device *dvbdev = file->private_data; struct dvb_net *dvbnet = dvbdev->priv; + mutex_lock(&dvbnet->remove_mutex); + dvb_generic_release(inode, file); - if(dvbdev->users == 1 && dvbnet->exit == 1) + if (dvbdev->users == 1 && dvbnet->exit == 1) { + mutex_unlock(&dvbnet->remove_mutex); wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&dvbnet->remove_mutex); + } + return 0; } @@ -1580,7 +1608,7 @@ static int dvb_net_close(struct inode *inode, struct file *file) static const struct file_operations dvb_net_fops = { .owner = THIS_MODULE, .unlocked_ioctl = dvb_net_ioctl, - .open = dvb_generic_open, + .open = locked_dvb_net_open, .release = dvb_net_close, .llseek = noop_llseek, }; @@ -1599,10 +1627,13 @@ void dvb_net_release (struct dvb_net *dvbnet) { int i; + mutex_lock(&dvbnet->remove_mutex); dvbnet->exit = 1; + mutex_unlock(&dvbnet->remove_mutex); + if (dvbnet->dvbdev->users < 1) wait_event(dvbnet->dvbdev->wait_queue, - dvbnet->dvbdev->users==1); + dvbnet->dvbdev->users == 1); dvb_unregister_device(dvbnet->dvbdev); @@ -1621,6 +1652,7 @@ int dvb_net_init (struct dvb_adapter *adap, struct dvb_net *dvbnet, int i; mutex_init(&dvbnet->ioctl_mutex); + mutex_init(&dvbnet->remove_mutex); dvbnet->demux = dmx; for (i=0; i Date: Fri, 12 May 2023 16:18:00 +0100 Subject: [PATCH 3363/4345] media: dvb-core: Fix kernel WARNING for blocking operation in wait_event*() [ Upstream commit b8c75e4a1b325ea0a9433fa8834be97b5836b946 ] Using a semaphore in the wait_event*() condition is no good idea. It hits a kernel WARN_ON() at prepare_to_wait_event() like: do not call blocking ops when !TASK_RUNNING; state=1 set at prepare_to_wait_event+0x6d/0x690 For avoiding the potential deadlock, rewrite to an open-coded loop instead. Unlike the loop in wait_event*(), this uses wait_woken() after the condition check, hence the task state stays consistent. CVE-2023-31084 was assigned to this bug. Link: https://lore.kernel.org/r/CA+UBctCu7fXn4q41O_3=id1+OdyQ85tZY1x+TkT-6OVBL6KAUw@mail.gmail.com/ Link: https://lore.kernel.org/linux-media/20230512151800.1874-1-tiwai@suse.de Reported-by: Yu Hao Closes: https://nvd.nist.gov/vuln/detail/CVE-2023-31084 Signed-off-by: Takashi Iwai Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/dvb-core/dvb_frontend.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index b04638321b75..ad3e42a4eaf7 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -292,14 +292,22 @@ static int dvb_frontend_get_event(struct dvb_frontend *fe, } if (events->eventw == events->eventr) { - int ret; + struct wait_queue_entry wait; + int ret = 0; if (flags & O_NONBLOCK) return -EWOULDBLOCK; - ret = wait_event_interruptible(events->wait_queue, - dvb_frontend_test_event(fepriv, events)); - + init_waitqueue_entry(&wait, current); + add_wait_queue(&events->wait_queue, &wait); + while (!dvb_frontend_test_event(fepriv, events)) { + wait_woken(&wait, TASK_INTERRUPTIBLE, 0); + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + } + remove_wait_queue(&events->wait_queue, &wait); if (ret < 0) return ret; } From 76169f7490899d74aad4b0e2c4c1b9d4904dd01f Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Mon, 21 Nov 2022 06:33:08 +0000 Subject: [PATCH 3364/4345] media: dvb-core: Fix use-after-free due to race condition at dvb_ca_en50221 [ Upstream commit 280a8ab81733da8bc442253c700a52c4c0886ffd ] If the device node of dvb_ca_en50221 is open() and the device is disconnected, a UAF may occur when calling close() on the device node. The root cause is that wake_up() and wait_event() for dvbdev->wait_queue are not implemented. So implement wait_event() function in dvb_ca_en50221_release() and add 'remove_mutex' which prevents race condition for 'ca->exit'. [mchehab: fix a checkpatch warning] Link: https://lore.kernel.org/linux-media/20221121063308.GA33821@ubuntu Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/dvb-core/dvb_ca_en50221.c | 37 ++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index b1a7b5f8b9aa..dec036e0336c 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -151,6 +151,12 @@ struct dvb_ca_private { /* mutex serializing ioctls */ struct mutex ioctl_mutex; + + /* A mutex used when a device is disconnected */ + struct mutex remove_mutex; + + /* Whether the device is disconnected */ + int exit; }; static void dvb_ca_private_free(struct dvb_ca_private *ca) @@ -1708,12 +1714,22 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dprintk("%s\n", __func__); - if (!try_module_get(ca->pub->owner)) + mutex_lock(&ca->remove_mutex); + + if (ca->exit) { + mutex_unlock(&ca->remove_mutex); + return -ENODEV; + } + + if (!try_module_get(ca->pub->owner)) { + mutex_unlock(&ca->remove_mutex); return -EIO; + } err = dvb_generic_open(inode, file); if (err < 0) { module_put(ca->pub->owner); + mutex_unlock(&ca->remove_mutex); return err; } @@ -1738,6 +1754,7 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dvb_ca_private_get(ca); + mutex_unlock(&ca->remove_mutex); return 0; } @@ -1757,6 +1774,8 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + /* mark the CA device as closed */ ca->open = 0; dvb_ca_en50221_thread_update_delay(ca); @@ -1767,6 +1786,13 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dvb_ca_private_put(ca); + if (dvbdev->users == 1 && ca->exit == 1) { + mutex_unlock(&ca->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&ca->remove_mutex); + } + return err; } @@ -1890,6 +1916,7 @@ int dvb_ca_en50221_init(struct dvb_adapter *dvb_adapter, } mutex_init(&ca->ioctl_mutex); + mutex_init(&ca->remove_mutex); if (signal_pending(current)) { ret = -EINTR; @@ -1932,6 +1959,14 @@ void dvb_ca_en50221_release(struct dvb_ca_en50221 *pubca) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + ca->exit = 1; + mutex_unlock(&ca->remove_mutex); + + if (ca->dvbdev->users < 1) + wait_event(ca->dvbdev->wait_queue, + ca->dvbdev->users == 1); + /* shutdown the thread if there was one */ kthread_stop(ca->thread); From 046721280664d1b6c39bef2e3012553a975ac979 Mon Sep 17 00:00:00 2001 From: Holger Dengler Date: Thu, 20 Apr 2023 14:34:10 +0200 Subject: [PATCH 3365/4345] s390/pkey: zeroize key blobs [ Upstream commit 844cf829e5f33e00b279230470c8c93b58b8c16f ] Key blobs for the IOCTLs PKEY_KBLOB2PROTK[23] may contain clear key material. Zeroize the copies of these keys in kernel memory after creating the protected key. Reviewed-by: Harald Freudenberger Signed-off-by: Holger Dengler Signed-off-by: Alexander Gordeev Signed-off-by: Sasha Levin --- drivers/s390/crypto/pkey_api.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index dd84995049b9..870e00effe43 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -1271,6 +1271,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return PTR_ERR(kkey); rc = pkey_keyblob2pkey(kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey()=%d\n", __func__, rc); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1404,6 +1405,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1530,6 +1532,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, protkey, &protkeylen); DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) { kfree(protkey); From 01c76cb5e512075bcd821fd00aea00fb22c09910 Mon Sep 17 00:00:00 2001 From: Yun Lu Date: Fri, 12 May 2023 09:20:55 +0800 Subject: [PATCH 3366/4345] wifi: rtl8xxxu: fix authentication timeout due to incorrect RCR value [ Upstream commit 20429444e653ee8242dfbf815c0c37866beb371b ] When using rtl8192cu with rtl8xxxu driver to connect wifi, there is a probability of failure, which shows "authentication with ... timed out". Through debugging, it was found that the RCR register has been inexplicably modified to an incorrect value, resulting in the nic not being able to receive authenticated frames. To fix this problem, add regrcr in rtl8xxxu_priv struct, and store the RCR value every time the register is written, and use it the next time the register need to be modified. Signed-off-by: Yun Lu Link: https://lore.kernel.org/all/20230427020512.1221062-1-luyun_611@163.com Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230512012055.2990472-1-luyun_611@163.com Signed-off-by: Sasha Levin --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h | 1 + drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h index 0ed4d67308d7..fe1e4c4c17c4 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h @@ -1346,6 +1346,7 @@ struct rtl8xxxu_priv { u32 rege9c; u32 regeb4; u32 regebc; + u32 regrcr; int next_mbox; int nr_out_eps; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index deef1c09de31..004778faf3d0 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -4045,6 +4045,7 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw) RCR_ACCEPT_MGMT_FRAME | RCR_HTC_LOC_CTRL | RCR_APPEND_PHYSTAT | RCR_APPEND_ICV | RCR_APPEND_MIC; rtl8xxxu_write32(priv, REG_RCR, val32); + priv->regrcr = val32; /* * Accept all multicast @@ -5999,7 +6000,7 @@ static void rtl8xxxu_configure_filter(struct ieee80211_hw *hw, unsigned int *total_flags, u64 multicast) { struct rtl8xxxu_priv *priv = hw->priv; - u32 rcr = rtl8xxxu_read32(priv, REG_RCR); + u32 rcr = priv->regrcr; dev_dbg(&priv->udev->dev, "%s: changed_flags %08x, total_flags %08x\n", __func__, changed_flags, *total_flags); @@ -6045,6 +6046,7 @@ static void rtl8xxxu_configure_filter(struct ieee80211_hw *hw, */ rtl8xxxu_write32(priv, REG_RCR, rcr); + priv->regrcr = rcr; *total_flags &= (FIF_ALLMULTI | FIF_FCSFAIL | FIF_BCN_PRBRESP_PROMISC | FIF_CONTROL | FIF_OTHER_BSS | FIF_PSPOLL | From 32f86763c2a2457cbd37c10f287e2945c786cb4d Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:38 +0200 Subject: [PATCH 3367/4345] ARM: dts: stm32: add pin map for CAN controller on stm32f7 [ Upstream commit 011644249686f2675e142519cd59e81e04cfc231 ] Add pin configurations for using CAN controller on stm32f7. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/all/20230427204540.3126234-4-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32f7-pinctrl.dtsi | 82 ++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) diff --git a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi index fe4cfda72a47..4e1b8b3359e2 100644 --- a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi +++ b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi @@ -284,6 +284,88 @@ slew-rate = <2>; }; }; + + can1_pins_a: can1-0 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_b: can1-1 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_c: can1-2 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can1_pins_d: can1-3 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can2_pins_a: can2-0 { + pins1 { + pinmux = ; /* CAN2_TX */ + }; + pins2 { + pinmux = ; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can2_pins_b: can2-1 { + pins1 { + pinmux = ; /* CAN2_TX */ + }; + pins2 { + pinmux = ; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can3_pins_a: can3-0 { + pins1 { + pinmux = ; /* CAN3_TX */ + }; + pins2 { + pinmux = ; /* CAN3_RX */ + bias-pull-up; + }; + }; + + can3_pins_b: can3-1 { + pins1 { + pinmux = ; /* CAN3_TX */ + }; + pins2 { + pinmux = ; /* CAN3_RX */ + bias-pull-up; + }; + }; }; }; }; From 05226a8f2288e7305f75f1894889c42eca5594da Mon Sep 17 00:00:00 2001 From: Min-Hua Chen Date: Tue, 2 May 2023 23:19:06 +0800 Subject: [PATCH 3368/4345] arm64/mm: mark private VM_FAULT_X defines as vm_fault_t [ Upstream commit d91d580878064b880f3574ac35b98d8b70ee8620 ] This patch fixes several sparse warnings for fault.c: arch/arm64/mm/fault.c:493:24: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:493:24: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:493:24: sparse: got int arch/arm64/mm/fault.c:501:32: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:501:32: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:501:32: sparse: got int arch/arm64/mm/fault.c:503:32: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:503:32: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:503:32: sparse: got int arch/arm64/mm/fault.c:511:24: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:511:24: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:511:24: sparse: got int arch/arm64/mm/fault.c:670:13: sparse: warning: restricted vm_fault_t degrades to integer arch/arm64/mm/fault.c:670:13: sparse: warning: restricted vm_fault_t degrades to integer arch/arm64/mm/fault.c:713:39: sparse: warning: restricted vm_fault_t degrades to integer Reported-by: kernel test robot Signed-off-by: Min-Hua Chen Link: https://lore.kernel.org/r/20230502151909.128810-1-minhuadotchen@gmail.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/mm/fault.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 2be856731e81..d8baedd160de 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -402,8 +402,8 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re } } -#define VM_FAULT_BADMAP 0x010000 -#define VM_FAULT_BADACCESS 0x020000 +#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) +#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags, From ea478186ea29ce5a0dd6bb132a2d34c2a514b82a Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Mon, 15 May 2023 15:01:56 +0800 Subject: [PATCH 3369/4345] scsi: core: Decrease scsi_device's iorequest_cnt if dispatch failed [ Upstream commit 09e797c8641f6ad435c33ae24c223351197ea29a ] If scsi_dispatch_cmd() failed, the SCSI command was not sent to the target, scsi_queue_rq() would return BLK_STS_RESOURCE and the related request would be requeued. The timeout of this request would not fire, no one would increase iodone_cnt. The above flow would result the iodone_cnt smaller than iorequest_cnt. So decrease the iorequest_cnt if dispatch failed to workaround the issue. Signed-off-by: Wenchao Hao Reported-by: Ming Lei Closes: https://lore.kernel.org/r/ZF+zB+bB7iqe0wGd@ovpn-8-17.pek2.redhat.com Link: https://lore.kernel.org/r/20230515070156.1790181-3-haowenchao2@huawei.com Reviewed-by: Ming Lei Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_lib.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 6f3d29d16d1f..99b90031500b 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1490,6 +1490,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) */ SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd, "queuecommand : device blocked\n")); + atomic_dec(&cmd->device->iorequest_cnt); return SCSI_MLQUEUE_DEVICE_BUSY; } @@ -1522,6 +1523,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) trace_scsi_dispatch_cmd_start(cmd); rtn = host->hostt->queuecommand(host, cmd); if (rtn) { + atomic_dec(&cmd->device->iorequest_cnt); trace_scsi_dispatch_cmd_error(cmd, rtn); if (rtn != SCSI_MLQUEUE_DEVICE_BUSY && rtn != SCSI_MLQUEUE_TARGET_BUSY) From 1c2537291e9c9bf23b394f1a06008d75da19b5ec Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 20:34:22 +0200 Subject: [PATCH 3370/4345] wifi: b43: fix incorrect __packed annotation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 212457ccbd60dba34f965e4ffbe62f0e4f970538 ] clang warns about an unpacked structure inside of a packed one: drivers/net/wireless/broadcom/b43/b43.h:654:4: error: field data within 'struct b43_iv' is less aligned than 'union (unnamed union at /home/arnd/arm-soc/drivers/net/wireless/broadcom/b43/b43.h:651:2)' and is usually due to 'struct b43_iv' being packed, which can lead to unaligned accesses [-Werror,-Wunaligned-access] The problem here is that the anonymous union has the default alignment from its members, apparently because the original author mixed up the placement of the __packed attribute by placing it next to the struct member rather than the union definition. As the struct itself is also marked as __packed, there is no need to mark its members, so just move the annotation to the inner type instead. As Michael noted, the same problem is present in b43legacy, so change both at the same time. Acked-by: Michael Büsch Reported-by: kernel test robot Reviewed-by: Simon Horman Tested-by: Larry Finger Link: https://lore.kernel.org/oe-kbuild-all/202305160749.ay1HAoyP-lkp@intel.com/ Signed-off-by: Arnd Bergmann Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230516183442.536589-1-arnd@kernel.org Signed-off-by: Sasha Levin --- drivers/net/wireless/broadcom/b43/b43.h | 2 +- drivers/net/wireless/broadcom/b43legacy/b43legacy.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/broadcom/b43/b43.h b/drivers/net/wireless/broadcom/b43/b43.h index 9fc7c088a539..67b4bac048e5 100644 --- a/drivers/net/wireless/broadcom/b43/b43.h +++ b/drivers/net/wireless/broadcom/b43/b43.h @@ -651,7 +651,7 @@ struct b43_iv { union { __be16 d16; __be32 d32; - } data __packed; + } __packed data; } __packed; diff --git a/drivers/net/wireless/broadcom/b43legacy/b43legacy.h b/drivers/net/wireless/broadcom/b43legacy/b43legacy.h index 6b0cec467938..f49365d14619 100644 --- a/drivers/net/wireless/broadcom/b43legacy/b43legacy.h +++ b/drivers/net/wireless/broadcom/b43legacy/b43legacy.h @@ -379,7 +379,7 @@ struct b43legacy_iv { union { __be16 d16; __be32 d32; - } data __packed; + } __packed data; } __packed; #define B43legacy_PHYMODE(phytype) (1 << (phytype)) From 4987bf04465eb837fcbe48833fd3daddf375267d Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 14 May 2023 10:00:10 -0400 Subject: [PATCH 3371/4345] netfilter: conntrack: define variables exp_nat_nla_policy and any_addr with CONFIG_NF_NAT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 224a876e37543eee111bf9b6aa4935080e619335 ] gcc with W=1 and ! CONFIG_NF_NAT net/netfilter/nf_conntrack_netlink.c:3463:32: error: ‘exp_nat_nla_policy’ defined but not used [-Werror=unused-const-variable=] 3463 | static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { | ^~~~~~~~~~~~~~~~~~ net/netfilter/nf_conntrack_netlink.c:2979:33: error: ‘any_addr’ defined but not used [-Werror=unused-const-variable=] 2979 | static const union nf_inet_addr any_addr; | ^~~~~~~~ These variables use is controlled by CONFIG_NF_NAT, so should their definitions. Signed-off-by: Tom Rix Reviewed-by: Simon Horman Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_netlink.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 6a055a221683..ceb7c988edef 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2968,7 +2968,9 @@ nla_put_failure: return -1; } +#if IS_ENABLED(CONFIG_NF_NAT) static const union nf_inet_addr any_addr; +#endif static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { @@ -3458,10 +3460,12 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x, return 0; } +#if IS_ENABLED(CONFIG_NF_NAT) static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; +#endif static int ctnetlink_parse_expect_nat(const struct nlattr *attr, From 93a61212db4b687df4e8d31442011a990b16763f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:50:42 +0200 Subject: [PATCH 3372/4345] ALSA: oss: avoid missing-prototype warnings [ Upstream commit 040b5a046a9e18098580d3ccd029e2318fca7859 ] Two functions are defined and used in pcm_oss.c but also optionally used from io.c, with an optional prototype. If CONFIG_SND_PCM_OSS_PLUGINS is disabled, this causes a warning as the functions are not static and have no prototype: sound/core/oss/pcm_oss.c:1235:19: error: no previous prototype for 'snd_pcm_oss_write3' [-Werror=missing-prototypes] sound/core/oss/pcm_oss.c:1266:19: error: no previous prototype for 'snd_pcm_oss_read3' [-Werror=missing-prototypes] Avoid this by making the prototypes unconditional. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516195046.550584-2-arnd@kernel.org Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/core/oss/pcm_plugin.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/sound/core/oss/pcm_plugin.h b/sound/core/oss/pcm_plugin.h index 46e273bd4a78..50a6b50f5db4 100644 --- a/sound/core/oss/pcm_plugin.h +++ b/sound/core/oss/pcm_plugin.h @@ -141,6 +141,14 @@ int snd_pcm_area_copy(const struct snd_pcm_channel_area *src_channel, void *snd_pcm_plug_buf_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t size); void snd_pcm_plug_buf_unlock(struct snd_pcm_substream *plug, void *ptr); +#else + +static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } +static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } +static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } + +#endif + snd_pcm_sframes_t snd_pcm_oss_write3(struct snd_pcm_substream *substream, const char *ptr, snd_pcm_uframes_t size, int in_kernel); @@ -151,14 +159,6 @@ snd_pcm_sframes_t snd_pcm_oss_writev3(struct snd_pcm_substream *substream, snd_pcm_sframes_t snd_pcm_oss_readv3(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames); -#else - -static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } -static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } -static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } - -#endif - #ifdef PLUGIN_DEBUG #define pdprintf(fmt, args...) printk(KERN_DEBUG "plugin: " fmt, ##args) #else From ab332304583d6560af0bd70e8c08fdcd1013f448 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 16 May 2023 15:20:37 -0700 Subject: [PATCH 3373/4345] drm/msm: Be more shouty if per-process pgtables aren't working [ Upstream commit 5c054db54c43a5fcb5cc81012361f5e3fac37637 ] Otherwise it is not always obvious if a dt or iommu change is causing us to fall back to global pgtable. Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/537359/ Link: https://lore.kernel.org/r/20230516222039.907690-2-robdclark@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/msm_iommu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index ecab6287c1c3..b81390d6ebd3 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -155,7 +155,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Get the pagetable configuration from the domain */ if (adreno_smmu->cookie) ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); - if (!ttbr1_cfg) + + /* + * If you hit this WARN_ONCE() you are probably missing an entry in + * qcom_smmu_impl_of_match[] in arm-smmu-qcom.c + */ + if (WARN_ONCE(!ttbr1_cfg, "No per-process page tables")) return ERR_PTR(-ENODEV); pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL); From c05ac53bb0df5f1aafa718bc239bebdeef07586b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:34 +0200 Subject: [PATCH 3374/4345] atm: hide unused procfs functions [ Upstream commit fb1b7be9b16c1f4626969ba4e95a97da2a452b41 ] When CONFIG_PROC_FS is disabled, the function declarations for some procfs functions are hidden, but the definitions are still build, as shown by this compiler warning: net/atm/resources.c:403:7: error: no previous prototype for 'atm_dev_seq_start' [-Werror=missing-prototypes] net/atm/resources.c:409:6: error: no previous prototype for 'atm_dev_seq_stop' [-Werror=missing-prototypes] net/atm/resources.c:414:7: error: no previous prototype for 'atm_dev_seq_next' [-Werror=missing-prototypes] Add another #ifdef to leave these out of the build. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516194625.549249-2-arnd@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/atm/resources.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/atm/resources.c b/net/atm/resources.c index 53236986dfe0..3ad39ae97132 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -403,6 +403,7 @@ done: return error; } +#ifdef CONFIG_PROC_FS void *atm_dev_seq_start(struct seq_file *seq, loff_t *pos) { mutex_lock(&atm_dev_mutex); @@ -418,3 +419,4 @@ void *atm_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &atm_devs, pos); } +#endif From 5a445c2bf651ed0b762ae781c737a93151f33d7a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 5 May 2023 12:22:09 +0300 Subject: [PATCH 3375/4345] mailbox: mailbox-test: fix a locking issue in mbox_test_message_write() [ Upstream commit 8fe72b76db79d694858e872370df49676bc3be8c ] There was a bug where this code forgot to unlock the tdev->mutex if the kzalloc() failed. Fix this issue, by moving the allocation outside the lock. Fixes: 2d1e952a2b8e ("mailbox: mailbox-test: Fix potential double-free in mbox_test_message_write()") Signed-off-by: Dan Carpenter Reviewed-by: Lee Jones Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/mailbox-test.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 6dd5b9614452..abcee58e851c 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -97,6 +97,7 @@ static ssize_t mbox_test_message_write(struct file *filp, size_t count, loff_t *ppos) { struct mbox_test_device *tdev = filp->private_data; + char *message; void *data; int ret; @@ -112,12 +113,13 @@ static ssize_t mbox_test_message_write(struct file *filp, return -EINVAL; } - mutex_lock(&tdev->mutex); - - tdev->message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); - if (!tdev->message) + message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); + if (!message) return -ENOMEM; + mutex_lock(&tdev->mutex); + + tdev->message = message; ret = copy_from_user(tdev->message, userbuf, count); if (ret) { ret = -EFAULT; From 55c507a34e7ef83f07213f19da8361cce4786b7f Mon Sep 17 00:00:00 2001 From: Jiakai Luo Date: Sat, 22 Apr 2023 06:34:06 -0700 Subject: [PATCH 3376/4345] iio: adc: mxs-lradc: fix the order of two cleanup operations commit 27b2ed5b6d53cd62fc61c3f259ae52f5cac23b66 upstream. Smatch reports: drivers/iio/adc/mxs-lradc-adc.c:766 mxs_lradc_adc_probe() warn: missing unwind goto? the order of three init operation: 1.mxs_lradc_adc_trigger_init 2.iio_triggered_buffer_setup 3.mxs_lradc_adc_hw_init thus, the order of three cleanup operation should be: 1.mxs_lradc_adc_hw_stop 2.iio_triggered_buffer_cleanup 3.mxs_lradc_adc_trigger_remove we exchange the order of two cleanup operations, introducing the following differences: 1.if mxs_lradc_adc_trigger_init fails, returns directly; 2.if trigger_init succeeds but iio_triggered_buffer_setup fails, goto err_trig and remove the trigger. In addition, we also reorder the unwind that goes on in the remove() callback to match the new ordering. Fixes: 6dd112b9f85e ("iio: adc: mxs-lradc: Add support for ADC driver") Signed-off-by: Jiakai Luo Reviewed-by: Dongliang Mu Link: https://lore.kernel.org/r/20230422133407.72908-1-jkluo@hust.edu.cn Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/mxs-lradc-adc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/iio/adc/mxs-lradc-adc.c b/drivers/iio/adc/mxs-lradc-adc.c index c480cb489c1a..c37e39b96f0e 100644 --- a/drivers/iio/adc/mxs-lradc-adc.c +++ b/drivers/iio/adc/mxs-lradc-adc.c @@ -757,13 +757,13 @@ static int mxs_lradc_adc_probe(struct platform_device *pdev) ret = mxs_lradc_adc_trigger_init(iio); if (ret) - goto err_trig; + return ret; ret = iio_triggered_buffer_setup(iio, &iio_pollfunc_store_time, &mxs_lradc_adc_trigger_handler, &mxs_lradc_adc_buffer_ops); if (ret) - return ret; + goto err_trig; adc->vref_mv = mxs_lradc_adc_vref_mv[lradc->soc]; @@ -801,9 +801,9 @@ static int mxs_lradc_adc_probe(struct platform_device *pdev) err_dev: mxs_lradc_adc_hw_stop(adc); - mxs_lradc_adc_trigger_remove(iio); -err_trig: iio_triggered_buffer_cleanup(iio); +err_trig: + mxs_lradc_adc_trigger_remove(iio); return ret; } @@ -814,8 +814,8 @@ static int mxs_lradc_adc_remove(struct platform_device *pdev) iio_device_unregister(iio); mxs_lradc_adc_hw_stop(adc); - mxs_lradc_adc_trigger_remove(iio); iio_triggered_buffer_cleanup(iio); + mxs_lradc_adc_trigger_remove(iio); return 0; } From adac1c22f54bef359eedb4f14461dfa07533e8af Mon Sep 17 00:00:00 2001 From: Sung-Chi Li Date: Mon, 24 Apr 2023 10:37:36 +0800 Subject: [PATCH 3377/4345] HID: google: add jewel USB id commit ed84c4517a5bc536e8572a01dfa11bc22a280d06 upstream. Add 1 additional hammer-like device. Signed-off-by: Sung-Chi Li Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-google-hammer.c | 2 ++ drivers/hid/hid-ids.h | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 047630198396..2f4c5b45d409 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -532,6 +532,8 @@ static const struct hid_device_id hammer_devices[] = { USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_EEL) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_JEWEL) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 1d1306a6004e..2b658d820b80 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -491,6 +491,7 @@ #define USB_DEVICE_ID_GOOGLE_MOONBALL 0x5044 #define USB_DEVICE_ID_GOOGLE_DON 0x5050 #define USB_DEVICE_ID_GOOGLE_EEL 0x5057 +#define USB_DEVICE_ID_GOOGLE_JEWEL 0x5061 #define USB_VENDOR_ID_GOTOP 0x08f2 #define USB_DEVICE_ID_SUPER_Q2 0x007f From 954bd5a44b091340cc0c1d6cba4a110e83ab9294 Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Mon, 17 Apr 2023 09:01:48 -0700 Subject: [PATCH 3378/4345] HID: wacom: avoid integer overflow in wacom_intuos_inout() commit bd249b91977b768ea02bf84d04625d2690ad2b98 upstream. If high bit is set to 1 in ((data[3] & 0x0f << 28), after all arithmetic operations and integer promotions are done, high bits in wacom->serial[idx] will be filled with 1s as well. Avoid this, albeit unlikely, issue by specifying left operand's __u64 type for the right operand. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: 3bea733ab212 ("USB: wacom tablet driver reorganization") Signed-off-by: Nikita Zhandarovich Reviewed-by: Ping Cheng Cc: stable@vger.kernel.org Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom_wac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 37754a1f733b..1bfcc94c1d23 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -831,7 +831,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) /* Enter report */ if ((data[1] & 0xfc) == 0xc0) { /* serial number of the tool */ - wacom->serial[idx] = ((data[3] & 0x0f) << 28) + + wacom->serial[idx] = ((__u64)(data[3] & 0x0f) << 28) + (data[4] << 20) + (data[5] << 12) + (data[6] << 4) + (data[7] >> 4); From ff864a92d90340742d4f26d63b36bccf72d7238e Mon Sep 17 00:00:00 2001 From: Jean-Baptiste Maneyrol Date: Tue, 9 May 2023 15:22:02 +0000 Subject: [PATCH 3379/4345] iio: imu: inv_icm42600: fix timestamp reset commit bbaae0c79ebd49f61ad942a8bf9e12bfc7f821bb upstream. Timestamp reset is not done in the correct place. It must be done before enabling buffer. The reason is that interrupt timestamping is always happening when the chip is on, even if the corresponding sensor is off. When the sensor restarts, timestamp is wrong if you don't do a reset first. Fixes: ec74ae9fd37c ("iio: imu: inv_icm42600: add accurate timestamping") Signed-off-by: Jean-Baptiste Maneyrol Cc: Link: https://lore.kernel.org/r/20230509152202.245444-1-inv.git-commit@tdk.com Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c index 99576b2c171f..32d7f8364230 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c @@ -275,9 +275,14 @@ static int inv_icm42600_buffer_preenable(struct iio_dev *indio_dev) { struct inv_icm42600_state *st = iio_device_get_drvdata(indio_dev); struct device *dev = regmap_get_device(st->map); + struct inv_icm42600_timestamp *ts = iio_priv(indio_dev); pm_runtime_get_sync(dev); + mutex_lock(&st->lock); + inv_icm42600_timestamp_reset(ts); + mutex_unlock(&st->lock); + return 0; } @@ -375,7 +380,6 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) struct device *dev = regmap_get_device(st->map); unsigned int sensor; unsigned int *watermark; - struct inv_icm42600_timestamp *ts; struct inv_icm42600_sensor_conf conf = INV_ICM42600_SENSOR_CONF_INIT; unsigned int sleep_temp = 0; unsigned int sleep_sensor = 0; @@ -385,11 +389,9 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) if (indio_dev == st->indio_gyro) { sensor = INV_ICM42600_SENSOR_GYRO; watermark = &st->fifo.watermark.gyro; - ts = iio_priv(st->indio_gyro); } else if (indio_dev == st->indio_accel) { sensor = INV_ICM42600_SENSOR_ACCEL; watermark = &st->fifo.watermark.accel; - ts = iio_priv(st->indio_accel); } else { return -EINVAL; } @@ -417,8 +419,6 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) if (!st->fifo.on) ret = inv_icm42600_set_temp_conf(st, false, &sleep_temp); - inv_icm42600_timestamp_reset(ts); - out_unlock: mutex_unlock(&st->lock); From 81c70f4beaadcedee730566f526ac092b96e82e5 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Mon, 1 May 2023 10:36:04 -0400 Subject: [PATCH 3380/4345] iio: light: vcnl4035: fixed chip ID check commit a551c26e8e568fad42120843521529241b9bceec upstream. VCNL4035 register(0xE) ID_L and ID_M define as: ID_L: 0x80 ID_H: 7:6 (0:0) 5:4 (0:0) slave address = 0x60 (7-bit) (0:1) slave address = 0x51 (7-bit) (1:0) slave address = 0x40 (7-bit) (1:0) slave address = 0x41 (7-bit) 3:0 Version code default (0:0:0:0) So just check ID_L. Fixes: 55707294c4eb ("iio: light: Add support for vishay vcnl4035") Signed-off-by: Frank Li Link: https://lore.kernel.org/r/20230501143605.1615549-1-Frank.Li@nxp.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/light/vcnl4035.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iio/light/vcnl4035.c b/drivers/iio/light/vcnl4035.c index 1bd85e21fd11..6e38a33f55c7 100644 --- a/drivers/iio/light/vcnl4035.c +++ b/drivers/iio/light/vcnl4035.c @@ -8,6 +8,7 @@ * TODO: Proximity */ #include +#include #include #include #include @@ -42,6 +43,7 @@ #define VCNL4035_ALS_PERS_MASK GENMASK(3, 2) #define VCNL4035_INT_ALS_IF_H_MASK BIT(12) #define VCNL4035_INT_ALS_IF_L_MASK BIT(13) +#define VCNL4035_DEV_ID_MASK GENMASK(7, 0) /* Default values */ #define VCNL4035_MODE_ALS_ENABLE BIT(0) @@ -415,6 +417,7 @@ static int vcnl4035_init(struct vcnl4035_data *data) return ret; } + id = FIELD_GET(VCNL4035_DEV_ID_MASK, id); if (id != VCNL4035_DEV_ID_VAL) { dev_err(&data->client->dev, "Wrong id, got %x, expected %x\n", id, VCNL4035_DEV_ID_VAL); From 143dbb313aea42e5e966e027386422b445bbd369 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 11 May 2023 02:43:30 +0200 Subject: [PATCH 3381/4345] iio: dac: mcp4725: Fix i2c_master_send() return value handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 09d3bec7009186bdba77039df01e5834788b3f95 upstream. The i2c_master_send() returns number of sent bytes on success, or negative on error. The suspend/resume callbacks expect zero on success and non-zero on error. Adapt the return value of the i2c_master_send() to the expectation of the suspend and resume callbacks, including proper validation of the return value. Fixes: cf35ad61aca2 ("iio: add mcp4725 I2C DAC driver") Signed-off-by: Marek Vasut Reviewed-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230511004330.206942-1-marex@denx.de Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/dac/mcp4725.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index beb9a15b7c74..0c0e726ae054 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -47,12 +47,18 @@ static int __maybe_unused mcp4725_suspend(struct device *dev) struct mcp4725_data *data = iio_priv(i2c_get_clientdata( to_i2c_client(dev))); u8 outbuf[2]; + int ret; outbuf[0] = (data->powerdown_mode + 1) << 4; outbuf[1] = 0; data->powerdown = true; - return i2c_master_send(data->client, outbuf, 2); + ret = i2c_master_send(data->client, outbuf, 2); + if (ret < 0) + return ret; + else if (ret != 2) + return -EIO; + return 0; } static int __maybe_unused mcp4725_resume(struct device *dev) @@ -60,13 +66,19 @@ static int __maybe_unused mcp4725_resume(struct device *dev) struct mcp4725_data *data = iio_priv(i2c_get_clientdata( to_i2c_client(dev))); u8 outbuf[2]; + int ret; /* restore previous DAC value */ outbuf[0] = (data->dac_value >> 8) & 0xf; outbuf[1] = data->dac_value & 0xff; data->powerdown = false; - return i2c_master_send(data->client, outbuf, 2); + ret = i2c_master_send(data->client, outbuf, 2); + if (ret < 0) + return ret; + else if (ret != 2) + return -EIO; + return 0; } static SIMPLE_DEV_PM_OPS(mcp4725_pm_ops, mcp4725_suspend, mcp4725_resume); From a869ab6987f4d9d940fbcfe299d682debb4720dd Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Thu, 30 Mar 2023 12:21:00 +0200 Subject: [PATCH 3382/4345] iio: adc: ad7192: Change "shorted" channels to differential commit e55245d115bb9054cb72cdd5dda5660f4484873a upstream. The AD7192 provides a specific channel configuration where both negative and positive inputs are connected to AIN2. This was represented in the ad7192 driver as a IIO channel with .channel = 2 and .extended_name set to "shorted". The problem with this approach, is that the driver provided two IIO channels with the identifier .channel = 2; one "shorted" and the other not. This goes against the IIO ABI, as a channel identifier should be unique. Address this issue by changing "shorted" channels to being differential instead, with channel 2 vs. itself, as we're actually measuring AIN2 vs. itself. Note that the fix tag is for the commit that moved the driver out of staging. The bug existed before that, but backporting would become very complex further down and unlikely to happen. Fixes: b581f748cce0 ("staging: iio: adc: ad7192: move out of staging") Signed-off-by: Paul Cercueil Co-developed-by: Alisa Roman Signed-off-by: Alisa Roman Reviewed-by: Nuno Sa Link: https://lore.kernel.org/r/20230330102100.17590-1-paul@crapouillou.net Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/ad7192.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 1b8baba9d4d6..614c5e807bb8 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -835,10 +835,6 @@ static const struct iio_info ad7195_info = { __AD719x_CHANNEL(_si, _channel1, -1, _address, NULL, IIO_VOLTAGE, \ BIT(IIO_CHAN_INFO_SCALE), ad7192_calibsys_ext_info) -#define AD719x_SHORTED_CHANNEL(_si, _channel1, _address) \ - __AD719x_CHANNEL(_si, _channel1, -1, _address, "shorted", IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SCALE), ad7192_calibsys_ext_info) - #define AD719x_TEMP_CHANNEL(_si, _address) \ __AD719x_CHANNEL(_si, 0, -1, _address, NULL, IIO_TEMP, 0, NULL) @@ -846,7 +842,7 @@ static const struct iio_chan_spec ad7192_channels[] = { AD719x_DIFF_CHANNEL(0, 1, 2, AD7192_CH_AIN1P_AIN2M), AD719x_DIFF_CHANNEL(1, 3, 4, AD7192_CH_AIN3P_AIN4M), AD719x_TEMP_CHANNEL(2, AD7192_CH_TEMP), - AD719x_SHORTED_CHANNEL(3, 2, AD7192_CH_AIN2P_AIN2M), + AD719x_DIFF_CHANNEL(3, 2, 2, AD7192_CH_AIN2P_AIN2M), AD719x_CHANNEL(4, 1, AD7192_CH_AIN1), AD719x_CHANNEL(5, 2, AD7192_CH_AIN2), AD719x_CHANNEL(6, 3, AD7192_CH_AIN3), @@ -860,7 +856,7 @@ static const struct iio_chan_spec ad7193_channels[] = { AD719x_DIFF_CHANNEL(2, 5, 6, AD7193_CH_AIN5P_AIN6M), AD719x_DIFF_CHANNEL(3, 7, 8, AD7193_CH_AIN7P_AIN8M), AD719x_TEMP_CHANNEL(4, AD7193_CH_TEMP), - AD719x_SHORTED_CHANNEL(5, 2, AD7193_CH_AIN2P_AIN2M), + AD719x_DIFF_CHANNEL(5, 2, 2, AD7193_CH_AIN2P_AIN2M), AD719x_CHANNEL(6, 1, AD7193_CH_AIN1), AD719x_CHANNEL(7, 2, AD7193_CH_AIN2), AD719x_CHANNEL(8, 3, AD7193_CH_AIN3), From e18b0009ddfba0b80a60dbee0ed99552876132fe Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 8 May 2023 06:02:08 +0200 Subject: [PATCH 3383/4345] iio: dac: build ad5758 driver when AD5758 is selected commit a146eccb68be161ae9eab5f3f68bb0ed7c0fbaa8 upstream. Commit 28d1a7ac2a0d ("iio: dac: Add AD5758 support") adds the config AD5758 and the corresponding driver ad5758.c. In the Makefile, the ad5758 driver is however included when AD5755 is selected, not when AD5758 is selected. Probably, this was simply a mistake that happened by copy-and-paste and forgetting to adjust the actual line. Surprisingly, no one has ever noticed that this driver is actually only included when AD5755 is selected and that the config AD5758 has actually no effect on the build. Fixes: 28d1a7ac2a0d ("iio: dac: Add AD5758 support") Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20230508040208.12033-1-lukas.bulwahn@gmail.com Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/dac/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile index 2fc481167724..09506d248c9e 100644 --- a/drivers/iio/dac/Makefile +++ b/drivers/iio/dac/Makefile @@ -16,7 +16,7 @@ obj-$(CONFIG_AD5592R_BASE) += ad5592r-base.o obj-$(CONFIG_AD5592R) += ad5592r.o obj-$(CONFIG_AD5593R) += ad5593r.o obj-$(CONFIG_AD5755) += ad5755.o -obj-$(CONFIG_AD5755) += ad5758.o +obj-$(CONFIG_AD5758) += ad5758.o obj-$(CONFIG_AD5761) += ad5761.o obj-$(CONFIG_AD5764) += ad5764.o obj-$(CONFIG_AD5770R) += ad5770r.o From 90f581eb745c46f709157493438abe913b7d71a2 Mon Sep 17 00:00:00 2001 From: Sebastian Krzyszkowiak Date: Fri, 26 May 2023 16:38:11 +0200 Subject: [PATCH 3384/4345] net: usb: qmi_wwan: Set DTR quirk for BroadMobi BM818 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 36936a56e1814f6c526fe71fbf980beab4f5577a upstream. BM818 is based on Qualcomm MDM9607 chipset. Fixes: 9a07406b00cd ("net: usb: qmi_wwan: Add the BroadMobi BM818 card") Cc: stable@vger.kernel.org Signed-off-by: Sebastian Krzyszkowiak Acked-by: Bjørn Mork Link: https://lore.kernel.org/r/20230526-bm818-dtr-v1-1-64bbfa6ba8af@puri.sm Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/qmi_wwan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 070910567c44..53f1cd0bfaf4 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1260,7 +1260,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2001, 0x7e3d, 4)}, /* D-Link DWM-222 A2 */ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ - {QMI_FIXED_INTF(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ + {QMI_QUIRK_SET_DTR(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ From a4f88cb043c5964b1ababfdc5397bb9d7b972509 Mon Sep 17 00:00:00 2001 From: Uttkarsh Aggarwal Date: Thu, 25 May 2023 14:58:54 +0530 Subject: [PATCH 3385/4345] usb: gadget: f_fs: Add unbind event before functionfs_unbind commit efb6b535207395a5c7317993602e2503ca8cb4b3 upstream. While exercising the unbind path, with the current implementation the functionfs_unbind would be calling which waits for the ffs->mutex to be available, however within the same time ffs_ep0_read is invoked & if no setup packets are pending, it will invoke function wait_event_interruptible_exclusive_locked_irq which by definition waits for the ev.count to be increased inside the same mutex for which functionfs_unbind is waiting. This creates deadlock situation because the functionfs_unbind won't get the lock until ev.count is increased which can only happen if the caller ffs_func_unbind can proceed further. Following is the illustration: CPU1 CPU2 ffs_func_unbind() ffs_ep0_read() mutex_lock(ffs->mutex) wait_event(ffs->ev.count) functionfs_unbind() mutex_lock(ffs->mutex) mutex_unlock(ffs->mutex) ffs_event_add() Fix this by moving the event unbind before functionfs_unbind to ensure the ev.count is incrased properly. Fixes: 6a19da111057 ("usb: gadget: f_fs: Prevent race during ffs_ep0_queue_wait") Cc: stable Signed-off-by: Uttkarsh Aggarwal Link: https://lore.kernel.org/r/20230525092854.7992-1-quic_uaggarwa@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 8c48c9f801be..b17acab77fe2 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3609,6 +3609,7 @@ static void ffs_func_unbind(struct usb_configuration *c, /* Drain any pending AIO completions */ drain_workqueue(ffs->io_completion_wq); + ffs_event_add(ffs, FUNCTIONFS_UNBIND); if (!--opts->refcnt) functionfs_unbind(ffs); @@ -3633,7 +3634,6 @@ static void ffs_func_unbind(struct usb_configuration *c, func->function.ssp_descriptors = NULL; func->interfaces_nums = NULL; - ffs_event_add(ffs, FUNCTIONFS_UNBIND); } static struct usb_function *ffs_alloc(struct usb_function_instance *fi) From dacb7c103c2f4fdc3b85074c389914d11784342b Mon Sep 17 00:00:00 2001 From: Richard Acayan Date: Tue, 23 May 2023 16:25:49 +0100 Subject: [PATCH 3386/4345] misc: fastrpc: return -EPIPE to invocations on device removal commit b6a062853ddf6b4f653af2d8b75ba45bb9a036ad upstream. The return value is initialized as -1, or -EPERM. The completion of an invocation implies that the return value is set appropriately, but "Permission denied" does not accurately describe the outcome of the invocation. Set the invocation's return value to a more appropriate "Broken pipe", as the cleanup breaks the driver's connection with rpmsg. Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Cc: stable Signed-off-by: Richard Acayan Reviewed-by: Srinivas Kandagatla Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230523152550.438363-4-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 67a51f69cf9a..643afb31c952 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1675,8 +1675,10 @@ static void fastrpc_notify_users(struct fastrpc_user *user) struct fastrpc_invoke_ctx *ctx; spin_lock(&user->lock); - list_for_each_entry(ctx, &user->pending, node) + list_for_each_entry(ctx, &user->pending, node) { + ctx->retval = -EPIPE; complete(&ctx->work); + } spin_unlock(&user->lock); } From 86b2d292c260c76ebeb2ea86dea97ccc3bef665e Mon Sep 17 00:00:00 2001 From: Richard Acayan Date: Tue, 23 May 2023 16:25:50 +0100 Subject: [PATCH 3387/4345] misc: fastrpc: reject new invocations during device removal commit 46248400d81e2aa0b65cd659d6f40188192a58b6 upstream. The channel's rpmsg object allows new invocations to be made. After old invocations are already interrupted, the driver shouldn't try to invoke anymore. Invalidating the rpmsg at the end of the driver removal function makes it easy to cause a race condition in userspace. Even closing a file descriptor before the driver finishes its cleanup can cause an invocation via fastrpc_release_current_dsp_process() and subsequent timeout. Invalidate the channel before the invocations are interrupted to make sure that no invocations can be created to hang after the device closes. Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Cc: stable Signed-off-by: Richard Acayan Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230523152550.438363-5-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 643afb31c952..2488a9a67d18 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1688,7 +1688,9 @@ static void fastrpc_rpmsg_remove(struct rpmsg_device *rpdev) struct fastrpc_user *user; unsigned long flags; + /* No invocations past this point */ spin_lock_irqsave(&cctx->lock, flags); + cctx->rpdev = NULL; list_for_each_entry(user, &cctx->users, user) fastrpc_notify_users(user); spin_unlock_irqrestore(&cctx->lock, flags); @@ -1696,7 +1698,6 @@ static void fastrpc_rpmsg_remove(struct rpmsg_device *rpdev) misc_deregister(&cctx->miscdev); of_platform_depopulate(&rpdev->dev); - cctx->rpdev = NULL; fastrpc_channel_ctx_put(cctx); } From ae0d7613e0e342be7e6371f9a73626a53adfdf26 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 29 May 2023 12:50:34 -0700 Subject: [PATCH 3388/4345] scsi: stex: Fix gcc 13 warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6d074ce231772c66e648a61f6bd2245e7129d1f5 upstream. gcc 13 may assign another type to enumeration constants than gcc 12. Split the large enum at the top of source file stex.c such that the type of the constants used in time expressions is changed back to the same type chosen by gcc 12. This patch suppresses compiler warnings like this one: In file included from ./include/linux/bitops.h:7, from ./include/linux/kernel.h:22, from drivers/scsi/stex.c:13: drivers/scsi/stex.c: In function ‘stex_common_handshake’: ./include/linux/typecheck.h:12:25: error: comparison of distinct pointer types lacks a cast [-Werror] 12 | (void)(&__dummy == &__dummy2); \ | ^~ ./include/linux/jiffies.h:106:10: note: in expansion of macro ‘typecheck’ 106 | typecheck(unsigned long, b) && \ | ^~~~~~~~~ drivers/scsi/stex.c:1035:29: note: in expansion of macro ‘time_after’ 1035 | if (time_after(jiffies, before + MU_MAX_DELAY * HZ)) { | ^~~~~~~~~~ See also https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107405. Cc: stable@vger.kernel.org Acked-by: Randy Dunlap Tested-by: Randy Dunlap # build-tested Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20230529195034.3077-1-bvanassche@acm.org Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/stex.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c index a3bce11ed4b4..fa607f218250 100644 --- a/drivers/scsi/stex.c +++ b/drivers/scsi/stex.c @@ -109,7 +109,9 @@ enum { TASK_ATTRIBUTE_HEADOFQUEUE = 0x1, TASK_ATTRIBUTE_ORDERED = 0x2, TASK_ATTRIBUTE_ACA = 0x4, +}; +enum { SS_STS_NORMAL = 0x80000000, SS_STS_DONE = 0x40000000, SS_STS_HANDSHAKE = 0x20000000, @@ -121,7 +123,9 @@ enum { SS_I2H_REQUEST_RESET = 0x2000, SS_MU_OPERATIONAL = 0x80000000, +}; +enum { STEX_CDB_LENGTH = 16, STATUS_VAR_LEN = 128, From 3442be8f309599f74574dbc667915bf9abf00ca9 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 22 May 2023 20:09:57 +0900 Subject: [PATCH 3389/4345] ata: libata-scsi: Use correct device no in ata_find_dev() commit 7f875850f20a42f488840c9df7af91ef7db2d576 upstream. For devices not attached to a port multiplier and managed directly by libata, the device number passed to ata_find_dev() must always be lower than the maximum number of devices returned by ata_link_max_devices(). That is 1 for SATA devices or 2 for an IDE link with master+slave devices. This device number is the SCSI device ID which matches these constraints as the IDs are generated per port and so never exceed the maximum number of devices for the link being used. However, for libsas managed devices, SCSI device IDs are assigned per struct scsi_host, leading to device IDs for SATA devices that can be well in excess of libata per-link maximum number of devices. This results in ata_find_dev() to always return NULL for libsas managed devices except for the first device of the target scsi_host with ID (device number) equal to 0. This issue is visible by executing the hdparm utility, which fails. E.g.: hdparm -i /dev/sdX /dev/sdX: HDIO_GET_IDENTITY failed: No message of desired type Fix this by rewriting ata_find_dev() to ignore the device number for non-PMP attached devices with a link with at most 1 device, that is SATA devices. For these, the device number 0 is always used to return the correct pointer to the struct ata_device of the port link. This change excludes IDE master/slave setups (maximum number of devices per link is 2) and port-multiplier attached devices. Also, to be consistant with the fact that SCSI device IDs and channel numbers used as device numbers are both unsigned int, change the devno argument of ata_find_dev() to unsigned int. Reported-by: Xingui Yang Fixes: 41bda9c98035 ("libata-link: update hotplug to handle PMP links") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Jason Yan Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libata-scsi.c | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index f1755efd30a2..dfa090ccd21c 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2742,18 +2742,36 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc) return 0; } -static struct ata_device *ata_find_dev(struct ata_port *ap, int devno) +static struct ata_device *ata_find_dev(struct ata_port *ap, unsigned int devno) { - if (!sata_pmp_attached(ap)) { - if (likely(devno >= 0 && - devno < ata_link_max_devices(&ap->link))) + /* + * For the non-PMP case, ata_link_max_devices() returns 1 (SATA case), + * or 2 (IDE master + slave case). However, the former case includes + * libsas hosted devices which are numbered per scsi host, leading + * to devno potentially being larger than 0 but with each struct + * ata_device having its own struct ata_port and struct ata_link. + * To accommodate these, ignore devno and always use device number 0. + */ + if (likely(!sata_pmp_attached(ap))) { + int link_max_devices = ata_link_max_devices(&ap->link); + + if (link_max_devices == 1) + return &ap->link.device[0]; + + if (devno < link_max_devices) return &ap->link.device[devno]; - } else { - if (likely(devno >= 0 && - devno < ap->nr_pmp_links)) - return &ap->pmp_link[devno].device[0]; + + return NULL; } + /* + * For PMP-attached devices, the device number corresponds to C + * (channel) of SCSI [H:C:I:L], indicating the port pmp link + * for the device. + */ + if (devno < ap->nr_pmp_links) + return &ap->pmp_link[devno].device[0]; + return NULL; } From 93e28b66c1048ba4c8a5a00f53b1e5e5b248047c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sun, 27 Feb 2022 11:59:18 -0800 Subject: [PATCH 3390/4345] x86/boot: Wrap literal addresses in absolute_pointer() commit aeb84412037b89e06f45e382f044da6f200e12f8 upstream. GCC 11 (incorrectly[1]) assumes that literal values cast to (void *) should be treated like a NULL pointer with an offset, and raises diagnostics when doing bounds checking under -Warray-bounds. GCC 12 got "smarter" about finding these: In function 'rdfs8', inlined from 'vga_recalc_vertical' at /srv/code/arch/x86/boot/video-mode.c:124:29, inlined from 'set_mode' at /srv/code/arch/x86/boot/video-mode.c:163:3: /srv/code/arch/x86/boot/boot.h:114:9: warning: array subscript 0 is outside array bounds of 'u8[0]' {aka 'unsigned char[]'} [-Warray-bounds] 114 | asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr)); | ^~~ This has been solved in other places[2] already by using the recently added absolute_pointer() macro. Do the same here. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99578 [2] https://lore.kernel.org/all/20210912160149.2227137-1-linux@roeck-us.net/ Signed-off-by: Kees Cook Signed-off-by: Borislav Petkov Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20220227195918.705219-1-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/boot/boot.h | 36 ++++++++++++++++++++++++------------ arch/x86/boot/main.c | 2 +- 2 files changed, 25 insertions(+), 13 deletions(-) diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index ca866f1cca2e..4d79391bb787 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -110,66 +110,78 @@ typedef unsigned int addr_t; static inline u8 rdfs8(addr_t addr) { + u8 *ptr = (u8 *)absolute_pointer(addr); u8 v; - asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr)); + asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*ptr)); return v; } static inline u16 rdfs16(addr_t addr) { + u16 *ptr = (u16 *)absolute_pointer(addr); u16 v; - asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr)); + asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline u32 rdfs32(addr_t addr) { + u32 *ptr = (u32 *)absolute_pointer(addr); u32 v; - asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr)); + asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline void wrfs8(u8 v, addr_t addr) { - asm volatile("movb %1,%%fs:%0" : "+m" (*(u8 *)addr) : "qi" (v)); + u8 *ptr = (u8 *)absolute_pointer(addr); + asm volatile("movb %1,%%fs:%0" : "+m" (*ptr) : "qi" (v)); } static inline void wrfs16(u16 v, addr_t addr) { - asm volatile("movw %1,%%fs:%0" : "+m" (*(u16 *)addr) : "ri" (v)); + u16 *ptr = (u16 *)absolute_pointer(addr); + asm volatile("movw %1,%%fs:%0" : "+m" (*ptr) : "ri" (v)); } static inline void wrfs32(u32 v, addr_t addr) { - asm volatile("movl %1,%%fs:%0" : "+m" (*(u32 *)addr) : "ri" (v)); + u32 *ptr = (u32 *)absolute_pointer(addr); + asm volatile("movl %1,%%fs:%0" : "+m" (*ptr) : "ri" (v)); } static inline u8 rdgs8(addr_t addr) { + u8 *ptr = (u8 *)absolute_pointer(addr); u8 v; - asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr)); + asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*ptr)); return v; } static inline u16 rdgs16(addr_t addr) { + u16 *ptr = (u16 *)absolute_pointer(addr); u16 v; - asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr)); + asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline u32 rdgs32(addr_t addr) { + u32 *ptr = (u32 *)absolute_pointer(addr); u32 v; - asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr)); + asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*ptr)); return v; } static inline void wrgs8(u8 v, addr_t addr) { - asm volatile("movb %1,%%gs:%0" : "+m" (*(u8 *)addr) : "qi" (v)); + u8 *ptr = (u8 *)absolute_pointer(addr); + asm volatile("movb %1,%%gs:%0" : "+m" (*ptr) : "qi" (v)); } static inline void wrgs16(u16 v, addr_t addr) { - asm volatile("movw %1,%%gs:%0" : "+m" (*(u16 *)addr) : "ri" (v)); + u16 *ptr = (u16 *)absolute_pointer(addr); + asm volatile("movw %1,%%gs:%0" : "+m" (*ptr) : "ri" (v)); } static inline void wrgs32(u32 v, addr_t addr) { - asm volatile("movl %1,%%gs:%0" : "+m" (*(u32 *)addr) : "ri" (v)); + u32 *ptr = (u32 *)absolute_pointer(addr); + asm volatile("movl %1,%%gs:%0" : "+m" (*ptr) : "ri" (v)); } /* Note: these only return true/false, not a signed return value! */ diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index e3add857c2c9..c421af5a3cdc 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -33,7 +33,7 @@ static void copy_boot_params(void) u16 cl_offset; }; const struct old_cmdline * const oldcmd = - (const struct old_cmdline *)OLD_CL_ADDRESS; + absolute_pointer(OLD_CL_ADDRESS); BUILD_BUG_ON(sizeof(boot_params) != 4096); memcpy(&boot_params.hdr, &hdr, sizeof(hdr)); From c92ea38a779f19f8da4a25b182748d3fbcba23d8 Mon Sep 17 00:00:00 2001 From: Adam Borowski Date: Mon, 15 Nov 2021 18:32:08 +0100 Subject: [PATCH 3391/4345] ACPI: thermal: drop an always true check commit e5b5d25444e9ee3ae439720e62769517d331fa39 upstream. Address of a field inside a struct can't possibly be null; gcc-12 warns about this. Signed-off-by: Adam Borowski Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/thermal.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 859b1de31ddc..d62bf6df78f8 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -1120,8 +1120,6 @@ static int acpi_thermal_resume(struct device *dev) return -EINVAL; for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE; i++) { - if (!(&tz->trips.active[i])) - break; if (!tz->trips.active[i].flags.valid) break; tz->trips.active[i].flags.enabled = 1; From 7c602f540bfd15affabd880b98b99fec01bb7a23 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 8 Dec 2021 10:44:00 +0200 Subject: [PATCH 3392/4345] ath6kl: Use struct_group() to avoid size-mismatched casting commit e3128a9d482cff9cc2a826adec5e1f7acb922b8f upstream. In builds with -Warray-bounds, casts from smaller objects to larger objects will produce warnings. These can be overly conservative, but since -Warray-bounds has been finding legitimate bugs, it is desirable to turn it on globally. Instead of casting a u32 to a larger object, redefine the u32 portion of the header to a separate struct that can be used for both u32 operations and the distinct header fields. Silences this warning: drivers/net/wireless/ath/ath6kl/htc_mbox.c: In function 'htc_wait_for_ctrl_msg': drivers/net/wireless/ath/ath6kl/htc_mbox.c:2275:20: error: array subscript 'struct htc_frame_hdr[0]' is partly outside array bounds of 'u32[1]' {aka 'unsigned int[1]'} [-Werror=array-bounds] 2275 | if (htc_hdr->eid != ENDPOINT_0) | ^~ drivers/net/wireless/ath/ath6kl/htc_mbox.c:2264:13: note: while referencing 'look_ahead' 2264 | u32 look_ahead; | ^~~~~~~~~~ This change results in no executable instruction differences. Signed-off-by: Kees Cook Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20211207063538.2767954-1-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ath/ath6kl/htc.h | 15 +++++++++++---- drivers/net/wireless/ath/ath6kl/htc_mbox.c | 15 ++++++--------- 2 files changed, 17 insertions(+), 13 deletions(-) diff --git a/drivers/net/wireless/ath/ath6kl/htc.h b/drivers/net/wireless/ath/ath6kl/htc.h index 112d8a9b8d43..d3534a29c4f0 100644 --- a/drivers/net/wireless/ath/ath6kl/htc.h +++ b/drivers/net/wireless/ath/ath6kl/htc.h @@ -153,12 +153,19 @@ * implementations. */ struct htc_frame_hdr { - u8 eid; - u8 flags; + struct_group_tagged(htc_frame_look_ahead, header, + union { + struct { + u8 eid; + u8 flags; - /* length of data (including trailer) that follows the header */ - __le16 payld_len; + /* length of data (including trailer) that follows the header */ + __le16 payld_len; + }; + u32 word; + }; + ); /* end of 4-byte lookahead */ u8 ctrl[2]; diff --git a/drivers/net/wireless/ath/ath6kl/htc_mbox.c b/drivers/net/wireless/ath/ath6kl/htc_mbox.c index 998947ef63b6..e3874421c4c0 100644 --- a/drivers/net/wireless/ath/ath6kl/htc_mbox.c +++ b/drivers/net/wireless/ath/ath6kl/htc_mbox.c @@ -2260,19 +2260,16 @@ int ath6kl_htc_rxmsg_pending_handler(struct htc_target *target, static struct htc_packet *htc_wait_for_ctrl_msg(struct htc_target *target) { struct htc_packet *packet = NULL; - struct htc_frame_hdr *htc_hdr; - u32 look_ahead; + struct htc_frame_look_ahead look_ahead; - if (ath6kl_hif_poll_mboxmsg_rx(target->dev, &look_ahead, + if (ath6kl_hif_poll_mboxmsg_rx(target->dev, &look_ahead.word, HTC_TARGET_RESPONSE_TIMEOUT)) return NULL; ath6kl_dbg(ATH6KL_DBG_HTC, - "htc rx wait ctrl look_ahead 0x%X\n", look_ahead); + "htc rx wait ctrl look_ahead 0x%X\n", look_ahead.word); - htc_hdr = (struct htc_frame_hdr *)&look_ahead; - - if (htc_hdr->eid != ENDPOINT_0) + if (look_ahead.eid != ENDPOINT_0) return NULL; packet = htc_get_control_buf(target, false); @@ -2281,8 +2278,8 @@ static struct htc_packet *htc_wait_for_ctrl_msg(struct htc_target *target) return NULL; packet->info.rx.rx_flags = 0; - packet->info.rx.exp_hdr = look_ahead; - packet->act_len = le16_to_cpu(htc_hdr->payld_len) + HTC_HDR_LENGTH; + packet->info.rx.exp_hdr = look_ahead.word; + packet->act_len = le16_to_cpu(look_ahead.payld_len) + HTC_HDR_LENGTH; if (packet->act_len > packet->buf_len) goto fail_ctrl_rx; From 1d8693376aaa10f12bbd67cfecb72a26a83058c5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 9 Jun 2022 09:41:42 -0700 Subject: [PATCH 3393/4345] gcc-12: disable '-Wdangling-pointer' warning for now MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f7d63b50898172b9eb061b9e2daad61b428792d0 upstream. [ Upstream commit 49beadbd47c270a00754c107a837b4f29df4c822 ] While the concept of checking for dangling pointers to local variables at function exit is really interesting, the gcc-12 implementation is not compatible with reality, and results in false positives. For example, gcc sees us putting things on a local list head allocated on the stack, which involves exactly those kinds of pointers to the local stack entry: In function ‘__list_add’, inlined from ‘list_add_tail’ at include/linux/list.h:102:2, inlined from ‘rebuild_snap_realms’ at fs/ceph/snap.c:434:2: include/linux/list.h:74:19: warning: storing the address of local variable ‘realm_queue’ in ‘*&realm_27(D)->rebuild_item.prev’ [-Wdangling-pointer=] 74 | new->prev = prev; | ~~~~~~~~~~^~~~~~ But then gcc - understandably - doesn't really understand the big picture how the doubly linked list works, so doesn't see how we then end up emptying said list head in a loop and the pointer we added has been removed. Gcc also complains about us (intentionally) using this as a way to store a kind of fake stack trace, eg drivers/acpi/acpica/utdebug.c:40:38: warning: storing the address of local variable ‘current_sp’ in ‘acpi_gbl_entry_stack_pointer’ [-Wdangling-pointer=] 40 | acpi_gbl_entry_stack_pointer = ¤t_sp; | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~ which is entirely reasonable from a compiler standpoint, and we may want to change those kinds of patterns, but not not. So this is one of those "it would be lovely if the compiler were to complain about us leaving dangling pointers to the stack", but not this way. Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- Makefile | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Makefile b/Makefile index 2f0efde21902..209d5ae9ddb5 100644 --- a/Makefile +++ b/Makefile @@ -808,6 +808,10 @@ endif KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) + +# These result in bogus false positives +KBUILD_CFLAGS += $(call cc-disable-warning, dangling-pointer) + ifdef CONFIG_FRAME_POINTER KBUILD_CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls else From 99cb5ed15d3e1aedcfcc2c5b6a8d3cec72fd3a3f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Li=C5=A1ka?= Date: Wed, 18 May 2022 09:18:53 +0200 Subject: [PATCH 3394/4345] eth: sun: cassini: remove dead code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 32329216ca1d6ee29c41215f18b3053bb6158541 upstream. Fixes the following GCC warning: drivers/net/ethernet/sun/cassini.c:1316:29: error: comparison between two arrays [-Werror=array-compare] drivers/net/ethernet/sun/cassini.c:3783:34: error: comparison between two arrays [-Werror=array-compare] Note that 2 arrays should be compared by comparing of their addresses: note: use ‘&cas_prog_workaroundtab[0] == &cas_prog_null[0]’ to compare the addresses Signed-off-by: Martin Liska Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/sun/cassini.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index d245f6e21e8c..b929c6f6ce51 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -1325,7 +1325,7 @@ static void cas_init_rx_dma(struct cas *cp) writel(val, cp->regs + REG_RX_PAGE_SIZE); /* enable the header parser if desired */ - if (CAS_HP_FIRMWARE == cas_prog_null) + if (&CAS_HP_FIRMWARE[0] == &cas_prog_null[0]) return; val = CAS_BASE(HP_CFG_NUM_CPU, CAS_NCPUS > 63 ? 0 : CAS_NCPUS); @@ -3793,7 +3793,7 @@ static void cas_reset(struct cas *cp, int blkflag) /* program header parser */ if ((cp->cas_flags & CAS_FLAG_TARGET_ABORT) || - (CAS_HP_ALT_FIRMWARE == cas_prog_null)) { + (&CAS_HP_ALT_FIRMWARE[0] == &cas_prog_null[0])) { cas_load_firmware(cp, CAS_HP_FIRMWARE); } else { cas_load_firmware(cp, CAS_HP_ALT_FIRMWARE); From 6127e956c3a73eb3583af26eec165e26483edacb Mon Sep 17 00:00:00 2001 From: Deren Wu Date: Sat, 13 May 2023 22:48:15 +0800 Subject: [PATCH 3395/4345] mmc: vub300: fix invalid response handling commit a99d21cefd351c8aaa20b83a3c942340e5789d45 upstream. We may get an empty response with zero length at the beginning of the driver start and get following UBSAN error. Since there is no content(SDRT_NONE) for the response, just return and skip the response handling to avoid this problem. Test pass : SDIO wifi throughput test with this patch [ 126.980684] UBSAN: array-index-out-of-bounds in drivers/mmc/host/vub300.c:1719:12 [ 126.980709] index -1 is out of range for type 'u32 [4]' [ 126.980729] CPU: 4 PID: 9 Comm: kworker/u16:0 Tainted: G E 6.3.0-rc4-mtk-local-202304272142 #1 [ 126.980754] Hardware name: Intel(R) Client Systems NUC8i7BEH/NUC8BEB, BIOS BECFL357.86A.0081.2020.0504.1834 05/04/2020 [ 126.980770] Workqueue: kvub300c vub300_cmndwork_thread [vub300] [ 126.980833] Call Trace: [ 126.980845] [ 126.980860] dump_stack_lvl+0x48/0x70 [ 126.980895] dump_stack+0x10/0x20 [ 126.980916] ubsan_epilogue+0x9/0x40 [ 126.980944] __ubsan_handle_out_of_bounds+0x70/0x90 [ 126.980979] vub300_cmndwork_thread+0x58e7/0x5e10 [vub300] [ 126.981018] ? _raw_spin_unlock+0x18/0x40 [ 126.981042] ? finish_task_switch+0x175/0x6f0 [ 126.981070] ? __switch_to+0x42e/0xda0 [ 126.981089] ? __switch_to_asm+0x3a/0x80 [ 126.981129] ? __pfx_vub300_cmndwork_thread+0x10/0x10 [vub300] [ 126.981174] ? __kasan_check_read+0x11/0x20 [ 126.981204] process_one_work+0x7ee/0x13d0 [ 126.981246] worker_thread+0x53c/0x1240 [ 126.981291] kthread+0x2b8/0x370 [ 126.981312] ? __pfx_worker_thread+0x10/0x10 [ 126.981336] ? __pfx_kthread+0x10/0x10 [ 126.981359] ret_from_fork+0x29/0x50 [ 126.981400] Fixes: 88095e7b473a ("mmc: Add new VUB300 USB-to-SD/SDIO/MMC driver") Signed-off-by: Deren Wu Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/048cd6972c50c33c2e8f81d5228fed928519918b.1683987673.git.deren.wu@mediatek.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/vub300.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index 72f65f32abbc..7dc0e91dabfc 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -1715,6 +1715,9 @@ static void construct_request_response(struct vub300_mmc_host *vub300, int bytes = 3 & less_cmd; int words = less_cmd >> 2; u8 *r = vub300->resp.response.command_response; + + if (!resp_len) + return; if (bytes == 3) { cmd->resp[words] = (r[1 + (words << 2)] << 24) | (r[2 + (words << 2)] << 16) From 6c859764f44d7bd31ca3712378082468111f6142 Mon Sep 17 00:00:00 2001 From: Sherry Sun Date: Fri, 19 May 2023 17:47:51 +0800 Subject: [PATCH 3396/4345] tty: serial: fsl_lpuart: use UARTCTRL_TXINV to send break instead of UARTCTRL_SBK commit 2474e05467c00f7d51af3039b664de6886325257 upstream. LPUART IP now has two known bugs, one is that CTS has higher priority than the break signal, which causes the break signal sending through UARTCTRL_SBK may impacted by the CTS input if the HW flow control is enabled. It exists on all platforms we support in this driver. So we add a workaround patch for this issue: commit c4c81db5cf8b ("tty: serial: fsl_lpuart: disable the CTS when send break signal"). Another IP bug is i.MX8QM LPUART may have an additional break character being sent after SBK was cleared. It may need to add some delay between clearing SBK and re-enabling CTS to ensure that the SBK latch are completely cleared. But we found that during the delay period before CTS is enabled, there is still a risk that Bluetooth data in TX FIFO may be sent out during this period because of break off and CTS disabled(even if BT sets CTS line deasserted, data is still sent to BT). Due to this risk, we have to drop the CTS-disabling workaround for SBK bugs, use TXINV seems to be a better way to replace SBK feature and avoid above risk. Also need to disable the transmitter to prevent any data from being sent out during break, then invert the TX line to send break. Then disable the TXINV when turn off break and re-enable transmitter. Fixes: c4c81db5cf8b ("tty: serial: fsl_lpuart: disable the CTS when send break signal") Cc: stable Signed-off-by: Sherry Sun Link: https://lore.kernel.org/r/20230519094751.28948-1-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 44 +++++++++++++++++---------------- 1 file changed, 23 insertions(+), 21 deletions(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index a2efa81471f3..ca22a1125821 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1455,34 +1455,36 @@ static void lpuart_break_ctl(struct uart_port *port, int break_state) static void lpuart32_break_ctl(struct uart_port *port, int break_state) { - unsigned long temp, modem; - struct tty_struct *tty; - unsigned int cflag = 0; + unsigned long temp; - tty = tty_port_tty_get(&port->state->port); - if (tty) { - cflag = tty->termios.c_cflag; - tty_kref_put(tty); - } - - temp = lpuart32_read(port, UARTCTRL) & ~UARTCTRL_SBK; - modem = lpuart32_read(port, UARTMODIR); + temp = lpuart32_read(port, UARTCTRL); + /* + * LPUART IP now has two known bugs, one is CTS has higher priority than the + * break signal, which causes the break signal sending through UARTCTRL_SBK + * may impacted by the CTS input if the HW flow control is enabled. It + * exists on all platforms we support in this driver. + * Another bug is i.MX8QM LPUART may have an additional break character + * being sent after SBK was cleared. + * To avoid above two bugs, we use Transmit Data Inversion function to send + * the break signal instead of UARTCTRL_SBK. + */ if (break_state != 0) { - temp |= UARTCTRL_SBK; /* - * LPUART CTS has higher priority than SBK, need to disable CTS before - * asserting SBK to avoid any interference if flow control is enabled. + * Disable the transmitter to prevent any data from being sent out + * during break, then invert the TX line to send break. */ - if (cflag & CRTSCTS && modem & UARTMODIR_TXCTSE) - lpuart32_write(port, modem & ~UARTMODIR_TXCTSE, UARTMODIR); + temp &= ~UARTCTRL_TE; + lpuart32_write(port, temp, UARTCTRL); + temp |= UARTCTRL_TXINV; + lpuart32_write(port, temp, UARTCTRL); } else { - /* Re-enable the CTS when break off. */ - if (cflag & CRTSCTS && !(modem & UARTMODIR_TXCTSE)) - lpuart32_write(port, modem | UARTMODIR_TXCTSE, UARTMODIR); + /* Disable the TXINV to turn off break and re-enable transmitter. */ + temp &= ~UARTCTRL_TXINV; + lpuart32_write(port, temp, UARTCTRL); + temp |= UARTCTRL_TE; + lpuart32_write(port, temp, UARTCTRL); } - - lpuart32_write(port, temp, UARTCTRL); } static void lpuart_setup_watermark(struct lpuart_port *sport) From e0b8664c2fec4dbfa450051d3f6b3bf87c0d3f64 Mon Sep 17 00:00:00 2001 From: pengfuyuan Date: Tue, 23 May 2023 15:09:55 +0800 Subject: [PATCH 3397/4345] btrfs: fix csum_tree_block page iteration to avoid tripping on -Werror=array-bounds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 5ad9b4719fc9bc4715c7e19875a962095b0577e7 upstream. When compiling on a MIPS 64-bit machine we get these warnings: In file included from ./arch/mips/include/asm/cacheflush.h:13, from ./include/linux/cacheflush.h:5, from ./include/linux/highmem.h:8, from ./include/linux/bvec.h:10, from ./include/linux/blk_types.h:10, from ./include/linux/blkdev.h:9, from fs/btrfs/disk-io.c:7: fs/btrfs/disk-io.c: In function ‘csum_tree_block’: fs/btrfs/disk-io.c:100:34: error: array subscript 1 is above array bounds of ‘struct page *[1]’ [-Werror=array-bounds] 100 | kaddr = page_address(buf->pages[i]); | ~~~~~~~~~~^~~ ./include/linux/mm.h:2135:48: note: in definition of macro ‘page_address’ 2135 | #define page_address(page) lowmem_page_address(page) | ^~~~ cc1: all warnings being treated as errors We can check if i overflows to solve the problem. However, this doesn't make much sense, since i == 1 and num_pages == 1 doesn't execute the body of the loop. In addition, i < num_pages can also ensure that buf->pages[i] will not cross the boundary. Unfortunately, this doesn't help with the problem observed here: gcc still complains. To fix this add a compile-time condition for the extent buffer page array size limit, which would eventually lead to eliminating the whole for loop. CC: stable@vger.kernel.org # 5.10+ Signed-off-by: pengfuyuan Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 60b7a227624d..5a114cad988a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -220,7 +220,7 @@ static void csum_tree_block(struct extent_buffer *buf, u8 *result) crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, PAGE_SIZE - BTRFS_CSUM_SIZE); - for (i = 1; i < num_pages; i++) { + for (i = 1; i < num_pages && INLINE_EXTENT_BUFFER_PAGES > 1; i++) { kaddr = page_address(buf->pages[i]); crypto_shash_update(shash, kaddr, PAGE_SIZE); } From 122ba1d40bea8e2fed68f0acb0a9a4a4bddeedf0 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 1 Jun 2023 10:21:21 -0400 Subject: [PATCH 3398/4345] selinux: don't use make's grouped targets feature yet commit 42c4e97e06a839b07d834f640a10911ad84ec8b3 upstream. The Linux Kernel currently only requires make v3.82 while the grouped target functionality requires make v4.3. Removed the grouped target introduced in 4ce1f694eb5d ("selinux: ensure av_permissions.h is built when needed") as well as the multiple header file targets in the make rule. This effectively reverts the problem commit. We will revisit this change when make >= 4.3 is required by the rest of the kernel. Cc: stable@vger.kernel.org Fixes: 4ce1f694eb5d ("selinux: ensure av_permissions.h is built when needed") Reported-by: Erwan Velu Reported-by: Luiz Capitulino Tested-by: Luiz Capitulino Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- security/selinux/Makefile | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/security/selinux/Makefile b/security/selinux/Makefile index ee1ddda96447..332a1c752b49 100644 --- a/security/selinux/Makefile +++ b/security/selinux/Makefile @@ -24,5 +24,9 @@ quiet_cmd_flask = GEN $(obj)/flask.h $(obj)/av_permissions.h cmd_flask = $< $(obj)/flask.h $(obj)/av_permissions.h targets += flask.h av_permissions.h -$(obj)/flask.h $(obj)/av_permissions.h &: scripts/selinux/genheaders/genheaders FORCE +# once make >= 4.3 is required, we can use grouped targets in the rule below, +# which basically involves adding both headers and a '&' before the colon, see +# the example below: +# $(obj)/flask.h $(obj)/av_permissions.h &: scripts/selinux/... +$(obj)/flask.h: scripts/selinux/genheaders/genheaders FORCE $(call if_changed,flask) From 57eb824b8cbb29156fb352153e18a91ac2ed0daa Mon Sep 17 00:00:00 2001 From: Pietro Borrello Date: Sat, 28 Jan 2023 16:23:41 +0000 Subject: [PATCH 3399/4345] tracing/probe: trace_probe_primary_from_call(): checked list_first_entry commit 81d0fa4cb4fc0e1a49c2b22f92c43d9fe972ebcf upstream. All callers of trace_probe_primary_from_call() check the return value to be non NULL. However, the function returns list_first_entry(&tpe->probes, ...) which can never be NULL. Additionally, it does not check for the list being possibly empty, possibly causing a type confusion on empty lists. Use list_first_entry_or_null() which solves both problems. Link: https://lore.kernel.org/linux-trace-kernel/20230128-list-entry-null-check-v1-1-8bde6a3da2ef@diag.uniroma1.it/ Fixes: 60d53e2c3b75 ("tracing/probe: Split trace_event related data from trace_probe") Signed-off-by: Pietro Borrello Reviewed-by: Steven Rostedt (Google) Acked-by: Masami Hiramatsu (Google) Acked-by: Mukesh Ojha Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_probe.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 6d41e20c47ce..d4a69b83902e 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -301,7 +301,7 @@ trace_probe_primary_from_call(struct trace_event_call *call) { struct trace_probe_event *tpe = trace_probe_event_from_call(call); - return list_first_entry(&tpe->probes, struct trace_probe, list); + return list_first_entry_or_null(&tpe->probes, struct trace_probe, list); } static inline struct list_head *trace_probe_probe_list(struct trace_probe *tp) From 54dea0aa6bef847de926db2e6a3b20c3361b2369 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Sun, 28 May 2023 19:35:27 +0200 Subject: [PATCH 3400/4345] selftests: mptcp: connect: skip if MPTCP is not supported commit d83013bdf90a7994a474b0e650a7fc94b0d4ded6 upstream. Selftests are supposed to run on any kernels, including the old ones not supporting MPTCP. A new check is then added to make sure MPTCP is supported. If not, the test stops and is marked as "skipped". Note that this check can also mark the test as failed if 'SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES' env var is set to 1: by doing that, we can make sure a test is not being skipped by mistake. A new shared file is added here to be able to re-used the same check in the different selftests we have. Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 048d19d444be ("mptcp: add basic kselftest for mptcp") Cc: stable@vger.kernel.org Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/mptcp/Makefile | 2 +- .../selftests/net/mptcp/mptcp_connect.sh | 4 ++ .../testing/selftests/net/mptcp/mptcp_lib.sh | 40 +++++++++++++++++++ 3 files changed, 45 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/net/mptcp/mptcp_lib.sh diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 00bb158b4a5d..7072ef1c0ae7 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -10,7 +10,7 @@ TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ TEST_GEN_FILES = mptcp_connect pm_nl_ctl -TEST_FILES := settings +TEST_FILES := mptcp_lib.sh settings EXTRA_CLEAN := *.pcap diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 987a914ee0df..fb89298bdde4 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + time_start=$(date +%s) optstring="S:R:d:e:l:r:h4cm:f:t" @@ -131,6 +133,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh new file mode 100644 index 000000000000..3286536b79d5 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -0,0 +1,40 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly KSFT_FAIL=1 +readonly KSFT_SKIP=4 + +# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all +# features using the last version of the kernel and the selftests to make sure +# a test is not being skipped by mistake. +mptcp_lib_expect_all_features() { + [ "${SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES:-}" = "1" ] +} + +# $1: msg +mptcp_lib_fail_if_expected_feature() { + if mptcp_lib_expect_all_features; then + echo "ERROR: missing feature: ${*}" + exit ${KSFT_FAIL} + fi + + return 1 +} + +# $1: file +mptcp_lib_has_file() { + local f="${1}" + + if [ -f "${f}" ]; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${f} file not found" +} + +mptcp_lib_check_mptcp() { + if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then + echo "SKIP: MPTCP support is not available" + exit ${KSFT_SKIP} + fi +} From 6d0adaa90dbe53cc2a8ff26afdc9c8b2fa10bf55 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Sun, 28 May 2023 19:35:28 +0200 Subject: [PATCH 3401/4345] selftests: mptcp: pm nl: skip if MPTCP is not supported commit 0f4955a40dafe18a1122e3714d8173e4b018e869 upstream. Selftests are supposed to run on any kernels, including the old ones not supporting MPTCP. A new check is then added to make sure MPTCP is supported. If not, the test stops and is marked as "skipped". Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: eedbc685321b ("selftests: add PM netlink functional tests") Cc: stable@vger.kernel.org Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/mptcp/pm_netlink.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 15f4f46ca3a9..f7cdba0a97a9 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ksft_skip=4 ret=0 @@ -34,6 +36,8 @@ cleanup() ip netns del $ns1 } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" From 6d67d4966c1e7fda765d877315caa372493fe838 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 23 May 2023 23:49:48 -0400 Subject: [PATCH 3402/4345] ext4: add EA_INODE checking to ext4_iget() commit b3e6bcb94590dea45396b9481e47b809b1be4afa upstream. Add a new flag, EXT4_IGET_EA_INODE which indicates whether the inode is expected to have the EA_INODE flag or not. If the flag is not set/clear as expected, then fail the iget() operation and mark the file system as corrupted. This commit also makes the ext4_iget() always perform the is_bad_inode() check even when the inode is already inode cache. This allows us to remove the is_bad_inode() check from the callers of ext4_iget() in the ea_inode code. Reported-by: syzbot+cbb68193bdb95af4340a@syzkaller.appspotmail.com Reported-by: syzbot+62120febbd1ee3c3c860@syzkaller.appspotmail.com Reported-by: syzbot+edce54daffee36421b4c@syzkaller.appspotmail.com Cc: stable@kernel.org Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20230524034951.779531-2-tytso@mit.edu Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ext4.h | 3 ++- fs/ext4/inode.c | 31 ++++++++++++++++++++++++++----- fs/ext4/xattr.c | 36 +++++++----------------------------- 3 files changed, 35 insertions(+), 35 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 84a240025aa4..75cdfae9f8f5 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2849,7 +2849,8 @@ typedef enum { EXT4_IGET_NORMAL = 0, EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */ EXT4_IGET_HANDLE = 0x0002, /* Inode # is from a handle */ - EXT4_IGET_BAD = 0x0004 /* Allow to iget a bad inode */ + EXT4_IGET_BAD = 0x0004, /* Allow to iget a bad inode */ + EXT4_IGET_EA_INODE = 0x0008 /* Inode should contain an EA value */ } ext4_iget_flags; extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 735109b9e88d..2e0635d79d7e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4680,6 +4680,21 @@ static inline u64 ext4_inode_peek_iversion(const struct inode *inode) return inode_peek_iversion(inode); } +static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags) + +{ + if (flags & EXT4_IGET_EA_INODE) { + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return "missing EA_INODE flag"; + } else { + if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return "unexpected EA_INODE flag"; + } + if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) + return "unexpected bad inode w/o EXT4_IGET_BAD"; + return NULL; +} + struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, unsigned int line) @@ -4688,6 +4703,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, struct ext4_inode *raw_inode; struct ext4_inode_info *ei; struct inode *inode; + const char *err_str; journal_t *journal = EXT4_SB(sb)->s_journal; long ret; loff_t size; @@ -4711,8 +4727,14 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode->i_state & I_NEW)) { + if ((err_str = check_igot_inode(inode, flags)) != NULL) { + ext4_error_inode(inode, function, line, 0, err_str); + iput(inode); + return ERR_PTR(-EFSCORRUPTED); + } return inode; + } ei = EXT4_I(inode); iloc.bh = NULL; @@ -4981,10 +5003,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) ext4_error_inode(inode, function, line, 0, "casefold flag without casefold feature"); - if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) { - ext4_error_inode(inode, function, line, 0, - "bad inode without EXT4_IGET_BAD flag"); - ret = -EUCLEAN; + if ((err_str = check_igot_inode(inode, flags)) != NULL) { + ext4_error_inode(inode, function, line, 0, err_str); + ret = -EFSCORRUPTED; goto bad_inode; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index abcba0255109..eee9304f50f9 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -397,7 +397,7 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, return -EFSCORRUPTED; } - inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL); + inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_EA_INODE); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(parent->i_sb, @@ -405,23 +405,6 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, err); return err; } - - if (is_bad_inode(inode)) { - ext4_error(parent->i_sb, - "error while reading EA inode %lu is_bad_inode", - ea_ino); - err = -EIO; - goto error; - } - - if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { - ext4_error(parent->i_sb, - "EA inode %lu does not have EXT4_EA_INODE_FL flag", - ea_ino); - err = -EINVAL; - goto error; - } - ext4_xattr_inode_set_class(inode); /* @@ -442,9 +425,6 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, *ea_inode = inode; return 0; -error: - iput(inode); - return err; } /* Remove entry from mbcache when EA inode is getting evicted */ @@ -1500,11 +1480,10 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, while (ce) { ea_inode = ext4_iget(inode->i_sb, ce->e_value, - EXT4_IGET_NORMAL); - if (!IS_ERR(ea_inode) && - !is_bad_inode(ea_inode) && - (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) && - i_size_read(ea_inode) == value_len && + EXT4_IGET_EA_INODE); + if (IS_ERR(ea_inode)) + goto next_entry; + if (i_size_read(ea_inode) == value_len && !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, value_len) && @@ -1514,9 +1493,8 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, kvfree(ea_data); return ea_inode; } - - if (!IS_ERR(ea_inode)) - iput(ea_inode); + iput(ea_inode); + next_entry: ce = mb_cache_entry_find_next(ea_inode_cache, ce); } kvfree(ea_data); From 6f4fa43757bbf2cc97751545a4a428a5abc6ec5f Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 23 May 2023 23:49:49 -0400 Subject: [PATCH 3403/4345] ext4: set lockdep subclass for the ea_inode in ext4_xattr_inode_cache_find() commit b928dfdcb27d8fa59917b794cfba53052a2f050f upstream. If the ea_inode has been pushed out of the inode cache while there is still a reference in the mb_cache, the lockdep subclass will not be set on the inode, which can lead to some lockdep false positives. Fixes: 33d201e0277b ("ext4: fix lockdep warning about recursive inode locking") Cc: stable@kernel.org Reported-by: syzbot+d4b971e744b1f5439336@syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20230524034951.779531-3-tytso@mit.edu Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index eee9304f50f9..9a4ae4210ba4 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1483,6 +1483,7 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, EXT4_IGET_EA_INODE); if (IS_ERR(ea_inode)) goto next_entry; + ext4_xattr_inode_set_class(ea_inode); if (i_size_read(ea_inode) == value_len && !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, From ef70012ab51c1b3642137b3f0922143162870110 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 23 May 2023 23:49:50 -0400 Subject: [PATCH 3404/4345] ext4: disallow ea_inodes with extended attributes commit 2bc7e7c1a3bc9bd0cbf0f71006f6fe7ef24a00c2 upstream. An ea_inode stores the value of an extended attribute; it can not have extended attributes itself, or this will cause recursive nightmares. Add a check in ext4_iget() to make sure this is the case. Cc: stable@kernel.org Reported-by: syzbot+e44749b6ba4d0434cd47@syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20230524034951.779531-4-tytso@mit.edu Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2e0635d79d7e..d3143746bcdb 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4686,6 +4686,9 @@ static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags) if (flags & EXT4_IGET_EA_INODE) { if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) return "missing EA_INODE flag"; + if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) || + EXT4_I(inode)->i_file_acl) + return "ea_inode with extended attributes"; } else { if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) return "unexpected EA_INODE flag"; From c94228a5aea4fe72f41f370bb45455ea90103475 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 23 May 2023 23:49:51 -0400 Subject: [PATCH 3405/4345] ext4: add lockdep annotations for i_data_sem for ea_inode's commit aff3bea95388299eec63440389b4545c8041b357 upstream. Treat i_data_sem for ea_inodes as being in their own lockdep class to avoid lockdep complaints about ext4_setattr's use of inode_lock() on normal inodes potentially causing lock ordering with i_data_sem on ea_inodes in ext4_xattr_inode_write(). However, ea_inodes will be operated on by ext4_setattr(), so this isn't a problem. Cc: stable@kernel.org Link: https://syzkaller.appspot.com/bug?extid=298c5d8fb4a128bc27b0 Reported-by: syzbot+298c5d8fb4a128bc27b0@syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20230524034951.779531-5-tytso@mit.edu Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ext4.h | 2 ++ fs/ext4/xattr.c | 4 ++++ 2 files changed, 6 insertions(+) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 75cdfae9f8f5..c8fdf127d843 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -980,11 +980,13 @@ do { \ * where the second inode has larger inode number * than the first * I_DATA_SEM_QUOTA - Used for quota inodes only + * I_DATA_SEM_EA - Used for ea_inodes only */ enum { I_DATA_SEM_NORMAL = 0, I_DATA_SEM_OTHER, I_DATA_SEM_QUOTA, + I_DATA_SEM_EA }; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 9a4ae4210ba4..10b2f570d400 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -123,7 +123,11 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { + struct ext4_inode_info *ei = EXT4_I(ea_inode); + lockdep_set_subclass(&ea_inode->i_rwsem, 1); + (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ + lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA); } #endif From b02ae50c7fd87762befaa9728e2f790f47f71852 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 27 May 2023 08:41:09 +0200 Subject: [PATCH 3406/4345] fbcon: Fix null-ptr-deref in soft_cursor commit d78bd6cc68276bd57f766f7cb98bfe32c23ab327 upstream. syzbot repored this bug in the softcursor code: BUG: KASAN: null-ptr-deref in soft_cursor+0x384/0x6b4 drivers/video/fbdev/core/softcursor.c:70 Read of size 16 at addr 0000000000000200 by task kworker/u4:1/12 CPU: 0 PID: 12 Comm: kworker/u4:1 Not tainted 6.4.0-rc3-syzkaller-geb0f1697d729 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/28/2023 Workqueue: events_power_efficient fb_flashcursor Call trace: dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:233 show_stack+0x2c/0x44 arch/arm64/kernel/stacktrace.c:240 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106 print_report+0xe4/0x514 mm/kasan/report.c:465 kasan_report+0xd4/0x130 mm/kasan/report.c:572 kasan_check_range+0x264/0x2a4 mm/kasan/generic.c:187 __asan_memcpy+0x3c/0x84 mm/kasan/shadow.c:105 soft_cursor+0x384/0x6b4 drivers/video/fbdev/core/softcursor.c:70 bit_cursor+0x113c/0x1a64 drivers/video/fbdev/core/bitblit.c:377 fb_flashcursor+0x35c/0x54c drivers/video/fbdev/core/fbcon.c:380 process_one_work+0x788/0x12d4 kernel/workqueue.c:2405 worker_thread+0x8e0/0xfe8 kernel/workqueue.c:2552 kthread+0x288/0x310 kernel/kthread.c:379 ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:853 This fix let bit_cursor() bail out early when a font bitmap isn't available yet. Signed-off-by: Helge Deller Reported-by: syzbot+d910bd780e6efac35869@syzkaller.appspotmail.com Acked-by: Sam Ravnborg Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/core/bitblit.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index 9725ecd1255b..8e095b0982db 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -247,6 +247,9 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode, cursor.set = 0; + if (!vc->vc_font.data) + return; + c = scr_readw((u16 *) vc->vc_pos); attribute = get_attribute(info, c); src = vc->vc_font.data + ((c & charmask) * (w * vc->vc_font.height)); From 510e015b90584fd4cdf0aca4195326296521e6ad Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 14 May 2023 13:25:42 +0200 Subject: [PATCH 3407/4345] serial: 8250_tegra: Fix an error handling path in tegra_uart_probe() commit 134f49dec0b6aca3259cd8259de4c572048bd207 upstream. If an error occurs after reset_control_deassert(), it must be re-asserted, as already done in the .remove() function. Fixes: c6825c6395b7 ("serial: 8250_tegra: Create Tegra specific 8250 driver") Cc: stable Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/f8130f35339cc80edc6b9aac4bb2a60b60a226bf.1684063511.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_tegra.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_tegra.c b/drivers/tty/serial/8250/8250_tegra.c index c0ffad1572c6..b6694ddfc4ea 100644 --- a/drivers/tty/serial/8250/8250_tegra.c +++ b/drivers/tty/serial/8250/8250_tegra.c @@ -111,13 +111,15 @@ static int tegra_uart_probe(struct platform_device *pdev) ret = serial8250_register_8250_port(&port8250); if (ret < 0) - goto err_clkdisable; + goto err_ctrl_assert; platform_set_drvdata(pdev, uart); uart->line = ret; return 0; +err_ctrl_assert: + reset_control_assert(uart->rst); err_clkdisable: clk_disable_unprepare(uart->clk); From 21bb3cd2e1bc50b0fb63b74de1ef1103efb6e064 Mon Sep 17 00:00:00 2001 From: Mirsad Goran Todorovac Date: Tue, 9 May 2023 10:47:49 +0200 Subject: [PATCH 3408/4345] test_firmware: fix the memory leak of the allocated firmware buffer commit 48e156023059e57a8fc68b498439832f7600ffff upstream. The following kernel memory leak was noticed after running tools/testing/selftests/firmware/fw_run_tests.sh: [root@pc-mtodorov firmware]# cat /sys/kernel/debug/kmemleak . . . unreferenced object 0xffff955389bc3400 (size 1024): comm "test_firmware-0", pid 5451, jiffies 4294944822 (age 65.652s) hex dump (first 32 bytes): 47 48 34 35 36 37 0a 00 00 00 00 00 00 00 00 00 GH4567.......... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] slab_post_alloc_hook+0x8c/0x3c0 [] __kmem_cache_alloc_node+0x184/0x240 [] kmalloc_trace+0x2e/0xc0 [] test_fw_run_batch_request+0x9d/0x180 [] kthread+0x10b/0x140 [] ret_from_fork+0x29/0x50 unreferenced object 0xffff9553c334b400 (size 1024): comm "test_firmware-1", pid 5452, jiffies 4294944822 (age 65.652s) hex dump (first 32 bytes): 47 48 34 35 36 37 0a 00 00 00 00 00 00 00 00 00 GH4567.......... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] slab_post_alloc_hook+0x8c/0x3c0 [] __kmem_cache_alloc_node+0x184/0x240 [] kmalloc_trace+0x2e/0xc0 [] test_fw_run_batch_request+0x9d/0x180 [] kthread+0x10b/0x140 [] ret_from_fork+0x29/0x50 unreferenced object 0xffff9553c334f000 (size 1024): comm "test_firmware-2", pid 5453, jiffies 4294944822 (age 65.652s) hex dump (first 32 bytes): 47 48 34 35 36 37 0a 00 00 00 00 00 00 00 00 00 GH4567.......... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] slab_post_alloc_hook+0x8c/0x3c0 [] __kmem_cache_alloc_node+0x184/0x240 [] kmalloc_trace+0x2e/0xc0 [] test_fw_run_batch_request+0x9d/0x180 [] kthread+0x10b/0x140 [] ret_from_fork+0x29/0x50 unreferenced object 0xffff9553c3348400 (size 1024): comm "test_firmware-3", pid 5454, jiffies 4294944822 (age 65.652s) hex dump (first 32 bytes): 47 48 34 35 36 37 0a 00 00 00 00 00 00 00 00 00 GH4567.......... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] slab_post_alloc_hook+0x8c/0x3c0 [] __kmem_cache_alloc_node+0x184/0x240 [] kmalloc_trace+0x2e/0xc0 [] test_fw_run_batch_request+0x9d/0x180 [] kthread+0x10b/0x140 [] ret_from_fork+0x29/0x50 [root@pc-mtodorov firmware]# Note that the size 1024 corresponds to the size of the test firmware buffer. The actual number of the buffers leaked is around 70-110, depending on the test run. The cause of the leak is the following: request_partial_firmware_into_buf() and request_firmware_into_buf() provided firmware buffer isn't released on release_firmware(), we have allocated it and we are responsible for deallocating it manually. This is introduced in a number of context where previously only release_firmware() was called, which was insufficient. Reported-by: Mirsad Goran Todorovac Fixes: 7feebfa487b92 ("test_firmware: add support for request_firmware_into_buf") Cc: Greg Kroah-Hartman Cc: Dan Carpenter Cc: Takashi Iwai Cc: Luis Chamberlain Cc: Russ Weight Cc: Tianfei zhang Cc: Christophe JAILLET Cc: Zhengchao Shao Cc: Colin Ian King Cc: linux-kernel@vger.kernel.org Cc: Kees Cook Cc: Scott Branden Cc: Luis R. Rodriguez Cc: linux-kselftest@vger.kernel.org Cc: stable@vger.kernel.org # v5.4 Signed-off-by: Mirsad Goran Todorovac Link: https://lore.kernel.org/r/20230509084746.48259-3-mirsad.todorovac@alu.unizg.hr Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- lib/test_firmware.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 76550d2e2edc..581ee3fcdd5c 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -41,6 +41,7 @@ struct test_batched_req { bool sent; const struct firmware *fw; const char *name; + const char *fw_buf; struct completion completion; struct task_struct *task; struct device *dev; @@ -143,8 +144,14 @@ static void __test_release_all_firmware(void) for (i = 0; i < test_fw_config->num_requests; i++) { req = &test_fw_config->reqs[i]; - if (req->fw) + if (req->fw) { + if (req->fw_buf) { + kfree_const(req->fw_buf); + req->fw_buf = NULL; + } release_firmware(req->fw); + req->fw = NULL; + } } vfree(test_fw_config->reqs); @@ -589,6 +596,8 @@ static ssize_t trigger_request_store(struct device *dev, mutex_lock(&test_fw_mutex); release_firmware(test_firmware); + if (test_fw_config->reqs) + __test_release_all_firmware(); test_firmware = NULL; rc = request_firmware(&test_firmware, name, dev); if (rc) { @@ -689,6 +698,8 @@ static ssize_t trigger_async_request_store(struct device *dev, mutex_lock(&test_fw_mutex); release_firmware(test_firmware); test_firmware = NULL; + if (test_fw_config->reqs) + __test_release_all_firmware(); rc = request_firmware_nowait(THIS_MODULE, 1, name, dev, GFP_KERNEL, NULL, trigger_async_request_cb); if (rc) { @@ -731,6 +742,8 @@ static ssize_t trigger_custom_fallback_store(struct device *dev, mutex_lock(&test_fw_mutex); release_firmware(test_firmware); + if (test_fw_config->reqs) + __test_release_all_firmware(); test_firmware = NULL; rc = request_firmware_nowait(THIS_MODULE, FW_ACTION_NOHOTPLUG, name, dev, GFP_KERNEL, NULL, @@ -793,6 +806,8 @@ static int test_fw_run_batch_request(void *data) test_fw_config->buf_size); if (!req->fw) kfree(test_buf); + else + req->fw_buf = test_buf; } else { req->rc = test_fw_config->req_firmware(&req->fw, req->name, @@ -848,6 +863,7 @@ static ssize_t trigger_batched_requests_store(struct device *dev, req->fw = NULL; req->idx = i; req->name = test_fw_config->name; + req->fw_buf = NULL; req->dev = dev; init_completion(&req->completion); req->task = kthread_run(test_fw_run_batch_request, req, @@ -947,6 +963,7 @@ ssize_t trigger_batched_requests_async_store(struct device *dev, for (i = 0; i < test_fw_config->num_requests; i++) { req = &test_fw_config->reqs[i]; req->name = test_fw_config->name; + req->fw_buf = NULL; req->fw = NULL; req->idx = i; init_completion(&req->completion); From 3295dc04af33a3f1126a5dc9e276701b372c92b7 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 1 Jun 2023 18:19:19 -0700 Subject: [PATCH 3409/4345] KVM: x86: Account fastpath-only VM-Exits in vCPU stats commit 8b703a49c9df5e74870381ad7ba9c85d8a74ed2c upstream. Increment vcpu->stat.exits when handling a fastpath VM-Exit without going through any part of the "slow" path. Not bumping the exits stat can result in wildly misleading exit counts, e.g. if the primary reason the guest is exiting is to program the TSC deadline timer. Fixes: 404d5d7bff0d ("KVM: X86: Introduce more exit_fastpath_completion enum values") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230602011920.787844-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5fbae8cc0697..34670943f543 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1588,6 +1588,9 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type) allowed = !!test_bit(index - start, bitmap); break; } + + /* Note, VM-Exits that go down the "slow" path are accounted below. */ + ++vcpu->stat.exits; } out: From cb1cbe430e6738179b3a3062dec9cf3748ef39c1 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Thu, 8 Dec 2022 10:56:46 +0100 Subject: [PATCH 3410/4345] KEYS: asymmetric: Copy sig and digest in public_key_verify_signature() commit c3d03e8e35e005e1a614e51bb59053eeb5857f76 upstream. Commit ac4e97abce9b8 ("scatterlist: sg_set_buf() argument must be in linear mapping") checks that both the signature and the digest reside in the linear mapping area. However, more recently commit ba14a194a434c ("fork: Add generic vmalloced stack support") made it possible to move the stack in the vmalloc area, which is not contiguous, and thus not suitable for sg_set_buf() which needs adjacent pages. Always make a copy of the signature and digest in the same buffer used to store the key and its parameters, and pass them to sg_init_one(). Prefer it to conditionally doing the copy if necessary, to keep the code simple. The buffer allocated with kmalloc() is in the linear mapping area. Cc: stable@vger.kernel.org # 4.9.x Fixes: ba14a194a434 ("fork: Add generic vmalloced stack support") Link: https://lore.kernel.org/linux-integrity/Y4pIpxbjBdajymBJ@sol.localdomain/ Suggested-by: Eric Biggers Signed-off-by: Roberto Sassu Reviewed-by: Eric Biggers Tested-by: Stefan Berger Signed-off-by: Greg Kroah-Hartman --- crypto/asymmetric_keys/public_key.c | 38 ++++++++++++++++------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index cf9b7ac36202..bd713a214d7a 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -316,9 +316,10 @@ int public_key_verify_signature(const struct public_key *pkey, struct crypto_wait cwait; struct crypto_akcipher *tfm; struct akcipher_request *req; - struct scatterlist src_sg[2]; + struct scatterlist src_sg; char alg_name[CRYPTO_MAX_ALG_NAME]; - char *key, *ptr; + char *buf, *ptr; + size_t buf_len; int ret; pr_devel("==>%s()\n", __func__); @@ -342,34 +343,37 @@ int public_key_verify_signature(const struct public_key *pkey, if (!req) goto error_free_tfm; - key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen, - GFP_KERNEL); - if (!key) + buf_len = max_t(size_t, pkey->keylen + sizeof(u32) * 2 + pkey->paramlen, + sig->s_size + sig->digest_size); + + buf = kmalloc(buf_len, GFP_KERNEL); + if (!buf) goto error_free_req; - memcpy(key, pkey->key, pkey->keylen); - ptr = key + pkey->keylen; + memcpy(buf, pkey->key, pkey->keylen); + ptr = buf + pkey->keylen; ptr = pkey_pack_u32(ptr, pkey->algo); ptr = pkey_pack_u32(ptr, pkey->paramlen); memcpy(ptr, pkey->params, pkey->paramlen); if (pkey->key_is_private) - ret = crypto_akcipher_set_priv_key(tfm, key, pkey->keylen); + ret = crypto_akcipher_set_priv_key(tfm, buf, pkey->keylen); else - ret = crypto_akcipher_set_pub_key(tfm, key, pkey->keylen); + ret = crypto_akcipher_set_pub_key(tfm, buf, pkey->keylen); if (ret) - goto error_free_key; + goto error_free_buf; if (strcmp(pkey->pkey_algo, "sm2") == 0 && sig->data_size) { ret = cert_sig_digest_update(sig, tfm); if (ret) - goto error_free_key; + goto error_free_buf; } - sg_init_table(src_sg, 2); - sg_set_buf(&src_sg[0], sig->s, sig->s_size); - sg_set_buf(&src_sg[1], sig->digest, sig->digest_size); - akcipher_request_set_crypt(req, src_sg, NULL, sig->s_size, + memcpy(buf, sig->s, sig->s_size); + memcpy(buf + sig->s_size, sig->digest, sig->digest_size); + + sg_init_one(&src_sg, buf, sig->s_size + sig->digest_size); + akcipher_request_set_crypt(req, &src_sg, NULL, sig->s_size, sig->digest_size); crypto_init_wait(&cwait); akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | @@ -377,8 +381,8 @@ int public_key_verify_signature(const struct public_key *pkey, crypto_req_done, &cwait); ret = crypto_wait_req(crypto_akcipher_verify(req), &cwait); -error_free_key: - kfree(key); +error_free_buf: + kfree(buf); error_free_req: akcipher_request_free(req); error_free_tfm: From 608c1f20830c3a07c0a16886e465deba7280364d Mon Sep 17 00:00:00 2001 From: Jim Wylder Date: Wed, 17 May 2023 10:20:11 -0500 Subject: [PATCH 3411/4345] regmap: Account for register length when chunking commit 3981514180c987a79ea98f0ae06a7cbf58a9ac0f upstream. Currently, when regmap_raw_write() splits the data, it uses the max_raw_write value defined for the bus. For any bus that includes the target register address in the max_raw_write value, the chunked transmission will always exceed the maximum transmission length. To avoid this problem, subtract the length of the register and the padding from the maximum transmission. Signed-off-by: Jim Wylder --- drivers/base/regmap/regmap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 55a30afc14a0..2a3c3dfefdce 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1998,6 +1998,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, size_t val_count = val_len / val_bytes; size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; + size_t max_data = map->max_raw_write - map->format.reg_bytes - + map->format.pad_bytes; int ret, i; if (!val_count) @@ -2005,8 +2007,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, if (map->use_single_write) chunk_regs = 1; - else if (map->max_raw_write && val_len > map->max_raw_write) - chunk_regs = map->max_raw_write / val_bytes; + else if (map->max_raw_write && val_len > max_data) + chunk_regs = max_data / val_bytes; chunk_count = val_count / chunk_regs; chunk_bytes = chunk_regs * val_bytes; From d21e955de918821643c03fa93be581393cbcca4f Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Thu, 24 Nov 2022 14:55:34 +0100 Subject: [PATCH 3412/4345] tpm, tpm_tis: Request threaded interrupt handler MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 0c7e66e5fd69bf21034c9a9b081d7de7c3eb2cea upstream. The TIS interrupt handler at least has to read and write the interrupt status register. In case of SPI both operations result in a call to tpm_tis_spi_transfer() which uses the bus_lock_mutex of the spi device and thus must only be called from a sleepable context. To ensure this request a threaded interrupt handler. Signed-off-by: Lino Sanfilippo Tested-by: Michael Niewöhner Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm_tis_core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index d65fff4e2ebe..512c867495ea 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -764,8 +764,11 @@ static int tpm_tis_probe_irq_single(struct tpm_chip *chip, u32 intmask, int rc; u32 int_status; - if (devm_request_irq(chip->dev.parent, irq, tis_int_handler, flags, - dev_name(&chip->dev), chip) != 0) { + + rc = devm_request_threaded_irq(chip->dev.parent, irq, NULL, + tis_int_handler, IRQF_ONESHOT | flags, + dev_name(&chip->dev), chip); + if (rc) { dev_info(&chip->dev, "Unable to request irq: %d for probe\n", irq); return -1; From c759c9e4bf38312557cf192cc7eaf9c9dea9e1ec Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 4 Dec 2020 00:07:30 +0100 Subject: [PATCH 3413/4345] media: ti-vpe: cal: avoid FIELD_GET assertion commit d7a7d721064c548042b019cd0d4d62e0bb878d71 upstream. FIELD_GET() must only be used with a mask that is a compile-time constant: drivers/media/platform/ti-vpe/cal.h: In function 'cal_read_field': include/linux/compiler_types.h:320:38: error: call to '__compiletime_assert_247' declared with attribute error: FIELD_GET: mask is not constant include/linux/bitfield.h:46:3: note: in expansion of macro 'BUILD_BUG_ON_MSG' 46 | BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \ | ^~~~~~~~~~~~~~~~ drivers/media/platform/ti-vpe/cal.h:220:9: note: in expansion of macro 'FIELD_GET' 220 | return FIELD_GET(mask, cal_read(cal, offset)); | ^~~~~~~~~ The problem here is that the function is not always inlined. Mark it __always_inline to avoid the problem. Signed-off-by: Arnd Bergmann Reviewed-by: Laurent Pinchart Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Cc: Dan Carpenter Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/ti-vpe/cal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/ti-vpe/cal.h b/drivers/media/platform/ti-vpe/cal.h index 4123405ee0cf..20d07311d222 100644 --- a/drivers/media/platform/ti-vpe/cal.h +++ b/drivers/media/platform/ti-vpe/cal.h @@ -215,7 +215,7 @@ static inline void cal_write(struct cal_dev *cal, u32 offset, u32 val) iowrite32(val, cal->base + offset); } -static inline u32 cal_read_field(struct cal_dev *cal, u32 offset, u32 mask) +static __always_inline u32 cal_read_field(struct cal_dev *cal, u32 offset, u32 mask) { return FIELD_GET(mask, cal_read(cal, offset)); } From 6d6612f7f9768c8d58527767bf4c94f0f67acf06 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 27 Sep 2021 16:26:23 +0200 Subject: [PATCH 3414/4345] drm/rcar: stop using 'imply' for dependencies commit 42d95d1b3a9c649bf5ee881fee5938e00126479a upstream. The meaning of the 'imply' keyword has changed recently, and neither the old meaning (select the symbol if its dependencies are met) nor the new meaning (enable it by default, but let the user set any other setting) is what we want here. Work around this by adding two more Kconfig options that lead to the correct behavior: if DRM_RCAR_USE_CMM and DRM_RCAR_USE_LVDS are enabled, that portion of the driver becomes usable, and no configuration results in a link error. This avoids a link failure: arm-linux-gnueabi-ld: drivers/gpu/drm/rcar-du/rcar_du_crtc.o: in function `rcar_du_crtc_atomic_begin': rcar_du_crtc.c:(.text+0x1444): undefined reference to `rcar_cmm_setup' arm-linux-gnueabi-ld: drivers/gpu/drm/rcar-du/rcar_du_crtc.o: in function `rcar_du_crtc_atomic_enable': rcar_du_crtc.c:(.text+0x14d4): undefined reference to `rcar_cmm_enable' arm-linux-gnueabi-ld: rcar_du_crtc.c:(.text+0x1548): undefined reference to `rcar_cmm_setup' arm-linux-gnueabi-ld: drivers/gpu/drm/rcar-du/rcar_du_crtc.o: in function `rcar_du_crtc_atomic_disable': rcar_du_crtc.c:(.text+0x18b8): undefined reference to `rcar_cmm_disable' arm-linux-gnueabi-ld: drivers/gpu/drm/rcar-du/rcar_du_kms.o: in function `rcar_du_modeset_init': Link: https://lore.kernel.org/all/20200417155553.675905-5-arnd@arndb.de/ Signed-off-by: Arnd Bergmann Reviewed-by: Laurent Pinchart Reviewed-by: Randy Dunlap Signed-off-by: Laurent Pinchart Cc: Dan Carpenter Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/rcar-du/Kconfig | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig index b47e74421e34..3e588ddba245 100644 --- a/drivers/gpu/drm/rcar-du/Kconfig +++ b/drivers/gpu/drm/rcar-du/Kconfig @@ -4,8 +4,6 @@ config DRM_RCAR_DU depends on DRM && OF depends on ARM || ARM64 depends on ARCH_RENESAS || COMPILE_TEST - imply DRM_RCAR_CMM - imply DRM_RCAR_LVDS select DRM_KMS_HELPER select DRM_KMS_CMA_HELPER select DRM_GEM_CMA_HELPER @@ -14,13 +12,17 @@ config DRM_RCAR_DU Choose this option if you have an R-Car chipset. If M is selected the module will be called rcar-du-drm. -config DRM_RCAR_CMM - tristate "R-Car DU Color Management Module (CMM) Support" - depends on DRM && OF +config DRM_RCAR_USE_CMM + bool "R-Car DU Color Management Module (CMM) Support" depends on DRM_RCAR_DU + default DRM_RCAR_DU help Enable support for R-Car Color Management Module (CMM). +config DRM_RCAR_CMM + def_tristate DRM_RCAR_DU + depends on DRM_RCAR_USE_CMM + config DRM_RCAR_DW_HDMI tristate "R-Car Gen3 and RZ/G2 DU HDMI Encoder Support" depends on DRM && OF @@ -28,15 +30,20 @@ config DRM_RCAR_DW_HDMI help Enable support for R-Car Gen3 or RZ/G2 internal HDMI encoder. +config DRM_RCAR_USE_LVDS + bool "R-Car DU LVDS Encoder Support" + depends on DRM_BRIDGE && OF + default DRM_RCAR_DU + help + Enable support for the R-Car Display Unit embedded LVDS encoders. + config DRM_RCAR_LVDS - tristate "R-Car DU LVDS Encoder Support" - depends on DRM && DRM_BRIDGE && OF + def_tristate DRM_RCAR_DU + depends on DRM_RCAR_USE_LVDS select DRM_KMS_HELPER select DRM_PANEL select OF_FLATTREE select OF_OVERLAY - help - Enable support for the R-Car Display Unit embedded LVDS encoders. config DRM_RCAR_VSP bool "R-Car DU VSP Compositor Support" if ARM From a2cd7599b558d6c70c01880d470f6eedaf6a8f23 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 27 May 2023 15:34:30 +0200 Subject: [PATCH 3415/4345] scsi: dpt_i2o: Remove broken pass-through ioctl (I2OUSERCMD) adpt_i2o_passthru() takes a user-provided message and passes it through to the hardware with appropriate translation of addresses and message IDs. It has a number of bugs: - When a message requires scatter/gather, it doesn't verify that the offset to the scatter/gather list is less than the message size. - When a message requires scatter/gather, it overwrites the DMA addresses with the user-space virtual addresses before unmapping the DMA buffers. - It reads the message from user memory multiple times. This allows user-space to change the message and bypass validation. - It assumes that the message is at least 4 words long, but doesn't check that. I tried fixing these, but even the maintainer of the corresponding user-space in Debian doesn't have the hardware any more. Instead, remove the pass-through ioctl (I2OUSRCMD) and supporting code. There is no corresponding upstream commit, because this driver was removed upstream. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Fixes: 67af2b060e02 ("[SCSI] dpt_i2o: move from virt_to_bus/bus_to_virt ...") Signed-off-by: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/dpt_i2o.c | 274 ++--------------------------------------- drivers/scsi/dpti.h | 1 - 2 files changed, 8 insertions(+), 267 deletions(-) diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c index 4251212acbbe..85f4d6535154 100644 --- a/drivers/scsi/dpt_i2o.c +++ b/drivers/scsi/dpt_i2o.c @@ -582,51 +582,6 @@ static int adpt_show_info(struct seq_file *m, struct Scsi_Host *host) return 0; } -/* - * Turn a pointer to ioctl reply data into an u32 'context' - */ -static u32 adpt_ioctl_to_context(adpt_hba * pHba, void *reply) -{ -#if BITS_PER_LONG == 32 - return (u32)(unsigned long)reply; -#else - ulong flags = 0; - u32 nr, i; - - spin_lock_irqsave(pHba->host->host_lock, flags); - nr = ARRAY_SIZE(pHba->ioctl_reply_context); - for (i = 0; i < nr; i++) { - if (pHba->ioctl_reply_context[i] == NULL) { - pHba->ioctl_reply_context[i] = reply; - break; - } - } - spin_unlock_irqrestore(pHba->host->host_lock, flags); - if (i >= nr) { - printk(KERN_WARNING"%s: Too many outstanding " - "ioctl commands\n", pHba->name); - return (u32)-1; - } - - return i; -#endif -} - -/* - * Go from an u32 'context' to a pointer to ioctl reply data. - */ -static void *adpt_ioctl_from_context(adpt_hba *pHba, u32 context) -{ -#if BITS_PER_LONG == 32 - return (void *)(unsigned long)context; -#else - void *p = pHba->ioctl_reply_context[context]; - pHba->ioctl_reply_context[context] = NULL; - - return p; -#endif -} - /*=========================================================================== * Error Handling routines *=========================================================================== @@ -1648,208 +1603,6 @@ static int adpt_close(struct inode *inode, struct file *file) return 0; } - -static int adpt_i2o_passthru(adpt_hba* pHba, u32 __user *arg) -{ - u32 msg[MAX_MESSAGE_SIZE]; - u32* reply = NULL; - u32 size = 0; - u32 reply_size = 0; - u32 __user *user_msg = arg; - u32 __user * user_reply = NULL; - void **sg_list = NULL; - u32 sg_offset = 0; - u32 sg_count = 0; - int sg_index = 0; - u32 i = 0; - u32 rcode = 0; - void *p = NULL; - dma_addr_t addr; - ulong flags = 0; - - memset(&msg, 0, MAX_MESSAGE_SIZE*4); - // get user msg size in u32s - if(get_user(size, &user_msg[0])){ - return -EFAULT; - } - size = size>>16; - - user_reply = &user_msg[size]; - if(size > MAX_MESSAGE_SIZE){ - return -EFAULT; - } - size *= 4; // Convert to bytes - - /* Copy in the user's I2O command */ - if(copy_from_user(msg, user_msg, size)) { - return -EFAULT; - } - get_user(reply_size, &user_reply[0]); - reply_size = reply_size>>16; - if(reply_size > REPLY_FRAME_SIZE){ - reply_size = REPLY_FRAME_SIZE; - } - reply_size *= 4; - reply = kzalloc(REPLY_FRAME_SIZE*4, GFP_KERNEL); - if(reply == NULL) { - printk(KERN_WARNING"%s: Could not allocate reply buffer\n",pHba->name); - return -ENOMEM; - } - sg_offset = (msg[0]>>4)&0xf; - msg[2] = 0x40000000; // IOCTL context - msg[3] = adpt_ioctl_to_context(pHba, reply); - if (msg[3] == (u32)-1) { - rcode = -EBUSY; - goto free; - } - - sg_list = kcalloc(pHba->sg_tablesize, sizeof(*sg_list), GFP_KERNEL); - if (!sg_list) { - rcode = -ENOMEM; - goto free; - } - if(sg_offset) { - // TODO add 64 bit API - struct sg_simple_element *sg = (struct sg_simple_element*) (msg+sg_offset); - sg_count = (size - sg_offset*4) / sizeof(struct sg_simple_element); - if (sg_count > pHba->sg_tablesize){ - printk(KERN_DEBUG"%s:IOCTL SG List too large (%u)\n", pHba->name,sg_count); - rcode = -EINVAL; - goto free; - } - - for(i = 0; i < sg_count; i++) { - int sg_size; - - if (!(sg[i].flag_count & 0x10000000 /*I2O_SGL_FLAGS_SIMPLE_ADDRESS_ELEMENT*/)) { - printk(KERN_DEBUG"%s:Bad SG element %d - not simple (%x)\n",pHba->name,i, sg[i].flag_count); - rcode = -EINVAL; - goto cleanup; - } - sg_size = sg[i].flag_count & 0xffffff; - /* Allocate memory for the transfer */ - p = dma_alloc_coherent(&pHba->pDev->dev, sg_size, &addr, GFP_KERNEL); - if(!p) { - printk(KERN_DEBUG"%s: Could not allocate SG buffer - size = %d buffer number %d of %d\n", - pHba->name,sg_size,i,sg_count); - rcode = -ENOMEM; - goto cleanup; - } - sg_list[sg_index++] = p; // sglist indexed with input frame, not our internal frame. - /* Copy in the user's SG buffer if necessary */ - if(sg[i].flag_count & 0x04000000 /*I2O_SGL_FLAGS_DIR*/) { - // sg_simple_element API is 32 bit - if (copy_from_user(p,(void __user *)(ulong)sg[i].addr_bus, sg_size)) { - printk(KERN_DEBUG"%s: Could not copy SG buf %d FROM user\n",pHba->name,i); - rcode = -EFAULT; - goto cleanup; - } - } - /* sg_simple_element API is 32 bit, but addr < 4GB */ - sg[i].addr_bus = addr; - } - } - - do { - /* - * Stop any new commands from enterring the - * controller while processing the ioctl - */ - if (pHba->host) { - scsi_block_requests(pHba->host); - spin_lock_irqsave(pHba->host->host_lock, flags); - } - rcode = adpt_i2o_post_wait(pHba, msg, size, FOREVER); - if (rcode != 0) - printk("adpt_i2o_passthru: post wait failed %d %p\n", - rcode, reply); - if (pHba->host) { - spin_unlock_irqrestore(pHba->host->host_lock, flags); - scsi_unblock_requests(pHba->host); - } - } while (rcode == -ETIMEDOUT); - - if(rcode){ - goto cleanup; - } - - if(sg_offset) { - /* Copy back the Scatter Gather buffers back to user space */ - u32 j; - // TODO add 64 bit API - struct sg_simple_element* sg; - int sg_size; - - // re-acquire the original message to handle correctly the sg copy operation - memset(&msg, 0, MAX_MESSAGE_SIZE*4); - // get user msg size in u32s - if(get_user(size, &user_msg[0])){ - rcode = -EFAULT; - goto cleanup; - } - size = size>>16; - size *= 4; - if (size > MAX_MESSAGE_SIZE) { - rcode = -EINVAL; - goto cleanup; - } - /* Copy in the user's I2O command */ - if (copy_from_user (msg, user_msg, size)) { - rcode = -EFAULT; - goto cleanup; - } - sg_count = (size - sg_offset*4) / sizeof(struct sg_simple_element); - - // TODO add 64 bit API - sg = (struct sg_simple_element*)(msg + sg_offset); - for (j = 0; j < sg_count; j++) { - /* Copy out the SG list to user's buffer if necessary */ - if(! (sg[j].flag_count & 0x4000000 /*I2O_SGL_FLAGS_DIR*/)) { - sg_size = sg[j].flag_count & 0xffffff; - // sg_simple_element API is 32 bit - if (copy_to_user((void __user *)(ulong)sg[j].addr_bus,sg_list[j], sg_size)) { - printk(KERN_WARNING"%s: Could not copy %p TO user %x\n",pHba->name, sg_list[j], sg[j].addr_bus); - rcode = -EFAULT; - goto cleanup; - } - } - } - } - - /* Copy back the reply to user space */ - if (reply_size) { - // we wrote our own values for context - now restore the user supplied ones - if(copy_from_user(reply+2, user_msg+2, sizeof(u32)*2)) { - printk(KERN_WARNING"%s: Could not copy message context FROM user\n",pHba->name); - rcode = -EFAULT; - } - if(copy_to_user(user_reply, reply, reply_size)) { - printk(KERN_WARNING"%s: Could not copy reply TO user\n",pHba->name); - rcode = -EFAULT; - } - } - - -cleanup: - if (rcode != -ETIME && rcode != -EINTR) { - struct sg_simple_element *sg = - (struct sg_simple_element*) (msg +sg_offset); - while(sg_index) { - if(sg_list[--sg_index]) { - dma_free_coherent(&pHba->pDev->dev, - sg[sg_index].flag_count & 0xffffff, - sg_list[sg_index], - sg[sg_index].addr_bus); - } - } - } - -free: - kfree(sg_list); - kfree(reply); - return rcode; -} - #if defined __ia64__ static void adpt_ia64_info(sysInfo_S* si) { @@ -1976,8 +1729,6 @@ static int adpt_ioctl(struct inode *inode, struct file *file, uint cmd, ulong ar return -EFAULT; } break; - case I2OUSRCMD: - return adpt_i2o_passthru(pHba, argp); case DPT_CTRLINFO:{ drvrHBAinfo_S HbaInfo; @@ -2134,13 +1885,6 @@ static irqreturn_t adpt_isr(int irq, void *dev_id) adpt_send_nop(pHba, old_m); } context = readl(reply+8); - if(context & 0x40000000){ // IOCTL - void *p = adpt_ioctl_from_context(pHba, readl(reply+12)); - if( p != NULL) { - memcpy_fromio(p, reply, REPLY_FRAME_SIZE * 4); - } - // All IOCTLs will also be post wait - } if(context & 0x80000000){ // Post wait message status = readl(reply+16); if(status >> 24){ @@ -2148,16 +1892,14 @@ static irqreturn_t adpt_isr(int irq, void *dev_id) } else { status = I2O_POST_WAIT_OK; } - if(!(context & 0x40000000)) { - /* - * The request tag is one less than the command tag - * as the firmware might treat a 0 tag as invalid - */ - cmd = scsi_host_find_tag(pHba->host, - readl(reply + 12) - 1); - if(cmd != NULL) { - printk(KERN_WARNING"%s: Apparent SCSI cmd in Post Wait Context - cmd=%p context=%x\n", pHba->name, cmd, context); - } + /* + * The request tag is one less than the command tag + * as the firmware might treat a 0 tag as invalid + */ + cmd = scsi_host_find_tag(pHba->host, + readl(reply + 12) - 1); + if(cmd != NULL) { + printk(KERN_WARNING"%s: Apparent SCSI cmd in Post Wait Context - cmd=%p context=%x\n", pHba->name, cmd, context); } adpt_i2o_post_wait_complete(context, status); } else { // SCSI message diff --git a/drivers/scsi/dpti.h b/drivers/scsi/dpti.h index 8a079e8d7f65..0565533e8095 100644 --- a/drivers/scsi/dpti.h +++ b/drivers/scsi/dpti.h @@ -248,7 +248,6 @@ typedef struct _adpt_hba { void __iomem *FwDebugBLEDflag_P;// Virtual Addr Of FW Debug BLED void __iomem *FwDebugBLEDvalue_P;// Virtual Addr Of FW Debug BLED u32 FwDebugFlags; - u32 *ioctl_reply_context[4]; } adpt_hba; struct sg_simple_element { From d21a20f4421db37310c624845a38605436b81fcb Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 27 May 2023 15:52:48 +0200 Subject: [PATCH 3416/4345] scsi: dpt_i2o: Do not process completions with invalid addresses adpt_isr() reads reply addresses from a hardware register, which should always be within the DMA address range of the device's pool of reply address buffers. In case the address is out of range, it tries to muddle on, converting to a virtual address using bus_to_virt(). bus_to_virt() does not take DMA addresses, and it doesn't make sense to try to handle the completion in this case. Ignore it and continue looping to service the interrupt. If a completion has been lost then the SCSI core should eventually time-out and trigger a reset. There is no corresponding upstream commit, because this driver was removed upstream. Fixes: 67af2b060e02 ("[SCSI] dpt_i2o: move from virt_to_bus/bus_to_virt ...") Signed-off-by: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/Kconfig | 2 +- drivers/scsi/dpt_i2o.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 701b61ec76ee..6524e1fe54d2 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -444,7 +444,7 @@ config SCSI_MVUMI config SCSI_DPT_I2O tristate "Adaptec I2O RAID support " - depends on SCSI && PCI && VIRT_TO_BUS + depends on SCSI && PCI help This driver supports all of Adaptec's I2O based RAID controllers as well as the DPT SmartRaid V cards. This is an Adaptec maintained diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c index 85f4d6535154..43ec5657a935 100644 --- a/drivers/scsi/dpt_i2o.c +++ b/drivers/scsi/dpt_i2o.c @@ -56,7 +56,7 @@ MODULE_DESCRIPTION("Adaptec I2O RAID Driver"); #include #include /* for boot_cpu_data */ -#include /* for virt_to_bus, etc. */ +#include #include #include @@ -1865,7 +1865,7 @@ static irqreturn_t adpt_isr(int irq, void *dev_id) } else { /* Ick, we should *never* be here */ printk(KERN_ERR "dpti: reply frame not from pool\n"); - reply = (u8 *)bus_to_virt(m); + continue; } if (readl(reply) & MSG_FAIL) { From 1f988ce6e44f0f8222c366804144f9288fdc6552 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 6 Apr 2021 15:49:47 -0700 Subject: [PATCH 3417/4345] crypto: ccp: Reject SEV commands with mismatching command buffer commit d5760dee127bf6f390b05e747369d7c37ae1a7b8 upstream. WARN on and reject SEV commands that provide a valid data pointer, but do not have a known, non-zero length. And conversely, reject commands that take a command buffer but none is provided (data is null). Aside from sanity checking input, disallowing a non-null pointer without a non-zero size will allow a future patch to cleanly handle vmalloc'd data by copying the data to an internal __pa() friendly buffer. Note, this also effectively prevents callers from using commands that have a non-zero length and are not known to the kernel. This is not an explicit goal, but arguably the side effect is a good thing from the kernel's perspective. Cc: Brijesh Singh Cc: Borislav Petkov Cc: Tom Lendacky Signed-off-by: Sean Christopherson Message-Id: <20210406224952.4177376-4-seanjc@google.com> Reviewed-by: Brijesh Singh Acked-by: Tom Lendacky Signed-off-by: Paolo Bonzini Cc: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/ccp/sev-dev.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 856d867f46eb..0286b6d5de17 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -156,6 +156,7 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) struct sev_device *sev; unsigned int phys_lsb, phys_msb; unsigned int reg, ret = 0; + int buf_len; if (!psp || !psp->sev_data) return -ENODEV; @@ -165,6 +166,10 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) sev = psp->sev_data; + buf_len = sev_cmd_buffer_len(cmd); + if (WARN_ON_ONCE(!data != !buf_len)) + return -EINVAL; + if (data && WARN_ON_ONCE(!virt_addr_valid(data))) return -EINVAL; @@ -176,7 +181,7 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) cmd, phys_msb, phys_lsb, psp_timeout); print_hex_dump_debug("(in): ", DUMP_PREFIX_OFFSET, 16, 2, data, - sev_cmd_buffer_len(cmd), false); + buf_len, false); iowrite32(phys_lsb, sev->io_regs + sev->vdata->cmdbuff_addr_lo_reg); iowrite32(phys_msb, sev->io_regs + sev->vdata->cmdbuff_addr_hi_reg); @@ -212,7 +217,7 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) } print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, - sev_cmd_buffer_len(cmd), false); + buf_len, false); return ret; } From 81df7153f011279ab2e6daad156776d234f9db0a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 6 Apr 2021 15:49:48 -0700 Subject: [PATCH 3418/4345] crypto: ccp: Play nice with vmalloc'd memory for SEV command structs commit 8347b99473a313be6549a5b940bc3c56a71be81c upstream. Copy the incoming @data comman to an internal buffer so that callers can put SEV command buffers on the stack without running afoul of CONFIG_VMAP_STACK=y, i.e. without bombing on vmalloc'd pointers. As of today, the largest supported command takes a 68 byte buffer, i.e. pretty much every command can be put on the stack. Because sev_cmd_mutex is held for the entirety of a transaction, only a single bounce buffer is required. Use the internal buffer unconditionally, as the majority of in-kernel users will soon switch to using the stack. At that point, checking virt_addr_valid() becomes (negligible) overhead in most cases, and supporting both paths slightly increases complexity. Since the commands are all quite small, the cost of the copies is insignificant compared to the latency of communicating with the PSP. Allocate a full page for the buffer as opportunistic preparation for SEV-SNP, which requires the command buffer to be in firmware state for commands that trigger memory writes from the PSP firmware. Using a full page now will allow SEV-SNP support to simply transition the page as needed. Cc: Brijesh Singh Cc: Borislav Petkov Cc: Tom Lendacky Cc: Christophe Leroy Signed-off-by: Sean Christopherson Message-Id: <20210406224952.4177376-5-seanjc@google.com> Reviewed-by: Brijesh Singh Acked-by: Tom Lendacky Signed-off-by: Paolo Bonzini Cc: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/ccp/sev-dev.c | 28 +++++++++++++++++++++++----- drivers/crypto/ccp/sev-dev.h | 2 ++ 2 files changed, 25 insertions(+), 5 deletions(-) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 0286b6d5de17..8e2672ec6e03 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -170,12 +170,17 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) if (WARN_ON_ONCE(!data != !buf_len)) return -EINVAL; - if (data && WARN_ON_ONCE(!virt_addr_valid(data))) - return -EINVAL; + /* + * Copy the incoming data to driver's scratch buffer as __pa() will not + * work for some memory, e.g. vmalloc'd addresses, and @data may not be + * physically contiguous. + */ + if (data) + memcpy(sev->cmd_buf, data, buf_len); /* Get the physical address of the command buffer */ - phys_lsb = data ? lower_32_bits(__psp_pa(data)) : 0; - phys_msb = data ? upper_32_bits(__psp_pa(data)) : 0; + phys_lsb = data ? lower_32_bits(__psp_pa(sev->cmd_buf)) : 0; + phys_msb = data ? upper_32_bits(__psp_pa(sev->cmd_buf)) : 0; dev_dbg(sev->dev, "sev command id %#x buffer 0x%08x%08x timeout %us\n", cmd, phys_msb, phys_lsb, psp_timeout); @@ -219,6 +224,13 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, buf_len, false); + /* + * Copy potential output from the PSP back to data. Do this even on + * failure in case the caller wants to glean something from the error. + */ + if (data) + memcpy(data, sev->cmd_buf, buf_len); + return ret; } @@ -979,6 +991,10 @@ int sev_dev_init(struct psp_device *psp) if (!sev) goto e_err; + sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 0); + if (!sev->cmd_buf) + goto e_sev; + psp->sev_data = sev; sev->dev = dev; @@ -990,7 +1006,7 @@ int sev_dev_init(struct psp_device *psp) if (!sev->vdata) { ret = -ENODEV; dev_err(dev, "sev: missing driver data\n"); - goto e_sev; + goto e_buf; } psp_set_sev_irq_handler(psp, sev_irq_handler, sev); @@ -1005,6 +1021,8 @@ int sev_dev_init(struct psp_device *psp) e_irq: psp_clear_sev_irq_handler(psp); +e_buf: + devm_free_pages(dev, (unsigned long)sev->cmd_buf); e_sev: devm_kfree(dev, sev); e_err: diff --git a/drivers/crypto/ccp/sev-dev.h b/drivers/crypto/ccp/sev-dev.h index 3b0cd0f854df..0fd21433f627 100644 --- a/drivers/crypto/ccp/sev-dev.h +++ b/drivers/crypto/ccp/sev-dev.h @@ -51,6 +51,8 @@ struct sev_device { u8 api_major; u8 api_minor; u8 build; + + void *cmd_buf; }; int sev_dev_init(struct psp_device *psp); From 4f8356ab74dde51d17d75eb18abd75c95968d242 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Sun, 28 May 2023 19:35:30 +0200 Subject: [PATCH 3419/4345] selftests: mptcp: diag: skip if MPTCP is not supported commit 46565acdd29facbf418a11e4a3791b3c8967308d upstream. Selftests are supposed to run on any kernels, including the old ones not supporting MPTCP. A new check is then added to make sure MPTCP is supported. If not, the test stops and is marked as "skipped". Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: df62f2ec3df6 ("selftests/mptcp: add diag interface tests") Cc: stable@vger.kernel.org Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/mptcp/diag.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 39edce4f541c..34577d469f58 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns="ns1-$rndh" ksft_skip=4 @@ -28,6 +30,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" From 1a6db1f927244c7695d17c017940836637450eb9 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Sun, 28 May 2023 19:35:31 +0200 Subject: [PATCH 3420/4345] selftests: mptcp: simult flows: skip if MPTCP is not supported commit 9161f21c74a1a0e7bb39eb84ea0c86b23c92fc87 upstream. Selftests are supposed to run on any kernels, including the old ones not supporting MPTCP. A new check is then added to make sure MPTCP is supported. If not, the test stops and is marked as "skipped". Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 1a418cb8e888 ("mptcp: simult flow self-tests") Cc: stable@vger.kernel.org Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/mptcp/simult_flows.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 8fcb28927818..b51afba244be 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns1="ns1-$rndh" ns2="ns2-$rndh" @@ -31,6 +33,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" From 92450a1eaa9e570d296bf86e9719a95ebe853f18 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Sun, 28 May 2023 19:35:29 +0200 Subject: [PATCH 3421/4345] selftests: mptcp: join: skip if MPTCP is not supported commit 715c78a82e00f848f99ef76e6f6b89216ccba268 upstream. Selftests are supposed to run on any kernels, including the old ones not supporting MPTCP. A new check is then added to make sure MPTCP is supported. If not, the test stops and is marked as "skipped". Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: b08fbf241064 ("selftests: add test-cases for MPTCP MP_JOIN") Cc: stable@vger.kernel.org Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 08f53d86dedc..94b15bb28e11 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sout="" @@ -88,6 +90,8 @@ for arg in "$@"; do fi done +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" From 2c0ea7a06db5268085a5bd5044cedce6c950ad87 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 26 May 2023 23:57:29 -0400 Subject: [PATCH 3422/4345] ext4: enable the lazy init thread when remounting read/write commit eb1f822c76beeaa76ab8b6737ab9dc9f9798408c upstream. In commit a44be64bbecb ("ext4: don't clear SB_RDONLY when remounting r/w until quota is re-enabled") we defer clearing tyhe SB_RDONLY flag in struct super. However, we didn't defer when we checked sb_rdonly() to determine the lazy itable init thread should be enabled, with the next result that the lazy inode table initialization would not be properly started. This can cause generic/231 to fail in ext4's nojournal mode. Fix this by moving when we decide to start or stop the lazy itable init thread to after we clear the SB_RDONLY flag when we are remounting the file system read/write. Fixes a44be64bbecb ("ext4: don't clear SB_RDONLY when remounting r/w until...") Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20230527035729.1001605-1-tytso@mit.edu Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/super.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d89750e90bc4..f72896384dbc 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6005,18 +6005,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } } - /* - * Reinitialize lazy itable initialization thread based on - * current settings - */ - if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) - ext4_unregister_li_request(sb); - else { - ext4_group_t first_not_zeroed; - first_not_zeroed = ext4_has_uninit_itable(sb); - ext4_register_li_request(sb, first_not_zeroed); - } - /* * Handle creation of system zone data early because it can fail. * Releasing of existing data is done when we are sure remount will @@ -6054,6 +6042,18 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (enable_rw) sb->s_flags &= ~SB_RDONLY; + /* + * Reinitialize lazy itable initialization thread based on + * current settings + */ + if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) + ext4_unregister_li_request(sb); + else { + ext4_group_t first_not_zeroed; + first_not_zeroed = ext4_has_uninit_itable(sb); + ext4_register_li_request(sb, first_not_zeroed); + } + if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); From 842156dc0aad51937b934c5eff0572bdd6b4ab85 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Aug 2022 16:27:13 +0200 Subject: [PATCH 3423/4345] ARM: defconfig: drop CONFIG_DRM_RCAR_LVDS commit 1441a15dd49616bd9dd4c25a018b0508cdada576 upstream. This is now a hidden symbol, so just drop the defconfig line. Fixes: 42d95d1b3a9c ("drm/rcar: stop using 'imply' for dependencies") Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- arch/arm/configs/multi_v7_defconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index a611b0c1e540..07b7a2b76cb4 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -672,7 +672,6 @@ CONFIG_DRM_IMX_LDB=m CONFIG_DRM_IMX_HDMI=m CONFIG_DRM_ATMEL_HLCDC=m CONFIG_DRM_RCAR_DU=m -CONFIG_DRM_RCAR_LVDS=y CONFIG_DRM_SUN4I=m CONFIG_DRM_MSM=m CONFIG_DRM_FSL_DCU=m From 7356714b95aa6b186430289090a7fe5bdff2cf18 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 9 Jun 2023 10:30:19 +0200 Subject: [PATCH 3424/4345] Linux 5.10.183 Link: https://lore.kernel.org/r/20230607200900.915613242@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Shuah Khan Tested-by: Chris Paterson (CIP) Tested-by: Linux Kernel Functional Testing Tested-by: Salvatore Bonaccorso Tested-by: Guenter Roeck Tested-by: Sudip Mukherjee Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 209d5ae9ddb5..28115681fffd 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 182 +SUBLEVEL = 183 EXTRAVERSION = NAME = Dare mighty things From b82903573e481f61ea5d21812d6a2c778cd1119f Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 8 Mar 2023 20:40:43 +0000 Subject: [PATCH 3425/4345] FROMGIT: pstore: Revert pmsg_lock back to a normal mutex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 76d62f24db07f22ccf9bc18ca793c27d4ebef721. So while priority inversion on the pmsg_lock is an occasional problem that an rt_mutex would help with, in uses where logging is writing to pmsg heavily from multiple threads, the pmsg_lock can be heavily contended. After this change landed, it was reported that cases where the mutex locking overhead was commonly adding on the order of 10s of usecs delay had suddenly jumped to ~msec delay with rtmutex. It seems the slight differences in the locks under this level of contention causes the normal mutexes to utilize the spinning optimizations, while the rtmutexes end up in the sleeping slowpath (which allows additional threads to pile on trying to take the lock). In this case, it devolves to a worse case senerio where the lock acquisition and scheduling overhead dominates, and each thread is waiting on the order of ~ms to do ~us of work. Obviously, having tons of threads all contending on a single lock for logging is non-optimal, so the proper fix is probably reworking pstore pmsg to have per-cpu buffers so we don't have contention. Additionally, Steven Rostedt has provided some furhter optimizations for rtmutexes that improves the rtmutex spinning path, but at least in my testing, I still see the test tripping into the sleeping path on rtmutexes while utilizing the spinning path with mutexes. But in the short term, lets revert the change to the rt_mutex and go back to normal mutexes to avoid a potentially major performance regression. And we can work on optimizations to both rtmutexes and finer-grained locking for pstore pmsg in the future. Cc: Wei Wang Cc: Midas Chien Cc: "Chunhui Li (李春辉)" Cc: Steven Rostedt Cc: Kees Cook Cc: Anton Vorontsov Cc: "Guilherme G. Piccoli" Cc: Tony Luck Cc: kernel-team@android.com Fixes: 76d62f24db07 ("pstore: Switch pmsg_lock to an rt_mutex to avoid priority inversion") Reported-by: "Chunhui Li (李春辉)" Signed-off-by: John Stultz Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230308204043.2061631-1-jstultz@google.com Bug: 271041816 Bug: 272453930 (cherry picked from commit 5239a89b06d6b199f133bf0ffea421683187f257 https://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/pstore ) Change-Id: Iadf30bcbf5ba3895dd4af8c15c3a8aecf4301acb Signed-off-by: John Stultz (cherry picked from commit 64c66caa8f1f2412377a8d6c75a73da1234bee0d) --- fs/pstore/pmsg.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index 18cf94b597e0..d8542ec2f38c 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -7,10 +7,9 @@ #include #include #include -#include #include "internal.h" -static DEFINE_RT_MUTEX(pmsg_lock); +static DEFINE_MUTEX(pmsg_lock); static ssize_t write_pmsg(struct file *file, const char __user *buf, size_t count, loff_t *ppos) @@ -29,9 +28,9 @@ static ssize_t write_pmsg(struct file *file, const char __user *buf, if (!access_ok(buf, count)) return -EFAULT; - rt_mutex_lock(&pmsg_lock); + mutex_lock(&pmsg_lock); ret = psinfo->write_user(&record, buf); - rt_mutex_unlock(&pmsg_lock); + mutex_unlock(&pmsg_lock); return ret ? ret : count; } From 708d51e22a10a68c782a5d1a9b3d25b35b9659e6 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Mon, 13 Mar 2023 22:43:25 +0800 Subject: [PATCH 3426/4345] UPSTREAM: 9p/xen : Fix use after free bug in xen_9pfs_front_remove due to race condition [ Upstream commit ea4f1009408efb4989a0f139b70fb338e7f687d0 ] In xen_9pfs_front_probe, it calls xen_9pfs_front_alloc_dataring to init priv->rings and bound &ring->work with p9_xen_response. When it calls xen_9pfs_front_event_handler to handle IRQ requests, it will finally call schedule_work to start the work. When we call xen_9pfs_front_remove to remove the driver, there may be a sequence as follows: Fix it by finishing the work before cleanup in xen_9pfs_front_free. Note that, this bug is found by static analysis, which might be false positive. CPU0 CPU1 |p9_xen_response xen_9pfs_front_remove| xen_9pfs_front_free| kfree(priv) | //free priv | |p9_tag_lookup |//use priv->client Bug: 284409180 Fixes: 71ebd71921e4 ("xen/9pfs: connect to the backend") Signed-off-by: Zheng Wang Reviewed-by: Michal Swiatkowski Signed-off-by: Eric Van Hensbergen Signed-off-by: Sasha Levin (cherry picked from commit 9266e939d76279d8710196d86215ba2be6345041) Signed-off-by: Lee Jones Change-Id: I3a50acfe9957e0140e01d17f4d766532ec5670e0 --- net/9p/trans_xen.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 220e8f4ac0cf..da056170849b 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -300,6 +300,10 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) write_unlock(&xen_9pfs_lock); for (i = 0; i < priv->num_rings; i++) { + struct xen_9pfs_dataring *ring = &priv->rings[i]; + + cancel_work_sync(&ring->work); + if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) From 17bbc533f8f3bdadfe82a153b854bed397bcaa19 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 20 Apr 2023 08:27:18 +0100 Subject: [PATCH 3427/4345] UPSTREAM: mailbox: mailbox-test: Fix potential double-free in mbox_test_message_write() [ Upstream commit 2d1e952a2b8e5e92d8d55ac88a7cf7ca5ea591ad ] If a user can make copy_from_user() fail, there is a potential for UAF/DF due to a lack of locking around the allocation, use and freeing of the data buffers. This issue is not theoretical. I managed to author a POC for it: BUG: KASAN: double-free in kfree+0x5c/0xac Free of addr ffff29280be5de00 by task poc/356 CPU: 1 PID: 356 Comm: poc Not tainted 6.1.0-00001-g961aa6552c04-dirty #20 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace.part.0+0xe0/0xf0 show_stack+0x18/0x40 dump_stack_lvl+0x64/0x80 print_report+0x188/0x48c kasan_report_invalid_free+0xa0/0xc0 ____kasan_slab_free+0x174/0x1b0 __kasan_slab_free+0x18/0x24 __kmem_cache_free+0x130/0x2e0 kfree+0x5c/0xac mbox_test_message_write+0x208/0x29c full_proxy_write+0x90/0xf0 vfs_write+0x154/0x440 ksys_write+0xcc/0x180 __arm64_sys_write+0x44/0x60 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x40/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xf4/0x120 el0t_64_sync+0x18c/0x190 Allocated by task 356: kasan_save_stack+0x3c/0x70 kasan_set_track+0x2c/0x40 kasan_save_alloc_info+0x24/0x34 __kasan_kmalloc+0xb8/0xc0 kmalloc_trace+0x58/0x70 mbox_test_message_write+0x6c/0x29c full_proxy_write+0x90/0xf0 vfs_write+0x154/0x440 ksys_write+0xcc/0x180 __arm64_sys_write+0x44/0x60 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x40/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xf4/0x120 el0t_64_sync+0x18c/0x190 Freed by task 357: kasan_save_stack+0x3c/0x70 kasan_set_track+0x2c/0x40 kasan_save_free_info+0x38/0x5c ____kasan_slab_free+0x13c/0x1b0 __kasan_slab_free+0x18/0x24 __kmem_cache_free+0x130/0x2e0 kfree+0x5c/0xac mbox_test_message_write+0x208/0x29c full_proxy_write+0x90/0xf0 vfs_write+0x154/0x440 ksys_write+0xcc/0x180 __arm64_sys_write+0x44/0x60 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x40/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xf4/0x120 el0t_64_sync+0x18c/0x190 Bug: 275340532 Signed-off-by: Lee Jones Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin (cherry picked from commit cad1abbe488dfd149499e492344c03b87bb0b08c) Signed-off-by: Lee Jones Change-Id: I79753a9a63d8b04e139eaaeb9435bf1d05d38892 --- drivers/mailbox/mailbox-test.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 4555d678fadd..6dd5b9614452 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -38,6 +39,7 @@ struct mbox_test_device { char *signal; char *message; spinlock_t lock; + struct mutex mutex; wait_queue_head_t waitq; struct fasync_struct *async_queue; struct dentry *root_debugfs_dir; @@ -110,6 +112,8 @@ static ssize_t mbox_test_message_write(struct file *filp, return -EINVAL; } + mutex_lock(&tdev->mutex); + tdev->message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); if (!tdev->message) return -ENOMEM; @@ -144,6 +148,8 @@ out: kfree(tdev->message); tdev->signal = NULL; + mutex_unlock(&tdev->mutex); + return ret < 0 ? ret : count; } @@ -392,6 +398,7 @@ static int mbox_test_probe(struct platform_device *pdev) platform_set_drvdata(pdev, tdev); spin_lock_init(&tdev->lock); + mutex_init(&tdev->mutex); if (tdev->rx_channel) { tdev->rx_buffer = devm_kzalloc(&pdev->dev, From 0a52039fcbba79985a4e8b4b5a38fc134881c2a8 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 5 May 2023 12:22:09 +0300 Subject: [PATCH 3428/4345] UPSTREAM: mailbox: mailbox-test: fix a locking issue in mbox_test_message_write() [ Upstream commit 8fe72b76db79d694858e872370df49676bc3be8c ] There was a bug where this code forgot to unlock the tdev->mutex if the kzalloc() failed. Fix this issue, by moving the allocation outside the lock. Bug: 275340532 Fixes: 2d1e952a2b8e ("mailbox: mailbox-test: Fix potential double-free in mbox_test_message_write()") Signed-off-by: Dan Carpenter Reviewed-by: Lee Jones Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin (cherry picked from commit 7d233f93594f0d9afe44e9409131a8d6ad4f593c) Signed-off-by: Lee Jones Change-Id: I7a4a1bf06abbb2092aceb72610e3f894b2bfbf0f --- drivers/mailbox/mailbox-test.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 6dd5b9614452..abcee58e851c 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -97,6 +97,7 @@ static ssize_t mbox_test_message_write(struct file *filp, size_t count, loff_t *ppos) { struct mbox_test_device *tdev = filp->private_data; + char *message; void *data; int ret; @@ -112,12 +113,13 @@ static ssize_t mbox_test_message_write(struct file *filp, return -EINVAL; } - mutex_lock(&tdev->mutex); - - tdev->message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); - if (!tdev->message) + message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); + if (!message) return -ENOMEM; + mutex_lock(&tdev->mutex); + + tdev->message = message; ret = copy_from_user(tdev->message, userbuf, count); if (ret) { ret = -EFAULT; From c6ae8be4e6f0aff05ae186a10e2d6a5314bec733 Mon Sep 17 00:00:00 2001 From: Kyongho Cho Date: Mon, 12 Jun 2023 09:45:30 -0700 Subject: [PATCH 3429/4345] ANDROID: GKI: update symbol list for exynos Leaf changes summary: 3 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 3 Added functions Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 0 Added variable 3 Added functions: [A] 'function void copy_highpage(page*, page*)' [A] 'function void ttm_bo_unmap_virtual(ttm_buffer_object*)' [A] 'function int ttm_bo_wait(ttm_buffer_object*, bool, bool)' Bug: 286912592 Change-Id: I97371458327427fffef390154f817149a3120cbd Signed-off-by: Kyongho Cho --- android/abi_gki_aarch64.xml | 162 ++++++++++++++++++--------------- android/abi_gki_aarch64_exynos | 3 + 2 files changed, 93 insertions(+), 72 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 878779269b2b..ef03b0c13e9b 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -1300,6 +1300,7 @@ + @@ -5581,7 +5582,9 @@ + + @@ -122097,12 +122100,12 @@ - - - - - - + + + + + + @@ -124529,6 +124532,11 @@ + + + + + @@ -130870,10 +130878,10 @@ - - - - + + + + @@ -131506,10 +131514,10 @@ - - - - + + + + @@ -141682,12 +141690,12 @@ - - - - - - + + + + + + @@ -146687,12 +146695,22 @@ + + + + + + + + + + @@ -147456,11 +147474,11 @@ - - - - - + + + + + @@ -147642,13 +147660,13 @@ - - + + - - - + + + @@ -147817,8 +147835,8 @@ - - + + @@ -147981,8 +147999,8 @@ - - + + @@ -147994,9 +148012,9 @@ - - - + + + @@ -148011,8 +148029,8 @@ - - + + @@ -148052,7 +148070,7 @@ - + @@ -148172,10 +148190,10 @@ - - - - + + + + @@ -148386,9 +148404,9 @@ - - - + + + @@ -149842,22 +149860,22 @@ - - - - + + + + - - - - + + + + - - - - + + + + @@ -149928,23 +149946,23 @@ - - - - + + + + - - - - + + + + - - - - - + + + + + diff --git a/android/abi_gki_aarch64_exynos b/android/abi_gki_aarch64_exynos index 5f0526297f1c..c64082bb95b0 100644 --- a/android/abi_gki_aarch64_exynos +++ b/android/abi_gki_aarch64_exynos @@ -172,6 +172,7 @@ __const_udelay consume_skb contig_page_data + copy_highpage __cpu_active_mask cpu_all_bits cpu_bit_bitmap @@ -2114,7 +2115,9 @@ ttm_bo_move_ttm ttm_bo_put ttm_bo_unlock_delayed_workqueue + ttm_bo_unmap_virtual ttm_bo_validate + ttm_bo_wait ttm_dma_page_alloc_debugfs ttm_dma_populate ttm_dma_tt_fini From 552009b284ada00b6787c2bdba8cd60deaba63a7 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 17 May 2023 13:38:08 +0000 Subject: [PATCH 3430/4345] UPSTREAM: net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize commit 7e01c7f7046efc2c7c192c3619db43292b98e997 upstream. Currently in cdc_ncm_check_tx_max(), if dwNtbOutMaxSize is lower than the calculated "min" value, but greater than zero, the logic sets tx_max to dwNtbOutMaxSize. This is then used to allocate a new SKB in cdc_ncm_fill_tx_frame() where all the data is handled. For small values of dwNtbOutMaxSize the memory allocated during alloc_skb(dwNtbOutMaxSize, GFP_ATOMIC) will have the same size, due to how size is aligned at alloc time: size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); Thus we hit the same bug that we tried to squash with commit 2be6d4d16a084 ("net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero") Low values of dwNtbOutMaxSize do not cause an issue presently because at alloc_skb() time more memory (512b) is allocated than required for the SKB headers alone (320b), leaving some space (512b - 320b = 192b) for CDC data (172b). However, if more elements (for example 3 x u64 = [24b]) were added to one of the SKB header structs, say 'struct skb_shared_info', increasing its original size (320b [320b aligned]) to something larger (344b [384b aligned]), then suddenly the CDC data (172b) no longer fits in the spare SKB data area (512b - 384b = 128b). Consequently the SKB bounds checking semantics fails and panics: skbuff: skb_over_panic: text:ffffffff831f755b len:184 put:172 head:ffff88811f1c6c00 data:ffff88811f1c6c00 tail:0xb8 end:0x80 dev: ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:113! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 57 Comm: kworker/0:2 Not tainted 5.15.106-syzkaller-00249-g19c0ed55a470 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023 Workqueue: mld mld_ifc_work RIP: 0010:skb_panic net/core/skbuff.c:113 [inline] RIP: 0010:skb_over_panic+0x14c/0x150 net/core/skbuff.c:118 [snip] Call Trace: skb_put+0x151/0x210 net/core/skbuff.c:2047 skb_put_zero include/linux/skbuff.h:2422 [inline] cdc_ncm_ndp16 drivers/net/usb/cdc_ncm.c:1131 [inline] cdc_ncm_fill_tx_frame+0x11ab/0x3da0 drivers/net/usb/cdc_ncm.c:1308 cdc_ncm_tx_fixup+0xa3/0x100 Deal with too low values of dwNtbOutMaxSize, clamp it in the range [USB_CDC_NCM_NTB_MIN_OUT_SIZE, CDC_NCM_NTB_MAX_SIZE_TX]. We ensure enough data space is allocated to handle CDC data by making sure dwNtbOutMaxSize is not smaller than USB_CDC_NCM_NTB_MIN_OUT_SIZE. Fixes: 289507d3364f ("net: cdc_ncm: use sysfs for rx/tx aggregation tuning") Cc: stable@vger.kernel.org Reported-by: syzbot+9f575a1f15fc0c01ed69@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=b982f1059506db48409d Link: https://lore.kernel.org/all/20211202143437.1411410-1-lee.jones@linaro.org/ Signed-off-by: Tudor Ambarus Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230517133808.1873695-2-tudor.ambarus@linaro.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman Bug: 281604646 Bug: 281606231 Change-Id: Ic1d912e7bf2ba53620eb8293b68ec6046422e047 Signed-off-by: Tudor Ambarus --- drivers/net/usb/cdc_ncm.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 913d91381f23..73455643acba 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -180,9 +180,12 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx) else min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32); - max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize)); - if (max == 0) + if (le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) == 0) max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */ + else + max = clamp_t(u32, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize), + USB_CDC_NCM_NTB_MIN_OUT_SIZE, + CDC_NCM_NTB_MAX_SIZE_TX); /* some devices set dwNtbOutMaxSize too low for the above default */ min = min(min, max); @@ -1230,6 +1233,9 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) * further. */ if (skb_out == NULL) { + /* If even the smallest allocation fails, abort. */ + if (ctx->tx_curr_size == USB_CDC_NCM_NTB_MIN_OUT_SIZE) + goto alloc_failed; ctx->tx_low_mem_max_cnt = min(ctx->tx_low_mem_max_cnt + 1, (unsigned)CDC_NCM_LOW_MEM_MAX_CNT); ctx->tx_low_mem_val = ctx->tx_low_mem_max_cnt; @@ -1248,13 +1254,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) skb_out = alloc_skb(ctx->tx_curr_size, GFP_ATOMIC); /* No allocation possible so we will abort */ - if (skb_out == NULL) { - if (skb != NULL) { - dev_kfree_skb_any(skb); - dev->net->stats.tx_dropped++; - } - goto exit_no_skb; - } + if (!skb_out) + goto alloc_failed; ctx->tx_low_mem_val--; } if (ctx->is_ndp16) { @@ -1447,6 +1448,11 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) return skb_out; +alloc_failed: + if (skb) { + dev_kfree_skb_any(skb); + dev->net->stats.tx_dropped++; + } exit_no_skb: /* Start timer, if there is a remaining non-empty skb */ if (ctx->tx_curr_skb != NULL && n > 0) From 4c3ddc06cedb62f2904e58fd95170bf206bee149 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 8 Jun 2023 23:13:34 +0100 Subject: [PATCH 3431/4345] ata: ahci: fix enum constants for gcc-13 commit f07788079f515ca4a681c5f595bdad19cfbd7b1d upstream. gcc-13 slightly changes the type of constant expressions that are defined in an enum, which triggers a compile time sanity check in libata: linux/drivers/ata/libahci.c: In function 'ahci_led_store': linux/include/linux/compiler_types.h:357:45: error: call to '__compiletime_assert_302' declared with attribute error: BUILD_BUG_ON failed: sizeof(_s) > sizeof(long) 357 | _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) The new behavior is that sizeof() returns the same value for the constant as it does for the enum type, which is generally more sensible and consistent. The problem in libata is that it contains a single enum definition for lots of unrelated constants, some of which are large positive (unsigned) integers like 0xffffffff, while others like (1<<31) are interpreted as negative integers, and this forces the enum type to become 64 bit wide even though most constants would still fit into a signed 32-bit 'int'. Fix this by changing the entire enum definition to use BIT(x) in place of (1< Cc: linux-ide@vger.kernel.org Cc: Damien Le Moal Cc: stable@vger.kernel.org Cc: Randy Dunlap Signed-off-by: Arnd Bergmann Tested-by: Luis Machado Signed-off-by: Damien Le Moal [ Modified to account for slight differences in the enum contents in the 5.10.y tree.] Signed-off-by: Paul Barker Signed-off-by: Greg Kroah-Hartman --- drivers/ata/ahci.h | 241 +++++++++++++++++++++++---------------------- 1 file changed, 121 insertions(+), 120 deletions(-) diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 1ce897356993..7cc6feb17e97 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -24,6 +24,7 @@ #include #include #include +#include /* Enclosure Management Control */ #define EM_CTRL_MSG_TYPE 0x000f0000 @@ -54,12 +55,12 @@ enum { AHCI_PORT_PRIV_FBS_DMA_SZ = AHCI_CMD_SLOT_SZ + AHCI_CMD_TBL_AR_SZ + (AHCI_RX_FIS_SZ * 16), - AHCI_IRQ_ON_SG = (1 << 31), - AHCI_CMD_ATAPI = (1 << 5), - AHCI_CMD_WRITE = (1 << 6), - AHCI_CMD_PREFETCH = (1 << 7), - AHCI_CMD_RESET = (1 << 8), - AHCI_CMD_CLR_BUSY = (1 << 10), + AHCI_IRQ_ON_SG = BIT(31), + AHCI_CMD_ATAPI = BIT(5), + AHCI_CMD_WRITE = BIT(6), + AHCI_CMD_PREFETCH = BIT(7), + AHCI_CMD_RESET = BIT(8), + AHCI_CMD_CLR_BUSY = BIT(10), RX_FIS_PIO_SETUP = 0x20, /* offset of PIO Setup FIS data */ RX_FIS_D2H_REG = 0x40, /* offset of D2H Register FIS data */ @@ -77,37 +78,37 @@ enum { HOST_CAP2 = 0x24, /* host capabilities, extended */ /* HOST_CTL bits */ - HOST_RESET = (1 << 0), /* reset controller; self-clear */ - HOST_IRQ_EN = (1 << 1), /* global IRQ enable */ - HOST_MRSM = (1 << 2), /* MSI Revert to Single Message */ - HOST_AHCI_EN = (1 << 31), /* AHCI enabled */ + HOST_RESET = BIT(0), /* reset controller; self-clear */ + HOST_IRQ_EN = BIT(1), /* global IRQ enable */ + HOST_MRSM = BIT(2), /* MSI Revert to Single Message */ + HOST_AHCI_EN = BIT(31), /* AHCI enabled */ /* HOST_CAP bits */ - HOST_CAP_SXS = (1 << 5), /* Supports External SATA */ - HOST_CAP_EMS = (1 << 6), /* Enclosure Management support */ - HOST_CAP_CCC = (1 << 7), /* Command Completion Coalescing */ - HOST_CAP_PART = (1 << 13), /* Partial state capable */ - HOST_CAP_SSC = (1 << 14), /* Slumber state capable */ - HOST_CAP_PIO_MULTI = (1 << 15), /* PIO multiple DRQ support */ - HOST_CAP_FBS = (1 << 16), /* FIS-based switching support */ - HOST_CAP_PMP = (1 << 17), /* Port Multiplier support */ - HOST_CAP_ONLY = (1 << 18), /* Supports AHCI mode only */ - HOST_CAP_CLO = (1 << 24), /* Command List Override support */ - HOST_CAP_LED = (1 << 25), /* Supports activity LED */ - HOST_CAP_ALPM = (1 << 26), /* Aggressive Link PM support */ - HOST_CAP_SSS = (1 << 27), /* Staggered Spin-up */ - HOST_CAP_MPS = (1 << 28), /* Mechanical presence switch */ - HOST_CAP_SNTF = (1 << 29), /* SNotification register */ - HOST_CAP_NCQ = (1 << 30), /* Native Command Queueing */ - HOST_CAP_64 = (1 << 31), /* PCI DAC (64-bit DMA) support */ + HOST_CAP_SXS = BIT(5), /* Supports External SATA */ + HOST_CAP_EMS = BIT(6), /* Enclosure Management support */ + HOST_CAP_CCC = BIT(7), /* Command Completion Coalescing */ + HOST_CAP_PART = BIT(13), /* Partial state capable */ + HOST_CAP_SSC = BIT(14), /* Slumber state capable */ + HOST_CAP_PIO_MULTI = BIT(15), /* PIO multiple DRQ support */ + HOST_CAP_FBS = BIT(16), /* FIS-based switching support */ + HOST_CAP_PMP = BIT(17), /* Port Multiplier support */ + HOST_CAP_ONLY = BIT(18), /* Supports AHCI mode only */ + HOST_CAP_CLO = BIT(24), /* Command List Override support */ + HOST_CAP_LED = BIT(25), /* Supports activity LED */ + HOST_CAP_ALPM = BIT(26), /* Aggressive Link PM support */ + HOST_CAP_SSS = BIT(27), /* Staggered Spin-up */ + HOST_CAP_MPS = BIT(28), /* Mechanical presence switch */ + HOST_CAP_SNTF = BIT(29), /* SNotification register */ + HOST_CAP_NCQ = BIT(30), /* Native Command Queueing */ + HOST_CAP_64 = BIT(31), /* PCI DAC (64-bit DMA) support */ /* HOST_CAP2 bits */ - HOST_CAP2_BOH = (1 << 0), /* BIOS/OS handoff supported */ - HOST_CAP2_NVMHCI = (1 << 1), /* NVMHCI supported */ - HOST_CAP2_APST = (1 << 2), /* Automatic partial to slumber */ - HOST_CAP2_SDS = (1 << 3), /* Support device sleep */ - HOST_CAP2_SADM = (1 << 4), /* Support aggressive DevSlp */ - HOST_CAP2_DESO = (1 << 5), /* DevSlp from slumber only */ + HOST_CAP2_BOH = BIT(0), /* BIOS/OS handoff supported */ + HOST_CAP2_NVMHCI = BIT(1), /* NVMHCI supported */ + HOST_CAP2_APST = BIT(2), /* Automatic partial to slumber */ + HOST_CAP2_SDS = BIT(3), /* Support device sleep */ + HOST_CAP2_SADM = BIT(4), /* Support aggressive DevSlp */ + HOST_CAP2_DESO = BIT(5), /* DevSlp from slumber only */ /* registers for each SATA port */ PORT_LST_ADDR = 0x00, /* command list DMA addr */ @@ -129,24 +130,24 @@ enum { PORT_DEVSLP = 0x44, /* device sleep */ /* PORT_IRQ_{STAT,MASK} bits */ - PORT_IRQ_COLD_PRES = (1 << 31), /* cold presence detect */ - PORT_IRQ_TF_ERR = (1 << 30), /* task file error */ - PORT_IRQ_HBUS_ERR = (1 << 29), /* host bus fatal error */ - PORT_IRQ_HBUS_DATA_ERR = (1 << 28), /* host bus data error */ - PORT_IRQ_IF_ERR = (1 << 27), /* interface fatal error */ - PORT_IRQ_IF_NONFATAL = (1 << 26), /* interface non-fatal error */ - PORT_IRQ_OVERFLOW = (1 << 24), /* xfer exhausted available S/G */ - PORT_IRQ_BAD_PMP = (1 << 23), /* incorrect port multiplier */ + PORT_IRQ_COLD_PRES = BIT(31), /* cold presence detect */ + PORT_IRQ_TF_ERR = BIT(30), /* task file error */ + PORT_IRQ_HBUS_ERR = BIT(29), /* host bus fatal error */ + PORT_IRQ_HBUS_DATA_ERR = BIT(28), /* host bus data error */ + PORT_IRQ_IF_ERR = BIT(27), /* interface fatal error */ + PORT_IRQ_IF_NONFATAL = BIT(26), /* interface non-fatal error */ + PORT_IRQ_OVERFLOW = BIT(24), /* xfer exhausted available S/G */ + PORT_IRQ_BAD_PMP = BIT(23), /* incorrect port multiplier */ - PORT_IRQ_PHYRDY = (1 << 22), /* PhyRdy changed */ - PORT_IRQ_DEV_ILCK = (1 << 7), /* device interlock */ - PORT_IRQ_CONNECT = (1 << 6), /* port connect change status */ - PORT_IRQ_SG_DONE = (1 << 5), /* descriptor processed */ - PORT_IRQ_UNK_FIS = (1 << 4), /* unknown FIS rx'd */ - PORT_IRQ_SDB_FIS = (1 << 3), /* Set Device Bits FIS rx'd */ - PORT_IRQ_DMAS_FIS = (1 << 2), /* DMA Setup FIS rx'd */ - PORT_IRQ_PIOS_FIS = (1 << 1), /* PIO Setup FIS rx'd */ - PORT_IRQ_D2H_REG_FIS = (1 << 0), /* D2H Register FIS rx'd */ + PORT_IRQ_PHYRDY = BIT(22), /* PhyRdy changed */ + PORT_IRQ_DEV_ILCK = BIT(7), /* device interlock */ + PORT_IRQ_CONNECT = BIT(6), /* port connect change status */ + PORT_IRQ_SG_DONE = BIT(5), /* descriptor processed */ + PORT_IRQ_UNK_FIS = BIT(4), /* unknown FIS rx'd */ + PORT_IRQ_SDB_FIS = BIT(3), /* Set Device Bits FIS rx'd */ + PORT_IRQ_DMAS_FIS = BIT(2), /* DMA Setup FIS rx'd */ + PORT_IRQ_PIOS_FIS = BIT(1), /* PIO Setup FIS rx'd */ + PORT_IRQ_D2H_REG_FIS = BIT(0), /* D2H Register FIS rx'd */ PORT_IRQ_FREEZE = PORT_IRQ_HBUS_ERR | PORT_IRQ_IF_ERR | @@ -162,34 +163,34 @@ enum { PORT_IRQ_PIOS_FIS | PORT_IRQ_D2H_REG_FIS, /* PORT_CMD bits */ - PORT_CMD_ASP = (1 << 27), /* Aggressive Slumber/Partial */ - PORT_CMD_ALPE = (1 << 26), /* Aggressive Link PM enable */ - PORT_CMD_ATAPI = (1 << 24), /* Device is ATAPI */ - PORT_CMD_FBSCP = (1 << 22), /* FBS Capable Port */ - PORT_CMD_ESP = (1 << 21), /* External Sata Port */ - PORT_CMD_HPCP = (1 << 18), /* HotPlug Capable Port */ - PORT_CMD_PMP = (1 << 17), /* PMP attached */ - PORT_CMD_LIST_ON = (1 << 15), /* cmd list DMA engine running */ - PORT_CMD_FIS_ON = (1 << 14), /* FIS DMA engine running */ - PORT_CMD_FIS_RX = (1 << 4), /* Enable FIS receive DMA engine */ - PORT_CMD_CLO = (1 << 3), /* Command list override */ - PORT_CMD_POWER_ON = (1 << 2), /* Power up device */ - PORT_CMD_SPIN_UP = (1 << 1), /* Spin up device */ - PORT_CMD_START = (1 << 0), /* Enable port DMA engine */ + PORT_CMD_ASP = BIT(27), /* Aggressive Slumber/Partial */ + PORT_CMD_ALPE = BIT(26), /* Aggressive Link PM enable */ + PORT_CMD_ATAPI = BIT(24), /* Device is ATAPI */ + PORT_CMD_FBSCP = BIT(22), /* FBS Capable Port */ + PORT_CMD_ESP = BIT(21), /* External Sata Port */ + PORT_CMD_HPCP = BIT(18), /* HotPlug Capable Port */ + PORT_CMD_PMP = BIT(17), /* PMP attached */ + PORT_CMD_LIST_ON = BIT(15), /* cmd list DMA engine running */ + PORT_CMD_FIS_ON = BIT(14), /* FIS DMA engine running */ + PORT_CMD_FIS_RX = BIT(4), /* Enable FIS receive DMA engine */ + PORT_CMD_CLO = BIT(3), /* Command list override */ + PORT_CMD_POWER_ON = BIT(2), /* Power up device */ + PORT_CMD_SPIN_UP = BIT(1), /* Spin up device */ + PORT_CMD_START = BIT(0), /* Enable port DMA engine */ - PORT_CMD_ICC_MASK = (0xf << 28), /* i/f ICC state mask */ - PORT_CMD_ICC_ACTIVE = (0x1 << 28), /* Put i/f in active state */ - PORT_CMD_ICC_PARTIAL = (0x2 << 28), /* Put i/f in partial state */ - PORT_CMD_ICC_SLUMBER = (0x6 << 28), /* Put i/f in slumber state */ + PORT_CMD_ICC_MASK = (0xfu << 28), /* i/f ICC state mask */ + PORT_CMD_ICC_ACTIVE = (0x1u << 28), /* Put i/f in active state */ + PORT_CMD_ICC_PARTIAL = (0x2u << 28), /* Put i/f in partial state */ + PORT_CMD_ICC_SLUMBER = (0x6u << 28), /* Put i/f in slumber state */ /* PORT_FBS bits */ PORT_FBS_DWE_OFFSET = 16, /* FBS device with error offset */ PORT_FBS_ADO_OFFSET = 12, /* FBS active dev optimization offset */ PORT_FBS_DEV_OFFSET = 8, /* FBS device to issue offset */ PORT_FBS_DEV_MASK = (0xf << PORT_FBS_DEV_OFFSET), /* FBS.DEV */ - PORT_FBS_SDE = (1 << 2), /* FBS single device error */ - PORT_FBS_DEC = (1 << 1), /* FBS device error clear */ - PORT_FBS_EN = (1 << 0), /* Enable FBS */ + PORT_FBS_SDE = BIT(2), /* FBS single device error */ + PORT_FBS_DEC = BIT(1), /* FBS device error clear */ + PORT_FBS_EN = BIT(0), /* Enable FBS */ /* PORT_DEVSLP bits */ PORT_DEVSLP_DM_OFFSET = 25, /* DITO multiplier offset */ @@ -197,52 +198,52 @@ enum { PORT_DEVSLP_DITO_OFFSET = 15, /* DITO offset */ PORT_DEVSLP_MDAT_OFFSET = 10, /* Minimum assertion time */ PORT_DEVSLP_DETO_OFFSET = 2, /* DevSlp exit timeout */ - PORT_DEVSLP_DSP = (1 << 1), /* DevSlp present */ - PORT_DEVSLP_ADSE = (1 << 0), /* Aggressive DevSlp enable */ + PORT_DEVSLP_DSP = BIT(1), /* DevSlp present */ + PORT_DEVSLP_ADSE = BIT(0), /* Aggressive DevSlp enable */ /* hpriv->flags bits */ #define AHCI_HFLAGS(flags) .private_data = (void *)(flags) - AHCI_HFLAG_NO_NCQ = (1 << 0), - AHCI_HFLAG_IGN_IRQ_IF_ERR = (1 << 1), /* ignore IRQ_IF_ERR */ - AHCI_HFLAG_IGN_SERR_INTERNAL = (1 << 2), /* ignore SERR_INTERNAL */ - AHCI_HFLAG_32BIT_ONLY = (1 << 3), /* force 32bit */ - AHCI_HFLAG_MV_PATA = (1 << 4), /* PATA port */ - AHCI_HFLAG_NO_MSI = (1 << 5), /* no PCI MSI */ - AHCI_HFLAG_NO_PMP = (1 << 6), /* no PMP */ - AHCI_HFLAG_SECT255 = (1 << 8), /* max 255 sectors */ - AHCI_HFLAG_YES_NCQ = (1 << 9), /* force NCQ cap on */ - AHCI_HFLAG_NO_SUSPEND = (1 << 10), /* don't suspend */ - AHCI_HFLAG_SRST_TOUT_IS_OFFLINE = (1 << 11), /* treat SRST timeout as - link offline */ - AHCI_HFLAG_NO_SNTF = (1 << 12), /* no sntf */ - AHCI_HFLAG_NO_FPDMA_AA = (1 << 13), /* no FPDMA AA */ - AHCI_HFLAG_YES_FBS = (1 << 14), /* force FBS cap on */ - AHCI_HFLAG_DELAY_ENGINE = (1 << 15), /* do not start engine on - port start (wait until - error-handling stage) */ - AHCI_HFLAG_NO_DEVSLP = (1 << 17), /* no device sleep */ - AHCI_HFLAG_NO_FBS = (1 << 18), /* no FBS */ + AHCI_HFLAG_NO_NCQ = BIT(0), + AHCI_HFLAG_IGN_IRQ_IF_ERR = BIT(1), /* ignore IRQ_IF_ERR */ + AHCI_HFLAG_IGN_SERR_INTERNAL = BIT(2), /* ignore SERR_INTERNAL */ + AHCI_HFLAG_32BIT_ONLY = BIT(3), /* force 32bit */ + AHCI_HFLAG_MV_PATA = BIT(4), /* PATA port */ + AHCI_HFLAG_NO_MSI = BIT(5), /* no PCI MSI */ + AHCI_HFLAG_NO_PMP = BIT(6), /* no PMP */ + AHCI_HFLAG_SECT255 = BIT(8), /* max 255 sectors */ + AHCI_HFLAG_YES_NCQ = BIT(9), /* force NCQ cap on */ + AHCI_HFLAG_NO_SUSPEND = BIT(10), /* don't suspend */ + AHCI_HFLAG_SRST_TOUT_IS_OFFLINE = BIT(11), /* treat SRST timeout as + link offline */ + AHCI_HFLAG_NO_SNTF = BIT(12), /* no sntf */ + AHCI_HFLAG_NO_FPDMA_AA = BIT(13), /* no FPDMA AA */ + AHCI_HFLAG_YES_FBS = BIT(14), /* force FBS cap on */ + AHCI_HFLAG_DELAY_ENGINE = BIT(15), /* do not start engine on + port start (wait until + error-handling stage) */ + AHCI_HFLAG_NO_DEVSLP = BIT(17), /* no device sleep */ + AHCI_HFLAG_NO_FBS = BIT(18), /* no FBS */ #ifdef CONFIG_PCI_MSI - AHCI_HFLAG_MULTI_MSI = (1 << 20), /* per-port MSI(-X) */ + AHCI_HFLAG_MULTI_MSI = BIT(20), /* per-port MSI(-X) */ #else /* compile out MSI infrastructure */ AHCI_HFLAG_MULTI_MSI = 0, #endif - AHCI_HFLAG_WAKE_BEFORE_STOP = (1 << 22), /* wake before DMA stop */ - AHCI_HFLAG_YES_ALPM = (1 << 23), /* force ALPM cap on */ - AHCI_HFLAG_NO_WRITE_TO_RO = (1 << 24), /* don't write to read - only registers */ - AHCI_HFLAG_IS_MOBILE = (1 << 25), /* mobile chipset, use - SATA_MOBILE_LPM_POLICY - as default lpm_policy */ - AHCI_HFLAG_SUSPEND_PHYS = (1 << 26), /* handle PHYs during - suspend/resume */ - AHCI_HFLAG_IGN_NOTSUPP_POWER_ON = (1 << 27), /* ignore -EOPNOTSUPP - from phy_power_on() */ - AHCI_HFLAG_NO_SXS = (1 << 28), /* SXS not supported */ + AHCI_HFLAG_WAKE_BEFORE_STOP = BIT(22), /* wake before DMA stop */ + AHCI_HFLAG_YES_ALPM = BIT(23), /* force ALPM cap on */ + AHCI_HFLAG_NO_WRITE_TO_RO = BIT(24), /* don't write to read + only registers */ + AHCI_HFLAG_IS_MOBILE = BIT(25), /* mobile chipset, use + SATA_MOBILE_LPM_POLICY + as default lpm_policy */ + AHCI_HFLAG_SUSPEND_PHYS = BIT(26), /* handle PHYs during + suspend/resume */ + AHCI_HFLAG_IGN_NOTSUPP_POWER_ON = BIT(27), /* ignore -EOPNOTSUPP + from phy_power_on() */ + AHCI_HFLAG_NO_SXS = BIT(28), /* SXS not supported */ /* ap->flags bits */ @@ -258,22 +259,22 @@ enum { EM_MAX_RETRY = 5, /* em_ctl bits */ - EM_CTL_RST = (1 << 9), /* Reset */ - EM_CTL_TM = (1 << 8), /* Transmit Message */ - EM_CTL_MR = (1 << 0), /* Message Received */ - EM_CTL_ALHD = (1 << 26), /* Activity LED */ - EM_CTL_XMT = (1 << 25), /* Transmit Only */ - EM_CTL_SMB = (1 << 24), /* Single Message Buffer */ - EM_CTL_SGPIO = (1 << 19), /* SGPIO messages supported */ - EM_CTL_SES = (1 << 18), /* SES-2 messages supported */ - EM_CTL_SAFTE = (1 << 17), /* SAF-TE messages supported */ - EM_CTL_LED = (1 << 16), /* LED messages supported */ + EM_CTL_RST = BIT(9), /* Reset */ + EM_CTL_TM = BIT(8), /* Transmit Message */ + EM_CTL_MR = BIT(0), /* Message Received */ + EM_CTL_ALHD = BIT(26), /* Activity LED */ + EM_CTL_XMT = BIT(25), /* Transmit Only */ + EM_CTL_SMB = BIT(24), /* Single Message Buffer */ + EM_CTL_SGPIO = BIT(19), /* SGPIO messages supported */ + EM_CTL_SES = BIT(18), /* SES-2 messages supported */ + EM_CTL_SAFTE = BIT(17), /* SAF-TE messages supported */ + EM_CTL_LED = BIT(16), /* LED messages supported */ /* em message type */ - EM_MSG_TYPE_LED = (1 << 0), /* LED */ - EM_MSG_TYPE_SAFTE = (1 << 1), /* SAF-TE */ - EM_MSG_TYPE_SES2 = (1 << 2), /* SES-2 */ - EM_MSG_TYPE_SGPIO = (1 << 3), /* SGPIO */ + EM_MSG_TYPE_LED = BIT(0), /* LED */ + EM_MSG_TYPE_SAFTE = BIT(1), /* SAF-TE */ + EM_MSG_TYPE_SES2 = BIT(2), /* SES-2 */ + EM_MSG_TYPE_SGPIO = BIT(3), /* SGPIO */ }; struct ahci_cmd_hdr { From 02ce3cf222913143a6a44c2e1901e69b80885f09 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 8 Jun 2023 23:13:35 +0100 Subject: [PATCH 3432/4345] gcc-plugins: Reorganize gimple includes for GCC 13 mainline commit: e6a71160cc145e18ab45195abf89884112e02dfb The gimple-iterator.h header must be included before gimple-fold.h starting with GCC 13. Reorganize gimple headers to work for all GCC versions. Reported-by: Palmer Dabbelt Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/all/20230113173033.4380-1-palmer@rivosinc.com/ Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook [ Modified to handle differences in other includes and conditional compilation in the 5.10.y tree. ] Signed-off-by: Paul Barker Signed-off-by: Greg Kroah-Hartman --- scripts/gcc-plugins/gcc-common.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 9ad76b7f3f10..6d4563b8a52c 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -108,7 +108,13 @@ #include "varasm.h" #include "stor-layout.h" #include "internal-fn.h" +#endif + +#include "gimple.h" + +#if BUILDING_GCC_VERSION >= 4009 #include "gimple-expr.h" +#include "gimple-iterator.h" #include "gimple-fold.h" #include "context.h" #include "tree-ssa-alias.h" @@ -124,13 +130,10 @@ #include "gimplify.h" #endif -#include "gimple.h" - #if BUILDING_GCC_VERSION >= 4009 #include "tree-ssa-operands.h" #include "tree-phinodes.h" #include "tree-cfg.h" -#include "gimple-iterator.h" #include "gimple-ssa.h" #include "ssa-iterators.h" #endif From 9236470a1dd483771a0360fe98c72c498431d1ca Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 31 Oct 2022 12:44:40 +0100 Subject: [PATCH 3433/4345] sfc (gcc13): synchronize ef100_enqueue_skb()'s return type commit 3319dbb3e755398f254c3daa04b9030197137efe upstream. ef100_enqueue_skb() generates a valid warning with gcc-13: drivers/net/ethernet/sfc/ef100_tx.c:370:5: error: conflicting types for 'ef100_enqueue_skb' due to enum/integer mismatch; have 'int(struct efx_tx_queue *, struct sk_buff *)' drivers/net/ethernet/sfc/ef100_tx.h:25:13: note: previous declaration of 'ef100_enqueue_skb' with type 'netdev_tx_t(struct efx_tx_queue *, struct sk_buff *)' I.e. the type of the ef100_enqueue_skb()'s return value in the declaration is int, while the definition spells enum netdev_tx_t. Synchronize them to the latter. Cc: Martin Liska Cc: Edward Cree Cc: Martin Habets Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20221031114440.10461-1-jirislaby@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/sfc/ef100_tx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/ef100_tx.c b/drivers/net/ethernet/sfc/ef100_tx.c index a90e5a9d2a37..6ddda1a5e536 100644 --- a/drivers/net/ethernet/sfc/ef100_tx.c +++ b/drivers/net/ethernet/sfc/ef100_tx.c @@ -333,7 +333,8 @@ void ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event) * Returns 0 on success, error code otherwise. In case of an error this * function will free the SKB. */ -int ef100_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) +netdev_tx_t ef100_enqueue_skb(struct efx_tx_queue *tx_queue, + struct sk_buff *skb) { unsigned int old_insert_count = tx_queue->insert_count; struct efx_nic *efx = tx_queue->efx; From f122e5517401139fa3b7b89a4cb1d271aa489655 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 21 Jul 2022 08:41:02 +0200 Subject: [PATCH 3434/4345] remove the sx8 block driver commit d13bc4d84a8e91060d3797fc95c1a0202bfd1499 upstream. This driver is for fairly obscure hardware, and has only seen random drive-by changes after the maintainer stopped working on it in 2005 (about a year and a half after it was introduced). It has some "interesting" block layer interactions, so let's just drop it unless anyone complains. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220721064102.1715460-1-hch@lst.de [axboe: fix date typo, it was in 2005, not 2015] Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/Kconfig | 9 - drivers/block/Makefile | 2 - drivers/block/sx8.c | 1586 ---------------------------------------- 3 files changed, 1597 deletions(-) delete mode 100644 drivers/block/sx8.c diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 9617688b58b3..408c7428cca5 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -293,15 +293,6 @@ config BLK_DEV_SKD Use device /dev/skd$N amd /dev/skd$Np$M. -config BLK_DEV_SX8 - tristate "Promise SATA SX8 support" - depends on PCI - help - Saying Y or M here will enable support for the - Promise SATA SX8 controllers. - - Use devices /dev/sx8/$N and /dev/sx8/$Np$M. - config BLK_DEV_RAM tristate "RAM block device support" help diff --git a/drivers/block/Makefile b/drivers/block/Makefile index a3170859e01d..24427da7dd64 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -29,8 +29,6 @@ obj-$(CONFIG_BLK_DEV_NBD) += nbd.o obj-$(CONFIG_BLK_DEV_CRYPTOLOOP) += cryptoloop.o obj-$(CONFIG_VIRTIO_BLK) += virtio_blk.o -obj-$(CONFIG_BLK_DEV_SX8) += sx8.o - obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += xen-blkfront.o obj-$(CONFIG_XEN_BLKDEV_BACKEND) += xen-blkback/ obj-$(CONFIG_BLK_DEV_DRBD) += drbd/ diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c deleted file mode 100644 index 4478eb7efee0..000000000000 --- a/drivers/block/sx8.c +++ /dev/null @@ -1,1586 +0,0 @@ -/* - * sx8.c: Driver for Promise SATA SX8 looks-like-I2O hardware - * - * Copyright 2004-2005 Red Hat, Inc. - * - * Author/maintainer: Jeff Garzik - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#if 0 -#define CARM_DEBUG -#define CARM_VERBOSE_DEBUG -#else -#undef CARM_DEBUG -#undef CARM_VERBOSE_DEBUG -#endif -#undef CARM_NDEBUG - -#define DRV_NAME "sx8" -#define DRV_VERSION "1.0" -#define PFX DRV_NAME ": " - -MODULE_AUTHOR("Jeff Garzik"); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Promise SATA SX8 block driver"); -MODULE_VERSION(DRV_VERSION); - -/* - * SX8 hardware has a single message queue for all ATA ports. - * When this driver was written, the hardware (firmware?) would - * corrupt data eventually, if more than one request was outstanding. - * As one can imagine, having 8 ports bottlenecking on a single - * command hurts performance. - * - * Based on user reports, later versions of the hardware (firmware?) - * seem to be able to survive with more than one command queued. - * - * Therefore, we default to the safe option -- 1 command -- but - * allow the user to increase this. - * - * SX8 should be able to support up to ~60 queued commands (CARM_MAX_REQ), - * but problems seem to occur when you exceed ~30, even on newer hardware. - */ -static int max_queue = 1; -module_param(max_queue, int, 0444); -MODULE_PARM_DESC(max_queue, "Maximum number of queued commands. (min==1, max==30, safe==1)"); - - -#define NEXT_RESP(idx) ((idx + 1) % RMSG_Q_LEN) - -/* 0xf is just arbitrary, non-zero noise; this is sorta like poisoning */ -#define TAG_ENCODE(tag) (((tag) << 16) | 0xf) -#define TAG_DECODE(tag) (((tag) >> 16) & 0x1f) -#define TAG_VALID(tag) ((((tag) & 0xf) == 0xf) && (TAG_DECODE(tag) < 32)) - -/* note: prints function name for you */ -#ifdef CARM_DEBUG -#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#ifdef CARM_VERBOSE_DEBUG -#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#else -#define VPRINTK(fmt, args...) -#endif /* CARM_VERBOSE_DEBUG */ -#else -#define DPRINTK(fmt, args...) -#define VPRINTK(fmt, args...) -#endif /* CARM_DEBUG */ - -#ifdef CARM_NDEBUG -#define assert(expr) -#else -#define assert(expr) \ - if(unlikely(!(expr))) { \ - printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \ - #expr, __FILE__, __func__, __LINE__); \ - } -#endif - -/* defines only for the constants which don't work well as enums */ -struct carm_host; - -enum { - /* adapter-wide limits */ - CARM_MAX_PORTS = 8, - CARM_SHM_SIZE = (4096 << 7), - CARM_MINORS_PER_MAJOR = 256 / CARM_MAX_PORTS, - CARM_MAX_WAIT_Q = CARM_MAX_PORTS + 1, - - /* command message queue limits */ - CARM_MAX_REQ = 64, /* max command msgs per host */ - CARM_MSG_LOW_WATER = (CARM_MAX_REQ / 4), /* refill mark */ - - /* S/G limits, host-wide and per-request */ - CARM_MAX_REQ_SG = 32, /* max s/g entries per request */ - CARM_MAX_HOST_SG = 600, /* max s/g entries per host */ - CARM_SG_LOW_WATER = (CARM_MAX_HOST_SG / 4), /* re-fill mark */ - - /* hardware registers */ - CARM_IHQP = 0x1c, - CARM_INT_STAT = 0x10, /* interrupt status */ - CARM_INT_MASK = 0x14, /* interrupt mask */ - CARM_HMUC = 0x18, /* host message unit control */ - RBUF_ADDR_LO = 0x20, /* response msg DMA buf low 32 bits */ - RBUF_ADDR_HI = 0x24, /* response msg DMA buf high 32 bits */ - RBUF_BYTE_SZ = 0x28, - CARM_RESP_IDX = 0x2c, - CARM_CMS0 = 0x30, /* command message size reg 0 */ - CARM_LMUC = 0x48, - CARM_HMPHA = 0x6c, - CARM_INITC = 0xb5, - - /* bits in CARM_INT_{STAT,MASK} */ - INT_RESERVED = 0xfffffff0, - INT_WATCHDOG = (1 << 3), /* watchdog timer */ - INT_Q_OVERFLOW = (1 << 2), /* cmd msg q overflow */ - INT_Q_AVAILABLE = (1 << 1), /* cmd msg q has free space */ - INT_RESPONSE = (1 << 0), /* response msg available */ - INT_ACK_MASK = INT_WATCHDOG | INT_Q_OVERFLOW, - INT_DEF_MASK = INT_RESERVED | INT_Q_OVERFLOW | - INT_RESPONSE, - - /* command messages, and related register bits */ - CARM_HAVE_RESP = 0x01, - CARM_MSG_READ = 1, - CARM_MSG_WRITE = 2, - CARM_MSG_VERIFY = 3, - CARM_MSG_GET_CAPACITY = 4, - CARM_MSG_FLUSH = 5, - CARM_MSG_IOCTL = 6, - CARM_MSG_ARRAY = 8, - CARM_MSG_MISC = 9, - CARM_CME = (1 << 2), - CARM_RME = (1 << 1), - CARM_WZBC = (1 << 0), - CARM_RMI = (1 << 0), - CARM_Q_FULL = (1 << 3), - CARM_MSG_SIZE = 288, - CARM_Q_LEN = 48, - - /* CARM_MSG_IOCTL messages */ - CARM_IOC_SCAN_CHAN = 5, /* scan channels for devices */ - CARM_IOC_GET_TCQ = 13, /* get tcq/ncq depth */ - CARM_IOC_SET_TCQ = 14, /* set tcq/ncq depth */ - - IOC_SCAN_CHAN_NODEV = 0x1f, - IOC_SCAN_CHAN_OFFSET = 0x40, - - /* CARM_MSG_ARRAY messages */ - CARM_ARRAY_INFO = 0, - - ARRAY_NO_EXIST = (1 << 31), - - /* response messages */ - RMSG_SZ = 8, /* sizeof(struct carm_response) */ - RMSG_Q_LEN = 48, /* resp. msg list length */ - RMSG_OK = 1, /* bit indicating msg was successful */ - /* length of entire resp. msg buffer */ - RBUF_LEN = RMSG_SZ * RMSG_Q_LEN, - - PDC_SHM_SIZE = (4096 << 7), /* length of entire h/w buffer */ - - /* CARM_MSG_MISC messages */ - MISC_GET_FW_VER = 2, - MISC_ALLOC_MEM = 3, - MISC_SET_TIME = 5, - - /* MISC_GET_FW_VER feature bits */ - FW_VER_4PORT = (1 << 2), /* 1=4 ports, 0=8 ports */ - FW_VER_NON_RAID = (1 << 1), /* 1=non-RAID firmware, 0=RAID */ - FW_VER_ZCR = (1 << 0), /* zero channel RAID (whatever that is) */ - - /* carm_host flags */ - FL_NON_RAID = FW_VER_NON_RAID, - FL_4PORT = FW_VER_4PORT, - FL_FW_VER_MASK = (FW_VER_NON_RAID | FW_VER_4PORT), - FL_DYN_MAJOR = (1 << 17), -}; - -enum { - CARM_SG_BOUNDARY = 0xffffUL, /* s/g segment boundary */ -}; - -enum scatter_gather_types { - SGT_32BIT = 0, - SGT_64BIT = 1, -}; - -enum host_states { - HST_INVALID, /* invalid state; never used */ - HST_ALLOC_BUF, /* setting up master SHM area */ - HST_ERROR, /* we never leave here */ - HST_PORT_SCAN, /* start dev scan */ - HST_DEV_SCAN_START, /* start per-device probe */ - HST_DEV_SCAN, /* continue per-device probe */ - HST_DEV_ACTIVATE, /* activate devices we found */ - HST_PROBE_FINISHED, /* probe is complete */ - HST_PROBE_START, /* initiate probe */ - HST_SYNC_TIME, /* tell firmware what time it is */ - HST_GET_FW_VER, /* get firmware version, adapter port cnt */ -}; - -#ifdef CARM_DEBUG -static const char *state_name[] = { - "HST_INVALID", - "HST_ALLOC_BUF", - "HST_ERROR", - "HST_PORT_SCAN", - "HST_DEV_SCAN_START", - "HST_DEV_SCAN", - "HST_DEV_ACTIVATE", - "HST_PROBE_FINISHED", - "HST_PROBE_START", - "HST_SYNC_TIME", - "HST_GET_FW_VER", -}; -#endif - -struct carm_port { - unsigned int port_no; - struct gendisk *disk; - struct carm_host *host; - - /* attached device characteristics */ - u64 capacity; - char name[41]; - u16 dev_geom_head; - u16 dev_geom_sect; - u16 dev_geom_cyl; -}; - -struct carm_request { - int n_elem; - unsigned int msg_type; - unsigned int msg_subtype; - unsigned int msg_bucket; - struct scatterlist sg[CARM_MAX_REQ_SG]; -}; - -struct carm_host { - unsigned long flags; - void __iomem *mmio; - void *shm; - dma_addr_t shm_dma; - - int major; - int id; - char name[32]; - - spinlock_t lock; - struct pci_dev *pdev; - unsigned int state; - u32 fw_ver; - - struct blk_mq_tag_set tag_set; - struct request_queue *oob_q; - unsigned int n_oob; - - unsigned int hw_sg_used; - - unsigned int resp_idx; - - unsigned int wait_q_prod; - unsigned int wait_q_cons; - struct request_queue *wait_q[CARM_MAX_WAIT_Q]; - - void *msg_base; - dma_addr_t msg_dma; - - int cur_scan_dev; - unsigned long dev_active; - unsigned long dev_present; - struct carm_port port[CARM_MAX_PORTS]; - - struct work_struct fsm_task; - - struct completion probe_comp; -}; - -struct carm_response { - __le32 ret_handle; - __le32 status; -} __attribute__((packed)); - -struct carm_msg_sg { - __le32 start; - __le32 len; -} __attribute__((packed)); - -struct carm_msg_rw { - u8 type; - u8 id; - u8 sg_count; - u8 sg_type; - __le32 handle; - __le32 lba; - __le16 lba_count; - __le16 lba_high; - struct carm_msg_sg sg[32]; -} __attribute__((packed)); - -struct carm_msg_allocbuf { - u8 type; - u8 subtype; - u8 n_sg; - u8 sg_type; - __le32 handle; - __le32 addr; - __le32 len; - __le32 evt_pool; - __le32 n_evt; - __le32 rbuf_pool; - __le32 n_rbuf; - __le32 msg_pool; - __le32 n_msg; - struct carm_msg_sg sg[8]; -} __attribute__((packed)); - -struct carm_msg_ioctl { - u8 type; - u8 subtype; - u8 array_id; - u8 reserved1; - __le32 handle; - __le32 data_addr; - u32 reserved2; -} __attribute__((packed)); - -struct carm_msg_sync_time { - u8 type; - u8 subtype; - u16 reserved1; - __le32 handle; - u32 reserved2; - __le32 timestamp; -} __attribute__((packed)); - -struct carm_msg_get_fw_ver { - u8 type; - u8 subtype; - u16 reserved1; - __le32 handle; - __le32 data_addr; - u32 reserved2; -} __attribute__((packed)); - -struct carm_fw_ver { - __le32 version; - u8 features; - u8 reserved1; - u16 reserved2; -} __attribute__((packed)); - -struct carm_array_info { - __le32 size; - - __le16 size_hi; - __le16 stripe_size; - - __le32 mode; - - __le16 stripe_blk_sz; - __le16 reserved1; - - __le16 cyl; - __le16 head; - - __le16 sect; - u8 array_id; - u8 reserved2; - - char name[40]; - - __le32 array_status; - - /* device list continues beyond this point? */ -} __attribute__((packed)); - -static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent); -static void carm_remove_one (struct pci_dev *pdev); -static int carm_bdev_getgeo(struct block_device *bdev, struct hd_geometry *geo); - -static const struct pci_device_id carm_pci_tbl[] = { - { PCI_VENDOR_ID_PROMISE, 0x8000, PCI_ANY_ID, PCI_ANY_ID, 0, 0, }, - { PCI_VENDOR_ID_PROMISE, 0x8002, PCI_ANY_ID, PCI_ANY_ID, 0, 0, }, - { } /* terminate list */ -}; -MODULE_DEVICE_TABLE(pci, carm_pci_tbl); - -static struct pci_driver carm_driver = { - .name = DRV_NAME, - .id_table = carm_pci_tbl, - .probe = carm_init_one, - .remove = carm_remove_one, -}; - -static const struct block_device_operations carm_bd_ops = { - .owner = THIS_MODULE, - .getgeo = carm_bdev_getgeo, -}; - -static unsigned int carm_host_id; -static unsigned long carm_major_alloc; - - - -static int carm_bdev_getgeo(struct block_device *bdev, struct hd_geometry *geo) -{ - struct carm_port *port = bdev->bd_disk->private_data; - - geo->heads = (u8) port->dev_geom_head; - geo->sectors = (u8) port->dev_geom_sect; - geo->cylinders = port->dev_geom_cyl; - return 0; -} - -static const u32 msg_sizes[] = { 32, 64, 128, CARM_MSG_SIZE }; - -static inline int carm_lookup_bucket(u32 msg_size) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(msg_sizes); i++) - if (msg_size <= msg_sizes[i]) - return i; - - return -ENOENT; -} - -static void carm_init_buckets(void __iomem *mmio) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(msg_sizes); i++) - writel(msg_sizes[i], mmio + CARM_CMS0 + (4 * i)); -} - -static inline void *carm_ref_msg(struct carm_host *host, - unsigned int msg_idx) -{ - return host->msg_base + (msg_idx * CARM_MSG_SIZE); -} - -static inline dma_addr_t carm_ref_msg_dma(struct carm_host *host, - unsigned int msg_idx) -{ - return host->msg_dma + (msg_idx * CARM_MSG_SIZE); -} - -static int carm_send_msg(struct carm_host *host, - struct carm_request *crq, unsigned tag) -{ - void __iomem *mmio = host->mmio; - u32 msg = (u32) carm_ref_msg_dma(host, tag); - u32 cm_bucket = crq->msg_bucket; - u32 tmp; - int rc = 0; - - VPRINTK("ENTER\n"); - - tmp = readl(mmio + CARM_HMUC); - if (tmp & CARM_Q_FULL) { -#if 0 - tmp = readl(mmio + CARM_INT_MASK); - tmp |= INT_Q_AVAILABLE; - writel(tmp, mmio + CARM_INT_MASK); - readl(mmio + CARM_INT_MASK); /* flush */ -#endif - DPRINTK("host msg queue full\n"); - rc = -EBUSY; - } else { - writel(msg | (cm_bucket << 1), mmio + CARM_IHQP); - readl(mmio + CARM_IHQP); /* flush */ - } - - return rc; -} - -static int carm_array_info (struct carm_host *host, unsigned int array_idx) -{ - struct carm_msg_ioctl *ioc; - u32 msg_data; - dma_addr_t msg_dma; - struct carm_request *crq; - struct request *rq; - int rc; - - rq = blk_mq_alloc_request(host->oob_q, REQ_OP_DRV_OUT, 0); - if (IS_ERR(rq)) { - rc = -ENOMEM; - goto err_out; - } - crq = blk_mq_rq_to_pdu(rq); - - ioc = carm_ref_msg(host, rq->tag); - msg_dma = carm_ref_msg_dma(host, rq->tag); - msg_data = (u32) (msg_dma + sizeof(struct carm_array_info)); - - crq->msg_type = CARM_MSG_ARRAY; - crq->msg_subtype = CARM_ARRAY_INFO; - rc = carm_lookup_bucket(sizeof(struct carm_msg_ioctl) + - sizeof(struct carm_array_info)); - BUG_ON(rc < 0); - crq->msg_bucket = (u32) rc; - - memset(ioc, 0, sizeof(*ioc)); - ioc->type = CARM_MSG_ARRAY; - ioc->subtype = CARM_ARRAY_INFO; - ioc->array_id = (u8) array_idx; - ioc->handle = cpu_to_le32(TAG_ENCODE(rq->tag)); - ioc->data_addr = cpu_to_le32(msg_data); - - spin_lock_irq(&host->lock); - assert(host->state == HST_DEV_SCAN_START || - host->state == HST_DEV_SCAN); - spin_unlock_irq(&host->lock); - - DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag); - blk_execute_rq_nowait(host->oob_q, NULL, rq, true, NULL); - - return 0; - -err_out: - spin_lock_irq(&host->lock); - host->state = HST_ERROR; - spin_unlock_irq(&host->lock); - return rc; -} - -typedef unsigned int (*carm_sspc_t)(struct carm_host *, unsigned int, void *); - -static int carm_send_special (struct carm_host *host, carm_sspc_t func) -{ - struct request *rq; - struct carm_request *crq; - struct carm_msg_ioctl *ioc; - void *mem; - unsigned int msg_size; - int rc; - - rq = blk_mq_alloc_request(host->oob_q, REQ_OP_DRV_OUT, 0); - if (IS_ERR(rq)) - return -ENOMEM; - crq = blk_mq_rq_to_pdu(rq); - - mem = carm_ref_msg(host, rq->tag); - - msg_size = func(host, rq->tag, mem); - - ioc = mem; - crq->msg_type = ioc->type; - crq->msg_subtype = ioc->subtype; - rc = carm_lookup_bucket(msg_size); - BUG_ON(rc < 0); - crq->msg_bucket = (u32) rc; - - DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag); - blk_execute_rq_nowait(host->oob_q, NULL, rq, true, NULL); - - return 0; -} - -static unsigned int carm_fill_sync_time(struct carm_host *host, - unsigned int idx, void *mem) -{ - struct carm_msg_sync_time *st = mem; - - time64_t tv = ktime_get_real_seconds(); - - memset(st, 0, sizeof(*st)); - st->type = CARM_MSG_MISC; - st->subtype = MISC_SET_TIME; - st->handle = cpu_to_le32(TAG_ENCODE(idx)); - st->timestamp = cpu_to_le32(tv); - - return sizeof(struct carm_msg_sync_time); -} - -static unsigned int carm_fill_alloc_buf(struct carm_host *host, - unsigned int idx, void *mem) -{ - struct carm_msg_allocbuf *ab = mem; - - memset(ab, 0, sizeof(*ab)); - ab->type = CARM_MSG_MISC; - ab->subtype = MISC_ALLOC_MEM; - ab->handle = cpu_to_le32(TAG_ENCODE(idx)); - ab->n_sg = 1; - ab->sg_type = SGT_32BIT; - ab->addr = cpu_to_le32(host->shm_dma + (PDC_SHM_SIZE >> 1)); - ab->len = cpu_to_le32(PDC_SHM_SIZE >> 1); - ab->evt_pool = cpu_to_le32(host->shm_dma + (16 * 1024)); - ab->n_evt = cpu_to_le32(1024); - ab->rbuf_pool = cpu_to_le32(host->shm_dma); - ab->n_rbuf = cpu_to_le32(RMSG_Q_LEN); - ab->msg_pool = cpu_to_le32(host->shm_dma + RBUF_LEN); - ab->n_msg = cpu_to_le32(CARM_Q_LEN); - ab->sg[0].start = cpu_to_le32(host->shm_dma + (PDC_SHM_SIZE >> 1)); - ab->sg[0].len = cpu_to_le32(65536); - - return sizeof(struct carm_msg_allocbuf); -} - -static unsigned int carm_fill_scan_channels(struct carm_host *host, - unsigned int idx, void *mem) -{ - struct carm_msg_ioctl *ioc = mem; - u32 msg_data = (u32) (carm_ref_msg_dma(host, idx) + - IOC_SCAN_CHAN_OFFSET); - - memset(ioc, 0, sizeof(*ioc)); - ioc->type = CARM_MSG_IOCTL; - ioc->subtype = CARM_IOC_SCAN_CHAN; - ioc->handle = cpu_to_le32(TAG_ENCODE(idx)); - ioc->data_addr = cpu_to_le32(msg_data); - - /* fill output data area with "no device" default values */ - mem += IOC_SCAN_CHAN_OFFSET; - memset(mem, IOC_SCAN_CHAN_NODEV, CARM_MAX_PORTS); - - return IOC_SCAN_CHAN_OFFSET + CARM_MAX_PORTS; -} - -static unsigned int carm_fill_get_fw_ver(struct carm_host *host, - unsigned int idx, void *mem) -{ - struct carm_msg_get_fw_ver *ioc = mem; - u32 msg_data = (u32) (carm_ref_msg_dma(host, idx) + sizeof(*ioc)); - - memset(ioc, 0, sizeof(*ioc)); - ioc->type = CARM_MSG_MISC; - ioc->subtype = MISC_GET_FW_VER; - ioc->handle = cpu_to_le32(TAG_ENCODE(idx)); - ioc->data_addr = cpu_to_le32(msg_data); - - return sizeof(struct carm_msg_get_fw_ver) + - sizeof(struct carm_fw_ver); -} - -static inline void carm_push_q (struct carm_host *host, struct request_queue *q) -{ - unsigned int idx = host->wait_q_prod % CARM_MAX_WAIT_Q; - - blk_mq_stop_hw_queues(q); - VPRINTK("STOPPED QUEUE %p\n", q); - - host->wait_q[idx] = q; - host->wait_q_prod++; - BUG_ON(host->wait_q_prod == host->wait_q_cons); /* overrun */ -} - -static inline struct request_queue *carm_pop_q(struct carm_host *host) -{ - unsigned int idx; - - if (host->wait_q_prod == host->wait_q_cons) - return NULL; - - idx = host->wait_q_cons % CARM_MAX_WAIT_Q; - host->wait_q_cons++; - - return host->wait_q[idx]; -} - -static inline void carm_round_robin(struct carm_host *host) -{ - struct request_queue *q = carm_pop_q(host); - if (q) { - blk_mq_start_hw_queues(q); - VPRINTK("STARTED QUEUE %p\n", q); - } -} - -static inline enum dma_data_direction carm_rq_dir(struct request *rq) -{ - return op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE; -} - -static blk_status_t carm_queue_rq(struct blk_mq_hw_ctx *hctx, - const struct blk_mq_queue_data *bd) -{ - struct request_queue *q = hctx->queue; - struct request *rq = bd->rq; - struct carm_port *port = q->queuedata; - struct carm_host *host = port->host; - struct carm_request *crq = blk_mq_rq_to_pdu(rq); - struct carm_msg_rw *msg; - struct scatterlist *sg; - int i, n_elem = 0, rc; - unsigned int msg_size; - u32 tmp; - - crq->n_elem = 0; - sg_init_table(crq->sg, CARM_MAX_REQ_SG); - - blk_mq_start_request(rq); - - spin_lock_irq(&host->lock); - if (req_op(rq) == REQ_OP_DRV_OUT) - goto send_msg; - - /* get scatterlist from block layer */ - sg = &crq->sg[0]; - n_elem = blk_rq_map_sg(q, rq, sg); - if (n_elem <= 0) - goto out_ioerr; - - /* map scatterlist to PCI bus addresses */ - n_elem = dma_map_sg(&host->pdev->dev, sg, n_elem, carm_rq_dir(rq)); - if (n_elem <= 0) - goto out_ioerr; - - /* obey global hardware limit on S/G entries */ - if (host->hw_sg_used >= CARM_MAX_HOST_SG - n_elem) - goto out_resource; - - crq->n_elem = n_elem; - host->hw_sg_used += n_elem; - - /* - * build read/write message - */ - - VPRINTK("build msg\n"); - msg = (struct carm_msg_rw *) carm_ref_msg(host, rq->tag); - - if (rq_data_dir(rq) == WRITE) { - msg->type = CARM_MSG_WRITE; - crq->msg_type = CARM_MSG_WRITE; - } else { - msg->type = CARM_MSG_READ; - crq->msg_type = CARM_MSG_READ; - } - - msg->id = port->port_no; - msg->sg_count = n_elem; - msg->sg_type = SGT_32BIT; - msg->handle = cpu_to_le32(TAG_ENCODE(rq->tag)); - msg->lba = cpu_to_le32(blk_rq_pos(rq) & 0xffffffff); - tmp = (blk_rq_pos(rq) >> 16) >> 16; - msg->lba_high = cpu_to_le16( (u16) tmp ); - msg->lba_count = cpu_to_le16(blk_rq_sectors(rq)); - - msg_size = sizeof(struct carm_msg_rw) - sizeof(msg->sg); - for (i = 0; i < n_elem; i++) { - struct carm_msg_sg *carm_sg = &msg->sg[i]; - carm_sg->start = cpu_to_le32(sg_dma_address(&crq->sg[i])); - carm_sg->len = cpu_to_le32(sg_dma_len(&crq->sg[i])); - msg_size += sizeof(struct carm_msg_sg); - } - - rc = carm_lookup_bucket(msg_size); - BUG_ON(rc < 0); - crq->msg_bucket = (u32) rc; -send_msg: - /* - * queue read/write message to hardware - */ - VPRINTK("send msg, tag == %u\n", rq->tag); - rc = carm_send_msg(host, crq, rq->tag); - if (rc) { - host->hw_sg_used -= n_elem; - goto out_resource; - } - - spin_unlock_irq(&host->lock); - return BLK_STS_OK; -out_resource: - dma_unmap_sg(&host->pdev->dev, &crq->sg[0], n_elem, carm_rq_dir(rq)); - carm_push_q(host, q); - spin_unlock_irq(&host->lock); - return BLK_STS_DEV_RESOURCE; -out_ioerr: - carm_round_robin(host); - spin_unlock_irq(&host->lock); - return BLK_STS_IOERR; -} - -static void carm_handle_array_info(struct carm_host *host, - struct carm_request *crq, u8 *mem, - blk_status_t error) -{ - struct carm_port *port; - u8 *msg_data = mem + sizeof(struct carm_array_info); - struct carm_array_info *desc = (struct carm_array_info *) msg_data; - u64 lo, hi; - int cur_port; - size_t slen; - - DPRINTK("ENTER\n"); - - if (error) - goto out; - if (le32_to_cpu(desc->array_status) & ARRAY_NO_EXIST) - goto out; - - cur_port = host->cur_scan_dev; - - /* should never occur */ - if ((cur_port < 0) || (cur_port >= CARM_MAX_PORTS)) { - printk(KERN_ERR PFX "BUG: cur_scan_dev==%d, array_id==%d\n", - cur_port, (int) desc->array_id); - goto out; - } - - port = &host->port[cur_port]; - - lo = (u64) le32_to_cpu(desc->size); - hi = (u64) le16_to_cpu(desc->size_hi); - - port->capacity = lo | (hi << 32); - port->dev_geom_head = le16_to_cpu(desc->head); - port->dev_geom_sect = le16_to_cpu(desc->sect); - port->dev_geom_cyl = le16_to_cpu(desc->cyl); - - host->dev_active |= (1 << cur_port); - - strncpy(port->name, desc->name, sizeof(port->name)); - port->name[sizeof(port->name) - 1] = 0; - slen = strlen(port->name); - while (slen && (port->name[slen - 1] == ' ')) { - port->name[slen - 1] = 0; - slen--; - } - - printk(KERN_INFO DRV_NAME "(%s): port %u device %Lu sectors\n", - pci_name(host->pdev), port->port_no, - (unsigned long long) port->capacity); - printk(KERN_INFO DRV_NAME "(%s): port %u device \"%s\"\n", - pci_name(host->pdev), port->port_no, port->name); - -out: - assert(host->state == HST_DEV_SCAN); - schedule_work(&host->fsm_task); -} - -static void carm_handle_scan_chan(struct carm_host *host, - struct carm_request *crq, u8 *mem, - blk_status_t error) -{ - u8 *msg_data = mem + IOC_SCAN_CHAN_OFFSET; - unsigned int i, dev_count = 0; - int new_state = HST_DEV_SCAN_START; - - DPRINTK("ENTER\n"); - - if (error) { - new_state = HST_ERROR; - goto out; - } - - /* TODO: scan and support non-disk devices */ - for (i = 0; i < 8; i++) - if (msg_data[i] == 0) { /* direct-access device (disk) */ - host->dev_present |= (1 << i); - dev_count++; - } - - printk(KERN_INFO DRV_NAME "(%s): found %u interesting devices\n", - pci_name(host->pdev), dev_count); - -out: - assert(host->state == HST_PORT_SCAN); - host->state = new_state; - schedule_work(&host->fsm_task); -} - -static void carm_handle_generic(struct carm_host *host, - struct carm_request *crq, blk_status_t error, - int cur_state, int next_state) -{ - DPRINTK("ENTER\n"); - - assert(host->state == cur_state); - if (error) - host->state = HST_ERROR; - else - host->state = next_state; - schedule_work(&host->fsm_task); -} - -static inline void carm_handle_resp(struct carm_host *host, - __le32 ret_handle_le, u32 status) -{ - u32 handle = le32_to_cpu(ret_handle_le); - unsigned int msg_idx; - struct request *rq; - struct carm_request *crq; - blk_status_t error = (status == RMSG_OK) ? 0 : BLK_STS_IOERR; - u8 *mem; - - VPRINTK("ENTER, handle == 0x%x\n", handle); - - if (unlikely(!TAG_VALID(handle))) { - printk(KERN_ERR DRV_NAME "(%s): BUG: invalid tag 0x%x\n", - pci_name(host->pdev), handle); - return; - } - - msg_idx = TAG_DECODE(handle); - VPRINTK("tag == %u\n", msg_idx); - - rq = blk_mq_tag_to_rq(host->tag_set.tags[0], msg_idx); - crq = blk_mq_rq_to_pdu(rq); - - /* fast path */ - if (likely(crq->msg_type == CARM_MSG_READ || - crq->msg_type == CARM_MSG_WRITE)) { - dma_unmap_sg(&host->pdev->dev, &crq->sg[0], crq->n_elem, - carm_rq_dir(rq)); - goto done; - } - - mem = carm_ref_msg(host, msg_idx); - - switch (crq->msg_type) { - case CARM_MSG_IOCTL: { - switch (crq->msg_subtype) { - case CARM_IOC_SCAN_CHAN: - carm_handle_scan_chan(host, crq, mem, error); - goto done; - default: - /* unknown / invalid response */ - goto err_out; - } - break; - } - - case CARM_MSG_MISC: { - switch (crq->msg_subtype) { - case MISC_ALLOC_MEM: - carm_handle_generic(host, crq, error, - HST_ALLOC_BUF, HST_SYNC_TIME); - goto done; - case MISC_SET_TIME: - carm_handle_generic(host, crq, error, - HST_SYNC_TIME, HST_GET_FW_VER); - goto done; - case MISC_GET_FW_VER: { - struct carm_fw_ver *ver = (struct carm_fw_ver *) - (mem + sizeof(struct carm_msg_get_fw_ver)); - if (!error) { - host->fw_ver = le32_to_cpu(ver->version); - host->flags |= (ver->features & FL_FW_VER_MASK); - } - carm_handle_generic(host, crq, error, - HST_GET_FW_VER, HST_PORT_SCAN); - goto done; - } - default: - /* unknown / invalid response */ - goto err_out; - } - break; - } - - case CARM_MSG_ARRAY: { - switch (crq->msg_subtype) { - case CARM_ARRAY_INFO: - carm_handle_array_info(host, crq, mem, error); - break; - default: - /* unknown / invalid response */ - goto err_out; - } - break; - } - - default: - /* unknown / invalid response */ - goto err_out; - } - - return; - -err_out: - printk(KERN_WARNING DRV_NAME "(%s): BUG: unhandled message type %d/%d\n", - pci_name(host->pdev), crq->msg_type, crq->msg_subtype); - error = BLK_STS_IOERR; -done: - host->hw_sg_used -= crq->n_elem; - blk_mq_end_request(blk_mq_rq_from_pdu(crq), error); - - if (host->hw_sg_used <= CARM_SG_LOW_WATER) - carm_round_robin(host); -} - -static inline void carm_handle_responses(struct carm_host *host) -{ - void __iomem *mmio = host->mmio; - struct carm_response *resp = (struct carm_response *) host->shm; - unsigned int work = 0; - unsigned int idx = host->resp_idx % RMSG_Q_LEN; - - while (1) { - u32 status = le32_to_cpu(resp[idx].status); - - if (status == 0xffffffff) { - VPRINTK("ending response on index %u\n", idx); - writel(idx << 3, mmio + CARM_RESP_IDX); - break; - } - - /* response to a message we sent */ - else if ((status & (1 << 31)) == 0) { - VPRINTK("handling msg response on index %u\n", idx); - carm_handle_resp(host, resp[idx].ret_handle, status); - resp[idx].status = cpu_to_le32(0xffffffff); - } - - /* asynchronous events the hardware throws our way */ - else if ((status & 0xff000000) == (1 << 31)) { - u8 *evt_type_ptr = (u8 *) &resp[idx]; - u8 evt_type = *evt_type_ptr; - printk(KERN_WARNING DRV_NAME "(%s): unhandled event type %d\n", - pci_name(host->pdev), (int) evt_type); - resp[idx].status = cpu_to_le32(0xffffffff); - } - - idx = NEXT_RESP(idx); - work++; - } - - VPRINTK("EXIT, work==%u\n", work); - host->resp_idx += work; -} - -static irqreturn_t carm_interrupt(int irq, void *__host) -{ - struct carm_host *host = __host; - void __iomem *mmio; - u32 mask; - int handled = 0; - unsigned long flags; - - if (!host) { - VPRINTK("no host\n"); - return IRQ_NONE; - } - - spin_lock_irqsave(&host->lock, flags); - - mmio = host->mmio; - - /* reading should also clear interrupts */ - mask = readl(mmio + CARM_INT_STAT); - - if (mask == 0 || mask == 0xffffffff) { - VPRINTK("no work, mask == 0x%x\n", mask); - goto out; - } - - if (mask & INT_ACK_MASK) - writel(mask, mmio + CARM_INT_STAT); - - if (unlikely(host->state == HST_INVALID)) { - VPRINTK("not initialized yet, mask = 0x%x\n", mask); - goto out; - } - - if (mask & CARM_HAVE_RESP) { - handled = 1; - carm_handle_responses(host); - } - -out: - spin_unlock_irqrestore(&host->lock, flags); - VPRINTK("EXIT\n"); - return IRQ_RETVAL(handled); -} - -static void carm_fsm_task (struct work_struct *work) -{ - struct carm_host *host = - container_of(work, struct carm_host, fsm_task); - unsigned long flags; - unsigned int state; - int rc, i, next_dev; - int reschedule = 0; - int new_state = HST_INVALID; - - spin_lock_irqsave(&host->lock, flags); - state = host->state; - spin_unlock_irqrestore(&host->lock, flags); - - DPRINTK("ENTER, state == %s\n", state_name[state]); - - switch (state) { - case HST_PROBE_START: - new_state = HST_ALLOC_BUF; - reschedule = 1; - break; - - case HST_ALLOC_BUF: - rc = carm_send_special(host, carm_fill_alloc_buf); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - break; - - case HST_SYNC_TIME: - rc = carm_send_special(host, carm_fill_sync_time); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - break; - - case HST_GET_FW_VER: - rc = carm_send_special(host, carm_fill_get_fw_ver); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - break; - - case HST_PORT_SCAN: - rc = carm_send_special(host, carm_fill_scan_channels); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - break; - - case HST_DEV_SCAN_START: - host->cur_scan_dev = -1; - new_state = HST_DEV_SCAN; - reschedule = 1; - break; - - case HST_DEV_SCAN: - next_dev = -1; - for (i = host->cur_scan_dev + 1; i < CARM_MAX_PORTS; i++) - if (host->dev_present & (1 << i)) { - next_dev = i; - break; - } - - if (next_dev >= 0) { - host->cur_scan_dev = next_dev; - rc = carm_array_info(host, next_dev); - if (rc) { - new_state = HST_ERROR; - reschedule = 1; - } - } else { - new_state = HST_DEV_ACTIVATE; - reschedule = 1; - } - break; - - case HST_DEV_ACTIVATE: { - int activated = 0; - for (i = 0; i < CARM_MAX_PORTS; i++) - if (host->dev_active & (1 << i)) { - struct carm_port *port = &host->port[i]; - struct gendisk *disk = port->disk; - - set_capacity(disk, port->capacity); - add_disk(disk); - activated++; - } - - printk(KERN_INFO DRV_NAME "(%s): %d ports activated\n", - pci_name(host->pdev), activated); - - new_state = HST_PROBE_FINISHED; - reschedule = 1; - break; - } - - case HST_PROBE_FINISHED: - complete(&host->probe_comp); - break; - - case HST_ERROR: - /* FIXME: TODO */ - break; - - default: - /* should never occur */ - printk(KERN_ERR PFX "BUG: unknown state %d\n", state); - assert(0); - break; - } - - if (new_state != HST_INVALID) { - spin_lock_irqsave(&host->lock, flags); - host->state = new_state; - spin_unlock_irqrestore(&host->lock, flags); - } - if (reschedule) - schedule_work(&host->fsm_task); -} - -static int carm_init_wait(void __iomem *mmio, u32 bits, unsigned int test_bit) -{ - unsigned int i; - - for (i = 0; i < 50000; i++) { - u32 tmp = readl(mmio + CARM_LMUC); - udelay(100); - - if (test_bit) { - if ((tmp & bits) == bits) - return 0; - } else { - if ((tmp & bits) == 0) - return 0; - } - - cond_resched(); - } - - printk(KERN_ERR PFX "carm_init_wait timeout, bits == 0x%x, test_bit == %s\n", - bits, test_bit ? "yes" : "no"); - return -EBUSY; -} - -static void carm_init_responses(struct carm_host *host) -{ - void __iomem *mmio = host->mmio; - unsigned int i; - struct carm_response *resp = (struct carm_response *) host->shm; - - for (i = 0; i < RMSG_Q_LEN; i++) - resp[i].status = cpu_to_le32(0xffffffff); - - writel(0, mmio + CARM_RESP_IDX); -} - -static int carm_init_host(struct carm_host *host) -{ - void __iomem *mmio = host->mmio; - u32 tmp; - u8 tmp8; - int rc; - - DPRINTK("ENTER\n"); - - writel(0, mmio + CARM_INT_MASK); - - tmp8 = readb(mmio + CARM_INITC); - if (tmp8 & 0x01) { - tmp8 &= ~0x01; - writeb(tmp8, mmio + CARM_INITC); - readb(mmio + CARM_INITC); /* flush */ - - DPRINTK("snooze...\n"); - msleep(5000); - } - - tmp = readl(mmio + CARM_HMUC); - if (tmp & CARM_CME) { - DPRINTK("CME bit present, waiting\n"); - rc = carm_init_wait(mmio, CARM_CME, 1); - if (rc) { - DPRINTK("EXIT, carm_init_wait 1 failed\n"); - return rc; - } - } - if (tmp & CARM_RME) { - DPRINTK("RME bit present, waiting\n"); - rc = carm_init_wait(mmio, CARM_RME, 1); - if (rc) { - DPRINTK("EXIT, carm_init_wait 2 failed\n"); - return rc; - } - } - - tmp &= ~(CARM_RME | CARM_CME); - writel(tmp, mmio + CARM_HMUC); - readl(mmio + CARM_HMUC); /* flush */ - - rc = carm_init_wait(mmio, CARM_RME | CARM_CME, 0); - if (rc) { - DPRINTK("EXIT, carm_init_wait 3 failed\n"); - return rc; - } - - carm_init_buckets(mmio); - - writel(host->shm_dma & 0xffffffff, mmio + RBUF_ADDR_LO); - writel((host->shm_dma >> 16) >> 16, mmio + RBUF_ADDR_HI); - writel(RBUF_LEN, mmio + RBUF_BYTE_SZ); - - tmp = readl(mmio + CARM_HMUC); - tmp |= (CARM_RME | CARM_CME | CARM_WZBC); - writel(tmp, mmio + CARM_HMUC); - readl(mmio + CARM_HMUC); /* flush */ - - rc = carm_init_wait(mmio, CARM_RME | CARM_CME, 1); - if (rc) { - DPRINTK("EXIT, carm_init_wait 4 failed\n"); - return rc; - } - - writel(0, mmio + CARM_HMPHA); - writel(INT_DEF_MASK, mmio + CARM_INT_MASK); - - carm_init_responses(host); - - /* start initialization, probing state machine */ - spin_lock_irq(&host->lock); - assert(host->state == HST_INVALID); - host->state = HST_PROBE_START; - spin_unlock_irq(&host->lock); - schedule_work(&host->fsm_task); - - DPRINTK("EXIT\n"); - return 0; -} - -static const struct blk_mq_ops carm_mq_ops = { - .queue_rq = carm_queue_rq, -}; - -static int carm_init_disk(struct carm_host *host, unsigned int port_no) -{ - struct carm_port *port = &host->port[port_no]; - struct gendisk *disk; - struct request_queue *q; - - port->host = host; - port->port_no = port_no; - - disk = alloc_disk(CARM_MINORS_PER_MAJOR); - if (!disk) - return -ENOMEM; - - port->disk = disk; - sprintf(disk->disk_name, DRV_NAME "/%u", - (unsigned int)host->id * CARM_MAX_PORTS + port_no); - disk->major = host->major; - disk->first_minor = port_no * CARM_MINORS_PER_MAJOR; - disk->fops = &carm_bd_ops; - disk->private_data = port; - - q = blk_mq_init_queue(&host->tag_set); - if (IS_ERR(q)) - return PTR_ERR(q); - - blk_queue_max_segments(q, CARM_MAX_REQ_SG); - blk_queue_segment_boundary(q, CARM_SG_BOUNDARY); - - q->queuedata = port; - disk->queue = q; - return 0; -} - -static void carm_free_disk(struct carm_host *host, unsigned int port_no) -{ - struct carm_port *port = &host->port[port_no]; - struct gendisk *disk = port->disk; - - if (!disk) - return; - - if (disk->flags & GENHD_FL_UP) - del_gendisk(disk); - if (disk->queue) - blk_cleanup_queue(disk->queue); - put_disk(disk); -} - -static int carm_init_shm(struct carm_host *host) -{ - host->shm = dma_alloc_coherent(&host->pdev->dev, CARM_SHM_SIZE, - &host->shm_dma, GFP_KERNEL); - if (!host->shm) - return -ENOMEM; - - host->msg_base = host->shm + RBUF_LEN; - host->msg_dma = host->shm_dma + RBUF_LEN; - - memset(host->shm, 0xff, RBUF_LEN); - memset(host->msg_base, 0, PDC_SHM_SIZE - RBUF_LEN); - - return 0; -} - -static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) -{ - struct carm_host *host; - int rc; - struct request_queue *q; - unsigned int i; - - printk_once(KERN_DEBUG DRV_NAME " version " DRV_VERSION "\n"); - - rc = pci_enable_device(pdev); - if (rc) - return rc; - - rc = pci_request_regions(pdev, DRV_NAME); - if (rc) - goto err_out; - - rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); - if (rc) { - printk(KERN_ERR DRV_NAME "(%s): DMA mask failure\n", - pci_name(pdev)); - goto err_out_regions; - } - - host = kzalloc(sizeof(*host), GFP_KERNEL); - if (!host) { - printk(KERN_ERR DRV_NAME "(%s): memory alloc failure\n", - pci_name(pdev)); - rc = -ENOMEM; - goto err_out_regions; - } - - host->pdev = pdev; - spin_lock_init(&host->lock); - INIT_WORK(&host->fsm_task, carm_fsm_task); - init_completion(&host->probe_comp); - - host->mmio = ioremap(pci_resource_start(pdev, 0), - pci_resource_len(pdev, 0)); - if (!host->mmio) { - printk(KERN_ERR DRV_NAME "(%s): MMIO alloc failure\n", - pci_name(pdev)); - rc = -ENOMEM; - goto err_out_kfree; - } - - rc = carm_init_shm(host); - if (rc) { - printk(KERN_ERR DRV_NAME "(%s): DMA SHM alloc failure\n", - pci_name(pdev)); - goto err_out_iounmap; - } - - memset(&host->tag_set, 0, sizeof(host->tag_set)); - host->tag_set.ops = &carm_mq_ops; - host->tag_set.cmd_size = sizeof(struct carm_request); - host->tag_set.nr_hw_queues = 1; - host->tag_set.nr_maps = 1; - host->tag_set.queue_depth = max_queue; - host->tag_set.numa_node = NUMA_NO_NODE; - host->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - - rc = blk_mq_alloc_tag_set(&host->tag_set); - if (rc) - goto err_out_dma_free; - - q = blk_mq_init_queue(&host->tag_set); - if (IS_ERR(q)) { - rc = PTR_ERR(q); - blk_mq_free_tag_set(&host->tag_set); - goto err_out_dma_free; - } - - host->oob_q = q; - q->queuedata = host; - - /* - * Figure out which major to use: 160, 161, or dynamic - */ - if (!test_and_set_bit(0, &carm_major_alloc)) - host->major = 160; - else if (!test_and_set_bit(1, &carm_major_alloc)) - host->major = 161; - else - host->flags |= FL_DYN_MAJOR; - - host->id = carm_host_id; - sprintf(host->name, DRV_NAME "%d", carm_host_id); - - rc = register_blkdev(host->major, host->name); - if (rc < 0) - goto err_out_free_majors; - if (host->flags & FL_DYN_MAJOR) - host->major = rc; - - for (i = 0; i < CARM_MAX_PORTS; i++) { - rc = carm_init_disk(host, i); - if (rc) - goto err_out_blkdev_disks; - } - - pci_set_master(pdev); - - rc = request_irq(pdev->irq, carm_interrupt, IRQF_SHARED, DRV_NAME, host); - if (rc) { - printk(KERN_ERR DRV_NAME "(%s): irq alloc failure\n", - pci_name(pdev)); - goto err_out_blkdev_disks; - } - - rc = carm_init_host(host); - if (rc) - goto err_out_free_irq; - - DPRINTK("waiting for probe_comp\n"); - wait_for_completion(&host->probe_comp); - - printk(KERN_INFO "%s: pci %s, ports %d, io %llx, irq %u, major %d\n", - host->name, pci_name(pdev), (int) CARM_MAX_PORTS, - (unsigned long long)pci_resource_start(pdev, 0), - pdev->irq, host->major); - - carm_host_id++; - pci_set_drvdata(pdev, host); - return 0; - -err_out_free_irq: - free_irq(pdev->irq, host); -err_out_blkdev_disks: - for (i = 0; i < CARM_MAX_PORTS; i++) - carm_free_disk(host, i); - unregister_blkdev(host->major, host->name); -err_out_free_majors: - if (host->major == 160) - clear_bit(0, &carm_major_alloc); - else if (host->major == 161) - clear_bit(1, &carm_major_alloc); - blk_cleanup_queue(host->oob_q); - blk_mq_free_tag_set(&host->tag_set); -err_out_dma_free: - dma_free_coherent(&pdev->dev, CARM_SHM_SIZE, host->shm, host->shm_dma); -err_out_iounmap: - iounmap(host->mmio); -err_out_kfree: - kfree(host); -err_out_regions: - pci_release_regions(pdev); -err_out: - pci_disable_device(pdev); - return rc; -} - -static void carm_remove_one (struct pci_dev *pdev) -{ - struct carm_host *host = pci_get_drvdata(pdev); - unsigned int i; - - if (!host) { - printk(KERN_ERR PFX "BUG: no host data for PCI(%s)\n", - pci_name(pdev)); - return; - } - - free_irq(pdev->irq, host); - for (i = 0; i < CARM_MAX_PORTS; i++) - carm_free_disk(host, i); - unregister_blkdev(host->major, host->name); - if (host->major == 160) - clear_bit(0, &carm_major_alloc); - else if (host->major == 161) - clear_bit(1, &carm_major_alloc); - blk_cleanup_queue(host->oob_q); - blk_mq_free_tag_set(&host->tag_set); - dma_free_coherent(&pdev->dev, CARM_SHM_SIZE, host->shm, host->shm_dma); - iounmap(host->mmio); - kfree(host); - pci_release_regions(pdev); - pci_disable_device(pdev); -} - -module_pci_driver(carm_driver); From d3b74c288d84e10e9b2c0671c3846f73070e6416 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 31 Oct 2022 12:44:09 +0100 Subject: [PATCH 3435/4345] bonding (gcc13): synchronize bond_{a,t}lb_xmit() types commit 777fa87c7682228e155cf0892ba61cb2ab1fe3ae upstream. Both bond_alb_xmit() and bond_tlb_xmit() produce a valid warning with gcc-13: drivers/net/bonding/bond_alb.c:1409:13: error: conflicting types for 'bond_tlb_xmit' due to enum/integer mismatch; have 'netdev_tx_t(struct sk_buff *, struct net_device *)' ... include/net/bond_alb.h:160:5: note: previous declaration of 'bond_tlb_xmit' with type 'int(struct sk_buff *, struct net_device *)' drivers/net/bonding/bond_alb.c:1523:13: error: conflicting types for 'bond_alb_xmit' due to enum/integer mismatch; have 'netdev_tx_t(struct sk_buff *, struct net_device *)' ... include/net/bond_alb.h:159:5: note: previous declaration of 'bond_alb_xmit' with type 'int(struct sk_buff *, struct net_device *)' I.e. the return type of the declaration is int, while the definitions spell netdev_tx_t. Synchronize both of them to the latter. Cc: Martin Liska Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20221031114409.10417-1-jirislaby@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/bond_alb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index 191c36afa1f4..9dc082b2d543 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -156,8 +156,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave); void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave); void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char link); void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave); -int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev); -int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev); struct slave *bond_xmit_alb_slave_get(struct bonding *bond, struct sk_buff *skb); struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, From 9214a5484e33f972845285d9f5b08456c6d59741 Mon Sep 17 00:00:00 2001 From: Qilin Tan Date: Fri, 31 Mar 2023 17:26:56 +0800 Subject: [PATCH 3436/4345] f2fs: fix iostat lock protection commit 144f1cd40bf91fb3ac1d41806470756ce774f389 upstream. Made iostat lock irq safe to avoid potentinal deadlock. Deadlock scenario: f2fs_attr_store -> f2fs_sbi_store -> _sbi_store -> spin_lock(sbi->iostat_lock) -> scsi_end_request -> bio_endio -> f2fs_dio_read_end_io -> f2fs_update_iostat -> spin_lock_irqsave(sbi->iostat_lock) ===> Dead lock here Fixes: 61803e984307 ("f2fs: fix iostat related lock protection") Fixes: a1e09b03e6f5 ("f2fs: use iomap for direct I/O") Signed-off-by: Qilin Tan Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim Cc: Daniel Rosenberg Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/sysfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index a7e7d68256e0..2501c11d8c46 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -403,9 +403,9 @@ out: if (!strcmp(a->attr.name, "iostat_period_ms")) { if (t < MIN_IOSTAT_PERIOD_MS || t > MAX_IOSTAT_PERIOD_MS) return -EINVAL; - spin_lock(&sbi->iostat_lock); + spin_lock_irq(&sbi->iostat_lock); sbi->iostat_period_ms = (unsigned int)t; - spin_unlock(&sbi->iostat_lock); + spin_unlock_irq(&sbi->iostat_lock); return count; } From b6d652f7fbdc9bb40b81eee1383e7a3eaa8fa49a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Jan 2023 09:07:01 +0100 Subject: [PATCH 3437/4345] blk-iocost: avoid 64-bit division in ioc_timer_fn commit 5f2779dfa7b8cc7dfd4a1b6586d86e0d193266f3 upstream. The behavior of 'enum' types has changed in gcc-13, so now the UNBUSY_THR_PCT constant is interpreted as a 64-bit number because it is defined as part of the same enum definition as some other constants that do not fit within a 32-bit integer. This in turn leads to some inefficient code on 32-bit architectures as well as a link error: arm-linux-gnueabi/bin/arm-linux-gnueabi-ld: block/blk-iocost.o: in function `ioc_timer_fn': blk-iocost.c:(.text+0x68e8): undefined reference to `__aeabi_uldivmod' arm-linux-gnueabi-ld: blk-iocost.c:(.text+0x6908): undefined reference to `__aeabi_uldivmod' Split the enum definition to keep the 64-bit timing constants in a separate enum type from those constants that can clearly fit within a smaller type. Signed-off-by: Arnd Bergmann Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20230118080706.3303186-1-arnd@kernel.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/blk-iocost.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 9255b642d6ad..02054ea03cb4 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -256,6 +256,11 @@ enum { VRATE_MIN = VTIME_PER_USEC * VRATE_MIN_PPM / MILLION, VRATE_CLAMP_ADJ_PCT = 4, + /* switch iff the conditions are met for longer than this */ + AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC, +}; + +enum { /* if IOs end up waiting for requests, issue less */ RQ_WAIT_BUSY_PCT = 5, @@ -294,9 +299,6 @@ enum { /* don't let cmds which take a very long time pin lagging for too long */ MAX_LAGGING_PERIODS = 10, - /* switch iff the conditions are met for longer than this */ - AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC, - /* * Count IO size in 4k pages. The 12bit shift helps keeping * size-proportional components of cost calculation in closer From 318e2c18da7c783e7174e6eb3bd958ab5f87f1df Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Tue, 13 Dec 2022 13:08:26 +0100 Subject: [PATCH 3438/4345] block/blk-iocost (gcc13): keep large values in a new enum commit ff1cc97b1f4c10db224f276d9615b22835b8c424 upstream. Since gcc13, each member of an enum has the same type as the enum [1]. And that is inherited from its members. Provided: VTIME_PER_SEC_SHIFT = 37, VTIME_PER_SEC = 1LLU << VTIME_PER_SEC_SHIFT, ... AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC, the named type is unsigned long. This generates warnings with gcc-13: block/blk-iocost.c: In function 'ioc_weight_prfill': block/blk-iocost.c:3037:37: error: format '%u' expects argument of type 'unsigned int', but argument 4 has type 'long unsigned int' block/blk-iocost.c: In function 'ioc_weight_show': block/blk-iocost.c:3047:34: error: format '%u' expects argument of type 'unsigned int', but argument 3 has type 'long unsigned int' So split the anonymous enum with large values to a separate enum, so that they don't affect other members. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=36113 Cc: Martin Liska Cc: Tejun Heo Cc: Josef Bacik Cc: Jens Axboe Cc: cgroups@vger.kernel.org Cc: linux-block@vger.kernel.org Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20221213120826.17446-1-jirislaby@kernel.org Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/blk-iocost.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 02054ea03cb4..105ad23dff06 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -232,7 +232,9 @@ enum { /* 1/64k is granular enough and can easily be handled w/ u32 */ WEIGHT_ONE = 1 << 16, +}; +enum { /* * As vtime is used to calculate the cost of each IO, it needs to * be fairly high precision. For example, it should be able to From f7e208d1c5499a52ffa984693ba8036cb60678bc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 9 Jun 2023 16:58:27 +0200 Subject: [PATCH 3439/4345] i40iw: fix build warning in i40iw_manage_apbvt() Not upstream as this function is no longer around anymore. The function i40iw_manage_apbvt() has the wrong prototype match from the .h file to the .c declaration, so fix it up, otherwise gcc-13 complains (rightfully) that the type is incorrect. Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/i40iw/i40iw.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index 832b80de004f..13545fcdc5ad 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -422,9 +422,8 @@ void i40iw_manage_arp_cache(struct i40iw_device *iwdev, bool ipv4, u32 action); -int i40iw_manage_apbvt(struct i40iw_device *iwdev, - u16 accel_local_port, - bool add_port); +enum i40iw_status_code i40iw_manage_apbvt(struct i40iw_device *iwdev, + u16 accel_local_port, bool add_port); struct i40iw_cqp_request *i40iw_get_cqp_request(struct i40iw_cqp *cqp, bool wait); void i40iw_free_cqp_request(struct i40iw_cqp *cqp, struct i40iw_cqp_request *cqp_request); From 15ca8d584c1abc81c6f01d9aae8639630e733b46 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 9 Jun 2023 17:10:11 +0200 Subject: [PATCH 3440/4345] i40e: fix build warnings in i40e_alloc.h Not upstream as it was fixed in a much larger api change in newer kernels. gcc-13 rightfully complains that enum is not the same as an int, so fix up the function prototypes in i40e_alloc.h to be correct, solving a bunch of build warnings. Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/i40e/i40e_alloc.h | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_alloc.h b/drivers/net/ethernet/intel/i40e/i40e_alloc.h index cb8689222c8b..55ba6b690ab6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_alloc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_alloc.h @@ -20,16 +20,11 @@ enum i40e_memory_type { }; /* prototype for functions used for dynamic memory allocation */ -i40e_status i40e_allocate_dma_mem(struct i40e_hw *hw, - struct i40e_dma_mem *mem, - enum i40e_memory_type type, - u64 size, u32 alignment); -i40e_status i40e_free_dma_mem(struct i40e_hw *hw, - struct i40e_dma_mem *mem); -i40e_status i40e_allocate_virt_mem(struct i40e_hw *hw, - struct i40e_virt_mem *mem, - u32 size); -i40e_status i40e_free_virt_mem(struct i40e_hw *hw, - struct i40e_virt_mem *mem); +int i40e_allocate_dma_mem(struct i40e_hw *hw, struct i40e_dma_mem *mem, + enum i40e_memory_type type, u64 size, u32 alignment); +int i40e_free_dma_mem(struct i40e_hw *hw, struct i40e_dma_mem *mem); +int i40e_allocate_virt_mem(struct i40e_hw *hw, struct i40e_virt_mem *mem, + u32 size); +int i40e_free_virt_mem(struct i40e_hw *hw, struct i40e_virt_mem *mem); #endif /* _I40E_ALLOC_H_ */ From fa303270602d9d281a39c1e3a7454fa06452d70e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 9 Jun 2023 12:43:39 +0200 Subject: [PATCH 3441/4345] i40e: fix build warning in ice_fltr_add_mac_to_list() Not upstream as this was fixed in a much larger change in commit 5e24d5984c80 ("ice: Use int for ice_status") The function ice_fltr_add_mac_to_list() has the wrong prototype match from the .h file to the .c declaration, so fix it up, otherwise gcc-13 complains (rightfully) that the type is incorrect. Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/intel/ice/ice_fltr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index 2418d4fff037..e27b4de7e7aa 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -128,7 +128,7 @@ void ice_fltr_remove_all(struct ice_vsi *vsi) * @mac: MAC address to add * @action: filter action */ -int +enum ice_status ice_fltr_add_mac_to_list(struct ice_vsi *vsi, struct list_head *list, const u8 *mac, enum ice_sw_fwd_act_type action) { From e7c61c39d6d11758be5dc9971e1407213c062492 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sun, 25 Apr 2021 12:51:02 +0200 Subject: [PATCH 3442/4345] staging: vchiq_core: drop vchiq_status from vchiq_initialise commit abf2836a381a30763e24acd58da56fa615c6581a upstream. Replace the custom set of return values with proper Linux error codes for vchiq_initialise(). Reviewed-by: Nicolas Saenz Julienne Signed-off-by: Stefan Wahren Link: https://lore.kernel.org/r/1619347863-16080-11-git-send-email-stefan.wahren@i2se.com Signed-off-by: Greg Kroah-Hartman --- .../interface/vchiq_arm/vchiq_arm.c | 20 ++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 3d378da119e7..893d102d2dcf 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -147,12 +147,11 @@ vchiq_blocking_bulk_transfer(unsigned int handle, void *data, unsigned int size, enum vchiq_bulk_dir dir); #define VCHIQ_INIT_RETRIES 10 -enum vchiq_status vchiq_initialise(struct vchiq_instance **instance_out) +int vchiq_initialise(struct vchiq_instance **instance_out) { - enum vchiq_status status = VCHIQ_ERROR; struct vchiq_state *state; struct vchiq_instance *instance = NULL; - int i; + int i, ret; vchiq_log_trace(vchiq_core_log_level, "%s called", __func__); @@ -169,6 +168,7 @@ enum vchiq_status vchiq_initialise(struct vchiq_instance **instance_out) if (i == VCHIQ_INIT_RETRIES) { vchiq_log_error(vchiq_core_log_level, "%s: videocore not initialized\n", __func__); + ret = -ENOTCONN; goto failed; } else if (i > 0) { vchiq_log_warning(vchiq_core_log_level, @@ -180,6 +180,7 @@ enum vchiq_status vchiq_initialise(struct vchiq_instance **instance_out) if (!instance) { vchiq_log_error(vchiq_core_log_level, "%s: error allocating vchiq instance\n", __func__); + ret = -ENOMEM; goto failed; } @@ -190,13 +191,13 @@ enum vchiq_status vchiq_initialise(struct vchiq_instance **instance_out) *instance_out = instance; - status = VCHIQ_SUCCESS; + ret = 0; failed: vchiq_log_trace(vchiq_core_log_level, - "%s(%p): returning %d", __func__, instance, status); + "%s(%p): returning %d", __func__, instance, ret); - return status; + return ret; } EXPORT_SYMBOL(vchiq_initialise); @@ -2223,6 +2224,7 @@ vchiq_keepalive_thread_func(void *v) enum vchiq_status status; struct vchiq_instance *instance; unsigned int ka_handle; + int ret; struct vchiq_service_params_kernel params = { .fourcc = VCHIQ_MAKE_FOURCC('K', 'E', 'E', 'P'), @@ -2231,10 +2233,10 @@ vchiq_keepalive_thread_func(void *v) .version_min = KEEPALIVE_VER_MIN }; - status = vchiq_initialise(&instance); - if (status != VCHIQ_SUCCESS) { + ret = vchiq_initialise(&instance); + if (ret) { vchiq_log_error(vchiq_susp_log_level, - "%s vchiq_initialise failed %d", __func__, status); + "%s vchiq_initialise failed %d", __func__, ret); goto exit; } From 1ed651e234fd7295f167073dd66bd0050f7880c5 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Thu, 18 May 2023 15:04:25 +0200 Subject: [PATCH 3443/4345] spi: qup: Request DMA before enabling clocks [ Upstream commit 0c331fd1dccfba657129380ee084b95c1cedfbef ] It is usually better to request all necessary resources (clocks, regulators, ...) before starting to make use of them. That way they do not change state in case one of the resources is not available yet and probe deferral (-EPROBE_DEFER) is necessary. This is particularly important for DMA channels and IOMMUs which are not enforced by fw_devlink yet (unless you use fw_devlink.strict=1). spi-qup does this in the wrong order, the clocks are enabled and disabled again when the DMA channels are not available yet. This causes issues in some cases: On most SoCs one of the SPI QUP clocks is shared with the UART controller. When using earlycon UART is actively used during boot but might not have probed yet, usually for the same reason (waiting for the DMA controller). In this case, the brief enable/disable cycle ends up gating the clock and further UART console output will halt the system completely. Avoid this by requesting the DMA channels before changing the clock state. Fixes: 612762e82ae6 ("spi: qup: Add DMA capabilities") Signed-off-by: Stephan Gerhold Link: https://lore.kernel.org/r/20230518-spi-qup-clk-defer-v1-1-f49fc9ca4e02@gerhold.net Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-qup.c | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index 8bf58510cca6..2cc9bb413c10 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -1030,23 +1030,8 @@ static int spi_qup_probe(struct platform_device *pdev) return -ENXIO; } - ret = clk_prepare_enable(cclk); - if (ret) { - dev_err(dev, "cannot enable core clock\n"); - return ret; - } - - ret = clk_prepare_enable(iclk); - if (ret) { - clk_disable_unprepare(cclk); - dev_err(dev, "cannot enable iface clock\n"); - return ret; - } - master = spi_alloc_master(dev, sizeof(struct spi_qup)); if (!master) { - clk_disable_unprepare(cclk); - clk_disable_unprepare(iclk); dev_err(dev, "cannot allocate master\n"); return -ENOMEM; } @@ -1092,6 +1077,19 @@ static int spi_qup_probe(struct platform_device *pdev) spin_lock_init(&controller->lock); init_completion(&controller->done); + ret = clk_prepare_enable(cclk); + if (ret) { + dev_err(dev, "cannot enable core clock\n"); + goto error_dma; + } + + ret = clk_prepare_enable(iclk); + if (ret) { + clk_disable_unprepare(cclk); + dev_err(dev, "cannot enable iface clock\n"); + goto error_dma; + } + iomode = readl_relaxed(base + QUP_IO_M_MODES); size = QUP_IO_M_OUTPUT_BLOCK_SIZE(iomode); @@ -1121,7 +1119,7 @@ static int spi_qup_probe(struct platform_device *pdev) ret = spi_qup_set_state(controller, QUP_STATE_RESET); if (ret) { dev_err(dev, "cannot set RESET state\n"); - goto error_dma; + goto error_clk; } writel_relaxed(0, base + QUP_OPERATIONAL); @@ -1145,7 +1143,7 @@ static int spi_qup_probe(struct platform_device *pdev) ret = devm_request_irq(dev, irq, spi_qup_qup_irq, IRQF_TRIGGER_HIGH, pdev->name, controller); if (ret) - goto error_dma; + goto error_clk; pm_runtime_set_autosuspend_delay(dev, MSEC_PER_SEC); pm_runtime_use_autosuspend(dev); @@ -1160,11 +1158,12 @@ static int spi_qup_probe(struct platform_device *pdev) disable_pm: pm_runtime_disable(&pdev->dev); +error_clk: + clk_disable_unprepare(cclk); + clk_disable_unprepare(iclk); error_dma: spi_qup_release_dma(master); error: - clk_disable_unprepare(cclk); - clk_disable_unprepare(iclk); spi_master_put(master); return ret; } From 2d3e4c5b3e0583742ad2bd7d61232577c01cf52f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Jun 2023 09:47:13 +0100 Subject: [PATCH 3444/4345] afs: Fix setting of mtime when creating a file/dir/symlink [ Upstream commit a27648c742104a833a01c54becc24429898d85bf ] kafs incorrectly passes a zero mtime (ie. 1st Jan 1970) to the server when creating a file, dir or symlink because the mtime recorded in the afs_operation struct gets passed to the server by the marshalling routines, but the afs_mkdir(), afs_create() and afs_symlink() functions don't set it. This gets masked if a file or directory is subsequently modified. Fix this by filling in op->mtime before calling the create op. Fixes: e49c7b2f6de7 ("afs: Build an abstraction around an "operation" concept") Signed-off-by: David Howells Reviewed-by: Jeffrey Altman Reviewed-by: Marc Dionne cc: linux-afs@lists.infradead.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/afs/dir.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 159795059547..a59d6293a32b 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1313,6 +1313,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) op->dentry = dentry; op->create.mode = S_IFDIR | mode; op->create.reason = afs_edit_dir_for_mkdir; + op->mtime = current_time(dir); op->ops = &afs_mkdir_operation; return afs_do_sync_operation(op); } @@ -1616,6 +1617,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, op->dentry = dentry; op->create.mode = S_IFREG | mode; op->create.reason = afs_edit_dir_for_create; + op->mtime = current_time(dir); op->ops = &afs_create_operation; return afs_do_sync_operation(op); @@ -1745,6 +1747,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, op->ops = &afs_symlink_operation; op->create.reason = afs_edit_dir_for_symlink; op->create.symlink = content; + op->mtime = current_time(dir); return afs_do_sync_operation(op); error: From 99883d4a0be29ac364cdb27a41f403c630fdd01d Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 24 May 2023 16:39:32 +0200 Subject: [PATCH 3445/4345] wifi: mt76: mt7615: fix possible race in mt7615_mac_sta_poll [ Upstream commit 30bc32c7c1f975cc3c14e1c7dc437266311282cf ] Grab sta_poll_lock spinlock in mt7615_mac_sta_poll routine in order to avoid possible races with mt7615_mac_add_txs() or mt7615_mac_fill_rx() removing msta pointer from sta_poll_list. Fixes: a621372a04ac ("mt76: mt7615: rework mt7615_mac_sta_poll for usb code") Signed-off-by: Lorenzo Bianconi Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/48b23404b759de4f1db2ef85975c72a4aeb1097c.1684938695.git.lorenzo@kernel.org Signed-off-by: Sasha Levin --- drivers/net/wireless/mediatek/mt76/mt7615/mac.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index b26617026e83..4364f73b501d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -779,7 +779,10 @@ void mt7615_mac_sta_poll(struct mt7615_dev *dev) msta = list_first_entry(&sta_poll_list, struct mt7615_sta, poll_list); + + spin_lock_bh(&dev->sta_poll_lock); list_del_init(&msta->poll_list); + spin_unlock_bh(&dev->sta_poll_lock); addr = mt7615_mac_wtbl_addr(dev, msta->wcid.idx) + 19 * 4; From 9fcc3c3d26a049aa04e0bc0462f84a9a775f428e Mon Sep 17 00:00:00 2001 From: Qingfang DENG Date: Thu, 1 Jun 2023 09:54:32 +0800 Subject: [PATCH 3446/4345] neighbour: fix unaligned access to pneigh_entry [ Upstream commit ed779fe4c9b5a20b4ab4fd6f3e19807445bb78c7 ] After the blamed commit, the member key is longer 4-byte aligned. On platforms that do not support unaligned access, e.g., MIPS32R2 with unaligned_action set to 1, this will trigger a crash when accessing an IPv6 pneigh_entry, as the key is cast to an in6_addr pointer. Change the type of the key to u32 to make it aligned. Fixes: 62dd93181aaa ("[IPV6] NDISC: Set per-entry is_router flag in Proxy NA.") Signed-off-by: Qingfang DENG Link: https://lore.kernel.org/r/20230601015432.159066-1-dqfext@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/neighbour.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index d5767e25509c..abb22cfd4827 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -174,7 +174,7 @@ struct pneigh_entry { struct net_device *dev; u8 flags; u8 protocol; - u8 key[]; + u32 key[]; }; /* From 47ef881f1cbed2c4919a6d703380f1e31288ca81 Mon Sep 17 00:00:00 2001 From: Alexander Sverdlin Date: Wed, 31 May 2023 16:38:26 +0200 Subject: [PATCH 3447/4345] net: dsa: lan9303: allow vid != 0 in port_fdb_{add|del} methods [ Upstream commit 5a59a58ec25d44f853c26bdbfda47d73b3067435 ] LAN9303 doesn't associate FDB (ALR) entries with VLANs, it has just one global Address Logic Resolution table [1]. Ignore VID in port_fdb_{add|del} methods, go on with the global table. This is the same semantics as hellcreek or RZ/N1 implement. Visible symptoms: LAN9303_MDIO 5b050000.ethernet-1:00: port 2 failed to delete 00:xx:xx:xx:xx:cf vid 1 from fdb: -2 LAN9303_MDIO 5b050000.ethernet-1:00: port 2 failed to add 00:xx:xx:xx:xx:cf vid 1 to fdb: -95 [1] https://ww1.microchip.com/downloads/en/DeviceDoc/00002308A.pdf Fixes: 0620427ea0d6 ("net: dsa: lan9303: Add fdb/mdb manipulation") Signed-off-by: Alexander Sverdlin Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230531143826.477267-1-alexander.sverdlin@siemens.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/lan9303-core.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index deeed50a42c0..f5ab0bff4ac2 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1187,8 +1187,6 @@ static int lan9303_port_fdb_add(struct dsa_switch *ds, int port, struct lan9303 *chip = ds->priv; dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, addr, vid); - if (vid) - return -EOPNOTSUPP; return lan9303_alr_add_port(chip, addr, port, false); } @@ -1200,8 +1198,6 @@ static int lan9303_port_fdb_del(struct dsa_switch *ds, int port, struct lan9303 *chip = ds->priv; dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, addr, vid); - if (vid) - return -EOPNOTSUPP; lan9303_alr_del_port(chip, addr, port); return 0; From 8ab2bec9e16560b8c15023de04a9f7a65c472c17 Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Thu, 1 Jun 2023 16:41:52 +0800 Subject: [PATCH 3448/4345] net/smc: Avoid to access invalid RMBs' MRs in SMCRv1 ADD LINK CONT [ Upstream commit c308e9ec004721a656c193243eab61a8be324657 ] SMCRv1 has a similar issue to SMCRv2 (see link below) that may access invalid MRs of RMBs when construct LLC ADD LINK CONT messages. BUG: kernel NULL pointer dereference, address: 0000000000000014 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 5 PID: 48 Comm: kworker/5:0 Kdump: loaded Tainted: G W E 6.4.0-rc3+ #49 Workqueue: events smc_llc_add_link_work [smc] RIP: 0010:smc_llc_add_link_cont+0x160/0x270 [smc] RSP: 0018:ffffa737801d3d50 EFLAGS: 00010286 RAX: ffff964f82144000 RBX: ffffa737801d3dd8 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff964f81370c30 RBP: ffffa737801d3dd4 R08: ffff964f81370000 R09: ffffa737801d3db0 R10: 0000000000000001 R11: 0000000000000060 R12: ffff964f82e70000 R13: ffff964f81370c38 R14: ffffa737801d3dd3 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff9652bfd40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000014 CR3: 000000008fa20004 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: smc_llc_srv_rkey_exchange+0xa7/0x190 [smc] smc_llc_srv_add_link+0x3ae/0x5a0 [smc] smc_llc_add_link_work+0xb8/0x140 [smc] process_one_work+0x1e5/0x3f0 worker_thread+0x4d/0x2f0 ? __pfx_worker_thread+0x10/0x10 kthread+0xe5/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2c/0x50 When an alernate RNIC is available in system, SMC will try to add a new link based on the RNIC for resilience. All the RMBs in use will be mapped to the new link. Then the RMBs' MRs corresponding to the new link will be filled into LLC messages. For SMCRv1, they are ADD LINK CONT messages. However smc_llc_add_link_cont() may mistakenly access to unused RMBs which haven't been mapped to the new link and have no valid MRs, thus causing a crash. So this patch fixes it. Fixes: 87f88cda2128 ("net/smc: rkey processing for a new link as SMC client") Link: https://lore.kernel.org/r/1685101741-74826-3-git-send-email-guwen@linux.alibaba.com Signed-off-by: Wen Gu Reviewed-by: Wenjia Zhang Reviewed-by: Tony Lu Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/smc/smc_llc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 0ef15f8fba90..d5ee961ca72d 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -716,6 +716,8 @@ static int smc_llc_add_link_cont(struct smc_link *link, addc_llc->num_rkeys = *num_rkeys_todo; n = *num_rkeys_todo; for (i = 0; i < min_t(u8, n, SMC_LLC_RKEYS_PER_CONT_MSG); i++) { + while (*buf_pos && !(*buf_pos)->used) + *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); if (!*buf_pos) { addc_llc->num_rkeys = addc_llc->num_rkeys - *num_rkeys_todo; @@ -731,8 +733,6 @@ static int smc_llc_add_link_cont(struct smc_link *link, (*num_rkeys_todo)--; *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); - while (*buf_pos && !(*buf_pos)->used) - *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); } addc_llc->hd.common.type = SMC_LLC_ADD_LINK_CONT; addc_llc->hd.length = sizeof(struct smc_llc_msg_add_link_cont); From 83cfac5851c27669d2c0e091f5b7c61ff93702ea Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Jun 2023 12:37:47 +0000 Subject: [PATCH 3449/4345] net/sched: fq_pie: ensure reasonable TCA_FQ_PIE_QUANTUM values [ Upstream commit cd2b8113c2e8b9f5a88a942e1eaca61eba401b85 ] We got multiple syzbot reports, all duplicates of the following [1] syzbot managed to install fq_pie with a zero TCA_FQ_PIE_QUANTUM, thus triggering infinite loops. Use limits similar to sch_fq, with commits 3725a269815b ("pkt_sched: fq: avoid hang when quantum 0") and d9e15a273306 ("pkt_sched: fq: do not accept silly TCA_FQ_QUANTUM") [1] watchdog: BUG: soft lockup - CPU#0 stuck for 26s! [swapper/0:0] Modules linked in: irq event stamp: 172817 hardirqs last enabled at (172816): [] __el1_irq arch/arm64/kernel/entry-common.c:476 [inline] hardirqs last enabled at (172816): [] el1_interrupt+0x58/0x68 arch/arm64/kernel/entry-common.c:486 hardirqs last disabled at (172817): [] __el1_irq arch/arm64/kernel/entry-common.c:468 [inline] hardirqs last disabled at (172817): [] el1_interrupt+0x24/0x68 arch/arm64/kernel/entry-common.c:486 softirqs last enabled at (167634): [] softirq_handle_end kernel/softirq.c:414 [inline] softirqs last enabled at (167634): [] __do_softirq+0xac0/0xd54 kernel/softirq.c:600 softirqs last disabled at (167701): [] ____do_softirq+0x14/0x20 arch/arm64/kernel/irq.c:80 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.4.0-rc3-syzkaller-geb0f1697d729 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/28/2023 pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : fq_pie_qdisc_dequeue+0x10c/0x8ac net/sched/sch_fq_pie.c:246 lr : fq_pie_qdisc_dequeue+0xe4/0x8ac net/sched/sch_fq_pie.c:240 sp : ffff800008007210 x29: ffff800008007280 x28: ffff0000c86f7890 x27: ffff0000cb20c2e8 x26: ffff0000cb20c2f0 x25: dfff800000000000 x24: ffff0000cb20c2e0 x23: ffff0000c86f7880 x22: 0000000000000040 x21: 1fffe000190def10 x20: ffff0000cb20c2e0 x19: ffff0000cb20c2e0 x18: ffff800008006e60 x17: 0000000000000000 x16: ffff80000850af6c x15: 0000000000000302 x14: 0000000000000100 x13: 0000000000000000 x12: 0000000000000001 x11: 0000000000000302 x10: 0000000000000100 x9 : 0000000000000000 x8 : 0000000000000000 x7 : ffff80000841c468 x6 : 0000000000000000 x5 : 0000000000000001 x4 : 0000000000000001 x3 : 0000000000000000 x2 : ffff0000cb20c2e0 x1 : ffff0000cb20c2e0 x0 : 0000000000000001 Call trace: fq_pie_qdisc_dequeue+0x10c/0x8ac net/sched/sch_fq_pie.c:246 dequeue_skb net/sched/sch_generic.c:292 [inline] qdisc_restart net/sched/sch_generic.c:397 [inline] __qdisc_run+0x1fc/0x231c net/sched/sch_generic.c:415 __dev_xmit_skb net/core/dev.c:3868 [inline] __dev_queue_xmit+0xc80/0x3318 net/core/dev.c:4210 dev_queue_xmit include/linux/netdevice.h:3085 [inline] neigh_connected_output+0x2f8/0x38c net/core/neighbour.c:1581 neigh_output include/net/neighbour.h:544 [inline] ip6_finish_output2+0xd60/0x1a1c net/ipv6/ip6_output.c:134 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x538/0x8c8 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:292 [inline] ip6_output+0x270/0x594 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:458 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ndisc_send_skb+0xc30/0x1790 net/ipv6/ndisc.c:508 ndisc_send_rs+0x47c/0x5d4 net/ipv6/ndisc.c:718 addrconf_rs_timer+0x300/0x58c net/ipv6/addrconf.c:3936 call_timer_fn+0x19c/0x8cc kernel/time/timer.c:1700 expire_timers kernel/time/timer.c:1751 [inline] __run_timers+0x55c/0x734 kernel/time/timer.c:2022 run_timer_softirq+0x7c/0x114 kernel/time/timer.c:2035 __do_softirq+0x2d0/0xd54 kernel/softirq.c:571 ____do_softirq+0x14/0x20 arch/arm64/kernel/irq.c:80 call_on_irq_stack+0x24/0x4c arch/arm64/kernel/entry.S:882 do_softirq_own_stack+0x20/0x2c arch/arm64/kernel/irq.c:85 invoke_softirq kernel/softirq.c:452 [inline] __irq_exit_rcu+0x28c/0x534 kernel/softirq.c:650 irq_exit_rcu+0x14/0x84 kernel/softirq.c:662 __el1_irq arch/arm64/kernel/entry-common.c:472 [inline] el1_interrupt+0x38/0x68 arch/arm64/kernel/entry-common.c:486 el1h_64_irq_handler+0x18/0x24 arch/arm64/kernel/entry-common.c:491 el1h_64_irq+0x64/0x68 arch/arm64/kernel/entry.S:587 __daif_local_irq_enable arch/arm64/include/asm/irqflags.h:33 [inline] arch_local_irq_enable+0x8/0xc arch/arm64/include/asm/irqflags.h:55 cpuidle_idle_call kernel/sched/idle.c:170 [inline] do_idle+0x1f0/0x4e8 kernel/sched/idle.c:282 cpu_startup_entry+0x24/0x28 kernel/sched/idle.c:379 rest_init+0x2dc/0x2f4 init/main.c:735 start_kernel+0x0/0x55c init/main.c:834 start_kernel+0x3f0/0x55c init/main.c:1088 __primary_switched+0xb8/0xc0 arch/arm64/kernel/head.S:523 Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Jamal Hadi Salim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/sch_fq_pie.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index cf04f70e96bf..4f6b5b6fba3e 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -201,6 +201,11 @@ out: return NET_XMIT_CN; } +static struct netlink_range_validation fq_pie_q_range = { + .min = 1, + .max = 1 << 20, +}; + static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = { [TCA_FQ_PIE_LIMIT] = {.type = NLA_U32}, [TCA_FQ_PIE_FLOWS] = {.type = NLA_U32}, @@ -208,7 +213,8 @@ static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = { [TCA_FQ_PIE_TUPDATE] = {.type = NLA_U32}, [TCA_FQ_PIE_ALPHA] = {.type = NLA_U32}, [TCA_FQ_PIE_BETA] = {.type = NLA_U32}, - [TCA_FQ_PIE_QUANTUM] = {.type = NLA_U32}, + [TCA_FQ_PIE_QUANTUM] = + NLA_POLICY_FULL_RANGE(NLA_U32, &fq_pie_q_range), [TCA_FQ_PIE_MEMORY_LIMIT] = {.type = NLA_U32}, [TCA_FQ_PIE_ECN_PROB] = {.type = NLA_U32}, [TCA_FQ_PIE_ECN] = {.type = NLA_U32}, From 00665980128ce60c065f7cafd4a2d58ef329c47e Mon Sep 17 00:00:00 2001 From: Ying Hsu Date: Wed, 31 May 2023 03:44:56 +0000 Subject: [PATCH 3450/4345] Bluetooth: Fix l2cap_disconnect_req deadlock [ Upstream commit 02c5ea5246a44d6ffde0fddebfc1d56188052976 ] L2CAP assumes that the locks conn->chan_lock and chan->lock are acquired in the order conn->chan_lock, chan->lock to avoid potential deadlock. For example, l2sock_shutdown acquires these locks in the order: mutex_lock(&conn->chan_lock) l2cap_chan_lock(chan) However, l2cap_disconnect_req acquires chan->lock in l2cap_get_chan_by_scid first and then acquires conn->chan_lock before calling l2cap_chan_del. This means that these locks are acquired in unexpected order, which leads to potential deadlock: l2cap_chan_lock(c) mutex_lock(&conn->chan_lock) This patch releases chan->lock before acquiring the conn_chan_lock to avoid the potential deadlock. Fixes: a2a9339e1c9d ("Bluetooth: L2CAP: Fix use-after-free in l2cap_disconnect_{req,rsp}") Signed-off-by: Ying Hsu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b85ce276e2a3..2f05507bb36e 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4659,7 +4659,9 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, chan->ops->set_shutdown(chan); + l2cap_chan_unlock(chan); mutex_lock(&conn->chan_lock); + l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNRESET); mutex_unlock(&conn->chan_lock); @@ -4698,7 +4700,9 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, return 0; } + l2cap_chan_unlock(chan); mutex_lock(&conn->chan_lock); + l2cap_chan_lock(chan); l2cap_chan_del(chan, 0); mutex_unlock(&conn->chan_lock); From 0fee54fa330b6e86a960fa778c9d10d3e209d473 Mon Sep 17 00:00:00 2001 From: Sungwoo Kim Date: Sat, 3 Jun 2023 08:28:09 -0400 Subject: [PATCH 3451/4345] Bluetooth: L2CAP: Add missing checks for invalid DCID [ Upstream commit 75767213f3d9b97f63694d02260b6a49a2271876 ] When receiving a connect response we should make sure that the DCID is within the valid range and that we don't already have another channel allocated for the same DCID. Missing checks may violate the specification (BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 3, Part A, Page 1046). Fixes: 40624183c202 ("Bluetooth: L2CAP: Add missing checks for invalid LE DCID") Signed-off-by: Sungwoo Kim Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin --- net/bluetooth/l2cap_core.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 2f05507bb36e..568f0f072b3d 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4303,6 +4303,10 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, result = __le16_to_cpu(rsp->result); status = __le16_to_cpu(rsp->status); + if (result == L2CAP_CR_SUCCESS && (dcid < L2CAP_CID_DYN_START || + dcid > L2CAP_CID_DYN_END)) + return -EPROTO; + BT_DBG("dcid 0x%4.4x scid 0x%4.4x result 0x%2.2x status 0x%2.2x", dcid, scid, result, status); @@ -4334,6 +4338,11 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, switch (result) { case L2CAP_CR_SUCCESS: + if (__l2cap_get_chan_by_dcid(conn, dcid)) { + err = -EBADSLT; + break; + } + l2cap_state_change(chan, BT_CONFIG); chan->ident = 0; chan->dcid = dcid; From c4ba90ae357836aad531b57fd27e59ea53c7e49d Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 5 Jun 2023 16:56:00 +0530 Subject: [PATCH 3452/4345] qed/qede: Fix scheduling while atomic [ Upstream commit 42510dffd0e2c27046905f742172ed6662af5557 ] Statistics read through bond interface via sysfs causes below bug and traces as it triggers the bonding module to collect the slave device statistics while holding the spinlock, beneath that qede->qed driver statistics flow gets scheduled out due to usleep_range() used in PTT acquire logic [ 3673.988874] Hardware name: HPE ProLiant DL365 Gen10 Plus/ProLiant DL365 Gen10 Plus, BIOS A42 10/29/2021 [ 3673.988878] Call Trace: [ 3673.988891] dump_stack_lvl+0x34/0x44 [ 3673.988908] __schedule_bug.cold+0x47/0x53 [ 3673.988918] __schedule+0x3fb/0x560 [ 3673.988929] schedule+0x43/0xb0 [ 3673.988932] schedule_hrtimeout_range_clock+0xbf/0x1b0 [ 3673.988937] ? __hrtimer_init+0xc0/0xc0 [ 3673.988950] usleep_range+0x5e/0x80 [ 3673.988955] qed_ptt_acquire+0x2b/0xd0 [qed] [ 3673.988981] _qed_get_vport_stats+0x141/0x240 [qed] [ 3673.989001] qed_get_vport_stats+0x18/0x80 [qed] [ 3673.989016] qede_fill_by_demand_stats+0x37/0x400 [qede] [ 3673.989028] qede_get_stats64+0x19/0xe0 [qede] [ 3673.989034] dev_get_stats+0x5c/0xc0 [ 3673.989045] netstat_show.constprop.0+0x52/0xb0 [ 3673.989055] dev_attr_show+0x19/0x40 [ 3673.989065] sysfs_kf_seq_show+0x9b/0xf0 [ 3673.989076] seq_read_iter+0x120/0x4b0 [ 3673.989087] new_sync_read+0x118/0x1a0 [ 3673.989095] vfs_read+0xf3/0x180 [ 3673.989099] ksys_read+0x5f/0xe0 [ 3673.989102] do_syscall_64+0x3b/0x90 [ 3673.989109] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 3673.989115] RIP: 0033:0x7f8467d0b082 [ 3673.989119] Code: c0 e9 b2 fe ff ff 50 48 8d 3d ca 05 08 00 e8 35 e7 01 00 0f 1f 44 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 0f 05 <48> 3d 00 f0 ff ff 77 56 c3 0f 1f 44 00 00 48 83 ec 28 48 89 54 24 [ 3673.989121] RSP: 002b:00007ffffb21fd08 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 3673.989127] RAX: ffffffffffffffda RBX: 000000000100eca0 RCX: 00007f8467d0b082 [ 3673.989128] RDX: 00000000000003ff RSI: 00007ffffb21fdc0 RDI: 0000000000000003 [ 3673.989130] RBP: 00007f8467b96028 R08: 0000000000000010 R09: 00007ffffb21ec00 [ 3673.989132] R10: 00007ffffb27b170 R11: 0000000000000246 R12: 00000000000000f0 [ 3673.989134] R13: 0000000000000003 R14: 00007f8467b92000 R15: 0000000000045a05 [ 3673.989139] CPU: 30 PID: 285188 Comm: read_all Kdump: loaded Tainted: G W OE Fix this by collecting the statistics asynchronously from a periodic delayed work scheduled at default stats coalescing interval and return the recent copy of statisitcs from .ndo_get_stats64(), also add ability to configure/retrieve stats coalescing interval using below commands - ethtool -C ethx stats-block-usecs ethtool -c ethx Fixes: 133fac0eedc3 ("qede: Add basic ethtool support") Cc: Sudarsana Kalluru Cc: David Miller Signed-off-by: Manish Chopra Link: https://lore.kernel.org/r/20230605112600.48238-1-manishc@marvell.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 2 +- drivers/net/ethernet/qlogic/qede/qede.h | 4 +++ .../net/ethernet/qlogic/qede/qede_ethtool.c | 24 +++++++++++-- drivers/net/ethernet/qlogic/qede/qede_main.c | 34 ++++++++++++++++++- 4 files changed, 60 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 07824bf9d68d..0157bcd2efff 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1902,7 +1902,7 @@ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats) { u32 i; - if (!cdev) { + if (!cdev || cdev->recov_in_prog) { memset(stats, 0, sizeof(*stats)); return; } diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index f313fd730331..3251d58a263f 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -273,6 +273,10 @@ struct qede_dev { #define QEDE_ERR_WARN 3 struct qede_dump_info dump_info; + struct delayed_work periodic_task; + unsigned long stats_coal_ticks; + u32 stats_coal_usecs; + spinlock_t stats_lock; /* lock for vport stats access */ }; enum QEDE_STATE { diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index bedbb85a179a..db104e035ba1 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -426,6 +426,8 @@ static void qede_get_ethtool_stats(struct net_device *dev, } } + spin_lock(&edev->stats_lock); + for (i = 0; i < QEDE_NUM_STATS; i++) { if (qede_is_irrelevant_stat(edev, i)) continue; @@ -435,6 +437,8 @@ static void qede_get_ethtool_stats(struct net_device *dev, buf++; } + spin_unlock(&edev->stats_lock); + __qede_unlock(edev); } @@ -815,6 +819,7 @@ out: coal->rx_coalesce_usecs = rx_coal; coal->tx_coalesce_usecs = tx_coal; + coal->stats_block_coalesce_usecs = edev->stats_coal_usecs; return rc; } @@ -827,6 +832,19 @@ static int qede_set_coalesce(struct net_device *dev, int i, rc = 0; u16 rxc, txc; + if (edev->stats_coal_usecs != coal->stats_block_coalesce_usecs) { + edev->stats_coal_usecs = coal->stats_block_coalesce_usecs; + if (edev->stats_coal_usecs) { + edev->stats_coal_ticks = usecs_to_jiffies(edev->stats_coal_usecs); + schedule_delayed_work(&edev->periodic_task, 0); + + DP_INFO(edev, "Configured stats coal ticks=%lu jiffies\n", + edev->stats_coal_ticks); + } else { + cancel_delayed_work_sync(&edev->periodic_task); + } + } + if (!netif_running(dev)) { DP_INFO(edev, "Interface is down\n"); return -EINVAL; @@ -2106,7 +2124,8 @@ err: } static const struct ethtool_ops qede_ethtool_ops = { - .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_STATS_BLOCK_USECS, .get_link_ksettings = qede_get_link_ksettings, .set_link_ksettings = qede_set_link_ksettings, .get_drvinfo = qede_get_drvinfo, @@ -2155,7 +2174,8 @@ static const struct ethtool_ops qede_ethtool_ops = { }; static const struct ethtool_ops qede_vf_ethtool_ops = { - .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_STATS_BLOCK_USECS, .get_link_ksettings = qede_get_link_ksettings, .get_drvinfo = qede_get_drvinfo, .get_msglevel = qede_get_msglevel, diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index e93f06e4a172..681ec142c23d 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -313,6 +313,8 @@ void qede_fill_by_demand_stats(struct qede_dev *edev) edev->ops->get_vport_stats(edev->cdev, &stats); + spin_lock(&edev->stats_lock); + p_common->no_buff_discards = stats.common.no_buff_discards; p_common->packet_too_big_discard = stats.common.packet_too_big_discard; p_common->ttl0_discard = stats.common.ttl0_discard; @@ -410,6 +412,8 @@ void qede_fill_by_demand_stats(struct qede_dev *edev) p_ah->tx_1519_to_max_byte_packets = stats.ah.tx_1519_to_max_byte_packets; } + + spin_unlock(&edev->stats_lock); } static void qede_get_stats64(struct net_device *dev, @@ -418,9 +422,10 @@ static void qede_get_stats64(struct net_device *dev, struct qede_dev *edev = netdev_priv(dev); struct qede_stats_common *p_common; - qede_fill_by_demand_stats(edev); p_common = &edev->stats.common; + spin_lock(&edev->stats_lock); + stats->rx_packets = p_common->rx_ucast_pkts + p_common->rx_mcast_pkts + p_common->rx_bcast_pkts; stats->tx_packets = p_common->tx_ucast_pkts + p_common->tx_mcast_pkts + @@ -440,6 +445,8 @@ static void qede_get_stats64(struct net_device *dev, stats->collisions = edev->stats.bb.tx_total_collisions; stats->rx_crc_errors = p_common->rx_crc_errors; stats->rx_frame_errors = p_common->rx_align_errors; + + spin_unlock(&edev->stats_lock); } #ifdef CONFIG_QED_SRIOV @@ -1001,6 +1008,23 @@ static void qede_unlock(struct qede_dev *edev) rtnl_unlock(); } +static void qede_periodic_task(struct work_struct *work) +{ + struct qede_dev *edev = container_of(work, struct qede_dev, + periodic_task.work); + + qede_fill_by_demand_stats(edev); + schedule_delayed_work(&edev->periodic_task, edev->stats_coal_ticks); +} + +static void qede_init_periodic_task(struct qede_dev *edev) +{ + INIT_DELAYED_WORK(&edev->periodic_task, qede_periodic_task); + spin_lock_init(&edev->stats_lock); + edev->stats_coal_usecs = USEC_PER_SEC; + edev->stats_coal_ticks = usecs_to_jiffies(USEC_PER_SEC); +} + static void qede_sp_task(struct work_struct *work) { struct qede_dev *edev = container_of(work, struct qede_dev, @@ -1020,6 +1044,7 @@ static void qede_sp_task(struct work_struct *work) */ if (test_and_clear_bit(QEDE_SP_RECOVERY, &edev->sp_flags)) { + cancel_delayed_work_sync(&edev->periodic_task); #ifdef CONFIG_QED_SRIOV /* SRIOV must be disabled outside the lock to avoid a deadlock. * The recovery of the active VFs is currently not supported. @@ -1216,6 +1241,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, */ INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task); mutex_init(&edev->qede_lock); + qede_init_periodic_task(edev); rc = register_netdev(edev->ndev); if (rc) { @@ -1240,6 +1266,11 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, edev->rx_copybreak = QEDE_RX_HDR_SIZE; qede_log_probe(edev); + + /* retain user config (for example - after recovery) */ + if (edev->stats_coal_usecs) + schedule_delayed_work(&edev->periodic_task, 0); + return 0; err4: @@ -1308,6 +1339,7 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) unregister_netdev(ndev); cancel_delayed_work_sync(&edev->sp_task); + cancel_delayed_work_sync(&edev->periodic_task); edev->ops->common->set_power_state(cdev, PCI_D0); From 35c89cfcac05206c99d3654149b3416e5fcf4a71 Mon Sep 17 00:00:00 2001 From: Tijs Van Buggenhout Date: Thu, 25 May 2023 12:25:26 +0200 Subject: [PATCH 3453/4345] netfilter: conntrack: fix NULL pointer dereference in nf_confirm_cthelper [ Upstream commit e1f543dc660b44618a1bd72ddb4ca0828a95f7ad ] An nf_conntrack_helper from nf_conn_help may become NULL after DNAT. Observed when TCP port 1720 (Q931_PORT), associated with h323 conntrack helper, is DNAT'ed to another destination port (e.g. 1730), while nfqueue is being used for final acceptance (e.g. snort). This happenned after transition from kernel 4.14 to 5.10.161. Workarounds: * keep the same port (1720) in DNAT * disable nfqueue * disable/unload h323 NAT helper $ linux-5.10/scripts/decode_stacktrace.sh vmlinux < /tmp/kernel.log BUG: kernel NULL pointer dereference, address: 0000000000000084 [..] RIP: 0010:nf_conntrack_update (net/netfilter/nf_conntrack_core.c:2080 net/netfilter/nf_conntrack_core.c:2134) nf_conntrack [..] nfqnl_reinject (net/netfilter/nfnetlink_queue.c:237) nfnetlink_queue nfqnl_recv_verdict (net/netfilter/nfnetlink_queue.c:1230) nfnetlink_queue nfnetlink_rcv_msg (net/netfilter/nfnetlink.c:241) nfnetlink [..] Fixes: ee04805ff54a ("netfilter: conntrack: make conntrack userspace helpers work again") Signed-off-by: Tijs Van Buggenhout Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 193a18bfddc0..f82a234ac53a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2075,6 +2075,9 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct, return 0; helper = rcu_dereference(help->helper); + if (!helper) + return 0; + if (!(helper->flags & NF_CT_HELPER_F_USERSPACE)) return 0; From b4be099c5fb54a0cee9624e51b3829f1784fff5e Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 18 May 2023 10:33:00 -0700 Subject: [PATCH 3454/4345] netfilter: ipset: Add schedule point in call_ad(). [ Upstream commit 24e227896bbf003165e006732dccb3516f87f88e ] syzkaller found a repro that causes Hung Task [0] with ipset. The repro first creates an ipset and then tries to delete a large number of IPs from the ipset concurrently: IPSET_ATTR_IPADDR_IPV4 : 172.20.20.187 IPSET_ATTR_CIDR : 2 The first deleting thread hogs a CPU with nfnl_lock(NFNL_SUBSYS_IPSET) held, and other threads wait for it to be released. Previously, the same issue existed in set->variant->uadt() that could run so long under ip_set_lock(set). Commit 5e29dc36bd5e ("netfilter: ipset: Rework long task execution when adding/deleting entries") tried to fix it, but the issue still exists in the caller with another mutex. While adding/deleting many IPs, we should release the CPU periodically to prevent someone from abusing ipset to hang the system. Note we need to increment the ipset's refcnt to prevent the ipset from being destroyed while rescheduling. [0]: INFO: task syz-executor174:268 blocked for more than 143 seconds. Not tainted 6.4.0-rc1-00145-gba79e9a73284 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor174 state:D stack:0 pid:268 ppid:260 flags:0x0000000d Call trace: __switch_to+0x308/0x714 arch/arm64/kernel/process.c:556 context_switch kernel/sched/core.c:5343 [inline] __schedule+0xd84/0x1648 kernel/sched/core.c:6669 schedule+0xf0/0x214 kernel/sched/core.c:6745 schedule_preempt_disabled+0x58/0xf0 kernel/sched/core.c:6804 __mutex_lock_common kernel/locking/mutex.c:679 [inline] __mutex_lock+0x6fc/0xdb0 kernel/locking/mutex.c:747 __mutex_lock_slowpath+0x14/0x20 kernel/locking/mutex.c:1035 mutex_lock+0x98/0xf0 kernel/locking/mutex.c:286 nfnl_lock net/netfilter/nfnetlink.c:98 [inline] nfnetlink_rcv_msg+0x480/0x70c net/netfilter/nfnetlink.c:295 netlink_rcv_skb+0x1c0/0x350 net/netlink/af_netlink.c:2546 nfnetlink_rcv+0x18c/0x199c net/netfilter/nfnetlink.c:658 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x664/0x8cc net/netlink/af_netlink.c:1365 netlink_sendmsg+0x6d0/0xa4c net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x4b8/0x810 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1f8/0x2a4 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __arm64_sys_sendmsg+0x80/0x94 net/socket.c:2593 __invoke_syscall arch/arm64/kernel/syscall.c:38 [inline] invoke_syscall+0x84/0x270 arch/arm64/kernel/syscall.c:52 el0_svc_common+0x134/0x24c arch/arm64/kernel/syscall.c:142 do_el0_svc+0x64/0x198 arch/arm64/kernel/syscall.c:193 el0_svc+0x2c/0x7c arch/arm64/kernel/entry-common.c:637 el0t_64_sync_handler+0x84/0xf0 arch/arm64/kernel/entry-common.c:655 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:591 Reported-by: syzkaller Fixes: a7b4f989a629 ("netfilter: ipset: IP set core support") Signed-off-by: Kuniyuki Iwashima Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/ipset/ip_set_core.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 1bf6ab83644b..55ac0cc12657 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1704,6 +1704,14 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { + if (retried) { + __ip_set_get(set); + nfnl_unlock(NFNL_SUBSYS_IPSET); + cond_resched(); + nfnl_lock(NFNL_SUBSYS_IPSET); + __ip_set_put(set); + } + ip_set_lock(set); ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); ip_set_unlock(set); From 86e3981ff1bc501071100036435683c45aa70958 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 5 Jun 2023 11:06:17 -0700 Subject: [PATCH 3455/4345] ipv6: rpl: Fix Route of Death. [ Upstream commit a2f4c143d76b1a47c91ef9bc46907116b111da0b ] A remote DoS vulnerability of RPL Source Routing is assigned CVE-2023-2156. The Source Routing Header (SRH) has the following format: 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Next Header | Hdr Ext Len | Routing Type | Segments Left | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | CmprI | CmprE | Pad | Reserved | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | . . . Addresses[1..n] . . . | | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ The originator of an SRH places the first hop's IPv6 address in the IPv6 header's IPv6 Destination Address and the second hop's IPv6 address as the first address in Addresses[1..n]. The CmprI and CmprE fields indicate the number of prefix octets that are shared with the IPv6 Destination Address. When CmprI or CmprE is not 0, Addresses[1..n] are compressed as follows: 1..n-1 : (16 - CmprI) bytes n : (16 - CmprE) bytes Segments Left indicates the number of route segments remaining. When the value is not zero, the SRH is forwarded to the next hop. Its address is extracted from Addresses[n - Segment Left + 1] and swapped with IPv6 Destination Address. When Segment Left is greater than or equal to 2, the size of SRH is not changed because Addresses[1..n-1] are decompressed and recompressed with CmprI. OTOH, when Segment Left changes from 1 to 0, the new SRH could have a different size because Addresses[1..n-1] are decompressed with CmprI and recompressed with CmprE. Let's say CmprI is 15 and CmprE is 0. When we receive SRH with Segment Left >= 2, Addresses[1..n-1] have 1 byte for each, and Addresses[n] has 16 bytes. When Segment Left is 1, Addresses[1..n-1] is decompressed to 16 bytes and not recompressed. Finally, the new SRH will need more room in the header, and the size is (16 - 1) * (n - 1) bytes. Here the max value of n is 255 as Segment Left is u8, so in the worst case, we have to allocate 3825 bytes in the skb headroom. However, now we only allocate a small fixed buffer that is IPV6_RPL_SRH_WORST_SWAP_SIZE (16 + 7 bytes). If the decompressed size overflows the room, skb_push() hits BUG() below [0]. Instead of allocating the fixed buffer for every packet, let's allocate enough headroom only when we receive SRH with Segment Left 1. [0]: skbuff: skb_under_panic: text:ffffffff81c9f6e2 len:576 put:576 head:ffff8880070b5180 data:ffff8880070b4fb0 tail:0x70 end:0x140 dev:lo kernel BUG at net/core/skbuff.c:200! invalid opcode: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 154 Comm: python3 Not tainted 6.4.0-rc4-00190-gc308e9ec0047 #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:skb_panic (net/core/skbuff.c:200) Code: 4f 70 50 8b 87 bc 00 00 00 50 8b 87 b8 00 00 00 50 ff b7 c8 00 00 00 4c 8b 8f c0 00 00 00 48 c7 c7 80 6e 77 82 e8 ad 8b 60 ff <0f> 0b 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 RSP: 0018:ffffc90000003da0 EFLAGS: 00000246 RAX: 0000000000000085 RBX: ffff8880058a6600 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff88807dc1c540 RDI: ffff88807dc1c540 RBP: ffffc90000003e48 R08: ffffffff82b392c8 R09: 00000000ffffdfff R10: ffffffff82a592e0 R11: ffffffff82b092e0 R12: ffff888005b1c800 R13: ffff8880070b51b8 R14: ffff888005b1ca18 R15: ffff8880070b5190 FS: 00007f4539f0b740(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055670baf3000 CR3: 0000000005b0e000 CR4: 00000000007506f0 PKRU: 55555554 Call Trace: skb_push (net/core/skbuff.c:210) ipv6_rthdr_rcv (./include/linux/skbuff.h:2880 net/ipv6/exthdrs.c:634 net/ipv6/exthdrs.c:718) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:437 (discriminator 5)) ip6_input_finish (./include/linux/rcupdate.h:805 net/ipv6/ip6_input.c:483) __netif_receive_skb_one_core (net/core/dev.c:5494) process_backlog (./include/linux/rcupdate.h:805 net/core/dev.c:5934) __napi_poll (net/core/dev.c:6496) net_rx_action (net/core/dev.c:6565 net/core/dev.c:6696) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:572) do_softirq (kernel/softirq.c:472 kernel/softirq.c:459) __local_bh_enable_ip (kernel/softirq.c:396) __dev_queue_xmit (net/core/dev.c:4272) ip6_finish_output2 (./include/net/neighbour.h:544 net/ipv6/ip6_output.c:134) rawv6_sendmsg (./include/net/dst.h:458 ./include/linux/netfilter.h:303 net/ipv6/raw.c:656 net/ipv6/raw.c:914) sock_sendmsg (net/socket.c:724 net/socket.c:747) __sys_sendto (net/socket.c:2144) __x64_sys_sendto (net/socket.c:2156 net/socket.c:2152 net/socket.c:2152) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f453a138aea Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 RSP: 002b:00007ffcc212a1c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007ffcc212a288 RCX: 00007f453a138aea RDX: 0000000000000060 RSI: 00007f4539084c20 RDI: 0000000000000003 RBP: 00007f4538308e80 R08: 00007ffcc212a300 R09: 000000000000001c R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: ffffffffc4653600 R14: 0000000000000001 R15: 00007f4539712d1b Modules linked in: Fixes: 8610c7c6e3bd ("net: ipv6: add support for rpl sr exthdr") Reported-by: Max VA Closes: https://www.interruptlabs.co.uk/articles/linux-ipv6-route-of-death Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230605180617.67284-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/rpl.h | 3 --- net/ipv6/exthdrs.c | 29 +++++++++++------------------ 2 files changed, 11 insertions(+), 21 deletions(-) diff --git a/include/net/rpl.h b/include/net/rpl.h index 308ef0a05cae..30fe780d1e7c 100644 --- a/include/net/rpl.h +++ b/include/net/rpl.h @@ -23,9 +23,6 @@ static inline int rpl_init(void) static inline void rpl_exit(void) {} #endif -/* Worst decompression memory usage ipv6 address (16) + pad 7 */ -#define IPV6_RPL_SRH_WORST_SWAP_SIZE (sizeof(struct in6_addr) + 7) - size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 4932dea9820b..cdad9019c77c 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -552,24 +552,6 @@ looped_back: return -1; } - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE, 0, - GFP_ATOMIC)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTDISCARDS); - kfree_skb(skb); - return -1; - } - } else { - err = skb_cow_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE); - if (unlikely(err)) { - kfree_skb(skb); - return -1; - } - } - - hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); - if (!pskb_may_pull(skb, ipv6_rpl_srh_size(n, hdr->cmpri, hdr->cmpre))) { kfree_skb(skb); @@ -615,6 +597,17 @@ looped_back: skb_pull(skb, ((hdr->hdrlen + 1) << 3)); skb_postpull_rcsum(skb, oldhdr, sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); + if (unlikely(!hdr->segments_left)) { + if (pskb_expand_head(skb, sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3), 0, + GFP_ATOMIC)) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + kfree(buf); + return -1; + } + + oldhdr = ipv6_hdr(skb); + } skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); From c62ca9d03777c81b4c69895cf2955a31012594c7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 07:41:14 +0000 Subject: [PATCH 3456/4345] rfs: annotate lockless accesses to sk->sk_rxhash [ Upstream commit 1e5c647c3f6d4f8497dedcd226204e1880e0ffb3 ] Add READ_ONCE()/WRITE_ONCE() on accesses to sk->sk_rxhash. This also prevents a (smart ?) compiler to remove the condition in: if (sk->sk_rxhash != newval) sk->sk_rxhash = newval; We need the condition to avoid dirtying a shared cache line. Fixes: fec5e652e58f ("rfs: Receive Flow Steering") Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/sock.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 3da0601b573e..51b499d74549 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1073,8 +1073,12 @@ static inline void sock_rps_record_flow(const struct sock *sk) * OR an additional socket flag * [1] : sk_state and sk_prot are in the same cache line. */ - if (sk->sk_state == TCP_ESTABLISHED) - sock_rps_record_flow_hash(sk->sk_rxhash); + if (sk->sk_state == TCP_ESTABLISHED) { + /* This READ_ONCE() is paired with the WRITE_ONCE() + * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). + */ + sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); + } } #endif } @@ -1083,15 +1087,19 @@ static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS - if (unlikely(sk->sk_rxhash != skb->hash)) - sk->sk_rxhash = skb->hash; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in sock_rps_record_flow(). + */ + if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash)) + WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS - sk->sk_rxhash = 0; + /* Paired with READ_ONCE() in sock_rps_record_flow() */ + WRITE_ONCE(sk->sk_rxhash, 0); #endif } From dad7417db765da7068b3c96447520bd0a9d10cff Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 07:41:15 +0000 Subject: [PATCH 3457/4345] rfs: annotate lockless accesses to RFS sock flow table [ Upstream commit 5c3b74a92aa285a3df722bf6329ba7ccf70346d6 ] Add READ_ONCE()/WRITE_ONCE() on accesses to the sock flow table. This also prevents a (smart ?) compiler to remove the condition in: if (table->ents[index] != newval) table->ents[index] = newval; We need the condition to avoid dirtying a shared cache line. Fixes: fec5e652e58f ("rfs: Receive Flow Steering") Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/netdevice.h | 7 +++++-- net/core/dev.c | 6 ++++-- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9ef63bc14b00..24fe2cd4b0e8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -744,8 +744,11 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); - if (table->ents[index] != val) - table->ents[index] = val; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); } } diff --git a/net/core/dev.c b/net/core/dev.c index 29e6e11c481c..f4aad9b00cc9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4385,8 +4385,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, u32 next_cpu; u32 ident; - /* First check into global flow table if there is a match */ - ident = sock_flow_table->ents[hash & sock_flow_table->mask]; + /* First check into global flow table if there is a match. + * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). + */ + ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); if ((ident ^ hash) & ~rps_cpu_mask) goto try_rps; From 54acac57fe39458fdf2b9e9347aa93f84dd9e5ec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 11:42:33 +0000 Subject: [PATCH 3458/4345] net: sched: move rtm_tca_policy declaration to include file [ Upstream commit 886bc7d6ed3357975c5f1d3c784da96000d4bbb4 ] rtm_tca_policy is used from net/sched/sch_api.c and net/sched/cls_api.c, thus should be declared in an include file. This fixes the following sparse warning: net/sched/sch_api.c:1434:25: warning: symbol 'rtm_tca_policy' was not declared. Should it be static? Fixes: e331473fee3d ("net/sched: cls_api: add missing validation of netlink attributes") Signed-off-by: Eric Dumazet Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/net/pkt_sched.h | 2 ++ net/sched/cls_api.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 50d5ffbad473..ba781e0aaf56 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -129,6 +129,8 @@ static inline void qdisc_run(struct Qdisc *q) } } +extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; + /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 53d315ed9430..16960d9663e9 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -41,8 +41,6 @@ #include #include -extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; - /* The list of all installed classifier types */ static LIST_HEAD(tcf_proto_base); From 36d07046c2d90feb4ff8de50f82a17f60c6857dc Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Wed, 7 Jun 2023 10:23:01 +0800 Subject: [PATCH 3459/4345] net: sched: fix possible refcount leak in tc_chain_tmplt_add() [ Upstream commit 44f8baaf230c655c249467ca415b570deca8df77 ] try_module_get will be called in tcf_proto_lookup_ops. So module_put needs to be called to drop the refcount if ops don't implement the required function. Fixes: 9f407f1768d3 ("net: sched: introduce chain templates") Signed-off-by: Hangyu Hua Reviewed-by: Larysa Zaremba Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/cls_api.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 16960d9663e9..befe42aad04b 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2772,6 +2772,7 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, return PTR_ERR(ops); if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier"); + module_put(ops->owner); return -EOPNOTSUPP; } From 27b8d6931f3f08e36d8bb08faf04082c4f693fc0 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 6 Jun 2023 11:17:14 -0700 Subject: [PATCH 3460/4345] bpf: Add extra path pointer check to d_path helper [ Upstream commit f46fab0e36e611a2389d3843f34658c849b6bd60 ] Anastasios reported crash on stable 5.15 kernel with following BPF attached to lsm hook: SEC("lsm.s/bprm_creds_for_exec") int BPF_PROG(bprm_creds_for_exec, struct linux_binprm *bprm) { struct path *path = &bprm->executable->f_path; char p[128] = { 0 }; bpf_d_path(path, p, 128); return 0; } But bprm->executable can be NULL, so bpf_d_path call will crash: BUG: kernel NULL pointer dereference, address: 0000000000000018 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC NOPTI ... RIP: 0010:d_path+0x22/0x280 ... Call Trace: bpf_d_path+0x21/0x60 bpf_prog_db9cf176e84498d9_bprm_creds_for_exec+0x94/0x99 bpf_trampoline_6442506293_0+0x55/0x1000 bpf_lsm_bprm_creds_for_exec+0x5/0x10 security_bprm_creds_for_exec+0x29/0x40 bprm_execve+0x1c1/0x900 do_execveat_common.isra.0+0x1af/0x260 __x64_sys_execve+0x32/0x40 It's problem for all stable trees with bpf_d_path helper, which was added in 5.9. This issue is fixed in current bpf code, where we identify and mark trusted pointers, so the above code would fail even to load. For the sake of the stable trees and to workaround potentially broken verifier in the future, adding the code that reads the path object from the passed pointer and verifies it's valid in kernel space. Fixes: 6e22ab9da793 ("bpf: Add d_path helper") Reported-by: Anastasios Papagiannis Suggested-by: Alexei Starovoitov Signed-off-by: Jiri Olsa Signed-off-by: Daniel Borkmann Acked-by: Stanislav Fomichev Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20230606181714.532998-1-jolsa@kernel.org Signed-off-by: Sasha Levin --- kernel/trace/bpf_trace.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 94e51d36fb49..9e90d1e7af2c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1128,13 +1128,23 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = { BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz) { + struct path copy; long len; char *p; if (!sz) return 0; - p = d_path(path, buf, sz); + /* + * The path pointer is verified as trusted and safe to use, + * but let's double check it's valid anyway to workaround + * potentially broken verifier. + */ + len = copy_from_kernel_nofault(©, path, sizeof(*path)); + if (len < 0) + return len; + + p = d_path(©, buf, sz); if (IS_ERR(p)) { len = PTR_ERR(p); } else { From dedd47977ae51cb3726b592de99d99a6c2e145c0 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 2 Jun 2023 20:28:15 +0200 Subject: [PATCH 3461/4345] lib: cpu_rmap: Fix potential use-after-free in irq_cpu_rmap_release() [ Upstream commit 7c5d4801ecf0564c860033d89726b99723c55146 ] irq_cpu_rmap_release() calls cpu_rmap_put(), which may free the rmap. So we need to clear the pointer to our glue structure in rmap before doing that, not after. Fixes: 4e0473f1060a ("lib: cpu_rmap: Avoid use after free on rmap->obj array entries") Signed-off-by: Ben Hutchings Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/ZHo0vwquhOy3FaXc@decadent.org.uk Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- lib/cpu_rmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c index e77f12bb3c77..1833ad73de6f 100644 --- a/lib/cpu_rmap.c +++ b/lib/cpu_rmap.c @@ -268,8 +268,8 @@ static void irq_cpu_rmap_release(struct kref *ref) struct irq_glue *glue = container_of(ref, struct irq_glue, notify.kref); - cpu_rmap_put(glue->rmap); glue->rmap->obj[glue->index] = NULL; + cpu_rmap_put(glue->rmap); kfree(glue); } From 84dbd27ad5dace21830c67d01470e9121a044b22 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Wed, 7 Jun 2023 00:54:05 -0700 Subject: [PATCH 3462/4345] bnxt_en: Don't issue AP reset during ethtool's reset operation [ Upstream commit 1d997801c7cc6a7f542e46d5a6bf16f893ad3fe9 ] Only older NIC controller's firmware uses the PROC AP reset type. Firmware on 5731X/5741X and newer chips does not support this reset type. When bnxt_reset() issues a series of resets, this PROC AP reset may actually fail on these newer chips because the firmware is not ready to accept this unsupported command yet. Avoid this unnecessary error by skipping this reset type on chips that don't support it. Fixes: 7a13240e3718 ("bnxt_en: fix ethtool_reset_flags ABI violations") Reviewed-by: Pavan Chebbi Signed-off-by: Sreekanth Reddy Signed-off-by: Michael Chan Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 1e67e86fc334..2984234df67e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -3440,7 +3440,7 @@ static int bnxt_reset(struct net_device *dev, u32 *flags) } } - if (req & BNXT_FW_RESET_AP) { + if (!BNXT_CHIP_P4_PLUS(bp) && (req & BNXT_FW_RESET_AP)) { /* This feature is not supported in older firmware versions */ if (bp->hwrm_spec_code >= 0x10803) { if (!bnxt_firmware_reset_ap(dev)) { From deead0d8729f33f47cbedd0010a7e0e381527f9b Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Wed, 7 Jun 2023 00:54:06 -0700 Subject: [PATCH 3463/4345] bnxt_en: Query default VLAN before VNIC setup on a VF [ Upstream commit 1a9e4f501bc6ff1b6ecb60df54fbf2b54db43bfe ] We need to call bnxt_hwrm_func_qcfg() on a VF to query the default VLAN that may be setup by the PF. If a default VLAN is enabled, the VF cannot support VLAN acceleration on the receive side and the VNIC must be setup to strip out the default VLAN tag. If a default VLAN is not enabled, the VF can support VLAN acceleration on the receive side. The VNIC should be set up to strip or not strip the VLAN based on the RX VLAN acceleration setting. Without this call to determine the default VLAN before calling bnxt_setup_vnic(), the VNIC may not be set up correctly. For example, bnxt_setup_vnic() may set up to strip the VLAN tag based on stale default VLAN information. If RX VLAN acceleration is not enabled, the VLAN tag will be incorrectly stripped and the RX data path will not work correctly. Fixes: cf6645f8ebc6 ("bnxt_en: Add function for VF driver to query default VLAN.") Reviewed-by: Pavan Chebbi Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 3a9fcf942a6d..127ed119b5f7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8337,6 +8337,9 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) goto err_out; } + if (BNXT_VF(bp)) + bnxt_hwrm_func_qcfg(bp); + rc = bnxt_setup_vnic(bp, 0); if (rc) goto err_out; From 3f6dfff5fe416bda6469cf235eaa9c54fee2a0bc Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Wed, 7 Jun 2023 00:54:09 -0700 Subject: [PATCH 3464/4345] bnxt_en: Implement .set_port / .unset_port UDP tunnel callbacks [ Upstream commit 1eb4ef12591348c440ac9d6efcf7521e73cf2b10 ] As per the new udp tunnel framework, drivers which need to know the details of a port entry (i.e. port type) when it gets deleted should use the .set_port / .unset_port callbacks. Implementing the current .udp_tunnel_sync callback would mean that the deleted tunnel port entry would be all zeros. This used to work on older firmware because it would not check the input when deleting a tunnel port. With newer firmware, the delete will now fail and subsequent tunnel port allocation will fail as a result. Fixes: 442a35a5a7aa ("bnxt: convert to new udp_tunnel_nic infra") Reviewed-by: Kalesh Anakkur Purayil Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 25 ++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 127ed119b5f7..d8366351cf14 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12104,26 +12104,37 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) #endif /* CONFIG_RFS_ACCEL */ -static int bnxt_udp_tunnel_sync(struct net_device *netdev, unsigned int table) +static int bnxt_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) { struct bnxt *bp = netdev_priv(netdev); - struct udp_tunnel_info ti; unsigned int cmd; - udp_tunnel_nic_get_port(netdev, table, 0, &ti); - if (ti.type == UDP_TUNNEL_TYPE_VXLAN) + if (ti->type == UDP_TUNNEL_TYPE_VXLAN) cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN; else cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE; - if (ti.port) - return bnxt_hwrm_tunnel_dst_port_alloc(bp, ti.port, cmd); + return bnxt_hwrm_tunnel_dst_port_alloc(bp, ti->port, cmd); +} + +static int bnxt_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) +{ + struct bnxt *bp = netdev_priv(netdev); + unsigned int cmd; + + if (ti->type == UDP_TUNNEL_TYPE_VXLAN) + cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN; + else + cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE; return bnxt_hwrm_tunnel_dst_port_free(bp, cmd); } static const struct udp_tunnel_nic_info bnxt_udp_tunnels = { - .sync_table = bnxt_udp_tunnel_sync, + .set_port = bnxt_udp_tunnel_set_port, + .unset_port = bnxt_udp_tunnel_unset_port, .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | UDP_TUNNEL_NIC_INFO_OPEN_ONLY, .tables = { From 9ece26ff08152393231cfbfd0b29a402bdee2f78 Mon Sep 17 00:00:00 2001 From: Vladislav Efanov Date: Fri, 26 May 2023 19:16:32 +0300 Subject: [PATCH 3465/4345] batman-adv: Broken sync while rescheduling delayed work commit abac3ac97fe8734b620e7322a116450d7f90aa43 upstream. Syzkaller got a lot of crashes like: KASAN: use-after-free Write in *_timers* All of these crashes point to the same memory area: The buggy address belongs to the object at ffff88801f870000 which belongs to the cache kmalloc-8k of size 8192 The buggy address is located 5320 bytes inside of 8192-byte region [ffff88801f870000, ffff88801f872000) This area belongs to : batadv_priv->batadv_priv_dat->delayed_work->timer_list The reason for these issues is the lack of synchronization. Delayed work (batadv_dat_purge) schedules new timer/work while the device is being deleted. As the result new timer/delayed work is set after cancel_delayed_work_sync() was called. So after the device is freed the timer list contains pointer to already freed memory. Found by Linux Verification Center (linuxtesting.org) with syzkaller. Cc: stable@kernel.org Fixes: 2f1dfbe18507 ("batman-adv: Distributed ARP Table - implement local storage") Signed-off-by: Vladislav Efanov Acked-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/distributed-arp-table.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 338e4e9c33b8..ddd3b4c70a51 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -102,7 +102,6 @@ static void batadv_dat_purge(struct work_struct *work); */ static void batadv_dat_start_timer(struct batadv_priv *bat_priv) { - INIT_DELAYED_WORK(&bat_priv->dat.work, batadv_dat_purge); queue_delayed_work(batadv_event_workqueue, &bat_priv->dat.work, msecs_to_jiffies(10000)); } @@ -822,6 +821,7 @@ int batadv_dat_init(struct batadv_priv *bat_priv) if (!bat_priv->dat.hash) return -ENOMEM; + INIT_DELAYED_WORK(&bat_priv->dat.work, batadv_dat_purge); batadv_dat_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_dat_tvlv_ogm_handler_v1, From 86efc409f29db44c2fcbc353299865238ff372c0 Mon Sep 17 00:00:00 2001 From: Ismael Ferreras Morezuelas Date: Tue, 23 May 2023 14:45:10 -0700 Subject: [PATCH 3466/4345] Input: xpad - delete a Razer DeathAdder mouse VID/PID entry commit feee70f4568650cf44c573488798ffc0a2faeea3 upstream. While doing my research to improve the xpad device names I noticed that the 1532:0037 VID/PID seems to be used by the DeathAdder 2013, so that Razer Sabertooth instance looked wrong and very suspect to me. I didn't see any mention in the official drivers, either. After doing more research, it turns out that the xpad list is used by many other projects (like Steam) as-is [1], this issue was reported [2] and Valve/Sam Lantinga fixed it [3]: [1]: https://github.com/libsdl-org/SDL/blob/dcc5eef0e2395854b254ea2873a4899edab347c6/src/joystick/controller_type.h#L251 [2]: https://steamcommunity.com/app/353380/discussions/0/1743392486228754770/ [3]: https://hg.libsdl.org/SDL/rev/29809f6f0271 (With multiple Internet users reporting similar issues, not linked here) After not being able to find the correct VID/PID combination anywhere on the Internet and not receiving any reply from Razer support I did some additional detective work, it seems like it presents itself as "Razer Sabertooth Gaming Controller (XBOX360)", code 1689:FE00. Leaving us with this: * Razer Sabertooth (1689:fe00) * Razer Sabertooth Elite (24c6:5d04) * Razer DeathAdder 2013 (1532:0037) [note: not a gamepad] So, to sum things up; remove this conflicting/duplicate entry: { 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 }, As the real/correct one is already present there, even if the Internet as a whole insists on presenting it as the Razer Sabertooth Elite, which (by all accounts) is not: { 0x1689, 0xfe00, "Razer Sabertooth", 0, XTYPE_XBOX360 }, Actual change in SDL2 referencing this kernel issue: https://github.com/libsdl-org/SDL/commit/e5e54169754ca5d3e86339d968b20126d9da0a15 For more information of the device, take a look here: https://github.com/xboxdrv/xboxdrv/pull/59 You can see a lsusb dump here: https://github.com/xboxdrv/xboxdrv/files/76581/Qa6dBcrv.txt Fixes: f554f619b70 ("Input: xpad - sync device IDs with xboxdrv") Signed-off-by: Ismael Ferreras Morezuelas Reviewed-by: Cameron Gutman Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/5c12dbdb-5774-fc68-5c58-ca596383663e@gmail.com Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/joystick/xpad.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 0bd55e1fca37..b99318fb58dc 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -262,7 +262,6 @@ static const struct xpad_device { { 0x1430, 0xf801, "RedOctane Controller", 0, XTYPE_XBOX360 }, { 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 }, { 0x146b, 0x0604, "Bigben Interactive DAIJA Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, - { 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 }, { 0x1532, 0x0a00, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, { 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE }, { 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 }, From ca26d00828d3a0c15eb1151a96a924c854665500 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 11 May 2023 12:08:37 -0700 Subject: [PATCH 3467/4345] Input: psmouse - fix OOB access in Elantech protocol commit 7b63a88bb62ba2ddf5fcd956be85fe46624628b9 upstream. The kernel only allocate 5 MT slots; check that transmitted slot ID falls within the acceptable range. Link: https://lore.kernel.org/r/ZFnEL91nrT789dbG@google.com Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/mouse/elantech.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 2e53ea261e01..598fcb99f6c9 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -674,10 +674,11 @@ static void process_packet_head_v4(struct psmouse *psmouse) struct input_dev *dev = psmouse->dev; struct elantech_data *etd = psmouse->private; unsigned char *packet = psmouse->packet; - int id = ((packet[3] & 0xe0) >> 5) - 1; + int id; int pres, traces; - if (id < 0) + id = ((packet[3] & 0xe0) >> 5) - 1; + if (id < 0 || id >= ETP_MAX_FINGERS) return; etd->mt[id].x = ((packet[1] & 0x0f) << 8) | packet[2]; @@ -707,7 +708,7 @@ static void process_packet_motion_v4(struct psmouse *psmouse) int id, sid; id = ((packet[0] & 0xe0) >> 5) - 1; - if (id < 0) + if (id < 0 || id >= ETP_MAX_FINGERS) return; sid = ((packet[3] & 0xe0) >> 5) - 1; @@ -728,7 +729,7 @@ static void process_packet_motion_v4(struct psmouse *psmouse) input_report_abs(dev, ABS_MT_POSITION_X, etd->mt[id].x); input_report_abs(dev, ABS_MT_POSITION_Y, etd->mt[id].y); - if (sid >= 0) { + if (sid >= 0 && sid < ETP_MAX_FINGERS) { etd->mt[sid].x += delta_x2 * weight; etd->mt[sid].y -= delta_y2 * weight; input_mt_slot(dev, sid); From 95520b3fba920ca46f6ac250cef7c8cf9a9735f9 Mon Sep 17 00:00:00 2001 From: Ai Chao Date: Fri, 26 May 2023 17:47:04 +0800 Subject: [PATCH 3468/4345] ALSA: hda/realtek: Add a quirk for HP Slim Desktop S01 commit 527c356b51f3ddee02c9ed5277538f85e30a2cdc upstream. Add a quirk for HP Slim Desktop S01 to fixup headset MIC no presence. Signed-off-by: Ai Chao Cc: Link: https://lore.kernel.org/r/20230526094704.14597-1-aichao@kylinos.cn Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 21c8b474a4df..984cfded010f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11162,6 +11162,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x872b, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), + SND_PCI_QUIRK(0x103c, 0x8768, "HP Slim Desktop S01", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x885f, "HP 288 Pro G8", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x1043, 0x1080, "Asus UX501VW", ALC668_FIXUP_HEADSET_MODE), From ef95f987bea8197717fb54b8e7103c1ecfc313a0 Mon Sep 17 00:00:00 2001 From: RenHai Date: Fri, 2 Jun 2023 08:36:04 +0800 Subject: [PATCH 3469/4345] ALSA: hda/realtek: Add Lenovo P3 Tower platform commit 7ca4c8d4d3f41c2cd9b4cf22bb829bf03dac0956 upstream. Headset microphone on this platform does not work without ALC897_FIXUP_HEADSET_MIC_PIN fixup. Signed-off-by: RenHai Cc: Link: https://lore.kernel.org/r/20230602003604.975892-1-kean0048@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 984cfded010f..8a42262dd7fa 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11184,6 +11184,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x1057, "Lenovo P360", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x1064, "Lenovo P3 Tower", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32ca, "Lenovo ThinkCentre M80", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN), From 00380551353be6581815efb2f1ff9c687a2f40df Mon Sep 17 00:00:00 2001 From: Chia-I Wu Date: Thu, 1 Jun 2023 14:48:08 -0700 Subject: [PATCH 3470/4345] drm/amdgpu: fix xclk freq on CHIP_STONEY commit b447b079cf3a9971ea4d31301e673f49612ccc18 upstream. According to Alex, most APUs from that time seem to have the same issue (vbios says 48Mhz, actual is 100Mhz). I only have a CHIP_STONEY so I limit the fixup to CHIP_STONEY Signed-off-by: Chia-I Wu Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/vi.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 9bcd0eebc6d7..2e030a308b6e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -329,8 +329,15 @@ static u32 vi_get_xclk(struct amdgpu_device *adev) u32 reference_clock = adev->clock.spll.reference_freq; u32 tmp; - if (adev->flags & AMD_IS_APU) - return reference_clock; + if (adev->flags & AMD_IS_APU) { + switch (adev->asic_type) { + case CHIP_STONEY: + /* vbios says 48Mhz, but the actual freq is 100Mhz */ + return 10000; + default: + return reference_clock; + } + } tmp = RREG32_SMC(ixCG_CLKPIN_CNTL_2); if (REG_GET_FIELD(tmp, CG_CLKPIN_CNTL_2, MUX_TCLK_TO_XCLK)) From 0268005076409a75b4bf31b3d378dc3d3327662f Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 26 May 2023 10:19:46 +0200 Subject: [PATCH 3471/4345] can: j1939: j1939_sk_send_loop_abort(): improved error queue handling in J1939 Socket commit 2a84aea80e925ecba6349090559754f8e8eb68ef upstream. This patch addresses an issue within the j1939_sk_send_loop_abort() function in the j1939/socket.c file, specifically in the context of Transport Protocol (TP) sessions. Without this patch, when a TP session is initiated and a Clear To Send (CTS) frame is received from the remote side requesting one data packet, the kernel dispatches the first Data Transport (DT) frame and then waits for the next CTS. If the remote side doesn't respond with another CTS, the kernel aborts due to a timeout. This leads to the user-space receiving an EPOLLERR on the socket, and the socket becomes active. However, when trying to read the error queue from the socket with sock.recvmsg(, , socket.MSG_ERRQUEUE), it returns -EAGAIN, given that the socket is non-blocking. This situation results in an infinite loop: the user-space repeatedly calls epoll(), epoll() returns the socket file descriptor with EPOLLERR, but the socket then blocks on the recv() of ERRQUEUE. This patch introduces an additional check for the J1939_SOCK_ERRQUEUE flag within the j1939_sk_send_loop_abort() function. If the flag is set, it indicates that the application has subscribed to receive error queue messages. In such cases, the kernel can communicate the current transfer state via the error queue. This allows for the function to return early, preventing the unnecessary setting of the socket into an error state, and breaking the infinite loop. It is crucial to note that a socket error is only needed if the application isn't using the error queue, as, without it, the application wouldn't be aware of transfer issues. Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Reported-by: David Jander Tested-by: David Jander Signed-off-by: Oleksij Rempel Link: https://lore.kernel.org/r/20230526081946.715190-1-o.rempel@pengutronix.de Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/j1939/socket.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 76cd5f43faf7..906a08d38c1c 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -1013,6 +1013,11 @@ void j1939_sk_errqueue(struct j1939_session *session, void j1939_sk_send_loop_abort(struct sock *sk, int err) { + struct j1939_sock *jsk = j1939_sk(sk); + + if (jsk->state & J1939_SOCK_ERRQUEUE) + return; + sk->sk_err = err; sk->sk_error_report(sk); From cc834f4d976230d586f921e4a8c63a68dcba2a62 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Fri, 26 May 2023 20:19:09 +0300 Subject: [PATCH 3472/4345] can: j1939: change j1939_netdev_lock type to mutex commit cd9c790de2088b0d797dc4d244b4f174f9962554 upstream. It turns out access to j1939_can_rx_register() needs to be serialized, otherwise j1939_priv can be corrupted when parallel threads call j1939_netdev_start() and j1939_can_rx_register() fails. This issue is thoroughly covered in other commit which serializes access to j1939_can_rx_register(). Change j1939_netdev_lock type to mutex so that we do not need to remove GFP_KERNEL from can_rx_register(). j1939_netdev_lock seems to be used in normal contexts where mutex usage is not prohibited. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Suggested-by: Alexey Khoroshilov Signed-off-by: Fedor Pchelkin Tested-by: Oleksij Rempel Acked-by: Oleksij Rempel Link: https://lore.kernel.org/r/20230526171910.227615-2-pchelkin@ispras.ru Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/j1939/main.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 9da8fbc81c04..6c48fc356439 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -122,7 +122,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) #define J1939_CAN_ID CAN_EFF_FLAG #define J1939_CAN_MASK (CAN_EFF_FLAG | CAN_RTR_FLAG) -static DEFINE_SPINLOCK(j1939_netdev_lock); +static DEFINE_MUTEX(j1939_netdev_lock); static struct j1939_priv *j1939_priv_create(struct net_device *ndev) { @@ -216,7 +216,7 @@ static void __j1939_rx_release(struct kref *kref) j1939_can_rx_unregister(priv); j1939_ecu_unmap_all(priv); j1939_priv_set(priv->ndev, NULL); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); } /* get pointer to priv without increasing ref counter */ @@ -244,9 +244,9 @@ static struct j1939_priv *j1939_priv_get_by_ndev(struct net_device *ndev) { struct j1939_priv *priv; - spin_lock(&j1939_netdev_lock); + mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); return priv; } @@ -256,14 +256,14 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) struct j1939_priv *priv, *priv_new; int ret; - spin_lock(&j1939_netdev_lock); + mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); if (priv) { kref_get(&priv->rx_kref); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); return priv; } - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); priv = j1939_priv_create(ndev); if (!priv) @@ -273,20 +273,20 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) spin_lock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); - spin_lock(&j1939_netdev_lock); + mutex_lock(&j1939_netdev_lock); priv_new = j1939_priv_get_by_ndev_locked(ndev); if (priv_new) { /* Someone was faster than us, use their priv and roll * back our's. */ kref_get(&priv_new->rx_kref); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); return priv_new; } j1939_priv_set(ndev, priv); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); ret = j1939_can_rx_register(priv); if (ret < 0) @@ -304,7 +304,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) void j1939_netdev_stop(struct j1939_priv *priv) { - kref_put_lock(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); + kref_put_mutex(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); j1939_priv_put(priv); } From 67148731582d0426ee04be681583176799f052af Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Fri, 26 May 2023 20:19:10 +0300 Subject: [PATCH 3473/4345] can: j1939: avoid possible use-after-free when j1939_can_rx_register fails commit 9f16eb106aa5fce15904625661312623ec783ed3 upstream. Syzkaller reports the following failure: BUG: KASAN: use-after-free in kref_put include/linux/kref.h:64 [inline] BUG: KASAN: use-after-free in j1939_priv_put+0x25/0xa0 net/can/j1939/main.c:172 Write of size 4 at addr ffff888141c15058 by task swapper/3/0 CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.10.144-syzkaller #0 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x107/0x167 lib/dump_stack.c:118 print_address_description.constprop.0+0x1c/0x220 mm/kasan/report.c:385 __kasan_report mm/kasan/report.c:545 [inline] kasan_report.cold+0x1f/0x37 mm/kasan/report.c:562 check_memory_region_inline mm/kasan/generic.c:186 [inline] check_memory_region+0x145/0x190 mm/kasan/generic.c:192 instrument_atomic_read_write include/linux/instrumented.h:101 [inline] atomic_fetch_sub_release include/asm-generic/atomic-instrumented.h:220 [inline] __refcount_sub_and_test include/linux/refcount.h:272 [inline] __refcount_dec_and_test include/linux/refcount.h:315 [inline] refcount_dec_and_test include/linux/refcount.h:333 [inline] kref_put include/linux/kref.h:64 [inline] j1939_priv_put+0x25/0xa0 net/can/j1939/main.c:172 j1939_sk_sock_destruct+0x44/0x90 net/can/j1939/socket.c:374 __sk_destruct+0x4e/0x820 net/core/sock.c:1784 rcu_do_batch kernel/rcu/tree.c:2485 [inline] rcu_core+0xb35/0x1a30 kernel/rcu/tree.c:2726 __do_softirq+0x289/0x9a3 kernel/softirq.c:298 asm_call_irq_on_stack+0x12/0x20 __run_on_irqstack arch/x86/include/asm/irq_stack.h:26 [inline] run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:77 [inline] do_softirq_own_stack+0xaa/0xe0 arch/x86/kernel/irq_64.c:77 invoke_softirq kernel/softirq.c:393 [inline] __irq_exit_rcu kernel/softirq.c:423 [inline] irq_exit_rcu+0x136/0x200 kernel/softirq.c:435 sysvec_apic_timer_interrupt+0x4d/0x100 arch/x86/kernel/apic/apic.c:1095 asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:635 Allocated by task 1141: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:48 kasan_set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc.constprop.0+0xc9/0xd0 mm/kasan/common.c:461 kmalloc include/linux/slab.h:552 [inline] kzalloc include/linux/slab.h:664 [inline] j1939_priv_create net/can/j1939/main.c:131 [inline] j1939_netdev_start+0x111/0x860 net/can/j1939/main.c:268 j1939_sk_bind+0x8ea/0xd30 net/can/j1939/socket.c:485 __sys_bind+0x1f2/0x260 net/socket.c:1645 __do_sys_bind net/socket.c:1656 [inline] __se_sys_bind net/socket.c:1654 [inline] __x64_sys_bind+0x6f/0xb0 net/socket.c:1654 do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x61/0xc6 Freed by task 1141: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:48 kasan_set_track+0x1c/0x30 mm/kasan/common.c:56 kasan_set_free_info+0x1b/0x30 mm/kasan/generic.c:355 __kasan_slab_free+0x112/0x170 mm/kasan/common.c:422 slab_free_hook mm/slub.c:1542 [inline] slab_free_freelist_hook+0xad/0x190 mm/slub.c:1576 slab_free mm/slub.c:3149 [inline] kfree+0xd9/0x3b0 mm/slub.c:4125 j1939_netdev_start+0x5ee/0x860 net/can/j1939/main.c:300 j1939_sk_bind+0x8ea/0xd30 net/can/j1939/socket.c:485 __sys_bind+0x1f2/0x260 net/socket.c:1645 __do_sys_bind net/socket.c:1656 [inline] __se_sys_bind net/socket.c:1654 [inline] __x64_sys_bind+0x6f/0xb0 net/socket.c:1654 do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x61/0xc6 It can be caused by this scenario: CPU0 CPU1 j1939_sk_bind(socket0, ndev0, ...) j1939_netdev_start() j1939_sk_bind(socket1, ndev0, ...) j1939_netdev_start() mutex_lock(&j1939_netdev_lock) j1939_priv_set(ndev0, priv) mutex_unlock(&j1939_netdev_lock) if (priv_new) kref_get(&priv_new->rx_kref) return priv_new; /* inside j1939_sk_bind() */ jsk->priv = priv j1939_can_rx_register(priv) // fails j1939_priv_set(ndev, NULL) kfree(priv) j1939_sk_sock_destruct() j1939_priv_put() // <- uaf To avoid this, call j1939_can_rx_register() under j1939_netdev_lock so that a concurrent thread cannot process j1939_priv before j1939_can_rx_register() returns. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Signed-off-by: Fedor Pchelkin Tested-by: Oleksij Rempel Acked-by: Oleksij Rempel Link: https://lore.kernel.org/r/20230526171910.227615-3-pchelkin@ispras.ru Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/j1939/main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 6c48fc356439..9169ef174ff0 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -286,16 +286,18 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) return priv_new; } j1939_priv_set(ndev, priv); - mutex_unlock(&j1939_netdev_lock); ret = j1939_can_rx_register(priv); if (ret < 0) goto out_priv_put; + mutex_unlock(&j1939_netdev_lock); return priv; out_priv_put: j1939_priv_set(ndev, NULL); + mutex_unlock(&j1939_netdev_lock); + dev_put(ndev); kfree(priv); From e715c86e92fd9137a0bbfe8409bc15b3146138b4 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 1 Jun 2023 08:59:31 +0800 Subject: [PATCH 3474/4345] ceph: fix use-after-free bug for inodes when flushing capsnaps commit 409e873ea3c1fd3079909718bbeb06ac1ec7f38b upstream. There is a race between capsnaps flush and removing the inode from 'mdsc->snap_flush_list' list: == Thread A == == Thread B == ceph_queue_cap_snap() -> allocate 'capsnapA' ->ihold('&ci->vfs_inode') ->add 'capsnapA' to 'ci->i_cap_snaps' ->add 'ci' to 'mdsc->snap_flush_list' ... == Thread C == ceph_flush_snaps() ->__ceph_flush_snaps() ->__send_flush_snap() handle_cap_flushsnap_ack() ->iput('&ci->vfs_inode') this also will release 'ci' ... == Thread D == ceph_handle_snap() ->flush_snaps() ->iterate 'mdsc->snap_flush_list' ->get the stale 'ci' ->remove 'ci' from ->ihold(&ci->vfs_inode) this 'mdsc->snap_flush_list' will WARNING To fix this we will increase the inode's i_count ref when adding 'ci' to the 'mdsc->snap_flush_list' list. [ idryomov: need_put int -> bool ] Cc: stable@vger.kernel.org Link: https://bugzilla.redhat.com/show_bug.cgi?id=2209299 Signed-off-by: Xiubo Li Reviewed-by: Milind Changire Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- fs/ceph/caps.c | 6 ++++++ fs/ceph/snap.c | 4 +++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 210496dc2fd4..e1fda3923944 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1636,6 +1636,7 @@ void ceph_flush_snaps(struct ceph_inode_info *ci, struct inode *inode = &ci->vfs_inode; struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_mds_session *session = NULL; + bool need_put = false; int mds; dout("ceph_flush_snaps %p\n", inode); @@ -1687,8 +1688,13 @@ out: } /* we flushed them all; remove this inode from the queue */ spin_lock(&mdsc->snap_flush_lock); + if (!list_empty(&ci->i_snap_flush_item)) + need_put = true; list_del_init(&ci->i_snap_flush_item); spin_unlock(&mdsc->snap_flush_lock); + + if (need_put) + iput(inode); } /* diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 8e6fc45ccc9e..db464682b2cb 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -647,8 +647,10 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, capsnap->size); spin_lock(&mdsc->snap_flush_lock); - if (list_empty(&ci->i_snap_flush_item)) + if (list_empty(&ci->i_snap_flush_item)) { + ihold(inode); list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); + } spin_unlock(&mdsc->snap_flush_lock); return 1; /* caller may want to ceph_flush_snaps */ } From 76b40319a1ea75682aee6b660fac6dc2e8168c3d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=C3=B6ppner?= Date: Fri, 9 Jun 2023 17:37:50 +0200 Subject: [PATCH 3475/4345] s390/dasd: Use correct lock while counting channel queue length MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit ccc45cb4e7271c74dbb27776ae8f73d84557f5c6 upstream. The lock around counting the channel queue length in the BIODASDINFO ioctl was incorrectly changed to the dasd_block->queue_lock with commit 583d6535cb9d ("dasd: remove dead code"). This can lead to endless list iterations and a subsequent crash. The queue_lock is supposed to be used only for queue lists belonging to dasd_block. For dasd_device related queue lists the ccwdev lock must be used. Fix the mentioned issues by correctly using the ccwdev lock instead of the queue lock. Fixes: 583d6535cb9d ("dasd: remove dead code") Cc: stable@vger.kernel.org # v5.0+ Signed-off-by: Jan Höppner Reviewed-by: Stefan Haberland Signed-off-by: Stefan Haberland Link: https://lore.kernel.org/r/20230609153750.1258763-2-sth@linux.ibm.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/s390/block/dasd_ioctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index cb6427fb9f3d..6d5c9cb83592 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -505,10 +505,10 @@ static int __dasd_ioctl_information(struct dasd_block *block, memcpy(dasd_info->type, base->discipline->name, 4); - spin_lock_irqsave(&block->queue_lock, flags); + spin_lock_irqsave(get_ccwdev_lock(base->cdev), flags); list_for_each(l, &base->ccw_queue) dasd_info->chanq_len++; - spin_unlock_irqrestore(&block->queue_lock, flags); + spin_unlock_irqrestore(get_ccwdev_lock(base->cdev), flags); return 0; } From 2270e32bd1995f90377e217b478bc38af1ab15a9 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Tue, 30 May 2023 13:48:44 -0700 Subject: [PATCH 3476/4345] Bluetooth: Fix use-after-free in hci_remove_ltk/hci_remove_irk commit c5d2b6fa26b5b8386a9cc902cdece3a46bef2bd2 upstream. Similar to commit 0f7d9b31ce7a ("netfilter: nf_tables: fix use-after-free in nft_set_catchall_destroy()"). We can not access k after kfree_rcu() call. Cc: stable@vger.kernel.org Signed-off-by: Min Li Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- net/bluetooth/hci_core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 08c473aa0113..bd6f20ef13f3 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2685,10 +2685,10 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { - struct smp_ltk *k; + struct smp_ltk *k, *tmp; int removed = 0; - list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type) continue; @@ -2704,9 +2704,9 @@ int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { - struct smp_irk *k; + struct smp_irk *k, *tmp; - list_for_each_entry_rcu(k, &hdev->identity_resolving_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type) continue; From a94024991d82a94a2c3cac3566db4b2651104349 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 31 May 2023 10:57:59 +0200 Subject: [PATCH 3477/4345] Bluetooth: hci_qca: fix debugfs registration commit 47c5d829a3e326b7395352a10fc8a6effe7afa15 upstream. Since commit 3e4be65eb82c ("Bluetooth: hci_qca: Add poweroff support during hci down for wcn3990"), the setup callback which registers the debugfs interface can be called multiple times. This specifically leads to the following error when powering on the controller: debugfs: Directory 'ibs' with parent 'hci0' already present! Add a driver flag to avoid trying to register the debugfs interface more than once. Fixes: 3e4be65eb82c ("Bluetooth: hci_qca: Add poweroff support during hci down for wcn3990") Cc: stable@vger.kernel.org # 4.20 Signed-off-by: Johan Hovold Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_qca.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 5347fc465ce8..bc0850d3f7d2 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -78,7 +78,8 @@ enum qca_flags { QCA_HW_ERROR_EVENT, QCA_SSR_TRIGGERED, QCA_BT_OFF, - QCA_ROM_FW + QCA_ROM_FW, + QCA_DEBUGFS_CREATED, }; enum qca_capabilities { @@ -633,6 +634,9 @@ static void qca_debugfs_init(struct hci_dev *hdev) if (!hdev->debugfs) return; + if (test_and_set_bit(QCA_DEBUGFS_CREATED, &qca->flags)) + return; + ibs_dir = debugfs_create_dir("ibs", hdev->debugfs); /* read only */ From 841d3b5a8446cf7614aecabc4549f08a70b3de24 Mon Sep 17 00:00:00 2001 From: Rijo Thomas Date: Tue, 9 May 2023 13:02:40 +0530 Subject: [PATCH 3478/4345] tee: amdtee: Add return_origin to 'struct tee_cmd_load_ta' commit 436eeae0411acdfc54521ddea80ee76d4ae8a7ea upstream. After TEE has completed processing of TEE_CMD_ID_LOAD_TA, set proper value in 'return_origin' argument passed by open_session() call. To do so, add 'return_origin' field to the structure tee_cmd_load_ta. The Trusted OS shall update return_origin as part of TEE processing. This change to 'struct tee_cmd_load_ta' interface requires a similar update in AMD-TEE Trusted OS's TEE_CMD_ID_LOAD_TA interface. This patch has been verified on Phoenix Birman setup. On older APUs, return_origin value will be 0. Cc: stable@vger.kernel.org Fixes: 757cc3e9ff1d ("tee: add AMD-TEE driver") Tested-by: Sourabh Das Signed-off-by: Rijo Thomas Acked-by: Sumit Garg Signed-off-by: Jens Wiklander Signed-off-by: Greg Kroah-Hartman --- drivers/tee/amdtee/amdtee_if.h | 10 ++++++---- drivers/tee/amdtee/call.c | 28 ++++++++++++++++------------ 2 files changed, 22 insertions(+), 16 deletions(-) diff --git a/drivers/tee/amdtee/amdtee_if.h b/drivers/tee/amdtee/amdtee_if.h index ff48c3e47375..e2014e21530a 100644 --- a/drivers/tee/amdtee/amdtee_if.h +++ b/drivers/tee/amdtee/amdtee_if.h @@ -118,16 +118,18 @@ struct tee_cmd_unmap_shared_mem { /** * struct tee_cmd_load_ta - load Trusted Application (TA) binary into TEE - * @low_addr: [in] bits [31:0] of the physical address of the TA binary - * @hi_addr: [in] bits [63:32] of the physical address of the TA binary - * @size: [in] size of TA binary in bytes - * @ta_handle: [out] return handle of the loaded TA + * @low_addr: [in] bits [31:0] of the physical address of the TA binary + * @hi_addr: [in] bits [63:32] of the physical address of the TA binary + * @size: [in] size of TA binary in bytes + * @ta_handle: [out] return handle of the loaded TA + * @return_origin: [out] origin of return code after TEE processing */ struct tee_cmd_load_ta { u32 low_addr; u32 hi_addr; u32 size; u32 ta_handle; + u32 return_origin; }; /** diff --git a/drivers/tee/amdtee/call.c b/drivers/tee/amdtee/call.c index 07f36ac834c8..63d428423e90 100644 --- a/drivers/tee/amdtee/call.c +++ b/drivers/tee/amdtee/call.c @@ -423,19 +423,23 @@ int handle_load_ta(void *data, u32 size, struct tee_ioctl_open_session_arg *arg) if (ret) { arg->ret_origin = TEEC_ORIGIN_COMMS; arg->ret = TEEC_ERROR_COMMUNICATION; - } else if (arg->ret == TEEC_SUCCESS) { - ret = get_ta_refcount(load_cmd.ta_handle); - if (!ret) { - arg->ret_origin = TEEC_ORIGIN_COMMS; - arg->ret = TEEC_ERROR_OUT_OF_MEMORY; + } else { + arg->ret_origin = load_cmd.return_origin; - /* Unload the TA on error */ - unload_cmd.ta_handle = load_cmd.ta_handle; - psp_tee_process_cmd(TEE_CMD_ID_UNLOAD_TA, - (void *)&unload_cmd, - sizeof(unload_cmd), &ret); - } else { - set_session_id(load_cmd.ta_handle, 0, &arg->session); + if (arg->ret == TEEC_SUCCESS) { + ret = get_ta_refcount(load_cmd.ta_handle); + if (!ret) { + arg->ret_origin = TEEC_ORIGIN_COMMS; + arg->ret = TEEC_ERROR_OUT_OF_MEMORY; + + /* Unload the TA on error */ + unload_cmd.ta_handle = load_cmd.ta_handle; + psp_tee_process_cmd(TEE_CMD_ID_UNLOAD_TA, + (void *)&unload_cmd, + sizeof(unload_cmd), &ret); + } else { + set_session_id(load_cmd.ta_handle, 0, &arg->session); + } } } mutex_unlock(&ta_refcount_mutex); From 76ae4a7bc9996a28d24d8305a73bde75f7b4f3fb Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 5 Jun 2023 16:33:35 +0200 Subject: [PATCH 3479/4345] rbd: move RBD_OBJ_FLAG_COPYUP_ENABLED flag setting commit 09fe05c57b5aaf23e2c35036c98ea9f282b19a77 upstream. Move RBD_OBJ_FLAG_COPYUP_ENABLED flag setting into the object request state machine to allow for the snapshot context to be captured in the image request state machine rather than in rbd_queue_workfn(). Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/rbd.c | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 932d4bb8e403..cc578818a82b 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1397,14 +1397,28 @@ static bool rbd_obj_is_tail(struct rbd_obj_request *obj_req) /* * Must be called after rbd_obj_calc_img_extents(). */ -static bool rbd_obj_copyup_enabled(struct rbd_obj_request *obj_req) +static void rbd_obj_set_copyup_enabled(struct rbd_obj_request *obj_req) { - if (!obj_req->num_img_extents || - (rbd_obj_is_entire(obj_req) && - !obj_req->img_request->snapc->num_snaps)) - return false; + if (obj_req->img_request->op_type == OBJ_OP_DISCARD) { + dout("%s %p objno %llu discard\n", __func__, obj_req, + obj_req->ex.oe_objno); + return; + } - return true; + if (!obj_req->num_img_extents) { + dout("%s %p objno %llu not overlapping\n", __func__, obj_req, + obj_req->ex.oe_objno); + return; + } + + if (rbd_obj_is_entire(obj_req) && + !obj_req->img_request->snapc->num_snaps) { + dout("%s %p objno %llu entire\n", __func__, obj_req, + obj_req->ex.oe_objno); + return; + } + + obj_req->flags |= RBD_OBJ_FLAG_COPYUP_ENABLED; } static u64 rbd_obj_img_extents_bytes(struct rbd_obj_request *obj_req) @@ -2296,9 +2310,6 @@ static int rbd_obj_init_write(struct rbd_obj_request *obj_req) if (ret) return ret; - if (rbd_obj_copyup_enabled(obj_req)) - obj_req->flags |= RBD_OBJ_FLAG_COPYUP_ENABLED; - obj_req->write_state = RBD_OBJ_WRITE_START; return 0; } @@ -2404,8 +2415,6 @@ static int rbd_obj_init_zeroout(struct rbd_obj_request *obj_req) if (ret) return ret; - if (rbd_obj_copyup_enabled(obj_req)) - obj_req->flags |= RBD_OBJ_FLAG_COPYUP_ENABLED; if (!obj_req->num_img_extents) { obj_req->flags |= RBD_OBJ_FLAG_NOOP_FOR_NONEXISTENT; if (rbd_obj_is_entire(obj_req)) @@ -3351,6 +3360,7 @@ again: case RBD_OBJ_WRITE_START: rbd_assert(!*result); + rbd_obj_set_copyup_enabled(obj_req); if (rbd_obj_write_is_noop(obj_req)) return true; From 1981d37b1d762336930a3da4e1eeab2a7b65400d Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 5 Jun 2023 16:33:35 +0200 Subject: [PATCH 3480/4345] rbd: get snapshot context after exclusive lock is ensured to be held commit 870611e4877eff1e8413c3fb92a585e45d5291f6 upstream. Move capturing the snapshot context into the image request state machine, after exclusive lock is ensured to be held for the duration of dealing with the image request. This is needed to ensure correctness of fast-diff states (OBJECT_EXISTS vs OBJECT_EXISTS_CLEAN) and object deltas computed based off of them. Otherwise the object map that is forked for the snapshot isn't guaranteed to accurately reflect the contents of the snapshot when the snapshot is taken under I/O. This breaks differential backup and snapshot-based mirroring use cases with fast-diff enabled: since some object deltas may be incomplete, the destination image may get corrupted. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/61472 Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Signed-off-by: Greg Kroah-Hartman --- drivers/block/rbd.c | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index cc578818a82b..63491748dc8d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1399,6 +1399,8 @@ static bool rbd_obj_is_tail(struct rbd_obj_request *obj_req) */ static void rbd_obj_set_copyup_enabled(struct rbd_obj_request *obj_req) { + rbd_assert(obj_req->img_request->snapc); + if (obj_req->img_request->op_type == OBJ_OP_DISCARD) { dout("%s %p objno %llu discard\n", __func__, obj_req, obj_req->ex.oe_objno); @@ -1519,6 +1521,7 @@ __rbd_obj_add_osd_request(struct rbd_obj_request *obj_req, static struct ceph_osd_request * rbd_obj_add_osd_request(struct rbd_obj_request *obj_req, int num_ops) { + rbd_assert(obj_req->img_request->snapc); return __rbd_obj_add_osd_request(obj_req, obj_req->img_request->snapc, num_ops); } @@ -1655,15 +1658,18 @@ static void rbd_img_request_init(struct rbd_img_request *img_request, mutex_init(&img_request->state_mutex); } +/* + * Only snap_id is captured here, for reads. For writes, snapshot + * context is captured in rbd_img_object_requests() after exclusive + * lock is ensured to be held. + */ static void rbd_img_capture_header(struct rbd_img_request *img_req) { struct rbd_device *rbd_dev = img_req->rbd_dev; lockdep_assert_held(&rbd_dev->header_rwsem); - if (rbd_img_is_write(img_req)) - img_req->snapc = ceph_get_snap_context(rbd_dev->header.snapc); - else + if (!rbd_img_is_write(img_req)) img_req->snap_id = rbd_dev->spec->snap_id; if (rbd_dev_parent_get(rbd_dev)) @@ -3547,9 +3553,19 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req) static void rbd_img_object_requests(struct rbd_img_request *img_req) { + struct rbd_device *rbd_dev = img_req->rbd_dev; struct rbd_obj_request *obj_req; rbd_assert(!img_req->pending.result && !img_req->pending.num_pending); + rbd_assert(!need_exclusive_lock(img_req) || + __rbd_is_lock_owner(rbd_dev)); + + if (rbd_img_is_write(img_req)) { + rbd_assert(!img_req->snapc); + down_read(&rbd_dev->header_rwsem); + img_req->snapc = ceph_get_snap_context(rbd_dev->header.snapc); + up_read(&rbd_dev->header_rwsem); + } for_each_obj_request(img_req, obj_req) { int result = 0; @@ -3567,7 +3583,6 @@ static void rbd_img_object_requests(struct rbd_img_request *img_req) static bool rbd_img_advance(struct rbd_img_request *img_req, int *result) { - struct rbd_device *rbd_dev = img_req->rbd_dev; int ret; again: @@ -3588,9 +3603,6 @@ again: if (*result) return true; - rbd_assert(!need_exclusive_lock(img_req) || - __rbd_is_lock_owner(rbd_dev)); - rbd_img_object_requests(img_req); if (!img_req->pending.num_pending) { *result = img_req->pending.result; @@ -4048,6 +4060,10 @@ static int rbd_post_acquire_action(struct rbd_device *rbd_dev) { int ret; + ret = rbd_dev_refresh(rbd_dev); + if (ret) + return ret; + if (rbd_dev->header.features & RBD_FEATURE_OBJECT_MAP) { ret = rbd_object_map_open(rbd_dev); if (ret) From bcd474d1838e460859da55f94e427c1dbaad8a29 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Hundeb=C3=B8ll?= Date: Fri, 12 May 2023 08:49:25 +0200 Subject: [PATCH 3481/4345] pinctrl: meson-axg: add missing GPIOA_18 gpio group MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 5b10ff013e8a57f8845615ac2cc37edf7f6eef05 upstream. Without this, the gpio cannot be explicitly mux'ed to its gpio function. Fixes: 83c566806a68a ("pinctrl: meson-axg: Add new pinctrl driver for Meson AXG SoC") Cc: stable@vger.kernel.org Signed-off-by: Martin Hundebøll Reviewed-by: Neil Armstrong Reviewed-by: Dmitry Rokosov Link: https://lore.kernel.org/r/20230512064925.133516-1-martin@geanix.com Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/meson/pinctrl-meson-axg.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/meson/pinctrl-meson-axg.c b/drivers/pinctrl/meson/pinctrl-meson-axg.c index 072765db93d7..505466b06629 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-axg.c +++ b/drivers/pinctrl/meson/pinctrl-meson-axg.c @@ -400,6 +400,7 @@ static struct meson_pmx_group meson_axg_periphs_groups[] = { GPIO_GROUP(GPIOA_15), GPIO_GROUP(GPIOA_16), GPIO_GROUP(GPIOA_17), + GPIO_GROUP(GPIOA_18), GPIO_GROUP(GPIOA_19), GPIO_GROUP(GPIOA_20), From 143f405721744df0563982195548f3d8c1ca0c49 Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Mon, 15 May 2023 21:09:55 +0800 Subject: [PATCH 3482/4345] usb: usbfs: Enforce page requirements for mmap commit 0143d148d1e882fb1538dc9974c94d63961719b9 upstream. The current implementation of usbdev_mmap uses usb_alloc_coherent to allocate memory pages that will later be mapped into the user space. Meanwhile, usb_alloc_coherent employs three different methods to allocate memory, as outlined below: * If hcd->localmem_pool is non-null, it uses gen_pool_dma_alloc to allocate memory; * If DMA is not available, it uses kmalloc to allocate memory; * Otherwise, it uses dma_alloc_coherent. However, it should be noted that gen_pool_dma_alloc does not guarantee that the resulting memory will be page-aligned. Furthermore, trying to map slab pages (i.e., memory allocated by kmalloc) into the user space is not resonable and can lead to problems, such as a type confusion bug when PAGE_TABLE_CHECK=y [1]. To address these issues, this patch introduces hcd_alloc_coherent_pages, which addresses the above two problems. Specifically, hcd_alloc_coherent_pages uses gen_pool_dma_alloc_align instead of gen_pool_dma_alloc to ensure that the memory is page-aligned. To replace kmalloc, hcd_alloc_coherent_pages directly allocates pages by calling __get_free_pages. Reported-by: syzbot+fcf1a817ceb50935ce99@syzkaller.appspotmail.comm Closes: https://lore.kernel.org/lkml/000000000000258e5e05fae79fc1@google.com/ [1] Fixes: f7d34b445abc ("USB: Add support for usbfs zerocopy.") Fixes: ff2437befd8f ("usb: host: Fix excessive alignment restriction for local memory allocations") Cc: stable@vger.kernel.org Signed-off-by: Ruihan Li Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230515130958.32471-2-lrh2000@pku.edu.cn Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/buffer.c | 41 +++++++++++++++++++++++++++++++++++++++ drivers/usb/core/devio.c | 9 +++++---- include/linux/usb/hcd.h | 5 +++++ 3 files changed, 51 insertions(+), 4 deletions(-) diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c index 6cf22c27f2d2..be8738750948 100644 --- a/drivers/usb/core/buffer.c +++ b/drivers/usb/core/buffer.c @@ -170,3 +170,44 @@ void hcd_buffer_free( } dma_free_coherent(hcd->self.sysdev, size, addr, dma); } + +void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, + size_t size, gfp_t mem_flags, dma_addr_t *dma) +{ + if (size == 0) + return NULL; + + if (hcd->localmem_pool) + return gen_pool_dma_alloc_align(hcd->localmem_pool, + size, dma, PAGE_SIZE); + + /* some USB hosts just use PIO */ + if (!hcd_uses_dma(hcd)) { + *dma = DMA_MAPPING_ERROR; + return (void *)__get_free_pages(mem_flags, + get_order(size)); + } + + return dma_alloc_coherent(hcd->self.sysdev, + size, dma, mem_flags); +} + +void hcd_buffer_free_pages(struct usb_hcd *hcd, + size_t size, void *addr, dma_addr_t dma) +{ + if (!addr) + return; + + if (hcd->localmem_pool) { + gen_pool_free(hcd->localmem_pool, + (unsigned long)addr, size); + return; + } + + if (!hcd_uses_dma(hcd)) { + free_pages((unsigned long)addr, get_order(size)); + return; + } + + dma_free_coherent(hcd->self.sysdev, size, addr, dma); +} diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 73b60f013b20..1590fec738f6 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -173,6 +173,7 @@ static int connected(struct usb_dev_state *ps) static void dec_usb_memory_use_count(struct usb_memory *usbm, int *count) { struct usb_dev_state *ps = usbm->ps; + struct usb_hcd *hcd = bus_to_hcd(ps->dev->bus); unsigned long flags; spin_lock_irqsave(&ps->lock, flags); @@ -181,8 +182,8 @@ static void dec_usb_memory_use_count(struct usb_memory *usbm, int *count) list_del(&usbm->memlist); spin_unlock_irqrestore(&ps->lock, flags); - usb_free_coherent(ps->dev, usbm->size, usbm->mem, - usbm->dma_handle); + hcd_buffer_free_pages(hcd, usbm->size, + usbm->mem, usbm->dma_handle); usbfs_decrease_memory_usage( usbm->size + sizeof(struct usb_memory)); kfree(usbm); @@ -234,8 +235,8 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) goto error_decrease_mem; } - mem = usb_alloc_coherent(ps->dev, size, GFP_USER | __GFP_NOWARN, - &dma_handle); + mem = hcd_buffer_alloc_pages(hcd, + size, GFP_USER | __GFP_NOWARN, &dma_handle); if (!mem) { ret = -ENOMEM; goto error_free_usbm; diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index c0cf20b19e63..528be670006f 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -504,6 +504,11 @@ void *hcd_buffer_alloc(struct usb_bus *bus, size_t size, void hcd_buffer_free(struct usb_bus *bus, size_t size, void *addr, dma_addr_t dma); +void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, + size_t size, gfp_t mem_flags, dma_addr_t *dma); +void hcd_buffer_free_pages(struct usb_hcd *hcd, + size_t size, void *addr, dma_addr_t dma); + /* generic bus glue, needed for host controllers that don't use PCI */ extern irqreturn_t usb_hcd_irq(int irq, void *__hcd); From 0d3c75a6934468ee9846d6ccfb6a37e7245c96eb Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Mon, 15 May 2023 21:09:56 +0800 Subject: [PATCH 3483/4345] usb: usbfs: Use consistent mmap functions commit d0b861653f8c16839c3035875b556afc4472f941 upstream. When hcd->localmem_pool is non-null, localmem_pool is used to allocate DMA memory. In this case, the dma address will be properly returned (in dma_handle), and dma_mmap_coherent should be used to map this memory into the user space. However, the current implementation uses pfn_remap_range, which is supposed to map normal pages. Instead of repeating the logic in the memory allocation function, this patch introduces a more robust solution. Here, the type of allocated memory is checked by testing whether dma_handle is properly set. If dma_handle is properly returned, it means some DMA pages are allocated and dma_mmap_coherent should be used to map them. Otherwise, normal pages are allocated and pfn_remap_range should be called. This ensures that the correct mmap functions are used consistently, independently with logic details that determine which type of memory gets allocated. Fixes: a0e710a7def4 ("USB: usbfs: fix mmap dma mismatch") Cc: stable@vger.kernel.org Signed-off-by: Ruihan Li Link: https://lore.kernel.org/r/20230515130958.32471-3-lrh2000@pku.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/devio.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 1590fec738f6..2fe29319de44 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -222,7 +222,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) size_t size = vma->vm_end - vma->vm_start; void *mem; unsigned long flags; - dma_addr_t dma_handle; + dma_addr_t dma_handle = DMA_MAPPING_ERROR; int ret; ret = usbfs_increase_memory_usage(size + sizeof(struct usb_memory)); @@ -252,7 +252,14 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) usbm->vma_use_count = 1; INIT_LIST_HEAD(&usbm->memlist); - if (hcd->localmem_pool || !hcd_uses_dma(hcd)) { + /* + * In DMA-unavailable cases, hcd_buffer_alloc_pages allocates + * normal pages and assigns DMA_MAPPING_ERROR to dma_handle. Check + * whether we are in such cases, and then use remap_pfn_range (or + * dma_mmap_coherent) to map normal (or DMA) pages into the user + * space, respectively. + */ + if (dma_handle == DMA_MAPPING_ERROR) { if (remap_pfn_range(vma, vma->vm_start, virt_to_phys(usbm->mem) >> PAGE_SHIFT, size, vma->vm_page_prot) < 0) { From b6f309e9d24e9b14ffa8d35422b55fec3b9e713e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 11 Jun 2023 15:39:46 +0200 Subject: [PATCH 3484/4345] staging: vc04_services: fix gcc-13 build warning Not upstream as newer kernels fixed this properly. Fix up a mismatched function prototype warning in the vc04_services driver that gcc-13 shows. Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 893d102d2dcf..178cf90fb3e5 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -2315,7 +2315,7 @@ vchiq_arm_init_state(struct vchiq_state *state, return VCHIQ_SUCCESS; } -enum vchiq_status +int vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service, enum USE_TYPE_E use_type) { @@ -2375,7 +2375,7 @@ out: return ret; } -enum vchiq_status +int vchiq_release_internal(struct vchiq_state *state, struct vchiq_service *service) { struct vchiq_arm_state *arm_state = vchiq_platform_get_arm_state(state); From c4aeef56022eb97ad060e14fcede3047e1db772d Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 23 May 2023 16:46:05 +0100 Subject: [PATCH 3485/4345] ASoC: codecs: wsa881x: do not set can_multi_write flag [ Upstream commit 6e7a6d4797ef521c0762914610ed682e102b9d36 ] regmap-sdw does not support multi register writes, so there is no point in setting this flag. This also leads to incorrect programming of WSA codecs with regmap_multi_reg_write() call. This invalid configuration should have been rejected by regmap-sdw. Fixes: a0aab9e1404a ("ASoC: codecs: add wsa881x amplifier support") Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230523154605.4284-2-srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/wsa881x.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 15b3f47fbfa3..9f66f6dc2c67 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -646,7 +646,6 @@ static struct regmap_config wsa881x_regmap_config = { .readable_reg = wsa881x_readable_register, .reg_format_endian = REGMAP_ENDIAN_NATIVE, .val_format_endian = REGMAP_ENDIAN_NATIVE, - .can_multi_write = true, }; enum { From 10e376a7c3874187d9a59ea2e33bca1ddcbc6394 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 9 Mar 2023 10:58:19 +0100 Subject: [PATCH 3486/4345] i2c: sprd: Delete i2c adapter in .remove's error path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ca0aa17f2db3468fd017038d23a78e17388e2f67 ] If pm runtime resume fails the .remove callback used to exit early. This resulted in an error message by the driver core but the device gets removed anyhow. This lets the registered i2c adapter stay around with an unbound parent device. So only skip clk disabling if resume failed, but do delete the adapter. Fixes: 8b9ec0719834 ("i2c: Add Spreadtrum I2C controller driver") Signed-off-by: Uwe Kleine-König Reviewed-by: Andi Shyti Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-sprd.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c index 8ead7e021008..a520aa06d2cb 100644 --- a/drivers/i2c/busses/i2c-sprd.c +++ b/drivers/i2c/busses/i2c-sprd.c @@ -576,12 +576,14 @@ static int sprd_i2c_remove(struct platform_device *pdev) struct sprd_i2c *i2c_dev = platform_get_drvdata(pdev); int ret; - ret = pm_runtime_resume_and_get(i2c_dev->dev); + ret = pm_runtime_get_sync(i2c_dev->dev); if (ret < 0) - return ret; + dev_err(&pdev->dev, "Failed to resume device (%pe)\n", ERR_PTR(ret)); i2c_del_adapter(&i2c_dev->adap); - clk_disable_unprepare(i2c_dev->clk); + + if (ret >= 0) + clk_disable_unprepare(i2c_dev->clk); pm_runtime_put_noidle(i2c_dev->dev); pm_runtime_disable(i2c_dev->dev); From c6b905087428f17243e4e203aa1b43a3b88a30cc Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 7 Jun 2023 19:54:24 -0700 Subject: [PATCH 3487/4345] eeprom: at24: also select REGMAP [ Upstream commit 7f3c782b3914e510b646a77aedc3adeac2e4a63b ] Selecting only REGMAP_I2C can leave REGMAP unset, causing build errors, so also select REGMAP to prevent the build errors. ../drivers/misc/eeprom/at24.c:540:42: warning: 'struct regmap_config' declared inside parameter list will not be visible outside of this definition or declaration 540 | struct regmap_config *regmap_config) ../drivers/misc/eeprom/at24.c: In function 'at24_make_dummy_client': ../drivers/misc/eeprom/at24.c:552:18: error: implicit declaration of function 'devm_regmap_init_i2c' [-Werror=implicit-function-declaration] 552 | regmap = devm_regmap_init_i2c(dummy_client, regmap_config); ../drivers/misc/eeprom/at24.c:552:16: warning: assignment to 'struct regmap *' from 'int' makes pointer from integer without a cast [-Wint-conversion] 552 | regmap = devm_regmap_init_i2c(dummy_client, regmap_config); ../drivers/misc/eeprom/at24.c: In function 'at24_probe': ../drivers/misc/eeprom/at24.c:586:16: error: variable 'regmap_config' has initializer but incomplete type 586 | struct regmap_config regmap_config = { }; ../drivers/misc/eeprom/at24.c:586:30: error: storage size of 'regmap_config' isn't known 586 | struct regmap_config regmap_config = { }; ../drivers/misc/eeprom/at24.c:586:30: warning: unused variable 'regmap_config' [-Wunused-variable] Fixes: 5c015258478e ("eeprom: at24: add basic regmap_i2c support") Signed-off-by: Randy Dunlap Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/misc/eeprom/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/misc/eeprom/Kconfig b/drivers/misc/eeprom/Kconfig index 0f791bfdc1f5..c92f2cdf4026 100644 --- a/drivers/misc/eeprom/Kconfig +++ b/drivers/misc/eeprom/Kconfig @@ -6,6 +6,7 @@ config EEPROM_AT24 depends on I2C && SYSFS select NVMEM select NVMEM_SYSFS + select REGMAP select REGMAP_I2C help Enable this driver to get read/write support to most I2C EEPROMs From 461c88caa889d95ebfa6cc66da86e3ac835cb78a Mon Sep 17 00:00:00 2001 From: Ruan Jinjie Date: Thu, 4 May 2023 15:29:10 +0800 Subject: [PATCH 3488/4345] riscv: fix kprobe __user string arg print fault issue MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 99a670b2069c725a7b50318aa681d9cae8f89325 ] On riscv qemu platform, when add kprobe event on do_sys_open() to show filename string arg, it just print fault as follow: echo 'p:myprobe do_sys_open dfd=$arg1 filename=+0($arg2):string flags=$arg3 mode=$arg4' > kprobe_events bash-166 [000] ...1. 360.195367: myprobe: (do_sys_open+0x0/0x84) dfd=0xffffffffffffff9c filename=(fault) flags=0x8241 mode=0x1b6 bash-166 [000] ...1. 360.219369: myprobe: (do_sys_open+0x0/0x84) dfd=0xffffffffffffff9c filename=(fault) flags=0x8241 mode=0x1b6 bash-191 [000] ...1. 360.378827: myprobe: (do_sys_open+0x0/0x84) dfd=0xffffffffffffff9c filename=(fault) flags=0x98800 mode=0x0 As riscv do not select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE, the +0($arg2) addr is processed as a kernel address though it is a userspace address, cause the above filename=(fault) print. So select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE to avoid the issue, after that the kprobe trace is ok as below: bash-166 [000] ...1. 96.767641: myprobe: (do_sys_open+0x0/0x84) dfd=0xffffffffffffff9c filename="/dev/null" flags=0x8241 mode=0x1b6 bash-166 [000] ...1. 96.793751: myprobe: (do_sys_open+0x0/0x84) dfd=0xffffffffffffff9c filename="/dev/null" flags=0x8241 mode=0x1b6 bash-177 [000] ...1. 96.962354: myprobe: (do_sys_open+0x0/0x84) dfd=0xffffffffffffff9c filename="/sys/kernel/debug/tracing/events/kprobes/" flags=0x98800 mode=0x0 Signed-off-by: Ruan Jinjie Acked-by: Björn Töpel Fixes: 0ebeea8ca8a4 ("bpf: Restrict bpf_probe_read{, str}() only to archs where they work") Link: https://lore.kernel.org/r/20230504072910.3742842-1-ruanjinjie@huawei.com Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin --- arch/riscv/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c192bd7305dc..b28fabfc91bf 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -22,6 +22,7 @@ config RISCV select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV select ARCH_HAS_MMIOWB + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_DIRECT_MAP select ARCH_HAS_SET_MEMORY From cfa91c0573a563a51d33513883d2e96b4f4e193b Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Mon, 24 Apr 2023 15:50:30 -0700 Subject: [PATCH 3489/4345] vhost: support PACKED when setting-getting vring_base [ Upstream commit 55d8122f5cd62d5aaa225d7167dcd14a44c850b9 ] Use the right structs for PACKED or split vqs when setting and getting the vring base. Fixes: 4c8cf31885f6 ("vhost: introduce vDPA-based backend") Signed-off-by: Shannon Nelson Message-Id: <20230424225031.18947-3-shannon.nelson@amd.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Signed-off-by: Sasha Levin --- drivers/vhost/vhost.c | 18 +++++++++++++----- drivers/vhost/vhost.h | 8 ++++++-- 2 files changed, 19 insertions(+), 7 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 1f9a1554ce5f..de110363af52 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1621,17 +1621,25 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg r = -EFAULT; break; } - if (s.num > 0xffff) { - r = -EINVAL; - break; + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { + vq->last_avail_idx = s.num & 0xffff; + vq->last_used_idx = (s.num >> 16) & 0xffff; + } else { + if (s.num > 0xffff) { + r = -EINVAL; + break; + } + vq->last_avail_idx = s.num; } - vq->last_avail_idx = s.num; /* Forget the cached index value. */ vq->avail_idx = vq->last_avail_idx; break; case VHOST_GET_VRING_BASE: s.index = idx; - s.num = vq->last_avail_idx; + if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) + s.num = (u32)vq->last_avail_idx | ((u32)vq->last_used_idx << 16); + else + s.num = vq->last_avail_idx; if (copy_to_user(argp, &s, sizeof s)) r = -EFAULT; break; diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 8f80d6b0d843..e00347f2b4d3 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -87,13 +87,17 @@ struct vhost_virtqueue { /* The routine to call when the Guest pings us, or timeout. */ vhost_work_fn_t handle_kick; - /* Last available index we saw. */ + /* Last available index we saw. + * Values are limited to 0x7fff, and the high bit is used as + * a wrap counter when using VIRTIO_F_RING_PACKED. */ u16 last_avail_idx; /* Caches available index value from user. */ u16 avail_idx; - /* Last index we used. */ + /* Last index we used. + * Values are limited to 0x7fff, and the high bit is used as + * a wrap counter when using VIRTIO_F_RING_PACKED. */ u16 last_used_idx; /* Used flags */ From fd6cb5171903b3e46fd4c7f0e730cda496f4b6c9 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 8 Jun 2023 09:57:04 -0400 Subject: [PATCH 3490/4345] Revert "ext4: don't clear SB_RDONLY when remounting r/w until quota is re-enabled" commit 1b29243933098cdbc31b579b5616e183b4275e2f upstream. This reverts commit a44be64bbecb15a452496f60db6eacfee2b59c79. Link: https://lore.kernel.org/r/653b3359-2005-21b1-039d-c55ca4cffdcc@gmail.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/super.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f72896384dbc..84b4fc9833e3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5799,7 +5799,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_group_t g; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; int err = 0; - int enable_rw = 0; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; @@ -5992,7 +5991,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (err) goto restore_opts; - enable_rw = 1; + sb->s_flags &= ~SB_RDONLY; if (ext4_has_feature_mmp(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); @@ -6039,9 +6038,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); - if (enable_rw) - sb->s_flags &= ~SB_RDONLY; - /* * Reinitialize lazy itable initialization thread based on * current settings From 1b4b3350969e0d56363eaa0f46bd0c1d07b066d8 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 8 Jun 2023 10:06:40 -0400 Subject: [PATCH 3491/4345] ext4: only check dquot_initialize_needed() when debugging commit dea9d8f7643fab07bf89a1155f1f94f37d096a5e upstream. ext4_xattr_block_set() relies on its caller to call dquot_initialize() on the inode. To assure that this has happened there are WARN_ON checks. Unfortunately, this is subject to false positives if there is an antagonist thread which is flipping the file system at high rates between r/o and rw. So only do the check if EXT4_XATTR_DEBUG is enabled. Link: https://lore.kernel.org/r/20230608044056.GA1418535@mit.edu Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 10b2f570d400..ed39101dc7b6 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1999,8 +1999,9 @@ inserted: else { u32 ref; +#ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); - +#endif /* The old block is released after updating the inode. */ error = dquot_alloc_block(inode, @@ -2062,8 +2063,9 @@ inserted: /* We need to allocate a new block */ ext4_fsblk_t goal, block; +#ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); - +#endif goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); block = ext4_new_meta_blocks(handle, inode, goal, 0, From 58e8cf94de128ca8faa9191d2b9feae051118824 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 29 Mar 2021 10:40:49 -0700 Subject: [PATCH 3492/4345] tcp: fix tcp_min_tso_segs sysctl commit d24f511b04b8b159b705ec32a3b8782667d1b06a upstream. tcp_min_tso_segs is now stored in u8, so max value is 255. 255 limit is enforced by proc_dou8vec_minmax(). We can therefore remove the gso_max_segs variable. Fixes: 47996b489bdc ("tcp: convert elligible sysctls to u8") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/sysctl_net_ipv4.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3a34e9768bff..5aa8bde3e9c8 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -31,7 +31,6 @@ static int two = 2; static int four = 4; static int thousand = 1000; -static int gso_max_segs = GSO_MAX_SEGS; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; @@ -1193,7 +1192,6 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ONE, - .extra2 = &gso_max_segs, }, { .procname = "tcp_min_rtt_wlen", From 0e98a97f772f2ffcee8ced7a49b71e72916e0aa1 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 12 Apr 2023 15:49:23 +1000 Subject: [PATCH 3493/4345] xfs: verify buffer contents when we skip log replay commit 22ed903eee23a5b174e240f1cdfa9acf393a5210 upstream. syzbot detected a crash during log recovery: XFS (loop0): Mounting V5 Filesystem bfdc47fc-10d8-4eed-a562-11a831b3f791 XFS (loop0): Torn write (CRC failure) detected at log block 0x180. Truncating head block from 0x200. XFS (loop0): Starting recovery (logdev: internal) ================================================================== BUG: KASAN: slab-out-of-bounds in xfs_btree_lookup_get_block+0x15c/0x6d0 fs/xfs/libxfs/xfs_btree.c:1813 Read of size 8 at addr ffff88807e89f258 by task syz-executor132/5074 CPU: 0 PID: 5074 Comm: syz-executor132 Not tainted 6.2.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x290 lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:306 print_report+0x107/0x1f0 mm/kasan/report.c:417 kasan_report+0xcd/0x100 mm/kasan/report.c:517 xfs_btree_lookup_get_block+0x15c/0x6d0 fs/xfs/libxfs/xfs_btree.c:1813 xfs_btree_lookup+0x346/0x12c0 fs/xfs/libxfs/xfs_btree.c:1913 xfs_btree_simple_query_range+0xde/0x6a0 fs/xfs/libxfs/xfs_btree.c:4713 xfs_btree_query_range+0x2db/0x380 fs/xfs/libxfs/xfs_btree.c:4953 xfs_refcount_recover_cow_leftovers+0x2d1/0xa60 fs/xfs/libxfs/xfs_refcount.c:1946 xfs_reflink_recover_cow+0xab/0x1b0 fs/xfs/xfs_reflink.c:930 xlog_recover_finish+0x824/0x920 fs/xfs/xfs_log_recover.c:3493 xfs_log_mount_finish+0x1ec/0x3d0 fs/xfs/xfs_log.c:829 xfs_mountfs+0x146a/0x1ef0 fs/xfs/xfs_mount.c:933 xfs_fs_fill_super+0xf95/0x11f0 fs/xfs/xfs_super.c:1666 get_tree_bdev+0x400/0x620 fs/super.c:1282 vfs_get_tree+0x88/0x270 fs/super.c:1489 do_new_mount+0x289/0xad0 fs/namespace.c:3145 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x2d3/0x3c0 fs/namespace.c:3674 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f89fa3f4aca Code: 83 c4 08 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fffd5fb5ef8 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00646975756f6e2c RCX: 00007f89fa3f4aca RDX: 0000000020000100 RSI: 0000000020009640 RDI: 00007fffd5fb5f10 RBP: 00007fffd5fb5f10 R08: 00007fffd5fb5f50 R09: 000000000000970d R10: 0000000000200800 R11: 0000000000000206 R12: 0000000000000004 R13: 0000555556c6b2c0 R14: 0000000000200800 R15: 00007fffd5fb5f50 The fuzzed image contains an AGF with an obviously garbage agf_refcount_level value of 32, and a dirty log with a buffer log item for that AGF. The ondisk AGF has a higher LSN than the recovered log item. xlog_recover_buf_commit_pass2 reads the buffer, compares the LSNs, and decides to skip replay because the ondisk buffer appears to be newer. Unfortunately, the ondisk buffer is corrupt, but recovery just read the buffer with no buffer ops specified: error = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len, buf_flags, &bp, NULL); Skipping the buffer leaves its contents in memory unverified. This sets us up for a kernel crash because xfs_refcount_recover_cow_leftovers reads the buffer (which is still around in XBF_DONE state, so no read verification) and creates a refcountbt cursor of height 32. This is impossible so we run off the end of the cursor object and crash. Fix this by invoking the verifier on all skipped buffers and aborting log recovery if the ondisk buffer is corrupt. It might be smarter to force replay the log item atop the buffer and then see if it'll pass the write verifier (like ext4 does) but for now let's go with the conservative option where we stop immediately. Link: https://syzkaller.appspot.com/bug?extid=7e9494b8b399902e994e Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner Signed-off-by: Leah Rumancik Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_buf_item_recover.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index b374c9cee117..a053b0bf7930 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -924,6 +924,16 @@ xlog_recover_buf_commit_pass2( if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) { trace_xfs_log_recover_buf_skip(log, buf_f); xlog_recover_validate_buf_type(mp, bp, buf_f, NULLCOMMITLSN); + + /* + * We're skipping replay of this buffer log item due to the log + * item LSN being behind the ondisk buffer. Verify the buffer + * contents since we aren't going to run the write verifier. + */ + if (bp->b_ops) { + bp->b_ops->verify_read(bp); + error = bp->b_error; + } goto out_release; } From 1659268d1ab4c11923b8fde86eca91f4ce256c96 Mon Sep 17 00:00:00 2001 From: Rui Wang Date: Thu, 29 Jul 2021 17:31:52 +0800 Subject: [PATCH 3494/4345] MIPS: locking/atomic: Fix atomic{_64,}_sub_if_positive commit cb95ea79b3fc772c5873a7a4532ab4c14a455da2 upstream. This looks like a typo and that caused atomic64 test failed. Signed-off-by: Rui Wang Signed-off-by: Thomas Bogendoerfer Signed-off-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- arch/mips/include/asm/atomic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 27ad76791539..fd0e09033a7c 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -203,7 +203,7 @@ ATOMIC_OPS(atomic64, xor, s64, ^=, xor, lld, scd) * The function returns the old value of @v minus @i. */ #define ATOMIC_SIP_OP(pfx, type, op, ll, sc) \ -static __inline__ int pfx##_sub_if_positive(type i, pfx##_t * v) \ +static __inline__ type pfx##_sub_if_positive(type i, pfx##_t * v) \ { \ type temp, result; \ \ From ea0d413094e064389755fd3585a4264b54d1d44a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 9 Feb 2022 11:19:27 +0200 Subject: [PATCH 3495/4345] drm/atomic: Don't pollute crtc_state->mode_blob with error pointers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 439cf34c8e0a8a33d8c15a31be1b7423426bc765 upstream. Make sure we don't assign an error pointer to crtc_state->mode_blob as that will break all kinds of places that assume either NULL or a valid pointer (eg. drm_property_blob_put()). Cc: stable@vger.kernel.org Reported-by: fuyufan Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20220209091928.14766-1-ville.syrjala@linux.intel.com Acked-by: Maxime Ripard Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_atomic_uapi.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 25c269bc4681..b6062833370f 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -75,15 +75,17 @@ int drm_atomic_set_mode_for_crtc(struct drm_crtc_state *state, state->mode_blob = NULL; if (mode) { + struct drm_property_blob *blob; + drm_mode_convert_to_umode(&umode, mode); - state->mode_blob = - drm_property_create_blob(state->crtc->dev, - sizeof(umode), - &umode); - if (IS_ERR(state->mode_blob)) - return PTR_ERR(state->mode_blob); + blob = drm_property_create_blob(crtc->dev, + sizeof(umode), &umode); + if (IS_ERR(blob)) + return PTR_ERR(blob); drm_mode_copy(&state->mode, mode); + + state->mode_blob = blob; state->enable = true; DRM_DEBUG_ATOMIC("Set [MODE:%s] for [CRTC:%d:%s] state %p\n", mode->name, crtc->base.id, crtc->name, state); From 6f371623f315c26100e603c2e8837cdbe130f9e0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 12 Mar 2021 15:25:34 -0500 Subject: [PATCH 3496/4345] btrfs: check return value of btrfs_commit_transaction in relocation commit fb686c6824dd6294ca772b92424b8fba666e7d00 upstream. There are a few places where we don't check the return value of btrfs_commit_transaction in relocation.c. Thankfully all these places have straightforward error handling, so simply change all of the sites at once. Reviewed-by: Qu Wenruo Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Stefan Ghinea Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/relocation.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index c21545c5b34b..7d64180fec2e 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1895,7 +1895,7 @@ again: list_splice(&reloc_roots, &rc->reloc_roots); if (!err) - btrfs_commit_transaction(trans); + err = btrfs_commit_transaction(trans); else btrfs_end_transaction(trans); return err; @@ -3270,8 +3270,7 @@ int prepare_to_relocate(struct reloc_control *rc) */ return PTR_ERR(trans); } - btrfs_commit_transaction(trans); - return 0; + return btrfs_commit_transaction(trans); } static noinline_for_stack int relocate_block_group(struct reloc_control *rc) @@ -3443,7 +3442,9 @@ restart: err = PTR_ERR(trans); goto out_free; } - btrfs_commit_transaction(trans); + ret = btrfs_commit_transaction(trans); + if (ret && !err) + err = ret; out_free: ret = clean_dirty_subvols(rc); if (ret < 0 && !err) From b60e862e133f646f19023ece1d476d630a660de1 Mon Sep 17 00:00:00 2001 From: Zixuan Fu Date: Thu, 21 Jul 2022 15:48:29 +0800 Subject: [PATCH 3497/4345] btrfs: unset reloc control if transaction commit fails in prepare_to_relocate() commit 85f02d6c856b9f3a0acf5219de6e32f58b9778eb upstream. In btrfs_relocate_block_group(), the rc is allocated. Then btrfs_relocate_block_group() calls relocate_block_group() prepare_to_relocate() set_reloc_control() that assigns rc to the variable fs_info->reloc_ctl. When prepare_to_relocate() returns, it calls btrfs_commit_transaction() btrfs_start_dirty_block_groups() btrfs_alloc_path() kmem_cache_zalloc() which may fail for example (or other errors could happen). When the failure occurs, btrfs_relocate_block_group() detects the error and frees rc and doesn't set fs_info->reloc_ctl to NULL. After that, in btrfs_init_reloc_root(), rc is retrieved from fs_info->reloc_ctl and then used, which may cause a use-after-free bug. This possible bug can be triggered by calling btrfs_ioctl_balance() before calling btrfs_ioctl_defrag(). To fix this possible bug, in prepare_to_relocate(), check if btrfs_commit_transaction() fails. If the failure occurs, unset_reloc_control() is called to set fs_info->reloc_ctl to NULL. The error log in our fault-injection testing is shown as follows: [ 58.751070] BUG: KASAN: use-after-free in btrfs_init_reloc_root+0x7ca/0x920 [btrfs] ... [ 58.753577] Call Trace: ... [ 58.755800] kasan_report+0x45/0x60 [ 58.756066] btrfs_init_reloc_root+0x7ca/0x920 [btrfs] [ 58.757304] record_root_in_trans+0x792/0xa10 [btrfs] [ 58.757748] btrfs_record_root_in_trans+0x463/0x4f0 [btrfs] [ 58.758231] start_transaction+0x896/0x2950 [btrfs] [ 58.758661] btrfs_defrag_root+0x250/0xc00 [btrfs] [ 58.759083] btrfs_ioctl_defrag+0x467/0xa00 [btrfs] [ 58.759513] btrfs_ioctl+0x3c95/0x114e0 [btrfs] ... [ 58.768510] Allocated by task 23683: [ 58.768777] ____kasan_kmalloc+0xb5/0xf0 [ 58.769069] __kmalloc+0x227/0x3d0 [ 58.769325] alloc_reloc_control+0x10a/0x3d0 [btrfs] [ 58.769755] btrfs_relocate_block_group+0x7aa/0x1e20 [btrfs] [ 58.770228] btrfs_relocate_chunk+0xf1/0x760 [btrfs] [ 58.770655] __btrfs_balance+0x1326/0x1f10 [btrfs] [ 58.771071] btrfs_balance+0x3150/0x3d30 [btrfs] [ 58.771472] btrfs_ioctl_balance+0xd84/0x1410 [btrfs] [ 58.771902] btrfs_ioctl+0x4caa/0x114e0 [btrfs] ... [ 58.773337] Freed by task 23683: ... [ 58.774815] kfree+0xda/0x2b0 [ 58.775038] free_reloc_control+0x1d6/0x220 [btrfs] [ 58.775465] btrfs_relocate_block_group+0x115c/0x1e20 [btrfs] [ 58.775944] btrfs_relocate_chunk+0xf1/0x760 [btrfs] [ 58.776369] __btrfs_balance+0x1326/0x1f10 [btrfs] [ 58.776784] btrfs_balance+0x3150/0x3d30 [btrfs] [ 58.777185] btrfs_ioctl_balance+0xd84/0x1410 [btrfs] [ 58.777621] btrfs_ioctl+0x4caa/0x114e0 [btrfs] ... Reported-by: TOTE Robot CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Sweet Tea Dorminy Reviewed-by: Nikolay Borisov Signed-off-by: Zixuan Fu Signed-off-by: David Sterba Signed-off-by: Stefan Ghinea Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/relocation.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 7d64180fec2e..93db4486a943 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3270,7 +3270,12 @@ int prepare_to_relocate(struct reloc_control *rc) */ return PTR_ERR(trans); } - return btrfs_commit_transaction(trans); + + ret = btrfs_commit_transaction(trans); + if (ret) + unset_reloc_control(rc); + + return ret; } static noinline_for_stack int relocate_block_group(struct reloc_control *rc) From 7f896130eff772a5b340a78d166ed881b8376412 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 12 Jun 2023 12:06:32 +0200 Subject: [PATCH 3498/4345] Revert "staging: rtl8192e: Replace macro RTL_PCI_DEVICE with PCI_DEVICE" This reverts commit bb1313f37e7b267fcf0fe475b974be8de5f39945 which is commit fda2093860df4812d69052a8cf4997e53853a340 upstream. Ben reports that this should not have been backported to the older kernels as the rest of the macro is not empty. It was a clean-up patch in 6.4-rc1 only, it did not add new device ids. Reported-by: Ben Hutchings Cc: Philipp Hortmann Cc: Sasha Levin Link: https://lore.kernel.org/r/aa0d401a7f63448cd4c2fe4a2d7e8495d9aa123e.camel@decadent.org.uk Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 6 +++--- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 5 +++++ 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 4c201679fc08..291f98251f7f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -50,9 +50,9 @@ static const struct rtl819x_ops rtl819xp_ops = { }; static struct pci_device_id rtl8192_pci_id_tbl[] = { - {PCI_DEVICE(0x10ec, 0x8192)}, - {PCI_DEVICE(0x07aa, 0x0044)}, - {PCI_DEVICE(0x07aa, 0x0047)}, + {RTL_PCI_DEVICE(0x10ec, 0x8192, rtl819xp_ops)}, + {RTL_PCI_DEVICE(0x07aa, 0x0044, rtl819xp_ops)}, + {RTL_PCI_DEVICE(0x07aa, 0x0047, rtl819xp_ops)}, {} }; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 7bbd884aa5f1..736f1a824cd2 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -55,6 +55,11 @@ #define IS_HARDWARE_TYPE_8192SE(_priv) \ (((struct r8192_priv *)rtllib_priv(dev))->card_8192 == NIC_8192SE) +#define RTL_PCI_DEVICE(vend, dev, cfg) \ + .vendor = (vend), .device = (dev), \ + .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, \ + .driver_data = (kernel_ulong_t)&(cfg) + #define TOTAL_CAM_ENTRY 32 #define CAM_CONTENT_COUNT 8 From a1f0beb13d9b8955e00caa48f909462fb70e6f73 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 14 Jun 2023 11:10:02 +0200 Subject: [PATCH 3499/4345] Linux 5.10.184 Link: https://lore.kernel.org/r/20230612101658.437327280@linuxfoundation.org Tested-by: Chris Paterson (CIP) Tested-by: Shuah Khan Tested-by: Jon Hunter Tested-by: Linux Kernel Functional Testing Tested-by: Sudip Mukherjee Tested-by: Allen Pais Tested-by: Salvatore Bonaccorso Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 28115681fffd..3450b061e8d6 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 183 +SUBLEVEL = 184 EXTRAVERSION = NAME = Dare mighty things From ab25d94e88082d3cd6870b8338da55da42e3cf5e Mon Sep 17 00:00:00 2001 From: Uttkarsh Aggarwal Date: Thu, 25 May 2023 14:58:54 +0530 Subject: [PATCH 3500/4345] UPSTREAM: usb: gadget: f_fs: Add unbind event before functionfs_unbind While exercising the unbind path, with the current implementation the functionfs_unbind would be calling which waits for the ffs->mutex to be available, however within the same time ffs_ep0_read is invoked & if no setup packets are pending, it will invoke function wait_event_interruptible_exclusive_locked_irq which by definition waits for the ev.count to be increased inside the same mutex for which functionfs_unbind is waiting. This creates deadlock situation because the functionfs_unbind won't get the lock until ev.count is increased which can only happen if the caller ffs_func_unbind can proceed further. Following is the illustration: CPU1 CPU2 ffs_func_unbind() ffs_ep0_read() mutex_lock(ffs->mutex) wait_event(ffs->ev.count) functionfs_unbind() mutex_lock(ffs->mutex) mutex_unlock(ffs->mutex) ffs_event_add() Fix this by moving the event unbind before functionfs_unbind to ensure the ev.count is incrased properly. Fixes: 6a19da111057 ("usb: gadget: f_fs: Prevent race during ffs_ep0_queue_wait") Cc: stable Signed-off-by: Uttkarsh Aggarwal Link: https://lore.kernel.org/r/20230525092854.7992-1-quic_uaggarwa@quicinc.com Signed-off-by: Greg Kroah-Hartman Bug: 285072336 (cherry picked from commit efb6b535207395a5c7317993602e2503ca8cb4b3) Change-Id: Iae8cbdacc64810b3a63f77d0510b61fb39d10ae8 Signed-off-by: Uttkarsh Aggarwal --- drivers/usb/gadget/function/f_fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 53154a6fd9fb..deaba9128949 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3619,6 +3619,7 @@ static void ffs_func_unbind(struct usb_configuration *c, /* Drain any pending AIO completions */ drain_workqueue(ffs->io_completion_wq); + ffs_event_add(ffs, FUNCTIONFS_UNBIND); if (!--opts->refcnt) functionfs_unbind(ffs); @@ -3643,7 +3644,6 @@ static void ffs_func_unbind(struct usb_configuration *c, func->function.ssp_descriptors = NULL; func->interfaces_nums = NULL; - ffs_event_add(ffs, FUNCTIONFS_UNBIND); } static struct usb_function *ffs_alloc(struct usb_function_instance *fi) From c93516a2d02c0a1f0466b3f512977c40c1bee4f0 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 13 Jun 2023 14:45:31 +0100 Subject: [PATCH 3501/4345] ANDROID: HID; Over-ride default maximum buffer size when using UHID Presently, when a report is processed, its proposed size, provided by the user of the API (as Report Size * Report Count) is compared against the subsystem default HID_MAX_BUFFER_SIZE (16k). However, some low-level HID drivers allocate a reduced amount of memory to their buffers (e.g. UHID only allocates UHID_DATA_MAX (4k) buffers), rending this check inadequate in some cases. In these circumstances, if the received report ends up being smaller than the proposed report size, the remainder of the buffer is zeroed. That is, the space between sizeof(csize) (size of the current report) and the rsize (size proposed i.e. Report Size * Report Count), which can be handled up to HID_MAX_BUFFER_SIZE (16k). Meaning that memset() shoots straight past the end of the buffer boundary and starts zeroing out in-use values, often resulting in calamity. This is an Android specific patch which essentially achieves the same goal as the recently reverted upstream commits b1a37ed00d790 "(HID: core: Provide new max_buffer_size attribute to over-ride the default") and 1c5d4221240a2 ("HID: uhid: Over-ride the default maximum data buffer value with our own") only it does so in an ABI friendly (albeit more hacky) way. Bug: 260007429 Signed-off-by: Lee Jones Change-Id: I1f56673bb67b63ab14b58634bfe74a04b0758e3d (cherry picked from commit 71761b36c37ae15a09fdd4d4adcc98bb939c426c) --- drivers/hid/hid-core.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 5f9ec1d1464a..ad82324e7a4b 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -32,6 +32,7 @@ #include #include #include +#include #include "hid-ids.h" @@ -258,6 +259,7 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign { struct hid_report *report; struct hid_field *field; + unsigned int max_buffer_size = HID_MAX_BUFFER_SIZE; unsigned int usages; unsigned int offset; unsigned int i; @@ -288,8 +290,11 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign offset = report->size; report->size += parser->global.report_size * parser->global.report_count; + if (parser->device->ll_driver == &uhid_hid_driver) + max_buffer_size = UHID_DATA_MAX; + /* Total size check: Allow for possible report index byte */ - if (report->size > (HID_MAX_BUFFER_SIZE - 1) << 3) { + if (report->size > (max_buffer_size - 1) << 3) { hid_err(parser->device, "report is too long\n"); return -1; } @@ -1752,6 +1757,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, struct hid_report_enum *report_enum = hid->report_enum + type; struct hid_report *report; struct hid_driver *hdrv; + int max_buffer_size = HID_MAX_BUFFER_SIZE; unsigned int a; u32 rsize, csize = size; u8 *cdata = data; @@ -1768,10 +1774,13 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, rsize = hid_compute_report_size(report); - if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) - rsize = HID_MAX_BUFFER_SIZE - 1; - else if (rsize > HID_MAX_BUFFER_SIZE) - rsize = HID_MAX_BUFFER_SIZE; + if (hid->ll_driver == &uhid_hid_driver) + max_buffer_size = UHID_DATA_MAX; + + if (report_enum->numbered && rsize >= max_buffer_size) + rsize = max_buffer_size - 1; + else if (rsize > max_buffer_size) + rsize = max_buffer_size; if (csize < rsize) { dbg_hid("report %d is too short, (%d < %d)\n", report->id, From 5bffeca4fb12b0ffe297c4754923764a97a829cc Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Sun, 16 Apr 2023 16:14:04 +0800 Subject: [PATCH 3502/4345] UPSTREAM: bluetooth: Perform careful capability checks in hci_sock_ioctl() commit 25c150ac103a4ebeed0319994c742a90634ddf18 upstream. Previously, capability was checked using capable(), which verified that the caller of the ioctl system call had the required capability. In addition, the result of the check would be stored in the HCI_SOCK_TRUSTED flag, making it persistent for the socket. However, malicious programs can abuse this approach by deliberately sharing an HCI socket with a privileged task. The HCI socket will be marked as trusted when the privileged task occasionally makes an ioctl call. This problem can be solved by using sk_capable() to check capability, which ensures that not only the current task but also the socket opener has the specified capability, thus reducing the risk of privilege escalation through the previously identified vulnerability. Bug: 286456284 Cc: stable@vger.kernel.org Fixes: f81f5b2db869 ("Bluetooth: Send control open and close messages for HCI raw sockets") Signed-off-by: Ruihan Li Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 47e6893a5b0ad14c0b1c25983a1facb1cf667b6e) Signed-off-by: Lee Jones Change-Id: I9a4b20c7b1e9b4e6bbd6371264aec039770a52ff --- net/bluetooth/hci_sock.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 7a2a7b6c10ca..5f32209f8c11 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -996,7 +996,14 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, if (hci_sock_gen_cookie(sk)) { struct sk_buff *skb; - if (capable(CAP_NET_ADMIN)) + /* Perform careful checks before setting the HCI_SOCK_TRUSTED + * flag. Make sure that not only the current task but also + * the socket opener has the required capability, since + * privileged programs can be tricked into making ioctl calls + * on HCI sockets, and the socket should not be marked as + * trusted simply because the ioctl caller is privileged. + */ + if (sk_capable(sk, CAP_NET_ADMIN)) hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); /* Send event to monitor */ From e1be34342995f2a5f7cedc1894d56efb6c40d93c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Jun 2023 11:16:56 +0000 Subject: [PATCH 3503/4345] Revert "sched/fair: Fixes for capacity inversion detection" This reverts commit 4735b6f74f25e5e869ef1e199064c4f4cd31aa68. It breaks the Android kernel abi, so revert it. If it needs to come back later, it can do so in an abi-safe way. Bug: 161946584 Cc: Qais Yousef Change-Id: I91e7a2222c06516f4df460603cc27cf7c1106823 Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 78efbb3522b8..71a493bdeacd 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8545,23 +8545,16 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) * * Thermal pressure will impact all cpus in this perf domain * equally. */ - if (sched_energy_enabled()) { + if (static_branch_unlikely(&sched_asym_cpucapacity)) { unsigned long inv_cap = capacity_orig - thermal_load_avg(rq); - struct perf_domain *pd; + struct perf_domain *pd = rcu_dereference(rq->rd->pd); - rcu_read_lock(); - - pd = rcu_dereference(rq->rd->pd); rq->cpu_capacity_inverted = 0; for (; pd; pd = pd->next) { struct cpumask *pd_span = perf_domain_span(pd); unsigned long pd_cap_orig, pd_cap; - /* We can't be inverted against our own pd */ - if (cpumask_test_cpu(cpu_of(rq), pd_span)) - continue; - cpu = cpumask_any(pd_span); pd_cap_orig = arch_scale_cpu_capacity(cpu); @@ -8586,8 +8579,6 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) break; } } - - rcu_read_unlock(); } trace_sched_cpu_capacity_tp(rq); From 652a7f2c7ec82db3fd1542d725590eed2d8c9f9c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Jun 2023 11:17:10 +0000 Subject: [PATCH 3504/4345] Revert "sched/uclamp: Fix a uninitialized variable warnings" This reverts commit 89ad8a672f57fb119e1743901ed129d4b0a2dc2b. It breaks the Android kernel abi, so revert it. If it needs to come back later, it can do so in an abi-safe way. Bug: 161946584 Cc: Qais Yousef Change-Id: I5e23eb845f1e2558992cdfe828e9ebcf32055a52 Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 71a493bdeacd..074d8f5b655b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6913,9 +6913,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu, int sy target_cap = boosted ? 0 : ULONG_MAX; for (; pd; pd = pd->next) { - unsigned long util_min = p_util_min, util_max = p_util_max; unsigned long cur_delta, spare_cap, max_spare_cap = 0; unsigned long rq_util_min, rq_util_max; + unsigned long util_min, util_max; unsigned long base_energy_pd; int max_spare_cap_cpu = -1; @@ -6924,8 +6924,6 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu, int sy base_energy += base_energy_pd; for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { - struct rq *rq = cpu_rq(cpu); - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; @@ -6941,19 +6939,24 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu, int sy * much capacity we can get out of the CPU; this is * aligned with schedutil_cpu_util(). */ - if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) { - /* - * Open code uclamp_rq_util_with() except for - * the clamp() part. Ie: apply max aggregation - * only. util_fits_cpu() logic requires to - * operate on non clamped util but must use the - * max-aggregated uclamp_{min, max}. - */ - rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN); - rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX); + if (uclamp_is_used()) { + if (uclamp_rq_is_idle(cpu_rq(cpu))) { + util_min = p_util_min; + util_max = p_util_max; + } else { + /* + * Open code uclamp_rq_util_with() except for + * the clamp() part. Ie: apply max aggregation + * only. util_fits_cpu() logic requires to + * operate on non clamped util but must use the + * max-aggregated uclamp_{min, max}. + */ + rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); + rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); - util_min = max(rq_util_min, p_util_min); - util_max = max(rq_util_max, p_util_max); + util_min = max(rq_util_min, p_util_min); + util_max = max(rq_util_max, p_util_max); + } } if (!util_fits_cpu(util, util_min, util_max, cpu)) continue; From ce3ecd63bf9d1e7a32788c7d647ea7b3ecab30f0 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Jun 2023 11:17:22 +0000 Subject: [PATCH 3505/4345] Revert "sched/fair: Consider capacity inversion in util_fits_cpu()" This reverts commit 09129798a608eee34c0e53e5cb4974023628944f. It breaks the Android kernel abi, so revert it. If it needs to come back later, it can do so in an abi-safe way. Bug: 161946584 Cc: Qais Yousef Change-Id: Ied83e33a14ff0e09f5f9f288d4e779d8175a8f0f Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 074d8f5b655b..a6f8251089f2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4128,16 +4128,12 @@ static inline int util_fits_cpu(unsigned long util, * For uclamp_max, we can tolerate a drop in performance level as the * goal is to cap the task. So it's okay if it's getting less. * - * In case of capacity inversion we should honour the inverted capacity - * for both uclamp_min and uclamp_max all the time. + * In case of capacity inversion, which is not handled yet, we should + * honour the inverted capacity for both uclamp_min and uclamp_max all + * the time. */ - capacity_orig = cpu_in_capacity_inversion(cpu); - if (capacity_orig) { - capacity_orig_thermal = capacity_orig; - } else { - capacity_orig = capacity_orig_of(cpu); - capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); - } + capacity_orig = capacity_orig_of(cpu); + capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); /* * We want to force a task to fit a cpu as implied by uclamp_max. From 571879dd5fc29c722b1fa12f03ad983c7a5b62b2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Jun 2023 11:19:02 +0000 Subject: [PATCH 3506/4345] Revert "sched/fair: Detect capacity inversion" This reverts commit 30f04dd56dfddfc58cd7fe9b45728ba9c1682a94. It breaks the Android kernel abi, so revert it. If it needs to come back later, it can do so in an abi-safe way. Bug: 161946584 Cc: Qais Yousef Signed-off-by: Greg Kroah-Hartman Change-Id: I576fa3894406ad6db3d4eafe5c08572d20c71902 --- kernel/sched/fair.c | 63 +++----------------------------------------- kernel/sched/sched.h | 19 ------------- 2 files changed, 3 insertions(+), 79 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a6f8251089f2..7d028677b970 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8513,74 +8513,17 @@ static unsigned long scale_rt_capacity(int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity_orig = arch_scale_cpu_capacity(cpu); unsigned long capacity = scale_rt_capacity(cpu); struct sched_group *sdg = sd->groups; - struct rq *rq = cpu_rq(cpu); - rq->cpu_capacity_orig = capacity_orig; + cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu); if (!capacity) capacity = 1; trace_android_rvh_update_cpu_capacity(cpu, &capacity); - rq->cpu_capacity = capacity; - - /* - * Detect if the performance domain is in capacity inversion state. - * - * Capacity inversion happens when another perf domain with equal or - * lower capacity_orig_of() ends up having higher capacity than this - * domain after subtracting thermal pressure. - * - * We only take into account thermal pressure in this detection as it's - * the only metric that actually results in *real* reduction of - * capacity due to performance points (OPPs) being dropped/become - * unreachable due to thermal throttling. - * - * We assume: - * * That all cpus in a perf domain have the same capacity_orig - * (same uArch). - * * Thermal pressure will impact all cpus in this perf domain - * equally. - */ - if (static_branch_unlikely(&sched_asym_cpucapacity)) { - unsigned long inv_cap = capacity_orig - thermal_load_avg(rq); - struct perf_domain *pd = rcu_dereference(rq->rd->pd); - - rq->cpu_capacity_inverted = 0; - - for (; pd; pd = pd->next) { - struct cpumask *pd_span = perf_domain_span(pd); - unsigned long pd_cap_orig, pd_cap; - - cpu = cpumask_any(pd_span); - pd_cap_orig = arch_scale_cpu_capacity(cpu); - - if (capacity_orig < pd_cap_orig) - continue; - - /* - * handle the case of multiple perf domains have the - * same capacity_orig but one of them is under higher - * thermal pressure. We record it as capacity - * inversion. - */ - if (capacity_orig == pd_cap_orig) { - pd_cap = pd_cap_orig - thermal_load_avg(cpu_rq(cpu)); - - if (pd_cap > inv_cap) { - rq->cpu_capacity_inverted = inv_cap; - break; - } - } else if (pd_cap_orig > inv_cap) { - rq->cpu_capacity_inverted = inv_cap; - break; - } - } - } - - trace_sched_cpu_capacity_tp(rq); + cpu_rq(cpu)->cpu_capacity = capacity; + trace_sched_cpu_capacity_tp(cpu_rq(cpu)); sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = capacity; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 6fcabd1a0994..3764b5dcfd0f 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -993,7 +993,6 @@ struct rq { unsigned long cpu_capacity; unsigned long cpu_capacity_orig; - unsigned long cpu_capacity_inverted; struct callback_head *balance_callback; @@ -2625,24 +2624,6 @@ static inline unsigned long capacity_orig_of(int cpu) { return cpu_rq(cpu)->cpu_capacity_orig; } - -/* - * Returns inverted capacity if the CPU is in capacity inversion state. - * 0 otherwise. - * - * Capacity inversion detection only considers thermal impact where actual - * performance points (OPPs) gets dropped. - * - * Capacity inversion state happens when another performance domain that has - * equal or lower capacity_orig_of() becomes effectively larger than the perf - * domain this CPU belongs to due to thermal pressure throttling it hard. - * - * See comment in update_cpu_capacity(). - */ -static inline unsigned long cpu_in_capacity_inversion(int cpu) -{ - return cpu_rq(cpu)->cpu_capacity_inverted; -} #endif /** From 40aea038ea8ce7866d8c1eb75039854a295818d7 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 19 Jun 2023 14:41:36 +0100 Subject: [PATCH 3507/4345] ANDROID: HID: Only utilise UHID provided exports if UHID is enabled Commit "ANDROID: HID; Over-ride default maximum buffer size when using UHID" provided a means for the UHID driver to offer an alternative (smaller) report buffer size when dealing with user-space. The method used was an Android-only solution designed to prevent the KMI ABI from being broken (nb: the upstream solution was cleaner, but broke the ABI). Since this solution involved consuming resources exported by a subordinate driver, that driver would have to be enabled for the export to take place. Since all of our default configs enable UHID, an issue was not detected. However, for more specific kernel configs, where HID is enabled, but UHID is not, this leads to compile-time undefined symbol errors: ld.lld: error: undefined symbol: uhid_hid_driver This patch relies on the compiler to leave out unutilised sections of the code if the associated resources are not available. Bug: 260007429 Reported-by: Paul Lawrence Reported-by: Nathan Chancellor Signed-off-by: Lee Jones Change-Id: I80b1aa7454c89d5c5e21f0268252ffb666efab97 Signed-off-by: Lee Jones --- drivers/hid/hid-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index ad82324e7a4b..b007074a30ec 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -290,7 +290,7 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign offset = report->size; report->size += parser->global.report_size * parser->global.report_count; - if (parser->device->ll_driver == &uhid_hid_driver) + if (IS_ENABLED(CONFIG_UHID) && parser->device->ll_driver == &uhid_hid_driver) max_buffer_size = UHID_DATA_MAX; /* Total size check: Allow for possible report index byte */ @@ -1774,7 +1774,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, rsize = hid_compute_report_size(report); - if (hid->ll_driver == &uhid_hid_driver) + if (IS_ENABLED(CONFIG_UHID) && hid->ll_driver == &uhid_hid_driver) max_buffer_size = UHID_DATA_MAX; if (report_enum->numbered && rsize >= max_buffer_size) From 5f17bf82b43fdeb7367656707881c9c9fdb91682 Mon Sep 17 00:00:00 2001 From: LongPing Wei Date: Mon, 19 Jun 2023 20:25:03 +0800 Subject: [PATCH 3508/4345] ANDROID: Export memcg functions to allow module to add new files Export cgroup_add_dfl_cftypes to allow vendor module to expose additional files in the memory cgroup-v2 hierarchy. Bug: 287922632 Change-Id: I103b983fbb46ff7a45cfc57f5657142a1bbd3d68 Signed-off-by: LongPing Wei --- kernel/cgroup/cgroup.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index f08f898ea929..1b7e1da46dfa 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4219,6 +4219,7 @@ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) cft->flags |= __CFTYPE_ONLY_ON_DFL; return cgroup_add_cftypes(ss, cfts); } +EXPORT_SYMBOL_GPL(cgroup_add_dfl_cftypes); /** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies From b3af11bf9080375dd8dd34cbdcff84f5b7f5686a Mon Sep 17 00:00:00 2001 From: LongPing Wei Date: Mon, 19 Jun 2023 21:46:19 +0800 Subject: [PATCH 3509/4345] ANDROID: ABI: Update oplus symbol list 1 function symbol(s) added 'int cgroup_add_dfl_cftypes(struct cgroup_subsys *, struct cftype *)' Bug: 287922632 Change-Id: I7f6d9d7310c59601079566951303208d2b9dcfc4 Signed-off-by: LongPing Wei --- android/abi_gki_aarch64.xml | 209 +++++++++++++++++++++------------- android/abi_gki_aarch64_oplus | 1 + 2 files changed, 128 insertions(+), 82 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index ef03b0c13e9b..0bab4531f386 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -1182,6 +1182,7 @@ + @@ -44629,7 +44630,23 @@ - + + + + + + + + + + + + + + + + + @@ -48969,6 +48986,7 @@ + @@ -53926,6 +53944,13 @@ + + + + + + + @@ -66586,6 +66611,13 @@ + + + + + + + @@ -91377,6 +91409,7 @@ + @@ -103144,6 +103177,12 @@ + + + + + + @@ -111390,6 +111429,7 @@ + @@ -117232,16 +117272,16 @@ - - - - + + + + - - - - + + + + @@ -123717,41 +123757,41 @@ - - - - - + + + + + - - - + + + - - - - + + + + - - - + + + - - - + + + - - + + - - - + + + @@ -123897,9 +123937,14 @@ - - - + + + + + + + + @@ -125342,14 +125387,14 @@ - - - + + + - - - + + + @@ -133020,71 +133065,71 @@ - - + + - + - - - + + + - - + + - - + + - - - + + + - - + + - - - - - - + + + + + + - - + + - - - - + + + + - - - - - - + + + + + + - - + + - - - - - - + + + + + + diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index bd21cf7d3005..61477d74b5cb 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -143,6 +143,7 @@ cdev_device_del cdev_init __cfi_slowpath + cgroup_add_dfl_cftypes cgroup_add_legacy_cftypes cgroup_path_ns cgroup_taskset_first From c2def5578b440f6ac45fcffcf766d968d7c3bea5 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 15 Dec 2020 20:44:00 -0800 Subject: [PATCH 3510/4345] lib: cleanup kstrto*() usage [ Upstream commit 506dfc9906e5cbf453bbcd5eb627689435583558 ] Use proper conversion functions. kstrto*() variants exist for all standard types. Link: https://lkml.kernel.org/r/20201122123410.GB92364@localhost.localdomain Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Stable-dep-of: 4acfe3dfde68 ("test_firmware: prevent race conditions by a correct implementation of locking") Signed-off-by: Sasha Levin --- lib/test_firmware.c | 9 +++------ lib/test_kmod.c | 26 ++++++++++---------------- 2 files changed, 13 insertions(+), 22 deletions(-) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 581ee3fcdd5c..3edbc17d92db 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -371,18 +371,15 @@ static ssize_t test_dev_config_show_int(char *buf, int val) static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { + u8 val; int ret; - long new; - ret = kstrtol(buf, 10, &new); + ret = kstrtou8(buf, 10, &val); if (ret) return ret; - if (new > U8_MAX) - return -EINVAL; - mutex_lock(&test_fw_mutex); - *(u8 *)cfg = new; + *(u8 *)cfg = val; mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ diff --git a/lib/test_kmod.c b/lib/test_kmod.c index c637f6b5053a..c282728de3af 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -877,20 +877,17 @@ static int test_dev_config_update_uint_sync(struct kmod_test_device *test_dev, int (*test_sync)(struct kmod_test_device *test_dev)) { int ret; - unsigned long new; + unsigned int val; unsigned int old_val; - ret = kstrtoul(buf, 10, &new); + ret = kstrtouint(buf, 10, &val); if (ret) return ret; - if (new > UINT_MAX) - return -EINVAL; - mutex_lock(&test_dev->config_mutex); old_val = *config; - *(unsigned int *)config = new; + *(unsigned int *)config = val; ret = test_sync(test_dev); if (ret) { @@ -914,18 +911,18 @@ static int test_dev_config_update_uint_range(struct kmod_test_device *test_dev, unsigned int min, unsigned int max) { + unsigned int val; int ret; - unsigned long new; - ret = kstrtoul(buf, 10, &new); + ret = kstrtouint(buf, 10, &val); if (ret) return ret; - if (new < min || new > max) + if (val < min || val > max) return -EINVAL; mutex_lock(&test_dev->config_mutex); - *config = new; + *config = val; mutex_unlock(&test_dev->config_mutex); /* Always return full write size even if we didn't consume all */ @@ -936,18 +933,15 @@ static int test_dev_config_update_int(struct kmod_test_device *test_dev, const char *buf, size_t size, int *config) { + int val; int ret; - long new; - ret = kstrtol(buf, 10, &new); + ret = kstrtoint(buf, 10, &val); if (ret) return ret; - if (new < INT_MIN || new > INT_MAX) - return -EINVAL; - mutex_lock(&test_dev->config_mutex); - *config = new; + *config = val; mutex_unlock(&test_dev->config_mutex); /* Always return full write size even if we didn't consume all */ return size; From 6e2e551e39fddda9a6c3385115368578c01d570e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jun 2021 18:56:10 -0700 Subject: [PATCH 3511/4345] kernel.h: split out kstrtox() and simple_strtox() to a separate header [ Upstream commit 4c52729377eab025b238caeed48994a39c3b73f2 ] kernel.h is being used as a dump for all kinds of stuff for a long time. Here is the attempt to start cleaning it up by splitting out kstrtox() and simple_strtox() helpers. At the same time convert users in header and lib folders to use new header. Though for time being include new header back to kernel.h to avoid twisted indirected includes for existing users. [andy.shevchenko@gmail.com: fix documentation references] Link: https://lkml.kernel.org/r/20210615220003.377901-1-andy.shevchenko@gmail.com Link: https://lkml.kernel.org/r/20210611185815.44103-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Acked-by: Jonathan Cameron Cc: Francis Laniel Cc: Randy Dunlap Cc: Kars Mulder Cc: Trond Myklebust Cc: Anna Schumaker Cc: "J. Bruce Fields" Cc: Chuck Lever Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Stable-dep-of: 4acfe3dfde68 ("test_firmware: prevent race conditions by a correct implementation of locking") Signed-off-by: Sasha Levin --- Documentation/core-api/kernel-api.rst | 7 +- include/linux/kernel.h | 143 +----------------------- include/linux/kstrtox.h | 155 ++++++++++++++++++++++++++ include/linux/string.h | 7 -- include/linux/sunrpc/cache.h | 1 + lib/kstrtox.c | 5 +- lib/parser.c | 1 + 7 files changed, 163 insertions(+), 156 deletions(-) create mode 100644 include/linux/kstrtox.h diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 741aa37dc181..2a7444e3a4c2 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -24,11 +24,8 @@ String Conversions .. kernel-doc:: lib/vsprintf.c :export: -.. kernel-doc:: include/linux/kernel.h - :functions: kstrtol - -.. kernel-doc:: include/linux/kernel.h - :functions: kstrtoul +.. kernel-doc:: include/linux/kstrtox.h + :functions: kstrtol kstrtoul .. kernel-doc:: lib/kstrtox.c :export: diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 66948e1bf4fa..cdd6ed5bbcf2 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -329,148 +330,6 @@ extern bool oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; -/* Internal, do not use. */ -int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); -int __must_check _kstrtol(const char *s, unsigned int base, long *res); - -int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); -int __must_check kstrtoll(const char *s, unsigned int base, long long *res); - -/** - * kstrtoul - convert a string to an unsigned long - * @s: The start of the string. The string must be null-terminated, and may also - * include a single newline before its terminating null. The first character - * may also be a plus sign, but not a minus sign. - * @base: The number base to use. The maximum supported base is 16. If base is - * given as 0, then the base of the string is automatically detected with the - * conventional semantics - If it begins with 0x the number will be parsed as a - * hexadecimal (case insensitive), if it otherwise begins with 0, it will be - * parsed as an octal number. Otherwise it will be parsed as a decimal. - * @res: Where to write the result of the conversion on success. - * - * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Preferred over simple_strtoul(). Return code must be checked. -*/ -static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) -{ - /* - * We want to shortcut function call, but - * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0. - */ - if (sizeof(unsigned long) == sizeof(unsigned long long) && - __alignof__(unsigned long) == __alignof__(unsigned long long)) - return kstrtoull(s, base, (unsigned long long *)res); - else - return _kstrtoul(s, base, res); -} - -/** - * kstrtol - convert a string to a long - * @s: The start of the string. The string must be null-terminated, and may also - * include a single newline before its terminating null. The first character - * may also be a plus sign or a minus sign. - * @base: The number base to use. The maximum supported base is 16. If base is - * given as 0, then the base of the string is automatically detected with the - * conventional semantics - If it begins with 0x the number will be parsed as a - * hexadecimal (case insensitive), if it otherwise begins with 0, it will be - * parsed as an octal number. Otherwise it will be parsed as a decimal. - * @res: Where to write the result of the conversion on success. - * - * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Preferred over simple_strtol(). Return code must be checked. - */ -static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) -{ - /* - * We want to shortcut function call, but - * __builtin_types_compatible_p(long, long long) = 0. - */ - if (sizeof(long) == sizeof(long long) && - __alignof__(long) == __alignof__(long long)) - return kstrtoll(s, base, (long long *)res); - else - return _kstrtol(s, base, res); -} - -int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res); -int __must_check kstrtoint(const char *s, unsigned int base, int *res); - -static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res) -{ - return kstrtoull(s, base, res); -} - -static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res) -{ - return kstrtoll(s, base, res); -} - -static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res) -{ - return kstrtouint(s, base, res); -} - -static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res) -{ - return kstrtoint(s, base, res); -} - -int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); -int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); -int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); -int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); -int __must_check kstrtobool(const char *s, bool *res); - -int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); -int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); -int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res); -int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res); -int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res); -int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res); -int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res); -int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); -int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); -int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); -int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); - -static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) -{ - return kstrtoull_from_user(s, count, base, res); -} - -static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res) -{ - return kstrtoll_from_user(s, count, base, res); -} - -static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res) -{ - return kstrtouint_from_user(s, count, base, res); -} - -static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res) -{ - return kstrtoint_from_user(s, count, base, res); -} - -/* - * Use kstrto instead. - * - * NOTE: simple_strto does not check for the range overflow and, - * depending on the input, may give interesting results. - * - * Use these functions if and only if you cannot use kstrto, because - * the conversion ends on the first non-digit character, which may be far - * beyond the supported range. It might be useful to parse the strings like - * 10x50 or 12:21 without altering original string or temporary buffer in use. - * Keep in mind above caveat. - */ - -extern unsigned long simple_strtoul(const char *,char **,unsigned int); -extern long simple_strtol(const char *,char **,unsigned int); -extern unsigned long long simple_strtoull(const char *,char **,unsigned int); -extern long long simple_strtoll(const char *,char **,unsigned int); - extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); diff --git a/include/linux/kstrtox.h b/include/linux/kstrtox.h new file mode 100644 index 000000000000..529974e22ea7 --- /dev/null +++ b/include/linux/kstrtox.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KSTRTOX_H +#define _LINUX_KSTRTOX_H + +#include +#include + +/* Internal, do not use. */ +int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); +int __must_check _kstrtol(const char *s, unsigned int base, long *res); + +int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); +int __must_check kstrtoll(const char *s, unsigned int base, long long *res); + +/** + * kstrtoul - convert a string to an unsigned long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign, but not a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Preferred over simple_strtoul(). Return code must be checked. +*/ +static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) +{ + /* + * We want to shortcut function call, but + * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0. + */ + if (sizeof(unsigned long) == sizeof(unsigned long long) && + __alignof__(unsigned long) == __alignof__(unsigned long long)) + return kstrtoull(s, base, (unsigned long long *)res); + else + return _kstrtoul(s, base, res); +} + +/** + * kstrtol - convert a string to a long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign or a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Preferred over simple_strtol(). Return code must be checked. + */ +static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) +{ + /* + * We want to shortcut function call, but + * __builtin_types_compatible_p(long, long long) = 0. + */ + if (sizeof(long) == sizeof(long long) && + __alignof__(long) == __alignof__(long long)) + return kstrtoll(s, base, (long long *)res); + else + return _kstrtol(s, base, res); +} + +int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res); +int __must_check kstrtoint(const char *s, unsigned int base, int *res); + +static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res) +{ + return kstrtoull(s, base, res); +} + +static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res) +{ + return kstrtoll(s, base, res); +} + +static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res) +{ + return kstrtouint(s, base, res); +} + +static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res) +{ + return kstrtoint(s, base, res); +} + +int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); +int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); +int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); +int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); +int __must_check kstrtobool(const char *s, bool *res); + +int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); +int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); +int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res); +int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res); +int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res); +int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res); +int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res); +int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); +int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); +int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); +int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); + +static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) +{ + return kstrtoull_from_user(s, count, base, res); +} + +static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res) +{ + return kstrtoll_from_user(s, count, base, res); +} + +static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res) +{ + return kstrtouint_from_user(s, count, base, res); +} + +static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res) +{ + return kstrtoint_from_user(s, count, base, res); +} + +/* + * Use kstrto instead. + * + * NOTE: simple_strto does not check for the range overflow and, + * depending on the input, may give interesting results. + * + * Use these functions if and only if you cannot use kstrto, because + * the conversion ends on the first non-digit character, which may be far + * beyond the supported range. It might be useful to parse the strings like + * 10x50 or 12:21 without altering original string or temporary buffer in use. + * Keep in mind above caveat. + */ + +extern unsigned long simple_strtoul(const char *,char **,unsigned int); +extern long simple_strtol(const char *,char **,unsigned int); +extern unsigned long long simple_strtoull(const char *,char **,unsigned int); +extern long long simple_strtoll(const char *,char **,unsigned int); + +static inline int strtobool(const char *s, bool *res) +{ + return kstrtobool(s, res); +} + +#endif /* _LINUX_KSTRTOX_H */ diff --git a/include/linux/string.h b/include/linux/string.h index b1f3894a0a3e..0cef345a6e87 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -2,7 +2,6 @@ #ifndef _LINUX_STRING_H_ #define _LINUX_STRING_H_ - #include /* for inline */ #include /* for size_t */ #include /* for NULL */ @@ -183,12 +182,6 @@ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); -extern int kstrtobool(const char *s, bool *res); -static inline int strtobool(const char *s, bool *res) -{ - return kstrtobool(s, res); -} - int match_string(const char * const *array, size_t n, const char *string); int __sysfs_match_string(const char * const *array, size_t n, const char *s); diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index d0965e2997b0..b134b2b3371c 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -14,6 +14,7 @@ #include #include #include +#include #include /* diff --git a/lib/kstrtox.c b/lib/kstrtox.c index 8504526541c1..53fa01fb7509 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -14,11 +14,12 @@ */ #include #include -#include -#include #include +#include +#include #include #include + #include "kstrtox.h" const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) diff --git a/lib/parser.c b/lib/parser.c index f5b3e5d7a7f9..5c37d6345cb0 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include From 682ca602515ddec705451a738f8e7310fed3dc77 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 14 Jan 2023 10:22:03 +0100 Subject: [PATCH 3512/4345] test_firmware: Use kstrtobool() instead of strtobool() [ Upstream commit f7d85515bd21902b218370a1a6301f76e4e636ff ] strtobool() is the same as kstrtobool(). However, the latter is more used within the kernel. In order to remove strtobool() and slightly simplify kstrtox.h, switch to the other function name. While at it, include the corresponding header file () Signed-off-by: Christophe JAILLET Acked-by: Luis Chamberlain Link: https://lore.kernel.org/r/34f04735d20e0138695dd4070651bd860a36b81c.1673688120.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman Stable-dep-of: 4acfe3dfde68 ("test_firmware: prevent race conditions by a correct implementation of locking") Signed-off-by: Sasha Levin --- lib/test_firmware.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 3edbc17d92db..b99cf0a50a69 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -326,7 +327,7 @@ static int test_dev_config_update_bool(const char *buf, size_t size, int ret; mutex_lock(&test_fw_mutex); - if (strtobool(buf, cfg) < 0) + if (kstrtobool(buf, cfg) < 0) ret = -EINVAL; else ret = size; From af36f35074b10dda0516cfc63d209accd4ef4d17 Mon Sep 17 00:00:00 2001 From: Mirsad Goran Todorovac Date: Tue, 9 May 2023 10:47:45 +0200 Subject: [PATCH 3513/4345] test_firmware: prevent race conditions by a correct implementation of locking [ Upstream commit 4acfe3dfde685a5a9eaec5555351918e2d7266a1 ] Dan Carpenter spotted a race condition in a couple of situations like these in the test_firmware driver: static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { u8 val; int ret; ret = kstrtou8(buf, 10, &val); if (ret) return ret; mutex_lock(&test_fw_mutex); *(u8 *)cfg = val; mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; } static ssize_t config_num_requests_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int rc; mutex_lock(&test_fw_mutex); if (test_fw_config->reqs) { pr_err("Must call release_all_firmware prior to changing config\n"); rc = -EINVAL; mutex_unlock(&test_fw_mutex); goto out; } mutex_unlock(&test_fw_mutex); rc = test_dev_config_update_u8(buf, count, &test_fw_config->num_requests); out: return rc; } static ssize_t config_read_fw_idx_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return test_dev_config_update_u8(buf, count, &test_fw_config->read_fw_idx); } The function test_dev_config_update_u8() is called from both the locked and the unlocked context, function config_num_requests_store() and config_read_fw_idx_store() which can both be called asynchronously as they are driver's methods, while test_dev_config_update_u8() and siblings change their argument pointed to by u8 *cfg or similar pointer. To avoid deadlock on test_fw_mutex, the lock is dropped before calling test_dev_config_update_u8() and re-acquired within test_dev_config_update_u8() itself, but alas this creates a race condition. Having two locks wouldn't assure a race-proof mutual exclusion. This situation is best avoided by the introduction of a new, unlocked function __test_dev_config_update_u8() which can be called from the locked context and reducing test_dev_config_update_u8() to: static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { int ret; mutex_lock(&test_fw_mutex); ret = __test_dev_config_update_u8(buf, size, cfg); mutex_unlock(&test_fw_mutex); return ret; } doing the locking and calling the unlocked primitive, which enables both locked and unlocked versions without duplication of code. The similar approach was applied to all functions called from the locked and the unlocked context, which safely mitigates both deadlocks and race conditions in the driver. __test_dev_config_update_bool(), __test_dev_config_update_u8() and __test_dev_config_update_size_t() unlocked versions of the functions were introduced to be called from the locked contexts as a workaround without releasing the main driver's lock and thereof causing a race condition. The test_dev_config_update_bool(), test_dev_config_update_u8() and test_dev_config_update_size_t() locked versions of the functions are being called from driver methods without the unnecessary multiplying of the locking and unlocking code for each method, and complicating the code with saving of the return value across lock. Fixes: 7feebfa487b92 ("test_firmware: add support for request_firmware_into_buf") Cc: Luis Chamberlain Cc: Greg Kroah-Hartman Cc: Russ Weight Cc: Takashi Iwai Cc: Tianfei Zhang Cc: Shuah Khan Cc: Colin Ian King Cc: Randy Dunlap Cc: linux-kselftest@vger.kernel.org Cc: stable@vger.kernel.org # v5.4 Suggested-by: Dan Carpenter Signed-off-by: Mirsad Goran Todorovac Link: https://lore.kernel.org/r/20230509084746.48259-1-mirsad.todorovac@alu.unizg.hr Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- lib/test_firmware.c | 56 ++++++++++++++++++++++++++++++--------------- 1 file changed, 37 insertions(+), 19 deletions(-) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index b99cf0a50a69..4884057eb53f 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -321,16 +321,26 @@ static ssize_t config_test_show_str(char *dst, return len; } +static inline int __test_dev_config_update_bool(const char *buf, size_t size, + bool *cfg) +{ + int ret; + + if (kstrtobool(buf, cfg) < 0) + ret = -EINVAL; + else + ret = size; + + return ret; +} + static int test_dev_config_update_bool(const char *buf, size_t size, bool *cfg) { int ret; mutex_lock(&test_fw_mutex); - if (kstrtobool(buf, cfg) < 0) - ret = -EINVAL; - else - ret = size; + ret = __test_dev_config_update_bool(buf, size, cfg); mutex_unlock(&test_fw_mutex); return ret; @@ -341,7 +351,8 @@ static ssize_t test_dev_config_show_bool(char *buf, bool val) return snprintf(buf, PAGE_SIZE, "%d\n", val); } -static int test_dev_config_update_size_t(const char *buf, +static int __test_dev_config_update_size_t( + const char *buf, size_t size, size_t *cfg) { @@ -352,9 +363,7 @@ static int test_dev_config_update_size_t(const char *buf, if (ret) return ret; - mutex_lock(&test_fw_mutex); *(size_t *)cfg = new; - mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; @@ -370,7 +379,7 @@ static ssize_t test_dev_config_show_int(char *buf, int val) return snprintf(buf, PAGE_SIZE, "%d\n", val); } -static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +static int __test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { u8 val; int ret; @@ -379,14 +388,23 @@ static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) if (ret) return ret; - mutex_lock(&test_fw_mutex); *(u8 *)cfg = val; - mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; } +static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +{ + int ret; + + mutex_lock(&test_fw_mutex); + ret = __test_dev_config_update_u8(buf, size, cfg); + mutex_unlock(&test_fw_mutex); + + return ret; +} + static ssize_t test_dev_config_show_u8(char *buf, u8 val) { return snprintf(buf, PAGE_SIZE, "%u\n", val); @@ -413,10 +431,10 @@ static ssize_t config_num_requests_store(struct device *dev, mutex_unlock(&test_fw_mutex); goto out; } - mutex_unlock(&test_fw_mutex); - rc = test_dev_config_update_u8(buf, count, - &test_fw_config->num_requests); + rc = __test_dev_config_update_u8(buf, count, + &test_fw_config->num_requests); + mutex_unlock(&test_fw_mutex); out: return rc; @@ -460,10 +478,10 @@ static ssize_t config_buf_size_store(struct device *dev, mutex_unlock(&test_fw_mutex); goto out; } - mutex_unlock(&test_fw_mutex); - rc = test_dev_config_update_size_t(buf, count, - &test_fw_config->buf_size); + rc = __test_dev_config_update_size_t(buf, count, + &test_fw_config->buf_size); + mutex_unlock(&test_fw_mutex); out: return rc; @@ -490,10 +508,10 @@ static ssize_t config_file_offset_store(struct device *dev, mutex_unlock(&test_fw_mutex); goto out; } - mutex_unlock(&test_fw_mutex); - rc = test_dev_config_update_size_t(buf, count, - &test_fw_config->file_offset); + rc = __test_dev_config_update_size_t(buf, count, + &test_fw_config->file_offset); + mutex_unlock(&test_fw_mutex); out: return rc; From 539c387f0bb9c4a13ccd50133103a7b38db33b2b Mon Sep 17 00:00:00 2001 From: Mirsad Goran Todorovac Date: Tue, 9 May 2023 10:47:47 +0200 Subject: [PATCH 3514/4345] test_firmware: fix a memory leak with reqs buffer [ Upstream commit be37bed754ed90b2655382f93f9724b3c1aae847 ] Dan Carpenter spotted that test_fw_config->reqs will be leaked if trigger_batched_requests_store() is called two or more times. The same appears with trigger_batched_requests_async_store(). This bug wasn't trigger by the tests, but observed by Dan's visual inspection of the code. The recommended workaround was to return -EBUSY if test_fw_config->reqs is already allocated. Fixes: 7feebfa487b92 ("test_firmware: add support for request_firmware_into_buf") Cc: Luis Chamberlain Cc: Greg Kroah-Hartman Cc: Russ Weight Cc: Tianfei Zhang Cc: Shuah Khan Cc: Colin Ian King Cc: Randy Dunlap Cc: linux-kselftest@vger.kernel.org Cc: stable@vger.kernel.org # v5.4 Suggested-by: Dan Carpenter Suggested-by: Takashi Iwai Signed-off-by: Mirsad Goran Todorovac Reviewed-by: Dan Carpenter Acked-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230509084746.48259-2-mirsad.todorovac@alu.unizg.hr Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- lib/test_firmware.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 4884057eb53f..ed0455a9ded8 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -863,6 +863,11 @@ static ssize_t trigger_batched_requests_store(struct device *dev, mutex_lock(&test_fw_mutex); + if (test_fw_config->reqs) { + rc = -EBUSY; + goto out_bail; + } + test_fw_config->reqs = vzalloc(array3_size(sizeof(struct test_batched_req), test_fw_config->num_requests, 2)); @@ -962,6 +967,11 @@ ssize_t trigger_batched_requests_async_store(struct device *dev, mutex_lock(&test_fw_mutex); + if (test_fw_config->reqs) { + rc = -EBUSY; + goto out_bail; + } + test_fw_config->reqs = vzalloc(array3_size(sizeof(struct test_batched_req), test_fw_config->num_requests, 2)); From 9e9e150fa8a61cf1780aa680fcdffe24229e0c80 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 18:07:29 +0200 Subject: [PATCH 3515/4345] power: supply: ab8500: Fix external_power_changed race [ Upstream commit a5299ce4e96f3e8930e9c051b28d8093ada87b08 ] ab8500_btemp_external_power_changed() dereferences di->btemp_psy, which gets sets in ab8500_btemp_probe() like this: di->btemp_psy = devm_power_supply_register(dev, &ab8500_btemp_desc, &psy_cfg); As soon as devm_power_supply_register() has called device_add() the external_power_changed callback can get called. So there is a window where ab8500_btemp_external_power_changed() may get called while di->btemp_psy has not been set yet leading to a NULL pointer dereference. Fixing this is easy. The external_power_changed callback gets passed the power_supply which will eventually get stored in di->btemp_psy, so ab8500_btemp_external_power_changed() can simply directly use the passed in psy argument which is always valid. And the same applies to ab8500_fg_external_power_changed(). Signed-off-by: Hans de Goede Reviewed-by: Linus Walleij Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/ab8500_btemp.c | 6 ++---- drivers/power/supply/ab8500_fg.c | 6 ++---- 2 files changed, 4 insertions(+), 8 deletions(-) diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 4417d64c31f9..5a1adceb6974 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -921,10 +921,8 @@ static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data) */ static void ab8500_btemp_external_power_changed(struct power_supply *psy) { - struct ab8500_btemp *di = power_supply_get_drvdata(psy); - - class_for_each_device(power_supply_class, NULL, - di->btemp_psy, ab8500_btemp_get_ext_psy_data); + class_for_each_device(power_supply_class, NULL, psy, + ab8500_btemp_get_ext_psy_data); } /* ab8500 btemp driver interrupts and their respective isr */ diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index a6b4a94c2766..a88590563647 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -2380,10 +2380,8 @@ out: */ static void ab8500_fg_external_power_changed(struct power_supply *psy) { - struct ab8500_fg *di = power_supply_get_drvdata(psy); - - class_for_each_device(power_supply_class, NULL, - di->fg_psy, ab8500_fg_get_ext_psy_data); + class_for_each_device(power_supply_class, NULL, psy, + ab8500_fg_get_ext_psy_data); } /** From ce2b5f24caadb14ddbc34dd5ad30476e875a89cf Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 18:07:32 +0200 Subject: [PATCH 3516/4345] power: supply: sc27xx: Fix external_power_changed race [ Upstream commit 4d5c129d6c8993fe96e9ae712141eedcb9ca68c2 ] sc27xx_fgu_external_power_changed() dereferences data->battery, which gets sets in ab8500_btemp_probe() like this: data->battery = devm_power_supply_register(dev, &sc27xx_fgu_desc, &fgu_cfg); As soon as devm_power_supply_register() has called device_add() the external_power_changed callback can get called. So there is a window where sc27xx_fgu_external_power_changed() may get called while data->battery has not been set yet leading to a NULL pointer dereference. Fixing this is easy. The external_power_changed callback gets passed the power_supply which will eventually get stored in data->battery, so sc27xx_fgu_external_power_changed() can simply directly use the passed in psy argument which is always valid. After this change sc27xx_fgu_external_power_changed() is reduced to just "power_supply_changed(psy);" and it has the same prototype. While at it simply replace it with making the external_power_changed callback directly point to power_supply_changed. Cc: Orson Zhai Cc: Chunyan Zhang Signed-off-by: Hans de Goede Reviewed-by: Baolin Wang Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/sc27xx_fuel_gauge.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/power/supply/sc27xx_fuel_gauge.c b/drivers/power/supply/sc27xx_fuel_gauge.c index 1ae8374e1ceb..3bf4b263950d 100644 --- a/drivers/power/supply/sc27xx_fuel_gauge.c +++ b/drivers/power/supply/sc27xx_fuel_gauge.c @@ -733,13 +733,6 @@ static int sc27xx_fgu_set_property(struct power_supply *psy, return ret; } -static void sc27xx_fgu_external_power_changed(struct power_supply *psy) -{ - struct sc27xx_fgu_data *data = power_supply_get_drvdata(psy); - - power_supply_changed(data->battery); -} - static int sc27xx_fgu_property_is_writeable(struct power_supply *psy, enum power_supply_property psp) { @@ -774,7 +767,7 @@ static const struct power_supply_desc sc27xx_fgu_desc = { .num_properties = ARRAY_SIZE(sc27xx_fgu_props), .get_property = sc27xx_fgu_get_property, .set_property = sc27xx_fgu_set_property, - .external_power_changed = sc27xx_fgu_external_power_changed, + .external_power_changed = power_supply_changed, .property_is_writeable = sc27xx_fgu_property_is_writeable, .no_thermal = true, }; From b2856c3cd3b233df5615dab731a87d63ae5e4072 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:39 +0200 Subject: [PATCH 3517/4345] power: supply: bq27xxx: Use mod_delayed_work() instead of cancel() + schedule() [ Upstream commit 59dddea9879713423c7b2ade43c423bb71e0d216 ] Use mod_delayed_work() instead of separate cancel_delayed_work_sync() + schedule_delayed_work() calls. Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/bq27xxx_battery.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 235647b21af7..0673e0fe0ffb 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1018,10 +1018,8 @@ static int poll_interval_param_set(const char *val, const struct kernel_param *k return ret; mutex_lock(&bq27xxx_list_lock); - list_for_each_entry(di, &bq27xxx_battery_devices, list) { - cancel_delayed_work_sync(&di->work); - schedule_delayed_work(&di->work, 0); - } + list_for_each_entry(di, &bq27xxx_battery_devices, list) + mod_delayed_work(system_wq, &di->work, 0); mutex_unlock(&bq27xxx_list_lock); return ret; From 39eb9eb9ea4339e6e31cc95c09e89151868a76f5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 23 Apr 2023 17:08:37 +0200 Subject: [PATCH 3518/4345] ARM: dts: vexpress: add missing cache properties [ Upstream commit 328acc5657c6197753238d7ce0a6924ead829347 ] As all level 2 and level 3 caches are unified, add required cache-unified property to fix warnings like: vexpress-v2p-ca5s.dtb: cache-controller@2c0f0000: 'cache-unified' is a required property Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230423150837.118466-1-krzysztof.kozlowski@linaro.org Signed-off-by: Sudeep Holla Signed-off-by: Sasha Levin --- arch/arm/boot/dts/vexpress-v2p-ca5s.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts index 7aa64ae25779..6fc48016fe8e 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts @@ -132,6 +132,7 @@ reg = <0x2c0f0000 0x1000>; interrupts = <0 84 4>; cache-level = <2>; + cache-unified; }; pmu { From 6be7a4bef9dc623af2dda541cf69dfed35fc18db Mon Sep 17 00:00:00 2001 From: Milo Spadacini Date: Mon, 8 May 2023 15:18:48 +0200 Subject: [PATCH 3519/4345] tools: gpio: fix debounce_period_us output of lsgpio [ Upstream commit eb4b8eca1bad98f4b8574558a74f041f9acb5a54 ] Fix incorrect output that could occur when more attributes are used and GPIO_V2_LINE_ATTR_ID_DEBOUNCE is not the first one. Signed-off-by: Milo Spadacini Reviewed-by: Linus Walleij Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- tools/gpio/lsgpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c index 5a05a454d0c9..85a2aa292f5d 100644 --- a/tools/gpio/lsgpio.c +++ b/tools/gpio/lsgpio.c @@ -90,7 +90,7 @@ static void print_attributes(struct gpio_v2_line_info *info) for (i = 0; i < info->num_attrs; i++) { if (info->attrs[i].id == GPIO_V2_LINE_ATTR_ID_DEBOUNCE) fprintf(stdout, ", debounce_period=%dusec", - info->attrs[0].debounce_period_us); + info->attrs[i].debounce_period_us); } } From 88d1c1365ff65462647ce39d7ad61d5ff14eb0a2 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 5 Mar 2023 21:52:26 +0100 Subject: [PATCH 3520/4345] power: supply: Ratelimit no data debug output [ Upstream commit 155c45a25679f571c2ae57d10db843a9dfc63430 ] Reduce the amount of output this dev_dbg() statement emits into logs, otherwise if system software polls the sysfs entry for data and keeps getting -ENODATA, it could end up filling the logs up. This does in fact make systemd journald choke, since during boot the sysfs power supply entries are polled and if journald starts at the same time, the journal is just being repeatedly filled up, and the system stops on trying to start journald without booting any further. Signed-off-by: Marek Vasut Reviewed-by: Hans de Goede Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/power_supply_sysfs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index a616b9d8f43c..2b1df9c33969 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -276,7 +276,8 @@ static ssize_t power_supply_show_property(struct device *dev, if (ret < 0) { if (ret == -ENODATA) - dev_dbg(dev, "driver has no data for `%s' property\n", + dev_dbg_ratelimited(dev, + "driver has no data for `%s' property\n", attr->attr.name); else if (ret != -ENODEV && ret != -EAGAIN) dev_err_ratelimited(dev, From 37bcc48e7dd15a8afcc8f66e16f283303a7f6d38 Mon Sep 17 00:00:00 2001 From: Alexandru Sorodoc Date: Fri, 12 May 2023 13:15:17 +0300 Subject: [PATCH 3521/4345] platform/x86: asus-wmi: Ignore WMI events with codes 0x7B, 0xC0 [ Upstream commit 362c1f2ec82cb65940e1c73e15a395a7a891fc6f ] On ASUS GU604V the key 0x7B is issued when the charger is connected or disconnected, and key 0xC0 is issued when an external display is connected or disconnected. This commit maps them to KE_IGNORE to slience kernel messages about unknown keys, such as: kernel: asus_wmi: Unknown key code 0x7b Signed-off-by: Alexandru Sorodoc Link: https://lore.kernel.org/r/20230512101517.47416-1-ealex95@gmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/asus-nb-wmi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 74637bd0433e..b4a5cbdae904 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -507,6 +507,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x71, { KEY_F13 } }, /* General-purpose button */ { KE_IGNORE, 0x79, }, /* Charger type dectection notification */ { KE_KEY, 0x7a, { KEY_ALS_TOGGLE } }, /* Ambient Light Sensor Toggle */ + { KE_IGNORE, 0x7B, }, /* Charger connect/disconnect notification */ { KE_KEY, 0x7c, { KEY_MICMUTE } }, { KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */ { KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */ @@ -532,6 +533,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0xA6, { KEY_SWITCHVIDEOMODE } }, /* SDSP CRT + TV + HDMI */ { KE_KEY, 0xA7, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + CRT + TV + HDMI */ { KE_KEY, 0xB5, { KEY_CALC } }, + { KE_IGNORE, 0xC0, }, /* External display connect/disconnect notification */ { KE_KEY, 0xC4, { KEY_KBDILLUMUP } }, { KE_KEY, 0xC5, { KEY_KBDILLUMDOWN } }, { KE_IGNORE, 0xC6, }, /* Ambient Light Sensor notification */ From dbf610997242ec62facd04a11c5258ba84607ea1 Mon Sep 17 00:00:00 2001 From: Osama Muhammad Date: Mon, 15 May 2023 22:29:38 +0500 Subject: [PATCH 3522/4345] regulator: Fix error checking for debugfs_create_dir [ Upstream commit 2bf1c45be3b8f3a3f898d0756c1282f09719debd ] This patch fixes the error checking in core.c in debugfs_create_dir. The correct way to check if an error occurred is 'IS_ERR' inline function. Signed-off-by: Osama Muhammad --- drivers/regulator/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 47a04c5f7a9b..f5ab74683b58 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5032,7 +5032,7 @@ static void rdev_init_debugfs(struct regulator_dev *rdev) } rdev->debugfs = debugfs_create_dir(rname, debugfs_root); - if (!rdev->debugfs) { + if (IS_ERR(rdev->debugfs)) { rdev_warn(rdev, "Failed to create debugfs directory\n"); return; } @@ -5937,7 +5937,7 @@ static int __init regulator_init(void) ret = class_register(®ulator_class); debugfs_root = debugfs_create_dir("regulator", NULL); - if (!debugfs_root) + if (IS_ERR(debugfs_root)) pr_warn("regulator: Failed to create debugfs directory\n"); #ifdef CONFIG_DEBUG_FS From 8b7a2207ee40426e5f93d519d801f8916ae010d8 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 15 May 2023 13:13:51 -0700 Subject: [PATCH 3523/4345] irqchip/gic-v3: Disable pseudo NMIs on Mediatek devices w/ firmware issues [ Upstream commit 44bd78dd2b8897f59b7e3963f088caadb7e4f047 ] Some Chromebooks with Mediatek SoCs have a problem where the firmware doesn't properly save/restore certain GICR registers. Newer Chromebooks should fix this issue and we may be able to do firmware updates for old Chromebooks. At the moment, the only known issue with these Chromebooks is that we can't enable "pseudo NMIs" since the priority register can be lost. Enabling "pseudo NMIs" on Chromebooks with the problematic firmware causes crashes and freezes. Let's detect devices with this problem and then disable "pseudo NMIs" on them. We'll detect the problem by looking for the presence of the "mediatek,broken-save-restore-fw" property in the GIC device tree node. Any devices with fixed firmware will not have this property. Our detection plan works because we never bake a Chromebook's device tree into firmware. Instead, device trees are always bundled with the kernel. We'll update the device trees of all affected Chromebooks and then we'll never enable "pseudo NMI" on a kernel that is bundled with old device trees. When a firmware update is shipped that fixes this issue it will know to patch the device tree to remove the property. In order to make this work, the quick detection mechanism of the GICv3 code is extended to be able to look for properties in addition to looking at "compatible". Reviewed-by: Julius Werner Signed-off-by: Douglas Anderson Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230515131353.v2.2.I88dc0a0eb1d9d537de61604cd8994ecc55c0cac1@changeid Signed-off-by: Sasha Levin --- drivers/irqchip/irq-gic-common.c | 8 ++++++-- drivers/irqchip/irq-gic-common.h | 1 + drivers/irqchip/irq-gic-v3.c | 20 ++++++++++++++++++++ 3 files changed, 27 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c index f47b41dfd023..02828a16979a 100644 --- a/drivers/irqchip/irq-gic-common.c +++ b/drivers/irqchip/irq-gic-common.c @@ -29,7 +29,11 @@ void gic_enable_of_quirks(const struct device_node *np, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { - if (!of_device_is_compatible(np, quirks->compatible)) + if (quirks->compatible && + !of_device_is_compatible(np, quirks->compatible)) + continue; + if (quirks->property && + !of_property_read_bool(np, quirks->property)) continue; if (quirks->init(data)) pr_info("GIC: enabling workaround for %s\n", @@ -41,7 +45,7 @@ void gic_enable_quirks(u32 iidr, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { - if (quirks->compatible) + if (quirks->compatible || quirks->property) continue; if (quirks->iidr != (quirks->mask & iidr)) continue; diff --git a/drivers/irqchip/irq-gic-common.h b/drivers/irqchip/irq-gic-common.h index ccba8b0fe0f5..b42572d88f9f 100644 --- a/drivers/irqchip/irq-gic-common.h +++ b/drivers/irqchip/irq-gic-common.h @@ -13,6 +13,7 @@ struct gic_quirk { const char *desc; const char *compatible; + const char *property; bool (*init)(void *data); u32 iidr; u32 mask; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 2805969e4f15..c1f8c1be8485 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -35,6 +35,7 @@ #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) +#define FLAGS_WORKAROUND_MTK_GICR_SAVE (1ULL << 2) #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) @@ -1587,6 +1588,15 @@ static bool gic_enable_quirk_msm8996(void *data) return true; } +static bool gic_enable_quirk_mtk_gicr(void *data) +{ + struct gic_chip_data *d = data; + + d->flags |= FLAGS_WORKAROUND_MTK_GICR_SAVE; + + return true; +} + static bool gic_enable_quirk_cavium_38539(void *data) { struct gic_chip_data *d = data; @@ -1622,6 +1632,11 @@ static const struct gic_quirk gic_quirks[] = { .compatible = "qcom,msm8996-gic-v3", .init = gic_enable_quirk_msm8996, }, + { + .desc = "GICv3: Mediatek Chromebook GICR save problem", + .property = "mediatek,broken-save-restore-fw", + .init = gic_enable_quirk_mtk_gicr, + }, { .desc = "GICv3: HIP06 erratum 161010803", .iidr = 0x0204043b, @@ -1658,6 +1673,11 @@ static void gic_enable_nmi_support(void) if (!gic_prio_masking_enabled()) return; + if (gic_data.flags & FLAGS_WORKAROUND_MTK_GICR_SAVE) { + pr_warn("Skipping NMI enable due to firmware issues\n"); + return; + } + ppi_nmi_refs = kcalloc(gic_data.ppi_nr, sizeof(*ppi_nmi_refs), GFP_KERNEL); if (!ppi_nmi_refs) return; From 35d32d841592b5ac6b12a2359730ef6c7dd58edc Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 16 May 2023 13:25:40 -0500 Subject: [PATCH 3524/4345] power: supply: Fix logic checking if system is running from battery [ Upstream commit 95339f40a8b652b5b1773def31e63fc53c26378a ] The logic used for power_supply_is_system_supplied() counts all power supplies and assumes that the system is running from AC if there is either a non-battery power-supply reporting to be online or if no power-supplies exist at all. The second rule is for desktop systems, that don't have any battery/charger devices. These systems will incorrectly report to be powered from battery once a device scope power-supply is registered (e.g. a HID device), since these power-supplies increase the counter. Apart from HID devices, recent dGPUs provide UCSI power supplies on a desktop systems. The dGPU by default doesn't have anything plugged in so it's 'offline'. This makes power_supply_is_system_supplied() return 0 with a count of 1 meaning all drivers that use this get a wrong judgement. To fix this case adjust the logic to also examine the scope of the power supply. If the power supply is deemed a device power supply, then don't count it. Cc: Evan Quan Suggested-by: Lijo Lazar Signed-off-by: Mario Limonciello Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/power_supply_core.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 53e5b3e04be1..5c8c117b396e 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -347,6 +347,10 @@ static int __power_supply_is_system_supplied(struct device *dev, void *data) struct power_supply *psy = dev_get_drvdata(dev); unsigned int *count = data; + if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_SCOPE, &ret)) + if (ret.intval == POWER_SUPPLY_SCOPE_DEVICE) + return 0; + (*count)++; if (psy->desc->type != POWER_SUPPLY_TYPE_BATTERY) if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_ONLINE, @@ -365,8 +369,8 @@ int power_supply_is_system_supplied(void) __power_supply_is_system_supplied); /* - * If no power class device was found at all, most probably we are - * running on a desktop system, so assume we are on mains power. + * If no system scope power class device was found at all, most probably we + * are running on a desktop system, so assume we are on mains power. */ if (count == 0) return 1; From 142fbad3140553ad357d231cfbe79ac55c8ff055 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 13 Apr 2023 13:57:17 +0800 Subject: [PATCH 3525/4345] btrfs: scrub: try harder to mark RAID56 block groups read-only [ Upstream commit 7561551e7ba870b9659083b95feb520fb2dacce3 ] Currently we allow a block group not to be marked read-only for scrub. But for RAID56 block groups if we require the block group to be read-only, then we're allowed to use cached content from scrub stripe to reduce unnecessary RAID56 reads. So this patch would: - Make btrfs_inc_block_group_ro() try harder During my tests, for cases like btrfs/061 and btrfs/064, we can hit ENOSPC from btrfs_inc_block_group_ro() calls during scrub. The reason is if we only have one single data chunk, and trying to scrub it, we won't have any space left for any newer data writes. But this check should be done by the caller, especially for scrub cases we only temporarily mark the chunk read-only. And newer data writes would always try to allocate a new data chunk when needed. - Return error for scrub if we failed to mark a RAID56 chunk read-only Signed-off-by: Qu Wenruo Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/block-group.c | 14 ++++++++++++-- fs/btrfs/scrub.c | 9 ++++++++- 2 files changed, 20 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 889a598b17f6..d0fecbd28232 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2279,10 +2279,20 @@ again: } ret = inc_block_group_ro(cache, 0); - if (!do_chunk_alloc || ret == -ETXTBSY) - goto unlock_out; if (!ret) goto out; + if (ret == -ETXTBSY) + goto unlock_out; + + /* + * Skip chunk alloction if the bg is SYSTEM, this is to avoid system + * chunk allocation storm to exhaust the system chunk array. Otherwise + * we still want to try our best to mark the block group read-only. + */ + if (!do_chunk_alloc && ret == -ENOSPC && + (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM)) + goto unlock_out; + alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags); ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); if (ret < 0) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 88b9a5394561..715a0329ba27 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3559,13 +3559,20 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, ret = btrfs_inc_block_group_ro(cache, sctx->is_dev_replace); if (ret == 0) { ro_set = 1; - } else if (ret == -ENOSPC && !sctx->is_dev_replace) { + } else if (ret == -ENOSPC && !sctx->is_dev_replace && + !(cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK)) { /* * btrfs_inc_block_group_ro return -ENOSPC when it * failed in creating new chunk for metadata. * It is not a problem for scrub, because * metadata are always cowed, and our scrub paused * commit_transactions. + * + * For RAID56 chunks, we have to mark them read-only + * for scrub, as later we would use our own cache + * out of RAID56 realm. + * Thus we want the RAID56 bg to be marked RO to + * prevent RMW from screwing up out cache. */ ro_set = 0; } else if (ret == -ETXTBSY) { From 3bc883132d03c3a8daf1794ef0c2fa8067e5fe1d Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 4 May 2023 13:58:13 +0200 Subject: [PATCH 3526/4345] btrfs: handle memory allocation failure in btrfs_csum_one_bio [ Upstream commit 806570c0bb7b4847828c22c4934fcf2dc8fc572f ] Since f8a53bb58ec7 ("btrfs: handle checksum generation in the storage layer") the failures of btrfs_csum_one_bio() are handled via bio_end_io(). This means, we can return BLK_STS_RESOURCE from btrfs_csum_one_bio() in case the allocation of the ordered sums fails. This also fixes a syzkaller report, where injecting a failure into the kvzalloc() call results in a BUG_ON(). Reported-by: syzbot+d8941552e21eac774778@syzkaller.appspotmail.com Reviewed-by: Christoph Hellwig Reviewed-by: Anand Jain Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/file-item.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 2de1d8247494..cbea4f572155 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -602,7 +602,9 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio, sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bytes_left), GFP_KERNEL); memalloc_nofs_restore(nofs_flag); - BUG_ON(!sums); /* -ENOMEM */ + if (!sums) + return BLK_STS_RESOURCE; + sums->len = bytes_left; ordered = btrfs_lookup_ordered_extent(inode, offset); From 73102fdb5bf3d7c8582d9388b68f96c6bef4665f Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Wed, 17 May 2023 13:57:31 -0500 Subject: [PATCH 3527/4345] ASoC: soc-pcm: test if a BE can be prepared [ Upstream commit e123036be377ddf628226a7c6d4f9af5efd113d3 ] In the BE hw_params configuration, the existing code checks if any of the existing FEs are prepared, running, paused or suspended - and skips the configuration in those cases. This allows multiple calls of hw_params which the ALSA state machine supports. This check is not handled for the prepare stage, which can lead to the same BE being prepared multiple times. This patch adds a check similar to that of the hw_params, with the main difference being that the suspended state is allowed: the ALSA state machine allows a transition from suspended to prepared with hw_params skipped. This problem was detected on Intel IPC4/SoundWire devices, where the BE dailink .prepare stage is used to configure the SoundWire stream with a bank switch. Multiple .prepare calls lead to conflicts with the .trigger operation with IPC4 configurations. This problem was not detected earlier on Intel devices, HDaudio BE dailinks detect that the link is already prepared and skip the configuration, and for IPC3 devices there is no BE trigger. Link: https://github.com/thesofproject/sof/issues/7596 Signed-off-by: Ranjani Sridharan --- include/sound/soc-dpcm.h | 4 ++++ sound/soc/soc-pcm.c | 20 ++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h index 0f6c50b17bba..bd8795198a7d 100644 --- a/include/sound/soc-dpcm.h +++ b/include/sound/soc-dpcm.h @@ -121,6 +121,10 @@ int snd_soc_dpcm_can_be_free_stop(struct snd_soc_pcm_runtime *fe, int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, struct snd_soc_pcm_runtime *be, int stream); +/* can this BE perform prepare */ +int snd_soc_dpcm_can_be_prepared(struct snd_soc_pcm_runtime *fe, + struct snd_soc_pcm_runtime *be, int stream); + /* is the current PCM operation for this FE ? */ int snd_soc_dpcm_fe_can_update(struct snd_soc_pcm_runtime *fe, int stream); diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index fb874f924bbe..e52c030bd17a 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -2332,6 +2332,9 @@ int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream) if (!snd_soc_dpcm_be_can_update(fe, be, stream)) continue; + if (!snd_soc_dpcm_can_be_prepared(fe, be, stream)) + continue; + if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_PARAMS) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND) && @@ -2972,3 +2975,20 @@ int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); } EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_params); + +/* + * We can only prepare a BE DAI if any of it's FE are not prepared, + * running or paused for the specified stream direction. + */ +int snd_soc_dpcm_can_be_prepared(struct snd_soc_pcm_runtime *fe, + struct snd_soc_pcm_runtime *be, int stream) +{ + const enum snd_soc_dpcm_state state[] = { + SND_SOC_DPCM_STATE_START, + SND_SOC_DPCM_STATE_PAUSED, + SND_SOC_DPCM_STATE_PREPARE, + }; + + return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); +} +EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_prepared); From 3f7625e0862050dbeb00396d57a44b98103d8c47 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 17 May 2023 15:52:30 +0200 Subject: [PATCH 3528/4345] parisc: Improve cache flushing for PCXL in arch_sync_dma_for_cpu() [ Upstream commit 59fa12646d9f56c842b4d5b6418ed77af625c588 ] Add comment in arch_sync_dma_for_device() and handle the direction flag in arch_sync_dma_for_cpu(). When receiving data from the device (DMA_FROM_DEVICE) unconditionally purge the data cache in arch_sync_dma_for_cpu(). Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- arch/parisc/kernel/pci-dma.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index 36610a5c029f..fc90ccfee157 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -446,11 +446,27 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { + /* + * fdc: The data cache line is written back to memory, if and only if + * it is dirty, and then invalidated from the data cache. + */ flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); } void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); + unsigned long addr = (unsigned long) phys_to_virt(paddr); + + switch (dir) { + case DMA_TO_DEVICE: + case DMA_BIDIRECTIONAL: + flush_kernel_dcache_range(addr, size); + return; + case DMA_FROM_DEVICE: + purge_kernel_dcache_range_asm(addr, addr + size); + return; + default: + BUG(); + } } From 0ca73b45b767822f1c59c77caefd93e2460778d4 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 17 May 2023 15:54:40 +0200 Subject: [PATCH 3529/4345] parisc: Flush gatt writes and adjust gatt mask in parisc_agp_mask_memory() [ Upstream commit d703797380c540bbeac03f104ebcfc364eaf47cc ] Flush caches after changing gatt entries and calculate entry according to SBA requirements. Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/char/agp/parisc-agp.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index d68d05d5d383..514f9f287a78 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -90,6 +90,9 @@ parisc_agp_tlbflush(struct agp_memory *mem) { struct _parisc_agp_info *info = &parisc_agp_info; + /* force fdc ops to be visible to IOMMU */ + asm_io_sync(); + writeq(info->gart_base | ilog2(info->gart_size), info->ioc_regs+IOC_PCOM); readq(info->ioc_regs+IOC_PCOM); /* flush */ } @@ -158,6 +161,7 @@ parisc_agp_insert_memory(struct agp_memory *mem, off_t pg_start, int type) info->gatt[j] = parisc_agp_mask_memory(agp_bridge, paddr, type); + asm_io_fdc(&info->gatt[j]); } } @@ -191,7 +195,16 @@ static unsigned long parisc_agp_mask_memory(struct agp_bridge_data *bridge, dma_addr_t addr, int type) { - return SBA_PDIR_VALID_BIT | addr; + unsigned ci; /* coherent index */ + dma_addr_t pa; + + pa = addr & IOVP_MASK; + asm("lci 0(%1), %0" : "=r" (ci) : "r" (phys_to_virt(pa))); + + pa |= (ci >> PAGE_SHIFT) & 0xff;/* move CI (8 bits) into lowest byte */ + pa |= SBA_PDIR_VALID_BIT; /* set "valid" bit */ + + return cpu_to_le64(pa); } static void From 619672bf2d04cdc1bc3925defd0312c2ef11e5d0 Mon Sep 17 00:00:00 2001 From: Manuel Lauss Date: Thu, 11 May 2023 17:30:10 +0200 Subject: [PATCH 3530/4345] MIPS: Alchemy: fix dbdma2 [ Upstream commit 2d645604f69f3a772d58ead702f9a8e84ab2b342 ] Various fixes for the Au1200/Au1550/Au1300 DBDMA2 code: - skip cache invalidation if chip has working coherency circuitry. - invalidate KSEG0-portion of the (physical) data address. - force the dma channel doorbell write out to bus immediately with a sync. Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/alchemy/common/dbdma.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/arch/mips/alchemy/common/dbdma.c b/arch/mips/alchemy/common/dbdma.c index 4ca2c28878e0..e9ee9ab90a0c 100644 --- a/arch/mips/alchemy/common/dbdma.c +++ b/arch/mips/alchemy/common/dbdma.c @@ -30,6 +30,7 @@ * */ +#include /* for dma_default_coherent */ #include #include #include @@ -623,17 +624,18 @@ u32 au1xxx_dbdma_put_source(u32 chanid, dma_addr_t buf, int nbytes, u32 flags) dp->dscr_cmd0 &= ~DSCR_CMD0_IE; /* - * There is an errata on the Au1200/Au1550 parts that could result - * in "stale" data being DMA'ed. It has to do with the snoop logic on - * the cache eviction buffer. DMA_NONCOHERENT is on by default for - * these parts. If it is fixed in the future, these dma_cache_inv will - * just be nothing more than empty macros. See io.h. + * There is an erratum on certain Au1200/Au1550 revisions that could + * result in "stale" data being DMA'ed. It has to do with the snoop + * logic on the cache eviction buffer. dma_default_coherent is set + * to false on these parts. */ - dma_cache_wback_inv((unsigned long)buf, nbytes); + if (!dma_default_coherent) + dma_cache_wback_inv(KSEG0ADDR(buf), nbytes); dp->dscr_cmd0 |= DSCR_CMD0_V; /* Let it rip */ wmb(); /* drain writebuffer */ dma_cache_wback_inv((unsigned long)dp, sizeof(*dp)); ctp->chan_ptr->ddma_dbell = 0; + wmb(); /* force doorbell write out to dma engine */ /* Get next descriptor pointer. */ ctp->put_ptr = phys_to_virt(DSCR_GET_NXTPTR(dp->dscr_nxtptr)); @@ -685,17 +687,18 @@ u32 au1xxx_dbdma_put_dest(u32 chanid, dma_addr_t buf, int nbytes, u32 flags) dp->dscr_source1, dp->dscr_dest0, dp->dscr_dest1); #endif /* - * There is an errata on the Au1200/Au1550 parts that could result in - * "stale" data being DMA'ed. It has to do with the snoop logic on the - * cache eviction buffer. DMA_NONCOHERENT is on by default for these - * parts. If it is fixed in the future, these dma_cache_inv will just - * be nothing more than empty macros. See io.h. + * There is an erratum on certain Au1200/Au1550 revisions that could + * result in "stale" data being DMA'ed. It has to do with the snoop + * logic on the cache eviction buffer. dma_default_coherent is set + * to false on these parts. */ - dma_cache_inv((unsigned long)buf, nbytes); + if (!dma_default_coherent) + dma_cache_inv(KSEG0ADDR(buf), nbytes); dp->dscr_cmd0 |= DSCR_CMD0_V; /* Let it rip */ wmb(); /* drain writebuffer */ dma_cache_wback_inv((unsigned long)dp, sizeof(*dp)); ctp->chan_ptr->ddma_dbell = 0; + wmb(); /* force doorbell write out to dma engine */ /* Get next descriptor pointer. */ ctp->put_ptr = phys_to_virt(DSCR_GET_NXTPTR(dp->dscr_nxtptr)); From d47b5a6d233196ccbdc6791e99d6a70cc2938968 Mon Sep 17 00:00:00 2001 From: Liviu Dudau Date: Tue, 9 May 2023 18:29:21 +0100 Subject: [PATCH 3531/4345] mips: Move initrd_start check after initrd address sanitisation. [ Upstream commit 4897a898a216058dec55e5e5902534e6e224fcdf ] PAGE_OFFSET is technically a virtual address so when checking the value of initrd_start against it we should make sure that it has been sanitised from the values passed by the bootloader. Without this change, even with a bootloader that passes correct addresses for an initrd, we are failing to load it on MT7621 boards, for example. Signed-off-by: Liviu Dudau Signed-off-by: Thomas Bogendoerfer Signed-off-by: Sasha Levin --- arch/mips/kernel/setup.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 9d11f68a9e8b..b49ad569e469 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -154,10 +154,6 @@ static unsigned long __init init_initrd(void) pr_err("initrd start must be page aligned\n"); goto disable; } - if (initrd_start < PAGE_OFFSET) { - pr_err("initrd start < PAGE_OFFSET\n"); - goto disable; - } /* * Sanitize initrd addresses. For example firmware @@ -170,6 +166,11 @@ static unsigned long __init init_initrd(void) initrd_end = (unsigned long)__va(end); initrd_start = (unsigned long)__va(__pa(initrd_start)); + if (initrd_start < PAGE_OFFSET) { + pr_err("initrd start < PAGE_OFFSET\n"); + goto disable; + } + ROOT_DEV = Root_RAM0; return PFN_UP(end); disable: From 8e45fb70f4b56659b9ad34113d7fe089e984d6c9 Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Fri, 12 May 2023 14:03:42 +0300 Subject: [PATCH 3532/4345] ASoC: dwc: move DMA init to snd_soc_dai_driver probe() [ Upstream commit 011a8719d6105dcb48077ea7a6a88ac019d4aa50 ] When using DMA mode we are facing with Oops: [ 396.458157] Unable to handle kernel access to user memory without uaccess routines at virtual address 000000000000000c [ 396.469374] Oops [#1] [ 396.471839] Modules linked in: [ 396.475144] CPU: 0 PID: 114 Comm: arecord Not tainted 6.0.0-00164-g9a8eccdaf2be-dirty #68 [ 396.483619] Hardware name: YMP ELCT FPGA (DT) [ 396.488156] epc : dmaengine_pcm_open+0x1d2/0x342 [ 396.493227] ra : dmaengine_pcm_open+0x1d2/0x342 [ 396.498140] epc : ffffffff807fe346 ra : ffffffff807fe346 sp : ffffffc804e138f0 [ 396.505602] gp : ffffffff817bf730 tp : ffffffd8042c8ac0 t0 : 6500000000000000 [ 396.513045] t1 : 0000000000000064 t2 : 656e69676e65616d s0 : ffffffc804e13990 [ 396.520477] s1 : ffffffd801b86a18 a0 : 0000000000000026 a1 : ffffffff816920f8 [ 396.527897] a2 : 0000000000000010 a3 : fffffffffffffffe a4 : 0000000000000000 [ 396.535319] a5 : 0000000000000000 a6 : ffffffd801b87040 a7 : 0000000000000038 [ 396.542740] s2 : ffffffd801b94a00 s3 : 0000000000000000 s4 : ffffffd80427f5e8 [ 396.550153] s5 : ffffffd80427f5e8 s6 : ffffffd801b44410 s7 : fffffffffffffff5 [ 396.557569] s8 : 0000000000000800 s9 : 0000000000000001 s10: ffffffff8066d254 [ 396.564978] s11: ffffffd8059cf768 t3 : ffffffff817d5577 t4 : ffffffff817d5577 [ 396.572391] t5 : ffffffff817d5578 t6 : ffffffc804e136e8 [ 396.577876] status: 0000000200000120 badaddr: 000000000000000c cause: 000000000000000d [ 396.586007] [] snd_soc_component_open+0x1a/0x68 [ 396.592439] [] __soc_pcm_open+0xf0/0x502 [ 396.598217] [] soc_pcm_open+0x2e/0x4e [ 396.603741] [] snd_pcm_open_substream+0x442/0x68e [ 396.610313] [] snd_pcm_open+0xfa/0x212 [ 396.615868] [] snd_pcm_capture_open+0x3a/0x60 [ 396.622048] [] snd_open+0xa8/0x17a [ 396.627421] [] chrdev_open+0xa0/0x218 [ 396.632893] [] do_dentry_open+0x17c/0x2a6 [ 396.638713] [] vfs_open+0x1e/0x26 [ 396.643850] [] path_openat+0x96e/0xc96 [ 396.649518] [] do_filp_open+0x7c/0xf6 [ 396.655034] [] do_sys_openat2+0x8a/0x11e [ 396.660765] [] sys_openat+0x50/0x7c [ 396.666068] [] ret_from_syscall+0x0/0x2 [ 396.674964] ---[ end trace 0000000000000000 ]--- It happens because of play_dma_data/capture_dma_data pointers are NULL. Current implementation assigns these pointers at snd_soc_dai_driver startup() callback and reset them back to NULL at shutdown(). But soc_pcm_open() sequence uses DMA pointers in dmaengine_pcm_open() before snd_soc_dai_driver startup(). Most generic DMA capable I2S drivers use snd_soc_dai_driver probe() callback to init DMA pointers only once at probe. So move DMA init to dw_i2s_dai_probe and drop shutdown() and startup() callbacks. Signed-off-by: Maxim Kochetkov Link: https://lore.kernel.org/r/20230512110343.66664-1-fido_max@inbox.ru Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/dwc/dwc-i2s.c | 41 +++++++++-------------------------------- 1 file changed, 9 insertions(+), 32 deletions(-) diff --git a/sound/soc/dwc/dwc-i2s.c b/sound/soc/dwc/dwc-i2s.c index 5469399abcb4..8e58347dabe8 100644 --- a/sound/soc/dwc/dwc-i2s.c +++ b/sound/soc/dwc/dwc-i2s.c @@ -183,30 +183,6 @@ static void i2s_stop(struct dw_i2s_dev *dev, } } -static int dw_i2s_startup(struct snd_pcm_substream *substream, - struct snd_soc_dai *cpu_dai) -{ - struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(cpu_dai); - union dw_i2s_snd_dma_data *dma_data = NULL; - - if (!(dev->capability & DWC_I2S_RECORD) && - (substream->stream == SNDRV_PCM_STREAM_CAPTURE)) - return -EINVAL; - - if (!(dev->capability & DWC_I2S_PLAY) && - (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)) - return -EINVAL; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - dma_data = &dev->play_dma_data; - else if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) - dma_data = &dev->capture_dma_data; - - snd_soc_dai_set_dma_data(cpu_dai, substream, (void *)dma_data); - - return 0; -} - static void dw_i2s_config(struct dw_i2s_dev *dev, int stream) { u32 ch_reg; @@ -305,12 +281,6 @@ static int dw_i2s_hw_params(struct snd_pcm_substream *substream, return 0; } -static void dw_i2s_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - snd_soc_dai_set_dma_data(dai, substream, NULL); -} - static int dw_i2s_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { @@ -382,8 +352,6 @@ static int dw_i2s_set_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt) } static const struct snd_soc_dai_ops dw_i2s_dai_ops = { - .startup = dw_i2s_startup, - .shutdown = dw_i2s_shutdown, .hw_params = dw_i2s_hw_params, .prepare = dw_i2s_prepare, .trigger = dw_i2s_trigger, @@ -624,6 +592,14 @@ static int dw_configure_dai_by_dt(struct dw_i2s_dev *dev, } +static int dw_i2s_dai_probe(struct snd_soc_dai *dai) +{ + struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(dai); + + snd_soc_dai_init_dma_data(dai, &dev->play_dma_data, &dev->capture_dma_data); + return 0; +} + static int dw_i2s_probe(struct platform_device *pdev) { const struct i2s_platform_data *pdata = pdev->dev.platform_data; @@ -642,6 +618,7 @@ static int dw_i2s_probe(struct platform_device *pdev) return -ENOMEM; dw_i2s_dai->ops = &dw_i2s_dai_ops; + dw_i2s_dai->probe = dw_i2s_dai_probe; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); dev->i2s_base = devm_ioremap_resource(&pdev->dev, res); From 7c0b17679b4300cebd7604ec1e7103746158dd58 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Wed, 26 Apr 2023 17:40:05 +0100 Subject: [PATCH 3533/4345] xen/blkfront: Only check REQ_FUA for writes [ Upstream commit b6ebaa8100090092aa602530d7e8316816d0c98d ] The existing code silently converts read operations with the REQ_FUA bit set into write-barrier operations. This results in data loss as the backend scribbles zeroes over the data instead of returning it. While the REQ_FUA bit doesn't make sense on a read operation, at least one well-known out-of-tree kernel module does set it and since it results in data loss, let's be safe here and only look at REQ_FUA for writes. Signed-off-by: Ross Lagerwall Acked-by: Juergen Gross Link: https://lore.kernel.org/r/20230426164005.2213139-1-ross.lagerwall@citrix.com Signed-off-by: Juergen Gross Signed-off-by: Sasha Levin --- drivers/block/xen-blkfront.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 6f33d62331b1..d68a8ca2161f 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -792,7 +792,8 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri ring_req->u.rw.handle = info->handle; ring_req->operation = rq_data_dir(req) ? BLKIF_OP_WRITE : BLKIF_OP_READ; - if (req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA) { + if (req_op(req) == REQ_OP_FLUSH || + (req_op(req) == REQ_OP_WRITE && (req->cmd_flags & REQ_FUA))) { /* * Ideally we can do an unordered flush-to-disk. * In case the backend onlysupports barriers, use that. From 2a2641a842eac11abd906eafa90e76b20afe32e8 Mon Sep 17 00:00:00 2001 From: Sukrut Bellary Date: Wed, 3 May 2023 16:15:07 -0700 Subject: [PATCH 3534/4345] drm:amd:amdgpu: Fix missing buffer object unlock in failure path [ Upstream commit 60ecaaf54886b0642d5c4744f7fbf1ff0d6b3e42 ] smatch warning - 1) drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:3615 gfx_v9_0_kiq_resume() warn: inconsistent returns 'ring->mqd_obj->tbo.base.resv'. 2) drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c:6901 gfx_v10_0_kiq_resume() warn: inconsistent returns 'ring->mqd_obj->tbo.base.resv'. Signed-off-by: Sukrut Bellary Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 4 +++- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 0e3ff5c3766e..72410a2d4e6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -6702,8 +6702,10 @@ static int gfx_v10_0_kiq_resume(struct amdgpu_device *adev) return r; r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&ring->mqd_ptr); - if (unlikely(r != 0)) + if (unlikely(r != 0)) { + amdgpu_bo_unreserve(ring->mqd_obj); return r; + } gfx_v10_0_kiq_init_queue(ring); amdgpu_bo_kunmap(ring->mqd_obj); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 629671f66b31..acef2227d992 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3800,8 +3800,10 @@ static int gfx_v9_0_kiq_resume(struct amdgpu_device *adev) return r; r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&ring->mqd_ptr); - if (unlikely(r != 0)) + if (unlikely(r != 0)) { + amdgpu_bo_unreserve(ring->mqd_obj); return r; + } gfx_v9_0_kiq_init_queue(ring); amdgpu_bo_kunmap(ring->mqd_obj); From 93a68acc497bf59d523761ae40f348ded413c744 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 30 May 2023 11:01:22 +0100 Subject: [PATCH 3535/4345] irqchip/gic: Correctly validate OF quirk descriptors [ Upstream commit 91539341a3b6e9c868024a4292455dae36e6f58c ] When checking for OF quirks, make sure either 'compatible' or 'property' is set, and give up otherwise. This avoids non-OF quirks being randomly applied as they don't have any of the OF data that need checking. Cc: Douglas Anderson Reported-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Fixes: 44bd78dd2b88 ("irqchip/gic-v3: Disable pseudo NMIs on Mediatek devices w/ firmware issues") Signed-off-by: Marc Zyngier Signed-off-by: Sasha Levin --- drivers/irqchip/irq-gic-common.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c index 02828a16979a..b8a10f2e72da 100644 --- a/drivers/irqchip/irq-gic-common.c +++ b/drivers/irqchip/irq-gic-common.c @@ -29,6 +29,8 @@ void gic_enable_of_quirks(const struct device_node *np, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { + if (!quirks->compatible && !quirks->property) + continue; if (quirks->compatible && !of_device_is_compatible(np, quirks->compatible)) continue; From 4716c73b188566865bdd79c3a6709696a224ac04 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 16 Jun 2023 21:12:06 -0600 Subject: [PATCH 3536/4345] io_uring: hold uring mutex around poll removal Snipped from commit 9ca9fb24d5febccea354089c41f96a8ad0d853f8 upstream. While reworking the poll hashing in the v6.0 kernel, we ended up grabbing the ctx->uring_lock in poll update/removal. This also fixed a bug with linked timeouts racing with timeout expiry and poll removal. Bring back just the locking fix for that. Reported-and-tested-by: Querijn Voet Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index fd799567fc23..58e063114398 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5966,6 +5966,8 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) struct io_kiocb *preq; int ret2, ret = 0; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + spin_lock(&ctx->completion_lock); preq = io_poll_find(ctx, req->poll_update.old_user_data, true); if (!preq || !io_poll_disarm(preq)) { @@ -5997,6 +5999,7 @@ out: req_set_fail(req); /* complete update request, we're done with it */ io_req_complete(req, ret); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return 0; } From 370f5d98ffe58a95e31506390bc0704b9ddb05d4 Mon Sep 17 00:00:00 2001 From: Benjamin Segall Date: Tue, 30 May 2023 11:32:28 -0700 Subject: [PATCH 3537/4345] epoll: ep_autoremove_wake_function should use list_del_init_careful commit 2192bba03d80f829233bfa34506b428f71e531e7 upstream. autoremove_wake_function uses list_del_init_careful, so should epoll's more aggressive variant. It only doesn't because it was copied from an older wait.c rather than the most recent. [bsegall@google.com: add comment] Link: https://lkml.kernel.org/r/xm26bki0ulsr.fsf_-_@google.com Link: https://lkml.kernel.org/r/xm26pm6hvfer.fsf@google.com Fixes: a16ceb139610 ("epoll: autoremove wakers even more aggressively") Signed-off-by: Ben Segall Cc: Al Viro Cc: Christian Brauner Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/eventpoll.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 13d4c3d50412..5ce1ea1f452b 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1817,7 +1817,11 @@ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, { int ret = default_wake_function(wq_entry, mode, sync, key); - list_del_init(&wq_entry->entry); + /* + * Pairs with list_empty_careful in ep_poll, and ensures future loop + * iterations see the cause of this wakeup. + */ + list_del_init_careful(&wq_entry->entry); return ret; } From e73b135f540c76e868c515ab6fbcda525185d3ea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= Date: Mon, 22 May 2023 11:21:12 +0100 Subject: [PATCH 3538/4345] ocfs2: fix use-after-free when unmounting read-only filesystem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 50d927880e0f90d5cb25e897e9d03e5edacc79a8 upstream. It's trivial to trigger a use-after-free bug in the ocfs2 quotas code using fstest generic/452. After a read-only remount, quotas are suspended and ocfs2_mem_dqinfo is freed through ->ocfs2_local_free_info(). When unmounting the filesystem, an UAF access to the oinfo will eventually cause a crash. BUG: KASAN: slab-use-after-free in timer_delete+0x54/0xc0 Read of size 8 at addr ffff8880389a8208 by task umount/669 ... Call Trace: ... timer_delete+0x54/0xc0 try_to_grab_pending+0x31/0x230 __cancel_work_timer+0x6c/0x270 ocfs2_disable_quotas.isra.0+0x3e/0xf0 [ocfs2] ocfs2_dismount_volume+0xdd/0x450 [ocfs2] generic_shutdown_super+0xaa/0x280 kill_block_super+0x46/0x70 deactivate_locked_super+0x4d/0xb0 cleanup_mnt+0x135/0x1f0 ... Allocated by task 632: kasan_save_stack+0x1c/0x40 kasan_set_track+0x21/0x30 __kasan_kmalloc+0x8b/0x90 ocfs2_local_read_info+0xe3/0x9a0 [ocfs2] dquot_load_quota_sb+0x34b/0x680 dquot_load_quota_inode+0xfe/0x1a0 ocfs2_enable_quotas+0x190/0x2f0 [ocfs2] ocfs2_fill_super+0x14ef/0x2120 [ocfs2] mount_bdev+0x1be/0x200 legacy_get_tree+0x6c/0xb0 vfs_get_tree+0x3e/0x110 path_mount+0xa90/0xe10 __x64_sys_mount+0x16f/0x1a0 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 650: kasan_save_stack+0x1c/0x40 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x50 __kasan_slab_free+0xf9/0x150 __kmem_cache_free+0x89/0x180 ocfs2_local_free_info+0x2ba/0x3f0 [ocfs2] dquot_disable+0x35f/0xa70 ocfs2_susp_quotas.isra.0+0x159/0x1a0 [ocfs2] ocfs2_remount+0x150/0x580 [ocfs2] reconfigure_super+0x1a5/0x3a0 path_mount+0xc8a/0xe10 __x64_sys_mount+0x16f/0x1a0 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc Link: https://lkml.kernel.org/r/20230522102112.9031-1-lhenriques@suse.de Signed-off-by: Luís Henriques Reviewed-by: Joseph Qi Tested-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/super.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 04ce30ae4404..dc21d35527ab 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -955,8 +955,10 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb) for (type = 0; type < OCFS2_MAXQUOTAS; type++) { if (!sb_has_quota_loaded(sb, type)) continue; - oinfo = sb_dqinfo(sb, type)->dqi_priv; - cancel_delayed_work_sync(&oinfo->dqi_sync_work); + if (!sb_has_quota_suspended(sb, type)) { + oinfo = sb_dqinfo(sb, type)->dqi_priv; + cancel_delayed_work_sync(&oinfo->dqi_sync_work); + } inode = igrab(sb->s_dquot.files[type]); /* Turn off quotas. This will remove all dquot structures from * memory and so they will be automatically synced to global From 2847d9eed48b9936d52f5fc524a4e6f4916ba2af Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lu=C3=ADs=20Henriques?= Date: Mon, 29 May 2023 16:26:45 +0100 Subject: [PATCH 3539/4345] ocfs2: check new file size on fallocate call MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 26a6ffff7de5dd369cdb12e38ba11db682f1dec0 upstream. When changing a file size with fallocate() the new size isn't being checked. In particular, the FSIZE ulimit isn't being checked, which makes fstest generic/228 fail. Simply adding a call to inode_newsize_ok() fixes this issue. Link: https://lkml.kernel.org/r/20230529152645.32680-1-lhenriques@suse.de Signed-off-by: Luís Henriques Reviewed-by: Mark Fasheh Reviewed-by: Joseph Qi Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/file.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index ca00cac5a12f..df36d84aedc4 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2103,14 +2103,20 @@ static long ocfs2_fallocate(struct file *file, int mode, loff_t offset, struct ocfs2_space_resv sr; int change_size = 1; int cmd = OCFS2_IOC_RESVSP64; + int ret = 0; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (!ocfs2_writes_unwritten_extents(osb)) return -EOPNOTSUPP; - if (mode & FALLOC_FL_KEEP_SIZE) + if (mode & FALLOC_FL_KEEP_SIZE) { change_size = 0; + } else { + ret = inode_newsize_ok(inode, offset + len); + if (ret) + return ret; + } if (mode & FALLOC_FL_PUNCH_HOLE) cmd = OCFS2_IOC_UNRESVSP64; From d59293f082dcccef2208716bcf95ce6b8de5341d Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Sun, 12 Feb 2023 13:16:32 +0100 Subject: [PATCH 3540/4345] nios2: dts: Fix tse_mac "max-frame-size" property commit 85041e12418fd0c08ff972b7729f7971afb361f8 upstream. The given value of 1518 seems to refer to the layer 2 ethernet frame size without 802.1Q tag. Actual use of the "max-frame-size" including in the consumer of the "altr,tse-1.0" compatible is the MTU. Fixes: 95acd4c7b69c ("nios2: Device tree support") Fixes: 61c610ec61bb ("nios2: Add Max10 device tree") Cc: Signed-off-by: Janne Grunau Signed-off-by: Dinh Nguyen Signed-off-by: Greg Kroah-Hartman --- arch/nios2/boot/dts/10m50_devboard.dts | 2 +- arch/nios2/boot/dts/3c120_devboard.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/nios2/boot/dts/10m50_devboard.dts b/arch/nios2/boot/dts/10m50_devboard.dts index 56339bef3247..0e7e5b0dd685 100644 --- a/arch/nios2/boot/dts/10m50_devboard.dts +++ b/arch/nios2/boot/dts/10m50_devboard.dts @@ -97,7 +97,7 @@ rx-fifo-depth = <8192>; tx-fifo-depth = <8192>; address-bits = <48>; - max-frame-size = <1518>; + max-frame-size = <1500>; local-mac-address = [00 00 00 00 00 00]; altr,has-supplementary-unicast; altr,enable-sup-addr = <1>; diff --git a/arch/nios2/boot/dts/3c120_devboard.dts b/arch/nios2/boot/dts/3c120_devboard.dts index d10fb81686c7..3ee316906379 100644 --- a/arch/nios2/boot/dts/3c120_devboard.dts +++ b/arch/nios2/boot/dts/3c120_devboard.dts @@ -106,7 +106,7 @@ interrupt-names = "rx_irq", "tx_irq"; rx-fifo-depth = <8192>; tx-fifo-depth = <8192>; - max-frame-size = <1518>; + max-frame-size = <1500>; local-mac-address = [ 00 00 00 00 00 00 ]; phy-mode = "rgmii-id"; phy-handle = <&phy0>; From 902fcec05295a66370f7b15822243d7898bf7b46 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sat, 13 May 2023 19:24:28 +0900 Subject: [PATCH 3541/4345] nilfs2: fix incomplete buffer cleanup in nilfs_btnode_abort_change_key() commit 2f012f2baca140c488e43d27a374029c1e59098d upstream. A syzbot fault injection test reported that nilfs_btnode_create_block, a helper function that allocates a new node block for b-trees, causes a kernel BUG for disk images where the file system block size is smaller than the page size. This was due to unexpected flags on the newly allocated buffer head, and it turned out to be because the buffer flags were not cleared by nilfs_btnode_abort_change_key() after an error occurred during a b-tree update operation and the buffer was later reused in that state. Fix this issue by using nilfs_btnode_delete() to abandon the unused preallocated buffer in nilfs_btnode_abort_change_key(). Link: https://lkml.kernel.org/r/20230513102428.10223-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+b0a35a5c1f7e846d3b09@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/000000000000d1d6c205ebc4d512@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/btnode.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index e00e184b1261..1776121677e2 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -285,6 +285,14 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc, if (nbh == NULL) { /* blocksize == pagesize */ xa_erase_irq(&btnc->i_pages, newkey); unlock_page(ctxt->bh->b_page); - } else - brelse(nbh); + } else { + /* + * When canceling a buffer that a prepare operation has + * allocated to copy a node block to another location, use + * nilfs_btnode_delete() to initialize and release the buffer + * so that the buffer flags will not be in an inconsistent + * state when it is reallocated. + */ + nilfs_btnode_delete(nbh); + } } From 7e78b9142fdf7dffe62534b48bcf43734247de40 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Wed, 24 May 2023 18:43:48 +0900 Subject: [PATCH 3542/4345] nilfs2: fix possible out-of-bounds segment allocation in resize ioctl commit fee5eaecca86afa544355569b831c1f90f334b85 upstream. Syzbot reports that in its stress test for resize ioctl, the log writing function nilfs_segctor_do_construct hits a WARN_ON in nilfs_segctor_truncate_segments(). It turned out that there is a problem with the current implementation of the resize ioctl, which changes the writable range on the device (the range of allocatable segments) at the end of the resize process. This order is necessary for file system expansion to avoid corrupting the superblock at trailing edge. However, in the case of a file system shrink, if log writes occur after truncating out-of-bounds trailing segments and before the resize is complete, segments may be allocated from the truncated space. The userspace resize tool was fine as it limits the range of allocatable segments before performing the resize, but it can run into this issue if the resize ioctl is called alone. Fix this issue by changing nilfs_sufile_resize() to update the range of allocatable segments immediately after successful truncation of segment space in case of file system shrink. Link: https://lkml.kernel.org/r/20230524094348.3784-1-konishi.ryusuke@gmail.com Fixes: 4e33f9eab07e ("nilfs2: implement resize ioctl") Signed-off-by: Ryusuke Konishi Reported-by: syzbot+33494cd0df2ec2931851@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/0000000000005434c405fbbafdc5@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/sufile.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 51f4cb060231..b3abe69382fd 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -779,6 +779,15 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs) goto out_header; sui->ncleansegs -= nsegs - newnsegs; + + /* + * If the sufile is successfully truncated, immediately adjust + * the segment allocation space while locking the semaphore + * "mi_sem" so that nilfs_sufile_alloc() never allocates + * segments in the truncated space. + */ + sui->allocmax = newnsegs - 1; + sui->allocmin = 0; } kaddr = kmap_atomic(header_bh->b_page); From f368aed4827bd4276c0e3664fb2cb815a8d7caf3 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Fri, 19 May 2023 16:47:36 +0200 Subject: [PATCH 3543/4345] kexec: support purgatories with .text.hot sections commit 8652d44f466ad5772e7d1756e9457046189b0dfc upstream. Patch series "kexec: Fix kexec_file_load for llvm16 with PGO", v7. When upreving llvm I realised that kexec stopped working on my test platform. The reason seems to be that due to PGO there are multiple .text sections on the purgatory, and kexec does not supports that. This patch (of 4): Clang16 links the purgatory text in two sections when PGO is in use: [ 1] .text PROGBITS 0000000000000000 00000040 00000000000011a1 0000000000000000 AX 0 0 16 [ 2] .rela.text RELA 0000000000000000 00003498 0000000000000648 0000000000000018 I 24 1 8 ... [17] .text.hot. PROGBITS 0000000000000000 00003220 000000000000020b 0000000000000000 AX 0 0 1 [18] .rela.text.hot. RELA 0000000000000000 00004428 0000000000000078 0000000000000018 I 24 17 8 And both of them have their range [sh_addr ... sh_addr+sh_size] on the area pointed by `e_entry`. This causes that image->start is calculated twice, once for .text and another time for .text.hot. The second calculation leaves image->start in a random location. Because of this, the system crashes immediately after: kexec_core: Starting new kernel Link: https://lkml.kernel.org/r/20230321-kexec_clang16-v7-0-b05c520b7296@chromium.org Link: https://lkml.kernel.org/r/20230321-kexec_clang16-v7-1-b05c520b7296@chromium.org Fixes: 930457057abe ("kernel/kexec_file.c: split up __kexec_load_puragory") Signed-off-by: Ricardo Ribalda Reviewed-by: Ross Zwisler Reviewed-by: Steven Rostedt (Google) Reviewed-by: Philipp Rudo Cc: Albert Ou Cc: Baoquan He Cc: Borislav Petkov (AMD) Cc: Christophe Leroy Cc: Dave Hansen Cc: Dave Young Cc: Eric W. Biederman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Michael Ellerman Cc: Nathan Chancellor Cc: Nicholas Piggin Cc: Nick Desaulniers Cc: Palmer Dabbelt Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Simon Horman Cc: Thomas Gleixner Cc: Tom Rix Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- kernel/kexec_file.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index b9c857782ada..804dc508d926 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -910,10 +910,22 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi, } offset = ALIGN(offset, align); + + /* + * Check if the segment contains the entry point, if so, + * calculate the value of image->start based on it. + * If the compiler has produced more than one .text section + * (Eg: .text.hot), they are generally after the main .text + * section, and they shall not be used to calculate + * image->start. So do not re-calculate image->start if it + * is not set to the initial value, and warn the user so they + * have a chance to fix their purgatory's linker script. + */ if (sechdrs[i].sh_flags & SHF_EXECINSTR && pi->ehdr->e_entry >= sechdrs[i].sh_addr && pi->ehdr->e_entry < (sechdrs[i].sh_addr - + sechdrs[i].sh_size)) { + + sechdrs[i].sh_size) && + !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) { kbuf->image->start -= sechdrs[i].sh_addr; kbuf->image->start += kbuf->mem + offset; } From 26c80741ceb689f3789086407516edab99faed3b Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Fri, 19 May 2023 16:47:37 +0200 Subject: [PATCH 3544/4345] x86/purgatory: remove PGO flags commit 97b6b9cbba40a21c1d9a344d5c1991f8cfbf136e upstream. If profile-guided optimization is enabled, the purgatory ends up with multiple .text sections. This is not supported by kexec and crashes the system. Link: https://lkml.kernel.org/r/20230321-kexec_clang16-v7-2-b05c520b7296@chromium.org Fixes: 930457057abe ("kernel/kexec_file.c: split up __kexec_load_puragory") Signed-off-by: Ricardo Ribalda Cc: Cc: Albert Ou Cc: Baoquan He Cc: Borislav Petkov (AMD) Cc: Christophe Leroy Cc: Dave Hansen Cc: Dave Young Cc: Eric W. Biederman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Michael Ellerman Cc: Nathan Chancellor Cc: Nicholas Piggin Cc: Nick Desaulniers Cc: Palmer Dabbelt Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Philipp Rudo Cc: Ross Zwisler Cc: Simon Horman Cc: Steven Rostedt (Google) Cc: Thomas Gleixner Cc: Tom Rix Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- arch/x86/purgatory/Makefile | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index ebaf329a2368..dc0b91c1db04 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -14,6 +14,11 @@ $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE CFLAGS_sha256.o := -D__DISABLE_EXPORTS +# When profile-guided optimization is enabled, llvm emits two different +# overlapping text sections, which is not supported by kexec. Remove profile +# optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) + # When linking purgatory.ro with -r unresolved symbols are not checked, # also link a purgatory.chk binary without -r to check for unresolved symbols. PURGATORY_LDFLAGS := -e purgatory_start -nostdlib -z nodefaultlib From f1f7117b22369977cdb771e95f3feabe4e68b5e3 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Fri, 19 May 2023 16:47:38 +0200 Subject: [PATCH 3545/4345] powerpc/purgatory: remove PGO flags commit 20188baceb7a1463dc0bcb0c8678b69c2f447df6 upstream. If profile-guided optimization is enabled, the purgatory ends up with multiple .text sections. This is not supported by kexec and crashes the system. Link: https://lkml.kernel.org/r/20230321-kexec_clang16-v7-3-b05c520b7296@chromium.org Fixes: 930457057abe ("kernel/kexec_file.c: split up __kexec_load_puragory") Signed-off-by: Ricardo Ribalda Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Cc: Albert Ou Cc: Baoquan He Cc: Borislav Petkov (AMD) Cc: Dave Hansen Cc: Dave Young Cc: Eric W. Biederman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Palmer Dabbelt Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Philipp Rudo Cc: Ross Zwisler Cc: Simon Horman Cc: Steven Rostedt (Google) Cc: Thomas Gleixner Cc: Tom Rix Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/purgatory/Makefile | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile index 348f59581052..d08239ae2bcd 100644 --- a/arch/powerpc/purgatory/Makefile +++ b/arch/powerpc/purgatory/Makefile @@ -4,6 +4,11 @@ KASAN_SANITIZE := n targets += trampoline_$(BITS).o purgatory.ro kexec-purgatory.c +# When profile-guided optimization is enabled, llvm emits two different +# overlapping text sections, which is not supported by kexec. Remove profile +# optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) + LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined $(obj)/purgatory.ro: $(obj)/trampoline_$(BITS).o FORCE From 96e14c91c5301c2aad0de1ec8eee3dd4f031d96d Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 15 Jun 2023 12:22:11 +1000 Subject: [PATCH 3546/4345] nouveau: fix client work fence deletion race commit c8a5d5ea3ba6a18958f8d76430e4cd68eea33943 upstream. This seems to have existed for ever but is now more apparant after commit 9bff18d13473 ("drm/ttm: use per BO cleanup workers") My analysis: two threads are running, one in the irq signalling the fence, in dma_fence_signal_timestamp_locked, it has done the DMA_FENCE_FLAG_SIGNALLED_BIT setting, but hasn't yet reached the callbacks. The second thread in nouveau_cli_work_ready, where it sees the fence is signalled, so then puts the fence, cleanups the object and frees the work item, which contains the callback. Thread one goes again and tries to call the callback and causes the use-after-free. Proposed fix: lock the fence signalled check in nouveau_cli_work_ready, so either the callbacks are done or the memory is freed. Reviewed-by: Karol Herbst Fixes: 11e451e74050 ("drm/nouveau: remove fence wait code from deferred client work handler") Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie Link: https://lore.kernel.org/dri-devel/20230615024008.1600281-1-airlied@gmail.com/ Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/nouveau/nouveau_drm.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index ac96b6ab44c0..8e15ff95b809 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -124,10 +124,16 @@ nouveau_name(struct drm_device *dev) static inline bool nouveau_cli_work_ready(struct dma_fence *fence) { - if (!dma_fence_is_signaled(fence)) - return false; - dma_fence_put(fence); - return true; + bool ret = true; + + spin_lock_irq(fence->lock); + if (!dma_fence_is_signaled_locked(fence)) + ret = false; + spin_unlock_irq(fence->lock); + + if (ret == true) + dma_fence_put(fence); + return ret; } static void From d7acfd522560744ee3cf848ab16319592afdf416 Mon Sep 17 00:00:00 2001 From: Edward Srouji Date: Mon, 5 Jun 2023 13:33:24 +0300 Subject: [PATCH 3547/4345] RDMA/uverbs: Restrict usage of privileged QKEYs commit 0cadb4db79e1d9eea66711c4031e435c2191907e upstream. According to the IB specification rel-1.6, section 3.5.3: "QKEYs with the most significant bit set are considered controlled QKEYs, and a HCA does not allow a consumer to arbitrarily specify a controlled QKEY." Thus, block non-privileged users from setting such a QKEY. Cc: stable@vger.kernel.org Fixes: bc38a6abdd5a ("[PATCH] IB uverbs: core implementation") Signed-off-by: Edward Srouji Link: https://lore.kernel.org/r/c00c809ddafaaf87d6f6cb827978670989a511b3.1685960567.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/core/uverbs_cmd.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index d7c90da9ce7f..09cf470c08d6 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1842,8 +1842,13 @@ static int modify_qp(struct uverbs_attr_bundle *attrs, attr->path_mtu = cmd->base.path_mtu; if (cmd->base.attr_mask & IB_QP_PATH_MIG_STATE) attr->path_mig_state = cmd->base.path_mig_state; - if (cmd->base.attr_mask & IB_QP_QKEY) + if (cmd->base.attr_mask & IB_QP_QKEY) { + if (cmd->base.qkey & IB_QP_SET_QKEY && !capable(CAP_NET_RAW)) { + ret = -EPERM; + goto release_qp; + } attr->qkey = cmd->base.qkey; + } if (cmd->base.attr_mask & IB_QP_RQ_PSN) attr->rq_psn = cmd->base.rq_psn; if (cmd->base.attr_mask & IB_QP_SQ_PSN) From 1148d4ca3029d85bff60f975fabc66716584852c Mon Sep 17 00:00:00 2001 From: Wes Huang Date: Thu, 8 Jun 2023 11:01:42 +0800 Subject: [PATCH 3548/4345] net: usb: qmi_wwan: add support for Compal RXM-G1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 863199199713908afaa47ba09332b87621c12496 upstream. Add support for Compal RXM-G1 which is based on Qualcomm SDX55 chip. This patch adds support for two compositions: 0x9091: DIAG + MODEM + QMI_RMNET + ADB 0x90db: DIAG + DUN + RMNET + DPL + QDSS(Trace) + ADB T: Bus=03 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=5000 MxCh= 0 D: Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs= 1 P: Vendor=05c6 ProdID=9091 Rev= 4.14 S: Manufacturer=QCOM S: Product=SDXPRAIRIE-MTP _SN:719AB680 S: SerialNumber=719ab680 C:* #Ifs= 4 Cfg#= 1 Atr=80 MxPwr=896mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=(none) E: Ad=81(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan E: Ad=84(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=8e(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=0f(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) E: Ad=03(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=85(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms T: Bus=03 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=5000 MxCh= 0 D: Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs= 1 P: Vendor=05c6 ProdID=90db Rev= 4.14 S: Manufacturer=QCOM S: Product=SDXPRAIRIE-MTP _SN:719AB680 S: SerialNumber=719ab680 C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=896mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=(none) E: Ad=81(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=01(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none) E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=82(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan E: Ad=84(I) Atr=03(Int.) MxPS= 8 Ivl=32ms E: Ad=8e(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=0f(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms I:* If#= 3 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=8f(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=85(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) E: Ad=03(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=86(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms Cc: stable@vger.kernel.org Signed-off-by: Wes Huang Acked-by: Bjørn Mork Link: https://lore.kernel.org/r/20230608030141.3546-1-wes.huang@moxa.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/qmi_wwan.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 53f1cd0bfaf4..de6c56153534 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1156,7 +1156,9 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x05c6, 0x9080, 8)}, {QMI_FIXED_INTF(0x05c6, 0x9083, 3)}, {QMI_FIXED_INTF(0x05c6, 0x9084, 4)}, + {QMI_QUIRK_SET_DTR(0x05c6, 0x9091, 2)}, /* Compal RXM-G1 */ {QMI_FIXED_INTF(0x05c6, 0x90b2, 3)}, /* ublox R410M */ + {QMI_QUIRK_SET_DTR(0x05c6, 0x90db, 2)}, /* Compal RXM-G1 */ {QMI_FIXED_INTF(0x05c6, 0x920d, 0)}, {QMI_FIXED_INTF(0x05c6, 0x920d, 5)}, {QMI_QUIRK_SET_DTR(0x05c6, 0x9625, 4)}, /* YUGA CLM920-NC5 */ From e9d384983fa94eecb0320feeb91577104607ac65 Mon Sep 17 00:00:00 2001 From: Edson Juliano Drosdeck Date: Fri, 9 Jun 2023 17:10:58 -0300 Subject: [PATCH 3549/4345] ALSA: hda/realtek: Add a quirk for Compaq N14JP6 commit a2a871483161014f1bcc4e9a04354b01aa77cedb upstream. Add a quirk for Compaq N14JP6 to fixup ALC897 headset MIC no sound. Signed-off-by: Edson Juliano Drosdeck Cc: Link: https://lore.kernel.org/r/20230609201058.523499-1-edson.drosdeck@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8a42262dd7fa..7d6a36b647a7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11199,6 +11199,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1b0a, 0x01b8, "ACER Veriton", ALC662_FIXUP_ACER_VERITON), SND_PCI_QUIRK(0x1b35, 0x1234, "CZC ET26", ALC662_FIXUP_CZC_ET26), SND_PCI_QUIRK(0x1b35, 0x2206, "CZC P10T", ALC662_FIXUP_CZC_P10T), + SND_PCI_QUIRK(0x1c6c, 0x1239, "Compaq N14JP6-V2", ALC897_FIXUP_HP_HSMIC_VERB), #if 0 /* Below is a quirk table taken from the old code. From 1c004b379b0327992c1713334198cf5eba29a4ba Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Wed, 17 Aug 2022 17:43:21 -0700 Subject: [PATCH 3550/4345] Remove DECnet support from kernel commit 1202cdd665315c525b5237e96e0bedc76d7e754f upstream. DECnet is an obsolete network protocol that receives more attention from kernel janitors than users. It belongs in computer protocol history museum not in Linux kernel. It has been "Orphaned" in kernel since 2010. The iproute2 support for DECnet was dropped in 5.0 release. The documentation link on Sourceforge says it is abandoned there as well. Leave the UAPI alone to keep userspace programs compiling. This means that there is still an empty neighbour table for AF_DECNET. The table of /proc/sys/net entries was updated to match current directories and reformatted to be alphabetical. Signed-off-by: Stephen Hemminger Acked-by: David Ahern Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- .../admin-guide/kernel-parameters.txt | 4 - Documentation/admin-guide/sysctl/net.rst | 15 +- Documentation/networking/decnet.rst | 243 -- Documentation/networking/index.rst | 1 - .../userspace-api/ioctl/ioctl-number.rst | 1 - MAINTAINERS | 7 - arch/mips/configs/decstation_64_defconfig | 2 - arch/mips/configs/decstation_defconfig | 2 - arch/mips/configs/decstation_r4k_defconfig | 2 - arch/mips/configs/gpr_defconfig | 2 - arch/mips/configs/mtx1_defconfig | 2 - arch/mips/configs/nlm_xlp_defconfig | 2 - arch/mips/configs/nlm_xlr_defconfig | 2 - arch/mips/configs/rm200_defconfig | 2 - arch/powerpc/configs/ppc6xx_defconfig | 2 - include/linux/netdevice.h | 4 - include/linux/netfilter.h | 5 - include/linux/netfilter_defs.h | 8 - include/net/dn.h | 231 -- include/net/dn_dev.h | 199 -- include/net/dn_fib.h | 167 -- include/net/dn_neigh.h | 30 - include/net/dn_nsp.h | 195 -- include/net/dn_route.h | 115 - include/net/netns/netfilter.h | 3 - include/uapi/linux/dn.h | 149 - include/uapi/linux/netfilter_decnet.h | 72 - include/uapi/linux/netlink.h | 2 +- net/Kconfig | 2 - net/Makefile | 1 - net/core/dev.c | 4 +- net/core/neighbour.c | 3 - net/decnet/Kconfig | 43 - net/decnet/Makefile | 10 - net/decnet/README | 8 - net/decnet/af_decnet.c | 2400 ----------------- net/decnet/dn_dev.c | 1435 ---------- net/decnet/dn_fib.c | 799 ------ net/decnet/dn_neigh.c | 605 ----- net/decnet/dn_nsp_in.c | 906 ------- net/decnet/dn_nsp_out.c | 695 ----- net/decnet/dn_route.c | 1923 ------------- net/decnet/dn_rules.c | 258 -- net/decnet/dn_table.c | 929 ------- net/decnet/dn_timer.c | 104 - net/decnet/netfilter/Kconfig | 17 - net/decnet/netfilter/Makefile | 6 - net/decnet/netfilter/dn_rtmsg.c | 158 -- net/decnet/sysctl_net_decnet.c | 362 --- net/netfilter/core.c | 10 - 50 files changed, 10 insertions(+), 12137 deletions(-) delete mode 100644 Documentation/networking/decnet.rst delete mode 100644 include/net/dn.h delete mode 100644 include/net/dn_dev.h delete mode 100644 include/net/dn_fib.h delete mode 100644 include/net/dn_neigh.h delete mode 100644 include/net/dn_nsp.h delete mode 100644 include/net/dn_route.h delete mode 100644 include/uapi/linux/dn.h delete mode 100644 include/uapi/linux/netfilter_decnet.h delete mode 100644 net/decnet/Kconfig delete mode 100644 net/decnet/Makefile delete mode 100644 net/decnet/README delete mode 100644 net/decnet/af_decnet.c delete mode 100644 net/decnet/dn_dev.c delete mode 100644 net/decnet/dn_fib.c delete mode 100644 net/decnet/dn_neigh.c delete mode 100644 net/decnet/dn_nsp_in.c delete mode 100644 net/decnet/dn_nsp_out.c delete mode 100644 net/decnet/dn_route.c delete mode 100644 net/decnet/dn_rules.c delete mode 100644 net/decnet/dn_table.c delete mode 100644 net/decnet/dn_timer.c delete mode 100644 net/decnet/netfilter/Kconfig delete mode 100644 net/decnet/netfilter/Makefile delete mode 100644 net/decnet/netfilter/dn_rtmsg.c delete mode 100644 net/decnet/sysctl_net_decnet.c diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index eb437d659f2c..1f4a0523dc1a 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -866,10 +866,6 @@ debugpat [X86] Enable PAT debugging - decnet.addr= [HW,NET] - Format: [,] - See also Documentation/networking/decnet.rst. - default_hugepagesz= [HW] The size of the default HugeTLB page. This is the size represented by the legacy /proc/ hugepages diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 7f553859dba8..4f1a686b4b64 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -34,13 +34,14 @@ Table : Subdirectories in /proc/sys/net ========= =================== = ========== ================== Directory Content Directory Content ========= =================== = ========== ================== - core General parameter appletalk Appletalk protocol - unix Unix domain sockets netrom NET/ROM - 802 E802 protocol ax25 AX25 - ethernet Ethernet protocol rose X.25 PLP layer - ipv4 IP version 4 x25 X.25 protocol - bridge Bridging decnet DEC net - ipv6 IP version 6 tipc TIPC + 802 E802 protocol mptcp Multipath TCP + appletalk Appletalk protocol netfilter Network Filter + ax25 AX25 netrom NET/ROM + bridge Bridging rose X.25 PLP layer + core General parameter tipc TIPC + ethernet Ethernet protocol unix Unix domain sockets + ipv4 IP version 4 x25 X.25 protocol + ipv6 IP version 6 ========= =================== = ========== ================== 1. /proc/sys/net/core - Network core options diff --git a/Documentation/networking/decnet.rst b/Documentation/networking/decnet.rst deleted file mode 100644 index b8bc11ff8370..000000000000 --- a/Documentation/networking/decnet.rst +++ /dev/null @@ -1,243 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -========================================= -Linux DECnet Networking Layer Information -========================================= - -1. Other documentation.... -========================== - - - Project Home Pages - - http://www.chygwyn.com/ - Kernel info - - http://linux-decnet.sourceforge.net/ - Userland tools - - http://www.sourceforge.net/projects/linux-decnet/ - Status page - -2. Configuring the kernel -========================= - -Be sure to turn on the following options: - - - CONFIG_DECNET (obviously) - - CONFIG_PROC_FS (to see what's going on) - - CONFIG_SYSCTL (for easy configuration) - -if you want to try out router support (not properly debugged yet) -you'll need the following options as well... - - - CONFIG_DECNET_ROUTER (to be able to add/delete routes) - - CONFIG_NETFILTER (will be required for the DECnet routing daemon) - -Don't turn on SIOCGIFCONF support for DECnet unless you are really sure -that you need it, in general you won't and it can cause ifconfig to -malfunction. - -Run time configuration has changed slightly from the 2.4 system. If you -want to configure an endnode, then the simplified procedure is as follows: - - - Set the MAC address on your ethernet card before starting _any_ other - network protocols. - -As soon as your network card is brought into the UP state, DECnet should -start working. If you need something more complicated or are unsure how -to set the MAC address, see the next section. Also all configurations which -worked with 2.4 will work under 2.5 with no change. - -3. Command line options -======================= - -You can set a DECnet address on the kernel command line for compatibility -with the 2.4 configuration procedure, but in general it's not needed any more. -If you do st a DECnet address on the command line, it has only one purpose -which is that its added to the addresses on the loopback device. - -With 2.4 kernels, DECnet would only recognise addresses as local if they -were added to the loopback device. In 2.5, any local interface address -can be used to loop back to the local machine. Of course this does not -prevent you adding further addresses to the loopback device if you -want to. - -N.B. Since the address list of an interface determines the addresses for -which "hello" messages are sent, if you don't set an address on the loopback -interface then you won't see any entries in /proc/net/neigh for the local -host until such time as you start a connection. This doesn't affect the -operation of the local communications in any other way though. - -The kernel command line takes options looking like the following:: - - decnet.addr=1,2 - -the two numbers are the node address 1,2 = 1.2 For 2.2.xx kernels -and early 2.3.xx kernels, you must use a comma when specifying the -DECnet address like this. For more recent 2.3.xx kernels, you may -use almost any character except space, although a `.` would be the most -obvious choice :-) - -There used to be a third number specifying the node type. This option -has gone away in favour of a per interface node type. This is now set -using /proc/sys/net/decnet/conf//forwarding. This file can be -set with a single digit, 0=EndNode, 1=L1 Router and 2=L2 Router. - -There are also equivalent options for modules. The node address can -also be set through the /proc/sys/net/decnet/ files, as can other system -parameters. - -Currently the only supported devices are ethernet and ip_gre. The -ethernet address of your ethernet card has to be set according to the DECnet -address of the node in order for it to be autoconfigured (and then appear in -/proc/net/decnet_dev). There is a utility available at the above -FTP sites called dn2ethaddr which can compute the correct ethernet -address to use. The address can be set by ifconfig either before or -at the time the device is brought up. If you are using RedHat you can -add the line:: - - MACADDR=AA:00:04:00:03:04 - -or something similar, to /etc/sysconfig/network-scripts/ifcfg-eth0 or -wherever your network card's configuration lives. Setting the MAC address -of your ethernet card to an address starting with "hi-ord" will cause a -DECnet address which matches to be added to the interface (which you can -verify with iproute2). - -The default device for routing can be set through the /proc filesystem -by setting /proc/sys/net/decnet/default_device to the -device you want DECnet to route packets out of when no specific route -is available. Usually this will be eth0, for example:: - - echo -n "eth0" >/proc/sys/net/decnet/default_device - -If you don't set the default device, then it will default to the first -ethernet card which has been autoconfigured as described above. You can -confirm that by looking in the default_device file of course. - -There is a list of what the other files under /proc/sys/net/decnet/ do -on the kernel patch web site (shown above). - -4. Run time kernel configuration -================================ - - -This is either done through the sysctl/proc interface (see the kernel web -pages for details on what the various options do) or through the iproute2 -package in the same way as IPv4/6 configuration is performed. - -Documentation for iproute2 is included with the package, although there is -as yet no specific section on DECnet, most of the features apply to both -IP and DECnet, albeit with DECnet addresses instead of IP addresses and -a reduced functionality. - -If you want to configure a DECnet router you'll need the iproute2 package -since its the _only_ way to add and delete routes currently. Eventually -there will be a routing daemon to send and receive routing messages for -each interface and update the kernel routing tables accordingly. The -routing daemon will use netfilter to listen to routing packets, and -rtnetlink to update the kernels routing tables. - -The DECnet raw socket layer has been removed since it was there purely -for use by the routing daemon which will now use netfilter (a much cleaner -and more generic solution) instead. - -5. How can I tell if its working? -================================= - -Here is a quick guide of what to look for in order to know if your DECnet -kernel subsystem is working. - - - Is the node address set (see /proc/sys/net/decnet/node_address) - - Is the node of the correct type - (see /proc/sys/net/decnet/conf//forwarding) - - Is the Ethernet MAC address of each Ethernet card set to match - the DECnet address. If in doubt use the dn2ethaddr utility available - at the ftp archive. - - If the previous two steps are satisfied, and the Ethernet card is up, - you should find that it is listed in /proc/net/decnet_dev and also - that it appears as a directory in /proc/sys/net/decnet/conf/. The - loopback device (lo) should also appear and is required to communicate - within a node. - - If you have any DECnet routers on your network, they should appear - in /proc/net/decnet_neigh, otherwise this file will only contain the - entry for the node itself (if it doesn't check to see if lo is up). - - If you want to send to any node which is not listed in the - /proc/net/decnet_neigh file, you'll need to set the default device - to point to an Ethernet card with connection to a router. This is - again done with the /proc/sys/net/decnet/default_device file. - - Try starting a simple server and client, like the dnping/dnmirror - over the loopback interface. With luck they should communicate. - For this step and those after, you'll need the DECnet library - which can be obtained from the above ftp sites as well as the - actual utilities themselves. - - If this seems to work, then try talking to a node on your local - network, and see if you can obtain the same results. - - At this point you are on your own... :-) - -6. How to send a bug report -=========================== - -If you've found a bug and want to report it, then there are several things -you can do to help me work out exactly what it is that is wrong. Useful -information (_most_ of which _is_ _essential_) includes: - - - What kernel version are you running ? - - What version of the patch are you running ? - - How far though the above set of tests can you get ? - - What is in the /proc/decnet* files and /proc/sys/net/decnet/* files ? - - Which services are you running ? - - Which client caused the problem ? - - How much data was being transferred ? - - Was the network congested ? - - How can the problem be reproduced ? - - Can you use tcpdump to get a trace ? (N.B. Most (all?) versions of - tcpdump don't understand how to dump DECnet properly, so including - the hex listing of the packet contents is _essential_, usually the -x flag. - You may also need to increase the length grabbed with the -s flag. The - -e flag also provides very useful information (ethernet MAC addresses)) - -7. MAC FAQ -========== - -A quick FAQ on ethernet MAC addresses to explain how Linux and DECnet -interact and how to get the best performance from your hardware. - -Ethernet cards are designed to normally only pass received network frames -to a host computer when they are addressed to it, or to the broadcast address. - -Linux has an interface which allows the setting of extra addresses for -an ethernet card to listen to. If the ethernet card supports it, the -filtering operation will be done in hardware, if not the extra unwanted packets -received will be discarded by the host computer. In the latter case, -significant processor time and bus bandwidth can be used up on a busy -network (see the NAPI documentation for a longer explanation of these -effects). - -DECnet makes use of this interface to allow running DECnet on an ethernet -card which has already been configured using TCP/IP (presumably using the -built in MAC address of the card, as usual) and/or to allow multiple DECnet -addresses on each physical interface. If you do this, be aware that if your -ethernet card doesn't support perfect hashing in its MAC address filter -then your computer will be doing more work than required. Some cards -will simply set themselves into promiscuous mode in order to receive -packets from the DECnet specified addresses. So if you have one of these -cards its better to set the MAC address of the card as described above -to gain the best efficiency. Better still is to use a card which supports -NAPI as well. - - -8. Mailing list -=============== - -If you are keen to get involved in development, or want to ask questions -about configuration, or even just report bugs, then there is a mailing -list that you can join, details are at: - -http://sourceforge.net/mail/?group_id=4993 - -9. Legal Info -============= - -The Linux DECnet project team have placed their code under the GPL. The -software is provided "as is" and without warranty express or implied. -DECnet is a trademark of Compaq. This software is not a product of -Compaq. We acknowledge the help of people at Compaq in providing extra -documentation above and beyond what was previously publicly available. - -Steve Whitehouse - diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 63ef386afd0a..9fab919ed530 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -46,7 +46,6 @@ Contents: cdc_mbim dccp dctcp - decnet dns_resolver driver eql diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 55a2d9b2ce33..a7373d4e3984 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -303,7 +303,6 @@ Code Seq# Include File Comments 0x89 00-06 arch/x86/include/asm/sockios.h 0x89 0B-DF linux/sockios.h 0x89 E0-EF linux/sockios.h SIOCPROTOPRIVATE range -0x89 E0-EF linux/dn.h PROTOPRIVATE range 0x89 F0-FF linux/sockios.h SIOCDEVPRIVATE range 0x8B all linux/wireless.h 0x8C 00-3F WiNRADiO driver diff --git a/MAINTAINERS b/MAINTAINERS index 6c5efc4013ab..cdb5f1f22f4c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4905,13 +4905,6 @@ F: include/linux/tfrc.h F: include/uapi/linux/dccp.h F: net/dccp/ -DECnet NETWORK LAYER -L: linux-decnet-user@lists.sourceforge.net -S: Orphan -W: http://linux-decnet.sourceforge.net -F: Documentation/networking/decnet.rst -F: net/decnet/ - DECSTATION PLATFORM SUPPORT M: "Maciej W. Rozycki" L: linux-mips@vger.kernel.org diff --git a/arch/mips/configs/decstation_64_defconfig b/arch/mips/configs/decstation_64_defconfig index 85f1955b4b00..4a81297e21a7 100644 --- a/arch/mips/configs/decstation_64_defconfig +++ b/arch/mips/configs/decstation_64_defconfig @@ -53,8 +53,6 @@ CONFIG_IPV6_SUBTREES=y CONFIG_NETWORK_SECMARK=y CONFIG_IP_SCTP=m CONFIG_VLAN_8021Q=m -CONFIG_DECNET=m -CONFIG_DECNET_ROUTER=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set # CONFIG_FW_LOADER is not set diff --git a/arch/mips/configs/decstation_defconfig b/arch/mips/configs/decstation_defconfig index 30a6eafdb1d0..fd35454bae4c 100644 --- a/arch/mips/configs/decstation_defconfig +++ b/arch/mips/configs/decstation_defconfig @@ -49,8 +49,6 @@ CONFIG_IPV6_SUBTREES=y CONFIG_NETWORK_SECMARK=y CONFIG_IP_SCTP=m CONFIG_VLAN_8021Q=m -CONFIG_DECNET=m -CONFIG_DECNET_ROUTER=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set # CONFIG_FW_LOADER is not set diff --git a/arch/mips/configs/decstation_r4k_defconfig b/arch/mips/configs/decstation_r4k_defconfig index e2b58dbf4aa9..7ed8f4c7cbdd 100644 --- a/arch/mips/configs/decstation_r4k_defconfig +++ b/arch/mips/configs/decstation_r4k_defconfig @@ -48,8 +48,6 @@ CONFIG_IPV6_SUBTREES=y CONFIG_NETWORK_SECMARK=y CONFIG_IP_SCTP=m CONFIG_VLAN_8021Q=m -CONFIG_DECNET=m -CONFIG_DECNET_ROUTER=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set # CONFIG_FW_LOADER is not set diff --git a/arch/mips/configs/gpr_defconfig b/arch/mips/configs/gpr_defconfig index 9085f4d6c698..5b9b59a8fe68 100644 --- a/arch/mips/configs/gpr_defconfig +++ b/arch/mips/configs/gpr_defconfig @@ -69,7 +69,6 @@ CONFIG_IP_NF_RAW=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_DECNET_NF_GRABULATOR=m CONFIG_BRIDGE_NF_EBTABLES=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_T_FILTER=m @@ -99,7 +98,6 @@ CONFIG_ATM_MPOA=m CONFIG_ATM_BR2684=m CONFIG_BRIDGE=m CONFIG_VLAN_8021Q=m -CONFIG_DECNET=m CONFIG_LLC2=m CONFIG_ATALK=m CONFIG_DEV_APPLETALK=m diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index 914af125a7fa..d6578536d77c 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -117,7 +117,6 @@ CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_DECNET_NF_GRABULATOR=m CONFIG_BRIDGE_NF_EBTABLES=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_T_FILTER=m @@ -147,7 +146,6 @@ CONFIG_ATM_MPOA=m CONFIG_ATM_BR2684=m CONFIG_BRIDGE=m CONFIG_VLAN_8021Q=m -CONFIG_DECNET=m CONFIG_LLC2=m CONFIG_ATALK=m CONFIG_DEV_APPLETALK=m diff --git a/arch/mips/configs/nlm_xlp_defconfig b/arch/mips/configs/nlm_xlp_defconfig index 72a211d2d556..45421a05bb0e 100644 --- a/arch/mips/configs/nlm_xlp_defconfig +++ b/arch/mips/configs/nlm_xlp_defconfig @@ -200,7 +200,6 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m -CONFIG_DECNET_NF_GRABULATOR=m CONFIG_BRIDGE_NF_EBTABLES=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_T_FILTER=m @@ -234,7 +233,6 @@ CONFIG_ATM_BR2684=m CONFIG_BRIDGE=m CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y -CONFIG_DECNET=m CONFIG_LLC2=m CONFIG_ATALK=m CONFIG_DEV_APPLETALK=m diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig index 4ecb157e56d4..1081972c81da 100644 --- a/arch/mips/configs/nlm_xlr_defconfig +++ b/arch/mips/configs/nlm_xlr_defconfig @@ -198,7 +198,6 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m -CONFIG_DECNET_NF_GRABULATOR=m CONFIG_BRIDGE_NF_EBTABLES=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_T_FILTER=m @@ -232,7 +231,6 @@ CONFIG_ATM_BR2684=m CONFIG_BRIDGE=m CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y -CONFIG_DECNET=m CONFIG_LLC2=m CONFIG_ATALK=m CONFIG_DEV_APPLETALK=m diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig index 30d7c3db884e..2d0506159dfa 100644 --- a/arch/mips/configs/rm200_defconfig +++ b/arch/mips/configs/rm200_defconfig @@ -116,7 +116,6 @@ CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_DECNET_NF_GRABULATOR=m CONFIG_BRIDGE_NF_EBTABLES=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_T_FILTER=m @@ -137,7 +136,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m CONFIG_BRIDGE_EBT_SNAT=m CONFIG_BRIDGE_EBT_LOG=m CONFIG_BRIDGE=m -CONFIG_DECNET=m CONFIG_NET_SCHED=y CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_HTB=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 66e9a0fd64ff..021da6736570 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -245,8 +245,6 @@ CONFIG_ATM_LANE=m CONFIG_ATM_BR2684=m CONFIG_BRIDGE=m CONFIG_VLAN_8021Q=m -CONFIG_DECNET=m -CONFIG_DECNET_ROUTER=y CONFIG_ATALK=m CONFIG_DEV_APPLETALK=m CONFIG_IPDDP=m diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 24fe2cd4b0e8..8f03cc42bd43 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1759,7 +1759,6 @@ enum netdev_ml_priv_type { * @tipc_ptr: TIPC specific data * @atalk_ptr: AppleTalk link * @ip_ptr: IPv4 specific data - * @dn_ptr: DECnet specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering @@ -2038,9 +2037,6 @@ struct net_device { void *atalk_ptr; #endif struct in_device __rcu *ip_ptr; -#if IS_ENABLED(CONFIG_DECNET) - struct dn_dev __rcu *dn_ptr; -#endif struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0101747de549..8b229abf1435 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -237,11 +237,6 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, hook_head = rcu_dereference(net->nf.hooks_bridge[hook]); #endif break; -#if IS_ENABLED(CONFIG_DECNET) - case NFPROTO_DECNET: - hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); - break; -#endif default: WARN_ON_ONCE(1); break; diff --git a/include/linux/netfilter_defs.h b/include/linux/netfilter_defs.h index 8dddfb151f00..a5f7bef1b3a4 100644 --- a/include/linux/netfilter_defs.h +++ b/include/linux/netfilter_defs.h @@ -7,14 +7,6 @@ /* in/out/forward only */ #define NF_ARP_NUMHOOKS 3 -/* max hook is NF_DN_ROUTE (6), also see uapi/linux/netfilter_decnet.h */ -#define NF_DN_NUMHOOKS 7 - -#if IS_ENABLED(CONFIG_DECNET) -/* Largest hook number + 1, see uapi/linux/netfilter_decnet.h */ -#define NF_MAX_HOOKS NF_DN_NUMHOOKS -#else #define NF_MAX_HOOKS NF_INET_NUMHOOKS -#endif #endif diff --git a/include/net/dn.h b/include/net/dn.h deleted file mode 100644 index 56ab0726c641..000000000000 --- a/include/net/dn.h +++ /dev/null @@ -1,231 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_DN_H -#define _NET_DN_H - -#include -#include -#include -#include -#include - -struct dn_scp /* Session Control Port */ -{ - unsigned char state; -#define DN_O 1 /* Open */ -#define DN_CR 2 /* Connect Receive */ -#define DN_DR 3 /* Disconnect Reject */ -#define DN_DRC 4 /* Discon. Rej. Complete*/ -#define DN_CC 5 /* Connect Confirm */ -#define DN_CI 6 /* Connect Initiate */ -#define DN_NR 7 /* No resources */ -#define DN_NC 8 /* No communication */ -#define DN_CD 9 /* Connect Delivery */ -#define DN_RJ 10 /* Rejected */ -#define DN_RUN 11 /* Running */ -#define DN_DI 12 /* Disconnect Initiate */ -#define DN_DIC 13 /* Disconnect Complete */ -#define DN_DN 14 /* Disconnect Notificat */ -#define DN_CL 15 /* Closed */ -#define DN_CN 16 /* Closed Notification */ - - __le16 addrloc; - __le16 addrrem; - __u16 numdat; - __u16 numoth; - __u16 numoth_rcv; - __u16 numdat_rcv; - __u16 ackxmt_dat; - __u16 ackxmt_oth; - __u16 ackrcv_dat; - __u16 ackrcv_oth; - __u8 flowrem_sw; - __u8 flowloc_sw; -#define DN_SEND 2 -#define DN_DONTSEND 1 -#define DN_NOCHANGE 0 - __u16 flowrem_dat; - __u16 flowrem_oth; - __u16 flowloc_dat; - __u16 flowloc_oth; - __u8 services_rem; - __u8 services_loc; - __u8 info_rem; - __u8 info_loc; - - __u16 segsize_rem; - __u16 segsize_loc; - - __u8 nonagle; - __u8 multi_ireq; - __u8 accept_mode; - unsigned long seg_total; /* Running total of current segment */ - - struct optdata_dn conndata_in; - struct optdata_dn conndata_out; - struct optdata_dn discdata_in; - struct optdata_dn discdata_out; - struct accessdata_dn accessdata; - - struct sockaddr_dn addr; /* Local address */ - struct sockaddr_dn peer; /* Remote address */ - - /* - * In this case the RTT estimation is not specified in the - * docs, nor is any back off algorithm. Here we follow well - * known tcp algorithms with a few small variations. - * - * snd_window: Max number of packets we send before we wait for - * an ack to come back. This will become part of a - * more complicated scheme when we support flow - * control. - * - * nsp_srtt: Round-Trip-Time (x8) in jiffies. This is a rolling - * average. - * nsp_rttvar: Round-Trip-Time-Varience (x4) in jiffies. This is the - * varience of the smoothed average (but calculated in - * a simpler way than for normal statistical varience - * calculations). - * - * nsp_rxtshift: Backoff counter. Value is zero normally, each time - * a packet is lost is increases by one until an ack - * is received. Its used to index an array of backoff - * multipliers. - */ -#define NSP_MIN_WINDOW 1 -#define NSP_MAX_WINDOW (0x07fe) - unsigned long max_window; - unsigned long snd_window; -#define NSP_INITIAL_SRTT (HZ) - unsigned long nsp_srtt; -#define NSP_INITIAL_RTTVAR (HZ*3) - unsigned long nsp_rttvar; -#define NSP_MAXRXTSHIFT 12 - unsigned long nsp_rxtshift; - - /* - * Output queues, one for data, one for otherdata/linkservice - */ - struct sk_buff_head data_xmit_queue; - struct sk_buff_head other_xmit_queue; - - /* - * Input queue for other data - */ - struct sk_buff_head other_receive_queue; - int other_report; - - /* - * Stuff to do with the slow timer - */ - unsigned long stamp; /* time of last transmit */ - unsigned long persist; - int (*persist_fxn)(struct sock *sk); - unsigned long keepalive; - void (*keepalive_fxn)(struct sock *sk); - -}; - -static inline struct dn_scp *DN_SK(struct sock *sk) -{ - return (struct dn_scp *)(sk + 1); -} - -/* - * src,dst : Source and Destination DECnet addresses - * hops : Number of hops through the network - * dst_port, src_port : NSP port numbers - * services, info : Useful data extracted from conninit messages - * rt_flags : Routing flags byte - * nsp_flags : NSP layer flags byte - * segsize : Size of segment - * segnum : Number, for data, otherdata and linkservice - * xmit_count : Number of times we've transmitted this skb - * stamp : Time stamp of most recent transmission, used in RTT calculations - * iif: Input interface number - * - * As a general policy, this structure keeps all addresses in network - * byte order, and all else in host byte order. Thus dst, src, dst_port - * and src_port are in network order. All else is in host order. - * - */ -#define DN_SKB_CB(skb) ((struct dn_skb_cb *)(skb)->cb) -struct dn_skb_cb { - __le16 dst; - __le16 src; - __u16 hops; - __le16 dst_port; - __le16 src_port; - __u8 services; - __u8 info; - __u8 rt_flags; - __u8 nsp_flags; - __u16 segsize; - __u16 segnum; - __u16 xmit_count; - unsigned long stamp; - int iif; -}; - -static inline __le16 dn_eth2dn(unsigned char *ethaddr) -{ - return get_unaligned((__le16 *)(ethaddr + 4)); -} - -static inline __le16 dn_saddr2dn(struct sockaddr_dn *saddr) -{ - return *(__le16 *)saddr->sdn_nodeaddr; -} - -static inline void dn_dn2eth(unsigned char *ethaddr, __le16 addr) -{ - __u16 a = le16_to_cpu(addr); - ethaddr[0] = 0xAA; - ethaddr[1] = 0x00; - ethaddr[2] = 0x04; - ethaddr[3] = 0x00; - ethaddr[4] = (__u8)(a & 0xff); - ethaddr[5] = (__u8)(a >> 8); -} - -static inline void dn_sk_ports_copy(struct flowidn *fld, struct dn_scp *scp) -{ - fld->fld_sport = scp->addrloc; - fld->fld_dport = scp->addrrem; -} - -unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu); -void dn_register_sysctl(void); -void dn_unregister_sysctl(void); - -#define DN_MENUVER_ACC 0x01 -#define DN_MENUVER_USR 0x02 -#define DN_MENUVER_PRX 0x04 -#define DN_MENUVER_UIC 0x08 - -struct sock *dn_sklist_find_listener(struct sockaddr_dn *addr); -struct sock *dn_find_by_skb(struct sk_buff *skb); -#define DN_ASCBUF_LEN 9 -char *dn_addr2asc(__u16, char *); -int dn_destroy_timer(struct sock *sk); - -int dn_sockaddr2username(struct sockaddr_dn *addr, unsigned char *buf, - unsigned char type); -int dn_username2sockaddr(unsigned char *data, int len, struct sockaddr_dn *addr, - unsigned char *type); - -void dn_start_slow_timer(struct sock *sk); -void dn_stop_slow_timer(struct sock *sk); - -extern __le16 decnet_address; -extern int decnet_debug_level; -extern int decnet_time_wait; -extern int decnet_dn_count; -extern int decnet_di_count; -extern int decnet_dr_count; -extern int decnet_no_fc_max_cwnd; - -extern long sysctl_decnet_mem[3]; -extern int sysctl_decnet_wmem[3]; -extern int sysctl_decnet_rmem[3]; - -#endif /* _NET_DN_H */ diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h deleted file mode 100644 index 595b4f6c1eb1..000000000000 --- a/include/net/dn_dev.h +++ /dev/null @@ -1,199 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_DN_DEV_H -#define _NET_DN_DEV_H - - -struct dn_dev; - -struct dn_ifaddr { - struct dn_ifaddr __rcu *ifa_next; - struct dn_dev *ifa_dev; - __le16 ifa_local; - __le16 ifa_address; - __u32 ifa_flags; - __u8 ifa_scope; - char ifa_label[IFNAMSIZ]; - struct rcu_head rcu; -}; - -#define DN_DEV_S_RU 0 /* Run - working normally */ -#define DN_DEV_S_CR 1 /* Circuit Rejected */ -#define DN_DEV_S_DS 2 /* Data Link Start */ -#define DN_DEV_S_RI 3 /* Routing Layer Initialize */ -#define DN_DEV_S_RV 4 /* Routing Layer Verify */ -#define DN_DEV_S_RC 5 /* Routing Layer Complete */ -#define DN_DEV_S_OF 6 /* Off */ -#define DN_DEV_S_HA 7 /* Halt */ - - -/* - * The dn_dev_parms structure contains the set of parameters - * for each device (hence inclusion in the dn_dev structure) - * and an array is used to store the default types of supported - * device (in dn_dev.c). - * - * The type field matches the ARPHRD_ constants and is used in - * searching the list for supported devices when new devices - * come up. - * - * The mode field is used to find out if a device is broadcast, - * multipoint, or pointopoint. Please note that DECnet thinks - * different ways about devices to the rest of the kernel - * so the normal IFF_xxx flags are invalid here. For devices - * which can be any combination of the previously mentioned - * attributes, you can set this on a per device basis by - * installing an up() routine. - * - * The device state field, defines the initial state in which the - * device will come up. In the dn_dev structure, it is the actual - * state. - * - * Things have changed here. I've killed timer1 since it's a user space - * issue for a user space routing deamon to sort out. The kernel does - * not need to be bothered with it. - * - * Timers: - * t2 - Rate limit timer, min time between routing and hello messages - * t3 - Hello timer, send hello messages when it expires - * - * Callbacks: - * up() - Called to initialize device, return value can veto use of - * device with DECnet. - * down() - Called to turn device off when it goes down - * timer3() - Called once for each ifaddr when timer 3 goes off - * - * sysctl - Hook for sysctl things - * - */ -struct dn_dev_parms { - int type; /* ARPHRD_xxx */ - int mode; /* Broadcast, Unicast, Mulitpoint */ -#define DN_DEV_BCAST 1 -#define DN_DEV_UCAST 2 -#define DN_DEV_MPOINT 4 - int state; /* Initial state */ - int forwarding; /* 0=EndNode, 1=L1Router, 2=L2Router */ - unsigned long t2; /* Default value of t2 */ - unsigned long t3; /* Default value of t3 */ - int priority; /* Priority to be a router */ - char *name; /* Name for sysctl */ - int (*up)(struct net_device *); - void (*down)(struct net_device *); - void (*timer3)(struct net_device *, struct dn_ifaddr *ifa); - void *sysctl; -}; - - -struct dn_dev { - struct dn_ifaddr __rcu *ifa_list; - struct net_device *dev; - struct dn_dev_parms parms; - char use_long; - struct timer_list timer; - unsigned long t3; - struct neigh_parms *neigh_parms; - __u8 addr[ETH_ALEN]; - struct neighbour *router; /* Default router on circuit */ - struct neighbour *peer; /* Peer on pointopoint links */ - unsigned long uptime; /* Time device went up in jiffies */ -}; - -struct dn_short_packet { - __u8 msgflg; - __le16 dstnode; - __le16 srcnode; - __u8 forward; -} __packed; - -struct dn_long_packet { - __u8 msgflg; - __u8 d_area; - __u8 d_subarea; - __u8 d_id[6]; - __u8 s_area; - __u8 s_subarea; - __u8 s_id[6]; - __u8 nl2; - __u8 visit_ct; - __u8 s_class; - __u8 pt; -} __packed; - -/*------------------------- DRP - Routing messages ---------------------*/ - -struct endnode_hello_message { - __u8 msgflg; - __u8 tiver[3]; - __u8 id[6]; - __u8 iinfo; - __le16 blksize; - __u8 area; - __u8 seed[8]; - __u8 neighbor[6]; - __le16 timer; - __u8 mpd; - __u8 datalen; - __u8 data[2]; -} __packed; - -struct rtnode_hello_message { - __u8 msgflg; - __u8 tiver[3]; - __u8 id[6]; - __u8 iinfo; - __le16 blksize; - __u8 priority; - __u8 area; - __le16 timer; - __u8 mpd; -} __packed; - - -void dn_dev_init(void); -void dn_dev_cleanup(void); - -int dn_dev_ioctl(unsigned int cmd, void __user *arg); - -void dn_dev_devices_off(void); -void dn_dev_devices_on(void); - -void dn_dev_init_pkt(struct sk_buff *skb); -void dn_dev_veri_pkt(struct sk_buff *skb); -void dn_dev_hello(struct sk_buff *skb); - -void dn_dev_up(struct net_device *); -void dn_dev_down(struct net_device *); - -int dn_dev_set_default(struct net_device *dev, int force); -struct net_device *dn_dev_get_default(void); -int dn_dev_bind_default(__le16 *addr); - -int register_dnaddr_notifier(struct notifier_block *nb); -int unregister_dnaddr_notifier(struct notifier_block *nb); - -static inline int dn_dev_islocal(struct net_device *dev, __le16 addr) -{ - struct dn_dev *dn_db; - struct dn_ifaddr *ifa; - int res = 0; - - rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); - if (dn_db == NULL) { - printk(KERN_DEBUG "dn_dev_islocal: Called for non DECnet device\n"); - goto out; - } - - for (ifa = rcu_dereference(dn_db->ifa_list); - ifa != NULL; - ifa = rcu_dereference(ifa->ifa_next)) - if ((addr ^ ifa->ifa_local) == 0) { - res = 1; - break; - } -out: - rcu_read_unlock(); - return res; -} - -#endif /* _NET_DN_DEV_H */ diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h deleted file mode 100644 index ccc6e9df178b..000000000000 --- a/include/net/dn_fib.h +++ /dev/null @@ -1,167 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_DN_FIB_H -#define _NET_DN_FIB_H - -#include -#include - -extern const struct nla_policy rtm_dn_policy[]; - -struct dn_fib_res { - struct fib_rule *r; - struct dn_fib_info *fi; - unsigned char prefixlen; - unsigned char nh_sel; - unsigned char type; - unsigned char scope; -}; - -struct dn_fib_nh { - struct net_device *nh_dev; - unsigned int nh_flags; - unsigned char nh_scope; - int nh_weight; - int nh_power; - int nh_oif; - __le16 nh_gw; -}; - -struct dn_fib_info { - struct dn_fib_info *fib_next; - struct dn_fib_info *fib_prev; - int fib_treeref; - refcount_t fib_clntref; - int fib_dead; - unsigned int fib_flags; - int fib_protocol; - __le16 fib_prefsrc; - __u32 fib_priority; - __u32 fib_metrics[RTAX_MAX]; - int fib_nhs; - int fib_power; - struct dn_fib_nh fib_nh[0]; -#define dn_fib_dev fib_nh[0].nh_dev -}; - - -#define DN_FIB_RES_RESET(res) ((res).nh_sel = 0) -#define DN_FIB_RES_NH(res) ((res).fi->fib_nh[(res).nh_sel]) - -#define DN_FIB_RES_PREFSRC(res) ((res).fi->fib_prefsrc ? : __dn_fib_res_prefsrc(&res)) -#define DN_FIB_RES_GW(res) (DN_FIB_RES_NH(res).nh_gw) -#define DN_FIB_RES_DEV(res) (DN_FIB_RES_NH(res).nh_dev) -#define DN_FIB_RES_OIF(res) (DN_FIB_RES_NH(res).nh_oif) - -typedef struct { - __le16 datum; -} dn_fib_key_t; - -typedef struct { - __le16 datum; -} dn_fib_hash_t; - -typedef struct { - __u16 datum; -} dn_fib_idx_t; - -struct dn_fib_node { - struct dn_fib_node *fn_next; - struct dn_fib_info *fn_info; -#define DN_FIB_INFO(f) ((f)->fn_info) - dn_fib_key_t fn_key; - u8 fn_type; - u8 fn_scope; - u8 fn_state; -}; - - -struct dn_fib_table { - struct hlist_node hlist; - u32 n; - - int (*insert)(struct dn_fib_table *t, struct rtmsg *r, - struct nlattr *attrs[], struct nlmsghdr *n, - struct netlink_skb_parms *req); - int (*delete)(struct dn_fib_table *t, struct rtmsg *r, - struct nlattr *attrs[], struct nlmsghdr *n, - struct netlink_skb_parms *req); - int (*lookup)(struct dn_fib_table *t, const struct flowidn *fld, - struct dn_fib_res *res); - int (*flush)(struct dn_fib_table *t); - int (*dump)(struct dn_fib_table *t, struct sk_buff *skb, struct netlink_callback *cb); - - unsigned char data[]; -}; - -#ifdef CONFIG_DECNET_ROUTER -/* - * dn_fib.c - */ -void dn_fib_init(void); -void dn_fib_cleanup(void); - -int dn_fib_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); -struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, - struct nlattr *attrs[], - const struct nlmsghdr *nlh, int *errp); -int dn_fib_semantic_match(int type, struct dn_fib_info *fi, - const struct flowidn *fld, struct dn_fib_res *res); -void dn_fib_release_info(struct dn_fib_info *fi); -void dn_fib_flush(void); -void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res); - -/* - * dn_tables.c - */ -struct dn_fib_table *dn_fib_get_table(u32 n, int creat); -struct dn_fib_table *dn_fib_empty_table(void); -void dn_fib_table_init(void); -void dn_fib_table_cleanup(void); - -/* - * dn_rules.c - */ -void dn_fib_rules_init(void); -void dn_fib_rules_cleanup(void); -unsigned int dnet_addr_type(__le16 addr); -int dn_fib_lookup(struct flowidn *fld, struct dn_fib_res *res); - -int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb); - -void dn_fib_free_info(struct dn_fib_info *fi); - -static inline void dn_fib_info_put(struct dn_fib_info *fi) -{ - if (refcount_dec_and_test(&fi->fib_clntref)) - dn_fib_free_info(fi); -} - -static inline void dn_fib_res_put(struct dn_fib_res *res) -{ - if (res->fi) - dn_fib_info_put(res->fi); - if (res->r) - fib_rule_put(res->r); -} - -#else /* Endnode */ - -#define dn_fib_init() do { } while(0) -#define dn_fib_cleanup() do { } while(0) - -#define dn_fib_lookup(fl, res) (-ESRCH) -#define dn_fib_info_put(fi) do { } while(0) -#define dn_fib_select_multipath(fl, res) do { } while(0) -#define dn_fib_rules_policy(saddr,res,flags) (0) -#define dn_fib_res_put(res) do { } while(0) - -#endif /* CONFIG_DECNET_ROUTER */ - -static inline __le16 dnet_make_mask(int n) -{ - if (n) - return cpu_to_le16(~((1 << (16 - n)) - 1)); - return cpu_to_le16(0); -} - -#endif /* _NET_DN_FIB_H */ diff --git a/include/net/dn_neigh.h b/include/net/dn_neigh.h deleted file mode 100644 index 2e3e7793973a..000000000000 --- a/include/net/dn_neigh.h +++ /dev/null @@ -1,30 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NET_DN_NEIGH_H -#define _NET_DN_NEIGH_H - -/* - * The position of the first two fields of - * this structure are critical - SJW - */ -struct dn_neigh { - struct neighbour n; - __le16 addr; - unsigned long flags; -#define DN_NDFLAG_R1 0x0001 /* Router L1 */ -#define DN_NDFLAG_R2 0x0002 /* Router L2 */ -#define DN_NDFLAG_P3 0x0004 /* Phase III Node */ - unsigned long blksize; - __u8 priority; -}; - -void dn_neigh_init(void); -void dn_neigh_cleanup(void); -int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb); -int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb); -void dn_neigh_pointopoint_hello(struct sk_buff *skb); -int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n); -int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb); - -extern struct neigh_table dn_neigh_table; - -#endif /* _NET_DN_NEIGH_H */ diff --git a/include/net/dn_nsp.h b/include/net/dn_nsp.h deleted file mode 100644 index f83932b864a9..000000000000 --- a/include/net/dn_nsp.h +++ /dev/null @@ -1,195 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _NET_DN_NSP_H -#define _NET_DN_NSP_H -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - -*******************************************************************************/ -/* dn_nsp.c functions prototyping */ - -void dn_nsp_send_data_ack(struct sock *sk); -void dn_nsp_send_oth_ack(struct sock *sk); -void dn_send_conn_ack(struct sock *sk); -void dn_send_conn_conf(struct sock *sk, gfp_t gfp); -void dn_nsp_send_disc(struct sock *sk, unsigned char type, - unsigned short reason, gfp_t gfp); -void dn_nsp_return_disc(struct sk_buff *skb, unsigned char type, - unsigned short reason); -void dn_nsp_send_link(struct sock *sk, unsigned char lsflags, char fcval); -void dn_nsp_send_conninit(struct sock *sk, unsigned char flags); - -void dn_nsp_output(struct sock *sk); -int dn_nsp_check_xmit_queue(struct sock *sk, struct sk_buff *skb, - struct sk_buff_head *q, unsigned short acknum); -void dn_nsp_queue_xmit(struct sock *sk, struct sk_buff *skb, gfp_t gfp, - int oob); -unsigned long dn_nsp_persist(struct sock *sk); -int dn_nsp_xmit_timeout(struct sock *sk); - -int dn_nsp_rx(struct sk_buff *); -int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb); - -struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri); -struct sk_buff *dn_alloc_send_skb(struct sock *sk, size_t *size, int noblock, - long timeo, int *err); - -#define NSP_REASON_OK 0 /* No error */ -#define NSP_REASON_NR 1 /* No resources */ -#define NSP_REASON_UN 2 /* Unrecognised node name */ -#define NSP_REASON_SD 3 /* Node shutting down */ -#define NSP_REASON_ID 4 /* Invalid destination end user */ -#define NSP_REASON_ER 5 /* End user lacks resources */ -#define NSP_REASON_OB 6 /* Object too busy */ -#define NSP_REASON_US 7 /* Unspecified error */ -#define NSP_REASON_TP 8 /* Third-Party abort */ -#define NSP_REASON_EA 9 /* End user has aborted the link */ -#define NSP_REASON_IF 10 /* Invalid node name format */ -#define NSP_REASON_LS 11 /* Local node shutdown */ -#define NSP_REASON_LL 32 /* Node lacks logical-link resources */ -#define NSP_REASON_LE 33 /* End user lacks logical-link resources */ -#define NSP_REASON_UR 34 /* Unacceptable RQSTRID or PASSWORD field */ -#define NSP_REASON_UA 36 /* Unacceptable ACCOUNT field */ -#define NSP_REASON_TM 38 /* End user timed out logical link */ -#define NSP_REASON_NU 39 /* Node unreachable */ -#define NSP_REASON_NL 41 /* No-link message */ -#define NSP_REASON_DC 42 /* Disconnect confirm */ -#define NSP_REASON_IO 43 /* Image data field overflow */ - -#define NSP_DISCINIT 0x38 -#define NSP_DISCCONF 0x48 - -/*------------------------- NSP - messages ------------------------------*/ -/* Data Messages */ -/*---------------*/ - -/* Data Messages (data segment/interrupt/link service) */ - -struct nsp_data_seg_msg { - __u8 msgflg; - __le16 dstaddr; - __le16 srcaddr; -} __packed; - -struct nsp_data_opt_msg { - __le16 acknum; - __le16 segnum; - __le16 lsflgs; -} __packed; - -struct nsp_data_opt_msg1 { - __le16 acknum; - __le16 segnum; -} __packed; - - -/* Acknowledgment Message (data/other data) */ -struct nsp_data_ack_msg { - __u8 msgflg; - __le16 dstaddr; - __le16 srcaddr; - __le16 acknum; -} __packed; - -/* Connect Acknowledgment Message */ -struct nsp_conn_ack_msg { - __u8 msgflg; - __le16 dstaddr; -} __packed; - - -/* Connect Initiate/Retransmit Initiate/Connect Confirm */ -struct nsp_conn_init_msg { - __u8 msgflg; -#define NSP_CI 0x18 /* Connect Initiate */ -#define NSP_RCI 0x68 /* Retrans. Conn Init */ - __le16 dstaddr; - __le16 srcaddr; - __u8 services; -#define NSP_FC_NONE 0x00 /* Flow Control None */ -#define NSP_FC_SRC 0x04 /* Seg Req. Count */ -#define NSP_FC_SCMC 0x08 /* Sess. Control Mess */ -#define NSP_FC_MASK 0x0c /* FC type mask */ - __u8 info; - __le16 segsize; -} __packed; - -/* Disconnect Initiate/Disconnect Confirm */ -struct nsp_disconn_init_msg { - __u8 msgflg; - __le16 dstaddr; - __le16 srcaddr; - __le16 reason; -} __packed; - - - -struct srcobj_fmt { - __u8 format; - __u8 task; - __le16 grpcode; - __le16 usrcode; - __u8 dlen; -} __packed; - -/* - * A collection of functions for manipulating the sequence - * numbers used in NSP. Similar in operation to the functions - * of the same name in TCP. - */ -static __inline__ int dn_before(__u16 seq1, __u16 seq2) -{ - seq1 &= 0x0fff; - seq2 &= 0x0fff; - - return (int)((seq1 - seq2) & 0x0fff) > 2048; -} - - -static __inline__ int dn_after(__u16 seq1, __u16 seq2) -{ - seq1 &= 0x0fff; - seq2 &= 0x0fff; - - return (int)((seq2 - seq1) & 0x0fff) > 2048; -} - -static __inline__ int dn_equal(__u16 seq1, __u16 seq2) -{ - return ((seq1 ^ seq2) & 0x0fff) == 0; -} - -static __inline__ int dn_before_or_equal(__u16 seq1, __u16 seq2) -{ - return (dn_before(seq1, seq2) || dn_equal(seq1, seq2)); -} - -static __inline__ void seq_add(__u16 *seq, __u16 off) -{ - (*seq) += off; - (*seq) &= 0x0fff; -} - -static __inline__ int seq_next(__u16 seq1, __u16 seq2) -{ - return dn_equal(seq1 + 1, seq2); -} - -/* - * Can we delay the ack ? - */ -static __inline__ int sendack(__u16 seq) -{ - return (int)((seq & 0x1000) ? 0 : 1); -} - -/* - * Is socket congested ? - */ -static __inline__ int dn_congested(struct sock *sk) -{ - return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); -} - -#define DN_MAX_NSP_DATA_HEADER (11) - -#endif /* _NET_DN_NSP_H */ diff --git a/include/net/dn_route.h b/include/net/dn_route.h deleted file mode 100644 index 6f1e94ac0bdf..000000000000 --- a/include/net/dn_route.h +++ /dev/null @@ -1,115 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _NET_DN_ROUTE_H -#define _NET_DN_ROUTE_H - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - -*******************************************************************************/ - -struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri); -int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *, - struct sock *sk, int flags); -int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb); -void dn_rt_cache_flush(int delay); -int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev); - -/* Masks for flags field */ -#define DN_RT_F_PID 0x07 /* Mask for packet type */ -#define DN_RT_F_PF 0x80 /* Padding Follows */ -#define DN_RT_F_VER 0x40 /* Version =0 discard packet if ==1 */ -#define DN_RT_F_IE 0x20 /* Intra Ethernet, Reserved in short pkt */ -#define DN_RT_F_RTS 0x10 /* Packet is being returned to sender */ -#define DN_RT_F_RQR 0x08 /* Return packet to sender upon non-delivery */ - -/* Mask for types of routing packets */ -#define DN_RT_PKT_MSK 0x06 -/* Types of routing packets */ -#define DN_RT_PKT_SHORT 0x02 /* Short routing packet */ -#define DN_RT_PKT_LONG 0x06 /* Long routing packet */ - -/* Mask for control/routing selection */ -#define DN_RT_PKT_CNTL 0x01 /* Set to 1 if a control packet */ -/* Types of control packets */ -#define DN_RT_CNTL_MSK 0x0f /* Mask for control packets */ -#define DN_RT_PKT_INIT 0x01 /* Initialisation packet */ -#define DN_RT_PKT_VERI 0x03 /* Verification Message */ -#define DN_RT_PKT_HELO 0x05 /* Hello and Test Message */ -#define DN_RT_PKT_L1RT 0x07 /* Level 1 Routing Message */ -#define DN_RT_PKT_L2RT 0x09 /* Level 2 Routing Message */ -#define DN_RT_PKT_ERTH 0x0b /* Ethernet Router Hello */ -#define DN_RT_PKT_EEDH 0x0d /* Ethernet EndNode Hello */ - -/* Values for info field in hello message */ -#define DN_RT_INFO_TYPE 0x03 /* Type mask */ -#define DN_RT_INFO_L1RT 0x02 /* L1 Router */ -#define DN_RT_INFO_L2RT 0x01 /* L2 Router */ -#define DN_RT_INFO_ENDN 0x03 /* EndNode */ -#define DN_RT_INFO_VERI 0x04 /* Verification Reqd. */ -#define DN_RT_INFO_RJCT 0x08 /* Reject Flag, Reserved */ -#define DN_RT_INFO_VFLD 0x10 /* Verification Failed, Reserved */ -#define DN_RT_INFO_NOML 0x20 /* No Multicast traffic accepted */ -#define DN_RT_INFO_BLKR 0x40 /* Blocking Requested */ - -/* - * The fl structure is what we used to look up the route. - * The rt_saddr & rt_daddr entries are the same as key.saddr & key.daddr - * except for local input routes, where the rt_saddr = fl.fld_dst and - * rt_daddr = fl.fld_src to allow the route to be used for returning - * packets to the originating host. - */ -struct dn_route { - struct dst_entry dst; - struct dn_route __rcu *dn_next; - - struct neighbour *n; - - struct flowidn fld; - - __le16 rt_saddr; - __le16 rt_daddr; - __le16 rt_gateway; - __le16 rt_local_src; /* Source used for forwarding packets */ - __le16 rt_src_map; - __le16 rt_dst_map; - - unsigned int rt_flags; - unsigned int rt_type; -}; - -static inline bool dn_is_input_route(struct dn_route *rt) -{ - return rt->fld.flowidn_iif != 0; -} - -static inline bool dn_is_output_route(struct dn_route *rt) -{ - return rt->fld.flowidn_iif == 0; -} - -void dn_route_init(void); -void dn_route_cleanup(void); - -#include -#include - -static inline void dn_rt_send(struct sk_buff *skb) -{ - dev_queue_xmit(skb); -} - -static inline void dn_rt_finish_output(struct sk_buff *skb, char *dst, char *src) -{ - struct net_device *dev = skb->dev; - - if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK)) - dst = NULL; - - if (dev_hard_header(skb, dev, ETH_P_DNA_RT, dst, src, skb->len) >= 0) - dn_rt_send(skb); - else - kfree_skb(skb); -} - -#endif /* _NET_DN_ROUTE_H */ diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index ca043342c0eb..2e57312ac589 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -25,9 +25,6 @@ struct netns_nf { #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE struct nf_hook_entries __rcu *hooks_bridge[NF_INET_NUMHOOKS]; #endif -#if IS_ENABLED(CONFIG_DECNET) - struct nf_hook_entries __rcu *hooks_decnet[NF_DN_NUMHOOKS]; -#endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) bool defrag_ipv4; #endif diff --git a/include/uapi/linux/dn.h b/include/uapi/linux/dn.h deleted file mode 100644 index 36ca71bd8bbe..000000000000 --- a/include/uapi/linux/dn.h +++ /dev/null @@ -1,149 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _LINUX_DN_H -#define _LINUX_DN_H - -#include -#include -#include - -/* - - DECnet Data Structures and Constants - -*/ - -/* - * DNPROTO_NSP can't be the same as SOL_SOCKET, - * so increment each by one (compared to ULTRIX) - */ -#define DNPROTO_NSP 2 /* NSP protocol number */ -#define DNPROTO_ROU 3 /* Routing protocol number */ -#define DNPROTO_NML 4 /* Net mgt protocol number */ -#define DNPROTO_EVL 5 /* Evl protocol number (usr) */ -#define DNPROTO_EVR 6 /* Evl protocol number (evl) */ -#define DNPROTO_NSPT 7 /* NSP trace protocol number */ - - -#define DN_ADDL 2 -#define DN_MAXADDL 2 /* ULTRIX headers have 20 here, but pathworks has 2 */ -#define DN_MAXOPTL 16 -#define DN_MAXOBJL 16 -#define DN_MAXACCL 40 -#define DN_MAXALIASL 128 -#define DN_MAXNODEL 256 -#define DNBUFSIZE 65023 - -/* - * SET/GET Socket options - must match the DSO_ numbers below - */ -#define SO_CONDATA 1 -#define SO_CONACCESS 2 -#define SO_PROXYUSR 3 -#define SO_LINKINFO 7 - -#define DSO_CONDATA 1 /* Set/Get connect data */ -#define DSO_DISDATA 10 /* Set/Get disconnect data */ -#define DSO_CONACCESS 2 /* Set/Get connect access data */ -#define DSO_ACCEPTMODE 4 /* Set/Get accept mode */ -#define DSO_CONACCEPT 5 /* Accept deferred connection */ -#define DSO_CONREJECT 6 /* Reject deferred connection */ -#define DSO_LINKINFO 7 /* Set/Get link information */ -#define DSO_STREAM 8 /* Set socket type to stream */ -#define DSO_SEQPACKET 9 /* Set socket type to sequenced packet */ -#define DSO_MAXWINDOW 11 /* Maximum window size allowed */ -#define DSO_NODELAY 12 /* Turn off nagle */ -#define DSO_CORK 13 /* Wait for more data! */ -#define DSO_SERVICES 14 /* NSP Services field */ -#define DSO_INFO 15 /* NSP Info field */ -#define DSO_MAX 15 /* Maximum option number */ - - -/* LINK States */ -#define LL_INACTIVE 0 -#define LL_CONNECTING 1 -#define LL_RUNNING 2 -#define LL_DISCONNECTING 3 - -#define ACC_IMMED 0 -#define ACC_DEFER 1 - -#define SDF_WILD 1 /* Wild card object */ -#define SDF_PROXY 2 /* Addr eligible for proxy */ -#define SDF_UICPROXY 4 /* Use uic-based proxy */ - -/* Structures */ - - -struct dn_naddr { - __le16 a_len; - __u8 a_addr[DN_MAXADDL]; /* Two bytes little endian */ -}; - -struct sockaddr_dn { - __u16 sdn_family; - __u8 sdn_flags; - __u8 sdn_objnum; - __le16 sdn_objnamel; - __u8 sdn_objname[DN_MAXOBJL]; - struct dn_naddr sdn_add; -}; -#define sdn_nodeaddrl sdn_add.a_len /* Node address length */ -#define sdn_nodeaddr sdn_add.a_addr /* Node address */ - - - -/* - * DECnet set/get DSO_CONDATA, DSO_DISDATA (optional data) structure - */ -struct optdata_dn { - __le16 opt_status; /* Extended status return */ -#define opt_sts opt_status - __le16 opt_optl; /* Length of user data */ - __u8 opt_data[16]; /* User data */ -}; - -struct accessdata_dn { - __u8 acc_accl; - __u8 acc_acc[DN_MAXACCL]; - __u8 acc_passl; - __u8 acc_pass[DN_MAXACCL]; - __u8 acc_userl; - __u8 acc_user[DN_MAXACCL]; -}; - -/* - * DECnet logical link information structure - */ -struct linkinfo_dn { - __u16 idn_segsize; /* Segment size for link */ - __u8 idn_linkstate; /* Logical link state */ -}; - -/* - * Ethernet address format (for DECnet) - */ -union etheraddress { - __u8 dne_addr[ETH_ALEN]; /* Full ethernet address */ - struct { - __u8 dne_hiord[4]; /* DECnet HIORD prefix */ - __u8 dne_nodeaddr[2]; /* DECnet node address */ - } dne_remote; -}; - - -/* - * DECnet physical socket address format - */ -struct dn_addr { - __le16 dna_family; /* AF_DECnet */ - union etheraddress dna_netaddr; /* DECnet ethernet address */ -}; - -#define DECNET_IOCTL_BASE 0x89 /* PROTOPRIVATE range */ - -#define SIOCSNETADDR _IOW(DECNET_IOCTL_BASE, 0xe0, struct dn_naddr) -#define SIOCGNETADDR _IOR(DECNET_IOCTL_BASE, 0xe1, struct dn_naddr) -#define OSIOCSNETADDR _IOW(DECNET_IOCTL_BASE, 0xe0, int) -#define OSIOCGNETADDR _IOR(DECNET_IOCTL_BASE, 0xe1, int) - -#endif /* _LINUX_DN_H */ diff --git a/include/uapi/linux/netfilter_decnet.h b/include/uapi/linux/netfilter_decnet.h deleted file mode 100644 index 3c77f54560f2..000000000000 --- a/include/uapi/linux/netfilter_decnet.h +++ /dev/null @@ -1,72 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __LINUX_DECNET_NETFILTER_H -#define __LINUX_DECNET_NETFILTER_H - -/* DECnet-specific defines for netfilter. - * This file (C) Steve Whitehouse 1999 derived from the - * ipv4 netfilter header file which is - * (C)1998 Rusty Russell -- This code is GPL. - */ - -#include - -/* only for userspace compatibility */ -#ifndef __KERNEL__ - -#include /* for INT_MIN, INT_MAX */ - -/* kernel define is in netfilter_defs.h */ -#define NF_DN_NUMHOOKS 7 -#endif /* ! __KERNEL__ */ - -/* DECnet Hooks */ -/* After promisc drops, checksum checks. */ -#define NF_DN_PRE_ROUTING 0 -/* If the packet is destined for this box. */ -#define NF_DN_LOCAL_IN 1 -/* If the packet is destined for another interface. */ -#define NF_DN_FORWARD 2 -/* Packets coming from a local process. */ -#define NF_DN_LOCAL_OUT 3 -/* Packets about to hit the wire. */ -#define NF_DN_POST_ROUTING 4 -/* Input Hello Packets */ -#define NF_DN_HELLO 5 -/* Input Routing Packets */ -#define NF_DN_ROUTE 6 - -enum nf_dn_hook_priorities { - NF_DN_PRI_FIRST = INT_MIN, - NF_DN_PRI_CONNTRACK = -200, - NF_DN_PRI_MANGLE = -150, - NF_DN_PRI_NAT_DST = -100, - NF_DN_PRI_FILTER = 0, - NF_DN_PRI_NAT_SRC = 100, - NF_DN_PRI_DNRTMSG = 200, - NF_DN_PRI_LAST = INT_MAX, -}; - -struct nf_dn_rtmsg { - int nfdn_ifindex; -}; - -#define NFDN_RTMSG(r) ((unsigned char *)(r) + NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg))) - -#ifndef __KERNEL__ -/* backwards compatibility for userspace */ -#define DNRMG_L1_GROUP 0x01 -#define DNRMG_L2_GROUP 0x02 -#endif - -enum { - DNRNG_NLGRP_NONE, -#define DNRNG_NLGRP_NONE DNRNG_NLGRP_NONE - DNRNG_NLGRP_L1, -#define DNRNG_NLGRP_L1 DNRNG_NLGRP_L1 - DNRNG_NLGRP_L2, -#define DNRNG_NLGRP_L2 DNRNG_NLGRP_L2 - __DNRNG_NLGRP_MAX -}; -#define DNRNG_NLGRP_MAX (__DNRNG_NLGRP_MAX - 1) - -#endif /*__LINUX_DECNET_NETFILTER_H*/ diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 3d94269bbfa8..49751d5fee88 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -20,7 +20,7 @@ #define NETLINK_CONNECTOR 11 #define NETLINK_NETFILTER 12 /* netfilter subsystem */ #define NETLINK_IP6_FW 13 -#define NETLINK_DNRTMSG 14 /* DECnet routing messages */ +#define NETLINK_DNRTMSG 14 /* DECnet routing messages (obsolete) */ #define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */ #define NETLINK_GENERIC 16 /* leave room for NETLINK_DM (DM Events) */ diff --git a/net/Kconfig b/net/Kconfig index d6567162c1cf..a22c3fb88564 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -204,7 +204,6 @@ config BRIDGE_NETFILTER source "net/netfilter/Kconfig" source "net/ipv4/netfilter/Kconfig" source "net/ipv6/netfilter/Kconfig" -source "net/decnet/netfilter/Kconfig" source "net/bridge/netfilter/Kconfig" endif @@ -221,7 +220,6 @@ source "net/802/Kconfig" source "net/bridge/Kconfig" source "net/dsa/Kconfig" source "net/8021q/Kconfig" -source "net/decnet/Kconfig" source "net/llc/Kconfig" source "drivers/net/appletalk/Kconfig" source "net/x25/Kconfig" diff --git a/net/Makefile b/net/Makefile index 5744bf1997fd..45c03aa92ace 100644 --- a/net/Makefile +++ b/net/Makefile @@ -39,7 +39,6 @@ obj-$(CONFIG_AF_KCM) += kcm/ obj-$(CONFIG_STREAM_PARSER) += strparser/ obj-$(CONFIG_ATM) += atm/ obj-$(CONFIG_L2TP) += l2tp/ -obj-$(CONFIG_DECNET) += decnet/ obj-$(CONFIG_PHONET) += phonet/ ifneq ($(CONFIG_VLAN_8021Q),) obj-y += 8021q/ diff --git a/net/core/dev.c b/net/core/dev.c index f4aad9b00cc9..3fc27b52bf42 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10300,9 +10300,7 @@ void netdev_run_todo(void) BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); -#if IS_ENABLED(CONFIG_DECNET) - WARN_ON(dev->dn_ptr); -#endif + if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 82ccc3eebe71..6addfb4fff72 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1802,9 +1802,6 @@ static struct neigh_table *neigh_find_table(int family) case AF_INET6: tbl = neigh_tables[NEIGH_ND_TABLE]; break; - case AF_DECnet: - tbl = neigh_tables[NEIGH_DN_TABLE]; - break; } return tbl; diff --git a/net/decnet/Kconfig b/net/decnet/Kconfig deleted file mode 100644 index 24336bdb1054..000000000000 --- a/net/decnet/Kconfig +++ /dev/null @@ -1,43 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# DECnet configuration -# -config DECNET - tristate "DECnet Support" - help - The DECnet networking protocol was used in many products made by - Digital (now Compaq). It provides reliable stream and sequenced - packet communications over which run a variety of services similar - to those which run over TCP/IP. - - To find some tools to use with the kernel layer support, please - look at Patrick Caulfield's web site: - . - - More detailed documentation is available in - . - - Be sure to say Y to "/proc file system support" and "Sysctl support" - below when using DECnet, since you will need sysctl support to aid - in configuration at run time. - - The DECnet code is also available as a module ( = code which can be - inserted in and removed from the running kernel whenever you want). - The module is called decnet. - -config DECNET_ROUTER - bool "DECnet: router support" - depends on DECNET - select FIB_RULES - help - Add support for turning your DECnet Endnode into a level 1 or 2 - router. This is an experimental, but functional option. If you - do say Y here, then make sure that you also say Y to "Kernel/User - network link driver", "Routing messages" and "Network packet - filtering". The first two are required to allow configuration via - rtnetlink (you will need Alexey Kuznetsov's iproute2 package - from ). The "Network packet - filtering" option will be required for the forthcoming routing daemon - to work. - - See for more information. diff --git a/net/decnet/Makefile b/net/decnet/Makefile deleted file mode 100644 index 07b38e441b2d..000000000000 --- a/net/decnet/Makefile +++ /dev/null @@ -1,10 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -obj-$(CONFIG_DECNET) += decnet.o - -decnet-y := af_decnet.o dn_nsp_in.o dn_nsp_out.o \ - dn_route.o dn_dev.o dn_neigh.o dn_timer.o -decnet-$(CONFIG_DECNET_ROUTER) += dn_fib.o dn_rules.o dn_table.o -decnet-y += sysctl_net_decnet.o - -obj-$(CONFIG_NETFILTER) += netfilter/ diff --git a/net/decnet/README b/net/decnet/README deleted file mode 100644 index 60e7ec88c81f..000000000000 --- a/net/decnet/README +++ /dev/null @@ -1,8 +0,0 @@ - Linux DECnet Project - ====================== - -The documentation for this kernel subsystem is available in the -Documentation/networking subdirectory of this distribution and also -on line at http://www.chygwyn.com/DECnet/ - -Steve Whitehouse diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c deleted file mode 100644 index 7d542eb46172..000000000000 --- a/net/decnet/af_decnet.c +++ /dev/null @@ -1,2400 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later - -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Socket Layer Interface - * - * Authors: Eduardo Marcelo Serrat - * Patrick Caulfield - * - * Changes: - * Steve Whitehouse: Copied from Eduardo Serrat and Patrick Caulfield's - * version of the code. Original copyright preserved - * below. - * Steve Whitehouse: Some bug fixes, cleaning up some code to make it - * compatible with my routing layer. - * Steve Whitehouse: Merging changes from Eduardo Serrat and Patrick - * Caulfield. - * Steve Whitehouse: Further bug fixes, checking module code still works - * with new routing layer. - * Steve Whitehouse: Additional set/get_sockopt() calls. - * Steve Whitehouse: Fixed TIOCINQ ioctl to be same as Eduardo's new - * code. - * Steve Whitehouse: recvmsg() changed to try and behave in a POSIX like - * way. Didn't manage it entirely, but its better. - * Steve Whitehouse: ditto for sendmsg(). - * Steve Whitehouse: A selection of bug fixes to various things. - * Steve Whitehouse: Added TIOCOUTQ ioctl. - * Steve Whitehouse: Fixes to username2sockaddr & sockaddr2username. - * Steve Whitehouse: Fixes to connect() error returns. - * Patrick Caulfield: Fixes to delayed acceptance logic. - * David S. Miller: New socket locking - * Steve Whitehouse: Socket list hashing/locking - * Arnaldo C. Melo: use capable, not suser - * Steve Whitehouse: Removed unused code. Fix to use sk->allocation - * when required. - * Patrick Caulfield: /proc/net/decnet now has object name/number - * Steve Whitehouse: Fixed local port allocation, hashed sk list - * Matthew Wilcox: Fixes for dn_ioctl() - * Steve Whitehouse: New connect/accept logic to allow timeouts and - * prepare for sendpage etc. - */ - - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - - -HISTORY: - -Version Kernel Date Author/Comments -------- ------ ---- --------------- -Version 0.0.1 2.0.30 01-dic-97 Eduardo Marcelo Serrat - (emserrat@geocities.com) - - First Development of DECnet Socket La- - yer for Linux. Only supports outgoing - connections. - -Version 0.0.2 2.1.105 20-jun-98 Patrick J. Caulfield - (patrick@pandh.demon.co.uk) - - Port to new kernel development version. - -Version 0.0.3 2.1.106 25-jun-98 Eduardo Marcelo Serrat - (emserrat@geocities.com) - _ - Added support for incoming connections - so we can start developing server apps - on Linux. - - - Module Support -Version 0.0.4 2.1.109 21-jul-98 Eduardo Marcelo Serrat - (emserrat@geocities.com) - _ - Added support for X11R6.4. Now we can - use DECnet transport for X on Linux!!! - - -Version 0.0.5 2.1.110 01-aug-98 Eduardo Marcelo Serrat - (emserrat@geocities.com) - Removed bugs on flow control - Removed bugs on incoming accessdata - order - - -Version 0.0.6 2.1.110 07-aug-98 Eduardo Marcelo Serrat - dn_recvmsg fixes - - Patrick J. Caulfield - dn_bind fixes -*******************************************************************************/ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -struct dn_sock { - struct sock sk; - struct dn_scp scp; -}; - -static void dn_keepalive(struct sock *sk); - -#define DN_SK_HASH_SHIFT 8 -#define DN_SK_HASH_SIZE (1 << DN_SK_HASH_SHIFT) -#define DN_SK_HASH_MASK (DN_SK_HASH_SIZE - 1) - - -static const struct proto_ops dn_proto_ops; -static DEFINE_RWLOCK(dn_hash_lock); -static struct hlist_head dn_sk_hash[DN_SK_HASH_SIZE]; -static struct hlist_head dn_wild_sk; -static atomic_long_t decnet_memory_allocated; - -static int __dn_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int optlen, int flags); -static int __dn_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen, int flags); - -static struct hlist_head *dn_find_list(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->addr.sdn_flags & SDF_WILD) - return hlist_empty(&dn_wild_sk) ? &dn_wild_sk : NULL; - - return &dn_sk_hash[le16_to_cpu(scp->addrloc) & DN_SK_HASH_MASK]; -} - -/* - * Valid ports are those greater than zero and not already in use. - */ -static int check_port(__le16 port) -{ - struct sock *sk; - - if (port == 0) - return -1; - - sk_for_each(sk, &dn_sk_hash[le16_to_cpu(port) & DN_SK_HASH_MASK]) { - struct dn_scp *scp = DN_SK(sk); - if (scp->addrloc == port) - return -1; - } - return 0; -} - -static unsigned short port_alloc(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - static unsigned short port = 0x2000; - unsigned short i_port = port; - - while(check_port(cpu_to_le16(++port)) != 0) { - if (port == i_port) - return 0; - } - - scp->addrloc = cpu_to_le16(port); - - return 1; -} - -/* - * Since this is only ever called from user - * level, we don't need a write_lock() version - * of this. - */ -static int dn_hash_sock(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - struct hlist_head *list; - int rv = -EUSERS; - - BUG_ON(sk_hashed(sk)); - - write_lock_bh(&dn_hash_lock); - - if (!scp->addrloc && !port_alloc(sk)) - goto out; - - rv = -EADDRINUSE; - if ((list = dn_find_list(sk)) == NULL) - goto out; - - sk_add_node(sk, list); - rv = 0; -out: - write_unlock_bh(&dn_hash_lock); - return rv; -} - -static void dn_unhash_sock(struct sock *sk) -{ - write_lock(&dn_hash_lock); - sk_del_node_init(sk); - write_unlock(&dn_hash_lock); -} - -static void dn_unhash_sock_bh(struct sock *sk) -{ - write_lock_bh(&dn_hash_lock); - sk_del_node_init(sk); - write_unlock_bh(&dn_hash_lock); -} - -static struct hlist_head *listen_hash(struct sockaddr_dn *addr) -{ - int i; - unsigned int hash = addr->sdn_objnum; - - if (hash == 0) { - hash = addr->sdn_objnamel; - for(i = 0; i < le16_to_cpu(addr->sdn_objnamel); i++) { - hash ^= addr->sdn_objname[i]; - hash ^= (hash << 3); - } - } - - return &dn_sk_hash[hash & DN_SK_HASH_MASK]; -} - -/* - * Called to transform a socket from bound (i.e. with a local address) - * into a listening socket (doesn't need a local port number) and rehashes - * based upon the object name/number. - */ -static void dn_rehash_sock(struct sock *sk) -{ - struct hlist_head *list; - struct dn_scp *scp = DN_SK(sk); - - if (scp->addr.sdn_flags & SDF_WILD) - return; - - write_lock_bh(&dn_hash_lock); - sk_del_node_init(sk); - DN_SK(sk)->addrloc = 0; - list = listen_hash(&DN_SK(sk)->addr); - sk_add_node(sk, list); - write_unlock_bh(&dn_hash_lock); -} - -int dn_sockaddr2username(struct sockaddr_dn *sdn, unsigned char *buf, unsigned char type) -{ - int len = 2; - - *buf++ = type; - - switch (type) { - case 0: - *buf++ = sdn->sdn_objnum; - break; - case 1: - *buf++ = 0; - *buf++ = le16_to_cpu(sdn->sdn_objnamel); - memcpy(buf, sdn->sdn_objname, le16_to_cpu(sdn->sdn_objnamel)); - len = 3 + le16_to_cpu(sdn->sdn_objnamel); - break; - case 2: - memset(buf, 0, 5); - buf += 5; - *buf++ = le16_to_cpu(sdn->sdn_objnamel); - memcpy(buf, sdn->sdn_objname, le16_to_cpu(sdn->sdn_objnamel)); - len = 7 + le16_to_cpu(sdn->sdn_objnamel); - break; - } - - return len; -} - -/* - * On reception of usernames, we handle types 1 and 0 for destination - * addresses only. Types 2 and 4 are used for source addresses, but the - * UIC, GIC are ignored and they are both treated the same way. Type 3 - * is never used as I've no idea what its purpose might be or what its - * format is. - */ -int dn_username2sockaddr(unsigned char *data, int len, struct sockaddr_dn *sdn, unsigned char *fmt) -{ - unsigned char type; - int size = len; - int namel = 12; - - sdn->sdn_objnum = 0; - sdn->sdn_objnamel = cpu_to_le16(0); - memset(sdn->sdn_objname, 0, DN_MAXOBJL); - - if (len < 2) - return -1; - - len -= 2; - *fmt = *data++; - type = *data++; - - switch (*fmt) { - case 0: - sdn->sdn_objnum = type; - return 2; - case 1: - namel = 16; - break; - case 2: - len -= 4; - data += 4; - break; - case 4: - len -= 8; - data += 8; - break; - default: - return -1; - } - - len -= 1; - - if (len < 0) - return -1; - - sdn->sdn_objnamel = cpu_to_le16(*data++); - len -= le16_to_cpu(sdn->sdn_objnamel); - - if ((len < 0) || (le16_to_cpu(sdn->sdn_objnamel) > namel)) - return -1; - - memcpy(sdn->sdn_objname, data, le16_to_cpu(sdn->sdn_objnamel)); - - return size - len; -} - -struct sock *dn_sklist_find_listener(struct sockaddr_dn *addr) -{ - struct hlist_head *list = listen_hash(addr); - struct sock *sk; - - read_lock(&dn_hash_lock); - sk_for_each(sk, list) { - struct dn_scp *scp = DN_SK(sk); - if (sk->sk_state != TCP_LISTEN) - continue; - if (scp->addr.sdn_objnum) { - if (scp->addr.sdn_objnum != addr->sdn_objnum) - continue; - } else { - if (addr->sdn_objnum) - continue; - if (scp->addr.sdn_objnamel != addr->sdn_objnamel) - continue; - if (memcmp(scp->addr.sdn_objname, addr->sdn_objname, le16_to_cpu(addr->sdn_objnamel)) != 0) - continue; - } - sock_hold(sk); - read_unlock(&dn_hash_lock); - return sk; - } - - sk = sk_head(&dn_wild_sk); - if (sk) { - if (sk->sk_state == TCP_LISTEN) - sock_hold(sk); - else - sk = NULL; - } - - read_unlock(&dn_hash_lock); - return sk; -} - -struct sock *dn_find_by_skb(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct sock *sk; - struct dn_scp *scp; - - read_lock(&dn_hash_lock); - sk_for_each(sk, &dn_sk_hash[le16_to_cpu(cb->dst_port) & DN_SK_HASH_MASK]) { - scp = DN_SK(sk); - if (cb->src != dn_saddr2dn(&scp->peer)) - continue; - if (cb->dst_port != scp->addrloc) - continue; - if (scp->addrrem && (cb->src_port != scp->addrrem)) - continue; - sock_hold(sk); - goto found; - } - sk = NULL; -found: - read_unlock(&dn_hash_lock); - return sk; -} - - - -static void dn_destruct(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - skb_queue_purge(&scp->data_xmit_queue); - skb_queue_purge(&scp->other_xmit_queue); - skb_queue_purge(&scp->other_receive_queue); - - dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); -} - -static unsigned long dn_memory_pressure; - -static void dn_enter_memory_pressure(struct sock *sk) -{ - if (!dn_memory_pressure) { - dn_memory_pressure = 1; - } -} - -static struct proto dn_proto = { - .name = "NSP", - .owner = THIS_MODULE, - .enter_memory_pressure = dn_enter_memory_pressure, - .memory_pressure = &dn_memory_pressure, - .memory_allocated = &decnet_memory_allocated, - .sysctl_mem = sysctl_decnet_mem, - .sysctl_wmem = sysctl_decnet_wmem, - .sysctl_rmem = sysctl_decnet_rmem, - .max_header = DN_MAX_NSP_DATA_HEADER + 64, - .obj_size = sizeof(struct dn_sock), -}; - -static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gfp, int kern) -{ - struct dn_scp *scp; - struct sock *sk = sk_alloc(net, PF_DECnet, gfp, &dn_proto, kern); - - if (!sk) - goto out; - - if (sock) - sock->ops = &dn_proto_ops; - sock_init_data(sock, sk); - - sk->sk_backlog_rcv = dn_nsp_backlog_rcv; - sk->sk_destruct = dn_destruct; - sk->sk_no_check_tx = 1; - sk->sk_family = PF_DECnet; - sk->sk_protocol = 0; - sk->sk_allocation = gfp; - sk->sk_sndbuf = READ_ONCE(sysctl_decnet_wmem[1]); - sk->sk_rcvbuf = READ_ONCE(sysctl_decnet_rmem[1]); - - /* Initialization of DECnet Session Control Port */ - scp = DN_SK(sk); - scp->state = DN_O; /* Open */ - scp->numdat = 1; /* Next data seg to tx */ - scp->numoth = 1; /* Next oth data to tx */ - scp->ackxmt_dat = 0; /* Last data seg ack'ed */ - scp->ackxmt_oth = 0; /* Last oth data ack'ed */ - scp->ackrcv_dat = 0; /* Highest data ack recv*/ - scp->ackrcv_oth = 0; /* Last oth data ack rec*/ - scp->flowrem_sw = DN_SEND; - scp->flowloc_sw = DN_SEND; - scp->flowrem_dat = 0; - scp->flowrem_oth = 1; - scp->flowloc_dat = 0; - scp->flowloc_oth = 1; - scp->services_rem = 0; - scp->services_loc = 1 | NSP_FC_NONE; - scp->info_rem = 0; - scp->info_loc = 0x03; /* NSP version 4.1 */ - scp->segsize_rem = 230 - DN_MAX_NSP_DATA_HEADER; /* Default: Updated by remote segsize */ - scp->nonagle = 0; - scp->multi_ireq = 1; - scp->accept_mode = ACC_IMMED; - scp->addr.sdn_family = AF_DECnet; - scp->peer.sdn_family = AF_DECnet; - scp->accessdata.acc_accl = 5; - memcpy(scp->accessdata.acc_acc, "LINUX", 5); - - scp->max_window = NSP_MAX_WINDOW; - scp->snd_window = NSP_MIN_WINDOW; - scp->nsp_srtt = NSP_INITIAL_SRTT; - scp->nsp_rttvar = NSP_INITIAL_RTTVAR; - scp->nsp_rxtshift = 0; - - skb_queue_head_init(&scp->data_xmit_queue); - skb_queue_head_init(&scp->other_xmit_queue); - skb_queue_head_init(&scp->other_receive_queue); - - scp->persist = 0; - scp->persist_fxn = NULL; - scp->keepalive = 10 * HZ; - scp->keepalive_fxn = dn_keepalive; - - dn_start_slow_timer(sk); -out: - return sk; -} - -/* - * Keepalive timer. - * FIXME: Should respond to SO_KEEPALIVE etc. - */ -static void dn_keepalive(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - /* - * By checking the other_data transmit queue is empty - * we are double checking that we are not sending too - * many of these keepalive frames. - */ - if (skb_queue_empty(&scp->other_xmit_queue)) - dn_nsp_send_link(sk, DN_NOCHANGE, 0); -} - - -/* - * Timer for shutdown/destroyed sockets. - * When socket is dead & no packets have been sent for a - * certain amount of time, they are removed by this - * routine. Also takes care of sending out DI & DC - * frames at correct times. - */ -int dn_destroy_timer(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - scp->persist = dn_nsp_persist(sk); - - switch (scp->state) { - case DN_DI: - dn_nsp_send_disc(sk, NSP_DISCINIT, 0, GFP_ATOMIC); - if (scp->nsp_rxtshift >= decnet_di_count) - scp->state = DN_CN; - return 0; - - case DN_DR: - dn_nsp_send_disc(sk, NSP_DISCINIT, 0, GFP_ATOMIC); - if (scp->nsp_rxtshift >= decnet_dr_count) - scp->state = DN_DRC; - return 0; - - case DN_DN: - if (scp->nsp_rxtshift < decnet_dn_count) { - /* printk(KERN_DEBUG "dn_destroy_timer: DN\n"); */ - dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, - GFP_ATOMIC); - return 0; - } - } - - scp->persist = (HZ * decnet_time_wait); - - if (sk->sk_socket) - return 0; - - if (time_after_eq(jiffies, scp->stamp + HZ * decnet_time_wait)) { - dn_unhash_sock(sk); - sock_put(sk); - return 1; - } - - return 0; -} - -static void dn_destroy_sock(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - scp->nsp_rxtshift = 0; /* reset back off */ - - if (sk->sk_socket) { - if (sk->sk_socket->state != SS_UNCONNECTED) - sk->sk_socket->state = SS_DISCONNECTING; - } - - sk->sk_state = TCP_CLOSE; - - switch (scp->state) { - case DN_DN: - dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, - sk->sk_allocation); - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - break; - case DN_CR: - scp->state = DN_DR; - goto disc_reject; - case DN_RUN: - scp->state = DN_DI; - fallthrough; - case DN_DI: - case DN_DR: -disc_reject: - dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation); - fallthrough; - case DN_NC: - case DN_NR: - case DN_RJ: - case DN_DIC: - case DN_CN: - case DN_DRC: - case DN_CI: - case DN_CD: - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - break; - default: - printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n"); - fallthrough; - case DN_O: - dn_stop_slow_timer(sk); - - dn_unhash_sock_bh(sk); - sock_put(sk); - - break; - } -} - -char *dn_addr2asc(__u16 addr, char *buf) -{ - unsigned short node, area; - - node = addr & 0x03ff; - area = addr >> 10; - sprintf(buf, "%hd.%hd", area, node); - - return buf; -} - - - -static int dn_create(struct net *net, struct socket *sock, int protocol, - int kern) -{ - struct sock *sk; - - if (protocol < 0 || protocol > U8_MAX) - return -EINVAL; - - if (!net_eq(net, &init_net)) - return -EAFNOSUPPORT; - - switch (sock->type) { - case SOCK_SEQPACKET: - if (protocol != DNPROTO_NSP) - return -EPROTONOSUPPORT; - break; - case SOCK_STREAM: - break; - default: - return -ESOCKTNOSUPPORT; - } - - - if ((sk = dn_alloc_sock(net, sock, GFP_KERNEL, kern)) == NULL) - return -ENOBUFS; - - sk->sk_protocol = protocol; - - return 0; -} - - -static int -dn_release(struct socket *sock) -{ - struct sock *sk = sock->sk; - - if (sk) { - sock_orphan(sk); - sock_hold(sk); - lock_sock(sk); - dn_destroy_sock(sk); - release_sock(sk); - sock_put(sk); - } - - return 0; -} - -static int dn_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - struct sockaddr_dn *saddr = (struct sockaddr_dn *)uaddr; - struct net_device *dev, *ldev; - int rv; - - if (addr_len != sizeof(struct sockaddr_dn)) - return -EINVAL; - - if (saddr->sdn_family != AF_DECnet) - return -EINVAL; - - if (le16_to_cpu(saddr->sdn_nodeaddrl) && (le16_to_cpu(saddr->sdn_nodeaddrl) != 2)) - return -EINVAL; - - if (le16_to_cpu(saddr->sdn_objnamel) > DN_MAXOBJL) - return -EINVAL; - - if (saddr->sdn_flags & ~SDF_WILD) - return -EINVAL; - - if (!capable(CAP_NET_BIND_SERVICE) && (saddr->sdn_objnum || - (saddr->sdn_flags & SDF_WILD))) - return -EACCES; - - if (!(saddr->sdn_flags & SDF_WILD)) { - if (le16_to_cpu(saddr->sdn_nodeaddrl)) { - rcu_read_lock(); - ldev = NULL; - for_each_netdev_rcu(&init_net, dev) { - if (!dev->dn_ptr) - continue; - if (dn_dev_islocal(dev, dn_saddr2dn(saddr))) { - ldev = dev; - break; - } - } - rcu_read_unlock(); - if (ldev == NULL) - return -EADDRNOTAVAIL; - } - } - - rv = -EINVAL; - lock_sock(sk); - if (sock_flag(sk, SOCK_ZAPPED)) { - memcpy(&scp->addr, saddr, addr_len); - sock_reset_flag(sk, SOCK_ZAPPED); - - rv = dn_hash_sock(sk); - if (rv) - sock_set_flag(sk, SOCK_ZAPPED); - } - release_sock(sk); - - return rv; -} - - -static int dn_auto_bind(struct socket *sock) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - int rv; - - sock_reset_flag(sk, SOCK_ZAPPED); - - scp->addr.sdn_flags = 0; - scp->addr.sdn_objnum = 0; - - /* - * This stuff is to keep compatibility with Eduardo's - * patch. I hope I can dispense with it shortly... - */ - if ((scp->accessdata.acc_accl != 0) && - (scp->accessdata.acc_accl <= 12)) { - - scp->addr.sdn_objnamel = cpu_to_le16(scp->accessdata.acc_accl); - memcpy(scp->addr.sdn_objname, scp->accessdata.acc_acc, le16_to_cpu(scp->addr.sdn_objnamel)); - - scp->accessdata.acc_accl = 0; - memset(scp->accessdata.acc_acc, 0, 40); - } - /* End of compatibility stuff */ - - scp->addr.sdn_add.a_len = cpu_to_le16(2); - rv = dn_dev_bind_default((__le16 *)scp->addr.sdn_add.a_addr); - if (rv == 0) { - rv = dn_hash_sock(sk); - if (rv) - sock_set_flag(sk, SOCK_ZAPPED); - } - - return rv; -} - -static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) -{ - struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int err; - - if (scp->state != DN_CR) - return -EINVAL; - - scp->state = DN_CC; - scp->segsize_loc = dst_metric_advmss(__sk_dst_get(sk)); - dn_send_conn_conf(sk, allocation); - - add_wait_queue(sk_sleep(sk), &wait); - for(;;) { - release_sock(sk); - if (scp->state == DN_CC) - *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); - lock_sock(sk); - err = 0; - if (scp->state == DN_RUN) - break; - err = sock_error(sk); - if (err) - break; - err = sock_intr_errno(*timeo); - if (signal_pending(current)) - break; - err = -EAGAIN; - if (!*timeo) - break; - } - remove_wait_queue(sk_sleep(sk), &wait); - if (err == 0) { - sk->sk_socket->state = SS_CONNECTED; - } else if (scp->state != DN_CC) { - sk->sk_socket->state = SS_UNCONNECTED; - } - return err; -} - -static int dn_wait_run(struct sock *sk, long *timeo) -{ - struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int err = 0; - - if (scp->state == DN_RUN) - goto out; - - if (!*timeo) - return -EALREADY; - - add_wait_queue(sk_sleep(sk), &wait); - for(;;) { - release_sock(sk); - if (scp->state == DN_CI || scp->state == DN_CC) - *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); - lock_sock(sk); - err = 0; - if (scp->state == DN_RUN) - break; - err = sock_error(sk); - if (err) - break; - err = sock_intr_errno(*timeo); - if (signal_pending(current)) - break; - err = -ETIMEDOUT; - if (!*timeo) - break; - } - remove_wait_queue(sk_sleep(sk), &wait); -out: - if (err == 0) { - sk->sk_socket->state = SS_CONNECTED; - } else if (scp->state != DN_CI && scp->state != DN_CC) { - sk->sk_socket->state = SS_UNCONNECTED; - } - return err; -} - -static int __dn_connect(struct sock *sk, struct sockaddr_dn *addr, int addrlen, long *timeo, int flags) -{ - struct socket *sock = sk->sk_socket; - struct dn_scp *scp = DN_SK(sk); - int err = -EISCONN; - struct flowidn fld; - struct dst_entry *dst; - - if (sock->state == SS_CONNECTED) - goto out; - - if (sock->state == SS_CONNECTING) { - err = 0; - if (scp->state == DN_RUN) { - sock->state = SS_CONNECTED; - goto out; - } - err = -ECONNREFUSED; - if (scp->state != DN_CI && scp->state != DN_CC) { - sock->state = SS_UNCONNECTED; - goto out; - } - return dn_wait_run(sk, timeo); - } - - err = -EINVAL; - if (scp->state != DN_O) - goto out; - - if (addr == NULL || addrlen != sizeof(struct sockaddr_dn)) - goto out; - if (addr->sdn_family != AF_DECnet) - goto out; - if (addr->sdn_flags & SDF_WILD) - goto out; - - if (sock_flag(sk, SOCK_ZAPPED)) { - err = dn_auto_bind(sk->sk_socket); - if (err) - goto out; - } - - memcpy(&scp->peer, addr, sizeof(struct sockaddr_dn)); - - err = -EHOSTUNREACH; - memset(&fld, 0, sizeof(fld)); - fld.flowidn_oif = sk->sk_bound_dev_if; - fld.daddr = dn_saddr2dn(&scp->peer); - fld.saddr = dn_saddr2dn(&scp->addr); - dn_sk_ports_copy(&fld, scp); - fld.flowidn_proto = DNPROTO_NSP; - if (dn_route_output_sock(&sk->sk_dst_cache, &fld, sk, flags) < 0) - goto out; - dst = __sk_dst_get(sk); - sk->sk_route_caps = dst->dev->features; - sock->state = SS_CONNECTING; - scp->state = DN_CI; - scp->segsize_loc = dst_metric_advmss(dst); - - dn_nsp_send_conninit(sk, NSP_CI); - err = -EINPROGRESS; - if (*timeo) { - err = dn_wait_run(sk, timeo); - } -out: - return err; -} - -static int dn_connect(struct socket *sock, struct sockaddr *uaddr, int addrlen, int flags) -{ - struct sockaddr_dn *addr = (struct sockaddr_dn *)uaddr; - struct sock *sk = sock->sk; - int err; - long timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); - - lock_sock(sk); - err = __dn_connect(sk, addr, addrlen, &timeo, 0); - release_sock(sk); - - return err; -} - -static inline int dn_check_state(struct sock *sk, struct sockaddr_dn *addr, int addrlen, long *timeo, int flags) -{ - struct dn_scp *scp = DN_SK(sk); - - switch (scp->state) { - case DN_RUN: - return 0; - case DN_CR: - return dn_confirm_accept(sk, timeo, sk->sk_allocation); - case DN_CI: - case DN_CC: - return dn_wait_run(sk, timeo); - case DN_O: - return __dn_connect(sk, addr, addrlen, timeo, flags); - } - - return -EINVAL; -} - - -static void dn_access_copy(struct sk_buff *skb, struct accessdata_dn *acc) -{ - unsigned char *ptr = skb->data; - - acc->acc_userl = *ptr++; - memcpy(&acc->acc_user, ptr, acc->acc_userl); - ptr += acc->acc_userl; - - acc->acc_passl = *ptr++; - memcpy(&acc->acc_pass, ptr, acc->acc_passl); - ptr += acc->acc_passl; - - acc->acc_accl = *ptr++; - memcpy(&acc->acc_acc, ptr, acc->acc_accl); - - skb_pull(skb, acc->acc_accl + acc->acc_passl + acc->acc_userl + 3); - -} - -static void dn_user_copy(struct sk_buff *skb, struct optdata_dn *opt) -{ - unsigned char *ptr = skb->data; - u16 len = *ptr++; /* yes, it's 8bit on the wire */ - - BUG_ON(len > 16); /* we've checked the contents earlier */ - opt->opt_optl = cpu_to_le16(len); - opt->opt_status = 0; - memcpy(opt->opt_data, ptr, len); - skb_pull(skb, len + 1); -} - -static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - struct sk_buff *skb = NULL; - int err = 0; - - add_wait_queue(sk_sleep(sk), &wait); - for(;;) { - release_sock(sk); - skb = skb_dequeue(&sk->sk_receive_queue); - if (skb == NULL) { - *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo); - skb = skb_dequeue(&sk->sk_receive_queue); - } - lock_sock(sk); - if (skb != NULL) - break; - err = -EINVAL; - if (sk->sk_state != TCP_LISTEN) - break; - err = sock_intr_errno(*timeo); - if (signal_pending(current)) - break; - err = -EAGAIN; - if (!*timeo) - break; - } - remove_wait_queue(sk_sleep(sk), &wait); - - return skb == NULL ? ERR_PTR(err) : skb; -} - -static int dn_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) -{ - struct sock *sk = sock->sk, *newsk; - struct sk_buff *skb = NULL; - struct dn_skb_cb *cb; - unsigned char menuver; - int err = 0; - unsigned char type; - long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); - struct dst_entry *dst; - - lock_sock(sk); - - if (sk->sk_state != TCP_LISTEN || DN_SK(sk)->state != DN_O) { - release_sock(sk); - return -EINVAL; - } - - skb = skb_dequeue(&sk->sk_receive_queue); - if (skb == NULL) { - skb = dn_wait_for_connect(sk, &timeo); - if (IS_ERR(skb)) { - release_sock(sk); - return PTR_ERR(skb); - } - } - - cb = DN_SKB_CB(skb); - sk_acceptq_removed(sk); - newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern); - if (newsk == NULL) { - release_sock(sk); - kfree_skb(skb); - return -ENOBUFS; - } - release_sock(sk); - - dst = skb_dst(skb); - sk_dst_set(newsk, dst); - skb_dst_set(skb, NULL); - - DN_SK(newsk)->state = DN_CR; - DN_SK(newsk)->addrrem = cb->src_port; - DN_SK(newsk)->services_rem = cb->services; - DN_SK(newsk)->info_rem = cb->info; - DN_SK(newsk)->segsize_rem = cb->segsize; - DN_SK(newsk)->accept_mode = DN_SK(sk)->accept_mode; - - if (DN_SK(newsk)->segsize_rem < 230) - DN_SK(newsk)->segsize_rem = 230; - - if ((DN_SK(newsk)->services_rem & NSP_FC_MASK) == NSP_FC_NONE) - DN_SK(newsk)->max_window = decnet_no_fc_max_cwnd; - - newsk->sk_state = TCP_LISTEN; - memcpy(&(DN_SK(newsk)->addr), &(DN_SK(sk)->addr), sizeof(struct sockaddr_dn)); - - /* - * If we are listening on a wild socket, we don't want - * the newly created socket on the wrong hash queue. - */ - DN_SK(newsk)->addr.sdn_flags &= ~SDF_WILD; - - skb_pull(skb, dn_username2sockaddr(skb->data, skb->len, &(DN_SK(newsk)->addr), &type)); - skb_pull(skb, dn_username2sockaddr(skb->data, skb->len, &(DN_SK(newsk)->peer), &type)); - *(__le16 *)(DN_SK(newsk)->peer.sdn_add.a_addr) = cb->src; - *(__le16 *)(DN_SK(newsk)->addr.sdn_add.a_addr) = cb->dst; - - menuver = *skb->data; - skb_pull(skb, 1); - - if (menuver & DN_MENUVER_ACC) - dn_access_copy(skb, &(DN_SK(newsk)->accessdata)); - - if (menuver & DN_MENUVER_USR) - dn_user_copy(skb, &(DN_SK(newsk)->conndata_in)); - - if (menuver & DN_MENUVER_PRX) - DN_SK(newsk)->peer.sdn_flags |= SDF_PROXY; - - if (menuver & DN_MENUVER_UIC) - DN_SK(newsk)->peer.sdn_flags |= SDF_UICPROXY; - - kfree_skb(skb); - - memcpy(&(DN_SK(newsk)->conndata_out), &(DN_SK(sk)->conndata_out), - sizeof(struct optdata_dn)); - memcpy(&(DN_SK(newsk)->discdata_out), &(DN_SK(sk)->discdata_out), - sizeof(struct optdata_dn)); - - lock_sock(newsk); - err = dn_hash_sock(newsk); - if (err == 0) { - sock_reset_flag(newsk, SOCK_ZAPPED); - dn_send_conn_ack(newsk); - - /* - * Here we use sk->sk_allocation since although the conn conf is - * for the newsk, the context is the old socket. - */ - if (DN_SK(newsk)->accept_mode == ACC_IMMED) - err = dn_confirm_accept(newsk, &timeo, - sk->sk_allocation); - } - release_sock(newsk); - return err; -} - - -static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int peer) -{ - struct sockaddr_dn *sa = (struct sockaddr_dn *)uaddr; - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - - lock_sock(sk); - - if (peer) { - if ((sock->state != SS_CONNECTED && - sock->state != SS_CONNECTING) && - scp->accept_mode == ACC_IMMED) { - release_sock(sk); - return -ENOTCONN; - } - - memcpy(sa, &scp->peer, sizeof(struct sockaddr_dn)); - } else { - memcpy(sa, &scp->addr, sizeof(struct sockaddr_dn)); - } - - release_sock(sk); - - return sizeof(struct sockaddr_dn); -} - - -static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wait) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - __poll_t mask = datagram_poll(file, sock, wait); - - if (!skb_queue_empty_lockless(&scp->other_receive_queue)) - mask |= EPOLLRDBAND; - - return mask; -} - -static int dn_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - int err = -EOPNOTSUPP; - long amount = 0; - struct sk_buff *skb; - int val; - - switch(cmd) - { - case SIOCGIFADDR: - case SIOCSIFADDR: - return dn_dev_ioctl(cmd, (void __user *)arg); - - case SIOCATMARK: - lock_sock(sk); - val = !skb_queue_empty(&scp->other_receive_queue); - if (scp->state != DN_RUN) - val = -ENOTCONN; - release_sock(sk); - return val; - - case TIOCOUTQ: - amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); - if (amount < 0) - amount = 0; - err = put_user(amount, (int __user *)arg); - break; - - case TIOCINQ: - lock_sock(sk); - skb = skb_peek(&scp->other_receive_queue); - if (skb) { - amount = skb->len; - } else { - skb_queue_walk(&sk->sk_receive_queue, skb) - amount += skb->len; - } - release_sock(sk); - err = put_user(amount, (int __user *)arg); - break; - - default: - err = -ENOIOCTLCMD; - break; - } - - return err; -} - -static int dn_listen(struct socket *sock, int backlog) -{ - struct sock *sk = sock->sk; - int err = -EINVAL; - - lock_sock(sk); - - if (sock_flag(sk, SOCK_ZAPPED)) - goto out; - - if ((DN_SK(sk)->state != DN_O) || (sk->sk_state == TCP_LISTEN)) - goto out; - - sk->sk_max_ack_backlog = backlog; - sk->sk_ack_backlog = 0; - sk->sk_state = TCP_LISTEN; - err = 0; - dn_rehash_sock(sk); - -out: - release_sock(sk); - - return err; -} - - -static int dn_shutdown(struct socket *sock, int how) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - int err = -ENOTCONN; - - lock_sock(sk); - - if (sock->state == SS_UNCONNECTED) - goto out; - - err = 0; - if (sock->state == SS_DISCONNECTING) - goto out; - - err = -EINVAL; - if (scp->state == DN_O) - goto out; - - if (how != SHUT_RDWR) - goto out; - - sk->sk_shutdown = SHUTDOWN_MASK; - dn_destroy_sock(sk); - err = 0; - -out: - release_sock(sk); - - return err; -} - -static int dn_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int optlen) -{ - struct sock *sk = sock->sk; - int err; - - lock_sock(sk); - err = __dn_setsockopt(sock, level, optname, optval, optlen, 0); - release_sock(sk); -#ifdef CONFIG_NETFILTER - /* we need to exclude all possible ENOPROTOOPTs except default case */ - if (err == -ENOPROTOOPT && optname != DSO_LINKINFO && - optname != DSO_STREAM && optname != DSO_SEQPACKET) - err = nf_setsockopt(sk, PF_DECnet, optname, optval, optlen); -#endif - - return err; -} - -static int __dn_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int optlen, int flags) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - long timeo; - union { - struct optdata_dn opt; - struct accessdata_dn acc; - int mode; - unsigned long win; - int val; - unsigned char services; - unsigned char info; - } u; - int err; - - if (optlen && sockptr_is_null(optval)) - return -EINVAL; - - if (optlen > sizeof(u)) - return -EINVAL; - - if (copy_from_sockptr(&u, optval, optlen)) - return -EFAULT; - - switch (optname) { - case DSO_CONDATA: - if (sock->state == SS_CONNECTED) - return -EISCONN; - if ((scp->state != DN_O) && (scp->state != DN_CR)) - return -EINVAL; - - if (optlen != sizeof(struct optdata_dn)) - return -EINVAL; - - if (le16_to_cpu(u.opt.opt_optl) > 16) - return -EINVAL; - - memcpy(&scp->conndata_out, &u.opt, optlen); - break; - - case DSO_DISDATA: - if (sock->state != SS_CONNECTED && - scp->accept_mode == ACC_IMMED) - return -ENOTCONN; - - if (optlen != sizeof(struct optdata_dn)) - return -EINVAL; - - if (le16_to_cpu(u.opt.opt_optl) > 16) - return -EINVAL; - - memcpy(&scp->discdata_out, &u.opt, optlen); - break; - - case DSO_CONACCESS: - if (sock->state == SS_CONNECTED) - return -EISCONN; - if (scp->state != DN_O) - return -EINVAL; - - if (optlen != sizeof(struct accessdata_dn)) - return -EINVAL; - - if ((u.acc.acc_accl > DN_MAXACCL) || - (u.acc.acc_passl > DN_MAXACCL) || - (u.acc.acc_userl > DN_MAXACCL)) - return -EINVAL; - - memcpy(&scp->accessdata, &u.acc, optlen); - break; - - case DSO_ACCEPTMODE: - if (sock->state == SS_CONNECTED) - return -EISCONN; - if (scp->state != DN_O) - return -EINVAL; - - if (optlen != sizeof(int)) - return -EINVAL; - - if ((u.mode != ACC_IMMED) && (u.mode != ACC_DEFER)) - return -EINVAL; - - scp->accept_mode = (unsigned char)u.mode; - break; - - case DSO_CONACCEPT: - if (scp->state != DN_CR) - return -EINVAL; - timeo = sock_rcvtimeo(sk, 0); - err = dn_confirm_accept(sk, &timeo, sk->sk_allocation); - return err; - - case DSO_CONREJECT: - if (scp->state != DN_CR) - return -EINVAL; - - scp->state = DN_DR; - sk->sk_shutdown = SHUTDOWN_MASK; - dn_nsp_send_disc(sk, 0x38, 0, sk->sk_allocation); - break; - - case DSO_MAXWINDOW: - if (optlen != sizeof(unsigned long)) - return -EINVAL; - if (u.win > NSP_MAX_WINDOW) - u.win = NSP_MAX_WINDOW; - if (u.win == 0) - return -EINVAL; - scp->max_window = u.win; - if (scp->snd_window > u.win) - scp->snd_window = u.win; - break; - - case DSO_NODELAY: - if (optlen != sizeof(int)) - return -EINVAL; - if (scp->nonagle == TCP_NAGLE_CORK) - return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_OFF; - /* if (scp->nonagle == 1) { Push pending frames } */ - break; - - case DSO_CORK: - if (optlen != sizeof(int)) - return -EINVAL; - if (scp->nonagle == TCP_NAGLE_OFF) - return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_CORK; - /* if (scp->nonagle == 0) { Push pending frames } */ - break; - - case DSO_SERVICES: - if (optlen != sizeof(unsigned char)) - return -EINVAL; - if ((u.services & ~NSP_FC_MASK) != 0x01) - return -EINVAL; - if ((u.services & NSP_FC_MASK) == NSP_FC_MASK) - return -EINVAL; - scp->services_loc = u.services; - break; - - case DSO_INFO: - if (optlen != sizeof(unsigned char)) - return -EINVAL; - if (u.info & 0xfc) - return -EINVAL; - scp->info_loc = u.info; - break; - - case DSO_LINKINFO: - case DSO_STREAM: - case DSO_SEQPACKET: - default: - return -ENOPROTOOPT; - } - - return 0; -} - -static int dn_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) -{ - struct sock *sk = sock->sk; - int err; - - lock_sock(sk); - err = __dn_getsockopt(sock, level, optname, optval, optlen, 0); - release_sock(sk); -#ifdef CONFIG_NETFILTER - if (err == -ENOPROTOOPT && optname != DSO_STREAM && - optname != DSO_SEQPACKET && optname != DSO_CONACCEPT && - optname != DSO_CONREJECT) { - int len; - - if (get_user(len, optlen)) - return -EFAULT; - - err = nf_getsockopt(sk, PF_DECnet, optname, optval, &len); - if (err >= 0) - err = put_user(len, optlen); - } -#endif - - return err; -} - -static int __dn_getsockopt(struct socket *sock, int level,int optname, char __user *optval,int __user *optlen, int flags) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - struct linkinfo_dn link; - unsigned int r_len; - void *r_data = NULL; - unsigned int val; - - if(get_user(r_len , optlen)) - return -EFAULT; - - switch (optname) { - case DSO_CONDATA: - if (r_len > sizeof(struct optdata_dn)) - r_len = sizeof(struct optdata_dn); - r_data = &scp->conndata_in; - break; - - case DSO_DISDATA: - if (r_len > sizeof(struct optdata_dn)) - r_len = sizeof(struct optdata_dn); - r_data = &scp->discdata_in; - break; - - case DSO_CONACCESS: - if (r_len > sizeof(struct accessdata_dn)) - r_len = sizeof(struct accessdata_dn); - r_data = &scp->accessdata; - break; - - case DSO_ACCEPTMODE: - if (r_len > sizeof(unsigned char)) - r_len = sizeof(unsigned char); - r_data = &scp->accept_mode; - break; - - case DSO_LINKINFO: - if (r_len > sizeof(struct linkinfo_dn)) - r_len = sizeof(struct linkinfo_dn); - - memset(&link, 0, sizeof(link)); - - switch (sock->state) { - case SS_CONNECTING: - link.idn_linkstate = LL_CONNECTING; - break; - case SS_DISCONNECTING: - link.idn_linkstate = LL_DISCONNECTING; - break; - case SS_CONNECTED: - link.idn_linkstate = LL_RUNNING; - break; - default: - link.idn_linkstate = LL_INACTIVE; - } - - link.idn_segsize = scp->segsize_rem; - r_data = &link; - break; - - case DSO_MAXWINDOW: - if (r_len > sizeof(unsigned long)) - r_len = sizeof(unsigned long); - r_data = &scp->max_window; - break; - - case DSO_NODELAY: - if (r_len > sizeof(int)) - r_len = sizeof(int); - val = (scp->nonagle == TCP_NAGLE_OFF); - r_data = &val; - break; - - case DSO_CORK: - if (r_len > sizeof(int)) - r_len = sizeof(int); - val = (scp->nonagle == TCP_NAGLE_CORK); - r_data = &val; - break; - - case DSO_SERVICES: - if (r_len > sizeof(unsigned char)) - r_len = sizeof(unsigned char); - r_data = &scp->services_rem; - break; - - case DSO_INFO: - if (r_len > sizeof(unsigned char)) - r_len = sizeof(unsigned char); - r_data = &scp->info_rem; - break; - - case DSO_STREAM: - case DSO_SEQPACKET: - case DSO_CONACCEPT: - case DSO_CONREJECT: - default: - return -ENOPROTOOPT; - } - - if (r_data) { - if (copy_to_user(optval, r_data, r_len)) - return -EFAULT; - if (put_user(r_len, optlen)) - return -EFAULT; - } - - return 0; -} - - -static int dn_data_ready(struct sock *sk, struct sk_buff_head *q, int flags, int target) -{ - struct sk_buff *skb; - int len = 0; - - if (flags & MSG_OOB) - return !skb_queue_empty(q) ? 1 : 0; - - skb_queue_walk(q, skb) { - struct dn_skb_cb *cb = DN_SKB_CB(skb); - len += skb->len; - - if (cb->nsp_flags & 0x40) { - /* SOCK_SEQPACKET reads to EOM */ - if (sk->sk_type == SOCK_SEQPACKET) - return 1; - /* so does SOCK_STREAM unless WAITALL is specified */ - if (!(flags & MSG_WAITALL)) - return 1; - } - - /* minimum data length for read exceeded */ - if (len >= target) - return 1; - } - - return 0; -} - - -static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, - int flags) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - struct sk_buff_head *queue = &sk->sk_receive_queue; - size_t target = size > 1 ? 1 : 0; - size_t copied = 0; - int rv = 0; - struct sk_buff *skb, *n; - struct dn_skb_cb *cb = NULL; - unsigned char eor = 0; - long timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - - lock_sock(sk); - - if (sock_flag(sk, SOCK_ZAPPED)) { - rv = -EADDRNOTAVAIL; - goto out; - } - - if (sk->sk_shutdown & RCV_SHUTDOWN) { - rv = 0; - goto out; - } - - rv = dn_check_state(sk, NULL, 0, &timeo, flags); - if (rv) - goto out; - - if (flags & ~(MSG_CMSG_COMPAT|MSG_PEEK|MSG_OOB|MSG_WAITALL|MSG_DONTWAIT|MSG_NOSIGNAL)) { - rv = -EOPNOTSUPP; - goto out; - } - - if (flags & MSG_OOB) - queue = &scp->other_receive_queue; - - if (flags & MSG_WAITALL) - target = size; - - - /* - * See if there is data ready to read, sleep if there isn't - */ - for(;;) { - DEFINE_WAIT_FUNC(wait, woken_wake_function); - - if (sk->sk_err) - goto out; - - if (!skb_queue_empty(&scp->other_receive_queue)) { - if (!(flags & MSG_OOB)) { - msg->msg_flags |= MSG_OOB; - if (!scp->other_report) { - scp->other_report = 1; - goto out; - } - } - } - - if (scp->state != DN_RUN) - goto out; - - if (signal_pending(current)) { - rv = sock_intr_errno(timeo); - goto out; - } - - if (dn_data_ready(sk, queue, flags, target)) - break; - - if (flags & MSG_DONTWAIT) { - rv = -EWOULDBLOCK; - goto out; - } - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - } - - skb_queue_walk_safe(queue, skb, n) { - unsigned int chunk = skb->len; - cb = DN_SKB_CB(skb); - - if ((chunk + copied) > size) - chunk = size - copied; - - if (memcpy_to_msg(msg, skb->data, chunk)) { - rv = -EFAULT; - break; - } - copied += chunk; - - if (!(flags & MSG_PEEK)) - skb_pull(skb, chunk); - - eor = cb->nsp_flags & 0x40; - - if (skb->len == 0) { - skb_unlink(skb, queue); - kfree_skb(skb); - /* - * N.B. Don't refer to skb or cb after this point - * in loop. - */ - if ((scp->flowloc_sw == DN_DONTSEND) && !dn_congested(sk)) { - scp->flowloc_sw = DN_SEND; - dn_nsp_send_link(sk, DN_SEND, 0); - } - } - - if (eor) { - if (sk->sk_type == SOCK_SEQPACKET) - break; - if (!(flags & MSG_WAITALL)) - break; - } - - if (flags & MSG_OOB) - break; - - if (copied >= target) - break; - } - - rv = copied; - - - if (eor && (sk->sk_type == SOCK_SEQPACKET)) - msg->msg_flags |= MSG_EOR; - -out: - if (rv == 0) - rv = (flags & MSG_PEEK) ? -sk->sk_err : sock_error(sk); - - if ((rv >= 0) && msg->msg_name) { - __sockaddr_check_size(sizeof(struct sockaddr_dn)); - memcpy(msg->msg_name, &scp->peer, sizeof(struct sockaddr_dn)); - msg->msg_namelen = sizeof(struct sockaddr_dn); - } - - release_sock(sk); - - return rv; -} - - -static inline int dn_queue_too_long(struct dn_scp *scp, struct sk_buff_head *queue, int flags) -{ - unsigned char fctype = scp->services_rem & NSP_FC_MASK; - if (skb_queue_len(queue) >= scp->snd_window) - return 1; - if (fctype != NSP_FC_NONE) { - if (flags & MSG_OOB) { - if (scp->flowrem_oth == 0) - return 1; - } else { - if (scp->flowrem_dat == 0) - return 1; - } - } - return 0; -} - -/* - * The DECnet spec requires that the "routing layer" accepts packets which - * are at least 230 bytes in size. This excludes any headers which the NSP - * layer might add, so we always assume that we'll be using the maximal - * length header on data packets. The variation in length is due to the - * inclusion (or not) of the two 16 bit acknowledgement fields so it doesn't - * make much practical difference. - */ -unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu) -{ - unsigned int mss = 230 - DN_MAX_NSP_DATA_HEADER; - if (dev) { - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - mtu -= LL_RESERVED_SPACE(dev); - if (dn_db->use_long) - mtu -= 21; - else - mtu -= 6; - mtu -= DN_MAX_NSP_DATA_HEADER; - } else { - /* - * 21 = long header, 16 = guess at MAC header length - */ - mtu -= (21 + DN_MAX_NSP_DATA_HEADER + 16); - } - if (mtu > mss) - mss = mtu; - return mss; -} - -static inline unsigned int dn_current_mss(struct sock *sk, int flags) -{ - struct dst_entry *dst = __sk_dst_get(sk); - struct dn_scp *scp = DN_SK(sk); - int mss_now = min_t(int, scp->segsize_loc, scp->segsize_rem); - - /* Other data messages are limited to 16 bytes per packet */ - if (flags & MSG_OOB) - return 16; - - /* This works out the maximum size of segment we can send out */ - if (dst) { - u32 mtu = dst_mtu(dst); - mss_now = min_t(int, dn_mss_from_pmtu(dst->dev, mtu), mss_now); - } - - return mss_now; -} - -/* - * N.B. We get the timeout wrong here, but then we always did get it - * wrong before and this is another step along the road to correcting - * it. It ought to get updated each time we pass through the routine, - * but in practise it probably doesn't matter too much for now. - */ -static inline struct sk_buff *dn_alloc_send_pskb(struct sock *sk, - unsigned long datalen, int noblock, - int *errcode) -{ - struct sk_buff *skb = sock_alloc_send_skb(sk, datalen, - noblock, errcode); - if (skb) { - skb->protocol = htons(ETH_P_DNA_RT); - skb->pkt_type = PACKET_OUTGOING; - } - return skb; -} - -static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - size_t mss; - struct sk_buff_head *queue = &scp->data_xmit_queue; - int flags = msg->msg_flags; - int err = 0; - size_t sent = 0; - int addr_len = msg->msg_namelen; - DECLARE_SOCKADDR(struct sockaddr_dn *, addr, msg->msg_name); - struct sk_buff *skb = NULL; - struct dn_skb_cb *cb; - size_t len; - unsigned char fctype; - long timeo; - - if (flags & ~(MSG_TRYHARD|MSG_OOB|MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL|MSG_MORE|MSG_CMSG_COMPAT)) - return -EOPNOTSUPP; - - if (addr_len && (addr_len != sizeof(struct sockaddr_dn))) - return -EINVAL; - - lock_sock(sk); - timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - /* - * The only difference between stream sockets and sequenced packet - * sockets is that the stream sockets always behave as if MSG_EOR - * has been set. - */ - if (sock->type == SOCK_STREAM) { - if (flags & MSG_EOR) { - err = -EINVAL; - goto out; - } - flags |= MSG_EOR; - } - - - err = dn_check_state(sk, addr, addr_len, &timeo, flags); - if (err) - goto out_err; - - if (sk->sk_shutdown & SEND_SHUTDOWN) { - err = -EPIPE; - if (!(flags & MSG_NOSIGNAL)) - send_sig(SIGPIPE, current, 0); - goto out_err; - } - - if ((flags & MSG_TRYHARD) && sk->sk_dst_cache) - dst_negative_advice(sk); - - mss = scp->segsize_rem; - fctype = scp->services_rem & NSP_FC_MASK; - - mss = dn_current_mss(sk, flags); - - if (flags & MSG_OOB) { - queue = &scp->other_xmit_queue; - if (size > mss) { - err = -EMSGSIZE; - goto out; - } - } - - scp->persist_fxn = dn_nsp_xmit_timeout; - - while(sent < size) { - err = sock_error(sk); - if (err) - goto out; - - if (signal_pending(current)) { - err = sock_intr_errno(timeo); - goto out; - } - - /* - * Calculate size that we wish to send. - */ - len = size - sent; - - if (len > mss) - len = mss; - - /* - * Wait for queue size to go down below the window - * size. - */ - if (dn_queue_too_long(scp, queue, flags)) { - DEFINE_WAIT_FUNC(wait, woken_wake_function); - - if (flags & MSG_DONTWAIT) { - err = -EWOULDBLOCK; - goto out; - } - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - sk_wait_event(sk, &timeo, - !dn_queue_too_long(scp, queue, flags), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - continue; - } - - /* - * Get a suitably sized skb. - * 64 is a bit of a hack really, but its larger than any - * link-layer headers and has served us well as a good - * guess as to their real length. - */ - skb = dn_alloc_send_pskb(sk, len + 64 + DN_MAX_NSP_DATA_HEADER, - flags & MSG_DONTWAIT, &err); - - if (err) - break; - - if (!skb) - continue; - - cb = DN_SKB_CB(skb); - - skb_reserve(skb, 64 + DN_MAX_NSP_DATA_HEADER); - - if (memcpy_from_msg(skb_put(skb, len), msg, len)) { - err = -EFAULT; - goto out; - } - - if (flags & MSG_OOB) { - cb->nsp_flags = 0x30; - if (fctype != NSP_FC_NONE) - scp->flowrem_oth--; - } else { - cb->nsp_flags = 0x00; - if (scp->seg_total == 0) - cb->nsp_flags |= 0x20; - - scp->seg_total += len; - - if (((sent + len) == size) && (flags & MSG_EOR)) { - cb->nsp_flags |= 0x40; - scp->seg_total = 0; - if (fctype == NSP_FC_SCMC) - scp->flowrem_dat--; - } - if (fctype == NSP_FC_SRC) - scp->flowrem_dat--; - } - - sent += len; - dn_nsp_queue_xmit(sk, skb, sk->sk_allocation, flags & MSG_OOB); - skb = NULL; - - scp->persist = dn_nsp_persist(sk); - - } -out: - - kfree_skb(skb); - - release_sock(sk); - - return sent ? sent : err; - -out_err: - err = sk_stream_error(sk, flags, err); - release_sock(sk); - return err; -} - -static int dn_device_event(struct notifier_block *this, unsigned long event, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - switch (event) { - case NETDEV_UP: - dn_dev_up(dev); - break; - case NETDEV_DOWN: - dn_dev_down(dev); - break; - default: - break; - } - - return NOTIFY_DONE; -} - -static struct notifier_block dn_dev_notifier = { - .notifier_call = dn_device_event, -}; - -static struct packet_type dn_dix_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_DNA_RT), - .func = dn_route_rcv, -}; - -#ifdef CONFIG_PROC_FS -struct dn_iter_state { - int bucket; -}; - -static struct sock *dn_socket_get_first(struct seq_file *seq) -{ - struct dn_iter_state *state = seq->private; - struct sock *n = NULL; - - for(state->bucket = 0; - state->bucket < DN_SK_HASH_SIZE; - ++state->bucket) { - n = sk_head(&dn_sk_hash[state->bucket]); - if (n) - break; - } - - return n; -} - -static struct sock *dn_socket_get_next(struct seq_file *seq, - struct sock *n) -{ - struct dn_iter_state *state = seq->private; - - n = sk_next(n); - while (!n) { - if (++state->bucket >= DN_SK_HASH_SIZE) - break; - n = sk_head(&dn_sk_hash[state->bucket]); - } - return n; -} - -static struct sock *socket_get_idx(struct seq_file *seq, loff_t *pos) -{ - struct sock *sk = dn_socket_get_first(seq); - - if (sk) { - while(*pos && (sk = dn_socket_get_next(seq, sk))) - --*pos; - } - return *pos ? NULL : sk; -} - -static void *dn_socket_get_idx(struct seq_file *seq, loff_t pos) -{ - void *rc; - read_lock_bh(&dn_hash_lock); - rc = socket_get_idx(seq, &pos); - if (!rc) { - read_unlock_bh(&dn_hash_lock); - } - return rc; -} - -static void *dn_socket_seq_start(struct seq_file *seq, loff_t *pos) -{ - return *pos ? dn_socket_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; -} - -static void *dn_socket_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - void *rc; - - if (v == SEQ_START_TOKEN) { - rc = dn_socket_get_idx(seq, 0); - goto out; - } - - rc = dn_socket_get_next(seq, v); - if (rc) - goto out; - read_unlock_bh(&dn_hash_lock); -out: - ++*pos; - return rc; -} - -static void dn_socket_seq_stop(struct seq_file *seq, void *v) -{ - if (v && v != SEQ_START_TOKEN) - read_unlock_bh(&dn_hash_lock); -} - -#define IS_NOT_PRINTABLE(x) ((x) < 32 || (x) > 126) - -static void dn_printable_object(struct sockaddr_dn *dn, unsigned char *buf) -{ - int i; - - switch (le16_to_cpu(dn->sdn_objnamel)) { - case 0: - sprintf(buf, "%d", dn->sdn_objnum); - break; - default: - for (i = 0; i < le16_to_cpu(dn->sdn_objnamel); i++) { - buf[i] = dn->sdn_objname[i]; - if (IS_NOT_PRINTABLE(buf[i])) - buf[i] = '.'; - } - buf[i] = 0; - } -} - -static char *dn_state2asc(unsigned char state) -{ - switch (state) { - case DN_O: - return "OPEN"; - case DN_CR: - return " CR"; - case DN_DR: - return " DR"; - case DN_DRC: - return " DRC"; - case DN_CC: - return " CC"; - case DN_CI: - return " CI"; - case DN_NR: - return " NR"; - case DN_NC: - return " NC"; - case DN_CD: - return " CD"; - case DN_RJ: - return " RJ"; - case DN_RUN: - return " RUN"; - case DN_DI: - return " DI"; - case DN_DIC: - return " DIC"; - case DN_DN: - return " DN"; - case DN_CL: - return " CL"; - case DN_CN: - return " CN"; - } - - return "????"; -} - -static inline void dn_socket_format_entry(struct seq_file *seq, struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - char buf1[DN_ASCBUF_LEN]; - char buf2[DN_ASCBUF_LEN]; - char local_object[DN_MAXOBJL+3]; - char remote_object[DN_MAXOBJL+3]; - - dn_printable_object(&scp->addr, local_object); - dn_printable_object(&scp->peer, remote_object); - - seq_printf(seq, - "%6s/%04X %04d:%04d %04d:%04d %01d %-16s " - "%6s/%04X %04d:%04d %04d:%04d %01d %-16s %4s %s\n", - dn_addr2asc(le16_to_cpu(dn_saddr2dn(&scp->addr)), buf1), - scp->addrloc, - scp->numdat, - scp->numoth, - scp->ackxmt_dat, - scp->ackxmt_oth, - scp->flowloc_sw, - local_object, - dn_addr2asc(le16_to_cpu(dn_saddr2dn(&scp->peer)), buf2), - scp->addrrem, - scp->numdat_rcv, - scp->numoth_rcv, - scp->ackrcv_dat, - scp->ackrcv_oth, - scp->flowrem_sw, - remote_object, - dn_state2asc(scp->state), - ((scp->accept_mode == ACC_IMMED) ? "IMMED" : "DEFER")); -} - -static int dn_socket_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) { - seq_puts(seq, "Local Remote\n"); - } else { - dn_socket_format_entry(seq, v); - } - return 0; -} - -static const struct seq_operations dn_socket_seq_ops = { - .start = dn_socket_seq_start, - .next = dn_socket_seq_next, - .stop = dn_socket_seq_stop, - .show = dn_socket_seq_show, -}; -#endif - -static const struct net_proto_family dn_family_ops = { - .family = AF_DECnet, - .create = dn_create, - .owner = THIS_MODULE, -}; - -static const struct proto_ops dn_proto_ops = { - .family = AF_DECnet, - .owner = THIS_MODULE, - .release = dn_release, - .bind = dn_bind, - .connect = dn_connect, - .socketpair = sock_no_socketpair, - .accept = dn_accept, - .getname = dn_getname, - .poll = dn_poll, - .ioctl = dn_ioctl, - .listen = dn_listen, - .shutdown = dn_shutdown, - .setsockopt = dn_setsockopt, - .getsockopt = dn_getsockopt, - .sendmsg = dn_sendmsg, - .recvmsg = dn_recvmsg, - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, -}; - -MODULE_DESCRIPTION("The Linux DECnet Network Protocol"); -MODULE_AUTHOR("Linux DECnet Project Team"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NETPROTO(PF_DECnet); - -static const char banner[] __initconst = KERN_INFO -"NET4: DECnet for Linux: V.2.5.68s (C) 1995-2003 Linux DECnet Project Team\n"; - -static int __init decnet_init(void) -{ - int rc; - - printk(banner); - - rc = proto_register(&dn_proto, 1); - if (rc != 0) - goto out; - - dn_neigh_init(); - dn_dev_init(); - dn_route_init(); - dn_fib_init(); - - sock_register(&dn_family_ops); - dev_add_pack(&dn_dix_packet_type); - register_netdevice_notifier(&dn_dev_notifier); - - proc_create_seq_private("decnet", 0444, init_net.proc_net, - &dn_socket_seq_ops, sizeof(struct dn_iter_state), - NULL); - dn_register_sysctl(); -out: - return rc; - -} -module_init(decnet_init); - -/* - * Prevent DECnet module unloading until its fixed properly. - * Requires an audit of the code to check for memory leaks and - * initialisation problems etc. - */ -#if 0 -static void __exit decnet_exit(void) -{ - sock_unregister(AF_DECnet); - rtnl_unregister_all(PF_DECnet); - dev_remove_pack(&dn_dix_packet_type); - - dn_unregister_sysctl(); - - unregister_netdevice_notifier(&dn_dev_notifier); - - dn_route_cleanup(); - dn_dev_cleanup(); - dn_neigh_cleanup(); - dn_fib_cleanup(); - - remove_proc_entry("decnet", init_net.proc_net); - - proto_unregister(&dn_proto); - - rcu_barrier(); /* Wait for completion of call_rcu()'s */ -} -module_exit(decnet_exit); -#endif diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c deleted file mode 100644 index 15d42353f1a3..000000000000 --- a/net/decnet/dn_dev.c +++ /dev/null @@ -1,1435 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Device Layer - * - * Authors: Steve Whitehouse - * Eduardo Marcelo Serrat - * - * Changes: - * Steve Whitehouse : Devices now see incoming frames so they - * can mark on who it came from. - * Steve Whitehouse : Fixed bug in creating neighbours. Each neighbour - * can now have a device specific setup func. - * Steve Whitehouse : Added /proc/sys/net/decnet/conf// - * Steve Whitehouse : Fixed bug which sometimes killed timer - * Steve Whitehouse : Multiple ifaddr support - * Steve Whitehouse : SIOCGIFCONF is now a compile time option - * Steve Whitehouse : /proc/sys/net/decnet/conf//forwarding - * Steve Whitehouse : Removed timer1 - it's a user space issue now - * Patrick Caulfield : Fixed router hello message format - * Steve Whitehouse : Got rid of constant sizes for blksize for - * devices. All mtu based now. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define DN_IFREQ_SIZE (offsetof(struct ifreq, ifr_ifru) + sizeof(struct sockaddr_dn)) - -static char dn_rt_all_end_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x04,0x00,0x00}; -static char dn_rt_all_rt_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x03,0x00,0x00}; -static char dn_hiord[ETH_ALEN] = {0xAA,0x00,0x04,0x00,0x00,0x00}; -static unsigned char dn_eco_version[3] = {0x02,0x00,0x00}; - -extern struct neigh_table dn_neigh_table; - -/* - * decnet_address is kept in network order. - */ -__le16 decnet_address = 0; - -static DEFINE_SPINLOCK(dndev_lock); -static struct net_device *decnet_default_device; -static BLOCKING_NOTIFIER_HEAD(dnaddr_chain); - -static struct dn_dev *dn_dev_create(struct net_device *dev, int *err); -static void dn_dev_delete(struct net_device *dev); -static void dn_ifaddr_notify(int event, struct dn_ifaddr *ifa); - -static int dn_eth_up(struct net_device *); -static void dn_eth_down(struct net_device *); -static void dn_send_brd_hello(struct net_device *dev, struct dn_ifaddr *ifa); -static void dn_send_ptp_hello(struct net_device *dev, struct dn_ifaddr *ifa); - -static struct dn_dev_parms dn_dev_list[] = { -{ - .type = ARPHRD_ETHER, /* Ethernet */ - .mode = DN_DEV_BCAST, - .state = DN_DEV_S_RU, - .t2 = 1, - .t3 = 10, - .name = "ethernet", - .up = dn_eth_up, - .down = dn_eth_down, - .timer3 = dn_send_brd_hello, -}, -{ - .type = ARPHRD_IPGRE, /* DECnet tunneled over GRE in IP */ - .mode = DN_DEV_BCAST, - .state = DN_DEV_S_RU, - .t2 = 1, - .t3 = 10, - .name = "ipgre", - .timer3 = dn_send_brd_hello, -}, -#if 0 -{ - .type = ARPHRD_X25, /* Bog standard X.25 */ - .mode = DN_DEV_UCAST, - .state = DN_DEV_S_DS, - .t2 = 1, - .t3 = 120, - .name = "x25", - .timer3 = dn_send_ptp_hello, -}, -#endif -#if 0 -{ - .type = ARPHRD_PPP, /* DECnet over PPP */ - .mode = DN_DEV_BCAST, - .state = DN_DEV_S_RU, - .t2 = 1, - .t3 = 10, - .name = "ppp", - .timer3 = dn_send_brd_hello, -}, -#endif -{ - .type = ARPHRD_DDCMP, /* DECnet over DDCMP */ - .mode = DN_DEV_UCAST, - .state = DN_DEV_S_DS, - .t2 = 1, - .t3 = 120, - .name = "ddcmp", - .timer3 = dn_send_ptp_hello, -}, -{ - .type = ARPHRD_LOOPBACK, /* Loopback interface - always last */ - .mode = DN_DEV_BCAST, - .state = DN_DEV_S_RU, - .t2 = 1, - .t3 = 10, - .name = "loopback", - .timer3 = dn_send_brd_hello, -} -}; - -#define DN_DEV_LIST_SIZE ARRAY_SIZE(dn_dev_list) - -#define DN_DEV_PARMS_OFFSET(x) offsetof(struct dn_dev_parms, x) - -#ifdef CONFIG_SYSCTL - -static int min_t2[] = { 1 }; -static int max_t2[] = { 60 }; /* No max specified, but this seems sensible */ -static int min_t3[] = { 1 }; -static int max_t3[] = { 8191 }; /* Must fit in 16 bits when multiplied by BCT3MULT or T3MULT */ - -static int min_priority[1]; -static int max_priority[] = { 127 }; /* From DECnet spec */ - -static int dn_forwarding_proc(struct ctl_table *, int, void *, size_t *, - loff_t *); -static struct dn_dev_sysctl_table { - struct ctl_table_header *sysctl_header; - struct ctl_table dn_dev_vars[5]; -} dn_dev_sysctl = { - NULL, - { - { - .procname = "forwarding", - .data = (void *)DN_DEV_PARMS_OFFSET(forwarding), - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = dn_forwarding_proc, - }, - { - .procname = "priority", - .data = (void *)DN_DEV_PARMS_OFFSET(priority), - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_priority, - .extra2 = &max_priority - }, - { - .procname = "t2", - .data = (void *)DN_DEV_PARMS_OFFSET(t2), - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_t2, - .extra2 = &max_t2 - }, - { - .procname = "t3", - .data = (void *)DN_DEV_PARMS_OFFSET(t3), - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_t3, - .extra2 = &max_t3 - }, - { } - }, -}; - -static void dn_dev_sysctl_register(struct net_device *dev, struct dn_dev_parms *parms) -{ - struct dn_dev_sysctl_table *t; - int i; - - char path[sizeof("net/decnet/conf/") + IFNAMSIZ]; - - t = kmemdup(&dn_dev_sysctl, sizeof(*t), GFP_KERNEL); - if (t == NULL) - return; - - for(i = 0; i < ARRAY_SIZE(t->dn_dev_vars) - 1; i++) { - long offset = (long)t->dn_dev_vars[i].data; - t->dn_dev_vars[i].data = ((char *)parms) + offset; - } - - snprintf(path, sizeof(path), "net/decnet/conf/%s", - dev? dev->name : parms->name); - - t->dn_dev_vars[0].extra1 = (void *)dev; - - t->sysctl_header = register_net_sysctl(&init_net, path, t->dn_dev_vars); - if (t->sysctl_header == NULL) - kfree(t); - else - parms->sysctl = t; -} - -static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) -{ - if (parms->sysctl) { - struct dn_dev_sysctl_table *t = parms->sysctl; - parms->sysctl = NULL; - unregister_net_sysctl_table(t->sysctl_header); - kfree(t); - } -} - -static int dn_forwarding_proc(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ -#ifdef CONFIG_DECNET_ROUTER - struct net_device *dev = table->extra1; - struct dn_dev *dn_db; - int err; - int tmp, old; - - if (table->extra1 == NULL) - return -EINVAL; - - dn_db = rcu_dereference_raw(dev->dn_ptr); - old = dn_db->parms.forwarding; - - err = proc_dointvec(table, write, buffer, lenp, ppos); - - if ((err >= 0) && write) { - if (dn_db->parms.forwarding < 0) - dn_db->parms.forwarding = 0; - if (dn_db->parms.forwarding > 2) - dn_db->parms.forwarding = 2; - /* - * What an ugly hack this is... its works, just. It - * would be nice if sysctl/proc were just that little - * bit more flexible so I don't have to write a special - * routine, or suffer hacks like this - SJW - */ - tmp = dn_db->parms.forwarding; - dn_db->parms.forwarding = old; - if (dn_db->parms.down) - dn_db->parms.down(dev); - dn_db->parms.forwarding = tmp; - if (dn_db->parms.up) - dn_db->parms.up(dev); - } - - return err; -#else - return -EINVAL; -#endif -} - -#else /* CONFIG_SYSCTL */ -static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) -{ -} -static void dn_dev_sysctl_register(struct net_device *dev, struct dn_dev_parms *parms) -{ -} - -#endif /* CONFIG_SYSCTL */ - -static inline __u16 mtu2blksize(struct net_device *dev) -{ - u32 blksize = dev->mtu; - if (blksize > 0xffff) - blksize = 0xffff; - - if (dev->type == ARPHRD_ETHER || - dev->type == ARPHRD_PPP || - dev->type == ARPHRD_IPGRE || - dev->type == ARPHRD_LOOPBACK) - blksize -= 2; - - return (__u16)blksize; -} - -static struct dn_ifaddr *dn_dev_alloc_ifa(void) -{ - struct dn_ifaddr *ifa; - - ifa = kzalloc(sizeof(*ifa), GFP_KERNEL); - - return ifa; -} - -static void dn_dev_free_ifa(struct dn_ifaddr *ifa) -{ - kfree_rcu(ifa, rcu); -} - -static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr __rcu **ifap, int destroy) -{ - struct dn_ifaddr *ifa1 = rtnl_dereference(*ifap); - unsigned char mac_addr[6]; - struct net_device *dev = dn_db->dev; - - ASSERT_RTNL(); - - *ifap = ifa1->ifa_next; - - if (dn_db->dev->type == ARPHRD_ETHER) { - if (ifa1->ifa_local != dn_eth2dn(dev->dev_addr)) { - dn_dn2eth(mac_addr, ifa1->ifa_local); - dev_mc_del(dev, mac_addr); - } - } - - dn_ifaddr_notify(RTM_DELADDR, ifa1); - blocking_notifier_call_chain(&dnaddr_chain, NETDEV_DOWN, ifa1); - if (destroy) { - dn_dev_free_ifa(ifa1); - - if (dn_db->ifa_list == NULL) - dn_dev_delete(dn_db->dev); - } -} - -static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) -{ - struct net_device *dev = dn_db->dev; - struct dn_ifaddr *ifa1; - unsigned char mac_addr[6]; - - ASSERT_RTNL(); - - /* Check for duplicates */ - for (ifa1 = rtnl_dereference(dn_db->ifa_list); - ifa1 != NULL; - ifa1 = rtnl_dereference(ifa1->ifa_next)) { - if (ifa1->ifa_local == ifa->ifa_local) - return -EEXIST; - } - - if (dev->type == ARPHRD_ETHER) { - if (ifa->ifa_local != dn_eth2dn(dev->dev_addr)) { - dn_dn2eth(mac_addr, ifa->ifa_local); - dev_mc_add(dev, mac_addr); - } - } - - ifa->ifa_next = dn_db->ifa_list; - rcu_assign_pointer(dn_db->ifa_list, ifa); - - dn_ifaddr_notify(RTM_NEWADDR, ifa); - blocking_notifier_call_chain(&dnaddr_chain, NETDEV_UP, ifa); - - return 0; -} - -static int dn_dev_set_ifa(struct net_device *dev, struct dn_ifaddr *ifa) -{ - struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); - int rv; - - if (dn_db == NULL) { - int err; - dn_db = dn_dev_create(dev, &err); - if (dn_db == NULL) - return err; - } - - ifa->ifa_dev = dn_db; - - if (dev->flags & IFF_LOOPBACK) - ifa->ifa_scope = RT_SCOPE_HOST; - - rv = dn_dev_insert_ifa(dn_db, ifa); - if (rv) - dn_dev_free_ifa(ifa); - return rv; -} - - -int dn_dev_ioctl(unsigned int cmd, void __user *arg) -{ - char buffer[DN_IFREQ_SIZE]; - struct ifreq *ifr = (struct ifreq *)buffer; - struct sockaddr_dn *sdn = (struct sockaddr_dn *)&ifr->ifr_addr; - struct dn_dev *dn_db; - struct net_device *dev; - struct dn_ifaddr *ifa = NULL; - struct dn_ifaddr __rcu **ifap = NULL; - int ret = 0; - - if (copy_from_user(ifr, arg, DN_IFREQ_SIZE)) - return -EFAULT; - ifr->ifr_name[IFNAMSIZ-1] = 0; - - dev_load(&init_net, ifr->ifr_name); - - switch (cmd) { - case SIOCGIFADDR: - break; - case SIOCSIFADDR: - if (!capable(CAP_NET_ADMIN)) - return -EACCES; - if (sdn->sdn_family != AF_DECnet) - return -EINVAL; - break; - default: - return -EINVAL; - } - - rtnl_lock(); - - if ((dev = __dev_get_by_name(&init_net, ifr->ifr_name)) == NULL) { - ret = -ENODEV; - goto done; - } - - if ((dn_db = rtnl_dereference(dev->dn_ptr)) != NULL) { - for (ifap = &dn_db->ifa_list; - (ifa = rtnl_dereference(*ifap)) != NULL; - ifap = &ifa->ifa_next) - if (strcmp(ifr->ifr_name, ifa->ifa_label) == 0) - break; - } - - if (ifa == NULL && cmd != SIOCSIFADDR) { - ret = -EADDRNOTAVAIL; - goto done; - } - - switch (cmd) { - case SIOCGIFADDR: - *((__le16 *)sdn->sdn_nodeaddr) = ifa->ifa_local; - if (copy_to_user(arg, ifr, DN_IFREQ_SIZE)) - ret = -EFAULT; - break; - - case SIOCSIFADDR: - if (!ifa) { - if ((ifa = dn_dev_alloc_ifa()) == NULL) { - ret = -ENOBUFS; - break; - } - memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); - } else { - if (ifa->ifa_local == dn_saddr2dn(sdn)) - break; - dn_dev_del_ifa(dn_db, ifap, 0); - } - - ifa->ifa_local = ifa->ifa_address = dn_saddr2dn(sdn); - - ret = dn_dev_set_ifa(dev, ifa); - } -done: - rtnl_unlock(); - - return ret; -} - -struct net_device *dn_dev_get_default(void) -{ - struct net_device *dev; - - spin_lock(&dndev_lock); - dev = decnet_default_device; - if (dev) { - if (dev->dn_ptr) - dev_hold(dev); - else - dev = NULL; - } - spin_unlock(&dndev_lock); - - return dev; -} - -int dn_dev_set_default(struct net_device *dev, int force) -{ - struct net_device *old = NULL; - int rv = -EBUSY; - if (!dev->dn_ptr) - return -ENODEV; - - spin_lock(&dndev_lock); - if (force || decnet_default_device == NULL) { - old = decnet_default_device; - decnet_default_device = dev; - rv = 0; - } - spin_unlock(&dndev_lock); - - if (old) - dev_put(old); - return rv; -} - -static void dn_dev_check_default(struct net_device *dev) -{ - spin_lock(&dndev_lock); - if (dev == decnet_default_device) { - decnet_default_device = NULL; - } else { - dev = NULL; - } - spin_unlock(&dndev_lock); - - if (dev) - dev_put(dev); -} - -/* - * Called with RTNL - */ -static struct dn_dev *dn_dev_by_index(int ifindex) -{ - struct net_device *dev; - struct dn_dev *dn_dev = NULL; - - dev = __dev_get_by_index(&init_net, ifindex); - if (dev) - dn_dev = rtnl_dereference(dev->dn_ptr); - - return dn_dev; -} - -static const struct nla_policy dn_ifa_policy[IFA_MAX+1] = { - [IFA_ADDRESS] = { .type = NLA_U16 }, - [IFA_LOCAL] = { .type = NLA_U16 }, - [IFA_LABEL] = { .type = NLA_STRING, - .len = IFNAMSIZ - 1 }, - [IFA_FLAGS] = { .type = NLA_U32 }, -}; - -static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(skb->sk); - struct nlattr *tb[IFA_MAX+1]; - struct dn_dev *dn_db; - struct ifaddrmsg *ifm; - struct dn_ifaddr *ifa; - struct dn_ifaddr __rcu **ifap; - int err = -EINVAL; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!net_eq(net, &init_net)) - goto errout; - - err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - dn_ifa_policy, extack); - if (err < 0) - goto errout; - - err = -ENODEV; - ifm = nlmsg_data(nlh); - if ((dn_db = dn_dev_by_index(ifm->ifa_index)) == NULL) - goto errout; - - err = -EADDRNOTAVAIL; - for (ifap = &dn_db->ifa_list; - (ifa = rtnl_dereference(*ifap)) != NULL; - ifap = &ifa->ifa_next) { - if (tb[IFA_LOCAL] && - nla_memcmp(tb[IFA_LOCAL], &ifa->ifa_local, 2)) - continue; - - if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) - continue; - - dn_dev_del_ifa(dn_db, ifap, 1); - return 0; - } - -errout: - return err; -} - -static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(skb->sk); - struct nlattr *tb[IFA_MAX+1]; - struct net_device *dev; - struct dn_dev *dn_db; - struct ifaddrmsg *ifm; - struct dn_ifaddr *ifa; - int err; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!net_eq(net, &init_net)) - return -EINVAL; - - err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - dn_ifa_policy, extack); - if (err < 0) - return err; - - if (tb[IFA_LOCAL] == NULL) - return -EINVAL; - - ifm = nlmsg_data(nlh); - if ((dev = __dev_get_by_index(&init_net, ifm->ifa_index)) == NULL) - return -ENODEV; - - if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL) { - dn_db = dn_dev_create(dev, &err); - if (!dn_db) - return err; - } - - if ((ifa = dn_dev_alloc_ifa()) == NULL) - return -ENOBUFS; - - if (tb[IFA_ADDRESS] == NULL) - tb[IFA_ADDRESS] = tb[IFA_LOCAL]; - - ifa->ifa_local = nla_get_le16(tb[IFA_LOCAL]); - ifa->ifa_address = nla_get_le16(tb[IFA_ADDRESS]); - ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : - ifm->ifa_flags; - ifa->ifa_scope = ifm->ifa_scope; - ifa->ifa_dev = dn_db; - - if (tb[IFA_LABEL]) - nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); - else - memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); - - err = dn_dev_insert_ifa(dn_db, ifa); - if (err) - dn_dev_free_ifa(ifa); - - return err; -} - -static inline size_t dn_ifaddr_nlmsg_size(void) -{ - return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) - + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ - + nla_total_size(2) /* IFA_ADDRESS */ - + nla_total_size(2) /* IFA_LOCAL */ - + nla_total_size(4); /* IFA_FLAGS */ -} - -static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, - u32 portid, u32 seq, int event, unsigned int flags) -{ - struct ifaddrmsg *ifm; - struct nlmsghdr *nlh; - u32 ifa_flags = ifa->ifa_flags | IFA_F_PERMANENT; - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); - if (nlh == NULL) - return -EMSGSIZE; - - ifm = nlmsg_data(nlh); - ifm->ifa_family = AF_DECnet; - ifm->ifa_prefixlen = 16; - ifm->ifa_flags = ifa_flags; - ifm->ifa_scope = ifa->ifa_scope; - ifm->ifa_index = ifa->ifa_dev->dev->ifindex; - - if ((ifa->ifa_address && - nla_put_le16(skb, IFA_ADDRESS, ifa->ifa_address)) || - (ifa->ifa_local && - nla_put_le16(skb, IFA_LOCAL, ifa->ifa_local)) || - (ifa->ifa_label[0] && - nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || - nla_put_u32(skb, IFA_FLAGS, ifa_flags)) - goto nla_put_failure; - nlmsg_end(skb, nlh); - return 0; - -nla_put_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; -} - -static void dn_ifaddr_notify(int event, struct dn_ifaddr *ifa) -{ - struct sk_buff *skb; - int err = -ENOBUFS; - - skb = alloc_skb(dn_ifaddr_nlmsg_size(), GFP_KERNEL); - if (skb == NULL) - goto errout; - - err = dn_nl_fill_ifaddr(skb, ifa, 0, 0, event, 0); - if (err < 0) { - /* -EMSGSIZE implies BUG in dn_ifaddr_nlmsg_size() */ - WARN_ON(err == -EMSGSIZE); - kfree_skb(skb); - goto errout; - } - rtnl_notify(skb, &init_net, 0, RTNLGRP_DECnet_IFADDR, NULL, GFP_KERNEL); - return; -errout: - if (err < 0) - rtnl_set_sk_err(&init_net, RTNLGRP_DECnet_IFADDR, err); -} - -static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - int idx, dn_idx = 0, skip_ndevs, skip_naddr; - struct net_device *dev; - struct dn_dev *dn_db; - struct dn_ifaddr *ifa; - - if (!net_eq(net, &init_net)) - return 0; - - skip_ndevs = cb->args[0]; - skip_naddr = cb->args[1]; - - idx = 0; - rcu_read_lock(); - for_each_netdev_rcu(&init_net, dev) { - if (idx < skip_ndevs) - goto cont; - else if (idx > skip_ndevs) { - /* Only skip over addresses for first dev dumped - * in this iteration (idx == skip_ndevs) */ - skip_naddr = 0; - } - - if ((dn_db = rcu_dereference(dev->dn_ptr)) == NULL) - goto cont; - - for (ifa = rcu_dereference(dn_db->ifa_list), dn_idx = 0; ifa; - ifa = rcu_dereference(ifa->ifa_next), dn_idx++) { - if (dn_idx < skip_naddr) - continue; - - if (dn_nl_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWADDR, - NLM_F_MULTI) < 0) - goto done; - } -cont: - idx++; - } -done: - rcu_read_unlock(); - cb->args[0] = idx; - cb->args[1] = dn_idx; - - return skb->len; -} - -static int dn_dev_get_first(struct net_device *dev, __le16 *addr) -{ - struct dn_dev *dn_db; - struct dn_ifaddr *ifa; - int rv = -ENODEV; - - rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); - if (dn_db == NULL) - goto out; - - ifa = rcu_dereference(dn_db->ifa_list); - if (ifa != NULL) { - *addr = ifa->ifa_local; - rv = 0; - } -out: - rcu_read_unlock(); - return rv; -} - -/* - * Find a default address to bind to. - * - * This is one of those areas where the initial VMS concepts don't really - * map onto the Linux concepts, and since we introduced multiple addresses - * per interface we have to cope with slightly odd ways of finding out what - * "our address" really is. Mostly it's not a problem; for this we just guess - * a sensible default. Eventually the routing code will take care of all the - * nasties for us I hope. - */ -int dn_dev_bind_default(__le16 *addr) -{ - struct net_device *dev; - int rv; - dev = dn_dev_get_default(); -last_chance: - if (dev) { - rv = dn_dev_get_first(dev, addr); - dev_put(dev); - if (rv == 0 || dev == init_net.loopback_dev) - return rv; - } - dev = init_net.loopback_dev; - dev_hold(dev); - goto last_chance; -} - -static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) -{ - struct endnode_hello_message *msg; - struct sk_buff *skb = NULL; - __le16 *pktlen; - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if ((skb = dn_alloc_skb(NULL, sizeof(*msg), GFP_ATOMIC)) == NULL) - return; - - skb->dev = dev; - - msg = skb_put(skb, sizeof(*msg)); - - msg->msgflg = 0x0D; - memcpy(msg->tiver, dn_eco_version, 3); - dn_dn2eth(msg->id, ifa->ifa_local); - msg->iinfo = DN_RT_INFO_ENDN; - msg->blksize = cpu_to_le16(mtu2blksize(dev)); - msg->area = 0x00; - memset(msg->seed, 0, 8); - memcpy(msg->neighbor, dn_hiord, ETH_ALEN); - - if (dn_db->router) { - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; - dn_dn2eth(msg->neighbor, dn->addr); - } - - msg->timer = cpu_to_le16((unsigned short)dn_db->parms.t3); - msg->mpd = 0x00; - msg->datalen = 0x02; - memset(msg->data, 0xAA, 2); - - pktlen = skb_push(skb, 2); - *pktlen = cpu_to_le16(skb->len - 2); - - skb_reset_network_header(skb); - - dn_rt_finish_output(skb, dn_rt_all_rt_mcast, msg->id); -} - - -#define DRDELAY (5 * HZ) - -static int dn_am_i_a_router(struct dn_neigh *dn, struct dn_dev *dn_db, struct dn_ifaddr *ifa) -{ - /* First check time since device went up */ - if (time_before(jiffies, dn_db->uptime + DRDELAY)) - return 0; - - /* If there is no router, then yes... */ - if (!dn_db->router) - return 1; - - /* otherwise only if we have a higher priority or.. */ - if (dn->priority < dn_db->parms.priority) - return 1; - - /* if we have equal priority and a higher node number */ - if (dn->priority != dn_db->parms.priority) - return 0; - - if (le16_to_cpu(dn->addr) < le16_to_cpu(ifa->ifa_local)) - return 1; - - return 0; -} - -static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) -{ - int n; - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; - struct sk_buff *skb; - size_t size; - unsigned char *ptr; - unsigned char *i1, *i2; - __le16 *pktlen; - char *src; - - if (mtu2blksize(dev) < (26 + 7)) - return; - - n = mtu2blksize(dev) - 26; - n /= 7; - - if (n > 32) - n = 32; - - size = 2 + 26 + 7 * n; - - if ((skb = dn_alloc_skb(NULL, size, GFP_ATOMIC)) == NULL) - return; - - skb->dev = dev; - ptr = skb_put(skb, size); - - *ptr++ = DN_RT_PKT_CNTL | DN_RT_PKT_ERTH; - *ptr++ = 2; /* ECO */ - *ptr++ = 0; - *ptr++ = 0; - dn_dn2eth(ptr, ifa->ifa_local); - src = ptr; - ptr += ETH_ALEN; - *ptr++ = dn_db->parms.forwarding == 1 ? - DN_RT_INFO_L1RT : DN_RT_INFO_L2RT; - *((__le16 *)ptr) = cpu_to_le16(mtu2blksize(dev)); - ptr += 2; - *ptr++ = dn_db->parms.priority; /* Priority */ - *ptr++ = 0; /* Area: Reserved */ - *((__le16 *)ptr) = cpu_to_le16((unsigned short)dn_db->parms.t3); - ptr += 2; - *ptr++ = 0; /* MPD: Reserved */ - i1 = ptr++; - memset(ptr, 0, 7); /* Name: Reserved */ - ptr += 7; - i2 = ptr++; - - n = dn_neigh_elist(dev, ptr, n); - - *i2 = 7 * n; - *i1 = 8 + *i2; - - skb_trim(skb, (27 + *i2)); - - pktlen = skb_push(skb, 2); - *pktlen = cpu_to_le16(skb->len - 2); - - skb_reset_network_header(skb); - - if (dn_am_i_a_router(dn, dn_db, ifa)) { - struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC); - if (skb2) { - dn_rt_finish_output(skb2, dn_rt_all_end_mcast, src); - } - } - - dn_rt_finish_output(skb, dn_rt_all_rt_mcast, src); -} - -static void dn_send_brd_hello(struct net_device *dev, struct dn_ifaddr *ifa) -{ - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if (dn_db->parms.forwarding == 0) - dn_send_endnode_hello(dev, ifa); - else - dn_send_router_hello(dev, ifa); -} - -static void dn_send_ptp_hello(struct net_device *dev, struct dn_ifaddr *ifa) -{ - int tdlen = 16; - int size = dev->hard_header_len + 2 + 4 + tdlen; - struct sk_buff *skb = dn_alloc_skb(NULL, size, GFP_ATOMIC); - int i; - unsigned char *ptr; - char src[ETH_ALEN]; - - if (skb == NULL) - return ; - - skb->dev = dev; - skb_push(skb, dev->hard_header_len); - ptr = skb_put(skb, 2 + 4 + tdlen); - - *ptr++ = DN_RT_PKT_HELO; - *((__le16 *)ptr) = ifa->ifa_local; - ptr += 2; - *ptr++ = tdlen; - - for(i = 0; i < tdlen; i++) - *ptr++ = 0252; - - dn_dn2eth(src, ifa->ifa_local); - dn_rt_finish_output(skb, dn_rt_all_rt_mcast, src); -} - -static int dn_eth_up(struct net_device *dev) -{ - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if (dn_db->parms.forwarding == 0) - dev_mc_add(dev, dn_rt_all_end_mcast); - else - dev_mc_add(dev, dn_rt_all_rt_mcast); - - dn_db->use_long = 1; - - return 0; -} - -static void dn_eth_down(struct net_device *dev) -{ - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if (dn_db->parms.forwarding == 0) - dev_mc_del(dev, dn_rt_all_end_mcast); - else - dev_mc_del(dev, dn_rt_all_rt_mcast); -} - -static void dn_dev_set_timer(struct net_device *dev); - -static void dn_dev_timer_func(struct timer_list *t) -{ - struct dn_dev *dn_db = from_timer(dn_db, t, timer); - struct net_device *dev; - struct dn_ifaddr *ifa; - - rcu_read_lock(); - dev = dn_db->dev; - if (dn_db->t3 <= dn_db->parms.t2) { - if (dn_db->parms.timer3) { - for (ifa = rcu_dereference(dn_db->ifa_list); - ifa; - ifa = rcu_dereference(ifa->ifa_next)) { - if (!(ifa->ifa_flags & IFA_F_SECONDARY)) - dn_db->parms.timer3(dev, ifa); - } - } - dn_db->t3 = dn_db->parms.t3; - } else { - dn_db->t3 -= dn_db->parms.t2; - } - rcu_read_unlock(); - dn_dev_set_timer(dev); -} - -static void dn_dev_set_timer(struct net_device *dev) -{ - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if (dn_db->parms.t2 > dn_db->parms.t3) - dn_db->parms.t2 = dn_db->parms.t3; - - dn_db->timer.expires = jiffies + (dn_db->parms.t2 * HZ); - - add_timer(&dn_db->timer); -} - -static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) -{ - int i; - struct dn_dev_parms *p = dn_dev_list; - struct dn_dev *dn_db; - - for(i = 0; i < DN_DEV_LIST_SIZE; i++, p++) { - if (p->type == dev->type) - break; - } - - *err = -ENODEV; - if (i == DN_DEV_LIST_SIZE) - return NULL; - - *err = -ENOBUFS; - if ((dn_db = kzalloc(sizeof(struct dn_dev), GFP_ATOMIC)) == NULL) - return NULL; - - memcpy(&dn_db->parms, p, sizeof(struct dn_dev_parms)); - - rcu_assign_pointer(dev->dn_ptr, dn_db); - dn_db->dev = dev; - timer_setup(&dn_db->timer, dn_dev_timer_func, 0); - - dn_db->uptime = jiffies; - - dn_db->neigh_parms = neigh_parms_alloc(dev, &dn_neigh_table); - if (!dn_db->neigh_parms) { - RCU_INIT_POINTER(dev->dn_ptr, NULL); - kfree(dn_db); - return NULL; - } - - if (dn_db->parms.up) { - if (dn_db->parms.up(dev) < 0) { - neigh_parms_release(&dn_neigh_table, dn_db->neigh_parms); - dev->dn_ptr = NULL; - kfree(dn_db); - return NULL; - } - } - - dn_dev_sysctl_register(dev, &dn_db->parms); - - dn_dev_set_timer(dev); - - *err = 0; - return dn_db; -} - - -/* - * This processes a device up event. We only start up - * the loopback device & ethernet devices with correct - * MAC addresses automatically. Others must be started - * specifically. - * - * FIXME: How should we configure the loopback address ? If we could dispense - * with using decnet_address here and for autobind, it will be one less thing - * for users to worry about setting up. - */ - -void dn_dev_up(struct net_device *dev) -{ - struct dn_ifaddr *ifa; - __le16 addr = decnet_address; - int maybe_default = 0; - struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); - - if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK)) - return; - - /* - * Need to ensure that loopback device has a dn_db attached to it - * to allow creation of neighbours against it, even though it might - * not have a local address of its own. Might as well do the same for - * all autoconfigured interfaces. - */ - if (dn_db == NULL) { - int err; - dn_db = dn_dev_create(dev, &err); - if (dn_db == NULL) - return; - } - - if (dev->type == ARPHRD_ETHER) { - if (memcmp(dev->dev_addr, dn_hiord, 4) != 0) - return; - addr = dn_eth2dn(dev->dev_addr); - maybe_default = 1; - } - - if (addr == 0) - return; - - if ((ifa = dn_dev_alloc_ifa()) == NULL) - return; - - ifa->ifa_local = ifa->ifa_address = addr; - ifa->ifa_flags = 0; - ifa->ifa_scope = RT_SCOPE_UNIVERSE; - strcpy(ifa->ifa_label, dev->name); - - dn_dev_set_ifa(dev, ifa); - - /* - * Automagically set the default device to the first automatically - * configured ethernet card in the system. - */ - if (maybe_default) { - dev_hold(dev); - if (dn_dev_set_default(dev, 0)) - dev_put(dev); - } -} - -static void dn_dev_delete(struct net_device *dev) -{ - struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); - - if (dn_db == NULL) - return; - - del_timer_sync(&dn_db->timer); - dn_dev_sysctl_unregister(&dn_db->parms); - dn_dev_check_default(dev); - neigh_ifdown(&dn_neigh_table, dev); - - if (dn_db->parms.down) - dn_db->parms.down(dev); - - dev->dn_ptr = NULL; - - neigh_parms_release(&dn_neigh_table, dn_db->neigh_parms); - neigh_ifdown(&dn_neigh_table, dev); - - if (dn_db->router) - neigh_release(dn_db->router); - if (dn_db->peer) - neigh_release(dn_db->peer); - - kfree(dn_db); -} - -void dn_dev_down(struct net_device *dev) -{ - struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); - struct dn_ifaddr *ifa; - - if (dn_db == NULL) - return; - - while ((ifa = rtnl_dereference(dn_db->ifa_list)) != NULL) { - dn_dev_del_ifa(dn_db, &dn_db->ifa_list, 0); - dn_dev_free_ifa(ifa); - } - - dn_dev_delete(dev); -} - -void dn_dev_init_pkt(struct sk_buff *skb) -{ -} - -void dn_dev_veri_pkt(struct sk_buff *skb) -{ -} - -void dn_dev_hello(struct sk_buff *skb) -{ -} - -void dn_dev_devices_off(void) -{ - struct net_device *dev; - - rtnl_lock(); - for_each_netdev(&init_net, dev) - dn_dev_down(dev); - rtnl_unlock(); - -} - -void dn_dev_devices_on(void) -{ - struct net_device *dev; - - rtnl_lock(); - for_each_netdev(&init_net, dev) { - if (dev->flags & IFF_UP) - dn_dev_up(dev); - } - rtnl_unlock(); -} - -int register_dnaddr_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_register(&dnaddr_chain, nb); -} - -int unregister_dnaddr_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_unregister(&dnaddr_chain, nb); -} - -#ifdef CONFIG_PROC_FS -static inline int is_dn_dev(struct net_device *dev) -{ - return dev->dn_ptr != NULL; -} - -static void *dn_dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) -{ - int i; - struct net_device *dev; - - rcu_read_lock(); - - if (*pos == 0) - return SEQ_START_TOKEN; - - i = 1; - for_each_netdev_rcu(&init_net, dev) { - if (!is_dn_dev(dev)) - continue; - - if (i++ == *pos) - return dev; - } - - return NULL; -} - -static void *dn_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct net_device *dev; - - ++*pos; - - dev = v; - if (v == SEQ_START_TOKEN) - dev = net_device_entry(&init_net.dev_base_head); - - for_each_netdev_continue_rcu(&init_net, dev) { - if (!is_dn_dev(dev)) - continue; - - return dev; - } - - return NULL; -} - -static void dn_dev_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) -{ - rcu_read_unlock(); -} - -static char *dn_type2asc(char type) -{ - switch (type) { - case DN_DEV_BCAST: - return "B"; - case DN_DEV_UCAST: - return "U"; - case DN_DEV_MPOINT: - return "M"; - } - - return "?"; -} - -static int dn_dev_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Name Flags T1 Timer1 T3 Timer3 BlkSize Pri State DevType Router Peer\n"); - else { - struct net_device *dev = v; - char peer_buf[DN_ASCBUF_LEN]; - char router_buf[DN_ASCBUF_LEN]; - struct dn_dev *dn_db = rcu_dereference(dev->dn_ptr); - - seq_printf(seq, "%-8s %1s %04u %04u %04lu %04lu" - " %04hu %03d %02x %-10s %-7s %-7s\n", - dev->name, - dn_type2asc(dn_db->parms.mode), - 0, 0, - dn_db->t3, dn_db->parms.t3, - mtu2blksize(dev), - dn_db->parms.priority, - dn_db->parms.state, dn_db->parms.name, - dn_db->router ? dn_addr2asc(le16_to_cpu(*(__le16 *)dn_db->router->primary_key), router_buf) : "", - dn_db->peer ? dn_addr2asc(le16_to_cpu(*(__le16 *)dn_db->peer->primary_key), peer_buf) : ""); - } - return 0; -} - -static const struct seq_operations dn_dev_seq_ops = { - .start = dn_dev_seq_start, - .next = dn_dev_seq_next, - .stop = dn_dev_seq_stop, - .show = dn_dev_seq_show, -}; -#endif /* CONFIG_PROC_FS */ - -static int addr[2]; -module_param_array(addr, int, NULL, 0444); -MODULE_PARM_DESC(addr, "The DECnet address of this machine: area,node"); - -void __init dn_dev_init(void) -{ - if (addr[0] > 63 || addr[0] < 0) { - printk(KERN_ERR "DECnet: Area must be between 0 and 63"); - return; - } - - if (addr[1] > 1023 || addr[1] < 0) { - printk(KERN_ERR "DECnet: Node must be between 0 and 1023"); - return; - } - - decnet_address = cpu_to_le16((addr[0] << 10) | addr[1]); - - dn_dev_devices_on(); - - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_NEWADDR, - dn_nl_newaddr, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_DELADDR, - dn_nl_deladdr, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETADDR, - NULL, dn_nl_dump_ifaddr, 0); - - proc_create_seq("decnet_dev", 0444, init_net.proc_net, &dn_dev_seq_ops); - -#ifdef CONFIG_SYSCTL - { - int i; - for(i = 0; i < DN_DEV_LIST_SIZE; i++) - dn_dev_sysctl_register(NULL, &dn_dev_list[i]); - } -#endif /* CONFIG_SYSCTL */ -} - -void __exit dn_dev_cleanup(void) -{ -#ifdef CONFIG_SYSCTL - { - int i; - for(i = 0; i < DN_DEV_LIST_SIZE; i++) - dn_dev_sysctl_unregister(&dn_dev_list[i]); - } -#endif /* CONFIG_SYSCTL */ - - remove_proc_entry("decnet_dev", init_net.proc_net); - - dn_dev_devices_off(); -} diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c deleted file mode 100644 index 77fbf8e9df4b..000000000000 --- a/net/decnet/dn_fib.c +++ /dev/null @@ -1,799 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Forwarding Information Base (Glue/Info List) - * - * Author: Steve Whitehouse - * - * - * Changes: - * Alexey Kuznetsov : SMP locking changes - * Steve Whitehouse : Rewrote it... Well to be more correct, I - * copied most of it from the ipv4 fib code. - * Steve Whitehouse : Updated it in style and fixed a few bugs - * which were fixed in the ipv4 code since - * this code was copied from it. - * - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define RT_MIN_TABLE 1 - -#define for_fib_info() { struct dn_fib_info *fi;\ - for(fi = dn_fib_info_list; fi; fi = fi->fib_next) -#define endfor_fib_info() } - -#define for_nexthops(fi) { int nhsel; const struct dn_fib_nh *nh;\ - for(nhsel = 0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) - -#define change_nexthops(fi) { int nhsel; struct dn_fib_nh *nh;\ - for(nhsel = 0, nh = (struct dn_fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++) - -#define endfor_nexthops(fi) } - -static DEFINE_SPINLOCK(dn_fib_multipath_lock); -static struct dn_fib_info *dn_fib_info_list; -static DEFINE_SPINLOCK(dn_fib_info_lock); - -static struct -{ - int error; - u8 scope; -} dn_fib_props[RTN_MAX+1] = { - [RTN_UNSPEC] = { .error = 0, .scope = RT_SCOPE_NOWHERE }, - [RTN_UNICAST] = { .error = 0, .scope = RT_SCOPE_UNIVERSE }, - [RTN_LOCAL] = { .error = 0, .scope = RT_SCOPE_HOST }, - [RTN_BROADCAST] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE }, - [RTN_ANYCAST] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE }, - [RTN_MULTICAST] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE }, - [RTN_BLACKHOLE] = { .error = -EINVAL, .scope = RT_SCOPE_UNIVERSE }, - [RTN_UNREACHABLE] = { .error = -EHOSTUNREACH, .scope = RT_SCOPE_UNIVERSE }, - [RTN_PROHIBIT] = { .error = -EACCES, .scope = RT_SCOPE_UNIVERSE }, - [RTN_THROW] = { .error = -EAGAIN, .scope = RT_SCOPE_UNIVERSE }, - [RTN_NAT] = { .error = 0, .scope = RT_SCOPE_NOWHERE }, - [RTN_XRESOLVE] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE }, -}; - -static int dn_fib_sync_down(__le16 local, struct net_device *dev, int force); -static int dn_fib_sync_up(struct net_device *dev); - -void dn_fib_free_info(struct dn_fib_info *fi) -{ - if (fi->fib_dead == 0) { - printk(KERN_DEBUG "DECnet: BUG! Attempt to free alive dn_fib_info\n"); - return; - } - - change_nexthops(fi) { - if (nh->nh_dev) - dev_put(nh->nh_dev); - nh->nh_dev = NULL; - } endfor_nexthops(fi); - kfree(fi); -} - -void dn_fib_release_info(struct dn_fib_info *fi) -{ - spin_lock(&dn_fib_info_lock); - if (fi && --fi->fib_treeref == 0) { - if (fi->fib_next) - fi->fib_next->fib_prev = fi->fib_prev; - if (fi->fib_prev) - fi->fib_prev->fib_next = fi->fib_next; - if (fi == dn_fib_info_list) - dn_fib_info_list = fi->fib_next; - fi->fib_dead = 1; - dn_fib_info_put(fi); - } - spin_unlock(&dn_fib_info_lock); -} - -static inline int dn_fib_nh_comp(const struct dn_fib_info *fi, const struct dn_fib_info *ofi) -{ - const struct dn_fib_nh *onh = ofi->fib_nh; - - for_nexthops(fi) { - if (nh->nh_oif != onh->nh_oif || - nh->nh_gw != onh->nh_gw || - nh->nh_scope != onh->nh_scope || - nh->nh_weight != onh->nh_weight || - ((nh->nh_flags^onh->nh_flags)&~RTNH_F_DEAD)) - return -1; - onh++; - } endfor_nexthops(fi); - return 0; -} - -static inline struct dn_fib_info *dn_fib_find_info(const struct dn_fib_info *nfi) -{ - for_fib_info() { - if (fi->fib_nhs != nfi->fib_nhs) - continue; - if (nfi->fib_protocol == fi->fib_protocol && - nfi->fib_prefsrc == fi->fib_prefsrc && - nfi->fib_priority == fi->fib_priority && - memcmp(nfi->fib_metrics, fi->fib_metrics, sizeof(fi->fib_metrics)) == 0 && - ((nfi->fib_flags^fi->fib_flags)&~RTNH_F_DEAD) == 0 && - (nfi->fib_nhs == 0 || dn_fib_nh_comp(fi, nfi) == 0)) - return fi; - } endfor_fib_info(); - return NULL; -} - -static int dn_fib_count_nhs(const struct nlattr *attr) -{ - struct rtnexthop *nhp = nla_data(attr); - int nhs = 0, nhlen = nla_len(attr); - - while (rtnh_ok(nhp, nhlen)) { - nhs++; - nhp = rtnh_next(nhp, &nhlen); - } - - /* leftover implies invalid nexthop configuration, discard it */ - return nhlen > 0 ? 0 : nhs; -} - -static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr, - const struct rtmsg *r) -{ - struct rtnexthop *nhp = nla_data(attr); - int nhlen = nla_len(attr); - - change_nexthops(fi) { - int attrlen; - - if (!rtnh_ok(nhp, nhlen)) - return -EINVAL; - - nh->nh_flags = (r->rtm_flags&~0xFF) | nhp->rtnh_flags; - nh->nh_oif = nhp->rtnh_ifindex; - nh->nh_weight = nhp->rtnh_hops + 1; - - attrlen = rtnh_attrlen(nhp); - if (attrlen > 0) { - struct nlattr *gw_attr; - - gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY); - nh->nh_gw = gw_attr ? nla_get_le16(gw_attr) : 0; - } - - nhp = rtnh_next(nhp, &nhlen); - } endfor_nexthops(fi); - - return 0; -} - - -static int dn_fib_check_nh(const struct rtmsg *r, struct dn_fib_info *fi, struct dn_fib_nh *nh) -{ - int err; - - if (nh->nh_gw) { - struct flowidn fld; - struct dn_fib_res res; - - if (nh->nh_flags&RTNH_F_ONLINK) { - struct net_device *dev; - - if (r->rtm_scope >= RT_SCOPE_LINK) - return -EINVAL; - if (dnet_addr_type(nh->nh_gw) != RTN_UNICAST) - return -EINVAL; - if ((dev = __dev_get_by_index(&init_net, nh->nh_oif)) == NULL) - return -ENODEV; - if (!(dev->flags&IFF_UP)) - return -ENETDOWN; - nh->nh_dev = dev; - dev_hold(dev); - nh->nh_scope = RT_SCOPE_LINK; - return 0; - } - - memset(&fld, 0, sizeof(fld)); - fld.daddr = nh->nh_gw; - fld.flowidn_oif = nh->nh_oif; - fld.flowidn_scope = r->rtm_scope + 1; - - if (fld.flowidn_scope < RT_SCOPE_LINK) - fld.flowidn_scope = RT_SCOPE_LINK; - - if ((err = dn_fib_lookup(&fld, &res)) != 0) - return err; - - err = -EINVAL; - if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) - goto out; - nh->nh_scope = res.scope; - nh->nh_oif = DN_FIB_RES_OIF(res); - nh->nh_dev = DN_FIB_RES_DEV(res); - if (nh->nh_dev == NULL) - goto out; - dev_hold(nh->nh_dev); - err = -ENETDOWN; - if (!(nh->nh_dev->flags & IFF_UP)) - goto out; - err = 0; -out: - dn_fib_res_put(&res); - return err; - } else { - struct net_device *dev; - - if (nh->nh_flags&(RTNH_F_PERVASIVE|RTNH_F_ONLINK)) - return -EINVAL; - - dev = __dev_get_by_index(&init_net, nh->nh_oif); - if (dev == NULL || dev->dn_ptr == NULL) - return -ENODEV; - if (!(dev->flags&IFF_UP)) - return -ENETDOWN; - nh->nh_dev = dev; - dev_hold(nh->nh_dev); - nh->nh_scope = RT_SCOPE_HOST; - } - - return 0; -} - - -struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct nlattr *attrs[], - const struct nlmsghdr *nlh, int *errp) -{ - int err; - struct dn_fib_info *fi = NULL; - struct dn_fib_info *ofi; - int nhs = 1; - - if (r->rtm_type > RTN_MAX) - goto err_inval; - - if (dn_fib_props[r->rtm_type].scope > r->rtm_scope) - goto err_inval; - - if (attrs[RTA_MULTIPATH] && - (nhs = dn_fib_count_nhs(attrs[RTA_MULTIPATH])) == 0) - goto err_inval; - - fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL); - err = -ENOBUFS; - if (fi == NULL) - goto failure; - - fi->fib_protocol = r->rtm_protocol; - fi->fib_nhs = nhs; - fi->fib_flags = r->rtm_flags; - - if (attrs[RTA_PRIORITY]) - fi->fib_priority = nla_get_u32(attrs[RTA_PRIORITY]); - - if (attrs[RTA_METRICS]) { - struct nlattr *attr; - int rem; - - nla_for_each_nested(attr, attrs[RTA_METRICS], rem) { - int type = nla_type(attr); - - if (type) { - if (type > RTAX_MAX || type == RTAX_CC_ALGO || - nla_len(attr) < 4) - goto err_inval; - - fi->fib_metrics[type-1] = nla_get_u32(attr); - } - } - } - - if (attrs[RTA_PREFSRC]) - fi->fib_prefsrc = nla_get_le16(attrs[RTA_PREFSRC]); - - if (attrs[RTA_MULTIPATH]) { - if ((err = dn_fib_get_nhs(fi, attrs[RTA_MULTIPATH], r)) != 0) - goto failure; - - if (attrs[RTA_OIF] && - fi->fib_nh->nh_oif != nla_get_u32(attrs[RTA_OIF])) - goto err_inval; - - if (attrs[RTA_GATEWAY] && - fi->fib_nh->nh_gw != nla_get_le16(attrs[RTA_GATEWAY])) - goto err_inval; - } else { - struct dn_fib_nh *nh = fi->fib_nh; - - if (attrs[RTA_OIF]) - nh->nh_oif = nla_get_u32(attrs[RTA_OIF]); - - if (attrs[RTA_GATEWAY]) - nh->nh_gw = nla_get_le16(attrs[RTA_GATEWAY]); - - nh->nh_flags = r->rtm_flags; - nh->nh_weight = 1; - } - - if (r->rtm_type == RTN_NAT) { - if (!attrs[RTA_GATEWAY] || nhs != 1 || attrs[RTA_OIF]) - goto err_inval; - - fi->fib_nh->nh_gw = nla_get_le16(attrs[RTA_GATEWAY]); - goto link_it; - } - - if (dn_fib_props[r->rtm_type].error) { - if (attrs[RTA_GATEWAY] || attrs[RTA_OIF] || attrs[RTA_MULTIPATH]) - goto err_inval; - - goto link_it; - } - - if (r->rtm_scope > RT_SCOPE_HOST) - goto err_inval; - - if (r->rtm_scope == RT_SCOPE_HOST) { - struct dn_fib_nh *nh = fi->fib_nh; - - /* Local address is added */ - if (nhs != 1 || nh->nh_gw) - goto err_inval; - nh->nh_scope = RT_SCOPE_NOWHERE; - nh->nh_dev = dev_get_by_index(&init_net, fi->fib_nh->nh_oif); - err = -ENODEV; - if (nh->nh_dev == NULL) - goto failure; - } else { - change_nexthops(fi) { - if ((err = dn_fib_check_nh(r, fi, nh)) != 0) - goto failure; - } endfor_nexthops(fi) - } - - if (fi->fib_prefsrc) { - if (r->rtm_type != RTN_LOCAL || !attrs[RTA_DST] || - fi->fib_prefsrc != nla_get_le16(attrs[RTA_DST])) - if (dnet_addr_type(fi->fib_prefsrc) != RTN_LOCAL) - goto err_inval; - } - -link_it: - if ((ofi = dn_fib_find_info(fi)) != NULL) { - fi->fib_dead = 1; - dn_fib_free_info(fi); - ofi->fib_treeref++; - return ofi; - } - - fi->fib_treeref++; - refcount_set(&fi->fib_clntref, 1); - spin_lock(&dn_fib_info_lock); - fi->fib_next = dn_fib_info_list; - fi->fib_prev = NULL; - if (dn_fib_info_list) - dn_fib_info_list->fib_prev = fi; - dn_fib_info_list = fi; - spin_unlock(&dn_fib_info_lock); - return fi; - -err_inval: - err = -EINVAL; - -failure: - *errp = err; - if (fi) { - fi->fib_dead = 1; - dn_fib_free_info(fi); - } - - return NULL; -} - -int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn *fld, struct dn_fib_res *res) -{ - int err = dn_fib_props[type].error; - - if (err == 0) { - if (fi->fib_flags & RTNH_F_DEAD) - return 1; - - res->fi = fi; - - switch (type) { - case RTN_NAT: - DN_FIB_RES_RESET(*res); - refcount_inc(&fi->fib_clntref); - return 0; - case RTN_UNICAST: - case RTN_LOCAL: - for_nexthops(fi) { - if (nh->nh_flags & RTNH_F_DEAD) - continue; - if (!fld->flowidn_oif || - fld->flowidn_oif == nh->nh_oif) - break; - } - if (nhsel < fi->fib_nhs) { - res->nh_sel = nhsel; - refcount_inc(&fi->fib_clntref); - return 0; - } - endfor_nexthops(fi); - res->fi = NULL; - return 1; - default: - net_err_ratelimited("DECnet: impossible routing event : dn_fib_semantic_match type=%d\n", - type); - res->fi = NULL; - return -EINVAL; - } - } - return err; -} - -void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res) -{ - struct dn_fib_info *fi = res->fi; - int w; - - spin_lock_bh(&dn_fib_multipath_lock); - if (fi->fib_power <= 0) { - int power = 0; - change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD)) { - power += nh->nh_weight; - nh->nh_power = nh->nh_weight; - } - } endfor_nexthops(fi); - fi->fib_power = power; - if (power < 0) { - spin_unlock_bh(&dn_fib_multipath_lock); - res->nh_sel = 0; - return; - } - } - - w = jiffies % fi->fib_power; - - change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD) && nh->nh_power) { - if ((w -= nh->nh_power) <= 0) { - nh->nh_power--; - fi->fib_power--; - res->nh_sel = nhsel; - spin_unlock_bh(&dn_fib_multipath_lock); - return; - } - } - } endfor_nexthops(fi); - res->nh_sel = 0; - spin_unlock_bh(&dn_fib_multipath_lock); -} - -static inline u32 rtm_get_table(struct nlattr *attrs[], u8 table) -{ - if (attrs[RTA_TABLE]) - table = nla_get_u32(attrs[RTA_TABLE]); - - return table; -} - -static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(skb->sk); - struct dn_fib_table *tb; - struct rtmsg *r = nlmsg_data(nlh); - struct nlattr *attrs[RTA_MAX+1]; - int err; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!net_eq(net, &init_net)) - return -EINVAL; - - err = nlmsg_parse_deprecated(nlh, sizeof(*r), attrs, RTA_MAX, - rtm_dn_policy, extack); - if (err < 0) - return err; - - tb = dn_fib_get_table(rtm_get_table(attrs, r->rtm_table), 0); - if (!tb) - return -ESRCH; - - return tb->delete(tb, r, attrs, nlh, &NETLINK_CB(skb)); -} - -static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(skb->sk); - struct dn_fib_table *tb; - struct rtmsg *r = nlmsg_data(nlh); - struct nlattr *attrs[RTA_MAX+1]; - int err; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!net_eq(net, &init_net)) - return -EINVAL; - - err = nlmsg_parse_deprecated(nlh, sizeof(*r), attrs, RTA_MAX, - rtm_dn_policy, extack); - if (err < 0) - return err; - - tb = dn_fib_get_table(rtm_get_table(attrs, r->rtm_table), 1); - if (!tb) - return -ENOBUFS; - - return tb->insert(tb, r, attrs, nlh, &NETLINK_CB(skb)); -} - -static void fib_magic(int cmd, int type, __le16 dst, int dst_len, struct dn_ifaddr *ifa) -{ - struct dn_fib_table *tb; - struct { - struct nlmsghdr nlh; - struct rtmsg rtm; - } req; - struct { - struct nlattr hdr; - __le16 dst; - } dst_attr = { - .dst = dst, - }; - struct { - struct nlattr hdr; - __le16 prefsrc; - } prefsrc_attr = { - .prefsrc = ifa->ifa_local, - }; - struct { - struct nlattr hdr; - u32 oif; - } oif_attr = { - .oif = ifa->ifa_dev->dev->ifindex, - }; - struct nlattr *attrs[RTA_MAX+1] = { - [RTA_DST] = (struct nlattr *) &dst_attr, - [RTA_PREFSRC] = (struct nlattr * ) &prefsrc_attr, - [RTA_OIF] = (struct nlattr *) &oif_attr, - }; - - memset(&req.rtm, 0, sizeof(req.rtm)); - - if (type == RTN_UNICAST) - tb = dn_fib_get_table(RT_MIN_TABLE, 1); - else - tb = dn_fib_get_table(RT_TABLE_LOCAL, 1); - - if (tb == NULL) - return; - - req.nlh.nlmsg_len = sizeof(req); - req.nlh.nlmsg_type = cmd; - req.nlh.nlmsg_flags = NLM_F_REQUEST|NLM_F_CREATE|NLM_F_APPEND; - req.nlh.nlmsg_pid = 0; - req.nlh.nlmsg_seq = 0; - - req.rtm.rtm_dst_len = dst_len; - req.rtm.rtm_table = tb->n; - req.rtm.rtm_protocol = RTPROT_KERNEL; - req.rtm.rtm_scope = (type != RTN_LOCAL ? RT_SCOPE_LINK : RT_SCOPE_HOST); - req.rtm.rtm_type = type; - - if (cmd == RTM_NEWROUTE) - tb->insert(tb, &req.rtm, attrs, &req.nlh, NULL); - else - tb->delete(tb, &req.rtm, attrs, &req.nlh, NULL); -} - -static void dn_fib_add_ifaddr(struct dn_ifaddr *ifa) -{ - - fib_magic(RTM_NEWROUTE, RTN_LOCAL, ifa->ifa_local, 16, ifa); - -#if 0 - if (!(dev->flags&IFF_UP)) - return; - /* In the future, we will want to add default routes here */ - -#endif -} - -static void dn_fib_del_ifaddr(struct dn_ifaddr *ifa) -{ - int found_it = 0; - struct net_device *dev; - struct dn_dev *dn_db; - struct dn_ifaddr *ifa2; - - ASSERT_RTNL(); - - /* Scan device list */ - rcu_read_lock(); - for_each_netdev_rcu(&init_net, dev) { - dn_db = rcu_dereference(dev->dn_ptr); - if (dn_db == NULL) - continue; - for (ifa2 = rcu_dereference(dn_db->ifa_list); - ifa2 != NULL; - ifa2 = rcu_dereference(ifa2->ifa_next)) { - if (ifa2->ifa_local == ifa->ifa_local) { - found_it = 1; - break; - } - } - } - rcu_read_unlock(); - - if (found_it == 0) { - fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 16, ifa); - - if (dnet_addr_type(ifa->ifa_local) != RTN_LOCAL) { - if (dn_fib_sync_down(ifa->ifa_local, NULL, 0)) - dn_fib_flush(); - } - } -} - -static void dn_fib_disable_addr(struct net_device *dev, int force) -{ - if (dn_fib_sync_down(0, dev, force)) - dn_fib_flush(); - dn_rt_cache_flush(0); - neigh_ifdown(&dn_neigh_table, dev); -} - -static int dn_fib_dnaddr_event(struct notifier_block *this, unsigned long event, void *ptr) -{ - struct dn_ifaddr *ifa = (struct dn_ifaddr *)ptr; - - switch (event) { - case NETDEV_UP: - dn_fib_add_ifaddr(ifa); - dn_fib_sync_up(ifa->ifa_dev->dev); - dn_rt_cache_flush(-1); - break; - case NETDEV_DOWN: - dn_fib_del_ifaddr(ifa); - if (ifa->ifa_dev && ifa->ifa_dev->ifa_list == NULL) { - dn_fib_disable_addr(ifa->ifa_dev->dev, 1); - } else { - dn_rt_cache_flush(-1); - } - break; - } - return NOTIFY_DONE; -} - -static int dn_fib_sync_down(__le16 local, struct net_device *dev, int force) -{ - int ret = 0; - int scope = RT_SCOPE_NOWHERE; - - if (force) - scope = -1; - - for_fib_info() { - /* - * This makes no sense for DECnet.... we will almost - * certainly have more than one local address the same - * over all our interfaces. It needs thinking about - * some more. - */ - if (local && fi->fib_prefsrc == local) { - fi->fib_flags |= RTNH_F_DEAD; - ret++; - } else if (dev && fi->fib_nhs) { - int dead = 0; - - change_nexthops(fi) { - if (nh->nh_flags&RTNH_F_DEAD) - dead++; - else if (nh->nh_dev == dev && - nh->nh_scope != scope) { - spin_lock_bh(&dn_fib_multipath_lock); - nh->nh_flags |= RTNH_F_DEAD; - fi->fib_power -= nh->nh_power; - nh->nh_power = 0; - spin_unlock_bh(&dn_fib_multipath_lock); - dead++; - } - } endfor_nexthops(fi) - if (dead == fi->fib_nhs) { - fi->fib_flags |= RTNH_F_DEAD; - ret++; - } - } - } endfor_fib_info(); - return ret; -} - - -static int dn_fib_sync_up(struct net_device *dev) -{ - int ret = 0; - - if (!(dev->flags&IFF_UP)) - return 0; - - for_fib_info() { - int alive = 0; - - change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD)) { - alive++; - continue; - } - if (nh->nh_dev == NULL || !(nh->nh_dev->flags&IFF_UP)) - continue; - if (nh->nh_dev != dev || dev->dn_ptr == NULL) - continue; - alive++; - spin_lock_bh(&dn_fib_multipath_lock); - nh->nh_power = 0; - nh->nh_flags &= ~RTNH_F_DEAD; - spin_unlock_bh(&dn_fib_multipath_lock); - } endfor_nexthops(fi); - - if (alive > 0) { - fi->fib_flags &= ~RTNH_F_DEAD; - ret++; - } - } endfor_fib_info(); - return ret; -} - -static struct notifier_block dn_fib_dnaddr_notifier = { - .notifier_call = dn_fib_dnaddr_event, -}; - -void __exit dn_fib_cleanup(void) -{ - dn_fib_table_cleanup(); - dn_fib_rules_cleanup(); - - unregister_dnaddr_notifier(&dn_fib_dnaddr_notifier); -} - - -void __init dn_fib_init(void) -{ - dn_fib_table_init(); - dn_fib_rules_init(); - - register_dnaddr_notifier(&dn_fib_dnaddr_notifier); - - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_NEWROUTE, - dn_fib_rtm_newroute, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_DELROUTE, - dn_fib_rtm_delroute, NULL, 0); -} diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c deleted file mode 100644 index 94b306f6d551..000000000000 --- a/net/decnet/dn_neigh.c +++ /dev/null @@ -1,605 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Neighbour Functions (Adjacency Database and - * On-Ethernet Cache) - * - * Author: Steve Whitehouse - * - * - * Changes: - * Steve Whitehouse : Fixed router listing routine - * Steve Whitehouse : Added error_report functions - * Steve Whitehouse : Added default router detection - * Steve Whitehouse : Hop counts in outgoing messages - * Steve Whitehouse : Fixed src/dst in outgoing messages so - * forwarding now stands a good chance of - * working. - * Steve Whitehouse : Fixed neighbour states (for now anyway). - * Steve Whitehouse : Made error_report functions dummies. This - * is not the right place to return skbs. - * Steve Whitehouse : Convert to seq_file - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static int dn_neigh_construct(struct neighbour *); -static void dn_neigh_error_report(struct neighbour *, struct sk_buff *); -static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb); - -/* - * Operations for adding the link layer header. - */ -static const struct neigh_ops dn_neigh_ops = { - .family = AF_DECnet, - .error_report = dn_neigh_error_report, - .output = dn_neigh_output, - .connected_output = dn_neigh_output, -}; - -static u32 dn_neigh_hash(const void *pkey, - const struct net_device *dev, - __u32 *hash_rnd) -{ - return jhash_2words(*(__u16 *)pkey, 0, hash_rnd[0]); -} - -static bool dn_key_eq(const struct neighbour *neigh, const void *pkey) -{ - return neigh_key_eq16(neigh, pkey); -} - -struct neigh_table dn_neigh_table = { - .family = PF_DECnet, - .entry_size = NEIGH_ENTRY_SIZE(sizeof(struct dn_neigh)), - .key_len = sizeof(__le16), - .protocol = cpu_to_be16(ETH_P_DNA_RT), - .hash = dn_neigh_hash, - .key_eq = dn_key_eq, - .constructor = dn_neigh_construct, - .id = "dn_neigh_cache", - .parms ={ - .tbl = &dn_neigh_table, - .reachable_time = 30 * HZ, - .data = { - [NEIGH_VAR_MCAST_PROBES] = 0, - [NEIGH_VAR_UCAST_PROBES] = 0, - [NEIGH_VAR_APP_PROBES] = 0, - [NEIGH_VAR_RETRANS_TIME] = 1 * HZ, - [NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ, - [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, - [NEIGH_VAR_GC_STALETIME] = 60 * HZ, - [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, - [NEIGH_VAR_PROXY_QLEN] = 0, - [NEIGH_VAR_ANYCAST_DELAY] = 0, - [NEIGH_VAR_PROXY_DELAY] = 0, - [NEIGH_VAR_LOCKTIME] = 1 * HZ, - }, - }, - .gc_interval = 30 * HZ, - .gc_thresh1 = 128, - .gc_thresh2 = 512, - .gc_thresh3 = 1024, -}; - -static int dn_neigh_construct(struct neighbour *neigh) -{ - struct net_device *dev = neigh->dev; - struct dn_neigh *dn = container_of(neigh, struct dn_neigh, n); - struct dn_dev *dn_db; - struct neigh_parms *parms; - - rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); - if (dn_db == NULL) { - rcu_read_unlock(); - return -EINVAL; - } - - parms = dn_db->neigh_parms; - if (!parms) { - rcu_read_unlock(); - return -EINVAL; - } - - __neigh_parms_put(neigh->parms); - neigh->parms = neigh_parms_clone(parms); - rcu_read_unlock(); - - neigh->ops = &dn_neigh_ops; - neigh->nud_state = NUD_NOARP; - neigh->output = neigh->ops->connected_output; - - if ((dev->type == ARPHRD_IPGRE) || (dev->flags & IFF_POINTOPOINT)) - memcpy(neigh->ha, dev->broadcast, dev->addr_len); - else if ((dev->type == ARPHRD_ETHER) || (dev->type == ARPHRD_LOOPBACK)) - dn_dn2eth(neigh->ha, dn->addr); - else { - net_dbg_ratelimited("Trying to create neigh for hw %d\n", - dev->type); - return -EINVAL; - } - - /* - * Make an estimate of the remote block size by assuming that its - * two less then the device mtu, which it true for ethernet (and - * other things which support long format headers) since there is - * an extra length field (of 16 bits) which isn't part of the - * ethernet headers and which the DECnet specs won't admit is part - * of the DECnet routing headers either. - * - * If we over estimate here its no big deal, the NSP negotiations - * will prevent us from sending packets which are too large for the - * remote node to handle. In any case this figure is normally updated - * by a hello message in most cases. - */ - dn->blksize = dev->mtu - 2; - - return 0; -} - -static void dn_neigh_error_report(struct neighbour *neigh, struct sk_buff *skb) -{ - printk(KERN_DEBUG "dn_neigh_error_report: called\n"); - kfree_skb(skb); -} - -static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - struct dn_route *rt = (struct dn_route *)dst; - struct net_device *dev = neigh->dev; - char mac_addr[ETH_ALEN]; - unsigned int seq; - int err; - - dn_dn2eth(mac_addr, rt->rt_local_src); - do { - seq = read_seqbegin(&neigh->ha_lock); - err = dev_hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, mac_addr, skb->len); - } while (read_seqretry(&neigh->ha_lock, seq)); - - if (err >= 0) - err = dev_queue_xmit(skb); - else { - kfree_skb(skb); - err = -EINVAL; - } - return err; -} - -static int dn_neigh_output_packet(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - struct dn_route *rt = (struct dn_route *)dst; - struct neighbour *neigh = rt->n; - - return neigh->output(neigh, skb); -} - -/* - * For talking to broadcast devices: Ethernet & PPP - */ -static int dn_long_output(struct neighbour *neigh, struct sock *sk, - struct sk_buff *skb) -{ - struct net_device *dev = neigh->dev; - int headroom = dev->hard_header_len + sizeof(struct dn_long_packet) + 3; - unsigned char *data; - struct dn_long_packet *lp; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - - if (skb_headroom(skb) < headroom) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); - if (skb2 == NULL) { - net_crit_ratelimited("dn_long_output: no memory\n"); - kfree_skb(skb); - return -ENOBUFS; - } - consume_skb(skb); - skb = skb2; - net_info_ratelimited("dn_long_output: Increasing headroom\n"); - } - - data = skb_push(skb, sizeof(struct dn_long_packet) + 3); - lp = (struct dn_long_packet *)(data+3); - - *((__le16 *)data) = cpu_to_le16(skb->len - 2); - *(data + 2) = 1 | DN_RT_F_PF; /* Padding */ - - lp->msgflg = DN_RT_PKT_LONG|(cb->rt_flags&(DN_RT_F_IE|DN_RT_F_RQR|DN_RT_F_RTS)); - lp->d_area = lp->d_subarea = 0; - dn_dn2eth(lp->d_id, cb->dst); - lp->s_area = lp->s_subarea = 0; - dn_dn2eth(lp->s_id, cb->src); - lp->nl2 = 0; - lp->visit_ct = cb->hops & 0x3f; - lp->s_class = 0; - lp->pt = 0; - - skb_reset_network_header(skb); - - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, - &init_net, sk, skb, NULL, neigh->dev, - dn_neigh_output_packet); -} - -/* - * For talking to pointopoint and multidrop devices: DDCMP and X.25 - */ -static int dn_short_output(struct neighbour *neigh, struct sock *sk, - struct sk_buff *skb) -{ - struct net_device *dev = neigh->dev; - int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; - struct dn_short_packet *sp; - unsigned char *data; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - - if (skb_headroom(skb) < headroom) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); - if (skb2 == NULL) { - net_crit_ratelimited("dn_short_output: no memory\n"); - kfree_skb(skb); - return -ENOBUFS; - } - consume_skb(skb); - skb = skb2; - net_info_ratelimited("dn_short_output: Increasing headroom\n"); - } - - data = skb_push(skb, sizeof(struct dn_short_packet) + 2); - *((__le16 *)data) = cpu_to_le16(skb->len - 2); - sp = (struct dn_short_packet *)(data+2); - - sp->msgflg = DN_RT_PKT_SHORT|(cb->rt_flags&(DN_RT_F_RQR|DN_RT_F_RTS)); - sp->dstnode = cb->dst; - sp->srcnode = cb->src; - sp->forward = cb->hops & 0x3f; - - skb_reset_network_header(skb); - - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, - &init_net, sk, skb, NULL, neigh->dev, - dn_neigh_output_packet); -} - -/* - * For talking to DECnet phase III nodes - * Phase 3 output is the same as short output, execpt that - * it clears the area bits before transmission. - */ -static int dn_phase3_output(struct neighbour *neigh, struct sock *sk, - struct sk_buff *skb) -{ - struct net_device *dev = neigh->dev; - int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; - struct dn_short_packet *sp; - unsigned char *data; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - if (skb_headroom(skb) < headroom) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); - if (skb2 == NULL) { - net_crit_ratelimited("dn_phase3_output: no memory\n"); - kfree_skb(skb); - return -ENOBUFS; - } - consume_skb(skb); - skb = skb2; - net_info_ratelimited("dn_phase3_output: Increasing headroom\n"); - } - - data = skb_push(skb, sizeof(struct dn_short_packet) + 2); - *((__le16 *)data) = cpu_to_le16(skb->len - 2); - sp = (struct dn_short_packet *)(data + 2); - - sp->msgflg = DN_RT_PKT_SHORT|(cb->rt_flags&(DN_RT_F_RQR|DN_RT_F_RTS)); - sp->dstnode = cb->dst & cpu_to_le16(0x03ff); - sp->srcnode = cb->src & cpu_to_le16(0x03ff); - sp->forward = cb->hops & 0x3f; - - skb_reset_network_header(skb); - - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, - &init_net, sk, skb, NULL, neigh->dev, - dn_neigh_output_packet); -} - -int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - struct dn_route *rt = (struct dn_route *) dst; - struct neighbour *neigh = rt->n; - struct dn_neigh *dn = container_of(neigh, struct dn_neigh, n); - struct dn_dev *dn_db; - bool use_long; - - rcu_read_lock(); - dn_db = rcu_dereference(neigh->dev->dn_ptr); - if (dn_db == NULL) { - rcu_read_unlock(); - return -EINVAL; - } - use_long = dn_db->use_long; - rcu_read_unlock(); - - if (dn->flags & DN_NDFLAG_P3) - return dn_phase3_output(neigh, sk, skb); - if (use_long) - return dn_long_output(neigh, sk, skb); - else - return dn_short_output(neigh, sk, skb); -} - -/* - * Unfortunately, the neighbour code uses the device in its hash - * function, so we don't get any advantage from it. This function - * basically does a neigh_lookup(), but without comparing the device - * field. This is required for the On-Ethernet cache - */ - -/* - * Pointopoint link receives a hello message - */ -void dn_neigh_pointopoint_hello(struct sk_buff *skb) -{ - kfree_skb(skb); -} - -/* - * Ethernet router hello message received - */ -int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct rtnode_hello_message *msg = (struct rtnode_hello_message *)skb->data; - - struct neighbour *neigh; - struct dn_neigh *dn; - struct dn_dev *dn_db; - __le16 src; - - src = dn_eth2dn(msg->id); - - neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1); - - dn = container_of(neigh, struct dn_neigh, n); - - if (neigh) { - write_lock(&neigh->lock); - - neigh->used = jiffies; - dn_db = rcu_dereference(neigh->dev->dn_ptr); - - if (!(neigh->nud_state & NUD_PERMANENT)) { - neigh->updated = jiffies; - - if (neigh->dev->type == ARPHRD_ETHER) - memcpy(neigh->ha, ð_hdr(skb)->h_source, ETH_ALEN); - - dn->blksize = le16_to_cpu(msg->blksize); - dn->priority = msg->priority; - - dn->flags &= ~DN_NDFLAG_P3; - - switch (msg->iinfo & DN_RT_INFO_TYPE) { - case DN_RT_INFO_L1RT: - dn->flags &=~DN_NDFLAG_R2; - dn->flags |= DN_NDFLAG_R1; - break; - case DN_RT_INFO_L2RT: - dn->flags |= DN_NDFLAG_R2; - } - } - - /* Only use routers in our area */ - if ((le16_to_cpu(src)>>10) == (le16_to_cpu((decnet_address))>>10)) { - if (!dn_db->router) { - dn_db->router = neigh_clone(neigh); - } else { - if (msg->priority > ((struct dn_neigh *)dn_db->router)->priority) - neigh_release(xchg(&dn_db->router, neigh_clone(neigh))); - } - } - write_unlock(&neigh->lock); - neigh_release(neigh); - } - - kfree_skb(skb); - return 0; -} - -/* - * Endnode hello message received - */ -int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct endnode_hello_message *msg = (struct endnode_hello_message *)skb->data; - struct neighbour *neigh; - struct dn_neigh *dn; - __le16 src; - - src = dn_eth2dn(msg->id); - - neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1); - - dn = container_of(neigh, struct dn_neigh, n); - - if (neigh) { - write_lock(&neigh->lock); - - neigh->used = jiffies; - - if (!(neigh->nud_state & NUD_PERMANENT)) { - neigh->updated = jiffies; - - if (neigh->dev->type == ARPHRD_ETHER) - memcpy(neigh->ha, ð_hdr(skb)->h_source, ETH_ALEN); - dn->flags &= ~(DN_NDFLAG_R1 | DN_NDFLAG_R2); - dn->blksize = le16_to_cpu(msg->blksize); - dn->priority = 0; - } - - write_unlock(&neigh->lock); - neigh_release(neigh); - } - - kfree_skb(skb); - return 0; -} - -static char *dn_find_slot(char *base, int max, int priority) -{ - int i; - unsigned char *min = NULL; - - base += 6; /* skip first id */ - - for(i = 0; i < max; i++) { - if (!min || (*base < *min)) - min = base; - base += 7; /* find next priority */ - } - - if (!min) - return NULL; - - return (*min < priority) ? (min - 6) : NULL; -} - -struct elist_cb_state { - struct net_device *dev; - unsigned char *ptr; - unsigned char *rs; - int t, n; -}; - -static void neigh_elist_cb(struct neighbour *neigh, void *_info) -{ - struct elist_cb_state *s = _info; - struct dn_neigh *dn; - - if (neigh->dev != s->dev) - return; - - dn = container_of(neigh, struct dn_neigh, n); - if (!(dn->flags & (DN_NDFLAG_R1|DN_NDFLAG_R2))) - return; - - if (s->t == s->n) - s->rs = dn_find_slot(s->ptr, s->n, dn->priority); - else - s->t++; - if (s->rs == NULL) - return; - - dn_dn2eth(s->rs, dn->addr); - s->rs += 6; - *(s->rs) = neigh->nud_state & NUD_CONNECTED ? 0x80 : 0x0; - *(s->rs) |= dn->priority; - s->rs++; -} - -int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n) -{ - struct elist_cb_state state; - - state.dev = dev; - state.t = 0; - state.n = n; - state.ptr = ptr; - state.rs = ptr; - - neigh_for_each(&dn_neigh_table, neigh_elist_cb, &state); - - return state.t; -} - - -#ifdef CONFIG_PROC_FS - -static inline void dn_neigh_format_entry(struct seq_file *seq, - struct neighbour *n) -{ - struct dn_neigh *dn = container_of(n, struct dn_neigh, n); - char buf[DN_ASCBUF_LEN]; - - read_lock(&n->lock); - seq_printf(seq, "%-7s %s%s%s %02x %02d %07ld %-8s\n", - dn_addr2asc(le16_to_cpu(dn->addr), buf), - (dn->flags&DN_NDFLAG_R1) ? "1" : "-", - (dn->flags&DN_NDFLAG_R2) ? "2" : "-", - (dn->flags&DN_NDFLAG_P3) ? "3" : "-", - dn->n.nud_state, - refcount_read(&dn->n.refcnt), - dn->blksize, - (dn->n.dev) ? dn->n.dev->name : "?"); - read_unlock(&n->lock); -} - -static int dn_neigh_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) { - seq_puts(seq, "Addr Flags State Use Blksize Dev\n"); - } else { - dn_neigh_format_entry(seq, v); - } - - return 0; -} - -static void *dn_neigh_seq_start(struct seq_file *seq, loff_t *pos) -{ - return neigh_seq_start(seq, pos, &dn_neigh_table, - NEIGH_SEQ_NEIGH_ONLY); -} - -static const struct seq_operations dn_neigh_seq_ops = { - .start = dn_neigh_seq_start, - .next = neigh_seq_next, - .stop = neigh_seq_stop, - .show = dn_neigh_seq_show, -}; -#endif - -void __init dn_neigh_init(void) -{ - neigh_table_init(NEIGH_DN_TABLE, &dn_neigh_table); - proc_create_net("decnet_neigh", 0444, init_net.proc_net, - &dn_neigh_seq_ops, sizeof(struct neigh_seq_state)); -} - -void __exit dn_neigh_cleanup(void) -{ - remove_proc_entry("decnet_neigh", init_net.proc_net); - neigh_table_clear(NEIGH_DN_TABLE, &dn_neigh_table); -} diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c deleted file mode 100644 index c97bdca5ec30..000000000000 --- a/net/decnet/dn_nsp_in.c +++ /dev/null @@ -1,906 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Network Services Protocol (Input) - * - * Author: Eduardo Marcelo Serrat - * - * Changes: - * - * Steve Whitehouse: Split into dn_nsp_in.c and dn_nsp_out.c from - * original dn_nsp.c. - * Steve Whitehouse: Updated to work with my new routing architecture. - * Steve Whitehouse: Add changes from Eduardo Serrat's patches. - * Steve Whitehouse: Put all ack handling code in a common routine. - * Steve Whitehouse: Put other common bits into dn_nsp_rx() - * Steve Whitehouse: More checks on skb->len to catch bogus packets - * Fixed various race conditions and possible nasties. - * Steve Whitehouse: Now handles returned conninit frames. - * David S. Miller: New socket locking - * Steve Whitehouse: Fixed lockup when socket filtering was enabled. - * Paul Koning: Fix to push CC sockets into RUN when acks are - * received. - * Steve Whitehouse: - * Patrick Caulfield: Checking conninits for correctness & sending of error - * responses. - * Steve Whitehouse: Added backlog congestion level return codes. - * Patrick Caulfield: - * Steve Whitehouse: Added flow control support (outbound) - * Steve Whitehouse: Prepare for nonlinear skbs - */ - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - -*******************************************************************************/ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -extern int decnet_log_martians; - -static void dn_log_martian(struct sk_buff *skb, const char *msg) -{ - if (decnet_log_martians) { - char *devname = skb->dev ? skb->dev->name : "???"; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - net_info_ratelimited("DECnet: Martian packet (%s) dev=%s src=0x%04hx dst=0x%04hx srcport=0x%04hx dstport=0x%04hx\n", - msg, devname, - le16_to_cpu(cb->src), - le16_to_cpu(cb->dst), - le16_to_cpu(cb->src_port), - le16_to_cpu(cb->dst_port)); - } -} - -/* - * For this function we've flipped the cross-subchannel bit - * if the message is an otherdata or linkservice message. Thus - * we can use it to work out what to update. - */ -static void dn_ack(struct sock *sk, struct sk_buff *skb, unsigned short ack) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short type = ((ack >> 12) & 0x0003); - int wakeup = 0; - - switch (type) { - case 0: /* ACK - Data */ - if (dn_after(ack, scp->ackrcv_dat)) { - scp->ackrcv_dat = ack & 0x0fff; - wakeup |= dn_nsp_check_xmit_queue(sk, skb, - &scp->data_xmit_queue, - ack); - } - break; - case 1: /* NAK - Data */ - break; - case 2: /* ACK - OtherData */ - if (dn_after(ack, scp->ackrcv_oth)) { - scp->ackrcv_oth = ack & 0x0fff; - wakeup |= dn_nsp_check_xmit_queue(sk, skb, - &scp->other_xmit_queue, - ack); - } - break; - case 3: /* NAK - OtherData */ - break; - } - - if (wakeup && !sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); -} - -/* - * This function is a universal ack processor. - */ -static int dn_process_ack(struct sock *sk, struct sk_buff *skb, int oth) -{ - __le16 *ptr = (__le16 *)skb->data; - int len = 0; - unsigned short ack; - - if (skb->len < 2) - return len; - - if ((ack = le16_to_cpu(*ptr)) & 0x8000) { - skb_pull(skb, 2); - ptr++; - len += 2; - if ((ack & 0x4000) == 0) { - if (oth) - ack ^= 0x2000; - dn_ack(sk, skb, ack); - } - } - - if (skb->len < 2) - return len; - - if ((ack = le16_to_cpu(*ptr)) & 0x8000) { - skb_pull(skb, 2); - len += 2; - if ((ack & 0x4000) == 0) { - if (oth) - ack ^= 0x2000; - dn_ack(sk, skb, ack); - } - } - - return len; -} - - -/** - * dn_check_idf - Check an image data field format is correct. - * @pptr: Pointer to pointer to image data - * @len: Pointer to length of image data - * @max: The maximum allowed length of the data in the image data field - * @follow_on: Check that this many bytes exist beyond the end of the image data - * - * Returns: 0 if ok, -1 on error - */ -static inline int dn_check_idf(unsigned char **pptr, int *len, unsigned char max, unsigned char follow_on) -{ - unsigned char *ptr = *pptr; - unsigned char flen = *ptr++; - - (*len)--; - if (flen > max) - return -1; - if ((flen + follow_on) > *len) - return -1; - - *len -= flen; - *pptr = ptr + flen; - return 0; -} - -/* - * Table of reason codes to pass back to node which sent us a badly - * formed message, plus text messages for the log. A zero entry in - * the reason field means "don't reply" otherwise a disc init is sent with - * the specified reason code. - */ -static struct { - unsigned short reason; - const char *text; -} ci_err_table[] = { - { 0, "CI: Truncated message" }, - { NSP_REASON_ID, "CI: Destination username error" }, - { NSP_REASON_ID, "CI: Destination username type" }, - { NSP_REASON_US, "CI: Source username error" }, - { 0, "CI: Truncated at menuver" }, - { 0, "CI: Truncated before access or user data" }, - { NSP_REASON_IO, "CI: Access data format error" }, - { NSP_REASON_IO, "CI: User data format error" } -}; - -/* - * This function uses a slightly different lookup method - * to find its sockets, since it searches on object name/number - * rather than port numbers. Various tests are done to ensure that - * the incoming data is in the correct format before it is queued to - * a socket. - */ -static struct sock *dn_find_listener(struct sk_buff *skb, unsigned short *reason) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct nsp_conn_init_msg *msg = (struct nsp_conn_init_msg *)skb->data; - struct sockaddr_dn dstaddr; - struct sockaddr_dn srcaddr; - unsigned char type = 0; - int dstlen; - int srclen; - unsigned char *ptr; - int len; - int err = 0; - unsigned char menuver; - - memset(&dstaddr, 0, sizeof(struct sockaddr_dn)); - memset(&srcaddr, 0, sizeof(struct sockaddr_dn)); - - /* - * 1. Decode & remove message header - */ - cb->src_port = msg->srcaddr; - cb->dst_port = msg->dstaddr; - cb->services = msg->services; - cb->info = msg->info; - cb->segsize = le16_to_cpu(msg->segsize); - - if (!pskb_may_pull(skb, sizeof(*msg))) - goto err_out; - - skb_pull(skb, sizeof(*msg)); - - len = skb->len; - ptr = skb->data; - - /* - * 2. Check destination end username format - */ - dstlen = dn_username2sockaddr(ptr, len, &dstaddr, &type); - err++; - if (dstlen < 0) - goto err_out; - - err++; - if (type > 1) - goto err_out; - - len -= dstlen; - ptr += dstlen; - - /* - * 3. Check source end username format - */ - srclen = dn_username2sockaddr(ptr, len, &srcaddr, &type); - err++; - if (srclen < 0) - goto err_out; - - len -= srclen; - ptr += srclen; - err++; - if (len < 1) - goto err_out; - - menuver = *ptr; - ptr++; - len--; - - /* - * 4. Check that optional data actually exists if menuver says it does - */ - err++; - if ((menuver & (DN_MENUVER_ACC | DN_MENUVER_USR)) && (len < 1)) - goto err_out; - - /* - * 5. Check optional access data format - */ - err++; - if (menuver & DN_MENUVER_ACC) { - if (dn_check_idf(&ptr, &len, 39, 1)) - goto err_out; - if (dn_check_idf(&ptr, &len, 39, 1)) - goto err_out; - if (dn_check_idf(&ptr, &len, 39, (menuver & DN_MENUVER_USR) ? 1 : 0)) - goto err_out; - } - - /* - * 6. Check optional user data format - */ - err++; - if (menuver & DN_MENUVER_USR) { - if (dn_check_idf(&ptr, &len, 16, 0)) - goto err_out; - } - - /* - * 7. Look up socket based on destination end username - */ - return dn_sklist_find_listener(&dstaddr); -err_out: - dn_log_martian(skb, ci_err_table[err].text); - *reason = ci_err_table[err].reason; - return NULL; -} - - -static void dn_nsp_conn_init(struct sock *sk, struct sk_buff *skb) -{ - if (sk_acceptq_is_full(sk)) { - kfree_skb(skb); - return; - } - - sk_acceptq_added(sk); - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_state_change(sk); -} - -static void dn_nsp_conn_conf(struct sock *sk, struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dn_scp *scp = DN_SK(sk); - unsigned char *ptr; - - if (skb->len < 4) - goto out; - - ptr = skb->data; - cb->services = *ptr++; - cb->info = *ptr++; - cb->segsize = le16_to_cpu(*(__le16 *)ptr); - - if ((scp->state == DN_CI) || (scp->state == DN_CD)) { - scp->persist = 0; - scp->addrrem = cb->src_port; - sk->sk_state = TCP_ESTABLISHED; - scp->state = DN_RUN; - scp->services_rem = cb->services; - scp->info_rem = cb->info; - scp->segsize_rem = cb->segsize; - - if ((scp->services_rem & NSP_FC_MASK) == NSP_FC_NONE) - scp->max_window = decnet_no_fc_max_cwnd; - - if (skb->len > 0) { - u16 dlen = *skb->data; - if ((dlen <= 16) && (dlen <= skb->len)) { - scp->conndata_in.opt_optl = cpu_to_le16(dlen); - skb_copy_from_linear_data_offset(skb, 1, - scp->conndata_in.opt_data, dlen); - } - } - dn_nsp_send_link(sk, DN_NOCHANGE, 0); - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - } - -out: - kfree_skb(skb); -} - -static void dn_nsp_conn_ack(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->state == DN_CI) { - scp->state = DN_CD; - scp->persist = 0; - } - - kfree_skb(skb); -} - -static void dn_nsp_disc_init(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned short reason; - - if (skb->len < 2) - goto out; - - reason = le16_to_cpu(*(__le16 *)skb->data); - skb_pull(skb, 2); - - scp->discdata_in.opt_status = cpu_to_le16(reason); - scp->discdata_in.opt_optl = 0; - memset(scp->discdata_in.opt_data, 0, 16); - - if (skb->len > 0) { - u16 dlen = *skb->data; - if ((dlen <= 16) && (dlen <= skb->len)) { - scp->discdata_in.opt_optl = cpu_to_le16(dlen); - skb_copy_from_linear_data_offset(skb, 1, scp->discdata_in.opt_data, dlen); - } - } - - scp->addrrem = cb->src_port; - sk->sk_state = TCP_CLOSE; - - switch (scp->state) { - case DN_CI: - case DN_CD: - scp->state = DN_RJ; - sk->sk_err = ECONNREFUSED; - break; - case DN_RUN: - sk->sk_shutdown |= SHUTDOWN_MASK; - scp->state = DN_DN; - break; - case DN_DI: - scp->state = DN_DIC; - break; - } - - if (!sock_flag(sk, SOCK_DEAD)) { - if (sk->sk_socket->state != SS_UNCONNECTED) - sk->sk_socket->state = SS_DISCONNECTING; - sk->sk_state_change(sk); - } - - /* - * It appears that its possible for remote machines to send disc - * init messages with no port identifier if we are in the CI and - * possibly also the CD state. Obviously we shouldn't reply with - * a message if we don't know what the end point is. - */ - if (scp->addrrem) { - dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, GFP_ATOMIC); - } - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - -out: - kfree_skb(skb); -} - -/* - * disc_conf messages are also called no_resources or no_link - * messages depending upon the "reason" field. - */ -static void dn_nsp_disc_conf(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short reason; - - if (skb->len != 2) - goto out; - - reason = le16_to_cpu(*(__le16 *)skb->data); - - sk->sk_state = TCP_CLOSE; - - switch (scp->state) { - case DN_CI: - scp->state = DN_NR; - break; - case DN_DR: - if (reason == NSP_REASON_DC) - scp->state = DN_DRC; - if (reason == NSP_REASON_NL) - scp->state = DN_CN; - break; - case DN_DI: - scp->state = DN_DIC; - break; - case DN_RUN: - sk->sk_shutdown |= SHUTDOWN_MASK; - fallthrough; - case DN_CC: - scp->state = DN_CN; - } - - if (!sock_flag(sk, SOCK_DEAD)) { - if (sk->sk_socket->state != SS_UNCONNECTED) - sk->sk_socket->state = SS_DISCONNECTING; - sk->sk_state_change(sk); - } - - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - -out: - kfree_skb(skb); -} - -static void dn_nsp_linkservice(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short segnum; - unsigned char lsflags; - signed char fcval; - int wake_up = 0; - char *ptr = skb->data; - unsigned char fctype = scp->services_rem & NSP_FC_MASK; - - if (skb->len != 4) - goto out; - - segnum = le16_to_cpu(*(__le16 *)ptr); - ptr += 2; - lsflags = *(unsigned char *)ptr++; - fcval = *ptr; - - /* - * Here we ignore erronous packets which should really - * should cause a connection abort. It is not critical - * for now though. - */ - if (lsflags & 0xf8) - goto out; - - if (seq_next(scp->numoth_rcv, segnum)) { - seq_add(&scp->numoth_rcv, 1); - switch(lsflags & 0x04) { /* FCVAL INT */ - case 0x00: /* Normal Request */ - switch(lsflags & 0x03) { /* FCVAL MOD */ - case 0x00: /* Request count */ - if (fcval < 0) { - unsigned char p_fcval = -fcval; - if ((scp->flowrem_dat > p_fcval) && - (fctype == NSP_FC_SCMC)) { - scp->flowrem_dat -= p_fcval; - } - } else if (fcval > 0) { - scp->flowrem_dat += fcval; - wake_up = 1; - } - break; - case 0x01: /* Stop outgoing data */ - scp->flowrem_sw = DN_DONTSEND; - break; - case 0x02: /* Ok to start again */ - scp->flowrem_sw = DN_SEND; - dn_nsp_output(sk); - wake_up = 1; - } - break; - case 0x04: /* Interrupt Request */ - if (fcval > 0) { - scp->flowrem_oth += fcval; - wake_up = 1; - } - break; - } - if (wake_up && !sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - } - - dn_nsp_send_oth_ack(sk); - -out: - kfree_skb(skb); -} - -/* - * Copy of sock_queue_rcv_skb (from sock.h) without - * bh_lock_sock() (its already held when this is called) which - * also allows data and other data to be queued to a socket. - */ -static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig, struct sk_buff_head *queue) -{ - int err; - - /* Cast skb->rcvbuf to unsigned... It's pointless, but reduces - number of warnings when compiling with -W --ANK - */ - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned int)sk->sk_rcvbuf) { - err = -ENOMEM; - goto out; - } - - err = sk_filter(sk, skb); - if (err) - goto out; - - skb_set_owner_r(skb, sk); - skb_queue_tail(queue, skb); - - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); -out: - return err; -} - -static void dn_nsp_otherdata(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short segnum; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - int queued = 0; - - if (skb->len < 2) - goto out; - - cb->segnum = segnum = le16_to_cpu(*(__le16 *)skb->data); - skb_pull(skb, 2); - - if (seq_next(scp->numoth_rcv, segnum)) { - - if (dn_queue_skb(sk, skb, SIGURG, &scp->other_receive_queue) == 0) { - seq_add(&scp->numoth_rcv, 1); - scp->other_report = 0; - queued = 1; - } - } - - dn_nsp_send_oth_ack(sk); -out: - if (!queued) - kfree_skb(skb); -} - -static void dn_nsp_data(struct sock *sk, struct sk_buff *skb) -{ - int queued = 0; - unsigned short segnum; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dn_scp *scp = DN_SK(sk); - - if (skb->len < 2) - goto out; - - cb->segnum = segnum = le16_to_cpu(*(__le16 *)skb->data); - skb_pull(skb, 2); - - if (seq_next(scp->numdat_rcv, segnum)) { - if (dn_queue_skb(sk, skb, SIGIO, &sk->sk_receive_queue) == 0) { - seq_add(&scp->numdat_rcv, 1); - queued = 1; - } - - if ((scp->flowloc_sw == DN_SEND) && dn_congested(sk)) { - scp->flowloc_sw = DN_DONTSEND; - dn_nsp_send_link(sk, DN_DONTSEND, 0); - } - } - - dn_nsp_send_data_ack(sk); -out: - if (!queued) - kfree_skb(skb); -} - -/* - * If one of our conninit messages is returned, this function - * deals with it. It puts the socket into the NO_COMMUNICATION - * state. - */ -static void dn_returned_conn_init(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->state == DN_CI) { - scp->state = DN_NC; - sk->sk_state = TCP_CLOSE; - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - } - - kfree_skb(skb); -} - -static int dn_nsp_no_socket(struct sk_buff *skb, unsigned short reason) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - int ret = NET_RX_DROP; - - /* Must not reply to returned packets */ - if (cb->rt_flags & DN_RT_F_RTS) - goto out; - - if ((reason != NSP_REASON_OK) && ((cb->nsp_flags & 0x0c) == 0x08)) { - switch (cb->nsp_flags & 0x70) { - case 0x10: - case 0x60: /* (Retransmitted) Connect Init */ - dn_nsp_return_disc(skb, NSP_DISCINIT, reason); - ret = NET_RX_SUCCESS; - break; - case 0x20: /* Connect Confirm */ - dn_nsp_return_disc(skb, NSP_DISCCONF, reason); - ret = NET_RX_SUCCESS; - break; - } - } - -out: - kfree_skb(skb); - return ret; -} - -static int dn_nsp_rx_packet(struct net *net, struct sock *sk2, - struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct sock *sk = NULL; - unsigned char *ptr = (unsigned char *)skb->data; - unsigned short reason = NSP_REASON_NL; - - if (!pskb_may_pull(skb, 2)) - goto free_out; - - skb_reset_transport_header(skb); - cb->nsp_flags = *ptr++; - - if (decnet_debug_level & 2) - printk(KERN_DEBUG "dn_nsp_rx: Message type 0x%02x\n", (int)cb->nsp_flags); - - if (cb->nsp_flags & 0x83) - goto free_out; - - /* - * Filter out conninits and useless packet types - */ - if ((cb->nsp_flags & 0x0c) == 0x08) { - switch (cb->nsp_flags & 0x70) { - case 0x00: /* NOP */ - case 0x70: /* Reserved */ - case 0x50: /* Reserved, Phase II node init */ - goto free_out; - case 0x10: - case 0x60: - if (unlikely(cb->rt_flags & DN_RT_F_RTS)) - goto free_out; - sk = dn_find_listener(skb, &reason); - goto got_it; - } - } - - if (!pskb_may_pull(skb, 3)) - goto free_out; - - /* - * Grab the destination address. - */ - cb->dst_port = *(__le16 *)ptr; - cb->src_port = 0; - ptr += 2; - - /* - * If not a connack, grab the source address too. - */ - if (pskb_may_pull(skb, 5)) { - cb->src_port = *(__le16 *)ptr; - ptr += 2; - skb_pull(skb, 5); - } - - /* - * Returned packets... - * Swap src & dst and look up in the normal way. - */ - if (unlikely(cb->rt_flags & DN_RT_F_RTS)) { - swap(cb->dst_port, cb->src_port); - swap(cb->dst, cb->src); - } - - /* - * Find the socket to which this skb is destined. - */ - sk = dn_find_by_skb(skb); -got_it: - if (sk != NULL) { - struct dn_scp *scp = DN_SK(sk); - - /* Reset backoff */ - scp->nsp_rxtshift = 0; - - /* - * We linearize everything except data segments here. - */ - if (cb->nsp_flags & ~0x60) { - if (unlikely(skb_linearize(skb))) - goto free_out; - } - - return sk_receive_skb(sk, skb, 0); - } - - return dn_nsp_no_socket(skb, reason); - -free_out: - kfree_skb(skb); - return NET_RX_DROP; -} - -int dn_nsp_rx(struct sk_buff *skb) -{ - return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, - &init_net, NULL, skb, skb->dev, NULL, - dn_nsp_rx_packet); -} - -/* - * This is the main receive routine for sockets. It is called - * from the above when the socket is not busy, and also from - * sock_release() when there is a backlog queued up. - */ -int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - if (cb->rt_flags & DN_RT_F_RTS) { - if (cb->nsp_flags == 0x18 || cb->nsp_flags == 0x68) - dn_returned_conn_init(sk, skb); - else - kfree_skb(skb); - return NET_RX_SUCCESS; - } - - /* - * Control packet. - */ - if ((cb->nsp_flags & 0x0c) == 0x08) { - switch (cb->nsp_flags & 0x70) { - case 0x10: - case 0x60: - dn_nsp_conn_init(sk, skb); - break; - case 0x20: - dn_nsp_conn_conf(sk, skb); - break; - case 0x30: - dn_nsp_disc_init(sk, skb); - break; - case 0x40: - dn_nsp_disc_conf(sk, skb); - break; - } - - } else if (cb->nsp_flags == 0x24) { - /* - * Special for connacks, 'cos they don't have - * ack data or ack otherdata info. - */ - dn_nsp_conn_ack(sk, skb); - } else { - int other = 1; - - /* both data and ack frames can kick a CC socket into RUN */ - if ((scp->state == DN_CC) && !sock_flag(sk, SOCK_DEAD)) { - scp->state = DN_RUN; - sk->sk_state = TCP_ESTABLISHED; - sk->sk_state_change(sk); - } - - if ((cb->nsp_flags & 0x1c) == 0) - other = 0; - if (cb->nsp_flags == 0x04) - other = 0; - - /* - * Read out ack data here, this applies equally - * to data, other data, link serivce and both - * ack data and ack otherdata. - */ - dn_process_ack(sk, skb, other); - - /* - * If we've some sort of data here then call a - * suitable routine for dealing with it, otherwise - * the packet is an ack and can be discarded. - */ - if ((cb->nsp_flags & 0x0c) == 0) { - - if (scp->state != DN_RUN) - goto free_out; - - switch (cb->nsp_flags) { - case 0x10: /* LS */ - dn_nsp_linkservice(sk, skb); - break; - case 0x30: /* OD */ - dn_nsp_otherdata(sk, skb); - break; - default: - dn_nsp_data(sk, skb); - } - - } else { /* Ack, chuck it out here */ -free_out: - kfree_skb(skb); - } - } - - return NET_RX_SUCCESS; -} diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c deleted file mode 100644 index 00f2ed721ec1..000000000000 --- a/net/decnet/dn_nsp_out.c +++ /dev/null @@ -1,695 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Network Services Protocol (Output) - * - * Author: Eduardo Marcelo Serrat - * - * Changes: - * - * Steve Whitehouse: Split into dn_nsp_in.c and dn_nsp_out.c from - * original dn_nsp.c. - * Steve Whitehouse: Updated to work with my new routing architecture. - * Steve Whitehouse: Added changes from Eduardo Serrat's patches. - * Steve Whitehouse: Now conninits have the "return" bit set. - * Steve Whitehouse: Fixes to check alloc'd skbs are non NULL! - * Moved output state machine into one function - * Steve Whitehouse: New output state machine - * Paul Koning: Connect Confirm message fix. - * Eduardo Serrat: Fix to stop dn_nsp_do_disc() sending malformed packets. - * Steve Whitehouse: dn_nsp_output() and friends needed a spring clean - * Steve Whitehouse: Moved dn_nsp_send() in here from route.h - */ - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - -*******************************************************************************/ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - - -static int nsp_backoff[NSP_MAXRXTSHIFT + 1] = { 1, 2, 4, 8, 16, 32, 64, 64, 64, 64, 64, 64, 64 }; - -static void dn_nsp_send(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - struct dn_scp *scp = DN_SK(sk); - struct dst_entry *dst; - struct flowidn fld; - - skb_reset_transport_header(skb); - scp->stamp = jiffies; - - dst = sk_dst_check(sk, 0); - if (dst) { -try_again: - skb_dst_set(skb, dst); - dst_output(&init_net, skb->sk, skb); - return; - } - - memset(&fld, 0, sizeof(fld)); - fld.flowidn_oif = sk->sk_bound_dev_if; - fld.saddr = dn_saddr2dn(&scp->addr); - fld.daddr = dn_saddr2dn(&scp->peer); - dn_sk_ports_copy(&fld, scp); - fld.flowidn_proto = DNPROTO_NSP; - if (dn_route_output_sock(&sk->sk_dst_cache, &fld, sk, 0) == 0) { - dst = sk_dst_get(sk); - sk->sk_route_caps = dst->dev->features; - goto try_again; - } - - sk->sk_err = EHOSTUNREACH; - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); -} - - -/* - * If sk == NULL, then we assume that we are supposed to be making - * a routing layer skb. If sk != NULL, then we are supposed to be - * creating an skb for the NSP layer. - * - * The eventual aim is for each socket to have a cached header size - * for its outgoing packets, and to set hdr from this when sk != NULL. - */ -struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri) -{ - struct sk_buff *skb; - int hdr = 64; - - if ((skb = alloc_skb(size + hdr, pri)) == NULL) - return NULL; - - skb->protocol = htons(ETH_P_DNA_RT); - skb->pkt_type = PACKET_OUTGOING; - - if (sk) - skb_set_owner_w(skb, sk); - - skb_reserve(skb, hdr); - - return skb; -} - -/* - * Calculate persist timer based upon the smoothed round - * trip time and the variance. Backoff according to the - * nsp_backoff[] array. - */ -unsigned long dn_nsp_persist(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - unsigned long t = ((scp->nsp_srtt >> 2) + scp->nsp_rttvar) >> 1; - - t *= nsp_backoff[scp->nsp_rxtshift]; - - if (t < HZ) t = HZ; - if (t > (600*HZ)) t = (600*HZ); - - if (scp->nsp_rxtshift < NSP_MAXRXTSHIFT) - scp->nsp_rxtshift++; - - /* printk(KERN_DEBUG "rxtshift %lu, t=%lu\n", scp->nsp_rxtshift, t); */ - - return t; -} - -/* - * This is called each time we get an estimate for the rtt - * on the link. - */ -static void dn_nsp_rtt(struct sock *sk, long rtt) -{ - struct dn_scp *scp = DN_SK(sk); - long srtt = (long)scp->nsp_srtt; - long rttvar = (long)scp->nsp_rttvar; - long delta; - - /* - * If the jiffies clock flips over in the middle of timestamp - * gathering this value might turn out negative, so we make sure - * that is it always positive here. - */ - if (rtt < 0) - rtt = -rtt; - /* - * Add new rtt to smoothed average - */ - delta = ((rtt << 3) - srtt); - srtt += (delta >> 3); - if (srtt >= 1) - scp->nsp_srtt = (unsigned long)srtt; - else - scp->nsp_srtt = 1; - - /* - * Add new rtt varience to smoothed varience - */ - delta >>= 1; - rttvar += ((((delta>0)?(delta):(-delta)) - rttvar) >> 2); - if (rttvar >= 1) - scp->nsp_rttvar = (unsigned long)rttvar; - else - scp->nsp_rttvar = 1; - - /* printk(KERN_DEBUG "srtt=%lu rttvar=%lu\n", scp->nsp_srtt, scp->nsp_rttvar); */ -} - -/** - * dn_nsp_clone_and_send - Send a data packet by cloning it - * @skb: The packet to clone and transmit - * @gfp: memory allocation flag - * - * Clone a queued data or other data packet and transmit it. - * - * Returns: The number of times the packet has been sent previously - */ -static inline unsigned int dn_nsp_clone_and_send(struct sk_buff *skb, - gfp_t gfp) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct sk_buff *skb2; - int ret = 0; - - if ((skb2 = skb_clone(skb, gfp)) != NULL) { - ret = cb->xmit_count; - cb->xmit_count++; - cb->stamp = jiffies; - skb2->sk = skb->sk; - dn_nsp_send(skb2); - } - - return ret; -} - -/** - * dn_nsp_output - Try and send something from socket queues - * @sk: The socket whose queues are to be investigated - * - * Try and send the packet on the end of the data and other data queues. - * Other data gets priority over data, and if we retransmit a packet we - * reduce the window by dividing it in two. - * - */ -void dn_nsp_output(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb; - unsigned int reduce_win = 0; - - /* - * First we check for otherdata/linkservice messages - */ - if ((skb = skb_peek(&scp->other_xmit_queue)) != NULL) - reduce_win = dn_nsp_clone_and_send(skb, GFP_ATOMIC); - - /* - * If we may not send any data, we don't. - * If we are still trying to get some other data down the - * channel, we don't try and send any data. - */ - if (reduce_win || (scp->flowrem_sw != DN_SEND)) - goto recalc_window; - - if ((skb = skb_peek(&scp->data_xmit_queue)) != NULL) - reduce_win = dn_nsp_clone_and_send(skb, GFP_ATOMIC); - - /* - * If we've sent any frame more than once, we cut the - * send window size in half. There is always a minimum - * window size of one available. - */ -recalc_window: - if (reduce_win) { - scp->snd_window >>= 1; - if (scp->snd_window < NSP_MIN_WINDOW) - scp->snd_window = NSP_MIN_WINDOW; - } -} - -int dn_nsp_xmit_timeout(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - dn_nsp_output(sk); - - if (!skb_queue_empty(&scp->data_xmit_queue) || - !skb_queue_empty(&scp->other_xmit_queue)) - scp->persist = dn_nsp_persist(sk); - - return 0; -} - -static inline __le16 *dn_mk_common_header(struct dn_scp *scp, struct sk_buff *skb, unsigned char msgflag, int len) -{ - unsigned char *ptr = skb_push(skb, len); - - BUG_ON(len < 5); - - *ptr++ = msgflag; - *((__le16 *)ptr) = scp->addrrem; - ptr += 2; - *((__le16 *)ptr) = scp->addrloc; - ptr += 2; - return (__le16 __force *)ptr; -} - -static __le16 *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, unsigned char msgflag, int hlen, int other) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short acknum = scp->numdat_rcv & 0x0FFF; - unsigned short ackcrs = scp->numoth_rcv & 0x0FFF; - __le16 *ptr; - - BUG_ON(hlen < 9); - - scp->ackxmt_dat = acknum; - scp->ackxmt_oth = ackcrs; - acknum |= 0x8000; - ackcrs |= 0x8000; - - /* If this is an "other data/ack" message, swap acknum and ackcrs */ - if (other) - swap(acknum, ackcrs); - - /* Set "cross subchannel" bit in ackcrs */ - ackcrs |= 0x2000; - - ptr = dn_mk_common_header(scp, skb, msgflag, hlen); - - *ptr++ = cpu_to_le16(acknum); - *ptr++ = cpu_to_le16(ackcrs); - - return ptr; -} - -static __le16 *dn_nsp_mk_data_header(struct sock *sk, struct sk_buff *skb, int oth) -{ - struct dn_scp *scp = DN_SK(sk); - struct dn_skb_cb *cb = DN_SKB_CB(skb); - __le16 *ptr = dn_mk_ack_header(sk, skb, cb->nsp_flags, 11, oth); - - if (unlikely(oth)) { - cb->segnum = scp->numoth; - seq_add(&scp->numoth, 1); - } else { - cb->segnum = scp->numdat; - seq_add(&scp->numdat, 1); - } - *(ptr++) = cpu_to_le16(cb->segnum); - - return ptr; -} - -void dn_nsp_queue_xmit(struct sock *sk, struct sk_buff *skb, - gfp_t gfp, int oth) -{ - struct dn_scp *scp = DN_SK(sk); - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned long t = ((scp->nsp_srtt >> 2) + scp->nsp_rttvar) >> 1; - - cb->xmit_count = 0; - dn_nsp_mk_data_header(sk, skb, oth); - - /* - * Slow start: If we have been idle for more than - * one RTT, then reset window to min size. - */ - if ((jiffies - scp->stamp) > t) - scp->snd_window = NSP_MIN_WINDOW; - - if (oth) - skb_queue_tail(&scp->other_xmit_queue, skb); - else - skb_queue_tail(&scp->data_xmit_queue, skb); - - if (scp->flowrem_sw != DN_SEND) - return; - - dn_nsp_clone_and_send(skb, gfp); -} - - -int dn_nsp_check_xmit_queue(struct sock *sk, struct sk_buff *skb, struct sk_buff_head *q, unsigned short acknum) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb2, *n, *ack = NULL; - int wakeup = 0; - int try_retrans = 0; - unsigned long reftime = cb->stamp; - unsigned long pkttime; - unsigned short xmit_count; - unsigned short segnum; - - skb_queue_walk_safe(q, skb2, n) { - struct dn_skb_cb *cb2 = DN_SKB_CB(skb2); - - if (dn_before_or_equal(cb2->segnum, acknum)) - ack = skb2; - - /* printk(KERN_DEBUG "ack: %s %04x %04x\n", ack ? "ACK" : "SKIP", (int)cb2->segnum, (int)acknum); */ - - if (ack == NULL) - continue; - - /* printk(KERN_DEBUG "check_xmit_queue: %04x, %d\n", acknum, cb2->xmit_count); */ - - /* Does _last_ packet acked have xmit_count > 1 */ - try_retrans = 0; - /* Remember to wake up the sending process */ - wakeup = 1; - /* Keep various statistics */ - pkttime = cb2->stamp; - xmit_count = cb2->xmit_count; - segnum = cb2->segnum; - /* Remove and drop ack'ed packet */ - skb_unlink(ack, q); - kfree_skb(ack); - ack = NULL; - - /* - * We don't expect to see acknowledgements for packets we - * haven't sent yet. - */ - WARN_ON(xmit_count == 0); - - /* - * If the packet has only been sent once, we can use it - * to calculate the RTT and also open the window a little - * further. - */ - if (xmit_count == 1) { - if (dn_equal(segnum, acknum)) - dn_nsp_rtt(sk, (long)(pkttime - reftime)); - - if (scp->snd_window < scp->max_window) - scp->snd_window++; - } - - /* - * Packet has been sent more than once. If this is the last - * packet to be acknowledged then we want to send the next - * packet in the send queue again (assumes the remote host does - * go-back-N error control). - */ - if (xmit_count > 1) - try_retrans = 1; - } - - if (try_retrans) - dn_nsp_output(sk); - - return wakeup; -} - -void dn_nsp_send_data_ack(struct sock *sk) -{ - struct sk_buff *skb = NULL; - - if ((skb = dn_alloc_skb(sk, 9, GFP_ATOMIC)) == NULL) - return; - - skb_reserve(skb, 9); - dn_mk_ack_header(sk, skb, 0x04, 9, 0); - dn_nsp_send(skb); -} - -void dn_nsp_send_oth_ack(struct sock *sk) -{ - struct sk_buff *skb = NULL; - - if ((skb = dn_alloc_skb(sk, 9, GFP_ATOMIC)) == NULL) - return; - - skb_reserve(skb, 9); - dn_mk_ack_header(sk, skb, 0x14, 9, 1); - dn_nsp_send(skb); -} - - -void dn_send_conn_ack (struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb = NULL; - struct nsp_conn_ack_msg *msg; - - if ((skb = dn_alloc_skb(sk, 3, sk->sk_allocation)) == NULL) - return; - - msg = skb_put(skb, 3); - msg->msgflg = 0x24; - msg->dstaddr = scp->addrrem; - - dn_nsp_send(skb); -} - -static int dn_nsp_retrans_conn_conf(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->state == DN_CC) - dn_send_conn_conf(sk, GFP_ATOMIC); - - return 0; -} - -void dn_send_conn_conf(struct sock *sk, gfp_t gfp) -{ - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb = NULL; - struct nsp_conn_init_msg *msg; - __u8 len = (__u8)le16_to_cpu(scp->conndata_out.opt_optl); - - if ((skb = dn_alloc_skb(sk, 50 + len, gfp)) == NULL) - return; - - msg = skb_put(skb, sizeof(*msg)); - msg->msgflg = 0x28; - msg->dstaddr = scp->addrrem; - msg->srcaddr = scp->addrloc; - msg->services = scp->services_loc; - msg->info = scp->info_loc; - msg->segsize = cpu_to_le16(scp->segsize_loc); - - skb_put_u8(skb, len); - - if (len > 0) - skb_put_data(skb, scp->conndata_out.opt_data, len); - - - dn_nsp_send(skb); - - scp->persist = dn_nsp_persist(sk); - scp->persist_fxn = dn_nsp_retrans_conn_conf; -} - - -static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, - unsigned short reason, gfp_t gfp, - struct dst_entry *dst, - int ddl, unsigned char *dd, __le16 rem, __le16 loc) -{ - struct sk_buff *skb = NULL; - int size = 7 + ddl + ((msgflg == NSP_DISCINIT) ? 1 : 0); - unsigned char *msg; - - if ((dst == NULL) || (rem == 0)) { - net_dbg_ratelimited("DECnet: dn_nsp_do_disc: BUG! Please report this to SteveW@ACM.org rem=%u dst=%p\n", - le16_to_cpu(rem), dst); - return; - } - - if ((skb = dn_alloc_skb(sk, size, gfp)) == NULL) - return; - - msg = skb_put(skb, size); - *msg++ = msgflg; - *(__le16 *)msg = rem; - msg += 2; - *(__le16 *)msg = loc; - msg += 2; - *(__le16 *)msg = cpu_to_le16(reason); - msg += 2; - if (msgflg == NSP_DISCINIT) - *msg++ = ddl; - - if (ddl) { - memcpy(msg, dd, ddl); - } - - /* - * This doesn't go via the dn_nsp_send() function since we need - * to be able to send disc packets out which have no socket - * associations. - */ - skb_dst_set(skb, dst_clone(dst)); - dst_output(&init_net, skb->sk, skb); -} - - -void dn_nsp_send_disc(struct sock *sk, unsigned char msgflg, - unsigned short reason, gfp_t gfp) -{ - struct dn_scp *scp = DN_SK(sk); - int ddl = 0; - - if (msgflg == NSP_DISCINIT) - ddl = le16_to_cpu(scp->discdata_out.opt_optl); - - if (reason == 0) - reason = le16_to_cpu(scp->discdata_out.opt_status); - - dn_nsp_do_disc(sk, msgflg, reason, gfp, __sk_dst_get(sk), ddl, - scp->discdata_out.opt_data, scp->addrrem, scp->addrloc); -} - - -void dn_nsp_return_disc(struct sk_buff *skb, unsigned char msgflg, - unsigned short reason) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - int ddl = 0; - gfp_t gfp = GFP_ATOMIC; - - dn_nsp_do_disc(NULL, msgflg, reason, gfp, skb_dst(skb), ddl, - NULL, cb->src_port, cb->dst_port); -} - - -void dn_nsp_send_link(struct sock *sk, unsigned char lsflags, char fcval) -{ - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb; - unsigned char *ptr; - gfp_t gfp = GFP_ATOMIC; - - if ((skb = dn_alloc_skb(sk, DN_MAX_NSP_DATA_HEADER + 2, gfp)) == NULL) - return; - - skb_reserve(skb, DN_MAX_NSP_DATA_HEADER); - ptr = skb_put(skb, 2); - DN_SKB_CB(skb)->nsp_flags = 0x10; - *ptr++ = lsflags; - *ptr = fcval; - - dn_nsp_queue_xmit(sk, skb, gfp, 1); - - scp->persist = dn_nsp_persist(sk); - scp->persist_fxn = dn_nsp_xmit_timeout; -} - -static int dn_nsp_retrans_conninit(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->state == DN_CI) - dn_nsp_send_conninit(sk, NSP_RCI); - - return 0; -} - -void dn_nsp_send_conninit(struct sock *sk, unsigned char msgflg) -{ - struct dn_scp *scp = DN_SK(sk); - struct nsp_conn_init_msg *msg; - unsigned char aux; - unsigned char menuver; - struct dn_skb_cb *cb; - unsigned char type = 1; - gfp_t allocation = (msgflg == NSP_CI) ? sk->sk_allocation : GFP_ATOMIC; - struct sk_buff *skb = dn_alloc_skb(sk, 200, allocation); - - if (!skb) - return; - - cb = DN_SKB_CB(skb); - msg = skb_put(skb, sizeof(*msg)); - - msg->msgflg = msgflg; - msg->dstaddr = 0x0000; /* Remote Node will assign it*/ - - msg->srcaddr = scp->addrloc; - msg->services = scp->services_loc; /* Requested flow control */ - msg->info = scp->info_loc; /* Version Number */ - msg->segsize = cpu_to_le16(scp->segsize_loc); /* Max segment size */ - - if (scp->peer.sdn_objnum) - type = 0; - - skb_put(skb, dn_sockaddr2username(&scp->peer, - skb_tail_pointer(skb), type)); - skb_put(skb, dn_sockaddr2username(&scp->addr, - skb_tail_pointer(skb), 2)); - - menuver = DN_MENUVER_ACC | DN_MENUVER_USR; - if (scp->peer.sdn_flags & SDF_PROXY) - menuver |= DN_MENUVER_PRX; - if (scp->peer.sdn_flags & SDF_UICPROXY) - menuver |= DN_MENUVER_UIC; - - skb_put_u8(skb, menuver); /* Menu Version */ - - aux = scp->accessdata.acc_userl; - skb_put_u8(skb, aux); - if (aux > 0) - skb_put_data(skb, scp->accessdata.acc_user, aux); - - aux = scp->accessdata.acc_passl; - skb_put_u8(skb, aux); - if (aux > 0) - skb_put_data(skb, scp->accessdata.acc_pass, aux); - - aux = scp->accessdata.acc_accl; - skb_put_u8(skb, aux); - if (aux > 0) - skb_put_data(skb, scp->accessdata.acc_acc, aux); - - aux = (__u8)le16_to_cpu(scp->conndata_out.opt_optl); - skb_put_u8(skb, aux); - if (aux > 0) - skb_put_data(skb, scp->conndata_out.opt_data, aux); - - scp->persist = dn_nsp_persist(sk); - scp->persist_fxn = dn_nsp_retrans_conninit; - - cb->rt_flags = DN_RT_F_RQR; - - dn_nsp_send(skb); -} diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c deleted file mode 100644 index 4cac31d22a50..000000000000 --- a/net/decnet/dn_route.c +++ /dev/null @@ -1,1923 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Functions (Endnode and Router) - * - * Authors: Steve Whitehouse - * Eduardo Marcelo Serrat - * - * Changes: - * Steve Whitehouse : Fixes to allow "intra-ethernet" and - * "return-to-sender" bits on outgoing - * packets. - * Steve Whitehouse : Timeouts for cached routes. - * Steve Whitehouse : Use dst cache for input routes too. - * Steve Whitehouse : Fixed error values in dn_send_skb. - * Steve Whitehouse : Rework routing functions to better fit - * DECnet routing design - * Alexey Kuznetsov : New SMP locking - * Steve Whitehouse : More SMP locking changes & dn_cache_dump() - * Steve Whitehouse : Prerouting NF hook, now really is prerouting. - * Fixed possible skb leak in rtnetlink funcs. - * Steve Whitehouse : Dave Miller's dynamic hash table sizing and - * Alexey Kuznetsov's finer grained locking - * from ipv4/route.c. - * Steve Whitehouse : Routing is now starting to look like a - * sensible set of code now, mainly due to - * my copying the IPv4 routing code. The - * hooks here are modified and will continue - * to evolve for a while. - * Steve Whitehouse : Real SMP at last :-) Also new netfilter - * stuff. Look out raw sockets your days - * are numbered! - * Steve Whitehouse : Added return-to-sender functions. Added - * backlog congestion level return codes. - * Steve Whitehouse : Fixed bug where routes were set up with - * no ref count on net devices. - * Steve Whitehouse : RCU for the route cache - * Steve Whitehouse : Preparations for the flow cache - * Steve Whitehouse : Prepare for nonlinear skbs - */ - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - -*******************************************************************************/ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -struct dn_rt_hash_bucket -{ - struct dn_route __rcu *chain; - spinlock_t lock; -}; - -extern struct neigh_table dn_neigh_table; - - -static unsigned char dn_hiord_addr[6] = {0xAA,0x00,0x04,0x00,0x00,0x00}; - -static const int dn_rt_min_delay = 2 * HZ; -static const int dn_rt_max_delay = 10 * HZ; -static const int dn_rt_mtu_expires = 10 * 60 * HZ; - -static unsigned long dn_rt_deadline; - -static int dn_dst_gc(struct dst_ops *ops); -static struct dst_entry *dn_dst_check(struct dst_entry *, __u32); -static unsigned int dn_dst_default_advmss(const struct dst_entry *dst); -static unsigned int dn_dst_mtu(const struct dst_entry *dst); -static void dn_dst_destroy(struct dst_entry *); -static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); -static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); -static void dn_dst_link_failure(struct sk_buff *); -static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb , u32 mtu, - bool confirm_neigh); -static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb); -static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, - struct sk_buff *skb, - const void *daddr); -static int dn_route_input(struct sk_buff *); -static void dn_run_flush(struct timer_list *unused); - -static struct dn_rt_hash_bucket *dn_rt_hash_table; -static unsigned int dn_rt_hash_mask; - -static struct timer_list dn_route_timer; -static DEFINE_TIMER(dn_rt_flush_timer, dn_run_flush); -int decnet_dst_gc_interval = 2; - -static struct dst_ops dn_dst_ops = { - .family = PF_DECnet, - .gc_thresh = 128, - .gc = dn_dst_gc, - .check = dn_dst_check, - .default_advmss = dn_dst_default_advmss, - .mtu = dn_dst_mtu, - .cow_metrics = dst_cow_metrics_generic, - .destroy = dn_dst_destroy, - .ifdown = dn_dst_ifdown, - .negative_advice = dn_dst_negative_advice, - .link_failure = dn_dst_link_failure, - .update_pmtu = dn_dst_update_pmtu, - .redirect = dn_dst_redirect, - .neigh_lookup = dn_dst_neigh_lookup, -}; - -static void dn_dst_destroy(struct dst_entry *dst) -{ - struct dn_route *rt = (struct dn_route *) dst; - - if (rt->n) - neigh_release(rt->n); - dst_destroy_metrics_generic(dst); -} - -static void dn_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) -{ - if (how) { - struct dn_route *rt = (struct dn_route *) dst; - struct neighbour *n = rt->n; - - if (n && n->dev == dev) { - n->dev = dev_net(dev)->loopback_dev; - dev_hold(n->dev); - dev_put(dev); - } - } -} - -static __inline__ unsigned int dn_hash(__le16 src, __le16 dst) -{ - __u16 tmp = (__u16 __force)(src ^ dst); - tmp ^= (tmp >> 3); - tmp ^= (tmp >> 5); - tmp ^= (tmp >> 10); - return dn_rt_hash_mask & (unsigned int)tmp; -} - -static void dn_dst_check_expire(struct timer_list *unused) -{ - int i; - struct dn_route *rt; - struct dn_route __rcu **rtp; - unsigned long now = jiffies; - unsigned long expire = 120 * HZ; - - for (i = 0; i <= dn_rt_hash_mask; i++) { - rtp = &dn_rt_hash_table[i].chain; - - spin_lock(&dn_rt_hash_table[i].lock); - while ((rt = rcu_dereference_protected(*rtp, - lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { - if (atomic_read(&rt->dst.__refcnt) > 1 || - (now - rt->dst.lastuse) < expire) { - rtp = &rt->dn_next; - continue; - } - *rtp = rt->dn_next; - rt->dn_next = NULL; - dst_dev_put(&rt->dst); - dst_release(&rt->dst); - } - spin_unlock(&dn_rt_hash_table[i].lock); - - if ((jiffies - now) > 0) - break; - } - - mod_timer(&dn_route_timer, now + decnet_dst_gc_interval * HZ); -} - -static int dn_dst_gc(struct dst_ops *ops) -{ - struct dn_route *rt; - struct dn_route __rcu **rtp; - int i; - unsigned long now = jiffies; - unsigned long expire = 10 * HZ; - - for (i = 0; i <= dn_rt_hash_mask; i++) { - - spin_lock_bh(&dn_rt_hash_table[i].lock); - rtp = &dn_rt_hash_table[i].chain; - - while ((rt = rcu_dereference_protected(*rtp, - lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { - if (atomic_read(&rt->dst.__refcnt) > 1 || - (now - rt->dst.lastuse) < expire) { - rtp = &rt->dn_next; - continue; - } - *rtp = rt->dn_next; - rt->dn_next = NULL; - dst_dev_put(&rt->dst); - dst_release(&rt->dst); - break; - } - spin_unlock_bh(&dn_rt_hash_table[i].lock); - } - - return 0; -} - -/* - * The decnet standards don't impose a particular minimum mtu, what they - * do insist on is that the routing layer accepts a datagram of at least - * 230 bytes long. Here we have to subtract the routing header length from - * 230 to get the minimum acceptable mtu. If there is no neighbour, then we - * assume the worst and use a long header size. - * - * We update both the mtu and the advertised mss (i.e. the segment size we - * advertise to the other end). - */ -static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu, - bool confirm_neigh) -{ - struct dn_route *rt = (struct dn_route *) dst; - struct neighbour *n = rt->n; - u32 min_mtu = 230; - struct dn_dev *dn; - - dn = n ? rcu_dereference_raw(n->dev->dn_ptr) : NULL; - - if (dn && dn->use_long == 0) - min_mtu -= 6; - else - min_mtu -= 21; - - if (dst_metric(dst, RTAX_MTU) > mtu && mtu >= min_mtu) { - if (!(dst_metric_locked(dst, RTAX_MTU))) { - dst_metric_set(dst, RTAX_MTU, mtu); - dst_set_expires(dst, dn_rt_mtu_expires); - } - if (!(dst_metric_locked(dst, RTAX_ADVMSS))) { - u32 mss = mtu - DN_MAX_NSP_DATA_HEADER; - u32 existing_mss = dst_metric_raw(dst, RTAX_ADVMSS); - if (!existing_mss || existing_mss > mss) - dst_metric_set(dst, RTAX_ADVMSS, mss); - } - } -} - -static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb) -{ -} - -/* - * When a route has been marked obsolete. (e.g. routing cache flush) - */ -static struct dst_entry *dn_dst_check(struct dst_entry *dst, __u32 cookie) -{ - return NULL; -} - -static struct dst_entry *dn_dst_negative_advice(struct dst_entry *dst) -{ - dst_release(dst); - return NULL; -} - -static void dn_dst_link_failure(struct sk_buff *skb) -{ -} - -static inline int compare_keys(struct flowidn *fl1, struct flowidn *fl2) -{ - return ((fl1->daddr ^ fl2->daddr) | - (fl1->saddr ^ fl2->saddr) | - (fl1->flowidn_mark ^ fl2->flowidn_mark) | - (fl1->flowidn_scope ^ fl2->flowidn_scope) | - (fl1->flowidn_oif ^ fl2->flowidn_oif) | - (fl1->flowidn_iif ^ fl2->flowidn_iif)) == 0; -} - -static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_route **rp) -{ - struct dn_route *rth; - struct dn_route __rcu **rthp; - unsigned long now = jiffies; - - rthp = &dn_rt_hash_table[hash].chain; - - spin_lock_bh(&dn_rt_hash_table[hash].lock); - while ((rth = rcu_dereference_protected(*rthp, - lockdep_is_held(&dn_rt_hash_table[hash].lock))) != NULL) { - if (compare_keys(&rth->fld, &rt->fld)) { - /* Put it first */ - *rthp = rth->dn_next; - rcu_assign_pointer(rth->dn_next, - dn_rt_hash_table[hash].chain); - rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth); - - dst_hold_and_use(&rth->dst, now); - spin_unlock_bh(&dn_rt_hash_table[hash].lock); - - dst_release_immediate(&rt->dst); - *rp = rth; - return 0; - } - rthp = &rth->dn_next; - } - - rcu_assign_pointer(rt->dn_next, dn_rt_hash_table[hash].chain); - rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt); - - dst_hold_and_use(&rt->dst, now); - spin_unlock_bh(&dn_rt_hash_table[hash].lock); - *rp = rt; - return 0; -} - -static void dn_run_flush(struct timer_list *unused) -{ - int i; - struct dn_route *rt, *next; - - for (i = 0; i < dn_rt_hash_mask; i++) { - spin_lock_bh(&dn_rt_hash_table[i].lock); - - if ((rt = xchg((struct dn_route **)&dn_rt_hash_table[i].chain, NULL)) == NULL) - goto nothing_to_declare; - - for(; rt; rt = next) { - next = rcu_dereference_raw(rt->dn_next); - RCU_INIT_POINTER(rt->dn_next, NULL); - dst_dev_put(&rt->dst); - dst_release(&rt->dst); - } - -nothing_to_declare: - spin_unlock_bh(&dn_rt_hash_table[i].lock); - } -} - -static DEFINE_SPINLOCK(dn_rt_flush_lock); - -void dn_rt_cache_flush(int delay) -{ - unsigned long now = jiffies; - int user_mode = !in_interrupt(); - - if (delay < 0) - delay = dn_rt_min_delay; - - spin_lock_bh(&dn_rt_flush_lock); - - if (del_timer(&dn_rt_flush_timer) && delay > 0 && dn_rt_deadline) { - long tmo = (long)(dn_rt_deadline - now); - - if (user_mode && tmo < dn_rt_max_delay - dn_rt_min_delay) - tmo = 0; - - if (delay > tmo) - delay = tmo; - } - - if (delay <= 0) { - spin_unlock_bh(&dn_rt_flush_lock); - dn_run_flush(NULL); - return; - } - - if (dn_rt_deadline == 0) - dn_rt_deadline = now + dn_rt_max_delay; - - dn_rt_flush_timer.expires = now + delay; - add_timer(&dn_rt_flush_timer); - spin_unlock_bh(&dn_rt_flush_lock); -} - -/** - * dn_return_short - Return a short packet to its sender - * @skb: The packet to return - * - */ -static int dn_return_short(struct sk_buff *skb) -{ - struct dn_skb_cb *cb; - unsigned char *ptr; - __le16 *src; - __le16 *dst; - - /* Add back headers */ - skb_push(skb, skb->data - skb_network_header(skb)); - - if ((skb = skb_unshare(skb, GFP_ATOMIC)) == NULL) - return NET_RX_DROP; - - cb = DN_SKB_CB(skb); - /* Skip packet length and point to flags */ - ptr = skb->data + 2; - *ptr++ = (cb->rt_flags & ~DN_RT_F_RQR) | DN_RT_F_RTS; - - dst = (__le16 *)ptr; - ptr += 2; - src = (__le16 *)ptr; - ptr += 2; - *ptr = 0; /* Zero hop count */ - - swap(*src, *dst); - - skb->pkt_type = PACKET_OUTGOING; - dn_rt_finish_output(skb, NULL, NULL); - return NET_RX_SUCCESS; -} - -/** - * dn_return_long - Return a long packet to its sender - * @skb: The long format packet to return - * - */ -static int dn_return_long(struct sk_buff *skb) -{ - struct dn_skb_cb *cb; - unsigned char *ptr; - unsigned char *src_addr, *dst_addr; - unsigned char tmp[ETH_ALEN]; - - /* Add back all headers */ - skb_push(skb, skb->data - skb_network_header(skb)); - - if ((skb = skb_unshare(skb, GFP_ATOMIC)) == NULL) - return NET_RX_DROP; - - cb = DN_SKB_CB(skb); - /* Ignore packet length and point to flags */ - ptr = skb->data + 2; - - /* Skip padding */ - if (*ptr & DN_RT_F_PF) { - char padlen = (*ptr & ~DN_RT_F_PF); - ptr += padlen; - } - - *ptr++ = (cb->rt_flags & ~DN_RT_F_RQR) | DN_RT_F_RTS; - ptr += 2; - dst_addr = ptr; - ptr += 8; - src_addr = ptr; - ptr += 6; - *ptr = 0; /* Zero hop count */ - - /* Swap source and destination */ - memcpy(tmp, src_addr, ETH_ALEN); - memcpy(src_addr, dst_addr, ETH_ALEN); - memcpy(dst_addr, tmp, ETH_ALEN); - - skb->pkt_type = PACKET_OUTGOING; - dn_rt_finish_output(skb, dst_addr, src_addr); - return NET_RX_SUCCESS; -} - -/** - * dn_route_rx_packet - Try and find a route for an incoming packet - * @net: The applicable net namespace - * @sk: Socket packet transmitted on - * @skb: The packet to find a route for - * - * Returns: result of input function if route is found, error code otherwise - */ -static int dn_route_rx_packet(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dn_skb_cb *cb; - int err; - - if ((err = dn_route_input(skb)) == 0) - return dst_input(skb); - - cb = DN_SKB_CB(skb); - if (decnet_debug_level & 4) { - char *devname = skb->dev ? skb->dev->name : "???"; - - printk(KERN_DEBUG - "DECnet: dn_route_rx_packet: rt_flags=0x%02x dev=%s len=%d src=0x%04hx dst=0x%04hx err=%d type=%d\n", - (int)cb->rt_flags, devname, skb->len, - le16_to_cpu(cb->src), le16_to_cpu(cb->dst), - err, skb->pkt_type); - } - - if ((skb->pkt_type == PACKET_HOST) && (cb->rt_flags & DN_RT_F_RQR)) { - switch (cb->rt_flags & DN_RT_PKT_MSK) { - case DN_RT_PKT_SHORT: - return dn_return_short(skb); - case DN_RT_PKT_LONG: - return dn_return_long(skb); - } - } - - kfree_skb(skb); - return NET_RX_DROP; -} - -static int dn_route_rx_long(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned char *ptr = skb->data; - - if (!pskb_may_pull(skb, 21)) /* 20 for long header, 1 for shortest nsp */ - goto drop_it; - - skb_pull(skb, 20); - skb_reset_transport_header(skb); - - /* Destination info */ - ptr += 2; - cb->dst = dn_eth2dn(ptr); - if (memcmp(ptr, dn_hiord_addr, 4) != 0) - goto drop_it; - ptr += 6; - - - /* Source info */ - ptr += 2; - cb->src = dn_eth2dn(ptr); - if (memcmp(ptr, dn_hiord_addr, 4) != 0) - goto drop_it; - ptr += 6; - /* Other junk */ - ptr++; - cb->hops = *ptr++; /* Visit Count */ - - return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, - &init_net, NULL, skb, skb->dev, NULL, - dn_route_rx_packet); - -drop_it: - kfree_skb(skb); - return NET_RX_DROP; -} - - - -static int dn_route_rx_short(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned char *ptr = skb->data; - - if (!pskb_may_pull(skb, 6)) /* 5 for short header + 1 for shortest nsp */ - goto drop_it; - - skb_pull(skb, 5); - skb_reset_transport_header(skb); - - cb->dst = *(__le16 *)ptr; - ptr += 2; - cb->src = *(__le16 *)ptr; - ptr += 2; - cb->hops = *ptr & 0x3f; - - return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, - &init_net, NULL, skb, skb->dev, NULL, - dn_route_rx_packet); - -drop_it: - kfree_skb(skb); - return NET_RX_DROP; -} - -static int dn_route_discard(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - /* - * I know we drop the packet here, but thats considered success in - * this case - */ - kfree_skb(skb); - return NET_RX_SUCCESS; -} - -static int dn_route_ptp_hello(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - dn_dev_hello(skb); - dn_neigh_pointopoint_hello(skb); - return NET_RX_SUCCESS; -} - -int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) -{ - struct dn_skb_cb *cb; - unsigned char flags = 0; - __u16 len = le16_to_cpu(*(__le16 *)skb->data); - struct dn_dev *dn = rcu_dereference(dev->dn_ptr); - unsigned char padlen = 0; - - if (!net_eq(dev_net(dev), &init_net)) - goto dump_it; - - if (dn == NULL) - goto dump_it; - - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) - goto out; - - if (!pskb_may_pull(skb, 3)) - goto dump_it; - - skb_pull(skb, 2); - - if (len > skb->len) - goto dump_it; - - skb_trim(skb, len); - - flags = *skb->data; - - cb = DN_SKB_CB(skb); - cb->stamp = jiffies; - cb->iif = dev->ifindex; - - /* - * If we have padding, remove it. - */ - if (flags & DN_RT_F_PF) { - padlen = flags & ~DN_RT_F_PF; - if (!pskb_may_pull(skb, padlen + 1)) - goto dump_it; - skb_pull(skb, padlen); - flags = *skb->data; - } - - skb_reset_network_header(skb); - - /* - * Weed out future version DECnet - */ - if (flags & DN_RT_F_VER) - goto dump_it; - - cb->rt_flags = flags; - - if (decnet_debug_level & 1) - printk(KERN_DEBUG - "dn_route_rcv: got 0x%02x from %s [%d %d %d]\n", - (int)flags, dev->name, len, skb->len, - padlen); - - if (flags & DN_RT_PKT_CNTL) { - if (unlikely(skb_linearize(skb))) - goto dump_it; - - switch (flags & DN_RT_CNTL_MSK) { - case DN_RT_PKT_INIT: - dn_dev_init_pkt(skb); - break; - case DN_RT_PKT_VERI: - dn_dev_veri_pkt(skb); - break; - } - - if (dn->parms.state != DN_DEV_S_RU) - goto dump_it; - - switch (flags & DN_RT_CNTL_MSK) { - case DN_RT_PKT_HELO: - return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - &init_net, NULL, skb, skb->dev, NULL, - dn_route_ptp_hello); - - case DN_RT_PKT_L1RT: - case DN_RT_PKT_L2RT: - return NF_HOOK(NFPROTO_DECNET, NF_DN_ROUTE, - &init_net, NULL, skb, skb->dev, NULL, - dn_route_discard); - case DN_RT_PKT_ERTH: - return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - &init_net, NULL, skb, skb->dev, NULL, - dn_neigh_router_hello); - - case DN_RT_PKT_EEDH: - return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - &init_net, NULL, skb, skb->dev, NULL, - dn_neigh_endnode_hello); - } - } else { - if (dn->parms.state != DN_DEV_S_RU) - goto dump_it; - - skb_pull(skb, 1); /* Pull flags */ - - switch (flags & DN_RT_PKT_MSK) { - case DN_RT_PKT_LONG: - return dn_route_rx_long(skb); - case DN_RT_PKT_SHORT: - return dn_route_rx_short(skb); - } - } - -dump_it: - kfree_skb(skb); -out: - return NET_RX_DROP; -} - -static int dn_output(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - struct dn_route *rt = (struct dn_route *)dst; - struct net_device *dev = dst->dev; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - int err = -EINVAL; - - if (rt->n == NULL) - goto error; - - skb->dev = dev; - - cb->src = rt->rt_saddr; - cb->dst = rt->rt_daddr; - - /* - * Always set the Intra-Ethernet bit on all outgoing packets - * originated on this node. Only valid flag from upper layers - * is return-to-sender-requested. Set hop count to 0 too. - */ - cb->rt_flags &= ~DN_RT_F_RQR; - cb->rt_flags |= DN_RT_F_IE; - cb->hops = 0; - - return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, - &init_net, sk, skb, NULL, dev, - dn_to_neigh_output); - -error: - net_dbg_ratelimited("dn_output: This should not happen\n"); - - kfree_skb(skb); - - return err; -} - -static int dn_forward(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dst_entry *dst = skb_dst(skb); - struct dn_dev *dn_db = rcu_dereference(dst->dev->dn_ptr); - struct dn_route *rt; - int header_len; - struct net_device *dev = skb->dev; - - if (skb->pkt_type != PACKET_HOST) - goto drop; - - /* Ensure that we have enough space for headers */ - rt = (struct dn_route *)skb_dst(skb); - header_len = dn_db->use_long ? 21 : 6; - if (skb_cow(skb, LL_RESERVED_SPACE(rt->dst.dev)+header_len)) - goto drop; - - /* - * Hop count exceeded. - */ - if (++cb->hops > 30) - goto drop; - - skb->dev = rt->dst.dev; - - /* - * If packet goes out same interface it came in on, then set - * the Intra-Ethernet bit. This has no effect for short - * packets, so we don't need to test for them here. - */ - cb->rt_flags &= ~DN_RT_F_IE; - if (rt->rt_flags & RTCF_DOREDIRECT) - cb->rt_flags |= DN_RT_F_IE; - - return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, - &init_net, NULL, skb, dev, skb->dev, - dn_to_neigh_output); - -drop: - kfree_skb(skb); - return NET_RX_DROP; -} - -/* - * Used to catch bugs. This should never normally get - * called. - */ -static int dn_rt_bug_out(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - net_dbg_ratelimited("dn_rt_bug: skb from:%04x to:%04x\n", - le16_to_cpu(cb->src), le16_to_cpu(cb->dst)); - - kfree_skb(skb); - - return NET_RX_DROP; -} - -static int dn_rt_bug(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - net_dbg_ratelimited("dn_rt_bug: skb from:%04x to:%04x\n", - le16_to_cpu(cb->src), le16_to_cpu(cb->dst)); - - kfree_skb(skb); - - return NET_RX_DROP; -} - -static unsigned int dn_dst_default_advmss(const struct dst_entry *dst) -{ - return dn_mss_from_pmtu(dst->dev, dst_mtu(dst)); -} - -static unsigned int dn_dst_mtu(const struct dst_entry *dst) -{ - unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); - - return mtu ? : dst->dev->mtu; -} - -static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, - struct sk_buff *skb, - const void *daddr) -{ - return __neigh_lookup_errno(&dn_neigh_table, daddr, dst->dev); -} - -static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) -{ - struct dn_fib_info *fi = res->fi; - struct net_device *dev = rt->dst.dev; - unsigned int mss_metric; - struct neighbour *n; - - if (fi) { - if (DN_FIB_RES_GW(*res) && - DN_FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) - rt->rt_gateway = DN_FIB_RES_GW(*res); - dst_init_metrics(&rt->dst, fi->fib_metrics, true); - } - rt->rt_type = res->type; - - if (dev != NULL && rt->n == NULL) { - n = __neigh_lookup_errno(&dn_neigh_table, &rt->rt_gateway, dev); - if (IS_ERR(n)) - return PTR_ERR(n); - rt->n = n; - } - - if (dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu) - dst_metric_set(&rt->dst, RTAX_MTU, rt->dst.dev->mtu); - mss_metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS); - if (mss_metric) { - unsigned int mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->dst)); - if (mss_metric > mss) - dst_metric_set(&rt->dst, RTAX_ADVMSS, mss); - } - return 0; -} - -static inline int dn_match_addr(__le16 addr1, __le16 addr2) -{ - __u16 tmp = le16_to_cpu(addr1) ^ le16_to_cpu(addr2); - int match = 16; - while(tmp) { - tmp >>= 1; - match--; - } - return match; -} - -static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int scope) -{ - __le16 saddr = 0; - struct dn_dev *dn_db; - struct dn_ifaddr *ifa; - int best_match = 0; - int ret; - - rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); - for (ifa = rcu_dereference(dn_db->ifa_list); - ifa != NULL; - ifa = rcu_dereference(ifa->ifa_next)) { - if (ifa->ifa_scope > scope) - continue; - if (!daddr) { - saddr = ifa->ifa_local; - break; - } - ret = dn_match_addr(daddr, ifa->ifa_local); - if (ret > best_match) - saddr = ifa->ifa_local; - if (best_match == 0) - saddr = ifa->ifa_local; - } - rcu_read_unlock(); - - return saddr; -} - -static inline __le16 __dn_fib_res_prefsrc(struct dn_fib_res *res) -{ - return dnet_select_source(DN_FIB_RES_DEV(*res), DN_FIB_RES_GW(*res), res->scope); -} - -static inline __le16 dn_fib_rules_map_destination(__le16 daddr, struct dn_fib_res *res) -{ - __le16 mask = dnet_make_mask(res->prefixlen); - return (daddr&~mask)|res->fi->fib_nh->nh_gw; -} - -static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *oldflp, int try_hard) -{ - struct flowidn fld = { - .daddr = oldflp->daddr, - .saddr = oldflp->saddr, - .flowidn_scope = RT_SCOPE_UNIVERSE, - .flowidn_mark = oldflp->flowidn_mark, - .flowidn_iif = LOOPBACK_IFINDEX, - .flowidn_oif = oldflp->flowidn_oif, - }; - struct dn_route *rt = NULL; - struct net_device *dev_out = NULL, *dev; - struct neighbour *neigh = NULL; - unsigned int hash; - unsigned int flags = 0; - struct dn_fib_res res = { .fi = NULL, .type = RTN_UNICAST }; - int err; - int free_res = 0; - __le16 gateway = 0; - - if (decnet_debug_level & 16) - printk(KERN_DEBUG - "dn_route_output_slow: dst=%04x src=%04x mark=%d" - " iif=%d oif=%d\n", le16_to_cpu(oldflp->daddr), - le16_to_cpu(oldflp->saddr), - oldflp->flowidn_mark, LOOPBACK_IFINDEX, - oldflp->flowidn_oif); - - /* If we have an output interface, verify its a DECnet device */ - if (oldflp->flowidn_oif) { - dev_out = dev_get_by_index(&init_net, oldflp->flowidn_oif); - err = -ENODEV; - if (dev_out && dev_out->dn_ptr == NULL) { - dev_put(dev_out); - dev_out = NULL; - } - if (dev_out == NULL) - goto out; - } - - /* If we have a source address, verify that its a local address */ - if (oldflp->saddr) { - err = -EADDRNOTAVAIL; - - if (dev_out) { - if (dn_dev_islocal(dev_out, oldflp->saddr)) - goto source_ok; - dev_put(dev_out); - goto out; - } - rcu_read_lock(); - for_each_netdev_rcu(&init_net, dev) { - if (!dev->dn_ptr) - continue; - if (!dn_dev_islocal(dev, oldflp->saddr)) - continue; - if ((dev->flags & IFF_LOOPBACK) && - oldflp->daddr && - !dn_dev_islocal(dev, oldflp->daddr)) - continue; - - dev_out = dev; - break; - } - rcu_read_unlock(); - if (dev_out == NULL) - goto out; - dev_hold(dev_out); -source_ok: - ; - } - - /* No destination? Assume its local */ - if (!fld.daddr) { - fld.daddr = fld.saddr; - - if (dev_out) - dev_put(dev_out); - err = -EINVAL; - dev_out = init_net.loopback_dev; - if (!dev_out->dn_ptr) - goto out; - err = -EADDRNOTAVAIL; - dev_hold(dev_out); - if (!fld.daddr) { - fld.daddr = - fld.saddr = dnet_select_source(dev_out, 0, - RT_SCOPE_HOST); - if (!fld.daddr) - goto out; - } - fld.flowidn_oif = LOOPBACK_IFINDEX; - res.type = RTN_LOCAL; - goto make_route; - } - - if (decnet_debug_level & 16) - printk(KERN_DEBUG - "dn_route_output_slow: initial checks complete." - " dst=%04x src=%04x oif=%d try_hard=%d\n", - le16_to_cpu(fld.daddr), le16_to_cpu(fld.saddr), - fld.flowidn_oif, try_hard); - - /* - * N.B. If the kernel is compiled without router support then - * dn_fib_lookup() will evaluate to non-zero so this if () block - * will always be executed. - */ - err = -ESRCH; - if (try_hard || (err = dn_fib_lookup(&fld, &res)) != 0) { - struct dn_dev *dn_db; - if (err != -ESRCH) - goto out; - /* - * Here the fallback is basically the standard algorithm for - * routing in endnodes which is described in the DECnet routing - * docs - * - * If we are not trying hard, look in neighbour cache. - * The result is tested to ensure that if a specific output - * device/source address was requested, then we honour that - * here - */ - if (!try_hard) { - neigh = neigh_lookup_nodev(&dn_neigh_table, &init_net, &fld.daddr); - if (neigh) { - if ((oldflp->flowidn_oif && - (neigh->dev->ifindex != oldflp->flowidn_oif)) || - (oldflp->saddr && - (!dn_dev_islocal(neigh->dev, - oldflp->saddr)))) { - neigh_release(neigh); - neigh = NULL; - } else { - if (dev_out) - dev_put(dev_out); - if (dn_dev_islocal(neigh->dev, fld.daddr)) { - dev_out = init_net.loopback_dev; - res.type = RTN_LOCAL; - } else { - dev_out = neigh->dev; - } - dev_hold(dev_out); - goto select_source; - } - } - } - - /* Not there? Perhaps its a local address */ - if (dev_out == NULL) - dev_out = dn_dev_get_default(); - err = -ENODEV; - if (dev_out == NULL) - goto out; - dn_db = rcu_dereference_raw(dev_out->dn_ptr); - if (!dn_db) - goto e_inval; - /* Possible improvement - check all devices for local addr */ - if (dn_dev_islocal(dev_out, fld.daddr)) { - dev_put(dev_out); - dev_out = init_net.loopback_dev; - dev_hold(dev_out); - res.type = RTN_LOCAL; - goto select_source; - } - /* Not local either.... try sending it to the default router */ - neigh = neigh_clone(dn_db->router); - BUG_ON(neigh && neigh->dev != dev_out); - - /* Ok then, we assume its directly connected and move on */ -select_source: - if (neigh) - gateway = ((struct dn_neigh *)neigh)->addr; - if (gateway == 0) - gateway = fld.daddr; - if (fld.saddr == 0) { - fld.saddr = dnet_select_source(dev_out, gateway, - res.type == RTN_LOCAL ? - RT_SCOPE_HOST : - RT_SCOPE_LINK); - if (fld.saddr == 0 && res.type != RTN_LOCAL) - goto e_addr; - } - fld.flowidn_oif = dev_out->ifindex; - goto make_route; - } - free_res = 1; - - if (res.type == RTN_NAT) - goto e_inval; - - if (res.type == RTN_LOCAL) { - if (!fld.saddr) - fld.saddr = fld.daddr; - if (dev_out) - dev_put(dev_out); - dev_out = init_net.loopback_dev; - dev_hold(dev_out); - if (!dev_out->dn_ptr) - goto e_inval; - fld.flowidn_oif = dev_out->ifindex; - if (res.fi) - dn_fib_info_put(res.fi); - res.fi = NULL; - goto make_route; - } - - if (res.fi->fib_nhs > 1 && fld.flowidn_oif == 0) - dn_fib_select_multipath(&fld, &res); - - /* - * We could add some logic to deal with default routes here and - * get rid of some of the special casing above. - */ - - if (!fld.saddr) - fld.saddr = DN_FIB_RES_PREFSRC(res); - - if (dev_out) - dev_put(dev_out); - dev_out = DN_FIB_RES_DEV(res); - dev_hold(dev_out); - fld.flowidn_oif = dev_out->ifindex; - gateway = DN_FIB_RES_GW(res); - -make_route: - if (dev_out->flags & IFF_LOOPBACK) - flags |= RTCF_LOCAL; - - rt = dst_alloc(&dn_dst_ops, dev_out, 0, DST_OBSOLETE_NONE, 0); - if (rt == NULL) - goto e_nobufs; - - rt->dn_next = NULL; - memset(&rt->fld, 0, sizeof(rt->fld)); - rt->fld.saddr = oldflp->saddr; - rt->fld.daddr = oldflp->daddr; - rt->fld.flowidn_oif = oldflp->flowidn_oif; - rt->fld.flowidn_iif = 0; - rt->fld.flowidn_mark = oldflp->flowidn_mark; - - rt->rt_saddr = fld.saddr; - rt->rt_daddr = fld.daddr; - rt->rt_gateway = gateway ? gateway : fld.daddr; - rt->rt_local_src = fld.saddr; - - rt->rt_dst_map = fld.daddr; - rt->rt_src_map = fld.saddr; - - rt->n = neigh; - neigh = NULL; - - rt->dst.lastuse = jiffies; - rt->dst.output = dn_output; - rt->dst.input = dn_rt_bug; - rt->rt_flags = flags; - if (flags & RTCF_LOCAL) - rt->dst.input = dn_nsp_rx; - - err = dn_rt_set_next_hop(rt, &res); - if (err) - goto e_neighbour; - - hash = dn_hash(rt->fld.saddr, rt->fld.daddr); - /* dn_insert_route() increments dst->__refcnt */ - dn_insert_route(rt, hash, (struct dn_route **)pprt); - -done: - if (neigh) - neigh_release(neigh); - if (free_res) - dn_fib_res_put(&res); - if (dev_out) - dev_put(dev_out); -out: - return err; - -e_addr: - err = -EADDRNOTAVAIL; - goto done; -e_inval: - err = -EINVAL; - goto done; -e_nobufs: - err = -ENOBUFS; - goto done; -e_neighbour: - dst_release_immediate(&rt->dst); - goto e_nobufs; -} - - -/* - * N.B. The flags may be moved into the flowi at some future stage. - */ -static int __dn_route_output_key(struct dst_entry **pprt, const struct flowidn *flp, int flags) -{ - unsigned int hash = dn_hash(flp->saddr, flp->daddr); - struct dn_route *rt = NULL; - - if (!(flags & MSG_TRYHARD)) { - rcu_read_lock_bh(); - for (rt = rcu_dereference_bh(dn_rt_hash_table[hash].chain); rt; - rt = rcu_dereference_bh(rt->dn_next)) { - if ((flp->daddr == rt->fld.daddr) && - (flp->saddr == rt->fld.saddr) && - (flp->flowidn_mark == rt->fld.flowidn_mark) && - dn_is_output_route(rt) && - (rt->fld.flowidn_oif == flp->flowidn_oif)) { - dst_hold_and_use(&rt->dst, jiffies); - rcu_read_unlock_bh(); - *pprt = &rt->dst; - return 0; - } - } - rcu_read_unlock_bh(); - } - - return dn_route_output_slow(pprt, flp, flags); -} - -static int dn_route_output_key(struct dst_entry **pprt, struct flowidn *flp, int flags) -{ - int err; - - err = __dn_route_output_key(pprt, flp, flags); - if (err == 0 && flp->flowidn_proto) { - *pprt = xfrm_lookup(&init_net, *pprt, - flowidn_to_flowi(flp), NULL, 0); - if (IS_ERR(*pprt)) { - err = PTR_ERR(*pprt); - *pprt = NULL; - } - } - return err; -} - -int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *fl, struct sock *sk, int flags) -{ - int err; - - err = __dn_route_output_key(pprt, fl, flags & MSG_TRYHARD); - if (err == 0 && fl->flowidn_proto) { - *pprt = xfrm_lookup(&init_net, *pprt, - flowidn_to_flowi(fl), sk, 0); - if (IS_ERR(*pprt)) { - err = PTR_ERR(*pprt); - *pprt = NULL; - } - } - return err; -} - -static int dn_route_input_slow(struct sk_buff *skb) -{ - struct dn_route *rt = NULL; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct net_device *in_dev = skb->dev; - struct net_device *out_dev = NULL; - struct dn_dev *dn_db; - struct neighbour *neigh = NULL; - unsigned int hash; - int flags = 0; - __le16 gateway = 0; - __le16 local_src = 0; - struct flowidn fld = { - .daddr = cb->dst, - .saddr = cb->src, - .flowidn_scope = RT_SCOPE_UNIVERSE, - .flowidn_mark = skb->mark, - .flowidn_iif = skb->dev->ifindex, - }; - struct dn_fib_res res = { .fi = NULL, .type = RTN_UNREACHABLE }; - int err = -EINVAL; - int free_res = 0; - - dev_hold(in_dev); - - if ((dn_db = rcu_dereference(in_dev->dn_ptr)) == NULL) - goto out; - - /* Zero source addresses are not allowed */ - if (fld.saddr == 0) - goto out; - - /* - * In this case we've just received a packet from a source - * outside ourselves pretending to come from us. We don't - * allow it any further to prevent routing loops, spoofing and - * other nasties. Loopback packets already have the dst attached - * so this only affects packets which have originated elsewhere. - */ - err = -ENOTUNIQ; - if (dn_dev_islocal(in_dev, cb->src)) - goto out; - - err = dn_fib_lookup(&fld, &res); - if (err) { - if (err != -ESRCH) - goto out; - /* - * Is the destination us ? - */ - if (!dn_dev_islocal(in_dev, cb->dst)) - goto e_inval; - - res.type = RTN_LOCAL; - } else { - __le16 src_map = fld.saddr; - free_res = 1; - - out_dev = DN_FIB_RES_DEV(res); - if (out_dev == NULL) { - net_crit_ratelimited("Bug in dn_route_input_slow() No output device\n"); - goto e_inval; - } - dev_hold(out_dev); - - if (res.r) - src_map = fld.saddr; /* no NAT support for now */ - - gateway = DN_FIB_RES_GW(res); - if (res.type == RTN_NAT) { - fld.daddr = dn_fib_rules_map_destination(fld.daddr, &res); - dn_fib_res_put(&res); - free_res = 0; - if (dn_fib_lookup(&fld, &res)) - goto e_inval; - free_res = 1; - if (res.type != RTN_UNICAST) - goto e_inval; - flags |= RTCF_DNAT; - gateway = fld.daddr; - } - fld.saddr = src_map; - } - - switch(res.type) { - case RTN_UNICAST: - /* - * Forwarding check here, we only check for forwarding - * being turned off, if you want to only forward intra - * area, its up to you to set the routing tables up - * correctly. - */ - if (dn_db->parms.forwarding == 0) - goto e_inval; - - if (res.fi->fib_nhs > 1 && fld.flowidn_oif == 0) - dn_fib_select_multipath(&fld, &res); - - /* - * Check for out_dev == in_dev. We use the RTCF_DOREDIRECT - * flag as a hint to set the intra-ethernet bit when - * forwarding. If we've got NAT in operation, we don't do - * this optimisation. - */ - if (out_dev == in_dev && !(flags & RTCF_NAT)) - flags |= RTCF_DOREDIRECT; - - local_src = DN_FIB_RES_PREFSRC(res); - - case RTN_BLACKHOLE: - case RTN_UNREACHABLE: - break; - case RTN_LOCAL: - flags |= RTCF_LOCAL; - fld.saddr = cb->dst; - fld.daddr = cb->src; - - /* Routing tables gave us a gateway */ - if (gateway) - goto make_route; - - /* Packet was intra-ethernet, so we know its on-link */ - if (cb->rt_flags & DN_RT_F_IE) { - gateway = cb->src; - goto make_route; - } - - /* Use the default router if there is one */ - neigh = neigh_clone(dn_db->router); - if (neigh) { - gateway = ((struct dn_neigh *)neigh)->addr; - goto make_route; - } - - /* Close eyes and pray */ - gateway = cb->src; - goto make_route; - default: - goto e_inval; - } - -make_route: - rt = dst_alloc(&dn_dst_ops, out_dev, 1, DST_OBSOLETE_NONE, 0); - if (rt == NULL) - goto e_nobufs; - - rt->dn_next = NULL; - memset(&rt->fld, 0, sizeof(rt->fld)); - rt->rt_saddr = fld.saddr; - rt->rt_daddr = fld.daddr; - rt->rt_gateway = fld.daddr; - if (gateway) - rt->rt_gateway = gateway; - rt->rt_local_src = local_src ? local_src : rt->rt_saddr; - - rt->rt_dst_map = fld.daddr; - rt->rt_src_map = fld.saddr; - - rt->fld.saddr = cb->src; - rt->fld.daddr = cb->dst; - rt->fld.flowidn_oif = 0; - rt->fld.flowidn_iif = in_dev->ifindex; - rt->fld.flowidn_mark = fld.flowidn_mark; - - rt->n = neigh; - rt->dst.lastuse = jiffies; - rt->dst.output = dn_rt_bug_out; - switch (res.type) { - case RTN_UNICAST: - rt->dst.input = dn_forward; - break; - case RTN_LOCAL: - rt->dst.output = dn_output; - rt->dst.input = dn_nsp_rx; - rt->dst.dev = in_dev; - flags |= RTCF_LOCAL; - break; - default: - case RTN_UNREACHABLE: - case RTN_BLACKHOLE: - rt->dst.input = dst_discard; - } - rt->rt_flags = flags; - - err = dn_rt_set_next_hop(rt, &res); - if (err) - goto e_neighbour; - - hash = dn_hash(rt->fld.saddr, rt->fld.daddr); - /* dn_insert_route() increments dst->__refcnt */ - dn_insert_route(rt, hash, &rt); - skb_dst_set(skb, &rt->dst); - -done: - if (neigh) - neigh_release(neigh); - if (free_res) - dn_fib_res_put(&res); - dev_put(in_dev); - if (out_dev) - dev_put(out_dev); -out: - return err; - -e_inval: - err = -EINVAL; - goto done; - -e_nobufs: - err = -ENOBUFS; - goto done; - -e_neighbour: - dst_release_immediate(&rt->dst); - goto done; -} - -static int dn_route_input(struct sk_buff *skb) -{ - struct dn_route *rt; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned int hash = dn_hash(cb->src, cb->dst); - - if (skb_dst(skb)) - return 0; - - rcu_read_lock(); - for(rt = rcu_dereference(dn_rt_hash_table[hash].chain); rt != NULL; - rt = rcu_dereference(rt->dn_next)) { - if ((rt->fld.saddr == cb->src) && - (rt->fld.daddr == cb->dst) && - (rt->fld.flowidn_oif == 0) && - (rt->fld.flowidn_mark == skb->mark) && - (rt->fld.flowidn_iif == cb->iif)) { - dst_hold_and_use(&rt->dst, jiffies); - rcu_read_unlock(); - skb_dst_set(skb, (struct dst_entry *)rt); - return 0; - } - } - rcu_read_unlock(); - - return dn_route_input_slow(skb); -} - -static int dn_rt_fill_info(struct sk_buff *skb, u32 portid, u32 seq, - int event, int nowait, unsigned int flags) -{ - struct dn_route *rt = (struct dn_route *)skb_dst(skb); - struct rtmsg *r; - struct nlmsghdr *nlh; - long expires; - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), flags); - if (!nlh) - return -EMSGSIZE; - - r = nlmsg_data(nlh); - r->rtm_family = AF_DECnet; - r->rtm_dst_len = 16; - r->rtm_src_len = 0; - r->rtm_tos = 0; - r->rtm_table = RT_TABLE_MAIN; - r->rtm_type = rt->rt_type; - r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; - r->rtm_scope = RT_SCOPE_UNIVERSE; - r->rtm_protocol = RTPROT_UNSPEC; - - if (rt->rt_flags & RTCF_NOTIFY) - r->rtm_flags |= RTM_F_NOTIFY; - - if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN) < 0 || - nla_put_le16(skb, RTA_DST, rt->rt_daddr) < 0) - goto errout; - - if (rt->fld.saddr) { - r->rtm_src_len = 16; - if (nla_put_le16(skb, RTA_SRC, rt->fld.saddr) < 0) - goto errout; - } - if (rt->dst.dev && - nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex) < 0) - goto errout; - - /* - * Note to self - change this if input routes reverse direction when - * they deal only with inputs and not with replies like they do - * currently. - */ - if (nla_put_le16(skb, RTA_PREFSRC, rt->rt_local_src) < 0) - goto errout; - - if (rt->rt_daddr != rt->rt_gateway && - nla_put_le16(skb, RTA_GATEWAY, rt->rt_gateway) < 0) - goto errout; - - if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) - goto errout; - - expires = rt->dst.expires ? rt->dst.expires - jiffies : 0; - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, - rt->dst.error) < 0) - goto errout; - - if (dn_is_input_route(rt) && - nla_put_u32(skb, RTA_IIF, rt->fld.flowidn_iif) < 0) - goto errout; - - nlmsg_end(skb, nlh); - return 0; - -errout: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; -} - -const struct nla_policy rtm_dn_policy[RTA_MAX + 1] = { - [RTA_DST] = { .type = NLA_U16 }, - [RTA_SRC] = { .type = NLA_U16 }, - [RTA_IIF] = { .type = NLA_U32 }, - [RTA_OIF] = { .type = NLA_U32 }, - [RTA_GATEWAY] = { .type = NLA_U16 }, - [RTA_PRIORITY] = { .type = NLA_U32 }, - [RTA_PREFSRC] = { .type = NLA_U16 }, - [RTA_METRICS] = { .type = NLA_NESTED }, - [RTA_MULTIPATH] = { .type = NLA_NESTED }, - [RTA_TABLE] = { .type = NLA_U32 }, - [RTA_MARK] = { .type = NLA_U32 }, -}; - -/* - * This is called by both endnodes and routers now. - */ -static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(in_skb->sk); - struct rtmsg *rtm = nlmsg_data(nlh); - struct dn_route *rt = NULL; - struct dn_skb_cb *cb; - int err; - struct sk_buff *skb; - struct flowidn fld; - struct nlattr *tb[RTA_MAX+1]; - - if (!net_eq(net, &init_net)) - return -EINVAL; - - err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, - rtm_dn_policy, extack); - if (err < 0) - return err; - - memset(&fld, 0, sizeof(fld)); - fld.flowidn_proto = DNPROTO_NSP; - - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb == NULL) - return -ENOBUFS; - skb_reset_mac_header(skb); - cb = DN_SKB_CB(skb); - - if (tb[RTA_SRC]) - fld.saddr = nla_get_le16(tb[RTA_SRC]); - - if (tb[RTA_DST]) - fld.daddr = nla_get_le16(tb[RTA_DST]); - - if (tb[RTA_IIF]) - fld.flowidn_iif = nla_get_u32(tb[RTA_IIF]); - - if (fld.flowidn_iif) { - struct net_device *dev; - dev = __dev_get_by_index(&init_net, fld.flowidn_iif); - if (!dev || !dev->dn_ptr) { - kfree_skb(skb); - return -ENODEV; - } - skb->protocol = htons(ETH_P_DNA_RT); - skb->dev = dev; - cb->src = fld.saddr; - cb->dst = fld.daddr; - local_bh_disable(); - err = dn_route_input(skb); - local_bh_enable(); - memset(cb, 0, sizeof(struct dn_skb_cb)); - rt = (struct dn_route *)skb_dst(skb); - if (!err && -rt->dst.error) - err = rt->dst.error; - } else { - if (tb[RTA_OIF]) - fld.flowidn_oif = nla_get_u32(tb[RTA_OIF]); - - err = dn_route_output_key((struct dst_entry **)&rt, &fld, 0); - } - - skb->dev = NULL; - if (err) - goto out_free; - skb_dst_set(skb, &rt->dst); - if (rtm->rtm_flags & RTM_F_NOTIFY) - rt->rt_flags |= RTCF_NOTIFY; - - err = dn_rt_fill_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); - if (err < 0) { - err = -EMSGSIZE; - goto out_free; - } - - return rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).portid); - -out_free: - kfree_skb(skb); - return err; -} - -/* - * For routers, this is called from dn_fib_dump, but for endnodes its - * called directly from the rtnetlink dispatch table. - */ -int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - struct dn_route *rt; - int h, s_h; - int idx, s_idx; - struct rtmsg *rtm; - - if (!net_eq(net, &init_net)) - return 0; - - if (nlmsg_len(cb->nlh) < sizeof(struct rtmsg)) - return -EINVAL; - - rtm = nlmsg_data(cb->nlh); - if (!(rtm->rtm_flags & RTM_F_CLONED)) - return 0; - - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - for(h = 0; h <= dn_rt_hash_mask; h++) { - if (h < s_h) - continue; - if (h > s_h) - s_idx = 0; - rcu_read_lock_bh(); - for(rt = rcu_dereference_bh(dn_rt_hash_table[h].chain), idx = 0; - rt; - rt = rcu_dereference_bh(rt->dn_next), idx++) { - if (idx < s_idx) - continue; - skb_dst_set(skb, dst_clone(&rt->dst)); - if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWROUTE, - 1, NLM_F_MULTI) < 0) { - skb_dst_drop(skb); - rcu_read_unlock_bh(); - goto done; - } - skb_dst_drop(skb); - } - rcu_read_unlock_bh(); - } - -done: - cb->args[0] = h; - cb->args[1] = idx; - return skb->len; -} - -#ifdef CONFIG_PROC_FS -struct dn_rt_cache_iter_state { - int bucket; -}; - -static struct dn_route *dn_rt_cache_get_first(struct seq_file *seq) -{ - struct dn_route *rt = NULL; - struct dn_rt_cache_iter_state *s = seq->private; - - for(s->bucket = dn_rt_hash_mask; s->bucket >= 0; --s->bucket) { - rcu_read_lock_bh(); - rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain); - if (rt) - break; - rcu_read_unlock_bh(); - } - return rt; -} - -static struct dn_route *dn_rt_cache_get_next(struct seq_file *seq, struct dn_route *rt) -{ - struct dn_rt_cache_iter_state *s = seq->private; - - rt = rcu_dereference_bh(rt->dn_next); - while (!rt) { - rcu_read_unlock_bh(); - if (--s->bucket < 0) - break; - rcu_read_lock_bh(); - rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain); - } - return rt; -} - -static void *dn_rt_cache_seq_start(struct seq_file *seq, loff_t *pos) -{ - struct dn_route *rt = dn_rt_cache_get_first(seq); - - if (rt) { - while(*pos && (rt = dn_rt_cache_get_next(seq, rt))) - --*pos; - } - return *pos ? NULL : rt; -} - -static void *dn_rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct dn_route *rt = dn_rt_cache_get_next(seq, v); - ++*pos; - return rt; -} - -static void dn_rt_cache_seq_stop(struct seq_file *seq, void *v) -{ - if (v) - rcu_read_unlock_bh(); -} - -static int dn_rt_cache_seq_show(struct seq_file *seq, void *v) -{ - struct dn_route *rt = v; - char buf1[DN_ASCBUF_LEN], buf2[DN_ASCBUF_LEN]; - - seq_printf(seq, "%-8s %-7s %-7s %04d %04d %04d\n", - rt->dst.dev ? rt->dst.dev->name : "*", - dn_addr2asc(le16_to_cpu(rt->rt_daddr), buf1), - dn_addr2asc(le16_to_cpu(rt->rt_saddr), buf2), - atomic_read(&rt->dst.__refcnt), - rt->dst.__use, 0); - return 0; -} - -static const struct seq_operations dn_rt_cache_seq_ops = { - .start = dn_rt_cache_seq_start, - .next = dn_rt_cache_seq_next, - .stop = dn_rt_cache_seq_stop, - .show = dn_rt_cache_seq_show, -}; -#endif /* CONFIG_PROC_FS */ - -void __init dn_route_init(void) -{ - int i, goal, order; - - dn_dst_ops.kmem_cachep = - kmem_cache_create("dn_dst_cache", sizeof(struct dn_route), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); - dst_entries_init(&dn_dst_ops); - timer_setup(&dn_route_timer, dn_dst_check_expire, 0); - dn_route_timer.expires = jiffies + decnet_dst_gc_interval * HZ; - add_timer(&dn_route_timer); - - goal = totalram_pages() >> (26 - PAGE_SHIFT); - - for(order = 0; (1UL << order) < goal; order++) - /* NOTHING */; - - /* - * Only want 1024 entries max, since the table is very, very unlikely - * to be larger than that. - */ - while(order && ((((1UL << order) * PAGE_SIZE) / - sizeof(struct dn_rt_hash_bucket)) >= 2048)) - order--; - - do { - dn_rt_hash_mask = (1UL << order) * PAGE_SIZE / - sizeof(struct dn_rt_hash_bucket); - while(dn_rt_hash_mask & (dn_rt_hash_mask - 1)) - dn_rt_hash_mask--; - dn_rt_hash_table = (struct dn_rt_hash_bucket *) - __get_free_pages(GFP_ATOMIC, order); - } while (dn_rt_hash_table == NULL && --order > 0); - - if (!dn_rt_hash_table) - panic("Failed to allocate DECnet route cache hash table\n"); - - printk(KERN_INFO - "DECnet: Routing cache hash table of %u buckets, %ldKbytes\n", - dn_rt_hash_mask, - (long)(dn_rt_hash_mask*sizeof(struct dn_rt_hash_bucket))/1024); - - dn_rt_hash_mask--; - for(i = 0; i <= dn_rt_hash_mask; i++) { - spin_lock_init(&dn_rt_hash_table[i].lock); - dn_rt_hash_table[i].chain = NULL; - } - - dn_dst_ops.gc_thresh = (dn_rt_hash_mask + 1); - - proc_create_seq_private("decnet_cache", 0444, init_net.proc_net, - &dn_rt_cache_seq_ops, - sizeof(struct dn_rt_cache_iter_state), NULL); - -#ifdef CONFIG_DECNET_ROUTER - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETROUTE, - dn_cache_getroute, dn_fib_dump, 0); -#else - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETROUTE, - dn_cache_getroute, dn_cache_dump, 0); -#endif -} - -void __exit dn_route_cleanup(void) -{ - del_timer(&dn_route_timer); - dn_run_flush(NULL); - - remove_proc_entry("decnet_cache", init_net.proc_net); - dst_entries_destroy(&dn_dst_ops); -} diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c deleted file mode 100644 index 4a4e3c17740c..000000000000 --- a/net/decnet/dn_rules.c +++ /dev/null @@ -1,258 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Forwarding Information Base (Rules) - * - * Author: Steve Whitehouse - * Mostly copied from Alexey Kuznetsov's ipv4/fib_rules.c - * - * - * Changes: - * Steve Whitehouse - * Updated for Thomas Graf's generic rules - * - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static struct fib_rules_ops *dn_fib_rules_ops; - -struct dn_fib_rule -{ - struct fib_rule common; - unsigned char dst_len; - unsigned char src_len; - __le16 src; - __le16 srcmask; - __le16 dst; - __le16 dstmask; - __le16 srcmap; - u8 flags; -}; - - -int dn_fib_lookup(struct flowidn *flp, struct dn_fib_res *res) -{ - struct fib_lookup_arg arg = { - .result = res, - }; - int err; - - err = fib_rules_lookup(dn_fib_rules_ops, - flowidn_to_flowi(flp), 0, &arg); - res->r = arg.rule; - - return err; -} - -static int dn_fib_rule_action(struct fib_rule *rule, struct flowi *flp, - int flags, struct fib_lookup_arg *arg) -{ - struct flowidn *fld = &flp->u.dn; - int err = -EAGAIN; - struct dn_fib_table *tbl; - - switch(rule->action) { - case FR_ACT_TO_TBL: - break; - - case FR_ACT_UNREACHABLE: - err = -ENETUNREACH; - goto errout; - - case FR_ACT_PROHIBIT: - err = -EACCES; - goto errout; - - case FR_ACT_BLACKHOLE: - default: - err = -EINVAL; - goto errout; - } - - tbl = dn_fib_get_table(rule->table, 0); - if (tbl == NULL) - goto errout; - - err = tbl->lookup(tbl, fld, (struct dn_fib_res *)arg->result); - if (err > 0) - err = -EAGAIN; -errout: - return err; -} - -static const struct nla_policy dn_fib_rule_policy[FRA_MAX+1] = { - FRA_GENERIC_POLICY, -}; - -static int dn_fib_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) -{ - struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - struct flowidn *fld = &fl->u.dn; - __le16 daddr = fld->daddr; - __le16 saddr = fld->saddr; - - if (((saddr ^ r->src) & r->srcmask) || - ((daddr ^ r->dst) & r->dstmask)) - return 0; - - return 1; -} - -static int dn_fib_rule_configure(struct fib_rule *rule, struct sk_buff *skb, - struct fib_rule_hdr *frh, - struct nlattr **tb, - struct netlink_ext_ack *extack) -{ - int err = -EINVAL; - struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - - if (frh->tos) { - NL_SET_ERR_MSG(extack, "Invalid tos value"); - goto errout; - } - - if (rule->table == RT_TABLE_UNSPEC) { - if (rule->action == FR_ACT_TO_TBL) { - struct dn_fib_table *table; - - table = dn_fib_empty_table(); - if (table == NULL) { - err = -ENOBUFS; - goto errout; - } - - rule->table = table->n; - } - } - - if (frh->src_len) - r->src = nla_get_le16(tb[FRA_SRC]); - - if (frh->dst_len) - r->dst = nla_get_le16(tb[FRA_DST]); - - r->src_len = frh->src_len; - r->srcmask = dnet_make_mask(r->src_len); - r->dst_len = frh->dst_len; - r->dstmask = dnet_make_mask(r->dst_len); - err = 0; -errout: - return err; -} - -static int dn_fib_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, - struct nlattr **tb) -{ - struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - - if (frh->src_len && (r->src_len != frh->src_len)) - return 0; - - if (frh->dst_len && (r->dst_len != frh->dst_len)) - return 0; - - if (frh->src_len && (r->src != nla_get_le16(tb[FRA_SRC]))) - return 0; - - if (frh->dst_len && (r->dst != nla_get_le16(tb[FRA_DST]))) - return 0; - - return 1; -} - -unsigned int dnet_addr_type(__le16 addr) -{ - struct flowidn fld = { .daddr = addr }; - struct dn_fib_res res; - unsigned int ret = RTN_UNICAST; - struct dn_fib_table *tb = dn_fib_get_table(RT_TABLE_LOCAL, 0); - - res.r = NULL; - - if (tb) { - if (!tb->lookup(tb, &fld, &res)) { - ret = res.type; - dn_fib_res_put(&res); - } - } - return ret; -} - -static int dn_fib_rule_fill(struct fib_rule *rule, struct sk_buff *skb, - struct fib_rule_hdr *frh) -{ - struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - - frh->dst_len = r->dst_len; - frh->src_len = r->src_len; - frh->tos = 0; - - if ((r->dst_len && - nla_put_le16(skb, FRA_DST, r->dst)) || - (r->src_len && - nla_put_le16(skb, FRA_SRC, r->src))) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -ENOBUFS; -} - -static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops) -{ - dn_rt_cache_flush(-1); -} - -static const struct fib_rules_ops __net_initconst dn_fib_rules_ops_template = { - .family = AF_DECnet, - .rule_size = sizeof(struct dn_fib_rule), - .addr_size = sizeof(u16), - .action = dn_fib_rule_action, - .match = dn_fib_rule_match, - .configure = dn_fib_rule_configure, - .compare = dn_fib_rule_compare, - .fill = dn_fib_rule_fill, - .flush_cache = dn_fib_rule_flush_cache, - .nlgroup = RTNLGRP_DECnet_RULE, - .policy = dn_fib_rule_policy, - .owner = THIS_MODULE, - .fro_net = &init_net, -}; - -void __init dn_fib_rules_init(void) -{ - dn_fib_rules_ops = - fib_rules_register(&dn_fib_rules_ops_template, &init_net); - BUG_ON(IS_ERR(dn_fib_rules_ops)); - BUG_ON(fib_default_rule_add(dn_fib_rules_ops, 0x7fff, - RT_TABLE_MAIN, 0)); -} - -void __exit dn_fib_rules_cleanup(void) -{ - rtnl_lock(); - fib_rules_unregister(dn_fib_rules_ops); - rtnl_unlock(); - rcu_barrier(); -} diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c deleted file mode 100644 index 4086f9c746af..000000000000 --- a/net/decnet/dn_table.c +++ /dev/null @@ -1,929 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Forwarding Information Base (Routing Tables) - * - * Author: Steve Whitehouse - * Mostly copied from the IPv4 routing code - * - * - * Changes: - * - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include /* RTF_xxx */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -struct dn_zone -{ - struct dn_zone *dz_next; - struct dn_fib_node **dz_hash; - int dz_nent; - int dz_divisor; - u32 dz_hashmask; -#define DZ_HASHMASK(dz) ((dz)->dz_hashmask) - int dz_order; - __le16 dz_mask; -#define DZ_MASK(dz) ((dz)->dz_mask) -}; - -struct dn_hash -{ - struct dn_zone *dh_zones[17]; - struct dn_zone *dh_zone_list; -}; - -#define dz_key_0(key) ((key).datum = 0) - -#define for_nexthops(fi) { int nhsel; const struct dn_fib_nh *nh;\ - for(nhsel = 0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) - -#define endfor_nexthops(fi) } - -#define DN_MAX_DIVISOR 1024 -#define DN_S_ZOMBIE 1 -#define DN_S_ACCESSED 2 - -#define DN_FIB_SCAN(f, fp) \ -for( ; ((f) = *(fp)) != NULL; (fp) = &(f)->fn_next) - -#define DN_FIB_SCAN_KEY(f, fp, key) \ -for( ; ((f) = *(fp)) != NULL && dn_key_eq((f)->fn_key, (key)); (fp) = &(f)->fn_next) - -#define RT_TABLE_MIN 1 -#define DN_FIB_TABLE_HASHSZ 256 -static struct hlist_head dn_fib_table_hash[DN_FIB_TABLE_HASHSZ]; -static DEFINE_RWLOCK(dn_fib_tables_lock); - -static struct kmem_cache *dn_hash_kmem __read_mostly; -static int dn_fib_hash_zombies; - -static inline dn_fib_idx_t dn_hash(dn_fib_key_t key, struct dn_zone *dz) -{ - u16 h = le16_to_cpu(key.datum)>>(16 - dz->dz_order); - h ^= (h >> 10); - h ^= (h >> 6); - h &= DZ_HASHMASK(dz); - return *(dn_fib_idx_t *)&h; -} - -static inline dn_fib_key_t dz_key(__le16 dst, struct dn_zone *dz) -{ - dn_fib_key_t k; - k.datum = dst & DZ_MASK(dz); - return k; -} - -static inline struct dn_fib_node **dn_chain_p(dn_fib_key_t key, struct dn_zone *dz) -{ - return &dz->dz_hash[dn_hash(key, dz).datum]; -} - -static inline struct dn_fib_node *dz_chain(dn_fib_key_t key, struct dn_zone *dz) -{ - return dz->dz_hash[dn_hash(key, dz).datum]; -} - -static inline int dn_key_eq(dn_fib_key_t a, dn_fib_key_t b) -{ - return a.datum == b.datum; -} - -static inline int dn_key_leq(dn_fib_key_t a, dn_fib_key_t b) -{ - return a.datum <= b.datum; -} - -static inline void dn_rebuild_zone(struct dn_zone *dz, - struct dn_fib_node **old_ht, - int old_divisor) -{ - struct dn_fib_node *f, **fp, *next; - int i; - - for(i = 0; i < old_divisor; i++) { - for(f = old_ht[i]; f; f = next) { - next = f->fn_next; - for(fp = dn_chain_p(f->fn_key, dz); - *fp && dn_key_leq((*fp)->fn_key, f->fn_key); - fp = &(*fp)->fn_next) - /* NOTHING */; - f->fn_next = *fp; - *fp = f; - } - } -} - -static void dn_rehash_zone(struct dn_zone *dz) -{ - struct dn_fib_node **ht, **old_ht; - int old_divisor, new_divisor; - u32 new_hashmask; - - old_divisor = dz->dz_divisor; - - switch (old_divisor) { - case 16: - new_divisor = 256; - new_hashmask = 0xFF; - break; - default: - printk(KERN_DEBUG "DECnet: dn_rehash_zone: BUG! %d\n", - old_divisor); - fallthrough; - case 256: - new_divisor = 1024; - new_hashmask = 0x3FF; - break; - } - - ht = kcalloc(new_divisor, sizeof(struct dn_fib_node*), GFP_KERNEL); - if (ht == NULL) - return; - - write_lock_bh(&dn_fib_tables_lock); - old_ht = dz->dz_hash; - dz->dz_hash = ht; - dz->dz_hashmask = new_hashmask; - dz->dz_divisor = new_divisor; - dn_rebuild_zone(dz, old_ht, old_divisor); - write_unlock_bh(&dn_fib_tables_lock); - kfree(old_ht); -} - -static void dn_free_node(struct dn_fib_node *f) -{ - dn_fib_release_info(DN_FIB_INFO(f)); - kmem_cache_free(dn_hash_kmem, f); -} - - -static struct dn_zone *dn_new_zone(struct dn_hash *table, int z) -{ - int i; - struct dn_zone *dz = kzalloc(sizeof(struct dn_zone), GFP_KERNEL); - if (!dz) - return NULL; - - if (z) { - dz->dz_divisor = 16; - dz->dz_hashmask = 0x0F; - } else { - dz->dz_divisor = 1; - dz->dz_hashmask = 0; - } - - dz->dz_hash = kcalloc(dz->dz_divisor, sizeof(struct dn_fib_node *), GFP_KERNEL); - if (!dz->dz_hash) { - kfree(dz); - return NULL; - } - - dz->dz_order = z; - dz->dz_mask = dnet_make_mask(z); - - for(i = z + 1; i <= 16; i++) - if (table->dh_zones[i]) - break; - - write_lock_bh(&dn_fib_tables_lock); - if (i>16) { - dz->dz_next = table->dh_zone_list; - table->dh_zone_list = dz; - } else { - dz->dz_next = table->dh_zones[i]->dz_next; - table->dh_zones[i]->dz_next = dz; - } - table->dh_zones[z] = dz; - write_unlock_bh(&dn_fib_tables_lock); - return dz; -} - - -static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct nlattr *attrs[], struct dn_fib_info *fi) -{ - struct rtnexthop *nhp; - int nhlen; - - if (attrs[RTA_PRIORITY] && - nla_get_u32(attrs[RTA_PRIORITY]) != fi->fib_priority) - return 1; - - if (attrs[RTA_OIF] || attrs[RTA_GATEWAY]) { - if ((!attrs[RTA_OIF] || nla_get_u32(attrs[RTA_OIF]) == fi->fib_nh->nh_oif) && - (!attrs[RTA_GATEWAY] || nla_get_le16(attrs[RTA_GATEWAY]) != fi->fib_nh->nh_gw)) - return 0; - return 1; - } - - if (!attrs[RTA_MULTIPATH]) - return 0; - - nhp = nla_data(attrs[RTA_MULTIPATH]); - nhlen = nla_len(attrs[RTA_MULTIPATH]); - - for_nexthops(fi) { - int attrlen = nhlen - sizeof(struct rtnexthop); - __le16 gw; - - if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0) - return -EINVAL; - if (nhp->rtnh_ifindex && nhp->rtnh_ifindex != nh->nh_oif) - return 1; - if (attrlen) { - struct nlattr *gw_attr; - - gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY); - gw = gw_attr ? nla_get_le16(gw_attr) : 0; - - if (gw && gw != nh->nh_gw) - return 1; - } - nhp = RTNH_NEXT(nhp); - } endfor_nexthops(fi); - - return 0; -} - -static inline size_t dn_fib_nlmsg_size(struct dn_fib_info *fi) -{ - size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) - + nla_total_size(4) /* RTA_TABLE */ - + nla_total_size(2) /* RTA_DST */ - + nla_total_size(4) /* RTA_PRIORITY */ - + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */ - - /* space for nested metrics */ - payload += nla_total_size((RTAX_MAX * nla_total_size(4))); - - if (fi->fib_nhs) { - /* Also handles the special case fib_nhs == 1 */ - - /* each nexthop is packed in an attribute */ - size_t nhsize = nla_total_size(sizeof(struct rtnexthop)); - - /* may contain a gateway attribute */ - nhsize += nla_total_size(4); - - /* all nexthops are packed in a nested attribute */ - payload += nla_total_size(fi->fib_nhs * nhsize); - } - - return payload; -} - -static int dn_fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, - u32 tb_id, u8 type, u8 scope, void *dst, int dst_len, - struct dn_fib_info *fi, unsigned int flags) -{ - struct rtmsg *rtm; - struct nlmsghdr *nlh; - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); - if (!nlh) - return -EMSGSIZE; - - rtm = nlmsg_data(nlh); - rtm->rtm_family = AF_DECnet; - rtm->rtm_dst_len = dst_len; - rtm->rtm_src_len = 0; - rtm->rtm_tos = 0; - rtm->rtm_table = tb_id; - rtm->rtm_flags = fi->fib_flags; - rtm->rtm_scope = scope; - rtm->rtm_type = type; - rtm->rtm_protocol = fi->fib_protocol; - - if (nla_put_u32(skb, RTA_TABLE, tb_id) < 0) - goto errout; - - if (rtm->rtm_dst_len && - nla_put(skb, RTA_DST, 2, dst) < 0) - goto errout; - - if (fi->fib_priority && - nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority) < 0) - goto errout; - - if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) - goto errout; - - if (fi->fib_nhs == 1) { - if (fi->fib_nh->nh_gw && - nla_put_le16(skb, RTA_GATEWAY, fi->fib_nh->nh_gw) < 0) - goto errout; - - if (fi->fib_nh->nh_oif && - nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif) < 0) - goto errout; - } - - if (fi->fib_nhs > 1) { - struct rtnexthop *nhp; - struct nlattr *mp_head; - - mp_head = nla_nest_start_noflag(skb, RTA_MULTIPATH); - if (!mp_head) - goto errout; - - for_nexthops(fi) { - if (!(nhp = nla_reserve_nohdr(skb, sizeof(*nhp)))) - goto errout; - - nhp->rtnh_flags = nh->nh_flags & 0xFF; - nhp->rtnh_hops = nh->nh_weight - 1; - nhp->rtnh_ifindex = nh->nh_oif; - - if (nh->nh_gw && - nla_put_le16(skb, RTA_GATEWAY, nh->nh_gw) < 0) - goto errout; - - nhp->rtnh_len = skb_tail_pointer(skb) - (unsigned char *)nhp; - } endfor_nexthops(fi); - - nla_nest_end(skb, mp_head); - } - - nlmsg_end(skb, nlh); - return 0; - -errout: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; -} - - -static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, u32 tb_id, - struct nlmsghdr *nlh, struct netlink_skb_parms *req) -{ - struct sk_buff *skb; - u32 portid = req ? req->portid : 0; - int err = -ENOBUFS; - - skb = nlmsg_new(dn_fib_nlmsg_size(DN_FIB_INFO(f)), GFP_KERNEL); - if (skb == NULL) - goto errout; - - err = dn_fib_dump_info(skb, portid, nlh->nlmsg_seq, event, tb_id, - f->fn_type, f->fn_scope, &f->fn_key, z, - DN_FIB_INFO(f), 0); - if (err < 0) { - /* -EMSGSIZE implies BUG in dn_fib_nlmsg_size() */ - WARN_ON(err == -EMSGSIZE); - kfree_skb(skb); - goto errout; - } - rtnl_notify(skb, &init_net, portid, RTNLGRP_DECnet_ROUTE, nlh, GFP_KERNEL); - return; -errout: - if (err < 0) - rtnl_set_sk_err(&init_net, RTNLGRP_DECnet_ROUTE, err); -} - -static __inline__ int dn_hash_dump_bucket(struct sk_buff *skb, - struct netlink_callback *cb, - struct dn_fib_table *tb, - struct dn_zone *dz, - struct dn_fib_node *f) -{ - int i, s_i; - - s_i = cb->args[4]; - for(i = 0; f; i++, f = f->fn_next) { - if (i < s_i) - continue; - if (f->fn_state & DN_S_ZOMBIE) - continue; - if (dn_fib_dump_info(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWROUTE, - tb->n, - (f->fn_state & DN_S_ZOMBIE) ? 0 : f->fn_type, - f->fn_scope, &f->fn_key, dz->dz_order, - f->fn_info, NLM_F_MULTI) < 0) { - cb->args[4] = i; - return -1; - } - } - cb->args[4] = i; - return skb->len; -} - -static __inline__ int dn_hash_dump_zone(struct sk_buff *skb, - struct netlink_callback *cb, - struct dn_fib_table *tb, - struct dn_zone *dz) -{ - int h, s_h; - - s_h = cb->args[3]; - for(h = 0; h < dz->dz_divisor; h++) { - if (h < s_h) - continue; - if (h > s_h) - memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0])); - if (dz->dz_hash == NULL || dz->dz_hash[h] == NULL) - continue; - if (dn_hash_dump_bucket(skb, cb, tb, dz, dz->dz_hash[h]) < 0) { - cb->args[3] = h; - return -1; - } - } - cb->args[3] = h; - return skb->len; -} - -static int dn_fib_table_dump(struct dn_fib_table *tb, struct sk_buff *skb, - struct netlink_callback *cb) -{ - int m, s_m; - struct dn_zone *dz; - struct dn_hash *table = (struct dn_hash *)tb->data; - - s_m = cb->args[2]; - read_lock(&dn_fib_tables_lock); - for(dz = table->dh_zone_list, m = 0; dz; dz = dz->dz_next, m++) { - if (m < s_m) - continue; - if (m > s_m) - memset(&cb->args[3], 0, sizeof(cb->args) - 3*sizeof(cb->args[0])); - - if (dn_hash_dump_zone(skb, cb, tb, dz) < 0) { - cb->args[2] = m; - read_unlock(&dn_fib_tables_lock); - return -1; - } - } - read_unlock(&dn_fib_tables_lock); - cb->args[2] = m; - - return skb->len; -} - -int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - unsigned int h, s_h; - unsigned int e = 0, s_e; - struct dn_fib_table *tb; - int dumped = 0; - - if (!net_eq(net, &init_net)) - return 0; - - if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && - ((struct rtmsg *)nlmsg_data(cb->nlh))->rtm_flags&RTM_F_CLONED) - return dn_cache_dump(skb, cb); - - s_h = cb->args[0]; - s_e = cb->args[1]; - - for (h = s_h; h < DN_FIB_TABLE_HASHSZ; h++, s_h = 0) { - e = 0; - hlist_for_each_entry(tb, &dn_fib_table_hash[h], hlist) { - if (e < s_e) - goto next; - if (dumped) - memset(&cb->args[2], 0, sizeof(cb->args) - - 2 * sizeof(cb->args[0])); - if (tb->dump(tb, skb, cb) < 0) - goto out; - dumped = 1; -next: - e++; - } - } -out: - cb->args[1] = e; - cb->args[0] = h; - - return skb->len; -} - -static int dn_fib_table_insert(struct dn_fib_table *tb, struct rtmsg *r, struct nlattr *attrs[], - struct nlmsghdr *n, struct netlink_skb_parms *req) -{ - struct dn_hash *table = (struct dn_hash *)tb->data; - struct dn_fib_node *new_f, *f, **fp, **del_fp; - struct dn_zone *dz; - struct dn_fib_info *fi; - int z = r->rtm_dst_len; - int type = r->rtm_type; - dn_fib_key_t key; - int err; - - if (z > 16) - return -EINVAL; - - dz = table->dh_zones[z]; - if (!dz && !(dz = dn_new_zone(table, z))) - return -ENOBUFS; - - dz_key_0(key); - if (attrs[RTA_DST]) { - __le16 dst = nla_get_le16(attrs[RTA_DST]); - if (dst & ~DZ_MASK(dz)) - return -EINVAL; - key = dz_key(dst, dz); - } - - if ((fi = dn_fib_create_info(r, attrs, n, &err)) == NULL) - return err; - - if (dz->dz_nent > (dz->dz_divisor << 2) && - dz->dz_divisor > DN_MAX_DIVISOR && - (z==16 || (1< dz->dz_divisor)) - dn_rehash_zone(dz); - - fp = dn_chain_p(key, dz); - - DN_FIB_SCAN(f, fp) { - if (dn_key_leq(key, f->fn_key)) - break; - } - - del_fp = NULL; - - if (f && (f->fn_state & DN_S_ZOMBIE) && - dn_key_eq(f->fn_key, key)) { - del_fp = fp; - fp = &f->fn_next; - f = *fp; - goto create; - } - - DN_FIB_SCAN_KEY(f, fp, key) { - if (fi->fib_priority <= DN_FIB_INFO(f)->fib_priority) - break; - } - - if (f && dn_key_eq(f->fn_key, key) && - fi->fib_priority == DN_FIB_INFO(f)->fib_priority) { - struct dn_fib_node **ins_fp; - - err = -EEXIST; - if (n->nlmsg_flags & NLM_F_EXCL) - goto out; - - if (n->nlmsg_flags & NLM_F_REPLACE) { - del_fp = fp; - fp = &f->fn_next; - f = *fp; - goto replace; - } - - ins_fp = fp; - err = -EEXIST; - - DN_FIB_SCAN_KEY(f, fp, key) { - if (fi->fib_priority != DN_FIB_INFO(f)->fib_priority) - break; - if (f->fn_type == type && - f->fn_scope == r->rtm_scope && - DN_FIB_INFO(f) == fi) - goto out; - } - - if (!(n->nlmsg_flags & NLM_F_APPEND)) { - fp = ins_fp; - f = *fp; - } - } - -create: - err = -ENOENT; - if (!(n->nlmsg_flags & NLM_F_CREATE)) - goto out; - -replace: - err = -ENOBUFS; - new_f = kmem_cache_zalloc(dn_hash_kmem, GFP_KERNEL); - if (new_f == NULL) - goto out; - - new_f->fn_key = key; - new_f->fn_type = type; - new_f->fn_scope = r->rtm_scope; - DN_FIB_INFO(new_f) = fi; - - new_f->fn_next = f; - write_lock_bh(&dn_fib_tables_lock); - *fp = new_f; - write_unlock_bh(&dn_fib_tables_lock); - dz->dz_nent++; - - if (del_fp) { - f = *del_fp; - write_lock_bh(&dn_fib_tables_lock); - *del_fp = f->fn_next; - write_unlock_bh(&dn_fib_tables_lock); - - if (!(f->fn_state & DN_S_ZOMBIE)) - dn_rtmsg_fib(RTM_DELROUTE, f, z, tb->n, n, req); - if (f->fn_state & DN_S_ACCESSED) - dn_rt_cache_flush(-1); - dn_free_node(f); - dz->dz_nent--; - } else { - dn_rt_cache_flush(-1); - } - - dn_rtmsg_fib(RTM_NEWROUTE, new_f, z, tb->n, n, req); - - return 0; -out: - dn_fib_release_info(fi); - return err; -} - - -static int dn_fib_table_delete(struct dn_fib_table *tb, struct rtmsg *r, struct nlattr *attrs[], - struct nlmsghdr *n, struct netlink_skb_parms *req) -{ - struct dn_hash *table = (struct dn_hash*)tb->data; - struct dn_fib_node **fp, **del_fp, *f; - int z = r->rtm_dst_len; - struct dn_zone *dz; - dn_fib_key_t key; - int matched; - - - if (z > 16) - return -EINVAL; - - if ((dz = table->dh_zones[z]) == NULL) - return -ESRCH; - - dz_key_0(key); - if (attrs[RTA_DST]) { - __le16 dst = nla_get_le16(attrs[RTA_DST]); - if (dst & ~DZ_MASK(dz)) - return -EINVAL; - key = dz_key(dst, dz); - } - - fp = dn_chain_p(key, dz); - - DN_FIB_SCAN(f, fp) { - if (dn_key_eq(f->fn_key, key)) - break; - if (dn_key_leq(key, f->fn_key)) - return -ESRCH; - } - - matched = 0; - del_fp = NULL; - DN_FIB_SCAN_KEY(f, fp, key) { - struct dn_fib_info *fi = DN_FIB_INFO(f); - - if (f->fn_state & DN_S_ZOMBIE) - return -ESRCH; - - matched++; - - if (del_fp == NULL && - (!r->rtm_type || f->fn_type == r->rtm_type) && - (r->rtm_scope == RT_SCOPE_NOWHERE || f->fn_scope == r->rtm_scope) && - (!r->rtm_protocol || - fi->fib_protocol == r->rtm_protocol) && - dn_fib_nh_match(r, n, attrs, fi) == 0) - del_fp = fp; - } - - if (del_fp) { - f = *del_fp; - dn_rtmsg_fib(RTM_DELROUTE, f, z, tb->n, n, req); - - if (matched != 1) { - write_lock_bh(&dn_fib_tables_lock); - *del_fp = f->fn_next; - write_unlock_bh(&dn_fib_tables_lock); - - if (f->fn_state & DN_S_ACCESSED) - dn_rt_cache_flush(-1); - dn_free_node(f); - dz->dz_nent--; - } else { - f->fn_state |= DN_S_ZOMBIE; - if (f->fn_state & DN_S_ACCESSED) { - f->fn_state &= ~DN_S_ACCESSED; - dn_rt_cache_flush(-1); - } - if (++dn_fib_hash_zombies > 128) - dn_fib_flush(); - } - - return 0; - } - - return -ESRCH; -} - -static inline int dn_flush_list(struct dn_fib_node **fp, int z, struct dn_hash *table) -{ - int found = 0; - struct dn_fib_node *f; - - while((f = *fp) != NULL) { - struct dn_fib_info *fi = DN_FIB_INFO(f); - - if (fi && ((f->fn_state & DN_S_ZOMBIE) || (fi->fib_flags & RTNH_F_DEAD))) { - write_lock_bh(&dn_fib_tables_lock); - *fp = f->fn_next; - write_unlock_bh(&dn_fib_tables_lock); - - dn_free_node(f); - found++; - continue; - } - fp = &f->fn_next; - } - - return found; -} - -static int dn_fib_table_flush(struct dn_fib_table *tb) -{ - struct dn_hash *table = (struct dn_hash *)tb->data; - struct dn_zone *dz; - int found = 0; - - dn_fib_hash_zombies = 0; - for(dz = table->dh_zone_list; dz; dz = dz->dz_next) { - int i; - int tmp = 0; - for(i = dz->dz_divisor-1; i >= 0; i--) - tmp += dn_flush_list(&dz->dz_hash[i], dz->dz_order, table); - dz->dz_nent -= tmp; - found += tmp; - } - - return found; -} - -static int dn_fib_table_lookup(struct dn_fib_table *tb, const struct flowidn *flp, struct dn_fib_res *res) -{ - int err; - struct dn_zone *dz; - struct dn_hash *t = (struct dn_hash *)tb->data; - - read_lock(&dn_fib_tables_lock); - for(dz = t->dh_zone_list; dz; dz = dz->dz_next) { - struct dn_fib_node *f; - dn_fib_key_t k = dz_key(flp->daddr, dz); - - for(f = dz_chain(k, dz); f; f = f->fn_next) { - if (!dn_key_eq(k, f->fn_key)) { - if (dn_key_leq(k, f->fn_key)) - break; - else - continue; - } - - f->fn_state |= DN_S_ACCESSED; - - if (f->fn_state&DN_S_ZOMBIE) - continue; - - if (f->fn_scope < flp->flowidn_scope) - continue; - - err = dn_fib_semantic_match(f->fn_type, DN_FIB_INFO(f), flp, res); - - if (err == 0) { - res->type = f->fn_type; - res->scope = f->fn_scope; - res->prefixlen = dz->dz_order; - goto out; - } - if (err < 0) - goto out; - } - } - err = 1; -out: - read_unlock(&dn_fib_tables_lock); - return err; -} - - -struct dn_fib_table *dn_fib_get_table(u32 n, int create) -{ - struct dn_fib_table *t; - unsigned int h; - - if (n < RT_TABLE_MIN) - return NULL; - - if (n > RT_TABLE_MAX) - return NULL; - - h = n & (DN_FIB_TABLE_HASHSZ - 1); - rcu_read_lock(); - hlist_for_each_entry_rcu(t, &dn_fib_table_hash[h], hlist) { - if (t->n == n) { - rcu_read_unlock(); - return t; - } - } - rcu_read_unlock(); - - if (!create) - return NULL; - - if (in_interrupt()) { - net_dbg_ratelimited("DECnet: BUG! Attempt to create routing table from interrupt\n"); - return NULL; - } - - t = kzalloc(sizeof(struct dn_fib_table) + sizeof(struct dn_hash), - GFP_KERNEL); - if (t == NULL) - return NULL; - - t->n = n; - t->insert = dn_fib_table_insert; - t->delete = dn_fib_table_delete; - t->lookup = dn_fib_table_lookup; - t->flush = dn_fib_table_flush; - t->dump = dn_fib_table_dump; - hlist_add_head_rcu(&t->hlist, &dn_fib_table_hash[h]); - - return t; -} - -struct dn_fib_table *dn_fib_empty_table(void) -{ - u32 id; - - for(id = RT_TABLE_MIN; id <= RT_TABLE_MAX; id++) - if (dn_fib_get_table(id, 0) == NULL) - return dn_fib_get_table(id, 1); - return NULL; -} - -void dn_fib_flush(void) -{ - int flushed = 0; - struct dn_fib_table *tb; - unsigned int h; - - for (h = 0; h < DN_FIB_TABLE_HASHSZ; h++) { - hlist_for_each_entry(tb, &dn_fib_table_hash[h], hlist) - flushed += tb->flush(tb); - } - - if (flushed) - dn_rt_cache_flush(-1); -} - -void __init dn_fib_table_init(void) -{ - dn_hash_kmem = kmem_cache_create("dn_fib_info_cache", - sizeof(struct dn_fib_info), - 0, SLAB_HWCACHE_ALIGN, - NULL); -} - -void __exit dn_fib_table_cleanup(void) -{ - struct dn_fib_table *t; - struct hlist_node *next; - unsigned int h; - - write_lock(&dn_fib_tables_lock); - for (h = 0; h < DN_FIB_TABLE_HASHSZ; h++) { - hlist_for_each_entry_safe(t, next, &dn_fib_table_hash[h], - hlist) { - hlist_del(&t->hlist); - kfree(t); - } - } - write_unlock(&dn_fib_tables_lock); -} diff --git a/net/decnet/dn_timer.c b/net/decnet/dn_timer.c deleted file mode 100644 index aa4155875ca8..000000000000 --- a/net/decnet/dn_timer.c +++ /dev/null @@ -1,104 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Socket Timer Functions - * - * Author: Steve Whitehouse - * - * - * Changes: - * Steve Whitehouse : Made keepalive timer part of the same - * timer idea. - * Steve Whitehouse : Added checks for sk->sock_readers - * David S. Miller : New socket locking - * Steve Whitehouse : Timer grabs socket ref. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * Slow timer is for everything else (n * 500mS) - */ - -#define SLOW_INTERVAL (HZ/2) - -static void dn_slow_timer(struct timer_list *t); - -void dn_start_slow_timer(struct sock *sk) -{ - timer_setup(&sk->sk_timer, dn_slow_timer, 0); - sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); -} - -void dn_stop_slow_timer(struct sock *sk) -{ - sk_stop_timer(sk, &sk->sk_timer); -} - -static void dn_slow_timer(struct timer_list *t) -{ - struct sock *sk = from_timer(sk, t, sk_timer); - struct dn_scp *scp = DN_SK(sk); - - bh_lock_sock(sk); - - if (sock_owned_by_user(sk)) { - sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 10); - goto out; - } - - /* - * The persist timer is the standard slow timer used for retransmits - * in both connection establishment and disconnection as well as - * in the RUN state. The different states are catered for by changing - * the function pointer in the socket. Setting the timer to a value - * of zero turns it off. We allow the persist_fxn to turn the - * timer off in a permant way by returning non-zero, so that - * timer based routines may remove sockets. This is why we have a - * sock_hold()/sock_put() around the timer to prevent the socket - * going away in the middle. - */ - if (scp->persist && scp->persist_fxn) { - if (scp->persist <= SLOW_INTERVAL) { - scp->persist = 0; - - if (scp->persist_fxn(sk)) - goto out; - } else { - scp->persist -= SLOW_INTERVAL; - } - } - - /* - * Check for keepalive timeout. After the other timer 'cos if - * the previous timer caused a retransmit, we don't need to - * do this. scp->stamp is the last time that we sent a packet. - * The keepalive function sends a link service packet to the - * other end. If it remains unacknowledged, the standard - * socket timers will eventually shut the socket down. Each - * time we do this, scp->stamp will be updated, thus - * we won't try and send another until scp->keepalive has passed - * since the last successful transmission. - */ - if (scp->keepalive && scp->keepalive_fxn && (scp->state == DN_RUN)) { - if (time_after_eq(jiffies, scp->stamp + scp->keepalive)) - scp->keepalive_fxn(sk); - } - - sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); -out: - bh_unlock_sock(sk); - sock_put(sk); -} diff --git a/net/decnet/netfilter/Kconfig b/net/decnet/netfilter/Kconfig deleted file mode 100644 index 14ec4ef95fab..000000000000 --- a/net/decnet/netfilter/Kconfig +++ /dev/null @@ -1,17 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# DECnet netfilter configuration -# - -menu "DECnet: Netfilter Configuration" - depends on DECNET && NETFILTER - depends on NETFILTER_ADVANCED - -config DECNET_NF_GRABULATOR - tristate "Routing message grabulator (for userland routing daemon)" - help - Enable this module if you want to use the userland DECnet routing - daemon. You will also need to enable routing support for DECnet - unless you just want to monitor routing messages from other nodes. - -endmenu diff --git a/net/decnet/netfilter/Makefile b/net/decnet/netfilter/Makefile deleted file mode 100644 index 429c84289d0f..000000000000 --- a/net/decnet/netfilter/Makefile +++ /dev/null @@ -1,6 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# Makefile for DECnet netfilter modules -# - -obj-$(CONFIG_DECNET_NF_GRABULATOR) += dn_rtmsg.o diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c deleted file mode 100644 index 26a9193df783..000000000000 --- a/net/decnet/netfilter/dn_rtmsg.c +++ /dev/null @@ -1,158 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Message Grabulator - * - * (C) 2000 ChyGwyn Limited - https://www.chygwyn.com/ - * - * Author: Steven Whitehouse - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -static struct sock *dnrmg = NULL; - - -static struct sk_buff *dnrmg_build_message(struct sk_buff *rt_skb, int *errp) -{ - struct sk_buff *skb = NULL; - size_t size; - sk_buff_data_t old_tail; - struct nlmsghdr *nlh; - unsigned char *ptr; - struct nf_dn_rtmsg *rtm; - - size = NLMSG_ALIGN(rt_skb->len) + - NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg)); - skb = nlmsg_new(size, GFP_ATOMIC); - if (!skb) { - *errp = -ENOMEM; - return NULL; - } - old_tail = skb->tail; - nlh = nlmsg_put(skb, 0, 0, 0, size, 0); - if (!nlh) { - kfree_skb(skb); - *errp = -ENOMEM; - return NULL; - } - rtm = (struct nf_dn_rtmsg *)nlmsg_data(nlh); - rtm->nfdn_ifindex = rt_skb->dev->ifindex; - ptr = NFDN_RTMSG(rtm); - skb_copy_from_linear_data(rt_skb, ptr, rt_skb->len); - nlh->nlmsg_len = skb->tail - old_tail; - return skb; -} - -static void dnrmg_send_peer(struct sk_buff *skb) -{ - struct sk_buff *skb2; - int status = 0; - int group = 0; - unsigned char flags = *skb->data; - - switch (flags & DN_RT_CNTL_MSK) { - case DN_RT_PKT_L1RT: - group = DNRNG_NLGRP_L1; - break; - case DN_RT_PKT_L2RT: - group = DNRNG_NLGRP_L2; - break; - default: - return; - } - - skb2 = dnrmg_build_message(skb, &status); - if (skb2 == NULL) - return; - NETLINK_CB(skb2).dst_group = group; - netlink_broadcast(dnrmg, skb2, 0, group, GFP_ATOMIC); -} - - -static unsigned int dnrmg_hook(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - dnrmg_send_peer(skb); - return NF_ACCEPT; -} - - -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err), NULL); return; } while (0) - -static inline void dnrmg_receive_user_skb(struct sk_buff *skb) -{ - struct nlmsghdr *nlh = nlmsg_hdr(skb); - - if (skb->len < sizeof(*nlh) || - nlh->nlmsg_len < sizeof(*nlh) || - skb->len < nlh->nlmsg_len) - return; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - RCV_SKB_FAIL(-EPERM); - - /* Eventually we might send routing messages too */ - - RCV_SKB_FAIL(-EINVAL); -} - -static const struct nf_hook_ops dnrmg_ops = { - .hook = dnrmg_hook, - .pf = NFPROTO_DECNET, - .hooknum = NF_DN_ROUTE, - .priority = NF_DN_PRI_DNRTMSG, -}; - -static int __init dn_rtmsg_init(void) -{ - int rv = 0; - struct netlink_kernel_cfg cfg = { - .groups = DNRNG_NLGRP_MAX, - .input = dnrmg_receive_user_skb, - }; - - dnrmg = netlink_kernel_create(&init_net, NETLINK_DNRTMSG, &cfg); - if (dnrmg == NULL) { - printk(KERN_ERR "dn_rtmsg: Cannot create netlink socket"); - return -ENOMEM; - } - - rv = nf_register_net_hook(&init_net, &dnrmg_ops); - if (rv) { - netlink_kernel_release(dnrmg); - } - - return rv; -} - -static void __exit dn_rtmsg_fini(void) -{ - nf_unregister_net_hook(&init_net, &dnrmg_ops); - netlink_kernel_release(dnrmg); -} - - -MODULE_DESCRIPTION("DECnet Routing Message Grabulator"); -MODULE_AUTHOR("Steven Whitehouse "); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_DNRTMSG); - -module_init(dn_rtmsg_init); -module_exit(dn_rtmsg_fini); diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c deleted file mode 100644 index 67b5ab2657b7..000000000000 --- a/net/decnet/sysctl_net_decnet.c +++ /dev/null @@ -1,362 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet sysctl support functions - * - * Author: Steve Whitehouse - * - * - * Changes: - * Steve Whitehouse - C99 changes and default device handling - * Steve Whitehouse - Memory buffer settings, like the tcp ones - * - */ -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -#include -#include -#include - - -int decnet_debug_level; -int decnet_time_wait = 30; -int decnet_dn_count = 1; -int decnet_di_count = 3; -int decnet_dr_count = 3; -int decnet_log_martians = 1; -int decnet_no_fc_max_cwnd = NSP_MIN_WINDOW; - -/* Reasonable defaults, I hope, based on tcp's defaults */ -long sysctl_decnet_mem[3] = { 768 << 3, 1024 << 3, 1536 << 3 }; -int sysctl_decnet_wmem[3] = { 4 * 1024, 16 * 1024, 128 * 1024 }; -int sysctl_decnet_rmem[3] = { 4 * 1024, 87380, 87380 * 2 }; - -#ifdef CONFIG_SYSCTL -extern int decnet_dst_gc_interval; -static int min_decnet_time_wait[] = { 5 }; -static int max_decnet_time_wait[] = { 600 }; -static int min_state_count[] = { 1 }; -static int max_state_count[] = { NSP_MAXRXTSHIFT }; -static int min_decnet_dst_gc_interval[] = { 1 }; -static int max_decnet_dst_gc_interval[] = { 60 }; -static int min_decnet_no_fc_max_cwnd[] = { NSP_MIN_WINDOW }; -static int max_decnet_no_fc_max_cwnd[] = { NSP_MAX_WINDOW }; -static char node_name[7] = "???"; - -static struct ctl_table_header *dn_table_header = NULL; - -/* - * ctype.h :-) - */ -#define ISNUM(x) (((x) >= '0') && ((x) <= '9')) -#define ISLOWER(x) (((x) >= 'a') && ((x) <= 'z')) -#define ISUPPER(x) (((x) >= 'A') && ((x) <= 'Z')) -#define ISALPHA(x) (ISLOWER(x) || ISUPPER(x)) -#define INVALID_END_CHAR(x) (ISNUM(x) || ISALPHA(x)) - -static void strip_it(char *str) -{ - for(;;) { - switch (*str) { - case ' ': - case '\n': - case '\r': - case ':': - *str = 0; - fallthrough; - case 0: - return; - } - str++; - } -} - -/* - * Simple routine to parse an ascii DECnet address - * into a network order address. - */ -static int parse_addr(__le16 *addr, char *str) -{ - __u16 area, node; - - while(*str && !ISNUM(*str)) str++; - - if (*str == 0) - return -1; - - area = (*str++ - '0'); - if (ISNUM(*str)) { - area *= 10; - area += (*str++ - '0'); - } - - if (*str++ != '.') - return -1; - - if (!ISNUM(*str)) - return -1; - - node = *str++ - '0'; - if (ISNUM(*str)) { - node *= 10; - node += (*str++ - '0'); - } - if (ISNUM(*str)) { - node *= 10; - node += (*str++ - '0'); - } - if (ISNUM(*str)) { - node *= 10; - node += (*str++ - '0'); - } - - if ((node > 1023) || (area > 63)) - return -1; - - if (INVALID_END_CHAR(*str)) - return -1; - - *addr = cpu_to_le16((area << 10) | node); - - return 0; -} - -static int dn_node_address_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - char addr[DN_ASCBUF_LEN]; - size_t len; - __le16 dnaddr; - - if (!*lenp || (*ppos && !write)) { - *lenp = 0; - return 0; - } - - if (write) { - len = (*lenp < DN_ASCBUF_LEN) ? *lenp : (DN_ASCBUF_LEN-1); - memcpy(addr, buffer, len); - addr[len] = 0; - strip_it(addr); - - if (parse_addr(&dnaddr, addr)) - return -EINVAL; - - dn_dev_devices_off(); - - decnet_address = dnaddr; - - dn_dev_devices_on(); - - *ppos += len; - - return 0; - } - - dn_addr2asc(le16_to_cpu(decnet_address), addr); - len = strlen(addr); - addr[len++] = '\n'; - - if (len > *lenp) - len = *lenp; - memcpy(buffer, addr, len); - *lenp = len; - *ppos += len; - - return 0; -} - -static int dn_def_dev_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - size_t len; - struct net_device *dev; - char devname[17]; - - if (!*lenp || (*ppos && !write)) { - *lenp = 0; - return 0; - } - - if (write) { - if (*lenp > 16) - return -E2BIG; - - memcpy(devname, buffer, *lenp); - devname[*lenp] = 0; - strip_it(devname); - - dev = dev_get_by_name(&init_net, devname); - if (dev == NULL) - return -ENODEV; - - if (dev->dn_ptr == NULL) { - dev_put(dev); - return -ENODEV; - } - - if (dn_dev_set_default(dev, 1)) { - dev_put(dev); - return -ENODEV; - } - *ppos += *lenp; - - return 0; - } - - dev = dn_dev_get_default(); - if (dev == NULL) { - *lenp = 0; - return 0; - } - - strcpy(devname, dev->name); - dev_put(dev); - len = strlen(devname); - devname[len++] = '\n'; - - if (len > *lenp) len = *lenp; - - memcpy(buffer, devname, len); - *lenp = len; - *ppos += len; - - return 0; -} - -static struct ctl_table dn_table[] = { - { - .procname = "node_address", - .maxlen = 7, - .mode = 0644, - .proc_handler = dn_node_address_handler, - }, - { - .procname = "node_name", - .data = node_name, - .maxlen = 7, - .mode = 0644, - .proc_handler = proc_dostring, - }, - { - .procname = "default_device", - .maxlen = 16, - .mode = 0644, - .proc_handler = dn_def_dev_handler, - }, - { - .procname = "time_wait", - .data = &decnet_time_wait, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_decnet_time_wait, - .extra2 = &max_decnet_time_wait - }, - { - .procname = "dn_count", - .data = &decnet_dn_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_state_count, - .extra2 = &max_state_count - }, - { - .procname = "di_count", - .data = &decnet_di_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_state_count, - .extra2 = &max_state_count - }, - { - .procname = "dr_count", - .data = &decnet_dr_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_state_count, - .extra2 = &max_state_count - }, - { - .procname = "dst_gc_interval", - .data = &decnet_dst_gc_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_decnet_dst_gc_interval, - .extra2 = &max_decnet_dst_gc_interval - }, - { - .procname = "no_fc_max_cwnd", - .data = &decnet_no_fc_max_cwnd, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_decnet_no_fc_max_cwnd, - .extra2 = &max_decnet_no_fc_max_cwnd - }, - { - .procname = "decnet_mem", - .data = &sysctl_decnet_mem, - .maxlen = sizeof(sysctl_decnet_mem), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax - }, - { - .procname = "decnet_rmem", - .data = &sysctl_decnet_rmem, - .maxlen = sizeof(sysctl_decnet_rmem), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "decnet_wmem", - .data = &sysctl_decnet_wmem, - .maxlen = sizeof(sysctl_decnet_wmem), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "debug", - .data = &decnet_debug_level, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { } -}; - -void dn_register_sysctl(void) -{ - dn_table_header = register_net_sysctl(&init_net, "net/decnet", dn_table); -} - -void dn_unregister_sysctl(void) -{ - unregister_net_sysctl_table(dn_table_header); -} - -#else /* CONFIG_SYSCTL */ -void dn_unregister_sysctl(void) -{ -} -void dn_register_sysctl(void) -{ -} - -#endif diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 5b7578adbf0f..d0c7c396ba71 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -300,12 +300,6 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv6) <= hooknum)) return NULL; return net->nf.hooks_ipv6 + hooknum; -#if IS_ENABLED(CONFIG_DECNET) - case NFPROTO_DECNET: - if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_decnet) <= hooknum)) - return NULL; - return net->nf.hooks_decnet + hooknum; -#endif default: WARN_ON_ONCE(1); return NULL; @@ -724,10 +718,6 @@ static int __net_init netfilter_net_init(struct net *net) #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE __netfilter_net_init(net->nf.hooks_bridge, ARRAY_SIZE(net->nf.hooks_bridge)); #endif -#if IS_ENABLED(CONFIG_DECNET) - __netfilter_net_init(net->nf.hooks_decnet, ARRAY_SIZE(net->nf.hooks_decnet)); -#endif - #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); From 0b6e65016c3c56c8db0d79a560ed6f4bf9166349 Mon Sep 17 00:00:00 2001 From: Jerry Meng Date: Wed, 31 May 2023 11:51:16 +0800 Subject: [PATCH 3551/4345] USB: serial: option: add Quectel EM061KGL series commit f1832e2b5e498e258b090af3b065b85cf8cc5161 upstream. Add support for Quectel EM061KGL series which are based on Qualcomm SDX12 chip: EM061KGL_LTA(0x2c7c / 0x0123): MBIM + GNSS + DIAG + NMEA + AT + QDSS + DPL EM061KGL_LMS(0x2c7c / 0x0124): MBIM + GNSS + DIAG + NMEA + AT + QDSS + DPL EM061KGL_LWW(0x2c7c / 0x6008): MBIM + GNSS + DIAG + NMEA + AT + QDSS + DPL EM061KGL_LCN(0x2c7c / 0x6009): MBIM + GNSS + DIAG + NMEA + AT + QDSS + DPL Above products use the exact same interface layout and option driver is for interfaces DIAG, NMEA and AT. T: Bus=03 Lev=01 Prnt=01 Port=01 Cnt=02 Dev#= 5 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2c7c ProdID=6008 Rev= 5.04 S: Manufacturer=Quectel S: Product=Quectel EM061K-GL S: SerialNumber=f6fa08b6 C:* #Ifs= 8 Cfg#= 1 Atr=a0 MxPwr=500mA A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00 I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim E: Ad=81(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim E: Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=0f(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 2 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) E: Ad=82(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=40 Driver=option E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 6 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=70 Driver=(none) E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I:* If#= 7 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=80 Driver=(none) E: Ad=8f(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Jerry Meng Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 5b474efeab6a..243f97a30779 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -248,6 +248,8 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_VENDOR_ID 0x2c7c /* These Quectel products use Quectel's vendor ID */ #define QUECTEL_PRODUCT_EC21 0x0121 +#define QUECTEL_PRODUCT_EM061K_LTA 0x0123 +#define QUECTEL_PRODUCT_EM061K_LMS 0x0124 #define QUECTEL_PRODUCT_EC25 0x0125 #define QUECTEL_PRODUCT_EG91 0x0191 #define QUECTEL_PRODUCT_EG95 0x0195 @@ -266,6 +268,8 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_RM520N 0x0801 #define QUECTEL_PRODUCT_EC200U 0x0901 #define QUECTEL_PRODUCT_EC200S_CN 0x6002 +#define QUECTEL_PRODUCT_EM061K_LWW 0x6008 +#define QUECTEL_PRODUCT_EM061K_LCN 0x6009 #define QUECTEL_PRODUCT_EC200T 0x6026 #define QUECTEL_PRODUCT_RM500K 0x7001 @@ -1189,6 +1193,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LMS, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LMS, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LMS, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LTA, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LTA, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LTA, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LWW, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LWW, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LWW, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff), .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) }, From f4bc416942898bc789c4f05b306213164e0440bb Mon Sep 17 00:00:00 2001 From: Bernhard Seibold Date: Fri, 2 Jun 2023 15:30:29 +0200 Subject: [PATCH 3552/4345] serial: lantiq: add missing interrupt ack MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 306320034e8fbe7ee1cc4f5269c55658b4612048 upstream. Currently, the error interrupt is never acknowledged, so once active it will stay active indefinitely, causing the handler to be called in an infinite loop. Fixes: 2f0fc4159a6a ("SERIAL: Lantiq: Add driver for MIPS Lantiq SOCs.") Cc: Signed-off-by: Bernhard Seibold Reviewed-by: Ilpo Järvinen Message-ID: <20230602133029.546-1-mail@bernhard-seibold.de> Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/lantiq.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/lantiq.c b/drivers/tty/serial/lantiq.c index 62813e421f12..ee5fd4d845c8 100644 --- a/drivers/tty/serial/lantiq.c +++ b/drivers/tty/serial/lantiq.c @@ -274,6 +274,7 @@ lqasc_err_int(int irq, void *_port) struct ltq_uart_port *ltq_port = to_ltq_uart_port(port); spin_lock_irqsave(<q_port->lock, flags); + __raw_writel(ASC_IRNCR_EIR, port->membase + LTQ_ASC_IRNCR); /* clear any pending interrupts */ asc_update_bits(0, ASCWHBSTATE_CLRPE | ASCWHBSTATE_CLRFE | ASCWHBSTATE_CLRROE, port->membase + LTQ_ASC_WHBSTATE); From 26293251ab641f16ee7a4f9ded2e2504044979a8 Mon Sep 17 00:00:00 2001 From: Elson Roy Serrao Date: Thu, 1 Jun 2023 14:27:30 -0700 Subject: [PATCH 3553/4345] usb: dwc3: gadget: Reset num TRBs before giving back the request commit 00f8205ffcf112dcef14f8151d78075d38d22c08 upstream. Consider a scenario where cable disconnect happens when there is an active usb reqest queued to the UDC. As part of the disconnect we would issue an end transfer with no interrupt-on-completion before giving back this request. Since we are giving back the request without skipping TRBs the num_trbs field of dwc3_request still holds the stale value previously used. Function drivers re-use same request for a given bind-unbind session and hence their dwc3_request context gets preserved across cable disconnect/connect. When such a request gets re-queued after cable connect, we would increase the num_trbs field on top of the previous stale value thus incorrectly representing the number of TRBs used. Fix this by resetting num_trbs field before giving back the request. Fixes: 09fe1f8d7e2f ("usb: dwc3: gadget: track number of TRBs per request") Cc: stable Signed-off-by: Elson Roy Serrao Acked-by: Thinh Nguyen Message-ID: <1685654850-8468-1-git-send-email-quic_eserrao@quicinc.com> Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 4e3b451ed749..164910237669 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -180,6 +180,7 @@ static void dwc3_gadget_del_and_unmap_request(struct dwc3_ep *dep, list_del(&req->list); req->remaining = 0; req->needs_extra_trb = false; + req->num_trbs = 0; if (req->request.status == -EINPROGRESS) req->request.status = status; From cb6ec51ddd00aa8768e0b7d24a8d3b189bf52837 Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Tue, 25 Apr 2023 01:02:42 +0000 Subject: [PATCH 3554/4345] RDMA/rtrs: Fix the last iu->buf leak in err path [ Upstream commit 3bf3a7c6985c625f64e73baefdaa36f1c2045a29 ] The last iu->buf will leak if ib_dma_mapping_error() fails. Fixes: c0894b3ea69d ("RDMA/rtrs: core: lib functions shared between client and server modules") Link: https://lore.kernel.org/r/1682384563-2-3-git-send-email-lizhijian@fujitsu.com Signed-off-by: Li Zhijian Acked-by: Guoqing Jiang Acked-by: Jack Wang Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/rtrs/rtrs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c index 4629bb758126..76b993e8d672 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs.c +++ b/drivers/infiniband/ulp/rtrs/rtrs.c @@ -37,8 +37,10 @@ struct rtrs_iu *rtrs_iu_alloc(u32 queue_size, size_t size, gfp_t gfp_mask, goto err; iu->dma_addr = ib_dma_map_single(dma_dev, iu->buf, size, dir); - if (ib_dma_mapping_error(dma_dev, iu->dma_addr)) + if (ib_dma_mapping_error(dma_dev, iu->dma_addr)) { + kfree(iu->buf); goto err; + } iu->cqe.done = done; iu->size = size; From af42c4fd827ce46c454a8503702381338245eb17 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 30 May 2023 01:34:02 +0300 Subject: [PATCH 3555/4345] spi: fsl-dspi: avoid SCK glitches with continuous transfers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c5c31fb71f16ba75bad4ade208abbae225305b65 ] The DSPI controller has configurable timing for (a) tCSC: the interval between the assertion of the chip select and the first clock edge (b) tASC: the interval between the last clock edge and the deassertion of the chip select What is a bit surprising, but is documented in the figure "Example of continuous transfer (CPHA=1, CONT=1)" in the datasheet, is that when the chip select stays asserted between multiple TX FIFO writes, the tCSC and tASC times still apply. With CONT=1, chip select remains asserted, but SCK takes a break and goes to the idle state for tASC + tCSC ns. In other words, the default values (of 0 and 0 ns) result in SCK glitches where the SCK transition to the idle state, as well as the SCK transition from the idle state, will have no delay in between, and it may appear that a SCK cycle has simply gone missing. The resulting timing violation might cause data corruption in many peripherals, as their chip select is asserted. The driver has device tree bindings for tCSC ("fsl,spi-cs-sck-delay") and tASC ("fsl,spi-sck-cs-delay"), but these are only specified to apply when the chip select toggles in the first place, and this timing characteristic depends on each peripheral. Many peripherals do not have explicit timing requirements, so many device trees do not have these properties present at all. Nonetheless, the lack of SCK glitches is a common sense requirement, and since the SCK stays in the idle state during transfers for tCSC+tASC ns, and that in itself should look like half a cycle, then let's ensure that tCSC and tASC are at least a quarter of a SCK period, such that their sum is at least half of one. Fixes: 95bf15f38641 ("spi: fsl-dspi: Add ~50ns delay between cs and sck") Reported-by: Lisa Chen (陈敏捷) Debugged-by: Lisa Chen (陈敏捷) Tested-by: Lisa Chen (陈敏捷) Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230529223402.1199503-1-vladimir.oltean@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-fsl-dspi.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index fd004c9db9dc..0d9201a2999d 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -975,7 +975,9 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, static int dspi_setup(struct spi_device *spi) { struct fsl_dspi *dspi = spi_controller_get_devdata(spi->controller); + u32 period_ns = DIV_ROUND_UP(NSEC_PER_SEC, spi->max_speed_hz); unsigned char br = 0, pbr = 0, pcssck = 0, cssck = 0; + u32 quarter_period_ns = DIV_ROUND_UP(period_ns, 4); u32 cs_sck_delay = 0, sck_cs_delay = 0; struct fsl_dspi_platform_data *pdata; unsigned char pasc = 0, asc = 0; @@ -1003,6 +1005,19 @@ static int dspi_setup(struct spi_device *spi) sck_cs_delay = pdata->sck_cs_delay; } + /* Since tCSC and tASC apply to continuous transfers too, avoid SCK + * glitches of half a cycle by never allowing tCSC + tASC to go below + * half a SCK period. + */ + if (cs_sck_delay < quarter_period_ns) + cs_sck_delay = quarter_period_ns; + if (sck_cs_delay < quarter_period_ns) + sck_cs_delay = quarter_period_ns; + + dev_dbg(&spi->dev, + "DSPI controller timing params: CS-to-SCK delay %u ns, SCK-to-CS delay %u ns\n", + cs_sck_delay, sck_cs_delay); + clkrate = clk_get_rate(dspi->clk); hz_to_spi_baud(&pbr, &br, spi->max_speed_hz, clkrate); From 1200af82cf0bbf28a608905c9e9be7bf37c00c98 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 8 Jun 2023 00:19:12 +0200 Subject: [PATCH 3556/4345] netfilter: nfnetlink: skip error delivery on batch in case of ENOMEM [ Upstream commit a1a64a151dae8ac3581c1cbde44b672045cb658b ] If caller reports ENOMEM, then stop iterating over the batch and send a single netlink message to userspace to report OOM. Fixes: cbb8125eb40b ("netfilter: nfnetlink: deliver netlink errors on batch completion") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nfnetlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index edf386a020b9..bec9ac8b8fbe 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -473,7 +473,8 @@ ack: * processed, this avoids that the same error is * reported several times when replaying the batch. */ - if (nfnl_err_add(&err_list, nlh, err, &extack) < 0) { + if (err == -ENOMEM || + nfnl_err_add(&err_list, nlh, err, &extack) < 0) { /* We failed to enqueue an error, reset the * list of errors and send OOM to userspace * pointing to the batch header. From 9e666a77f00850ba7e47eea14c04c55293cd7ebd Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Wed, 7 Jun 2023 17:10:48 +0800 Subject: [PATCH 3557/4345] net: enetc: correct the indexes of highest and 2nd highest TCs [ Upstream commit 21225873be1472b7c59ed3650396af0e40578112 ] For ENETC hardware, the TCs are numbered from 0 to N-1, where N is the number of TCs. Numerically higher TC has higher priority. It's obvious that the highest priority TC index should be N-1 and the 2nd highest priority TC index should be N-2. However, the previous logic uses netdev_get_prio_tc_map() to get the indexes of highest priority and 2nd highest priority TCs, it does not make sense and is incorrect to give a "tc" argument to netdev_get_prio_tc_map(). So the driver may get the wrong indexes of the two highest priotiry TCs which would lead to failed to set the CBS for the two highest priotiry TCs. e.g. $ tc qdisc add dev eno0 parent root handle 100: mqprio num_tc 6 \ map 0 0 1 1 2 3 4 5 queues 1@0 1@1 1@2 1@3 2@4 2@6 hw 1 $ tc qdisc replace dev eno0 parent 100:6 cbs idleslope 100000 \ sendslope -900000 hicredit 12 locredit -113 offload 1 $ Error: Specified device failed to setup cbs hardware offload. ^^^^^ In this example, the previous logic deems the indexes of the two highest priotiry TCs should be 3 and 2. Actually, the indexes are 5 and 4, because the number of TCs is 6. So it would be failed to configure the CBS for the two highest priority TCs. Fixes: c431047c4efe ("enetc: add support Credit Based Shaper(CBS) for hardware offload") Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Reviewed-by: Maciej Fijalkowski Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/freescale/enetc/enetc_qos.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 8d92dc6bc994..d7215bd772f3 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -196,8 +196,8 @@ int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data) int bw_sum = 0; u8 bw; - prio_top = netdev_get_prio_tc_map(ndev, tc_nums - 1); - prio_next = netdev_get_prio_tc_map(ndev, tc_nums - 2); + prio_top = tc_nums - 1; + prio_next = tc_nums - 2; /* Support highest prio and second prio tc in cbs mode */ if (tc != prio_top && tc != prio_next) From 5852d17aaa8b0c4aef497aabe91052ff6ceebce8 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Wed, 7 Jun 2023 18:05:02 +0200 Subject: [PATCH 3558/4345] ping6: Fix send to link-local addresses with VRF. [ Upstream commit 91ffd1bae1dafbb9e34b46813f5b058581d9144d ] Ping sockets can't send packets when they're bound to a VRF master device and the output interface is set to a slave device. For example, when net.ipv4.ping_group_range is properly set, so that ping6 can use ping sockets, the following kind of commands fails: $ ip vrf exec red ping6 fe80::854:e7ff:fe88:4bf1%eth1 What happens is that sk->sk_bound_dev_if is set to the VRF master device, but 'oif' is set to the real output device. Since both are set but different, ping_v6_sendmsg() sees their value as inconsistent and fails. Fix this by allowing 'oif' to be a slave device of ->sk_bound_dev_if. This fixes the following kselftest failure: $ ./fcnal-test.sh -t ipv6_ping [...] TEST: ping out, vrf device+address bind - ns-B IPv6 LLA [FAIL] Reported-by: Mirsad Todorovac Closes: https://lore.kernel.org/netdev/b6191f90-ffca-dbca-7d06-88a9788def9c@alu.unizg.hr/ Tested-by: Mirsad Todorovac Fixes: 5e457896986e ("net: ipv6: Fix ping to link-local addresses.") Signed-off-by: Guillaume Nault Reviewed-by: David Ahern Link: https://lore.kernel.org/r/6c8b53108816a8d0d5705ae37bdc5a8322b5e3d9.1686153846.git.gnault@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv6/ping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 6ac88fe24a8e..7fab29f3ce6e 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -96,7 +96,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) addr_type = ipv6_addr_type(daddr); if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || (addr_type & IPV6_ADDR_MAPPED) || - (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) + (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if && + l3mdev_master_ifindex_by_index(sock_net(sk), oif) != sk->sk_bound_dev_if)) return -EINVAL; /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ From af6eaa57986e82d7efd81984ee607927c6de61e4 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 8 Jun 2023 08:29:03 +0100 Subject: [PATCH 3559/4345] net/sched: cls_u32: Fix reference counter leak leading to overflow [ Upstream commit 04c55383fa5689357bcdd2c8036725a55ed632bc ] In the event of a failure in tcf_change_indev(), u32_set_parms() will immediately return without decrementing the recently incremented reference counter. If this happens enough times, the counter will rollover and the reference freed, leading to a double free which can be used to do 'bad things'. In order to prevent this, move the point of possible failure above the point where the reference counter is incremented. Also save any meaningful return values to be applied to the return data at the appropriate point in time. This issue was caught with KASAN. Fixes: 705c7091262d ("net: sched: cls_u32: no need to call tcf_exts_change for newly allocated struct") Suggested-by: Eric Dumazet Signed-off-by: Lee Jones Reviewed-by: Eric Dumazet Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/cls_u32.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index da042bc8b239..1ac8ff445a6d 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -716,12 +716,18 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) { - int err; + int err, ifindex = -1; err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, true, extack); if (err < 0) return err; + if (tb[TCA_U32_INDEV]) { + ifindex = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); + if (ifindex < 0) + return -EINVAL; + } + if (tb[TCA_U32_LINK]) { u32 handle = nla_get_u32(tb[TCA_U32_LINK]); struct tc_u_hnode *ht_down = NULL, *ht_old; @@ -756,13 +762,9 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, tcf_bind_filter(tp, &n->res, base); } - if (tb[TCA_U32_INDEV]) { - int ret; - ret = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); - if (ret < 0) - return -EINVAL; - n->ifindex = ret; - } + if (ifindex >= 0) + n->ifindex = ifindex; + return 0; } From 6205c0d9ff8b03603491af6b99160bc1f8134055 Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Sun, 21 Aug 2022 21:16:15 -0400 Subject: [PATCH 3560/4345] RDMA/rxe: Remove the unused variable obj [ Upstream commit f07853582d1f6ed282f8d9a0b1209a87dd761f58 ] The member variable obj in struct rxe_task is not needed. So remove it to save memory. Link: https://lore.kernel.org/r/20220822011615.805603-4-yanjun.zhu@linux.dev Signed-off-by: Zhu Yanjun Reviewed-by: Li Zhijian Reviewed-by: Bob Pearson Signed-off-by: Leon Romanovsky Stable-dep-of: 2a62b6210ce8 ("RDMA/rxe: Fix the use-before-initialization error of resp_pkts") Signed-off-by: Sasha Levin --- drivers/infiniband/sw/rxe/rxe_qp.c | 6 +++--- drivers/infiniband/sw/rxe/rxe_task.c | 3 +-- drivers/infiniband/sw/rxe/rxe_task.h | 3 +-- 3 files changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 99c1b3553e6e..b1bad20c76d4 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -249,9 +249,9 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, skb_queue_head_init(&qp->req_pkts); - rxe_init_task(rxe, &qp->req.task, qp, + rxe_init_task(&qp->req.task, qp, rxe_requester, "req"); - rxe_init_task(rxe, &qp->comp.task, qp, + rxe_init_task(&qp->comp.task, qp, rxe_completer, "comp"); qp->qp_timeout_jiffies = 0; /* Can't be set for UD/UC in modify_qp */ @@ -298,7 +298,7 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp, skb_queue_head_init(&qp->resp_pkts); - rxe_init_task(rxe, &qp->resp.task, qp, + rxe_init_task(&qp->resp.task, qp, rxe_responder, "resp"); qp->resp.opcode = OPCODE_NONE; diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index 568cf56c236b..f48882b20d6b 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -95,10 +95,9 @@ void rxe_do_task(struct tasklet_struct *t) task->ret = ret; } -int rxe_init_task(void *obj, struct rxe_task *task, +int rxe_init_task(struct rxe_task *task, void *arg, int (*func)(void *), char *name) { - task->obj = obj; task->arg = arg; task->func = func; snprintf(task->name, sizeof(task->name), "%s", name); diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h index 11d183fd3338..7f612a1c68a7 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.h +++ b/drivers/infiniband/sw/rxe/rxe_task.h @@ -19,7 +19,6 @@ enum { * called again. */ struct rxe_task { - void *obj; struct tasklet_struct tasklet; int state; spinlock_t state_lock; /* spinlock for task state */ @@ -35,7 +34,7 @@ struct rxe_task { * arg => parameter to pass to fcn * func => function to call until it returns != 0 */ -int rxe_init_task(void *obj, struct rxe_task *task, +int rxe_init_task(struct rxe_task *task, void *arg, int (*func)(void *), char *name); /* cleanup task */ From 089a0e831f68df032926a9e68ca8a3bb2946d2fa Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Fri, 21 Oct 2022 15:01:04 -0500 Subject: [PATCH 3561/4345] RDMA/rxe: Removed unused name from rxe_task struct [ Upstream commit de669ae8af49ceed0eed44f5b3d51dc62affc5e4 ] The name field in struct rxe_task is never used. This patch removes it. Link: https://lore.kernel.org/r/20221021200118.2163-4-rpearsonhpe@gmail.com Signed-off-by: Ian Ziemba Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe Stable-dep-of: 2a62b6210ce8 ("RDMA/rxe: Fix the use-before-initialization error of resp_pkts") Signed-off-by: Sasha Levin --- drivers/infiniband/sw/rxe/rxe_qp.c | 9 +++------ drivers/infiniband/sw/rxe/rxe_task.c | 4 +--- drivers/infiniband/sw/rxe/rxe_task.h | 4 +--- 3 files changed, 5 insertions(+), 12 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index b1bad20c76d4..6ff6718fcde6 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -249,10 +249,8 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, skb_queue_head_init(&qp->req_pkts); - rxe_init_task(&qp->req.task, qp, - rxe_requester, "req"); - rxe_init_task(&qp->comp.task, qp, - rxe_completer, "comp"); + rxe_init_task(&qp->req.task, qp, rxe_requester); + rxe_init_task(&qp->comp.task, qp, rxe_completer); qp->qp_timeout_jiffies = 0; /* Can't be set for UD/UC in modify_qp */ if (init->qp_type == IB_QPT_RC) { @@ -298,8 +296,7 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp, skb_queue_head_init(&qp->resp_pkts); - rxe_init_task(&qp->resp.task, qp, - rxe_responder, "resp"); + rxe_init_task(&qp->resp.task, qp, rxe_responder); qp->resp.opcode = OPCODE_NONE; qp->resp.msn = 0; diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index f48882b20d6b..5aa69947a979 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -95,12 +95,10 @@ void rxe_do_task(struct tasklet_struct *t) task->ret = ret; } -int rxe_init_task(struct rxe_task *task, - void *arg, int (*func)(void *), char *name) +int rxe_init_task(struct rxe_task *task, void *arg, int (*func)(void *)) { task->arg = arg; task->func = func; - snprintf(task->name, sizeof(task->name), "%s", name); task->destroyed = false; tasklet_setup(&task->tasklet, rxe_do_task); diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h index 7f612a1c68a7..b3dfd970d1dc 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.h +++ b/drivers/infiniband/sw/rxe/rxe_task.h @@ -25,7 +25,6 @@ struct rxe_task { void *arg; int (*func)(void *arg); int ret; - char name[16]; bool destroyed; }; @@ -34,8 +33,7 @@ struct rxe_task { * arg => parameter to pass to fcn * func => function to call until it returns != 0 */ -int rxe_init_task(struct rxe_task *task, - void *arg, int (*func)(void *), char *name); +int rxe_init_task(struct rxe_task *task, void *arg, int (*func)(void *)); /* cleanup task */ void rxe_cleanup_task(struct rxe_task *task); From 079a9591ee182b0fccf67877cec9312087940087 Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Fri, 2 Jun 2023 11:54:08 +0800 Subject: [PATCH 3562/4345] RDMA/rxe: Fix the use-before-initialization error of resp_pkts [ Upstream commit 2a62b6210ce876c596086ab8fd4c8a0c3d10611a ] In the following: Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 assign_lock_key kernel/locking/lockdep.c:982 [inline] register_lock_class+0xdb6/0x1120 kernel/locking/lockdep.c:1295 __lock_acquire+0x10a/0x5df0 kernel/locking/lockdep.c:4951 lock_acquire kernel/locking/lockdep.c:5691 [inline] lock_acquire+0x1b1/0x520 kernel/locking/lockdep.c:5656 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0x3d/0x60 kernel/locking/spinlock.c:162 skb_dequeue+0x20/0x180 net/core/skbuff.c:3639 drain_resp_pkts drivers/infiniband/sw/rxe/rxe_comp.c:555 [inline] rxe_completer+0x250d/0x3cc0 drivers/infiniband/sw/rxe/rxe_comp.c:652 rxe_qp_do_cleanup+0x1be/0x820 drivers/infiniband/sw/rxe/rxe_qp.c:761 execute_in_process_context+0x3b/0x150 kernel/workqueue.c:3473 __rxe_cleanup+0x21e/0x370 drivers/infiniband/sw/rxe/rxe_pool.c:233 rxe_create_qp+0x3f6/0x5f0 drivers/infiniband/sw/rxe/rxe_verbs.c:583 This is a use-before-initialization problem. It happens because rxe_qp_do_cleanup is called during error unwind before the struct has been fully initialized. Move the initialization of the skb earlier. Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://lore.kernel.org/r/20230602035408.741534-1-yanjun.zhu@intel.com Reported-by: syzbot+eba589d8f49c73d356da@syzkaller.appspotmail.com Signed-off-by: Zhu Yanjun Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/sw/rxe/rxe_qp.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 6ff6718fcde6..4c938d841f76 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -192,6 +192,9 @@ static void rxe_qp_init_misc(struct rxe_dev *rxe, struct rxe_qp *qp, spin_lock_init(&qp->rq.producer_lock); spin_lock_init(&qp->rq.consumer_lock); + skb_queue_head_init(&qp->req_pkts); + skb_queue_head_init(&qp->resp_pkts); + atomic_set(&qp->ssn, 0); atomic_set(&qp->skb_out, 0); } @@ -247,8 +250,6 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, qp->req.opcode = -1; qp->comp.opcode = -1; - skb_queue_head_init(&qp->req_pkts); - rxe_init_task(&qp->req.task, qp, rxe_requester); rxe_init_task(&qp->comp.task, qp, rxe_completer); @@ -294,8 +295,6 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp, } } - skb_queue_head_init(&qp->resp_pkts); - rxe_init_task(&qp->resp.task, qp, rxe_responder); qp->resp.opcode = OPCODE_NONE; From 0fb48a2a6ad4faa48cbf4ff372c40447d60fdf9f Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Thu, 8 Jun 2023 13:02:26 -0700 Subject: [PATCH 3563/4345] iavf: remove mask from iavf_irq_enable_queues() [ Upstream commit c37cf54c12cfaa51e7aaf88708167b0d3259e64e ] Enable more than 32 IRQs by removing the u32 bit mask in iavf_irq_enable_queues(). There is no need for the mask as there are no callers that select individual IRQs through the bitmask. Also, if the PF allocates more than 32 IRQs, this mask will prevent us from using all of them. Modify the comment in iavf_register.h to show that the maximum number allowed for the IRQ index is 63 as per the iAVF standard 1.0 [1]. link: [1] https://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/ethernet-adaptive-virtual-function-hardware-spec.pdf Fixes: 5eae00c57f5e ("i40evf: main driver core") Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Reviewed-by: Maciej Fijalkowski Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20230608200226.451861-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf.h | 2 +- drivers/net/ethernet/intel/iavf/iavf_main.c | 15 ++++++--------- drivers/net/ethernet/intel/iavf/iavf_register.h | 2 +- 3 files changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index a994a2970ab2..6a6b5f6e8276 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -398,7 +398,7 @@ void iavf_set_ethtool_ops(struct net_device *netdev); void iavf_update_stats(struct iavf_adapter *adapter); void iavf_reset_interrupt_capability(struct iavf_adapter *adapter); int iavf_init_interrupt_scheme(struct iavf_adapter *adapter); -void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask); +void iavf_irq_enable_queues(struct iavf_adapter *adapter); void iavf_free_all_tx_resources(struct iavf_adapter *adapter); void iavf_free_all_rx_resources(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index ae96b552a3bb..e45f3a1a11f3 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -234,21 +234,18 @@ static void iavf_irq_disable(struct iavf_adapter *adapter) } /** - * iavf_irq_enable_queues - Enable interrupt for specified queues + * iavf_irq_enable_queues - Enable interrupt for all queues * @adapter: board private structure - * @mask: bitmap of queues to enable **/ -void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask) +void iavf_irq_enable_queues(struct iavf_adapter *adapter) { struct iavf_hw *hw = &adapter->hw; int i; for (i = 1; i < adapter->num_msix_vectors; i++) { - if (mask & BIT(i - 1)) { - wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), - IAVF_VFINT_DYN_CTLN1_INTENA_MASK | - IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK); - } + wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), + IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK); } } @@ -262,7 +259,7 @@ void iavf_irq_enable(struct iavf_adapter *adapter, bool flush) struct iavf_hw *hw = &adapter->hw; iavf_misc_irq_enable(adapter); - iavf_irq_enable_queues(adapter, ~0); + iavf_irq_enable_queues(adapter); if (flush) iavf_flush(hw); diff --git a/drivers/net/ethernet/intel/iavf/iavf_register.h b/drivers/net/ethernet/intel/iavf/iavf_register.h index bf793332fc9d..a19e88898a0b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_register.h +++ b/drivers/net/ethernet/intel/iavf/iavf_register.h @@ -40,7 +40,7 @@ #define IAVF_VFINT_DYN_CTL01_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTL01_INTENA_SHIFT) #define IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3 #define IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT) -#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */ +#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...63 */ /* Reset: VFR */ #define IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT 0 #define IAVF_VFINT_DYN_CTLN1_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT) #define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2 From aa277d5cd4b2b11d1f2aa4e5b689aa11e4e22c35 Mon Sep 17 00:00:00 2001 From: Satha Rao Date: Thu, 8 Jun 2023 17:12:00 +0530 Subject: [PATCH 3564/4345] octeontx2-af: fixed resource availability check [ Upstream commit 4e635f9d86165e47f5440196f2ebdb258efb8341 ] txschq_alloc response have two different arrays to store continuous and non-continuous schedulers of each level. Requested count should be checked for each array separately. Fixes: 5d9b976d4480 ("octeontx2-af: Support fixed transmit scheduler topology") Signed-off-by: Satha Rao Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Naveen Mamindlapalli Reviewed-by: Sridhar Samudrala Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 9886a30e9723..449f5224d1ae 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -1385,7 +1385,8 @@ static int nix_check_txschq_alloc_req(struct rvu *rvu, int lvl, u16 pcifunc, free_cnt = rvu_rsrc_free_count(&txsch->schq); } - if (free_cnt < req_schq || req_schq > MAX_TXSCHQ_PER_FUNC) + if (free_cnt < req_schq || req->schq[lvl] > MAX_TXSCHQ_PER_FUNC || + req->schq_contig[lvl] > MAX_TXSCHQ_PER_FUNC) return NIX_AF_ERR_TLX_ALLOC_FAIL; /* If contiguous queues are needed, check for availability */ From f49abbb274162637f6af440a0979005e35d16ce3 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Mon, 5 Jun 2023 13:33:17 +0300 Subject: [PATCH 3565/4345] RDMA/mlx5: Initiate dropless RQ for RAW Ethernet functions [ Upstream commit ee4d269eccfea6c17b18281bef482700d898e86f ] Delay drop data is initiated for PFs that have the capability of rq_delay_drop and are in roce profile. However, PFs with RAW ethernet profile do not initiate delay drop data on function load, causing kernel panic if delay drop struct members are accessed later on in case a dropless RQ is created. Thus, stage the delay drop initialization as part of RAW ethernet PF loading process. Fixes: b5ca15ad7e61 ("IB/mlx5: Add proper representors support") Signed-off-by: Maher Sanalla Reviewed-by: Maor Gottlieb Link: https://lore.kernel.org/r/2e9d386785043d48c38711826eb910315c1de141.1685960567.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx5/main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5ef37902e96b..39ba7005f2c4 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4746,6 +4746,9 @@ const struct mlx5_ib_profile raw_eth_profile = { STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR, mlx5_ib_stage_post_ib_reg_umr_init, NULL), + STAGE_CREATE(MLX5_IB_STAGE_DELAY_DROP, + mlx5_ib_stage_delay_drop_init, + mlx5_ib_stage_delay_drop_cleanup), STAGE_CREATE(MLX5_IB_STAGE_RESTRACK, mlx5_ib_restrack_init, NULL), From 6cccdbc9f09c76925e3c01570676354b0e9178fb Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Mon, 5 Jun 2023 13:33:23 +0300 Subject: [PATCH 3566/4345] RDMA/cma: Always set static rate to 0 for RoCE [ Upstream commit 58030c76cce473b6cfd630bbecb97215def0dff8 ] Set static rate to 0 as it should be discovered by path query and has no meaning for RoCE. This also avoid of using the rtnl lock and ethtool API, which is a bottleneck when try to setup many rdma-cm connections at the same time, especially with multiple processes. Fixes: 3c86aa70bf67 ("RDMA/cm: Add RDMA CM support for IBoE devices") Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/f72a4f8b667b803aee9fa794069f61afb5839ce4.1685960567.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/cma.c | 4 ++-- include/rdma/ib_addr.h | 23 ----------------------- 2 files changed, 2 insertions(+), 25 deletions(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index fdcad8d6a5a0..db24f7dfa00f 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3069,7 +3069,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) route->path_rec->traffic_class = tos; route->path_rec->mtu = iboe_get_mtu(ndev->mtu); route->path_rec->rate_selector = IB_SA_EQ; - route->path_rec->rate = iboe_get_rate(ndev); + route->path_rec->rate = IB_RATE_PORT_CURRENT; dev_put(ndev); route->path_rec->packet_life_time_selector = IB_SA_EQ; /* In case ACK timeout is set, use this value to calculate @@ -4719,7 +4719,7 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, if (!ndev) return -ENODEV; - ib.rec.rate = iboe_get_rate(ndev); + ib.rec.rate = IB_RATE_PORT_CURRENT; ib.rec.hop_limit = 1; ib.rec.mtu = iboe_get_mtu(ndev->mtu); diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h index b0e636ac6690..8c5c9582c4fb 100644 --- a/include/rdma/ib_addr.h +++ b/include/rdma/ib_addr.h @@ -193,29 +193,6 @@ static inline enum ib_mtu iboe_get_mtu(int mtu) return 0; } -static inline int iboe_get_rate(struct net_device *dev) -{ - struct ethtool_link_ksettings cmd; - int err; - - rtnl_lock(); - err = __ethtool_get_link_ksettings(dev, &cmd); - rtnl_unlock(); - if (err) - return IB_RATE_PORT_CURRENT; - - if (cmd.base.speed >= 40000) - return IB_RATE_40_GBPS; - else if (cmd.base.speed >= 30000) - return IB_RATE_30_GBPS; - else if (cmd.base.speed >= 20000) - return IB_RATE_20_GBPS; - else if (cmd.base.speed >= 10000) - return IB_RATE_10_GBPS; - else - return IB_RATE_PORT_CURRENT; -} - static inline int rdma_link_local_addr(struct in6_addr *addr) { if (addr->s6_addr32[0] == htonl(0xfe800000) && From 2f9d26345c6eb3521724d04328d6c25560b2e409 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 5 Jun 2023 13:33:25 +0300 Subject: [PATCH 3567/4345] IB/uverbs: Fix to consider event queue closing also upon non-blocking mode [ Upstream commit 62fab312fa1683e812e605db20d4f22de3e3fb2f ] Fix ib_uverbs_event_read() to consider event queue closing also upon non-blocking mode. Once the queue is closed (e.g. hot-plug flow) all the existing events are cleaned-up as part of ib_uverbs_free_event_queue(). An application that uses the non-blocking FD mode should get -EIO in that case to let it knows that the device was removed already. Otherwise, it can loose the indication that the device was removed and won't recover. As part of that, refactor the code to have a single flow with regards to 'is_closed' for both blocking and non-blocking modes. Fixes: 14e23bd6d221 ("RDMA/core: Fix locking in ib_uverbs_event_read") Reviewed-by: Maor Gottlieb Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/97b00116a1e1e13f8dc4ec38a5ea81cf8c030210.1685960567.git.leon@kernel.org Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/core/uverbs_main.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 4bb7c642f80c..099f5acc749e 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -222,8 +222,12 @@ static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue, spin_lock_irq(&ev_queue->lock); while (list_empty(&ev_queue->event_list)) { - spin_unlock_irq(&ev_queue->lock); + if (ev_queue->is_closed) { + spin_unlock_irq(&ev_queue->lock); + return -EIO; + } + spin_unlock_irq(&ev_queue->lock); if (filp->f_flags & O_NONBLOCK) return -EAGAIN; @@ -233,12 +237,6 @@ static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue, return -ERESTARTSYS; spin_lock_irq(&ev_queue->lock); - - /* If device was disassociated and no event exists set an error */ - if (list_empty(&ev_queue->event_list) && ev_queue->is_closed) { - spin_unlock_irq(&ev_queue->lock); - return -EIO; - } } event = list_entry(ev_queue->event_list.next, struct ib_uverbs_event, list); From 2b6f8817ca66cd4c0acc663bb295f5d17a9f9d9b Mon Sep 17 00:00:00 2001 From: Saravanan Vajravel Date: Tue, 6 Jun 2023 03:25:29 -0700 Subject: [PATCH 3568/4345] IB/isert: Fix dead lock in ib_isert [ Upstream commit 691b0480933f0ce88a81ed1d1a0aff340ff6293a ] - When a iSER session is released, ib_isert module is taking a mutex lock and releasing all pending connections. As part of this, ib_isert is destroying rdma cm_id. To destroy cm_id, rdma_cm module is sending CM events to CMA handler of ib_isert. This handler is taking same mutex lock. Hence it leads to deadlock between ib_isert & rdma_cm modules. - For fix, created local list of pending connections and release the connection outside of mutex lock. Calltrace: --------- [ 1229.791410] INFO: task kworker/10:1:642 blocked for more than 120 seconds. [ 1229.791416] Tainted: G OE --------- - - 4.18.0-372.9.1.el8.x86_64 #1 [ 1229.791418] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 1229.791419] task:kworker/10:1 state:D stack: 0 pid: 642 ppid: 2 flags:0x80004000 [ 1229.791424] Workqueue: ib_cm cm_work_handler [ib_cm] [ 1229.791436] Call Trace: [ 1229.791438] __schedule+0x2d1/0x830 [ 1229.791445] ? select_idle_sibling+0x23/0x6f0 [ 1229.791449] schedule+0x35/0xa0 [ 1229.791451] schedule_preempt_disabled+0xa/0x10 [ 1229.791453] __mutex_lock.isra.7+0x310/0x420 [ 1229.791456] ? select_task_rq_fair+0x351/0x990 [ 1229.791459] isert_cma_handler+0x224/0x330 [ib_isert] [ 1229.791463] ? ttwu_queue_wakelist+0x159/0x170 [ 1229.791466] cma_cm_event_handler+0x25/0xd0 [rdma_cm] [ 1229.791474] cma_ib_handler+0xa7/0x2e0 [rdma_cm] [ 1229.791478] cm_process_work+0x22/0xf0 [ib_cm] [ 1229.791483] cm_work_handler+0xf4/0xf30 [ib_cm] [ 1229.791487] ? move_linked_works+0x6e/0xa0 [ 1229.791490] process_one_work+0x1a7/0x360 [ 1229.791491] ? create_worker+0x1a0/0x1a0 [ 1229.791493] worker_thread+0x30/0x390 [ 1229.791494] ? create_worker+0x1a0/0x1a0 [ 1229.791495] kthread+0x10a/0x120 [ 1229.791497] ? set_kthread_struct+0x40/0x40 [ 1229.791499] ret_from_fork+0x1f/0x40 [ 1229.791739] INFO: task targetcli:28666 blocked for more than 120 seconds. [ 1229.791740] Tainted: G OE --------- - - 4.18.0-372.9.1.el8.x86_64 #1 [ 1229.791741] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 1229.791742] task:targetcli state:D stack: 0 pid:28666 ppid: 5510 flags:0x00004080 [ 1229.791743] Call Trace: [ 1229.791744] __schedule+0x2d1/0x830 [ 1229.791746] schedule+0x35/0xa0 [ 1229.791748] schedule_preempt_disabled+0xa/0x10 [ 1229.791749] __mutex_lock.isra.7+0x310/0x420 [ 1229.791751] rdma_destroy_id+0x15/0x20 [rdma_cm] [ 1229.791755] isert_connect_release+0x115/0x130 [ib_isert] [ 1229.791757] isert_free_np+0x87/0x140 [ib_isert] [ 1229.791761] iscsit_del_np+0x74/0x120 [iscsi_target_mod] [ 1229.791776] lio_target_np_driver_store+0xe9/0x140 [iscsi_target_mod] [ 1229.791784] configfs_write_file+0xb2/0x110 [ 1229.791788] vfs_write+0xa5/0x1a0 [ 1229.791792] ksys_write+0x4f/0xb0 [ 1229.791794] do_syscall_64+0x5b/0x1a0 [ 1229.791798] entry_SYSCALL_64_after_hwframe+0x65/0xca Fixes: bd3792205aae ("iser-target: Fix pending connections handling in target stack shutdown sequnce") Reviewed-by: Sagi Grimberg Signed-off-by: Selvin Xavier Signed-off-by: Saravanan Vajravel Link: https://lore.kernel.org/r/20230606102531.162967-2-saravanan.vajravel@broadcom.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/isert/ib_isert.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 2d0d966fba2c..988b957107cc 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -2421,6 +2421,7 @@ isert_free_np(struct iscsi_np *np) { struct isert_np *isert_np = np->np_context; struct isert_conn *isert_conn, *n; + LIST_HEAD(drop_conn_list); if (isert_np->cm_id) rdma_destroy_id(isert_np->cm_id); @@ -2440,7 +2441,7 @@ isert_free_np(struct iscsi_np *np) node) { isert_info("cleaning isert_conn %p state (%d)\n", isert_conn, isert_conn->state); - isert_connect_release(isert_conn); + list_move_tail(&isert_conn->node, &drop_conn_list); } } @@ -2451,11 +2452,16 @@ isert_free_np(struct iscsi_np *np) node) { isert_info("cleaning isert_conn %p state (%d)\n", isert_conn, isert_conn->state); - isert_connect_release(isert_conn); + list_move_tail(&isert_conn->node, &drop_conn_list); } } mutex_unlock(&isert_np->mutex); + list_for_each_entry_safe(isert_conn, n, &drop_conn_list, node) { + list_del_init(&isert_conn->node); + isert_connect_release(isert_conn); + } + np->np_context = NULL; kfree(isert_np); } From da6ae4aab5a643cba39d229b05c1f0d8d6cc4dc6 Mon Sep 17 00:00:00 2001 From: Saravanan Vajravel Date: Tue, 6 Jun 2023 03:25:30 -0700 Subject: [PATCH 3569/4345] IB/isert: Fix possible list corruption in CMA handler [ Upstream commit 7651e2d6c5b359a28c2d4c904fec6608d1021ca8 ] When ib_isert module receives connection error event, it is releasing the isert session and removes corresponding list node but it doesn't take appropriate mutex lock to remove the list node. This can lead to linked list corruption Fixes: bd3792205aae ("iser-target: Fix pending connections handling in target stack shutdown sequnce") Signed-off-by: Selvin Xavier Signed-off-by: Saravanan Vajravel Link: https://lore.kernel.org/r/20230606102531.162967-3-saravanan.vajravel@broadcom.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/isert/ib_isert.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 988b957107cc..ed375f517e8a 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -656,9 +656,13 @@ static int isert_connect_error(struct rdma_cm_id *cma_id) { struct isert_conn *isert_conn = cma_id->qp->qp_context; + struct isert_np *isert_np = cma_id->context; ib_drain_qp(isert_conn->qp); + + mutex_lock(&isert_np->mutex); list_del_init(&isert_conn->node); + mutex_unlock(&isert_np->mutex); isert_conn->cm_id = NULL; isert_put_conn(isert_conn); From 3c97f2c9ec29ce2f61772f6120aabc852f57132e Mon Sep 17 00:00:00 2001 From: Saravanan Vajravel Date: Tue, 6 Jun 2023 03:25:31 -0700 Subject: [PATCH 3570/4345] IB/isert: Fix incorrect release of isert connection [ Upstream commit 699826f4e30ab76a62c238c86fbef7e826639c8d ] The ib_isert module is releasing the isert connection both in isert_wait_conn() handler as well as isert_free_conn() handler. In isert_wait_conn() handler, it is expected to wait for iSCSI session logout operation to complete. It should free the isert connection only in isert_free_conn() handler. When a bunch of iSER target is cleared, this issue can lead to use-after-free memory issue as isert conn is twice released Fixes: b02efbfc9a05 ("iser-target: Fix implicit termination of connections") Reviewed-by: Sagi Grimberg Signed-off-by: Saravanan Vajravel Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/20230606102531.162967-4-saravanan.vajravel@broadcom.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/ulp/isert/ib_isert.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index ed375f517e8a..7cd90604502e 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -2560,8 +2560,6 @@ static void isert_wait_conn(struct iscsi_conn *conn) isert_put_unsol_pending_cmds(conn); isert_wait4cmds(conn); isert_wait4logout(isert_conn); - - queue_work(isert_release_wq, &isert_conn->release_work); } static void isert_free_conn(struct iscsi_conn *conn) From 5c47ed7f25d61b15890f3238c0e3c2f9699ca622 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 9 Jun 2023 17:15:02 +0800 Subject: [PATCH 3571/4345] ipvlan: fix bound dev checking for IPv6 l3s mode [ Upstream commit ce57adc222aba32431c42632b396e9213d0eb0b8 ] The commit 59a0b022aa24 ("ipvlan: Make skb->skb_iif track skb->dev for l3s mode") fixed ipvlan bonded dev checking by updating skb skb_iif. This fix works for IPv4, as in raw_v4_input() the dif is from inet_iif(skb), which is skb->skb_iif when there is no route. But for IPv6, the fix is not enough, because in ipv6_raw_deliver() -> raw_v6_match(), the dif is inet6_iif(skb), which is returns IP6CB(skb)->iif instead of skb->skb_iif if it's not a l3_slave. To fix the IPv6 part issue. Let's set IP6CB(skb)->iif to correct ifindex. BTW, ipvlan handles NS/NA specifically. Since it works fine, I will not reset IP6CB(skb)->iif when addr->atype is IPVL_ICMPV6. Fixes: c675e06a98a4 ("ipvlan: decouple l3s mode dependencies from other modes") Link: https://bugzilla.redhat.com/show_bug.cgi?id=2196710 Signed-off-by: Hangbin Liu Reviewed-by: Larysa Zaremba Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ipvlan/ipvlan_l3s.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c index 71712ea25403..d5b05e803219 100644 --- a/drivers/net/ipvlan/ipvlan_l3s.c +++ b/drivers/net/ipvlan/ipvlan_l3s.c @@ -102,6 +102,10 @@ static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, skb->dev = addr->master->dev; skb->skb_iif = skb->dev->ifindex; +#if IS_ENABLED(CONFIG_IPV6) + if (addr->atype == IPVL_IPV6) + IP6CB(skb)->iif = skb->dev->ifindex; +#endif len = skb->len + ETH_HLEN; ipvlan_count_rx(addr->master, len, true, false); out: From 221281d60c46d82b3ea7395fd857c641dcdab08c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 9 Jun 2023 14:05:19 +0300 Subject: [PATCH 3572/4345] sctp: fix an error code in sctp_sf_eat_auth() [ Upstream commit 75e6def3b26736e7ff80639810098c9074229737 ] The sctp_sf_eat_auth() function is supposed to enum sctp_disposition values and returning a kernel error code will cause issues in the caller. Change -ENOMEM to SCTP_DISPOSITION_NOMEM. Fixes: 65b07e5d0d09 ("[SCTP]: API updates to suport SCTP-AUTH extensions.") Signed-off-by: Dan Carpenter Acked-by: Xin Long Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sctp/sm_statefuns.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index ee0b2b03657c..1e82c51657a7 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4379,7 +4379,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net, SCTP_AUTH_NEW_KEY, GFP_ATOMIC); if (!ev) - return -ENOMEM; + return SCTP_DISPOSITION_NOMEM; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); From 8c3446ab5902baef75e33761f2e3078751c75313 Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Tue, 25 Apr 2023 17:44:14 +0200 Subject: [PATCH 3573/4345] igb: fix nvm.ops.read() error handling [ Upstream commit 48a821fd58837800750ec1b3962f0f799630a844 ] Add error handling into igb_set_eeprom() function, in case nvm.ops.read() fails just quit with error code asap. Fixes: 9d5c824399de ("igb: PCI-Express 82575 Gigabit Ethernet driver") Signed-off-by: Aleksandr Loktionov Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igb/igb_ethtool.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 5e3b0a5843a8..d9de3b811543 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -822,6 +822,8 @@ static int igb_set_eeprom(struct net_device *netdev, */ ret_val = hw->nvm.ops.read(hw, last_word, 1, &eeprom_buff[last_word - first_word]); + if (ret_val) + goto out; } /* Device's eeprom is always little-endian, word addressable */ @@ -841,6 +843,7 @@ static int igb_set_eeprom(struct net_device *netdev, hw->nvm.ops.update(hw); igb_set_fw_version(adapter); +out: kfree(eeprom_buff); return ret_val; } From edb970e03d65b699d20912df494521a60938feeb Mon Sep 17 00:00:00 2001 From: Ratchanan Srirattanamet Date: Wed, 24 May 2023 04:11:56 +0700 Subject: [PATCH 3574/4345] drm/nouveau: don't detect DSM for non-NVIDIA device [ Upstream commit 11d24327c2d7ad7f24fcc44fb00e1fa91ebf6525 ] The call site of nouveau_dsm_pci_probe() uses single set of output variables for all invocations. So, we must not write anything to them unless it's an NVIDIA device. Otherwise, if we are called with another device after the NVIDIA device, we'll clober the result of the NVIDIA device. For example, if the other device doesn't have _PR3 resources, the detection later would miss the presence of power resource support, and the rest of the code will keep using Optimus DSM, breaking power management for that machine. Also, because we're detecting NVIDIA's DSM, it doesn't make sense to run this detection on a non-NVIDIA device anyway. Thus, check at the beginning of the detection code if this is an NVIDIA card, and just return if it isn't. This, together with commit d22915d22ded ("drm/nouveau/devinit/tu102-: wait for GFW_BOOT_PROGRESS == COMPLETED") developed independently and landed earlier, fixes runtime power management of the NVIDIA card in Lenovo Legion 5-15ARH05. Without this patch, the GPU resumption code will "timeout", sometimes hanging userspace. As a bonus, we'll also stop preventing _PR3 usage from the bridge for unrelated devices, which is always nice, I guess. Fixes: ccfc2d5cdb02 ("drm/nouveau: Use generic helper to check _PR3 presence") Signed-off-by: Ratchanan Srirattanamet Closes: https://gitlab.freedesktop.org/drm/nouveau/-/issues/79 Reviewed-by: Karol Herbst Signed-off-by: Karol Herbst Link: https://patchwork.freedesktop.org/patch/msgid/DM6PR19MB2780805D4BE1E3F9B3AC96D0BC409@DM6PR19MB2780.namprd19.prod.outlook.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/nouveau/nouveau_acpi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index 69a84d0197d0..7b946d44ab2c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -220,6 +220,9 @@ static void nouveau_dsm_pci_probe(struct pci_dev *pdev, acpi_handle *dhandle_out int optimus_funcs; struct pci_dev *parent_pdev; + if (pdev->vendor != PCI_VENDOR_ID_NVIDIA) + return; + *has_pr3 = false; parent_pdev = pci_upstream_bridge(pdev); if (parent_pdev) { From 5d43bb9b3e0c03751f69209ce277006499a9f747 Mon Sep 17 00:00:00 2001 From: Natalia Petrova Date: Fri, 12 May 2023 14:15:26 +0300 Subject: [PATCH 3575/4345] drm/nouveau/dp: check for NULL nv_connector->native_mode [ Upstream commit 20a2ce87fbaf81e4c3dcb631d738e423959eb320 ] Add checking for NULL before calling nouveau_connector_detect_depth() in nouveau_connector_get_modes() function because nv_connector->native_mode could be dereferenced there since connector pointer passed to nouveau_connector_detect_depth() and the same value of nv_connector->native_mode is used there. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: d4c2c99bdc83 ("drm/nouveau/dp: remove broken display depth function, use the improved one") Signed-off-by: Natalia Petrova Reviewed-by: Lyude Paul Signed-off-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20230512111526.82408-1-n.petrova@fintech.ru Signed-off-by: Sasha Levin --- drivers/gpu/drm/nouveau/nouveau_connector.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 9542fc63e796..7478f2a1411e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -946,7 +946,7 @@ nouveau_connector_get_modes(struct drm_connector *connector) /* Determine display colour depth for everything except LVDS now, * DP requires this before mode_valid() is called. */ - if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS) + if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode) nouveau_connector_detect_depth(connector); /* Find the native mode if this is a digital panel, if we didn't @@ -967,7 +967,7 @@ nouveau_connector_get_modes(struct drm_connector *connector) * "native" mode as some VBIOS tables require us to use the * pixel clock as part of the lookup... */ - if (connector->connector_type == DRM_MODE_CONNECTOR_LVDS) + if (connector->connector_type == DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode) nouveau_connector_detect_depth(connector); if (nv_encoder->dcb->type == DCB_OUTPUT_TV) From 6ab91d1adb5a57d7380e902ff3b89564f138c4e7 Mon Sep 17 00:00:00 2001 From: Natalia Petrova Date: Fri, 12 May 2023 13:33:20 +0300 Subject: [PATCH 3576/4345] drm/nouveau: add nv_encoder pointer check for NULL [ Upstream commit 55b94bb8c42464bad3d2217f6874aa1a85664eac ] Pointer nv_encoder could be dereferenced at nouveau_connector.c in case it's equal to NULL by jumping to goto label. This patch adds a NULL-check to avoid it. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 3195c5f9784a ("drm/nouveau: set encoder for lvds") Signed-off-by: Natalia Petrova Reviewed-by: Lyude Paul [Fixed patch title] Signed-off-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20230512103320.82234-1-n.petrova@fintech.ru Signed-off-by: Sasha Levin --- drivers/gpu/drm/nouveau/nouveau_connector.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 7478f2a1411e..b8884272d65e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -726,7 +726,8 @@ out: #endif nouveau_connector_set_edid(nv_connector, edid); - nouveau_connector_set_encoder(connector, nv_encoder); + if (nv_encoder) + nouveau_connector_set_encoder(connector, nv_encoder); return status; } From efed5b50f3b835b7e12459f5a77b99931215596c Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Wed, 14 Jun 2023 12:02:55 +0200 Subject: [PATCH 3577/4345] ext4: drop the call to ext4_error() from ext4_get_group_info() [ Upstream commit f451fd97dd2b78f286379203a47d9d295c467255 ] A recent patch added a call to ext4_error() which is problematic since some callers of the ext4_get_group_info() function may be holding a spinlock, whereas ext4_error() must never be called in atomic context. This triggered a report from Syzbot: "BUG: sleeping function called from invalid context in ext4_update_super" (see the link below). Therefore, drop the call to ext4_error() from ext4_get_group_info(). In the meantime use eight characters tabs instead of nine characters ones. Reported-by: syzbot+4acc7d910e617b360859@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/00000000000070575805fdc6cdb2@google.com/ Fixes: 5354b2af3406 ("ext4: allow ext4_get_group_info() to fail") Suggested-by: Theodore Ts'o Signed-off-by: Fabio M. De Francesco Link: https://lore.kernel.org/r/20230614100446.14337-1-fmdefrancesco@gmail.com Signed-off-by: Sasha Levin --- fs/ext4/balloc.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index a43167042b6b..4efe71efe127 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -322,17 +322,15 @@ static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, struct ext4_group_info *ext4_get_group_info(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info **grp_info; - long indexv, indexh; + struct ext4_group_info **grp_info; + long indexv, indexh; - if (unlikely(group >= EXT4_SB(sb)->s_groups_count)) { - ext4_error(sb, "invalid group %u", group); - return NULL; - } - indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); - indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); - return grp_info[indexh]; + if (unlikely(group >= EXT4_SB(sb)->s_groups_count)) + return NULL; + indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); + indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); + grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); + return grp_info[indexh]; } /* From 6ee3728ae87eaf86ff693ec1440e0bf96a513eec Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 12 Jun 2023 11:34:26 +0200 Subject: [PATCH 3578/4345] net/sched: cls_api: Fix lockup on flushing explicitly created chain [ Upstream commit c9a82bec02c339cdda99b37c5e62b3b71fc4209c ] Mingshuai Ren reports: When a new chain is added by using tc, one soft lockup alarm will be generated after delete the prio 0 filter of the chain. To reproduce the problem, perform the following steps: (1) tc qdisc add dev eth0 root handle 1: htb default 1 (2) tc chain add dev eth0 (3) tc filter del dev eth0 chain 0 parent 1: prio 0 (4) tc filter add dev eth0 chain 0 parent 1: Fix the issue by accounting for additional reference to chains that are explicitly created by RTM_NEWCHAIN message as opposed to implicitly by RTM_NEWTFILTER message. Fixes: 726d061286ce ("net: sched: prevent insertion of new classifiers during chain flush") Reported-by: Mingshuai Ren Closes: https://lore.kernel.org/lkml/87legswvi3.fsf@nvidia.com/T/ Signed-off-by: Vlad Buslov Link: https://lore.kernel.org/r/20230612093426.2867183-1-vladbu@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/cls_api.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index befe42aad04b..beedd0d2b509 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -533,8 +533,8 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, { struct tcf_block *block = chain->block; const struct tcf_proto_ops *tmplt_ops; + unsigned int refcnt, non_act_refcnt; bool free_block = false; - unsigned int refcnt; void *tmplt_priv; mutex_lock(&block->lock); @@ -554,13 +554,15 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, * save these to temporary variables. */ refcnt = --chain->refcnt; + non_act_refcnt = refcnt - chain->action_refcnt; tmplt_ops = chain->tmplt_ops; tmplt_priv = chain->tmplt_priv; - /* The last dropped non-action reference will trigger notification. */ - if (refcnt - chain->action_refcnt == 0 && !by_act) { - tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain->index, - block, NULL, 0, 0, false); + if (non_act_refcnt == chain->explicitly_created && !by_act) { + if (non_act_refcnt == 0) + tc_chain_notify_delete(tmplt_ops, tmplt_priv, + chain->index, block, NULL, 0, 0, + false); /* Last reference to chain, no need to lock. */ chain->flushing = false; } From 5fd696b404fb1d6db749d2e4f1195495d832351a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 14 Jun 2023 16:18:02 +0000 Subject: [PATCH 3579/4345] net: lapbether: only support ethernet devices [ Upstream commit 9eed321cde22fc1afd76eac563ce19d899e0d6b2 ] It probbaly makes no sense to support arbitrary network devices for lapbether. syzbot reported: skbuff: skb_under_panic: text:ffff80008934c100 len:44 put:40 head:ffff0000d18dd200 data:ffff0000d18dd1ea tail:0x16 end:0x140 dev:bond1 kernel BUG at net/core/skbuff.c:200 ! Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 5643 Comm: dhcpcd Not tainted 6.4.0-rc5-syzkaller-g4641cff8e810 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023 pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : skb_panic net/core/skbuff.c:196 [inline] pc : skb_under_panic+0x13c/0x140 net/core/skbuff.c:210 lr : skb_panic net/core/skbuff.c:196 [inline] lr : skb_under_panic+0x13c/0x140 net/core/skbuff.c:210 sp : ffff8000973b7260 x29: ffff8000973b7270 x28: ffff8000973b7360 x27: dfff800000000000 x26: ffff0000d85d8150 x25: 0000000000000016 x24: ffff0000d18dd1ea x23: ffff0000d18dd200 x22: 000000000000002c x21: 0000000000000140 x20: 0000000000000028 x19: ffff80008934c100 x18: ffff8000973b68a0 x17: 0000000000000000 x16: ffff80008a43bfbc x15: 0000000000000202 x14: 0000000000000000 x13: 0000000000000001 x12: 0000000000000001 x11: 0000000000000201 x10: 0000000000000000 x9 : f22f7eb937cced00 x8 : f22f7eb937cced00 x7 : 0000000000000001 x6 : 0000000000000001 x5 : ffff8000973b6b78 x4 : ffff80008df9ee80 x3 : ffff8000805974f4 x2 : 0000000000000001 x1 : 0000000100000201 x0 : 0000000000000086 Call trace: skb_panic net/core/skbuff.c:196 [inline] skb_under_panic+0x13c/0x140 net/core/skbuff.c:210 skb_push+0xf0/0x108 net/core/skbuff.c:2409 ip6gre_header+0xbc/0x738 net/ipv6/ip6_gre.c:1383 dev_hard_header include/linux/netdevice.h:3137 [inline] lapbeth_data_transmit+0x1c4/0x298 drivers/net/wan/lapbether.c:257 lapb_data_transmit+0x8c/0xb0 net/lapb/lapb_iface.c:447 lapb_transmit_buffer+0x178/0x204 net/lapb/lapb_out.c:149 lapb_send_control+0x220/0x320 net/lapb/lapb_subr.c:251 lapb_establish_data_link+0x94/0xec lapb_device_event+0x348/0x4e0 notifier_call_chain+0x1a4/0x510 kernel/notifier.c:93 raw_notifier_call_chain+0x3c/0x50 kernel/notifier.c:461 __dev_notify_flags+0x2bc/0x544 dev_change_flags+0xd0/0x15c net/core/dev.c:8643 devinet_ioctl+0x858/0x17e4 net/ipv4/devinet.c:1150 inet_ioctl+0x2ac/0x4d8 net/ipv4/af_inet.c:979 sock_do_ioctl+0x134/0x2dc net/socket.c:1201 sock_ioctl+0x4ec/0x858 net/socket.c:1318 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __arm64_sys_ioctl+0x14c/0x1c8 fs/ioctl.c:856 __invoke_syscall arch/arm64/kernel/syscall.c:38 [inline] invoke_syscall+0x98/0x2c0 arch/arm64/kernel/syscall.c:52 el0_svc_common+0x138/0x244 arch/arm64/kernel/syscall.c:142 do_el0_svc+0x64/0x198 arch/arm64/kernel/syscall.c:191 el0_svc+0x4c/0x160 arch/arm64/kernel/entry-common.c:647 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:665 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:591 Code: aa1803e6 aa1903e7 a90023f5 947730f5 (d4210000) Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Martin Schiller Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/wan/lapbether.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index b965eb6a4bb1..24c53cc0c112 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -341,6 +341,9 @@ static int lapbeth_new_device(struct net_device *dev) ASSERT_RTNL(); + if (dev->type != ARPHRD_ETHER) + return -EINVAL; + ndev = alloc_netdev(sizeof(*lapbeth), "lapb%d", NET_NAME_UNKNOWN, lapbeth_setup); if (!ndev) From 08899e8d5a99d94ae2353f12fca090e80bca2d2d Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Wed, 14 Jun 2023 20:06:04 +0800 Subject: [PATCH 3580/4345] net: tipc: resize nlattr array to correct size [ Upstream commit 44194cb1b6045dea33ae9a0d54fb7e7cd93a2e09 ] According to nla_parse_nested_deprecated(), the tb[] is supposed to the destination array with maxtype+1 elements. In current tipc_nl_media_get() and __tipc_nl_media_set(), a larger array is used which is unnecessary. This patch resize them to a proper size. Fixes: 1e55417d8fc6 ("tipc: add media set to new netlink api") Fixes: 46f15c6794fb ("tipc: add media get/dump to new netlink api") Signed-off-by: Lin Ma Reviewed-by: Florian Westphal Reviewed-by: Tung Nguyen Link: https://lore.kernel.org/r/20230614120604.1196377-1-linma@zju.edu.cn Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/tipc/bearer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 91e678fa3feb..df6aba2246fa 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1242,7 +1242,7 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) struct tipc_nl_msg msg; struct tipc_media *media; struct sk_buff *rep; - struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; @@ -1291,7 +1291,7 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) int err; char *name; struct tipc_media *m; - struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; From 49b6607dedc238db3bb0e838801f39a936461d84 Mon Sep 17 00:00:00 2001 From: Alex Maftei Date: Thu, 15 Jun 2023 09:34:04 +0100 Subject: [PATCH 3581/4345] selftests/ptp: Fix timestamp printf format for PTP_SYS_OFFSET [ Upstream commit 76a4c8b82938bc5020b67663db41f451684bf327 ] Previously, timestamps were printed using "%lld.%u" which is incorrect for nanosecond values lower than 100,000,000 as they're fractional digits, therefore leading zeros are meaningful. This patch changes the format strings to "%lld.%09u" in order to add leading zeros to the nanosecond value. Fixes: 568ebc5985f5 ("ptp: add the PTP_SYS_OFFSET ioctl to the testptp program") Fixes: 4ec54f95736f ("ptp: Fix compiler warnings in the testptp utility") Fixes: 6ab0e475f1f3 ("Documentation: fix misc. warnings") Signed-off-by: Alex Maftei Acked-by: Richard Cochran Link: https://lore.kernel.org/r/20230615083404.57112-1-alex.maftei@amd.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- tools/testing/selftests/ptp/testptp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index f7911aaeb007..aa474febb471 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -492,11 +492,11 @@ int main(int argc, char *argv[]) interval = t2 - t1; offset = (t2 + t1) / 2 - tp; - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i)->sec, (pct+2*i)->nsec); - printf("phc time: %lld.%u\n", + printf("phc time: %lld.%09u\n", (pct+2*i+1)->sec, (pct+2*i+1)->nsec); - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i+2)->sec, (pct+2*i+2)->nsec); printf("system/phc clock time offset is %" PRId64 " ns\n" "system clock time delay is %" PRId64 " ns\n", From 4c10843863321d87c7be82332e9f848cac8f896c Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 16 Jun 2023 22:39:39 +0100 Subject: [PATCH 3582/4345] afs: Fix vlserver probe RTT handling [ Upstream commit ba00b190670809c1a89326d80de96d714f6004f2 ] In the same spirit as commit ca57f02295f1 ("afs: Fix fileserver probe RTT handling"), don't rule out using a vlserver just because there haven't been enough packets yet to calculate a real rtt. Always set the server's probe rtt from the estimate provided by rxrpc_kernel_get_srtt, which is capped at 1 second. This could lead to EDESTADDRREQ errors when accessing a cell for the first time, even though the vl servers are known and have responded to a probe. Fixes: 1d4adfaf6574 ("rxrpc: Make rxrpc_kernel_get_srtt() indicate validity") Signed-off-by: Marc Dionne Signed-off-by: David Howells cc: linux-afs@lists.infradead.org Link: http://lists.infradead.org/pipermail/linux-afs/2023-June/006746.html Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- fs/afs/vl_probe.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index d1c7068b4346..58452b86e672 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -115,8 +115,8 @@ responded: } } - if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && - rtt_us < server->probe.rtt) { + rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us); + if (rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; server->rtt = rtt_us; alist->preferred = index; From a261589621764519207ab07c898c1e7d6b78fc1f Mon Sep 17 00:00:00 2001 From: John Sperbeck Date: Sun, 21 May 2023 19:29:53 +0000 Subject: [PATCH 3583/4345] cgroup: always put cset in cgroup_css_set_put_fork commit 2bd110339288c18823dcace602b63b0d8627e520 upstream. A successful call to cgroup_css_set_fork() will always have taken a ref on kargs->cset (regardless of CLONE_INTO_CGROUP), so always do a corresponding put in cgroup_css_set_put_fork(). Without this, a cset and its contained css structures will be leaked for some fork failures. The following script reproduces the leak for a fork failure due to exceeding pids.max in the pids controller. A similar thing can happen if we jump to the bad_fork_cancel_cgroup label in copy_process(). [ -z "$1" ] && echo "Usage $0 pids-root" && exit 1 PID_ROOT=$1 CGROUP=$PID_ROOT/foo [ -e $CGROUP ] && rmdir -f $CGROUP mkdir $CGROUP echo 5 > $CGROUP/pids.max echo $$ > $CGROUP/cgroup.procs fork_bomb() { set -e for i in $(seq 10); do /bin/sleep 3600 & done } (fork_bomb) & wait echo $$ > $PID_ROOT/cgroup.procs kill $(cat $CGROUP/cgroup.procs) rmdir $CGROUP Fixes: ef2c41cf38a7 ("clone3: allow spawning processes into cgroups") Cc: stable@vger.kernel.org # v5.7+ Signed-off-by: John Sperbeck Signed-off-by: Tejun Heo [TJM: This backport accommodates the lack of cgroup_unlock] Signed-off-by: T.J. Mercier Signed-off-by: Greg Kroah-Hartman --- kernel/cgroup/cgroup.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 684c16849eff..f123b7f64249 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6138,19 +6138,18 @@ err: static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { + struct cgroup *cgrp = kargs->cgrp; + struct css_set *cset = kargs->cset; + cgroup_threadgroup_change_end(current); + if (cset) { + put_css_set(cset); + kargs->cset = NULL; + } + if (kargs->flags & CLONE_INTO_CGROUP) { - struct cgroup *cgrp = kargs->cgrp; - struct css_set *cset = kargs->cset; - mutex_unlock(&cgroup_mutex); - - if (cset) { - put_css_set(cset); - kargs->cset = NULL; - } - if (cgrp) { cgroup_put(cgrp); kargs->cgrp = NULL; From 7230a9e599d30d0fac0d57d866e0e79478e8f0a7 Mon Sep 17 00:00:00 2001 From: Ziwei Dai Date: Fri, 31 Mar 2023 20:42:09 +0800 Subject: [PATCH 3584/4345] rcu/kvfree: Avoid freeing new kfree_rcu() memory after old grace period commit 5da7cb193db32da783a3f3e77d8b639989321d48 upstream. Memory passed to kvfree_rcu() that is to be freed is tracked by a per-CPU kfree_rcu_cpu structure, which in turn contains pointers to kvfree_rcu_bulk_data structures that contain pointers to memory that has not yet been handed to RCU, along with an kfree_rcu_cpu_work structure that tracks the memory that has already been handed to RCU. These structures track three categories of memory: (1) Memory for kfree(), (2) Memory for kvfree(), and (3) Memory for both that arrived during an OOM episode. The first two categories are tracked in a cache-friendly manner involving a dynamically allocated page of pointers (the aforementioned kvfree_rcu_bulk_data structures), while the third uses a simple (but decidedly cache-unfriendly) linked list through the rcu_head structures in each block of memory. On a given CPU, these three categories are handled as a unit, with that CPU's kfree_rcu_cpu_work structure having one pointer for each of the three categories. Clearly, new memory for a given category cannot be placed in the corresponding kfree_rcu_cpu_work structure until any old memory has had its grace period elapse and thus has been removed. And the kfree_rcu_monitor() function does in fact check for this. Except that the kfree_rcu_monitor() function checks these pointers one at a time. This means that if the previous kfree_rcu() memory passed to RCU had only category 1 and the current one has only category 2, the kfree_rcu_monitor() function will send that current category-2 memory along immediately. This can result in memory being freed too soon, that is, out from under unsuspecting RCU readers. To see this, consider the following sequence of events, in which: o Task A on CPU 0 calls rcu_read_lock(), then uses "from_cset", then is preempted. o CPU 1 calls kfree_rcu(cset, rcu_head) in order to free "from_cset" after a later grace period. Except that "from_cset" is freed right after the previous grace period ended, so that "from_cset" is immediately freed. Task A resumes and references "from_cset"'s member, after which nothing good happens. In full detail: CPU 0 CPU 1 ---------------------- ---------------------- count_memcg_event_mm() |rcu_read_lock() <--- |mem_cgroup_from_task() |// css_set_ptr is the "from_cset" mentioned on CPU 1 |css_set_ptr = rcu_dereference((task)->cgroups) |// Hard irq comes, current task is scheduled out. cgroup_attach_task() |cgroup_migrate() |cgroup_migrate_execute() |css_set_move_task(task, from_cset, to_cset, true) |cgroup_move_task(task, to_cset) |rcu_assign_pointer(.., to_cset) |... |cgroup_migrate_finish() |put_css_set_locked(from_cset) |from_cset->refcount return 0 |kfree_rcu(cset, rcu_head) // free from_cset after new gp |add_ptr_to_bulk_krc_lock() |schedule_delayed_work(&krcp->monitor_work, ..) kfree_rcu_monitor() |krcp->bulk_head[0]'s work attached to krwp->bulk_head_free[] |queue_rcu_work(system_wq, &krwp->rcu_work) |if rwork->rcu.work is not in WORK_STRUCT_PENDING_BIT state, |call_rcu(&rwork->rcu, rcu_work_rcufn) <--- request new gp // There is a perious call_rcu(.., rcu_work_rcufn) // gp end, rcu_work_rcufn() is called. rcu_work_rcufn() |__queue_work(.., rwork->wq, &rwork->work); |kfree_rcu_work() |krwp->bulk_head_free[0] bulk is freed before new gp end!!! |The "from_cset" is freed before new gp end. // the task resumes some time later. |css_set_ptr->subsys[(subsys_id) <--- Caused kernel crash, because css_set_ptr is freed. This commit therefore causes kfree_rcu_monitor() to refrain from moving kfree_rcu() memory to the kfree_rcu_cpu_work structure until the RCU grace period has completed for all three categories. v2: Use helper function instead of inserted code block at kfree_rcu_monitor(). Fixes: 34c881745549 ("rcu: Support kfree_bulk() interface in kfree_rcu()") Fixes: 5f3c8d620447 ("rcu/tree: Maintain separate array for vmalloc ptrs") Reported-by: Mukesh Ojha Signed-off-by: Ziwei Dai Reviewed-by: Uladzislau Rezki (Sony) Tested-by: Uladzislau Rezki (Sony) Signed-off-by: Paul E. McKenney Signed-off-by: Suren Baghdasaryan Signed-off-by: Greg Kroah-Hartman --- kernel/rcu/tree.c | 49 +++++++++++++++++++++++++++++++++-------------- 1 file changed, 35 insertions(+), 14 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 30e1d7fedb5f..eec8e2f7537e 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3281,6 +3281,30 @@ static void kfree_rcu_work(struct work_struct *work) } } +static bool +need_offload_krc(struct kfree_rcu_cpu *krcp) +{ + int i; + + for (i = 0; i < FREE_N_CHANNELS; i++) + if (krcp->bkvhead[i]) + return true; + + return !!krcp->head; +} + +static bool +need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp) +{ + int i; + + for (i = 0; i < FREE_N_CHANNELS; i++) + if (krwp->bkvhead_free[i]) + return true; + + return !!krwp->head_free; +} + /* * Schedule the kfree batch RCU work to run in workqueue context after a GP. * @@ -3298,16 +3322,13 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) for (i = 0; i < KFREE_N_BATCHES; i++) { krwp = &(krcp->krw_arr[i]); - /* - * Try to detach bkvhead or head and attach it over any - * available corresponding free channel. It can be that - * a previous RCU batch is in progress, it means that - * immediately to queue another one is not possible so - * return false to tell caller to retry. - */ - if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) || - (krcp->bkvhead[1] && !krwp->bkvhead_free[1]) || - (krcp->head && !krwp->head_free)) { + // Try to detach bulk_head or head and attach it, only when + // all channels are free. Any channel is not free means at krwp + // there is on-going rcu work to handle krwp's free business. + if (need_wait_for_krwp_work(krwp)) + continue; + + if (need_offload_krc(krcp)) { // Channel 1 corresponds to SLAB ptrs. // Channel 2 corresponds to vmalloc ptrs. for (j = 0; j < FREE_N_CHANNELS; j++) { @@ -3334,12 +3355,12 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) */ queue_rcu_work(system_wq, &krwp->rcu_work); } - - // Repeat if any "free" corresponding channel is still busy. - if (krcp->bkvhead[0] || krcp->bkvhead[1] || krcp->head) - repeat = true; } + // Repeat if any "free" corresponding channel is still busy. + if (need_offload_krc(krcp)) + repeat = true; + return !repeat; } From 53076071fb92a46119ba7f4e3369f1e7a5237f9c Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 22 Sep 2022 16:38:55 +0800 Subject: [PATCH 3585/4345] neighbour: Remove unused inline function neigh_key_eq16() commit c8f01a4a54473f88f8cc0d9046ec9eb5a99815d5 upstream. All uses of neigh_key_eq16() have been removed since commit 1202cdd66531 ("Remove DECnet support from kernel"), so remove it. Signed-off-by: Gaosheng Cui Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/neighbour.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index abb22cfd4827..8cce830d88d8 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -260,11 +260,6 @@ static inline void *neighbour_priv(const struct neighbour *n) extern const struct nla_policy nda_policy[]; -static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey) -{ - return *(const u16 *)n->primary_key == *(const u16 *)pkey; -} - static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) { return *(const u32 *)n->primary_key == *(const u32 *)pkey; From 7d07fd03f50c2048abe4c45719630de3b9613c46 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Thu, 22 Sep 2022 16:38:57 +0800 Subject: [PATCH 3586/4345] net: Remove unused inline function dst_hold_and_use() commit 0b81882ddf8ac2743f657afb001beec7fc3929af upstream. All uses of dst_hold_and_use() have been removed since commit 1202cdd66531 ("Remove DECnet support from kernel"), so remove it. Signed-off-by: Gaosheng Cui Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/dst.h | 6 ------ 1 file changed, 6 deletions(-) diff --git a/include/net/dst.h b/include/net/dst.h index ae2cf57d796b..48e613420b95 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -235,12 +235,6 @@ static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) } } -static inline void dst_hold_and_use(struct dst_entry *dst, unsigned long time) -{ - dst_hold(dst); - dst_use_noref(dst, time); -} - static inline struct dst_entry *dst_clone(struct dst_entry *dst) { if (dst) From bf82668eb950e3ca977b5f92bcb1a756db5563dc Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 30 Sep 2022 16:37:30 +0200 Subject: [PATCH 3587/4345] net: Remove DECnet leftovers from flow.h. commit 9bc61c04ff6cce6a3756b86e6b34914f7b39d734 upstream. DECnet was removed by commit 1202cdd66531 ("Remove DECnet support from kernel"). Let's also revome its flow structure. Compile-tested only (allmodconfig). Signed-off-by: Guillaume Nault Acked-by: Stephen Hemminger Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/flow.h | 26 -------------------------- 1 file changed, 26 deletions(-) diff --git a/include/net/flow.h b/include/net/flow.h index 39d0cedcddee..236d0941c69f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -54,11 +54,6 @@ union flowi_uli { __u8 code; } icmpt; - struct { - __le16 dport; - __le16 sport; - } dnports; - __be32 spi; __be32 gre_key; @@ -156,27 +151,11 @@ struct flowi6 { __u32 mp_hash; } __attribute__((__aligned__(BITS_PER_LONG/8))); -struct flowidn { - struct flowi_common __fl_common; -#define flowidn_oif __fl_common.flowic_oif -#define flowidn_iif __fl_common.flowic_iif -#define flowidn_mark __fl_common.flowic_mark -#define flowidn_scope __fl_common.flowic_scope -#define flowidn_proto __fl_common.flowic_proto -#define flowidn_flags __fl_common.flowic_flags - __le16 daddr; - __le16 saddr; - union flowi_uli uli; -#define fld_sport uli.ports.sport -#define fld_dport uli.ports.dport -} __attribute__((__aligned__(BITS_PER_LONG/8))); - struct flowi { union { struct flowi_common __fl_common; struct flowi4 ip4; struct flowi6 ip6; - struct flowidn dn; } u; #define flowi_oif u.__fl_common.flowic_oif #define flowi_iif u.__fl_common.flowic_iif @@ -210,11 +189,6 @@ static inline struct flowi_common *flowi6_to_flowi_common(struct flowi6 *fl6) return &(flowi6_to_flowi(fl6)->u.__fl_common); } -static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn) -{ - return container_of(fldn, struct flowi, u.dn); -} - __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys); #endif From e6104284c42fd4659cab90b3ee9be0fa2e3d7ee1 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 8 Mar 2023 11:23:13 +0200 Subject: [PATCH 3588/4345] neighbour: delete neigh_lookup_nodev as not used commit 76b9bf965c98c9b53ef7420b3b11438dbd764f92 upstream. neigh_lookup_nodev isn't used in the kernel after removal of DECnet. So let's remove it. Fixes: 1202cdd66531 ("Remove DECnet support from kernel") Signed-off-by: Leon Romanovsky Reviewed-by: Eric Dumazet Reviewed-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/eb5656200d7964b2d177a36b77efa3c597d6d72d.1678267343.git.leonro@nvidia.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/neighbour.h | 2 -- net/core/neighbour.c | 31 ------------------------------- 2 files changed, 33 deletions(-) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 8cce830d88d8..0e9d33e4439e 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -309,8 +309,6 @@ void neigh_table_init(int index, struct neigh_table *tbl); int neigh_table_clear(int index, struct neigh_table *tbl); struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev); -struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, - const void *pkey); struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref); static inline struct neighbour *neigh_create(struct neigh_table *tbl, diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6addfb4fff72..3b642c412cf3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -571,37 +571,6 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, } EXPORT_SYMBOL(neigh_lookup); -struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, - const void *pkey) -{ - struct neighbour *n; - unsigned int key_len = tbl->key_len; - u32 hash_val; - struct neigh_hash_table *nht; - - NEIGH_CACHE_STAT_INC(tbl, lookups); - - rcu_read_lock_bh(); - nht = rcu_dereference_bh(tbl->nht); - hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) >> (32 - nht->hash_shift); - - for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference_bh(n->next)) { - if (!memcmp(n->primary_key, pkey, key_len) && - net_eq(dev_net(n->dev), net)) { - if (!refcount_inc_not_zero(&n->refcnt)) - n = NULL; - NEIGH_CACHE_STAT_INC(tbl, hits); - break; - } - } - - rcu_read_unlock_bh(); - return n; -} -EXPORT_SYMBOL(neigh_lookup_nodev); - static struct neighbour * ___neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, u8 flags, From 7ce0e8b287204dd0b8c9ca001da16b8f6658ceee Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Fri, 23 Jul 2021 19:23:17 +0200 Subject: [PATCH 3589/4345] batman-adv: Switch to kstrtox.h for kstrtou64 commit 55207227189a07513ba4107d72e256313a66a2f3 upstream. The commit 4c52729377ea ("kernel.h: split out kstrtox() and simple_strtox() to a separate header") moved the kstrtou64 function to a new header called linux/kstrtox.h. Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/gateway_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 16cd9450ceb1..d65ff10076d6 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include #include From e6dc6a9d0a760b7d4dd62cc6452f85f6eee45bff Mon Sep 17 00:00:00 2001 From: Christian Loehle Date: Wed, 26 Apr 2023 16:59:39 +0000 Subject: [PATCH 3590/4345] mmc: block: ensure error propagation for non-blk commit 003fb0a51162d940f25fc35e70b0996a12c9e08a upstream. Requests to the mmc layer usually come through a block device IO. The exceptions are the ioctl interface, RPMB chardev ioctl and debugfs, which issue their own blk_mq requests through blk_execute_rq and do not query the BLK_STS error but the mmcblk-internal drv_op_result. This patch ensures that drv_op_result defaults to an error and has to be overwritten by the operation to be considered successful. The behavior leads to a bug where the request never propagates the error, e.g. by directly erroring out at mmc_blk_mq_issue_rq if mmc_blk_part_switch fails. The ioctl caller of the rpmb chardev then can never see an error (BLK_STS_IOERR, but drv_op_result is unchanged) and thus may assume that their call executed successfully when it did not. While always checking the blk_execute_rq return value would be advised, let's eliminate the error by always setting drv_op_result as -EIO to be overwritten on success (or other error) Fixes: 614f0388f580 ("mmc: block: move single ioctl() commands to block requests") Signed-off-by: Christian Loehle Acked-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/59c17ada35664b818b7bd83752119b2d@hyperstone.com Signed-off-by: Ulf Hansson Signed-off-by: Christian Loehle Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/core/block.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 6622e3262187..599b7317b59a 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -253,6 +253,7 @@ static ssize_t power_ro_lock_store(struct device *dev, goto out_put; } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; blk_execute_rq(mq->queue, NULL, req, 0); ret = req_to_mmc_queue_req(req)->drv_op_result; blk_put_request(req); @@ -638,6 +639,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md, idatas[0] = idata; req_to_mmc_queue_req(req)->drv_op = rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = idatas; req_to_mmc_queue_req(req)->ioc_count = 1; blk_execute_rq(mq->queue, NULL, req, 0); @@ -707,6 +709,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, } req_to_mmc_queue_req(req)->drv_op = rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = idata; req_to_mmc_queue_req(req)->ioc_count = num_of_cmds; blk_execute_rq(mq->queue, NULL, req, 0); @@ -2749,6 +2752,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val) if (IS_ERR(req)) return PTR_ERR(req); req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; blk_execute_rq(mq->queue, NULL, req, 0); ret = req_to_mmc_queue_req(req)->drv_op_result; if (ret >= 0) { @@ -2787,6 +2791,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp) goto out_free; } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = &ext_csd; blk_execute_rq(mq->queue, NULL, req, 0); err = req_to_mmc_queue_req(req)->drv_op_result; From c374552b54d6fd93e048e834bb48c1c079a51f2e Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 12 Nov 2020 14:38:13 +0100 Subject: [PATCH 3591/4345] mm/memory_hotplug: extend offline_and_remove_memory() to handle more than one memory block commit 8dc4bb58a146655eb057247d7c9d19e73928715b upstream. virtio-mem soon wants to use offline_and_remove_memory() memory that exceeds a single Linux memory block (memory_block_size_bytes()). Let's remove that restriction. Let's remember the old state and try to restore that if anything goes wrong. While re-onlining can, in general, fail, it's highly unlikely to happen (usually only when a notifier fails to allocate memory, and these are rather rare). This will be used by virtio-mem to offline+remove memory ranges that are bigger than a single memory block - for example, with a device block size of 1 GiB (e.g., gigantic pages in the hypervisor) and a Linux memory block size of 128MB. While we could compress the state into 2 bit, using 8 bit is much easier. This handling is similar, but different to acpi_scan_try_to_offline(): a) We don't try to offline twice. I am not sure if this CONFIG_MEMCG optimization is still relevant - it should only apply to ZONE_NORMAL (where we have no guarantees). If relevant, we can always add it. b) acpi_scan_try_to_offline() simply onlines all memory in case something goes wrong. It doesn't restore previous online type. Let's do that, so we won't overwrite what e.g., user space configured. Reviewed-by: Wei Yang Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Pankaj Gupta Cc: Michal Hocko Cc: Oscar Salvador Cc: Wei Yang Cc: Andrew Morton Signed-off-by: David Hildenbrand Link: https://lore.kernel.org/r/20201112133815.13332-28-david@redhat.com Signed-off-by: Michael S. Tsirkin Acked-by: Andrew Morton Signed-off-by: Ma Wupeng Signed-off-by: Greg Kroah-Hartman --- mm/memory_hotplug.c | 109 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 91 insertions(+), 18 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f0633f9a9116..9ec9e1e67705 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1788,39 +1788,112 @@ int remove_memory(int nid, u64 start, u64 size) } EXPORT_SYMBOL_GPL(remove_memory); +static int try_offline_memory_block(struct memory_block *mem, void *arg) +{ + uint8_t online_type = MMOP_ONLINE_KERNEL; + uint8_t **online_types = arg; + struct page *page; + int rc; + + /* + * Sense the online_type via the zone of the memory block. Offlining + * with multiple zones within one memory block will be rejected + * by offlining code ... so we don't care about that. + */ + page = pfn_to_online_page(section_nr_to_pfn(mem->start_section_nr)); + if (page && zone_idx(page_zone(page)) == ZONE_MOVABLE) + online_type = MMOP_ONLINE_MOVABLE; + + rc = device_offline(&mem->dev); + /* + * Default is MMOP_OFFLINE - change it only if offlining succeeded, + * so try_reonline_memory_block() can do the right thing. + */ + if (!rc) + **online_types = online_type; + + (*online_types)++; + /* Ignore if already offline. */ + return rc < 0 ? rc : 0; +} + +static int try_reonline_memory_block(struct memory_block *mem, void *arg) +{ + uint8_t **online_types = arg; + int rc; + + if (**online_types != MMOP_OFFLINE) { + mem->online_type = **online_types; + rc = device_online(&mem->dev); + if (rc < 0) + pr_warn("%s: Failed to re-online memory: %d", + __func__, rc); + } + + /* Continue processing all remaining memory blocks. */ + (*online_types)++; + return 0; +} + /* - * Try to offline and remove a memory block. Might take a long time to - * finish in case memory is still in use. Primarily useful for memory devices - * that logically unplugged all memory (so it's no longer in use) and want to - * offline + remove the memory block. + * Try to offline and remove memory. Might take a long time to finish in case + * memory is still in use. Primarily useful for memory devices that logically + * unplugged all memory (so it's no longer in use) and want to offline + remove + * that memory. */ int offline_and_remove_memory(int nid, u64 start, u64 size) { - struct memory_block *mem; - int rc = -EINVAL; + const unsigned long mb_count = size / memory_block_size_bytes(); + uint8_t *online_types, *tmp; + int rc; if (!IS_ALIGNED(start, memory_block_size_bytes()) || - size != memory_block_size_bytes()) - return rc; - - lock_device_hotplug(); - mem = find_memory_block(__pfn_to_section(PFN_DOWN(start))); - if (mem) - rc = device_offline(&mem->dev); - /* Ignore if the device is already offline. */ - if (rc > 0) - rc = 0; + !IS_ALIGNED(size, memory_block_size_bytes()) || !size) + return -EINVAL; /* - * In case we succeeded to offline the memory block, remove it. + * We'll remember the old online type of each memory block, so we can + * try to revert whatever we did when offlining one memory block fails + * after offlining some others succeeded. + */ + online_types = kmalloc_array(mb_count, sizeof(*online_types), + GFP_KERNEL); + if (!online_types) + return -ENOMEM; + /* + * Initialize all states to MMOP_OFFLINE, so when we abort processing in + * try_offline_memory_block(), we'll skip all unprocessed blocks in + * try_reonline_memory_block(). + */ + memset(online_types, MMOP_OFFLINE, mb_count); + + lock_device_hotplug(); + + tmp = online_types; + rc = walk_memory_blocks(start, size, &tmp, try_offline_memory_block); + + /* + * In case we succeeded to offline all memory, remove it. * This cannot fail as it cannot get onlined in the meantime. */ if (!rc) { rc = try_remove_memory(nid, start, size); - WARN_ON_ONCE(rc); + if (rc) + pr_err("%s: Failed to remove memory: %d", __func__, rc); + } + + /* + * Rollback what we did. While memory onlining might theoretically fail + * (nacked by a notifier), it barely ever happens. + */ + if (rc) { + tmp = online_types; + walk_memory_blocks(start, size, &tmp, + try_reonline_memory_block); } unlock_device_hotplug(); + kfree(online_types); return rc; } EXPORT_SYMBOL_GPL(offline_and_remove_memory); From a13dee47fa2a5799999fb3c104939d751f16810d Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 26 May 2023 11:13:32 +0900 Subject: [PATCH 3592/4345] nilfs2: reject devices with insufficient block count commit 92c5d1b860e9581d64baca76779576c0ab0d943d upstream. The current sanity check for nilfs2 geometry information lacks checks for the number of segments stored in superblocks, so even for device images that have been destructively truncated or have an unusually high number of segments, the mount operation may succeed. This causes out-of-bounds block I/O on file system block reads or log writes to the segments, the latter in particular causing "a_ops->writepages" to repeatedly fail, resulting in sync_inodes_sb() to hang. Fix this issue by checking the number of segments stored in the superblock and avoiding mounting devices that can cause out-of-bounds accesses. To eliminate the possibility of overflow when calculating the number of blocks required for the device from the number of segments, this also adds a helper function to calculate the upper bound on the number of segments and inserts a check using it. Link: https://lkml.kernel.org/r/20230526021332.3431-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+7d50f1e54a12ba3aeae2@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=7d50f1e54a12ba3aeae2 Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/the_nilfs.c | 44 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 43 insertions(+), 1 deletion(-) diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index d8d08fa5c340..1566e86e8e55 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -405,6 +405,18 @@ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs) 100)); } +/** + * nilfs_max_segment_count - calculate the maximum number of segments + * @nilfs: nilfs object + */ +static u64 nilfs_max_segment_count(struct the_nilfs *nilfs) +{ + u64 max_count = U64_MAX; + + do_div(max_count, nilfs->ns_blocks_per_segment); + return min_t(u64, max_count, ULONG_MAX); +} + void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) { nilfs->ns_nsegments = nsegs; @@ -414,6 +426,8 @@ void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) static int nilfs_store_disk_layout(struct the_nilfs *nilfs, struct nilfs_super_block *sbp) { + u64 nsegments, nblocks; + if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) { nilfs_err(nilfs->ns_sb, "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).", @@ -457,7 +471,35 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, return -EINVAL; } - nilfs_set_nsegments(nilfs, le64_to_cpu(sbp->s_nsegments)); + nsegments = le64_to_cpu(sbp->s_nsegments); + if (nsegments > nilfs_max_segment_count(nilfs)) { + nilfs_err(nilfs->ns_sb, + "segment count %llu exceeds upper limit (%llu segments)", + (unsigned long long)nsegments, + (unsigned long long)nilfs_max_segment_count(nilfs)); + return -EINVAL; + } + + nblocks = (u64)i_size_read(nilfs->ns_sb->s_bdev->bd_inode) >> + nilfs->ns_sb->s_blocksize_bits; + if (nblocks) { + u64 min_block_count = nsegments * nilfs->ns_blocks_per_segment; + /* + * To avoid failing to mount early device images without a + * second superblock, exclude that block count from the + * "min_block_count" calculation. + */ + + if (nblocks < min_block_count) { + nilfs_err(nilfs->ns_sb, + "total number of segment blocks %llu exceeds device size (%llu blocks)", + (unsigned long long)min_block_count, + (unsigned long long)nblocks); + return -EINVAL; + } + } + + nilfs_set_nsegments(nilfs, nsegments); nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed); return 0; } From a1b26dac8bc6b1a8814594010f8808e0debc3dc1 Mon Sep 17 00:00:00 2001 From: Dinghao Liu Date: Mon, 12 Jun 2023 16:39:05 +0300 Subject: [PATCH 3593/4345] media: dvbdev: Fix memleak in dvb_register_device commit 167faadfcf9339088910e9e85a1b711fcbbef8e9 upstream. When device_create() fails, dvbdev and dvbdevfops should be freed just like when dvb_register_media_device() fails. Signed-off-by: Dinghao Liu Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman --- drivers/media/dvb-core/dvbdev.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index fea2d82300b0..52315434e0a9 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -545,6 +545,9 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, if (IS_ERR(clsdev)) { pr_err("%s: failed to create device dvb%d.%s%d (%ld)\n", __func__, adap->num, dnames[type], id, PTR_ERR(clsdev)); + dvb_media_device_free(dvbdev); + kfree(dvbdevfops); + kfree(dvbdev); return PTR_ERR(clsdev); } dprintk("DVB: register adapter%d/%s%d @ minor: %i (0x%02x)\n", From 5c61c3945adf14757a4d914633bbb47439484cce Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 12 Jun 2023 16:39:06 +0300 Subject: [PATCH 3594/4345] media: dvbdev: fix error logic at dvb_register_device() commit 1fec2ecc252301110e4149e6183fa70460d29674 upstream. As reported by smatch: drivers/media/dvb-core/dvbdev.c: drivers/media/dvb-core/dvbdev.c:510 dvb_register_device() warn: '&dvbdev->list_head' not removed from list drivers/media/dvb-core/dvbdev.c: drivers/media/dvb-core/dvbdev.c:530 dvb_register_device() warn: '&dvbdev->list_head' not removed from list drivers/media/dvb-core/dvbdev.c: drivers/media/dvb-core/dvbdev.c:545 dvb_register_device() warn: '&dvbdev->list_head' not removed from list The error logic inside dvb_register_device() doesn't remove devices from the dvb_adapter_list in case of errors. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman --- drivers/media/dvb-core/dvbdev.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index 52315434e0a9..6e2b7e97da17 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -511,6 +511,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, break; if (minor == MAX_DVB_MINORS) { + list_del (&dvbdev->list_head); kfree(dvbdevfops); kfree(dvbdev); up_write(&minor_rwsem); @@ -531,6 +532,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, __func__); dvb_media_device_free(dvbdev); + list_del (&dvbdev->list_head); kfree(dvbdevfops); kfree(dvbdev); mutex_unlock(&dvbdev_register_lock); @@ -546,6 +548,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, pr_err("%s: failed to create device dvb%d.%s%d (%ld)\n", __func__, adap->num, dnames[type], id, PTR_ERR(clsdev)); dvb_media_device_free(dvbdev); + list_del (&dvbdev->list_head); kfree(dvbdevfops); kfree(dvbdev); return PTR_ERR(clsdev); From 2d1c19597d1eb7f18c9d906aa7e144733eccdcc8 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Mon, 12 Jun 2023 16:39:07 +0300 Subject: [PATCH 3595/4345] media: dvb-core: Fix use-after-free due to race at dvb_register_device() commit 627bb528b086b4136315c25d6a447a98ea9448d3 upstream. dvb_register_device() dynamically allocates fops with kmemdup() to set the fops->owner. And these fops are registered in 'file->f_ops' using replace_fops() in the dvb_device_open() process, and kfree()d in dvb_free_device(). However, it is not common to use dynamically allocated fops instead of 'static const' fops as an argument of replace_fops(), and UAF may occur. These UAFs can occur on any dvb type using dvb_register_device(), such as dvb_dvr, dvb_demux, dvb_frontend, dvb_net, etc. So, instead of kfree() the fops dynamically allocated in dvb_register_device() in dvb_free_device() called during the .disconnect() process, kfree() it collectively in exit_dvbdev() called when the dvbdev.c module is removed. Link: https://lore.kernel.org/linux-media/20221117045925.14297-4-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman --- drivers/media/dvb-core/dvbdev.c | 84 ++++++++++++++++++++++++--------- include/media/dvbdev.h | 15 ++++++ 2 files changed, 78 insertions(+), 21 deletions(-) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index 6e2b7e97da17..2ff8a1b776fb 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -37,6 +37,7 @@ #include static DEFINE_MUTEX(dvbdev_mutex); +static LIST_HEAD(dvbdevfops_list); static int dvbdev_debug; module_param(dvbdev_debug, int, 0644); @@ -462,14 +463,15 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, enum dvb_device_type type, int demux_sink_pads) { struct dvb_device *dvbdev; - struct file_operations *dvbdevfops; + struct file_operations *dvbdevfops = NULL; + struct dvbdevfops_node *node = NULL, *new_node = NULL; struct device *clsdev; int minor; int id, ret; mutex_lock(&dvbdev_register_lock); - if ((id = dvbdev_get_free_id (adap, type)) < 0){ + if ((id = dvbdev_get_free_id (adap, type)) < 0) { mutex_unlock(&dvbdev_register_lock); *pdvbdev = NULL; pr_err("%s: couldn't find free device id\n", __func__); @@ -477,18 +479,45 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } *pdvbdev = dvbdev = kzalloc(sizeof(*dvbdev), GFP_KERNEL); - if (!dvbdev){ mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } - dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + /* + * When a device of the same type is probe()d more than once, + * the first allocated fops are used. This prevents memory leaks + * that can occur when the same device is probe()d repeatedly. + */ + list_for_each_entry(node, &dvbdevfops_list, list_head) { + if (node->fops->owner == adap->module && + node->type == type && + node->template == template) { + dvbdevfops = node->fops; + break; + } + } - if (!dvbdevfops){ - kfree (dvbdev); - mutex_unlock(&dvbdev_register_lock); - return -ENOMEM; + if (dvbdevfops == NULL) { + dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + if (!dvbdevfops) { + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node = kzalloc(sizeof(struct dvbdevfops_node), GFP_KERNEL); + if (!new_node) { + kfree(dvbdevfops); + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node->fops = dvbdevfops; + new_node->type = type; + new_node->template = template; + list_add_tail (&new_node->list_head, &dvbdevfops_list); } memcpy(dvbdev, template, sizeof(struct dvb_device)); @@ -499,20 +528,20 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvbdev->priv = priv; dvbdev->fops = dvbdevfops; init_waitqueue_head (&dvbdev->wait_queue); - dvbdevfops->owner = adap->module; - list_add_tail (&dvbdev->list_head, &adap->device_list); - down_write(&minor_rwsem); #ifdef CONFIG_DVB_DYNAMIC_MINORS for (minor = 0; minor < MAX_DVB_MINORS; minor++) if (dvb_minors[minor] == NULL) break; - if (minor == MAX_DVB_MINORS) { + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); @@ -521,41 +550,47 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, #else minor = nums2minor(adap->num, type, id); #endif - dvbdev->minor = minor; dvb_minors[minor] = dvb_device_get(dvbdev); up_write(&minor_rwsem); - ret = dvb_register_media_device(dvbdev, type, minor, demux_sink_pads); if (ret) { pr_err("%s: dvb_register_media_device failed to create the mediagraph\n", __func__); - + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); mutex_unlock(&dvbdev_register_lock); return ret; } - mutex_unlock(&dvbdev_register_lock); - clsdev = device_create(dvb_class, adap->device, MKDEV(DVB_MAJOR, minor), dvbdev, "dvb%d.%s%d", adap->num, dnames[type], id); if (IS_ERR(clsdev)) { pr_err("%s: failed to create device dvb%d.%s%d (%ld)\n", __func__, adap->num, dnames[type], id, PTR_ERR(clsdev)); + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); return PTR_ERR(clsdev); } + dprintk("DVB: register adapter%d/%s%d @ minor: %i (0x%02x)\n", adap->num, dnames[type], id, minor, minor); + mutex_unlock(&dvbdev_register_lock); return 0; } EXPORT_SYMBOL(dvb_register_device); @@ -584,7 +619,6 @@ static void dvb_free_device(struct kref *ref) { struct dvb_device *dvbdev = container_of(ref, struct dvb_device, ref); - kfree (dvbdev->fops); kfree (dvbdev); } @@ -1090,9 +1124,17 @@ error: static void __exit exit_dvbdev(void) { + struct dvbdevfops_node *node, *next; + class_destroy(dvb_class); cdev_del(&dvb_device_cdev); unregister_chrdev_region(MKDEV(DVB_MAJOR, 0), MAX_DVB_MINORS); + + list_for_each_entry_safe(node, next, &dvbdevfops_list, list_head) { + list_del (&node->list_head); + kfree(node->fops); + kfree(node); + } } subsys_initcall(init_dvbdev); diff --git a/include/media/dvbdev.h b/include/media/dvbdev.h index c493a3ffe45c..91ff2d5fcd08 100644 --- a/include/media/dvbdev.h +++ b/include/media/dvbdev.h @@ -189,6 +189,21 @@ struct dvb_device { void *priv; }; +/** + * struct dvbdevfops_node - fops nodes registered in dvbdevfops_list + * + * @fops: Dynamically allocated fops for ->owner registration + * @type: type of dvb_device + * @template: dvb_device used for registration + * @list_head: list_head for dvbdevfops_list + */ +struct dvbdevfops_node { + struct file_operations *fops; + enum dvb_device_type type; + const struct dvb_device *template; + struct list_head list_head; +}; + /** * dvb_device_get - Increase dvb_device reference * From 27458487c8f466924868bab2f2e73be97b86e601 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Thu, 15 Jun 2023 13:39:08 +0200 Subject: [PATCH 3596/4345] drm/i915/dg1: Wait for pcode/uncore handshake at startup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f9c730ede7d3f40900cb493890d94d868ff2f00f ] DG1 does some additional pcode/uncore handshaking at boot time; this handshaking must complete before various other pcode commands are effective and before general work is submitted to the GPU. We need to poll a new pcode mailbox during startup until it reports that this handshaking is complete. The bspec doesn't give guidance on how long we may need to wait for this handshaking to complete. For now, let's just set a really long timeout; if we still don't get a completion status by the end of that timeout, we'll just continue on and hope for the best. v2 (Lucas): Rename macros to make clear the relation between command and result (requested by José) Bspec: 52065 Cc: Clinton Taylor Cc: Ville Syrjälä Cc: Radhakrishna Sripada Signed-off-by: Matt Roper Signed-off-by: Lucas De Marchi Reviewed-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20201001063917.3133475-2-lucas.demarchi@intel.com Signed-off-by: Henning Schild Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/i915_drv.c | 3 +++ drivers/gpu/drm/i915/i915_reg.h | 3 +++ drivers/gpu/drm/i915/intel_sideband.c | 15 +++++++++++++++ drivers/gpu/drm/i915/intel_sideband.h | 2 ++ 4 files changed, 23 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 382cf048eefe..f72e3bb4ee9a 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -84,6 +84,7 @@ #include "intel_gvt.h" #include "intel_memory_region.h" #include "intel_pm.h" +#include "intel_sideband.h" #include "vlv_suspend.h" static struct drm_driver driver; @@ -614,6 +615,8 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) */ intel_dram_detect(dev_priv); + intel_pcode_init(dev_priv); + intel_bw_init_hw(dev_priv); return 0; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 04157d8ced32..728a46489f9c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -9235,6 +9235,9 @@ enum { #define GEN9_SAGV_DISABLE 0x0 #define GEN9_SAGV_IS_DISABLED 0x1 #define GEN9_SAGV_ENABLE 0x3 +#define DG1_PCODE_STATUS 0x7E +#define DG1_UNCORE_GET_INIT_STATUS 0x0 +#define DG1_UNCORE_INIT_STATUS_COMPLETE 0x1 #define GEN12_PCODE_READ_SAGV_BLOCK_TIME_US 0x23 #define GEN6_PCODE_DATA _MMIO(0x138128) #define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8 diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c index 5b3279262123..02ebf5a04a9b 100644 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ b/drivers/gpu/drm/i915/intel_sideband.c @@ -555,3 +555,18 @@ out: return ret ? ret : status; #undef COND } + +void intel_pcode_init(struct drm_i915_private *i915) +{ + int ret; + + if (!IS_DGFX(i915)) + return; + + ret = skl_pcode_request(i915, DG1_PCODE_STATUS, + DG1_UNCORE_GET_INIT_STATUS, + DG1_UNCORE_INIT_STATUS_COMPLETE, + DG1_UNCORE_INIT_STATUS_COMPLETE, 50); + if (ret) + drm_err(&i915->drm, "Pcode did not report uncore initialization completion!\n"); +} diff --git a/drivers/gpu/drm/i915/intel_sideband.h b/drivers/gpu/drm/i915/intel_sideband.h index 7fb95745a444..094c7b19c5d4 100644 --- a/drivers/gpu/drm/i915/intel_sideband.h +++ b/drivers/gpu/drm/i915/intel_sideband.h @@ -138,4 +138,6 @@ int sandybridge_pcode_write_timeout(struct drm_i915_private *i915, u32 mbox, int skl_pcode_request(struct drm_i915_private *i915, u32 mbox, u32 request, u32 reply_mask, u32 reply, int timeout_base_ms); +void intel_pcode_init(struct drm_i915_private *i915); + #endif /* _INTEL_SIDEBAND_H */ From f73ec12dc718ee90ec45fd23dad38c5020a5b1f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Roberto=20de=20Souza?= Date: Thu, 15 Jun 2023 13:39:09 +0200 Subject: [PATCH 3597/4345] drm/i915/gen11+: Only load DRAM information from pcode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5d0c938ec9cc96fc7b8abcff0ca8b2a084e9c90c ] Up to now we were reading some DRAM information from MCHBAR register and from pcode what is already not good but some GEN12(TGL-H and ADL-S) platforms have MCHBAR DRAM information in different offsets. This was notified to HW team that decided that the best alternative is always apply the 16gb_dimm watermark adjustment for GEN12+ platforms and read the remaning DRAM information needed to other display programming from pcode. So here moving the DRAM pcode function to intel_dram.c, removing the duplicated fields from intel_qgv_info, setting and using information from dram_info. v2: - bring back num_points to intel_qgv_info as num_qgv_point can be overwritten in icl_get_qgv_points() - add gen12_get_dram_info() and simplify gen11_get_dram_info() Reviewed-by: Lucas De Marchi Signed-off-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20210128164312.91160-2-jose.souza@intel.com Signed-off-by: Henning Schild Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/display/intel_bw.c | 80 +++--------------------- drivers/gpu/drm/i915/i915_drv.c | 5 +- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/intel_dram.c | 82 ++++++++++++++++++++++++- 4 files changed, 93 insertions(+), 75 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index bd060404d249..4b5a30ac84bc 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -20,76 +20,9 @@ struct intel_qgv_point { struct intel_qgv_info { struct intel_qgv_point points[I915_NUM_QGV_POINTS]; u8 num_points; - u8 num_channels; u8 t_bl; - enum intel_dram_type dram_type; }; -static int icl_pcode_read_mem_global_info(struct drm_i915_private *dev_priv, - struct intel_qgv_info *qi) -{ - u32 val = 0; - int ret; - - ret = sandybridge_pcode_read(dev_priv, - ICL_PCODE_MEM_SUBSYSYSTEM_INFO | - ICL_PCODE_MEM_SS_READ_GLOBAL_INFO, - &val, NULL); - if (ret) - return ret; - - if (IS_GEN(dev_priv, 12)) { - switch (val & 0xf) { - case 0: - qi->dram_type = INTEL_DRAM_DDR4; - break; - case 3: - qi->dram_type = INTEL_DRAM_LPDDR4; - break; - case 4: - qi->dram_type = INTEL_DRAM_DDR3; - break; - case 5: - qi->dram_type = INTEL_DRAM_LPDDR3; - break; - default: - MISSING_CASE(val & 0xf); - break; - } - } else if (IS_GEN(dev_priv, 11)) { - switch (val & 0xf) { - case 0: - qi->dram_type = INTEL_DRAM_DDR4; - break; - case 1: - qi->dram_type = INTEL_DRAM_DDR3; - break; - case 2: - qi->dram_type = INTEL_DRAM_LPDDR3; - break; - case 3: - qi->dram_type = INTEL_DRAM_LPDDR4; - break; - default: - MISSING_CASE(val & 0xf); - break; - } - } else { - MISSING_CASE(INTEL_GEN(dev_priv)); - qi->dram_type = INTEL_DRAM_LPDDR3; /* Conservative default */ - } - - qi->num_channels = (val & 0xf0) >> 4; - qi->num_points = (val & 0xf00) >> 8; - - if (IS_GEN(dev_priv, 12)) - qi->t_bl = qi->dram_type == INTEL_DRAM_DDR4 ? 4 : 16; - else if (IS_GEN(dev_priv, 11)) - qi->t_bl = qi->dram_type == INTEL_DRAM_DDR4 ? 4 : 8; - - return 0; -} - static int icl_pcode_read_qgv_point_info(struct drm_i915_private *dev_priv, struct intel_qgv_point *sp, int point) @@ -139,11 +72,15 @@ int icl_pcode_restrict_qgv_points(struct drm_i915_private *dev_priv, static int icl_get_qgv_points(struct drm_i915_private *dev_priv, struct intel_qgv_info *qi) { + const struct dram_info *dram_info = &dev_priv->dram_info; int i, ret; - ret = icl_pcode_read_mem_global_info(dev_priv, qi); - if (ret) - return ret; + qi->num_points = dram_info->num_qgv_points; + + if (IS_GEN(dev_priv, 12)) + qi->t_bl = dev_priv->dram_info.type == INTEL_DRAM_DDR4 ? 4 : 16; + else if (IS_GEN(dev_priv, 11)) + qi->t_bl = dev_priv->dram_info.type == INTEL_DRAM_DDR4 ? 4 : 8; if (drm_WARN_ON(&dev_priv->drm, qi->num_points > ARRAY_SIZE(qi->points))) @@ -209,7 +146,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel { struct intel_qgv_info qi = {}; bool is_y_tile = true; /* assume y tile may be used */ - int num_channels; + int num_channels = dev_priv->dram_info.num_channels; int deinterleave; int ipqdepth, ipqdepthpch; int dclk_max; @@ -222,7 +159,6 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel "Failed to get memory subsystem information, ignoring bandwidth limits"); return ret; } - num_channels = qi.num_channels; deinterleave = DIV_ROUND_UP(num_channels, is_y_tile ? 4 : 2); dclk_max = icl_sagv_max_dclk(&qi); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f72e3bb4ee9a..c72a26af181c 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -609,14 +609,15 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) goto err_msi; intel_opregion_setup(dev_priv); + + intel_pcode_init(dev_priv); + /* * Fill the dram structure to get the system raw bandwidth and * dram info. This will be used for memory latency calculation. */ intel_dram_detect(dev_priv); - intel_pcode_init(dev_priv); - intel_bw_init_hw(dev_priv); return 0; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 6909901b3551..a8b65bab82c8 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1148,6 +1148,7 @@ struct drm_i915_private { INTEL_DRAM_LPDDR3, INTEL_DRAM_LPDDR4 } type; + u8 num_qgv_points; } dram_info; struct intel_bw_info { diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c index 8aa12cad93ce..26e109c64984 100644 --- a/drivers/gpu/drm/i915/intel_dram.c +++ b/drivers/gpu/drm/i915/intel_dram.c @@ -5,6 +5,7 @@ #include "i915_drv.h" #include "intel_dram.h" +#include "intel_sideband.h" struct dram_dimm_info { u8 size, width, ranks; @@ -433,6 +434,81 @@ static int bxt_get_dram_info(struct drm_i915_private *i915) return 0; } +static int icl_pcode_read_mem_global_info(struct drm_i915_private *dev_priv) +{ + struct dram_info *dram_info = &dev_priv->dram_info; + u32 val = 0; + int ret; + + ret = sandybridge_pcode_read(dev_priv, + ICL_PCODE_MEM_SUBSYSYSTEM_INFO | + ICL_PCODE_MEM_SS_READ_GLOBAL_INFO, + &val, NULL); + if (ret) + return ret; + + if (IS_GEN(dev_priv, 12)) { + switch (val & 0xf) { + case 0: + dram_info->type = INTEL_DRAM_DDR4; + break; + case 3: + dram_info->type = INTEL_DRAM_LPDDR4; + break; + case 4: + dram_info->type = INTEL_DRAM_DDR3; + break; + case 5: + dram_info->type = INTEL_DRAM_LPDDR3; + break; + default: + MISSING_CASE(val & 0xf); + return -1; + } + } else { + switch (val & 0xf) { + case 0: + dram_info->type = INTEL_DRAM_DDR4; + break; + case 1: + dram_info->type = INTEL_DRAM_DDR3; + break; + case 2: + dram_info->type = INTEL_DRAM_LPDDR3; + break; + case 3: + dram_info->type = INTEL_DRAM_LPDDR4; + break; + default: + MISSING_CASE(val & 0xf); + return -1; + } + } + + dram_info->num_channels = (val & 0xf0) >> 4; + dram_info->num_qgv_points = (val & 0xf00) >> 8; + + return 0; +} + +static int gen11_get_dram_info(struct drm_i915_private *i915) +{ + int ret = skl_get_dram_info(i915); + + if (ret) + return ret; + + return icl_pcode_read_mem_global_info(i915); +} + +static int gen12_get_dram_info(struct drm_i915_private *i915) +{ + /* Always needed for GEN12+ */ + i915->dram_info.is_16gb_dimm = true; + + return icl_pcode_read_mem_global_info(i915); +} + void intel_dram_detect(struct drm_i915_private *i915) { struct dram_info *dram_info = &i915->dram_info; @@ -448,7 +524,11 @@ void intel_dram_detect(struct drm_i915_private *i915) if (INTEL_GEN(i915) < 9 || !HAS_DISPLAY(i915)) return; - if (IS_GEN9_LP(i915)) + if (INTEL_GEN(i915) >= 12) + ret = gen12_get_dram_info(i915); + else if (INTEL_GEN(i915) >= 11) + ret = gen11_get_dram_info(i915); + else if (IS_GEN9_LP(i915)) ret = bxt_get_dram_info(i915); else ret = skl_get_dram_info(i915); From ed2bf5cee6c6d5dc788ef19e8b984182c594d3ec Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 14 Dec 2020 20:51:02 +0100 Subject: [PATCH 3598/4345] um: Fix build w/o CONFIG_PM_SLEEP commit 1fb1abc83636f5329c26cd29f0f19f3faeb697a5 upstream. uml_pm_wake() is unconditionally called from the SIGUSR1 wakeup handler since that's in the userspace portion of UML, and thus a bit tricky to ifdef out. Since pm_system_wakeup() can always be called (but may be an empty inline), also simply always have uml_pm_wake() to fix the build. Reported-by: Randy Dunlap Acked-by: Randy Dunlap # build-tested Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger Signed-off-by: Greg Kroah-Hartman --- arch/um/kernel/um_arch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 00c6dce14bd2..55930ca498e9 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -387,12 +387,12 @@ void text_poke_sync(void) { } -#ifdef CONFIG_PM_SLEEP void uml_pm_wake(void) { pm_system_wakeup(); } +#ifdef CONFIG_PM_SLEEP static int init_pm_wake_signal(void) { /* From ef0d5feb32ab7007d1316e9c5037cd7d9f7febbf Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Jun 2023 15:45:41 +0200 Subject: [PATCH 3599/4345] Linux 5.10.185 Link: https://lore.kernel.org/r/20230619102138.279161276@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Salvatore Bonaccorso Tested-by: Chris Paterson (CIP) Tested-by: Jon Hunter Tested-by: Sudip Mukherjee Tested-by: Linux Kernel Functional Testing Tested-by: Allen Pais Tested-by: Shuah Khan Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 3450b061e8d6..73e6cc1992c2 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 184 +SUBLEVEL = 185 EXTRAVERSION = NAME = Dare mighty things From e6d71f847b98bd0c747251d9680771f9e2a21f86 Mon Sep 17 00:00:00 2001 From: Zixuan Fu Date: Thu, 21 Jul 2022 15:48:29 +0800 Subject: [PATCH 3600/4345] BACKPORT: btrfs: unset reloc control if transaction commit fails in prepare_to_relocate() commit 85f02d6c856b9f3a0acf5219de6e32f58b9778eb upstream. In btrfs_relocate_block_group(), the rc is allocated. Then btrfs_relocate_block_group() calls relocate_block_group() prepare_to_relocate() set_reloc_control() that assigns rc to the variable fs_info->reloc_ctl. When prepare_to_relocate() returns, it calls btrfs_commit_transaction() btrfs_start_dirty_block_groups() btrfs_alloc_path() kmem_cache_zalloc() which may fail for example (or other errors could happen). When the failure occurs, btrfs_relocate_block_group() detects the error and frees rc and doesn't set fs_info->reloc_ctl to NULL. After that, in btrfs_init_reloc_root(), rc is retrieved from fs_info->reloc_ctl and then used, which may cause a use-after-free bug. This possible bug can be triggered by calling btrfs_ioctl_balance() before calling btrfs_ioctl_defrag(). To fix this possible bug, in prepare_to_relocate(), check if btrfs_commit_transaction() fails. If the failure occurs, unset_reloc_control() is called to set fs_info->reloc_ctl to NULL. The error log in our fault-injection testing is shown as follows: [ 58.751070] BUG: KASAN: use-after-free in btrfs_init_reloc_root+0x7ca/0x920 [btrfs] ... [ 58.753577] Call Trace: ... [ 58.755800] kasan_report+0x45/0x60 [ 58.756066] btrfs_init_reloc_root+0x7ca/0x920 [btrfs] [ 58.757304] record_root_in_trans+0x792/0xa10 [btrfs] [ 58.757748] btrfs_record_root_in_trans+0x463/0x4f0 [btrfs] [ 58.758231] start_transaction+0x896/0x2950 [btrfs] [ 58.758661] btrfs_defrag_root+0x250/0xc00 [btrfs] [ 58.759083] btrfs_ioctl_defrag+0x467/0xa00 [btrfs] [ 58.759513] btrfs_ioctl+0x3c95/0x114e0 [btrfs] ... [ 58.768510] Allocated by task 23683: [ 58.768777] ____kasan_kmalloc+0xb5/0xf0 [ 58.769069] __kmalloc+0x227/0x3d0 [ 58.769325] alloc_reloc_control+0x10a/0x3d0 [btrfs] [ 58.769755] btrfs_relocate_block_group+0x7aa/0x1e20 [btrfs] [ 58.770228] btrfs_relocate_chunk+0xf1/0x760 [btrfs] [ 58.770655] __btrfs_balance+0x1326/0x1f10 [btrfs] [ 58.771071] btrfs_balance+0x3150/0x3d30 [btrfs] [ 58.771472] btrfs_ioctl_balance+0xd84/0x1410 [btrfs] [ 58.771902] btrfs_ioctl+0x4caa/0x114e0 [btrfs] ... [ 58.773337] Freed by task 23683: ... [ 58.774815] kfree+0xda/0x2b0 [ 58.775038] free_reloc_control+0x1d6/0x220 [btrfs] [ 58.775465] btrfs_relocate_block_group+0x115c/0x1e20 [btrfs] [ 58.775944] btrfs_relocate_chunk+0xf1/0x760 [btrfs] [ 58.776369] __btrfs_balance+0x1326/0x1f10 [btrfs] [ 58.776784] btrfs_balance+0x3150/0x3d30 [btrfs] [ 58.777185] btrfs_ioctl_balance+0xd84/0x1410 [btrfs] [ 58.777621] btrfs_ioctl+0x4caa/0x114e0 [btrfs] ... Bug: 286629572 Reported-by: TOTE Robot CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Sweet Tea Dorminy Reviewed-by: Nikolay Borisov Signed-off-by: Zixuan Fu Signed-off-by: David Sterba Signed-off-by: Stefan Ghinea Signed-off-by: Greg Kroah-Hartman (cherry picked from commit b60e862e133f646f19023ece1d476d630a660de1) [Lee: Fixed minor conflict - returning result vs returning 0] Signed-off-by: Lee Jones Change-Id: I9212b61a85d36e20eed337d59fbadc2782d96a24 --- fs/btrfs/relocation.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index c21545c5b34b..206e0bc1b2d6 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3270,8 +3270,12 @@ int prepare_to_relocate(struct reloc_control *rc) */ return PTR_ERR(trans); } - btrfs_commit_transaction(trans); - return 0; + + ret = btrfs_commit_transaction(trans); + if (ret) + unset_reloc_control(rc); + + return ret; } static noinline_for_stack int relocate_block_group(struct reloc_control *rc) From 1c98645c8e83ede34b20cd0ec4450db9893f1242 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Wed, 8 Mar 2023 00:43:38 +0800 Subject: [PATCH 3601/4345] UPSTREAM: memstick: r592: Fix UAF bug in r592_remove due to race condition [ Upstream commit 63264422785021704c39b38f65a78ab9e4a186d7 ] In r592_probe, dev->detect_timer was bound with r592_detect_timer. In r592_irq function, the timer function will be invoked by mod_timer. If we remove the module which will call hantro_release to make cleanup, there may be a unfinished work. The possible sequence is as follows, which will cause a typical UAF bug. Fix it by canceling the work before cleanup in r592_remove. CPU0 CPU1 |r592_detect_timer r592_remove | memstick_free_host| put_device; | kfree(host); | | | queue_work | &host->media_checker //use Bug: 287729043 Signed-off-by: Zheng Wang Link: https://lore.kernel.org/r/20230307164338.1246287-1-zyytlz.wz@163.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin (cherry picked from commit 9a342d4eb9fb8e52f7d1afe088a79513f3f9a9a5) Signed-off-by: Lee Jones Change-Id: Idb15f593287ebaeec294b3e276126306fa6743ba --- drivers/memstick/host/r592.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/memstick/host/r592.c b/drivers/memstick/host/r592.c index eaa2a94d18be..dd06c18495eb 100644 --- a/drivers/memstick/host/r592.c +++ b/drivers/memstick/host/r592.c @@ -828,7 +828,7 @@ static void r592_remove(struct pci_dev *pdev) /* Stop the processing thread. That ensures that we won't take any more requests */ kthread_stop(dev->io_thread); - + del_timer_sync(&dev->detect_timer); r592_enable_device(dev, false); while (!error && dev->req) { From 4991def0fa4cf4af67957e25233383ca05574d32 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 12 Apr 2023 15:49:23 +1000 Subject: [PATCH 3602/4345] UPSTREAM: xfs: verify buffer contents when we skip log replay commit 22ed903eee23a5b174e240f1cdfa9acf393a5210 upstream. syzbot detected a crash during log recovery: XFS (loop0): Mounting V5 Filesystem bfdc47fc-10d8-4eed-a562-11a831b3f791 XFS (loop0): Torn write (CRC failure) detected at log block 0x180. Truncating head block from 0x200. XFS (loop0): Starting recovery (logdev: internal) ================================================================== BUG: KASAN: slab-out-of-bounds in xfs_btree_lookup_get_block+0x15c/0x6d0 fs/xfs/libxfs/xfs_btree.c:1813 Read of size 8 at addr ffff88807e89f258 by task syz-executor132/5074 CPU: 0 PID: 5074 Comm: syz-executor132 Not tainted 6.2.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x290 lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:306 print_report+0x107/0x1f0 mm/kasan/report.c:417 kasan_report+0xcd/0x100 mm/kasan/report.c:517 xfs_btree_lookup_get_block+0x15c/0x6d0 fs/xfs/libxfs/xfs_btree.c:1813 xfs_btree_lookup+0x346/0x12c0 fs/xfs/libxfs/xfs_btree.c:1913 xfs_btree_simple_query_range+0xde/0x6a0 fs/xfs/libxfs/xfs_btree.c:4713 xfs_btree_query_range+0x2db/0x380 fs/xfs/libxfs/xfs_btree.c:4953 xfs_refcount_recover_cow_leftovers+0x2d1/0xa60 fs/xfs/libxfs/xfs_refcount.c:1946 xfs_reflink_recover_cow+0xab/0x1b0 fs/xfs/xfs_reflink.c:930 xlog_recover_finish+0x824/0x920 fs/xfs/xfs_log_recover.c:3493 xfs_log_mount_finish+0x1ec/0x3d0 fs/xfs/xfs_log.c:829 xfs_mountfs+0x146a/0x1ef0 fs/xfs/xfs_mount.c:933 xfs_fs_fill_super+0xf95/0x11f0 fs/xfs/xfs_super.c:1666 get_tree_bdev+0x400/0x620 fs/super.c:1282 vfs_get_tree+0x88/0x270 fs/super.c:1489 do_new_mount+0x289/0xad0 fs/namespace.c:3145 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x2d3/0x3c0 fs/namespace.c:3674 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f89fa3f4aca Code: 83 c4 08 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fffd5fb5ef8 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00646975756f6e2c RCX: 00007f89fa3f4aca RDX: 0000000020000100 RSI: 0000000020009640 RDI: 00007fffd5fb5f10 RBP: 00007fffd5fb5f10 R08: 00007fffd5fb5f50 R09: 000000000000970d R10: 0000000000200800 R11: 0000000000000206 R12: 0000000000000004 R13: 0000555556c6b2c0 R14: 0000000000200800 R15: 00007fffd5fb5f50 The fuzzed image contains an AGF with an obviously garbage agf_refcount_level value of 32, and a dirty log with a buffer log item for that AGF. The ondisk AGF has a higher LSN than the recovered log item. xlog_recover_buf_commit_pass2 reads the buffer, compares the LSNs, and decides to skip replay because the ondisk buffer appears to be newer. Unfortunately, the ondisk buffer is corrupt, but recovery just read the buffer with no buffer ops specified: error = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len, buf_flags, &bp, NULL); Skipping the buffer leaves its contents in memory unverified. This sets us up for a kernel crash because xfs_refcount_recover_cow_leftovers reads the buffer (which is still around in XBF_DONE state, so no read verification) and creates a refcountbt cursor of height 32. This is impossible so we run off the end of the cursor object and crash. Fix this by invoking the verifier on all skipped buffers and aborting log recovery if the ondisk buffer is corrupt. It might be smarter to force replay the log item atop the buffer and then see if it'll pass the write verifier (like ext4 does) but for now let's go with the conservative option where we stop immediately. Bug: 284409747 Link: https://syzkaller.appspot.com/bug?extid=7e9494b8b399902e994e Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner Reported-by: Danila Chernetsov Link: https://lore.kernel.org/linux-xfs/20230601164439.15404-1-listdansp@mail.ru Signed-off-by: Amir Goldstein Acked-by: Darrick J. Wong Signed-off-by: Greg Kroah-Hartman (cherry picked from commit a2961463d74f5c86a8dda3b41c484c28ccc4c289) Signed-off-by: Lee Jones Change-Id: Ie5e156221966323a9cb7cc261b4ed17593cfaabd --- fs/xfs/xfs_buf_item_recover.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index b374c9cee117..a053b0bf7930 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -924,6 +924,16 @@ xlog_recover_buf_commit_pass2( if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) { trace_xfs_log_recover_buf_skip(log, buf_f); xlog_recover_validate_buf_type(mp, bp, buf_f, NULLCOMMITLSN); + + /* + * We're skipping replay of this buffer log item due to the log + * item LSN being behind the ondisk buffer. Verify the buffer + * contents since we aren't going to run the write verifier. + */ + if (bp->b_ops) { + bp->b_ops->verify_read(bp); + error = bp->b_error; + } goto out_release; } From 01e0792f609c66e909b6effcab4cf96d0416762f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Jun 2023 19:17:39 +0000 Subject: [PATCH 3603/4345] Revert "uapi/linux/const.h: prefer ISO-friendly __typeof__" This reverts commit a69eb1200eb699fb8c07f2b42285dfa291af071b. It breaks the CRC generation of the ABI for no good reason so revert it for now. Bug: 161946584 Change-Id: Ia0e5e95557a439465b98f292384587d81073b4e7 Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/const.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index a429381e7ca5..af2a44c08683 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) From 24c41942a442ade625c0533e22750e16c27b8502 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Jun 2023 17:09:21 +0000 Subject: [PATCH 3604/4345] Revert "workqueue: Fix hung time report of worker pools" This reverts commit 647781347af925268434c5dc99b04f7077de8e8e which is commit 335a42ebb0ca8ee9997a1731aaaae6dcd704c113 upstream. It breaks the Android kernel abi, so revert it. If it needs to come back later, it can do so in an abi-safe way. Bug: 161946584 Change-Id: I702fcb45a1147789f1ff78ed07500162e8632d5f Signed-off-by: Greg Kroah-Hartman --- kernel/workqueue.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c830ac463a15..3afe533cf3e9 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4833,19 +4833,16 @@ void show_workqueue_state(void) for_each_pool(pool, pi) { struct worker *worker; bool first = true; - unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; - /* How long the first pending work is waiting for a worker. */ - if (!list_empty(&pool->worklist)) - hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; - pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); - pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); + pr_cont(" hung=%us workers=%d", + jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000, + pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); From b38d756cea19115da9049d483a32a0e4fd2e8645 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Jun 2023 17:09:42 +0000 Subject: [PATCH 3605/4345] Revert "workqueue: Rename "delayed" (delayed by active management) to "inactive"" This reverts commit 77d9a64cfbc677169264e961dd36c00b5d7cd63c which is commit f97a4a1a3f8769e3452885967955e21c88f3f263 upstream. It breaks the Android kernel abi, so revert it. If it needs to come back later, it can do so in an abi-safe way. Bug: 161946584 Change-Id: Ia1a60890202c1cddb635ecbd392e1a0726463a3c Signed-off-by: Greg Kroah-Hartman --- include/linux/workqueue.h | 4 +-- kernel/workqueue.c | 58 +++++++++++++++++++-------------------- 2 files changed, 31 insertions(+), 31 deletions(-) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index a439232c0617..e98cc6dea2b9 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -30,7 +30,7 @@ void delayed_work_timer_fn(struct timer_list *t); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_INACTIVE_BIT= 1, /* work item is inactive */ + WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */ WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -43,7 +43,7 @@ enum { WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, - WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, + WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3afe533cf3e9..0408e5cd3d38 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -211,7 +211,7 @@ struct pool_workqueue { /* L: nr of in_flight works */ int nr_active; /* L: nr of active works */ int max_active; /* L: max active works */ - struct list_head inactive_works; /* L: inactive works */ + struct list_head delayed_works; /* L: delayed works */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ @@ -1152,7 +1152,7 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) } } -static void pwq_activate_inactive_work(struct work_struct *work) +static void pwq_activate_delayed_work(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); @@ -1160,16 +1160,16 @@ static void pwq_activate_inactive_work(struct work_struct *work) if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); - __clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work)); + __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); pwq->nr_active++; } -static void pwq_activate_first_inactive(struct pool_workqueue *pwq) +static void pwq_activate_first_delayed(struct pool_workqueue *pwq) { - struct work_struct *work = list_first_entry(&pwq->inactive_works, + struct work_struct *work = list_first_entry(&pwq->delayed_works, struct work_struct, entry); - pwq_activate_inactive_work(work); + pwq_activate_delayed_work(work); } /** @@ -1192,10 +1192,10 @@ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color) pwq->nr_in_flight[color]--; pwq->nr_active--; - if (!list_empty(&pwq->inactive_works)) { - /* one down, submit an inactive one */ + if (!list_empty(&pwq->delayed_works)) { + /* one down, submit a delayed one */ if (pwq->nr_active < pwq->max_active) - pwq_activate_first_inactive(pwq); + pwq_activate_first_delayed(pwq); } /* is flush in progress and are we at the flushing tip? */ @@ -1297,14 +1297,14 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, debug_work_deactivate(work); /* - * An inactive work item cannot be grabbed directly because + * A delayed work item cannot be grabbed directly because * it might have linked NO_COLOR work items which, if left - * on the inactive_works list, will confuse pwq->nr_active + * on the delayed_list, will confuse pwq->nr_active * management later on and cause stall. Make sure the work * item is activated before grabbing. */ - if (*work_data_bits(work) & WORK_STRUCT_INACTIVE) - pwq_activate_inactive_work(work); + if (*work_data_bits(work) & WORK_STRUCT_DELAYED) + pwq_activate_delayed_work(work); list_del_init(&work->entry); pwq_dec_nr_in_flight(pwq, get_work_color(work)); @@ -1506,8 +1506,8 @@ retry: if (list_empty(worklist)) pwq->pool->watchdog_ts = jiffies; } else { - work_flags |= WORK_STRUCT_INACTIVE; - worklist = &pwq->inactive_works; + work_flags |= WORK_STRUCT_DELAYED; + worklist = &pwq->delayed_works; } debug_work_activate(work); @@ -2551,7 +2551,7 @@ repeat: /* * The above execution of rescued work items could * have created more to rescue through - * pwq_activate_first_inactive() or chained + * pwq_activate_first_delayed() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't @@ -2977,7 +2977,7 @@ reflush: bool drained; raw_spin_lock_irq(&pwq->pool->lock); - drained = !pwq->nr_active && list_empty(&pwq->inactive_works); + drained = !pwq->nr_active && list_empty(&pwq->delayed_works); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) @@ -3731,7 +3731,7 @@ static void pwq_unbound_release_workfn(struct work_struct *work) * @pwq: target pool_workqueue * * If @pwq isn't freezing, set @pwq->max_active to the associated - * workqueue's saved_max_active and activate inactive work items + * workqueue's saved_max_active and activate delayed work items * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. */ static void pwq_adjust_max_active(struct pool_workqueue *pwq) @@ -3760,9 +3760,9 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq) pwq->max_active = wq->saved_max_active; - while (!list_empty(&pwq->inactive_works) && + while (!list_empty(&pwq->delayed_works) && pwq->nr_active < pwq->max_active) { - pwq_activate_first_inactive(pwq); + pwq_activate_first_delayed(pwq); kick = true; } @@ -3793,7 +3793,7 @@ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; - INIT_LIST_HEAD(&pwq->inactive_works); + INIT_LIST_HEAD(&pwq->delayed_works); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn); @@ -4380,7 +4380,7 @@ static bool pwq_busy(struct pool_workqueue *pwq) if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1)) return true; - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) return true; return false; @@ -4576,7 +4576,7 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) else pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); - ret = !list_empty(&pwq->inactive_works); + ret = !list_empty(&pwq->delayed_works); preempt_enable(); rcu_read_unlock(); @@ -4772,11 +4772,11 @@ static void show_pwq(struct pool_workqueue *pwq) pr_cont("\n"); } - if (!list_empty(&pwq->inactive_works)) { + if (!list_empty(&pwq->delayed_works)) { bool comma = false; - pr_info(" inactive:"); - list_for_each_entry(work, &pwq->inactive_works, entry) { + pr_info(" delayed:"); + list_for_each_entry(work, &pwq->delayed_works, entry) { pr_cont_work(comma, work); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } @@ -4806,7 +4806,7 @@ void show_workqueue_state(void) bool idle = true; for_each_pwq(pwq, wq) { - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) { idle = false; break; } @@ -4818,7 +4818,7 @@ void show_workqueue_state(void) for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, flags); - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) show_pwq(pwq); raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); /* @@ -5194,7 +5194,7 @@ EXPORT_SYMBOL_GPL(work_on_cpu_safe); * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable - * workqueues will queue new works to their inactive_works list instead of + * workqueues will queue new works to their delayed_works list instead of * pool->worklist. * * CONTEXT: From 39c3d16903dc2621de4c135d296636e05cf6e614 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 8 Jun 2023 08:29:03 +0100 Subject: [PATCH 3606/4345] UPSTREAM: net/sched: cls_u32: Fix reference counter leak leading to overflow [ Upstream commit 04c55383fa5689357bcdd2c8036725a55ed632bc ] In the event of a failure in tcf_change_indev(), u32_set_parms() will immediately return without decrementing the recently incremented reference counter. If this happens enough times, the counter will rollover and the reference freed, leading to a double free which can be used to do 'bad things'. In order to prevent this, move the point of possible failure above the point where the reference counter is incremented. Also save any meaningful return values to be applied to the return data at the appropriate point in time. This issue was caught with KASAN. Bug: 273251569 Fixes: 705c7091262d ("net: sched: cls_u32: no need to call tcf_exts_change for newly allocated struct") Suggested-by: Eric Dumazet Signed-off-by: Lee Jones Reviewed-by: Eric Dumazet Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin (cherry picked from commit 07f9cc229b44cbcee6385802d390091d915f38c3) Signed-off-by: Lee Jones Change-Id: I95524bfda9a08a40b3d54515e528419dba18dc55 --- net/sched/cls_u32.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index da042bc8b239..1ac8ff445a6d 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -716,12 +716,18 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) { - int err; + int err, ifindex = -1; err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, true, extack); if (err < 0) return err; + if (tb[TCA_U32_INDEV]) { + ifindex = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); + if (ifindex < 0) + return -EINVAL; + } + if (tb[TCA_U32_LINK]) { u32 handle = nla_get_u32(tb[TCA_U32_LINK]); struct tc_u_hnode *ht_down = NULL, *ht_old; @@ -756,13 +762,9 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, tcf_bind_filter(tp, &n->res, base); } - if (tb[TCA_U32_INDEV]) { - int ret; - ret = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); - if (ret < 0) - return -EINVAL; - n->ifindex = ret; - } + if (ifindex >= 0) + n->ifindex = ifindex; + return 0; } From 6229d57677bd85b984b3ffe1e17db0f514508986 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 26 Jun 2023 15:19:54 +0000 Subject: [PATCH 3607/4345] Revert "arm64: Stash shadow stack pointer in the task struct on interrupt" This reverts commit 3f225f29c69c13ce1cbdb1d607a42efeef080056 which is commit 59b37fe52f49955791a460752c37145f1afdcad1 upstream. It breaks some test systems, so obviously the backport to 5.10.y wasn't quite correct :( Revert it for now until this can be figured out better. Cc: Ard Biesheuvel Cc: Kees Cook Cc: Mark Rutland Cc: Catalin Marinas Signed-off-by: Greg Kroah-Hartman Change-Id: I1071c357225a8b41f15767a27b5c56cf94d7a5f7 --- arch/arm64/kernel/entry.S | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 6daea7bffb2d..c747ebff5d09 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -530,7 +530,9 @@ SYM_CODE_END(__swpan_exit_el0) .macro irq_stack_entry mov x19, sp // preserve the original sp - scs_save tsk // preserve the original shadow stack +#ifdef CONFIG_SHADOW_CALL_STACK + mov x24, scs_sp // preserve the original shadow stack +#endif /* * Compare sp with the base of the task stack. @@ -564,7 +566,9 @@ SYM_CODE_END(__swpan_exit_el0) */ .macro irq_stack_exit mov sp, x19 - scs_load_current +#ifdef CONFIG_SHADOW_CALL_STACK + mov scs_sp, x24 +#endif .endm /* GPRs used by entry code */ From 7c491aaf0794817bebbc65c9608e3074a02fb055 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 13 Jun 2023 20:54:09 +0000 Subject: [PATCH 3608/4345] Revert "firmware: arm_sdei: Fix sleep from invalid context BUG" This reverts commit 7d8f5ccc826b39e05ff252b1fccd808c7a0725e0 which is commit d2c48b2387eb89e0bf2a2e06e30987cf410acad4 upstream. It breaks the Android kernel abi, so revert it for now. If it is needed in the future it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: I65e8ac1f57e138b38ba4e56a6595925e32029825 Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/arm_sdei.c | 37 +++++++++++++++++-------------------- include/linux/cpuhotplug.h | 1 + 2 files changed, 18 insertions(+), 20 deletions(-) diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c index 5a877d76078f..840754dcc6ca 100644 --- a/drivers/firmware/arm_sdei.c +++ b/drivers/firmware/arm_sdei.c @@ -44,8 +44,6 @@ static asmlinkage void (*sdei_firmware_call)(unsigned long function_id, /* entry point from firmware to arch asm code */ static unsigned long sdei_entry_point; -static int sdei_hp_state; - struct sdei_event { /* These three are protected by the sdei_list_lock */ struct list_head list; @@ -304,6 +302,8 @@ int sdei_mask_local_cpu(void) { int err; + WARN_ON_ONCE(preemptible()); + err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_MASK, 0, 0, 0, 0, 0, NULL); if (err && err != -EIO) { pr_warn_once("failed to mask CPU[%u]: %d\n", @@ -316,7 +316,6 @@ int sdei_mask_local_cpu(void) static void _ipi_mask_cpu(void *ignored) { - WARN_ON_ONCE(preemptible()); sdei_mask_local_cpu(); } @@ -324,6 +323,8 @@ int sdei_unmask_local_cpu(void) { int err; + WARN_ON_ONCE(preemptible()); + err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_UNMASK, 0, 0, 0, 0, 0, NULL); if (err && err != -EIO) { pr_warn_once("failed to unmask CPU[%u]: %d\n", @@ -336,7 +337,6 @@ int sdei_unmask_local_cpu(void) static void _ipi_unmask_cpu(void *ignored) { - WARN_ON_ONCE(preemptible()); sdei_unmask_local_cpu(); } @@ -344,8 +344,6 @@ static void _ipi_private_reset(void *ignored) { int err; - WARN_ON_ONCE(preemptible()); - err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PRIVATE_RESET, 0, 0, 0, 0, 0, NULL); if (err && err != -EIO) @@ -392,6 +390,8 @@ static void _local_event_enable(void *data) int err; struct sdei_crosscall_args *arg = data; + WARN_ON_ONCE(preemptible()); + err = sdei_api_event_enable(arg->event->event_num); sdei_cross_call_return(arg, err); @@ -480,6 +480,8 @@ static void _local_event_unregister(void *data) int err; struct sdei_crosscall_args *arg = data; + WARN_ON_ONCE(preemptible()); + err = sdei_api_event_unregister(arg->event->event_num); sdei_cross_call_return(arg, err); @@ -560,6 +562,8 @@ static void _local_event_register(void *data) struct sdei_registered_event *reg; struct sdei_crosscall_args *arg = data; + WARN_ON(preemptible()); + reg = per_cpu_ptr(arg->event->private_registered, smp_processor_id()); err = sdei_api_event_register(arg->event->event_num, sdei_entry_point, reg, 0, 0); @@ -714,8 +718,6 @@ static int sdei_pm_notifier(struct notifier_block *nb, unsigned long action, { int rv; - WARN_ON_ONCE(preemptible()); - switch (action) { case CPU_PM_ENTER: rv = sdei_mask_local_cpu(); @@ -764,7 +766,7 @@ static int sdei_device_freeze(struct device *dev) int err; /* unregister private events */ - cpuhp_remove_state(sdei_entry_point); + cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING); err = sdei_unregister_shared(); if (err) @@ -785,15 +787,12 @@ static int sdei_device_thaw(struct device *dev) return err; } - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SDEI", + err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI", &sdei_cpuhp_up, &sdei_cpuhp_down); - if (err < 0) { + if (err) pr_warn("Failed to re-register CPU hotplug notifier...\n"); - return err; - } - sdei_hp_state = err; - return 0; + return err; } static int sdei_device_restore(struct device *dev) @@ -825,7 +824,7 @@ static int sdei_reboot_notifier(struct notifier_block *nb, unsigned long action, * We are going to reset the interface, after this there is no point * doing work when we take CPUs offline. */ - cpuhp_remove_state(sdei_hp_state); + cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING); sdei_platform_reset(); @@ -1005,15 +1004,13 @@ static int sdei_probe(struct platform_device *pdev) goto remove_cpupm; } - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SDEI", + err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI", &sdei_cpuhp_up, &sdei_cpuhp_down); - if (err < 0) { + if (err) { pr_warn("Failed to register CPU hotplug notifier...\n"); goto remove_reboot; } - sdei_hp_state = err; - return 0; remove_reboot: diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d142b92cbd02..843bb056b8c6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -114,6 +114,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_MIPS_OP_LOONGSON3_STARTING, + CPUHP_AP_ARM_SDEI_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, From c86beaeed18b07dd66a3c299b00bed6b524f3973 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Jun 2023 10:08:16 +0000 Subject: [PATCH 3609/4345] Revert "tcp: fix possible sk_priority leak in tcp_v4_send_reset()" This reverts commit e7fd68abbba3409b1c365fe04e7b2c37298954a1 which is commit 1e306ec49a1f206fd2cc89a42fac6e6f592a8cc1 uptream. It breaks the Android kernel abi, so revert it for now. If it is needed in the future it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: I1c86735875631e9fc0031bab4e87e487298c45e4 Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_ipv4.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 270b20e0907c..1995d46afb21 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -805,9 +805,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); - } else { - ctl_sk->sk_mark = 0; - ctl_sk->sk_priority = 0; } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -815,6 +812,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) &arg, arg.iov[0].iov_len, transmit_time); + ctl_sk->sk_mark = 0; xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); @@ -913,6 +911,7 @@ static void tcp_v4_send_ack(const struct sock *sk, &arg, arg.iov[0].iov_len, transmit_time); + ctl_sk->sk_mark = 0; sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); From a4be51e26a8c8208f1a6b1142b1bc7f0db4376c6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Jun 2023 10:08:27 +0000 Subject: [PATCH 3610/4345] Revert "net: Find dst with sk's xfrm policy not ctl_sk" This reverts commit 788791990d74d3d2140c0f72df0b9218d3984dd8 which is commit e22aa14866684f77b4f6b6cae98539e520ddb731 upstream. It breaks the Android kernel abi, so revert it for now. If it is needed in the future it can be brought back in an ABI-safe way. Bug: 161946584 Change-Id: Ibbbc25dce5304664307a4d06420c24aa6d6ff708 Signed-off-by: Greg Kroah-Hartman --- include/net/xfrm.h | 2 -- net/ipv4/ip_output.c | 2 +- net/ipv4/tcp_ipv4.c | 2 -- net/ipv6/tcp_ipv6.c | 5 +---- 4 files changed, 2 insertions(+), 9 deletions(-) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 93b785edf813..5c022fc018a4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1169,8 +1169,6 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { - if (!sk_fullsock(osk)) - return 0; sk->sk_policy[0] = NULL; sk->sk_policy[1] = NULL; if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6fd04f2f8b40..1e07df282177 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1723,7 +1723,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, tcp_hdr(skb)->source, tcp_hdr(skb)->dest, arg->uid); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); - rt = ip_route_output_flow(net, &fl4, sk); + rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1995d46afb21..275ae42be99e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -804,7 +804,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); - xfrm_sk_clone_policy(ctl_sk, sk); } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -813,7 +812,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) transmit_time); ctl_sk->sk_mark = 0; - xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index fe29bc66aeac..2347740d3cc7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -984,10 +984,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 * Underlying function will use this to retrieve the network * namespace */ - if (sk && sk->sk_state != TCP_TIME_WAIT) - dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/ - else - dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, From 8231b54cd2842dd2f159bfb38ee99629e5c730ba Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 13 Jun 2023 19:07:10 +0000 Subject: [PATCH 3611/4345] ANDROID: GKI: preserve CRC generation for some bluetooth symbols In commit a2d816f55da1 ("Bluetooth: hci_bcm: Fall back to getting bdaddr from EFI if not set"), a "#include " was added which caused the CRC generation of some bluetooth symbols to be modified due to some structures now coming into "scope". Fix this up by hacking in our favorite __GENKSYMS__ test, which fixes everything up right and all is calm again. Bug: 161946584 Fixes: a2d816f55da1 ("Bluetooth: hci_bcm: Fall back to getting bdaddr from EFI if not set") Change-Id: I5ddb1d3895f079980c3efd64ae773b91da3ca809 Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btbcm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index 636db3b7e470..3fe056c8b99e 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -6,7 +6,9 @@ * Copyright (C) 2015 Intel Corporation */ +#ifndef __GENKSYMS__ // ANDROID CRC kabi preservation hack due to commit 76dd7893bd10 #include +#endif #include #include #include From f015c92c49584ee3c2e7883cb497706544e33c9b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 11 Aug 2022 12:33:39 +0200 Subject: [PATCH 3612/4345] Revert "ipv4/tcp: do not use per netns ctl sockets" This reverts commit a9ef8b2589885851c769982ef34cb01348fb07bb which is commit 37ba017dcc3b1123206808979834655ddcf93251 upstream. It breaks the Android kernel ABI and is not needed for Android devices, so it is safe to revert for now. If it is determined that it is needed in the future, it can be brought back in an abi-preserving way. Bug: 161946584 Signed-off-by: Greg Kroah-Hartman Change-Id: Ie1e6f2b24c5e360577bc66fde8f969eeea96e99d --- include/net/netns/ipv4.h | 1 + net/ipv4/tcp_ipv4.c | 61 ++++++++++++++++++++++------------------ 2 files changed, 35 insertions(+), 27 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 033d5c8ffdd6..fb94551d03e6 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -72,6 +72,7 @@ struct netns_ipv4 { struct sock *mc_autojoin_sk; struct inet_peer_base *peers; + struct sock * __percpu *tcp_sk; struct fqdir *fqdir; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 275ae42be99e..8bd7b1ec3b6a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -91,8 +91,6 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); -static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk); - static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, @@ -796,8 +794,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(ipv4_tcp_sk); - sock_net_set(ctl_sk, net); + ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; @@ -812,7 +809,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) transmit_time); ctl_sk->sk_mark = 0; - sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_bh_enable(); @@ -896,8 +892,7 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(ipv4_tcp_sk); - sock_net_set(ctl_sk, net); + ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? @@ -910,7 +905,6 @@ static void tcp_v4_send_ack(const struct sock *sk, transmit_time); ctl_sk->sk_mark = 0; - sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); } @@ -2834,14 +2828,41 @@ EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { + int cpu; + if (net->ipv4.tcp_congestion_control) bpf_module_put(net->ipv4.tcp_congestion_control, net->ipv4.tcp_congestion_control->owner); + + for_each_possible_cpu(cpu) + inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); + free_percpu(net->ipv4.tcp_sk); } static int __net_init tcp_sk_init(struct net *net) { - int cnt; + int res, cpu, cnt; + + net->ipv4.tcp_sk = alloc_percpu(struct sock *); + if (!net->ipv4.tcp_sk) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, net); + if (res) + goto fail; + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + /* Please enforce IP_DF and IPID==0 for RST and + * ACK sent in SYN-RECV and TIME-WAIT state. + */ + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; + } net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_ecn_fallback = 1; @@ -2926,6 +2947,10 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.tcp_congestion_control = &tcp_reno; return 0; +fail: + tcp_sk_exit(net); + + return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) @@ -3002,24 +3027,6 @@ static void __init bpf_iter_register(void) void __init tcp_v4_init(void) { - int cpu, res; - - for_each_possible_cpu(cpu) { - struct sock *sk; - - res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, - IPPROTO_TCP, &init_net); - if (res) - panic("Failed to create the TCP control socket.\n"); - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); - - /* Please enforce IP_DF and IPID==0 for RST and - * ACK sent in SYN-RECV and TIME-WAIT state. - */ - inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; - - per_cpu(ipv4_tcp_sk, cpu) = sk; - } if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); From 4a7c41b710abd8091cadba40223555933f0b55e2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Jun 2023 12:09:32 +0000 Subject: [PATCH 3613/4345] Revert "tipc: check the bearer min mtu properly when setting it by netlink" This reverts commit 2937127d24ccb83e57ee5dbcd0309995f0fa5386 which is commit 35a089b5d793d2bfd2cc7cfa6104545184de2ce7 upstream. It breaks the Android kernel ABI and is not needed for Android devices, so it is safe to revert for now. If it is determined that it is needed in the future, it can be brought back in an abi-preserving way. Bug: 161946584 Change-Id: Iac2aaf58f7e53317626d0f7f125b55e72228c770 Signed-off-by: Greg Kroah-Hartman --- net/tipc/bearer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 91e678fa3feb..c6a9b3446ff8 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1135,8 +1135,8 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP - if (nla_get_u32(props[TIPC_NLA_PROP_MTU]) < - b->encap_hlen + TIPC_MIN_BEARER_MTU) { + if (tipc_udp_mtu_bad(nla_get_u32 + (props[TIPC_NLA_PROP_MTU]))) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; From 7ae5626406aafb64a207ee48e87269274a1c9c4c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Jun 2023 12:10:03 +0000 Subject: [PATCH 3614/4345] Revert "tipc: do not update mtu if msg_max is too small in mtu negotiation" This reverts commit 2bd4ff4ffb92113f8acd04dbaed83269172c24b4 which is commit 56077b56cd3fb78e1c8619e29581ba25a5c55e86 upstream. It breaks the Android kernel ABI and is not needed for Android devices, so it is safe to revert for now. If it is determined that it is needed in the future, it can be brought back in an abi-preserving way. Bug: 161946584 Change-Id: I5fc048bf94f78a38691e3b27cf225536200bcd49 Signed-off-by: Greg Kroah-Hartman --- net/tipc/link.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index dbb1bc722ba9..c1e56d1f21b3 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2164,7 +2164,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; - u32 dlen = msg_data_sz(hdr), glen = 0, msg_max; + u32 dlen = msg_data_sz(hdr), glen = 0; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); @@ -2203,9 +2203,6 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG: - msg_max = msg_max_pkt(hdr); - if (msg_max < tipc_bearer_min_mtu(l->net, l->bearer_id)) - break; /* Complete own link name with peer's interface name */ if_name = strrchr(l->name, ':') + 1; if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) @@ -2250,8 +2247,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, l->peer_session = msg_session(hdr); l->in_session = true; l->peer_bearer_id = msg_bearer_id(hdr); - if (l->mtu > msg_max) - l->mtu = msg_max; + if (l->mtu > msg_max_pkt(hdr)) + l->mtu = msg_max_pkt(hdr); break; case STATE_MSG: From f8e98486564494f075d49d33229aa81fb7da013d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Jun 2023 12:10:13 +0000 Subject: [PATCH 3615/4345] Revert "tipc: add tipc_bearer_min_mtu to calculate min mtu" This reverts commit 097ea78d8ccaf789eeeb154fdfb6afbd274a2a87 which is commit 3ae6d66b605be604644d4bb5708a7ffd9cf1abe8 upstream. It breaks the Android kernel ABI and is not needed for Android devices, so it is safe to revert for now. If it is determined that it is needed in the future, it can be brought back in an abi-preserving way. Bug: 161946584 Change-Id: I0b32b3b8d7c81895dd1680f7aec65d38cace080d Signed-off-by: Greg Kroah-Hartman --- net/tipc/bearer.c | 13 ------------- net/tipc/bearer.h | 3 --- net/tipc/udp_media.c | 5 ++--- 3 files changed, 2 insertions(+), 19 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index c6a9b3446ff8..72c31ef985eb 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -525,19 +525,6 @@ int tipc_bearer_mtu(struct net *net, u32 bearer_id) return mtu; } -int tipc_bearer_min_mtu(struct net *net, u32 bearer_id) -{ - int mtu = TIPC_MIN_BEARER_MTU; - struct tipc_bearer *b; - - rcu_read_lock(); - b = bearer_get(net, bearer_id); - if (b) - mtu += b->encap_hlen; - rcu_read_unlock(); - return mtu; -} - /* tipc_bearer_xmit_skb - sends buffer to destination over bearer */ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 711a50f44993..6bf4550aa1ac 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -146,7 +146,6 @@ struct tipc_media { * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer - * @encap_hlen: encap headers length * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * @@ -171,7 +170,6 @@ struct tipc_bearer { u32 identity; struct tipc_discoverer *disc; char net_plane; - u16 encap_hlen; unsigned long up; refcount_t refcnt; }; @@ -234,7 +232,6 @@ int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); -int tipc_bearer_min_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 3e47501f024f..a23628108272 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -730,8 +730,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = local.ipv4.s_addr; udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; - b->encap_hlen = sizeof(struct iphdr) + sizeof(struct udphdr); - if (tipc_mtu_bad(dev, b->encap_hlen)) { + if (tipc_mtu_bad(dev, sizeof(struct iphdr) + + sizeof(struct udphdr))) { err = -EINVAL; goto err; } @@ -752,7 +752,6 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, else udp_conf.local_ip6 = local.ipv6; ub->ifindex = dev->ifindex; - b->encap_hlen = sizeof(struct ipv6hdr) + sizeof(struct udphdr); b->mtu = 1280; #endif } else { From 4d5a15daae478e1a5b387d769c6b16eae0a744db Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Jun 2023 15:41:05 +0000 Subject: [PATCH 3616/4345] Revert "regulator: pca9450: Fix BUCK2 enable_mask" This reverts commit 860ad704e4506a4716631a46e93c2ed4a6a0e23c which is commit d67dada3e2524514b09496b9ee1df22d4507a280 upstream. It is part of a series that breaks the Android kernel abi and can be safely reverted at this point in time. If it needs to come back in the future, it can be done so in an abi-safe way. Bug: 161946584 Change-Id: I33e439ca99e09cee71174eaa1149750bfee93c1e Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/pca9450-regulator.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index b3d206ebb289..fd184c6c7c78 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -256,7 +256,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_reg = PCA9450_REG_BUCK2OUT_DVS0, .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, - .enable_mask = BUCK2_ENMODE_MASK, + .enable_mask = BUCK1_ENMODE_MASK, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, @@ -494,7 +494,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_reg = PCA9450_REG_BUCK2OUT_DVS0, .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, - .enable_mask = BUCK2_ENMODE_MASK, + .enable_mask = BUCK1_ENMODE_MASK, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, From 5e8d66e06a4fc93a4971e793219e6e1c54c9134c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Jun 2023 15:41:07 +0000 Subject: [PATCH 3617/4345] Revert "regulator: pca9450: Convert to use regulator_set_ramp_delay_regmap" This reverts commit b3a9c4081db956dd383137e55a008f82e1d8bb87 which is commit 4c4fce171c4ca08cd98be7db350e6950630b046a upstream. It is part of a series that breaks the Android kernel abi and can be safely reverted at this point in time. If it needs to come back in the future, it can be done so in an abi-safe way. Bug: 161946584 Change-Id: I20ea532f38c565713dc4a29ad0a35916f851aebe Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/pca9450-regulator.c | 51 ++++++++++++++------------- 1 file changed, 27 insertions(+), 24 deletions(-) diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index fd184c6c7c78..d38109cc3a01 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -65,9 +65,32 @@ static const struct regmap_config pca9450_regmap_config = { * 10: 25mV/4usec * 11: 25mV/8usec */ -static const unsigned int pca9450_dvs_buck_ramp_table[] = { - 25000, 12500, 6250, 3125 -}; +static int pca9450_dvs_set_ramp_delay(struct regulator_dev *rdev, + int ramp_delay) +{ + int id = rdev_get_id(rdev); + unsigned int ramp_value; + + switch (ramp_delay) { + case 1 ... 3125: + ramp_value = BUCK1_RAMP_3P125MV; + break; + case 3126 ... 6250: + ramp_value = BUCK1_RAMP_6P25MV; + break; + case 6251 ... 12500: + ramp_value = BUCK1_RAMP_12P5MV; + break; + case 12501 ... 25000: + ramp_value = BUCK1_RAMP_25MV; + break; + default: + ramp_value = BUCK1_RAMP_25MV; + } + + return regmap_update_bits(rdev->regmap, PCA9450_REG_BUCK1CTRL + id * 3, + BUCK1_RAMP_MASK, ramp_value << 6); +} static const struct regulator_ops pca9450_dvs_buck_regulator_ops = { .enable = regulator_enable_regmap, @@ -77,7 +100,7 @@ static const struct regulator_ops pca9450_dvs_buck_regulator_ops = { .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_time_sel = regulator_set_voltage_time_sel, - .set_ramp_delay = regulator_set_ramp_delay_regmap, + .set_ramp_delay = pca9450_dvs_set_ramp_delay, }; static const struct regulator_ops pca9450_buck_regulator_ops = { @@ -228,10 +251,6 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK1OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK1CTRL, .enable_mask = BUCK1_ENMODE_MASK, - .ramp_reg = PCA9450_REG_BUCK1CTRL, - .ramp_mask = BUCK1_RAMP_MASK, - .ramp_delay_table = pca9450_dvs_buck_ramp_table, - .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, @@ -257,10 +276,6 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, .enable_mask = BUCK1_ENMODE_MASK, - .ramp_reg = PCA9450_REG_BUCK2CTRL, - .ramp_mask = BUCK2_RAMP_MASK, - .ramp_delay_table = pca9450_dvs_buck_ramp_table, - .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, @@ -286,10 +301,6 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_mask = BUCK3OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK3CTRL, .enable_mask = BUCK3_ENMODE_MASK, - .ramp_reg = PCA9450_REG_BUCK3CTRL, - .ramp_mask = BUCK3_RAMP_MASK, - .ramp_delay_table = pca9450_dvs_buck_ramp_table, - .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, @@ -466,10 +477,6 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_mask = BUCK1OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK1CTRL, .enable_mask = BUCK1_ENMODE_MASK, - .ramp_reg = PCA9450_REG_BUCK1CTRL, - .ramp_mask = BUCK1_RAMP_MASK, - .ramp_delay_table = pca9450_dvs_buck_ramp_table, - .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, @@ -495,10 +502,6 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, .enable_mask = BUCK1_ENMODE_MASK, - .ramp_reg = PCA9450_REG_BUCK2CTRL, - .ramp_mask = BUCK2_RAMP_MASK, - .ramp_delay_table = pca9450_dvs_buck_ramp_table, - .n_ramp_values = ARRAY_SIZE(pca9450_dvs_buck_ramp_table), .owner = THIS_MODULE, .of_parse_cb = pca9450_set_dvs_levels, }, From 04a55bbb7fa798b855e29ba1a0448f5aaacdc658 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Jun 2023 15:41:08 +0000 Subject: [PATCH 3618/4345] Revert "regulator: Add regmap helper for ramp-delay setting" This reverts commit 12cb97ed85fb8bfc3ef88b66d80b09950d49af91 which is commit fb8fee9efdcf084d9e31ba14cc4734d97e5dd972 upstream. It is part of a series that breaks the Android kernel abi and can be safely reverted at this point in time. If it needs to come back in the future, it can be done so in an abi-safe way. Bug: 161946584 Change-Id: I8b912fb1cd2aa9e0ebfba10aaba93a147a32815b Signed-off-by: Greg Kroah-Hartman --- drivers/regulator/helpers.c | 65 -------------------------------- include/linux/regulator/driver.h | 5 --- 2 files changed, 70 deletions(-) diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c index a356f84b1285..e4bb09bbd3fa 100644 --- a/drivers/regulator/helpers.c +++ b/drivers/regulator/helpers.c @@ -879,68 +879,3 @@ bool regulator_is_equal(struct regulator *reg1, struct regulator *reg2) return reg1->rdev == reg2->rdev; } EXPORT_SYMBOL_GPL(regulator_is_equal); - -static int find_closest_bigger(unsigned int target, const unsigned int *table, - unsigned int num_sel, unsigned int *sel) -{ - unsigned int s, tmp, max, maxsel = 0; - bool found = false; - - max = table[0]; - - for (s = 0; s < num_sel; s++) { - if (table[s] > max) { - max = table[s]; - maxsel = s; - } - if (table[s] >= target) { - if (!found || table[s] - target < tmp - target) { - tmp = table[s]; - *sel = s; - found = true; - if (tmp == target) - break; - } - } - } - - if (!found) { - *sel = maxsel; - return -EINVAL; - } - - return 0; -} - -/** - * regulator_set_ramp_delay_regmap - set_ramp_delay() helper - * - * @rdev: regulator to operate on - * - * Regulators that use regmap for their register I/O can set the ramp_reg - * and ramp_mask fields in their descriptor and then use this as their - * set_ramp_delay operation, saving some code. - */ -int regulator_set_ramp_delay_regmap(struct regulator_dev *rdev, int ramp_delay) -{ - int ret; - unsigned int sel; - - if (!rdev->desc->n_ramp_values) - return -EINVAL; - - ret = find_closest_bigger(ramp_delay, rdev->desc->ramp_delay_table, - rdev->desc->n_ramp_values, &sel); - - if (ret) { - dev_warn(rdev_get_dev(rdev), - "Can't set ramp-delay %u, setting %u\n", ramp_delay, - rdev->desc->ramp_delay_table[sel]); - } - - sel <<= ffs(rdev->desc->ramp_mask) - 1; - - return regmap_update_bits(rdev->regmap, rdev->desc->ramp_reg, - rdev->desc->ramp_mask, sel); -} -EXPORT_SYMBOL_GPL(regulator_set_ramp_delay_regmap); diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 63a91049068d..4d73dc580d75 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -376,10 +376,6 @@ struct regulator_desc { unsigned int pull_down_reg; unsigned int pull_down_mask; unsigned int pull_down_val_on; - unsigned int ramp_reg; - unsigned int ramp_mask; - const unsigned int *ramp_delay_table; - unsigned int n_ramp_values; unsigned int enable_time; @@ -546,7 +542,6 @@ int regulator_set_current_limit_regmap(struct regulator_dev *rdev, int min_uA, int max_uA); int regulator_get_current_limit_regmap(struct regulator_dev *rdev); void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data); -int regulator_set_ramp_delay_regmap(struct regulator_dev *rdev, int ramp_delay); /* * Helper functions intended to be used by regulator drivers prior registering From 0c0856714ed742acf40d30b422eba3d7a5e74a91 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 28 Jun 2023 06:29:42 +0000 Subject: [PATCH 3619/4345] Revert "tcp: deny tcp_disconnect() when threads are waiting" This reverts commit cccc6209708f59b0d5f0b4853588a720c829a111 which is commit 4faeee0cf8a5d88d63cdbc3bab124fb0e6aed08c upstream. It breaks the Android kernel abi, and if it is needed in the future can come back in an abi-safe way. Bug: 161946584 Change-Id: If50dd244848a8aa70b08be347020b263c71f4a61 Signed-off-by: Greg Kroah-Hartman --- include/net/sock.h | 4 ---- net/ipv4/af_inet.c | 2 -- net/ipv4/inet_connection_sock.c | 1 - net/ipv4/tcp.c | 6 ------ 4 files changed, 13 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index ad88af26a118..99ef1004bbc6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -328,7 +328,6 @@ struct bpf_local_storage; * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start - * @sk_wait_pending: number of threads blocked on this socket * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available @@ -413,7 +412,6 @@ struct sock { unsigned int sk_napi_id; #endif int sk_rcvbuf; - int sk_wait_pending; struct sk_filter __rcu *sk_filter; union { @@ -1118,7 +1116,6 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ - __sk->sk_wait_pending++; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ @@ -1128,7 +1125,6 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } \ sched_annotate_sleep(); \ lock_sock(__sk); \ - __sk->sk_wait_pending--; \ __rc = __condition; \ __rc; \ }) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 038e5915cd38..769902ff9eff 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -588,7 +588,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; - sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -604,7 +603,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; - sk->sk_wait_pending--; return timeo; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 713f77d4df5f..4fbc23e1e640 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -839,7 +839,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); - newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bf237c6cf891..35c9dc0fb701 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2727,12 +2727,6 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; - /* Deny disconnect if other threads are blocked in sk_wait_event() - * or inet_wait_for_connect(). - */ - if (sk->sk_wait_pending) - return -EBUSY; - if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); From b1b42fff8ae1ac7db8ea8b468c849822914b94f1 Mon Sep 17 00:00:00 2001 From: Tom Chung Date: Mon, 29 May 2023 18:00:09 +0800 Subject: [PATCH 3620/4345] drm/amd/display: fix the system hang while disable PSR [ Upstream commit ea2062dd1f0384ae1b136d333ee4ced15bedae38 ] [Why] When the PSR enabled. If you try to adjust the timing parameters, it may cause system hang. Because the timing mismatch with the DMCUB settings. [How] Disable the PSR before adjusting timing parameters. Cc: Mario Limonciello Cc: Alex Deucher Cc: stable@vger.kernel.org Acked-by: Stylon Wang Signed-off-by: Tom Chung Reviewed-by: Wayne Lin Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 3ca1ee396e4c..0bdc83d89946 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7430,6 +7430,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, if (acrtc_state->abm_level != dm_old_crtc_state->abm_level) bundle->stream_update.abm_level = &acrtc_state->abm_level; + mutex_lock(&dm->dc_lock); + if ((acrtc_state->update_type > UPDATE_TYPE_FAST) && + acrtc_state->stream->link->psr_settings.psr_allow_active) + amdgpu_dm_psr_disable(acrtc_state->stream); + mutex_unlock(&dm->dc_lock); + /* * If FreeSync state on the stream has changed then we need to * re-adjust the min/max bounds now that DC doesn't handle this @@ -7444,9 +7450,6 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); } mutex_lock(&dm->dc_lock); - if ((acrtc_state->update_type > UPDATE_TYPE_FAST) && - acrtc_state->stream->link->psr_settings.psr_allow_active) - amdgpu_dm_psr_disable(acrtc_state->stream); dc_commit_updates_for_stream(dm->dc, bundle->surface_updates, From 9ced73049016c117cc16339e83559b8e4c4d7a5e Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Sat, 10 Jun 2023 20:30:15 -0700 Subject: [PATCH 3621/4345] net/sched: Refactor qdisc_graft() for ingress and clsact Qdiscs [ Upstream commit 2d5f6a8d7aef7852a9ecc555f88c673a1c91754f ] Grafting ingress and clsact Qdiscs does not need a for-loop in qdisc_graft(). Refactor it. No functional changes intended. Tested-by: Pedro Tammela Acked-by: Jamal Hadi Salim Reviewed-by: Jamal Hadi Salim Reviewed-by: Vlad Buslov Signed-off-by: Peilin Ye Signed-off-by: Paolo Abeni Stable-dep-of: 84ad0af0bccd ("net/sched: qdisc_destroy() old ingress and clsact Qdiscs before grafting") Signed-off-by: Sasha Levin --- net/sched/sch_api.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 2084724c36ad..fb50e3f3283f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1044,12 +1044,12 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (parent == NULL) { unsigned int i, num_q, ingress; + struct netdev_queue *dev_queue; ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || (new && new->flags & TCQ_F_INGRESS)) { - num_q = 1; ingress = 1; if (!dev_ingress_queue(dev)) { NL_SET_ERR_MSG(extack, "Device does not have an ingress queue"); @@ -1065,18 +1065,18 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (new && new->ops->attach) goto skip; - for (i = 0; i < num_q; i++) { - struct netdev_queue *dev_queue = dev_ingress_queue(dev); - - if (!ingress) + if (!ingress) { + for (i = 0; i < num_q; i++) { dev_queue = netdev_get_tx_queue(dev, i); + old = dev_graft_qdisc(dev_queue, new); - old = dev_graft_qdisc(dev_queue, new); - if (new && i > 0) - qdisc_refcount_inc(new); - - if (!ingress) + if (new && i > 0) + qdisc_refcount_inc(new); qdisc_put(old); + } + } else { + dev_queue = dev_ingress_queue(dev); + old = dev_graft_qdisc(dev_queue, new); } skip: From db4ab0c97a4d8952d4b1225696f5be3d2b868a8a Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 23 Nov 2022 14:25:57 -0500 Subject: [PATCH 3622/4345] tracing: Add tracing_reset_all_online_cpus_unlocked() function commit e18eb8783ec4949adebc7d7b0fdb65f65bfeefd9 upstream. Currently the tracing_reset_all_online_cpus() requires the trace_types_lock held. But only one caller of this function actually has that lock held before calling it, and the other just takes the lock so that it can call it. More users of this function is needed where the lock is not held. Add a tracing_reset_all_online_cpus_unlocked() function for the one use case that calls it without being held, and also add a lockdep_assert to make sure it is held when called. Then have tracing_reset_all_online_cpus() take the lock internally, such that callers do not need to worry about taking it. Link: https://lkml.kernel.org/r/20221123192741.658273220@goodmis.org Cc: Masami Hiramatsu Cc: Andrew Morton Cc: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Zheng Yejian Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 11 ++++++++++- kernel/trace/trace.h | 1 + kernel/trace/trace_events.c | 2 +- kernel/trace/trace_events_synth.c | 2 -- 4 files changed, 12 insertions(+), 4 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 482ec6606b7b..70526400e05c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2178,10 +2178,12 @@ void tracing_reset_online_cpus(struct array_buffer *buf) } /* Must have trace_types_lock held */ -void tracing_reset_all_online_cpus(void) +void tracing_reset_all_online_cpus_unlocked(void) { struct trace_array *tr; + lockdep_assert_held(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (!tr->clear_trace) continue; @@ -2193,6 +2195,13 @@ void tracing_reset_all_online_cpus(void) } } +void tracing_reset_all_online_cpus(void) +{ + mutex_lock(&trace_types_lock); + tracing_reset_all_online_cpus_unlocked(); + mutex_unlock(&trace_types_lock); +} + /* * The tgid_map array maps from pid to tgid; i.e. the value stored at index i * is the tgid last observed corresponding to pid=i. diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 37f616bf5fa9..e5b505b5b7d0 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -725,6 +725,7 @@ int tracing_is_enabled(void); void tracing_reset_online_cpus(struct array_buffer *buf); void tracing_reset_current(int cpu); void tracing_reset_all_online_cpus(void); +void tracing_reset_all_online_cpus_unlocked(void); int tracing_open_generic(struct inode *inode, struct file *filp); int tracing_open_generic_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index bac13f24a96e..f8ed66f38175 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2661,7 +2661,7 @@ static void trace_module_remove_events(struct module *mod) * over from this module may be passed to the new module events and * unexpected results may occur. */ - tracing_reset_all_online_cpus(); + tracing_reset_all_online_cpus_unlocked(); } static int trace_module_notify(struct notifier_block *self, diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 18291ab35657..ee174de0b8f6 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1363,7 +1363,6 @@ int synth_event_delete(const char *event_name) mutex_unlock(&event_mutex); if (mod) { - mutex_lock(&trace_types_lock); /* * It is safest to reset the ring buffer if the module * being unloaded registered any events that were @@ -1375,7 +1374,6 @@ int synth_event_delete(const char *event_name) * occur. */ tracing_reset_all_online_cpus(); - mutex_unlock(&trace_types_lock); } return ret; From 3cc7935d32212f6252442c5ce0e1a1c81e466319 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 15 Jun 2023 11:18:30 +0200 Subject: [PATCH 3623/4345] tick/common: Align tick period during sched_timer setup commit 13bb06f8dd42071cb9a49f6e21099eea05d4b856 upstream. The tick period is aligned very early while the first clock_event_device is registered. At that point the system runs in periodic mode and switches later to one-shot mode if possible. The next wake-up event is programmed based on the aligned value (tick_next_period) but the delta value, that is used to program the clock_event_device, is computed based on ktime_get(). With the subtracted offset, the device fires earlier than the exact time frame. With a large enough offset the system programs the timer for the next wake-up and the remaining time left is too small to make any boot progress. The system hangs. Move the alignment later to the setup of tick_sched timer. At this point the system switches to oneshot mode and a high resolution clocksource is available. At this point it is safe to align tick_next_period because ktime_get() will now return accurate (not jiffies based) time. [bigeasy: Patch description + testing]. Fixes: e9523a0d81899 ("tick/common: Align tick period with the HZ tick.") Reported-by: Mathias Krause Reported-by: "Bhatnagar, Rishabh" Suggested-by: Mathias Krause Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Tested-by: Richard W.M. Jones Tested-by: Mathias Krause Acked-by: SeongJae Park Cc: stable@vger.kernel.org Link: https://lore.kernel.org/5a56290d-806e-b9a5-f37c-f21958b5a8c0@grsecurity.net Link: https://lore.kernel.org/12c6f9a3-d087-b824-0d05-0d18c9bc1bf3@amazon.com Link: https://lore.kernel.org/r/20230615091830.RxMV2xf_@linutronix.de Signed-off-by: Greg Kroah-Hartman --- kernel/time/tick-common.c | 13 +------------ kernel/time/tick-sched.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 2b7448ae5b47..e883d12dcb0d 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -216,19 +216,8 @@ static void tick_setup_device(struct tick_device *td, * this cpu: */ if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { - ktime_t next_p; - u32 rem; - tick_do_timer_cpu = cpu; - - next_p = ktime_get(); - div_u64_rem(next_p, TICK_NSEC, &rem); - if (rem) { - next_p -= rem; - next_p += TICK_NSEC; - } - - tick_next_period = next_p; + tick_next_period = ktime_get(); #ifdef CONFIG_NO_HZ_FULL /* * The boot CPU may be nohz_full, in which case set diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 17dc3f53efef..d07de3ff42ac 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -129,8 +129,19 @@ static ktime_t tick_init_jiffy_update(void) raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); /* Did we start the jiffies update yet ? */ - if (last_jiffies_update == 0) + if (last_jiffies_update == 0) { + u32 rem; + + /* + * Ensure that the tick is aligned to a multiple of + * TICK_NSEC. + */ + div_u64_rem(tick_next_period, TICK_NSEC, &rem); + if (rem) + tick_next_period += TICK_NSEC - rem; + last_jiffies_update = tick_next_period; + } period = last_jiffies_update; write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); From 6d20cfbc578d01d87cc1b1610d32ce1d1d0d8480 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Thu, 8 Jun 2023 18:38:43 +0200 Subject: [PATCH 3624/4345] selftests: mptcp: lib: skip if missing symbol commit 673004821ab98c6645bd21af56a290854e88f533 upstream. Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features. New functions are now available to easily detect if a certain feature is missing by looking at kallsyms. These new helpers are going to be used in the following commits. In order to ease the backport of such future patches, it would be good if this patch is backported up to the introduction of MPTCP selftests, hence the Fixes tag below: this type of check was supposed to be done from the beginning. Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 048d19d444be ("mptcp: add basic kselftest for mptcp") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/mptcp/config | 1 + .../testing/selftests/net/mptcp/mptcp_lib.sh | 38 +++++++++++++++++++ 2 files changed, 39 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 741a1c4f4ae8..1a4c11a444d9 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -1,3 +1,4 @@ +CONFIG_KALLSYMS=y CONFIG_MPTCP=y CONFIG_IPV6=y CONFIG_MPTCP_IPV6=y diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 3286536b79d5..29b65f4b73b2 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -38,3 +38,41 @@ mptcp_lib_check_mptcp() { exit ${KSFT_SKIP} fi } + +mptcp_lib_check_kallsyms() { + if ! mptcp_lib_has_file "/proc/kallsyms"; then + echo "SKIP: CONFIG_KALLSYMS is missing" + exit ${KSFT_SKIP} + fi +} + +# Internal: use mptcp_lib_kallsyms_has() instead +__mptcp_lib_kallsyms_has() { + local sym="${1}" + + mptcp_lib_check_kallsyms + + grep -q " ${sym}" /proc/kallsyms +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_has() { + local sym="${1}" + + if __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol not found" +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_doesnt_have() { + local sym="${1}" + + if ! __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol has been found" +} From 4c4ca42418a5e2935dfeba99345adc7b23e64d47 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Sat, 10 Jun 2023 18:11:36 +0200 Subject: [PATCH 3625/4345] selftests: mptcp: lib: skip if not below kernel version commit b1a6a38ab8a633546cefae890da842f19e006c74 upstream. Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features. A new function is now available to easily detect if a feature is missing by looking at the kernel version. That's clearly not ideal and this kind of check should be avoided as soon as possible. But sometimes, there are no external sign that a "feature" is available or not: internal behaviours can change without modifying the uAPI and these selftests are verifying the internal behaviours. Sometimes, the only (easy) way to verify if the feature is present is to run the test but then the validation cannot determine if there is a failure with the feature or if the feature is missing. Then it looks better to check the kernel version instead of having tests that can never fail. In any case, we need a solution not to have a whole selftest being marked as failed just because one sub-test has failed. Note that this env var car be set to 1 not to do such check and run the linked sub-test: SELFTESTS_MPTCP_LIB_NO_KVERSION_CHECK. This new helper is going to be used in the following commits. In order to ease the backport of such future patches, it would be good if this patch is backported up to the introduction of MPTCP selftests, hence the Fixes tag below: this type of check was supposed to be done from the beginning. Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: 048d19d444be ("mptcp: add basic kselftest for mptcp") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- .../testing/selftests/net/mptcp/mptcp_lib.sh | 26 +++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 29b65f4b73b2..f32045b23b89 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -76,3 +76,29 @@ mptcp_lib_kallsyms_doesnt_have() { mptcp_lib_fail_if_expected_feature "${sym} symbol has been found" } + +# !!!AVOID USING THIS!!! +# Features might not land in the expected version and features can be backported +# +# $1: kernel version, e.g. 6.3 +mptcp_lib_kversion_ge() { + local exp_maj="${1%.*}" + local exp_min="${1#*.}" + local v maj min + + # If the kernel has backported features, set this env var to 1: + if [ "${SELFTESTS_MPTCP_LIB_NO_KVERSION_CHECK:-}" = "1" ]; then + return 0 + fi + + v=$(uname -r | cut -d'.' -f1,2) + maj=${v%.*} + min=${v#*.} + + if [ "${maj}" -gt "${exp_maj}" ] || + { [ "${maj}" -eq "${exp_maj}" ] && [ "${min}" -ge "${exp_min}" ]; }; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}" +} From e508d9cef887a96971c9481d829a6846b4e8aec3 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Thu, 22 Jun 2023 15:59:47 +0200 Subject: [PATCH 3626/4345] selftests: mptcp: pm nl: remove hardcoded default limits commit 2177d0b08e421971e035672b70f3228d9485c650 upstream. Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features. One of them is the checks of the default limits returned by the MPTCP in-kernel path-manager. The default values have been modified by commit 72bcbc46a5c3 ("mptcp: increase default max additional subflows to 2"). Instead of comparing with hardcoded values, we can get the default one and compare with them. Note that if we expect to have the latest version, we continue to check the hardcoded values to avoid unexpected behaviour changes. Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: eedbc685321b ("selftests: add PM netlink functional tests") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski Signed-off-by: Matthieu Baerts Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/net/mptcp/pm_netlink.sh | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index f7cdba0a97a9..fff6f74ebe16 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -73,8 +73,12 @@ check() } check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 + +default_limits="$(ip netns exec $ns1 ./pm_nl_ctl limits)" +if mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 subflows 0" "defaults limits" +fi ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo @@ -120,12 +124,10 @@ ip netns exec $ns1 ./pm_nl_ctl flush check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" ip netns exec $ns1 ./pm_nl_ctl limits 9 1 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "rcv addrs above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "rcv addrs above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 1 9 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "subflows above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 From 524a2c0bcf99e99cc3e071a45aeb1f927033d64f Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Thu, 22 Jun 2023 15:59:48 +0200 Subject: [PATCH 3627/4345] selftests: mptcp: join: skip check if MIB counter not supported commit 47867f0a7e831e24e5eab3330667ce9682d50fb1 upstream. Selftests are supposed to run on any kernels, including the old ones not supporting all MPTCP features. One of them is the MPTCP MIB counters introduced in commit fc518953bc9c ("mptcp: add and use MIB counter infrastructure") and more later. The MPTCP Join selftest heavily relies on these counters. If a counter is not supported by the kernel, it is not displayed when using 'nstat -z'. We can then detect that and skip the verification. A new helper (get_counter()) has been added to do the required checks and return an error if the counter is not available. Note that if we expect to have these features available and if SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var is set to 1, the tests will be marked as failed instead of skipped. This new helper also makes sure we get the exact counter we want to avoid issues we had in the past, e.g. with MPTcpExtRmAddr and MPTcpExtRmAddrDrop sharing the same prefix. While at it, we uniform the way we fetch a MIB counter. Note for the backports: we rarely change these modified blocks so if there is are conflicts, it is very likely because a counter is not used in the older kernels and we don't need that chunk. Link: https://github.com/multipath-tcp/mptcp_net-next/issues/368 Fixes: b08fbf241064 ("selftests: add test-cases for MPTCP MP_JOIN") Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski Signed-off-by: Matthieu Baerts Signed-off-by: Greg Kroah-Hartman --- .../testing/selftests/net/mptcp/mptcp_join.sh | 65 +++++++++++++------ 1 file changed, 44 insertions(+), 21 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 94b15bb28e11..d205828d7575 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -130,6 +130,22 @@ do_ping() fi } +# $1: ns ; $2: counter +get_counter() +{ + local ns="${1}" + local counter="${2}" + local count + + count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi + + echo "${count}" +} + do_transfer() { listener_ns="$1" @@ -291,9 +307,10 @@ chk_join_nr() local dump_stats printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'` - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" ret=1 dump_stats=1 @@ -302,9 +319,10 @@ chk_join_nr() fi echo -n " - synack" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}'` - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" ret=1 dump_stats=1 @@ -313,9 +331,10 @@ chk_join_nr() fi echo -n " - ack" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}'` - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" ret=1 dump_stats=1 @@ -338,9 +357,10 @@ chk_add_nr() local dump_stats printf "%-39s %s" " " "add" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtAddAddr | awk '{print $2}'` - [ -z "$count" ] && count=0 - if [ "$count" != "$add_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtAddAddr") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$add_nr" ]; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" ret=1 dump_stats=1 @@ -349,9 +369,10 @@ chk_add_nr() fi echo -n " - echo " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}'` - [ -z "$count" ] && count=0 - if [ "$count" != "$echo_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" ret=1 dump_stats=1 @@ -375,9 +396,10 @@ chk_rm_nr() local dump_stats printf "%-39s %s" " " "rm " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtRmAddr | awk '{print $2}'` - [ -z "$count" ] && count=0 - if [ "$count" != "$rm_addr_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtRmAddr") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" ret=1 dump_stats=1 @@ -386,9 +408,10 @@ chk_rm_nr() fi echo -n " - sf " - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}'` - [ -z "$count" ] && count=0 - if [ "$count" != "$rm_subflow_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtRmSubflow") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" ret=1 dump_stats=1 From b435298349aba83e3412bb5c881e7a6624f5df89 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 9 Jun 2023 12:57:32 +0900 Subject: [PATCH 3628/4345] nilfs2: fix buffer corruption due to concurrent device reads commit 679bd7ebdd315bf457a4740b306ae99f1d0a403d upstream. As a result of analysis of a syzbot report, it turned out that in three cases where nilfs2 allocates block device buffers directly via sb_getblk, concurrent reads to the device can corrupt the allocated buffers. Nilfs2 uses sb_getblk for segment summary blocks, that make up a log header, and the super root block, that is the trailer, and when moving and writing the second super block after fs resize. In any of these, since the uptodate flag is not set when storing metadata to be written in the allocated buffers, the stored metadata will be overwritten if a device read of the same block occurs concurrently before the write. This causes metadata corruption and misbehavior in the log write itself, causing warnings in nilfs_btree_assign() as reported. Fix these issues by setting an uptodate flag on the buffer head on the first or before modifying each buffer obtained with sb_getblk, and clearing the flag on failure. When setting the uptodate flag, the lock_buffer/unlock_buffer pair is used to perform necessary exclusive control, and the buffer is filled to ensure that uninitialized bytes are not mixed into the data read from others. As for buffers for segment summary blocks, they are filled incrementally, so if the uptodate flag was unset on their allocation, set the flag and zero fill the buffer once at that point. Also, regarding the superblock move routine, the starting point of the memset call to zerofill the block is incorrectly specified, which can cause a buffer overflow on file systems with block sizes greater than 4KiB. In addition, if the superblock is moved within a large block, it is necessary to assume the possibility that the data in the superblock will be destroyed by zero-filling before copying. So fix these potential issues as well. Link: https://lkml.kernel.org/r/20230609035732.20426-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+31837fe952932efc8fb9@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/00000000000030000a05e981f475@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/segbuf.c | 6 ++++++ fs/nilfs2/segment.c | 7 +++++++ fs/nilfs2/super.c | 25 +++++++++++++++++++++++-- 3 files changed, 36 insertions(+), 2 deletions(-) diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 1a8729eded8b..9f435879a048 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -101,6 +101,12 @@ int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *segbuf) if (unlikely(!bh)) return -ENOMEM; + lock_buffer(bh); + if (!buffer_uptodate(bh)) { + memset(bh->b_data, 0, bh->b_size); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); nilfs_segbuf_add_segsum_buffer(segbuf, bh); return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index cdaca232ac4d..4a910c8a5691 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -984,10 +984,13 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, unsigned int isz, srsz; bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root; + + lock_buffer(bh_sr); raw_sr = (struct nilfs_super_root *)bh_sr->b_data; isz = nilfs->ns_inode_size; srsz = NILFS_SR_BYTES(isz); + raw_sr->sr_sum = 0; /* Ensure initialization within this update */ raw_sr->sr_bytes = cpu_to_le16(srsz); raw_sr->sr_nongc_ctime = cpu_to_le64(nilfs_doing_gc() ? @@ -1001,6 +1004,8 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr + NILFS_SR_SUFILE_OFFSET(isz), 1); memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz); + set_buffer_uptodate(bh_sr); + unlock_buffer(bh_sr); } static void nilfs_redirty_inodes(struct list_head *head) @@ -1783,6 +1788,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(segbuf, logs, sb_list) { list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1794,6 +1800,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) b_assoc_buffers) { clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 9aae60d9a32e..037456e9c511 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -372,10 +372,31 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) goto out; } nsbp = (void *)nsbh->b_data + offset; - memset(nsbp, 0, nilfs->ns_blocksize); + + lock_buffer(nsbh); + if (sb2i >= 0) { + /* + * The position of the second superblock only changes by 4KiB, + * which is larger than the maximum superblock data size + * (= 1KiB), so there is no need to use memmove() to allow + * overlap between source and destination. + */ + memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize); + + /* + * Zero fill after copy to avoid overwriting in case of move + * within the same block. + */ + memset(nsbh->b_data, 0, offset); + memset((void *)nsbp + nilfs->ns_sbsize, 0, + nsbh->b_size - offset - nilfs->ns_sbsize); + } else { + memset(nsbh->b_data, 0, nsbh->b_size); + } + set_buffer_uptodate(nsbh); + unlock_buffer(nsbh); if (sb2i >= 0) { - memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize); brelse(nilfs->ns_sbh[sb2i]); nilfs->ns_sbh[sb2i] = nsbh; nilfs->ns_sbp[sb2i] = nsbp; From 8b8c9812c04828dd8304e9680e88a1e0b458da67 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Thu, 18 May 2023 08:13:52 -0700 Subject: [PATCH 3629/4345] Drivers: hv: vmbus: Fix vmbus_wait_for_unload() to scan present CPUs commit 320805ab61e5f1e2a5729ae266e16bec2904050c upstream. vmbus_wait_for_unload() may be called in the panic path after other CPUs are stopped. vmbus_wait_for_unload() currently loops through online CPUs looking for the UNLOAD response message. But the values of CONFIG_KEXEC_CORE and crash_kexec_post_notifiers affect the path used to stop the other CPUs, and in one of the paths the stopped CPUs are removed from cpu_online_mask. This removal happens in both x86/x64 and arm64 architectures. In such a case, vmbus_wait_for_unload() only checks the panic'ing CPU, and misses the UNLOAD response message except when the panic'ing CPU is CPU 0. vmbus_wait_for_unload() eventually times out, but only after waiting 100 seconds. Fix this by looping through *present* CPUs in vmbus_wait_for_unload(). The cpu_present_mask is not modified by stopping the other CPUs in the panic path, nor should it be. Also, in a CoCo VM the synic_message_page is not allocated in hv_synic_alloc(), but is set and cleared in hv_synic_enable_regs() and hv_synic_disable_regs() such that it is set only when the CPU is online. If not all present CPUs are online when vmbus_wait_for_unload() is called, the synic_message_page might be NULL. Add a check for this. Fixes: cd95aad55793 ("Drivers: hv: vmbus: handle various crash scenarios") Cc: stable@vger.kernel.org Reported-by: John Starks Signed-off-by: Michael Kelley Reviewed-by: Vitaly Kuznetsov Link: https://lore.kernel.org/r/1684422832-38476-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel_mgmt.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 5b902adb0d1b..0c6c54061088 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -765,11 +765,22 @@ static void vmbus_wait_for_unload(void) if (completion_done(&vmbus_connection.unload_event)) goto completed; - for_each_online_cpu(cpu) { + for_each_present_cpu(cpu) { struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); + /* + * In a CoCo VM the synic_message_page is not allocated + * in hv_synic_alloc(). Instead it is set/cleared in + * hv_synic_enable_regs() and hv_synic_disable_regs() + * such that it is set only when the CPU is online. If + * not all present CPUs are online, the message page + * might be NULL, so skip such CPUs. + */ page_addr = hv_cpu->synic_message_page; + if (!page_addr) + continue; + msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT; @@ -803,11 +814,14 @@ completed: * maybe-pending messages on all CPUs to be able to receive new * messages after we reconnect. */ - for_each_online_cpu(cpu) { + for_each_present_cpu(cpu) { struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); page_addr = hv_cpu->synic_message_page; + if (!page_addr) + continue; + msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT; msg->header.message_type = HVMSG_NONE; } From 79ceb758e3dbddfd646d226e2262598b948225f4 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 14 Jun 2023 21:44:47 -0700 Subject: [PATCH 3630/4345] PCI: hv: Fix a race condition bug in hv_pci_query_relations() commit 440b5e3663271b0ffbd4908115044a6a51fb938b upstream. Since day 1 of the driver, there has been a race between hv_pci_query_relations() and survey_child_resources(): during fast device hotplug, hv_pci_query_relations() may error out due to device-remove and the stack variable 'comp' is no longer valid; however, pci_devices_present_work() -> survey_child_resources() -> complete() may be running on another CPU and accessing the no-longer-valid 'comp'. Fix the race by flushing the workqueue before we exit from hv_pci_query_relations(). Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Acked-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-2-decui@microsoft.com Signed-off-by: Wei Liu Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pci-hyperv.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 4353443b89d8..16d582e1a64b 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -2912,6 +2912,24 @@ static int hv_pci_query_relations(struct hv_device *hdev) if (!ret) ret = wait_for_response(hdev, &comp); + /* + * In the case of fast device addition/removal, it's possible that + * vmbus_sendpacket() or wait_for_response() returns -ENODEV but we + * already got a PCI_BUS_RELATIONS* message from the host and the + * channel callback already scheduled a work to hbus->wq, which can be + * running pci_devices_present_work() -> survey_child_resources() -> + * complete(&hbus->survey_event), even after hv_pci_query_relations() + * exits and the stack variable 'comp' is no longer valid; as a result, + * a hang or a page fault may happen when the complete() calls + * raw_spin_lock_irqsave(). Flush hbus->wq before we exit from + * hv_pci_query_relations() to avoid the issues. Note: if 'ret' is + * -ENODEV, there can't be any more work item scheduled to hbus->wq + * after the flush_workqueue(): see vmbus_onoffer_rescind() -> + * vmbus_reset_channel_cb(), vmbus_rescind_cleanup() -> + * channel->rescind = true. + */ + flush_workqueue(hbus->wq); + return ret; } From 8b7484676994a071f5bb6d5ed3f95950ee1a7e6d Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 14 Jun 2023 21:44:50 -0700 Subject: [PATCH 3631/4345] Revert "PCI: hv: Fix a timing issue which causes kdump to fail occasionally" commit a847234e24d03d01a9566d1d9dcce018cc018d67 upstream. This reverts commit d6af2ed29c7c1c311b96dac989dcb991e90ee195. The statement "the hv_pci_bus_exit() call releases structures of all its child devices" in commit d6af2ed29c7c is not true: in the path hv_pci_probe() -> hv_pci_enter_d0() -> hv_pci_bus_exit(hdev, true): the parameter "keep_devs" is true, so hv_pci_bus_exit() does *not* release the child "struct hv_pci_dev *hpdev" that is created earlier in pci_devices_present_work() -> new_pcichild_device(). The commit d6af2ed29c7c was originally made in July 2020 for RHEL 7.7, where the old version of hv_pci_bus_exit() was used; when the commit was rebased and merged into the upstream, people didn't notice that it's not really necessary. The commit itself doesn't cause any issue, but it makes hv_pci_probe() more complicated. Revert it to facilitate some upcoming changes to hv_pci_probe(). Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Acked-by: Wei Hu Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-5-decui@microsoft.com Signed-off-by: Wei Liu Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pci-hyperv.c | 71 ++++++++++++++--------------- 1 file changed, 34 insertions(+), 37 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 16d582e1a64b..6f7dc28deb6f 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -2842,8 +2842,10 @@ static int hv_pci_enter_d0(struct hv_device *hdev) struct pci_bus_d0_entry *d0_entry; struct hv_pci_compl comp_pkt; struct pci_packet *pkt; + bool retry = true; int ret; +enter_d0_retry: /* * Tell the host that the bus is ready to use, and moved into the * powered-on state. This includes telling the host which region @@ -2870,6 +2872,38 @@ static int hv_pci_enter_d0(struct hv_device *hdev) if (ret) goto exit; + /* + * In certain case (Kdump) the pci device of interest was + * not cleanly shut down and resource is still held on host + * side, the host could return invalid device status. + * We need to explicitly request host to release the resource + * and try to enter D0 again. + */ + if (comp_pkt.completion_status < 0 && retry) { + retry = false; + + dev_err(&hdev->device, "Retrying D0 Entry\n"); + + /* + * Hv_pci_bus_exit() calls hv_send_resource_released() + * to free up resources of its child devices. + * In the kdump kernel we need to set the + * wslot_res_allocated to 255 so it scans all child + * devices to release resources allocated in the + * normal kernel before panic happened. + */ + hbus->wslot_res_allocated = 255; + + ret = hv_pci_bus_exit(hdev, true); + + if (ret == 0) { + kfree(pkt); + goto enter_d0_retry; + } + dev_err(&hdev->device, + "Retrying D0 failed with ret %d\n", ret); + } + if (comp_pkt.completion_status < 0) { dev_err(&hdev->device, "PCI Pass-through VSP failed D0 Entry with status %x\n", @@ -3125,7 +3159,6 @@ static int hv_pci_probe(struct hv_device *hdev, struct hv_pcibus_device *hbus; u16 dom_req, dom; char *name; - bool enter_d0_retry = true; int ret; /* @@ -3246,47 +3279,11 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_fwnode; -retry: ret = hv_pci_query_relations(hdev); if (ret) goto free_irq_domain; ret = hv_pci_enter_d0(hdev); - /* - * In certain case (Kdump) the pci device of interest was - * not cleanly shut down and resource is still held on host - * side, the host could return invalid device status. - * We need to explicitly request host to release the resource - * and try to enter D0 again. - * Since the hv_pci_bus_exit() call releases structures - * of all its child devices, we need to start the retry from - * hv_pci_query_relations() call, requesting host to send - * the synchronous child device relations message before this - * information is needed in hv_send_resources_allocated() - * call later. - */ - if (ret == -EPROTO && enter_d0_retry) { - enter_d0_retry = false; - - dev_err(&hdev->device, "Retrying D0 Entry\n"); - - /* - * Hv_pci_bus_exit() calls hv_send_resources_released() - * to free up resources of its child devices. - * In the kdump kernel we need to set the - * wslot_res_allocated to 255 so it scans all child - * devices to release resources allocated in the - * normal kernel before panic happened. - */ - hbus->wslot_res_allocated = 255; - ret = hv_pci_bus_exit(hdev, true); - - if (ret == 0) - goto retry; - - dev_err(&hdev->device, - "Retrying D0 failed with ret %d\n", ret); - } if (ret) goto free_irq_domain; From 8f2d5ebdfef77f8ceeca31bfe129c2310a897333 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 14 Jun 2023 21:44:49 -0700 Subject: [PATCH 3632/4345] PCI: hv: Remove the useless hv_pcichild_state from struct hv_pci_dev commit add9195e69c94b32e96f78c2f9cea68f0e850b3f upstream. The hpdev->state is never really useful. The only use in hv_pci_eject_device() and hv_eject_device_work() is not really necessary. Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Acked-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-4-decui@microsoft.com Signed-off-by: Wei Liu Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pci-hyperv.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 6f7dc28deb6f..55a77d901a1f 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -520,19 +520,10 @@ struct hv_dr_state { struct hv_pcidev_description func[]; }; -enum hv_pcichild_state { - hv_pcichild_init = 0, - hv_pcichild_requirements, - hv_pcichild_resourced, - hv_pcichild_ejecting, - hv_pcichild_maximum -}; - struct hv_pci_dev { /* List protected by pci_rescan_remove_lock */ struct list_head list_entry; refcount_t refs; - enum hv_pcichild_state state; struct pci_slot *pci_slot; struct hv_pcidev_description desc; bool reported_missing; @@ -2378,8 +2369,6 @@ static void hv_eject_device_work(struct work_struct *work) hpdev = container_of(work, struct hv_pci_dev, wrk); hbus = hpdev->hbus; - WARN_ON(hpdev->state != hv_pcichild_ejecting); - /* * Ejection can come before or after the PCI bus has been set up, so * attempt to find it and tear down the bus state, if it exists. This @@ -2438,7 +2427,6 @@ static void hv_pci_eject_device(struct hv_pci_dev *hpdev) return; } - hpdev->state = hv_pcichild_ejecting; get_pcichild(hpdev); INIT_WORK(&hpdev->wrk, hv_eject_device_work); get_hvpcibus(hbus); From 988d06f5eb3215e51029e3a93b8f76f005db33d2 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 14 Jun 2023 21:44:48 -0700 Subject: [PATCH 3633/4345] PCI: hv: Fix a race condition in hv_irq_unmask() that can cause panic commit 2738d5ab7929a845b654cd171a1e275c37eb428e upstream. When the host tries to remove a PCI device, the host first sends a PCI_EJECT message to the guest, and the guest is supposed to gracefully remove the PCI device and send a PCI_EJECTION_COMPLETE message to the host; the host then sends a VMBus message CHANNELMSG_RESCIND_CHANNELOFFER to the guest (when the guest receives this message, the device is already unassigned from the guest) and the guest can do some final cleanup work; if the guest fails to respond to the PCI_EJECT message within one minute, the host sends the VMBus message CHANNELMSG_RESCIND_CHANNELOFFER and removes the PCI device forcibly. In the case of fast device addition/removal, it's possible that the PCI device driver is still configuring MSI-X interrupts when the guest receives the PCI_EJECT message; the channel callback calls hv_pci_eject_device(), which sets hpdev->state to hv_pcichild_ejecting, and schedules a work hv_eject_device_work(); if the PCI device driver is calling pci_alloc_irq_vectors() -> ... -> hv_compose_msi_msg(), we can break the while loop in hv_compose_msi_msg() due to the updated hpdev->state, and leave data->chip_data with its default value of NULL; later, when the PCI device driver calls request_irq() -> ... -> hv_irq_unmask(), the guest crashes in hv_arch_irq_unmask() due to data->chip_data being NULL. Fix the issue by not testing hpdev->state in the while loop: when the guest receives PCI_EJECT, the device is still assigned to the guest, and the guest has one minute to finish the device removal gracefully. We don't really need to (and we should not) test hpdev->state in the loop. Fixes: de0aa7b2f97d ("PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()") Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-3-decui@microsoft.com Signed-off-by: Wei Liu Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pci-hyperv.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 55a77d901a1f..2d6c77dcc815 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1228,6 +1228,11 @@ static void hv_irq_unmask(struct irq_data *data) pbus = pdev->bus; hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); int_desc = data->chip_data; + if (!int_desc) { + dev_warn(&hbus->hdev->device, "%s() can not unmask irq %u\n", + __func__, data->irq); + return; + } spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags); @@ -1544,12 +1549,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) hv_pci_onchannelcallback(hbus); spin_unlock_irqrestore(&channel->sched_lock, flags); - if (hpdev->state == hv_pcichild_ejecting) { - dev_err_once(&hbus->hdev->device, - "the device is being ejected\n"); - goto enable_tasklet; - } - udelay(100); } From 63608437a83ddabe497cfc163237e654eb563701 Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Sat, 10 Jun 2023 17:26:43 +0800 Subject: [PATCH 3634/4345] cgroup: Do not corrupt task iteration when rebinding subsystem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 6f363f5aa845561f7ea496d8b1175e3204470486 upstream. We found a refcount UAF bug as follows: refcount_t: addition on 0; use-after-free. WARNING: CPU: 1 PID: 342 at lib/refcount.c:25 refcount_warn_saturate+0xa0/0x148 Workqueue: events cpuset_hotplug_workfn Call trace: refcount_warn_saturate+0xa0/0x148 __refcount_add.constprop.0+0x5c/0x80 css_task_iter_advance_css_set+0xd8/0x210 css_task_iter_advance+0xa8/0x120 css_task_iter_next+0x94/0x158 update_tasks_root_domain+0x58/0x98 rebuild_root_domains+0xa0/0x1b0 rebuild_sched_domains_locked+0x144/0x188 cpuset_hotplug_workfn+0x138/0x5a0 process_one_work+0x1e8/0x448 worker_thread+0x228/0x3e0 kthread+0xe0/0xf0 ret_from_fork+0x10/0x20 then a kernel panic will be triggered as below: Unable to handle kernel paging request at virtual address 00000000c0000010 Call trace: cgroup_apply_control_disable+0xa4/0x16c rebind_subsystems+0x224/0x590 cgroup_destroy_root+0x64/0x2e0 css_free_rwork_fn+0x198/0x2a0 process_one_work+0x1d4/0x4bc worker_thread+0x158/0x410 kthread+0x108/0x13c ret_from_fork+0x10/0x18 The race that cause this bug can be shown as below: (hotplug cpu) | (umount cpuset) mutex_lock(&cpuset_mutex) | mutex_lock(&cgroup_mutex) cpuset_hotplug_workfn | rebuild_root_domains | rebind_subsystems update_tasks_root_domain | spin_lock_irq(&css_set_lock) css_task_iter_start | list_move_tail(&cset->e_cset_node[ss->id] while(css_task_iter_next) | &dcgrp->e_csets[ss->id]); css_task_iter_end | spin_unlock_irq(&css_set_lock) mutex_unlock(&cpuset_mutex) | mutex_unlock(&cgroup_mutex) Inside css_task_iter_start/next/end, css_set_lock is hold and then released, so when iterating task(left side), the css_set may be moved to another list(right side), then it->cset_head points to the old list head and it->cset_pos->next points to the head node of new list, which can't be used as struct css_set. To fix this issue, switch from all css_sets to only scgrp's css_sets to patch in-flight iterators to preserve correct iteration, and then update it->cset_head as well. Reported-by: Gaosheng Cui Link: https://www.spinics.net/lists/cgroups/msg37935.html Suggested-by: Michal Koutný Link: https://lore.kernel.org/all/20230526114139.70274-1-xiujianfeng@huaweicloud.com/ Signed-off-by: Xiu Jianfeng Fixes: 2d8f243a5e6e ("cgroup: implement cgroup->e_csets[]") Cc: stable@vger.kernel.org # v3.16+ Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- kernel/cgroup/cgroup.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index f123b7f64249..70ed21607e47 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1712,7 +1712,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; - int ssid, i, ret; + int ssid, ret; u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); @@ -1756,7 +1756,8 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); - struct css_set *cset; + struct css_set *cset, *cset_pos; + struct css_task_iter *it; WARN_ON(!css || cgroup_css(dcgrp, ss)); @@ -1774,9 +1775,22 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) css->cgroup = dcgrp; spin_lock_irq(&css_set_lock); - hash_for_each(css_set_table, i, cset, hlist) + WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); + list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], + e_cset_node[ss->id]) { list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); + /* + * all css_sets of scgrp together in same order to dcgrp, + * patch in-flight iterators to preserve correct iteration. + * since the iterator is always advanced right away and + * finished when it->cset_pos meets it->cset_head, so only + * update it->cset_head is enough here. + */ + list_for_each_entry(it, &cset->task_iters, iters_node) + if (it->cset_head == &scgrp->e_csets[ss->id]) + it->cset_head = &dcgrp->e_csets[ss->id]; + } spin_unlock_irq(&css_set_lock); /* default hierarchy doesn't enable controllers by default */ From 1b97630cd9a9d66c9f5189a0a6a65438735f5b0c Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Thu, 18 May 2023 11:39:36 +0200 Subject: [PATCH 3635/4345] mmc: sdhci-msm: Disable broken 64-bit DMA on MSM8916 commit e6f9e590b72e12bbb86b1b8be7e1981f357392ad upstream. While SDHCI claims to support 64-bit DMA on MSM8916 it does not seem to be properly functional. It is not immediately obvious because SDHCI is usually used with IOMMU bypassed on this SoC, and all physical memory has 32-bit addresses. But when trying to enable the IOMMU it quickly fails with an error such as the following: arm-smmu 1e00000.iommu: Unhandled context fault: fsr=0x402, iova=0xfffff200, fsynr=0xe0000, cbfrsynra=0x140, cb=3 mmc1: ADMA error: 0x02000000 mmc1: sdhci: ============ SDHCI REGISTER DUMP =========== mmc1: sdhci: Sys addr: 0x00000000 | Version: 0x00002e02 mmc1: sdhci: Blk size: 0x00000008 | Blk cnt: 0x00000000 mmc1: sdhci: Argument: 0x00000000 | Trn mode: 0x00000013 mmc1: sdhci: Present: 0x03f80206 | Host ctl: 0x00000019 mmc1: sdhci: Power: 0x0000000f | Blk gap: 0x00000000 mmc1: sdhci: Wake-up: 0x00000000 | Clock: 0x00000007 mmc1: sdhci: Timeout: 0x0000000a | Int stat: 0x00000001 mmc1: sdhci: Int enab: 0x03ff900b | Sig enab: 0x03ff100b mmc1: sdhci: ACmd stat: 0x00000000 | Slot int: 0x00000000 mmc1: sdhci: Caps: 0x322dc8b2 | Caps_1: 0x00008007 mmc1: sdhci: Cmd: 0x0000333a | Max curr: 0x00000000 mmc1: sdhci: Resp[0]: 0x00000920 | Resp[1]: 0x5b590000 mmc1: sdhci: Resp[2]: 0xe6487f80 | Resp[3]: 0x0a404094 mmc1: sdhci: Host ctl2: 0x00000008 mmc1: sdhci: ADMA Err: 0x00000001 | ADMA Ptr: 0x0000000ffffff224 mmc1: sdhci_msm: ----------- VENDOR REGISTER DUMP ----------- mmc1: sdhci_msm: DLL sts: 0x00000000 | DLL cfg: 0x60006400 | DLL cfg2: 0x00000000 mmc1: sdhci_msm: DLL cfg3: 0x00000000 | DLL usr ctl: 0x00000000 | DDR cfg: 0x00000000 mmc1: sdhci_msm: Vndr func: 0x00018a9c | Vndr func2 : 0xf88018a8 Vndr func3: 0x00000000 mmc1: sdhci: ============================================ mmc1: sdhci: fffffffff200: DMA 0x0000ffffffffe100, LEN 0x0008, Attr=0x21 mmc1: sdhci: fffffffff20c: DMA 0x0000000000000000, LEN 0x0000, Attr=0x03 Looking closely it's obvious that only the 32-bit part of the address (0xfffff200) arrives at the SMMU, the higher 16-bit (0xffff...) get lost somewhere. This might not be a limitation of the SDHCI itself but perhaps the bus/interconnect it is connected to, or even the connection to the SMMU. Work around this by setting SDHCI_QUIRK2_BROKEN_64_BIT_DMA to avoid using 64-bit addresses. Signed-off-by: Stephan Gerhold Acked-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230518-msm8916-64bit-v1-1-5694b0f35211@gerhold.net Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/sdhci-msm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index ad2e73f9a58f..3366956a4ff1 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -2228,6 +2228,9 @@ static inline void sdhci_msm_get_of_property(struct platform_device *pdev, msm_host->ddr_config = DDR_CONFIG_POR_VAL; of_property_read_u32(node, "qcom,dll-config", &msm_host->dll_config); + + if (of_device_is_compatible(node, "qcom,msm8916-sdhci")) + host->quirks2 |= SDHCI_QUIRK2_BROKEN_64_BIT_DMA; } static int sdhci_msm_gcc_reset(struct device *dev, struct sdhci_host *host) From 1be288fd3b0d2f6c7a763680faa614f4b5a08449 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Hundeb=C3=B8ll?= Date: Wed, 7 Jun 2023 10:27:12 +0200 Subject: [PATCH 3636/4345] mmc: meson-gx: remove redundant mmc_request_done() call from irq context MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 3c40eb8145325b0f5b93b8a169146078cb2c49d6 upstream. The call to mmc_request_done() can schedule, so it must not be called from irq context. Wake the irq thread if it needs to be called, and let its existing logic do its work. Fixes the following kernel bug, which appears when running an RT patched kernel on the AmLogic Meson AXG A113X SoC: [ 11.111407] BUG: scheduling while atomic: kworker/0:1H/75/0x00010001 [ 11.111438] Modules linked in: [ 11.111451] CPU: 0 PID: 75 Comm: kworker/0:1H Not tainted 6.4.0-rc3-rt2-rtx-00081-gfd07f41ed6b4-dirty #1 [ 11.111461] Hardware name: RTX AXG A113X Linux Platform Board (DT) [ 11.111469] Workqueue: kblockd blk_mq_run_work_fn [ 11.111492] Call trace: [ 11.111497] dump_backtrace+0xac/0xe8 [ 11.111510] show_stack+0x18/0x28 [ 11.111518] dump_stack_lvl+0x48/0x60 [ 11.111530] dump_stack+0x18/0x24 [ 11.111537] __schedule_bug+0x4c/0x68 [ 11.111548] __schedule+0x80/0x574 [ 11.111558] schedule_loop+0x2c/0x50 [ 11.111567] schedule_rtlock+0x14/0x20 [ 11.111576] rtlock_slowlock_locked+0x468/0x730 [ 11.111587] rt_spin_lock+0x40/0x64 [ 11.111596] __wake_up_common_lock+0x5c/0xc4 [ 11.111610] __wake_up+0x18/0x24 [ 11.111620] mmc_blk_mq_req_done+0x68/0x138 [ 11.111633] mmc_request_done+0x104/0x118 [ 11.111644] meson_mmc_request_done+0x38/0x48 [ 11.111654] meson_mmc_irq+0x128/0x1f0 [ 11.111663] __handle_irq_event_percpu+0x70/0x114 [ 11.111674] handle_irq_event_percpu+0x18/0x4c [ 11.111683] handle_irq_event+0x80/0xb8 [ 11.111691] handle_fasteoi_irq+0xa4/0x120 [ 11.111704] handle_irq_desc+0x20/0x38 [ 11.111712] generic_handle_domain_irq+0x1c/0x28 [ 11.111721] gic_handle_irq+0x8c/0xa8 [ 11.111735] call_on_irq_stack+0x24/0x4c [ 11.111746] do_interrupt_handler+0x88/0x94 [ 11.111757] el1_interrupt+0x34/0x64 [ 11.111769] el1h_64_irq_handler+0x18/0x24 [ 11.111779] el1h_64_irq+0x64/0x68 [ 11.111786] __add_wait_queue+0x0/0x4c [ 11.111795] mmc_blk_rw_wait+0x84/0x118 [ 11.111804] mmc_blk_mq_issue_rq+0x5c4/0x654 [ 11.111814] mmc_mq_queue_rq+0x194/0x214 [ 11.111822] blk_mq_dispatch_rq_list+0x3ac/0x528 [ 11.111834] __blk_mq_sched_dispatch_requests+0x340/0x4d0 [ 11.111847] blk_mq_sched_dispatch_requests+0x38/0x70 [ 11.111858] blk_mq_run_work_fn+0x3c/0x70 [ 11.111865] process_one_work+0x17c/0x1f0 [ 11.111876] worker_thread+0x1d4/0x26c [ 11.111885] kthread+0xe4/0xf4 [ 11.111894] ret_from_fork+0x10/0x20 Fixes: 51c5d8447bd7 ("MMC: meson: initial support for GX platforms") Cc: stable@vger.kernel.org Signed-off-by: Martin Hundebøll Link: https://lore.kernel.org/r/20230607082713.517157-1-martin@geanix.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/meson-gx-mmc.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 19a6b55e344f..e89bd6f4b317 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -970,11 +970,8 @@ static irqreturn_t meson_mmc_irq(int irq, void *dev_id) if (status & (IRQ_END_OF_CHAIN | IRQ_RESP_STATUS)) { if (data && !cmd->error) data->bytes_xfered = data->blksz * data->blocks; - if (meson_mmc_bounce_buf_read(data) || - meson_mmc_get_next_command(cmd)) - ret = IRQ_WAKE_THREAD; - else - ret = IRQ_HANDLED; + + return IRQ_WAKE_THREAD; } out: @@ -986,9 +983,6 @@ out: writel(start, host->regs + SD_EMMC_START); } - if (ret == IRQ_HANDLED) - meson_mmc_request_done(host->mmc, cmd->mrq); - return ret; } From 2e454015ca273a794e9311b4eda7b9659b09ad0d Mon Sep 17 00:00:00 2001 From: Christophe Kerello Date: Tue, 13 Jun 2023 15:41:46 +0200 Subject: [PATCH 3637/4345] mmc: mmci: stm32: fix max busy timeout calculation commit 47b3ad6b7842f49d374a01b054a4b1461a621bdc upstream. The way that the timeout is currently calculated could lead to a u64 timeout value in mmci_start_command(). This value is then cast in a u32 register that leads to mmc erase failed issue with some SD cards. Fixes: 8266c585f489 ("mmc: mmci: add hardware busy timeout feature") Signed-off-by: Yann Gautier Signed-off-by: Christophe Kerello Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230613134146.418016-1-yann.gautier@foss.st.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/mmci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 5d83c8e7bf5c..9cfffcecc9eb 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -1728,7 +1728,8 @@ static void mmci_set_max_busy_timeout(struct mmc_host *mmc) return; if (host->variant->busy_timeout && mmc->actual_clock) - max_busy_timeout = ~0UL / (mmc->actual_clock / MSEC_PER_SEC); + max_busy_timeout = U32_MAX / DIV_ROUND_UP(mmc->actual_clock, + MSEC_PER_SEC); mmc->max_busy_timeout = max_busy_timeout; } From 5938470f9c8015eeb08e1452e5e7782734400202 Mon Sep 17 00:00:00 2001 From: Matthias May Date: Thu, 21 Jul 2022 22:27:19 +0200 Subject: [PATCH 3638/4345] ip_tunnels: allow VXLAN/GENEVE to inherit TOS/TTL from VLAN commit 7074732c8faee201a245a6f983008a5789c0be33 upstream. The current code allows for VXLAN and GENEVE to inherit the TOS respective the TTL when skb-protocol is ETH_P_IP or ETH_P_IPV6. However when the payload is VLAN encapsulated, then this inheriting does not work, because the visible skb-protocol is of type ETH_P_8021Q or ETH_P_8021AD. Instead of skb->protocol use skb_protocol(). Signed-off-by: Matthias May Link: https://lore.kernel.org/r/20220721202718.10092-1-matthias.may@westermo.com Signed-off-by: Jakub Kicinski Cc: Nicolas Dichtel Signed-off-by: Greg Kroah-Hartman --- include/net/ip_tunnels.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index c3e55a9ae585..1ddd401a8981 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -378,9 +378,11 @@ static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t, static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, const struct sk_buff *skb) { - if (skb->protocol == htons(ETH_P_IP)) + __be16 payload_protocol = skb_protocol(skb, true); + + if (payload_protocol == htons(ETH_P_IP)) return iph->tos; - else if (skb->protocol == htons(ETH_P_IPV6)) + else if (payload_protocol == htons(ETH_P_IPV6)) return ipv6_get_dsfield((const struct ipv6hdr *)iph); else return 0; @@ -389,9 +391,11 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, const struct sk_buff *skb) { - if (skb->protocol == htons(ETH_P_IP)) + __be16 payload_protocol = skb_protocol(skb, true); + + if (payload_protocol == htons(ETH_P_IP)) return iph->ttl; - else if (skb->protocol == htons(ETH_P_IPV6)) + else if (payload_protocol == htons(ETH_P_IPV6)) return ((const struct ipv6hdr *)iph)->hop_limit; else return 0; From bc35f93e4bd7b134c09506c9d1f794c0c93f467c Mon Sep 17 00:00:00 2001 From: Teresa Remmet Date: Wed, 14 Jun 2023 14:52:40 +0200 Subject: [PATCH 3639/4345] regulator: pca9450: Fix LDO3OUT and LDO4OUT MASK [ Upstream commit 7257d930aadcd62d1c7971ab14f3b1126356abdc ] L3_OUT and L4_OUT Bit fields range from Bit 0:4 and thus the mask should be 0x1F instead of 0x0F. Fixes: 0935ff5f1f0a ("regulator: pca9450: add pca9450 pmic driver") Signed-off-by: Teresa Remmet Reviewed-by: Frieder Schrempf Link: https://lore.kernel.org/r/20230614125240.3946519-1-t.remmet@phytec.de Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- include/linux/regulator/pca9450.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 71902f41c919..0c3edff6bdff 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -196,11 +196,11 @@ enum { /* PCA9450_REG_LDO3_VOLT bits */ #define LDO3_EN_MASK 0xC0 -#define LDO3OUT_MASK 0x0F +#define LDO3OUT_MASK 0x1F /* PCA9450_REG_LDO4_VOLT bits */ #define LDO4_EN_MASK 0xC0 -#define LDO4OUT_MASK 0x0F +#define LDO4OUT_MASK 0x1F /* PCA9450_REG_LDO5_VOLT bits */ #define LDO5L_EN_MASK 0xC0 From f00cd687c2cd150219cd5a91799f7d1140562bcd Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Tue, 20 Jun 2023 13:28:24 -0700 Subject: [PATCH 3640/4345] regmap: spi-avmm: Fix regmap_bus max_raw_write [ Upstream commit c8e796895e2310b6130e7577248da1d771431a77 ] The max_raw_write member of the regmap_spi_avmm_bus structure is defined as: .max_raw_write = SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT SPI_AVMM_VAL_SIZE == 4 and MAX_WRITE_CNT == 1 so this results in a maximum write transfer size of 4 bytes which provides only enough space to transfer the address of the target register. It provides no space for the value to be transferred. This bug became an issue (divide-by-zero in _regmap_raw_write()) after the following was accepted into mainline: commit 3981514180c9 ("regmap: Account for register length when chunking") Change max_raw_write to include space (4 additional bytes) for both the register address and value: .max_raw_write = SPI_AVMM_REG_SIZE + SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT Fixes: 7f9fb67358a2 ("regmap: add Intel SPI Slave to AVMM Bus Bridge support") Reviewed-by: Matthew Gerlach Signed-off-by: Russ Weight Link: https://lore.kernel.org/r/20230620202824.380313-1-russell.h.weight@intel.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/base/regmap/regmap-spi-avmm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/regmap/regmap-spi-avmm.c b/drivers/base/regmap/regmap-spi-avmm.c index ad1da83e849f..67f89937219c 100644 --- a/drivers/base/regmap/regmap-spi-avmm.c +++ b/drivers/base/regmap/regmap-spi-avmm.c @@ -666,7 +666,7 @@ static const struct regmap_bus regmap_spi_avmm_bus = { .reg_format_endian_default = REGMAP_ENDIAN_NATIVE, .val_format_endian_default = REGMAP_ENDIAN_NATIVE, .max_raw_read = SPI_AVMM_VAL_SIZE * MAX_READ_CNT, - .max_raw_write = SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, + .max_raw_write = SPI_AVMM_REG_SIZE + SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, .free_context = spi_avmm_bridge_ctx_free, }; From 5a7101d8faab97fb1e258b134c2afc1ccad9c2d9 Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Tue, 6 Jun 2023 19:36:13 -0400 Subject: [PATCH 3641/4345] writeback: fix dereferencing NULL mapping->host on writeback_page_template commit 54abe19e00cfcc5a72773d15cd00ed19ab763439 upstream. When commit 19343b5bdd16 ("mm/page-writeback: introduce tracepoint for wait_on_page_writeback()") repurposed the writeback_dirty_page trace event as a template to create its new wait_on_page_writeback trace event, it ended up opening a window to NULL pointer dereference crashes due to the (infrequent) occurrence of a race where an access to a page in the swap-cache happens concurrently with the moment this page is being written to disk and the tracepoint is enabled: BUG: kernel NULL pointer dereference, address: 0000000000000040 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 800000010ec0a067 P4D 800000010ec0a067 PUD 102353067 PMD 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 1320 Comm: shmem-worker Kdump: loaded Not tainted 6.4.0-rc5+ #13 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20230301gitf80f052277c8-1.fc37 03/01/2023 RIP: 0010:trace_event_raw_event_writeback_folio_template+0x76/0xf0 Code: 4d 85 e4 74 5c 49 8b 3c 24 e8 06 98 ee ff 48 89 c7 e8 9e 8b ee ff ba 20 00 00 00 48 89 ef 48 89 c6 e8 fe d4 1a 00 49 8b 04 24 <48> 8b 40 40 48 89 43 28 49 8b 45 20 48 89 e7 48 89 43 30 e8 a2 4d RSP: 0000:ffffaad580b6fb60 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff90e38035c01c RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff90e38035c044 RBP: ffff90e38035c024 R08: 0000000000000002 R09: 0000000000000006 R10: ffff90e38035c02e R11: 0000000000000020 R12: ffff90e380bac000 R13: ffffe3a7456d9200 R14: 0000000000001b81 R15: ffffe3a7456d9200 FS: 00007f2e4e8a15c0(0000) GS:ffff90e3fbc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000040 CR3: 00000001150c6003 CR4: 0000000000170ee0 Call Trace: ? __die+0x20/0x70 ? page_fault_oops+0x76/0x170 ? kernelmode_fixup_or_oops+0x84/0x110 ? exc_page_fault+0x65/0x150 ? asm_exc_page_fault+0x22/0x30 ? trace_event_raw_event_writeback_folio_template+0x76/0xf0 folio_wait_writeback+0x6b/0x80 shmem_swapin_folio+0x24a/0x500 ? filemap_get_entry+0xe3/0x140 shmem_get_folio_gfp+0x36e/0x7c0 ? find_busiest_group+0x43/0x1a0 shmem_fault+0x76/0x2a0 ? __update_load_avg_cfs_rq+0x281/0x2f0 __do_fault+0x33/0x130 do_read_fault+0x118/0x160 do_pte_missing+0x1ed/0x2a0 __handle_mm_fault+0x566/0x630 handle_mm_fault+0x91/0x210 do_user_addr_fault+0x22c/0x740 exc_page_fault+0x65/0x150 asm_exc_page_fault+0x22/0x30 This problem arises from the fact that the repurposed writeback_dirty_page trace event code was written assuming that every pointer to mapping (struct address_space) would come from a file-mapped page-cache object, thus mapping->host would always be populated, and that was a valid case before commit 19343b5bdd16. The swap-cache address space (swapper_spaces), however, doesn't populate its ->host (struct inode) pointer, thus leading to the crashes in the corner-case aforementioned. commit 19343b5bdd16 ended up breaking the assignment of __entry->name and __entry->ino for the wait_on_page_writeback tracepoint -- both dependent on mapping->host carrying a pointer to a valid inode. The assignment of __entry->name was fixed by commit 68f23b89067f ("memcg: fix a crash in wb_workfn when a device disappears"), and this commit fixes the remaining case, for __entry->ino. Link: https://lkml.kernel.org/r/20230606233613.1290819-1-aquini@redhat.com Fixes: 19343b5bdd16 ("mm/page-writeback: introduce tracepoint for wait_on_page_writeback()") Signed-off-by: Rafael Aquini Reviewed-by: Yafang Shao Cc: Aristeu Rozanski Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/trace/events/writeback.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 57d795365987..453255afbe2d 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -67,7 +67,7 @@ DECLARE_EVENT_CLASS(writeback_page_template, strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); - __entry->ino = mapping ? mapping->host->i_ino : 0; + __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = page->index; ), From 5fdea4468f57db3fc304e366d03d7214ca3a209e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Jun 2023 07:38:14 -0600 Subject: [PATCH 3642/4345] io_uring/net: save msghdr->msg_control for retries Commit cac9e4418f4cbd548ccb065b3adcafe073f7f7d2 upstream. If the application sets ->msg_control and we have to later retry this command, or if it got queued with IOSQE_ASYNC to begin with, then we need to retain the original msg_control value. This is due to the net stack overwriting this field with an in-kernel pointer, to copy it in. Hitting that path for the second time will now fail the copy from user, as it's attempting to copy from a non-user address. Cc: stable@vger.kernel.org # 5.10+ Link: https://github.com/axboe/liburing/issues/880 Reported-and-tested-by: Marek Majkowski Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 58e063114398..1a76659659cf 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -581,6 +581,7 @@ struct io_sr_msg { size_t len; size_t done_io; struct io_buffer *kbuf; + void __user *msg_control; }; struct io_open { @@ -4718,10 +4719,16 @@ static int io_setup_async_msg(struct io_kiocb *req, static int io_sendmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { + struct io_sr_msg *sr = &req->sr_msg; + int ret; + iomsg->msg.msg_name = &iomsg->addr; iomsg->free_iov = iomsg->fast_iov; - return sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg, + ret = sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg, req->sr_msg.msg_flags, &iomsg->free_iov); + /* save msg_control as sys_sendmsg() overwrites it */ + sr->msg_control = iomsg->msg.msg_control; + return ret; } static int io_sendmsg_prep_async(struct io_kiocb *req) @@ -4778,6 +4785,8 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) if (ret) return ret; kmsg = &iomsg; + } else { + kmsg->msg.msg_control = sr->msg_control; } flags = req->sr_msg.msg_flags; From 826ee9fa3647785e45ca87aa70511b72d25c2588 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Jun 2023 07:39:42 -0600 Subject: [PATCH 3643/4345] io_uring/net: clear msg_controllen on partial sendmsg retry Commit b1dc492087db0f2e5a45f1072a743d04618dd6be upstream. If we have cmsg attached AND we transferred partial data at least, clear msg_controllen on retry so we don't attempt to send that again. Cc: stable@vger.kernel.org # 5.10+ Fixes: cac9e4418f4c ("io_uring/net: save msghdr->msg_control for retries") Reported-by: Stefan Metzmacher Reviewed-by: Stefan Metzmacher Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 1a76659659cf..42b5f9575d84 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5064,6 +5064,8 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { + kmsg->msg.msg_controllen = 0; + kmsg->msg.msg_control = NULL; sr->done_io += ret; req->flags |= REQ_F_PARTIAL_IO; return io_setup_async_msg(req, kmsg); From 3845c38417bdec561ccc4385e044c554ad837684 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Jun 2023 07:41:10 -0600 Subject: [PATCH 3644/4345] io_uring/net: disable partial retries for recvmsg with cmsg Commit 78d0d2063bab954d19a1696feae4c7706a626d48 upstream. We cannot sanely handle partial retries for recvmsg if we have cmsg attached. If we don't, then we'd just be overwriting the initial cmsg header on retries. Alternatively we could increment and handle this appropriately, but it doesn't seem worth the complication. Move the MSG_WAITALL check into the non-multishot case while at it, since MSG_WAITALL is explicitly disabled for multishot anyway. Link: https://lore.kernel.org/io-uring/0b0d4411-c8fd-4272-770b-e030af6919a0@kernel.dk/ Cc: stable@vger.kernel.org # 5.10+ Reported-by: Stefan Metzmacher Reviewed-by: Stefan Metzmacher Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 42b5f9575d84..f169b4645769 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5053,7 +5053,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) flags = req->sr_msg.msg_flags; if (force_nonblock) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) + if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen) min_ret = iov_iter_count(&kmsg->msg.msg_iter); ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg, From 4de2093674f2cb4cedc344fc766de57aa198f3b6 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 12 Jun 2023 11:14:56 +0900 Subject: [PATCH 3645/4345] nilfs2: prevent general protection fault in nilfs_clear_dirty_page() commit 782e53d0c14420858dbf0f8f797973c150d3b6d7 upstream. In a syzbot stress test that deliberately causes file system errors on nilfs2 with a corrupted disk image, it has been reported that nilfs_clear_dirty_page() called from nilfs_clear_dirty_pages() can cause a general protection fault. In nilfs_clear_dirty_pages(), when looking up dirty pages from the page cache and calling nilfs_clear_dirty_page() for each dirty page/folio retrieved, the back reference from the argument page to "mapping" may have been changed to NULL (and possibly others). It is necessary to check this after locking the page/folio. So, fix this issue by not calling nilfs_clear_dirty_page() on a page/folio after locking it in nilfs_clear_dirty_pages() if the back reference "mapping" from the page/folio is different from the "mapping" that held the page/folio just before. Link: https://lkml.kernel.org/r/20230612021456.3682-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+53369d11851d8f26735c@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/000000000000da4f6b05eb9bf593@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/nilfs2/page.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index d1a148f0cae3..81992b9a219b 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -369,7 +369,15 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) struct page *page = pvec.pages[i]; lock_page(page); - nilfs_clear_dirty_page(page, silent); + + /* + * This page may have been removed from the address + * space by truncation or invalidation when the lock + * was acquired. Skip processing in that case. + */ + if (likely(page->mapping == mapping)) + nilfs_clear_dirty_page(page, silent); + unlock_page(page); } pagevec_release(&pvec); From ad10dd21137081303dccde90a2434309d5762690 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 14 Jun 2023 17:38:54 +0100 Subject: [PATCH 3646/4345] x86/mm: Avoid using set_pgd() outside of real PGD pages commit d082d48737c75d2b3cc1f972b8c8674c25131534 upstream. KPTI keeps around two PGDs: one for userspace and another for the kernel. Among other things, set_pgd() contains infrastructure to ensure that updates to the kernel PGD are reflected in the user PGD as well. One side-effect of this is that set_pgd() expects to be passed whole pages. Unfortunately, init_trampoline_kaslr() passes in a single entry: 'trampoline_pgd_entry'. When KPTI is on, set_pgd() will update 'trampoline_pgd_entry' (an 8-Byte globally stored [.bss] variable) and will then proceed to replicate that value into the non-existent neighboring user page (located +4k away), leading to the corruption of other global [.bss] stored variables. Fix it by directly assigning 'trampoline_pgd_entry' and avoiding set_pgd(). [ dhansen: tweak subject and changelog ] Fixes: 0925dda5962e ("x86/mm/KASLR: Use only one PUD entry for real mode trampoline") Suggested-by: Dave Hansen Signed-off-by: Lee Jones Signed-off-by: Dave Hansen Cc: Link: https://lore.kernel.org/all/20230614163859.924309-1-lee@kernel.org/g Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/kaslr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 6e6b39710e5f..a8cdbbe67bb5 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -172,10 +172,10 @@ void __meminit init_trampoline_kaslr(void) set_p4d(p4d_tramp, __p4d(_KERNPG_TABLE | __pa(pud_page_tramp))); - set_pgd(&trampoline_pgd_entry, - __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp))); + trampoline_pgd_entry = + __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)); } else { - set_pgd(&trampoline_pgd_entry, - __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); + trampoline_pgd_entry = + __pgd(_KERNPG_TABLE | __pa(pud_page_tramp)); } } From e1aa3fe3e282a0532fffaa68360cbd45a2a59291 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Fri, 14 Jan 2022 14:07:17 -0800 Subject: [PATCH 3647/4345] mm/pagealloc: sysctl: change watermark_scale_factor max limit to 30% [ Upstream commit 39c65a94cd9661532be150e88f8b02f4a6844a35 ] For embedded systems with low total memory, having to run applications with relatively large memory requirements, 10% max limitation for watermark_scale_factor poses an issue of triggering direct reclaim every time such application is started. This results in slow application startup times and bad end-user experience. By increasing watermark_scale_factor max limit we allow vendors more flexibility to choose the right level of kswapd aggressiveness for their device and workload requirements. Link: https://lkml.kernel.org/r/20211124193604.2758863-1-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Lukas Middendorf Cc: Antti Palosaari Cc: Luis Chamberlain Cc: Kees Cook Cc: Iurii Zaikin Cc: Dave Hansen Cc: Vlastimil Babka Cc: Mel Gorman Cc: Jonathan Corbet Cc: Zhang Yi Cc: Fengfei Xi Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Stable-dep-of: 935d44acf621 ("memfd: check for non-NULL file_seals in memfd_create() syscall") Signed-off-by: Sasha Levin --- Documentation/admin-guide/sysctl/vm.rst | 2 +- kernel/sysctl.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 06027c6a233a..ac852f93f8da 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -948,7 +948,7 @@ how much memory needs to be free before kswapd goes back to sleep. The unit is in fractions of 10,000. The default value of 10 means the distances between watermarks are 0.1% of the available memory in the -node/system. The maximum value is 1000, or 10% of memory. +node/system. The maximum value is 3000, or 30% of memory. A high rate of threads entering direct reclaim (allocstall) or kswapd going to sleep prematurely (kswapd_low_wmark_hit_quickly) can indicate diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d981abea0358..953c02103970 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -120,6 +120,7 @@ static unsigned long long_max = LONG_MAX; static int one_hundred = 100; static int two_hundred = 200; static int one_thousand = 1000; +static int three_thousand = 3000; #ifdef CONFIG_PRINTK static int ten_thousand = 10000; #endif @@ -2987,7 +2988,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = watermark_scale_factor_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &one_thousand, + .extra2 = &three_thousand, }, { .procname = "percpu_pagelist_fraction", From 1ac6e9ee842859f03dc9e29ebfd50de478280ab6 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:10:55 -0800 Subject: [PATCH 3648/4345] sysctl: move some boundary constants from sysctl.c to sysctl_vals [ Upstream commit 78e36f3b0dae586f623c4a37ec5eb5496f5abbe1 ] sysctl has helpers which let us specify boundary values for a min or max int value. Since these are used for a boundary check only they don't change, so move these variables to sysctl_vals to avoid adding duplicate variables. This will help with our cleanup of kernel/sysctl.c. [akpm@linux-foundation.org: update it for "mm/pagealloc: sysctl: change watermark_scale_factor max limit to 30%"] [mcgrof@kernel.org: major rebase] Link: https://lkml.kernel.org/r/20211123202347.818157-3-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Reviewed-by: Kees Cook Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Benjamin LaHaise Cc: "Eric W. Biederman" Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: Jan Kara Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Qing Wang Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Tetsuo Handa Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Clemens Ladisch Cc: David Airlie Cc: Jani Nikula Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Phillip Potter Cc: Rodrigo Vivi Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Jani Nikula Cc: John Ogness Cc: Martin K. Petersen Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Stable-dep-of: 935d44acf621 ("memfd: check for non-NULL file_seals in memfd_create() syscall") Signed-off-by: Sasha Levin --- fs/proc/proc_sysctl.c | 2 +- include/linux/sysctl.h | 13 +++++++++--- kernel/sysctl.c | 45 ++++++++++++++++++------------------------ 3 files changed, 30 insertions(+), 30 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 1655b7b2a5ab..682f2bf2e525 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -26,7 +26,7 @@ static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; /* shared constants to be used in various sysctls */ -const int sysctl_vals[] = { 0, 1, INT_MAX }; +const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX }; EXPORT_SYMBOL(sysctl_vals); /* Support for permanently empty directories */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 4393de94cb32..c202a72e1690 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -38,9 +38,16 @@ struct ctl_table_header; struct ctl_dir; /* Keep the same order as in fs/proc/proc_sysctl.c */ -#define SYSCTL_ZERO ((void *)&sysctl_vals[0]) -#define SYSCTL_ONE ((void *)&sysctl_vals[1]) -#define SYSCTL_INT_MAX ((void *)&sysctl_vals[2]) +#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[0]) +#define SYSCTL_ZERO ((void *)&sysctl_vals[1]) +#define SYSCTL_ONE ((void *)&sysctl_vals[2]) +#define SYSCTL_TWO ((void *)&sysctl_vals[3]) +#define SYSCTL_FOUR ((void *)&sysctl_vals[4]) +#define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5]) +#define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6]) +#define SYSCTL_ONE_THOUSAND ((void *)&sysctl_vals[7]) +#define SYSCTL_THREE_THOUSAND ((void *)&sysctl_vals[8]) +#define SYSCTL_INT_MAX ((void *)&sysctl_vals[9]) extern const int sysctl_vals[]; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 953c02103970..a45f0dd10b9a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -111,16 +111,9 @@ static int sixty = 60; #endif -static int __maybe_unused neg_one = -1; -static int __maybe_unused two = 2; -static int __maybe_unused four = 4; static unsigned long zero_ul; static unsigned long one_ul = 1; static unsigned long long_max = LONG_MAX; -static int one_hundred = 100; -static int two_hundred = 200; -static int one_thousand = 1000; -static int three_thousand = 3000; #ifdef CONFIG_PRINTK static int ten_thousand = 10000; #endif @@ -2011,7 +2004,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &neg_one, + .extra1 = SYSCTL_NEG_ONE, .extra2 = SYSCTL_ONE, }, #endif @@ -2342,7 +2335,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax_sysadmin, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, #endif { @@ -2602,7 +2595,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &neg_one, + .extra1 = SYSCTL_NEG_ONE, }, #endif #ifdef CONFIG_RT_MUTEXES @@ -2664,7 +2657,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_cpu_time_max_percent_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "perf_event_max_stack", @@ -2682,7 +2675,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_event_max_stack_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_thousand, + .extra2 = SYSCTL_ONE_THOUSAND, }, #endif { @@ -2713,7 +2706,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = bpf_unpriv_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "bpf_stats_enabled", @@ -2756,7 +2749,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = overcommit_policy_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "panic_on_oom", @@ -2765,7 +2758,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "oom_kill_allocating_task", @@ -2810,7 +2803,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", @@ -2827,7 +2820,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", @@ -2867,7 +2860,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two_hundred, + .extra2 = SYSCTL_TWO_HUNDRED, }, #ifdef CONFIG_NUMA { @@ -2926,7 +2919,7 @@ static struct ctl_table vm_table[] = { .mode = 0200, .proc_handler = drop_caches_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &four, + .extra2 = SYSCTL_FOUR, }, #ifdef CONFIG_COMPACTION { @@ -2943,7 +2936,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "extfrag_threshold", @@ -2988,7 +2981,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = watermark_scale_factor_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &three_thousand, + .extra2 = SYSCTL_THREE_THOUSAND, }, { .procname = "percpu_pagelist_fraction", @@ -3075,7 +3068,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "min_slab_ratio", @@ -3084,7 +3077,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = sysctl_min_slab_ratio_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, #endif #ifdef CONFIG_SMP @@ -3367,7 +3360,7 @@ static struct ctl_table fs_table[] = { .mode = 0600, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "protected_regular", @@ -3376,7 +3369,7 @@ static struct ctl_table fs_table[] = { .mode = 0600, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "suid_dumpable", @@ -3385,7 +3378,7 @@ static struct ctl_table fs_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax_coredump, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) { From 051d6421337b473803bf6ae50ae05be1f0db64fb Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Wed, 7 Jun 2023 15:24:27 +0200 Subject: [PATCH 3649/4345] memfd: check for non-NULL file_seals in memfd_create() syscall [ Upstream commit 935d44acf621aa0688fef8312dec3e5940f38f4e ] Ensure that file_seals is non-NULL before using it in the memfd_create() syscall. One situation in which memfd_file_seals_ptr() could return a NULL pointer when CONFIG_SHMEM=n, oopsing the kernel. Link: https://lkml.kernel.org/r/20230607132427.2867435-1-roberto.sassu@huaweicloud.com Fixes: 47b9012ecdc7 ("shmem: add sealing support to hugetlb-backed memfd") Signed-off-by: Roberto Sassu Cc: Marc-Andr Lureau Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- mm/memfd.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memfd.c b/mm/memfd.c index fae4142f7d25..278e5636623e 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -330,7 +330,8 @@ SYSCALL_DEFINE2(memfd_create, if (flags & MFD_ALLOW_SEALING) { file_seals = memfd_file_seals_ptr(file); - *file_seals &= ~F_SEAL_SEAL; + if (file_seals) + *file_seals &= ~F_SEAL_SEAL; } fd_install(fd, file); From 47be2931c4e530fc978edc666ec3b8d37df712f3 Mon Sep 17 00:00:00 2001 From: Chen Aotian Date: Sun, 9 Apr 2023 10:20:48 +0800 Subject: [PATCH 3650/4345] ieee802154: hwsim: Fix possible memory leaks [ Upstream commit a61675294735570daca3779bd1dbb3715f7232bd ] After replacing e->info, it is necessary to free the old einfo. Fixes: f25da51fdc38 ("ieee802154: hwsim: add replacement for fakelb") Reviewed-by: Miquel Raynal Reviewed-by: Alexander Aring Signed-off-by: Chen Aotian Link: https://lore.kernel.org/r/20230409022048.61223-1-chenaotian2@163.com Signed-off-by: Stefan Schmidt Signed-off-by: Sasha Levin --- drivers/net/ieee802154/mac802154_hwsim.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 97981cf7661a..344f63bc94a2 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -522,7 +522,7 @@ static int hwsim_del_edge_nl(struct sk_buff *msg, struct genl_info *info) static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info) { struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1]; - struct hwsim_edge_info *einfo; + struct hwsim_edge_info *einfo, *einfo_old; struct hwsim_phy *phy_v0; struct hwsim_edge *e; u32 v0, v1; @@ -560,8 +560,10 @@ static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info) list_for_each_entry_rcu(e, &phy_v0->edges, list) { if (e->endpoint->idx == v1) { einfo->lqi = lqi; - rcu_assign_pointer(e->info, einfo); + einfo_old = rcu_replace_pointer(e->info, einfo, + lockdep_is_held(&hwsim_phys_lock)); rcu_read_unlock(); + kfree_rcu(einfo_old, rcu); mutex_unlock(&hwsim_phys_lock); return 0; } From cdaa6e1105c04195c91484162c5a4e8958b24ec8 Mon Sep 17 00:00:00 2001 From: Benedict Wong Date: Wed, 10 May 2023 01:30:21 +0000 Subject: [PATCH 3651/4345] xfrm: Treat already-verified secpath entries as optional [ Upstream commit 1f8b6df6a997a430b0c48b504638154b520781ad ] This change allows inbound traffic through nested IPsec tunnels to successfully match policies and templates, while retaining the secpath stack trace as necessary for netfilter policies. Specifically, this patch marks secpath entries that have already matched against a relevant policy as having been verified, allowing it to be treated as optional and skipped after a tunnel decapsulation (during which the src/dst/proto/etc may have changed, and the correct policy chain no long be resolvable). This approach is taken as opposed to the iteration in b0355dbbf13c, where the secpath was cleared, since that breaks subsequent validations that rely on the existence of the secpath entries (netfilter policies, or transport-in-tunnel mode, where policies remain resolvable). Fixes: b0355dbbf13c ("Fix XFRM-I support for nested ESP tunnels") Test: Tested against Android Kernel Unit Tests Test: Tested against Android CTS Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- include/net/xfrm.h | 1 + net/xfrm/xfrm_input.c | 1 + net/xfrm/xfrm_policy.c | 12 ++++++++++++ 3 files changed, 14 insertions(+) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 726a2dbb407f..7865db2f827e 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1034,6 +1034,7 @@ struct xfrm_offload { struct sec_path { int len; int olen; + int verified_cnt; struct xfrm_state *xvec[XFRM_MAX_DEPTH]; struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH]; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index fef99a1c5df1..f3bccab983f0 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -129,6 +129,7 @@ struct sec_path *secpath_set(struct sk_buff *skb) memset(sp->ovec, 0, sizeof(sp->ovec)); sp->olen = 0; sp->len = 0; + sp->verified_cnt = 0; return sp; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d3b128b74a38..465d28341ed6 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3277,6 +3277,13 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { + if (idx < sp->verified_cnt) { + /* Secpath entry previously verified, consider optional and + * continue searching + */ + continue; + } + if (start == -1) start = -2-idx; break; @@ -3688,6 +3695,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * Order is _important_. Later we will implement * some barriers, but at the moment barriers * are implied between each two transformations. + * Upon success, marks secpath entries as having been + * verified to allow them to be skipped in future policy + * checks (e.g. nested tunnels). */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); @@ -3706,6 +3716,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_pols_put(pols, npols); + sp->verified_cnt = k; + return 1; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); From 01af67ed83d0019e3d1c2d4bb8c1f878fe34e1d9 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sat, 3 Dec 2022 10:46:56 +0200 Subject: [PATCH 3652/4345] xfrm: interface: rename xfrm_interface.c to xfrm_interface_core.c [ Upstream commit ee9a113ab63468137802898bcd2c598998c96938 ] This change allows adding additional files to the xfrm_interface module. Signed-off-by: Eyal Birger Link: https://lore.kernel.org/r/20221203084659.1837829-2-eyal.birger@gmail.com Signed-off-by: Martin KaFai Lau Stable-dep-of: a287f5b0cfc6 ("xfrm: Ensure policies always checked on XFRM-I input path") Signed-off-by: Sasha Levin --- net/xfrm/Makefile | 2 ++ net/xfrm/{xfrm_interface.c => xfrm_interface_core.c} | 0 2 files changed, 2 insertions(+) rename net/xfrm/{xfrm_interface.c => xfrm_interface_core.c} (100%) diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 494aa744bfb9..08a2870fdd36 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -3,6 +3,8 @@ # Makefile for the XFRM subsystem. # +xfrm_interface-$(CONFIG_XFRM_INTERFACE) += xfrm_interface_core.o + obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ xfrm_input.o xfrm_output.o \ xfrm_sysctl.o xfrm_replay.o xfrm_device.o diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface_core.c similarity index 100% rename from net/xfrm/xfrm_interface.c rename to net/xfrm/xfrm_interface_core.c From bff7824db6811dbfa5212ab232786d3f40aa4fa8 Mon Sep 17 00:00:00 2001 From: Benedict Wong Date: Wed, 10 May 2023 01:30:22 +0000 Subject: [PATCH 3653/4345] xfrm: Ensure policies always checked on XFRM-I input path [ Upstream commit a287f5b0cfc6804c5b12a4be13c7c9fe27869e90 ] This change adds methods in the XFRM-I input path that ensures that policies are checked prior to processing of the subsequent decapsulated packet, after which the relevant policies may no longer be resolvable (due to changing src/dst/proto/etc). Notably, raw ESP/AH packets did not perform policy checks inherently, whereas all other encapsulated packets (UDP, TCP encapsulated) do policy checks after calling xfrm_input handling in the respective encapsulation layer. Fixes: b0355dbbf13c ("Fix XFRM-I support for nested ESP tunnels") Test: Verified with additional Android Kernel Unit tests Test: Verified against Android CTS Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/xfrm/xfrm_interface_core.c | 54 +++++++++++++++++++++++++++++++--- 1 file changed, 50 insertions(+), 4 deletions(-) diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index da518b4ca84c..e4f21a692415 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -207,6 +207,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } +static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -780,8 +826,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -831,8 +877,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, From 3b0a96db670b6d019d13fb052a40f3078264f224 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Wed, 15 Feb 2023 01:20:27 +0200 Subject: [PATCH 3654/4345] bpf: track immediate values written to stack by BPF_ST instruction [ Upstream commit ecdf985d7615356b78241fdb159c091830ed0380 ] For aligned stack writes using BPF_ST instruction track stored values in a same way BPF_STX is handled, e.g. make sure that the following commands produce similar verifier knowledge: fp[-8] = 42; r1 = 42; fp[-8] = r1; This covers two cases: - non-null values written to stack are stored as spill of fake registers; - null values written to stack are stored as STACK_ZERO marks. Previously both cases above used STACK_MISC marks instead. Some verifier test cases relied on the old logic to obtain STACK_MISC marks for some stack values. These test cases are updated in the same commit to avoid failures during bisect. Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20230214232030.1502829-2-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov Stable-dep-of: 713274f1f2c8 ("bpf: Fix verifier id tracking of scalars on spill") Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 18 ++- .../bpf/verifier/bounds_mix_sign_unsign.c | 110 ++++++++++-------- 2 files changed, 80 insertions(+), 48 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fd2082a9bf81..4fca456ba27a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2318,6 +2318,11 @@ static void save_register_state(struct bpf_func_state *state, scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); } +static bool is_bpf_st_mem(struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM; +} + /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ @@ -2329,8 +2334,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; - u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg; + struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; struct bpf_reg_state *reg = NULL; + u32 dst_reg = insn->dst_reg; err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), state->acquired_refs, true); @@ -2379,6 +2385,13 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, return err; } save_register_state(state, spi, reg, size); + } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && + insn->imm != 0 && env->bpf_capable) { + struct bpf_reg_state fake_reg = {}; + + __mark_reg_known(&fake_reg, (u32)insn->imm); + fake_reg.type = SCALAR_VALUE; + save_register_state(state, spi, &fake_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -2413,7 +2426,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; /* when we zero initialize stack slots mark them as such */ - if (reg && register_is_null(reg)) { + if ((reg && register_is_null(reg)) || + (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) { /* backtracking doesn't work for STACK_ZERO yet. */ err = mark_chain_precision(env, value_regno); if (err) diff --git a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c index c2aa6f26738b..bf82b923c5fe 100644 --- a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c +++ b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c @@ -1,13 +1,14 @@ { "bounds checks mixing signed and unsigned, positive bounds", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 2), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 3), @@ -17,20 +18,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), @@ -40,20 +42,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 2", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), @@ -65,20 +68,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 3", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 4), @@ -89,20 +93,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 4", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 1), BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), @@ -112,19 +117,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 5", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), @@ -135,17 +141,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 6", .insns = { + BPF_MOV64_REG(BPF_REG_9, BPF_REG_1), + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_9), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -512), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_6, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_6, 5), @@ -163,13 +172,14 @@ { "bounds checks mixing signed and unsigned, variant 7", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024), BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), @@ -179,19 +189,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 8", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), @@ -203,20 +214,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 9", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_LD_IMM64(BPF_REG_2, -9223372036854775808ULL), BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), @@ -228,19 +240,20 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 10", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), @@ -252,20 +265,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 11", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -278,20 +292,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 12", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -6), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -303,20 +318,21 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 13", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, 2), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -331,7 +347,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, @@ -340,13 +356,14 @@ .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1, offsetof(struct __sk_buff, mark)), + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -1), BPF_MOV64_IMM(BPF_REG_8, 2), @@ -360,20 +377,21 @@ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, -3), BPF_JMP_IMM(BPF_JA, 0, 0, -7), }, - .fixup_map_hash_8b = { 4 }, + .fixup_map_hash_8b = { 6 }, .errstr = "unbounded min value", .result = REJECT, }, { "bounds checks mixing signed and unsigned, variant 15", .insns = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), BPF_MOV64_IMM(BPF_REG_2, -6), BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), @@ -387,7 +405,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .fixup_map_hash_8b = { 3 }, + .fixup_map_hash_8b = { 5 }, .errstr = "unbounded min value", .result = REJECT, }, From 562800447f8beef8ebc5a8640c61411620911ad1 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 7 Jun 2023 15:39:50 +0300 Subject: [PATCH 3655/4345] bpf: Fix verifier id tracking of scalars on spill [ Upstream commit 713274f1f2c896d37017efee333fd44149710119 ] The following scenario describes a bug in the verifier where it incorrectly concludes about equivalent scalar IDs which could lead to verifier bypass in privileged mode: 1. Prepare a 32-bit rogue number. 2. Put the rogue number into the upper half of a 64-bit register, and roll a random (unknown to the verifier) bit in the lower half. The rest of the bits should be zero (although variations are possible). 3. Assign an ID to the register by MOVing it to another arbitrary register. 4. Perform a 32-bit spill of the register, then perform a 32-bit fill to another register. Due to a bug in the verifier, the ID will be preserved, although the new register will contain only the lower 32 bits, i.e. all zeros except one random bit. At this point there are two registers with different values but the same ID, which means the integrity of the verifier state has been corrupted. 5. Compare the new 32-bit register with 0. In the branch where it's equal to 0, the verifier will believe that the original 64-bit register is also 0, because it has the same ID, but its actual value still contains the rogue number in the upper half. Some optimizations of the verifier prevent the actual bypass, so extra care is needed: the comparison must be between two registers, and both branches must be reachable (this is why one random bit is needed). Both branches are still suitable for the bypass. 6. Right shift the original register by 32 bits to pop the rogue number. 7. Use the rogue number as an offset with any pointer. The verifier will believe that the offset is 0, while in reality it's the given number. The fix is similar to the 32-bit BPF_MOV handling in check_alu_op for SCALAR_VALUE. If the spill is narrowing the actual register value, don't keep the ID, make sure it's reset to 0. Fixes: 354e8f1970f8 ("bpf: Support <8-byte scalar spill and refill") Signed-off-by: Maxim Mikityanskiy Signed-off-by: Daniel Borkmann Tested-by: Andrii Nakryiko # Checked veristat delta Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20230607123951.558971-2-maxtram95@gmail.com Signed-off-by: Sasha Levin --- kernel/bpf/verifier.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4fca456ba27a..edb19ada0405 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2385,6 +2385,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, return err; } save_register_state(state, spi, reg, size); + /* Break the relation on a narrowing spill. */ + if (fls64(reg->umax_value) > BITS_PER_BYTE * size) + state->stack[spi].spilled_ptr.id = 0; } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && insn->imm != 0 && env->bpf_capable) { struct bpf_reg_state fake_reg = {}; From 07fbbddae5af1865c94bfd39688e3b12b6eba236 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Mon, 5 Jun 2023 04:06:54 -0700 Subject: [PATCH 3656/4345] xfrm: fix inbound ipv4/udp/esp packets to UDPv6 dualstack sockets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 1166a530a84758bb9e6b448fc8c195ed413f5ded ] Before Linux v5.8 an AF_INET6 SOCK_DGRAM (udp/udplite) socket with SOL_UDP, UDP_ENCAP, UDP_ENCAP_ESPINUDP{,_NON_IKE} enabled would just unconditionally use xfrm4_udp_encap_rcv(), afterwards such a socket would use the newly added xfrm6_udp_encap_rcv() which only handles IPv6 packets. Cc: Sabrina Dubroca Cc: Steffen Klassert Cc: Jakub Kicinski Cc: Benedict Wong Cc: Yan Yan Fixes: 0146dca70b87 ("xfrm: add support for UDPv6 encapsulation of ESP") Signed-off-by: Maciej Żenczykowski Reviewed-by: Simon Horman Reviewed-by: Sabrina Dubroca Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/ipv4/xfrm4_input.c | 1 + net/ipv6/xfrm6_input.c | 3 +++ 2 files changed, 4 insertions(+) diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index ad2afeef4f10..eac206a290d0 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -164,6 +164,7 @@ drop: kfree_skb(skb); return 0; } +EXPORT_SYMBOL(xfrm4_udp_encap_rcv); int xfrm4_rcv(struct sk_buff *skb) { diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 04cbeefd8982..4907ab241d6b 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -86,6 +86,9 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) __be32 *udpdata32; __u16 encap_type = up->encap_type; + if (skb->protocol == htons(ETH_P_IP)) + return xfrm4_udp_encap_rcv(sk, skb); + /* if this is not encapsulated socket, then just return now */ if (!encap_type) return 1; From 2af75a36af8d372a6976f3cccfcba692eacedcf4 Mon Sep 17 00:00:00 2001 From: Magali Lemes Date: Tue, 13 Jun 2023 09:32:21 -0300 Subject: [PATCH 3657/4345] selftests: net: vrf-xfrm-tests: change authentication and encryption algos [ Upstream commit cb43c60e64ca67fcc9d23bd08f51d2ab8209d9d7 ] The vrf-xfrm-tests tests use the hmac(md5) and cbc(des3_ede) algorithms for performing authentication and encryption, respectively. This causes the tests to fail when fips=1 is set, since these algorithms are not allowed in FIPS mode. Therefore, switch from hmac(md5) and cbc(des3_ede) to hmac(sha1) and cbc(aes), which are FIPS compliant. Fixes: 3f251d741150 ("selftests: Add tests for vrf and xfrms") Reviewed-by: David Ahern Signed-off-by: Magali Lemes Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- tools/testing/selftests/net/vrf-xfrm-tests.sh | 32 +++++++++---------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh index 184da81f554f..452638ae8aed 100755 --- a/tools/testing/selftests/net/vrf-xfrm-tests.sh +++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh @@ -264,60 +264,60 @@ setup_xfrm() ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ${devarg} ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ${devarg} ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} } From 31cd0d4a4470e28707471dd0f1b746af4d26ebbc Mon Sep 17 00:00:00 2001 From: Magali Lemes Date: Tue, 13 Jun 2023 09:32:22 -0300 Subject: [PATCH 3658/4345] selftests: net: fcnal-test: check if FIPS mode is enabled [ Upstream commit d7a2fc1437f71cb058c7b11bc33dfc19e4bf277a ] There are some MD5 tests which fail when the kernel is in FIPS mode, since MD5 is not FIPS compliant. Add a check and only run those tests if FIPS mode is not enabled. Fixes: f0bee1ebb5594 ("fcnal-test: Add TCP MD5 tests") Fixes: 5cad8bce26e01 ("fcnal-test: Add TCP MD5 tests for VRF") Reviewed-by: David Ahern Signed-off-by: Magali Lemes Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- tools/testing/selftests/net/fcnal-test.sh | 27 ++++++++++++++++------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 4a11ea2261cb..e13b0fb63333 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -81,6 +81,13 @@ NSC_CMD="ip netns exec ${NSC}" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) +# Check if FIPS mode is enabled +if [ -f /proc/sys/crypto/fips_enabled ]; then + fips_enabled=`cat /proc/sys/crypto/fips_enabled` +else + fips_enabled=0 +fi + ################################################################################ # utilities @@ -1139,7 +1146,7 @@ ipv4_tcp_novrf() run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" - ipv4_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv4_tcp_md5_novrf } ipv4_tcp_vrf() @@ -1193,9 +1200,11 @@ ipv4_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv4_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv4_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server @@ -2611,7 +2620,7 @@ ipv6_tcp_novrf() log_test_addr ${a} $? 1 "No server, device client, local conn" done - ipv6_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv6_tcp_md5_novrf } ipv6_tcp_vrf() @@ -2681,9 +2690,11 @@ ipv6_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv6_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv6_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server From b1b9c81e29d2251b3e7c35de9f15a8e9d446c6e4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 14 Jun 2023 12:02:02 +0200 Subject: [PATCH 3659/4345] xfrm: Linearize the skb after offloading if needed. [ Upstream commit f015b900bc3285322029b4a7d132d6aeb0e51857 ] With offloading enabled, esp_xmit() gets invoked very late, from within validate_xmit_xfrm() which is after validate_xmit_skb() validates and linearizes the skb if the underlying device does not support fragments. esp_output_tail() may add a fragment to the skb while adding the auth tag/ IV. Devices without the proper support will then send skb->data points to with the correct length so the packet will have garbage at the end. A pcap sniffer will claim that the proper data has been sent since it parses the skb properly. It is not affected with INET_ESP_OFFLOAD disabled. Linearize the skb after offloading if the sending hardware requires it. It was tested on v4, v6 has been adopted. Fixes: 7785bba299a8d ("esp: Add a software GRO codepath") Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin --- net/ipv4/esp4_offload.c | 3 +++ net/ipv6/esp6_offload.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 84257678160a..dc50764b0180 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -338,6 +338,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ secpath_reset(skb); + if (skb_needs_linearize(skb, skb->dev->features) && + __skb_linearize(skb)) + return -ENOMEM; return 0; } diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 7608be04d0f5..87dbd53c29a6 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -372,6 +372,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features secpath_reset(skb); + if (skb_needs_linearize(skb, skb->dev->features) && + __skb_linearize(skb)) + return -ENOMEM; return 0; } From ced13bc50ef0f0ba4f6ea8808792c472a0bcf308 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Wed, 14 Jun 2023 23:06:56 +0200 Subject: [PATCH 3660/4345] net: qca_spi: Avoid high load if QCA7000 is not available [ Upstream commit 92717c2356cb62c89e8a3dc37cbbab2502562524 ] In case the QCA7000 is not available via SPI (e.g. in reset), the driver will cause a high load. The reason for this is that the synchronization is never finished and schedule() is never called. Since the synchronization is not timing critical, it's safe to drop this from the scheduling condition. Signed-off-by: Stefan Wahren Fixes: 291ab06ecf67 ("net: qualcomm: new Ethernet over SPI driver for QCA7000") Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/qualcomm/qca_spi.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 36bcb5db3be9..44fa959ebcaa 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -574,8 +574,7 @@ qcaspi_spi_thread(void *data) while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); if ((qca->intr_req == qca->intr_svc) && - (qca->txr.skb[qca->txr.head] == NULL) && - (qca->sync == QCASPI_SYNC_READY)) + !qca->txr.skb[qca->txr.head]) schedule(); set_current_state(TASK_RUNNING); From 9b0417fd402fe176b22ff7cdd712a0b0105c7df9 Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 17 Jun 2023 23:36:13 +0300 Subject: [PATCH 3661/4345] mmc: mtk-sd: fix deferred probing [ Upstream commit 0c4dc0f054891a2cbde0426b0c0fdf232d89f47f ] The driver overrides the error codes returned by platform_get_irq() to -EINVAL, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream. Fixes: 208489032bdd ("mmc: mediatek: Add Mediatek MMC driver") Signed-off-by: Sergey Shtylyov Link: https://lore.kernel.org/r/20230617203622.6812-4-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/mtk-sd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index d71c113f428f..2c9ea5ed0b2f 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2443,7 +2443,7 @@ static int msdc_drv_probe(struct platform_device *pdev) host->irq = platform_get_irq(pdev, 0); if (host->irq < 0) { - ret = -EINVAL; + ret = host->irq; goto host_free; } From 9ad3c21fb66dcf9c0154f65ae2dfc5b9a6eb77be Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 17 Jun 2023 23:36:14 +0300 Subject: [PATCH 3662/4345] mmc: mvsdio: fix deferred probing [ Upstream commit 8d84064da0d4672e74f984e8710f27881137472c ] The driver overrides the error codes returned by platform_get_irq() to -ENXIO, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream. Fixes: 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") Signed-off-by: Sergey Shtylyov Link: https://lore.kernel.org/r/20230617203622.6812-5-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/mvsdio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c index 629efbe639c4..b4f6a0a2fcb5 100644 --- a/drivers/mmc/host/mvsdio.c +++ b/drivers/mmc/host/mvsdio.c @@ -704,7 +704,7 @@ static int mvsd_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); if (irq < 0) - return -ENXIO; + return irq; mmc = mmc_alloc_host(sizeof(struct mvsd_host), &pdev->dev); if (!mmc) { From 65d9318e3d564e54451a82f3267b453664a4c7b6 Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 17 Jun 2023 23:36:15 +0300 Subject: [PATCH 3663/4345] mmc: omap: fix deferred probing [ Upstream commit aedf4ba1ad00aaa94c1b66c73ecaae95e2564b95 ] The driver overrides the error codes returned by platform_get_irq() to -ENXIO, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream. Fixes: 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") Signed-off-by: Sergey Shtylyov Link: https://lore.kernel.org/r/20230617203622.6812-6-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/omap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c index 6aa0537f1f84..eb978b75d8e7 100644 --- a/drivers/mmc/host/omap.c +++ b/drivers/mmc/host/omap.c @@ -1344,7 +1344,7 @@ static int mmc_omap_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) - return -ENXIO; + return irq; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); host->virt_base = devm_ioremap_resource(&pdev->dev, res); From f29d0ab0e6bd031cad28919046dfad3b846446bf Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 17 Jun 2023 23:36:16 +0300 Subject: [PATCH 3664/4345] mmc: omap_hsmmc: fix deferred probing [ Upstream commit fb51b74a57859b707c3e8055ed0c25a7ca4f6a29 ] The driver overrides the error codes returned by platform_get_irq() to -ENXIO, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream. Fixes: 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") Signed-off-by: Sergey Shtylyov Link: https://lore.kernel.org/r/20230617203622.6812-7-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/omap_hsmmc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 5b6ede81fc9f..098075449ccd 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1832,9 +1832,11 @@ static int omap_hsmmc_probe(struct platform_device *pdev) } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - irq = platform_get_irq(pdev, 0); - if (res == NULL || irq < 0) + if (!res) return -ENXIO; + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(base)) From f6e176ef894af93a0542207d4eba4d6b2e619f4e Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 17 Jun 2023 23:36:17 +0300 Subject: [PATCH 3665/4345] mmc: owl: fix deferred probing [ Upstream commit 3c482e1e830d79b9be8afb900a965135c01f7893 ] The driver overrides the error codes returned by platform_get_irq() to -EINVAL, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream. Fixes: ff65ffe46d28 ("mmc: Add Actions Semi Owl SoCs SD/MMC driver") Signed-off-by: Sergey Shtylyov Link: https://lore.kernel.org/r/20230617203622.6812-8-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/owl-mmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/owl-mmc.c b/drivers/mmc/host/owl-mmc.c index 3d4abf175b1d..8a40cf8a92db 100644 --- a/drivers/mmc/host/owl-mmc.c +++ b/drivers/mmc/host/owl-mmc.c @@ -640,7 +640,7 @@ static int owl_mmc_probe(struct platform_device *pdev) owl_host->irq = platform_get_irq(pdev, 0); if (owl_host->irq < 0) { - ret = -EINVAL; + ret = owl_host->irq; goto err_release_channel; } From c2278de1382b07ed090cc323ee700167fd9a28d9 Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 17 Jun 2023 23:36:18 +0300 Subject: [PATCH 3666/4345] mmc: sdhci-acpi: fix deferred probing [ Upstream commit b465dea5e1540c7d7b5211adaf94926980d3014b ] The driver overrides the error codes returned by platform_get_irq() to -EINVAL, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream. Fixes: 1b7ba57ecc86 ("mmc: sdhci-acpi: Handle return value of platform_get_irq") Signed-off-by: Sergey Shtylyov Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20230617203622.6812-9-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/sdhci-acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index a2cdb37fcbbe..2a28101777c6 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -876,7 +876,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev) host->ops = &sdhci_acpi_ops_dflt; host->irq = platform_get_irq(pdev, 0); if (host->irq < 0) { - err = -EINVAL; + err = host->irq; goto err_free; } From 4a99e35c5a62cf191afb9d7ea169d7e7132c4933 Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 17 Jun 2023 23:36:20 +0300 Subject: [PATCH 3667/4345] mmc: sh_mmcif: fix deferred probing [ Upstream commit 5b067d7f855c61df7f8e2e8ccbcee133c282415e ] The driver overrides the error codes returned by platform_get_irq() to -ENXIO, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating the error codes upstream. Fixes: 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") Signed-off-by: Sergey Shtylyov Link: https://lore.kernel.org/r/20230617203622.6812-11-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/sh_mmcif.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index e5e457037235..5dec9e239c9b 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -1398,7 +1398,7 @@ static int sh_mmcif_probe(struct platform_device *pdev) irq[0] = platform_get_irq(pdev, 0); irq[1] = platform_get_irq_optional(pdev, 1); if (irq[0] < 0) - return -ENXIO; + return irq[0]; reg = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(reg)) From f2547bc71663d5f1da4da1ecc92ee2811f0f347d Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 17 Jun 2023 23:36:22 +0300 Subject: [PATCH 3668/4345] mmc: usdhi60rol0: fix deferred probing [ Upstream commit 413db499730248431c1005b392e8ed82c4fa19bf ] The driver overrides the error codes returned by platform_get_irq_byname() to -ENODEV, so if it returns -EPROBE_DEFER, the driver will fail the probe permanently instead of the deferred probing. Switch to propagating error codes upstream. Fixes: 9ec36cafe43b ("of/irq: do irq resolution in platform_get_irq") Signed-off-by: Sergey Shtylyov Link: https://lore.kernel.org/r/20230617203622.6812-13-s.shtylyov@omp.ru Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/mmc/host/usdhi6rol0.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c index b9b79b1089a0..4f22ecef9be5 100644 --- a/drivers/mmc/host/usdhi6rol0.c +++ b/drivers/mmc/host/usdhi6rol0.c @@ -1747,8 +1747,10 @@ static int usdhi6_probe(struct platform_device *pdev) irq_cd = platform_get_irq_byname(pdev, "card detect"); irq_sd = platform_get_irq_byname(pdev, "data"); irq_sdio = platform_get_irq_byname(pdev, "SDIO"); - if (irq_sd < 0 || irq_sdio < 0) - return -ENODEV; + if (irq_sd < 0) + return irq_sd; + if (irq_sdio < 0) + return irq_sdio; mmc = mmc_alloc_host(sizeof(struct usdhi6_host), dev); if (!mmc) From 7a1ae00005093a952d35a8e466ab0a0919b99600 Mon Sep 17 00:00:00 2001 From: Terin Stock Date: Fri, 9 Jun 2023 22:58:42 +0200 Subject: [PATCH 3669/4345] ipvs: align inner_mac_header for encapsulation [ Upstream commit d7fce52fdf96663ddc2eb21afecff3775588612a ] When using encapsulation the original packet's headers are copied to the inner headers. This preserves the space for an inner mac header, which is not used by the inner payloads for the encapsulation types supported by IPVS. If a packet is using GUE or GRE encapsulation and needs to be segmented, flow can be passed to __skb_udp_tunnel_segment() which calculates a negative tunnel header length. A negative tunnel header length causes pskb_may_pull() to fail, dropping the packet. This can be observed by attaching probes to ip_vs_in_hook(), __dev_queue_xmit(), and __skb_udp_tunnel_segment(): perf probe --add '__dev_queue_xmit skb->inner_mac_header \ skb->inner_network_header skb->mac_header skb->network_header' perf probe --add '__skb_udp_tunnel_segment:7 tnl_hlen' perf probe -m ip_vs --add 'ip_vs_in_hook skb->inner_mac_header \ skb->inner_network_header skb->mac_header skb->network_header' These probes the headers and tunnel header length for packets which traverse the IPVS encapsulation path. A TCP packet can be forced into the segmentation path by being smaller than a calculated clamped MSS, but larger than the advertised MSS. probe:ip_vs_in_hook: inner_mac_header=0x0 inner_network_header=0x0 mac_header=0x44 network_header=0x52 probe:ip_vs_in_hook: inner_mac_header=0x44 inner_network_header=0x52 mac_header=0x44 network_header=0x32 probe:dev_queue_xmit: inner_mac_header=0x44 inner_network_header=0x52 mac_header=0x44 network_header=0x32 probe:__skb_udp_tunnel_segment_L7: tnl_hlen=-2 When using veth-based encapsulation, the interfaces are set to be mac-less, which does not preserve space for an inner mac header. This prevents this issue from occurring. In our real-world testing of sending a 32KB file we observed operation time increasing from ~75ms for veth-based encapsulation to over 1.5s using IPVS encapsulation due to retries from dropped packets. This changeset modifies the packet on the encapsulation path in ip_vs_tunnel_xmit() and ip_vs_tunnel_xmit_v6() to remove the inner mac header offset. This fixes UDP segmentation for both encapsulation types, and corrects the inner headers for any IPIP flows that may use it. Fixes: 84c0d5e96f3a ("ipvs: allow tunneling with gue encapsulation") Signed-off-by: Terin Stock Acked-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/ipvs/ip_vs_xmit.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index d2e5a8f644b8..cd2130e98836 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1225,6 +1225,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, skb->transport_header = skb->network_header; skb_set_inner_ipproto(skb, next_protocol); + skb_set_inner_mac_header(skb, skb_inner_network_offset(skb)); if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { bool check = false; @@ -1373,6 +1374,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb->transport_header = skb->network_header; skb_set_inner_ipproto(skb, next_protocol); + skb_set_inner_mac_header(skb, skb_inner_network_offset(skb)); if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { bool check = false; From cebb5cee098442bec42232e06309b93edba4acee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 17 Jun 2023 09:26:45 +0300 Subject: [PATCH 3670/4345] net: dsa: mt7530: fix trapping frames on non-MT7621 SoC MT7530 switch MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 4ae90f90e4909e3014e2dc6a0627964617a7b824 ] All MT7530 switch IP variants share the MT7530_MFC register, but the current driver only writes it for the switch variant that is integrated in the MT7621 SoC. Modify the code to include all MT7530 derivatives. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Suggested-by: Vladimir Oltean Signed-off-by: Arınç ÜNAL Reviewed-by: Vladimir Oltean Reviewed-by: Russell King (Oracle) Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/dsa/mt7530.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index d3b42adef057..4056ca4255be 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -966,7 +966,7 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port) mt7530_rmw(priv, MT7530_MFC, UNM_FFP_MASK, UNM_FFP(BIT(port))); /* Set CPU port number */ - if (priv->id == ID_MT7621) + if (priv->id == ID_MT7530 || priv->id == ID_MT7621) mt7530_rmw(priv, MT7530_MFC, CPU_MASK, CPU_EN | CPU_PORT(port)); /* CPU port gets connected to all user ports of From 792bfe26a655299322887829d7509e60655955f7 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Fri, 16 Jun 2023 17:45:49 +0100 Subject: [PATCH 3671/4345] be2net: Extend xmit workaround to BE3 chip [ Upstream commit 7580e0a78eb29e7bb1a772eba4088250bbb70d41 ] We have seen a bug where the NIC incorrectly changes the length in the IP header of a padded packet to include the padding bytes. The driver already has a workaround for this so do the workaround for this NIC too. This resolves the issue. The NIC in question identifies itself as follows: [ 8.828494] be2net 0000:02:00.0: FW version is 10.7.110.31 [ 8.834759] be2net 0000:02:00.0: Emulex OneConnect(be3): PF FLEX10 port 1 02:00.0 Ethernet controller: Emulex Corporation OneConnect 10Gb NIC (be3) (rev 01) Fixes: ca34fe38f06d ("be2net: fix wrong usage of adapter->generation") Signed-off-by: Ross Lagerwall Link: https://lore.kernel.org/r/20230616164549.2863037-1-ross.lagerwall@citrix.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/emulex/benet/be_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 89697cb09d1c..81be560a2643 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1136,8 +1136,8 @@ static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter, eth_hdr_len = ntohs(skb->protocol) == ETH_P_8021Q ? VLAN_ETH_HLEN : ETH_HLEN; if (skb->len <= 60 && - (lancer_chip(adapter) || skb_vlan_tag_present(skb)) && - is_ipv4_pkt(skb)) { + (lancer_chip(adapter) || BE3_chip(adapter) || + skb_vlan_tag_present(skb)) && is_ipv4_pkt(skb)) { ip = (struct iphdr *)ip_hdr(skb); pskb_trim(skb, eth_hdr_len + ntohs(ip->tot_len)); } From 2a90da8e0dd50f42e577988f4219f4f4cd3616b7 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 16 Jun 2023 15:20:04 +0200 Subject: [PATCH 3672/4345] netfilter: nft_set_pipapo: .walk does not deal with generations [ Upstream commit 2b84e215f87443c74ac0aa7f76bb172d43a87033 ] The .walk callback iterates over the current active set, but it might be useful to iterate over the next generation set. Use the generation mask to determine what set view (either current or next generation) is use for the walk iteration. Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nft_set_pipapo.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 30cf0673d6c1..eb5934eb3adf 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1949,12 +1949,16 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_pipapo *priv = nft_set_priv(set); + struct net *net = read_pnet(&set->net); struct nft_pipapo_match *m; struct nft_pipapo_field *f; int i, r; rcu_read_lock(); - m = rcu_dereference(priv->match); + if (iter->genmask == nft_genmask_cur(net)) + m = rcu_dereference(priv->match); + else + m = priv->clone; if (unlikely(!m)) goto out; From 3d5c09c782a32ac86701c2e4ee5c4a4ba4f155ca Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 16 Jun 2023 15:20:16 +0200 Subject: [PATCH 3673/4345] netfilter: nf_tables: disallow element updates of bound anonymous sets [ Upstream commit c88c535b592d3baeee74009f3eceeeaf0fdd5e1b ] Anonymous sets come with NFT_SET_CONSTANT from userspace. Although API allows to create anonymous sets without NFT_SET_CONSTANT, it makes no sense to allow to add and to delete elements for bound anonymous sets. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fe51cedd9cc3..92ea3332cdda 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5460,7 +5460,8 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) + if (!list_empty(&set->bindings) && + (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) return -EBUSY; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { @@ -5666,7 +5667,9 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) + + if (!list_empty(&set->bindings) && + (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) return -EBUSY; if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) { From 5702afa2c331af560f0a1f2da7a360b36b536f03 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 15 Jun 2023 10:14:25 +0200 Subject: [PATCH 3674/4345] netfilter: nfnetlink_osf: fix module autoload [ Upstream commit 62f9a68a36d4441a6c412b81faed102594bc6670 ] Move the alias from xt_osf to nfnetlink_osf. Fixes: f9324952088f ("netfilter: nfnetlink_osf: extract nfnetlink_subsystem code from xt_osf.c") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nfnetlink_osf.c | 1 + net/netfilter/xt_osf.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 51e3953b414c..9dbaa5ce24e5 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -440,3 +440,4 @@ module_init(nfnl_osf_init); module_exit(nfnl_osf_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index e1990baf3a3b..dc9485854002 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -71,4 +71,3 @@ MODULE_AUTHOR("Evgeniy Polyakov "); MODULE_DESCRIPTION("Passive OS fingerprint matching."); MODULE_ALIAS("ipt_osf"); MODULE_ALIAS("ip6t_osf"); -MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF); From caddeadd0d0331cd5746cc1a72a7afd43e469d13 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Mon, 19 Jun 2023 17:44:35 +0200 Subject: [PATCH 3675/4345] Revert "net: phy: dp83867: perform soft reset and retain established link" [ Upstream commit a129b41fe0a8b4da828c46b10f5244ca07a3fec3 ] This reverts commit da9ef50f545f86ffe6ff786174d26500c4db737a. This fixes a regression in which the link would come up, but no communication was possible. The reverted commit was also removing a comment about DP83867_PHYCR_FORCE_LINK_GOOD, this is not added back in this commits since it seems that this is unrelated to the original code change. Closes: https://lore.kernel.org/all/ZGuDJos8D7N0J6Z2@francesco-nb.int.toradex.com/ Fixes: da9ef50f545f ("net: phy: dp83867: perform soft reset and retain established link") Signed-off-by: Francesco Dolcini Reviewed-by: Andrew Lunn Reviewed-by: Praneeth Bajjuri Link: https://lore.kernel.org/r/20230619154435.355485-1-francesco@dolcini.it Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/dp83867.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 5fabcd15ef77..834bf63dc200 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -802,7 +802,7 @@ static int dp83867_phy_reset(struct phy_device *phydev) { int err; - err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET); if (err < 0) return err; From bc75968b494ab9991e855ab429e850d415ac835e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Jun 2023 18:44:25 +0000 Subject: [PATCH 3676/4345] sch_netem: acquire qdisc lock in netem_change() [ Upstream commit 2174a08db80d1efeea382e25ac41c4e7511eb6d6 ] syzbot managed to trigger a divide error [1] in netem. It could happen if q->rate changes while netem_enqueue() is running, since q->rate is read twice. It turns out netem_change() always lacked proper synchronization. [1] divide error: 0000 [#1] SMP KASAN CPU: 1 PID: 7867 Comm: syz-executor.1 Not tainted 6.1.30-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023 RIP: 0010:div64_u64 include/linux/math64.h:69 [inline] RIP: 0010:packet_time_ns net/sched/sch_netem.c:357 [inline] RIP: 0010:netem_enqueue+0x2067/0x36d0 net/sched/sch_netem.c:576 Code: 89 e2 48 69 da 00 ca 9a 3b 42 80 3c 28 00 4c 8b a4 24 88 00 00 00 74 0d 4c 89 e7 e8 c3 4f 3b fd 48 8b 4c 24 18 48 89 d8 31 d2 <49> f7 34 24 49 01 c7 4c 8b 64 24 48 4d 01 f7 4c 89 e3 48 c1 eb 03 RSP: 0018:ffffc9000dccea60 EFLAGS: 00010246 RAX: 000001a442624200 RBX: 000001a442624200 RCX: ffff888108a4f000 RDX: 0000000000000000 RSI: 000000000000070d RDI: 000000000000070d RBP: ffffc9000dcceb90 R08: ffffffff849c5e26 R09: fffffbfff10e1297 R10: 0000000000000000 R11: dffffc0000000001 R12: ffff888108a4f358 R13: dffffc0000000000 R14: 0000001a8cd9a7ec R15: 0000000000000000 FS: 00007fa73fe18700(0000) GS:ffff8881f6b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fa73fdf7718 CR3: 000000011d36e000 CR4: 0000000000350ee0 Call Trace: [] __dev_xmit_skb net/core/dev.c:3931 [inline] [] __dev_queue_xmit+0xcf5/0x3370 net/core/dev.c:4290 [] dev_queue_xmit include/linux/netdevice.h:3030 [inline] [] neigh_hh_output include/net/neighbour.h:531 [inline] [] neigh_output include/net/neighbour.h:545 [inline] [] ip_finish_output2+0xb92/0x10d0 net/ipv4/ip_output.c:235 [] __ip_finish_output+0xc3/0x2b0 [] ip_finish_output+0x31/0x2a0 net/ipv4/ip_output.c:323 [] NF_HOOK_COND include/linux/netfilter.h:298 [inline] [] ip_output+0x224/0x2a0 net/ipv4/ip_output.c:437 [] dst_output include/net/dst.h:444 [inline] [] ip_local_out net/ipv4/ip_output.c:127 [inline] [] __ip_queue_xmit+0x1425/0x2000 net/ipv4/ip_output.c:542 [] ip_queue_xmit+0x4c/0x70 net/ipv4/ip_output.c:556 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Cc: Jamal Hadi Salim Cc: Cong Wang Cc: Jiri Pirko Reviewed-by: Jamal Hadi Salim Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230620184425.1179809-1-edumazet@google.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/sch_netem.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index adc5407fd5d5..be42b1196786 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -969,6 +969,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (ret < 0) return ret; + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; old_loss_model = q->loss_model; @@ -977,7 +978,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; - return ret; + goto unlock; } } else { q->loss_model = CLG_RANDOM; @@ -1044,6 +1045,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, /* capping jitter to the range acceptable by tabledist() */ q->jitter = min_t(s64, abs(q->jitter), INT_MAX); +unlock: + sch_tree_unlock(sch); return ret; get_table_failure: @@ -1053,7 +1056,8 @@ get_table_failure: */ q->clg = old_clg; q->loss_model = old_loss_model; - return ret; + + goto unlock; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, From 304802e5b038e9e33e1b7fe5f933864e7a8e0ec1 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 26 Oct 2021 18:58:11 +0100 Subject: [PATCH 3677/4345] gpio: Allow per-parent interrupt data [ Upstream commit cfe6807d82e97e81c3209dca9448f091e1448a57 ] The core gpiolib code is able to deal with multiple interrupt parents for a single gpio irqchip. It however only allows a single piece of data to be conveyed to all flow handlers (either the gpio_chip or some other, driver-specific data). This means that drivers have to go through some interesting dance to find the correct context, something that isn't great in interrupt context (see aebdc8abc9db86e2bd33070fc2f961012fff74b4 for a prime example). Instead, offer an optional way for a pinctrl/gpio driver to provide an array of pointers which gets used to provide the correct context to the flow handler. Signed-off-by: Marc Zyngier Signed-off-by: Joey Gouly Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20211026175815.52703-2-joey.gouly@arm.com Signed-off-by: Linus Walleij Stable-dep-of: 8c00914e5438 ("gpiolib: Fix GPIO chip IRQ initialization restriction") Signed-off-by: Sasha Levin --- drivers/gpio/gpiolib.c | 9 +++++++-- include/linux/gpio/driver.h | 19 +++++++++++++++++-- 2 files changed, 24 insertions(+), 4 deletions(-) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 3e01a3ac652d..7ac86037a419 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1595,9 +1595,14 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, } if (gc->irq.parent_handler) { - void *data = gc->irq.parent_handler_data ?: gc; - for (i = 0; i < gc->irq.num_parents; i++) { + void *data; + + if (gc->irq.per_parent_data) + data = gc->irq.parent_handler_data_array[i]; + else + data = gc->irq.parent_handler_data ?: gc; + /* * The parent IRQ chip is already using the chip_data * for this IRQ chip, so our callbacks simply use the diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 0552a9859a01..64c93a36a3a9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -168,11 +168,18 @@ struct gpio_irq_chip { /** * @parent_handler_data: + * @parent_handler_data_array: * * Data associated, and passed to, the handler for the parent - * interrupt. + * interrupt. Can either be a single pointer if @per_parent_data + * is false, or an array of @num_parents pointers otherwise. If + * @per_parent_data is true, @parent_handler_data_array cannot be + * NULL. */ - void *parent_handler_data; + union { + void *parent_handler_data; + void **parent_handler_data_array; + }; /** * @num_parents: @@ -203,6 +210,14 @@ struct gpio_irq_chip { */ bool threaded; + /** + * @per_parent_data: + * + * True if parent_handler_data_array describes a @num_parents + * sized array to be used as parent data. + */ + bool per_parent_data; + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when From 75aa3f255c884c458ff4f3e6d4608debafa96a8c Mon Sep 17 00:00:00 2001 From: Jiawen Wu Date: Wed, 7 Jun 2023 16:18:03 +0800 Subject: [PATCH 3678/4345] gpiolib: Fix GPIO chip IRQ initialization restriction [ Upstream commit 8c00914e5438e3636f26b4f814b3297ae2a1b9ee ] In case of gpio-regmap, IRQ chip is added by regmap-irq and associated with GPIO chip by gpiochip_irqchip_add_domain(). The initialization flag was not added in gpiochip_irqchip_add_domain(), causing gpiochip_to_irq() to return -EPROBE_DEFER. Fixes: 5467801f1fcb ("gpio: Restrict usage of GPIO chip irq members before initialization") Signed-off-by: Jiawen Wu Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski Signed-off-by: Sasha Levin --- drivers/gpio/gpiolib.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 7ac86037a419..d10f621085e2 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1792,6 +1792,14 @@ int gpiochip_irqchip_add_domain(struct gpio_chip *gc, gc->to_irq = gpiochip_to_irq; gc->irq.domain = domain; + /* + * Using barrier() here to prevent compiler from reordering + * gc->irq.initialized before adding irqdomain. + */ + barrier(); + + gc->irq.initialized = true; + return 0; } EXPORT_SYMBOL_GPL(gpiochip_irqchip_add_domain); From 2b43198de03f1694a36b21ec26e26745b2019a3d Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 8 May 2023 18:22:19 +0200 Subject: [PATCH 3679/4345] scsi: target: iscsi: Prevent login threads from racing between each other [ Upstream commit 2a737d3b8c792400118d6cf94958f559de9c5e59 ] The tpg->np_login_sem is a semaphore that is used to serialize the login process when multiple login threads run concurrently against the same target portal group. The iscsi_target_locate_portal() function finds the tpg, calls iscsit_access_np() against the np_login_sem semaphore and saves the tpg pointer in conn->tpg; If iscsi_target_locate_portal() fails, the caller will check for the conn->tpg pointer and, if it's not NULL, then it will assume that iscsi_target_locate_portal() called iscsit_access_np() on the semaphore. Make sure that conn->tpg gets initialized only if iscsit_access_np() was successful, otherwise iscsit_deaccess_np() may end up being called against a semaphore we never took, allowing more than one thread to access the same tpg. Signed-off-by: Maurizio Lombardi Link: https://lore.kernel.org/r/20230508162219.1731964-4-mlombard@redhat.com Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/iscsi/iscsi_target_nego.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 8b40f10976ff..393156501888 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -1079,6 +1079,7 @@ int iscsi_target_locate_portal( iscsi_target_set_sock_callbacks(conn); login->np = np; + conn->tpg = NULL; login_req = (struct iscsi_login_req *) login->req; payload_length = ntoh24(login_req->dlength); @@ -1148,7 +1149,6 @@ int iscsi_target_locate_portal( */ sessiontype = strncmp(s_buf, DISCOVERY, 9); if (!sessiontype) { - conn->tpg = iscsit_global->discovery_tpg; if (!login->leading_connection) goto get_target; @@ -1165,9 +1165,11 @@ int iscsi_target_locate_portal( * Serialize access across the discovery struct iscsi_portal_group to * process login attempt. */ + conn->tpg = iscsit_global->discovery_tpg; if (iscsit_access_np(np, conn->tpg) < 0) { iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_SVC_UNAVAILABLE); + conn->tpg = NULL; ret = -1; goto out; } From 49a2b18f49724b5504771a8d10f9ab57807afba4 Mon Sep 17 00:00:00 2001 From: Denis Arefev Date: Thu, 27 Apr 2023 14:47:45 +0300 Subject: [PATCH 3680/4345] HID: wacom: Add error check to wacom_parse_and_register() [ Upstream commit 16a9c24f24fbe4564284eb575b18cc20586b9270 ] Added a variable check and transition in case of an error Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Denis Arefev Reviewed-by: Ping Cheng Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin --- drivers/hid/wacom_sys.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index a93070f5b214..36cb456709ed 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2419,8 +2419,13 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail_quirks; } - if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR) + if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR) { error = hid_hw_open(hdev); + if (error) { + hid_err(hdev, "hw open failed\n"); + goto fail_quirks; + } + } wacom_set_shared_values(wacom_wac); devres_close_group(&hdev->dev, wacom); From c13573032b7beb3e52b7b157be8427393d594f21 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 15 May 2023 21:46:00 +0100 Subject: [PATCH 3681/4345] arm64: Add missing Set/Way CMO encodings [ Upstream commit 8d0f019e4c4f2ee2de81efd9bf1c27e9fb3c0460 ] Add the missing Set/Way CMOs that apply to tagged memory. Signed-off-by: Marc Zyngier Reviewed-by: Cornelia Huck Reviewed-by: Steven Price Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20230515204601.1270428-2-maz@kernel.org Signed-off-by: Sasha Levin --- arch/arm64/include/asm/sysreg.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 06755fad3830..9fea6e976809 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -104,8 +104,14 @@ #define SB_BARRIER_INSN __SYS_BARRIER_INSN(0, 7, 31) #define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2) +#define SYS_DC_IGSW sys_insn(1, 0, 7, 6, 4) +#define SYS_DC_IGDSW sys_insn(1, 0, 7, 6, 6) #define SYS_DC_CSW sys_insn(1, 0, 7, 10, 2) +#define SYS_DC_CGSW sys_insn(1, 0, 7, 10, 4) +#define SYS_DC_CGDSW sys_insn(1, 0, 7, 10, 6) #define SYS_DC_CISW sys_insn(1, 0, 7, 14, 2) +#define SYS_DC_CIGSW sys_insn(1, 0, 7, 14, 4) +#define SYS_DC_CIGDSW sys_insn(1, 0, 7, 14, 6) /* * System registers, organised loosely by encoding but grouped together From dc357c0787e8dcea2b6763e3a873814ca488e9f0 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 24 Apr 2023 16:07:28 +0100 Subject: [PATCH 3682/4345] media: cec: core: don't set last_initiator if tx in progress [ Upstream commit 73af6c7511038249cad3d5f3b44bf8d78ac0f499 ] When a message was received the last_initiator is set to 0xff. This will force the signal free time for the next transmit to that for a new initiator. However, if a new transmit is already in progress, then don't set last_initiator, since that's the initiator of the current transmit. Overwriting this would cause the signal free time of a following transmit to be that of the new initiator instead of a next transmit. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/cec/core/cec-adap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index e23aa608f66f..97b479223fe5 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1085,7 +1085,8 @@ void cec_received_msg_ts(struct cec_adapter *adap, mutex_lock(&adap->lock); dprintk(2, "%s: %*ph\n", __func__, msg->len, msg->msg); - adap->last_initiator = 0xff; + if (!adap->transmit_in_progress) + adap->last_initiator = 0xff; /* Check if this message was for us (directed or broadcast). */ if (!cec_msg_is_broadcast(msg)) From 7d1a0733a55e82836e1f706de144b1347f03f60f Mon Sep 17 00:00:00 2001 From: Osama Muhammad Date: Thu, 25 May 2023 22:27:46 +0500 Subject: [PATCH 3683/4345] nfcsim.c: Fix error checking for debugfs_create_dir [ Upstream commit 9b9e46aa07273ceb96866b2e812b46f1ee0b8d2f ] This patch fixes the error checking in nfcsim.c. The DebugFS kernel API is developed in a way that the caller can safely ignore the errors that occur during the creation of DebugFS nodes. Signed-off-by: Osama Muhammad Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/nfc/nfcsim.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index dd27c85190d3..b42d386350b7 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -336,10 +336,6 @@ static struct dentry *nfcsim_debugfs_root; static void nfcsim_debugfs_init(void) { nfcsim_debugfs_root = debugfs_create_dir("nfcsim", NULL); - - if (!nfcsim_debugfs_root) - pr_err("Could not create debugfs entry\n"); - } static void nfcsim_debugfs_remove(void) From eaf1fa94520696ee7002613cec0b85afdd4d076a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 25 May 2023 18:38:37 +0300 Subject: [PATCH 3684/4345] usb: gadget: udc: fix NULL dereference in remove() [ Upstream commit 016da9c65fec9f0e78c4909ed9a0f2d567af6775 ] The "udc" pointer was never set in the probe() function so it will lead to a NULL dereference in udc_pci_remove() when we do: usb_del_gadget_udc(&udc->gadget); Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/ZG+A/dNpFWAlCChk@kili Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/udc/amd5536udc_pci.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/udc/amd5536udc_pci.c b/drivers/usb/gadget/udc/amd5536udc_pci.c index c80f9bd51b75..a36913ae31f9 100644 --- a/drivers/usb/gadget/udc/amd5536udc_pci.c +++ b/drivers/usb/gadget/udc/amd5536udc_pci.c @@ -170,6 +170,9 @@ static int udc_pci_probe( retval = -ENODEV; goto err_probe; } + + udc = dev; + return 0; err_probe: From fe949c1662c98a7ea5eeb91f62c3698950726c8f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 11 May 2023 11:57:04 -0700 Subject: [PATCH 3685/4345] Input: soc_button_array - add invalid acpi_index DMI quirk handling [ Upstream commit 20a99a291d564a559cc2fd013b4824a3bb3f1db7 ] Some devices have a wrong entry in their button array which points to a GPIO which is required in another driver, so soc_button_array must not claim it. A specific example of this is the Lenovo Yoga Book X90F / X90L, where the PNP0C40 home button entry points to a GPIO which is not a home button and which is required by the lenovo-yogabook driver. Add a DMI quirk table which can specify an ACPI GPIO resource index which should be skipped; and add an entry for the Lenovo Yoga Book X90F / X90L to this new DMI quirk table. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230414072116.4497-1-hdegoede@redhat.com Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/misc/soc_button_array.c | 30 +++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index 31c02c2019c1..67a134c8448d 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -108,6 +108,27 @@ static const struct dmi_system_id dmi_use_low_level_irq[] = { {} /* Terminating entry */ }; +/* + * Some devices have a wrong entry which points to a GPIO which is + * required in another driver, so this driver must not claim it. + */ +static const struct dmi_system_id dmi_invalid_acpi_index[] = { + { + /* + * Lenovo Yoga Book X90F / X90L, the PNP0C40 home button entry + * points to a GPIO which is not a home button and which is + * required by the lenovo-yogabook driver. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"), + }, + .driver_data = (void *)1l, + }, + {} /* Terminating entry */ +}; + /* * Get the Nth GPIO number from the ACPI object. */ @@ -137,6 +158,8 @@ soc_button_device_create(struct platform_device *pdev, struct platform_device *pd; struct gpio_keys_button *gpio_keys; struct gpio_keys_platform_data *gpio_keys_pdata; + const struct dmi_system_id *dmi_id; + int invalid_acpi_index = -1; int error, gpio, irq; int n_buttons = 0; @@ -154,10 +177,17 @@ soc_button_device_create(struct platform_device *pdev, gpio_keys = (void *)(gpio_keys_pdata + 1); n_buttons = 0; + dmi_id = dmi_first_match(dmi_invalid_acpi_index); + if (dmi_id) + invalid_acpi_index = (long)dmi_id->driver_data; + for (info = button_info; info->name; info++) { if (info->autorepeat != autorepeat) continue; + if (info->acpi_index == invalid_acpi_index) + continue; + error = soc_button_lookup_gpio(&pdev->dev, info->acpi_index, &gpio, &irq); if (error || irq < 0) { /* From 97b6c4c1d1a8483818e5fd46112409cead4ac0f7 Mon Sep 17 00:00:00 2001 From: Vineeth Vijayan Date: Thu, 4 May 2023 20:53:20 +0200 Subject: [PATCH 3686/4345] s390/cio: unregister device when the only path is gone [ Upstream commit 89c0c62e947a01e7a36b54582fd9c9e346170255 ] Currently, if the device is offline and all the channel paths are either configured or varied offline, the associated subchannel gets unregistered. Don't unregister the subchannel, instead unregister offline device. Signed-off-by: Vineeth Vijayan Reviewed-by: Peter Oberparleiter Signed-off-by: Alexander Gordeev Signed-off-by: Sasha Levin --- drivers/s390/cio/device.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 33280ca181e9..6f9c81db6e42 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1385,6 +1385,7 @@ void ccw_device_set_notoper(struct ccw_device *cdev) enum io_sch_action { IO_SCH_UNREG, IO_SCH_ORPH_UNREG, + IO_SCH_UNREG_CDEV, IO_SCH_ATTACH, IO_SCH_UNREG_ATTACH, IO_SCH_ORPH_ATTACH, @@ -1417,7 +1418,7 @@ static enum io_sch_action sch_get_action(struct subchannel *sch) } if ((sch->schib.pmcw.pam & sch->opm) == 0) { if (ccw_device_notify(cdev, CIO_NO_PATH) != NOTIFY_OK) - return IO_SCH_UNREG; + return IO_SCH_UNREG_CDEV; return IO_SCH_DISC; } if (device_is_disconnected(cdev)) @@ -1479,6 +1480,7 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process) case IO_SCH_ORPH_ATTACH: ccw_device_set_disconnected(cdev); break; + case IO_SCH_UNREG_CDEV: case IO_SCH_UNREG_ATTACH: case IO_SCH_UNREG: if (!cdev) @@ -1512,6 +1514,7 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process) if (rc) goto out; break; + case IO_SCH_UNREG_CDEV: case IO_SCH_UNREG_ATTACH: spin_lock_irqsave(sch->lock, flags); if (cdev->private->flags.resuming) { From 9138ed7e2b439b9f8f393194861e5b7967b50716 Mon Sep 17 00:00:00 2001 From: Clark Wang Date: Fri, 5 May 2023 14:35:57 +0800 Subject: [PATCH 3687/4345] spi: lpspi: disable lpspi module irq in DMA mode [ Upstream commit 9728fb3ce11729aa8c276825ddf504edeb00611d ] When all bits of IER are set to 0, we still can observe the lpspi irq events when using DMA mode to transfer data. So disable irq to avoid the too much irq events. Signed-off-by: Clark Wang Link: https://lore.kernel.org/r/20230505063557.3962220-1-xiaoning.wang@nxp.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-fsl-lpspi.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 5d98611dd999..c5ff6e8c45be 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -906,9 +906,14 @@ static int fsl_lpspi_probe(struct platform_device *pdev) ret = fsl_lpspi_dma_init(&pdev->dev, fsl_lpspi, controller); if (ret == -EPROBE_DEFER) goto out_pm_get; - if (ret < 0) dev_err(&pdev->dev, "dma setup error %d, use pio\n", ret); + else + /* + * disable LPSPI module IRQ when enable DMA mode successfully, + * to prevent the unexpected LPSPI module IRQ events. + */ + disable_irq(irq); ret = devm_spi_register_controller(&pdev->dev, controller); if (ret < 0) { From fa08753c2d049442cb4c990759befd3e4effdc0b Mon Sep 17 00:00:00 2001 From: Herve Codina Date: Tue, 23 May 2023 17:12:22 +0200 Subject: [PATCH 3688/4345] ASoC: simple-card: Add missing of_node_put() in case of error [ Upstream commit 8938f75a5e35c597a647c28984a0304da7a33d63 ] In the error path, a of_node_put() for platform is missing. Just add it. Signed-off-by: Herve Codina Acked-by: Kuninori Morimoto Link: https://lore.kernel.org/r/20230523151223.109551-9-herve.codina@bootlin.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/generic/simple-card.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index d916ec69c24f..ac97e8b7978c 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -410,6 +410,7 @@ static int simple_for_each_link(struct asoc_simple_priv *priv, if (ret < 0) { of_node_put(codec); + of_node_put(plat); of_node_put(np); goto error; } From a819de62ec2bf2133892b955f8c357bbfa1c92df Mon Sep 17 00:00:00 2001 From: Edson Juliano Drosdeck Date: Mon, 29 May 2023 15:19:11 -0300 Subject: [PATCH 3689/4345] ASoC: nau8824: Add quirk to active-high jack-detect [ Upstream commit e384dba03e3294ce7ea69e4da558e9bf8f0e8946 ] Add entries for Positivo laptops: CW14Q01P, K1424G, N14ZP74G to the DMI table, so that active-high jack-detect will work properly on these laptops. Signed-off-by: Edson Juliano Drosdeck Link: https://lore.kernel.org/r/20230529181911.632851-1-edson.drosdeck@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/nau8824.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c index a95fe3fff1db..9b22219a7693 100644 --- a/sound/soc/codecs/nau8824.c +++ b/sound/soc/codecs/nau8824.c @@ -1896,6 +1896,30 @@ static const struct dmi_system_id nau8824_quirk_table[] = { }, .driver_data = (void *)(NAU8824_JD_ACTIVE_HIGH), }, + { + /* Positivo CW14Q01P */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Positivo Tecnologia SA"), + DMI_MATCH(DMI_BOARD_NAME, "CW14Q01P"), + }, + .driver_data = (void *)(NAU8824_JD_ACTIVE_HIGH), + }, + { + /* Positivo K1424G */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Positivo Tecnologia SA"), + DMI_MATCH(DMI_BOARD_NAME, "K1424G"), + }, + .driver_data = (void *)(NAU8824_JD_ACTIVE_HIGH), + }, + { + /* Positivo N14ZP74G */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Positivo Tecnologia SA"), + DMI_MATCH(DMI_BOARD_NAME, "N14ZP74G"), + }, + .driver_data = (void *)(NAU8824_JD_ACTIVE_HIGH), + }, {} }; From 79cf5657be38ce545f955a6bcdc36d083304853f Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Thu, 25 May 2023 19:41:45 +0200 Subject: [PATCH 3690/4345] s390/purgatory: disable branch profiling [ Upstream commit 03c5c83b70dca3729a3eb488e668e5044bd9a5ea ] Avoid linker error for randomly generated config file that has CONFIG_BRANCH_PROFILE_NONE enabled and make it similar to riscv, x86 and also to commit 4bf3ec384edf ("s390: disable branch profiling for vdso"). Reviewed-by: Vasily Gorbik Signed-off-by: Alexander Gordeev Signed-off-by: Sasha Levin --- arch/s390/purgatory/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile index 21c4ebe29b9a..a93c9aba834b 100644 --- a/arch/s390/purgatory/Makefile +++ b/arch/s390/purgatory/Makefile @@ -25,6 +25,7 @@ KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common KBUILD_CFLAGS += -fno-stack-protector +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING KBUILD_CFLAGS += $(CLANG_FLAGS) KBUILD_CFLAGS += $(call cc-option,-fno-PIE) KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS)) From 32134e7a0f218f30b89ba2d3ea29a637722ac507 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 10 May 2023 12:51:56 +0200 Subject: [PATCH 3691/4345] ARM: dts: Fix erroneous ADS touchscreen polarities [ Upstream commit 4a672d500bfd6bb87092c33d5a2572c3d0a1cf83 ] Several device tree files get the polarity of the pendown-gpios wrong: this signal is active low. Fix up all incorrect flags, so that operating systems can rely on the flag being correctly set. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230510105156.1134320-1-linus.walleij@linaro.org Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- arch/arm/boot/dts/am57xx-cl-som-am57x.dts | 2 +- arch/arm/boot/dts/at91sam9261ek.dts | 2 +- arch/arm/boot/dts/imx7d-pico-hobbit.dts | 2 +- arch/arm/boot/dts/imx7d-sdb.dts | 2 +- arch/arm/boot/dts/omap3-cm-t3x.dtsi | 2 +- arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi | 2 +- arch/arm/boot/dts/omap3-lilly-a83x.dtsi | 2 +- arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi | 2 +- arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi | 2 +- arch/arm/boot/dts/omap3-pandora-common.dtsi | 2 +- arch/arm/boot/dts/omap5-cm-t54.dts | 2 +- 11 files changed, 11 insertions(+), 11 deletions(-) diff --git a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts index aed81568a297..d783d1f6950b 100644 --- a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts +++ b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts @@ -527,7 +527,7 @@ interrupt-parent = <&gpio1>; interrupts = <31 0>; - pendown-gpio = <&gpio1 31 0>; + pendown-gpio = <&gpio1 31 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <0x0>; diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts index beed819609e8..8f3b483bb64d 100644 --- a/arch/arm/boot/dts/at91sam9261ek.dts +++ b/arch/arm/boot/dts/at91sam9261ek.dts @@ -156,7 +156,7 @@ compatible = "ti,ads7843"; interrupts-extended = <&pioC 2 IRQ_TYPE_EDGE_BOTH>; spi-max-frequency = <3000000>; - pendown-gpio = <&pioC 2 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&pioC 2 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <150>; ti,x-max = /bits/ 16 <3830>; diff --git a/arch/arm/boot/dts/imx7d-pico-hobbit.dts b/arch/arm/boot/dts/imx7d-pico-hobbit.dts index d917dc4f2f22..6ad39dca7009 100644 --- a/arch/arm/boot/dts/imx7d-pico-hobbit.dts +++ b/arch/arm/boot/dts/imx7d-pico-hobbit.dts @@ -64,7 +64,7 @@ interrupt-parent = <&gpio2>; interrupts = <7 0>; spi-max-frequency = <1000000>; - pendown-gpio = <&gpio2 7 0>; + pendown-gpio = <&gpio2 7 GPIO_ACTIVE_LOW>; vcc-supply = <®_3p3v>; ti,x-min = /bits/ 16 <0>; ti,x-max = /bits/ 16 <4095>; diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts index 6d562ebe9029..d3b49a5b30b7 100644 --- a/arch/arm/boot/dts/imx7d-sdb.dts +++ b/arch/arm/boot/dts/imx7d-sdb.dts @@ -198,7 +198,7 @@ pinctrl-0 = <&pinctrl_tsc2046_pendown>; interrupt-parent = <&gpio2>; interrupts = <29 0>; - pendown-gpio = <&gpio2 29 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio2 29 GPIO_ACTIVE_LOW>; touchscreen-max-pressure = <255>; wakeup-source; }; diff --git a/arch/arm/boot/dts/omap3-cm-t3x.dtsi b/arch/arm/boot/dts/omap3-cm-t3x.dtsi index e61b8a2bfb7d..51baedf1603b 100644 --- a/arch/arm/boot/dts/omap3-cm-t3x.dtsi +++ b/arch/arm/boot/dts/omap3-cm-t3x.dtsi @@ -227,7 +227,7 @@ interrupt-parent = <&gpio2>; interrupts = <25 0>; /* gpio_57 */ - pendown-gpio = <&gpio2 25 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio2 25 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <0x0>; ti,x-max = /bits/ 16 <0x0fff>; diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi b/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi index 3decc2d78a6c..a7f99ae0c1fe 100644 --- a/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi +++ b/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi @@ -54,7 +54,7 @@ interrupt-parent = <&gpio1>; interrupts = <27 0>; /* gpio_27 */ - pendown-gpio = <&gpio1 27 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio1 27 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <0x0>; ti,x-max = /bits/ 16 <0x0fff>; diff --git a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi index 73d477898ec2..06e7cf96c663 100644 --- a/arch/arm/boot/dts/omap3-lilly-a83x.dtsi +++ b/arch/arm/boot/dts/omap3-lilly-a83x.dtsi @@ -311,7 +311,7 @@ interrupt-parent = <&gpio1>; interrupts = <8 0>; /* boot6 / gpio_8 */ spi-max-frequency = <1000000>; - pendown-gpio = <&gpio1 8 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio1 8 GPIO_ACTIVE_LOW>; vcc-supply = <®_vcc3>; pinctrl-names = "default"; pinctrl-0 = <&tsc2048_pins>; diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi index 1d6e88f99eb3..c3570acc35fa 100644 --- a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi +++ b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi @@ -149,7 +149,7 @@ interrupt-parent = <&gpio4>; interrupts = <18 0>; /* gpio_114 */ - pendown-gpio = <&gpio4 18 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio4 18 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <0x0>; ti,x-max = /bits/ 16 <0x0fff>; diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi index 7e30f9d45790..d95a0e130058 100644 --- a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi +++ b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi @@ -160,7 +160,7 @@ interrupt-parent = <&gpio4>; interrupts = <18 0>; /* gpio_114 */ - pendown-gpio = <&gpio4 18 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio4 18 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <0x0>; ti,x-max = /bits/ 16 <0x0fff>; diff --git a/arch/arm/boot/dts/omap3-pandora-common.dtsi b/arch/arm/boot/dts/omap3-pandora-common.dtsi index 37608af6c07f..ca6d777ebf84 100644 --- a/arch/arm/boot/dts/omap3-pandora-common.dtsi +++ b/arch/arm/boot/dts/omap3-pandora-common.dtsi @@ -651,7 +651,7 @@ pinctrl-0 = <&penirq_pins>; interrupt-parent = <&gpio3>; interrupts = <30 IRQ_TYPE_NONE>; /* GPIO_94 */ - pendown-gpio = <&gpio3 30 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio3 30 GPIO_ACTIVE_LOW>; vcc-supply = <&vaux4>; ti,x-min = /bits/ 16 <0>; diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts index ca759b7b8a58..e62ea8b6d53f 100644 --- a/arch/arm/boot/dts/omap5-cm-t54.dts +++ b/arch/arm/boot/dts/omap5-cm-t54.dts @@ -354,7 +354,7 @@ interrupt-parent = <&gpio1>; interrupts = <15 0>; /* gpio1_wk15 */ - pendown-gpio = <&gpio1 15 GPIO_ACTIVE_HIGH>; + pendown-gpio = <&gpio1 15 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <0x0>; From 0b0fdc43b2ab7fee771da254e968b3b63e1c072a Mon Sep 17 00:00:00 2001 From: Inki Dae Date: Fri, 19 May 2023 08:55:05 +0900 Subject: [PATCH 3692/4345] drm/exynos: vidi: fix a wrong error return [ Upstream commit 4a059559809fd1ddbf16f847c4d2237309c08edf ] Fix a wrong error return by dropping an error return. When vidi driver is remvoed, if ctx->raw_edid isn't same as fake_edid_info then only what we have to is to free ctx->raw_edid so that driver removing can work correctly - it's not an error case. Signed-off-by: Inki Dae Reviewed-by: Andi Shyti Signed-off-by: Sasha Levin --- drivers/gpu/drm/exynos/exynos_drm_vidi.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index e5662bdcbbde..e96436e11a36 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -468,8 +468,6 @@ static int vidi_remove(struct platform_device *pdev) if (ctx->raw_edid != (struct edid *)fake_edid_info) { kfree(ctx->raw_edid); ctx->raw_edid = NULL; - - return -EINVAL; } component_del(&pdev->dev, &vidi_component_ops); From 485fe165084bdff372049f9d109326756764b620 Mon Sep 17 00:00:00 2001 From: Min Li Date: Fri, 26 May 2023 21:01:31 +0800 Subject: [PATCH 3693/4345] drm/exynos: fix race condition UAF in exynos_g2d_exec_ioctl [ Upstream commit 48bfd02569f5db49cc033f259e66d57aa6efc9a3 ] If it is async, runqueue_node is freed in g2d_runqueue_worker on another worker thread. So in extreme cases, if g2d_runqueue_worker runs first, and then executes the following if statement, there will be use-after-free. Signed-off-by: Min Li Reviewed-by: Andi Shyti Signed-off-by: Inki Dae Signed-off-by: Sasha Levin --- drivers/gpu/drm/exynos/exynos_drm_g2d.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 967a5cdc120e..81211a9d9d0a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -1332,7 +1332,7 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data, /* Let the runqueue know that there is work to do. */ queue_work(g2d->g2d_workq, &g2d->runqueue_work); - if (runqueue_node->async) + if (req->async) goto out; wait_for_completion(&runqueue_node->complete); From d8efc77f23c84a46bd8a43bec833cf637222b2bf Mon Sep 17 00:00:00 2001 From: Min Li Date: Sat, 3 Jun 2023 15:43:45 +0800 Subject: [PATCH 3694/4345] drm/radeon: fix race condition UAF in radeon_gem_set_domain_ioctl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 982b173a6c6d9472730c3116051977e05d17c8c5 ] Userspace can race to free the gobj(robj converted from), robj should not be accessed again after drm_gem_object_put, otherwith it will result in use-after-free. Reviewed-by: Christian König Signed-off-by: Min Li Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/radeon/radeon_gem.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index e5c4271e64ed..75053917d213 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -385,7 +385,6 @@ int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data, struct radeon_device *rdev = dev->dev_private; struct drm_radeon_gem_set_domain *args = data; struct drm_gem_object *gobj; - struct radeon_bo *robj; int r; /* for now if someone requests domain CPU - @@ -398,13 +397,12 @@ int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data, up_read(&rdev->exclusive_lock); return -ENOENT; } - robj = gem_to_radeon_bo(gobj); r = radeon_gem_set_domain(gobj, args->read_domains, args->write_domain); drm_gem_object_put(gobj); up_read(&rdev->exclusive_lock); - r = radeon_gem_handle_lockup(robj->rdev, r); + r = radeon_gem_handle_lockup(rdev, r); return r; } From 5a257f3553660164d406765ade2ea8407155dec7 Mon Sep 17 00:00:00 2001 From: Dheeraj Kumar Srivastava Date: Sat, 17 Jun 2023 02:52:36 +0530 Subject: [PATCH 3695/4345] x86/apic: Fix kernel panic when booting with intremap=off and x2apic_phys [ Upstream commit 85d38d5810e285d5aec7fb5283107d1da70c12a9 ] When booting with "intremap=off" and "x2apic_phys" on the kernel command line, the physical x2APIC driver ends up being used even when x2APIC mode is disabled ("intremap=off" disables x2APIC mode). This happens because the first compound condition check in x2apic_phys_probe() is false due to x2apic_mode == 0 and so the following one returns true after default_acpi_madt_oem_check() having already selected the physical x2APIC driver. This results in the following panic: kernel BUG at arch/x86/kernel/apic/io_apic.c:2409! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.4.0-rc2-ver4.1rc2 #2 Hardware name: Dell Inc. PowerEdge R6515/07PXPY, BIOS 2.3.6 07/06/2021 RIP: 0010:setup_IO_APIC+0x9c/0xaf0 Call Trace: ? native_read_msr apic_intr_mode_init x86_late_time_init start_kernel x86_64_start_reservations x86_64_start_kernel secondary_startup_64_no_verify which is: setup_IO_APIC: apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n"); for_each_ioapic(ioapic) BUG_ON(mp_irqdomain_create(ioapic)); Return 0 to denote that x2APIC has not been enabled when probing the physical x2APIC driver. [ bp: Massage commit message heavily. ] Fixes: 9ebd680bd029 ("x86, apic: Use probe routines to simplify apic selection") Signed-off-by: Dheeraj Kumar Srivastava Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Kishon Vijay Abraham I Reviewed-by: Vasant Hegde Reviewed-by: Cyrill Gorcunov Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230616212236.1389-1-dheerajkumar.srivastava@amd.com Signed-off-by: Sasha Levin --- arch/x86/kernel/apic/x2apic_phys.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 032a00e5d9fa..76c80e191a1b 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -97,7 +97,10 @@ static void init_x2apic_ldr(void) static int x2apic_phys_probe(void) { - if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys())) + if (!x2apic_mode) + return 0; + + if (x2apic_phys || x2apic_fadt_phys()) return 1; return apic == &apic_x2apic_phys; From 42997367cb67f3e361dd1d6bc08ee07e21457dbc Mon Sep 17 00:00:00 2001 From: Clark Wang Date: Mon, 29 May 2023 16:02:51 +0800 Subject: [PATCH 3696/4345] i2c: imx-lpi2c: fix type char overflow issue when calculating the clock cycle [ Upstream commit e69b9bc170c6d93ee375a5cbfd15f74c0fb59bdd ] Claim clkhi and clklo as integer type to avoid possible calculation errors caused by data overflow. Fixes: a55fa9d0e42e ("i2c: imx-lpi2c: add low power i2c bus driver") Signed-off-by: Clark Wang Signed-off-by: Carlos Song Reviewed-by: Andi Shyti Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-imx-lpi2c.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index d45ec26d51cb..c688f11ae5c9 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -200,8 +200,8 @@ static void lpi2c_imx_stop(struct lpi2c_imx_struct *lpi2c_imx) /* CLKLO = I2C_CLK_RATIO * CLKHI, SETHOLD = CLKHI, DATAVD = CLKHI/2 */ static int lpi2c_imx_config(struct lpi2c_imx_struct *lpi2c_imx) { - u8 prescale, filt, sethold, clkhi, clklo, datavd; - unsigned int clk_rate, clk_cycle; + u8 prescale, filt, sethold, datavd; + unsigned int clk_rate, clk_cycle, clkhi, clklo; enum lpi2c_imx_pincfg pincfg; unsigned int temp; From f19a4818a92ae0d998df221f554be33c3224eee9 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 25 Jan 2021 23:19:17 +0100 Subject: [PATCH 3697/4345] netfilter: nftables: statify nft_parse_register() commit 08a01c11a5bb3de9b0a9c9b2685867e50eda9910 upstream. This function is not used anymore by any extension, statify it. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 1 - net/netfilter/nf_tables_api.c | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 564fbe0c865f..030237f3d82a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -205,7 +205,6 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) } int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); -unsigned int nft_parse_register(const struct nlattr *attr); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 92ea3332cdda..07807b397be2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8492,7 +8492,7 @@ EXPORT_SYMBOL_GPL(nft_parse_u32_check); * Registers used to be 128 bit wide, these register numbers will be * mapped to the corresponding 32 bit register numbers. */ -unsigned int nft_parse_register(const struct nlattr *attr) +static unsigned int nft_parse_register(const struct nlattr *attr) { unsigned int reg; @@ -8504,7 +8504,6 @@ unsigned int nft_parse_register(const struct nlattr *attr) return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; } } -EXPORT_SYMBOL_GPL(nft_parse_register); /** * nft_dump_register - dump a register value to a netlink attribute From 9e8d927cfa564e5a00cd287bd66fac6d45f0af39 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 17 Mar 2022 11:59:26 +0100 Subject: [PATCH 3698/4345] netfilter: nf_tables: validate registers coming from userspace. commit 6e1acfa387b9ff82cfc7db8cc3b6959221a95851 upstream. Bail out in case userspace uses unsupported registers. Fixes: 49499c3e6e18 ("netfilter: nf_tables: switch registers to 32 bit addressing") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 07807b397be2..9f9a5a3b4c99 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8483,26 +8483,23 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) } EXPORT_SYMBOL_GPL(nft_parse_u32_check); -/** - * nft_parse_register - parse a register value from a netlink attribute - * - * @attr: netlink attribute - * - * Parse and translate a register value from a netlink attribute. - * Registers used to be 128 bit wide, these register numbers will be - * mapped to the corresponding 32 bit register numbers. - */ -static unsigned int nft_parse_register(const struct nlattr *attr) +static int nft_parse_register(const struct nlattr *attr, u32 *preg) { unsigned int reg; reg = ntohl(nla_get_be32(attr)); switch (reg) { case NFT_REG_VERDICT...NFT_REG_4: - return reg * NFT_REG_SIZE / NFT_REG32_SIZE; + *preg = reg * NFT_REG_SIZE / NFT_REG32_SIZE; + break; + case NFT_REG32_00...NFT_REG32_15: + *preg = reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; + break; default: - return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; + return -ERANGE; } + + return 0; } /** @@ -8553,7 +8550,10 @@ int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) u32 reg; int err; - reg = nft_parse_register(attr); + err = nft_parse_register(attr, ®); + if (err < 0) + return err; + err = nft_validate_register_load(reg, len); if (err < 0) return err; @@ -8622,7 +8622,10 @@ int nft_parse_register_store(const struct nft_ctx *ctx, int err; u32 reg; - reg = nft_parse_register(attr); + err = nft_parse_register(attr, ®); + if (err < 0) + return err; + err = nft_validate_register_store(ctx, reg, data, type, len); if (err < 0) return err; From 8b7454dd984a75d0eaa6a02940c65cd3671fcddc Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 30 May 2022 18:24:05 +0200 Subject: [PATCH 3699/4345] netfilter: nf_tables: hold mutex on netns pre_exit path commit 3923b1e4406680d57da7e873da77b1683035d83f upstream. clean_net() runs in workqueue while walking over the lists, grab mutex. Fixes: 767d1216bff8 ("netfilter: nftables: fix possible UAF over chains from packet path in netns") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9f9a5a3b4c99..e59cad1f7a36 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8983,7 +8983,9 @@ static int __net_init nf_tables_init_net(struct net *net) static void __net_exit nf_tables_pre_exit_net(struct net *net) { + mutex_lock(&net->nft.commit_mutex); __nft_release_hooks(net); + mutex_unlock(&net->nft.commit_mutex); } static void __net_exit nf_tables_exit_net(struct net *net) From 29917a20be438602e5a1042a639e7d9af9db5bdc Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Thu, 15 Jun 2023 16:56:07 +0200 Subject: [PATCH 3700/4345] bpf/btf: Accept function names that contain dots [ Upstream commit 9724160b3942b0a967b91a59f81da5593f28b8ba ] When building a kernel with LLVM=1, LLVM_IAS=0 and CONFIG_KASAN=y, LLVM leaves DWARF tags for the "asan.module_ctor" & co symbols. In turn, pahole creates BTF_KIND_FUNC entries for these and this makes the BTF metadata validation fail because they contain a dot. In a dramatic turn of event, this BTF verification failure can cause the netfilter_bpf initialization to fail, causing netfilter_core to free the netfilter_helper hashmap and netfilter_ftp to trigger a use-after-free. The risk of u-a-f in netfilter will be addressed separately but the existence of "asan.module_ctor" debug info under some build conditions sounds like a good enough reason to accept functions that contain dots in BTF. Although using only LLVM=1 is the recommended way to compile clang-based kernels, users can certainly do LLVM=1, LLVM_IAS=0 as well and we still try to support that combination according to Nick. To clarify: - > v5.10 kernel, LLVM=1 (LLVM_IAS=0 is not the default) is recommended, but user can still have LLVM=1, LLVM_IAS=0 to trigger the issue - <= 5.10 kernel, LLVM=1 (LLVM_IAS=0 is the default) is recommended in which case GNU as will be used Fixes: 1dc92851849c ("bpf: kernel side support for BTF Var and DataSec") Signed-off-by: Florent Revest Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Cc: Yonghong Song Cc: Nick Desaulniers Link: https://lore.kernel.org/bpf/20230615145607.3469985-1-revest@chromium.org Signed-off-by: Sasha Levin --- kernel/bpf/btf.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index cb80d18a49b5..06c028bdb8d4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -604,31 +604,30 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset) offset < btf->hdr.str_len; } -static bool __btf_name_char_ok(char c, bool first, bool dot_ok) +static bool __btf_name_char_ok(char c, bool first) { if ((first ? !isalpha(c) : !isalnum(c)) && c != '_' && - ((c == '.' && !dot_ok) || - c != '.')) + c != '.') return false; return true; } -static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) +static bool __btf_name_valid(const struct btf *btf, u32 offset) { /* offset must be valid */ const char *src = &btf->strings[offset]; const char *src_limit; - if (!__btf_name_char_ok(*src, true, dot_ok)) + if (!__btf_name_char_ok(*src, true)) return false; /* set a limit on identifier length */ src_limit = src + KSYM_NAME_LEN; src++; while (*src && src < src_limit) { - if (!__btf_name_char_ok(*src, false, dot_ok)) + if (!__btf_name_char_ok(*src, false)) return false; src++; } @@ -636,17 +635,14 @@ static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) return !*src; } -/* Only C-style identifier is permitted. This can be relaxed if - * necessary. - */ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) { - return __btf_name_valid(btf, offset, false); + return __btf_name_valid(btf, offset); } static bool btf_name_valid_section(const struct btf *btf, u32 offset) { - return __btf_name_valid(btf, offset, true); + return __btf_name_valid(btf, offset); } static const char *__btf_name_by_offset(const struct btf *btf, u32 offset) @@ -3417,7 +3413,7 @@ static s32 btf_var_check_meta(struct btf_verifier_env *env, } if (!t->name_off || - !__btf_name_valid(env->btf, t->name_off, true)) { + !__btf_name_valid(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } From 381518b4a9165cd793599c1668c82079fcbcbe1f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 28 Jun 2023 10:28:17 +0200 Subject: [PATCH 3701/4345] Linux 5.10.186 Link: https://lore.kernel.org/r/20230626180744.453069285@linuxfoundation.org Tested-by: Jon Hunter Tested-by: Chris Paterson (CIP) Tested-by: Guenter Roeck Tested-by: Salvatore Bonaccorso Tested-by: Linux Kernel Functional Testing Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 73e6cc1992c2..bb2be0ed9ff2 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 185 +SUBLEVEL = 186 EXTRAVERSION = NAME = Dare mighty things From 2f2122a869394074fa55a66af652a857fd78bd82 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 28 Jun 2023 10:28:01 +0000 Subject: [PATCH 3702/4345] Revert "neighbour: fix unaligned access to pneigh_entry" This reverts commit 9fcc3c3d26a049aa04e0bc0462f84a9a775f428e which is commit ed779fe4c9b5a20b4ab4fd6f3e19807445bb78c7 upstream. It breaks the Android kernel abi and is not needed for Android systems, so it is safe to revert. Bug: 161946584 Change-Id: I0aa37ddcb0939b55d0d1b74ab3e0432b02cc5285 Signed-off-by: Greg Kroah-Hartman --- include/net/neighbour.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 67093655d796..7750ef0fe0dd 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -180,7 +180,7 @@ struct pneigh_entry { struct net_device *dev; u8 flags; u8 protocol; - u32 key[]; + u8 key[]; }; /* From 69dc2c1a79b89c0bed7355a1c47020772b6efa6c Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 10 Apr 2023 10:14:02 +0800 Subject: [PATCH 3703/4345] UPSTREAM: f2fs: fix to avoid use-after-free for cached IPU bio [ Upstream commit 5cdb422c839134273866208dad5360835ddb9794 ] xfstest generic/019 reports a bug: kernel BUG at mm/filemap.c:1619! RIP: 0010:folio_end_writeback+0x8a/0x90 Call Trace: end_page_writeback+0x1c/0x60 f2fs_write_end_io+0x199/0x420 bio_endio+0x104/0x180 submit_bio_noacct+0xa5/0x510 submit_bio+0x48/0x80 f2fs_submit_write_bio+0x35/0x300 f2fs_submit_merged_ipu_write+0x2a0/0x2b0 f2fs_write_single_data_page+0x838/0x8b0 f2fs_write_cache_pages+0x379/0xa30 f2fs_write_data_pages+0x30c/0x340 do_writepages+0xd8/0x1b0 __writeback_single_inode+0x44/0x370 writeback_sb_inodes+0x233/0x4d0 __writeback_inodes_wb+0x56/0xf0 wb_writeback+0x1dd/0x2d0 wb_workfn+0x367/0x4a0 process_one_work+0x21d/0x430 worker_thread+0x4e/0x3c0 kthread+0x103/0x130 ret_from_fork+0x2c/0x50 The root cause is: after cp_error is set, f2fs_submit_merged_ipu_write() in f2fs_write_single_data_page() tries to flush IPU bio in cache, however f2fs_submit_merged_ipu_write() missed to check validity of @bio parameter, result in submitting random cached bio which belong to other IO context, then it will cause use-after-free issue, fix it by adding additional validity check. Fixes: 0b20fcec8651 ("f2fs: cache global IPU bio") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin Bug: 268109575 Change-Id: Ifbdad0f8e8b51592ed63d025cf13965e623a7956 Signed-off-by: Tudor Ambarus --- fs/f2fs/data.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index d6be65b40302..113be0d3ee5b 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -829,6 +829,8 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, bool found = false; struct bio *target = bio ? *bio : NULL; + f2fs_bug_on(sbi, !target && !page); + for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) { struct f2fs_bio_info *io = sbi->write_io[DATA] + temp; struct list_head *head = &io->bio_list; @@ -2875,7 +2877,8 @@ out: if (unlikely(f2fs_cp_error(sbi))) { f2fs_submit_merged_write(sbi, DATA); - f2fs_submit_merged_ipu_write(sbi, bio, NULL); + if (bio && *bio) + f2fs_submit_merged_ipu_write(sbi, bio, NULL); submitted = NULL; } From 69a794a283c77a4fd33455697deaa77155d58d08 Mon Sep 17 00:00:00 2001 From: Oven Date: Fri, 16 Jun 2023 20:49:05 +0800 Subject: [PATCH 3704/4345] ANDROID: vendor_hooks: Add hooks to avoid key threads stalled in memory allocations We add these hooks to avoid key threads blocked in memory allocation path. -android_vh_free_unref_page_bypass ----We create a memory pool for the key threads. This hook determines whether a page should be free to the pool or to buddy freelist. It works with a existing hook `android_vh_alloc_pages_reclaim_bypass`, which takes pages out of the pool. -android_vh_kvmalloc_node_use_vmalloc ----For key threads, we perfer not to run into direct reclaim. So we clear __GFP_DIRECT_RECLAIM flag. For threads which are not that important, we perfer use vmalloc. -android_vh_should_alloc_pages_retry ----Before key threads run into direct reclaim, we want to retry with a lower watermark. -android_vh_unreserve_highatomic_bypass ----We want to keep more highatomic pages when unreserve them to avoid highatomic allocation failures. -android_vh_pageset_update ----We found the default per-cpu pageset is quite few in smartphones with large ram size. This hook is used to increase it to reduce zone->lock contentions. -android_vh_rmqueue_bulk_bypass ----We found sometimes when key threads run into rmqueue_bulk, it took several milliseconds spinning at zone->lock or filling per-cpu pages. We use this hook to take pages from the mempool mentioned above, rather than grab zone->lock and fill a batch of pages to per-cpu. Bug: 288216516 Change-Id: I1656032d6819ca627723341987b6094775bc345f Signed-off-by: Oven --- drivers/android/vendor_hooks.c | 6 ++++++ include/trace/hooks/mm.h | 21 +++++++++++++++++++++ mm/page_alloc.c | 30 ++++++++++++++++++++++++++++++ mm/util.c | 7 +++++++ 4 files changed, 64 insertions(+) diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index 2ce349294f3d..0aa79f03f578 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -332,6 +332,12 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_do_page_trylock); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_page_referenced_check_bypass); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_drain_all_pages_bypass); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_cma_drain_all_pages_bypass); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_free_unref_page_bypass); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_kvmalloc_node_use_vmalloc); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_should_alloc_pages_retry); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_unreserve_highatomic_bypass); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_pageset_update); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rmqueue_bulk_bypass); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_pcplist_add_cma_pages_bypass); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_psi_event); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_psi_group); diff --git a/include/trace/hooks/mm.h b/include/trace/hooks/mm.h index 8fecbc8b3d5b..d041bd44edaf 100644 --- a/include/trace/hooks/mm.h +++ b/include/trace/hooks/mm.h @@ -192,6 +192,27 @@ DECLARE_HOOK(android_vh_mark_page_accessed, DECLARE_HOOK(android_vh_cma_drain_all_pages_bypass, TP_PROTO(unsigned int migratetype, bool *bypass), TP_ARGS(migratetype, bypass)); +DECLARE_HOOK(android_vh_free_unref_page_bypass, + TP_PROTO(struct page *page, int order, int migratetype, bool *bypass), + TP_ARGS(page, order, migratetype, bypass)); +DECLARE_HOOK(android_vh_kvmalloc_node_use_vmalloc, + TP_PROTO(size_t size, gfp_t *kmalloc_flags, bool *use_vmalloc), + TP_ARGS(size, kmalloc_flags, use_vmalloc)); +DECLARE_HOOK(android_vh_should_alloc_pages_retry, + TP_PROTO(gfp_t gfp_mask, int order, int *alloc_flags, + int migratetype, struct zone *preferred_zone, struct page **page, bool *should_alloc_retry), + TP_ARGS(gfp_mask, order, alloc_flags, + migratetype, preferred_zone, page, should_alloc_retry)); +DECLARE_HOOK(android_vh_unreserve_highatomic_bypass, + TP_PROTO(bool force, struct zone *zone, bool *skip_unreserve_highatomic), + TP_ARGS(force, zone, skip_unreserve_highatomic)); +DECLARE_HOOK(android_vh_pageset_update, + TP_PROTO(unsigned long *high, unsigned long *batch), + TP_ARGS(high, batch)); +DECLARE_HOOK(android_vh_rmqueue_bulk_bypass, + TP_PROTO(unsigned int order, struct per_cpu_pages *pcp, int migratetype, + struct list_head *list), + TP_ARGS(order, pcp, migratetype, list)); DECLARE_HOOK(android_vh_pcplist_add_cma_pages_bypass, TP_PROTO(int migratetype, bool *bypass), TP_ARGS(migratetype, bypass)); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cd1c43bbf037..19eb65be0ea6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1608,11 +1608,16 @@ static void __free_pages_ok(struct page *page, unsigned int order, unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); + bool skip_free_unref_page = false; if (!free_pages_prepare(page, order, true, fpi_flags)) return; migratetype = get_pfnblock_migratetype(page, pfn); + trace_android_vh_free_unref_page_bypass(page, order, migratetype, &skip_free_unref_page); + if (skip_free_unref_page) + return; + local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, pfn, order, migratetype, @@ -2791,6 +2796,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, struct page *page; int order; bool ret; + bool skip_unreserve_highatomic = false; for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx, ac->nodemask) { @@ -2802,6 +2808,11 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, pageblock_nr_pages) continue; + trace_android_vh_unreserve_highatomic_bypass(force, zone, + &skip_unreserve_highatomic); + if (skip_unreserve_highatomic) + continue; + spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { struct free_area *area = &(zone->free_area[order]); @@ -3047,6 +3058,10 @@ static struct list_head *get_populated_pcp_list(struct zone *zone, struct list_head *list = &pcp->lists[migratetype]; if (list_empty(list)) { + trace_android_vh_rmqueue_bulk_bypass(order, pcp, migratetype, list); + if (!list_empty(list)) + return list; + pcp->count += rmqueue_bulk(zone, order, pcp->batch, list, migratetype, alloc_flags); @@ -3343,10 +3358,17 @@ void free_unref_page(struct page *page) { unsigned long flags; unsigned long pfn = page_to_pfn(page); + int migratetype; + bool skip_free_unref_page = false; if (!free_unref_page_prepare(page, pfn)) return; + migratetype = get_pfnblock_migratetype(page, pfn); + trace_android_vh_free_unref_page_bypass(page, 0, migratetype, &skip_free_unref_page); + if (skip_free_unref_page) + return; + local_irq_save(flags); free_unref_page_commit(page, pfn); local_irq_restore(flags); @@ -4822,6 +4844,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned int zonelist_iter_cookie; int reserve_flags; unsigned long vh_record; + bool should_alloc_retry = false; trace_android_vh_alloc_pages_slowpath_begin(gfp_mask, order, &vh_record); /* @@ -4962,6 +4985,12 @@ retry: if (page) goto got_pg; + trace_android_vh_should_alloc_pages_retry(gfp_mask, order, + &alloc_flags, ac->migratetype, ac->preferred_zoneref->zone, + &page, &should_alloc_retry); + if (should_alloc_retry) + goto retry; + /* Try direct reclaim and then allocating */ page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac, &did_some_progress); @@ -6604,6 +6633,7 @@ static int zone_batchsize(struct zone *zone) static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, unsigned long batch) { + trace_android_vh_pageset_update(&high, &batch); /* start with a fail safe value for batch */ pcp->batch = 1; smp_wmb(); diff --git a/mm/util.c b/mm/util.c index 9e2b223ebde3..6ed9861cb98c 100644 --- a/mm/util.c +++ b/mm/util.c @@ -29,6 +29,7 @@ #include "internal.h" #ifndef __GENKSYMS__ #include +#include #endif /** @@ -587,6 +588,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) { gfp_t kmalloc_flags = flags; void *ret; + bool use_vmalloc = false; /* * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables) @@ -595,6 +597,10 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) if ((flags & GFP_KERNEL) != GFP_KERNEL) return kmalloc_node(size, flags, node); + trace_android_vh_kvmalloc_node_use_vmalloc(size, &kmalloc_flags, &use_vmalloc); + if (use_vmalloc) + goto use_vmalloc_node; + /* * We want to attempt a large physically contiguous block first because * it is less likely to fragment multiple larger blocks and therefore @@ -624,6 +630,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) return NULL; } +use_vmalloc_node: return __vmalloc_node(size, 1, flags, node, __builtin_return_address(0)); } From 4782c8cb168f9119ff9fbdba2f01e9c10397f8c0 Mon Sep 17 00:00:00 2001 From: Oven Date: Fri, 16 Jun 2023 20:51:14 +0800 Subject: [PATCH 3705/4345] ANDROID: vendor_hook: Add hook to tune readaround size In some situations, we want to decrease readaround size for better performance. So we add this hook. Bug: 288216516 Change-Id: If2f5f75976c99ff1f82ce29d370f9216926055ab Signed-off-by: Oven --- drivers/android/vendor_hooks.c | 1 + include/trace/hooks/mm.h | 4 ++++ mm/filemap.c | 2 ++ 3 files changed, 7 insertions(+) diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index 0aa79f03f578..ae35b2a9ec8b 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -447,6 +447,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_binder_read_done); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_handle_tlb_conf); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_shrink_node_memcgs); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_ra_tuning_max_page); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_tune_mmap_readaround); EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_handle_pte_fault_end); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_handle_pte_fault_end); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_cow_user_page); diff --git a/include/trace/hooks/mm.h b/include/trace/hooks/mm.h index d041bd44edaf..7a1d74f646cb 100644 --- a/include/trace/hooks/mm.h +++ b/include/trace/hooks/mm.h @@ -222,6 +222,10 @@ DECLARE_HOOK(android_vh_subpage_dma_contig_alloc, DECLARE_HOOK(android_vh_ra_tuning_max_page, TP_PROTO(struct readahead_control *ractl, unsigned long *max_page), TP_ARGS(ractl, max_page)); +DECLARE_HOOK(android_vh_tune_mmap_readaround, + TP_PROTO(unsigned int ra_pages, pgoff_t pgoff, + pgoff_t *start, unsigned int *size, unsigned int *async_size), + TP_ARGS(ra_pages, pgoff, start, size, async_size)); DECLARE_RESTRICTED_HOOK(android_rvh_handle_pte_fault_end, TP_PROTO(struct vm_fault *vmf, unsigned long highest_memmap_pfn), TP_ARGS(vmf, highest_memmap_pfn), 1); diff --git a/mm/filemap.c b/mm/filemap.c index dd1db5745741..0450b4ef4b1a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2661,6 +2661,8 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; + trace_android_vh_tune_mmap_readaround(ra->ra_pages, vmf->pgoff, + &ra->start, &ra->size, &ra->async_size); ractl._index = ra->start; do_page_cache_ra(&ractl, ra->size, ra->async_size); return fpin; From 540586cf5b23c020ae90952c1b9b8ceab26545e1 Mon Sep 17 00:00:00 2001 From: Oven Date: Fri, 30 Jun 2023 00:33:10 +0800 Subject: [PATCH 3706/4345] ANDROID: GKI: Update symbols to symbol list Leaf changes summary: 14 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 7 Added functions Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 7 Added variables 7 Added functions: [A] 'function int __traceiter_android_vh_free_unref_page_bypass(void*, page*, int, int, bool*)' [A] 'function int __traceiter_android_vh_kvmalloc_node_use_vmalloc(void*, size_t, gfp_t*, bool*)' [A] 'function int __traceiter_android_vh_pageset_update(void*, unsigned long int*, unsigned long int*)' [A] 'function int __traceiter_android_vh_rmqueue_bulk_bypass(void*, unsigned int, per_cpu_pages*, int, list_head*)' [A] 'function int __traceiter_android_vh_should_alloc_pages_retry(void*, gfp_t, int, int*, int, zone*, page**, bool*)' [A] 'function int __traceiter_android_vh_tune_mmap_readaround(void*, unsigned int, unsigned long int, unsigned long int*, unsigned int*, unsigned int*)' [A] 'function int __traceiter_android_vh_unreserve_highatomic_bypass(void*, bool, zone*, bool*)' 7 Added variables: [A] 'tracepoint __tracepoint_android_vh_free_unref_page_bypass' [A] 'tracepoint __tracepoint_android_vh_kvmalloc_node_use_vmalloc' [A] 'tracepoint __tracepoint_android_vh_pageset_update' [A] 'tracepoint __tracepoint_android_vh_rmqueue_bulk_bypass' [A] 'tracepoint __tracepoint_android_vh_should_alloc_pages_retry' [A] 'tracepoint __tracepoint_android_vh_tune_mmap_readaround' [A] 'tracepoint __tracepoint_android_vh_unreserve_highatomic_bypass' Bug: 288216516 Change-Id: Id93d9871ea9fc292916e2b75b95b017ccb6e2011 Signed-off-by: Oven --- android/abi_gki_aarch64.xml | 847 ++++++++++++++++++---------------- android/abi_gki_aarch64_oplus | 18 + 2 files changed, 461 insertions(+), 404 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 0bab4531f386..7656ab64512c 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -509,6 +509,7 @@ + @@ -547,6 +548,7 @@ + @@ -587,6 +589,7 @@ + @@ -602,6 +605,7 @@ + @@ -648,6 +652,7 @@ + @@ -674,6 +679,7 @@ + @@ -691,6 +697,7 @@ + @@ -6569,6 +6576,7 @@ + @@ -6607,6 +6615,7 @@ + @@ -6647,6 +6656,7 @@ + @@ -6662,6 +6672,7 @@ + @@ -6708,6 +6719,7 @@ + @@ -6734,6 +6746,7 @@ + @@ -6751,6 +6764,7 @@ + @@ -12159,6 +12173,7 @@ + @@ -44630,23 +44645,7 @@ - - - - - - - - - - - - - - - - - + @@ -48986,7 +48985,6 @@ - @@ -53944,13 +53942,6 @@ - - - - - - - @@ -66611,13 +66602,6 @@ - - - - - - - @@ -91409,7 +91393,6 @@ - @@ -103177,12 +103160,6 @@ - - - - - - @@ -111429,7 +111406,6 @@ - @@ -116503,9 +116479,9 @@ - + - + @@ -116534,11 +116510,11 @@ - - - - - + + + + + @@ -117174,9 +117150,9 @@ - - - + + + @@ -117219,9 +117195,9 @@ - - - + + + @@ -117229,9 +117205,9 @@ - - - + + + @@ -117747,13 +117723,13 @@ - - - + + + - - + + @@ -118262,17 +118238,17 @@ - - - - + + + + - - - - - + + + + + @@ -118453,12 +118429,12 @@ - - - - - - + + + + + + @@ -118539,19 +118515,19 @@ - - - - - + + + + + - - - - - - + + + + + + @@ -118563,10 +118539,10 @@ - - - - + + + + @@ -118979,10 +118955,10 @@ - - - - + + + + @@ -119023,22 +118999,22 @@ - - - - - - - + + + + + + + - - - - - - - + + + + + + + @@ -119055,17 +119031,17 @@ - - - - + + + + - - - - - + + + + + @@ -119365,27 +119341,27 @@ - - - + + + - - - + + + - - - - - + + + + + - - - - + + + + @@ -119507,12 +119483,12 @@ - - - - - - + + + + + + @@ -119593,17 +119569,17 @@ - - - - + + + + - - - - - + + + + + @@ -119611,6 +119587,14 @@ + + + + + + + + @@ -119711,12 +119695,12 @@ - - - - - - + + + + + + @@ -119735,10 +119719,10 @@ - - - - + + + + @@ -119763,10 +119747,10 @@ - - - - + + + + @@ -119853,6 +119837,13 @@ + + + + + + + @@ -119865,24 +119856,24 @@ - - - - - - + + + + + + - - - - + + + + - - - - + + + + @@ -119939,10 +119930,10 @@ - - - - + + + + @@ -120049,10 +120040,10 @@ - - - - + + + + @@ -120063,11 +120054,11 @@ - - - - - + + + + + @@ -120101,10 +120092,16 @@ - - - - + + + + + + + + + + @@ -120140,10 +120137,10 @@ - - - - + + + + @@ -120170,9 +120167,9 @@ - - - + + + @@ -120191,6 +120188,14 @@ + + + + + + + + @@ -120420,9 +120425,9 @@ - - - + + + @@ -120451,6 +120456,17 @@ + + + + + + + + + + + @@ -120500,10 +120516,10 @@ - - - - + + + + @@ -120529,22 +120545,22 @@ - - - - - + + + + + - - - + + + - - - - + + + + @@ -120559,9 +120575,9 @@ - - - + + + @@ -120608,6 +120624,15 @@ + + + + + + + + + @@ -120721,10 +120746,17 @@ - - - - + + + + + + + + + + + @@ -120784,9 +120816,9 @@ - - - + + + @@ -121226,8 +121258,8 @@ - - + + @@ -121254,7 +121286,7 @@ - + @@ -121267,10 +121299,10 @@ - - + + - + @@ -121336,18 +121368,18 @@ - + - - + + - - + + @@ -121392,10 +121424,10 @@ - - - - + + + + @@ -121414,7 +121446,7 @@ - + @@ -121427,9 +121459,10 @@ - - + + + @@ -121446,15 +121479,15 @@ - + - + - + @@ -121468,11 +121501,12 @@ + - - - + + + @@ -121482,7 +121516,7 @@ - + @@ -121500,29 +121534,31 @@ - + - + - + + - + - + + @@ -121564,11 +121600,12 @@ - + + @@ -121577,17 +121614,17 @@ - + - - - + + + - + @@ -121595,6 +121632,7 @@ + @@ -121612,7 +121650,8 @@ - + + @@ -121621,7 +121660,7 @@ - + @@ -122234,9 +122273,9 @@ - - - + + + @@ -122360,9 +122399,9 @@ - - - + + + @@ -122444,7 +122483,7 @@ - + @@ -131366,15 +131405,15 @@ - + - - + + @@ -131391,10 +131430,10 @@ - - - - + + + + @@ -131619,14 +131658,14 @@ - - - + + + - - - + + + @@ -132199,9 +132238,9 @@ - - - + + + @@ -132218,9 +132257,9 @@ - - - + + + @@ -132262,10 +132301,10 @@ - - - - + + + + @@ -132574,8 +132613,8 @@ - - + + @@ -132855,10 +132894,10 @@ - - - - + + + + @@ -135196,8 +135235,8 @@ - - + + @@ -135296,16 +135335,16 @@ - - - - + + + + - - - - + + + + @@ -135431,14 +135470,14 @@ - - - + + + - - - + + + @@ -135446,10 +135485,10 @@ - - - - + + + + @@ -135733,8 +135772,8 @@ - - + + @@ -135742,10 +135781,10 @@ - - - - + + + + @@ -136247,14 +136286,14 @@ - - - + + + - - - + + + @@ -138446,14 +138485,14 @@ - - - - + + + + - - + + @@ -138462,12 +138501,12 @@ - - + + - - + + @@ -138532,24 +138571,24 @@ - - - - - - - - + + + + + + + + - - - - - - - - + + + + + + + + @@ -141089,17 +141128,17 @@ - - - - - + + + + + - - - - + + + + @@ -143618,11 +143657,11 @@ - + - - + + @@ -145414,9 +145453,9 @@ - - - + + + @@ -145699,9 +145738,9 @@ - - - + + + @@ -146589,9 +146628,9 @@ - - - + + + @@ -149929,16 +149968,16 @@ - + - - - - - - - + + + + + + + @@ -149986,9 +150025,9 @@ - - - + + + @@ -150635,19 +150674,19 @@ - - - - - - + + + + + + - - - - - + + + + + diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index 61477d74b5cb..20d15056b373 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -2794,6 +2794,15 @@ __traceiter_android_vh_clear_mask_adjust __traceiter_android_vh_clear_reserved_fmt_fields __traceiter_android_vh_cma_drain_all_pages_bypass + __traceiter_android_vh_alloc_pages_reclaim_bypass + __traceiter_android_vh_free_unref_page_bypass + __traceiter_android_vh_kvmalloc_node_use_vmalloc + __traceiter_android_vh_should_alloc_pages_retry + __traceiter_android_vh_unreserve_highatomic_bypass + __traceiter_android_vh_pageset_update + __traceiter_android_vh_rmqueue_bulk_bypass + __traceiter_android_vh_tune_mmap_readaround + __traceiter_android_vh_ra_tuning_max_page __traceiter_android_vh_cleanup_old_buffers_bypass __traceiter_android_vh_commit_creds __traceiter_android_vh_cpufreq_acct_update_power @@ -3050,6 +3059,15 @@ __tracepoint_android_vh_clear_mask_adjust __tracepoint_android_vh_clear_reserved_fmt_fields __tracepoint_android_vh_cma_drain_all_pages_bypass + __tracepoint_android_vh_alloc_pages_reclaim_bypass + __tracepoint_android_vh_free_unref_page_bypass + __tracepoint_android_vh_kvmalloc_node_use_vmalloc + __tracepoint_android_vh_should_alloc_pages_retry + __tracepoint_android_vh_unreserve_highatomic_bypass + __tracepoint_android_vh_pageset_update + __tracepoint_android_vh_rmqueue_bulk_bypass + __tracepoint_android_vh_tune_mmap_readaround + __tracepoint_android_vh_ra_tuning_max_page __tracepoint_android_vh_cleanup_old_buffers_bypass __tracepoint_android_vh_commit_creds __tracepoint_android_vh_cpufreq_acct_update_power From c4f52f22c7e5366ecd27ac5d495f1ba1a90e3df9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 30 Jun 2023 12:26:17 +0000 Subject: [PATCH 3707/4345] Revert "net: Remove DECnet leftovers from flow.h." This reverts commit bf82668eb950e3ca977b5f92bcb1a756db5563dc which is commit 9bc61c04ff6cce6a3756b86e6b34914f7b39d734 upstream. It is removing unused code, but that changes a structure size so revert it for now to preserve the ABI. Bug: 161946584 Change-Id: I237cda2e5c07440d25613a1a1e30fa499751c7ac Signed-off-by: Greg Kroah-Hartman --- include/net/flow.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/include/net/flow.h b/include/net/flow.h index 236d0941c69f..39d0cedcddee 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -54,6 +54,11 @@ union flowi_uli { __u8 code; } icmpt; + struct { + __le16 dport; + __le16 sport; + } dnports; + __be32 spi; __be32 gre_key; @@ -151,11 +156,27 @@ struct flowi6 { __u32 mp_hash; } __attribute__((__aligned__(BITS_PER_LONG/8))); +struct flowidn { + struct flowi_common __fl_common; +#define flowidn_oif __fl_common.flowic_oif +#define flowidn_iif __fl_common.flowic_iif +#define flowidn_mark __fl_common.flowic_mark +#define flowidn_scope __fl_common.flowic_scope +#define flowidn_proto __fl_common.flowic_proto +#define flowidn_flags __fl_common.flowic_flags + __le16 daddr; + __le16 saddr; + union flowi_uli uli; +#define fld_sport uli.ports.sport +#define fld_dport uli.ports.dport +} __attribute__((__aligned__(BITS_PER_LONG/8))); + struct flowi { union { struct flowi_common __fl_common; struct flowi4 ip4; struct flowi6 ip6; + struct flowidn dn; } u; #define flowi_oif u.__fl_common.flowic_oif #define flowi_iif u.__fl_common.flowic_iif @@ -189,6 +210,11 @@ static inline struct flowi_common *flowi6_to_flowi_common(struct flowi6 *fl6) return &(flowi6_to_flowi(fl6)->u.__fl_common); } +static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn) +{ + return container_of(fldn, struct flowi, u.dn); +} + __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys); #endif From c811ac11f792c50d5a636ca5fd9b60155befd555 Mon Sep 17 00:00:00 2001 From: "t.feng" Date: Wed, 10 May 2023 11:50:44 +0800 Subject: [PATCH 3708/4345] UPSTREAM: ipvlan:Fix out-of-bounds caused by unclear skb->cb [ Upstream commit 90cbed5247439a966b645b34eb0a2e037836ea8e ] If skb enqueue the qdisc, fq_skb_cb(skb)->time_to_send is changed which is actually skb->cb, and IPCB(skb_in)->opt will be used in __ip_options_echo. It is possible that memcpy is out of bounds and lead to stack overflow. We should clear skb->cb before ip_local_out or ip6_local_out. v2: 1. clean the stack info 2. use IPCB/IP6CB instead of skb->cb crash on stable-5.10(reproduce in kasan kernel). Stack info: [ 2203.651571] BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0x589/0x800 [ 2203.653327] Write of size 4 at addr ffff88811a388f27 by task swapper/3/0 [ 2203.655460] CPU: 3 PID: 0 Comm: swapper/3 Kdump: loaded Not tainted 5.10.0-60.18.0.50.h856.kasan.eulerosv2r11.x86_64 #1 [ 2203.655466] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-20181220_000000-szxrtosci10000 04/01/2014 [ 2203.655475] Call Trace: [ 2203.655481] [ 2203.655501] dump_stack+0x9c/0xd3 [ 2203.655514] print_address_description.constprop.0+0x19/0x170 [ 2203.655530] __kasan_report.cold+0x6c/0x84 [ 2203.655586] kasan_report+0x3a/0x50 [ 2203.655594] check_memory_region+0xfd/0x1f0 [ 2203.655601] memcpy+0x39/0x60 [ 2203.655608] __ip_options_echo+0x589/0x800 [ 2203.655654] __icmp_send+0x59a/0x960 [ 2203.655755] nf_send_unreach+0x129/0x3d0 [nf_reject_ipv4] [ 2203.655763] reject_tg+0x77/0x1bf [ipt_REJECT] [ 2203.655772] ipt_do_table+0x691/0xa40 [ip_tables] [ 2203.655821] nf_hook_slow+0x69/0x100 [ 2203.655828] __ip_local_out+0x21e/0x2b0 [ 2203.655857] ip_local_out+0x28/0x90 [ 2203.655868] ipvlan_process_v4_outbound+0x21e/0x260 [ipvlan] [ 2203.655931] ipvlan_xmit_mode_l3+0x3bd/0x400 [ipvlan] [ 2203.655967] ipvlan_queue_xmit+0xb3/0x190 [ipvlan] [ 2203.655977] ipvlan_start_xmit+0x2e/0xb0 [ipvlan] [ 2203.655984] xmit_one.constprop.0+0xe1/0x280 [ 2203.655992] dev_hard_start_xmit+0x62/0x100 [ 2203.656000] sch_direct_xmit+0x215/0x640 [ 2203.656028] __qdisc_run+0x153/0x1f0 [ 2203.656069] __dev_queue_xmit+0x77f/0x1030 [ 2203.656173] ip_finish_output2+0x59b/0xc20 [ 2203.656244] __ip_finish_output.part.0+0x318/0x3d0 [ 2203.656312] ip_finish_output+0x168/0x190 [ 2203.656320] ip_output+0x12d/0x220 [ 2203.656357] __ip_queue_xmit+0x392/0x880 [ 2203.656380] __tcp_transmit_skb+0x1088/0x11c0 [ 2203.656436] __tcp_retransmit_skb+0x475/0xa30 [ 2203.656505] tcp_retransmit_skb+0x2d/0x190 [ 2203.656512] tcp_retransmit_timer+0x3af/0x9a0 [ 2203.656519] tcp_write_timer_handler+0x3ba/0x510 [ 2203.656529] tcp_write_timer+0x55/0x180 [ 2203.656542] call_timer_fn+0x3f/0x1d0 [ 2203.656555] expire_timers+0x160/0x200 [ 2203.656562] run_timer_softirq+0x1f4/0x480 [ 2203.656606] __do_softirq+0xfd/0x402 [ 2203.656613] asm_call_irq_on_stack+0x12/0x20 [ 2203.656617] [ 2203.656623] do_softirq_own_stack+0x37/0x50 [ 2203.656631] irq_exit_rcu+0x134/0x1a0 [ 2203.656639] sysvec_apic_timer_interrupt+0x36/0x80 [ 2203.656646] asm_sysvec_apic_timer_interrupt+0x12/0x20 [ 2203.656654] RIP: 0010:default_idle+0x13/0x20 [ 2203.656663] Code: 89 f0 5d 41 5c 41 5d 41 5e c3 cc cc cc cc cc cc cc cc cc cc cc cc cc 0f 1f 44 00 00 0f 1f 44 00 00 0f 00 2d 9f 32 57 00 fb f4 cc cc cc cc 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 41 54 be 08 [ 2203.656668] RSP: 0018:ffff88810036fe78 EFLAGS: 00000256 [ 2203.656676] RAX: ffffffffaf2a87f0 RBX: ffff888100360000 RCX: ffffffffaf290191 [ 2203.656681] RDX: 0000000000098b5e RSI: 0000000000000004 RDI: ffff88811a3c4f60 [ 2203.656686] RBP: 0000000000000000 R08: 0000000000000001 R09: ffff88811a3c4f63 [ 2203.656690] R10: ffffed10234789ec R11: 0000000000000001 R12: 0000000000000003 [ 2203.656695] R13: ffff888100360000 R14: 0000000000000000 R15: 0000000000000000 [ 2203.656729] default_idle_call+0x5a/0x150 [ 2203.656735] cpuidle_idle_call+0x1c6/0x220 [ 2203.656780] do_idle+0xab/0x100 [ 2203.656786] cpu_startup_entry+0x19/0x20 [ 2203.656793] secondary_startup_64_no_verify+0xc2/0xcb [ 2203.657409] The buggy address belongs to the page: [ 2203.658648] page:0000000027a9842f refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x11a388 [ 2203.658665] flags: 0x17ffffc0001000(reserved|node=0|zone=2|lastcpupid=0x1fffff) [ 2203.658675] raw: 0017ffffc0001000 ffffea000468e208 ffffea000468e208 0000000000000000 [ 2203.658682] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 [ 2203.658686] page dumped because: kasan: bad access detected To reproduce(ipvlan with IPVLAN_MODE_L3): Env setting: ======================================================= modprobe ipvlan ipvlan_default_mode=1 sysctl net.ipv4.conf.eth0.forwarding=1 iptables -t nat -A POSTROUTING -s 20.0.0.0/255.255.255.0 -o eth0 -j MASQUERADE ip link add gw link eth0 type ipvlan ip -4 addr add 20.0.0.254/24 dev gw ip netns add net1 ip link add ipv1 link eth0 type ipvlan ip link set ipv1 netns net1 ip netns exec net1 ip link set ipv1 up ip netns exec net1 ip -4 addr add 20.0.0.4/24 dev ipv1 ip netns exec net1 route add default gw 20.0.0.254 ip netns exec net1 tc qdisc add dev ipv1 root netem loss 10% ifconfig gw up iptables -t filter -A OUTPUT -p tcp --dport 8888 -j REJECT --reject-with icmp-port-unreachable ======================================================= And then excute the shell(curl any address of eth0 can reach): for((i=1;i<=100000;i++)) do ip netns exec net1 curl x.x.x.x:8888 done ======================================================= Bug: 289225588 Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.") Signed-off-by: "t.feng" Suggested-by: Florian Westphal Reviewed-by: Paolo Abeni Signed-off-by: David S. Miller Signed-off-by: Sasha Levin (cherry picked from commit 610a433810b277b3b77389733c07d22e8af68de2) Signed-off-by: Lee Jones Change-Id: I08a12f6e3b1614210867cd23e9071918dc380faf --- drivers/net/ipvlan/ipvlan_core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index a33149ee0ddc..0a5b5ff597c6 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -437,6 +437,9 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) goto err; } skb_dst_set(skb, &rt->dst); + + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + err = ip_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; @@ -475,6 +478,9 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) goto err; } skb_dst_set(skb, dst); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + err = ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; From 6a975c2771cc214e71ae25e3ba392a5836bd3a9f Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Wed, 31 May 2023 18:28:04 +0800 Subject: [PATCH 3709/4345] UPSTREAM: net/sched: flower: fix possible OOB write in fl_set_geneve_opt() [ Upstream commit 4d56304e5827c8cc8cc18c75343d283af7c4825c ] If we send two TCA_FLOWER_KEY_ENC_OPTS_GENEVE packets and their total size is 252 bytes(key->enc_opts.len = 252) then key->enc_opts.len = opt->length = data_len / 4 = 0 when the third TCA_FLOWER_KEY_ENC_OPTS_GENEVE packet enters fl_set_geneve_opt. This bypasses the next bounds check and results in an out-of-bounds. Bug: 288660424 Fixes: 0a6e77784f49 ("net/sched: allow flower to match tunnel options") Signed-off-by: Hangyu Hua Reviewed-by: Simon Horman Reviewed-by: Pieter Jansen van Vuuren Link: https://lore.kernel.org/r/20230531102805.27090-1-hbh25y@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin (cherry picked from commit 45f47d2cf1142fbfe5d6fc39ad78f4aac058907c) Signed-off-by: Lee Jones Change-Id: I53c534b7d43f4c7da5a9f63556c79d35797aa598 --- net/sched/cls_flower.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 35ee6d8226e6..caf1a05bfbde 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1086,6 +1086,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, if (option_len > sizeof(struct geneve_opt)) data_len = option_len - sizeof(struct geneve_opt); + if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4) + return -ERANGE; + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; memset(opt, 0xff, option_len); opt->length = data_len / 4; From be9bc79296726ed38eee93f314419fe1bf1c0411 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 16 Jun 2023 21:12:06 -0600 Subject: [PATCH 3710/4345] UPSTREAM: io_uring: hold uring mutex around poll removal Snipped from commit 9ca9fb24d5febccea354089c41f96a8ad0d853f8 upstream. While reworking the poll hashing in the v6.0 kernel, we ended up grabbing the ctx->uring_lock in poll update/removal. This also fixed a bug with linked timeouts racing with timeout expiry and poll removal. Bring back just the locking fix for that. Bug: 289229683 Reported-and-tested-by: Querijn Voet Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 0e388fce7aec40992eadee654193cad345d62663) Signed-off-by: Lee Jones Change-Id: Ife3683f26b19af1887ae1c59d3bd8b4e1700c79a --- io_uring/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 5325e915a5d7..419a64990906 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -5976,6 +5976,8 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) struct io_kiocb *preq; int ret2, ret = 0; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + spin_lock(&ctx->completion_lock); preq = io_poll_find(ctx, req->poll_update.old_user_data, true); if (!preq || !io_poll_disarm(preq)) { @@ -6007,6 +6009,7 @@ out: req_set_fail(req); /* complete update request, we're done with it */ io_req_complete(req, ret); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return 0; } From 5db82d830f2bc40da8fe3e0948a0d1e4b62a637c Mon Sep 17 00:00:00 2001 From: Zhang Zhengming Date: Wed, 19 Apr 2023 12:02:03 +0800 Subject: [PATCH 3711/4345] UPSTREAM: relayfs: fix out-of-bounds access in relay_file_read commit 43ec16f1450f4936025a9bdf1a273affdb9732c1 upstream. There is a crash in relay_file_read, as the var from point to the end of last subbuf. The oops looks something like: pc : __arch_copy_to_user+0x180/0x310 lr : relay_file_read+0x20c/0x2c8 Call trace: __arch_copy_to_user+0x180/0x310 full_proxy_read+0x68/0x98 vfs_read+0xb0/0x1d0 ksys_read+0x6c/0xf0 __arm64_sys_read+0x20/0x28 el0_svc_common.constprop.3+0x84/0x108 do_el0_svc+0x74/0x90 el0_svc+0x1c/0x28 el0_sync_handler+0x88/0xb0 el0_sync+0x148/0x180 We get the condition by analyzing the vmcore: 1). The last produced byte and last consumed byte both at the end of the last subbuf 2). A softirq calls function(e.g __blk_add_trace) to write relay buffer occurs when an program is calling relay_file_read_avail(). relay_file_read relay_file_read_avail relay_file_read_consume(buf, 0, 0); //interrupted by softirq who will write subbuf .... return 1; //read_start point to the end of the last subbuf read_start = relay_file_read_start_pos //avail is equal to subsize avail = relay_file_read_subbuf_avail //from points to an invalid memory address from = buf->start + read_start //system is crashed copy_to_user(buffer, from, avail) Bug: 288957094 Link: https://lkml.kernel.org/r/20230419040203.37676-1-zhang.zhengming@h3c.com Fixes: 8d62fdebdaf9 ("relay file read: start-pos fix") Signed-off-by: Zhang Zhengming Reviewed-by: Zhao Lei Reviewed-by: Zhou Kete Reviewed-by: Pengcheng Yang Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman (cherry picked from commit f6ee841ff2169d7a7d045340ee72b2b9de9f06c5) Signed-off-by: Lee Jones Change-Id: Ibbdf65d8bf2268c3e8c09520f595167a2ed41e8b --- kernel/relay.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/relay.c b/kernel/relay.c index 067769b80d4a..f6826dec2103 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1077,7 +1077,8 @@ static size_t relay_file_read_start_pos(struct rchan_buf *buf) size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t consumed = buf->subbufs_consumed % n_subbufs; - size_t read_pos = consumed * subbuf_size + buf->bytes_consumed; + size_t read_pos = (consumed * subbuf_size + buf->bytes_consumed) + % (n_subbufs * subbuf_size); read_subbuf = read_pos / subbuf_size; padding = buf->padding[read_subbuf]; From 739f5722f44709628f2a8d9627a135779d679e77 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 14 Jun 2023 17:38:54 +0100 Subject: [PATCH 3712/4345] UPSTREAM: x86/mm: Avoid using set_pgd() outside of real PGD pages commit d082d48737c75d2b3cc1f972b8c8674c25131534 upstream. KPTI keeps around two PGDs: one for userspace and another for the kernel. Among other things, set_pgd() contains infrastructure to ensure that updates to the kernel PGD are reflected in the user PGD as well. One side-effect of this is that set_pgd() expects to be passed whole pages. Unfortunately, init_trampoline_kaslr() passes in a single entry: 'trampoline_pgd_entry'. When KPTI is on, set_pgd() will update 'trampoline_pgd_entry' (an 8-Byte globally stored [.bss] variable) and will then proceed to replicate that value into the non-existent neighboring user page (located +4k away), leading to the corruption of other global [.bss] stored variables. Fix it by directly assigning 'trampoline_pgd_entry' and avoiding set_pgd(). [ dhansen: tweak subject and changelog ] Bug: 274115504 Fixes: 0925dda5962e ("x86/mm/KASLR: Use only one PUD entry for real mode trampoline") Suggested-by: Dave Hansen Signed-off-by: Lee Jones Signed-off-by: Dave Hansen Cc: Link: https://lore.kernel.org/all/20230614163859.924309-1-lee@kernel.org/g Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 364fdcbb035bb910e58a2814708de72481256466) Signed-off-by: Lee Jones Change-Id: Idc1fc494d7ccb4a8a3765e1f46482583b528a584 --- arch/x86/mm/kaslr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 6e6b39710e5f..a8cdbbe67bb5 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -172,10 +172,10 @@ void __meminit init_trampoline_kaslr(void) set_p4d(p4d_tramp, __p4d(_KERNPG_TABLE | __pa(pud_page_tramp))); - set_pgd(&trampoline_pgd_entry, - __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp))); + trampoline_pgd_entry = + __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)); } else { - set_pgd(&trampoline_pgd_entry, - __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); + trampoline_pgd_entry = + __pgd(_KERNPG_TABLE | __pa(pud_page_tramp)); } } From 158d8bfffcd3c398e76eee11f5a68de8eaffcee7 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Mon, 13 Mar 2023 16:42:20 +0000 Subject: [PATCH 3713/4345] UPSTREAM: media: rkvdec: fix use after free bug in rkvdec_remove [ Upstream commit 3228cec23b8b29215e18090c6ba635840190993d ] In rkvdec_probe, rkvdec->watchdog_work is bound with rkvdec_watchdog_func. Then rkvdec_vp9_run may be called to start the work. If we remove the module which will call rkvdec_remove to make cleanup, there may be a unfinished work. The possible sequence is as follows, which will cause a typical UAF bug. Fix it by canceling the work before cleanup in rkvdec_remove. CPU0 CPU1 |rkvdec_watchdog_func rkvdec_remove | rkvdec_v4l2_cleanup| v4l2_m2m_release | kfree(m2m_dev); | | | v4l2_m2m_get_curr_priv | m2m_dev->curr_ctx //use Bug: 289003637 Fixes: cd33c830448b ("media: rkvdec: Add the rkvdec driver") Signed-off-by: Zheng Wang Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin (cherry picked from commit 6a17add9c61030683b9c1fc86878f00a2d318a95) Signed-off-by: Lee Jones Change-Id: Ibdf4667315d98ac1cd42545f61e271c291893edd --- drivers/staging/media/rkvdec/rkvdec.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c index e384ea8d7280..f6a29a707862 100644 --- a/drivers/staging/media/rkvdec/rkvdec.c +++ b/drivers/staging/media/rkvdec/rkvdec.c @@ -1077,6 +1077,8 @@ static int rkvdec_remove(struct platform_device *pdev) { struct rkvdec_dev *rkvdec = platform_get_drvdata(pdev); + cancel_delayed_work_sync(&rkvdec->watchdog_work); + rkvdec_v4l2_cleanup(rkvdec); pm_runtime_disable(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); From 505b4a192915e388bb2f1659672bca58af6086e3 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Mon, 20 Mar 2023 14:29:31 +0800 Subject: [PATCH 3714/4345] UPSTREAM: usb: gadget: udc: renesas_usb3: Fix use after free bug in renesas_usb3_remove due to race condition [ Upstream commit 2b947f8769be8b8181dc795fd292d3e7120f5204 ] In renesas_usb3_probe, role_work is bound with renesas_usb3_role_work. renesas_usb3_start will be called to start the work. If we remove the driver which will call usbhs_remove, there may be an unfinished work. The possible sequence is as follows: CPU0 CPU1 renesas_usb3_role_work renesas_usb3_remove usb_role_switch_unregister device_unregister kfree(sw) //free usb3->role_sw usb_role_switch_set_role //use usb3->role_sw The usb3->role_sw could be freed under such circumstance and then used in usb_role_switch_set_role. This bug was found by static analysis. And note that removing a driver is a root-only operation, and should never happen in normal case. But the root user may directly remove the device which will also trigger the remove function. Fix it by canceling the work before cleanup in the renesas_usb3_remove. Bug: 289003615 Fixes: 39facfa01c9f ("usb: gadget: udc: renesas_usb3: Add register of usb role switch") Signed-off-by: Zheng Wang Reviewed-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20230320062931.505170-1-zyytlz.wz@163.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin (cherry picked from commit df2380520926bdbc264cffab0f45da9a21f304c8) Signed-off-by: Lee Jones Change-Id: I79a1dbeba9a90ee5daf94648ef6a32207b283561 --- drivers/usb/gadget/udc/renesas_usb3.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 601829a6b4ba..a10f41c4a3f2 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -2568,6 +2568,7 @@ static int renesas_usb3_remove(struct platform_device *pdev) debugfs_remove_recursive(usb3->dentry); device_remove_file(&pdev->dev, &dev_attr_role); + cancel_work_sync(&usb3->role_work); usb_role_switch_unregister(usb3->role_sw); usb_del_gadget_udc(&usb3->gadget); From fc3985cbeebaefa13bd2757657a76e6ca2b14e96 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 30 Jun 2023 12:44:42 +0000 Subject: [PATCH 3715/4345] Revert "gpiolib: Fix GPIO chip IRQ initialization restriction" This reverts commit 75aa3f255c884c458ff4f3e6d4608debafa96a8c which is commit 8c00914e5438e3636f26b4f814b3297ae2a1b9ee upstream. It breaks the Android api, so revert it for now. If it needs to come back, it can do so in an abi-safe way. Bug: 161946584 Change-Id: Ic6c0f3eda15a05d292fa047430a900682505fa64 Signed-off-by: Greg Kroah-Hartman --- drivers/gpio/gpiolib.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index b8dfde86ae67..4dd37457948c 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1793,14 +1793,6 @@ int gpiochip_irqchip_add_domain(struct gpio_chip *gc, gc->to_irq = gpiochip_to_irq; gc->irq.domain = domain; - /* - * Using barrier() here to prevent compiler from reordering - * gc->irq.initialized before adding irqdomain. - */ - barrier(); - - gc->irq.initialized = true; - return 0; } EXPORT_SYMBOL_GPL(gpiochip_irqchip_add_domain); From c9606079a5cc589fb90fa7e8f4be142f0ccc847b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 30 Jun 2023 12:44:51 +0000 Subject: [PATCH 3716/4345] Revert "gpio: Allow per-parent interrupt data" This reverts commit 304802e5b038e9e33e1b7fe5f933864e7a8e0ec1 which is commit cfe6807d82e97e81c3209dca9448f091e1448a57 upstream. It breaks the Android api, so revert it for now. If it needs to come back, it can do so in an abi-safe way. Bug: 161946584 Change-Id: I0f1f7b4de721ff23d252eef9b55678c3b6053cb7 Signed-off-by: Greg Kroah-Hartman --- drivers/gpio/gpiolib.c | 9 ++------- include/linux/gpio/driver.h | 19 ++----------------- 2 files changed, 4 insertions(+), 24 deletions(-) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 4dd37457948c..e885218fb0c6 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1596,14 +1596,9 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, } if (gc->irq.parent_handler) { + void *data = gc->irq.parent_handler_data ?: gc; + for (i = 0; i < gc->irq.num_parents; i++) { - void *data; - - if (gc->irq.per_parent_data) - data = gc->irq.parent_handler_data_array[i]; - else - data = gc->irq.parent_handler_data ?: gc; - /* * The parent IRQ chip is already using the chip_data * for this IRQ chip, so our callbacks simply use the diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 6f573ca2a98f..c5585bcf53a5 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -169,18 +169,11 @@ struct gpio_irq_chip { /** * @parent_handler_data: - * @parent_handler_data_array: * * Data associated, and passed to, the handler for the parent - * interrupt. Can either be a single pointer if @per_parent_data - * is false, or an array of @num_parents pointers otherwise. If - * @per_parent_data is true, @parent_handler_data_array cannot be - * NULL. + * interrupt. */ - union { - void *parent_handler_data; - void **parent_handler_data_array; - }; + void *parent_handler_data; /** * @num_parents: @@ -211,14 +204,6 @@ struct gpio_irq_chip { */ bool threaded; - /** - * @per_parent_data: - * - * True if parent_handler_data_array describes a @num_parents - * sized array to be used as parent data. - */ - bool per_parent_data; - /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when From b52f2d4395e57b469ffcf6dd4ccea2ebe134a469 Mon Sep 17 00:00:00 2001 From: Krishna Kurapati Date: Sun, 18 Jun 2023 17:39:49 +0530 Subject: [PATCH 3717/4345] UPSTREAM: usb: dwc3: gadget: Propagate core init errors to UDC during pullup In scenarios where pullup relies on resume (get sync) to initialize the controller and set the run stop bit, then core_init is followed by gadget_resume which will eventually set run stop bit. But in cases where the core_init fails, the return value is not sent back to udc appropriately. So according to UDC the controller has started but in reality we never set the run stop bit. On systems like Android, there are uevents sent to HAL depending on whether the configfs_bind / configfs_disconnect were invoked. In the above mentioned scnenario, if the core init fails, the run stop won't be set and the cable plug-out won't result in generation of any disconnect event and userspace would never get any uevent regarding cable plug out and we never call pullup(0) again. Furthermore none of the next Plug-In/Plug-Out's would be known to configfs. Return back the appropriate result to UDC to let the userspace/ configfs know that the pullup failed so they can take appropriate action. Fixes: 77adb8bdf422 ("usb: dwc3: gadget: Allow runtime suspend if UDC unbinded") Cc: stable Change-Id: Ieb281722cdc4fa2ff15545d9edaabdc8c2d70223 Signed-off-by: Krishna Kurapati Acked-by: Thinh Nguyen Message-ID: <20230618120949.14868-1-quic_kriskura@quicinc.com> Signed-off-by: Greg Kroah-Hartman (cherry picked from commit c0aabed9cabe057309779a9e26fe86a113d24dad https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master) Bug: 289984280 Change-Id: I633b2c325dd954a3e4cdd636052158a90fd976a3 Signed-off-by: Krishna Kurapati --- drivers/usb/dwc3/gadget.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 35fd2c4fa82f..73e869ac1066 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2585,7 +2585,9 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) ret = pm_runtime_get_sync(dwc->dev); if (!ret || ret < 0) { pm_runtime_put(dwc->dev); - return 0; + if (ret < 0) + pm_runtime_set_suspended(dwc->dev); + return ret; } if (dwc->pullups_connected == is_on) { From 44da38b39ca6c0575815fd2deb005822425ad9c1 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 10 Jul 2023 16:20:23 +0000 Subject: [PATCH 3718/4345] ANDROID: GKI: fix up sysctl_vals ABI change. In commit 1ac6e9ee8428 ("sysctl: move some boundary constants from sysctl.c to sysctl_vals"), the sysctl_vals variable got changed, but unfortunatly many Android vendors liked using that array. To preserve the ABI, put the array back the way it was and rename the new change to be `android_gki_sysctl_vals` instead, and move the #defines to use it. This way if any external code is rebuilt, it will use the new symbols, but if not, the old ones will still work just as before, not requiring a rebuild at all. Bug: 161946584 Fixes: 1ac6e9ee8428 ("sysctl: move some boundary constants from sysctl.c to sysctl_vals") Change-Id: Ib094ae03682e11fee4f0b06af362541bbcba24d5 Signed-off-by: Greg Kroah-Hartman --- fs/proc/proc_sysctl.c | 4 +++- include/linux/sysctl.h | 21 +++++++++++---------- 2 files changed, 14 insertions(+), 11 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 682f2bf2e525..c64f0ddfc982 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -26,8 +26,10 @@ static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; /* shared constants to be used in various sysctls */ -const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX }; +const int sysctl_vals[] = { 0, 1, INT_MAX }; EXPORT_SYMBOL(sysctl_vals); +const int android_gki_sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX }; +EXPORT_SYMBOL(android_gki_sysctl_vals); /* Support for permanently empty directories */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index c202a72e1690..6ee587d0aeaa 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -38,18 +38,19 @@ struct ctl_table_header; struct ctl_dir; /* Keep the same order as in fs/proc/proc_sysctl.c */ -#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[0]) -#define SYSCTL_ZERO ((void *)&sysctl_vals[1]) -#define SYSCTL_ONE ((void *)&sysctl_vals[2]) -#define SYSCTL_TWO ((void *)&sysctl_vals[3]) -#define SYSCTL_FOUR ((void *)&sysctl_vals[4]) -#define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5]) -#define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6]) -#define SYSCTL_ONE_THOUSAND ((void *)&sysctl_vals[7]) -#define SYSCTL_THREE_THOUSAND ((void *)&sysctl_vals[8]) -#define SYSCTL_INT_MAX ((void *)&sysctl_vals[9]) +#define SYSCTL_NEG_ONE ((void *)&android_gki_sysctl_vals[0]) +#define SYSCTL_ZERO ((void *)&android_gki_sysctl_vals[1]) +#define SYSCTL_ONE ((void *)&android_gki_sysctl_vals[2]) +#define SYSCTL_TWO ((void *)&android_gki_sysctl_vals[3]) +#define SYSCTL_FOUR ((void *)&android_gki_sysctl_vals[4]) +#define SYSCTL_ONE_HUNDRED ((void *)&android_gki_sysctl_vals[5]) +#define SYSCTL_TWO_HUNDRED ((void *)&android_gki_sysctl_vals[6]) +#define SYSCTL_ONE_THOUSAND ((void *)&android_gki_sysctl_vals[7]) +#define SYSCTL_THREE_THOUSAND ((void *)&android_gki_sysctl_vals[8]) +#define SYSCTL_INT_MAX ((void *)&android_gki_sysctl_vals[9]) extern const int sysctl_vals[]; +extern const int android_gki_sysctl_vals[]; typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); From de4dc1c15c722079f3854dab4a6d467170f94225 Mon Sep 17 00:00:00 2001 From: Dylan Chang Date: Tue, 11 Jul 2023 11:56:27 +0800 Subject: [PATCH 3719/4345] ANDROID: GKI: Add symbol list for Nothing Add symbol list for Nothing at the first time 2 function symbol(s) added 'struct file_system_type* get_fs_type(const char*)' 'void iterate_supers_type(struct file_system_type*, void(*)(struct super_block*, void*), void*)' Bug: 290756100 Change-Id: I3cdf16cf21bf04df2c0ab10358e7e7dd4e82c2d1 Signed-off-by: Dylan Chang Signed-off-by: Giuliano Procida --- android/abi_gki_aarch64.xml | 119 ++++++++++++++++++++++++++++++-- android/abi_gki_aarch64_nothing | 4 ++ build.config.gki.aarch64 | 1 + 3 files changed, 119 insertions(+), 5 deletions(-) create mode 100644 android/abi_gki_aarch64_nothing diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 7656ab64512c..de2a2412ca6d 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -2798,6 +2798,7 @@ + @@ -3300,6 +3301,7 @@ + @@ -15444,6 +15446,89 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -33955,6 +34040,7 @@ + @@ -58997,6 +59083,11 @@ + + + + + @@ -68594,7 +68685,14 @@ - + + + + + + + + @@ -93905,6 +94003,7 @@ + @@ -130962,10 +131061,10 @@ - - - - + + + + @@ -132456,6 +132555,10 @@ + + + + @@ -135021,6 +135124,12 @@ + + + + + + diff --git a/android/abi_gki_aarch64_nothing b/android/abi_gki_aarch64_nothing new file mode 100644 index 000000000000..5960f2b3c287 --- /dev/null +++ b/android/abi_gki_aarch64_nothing @@ -0,0 +1,4 @@ +[abi_symbol_list] +# required by mount_state.ko + iterate_supers_type + get_fs_type \ No newline at end of file diff --git a/build.config.gki.aarch64 b/build.config.gki.aarch64 index 738ddee4af33..b0971e2a0c4f 100644 --- a/build.config.gki.aarch64 +++ b/build.config.gki.aarch64 @@ -23,6 +23,7 @@ android/abi_gki_aarch64_honor android/abi_gki_aarch64_imx android/abi_gki_aarch64_lenovo android/abi_gki_aarch64_mtk +android/abi_gki_aarch64_nothing android/abi_gki_aarch64_oplus android/abi_gki_aarch64_qcom android/abi_gki_aarch64_rockchip From bff06d6020dea5a813cfe740c98706aa8ea244af Mon Sep 17 00:00:00 2001 From: Liujie Xie Date: Wed, 12 Jul 2023 15:40:52 +0800 Subject: [PATCH 3720/4345] ANDROID: vendor_hooks: Supplement the missing hook call point. As a supplement to commit eed2741ae61d ("ANDROID: vendor_hook: add hooks to protect locking-tsk in cpu scheduler"). In rwsem read, we missed a lock-holding scenario, add it now. Bug: 290868674 Change-Id: I718dd942b24b330a79283fc241dcbf47cc34c0c5 Signed-off-by: Liujie Xie --- kernel/locking/rwsem.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 057c9e99251a..acd1fc78d059 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1066,6 +1066,8 @@ queue: raw_spin_unlock_irq(&sem->wait_lock); rwsem_set_reader_owned(sem); lockevent_inc(rwsem_rlock_fast); + trace_android_vh_record_rwsem_lock_starttime( + current, jiffies); return sem; } adjustment += RWSEM_FLAG_WAITERS; From 4def2dd1807f802810d8c16e13d81a8c5e5c4e55 Mon Sep 17 00:00:00 2001 From: Kyongho Cho Date: Thu, 13 Jul 2023 12:39:53 -0700 Subject: [PATCH 3721/4345] ANDROID: ABI: update symbol list for Xclipse GPU Leaf changes summary: 1 artifact changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 1 Added function Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 0 Added variable 1 Added function: [A] 'function void ttm_tt_unpopulate(ttm_bo_device*, ttm_tt*)' Xclipse GPU driver depends on TTM for graphics buffer allocation and management. It is required by customers to add graphics memory swap to improve overall memory efficiency. However TTM's swap feature can't be used since it selects victim buffer by LRU and we can't choose a specific buffer to swap. Xclipse GPU driver implements its own swap feature by means of APIs of TTM. But the problem is TTM's buffer allocations statistics in ttm_tt.c which are local to that file. Whenever a graphic buffer is swapped out, the size of total page allocation should be decreased but it is not possible from the outside of ttm_tt.c. If the statistics is not maintained well, TTM ends up swapping out TTM buffers globally which is unexpected. Bug: 291100620 Change-Id: I0edc4b5e8ae6d9e41e99750eb5f0e62fa78ec1fb Signed-off-by: Kyongho Cho --- android/abi_gki_aarch64.xml | 164 ++++++++++----------------------- android/abi_gki_aarch64_exynos | 1 + drivers/gpu/drm/ttm/ttm_tt.c | 1 + 3 files changed, 52 insertions(+), 114 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index de2a2412ca6d..a35c3777c1d0 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -5613,6 +5613,7 @@ + @@ -7303,6 +7304,14 @@ + + + + + + + + @@ -9500,9 +9509,9 @@ - - - + + + @@ -15446,89 +15455,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -24624,6 +24550,9 @@ + + + @@ -40110,8 +40039,8 @@ - - + + @@ -68685,14 +68614,7 @@ - - - - - - - - + @@ -71699,7 +71621,17 @@ - + + + + + + + + + + + @@ -94003,7 +93935,6 @@ - @@ -128282,16 +128213,16 @@ - - + + - - + + - - + + @@ -128303,16 +128234,16 @@ - - + + - - + + - - + + @@ -147002,6 +146933,11 @@ + + + + + @@ -147826,12 +147762,12 @@ - - + + - - + + diff --git a/android/abi_gki_aarch64_exynos b/android/abi_gki_aarch64_exynos index c64082bb95b0..ef69e40b6754 100644 --- a/android/abi_gki_aarch64_exynos +++ b/android/abi_gki_aarch64_exynos @@ -2136,6 +2136,7 @@ ttm_tt_destroy_common ttm_tt_populate ttm_tt_set_placement_caching + ttm_tt_unpopulate ttm_unmap_and_unpopulate_pages tty_flip_buffer_push tty_insert_flip_string_fixed_flag diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index f43fa69a1e65..3f1a029248ce 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -466,3 +466,4 @@ void ttm_tt_unpopulate(struct ttm_bo_device *bdev, else ttm_pool_unpopulate(ttm); } +EXPORT_SYMBOL(ttm_tt_unpopulate); From f48a4c3b296eb7cf187021f0bb6b9150c5aa74c7 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 11 Jul 2023 17:20:13 +0000 Subject: [PATCH 3722/4345] ANDROID: Incremental fs: Allocate data buffer based on input request size Presently the data buffer used to return the per-UID timeout description is created based on information provided by the user. It is expected that the user populates a variable called 'timeouts_array_size' which is heavily scrutinised to ensure the value provided is appropriate i.e. smaller than the largest possible value but large enough to contain all of the data we wish to pass back. The issue is that the aforementioned scrutiny is imposed on a different variable to the one expected. Contrary to expectation, the data buffer is actually being allocated to the size specified in a variable named 'timeouts_array_size_out'. A variable originally designed to only contain the output information i.e. the size of the data actually copied to the user for consumption. This value is also user provided and is not given the same level of scrutiny as the former. The fix in this case is simple. Ignore 'timeouts_array_size_out' until it is time to populate (over-write) it ourselves and use 'timeouts_array_size' to shape the buffer as intended. Bug: 281547360 Change-Id: I95e12879a33a2355f9e4bc0ce2bfc3f229141aa8 Signed-off-by: Lee Jones (cherry picked from commit 5a4d20a3eb4e651f88ed2f1f08cee066639ca801) --- fs/incfs/pseudo_files.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/incfs/pseudo_files.c b/fs/incfs/pseudo_files.c index 1b9bf000f598..d43ccb2ce3b0 100644 --- a/fs/incfs/pseudo_files.c +++ b/fs/incfs/pseudo_files.c @@ -916,10 +916,10 @@ static long ioctl_get_read_timeouts(struct mount_info *mi, void __user *arg) if (copy_from_user(&args, args_usr_ptr, sizeof(args))) return -EINVAL; - if (args.timeouts_array_size_out > INCFS_DATA_FILE_BLOCK_SIZE) + if (args.timeouts_array_size > INCFS_DATA_FILE_BLOCK_SIZE) return -EINVAL; - buffer = kzalloc(args.timeouts_array_size_out, GFP_NOFS); + buffer = kzalloc(args.timeouts_array_size, GFP_NOFS); if (!buffer) return -ENOMEM; From adad2dab31999467601f753a90a4290f344fee79 Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Tue, 25 Apr 2023 09:46:18 +0200 Subject: [PATCH 3723/4345] UPSTREAM: Revert "Fix XFRM-I support for nested ESP tunnels" [ Upstream commit 5fc46f94219d1d103ffb5f0832be9da674d85a73 ] This reverts commit b0355dbbf13c0052931dd14c38c789efed64d3de. The reverted commit clears the secpath on packets received via xfrm interfaces to support nested IPsec tunnels. This breaks Netfilter policy matching using xt_policy in the FORWARD chain, as the secpath is missing during forwarding. Additionally, Benedict Wong reports that it breaks Transport-in-Tunnel mode. Fix this regression by reverting the commit until we have a better approach for nested IPsec tunnels. Fixes: b0355dbbf13c ("Fix XFRM-I support for nested ESP tunnels") Link: https://lore.kernel.org/netdev/20230412085615.124791-1-martin@strongswan.org/ Signed-off-by: Martin Willi Signed-off-by: Steffen Klassert Signed-off-by: Sasha Levin Bug: 288489934 (cherry picked from commit c5449195f86ec02433a9ef8abe01be11d228fca1) Change-Id: Iefaed6d21a641fefb02e0fd0067086a9ae3a802a Signed-off-by: Carlos Llamas --- net/xfrm/xfrm_interface.c | 54 +++------------------------------------ net/xfrm/xfrm_policy.c | 3 --- 2 files changed, 4 insertions(+), 53 deletions(-) diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index e4f21a692415..da518b4ca84c 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -207,52 +207,6 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } -static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type, unsigned short family) -{ - struct sec_path *sp; - - sp = skb_sec_path(skb); - if (sp && (sp->len || sp->olen) && - !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) - goto discard; - - XFRM_SPI_SKB_CB(skb)->family = family; - if (family == AF_INET) { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; - } else { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; - } - - return xfrm_input(skb, nexthdr, spi, encap_type); -discard: - kfree_skb(skb); - return 0; -} - -static int xfrmi4_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); -} - -static int xfrmi6_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], - 0, 0, AF_INET6); -} - -static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); -} - -static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); -} - static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -826,8 +780,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrmi6_rcv, - .input_handler = xfrmi6_input, + .handler = xfrm6_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -877,8 +831,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrmi4_rcv, - .input_handler = xfrmi4_input, + .handler = xfrm4_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index c1aaf71d7ccb..7b9d21d85d48 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3698,9 +3698,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } - if (if_id) - secpath_reset(skb); - xfrm_pols_put(pols, npols); return 1; } From 28f1c8e015511c60a5b4ae888773a8b1ed946a87 Mon Sep 17 00:00:00 2001 From: shenjiangjiang Date: Wed, 5 Jul 2023 17:50:26 +0800 Subject: [PATCH 3724/4345] ANDROID: vendor_hook: Add hook to abort reclaim and compaction We need to abort the reclaim/compaction by sending signal(such as SIGUSR2) to the reclaim thread, or just abort when cpu-usage is too-high or free-mem is enough. Bug: 289987875 Change-Id: I4b637cbd2b37235eec27a985a9b5b95598247c59 Signed-off-by: shenjiangjiang (cherry picked from commit 024628cc9203cbd4f8471d98435b3a3d6f85764d) --- drivers/android/vendor_hooks.c | 2 ++ include/trace/hooks/mm.h | 6 ++++++ mm/compaction.c | 9 ++++++++- mm/madvise.c | 4 +++- 4 files changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index ae35b2a9ec8b..81334ada8a61 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -488,6 +488,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_look_around); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_look_around_migrate_page); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_test_clear_look_around_ref); EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_dma_buf_stats_teardown); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_madvise_cold_or_pageout_abort); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_compact_finished); /* * For type visibility */ diff --git a/include/trace/hooks/mm.h b/include/trace/hooks/mm.h index 7a1d74f646cb..480880a49d32 100644 --- a/include/trace/hooks/mm.h +++ b/include/trace/hooks/mm.h @@ -338,6 +338,12 @@ DECLARE_HOOK(android_vh_look_around, TP_PROTO(struct page_vma_mapped_walk *pvmw, struct page *page, struct vm_area_struct *vma, int *referenced), TP_ARGS(pvmw, page, vma, referenced)); +DECLARE_HOOK(android_vh_compact_finished, + TP_PROTO(bool *abort_compact), + TP_ARGS(abort_compact)); +DECLARE_HOOK(android_vh_madvise_cold_or_pageout_abort, + TP_PROTO(struct vm_area_struct *vma, bool *abort_madvise), + TP_ARGS(vma, abort_madvise)); /* macro versions of hooks are no longer required */ #endif /* _TRACE_HOOK_MM_H */ diff --git a/mm/compaction.c b/mm/compaction.c index eca4d0ea74c1..dc96fadb04da 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -45,6 +45,11 @@ static inline void count_compact_events(enum vm_event_item item, long delta) #define CREATE_TRACE_POINTS #include +#undef CREATE_TRACE_POINTS +#ifndef __GENKSYMS__ +#include +#endif + #define block_start_pfn(pfn, order) round_down(pfn, 1UL << (order)) #define block_end_pfn(pfn, order) ALIGN((pfn) + 1, 1UL << (order)) #define pageblock_start_pfn(pfn) block_start_pfn(pfn, pageblock_order) @@ -1984,6 +1989,7 @@ static enum compact_result __compact_finished(struct compact_control *cc) unsigned int order; const int migratetype = cc->migratetype; int ret; + bool abort_compact = false; /* Compaction run completes if the migrate and free scanner meet */ if (compact_scanners_met(cc)) { @@ -2083,7 +2089,8 @@ static enum compact_result __compact_finished(struct compact_control *cc) } out: - if (cc->contended || fatal_signal_pending(current)) + trace_android_vh_compact_finished(&abort_compact); + if (cc->contended || fatal_signal_pending(current) || abort_compact) ret = COMPACT_CONTENDED; return ret; diff --git a/mm/madvise.c b/mm/madvise.c index b3761ca637bb..d16fa1d8f60f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -322,8 +322,10 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, struct page *page = NULL; LIST_HEAD(page_list); bool allow_shared = false; + bool abort_madvise = false; - if (fatal_signal_pending(current)) + trace_android_vh_madvise_cold_or_pageout_abort(vma, &abort_madvise); + if (fatal_signal_pending(current) || abort_madvise) return -EINTR; trace_android_vh_madvise_cold_or_pageout(vma, &allow_shared); From 1dc57723228ef10764dd13b6da8651e6f1f67d3b Mon Sep 17 00:00:00 2001 From: shenjiangjiang Date: Mon, 17 Jul 2023 11:46:56 +0800 Subject: [PATCH 3725/4345] ANDROID: GKI: Update symbols to symbol list Leaf changes summary: 4 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 2 Added functions Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 2 Added variables 2 Added functions: [A] 'function int __traceiter_android_vh_compact_finished(void*, bool*)' [A] 'function int __traceiter_android_vh_madvise_cold_or_pageout_abort(void*, vm_area_struct*, bool*)' 2 Added variables: [A] 'tracepoint __tracepoint_android_vh_compact_finished' [A] 'tracepoint __tracepoint_android_vh_madvise_cold_or_pageout_abort' Bug: 288216516 Change-Id: I182b925aec69655ad6c17e5452d387c158e563ef Signed-off-by: shenjiangjiang --- android/abi_gki_aarch64.xml | 138 +++++++++++++++++----------------- android/abi_gki_aarch64_oplus | 4 + 2 files changed, 73 insertions(+), 69 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index a35c3777c1d0..af1caade63e1 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -471,6 +471,7 @@ + @@ -554,6 +555,7 @@ + @@ -6541,6 +6543,7 @@ + @@ -6624,6 +6627,7 @@ + @@ -8754,14 +8758,6 @@ - - - - - - - - @@ -44660,7 +44656,23 @@ - + + + + + + + + + + + + + + + + + @@ -49000,6 +49012,7 @@ + @@ -53957,6 +53970,13 @@ + + + + + + + @@ -65106,26 +65126,7 @@ - - - - - - - - - - - - - - - - - - - - + @@ -66622,6 +66623,13 @@ + + + + + + + @@ -91423,6 +91431,7 @@ + @@ -103190,6 +103199,12 @@ + + + + + + @@ -106596,29 +106611,7 @@ - - - - - - - - - - - - - - - - - - - - - - - + @@ -109544,13 +109537,6 @@ - - - - - - - @@ -111436,6 +111422,7 @@ + @@ -116509,20 +116496,20 @@ - + - + - - + + - - - + + + @@ -119371,6 +119358,11 @@ + + + + + @@ -119906,6 +119898,12 @@ + + + + + + @@ -121454,6 +121452,7 @@ + @@ -121537,6 +121536,7 @@ + @@ -135031,9 +135031,9 @@ - - - + + + diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index 20d15056b373..51738dc7cd4d 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -2794,6 +2794,7 @@ __traceiter_android_vh_clear_mask_adjust __traceiter_android_vh_clear_reserved_fmt_fields __traceiter_android_vh_cma_drain_all_pages_bypass + __traceiter_android_vh_compact_finished __traceiter_android_vh_alloc_pages_reclaim_bypass __traceiter_android_vh_free_unref_page_bypass __traceiter_android_vh_kvmalloc_node_use_vmalloc @@ -2851,6 +2852,7 @@ __traceiter_android_vh_logbuf __traceiter_android_vh_look_around __traceiter_android_vh_look_around_migrate_page + __traceiter_android_vh_madvise_cold_or_pageout_abort __traceiter_android_vh_mark_page_accessed __traceiter_android_vh_mem_cgroup_alloc __traceiter_android_vh_mem_cgroup_css_offline @@ -3059,6 +3061,7 @@ __tracepoint_android_vh_clear_mask_adjust __tracepoint_android_vh_clear_reserved_fmt_fields __tracepoint_android_vh_cma_drain_all_pages_bypass + __tracepoint_android_vh_compact_finished __tracepoint_android_vh_alloc_pages_reclaim_bypass __tracepoint_android_vh_free_unref_page_bypass __tracepoint_android_vh_kvmalloc_node_use_vmalloc @@ -3116,6 +3119,7 @@ __tracepoint_android_vh_logbuf __tracepoint_android_vh_look_around __tracepoint_android_vh_look_around_migrate_page + __tracepoint_android_vh_madvise_cold_or_pageout_abort __tracepoint_android_vh_mark_page_accessed __tracepoint_android_vh_mem_cgroup_alloc __tracepoint_android_vh_mem_cgroup_css_offline From b4b7d228301ff12eeef059f28d20b19ebd7c29b4 Mon Sep 17 00:00:00 2001 From: Vatsal Parasrampuria Date: Wed, 19 Jul 2023 20:04:28 +0000 Subject: [PATCH 3726/4345] ANDROID: wakeupbypass: Add vendor hook for batteryswap Implemented a hook to check if battery swap is enabled in alarm timer suspend routine. During a battery swap, it is crucial to ensure that the device remains in a suspended state, relying on a limited backup power source. It is essential to prevent any unintended awakenings in this state, as they could potentially lead to sudden surges in the power consumption, ultimately resulting in a device shutdown. Hence, we disable alarmtimer IRQs when in batteryswap mode. Bug: 290881352 Change-Id: I31dc30d9a3168bb1356cccba49f0a70fd6b73782 Signed-off-by: Vatsal Parasrampuria --- drivers/android/vendor_hooks.c | 2 ++ drivers/input/keyboard/gpio_keys.c | 18 ++++++++++++++---- include/trace/hooks/wakeupbypass.h | 17 +++++++++++++++++ kernel/time/alarmtimer.c | 7 +++++++ 4 files changed, 40 insertions(+), 4 deletions(-) create mode 100644 include/trace/hooks/wakeupbypass.h diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index 81334ada8a61..815c5efb5c22 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -76,6 +76,7 @@ #include #include #include +#include /* * Export tracepoints that act as a bare tracehook (ie: have no trace event @@ -490,6 +491,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_test_clear_look_around_ref); EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_dma_buf_stats_teardown); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_madvise_cold_or_pageout_abort); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_compact_finished); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_wakeup_bypass); /* * For type visibility */ diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c index f2d4e4daa818..725a196662af 100644 --- a/drivers/input/keyboard/gpio_keys.c +++ b/drivers/input/keyboard/gpio_keys.c @@ -28,6 +28,7 @@ #include #include #include +#include struct gpio_button_data { const struct gpio_keys_button *button; @@ -958,11 +959,16 @@ static int __maybe_unused gpio_keys_suspend(struct device *dev) struct gpio_keys_drvdata *ddata = dev_get_drvdata(dev); struct input_dev *input = ddata->input; int error; + int wakeup_bypass_enabled = 0; + + trace_android_vh_wakeup_bypass(&wakeup_bypass_enabled); if (device_may_wakeup(dev)) { - error = gpio_keys_enable_wakeup(ddata); - if (error) - return error; + if (!wakeup_bypass_enabled) { + error = gpio_keys_enable_wakeup(ddata); + if (error) + return error; + } } else { mutex_lock(&input->mutex); if (input->users) @@ -978,9 +984,13 @@ static int __maybe_unused gpio_keys_resume(struct device *dev) struct gpio_keys_drvdata *ddata = dev_get_drvdata(dev); struct input_dev *input = ddata->input; int error = 0; + int wakeup_bypass_enabled = 0; + + trace_android_vh_wakeup_bypass(&wakeup_bypass_enabled); if (device_may_wakeup(dev)) { - gpio_keys_disable_wakeup(ddata); + if (!wakeup_bypass_enabled) + gpio_keys_disable_wakeup(ddata); } else { mutex_lock(&input->mutex); if (input->users) diff --git a/include/trace/hooks/wakeupbypass.h b/include/trace/hooks/wakeupbypass.h new file mode 100644 index 000000000000..a96c8874481e --- /dev/null +++ b/include/trace/hooks/wakeupbypass.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM wakeupbypass + +#define TRACE_INCLUDE_PATH trace/hooks + +#if !defined(_TRACE_HOOK_WAKEUPBYPASS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_HOOK_WAKEUPBYPASS_H +#include + +DECLARE_HOOK(android_vh_wakeup_bypass, + TP_PROTO(int *is_wakeup_bypassed), + TP_ARGS(is_wakeup_bypassed)); + +#endif /* _TRACE_HOOK_WAKEUPBYPASS_H */ +/* This part must be outside protection */ +#include diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 1de426d3f694..3a20a9f9f7b5 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -33,6 +33,8 @@ #define CREATE_TRACE_POINTS #include +#undef CREATE_TRACE_POINTS +#include /** * struct alarm_base - Alarm timer bases * @lock: Lock for syncrhonized access to the base @@ -246,6 +248,7 @@ static int alarmtimer_suspend(struct device *dev) struct rtc_device *rtc; unsigned long flags; struct rtc_time tm; + int wakeup_bypass_enabled = 0; spin_lock_irqsave(&freezer_delta_lock, flags); min = freezer_delta; @@ -254,6 +257,10 @@ static int alarmtimer_suspend(struct device *dev) freezer_delta = 0; spin_unlock_irqrestore(&freezer_delta_lock, flags); + trace_android_vh_wakeup_bypass(&wakeup_bypass_enabled); + if (wakeup_bypass_enabled) + return 0; + rtc = alarmtimer_get_rtcdev(); /* If we have no rtcdev, just return */ if (!rtc) From 113ce5ed59fc99838ec7564c37323a3b4e500cde Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Tue, 2 May 2023 19:53:50 +0200 Subject: [PATCH 3727/4345] x86/microcode/AMD: Load late on both threads too commit a32b0f0db3f396f1c9be2fe621e77c09ec3d8e7d upstream. Do the same as early loading - load on both threads. Signed-off-by: Borislav Petkov (AMD) Cc: Link: https://lore.kernel.org/r/20230605141332.25948-1-bp@alien8.de Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/microcode/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index d3bce6d380ed..936085d819b1 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -700,7 +700,7 @@ static enum ucode_state apply_microcode_amd(int cpu) rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); /* need to apply patch? */ - if (rev >= mc_amd->hdr.patch_id) { + if (rev > mc_amd->hdr.patch_id) { ret = UCODE_OK; goto out; } From 191b8f9b0e3708e8325d8d28e1005a1fbe5e3991 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Sat, 15 Jul 2023 13:31:32 +0200 Subject: [PATCH 3728/4345] x86/cpu/amd: Move the errata checking functionality up Upstream commit: 8b6f687743dacce83dbb0c7cfacf88bab00f808a Avoid new and remove old forward declarations. No functional changes. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/amd.c | 139 ++++++++++++++++++-------------------- 1 file changed, 67 insertions(+), 72 deletions(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 89a9b7754476..6eea37f827b1 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -28,11 +28,6 @@ #include "cpu.h" -static const int amd_erratum_383[]; -static const int amd_erratum_400[]; -static const int amd_erratum_1054[]; -static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); - /* * nodes_per_socket: Stores the number of nodes per socket. * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX @@ -40,6 +35,73 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); */ static u32 nodes_per_socket = 1; +/* + * AMD errata checking + * + * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or + * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that + * have an OSVW id assigned, which it takes as first argument. Both take a + * variable number of family-specific model-stepping ranges created by + * AMD_MODEL_RANGE(). + * + * Example: + * + * const int amd_erratum_319[] = + * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2), + * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0), + * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); + */ + +#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } +#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } +#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ + ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) +#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) +#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) +#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) + +static const int amd_erratum_400[] = + AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), + AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); + +static const int amd_erratum_383[] = + AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); + +/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ +static const int amd_erratum_1054[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); + +static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) +{ + int osvw_id = *erratum++; + u32 range; + u32 ms; + + if (osvw_id >= 0 && osvw_id < 65536 && + cpu_has(cpu, X86_FEATURE_OSVW)) { + u64 osvw_len; + + rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len); + if (osvw_id < osvw_len) { + u64 osvw_bits; + + rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6), + osvw_bits); + return osvw_bits & (1ULL << (osvw_id & 0x3f)); + } + } + + /* OSVW unavailable or ID unknown, match family-model-stepping range */ + ms = (cpu->x86_model << 4) | cpu->x86_stepping; + while ((range = *erratum++)) + if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && + (ms >= AMD_MODEL_RANGE_START(range)) && + (ms <= AMD_MODEL_RANGE_END(range))) + return true; + + return false; +} + static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -1153,73 +1215,6 @@ static const struct cpu_dev amd_cpu_dev = { cpu_dev_register(amd_cpu_dev); -/* - * AMD errata checking - * - * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or - * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that - * have an OSVW id assigned, which it takes as first argument. Both take a - * variable number of family-specific model-stepping ranges created by - * AMD_MODEL_RANGE(). - * - * Example: - * - * const int amd_erratum_319[] = - * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2), - * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0), - * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); - */ - -#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } -#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } -#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ - ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) -#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) -#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) -#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) - -static const int amd_erratum_400[] = - AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), - AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); - -static const int amd_erratum_383[] = - AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); - -/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ -static const int amd_erratum_1054[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); - -static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) -{ - int osvw_id = *erratum++; - u32 range; - u32 ms; - - if (osvw_id >= 0 && osvw_id < 65536 && - cpu_has(cpu, X86_FEATURE_OSVW)) { - u64 osvw_len; - - rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len); - if (osvw_id < osvw_len) { - u64 osvw_bits; - - rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6), - osvw_bits); - return osvw_bits & (1ULL << (osvw_id & 0x3f)); - } - } - - /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_stepping; - while ((range = *erratum++)) - if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && - (ms >= AMD_MODEL_RANGE_START(range)) && - (ms <= AMD_MODEL_RANGE_END(range))) - return true; - - return false; -} - void set_dr_addr_mask(unsigned long mask, int dr) { if (!boot_cpu_has(X86_FEATURE_BPEXT)) From 93df00f9d48d48466ddbe01a06eaaf3311ecfb53 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Sat, 15 Jul 2023 13:41:28 +0200 Subject: [PATCH 3729/4345] x86/cpu/amd: Add a Zenbleed fix Upstream commit: 522b1d69219d8f083173819fde04f994aa051a98 Add a fix for the Zen2 VZEROUPPER data corruption bug where under certain circumstances executing VZEROUPPER can cause register corruption or leak data. The optimal fix is through microcode but in the case the proper microcode revision has not been applied, enable a fallback fix using a chicken bit. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/microcode.h | 1 + arch/x86/include/asm/microcode_amd.h | 2 + arch/x86/include/asm/msr-index.h | 1 + arch/x86/kernel/cpu/amd.c | 60 ++++++++++++++++++++++++++++ arch/x86/kernel/cpu/common.c | 2 + 5 files changed, 66 insertions(+) diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 509cc0262fdc..394605e59f2b 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -5,6 +5,7 @@ #include #include #include +#include struct ucode_patch { struct list_head plist; diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index a645b25ee442..403a8e76b310 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -48,11 +48,13 @@ extern void __init load_ucode_amd_bsp(unsigned int family); extern void load_ucode_amd_ap(unsigned int family); extern int __init save_microcode_in_initrd_amd(unsigned int family); void reload_ucode_amd(unsigned int cpu); +extern void amd_check_microcode(void); #else static inline void __init load_ucode_amd_bsp(unsigned int family) {} static inline void load_ucode_amd_ap(unsigned int family) {} static inline int __init save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } static inline void reload_ucode_amd(unsigned int cpu) {} +static inline void amd_check_microcode(void) {} #endif #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index f71a177b6b18..3fab152809ab 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -497,6 +497,7 @@ #define MSR_AMD64_DE_CFG 0xc0011029 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT) +#define MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT 9 #define MSR_AMD64_BU_CFG2 0xc001102a #define MSR_AMD64_IBSFETCHCTL 0xc0011030 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 6eea37f827b1..3d99a823ffac 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -71,6 +71,11 @@ static const int amd_erratum_383[] = static const int amd_erratum_1054[] = AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); +static const int amd_zenbleed[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf), + AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), + AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { int osvw_id = *erratum++; @@ -1030,6 +1035,47 @@ static void init_amd_zn(struct cpuinfo_x86 *c) } } +static bool cpu_has_zenbleed_microcode(void) +{ + u32 good_rev = 0; + + switch (boot_cpu_data.x86_model) { + case 0x30 ... 0x3f: good_rev = 0x0830107a; break; + case 0x60 ... 0x67: good_rev = 0x0860010b; break; + case 0x68 ... 0x6f: good_rev = 0x08608105; break; + case 0x70 ... 0x7f: good_rev = 0x08701032; break; + case 0xa0 ... 0xaf: good_rev = 0x08a00008; break; + + default: + return false; + break; + } + + if (boot_cpu_data.microcode < good_rev) + return false; + + return true; +} + +static void zenbleed_check(struct cpuinfo_x86 *c) +{ + if (!cpu_has_amd_erratum(c, amd_zenbleed)) + return; + + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return; + + if (!cpu_has(c, X86_FEATURE_AVX)) + return; + + if (!cpu_has_zenbleed_microcode()) { + pr_notice_once("Zenbleed: please update your microcode for the most optimal fix\n"); + msr_set_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT); + } else { + msr_clear_bit(MSR_AMD64_DE_CFG, MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT); + } +} + static void init_amd(struct cpuinfo_x86 *c) { early_init_amd(c); @@ -1120,6 +1166,8 @@ static void init_amd(struct cpuinfo_x86 *c) msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); check_null_seg_clears_base(c); + + zenbleed_check(c); } #ifdef CONFIG_X86_32 @@ -1233,3 +1281,15 @@ void set_dr_addr_mask(unsigned long mask, int dr) break; } } + +static void zenbleed_check_cpu(void *unused) +{ + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + + zenbleed_check(c); +} + +void amd_check_microcode(void) +{ + on_each_cpu(zenbleed_check_cpu, NULL, 1); +} diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index e2dee6010846..f41781d06a5f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2165,6 +2165,8 @@ void microcode_check(struct cpuinfo_x86 *prev_info) perf_check_microcode(); + amd_check_microcode(); + store_cpu_caps(&curr_info); if (!memcmp(&prev_info->x86_capability, &curr_info.x86_capability, From 140d69b4e41d185d886880460461fab70f3b5e84 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 24 Jul 2023 19:09:12 +0200 Subject: [PATCH 3730/4345] Linux 5.10.187 Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index bb2be0ed9ff2..2aaf3b0b9250 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 186 +SUBLEVEL = 187 EXTRAVERSION = NAME = Dare mighty things From e933b7be1c011205581e062d3925823dacef0cf4 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 12 May 2023 16:18:00 +0100 Subject: [PATCH 3731/4345] UPSTREAM: media: dvb-core: Fix kernel WARNING for blocking operation in wait_event*() [ Upstream commit b8c75e4a1b325ea0a9433fa8834be97b5836b946 ] Using a semaphore in the wait_event*() condition is no good idea. It hits a kernel WARN_ON() at prepare_to_wait_event() like: do not call blocking ops when !TASK_RUNNING; state=1 set at prepare_to_wait_event+0x6d/0x690 For avoiding the potential deadlock, rewrite to an open-coded loop instead. Unlike the loop in wait_event*(), this uses wait_woken() after the condition check, hence the task state stays consistent. CVE-2023-31084 was assigned to this bug. Link: https://lore.kernel.org/r/CA+UBctCu7fXn4q41O_3=id1+OdyQ85tZY1x+TkT-6OVBL6KAUw@mail.gmail.com/ Bug: 290204413 Link: https://lore.kernel.org/linux-media/20230512151800.1874-1-tiwai@suse.de Reported-by: Yu Hao Closes: https://nvd.nist.gov/vuln/detail/CVE-2023-31084 Signed-off-by: Takashi Iwai Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin (cherry picked from commit d0088ea444e676a0c75551efe183bee4a3d2cfc8) Signed-off-by: Lee Jones Change-Id: I1e715f6f1994e30781c1896c880b5491080f04da From 2427afff1e01fee0e0fc546d7af09ac96ff39373 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Fri, 28 Apr 2023 12:07:46 -0400 Subject: [PATCH 3732/4345] UPSTREAM: gfs2: Don't deref jdesc in evict [ Upstream commit 504a10d9e46bc37b23d0a1ae2f28973c8516e636 ] On corrupt gfs2 file systems the evict code can try to reference the journal descriptor structure, jdesc, after it has been freed and set to NULL. The sequence of events is: init_journal() ... fail_jindex: gfs2_jindex_free(sdp); <------frees journals, sets jdesc = NULL if (gfs2_holder_initialized(&ji_gh)) gfs2_glock_dq_uninit(&ji_gh); fail: iput(sdp->sd_jindex); <--references jdesc in evict_linked_inode evict() gfs2_evict_inode() evict_linked_inode() ret = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); <------references the now freed/zeroed sd_jdesc pointer. The call to gfs2_trans_begin is done because the truncate_inode_pages call can cause gfs2 events that require a transaction, such as removing journaled data (jdata) blocks from the journal. This patch fixes the problem by adding a check for sdp->sd_jdesc to function gfs2_evict_inode. In theory, this should only happen to corrupt gfs2 file systems, when gfs2 detects the problem, reports it, then tries to evict all the system inodes it has read in up to that point. Bug: 289870854 Reported-by: Yang Lan Signed-off-by: Bob Peterson Signed-off-by: Andreas Gruenbacher Signed-off-by: Sasha Levin (cherry picked from commit 5ae4a618a1558d2b536fdd5d42e53d3e2d73870c) Signed-off-by: Lee Jones Change-Id: I501e8631e1b60479023f5e6ad957540f9e10bcd5 From c4191be802f5ea1a0212268189feb20e07a12b00 Mon Sep 17 00:00:00 2001 From: Xiaojun Ji Date: Tue, 25 Jul 2023 17:31:18 +0800 Subject: [PATCH 3733/4345] ANDROID: GKI: add symbol list file for moto Leaf changes summary: 0 artifact changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 0 Added function Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 0 Added variable Bug: 289423315 Change-Id: I2f12145513148dced06d9d0ac3bf01dd92863662 Signed-off-by: Xiaojun Ji --- android/abi_gki_aarch64_moto | 3 +++ build.config.gki.aarch64 | 1 + 2 files changed, 4 insertions(+) create mode 100644 android/abi_gki_aarch64_moto diff --git a/android/abi_gki_aarch64_moto b/android/abi_gki_aarch64_moto new file mode 100644 index 000000000000..009165749001 --- /dev/null +++ b/android/abi_gki_aarch64_moto @@ -0,0 +1,3 @@ +[abi_symbol_list] + __traceiter_android_vh_tune_mmap_readaround + __tracepoint_android_vh_tune_mmap_readaround diff --git a/build.config.gki.aarch64 b/build.config.gki.aarch64 index b0971e2a0c4f..1134cb881e0e 100644 --- a/build.config.gki.aarch64 +++ b/build.config.gki.aarch64 @@ -22,6 +22,7 @@ android/abi_gki_aarch64_hikey960 android/abi_gki_aarch64_honor android/abi_gki_aarch64_imx android/abi_gki_aarch64_lenovo +android/abi_gki_aarch64_moto android/abi_gki_aarch64_mtk android/abi_gki_aarch64_nothing android/abi_gki_aarch64_oplus From 1d0fe3fb5d4be366c5ba236c8ad230768e1a5c9f Mon Sep 17 00:00:00 2001 From: Tsuchiya Yuto Date: Wed, 1 Dec 2021 15:19:04 +0100 Subject: [PATCH 3734/4345] media: atomisp: fix "variable dereferenced before check 'asd'" commit ac56760a8bbb4e654b2fd54e5de79dd5d72f937d upstream. There are two occurrences where the variable 'asd' is dereferenced before check. Fix this issue by using the variable after the check. Link: https://lore.kernel.org/linux-media/20211122074122.GA6581@kili/ Link: https://lore.kernel.org/linux-media/20211201141904.47231-1-kitakar@gmail.com Reported-by: Dan Carpenter Signed-off-by: Tsuchiya Yuto Signed-off-by: Mauro Carvalho Chehab Igned-off-by: Anastasia Belova Signed-off-by: Greg Kroah-Hartman --- drivers/staging/media/atomisp/pci/atomisp_cmd.c | 3 ++- drivers/staging/media/atomisp/pci/atomisp_ioctl.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.c b/drivers/staging/media/atomisp/pci/atomisp_cmd.c index 20c19e08968e..613bd9620224 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_cmd.c +++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.c @@ -5243,7 +5243,7 @@ static int atomisp_set_fmt_to_isp(struct video_device *vdev, int (*configure_pp_input)(struct atomisp_sub_device *asd, unsigned int width, unsigned int height) = configure_pp_input_nop; - u16 stream_index = atomisp_source_pad_to_stream_id(asd, source_pad); + u16 stream_index; const struct atomisp_in_fmt_conv *fc; int ret, i; @@ -5252,6 +5252,7 @@ static int atomisp_set_fmt_to_isp(struct video_device *vdev, __func__, vdev->name); return -EINVAL; } + stream_index = atomisp_source_pad_to_stream_id(asd, source_pad); v4l2_fh_init(&fh.vfh, vdev); diff --git a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c index 8a0648fd7c81..4615e4cae718 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c +++ b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c @@ -1123,7 +1123,7 @@ int __atomisp_reqbufs(struct file *file, void *fh, struct ia_css_frame *frame; struct videobuf_vmalloc_memory *vm_mem; u16 source_pad = atomisp_subdev_source_pad(vdev); - u16 stream_id = atomisp_source_pad_to_stream_id(asd, source_pad); + u16 stream_id; int ret = 0, i = 0; if (!asd) { @@ -1131,6 +1131,7 @@ int __atomisp_reqbufs(struct file *file, void *fh, __func__, vdev->name); return -EINVAL; } + stream_id = atomisp_source_pad_to_stream_id(asd, source_pad); if (req->count == 0) { mutex_lock(&pipe->capq.vb_lock); From 8667f7113107c8fab07ddd088e16c6a10d6d395f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 15 Jun 2023 22:33:55 +0200 Subject: [PATCH 3735/4345] x86/smp: Use dedicated cache-line for mwait_play_dead() commit f9c9987bf52f4e42e940ae217333ebb5a4c3b506 upstream. Monitoring idletask::thread_info::flags in mwait_play_dead() has been an obvious choice as all what is needed is a cache line which is not written by other CPUs. But there is a use case where a "dead" CPU needs to be brought out of MWAIT: kexec(). This is required as kexec() can overwrite text, pagetables, stacks and the monitored cacheline of the original kernel. The latter causes MWAIT to resume execution which obviously causes havoc on the kexec kernel which results usually in triple faults. Use a dedicated per CPU storage to prepare for that. Signed-off-by: Thomas Gleixner Reviewed-by: Ashok Raj Reviewed-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615193330.434553750@linutronix.de Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/smpboot.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index bda89ecc7799..d2403da17842 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -100,6 +100,17 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); +struct mwait_cpu_dead { + unsigned int control; + unsigned int status; +}; + +/* + * Cache line aligned data for mwait_play_dead(). Separate on purpose so + * that it's unlikely to be touched by other CPUs. + */ +static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead); + /* Logical package management. We might want to allocate that dynamically */ unsigned int __max_logical_packages __read_mostly; EXPORT_SYMBOL(__max_logical_packages); @@ -1674,10 +1685,10 @@ EXPORT_SYMBOL_GPL(cond_wakeup_cpu0); */ static inline void mwait_play_dead(void) { + struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead); unsigned int eax, ebx, ecx, edx; unsigned int highest_cstate = 0; unsigned int highest_subcstate = 0; - void *mwait_ptr; int i; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || @@ -1712,13 +1723,6 @@ static inline void mwait_play_dead(void) (highest_subcstate - 1); } - /* - * This should be a memory location in a cache line which is - * unlikely to be touched by other processors. The actual - * content is immaterial as it is not actually modified in any way. - */ - mwait_ptr = ¤t_thread_info()->flags; - wbinvd(); while (1) { @@ -1730,9 +1734,9 @@ static inline void mwait_play_dead(void) * case where we return around the loop. */ mb(); - clflush(mwait_ptr); + clflush(md); mb(); - __monitor(mwait_ptr, 0, 0); + __monitor(md, 0, 0); mb(); __mwait(eax, 0); From 02fbf62df99f208454097404567da5335bb5b55f Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 7 Jun 2023 09:27:08 +0200 Subject: [PATCH 3736/4345] can: isotp: isotp_sendmsg(): fix return error fix on TX path commit e38910c0072b541a91954682c8b074a93e57c09b upstream. With commit d674a8f123b4 ("can: isotp: isotp_sendmsg(): fix return error on FC timeout on TX path") the missing correct return value in the case of a protocol error was introduced. But the way the error value has been read and sent to the user space does not follow the common scheme to clear the error after reading which is provided by the sock_error() function. This leads to an error report at the following write() attempt although everything should be working. Fixes: d674a8f123b4 ("can: isotp: isotp_sendmsg(): fix return error on FC timeout on TX path") Reported-by: Carsten Schmidt Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20230607072708.38809-1-socketcan@hartkopp.net Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/isotp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/can/isotp.c b/net/can/isotp.c index 4fcd8162fad4..16ebc187af1c 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -990,8 +990,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); - if (sk->sk_err) - return -sk->sk_err; + err = sock_error(sk); + if (err) + return err; } return size; From 5b813734a0d221189f1430f89edff4c275f30167 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 3 May 2021 13:57:34 +0200 Subject: [PATCH 3737/4345] video: imsttfb: check for ioremap() failures commit 13b7c0390a5d3840e1e2cda8f44a310fdbb982de upstream. We should check if ioremap() were to somehow fail in imsttfb_probe() and handle the unwinding of the resources allocated here properly. Ideally if anyone cares about this driver (it's for a PowerMac era PCI display card), they wouldn't even be using fbdev anymore. Or the devm_* apis could be used, but that's just extra work for diminishing returns... Cc: Finn Thain Cc: Bartlomiej Zolnierkiewicz Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20210503115736.2104747-68-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/imsttfb.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c index e04411701ec8..16f272a50811 100644 --- a/drivers/video/fbdev/imsttfb.c +++ b/drivers/video/fbdev/imsttfb.c @@ -1469,6 +1469,7 @@ static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct imstt_par *par; struct fb_info *info; struct device_node *dp; + int ret = -ENOMEM; dp = pci_device_to_OF_node(pdev); if(dp) @@ -1504,23 +1505,37 @@ static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) default: printk(KERN_INFO "imsttfb: Device 0x%x unknown, " "contact maintainer.\n", pdev->device); - release_mem_region(addr, size); - framebuffer_release(info); - return -ENODEV; + ret = -ENODEV; + goto error; } info->fix.smem_start = addr; info->screen_base = (__u8 *)ioremap(addr, par->ramdac == IBM ? 0x400000 : 0x800000); + if (!info->screen_base) + goto error; info->fix.mmio_start = addr + 0x800000; par->dc_regs = ioremap(addr + 0x800000, 0x1000); + if (!par->dc_regs) + goto error; par->cmap_regs_phys = addr + 0x840000; par->cmap_regs = (__u8 *)ioremap(addr + 0x840000, 0x1000); + if (!par->cmap_regs) + goto error; info->pseudo_palette = par->palette; init_imstt(info); pci_set_drvdata(pdev, info); return 0; + +error: + if (par->dc_regs) + iounmap(par->dc_regs); + if (info->screen_base) + iounmap(info->screen_base); + release_mem_region(addr, size); + framebuffer_release(info); + return ret; } static void imsttfb_remove(struct pci_dev *pdev) From 2bf70b88cc358a437db376826f92c8dcf9c23587 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Thu, 27 Apr 2023 11:08:41 +0800 Subject: [PATCH 3738/4345] fbdev: imsttfb: Fix use after free bug in imsttfb_probe commit c75f5a55061091030a13fef71b9995b89bc86213 upstream. A use-after-free bug may occur if init_imstt invokes framebuffer_release and free the info ptr. The caller, imsttfb_probe didn't notice that and still keep the ptr as private data in pdev. If we remove the driver which will call imsttfb_remove to make cleanup, UAF happens. Fix it by return error code if bad case happens in init_imstt. Signed-off-by: Zheng Wang Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/imsttfb.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c index 16f272a50811..1b2fb8ed7623 100644 --- a/drivers/video/fbdev/imsttfb.c +++ b/drivers/video/fbdev/imsttfb.c @@ -1346,7 +1346,7 @@ static const struct fb_ops imsttfb_ops = { .fb_ioctl = imsttfb_ioctl, }; -static void init_imstt(struct fb_info *info) +static int init_imstt(struct fb_info *info) { struct imstt_par *par = info->par; __u32 i, tmp, *ip, *end; @@ -1419,7 +1419,7 @@ static void init_imstt(struct fb_info *info) || !(compute_imstt_regvals(par, info->var.xres, info->var.yres))) { printk("imsttfb: %ux%ux%u not supported\n", info->var.xres, info->var.yres, info->var.bits_per_pixel); framebuffer_release(info); - return; + return -ENODEV; } sprintf(info->fix.id, "IMS TT (%s)", par->ramdac == IBM ? "IBM" : "TVP"); @@ -1455,12 +1455,13 @@ static void init_imstt(struct fb_info *info) if (register_framebuffer(info) < 0) { framebuffer_release(info); - return; + return -ENODEV; } tmp = (read_reg_le32(par->dc_regs, SSTATUS) & 0x0f00) >> 8; fb_info(info, "%s frame buffer; %uMB vram; chip version %u\n", info->fix.id, info->fix.smem_len >> 20, tmp); + return 0; } static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -1523,10 +1524,10 @@ static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!par->cmap_regs) goto error; info->pseudo_palette = par->palette; - init_imstt(info); - - pci_set_drvdata(pdev, info); - return 0; + ret = init_imstt(info); + if (!ret) + pci_set_drvdata(pdev, info); + return ret; error: if (par->dc_regs) From 9598a647ecc8f300b0540abf9d3b3439859d163b Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Thu, 8 Jun 2023 14:38:28 -0700 Subject: [PATCH 3739/4345] HID: wacom: Use ktime_t rather than int when dealing with timestamps commit 9a6c0e28e215535b2938c61ded54603b4e5814c5 upstream. Code which interacts with timestamps needs to use the ktime_t type returned by functions like ktime_get. The int type does not offer enough space to store these values, and attempting to use it is a recipe for problems. In this particular case, overflows would occur when calculating/storing timestamps leading to incorrect values being reported to userspace. In some cases these bad timestamps cause input handling in userspace to appear hung. Link: https://gitlab.freedesktop.org/libinput/libinput/-/issues/901 Fixes: 17d793f3ed53 ("HID: wacom: insert timestamp to packed Bluetooth (BT) events") CC: stable@vger.kernel.org Signed-off-by: Jason Gerecke Reviewed-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20230608213828.2108-1-jason.gerecke@wacom.com Signed-off-by: Benjamin Tissoires Signed-off-by: Greg Kroah-Hartman --- drivers/hid/wacom_wac.c | 6 +++--- drivers/hid/wacom_wac.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 1bfcc94c1d23..de6fe9866870 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1307,7 +1307,7 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) struct input_dev *pen_input = wacom->pen_input; unsigned char *data = wacom->data; int number_of_valid_frames = 0; - int time_interval = 15000000; + ktime_t time_interval = 15000000; ktime_t time_packet_received = ktime_get(); int i; @@ -1341,7 +1341,7 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) if (number_of_valid_frames) { if (wacom->hid_data.time_delayed) time_interval = ktime_get() - wacom->hid_data.time_delayed; - time_interval /= number_of_valid_frames; + time_interval = div_u64(time_interval, number_of_valid_frames); wacom->hid_data.time_delayed = time_packet_received; } @@ -1352,7 +1352,7 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) bool range = frame[0] & 0x20; bool invert = frame[0] & 0x10; int frames_number_reversed = number_of_valid_frames - i - 1; - int event_timestamp = time_packet_received - frames_number_reversed * time_interval; + ktime_t event_timestamp = time_packet_received - frames_number_reversed * time_interval; if (!valid) continue; diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index 88badfbae999..166731292c35 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -320,7 +320,7 @@ struct hid_data { int bat_connected; int ps_connected; bool pad_input_event_flag; - int time_delayed; + ktime_t time_delayed; }; struct wacom_remote_data { From 02a4c4e225f4185fdc065c43167892136c734d11 Mon Sep 17 00:00:00 2001 From: Mike Hommey Date: Sun, 18 Jun 2023 08:09:57 +0900 Subject: [PATCH 3740/4345] HID: logitech-hidpp: add HIDPP_QUIRK_DELAYED_INIT for the T651. commit 5fe251112646d8626818ea90f7af325bab243efa upstream. commit 498ba2069035 ("HID: logitech-hidpp: Don't restart communication if not necessary") put restarting communication behind that flag, and this was apparently necessary on the T651, but the flag was not set for it. Fixes: 498ba2069035 ("HID: logitech-hidpp: Don't restart communication if not necessary") Cc: stable@vger.kernel.org Signed-off-by: Mike Hommey Link: https://lore.kernel.org/r/20230617230957.6mx73th4blv7owqk@glandium.org Signed-off-by: Benjamin Tissoires Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-logitech-hidpp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 2e32a21bbcbf..6ac0c2d9a147 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -4009,7 +4009,7 @@ static const struct hid_device_id hidpp_devices[] = { { /* wireless touchpad T651 */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_T651), - .driver_data = HIDPP_QUIRK_CLASS_WTP }, + .driver_data = HIDPP_QUIRK_CLASS_WTP | HIDPP_QUIRK_DELAYED_INIT }, { /* Mouse Logitech Anywhere MX */ LDJ_DEVICE(0x1017), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_1P0 }, { /* Mouse Logitech Cube */ From 649104c834baf7f189bfdc7757754a0d88794bbc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo?= Date: Thu, 25 May 2023 14:18:11 +0200 Subject: [PATCH 3741/4345] Revert "thermal/drivers/mediatek: Use devm_of_iomap to avoid resource leak in mtk_thermal_probe" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 86edac7d3888c715fe3a81bd61f3617ecfe2e1dd upstream. This reverts commit f05c7b7d9ea9477fcc388476c6f4ade8c66d2d26. That change was causing a regression in the generic-adc-thermal-probed bootrr test as reported in the kernelci-results list [1]. A proper rework will take longer, so revert it for now. [1] https://groups.io/g/kernelci-results/message/42660 Fixes: f05c7b7d9ea9 ("thermal/drivers/mediatek: Use devm_of_iomap to avoid resource leak in mtk_thermal_probe") Signed-off-by: Ricardo Cañuelo Suggested-by: AngeloGioacchino Del Regno Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230525121811.3360268-1-ricardo.canuelo@collabora.com Signed-off-by: Greg Kroah-Hartman --- drivers/thermal/mtk_thermal.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c index 9fe169dbed88..0bd7aa564bc2 100644 --- a/drivers/thermal/mtk_thermal.c +++ b/drivers/thermal/mtk_thermal.c @@ -1026,12 +1026,7 @@ static int mtk_thermal_probe(struct platform_device *pdev) return -ENODEV; } - auxadc_base = devm_of_iomap(&pdev->dev, auxadc, 0, NULL); - if (IS_ERR(auxadc_base)) { - of_node_put(auxadc); - return PTR_ERR(auxadc_base); - } - + auxadc_base = of_iomap(auxadc, 0); auxadc_phys_base = of_get_phys_base(auxadc); of_node_put(auxadc); @@ -1047,12 +1042,7 @@ static int mtk_thermal_probe(struct platform_device *pdev) return -ENODEV; } - apmixed_base = devm_of_iomap(&pdev->dev, apmixedsys, 0, NULL); - if (IS_ERR(apmixed_base)) { - of_node_put(apmixedsys); - return PTR_ERR(apmixed_base); - } - + apmixed_base = of_iomap(apmixedsys, 0); apmixed_phys_base = of_get_phys_base(apmixedsys); of_node_put(apmixedsys); From c484b65f93e0fefadd4b0b3bdeff9a2873838819 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Mon, 15 May 2023 19:32:16 +0200 Subject: [PATCH 3742/4345] scripts/tags.sh: Resolve gtags empty index generation commit e1b37563caffc410bb4b55f153ccb14dede66815 upstream. gtags considers any file outside of its current working directory "outside the source tree" and refuses to index it. For O= kernel builds, or when "make" is invoked from a directory other then the kernel source tree, gtags ignores the entire kernel source and generates an empty index. Force-set gtags current working directory to the kernel source tree. Due to commit 9da0763bdd82 ("kbuild: Use relative path when building in a subdir of the source tree"), if the kernel build is done in a sub-directory of the kernel source tree, the kernel Makefile will set the kernel's $srctree to ".." for shorter compile-time and run-time warnings. Consequently, the list of files to be indexed will be in the "../*" form, rendering all such paths invalid once gtags switches to the kernel source tree as its current working directory. If gtags indexing is requested and the build directory is not the kernel source tree, index all files in absolute-path form. Note, indexing in absolute-path form will not affect the generated index, as paths in gtags indices are always relative to the gtags "root directory" anyway (as evidenced by "gtags --dump"). Signed-off-by: Ahmed S. Darwish Cc: Signed-off-by: Masahiro Yamada Signed-off-by: Greg Kroah-Hartman --- scripts/tags.sh | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/scripts/tags.sh b/scripts/tags.sh index b82aebb0c995..d17801c9d85a 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -32,6 +32,13 @@ else ignore="$ignore ( -path ${tree}tools ) -prune -o" fi +# gtags(1) refuses to index any file outside of its current working dir. +# If gtags indexing is requested and the build output directory is not +# the kernel source tree, index all files in absolute-path form. +if [[ "$1" == "gtags" && -n "${tree}" ]]; then + tree=$(realpath "$tree")/ +fi + # Detect if ALLSOURCE_ARCHS is set. If not, we assume SRCARCH if [ "${ALLSOURCE_ARCHS}" = "" ]; then ALLSOURCE_ARCHS=${SRCARCH} @@ -131,7 +138,7 @@ docscope() dogtags() { - all_target_sources | gtags -i -f - + all_target_sources | gtags -i -C "${tree:-.}" -f - "$PWD" } # Basic regular expressions with an optional /kind-spec/ for ctags and From 0336c8f072237e6a0fdacdde3de7f02abd1bc0b3 Mon Sep 17 00:00:00 2001 From: Bas Nieuwenhuizen Date: Sat, 13 May 2023 14:51:00 +0200 Subject: [PATCH 3743/4345] drm/amdgpu: Validate VM ioctl flags. commit a2b308044dcaca8d3e580959a4f867a1d5c37fac upstream. None have been defined yet, so reject anybody setting any. Mesa sets it to 0 anyway. Signed-off-by: Bas Nieuwenhuizen Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 45b1f00c5968..c705ce11c436 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3252,6 +3252,10 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) long timeout = msecs_to_jiffies(2000); int r; + /* No valid flags defined yet */ + if (args->in.flags) + return -EINVAL; + switch (args->in.op) { case AMDGPU_VM_OP_RESERVE_VMID: /* We only have requirement to reserve vmid from gfxhub */ From f70407e8e0272e00d133c5e039168ff1bae6bcac Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 14 Mar 2023 19:51:59 +1100 Subject: [PATCH 3744/4345] nubus: Partially revert proc_create_single_data() conversion commit 0e96647cff9224db564a1cee6efccb13dbe11ee2 upstream. The conversion to proc_create_single_data() introduced a regression whereby reading a file in /proc/bus/nubus results in a seg fault: # grep -r . /proc/bus/nubus/e/ Data read fault at 0x00000020 in Super Data (pc=0x1074c2) BAD KERNEL BUSERR Oops: 00000000 Modules linked in: PC: [<001074c2>] PDE_DATA+0xc/0x16 SR: 2010 SP: 38284958 a2: 01152370 d0: 00000001 d1: 01013000 d2: 01002790 d3: 00000000 d4: 00000001 d5: 0008ce2e a0: 00000000 a1: 00222a40 Process grep (pid: 45, task=142f8727) Frame format=B ssw=074d isc=2008 isb=4e5e daddr=00000020 dobuf=01199e70 baddr=001074c8 dibuf=ffffffff ver=f Stack from 01199e48: 01199e70 00222a58 01002790 00000000 011a3000 01199eb0 015000c0 00000000 00000000 01199ec0 01199ec0 000d551a 011a3000 00000001 00000000 00018000 d003f000 00000003 00000001 0002800d 01052840 01199fa8 c01f8000 00000000 00000029 0b532b80 00000000 00000000 00000029 0b532b80 01199ee4 00103640 011198c0 d003f000 00018000 01199fa8 00000000 011198c0 00000000 01199f4c 000b3344 011198c0 d003f000 00018000 01199fa8 00000000 00018000 011198c0 Call Trace: [<00222a58>] nubus_proc_rsrc_show+0x18/0xa0 [<000d551a>] seq_read+0xc4/0x510 [<00018000>] fp_fcos+0x2/0x82 [<0002800d>] __sys_setreuid+0x115/0x1c6 [<00103640>] proc_reg_read+0x5c/0xb0 [<00018000>] fp_fcos+0x2/0x82 [<000b3344>] __vfs_read+0x2c/0x13c [<00018000>] fp_fcos+0x2/0x82 [<00018000>] fp_fcos+0x2/0x82 [<000b8aa2>] sys_statx+0x60/0x7e [<000b34b6>] vfs_read+0x62/0x12a [<00018000>] fp_fcos+0x2/0x82 [<00018000>] fp_fcos+0x2/0x82 [<000b39c2>] ksys_read+0x48/0xbe [<00018000>] fp_fcos+0x2/0x82 [<000b3a4e>] sys_read+0x16/0x1a [<00018000>] fp_fcos+0x2/0x82 [<00002b84>] syscall+0x8/0xc [<00018000>] fp_fcos+0x2/0x82 [<0000c016>] not_ext+0xa/0x18 Code: 4e5e 4e75 4e56 0000 206e 0008 2068 ffe8 <2068> 0020 2008 4e5e 4e75 4e56 0000 2f0b 206e 0008 2068 0004 2668 0020 206b ffe8 Disabling lock debugging due to kernel taint Segmentation fault The proc_create_single_data() conversion does not work because single_open(file, nubus_proc_rsrc_show, PDE_DATA(inode)) is not equivalent to the original code. Fixes: 3f3942aca6da ("proc: introduce proc_create_single{,_data}") Cc: Christoph Hellwig Cc: stable@vger.kernel.org # 5.6+ Signed-off-by: Finn Thain Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/d4e2a586e793cc8d9442595684ab8a077c0fe726.1678783919.git.fthain@linux-m68k.org Signed-off-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman --- drivers/nubus/proc.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/drivers/nubus/proc.c b/drivers/nubus/proc.c index 88e1f9a0faaf..78cf0e7b53d5 100644 --- a/drivers/nubus/proc.c +++ b/drivers/nubus/proc.c @@ -137,6 +137,18 @@ static int nubus_proc_rsrc_show(struct seq_file *m, void *v) return 0; } +static int nubus_rsrc_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, nubus_proc_rsrc_show, inode); +} + +static const struct proc_ops nubus_rsrc_proc_ops = { + .proc_open = nubus_rsrc_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + void nubus_proc_add_rsrc_mem(struct proc_dir_entry *procdir, const struct nubus_dirent *ent, unsigned int size) @@ -152,8 +164,8 @@ void nubus_proc_add_rsrc_mem(struct proc_dir_entry *procdir, pde_data = nubus_proc_alloc_pde_data(nubus_dirptr(ent), size); else pde_data = NULL; - proc_create_single_data(name, S_IFREG | 0444, procdir, - nubus_proc_rsrc_show, pde_data); + proc_create_data(name, S_IFREG | 0444, procdir, + &nubus_rsrc_proc_ops, pde_data); } void nubus_proc_add_rsrc(struct proc_dir_entry *procdir, @@ -166,9 +178,9 @@ void nubus_proc_add_rsrc(struct proc_dir_entry *procdir, return; snprintf(name, sizeof(name), "%x", ent->type); - proc_create_single_data(name, S_IFREG | 0444, procdir, - nubus_proc_rsrc_show, - nubus_proc_alloc_pde_data(data, 0)); + proc_create_data(name, S_IFREG | 0444, procdir, + &nubus_rsrc_proc_ops, + nubus_proc_alloc_pde_data(data, 0)); } /* From 1a82005f3f636e31e370f9d878ef2ca6e61b839f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:56:12 +0200 Subject: [PATCH 3745/4345] fs: pipe: reveal missing function protoypes [ Upstream commit 247c8d2f9837a3e29e3b6b7a4aa9c36c37659dd4 ] A couple of functions from fs/pipe.c are used both internally and for the watch queue code, but the declaration is only visible when the latter is enabled: fs/pipe.c:1254:5: error: no previous prototype for 'pipe_resize_ring' fs/pipe.c:758:15: error: no previous prototype for 'account_pipe_buffers' fs/pipe.c:764:6: error: no previous prototype for 'too_many_pipe_buffers_soft' fs/pipe.c:771:6: error: no previous prototype for 'too_many_pipe_buffers_hard' fs/pipe.c:777:6: error: no previous prototype for 'pipe_is_unprivileged_user' Make the visible unconditionally to avoid these warnings. Fixes: c73be61cede5 ("pipe: Add general notification queue support") Signed-off-by: Arnd Bergmann Message-Id: <20230516195629.551602-1-arnd@kernel.org> Signed-off-by: Christian Brauner Signed-off-by: Sasha Levin --- include/linux/pipe_fs_i.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index c0b6ec6bf65b..ef236dbaa294 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -256,18 +256,14 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -#ifdef CONFIG_WATCH_QUEUE unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new); bool too_many_pipe_buffers_soft(unsigned long user_bufs); bool too_many_pipe_buffers_hard(unsigned long user_bufs); bool pipe_is_unprivileged_user(void); -#endif /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ -#ifdef CONFIG_WATCH_QUEUE int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); -#endif long pipe_fcntl(struct file *, unsigned int, unsigned long arg); struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); From 3db97cc79b828d99a2dc9298050733c12a8776b3 Mon Sep 17 00:00:00 2001 From: Shawn Wang Date: Mon, 15 May 2023 14:04:48 +0800 Subject: [PATCH 3746/4345] x86/resctrl: Only show tasks' pid in current pid namespace [ Upstream commit 2997d94b5dd0e8b10076f5e0b6f18410c73e28bd ] When writing a task id to the "tasks" file in an rdtgroup, rdtgroup_tasks_write() treats the pid as a number in the current pid namespace. But when reading the "tasks" file, rdtgroup_tasks_show() shows the list of global pids from the init namespace, which is confusing and incorrect. To be more robust, let the "tasks" file only show pids in the current pid namespace. Fixes: e02737d5b826 ("x86/intel_rdt: Add tasks files") Signed-off-by: Shawn Wang Signed-off-by: Borislav Petkov (AMD) Acked-by: Reinette Chatre Acked-by: Fenghua Yu Tested-by: Reinette Chatre Link: https://lore.kernel.org/all/20230116071246.97717-1-shawnwang@linux.alibaba.com/ Signed-off-by: Sasha Levin --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 1a943743cfe4..1e73b6fae3b4 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -715,11 +715,15 @@ unlock: static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) { struct task_struct *p, *t; + pid_t pid; rcu_read_lock(); for_each_process_thread(p, t) { - if (is_closid_match(t, r) || is_rmid_match(t, r)) - seq_printf(s, "%d\n", t->pid); + if (is_closid_match(t, r) || is_rmid_match(t, r)) { + pid = task_pid_vnr(t); + if (pid) + seq_printf(s, "%d\n", pid); + } } rcu_read_unlock(); } From 8563b58a4360e648ce18f0e98a75a4be51667431 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Sat, 27 May 2023 17:19:04 +0800 Subject: [PATCH 3747/4345] blk-iocost: use spin_lock_irqsave in adjust_inuse_and_calc_cost [ Upstream commit 8d211554679d0b23702bd32ba04aeac0c1c4f660 ] adjust_inuse_and_calc_cost() use spin_lock_irq() and IRQ will be enabled when unlock. DEADLOCK might happen if we have held other locks and disabled IRQ before invoking it. Fix it by using spin_lock_irqsave() instead, which can keep IRQ state consistent with before when unlock. ================================ WARNING: inconsistent lock state 5.10.0-02758-g8e5f91fd772f #26 Not tainted -------------------------------- inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. kworker/2:3/388 [HC0[0]:SC0[0]:HE0:SE1] takes: ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: spin_lock_irq ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: bfq_bio_merge+0x141/0x390 {IN-HARDIRQ-W} state was registered at: __lock_acquire+0x3d7/0x1070 lock_acquire+0x197/0x4a0 __raw_spin_lock_irqsave _raw_spin_lock_irqsave+0x3b/0x60 bfq_idle_slice_timer_body bfq_idle_slice_timer+0x53/0x1d0 __run_hrtimer+0x477/0xa70 __hrtimer_run_queues+0x1c6/0x2d0 hrtimer_interrupt+0x302/0x9e0 local_apic_timer_interrupt __sysvec_apic_timer_interrupt+0xfd/0x420 run_sysvec_on_irqstack_cond sysvec_apic_timer_interrupt+0x46/0xa0 asm_sysvec_apic_timer_interrupt+0x12/0x20 irq event stamp: 837522 hardirqs last enabled at (837521): [] __raw_spin_unlock_irqrestore hardirqs last enabled at (837521): [] _raw_spin_unlock_irqrestore+0x3d/0x40 hardirqs last disabled at (837522): [] __raw_spin_lock_irq hardirqs last disabled at (837522): [] _raw_spin_lock_irq+0x43/0x50 softirqs last enabled at (835852): [] __do_softirq+0x558/0x8ec softirqs last disabled at (835845): [] asm_call_irq_on_stack+0xf/0x20 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&bfqd->lock); lock(&bfqd->lock); *** DEADLOCK *** 3 locks held by kworker/2:3/388: #0: ffff888107af0f38 ((wq_completion)kthrotld){+.+.}-{0:0}, at: process_one_work+0x742/0x13f0 #1: ffff8881176bfdd8 ((work_completion)(&td->dispatch_work)){+.+.}-{0:0}, at: process_one_work+0x777/0x13f0 #2: ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: spin_lock_irq #2: ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: bfq_bio_merge+0x141/0x390 stack backtrace: CPU: 2 PID: 388 Comm: kworker/2:3 Not tainted 5.10.0-02758-g8e5f91fd772f #26 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 Workqueue: kthrotld blk_throtl_dispatch_work_fn Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x107/0x167 print_usage_bug valid_state mark_lock_irq.cold+0x32/0x3a mark_lock+0x693/0xbc0 mark_held_locks+0x9e/0xe0 __trace_hardirqs_on_caller lockdep_hardirqs_on_prepare.part.0+0x151/0x360 trace_hardirqs_on+0x5b/0x180 __raw_spin_unlock_irq _raw_spin_unlock_irq+0x24/0x40 spin_unlock_irq adjust_inuse_and_calc_cost+0x4fb/0x970 ioc_rqos_merge+0x277/0x740 __rq_qos_merge+0x62/0xb0 rq_qos_merge bio_attempt_back_merge+0x12c/0x4a0 blk_mq_sched_try_merge+0x1b6/0x4d0 bfq_bio_merge+0x24a/0x390 __blk_mq_sched_bio_merge+0xa6/0x460 blk_mq_sched_bio_merge blk_mq_submit_bio+0x2e7/0x1ee0 __submit_bio_noacct_mq+0x175/0x3b0 submit_bio_noacct+0x1fb/0x270 blk_throtl_dispatch_work_fn+0x1ef/0x2b0 process_one_work+0x83e/0x13f0 process_scheduled_works worker_thread+0x7e3/0xd80 kthread+0x353/0x470 ret_from_fork+0x1f/0x30 Fixes: b0853ab4a238 ("blk-iocost: revamp in-period donation snapbacks") Signed-off-by: Li Nan Acked-by: Tejun Heo Reviewed-by: Yu Kuai Link: https://lore.kernel.org/r/20230527091904.3001833-1-linan666@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/blk-iocost.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 105ad23dff06..7ba7c4e4e4c9 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2426,6 +2426,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, u32 hwi, adj_step; s64 margin; u64 cost, new_inuse; + unsigned long flags; current_hweight(iocg, NULL, &hwi); old_hwi = hwi; @@ -2444,11 +2445,11 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, iocg->inuse == iocg->active) return cost; - spin_lock_irq(&ioc->lock); + spin_lock_irqsave(&ioc->lock, flags); /* we own inuse only when @iocg is in the normal active state */ if (iocg->abs_vdebt || list_empty(&iocg->active_list)) { - spin_unlock_irq(&ioc->lock); + spin_unlock_irqrestore(&ioc->lock, flags); return cost; } @@ -2469,7 +2470,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, } while (time_after64(vtime + cost, now->vnow) && iocg->inuse != iocg->active); - spin_unlock_irq(&ioc->lock); + spin_unlock_irqrestore(&ioc->lock, flags); TRACE_IOCG_PATH(inuse_adjust, iocg, now, old_inuse, iocg->inuse, old_hwi, hwi); From 39fa14e824acfd470db4f42c354297456bd82b53 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Mon, 15 May 2023 21:48:05 +0800 Subject: [PATCH 3748/4345] md/raid10: check slab-out-of-bounds in md_bitmap_get_counter [ Upstream commit 301867b1c16805aebbc306aafa6ecdc68b73c7e5 ] If we write a large number to md/bitmap_set_bits, md_bitmap_checkpage() will return -EINVAL because 'page >= bitmap->pages', but the return value was not checked immediately in md_bitmap_get_counter() in order to set *blocks value and slab-out-of-bounds occurs. Move check of 'page >= bitmap->pages' to md_bitmap_get_counter() and return directly if true. Fixes: ef4256733506 ("md/bitmap: optimise scanning of empty bitmaps.") Signed-off-by: Li Nan Reviewed-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230515134808.3936750-2-linan666@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/md-bitmap.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 20afc0aec177..f843ade442de 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -54,14 +54,7 @@ __acquires(bitmap->lock) { unsigned char *mappage; - if (page >= bitmap->pages) { - /* This can happen if bitmap_start_sync goes beyond - * End-of-device while looking for a whole page. - * It is harmless. - */ - return -EINVAL; - } - + WARN_ON_ONCE(page >= bitmap->pages); if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */ return 0; @@ -1365,6 +1358,14 @@ __acquires(bitmap->lock) sector_t csize; int err; + if (page >= bitmap->pages) { + /* + * This can happen if bitmap_start_sync goes beyond + * End-of-device while looking for a whole page or + * user set a huge number to sysfs bitmap_set_bits. + */ + return NULL; + } err = md_bitmap_checkpage(bitmap, page, create, 0); if (bitmap->bp[page].hijacked || From b3a0bc4a01fa8dc308bf04df7b76358c31fb0651 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Mon, 22 May 2023 15:25:33 +0800 Subject: [PATCH 3749/4345] md/raid10: fix overflow of md/safe_mode_delay [ Upstream commit 6beb489b2eed25978523f379a605073f99240c50 ] There is no input check when echo md/safe_mode_delay in safe_delay_store(). And msec might also overflow when HZ < 1000 in safe_delay_show(), Fix it by checking overflow in safe_delay_store() and use unsigned long conversion in safe_delay_show(). Fixes: 72e02075a33f ("md: factor out parsing of fixed-point numbers") Signed-off-by: Li Nan Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230522072535.1523740-2-linan666@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/md.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 1553c2495841..204838a6d443 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3890,8 +3890,9 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale) static ssize_t safe_delay_show(struct mddev *mddev, char *page) { - int msec = (mddev->safemode_delay*1000)/HZ; - return sprintf(page, "%d.%03d\n", msec/1000, msec%1000); + unsigned int msec = ((unsigned long)mddev->safemode_delay*1000)/HZ; + + return sprintf(page, "%u.%03u\n", msec/1000, msec%1000); } static ssize_t safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len) @@ -3903,7 +3904,7 @@ safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len) return -EINVAL; } - if (strict_strtoul_scaled(cbuf, &msec, 3) < 0) + if (strict_strtoul_scaled(cbuf, &msec, 3) < 0 || msec > UINT_MAX / HZ) return -EINVAL; if (msec == 0) mddev->safemode_delay = 0; From b1d8f38310bce3282374983b229d94edbaf1e570 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Mon, 22 May 2023 15:25:34 +0800 Subject: [PATCH 3750/4345] md/raid10: fix wrong setting of max_corr_read_errors [ Upstream commit f8b20a405428803bd9881881d8242c9d72c6b2b2 ] There is no input check when echo md/max_read_errors and overflow might occur. Add check of input number. Fixes: 1e50915fe0bb ("raid: improve MD/raid10 handling of correctable read errors.") Signed-off-by: Li Nan Reviewed-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230522072535.1523740-3-linan666@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/md.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/md.c b/drivers/md/md.c index 204838a6d443..bbf39abc32b7 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4574,6 +4574,8 @@ max_corrected_read_errors_store(struct mddev *mddev, const char *buf, size_t len rv = kstrtouint(buf, 10, &n); if (rv < 0) return rv; + if (n > INT_MAX) + return -EINVAL; atomic_set(&mddev->max_corr_read_errors, n); return len; } From 2990e2ece18dd4cca71b3109c80517ad94adb065 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Sat, 27 May 2023 15:22:15 +0800 Subject: [PATCH 3751/4345] md/raid10: fix null-ptr-deref of mreplace in raid10_sync_request [ Upstream commit 34817a2441747b48e444cb0e05d84e14bc9443da ] There are two check of 'mreplace' in raid10_sync_request(). In the first check, 'need_replace' will be set and 'mreplace' will be used later if no-Faulty 'mreplace' exists, In the second check, 'mreplace' will be set to NULL if it is Faulty, but 'need_replace' will not be changed accordingly. null-ptr-deref occurs if Faulty is set between two check. Fix it by merging two checks into one. And replace 'need_replace' with 'mreplace' because their values are always the same. Fixes: ee37d7314a32 ("md/raid10: Fix raid10 replace hang when new added disk faulty") Signed-off-by: Li Nan Reviewed-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230527072218.2365857-2-linan666@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/raid10.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 6a0459f9fafb..01680029f0de 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3037,7 +3037,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, int must_sync; int any_working; int need_recover = 0; - int need_replace = 0; struct raid10_info *mirror = &conf->mirrors[i]; struct md_rdev *mrdev, *mreplace; @@ -3049,11 +3048,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, !test_bit(Faulty, &mrdev->flags) && !test_bit(In_sync, &mrdev->flags)) need_recover = 1; - if (mreplace != NULL && - !test_bit(Faulty, &mreplace->flags)) - need_replace = 1; + if (mreplace && test_bit(Faulty, &mreplace->flags)) + mreplace = NULL; - if (!need_recover && !need_replace) { + if (!need_recover && !mreplace) { rcu_read_unlock(); continue; } @@ -3069,8 +3067,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, rcu_read_unlock(); continue; } - if (mreplace && test_bit(Faulty, &mreplace->flags)) - mreplace = NULL; /* Unless we are doing a full sync, or a replacement * we only need to recover the block if it is set in * the bitmap @@ -3193,11 +3189,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r10_bio->devs[1].repl_bio; if (bio) bio->bi_end_io = NULL; - /* Note: if need_replace, then bio + /* Note: if replace is not NULL, then bio * cannot be NULL as r10buf_pool_alloc will * have allocated it. */ - if (!need_replace) + if (!mreplace) break; bio->bi_next = biolist; biolist = bio; From 9d1cccdad080a5fbb3f78baa9533fae9cf6b162a Mon Sep 17 00:00:00 2001 From: Li Nan Date: Fri, 2 Jun 2023 17:18:39 +0800 Subject: [PATCH 3752/4345] md/raid10: fix io loss while replacement replace rdev [ Upstream commit 2ae6aaf76912bae53c74b191569d2ab484f24bf3 ] When removing a disk with replacement, the replacement will be used to replace rdev. During this process, there is a brief window in which both rdev and replacement are read as NULL in raid10_write_request(). This will result in io not being submitted but it should be. //remove //write raid10_remove_disk raid10_write_request mirror->rdev = NULL read rdev -> NULL mirror->rdev = mirror->replacement mirror->replacement = NULL read replacement -> NULL Fix it by reading replacement first and rdev later, meanwhile, use smp_mb() to prevent memory reordering. Fixes: 475b0321a4df ("md/raid10: writes should get directed to replacement as well as original.") Signed-off-by: Li Nan Reviewed-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230602091839.743798-3-linan666@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/raid10.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 01680029f0de..32a917e5103a 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -751,8 +751,16 @@ static struct md_rdev *read_balance(struct r10conf *conf, disk = r10_bio->devs[slot].devnum; rdev = rcu_dereference(conf->mirrors[disk].replacement); if (rdev == NULL || test_bit(Faulty, &rdev->flags) || - r10_bio->devs[slot].addr + sectors > rdev->recovery_offset) + r10_bio->devs[slot].addr + sectors > + rdev->recovery_offset) { + /* + * Read replacement first to prevent reading both rdev + * and replacement as NULL during replacement replace + * rdev. + */ + smp_mb(); rdev = rcu_dereference(conf->mirrors[disk].rdev); + } if (rdev == NULL || test_bit(Faulty, &rdev->flags)) continue; @@ -1346,9 +1354,15 @@ retry_write: for (i = 0; i < conf->copies; i++) { int d = r10_bio->devs[i].devnum; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[d].replacement); + struct md_rdev *rdev, *rrdev; + + rrdev = rcu_dereference(conf->mirrors[d].replacement); + /* + * Read replacement first to prevent reading both rdev and + * replacement as NULL during replacement replace rdev. + */ + smp_mb(); + rdev = rcu_dereference(conf->mirrors[d].rdev); if (rdev == rrdev) rrdev = NULL; if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { From 495cee0e14177c718c22782b7b61e7dc23698c27 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 6 Apr 2021 10:35:51 +0100 Subject: [PATCH 3753/4345] irqchip/jcore-aic: Kill use of irq_create_strict_mappings() [ Upstream commit 5f8b938bd790cff6542c7fe3c1495c71f89fef1b ] irq_create_strict_mappings() is a poor way to allow the use of a linear IRQ domain as a legacy one. Let's be upfront about it. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210406093557.1073423-4-maz@kernel.org Stable-dep-of: 4848229494a3 ("irqchip/jcore-aic: Fix missing allocation of IRQ descriptors") Signed-off-by: Sasha Levin --- drivers/irqchip/irq-jcore-aic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-jcore-aic.c b/drivers/irqchip/irq-jcore-aic.c index 033bccb41455..5f47d8ee4ae3 100644 --- a/drivers/irqchip/irq-jcore-aic.c +++ b/drivers/irqchip/irq-jcore-aic.c @@ -100,11 +100,11 @@ static int __init aic_irq_of_init(struct device_node *node, jcore_aic.irq_unmask = noop; jcore_aic.name = "AIC"; - domain = irq_domain_add_linear(node, dom_sz, &jcore_aic_irqdomain_ops, + domain = irq_domain_add_legacy(node, dom_sz - min_irq, min_irq, min_irq, + &jcore_aic_irqdomain_ops, &jcore_aic); if (!domain) return -ENOMEM; - irq_create_strict_mappings(domain, min_irq, min_irq, dom_sz - min_irq); return 0; } From b315d57da4561acb08fa4cc9abbd690afd6bab51 Mon Sep 17 00:00:00 2001 From: John Paul Adrian Glaubitz Date: Wed, 10 May 2023 18:33:42 +0200 Subject: [PATCH 3754/4345] irqchip/jcore-aic: Fix missing allocation of IRQ descriptors [ Upstream commit 4848229494a323eeaab62eee5574ef9f7de80374 ] The initialization function for the J-Core AIC aic_irq_of_init() is currently missing the call to irq_alloc_descs() which allocates and initializes all the IRQ descriptors. Add missing function call and return the error code from irq_alloc_descs() in case the allocation fails. Fixes: 981b58f66cfc ("irqchip/jcore-aic: Add J-Core AIC driver") Signed-off-by: John Paul Adrian Glaubitz Tested-by: Rob Landley Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230510163343.43090-1-glaubitz@physik.fu-berlin.de Signed-off-by: Sasha Levin --- drivers/irqchip/irq-jcore-aic.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/irqchip/irq-jcore-aic.c b/drivers/irqchip/irq-jcore-aic.c index 5f47d8ee4ae3..b9dcc8e78c75 100644 --- a/drivers/irqchip/irq-jcore-aic.c +++ b/drivers/irqchip/irq-jcore-aic.c @@ -68,6 +68,7 @@ static int __init aic_irq_of_init(struct device_node *node, unsigned min_irq = JCORE_AIC2_MIN_HWIRQ; unsigned dom_sz = JCORE_AIC_MAX_HWIRQ+1; struct irq_domain *domain; + int ret; pr_info("Initializing J-Core AIC\n"); @@ -100,6 +101,12 @@ static int __init aic_irq_of_init(struct device_node *node, jcore_aic.irq_unmask = noop; jcore_aic.name = "AIC"; + ret = irq_alloc_descs(-1, min_irq, dom_sz - min_irq, + of_node_to_nid(node)); + + if (ret < 0) + return ret; + domain = irq_domain_add_legacy(node, dom_sz - min_irq, min_irq, min_irq, &jcore_aic_irqdomain_ops, &jcore_aic); From f1be1ed32daa053484222f7f9beb2b16c624dffd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 1 Jun 2023 22:16:34 +0200 Subject: [PATCH 3755/4345] posix-timers: Prevent RT livelock in itimer_delete() [ Upstream commit 9d9e522010eb5685d8b53e8a24320653d9d4cbbf ] itimer_delete() has a retry loop when the timer is concurrently expired. On non-RT kernels this just spin-waits until the timer callback has completed, except for posix CPU timers which have HAVE_POSIX_CPU_TIMERS_TASK_WORK enabled. In that case and on RT kernels the existing task could live lock when preempting the task which does the timer delivery. Replace spin_unlock() with an invocation of timer_wait_running() to handle it the same way as the other retry loops in the posix timer code. Fixes: ec8f954a40da ("posix-timers: Use a callback for cancel synchronization on PREEMPT_RT") Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/r/87v8g7c50d.ffs@tglx Signed-off-by: Sasha Levin --- kernel/time/posix-timers.c | 43 +++++++++++++++++++++++++++++++------- 1 file changed, 35 insertions(+), 8 deletions(-) diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index d089627f2f2b..6d12a724d2b6 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1037,27 +1037,52 @@ retry_delete: } /* - * return timer owned by the process, used by exit_itimers + * Delete a timer if it is armed, remove it from the hash and schedule it + * for RCU freeing. */ static void itimer_delete(struct k_itimer *timer) { -retry_delete: - spin_lock_irq(&timer->it_lock); + unsigned long flags; + /* + * irqsave is required to make timer_wait_running() work. + */ + spin_lock_irqsave(&timer->it_lock, flags); + +retry_delete: + /* + * Even if the timer is not longer accessible from other tasks + * it still might be armed and queued in the underlying timer + * mechanism. Worse, that timer mechanism might run the expiry + * function concurrently. + */ if (timer_delete_hook(timer) == TIMER_RETRY) { - spin_unlock_irq(&timer->it_lock); + /* + * Timer is expired concurrently, prevent livelocks + * and pointless spinning on RT. + * + * timer_wait_running() drops timer::it_lock, which opens + * the possibility for another task to delete the timer. + * + * That's not possible here because this is invoked from + * do_exit() only for the last thread of the thread group. + * So no other task can access and delete that timer. + */ + if (WARN_ON_ONCE(timer_wait_running(timer, &flags) != timer)) + return; + goto retry_delete; } list_del(&timer->list); - spin_unlock_irq(&timer->it_lock); + spin_unlock_irqrestore(&timer->it_lock, flags); release_posix_timer(timer, IT_ID_SET); } /* - * This is called by do_exit or de_thread, only when nobody else can - * modify the signal->posix_timers list. Yet we need sighand->siglock - * to prevent the race with /proc/pid/timers. + * Invoked from do_exit() when the last thread of a thread group exits. + * At that point no other task can access the timers of the dying + * task anymore. */ void exit_itimers(struct task_struct *tsk) { @@ -1067,10 +1092,12 @@ void exit_itimers(struct task_struct *tsk) if (list_empty(&tsk->signal->posix_timers)) return; + /* Protect against concurrent read via /proc/$PID/timers */ spin_lock_irq(&tsk->sighand->siglock); list_replace_init(&tsk->signal->posix_timers, &timers); spin_unlock_irq(&tsk->sighand->siglock); + /* The timers are not longer accessible via tsk::signal */ while (!list_empty(&timers)) { tmr = list_first_entry(&timers, struct k_itimer, list); itimer_delete(tmr); From a2f83a4c7cb503aaacedc4199b1b1bc916bb996d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 18 Apr 2023 16:38:54 +0200 Subject: [PATCH 3756/4345] tracing/timer: Add missing hrtimer modes to decode_hrtimer_mode(). [ Upstream commit 2951580ba6adb082bb6b7154a5ecb24e7c1f7569 ] The trace output for the HRTIMER_MODE_.*_HARD modes is seen as a number since these modes are not decoded. The author was not aware of the fancy decoding function which makes the life easier. Extend decode_hrtimer_mode() with the additional HRTIMER_MODE_.*_HARD modes. Fixes: ae6683d815895 ("hrtimer: Introduce HARD expiry mode") Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Reviewed-by: Mukesh Ojha Acked-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20230418143854.8vHWQKLM@linutronix.de Signed-off-by: Sasha Levin --- include/trace/events/timer.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 40e9b5a12732..5c540ccabcac 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -156,7 +156,11 @@ DEFINE_EVENT(timer_class, timer_cancel, { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ - { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }) + { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ + { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ + { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ + { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ + { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_init - called when the hrtimer is initialized From ebdff0986513a29be242aace0ef89b6c105b0bf0 Mon Sep 17 00:00:00 2001 From: Feng Mingxi Date: Tue, 25 Apr 2023 06:56:11 +0000 Subject: [PATCH 3757/4345] clocksource/drivers/cadence-ttc: Fix memory leak in ttc_timer_probe [ Upstream commit 8b5bf64c89c7100c921bd807ba39b2eb003061ab ] Smatch reports: drivers/clocksource/timer-cadence-ttc.c:529 ttc_timer_probe() warn: 'timer_baseaddr' from of_iomap() not released on lines: 498,508,516. timer_baseaddr may have the problem of not being released after use, I replaced it with the devm_of_iomap() function and added the clk_put() function to cleanup the "clk_ce" and "clk_cs". Fixes: e932900a3279 ("arm: zynq: Use standard timer binding") Fixes: 70504f311d4b ("clocksource/drivers/cadence_ttc: Convert init function to return error") Signed-off-by: Feng Mingxi Reviewed-by: Dongliang Mu Acked-by: Michal Simek Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230425065611.702917-1-m202271825@hust.edu.cn Signed-off-by: Sasha Levin --- drivers/clocksource/timer-cadence-ttc.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/clocksource/timer-cadence-ttc.c b/drivers/clocksource/timer-cadence-ttc.c index 4efd0cf3b602..0d52e28fea4d 100644 --- a/drivers/clocksource/timer-cadence-ttc.c +++ b/drivers/clocksource/timer-cadence-ttc.c @@ -486,10 +486,10 @@ static int __init ttc_timer_probe(struct platform_device *pdev) * and use it. Note that the event timer uses the interrupt and it's the * 2nd TTC hence the irq_of_parse_and_map(,1) */ - timer_baseaddr = of_iomap(timer, 0); - if (!timer_baseaddr) { + timer_baseaddr = devm_of_iomap(&pdev->dev, timer, 0, NULL); + if (IS_ERR(timer_baseaddr)) { pr_err("ERROR: invalid timer base address\n"); - return -ENXIO; + return PTR_ERR(timer_baseaddr); } irq = irq_of_parse_and_map(timer, 1); @@ -513,20 +513,27 @@ static int __init ttc_timer_probe(struct platform_device *pdev) clk_ce = of_clk_get(timer, clksel); if (IS_ERR(clk_ce)) { pr_err("ERROR: timer input clock not found\n"); - return PTR_ERR(clk_ce); + ret = PTR_ERR(clk_ce); + goto put_clk_cs; } ret = ttc_setup_clocksource(clk_cs, timer_baseaddr, timer_width); if (ret) - return ret; + goto put_clk_ce; ret = ttc_setup_clockevent(clk_ce, timer_baseaddr + 4, irq); if (ret) - return ret; + goto put_clk_ce; pr_info("%pOFn #0 at %p, irq=%d\n", timer, timer_baseaddr, irq); return 0; + +put_clk_ce: + clk_put(clk_ce); +put_clk_cs: + clk_put(clk_cs); + return ret; } static const struct of_device_id ttc_timer_of_match[] = { From b69868d50df43f844b1b309d04ae7fcd16207b9d Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Tue, 18 Apr 2023 06:07:43 -0700 Subject: [PATCH 3758/4345] PM: domains: fix integer overflow issues in genpd_parse_state() [ Upstream commit e5d1c8722083f0332dcd3c85fa1273d85fb6bed8 ] Currently, while calculating residency and latency values, right operands may overflow if resulting values are big enough. To prevent this, albeit unlikely case, play it safe and convert right operands to left ones' type s64. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: 30f604283e05 ("PM / Domains: Allow domain power states to be read from DT") Signed-off-by: Nikita Zhandarovich Acked-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/base/power/domain.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index d0ba5459ce0b..8a90f08c9682 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2763,10 +2763,10 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state, err = of_property_read_u32(state_node, "min-residency-us", &residency); if (!err) - genpd_state->residency_ns = 1000 * residency; + genpd_state->residency_ns = 1000LL * residency; - genpd_state->power_on_latency_ns = 1000 * exit_latency; - genpd_state->power_off_latency_ns = 1000 * entry_latency; + genpd_state->power_on_latency_ns = 1000LL * exit_latency; + genpd_state->power_off_latency_ns = 1000LL * entry_latency; genpd_state->fwnode = &state_node->fwnode; return 0; From 23f6efd226448b5bef1db3eeec88a6d6085b3519 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 24 May 2023 17:44:32 +0100 Subject: [PATCH 3759/4345] perf/arm-cmn: Fix DTC reset [ Upstream commit 71746c995cac92fcf6a65661b51211cf2009d7f0 ] It turns out that my naive DTC reset logic fails to work as intended, since, after checking with the hardware designers, the PMU actually needs to be fully enabled in order to correctly clear any pending overflows. Therefore, invert the sequence to start with turning on both enables so that we can reliably get the DTCs into a known state, then moving to our normal counters-stopped state from there. Since all the DTM counters have already been unpaired during the initial discovery pass, we just need to additionally reset the cycle counters to ensure that no other unexpected overflows occur during this period. Fixes: 0ba64770a2f2 ("perf: Add Arm CMN-600 PMU driver") Reported-by: Geoff Blake Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/0ea4559261ea394f827c9aee5168c77a60aaee03.1684946389.git.robin.murphy@arm.com Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- drivers/perf/arm-cmn.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index bb019e383988..36061aaf026c 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -1254,9 +1254,10 @@ static int arm_cmn_init_dtc(struct arm_cmn *cmn, struct arm_cmn_node *dn, int id if (dtc->irq < 0) return dtc->irq; - writel_relaxed(0, dtc->base + CMN_DT_PMCR); + writel_relaxed(CMN_DT_DTC_CTL_DT_EN, dtc->base + CMN_DT_DTC_CTL); + writel_relaxed(CMN_DT_PMCR_PMU_EN | CMN_DT_PMCR_OVFL_INTR_EN, dtc->base + CMN_DT_PMCR); + writeq_relaxed(0, dtc->base + CMN_DT_PMCCNTR); writel_relaxed(0x1ff, dtc->base + CMN_DT_PMOVSR_CLR); - writel_relaxed(CMN_DT_PMCR_OVFL_INTR_EN, dtc->base + CMN_DT_PMCR); /* We do at least know that a DTC's XP must be in that DTC's domain */ xp = arm_cmn_node_to_xp(dn); @@ -1303,7 +1304,7 @@ static int arm_cmn_init_dtcs(struct arm_cmn *cmn) dn->type = CMN_TYPE_RNI; } - writel_relaxed(CMN_DT_DTC_CTL_DT_EN, cmn->dtc[0].base + CMN_DT_DTC_CTL); + arm_cmn_set_state(cmn, CMN_STATE_DISABLED); return 0; } From a50b75c13d37cfa34af6998fa67c5b35fd2c739f Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 6 Jun 2023 22:00:00 +0800 Subject: [PATCH 3760/4345] powercap: RAPL: Fix CONFIG_IOSF_MBI dependency [ Upstream commit 4658fe81b3f8afe8adf37734ec5fe595d90415c6 ] After commit 3382388d7148 ("intel_rapl: abstract RAPL common code"), accessing to IOSF_MBI interface is done in the RAPL common code. Thus it is the CONFIG_INTEL_RAPL_CORE that has dependency of CONFIG_IOSF_MBI, while CONFIG_INTEL_RAPL_MSR does not. This problem was not exposed previously because all the previous RAPL common code users, aka, the RAPL MSR and MMIO I/F drivers, have CONFIG_IOSF_MBI selected. Fix the CONFIG_IOSF_MBI dependency in RAPL code. This also fixes a build time failure when the RAPL TPMI I/F driver is introduced without selecting CONFIG_IOSF_MBI. x86_64-linux-ld: vmlinux.o: in function `set_floor_freq_atom': intel_rapl_common.c:(.text+0x2dac9b8): undefined reference to `iosf_mbi_write' x86_64-linux-ld: intel_rapl_common.c:(.text+0x2daca66): undefined reference to `iosf_mbi_read' Reference to iosf_mbi.h is also removed from the RAPL MSR I/F driver. Fixes: 3382388d7148 ("intel_rapl: abstract RAPL common code") Reported-by: Arnd Bergmann Link: https://lore.kernel.org/all/20230601213246.3271412-1-arnd@kernel.org Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/powercap/Kconfig | 4 +++- drivers/powercap/intel_rapl_msr.c | 1 - 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig index bc228725346b..0e4b2c214a70 100644 --- a/drivers/powercap/Kconfig +++ b/drivers/powercap/Kconfig @@ -18,10 +18,12 @@ if POWERCAP # Client driver configurations go here. config INTEL_RAPL_CORE tristate + depends on PCI + select IOSF_MBI config INTEL_RAPL tristate "Intel RAPL Support via MSR Interface" - depends on X86 && IOSF_MBI + depends on X86 && PCI select INTEL_RAPL_CORE help This enables support for the Intel Running Average Power Limit (RAPL) diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c index 1646808d354c..6b68e5ed2081 100644 --- a/drivers/powercap/intel_rapl_msr.c +++ b/drivers/powercap/intel_rapl_msr.c @@ -22,7 +22,6 @@ #include #include -#include #include #include From a8bfe527556b6f7fc29cbfd2d176dab960075b2f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Jun 2023 19:28:42 +0100 Subject: [PATCH 3761/4345] ARM: 9303/1: kprobes: avoid missing-declaration warnings [ Upstream commit 1b9c3ddcec6a55e15d3e38e7405e2d078db02020 ] checker_stack_use_t32strd() and kprobe_handler() can be made static since they are not used from other files, while coverage_start_registers() and __kprobes_test_case() are used from assembler code, and just need a declaration to avoid a warning with the global definition. arch/arm/probes/kprobes/checkers-common.c:43:18: error: no previous prototype for 'checker_stack_use_t32strd' arch/arm/probes/kprobes/core.c:236:16: error: no previous prototype for 'kprobe_handler' arch/arm/probes/kprobes/test-core.c:723:10: error: no previous prototype for 'coverage_start_registers' arch/arm/probes/kprobes/test-core.c:918:14: error: no previous prototype for '__kprobes_test_case_start' arch/arm/probes/kprobes/test-core.c:952:14: error: no previous prototype for '__kprobes_test_case_end_16' arch/arm/probes/kprobes/test-core.c:967:14: error: no previous prototype for '__kprobes_test_case_end_32' Fixes: 6624cf651f1a ("ARM: kprobes: collects stack consumption for store instructions") Fixes: 454f3e132d05 ("ARM/kprobes: Remove jprobe arm implementation") Acked-by: Masami Hiramatsu (Google) Reviewed-by: Kees Cook Signed-off-by: Arnd Bergmann Signed-off-by: Russell King (Oracle) Signed-off-by: Sasha Levin --- arch/arm/probes/kprobes/checkers-common.c | 2 +- arch/arm/probes/kprobes/core.c | 2 +- arch/arm/probes/kprobes/opt-arm.c | 2 -- arch/arm/probes/kprobes/test-core.c | 2 +- arch/arm/probes/kprobes/test-core.h | 4 ++++ 5 files changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/arm/probes/kprobes/checkers-common.c b/arch/arm/probes/kprobes/checkers-common.c index 4d720990cf2a..eba7ac4725c0 100644 --- a/arch/arm/probes/kprobes/checkers-common.c +++ b/arch/arm/probes/kprobes/checkers-common.c @@ -40,7 +40,7 @@ enum probes_insn checker_stack_use_imm_0xx(probes_opcode_t insn, * Different from other insn uses imm8, the real addressing offset of * STRD in T32 encoding should be imm8 * 4. See ARMARM description. */ -enum probes_insn checker_stack_use_t32strd(probes_opcode_t insn, +static enum probes_insn checker_stack_use_t32strd(probes_opcode_t insn, struct arch_probes_insn *asi, const struct decode_header *h) { diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index e513d8a46776..c0ed17289378 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -231,7 +231,7 @@ singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) * kprobe, and that level is reserved for user kprobe handlers, so we can't * risk encountering a new kprobe in an interrupt handler. */ -void __kprobes kprobe_handler(struct pt_regs *regs) +static void __kprobes kprobe_handler(struct pt_regs *regs) { struct kprobe *p, *cur; struct kprobe_ctlblk *kcb; diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index c78180172120..e20304f1d8bc 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -145,8 +145,6 @@ __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) } } -extern void kprobe_handler(struct pt_regs *regs); - static void optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) { diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c index c562832b8627..171c7076b89f 100644 --- a/arch/arm/probes/kprobes/test-core.c +++ b/arch/arm/probes/kprobes/test-core.c @@ -720,7 +720,7 @@ static const char coverage_register_lookup[16] = { [REG_TYPE_NOSPPCX] = COVERAGE_ANY_REG | COVERAGE_SP, }; -unsigned coverage_start_registers(const struct decode_header *h) +static unsigned coverage_start_registers(const struct decode_header *h) { unsigned regs = 0; int i; diff --git a/arch/arm/probes/kprobes/test-core.h b/arch/arm/probes/kprobes/test-core.h index 19a5b2add41e..805116c2ec27 100644 --- a/arch/arm/probes/kprobes/test-core.h +++ b/arch/arm/probes/kprobes/test-core.h @@ -453,3 +453,7 @@ void kprobe_thumb32_test_cases(void); #else void kprobe_arm_test_cases(void); #endif + +void __kprobes_test_case_start(void); +void __kprobes_test_case_end_16(void); +void __kprobes_test_case_end_32(void); From bacc49b2d5619bdc240ceed625416e0e15b2cbed Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Wed, 21 Jun 2023 09:58:39 +0300 Subject: [PATCH 3762/4345] cpufreq: intel_pstate: Fix energy_performance_preference for passive [ Upstream commit 03f44ffb3d5be2fceda375d92c70ab6de4df7081 ] If the intel_pstate driver is set to passive mode, then writing the same value to the energy_performance_preference sysfs twice will fail. This is caused by the wrong return value used (index of the matched energy_perf_string), instead of the length of the passed in parameter. Fix by forcing the internal return value to zero when the same preference is passed in by user. This same issue is not present when active mode is used for the driver. Fixes: f6ebbcf08f37 ("cpufreq: intel_pstate: Implement passive mode with HWP enabled") Reported-by: Niklas Neronin Signed-off-by: Tero Kristo Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/cpufreq/intel_pstate.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 1686705bee7b..4b06b81d8bb0 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -777,6 +777,8 @@ static ssize_t store_energy_performance_preference( err = cpufreq_start_governor(policy); if (!ret) ret = err; + } else { + ret = 0; } } From 456f783b83f87a645de7118ae0c1867ac67f584e Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 14 May 2023 20:46:05 +0200 Subject: [PATCH 3763/4345] thermal/drivers/sun8i: Fix some error handling paths in sun8i_ths_probe() [ Upstream commit 89382022b370dfd34eaae9c863baa123fcd4d132 ] Should an error occur after calling sun8i_ths_resource_init() in the probe function, some resources need to be released, as already done in the .remove() function. Switch to the devm_clk_get_enabled() helper and add a new devm_action to turn sun8i_ths_resource_init() into a fully managed function. Move the place where reset_control_deassert() is called so that the recommended order of reset release/clock enable steps is kept. A64 manual states that: 3.3.6.4. Gating and reset Make sure that the reset signal has been released before the release of module clock gating; This fixes the issue and removes some LoC at the same time. Fixes: dccc5c3b6f30 ("thermal/drivers/sun8i: Add thermal driver for H6/H5/H3/A64/A83T/R40") Signed-off-by: Christophe JAILLET Acked-by: Maxime Ripard Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/a8ae84bd2dc4b55fe428f8e20f31438bf8bb6762.1684089931.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/thermal/sun8i_thermal.c | 55 +++++++++++---------------------- 1 file changed, 18 insertions(+), 37 deletions(-) diff --git a/drivers/thermal/sun8i_thermal.c b/drivers/thermal/sun8i_thermal.c index f8b13071a6f4..e053b0628017 100644 --- a/drivers/thermal/sun8i_thermal.c +++ b/drivers/thermal/sun8i_thermal.c @@ -318,6 +318,11 @@ out: return ret; } +static void sun8i_ths_reset_control_assert(void *data) +{ + reset_control_assert(data); +} + static int sun8i_ths_resource_init(struct ths_device *tmdev) { struct device *dev = tmdev->dev; @@ -338,47 +343,35 @@ static int sun8i_ths_resource_init(struct ths_device *tmdev) if (IS_ERR(tmdev->reset)) return PTR_ERR(tmdev->reset); - tmdev->bus_clk = devm_clk_get(&pdev->dev, "bus"); + ret = reset_control_deassert(tmdev->reset); + if (ret) + return ret; + + ret = devm_add_action_or_reset(dev, sun8i_ths_reset_control_assert, + tmdev->reset); + if (ret) + return ret; + + tmdev->bus_clk = devm_clk_get_enabled(&pdev->dev, "bus"); if (IS_ERR(tmdev->bus_clk)) return PTR_ERR(tmdev->bus_clk); } if (tmdev->chip->has_mod_clk) { - tmdev->mod_clk = devm_clk_get(&pdev->dev, "mod"); + tmdev->mod_clk = devm_clk_get_enabled(&pdev->dev, "mod"); if (IS_ERR(tmdev->mod_clk)) return PTR_ERR(tmdev->mod_clk); } - ret = reset_control_deassert(tmdev->reset); + ret = clk_set_rate(tmdev->mod_clk, 24000000); if (ret) return ret; - ret = clk_prepare_enable(tmdev->bus_clk); - if (ret) - goto assert_reset; - - ret = clk_set_rate(tmdev->mod_clk, 24000000); - if (ret) - goto bus_disable; - - ret = clk_prepare_enable(tmdev->mod_clk); - if (ret) - goto bus_disable; - ret = sun8i_ths_calibrate(tmdev); if (ret) - goto mod_disable; + return ret; return 0; - -mod_disable: - clk_disable_unprepare(tmdev->mod_clk); -bus_disable: - clk_disable_unprepare(tmdev->bus_clk); -assert_reset: - reset_control_assert(tmdev->reset); - - return ret; } static int sun8i_h3_thermal_init(struct ths_device *tmdev) @@ -529,17 +522,6 @@ static int sun8i_ths_probe(struct platform_device *pdev) return 0; } -static int sun8i_ths_remove(struct platform_device *pdev) -{ - struct ths_device *tmdev = platform_get_drvdata(pdev); - - clk_disable_unprepare(tmdev->mod_clk); - clk_disable_unprepare(tmdev->bus_clk); - reset_control_assert(tmdev->reset); - - return 0; -} - static const struct ths_thermal_chip sun8i_a83t_ths = { .sensor_num = 3, .scale = 705, @@ -641,7 +623,6 @@ MODULE_DEVICE_TABLE(of, of_ths_match); static struct platform_driver ths_driver = { .probe = sun8i_ths_probe, - .remove = sun8i_ths_remove, .driver = { .name = "sun8i-thermal", .of_match_table = of_ths_match, From 8cd9917c13a70a82368b086a51c0948694be230b Mon Sep 17 00:00:00 2001 From: "Jiangong.Han" Date: Tue, 22 Jun 2021 18:37:08 +0800 Subject: [PATCH 3764/4345] rcuscale: Console output claims too few grace periods [ Upstream commit 811192c5f24bfd7246ce9ce06f668d8c408bf39b ] The rcuscale console output claims N grace periods, numbered from zero to N, which means that there were really N+1 grace periods. The root cause of this bug is that rcu_scale_writer() stores the number of the last grace period (numbered from zero) into writer_n_durations[me] instead of the number of grace periods. This commit therefore assigns the actual number of grace periods to writer_n_durations[me], and also makes the corresponding adjustment to the loop outputting per-grace-period measurements. Sample of old console output: rcu-scale: writer 0 gps: 133 ...... rcu-scale: 0 writer-duration: 0 44003961 rcu-scale: 0 writer-duration: 1 32003582 ...... rcu-scale: 0 writer-duration: 132 28004391 rcu-scale: 0 writer-duration: 133 27996410 Sample of new console output: rcu-scale: writer 0 gps: 134 ...... rcu-scale: 0 writer-duration: 0 44003961 rcu-scale: 0 writer-duration: 1 32003582 ...... rcu-scale: 0 writer-duration: 132 28004391 rcu-scale: 0 writer-duration: 133 27996410 Signed-off-by: Jiangong.Han Signed-off-by: Paul E. McKenney Stable-dep-of: 23fc8df26dea ("rcu/rcuscale: Stop kfree_scale_thread thread(s) after unloading rcuscale") Signed-off-by: Sasha Levin --- kernel/rcu/rcuscale.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 2819b95479af..28bc688e2705 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -457,7 +457,7 @@ retry: if (gp_async) { cur_ops->gp_barrier(); } - writer_n_durations[me] = i_max; + writer_n_durations[me] = i_max + 1; torture_kthread_stopping("rcu_scale_writer"); return 0; } @@ -531,7 +531,7 @@ rcu_scale_cleanup(void) wdpp = writer_durations[i]; if (!wdpp) continue; - for (j = 0; j <= writer_n_durations[i]; j++) { + for (j = 0; j < writer_n_durations[i]; j++) { wdp = &wdpp[j]; pr_alert("%s%s %4d writer-duration: %5d %llu\n", scale_type, SCALE_FLAG, From b62c816bdb5e00347f4618fc122a8d2bd79e676a Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Fri, 29 Oct 2021 17:40:28 +0800 Subject: [PATCH 3765/4345] rcuscale: Always log error message [ Upstream commit 86e7ed1bd57d020e35d430542bf5d689c3200568 ] Unconditionally log messages corresponding to errors. Acked-by: Davidlohr Bueso Signed-off-by: Li Zhijian Signed-off-by: Paul E. McKenney Stable-dep-of: 23fc8df26dea ("rcu/rcuscale: Stop kfree_scale_thread thread(s) after unloading rcuscale") Signed-off-by: Sasha Levin --- kernel/rcu/rcuscale.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 28bc688e2705..4452c3c4060c 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -49,8 +49,8 @@ MODULE_AUTHOR("Paul E. McKenney "); pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s) #define VERBOSE_SCALEOUT_STRING(s) \ do { if (verbose) pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s); } while (0) -#define VERBOSE_SCALEOUT_ERRSTRING(s) \ - do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! %s\n", scale_type, s); } while (0) +#define SCALEOUT_ERRSTRING(s) \ + pr_alert("%s" SCALE_FLAG "!!! %s\n", scale_type, s) /* * The intended use cases for the nreaders and nwriters module parameters @@ -484,11 +484,11 @@ rcu_scale_cleanup(void) * during the mid-boot phase, so have to wait till the end. */ if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp) - VERBOSE_SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); + SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); if (rcu_gp_is_normal() && gp_exp) - VERBOSE_SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); + SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); if (gp_exp && gp_async) - VERBOSE_SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!"); + SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!"); if (torture_cleanup_begin()) return; @@ -803,7 +803,7 @@ rcu_scale_init(void) reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]), GFP_KERNEL); if (reader_tasks == NULL) { - VERBOSE_SCALEOUT_ERRSTRING("out of memory"); + SCALEOUT_ERRSTRING("out of memory"); firsterr = -ENOMEM; goto unwind; } @@ -823,7 +823,7 @@ rcu_scale_init(void) kcalloc(nrealwriters, sizeof(*writer_n_durations), GFP_KERNEL); if (!writer_tasks || !writer_durations || !writer_n_durations) { - VERBOSE_SCALEOUT_ERRSTRING("out of memory"); + SCALEOUT_ERRSTRING("out of memory"); firsterr = -ENOMEM; goto unwind; } From ecc5e6dbc26941804433a949c3271757b4e8d3c9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 31 Jan 2023 12:08:54 -0800 Subject: [PATCH 3766/4345] rcuscale: Move shutdown from wait_event() to wait_event_idle() [ Upstream commit ef1ef3d47677dc191b88650a9f7f91413452cc1b ] The rcu_scale_shutdown() and kfree_scale_shutdown() kthreads/functions use wait_event() to wait for the rcuscale test to complete. However, each updater thread in such a test waits for at least 100 grace periods. If each grace period takes more than 1.2 seconds, which is long, but not insanely so, this can trigger the hung-task timeout. This commit therefore replaces those wait_event() calls with calls to wait_event_idle(), which do not trigger the hung-task timeout. Reported-by: kernel test robot Reported-by: Liam Howlett Signed-off-by: Paul E. McKenney Tested-by: Yujie Liu Signed-off-by: Boqun Feng Stable-dep-of: 23fc8df26dea ("rcu/rcuscale: Stop kfree_scale_thread thread(s) after unloading rcuscale") Signed-off-by: Sasha Levin --- kernel/rcu/rcuscale.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 4452c3c4060c..74be0b6438fb 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -579,8 +579,7 @@ static int compute_real(int n) static int rcu_scale_shutdown(void *arg) { - wait_event(shutdown_wq, - atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters); + wait_event_idle(shutdown_wq, atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters); smp_mb(); /* Wake before output. */ rcu_scale_cleanup(); kernel_power_off(); @@ -693,8 +692,8 @@ kfree_scale_cleanup(void) static int kfree_scale_shutdown(void *arg) { - wait_event(shutdown_wq, - atomic_read(&n_kfree_scale_thread_ended) >= kfree_nrealthreads); + wait_event_idle(shutdown_wq, + atomic_read(&n_kfree_scale_thread_ended) >= kfree_nrealthreads); smp_mb(); /* Wake before output. */ From d414e24d150943b1f115f740a3df5b8549e48966 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Wed, 22 Mar 2023 19:42:40 +0800 Subject: [PATCH 3767/4345] rcu/rcuscale: Move rcu_scale_*() after kfree_scale_cleanup() [ Upstream commit bf5ddd736509a7d9077c0b6793e6f0852214dbea ] This code-movement-only commit moves the rcu_scale_cleanup() and rcu_scale_shutdown() functions to follow kfree_scale_cleanup(). This is code movement is in preparation for a bug-fix patch that invokes kfree_scale_cleanup() from rcu_scale_cleanup(). Signed-off-by: Qiuxu Zhuo Signed-off-by: Paul E. McKenney Reviewed-by: Joel Fernandes (Google) Stable-dep-of: 23fc8df26dea ("rcu/rcuscale: Stop kfree_scale_thread thread(s) after unloading rcuscale") Signed-off-by: Sasha Levin --- kernel/rcu/rcuscale.c | 194 +++++++++++++++++++++--------------------- 1 file changed, 97 insertions(+), 97 deletions(-) diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 74be0b6438fb..dfc6172ffe1d 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -470,89 +470,6 @@ rcu_scale_print_module_parms(struct rcu_scale_ops *cur_ops, const char *tag) scale_type, tag, nrealreaders, nrealwriters, verbose, shutdown); } -static void -rcu_scale_cleanup(void) -{ - int i; - int j; - int ngps = 0; - u64 *wdp; - u64 *wdpp; - - /* - * Would like warning at start, but everything is expedited - * during the mid-boot phase, so have to wait till the end. - */ - if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp) - SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); - if (rcu_gp_is_normal() && gp_exp) - SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); - if (gp_exp && gp_async) - SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!"); - - if (torture_cleanup_begin()) - return; - if (!cur_ops) { - torture_cleanup_end(); - return; - } - - if (reader_tasks) { - for (i = 0; i < nrealreaders; i++) - torture_stop_kthread(rcu_scale_reader, - reader_tasks[i]); - kfree(reader_tasks); - } - - if (writer_tasks) { - for (i = 0; i < nrealwriters; i++) { - torture_stop_kthread(rcu_scale_writer, - writer_tasks[i]); - if (!writer_n_durations) - continue; - j = writer_n_durations[i]; - pr_alert("%s%s writer %d gps: %d\n", - scale_type, SCALE_FLAG, i, j); - ngps += j; - } - pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n", - scale_type, SCALE_FLAG, - t_rcu_scale_writer_started, t_rcu_scale_writer_finished, - t_rcu_scale_writer_finished - - t_rcu_scale_writer_started, - ngps, - rcuscale_seq_diff(b_rcu_gp_test_finished, - b_rcu_gp_test_started)); - for (i = 0; i < nrealwriters; i++) { - if (!writer_durations) - break; - if (!writer_n_durations) - continue; - wdpp = writer_durations[i]; - if (!wdpp) - continue; - for (j = 0; j < writer_n_durations[i]; j++) { - wdp = &wdpp[j]; - pr_alert("%s%s %4d writer-duration: %5d %llu\n", - scale_type, SCALE_FLAG, - i, j, *wdp); - if (j % 100 == 0) - schedule_timeout_uninterruptible(1); - } - kfree(writer_durations[i]); - } - kfree(writer_tasks); - kfree(writer_durations); - kfree(writer_n_durations); - } - - /* Do torture-type-specific cleanup operations. */ - if (cur_ops->cleanup != NULL) - cur_ops->cleanup(); - - torture_cleanup_end(); -} - /* * Return the number if non-negative. If -1, the number of CPUs. * If less than -1, that much less than the number of CPUs, but @@ -572,20 +489,6 @@ static int compute_real(int n) return nr; } -/* - * RCU scalability shutdown kthread. Just waits to be awakened, then shuts - * down system. - */ -static int -rcu_scale_shutdown(void *arg) -{ - wait_event_idle(shutdown_wq, atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters); - smp_mb(); /* Wake before output. */ - rcu_scale_cleanup(); - kernel_power_off(); - return -EINVAL; -} - /* * kfree_rcu() scalability tests: Start a kfree_rcu() loop on all CPUs for number * of iterations and measure total time and number of GP for all iterations to complete. @@ -747,6 +650,103 @@ unwind: return firsterr; } +static void +rcu_scale_cleanup(void) +{ + int i; + int j; + int ngps = 0; + u64 *wdp; + u64 *wdpp; + + /* + * Would like warning at start, but everything is expedited + * during the mid-boot phase, so have to wait till the end. + */ + if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp) + SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!"); + if (rcu_gp_is_normal() && gp_exp) + SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!"); + if (gp_exp && gp_async) + SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!"); + + if (torture_cleanup_begin()) + return; + if (!cur_ops) { + torture_cleanup_end(); + return; + } + + if (reader_tasks) { + for (i = 0; i < nrealreaders; i++) + torture_stop_kthread(rcu_scale_reader, + reader_tasks[i]); + kfree(reader_tasks); + } + + if (writer_tasks) { + for (i = 0; i < nrealwriters; i++) { + torture_stop_kthread(rcu_scale_writer, + writer_tasks[i]); + if (!writer_n_durations) + continue; + j = writer_n_durations[i]; + pr_alert("%s%s writer %d gps: %d\n", + scale_type, SCALE_FLAG, i, j); + ngps += j; + } + pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n", + scale_type, SCALE_FLAG, + t_rcu_scale_writer_started, t_rcu_scale_writer_finished, + t_rcu_scale_writer_finished - + t_rcu_scale_writer_started, + ngps, + rcuscale_seq_diff(b_rcu_gp_test_finished, + b_rcu_gp_test_started)); + for (i = 0; i < nrealwriters; i++) { + if (!writer_durations) + break; + if (!writer_n_durations) + continue; + wdpp = writer_durations[i]; + if (!wdpp) + continue; + for (j = 0; j < writer_n_durations[i]; j++) { + wdp = &wdpp[j]; + pr_alert("%s%s %4d writer-duration: %5d %llu\n", + scale_type, SCALE_FLAG, + i, j, *wdp); + if (j % 100 == 0) + schedule_timeout_uninterruptible(1); + } + kfree(writer_durations[i]); + } + kfree(writer_tasks); + kfree(writer_durations); + kfree(writer_n_durations); + } + + /* Do torture-type-specific cleanup operations. */ + if (cur_ops->cleanup != NULL) + cur_ops->cleanup(); + + torture_cleanup_end(); +} + +/* + * RCU scalability shutdown kthread. Just waits to be awakened, then shuts + * down system. + */ +static int +rcu_scale_shutdown(void *arg) +{ + wait_event_idle(shutdown_wq, atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters); + smp_mb(); /* Wake before output. */ + rcu_scale_cleanup(); + kernel_power_off(); + return -EINVAL; +} + static int __init rcu_scale_init(void) { From 604d6a5ff718874904b0fe614878a42b42c0d699 Mon Sep 17 00:00:00 2001 From: Qiuxu Zhuo Date: Wed, 22 Mar 2023 19:42:41 +0800 Subject: [PATCH 3768/4345] rcu/rcuscale: Stop kfree_scale_thread thread(s) after unloading rcuscale [ Upstream commit 23fc8df26dead16687ae6eb47b0561a4a832e2f6 ] Running the 'kfree_rcu_test' test case [1] results in a splat [2]. The root cause is the kfree_scale_thread thread(s) continue running after unloading the rcuscale module. This commit fixes that isue by invoking kfree_scale_cleanup() from rcu_scale_cleanup() when removing the rcuscale module. [1] modprobe rcuscale kfree_rcu_test=1 // After some time rmmod rcuscale rmmod torture [2] BUG: unable to handle page fault for address: ffffffffc0601a87 #PF: supervisor instruction fetch in kernel mode #PF: error_code(0x0010) - not-present page PGD 11de4f067 P4D 11de4f067 PUD 11de51067 PMD 112f4d067 PTE 0 Oops: 0010 [#1] PREEMPT SMP NOPTI CPU: 1 PID: 1798 Comm: kfree_scale_thr Not tainted 6.3.0-rc1-rcu+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.0.0 02/06/2015 RIP: 0010:0xffffffffc0601a87 Code: Unable to access opcode bytes at 0xffffffffc0601a5d. RSP: 0018:ffffb25bc2e57e18 EFLAGS: 00010297 RAX: 0000000000000000 RBX: ffffffffc061f0b6 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff962fd0de RDI: ffffffff962fd0de RBP: ffffb25bc2e57ea8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000000 R14: 000000000000000a R15: 00000000001c1dbe FS: 0000000000000000(0000) GS:ffff921fa2200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffc0601a5d CR3: 000000011de4c006 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? kvfree_call_rcu+0xf0/0x3a0 ? kthread+0xf3/0x120 ? kthread_complete_and_exit+0x20/0x20 ? ret_from_fork+0x1f/0x30 Modules linked in: rfkill sunrpc ... [last unloaded: torture] CR2: ffffffffc0601a87 ---[ end trace 0000000000000000 ]--- Fixes: e6e78b004fa7 ("rcuperf: Add kfree_rcu() performance Tests") Reviewed-by: Davidlohr Bueso Reviewed-by: Joel Fernandes (Google) Signed-off-by: Qiuxu Zhuo Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- kernel/rcu/rcuscale.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index dfc6172ffe1d..6c05365ed80f 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -670,6 +670,11 @@ rcu_scale_cleanup(void) if (gp_exp && gp_async) SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!"); + if (kfree_rcu_test) { + kfree_scale_cleanup(); + return; + } + if (torture_cleanup_begin()) return; if (!cur_ops) { From 365f546de5848795543acc8e177cf84b0f32b46d Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Thu, 4 May 2023 16:30:01 +0530 Subject: [PATCH 3769/4345] perf/ibs: Fix interface via core pmu events [ Upstream commit 2fad201fe38ff9a692acedb1990ece2c52a29f95 ] Although, IBS pmus can be invoked via their own interface, indirect IBS invocation via core pmu events is also supported with fixed set of events: cpu-cycles:p, r076:p (same as cpu-cycles:p) and r0C1:p (micro-ops) for user convenience. This indirect IBS invocation is broken since commit 66d258c5b048 ("perf/core: Optimize perf_init_event()"), which added RAW pmu under 'pmu_idr' list and thus if event_init() fails with RAW pmu, it started returning error instead of trying other pmus. Forward precise events from core pmu to IBS by overwriting 'type' and 'config' in the kernel copy of perf_event_attr. Overwriting will cause perf_init_event() to retry with updated 'type' and 'config', which will automatically forward event to IBS pmu. Without patch: $ sudo ./perf record -C 0 -e r076:p -- sleep 1 Error: The r076:p event is not supported. With patch: $ sudo ./perf record -C 0 -e r076:p -- sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.341 MB perf.data (37 samples) ] Fixes: 66d258c5b048 ("perf/core: Optimize perf_init_event()") Reported-by: Stephane Eranian Signed-off-by: Ravi Bangoria Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230504110003.2548-3-ravi.bangoria@amd.com Signed-off-by: Sasha Levin --- arch/x86/events/amd/core.c | 2 +- arch/x86/events/amd/ibs.c | 53 +++++++++++++++---------------- arch/x86/include/asm/perf_event.h | 2 ++ 3 files changed, 29 insertions(+), 28 deletions(-) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 52eba415928a..afc955340f81 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -364,7 +364,7 @@ static int amd_pmu_hw_config(struct perf_event *event) /* pass precise event sampling to ibs: */ if (event->attr.precise_ip && get_ibs_caps()) - return -ENOENT; + return forward_event_to_ibs(event); if (has_branch_stack(event)) return -EOPNOTSUPP; diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 8a85658a24cc..354d52e17ef5 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -202,7 +202,7 @@ static struct perf_ibs *get_ibs_pmu(int type) } /* - * Use IBS for precise event sampling: + * core pmu config -> IBS config * * perf record -a -e cpu-cycles:p ... # use ibs op counting cycle count * perf record -a -e r076:p ... # same as -e cpu-cycles:p @@ -211,25 +211,9 @@ static struct perf_ibs *get_ibs_pmu(int type) * IbsOpCntCtl (bit 19) of IBS Execution Control Register (IbsOpCtl, * MSRC001_1033) is used to select either cycle or micro-ops counting * mode. - * - * The rip of IBS samples has skid 0. Thus, IBS supports precise - * levels 1 and 2 and the PERF_EFLAGS_EXACT is set. In rare cases the - * rip is invalid when IBS was not able to record the rip correctly. - * We clear PERF_EFLAGS_EXACT and take the rip from pt_regs then. - * */ -static int perf_ibs_precise_event(struct perf_event *event, u64 *config) +static int core_pmu_ibs_config(struct perf_event *event, u64 *config) { - switch (event->attr.precise_ip) { - case 0: - return -ENOENT; - case 1: - case 2: - break; - default: - return -EOPNOTSUPP; - } - switch (event->attr.type) { case PERF_TYPE_HARDWARE: switch (event->attr.config) { @@ -255,22 +239,37 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config) return -EOPNOTSUPP; } +/* + * The rip of IBS samples has skid 0. Thus, IBS supports precise + * levels 1 and 2 and the PERF_EFLAGS_EXACT is set. In rare cases the + * rip is invalid when IBS was not able to record the rip correctly. + * We clear PERF_EFLAGS_EXACT and take the rip from pt_regs then. + */ +int forward_event_to_ibs(struct perf_event *event) +{ + u64 config = 0; + + if (!event->attr.precise_ip || event->attr.precise_ip > 2) + return -EOPNOTSUPP; + + if (!core_pmu_ibs_config(event, &config)) { + event->attr.type = perf_ibs_op.pmu.type; + event->attr.config = config; + } + return -ENOENT; +} + static int perf_ibs_init(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; struct perf_ibs *perf_ibs; u64 max_cnt, config; - int ret; perf_ibs = get_ibs_pmu(event->attr.type); - if (perf_ibs) { - config = event->attr.config; - } else { - perf_ibs = &perf_ibs_op; - ret = perf_ibs_precise_event(event, &config); - if (ret) - return ret; - } + if (!perf_ibs) + return -ENOENT; + + config = event->attr.config; if (event->pmu != &perf_ibs->pmu) return -ENOENT; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index b9a7fd0a27e2..a4e4bbb7795d 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -412,8 +412,10 @@ struct pebs_xmm { #ifdef CONFIG_X86_LOCAL_APIC extern u32 get_ibs_caps(void); +extern int forward_event_to_ibs(struct perf_event *event); #else static inline u32 get_ibs_caps(void) { return 0; } +static inline int forward_event_to_ibs(struct perf_event *event) { return -ENOENT; } #endif #ifdef CONFIG_PERF_EVENTS From cba85e1cb79f089f13e4b2cca6d66659b38567fa Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 6 Mar 2023 13:32:59 +0100 Subject: [PATCH 3770/4345] x86/mm: Fix __swp_entry_to_pte() for Xen PV guests [ Upstream commit 0f88130e8a6fd185b0aeb5d8e286083735f2585a ] Normally __swp_entry_to_pte() is never called with a value translating to a valid PTE. The only known exception is pte_swap_tests(), resulting in a WARN splat in Xen PV guests, as __pte_to_swp_entry() did translate the PFN of the valid PTE to a guest local PFN, while __swp_entry_to_pte() doesn't do the opposite translation. Fix that by using __pte() in __swp_entry_to_pte() instead of open coding the native variant of it. For correctness do the similar conversion for __swp_entry_to_pmd(). Fixes: 05289402d717 ("mm/debug_vm_pgtable: add tests validating arch helpers for core MM features") Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230306123259.12461-1-jgross@suse.com Signed-off-by: Sasha Levin --- arch/x86/include/asm/pgtable_64.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 56d0399a0cd1..dd520b44e89c 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -235,8 +235,8 @@ static inline void native_pgd_clear(pgd_t *pgd) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) -#define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val }) -#define __swp_entry_to_pmd(x) ((pmd_t) { .pmd = (x).val }) +#define __swp_entry_to_pte(x) (__pte((x).val)) +#define __swp_entry_to_pmd(x) (__pmd((x).val)) extern int kern_addr_valid(unsigned long addr); extern void cleanup_highmap(void); From 16ec59c03ad258b716374946a6b1530921d0faf3 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Mon, 6 Mar 2023 11:40:36 +0100 Subject: [PATCH 3771/4345] evm: Complete description of evm_inode_setattr() [ Upstream commit b1de86d4248b273cb12c4cd7d20c08d459519f7d ] Add the description for missing parameters of evm_inode_setattr() to avoid the warning arising with W=n compile option. Fixes: 817b54aa45db ("evm: add evm_inode_setattr to prevent updating an invalid security.evm") # v3.2+ Fixes: c1632a0f1120 ("fs: port ->setattr() to pass mnt_idmap") # v6.3+ Signed-off-by: Roberto Sassu Reviewed-by: Stefan Berger Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/evm/evm_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 0033364ac404..8cfc49fa4df5 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -472,7 +472,9 @@ void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name) /** * evm_inode_setattr - prevent updating an invalid EVM extended attribute + * @idmap: idmap of the mount * @dentry: pointer to the affected dentry + * @attr: iattr structure containing the new file attributes * * Permit update of file attributes when files have a valid EVM signature, * except in the case of them having an immutable portable signature. From 628709a05708918d17beddc9440b2d64320929c0 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Tue, 6 Jun 2023 09:41:13 +0200 Subject: [PATCH 3772/4345] ima: Fix build warnings [ Upstream commit 95526d13038c2bbddd567a4d8e39fac42484e182 ] Fix build warnings (function parameters description) for ima_collect_modsig(), ima_match_policy() and ima_parse_add_rule(). Fixes: 15588227e086 ("ima: Collect modsig") # v5.4+ Fixes: 2fe5d6def167 ("ima: integrity appraisal extension") # v5.14+ Fixes: 4af4662fa4a9 ("integrity: IMA policy") # v3.2+ Signed-off-by: Roberto Sassu Signed-off-by: Mimi Zohar Signed-off-by: Sasha Levin --- security/integrity/ima/ima_modsig.c | 3 +++ security/integrity/ima/ima_policy.c | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/security/integrity/ima/ima_modsig.c b/security/integrity/ima/ima_modsig.c index fb25723c65bc..3e7bee30080f 100644 --- a/security/integrity/ima/ima_modsig.c +++ b/security/integrity/ima/ima_modsig.c @@ -89,6 +89,9 @@ int ima_read_modsig(enum ima_hooks func, const void *buf, loff_t buf_len, /** * ima_collect_modsig - Calculate the file hash without the appended signature. + * @modsig: parsed module signature + * @buf: data to verify the signature on + * @size: data size * * Since the modsig is part of the file contents, the hash used in its signature * isn't the same one ordinarily calculated by IMA. Therefore PKCS7 code diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 96ecb7d25403..1c403e8a8044 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -628,6 +628,7 @@ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func) * @secid: LSM secid of the task to be validated * @func: IMA hook identifier * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC) + * @flags: IMA actions to consider (e.g. IMA_MEASURE | IMA_APPRAISE) * @pcr: set the pcr to extend * @template_desc: the template that should be used for this rule * @keyring: the keyring name, if given, to be used to check in the policy. @@ -1515,7 +1516,7 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) /** * ima_parse_add_rule - add a rule to ima_policy_rules - * @rule - ima measurement policy rule + * @rule: ima measurement policy rule * * Avoid locking by allowing just one writer at a time in ima_write_policy() * Returns the length of the rule parsed, an error code on failure From a14cb307267ba7a1715403e071bdc4deda77eef5 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 14 Jun 2023 17:37:33 +0800 Subject: [PATCH 3773/4345] pstore/ram: Add check for kstrdup [ Upstream commit d97038d5ec2062733c1e016caf9baaf68cf64ea1 ] Add check for the return value of kstrdup() and return the error if it fails in order to avoid NULL pointer dereference. Fixes: e163fdb3f7f8 ("pstore/ram: Regularize prz label allocation lifetime") Signed-off-by: Jiasheng Jiang Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230614093733.36048-1-jiasheng@iscas.ac.cn Signed-off-by: Sasha Levin --- fs/pstore/ram_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 184cb97c83bd..b6183f1f4ebc 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -577,6 +577,8 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, raw_spin_lock_init(&prz->buffer_lock); prz->flags = flags; prz->label = kstrdup(label, GFP_KERNEL); + if (!prz->label) + goto err; ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) From cbd0f41a5362a1500eec3b3d79fbe8c1b74bf46d Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 18 Apr 2023 15:30:42 +0200 Subject: [PATCH 3774/4345] igc: Enable and fix RX hash usage by netstack [ Upstream commit 84214ab4689f962b4bfc47fc9a5838d25ac4274d ] When function igc_rx_hash() was introduced in v4.20 via commit 0507ef8a0372 ("igc: Add transmit and receive fastpath and interrupt handlers"), the hardware wasn't configured to provide RSS hash, thus it made sense to not enable net_device NETIF_F_RXHASH feature bit. The NIC hardware was configured to enable RSS hash info in v5.2 via commit 2121c2712f82 ("igc: Add multiple receive queues control supporting"), but forgot to set the NETIF_F_RXHASH feature bit. The original implementation of igc_rx_hash() didn't extract the associated pkt_hash_type, but statically set PKT_HASH_TYPE_L3. The largest portions of this patch are about extracting the RSS Type from the hardware and mapping this to enum pkt_hash_types. This was based on Foxville i225 software user manual rev-1.3.1 and tested on Intel Ethernet Controller I225-LM (rev 03). For UDP it's worth noting that RSS (type) hashing have been disabled both for IPv4 and IPv6 (see IGC_MRQC_RSS_FIELD_IPV4_UDP + IGC_MRQC_RSS_FIELD_IPV6_UDP) because hardware RSS doesn't handle fragmented pkts well when enabled (can cause out-of-order). This results in PKT_HASH_TYPE_L3 for UDP packets, and hash value doesn't include UDP port numbers. Not being PKT_HASH_TYPE_L4, have the effect that netstack will do a software based hash calc calling into flow_dissect, but only when code calls skb_get_hash(), which doesn't necessary happen for local delivery. For QA verification testing I wrote a small bpftrace prog: [0] https://github.com/xdp-project/xdp-project/blob/master/areas/hints/monitor_skb_hash_on_dev.bt Fixes: 2121c2712f82 ("igc: Add multiple receive queues control supporting") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: Song Yoong Siang Link: https://lore.kernel.org/bpf/168182464270.616355.11391652654430626584.stgit@firesoul Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc.h | 28 ++++++++++++++++++++ drivers/net/ethernet/intel/igc/igc_main.c | 31 ++++++++++++++++++++--- 2 files changed, 55 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 970dd878d8a7..47ba1eafcdc7 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -13,6 +13,7 @@ #include #include #include +#include #include "igc_hw.h" @@ -272,6 +273,33 @@ extern char igc_driver_name[]; #define IGC_MRQC_RSS_FIELD_IPV4_UDP 0x00400000 #define IGC_MRQC_RSS_FIELD_IPV6_UDP 0x00800000 +/* RX-desc Write-Back format RSS Type's */ +enum igc_rss_type_num { + IGC_RSS_TYPE_NO_HASH = 0, + IGC_RSS_TYPE_HASH_TCP_IPV4 = 1, + IGC_RSS_TYPE_HASH_IPV4 = 2, + IGC_RSS_TYPE_HASH_TCP_IPV6 = 3, + IGC_RSS_TYPE_HASH_IPV6_EX = 4, + IGC_RSS_TYPE_HASH_IPV6 = 5, + IGC_RSS_TYPE_HASH_TCP_IPV6_EX = 6, + IGC_RSS_TYPE_HASH_UDP_IPV4 = 7, + IGC_RSS_TYPE_HASH_UDP_IPV6 = 8, + IGC_RSS_TYPE_HASH_UDP_IPV6_EX = 9, + IGC_RSS_TYPE_MAX = 10, +}; +#define IGC_RSS_TYPE_MAX_TABLE 16 +#define IGC_RSS_TYPE_MASK GENMASK(3,0) /* 4-bits (3:0) = mask 0x0F */ + +/* igc_rss_type - Rx descriptor RSS type field */ +static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc) +{ + /* RSS Type 4-bits (3:0) number: 0-9 (above 9 is reserved) + * Accessing the same bits via u16 (wb.lower.lo_dword.hs_rss.pkt_info) + * is slightly slower than via u32 (wb.lower.lo_dword.data) + */ + return le32_get_bits(rx_desc->wb.lower.lo_dword.data, IGC_RSS_TYPE_MASK); +} + /* Interrupt defines */ #define IGC_START_ITR 648 /* ~6000 ints/sec */ #define IGC_4K_ITR 980 diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 3aa0efb542aa..72d7d2cf126d 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1569,14 +1569,36 @@ static void igc_rx_checksum(struct igc_ring *ring, le32_to_cpu(rx_desc->wb.upper.status_error)); } +/* Mapping HW RSS Type to enum pkt_hash_types */ +static const enum pkt_hash_types igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE] = { + [IGC_RSS_TYPE_NO_HASH] = PKT_HASH_TYPE_L2, + [IGC_RSS_TYPE_HASH_TCP_IPV4] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_IPV4] = PKT_HASH_TYPE_L3, + [IGC_RSS_TYPE_HASH_TCP_IPV6] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_IPV6_EX] = PKT_HASH_TYPE_L3, + [IGC_RSS_TYPE_HASH_IPV6] = PKT_HASH_TYPE_L3, + [IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_UDP_IPV4] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_UDP_IPV6] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = PKT_HASH_TYPE_L4, + [10] = PKT_HASH_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW */ + [11] = PKT_HASH_TYPE_NONE, /* keep array sized for SW bit-mask */ + [12] = PKT_HASH_TYPE_NONE, /* to handle future HW revisons */ + [13] = PKT_HASH_TYPE_NONE, + [14] = PKT_HASH_TYPE_NONE, + [15] = PKT_HASH_TYPE_NONE, +}; + static inline void igc_rx_hash(struct igc_ring *ring, union igc_adv_rx_desc *rx_desc, struct sk_buff *skb) { - if (ring->netdev->features & NETIF_F_RXHASH) - skb_set_hash(skb, - le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), - PKT_HASH_TYPE_L3); + if (ring->netdev->features & NETIF_F_RXHASH) { + u32 rss_hash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); + u32 rss_type = igc_rss_type(rx_desc); + + skb_set_hash(skb, rss_hash, igc_rss_type_table[rss_type]); + } } /** @@ -5257,6 +5279,7 @@ static int igc_probe(struct pci_dev *pdev, netdev->features |= NETIF_F_TSO; netdev->features |= NETIF_F_TSO6; netdev->features |= NETIF_F_TSO_ECN; + netdev->features |= NETIF_F_RXHASH; netdev->features |= NETIF_F_RXCSUM; netdev->features |= NETIF_F_HW_CSUM; netdev->features |= NETIF_F_SCTP_CRC; From 0f3f41b47533179d027c433e8f30dea5b6ebe833 Mon Sep 17 00:00:00 2001 From: Peter Seiderer Date: Wed, 26 Apr 2023 17:35:00 +0300 Subject: [PATCH 3775/4345] wifi: ath9k: fix AR9003 mac hardware hang check register offset calculation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 3e56c80931c7615250fe4bf83f93b57881969266 ] Fix ath9k_hw_verify_hang()/ar9003_hw_detect_mac_hang() register offset calculation (do not overflow the shift for the second register/queues above five, use the register layout described in the comments above ath9k_hw_verify_hang() instead). Fixes: 222e04830ff0 ("ath9k: Fix MAC HW hang check for AR9003") Reported-by: Gregg Wonderly Link: https://lore.kernel.org/linux-wireless/E3A9C354-0CB7-420C-ADEF-F0177FB722F4@seqtechllc.com/ Signed-off-by: Peter Seiderer Acked-by: Toke Høiland-Jørgensen Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230422212423.26065-1-ps.report@gmx.net Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/ar9003_hw.c | 27 ++++++++++++++-------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/ar9003_hw.c b/drivers/net/wireless/ath/ath9k/ar9003_hw.c index 42f00a2a8c80..cf5648188459 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_hw.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_hw.c @@ -1099,17 +1099,22 @@ static bool ath9k_hw_verify_hang(struct ath_hw *ah, unsigned int queue) { u32 dma_dbg_chain, dma_dbg_complete; u8 dcu_chain_state, dcu_complete_state; + unsigned int dbg_reg, reg_offset; int i; - for (i = 0; i < NUM_STATUS_READS; i++) { - if (queue < 6) - dma_dbg_chain = REG_READ(ah, AR_DMADBG_4); - else - dma_dbg_chain = REG_READ(ah, AR_DMADBG_5); + if (queue < 6) { + dbg_reg = AR_DMADBG_4; + reg_offset = queue * 5; + } else { + dbg_reg = AR_DMADBG_5; + reg_offset = (queue - 6) * 5; + } + for (i = 0; i < NUM_STATUS_READS; i++) { + dma_dbg_chain = REG_READ(ah, dbg_reg); dma_dbg_complete = REG_READ(ah, AR_DMADBG_6); - dcu_chain_state = (dma_dbg_chain >> (5 * queue)) & 0x1f; + dcu_chain_state = (dma_dbg_chain >> reg_offset) & 0x1f; dcu_complete_state = dma_dbg_complete & 0x3; if ((dcu_chain_state != 0x6) || (dcu_complete_state != 0x1)) @@ -1128,6 +1133,7 @@ static bool ar9003_hw_detect_mac_hang(struct ath_hw *ah) u8 dcu_chain_state, dcu_complete_state; bool dcu_wait_frdone = false; unsigned long chk_dcu = 0; + unsigned int reg_offset; unsigned int i = 0; dma_dbg_4 = REG_READ(ah, AR_DMADBG_4); @@ -1139,12 +1145,15 @@ static bool ar9003_hw_detect_mac_hang(struct ath_hw *ah) goto exit; for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) { - if (i < 6) + if (i < 6) { chk_dbg = dma_dbg_4; - else + reg_offset = i * 5; + } else { chk_dbg = dma_dbg_5; + reg_offset = (i - 6) * 5; + } - dcu_chain_state = (chk_dbg >> (5 * i)) & 0x1f; + dcu_chain_state = (chk_dbg >> reg_offset) & 0x1f; if (dcu_chain_state == 0x6) { dcu_wait_frdone = true; chk_dcu |= BIT(i); From 250efb4d3f5b32a115ea6bf25437ba44a1b3c04f Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Wed, 26 Apr 2023 17:35:01 +0300 Subject: [PATCH 3776/4345] wifi: ath9k: avoid referencing uninit memory in ath9k_wmi_ctrl_rx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f24292e827088bba8de7158501ac25a59b064953 ] For the reasons also described in commit b383e8abed41 ("wifi: ath9k: avoid uninit memory read in ath9k_htc_rx_msg()"), ath9k_htc_rx_msg() should validate pkt_len before accessing the SKB. For example, the obtained SKB may have been badly constructed with pkt_len = 8. In this case, the SKB can only contain a valid htc_frame_hdr but after being processed in ath9k_htc_rx_msg() and passed to ath9k_wmi_ctrl_rx() endpoint RX handler, it is expected to have a WMI command header which should be located inside its data payload. Implement sanity checking inside ath9k_wmi_ctrl_rx(). Otherwise, uninit memory can be referenced. Tested on Qualcomm Atheros Communications AR9271 802.11n . Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.") Reported-and-tested-by: syzbot+f2cb6e0ffdb961921e4d@syzkaller.appspotmail.com Signed-off-by: Fedor Pchelkin Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230424183348.111355-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/wmi.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c index 19345b8f7bfd..d652c647d56b 100644 --- a/drivers/net/wireless/ath/ath9k/wmi.c +++ b/drivers/net/wireless/ath/ath9k/wmi.c @@ -221,6 +221,10 @@ static void ath9k_wmi_ctrl_rx(void *priv, struct sk_buff *skb, if (unlikely(wmi->stopped)) goto free_skb; + /* Validate the obtained SKB. */ + if (unlikely(skb->len < sizeof(struct wmi_cmd_hdr))) + goto free_skb; + hdr = (struct wmi_cmd_hdr *) skb->data; cmd_id = be16_to_cpu(hdr->command_id); From bd3e880dce27d225598730d2bbb3dc05b443af22 Mon Sep 17 00:00:00 2001 From: Pengcheng Yang Date: Fri, 5 May 2023 16:50:58 +0800 Subject: [PATCH 3777/4345] samples/bpf: Fix buffer overflow in tcp_basertt [ Upstream commit f4dea9689c5fea3d07170c2cb0703e216f1a0922 ] Using sizeof(nv) or strlen(nv)+1 is correct. Fixes: c890063e4404 ("bpf: sample BPF_SOCKET_OPS_BASE_RTT program") Signed-off-by: Pengcheng Yang Link: https://lore.kernel.org/r/1683276658-2860-1-git-send-email-yangpc@wangsu.com Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- samples/bpf/tcp_basertt_kern.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/samples/bpf/tcp_basertt_kern.c b/samples/bpf/tcp_basertt_kern.c index 8dfe09a92fec..822b0742b815 100644 --- a/samples/bpf/tcp_basertt_kern.c +++ b/samples/bpf/tcp_basertt_kern.c @@ -47,7 +47,7 @@ int bpf_basertt(struct bpf_sock_ops *skops) case BPF_SOCK_OPS_BASE_RTT: n = bpf_getsockopt(skops, SOL_TCP, TCP_CONGESTION, cong, sizeof(cong)); - if (!n && !__builtin_memcmp(cong, nv, sizeof(nv)+1)) { + if (!n && !__builtin_memcmp(cong, nv, sizeof(nv))) { /* Set base_rtt to 80us */ rv = 80; } else if (n) { From 795ef550307c02a4e15b7b81e7b243c51e6df317 Mon Sep 17 00:00:00 2001 From: Vijaya Krishna Nivarthi Date: Tue, 25 Apr 2023 14:12:08 +0530 Subject: [PATCH 3778/4345] spi: spi-geni-qcom: Correct CS_TOGGLE bit in SPI_TRANS_CFG [ Upstream commit 5fd7c99ecf45c8ee8a9b1268f0ffc91cc6271da2 ] The CS_TOGGLE bit when set is supposed to instruct FW to toggle CS line between words. The driver with intent of disabling this behaviour has been unsetting BIT(0). This has not caused any trouble so far because the original BIT(1) is untouched and BIT(0) likely wasn't being used. Correct this to prevent a potential future bug. Signed-off-by: Vijaya Krishna Nivarthi --- drivers/spi/spi-geni-qcom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c index 01ef79f15b02..be259c685cc8 100644 --- a/drivers/spi/spi-geni-qcom.c +++ b/drivers/spi/spi-geni-qcom.c @@ -32,7 +32,7 @@ #define CS_DEMUX_OUTPUT_SEL GENMASK(3, 0) #define SE_SPI_TRANS_CFG 0x25c -#define CS_TOGGLE BIT(0) +#define CS_TOGGLE BIT(1) #define SE_SPI_WORD_LEN 0x268 #define WORD_LEN_MSK GENMASK(9, 0) From 3ae910a375b67e51787978f224f5c4466cd4aa6e Mon Sep 17 00:00:00 2001 From: Amisha Patel Date: Fri, 21 Apr 2023 18:10:20 +0000 Subject: [PATCH 3779/4345] wifi: wilc1000: fix for absent RSN capabilities WFA testcase [ Upstream commit 9ce4bb09123e9754996e358bd808d39f5d112899 ] Mandatory WFA testcase CT_Security_WPA2Personal_STA_RSNEBoundsVerification-AbsentRSNCap, performs bounds verfication on Beacon and/or Probe response frames. It failed and observed the reason to be absence of cipher suite and AKM suite in RSN information. To fix this, enable the RSN flag before extracting RSN capabilities. Fixes: cd21d99e595e ("wifi: wilc1000: validate pairwise and authentication suite offsets") Signed-off-by: Amisha Patel Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230421181005.4865-1-amisha.patel@microchip.com Signed-off-by: Sasha Levin --- drivers/net/wireless/microchip/wilc1000/hif.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c index b25847799138..884f45e627a7 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.c +++ b/drivers/net/wireless/microchip/wilc1000/hif.c @@ -470,6 +470,9 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, int rsn_ie_len = sizeof(struct element) + rsn_ie[1]; int offset = 8; + param->mode_802_11i = 2; + param->rsn_found = true; + /* extract RSN capabilities */ if (offset < rsn_ie_len) { /* skip over pairwise suites */ @@ -479,11 +482,8 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, /* skip over authentication suites */ offset += (rsn_ie[offset] * 4) + 2; - if (offset + 1 < rsn_ie_len) { - param->mode_802_11i = 2; - param->rsn_found = true; + if (offset + 1 < rsn_ie_len) memcpy(param->rsn_cap, &rsn_ie[offset], 2); - } } } } From c62e2ac02e288b7e0039037e8e2e9759dafe8acf Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 6 May 2023 15:53:15 +0200 Subject: [PATCH 3780/4345] wifi: mwifiex: Fix the size of a memory allocation in mwifiex_ret_802_11_scan() [ Upstream commit d9aef04fcfa81ee4fb2804a21a3712b7bbd936af ] The type of "mwifiex_adapter->nd_info" is "struct cfg80211_wowlan_nd_info", not "struct cfg80211_wowlan_nd_match". Use struct_size() to ease the computation of the needed size. The current code over-allocates some memory, so is safe. But it wastes 32 bytes. Fixes: 7d7f07d8c5d3 ("mwifiex: add wowlan net-detect support") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/7a6074fb056d2181e058a3cc6048d8155c20aec7.1683371982.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/net/wireless/marvell/mwifiex/scan.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c index c2a685f63e95..78ef40e315b5 100644 --- a/drivers/net/wireless/marvell/mwifiex/scan.c +++ b/drivers/net/wireless/marvell/mwifiex/scan.c @@ -2200,9 +2200,9 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, if (nd_config) { adapter->nd_info = - kzalloc(sizeof(struct cfg80211_wowlan_nd_match) + - sizeof(struct cfg80211_wowlan_nd_match *) * - scan_rsp->number_of_sets, GFP_ATOMIC); + kzalloc(struct_size(adapter->nd_info, matches, + scan_rsp->number_of_sets), + GFP_ATOMIC); if (adapter->nd_info) adapter->nd_info->n_matches = scan_rsp->number_of_sets; From 08f61a34913558e06576e7b6318bf583f273c1be Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:34:59 -0800 Subject: [PATCH 3781/4345] bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE [ Upstream commit 9cacf81f8161111db25f98e78a7a0e32ae142b3f ] Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE. We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom call in do_tcp_getsockopt using the on-stack data. This removes 3% overhead for locking/unlocking the socket. Without this patch: 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc With the patch applied: 0.52% 0.12% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt_kern Note, exporting uapi/tcp.h requires removing netinet/tcp.h from test_progs.h because those headers have confliciting definitions. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-2-sdf@google.com Stable-dep-of: 2598619e012c ("sctp: add bpf_bypass_getsockopt proto callback") Signed-off-by: Sasha Levin --- include/linux/bpf-cgroup.h | 27 +- include/linux/indirect_call_wrapper.h | 6 + include/net/sock.h | 2 + include/net/tcp.h | 1 + kernel/bpf/cgroup.c | 46 +++ net/ipv4/tcp.c | 14 + net/ipv4/tcp_ipv4.c | 1 + net/ipv6/tcp_ipv6.c | 1 + net/socket.c | 3 + tools/include/uapi/linux/tcp.h | 357 ++++++++++++++++++ .../selftests/bpf/prog_tests/bpf_tcp_ca.c | 1 + .../selftests/bpf/prog_tests/cls_redirect.c | 1 + .../selftests/bpf/prog_tests/sockmap_basic.c | 1 + .../selftests/bpf/prog_tests/sockopt_sk.c | 28 ++ .../testing/selftests/bpf/progs/sockopt_sk.c | 23 +- tools/testing/selftests/bpf/test_progs.h | 1 - 16 files changed, 506 insertions(+), 7 deletions(-) create mode 100644 tools/include/uapi/linux/tcp.h diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 91b966978541..53702b83ce5f 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -158,6 +158,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int __user *optlen, int max_optlen, int retval); +int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, + int optname, void *optval, + int *optlen, int retval); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -404,10 +408,23 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, ({ \ int __ret = retval; \ if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \ - optname, optval, \ - optlen, max_optlen, \ - retval); \ + if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ + !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ + tcp_bpf_bypass_getsockopt, \ + level, optname)) \ + __ret = __cgroup_bpf_run_filter_getsockopt( \ + sock, level, optname, optval, optlen, \ + max_optlen, retval); \ + __ret; \ +}) + +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ + optlen, retval) \ +({ \ + int __ret = retval; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ + sock, level, optname, optval, optlen, retval); \ __ret; \ }) @@ -493,6 +510,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ + optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) ({ 0; }) diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 54c02c84906a..cfcfef37b2f1 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -60,4 +60,10 @@ #define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__) #endif +#if IS_ENABLED(CONFIG_INET) +#define INDIRECT_CALL_INET_1(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) +#else +#define INDIRECT_CALL_INET_1(f, f1, ...) f(__VA_ARGS__) +#endif + #endif diff --git a/include/net/sock.h b/include/net/sock.h index 51b499d74549..03e7f7581559 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1207,6 +1207,8 @@ struct proto { int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); + bool (*bpf_bypass_getsockopt)(int level, + int optname); void (*release_cb)(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index d213b86a4822..e231101e5001 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -389,6 +389,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); +bool tcp_bpf_bypass_getsockopt(int level, int optname); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index d3593a520bb7..85927c2aa343 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1546,6 +1546,52 @@ out: sockopt_free_buf(&ctx); return ret; } + +int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, + int optname, void *optval, + int *optlen, int retval) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_sockopt_kern ctx = { + .sk = sk, + .level = level, + .optname = optname, + .retval = retval, + .optlen = *optlen, + .optval = optval, + .optval_end = optval + *optlen, + }; + int ret; + + /* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy + * user data back into BPF buffer when reval != 0. This is + * done as an optimization to avoid extra copy, assuming + * kernel won't populate the data in case of an error. + * Here we always pass the data and memset() should + * be called if that data shouldn't be "exported". + */ + + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], + &ctx, BPF_PROG_RUN); + if (!ret) + return -EPERM; + + if (ctx.optlen > *optlen) + return -EFAULT; + + /* BPF programs only allowed to set retval to 0, not some + * arbitrary value. + */ + if (ctx.retval != 0 && ctx.retval != retval) + return -EFAULT; + + /* BPF programs can shrink the buffer, export the modifications. + */ + if (ctx.optlen != 0) + *optlen = ctx.optlen; + + return ctx.retval; +} #endif static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 82abbf192985..cc42ceadc112 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3970,6 +3970,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc); + err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, + &zc, &len, err); release_sock(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, err)) goto zerocopy_rcv_sk_err; @@ -4004,6 +4006,18 @@ zerocopy_rcv_out: return 0; } +bool tcp_bpf_bypass_getsockopt(int level, int optname) +{ + /* TCP do_tcp_getsockopt has optimized getsockopt implementation + * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE. + */ + if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE) + return true; + + return false; +} +EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); + int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 270b20e0907c..d62d5d7764ad 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2805,6 +2805,7 @@ struct proto tcp_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, + .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index fe29bc66aeac..5392aebd48f1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2135,6 +2135,7 @@ struct proto tcpv6_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, + .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, diff --git a/net/socket.c b/net/socket.c index 84223419da86..f2172b756c0f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2137,6 +2137,9 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, return __sys_setsockopt(fd, level, optname, optval, optlen); } +INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, + int optname)); + /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. diff --git a/tools/include/uapi/linux/tcp.h b/tools/include/uapi/linux/tcp.h new file mode 100644 index 000000000000..13ceeb395eb8 --- /dev/null +++ b/tools/include/uapi/linux/tcp.h @@ -0,0 +1,357 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions for the TCP protocol. + * + * Version: @(#)tcp.h 1.0.2 04/28/93 + * + * Author: Fred N. van Kempen, + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _UAPI_LINUX_TCP_H +#define _UAPI_LINUX_TCP_H + +#include +#include +#include + +struct tcphdr { + __be16 source; + __be16 dest; + __be32 seq; + __be32 ack_seq; +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u16 res1:4, + doff:4, + fin:1, + syn:1, + rst:1, + psh:1, + ack:1, + urg:1, + ece:1, + cwr:1; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u16 doff:4, + res1:4, + cwr:1, + ece:1, + urg:1, + ack:1, + psh:1, + rst:1, + syn:1, + fin:1; +#else +#error "Adjust your defines" +#endif + __be16 window; + __sum16 check; + __be16 urg_ptr; +}; + +/* + * The union cast uses a gcc extension to avoid aliasing problems + * (union is compatible to any of its members) + * This means this part of the code is -fstrict-aliasing safe now. + */ +union tcp_word_hdr { + struct tcphdr hdr; + __be32 words[5]; +}; + +#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) + +enum { + TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000), + TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000), + TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000), + TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000), + TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000), + TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000), + TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000), + TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000), + TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000), + TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000) +}; + +/* + * TCP general constants + */ +#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */ +#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */ + +/* TCP socket options */ +#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */ +#define TCP_MAXSEG 2 /* Limit MSS */ +#define TCP_CORK 3 /* Never send partially complete segments */ +#define TCP_KEEPIDLE 4 /* Start keeplives after this period */ +#define TCP_KEEPINTVL 5 /* Interval between keepalives */ +#define TCP_KEEPCNT 6 /* Number of keepalives before death */ +#define TCP_SYNCNT 7 /* Number of SYN retransmits */ +#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */ +#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */ +#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */ +#define TCP_INFO 11 /* Information about this connection. */ +#define TCP_QUICKACK 12 /* Block/reenable quick acks */ +#define TCP_CONGESTION 13 /* Congestion control algorithm */ +#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ +#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ +#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ +#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */ +#define TCP_REPAIR 19 /* TCP sock is under repair right now */ +#define TCP_REPAIR_QUEUE 20 +#define TCP_QUEUE_SEQ 21 +#define TCP_REPAIR_OPTIONS 22 +#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */ +#define TCP_TIMESTAMP 24 +#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */ +#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */ +#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */ +#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */ +#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */ +#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */ +#define TCP_ULP 31 /* Attach a ULP to a TCP connection */ +#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */ +#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */ +#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */ +#define TCP_ZEROCOPY_RECEIVE 35 +#define TCP_INQ 36 /* Notify bytes available to read as a cmsg on read */ + +#define TCP_CM_INQ TCP_INQ + +#define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */ + + +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF 0 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + +struct tcp_repair_opt { + __u32 opt_code; + __u32 opt_val; +}; + +struct tcp_repair_window { + __u32 snd_wl1; + __u32 snd_wnd; + __u32 max_window; + + __u32 rcv_wnd; + __u32 rcv_wup; +}; + +enum { + TCP_NO_QUEUE, + TCP_RECV_QUEUE, + TCP_SEND_QUEUE, + TCP_QUEUES_NR, +}; + +/* why fastopen failed from client perspective */ +enum tcp_fastopen_client_fail { + TFO_STATUS_UNSPEC, /* catch-all */ + TFO_COOKIE_UNAVAILABLE, /* if not in TFO_CLIENT_NO_COOKIE mode */ + TFO_DATA_NOT_ACKED, /* SYN-ACK did not ack SYN data */ + TFO_SYN_RETRANSMITTED, /* SYN-ACK did not ack SYN data after timeout */ +}; + +/* for TCP_INFO socket option */ +#define TCPI_OPT_TIMESTAMPS 1 +#define TCPI_OPT_SACK 2 +#define TCPI_OPT_WSCALE 4 +#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */ +#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */ +#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */ + +/* + * Sender's congestion state indicating normal or abnormal situations + * in the last round of packets sent. The state is driven by the ACK + * information and timer events. + */ +enum tcp_ca_state { + /* + * Nothing bad has been observed recently. + * No apparent reordering, packet loss, or ECN marks. + */ + TCP_CA_Open = 0, +#define TCPF_CA_Open (1< +#include #include #include "bpf_dctcp.skel.h" #include "bpf_cubic.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c index 9781d85cb223..e075d03ab630 100644 --- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -7,6 +7,7 @@ #include #include +#include #include diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 85f73261fab0..b8b48cac2ac3 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2020 Cloudflare #include +#include #include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index b25c9c45c148..d5b44b135c00 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -2,6 +2,12 @@ #include #include "cgroup_helpers.h" +#include + +#ifndef SOL_TCP +#define SOL_TCP IPPROTO_TCP +#endif + #define SOL_CUSTOM 0xdeadbeef static int getsetsockopt(void) @@ -11,6 +17,7 @@ static int getsetsockopt(void) char u8[4]; __u32 u32; char cc[16]; /* TCP_CA_NAME_MAX */ + struct tcp_zerocopy_receive zc; } buf = {}; socklen_t optlen; char *big_buf = NULL; @@ -154,6 +161,27 @@ static int getsetsockopt(void) goto err; } + /* TCP_ZEROCOPY_RECEIVE triggers */ + memset(&buf, 0, sizeof(buf)); + optlen = sizeof(buf.zc); + err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); + if (err) { + log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", + err, errno); + goto err; + } + + memset(&buf, 0, sizeof(buf)); + buf.zc.address = 12345; /* rejected by BPF */ + optlen = sizeof(buf.zc); + errno = 0; + err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); + if (errno != EPERM) { + log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", + err, errno); + goto err; + } + free(big_buf); close(fd); return 0; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 712df7b49cb1..d3597f81e6e9 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include -#include +#include #include +#include #include char _license[] SEC("license") = "GPL"; @@ -12,6 +12,10 @@ __u32 _version SEC("version") = 1; #define PAGE_SIZE 4096 #endif +#ifndef SOL_TCP +#define SOL_TCP IPPROTO_TCP +#endif + #define SOL_CUSTOM 0xdeadbeef struct sockopt_sk { @@ -57,6 +61,21 @@ int _getsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) { + /* Verify that TCP_ZEROCOPY_RECEIVE triggers. + * It has a custom implementation for performance + * reasons. + */ + + if (optval + sizeof(struct tcp_zerocopy_receive) > optval_end) + return 0; /* EPERM, bounds check */ + + if (((struct tcp_zerocopy_receive *)optval)->address != 0) + return 0; /* EPERM, unexpected data */ + + return 1; + } + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 238f5f61189e..1d429d67f8dd 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -16,7 +16,6 @@ typedef __u16 __sum16; #include #include #include -#include #include #include #include From b190ced50a5e98a604e9d029080f93ea78d63400 Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Thu, 11 May 2023 15:25:06 +0200 Subject: [PATCH 3782/4345] sctp: add bpf_bypass_getsockopt proto callback [ Upstream commit 2598619e012cee5273a2821441b9a051ad931249 ] Implement ->bpf_bypass_getsockopt proto callback and filter out SCTP_SOCKOPT_PEELOFF, SCTP_SOCKOPT_PEELOFF_FLAGS and SCTP_SOCKOPT_CONNECTX3 socket options from running eBPF hook on them. SCTP_SOCKOPT_PEELOFF and SCTP_SOCKOPT_PEELOFF_FLAGS options do fd_install(), and if BPF_CGROUP_RUN_PROG_GETSOCKOPT hook returns an error after success of the original handler sctp_getsockopt(...), userspace will receive an error from getsockopt syscall and will be not aware that fd was successfully installed into a fdtable. As pointed by Marcelo Ricardo Leitner it seems reasonable to skip bpf getsockopt hook for SCTP_SOCKOPT_CONNECTX3 sockopt too. Because internaly, it triggers connect() and if error is masked then userspace will be confused. This patch was born as a result of discussion around a new SCM_PIDFD interface: https://lore.kernel.org/all/20230413133355.350571-3-aleksandr.mikhalitsyn@canonical.com/ Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks") Cc: Daniel Borkmann Cc: Christian Brauner Cc: Stanislav Fomichev Cc: Neil Horman Cc: Marcelo Ricardo Leitner Cc: Xin Long Cc: linux-sctp@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org Suggested-by: Stanislav Fomichev Acked-by: Stanislav Fomichev Signed-off-by: Alexander Mikhalitsyn Acked-by: Xin Long Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sctp/socket.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 35d3eee26ea5..4a7f811abae4 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8039,6 +8039,22 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, return retval; } +static bool sctp_bpf_bypass_getsockopt(int level, int optname) +{ + if (level == SOL_SCTP) { + switch (optname) { + case SCTP_SOCKOPT_PEELOFF: + case SCTP_SOCKOPT_PEELOFF_FLAGS: + case SCTP_SOCKOPT_CONNECTX3: + return true; + default: + return false; + } + } + + return false; +} + static int sctp_hash(struct sock *sk) { /* STUB */ @@ -9407,6 +9423,7 @@ struct proto sctp_prot = { .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, + .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, @@ -9459,6 +9476,7 @@ struct proto sctpv6_prot = { .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, + .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, From ef7fe1b5c4fbc9a402bff70cb8aacf570afcab38 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 8 May 2023 23:55:02 -0700 Subject: [PATCH 3783/4345] libbpf: fix offsetof() and container_of() to work with CO-RE [ Upstream commit bdeeed3498c7871c17465bb4f11d1bc67f9098af ] It seems like __builtin_offset() doesn't preserve CO-RE field relocations properly. So if offsetof() macro is defined through __builtin_offset(), CO-RE-enabled BPF code using container_of() will be subtly and silently broken. To avoid this problem, redefine offsetof() and container_of() in the form that works with CO-RE relocations more reliably. Fixes: 5fbc220862fc ("tools/libpf: Add offsetof/container_of macro in bpf_helpers.h") Reported-by: Lennart Poettering Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230509065502.2306180-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- tools/lib/bpf/bpf_helpers.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 72b251110c4d..1c389b0f5499 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -42,16 +42,21 @@ /* * Helper macro to manipulate data structures */ -#ifndef offsetof -#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) -#endif -#ifndef container_of + +/* offsetof() definition that uses __builtin_offset() might not preserve field + * offset CO-RE relocation properly, so force-redefine offsetof() using + * old-school approach which works with CO-RE correctly + */ +#undef offsetof +#define offsetof(type, member) ((unsigned long)&((type *)0)->member) + +/* redefined container_of() to ensure we use the above offsetof() macro */ +#undef container_of #define container_of(ptr, type, member) \ ({ \ void *__mptr = (void *)(ptr); \ ((type *)(__mptr - offsetof(type, member))); \ }) -#endif /* * Helper macro to throw a compilation error if __bpf_unreachable() gets From 0be9de2ea01e8d52646e7310a7eef5459cf07ea8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 30 Jul 2021 16:41:59 +0200 Subject: [PATCH 3784/4345] nfc: constify several pointers to u8, char and sk_buff [ Upstream commit 3df40eb3a2ea58bf404a38f15a7a2768e4762cb0 ] Several functions receive pointers to u8, char or sk_buff but do not modify the contents so make them const. This allows doing the same for local variables and in total makes the code a little bit safer. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Jakub Kicinski Stable-dep-of: 0d9b41daa590 ("nfc: llcp: fix possible use of uninitialized variable in nfc_llcp_send_connect()") Signed-off-by: Sasha Levin --- include/net/nfc/nfc.h | 4 ++-- net/nfc/core.c | 4 ++-- net/nfc/hci/llc_shdlc.c | 10 ++++----- net/nfc/llcp.h | 8 +++---- net/nfc/llcp_commands.c | 46 ++++++++++++++++++++++------------------- net/nfc/llcp_core.c | 44 +++++++++++++++++++++------------------ net/nfc/nfc.h | 2 +- 7 files changed, 63 insertions(+), 55 deletions(-) diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 2cd3a261bcbc..32890e43f06c 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -266,7 +266,7 @@ struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp); int nfc_set_remote_general_bytes(struct nfc_dev *dev, - u8 *gt, u8 gt_len); + const u8 *gt, u8 gt_len); u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len); int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name, @@ -280,7 +280,7 @@ int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, - u8 *gb, size_t gb_len); + const u8 *gb, size_t gb_len); int nfc_tm_deactivated(struct nfc_dev *dev); int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb); diff --git a/net/nfc/core.c b/net/nfc/core.c index 2ef56366bd5f..10a3d740d155 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -634,7 +634,7 @@ error: return rc; } -int nfc_set_remote_general_bytes(struct nfc_dev *dev, u8 *gb, u8 gb_len) +int nfc_set_remote_general_bytes(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { pr_debug("dev_name=%s gb_len=%d\n", dev_name(&dev->dev), gb_len); @@ -663,7 +663,7 @@ int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb) EXPORT_SYMBOL(nfc_tm_data_received); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, - u8 *gb, size_t gb_len) + const u8 *gb, size_t gb_len) { int rc; diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 0eb4ddc056e7..02909e3e91ef 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -123,7 +123,7 @@ static bool llc_shdlc_x_lteq_y_lt_z(int x, int y, int z) return ((y >= x) || (y < z)) ? true : false; } -static struct sk_buff *llc_shdlc_alloc_skb(struct llc_shdlc *shdlc, +static struct sk_buff *llc_shdlc_alloc_skb(const struct llc_shdlc *shdlc, int payload_len) { struct sk_buff *skb; @@ -137,7 +137,7 @@ static struct sk_buff *llc_shdlc_alloc_skb(struct llc_shdlc *shdlc, } /* immediately sends an S frame. */ -static int llc_shdlc_send_s_frame(struct llc_shdlc *shdlc, +static int llc_shdlc_send_s_frame(const struct llc_shdlc *shdlc, enum sframe_type sframe_type, int nr) { int r; @@ -159,7 +159,7 @@ static int llc_shdlc_send_s_frame(struct llc_shdlc *shdlc, } /* immediately sends an U frame. skb may contain optional payload */ -static int llc_shdlc_send_u_frame(struct llc_shdlc *shdlc, +static int llc_shdlc_send_u_frame(const struct llc_shdlc *shdlc, struct sk_buff *skb, enum uframe_modifier uframe_modifier) { @@ -361,7 +361,7 @@ static void llc_shdlc_connect_complete(struct llc_shdlc *shdlc, int r) wake_up(shdlc->connect_wq); } -static int llc_shdlc_connect_initiate(struct llc_shdlc *shdlc) +static int llc_shdlc_connect_initiate(const struct llc_shdlc *shdlc) { struct sk_buff *skb; @@ -377,7 +377,7 @@ static int llc_shdlc_connect_initiate(struct llc_shdlc *shdlc) return llc_shdlc_send_u_frame(shdlc, skb, U_FRAME_RSET); } -static int llc_shdlc_connect_send_ua(struct llc_shdlc *shdlc) +static int llc_shdlc_connect_send_ua(const struct llc_shdlc *shdlc) { struct sk_buff *skb; diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index 97853c9cefc7..d49d4bf2e37c 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -221,15 +221,15 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *sk, struct socket *newsock); /* TLV API */ int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, - u8 *tlv_array, u16 tlv_array_len); + const u8 *tlv_array, u16 tlv_array_len); int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, - u8 *tlv_array, u16 tlv_array_len); + const u8 *tlv_array, u16 tlv_array_len); /* Commands API */ void nfc_llcp_recv(void *data, struct sk_buff *skb, int err); -u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length); +u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length); struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap); -struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, char *uri, +struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri, size_t uri_len); void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp); void nfc_llcp_free_sdp_tlv_list(struct hlist_head *sdp_head); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 475061c79c44..3c4172a5aeb5 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -15,7 +15,7 @@ #include "nfc.h" #include "llcp.h" -static u8 llcp_tlv_length[LLCP_TLV_MAX] = { +static const u8 llcp_tlv_length[LLCP_TLV_MAX] = { 0, 1, /* VERSION */ 2, /* MIUX */ @@ -29,7 +29,7 @@ static u8 llcp_tlv_length[LLCP_TLV_MAX] = { }; -static u8 llcp_tlv8(u8 *tlv, u8 type) +static u8 llcp_tlv8(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; @@ -37,7 +37,7 @@ static u8 llcp_tlv8(u8 *tlv, u8 type) return tlv[2]; } -static u16 llcp_tlv16(u8 *tlv, u8 type) +static u16 llcp_tlv16(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; @@ -46,37 +46,37 @@ static u16 llcp_tlv16(u8 *tlv, u8 type) } -static u8 llcp_tlv_version(u8 *tlv) +static u8 llcp_tlv_version(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_VERSION); } -static u16 llcp_tlv_miux(u8 *tlv) +static u16 llcp_tlv_miux(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_MIUX) & 0x7ff; } -static u16 llcp_tlv_wks(u8 *tlv) +static u16 llcp_tlv_wks(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_WKS); } -static u16 llcp_tlv_lto(u8 *tlv) +static u16 llcp_tlv_lto(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_LTO); } -static u8 llcp_tlv_opt(u8 *tlv) +static u8 llcp_tlv_opt(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_OPT); } -static u8 llcp_tlv_rw(u8 *tlv) +static u8 llcp_tlv_rw(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_RW) & 0xf; } -u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length) +u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length) { u8 *tlv, length; @@ -130,7 +130,7 @@ struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap) return sdres; } -struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, char *uri, +struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri, size_t uri_len) { struct nfc_llcp_sdp_tlv *sdreq; @@ -190,9 +190,10 @@ void nfc_llcp_free_sdp_tlv_list(struct hlist_head *head) } int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, - u8 *tlv_array, u16 tlv_array_len) + const u8 *tlv_array, u16 tlv_array_len) { - u8 *tlv = tlv_array, type, length, offset = 0; + const u8 *tlv = tlv_array; + u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); @@ -239,9 +240,10 @@ int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, } int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, - u8 *tlv_array, u16 tlv_array_len) + const u8 *tlv_array, u16 tlv_array_len) { - u8 *tlv = tlv_array, type, length, offset = 0; + const u8 *tlv = tlv_array; + u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); @@ -295,7 +297,7 @@ static struct sk_buff *llcp_add_header(struct sk_buff *pdu, return pdu; } -static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, u8 *tlv, +static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, const u8 *tlv, u8 tlv_length) { /* XXX Add an skb length check */ @@ -389,9 +391,10 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; - u8 *service_name_tlv = NULL, service_name_tlv_length; - u8 *miux_tlv = NULL, miux_tlv_length; - u8 *rw_tlv = NULL, rw_tlv_length, rw; + const u8 *service_name_tlv = NULL; + const u8 *miux_tlv = NULL; + const u8 *rw_tlv = NULL; + u8 service_name_tlv_length, miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; @@ -465,8 +468,9 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; - u8 *miux_tlv = NULL, miux_tlv_length; - u8 *rw_tlv = NULL, rw_tlv_length, rw; + const u8 *miux_tlv = NULL; + const u8 *rw_tlv = NULL; + u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index edadebb3efd2..fd43e75abd94 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -302,7 +302,7 @@ static char *wks[] = { "urn:nfc:sn:snep", }; -static int nfc_llcp_wks_sap(char *service_name, size_t service_name_len) +static int nfc_llcp_wks_sap(const char *service_name, size_t service_name_len) { int sap, num_wks; @@ -326,7 +326,7 @@ static int nfc_llcp_wks_sap(char *service_name, size_t service_name_len) static struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, - u8 *sn, size_t sn_len) + const u8 *sn, size_t sn_len) { struct sock *sk; struct nfc_llcp_sock *llcp_sock, *tmp_sock; @@ -523,7 +523,7 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) { u8 *gb_cur, version, version_length; u8 lto_length, wks_length, miux_length; - u8 *version_tlv = NULL, *lto_tlv = NULL, + const u8 *version_tlv = NULL, *lto_tlv = NULL, *wks_tlv = NULL, *miux_tlv = NULL; __be16 wks = cpu_to_be16(local->local_wks); u8 gb_len = 0; @@ -613,7 +613,7 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) return local->gb; } -int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) +int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { struct nfc_llcp_local *local; @@ -640,27 +640,27 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) local->remote_gb_len - 3); } -static u8 nfc_llcp_dsap(struct sk_buff *pdu) +static u8 nfc_llcp_dsap(const struct sk_buff *pdu) { return (pdu->data[0] & 0xfc) >> 2; } -static u8 nfc_llcp_ptype(struct sk_buff *pdu) +static u8 nfc_llcp_ptype(const struct sk_buff *pdu) { return ((pdu->data[0] & 0x03) << 2) | ((pdu->data[1] & 0xc0) >> 6); } -static u8 nfc_llcp_ssap(struct sk_buff *pdu) +static u8 nfc_llcp_ssap(const struct sk_buff *pdu) { return pdu->data[1] & 0x3f; } -static u8 nfc_llcp_ns(struct sk_buff *pdu) +static u8 nfc_llcp_ns(const struct sk_buff *pdu) { return pdu->data[2] >> 4; } -static u8 nfc_llcp_nr(struct sk_buff *pdu) +static u8 nfc_llcp_nr(const struct sk_buff *pdu) { return pdu->data[2] & 0xf; } @@ -802,7 +802,7 @@ out: } static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local, - u8 *sn, size_t sn_len) + const u8 *sn, size_t sn_len) { struct nfc_llcp_sock *llcp_sock; @@ -816,9 +816,10 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local, return llcp_sock; } -static u8 *nfc_llcp_connect_sn(struct sk_buff *skb, size_t *sn_len) +static const u8 *nfc_llcp_connect_sn(const struct sk_buff *skb, size_t *sn_len) { - u8 *tlv = &skb->data[2], type, length; + u8 type, length; + const u8 *tlv = &skb->data[2]; size_t tlv_array_len = skb->len - LLCP_HEADER_SIZE, offset = 0; while (offset < tlv_array_len) { @@ -876,7 +877,7 @@ static void nfc_llcp_recv_ui(struct nfc_llcp_local *local, } static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, - struct sk_buff *skb) + const struct sk_buff *skb) { struct sock *new_sk, *parent; struct nfc_llcp_sock *sock, *new_sock; @@ -894,7 +895,7 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, goto fail; } } else { - u8 *sn; + const u8 *sn; size_t sn_len; sn = nfc_llcp_connect_sn(skb, &sn_len); @@ -1113,7 +1114,7 @@ static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local, } static void nfc_llcp_recv_disc(struct nfc_llcp_local *local, - struct sk_buff *skb) + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; @@ -1156,7 +1157,8 @@ static void nfc_llcp_recv_disc(struct nfc_llcp_local *local, nfc_llcp_sock_put(llcp_sock); } -static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb) +static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; @@ -1189,7 +1191,8 @@ static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb) nfc_llcp_sock_put(llcp_sock); } -static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb) +static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; @@ -1227,12 +1230,13 @@ static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb) } static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, - struct sk_buff *skb) + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; - u8 dsap, ssap, *tlv, type, length, tid, sap; + u8 dsap, ssap, type, length, tid, sap; + const u8 *tlv; u16 tlv_len, offset; - char *service_name; + const char *service_name; size_t service_name_len; struct nfc_llcp_sdp_tlv *sdp; HLIST_HEAD(llc_sdres_list); diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index 889fefd64e56..de2ec66d7e83 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -48,7 +48,7 @@ void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_llcp_register_device(struct nfc_dev *dev); void nfc_llcp_unregister_device(struct nfc_dev *dev); -int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len); +int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len); u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len); int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); From 107e849f3c6a4de0ca597848331e240cc5c36c60 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 13 May 2023 13:52:04 +0200 Subject: [PATCH 3785/4345] nfc: llcp: fix possible use of uninitialized variable in nfc_llcp_send_connect() [ Upstream commit 0d9b41daa5907756a31772d8af8ac5ff25cf17c1 ] If sock->service_name is NULL, the local variable service_name_tlv_length will not be assigned by nfc_llcp_build_tlv(), later leading to using value frmo the stack. Smatch warning: net/nfc/llcp_commands.c:442 nfc_llcp_send_connect() error: uninitialized symbol 'service_name_tlv_length'. Fixes: de9e5aeb4f40 ("NFC: llcp: Fix usage of llcp_add_tlv()") Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/nfc/llcp_commands.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 3c4172a5aeb5..bb9f40563ff6 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -394,7 +394,8 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) const u8 *service_name_tlv = NULL; const u8 *miux_tlv = NULL; const u8 *rw_tlv = NULL; - u8 service_name_tlv_length, miux_tlv_length, rw_tlv_length, rw; + u8 service_name_tlv_length = 0; + u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; From 78f390aa0eb50501627429c0da7ed8e707230ead Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Fri, 12 May 2023 12:31:34 +0100 Subject: [PATCH 3786/4345] bpftool: JIT limited misreported as negative value on aarch64 [ Upstream commit 04cb8453a91c7c22f60ddadb6cef0d19abb33bb5 ] On aarch64, "bpftool feature" reports an incorrect BPF JIT limit: $ sudo /sbin/bpftool feature Scanning system configuration... bpf() syscall restricted to privileged users JIT compiler is enabled JIT compiler hardening is disabled JIT compiler kallsyms exports are enabled for root skipping kernel config, can't open file: No such file or directory Global memory limit for JIT compiler for unprivileged users is -201326592 bytes This is because /proc/sys/net/core/bpf_jit_limit reports $ sudo cat /proc/sys/net/core/bpf_jit_limit 68169519595520 ...and an int is assumed in read_procfs(). Change read_procfs() to return a long to avoid negative value reporting. Fixes: 7a4522bbef0c ("tools: bpftool: add probes for /proc/ eBPF parameters") Reported-by: Nicky Veitch Signed-off-by: Alan Maguire Signed-off-by: Daniel Borkmann Acked-by: Jiri Olsa Acked-by: Quentin Monnet Link: https://lore.kernel.org/bpf/20230512113134.58996-1-alan.maguire@oracle.com Signed-off-by: Sasha Levin --- tools/bpf/bpftool/feature.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 359960a8f1de..5f0b1397798e 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -135,12 +135,12 @@ static void print_end_section(void) /* Probing functions */ -static int read_procfs(const char *path) +static long read_procfs(const char *path) { char *endptr, *line = NULL; size_t len = 0; FILE *fd; - int res; + long res; fd = fopen(path, "r"); if (!fd) @@ -162,7 +162,7 @@ static int read_procfs(const char *path) static void probe_unprivileged_disabled(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -181,14 +181,14 @@ static void probe_unprivileged_disabled(void) printf("Unable to retrieve required privileges for bpf() syscall\n"); break; default: - printf("bpf() syscall restriction has unknown value %d\n", res); + printf("bpf() syscall restriction has unknown value %ld\n", res); } } } static void probe_jit_enable(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -210,7 +210,7 @@ static void probe_jit_enable(void) printf("Unable to retrieve JIT-compiler status\n"); break; default: - printf("JIT-compiler status has unknown value %d\n", + printf("JIT-compiler status has unknown value %ld\n", res); } } @@ -218,7 +218,7 @@ static void probe_jit_enable(void) static void probe_jit_harden(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -240,7 +240,7 @@ static void probe_jit_harden(void) printf("Unable to retrieve JIT hardening status\n"); break; default: - printf("JIT hardening status has unknown value %d\n", + printf("JIT hardening status has unknown value %ld\n", res); } } @@ -248,7 +248,7 @@ static void probe_jit_harden(void) static void probe_jit_kallsyms(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -267,14 +267,14 @@ static void probe_jit_kallsyms(void) printf("Unable to retrieve JIT kallsyms export status\n"); break; default: - printf("JIT kallsyms exports status has unknown value %d\n", res); + printf("JIT kallsyms exports status has unknown value %ld\n", res); } } } static void probe_jit_limit(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -287,7 +287,7 @@ static void probe_jit_limit(void) printf("Unable to retrieve global memory limit for JIT compiler for unprivileged users\n"); break; default: - printf("Global memory limit for JIT compiler for unprivileged users is %d bytes\n", res); + printf("Global memory limit for JIT compiler for unprivileged users is %ld bytes\n", res); } } } From 92bcd84941260f42a683fc7e3d1ebd8656897fb3 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 25 May 2023 13:13:58 +0200 Subject: [PATCH 3787/4345] regulator: core: Fix more error checking for debugfs_create_dir() [ Upstream commit 2715bb11cfff964aa33946847f9527cfbd4874f5 ] In case of failure, debugfs_create_dir() does not return NULL, but an error pointer. Most incorrect error checks were fixed, but the one in create_regulator() was forgotten. Fix the remaining error check. Fixes: 2bf1c45be3b8f3a3 ("regulator: Fix error checking for debugfs_create_dir") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/ee980a108b5854dd8ce3630f8f673e784e057d17.1685013051.git.geert+renesas@glider.be Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index f5ab74683b58..e4ff64d28c77 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1751,7 +1751,7 @@ static struct regulator *create_regulator(struct regulator_dev *rdev, if (err != -EEXIST) regulator->debugfs = debugfs_create_dir(supply_name, rdev->debugfs); - if (!regulator->debugfs) { + if (IS_ERR(regulator->debugfs)) { rdev_dbg(rdev, "Failed to create debugfs directory\n"); } else { debugfs_create_u32("uA_load", 0444, regulator->debugfs, From 8782dc2504da44ca27d6d0dc9d854ef44e848c68 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 25 May 2023 13:13:59 +0200 Subject: [PATCH 3788/4345] regulator: core: Streamline debugfs operations [ Upstream commit 08880713ceec023dd94d634f1e8902728c385939 ] If CONFIG_DEBUG_FS is not set: regulator: Failed to create debugfs directory ... regulator-dummy: Failed to create debugfs directory As per the comments for debugfs_create_dir(), errors returned by this function should be expected, and ignored: * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. * * NOTE: it's expected that most callers should _ignore_ the errors returned * by this function. Other debugfs functions handle the fact that the "dentry" * passed to them could be an error and they don't crash in that case. * Drivers should generally work fine even if debugfs fails to init anyway. Adhere to the debugfs spirit, and streamline all operations by: 1. Demoting the importance of the printed error messages to debug level, like is already done in create_regulator(), 2. Further ignoring any returned errors, as by design, all debugfs functions are no-ops when passed an error pointer. Fixes: 2bf1c45be3b8f3a3 ("regulator: Fix error checking for debugfs_create_dir") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/2f8bb6e113359ddfab7b59e4d4274bd4c06d6d0a.1685013051.git.geert+renesas@glider.be Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/regulator/core.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index e4ff64d28c77..52b75779dbb7 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1751,19 +1751,17 @@ static struct regulator *create_regulator(struct regulator_dev *rdev, if (err != -EEXIST) regulator->debugfs = debugfs_create_dir(supply_name, rdev->debugfs); - if (IS_ERR(regulator->debugfs)) { + if (IS_ERR(regulator->debugfs)) rdev_dbg(rdev, "Failed to create debugfs directory\n"); - } else { - debugfs_create_u32("uA_load", 0444, regulator->debugfs, - ®ulator->uA_load); - debugfs_create_u32("min_uV", 0444, regulator->debugfs, - ®ulator->voltage[PM_SUSPEND_ON].min_uV); - debugfs_create_u32("max_uV", 0444, regulator->debugfs, - ®ulator->voltage[PM_SUSPEND_ON].max_uV); - debugfs_create_file("constraint_flags", 0444, - regulator->debugfs, regulator, - &constraint_flags_fops); - } + + debugfs_create_u32("uA_load", 0444, regulator->debugfs, + ®ulator->uA_load); + debugfs_create_u32("min_uV", 0444, regulator->debugfs, + ®ulator->voltage[PM_SUSPEND_ON].min_uV); + debugfs_create_u32("max_uV", 0444, regulator->debugfs, + ®ulator->voltage[PM_SUSPEND_ON].max_uV); + debugfs_create_file("constraint_flags", 0444, regulator->debugfs, + regulator, &constraint_flags_fops); /* * Check now if the regulator is an always on regulator - if @@ -5032,10 +5030,8 @@ static void rdev_init_debugfs(struct regulator_dev *rdev) } rdev->debugfs = debugfs_create_dir(rname, debugfs_root); - if (IS_ERR(rdev->debugfs)) { - rdev_warn(rdev, "Failed to create debugfs directory\n"); - return; - } + if (IS_ERR(rdev->debugfs)) + rdev_dbg(rdev, "Failed to create debugfs directory\n"); debugfs_create_u32("use_count", 0444, rdev->debugfs, &rdev->use_count); @@ -5938,7 +5934,7 @@ static int __init regulator_init(void) debugfs_root = debugfs_create_dir("regulator", NULL); if (IS_ERR(debugfs_root)) - pr_warn("regulator: Failed to create debugfs directory\n"); + pr_debug("regulator: Failed to create debugfs directory\n"); #ifdef CONFIG_DEBUG_FS debugfs_create_file("supply_map", 0444, debugfs_root, NULL, From fb7d78feb55a3cd341ddc2d4981362cd24f854b0 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 20 May 2023 09:29:46 +0200 Subject: [PATCH 3789/4345] wifi: orinoco: Fix an error handling path in spectrum_cs_probe() [ Upstream commit 925244325159824385209e3e0e3f91fa6bf0646c ] Should spectrum_cs_config() fail, some resources need to be released as already done in the remove function. While at it, remove a useless and erroneous comment. The probe is spectrum_cs_probe(), not spectrum_cs_attach(). Fixes: 15b99ac17295 ("[PATCH] pcmcia: add return value to _config() functions") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/c0bc0c21c58ca477fc5521607615bafbf2aef8eb.1684567733.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/net/wireless/intersil/orinoco/spectrum_cs.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intersil/orinoco/spectrum_cs.c b/drivers/net/wireless/intersil/orinoco/spectrum_cs.c index 291ef97ed45e..841d623c621a 100644 --- a/drivers/net/wireless/intersil/orinoco/spectrum_cs.c +++ b/drivers/net/wireless/intersil/orinoco/spectrum_cs.c @@ -157,6 +157,7 @@ spectrum_cs_probe(struct pcmcia_device *link) { struct orinoco_private *priv; struct orinoco_pccard *card; + int ret; priv = alloc_orinocodev(sizeof(*card), &link->dev, spectrum_cs_hard_reset, @@ -169,8 +170,16 @@ spectrum_cs_probe(struct pcmcia_device *link) card->p_dev = link; link->priv = priv; - return spectrum_cs_config(link); -} /* spectrum_cs_attach */ + ret = spectrum_cs_config(link); + if (ret) + goto err_free_orinocodev; + + return 0; + +err_free_orinocodev: + free_orinocodev(priv); + return ret; +} static void spectrum_cs_detach(struct pcmcia_device *link) { From 86ebbcbdc7b1838d859ddfa8982275cb45912f9a Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 20 May 2023 09:38:22 +0200 Subject: [PATCH 3790/4345] wifi: orinoco: Fix an error handling path in orinoco_cs_probe() [ Upstream commit 67a81d911c01225f426cc6bee2373df044c1a9b7 ] Should orinoco_cs_config() fail, some resources need to be released as already done in the remove function. While at it, remove a useless and erroneous comment. The probe is orinoco_cs_probe(), not orinoco_cs_attach(). Fixes: 15b99ac17295 ("[PATCH] pcmcia: add return value to _config() functions") Signed-off-by: Christophe JAILLET Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/e24735ce4d82901d5f7ea08419eea53bfdde3d65.1684568286.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/net/wireless/intersil/orinoco/orinoco_cs.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_cs.c b/drivers/net/wireless/intersil/orinoco/orinoco_cs.c index a956f965a1e5..03bfd2482656 100644 --- a/drivers/net/wireless/intersil/orinoco/orinoco_cs.c +++ b/drivers/net/wireless/intersil/orinoco/orinoco_cs.c @@ -96,6 +96,7 @@ orinoco_cs_probe(struct pcmcia_device *link) { struct orinoco_private *priv; struct orinoco_pccard *card; + int ret; priv = alloc_orinocodev(sizeof(*card), &link->dev, orinoco_cs_hard_reset, NULL); @@ -107,8 +108,16 @@ orinoco_cs_probe(struct pcmcia_device *link) card->p_dev = link; link->priv = priv; - return orinoco_cs_config(link); -} /* orinoco_cs_attach */ + ret = orinoco_cs_config(link); + if (ret) + goto err_free_orinocodev; + + return 0; + +err_free_orinocodev: + free_orinocodev(priv); + return ret; +} static void orinoco_cs_detach(struct pcmcia_device *link) { From 5512db9bd40473238c841d0dc72cc5b19ea77657 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 20 May 2023 09:53:14 +0200 Subject: [PATCH 3791/4345] wifi: atmel: Fix an error handling path in atmel_probe() [ Upstream commit 6b92e4351a29af52c285fe235e6e4d1a75de04b2 ] Should atmel_config() fail, some resources need to be released as already done in the remove function. While at it, remove a useless and erroneous comment. The probe is atmel_probe(), not atmel_attach(). Fixes: 15b99ac17295 ("[PATCH] pcmcia: add return value to _config() functions") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1e65f174607a83348034197fa7d603bab10ba4a9.1684569156.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/net/wireless/atmel/atmel_cs.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/atmel/atmel_cs.c b/drivers/net/wireless/atmel/atmel_cs.c index 368eebefa741..e64f108d288b 100644 --- a/drivers/net/wireless/atmel/atmel_cs.c +++ b/drivers/net/wireless/atmel/atmel_cs.c @@ -73,6 +73,7 @@ struct local_info { static int atmel_probe(struct pcmcia_device *p_dev) { struct local_info *local; + int ret; dev_dbg(&p_dev->dev, "atmel_attach()\n"); @@ -83,8 +84,16 @@ static int atmel_probe(struct pcmcia_device *p_dev) p_dev->priv = local; - return atmel_config(p_dev); -} /* atmel_attach */ + ret = atmel_config(p_dev); + if (ret) + goto err_free_priv; + + return 0; + +err_free_priv: + kfree(p_dev->priv); + return ret; +} static void atmel_detach(struct pcmcia_device *link) { From 13cf0e3894d17489dd0a30b31555dfcaee39d958 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 2 Nov 2020 11:23:53 +0000 Subject: [PATCH 3792/4345] wl3501_cs: Fix misspelling and provide missing documentation [ Upstream commit 8b8a6f8c3b50193d161c598a6784e721128d6dc3 ] Fixes the following W=1 kernel build warning(s): In file included from drivers/net/wireless/wl3501_cs.c:57: drivers/net/wireless/wl3501_cs.c:143: warning: Function parameter or member 'reg_domain' not described in 'iw_valid_channel' drivers/net/wireless/wl3501_cs.c:143: warning: Excess function parameter 'reg_comain' description in 'iw_valid_channel' drivers/net/wireless/wl3501_cs.c:469: warning: Function parameter or member 'data' not described in 'wl3501_send_pkt' drivers/net/wireless/wl3501_cs.c:469: warning: Function parameter or member 'len' not described in 'wl3501_send_pkt' Cc: Kalle Valo Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Fox Chen Cc: de Melo Cc: Gustavo Niemeyer Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Lee Jones Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20201102112410.1049272-25-lee.jones@linaro.org Stable-dep-of: 391af06a02e7 ("wifi: wl3501_cs: Fix an error handling path in wl3501_probe()") Signed-off-by: Sasha Levin --- drivers/net/wireless/wl3501_cs.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c index ccf6344ed6fd..cb71b73853f4 100644 --- a/drivers/net/wireless/wl3501_cs.c +++ b/drivers/net/wireless/wl3501_cs.c @@ -134,7 +134,7 @@ static const struct { /** * iw_valid_channel - validate channel in regulatory domain - * @reg_comain: regulatory domain + * @reg_domain: regulatory domain * @channel: channel to validate * * Returns 0 if invalid in the specified regulatory domain, non-zero if valid. @@ -458,11 +458,9 @@ out: /** * wl3501_send_pkt - Send a packet. * @this: Card - * - * Send a packet. - * - * data = Ethernet raw frame. (e.g. data[0] - data[5] is Dest MAC Addr, + * @data: Ethernet raw frame. (e.g. data[0] - data[5] is Dest MAC Addr, * data[6] - data[11] is Src MAC Addr) + * @len: Packet length * Ref: IEEE 802.11 */ static int wl3501_send_pkt(struct wl3501_card *this, u8 *data, u16 len) From cbd44a9e1cf1952d0641302934afa5c90ead8d00 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 2 Sep 2021 11:10:37 -0700 Subject: [PATCH 3793/4345] net: create netdev->dev_addr assignment helpers [ Upstream commit 48eab831ae8b9f7002a533fa4235eed63ea1f1a3 ] Recent work on converting address list to a tree made it obvious we need an abstraction around writing netdev->dev_addr. Without such abstraction updating the main device address is invisible to the core. Introduce a number of helpers which for now just wrap memcpy() but in the future can make necessary changes to the address tree. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller Stable-dep-of: 391af06a02e7 ("wifi: wl3501_cs: Fix an error handling path in wl3501_probe()") Signed-off-by: Sasha Levin --- include/linux/etherdevice.h | 12 ++++++++++++ include/linux/netdevice.h | 18 ++++++++++++++++++ 2 files changed, 30 insertions(+) diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 99209f50915f..b060514bf25d 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -299,6 +299,18 @@ static inline void ether_addr_copy(u8 *dst, const u8 *src) #endif } +/** + * eth_hw_addr_set - Assign Ethernet address to a net_device + * @dev: pointer to net_device structure + * @addr: address to assign + * + * Assign given address to the net_device, addr_assign_type is not changed. + */ +static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) +{ + ether_addr_copy(dev->dev_addr, addr); +} + /** * eth_hw_addr_inherit - Copy dev_addr from another net_device * @dst: pointer to net_device to copy dev_addr to diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8f03cc42bd43..302abfc2a1f6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4474,6 +4474,24 @@ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ +static inline void +__dev_addr_set(struct net_device *dev, const u8 *addr, size_t len) +{ + memcpy(dev->dev_addr, addr, len); +} + +static inline void dev_addr_set(struct net_device *dev, const u8 *addr) +{ + __dev_addr_set(dev, addr, dev->addr_len); +} + +static inline void +dev_addr_mod(struct net_device *dev, unsigned int offset, + const u8 *addr, size_t len) +{ + memcpy(&dev->dev_addr[offset], addr, len); +} + int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, From b6f793de619b722ceb001b0c2d55e6aac4b81795 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 18 Oct 2021 16:50:20 -0700 Subject: [PATCH 3794/4345] wl3501_cs: use eth_hw_addr_set() [ Upstream commit 18774612246d036c04ce9fee7f67192f96f48725 ] Commit 406f42fa0d3c ("net-next: When a bond have a massive amount of VLANs...") introduced a rbtree for faster Ethernet address look up. To maintain netdev->dev_addr in this tree we need to make all the writes to it got through appropriate helpers. Signed-off-by: Jakub Kicinski Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20211018235021.1279697-15-kuba@kernel.org Stable-dep-of: 391af06a02e7 ("wifi: wl3501_cs: Fix an error handling path in wl3501_probe()") Signed-off-by: Sasha Levin --- drivers/net/wireless/wl3501_cs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c index cb71b73853f4..7351a2c127ad 100644 --- a/drivers/net/wireless/wl3501_cs.c +++ b/drivers/net/wireless/wl3501_cs.c @@ -1945,8 +1945,7 @@ static int wl3501_config(struct pcmcia_device *link) goto failed; } - for (i = 0; i < 6; i++) - dev->dev_addr[i] = ((char *)&this->mac_addr)[i]; + eth_hw_addr_set(dev, this->mac_addr); /* print probe information */ printk(KERN_INFO "%s: wl3501 @ 0x%3.3x, IRQ %d, " From 18d71562f70de4ec18455b7ca44a8825bc17494b Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 20 May 2023 10:05:08 +0200 Subject: [PATCH 3795/4345] wifi: wl3501_cs: Fix an error handling path in wl3501_probe() [ Upstream commit 391af06a02e7642039ac5f6c4b2c034ab0992b5d ] Should wl3501_config() fail, some resources need to be released as already done in the remove function. Fixes: 15b99ac17295 ("[PATCH] pcmcia: add return value to _config() functions") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/7cc9c9316489b7d69b36aeb0edd3123538500b41.1684569865.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/net/wireless/wl3501_cs.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c index 7351a2c127ad..4c408fd7c159 100644 --- a/drivers/net/wireless/wl3501_cs.c +++ b/drivers/net/wireless/wl3501_cs.c @@ -1862,6 +1862,7 @@ static int wl3501_probe(struct pcmcia_device *p_dev) { struct net_device *dev; struct wl3501_card *this; + int ret; /* The io structure describes IO port mapping */ p_dev->resource[0]->end = 16; @@ -1873,8 +1874,7 @@ static int wl3501_probe(struct pcmcia_device *p_dev) dev = alloc_etherdev(sizeof(struct wl3501_card)); if (!dev) - goto out_link; - + return -ENOMEM; dev->netdev_ops = &wl3501_netdev_ops; dev->watchdog_timeo = 5 * HZ; @@ -1887,9 +1887,15 @@ static int wl3501_probe(struct pcmcia_device *p_dev) netif_stop_queue(dev); p_dev->priv = dev; - return wl3501_config(p_dev); -out_link: - return -ENOMEM; + ret = wl3501_config(p_dev); + if (ret) + goto out_free_etherdev; + + return 0; + +out_free_etherdev: + free_netdev(dev); + return ret; } static int wl3501_config(struct pcmcia_device *link) From a66e3fd3801a88d4154051cc86b4423119e4cbfe Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 3 Jun 2022 19:44:13 +0300 Subject: [PATCH 3796/4345] wifi: ray_cs: Utilize strnlen() in parse_addr() [ Upstream commit 9e8e9187673cb24324f9165dd47b2b28f60b0b10 ] Instead of doing simple operations and using an additional variable on stack, utilize strnlen() and reuse len variable. Signed-off-by: Andy Shevchenko Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220603164414.48436-1-andriy.shevchenko@linux.intel.com Stable-dep-of: 4f8d66a9fb2e ("wifi: ray_cs: Fix an error handling path in ray_probe()") Signed-off-by: Sasha Levin --- drivers/net/wireless/ray_cs.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 091eea0d958d..5dcd86f81cbf 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -1641,31 +1641,29 @@ static void authenticate_timeout(struct timer_list *t) /*===========================================================================*/ static int parse_addr(char *in_str, UCHAR *out) { + int i, k; int len; - int i, j, k; int status; if (in_str == NULL) return 0; - if ((len = strlen(in_str)) < 2) + len = strnlen(in_str, ADDRLEN * 2 + 1) - 1; + if (len < 1) return 0; memset(out, 0, ADDRLEN); status = 1; - j = len - 1; - if (j > 12) - j = 12; i = 5; - while (j > 0) { - if ((k = hex_to_bin(in_str[j--])) != -1) + while (len > 0) { + if ((k = hex_to_bin(in_str[len--])) != -1) out[i] = k; else return 0; - if (j == 0) + if (len == 0) break; - if ((k = hex_to_bin(in_str[j--])) != -1) + if ((k = hex_to_bin(in_str[len--])) != -1) out[i] += k << 4; else return 0; From 8825991838fc4b9cb9ca24f658fa9d8c94f397c3 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 3 Jun 2022 19:44:14 +0300 Subject: [PATCH 3797/4345] wifi: ray_cs: Drop useless status variable in parse_addr() [ Upstream commit 4dfc63c002a555a2c3c34d89009532ad803be876 ] The status variable assigned only once and used also only once. Replace it's usage by actual value. Signed-off-by: Andy Shevchenko Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220603164414.48436-2-andriy.shevchenko@linux.intel.com Stable-dep-of: 4f8d66a9fb2e ("wifi: ray_cs: Fix an error handling path in ray_probe()") Signed-off-by: Sasha Levin --- drivers/net/wireless/ray_cs.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 5dcd86f81cbf..95d5ce1b6dfa 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -1643,7 +1643,6 @@ static int parse_addr(char *in_str, UCHAR *out) { int i, k; int len; - int status; if (in_str == NULL) return 0; @@ -1652,7 +1651,6 @@ static int parse_addr(char *in_str, UCHAR *out) return 0; memset(out, 0, ADDRLEN); - status = 1; i = 5; while (len > 0) { @@ -1670,7 +1668,7 @@ static int parse_addr(char *in_str, UCHAR *out) if (!i--) break; } - return status; + return 1; } /*===========================================================================*/ From c10c6ea9b3a27ceb42ed343b41f06c906a7d3d13 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 20 May 2023 10:13:22 +0200 Subject: [PATCH 3798/4345] wifi: ray_cs: Fix an error handling path in ray_probe() [ Upstream commit 4f8d66a9fb2edcd05c1e563456a55a08910bfb37 ] Should ray_config() fail, some resources need to be released as already done in the remove function. While at it, remove a useless and erroneous comment. The probe is ray_probe(), not ray_attach(). Fixes: 15b99ac17295 ("[PATCH] pcmcia: add return value to _config() functions") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/8c544d18084f8b37dd108e844f7e79e85ff708ff.1684570373.git.christophe.jaillet@wanadoo.fr Signed-off-by: Sasha Levin --- drivers/net/wireless/ray_cs.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 95d5ce1b6dfa..bf1282702761 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -270,13 +270,14 @@ static int ray_probe(struct pcmcia_device *p_dev) { ray_dev_t *local; struct net_device *dev; + int ret; dev_dbg(&p_dev->dev, "ray_attach()\n"); /* Allocate space for private device-specific data */ dev = alloc_etherdev(sizeof(ray_dev_t)); if (!dev) - goto fail_alloc_dev; + return -ENOMEM; local = netdev_priv(dev); local->finder = p_dev; @@ -313,11 +314,16 @@ static int ray_probe(struct pcmcia_device *p_dev) timer_setup(&local->timer, NULL, 0); this_device = p_dev; - return ray_config(p_dev); + ret = ray_config(p_dev); + if (ret) + goto err_free_dev; -fail_alloc_dev: - return -ENOMEM; -} /* ray_attach */ + return 0; + +err_free_dev: + free_netdev(dev); + return ret; +} static void ray_detach(struct pcmcia_device *link) { From 1044187e7249073f719ebbf9e5ffb4f16f99e555 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Wed, 17 May 2023 18:03:17 +0300 Subject: [PATCH 3799/4345] wifi: ath9k: don't allow to overwrite ENDPOINT0 attributes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 061b0cb9327b80d7a0f63a33e7c3e2a91a71f142 ] A bad USB device is able to construct a service connection response message with target endpoint being ENDPOINT0 which is reserved for HTC_CTRL_RSVD_SVC and should not be modified to be used for any other services. Reject such service connection responses. Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: fb9987d0f748 ("ath9k_htc: Support for AR9271 chipset.") Reported-by: syzbot+b68fbebe56d8362907e8@syzkaller.appspotmail.com Signed-off-by: Fedor Pchelkin Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230516150427.79469-1-pchelkin@ispras.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/htc_hst.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c index fe62ff668f75..99667aba289d 100644 --- a/drivers/net/wireless/ath/ath9k/htc_hst.c +++ b/drivers/net/wireless/ath/ath9k/htc_hst.c @@ -114,7 +114,13 @@ static void htc_process_conn_rsp(struct htc_target *target, if (svc_rspmsg->status == HTC_SERVICE_SUCCESS) { epid = svc_rspmsg->endpoint_id; - if (epid < 0 || epid >= ENDPOINT_MAX) + + /* Check that the received epid for the endpoint to attach + * a new service is valid. ENDPOINT0 can't be used here as it + * is already reserved for HTC_CTRL_RSVD_SVC service and thus + * should not be modified. + */ + if (epid <= ENDPOINT0 || epid >= ENDPOINT_MAX) return; service_id = be16_to_cpu(svc_rspmsg->service_id); From b2aeb97fd470206e67f7b3b4a3e68212a13f747b Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 28 May 2023 00:28:33 +0200 Subject: [PATCH 3800/4345] wifi: rsi: Do not configure WoWlan in shutdown hook if not enabled [ Upstream commit b241e260820b68c09586e8a0ae0fc23c0e3215bd ] In case WoWlan was never configured during the operation of the system, the hw->wiphy->wowlan_config will be NULL. rsi_config_wowlan() checks whether wowlan_config is non-NULL and if it is not, then WARNs about it. The warning is valid, as during normal operation the rsi_config_wowlan() should only ever be called with non-NULL wowlan_config. In shutdown this rsi_config_wowlan() should only ever be called if WoWlan was configured before by the user. Add checks for non-NULL wowlan_config into the shutdown hook. While at it, check whether the wiphy is also non-NULL before accessing wowlan_config . Drop the single-use wowlan_config variable, just inline it into function call. Fixes: 16bbc3eb8372 ("rsi: fix null pointer dereference during rsi_shutdown()") Signed-off-by: Marek Vasut Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230527222833.273741-1-marex@denx.de Signed-off-by: Sasha Levin --- drivers/net/wireless/rsi/rsi_91x_sdio.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c index 8108f941ccd3..2c26376faeac 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c @@ -1463,10 +1463,8 @@ static void rsi_shutdown(struct device *dev) rsi_dbg(ERR_ZONE, "SDIO Bus shutdown =====>\n"); - if (hw) { - struct cfg80211_wowlan *wowlan = hw->wiphy->wowlan_config; - - if (rsi_config_wowlan(adapter, wowlan)) + if (hw && hw->wiphy && hw->wiphy->wowlan_config) { + if (rsi_config_wowlan(adapter, hw->wiphy->wowlan_config)) rsi_dbg(ERR_ZONE, "Failed to configure WoWLAN\n"); } From 22da8363e35fa143a704e2a7803d26ce605a7012 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 28 May 2023 00:28:59 +0200 Subject: [PATCH 3801/4345] wifi: rsi: Do not set MMC_PM_KEEP_POWER in shutdown [ Upstream commit e74f562328b03fbe9cf438f958464dff3a644dfc ] It makes no sense to set MMC_PM_KEEP_POWER in shutdown. The flag indicates to the MMC subsystem to keep the slot powered on during suspend, but in shutdown the slot should actually be powered off. Drop this call. Fixes: 063848c3e155 ("rsi: sdio: Add WOWLAN support for S5 shutdown state") Signed-off-by: Marek Vasut Reviewed-by: Simon Horman Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230527222859.273768-1-marex@denx.de Signed-off-by: Sasha Levin --- drivers/net/wireless/rsi/rsi_91x_sdio.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c index 2c26376faeac..b1d3aea10d7d 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c @@ -1479,9 +1479,6 @@ static void rsi_shutdown(struct device *dev) if (sdev->write_fail) rsi_dbg(INFO_ZONE, "###### Device is not ready #######\n"); - if (rsi_set_sdio_pm_caps(adapter)) - rsi_dbg(INFO_ZONE, "Setting power management caps failed\n"); - rsi_dbg(INFO_ZONE, "***** RSI module shut down *****\n"); } From ac23d7f41426eded0ff81038bc8540da7f3211b1 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 19 May 2023 10:18:25 -0700 Subject: [PATCH 3802/4345] watchdog/perf: define dummy watchdog_update_hrtimer_threshold() on correct config [ Upstream commit 5e008df11c55228a86a1bae692cc2002503572c9 ] Patch series "watchdog/hardlockup: Add the buddy hardlockup detector", v5. This patch series adds the "buddy" hardlockup detector. In brief, the buddy hardlockup detector can detect hardlockups without arch-level support by having CPUs checkup on a "buddy" CPU periodically. Given the new design of this patch series, testing all combinations is fairly difficult. I've attempted to make sure that all combinations of CONFIG_ options are good, but it wouldn't surprise me if I missed something. I apologize in advance and I'll do my best to fix any problems that are found. This patch (of 18): The real watchdog_update_hrtimer_threshold() is defined in kernel/watchdog_hld.c. That file is included if CONFIG_HARDLOCKUP_DETECTOR_PERF and the function is defined in that file if CONFIG_HARDLOCKUP_CHECK_TIMESTAMP. The dummy version of the function in "nmi.h" didn't get that quite right. While this doesn't appear to be a huge deal, it's nice to make it consistent. It doesn't break builds because CHECK_TIMESTAMP is only defined by x86 so others don't get a double definition, and x86 uses perf lockup detector, so it gets the out of line version. Link: https://lkml.kernel.org/r/20230519101840.v5.18.Ia44852044cdcb074f387e80df6b45e892965d4a1@changeid Link: https://lkml.kernel.org/r/20230519101840.v5.1.I8cbb2f4fa740528fcfade4f5439b6cdcdd059251@changeid Fixes: 7edaeb6841df ("kernel/watchdog: Prevent false positives with turbo modes") Signed-off-by: Douglas Anderson Reviewed-by: Nicholas Piggin Reviewed-by: Petr Mladek Cc: Andi Kleen Cc: Catalin Marinas Cc: Chen-Yu Tsai Cc: Christophe Leroy Cc: Daniel Thompson Cc: "David S. Miller" Cc: Guenter Roeck Cc: Ian Rogers Cc: Lecopzer Chen Cc: Marc Zyngier Cc: Mark Rutland Cc: Masayoshi Mizuma Cc: Matthias Kaehlcke Cc: Michael Ellerman Cc: Pingfan Liu Cc: Randy Dunlap Cc: "Ravi V. Shankar" Cc: Ricardo Neri Cc: Stephane Eranian Cc: Stephen Boyd Cc: Sumit Garg Cc: Tzung-Bi Shih Cc: Will Deacon Cc: Colin Cross Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- include/linux/nmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index f700ff2df074..0db377ff8f60 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -197,7 +197,7 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh); #endif #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ - defined(CONFIG_HARDLOCKUP_DETECTOR) + defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) void watchdog_update_hrtimer_threshold(u64 period); #else static inline void watchdog_update_hrtimer_threshold(u64 period) { } From fdb07728d8ffa0f2f86767f3ef3d1bbe2e8270cb Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 19 May 2023 10:18:26 -0700 Subject: [PATCH 3803/4345] watchdog/perf: more properly prevent false positives with turbo modes [ Upstream commit 4379e59fe5665cfda737e45b8bf2f05321ef049c ] Currently, in the watchdog_overflow_callback() we first check to see if the watchdog had been touched and _then_ we handle the workaround for turbo mode. This order should be reversed. Specifically, "touching" the hardlockup detector's watchdog should avoid lockups being detected for one period that should be roughly the same regardless of whether we're running turbo or not. That means that we should do the extra accounting for turbo _before_ we look at (and clear) the global indicating that we've been touched. NOTE: this fix is made based on code inspection. I am not aware of any reports where the old code would have generated false positives. That being said, this order seems more correct and also makes it easier down the line to share code with the "buddy" hardlockup detector. Link: https://lkml.kernel.org/r/20230519101840.v5.2.I843b0d1de3e096ba111a179f3adb16d576bef5c7@changeid Fixes: 7edaeb6841df ("kernel/watchdog: Prevent false positives with turbo modes") Signed-off-by: Douglas Anderson Cc: Andi Kleen Cc: Catalin Marinas Cc: Chen-Yu Tsai Cc: Christophe Leroy Cc: Colin Cross Cc: Daniel Thompson Cc: "David S. Miller" Cc: Guenter Roeck Cc: Ian Rogers Cc: Lecopzer Chen Cc: Marc Zyngier Cc: Mark Rutland Cc: Masayoshi Mizuma Cc: Matthias Kaehlcke Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Petr Mladek Cc: Pingfan Liu Cc: Randy Dunlap Cc: "Ravi V. Shankar" Cc: Ricardo Neri Cc: Stephane Eranian Cc: Stephen Boyd Cc: Sumit Garg Cc: Tzung-Bi Shih Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- kernel/watchdog_hld.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 247bf0b1582c..1e8a49dc956e 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -114,14 +114,14 @@ static void watchdog_overflow_callback(struct perf_event *event, /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; + if (!watchdog_check_timestamp()) + return; + if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; } - if (!watchdog_check_timestamp()) - return; - /* check for a hardlockup * This is done by making sure our timer interrupt * is incrementing. The timer interrupt should have From 6cb477e7226bbceb9ca3f7fc306cdadf3eb92e7a Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Sat, 27 May 2023 20:34:34 +0800 Subject: [PATCH 3804/4345] kexec: fix a memory leak in crash_shrink_memory() [ Upstream commit 1cba6c4309f03de570202c46f03df3f73a0d4c82 ] Patch series "kexec: enable kexec_crash_size to support two crash kernel regions". When crashkernel=X fails to reserve region under 4G, it will fall back to reserve region above 4G and a region of the default size will also be reserved under 4G. Unfortunately, /sys/kernel/kexec_crash_size only supports one crash kernel region now, the user cannot sense the low memory reserved by reading /sys/kernel/kexec_crash_size. Also, low memory cannot be freed by writing this file. For example: resource_size(crashk_res) = 512M resource_size(crashk_low_res) = 256M The result of 'cat /sys/kernel/kexec_crash_size' is 512M, but it should be 768M. When we execute 'echo 0 > /sys/kernel/kexec_crash_size', the size of crashk_res becomes 0 and resource_size(crashk_low_res) is still 256 MB, which is incorrect. Since crashk_res manages the memory with high address and crashk_low_res manages the memory with low address, crashk_low_res is shrunken only when all crashk_res is shrunken. And because when there is only one crash kernel region, crashk_res is always used. Therefore, if all crashk_res is shrunken and crashk_low_res still exists, swap them. This patch (of 6): If the value of parameter 'new_size' is in the semi-open and semi-closed interval (crashk_res.end - KEXEC_CRASH_MEM_ALIGN + 1, crashk_res.end], the calculation result of ram_res is: ram_res->start = crashk_res.end + 1 ram_res->end = crashk_res.end The operation of insert_resource() fails, and ram_res is not added to iomem_resource. As a result, the memory of the control block ram_res is leaked. In fact, on all architectures, the start address and size of crashk_res are already aligned by KEXEC_CRASH_MEM_ALIGN. Therefore, we do not need to round up crashk_res.start again. Instead, we should round up 'new_size' in advance. Link: https://lkml.kernel.org/r/20230527123439.772-1-thunder.leizhen@huawei.com Link: https://lkml.kernel.org/r/20230527123439.772-2-thunder.leizhen@huawei.com Fixes: 6480e5a09237 ("kdump: add missing RAM resource in crash_shrink_memory()") Fixes: 06a7f711246b ("kexec: premit reduction of the reserved memory size") Signed-off-by: Zhen Lei Acked-by: Baoquan He Cc: Cong Wang Cc: Eric W. Biederman Cc: Michael Holzheu Signed-off-by: Andrew Morton Signed-off-by: Sasha Levin --- kernel/kexec_core.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 7a8104d48997..3a37fc62dc95 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1029,6 +1029,7 @@ int crash_shrink_memory(unsigned long new_size) start = crashk_res.start; end = crashk_res.end; old_size = (end == 0) ? 0 : end - start + 1; + new_size = roundup(new_size, KEXEC_CRASH_MEM_ALIGN); if (new_size >= old_size) { ret = (new_size == old_size) ? 0 : -EINVAL; goto unlock; @@ -1040,9 +1041,7 @@ int crash_shrink_memory(unsigned long new_size) goto unlock; } - start = roundup(start, KEXEC_CRASH_MEM_ALIGN); - end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN); - + end = start + new_size; crash_free_reserved_phys_range(end, crashk_res.end); if ((start == end) && (crashk_res.parent != NULL)) From 6b22c2c649a17b6ef3aad3b484c6b88800528d8e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 22:27:04 +0200 Subject: [PATCH 3805/4345] memstick r592: make memstick_debug_get_tpc_name() static [ Upstream commit 434587df9f7fd68575f99a889cc5f2efc2eaee5e ] There are no other files referencing this function, apparently it was left global to avoid an 'unused function' warning when the only caller is left out. With a 'W=1' build, it causes a 'missing prototype' warning though: drivers/memstick/host/r592.c:47:13: error: no previous prototype for 'memstick_debug_get_tpc_name' [-Werror=missing-prototypes] Annotate the function as 'static __maybe_unused' to avoid both problems. Fixes: 926341250102 ("memstick: add driver for Ricoh R5C592 card reader") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516202714.560929-1-arnd@kernel.org Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin --- drivers/memstick/host/r592.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/memstick/host/r592.c b/drivers/memstick/host/r592.c index dd06c18495eb..0e37c6a5ee36 100644 --- a/drivers/memstick/host/r592.c +++ b/drivers/memstick/host/r592.c @@ -44,12 +44,10 @@ static const char *tpc_names[] = { * memstick_debug_get_tpc_name - debug helper that returns string for * a TPC number */ -const char *memstick_debug_get_tpc_name(int tpc) +static __maybe_unused const char *memstick_debug_get_tpc_name(int tpc) { return tpc_names[tpc-1]; } -EXPORT_SYMBOL(memstick_debug_get_tpc_name); - /* Read a register*/ static inline u32 r592_read_reg(struct r592_device *dev, int address) From 581401cd3cf9f9ebffd6b65769fe016007111092 Mon Sep 17 00:00:00 2001 From: Remi Pommarel Date: Fri, 9 Jun 2023 11:37:44 +0200 Subject: [PATCH 3806/4345] wifi: ath9k: Fix possible stall on ath9k_txq_list_has_key() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 75086cc6dee046e3fbb3dba148b376d8802f83bc ] On EDMA capable hardware, ath9k_txq_list_has_key() can enter infinite loop if it is called while all txq_fifos have packets that use different key that the one we are looking for. Fix it by exiting the loop if all txq_fifos have been checked already. Because this loop is called under spin_lock_bh() (see ath_txq_lock) it causes the following rcu stall: rcu: INFO: rcu_sched self-detected stall on CPU ath10k_pci 0000:01:00.0: failed to read temperature -11 rcu: 1-....: (5254 ticks this GP) idle=189/1/0x4000000000000002 softirq=8442983/8442984 fqs=2579 (t=5257 jiffies g=17983297 q=334) Task dump for CPU 1: task:hostapd state:R running task stack: 0 pid: 297 ppid: 289 flags:0x0000000a Call trace: dump_backtrace+0x0/0x170 show_stack+0x1c/0x24 sched_show_task+0x140/0x170 dump_cpu_task+0x48/0x54 rcu_dump_cpu_stacks+0xf0/0x134 rcu_sched_clock_irq+0x8d8/0x9fc update_process_times+0xa0/0xec tick_sched_timer+0x5c/0xd0 __hrtimer_run_queues+0x154/0x320 hrtimer_interrupt+0x120/0x2f0 arch_timer_handler_virt+0x38/0x44 handle_percpu_devid_irq+0x9c/0x1e0 handle_domain_irq+0x64/0x90 gic_handle_irq+0x78/0xb0 call_on_irq_stack+0x28/0x38 do_interrupt_handler+0x54/0x5c el1_interrupt+0x2c/0x4c el1h_64_irq_handler+0x14/0x1c el1h_64_irq+0x74/0x78 ath9k_txq_has_key+0x1bc/0x250 [ath9k] ath9k_set_key+0x1cc/0x3dc [ath9k] drv_set_key+0x78/0x170 ieee80211_key_replace+0x564/0x6cc ieee80211_key_link+0x174/0x220 ieee80211_add_key+0x11c/0x300 nl80211_new_key+0x12c/0x330 genl_family_rcv_msg_doit+0xbc/0x11c genl_rcv_msg+0xd8/0x1c4 netlink_rcv_skb+0x40/0x100 genl_rcv+0x3c/0x50 netlink_unicast+0x1ec/0x2c0 netlink_sendmsg+0x198/0x3c0 ____sys_sendmsg+0x210/0x250 ___sys_sendmsg+0x78/0xc4 __sys_sendmsg+0x4c/0x90 __arm64_sys_sendmsg+0x28/0x30 invoke_syscall.constprop.0+0x60/0x100 do_el0_svc+0x48/0xd0 el0_svc+0x14/0x50 el0t_64_sync_handler+0xa8/0xb0 el0t_64_sync+0x158/0x15c This rcu stall is hard to reproduce as is, but changing ATH_TXFIFO_DEPTH from 8 to 2 makes it reasonably easy to reproduce. Fixes: ca2848022c12 ("ath9k: Postpone key cache entry deletion for TXQ frames reference it") Signed-off-by: Remi Pommarel Tested-by: Nicolas Escande Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230609093744.1985-1-repk@triplefau.lt Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/main.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index ac354dfc5055..2bd4d295c9bd 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -850,7 +850,7 @@ static bool ath9k_txq_list_has_key(struct list_head *txq_list, u32 keyix) static bool ath9k_txq_has_key(struct ath_softc *sc, u32 keyix) { struct ath_hw *ah = sc->sc_ah; - int i; + int i, j; struct ath_txq *txq; bool key_in_use = false; @@ -868,8 +868,9 @@ static bool ath9k_txq_has_key(struct ath_softc *sc, u32 keyix) if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) { int idx = txq->txq_tailidx; - while (!key_in_use && - !list_empty(&txq->txq_fifo[idx])) { + for (j = 0; !key_in_use && + !list_empty(&txq->txq_fifo[idx]) && + j < ATH_TXFIFO_DEPTH; j++) { key_in_use = ath9k_txq_list_has_key( &txq->txq_fifo[idx], keyix); INCR(idx, ATH_TXFIFO_DEPTH); From 2715617c2aad5092c7cb9c75020d2af051f9e664 Mon Sep 17 00:00:00 2001 From: Edwin Peer Date: Sun, 11 Jun 2023 13:51:08 +0300 Subject: [PATCH 3807/4345] rtnetlink: extend RTEXT_FILTER_SKIP_STATS to IFLA_VF_INFO [ Upstream commit fa0e21fa44438a0e856d42224bfa24641d37b979 ] This filter already exists for excluding IPv6 SNMP stats. Extend its definition to also exclude IFLA_VF_INFO stats in RTM_GETLINK. This patch constitutes a partial fix for a netlink attribute nesting overflow bug in IFLA_VFINFO_LIST. By excluding the stats when the requester doesn't need them, the truncation of the VF list is avoided. While it was technically only the stats added in commit c5a9f6f0ab40 ("net/core: Add drop counters to VF statistics") breaking the camel's back, the appreciable size of the stats data should never have been included without due consideration for the maximum number of VFs supported by PCI. Fixes: 3b766cd83232 ("net/core: Add reading VF statistics through the PF netdevice") Fixes: c5a9f6f0ab40 ("net/core: Add drop counters to VF statistics") Signed-off-by: Edwin Peer Cc: Edwin Peer Signed-off-by: Gal Pressman Link: https://lore.kernel.org/r/20230611105108.122586-1-gal@nvidia.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/core/rtnetlink.c | 96 +++++++++++++++++++++++--------------------- 1 file changed, 51 insertions(+), 45 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3c9c2d6e3b92..888ff53c8144 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -929,24 +929,27 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, nla_total_size(sizeof(struct ifla_vf_rate)) + nla_total_size(sizeof(struct ifla_vf_link_state)) + nla_total_size(sizeof(struct ifla_vf_rss_query_en)) + - nla_total_size(0) + /* nest IFLA_VF_STATS */ - /* IFLA_VF_STATS_RX_PACKETS */ - nla_total_size_64bit(sizeof(__u64)) + - /* IFLA_VF_STATS_TX_PACKETS */ - nla_total_size_64bit(sizeof(__u64)) + - /* IFLA_VF_STATS_RX_BYTES */ - nla_total_size_64bit(sizeof(__u64)) + - /* IFLA_VF_STATS_TX_BYTES */ - nla_total_size_64bit(sizeof(__u64)) + - /* IFLA_VF_STATS_BROADCAST */ - nla_total_size_64bit(sizeof(__u64)) + - /* IFLA_VF_STATS_MULTICAST */ - nla_total_size_64bit(sizeof(__u64)) + - /* IFLA_VF_STATS_RX_DROPPED */ - nla_total_size_64bit(sizeof(__u64)) + - /* IFLA_VF_STATS_TX_DROPPED */ - nla_total_size_64bit(sizeof(__u64)) + nla_total_size(sizeof(struct ifla_vf_trust))); + if (~ext_filter_mask & RTEXT_FILTER_SKIP_STATS) { + size += num_vfs * + (nla_total_size(0) + /* nest IFLA_VF_STATS */ + /* IFLA_VF_STATS_RX_PACKETS */ + nla_total_size_64bit(sizeof(__u64)) + + /* IFLA_VF_STATS_TX_PACKETS */ + nla_total_size_64bit(sizeof(__u64)) + + /* IFLA_VF_STATS_RX_BYTES */ + nla_total_size_64bit(sizeof(__u64)) + + /* IFLA_VF_STATS_TX_BYTES */ + nla_total_size_64bit(sizeof(__u64)) + + /* IFLA_VF_STATS_BROADCAST */ + nla_total_size_64bit(sizeof(__u64)) + + /* IFLA_VF_STATS_MULTICAST */ + nla_total_size_64bit(sizeof(__u64)) + + /* IFLA_VF_STATS_RX_DROPPED */ + nla_total_size_64bit(sizeof(__u64)) + + /* IFLA_VF_STATS_TX_DROPPED */ + nla_total_size_64bit(sizeof(__u64))); + } return size; } else return 0; @@ -1221,7 +1224,8 @@ static noinline_for_stack int rtnl_fill_stats(struct sk_buff *skb, static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, struct net_device *dev, int vfs_num, - struct nlattr *vfinfo) + struct nlattr *vfinfo, + u32 ext_filter_mask) { struct ifla_vf_rss_query_en vf_rss_query_en; struct nlattr *vf, *vfstats, *vfvlanlist; @@ -1327,33 +1331,35 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, goto nla_put_vf_failure; } nla_nest_end(skb, vfvlanlist); - memset(&vf_stats, 0, sizeof(vf_stats)); - if (dev->netdev_ops->ndo_get_vf_stats) - dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num, - &vf_stats); - vfstats = nla_nest_start_noflag(skb, IFLA_VF_STATS); - if (!vfstats) - goto nla_put_vf_failure; - if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS, - vf_stats.rx_packets, IFLA_VF_STATS_PAD) || - nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS, - vf_stats.tx_packets, IFLA_VF_STATS_PAD) || - nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_BYTES, - vf_stats.rx_bytes, IFLA_VF_STATS_PAD) || - nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_BYTES, - vf_stats.tx_bytes, IFLA_VF_STATS_PAD) || - nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST, - vf_stats.broadcast, IFLA_VF_STATS_PAD) || - nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST, - vf_stats.multicast, IFLA_VF_STATS_PAD) || - nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_DROPPED, - vf_stats.rx_dropped, IFLA_VF_STATS_PAD) || - nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_DROPPED, - vf_stats.tx_dropped, IFLA_VF_STATS_PAD)) { - nla_nest_cancel(skb, vfstats); - goto nla_put_vf_failure; + if (~ext_filter_mask & RTEXT_FILTER_SKIP_STATS) { + memset(&vf_stats, 0, sizeof(vf_stats)); + if (dev->netdev_ops->ndo_get_vf_stats) + dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num, + &vf_stats); + vfstats = nla_nest_start_noflag(skb, IFLA_VF_STATS); + if (!vfstats) + goto nla_put_vf_failure; + if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS, + vf_stats.rx_packets, IFLA_VF_STATS_PAD) || + nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS, + vf_stats.tx_packets, IFLA_VF_STATS_PAD) || + nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_BYTES, + vf_stats.rx_bytes, IFLA_VF_STATS_PAD) || + nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_BYTES, + vf_stats.tx_bytes, IFLA_VF_STATS_PAD) || + nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST, + vf_stats.broadcast, IFLA_VF_STATS_PAD) || + nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST, + vf_stats.multicast, IFLA_VF_STATS_PAD) || + nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_DROPPED, + vf_stats.rx_dropped, IFLA_VF_STATS_PAD) || + nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_DROPPED, + vf_stats.tx_dropped, IFLA_VF_STATS_PAD)) { + nla_nest_cancel(skb, vfstats); + goto nla_put_vf_failure; + } + nla_nest_end(skb, vfstats); } - nla_nest_end(skb, vfstats); nla_nest_end(skb, vf); return 0; @@ -1386,7 +1392,7 @@ static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb, return -EMSGSIZE; for (i = 0; i < num_vfs; i++) { - if (rtnl_fill_vfinfo(skb, dev, i, vfinfo)) + if (rtnl_fill_vfinfo(skb, dev, i, vfinfo, ext_filter_mask)) return -EMSGSIZE; } From 4e321c18ef9252af98f1910390862421843f4d63 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 14 Jun 2023 12:41:22 +0300 Subject: [PATCH 3808/4345] wifi: iwlwifi: pull from TXQs with softirqs disabled [ Upstream commit 96fb6f47db24a712d650b0a9b9074873f273fb0e ] In mac80211, it's required that we pull from TXQs by calling ieee80211_tx_dequeue() only with softirqs disabled. However, in iwl_mvm_queue_state_change() we're often called with them enabled, e.g. from flush if anything was flushed, triggering a mac80211 warning. Fix that by disabling the softirqs across the TX call. Fixes: cfbc6c4c5b91 ("iwlwifi: mvm: support mac80211 TXQs model") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230614123446.0feef7fa81db.I4dd62542d955b40dd8f0af34fa4accb9d0d17c7e@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 7c61d179895b..5b173f21e87b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -1174,8 +1174,11 @@ static void iwl_mvm_queue_state_change(struct iwl_op_mode *op_mode, mvmtxq = iwl_mvm_txq_from_mac80211(txq); mvmtxq->stopped = !start; - if (start && mvmsta->sta_state != IEEE80211_STA_NOTEXIST) + if (start && mvmsta->sta_state != IEEE80211_STA_NOTEXIST) { + local_bh_disable(); iwl_mvm_mac_itxq_xmit(mvm->hw, txq); + local_bh_enable(); + } } out: From 150ca0768b508ca255796b7800e73032006ceaa7 Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Fri, 16 Jun 2023 09:54:03 +0300 Subject: [PATCH 3809/4345] wifi: cfg80211: rewrite merging of inherited elements [ Upstream commit dfd9aa3e7a456d57b18021d66472ab7ff8373ab7 ] The cfg80211_gen_new_ie function merges the IEs using inheritance rules. Rewrite this function to fix issues around inheritance rules. In particular, vendor elements do not require any special handling, as they are either all inherited or overridden by the subprofile. Also, add fragmentation handling as this may be needed in some cases. This also changes the function to not require making a copy. The new version could be optimized a bit by explicitly tracking which IEs have been handled already rather than looking that up again every time. Note that a small behavioural change is the removal of the SSID special handling. This should be fine for the MBSSID element, as the SSID must be included in the subelement. Fixes: 0b8fb8235be8 ("cfg80211: Parsing of Multiple BSSID information in scanning") Signed-off-by: Benjamin Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230616094949.bc6152e146db.I2b5f3bc45085e1901e5b5192a674436adaf94748@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/scan.c | 217 +++++++++++++++++++++++++------------------- 1 file changed, 126 insertions(+), 91 deletions(-) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d09dabae5627..671c7f83d5fc 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -262,117 +262,152 @@ bool cfg80211_is_element_inherited(const struct element *elem, } EXPORT_SYMBOL(cfg80211_is_element_inherited); -static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, - const u8 *subelement, size_t subie_len, - u8 *new_ie, gfp_t gfp) +static size_t cfg80211_copy_elem_with_frags(const struct element *elem, + const u8 *ie, size_t ie_len, + u8 **pos, u8 *buf, size_t buf_len) { - u8 *pos, *tmp; - const u8 *tmp_old, *tmp_new; - const struct element *non_inherit_elem; - u8 *sub_copy; - - /* copy subelement as we need to change its content to - * mark an ie after it is processed. - */ - sub_copy = kmemdup(subelement, subie_len, gfp); - if (!sub_copy) + if (WARN_ON((u8 *)elem < ie || elem->data > ie + ie_len || + elem->data + elem->datalen > ie + ie_len)) return 0; - pos = &new_ie[0]; + if (elem->datalen + 2 > buf + buf_len - *pos) + return 0; - /* set new ssid */ - tmp_new = cfg80211_find_ie(WLAN_EID_SSID, sub_copy, subie_len); - if (tmp_new) { - memcpy(pos, tmp_new, tmp_new[1] + 2); - pos += (tmp_new[1] + 2); + memcpy(*pos, elem, elem->datalen + 2); + *pos += elem->datalen + 2; + + /* Finish if it is not fragmented */ + if (elem->datalen != 255) + return *pos - buf; + + ie_len = ie + ie_len - elem->data - elem->datalen; + ie = (const u8 *)elem->data + elem->datalen; + + for_each_element(elem, ie, ie_len) { + if (elem->id != WLAN_EID_FRAGMENT) + break; + + if (elem->datalen + 2 > buf + buf_len - *pos) + return 0; + + memcpy(*pos, elem, elem->datalen + 2); + *pos += elem->datalen + 2; + + if (elem->datalen != 255) + break; } - /* get non inheritance list if exists */ - non_inherit_elem = - cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, - sub_copy, subie_len); + return *pos - buf; +} - /* go through IEs in ie (skip SSID) and subelement, - * merge them into new_ie +static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, + const u8 *subie, size_t subie_len, + u8 *new_ie, size_t new_ie_len) +{ + const struct element *non_inherit_elem, *parent, *sub; + u8 *pos = new_ie; + u8 id, ext_id; + unsigned int match_len; + + non_inherit_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, + subie, subie_len); + + /* We copy the elements one by one from the parent to the generated + * elements. + * If they are not inherited (included in subie or in the non + * inheritance element), then we copy all occurrences the first time + * we see this element type. */ - tmp_old = cfg80211_find_ie(WLAN_EID_SSID, ie, ielen); - tmp_old = (tmp_old) ? tmp_old + tmp_old[1] + 2 : ie; + for_each_element(parent, ie, ielen) { + if (parent->id == WLAN_EID_FRAGMENT) + continue; + + if (parent->id == WLAN_EID_EXTENSION) { + if (parent->datalen < 1) + continue; + + id = WLAN_EID_EXTENSION; + ext_id = parent->data[0]; + match_len = 1; + } else { + id = parent->id; + match_len = 0; + } + + /* Find first occurrence in subie */ + sub = cfg80211_find_elem_match(id, subie, subie_len, + &ext_id, match_len, 0); + + /* Copy from parent if not in subie and inherited */ + if (!sub && + cfg80211_is_element_inherited(parent, non_inherit_elem)) { + if (!cfg80211_copy_elem_with_frags(parent, + ie, ielen, + &pos, new_ie, + new_ie_len)) + return 0; - while (tmp_old + 2 - ie <= ielen && - tmp_old + tmp_old[1] + 2 - ie <= ielen) { - if (tmp_old[0] == 0) { - tmp_old++; continue; } - if (tmp_old[0] == WLAN_EID_EXTENSION) - tmp = (u8 *)cfg80211_find_ext_ie(tmp_old[2], sub_copy, - subie_len); - else - tmp = (u8 *)cfg80211_find_ie(tmp_old[0], sub_copy, - subie_len); + /* Already copied if an earlier element had the same type */ + if (cfg80211_find_elem_match(id, ie, (u8 *)parent - ie, + &ext_id, match_len, 0)) + continue; - if (!tmp) { - const struct element *old_elem = (void *)tmp_old; + /* Not inheriting, copy all similar elements from subie */ + while (sub) { + if (!cfg80211_copy_elem_with_frags(sub, + subie, subie_len, + &pos, new_ie, + new_ie_len)) + return 0; - /* ie in old ie but not in subelement */ - if (cfg80211_is_element_inherited(old_elem, - non_inherit_elem)) { - memcpy(pos, tmp_old, tmp_old[1] + 2); - pos += tmp_old[1] + 2; - } - } else { - /* ie in transmitting ie also in subelement, - * copy from subelement and flag the ie in subelement - * as copied (by setting eid field to WLAN_EID_SSID, - * which is skipped anyway). - * For vendor ie, compare OUI + type + subType to - * determine if they are the same ie. - */ - if (tmp_old[0] == WLAN_EID_VENDOR_SPECIFIC) { - if (tmp_old[1] >= 5 && tmp[1] >= 5 && - !memcmp(tmp_old + 2, tmp + 2, 5)) { - /* same vendor ie, copy from - * subelement - */ - memcpy(pos, tmp, tmp[1] + 2); - pos += tmp[1] + 2; - tmp[0] = WLAN_EID_SSID; - } else { - memcpy(pos, tmp_old, tmp_old[1] + 2); - pos += tmp_old[1] + 2; - } - } else { - /* copy ie from subelement into new ie */ - memcpy(pos, tmp, tmp[1] + 2); - pos += tmp[1] + 2; - tmp[0] = WLAN_EID_SSID; - } + sub = cfg80211_find_elem_match(id, + sub->data + sub->datalen, + subie_len + subie - + (sub->data + + sub->datalen), + &ext_id, match_len, 0); } - - if (tmp_old + tmp_old[1] + 2 - ie == ielen) - break; - - tmp_old += tmp_old[1] + 2; } - /* go through subelement again to check if there is any ie not - * copied to new ie, skip ssid, capability, bssid-index ie + /* The above misses elements that are included in subie but not in the + * parent, so do a pass over subie and append those. + * Skip the non-tx BSSID caps and non-inheritance element. */ - tmp_new = sub_copy; - while (tmp_new + 2 - sub_copy <= subie_len && - tmp_new + tmp_new[1] + 2 - sub_copy <= subie_len) { - if (!(tmp_new[0] == WLAN_EID_NON_TX_BSSID_CAP || - tmp_new[0] == WLAN_EID_SSID)) { - memcpy(pos, tmp_new, tmp_new[1] + 2); - pos += tmp_new[1] + 2; + for_each_element(sub, subie, subie_len) { + if (sub->id == WLAN_EID_NON_TX_BSSID_CAP) + continue; + + if (sub->id == WLAN_EID_FRAGMENT) + continue; + + if (sub->id == WLAN_EID_EXTENSION) { + if (sub->datalen < 1) + continue; + + id = WLAN_EID_EXTENSION; + ext_id = sub->data[0]; + match_len = 1; + + if (ext_id == WLAN_EID_EXT_NON_INHERITANCE) + continue; + } else { + id = sub->id; + match_len = 0; } - if (tmp_new + tmp_new[1] + 2 - sub_copy == subie_len) - break; - tmp_new += tmp_new[1] + 2; + + /* Processed if one was included in the parent */ + if (cfg80211_find_elem_match(id, ie, ielen, + &ext_id, match_len, 0)) + continue; + + if (!cfg80211_copy_elem_with_frags(sub, subie, subie_len, + &pos, new_ie, new_ie_len)) + return 0; } - kfree(sub_copy); return pos - new_ie; } @@ -2170,7 +2205,7 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy, new_ie_len = cfg80211_gen_new_ie(ie, ielen, profile, profile_len, new_ie, - gfp); + IEEE80211_MAX_DATA_LEN); if (!new_ie_len) continue; From 660d4e73efb04dddd094f5a13b7a3bb2dbe2c6b6 Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Tue, 13 Jun 2023 16:46:55 +0300 Subject: [PATCH 3810/4345] wifi: ath9k: convert msecs to jiffies where needed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 2aa083acea9f61be3280184384551178f510ff51 ] Since 'ieee80211_queue_delayed_work()' expects timeout in jiffies and not milliseconds, 'msecs_to_jiffies()' should be used in 'ath_restart_work()' and '__ath9k_flush()'. Fixes: d63ffc45c5d3 ("ath9k: rename tx_complete_work to hw_check_work") Signed-off-by: Dmitry Antipov Acked-by: Toke Høiland-Jørgensen Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230613134655.248728-1-dmantipov@yandex.ru Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath9k/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 2bd4d295c9bd..b2cfc483515c 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -203,7 +203,7 @@ void ath_cancel_work(struct ath_softc *sc) void ath_restart_work(struct ath_softc *sc) { ieee80211_queue_delayed_work(sc->hw, &sc->hw_check_work, - ATH_HW_CHECK_POLL_INT); + msecs_to_jiffies(ATH_HW_CHECK_POLL_INT)); if (AR_SREV_9340(sc->sc_ah) || AR_SREV_9330(sc->sc_ah)) ieee80211_queue_delayed_work(sc->hw, &sc->hw_pll_work, @@ -2244,7 +2244,7 @@ void __ath9k_flush(struct ieee80211_hw *hw, u32 queues, bool drop, } ieee80211_queue_delayed_work(hw, &sc->hw_check_work, - ATH_HW_CHECK_POLL_INT); + msecs_to_jiffies(ATH_HW_CHECK_POLL_INT)); } static bool ath9k_tx_frames_pending(struct ieee80211_hw *hw) From 1ba91ffa1a0ed4cd134c5bf43508f797a7ea9dd0 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Wed, 7 Jun 2023 14:32:29 -0700 Subject: [PATCH 3811/4345] igc: Fix race condition in PTP tx code [ Upstream commit 9c50e2b150c8ee0eee5f8154e2ad168cdd748877 ] Currently, the igc driver supports timestamping only one tx packet at a time. During the transmission flow, the skb that requires hardware timestamping is saved in adapter->ptp_tx_skb. Once hardware has the timestamp, an interrupt is delivered, and adapter->ptp_tx_work is scheduled. In igc_ptp_tx_work(), we read the timestamp register, update adapter->ptp_tx_skb, and notify the network stack. While the thread executing the transmission flow (the user process running in kernel mode) and the thread executing ptp_tx_work don't access adapter->ptp_tx_skb concurrently, there are two other places where adapter->ptp_tx_skb is accessed: igc_ptp_tx_hang() and igc_ptp_suspend(). igc_ptp_tx_hang() is executed by the adapter->watchdog_task worker thread which runs periodically so it is possible we have two threads accessing ptp_tx_skb at the same time. Consider the following scenario: right after __IGC_PTP_TX_IN_PROGRESS is set in igc_xmit_frame_ring(), igc_ptp_tx_hang() is executed. Since adapter->ptp_tx_start hasn't been written yet, this is considered a timeout and adapter->ptp_tx_skb is cleaned up. This patch fixes the issue described above by adding the ptp_tx_lock to protect access to ptp_tx_skb and ptp_tx_start fields from igc_adapter. Since igc_xmit_frame_ring() called in atomic context by the networking stack, ptp_tx_lock is defined as a spinlock, and the irq safe variants of lock/unlock are used. With the introduction of the ptp_tx_lock, the __IGC_PTP_TX_IN_PROGRESS flag doesn't provide much of a use anymore so this patch gets rid of it. Fixes: 2c344ae24501 ("igc: Add support for TX timestamping") Signed-off-by: Andre Guedes Signed-off-by: Vinicius Costa Gomes Reviewed-by: Kurt Kanzenbach Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc.h | 5 +- drivers/net/ethernet/intel/igc/igc_main.c | 9 ++-- drivers/net/ethernet/intel/igc/igc_ptp.c | 57 ++++++++++++----------- 3 files changed, 41 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 47ba1eafcdc7..33f64c80335d 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -210,6 +210,10 @@ struct igc_adapter { struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_caps; struct work_struct ptp_tx_work; + /* Access to ptp_tx_skb and ptp_tx_start are protected by the + * ptp_tx_lock. + */ + spinlock_t ptp_tx_lock; struct sk_buff *ptp_tx_skb; struct hwtstamp_config tstamp_config; unsigned long ptp_tx_start; @@ -389,7 +393,6 @@ enum igc_state_t { __IGC_TESTING, __IGC_RESETTING, __IGC_DOWN, - __IGC_PTP_TX_IN_PROGRESS, }; enum igc_tx_flags { diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 72d7d2cf126d..a15e4b6d7fa4 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1467,9 +1467,10 @@ done: * the other timer registers before skipping the * timestamping request. */ - if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON && - !test_and_set_bit_lock(__IGC_PTP_TX_IN_PROGRESS, - &adapter->state)) { + unsigned long flags; + + spin_lock_irqsave(&adapter->ptp_tx_lock, flags); + if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON && !adapter->ptp_tx_skb) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGC_TX_FLAGS_TSTAMP; @@ -1478,6 +1479,8 @@ done: } else { adapter->tx_hwtstamp_skipped++; } + + spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); } /* record initial flags and protocol */ diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index ef53f7665b58..25b238c6a675 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -323,6 +323,7 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter, return 0; } +/* Requires adapter->ptp_tx_lock held by caller. */ static void igc_ptp_tx_timeout(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -330,7 +331,6 @@ static void igc_ptp_tx_timeout(struct igc_adapter *adapter) dev_kfree_skb_any(adapter->ptp_tx_skb); adapter->ptp_tx_skb = NULL; adapter->tx_hwtstamp_timeouts++; - clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); /* Clear the tx valid bit in TSYNCTXCTL register to enable interrupt. */ rd32(IGC_TXSTMPH); netdev_warn(adapter->netdev, "Tx timestamp timeout\n"); @@ -338,20 +338,20 @@ static void igc_ptp_tx_timeout(struct igc_adapter *adapter) void igc_ptp_tx_hang(struct igc_adapter *adapter) { - bool timeout = time_is_before_jiffies(adapter->ptp_tx_start + - IGC_PTP_TX_TIMEOUT); + unsigned long flags; - if (!test_bit(__IGC_PTP_TX_IN_PROGRESS, &adapter->state)) - return; + spin_lock_irqsave(&adapter->ptp_tx_lock, flags); - /* If we haven't received a timestamp within the timeout, it is - * reasonable to assume that it will never occur, so we can unlock the - * timestamp bit when this occurs. - */ - if (timeout) { - cancel_work_sync(&adapter->ptp_tx_work); - igc_ptp_tx_timeout(adapter); - } + if (!adapter->ptp_tx_skb) + goto unlock; + + if (time_is_after_jiffies(adapter->ptp_tx_start + IGC_PTP_TX_TIMEOUT)) + goto unlock; + + igc_ptp_tx_timeout(adapter); + +unlock: + spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); } /** @@ -361,6 +361,8 @@ void igc_ptp_tx_hang(struct igc_adapter *adapter) * If we were asked to do hardware stamping and such a time stamp is * available, then it must have been for this skb here because we only * allow only one such packet into the queue. + * + * Context: Expects adapter->ptp_tx_lock to be held by caller. */ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) { @@ -396,13 +398,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) shhwtstamps.hwtstamp = ktime_add_ns(shhwtstamps.hwtstamp, adjust); - /* Clear the lock early before calling skb_tstamp_tx so that - * applications are not woken up before the lock bit is clear. We use - * a copy of the skb pointer to ensure other threads can't change it - * while we're notifying the stack. - */ adapter->ptp_tx_skb = NULL; - clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); /* Notify the stack and free the skb after we've unlocked */ skb_tstamp_tx(skb, &shhwtstamps); @@ -413,24 +409,33 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) * igc_ptp_tx_work * @work: pointer to work struct * - * This work function polls the TSYNCTXCTL valid bit to determine when a - * timestamp has been taken for the current stored skb. + * This work function checks the TSYNCTXCTL valid bit to determine when + * a timestamp has been taken for the current stored skb. */ static void igc_ptp_tx_work(struct work_struct *work) { struct igc_adapter *adapter = container_of(work, struct igc_adapter, ptp_tx_work); struct igc_hw *hw = &adapter->hw; + unsigned long flags; u32 tsynctxctl; - if (!test_bit(__IGC_PTP_TX_IN_PROGRESS, &adapter->state)) - return; + spin_lock_irqsave(&adapter->ptp_tx_lock, flags); + + if (!adapter->ptp_tx_skb) + goto unlock; tsynctxctl = rd32(IGC_TSYNCTXCTL); - if (WARN_ON_ONCE(!(tsynctxctl & IGC_TSYNCTXCTL_TXTT_0))) - return; + tsynctxctl &= IGC_TSYNCTXCTL_TXTT_0; + if (!tsynctxctl) { + WARN_ONCE(1, "Received a TSTAMP interrupt but no TSTAMP is ready.\n"); + goto unlock; + } igc_ptp_tx_hwtstamp(adapter); + +unlock: + spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); } /** @@ -506,6 +511,7 @@ void igc_ptp_init(struct igc_adapter *adapter) return; } + spin_lock_init(&adapter->ptp_tx_lock); spin_lock_init(&adapter->tmreg_lock); INIT_WORK(&adapter->ptp_tx_work, igc_ptp_tx_work); @@ -559,7 +565,6 @@ void igc_ptp_suspend(struct igc_adapter *adapter) cancel_work_sync(&adapter->ptp_tx_work); dev_kfree_skb_any(adapter->ptp_tx_skb); adapter->ptp_tx_skb = NULL; - clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); if (pci_device_is_present(adapter->pdev)) igc_ptp_time_save(adapter); From 0c9e48428f6b3916a04eeb98a6394558ced0b6d2 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 21 Jun 2023 15:55:37 +0200 Subject: [PATCH 3812/4345] net: stmmac: fix double serdes powerdown [ Upstream commit c4fc88ad2a765224a648db8ab35f125e120fe41b ] Commit 49725ffc15fc ("net: stmmac: power up/down serdes in stmmac_open/release") correctly added a call to the serdes_powerdown() callback to stmmac_release() but did not remove the one from stmmac_remove() which leads to a doubled call to serdes_powerdown(). This can lead to all kinds of problems: in the case of the qcom ethqos driver, it caused an unbalanced regulator disable splat. Fixes: 49725ffc15fc ("net: stmmac: power up/down serdes in stmmac_open/release") Signed-off-by: Bartosz Golaszewski Reviewed-by: Jiri Pirko Acked-by: Junxiao Chang Reviewed-by: Andrew Halaney Tested-by: Andrew Halaney Link: https://lore.kernel.org/r/20230621135537.376649-1-brgl@bgdev.pl Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index de66406c5057..83e9a4d019c1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5254,12 +5254,6 @@ int stmmac_dvr_remove(struct device *dev) netif_carrier_off(ndev); unregister_netdev(ndev); - /* Serdes power down needs to happen after VLAN filter - * is deleted that is triggered by unregister_netdev(). - */ - if (priv->plat->serdes_powerdown) - priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv); - #ifdef CONFIG_DEBUG_FS stmmac_exit_fs(ndev); #endif From cde7b90e0539a3b11da377e463dfd2288a162dbf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 21 Jun 2023 15:43:37 +0000 Subject: [PATCH 3813/4345] netlink: fix potential deadlock in netlink_set_err() [ Upstream commit 8d61f926d42045961e6b65191c09e3678d86a9cf ] syzbot reported a possible deadlock in netlink_set_err() [1] A similar issue was fixed in commit 1d482e666b8e ("netlink: disable IRQs for netlink_lock_table()") in netlink_lock_table() This patch adds IRQ safety to netlink_set_err() and __netlink_diag_dump() which were not covered by cited commit. [1] WARNING: possible irq lock inversion dependency detected 6.4.0-rc6-syzkaller-00240-g4e9f0ec38852 #0 Not tainted syz-executor.2/23011 just changed the state of lock: ffffffff8e1a7a58 (nl_table_lock){.+.?}-{2:2}, at: netlink_set_err+0x2e/0x3a0 net/netlink/af_netlink.c:1612 but this lock was taken by another, SOFTIRQ-safe lock in the past: (&local->queue_stop_reason_lock){..-.}-{2:2} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(nl_table_lock); local_irq_disable(); lock(&local->queue_stop_reason_lock); lock(nl_table_lock); lock(&local->queue_stop_reason_lock); *** DEADLOCK *** Fixes: 1d482e666b8e ("netlink: disable IRQs for netlink_lock_table()") Reported-by: syzbot+a7d200a347f912723e5c@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=a7d200a347f912723e5c Link: https://lore.kernel.org/netdev/000000000000e38d1605fea5747e@google.com/T/#u Signed-off-by: Eric Dumazet Cc: Johannes Berg Link: https://lore.kernel.org/r/20230621154337.1668594-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/netlink/af_netlink.c | 5 +++-- net/netlink/diag.c | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 99c869d8d304..9737c3229c12 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1602,6 +1602,7 @@ out: int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; + unsigned long flags; struct sock *sk; int ret = 0; @@ -1611,12 +1612,12 @@ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) /* sk->sk_err wants a positive error value */ info.code = -code; - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); return ret; } EXPORT_SYMBOL(netlink_set_err); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index c6255eac305c..4143b2ea4195 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -94,6 +94,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net *net = sock_net(skb->sk); struct netlink_diag_req *req; struct netlink_sock *nlsk; + unsigned long flags; struct sock *sk; int num = 2; int ret = 0; @@ -152,7 +153,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, num++; mc_list: - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &tbl->mc_list) { if (sk_hashed(sk)) continue; @@ -173,7 +174,7 @@ mc_list: } num++; } - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); done: cb->args[0] = num; From 44db85c6e1a184b99a2cdf56b525ac63c4962c22 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 21 Jun 2023 17:47:20 +0000 Subject: [PATCH 3814/4345] netlink: do not hard code device address lenth in fdb dumps [ Upstream commit aa5406950726e336c5c9585b09799a734b6e77bf ] syzbot reports that some netdev devices do not have a six bytes address [1] Replace ETH_ALEN by dev->addr_len. [1] (Case of a device where dev->addr_len = 4) BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:114 [inline] BUG: KMSAN: kernel-infoleak in copyout+0xb8/0x100 lib/iov_iter.c:169 instrument_copy_to_user include/linux/instrumented.h:114 [inline] copyout+0xb8/0x100 lib/iov_iter.c:169 _copy_to_iter+0x6d8/0x1d00 lib/iov_iter.c:536 copy_to_iter include/linux/uio.h:206 [inline] simple_copy_to_iter+0x68/0xa0 net/core/datagram.c:513 __skb_datagram_iter+0x123/0xdc0 net/core/datagram.c:419 skb_copy_datagram_iter+0x5c/0x200 net/core/datagram.c:527 skb_copy_datagram_msg include/linux/skbuff.h:3960 [inline] netlink_recvmsg+0x4ae/0x15a0 net/netlink/af_netlink.c:1970 sock_recvmsg_nosec net/socket.c:1019 [inline] sock_recvmsg net/socket.c:1040 [inline] ____sys_recvmsg+0x283/0x7f0 net/socket.c:2722 ___sys_recvmsg+0x223/0x840 net/socket.c:2764 do_recvmmsg+0x4f9/0xfd0 net/socket.c:2858 __sys_recvmmsg net/socket.c:2937 [inline] __do_sys_recvmmsg net/socket.c:2960 [inline] __se_sys_recvmmsg net/socket.c:2953 [inline] __x64_sys_recvmmsg+0x397/0x490 net/socket.c:2953 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was stored to memory at: __nla_put lib/nlattr.c:1009 [inline] nla_put+0x1c6/0x230 lib/nlattr.c:1067 nlmsg_populate_fdb_fill+0x2b8/0x600 net/core/rtnetlink.c:4071 nlmsg_populate_fdb net/core/rtnetlink.c:4418 [inline] ndo_dflt_fdb_dump+0x616/0x840 net/core/rtnetlink.c:4456 rtnl_fdb_dump+0x14ff/0x1fc0 net/core/rtnetlink.c:4629 netlink_dump+0x9d1/0x1310 net/netlink/af_netlink.c:2268 netlink_recvmsg+0xc5c/0x15a0 net/netlink/af_netlink.c:1995 sock_recvmsg_nosec+0x7a/0x120 net/socket.c:1019 ____sys_recvmsg+0x664/0x7f0 net/socket.c:2720 ___sys_recvmsg+0x223/0x840 net/socket.c:2764 do_recvmmsg+0x4f9/0xfd0 net/socket.c:2858 __sys_recvmmsg net/socket.c:2937 [inline] __do_sys_recvmmsg net/socket.c:2960 [inline] __se_sys_recvmmsg net/socket.c:2953 [inline] __x64_sys_recvmmsg+0x397/0x490 net/socket.c:2953 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook+0x12d/0xb60 mm/slab.h:716 slab_alloc_node mm/slub.c:3451 [inline] __kmem_cache_alloc_node+0x4ff/0x8b0 mm/slub.c:3490 kmalloc_trace+0x51/0x200 mm/slab_common.c:1057 kmalloc include/linux/slab.h:559 [inline] __hw_addr_create net/core/dev_addr_lists.c:60 [inline] __hw_addr_add_ex+0x2e5/0x9e0 net/core/dev_addr_lists.c:118 __dev_mc_add net/core/dev_addr_lists.c:867 [inline] dev_mc_add+0x9a/0x130 net/core/dev_addr_lists.c:885 igmp6_group_added+0x267/0xbc0 net/ipv6/mcast.c:680 ipv6_mc_up+0x296/0x3b0 net/ipv6/mcast.c:2754 ipv6_mc_remap+0x1e/0x30 net/ipv6/mcast.c:2708 addrconf_type_change net/ipv6/addrconf.c:3731 [inline] addrconf_notify+0x4d3/0x1d90 net/ipv6/addrconf.c:3699 notifier_call_chain kernel/notifier.c:93 [inline] raw_notifier_call_chain+0xe4/0x430 kernel/notifier.c:461 call_netdevice_notifiers_info net/core/dev.c:1935 [inline] call_netdevice_notifiers_extack net/core/dev.c:1973 [inline] call_netdevice_notifiers+0x1ee/0x2d0 net/core/dev.c:1987 bond_enslave+0xccd/0x53f0 drivers/net/bonding/bond_main.c:1906 do_set_master net/core/rtnetlink.c:2626 [inline] rtnl_newlink_create net/core/rtnetlink.c:3460 [inline] __rtnl_newlink net/core/rtnetlink.c:3660 [inline] rtnl_newlink+0x378c/0x40e0 net/core/rtnetlink.c:3673 rtnetlink_rcv_msg+0x16a6/0x1840 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x371/0x650 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0xf28/0x1230 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x122f/0x13d0 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x999/0xd50 net/socket.c:2503 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2557 __sys_sendmsg net/socket.c:2586 [inline] __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x304/0x490 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Bytes 2856-2857 of 3500 are uninitialized Memory access of size 3500 starts at ffff888018d99104 Data copied to user address 0000000020000480 Fixes: d83b06036048 ("net: add fdb generic dump routine") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230621174720.1845040-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/rtnetlink.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 888ff53c8144..d3c03ebf06a5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3889,7 +3889,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, ndm->ndm_ifindex = dev->ifindex; ndm->ndm_state = ndm_state; - if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) + if (nla_put(skb, NDA_LLADDR, dev->addr_len, addr)) goto nla_put_failure; if (vid) if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid)) @@ -3903,10 +3903,10 @@ nla_put_failure: return -EMSGSIZE; } -static inline size_t rtnl_fdb_nlmsg_size(void) +static inline size_t rtnl_fdb_nlmsg_size(const struct net_device *dev) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + - nla_total_size(ETH_ALEN) + /* NDA_LLADDR */ + nla_total_size(dev->addr_len) + /* NDA_LLADDR */ nla_total_size(sizeof(u16)) + /* NDA_VLAN */ 0; } @@ -3918,7 +3918,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type, struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC); + skb = nlmsg_new(rtnl_fdb_nlmsg_size(dev), GFP_ATOMIC); if (!skb) goto errout; From 4d9cd4b330d80785c48f4e39790e6f8e2c1af834 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Thu, 22 Jun 2023 23:03:34 +0200 Subject: [PATCH 3815/4345] selftests: rtnetlink: remove netdevsim device after ipsec offload test [ Upstream commit 5f789f103671fec3733ebe756e56adf15c90c21d ] On systems where netdevsim is built-in or loaded before the test starts, kci_test_ipsec_offload doesn't remove the netdevsim device it created during the test. Fixes: e05b2d141fef ("netdevsim: move netdev creation/destruction to dev probe") Signed-off-by: Sabrina Dubroca Reviewed-by: Simon Horman Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/e1cb94f4f82f4eca4a444feec4488a1323396357.1687466906.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- tools/testing/selftests/net/rtnetlink.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index c3a905923ef2..cbf166df57da 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -835,6 +835,7 @@ EOF fi # clean up any leftovers + echo 0 > /sys/bus/netdevsim/del_device $probed && rmmod netdevsim if [ $ret -ne 0 ]; then From bccc7ace12e69dee4684a3bb4b69737972e570d6 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 22 Jun 2023 14:32:31 -0700 Subject: [PATCH 3816/4345] gtp: Fix use-after-free in __gtp_encap_destroy(). [ Upstream commit ce3aee7114c575fab32a5e9e939d4bbb3dcca79f ] syzkaller reported use-after-free in __gtp_encap_destroy(). [0] It shows the same process freed sk and touched it illegally. Commit e198987e7dd7 ("gtp: fix suspicious RCU usage") added lock_sock() and release_sock() in __gtp_encap_destroy() to protect sk->sk_user_data, but release_sock() is called after sock_put() releases the last refcnt. [0]: BUG: KASAN: slab-use-after-free in instrument_atomic_read_write include/linux/instrumented.h:96 [inline] BUG: KASAN: slab-use-after-free in atomic_try_cmpxchg_acquire include/linux/atomic/atomic-instrumented.h:541 [inline] BUG: KASAN: slab-use-after-free in queued_spin_lock include/asm-generic/qspinlock.h:111 [inline] BUG: KASAN: slab-use-after-free in do_raw_spin_lock include/linux/spinlock.h:186 [inline] BUG: KASAN: slab-use-after-free in __raw_spin_lock_bh include/linux/spinlock_api_smp.h:127 [inline] BUG: KASAN: slab-use-after-free in _raw_spin_lock_bh+0x75/0xe0 kernel/locking/spinlock.c:178 Write of size 4 at addr ffff88800dbef398 by task syz-executor.2/2401 CPU: 1 PID: 2401 Comm: syz-executor.2 Not tainted 6.4.0-rc5-01219-gfa0e21fa4443 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x72/0xa0 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:351 [inline] print_report+0xcc/0x620 mm/kasan/report.c:462 kasan_report+0xb2/0xe0 mm/kasan/report.c:572 check_region_inline mm/kasan/generic.c:181 [inline] kasan_check_range+0x39/0x1c0 mm/kasan/generic.c:187 instrument_atomic_read_write include/linux/instrumented.h:96 [inline] atomic_try_cmpxchg_acquire include/linux/atomic/atomic-instrumented.h:541 [inline] queued_spin_lock include/asm-generic/qspinlock.h:111 [inline] do_raw_spin_lock include/linux/spinlock.h:186 [inline] __raw_spin_lock_bh include/linux/spinlock_api_smp.h:127 [inline] _raw_spin_lock_bh+0x75/0xe0 kernel/locking/spinlock.c:178 spin_lock_bh include/linux/spinlock.h:355 [inline] release_sock+0x1f/0x1a0 net/core/sock.c:3526 gtp_encap_disable_sock drivers/net/gtp.c:651 [inline] gtp_encap_disable+0xb9/0x220 drivers/net/gtp.c:664 gtp_dev_uninit+0x19/0x50 drivers/net/gtp.c:728 unregister_netdevice_many_notify+0x97e/0x1520 net/core/dev.c:10841 rtnl_delete_link net/core/rtnetlink.c:3216 [inline] rtnl_dellink+0x3c0/0xb30 net/core/rtnetlink.c:3268 rtnetlink_rcv_msg+0x450/0xb10 net/core/rtnetlink.c:6423 netlink_rcv_skb+0x15d/0x450 net/netlink/af_netlink.c:2548 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x700/0x930 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x91c/0xe30 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b7/0x200 net/socket.c:747 ____sys_sendmsg+0x75a/0x990 net/socket.c:2493 ___sys_sendmsg+0x11d/0x1c0 net/socket.c:2547 __sys_sendmsg+0xfe/0x1d0 net/socket.c:2576 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f1168b1fe5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 73 9f 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007f1167edccc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004bbf80 RCX: 00007f1168b1fe5d RDX: 0000000000000000 RSI: 00000000200002c0 RDI: 0000000000000003 RBP: 00000000004bbf80 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007f1168b80530 R15: 0000000000000000 Allocated by task 1483: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 __kasan_slab_alloc+0x59/0x70 mm/kasan/common.c:328 kasan_slab_alloc include/linux/kasan.h:186 [inline] slab_post_alloc_hook mm/slab.h:711 [inline] slab_alloc_node mm/slub.c:3451 [inline] slab_alloc mm/slub.c:3459 [inline] __kmem_cache_alloc_lru mm/slub.c:3466 [inline] kmem_cache_alloc+0x16d/0x340 mm/slub.c:3475 sk_prot_alloc+0x5f/0x280 net/core/sock.c:2073 sk_alloc+0x34/0x6c0 net/core/sock.c:2132 inet6_create net/ipv6/af_inet6.c:192 [inline] inet6_create+0x2c7/0xf20 net/ipv6/af_inet6.c:119 __sock_create+0x2a1/0x530 net/socket.c:1535 sock_create net/socket.c:1586 [inline] __sys_socket_create net/socket.c:1623 [inline] __sys_socket_create net/socket.c:1608 [inline] __sys_socket+0x137/0x250 net/socket.c:1651 __do_sys_socket net/socket.c:1664 [inline] __se_sys_socket net/socket.c:1662 [inline] __x64_sys_socket+0x72/0xb0 net/socket.c:1662 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 2401: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x50 mm/kasan/generic.c:521 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free mm/kasan/common.c:200 [inline] __kasan_slab_free+0x10c/0x1b0 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:162 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook mm/slub.c:1807 [inline] slab_free mm/slub.c:3786 [inline] kmem_cache_free+0xb4/0x490 mm/slub.c:3808 sk_prot_free net/core/sock.c:2113 [inline] __sk_destruct+0x500/0x720 net/core/sock.c:2207 sk_destruct+0xc1/0xe0 net/core/sock.c:2222 __sk_free+0xed/0x3d0 net/core/sock.c:2233 sk_free+0x7c/0xa0 net/core/sock.c:2244 sock_put include/net/sock.h:1981 [inline] __gtp_encap_destroy+0x165/0x1b0 drivers/net/gtp.c:634 gtp_encap_disable_sock drivers/net/gtp.c:651 [inline] gtp_encap_disable+0xb9/0x220 drivers/net/gtp.c:664 gtp_dev_uninit+0x19/0x50 drivers/net/gtp.c:728 unregister_netdevice_many_notify+0x97e/0x1520 net/core/dev.c:10841 rtnl_delete_link net/core/rtnetlink.c:3216 [inline] rtnl_dellink+0x3c0/0xb30 net/core/rtnetlink.c:3268 rtnetlink_rcv_msg+0x450/0xb10 net/core/rtnetlink.c:6423 netlink_rcv_skb+0x15d/0x450 net/netlink/af_netlink.c:2548 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x700/0x930 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x91c/0xe30 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b7/0x200 net/socket.c:747 ____sys_sendmsg+0x75a/0x990 net/socket.c:2493 ___sys_sendmsg+0x11d/0x1c0 net/socket.c:2547 __sys_sendmsg+0xfe/0x1d0 net/socket.c:2576 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc The buggy address belongs to the object at ffff88800dbef300 which belongs to the cache UDPv6 of size 1344 The buggy address is located 152 bytes inside of freed 1344-byte region [ffff88800dbef300, ffff88800dbef840) The buggy address belongs to the physical page: page:00000000d31bfed5 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88800dbeed40 pfn:0xdbe8 head:00000000d31bfed5 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 memcg:ffff888008ee0801 flags: 0x100000000010200(slab|head|node=0|zone=1) page_type: 0xffffffff() raw: 0100000000010200 ffff88800c7a3000 dead000000000122 0000000000000000 raw: ffff88800dbeed40 0000000080160015 00000001ffffffff ffff888008ee0801 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88800dbef280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88800dbef300: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88800dbef380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88800dbef400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88800dbef480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: e198987e7dd7 ("gtp: fix suspicious RCU usage") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Reviewed-by: Pablo Neira Ayuso Link: https://lore.kernel.org/r/20230622213231.24651-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/gtp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 1c46bc4d2705..05ea3a18552b 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -291,7 +291,9 @@ static void __gtp_encap_destroy(struct sock *sk) gtp->sk1u = NULL; udp_sk(sk)->encap_type = 0; rcu_assign_sk_user_data(sk, NULL); + release_sock(sk); sock_put(sk); + return; } release_sock(sk); } From 6ccfec84f02576c44ebe98e5f59d60c07825a460 Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Thu, 22 Jun 2023 22:22:45 +0300 Subject: [PATCH 3817/4345] net: axienet: Move reset before 64-bit DMA detection [ Upstream commit f1bc9fc4a06de0108e0dca2a9a7e99ba1fc632f9 ] 64-bit DMA detection will fail if axienet was started before (by boot loader, boot ROM, etc). In this state axienet will not start properly. XAXIDMA_TX_CDESC_OFFSET + 4 register (MM2S_CURDESC_MSB) is used to detect 64-bit DMA capability here. But datasheet says: When DMACR.RS is 1 (axienet is in enabled state), CURDESC_PTR becomes Read Only (RO) and is used to fetch the first descriptor. So iowrite32()/ioread32() trick to this register to detect 64-bit DMA will not work. So move axienet reset before 64-bit DMA detection. Fixes: f735c40ed93c ("net: axienet: Autodetect 64-bit DMA capability") Signed-off-by: Maxim Kochetkov Reviewed-by: Robert Hancock Reviewed-by: Radhey Shyam Pandey Link: https://lore.kernel.org/r/20230622192245.116864-1-fido_max@inbox.ru Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 3d91baf2e55a..9d362283196a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2009,6 +2009,11 @@ static int axienet_probe(struct platform_device *pdev) goto cleanup_clk; } + /* Reset core now that clocks are enabled, prior to accessing MDIO */ + ret = __axienet_device_reset(lp); + if (ret) + goto cleanup_clk; + /* Autodetect the need for 64-bit DMA pointers. * When the IP is configured for a bus width bigger than 32 bits, * writing the MSB registers is mandatory, even if they are all 0. @@ -2055,11 +2060,6 @@ static int axienet_probe(struct platform_device *pdev) lp->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD; lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD; - /* Reset core now that clocks are enabled, prior to accessing MDIO */ - ret = __axienet_device_reset(lp); - if (ret) - goto cleanup_clk; - ret = axienet_mdio_setup(lp); if (ret) dev_warn(&pdev->dev, From cb1aa7cc562cab6a87ea33574c8c65f2d2fd7aeb Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Fri, 23 Jun 2023 15:34:48 +0100 Subject: [PATCH 3818/4345] sfc: fix crash when reading stats while NIC is resetting [ Upstream commit d1b355438b8325a486f087e506d412c4e852f37b ] efx_net_stats() (.ndo_get_stats64) can be called during an ethtool selftest, during which time nic_data->mc_stats is NULL as the NIC has been fini'd. In this case do not attempt to fetch the latest stats from the hardware, else we will crash on a NULL dereference: BUG: kernel NULL pointer dereference, address: 0000000000000038 RIP efx_nic_update_stats abridged calltrace: efx_ef10_update_stats_pf efx_net_stats dev_get_stats dev_seq_printf_stats Skipping the read is safe, we will simply give out stale stats. To ensure that the free in efx_ef10_fini_nic() does not race against efx_ef10_update_stats_pf(), which could cause a TOCTTOU bug, take the efx->stats_lock in fini_nic (it is already held across update_stats). Fixes: d3142c193dca ("sfc: refactor EF10 stats handling") Reviewed-by: Pieter Jansen van Vuuren Signed-off-by: Edward Cree Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/sfc/ef10.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 32654fe1f8b5..3f53b5ea7841 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1297,8 +1297,10 @@ static void efx_ef10_fini_nic(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; + spin_lock_bh(&efx->stats_lock); kfree(nic_data->mc_stats); nic_data->mc_stats = NULL; + spin_unlock_bh(&efx->stats_lock); } static int efx_ef10_init_nic(struct efx_nic *efx) @@ -1836,9 +1838,14 @@ static size_t efx_ef10_update_stats_pf(struct efx_nic *efx, u64 *full_stats, efx_ef10_get_stat_mask(efx, mask); - efx_nic_copy_stats(efx, nic_data->mc_stats); - efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, - mask, stats, nic_data->mc_stats, false); + /* If NIC was fini'd (probably resetting), then we can't read + * updated stats right now. + */ + if (nic_data->mc_stats) { + efx_nic_copy_stats(efx, nic_data->mc_stats); + efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, + mask, stats, nic_data->mc_stats, false); + } /* Update derived statistics */ efx_nic_fix_nodesc_drop_stat(efx, From a3a1550c4d2e5fecbd317778ef2832e933d4774b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 2 Mar 2022 20:25:19 +0100 Subject: [PATCH 3819/4345] nfc: llcp: simplify llcp_sock_connect() error paths [ Upstream commit ec10fd154d934cc4195da3cbd017a12817b41d51 ] The llcp_sock_connect() error paths were using a mixed way of central exit (goto) and cleanup Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller Stable-dep-of: 6709d4b7bc2e ("net: nfc: Fix use-after-free caused by nfc_llcp_find_local") Signed-off-by: Sasha Levin --- net/nfc/llcp_sock.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 0b93a17b9f11..fdf0856182c6 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -712,10 +712,8 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, llcp_sock->local = nfc_llcp_local_get(local); llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { - nfc_llcp_local_put(llcp_sock->local); - llcp_sock->local = NULL; ret = -ENOMEM; - goto put_dev; + goto sock_llcp_put_local; } llcp_sock->reserved_ssap = llcp_sock->ssap; @@ -760,8 +758,11 @@ sock_unlink: sock_llcp_release: nfc_llcp_put_ssap(local, llcp_sock->ssap); + +sock_llcp_put_local: nfc_llcp_local_put(llcp_sock->local); llcp_sock->local = NULL; + llcp_sock->dev = NULL; put_dev: nfc_put_device(dev); From 96f2c6f272ec04083d828de46285a7d7b17d1aad Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 25 Jun 2023 17:10:07 +0800 Subject: [PATCH 3820/4345] net: nfc: Fix use-after-free caused by nfc_llcp_find_local [ Upstream commit 6709d4b7bc2e079241fdef15d1160581c5261c10 ] This commit fixes several use-after-free that caused by function nfc_llcp_find_local(). For example, one UAF can happen when below buggy time window occurs. // nfc_genl_llc_get_params | // nfc_unregister_device | dev = nfc_get_device(idx); | device_lock(...) if (!dev) | dev->shutting_down = true; return -ENODEV; | device_unlock(...); | device_lock(...); | // nfc_llcp_unregister_device | nfc_llcp_find_local() nfc_llcp_find_local(...); | | local_cleanup() if (!local) { | rc = -ENODEV; | // nfc_llcp_local_put goto exit; | kref_put(.., local_release) } | | // local_release | list_del(&local->list) // nfc_genl_send_params | kfree() local->dev->idx !!!UAF!!! | | and the crash trace for the one of the discussed UAF like: BUG: KASAN: slab-use-after-free in nfc_genl_llc_get_params+0x72f/0x780 net/nfc/netlink.c:1045 Read of size 8 at addr ffff888105b0e410 by task 20114 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x72/0xa0 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:319 [inline] print_report+0xcc/0x620 mm/kasan/report.c:430 kasan_report+0xb2/0xe0 mm/kasan/report.c:536 nfc_genl_send_params net/nfc/netlink.c:999 [inline] nfc_genl_llc_get_params+0x72f/0x780 net/nfc/netlink.c:1045 genl_family_rcv_msg_doit.isra.0+0x1ee/0x2e0 net/netlink/genetlink.c:968 genl_family_rcv_msg net/netlink/genetlink.c:1048 [inline] genl_rcv_msg+0x503/0x7d0 net/netlink/genetlink.c:1065 netlink_rcv_skb+0x161/0x430 net/netlink/af_netlink.c:2548 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1076 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x644/0x900 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x934/0xe70 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b6/0x200 net/socket.c:747 ____sys_sendmsg+0x6e9/0x890 net/socket.c:2501 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2555 __sys_sendmsg+0xf7/0x1d0 net/socket.c:2584 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f34640a2389 RSP: 002b:00007f3463415168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f34641c1f80 RCX: 00007f34640a2389 RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000006 RBP: 00007f34640ed493 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe38449ecf R14: 00007f3463415300 R15: 0000000000022000 Allocated by task 20116: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:374 [inline] __kasan_kmalloc+0x7f/0x90 mm/kasan/common.c:383 kmalloc include/linux/slab.h:580 [inline] kzalloc include/linux/slab.h:720 [inline] nfc_llcp_register_device+0x49/0xa40 net/nfc/llcp_core.c:1567 nfc_register_device+0x61/0x260 net/nfc/core.c:1124 nci_register_device+0x776/0xb20 net/nfc/nci/core.c:1257 virtual_ncidev_open+0x147/0x230 drivers/nfc/virtual_ncidev.c:148 misc_open+0x379/0x4a0 drivers/char/misc.c:165 chrdev_open+0x26c/0x780 fs/char_dev.c:414 do_dentry_open+0x6c4/0x12a0 fs/open.c:920 do_open fs/namei.c:3560 [inline] path_openat+0x24fe/0x37e0 fs/namei.c:3715 do_filp_open+0x1ba/0x410 fs/namei.c:3742 do_sys_openat2+0x171/0x4c0 fs/open.c:1356 do_sys_open fs/open.c:1372 [inline] __do_sys_openat fs/open.c:1388 [inline] __se_sys_openat fs/open.c:1383 [inline] __x64_sys_openat+0x143/0x200 fs/open.c:1383 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 20115: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x50 mm/kasan/generic.c:521 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free mm/kasan/common.c:200 [inline] __kasan_slab_free+0x10a/0x190 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:162 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook mm/slub.c:1807 [inline] slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x7a/0x190 mm/slub.c:3800 local_release net/nfc/llcp_core.c:174 [inline] kref_put include/linux/kref.h:65 [inline] nfc_llcp_local_put net/nfc/llcp_core.c:182 [inline] nfc_llcp_local_put net/nfc/llcp_core.c:177 [inline] nfc_llcp_unregister_device+0x206/0x290 net/nfc/llcp_core.c:1620 nfc_unregister_device+0x160/0x1d0 net/nfc/core.c:1179 virtual_ncidev_close+0x52/0xa0 drivers/nfc/virtual_ncidev.c:163 __fput+0x252/0xa20 fs/file_table.c:321 task_work_run+0x174/0x270 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x108/0x110 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x21/0x50 kernel/entry/common.c:297 do_syscall_64+0x4c/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x72/0xdc Last potentially related work creation: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 __kasan_record_aux_stack+0x95/0xb0 mm/kasan/generic.c:491 kvfree_call_rcu+0x29/0xa80 kernel/rcu/tree.c:3328 drop_sysctl_table+0x3be/0x4e0 fs/proc/proc_sysctl.c:1735 unregister_sysctl_table.part.0+0x9c/0x190 fs/proc/proc_sysctl.c:1773 unregister_sysctl_table+0x24/0x30 fs/proc/proc_sysctl.c:1753 neigh_sysctl_unregister+0x5f/0x80 net/core/neighbour.c:3895 addrconf_notify+0x140/0x17b0 net/ipv6/addrconf.c:3684 notifier_call_chain+0xbe/0x210 kernel/notifier.c:87 call_netdevice_notifiers_info+0xb5/0x150 net/core/dev.c:1937 call_netdevice_notifiers_extack net/core/dev.c:1975 [inline] call_netdevice_notifiers net/core/dev.c:1989 [inline] dev_change_name+0x3c3/0x870 net/core/dev.c:1211 dev_ifsioc+0x800/0xf70 net/core/dev_ioctl.c:376 dev_ioctl+0x3d9/0xf80 net/core/dev_ioctl.c:542 sock_do_ioctl+0x160/0x260 net/socket.c:1213 sock_ioctl+0x3f9/0x670 net/socket.c:1316 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x19e/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc The buggy address belongs to the object at ffff888105b0e400 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 16 bytes inside of freed 1024-byte region [ffff888105b0e400, ffff888105b0e800) The buggy address belongs to the physical page: head:ffffea000416c200 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0x200000000010200(slab|head|node=0|zone=2) raw: 0200000000010200 ffff8881000430c0 ffffea00044c7010 ffffea0004510e10 raw: 0000000000000000 00000000000a000a 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888105b0e300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888105b0e380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888105b0e400: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888105b0e480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888105b0e500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb In summary, this patch solves those use-after-free by 1. Re-implement the nfc_llcp_find_local(). The current version does not grab the reference when getting the local from the linked list. For example, the llcp_sock_bind() gets the reference like below: // llcp_sock_bind() local = nfc_llcp_find_local(dev); // A ..... \ | raceable ..... / llcp_sock->local = nfc_llcp_local_get(local); // B There is an apparent race window that one can drop the reference and free the local object fetched in (A) before (B) gets the reference. 2. Some callers of the nfc_llcp_find_local() do not grab the reference at all. For example, the nfc_genl_llc_{{get/set}_params/sdreq} functions. We add the nfc_llcp_local_put() for them. Moreover, we add the necessary error handling function to put the reference. 3. Add the nfc_llcp_remove_local() helper. The local object is removed from the linked list in local_release() when all reference is gone. This patch removes it when nfc_llcp_unregister_device() is called. Therefore, every caller of nfc_llcp_find_local() will get a reference even when the nfc_llcp_unregister_device() is called. This promises no use-after-free for the local object is ever possible. Fixes: 52feb444a903 ("NFC: Extend netlink interface for LTO, RW, and MIUX parameters support") Fixes: c7aa12252f51 ("NFC: Take a reference on the LLCP local pointer when creating a socket") Signed-off-by: Lin Ma Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/nfc/llcp.h | 1 - net/nfc/llcp_commands.c | 12 +++++++--- net/nfc/llcp_core.c | 51 ++++++++++++++++++++++++++++++++++------- net/nfc/llcp_sock.c | 18 ++++++++------- net/nfc/netlink.c | 20 ++++++++++++---- net/nfc/nfc.h | 1 + 6 files changed, 78 insertions(+), 25 deletions(-) diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index d49d4bf2e37c..a81893bc06ce 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -202,7 +202,6 @@ void nfc_llcp_sock_link(struct llcp_sock_list *l, struct sock *s); void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *s); void nfc_llcp_socket_remote_param_init(struct nfc_llcp_sock *sock); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); -struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local); int nfc_llcp_local_put(struct nfc_llcp_local *local); u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, struct nfc_llcp_sock *sock); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index bb9f40563ff6..5b8754ae7d3a 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -361,6 +361,7 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) struct sk_buff *skb; struct nfc_llcp_local *local; u16 size = 0; + int err; pr_debug("Sending SYMM\n"); @@ -372,8 +373,10 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; skb = alloc_skb(size, GFP_KERNEL); - if (skb == NULL) - return -ENOMEM; + if (skb == NULL) { + err = -ENOMEM; + goto out; + } skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); @@ -383,8 +386,11 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX); - return nfc_data_exchange(dev, local->target_idx, skb, + err = nfc_data_exchange(dev, local->target_idx, skb, nfc_llcp_recv, local); +out: + nfc_llcp_local_put(local); + return err; } int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index fd43e75abd94..ddfd159f64e1 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -17,6 +17,8 @@ static u8 llcp_magic[3] = {0x46, 0x66, 0x6d}; static LIST_HEAD(llcp_devices); +/* Protects llcp_devices list */ +static DEFINE_SPINLOCK(llcp_devices_lock); static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb); @@ -143,7 +145,7 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, write_unlock(&local->raw_sockets.lock); } -struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) +static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { kref_get(&local->ref); @@ -171,7 +173,6 @@ static void local_release(struct kref *ref) local = container_of(ref, struct nfc_llcp_local, ref); - list_del(&local->list); local_cleanup(local); kfree(local); } @@ -284,12 +285,33 @@ static void nfc_llcp_sdreq_timer(struct timer_list *t) struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev) { struct nfc_llcp_local *local; + struct nfc_llcp_local *res = NULL; + spin_lock(&llcp_devices_lock); list_for_each_entry(local, &llcp_devices, list) - if (local->dev == dev) - return local; + if (local->dev == dev) { + res = nfc_llcp_local_get(local); + break; + } + spin_unlock(&llcp_devices_lock); - pr_debug("No device found\n"); + return res; +} + +static struct nfc_llcp_local *nfc_llcp_remove_local(struct nfc_dev *dev) +{ + struct nfc_llcp_local *local, *tmp; + + spin_lock(&llcp_devices_lock); + list_for_each_entry_safe(local, tmp, &llcp_devices, list) + if (local->dev == dev) { + list_del(&local->list); + spin_unlock(&llcp_devices_lock); + return local; + } + spin_unlock(&llcp_devices_lock); + + pr_warn("Shutting down device not found\n"); return NULL; } @@ -610,12 +632,15 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) *general_bytes_len = local->gb_len; + nfc_llcp_local_put(local); + return local->gb; } int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { struct nfc_llcp_local *local; + int err; if (gb_len < 3 || gb_len > NFC_MAX_GT_LEN) return -EINVAL; @@ -632,12 +657,16 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) if (memcmp(local->remote_gb, llcp_magic, 3)) { pr_err("MAC does not support LLCP\n"); - return -EINVAL; + err = -EINVAL; + goto out; } - return nfc_llcp_parse_gb_tlv(local, + err = nfc_llcp_parse_gb_tlv(local, &local->remote_gb[3], local->remote_gb_len - 3); +out: + nfc_llcp_local_put(local); + return err; } static u8 nfc_llcp_dsap(const struct sk_buff *pdu) @@ -1527,6 +1556,8 @@ int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb) __nfc_llcp_recv(local, skb); + nfc_llcp_local_put(local); + return 0; } @@ -1543,6 +1574,8 @@ void nfc_llcp_mac_is_down(struct nfc_dev *dev) /* Close and purge all existing sockets */ nfc_llcp_socket_release(local, true, 0); + + nfc_llcp_local_put(local); } void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, @@ -1568,6 +1601,8 @@ void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, mod_timer(&local->link_timer, jiffies + msecs_to_jiffies(local->remote_lto)); } + + nfc_llcp_local_put(local); } int nfc_llcp_register_device(struct nfc_dev *ndev) @@ -1618,7 +1653,7 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) void nfc_llcp_unregister_device(struct nfc_dev *dev) { - struct nfc_llcp_local *local = nfc_llcp_find_local(dev); + struct nfc_llcp_local *local = nfc_llcp_remove_local(dev); if (local == NULL) { pr_debug("No such device\n"); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index fdf0856182c6..6e1fba208493 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -99,7 +99,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; llcp_sock->service_name_len = min_t(unsigned int, llcp_addr.service_name_len, @@ -181,7 +181,7 @@ static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr, } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; nfc_llcp_sock_link(&local->raw_sockets, sk); @@ -698,22 +698,22 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, if (dev->dep_link_up == false) { ret = -ENOLINK; device_unlock(&dev->dev); - goto put_dev; + goto sock_llcp_put_local; } device_unlock(&dev->dev); if (local->rf_mode == NFC_RF_INITIATOR && addr->target_idx != local->target_idx) { ret = -ENOLINK; - goto put_dev; + goto sock_llcp_put_local; } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { ret = -ENOMEM; - goto sock_llcp_put_local; + goto sock_llcp_nullify; } llcp_sock->reserved_ssap = llcp_sock->ssap; @@ -759,11 +759,13 @@ sock_unlink: sock_llcp_release: nfc_llcp_put_ssap(local, llcp_sock->ssap); -sock_llcp_put_local: - nfc_llcp_local_put(llcp_sock->local); +sock_llcp_nullify: llcp_sock->local = NULL; llcp_sock->dev = NULL; +sock_llcp_put_local: + nfc_llcp_local_put(local); + put_dev: nfc_put_device(dev); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index e0e116865511..1c5b3ce1e8b1 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1039,11 +1039,14 @@ static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { rc = -ENOMEM; - goto exit; + goto put_local; } rc = nfc_genl_send_params(msg, local, info->snd_portid, info->snd_seq); +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); @@ -1105,7 +1108,7 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NFC_ATTR_LLC_PARAM_LTO]) { if (dev->dep_link_up) { rc = -EINPROGRESS; - goto exit; + goto put_local; } local->lto = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_LTO]); @@ -1117,6 +1120,9 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) local->miux = cpu_to_be16(miux); +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); @@ -1172,7 +1178,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) if (rc != 0) { rc = -EINVAL; - goto exit; + goto put_local; } if (!sdp_attrs[NFC_SDP_ATTR_URI]) @@ -1191,7 +1197,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) sdreq = nfc_llcp_build_sdreq_tlv(tid, uri, uri_len); if (sdreq == NULL) { rc = -ENOMEM; - goto exit; + goto put_local; } tlvs_len += sdreq->tlv_len; @@ -1201,10 +1207,14 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) if (hlist_empty(&sdreq_list)) { rc = -EINVAL; - goto exit; + goto put_local; } rc = nfc_llcp_send_snl_sdreq(local, &sdreq_list, tlvs_len); + +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index de2ec66d7e83..0b1e6466f4fb 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -52,6 +52,7 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len); u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len); int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); +int nfc_llcp_local_put(struct nfc_llcp_local *local); int __init nfc_llcp_init(void); void nfc_llcp_exit(void); void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp); From 36e07e8acfb9d4aacd6abf92a5e4c65b789f613a Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Mon, 19 Jun 2023 20:06:57 +0100 Subject: [PATCH 3821/4345] lib/ts_bm: reset initial match offset for every block of text [ Upstream commit 6f67fbf8192da80c4db01a1800c7fceaca9cf1f9 ] The `shift` variable which indicates the offset in the string at which to start matching the pattern is initialized to `bm->patlen - 1`, but it is not reset when a new block is retrieved. This means the implemen- tation may start looking at later and later positions in each successive block and miss occurrences of the pattern at the beginning. E.g., consider a HTTP packet held in a non-linear skb, where the HTTP request line occurs in the second block: [... 52 bytes of packet headers ...] GET /bmtest HTTP/1.1\r\nHost: www.example.com\r\n\r\n and the pattern is "GET /bmtest". Once the first block comprising the packet headers has been examined, `shift` will be pointing to somewhere near the end of the block, and so when the second block is examined the request line at the beginning will be missed. Reinitialize the variable for each new block. Fixes: 8082e4ed0a61 ("[LIB]: Boyer-Moore extension for textsearch infrastructure strike #2") Link: https://bugzilla.netfilter.org/show_bug.cgi?id=1390 Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- lib/ts_bm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/lib/ts_bm.c b/lib/ts_bm.c index 4cf250031f0f..352ae837e031 100644 --- a/lib/ts_bm.c +++ b/lib/ts_bm.c @@ -60,10 +60,12 @@ static unsigned int bm_find(struct ts_config *conf, struct ts_state *state) struct ts_bm *bm = ts_config_priv(conf); unsigned int i, text_len, consumed = state->offset; const u8 *text; - int shift = bm->patlen - 1, bs; + int bs; const u8 icase = conf->flags & TS_IGNORECASE; for (;;) { + int shift = bm->patlen - 1; + text_len = conf->get_next_block(consumed, &text, conf, state); if (unlikely(text_len == 0)) From 9bdcda7abaf22f6453e5b5efb7eb4e524095d5d8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 21 Jun 2023 17:56:53 +0200 Subject: [PATCH 3822/4345] netfilter: conntrack: dccp: copy entire header to stack buffer, not just basic one [ Upstream commit ff0a3a7d52ff7282dbd183e7fc29a1fe386b0c30 ] Eric Dumazet says: nf_conntrack_dccp_packet() has an unique: dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); And nothing more is 'pulled' from the packet, depending on the content. dh->dccph_doff, and/or dh->dccph_x ...) So dccp_ack_seq() is happily reading stuff past the _dh buffer. BUG: KASAN: stack-out-of-bounds in nf_conntrack_dccp_packet+0x1134/0x11c0 Read of size 4 at addr ffff000128f66e0c by task syz-executor.2/29371 [..] Fix this by increasing the stack buffer to also include room for the extra sequence numbers and all the known dccp packet type headers, then pull again after the initial validation of the basic header. While at it, mark packets invalid that lack 48bit sequence bit but where RFC says the type MUST use them. Compile tested only. v2: first skb_header_pointer() now needs to adjust the size to only pull the generic header. (Eric) Heads-up: I intend to remove dccp conntrack support later this year. Fixes: 2bc780499aa3 ("[NETFILTER]: nf_conntrack: add DCCP protocol support") Reported-by: Eric Dumazet Signed-off-by: Florian Westphal Reviewed-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_proto_dccp.c | 52 +++++++++++++++++++++++-- 1 file changed, 49 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 94001eb51ffe..a9ae292e932a 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -431,9 +431,19 @@ static bool dccp_error(const struct dccp_hdr *dh, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { + static const unsigned long require_seq48 = 1 << DCCP_PKT_REQUEST | + 1 << DCCP_PKT_RESPONSE | + 1 << DCCP_PKT_CLOSEREQ | + 1 << DCCP_PKT_CLOSE | + 1 << DCCP_PKT_RESET | + 1 << DCCP_PKT_SYNC | + 1 << DCCP_PKT_SYNCACK; unsigned int dccp_len = skb->len - dataoff; unsigned int cscov; const char *msg; + u8 type; + + BUILD_BUG_ON(DCCP_PKT_INVALID >= BITS_PER_LONG); if (dh->dccph_doff * 4 < sizeof(struct dccp_hdr) || dh->dccph_doff * 4 > dccp_len) { @@ -458,10 +468,17 @@ static bool dccp_error(const struct dccp_hdr *dh, goto out_invalid; } - if (dh->dccph_type >= DCCP_PKT_INVALID) { + type = dh->dccph_type; + if (type >= DCCP_PKT_INVALID) { msg = "nf_ct_dccp: reserved packet type "; goto out_invalid; } + + if (test_bit(type, &require_seq48) && !dh->dccph_x) { + msg = "nf_ct_dccp: type lacks 48bit sequence numbers"; + goto out_invalid; + } + return false; out_invalid: nf_l4proto_log_invalid(skb, state->net, state->pf, @@ -469,24 +486,53 @@ out_invalid: return true; } +struct nf_conntrack_dccp_buf { + struct dccp_hdr dh; /* generic header part */ + struct dccp_hdr_ext ext; /* optional depending dh->dccph_x */ + union { /* depends on header type */ + struct dccp_hdr_ack_bits ack; + struct dccp_hdr_request req; + struct dccp_hdr_response response; + struct dccp_hdr_reset rst; + } u; +}; + +static struct dccp_hdr * +dccp_header_pointer(const struct sk_buff *skb, int offset, const struct dccp_hdr *dh, + struct nf_conntrack_dccp_buf *buf) +{ + unsigned int hdrlen = __dccp_hdr_len(dh); + + if (hdrlen > sizeof(*buf)) + return NULL; + + return skb_header_pointer(skb, offset, hdrlen, buf); +} + int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - struct dccp_hdr _dh, *dh; + struct nf_conntrack_dccp_buf _dh; u_int8_t type, old_state, new_state; enum ct_dccp_roles role; unsigned int *timeouts; + struct dccp_hdr *dh; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); + dh = skb_header_pointer(skb, dataoff, sizeof(*dh), &_dh.dh); if (!dh) return NF_DROP; if (dccp_error(dh, skb, dataoff, state)) return -NF_ACCEPT; + /* pull again, including possible 48 bit sequences and subtype header */ + dh = dccp_header_pointer(skb, dataoff, dh, &_dh); + if (!dh) + return NF_DROP; + type = dh->dccph_type; if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh)) return -NF_ACCEPT; From 5215c009683903fde66eb11d29026f15f4d53332 Mon Sep 17 00:00:00 2001 From: "Ilia.Gavrilov" Date: Fri, 23 Jun 2023 11:23:46 +0000 Subject: [PATCH 3823/4345] netfilter: nf_conntrack_sip: fix the ct_sip_parse_numerical_param() return value. [ Upstream commit f188d30087480eab421cd8ca552fb15f55d57f4d ] ct_sip_parse_numerical_param() returns only 0 or 1 now. But process_register_request() and process_register_response() imply checking for a negative value if parsing of a numerical header parameter failed. The invocation in nf_nat_sip() looks correct: if (ct_sip_parse_numerical_param(...) > 0 && ...) { ... } Make the return value of the function ct_sip_parse_numerical_param() a tristate to fix all the cases a) return 1 if value is found; *val is set b) return 0 if value is not found; *val is unchanged c) return -1 on error; *val is undefined Found by InfoTeCS on behalf of Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 0f32a40fc91a ("[NETFILTER]: nf_conntrack_sip: create signalling expectations") Signed-off-by: Ilia.Gavrilov Reviewed-by: Simon Horman Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Sasha Levin --- net/netfilter/nf_conntrack_sip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 78fd9122b70c..751df19fe0f8 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -611,7 +611,7 @@ int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr, start += strlen(name); *val = simple_strtoul(start, &end, 0); if (start == end) - return 0; + return -1; if (matchoff && matchlen) { *matchoff = start - dptr; *matchlen = end - start; From d10b38036977310e1a7c763e9e4f99bd6fa3c1bb Mon Sep 17 00:00:00 2001 From: Cambda Zhu Date: Mon, 26 Jun 2023 17:33:47 +0800 Subject: [PATCH 3824/4345] ipvlan: Fix return value of ipvlan_queue_xmit() [ Upstream commit 8a9922e7be6d042fa00f894c376473b17a162b66 ] ipvlan_queue_xmit() should return NET_XMIT_XXX, but ipvlan_xmit_mode_l2/l3() returns rx_handler_result_t or NET_RX_XXX in some cases. ipvlan_rcv_frame() will only return RX_HANDLER_CONSUMED in ipvlan_xmit_mode_l2/l3() because 'local' is true. It's equal to NET_XMIT_SUCCESS. But dev_forward_skb() can return NET_RX_SUCCESS or NET_RX_DROP, and returning NET_RX_DROP(NET_XMIT_DROP) will increase both ipvlan and ipvlan->phy_dev drops counter. The skb to forward can be treated as xmitted successfully. This patch makes ipvlan_queue_xmit() return NET_XMIT_SUCCESS for forward skb. Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.") Signed-off-by: Cambda Zhu Link: https://lore.kernel.org/r/20230626093347.7492-1-cambda@linux.alibaba.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ipvlan/ipvlan_core.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 0a5b5ff597c6..ab09d110760e 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -586,7 +586,8 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) consume_skb(skb); return NET_XMIT_DROP; } - return ipvlan_rcv_frame(addr, &skb, true); + ipvlan_rcv_frame(addr, &skb, true); + return NET_XMIT_SUCCESS; } } out: @@ -612,7 +613,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) consume_skb(skb); return NET_XMIT_DROP; } - return ipvlan_rcv_frame(addr, &skb, true); + ipvlan_rcv_frame(addr, &skb, true); + return NET_XMIT_SUCCESS; } } skb = skb_share_check(skb, GFP_ATOMIC); @@ -624,7 +626,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) * the skb for the main-dev. At the RX side we just return * RX_PASS for it to be processed further on the stack. */ - return dev_forward_skb(ipvlan->phy_dev, skb); + dev_forward_skb(ipvlan->phy_dev, skb); + return NET_XMIT_SUCCESS; } else if (is_multicast_ether_addr(eth->h_dest)) { skb_reset_mac_header(skb); From 472a615e66b9b4c7d631f8d493553f035c9d96de Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 26 Jun 2023 09:43:13 -0700 Subject: [PATCH 3825/4345] netlink: Add __sock_i_ino() for __netlink_diag_dump(). [ Upstream commit 25a9c8a4431c364f97f75558cb346d2ad3f53fbb ] syzbot reported a warning in __local_bh_enable_ip(). [0] Commit 8d61f926d420 ("netlink: fix potential deadlock in netlink_set_err()") converted read_lock(&nl_table_lock) to read_lock_irqsave() in __netlink_diag_dump() to prevent a deadlock. However, __netlink_diag_dump() calls sock_i_ino() that uses read_lock_bh() and read_unlock_bh(). If CONFIG_TRACE_IRQFLAGS=y, read_unlock_bh() finally enables IRQ even though it should stay disabled until the following read_unlock_irqrestore(). Using read_lock() in sock_i_ino() would trigger a lockdep splat in another place that was fixed in commit f064af1e500a ("net: fix a lockdep splat"), so let's add __sock_i_ino() that would be safe to use under BH disabled. [0]: WARNING: CPU: 0 PID: 5012 at kernel/softirq.c:376 __local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 Modules linked in: CPU: 0 PID: 5012 Comm: syz-executor487 Not tainted 6.4.0-rc7-syzkaller-00202-g6f68fc395f49 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 RIP: 0010:__local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 Code: 45 bf 01 00 00 00 e8 91 5b 0a 00 e8 3c 15 3d 00 fb 65 8b 05 ec e9 b5 7e 85 c0 74 58 5b 5d c3 65 8b 05 b2 b6 b4 7e 85 c0 75 a2 <0f> 0b eb 9e e8 89 15 3d 00 eb 9f 48 89 ef e8 6f 49 18 00 eb a8 0f RSP: 0018:ffffc90003a1f3d0 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000201 RCX: 1ffffffff1cf5996 RDX: 0000000000000000 RSI: 0000000000000201 RDI: ffffffff8805c6f3 RBP: ffffffff8805c6f3 R08: 0000000000000001 R09: ffff8880152b03a3 R10: ffffed1002a56074 R11: 0000000000000005 R12: 00000000000073e4 R13: dffffc0000000000 R14: 0000000000000002 R15: 0000000000000000 FS: 0000555556726300(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000045ad50 CR3: 000000007c646000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: sock_i_ino+0x83/0xa0 net/core/sock.c:2559 __netlink_diag_dump+0x45c/0x790 net/netlink/diag.c:171 netlink_diag_dump+0xd6/0x230 net/netlink/diag.c:207 netlink_dump+0x570/0xc50 net/netlink/af_netlink.c:2269 __netlink_dump_start+0x64b/0x910 net/netlink/af_netlink.c:2374 netlink_dump_start include/linux/netlink.h:329 [inline] netlink_diag_handler_dump+0x1ae/0x250 net/netlink/diag.c:238 __sock_diag_cmd net/core/sock_diag.c:238 [inline] sock_diag_rcv_msg+0x31e/0x440 net/core/sock_diag.c:269 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2547 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:280 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x925/0xe30 net/netlink/af_netlink.c:1914 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0xde/0x190 net/socket.c:747 ____sys_sendmsg+0x71c/0x900 net/socket.c:2503 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2557 __sys_sendmsg+0xf7/0x1c0 net/socket.c:2586 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f5303aaabb9 Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc7506e548 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5303aaabb9 RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003 RBP: 00007f5303a6ed60 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f5303a6edf0 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Fixes: 8d61f926d420 ("netlink: fix potential deadlock in netlink_set_err()") Reported-by: syzbot+5da61cf6a9bc1902d422@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=5da61cf6a9bc1902d422 Suggested-by: Eric Dumazet Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230626164313.52528-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/sock.h | 1 + net/core/sock.c | 17 ++++++++++++++--- net/netlink/diag.c | 2 +- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 03e7f7581559..1fb5c535537c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1934,6 +1934,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) } kuid_t sock_i_uid(struct sock *sk); +unsigned long __sock_i_ino(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) diff --git a/net/core/sock.c b/net/core/sock.c index 9b013d052a72..4e00c6e2cb43 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2175,13 +2175,24 @@ kuid_t sock_i_uid(struct sock *sk) } EXPORT_SYMBOL(sock_i_uid); +unsigned long __sock_i_ino(struct sock *sk) +{ + unsigned long ino; + + read_lock(&sk->sk_callback_lock); + ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; + read_unlock(&sk->sk_callback_lock); + return ino; +} +EXPORT_SYMBOL(__sock_i_ino); + unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock_bh(&sk->sk_callback_lock); - ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock_bh(&sk->sk_callback_lock); + local_bh_disable(); + ino = __sock_i_ino(sk); + local_bh_enable(); return ino; } EXPORT_SYMBOL(sock_i_ino); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 4143b2ea4195..e4f21b1067bc 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -168,7 +168,7 @@ mc_list: NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - sock_i_ino(sk)) < 0) { + __sock_i_ino(sk)) < 0) { ret = 1; break; } From b2213fc60b83dcd7b15c39bffd22ebd201f50e15 Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Thu, 13 Apr 2023 08:12:28 -0700 Subject: [PATCH 3826/4345] radeon: avoid double free in ci_dpm_init() [ Upstream commit 20c3dffdccbd494e0dd631d1660aeecbff6775f2 ] Several calls to ci_dpm_fini() will attempt to free resources that either have been freed before or haven't been allocated yet. This may lead to undefined or dangerous behaviour. For instance, if r600_parse_extended_power_table() fails, it might call r600_free_extended_power_table() as will ci_dpm_fini() later during error handling. Fix this by only freeing pointers to objects previously allocated. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: cc8dbbb4f62a ("drm/radeon: add dpm support for CI dGPUs (v2)") Co-developed-by: Natalia Petrova Signed-off-by: Nikita Zhandarovich Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/radeon/ci_dpm.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 886e9959496f..f98df826972c 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -5541,6 +5541,7 @@ static int ci_parse_power_table(struct radeon_device *rdev) u8 frev, crev; u8 *power_state_offset; struct ci_ps *ps; + int ret; if (!atom_parse_data_header(mode_info->atom_context, index, NULL, &frev, &crev, &data_offset)) @@ -5570,11 +5571,15 @@ static int ci_parse_power_table(struct radeon_device *rdev) non_clock_array_index = power_state->v2.nonClockInfoIndex; non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *) &non_clock_info_array->nonClockInfo[non_clock_array_index]; - if (!rdev->pm.power_state[i].clock_info) - return -EINVAL; + if (!rdev->pm.power_state[i].clock_info) { + ret = -EINVAL; + goto err_free_ps; + } ps = kzalloc(sizeof(struct ci_ps), GFP_KERNEL); - if (ps == NULL) - return -ENOMEM; + if (ps == NULL) { + ret = -ENOMEM; + goto err_free_ps; + } rdev->pm.dpm.ps[i].ps_priv = ps; ci_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i], non_clock_info, @@ -5614,6 +5619,12 @@ static int ci_parse_power_table(struct radeon_device *rdev) } return 0; + +err_free_ps: + for (i = 0; i < rdev->pm.dpm.num_ps; i++) + kfree(rdev->pm.dpm.ps[i].ps_priv); + kfree(rdev->pm.dpm.ps); + return ret; } static int ci_get_vbios_boot_values(struct radeon_device *rdev, @@ -5702,25 +5713,26 @@ int ci_dpm_init(struct radeon_device *rdev) ret = ci_get_vbios_boot_values(rdev, &pi->vbios_boot_state); if (ret) { - ci_dpm_fini(rdev); + kfree(rdev->pm.dpm.priv); return ret; } ret = r600_get_platform_caps(rdev); if (ret) { - ci_dpm_fini(rdev); + kfree(rdev->pm.dpm.priv); return ret; } ret = r600_parse_extended_power_table(rdev); if (ret) { - ci_dpm_fini(rdev); + kfree(rdev->pm.dpm.priv); return ret; } ret = ci_parse_power_table(rdev); if (ret) { - ci_dpm_fini(rdev); + kfree(rdev->pm.dpm.priv); + r600_free_extended_power_table(rdev); return ret; } From 2780d5844855c7d5e245d273dac272ba1c00d86b Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Thu, 2 May 2019 13:21:48 -0400 Subject: [PATCH 3827/4345] drm/amd/display: Explicitly specify update type per plane info change [ Upstream commit 710cc1e7cd461446a9325c9bd1e9a54daa462952 ] [Why] The bit for flip addr is being set causing the determination for FAST vs MEDIUM to always return MEDIUM when plane info is provided as a surface update. This causes extreme stuttering for the typical atomic update path on Linux. [How] Don't use update_flags->raw for determining FAST vs MEDIUM. It's too fragile to changes like this. Explicitly specify the update type per update flag instead. It's not as clever as checking the bits itself but at least it's correct. Fixes: aa5fdb1ab5b6 ("drm/amd/display: Explicitly specify update type per plane info change") Reviewed-by: Rodrigo Siqueira Signed-off-by: Nicholas Kazlauskas Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/core/dc.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 7e0a55aa2b18..099542dd3154 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1855,9 +1855,6 @@ static enum surface_update_type det_surface_update(const struct dc *dc, enum surface_update_type overall_type = UPDATE_TYPE_FAST; union surface_update_flags *update_flags = &u->surface->update_flags; - if (u->flip_addr) - update_flags->bits.addr_update = 1; - if (!is_surface_in_context(context, u->surface) || u->surface->force_full_update) { update_flags->raw = 0xFFFFFFFF; return UPDATE_TYPE_FULL; From 4e0fd4f54beaeb92fe697cf2d1146a7105c1f84c Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Mon, 1 May 2023 17:01:45 -0700 Subject: [PATCH 3828/4345] Input: drv260x - sleep between polling GO bit [ Upstream commit efef661dfa6bf8cbafe4cd6a97433fcef0118967 ] When doing the initial startup there's no need to poll without any delay and spam the I2C bus. Let's sleep 15ms between each attempt, which is the same time as used in the vendor driver. Fixes: 7132fe4f5687 ("Input: drv260x - add TI drv260x haptics driver") Signed-off-by: Luca Weiss Link: https://lore.kernel.org/r/20230430-drv260x-improvements-v1-2-1fb28b4cc698@z3ntu.xyz Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/misc/drv260x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/misc/drv260x.c b/drivers/input/misc/drv260x.c index 79d7fa710a71..54002d1a446b 100644 --- a/drivers/input/misc/drv260x.c +++ b/drivers/input/misc/drv260x.c @@ -435,6 +435,7 @@ static int drv260x_init(struct drv260x_data *haptics) } do { + usleep_range(15000, 15500); error = regmap_read(haptics->regmap, DRV260X_GO, &cal_buf); if (error) { dev_err(&haptics->client->dev, From 1b4f23fdf27f537489a823e0b842de7d1caeab6d Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Thu, 27 Apr 2023 16:29:26 +0200 Subject: [PATCH 3829/4345] drm/bridge: tc358768: always enable HS video mode [ Upstream commit 75a8aeac2573ab258c53676eba9b3796ea691988 ] Always enable HS video mode setting the TXMD bit, without this change no video output is present with DSI sinks that are setting MIPI_DSI_MODE_LPM flag (tested with LT8912B DSI-HDMI bridge). Previously the driver was enabling HS mode only when the DSI sink was not explicitly setting the MIPI_DSI_MODE_LPM, however this is not correct. The MIPI_DSI_MODE_LPM is supposed to indicate that the sink is willing to receive data in low power mode, however clearing the TC358768_DSI_CONTROL_TXMD bit will make the TC358768 send video in LP mode that is not the intended behavior. Fixes: ff1ca6397b1d ("drm/bridge: Add tc358768 driver") Signed-off-by: Francesco Dolcini Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-2-francesco@dolcini.it Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358768.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index 8ed8302d6bbb..e65af025a771 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -819,8 +819,7 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) val = TC358768_DSI_CONFW_MODE_SET | TC358768_DSI_CONFW_ADDR_DSI_CONTROL; val |= (dsi_dev->lanes - 1) << 1; - if (!(dsi_dev->mode_flags & MIPI_DSI_MODE_LPM)) - val |= TC358768_DSI_CONTROL_TXMD; + val |= TC358768_DSI_CONTROL_TXMD; if (!(dsi_dev->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS)) val |= TC358768_DSI_CONTROL_HSCKMD; From 825b00c685893bddcf7b261d47927d94d589f476 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Thu, 27 Apr 2023 16:29:27 +0200 Subject: [PATCH 3830/4345] drm/bridge: tc358768: fix PLL parameters computation [ Upstream commit 6a4020b4c63911977aaf8047f904a300d15de739 ] According to Toshiba documentation the PLL input clock after the divider should be not less than 4MHz, fix the PLL parameters computation accordingly. Fixes: ff1ca6397b1d ("drm/bridge: Add tc358768 driver") Signed-off-by: Francesco Dolcini Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-3-francesco@dolcini.it Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358768.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index e65af025a771..d9021e750940 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -329,13 +329,17 @@ static int tc358768_calc_pll(struct tc358768_priv *priv, u32 fbd; for (fbd = 0; fbd < 512; ++fbd) { - u32 pll, diff; + u32 pll, diff, pll_in; pll = (u32)div_u64((u64)refclk * (fbd + 1), divisor); if (pll >= max_pll || pll < min_pll) continue; + pll_in = (u32)div_u64((u64)refclk, prd + 1); + if (pll_in < 4000000) + continue; + diff = max(pll, target_pll) - min(pll, target_pll); if (diff < best_diff) { From 46b74171898981a308cabe718b622ea1cc132f64 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Thu, 27 Apr 2023 16:29:28 +0200 Subject: [PATCH 3831/4345] drm/bridge: tc358768: fix PLL target frequency [ Upstream commit ffd2e4bbea626d565b9817312b0fcfb382fecb88 ] Correctly compute the PLL target frequency, the current formula works correctly only when the input bus width is 24bit, actually to properly compute the PLL target frequency what is relevant is the bits-per-pixel on the DSI link. No regression expected since the DSI format is currently hard-coded as MIPI_DSI_FMT_RGB888. Fixes: ff1ca6397b1d ("drm/bridge: Add tc358768 driver") Signed-off-by: Francesco Dolcini Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-4-francesco@dolcini.it Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358768.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index d9021e750940..4aec4b428189 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -147,6 +147,7 @@ struct tc358768_priv { u32 pd_lines; /* number of Parallel Port Input Data Lines */ u32 dsi_lanes; /* number of DSI Lanes */ + u32 dsi_bpp; /* number of Bits Per Pixel over DSI */ /* Parameters for PLL programming */ u32 fbd; /* PLL feedback divider */ @@ -279,12 +280,12 @@ static void tc358768_hw_disable(struct tc358768_priv *priv) static u32 tc358768_pll_to_pclk(struct tc358768_priv *priv, u32 pll_clk) { - return (u32)div_u64((u64)pll_clk * priv->dsi_lanes, priv->pd_lines); + return (u32)div_u64((u64)pll_clk * priv->dsi_lanes, priv->dsi_bpp); } static u32 tc358768_pclk_to_pll(struct tc358768_priv *priv, u32 pclk) { - return (u32)div_u64((u64)pclk * priv->pd_lines, priv->dsi_lanes); + return (u32)div_u64((u64)pclk * priv->dsi_bpp, priv->dsi_lanes); } static int tc358768_calc_pll(struct tc358768_priv *priv, @@ -421,6 +422,7 @@ static int tc358768_dsi_host_attach(struct mipi_dsi_host *host, priv->output.panel = panel; priv->dsi_lanes = dev->lanes; + priv->dsi_bpp = mipi_dsi_pixel_format_to_bpp(dev->format); /* get input ep (port0/endpoint0) */ ret = -EINVAL; @@ -432,7 +434,7 @@ static int tc358768_dsi_host_attach(struct mipi_dsi_host *host, } if (ret) - priv->pd_lines = mipi_dsi_pixel_format_to_bpp(dev->format); + priv->pd_lines = priv->dsi_bpp; drm_bridge_add(&priv->bridge); From 43b2d11ccffbce890d7a190498947e8c0b541a23 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Thu, 27 Apr 2023 16:29:29 +0200 Subject: [PATCH 3832/4345] drm/bridge: tc358768: fix TCLK_ZEROCNT computation [ Upstream commit f9cf811374f42fca31ac34aaf59ee2ae72b89879 ] Correct computation of TCLK_ZEROCNT register. This register must be set to a value that ensure that (TCLK-PREPARECNT + TCLK-ZERO) > 300ns with the actual value of (TCLK-PREPARECNT + TCLK-ZERO) being (1 to 2) + (TCLK_ZEROCNT + 1)) x HSByteClkCycle + (PHY output delay) with PHY output delay being about (2 to 3) x MIPIBitClk cycle in the BitClk conversion. Fixes: ff1ca6397b1d ("drm/bridge: Add tc358768 driver") Signed-off-by: Francesco Dolcini Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-5-francesco@dolcini.it Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358768.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index 4aec4b428189..facd4dab433b 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -725,10 +725,10 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) /* 38ns < TCLK_PREPARE < 95ns */ val = tc358768_ns_to_cnt(65, dsibclk_nsk) - 1; - /* TCLK_PREPARE > 300ns */ - val2 = tc358768_ns_to_cnt(300 + tc358768_to_ns(3 * ui_nsk), - dsibclk_nsk); - val |= (val2 - tc358768_to_ns(phy_delay_nsk - dsibclk_nsk)) << 8; + /* TCLK_PREPARE + TCLK_ZERO > 300ns */ + val2 = tc358768_ns_to_cnt(300 - tc358768_to_ns(2 * ui_nsk), + dsibclk_nsk) - 2; + val |= val2 << 8; dev_dbg(priv->dev, "TCLK_HEADERCNT: 0x%x\n", val); tc358768_write(priv, TC358768_TCLK_HEADERCNT, val); From 33abcfbb17b0a7b014161cf3a270d98a1cfa5eb7 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Thu, 30 Mar 2023 11:59:41 +0200 Subject: [PATCH 3833/4345] drm/bridge: tc358768: Add atomic_get_input_bus_fmts() implementation [ Upstream commit cec5ccef85bd0128cf895612de54a9d21d2015d0 ] Add atomic_get_input_bus_fmts() implementation, tc358768 has a parallel RGB input interface with the actual bus format depending on the amount of parallel input data lines. Without this change when the tc358768 is used with less than 24bit the color mapping is completely wrong. Signed-off-by: Francesco Dolcini Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230330095941.428122-7-francesco@dolcini.it Stable-dep-of: ee18698e212b ("drm/bridge: tc358768: fix TCLK_TRAILCNT computation") Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358768.c | 44 +++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index facd4dab433b..f6c0300090ec 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -871,6 +872,44 @@ static void tc358768_bridge_enable(struct drm_bridge *bridge) } } +#define MAX_INPUT_SEL_FORMATS 1 + +static u32 * +tc358768_atomic_get_input_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + u32 output_fmt, + unsigned int *num_input_fmts) +{ + struct tc358768_priv *priv = bridge_to_tc358768(bridge); + u32 *input_fmts; + + *num_input_fmts = 0; + + input_fmts = kcalloc(MAX_INPUT_SEL_FORMATS, sizeof(*input_fmts), + GFP_KERNEL); + if (!input_fmts) + return NULL; + + switch (priv->pd_lines) { + case 16: + input_fmts[0] = MEDIA_BUS_FMT_RGB565_1X16; + break; + case 18: + input_fmts[0] = MEDIA_BUS_FMT_RGB666_1X18; + break; + default: + case 24: + input_fmts[0] = MEDIA_BUS_FMT_RGB888_1X24; + break; + }; + + *num_input_fmts = MAX_INPUT_SEL_FORMATS; + + return input_fmts; +} + static const struct drm_bridge_funcs tc358768_bridge_funcs = { .attach = tc358768_bridge_attach, .mode_valid = tc358768_bridge_mode_valid, @@ -878,6 +917,11 @@ static const struct drm_bridge_funcs tc358768_bridge_funcs = { .enable = tc358768_bridge_enable, .disable = tc358768_bridge_disable, .post_disable = tc358768_bridge_post_disable, + + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_get_input_bus_fmts = tc358768_atomic_get_input_bus_fmts, }; static const struct drm_bridge_timings default_tc358768_timings = { From 6b9450723babe5af24cf16574f21052a5b458f90 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Thu, 27 Apr 2023 16:29:30 +0200 Subject: [PATCH 3834/4345] drm/bridge: tc358768: fix TCLK_TRAILCNT computation [ Upstream commit ee18698e212b1659dd0850d7e2ae0f22e16ed3d3 ] Correct computation of TCLK_TRAILCNT register. The driver does not implement non-continuous clock mode, so the actual value doesn't make a practical difference yet. However this change also ensures that the value does not write to reserved registers bits in case of under/overflow. This register must be set to a value that ensures that TCLK-TRAIL > 60ns and TEOT <= (105 ns + 12 x UI) with the actual value of TCLK-TRAIL being (TCLK_TRAILCNT + (1 to 2)) xHSByteClkCycle + (2 + (1 to 2)) * HSBYTECLKCycle - (PHY output delay) with PHY output delay being about (2 to 3) x MIPIBitClk cycle in the BitClk conversion. Fixes: ff1ca6397b1d ("drm/bridge: Add tc358768 driver") Signed-off-by: Francesco Dolcini Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-2-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-3-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-4-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-5-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-2-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-3-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-4-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-5-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-2-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-3-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-4-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-5-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-2-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-3-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-4-francesco@dolcini.it Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-5-francesco@dolcini.it Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358768.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index f6c0300090ec..b7372c5b0b81 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -633,6 +634,7 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) struct tc358768_priv *priv = bridge_to_tc358768(bridge); struct mipi_dsi_device *dsi_dev = priv->output.dev; u32 val, val2, lptxcnt, hact, data_type; + s32 raw_val; const struct drm_display_mode *mode; u32 dsibclk_nsk, dsiclk_nsk, ui_nsk, phy_delay_nsk; u32 dsiclk, dsibclk; @@ -733,9 +735,9 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) dev_dbg(priv->dev, "TCLK_HEADERCNT: 0x%x\n", val); tc358768_write(priv, TC358768_TCLK_HEADERCNT, val); - /* TCLK_TRAIL > 60ns + 3*UI */ - val = 60 + tc358768_to_ns(3 * ui_nsk); - val = tc358768_ns_to_cnt(val, dsibclk_nsk) - 5; + /* TCLK_TRAIL > 60ns AND TEOT <= 105 ns + 12*UI */ + raw_val = tc358768_ns_to_cnt(60 + tc358768_to_ns(2 * ui_nsk), dsibclk_nsk) - 5; + val = clamp(raw_val, 0, 127); dev_dbg(priv->dev, "TCLK_TRAILCNT: 0x%x\n", val); tc358768_write(priv, TC358768_TCLK_TRAILCNT, val); From 8e47328fe089ab0b125e6da172267dc6b040053a Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Thu, 27 Apr 2023 16:29:31 +0200 Subject: [PATCH 3835/4345] drm/bridge: tc358768: fix THS_ZEROCNT computation [ Upstream commit 77a089328da791118af9692543a5eedc79eb5fd4 ] Correct computation of THS_ZEROCNT register. This register must be set to a value that ensure that THS_PREPARE + THS_ZERO > 145ns + 10*UI with the actual value of (THS_PREPARE + THS_ZERO) being ((1 to 2) + 1 + (TCLK_ZEROCNT + 1) + (3 to 4)) x ByteClk cycle + + HSByteClk x (2 + (1 to 2)) + (PHY delay) with PHY delay being about (8 + (5 to 6)) x MIPIBitClk cycle in the BitClk conversion. Fixes: ff1ca6397b1d ("drm/bridge: Add tc358768 driver") Signed-off-by: Francesco Dolcini Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-7-francesco@dolcini.it Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358768.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index b7372c5b0b81..a35674b6ff24 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -744,9 +744,10 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) /* 40ns + 4*UI < THS_PREPARE < 85ns + 6*UI */ val = 50 + tc358768_to_ns(4 * ui_nsk); val = tc358768_ns_to_cnt(val, dsibclk_nsk) - 1; - /* THS_ZERO > 145ns + 10*UI */ - val2 = tc358768_ns_to_cnt(145 - tc358768_to_ns(ui_nsk), dsibclk_nsk); - val |= (val2 - tc358768_to_ns(phy_delay_nsk)) << 8; + /* THS_PREPARE + THS_ZERO > 145ns + 10*UI */ + raw_val = tc358768_ns_to_cnt(145 - tc358768_to_ns(3 * ui_nsk), dsibclk_nsk) - 10; + val2 = clamp(raw_val, 0, 127); + val |= val2 << 8; dev_dbg(priv->dev, "THS_HEADERCNT: 0x%x\n", val); tc358768_write(priv, TC358768_THS_HEADERCNT, val); From f2f7d0a4a22a7d8ad24ecf54897255b579245574 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Thu, 27 Apr 2023 16:29:32 +0200 Subject: [PATCH 3836/4345] drm/bridge: tc358768: fix TXTAGOCNT computation [ Upstream commit 3666aad8185af8d0ce164fd3c4974235417d6d0b ] Correct computation of TXTAGOCNT register. This register must be set to a value that ensure that the TTA-GO period = (4 x TLPX) with the actual value of TTA-GO being 4 x (TXTAGOCNT + 1) x (HSByteClk cycle) Fixes: ff1ca6397b1d ("drm/bridge: Add tc358768 driver") Signed-off-by: Francesco Dolcini Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-8-francesco@dolcini.it Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358768.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index a35674b6ff24..40fffce680c5 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -779,7 +779,7 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) /* TXTAGOCNT[26:16] RXTASURECNT[10:0] */ val = tc358768_to_ns((lptxcnt + 1) * dsibclk_nsk * 4); - val = tc358768_ns_to_cnt(val, dsibclk_nsk) - 1; + val = tc358768_ns_to_cnt(val, dsibclk_nsk) / 4 - 1; val2 = tc358768_ns_to_cnt(tc358768_to_ns((lptxcnt + 1) * dsibclk_nsk), dsibclk_nsk) - 2; val |= val2 << 16; From 46a34e145955480a19abf609815a82d1ca73e2ea Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Thu, 27 Apr 2023 16:29:33 +0200 Subject: [PATCH 3837/4345] drm/bridge: tc358768: fix THS_TRAILCNT computation [ Upstream commit bac7842cd179572e8e0fc2d7b5254e40c6e9e057 ] Correct computation of THS_TRAILCNT register. This register must be set to a value that ensure that THS_TRAIL > 60 ns + 4 x UI and THS_TRAIL > 8 x UI and THS_TRAIL < TEOT with TEOT = 105 ns + (12 x UI) with the actual value of THS_TRAIL being (1 + THS_TRAILCNT) x ByteClk cycle + ((1 to 2) + 2) xHSBYTECLK cycle + - (PHY output delay) with PHY output delay being about (8 + (5 to 6)) x MIPIBitClk cycle in the BitClk conversion. Fixes: ff1ca6397b1d ("drm/bridge: Add tc358768 driver") Signed-off-by: Francesco Dolcini Reviewed-by: Robert Foss Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20230427142934.55435-9-francesco@dolcini.it Signed-off-by: Sasha Levin --- drivers/gpu/drm/bridge/tc358768.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index 40fffce680c5..b4a69b210451 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -763,9 +763,10 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) dev_dbg(priv->dev, "TCLK_POSTCNT: 0x%x\n", val); tc358768_write(priv, TC358768_TCLK_POSTCNT, val); - /* 60ns + 4*UI < THS_PREPARE < 105ns + 12*UI */ - val = tc358768_ns_to_cnt(60 + tc358768_to_ns(15 * ui_nsk), - dsibclk_nsk) - 5; + /* max(60ns + 4*UI, 8*UI) < THS_TRAILCNT < 105ns + 12*UI */ + raw_val = tc358768_ns_to_cnt(60 + tc358768_to_ns(18 * ui_nsk), + dsibclk_nsk) - 4; + val = clamp(raw_val, 0, 15); dev_dbg(priv->dev, "THS_TRAILCNT: 0x%x\n", val); tc358768_write(priv, TC358768_THS_TRAILCNT, val); From 20ecae1af578ca741e6cfd0479f7e8f452745d36 Mon Sep 17 00:00:00 2001 From: Luc Ma Date: Mon, 8 May 2023 08:09:16 +0800 Subject: [PATCH 3838/4345] drm/vram-helper: fix function names in vram helper doc [ Upstream commit b8e392245105b50706f18418054821e71e637288 ] Refer to drmm_vram_helper_init() instead of the non-existent drmm_vram_helper_alloc_mm(). Fixes: a5f23a72355d ("drm/vram-helper: Managed vram helpers") Signed-off-by: Luc Ma Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/64583db2.630a0220.eb75d.8f51@mx.google.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/drm_gem_vram_helper.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 375c79e23ca5..eb104de16fa7 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -41,7 +41,7 @@ static const struct drm_gem_object_funcs drm_gem_vram_object_funcs; * the frame's scanout buffer or the cursor image. If there's no more space * left in VRAM, inactive GEM objects can be moved to system memory. * - * To initialize the VRAM helper library call drmm_vram_helper_alloc_mm(). + * To initialize the VRAM helper library call drmm_vram_helper_init(). * The function allocates and initializes an instance of &struct drm_vram_mm * in &struct drm_device.vram_mm . Use &DRM_GEM_VRAM_DRIVER to initialize * &struct drm_driver and &DRM_VRAM_MM_FILE_OPERATIONS to initialize @@ -69,7 +69,7 @@ static const struct drm_gem_object_funcs drm_gem_vram_object_funcs; * // setup device, vram base and size * // ... * - * ret = drmm_vram_helper_alloc_mm(dev, vram_base, vram_size); + * ret = drmm_vram_helper_init(dev, vram_base, vram_size); * if (ret) * return ret; * return 0; @@ -82,7 +82,7 @@ static const struct drm_gem_object_funcs drm_gem_vram_object_funcs; * to userspace. * * You don't have to clean up the instance of VRAM MM. - * drmm_vram_helper_alloc_mm() is a managed interface that installs a + * drmm_vram_helper_init() is a managed interface that installs a * clean-up handler to run during the DRM device's release. * * For drawing or scanout operations, rsp. buffer objects have to be pinned From bd46ade71497faaf8f11e861cf294b155f3b2047 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 3 May 2023 14:28:30 +0200 Subject: [PATCH 3839/4345] ARM: dts: BCM5301X: Drop "clock-names" from the SPI node MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit d3c8e2c5757153bbfad70019ec1decbca86f3def ] There is no such property in the SPI controller binding documentation. Also Linux driver doesn't look for it. This fixes: arch/arm/boot/dts/bcm4708-asus-rt-ac56u.dtb: spi@18029200: Unevaluated properties are not allowed ('clock-names' was unexpected) From schema: Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.yaml Signed-off-by: Rafał Miłecki Link: https://lore.kernel.org/r/20230503122830.3200-1-zajec5@gmail.com Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm5301x.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi index 9fdad20c40d1..4e9bb10f37d0 100644 --- a/arch/arm/boot/dts/bcm5301x.dtsi +++ b/arch/arm/boot/dts/bcm5301x.dtsi @@ -532,7 +532,6 @@ "spi_lr_session_done", "spi_lr_overread"; clocks = <&iprocmed>; - clock-names = "iprocmed"; num-cs = <2>; #address-cells = <1>; #size-cells = <0>; From e629efc6d60214cc3fd7987a6c8fb91a1aafc34d Mon Sep 17 00:00:00 2001 From: "hfdevel@gmx.net" Date: Fri, 7 Apr 2023 16:36:25 +0200 Subject: [PATCH 3840/4345] ARM: dts: meson8b: correct uart_B and uart_C clock references [ Upstream commit d542ce8d4769cdef6a7bc3437e59cfed9c68f0e4 ] With the current device tree for meson8b, uarts B (e.g. available on pins 8/10 on Odroid-C1) and C (pins 3/5 on Odroid-C1) do not work, because they are relying on incorrect clocks. Change the references of pclk to the correct CLKID, to allow use of the two uarts. Fixes: 3375aa77135f ("ARM: dts: meson8b: Fix the UART device-tree schema validation") Signed-off-by: Hans-Frieder Vogt Reviewed-by: Martin Blumenstingl Link: https://lore.kernel.org/r/trinity-bf20bcb9-790b-4ab9-99e3-0831ef8257f4-1680878185420@3c-app-gmx-bap55 Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm/boot/dts/meson8b.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/meson8b.dtsi b/arch/arm/boot/dts/meson8b.dtsi index f6eb7c803174..af2454c9f77a 100644 --- a/arch/arm/boot/dts/meson8b.dtsi +++ b/arch/arm/boot/dts/meson8b.dtsi @@ -599,13 +599,13 @@ &uart_B { compatible = "amlogic,meson8b-uart"; - clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clocks = <&xtal>, <&clkc CLKID_UART1>, <&clkc CLKID_CLK81>; clock-names = "xtal", "pclk", "baud"; }; &uart_C { compatible = "amlogic,meson8b-uart"; - clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clocks = <&xtal>, <&clkc CLKID_UART2>, <&clkc CLKID_CLK81>; clock-names = "xtal", "pclk", "baud"; }; From 39305592dc97b361b0c7f0088c70b30b3babf4a8 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 10 May 2023 17:27:55 -0700 Subject: [PATCH 3841/4345] Input: adxl34x - do not hardcode interrupt trigger type [ Upstream commit e96220bce5176ed2309f77f061dcc0430b82b25e ] Instead of hardcoding IRQ trigger type to IRQF_TRIGGER_HIGH, let's respect the settings specified in the firmware description. Fixes: e27c729219ad ("Input: add driver for ADXL345/346 Digital Accelerometers") Signed-off-by: Marek Vasut Acked-by: Michael Hennerich Link: https://lore.kernel.org/r/20230509203555.549158-1-marex@denx.de Signed-off-by: Dmitry Torokhov Signed-off-by: Sasha Levin --- drivers/input/misc/adxl34x.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/input/misc/adxl34x.c b/drivers/input/misc/adxl34x.c index 4cc4e8ff42b3..ad035c342cd3 100644 --- a/drivers/input/misc/adxl34x.c +++ b/drivers/input/misc/adxl34x.c @@ -811,8 +811,7 @@ struct adxl34x *adxl34x_probe(struct device *dev, int irq, AC_WRITE(ac, POWER_CTL, 0); err = request_threaded_irq(ac->irq, NULL, adxl34x_irq, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT, - dev_name(dev), ac); + IRQF_ONESHOT, dev_name(dev), ac); if (err) { dev_err(dev, "irq %d busy?\n", ac->irq); goto err_free_mem; From 3c87c98225be2d551f01742eca587f6416c13ec8 Mon Sep 17 00:00:00 2001 From: XuDong Liu Date: Sun, 30 Apr 2023 19:23:46 +0800 Subject: [PATCH 3842/4345] drm: sun4i_tcon: use devm_clk_get_enabled in `sun4i_tcon_init_clocks` [ Upstream commit 123ee07ba5b7123e0ce0e0f9d64938026c16a2ce ] Smatch reports: drivers/gpu/drm/sun4i/sun4i_tcon.c:805 sun4i_tcon_init_clocks() warn: 'tcon->clk' from clk_prepare_enable() not released on lines: 792,801. In the function sun4i_tcon_init_clocks(), tcon->clk and tcon->sclk0 are not disabled in the error handling, which affects the release of these variable. Although sun4i_tcon_bind(), which calls sun4i_tcon_init_clocks(), use sun4i_tcon_free_clocks to disable the variables mentioned, but the error handling branch of sun4i_tcon_init_clocks() ignores the required disable process. To fix this issue, use the devm_clk_get_enabled to automatically balance enable and disabled calls. As original implementation use sun4i_tcon_free_clocks() to disable clk explicitly, we delete the related calls and error handling that are no longer needed. Fixes: 9026e0d122ac ("drm: Add Allwinner A10 Display Engine support") Fixes: b14e945bda8a ("drm/sun4i: tcon: Prepare and enable TCON channel 0 clock at init") Fixes: 8e9240472522 ("drm/sun4i: support TCONs without channel 1") Fixes: 34d698f6e349 ("drm/sun4i: Add has_channel_0 TCON quirk") Signed-off-by: XuDong Liu Reviewed-by: Dongliang Mu Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20230430112347.4689-1-m202071377@hust.edu.cn Signed-off-by: Sasha Levin --- drivers/gpu/drm/sun4i/sun4i_tcon.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 9f06dec0fc61..bb43196d5d83 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -777,21 +777,19 @@ static irqreturn_t sun4i_tcon_handler(int irq, void *private) static int sun4i_tcon_init_clocks(struct device *dev, struct sun4i_tcon *tcon) { - tcon->clk = devm_clk_get(dev, "ahb"); + tcon->clk = devm_clk_get_enabled(dev, "ahb"); if (IS_ERR(tcon->clk)) { dev_err(dev, "Couldn't get the TCON bus clock\n"); return PTR_ERR(tcon->clk); } - clk_prepare_enable(tcon->clk); if (tcon->quirks->has_channel_0) { - tcon->sclk0 = devm_clk_get(dev, "tcon-ch0"); + tcon->sclk0 = devm_clk_get_enabled(dev, "tcon-ch0"); if (IS_ERR(tcon->sclk0)) { dev_err(dev, "Couldn't get the TCON channel 0 clock\n"); return PTR_ERR(tcon->sclk0); } } - clk_prepare_enable(tcon->sclk0); if (tcon->quirks->has_channel_1) { tcon->sclk1 = devm_clk_get(dev, "tcon-ch1"); @@ -804,12 +802,6 @@ static int sun4i_tcon_init_clocks(struct device *dev, return 0; } -static void sun4i_tcon_free_clocks(struct sun4i_tcon *tcon) -{ - clk_disable_unprepare(tcon->sclk0); - clk_disable_unprepare(tcon->clk); -} - static int sun4i_tcon_init_irq(struct device *dev, struct sun4i_tcon *tcon) { @@ -1224,14 +1216,14 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master, ret = sun4i_tcon_init_regmap(dev, tcon); if (ret) { dev_err(dev, "Couldn't init our TCON regmap\n"); - goto err_free_clocks; + goto err_assert_reset; } if (tcon->quirks->has_channel_0) { ret = sun4i_dclk_create(dev, tcon); if (ret) { dev_err(dev, "Couldn't create our TCON dot clock\n"); - goto err_free_clocks; + goto err_assert_reset; } } @@ -1294,8 +1286,6 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master, err_free_dotclock: if (tcon->quirks->has_channel_0) sun4i_dclk_free(tcon); -err_free_clocks: - sun4i_tcon_free_clocks(tcon); err_assert_reset: reset_control_assert(tcon->lcd_rst); return ret; @@ -1309,7 +1299,6 @@ static void sun4i_tcon_unbind(struct device *dev, struct device *master, list_del(&tcon->list); if (tcon->quirks->has_channel_0) sun4i_dclk_free(tcon); - sun4i_tcon_free_clocks(tcon); } static const struct component_ops sun4i_tcon_ops = { From 617a4da09d773e59ea74d9039772f6cbc6fec6be Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sun, 7 May 2023 20:26:38 +0300 Subject: [PATCH 3843/4345] drm/panel: sharp-ls043t1le01: adjust mode settings [ Upstream commit dee23b2c9e3ff46d59c5d45e1436eceb878e7c9a ] Using current settings causes panel flickering on APQ8074 dragonboard. Adjust panel settings to follow the vendor-provided mode. This also enables MIPI_DSI_MODE_VIDEO_SYNC_PULSE, which is also specified by the vendor dtsi for the mentioned dragonboard. Fixes: ee0172383190 ("drm/panel: Add Sharp LS043T1LE01 MIPI DSI panel") Signed-off-by: Dmitry Baryshkov Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230507172639.2320934-1-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c index 16dbf0f353ed..1f5fb1547730 100644 --- a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c +++ b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c @@ -192,15 +192,15 @@ static int sharp_nt_panel_enable(struct drm_panel *panel) } static const struct drm_display_mode default_mode = { - .clock = 41118, + .clock = (540 + 48 + 32 + 80) * (960 + 3 + 10 + 15) * 60 / 1000, .hdisplay = 540, .hsync_start = 540 + 48, - .hsync_end = 540 + 48 + 80, - .htotal = 540 + 48 + 80 + 32, + .hsync_end = 540 + 48 + 32, + .htotal = 540 + 48 + 32 + 80, .vdisplay = 960, .vsync_start = 960 + 3, - .vsync_end = 960 + 3 + 15, - .vtotal = 960 + 3 + 15 + 1, + .vsync_end = 960 + 3 + 10, + .vtotal = 960 + 3 + 10 + 15, }; static int sharp_nt_panel_get_modes(struct drm_panel *panel, @@ -280,6 +280,7 @@ static int sharp_nt_panel_probe(struct mipi_dsi_device *dsi) dsi->lanes = 2; dsi->format = MIPI_DSI_FMT_RGB888; dsi->mode_flags = MIPI_DSI_MODE_VIDEO | + MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_VIDEO_HSE | MIPI_DSI_CLOCK_NON_CONTINUOUS | MIPI_DSI_MODE_EOT_PACKET; From 8ee24ddf45f018cda76be99302362d5a6488e2c3 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 5 May 2023 23:37:29 +0200 Subject: [PATCH 3844/4345] ARM: dts: stm32: Move ethernet MAC EEPROM from SoM to carrier boards [ Upstream commit 9660efc2af37f3c12dc6e6a5511ad99e0addc297 ] The ethernet MAC EEPROM is not populated on the SoM itself, it has to be populated on each carrier board. Move the EEPROM into the correct place in DTs, i.e. the carrier board DTs. Add label to the EEPROM too. Fixes: 7e76f82acd9e1 ("ARM: dts: stm32: Split Avenger96 into DHCOR SoM and Avenger96 board") Signed-off-by: Marek Vasut Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi | 6 ++++++ arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi | 6 ------ 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi index 723b39bb2129..c43cf62736a6 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi @@ -232,6 +232,12 @@ }; }; }; + + dh_mac_eeprom: eeprom@53 { + compatible = "atmel,24c02"; + reg = <0x53>; + pagesize = <16>; + }; }; <dc { diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi index 5af32140e128..7dba02e9ba6d 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi @@ -167,12 +167,6 @@ status = "disabled"; }; }; - - eeprom@53 { - compatible = "atmel,24c02"; - reg = <0x53>; - pagesize = <16>; - }; }; &iwdg2 { From 726fdf47c148f0c2daa03483e41b04c3ac3e1de9 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 17 May 2023 10:04:16 +0300 Subject: [PATCH 3845/4345] bus: ti-sysc: Fix dispc quirk masking bool variables [ Upstream commit f620596fa347170852da499e778a5736d79a4b79 ] Fix warning drivers/bus/ti-sysc.c:1806 sysc_quirk_dispc() warn: masking a bool. While at it let's add a comment for what were doing to make the code a bit easier to follow. Fixes: 7324a7a0d5e2 ("bus: ti-sysc: Implement display subsystem reset quirk") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/linux-omap/a8ec8a68-9c2c-4076-bf47-09fccce7659f@kili.mountain/ Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- drivers/bus/ti-sysc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 4ee20be76508..4b1641fe30db 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1748,7 +1748,7 @@ static u32 sysc_quirk_dispc(struct sysc *ddata, int dispc_offset, if (!ddata->module_va) return -EIO; - /* DISP_CONTROL */ + /* DISP_CONTROL, shut down lcd and digit on disable if enabled */ val = sysc_read(ddata, dispc_offset + 0x40); lcd_en = val & lcd_en_mask; digit_en = val & digit_en_mask; @@ -1760,7 +1760,7 @@ static u32 sysc_quirk_dispc(struct sysc *ddata, int dispc_offset, else irq_mask |= BIT(2) | BIT(3); /* EVSYNC bits */ } - if (disable & (lcd_en | digit_en)) + if (disable && (lcd_en || digit_en)) sysc_write(ddata, dispc_offset + 0x40, val & ~(lcd_en_mask | digit_en_mask)); From 2a9895df808872c3f23ef0808e216a2a56c170c3 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Tue, 21 Feb 2023 11:50:37 +0100 Subject: [PATCH 3846/4345] arm64: dts: microchip: sparx5: do not use PSCI on reference boards [ Upstream commit 70be83708c925b3f72c508e4756e48ad2330c830 ] PSCI is not implemented on SparX-5 at all, there is no ATF and U-boot that is shipped does not implement it as well. I have tried flashing the latest BSP 2022.12 U-boot which did not work. After contacting Microchip, they confirmed that there is no ATF for the SoC nor PSCI implementation which is unfortunate in 2023. So, disable PSCI as otherwise kernel crashes as soon as it tries probing PSCI with, and the crash is only visible if earlycon is used. Since PSCI is not implemented, switch core bringup to use spin-tables which are implemented in the vendor U-boot and actually work. Tested on PCB134 with eMMC (VSC5640EV). Fixes: 6694aee00a4b ("arm64: dts: sparx5: Add basic cpu support") Signed-off-by: Robert Marko Acked-by: Steen Hegelund Link: https://lore.kernel.org/r/20230221105039.316819-1-robert.marko@sartura.hr Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/microchip/sparx5.dtsi | 2 +- arch/arm64/boot/dts/microchip/sparx5_pcb_common.dtsi | 12 ++++++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/microchip/sparx5.dtsi b/arch/arm64/boot/dts/microchip/sparx5.dtsi index 3cb01c39c3c8..8dd679fbeed1 100644 --- a/arch/arm64/boot/dts/microchip/sparx5.dtsi +++ b/arch/arm64/boot/dts/microchip/sparx5.dtsi @@ -61,7 +61,7 @@ interrupt-affinity = <&cpu0>, <&cpu1>; }; - psci { + psci: psci { compatible = "arm,psci-0.2"; method = "smc"; }; diff --git a/arch/arm64/boot/dts/microchip/sparx5_pcb_common.dtsi b/arch/arm64/boot/dts/microchip/sparx5_pcb_common.dtsi index 9d1a082de3e2..32bb76b3202a 100644 --- a/arch/arm64/boot/dts/microchip/sparx5_pcb_common.dtsi +++ b/arch/arm64/boot/dts/microchip/sparx5_pcb_common.dtsi @@ -6,6 +6,18 @@ /dts-v1/; #include "sparx5.dtsi" +&psci { + status = "disabled"; +}; + +&cpu0 { + enable-method = "spin-table"; +}; + +&cpu1 { + enable-method = "spin-table"; +}; + &uart0 { status = "okay"; }; From 7080ef46ad3da5ff592bec173829e5f8cefca955 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Thu, 18 May 2023 23:48:11 -0700 Subject: [PATCH 3847/4345] RDMA/bnxt_re: Disable/kill tasklet only if it is enabled [ Upstream commit ab112ee7899d6171da5acd77a7ed7ae103f488de ] When the ulp hook to start the IRQ fails because the rings are not available, tasklets are not enabled. In this case when the driver is unloaded, driver calls CREQ tasklet_kill. This causes an indefinite hang as the tasklet is not enabled. Driver shouldn't call tasklet_kill if it is not enabled. So using the creq->requested and nq->requested flags to identify if both tasklets/irqs are registered. Checking this flag while scheduling the tasklet from ISR. Also, added a cleanup for disabling tasklet, in case request_irq fails during start_irq. Check for return value for bnxt_qplib_rcfw_start_irq and in case the bnxt_qplib_rcfw_start_irq fails, return bnxt_re_start_irq without attempting to start NQ IRQs. Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Link: https://lore.kernel.org/r/1684478897-12247-2-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/main.c | 12 +++++++++--- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 16 ++++++++++------ drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 14 +++++++++----- 3 files changed, 28 insertions(+), 14 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 9ef6aea29ff1..bdde44286d56 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -294,15 +294,21 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent) for (indx = 0; indx < rdev->num_msix; indx++) rdev->msix_entries[indx].vector = ent[indx].vector; - bnxt_qplib_rcfw_start_irq(rcfw, msix_ent[BNXT_RE_AEQ_IDX].vector, - false); + rc = bnxt_qplib_rcfw_start_irq(rcfw, msix_ent[BNXT_RE_AEQ_IDX].vector, + false); + if (rc) { + ibdev_warn(&rdev->ibdev, "Failed to reinit CREQ\n"); + return; + } for (indx = BNXT_RE_NQ_IDX ; indx < rdev->num_msix; indx++) { nq = &rdev->nq[indx - 1]; rc = bnxt_qplib_nq_start_irq(nq, indx - 1, msix_ent[indx].vector, false); - if (rc) + if (rc) { ibdev_warn(&rdev->ibdev, "Failed to reinit NQ index %d\n", indx - 1); + return; + } } } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index b26a89187a19..9eba4b39c703 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -404,6 +404,9 @@ static irqreturn_t bnxt_qplib_nq_irq(int irq, void *dev_instance) void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill) { + if (!nq->requested) + return; + tasklet_disable(&nq->nq_tasklet); /* Mask h/w interrupt */ bnxt_qplib_ring_nq_db(&nq->nq_db.dbinfo, nq->res->cctx, false); @@ -411,11 +414,10 @@ void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill) synchronize_irq(nq->msix_vec); if (kill) tasklet_kill(&nq->nq_tasklet); - if (nq->requested) { - irq_set_affinity_hint(nq->msix_vec, NULL); - free_irq(nq->msix_vec, nq); - nq->requested = false; - } + + irq_set_affinity_hint(nq->msix_vec, NULL); + free_irq(nq->msix_vec, nq); + nq->requested = false; } void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq) @@ -454,8 +456,10 @@ int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx, snprintf(nq->name, sizeof(nq->name), "bnxt_qplib_nq-%d", nq_indx); rc = request_irq(nq->msix_vec, bnxt_qplib_nq_irq, 0, nq->name, nq); - if (rc) + if (rc) { + tasklet_disable(&nq->nq_tasklet); return rc; + } cpumask_clear(&nq->mask); cpumask_set_cpu(nq_indx, &nq->mask); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 5759027914b0..a111e880276f 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -633,6 +633,10 @@ void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill) struct bnxt_qplib_creq_ctx *creq; creq = &rcfw->creq; + + if (!creq->requested) + return; + tasklet_disable(&creq->creq_tasklet); /* Mask h/w interrupts */ bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo, rcfw->res->cctx, false); @@ -641,10 +645,8 @@ void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill) if (kill) tasklet_kill(&creq->creq_tasklet); - if (creq->requested) { - free_irq(creq->msix_vec, rcfw); - creq->requested = false; - } + free_irq(creq->msix_vec, rcfw); + creq->requested = false; } void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw) @@ -690,8 +692,10 @@ int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector, tasklet_enable(&creq->creq_tasklet); rc = request_irq(creq->msix_vec, bnxt_qplib_creq_irq, 0, "bnxt_qplib_creq", rcfw); - if (rc) + if (rc) { + tasklet_disable(&creq->creq_tasklet); return rc; + } creq->requested = true; bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo, rcfw->res->cctx, true); From 11bd3882c3a6021bf73815343ee811558452091e Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Thu, 18 May 2023 23:48:12 -0700 Subject: [PATCH 3848/4345] RDMA/bnxt_re: Fix to remove unnecessary return labels [ Upstream commit 9b3ee47796f529e5bc31a355d6cb756d68a7079a ] If there is no cleanup needed then just return directly. This cleans up the code and improve readability. Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Link: https://lore.kernel.org/r/1684478897-12247-3-git-send-email-selvin.xavier@broadcom.com Reviewed-by: Kashyap Desai Reviewed-by: Saravanan Vajravel Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 9eba4b39c703..b4b180652c0a 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -1603,7 +1603,7 @@ static int bnxt_qplib_put_inline(struct bnxt_qplib_qp *qp, il_src = (void *)wqe->sg_list[indx].addr; t_len += len; if (t_len > qp->max_inline_data) - goto bad; + return -ENOMEM; while (len) { if (pull_dst) { pull_dst = false; @@ -1627,8 +1627,6 @@ static int bnxt_qplib_put_inline(struct bnxt_qplib_qp *qp, } return t_len; -bad: - return -ENOMEM; } static u32 bnxt_qplib_put_sges(struct bnxt_qplib_hwq *hwq, @@ -2058,7 +2056,7 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) hwq_attr.sginfo = &cq->sg_info; rc = bnxt_qplib_alloc_init_hwq(&cq->hwq, &hwq_attr); if (rc) - goto exit; + return rc; RCFW_CMD_PREP(req, CREATE_CQ, cmd_flags); @@ -2099,7 +2097,6 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) fail: bnxt_qplib_free_hwq(res, &cq->hwq); -exit: return rc; } From b54b26ac50a2c9580bf0e3158ef609f038e324c1 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Thu, 18 May 2023 23:48:13 -0700 Subject: [PATCH 3849/4345] RDMA/bnxt_re: Use unique names while registering interrupts [ Upstream commit ff2e4bfd162cf66a112a81509e419805add44d64 ] bnxt_re currently uses the names "bnxt_qplib_creq" and "bnxt_qplib_nq-0" while registering IRQs. There is no way to distinguish the IRQs of different device ports when there are multiple IB devices registered. This could make the scenarios worse where one want to pin IRQs of a device port to certain CPUs. Fixed the code to use unique names which has PCI BDF information while registering interrupts like: "bnxt_re-nq-0@pci:0000:65:00.0" and "bnxt_re-creq@pci:0000:65:00.1". Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Link: https://lore.kernel.org/r/1684478897-12247-4-git-send-email-selvin.xavier@broadcom.com Reviewed-by: Bhargava Chenna Marreddy Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 12 ++++++++++-- drivers/infiniband/hw/bnxt_re/qplib_fp.h | 2 +- drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 15 +++++++++++++-- drivers/infiniband/hw/bnxt_re/qplib_rcfw.h | 1 + 4 files changed, 25 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index b4b180652c0a..d6b7c0d1f676 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -417,6 +417,8 @@ void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill) irq_set_affinity_hint(nq->msix_vec, NULL); free_irq(nq->msix_vec, nq); + kfree(nq->name); + nq->name = NULL; nq->requested = false; } @@ -443,6 +445,7 @@ void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq) int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx, int msix_vector, bool need_init) { + struct bnxt_qplib_res *res = nq->res; int rc; if (nq->requested) @@ -454,9 +457,14 @@ int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx, else tasklet_enable(&nq->nq_tasklet); - snprintf(nq->name, sizeof(nq->name), "bnxt_qplib_nq-%d", nq_indx); + nq->name = kasprintf(GFP_KERNEL, "bnxt_re-nq-%d@pci:%s", + nq_indx, pci_name(res->pdev)); + if (!nq->name) + return -ENOMEM; rc = request_irq(nq->msix_vec, bnxt_qplib_nq_irq, 0, nq->name, nq); if (rc) { + kfree(nq->name); + nq->name = NULL; tasklet_disable(&nq->nq_tasklet); return rc; } @@ -470,7 +478,7 @@ int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx, nq->msix_vec, nq_indx); } nq->requested = true; - bnxt_qplib_ring_nq_db(&nq->nq_db.dbinfo, nq->res->cctx, true); + bnxt_qplib_ring_nq_db(&nq->nq_db.dbinfo, res->cctx, true); return rc; } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index f50784405e27..667f93d90045 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -469,7 +469,7 @@ typedef int (*srqn_handler_t)(struct bnxt_qplib_nq *nq, struct bnxt_qplib_nq { struct pci_dev *pdev; struct bnxt_qplib_res *res; - char name[32]; + char *name; struct bnxt_qplib_hwq hwq; struct bnxt_qplib_nq_db nq_db; u16 ring_id; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index a111e880276f..4836bc433f53 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -646,6 +646,8 @@ void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill) tasklet_kill(&creq->creq_tasklet); free_irq(creq->msix_vec, rcfw); + kfree(creq->irq_name); + creq->irq_name = NULL; creq->requested = false; } @@ -678,9 +680,11 @@ int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector, bool need_init) { struct bnxt_qplib_creq_ctx *creq; + struct bnxt_qplib_res *res; int rc; creq = &rcfw->creq; + res = rcfw->res; if (creq->requested) return -EFAULT; @@ -690,15 +694,22 @@ int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector, tasklet_setup(&creq->creq_tasklet, bnxt_qplib_service_creq); else tasklet_enable(&creq->creq_tasklet); + + creq->irq_name = kasprintf(GFP_KERNEL, "bnxt_re-creq@pci:%s", + pci_name(res->pdev)); + if (!creq->irq_name) + return -ENOMEM; rc = request_irq(creq->msix_vec, bnxt_qplib_creq_irq, 0, - "bnxt_qplib_creq", rcfw); + creq->irq_name, rcfw); if (rc) { + kfree(creq->irq_name); + creq->irq_name = NULL; tasklet_disable(&creq->creq_tasklet); return rc; } creq->requested = true; - bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo, rcfw->res->cctx, true); + bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo, res->cctx, true); return 0; } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 6953f4e53dd2..7df7170c80e0 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -172,6 +172,7 @@ struct bnxt_qplib_creq_ctx { u16 ring_id; int msix_vec; bool requested; /*irq handler installed */ + char *irq_name; }; /* RCFW Communication Channels */ From 446092f136d319a8fdb734270b797f969b683944 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Thu, 18 May 2023 23:48:14 -0700 Subject: [PATCH 3850/4345] RDMA/bnxt_re: Remove a redundant check inside bnxt_re_update_gid [ Upstream commit b989f90cef0af48aa5679b6a75476371705ec53c ] The NULL check inside bnxt_re_update_gid() always return false. If sgid_tbl->tbl is not allocated, then dev_init would have failed. Fixes: 5fac5b1b297f ("RDMA/bnxt_re: Add vlan tag for untagged RoCE traffic when PFC is configured") Link: https://lore.kernel.org/r/1684478897-12247-5-git-send-email-selvin.xavier@broadcom.com Reviewed-by: Saravanan Vajravel Reviewed-by: Damodharam Ammepalli Reviewed-by: Ajit Khaparde Signed-off-by: Selvin Xavier Signed-off-by: Kalesh AP Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/main.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index bdde44286d56..8a618769915d 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1191,12 +1191,6 @@ static int bnxt_re_update_gid(struct bnxt_re_dev *rdev) if (!ib_device_try_get(&rdev->ibdev)) return 0; - if (!sgid_tbl) { - ibdev_err(&rdev->ibdev, "QPLIB: SGID table not allocated"); - rc = -EINVAL; - goto out; - } - for (index = 0; index < sgid_tbl->active; index++) { gid_idx = sgid_tbl->hw_id[index]; @@ -1214,7 +1208,7 @@ static int bnxt_re_update_gid(struct bnxt_re_dev *rdev) rc = bnxt_qplib_update_sgid(sgid_tbl, &gid, gid_idx, rdev->qplib_res.netdev->dev_addr); } -out: + ib_device_put(&rdev->ibdev); return rc; } From b0b180a712ee8b643f2d592608d2af45fd151e47 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Thu, 18 May 2023 23:48:15 -0700 Subject: [PATCH 3851/4345] RDMA/bnxt_re: Fix to remove an unnecessary log [ Upstream commit 43774bc156614346fe5dacabc8e8c229167f2536 ] During destroy_qp, driver sets the qp handle in the existing CQEs belonging to the QP being destroyed to NULL. As a result, a poll_cq after destroy_qp can report unnecessary messages. Remove this noise from system logs. Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Link: https://lore.kernel.org/r/1684478897-12247-6-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index d6b7c0d1f676..d44b6a5c90b5 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -2732,11 +2732,8 @@ static int bnxt_qplib_cq_process_terminal(struct bnxt_qplib_cq *cq, qp = (struct bnxt_qplib_qp *)((unsigned long) le64_to_cpu(hwcqe->qp_handle)); - if (!qp) { - dev_err(&cq->hwq.pdev->dev, - "FP: CQ Process terminal qp is NULL\n"); + if (!qp) return -EINVAL; - } /* Must block new posting of SQ and RQ */ qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; From e8b131d216380fc0105649c0ef733067e379fe6a Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 17 May 2023 13:32:25 +0300 Subject: [PATCH 3852/4345] ARM: dts: gta04: Move model property out of pinctrl node [ Upstream commit 4ffec92e70ac5097b9f67ec154065305b16a3b46 ] The model property should be at the top level, let's move it out of the pinctrl node. Fixes: d2eaf949d2c3 ("ARM: dts: omap3-gta04a5one: define GTA04A5 variant with OneNAND") Cc: Andreas Kemnade Cc: H. Nikolaus Schaller Signed-off-by: Tony Lindgren Signed-off-by: Sasha Levin --- arch/arm/boot/dts/omap3-gta04a5one.dts | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/omap3-gta04a5one.dts b/arch/arm/boot/dts/omap3-gta04a5one.dts index 9db9fe67cd63..95df45cc70c0 100644 --- a/arch/arm/boot/dts/omap3-gta04a5one.dts +++ b/arch/arm/boot/dts/omap3-gta04a5one.dts @@ -5,9 +5,11 @@ #include "omap3-gta04a5.dts" -&omap3_pmx_core { +/ { model = "Goldelico GTA04A5/Letux 2804 with OneNAND"; +}; +&omap3_pmx_core { gpmc_pins: pinmux_gpmc_pins { pinctrl-single,pins = < From 160ac75a5a82ee8af929b9db7246b0e92d10df7a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 19 Apr 2023 23:18:40 +0200 Subject: [PATCH 3853/4345] arm64: dts: qcom: msm8916: correct camss unit address [ Upstream commit 48798d992ce276cf0d57bf75318daf8eabd02aa4 ] Match unit-address to reg entry to fix dtbs W=1 warnings: Warning (simple_bus_reg): /soc@0/camss@1b00000: simple-bus unit address format error, expected "1b0ac00" Fixes: 58f479f90a7c ("arm64: dts: qcom: msm8916: Add CAMSS support") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230419211856.79332-2-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8916.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index c32e4a3833f2..5b79e4a37331 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -1006,7 +1006,7 @@ }; }; - camss: camss@1b00000 { + camss: camss@1b0ac00 { compatible = "qcom,msm8916-camss"; reg = <0x01b0ac00 0x200>, <0x01b00030 0x4>, From 6d103b1cc13367d6b5369b6956ae6cc4c16bff9e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 19 Apr 2023 23:18:46 +0200 Subject: [PATCH 3854/4345] arm64: dts: qcom: msm8994: correct SPMI unit address [ Upstream commit 24f0f6a8059c7108d4ee3476c95db1e7ff4feb79 ] Match unit-address to reg entry to fix dtbs W=1 warnings: Warning (simple_bus_reg): /soc/spmi@fc4c0000: simple-bus unit address format error, expected "fc4cf000" Fixes: b0ad598f8ec0 ("arm64: dts: qcom: msm8994: Add SPMI PMIC arbiter device") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230419211856.79332-8-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8994.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8994.dtsi b/arch/arm64/boot/dts/qcom/msm8994.dtsi index aeb5762566e9..caaf7102f579 100644 --- a/arch/arm64/boot/dts/qcom/msm8994.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8994.dtsi @@ -489,7 +489,7 @@ reg = <0xfc4ab000 0x4>; }; - spmi_bus: spmi@fc4c0000 { + spmi_bus: spmi@fc4cf000 { compatible = "qcom,spmi-pmic-arb"; reg = <0xfc4cf000 0x1000>, <0xfc4cb000 0x1000>, From 02d8b008ffeefae0bac88e14ae2479bc017fb3d2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 19 Apr 2023 23:18:47 +0200 Subject: [PATCH 3855/4345] arm64: dts: qcom: msm8996: correct camss unit address [ Upstream commit e959ced1d0e5ef0b1f66a0c2d0e1ae80790e5ca5 ] Match unit-address to reg entry to fix dtbs W=1 warnings: Warning (simple_bus_reg): /soc/camss@a00000: simple-bus unit address format error, expected "a34000" Fixes: e0531312e78f ("arm64: dts: qcom: msm8996: Add CAMSS support") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230419211856.79332-9-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/msm8996.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 159cdd03e7c0..73f7490911c9 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -956,7 +956,7 @@ }; }; - camss: camss@a00000 { + camss: camss@a34000 { compatible = "qcom,msm8996-camss"; reg = <0x00a34000 0x1000>, <0x00a00030 0x4>, From b574cd7e4dfc1de10aea8fe4bc28daed31883652 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Tue, 16 May 2023 10:50:39 +0200 Subject: [PATCH 3856/4345] drm/panel: simple: fix active size for Ampire AM-480272H3TMQW-T01H [ Upstream commit f24b49550814fdee4a98b9552e35e243ccafd4a8 ] The previous setting was related to the overall dimension and not to the active display area. In the "PHYSICAL SPECIFICATIONS" section, the datasheet shows the following parameters: ---------------------------------------------------------- | Item | Specifications | unit | ---------------------------------------------------------- | Display area | 98.7 (W) x 57.5 (H) | mm | ---------------------------------------------------------- | Overall dimension | 105.5(W) x 67.2(H) x 4.96(D) | mm | ---------------------------------------------------------- Fixes: 966fea78adf2 ("drm/panel: simple: Add support for Ampire AM-480272H3TMQW-T01H") Signed-off-by: Dario Binacchi Reviewed-by: Neil Armstrong [narmstrong: fixed Fixes commit id length] Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230516085039.3797303-1-dario.binacchi@amarulasolutions.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-simple.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 1a87cc445b5e..b0b92f436879 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -704,8 +704,8 @@ static const struct panel_desc ampire_am_480272h3tmqw_t01h = { .num_modes = 1, .bpc = 8, .size = { - .width = 105, - .height = 67, + .width = 99, + .height = 58, }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, }; From aec18da74194f35e62e258b58ea456e9a3b0a23a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 17:30:58 +0200 Subject: [PATCH 3857/4345] ARM: ep93xx: fix missing-prototype warnings [ Upstream commit 419013740ea1e4343d8ade535d999f59fa28e460 ] ep93xx_clocksource_read() is only called from the file it is declared in, while ep93xx_timer_init() is declared in a header that is not included here. arch/arm/mach-ep93xx/timer-ep93xx.c:120:13: error: no previous prototype for 'ep93xx_timer_init' arch/arm/mach-ep93xx/timer-ep93xx.c:63:5: error: no previous prototype for 'ep93xx_clocksource_read' Fixes: 000bc17817bf ("ARM: ep93xx: switch to GENERIC_CLOCKEVENTS") Acked-by: Alexander Sverdlin Link: https://lore.kernel.org/r/20230516153109.514251-3-arnd@kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- arch/arm/mach-ep93xx/timer-ep93xx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-ep93xx/timer-ep93xx.c b/arch/arm/mach-ep93xx/timer-ep93xx.c index dd4b164d1831..a9efa7bc2fa1 100644 --- a/arch/arm/mach-ep93xx/timer-ep93xx.c +++ b/arch/arm/mach-ep93xx/timer-ep93xx.c @@ -9,6 +9,7 @@ #include #include #include "soc.h" +#include "platform.h" /************************************************************************* * Timer handling for EP93xx @@ -60,7 +61,7 @@ static u64 notrace ep93xx_read_sched_clock(void) return ret; } -u64 ep93xx_clocksource_read(struct clocksource *c) +static u64 ep93xx_clocksource_read(struct clocksource *c) { u64 ret; From c85a076215a9f80b8456ed6d217fd19dfc7fafcb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 17:31:04 +0200 Subject: [PATCH 3858/4345] ARM: omap2: fix missing tick_broadcast() prototype [ Upstream commit 861bc1d2886d47bd57a2cbf2cda87fdbe3eb9d08 ] omap2 contains a hack to define tick_broadcast() on non-SMP configurations in place of the normal SMP definition. This one causes a warning because of a missing prototype: arch/arm/mach-omap2/board-generic.c:44:6: error: no previous prototype for 'tick_broadcast' Make sure to always include the header with the declaration. Fixes: d86ad463d670 ("ARM: OMAP2+: Fix regression for using local timer on non-SMP SoCs") Acked-by: Aaro Koskinen Link: https://lore.kernel.org/r/20230516153109.514251-9-arnd@kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: Sasha Levin --- arch/arm/mach-omap2/board-generic.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c index 1610c567a6a3..10d2f078e4a8 100644 --- a/arch/arm/mach-omap2/board-generic.c +++ b/arch/arm/mach-omap2/board-generic.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include From 392ee3cc995dd297ce575e08d16b46a1f6fcdde6 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 7 May 2023 19:45:16 +0200 Subject: [PATCH 3859/4345] arm64: dts: qcom: apq8096: fix fixed regulator name property [ Upstream commit c77612a07d18d4425fd8ddd532a8a9b8e1970c53 ] Correct the typo in 'regulator-name' property. apq8096-ifc6640.dtb: v1p05-regulator: 'regulator-name' is a required property apq8096-ifc6640.dtb: v1p05-regulator: Unevaluated properties are not allowed ('reglator-name' was unexpected) Fixes: 6cbdec2d3ca6 ("arm64: dts: qcom: msm8996: Introduce IFC6640") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230507174516.264936-3-krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/qcom/apq8096-ifc6640.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/apq8096-ifc6640.dts b/arch/arm64/boot/dts/qcom/apq8096-ifc6640.dts index f6ddf17ada81..861b356a982b 100644 --- a/arch/arm64/boot/dts/qcom/apq8096-ifc6640.dts +++ b/arch/arm64/boot/dts/qcom/apq8096-ifc6640.dts @@ -26,7 +26,7 @@ v1p05: v1p05-regulator { compatible = "regulator-fixed"; - reglator-name = "v1p05"; + regulator-name = "v1p05"; regulator-always-on; regulator-boot-on; @@ -38,7 +38,7 @@ v12_poe: v12-poe-regulator { compatible = "regulator-fixed"; - reglator-name = "v12_poe"; + regulator-name = "v12_poe"; regulator-always-on; regulator-boot-on; From ddc74d6ea3dcf7fd6e6d1f46dd0351678898b1a7 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 18 May 2023 02:42:32 +0200 Subject: [PATCH 3860/4345] ARM: dts: stm32: Shorten the AV96 HDMI sound card name [ Upstream commit 0cf765e598712addec34d0208cc1418c151fefb2 ] Fix the following error in kernel log due to too long sound card name: " asoc-audio-graph-card sound: ASoC: driver name too long 'STM32MP1-AV96-HDMI' -> 'STM32MP1-AV96-H' " Fixes: e027da342772 ("ARM: dts: stm32: Add bindings for audio on AV96") Signed-off-by: Marek Vasut Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi index c43cf62736a6..d8547307a950 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi @@ -88,7 +88,7 @@ sound { compatible = "audio-graph-card"; - label = "STM32MP1-AV96-HDMI"; + label = "STM32-AV96-HDMI"; dais = <&sai2a_port>; status = "okay"; }; From 105af71974eacb1e7abe3bd64c0864693db5374e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 13 May 2023 13:29:31 +0200 Subject: [PATCH 3861/4345] memory: brcmstb_dpfe: fix testing array offset after use [ Upstream commit 1d9e93fad549bc38f593147479ee063f2872c170 ] Code should first check for valid value of array offset, then use it as the index. Fixes smatch warning: drivers/memory/brcmstb_dpfe.c:443 __send_command() error: testing array offset 'cmd' after use. Fixes: 2f330caff577 ("memory: brcmstb: Add driver for DPFE") Acked-by: Markus Mayer Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20230513112931.176066-1-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- drivers/memory/brcmstb_dpfe.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/memory/brcmstb_dpfe.c b/drivers/memory/brcmstb_dpfe.c index f43ba69fbb3e..2daae2e0cb19 100644 --- a/drivers/memory/brcmstb_dpfe.c +++ b/drivers/memory/brcmstb_dpfe.c @@ -434,15 +434,17 @@ static void __finalize_command(struct brcmstb_dpfe_priv *priv) static int __send_command(struct brcmstb_dpfe_priv *priv, unsigned int cmd, u32 result[]) { - const u32 *msg = priv->dpfe_api->command[cmd]; void __iomem *regs = priv->regs; unsigned int i, chksum, chksum_idx; + const u32 *msg; int ret = 0; u32 resp; if (cmd >= DPFE_CMD_MAX) return -1; + msg = priv->dpfe_api->command[cmd]; + mutex_lock(&priv->lock); /* Wait for DCPU to become ready */ From d883e16c7f35478ad0950f4cb4f6bba011345b6c Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 30 May 2023 21:11:38 +0300 Subject: [PATCH 3862/4345] ASoC: es8316: Increment max value for ALC Capture Target Volume control [ Upstream commit 6f073429037cd79d7311cd8236311c53f5ea8f01 ] The following error occurs when trying to restore a previously saved ALSA mixer state (tested on a Rock 5B board): $ alsactl --no-ucm -f /tmp/asound.state store hw:Analog $ alsactl --no-ucm -I -f /tmp/asound.state restore hw:Analog alsactl: set_control:1475: Cannot write control '2:0:0:ALC Capture Target Volume:0' : Invalid argument According to ES8316 datasheet, the register at address 0x2B, which is related to the above mixer control, contains by default the value 0xB0. Considering the corresponding ALC target bits (ALCLVL) are 7:4, the control is initialized with 11, which is one step above the maximum value allowed by the driver: ALCLVL | dB gain -------+-------- 0000 | -16.5 0001 | -15.0 0010 | -13.5 .... | ..... 0111 | -6.0 1000 | -4.5 1001 | -3.0 1010 | -1.5 .... | ..... 1111 | -1.5 The tests performed using the VU meter feature (--vumeter=TYPE) of arecord/aplay confirm the specs are correct and there is no measured gain if the 1011-1111 range would have been mapped to 0 dB: dB gain | VU meter % --------+----------- -6.0 | 30-31 -4.5 | 35-36 -3.0 | 42-43 -1.5 | 50-51 0.0 | 50-51 Increment the max value allowed for ALC Capture Target Volume control, so that it matches the hardware default. Additionally, update the related TLV to prevent an artificial extension of the dB gain range. Fixes: b8b88b70875a ("ASoC: add es8316 codec driver") Signed-off-by: Cristian Ciocaltea Link: https://lore.kernel.org/r/20230530181140.483936-2-cristian.ciocaltea@collabora.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/es8316.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c index bc3d46617a11..423d9ce2df26 100644 --- a/sound/soc/codecs/es8316.c +++ b/sound/soc/codecs/es8316.c @@ -52,7 +52,12 @@ static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(dac_vol_tlv, -9600, 50, 1); static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(adc_vol_tlv, -9600, 50, 1); static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(alc_max_gain_tlv, -650, 150, 0); static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(alc_min_gain_tlv, -1200, 150, 0); -static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(alc_target_tlv, -1650, 150, 0); + +static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(alc_target_tlv, + 0, 10, TLV_DB_SCALE_ITEM(-1650, 150, 0), + 11, 11, TLV_DB_SCALE_ITEM(-150, 0, 0), +); + static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(hpmixer_gain_tlv, 0, 4, TLV_DB_SCALE_ITEM(-1200, 150, 0), 8, 11, TLV_DB_SCALE_ITEM(-450, 150, 0), @@ -115,7 +120,7 @@ static const struct snd_kcontrol_new es8316_snd_controls[] = { alc_max_gain_tlv), SOC_SINGLE_TLV("ALC Capture Min Volume", ES8316_ADC_ALC2, 0, 28, 0, alc_min_gain_tlv), - SOC_SINGLE_TLV("ALC Capture Target Volume", ES8316_ADC_ALC3, 4, 10, 0, + SOC_SINGLE_TLV("ALC Capture Target Volume", ES8316_ADC_ALC3, 4, 11, 0, alc_target_tlv), SOC_SINGLE("ALC Capture Hold Time", ES8316_ADC_ALC3, 0, 10, 0), SOC_SINGLE("ALC Capture Decay Time", ES8316_ADC_ALC4, 4, 10, 0), From 684a2f180e4632b40e8b8e4cf91879f274ab448b Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 30 May 2023 21:11:39 +0300 Subject: [PATCH 3863/4345] ASoC: es8316: Do not set rate constraints for unsupported MCLKs [ Upstream commit 60413129ee2b38a80347489270af7f6e1c1de4d0 ] When using the codec through the generic audio graph card, there are at least two calls of es8316_set_dai_sysclk(), with the effect of limiting the allowed sample rates according to the MCLK/LRCK ratios supported by the codec: 1. During audio card setup, to set the initial MCLK - see asoc_simple_init_dai(). 2. Before opening a stream, to update MCLK, according to the stream sample rate and the multiplication factor - see asoc_simple_hw_params(). In some cases the initial MCLK might be set to a frequency that doesn't match any of the supported ratios, e.g. 12287999 instead of 12288000, which is only 1 Hz below the supported clock, as that is what the hardware reports. This creates an empty list of rate constraints, which is further passed to snd_pcm_hw_constraint_list() via es8316_pcm_startup(), and causes the following error on the very first access of the sound card: $ speaker-test -D hw:Analog,0 -F S16_LE -c 2 -t wav Broken configuration for playback: no configurations available: Invalid argument Setting of hwparams failed: Invalid argument Note that all subsequent retries succeed thanks to the updated MCLK set at point 2 above, which uses a computed frequency value instead of a reading from the hardware registers. Normally this would have mitigated the issue, but es8316_pcm_startup() executes before the 2nd call to es8316_set_dai_sysclk(), hence it cannot make use of the updated constraints. Since es8316_pcm_hw_params() performs anyway a final validation of MCLK against the stream sample rate and the supported MCLK/LRCK ratios, fix the issue by ensuring that sysclk_constraints list is only set when at least one supported sample rate is autodetected by the codec. Fixes: b8b88b70875a ("ASoC: add es8316 codec driver") Signed-off-by: Cristian Ciocaltea Link: https://lore.kernel.org/r/20230530181140.483936-3-cristian.ciocaltea@collabora.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/codecs/es8316.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c index 423d9ce2df26..03ad34a275da 100644 --- a/sound/soc/codecs/es8316.c +++ b/sound/soc/codecs/es8316.c @@ -369,13 +369,11 @@ static int es8316_set_dai_sysclk(struct snd_soc_dai *codec_dai, int count = 0; es8316->sysclk = freq; + es8316->sysclk_constraints.list = NULL; + es8316->sysclk_constraints.count = 0; - if (freq == 0) { - es8316->sysclk_constraints.list = NULL; - es8316->sysclk_constraints.count = 0; - + if (freq == 0) return 0; - } ret = clk_set_rate(es8316->mclk, freq); if (ret) @@ -391,8 +389,10 @@ static int es8316_set_dai_sysclk(struct snd_soc_dai *codec_dai, es8316->allowed_rates[count++] = freq / ratio; } - es8316->sysclk_constraints.list = es8316->allowed_rates; - es8316->sysclk_constraints.count = count; + if (count) { + es8316->sysclk_constraints.list = es8316->allowed_rates; + es8316->sysclk_constraints.count = count; + } return 0; } From 9c14d1406662c3d203d4d007b7abdafed4252d59 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Tue, 16 May 2023 22:30:29 +0200 Subject: [PATCH 3864/4345] ARM: dts: meson8: correct uart_B and uart_C clock references [ Upstream commit 98b503c7fb13a17a47d8ebf15fa8f7c10118e75c ] On Meson8 uart_B and uart_C do not work, because they are relying on incorrect clocks. Change the references of pclk to the correct CLKID (UART1 for uart_B and UART2 for uart_C), to allow use of the two uarts. This was originally reported by Hans-Frieder Vogt for Meson8b [0], but the same bug is also present in meson8.dtsi [0] https://lore.kernel.org/linux-amlogic/trinity-bf20bcb9-790b-4ab9-99e3-0831ef8257f4-1680878185420@3c-app-gmx-bap55/ Fixes: 57007bfb5469 ("ARM: dts: meson8: Fix the UART device-tree schema validation") Reported-by: Hans-Frieder Vogt # for meson8b.dtsi Signed-off-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20230516203029.1031174-1-martin.blumenstingl@googlemail.com Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- arch/arm/boot/dts/meson8.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi index 08533116a39c..0d045add8165 100644 --- a/arch/arm/boot/dts/meson8.dtsi +++ b/arch/arm/boot/dts/meson8.dtsi @@ -611,13 +611,13 @@ &uart_B { compatible = "amlogic,meson8-uart"; - clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clocks = <&xtal>, <&clkc CLKID_UART1>, <&clkc CLKID_CLK81>; clock-names = "xtal", "pclk", "baud"; }; &uart_C { compatible = "amlogic,meson8-uart"; - clocks = <&xtal>, <&clkc CLKID_UART0>, <&clkc CLKID_CLK81>; + clocks = <&xtal>, <&clkc CLKID_UART2>, <&clkc CLKID_CLK81>; clock-names = "xtal", "pclk", "baud"; }; From 42b6865bf58c53a9e0e845d75a517f3d613b8ebc Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 21 May 2023 15:52:16 -0700 Subject: [PATCH 3865/4345] soc/fsl/qe: fix usb.c build errors [ Upstream commit 7b1a78babd0d2cd27aa07255dee0c2d7ac0f31e3 ] Fix build errors in soc/fsl/qe/usb.c when QUICC_ENGINE is not set. This happens when PPC_EP88XC is set, which selects CPM1 & CPM. When CPM is set, USB_FSL_QE can be set without QUICC_ENGINE being set. When USB_FSL_QE is set, QE_USB deafults to y, which causes build errors when QUICC_ENGINE is not set. Making QE_USB depend on QUICC_ENGINE prevents QE_USB from defaulting to y. Fixes these build errors: drivers/soc/fsl/qe/usb.o: in function `qe_usb_clock_set': usb.c:(.text+0x1e): undefined reference to `qe_immr' powerpc-linux-ld: usb.c:(.text+0x2a): undefined reference to `qe_immr' powerpc-linux-ld: usb.c:(.text+0xbc): undefined reference to `qe_setbrg' powerpc-linux-ld: usb.c:(.text+0xca): undefined reference to `cmxgcr_lock' powerpc-linux-ld: usb.c:(.text+0xce): undefined reference to `cmxgcr_lock' Fixes: 5e41486c408e ("powerpc/QE: add support for QE USB clocks routing") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Link: https://lore.kernel.org/all/202301101500.pillNv6R-lkp@intel.com/ Suggested-by: Michael Ellerman Cc: Christophe Leroy Cc: Leo Li Cc: Masahiro Yamada Cc: Nicolas Schier Cc: Qiang Zhao Cc: linuxppc-dev Cc: linux-arm-kernel@lists.infradead.org Cc: Kumar Gala Acked-by: Nicolas Schier Signed-off-by: Li Yang Signed-off-by: Sasha Levin --- drivers/soc/fsl/qe/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/soc/fsl/qe/Kconfig b/drivers/soc/fsl/qe/Kconfig index 357c5800b112..7afa796dbbb8 100644 --- a/drivers/soc/fsl/qe/Kconfig +++ b/drivers/soc/fsl/qe/Kconfig @@ -39,6 +39,7 @@ config QE_TDM config QE_USB bool + depends on QUICC_ENGINE default y if USB_FSL_QE help QE USB Controller support From 2d38866a99baedcbf619e96ab8cc1b884124a459 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 25 Nov 2021 20:53:22 +0100 Subject: [PATCH 3866/4345] IB/hfi1: Use bitmap_zalloc() when applicable [ Upstream commit f86dbc9fc5d83384eae7eda0de17f823e8c81ca0 ] Use 'bitmap_zalloc()' to simplify code, improve the semantic and avoid some open-coded arithmetic in allocator arguments. Also change the corresponding 'kfree()' into 'bitmap_free()' to keep consistency. Link: https://lore.kernel.org/r/d46c6bc1869b8869244fa71943d2cad4104b3668.1637869925.git.christophe.jaillet@wanadoo.fr Signed-off-by: Christophe JAILLET Signed-off-by: Jason Gunthorpe Stable-dep-of: c9358de193ec ("IB/hfi1: Fix wrong mmu_node used for user SDMA packet after invalidate") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/user_sdma.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index 1eb5a44a4ae6..3f49633bf985 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -202,9 +202,7 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt, if (!pq->reqs) goto pq_reqs_nomem; - pq->req_in_use = kcalloc(BITS_TO_LONGS(hfi1_sdma_comp_ring_size), - sizeof(*pq->req_in_use), - GFP_KERNEL); + pq->req_in_use = bitmap_zalloc(hfi1_sdma_comp_ring_size, GFP_KERNEL); if (!pq->req_in_use) goto pq_reqs_no_in_use; @@ -251,7 +249,7 @@ cq_comps_nomem: cq_nomem: kmem_cache_destroy(pq->txreq_cache); pq_txreq_nomem: - kfree(pq->req_in_use); + bitmap_free(pq->req_in_use); pq_reqs_no_in_use: kfree(pq->reqs); pq_reqs_nomem: @@ -298,7 +296,7 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd, pq->wait, !atomic_read(&pq->n_reqs)); kfree(pq->reqs); - kfree(pq->req_in_use); + bitmap_free(pq->req_in_use); kmem_cache_destroy(pq->txreq_cache); flush_pq_iowait(pq); kfree(pq); From 6cf8f3d690bb5ad31ef0f41a6206ecf5a068d179 Mon Sep 17 00:00:00 2001 From: Patrick Kelsey Date: Thu, 16 Feb 2023 11:56:28 -0500 Subject: [PATCH 3867/4345] IB/hfi1: Fix sdma.h tx->num_descs off-by-one errors [ Upstream commit fd8958efe8779d3db19c9124fce593ce681ac709 ] Fix three sources of error involving struct sdma_txreq.num_descs. When _extend_sdma_tx_descs() extends the descriptor array, it uses the value of tx->num_descs to determine how many existing entries from the tx's original, internal descriptor array to copy to the newly allocated one. As this value was incremented before the call, the copy loop will access one entry past the internal descriptor array, copying its contents into the corresponding slot in the new array. If the call to _extend_sdma_tx_descs() fails, _pad_smda_tx_descs() then invokes __sdma_tx_clean() which uses the value of tx->num_desc to drive a loop that unmaps all descriptor entries in use. As this value was incremented before the call, the unmap loop will invoke sdma_unmap_desc() on a descriptor entry whose contents consist of whatever random data was copied into it during (1), leading to cascading further calls into the kernel and driver using arbitrary data. _sdma_close_tx() was using tx->num_descs instead of tx->num_descs - 1. Fix all of the above by: - Only increment .num_descs after .descp is extended. - Use .num_descs - 1 instead of .num_descs for last .descp entry. Fixes: f4d26d81ad7f ("staging/rdma/hfi1: Add coalescing support for SDMA TX descriptors") Link: https://lore.kernel.org/r/167656658879.2223096.10026561343022570690.stgit@awfm-02.cornelisnetworks.com Signed-off-by: Brendan Cunningham Signed-off-by: Patrick Kelsey Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe Stable-dep-of: c9358de193ec ("IB/hfi1: Fix wrong mmu_node used for user SDMA packet after invalidate") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/sdma.c | 4 ++-- drivers/infiniband/hw/hfi1/sdma.h | 15 +++++++-------- 2 files changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 061562627dae..728bf122ee0a 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -3187,8 +3187,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) { int rval = 0; - tx->num_desc++; - if ((unlikely(tx->num_desc == tx->desc_limit))) { + if ((unlikely(tx->num_desc + 1 == tx->desc_limit))) { rval = _extend_sdma_tx_descs(dd, tx); if (rval) { __sdma_txclean(dd, tx); @@ -3203,6 +3202,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) NULL, dd->sdma_pad_phys, sizeof(u32) - (tx->packet_len & (sizeof(u32) - 1))); + tx->num_desc++; _sdma_close_tx(dd, tx); return rval; } diff --git a/drivers/infiniband/hw/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h index 7d4f316ac6e4..5a372ca1f6ac 100644 --- a/drivers/infiniband/hw/hfi1/sdma.h +++ b/drivers/infiniband/hw/hfi1/sdma.h @@ -674,14 +674,13 @@ static inline void sdma_txclean(struct hfi1_devdata *dd, struct sdma_txreq *tx) static inline void _sdma_close_tx(struct hfi1_devdata *dd, struct sdma_txreq *tx) { - tx->descp[tx->num_desc].qw[0] |= - SDMA_DESC0_LAST_DESC_FLAG; - tx->descp[tx->num_desc].qw[1] |= - dd->default_desc1; + u16 last_desc = tx->num_desc - 1; + + tx->descp[last_desc].qw[0] |= SDMA_DESC0_LAST_DESC_FLAG; + tx->descp[last_desc].qw[1] |= dd->default_desc1; if (tx->flags & SDMA_TXREQ_F_URGENT) - tx->descp[tx->num_desc].qw[1] |= - (SDMA_DESC1_HEAD_TO_HOST_FLAG | - SDMA_DESC1_INT_REQ_FLAG); + tx->descp[last_desc].qw[1] |= (SDMA_DESC1_HEAD_TO_HOST_FLAG | + SDMA_DESC1_INT_REQ_FLAG); } static inline int _sdma_txadd_daddr( @@ -700,6 +699,7 @@ static inline int _sdma_txadd_daddr( pinning_ctx, addr, len); WARN_ON(len > tx->tlen); + tx->num_desc++; tx->tlen -= len; /* special cases for last */ if (!tx->tlen) { @@ -711,7 +711,6 @@ static inline int _sdma_txadd_daddr( _sdma_close_tx(dd, tx); } } - tx->num_desc++; return rval; } From 7dcb9ea3ee4b40d7538a812a7edce35fe17a4d36 Mon Sep 17 00:00:00 2001 From: Brendan Cunningham Date: Fri, 19 May 2023 12:32:16 -0400 Subject: [PATCH 3868/4345] IB/hfi1: Fix wrong mmu_node used for user SDMA packet after invalidate [ Upstream commit c9358de193ecfb360c3ce75f27ce839ca0b0bc8c ] The hfi1 user SDMA pinned-page cache will leave a stale cache entry when the cache-entry's virtual address range is invalidated but that cache entry is in-use by an outstanding SDMA request. Subsequent user SDMA requests with buffers in or spanning the virtual address range of the stale cache entry will result in packets constructed from the wrong memory, the physical pages pointed to by the stale cache entry. To fix this, remove mmu_rb_node cache entries from the mmu_rb_handler cache independent of the cache entry's refcount. Add 'struct kref refcount' to struct mmu_rb_node and manage mmu_rb_node lifetime with kref_get() and kref_put(). mmu_rb_node.refcount makes sdma_mmu_node.refcount redundant. Remove 'atomic_t refcount' from struct sdma_mmu_node and change sdma_mmu_node code to use mmu_rb_node.refcount. Move the mmu_rb_handler destructor call after a wait-for-SDMA-request-completion call so mmu_rb_nodes that need mmu_rb_handler's workqueue to queue themselves up for destruction from an interrupt context may do so. Fixes: f48ad614c100 ("IB/hfi1: Move driver out of staging") Fixes: 00cbce5cbf88 ("IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests") Link: https://lore.kernel.org/r/168451393605.3700681.13493776139032178861.stgit@awfm-02.cornelisnetworks.com Reviewed-by: Dean Luick Signed-off-by: Brendan Cunningham Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hfi1/ipoib_tx.c | 4 +- drivers/infiniband/hw/hfi1/mmu_rb.c | 101 ++++++++++------- drivers/infiniband/hw/hfi1/mmu_rb.h | 3 + drivers/infiniband/hw/hfi1/sdma.c | 23 +++- drivers/infiniband/hw/hfi1/sdma.h | 47 +++++--- drivers/infiniband/hw/hfi1/sdma_txreq.h | 2 + drivers/infiniband/hw/hfi1/user_sdma.c | 137 ++++++++++-------------- drivers/infiniband/hw/hfi1/user_sdma.h | 1 - drivers/infiniband/hw/hfi1/vnic_sdma.c | 4 +- 9 files changed, 177 insertions(+), 145 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c index 956fc3fd88b9..188048468135 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_tx.c +++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c @@ -251,11 +251,11 @@ static int hfi1_ipoib_build_ulp_payload(struct ipoib_txreq *tx, const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; ret = sdma_txadd_page(dd, - NULL, txreq, skb_frag_page(frag), frag->bv_offset, - skb_frag_size(frag)); + skb_frag_size(frag), + NULL, NULL, NULL); if (unlikely(ret)) break; } diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index d331184ded30..a501b7a682fc 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -60,8 +60,7 @@ static int mmu_notifier_range_start(struct mmu_notifier *, const struct mmu_notifier_range *); static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *, unsigned long, unsigned long); -static void do_remove(struct mmu_rb_handler *handler, - struct list_head *del_list); +static void release_immediate(struct kref *refcount); static void handle_remove(struct work_struct *work); static const struct mmu_notifier_ops mn_opts = { @@ -144,7 +143,11 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) } spin_unlock_irqrestore(&handler->lock, flags); - do_remove(handler, &del_list); + while (!list_empty(&del_list)) { + rbnode = list_first_entry(&del_list, struct mmu_rb_node, list); + list_del(&rbnode->list); + kref_put(&rbnode->refcount, release_immediate); + } /* Now the mm may be freed. */ mmdrop(handler->mn.mm); @@ -172,12 +175,6 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, } __mmu_int_rb_insert(mnode, &handler->root); list_add_tail(&mnode->list, &handler->lru_list); - - ret = handler->ops->insert(handler->ops_arg, mnode); - if (ret) { - __mmu_int_rb_remove(mnode, &handler->root); - list_del(&mnode->list); /* remove from LRU list */ - } mnode->handler = handler; unlock: spin_unlock_irqrestore(&handler->lock, flags); @@ -221,6 +218,48 @@ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, return node; } +/* + * Must NOT call while holding mnode->handler->lock. + * mnode->handler->ops->remove() may sleep and mnode->handler->lock is a + * spinlock. + */ +static void release_immediate(struct kref *refcount) +{ + struct mmu_rb_node *mnode = + container_of(refcount, struct mmu_rb_node, refcount); + mnode->handler->ops->remove(mnode->handler->ops_arg, mnode); +} + +/* Caller must hold mnode->handler->lock */ +static void release_nolock(struct kref *refcount) +{ + struct mmu_rb_node *mnode = + container_of(refcount, struct mmu_rb_node, refcount); + list_move(&mnode->list, &mnode->handler->del_list); + queue_work(mnode->handler->wq, &mnode->handler->del_work); +} + +/* + * struct mmu_rb_node->refcount kref_put() callback. + * Adds mmu_rb_node to mmu_rb_node->handler->del_list and queues + * handler->del_work on handler->wq. + * Does not remove mmu_rb_node from handler->lru_list or handler->rb_root. + * Acquires mmu_rb_node->handler->lock; do not call while already holding + * handler->lock. + */ +void hfi1_mmu_rb_release(struct kref *refcount) +{ + struct mmu_rb_node *mnode = + container_of(refcount, struct mmu_rb_node, refcount); + struct mmu_rb_handler *handler = mnode->handler; + unsigned long flags; + + spin_lock_irqsave(&handler->lock, flags); + list_move(&mnode->list, &mnode->handler->del_list); + spin_unlock_irqrestore(&handler->lock, flags); + queue_work(handler->wq, &handler->del_work); +} + void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) { struct mmu_rb_node *rbnode, *ptr; @@ -235,6 +274,10 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) spin_lock_irqsave(&handler->lock, flags); list_for_each_entry_safe(rbnode, ptr, &handler->lru_list, list) { + /* refcount == 1 implies mmu_rb_handler has only rbnode ref */ + if (kref_read(&rbnode->refcount) > 1) + continue; + if (handler->ops->evict(handler->ops_arg, rbnode, evict_arg, &stop)) { __mmu_int_rb_remove(rbnode, &handler->root); @@ -247,7 +290,7 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) spin_unlock_irqrestore(&handler->lock, flags); list_for_each_entry_safe(rbnode, ptr, &del_list, list) { - handler->ops->remove(handler->ops_arg, rbnode); + kref_put(&rbnode->refcount, release_immediate); } } @@ -259,7 +302,6 @@ static int mmu_notifier_range_start(struct mmu_notifier *mn, struct rb_root_cached *root = &handler->root; struct mmu_rb_node *node, *ptr = NULL; unsigned long flags; - bool added = false; spin_lock_irqsave(&handler->lock, flags); for (node = __mmu_int_rb_iter_first(root, range->start, range->end-1); @@ -268,38 +310,16 @@ static int mmu_notifier_range_start(struct mmu_notifier *mn, ptr = __mmu_int_rb_iter_next(node, range->start, range->end - 1); trace_hfi1_mmu_mem_invalidate(node->addr, node->len); - if (handler->ops->invalidate(handler->ops_arg, node)) { - __mmu_int_rb_remove(node, root); - /* move from LRU list to delete list */ - list_move(&node->list, &handler->del_list); - added = true; - } + /* Remove from rb tree and lru_list. */ + __mmu_int_rb_remove(node, root); + list_del_init(&node->list); + kref_put(&node->refcount, release_nolock); } spin_unlock_irqrestore(&handler->lock, flags); - if (added) - queue_work(handler->wq, &handler->del_work); - return 0; } -/* - * Call the remove function for the given handler and the list. This - * is expected to be called with a delete list extracted from handler. - * The caller should not be holding the handler lock. - */ -static void do_remove(struct mmu_rb_handler *handler, - struct list_head *del_list) -{ - struct mmu_rb_node *node; - - while (!list_empty(del_list)) { - node = list_first_entry(del_list, struct mmu_rb_node, list); - list_del(&node->list); - handler->ops->remove(handler->ops_arg, node); - } -} - /* * Work queue function to remove all nodes that have been queued up to * be removed. The key feature is that mm->mmap_lock is not being held @@ -312,11 +332,16 @@ static void handle_remove(struct work_struct *work) del_work); struct list_head del_list; unsigned long flags; + struct mmu_rb_node *node; /* remove anything that is queued to get removed */ spin_lock_irqsave(&handler->lock, flags); list_replace_init(&handler->del_list, &del_list); spin_unlock_irqrestore(&handler->lock, flags); - do_remove(handler, &del_list); + while (!list_empty(&del_list)) { + node = list_first_entry(&del_list, struct mmu_rb_node, list); + list_del(&node->list); + handler->ops->remove(handler->ops_arg, node); + } } diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.h b/drivers/infiniband/hw/hfi1/mmu_rb.h index 0265d81c6206..be85537d2326 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.h +++ b/drivers/infiniband/hw/hfi1/mmu_rb.h @@ -57,6 +57,7 @@ struct mmu_rb_node { struct rb_node node; struct mmu_rb_handler *handler; struct list_head list; + struct kref refcount; }; /* @@ -92,6 +93,8 @@ int hfi1_mmu_rb_register(void *ops_arg, void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler); int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, struct mmu_rb_node *mnode); +void hfi1_mmu_rb_release(struct kref *refcount); + void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg); struct mmu_rb_node *hfi1_mmu_rb_get_first(struct mmu_rb_handler *handler, unsigned long addr, diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 728bf122ee0a..2dc97de434a5 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -1635,7 +1635,20 @@ static inline void sdma_unmap_desc( struct hfi1_devdata *dd, struct sdma_desc *descp) { - system_descriptor_complete(dd, descp); + switch (sdma_mapping_type(descp)) { + case SDMA_MAP_SINGLE: + dma_unmap_single(&dd->pcidev->dev, sdma_mapping_addr(descp), + sdma_mapping_len(descp), DMA_TO_DEVICE); + break; + case SDMA_MAP_PAGE: + dma_unmap_page(&dd->pcidev->dev, sdma_mapping_addr(descp), + sdma_mapping_len(descp), DMA_TO_DEVICE); + break; + } + + if (descp->pinning_ctx && descp->ctx_put) + descp->ctx_put(descp->pinning_ctx); + descp->pinning_ctx = NULL; } /* @@ -3155,8 +3168,8 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx, /* Add descriptor for coalesce buffer */ tx->desc_limit = MAX_DESC; - return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, NULL, tx, - addr, tx->tlen); + return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, tx, + addr, tx->tlen, NULL, NULL, NULL); } return 1; @@ -3199,9 +3212,9 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) make_tx_sdma_desc( tx, SDMA_MAP_NONE, - NULL, dd->sdma_pad_phys, - sizeof(u32) - (tx->packet_len & (sizeof(u32) - 1))); + sizeof(u32) - (tx->packet_len & (sizeof(u32) - 1)), + NULL, NULL, NULL); tx->num_desc++; _sdma_close_tx(dd, tx); return rval; diff --git a/drivers/infiniband/hw/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h index 5a372ca1f6ac..7611f09d78dc 100644 --- a/drivers/infiniband/hw/hfi1/sdma.h +++ b/drivers/infiniband/hw/hfi1/sdma.h @@ -635,9 +635,11 @@ static inline dma_addr_t sdma_mapping_addr(struct sdma_desc *d) static inline void make_tx_sdma_desc( struct sdma_txreq *tx, int type, - void *pinning_ctx, dma_addr_t addr, - size_t len) + size_t len, + void *pinning_ctx, + void (*ctx_get)(void *), + void (*ctx_put)(void *)) { struct sdma_desc *desc = &tx->descp[tx->num_desc]; @@ -654,7 +656,11 @@ static inline void make_tx_sdma_desc( << SDMA_DESC0_PHY_ADDR_SHIFT) | (((u64)len & SDMA_DESC0_BYTE_COUNT_MASK) << SDMA_DESC0_BYTE_COUNT_SHIFT); + desc->pinning_ctx = pinning_ctx; + desc->ctx_put = ctx_put; + if (pinning_ctx && ctx_get) + ctx_get(pinning_ctx); } /* helper to extend txreq */ @@ -686,18 +692,20 @@ static inline void _sdma_close_tx(struct hfi1_devdata *dd, static inline int _sdma_txadd_daddr( struct hfi1_devdata *dd, int type, - void *pinning_ctx, struct sdma_txreq *tx, dma_addr_t addr, - u16 len) + u16 len, + void *pinning_ctx, + void (*ctx_get)(void *), + void (*ctx_put)(void *)) { int rval = 0; make_tx_sdma_desc( tx, type, - pinning_ctx, - addr, len); + addr, len, + pinning_ctx, ctx_get, ctx_put); WARN_ON(len > tx->tlen); tx->num_desc++; tx->tlen -= len; @@ -717,11 +725,18 @@ static inline int _sdma_txadd_daddr( /** * sdma_txadd_page() - add a page to the sdma_txreq * @dd: the device to use for mapping - * @pinning_ctx: context to be released at descriptor retirement * @tx: tx request to which the page is added * @page: page to map * @offset: offset within the page * @len: length in bytes + * @pinning_ctx: context to be stored on struct sdma_desc .pinning_ctx. Not + * added if coalesce buffer is used. E.g. pointer to pinned-page + * cache entry for the sdma_desc. + * @ctx_get: optional function to take reference to @pinning_ctx. Not called if + * @pinning_ctx is NULL. + * @ctx_put: optional function to release reference to @pinning_ctx after + * sdma_desc completes. May be called in interrupt context so must + * not sleep. Not called if @pinning_ctx is NULL. * * This is used to add a page/offset/length descriptor. * @@ -733,11 +748,13 @@ static inline int _sdma_txadd_daddr( */ static inline int sdma_txadd_page( struct hfi1_devdata *dd, - void *pinning_ctx, struct sdma_txreq *tx, struct page *page, unsigned long offset, - u16 len) + u16 len, + void *pinning_ctx, + void (*ctx_get)(void *), + void (*ctx_put)(void *)) { dma_addr_t addr; int rval; @@ -761,7 +778,8 @@ static inline int sdma_txadd_page( return -ENOSPC; } - return _sdma_txadd_daddr(dd, SDMA_MAP_PAGE, pinning_ctx, tx, addr, len); + return _sdma_txadd_daddr(dd, SDMA_MAP_PAGE, tx, addr, len, + pinning_ctx, ctx_get, ctx_put); } /** @@ -795,8 +813,8 @@ static inline int sdma_txadd_daddr( return rval; } - return _sdma_txadd_daddr(dd, SDMA_MAP_NONE, NULL, tx, - addr, len); + return _sdma_txadd_daddr(dd, SDMA_MAP_NONE, tx, addr, len, + NULL, NULL, NULL); } /** @@ -842,7 +860,8 @@ static inline int sdma_txadd_kvaddr( return -ENOSPC; } - return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, NULL, tx, addr, len); + return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, tx, addr, len, + NULL, NULL, NULL); } struct iowait_work; @@ -1093,6 +1112,4 @@ u16 sdma_get_descq_cnt(void); extern uint mod_num_sdma; void sdma_update_lmc(struct hfi1_devdata *dd, u64 mask, u32 lid); - -void system_descriptor_complete(struct hfi1_devdata *dd, struct sdma_desc *descp); #endif diff --git a/drivers/infiniband/hw/hfi1/sdma_txreq.h b/drivers/infiniband/hw/hfi1/sdma_txreq.h index 4204650cebc2..fb091b5834b5 100644 --- a/drivers/infiniband/hw/hfi1/sdma_txreq.h +++ b/drivers/infiniband/hw/hfi1/sdma_txreq.h @@ -62,6 +62,8 @@ struct sdma_desc { /* private: don't use directly */ u64 qw[2]; void *pinning_ctx; + /* Release reference to @pinning_ctx. May be called in interrupt context. Must not sleep. */ + void (*ctx_put)(void *ctx); }; /** diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index 3f49633bf985..a67791187d46 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -103,18 +103,14 @@ static int defer_packet_queue( static void activate_packet_queue(struct iowait *wait, int reason); static bool sdma_rb_filter(struct mmu_rb_node *node, unsigned long addr, unsigned long len); -static int sdma_rb_insert(void *arg, struct mmu_rb_node *mnode); static int sdma_rb_evict(void *arg, struct mmu_rb_node *mnode, void *arg2, bool *stop); static void sdma_rb_remove(void *arg, struct mmu_rb_node *mnode); -static int sdma_rb_invalidate(void *arg, struct mmu_rb_node *mnode); static struct mmu_rb_ops sdma_rb_ops = { .filter = sdma_rb_filter, - .insert = sdma_rb_insert, .evict = sdma_rb_evict, .remove = sdma_rb_remove, - .invalidate = sdma_rb_invalidate }; static int add_system_pages_to_sdma_packet(struct user_sdma_request *req, @@ -288,14 +284,14 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd, spin_unlock(&fd->pq_rcu_lock); synchronize_srcu(&fd->pq_srcu); /* at this point there can be no more new requests */ - if (pq->handler) - hfi1_mmu_rb_unregister(pq->handler); iowait_sdma_drain(&pq->busy); /* Wait until all requests have been freed. */ wait_event_interruptible( pq->wait, !atomic_read(&pq->n_reqs)); kfree(pq->reqs); + if (pq->handler) + hfi1_mmu_rb_unregister(pq->handler); bitmap_free(pq->req_in_use); kmem_cache_destroy(pq->txreq_cache); flush_pq_iowait(pq); @@ -1316,25 +1312,17 @@ static void free_system_node(struct sdma_mmu_node *node) kfree(node); } -static inline void acquire_node(struct sdma_mmu_node *node) -{ - atomic_inc(&node->refcount); - WARN_ON(atomic_read(&node->refcount) < 0); -} - -static inline void release_node(struct mmu_rb_handler *handler, - struct sdma_mmu_node *node) -{ - atomic_dec(&node->refcount); - WARN_ON(atomic_read(&node->refcount) < 0); -} - +/* + * kref_get()'s an additional kref on the returned rb_node to prevent rb_node + * from being released until after rb_node is assigned to an SDMA descriptor + * (struct sdma_desc) under add_system_iovec_to_sdma_packet(), even if the + * virtual address range for rb_node is invalidated between now and then. + */ static struct sdma_mmu_node *find_system_node(struct mmu_rb_handler *handler, unsigned long start, unsigned long end) { struct mmu_rb_node *rb_node; - struct sdma_mmu_node *node; unsigned long flags; spin_lock_irqsave(&handler->lock, flags); @@ -1343,11 +1331,12 @@ static struct sdma_mmu_node *find_system_node(struct mmu_rb_handler *handler, spin_unlock_irqrestore(&handler->lock, flags); return NULL; } - node = container_of(rb_node, struct sdma_mmu_node, rb); - acquire_node(node); + + /* "safety" kref to prevent release before add_system_iovec_to_sdma_packet() */ + kref_get(&rb_node->refcount); spin_unlock_irqrestore(&handler->lock, flags); - return node; + return container_of(rb_node, struct sdma_mmu_node, rb); } static int pin_system_pages(struct user_sdma_request *req, @@ -1396,6 +1385,13 @@ retry: return 0; } +/* + * kref refcount on *node_p will be 2 on successful addition: one kref from + * kref_init() for mmu_rb_handler and one kref to prevent *node_p from being + * released until after *node_p is assigned to an SDMA descriptor (struct + * sdma_desc) under add_system_iovec_to_sdma_packet(), even if the virtual + * address range for *node_p is invalidated between now and then. + */ static int add_system_pinning(struct user_sdma_request *req, struct sdma_mmu_node **node_p, unsigned long start, unsigned long len) @@ -1409,6 +1405,12 @@ static int add_system_pinning(struct user_sdma_request *req, if (!node) return -ENOMEM; + /* First kref "moves" to mmu_rb_handler */ + kref_init(&node->rb.refcount); + + /* "safety" kref to prevent release before add_system_iovec_to_sdma_packet() */ + kref_get(&node->rb.refcount); + node->pq = pq; ret = pin_system_pages(req, start, len, node, PFN_DOWN(len)); if (ret == 0) { @@ -1472,15 +1474,15 @@ static int get_system_cache_entry(struct user_sdma_request *req, return 0; } - SDMA_DBG(req, "prepend: node->rb.addr %lx, node->refcount %d", - node->rb.addr, atomic_read(&node->refcount)); + SDMA_DBG(req, "prepend: node->rb.addr %lx, node->rb.refcount %d", + node->rb.addr, kref_read(&node->rb.refcount)); prepend_len = node->rb.addr - start; /* * This node will not be returned, instead a new node * will be. So release the reference. */ - release_node(handler, node); + kref_put(&node->rb.refcount, hfi1_mmu_rb_release); /* Prepend a node to cover the beginning of the allocation */ ret = add_system_pinning(req, node_p, start, prepend_len); @@ -1492,6 +1494,20 @@ static int get_system_cache_entry(struct user_sdma_request *req, } } +static void sdma_mmu_rb_node_get(void *ctx) +{ + struct mmu_rb_node *node = ctx; + + kref_get(&node->refcount); +} + +static void sdma_mmu_rb_node_put(void *ctx) +{ + struct sdma_mmu_node *node = ctx; + + kref_put(&node->rb.refcount, hfi1_mmu_rb_release); +} + static int add_mapping_to_sdma_packet(struct user_sdma_request *req, struct user_sdma_txreq *tx, struct sdma_mmu_node *cache_entry, @@ -1535,9 +1551,12 @@ static int add_mapping_to_sdma_packet(struct user_sdma_request *req, ctx = cache_entry; } - ret = sdma_txadd_page(pq->dd, ctx, &tx->txreq, + ret = sdma_txadd_page(pq->dd, &tx->txreq, cache_entry->pages[page_index], - page_offset, from_this_page); + page_offset, from_this_page, + ctx, + sdma_mmu_rb_node_get, + sdma_mmu_rb_node_put); if (ret) { /* * When there's a failure, the entire request is freed by @@ -1559,8 +1578,6 @@ static int add_system_iovec_to_sdma_packet(struct user_sdma_request *req, struct user_sdma_iovec *iovec, size_t from_this_iovec) { - struct mmu_rb_handler *handler = req->pq->handler; - while (from_this_iovec > 0) { struct sdma_mmu_node *cache_entry; size_t from_this_cache_entry; @@ -1581,15 +1598,15 @@ static int add_system_iovec_to_sdma_packet(struct user_sdma_request *req, ret = add_mapping_to_sdma_packet(req, tx, cache_entry, start, from_this_cache_entry); + + /* + * Done adding cache_entry to zero or more sdma_desc. Can + * kref_put() the "safety" kref taken under + * get_system_cache_entry(). + */ + kref_put(&cache_entry->rb.refcount, hfi1_mmu_rb_release); + if (ret) { - /* - * We're guaranteed that there will be no descriptor - * completion callback that releases this node - * because only the last descriptor referencing it - * has a context attached, and a failure means the - * last descriptor was never added. - */ - release_node(handler, cache_entry); SDMA_DBG(req, "add system segment failed %d", ret); return ret; } @@ -1640,42 +1657,12 @@ static int add_system_pages_to_sdma_packet(struct user_sdma_request *req, return 0; } -void system_descriptor_complete(struct hfi1_devdata *dd, - struct sdma_desc *descp) -{ - switch (sdma_mapping_type(descp)) { - case SDMA_MAP_SINGLE: - dma_unmap_single(&dd->pcidev->dev, sdma_mapping_addr(descp), - sdma_mapping_len(descp), DMA_TO_DEVICE); - break; - case SDMA_MAP_PAGE: - dma_unmap_page(&dd->pcidev->dev, sdma_mapping_addr(descp), - sdma_mapping_len(descp), DMA_TO_DEVICE); - break; - } - - if (descp->pinning_ctx) { - struct sdma_mmu_node *node = descp->pinning_ctx; - - release_node(node->rb.handler, node); - } -} - static bool sdma_rb_filter(struct mmu_rb_node *node, unsigned long addr, unsigned long len) { return (bool)(node->addr == addr); } -static int sdma_rb_insert(void *arg, struct mmu_rb_node *mnode) -{ - struct sdma_mmu_node *node = - container_of(mnode, struct sdma_mmu_node, rb); - - atomic_inc(&node->refcount); - return 0; -} - /* * Return 1 to remove the node from the rb tree and call the remove op. * @@ -1688,10 +1675,6 @@ static int sdma_rb_evict(void *arg, struct mmu_rb_node *mnode, container_of(mnode, struct sdma_mmu_node, rb); struct evict_data *evict_data = evict_arg; - /* is this node still being used? */ - if (atomic_read(&node->refcount)) - return 0; /* keep this node */ - /* this node will be evicted, add its pages to our count */ evict_data->cleared += node->npages; @@ -1709,13 +1692,3 @@ static void sdma_rb_remove(void *arg, struct mmu_rb_node *mnode) free_system_node(node); } - -static int sdma_rb_invalidate(void *arg, struct mmu_rb_node *mnode) -{ - struct sdma_mmu_node *node = - container_of(mnode, struct sdma_mmu_node, rb); - - if (!atomic_read(&node->refcount)) - return 1; - return 0; -} diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h index 9d417aacfa8b..b2b26b71fcef 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.h +++ b/drivers/infiniband/hw/hfi1/user_sdma.h @@ -145,7 +145,6 @@ struct hfi1_user_sdma_comp_q { struct sdma_mmu_node { struct mmu_rb_node rb; struct hfi1_user_sdma_pkt_q *pq; - atomic_t refcount; struct page **pages; unsigned int npages; }; diff --git a/drivers/infiniband/hw/hfi1/vnic_sdma.c b/drivers/infiniband/hw/hfi1/vnic_sdma.c index 7658c620a125..ab8bcdf10447 100644 --- a/drivers/infiniband/hw/hfi1/vnic_sdma.c +++ b/drivers/infiniband/hw/hfi1/vnic_sdma.c @@ -106,11 +106,11 @@ static noinline int build_vnic_ulp_payload(struct sdma_engine *sde, /* combine physically continuous fragments later? */ ret = sdma_txadd_page(sde->dd, - NULL, &tx->txreq, skb_frag_page(frag), skb_frag_off(frag), - skb_frag_size(frag)); + skb_frag_size(frag), + NULL, NULL, NULL); if (unlikely(ret)) goto bail_txadd; } From cc1b04b699e63a99e6790bef262651cba1cf029e Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Sat, 3 Oct 2020 20:20:02 -0300 Subject: [PATCH 3869/4345] RDMA: Remove uverbs_ex_cmd_mask values that are linked to functions [ Upstream commit b8e3130dd96b7b2d6d92e62dcd1515af30212fe2 ] Since a while now the uverbs layer checks if the driver implements a function before allowing the ucmd to proceed. This largely obsoletes the cmd_mask stuff, but there is some tricky bits in drivers preventing it from being removed. Remove the easy elements of uverbs_ex_cmd_mask by pre-setting them in the core code. These are triggered soley based on the related ops function pointer. query_device_ex is not triggered based on an op, but all drivers already implement something compatible with the extension, so enable it globally too. Link: https://lore.kernel.org/r/2-v1-caa70ba3d1ab+1436e-ucmd_mask_jgg@nvidia.com Signed-off-by: Jason Gunthorpe Stable-dep-of: cf5b608fb0e3 ("RDMA/hns: Fix hns_roce_table_get return value") Signed-off-by: Sasha Levin --- drivers/infiniband/core/device.c | 11 +++++++++++ drivers/infiniband/core/uverbs_cmd.c | 2 +- drivers/infiniband/hw/efa/efa_main.c | 3 --- drivers/infiniband/hw/hns/hns_roce_hw_v1.c | 7 ------- drivers/infiniband/hw/hns/hns_roce_main.c | 2 -- drivers/infiniband/hw/mlx4/main.c | 14 +------------- drivers/infiniband/hw/mlx5/main.c | 14 ++------------ 7 files changed, 15 insertions(+), 38 deletions(-) diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 5b7abcf102fe..3c29fd04b301 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -600,6 +600,17 @@ struct ib_device *_ib_alloc_device(size_t size) init_completion(&device->unreg_completion); INIT_WORK(&device->unregistration_work, ib_unregister_work); + device->uverbs_ex_cmd_mask = + BIT_ULL(IB_USER_VERBS_EX_CMD_CREATE_FLOW) | + BIT_ULL(IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL) | + BIT_ULL(IB_USER_VERBS_EX_CMD_CREATE_WQ) | + BIT_ULL(IB_USER_VERBS_EX_CMD_DESTROY_FLOW) | + BIT_ULL(IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL) | + BIT_ULL(IB_USER_VERBS_EX_CMD_DESTROY_WQ) | + BIT_ULL(IB_USER_VERBS_EX_CMD_MODIFY_CQ) | + BIT_ULL(IB_USER_VERBS_EX_CMD_MODIFY_WQ) | + BIT_ULL(IB_USER_VERBS_EX_CMD_QUERY_DEVICE); + return device; } EXPORT_SYMBOL(_ib_alloc_device); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 09cf470c08d6..158f9eadc4e9 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -3778,7 +3778,7 @@ const struct uapi_definition uverbs_def_write_intf[] = { IB_USER_VERBS_EX_CMD_MODIFY_CQ, ib_uverbs_ex_modify_cq, UAPI_DEF_WRITE_I(struct ib_uverbs_ex_modify_cq), - UAPI_DEF_METHOD_NEEDS_FN(create_cq))), + UAPI_DEF_METHOD_NEEDS_FN(modify_cq))), DECLARE_UVERBS_OBJECT( UVERBS_OBJECT_DEVICE, diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c index ffdd18f4217f..cd41cd114ab6 100644 --- a/drivers/infiniband/hw/efa/efa_main.c +++ b/drivers/infiniband/hw/efa/efa_main.c @@ -326,9 +326,6 @@ static int efa_ib_device_add(struct efa_dev *dev) (1ull << IB_USER_VERBS_CMD_CREATE_AH) | (1ull << IB_USER_VERBS_CMD_DESTROY_AH); - dev->ibdev.uverbs_ex_cmd_mask = - (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE); - ib_set_device_ops(&dev->ibdev, &efa_dev_ops); err = ib_register_device(&dev->ibdev, "efa_%d", &pdev->dev); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 5f4d8a32ed6d..b3d5ba8ef439 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -2062,11 +2062,6 @@ static void hns_roce_v1_write_cqc(struct hns_roce_dev *hr_dev, CQ_CONTEXT_CQC_BYTE_32_CQ_CONS_IDX_S, 0); } -static int hns_roce_v1_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period) -{ - return -EOPNOTSUPP; -} - static int hns_roce_v1_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) { @@ -4347,7 +4342,6 @@ static void hns_roce_v1_cleanup_eq_table(struct hns_roce_dev *hr_dev) static const struct ib_device_ops hns_roce_v1_dev_ops = { .destroy_qp = hns_roce_v1_destroy_qp, - .modify_cq = hns_roce_v1_modify_cq, .poll_cq = hns_roce_v1_poll_cq, .post_recv = hns_roce_v1_post_recv, .post_send = hns_roce_v1_post_send, @@ -4367,7 +4361,6 @@ static const struct hns_roce_hw hns_roce_hw_v1 = { .set_mtu = hns_roce_v1_set_mtu, .write_mtpt = hns_roce_v1_write_mtpt, .write_cqc = hns_roce_v1_write_cqc, - .modify_cq = hns_roce_v1_modify_cq, .clear_hem = hns_roce_v1_clear_hem, .modify_qp = hns_roce_v1_modify_qp, .query_qp = hns_roce_v1_query_qp, diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index 1e8b3e4ef1b1..8cc2dae269af 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -511,8 +511,6 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev) (1ULL << IB_USER_VERBS_CMD_QUERY_QP) | (1ULL << IB_USER_VERBS_CMD_DESTROY_QP); - ib_dev->uverbs_ex_cmd_mask |= (1ULL << IB_USER_VERBS_EX_CMD_MODIFY_CQ); - if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_REREG_MR) { ib_dev->uverbs_cmd_mask |= (1ULL << IB_USER_VERBS_CMD_REREG_MR); ib_set_device_ops(ib_dev, &hns_roce_dev_mr_ops); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 05c7200751e5..c62cdd645696 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -2682,8 +2682,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_ops); ibdev->ib_dev.uverbs_ex_cmd_mask |= - (1ull << IB_USER_VERBS_EX_CMD_MODIFY_CQ) | - (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE) | (1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ) | (1ull << IB_USER_VERBS_EX_CMD_CREATE_QP); @@ -2691,15 +2689,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ((mlx4_ib_port_link_layer(&ibdev->ib_dev, 1) == IB_LINK_LAYER_ETHERNET) || (mlx4_ib_port_link_layer(&ibdev->ib_dev, 2) == - IB_LINK_LAYER_ETHERNET))) { - ibdev->ib_dev.uverbs_ex_cmd_mask |= - (1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL); + IB_LINK_LAYER_ETHERNET))) ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_wq_ops); - } if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW || dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) { @@ -2718,9 +2709,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) if (check_flow_steering_support(dev)) { ibdev->steering_support = MLX4_STEERING_MODE_DEVICE_MANAGED; - ibdev->ib_dev.uverbs_ex_cmd_mask |= - (1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW); ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_fs_ops); } diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 39ba7005f2c4..215d6618839b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4180,14 +4180,10 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev) (1ull << IB_USER_VERBS_CMD_DESTROY_SRQ) | (1ull << IB_USER_VERBS_CMD_CREATE_XSRQ) | (1ull << IB_USER_VERBS_CMD_OPEN_QP); - dev->ib_dev.uverbs_ex_cmd_mask = - (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE) | + dev->ib_dev.uverbs_ex_cmd_mask |= (1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ) | (1ull << IB_USER_VERBS_EX_CMD_CREATE_QP) | - (1ull << IB_USER_VERBS_EX_CMD_MODIFY_QP) | - (1ull << IB_USER_VERBS_EX_CMD_MODIFY_CQ) | - (1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW); + (1ull << IB_USER_VERBS_EX_CMD_MODIFY_QP); if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads) && IS_ENABLED(CONFIG_MLX5_CORE_IPOIB)) @@ -4290,12 +4286,6 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev) ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap); if (ll == IB_LINK_LAYER_ETHERNET) { - dev->ib_dev.uverbs_ex_cmd_mask |= - (1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL); ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_common_roce_ops); port_num = mlx5_core_native_port_num(dev->mdev) - 1; From de1049dd18bd7a2566f253fdb2e9a2e7d12f0b76 Mon Sep 17 00:00:00 2001 From: Lang Cheng Date: Fri, 11 Dec 2020 09:37:33 +0800 Subject: [PATCH 3870/4345] RDMA/hns: Fix coding style issues [ Upstream commit dc93a0d987fcfe93b132871e72d4ea5aff36dd5c ] Just format the code without modifying anything, including fixing some redundant and missing blanks and spaces and changing the variable definition order. Link: https://lore.kernel.org/r/1607650657-35992-8-git-send-email-liweihang@huawei.com Signed-off-by: Lang Cheng Signed-off-by: Weihang Li Signed-off-by: Jason Gunthorpe Stable-dep-of: cf5b608fb0e3 ("RDMA/hns: Fix hns_roce_table_get return value") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_cmd.c | 27 +++++++++++----------- drivers/infiniband/hw/hns/hns_roce_cmd.h | 4 ++-- drivers/infiniband/hw/hns/hns_roce_cq.c | 2 +- drivers/infiniband/hw/hns/hns_roce_hem.c | 20 ++++++++-------- drivers/infiniband/hw/hns/hns_roce_hem.h | 2 +- drivers/infiniband/hw/hns/hns_roce_hw_v1.c | 9 +++----- drivers/infiniband/hw/hns/hns_roce_hw_v1.h | 2 +- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 9 +++----- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 6 ++--- drivers/infiniband/hw/hns/hns_roce_main.c | 6 ++--- drivers/infiniband/hw/hns/hns_roce_mr.c | 4 ++-- drivers/infiniband/hw/hns/hns_roce_qp.c | 2 +- drivers/infiniband/hw/hns/hns_roce_srq.c | 1 - 13 files changed, 43 insertions(+), 51 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_cmd.c b/drivers/infiniband/hw/hns/hns_roce_cmd.c index 455d533dd7c4..c493d7644b57 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cmd.c +++ b/drivers/infiniband/hw/hns/hns_roce_cmd.c @@ -36,9 +36,9 @@ #include "hns_roce_device.h" #include "hns_roce_cmd.h" -#define CMD_POLL_TOKEN 0xffff -#define CMD_MAX_NUM 32 -#define CMD_TOKEN_MASK 0x1f +#define CMD_POLL_TOKEN 0xffff +#define CMD_MAX_NUM 32 +#define CMD_TOKEN_MASK 0x1f static int hns_roce_cmd_mbox_post_hw(struct hns_roce_dev *hr_dev, u64 in_param, u64 out_param, u32 in_modifier, @@ -93,8 +93,8 @@ static int hns_roce_cmd_mbox_poll(struct hns_roce_dev *hr_dev, u64 in_param, void hns_roce_cmd_event(struct hns_roce_dev *hr_dev, u16 token, u8 status, u64 out_param) { - struct hns_roce_cmd_context - *context = &hr_dev->cmd.context[token & hr_dev->cmd.token_mask]; + struct hns_roce_cmd_context *context = + &hr_dev->cmd.context[token % hr_dev->cmd.max_cmds]; if (token != context->token) return; @@ -164,8 +164,8 @@ static int hns_roce_cmd_mbox_wait(struct hns_roce_dev *hr_dev, u64 in_param, int ret; down(&hr_dev->cmd.event_sem); - ret = __hns_roce_cmd_mbox_wait(hr_dev, in_param, out_param, - in_modifier, op_modifier, op, timeout); + ret = __hns_roce_cmd_mbox_wait(hr_dev, in_param, out_param, in_modifier, + op_modifier, op, timeout); up(&hr_dev->cmd.event_sem); return ret; @@ -231,9 +231,8 @@ int hns_roce_cmd_use_events(struct hns_roce_dev *hr_dev) struct hns_roce_cmdq *hr_cmd = &hr_dev->cmd; int i; - hr_cmd->context = kmalloc_array(hr_cmd->max_cmds, - sizeof(*hr_cmd->context), - GFP_KERNEL); + hr_cmd->context = + kcalloc(hr_cmd->max_cmds, sizeof(*hr_cmd->context), GFP_KERNEL); if (!hr_cmd->context) return -ENOMEM; @@ -262,8 +261,8 @@ void hns_roce_cmd_use_polling(struct hns_roce_dev *hr_dev) hr_cmd->use_events = 0; } -struct hns_roce_cmd_mailbox - *hns_roce_alloc_cmd_mailbox(struct hns_roce_dev *hr_dev) +struct hns_roce_cmd_mailbox * +hns_roce_alloc_cmd_mailbox(struct hns_roce_dev *hr_dev) { struct hns_roce_cmd_mailbox *mailbox; @@ -271,8 +270,8 @@ struct hns_roce_cmd_mailbox if (!mailbox) return ERR_PTR(-ENOMEM); - mailbox->buf = dma_pool_alloc(hr_dev->cmd.pool, GFP_KERNEL, - &mailbox->dma); + mailbox->buf = + dma_pool_alloc(hr_dev->cmd.pool, GFP_KERNEL, &mailbox->dma); if (!mailbox->buf) { kfree(mailbox); return ERR_PTR(-ENOMEM); diff --git a/drivers/infiniband/hw/hns/hns_roce_cmd.h b/drivers/infiniband/hw/hns/hns_roce_cmd.h index 1915bacaded0..8e63b827f28c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cmd.h +++ b/drivers/infiniband/hw/hns/hns_roce_cmd.h @@ -143,8 +143,8 @@ int hns_roce_cmd_mbox(struct hns_roce_dev *hr_dev, u64 in_param, u64 out_param, unsigned long in_modifier, u8 op_modifier, u16 op, unsigned long timeout); -struct hns_roce_cmd_mailbox - *hns_roce_alloc_cmd_mailbox(struct hns_roce_dev *hr_dev); +struct hns_roce_cmd_mailbox * +hns_roce_alloc_cmd_mailbox(struct hns_roce_dev *hr_dev); void hns_roce_free_cmd_mailbox(struct hns_roce_dev *hr_dev, struct hns_roce_cmd_mailbox *mailbox); diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c index 8a6bded9c11c..9200e6477e1e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cq.c +++ b/drivers/infiniband/hw/hns/hns_roce_cq.c @@ -41,9 +41,9 @@ static int alloc_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) { + struct ib_device *ibdev = &hr_dev->ib_dev; struct hns_roce_cmd_mailbox *mailbox; struct hns_roce_cq_table *cq_table; - struct ib_device *ibdev = &hr_dev->ib_dev; u64 mtts[MTT_MIN_COUNT] = { 0 }; dma_addr_t dma_handle; int ret; diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index c880a8be7e3c..edc287a0a91a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -198,9 +198,9 @@ int hns_roce_calc_hem_mhop(struct hns_roce_dev *hr_dev, { struct device *dev = hr_dev->dev; u32 chunk_ba_num; + u32 chunk_size; u32 table_idx; u32 bt_num; - u32 chunk_size; if (get_hem_table_config(hr_dev, mhop, table->type)) return -EINVAL; @@ -332,15 +332,15 @@ static int hns_roce_set_hem(struct hns_roce_dev *hr_dev, { spinlock_t *lock = &hr_dev->bt_cmd_lock; struct device *dev = hr_dev->dev; - long end; - unsigned long flags; struct hns_roce_hem_iter iter; void __iomem *bt_cmd; __le32 bt_cmd_val[2]; __le32 bt_cmd_h = 0; + unsigned long flags; __le32 bt_cmd_l; - u64 bt_ba; int ret = 0; + u64 bt_ba; + long end; /* Find the HEM(Hardware Entry Memory) entry */ unsigned long i = (obj & (table->num_obj - 1)) / @@ -640,8 +640,8 @@ int hns_roce_table_get(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, unsigned long obj) { struct device *dev = hr_dev->dev; - int ret = 0; unsigned long i; + int ret = 0; if (hns_roce_check_whether_mhop(hr_dev, table->type)) return hns_roce_table_mhop_get(hr_dev, table, obj); @@ -789,14 +789,14 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev, struct hns_roce_hem_chunk *chunk; struct hns_roce_hem_mhop mhop; struct hns_roce_hem *hem; - void *addr = NULL; unsigned long mhop_obj = obj; unsigned long obj_per_chunk; unsigned long idx_offset; int offset, dma_offset; + void *addr = NULL; + u32 hem_idx = 0; int length; int i, j; - u32 hem_idx = 0; if (!table->lowmem) return NULL; @@ -966,8 +966,8 @@ static void hns_roce_cleanup_mhop_hem_table(struct hns_roce_dev *hr_dev, { struct hns_roce_hem_mhop mhop; u32 buf_chunk_size; - int i; u64 obj; + int i; if (hns_roce_calc_hem_mhop(hr_dev, table, NULL, &mhop)) return; @@ -1298,8 +1298,8 @@ static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev, const struct hns_roce_buf_region *regions, int region_cnt) { - struct roce_hem_item *hem, *temp_hem, *root_hem; struct list_head temp_list[HNS_ROCE_MAX_BT_REGION]; + struct roce_hem_item *hem, *temp_hem, *root_hem; const struct hns_roce_buf_region *r; struct list_head temp_root; struct list_head temp_btm; @@ -1404,8 +1404,8 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev, { const struct hns_roce_buf_region *r; int ofs, end; - int ret; int unit; + int ret; int i; if (region_cnt > HNS_ROCE_MAX_BT_REGION) { diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h index b34c940077bb..112243d112c2 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.h +++ b/drivers/infiniband/hw/hns/hns_roce_hem.h @@ -174,4 +174,4 @@ static inline dma_addr_t hns_roce_hem_addr(struct hns_roce_hem_iter *iter) return sg_dma_address(&iter->chunk->mem[iter->page_idx]); } -#endif /*_HNS_ROCE_HEM_H*/ +#endif /* _HNS_ROCE_HEM_H */ diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index b3d5ba8ef439..cec705b58a84 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -239,7 +239,7 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, break; } - /*Ctrl field, ctrl set type: sig, solic, imm, fence */ + /* Ctrl field, ctrl set type: sig, solic, imm, fence */ /* SO wait for conforming application scenarios */ ctrl->flag |= (wr->send_flags & IB_SEND_SIGNALED ? cpu_to_le32(HNS_ROCE_WQE_CQ_NOTIFY) : 0) | @@ -300,7 +300,7 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, } ctrl->flag |= cpu_to_le32(HNS_ROCE_WQE_INLINE); } else { - /*sqe num is two */ + /* sqe num is two */ for (i = 0; i < wr->num_sge; i++) set_data_seg(dseg + i, wr->sg_list + i); @@ -1165,7 +1165,7 @@ static int hns_roce_raq_init(struct hns_roce_dev *hr_dev) } raq->e_raq_buf->map = addr; - /* Configure raq extended address. 48bit 4K align*/ + /* Configure raq extended address. 48bit 4K align */ roce_write(hr_dev, ROCEE_EXT_RAQ_REG, raq->e_raq_buf->map >> 12); /* Configure raq_shift */ @@ -2760,7 +2760,6 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, roce_set_field(context->qpc_bytes_16, QP_CONTEXT_QPC_BYTES_16_QP_NUM_M, QP_CONTEXT_QPC_BYTES_16_QP_NUM_S, hr_qp->qpn); - } else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_INIT) { roce_set_field(context->qpc_bytes_4, QP_CONTEXT_QPC_BYTES_4_TRANSPORT_SERVICE_TYPE_M, @@ -3793,7 +3792,6 @@ static int hns_roce_v1_aeq_int(struct hns_roce_dev *hr_dev, int event_type; while ((aeqe = next_aeqe_sw_v1(eq))) { - /* Make sure we read the AEQ entry after we have checked the * ownership bit */ @@ -3898,7 +3896,6 @@ static int hns_roce_v1_ceq_int(struct hns_roce_dev *hr_dev, u32 cqn; while ((ceqe = next_ceqe_sw_v1(eq))) { - /* Make sure we read CEQ entry after we have checked the * ownership bit */ diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h index ffd0156080f5..46ab0a321d21 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h @@ -419,7 +419,7 @@ struct hns_roce_wqe_data_seg { struct hns_roce_wqe_raddr_seg { __le32 rkey; - __le32 len;/* reserved */ + __le32 len; /* reserved */ __le64 raddr; }; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 76ed547b76ea..322f341f4145 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1028,8 +1028,8 @@ static int hns_roce_v2_rst_process_cmd(struct hns_roce_dev *hr_dev) struct hns_roce_v2_priv *priv = hr_dev->priv; struct hnae3_handle *handle = priv->handle; const struct hnae3_ae_ops *ops = handle->ae_algo->ops; - unsigned long instance_stage; /* the current instance stage */ - unsigned long reset_stage; /* the current reset stage */ + unsigned long instance_stage; /* the current instance stage */ + unsigned long reset_stage; /* the current reset stage */ unsigned long reset_cnt; bool sw_resetting; bool hw_resetting; @@ -2434,7 +2434,6 @@ static int hns_roce_init_link_table(struct hns_roce_dev *hr_dev, if (i < (pg_num - 1)) entry[i].blk_ba1_nxt_ptr |= (i + 1) << HNS_ROCE_LINK_TABLE_NXT_PTR_S; - } link_tbl->npages = pg_num; link_tbl->pg_sz = buf_chk_sz; @@ -5540,16 +5539,14 @@ static int hns_roce_v2_aeq_int(struct hns_roce_dev *hr_dev, case HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW: hns_roce_cq_event(hr_dev, cqn, event_type); break; - case HNS_ROCE_EVENT_TYPE_DB_OVERFLOW: - break; case HNS_ROCE_EVENT_TYPE_MB: hns_roce_cmd_event(hr_dev, le16_to_cpu(aeqe->event.cmd.token), aeqe->event.cmd.status, le64_to_cpu(aeqe->event.cmd.out_param)); break; + case HNS_ROCE_EVENT_TYPE_DB_OVERFLOW: case HNS_ROCE_EVENT_TYPE_CEQ_OVERFLOW: - break; case HNS_ROCE_EVENT_TYPE_FLR: break; default: diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 8a92faeb3d23..8948d2b5577d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -440,7 +440,7 @@ struct hns_roce_srq_context { #define SRQC_BYTE_60_SRQ_DB_RECORD_ADDR_S 1 #define SRQC_BYTE_60_SRQ_DB_RECORD_ADDR_M GENMASK(31, 1) -enum{ +enum { V2_MPT_ST_VALID = 0x1, V2_MPT_ST_FREE = 0x2, }; @@ -1076,9 +1076,9 @@ struct hns_roce_v2_ud_send_wqe { __le32 dmac; __le32 byte_48; u8 dgid[GID_LEN_V2]; - }; -#define V2_UD_SEND_WQE_BYTE_4_OPCODE_S 0 + +#define V2_UD_SEND_WQE_BYTE_4_OPCODE_S 0 #define V2_UD_SEND_WQE_BYTE_4_OPCODE_M GENMASK(4, 0) #define V2_UD_SEND_WQE_BYTE_4_OWNER_S 7 diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index 8cc2dae269af..90cbd15f6441 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -582,8 +582,8 @@ error_failed_setup_mtu_mac: static int hns_roce_init_hem(struct hns_roce_dev *hr_dev) { - int ret; struct device *dev = hr_dev->dev; + int ret; ret = hns_roce_init_hem_table(hr_dev, &hr_dev->mr_table.mtpt_table, HEM_TYPE_MTPT, hr_dev->caps.mtpt_entry_sz, @@ -723,8 +723,8 @@ err_unmap_dmpt: */ static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev) { - int ret; struct device *dev = hr_dev->dev; + int ret; spin_lock_init(&hr_dev->sm_lock); spin_lock_init(&hr_dev->bt_cmd_lock); @@ -847,8 +847,8 @@ void hns_roce_handle_device_err(struct hns_roce_dev *hr_dev) int hns_roce_init(struct hns_roce_dev *hr_dev) { - int ret; struct device *dev = hr_dev->dev; + int ret; if (hr_dev->hw->reset) { ret = hr_dev->hw->reset(hr_dev, true); diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 1c342a7bd7df..d5b3b10e0a80 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -167,10 +167,10 @@ static void hns_roce_mr_free(struct hns_roce_dev *hr_dev, static int hns_roce_mr_enable(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr) { - int ret; unsigned long mtpt_idx = key_to_hw_index(mr->key); - struct device *dev = hr_dev->dev; struct hns_roce_cmd_mailbox *mailbox; + struct device *dev = hr_dev->dev; + int ret; /* Allocate mailbox memory */ mailbox = hns_roce_alloc_cmd_mailbox(hr_dev); diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 6fe98af7741b..c42c6761382d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -114,8 +114,8 @@ void hns_roce_qp_event(struct hns_roce_dev *hr_dev, u32 qpn, int event_type) static void hns_roce_ib_qp_event(struct hns_roce_qp *hr_qp, enum hns_roce_event type) { - struct ib_event event; struct ib_qp *ibqp = &hr_qp->ibqp; + struct ib_event event; if (ibqp->event_handler) { event.device = ibqp->device; diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index 08df97e0a665..02e2416b5fed 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -245,7 +245,6 @@ static int alloc_srq_idx(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq, err = -ENOMEM; goto err_idx_mtr; } - } return 0; From aa495b927f9ca9669cbba899ad6fb694c91f4814 Mon Sep 17 00:00:00 2001 From: Weihang Li Date: Fri, 21 May 2021 17:29:54 +0800 Subject: [PATCH 3871/4345] RDMA/hns: Use refcount_t APIs for HEM [ Upstream commit 82eb481da64586ccd287b2b2c5a086202c65e7eb ] refcount_t is better than integer for reference counting, it will WARN on overflow/underflow and avoid use-after-free risks. Link: https://lore.kernel.org/r/1621589395-2435-5-git-send-email-liweihang@huawei.com Signed-off-by: Weihang Li Signed-off-by: Jason Gunthorpe Stable-dep-of: cf5b608fb0e3 ("RDMA/hns: Fix hns_roce_table_get return value") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_hem.c | 32 +++++++++++------------- drivers/infiniband/hw/hns/hns_roce_hem.h | 4 +-- 2 files changed, 17 insertions(+), 19 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index edc287a0a91a..831e9476c628 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -260,7 +260,6 @@ static struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev, if (!hem) return NULL; - hem->refcount = 0; INIT_LIST_HEAD(&hem->chunk_list); order = get_order(hem_alloc_size); @@ -607,7 +606,7 @@ static int hns_roce_table_mhop_get(struct hns_roce_dev *hr_dev, mutex_lock(&table->mutex); if (table->hem[index.buf]) { - ++table->hem[index.buf]->refcount; + refcount_inc(&table->hem[index.buf]->refcount); goto out; } @@ -626,7 +625,7 @@ static int hns_roce_table_mhop_get(struct hns_roce_dev *hr_dev, } } - ++table->hem[index.buf]->refcount; + refcount_set(&table->hem[index.buf]->refcount, 1); goto out; err_alloc: @@ -652,7 +651,7 @@ int hns_roce_table_get(struct hns_roce_dev *hr_dev, mutex_lock(&table->mutex); if (table->hem[i]) { - ++table->hem[i]->refcount; + refcount_inc(&table->hem[i]->refcount); goto out; } @@ -675,7 +674,7 @@ int hns_roce_table_get(struct hns_roce_dev *hr_dev, goto out; } - ++table->hem[i]->refcount; + refcount_set(&table->hem[i]->refcount, 1); out: mutex_unlock(&table->mutex); return ret; @@ -742,11 +741,11 @@ static void hns_roce_table_mhop_put(struct hns_roce_dev *hr_dev, return; } - mutex_lock(&table->mutex); - if (check_refcount && (--table->hem[index.buf]->refcount > 0)) { - mutex_unlock(&table->mutex); + if (!check_refcount) + mutex_lock(&table->mutex); + else if (!refcount_dec_and_mutex_lock(&table->hem[index.buf]->refcount, + &table->mutex)) return; - } clear_mhop_hem(hr_dev, table, obj, &mhop, &index); free_mhop_hem(hr_dev, table, &mhop, &index); @@ -768,16 +767,15 @@ void hns_roce_table_put(struct hns_roce_dev *hr_dev, i = (obj & (table->num_obj - 1)) / (table->table_chunk_size / table->obj_size); - mutex_lock(&table->mutex); + if (!refcount_dec_and_mutex_lock(&table->hem[i]->refcount, + &table->mutex)) + return; - if (--table->hem[i]->refcount == 0) { - /* Clear HEM base address */ - if (hr_dev->hw->clear_hem(hr_dev, table, obj, 0)) - dev_warn(dev, "Clear HEM base address failed.\n"); + if (hr_dev->hw->clear_hem(hr_dev, table, obj, 0)) + dev_warn(dev, "failed to clear HEM base address.\n"); - hns_roce_free_hem(hr_dev, table->hem[i]); - table->hem[i] = NULL; - } + hns_roce_free_hem(hr_dev, table->hem[i]); + table->hem[i] = NULL; mutex_unlock(&table->mutex); } diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h index 112243d112c2..03d44e2efa47 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.h +++ b/drivers/infiniband/hw/hns/hns_roce_hem.h @@ -87,8 +87,8 @@ struct hns_roce_hem_chunk { }; struct hns_roce_hem { - struct list_head chunk_list; - int refcount; + struct list_head chunk_list; + refcount_t refcount; }; struct hns_roce_hem_iter { From 9196f44239cf9b0d706ec68c1b54990a7b86d193 Mon Sep 17 00:00:00 2001 From: Xi Wang Date: Fri, 21 May 2021 17:29:55 +0800 Subject: [PATCH 3872/4345] RDMA/hns: Clean the hardware related code for HEM [ Upstream commit 68e11a6086b10e1a88d2b2c8432299f595db748d ] Move the HIP06 related code to the hw v1 source file for HEM. Link: https://lore.kernel.org/r/1621589395-2435-6-git-send-email-liweihang@huawei.com Signed-off-by: Xi Wang Signed-off-by: Weihang Li Signed-off-by: Jason Gunthorpe Stable-dep-of: cf5b608fb0e3 ("RDMA/hns: Fix hns_roce_table_get return value") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_device.h | 2 - drivers/infiniband/hw/hns/hns_roce_hem.c | 82 +-------------------- drivers/infiniband/hw/hns/hns_roce_hem.h | 9 +-- drivers/infiniband/hw/hns/hns_roce_hw_v1.c | 77 +++++++++++++++++++ drivers/infiniband/hw/hns/hns_roce_hw_v1.h | 5 ++ 5 files changed, 85 insertions(+), 90 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index d9aa7424d290..09b5e4935c2c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -46,8 +46,6 @@ #define HNS_ROCE_IB_MIN_SQ_STRIDE 6 -#define HNS_ROCE_BA_SIZE (32 * 4096) - #define BA_BYTE_LEN 8 /* Hardware specification only for v1 engine */ diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index 831e9476c628..3c3187f22216 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -36,9 +36,6 @@ #include "hns_roce_hem.h" #include "hns_roce_common.h" -#define DMA_ADDR_T_SHIFT 12 -#define BT_BA_SHIFT 32 - #define HEM_INDEX_BUF BIT(0) #define HEM_INDEX_L0 BIT(1) #define HEM_INDEX_L1 BIT(2) @@ -326,81 +323,6 @@ void hns_roce_free_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem *hem) kfree(hem); } -static int hns_roce_set_hem(struct hns_roce_dev *hr_dev, - struct hns_roce_hem_table *table, unsigned long obj) -{ - spinlock_t *lock = &hr_dev->bt_cmd_lock; - struct device *dev = hr_dev->dev; - struct hns_roce_hem_iter iter; - void __iomem *bt_cmd; - __le32 bt_cmd_val[2]; - __le32 bt_cmd_h = 0; - unsigned long flags; - __le32 bt_cmd_l; - int ret = 0; - u64 bt_ba; - long end; - - /* Find the HEM(Hardware Entry Memory) entry */ - unsigned long i = (obj & (table->num_obj - 1)) / - (table->table_chunk_size / table->obj_size); - - switch (table->type) { - case HEM_TYPE_QPC: - case HEM_TYPE_MTPT: - case HEM_TYPE_CQC: - case HEM_TYPE_SRQC: - roce_set_field(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_M, - ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_S, table->type); - break; - default: - return ret; - } - - roce_set_field(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_IN_MDF_M, - ROCEE_BT_CMD_H_ROCEE_BT_CMD_IN_MDF_S, obj); - roce_set_bit(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_S, 0); - roce_set_bit(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_HW_SYNS_S, 1); - - /* Currently iter only a chunk */ - for (hns_roce_hem_first(table->hem[i], &iter); - !hns_roce_hem_last(&iter); hns_roce_hem_next(&iter)) { - bt_ba = hns_roce_hem_addr(&iter) >> DMA_ADDR_T_SHIFT; - - spin_lock_irqsave(lock, flags); - - bt_cmd = hr_dev->reg_base + ROCEE_BT_CMD_H_REG; - - end = HW_SYNC_TIMEOUT_MSECS; - while (end > 0) { - if (!(readl(bt_cmd) >> BT_CMD_SYNC_SHIFT)) - break; - - mdelay(HW_SYNC_SLEEP_TIME_INTERVAL); - end -= HW_SYNC_SLEEP_TIME_INTERVAL; - } - - if (end <= 0) { - dev_err(dev, "Write bt_cmd err,hw_sync is not zero.\n"); - spin_unlock_irqrestore(lock, flags); - return -EBUSY; - } - - bt_cmd_l = cpu_to_le32(bt_ba); - roce_set_field(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_BA_H_M, - ROCEE_BT_CMD_H_ROCEE_BT_CMD_BA_H_S, - bt_ba >> BT_BA_SHIFT); - - bt_cmd_val[0] = bt_cmd_l; - bt_cmd_val[1] = bt_cmd_h; - hns_roce_write64_k(bt_cmd_val, - hr_dev->reg_base + ROCEE_BT_CMD_L_REG); - spin_unlock_irqrestore(lock, flags); - } - - return ret; -} - static int calc_hem_config(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table, unsigned long obj, struct hns_roce_hem_mhop *mhop, @@ -666,7 +588,7 @@ int hns_roce_table_get(struct hns_roce_dev *hr_dev, } /* Set HEM base address(128K/page, pa) to Hardware */ - if (hns_roce_set_hem(hr_dev, table, obj)) { + if (hr_dev->hw->set_hem(hr_dev, table, obj, HEM_HOP_STEP_DIRECT)) { hns_roce_free_hem(hr_dev, table->hem[i]); table->hem[i] = NULL; ret = -ENODEV; @@ -771,7 +693,7 @@ void hns_roce_table_put(struct hns_roce_dev *hr_dev, &table->mutex)) return; - if (hr_dev->hw->clear_hem(hr_dev, table, obj, 0)) + if (hr_dev->hw->clear_hem(hr_dev, table, obj, HEM_HOP_STEP_DIRECT)) dev_warn(dev, "failed to clear HEM base address.\n"); hns_roce_free_hem(hr_dev, table->hem[i]); diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h index 03d44e2efa47..b7617786b100 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.h +++ b/drivers/infiniband/hw/hns/hns_roce_hem.h @@ -34,9 +34,7 @@ #ifndef _HNS_ROCE_HEM_H #define _HNS_ROCE_HEM_H -#define HW_SYNC_SLEEP_TIME_INTERVAL 20 -#define HW_SYNC_TIMEOUT_MSECS (25 * HW_SYNC_SLEEP_TIME_INTERVAL) -#define BT_CMD_SYNC_SHIFT 31 +#define HEM_HOP_STEP_DIRECT 0xff enum { /* MAP HEM(Hardware Entry Memory) */ @@ -73,11 +71,6 @@ enum { (type >= HEM_TYPE_MTT && hop_num == 1) || \ (type >= HEM_TYPE_MTT && hop_num == HNS_ROCE_HOP_NUM_0)) -enum { - HNS_ROCE_HEM_PAGE_SHIFT = 12, - HNS_ROCE_HEM_PAGE_SIZE = 1 << HNS_ROCE_HEM_PAGE_SHIFT, -}; - struct hns_roce_hem_chunk { struct list_head list; int npages; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index cec705b58a84..6f9b024d4ff7 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -450,6 +450,82 @@ static void hns_roce_set_db_event_mode(struct hns_roce_dev *hr_dev, roce_write(hr_dev, ROCEE_GLB_CFG_REG, val); } +static int hns_roce_v1_set_hem(struct hns_roce_dev *hr_dev, + struct hns_roce_hem_table *table, int obj, + int step_idx) +{ + spinlock_t *lock = &hr_dev->bt_cmd_lock; + struct device *dev = hr_dev->dev; + struct hns_roce_hem_iter iter; + void __iomem *bt_cmd; + __le32 bt_cmd_val[2]; + __le32 bt_cmd_h = 0; + unsigned long flags; + __le32 bt_cmd_l; + int ret = 0; + u64 bt_ba; + long end; + + /* Find the HEM(Hardware Entry Memory) entry */ + unsigned long i = (obj & (table->num_obj - 1)) / + (table->table_chunk_size / table->obj_size); + + switch (table->type) { + case HEM_TYPE_QPC: + case HEM_TYPE_MTPT: + case HEM_TYPE_CQC: + case HEM_TYPE_SRQC: + roce_set_field(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_M, + ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_S, table->type); + break; + default: + return ret; + } + + roce_set_field(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_IN_MDF_M, + ROCEE_BT_CMD_H_ROCEE_BT_CMD_IN_MDF_S, obj); + roce_set_bit(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_S, 0); + roce_set_bit(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_HW_SYNS_S, 1); + + /* Currently iter only a chunk */ + for (hns_roce_hem_first(table->hem[i], &iter); + !hns_roce_hem_last(&iter); hns_roce_hem_next(&iter)) { + bt_ba = hns_roce_hem_addr(&iter) >> HNS_HW_PAGE_SHIFT; + + spin_lock_irqsave(lock, flags); + + bt_cmd = hr_dev->reg_base + ROCEE_BT_CMD_H_REG; + + end = HW_SYNC_TIMEOUT_MSECS; + while (end > 0) { + if (!(readl(bt_cmd) >> BT_CMD_SYNC_SHIFT)) + break; + + mdelay(HW_SYNC_SLEEP_TIME_INTERVAL); + end -= HW_SYNC_SLEEP_TIME_INTERVAL; + } + + if (end <= 0) { + dev_err(dev, "Write bt_cmd err,hw_sync is not zero.\n"); + spin_unlock_irqrestore(lock, flags); + return -EBUSY; + } + + bt_cmd_l = cpu_to_le32(bt_ba); + roce_set_field(bt_cmd_h, ROCEE_BT_CMD_H_ROCEE_BT_CMD_BA_H_M, + ROCEE_BT_CMD_H_ROCEE_BT_CMD_BA_H_S, + upper_32_bits(bt_ba)); + + bt_cmd_val[0] = bt_cmd_l; + bt_cmd_val[1] = bt_cmd_h; + hns_roce_write64_k(bt_cmd_val, + hr_dev->reg_base + ROCEE_BT_CMD_L_REG); + spin_unlock_irqrestore(lock, flags); + } + + return ret; +} + static void hns_roce_set_db_ext_mode(struct hns_roce_dev *hr_dev, u32 sdb_mode, u32 odb_mode) { @@ -4358,6 +4434,7 @@ static const struct hns_roce_hw hns_roce_hw_v1 = { .set_mtu = hns_roce_v1_set_mtu, .write_mtpt = hns_roce_v1_write_mtpt, .write_cqc = hns_roce_v1_write_cqc, + .set_hem = hns_roce_v1_set_hem, .clear_hem = hns_roce_v1_clear_hem, .modify_qp = hns_roce_v1_modify_qp, .query_qp = hns_roce_v1_query_qp, diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h index 46ab0a321d21..9ff1a41ddec3 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h @@ -1042,6 +1042,11 @@ struct hns_roce_db_table { struct hns_roce_ext_db *ext_db; }; +#define HW_SYNC_SLEEP_TIME_INTERVAL 20 +#define HW_SYNC_TIMEOUT_MSECS (25 * HW_SYNC_SLEEP_TIME_INTERVAL) +#define BT_CMD_SYNC_SHIFT 31 +#define HNS_ROCE_BA_SIZE (32 * 4096) + struct hns_roce_bt_table { struct hns_roce_buf_list qpc_buf; struct hns_roce_buf_list mtpt_buf; From 220f86cc19dc1e30a9084c8f7264fa830a23b18b Mon Sep 17 00:00:00 2001 From: Chengchang Tang Date: Tue, 23 May 2023 20:16:40 +0800 Subject: [PATCH 3873/4345] RDMA/hns: Fix hns_roce_table_get return value [ Upstream commit cf5b608fb0e369c473a8303cad6ddb386505e5b8 ] The return value of set_hem has been fixed to ENODEV, which will lead a diagnostic information missing. Fixes: 9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver") Link: https://lore.kernel.org/r/20230523121641.3132102-3-huangjunxian6@hisilicon.com Signed-off-by: Chengchang Tang Signed-off-by: Junxian Huang Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin --- drivers/infiniband/hw/hns/hns_roce_hem.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index 3c3187f22216..854b41c14774 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -588,11 +588,12 @@ int hns_roce_table_get(struct hns_roce_dev *hr_dev, } /* Set HEM base address(128K/page, pa) to Hardware */ - if (hr_dev->hw->set_hem(hr_dev, table, obj, HEM_HOP_STEP_DIRECT)) { + ret = hr_dev->hw->set_hem(hr_dev, table, obj, HEM_HOP_STEP_DIRECT); + if (ret) { hns_roce_free_hem(hr_dev, table->hem[i]); table->hem[i] = NULL; - ret = -ENODEV; - dev_err(dev, "set HEM base address to HW failed.\n"); + dev_err(dev, "set HEM base address to HW failed, ret = %d.\n", + ret); goto out; } From 6817914c67b7965452310079ae2d00992d16dac2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 23 May 2023 17:35:16 +0200 Subject: [PATCH 3874/4345] ARM: dts: iwg20d-q7-common: Fix backlight pwm specifier [ Upstream commit 0501fdec106a291c43b3c1b525cf22ab4c24b2d8 ] make dtbs_check: arch/arm/boot/dts/renesas/r8a7743-iwg20d-q7.dtb: backlight: pwms: [[58, 0, 5000000], [0]] is too long From schema: Documentation/devicetree/bindings/leds/backlight/pwm-backlight.yaml arch/arm/boot/dts/renesas/r8a7743-iwg20d-q7-dbcm-ca.dtb: backlight: pwms: [[67, 0, 5000000], [0]] is too long From schema: Documentation/devicetree/bindings/leds/backlight/pwm-backlight.yaml arch/arm/boot/dts/renesas/r8a7744-iwg20d-q7-dbcm-ca.dtb: backlight: pwms: [[67, 0, 5000000], [0]] is too long From schema: Documentation/devicetree/bindings/leds/backlight/pwm-backlight.yaml arch/arm/boot/dts/renesas/r8a7744-iwg20d-q7.dtb: backlight: pwms: [[58, 0, 5000000], [0]] is too long From schema: Documentation/devicetree/bindings/leds/backlight/pwm-backlight.yaml PWM specifiers referring to R-Car PWM Timer Controllers should contain only two cells. Fix this by dropping the bogus third cell. Fixes: 6f89dd9e9325d05b ("ARM: dts: iwg20d-q7-common: Add LCD support") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/6e5c3167424a43faf8c1fa68d9667b3d87dc86d8.1684855911.git.geert+renesas@glider.be Signed-off-by: Sasha Levin --- arch/arm/boot/dts/iwg20d-q7-common.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/iwg20d-q7-common.dtsi b/arch/arm/boot/dts/iwg20d-q7-common.dtsi index 63cafd220dba..358f5477deef 100644 --- a/arch/arm/boot/dts/iwg20d-q7-common.dtsi +++ b/arch/arm/boot/dts/iwg20d-q7-common.dtsi @@ -49,7 +49,7 @@ lcd_backlight: backlight { compatible = "pwm-backlight"; - pwms = <&pwm3 0 5000000 0>; + pwms = <&pwm3 0 5000000>; brightness-levels = <0 4 8 16 32 64 128 255>; default-brightness-level = <7>; enable-gpios = <&gpio5 14 GPIO_ACTIVE_HIGH>; From 34e1e2f3cf5a956f9c94916906acb229fd9a7070 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 25 May 2023 10:48:22 +0200 Subject: [PATCH 3875/4345] arm64: dts: renesas: ulcb-kf: Remove flow control for SCIF1 [ Upstream commit 1a2c4e5635177939a088d22fa35c6a7032725663 ] The schematics are misleading, the flow control is for HSCIF1. We need SCIF1 for GNSS/GPS which does not use flow control. Fixes: c6c816e22bc8 ("arm64: dts: ulcb-kf: enable SCIF1") Signed-off-by: Wolfram Sang Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230525084823.4195-2-wsa+renesas@sang-engineering.com Signed-off-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- arch/arm64/boot/dts/renesas/ulcb-kf.dtsi | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi index 05e64bfad023..24d0a1337ae1 100644 --- a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi @@ -270,7 +270,7 @@ }; scif1_pins: scif1 { - groups = "scif1_data_b", "scif1_ctrl"; + groups = "scif1_data_b"; function = "scif1"; }; @@ -330,7 +330,6 @@ &scif1 { pinctrl-0 = <&scif1_pins>; pinctrl-names = "default"; - uart-has-rtscts; status = "okay"; }; From ce6e0434e502abdf966164b7c72523fb5fe54635 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 4 Jun 2023 17:42:28 +0200 Subject: [PATCH 3876/4345] fbdev: omapfb: lcd_mipid: Fix an error handling path in mipid_spi_probe() [ Upstream commit 79a3908d1ea6c35157a6d907b1a9d8ec06015e7a ] If 'mipid_detect()' fails, we must free 'md' to avoid a memory leak. Fixes: 66d2f99d0bb5 ("omapfb: add support for MIPI-DCS compatible LCDs") Signed-off-by: Christophe JAILLET Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/omap/lcd_mipid.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/omap/lcd_mipid.c b/drivers/video/fbdev/omap/lcd_mipid.c index a75ae0c9b14c..d1cd8785d011 100644 --- a/drivers/video/fbdev/omap/lcd_mipid.c +++ b/drivers/video/fbdev/omap/lcd_mipid.c @@ -563,11 +563,15 @@ static int mipid_spi_probe(struct spi_device *spi) r = mipid_detect(md); if (r < 0) - return r; + goto free_md; omapfb_register_panel(&md->panel); return 0; + +free_md: + kfree(md); + return r; } static int mipid_spi_remove(struct spi_device *spi) From 17cd31487dc3089ccced8de1d26a1589d85c4201 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Wed, 19 Apr 2023 09:30:06 +0530 Subject: [PATCH 3877/4345] arm64: dts: ti: k3-j7200: Fix physical address of pin [ Upstream commit 3d011933000ed9054c649952d83162d24f020a93 ] wkup_pmx splits into multiple regions. Like wkup_pmx0 -> 13 pins (WKUP_PADCONFIG 0 - 12) wkup_pmx1 -> 2 pins (WKUP_PADCONFIG 14 - 15) wkup_pmx2 -> 59 pins (WKUP_PADCONFIG 26 - 84) wkup_pmx3 -> 8 pins (WKUP_PADCONFIG 93 - 100) With this split, pin offset needs to be adjusted to match with new pmx for all pins above wkup_pmx0. Example a pin under wkup_pmx1 should start from 0 instead of old offset(0x38 WKUP_PADCONFIG 14 offset) J7200 Datasheet (Table 6-106, Section 6.4 Pin Multiplexing) : https://www.ti.com/lit/ds/symlink/dra821u.pdf Fixes: 9ae21ac445e9 ("arm64: dts: ti: k3-j7200: Fix wakeup pinmux range") Signed-off-by: Keerthy Signed-off-by: Udit Kumar Link: https://lore.kernel.org/r/20230419040007.3022780-2-u-kumar1@ti.com Signed-off-by: Vignesh Raghavendra Signed-off-by: Sasha Levin --- .../dts/ti/k3-j7200-common-proc-board.dts | 28 +++++++++---------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts index 909ab6661aef..4ec5e955c33c 100644 --- a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts @@ -19,25 +19,25 @@ &wkup_pmx2 { mcu_cpsw_pins_default: mcu-cpsw-pins-default { pinctrl-single,pins = < - J721E_WKUP_IOPAD(0x0068, PIN_OUTPUT, 0) /* MCU_RGMII1_TX_CTL */ - J721E_WKUP_IOPAD(0x006c, PIN_INPUT, 0) /* MCU_RGMII1_RX_CTL */ - J721E_WKUP_IOPAD(0x0070, PIN_OUTPUT, 0) /* MCU_RGMII1_TD3 */ - J721E_WKUP_IOPAD(0x0074, PIN_OUTPUT, 0) /* MCU_RGMII1_TD2 */ - J721E_WKUP_IOPAD(0x0078, PIN_OUTPUT, 0) /* MCU_RGMII1_TD1 */ - J721E_WKUP_IOPAD(0x007c, PIN_OUTPUT, 0) /* MCU_RGMII1_TD0 */ - J721E_WKUP_IOPAD(0x0088, PIN_INPUT, 0) /* MCU_RGMII1_RD3 */ - J721E_WKUP_IOPAD(0x008c, PIN_INPUT, 0) /* MCU_RGMII1_RD2 */ - J721E_WKUP_IOPAD(0x0090, PIN_INPUT, 0) /* MCU_RGMII1_RD1 */ - J721E_WKUP_IOPAD(0x0094, PIN_INPUT, 0) /* MCU_RGMII1_RD0 */ - J721E_WKUP_IOPAD(0x0080, PIN_OUTPUT, 0) /* MCU_RGMII1_TXC */ - J721E_WKUP_IOPAD(0x0084, PIN_INPUT, 0) /* MCU_RGMII1_RXC */ + J721E_WKUP_IOPAD(0x0000, PIN_OUTPUT, 0) /* MCU_RGMII1_TX_CTL */ + J721E_WKUP_IOPAD(0x0004, PIN_INPUT, 0) /* MCU_RGMII1_RX_CTL */ + J721E_WKUP_IOPAD(0x0008, PIN_OUTPUT, 0) /* MCU_RGMII1_TD3 */ + J721E_WKUP_IOPAD(0x000c, PIN_OUTPUT, 0) /* MCU_RGMII1_TD2 */ + J721E_WKUP_IOPAD(0x0010, PIN_OUTPUT, 0) /* MCU_RGMII1_TD1 */ + J721E_WKUP_IOPAD(0x0014, PIN_OUTPUT, 0) /* MCU_RGMII1_TD0 */ + J721E_WKUP_IOPAD(0x0020, PIN_INPUT, 0) /* MCU_RGMII1_RD3 */ + J721E_WKUP_IOPAD(0x0024, PIN_INPUT, 0) /* MCU_RGMII1_RD2 */ + J721E_WKUP_IOPAD(0x0028, PIN_INPUT, 0) /* MCU_RGMII1_RD1 */ + J721E_WKUP_IOPAD(0x002c, PIN_INPUT, 0) /* MCU_RGMII1_RD0 */ + J721E_WKUP_IOPAD(0x0018, PIN_OUTPUT, 0) /* MCU_RGMII1_TXC */ + J721E_WKUP_IOPAD(0x001c, PIN_INPUT, 0) /* MCU_RGMII1_RXC */ >; }; mcu_mdio_pins_default: mcu-mdio1-pins-default { pinctrl-single,pins = < - J721E_WKUP_IOPAD(0x009c, PIN_OUTPUT, 0) /* (L1) MCU_MDIO0_MDC */ - J721E_WKUP_IOPAD(0x0098, PIN_INPUT, 0) /* (L4) MCU_MDIO0_MDIO */ + J721E_WKUP_IOPAD(0x0034, PIN_OUTPUT, 0) /* (L1) MCU_MDIO0_MDC */ + J721E_WKUP_IOPAD(0x0030, PIN_INPUT, 0) /* (L4) MCU_MDIO0_MDIO */ >; }; }; From badeb7fe2450ec9ed1bab0ed71302c0908055bcb Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Tue, 6 Jun 2023 20:01:12 +0200 Subject: [PATCH 3878/4345] ARM: dts: stm32: Fix audio routing on STM32MP15xx DHCOM PDK2 [ Upstream commit e3f2778b1b6ced649bffdc7cbb05b80bb92f2108 ] The audio routing flow is not correct, the flow should be from source (second element in the pair) to sink (first element in the pair). The flow now is from "HP_OUT" to "Playback", where "Playback" is source and "HP_OUT" is sink, i.e. the direction is swapped and there is no direct link between the two either. Fill in the correct routing, where "HP_OUT" supplies the "Headphone Jack", "Line In Jack" supplies "LINE_IN" input, "Microphone Jack" supplies "MIC_IN" input and "Mic Bias" supplies "Microphone Jack". Fixes: 34e0c7847dcf ("ARM: dts: stm32: Add DH Electronics DHCOM STM32MP1 SoM and PDK2 board") Signed-off-by: Marek Vasut Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi index fd0cd10cb093..2c391065135e 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi @@ -120,10 +120,13 @@ sound { compatible = "audio-graph-card"; - routing = - "MIC_IN", "Capture", - "Capture", "Mic Bias", - "Playback", "HP_OUT"; + widgets = "Headphone", "Headphone Jack", + "Line", "Line In Jack", + "Microphone", "Microphone Jack"; + routing = "Headphone Jack", "HP_OUT", + "LINE_IN", "Line In Jack", + "MIC_IN", "Microphone Jack", + "Microphone Jack", "Mic Bias"; dais = <&sai2a_port &sai2b_port>; status = "okay"; }; From 6e12311dcedd1125e0ed33eb29badf1fef65df5b Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Tue, 6 Jun 2023 13:56:04 +0200 Subject: [PATCH 3879/4345] ARM: dts: stm32: fix i2s endpoint format property for stm32mp15xx-dkx [ Upstream commit 076c74c592cabe4a47537fe5205b5b678bed010d ] Use "dai-format" to configure DAI audio format as specified in audio-graph-port.yaml bindings. Fixes: 144d1ba70548 ("ARM: dts: stm32: Adapt STM32MP157 DK boards to stm32 DT diversity") Signed-off-by: Olivier Moysan Signed-off-by: Alexandre Torgue Signed-off-by: Sasha Levin --- arch/arm/boot/dts/stm32mp15xx-dkx.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi b/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi index 47df8ac67cf1..75869d6a1ab2 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi @@ -406,7 +406,7 @@ i2s2_port: port { i2s2_endpoint: endpoint { remote-endpoint = <&sii9022_tx_endpoint>; - format = "i2s"; + dai-format = "i2s"; mclk-fs = <256>; }; }; From 4610efa404be030e1d718347f7e021081717a1fb Mon Sep 17 00:00:00 2001 From: Tim Harvey Date: Tue, 6 Jun 2023 08:30:04 -0700 Subject: [PATCH 3880/4345] hwmon: (gsc-hwmon) fix fan pwm temperature scaling [ Upstream commit a6d80df47ee2c69db99e4f2f8871aa4db154620b ] The GSC fan pwm temperature register is in centidegrees celcius but the Linux hwmon convention is to use milidegrees celcius. Fix the scaling. Fixes: 3bce5377ef66 ("hwmon: Add Gateworks System Controller support") Signed-off-by: Tim Harvey Link: https://lore.kernel.org/r/20230606153004.1448086-1-tharvey@gateworks.com Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/gsc-hwmon.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hwmon/gsc-hwmon.c b/drivers/hwmon/gsc-hwmon.c index f29ce49294da..89d036bf88df 100644 --- a/drivers/hwmon/gsc-hwmon.c +++ b/drivers/hwmon/gsc-hwmon.c @@ -82,8 +82,8 @@ static ssize_t pwm_auto_point_temp_store(struct device *dev, if (kstrtol(buf, 10, &temp)) return -EINVAL; - temp = clamp_val(temp, 0, 10000); - temp = DIV_ROUND_CLOSEST(temp, 10); + temp = clamp_val(temp, 0, 100000); + temp = DIV_ROUND_CLOSEST(temp, 100); regs[0] = temp & 0xff; regs[1] = (temp >> 8) & 0xff; @@ -100,7 +100,7 @@ static ssize_t pwm_auto_point_pwm_show(struct device *dev, { struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); - return sprintf(buf, "%d\n", 255 * (50 + (attr->index * 10)) / 100); + return sprintf(buf, "%d\n", 255 * (50 + (attr->index * 10))); } static SENSOR_DEVICE_ATTR_RO(pwm1_auto_point1_pwm, pwm_auto_point_pwm, 0); From a3c5d148b78b2f8bbade9396615676cb33640882 Mon Sep 17 00:00:00 2001 From: Chu Lin Date: Wed, 12 May 2021 17:10:43 +0000 Subject: [PATCH 3881/4345] hwmon: (adm1275) enable adm1272 temperature reporting [ Upstream commit 9da9c2dc57b2fa2e65521894cb66df4bf615214d ] adm1272 supports temperature reporting but it is disabled by default. Tested: ls temp1_* temp1_crit temp1_highest temp1_max temp1_crit_alarm temp1_input temp1_max_alarm cat temp1_input 26642 Signed-off-by: Chu Lin Link: https://lore.kernel.org/r/20210512171043.2433694-1-linchuyuan@google.com [groeck: Updated subject to reflect correct driver] Signed-off-by: Guenter Roeck Stable-dep-of: b153a0bb4199 ("hwmon: (pmbus/adm1275) Fix problems with temperature monitoring on ADM1272") Signed-off-by: Sasha Levin --- drivers/hwmon/pmbus/adm1275.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c index e7997f37b266..0be1b5777d2f 100644 --- a/drivers/hwmon/pmbus/adm1275.c +++ b/drivers/hwmon/pmbus/adm1275.c @@ -611,11 +611,13 @@ static int adm1275_probe(struct i2c_client *client) tindex = 8; info->func[0] |= PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT | - PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT; + PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | + PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP; - /* Enable VOUT if not enabled (it is disabled by default) */ - if (!(config & ADM1278_VOUT_EN)) { - config |= ADM1278_VOUT_EN; + /* Enable VOUT & TEMP1 if not enabled (disabled by default) */ + if ((config & (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)) != + (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)) { + config |= ADM1278_VOUT_EN | ADM1278_TEMP1_EN; ret = i2c_smbus_write_byte_data(client, ADM1275_PMON_CONFIG, config); @@ -625,10 +627,6 @@ static int adm1275_probe(struct i2c_client *client) return -ENODEV; } } - - if (config & ADM1278_TEMP1_EN) - info->func[0] |= - PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP; if (config & ADM1278_VIN_EN) info->func[0] |= PMBUS_HAVE_VIN; break; From 580e9b987b89ad834cc6b91087f620dfa12f705c Mon Sep 17 00:00:00 2001 From: Potin Lai Date: Wed, 2 Mar 2022 20:38:16 +0800 Subject: [PATCH 3882/4345] hwmon: (adm1275) Allow setting sample averaging [ Upstream commit a3cd66d7cbadcc0c29884f25b754fd22699c719c ] Current driver assume PWR_AVG and VI_AVG as 1 by default, and user needs to set sample averaging via sysfs manually. This patch parses the properties "adi,power-sample-average" and "adi,volt-curr-sample-average" from device tree, and setting sample averaging during probe. Input value must be one of value in the list [1, 2, 4, 8, 16, 32, 64, 128]. Signed-off-by: Potin Lai Link: https://lore.kernel.org/r/20220302123817.27025-2-potin.lai@quantatw.com Signed-off-by: Guenter Roeck Stable-dep-of: b153a0bb4199 ("hwmon: (pmbus/adm1275) Fix problems with temperature monitoring on ADM1272") Signed-off-by: Sasha Levin --- drivers/hwmon/pmbus/adm1275.c | 40 ++++++++++++++++++++++++++++++++++- 1 file changed, 39 insertions(+), 1 deletion(-) diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c index 0be1b5777d2f..92eb047ff246 100644 --- a/drivers/hwmon/pmbus/adm1275.c +++ b/drivers/hwmon/pmbus/adm1275.c @@ -475,6 +475,7 @@ static int adm1275_probe(struct i2c_client *client) int vindex = -1, voindex = -1, cindex = -1, pindex = -1; int tindex = -1; u32 shunt; + u32 avg; if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_BYTE_DATA @@ -687,7 +688,7 @@ static int adm1275_probe(struct i2c_client *client) if ((config & (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)) != (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)) { config |= ADM1278_VOUT_EN | ADM1278_TEMP1_EN; - ret = i2c_smbus_write_byte_data(client, + ret = i2c_smbus_write_word_data(client, ADM1275_PMON_CONFIG, config); if (ret < 0) { @@ -756,6 +757,43 @@ static int adm1275_probe(struct i2c_client *client) return -ENODEV; } + if (data->have_power_sampling && + of_property_read_u32(client->dev.of_node, + "adi,power-sample-average", &avg) == 0) { + if (!avg || avg > ADM1275_SAMPLES_AVG_MAX || + BIT(__fls(avg)) != avg) { + dev_err(&client->dev, + "Invalid number of power samples"); + return -EINVAL; + } + ret = adm1275_write_pmon_config(data, client, true, + ilog2(avg)); + if (ret < 0) { + dev_err(&client->dev, + "Setting power sample averaging failed with error %d", + ret); + return ret; + } + } + + if (of_property_read_u32(client->dev.of_node, + "adi,volt-curr-sample-average", &avg) == 0) { + if (!avg || avg > ADM1275_SAMPLES_AVG_MAX || + BIT(__fls(avg)) != avg) { + dev_err(&client->dev, + "Invalid number of voltage/current samples"); + return -EINVAL; + } + ret = adm1275_write_pmon_config(data, client, false, + ilog2(avg)); + if (ret < 0) { + dev_err(&client->dev, + "Setting voltage and current sample averaging failed with error %d", + ret); + return ret; + } + } + if (voindex < 0) voindex = vindex; if (vindex >= 0) { From 7e2edb84fe7c2c01543eb8a4976d55f2871ae3c7 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 2 Jun 2023 14:34:47 -0700 Subject: [PATCH 3883/4345] hwmon: (pmbus/adm1275) Fix problems with temperature monitoring on ADM1272 [ Upstream commit b153a0bb4199566abd337119207f82b59a8cd1ca ] The PMON_CONFIG register on ADM1272 is a 16 bit register. Writing a 8 bit value into it clears the upper 8 bits of the register, resulting in unexpected side effects. Fix by writing the 16 bit register value. Also, it has been reported that temperature readings are sometimes widely inaccurate, to the point where readings may result in device shutdown due to errant overtemperature faults. Improve by enabling temperature sampling. While at it, move the common code for ADM1272 and ADM1278 into a separate function, and clarify in the error message that an attempt was made to enable both VOUT and temperature monitoring. Last but not least, return the error code reported by the underlying I2C controller and not -ENODEV if updating the PMON_CONFIG register fails. After all, this does not indicate that the chip is not present, but an error in the communication with the chip. Fixes: 4ff0ce227a1e ("hwmon: (pmbus/adm1275) Add support for ADM1272") Fixes: 9da9c2dc57b2 ("hwmon: (adm1275) enable adm1272 temperature reporting") Signed-off-by: Guenter Roeck Link: https://lore.kernel.org/r/20230602213447.3557346-1-linux@roeck-us.net Signed-off-by: Guenter Roeck Signed-off-by: Sasha Levin --- drivers/hwmon/pmbus/adm1275.c | 52 +++++++++++++++++------------------ 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c index 92eb047ff246..c0618205758e 100644 --- a/drivers/hwmon/pmbus/adm1275.c +++ b/drivers/hwmon/pmbus/adm1275.c @@ -37,10 +37,13 @@ enum chips { adm1075, adm1272, adm1275, adm1276, adm1278, adm1293, adm1294 }; #define ADM1272_IRANGE BIT(0) +#define ADM1278_TSFILT BIT(15) #define ADM1278_TEMP1_EN BIT(3) #define ADM1278_VIN_EN BIT(2) #define ADM1278_VOUT_EN BIT(1) +#define ADM1278_PMON_DEFCONFIG (ADM1278_VOUT_EN | ADM1278_TEMP1_EN | ADM1278_TSFILT) + #define ADM1293_IRANGE_25 0 #define ADM1293_IRANGE_50 BIT(6) #define ADM1293_IRANGE_100 BIT(7) @@ -462,6 +465,22 @@ static const struct i2c_device_id adm1275_id[] = { }; MODULE_DEVICE_TABLE(i2c, adm1275_id); +/* Enable VOUT & TEMP1 if not enabled (disabled by default) */ +static int adm1275_enable_vout_temp(struct i2c_client *client, int config) +{ + int ret; + + if ((config & ADM1278_PMON_DEFCONFIG) != ADM1278_PMON_DEFCONFIG) { + config |= ADM1278_PMON_DEFCONFIG; + ret = i2c_smbus_write_word_data(client, ADM1275_PMON_CONFIG, config); + if (ret < 0) { + dev_err(&client->dev, "Failed to enable VOUT/TEMP1 monitoring\n"); + return ret; + } + } + return 0; +} + static int adm1275_probe(struct i2c_client *client) { s32 (*config_read_fn)(const struct i2c_client *client, u8 reg); @@ -615,19 +634,10 @@ static int adm1275_probe(struct i2c_client *client) PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP; - /* Enable VOUT & TEMP1 if not enabled (disabled by default) */ - if ((config & (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)) != - (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)) { - config |= ADM1278_VOUT_EN | ADM1278_TEMP1_EN; - ret = i2c_smbus_write_byte_data(client, - ADM1275_PMON_CONFIG, - config); - if (ret < 0) { - dev_err(&client->dev, - "Failed to enable VOUT monitoring\n"); - return -ENODEV; - } - } + ret = adm1275_enable_vout_temp(client, config); + if (ret) + return ret; + if (config & ADM1278_VIN_EN) info->func[0] |= PMBUS_HAVE_VIN; break; @@ -684,19 +694,9 @@ static int adm1275_probe(struct i2c_client *client) PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP; - /* Enable VOUT & TEMP1 if not enabled (disabled by default) */ - if ((config & (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)) != - (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)) { - config |= ADM1278_VOUT_EN | ADM1278_TEMP1_EN; - ret = i2c_smbus_write_word_data(client, - ADM1275_PMON_CONFIG, - config); - if (ret < 0) { - dev_err(&client->dev, - "Failed to enable VOUT monitoring\n"); - return -ENODEV; - } - } + ret = adm1275_enable_vout_temp(client, config); + if (ret) + return ret; if (config & ADM1278_VIN_EN) info->func[0] |= PMBUS_HAVE_VIN; From 245aa7c0233ed05fb61f6ef599254b069625eb3c Mon Sep 17 00:00:00 2001 From: Christian Lamparter Date: Thu, 8 Jun 2023 17:36:29 +0200 Subject: [PATCH 3884/4345] ARM: dts: BCM5301X: fix duplex-full => full-duplex [ Upstream commit fd274b733bfdde3ca72f0fa2a37f032f3a8c402c ] this typo was found by the dtbs_check | ports:port@5:fixed-link: 'oneOf' conditional failed, | {'speed': [[1000]], 'duplex-full': True} is not of type 'array' | 'duplex-full' does not match any of the regexes: 'pinctrl-[0-]..." this should have been full-duplex; Fixes: 935327a73553 ("ARM: dts: BCM5301X: Add DT for Meraki MR26") Fixes: ec88a9c344d9 ("ARM: BCM5301X: Add DT for Meraki MR32") Signed-off-by: Christian Lamparter Link: https://lore.kernel.org/r/50522f45566951a9eabd22820647924cc6b4a264.1686238550.git.chunkeey@gmail.com Signed-off-by: Florian Fainelli Signed-off-by: Sasha Levin --- arch/arm/boot/dts/bcm53015-meraki-mr26.dts | 2 +- arch/arm/boot/dts/bcm53016-meraki-mr32.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/bcm53015-meraki-mr26.dts b/arch/arm/boot/dts/bcm53015-meraki-mr26.dts index 14f58033efeb..ca2266b936ee 100644 --- a/arch/arm/boot/dts/bcm53015-meraki-mr26.dts +++ b/arch/arm/boot/dts/bcm53015-meraki-mr26.dts @@ -128,7 +128,7 @@ fixed-link { speed = <1000>; - duplex-full; + full-duplex; }; }; }; diff --git a/arch/arm/boot/dts/bcm53016-meraki-mr32.dts b/arch/arm/boot/dts/bcm53016-meraki-mr32.dts index 577a4dc604d9..edf9910100b0 100644 --- a/arch/arm/boot/dts/bcm53016-meraki-mr32.dts +++ b/arch/arm/boot/dts/bcm53016-meraki-mr32.dts @@ -212,7 +212,7 @@ fixed-link { speed = <1000>; - duplex-full; + full-duplex; }; }; }; From a77b80825bf1124c10e0e0deef3fc7e5abf023e0 Mon Sep 17 00:00:00 2001 From: Daniil Dulov Date: Thu, 11 May 2023 04:23:14 -0700 Subject: [PATCH 3885/4345] drm/amdkfd: Fix potential deallocation of previously deallocated memory. [ Upstream commit cabbdea1f1861098991768d7bbf5a49ed1608213 ] Pointer mqd_mem_obj can be deallocated in kfd_gtt_sa_allocate(). The function then returns non-zero value, which causes the second deallocation. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: d1f8f0d17d40 ("drm/amdkfd: Move non-sdma mqd allocation out of init_mqd") Signed-off-by: Daniil Dulov Signed-off-by: Felix Kuehling Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c index 3b6f5963180d..dadeb2013fd9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -113,18 +113,19 @@ static struct kfd_mem_obj *allocate_mqd(struct kfd_dev *kfd, &(mqd_mem_obj->gtt_mem), &(mqd_mem_obj->gpu_addr), (void *)&(mqd_mem_obj->cpu_ptr), true); + + if (retval) { + kfree(mqd_mem_obj); + return NULL; + } } else { retval = kfd_gtt_sa_allocate(kfd, sizeof(struct v9_mqd), &mqd_mem_obj); - } - - if (retval) { - kfree(mqd_mem_obj); - return NULL; + if (retval) + return NULL; } return mqd_mem_obj; - } static void init_mqd(struct mqd_manager *mm, void **mqd, From e070120e6d683cf806b044057d2ecc8bd750c916 Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Fri, 19 May 2023 08:33:27 -0700 Subject: [PATCH 3886/4345] drm/radeon: fix possible division-by-zero errors [ Upstream commit 1becc57cd1a905e2aa0e1eca60d2a37744525c4a ] Function rv740_get_decoded_reference_divider() may return 0 due to unpredictable reference divider value calculated in radeon_atom_get_clock_dividers(). This will lead to division-by-zero error once that value is used as a divider in calculating 'clk_s'. While unlikely, this issue should nonetheless be prevented so add a sanity check for such cases by testing 'decoded_ref' value against 0. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. v2: minor coding style fixes (Alex) In practice this should actually happen as the vbios should be properly populated. Fixes: 66229b200598 ("drm/radeon/kms: add dpm support for rv7xx (v4)") Signed-off-by: Nikita Zhandarovich Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/radeon/cypress_dpm.c | 8 ++++++-- drivers/gpu/drm/radeon/ni_dpm.c | 8 ++++++-- drivers/gpu/drm/radeon/rv740_dpm.c | 8 ++++++-- 3 files changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c index 35b177d77791..7120710d188f 100644 --- a/drivers/gpu/drm/radeon/cypress_dpm.c +++ b/drivers/gpu/drm/radeon/cypress_dpm.c @@ -559,8 +559,12 @@ static int cypress_populate_mclk_value(struct radeon_device *rdev, ASIC_INTERNAL_MEMORY_SS, vco_freq)) { u32 reference_clock = rdev->clock.mpll.reference_freq; u32 decoded_ref = rv740_get_decoded_reference_divider(dividers.ref_div); - u32 clk_s = reference_clock * 5 / (decoded_ref * ss.rate); - u32 clk_v = ss.percentage * + u32 clk_s, clk_v; + + if (!decoded_ref) + return -EINVAL; + clk_s = reference_clock * 5 / (decoded_ref * ss.rate); + clk_v = ss.percentage * (0x4000 * dividers.whole_fb_div + 0x800 * dividers.frac_fb_div) / (clk_s * 625); mpll_ss1 &= ~CLKV_MASK; diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index a5218747742b..f79b348d36ad 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -2240,8 +2240,12 @@ static int ni_populate_mclk_value(struct radeon_device *rdev, ASIC_INTERNAL_MEMORY_SS, vco_freq)) { u32 reference_clock = rdev->clock.mpll.reference_freq; u32 decoded_ref = rv740_get_decoded_reference_divider(dividers.ref_div); - u32 clk_s = reference_clock * 5 / (decoded_ref * ss.rate); - u32 clk_v = ss.percentage * + u32 clk_s, clk_v; + + if (!decoded_ref) + return -EINVAL; + clk_s = reference_clock * 5 / (decoded_ref * ss.rate); + clk_v = ss.percentage * (0x4000 * dividers.whole_fb_div + 0x800 * dividers.frac_fb_div) / (clk_s * 625); mpll_ss1 &= ~CLKV_MASK; diff --git a/drivers/gpu/drm/radeon/rv740_dpm.c b/drivers/gpu/drm/radeon/rv740_dpm.c index 327d65a76e1f..79b2de65e905 100644 --- a/drivers/gpu/drm/radeon/rv740_dpm.c +++ b/drivers/gpu/drm/radeon/rv740_dpm.c @@ -250,8 +250,12 @@ int rv740_populate_mclk_value(struct radeon_device *rdev, ASIC_INTERNAL_MEMORY_SS, vco_freq)) { u32 reference_clock = rdev->clock.mpll.reference_freq; u32 decoded_ref = rv740_get_decoded_reference_divider(dividers.ref_div); - u32 clk_s = reference_clock * 5 / (decoded_ref * ss.rate); - u32 clk_v = 0x40000 * ss.percentage * + u32 clk_s, clk_v; + + if (!decoded_ref) + return -EINVAL; + clk_s = reference_clock * 5 / (decoded_ref * ss.rate); + clk_v = 0x40000 * ss.percentage * (dividers.whole_fb_div + (dividers.frac_fb_div / 8)) / (clk_s * 10000); mpll_ss1 &= ~CLKV_MASK; From 968e27fd037ec4732068820a9b9836eccc0e0a12 Mon Sep 17 00:00:00 2001 From: Chia-I Wu Date: Thu, 1 Jun 2023 15:44:12 -0700 Subject: [PATCH 3887/4345] amdgpu: validate offset_in_bo of drm_amdgpu_gem_va MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 9f0bcf49e9895cb005d78b33a5eebfa11711b425 ] This is motivated by OOB access in amdgpu_vm_update_range when offset_in_bo+map_size overflows. v2: keep the validations in amdgpu_vm_bo_map v3: add the validations to amdgpu_vm_bo_map/amdgpu_vm_bo_replace_map rather than to amdgpu_gem_va_ioctl Fixes: 9f7eb5367d00 ("drm/amdgpu: actually use the VM map parameters") Reviewed-by: Christian König Signed-off-by: Chia-I Wu Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index c705ce11c436..8445bb7ae06a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2229,14 +2229,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, uint64_t eaddr; /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || - size == 0 || size & ~PAGE_MASK) + if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) + return -EINVAL; + if (saddr + size <= saddr || offset + size <= offset) return -EINVAL; /* make sure object fit at this offset */ eaddr = saddr + size - 1; - if (saddr >= eaddr || - (bo && offset + size > amdgpu_bo_size(bo)) || + if ((bo && offset + size > amdgpu_bo_size(bo)) || (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) return -EINVAL; @@ -2295,14 +2295,14 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, int r; /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || - size == 0 || size & ~PAGE_MASK) + if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) + return -EINVAL; + if (saddr + size <= saddr || offset + size <= offset) return -EINVAL; /* make sure object fit at this offset */ eaddr = saddr + size - 1; - if (saddr >= eaddr || - (bo && offset + size > amdgpu_bo_size(bo)) || + if ((bo && offset + size > amdgpu_bo_size(bo)) || (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) return -EINVAL; From 9341501e2f7af29f5b5562c2840a7fde40eb7de4 Mon Sep 17 00:00:00 2001 From: Kashyap Desai Date: Fri, 9 Jun 2023 04:01:38 -0700 Subject: [PATCH 3888/4345] RDMA/bnxt_re: wraparound mbox producer index [ Upstream commit 0af91306e17ef3d18e5f100aa58aa787869118af ] Driver is not handling the wraparound of the mbox producer index correctly. Currently the wraparound happens once u32 max is reached. Bit 31 of the producer index register is special and should be set only once for the first command. Because the producer index overflow setting bit31 after a long time, FW goes to initialization sequence and this causes FW hang. Fix is to wraparound the mbox producer index once it reaches u16 max. Fixes: cee0c7bba486 ("RDMA/bnxt_re: Refactor command queue management code") Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Signed-off-by: Kashyap Desai Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1686308514-11996-2-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 4836bc433f53..212e5cd82d0d 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -181,7 +181,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, } while (size > 0); cmdq->seq_num++; - cmdq_prod = hwq->prod; + cmdq_prod = hwq->prod & 0xFFFF; if (test_bit(FIRMWARE_FIRST_FLAG, &cmdq->flags)) { /* The very first doorbell write * is required to set this flag @@ -595,7 +595,7 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res, rcfw->cmdq_depth = BNXT_QPLIB_CMDQE_MAX_CNT_8192; sginfo.pgsize = bnxt_qplib_cmdqe_page_size(rcfw->cmdq_depth); - hwq_attr.depth = rcfw->cmdq_depth; + hwq_attr.depth = rcfw->cmdq_depth & 0x7FFFFFFF; hwq_attr.stride = BNXT_QPLIB_CMDQE_UNITS; hwq_attr.type = HWQ_TYPE_CTX; if (bnxt_qplib_alloc_init_hwq(&cmdq->hwq, &hwq_attr)) { From e749bc5a90548b0e0eca5ca19d454fc7bd03b4f7 Mon Sep 17 00:00:00 2001 From: Kashyap Desai Date: Fri, 9 Jun 2023 04:01:39 -0700 Subject: [PATCH 3889/4345] RDMA/bnxt_re: Avoid calling wake_up threads from spin_lock context [ Upstream commit 3099bcdc19b701f732f638ee45679858c08559bb ] bnxt_qplib_service_creq can be called from interrupt or tasklet or process context. So the function take irq variant of spin_lock. But when wake_up is invoked with the lock held, it is putting the calling context to sleep. [exception RIP: __wake_up_common+190] RIP: ffffffffb7539d7e RSP: ffffa73300207ad8 RFLAGS: 00000083 RAX: 0000000000000001 RBX: ffff91fa295f69b8 RCX: dead000000000200 RDX: ffffa733344af940 RSI: ffffa73336527940 RDI: ffffa73336527940 RBP: 000000000000001c R8: 0000000000000002 R9: 00000000000299c0 R10: 0000017230de82c5 R11: 0000000000000002 R12: ffffa73300207b28 R13: 0000000000000000 R14: ffffa733341bf928 R15: 0000000000000000 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 Call the wakeup after releasing the lock. Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Signed-off-by: Kashyap Desai Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1686308514-11996-3-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin --- drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 212e5cd82d0d..2b0c3a86293c 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -295,7 +295,8 @@ static int bnxt_qplib_process_func_event(struct bnxt_qplib_rcfw *rcfw, } static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, - struct creq_qp_event *qp_event) + struct creq_qp_event *qp_event, + u32 *num_wait) { struct creq_qp_error_notification *err_event; struct bnxt_qplib_hwq *hwq = &rcfw->cmdq.hwq; @@ -304,6 +305,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, u16 cbit, blocked = 0; struct pci_dev *pdev; unsigned long flags; + u32 wait_cmds = 0; __le16 mcookie; u16 cookie; int rc = 0; @@ -363,9 +365,10 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, crsqe->req_size = 0; if (!blocked) - wake_up(&rcfw->cmdq.waitq); + wait_cmds++; spin_unlock_irqrestore(&hwq->lock, flags); } + *num_wait += wait_cmds; return rc; } @@ -379,6 +382,7 @@ static void bnxt_qplib_service_creq(struct tasklet_struct *t) struct creq_base *creqe; u32 sw_cons, raw_cons; unsigned long flags; + u32 num_wakeup = 0; /* Service the CREQ until budget is over */ spin_lock_irqsave(&hwq->lock, flags); @@ -397,7 +401,8 @@ static void bnxt_qplib_service_creq(struct tasklet_struct *t) switch (type) { case CREQ_BASE_TYPE_QP_EVENT: bnxt_qplib_process_qp_event - (rcfw, (struct creq_qp_event *)creqe); + (rcfw, (struct creq_qp_event *)creqe, + &num_wakeup); creq->stats.creq_qp_event_processed++; break; case CREQ_BASE_TYPE_FUNC_EVENT: @@ -425,6 +430,8 @@ static void bnxt_qplib_service_creq(struct tasklet_struct *t) rcfw->res->cctx, true); } spin_unlock_irqrestore(&hwq->lock, flags); + if (num_wakeup) + wake_up_nr(&rcfw->cmdq.waitq, num_wakeup); } static irqreturn_t bnxt_qplib_creq_irq(int irq, void *dev_instance) From 294321349bd3b0680847fc2bbe66b9ab3e522fea Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Tue, 11 Apr 2023 09:51:07 +0800 Subject: [PATCH 3890/4345] clk: imx: clk-imx8mn: fix memory leak in imx8mn_clocks_probe [ Upstream commit 188d070de9132667956f5aadd98d2bd87d3eac89 ] Use devm_of_iomap() instead of of_iomap() to automatically handle the unused ioremap region. If any error occurs, regions allocated by kzalloc() will leak, but using devm_kzalloc() instead will automatically free the memory using devm_kfree(). Fixes: daeb14545514 ("clk: imx: imx8mn: Switch to clk_hw based API") Fixes: 96d6392b54db ("clk: imx: Add support for i.MX8MN clock driver") Signed-off-by: Hao Luo Reviewed-by: Dongliang Mu Reviewed-by: Peng Fan Link: https://lore.kernel.org/r/20230411015107.2645-1-m202171776@hust.edu.cn Signed-off-by: Abel Vesa Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx8mn.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c index 8a49e072d6e8..23f37a2cdf3a 100644 --- a/drivers/clk/imx/clk-imx8mn.c +++ b/drivers/clk/imx/clk-imx8mn.c @@ -291,7 +291,7 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) void __iomem *base; int ret; - clk_hw_data = kzalloc(struct_size(clk_hw_data, hws, + clk_hw_data = devm_kzalloc(dev, struct_size(clk_hw_data, hws, IMX8MN_CLK_END), GFP_KERNEL); if (WARN_ON(!clk_hw_data)) return -ENOMEM; @@ -308,10 +308,10 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) hws[IMX8MN_CLK_EXT4] = imx_obtain_fixed_clk_hw(np, "clk_ext4"); np = of_find_compatible_node(NULL, NULL, "fsl,imx8mn-anatop"); - base = of_iomap(np, 0); + base = devm_of_iomap(dev, np, 0, NULL); of_node_put(np); - if (WARN_ON(!base)) { - ret = -ENOMEM; + if (WARN_ON(IS_ERR(base))) { + ret = PTR_ERR(base); goto unregister_hws; } From cb047c13bbf9018693ae31f03a5a26b212d02f13 Mon Sep 17 00:00:00 2001 From: Yuxing Liu Date: Wed, 3 May 2023 07:06:07 +0000 Subject: [PATCH 3891/4345] clk: imx: clk-imx8mp: improve error handling in imx8mp_clocks_probe() [ Upstream commit 878b02d5f3b56cb090dbe2c70c89273be144087f ] Replace of_iomap() and kzalloc() with devm_of_iomap() and devm_kzalloc() which can automatically release the related memory when the device or driver is removed or unloaded to avoid potential memory leak. In this case, iounmap(anatop_base) in line 427,433 are removed as manual release is not required. Besides, referring to clk-imx8mq.c, check the return code of of_clk_add_hw_provider, if it returns negtive, print error info and unregister hws, which makes the program more robust. Fixes: 9c140d992676 ("clk: imx: Add support for i.MX8MP clock driver") Signed-off-by: Yuxing Liu Reviewed-by: Dongliang Mu Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230503070607.2462-1-lyx2022@hust.edu.cn Signed-off-by: Abel Vesa Signed-off-by: Sasha Levin --- drivers/clk/imx/clk-imx8mp.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 72592e35836b..98a4711ef38d 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -425,25 +425,22 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; void __iomem *anatop_base, *ccm_base; + int err; np = of_find_compatible_node(NULL, NULL, "fsl,imx8mp-anatop"); - anatop_base = of_iomap(np, 0); + anatop_base = devm_of_iomap(dev, np, 0, NULL); of_node_put(np); - if (WARN_ON(!anatop_base)) - return -ENOMEM; + if (WARN_ON(IS_ERR(anatop_base))) + return PTR_ERR(anatop_base); np = dev->of_node; ccm_base = devm_platform_ioremap_resource(pdev, 0); - if (WARN_ON(IS_ERR(ccm_base))) { - iounmap(anatop_base); + if (WARN_ON(IS_ERR(ccm_base))) return PTR_ERR(ccm_base); - } - clk_hw_data = kzalloc(struct_size(clk_hw_data, hws, IMX8MP_CLK_END), GFP_KERNEL); - if (WARN_ON(!clk_hw_data)) { - iounmap(anatop_base); + clk_hw_data = devm_kzalloc(dev, struct_size(clk_hw_data, hws, IMX8MP_CLK_END), GFP_KERNEL); + if (WARN_ON(!clk_hw_data)) return -ENOMEM; - } clk_hw_data->num = IMX8MP_CLK_END; hws = clk_hw_data->hws; @@ -743,7 +740,12 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) imx_check_clk_hws(hws, IMX8MP_CLK_END); - of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data); + err = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data); + if (err < 0) { + dev_err(dev, "failed to register hws for i.MX8MP\n"); + imx_unregister_hw_clocks(hws, IMX8MP_CLK_END); + return err; + } imx_register_uart_clocks(4); From 404e9f741acfb188212f7142d91e247630dd77cc Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Fri, 9 Dec 2022 09:41:24 +0000 Subject: [PATCH 3892/4345] clk: tegra: tegra124-emc: Fix potential memory leak [ Upstream commit 53a06e5924c0d43c11379a08c5a78529c3e61595 ] The tegra and tegra needs to be freed in the error handling path, otherwise it will be leaked. Fixes: 2db04f16b589 ("clk: tegra: Add EMC clock driver") Signed-off-by: Yuan Can Link: https://lore.kernel.org/r/20221209094124.71043-1-yuancan@huawei.com Acked-by: Thierry Reding Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/tegra/clk-tegra124-emc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/tegra/clk-tegra124-emc.c b/drivers/clk/tegra/clk-tegra124-emc.c index 733a962ff521..15f728edc54b 100644 --- a/drivers/clk/tegra/clk-tegra124-emc.c +++ b/drivers/clk/tegra/clk-tegra124-emc.c @@ -455,6 +455,7 @@ static int load_timings_from_dt(struct tegra_clk_emc *tegra, err = load_one_timing_from_dt(tegra, timing, child); if (err) { of_node_put(child); + kfree(tegra->timings); return err; } @@ -506,6 +507,7 @@ struct clk *tegra_clk_register_emc(void __iomem *base, struct device_node *np, err = load_timings_from_dt(tegra, node, node_ram_code); if (err) { of_node_put(node); + kfree(tegra); return ERR_PTR(err); } } From f923a582217b198b557756809ffe42ac0fad6adb Mon Sep 17 00:00:00 2001 From: Su Hui Date: Thu, 15 Jun 2023 10:17:32 +0800 Subject: [PATCH 3893/4345] ALSA: ac97: Fix possible NULL dereference in snd_ac97_mixer [ Upstream commit 79597c8bf64ca99eab385115743131d260339da5 ] smatch error: sound/pci/ac97/ac97_codec.c:2354 snd_ac97_mixer() error: we previously assumed 'rac97' could be null (see line 2072) remove redundant assignment, return error if rac97 is NULL. Fixes: da3cec35dd3c ("ALSA: Kill snd_assert() in sound/pci/*") Signed-off-by: Su Hui Link: https://lore.kernel.org/r/20230615021732.1972194-1-suhui@nfschina.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/ac97/ac97_codec.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c index cd66632bf1c3..e18572eae5e0 100644 --- a/sound/pci/ac97/ac97_codec.c +++ b/sound/pci/ac97/ac97_codec.c @@ -2007,8 +2007,8 @@ int snd_ac97_mixer(struct snd_ac97_bus *bus, struct snd_ac97_template *template, .dev_disconnect = snd_ac97_dev_disconnect, }; - if (rac97) - *rac97 = NULL; + if (!rac97) + return -EINVAL; if (snd_BUG_ON(!bus || !template)) return -EINVAL; if (snd_BUG_ON(template->num >= 4)) From c3b63584d8c2aae2ff1d4f7cd0aa860568bfefcf Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 12 Jun 2023 21:25:33 +0300 Subject: [PATCH 3894/4345] drm/msm/dpu: do not enable color-management if DSPPs are not available [ Upstream commit 3bcfc7b90465efd337d39b91b43972162f0d1908 ] We can not support color management without DSPP blocks being provided in the HW catalog. Do not enable color management for CRTCs if num_dspps is 0. Fixes: 4259ff7ae509 ("drm/msm/dpu: add support for pcc color block in dpu driver") Reported-by: Yongqin Liu Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Reviewed-by: Marijn Suijten Reviewed-by: Sumit Semwal Tested-by: Yongqin Liu Patchwork: https://patchwork.freedesktop.org/patch/542141/ Link: https://lore.kernel.org/r/20230612182534.3345805-1-dmitry.baryshkov@linaro.org Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 5afb3c544653..4c64e2d4f650 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -1262,6 +1262,8 @@ static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = { struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane, struct drm_plane *cursor) { + struct msm_drm_private *priv = dev->dev_private; + struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms); struct drm_crtc *crtc = NULL; struct dpu_crtc *dpu_crtc = NULL; int i; @@ -1293,7 +1295,8 @@ struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane, drm_crtc_helper_add(crtc, &dpu_crtc_helper_funcs); - drm_crtc_enable_color_mgmt(crtc, 0, true, 0); + if (dpu_kms->catalog->dspp_count) + drm_crtc_enable_color_mgmt(crtc, 0, true, 0); /* save user friendly CRTC name for later */ snprintf(dpu_crtc->name, DPU_CRTC_NAME_SIZE, "crtc%u", crtc->base.id); From c67a55f7cc8d767d624235bf1bcd0947e56abe0f Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 12 Jun 2023 15:02:59 -0700 Subject: [PATCH 3895/4345] drm/msm/dp: Free resources after unregistering them [ Upstream commit fa0048a4b1fa7a50c8b0e514f5b428abdf69a6f8 ] The DP component's unbind operation walks through the submodules to unregister and clean things up. But if the unbind happens because the DP controller itself is being removed, all the memory for those submodules has just been freed. Change the order of these operations to avoid the many use-after-free that otherwise happens in this code path. Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support") Signed-off-by: Bjorn Andersson Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/542166/ Link: https://lore.kernel.org/r/20230612220259.1884381-1-quic_bjorande@quicinc.com Signed-off-by: Dmitry Baryshkov Signed-off-by: Sasha Levin --- drivers/gpu/drm/msm/dp/dp_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 0bcccf422192..4da8cea76a11 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -1267,9 +1267,9 @@ static int dp_display_remove(struct platform_device *pdev) dp = container_of(g_dp_display, struct dp_display_private, dp_display); + component_del(&pdev->dev, &dp_display_comp_ops); dp_display_deinit_sub_modules(dp); - component_del(&pdev->dev, &dp_display_comp_ops); platform_set_drvdata(pdev, NULL); return 0; From 866d4340c6c994768ecfa5da5c96e87996304ea6 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 30 May 2023 12:39:06 +0300 Subject: [PATCH 3896/4345] clk: vc5: check memory returned by kasprintf() [ Upstream commit 144601f6228de5598f03e693822b60a95c367a17 ] kasprintf() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: f491276a5168 ("clk: vc5: Allow Versaclock driver to support multiple instances") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230530093913.1656095-2-claudiu.beznea@microchip.com Reviewed-by: Luca Ceresoli Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/clk-versaclock5.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/drivers/clk/clk-versaclock5.c b/drivers/clk/clk-versaclock5.c index eb597ea7bb87..3ddb974da039 100644 --- a/drivers/clk/clk-versaclock5.c +++ b/drivers/clk/clk-versaclock5.c @@ -906,6 +906,11 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id) } init.name = kasprintf(GFP_KERNEL, "%pOFn.mux", client->dev.of_node); + if (!init.name) { + ret = -ENOMEM; + goto err_clk; + } + init.ops = &vc5_mux_ops; init.flags = 0; init.parent_names = parent_names; @@ -920,6 +925,10 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id) memset(&init, 0, sizeof(init)); init.name = kasprintf(GFP_KERNEL, "%pOFn.dbl", client->dev.of_node); + if (!init.name) { + ret = -ENOMEM; + goto err_clk; + } init.ops = &vc5_dbl_ops; init.flags = CLK_SET_RATE_PARENT; init.parent_names = parent_names; @@ -935,6 +944,10 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id) /* Register PFD */ memset(&init, 0, sizeof(init)); init.name = kasprintf(GFP_KERNEL, "%pOFn.pfd", client->dev.of_node); + if (!init.name) { + ret = -ENOMEM; + goto err_clk; + } init.ops = &vc5_pfd_ops; init.flags = CLK_SET_RATE_PARENT; init.parent_names = parent_names; @@ -952,6 +965,10 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id) /* Register PLL */ memset(&init, 0, sizeof(init)); init.name = kasprintf(GFP_KERNEL, "%pOFn.pll", client->dev.of_node); + if (!init.name) { + ret = -ENOMEM; + goto err_clk; + } init.ops = &vc5_pll_ops; init.flags = CLK_SET_RATE_PARENT; init.parent_names = parent_names; @@ -971,6 +988,10 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id) memset(&init, 0, sizeof(init)); init.name = kasprintf(GFP_KERNEL, "%pOFn.fod%d", client->dev.of_node, idx); + if (!init.name) { + ret = -ENOMEM; + goto err_clk; + } init.ops = &vc5_fod_ops; init.flags = CLK_SET_RATE_PARENT; init.parent_names = parent_names; @@ -989,6 +1010,10 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id) memset(&init, 0, sizeof(init)); init.name = kasprintf(GFP_KERNEL, "%pOFn.out0_sel_i2cb", client->dev.of_node); + if (!init.name) { + ret = -ENOMEM; + goto err_clk; + } init.ops = &vc5_clk_out_ops; init.flags = CLK_SET_RATE_PARENT; init.parent_names = parent_names; @@ -1015,6 +1040,10 @@ static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id) memset(&init, 0, sizeof(init)); init.name = kasprintf(GFP_KERNEL, "%pOFn.out%d", client->dev.of_node, idx + 1); + if (!init.name) { + ret = -ENOMEM; + goto err_clk; + } init.ops = &vc5_clk_out_ops; init.flags = CLK_SET_RATE_PARENT; init.parent_names = parent_names; From f64fcd3acf1f93f7c21531d90bb029bd72300a3b Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 30 May 2023 12:39:07 +0300 Subject: [PATCH 3897/4345] clk: cdce925: check return value of kasprintf() [ Upstream commit bb7d09ddbf361d51eae46f38e7c8a2b85914ea2a ] kasprintf() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: 19fbbbbcd3a3 ("Add TI CDCE925 I2C controlled clock synthesizer driver") Depends-on: e665f029a283 ("clk: Convert to using %pOFn instead of device_node.name") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230530093913.1656095-3-claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/clk-cdce925.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/clk/clk-cdce925.c b/drivers/clk/clk-cdce925.c index 308b353815e1..470d91d7314d 100644 --- a/drivers/clk/clk-cdce925.c +++ b/drivers/clk/clk-cdce925.c @@ -705,6 +705,10 @@ static int cdce925_probe(struct i2c_client *client, for (i = 0; i < data->chip_info->num_plls; ++i) { pll_clk_name[i] = kasprintf(GFP_KERNEL, "%pOFn.pll%d", client->dev.of_node, i); + if (!pll_clk_name[i]) { + err = -ENOMEM; + goto error; + } init.name = pll_clk_name[i]; data->pll[i].chip = data; data->pll[i].hw.init = &init; @@ -746,6 +750,10 @@ static int cdce925_probe(struct i2c_client *client, init.num_parents = 1; init.parent_names = &parent_name; /* Mux Y1 to input */ init.name = kasprintf(GFP_KERNEL, "%pOFn.Y1", client->dev.of_node); + if (!init.name) { + err = -ENOMEM; + goto error; + } data->clk[0].chip = data; data->clk[0].hw.init = &init; data->clk[0].index = 0; @@ -764,6 +772,10 @@ static int cdce925_probe(struct i2c_client *client, for (i = 1; i < data->chip_info->num_outputs; ++i) { init.name = kasprintf(GFP_KERNEL, "%pOFn.Y%d", client->dev.of_node, i+1); + if (!init.name) { + err = -ENOMEM; + goto error; + } data->clk[i].chip = data; data->clk[i].hw.init = &init; data->clk[i].index = i; From fc813d05739ec5ae8f67f73488dbfb9de827acb9 Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Thu, 25 Mar 2021 13:26:40 -0600 Subject: [PATCH 3898/4345] clk: si5341: Allow different output VDD_SEL values [ Upstream commit b7bbf6ec4940d1a69811ec354edeeb9751fa8e85 ] The driver was not previously programming the VDD_SEL values for each output to indicate what external VDDO voltage was used for each. Add ability to specify a regulator supplying the VDDO pin for each output of the device. The voltage of the regulator is used to automatically set the VDD_SEL value appropriately. If no regulator is specified and the chip is being reconfigured, assume 2.5V which appears to be the chip default. Signed-off-by: Robert Hancock Link: https://lore.kernel.org/r/20210325192643.2190069-7-robert.hancock@calian.com Signed-off-by: Stephen Boyd Stable-dep-of: 2560114c06d7 ("clk: si5341: return error if one synth clock registration fails") Signed-off-by: Sasha Levin --- drivers/clk/clk-si5341.c | 136 +++++++++++++++++++++++++++++++-------- 1 file changed, 110 insertions(+), 26 deletions(-) diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c index 382a0619a048..64d962c54bba 100644 --- a/drivers/clk/clk-si5341.c +++ b/drivers/clk/clk-si5341.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -59,6 +60,7 @@ struct clk_si5341_synth { struct clk_si5341_output { struct clk_hw hw; struct clk_si5341 *data; + struct regulator *vddo_reg; u8 index; }; #define to_clk_si5341_output(_hw) \ @@ -84,6 +86,7 @@ struct clk_si5341 { struct clk_si5341_output_config { u8 out_format_drv_bits; u8 out_cm_ampl_bits; + u8 vdd_sel_bits; bool synth_master; bool always_on; }; @@ -136,6 +139,8 @@ struct clk_si5341_output_config { #define SI5341_OUT_R_REG(output) \ ((output)->data->reg_rdiv_offset[(output)->index]) +#define SI5341_OUT_MUX_VDD_SEL_MASK 0x38 + /* Synthesize N divider */ #define SI5341_SYNTH_N_NUM(x) (0x0302 + ((x) * 11)) #define SI5341_SYNTH_N_DEN(x) (0x0308 + ((x) * 11)) @@ -1250,11 +1255,11 @@ static const struct regmap_config si5341_regmap_config = { .volatile_table = &si5341_regmap_volatile, }; -static int si5341_dt_parse_dt(struct i2c_client *client, - struct clk_si5341_output_config *config) +static int si5341_dt_parse_dt(struct clk_si5341 *data, + struct clk_si5341_output_config *config) { struct device_node *child; - struct device_node *np = client->dev.of_node; + struct device_node *np = data->i2c_client->dev.of_node; u32 num; u32 val; @@ -1263,13 +1268,13 @@ static int si5341_dt_parse_dt(struct i2c_client *client, for_each_child_of_node(np, child) { if (of_property_read_u32(child, "reg", &num)) { - dev_err(&client->dev, "missing reg property of %s\n", + dev_err(&data->i2c_client->dev, "missing reg property of %s\n", child->name); goto put_child; } if (num >= SI5341_MAX_NUM_OUTPUTS) { - dev_err(&client->dev, "invalid clkout %d\n", num); + dev_err(&data->i2c_client->dev, "invalid clkout %d\n", num); goto put_child; } @@ -1288,7 +1293,7 @@ static int si5341_dt_parse_dt(struct i2c_client *client, config[num].out_format_drv_bits |= 0xc0; break; default: - dev_err(&client->dev, + dev_err(&data->i2c_client->dev, "invalid silabs,format %u for %u\n", val, num); goto put_child; @@ -1301,7 +1306,7 @@ static int si5341_dt_parse_dt(struct i2c_client *client, if (!of_property_read_u32(child, "silabs,common-mode", &val)) { if (val > 0xf) { - dev_err(&client->dev, + dev_err(&data->i2c_client->dev, "invalid silabs,common-mode %u\n", val); goto put_child; @@ -1312,7 +1317,7 @@ static int si5341_dt_parse_dt(struct i2c_client *client, if (!of_property_read_u32(child, "silabs,amplitude", &val)) { if (val > 0xf) { - dev_err(&client->dev, + dev_err(&data->i2c_client->dev, "invalid silabs,amplitude %u\n", val); goto put_child; @@ -1329,6 +1334,34 @@ static int si5341_dt_parse_dt(struct i2c_client *client, config[num].always_on = of_property_read_bool(child, "always-on"); + + config[num].vdd_sel_bits = 0x08; + if (data->clk[num].vddo_reg) { + int vdd = regulator_get_voltage(data->clk[num].vddo_reg); + + switch (vdd) { + case 3300000: + config[num].vdd_sel_bits |= 0 << 4; + break; + case 1800000: + config[num].vdd_sel_bits |= 1 << 4; + break; + case 2500000: + config[num].vdd_sel_bits |= 2 << 4; + break; + default: + dev_err(&data->i2c_client->dev, + "unsupported vddo voltage %d for %s\n", + vdd, child->name); + goto put_child; + } + } else { + /* chip seems to default to 2.5V when not set */ + dev_warn(&data->i2c_client->dev, + "no regulator set, defaulting vdd_sel to 2.5V for %s\n", + child->name); + config[num].vdd_sel_bits |= 2 << 4; + } } return 0; @@ -1454,9 +1487,33 @@ static int si5341_probe(struct i2c_client *client, } } - err = si5341_dt_parse_dt(client, config); + for (i = 0; i < SI5341_MAX_NUM_OUTPUTS; ++i) { + char reg_name[10]; + + snprintf(reg_name, sizeof(reg_name), "vddo%d", i); + data->clk[i].vddo_reg = devm_regulator_get_optional( + &client->dev, reg_name); + if (IS_ERR(data->clk[i].vddo_reg)) { + err = PTR_ERR(data->clk[i].vddo_reg); + data->clk[i].vddo_reg = NULL; + if (err == -ENODEV) + continue; + goto cleanup; + } else { + err = regulator_enable(data->clk[i].vddo_reg); + if (err) { + dev_err(&client->dev, + "failed to enable %s regulator: %d\n", + reg_name, err); + data->clk[i].vddo_reg = NULL; + goto cleanup; + } + } + } + + err = si5341_dt_parse_dt(data, config); if (err) - return err; + goto cleanup; if (of_property_read_string(client->dev.of_node, "clock-output-names", &init.name)) @@ -1464,21 +1521,23 @@ static int si5341_probe(struct i2c_client *client, root_clock_name = init.name; data->regmap = devm_regmap_init_i2c(client, &si5341_regmap_config); - if (IS_ERR(data->regmap)) - return PTR_ERR(data->regmap); + if (IS_ERR(data->regmap)) { + err = PTR_ERR(data->regmap); + goto cleanup; + } i2c_set_clientdata(client, data); err = si5341_probe_chip_id(data); if (err < 0) - return err; + goto cleanup; if (of_property_read_bool(client->dev.of_node, "silabs,reprogram")) { initialization_required = true; } else { err = si5341_is_programmed_already(data); if (err < 0) - return err; + goto cleanup; initialization_required = !err; } @@ -1487,11 +1546,11 @@ static int si5341_probe(struct i2c_client *client, /* Populate the regmap cache in preparation for "cache only" */ err = si5341_read_settings(data); if (err < 0) - return err; + goto cleanup; err = si5341_send_preamble(data); if (err < 0) - return err; + goto cleanup; /* * We intend to send all 'final' register values in a single @@ -1504,19 +1563,19 @@ static int si5341_probe(struct i2c_client *client, err = si5341_write_multiple(data, si5341_reg_defaults, ARRAY_SIZE(si5341_reg_defaults)); if (err < 0) - return err; + goto cleanup; } /* Input must be up and running at this point */ err = si5341_clk_select_active_input(data); if (err < 0) - return err; + goto cleanup; if (initialization_required) { /* PLL configuration is required */ err = si5341_initialize_pll(data); if (err < 0) - return err; + goto cleanup; } /* Register the PLL */ @@ -1529,7 +1588,7 @@ static int si5341_probe(struct i2c_client *client, err = devm_clk_hw_register(&client->dev, &data->hw); if (err) { dev_err(&client->dev, "clock registration failed\n"); - return err; + goto cleanup; } init.num_parents = 1; @@ -1566,13 +1625,17 @@ static int si5341_probe(struct i2c_client *client, regmap_write(data->regmap, SI5341_OUT_CM(&data->clk[i]), config[i].out_cm_ampl_bits); + regmap_update_bits(data->regmap, + SI5341_OUT_MUX_SEL(&data->clk[i]), + SI5341_OUT_MUX_VDD_SEL_MASK, + config[i].vdd_sel_bits); } err = devm_clk_hw_register(&client->dev, &data->clk[i].hw); kfree(init.name); /* clock framework made a copy of the name */ if (err) { dev_err(&client->dev, "output %u registration failed\n", i); - return err; + goto cleanup; } if (config[i].always_on) clk_prepare(data->clk[i].hw.clk); @@ -1582,7 +1645,7 @@ static int si5341_probe(struct i2c_client *client, data); if (err) { dev_err(&client->dev, "unable to add clk provider\n"); - return err; + goto cleanup; } if (initialization_required) { @@ -1590,11 +1653,11 @@ static int si5341_probe(struct i2c_client *client, regcache_cache_only(data->regmap, false); err = regcache_sync(data->regmap); if (err < 0) - return err; + goto cleanup; err = si5341_finalize_defaults(data); if (err < 0) - return err; + goto cleanup; } /* wait for device to report input clock present and PLL lock */ @@ -1603,14 +1666,14 @@ static int si5341_probe(struct i2c_client *client, 10000, 250000); if (err) { dev_err(&client->dev, "Error waiting for input clock or PLL lock\n"); - return err; + goto cleanup; } /* clear sticky alarm bits from initialization */ err = regmap_write(data->regmap, SI5341_STATUS_STICKY, 0); if (err) { dev_err(&client->dev, "unable to clear sticky status\n"); - return err; + goto cleanup; } /* Free the names, clk framework makes copies */ @@ -1618,6 +1681,26 @@ static int si5341_probe(struct i2c_client *client, devm_kfree(&client->dev, (void *)synth_clock_names[i]); return 0; + +cleanup: + for (i = 0; i < SI5341_MAX_NUM_OUTPUTS; ++i) { + if (data->clk[i].vddo_reg) + regulator_disable(data->clk[i].vddo_reg); + } + return err; +} + +static int si5341_remove(struct i2c_client *client) +{ + struct clk_si5341 *data = i2c_get_clientdata(client); + int i; + + for (i = 0; i < SI5341_MAX_NUM_OUTPUTS; ++i) { + if (data->clk[i].vddo_reg) + regulator_disable(data->clk[i].vddo_reg); + } + + return 0; } static const struct i2c_device_id si5341_id[] = { @@ -1646,6 +1729,7 @@ static struct i2c_driver si5341_driver = { .of_match_table = clk_si5341_of_match, }, .probe = si5341_probe, + .remove = si5341_remove, .id_table = si5341_id, }; module_i2c_driver(si5341_driver); From 040113980081eed26e431cb5dc5a2c183107ad61 Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Thu, 25 Mar 2021 13:26:43 -0600 Subject: [PATCH 3899/4345] clk: si5341: Add sysfs properties to allow checking/resetting device faults [ Upstream commit 9b13ff4340dff30f361462999a6a122fcc4e473f ] Add sysfs property files to allow viewing the current and latched states of the input present and PLL lock bits, and allow resetting the latched fault state. This allows manual checks or automated userspace polling for faults occurring after initialization. Signed-off-by: Robert Hancock Link: https://lore.kernel.org/r/20210325192643.2190069-10-robert.hancock@calian.com Signed-off-by: Stephen Boyd Stable-dep-of: 2560114c06d7 ("clk: si5341: return error if one synth clock registration fails") Signed-off-by: Sasha Levin --- drivers/clk/clk-si5341.c | 96 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c index 64d962c54bba..5175b3024f06 100644 --- a/drivers/clk/clk-si5341.c +++ b/drivers/clk/clk-si5341.c @@ -1450,6 +1450,94 @@ static int si5341_clk_select_active_input(struct clk_si5341 *data) return res; } +static ssize_t input_present_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct clk_si5341 *data = dev_get_drvdata(dev); + u32 status; + int res = regmap_read(data->regmap, SI5341_STATUS, &status); + + if (res < 0) + return res; + res = !(status & SI5341_STATUS_LOSREF); + return snprintf(buf, PAGE_SIZE, "%d\n", res); +} +static DEVICE_ATTR_RO(input_present); + +static ssize_t input_present_sticky_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct clk_si5341 *data = dev_get_drvdata(dev); + u32 status; + int res = regmap_read(data->regmap, SI5341_STATUS_STICKY, &status); + + if (res < 0) + return res; + res = !(status & SI5341_STATUS_LOSREF); + return snprintf(buf, PAGE_SIZE, "%d\n", res); +} +static DEVICE_ATTR_RO(input_present_sticky); + +static ssize_t pll_locked_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct clk_si5341 *data = dev_get_drvdata(dev); + u32 status; + int res = regmap_read(data->regmap, SI5341_STATUS, &status); + + if (res < 0) + return res; + res = !(status & SI5341_STATUS_LOL); + return snprintf(buf, PAGE_SIZE, "%d\n", res); +} +static DEVICE_ATTR_RO(pll_locked); + +static ssize_t pll_locked_sticky_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct clk_si5341 *data = dev_get_drvdata(dev); + u32 status; + int res = regmap_read(data->regmap, SI5341_STATUS_STICKY, &status); + + if (res < 0) + return res; + res = !(status & SI5341_STATUS_LOL); + return snprintf(buf, PAGE_SIZE, "%d\n", res); +} +static DEVICE_ATTR_RO(pll_locked_sticky); + +static ssize_t clear_sticky_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct clk_si5341 *data = dev_get_drvdata(dev); + long val; + + if (kstrtol(buf, 10, &val)) + return -EINVAL; + if (val) { + int res = regmap_write(data->regmap, SI5341_STATUS_STICKY, 0); + + if (res < 0) + return res; + } + return count; +} +static DEVICE_ATTR_WO(clear_sticky); + +static const struct attribute *si5341_attributes[] = { + &dev_attr_input_present.attr, + &dev_attr_input_present_sticky.attr, + &dev_attr_pll_locked.attr, + &dev_attr_pll_locked_sticky.attr, + &dev_attr_clear_sticky.attr, + NULL +}; + static int si5341_probe(struct i2c_client *client, const struct i2c_device_id *id) { @@ -1676,6 +1764,12 @@ static int si5341_probe(struct i2c_client *client, goto cleanup; } + err = sysfs_create_files(&client->dev.kobj, si5341_attributes); + if (err) { + dev_err(&client->dev, "unable to create sysfs files\n"); + goto cleanup; + } + /* Free the names, clk framework makes copies */ for (i = 0; i < data->num_synth; ++i) devm_kfree(&client->dev, (void *)synth_clock_names[i]); @@ -1695,6 +1789,8 @@ static int si5341_remove(struct i2c_client *client) struct clk_si5341 *data = i2c_get_clientdata(client); int i; + sysfs_remove_files(&client->dev.kobj, si5341_attributes); + for (i = 0; i < SI5341_MAX_NUM_OUTPUTS; ++i) { if (data->clk[i].vddo_reg) regulator_disable(data->clk[i].vddo_reg); From dc3eef64805531b56acdeb2fd9512b85478e4407 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 30 May 2023 12:39:08 +0300 Subject: [PATCH 3900/4345] clk: si5341: return error if one synth clock registration fails [ Upstream commit 2560114c06d7a752b3f4639f28cece58fed11267 ] In case devm_clk_hw_register() fails for one of synth clocks the probe continues. Later on, when registering output clocks which have as parents all the synth clocks, in case there is registration failure for at least one synth clock the information passed to clk core for registering output clock is not right: init.num_parents is fixed but init.parents may contain an array with less parents. Fixes: 3044a860fd09 ("clk: Add Si5341/Si5340 driver") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230530093913.1656095-4-claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/clk-si5341.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c index 5175b3024f06..baa5e2ad2266 100644 --- a/drivers/clk/clk-si5341.c +++ b/drivers/clk/clk-si5341.c @@ -1545,7 +1545,7 @@ static int si5341_probe(struct i2c_client *client, struct clk_init_data init; struct clk *input; const char *root_clock_name; - const char *synth_clock_names[SI5341_NUM_SYNTH]; + const char *synth_clock_names[SI5341_NUM_SYNTH] = { NULL }; int err; unsigned int i; struct clk_si5341_output_config config[SI5341_MAX_NUM_OUTPUTS]; @@ -1693,6 +1693,7 @@ static int si5341_probe(struct i2c_client *client, if (err) { dev_err(&client->dev, "synth N%u registration failed\n", i); + goto free_clk_names; } } @@ -1770,16 +1771,17 @@ static int si5341_probe(struct i2c_client *client, goto cleanup; } +free_clk_names: /* Free the names, clk framework makes copies */ for (i = 0; i < data->num_synth; ++i) devm_kfree(&client->dev, (void *)synth_clock_names[i]); - return 0; - cleanup: - for (i = 0; i < SI5341_MAX_NUM_OUTPUTS; ++i) { - if (data->clk[i].vddo_reg) - regulator_disable(data->clk[i].vddo_reg); + if (err) { + for (i = 0; i < SI5341_MAX_NUM_OUTPUTS; ++i) { + if (data->clk[i].vddo_reg) + regulator_disable(data->clk[i].vddo_reg); + } } return err; } From dc8d0178d50649861d9681e7c736d8ccb4725a1a Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 30 May 2023 12:39:09 +0300 Subject: [PATCH 3901/4345] clk: si5341: check return value of {devm_}kasprintf() [ Upstream commit 36e4ef82016a2b785cf2317eade77e76699b7bff ] {devm_}kasprintf() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: 3044a860fd09 ("clk: Add Si5341/Si5340 driver") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230530093913.1656095-5-claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/clk-si5341.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c index baa5e2ad2266..af66097f9ac5 100644 --- a/drivers/clk/clk-si5341.c +++ b/drivers/clk/clk-si5341.c @@ -1685,6 +1685,10 @@ static int si5341_probe(struct i2c_client *client, for (i = 0; i < data->num_synth; ++i) { synth_clock_names[i] = devm_kasprintf(&client->dev, GFP_KERNEL, "%s.N%u", client->dev.of_node->name, i); + if (!synth_clock_names[i]) { + err = -ENOMEM; + goto free_clk_names; + } init.name = synth_clock_names[i]; data->synth[i].index = i; data->synth[i].data = data; @@ -1703,6 +1707,10 @@ static int si5341_probe(struct i2c_client *client, for (i = 0; i < data->num_outputs; ++i) { init.name = kasprintf(GFP_KERNEL, "%s.%d", client->dev.of_node->name, i); + if (!init.name) { + err = -ENOMEM; + goto free_clk_names; + } init.flags = config[i].synth_master ? CLK_SET_RATE_PARENT : 0; data->clk[i].index = i; data->clk[i].data = data; From 0b754f9cfd66314175059c66118a717bf0542284 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 30 May 2023 12:39:10 +0300 Subject: [PATCH 3902/4345] clk: si5341: free unused memory on probe failure [ Upstream commit 267ad94b13c53d8c99a336f0841b1fa1595b1d0f ] Pointers from synth_clock_names[] should be freed at the end of probe either on probe success or failure path. Fixes: b7bbf6ec4940 ("clk: si5341: Allow different output VDD_SEL values") Fixes: 9b13ff4340df ("clk: si5341: Add sysfs properties to allow checking/resetting device faults") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230530093913.1656095-6-claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/clk-si5341.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c index af66097f9ac5..4dea29fa901d 100644 --- a/drivers/clk/clk-si5341.c +++ b/drivers/clk/clk-si5341.c @@ -1732,7 +1732,7 @@ static int si5341_probe(struct i2c_client *client, if (err) { dev_err(&client->dev, "output %u registration failed\n", i); - goto cleanup; + goto free_clk_names; } if (config[i].always_on) clk_prepare(data->clk[i].hw.clk); @@ -1742,7 +1742,7 @@ static int si5341_probe(struct i2c_client *client, data); if (err) { dev_err(&client->dev, "unable to add clk provider\n"); - goto cleanup; + goto free_clk_names; } if (initialization_required) { @@ -1750,11 +1750,11 @@ static int si5341_probe(struct i2c_client *client, regcache_cache_only(data->regmap, false); err = regcache_sync(data->regmap); if (err < 0) - goto cleanup; + goto free_clk_names; err = si5341_finalize_defaults(data); if (err < 0) - goto cleanup; + goto free_clk_names; } /* wait for device to report input clock present and PLL lock */ @@ -1763,21 +1763,19 @@ static int si5341_probe(struct i2c_client *client, 10000, 250000); if (err) { dev_err(&client->dev, "Error waiting for input clock or PLL lock\n"); - goto cleanup; + goto free_clk_names; } /* clear sticky alarm bits from initialization */ err = regmap_write(data->regmap, SI5341_STATUS_STICKY, 0); if (err) { dev_err(&client->dev, "unable to clear sticky status\n"); - goto cleanup; + goto free_clk_names; } err = sysfs_create_files(&client->dev.kobj, si5341_attributes); - if (err) { + if (err) dev_err(&client->dev, "unable to create sysfs files\n"); - goto cleanup; - } free_clk_names: /* Free the names, clk framework makes copies */ From fd9324fa4d81efe80800da027b084d670adde7b9 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 30 May 2023 12:39:11 +0300 Subject: [PATCH 3903/4345] clk: keystone: sci-clk: check return value of kasprintf() [ Upstream commit b73ed981da6d25c921aaefa7ca3df85bbd85b7fc ] kasprintf() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: b745c0794e2f ("clk: keystone: Add sci-clk driver support") Depends-on: 96488c09b0f4 ("clk: keystone: sci-clk: cut down the clock name length") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230530093913.1656095-7-claudiu.beznea@microchip.com Reviewed-by: Tony Lindgren Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/keystone/sci-clk.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/keystone/sci-clk.c b/drivers/clk/keystone/sci-clk.c index 7e1b136e71ae..8af2a9faa805 100644 --- a/drivers/clk/keystone/sci-clk.c +++ b/drivers/clk/keystone/sci-clk.c @@ -302,6 +302,8 @@ static int _sci_clk_build(struct sci_clk_provider *provider, name = kasprintf(GFP_KERNEL, "clk:%d:%d", sci_clk->dev_id, sci_clk->clk_id); + if (!name) + return -ENOMEM; init.name = name; From 5f149d053898f8978ad95be8cbb916c0a173f61c Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 30 May 2023 12:39:12 +0300 Subject: [PATCH 3904/4345] clk: ti: clkctrl: check return value of kasprintf() [ Upstream commit bd46cd0b802d9c9576ca78007aa084ae3e74907b ] kasprintf() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: 852049594b9a ("clk: ti: clkctrl: convert subclocks to use proper names also") Fixes: 6c3090520554 ("clk: ti: clkctrl: Fix hidden dependency to node name") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230530093913.1656095-8-claudiu.beznea@microchip.com Reviewed-by: Tony Lindgren Signed-off-by: Stephen Boyd Signed-off-by: Sasha Levin --- drivers/clk/ti/clkctrl.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index 864c484bde1b..157abc46dcf4 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -267,6 +267,9 @@ static const char * __init clkctrl_get_clock_name(struct device_node *np, if (clkctrl_name && !legacy_naming) { clock_name = kasprintf(GFP_KERNEL, "%s-clkctrl:%04x:%d", clkctrl_name, offset, index); + if (!clock_name) + return NULL; + strreplace(clock_name, '_', '-'); return clock_name; @@ -598,6 +601,10 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node) if (clkctrl_name) { provider->clkdm_name = kasprintf(GFP_KERNEL, "%s_clkdm", clkctrl_name); + if (!provider->clkdm_name) { + kfree(provider); + return; + } goto clkdm_found; } From 47f4d875aa54d613956b14c9a81bf5f8febb3c16 Mon Sep 17 00:00:00 2001 From: Alexey Romanov Date: Sat, 10 Jun 2023 12:04:14 +0300 Subject: [PATCH 3905/4345] drivers: meson: secure-pwrc: always enable DMA domain [ Upstream commit 0bb4644d583789c97e74d3e3047189f0c59c4742 ] Starting from commit e45f243409db ("firmware: meson_sm: populate platform devices from sm device tree data") pwrc is probed successfully and disables unused pwr domains. By A1 SoC family design, any TEE requires DMA pwr domain always enabled. Fixes: b3dde5013e13 ("soc: amlogic: Add support for Secure power domains controller") Signed-off-by: Alexey Romanov Acked-by: Neil Armstrong Link: https://lore.kernel.org/r/20230610090414.90529-1-avromanov@sberdevices.ru [narmstrong: added fixes tag] Signed-off-by: Neil Armstrong Signed-off-by: Sasha Levin --- drivers/soc/amlogic/meson-secure-pwrc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/amlogic/meson-secure-pwrc.c b/drivers/soc/amlogic/meson-secure-pwrc.c index fff92e2f3974..090a32666475 100644 --- a/drivers/soc/amlogic/meson-secure-pwrc.c +++ b/drivers/soc/amlogic/meson-secure-pwrc.c @@ -103,7 +103,7 @@ static struct meson_secure_pwrc_domain_desc a1_pwrc_domains[] = { SEC_PD(ACODEC, 0), SEC_PD(AUDIO, 0), SEC_PD(OTP, 0), - SEC_PD(DMA, 0), + SEC_PD(DMA, GENPD_FLAG_ALWAYS_ON | GENPD_FLAG_IRQ_SAFE), SEC_PD(SD_EMMC, 0), SEC_PD(RAMA, 0), /* SRAMB is used as ATF runtime memory, and should be always on */ From 714ba10a6dd19752a349e59aa875f3288ccb59b9 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 3 Apr 2023 11:29:59 +0300 Subject: [PATCH 3906/4345] ovl: update of dentry revalidate flags after copy up [ Upstream commit b07d5cc93e1b28df47a72c519d09d0a836043613 ] After copy up, we may need to update d_flags if upper dentry is on a remote fs and lower dentries are not. Add helpers to allow incremental update of the revalidate flags. Fixes: bccece1ead36 ("ovl: allow remote upper") Reviewed-by: Gao Xiang Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi Signed-off-by: Sasha Levin --- fs/overlayfs/copy_up.c | 2 ++ fs/overlayfs/dir.c | 3 +-- fs/overlayfs/export.c | 3 +-- fs/overlayfs/namei.c | 3 +-- fs/overlayfs/overlayfs.h | 6 ++++-- fs/overlayfs/super.c | 2 +- fs/overlayfs/util.c | 24 ++++++++++++++++++++---- 7 files changed, 30 insertions(+), 13 deletions(-) diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index e466c58f9ec4..7ef3c87f8a23 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -475,6 +475,7 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) /* Restore timestamps on parent (best effort) */ ovl_set_timestamps(upperdir, &c->pstat); ovl_dentry_set_upper_alias(c->dentry); + ovl_dentry_update_reval(c->dentry, upper); } } inode_unlock(udir); @@ -762,6 +763,7 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) inode_unlock(udir); ovl_dentry_set_upper_alias(c->dentry); + ovl_dentry_update_reval(c->dentry, ovl_dentry_upper(c->dentry)); } out: diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 8ebd9f2b1c95..a7021c87bfcb 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -266,8 +266,7 @@ static int ovl_instantiate(struct dentry *dentry, struct inode *inode, ovl_dir_modified(dentry->d_parent, false); ovl_dentry_set_upper_alias(dentry); - ovl_dentry_update_reval(dentry, newdentry, - DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); + ovl_dentry_init_reval(dentry, newdentry); if (!hardlink) { /* diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 44118f0ab0b3..f981283177ec 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -324,8 +324,7 @@ static struct dentry *ovl_obtain_alias(struct super_block *sb, if (upper_alias) ovl_dentry_set_upper_alias(dentry); - ovl_dentry_update_reval(dentry, upper, - DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); + ovl_dentry_init_reval(dentry, upper); return d_instantiate_anon(dentry, inode); diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 092812c2f118..ff5284b86bd5 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -1095,8 +1095,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, ovl_set_flag(OVL_UPPERDATA, inode); } - ovl_dentry_update_reval(dentry, upperdentry, - DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); + ovl_dentry_init_reval(dentry, upperdentry); revert_creds(old_cred); if (origin_path) { diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 898de3bf884e..26f91868fbda 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -257,8 +257,10 @@ bool ovl_index_all(struct super_block *sb); bool ovl_verify_lower(struct super_block *sb); struct ovl_entry *ovl_alloc_entry(unsigned int numlower); bool ovl_dentry_remote(struct dentry *dentry); -void ovl_dentry_update_reval(struct dentry *dentry, struct dentry *upperdentry, - unsigned int mask); +void ovl_dentry_update_reval(struct dentry *dentry, struct dentry *realdentry); +void ovl_dentry_init_reval(struct dentry *dentry, struct dentry *upperdentry); +void ovl_dentry_init_flags(struct dentry *dentry, struct dentry *upperdentry, + unsigned int mask); bool ovl_dentry_weird(struct dentry *dentry); enum ovl_path_type ovl_path_type(struct dentry *dentry); void ovl_path_upper(struct dentry *dentry, struct path *path); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e3cd5a00f880..5d7df839902d 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1868,7 +1868,7 @@ static struct dentry *ovl_get_root(struct super_block *sb, ovl_dentry_set_flag(OVL_E_CONNECTED, root); ovl_set_upperdata(d_inode(root)); ovl_inode_init(d_inode(root), &oip, ino, fsid); - ovl_dentry_update_reval(root, upperdentry, DCACHE_OP_WEAK_REVALIDATE); + ovl_dentry_init_flags(root, upperdentry, DCACHE_OP_WEAK_REVALIDATE); return root; } diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index e8b14d2c180c..060f9c99d9b3 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -90,14 +90,30 @@ struct ovl_entry *ovl_alloc_entry(unsigned int numlower) return oe; } +#define OVL_D_REVALIDATE (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE) + bool ovl_dentry_remote(struct dentry *dentry) { - return dentry->d_flags & - (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE); + return dentry->d_flags & OVL_D_REVALIDATE; } -void ovl_dentry_update_reval(struct dentry *dentry, struct dentry *upperdentry, - unsigned int mask) +void ovl_dentry_update_reval(struct dentry *dentry, struct dentry *realdentry) +{ + if (!ovl_dentry_remote(realdentry)) + return; + + spin_lock(&dentry->d_lock); + dentry->d_flags |= realdentry->d_flags & OVL_D_REVALIDATE; + spin_unlock(&dentry->d_lock); +} + +void ovl_dentry_init_reval(struct dentry *dentry, struct dentry *upperdentry) +{ + return ovl_dentry_init_flags(dentry, upperdentry, OVL_D_REVALIDATE); +} + +void ovl_dentry_init_flags(struct dentry *dentry, struct dentry *upperdentry, + unsigned int mask) { struct ovl_entry *oe = OVL_E(dentry); unsigned int i, flags = 0; From 07be8e60f27f095942608c4cc6ff474a4326f6c6 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Wed, 14 Jun 2023 15:15:09 +0300 Subject: [PATCH 3907/4345] ASoC: imx-audmix: check return value of devm_kasprintf() [ Upstream commit 2f76e1d6ca524a888d29aafe29f2ad2003857971 ] devm_kasprintf() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: b86ef5367761 ("ASoC: fsl: Add Audio Mixer machine driver") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230614121509.443926-1-claudiu.beznea@microchip.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/fsl/imx-audmix.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c index cbdc0a2c09c5..77d8234c7ac4 100644 --- a/sound/soc/fsl/imx-audmix.c +++ b/sound/soc/fsl/imx-audmix.c @@ -230,6 +230,8 @@ static int imx_audmix_probe(struct platform_device *pdev) dai_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s%s", fe_name_pref, args.np->full_name + 1); + if (!dai_name) + return -ENOMEM; dev_info(pdev->dev.parent, "DAI FE name:%s\n", dai_name); @@ -238,6 +240,8 @@ static int imx_audmix_probe(struct platform_device *pdev) capture_dai_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s %s", dai_name, "CPU-Capture"); + if (!capture_dai_name) + return -ENOMEM; } priv->dai[i].cpus = &dlc[0]; @@ -268,6 +272,8 @@ static int imx_audmix_probe(struct platform_device *pdev) "AUDMIX-Playback-%d", i); be_cp = devm_kasprintf(&pdev->dev, GFP_KERNEL, "AUDMIX-Capture-%d", i); + if (!be_name || !be_pb || !be_cp) + return -ENOMEM; priv->dai[num_dai + i].cpus = &dlc[3]; priv->dai[num_dai + i].codecs = &dlc[4]; @@ -295,6 +301,9 @@ static int imx_audmix_probe(struct platform_device *pdev) priv->dapm_routes[i].source = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s %s", dai_name, "CPU-Playback"); + if (!priv->dapm_routes[i].source) + return -ENOMEM; + priv->dapm_routes[i].sink = be_pb; priv->dapm_routes[num_dai + i].source = be_pb; priv->dapm_routes[num_dai + i].sink = be_cp; From 8e9907e9219f3ee160e796cc8f7b8b41874e7dc0 Mon Sep 17 00:00:00 2001 From: Siddharth Vadapalli Date: Wed, 15 Mar 2023 12:38:00 +0530 Subject: [PATCH 3908/4345] PCI: cadence: Fix Gen2 Link Retraining process [ Upstream commit 0e12f830236928b6fadf40d917a7527f0a048d2f ] The Link Retraining process is initiated to account for the Gen2 defect in the Cadence PCIe controller in J721E SoC. The errata corresponding to this is i2085, documented at: https://www.ti.com/lit/er/sprz455c/sprz455c.pdf The existing workaround implemented for the errata waits for the Data Link initialization to complete and assumes that the link retraining process at the Physical Layer has completed. However, it is possible that the Physical Layer training might be ongoing as indicated by the PCI_EXP_LNKSTA_LT bit in the PCI_EXP_LNKSTA register. Fix the existing workaround, to ensure that the Physical Layer training has also completed, in addition to the Data Link initialization. Link: https://lore.kernel.org/r/20230315070800.1615527-1-s-vadapalli@ti.com Fixes: 4740b969aaf5 ("PCI: cadence: Retrain Link to work around Gen2 training defect") Signed-off-by: Siddharth Vadapalli Signed-off-by: Lorenzo Pieralisi Reviewed-by: Vignesh Raghavendra Signed-off-by: Sasha Levin --- .../controller/cadence/pcie-cadence-host.c | 27 +++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c index fb96d37a135c..4d8d15ac51ef 100644 --- a/drivers/pci/controller/cadence/pcie-cadence-host.c +++ b/drivers/pci/controller/cadence/pcie-cadence-host.c @@ -12,6 +12,8 @@ #include "pcie-cadence.h" +#define LINK_RETRAIN_TIMEOUT HZ + static u64 bar_max_size[] = { [RP_BAR0] = _ULL(128 * SZ_2G), [RP_BAR1] = SZ_2G, @@ -77,6 +79,27 @@ static struct pci_ops cdns_pcie_host_ops = { .write = pci_generic_config_write, }; +static int cdns_pcie_host_training_complete(struct cdns_pcie *pcie) +{ + u32 pcie_cap_off = CDNS_PCIE_RP_CAP_OFFSET; + unsigned long end_jiffies; + u16 lnk_stat; + + /* Wait for link training to complete. Exit after timeout. */ + end_jiffies = jiffies + LINK_RETRAIN_TIMEOUT; + do { + lnk_stat = cdns_pcie_rp_readw(pcie, pcie_cap_off + PCI_EXP_LNKSTA); + if (!(lnk_stat & PCI_EXP_LNKSTA_LT)) + break; + usleep_range(0, 1000); + } while (time_before(jiffies, end_jiffies)); + + if (!(lnk_stat & PCI_EXP_LNKSTA_LT)) + return 0; + + return -ETIMEDOUT; +} + static int cdns_pcie_host_wait_for_link(struct cdns_pcie *pcie) { struct device *dev = pcie->dev; @@ -118,6 +141,10 @@ static int cdns_pcie_retrain(struct cdns_pcie *pcie) cdns_pcie_rp_writew(pcie, pcie_cap_off + PCI_EXP_LNKCTL, lnk_ctl); + ret = cdns_pcie_host_training_complete(pcie); + if (ret) + return ret; + ret = cdns_pcie_host_wait_for_link(pcie); } return ret; From ac64019e4d4b08c23edb117e0b2590985e33de1d Mon Sep 17 00:00:00 2001 From: Jinhong Zhu Date: Tue, 2 May 2023 22:00:21 +0800 Subject: [PATCH 3909/4345] scsi: qedf: Fix NULL dereference in error handling [ Upstream commit f025312b089474a54e4859f3453771314d9e3d4f ] Smatch reported: drivers/scsi/qedf/qedf_main.c:3056 qedf_alloc_global_queues() warn: missing unwind goto? At this point in the function, nothing has been allocated so we can return directly. In particular the "qedf->global_queues" have not been allocated so calling qedf_free_global_queues() will lead to a NULL dereference when we check if (!gl[i]) and "gl" is NULL. Fixes: 61d8658b4a43 ("scsi: qedf: Add QLogic FastLinQ offload FCoE driver framework.") Signed-off-by: Jinhong Zhu Link: https://lore.kernel.org/r/20230502140022.2852-1-jinhongzhu@hust.edu.cn Reviewed-by: Dan Carpenter Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qedf/qedf_main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index f48ef47546f4..b33cb1172f31 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -3042,9 +3042,8 @@ static int qedf_alloc_global_queues(struct qedf_ctx *qedf) * addresses of our queues */ if (!qedf->p_cpuq) { - status = -EINVAL; QEDF_ERR(&qedf->dbg_ctx, "p_cpuq is NULL.\n"); - goto mem_alloc_failure; + return -EINVAL; } qedf->global_queues = kzalloc((sizeof(struct global_queue *) From d27238fc83b9042cad13b260a8b736b5431ad722 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 16 Apr 2023 23:43:41 +0200 Subject: [PATCH 3910/4345] pinctrl: bcm2835: Handle gpiochip_add_pin_range() errors [ Upstream commit cdf7e616120065007687fe1df0412154f259daec ] gpiochip_add_pin_range() can fail, so better return its error code than a hard coded '0'. Fixes: d2b67744fd99 ("pinctrl: bcm2835: implement hook for missing gpio-ranges") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/98c3b5890bb72415145c9fe4e1d974711edae376.1681681402.git.christophe.jaillet@wanadoo.fr Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/bcm/pinctrl-bcm2835.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index c7ae9f900b53..e3f49d0ed029 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -359,10 +359,8 @@ static int bcm2835_of_gpio_ranges_fallback(struct gpio_chip *gc, if (!pctldev) return 0; - gpiochip_add_pin_range(gc, pinctrl_dev_get_devname(pctldev), 0, 0, - gc->ngpio); - - return 0; + return gpiochip_add_pin_range(gc, pinctrl_dev_get_devname(pctldev), 0, 0, + gc->ngpio); } static const struct gpio_chip bcm2835_gpio_chip = { From 7badf4d6f49a358a01ab072bbff88d3ee886c33b Mon Sep 17 00:00:00 2001 From: Ding Hui Date: Sun, 7 May 2023 11:40:57 +0800 Subject: [PATCH 3911/4345] PCI/ASPM: Disable ASPM on MFD function removal to avoid use-after-free [ Upstream commit 456d8aa37d0f56fc9e985e812496e861dcd6f2f2 ] Struct pcie_link_state->downstream is a pointer to the pci_dev of function 0. Previously we retained that pointer when removing function 0, and subsequent ASPM policy changes dereferenced it, resulting in a use-after-free warning from KASAN, e.g.: # echo 1 > /sys/bus/pci/devices/0000:03:00.0/remove # echo powersave > /sys/module/pcie_aspm/parameters/policy BUG: KASAN: slab-use-after-free in pcie_config_aspm_link+0x42d/0x500 Call Trace: kasan_report+0xae/0xe0 pcie_config_aspm_link+0x42d/0x500 pcie_aspm_set_policy+0x8e/0x1a0 param_attr_store+0x162/0x2c0 module_attr_store+0x3e/0x80 PCIe spec r6.0, sec 7.5.3.7, recommends that software program the same ASPM Control value in all functions of multi-function devices. Disable ASPM and free the pcie_link_state when any child function is removed so we can discard the dangling pcie_link_state->downstream pointer and maintain the same ASPM Control configuration for all functions. [bhelgaas: commit log and comment] Debugged-by: Zongquan Qin Suggested-by: Bjorn Helgaas Fixes: b5a0a9b59c81 ("PCI/ASPM: Read and set up L1 substate capabilities") Link: https://lore.kernel.org/r/20230507034057.20970-1-dinghui@sangfor.com.cn Signed-off-by: Ding Hui Signed-off-by: Bjorn Helgaas Signed-off-by: Sasha Levin --- drivers/pci/pcie/aspm.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index ac0557a305af..51da8ba67d21 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -993,21 +993,24 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) down_read(&pci_bus_sem); mutex_lock(&aspm_lock); - /* - * All PCIe functions are in one slot, remove one function will remove - * the whole slot, so just wait until we are the last function left. - */ - if (!list_empty(&parent->subordinate->devices)) - goto out; link = parent->link_state; root = link->root; parent_link = link->parent; - /* All functions are removed, so just disable ASPM for the link */ + /* + * link->downstream is a pointer to the pci_dev of function 0. If + * we remove that function, the pci_dev is about to be deallocated, + * so we can't use link->downstream again. Free the link state to + * avoid this. + * + * If we're removing a non-0 function, it's possible we could + * retain the link state, but PCIe r6.0, sec 7.5.3.7, recommends + * programming the same ASPM Control value for all functions of + * multi-function devices, so disable ASPM for all of them. + */ pcie_config_aspm_link(link, 0); list_del(&link->sibling); - /* Clock PM is for endpoint device */ free_link_state(link); /* Recheck latencies and configure upstream links */ @@ -1015,7 +1018,7 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) pcie_update_aspm_capable(root); pcie_config_aspm_path(parent_link); } -out: + mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); } From b9895a4c95f3db8eaeb073eee29f7efe47d3f3d5 Mon Sep 17 00:00:00 2001 From: Yuchen Yang Date: Fri, 5 May 2023 22:12:55 +0800 Subject: [PATCH 3912/4345] scsi: 3w-xxxx: Add error handling for initialization failure in tw_probe() [ Upstream commit 2e2fe5ac695a00ab03cab4db1f4d6be07168ed9d ] Smatch complains that: tw_probe() warn: missing error code 'retval' This patch adds error checking to tw_probe() to handle initialization failure. If tw_reset_sequence() function returns a non-zero value, the function will return -EINVAL to indicate initialization failure. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Yuchen Yang Link: https://lore.kernel.org/r/20230505141259.7730-1-u202114568@hust.edu.cn Reviewed-by: Dan Carpenter Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/3w-xxxx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c index fb6444d0409c..211a25351e7d 100644 --- a/drivers/scsi/3w-xxxx.c +++ b/drivers/scsi/3w-xxxx.c @@ -2308,8 +2308,10 @@ static int tw_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id) TW_DISABLE_INTERRUPTS(tw_dev); /* Initialize the card */ - if (tw_reset_sequence(tw_dev)) + if (tw_reset_sequence(tw_dev)) { + retval = -EINVAL; goto out_release_mem_region; + } /* Set host specific parameters */ host->max_id = TW_MAX_UNITS; From cb389e8edf64ca41e6b601f1e3b9b39b6b05569a Mon Sep 17 00:00:00 2001 From: Rongguang Wei Date: Fri, 12 May 2023 10:15:18 +0800 Subject: [PATCH 3913/4345] PCI: pciehp: Cancel bringup sequence if card is not present [ Upstream commit e8afd0d9fccc27c8ad263db5cf5952cfcf72d6fe ] If a PCIe hotplug slot has an Attention Button, the normal hot-add flow is: - Slot is empty and slot power is off - User inserts card in slot and presses Attention Button - OS blinks Power Indicator for 5 seconds - After 5 seconds, OS turns on Power Indicator, turns on slot power, and enumerates the device Previously, if a user pressed the Attention Button on an *empty* slot, pciehp logged the following messages and blinked the Power Indicator until a second button press: [0.000] pciehp: Button press: will power on in 5 sec [0.001] # Power Indicator starts blinking [5.001] # 5 second timeout; slot is empty, so we should cancel the request to power on and turn off Power Indicator [7.000] # Power Indicator still blinking [8.000] # possible card insertion [9.000] pciehp: Button press: canceling request to power on The first button press incorrectly left the slot in BLINKINGON_STATE, so the second was interpreted as a "cancel power on" event regardless of whether a card was present. If the slot is empty, turn off the Power Indicator and return from BLINKINGON_STATE to OFF_STATE after 5 seconds, effectively canceling the request to power on. Putting the slot in OFF_STATE also means the second button press will correctly request a slot power on if the slot is occupied. [bhelgaas: commit log] Link: https://lore.kernel.org/r/20230512021518.336460-1-clementwei90@163.com Fixes: d331710ea78f ("PCI: pciehp: Become resilient to missed events") Suggested-by: Lukas Wunner Signed-off-by: Rongguang Wei Signed-off-by: Bjorn Helgaas Reviewed-by: Lukas Wunner Signed-off-by: Sasha Levin --- drivers/pci/hotplug/pciehp_ctrl.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index 529c34808440..32baba1b7f13 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -256,6 +256,14 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) present = pciehp_card_present(ctrl); link_active = pciehp_check_link_active(ctrl); if (present <= 0 && link_active <= 0) { + if (ctrl->state == BLINKINGON_STATE) { + ctrl->state = OFF_STATE; + cancel_delayed_work(&ctrl->button_work); + pciehp_set_indicators(ctrl, PCI_EXP_SLTCTL_PWR_IND_OFF, + INDICATOR_NOOP); + ctrl_info(ctrl, "Slot(%s): Card not present\n", + slot_name(ctrl)); + } mutex_unlock(&ctrl->state_lock); return; } From b65fe59b2d623c7008c3a69a1064f0759d9f2b3e Mon Sep 17 00:00:00 2001 From: Junyan Ye Date: Mon, 8 May 2023 12:36:41 +0800 Subject: [PATCH 3914/4345] PCI: ftpci100: Release the clock resources [ Upstream commit c60738de85f40b0b9f5cb23c21f9246e5a47908c ] Smatch reported: 1. drivers/pci/controller/pci-ftpci100.c:526 faraday_pci_probe() warn: 'clk' from clk_prepare_enable() not released on lines: 442,451,462,478,512,517. 2. drivers/pci/controller/pci-ftpci100.c:526 faraday_pci_probe() warn: 'p->bus_clk' from clk_prepare_enable() not released on lines: 451,462,478,512,517. The clock resource is obtained by devm_clk_get(), and then clk_prepare_enable() makes the clock resource ready for use. After that, clk_disable_unprepare() should be called to release the clock resource when it is no longer needed. However, while doing some error handling in faraday_pci_probe(), clk_disable_unprepare() is not called to release clk and p->bus_clk before returning. These return lines are exactly 442, 451, 462, 478, 512, 517. Fix this warning by replacing devm_clk_get() with devm_clk_get_enabled(), which is equivalent to devm_clk_get() + clk_prepare_enable(). And with devm_clk_get_enabled(), the clock will automatically be disabled, unprepared and freed when the device is unbound from the bus. Link: https://lore.kernel.org/r/20230508043641.23807-1-yejunyan@hust.edu.cn Fixes: b3c433efb8a3 ("PCI: faraday: Fix wrong pointer passed to PTR_ERR()") Fixes: 2eeb02b28579 ("PCI: faraday: Add clock handling") Fixes: 783a862563f7 ("PCI: faraday: Use pci_parse_request_of_pci_ranges()") Fixes: d3c68e0a7e34 ("PCI: faraday: Add Faraday Technology FTPCI100 PCI Host Bridge driver") Fixes: f1e8bd21e39e ("PCI: faraday: Convert IRQ masking to raw PCI config accessors") Signed-off-by: Junyan Ye Signed-off-by: Lorenzo Pieralisi Reviewed-by: Dongliang Mu Reviewed-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pci/controller/pci-ftpci100.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c index aefef1986201..80cfea5d9f12 100644 --- a/drivers/pci/controller/pci-ftpci100.c +++ b/drivers/pci/controller/pci-ftpci100.c @@ -442,22 +442,12 @@ static int faraday_pci_probe(struct platform_device *pdev) p->dev = dev; /* Retrieve and enable optional clocks */ - clk = devm_clk_get(dev, "PCLK"); + clk = devm_clk_get_enabled(dev, "PCLK"); if (IS_ERR(clk)) return PTR_ERR(clk); - ret = clk_prepare_enable(clk); - if (ret) { - dev_err(dev, "could not prepare PCLK\n"); - return ret; - } - p->bus_clk = devm_clk_get(dev, "PCICLK"); + p->bus_clk = devm_clk_get_enabled(dev, "PCICLK"); if (IS_ERR(p->bus_clk)) return PTR_ERR(p->bus_clk); - ret = clk_prepare_enable(p->bus_clk); - if (ret) { - dev_err(dev, "could not prepare PCICLK\n"); - return ret; - } p->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(p->base)) From f0d2310f6b46c63b78556c94811d754364180ea2 Mon Sep 17 00:00:00 2001 From: Sui Jingfeng Date: Wed, 31 May 2023 18:27:44 +0800 Subject: [PATCH 3915/4345] PCI: Add pci_clear_master() stub for non-CONFIG_PCI [ Upstream commit 2aa5ac633259843f656eb6ecff4cf01e8e810c5e ] Add a pci_clear_master() stub when CONFIG_PCI is not set so drivers that support both PCI and platform devices don't need #ifdefs or extra Kconfig symbols for the PCI parts. [bhelgaas: commit log] Fixes: 6a479079c072 ("PCI: Add pci_clear_master() as opposite of pci_set_master()") Link: https://lore.kernel.org/r/20230531102744.2354313-1-suijingfeng@loongson.cn Signed-off-by: Sui Jingfeng Signed-off-by: Bjorn Helgaas Reviewed-by: Geert Uytterhoeven Signed-off-by: Sasha Levin --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/pci.h b/include/linux/pci.h index 4cc42ad2f6c5..550e1cdb473f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1719,6 +1719,7 @@ static inline struct pci_dev *pci_get_class(unsigned int class, #define pci_dev_put(dev) do { } while (0) static inline void pci_set_master(struct pci_dev *dev) { } +static inline void pci_clear_master(struct pci_dev *dev) { } static inline int pci_enable_device(struct pci_dev *dev) { return -EIO; } static inline void pci_disable_device(struct pci_dev *dev) { } static inline int pcim_enable_device(struct pci_dev *pdev) { return -EIO; } From 345ee8521655e69f63a01376572745431f461714 Mon Sep 17 00:00:00 2001 From: Sohaib Mohamed Date: Fri, 19 Nov 2021 08:14:08 +0200 Subject: [PATCH 3916/4345] perf bench: Use unbuffered output when pipe/tee'ing to a file [ Upstream commit f0a29c9647ff8bbb424641f79bc1894e83dec218 ] The output of 'perf bench' gets buffered when I pipe it to a file or to tee, in such a way that I can see it only at the end. E.g. $ perf bench internals synthesize -t < output comes out fine after each test run > $ perf bench internals synthesize -t | tee file.txt < output comes out only at the end of all tests > This patch resolves this issue for 'bench' and 'test' subcommands. See, also: $ perf bench mem all | tee file.txt $ perf bench sched all | tee file.txt $ perf bench internals all -t | tee file.txt $ perf bench internals all | tee file.txt Committer testing: It really gets staggered, i.e. outputs in bursts, when the buffer fills up and has to be drained to make up space for more output. Suggested-by: Riccardo Mancini Signed-off-by: Sohaib Mohamed Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Fabian Hemmer Cc: Ian Rogers Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20211119061409.78004-1-sohaib.amhmd@gmail.com Signed-off-by: Arnaldo Carvalho de Melo Stable-dep-of: 16203e9cd018 ("perf bench: Add missing setlocale() call to allow usage of %'d style formatting") Signed-off-by: Sasha Levin --- tools/perf/builtin-bench.c | 5 +++-- tools/perf/tests/builtin-test.c | 3 +++ 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 62a7b7420a44..609a941ae296 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -225,7 +225,6 @@ static void run_collection(struct collection *coll) if (!bench->fn) break; printf("# Running %s/%s benchmark...\n", coll->name, bench->name); - fflush(stdout); argv[1] = bench->name; run_bench(coll->name, bench->name, bench->fn, 1, argv); @@ -246,6 +245,9 @@ int cmd_bench(int argc, const char **argv) struct collection *coll; int ret = 0; + /* Unbuffered output */ + setvbuf(stdout, NULL, _IONBF, 0); + if (argc < 2) { /* No collection specified. */ print_usage(); @@ -299,7 +301,6 @@ int cmd_bench(int argc, const char **argv) if (bench_format == BENCH_FORMAT_DEFAULT) printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name); - fflush(stdout); ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1); goto end; } diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 132bdb3e6c31..73c911dd0c2c 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -793,6 +793,9 @@ int cmd_test(int argc, const char **argv) if (ret < 0) return ret; + /* Unbuffered output */ + setvbuf(stdout, NULL, _IONBF, 0); + argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0); if (argc >= 1 && !strcmp(argv[0], "list")) return perf_test__list(argc - 1, argv + 1); From 4b63caf86edacd79bec6bfb09f9aaae0433566d3 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 2 Jun 2023 15:38:25 -0300 Subject: [PATCH 3917/4345] perf bench: Add missing setlocale() call to allow usage of %'d style formatting [ Upstream commit 16203e9cd01896b4244100a8e3fb9f6e612ab2b1 ] Without this we were not getting the thousands separator for big numbers. Noticed while developing 'perf bench uprobe', but the use of %' predates that, for instance 'perf bench syscall' uses it. Before: # perf bench uprobe all # Running uprobe/baseline benchmark... # Executed 1000 usleep(1000) calls Total time: 1054082243ns 1054082.243000 nsecs/op # After: # perf bench uprobe all # Running uprobe/baseline benchmark... # Executed 1,000 usleep(1000) calls Total time: 1,053,715,144ns 1,053,715.144000 nsecs/op # Fixes: c2a08203052f8975 ("perf bench: Add basic syscall benchmark") Cc: Adrian Hunter Cc: Andre Fredette Cc: Clark Williams Cc: Dave Tucker Cc: Davidlohr Bueso Cc: Derek Barbosa Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Tiezhu Yang Link: https://lore.kernel.org/lkml/ZH3lcepZ4tBYr1jv@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/builtin-bench.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 609a941ae296..fb3029495c23 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -21,6 +21,7 @@ #include "builtin.h" #include "bench/bench.h" +#include #include #include #include @@ -247,6 +248,7 @@ int cmd_bench(int argc, const char **argv) /* Unbuffered output */ setvbuf(stdout, NULL, _IONBF, 0); + setlocale(LC_ALL, ""); if (argc < 2) { /* No collection specified. */ From 5533f0eb0a2935ca612fe3357b593e9bb45d05cd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 5 Jun 2023 17:37:34 +0300 Subject: [PATCH 3918/4345] pinctrl: cherryview: Return correct value if pin in push-pull mode [ Upstream commit 5835196a17be5cfdcad0b617f90cf4abe16951a4 ] Currently the getter returns ENOTSUPP on pin configured in the push-pull mode. Fix this by adding the missed switch case. Fixes: ccdf81d08dbe ("pinctrl: cherryview: add option to set open-drain pin config") Fixes: 6e08d6bbebeb ("pinctrl: Add Intel Cherryview/Braswell pin controller support") Acked-by: Mika Westerberg Signed-off-by: Andy Shevchenko Signed-off-by: Sasha Levin --- drivers/pinctrl/intel/pinctrl-cherryview.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 2ed17cdf946d..44caada37b71 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -945,11 +945,6 @@ static int chv_config_get(struct pinctrl_dev *pctldev, unsigned int pin, break; - case PIN_CONFIG_DRIVE_OPEN_DRAIN: - if (!(ctrl1 & CHV_PADCTRL1_ODEN)) - return -EINVAL; - break; - case PIN_CONFIG_BIAS_HIGH_IMPEDANCE: { u32 cfg; @@ -959,6 +954,16 @@ static int chv_config_get(struct pinctrl_dev *pctldev, unsigned int pin, return -EINVAL; break; + + case PIN_CONFIG_DRIVE_PUSH_PULL: + if (ctrl1 & CHV_PADCTRL1_ODEN) + return -EINVAL; + break; + + case PIN_CONFIG_DRIVE_OPEN_DRAIN: + if (!(ctrl1 & CHV_PADCTRL1_ODEN)) + return -EINVAL; + break; } default: From 958acb479ef21599a85f87f70eb07f38a8363568 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 12 May 2023 17:31:17 +0200 Subject: [PATCH 3919/4345] kcsan: Don't expect 64 bits atomic builtins from 32 bits architectures [ Upstream commit 353e7300a1db928e427462f2745f9a2cd1625b3d ] Activating KCSAN on a 32 bits architecture leads to the following link-time failure: LD .tmp_vmlinux.kallsyms1 powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_load': kernel/kcsan/core.c:1273: undefined reference to `__atomic_load_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_store': kernel/kcsan/core.c:1273: undefined reference to `__atomic_store_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_exchange': kernel/kcsan/core.c:1273: undefined reference to `__atomic_exchange_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_fetch_add': kernel/kcsan/core.c:1273: undefined reference to `__atomic_fetch_add_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_fetch_sub': kernel/kcsan/core.c:1273: undefined reference to `__atomic_fetch_sub_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_fetch_and': kernel/kcsan/core.c:1273: undefined reference to `__atomic_fetch_and_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_fetch_or': kernel/kcsan/core.c:1273: undefined reference to `__atomic_fetch_or_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_fetch_xor': kernel/kcsan/core.c:1273: undefined reference to `__atomic_fetch_xor_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_fetch_nand': kernel/kcsan/core.c:1273: undefined reference to `__atomic_fetch_nand_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_compare_exchange_strong': kernel/kcsan/core.c:1273: undefined reference to `__atomic_compare_exchange_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_compare_exchange_weak': kernel/kcsan/core.c:1273: undefined reference to `__atomic_compare_exchange_8' powerpc64-linux-ld: kernel/kcsan/core.o: in function `__tsan_atomic64_compare_exchange_val': kernel/kcsan/core.c:1273: undefined reference to `__atomic_compare_exchange_8' 32 bits architectures don't have 64 bits atomic builtins. Only include DEFINE_TSAN_ATOMIC_OPS(64) on 64 bits architectures. Fixes: 0f8ad5f2e934 ("kcsan: Add support for atomic builtins") Suggested-by: Marco Elver Signed-off-by: Christophe Leroy Reviewed-by: Marco Elver Acked-by: Marco Elver Signed-off-by: Michael Ellerman Link: https://msgid.link/d9c6afc28d0855240171a4e0ad9ffcdb9d07fceb.1683892665.git.christophe.leroy@csgroup.eu Signed-off-by: Sasha Levin --- kernel/kcsan/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index 762df6108c58..473dc04591b8 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -1035,7 +1035,9 @@ EXPORT_SYMBOL(__tsan_init); DEFINE_TSAN_ATOMIC_OPS(8); DEFINE_TSAN_ATOMIC_OPS(16); DEFINE_TSAN_ATOMIC_OPS(32); +#ifdef CONFIG_64BIT DEFINE_TSAN_ATOMIC_OPS(64); +#endif void __tsan_atomic_thread_fence(int memorder); void __tsan_atomic_thread_fence(int memorder) From 647c6d35ccfe47c8344a9c09e819e1fb09eb69cc Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Mar 2021 08:59:21 -0300 Subject: [PATCH 3920/4345] perf script: Fixup 'struct evsel_script' method prefix [ Upstream commit 297e69bfa4c7aa27259dd456af1377e868337043 ] They all operate on 'struct evsel_script' instances, so should be prefixed with evsel_script__, not with perf_evsel_script__. Signed-off-by: Arnaldo Carvalho de Melo Stable-dep-of: 36d3e4138e1b ("perf script: Fix allocation of evsel->priv related to per-event dump files") Signed-off-by: Sasha Levin --- tools/perf/builtin-script.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 5109d01619ee..5651714e527c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -295,8 +295,7 @@ static inline struct evsel_script *evsel_script(struct evsel *evsel) return (struct evsel_script *)evsel->priv; } -static struct evsel_script *perf_evsel_script__new(struct evsel *evsel, - struct perf_data *data) +static struct evsel_script *evsel_script__new(struct evsel *evsel, struct perf_data *data) { struct evsel_script *es = zalloc(sizeof(*es)); @@ -316,7 +315,7 @@ out_free: return NULL; } -static void perf_evsel_script__delete(struct evsel_script *es) +static void evsel_script__delete(struct evsel_script *es) { zfree(&es->filename); fclose(es->fp); @@ -324,7 +323,7 @@ static void perf_evsel_script__delete(struct evsel_script *es) free(es); } -static int perf_evsel_script__fprintf(struct evsel_script *es, FILE *fp) +static int evsel_script__fprintf(struct evsel_script *es, FILE *fp) { struct stat st; @@ -2166,8 +2165,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, if (!evsel->priv) { if (scr->per_event_dump) { - evsel->priv = perf_evsel_script__new(evsel, - scr->session->data); + evsel->priv = evsel_script__new(evsel, scr->session->data); } else { es = zalloc(sizeof(*es)); if (!es) @@ -2422,7 +2420,7 @@ static void perf_script__fclose_per_event_dump(struct perf_script *script) evlist__for_each_entry(evlist, evsel) { if (!evsel->priv) break; - perf_evsel_script__delete(evsel->priv); + evsel_script__delete(evsel->priv); evsel->priv = NULL; } } @@ -2442,7 +2440,7 @@ static int perf_script__fopen_per_event_dump(struct perf_script *script) if (evsel->priv != NULL) continue; - evsel->priv = perf_evsel_script__new(evsel, script->session->data); + evsel->priv = evsel_script__new(evsel, script->session->data); if (evsel->priv == NULL) goto out_err_fclose; } @@ -2477,8 +2475,8 @@ static void perf_script__exit_per_event_dump_stats(struct perf_script *script) evlist__for_each_entry(script->session->evlist, evsel) { struct evsel_script *es = evsel->priv; - perf_evsel_script__fprintf(es, stdout); - perf_evsel_script__delete(es); + evsel_script__fprintf(es, stdout); + evsel_script__delete(es); evsel->priv = NULL; } } From 75a3cb1e2317ade7c2918bcedccf40c868da2719 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 6 Jun 2023 16:11:10 -0300 Subject: [PATCH 3921/4345] perf script: Fix allocation of evsel->priv related to per-event dump files [ Upstream commit 36d3e4138e1b6cc9ab179f3f397b5548f8b1eaae ] When printing output we may want to generate per event files, where the --per-event-dump option should be used, creating perf.data.EVENT.dump files instead of printing to stdout. The callback thar processes event thus expects that evsel->priv->fp should point to either the per-event FILE descriptor or to stdout. The a3af66f51bd0bca7 ("perf script: Fix crash because of missing evsel->priv") changeset fixed a case where evsel->priv wasn't setup, thus set to NULL, causing a segfault when trying to access evsel->priv->fp. But it did it for the non --per-event-dump case by allocating a 'struct perf_evsel_script' just to set its ->fp to stdout. Since evsel->priv is only freed when --per-event-dump is used, we ended up with a memory leak, detected using ASAN. Fix it by using the same method as perf_script__setup_per_event_dump(), and reuse that static 'struct perf_evsel_script'. Also check if evsel_script__new() failed. Fixes: a3af66f51bd0bca7 ("perf script: Fix crash because of missing evsel->priv") Reported-by: Ian Rogers Tested-by: Ian Rogers Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Cc: Ravi Bangoria Link: https://lore.kernel.org/lkml/ZH+F0wGAWV14zvMP@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/builtin-script.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 5651714e527c..85befbacb2a4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2146,6 +2146,9 @@ out_put: return 0; } +// Used when scr->per_event_dump is not set +static struct evsel_script es_stdout; + static int process_attr(struct perf_tool *tool, union perf_event *event, struct evlist **pevlist) { @@ -2154,7 +2157,6 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, struct evsel *evsel, *pos; u64 sample_type; int err; - static struct evsel_script *es; err = perf_event__process_attr(tool, event, pevlist); if (err) @@ -2164,14 +2166,13 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, evsel = evlist__last(*pevlist); if (!evsel->priv) { - if (scr->per_event_dump) { + if (scr->per_event_dump) { evsel->priv = evsel_script__new(evsel, scr->session->data); - } else { - es = zalloc(sizeof(*es)); - if (!es) + if (!evsel->priv) return -ENOMEM; - es->fp = stdout; - evsel->priv = es; + } else { // Replicate what is done in perf_script__setup_per_event_dump() + es_stdout.fp = stdout; + evsel->priv = &es_stdout; } } @@ -2455,7 +2456,6 @@ out_err_fclose: static int perf_script__setup_per_event_dump(struct perf_script *script) { struct evsel *evsel; - static struct evsel_script es_stdout; if (script->per_event_dump) return perf_script__fopen_per_event_dump(script); From b7a38fc3f384932c50c712e8b0f81310939a1ba0 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 12 Jun 2023 16:41:01 -0700 Subject: [PATCH 3922/4345] perf dwarf-aux: Fix off-by-one in die_get_varname() [ Upstream commit 3abfcfd847717d232e36963f31a361747c388fe7 ] The die_get_varname() returns "(unknown_type)" string if it failed to find a type for the variable. But it had a space before the opening parenthesis and it made the closing parenthesis cut off due to the off-by-one in the string length (14). Signed-off-by: Namhyung Kim Fixes: 88fd633cdfa19060 ("perf probe: No need to use formatting strbuf method") Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230612234102.3909116-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/util/dwarf-aux.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index f8a10d5148f6..443374a77c8d 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -1081,7 +1081,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf) ret = die_get_typename(vr_die, buf); if (ret < 0) { pr_debug("Failed to get type, make it unknown.\n"); - ret = strbuf_add(buf, " (unknown_type)", 14); + ret = strbuf_add(buf, "(unknown_type)", 14); } return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die)); From f3c7b95c9991dab02e616fc251b6c3516e0bd0ac Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 15 Jun 2023 13:53:33 +0300 Subject: [PATCH 3923/4345] pinctrl: at91-pio4: check return value of devm_kasprintf() [ Upstream commit f6fd5d4ff8ca0b24cee1af4130bcb1fa96b61aa0 ] devm_kasprintf() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: 776180848b57 ("pinctrl: introduce driver for Atmel PIO4 controller") Depends-on: 1c4e5c470a56 ("pinctrl: at91: use devm_kasprintf() to avoid potential leaks") Depends-on: 5a8f9cf269e8 ("pinctrl: at91-pio4: use proper format specifier for unsigned int") Signed-off-by: Claudiu Beznea Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230615105333.585304-4-claudiu.beznea@microchip.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-at91-pio4.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 315a6c4d9ade..bf8aa0ea35d1 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1083,6 +1083,8 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) /* Pin naming convention: P(bank_name)(bank_pin_number). */ pin_desc[i].name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "P%c%d", bank + 'A', line); + if (!pin_desc[i].name) + return -ENOMEM; group->name = group_names[i] = pin_desc[i].name; group->pin = pin_desc[i].number; From 07c19c0ad4b07f4b598da369714de028f6a6a323 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 8 Jun 2023 10:58:49 +0100 Subject: [PATCH 3924/4345] powerpc/powernv/sriov: perform null check on iov before dereferencing iov [ Upstream commit f4f913c980bc6abe0ccfe88fe3909c125afe4a2d ] Currently pointer iov is being dereferenced before the null check of iov which can lead to null pointer dereference errors. Fix this by moving the iov null check before the dereferencing. Detected using cppcheck static analysis: linux/arch/powerpc/platforms/powernv/pci-sriov.c:597:12: warning: Either the condition '!iov' is redundant or there is possible null pointer dereference: iov. [nullPointerRedundantCheck] num_vfs = iov->num_vfs; ^ Fixes: 052da31d45fc ("powerpc/powernv/sriov: De-indent setup and teardown") Signed-off-by: Colin Ian King Signed-off-by: Michael Ellerman Link: https://msgid.link/20230608095849.1147969-1-colin.i.king@gmail.com Signed-off-by: Sasha Levin --- arch/powerpc/platforms/powernv/pci-sriov.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/platforms/powernv/pci-sriov.c b/arch/powerpc/platforms/powernv/pci-sriov.c index 28aac933a439..e3e52ff2cbf5 100644 --- a/arch/powerpc/platforms/powernv/pci-sriov.c +++ b/arch/powerpc/platforms/powernv/pci-sriov.c @@ -600,12 +600,12 @@ static void pnv_pci_sriov_disable(struct pci_dev *pdev) struct pnv_iov_data *iov; iov = pnv_iov_get(pdev); - num_vfs = iov->num_vfs; - base_pe = iov->vf_pe_arr[0].pe_number; - if (WARN_ON(!iov)) return; + num_vfs = iov->num_vfs; + base_pe = iov->vf_pe_arr[0].pe_number; + /* Release VF PEs */ pnv_ioda_release_vf_PE(pdev); From bfad11018806e5e33b7b20d2d046bde699309457 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 7 Jul 2021 18:09:53 -0700 Subject: [PATCH 3925/4345] mm: rename pud_page_vaddr to pud_pgtable and make it return pmd_t * [ Upstream commit 9cf6fa2458443118b84090aa1bf7a3630b5940e8 ] No functional change in this patch. [aneesh.kumar@linux.ibm.com: fix] Link: https://lkml.kernel.org/r/87wnqtnb60.fsf@linux.ibm.com [sfr@canb.auug.org.au: another fix] Link: https://lkml.kernel.org/r/20210619134410.89559-1-aneesh.kumar@linux.ibm.com Link: https://lkml.kernel.org/r/20210615110859.320299-1-aneesh.kumar@linux.ibm.com Link: https://lore.kernel.org/linuxppc-dev/CAHk-=wi+J+iodze9FtjM3Zi4j4OeS+qqbKxME9QN4roxPEXH9Q@mail.gmail.com/ Signed-off-by: Aneesh Kumar K.V Signed-off-by: Stephen Rothwell Cc: Christophe Leroy Cc: Hugh Dickins Cc: Joel Fernandes Cc: Kalesh Singh Cc: Kirill A. Shutemov Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Stable-dep-of: 0da90af431ab ("powerpc/book3s64/mm: Fix DirectMap stats in /proc/meminfo") Signed-off-by: Sasha Levin --- arch/alpha/include/asm/pgtable.h | 8 +++++--- arch/arm/include/asm/pgtable-3level.h | 2 +- arch/arm64/include/asm/pgtable.h | 4 ++-- arch/ia64/include/asm/pgtable.h | 2 +- arch/m68k/include/asm/motorola_pgtable.h | 2 +- arch/mips/include/asm/pgtable-64.h | 4 ++-- arch/parisc/include/asm/pgtable.h | 4 ++-- arch/powerpc/include/asm/book3s/64/pgtable.h | 6 +++++- arch/powerpc/include/asm/nohash/64/pgtable.h | 6 +++++- arch/powerpc/mm/book3s64/radix_pgtable.c | 4 ++-- arch/powerpc/mm/pgtable_64.c | 2 +- arch/riscv/include/asm/pgtable-64.h | 4 ++-- arch/sh/include/asm/pgtable-3level.h | 4 ++-- arch/sparc/include/asm/pgtable_32.h | 6 +++--- arch/sparc/include/asm/pgtable_64.h | 6 +++--- arch/um/include/asm/pgtable-3level.h | 2 +- arch/x86/include/asm/pgtable.h | 4 ++-- arch/x86/mm/pat/set_memory.c | 4 ++-- arch/x86/mm/pgtable.c | 2 +- include/asm-generic/pgtable-nopmd.h | 2 +- include/asm-generic/pgtable-nopud.h | 2 +- include/linux/pgtable.h | 2 +- 22 files changed, 46 insertions(+), 36 deletions(-) diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index 660b14ce1317..12c120e436a2 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -241,8 +241,10 @@ pmd_page_vaddr(pmd_t pmd) #define pud_page(pud) (mem_map + ((pud_val(pud) & _PFN_MASK) >> 32)) #endif -extern inline unsigned long pud_page_vaddr(pud_t pgd) -{ return PAGE_OFFSET + ((pud_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT)); } +extern inline pmd_t *pud_pgtable(pud_t pgd) +{ + return (pmd_t *)(PAGE_OFFSET + ((pud_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT))); +} extern inline int pte_none(pte_t pte) { return !pte_val(pte); } extern inline int pte_present(pte_t pte) { return pte_val(pte) & _PAGE_VALID; } @@ -292,7 +294,7 @@ extern inline pte_t pte_mkyoung(pte_t pte) { pte_val(pte) |= __ACCESS_BITS; retu /* Find an entry in the second-level page table.. */ extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address) { - pmd_t *ret = (pmd_t *) pud_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1)); + pmd_t *ret = pud_pgtable(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1)); smp_rmb(); /* see above */ return ret; } diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 2b85d175e999..4487aea88477 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -130,7 +130,7 @@ flush_pmd_entry(pudp); \ } while (0) -static inline pmd_t *pud_page_vaddr(pud_t pud) +static inline pmd_t *pud_pgtable(pud_t pud) { return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK); } diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 3f74db7b0a31..3635d48ada17 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -633,9 +633,9 @@ static inline phys_addr_t pud_page_paddr(pud_t pud) return __pud_to_phys(pud); } -static inline unsigned long pud_page_vaddr(pud_t pud) +static inline pmd_t *pud_pgtable(pud_t pud) { - return (unsigned long)__va(pud_page_paddr(pud)); + return (pmd_t *)__va(pud_page_paddr(pud)); } /* Find an entry in the second-level page table. */ diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 9f64fdfbf275..fd92792d148b 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -279,7 +279,7 @@ extern unsigned long VMALLOC_END; #define pud_bad(pud) (!ia64_phys_addr_valid(pud_val(pud))) #define pud_present(pud) (pud_val(pud) != 0UL) #define pud_clear(pudp) (pud_val(*(pudp)) = 0UL) -#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & _PFN_MASK)) +#define pud_pgtable(pud) ((pmd_t *) __va(pud_val(pud) & _PFN_MASK)) #define pud_page(pud) virt_to_page((pud_val(pud) + PAGE_OFFSET)) #if CONFIG_PGTABLE_LEVELS == 4 diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h index 8076467eff4b..956c80874f98 100644 --- a/arch/m68k/include/asm/motorola_pgtable.h +++ b/arch/m68k/include/asm/motorola_pgtable.h @@ -129,7 +129,7 @@ static inline void pud_set(pud_t *pudp, pmd_t *pmdp) #define __pte_page(pte) ((unsigned long)__va(pte_val(pte) & PAGE_MASK)) #define pmd_page_vaddr(pmd) ((unsigned long)__va(pmd_val(pmd) & _TABLE_MASK)) -#define pud_page_vaddr(pud) ((unsigned long)__va(pud_val(pud) & _TABLE_MASK)) +#define pud_pgtable(pud) ((pmd_t *)__va(pud_val(pud) & _TABLE_MASK)) #define pte_none(pte) (!pte_val(pte)) diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 1e7d6ce9d8d6..ab305453e90f 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -314,9 +314,9 @@ static inline void pud_clear(pud_t *pudp) #endif #ifndef __PAGETABLE_PMD_FOLDED -static inline unsigned long pud_page_vaddr(pud_t pud) +static inline pmd_t *pud_pgtable(pud_t pud) { - return pud_val(pud); + return (pmd_t *)pud_val(pud); } #define pud_phys(pud) virt_to_phys((void *)pud_val(pud)) #define pud_page(pud) (pfn_to_page(pud_phys(pud) >> PAGE_SHIFT)) diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 8964798b8274..ade591927cbf 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -330,8 +330,8 @@ static inline void pmd_clear(pmd_t *pmd) { #if CONFIG_PGTABLE_LEVELS == 3 -#define pud_page_vaddr(pud) ((unsigned long) __va(pud_address(pud))) -#define pud_page(pud) virt_to_page((void *)pud_page_vaddr(pud)) +#define pud_pgtable(pud) ((pmd_t *) __va(pud_address(pud))) +#define pud_page(pud) virt_to_page((void *)pud_pgtable(pud)) /* For 64 bit we have three level tables */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 71e2c524f1ee..5ebf6450f6da 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1030,9 +1030,13 @@ extern struct page *p4d_page(p4d_t p4d); /* Pointers in the page table tree are physical addresses */ #define __pgtable_ptr_val(ptr) __pa(ptr) -#define pud_page_vaddr(pud) __va(pud_val(pud) & ~PUD_MASKED_BITS) #define p4d_page_vaddr(p4d) __va(p4d_val(p4d) & ~P4D_MASKED_BITS) +static inline pmd_t *pud_pgtable(pud_t pud) +{ + return (pmd_t *)__va(pud_val(pud) & ~PUD_MASKED_BITS); +} + #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 1eacff0fff02..a4d475c0fc2c 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -164,7 +164,11 @@ static inline void pud_clear(pud_t *pudp) #define pud_bad(pud) (!is_kernel_addr(pud_val(pud)) \ || (pud_val(pud) & PUD_BAD_BITS)) #define pud_present(pud) (pud_val(pud) != 0) -#define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS) + +static inline pmd_t *pud_pgtable(pud_t pud) +{ + return (pmd_t *)(pud_val(pud) & ~PUD_MASKED_BITS); +} extern struct page *pud_page(pud_t pud); diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 5f0a2fa611fa..605c770dd819 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -864,7 +864,7 @@ static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, continue; } - pmd_base = (pmd_t *)pud_page_vaddr(*pud); + pmd_base = pud_pgtable(*pud); remove_pmd_table(pmd_base, addr, next); free_pmd_table(pmd_base, pud); } @@ -1156,7 +1156,7 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) pmd_t *pmd; int i; - pmd = (pmd_t *)pud_page_vaddr(*pud); + pmd = pud_pgtable(*pud); pud_clear(pud); flush_tlb_kernel_range(addr, addr + PUD_SIZE); diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index aefc2bfdf104..bd0d903196d9 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -117,7 +117,7 @@ struct page *pud_page(pud_t pud) VM_WARN_ON(!pud_huge(pud)); return pte_page(pud_pte(pud)); } - return virt_to_page(pud_page_vaddr(pud)); + return virt_to_page(pud_pgtable(pud)); } /* diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index f3b0da64c6c8..0e863f3f7187 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -60,9 +60,9 @@ static inline void pud_clear(pud_t *pudp) set_pud(pudp, __pud(0)); } -static inline unsigned long pud_page_vaddr(pud_t pud) +static inline pmd_t *pud_pgtable(pud_t pud) { - return (unsigned long)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); + return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT); } static inline struct page *pud_page(pud_t pud) diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index 82d74472dfcd..56bf35c2f29c 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -32,9 +32,9 @@ typedef struct { unsigned long long pmd; } pmd_t; #define pmd_val(x) ((x).pmd) #define __pmd(x) ((pmd_t) { (x) } ) -static inline unsigned long pud_page_vaddr(pud_t pud) +static inline pmd_t *pud_pgtable(pud_t pud) { - return pud_val(pud); + return (pmd_t *)pud_val(pud); } /* only used by the stubbed out hugetlb gup code, should never be called */ diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index 632cdb959542..7d1d10a8fd93 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -152,13 +152,13 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) return (unsigned long)__nocache_va(v << 4); } -static inline unsigned long pud_page_vaddr(pud_t pud) +static inline pmd_t *pud_pgtable(pud_t pud) { if (srmmu_device_memory(pud_val(pud))) { - return ~0; + return (pmd_t *)~0; } else { unsigned long v = pud_val(pud) & SRMMU_PTD_PMASK; - return (unsigned long)__nocache_va(v << 4); + return (pmd_t *)__nocache_va(v << 4); } } diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 7ef6affa105e..cac02ac301f1 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -845,18 +845,18 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) return ((unsigned long) __va(pfn << PAGE_SHIFT)); } -static inline unsigned long pud_page_vaddr(pud_t pud) +static inline pmd_t *pud_pgtable(pud_t pud) { pte_t pte = __pte(pud_val(pud)); unsigned long pfn; pfn = pte_pfn(pte); - return ((unsigned long) __va(pfn << PAGE_SHIFT)); + return ((pmd_t *) __va(pfn << PAGE_SHIFT)); } #define pmd_page(pmd) virt_to_page((void *)pmd_page_vaddr(pmd)) -#define pud_page(pud) virt_to_page((void *)pud_page_vaddr(pud)) +#define pud_page(pud) virt_to_page((void *)pud_pgtable(pud)) #define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0UL) #define pud_present(pud) (pud_val(pud) != 0U) #define pud_clear(pudp) (pud_val(*(pudp)) = 0UL) diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h index 7e6a4180db9d..091bff319ccd 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-3level.h @@ -84,7 +84,7 @@ static inline void pud_clear (pud_t *pud) } #define pud_page(pud) phys_to_page(pud_val(pud) & PAGE_MASK) -#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PAGE_MASK)) +#define pud_pgtable(pud) ((pmd_t *) __va(pud_val(pud) & PAGE_MASK)) static inline unsigned long pte_pfn(pte_t pte) { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 87de9f2d71cf..a90f6d02fb96 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -865,9 +865,9 @@ static inline int pud_present(pud_t pud) return pud_flags(pud) & _PAGE_PRESENT; } -static inline unsigned long pud_page_vaddr(pud_t pud) +static inline pmd_t *pud_pgtable(pud_t pud) { - return (unsigned long)__va(pud_val(pud) & pud_pfn_mask(pud)); + return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud)); } /* diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 40baa90e74f4..217dda690ed8 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -1126,7 +1126,7 @@ static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd, unsigned long start, unsigned long end) { if (unmap_pte_range(pmd, start, end)) - if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + if (try_to_free_pmd_page(pud_pgtable(*pud))) pud_clear(pud); } @@ -1170,7 +1170,7 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) * Try again to free the PMD page if haven't succeeded above. */ if (!pud_none(*pud)) - if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + if (try_to_free_pmd_page(pud_pgtable(*pud))) pud_clear(pud); } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index f6a9e2e36642..204b25ee26f0 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -805,7 +805,7 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) pte_t *pte; int i; - pmd = (pmd_t *)pud_page_vaddr(*pud); + pmd = pud_pgtable(*pud); pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL); if (!pmd_sv) return 0; diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index 3e13acd019ae..10789cf51d16 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -51,7 +51,7 @@ static inline pmd_t * pmd_offset(pud_t * pud, unsigned long address) #define __pmd(x) ((pmd_t) { __pud(x) } ) #define pud_page(pud) (pmd_page((pmd_t){ pud })) -#define pud_page_vaddr(pud) (pmd_page_vaddr((pmd_t){ pud })) +#define pud_pgtable(pud) ((pmd_t *)(pmd_page_vaddr((pmd_t){ pud }))) /* * allocating and freeing a pmd is trivial: the 1-entry pmd is diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h index a9d751fbda9e..7cbd15f70bf5 100644 --- a/include/asm-generic/pgtable-nopud.h +++ b/include/asm-generic/pgtable-nopud.h @@ -49,7 +49,7 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) #define __pud(x) ((pud_t) { __p4d(x) }) #define p4d_page(p4d) (pud_page((pud_t){ p4d })) -#define p4d_page_vaddr(p4d) (pud_page_vaddr((pud_t){ p4d })) +#define p4d_page_vaddr(p4d) (pud_pgtable((pud_t){ p4d })) /* * allocating and freeing a pud is trivial: the 1-entry pud is diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 9def1ac19546..f8570799bc26 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -89,7 +89,7 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) #ifndef pmd_offset static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { - return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); + return pud_pgtable(*pud) + pmd_index(address); } #define pmd_offset pmd_offset #endif From 7289ca7a51704e6c3f8d30cbd8ed980637e1267a Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 7 Jul 2021 18:09:56 -0700 Subject: [PATCH 3926/4345] mm: rename p4d_page_vaddr to p4d_pgtable and make it return pud_t * [ Upstream commit dc4875f0e791de554bdc45aa1dbd6e45e107e50f ] No functional change in this patch. [aneesh.kumar@linux.ibm.com: m68k build error reported by kernel robot] Link: https://lkml.kernel.org/r/87tulxnb2v.fsf@linux.ibm.com Link: https://lkml.kernel.org/r/20210615110859.320299-2-aneesh.kumar@linux.ibm.com Link: https://lore.kernel.org/linuxppc-dev/CAHk-=wi+J+iodze9FtjM3Zi4j4OeS+qqbKxME9QN4roxPEXH9Q@mail.gmail.com/ Signed-off-by: Aneesh Kumar K.V Cc: Christophe Leroy Cc: Hugh Dickins Cc: Joel Fernandes Cc: Kalesh Singh Cc: Kirill A. Shutemov Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Stable-dep-of: 0da90af431ab ("powerpc/book3s64/mm: Fix DirectMap stats in /proc/meminfo") Signed-off-by: Sasha Levin --- arch/arm64/include/asm/pgtable.h | 4 ++-- arch/ia64/include/asm/pgtable.h | 2 +- arch/mips/include/asm/pgtable-64.h | 4 ++-- arch/powerpc/include/asm/book3s/64/pgtable.h | 5 ++++- arch/powerpc/include/asm/nohash/64/pgtable-4k.h | 6 +++++- arch/powerpc/mm/book3s64/radix_pgtable.c | 2 +- arch/powerpc/mm/pgtable_64.c | 2 +- arch/sparc/include/asm/pgtable_64.h | 4 ++-- arch/x86/include/asm/pgtable.h | 4 ++-- arch/x86/mm/init_64.c | 4 ++-- include/asm-generic/pgtable-nop4d.h | 2 +- include/asm-generic/pgtable-nopud.h | 2 +- include/linux/pgtable.h | 2 +- 13 files changed, 25 insertions(+), 18 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 3635d48ada17..4eedfd784cf6 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -694,9 +694,9 @@ static inline phys_addr_t p4d_page_paddr(p4d_t p4d) return __p4d_to_phys(p4d); } -static inline unsigned long p4d_page_vaddr(p4d_t p4d) +static inline pud_t *p4d_pgtable(p4d_t p4d) { - return (unsigned long)__va(p4d_page_paddr(p4d)); + return (pud_t *)__va(p4d_page_paddr(p4d)); } /* Find an entry in the frst-level page table. */ diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index fd92792d148b..6e5c38756657 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -287,7 +287,7 @@ extern unsigned long VMALLOC_END; #define p4d_bad(p4d) (!ia64_phys_addr_valid(p4d_val(p4d))) #define p4d_present(p4d) (p4d_val(p4d) != 0UL) #define p4d_clear(p4dp) (p4d_val(*(p4dp)) = 0UL) -#define p4d_page_vaddr(p4d) ((unsigned long) __va(p4d_val(p4d) & _PFN_MASK)) +#define p4d_pgtable(p4d) ((pud_t *) __va(p4d_val(p4d) & _PFN_MASK)) #define p4d_page(p4d) virt_to_page((p4d_val(p4d) + PAGE_OFFSET)) #endif diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index ab305453e90f..b865edff2670 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -210,9 +210,9 @@ static inline void p4d_clear(p4d_t *p4dp) p4d_val(*p4dp) = (unsigned long)invalid_pud_table; } -static inline unsigned long p4d_page_vaddr(p4d_t p4d) +static inline pud_t *p4d_pgtable(p4d_t p4d) { - return p4d_val(p4d); + return (pud_t *)p4d_val(p4d); } #define p4d_phys(p4d) virt_to_phys((void *)p4d_val(p4d)) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 5ebf6450f6da..2b4af824bdc5 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1030,7 +1030,10 @@ extern struct page *p4d_page(p4d_t p4d); /* Pointers in the page table tree are physical addresses */ #define __pgtable_ptr_val(ptr) __pa(ptr) -#define p4d_page_vaddr(p4d) __va(p4d_val(p4d) & ~P4D_MASKED_BITS) +static inline pud_t *p4d_pgtable(p4d_t p4d) +{ + return (pud_t *)__va(p4d_val(p4d) & ~P4D_MASKED_BITS); +} static inline pmd_t *pud_pgtable(pud_t pud) { diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h index fe2f4c9acd9e..10f5cf444d72 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h @@ -56,10 +56,14 @@ #define p4d_none(p4d) (!p4d_val(p4d)) #define p4d_bad(p4d) (p4d_val(p4d) == 0) #define p4d_present(p4d) (p4d_val(p4d) != 0) -#define p4d_page_vaddr(p4d) (p4d_val(p4d) & ~P4D_MASKED_BITS) #ifndef __ASSEMBLY__ +static inline pud_t *p4d_pgtable(p4d_t p4d) +{ + return (pud_t *) (p4d_val(p4d) & ~P4D_MASKED_BITS); +} + static inline void p4d_clear(p4d_t *p4dp) { *p4dp = __p4d(0); diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 605c770dd819..44239e0acf8e 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -898,7 +898,7 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end) continue; } - pud_base = (pud_t *)p4d_page_vaddr(*p4d); + pud_base = p4d_pgtable(*p4d); remove_pud_table(pud_base, addr, next); free_pud_table(pud_base, p4d); } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index bd0d903196d9..175aabf101e8 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -106,7 +106,7 @@ struct page *p4d_page(p4d_t p4d) VM_WARN_ON(!p4d_huge(p4d)); return pte_page(p4d_pte(p4d)); } - return virt_to_page(p4d_page_vaddr(p4d)); + return virt_to_page(p4d_pgtable(p4d)); } #endif diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index cac02ac301f1..5a1efd600f77 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -860,8 +860,8 @@ static inline pmd_t *pud_pgtable(pud_t pud) #define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0UL) #define pud_present(pud) (pud_val(pud) != 0U) #define pud_clear(pudp) (pud_val(*(pudp)) = 0UL) -#define p4d_page_vaddr(p4d) \ - ((unsigned long) __va(p4d_val(p4d))) +#define p4d_pgtable(p4d) \ + ((pud_t *) __va(p4d_val(p4d))) #define p4d_present(p4d) (p4d_val(p4d) != 0U) #define p4d_clear(p4dp) (p4d_val(*(p4dp)) = 0UL) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index a90f6d02fb96..9bacde3ff514 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -906,9 +906,9 @@ static inline int p4d_present(p4d_t p4d) return p4d_flags(p4d) & _PAGE_PRESENT; } -static inline unsigned long p4d_page_vaddr(p4d_t p4d) +static inline pud_t *p4d_pgtable(p4d_t p4d) { - return (unsigned long)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); + return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); } /* diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 20951ab522a1..acf4e50c5988 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -193,8 +193,8 @@ static void sync_global_pgds_l4(unsigned long start, unsigned long end) spin_lock(pgt_lock); if (!p4d_none(*p4d_ref) && !p4d_none(*p4d)) - BUG_ON(p4d_page_vaddr(*p4d) - != p4d_page_vaddr(*p4d_ref)); + BUG_ON(p4d_pgtable(*p4d) + != p4d_pgtable(*p4d_ref)); if (p4d_none(*p4d)) set_p4d(p4d, *p4d_ref); diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h index ce2cbb3c380f..2f1d0aad645c 100644 --- a/include/asm-generic/pgtable-nop4d.h +++ b/include/asm-generic/pgtable-nop4d.h @@ -42,7 +42,7 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) #define __p4d(x) ((p4d_t) { __pgd(x) }) #define pgd_page(pgd) (p4d_page((p4d_t){ pgd })) -#define pgd_page_vaddr(pgd) (p4d_page_vaddr((p4d_t){ pgd })) +#define pgd_page_vaddr(pgd) ((unsigned long)(p4d_pgtable((p4d_t){ pgd }))) /* * allocating and freeing a p4d is trivial: the 1-entry p4d is diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h index 7cbd15f70bf5..eb70c6d7ceff 100644 --- a/include/asm-generic/pgtable-nopud.h +++ b/include/asm-generic/pgtable-nopud.h @@ -49,7 +49,7 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) #define __pud(x) ((pud_t) { __p4d(x) }) #define p4d_page(p4d) (pud_page((pud_t){ p4d })) -#define p4d_page_vaddr(p4d) (pud_pgtable((pud_t){ p4d })) +#define p4d_pgtable(p4d) ((pud_t *)(pud_pgtable((pud_t){ p4d }))) /* * allocating and freeing a pud is trivial: the 1-entry pud is diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index f8570799bc26..f924468d84ec 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -97,7 +97,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) #ifndef pud_offset static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { - return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address); + return p4d_pgtable(*p4d) + pud_index(address); } #define pud_offset pud_offset #endif From 7afd0de0cc1452daf868fed16d3227d5cd0d77c5 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 16 Jun 2023 16:38:13 +0530 Subject: [PATCH 3927/4345] powerpc/book3s64/mm: Fix DirectMap stats in /proc/meminfo [ Upstream commit 0da90af431abc3f497a38ec9ef6e43b0d0dabe80 ] On memory unplug reduce DirectMap page count correctly. root@ubuntu-guest:# grep Direct /proc/meminfo DirectMap4k: 0 kB DirectMap64k: 0 kB DirectMap2M: 115343360 kB DirectMap1G: 0 kB Before fix: root@ubuntu-guest:# ndctl disable-namespace all disabled 1 namespace root@ubuntu-guest:# grep Direct /proc/meminfo DirectMap4k: 0 kB DirectMap64k: 0 kB DirectMap2M: 115343360 kB DirectMap1G: 0 kB After fix: root@ubuntu-guest:# ndctl disable-namespace all disabled 1 namespace root@ubuntu-guest:# grep Direct /proc/meminfo DirectMap4k: 0 kB DirectMap64k: 0 kB DirectMap2M: 104857600 kB DirectMap1G: 0 kB Fixes: a2dc009afa9a ("powerpc/mm/book3s/radix: Add mapping statistics") Signed-off-by: Aneesh Kumar K.V Tested-by: Sachin Sant > Signed-off-by: Michael Ellerman Link: https://msgid.link/20230616110826.344417-4-aneesh.kumar@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/mm/book3s64/radix_pgtable.c | 34 +++++++++++++++--------- 1 file changed, 22 insertions(+), 12 deletions(-) diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 44239e0acf8e..3728c17de87e 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -783,9 +783,9 @@ static void free_pud_table(pud_t *pud_start, p4d_t *p4d) } static void remove_pte_table(pte_t *pte_start, unsigned long addr, - unsigned long end) + unsigned long end, bool direct) { - unsigned long next; + unsigned long next, pages = 0; pte_t *pte; pte = pte_start + pte_index(addr); @@ -807,13 +807,16 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, } pte_clear(&init_mm, addr, pte); + pages++; } + if (direct) + update_page_count(mmu_virtual_psize, -pages); } static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, - unsigned long end) + unsigned long end, bool direct) { - unsigned long next; + unsigned long next, pages = 0; pte_t *pte_base; pmd_t *pmd; @@ -831,19 +834,22 @@ static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, continue; } pte_clear(&init_mm, addr, (pte_t *)pmd); + pages++; continue; } pte_base = (pte_t *)pmd_page_vaddr(*pmd); - remove_pte_table(pte_base, addr, next); + remove_pte_table(pte_base, addr, next, direct); free_pte_table(pte_base, pmd); } + if (direct) + update_page_count(MMU_PAGE_2M, -pages); } static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, - unsigned long end) + unsigned long end, bool direct) { - unsigned long next; + unsigned long next, pages = 0; pmd_t *pmd_base; pud_t *pud; @@ -861,16 +867,20 @@ static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, continue; } pte_clear(&init_mm, addr, (pte_t *)pud); + pages++; continue; } pmd_base = pud_pgtable(*pud); - remove_pmd_table(pmd_base, addr, next); + remove_pmd_table(pmd_base, addr, next, direct); free_pmd_table(pmd_base, pud); } + if (direct) + update_page_count(MMU_PAGE_1G, -pages); } -static void __meminit remove_pagetable(unsigned long start, unsigned long end) +static void __meminit remove_pagetable(unsigned long start, unsigned long end, + bool direct) { unsigned long addr, next; pud_t *pud_base; @@ -899,7 +909,7 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end) } pud_base = p4d_pgtable(*p4d); - remove_pud_table(pud_base, addr, next); + remove_pud_table(pud_base, addr, next, direct); free_pud_table(pud_base, p4d); } @@ -922,7 +932,7 @@ int __meminit radix__create_section_mapping(unsigned long start, int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end) { - remove_pagetable(start, end); + remove_pagetable(start, end, true); return 0; } #endif /* CONFIG_MEMORY_HOTPLUG */ @@ -958,7 +968,7 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start, #ifdef CONFIG_MEMORY_HOTPLUG void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size) { - remove_pagetable(start, start + page_size); + remove_pagetable(start, start + page_size, false); } #endif #endif From aba192bb31df0da0eb5984132d0304d517708423 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 16 Jun 2023 16:38:15 +0530 Subject: [PATCH 3928/4345] powerpc/mm/dax: Fix the condition when checking if altmap vmemap can cross-boundary [ Upstream commit c8eebc4a99f15280654f23e914e746c40a516e50 ] Without this fix, the last subsection vmemmap can end up in memory even if the namespace is created with -M mem and has sufficient space in the altmap area. Fixes: cf387d9644d8 ("libnvdimm/altmap: Track namespace boundaries in altmap") Signed-off-by: Aneesh Kumar K.V Tested-by: Sachin Sant > Signed-off-by: Michael Ellerman Link: https://msgid.link/20230616110826.344417-6-aneesh.kumar@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/mm/init_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 386be136026e..b76cd49d521b 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -188,7 +188,7 @@ static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long star unsigned long nr_pfn = page_size / sizeof(struct page); unsigned long start_pfn = page_to_pfn((struct page *)start); - if ((start_pfn + nr_pfn) > altmap->end_pfn) + if ((start_pfn + nr_pfn - 1) > altmap->end_pfn) return true; if (start_pfn < altmap->base_pfn) From 5f23dae018c6b916e96ca398fa933750cca939e2 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Thu, 28 Oct 2021 12:11:08 +0200 Subject: [PATCH 3929/4345] hwrng: virtio - add an internal buffer [ Upstream commit bf3175bc50a3754dc427e2f5046e17a9fafc8be7 ] hwrng core uses two buffers that can be mixed in the virtio-rng queue. If the buffer is provided with wait=0 it is enqueued in the virtio-rng queue but unused by the caller. On the next call, core provides another buffer but the first one is filled instead and the new one queued. And the caller reads the data from the new one that is not updated, and the data in the first one are lost. To avoid this mix, virtio-rng needs to use its own unique internal buffer at a cost of a data copy to the caller buffer. Signed-off-by: Laurent Vivier Link: https://lore.kernel.org/r/20211028101111.128049-2-lvivier@redhat.com Signed-off-by: Michael S. Tsirkin Stable-dep-of: ac52578d6e8d ("hwrng: virtio - Fix race on data_avail and actual data") Signed-off-by: Sasha Levin --- drivers/char/hw_random/virtio-rng.c | 43 ++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 10 deletions(-) diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index a90001e02bf7..208c547dcac1 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -18,13 +18,20 @@ static DEFINE_IDA(rng_index_ida); struct virtrng_info { struct hwrng hwrng; struct virtqueue *vq; - struct completion have_data; char name[25]; - unsigned int data_avail; int index; bool busy; bool hwrng_register_done; bool hwrng_removed; + /* data transfer */ + struct completion have_data; + unsigned int data_avail; + /* minimal size returned by rng_buffer_size() */ +#if SMP_CACHE_BYTES < 32 + u8 data[32]; +#else + u8 data[SMP_CACHE_BYTES]; +#endif }; static void random_recv_done(struct virtqueue *vq) @@ -39,14 +46,14 @@ static void random_recv_done(struct virtqueue *vq) } /* The host will fill any buffer we give it with sweet, sweet randomness. */ -static void register_buffer(struct virtrng_info *vi, u8 *buf, size_t size) +static void register_buffer(struct virtrng_info *vi) { struct scatterlist sg; - sg_init_one(&sg, buf, size); + sg_init_one(&sg, vi->data, sizeof(vi->data)); /* There should always be room for one buffer. */ - virtqueue_add_inbuf(vi->vq, &sg, 1, buf, GFP_KERNEL); + virtqueue_add_inbuf(vi->vq, &sg, 1, vi->data, GFP_KERNEL); virtqueue_kick(vi->vq); } @@ -55,6 +62,8 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) { int ret; struct virtrng_info *vi = (struct virtrng_info *)rng->priv; + unsigned int chunk; + size_t read; if (vi->hwrng_removed) return -ENODEV; @@ -62,19 +71,33 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) if (!vi->busy) { vi->busy = true; reinit_completion(&vi->have_data); - register_buffer(vi, buf, size); + register_buffer(vi); } if (!wait) return 0; - ret = wait_for_completion_killable(&vi->have_data); - if (ret < 0) - return ret; + read = 0; + while (size != 0) { + ret = wait_for_completion_killable(&vi->have_data); + if (ret < 0) + return ret; + + chunk = min_t(unsigned int, size, vi->data_avail); + memcpy(buf + read, vi->data, chunk); + read += chunk; + size -= chunk; + vi->data_avail = 0; + + if (size != 0) { + reinit_completion(&vi->have_data); + register_buffer(vi); + } + } vi->busy = false; - return vi->data_avail; + return read; } static void virtio_cleanup(struct hwrng *rng) From d13ea82bfe150fce7cbd5defc888d31d3a33fc91 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Thu, 28 Oct 2021 12:11:09 +0200 Subject: [PATCH 3930/4345] hwrng: virtio - don't wait on cleanup [ Upstream commit 2bb31abdbe55742c89f4dc0cc26fcbc8467364f6 ] When virtio-rng device was dropped by the hwrng core we were forced to wait the buffer to come back from the device to not have remaining ongoing operation that could spoil the buffer. But now, as the buffer is internal to the virtio-rng we can release the waiting loop immediately, the buffer will be retrieve and use when the virtio-rng driver will be selected again. This avoids to hang on an rng_current write command if the virtio-rng device is blocked by a lack of entropy. This allows to select another entropy source if the current one is empty. Signed-off-by: Laurent Vivier Link: https://lore.kernel.org/r/20211028101111.128049-3-lvivier@redhat.com Signed-off-by: Michael S. Tsirkin Stable-dep-of: ac52578d6e8d ("hwrng: virtio - Fix race on data_avail and actual data") Signed-off-by: Sasha Levin --- drivers/char/hw_random/virtio-rng.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 208c547dcac1..173aeea835bb 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -82,6 +82,11 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) ret = wait_for_completion_killable(&vi->have_data); if (ret < 0) return ret; + /* if vi->data_avail is 0, we have been interrupted + * by a cleanup, but buffer stays in the queue + */ + if (vi->data_avail == 0) + return read; chunk = min_t(unsigned int, size, vi->data_avail); memcpy(buf + read, vi->data, chunk); @@ -105,7 +110,7 @@ static void virtio_cleanup(struct hwrng *rng) struct virtrng_info *vi = (struct virtrng_info *)rng->priv; if (vi->busy) - wait_for_completion(&vi->have_data); + complete(&vi->have_data); } static int probe_common(struct virtio_device *vdev) From ffc5ce9c272fc39de3acae3f4a1124bd06b9f54b Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Thu, 28 Oct 2021 12:11:10 +0200 Subject: [PATCH 3931/4345] hwrng: virtio - don't waste entropy [ Upstream commit 5c8e933050044d6dd2a000f9a5756ae73cbe7c44 ] if we don't use all the entropy available in the buffer, keep it and use it later. Signed-off-by: Laurent Vivier Link: https://lore.kernel.org/r/20211028101111.128049-4-lvivier@redhat.com Signed-off-by: Michael S. Tsirkin Stable-dep-of: ac52578d6e8d ("hwrng: virtio - Fix race on data_avail and actual data") Signed-off-by: Sasha Levin --- drivers/char/hw_random/virtio-rng.c | 52 +++++++++++++++++++---------- 1 file changed, 35 insertions(+), 17 deletions(-) diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 173aeea835bb..8ba97cf4ca8f 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -26,6 +26,7 @@ struct virtrng_info { /* data transfer */ struct completion have_data; unsigned int data_avail; + unsigned int data_idx; /* minimal size returned by rng_buffer_size() */ #if SMP_CACHE_BYTES < 32 u8 data[32]; @@ -42,6 +43,9 @@ static void random_recv_done(struct virtqueue *vq) if (!virtqueue_get_buf(vi->vq, &vi->data_avail)) return; + vi->data_idx = 0; + vi->busy = false; + complete(&vi->have_data); } @@ -58,6 +62,16 @@ static void register_buffer(struct virtrng_info *vi) virtqueue_kick(vi->vq); } +static unsigned int copy_data(struct virtrng_info *vi, void *buf, + unsigned int size) +{ + size = min_t(unsigned int, size, vi->data_avail); + memcpy(buf, vi->data + vi->data_idx, size); + vi->data_idx += size; + vi->data_avail -= size; + return size; +} + static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) { int ret; @@ -68,17 +82,29 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) if (vi->hwrng_removed) return -ENODEV; - if (!vi->busy) { - vi->busy = true; - reinit_completion(&vi->have_data); - register_buffer(vi); + read = 0; + + /* copy available data */ + if (vi->data_avail) { + chunk = copy_data(vi, buf, size); + size -= chunk; + read += chunk; } if (!wait) - return 0; + return read; - read = 0; + /* We have already copied available entropy, + * so either size is 0 or data_avail is 0 + */ while (size != 0) { + /* data_avail is 0 */ + if (!vi->busy) { + /* no pending request, ask for more */ + vi->busy = true; + reinit_completion(&vi->have_data); + register_buffer(vi); + } ret = wait_for_completion_killable(&vi->have_data); if (ret < 0) return ret; @@ -88,20 +114,11 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) if (vi->data_avail == 0) return read; - chunk = min_t(unsigned int, size, vi->data_avail); - memcpy(buf + read, vi->data, chunk); - read += chunk; + chunk = copy_data(vi, buf + read, size); size -= chunk; - vi->data_avail = 0; - - if (size != 0) { - reinit_completion(&vi->have_data); - register_buffer(vi); - } + read += chunk; } - vi->busy = false; - return read; } @@ -161,6 +178,7 @@ static void remove_common(struct virtio_device *vdev) vi->hwrng_removed = true; vi->data_avail = 0; + vi->data_idx = 0; complete(&vi->have_data); vdev->config->reset(vdev); vi->busy = false; From e8f51401d642a8070851f1c7d9f415fe1cf8f3fc Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Thu, 28 Oct 2021 12:11:11 +0200 Subject: [PATCH 3932/4345] hwrng: virtio - always add a pending request [ Upstream commit 9a4b612d675b03f7fc9fa1957ca399c8223f3954 ] If we ensure we have already some data available by enqueuing again the buffer once data are exhausted, we can return what we have without waiting for the device answer. Signed-off-by: Laurent Vivier Link: https://lore.kernel.org/r/20211028101111.128049-5-lvivier@redhat.com Signed-off-by: Michael S. Tsirkin Stable-dep-of: ac52578d6e8d ("hwrng: virtio - Fix race on data_avail and actual data") Signed-off-by: Sasha Levin --- drivers/char/hw_random/virtio-rng.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 8ba97cf4ca8f..0a7dde135db1 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -20,7 +20,6 @@ struct virtrng_info { struct virtqueue *vq; char name[25]; int index; - bool busy; bool hwrng_register_done; bool hwrng_removed; /* data transfer */ @@ -44,16 +43,18 @@ static void random_recv_done(struct virtqueue *vq) return; vi->data_idx = 0; - vi->busy = false; complete(&vi->have_data); } -/* The host will fill any buffer we give it with sweet, sweet randomness. */ -static void register_buffer(struct virtrng_info *vi) +static void request_entropy(struct virtrng_info *vi) { struct scatterlist sg; + reinit_completion(&vi->have_data); + vi->data_avail = 0; + vi->data_idx = 0; + sg_init_one(&sg, vi->data, sizeof(vi->data)); /* There should always be room for one buffer. */ @@ -69,6 +70,8 @@ static unsigned int copy_data(struct virtrng_info *vi, void *buf, memcpy(buf, vi->data + vi->data_idx, size); vi->data_idx += size; vi->data_avail -= size; + if (vi->data_avail == 0) + request_entropy(vi); return size; } @@ -98,13 +101,7 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) * so either size is 0 or data_avail is 0 */ while (size != 0) { - /* data_avail is 0 */ - if (!vi->busy) { - /* no pending request, ask for more */ - vi->busy = true; - reinit_completion(&vi->have_data); - register_buffer(vi); - } + /* data_avail is 0 but a request is pending */ ret = wait_for_completion_killable(&vi->have_data); if (ret < 0) return ret; @@ -126,8 +123,7 @@ static void virtio_cleanup(struct hwrng *rng) { struct virtrng_info *vi = (struct virtrng_info *)rng->priv; - if (vi->busy) - complete(&vi->have_data); + complete(&vi->have_data); } static int probe_common(struct virtio_device *vdev) @@ -163,6 +159,9 @@ static int probe_common(struct virtio_device *vdev) goto err_find; } + /* we always have a pending entropy request */ + request_entropy(vi); + return 0; err_find: @@ -181,7 +180,6 @@ static void remove_common(struct virtio_device *vdev) vi->data_idx = 0; complete(&vi->have_data); vdev->config->reset(vdev); - vi->busy = false; if (vi->hwrng_register_done) hwrng_unregister(&vi->hwrng); vdev->config->del_vqs(vdev); From 77471e4912d3960dafe141e268c44be8024fe4dc Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 4 May 2023 11:59:32 +0800 Subject: [PATCH 3933/4345] hwrng: virtio - Fix race on data_avail and actual data [ Upstream commit ac52578d6e8d300dd50f790f29a24169b1edd26c ] The virtio rng device kicks off a new entropy request whenever the data available reaches zero. When a new request occurs at the end of a read operation, that is, when the result of that request is only needed by the next reader, then there is a race between the writing of the new data and the next reader. This is because there is no synchronisation whatsoever between the writer and the reader. Fix this by writing data_avail with smp_store_release and reading it with smp_load_acquire when we first enter read. The subsequent reads are safe because they're either protected by the first load acquire, or by the completion mechanism. Also remove the redundant zeroing of data_idx in random_recv_done (data_idx must already be zero at this point) and data_avail in request_entropy (ditto). Reported-by: syzbot+726dc8c62c3536431ceb@syzkaller.appspotmail.com Fixes: f7f510ec1957 ("virtio: An entropy device, as suggested by hpa.") Signed-off-by: Herbert Xu Acked-by: Michael S. Tsirkin Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/char/hw_random/virtio-rng.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 0a7dde135db1..3a194eb3ce8a 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -4,6 +4,7 @@ * Copyright (C) 2007, 2008 Rusty Russell IBM Corporation */ +#include #include #include #include @@ -37,13 +38,13 @@ struct virtrng_info { static void random_recv_done(struct virtqueue *vq) { struct virtrng_info *vi = vq->vdev->priv; + unsigned int len; /* We can get spurious callbacks, e.g. shared IRQs + virtio_pci. */ - if (!virtqueue_get_buf(vi->vq, &vi->data_avail)) + if (!virtqueue_get_buf(vi->vq, &len)) return; - vi->data_idx = 0; - + smp_store_release(&vi->data_avail, len); complete(&vi->have_data); } @@ -52,7 +53,6 @@ static void request_entropy(struct virtrng_info *vi) struct scatterlist sg; reinit_completion(&vi->have_data); - vi->data_avail = 0; vi->data_idx = 0; sg_init_one(&sg, vi->data, sizeof(vi->data)); @@ -88,7 +88,7 @@ static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait) read = 0; /* copy available data */ - if (vi->data_avail) { + if (smp_load_acquire(&vi->data_avail)) { chunk = copy_data(vi, buf, size); size -= chunk; read += chunk; From 31195ee328e98d8347124b989437f36ab06c222f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 19 May 2023 15:33:34 -0700 Subject: [PATCH 3934/4345] crypto: nx - fix build warnings when DEBUG_FS is not enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b04b076fb56560b39d695ac3744db457e12278fd ] Fix build warnings when DEBUG_FS is not enabled by using an empty do-while loop instead of a value: In file included from ../drivers/crypto/nx/nx.c:27: ../drivers/crypto/nx/nx.c: In function 'nx_register_algs': ../drivers/crypto/nx/nx.h:173:33: warning: statement with no effect [-Wunused-value] 173 | #define NX_DEBUGFS_INIT(drv) (0) ../drivers/crypto/nx/nx.c:573:9: note: in expansion of macro 'NX_DEBUGFS_INIT' 573 | NX_DEBUGFS_INIT(&nx_driver); ../drivers/crypto/nx/nx.c: In function 'nx_remove': ../drivers/crypto/nx/nx.h:174:33: warning: statement with no effect [-Wunused-value] 174 | #define NX_DEBUGFS_FINI(drv) (0) ../drivers/crypto/nx/nx.c:793:17: note: in expansion of macro 'NX_DEBUGFS_FINI' 793 | NX_DEBUGFS_FINI(&nx_driver); Also, there is no need to build nx_debugfs.o when DEBUG_FS is not enabled, so change the Makefile to accommodate that. Fixes: ae0222b7289d ("powerpc/crypto: nx driver code supporting nx encryption") Fixes: aef7b31c8833 ("powerpc/crypto: Build files for the nx device driver") Signed-off-by: Randy Dunlap Cc: Breno Leitão Cc: Nayna Jain Cc: Paulo Flabiano Smorigo Cc: Herbert Xu Cc: "David S. Miller" Cc: linux-crypto@vger.kernel.org Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/nx/Makefile | 2 +- drivers/crypto/nx/nx.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/crypto/nx/Makefile b/drivers/crypto/nx/Makefile index bc89a20e5d9d..351822a598f9 100644 --- a/drivers/crypto/nx/Makefile +++ b/drivers/crypto/nx/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CRYPTO_DEV_NX_ENCRYPT) += nx-crypto.o nx-crypto-objs := nx.o \ - nx_debugfs.o \ nx-aes-cbc.o \ nx-aes-ecb.o \ nx-aes-gcm.o \ @@ -11,6 +10,7 @@ nx-crypto-objs := nx.o \ nx-sha256.o \ nx-sha512.o +nx-crypto-$(CONFIG_DEBUG_FS) += nx_debugfs.o obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_PSERIES) += nx-compress-pseries.o nx-compress.o obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_POWERNV) += nx-compress-powernv.o nx-compress.o nx-compress-objs := nx-842.o diff --git a/drivers/crypto/nx/nx.h b/drivers/crypto/nx/nx.h index c6233173c612..2697baebb6a3 100644 --- a/drivers/crypto/nx/nx.h +++ b/drivers/crypto/nx/nx.h @@ -170,8 +170,8 @@ struct nx_sg *nx_walk_and_build(struct nx_sg *, unsigned int, void nx_debugfs_init(struct nx_crypto_driver *); void nx_debugfs_fini(struct nx_crypto_driver *); #else -#define NX_DEBUGFS_INIT(drv) (0) -#define NX_DEBUGFS_FINI(drv) (0) +#define NX_DEBUGFS_INIT(drv) do {} while (0) +#define NX_DEBUGFS_FINI(drv) do {} while (0) #endif #define NX_PAGE_NUM(x) ((u64)(x) & 0xfffffffffffff000ULL) From 88978ef7fdefc31e00a2c30ded46f06abc03def1 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 1 Jun 2023 21:09:55 +0900 Subject: [PATCH 3935/4345] modpost: fix section mismatch message for R_ARM_ABS32 [ Upstream commit b7c63520f6703a25eebb4f8138fed764fcae1c6f ] addend_arm_rel() processes R_ARM_ABS32 in a wrong way. Here, test code. [test code 1] #include int __initdata foo; int get_foo(void) { return foo; } If you compile it with ARM versatile_defconfig, modpost will show the symbol name, (unknown). WARNING: modpost: vmlinux.o: section mismatch in reference: get_foo (section: .text) -> (unknown) (section: .init.data) (You need to use GNU linker instead of LLD to reproduce it.) If you compile it for other architectures, modpost will show the correct symbol name. WARNING: modpost: vmlinux.o: section mismatch in reference: get_foo (section: .text) -> foo (section: .init.data) For R_ARM_ABS32, addend_arm_rel() sets r->r_addend to a wrong value. I just mimicked the code in arch/arm/kernel/module.c. However, there is more difficulty for ARM. Here, test code. [test code 2] #include int __initdata foo; int get_foo(void) { return foo; } int __initdata bar; int get_bar(void) { return bar; } With this commit applied, modpost will show the following messages for ARM versatile_defconfig: WARNING: modpost: vmlinux.o: section mismatch in reference: get_foo (section: .text) -> foo (section: .init.data) WARNING: modpost: vmlinux.o: section mismatch in reference: get_bar (section: .text) -> foo (section: .init.data) The reference from 'get_bar' to 'foo' seems wrong. I have no solution for this because it is true in assembly level. In the following output, relocation at 0x1c is no longer associated with 'bar'. The two relocation entries point to the same symbol, and the offset to 'bar' is encoded in the instruction 'r0, [r3, #4]'. Disassembly of section .text: 00000000 : 0: e59f3004 ldr r3, [pc, #4] @ c 4: e5930000 ldr r0, [r3] 8: e12fff1e bx lr c: 00000000 .word 0x00000000 00000010 : 10: e59f3004 ldr r3, [pc, #4] @ 1c 14: e5930004 ldr r0, [r3, #4] 18: e12fff1e bx lr 1c: 00000000 .word 0x00000000 Relocation section '.rel.text' at offset 0x244 contains 2 entries: Offset Info Type Sym.Value Sym. Name 0000000c 00000c02 R_ARM_ABS32 00000000 .init.data 0000001c 00000c02 R_ARM_ABS32 00000000 .init.data When find_elf_symbol() gets into a situation where relsym->st_name is zero, there is no guarantee to get the symbol name as written in C. I am keeping the current logic because it is useful in many architectures, but the symbol name is not always correct depending on the optimization. I left some comments in find_tosym(). Fixes: 56a974fa2d59 ("kbuild: make better section mismatch reports on arm") Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- scripts/mod/modpost.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index e48742760fec..9216eae798ff 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1313,6 +1313,10 @@ static Elf_Sym *find_elf_symbol(struct elf_info *elf, Elf64_Sword addr, if (relsym->st_name != 0) return relsym; + /* + * Strive to find a better symbol name, but the resulting name may not + * match the symbol referenced in the original code. + */ relsym_secindex = get_secindex(elf, relsym); for (sym = elf->symtab_start; sym < elf->symtab_stop; sym++) { if (get_secindex(elf, sym) != relsym_secindex) @@ -1795,12 +1799,14 @@ static int addend_386_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r) static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r) { unsigned int r_typ = ELF_R_TYPE(r->r_info); + Elf_Sym *sym = elf->symtab_start + ELF_R_SYM(r->r_info); + void *loc = reloc_location(elf, sechdr, r); + uint32_t inst; switch (r_typ) { case R_ARM_ABS32: - /* From ARM ABI: (S + A) | T */ - r->r_addend = (int)(long) - (elf->symtab_start + ELF_R_SYM(r->r_info)); + inst = TO_NATIVE(*(uint32_t *)loc); + r->r_addend = inst + sym->st_value; break; case R_ARM_PC24: case R_ARM_CALL: From b54069445591ba444e8cbbe00f1bce686e771873 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 1 Jun 2023 21:09:56 +0900 Subject: [PATCH 3936/4345] modpost: fix section mismatch message for R_ARM_{PC24,CALL,JUMP24} [ Upstream commit 56a24b8ce6a7f9c4a21b2276a8644f6f3d8fc14d ] addend_arm_rel() processes R_ARM_PC24, R_ARM_CALL, R_ARM_JUMP24 in a wrong way. Here, test code. [test code for R_ARM_JUMP24] .section .init.text,"ax" bar: bx lr .section .text,"ax" .globl foo foo: b bar [test code for R_ARM_CALL] .section .init.text,"ax" bar: bx lr .section .text,"ax" .globl foo foo: push {lr} bl bar pop {pc} If you compile it with ARM multi_v7_defconfig, modpost will show the symbol name, (unknown). WARNING: modpost: vmlinux.o: section mismatch in reference: foo (section: .text) -> (unknown) (section: .init.text) (You need to use GNU linker instead of LLD to reproduce it.) Fix the code to make modpost show the correct symbol name. I imported (with adjustment) sign_extend32() from include/linux/bitops.h. The '+8' is the compensation for pc-relative instruction. It is documented in "ELF for the Arm Architecture" [1]. "If the relocation is pc-relative then compensation for the PC bias (the PC value is 8 bytes ahead of the executing instruction in Arm state and 4 bytes in Thumb state) must be encoded in the relocation by the object producer." [1]: https://github.com/ARM-software/abi-aa/blob/main/aaelf32/aaelf32.rst Fixes: 56a974fa2d59 ("kbuild: make better section mismatch reports on arm") Fixes: 6e2e340b59d2 ("ARM: 7324/1: modpost: Fix section warnings for ARM for many compilers") Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- scripts/mod/modpost.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 9216eae798ff..fb7f75fa786b 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1796,12 +1796,20 @@ static int addend_386_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r) #define R_ARM_THM_JUMP19 51 #endif +static int32_t sign_extend32(int32_t value, int index) +{ + uint8_t shift = 31 - index; + + return (int32_t)(value << shift) >> shift; +} + static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r) { unsigned int r_typ = ELF_R_TYPE(r->r_info); Elf_Sym *sym = elf->symtab_start + ELF_R_SYM(r->r_info); void *loc = reloc_location(elf, sechdr, r); uint32_t inst; + int32_t offset; switch (r_typ) { case R_ARM_ABS32: @@ -1811,6 +1819,10 @@ static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r) case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: + inst = TO_NATIVE(*(uint32_t *)loc); + offset = sign_extend32((inst & 0x00ffffff) << 2, 25); + r->r_addend = offset + sym->st_value + 8; + break; case R_ARM_THM_CALL: case R_ARM_THM_JUMP24: case R_ARM_THM_JUMP19: From f0350516b9d26578e0e520424a825325805c2772 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 May 2023 10:33:04 +0200 Subject: [PATCH 3937/4345] crypto: marvell/cesa - Fix type mismatch warning [ Upstream commit efbc7764c4446566edb76ca05e903b5905673d2e ] Commit df8fc4e934c1 ("kbuild: Enable -fstrict-flex-arrays=3") uncovered a type mismatch in cesa 3des support that leads to a memcpy beyond the end of a structure: In function 'fortify_memcpy_chk', inlined from 'mv_cesa_des3_ede_setkey' at drivers/crypto/marvell/cesa/cipher.c:307:2: include/linux/fortify-string.h:583:25: error: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror=attribute-warning] 583 | __write_overflow_field(p_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ This is probably harmless as the actual data that is copied has the correct type, but clearly worth fixing nonetheless. Fixes: 4ada48397823 ("crypto: marvell/cesa - add Triple-DES support") Cc: Kees Cook Cc: Gustavo A. R. Silva Signed-off-by: Arnd Bergmann Reviewed-by: Kees Cook Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/crypto/marvell/cesa/cipher.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/marvell/cesa/cipher.c b/drivers/crypto/marvell/cesa/cipher.c index 596a8c74e40a..8dc10f998894 100644 --- a/drivers/crypto/marvell/cesa/cipher.c +++ b/drivers/crypto/marvell/cesa/cipher.c @@ -287,7 +287,7 @@ static int mv_cesa_des_setkey(struct crypto_skcipher *cipher, const u8 *key, static int mv_cesa_des3_ede_setkey(struct crypto_skcipher *cipher, const u8 *key, unsigned int len) { - struct mv_cesa_des_ctx *ctx = crypto_skcipher_ctx(cipher); + struct mv_cesa_des3_ctx *ctx = crypto_skcipher_ctx(cipher); int err; err = verify_skcipher_des3_key(cipher, key); From cb0cdca5c979bc34c27602e2039562932c2591a4 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 8 Jun 2023 11:23:40 +0300 Subject: [PATCH 3938/4345] modpost: fix off by one in is_executable_section() [ Upstream commit 3a3f1e573a105328a2cca45a7cfbebabbf5e3192 ] The > comparison should be >= to prevent an out of bounds array access. Fixes: 52dc0595d540 ("modpost: handle relocations mismatch in __ex_table.") Signed-off-by: Dan Carpenter Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- scripts/mod/modpost.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index fb7f75fa786b..78ac98cfa02d 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1621,7 +1621,7 @@ static void default_mismatch_handler(const char *modname, struct elf_info *elf, static int is_executable_section(struct elf_info* elf, unsigned int section_index) { - if (section_index > elf->num_sections) + if (section_index >= elf->num_sections) fatal("section_index is outside elf->num_sections!\n"); return ((elf->sechdrs[section_index].sh_flags & SHF_EXECINSTR) == SHF_EXECINSTR); From bab0bf56779769cd0878edb8030b66b73c17f24a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 12 Jun 2023 00:50:50 +0900 Subject: [PATCH 3939/4345] ARC: define ASM_NL and __ALIGN(_STR) outside #ifdef __ASSEMBLY__ guard [ Upstream commit 92e2921eeafdfca9acd9b83f07d2b7ca099bac24 ] ASM_NL is useful not only in *.S files but also in .c files for using inline assembler in C code. On ARC, however, ASM_NL is evaluated inconsistently. It is expanded to a backquote (`) in *.S files, but a semicolon (;) in *.c files because arch/arc/include/asm/linkage.h defines it inside #ifdef __ASSEMBLY__, so the definition for C code falls back to the default value defined in include/linux/linkage.h. If ASM_NL is used in inline assembler in .c files, it will result in wrong assembly code because a semicolon is not an instruction separator, but the start of a comment for ARC. Move ASM_NL (also __ALIGN and __ALIGN_STR) out of the #ifdef. Fixes: 9df62f054406 ("arch: use ASM_NL instead of ';' for assembler new line character in the macro") Fixes: 8d92e992a785 ("ARC: define __ALIGN_STR and __ALIGN symbols for ARC") Signed-off-by: Masahiro Yamada Signed-off-by: Sasha Levin --- arch/arc/include/asm/linkage.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h index c9434ff3aa4c..8a3fb71e9cfa 100644 --- a/arch/arc/include/asm/linkage.h +++ b/arch/arc/include/asm/linkage.h @@ -8,6 +8,10 @@ #include +#define ASM_NL ` /* use '`' to mark new line in macro */ +#define __ALIGN .align 4 +#define __ALIGN_STR __stringify(__ALIGN) + #ifdef __ASSEMBLY__ .macro ST2 e, o, off @@ -28,10 +32,6 @@ #endif .endm -#define ASM_NL ` /* use '`' to mark new line in macro */ -#define __ALIGN .align 4 -#define __ALIGN_STR __stringify(__ALIGN) - /* annotation for data we want in DCCM - if enabled in .config */ .macro ARCFP_DATA nm #ifdef CONFIG_ARC_HAS_DCCM From 7c9f5a14d93b786568604994f4a221254c1862ea Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Sun, 18 Jun 2023 17:32:25 -0400 Subject: [PATCH 3940/4345] NFSv4.1: freeze the session table upon receiving NFS4ERR_BADSESSION [ Upstream commit c907e72f58ed979a24a9fdcadfbc447c51d5e509 ] When the client received NFS4ERR_BADSESSION, it schedules recovery and start the state manager thread which in turn freezes the session table and does not allow for any new requests to use the no-longer valid session. However, it is possible that before the state manager thread runs, a new operation would use the released slot that received BADSESSION and was therefore not updated its sequence number. Such re-use of the slot can lead the application errors. Fixes: 5c441544f045 ("NFSv4.x: Handle bad/dead sessions correctly in nfs41_sequence_process()") Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- fs/nfs/nfs4proc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index bca5d1bdd79b..b9567cc8698e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -926,6 +926,7 @@ out: out_noaction: return ret; session_recover: + set_bit(NFS4_SLOT_TBL_DRAINING, &session->fc_slot_table.slot_tbl_state); nfs4_schedule_session_recovery(session, status); dprintk("%s ERROR: %d Reset session\n", __func__, status); nfs41_sequence_free_slot(res); From 94a85474f5e3e518bdbf8c9f51cb343d734a04f7 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 2 Jun 2023 23:13:54 -0700 Subject: [PATCH 3941/4345] dax: Fix dax_mapping_release() use after free [ Upstream commit 6d24b170a9db0456f577b1ab01226a2254c016a8 ] A CONFIG_DEBUG_KOBJECT_RELEASE test of removing a device-dax region provider (like modprobe -r dax_hmem) yields: kobject: 'mapping0' (ffff93eb460e8800): kobject_release, parent 0000000000000000 (delayed 2000) [..] DEBUG_LOCKS_WARN_ON(1) WARNING: CPU: 23 PID: 282 at kernel/locking/lockdep.c:232 __lock_acquire+0x9fc/0x2260 [..] RIP: 0010:__lock_acquire+0x9fc/0x2260 [..] Call Trace: [..] lock_acquire+0xd4/0x2c0 ? ida_free+0x62/0x130 _raw_spin_lock_irqsave+0x47/0x70 ? ida_free+0x62/0x130 ida_free+0x62/0x130 dax_mapping_release+0x1f/0x30 device_release+0x36/0x90 kobject_delayed_cleanup+0x46/0x150 Due to attempting ida_free() on an ida object that has already been freed. Devices typically only hold a reference on their parent while registered. If a child needs a parent object to complete its release it needs to hold a reference that it drops from its release callback. Arrange for a dax_mapping to pin its parent dev_dax instance until dax_mapping_release(). Fixes: 0b07ce872a9e ("device-dax: introduce 'mapping' devices") Signed-off-by: Dan Williams Link: https://lore.kernel.org/r/168577283412.1672036.16111545266174261446.stgit@dwillia2-xfh.jf.intel.com Reviewed-by: Dave Jiang Reviewed-by: Fan Ni Reviewed-by: Ira Weiny Signed-off-by: Vishal Verma Signed-off-by: Sasha Levin --- drivers/dax/bus.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index a02777c93c07..48b7f0a64eb8 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -592,10 +592,12 @@ EXPORT_SYMBOL_GPL(alloc_dax_region); static void dax_mapping_release(struct device *dev) { struct dax_mapping *mapping = to_dax_mapping(dev); - struct dev_dax *dev_dax = to_dev_dax(dev->parent); + struct device *parent = dev->parent; + struct dev_dax *dev_dax = to_dev_dax(parent); ida_free(&dev_dax->ida, mapping->id); kfree(mapping); + put_device(parent); } static void unregister_dax_mapping(void *data) @@ -735,6 +737,7 @@ static int devm_register_dax_mapping(struct dev_dax *dev_dax, int range_id) dev = &mapping->dev; device_initialize(dev); dev->parent = &dev_dax->dev; + get_device(dev->parent); dev->type = &dax_mapping_type; dev_set_name(dev, "mapping%d", mapping->id); rc = device_add(dev); From 557e528255d5f5ea87b0db91969f317ebf4367f2 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 2 Jun 2023 23:14:05 -0700 Subject: [PATCH 3942/4345] dax: Introduce alloc_dev_dax_id() [ Upstream commit 70aab281e18c68a1284bc387de127c2fc0bed3f8 ] The reference counting of dax_region objects is needlessly complicated, has lead to confusion [1], and has hidden a bug [2]. Towards cleaning up that mess introduce alloc_dev_dax_id() to minimize the holding of a dax_region reference to only what dev_dax_release() needs, the dax_region->ida. Part of the reason for the mess was the design to dereference a dax_region in all cases in free_dev_dax_id() even if the id was statically assigned by the upper level dax_region driver. Remove the need to call "is_static(dax_region)" by tracking whether the id is dynamic directly in the dev_dax instance itself. With that flag the dax_region pinning and release per dev_dax instance can move to alloc_dev_dax_id() and free_dev_dax_id() respectively. A follow-on cleanup address the unnecessary references in the dax_region setup and drivers. Fixes: 0f3da14a4f05 ("device-dax: introduce 'seed' devices") Link: http://lore.kernel.org/r/20221203095858.612027-1-liuyongqiang13@huawei.com [1] Link: http://lore.kernel.org/r/3cf0890b-4eb0-e70e-cd9c-2ecc3d496263@hpe.com [2] Reported-by: Yongqiang Liu Reported-by: Paul Cassella Reported-by: Ira Weiny Signed-off-by: Dan Williams Link: https://lore.kernel.org/r/168577284563.1672036.13493034988900989554.stgit@dwillia2-xfh.jf.intel.com Reviewed-by: Ira Weiny Signed-off-by: Vishal Verma Signed-off-by: Sasha Levin --- drivers/dax/bus.c | 56 ++++++++++++++++++++++++--------------- drivers/dax/dax-private.h | 4 ++- 2 files changed, 37 insertions(+), 23 deletions(-) diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 48b7f0a64eb8..0541b7e4d5c6 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -403,18 +403,34 @@ static void unregister_dev_dax(void *dev) put_device(dev); } +static void dax_region_free(struct kref *kref) +{ + struct dax_region *dax_region; + + dax_region = container_of(kref, struct dax_region, kref); + kfree(dax_region); +} + +void dax_region_put(struct dax_region *dax_region) +{ + kref_put(&dax_region->kref, dax_region_free); +} +EXPORT_SYMBOL_GPL(dax_region_put); + /* a return value >= 0 indicates this invocation invalidated the id */ static int __free_dev_dax_id(struct dev_dax *dev_dax) { - struct dax_region *dax_region = dev_dax->region; struct device *dev = &dev_dax->dev; + struct dax_region *dax_region; int rc = dev_dax->id; device_lock_assert(dev); - if (is_static(dax_region) || dev_dax->id < 0) + if (!dev_dax->dyn_id || dev_dax->id < 0) return -1; + dax_region = dev_dax->region; ida_free(&dax_region->ida, dev_dax->id); + dax_region_put(dax_region); dev_dax->id = -1; return rc; } @@ -430,6 +446,20 @@ static int free_dev_dax_id(struct dev_dax *dev_dax) return rc; } +static int alloc_dev_dax_id(struct dev_dax *dev_dax) +{ + struct dax_region *dax_region = dev_dax->region; + int id; + + id = ida_alloc(&dax_region->ida, GFP_KERNEL); + if (id < 0) + return id; + kref_get(&dax_region->kref); + dev_dax->dyn_id = true; + dev_dax->id = id; + return id; +} + static ssize_t delete_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -517,20 +547,6 @@ static const struct attribute_group *dax_region_attribute_groups[] = { NULL, }; -static void dax_region_free(struct kref *kref) -{ - struct dax_region *dax_region; - - dax_region = container_of(kref, struct dax_region, kref); - kfree(dax_region); -} - -void dax_region_put(struct dax_region *dax_region) -{ - kref_put(&dax_region->kref, dax_region_free); -} -EXPORT_SYMBOL_GPL(dax_region_put); - static void dax_region_unregister(void *region) { struct dax_region *dax_region = region; @@ -1270,12 +1286,10 @@ static const struct attribute_group *dax_attribute_groups[] = { static void dev_dax_release(struct device *dev) { struct dev_dax *dev_dax = to_dev_dax(dev); - struct dax_region *dax_region = dev_dax->region; struct dax_device *dax_dev = dev_dax->dax_dev; put_dax(dax_dev); free_dev_dax_id(dev_dax); - dax_region_put(dax_region); kfree(dev_dax->pgmap); kfree(dev_dax); } @@ -1299,6 +1313,7 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) if (!dev_dax) return ERR_PTR(-ENOMEM); + dev_dax->region = dax_region; if (is_static(dax_region)) { if (dev_WARN_ONCE(parent, data->id < 0, "dynamic id specified to static region\n")) { @@ -1314,13 +1329,11 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) goto err_id; } - rc = ida_alloc(&dax_region->ida, GFP_KERNEL); + rc = alloc_dev_dax_id(dev_dax); if (rc < 0) goto err_id; - dev_dax->id = rc; } - dev_dax->region = dax_region; dev = &dev_dax->dev; device_initialize(dev); dev_set_name(dev, "dax%d.%d", dax_region->id, dev_dax->id); @@ -1358,7 +1371,6 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) dev_dax->target_node = dax_region->target_node; dev_dax->align = dax_region->align; ida_init(&dev_dax->ida); - kref_get(&dax_region->kref); inode = dax_inode(dax_dev); dev->devt = inode->i_rdev; diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h index 1c974b7caae6..afcada6fd2ed 100644 --- a/drivers/dax/dax-private.h +++ b/drivers/dax/dax-private.h @@ -52,7 +52,8 @@ struct dax_mapping { * @region - parent region * @dax_dev - core dax functionality * @target_node: effective numa node if dev_dax memory range is onlined - * @id: ida allocated id + * @dyn_id: is this a dynamic or statically created instance + * @id: ida allocated id when the dax_region is not static * @ida: mapping id allocator * @dev - device core * @pgmap - pgmap for memmap setup / lifetime (driver owned) @@ -64,6 +65,7 @@ struct dev_dax { struct dax_device *dax_dev; unsigned int align; int target_node; + bool dyn_id; int id; struct ida ida; struct device dev; From cd5837564ff59b34fefe1d07af3442089bcfeb23 Mon Sep 17 00:00:00 2001 From: Martin Kaiser Date: Fri, 16 Jun 2023 09:58:13 +0100 Subject: [PATCH 3943/4345] hwrng: st - keep clock enabled while hwrng is registered [ Upstream commit 501e197a02d4aef157f53ba3a0b9049c3e52fedc ] The st-rng driver uses devres to register itself with the hwrng core, the driver will be unregistered from hwrng when its device goes out of scope. This happens after the driver's remove function is called. However, st-rng's clock is disabled in the remove function. There's a short timeframe where st-rng is still registered with the hwrng core although its clock is disabled. I suppose the clock must be active to access the hardware and serve requests from the hwrng core. Switch to devm_clk_get_enabled and let devres disable the clock and unregister the hwrng. This avoids the race condition. Fixes: 3e75241be808 ("hwrng: drivers - Use device-managed registration API") Signed-off-by: Martin Kaiser Signed-off-by: Herbert Xu Signed-off-by: Sasha Levin --- drivers/char/hw_random/st-rng.c | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) diff --git a/drivers/char/hw_random/st-rng.c b/drivers/char/hw_random/st-rng.c index 15ba1e6fae4d..6e9dfac9fc9f 100644 --- a/drivers/char/hw_random/st-rng.c +++ b/drivers/char/hw_random/st-rng.c @@ -42,7 +42,6 @@ struct st_rng_data { void __iomem *base; - struct clk *clk; struct hwrng ops; }; @@ -85,26 +84,18 @@ static int st_rng_probe(struct platform_device *pdev) if (IS_ERR(base)) return PTR_ERR(base); - clk = devm_clk_get(&pdev->dev, NULL); + clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(clk)) return PTR_ERR(clk); - ret = clk_prepare_enable(clk); - if (ret) - return ret; - ddata->ops.priv = (unsigned long)ddata; ddata->ops.read = st_rng_read; ddata->ops.name = pdev->name; ddata->base = base; - ddata->clk = clk; - - dev_set_drvdata(&pdev->dev, ddata); ret = devm_hwrng_register(&pdev->dev, &ddata->ops); if (ret) { dev_err(&pdev->dev, "Failed to register HW RNG\n"); - clk_disable_unprepare(clk); return ret; } @@ -113,15 +104,6 @@ static int st_rng_probe(struct platform_device *pdev) return 0; } -static int st_rng_remove(struct platform_device *pdev) -{ - struct st_rng_data *ddata = dev_get_drvdata(&pdev->dev); - - clk_disable_unprepare(ddata->clk); - - return 0; -} - static const struct of_device_id st_rng_match[] __maybe_unused = { { .compatible = "st,rng" }, {}, @@ -134,7 +116,6 @@ static struct platform_driver st_rng_driver = { .of_match_table = of_match_ptr(st_rng_match), }, .probe = st_rng_probe, - .remove = st_rng_remove }; module_platform_driver(st_rng_driver); From 810e401b34c4c4c244d8b93b9947ea5b3d4d49f8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Jul 2023 09:35:30 -0600 Subject: [PATCH 3944/4345] io_uring: ensure IOPOLL locks around deferred work No direct upstream commit exists for this issue. It was fixed in 5.18 as part of a larger rework of the completion side. io_commit_cqring() writes the CQ ring tail to make it visible, but it also kicks off any deferred work we have. A ring setup with IOPOLL does not need any locking around the CQ ring updates, as we're always under the ctx uring_lock. But if we have deferred work that needs processing, then io_queue_deferred() assumes that the completion_lock is held, as it is for !IOPOLL. Add a lockdep assertion to check and document this fact, and have io_iopoll_complete() check if we have deferred work and run that separately with the appropriate lock grabbed. Cc: stable@vger.kernel.org # 5.10, 5.15 Reported-by: dghost david Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index f169b4645769..bce80ed27c4d 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1521,6 +1521,8 @@ static void io_kill_timeout(struct io_kiocb *req, int status) static void io_queue_deferred(struct io_ring_ctx *ctx) { + lockdep_assert_held(&ctx->completion_lock); + while (!list_empty(&ctx->defer_list)) { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); @@ -1572,14 +1574,24 @@ static void __io_commit_cqring_flush(struct io_ring_ctx *ctx) io_queue_deferred(ctx); } -static inline void io_commit_cqring(struct io_ring_ctx *ctx) +static inline bool io_commit_needs_flush(struct io_ring_ctx *ctx) +{ + return ctx->off_timeout_used || ctx->drain_active; +} + +static inline void __io_commit_cqring(struct io_ring_ctx *ctx) { - if (unlikely(ctx->off_timeout_used || ctx->drain_active)) - __io_commit_cqring_flush(ctx); /* order cqe stores with ring update */ smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); } +static inline void io_commit_cqring(struct io_ring_ctx *ctx) +{ + if (unlikely(io_commit_needs_flush(ctx))) + __io_commit_cqring_flush(ctx); + __io_commit_cqring(ctx); +} + static inline bool io_sqring_full(struct io_ring_ctx *ctx) { struct io_rings *r = ctx->rings; @@ -2518,7 +2530,12 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, io_req_free_batch(&rb, req, &ctx->submit_state); } - io_commit_cqring(ctx); + if (io_commit_needs_flush(ctx)) { + spin_lock(&ctx->completion_lock); + __io_commit_cqring_flush(ctx); + spin_unlock(&ctx->completion_lock); + } + __io_commit_cqring(ctx); io_cqring_ev_posted_iopoll(ctx); io_req_free_batch_finish(ctx, &rb); } From 8b0a55b59244163d70cf840e649e9fa4b3d98bb6 Mon Sep 17 00:00:00 2001 From: Davide Tronchin Date: Thu, 22 Jun 2023 11:29:21 +0200 Subject: [PATCH 3945/4345] USB: serial: option: add LARA-R6 01B PIDs commit ffa5f7a3bf28c1306eef85d4056539c2d4b8eb09 upstream. The new LARA-R6 product variant identified by the "01B" string can be configured (by AT interface) in three different USB modes: * Default mode (Vendor ID: 0x1546 Product ID: 0x1311) with 4 serial interfaces * RmNet mode (Vendor ID: 0x1546 Product ID: 0x1312) with 4 serial interfaces and 1 RmNet virtual network interface * CDC-ECM mode (Vendor ID: 0x1546 Product ID: 0x1313) with 4 serial interface and 1 CDC-ECM virtual network interface The first 4 interfaces of all the 3 USB configurations (default, RmNet, CDC-ECM) are the same. In default mode LARA-R6 01B exposes the following interfaces: If 0: Diagnostic If 1: AT parser If 2: AT parser If 3: AT parser/alternative functions In RmNet mode LARA-R6 01B exposes the following interfaces: If 0: Diagnostic If 1: AT parser If 2: AT parser If 3: AT parser/alternative functions If 4: RMNET interface In CDC-ECM mode LARA-R6 01B exposes the following interfaces: If 0: Diagnostic If 1: AT parser If 2: AT parser If 3: AT parser/alternative functions If 4: CDC-ECM interface Signed-off-by: Davide Tronchin Link: https://lore.kernel.org/r/20230622092921.12651-1-davide.tronchin.94@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 243f97a30779..625d9dc776be 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1151,6 +1151,10 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x90fa), .driver_info = RSVD(3) }, /* u-blox products */ + { USB_DEVICE(UBLOX_VENDOR_ID, 0x1311) }, /* u-blox LARA-R6 01B */ + { USB_DEVICE(UBLOX_VENDOR_ID, 0x1312), /* u-blox LARA-R6 01B (RMNET) */ + .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(UBLOX_VENDOR_ID, 0x1313, 0xff) }, /* u-blox LARA-R6 01B (ECM) */ { USB_DEVICE(UBLOX_VENDOR_ID, 0x1341) }, /* u-blox LARA-L6 */ { USB_DEVICE(UBLOX_VENDOR_ID, 0x1342), /* u-blox LARA-L6 (RMNET) */ .driver_info = RSVD(4) }, From fac7be49f1e62ea04edb00e95a9c4e3102d08964 Mon Sep 17 00:00:00 2001 From: Krishna Kurapati Date: Sun, 18 Jun 2023 17:39:49 +0530 Subject: [PATCH 3946/4345] usb: dwc3: gadget: Propagate core init errors to UDC during pullup commit c0aabed9cabe057309779a9e26fe86a113d24dad upstream. In scenarios where pullup relies on resume (get sync) to initialize the controller and set the run stop bit, then core_init is followed by gadget_resume which will eventually set run stop bit. But in cases where the core_init fails, the return value is not sent back to udc appropriately. So according to UDC the controller has started but in reality we never set the run stop bit. On systems like Android, there are uevents sent to HAL depending on whether the configfs_bind / configfs_disconnect were invoked. In the above mentioned scnenario, if the core init fails, the run stop won't be set and the cable plug-out won't result in generation of any disconnect event and userspace would never get any uevent regarding cable plug out and we never call pullup(0) again. Furthermore none of the next Plug-In/Plug-Out's would be known to configfs. Return back the appropriate result to UDC to let the userspace/ configfs know that the pullup failed so they can take appropriate action. Fixes: 77adb8bdf422 ("usb: dwc3: gadget: Allow runtime suspend if UDC unbinded") Cc: stable Signed-off-by: Krishna Kurapati Acked-by: Thinh Nguyen Message-ID: <20230618120949.14868-1-quic_kriskura@quicinc.com> Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 164910237669..221738b64426 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2215,7 +2215,9 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) ret = pm_runtime_get_sync(dwc->dev); if (!ret || ret < 0) { pm_runtime_put(dwc->dev); - return 0; + if (ret < 0) + pm_runtime_set_suspended(dwc->dev); + return ret; } if (dwc->pullups_connected == is_on) { From b6a107c52073496d2e5d2837915f59fb3103832f Mon Sep 17 00:00:00 2001 From: EJ Hsu Date: Fri, 9 Jun 2023 14:29:32 +0800 Subject: [PATCH 3947/4345] phy: tegra: xusb: Clear the driver reference in usb-phy dev commit c0c2fcb1325d0d4f3b322b5ee49385f8eca2560d upstream. For the dual-role port, it will assign the phy dev to usb-phy dev and use the port dev driver as the dev driver of usb-phy. When we try to destroy the port dev, it will destroy its dev driver as well. But we did not remove the reference from usb-phy dev. This might cause the use-after-free issue in KASAN. Fixes: e8f7d2f409a1 ("phy: tegra: xusb: Add usb-phy support") Cc: stable@vger.kernel.org Signed-off-by: EJ Hsu Signed-off-by: Haotien Hsu Acked-by: Thierry Reding Acked-by: Jon Hunter Link: https://lore.kernel.org/r/20230609062932.3276509-1-haotienh@nvidia.com Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/phy/tegra/xusb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index d07f33ec7939..f93be3c4a4a6 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -556,6 +556,7 @@ static void tegra_xusb_port_unregister(struct tegra_xusb_port *port) usb_role_switch_unregister(port->usb_role_sw); cancel_work_sync(&port->usb_phy_work); usb_remove_phy(&port->usb_phy); + port->usb_phy.dev->driver = NULL; } if (port->ops->remove) From 54da6c4c143fedc9dec675503a806e65eb85b055 Mon Sep 17 00:00:00 2001 From: Michael Schmitz Date: Wed, 21 Jun 2023 08:17:23 +1200 Subject: [PATCH 3948/4345] block: fix signed int overflow in Amiga partition support commit fc3d092c6bb48d5865fec15ed5b333c12f36288c upstream. The Amiga partition parser module uses signed int for partition sector address and count, which will overflow for disks larger than 1 TB. Use sector_t as type for sector address and size to allow using disks up to 2 TB without LBD support, and disks larger than 2 TB with LBD. This bug was reported originally in 2012, and the fix was created by the RDB author, Joanne Dow . A patch had been discussed and reviewed on linux-m68k at that time but never officially submitted. This patch differs from Joanne's patch only in its use of sector_t instead of unsigned int. No checking for overflows is done (see patch 3 of this series for that). Reported-by: Martin Steigerwald Closes: https://bugzilla.kernel.org/show_bug.cgi?id=43511 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Message-ID: <201206192146.09327.Martin@lichtvoll.de> Cc: # 5.2 Signed-off-by: Michael Schmitz Tested-by: Martin Steigerwald Reviewed-by: Geert Uytterhoeven Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230620201725.7020-2-schmitzmic@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/partitions/amiga.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c index 9526491d9aed..64f0844468aa 100644 --- a/block/partitions/amiga.c +++ b/block/partitions/amiga.c @@ -31,7 +31,8 @@ int amiga_partition(struct parsed_partitions *state) unsigned char *data; struct RigidDiskBlock *rdb; struct PartitionBlock *pb; - int start_sect, nr_sects, blk, part, res = 0; + sector_t start_sect, nr_sects; + int blk, part, res = 0; int blksize = 1; /* Multiplier for disk block size */ int slot = 1; char b[BDEVNAME_SIZE]; @@ -97,14 +98,14 @@ int amiga_partition(struct parsed_partitions *state) /* Tell Kernel about it */ - nr_sects = (be32_to_cpu(pb->pb_Environment[10]) + 1 - - be32_to_cpu(pb->pb_Environment[9])) * + nr_sects = ((sector_t)be32_to_cpu(pb->pb_Environment[10]) + 1 - + be32_to_cpu(pb->pb_Environment[9])) * be32_to_cpu(pb->pb_Environment[3]) * be32_to_cpu(pb->pb_Environment[5]) * blksize; if (!nr_sects) continue; - start_sect = be32_to_cpu(pb->pb_Environment[9]) * + start_sect = (sector_t)be32_to_cpu(pb->pb_Environment[9]) * be32_to_cpu(pb->pb_Environment[3]) * be32_to_cpu(pb->pb_Environment[5]) * blksize; From e4a9b3333e67a65d8a70a4bb1c2a20f473ee5eb8 Mon Sep 17 00:00:00 2001 From: Michael Schmitz Date: Wed, 21 Jun 2023 08:17:24 +1200 Subject: [PATCH 3949/4345] block: change all __u32 annotations to __be32 in affs_hardblocks.h commit 95a55437dc49fb3342c82e61f5472a71c63d9ed0 upstream. The Amiga partition parser module uses signed int for partition sector address and count, which will overflow for disks larger than 1 TB. Use u64 as type for sector address and size to allow using disks up to 2 TB without LBD support, and disks larger than 2 TB with LBD. The RBD format allows to specify disk sizes up to 2^128 bytes (though native OS limitations reduce this somewhat, to max 2^68 bytes), so check for u64 overflow carefully to protect against overflowing sector_t. This bug was reported originally in 2012, and the fix was created by the RDB author, Joanne Dow . A patch had been discussed and reviewed on linux-m68k at that time but never officially submitted (now resubmitted as patch 1 of this series). Patch 3 (this series) adds additional error checking and warning messages. One of the error checks now makes use of the previously unused rdb_CylBlocks field, which causes a 'sparse' warning (cast to restricted __be32). Annotate all 32 bit fields in affs_hardblocks.h as __be32, as the on-disk format of RDB and partition blocks is always big endian. Reported-by: Martin Steigerwald Closes: https://bugzilla.kernel.org/show_bug.cgi?id=43511 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Message-ID: <201206192146.09327.Martin@lichtvoll.de> Cc: # 5.2 Signed-off-by: Michael Schmitz Reviewed-by: Christoph Hellwig Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230620201725.7020-3-schmitzmic@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/affs_hardblocks.h | 68 ++++++++++++++-------------- 1 file changed, 34 insertions(+), 34 deletions(-) diff --git a/include/uapi/linux/affs_hardblocks.h b/include/uapi/linux/affs_hardblocks.h index 5e2fb8481252..a5aff2eb5f70 100644 --- a/include/uapi/linux/affs_hardblocks.h +++ b/include/uapi/linux/affs_hardblocks.h @@ -7,42 +7,42 @@ /* Just the needed definitions for the RDB of an Amiga HD. */ struct RigidDiskBlock { - __u32 rdb_ID; + __be32 rdb_ID; __be32 rdb_SummedLongs; - __s32 rdb_ChkSum; - __u32 rdb_HostID; + __be32 rdb_ChkSum; + __be32 rdb_HostID; __be32 rdb_BlockBytes; - __u32 rdb_Flags; - __u32 rdb_BadBlockList; + __be32 rdb_Flags; + __be32 rdb_BadBlockList; __be32 rdb_PartitionList; - __u32 rdb_FileSysHeaderList; - __u32 rdb_DriveInit; - __u32 rdb_Reserved1[6]; - __u32 rdb_Cylinders; - __u32 rdb_Sectors; - __u32 rdb_Heads; - __u32 rdb_Interleave; - __u32 rdb_Park; - __u32 rdb_Reserved2[3]; - __u32 rdb_WritePreComp; - __u32 rdb_ReducedWrite; - __u32 rdb_StepRate; - __u32 rdb_Reserved3[5]; - __u32 rdb_RDBBlocksLo; - __u32 rdb_RDBBlocksHi; - __u32 rdb_LoCylinder; - __u32 rdb_HiCylinder; - __u32 rdb_CylBlocks; - __u32 rdb_AutoParkSeconds; - __u32 rdb_HighRDSKBlock; - __u32 rdb_Reserved4; + __be32 rdb_FileSysHeaderList; + __be32 rdb_DriveInit; + __be32 rdb_Reserved1[6]; + __be32 rdb_Cylinders; + __be32 rdb_Sectors; + __be32 rdb_Heads; + __be32 rdb_Interleave; + __be32 rdb_Park; + __be32 rdb_Reserved2[3]; + __be32 rdb_WritePreComp; + __be32 rdb_ReducedWrite; + __be32 rdb_StepRate; + __be32 rdb_Reserved3[5]; + __be32 rdb_RDBBlocksLo; + __be32 rdb_RDBBlocksHi; + __be32 rdb_LoCylinder; + __be32 rdb_HiCylinder; + __be32 rdb_CylBlocks; + __be32 rdb_AutoParkSeconds; + __be32 rdb_HighRDSKBlock; + __be32 rdb_Reserved4; char rdb_DiskVendor[8]; char rdb_DiskProduct[16]; char rdb_DiskRevision[4]; char rdb_ControllerVendor[8]; char rdb_ControllerProduct[16]; char rdb_ControllerRevision[4]; - __u32 rdb_Reserved5[10]; + __be32 rdb_Reserved5[10]; }; #define IDNAME_RIGIDDISK 0x5244534B /* "RDSK" */ @@ -50,16 +50,16 @@ struct RigidDiskBlock { struct PartitionBlock { __be32 pb_ID; __be32 pb_SummedLongs; - __s32 pb_ChkSum; - __u32 pb_HostID; + __be32 pb_ChkSum; + __be32 pb_HostID; __be32 pb_Next; - __u32 pb_Flags; - __u32 pb_Reserved1[2]; - __u32 pb_DevFlags; + __be32 pb_Flags; + __be32 pb_Reserved1[2]; + __be32 pb_DevFlags; __u8 pb_DriveName[32]; - __u32 pb_Reserved2[15]; + __be32 pb_Reserved2[15]; __be32 pb_Environment[17]; - __u32 pb_EReserved[15]; + __be32 pb_EReserved[15]; }; #define IDNAME_PARTITION 0x50415254 /* "PART" */ From cd5ec3ee52ce4b7e283cc11facfa420c297c8065 Mon Sep 17 00:00:00 2001 From: Ding Hui Date: Mon, 15 May 2023 10:13:07 +0800 Subject: [PATCH 3950/4345] SUNRPC: Fix UAF in svc_tcp_listen_data_ready() commit fc80fc2d4e39137869da3150ee169b40bf879287 upstream. After the listener svc_sock is freed, and before invoking svc_tcp_accept() for the established child sock, there is a window that the newsock retaining a freed listener svc_sock in sk_user_data which cloning from parent. In the race window, if data is received on the newsock, we will observe use-after-free report in svc_tcp_listen_data_ready(). Reproduce by two tasks: 1. while :; do rpc.nfsd 0 ; rpc.nfsd; done 2. while :; do echo "" | ncat -4 127.0.0.1 2049 ; done KASAN report: ================================================================== BUG: KASAN: slab-use-after-free in svc_tcp_listen_data_ready+0x1cf/0x1f0 [sunrpc] Read of size 8 at addr ffff888139d96228 by task nc/102553 CPU: 7 PID: 102553 Comm: nc Not tainted 6.3.0+ #18 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020 Call Trace: dump_stack_lvl+0x33/0x50 print_address_description.constprop.0+0x27/0x310 print_report+0x3e/0x70 kasan_report+0xae/0xe0 svc_tcp_listen_data_ready+0x1cf/0x1f0 [sunrpc] tcp_data_queue+0x9f4/0x20e0 tcp_rcv_established+0x666/0x1f60 tcp_v4_do_rcv+0x51c/0x850 tcp_v4_rcv+0x23fc/0x2e80 ip_protocol_deliver_rcu+0x62/0x300 ip_local_deliver_finish+0x267/0x350 ip_local_deliver+0x18b/0x2d0 ip_rcv+0x2fb/0x370 __netif_receive_skb_one_core+0x166/0x1b0 process_backlog+0x24c/0x5e0 __napi_poll+0xa2/0x500 net_rx_action+0x854/0xc90 __do_softirq+0x1bb/0x5de do_softirq+0xcb/0x100 ... Allocated by task 102371: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 __kasan_kmalloc+0x7b/0x90 svc_setup_socket+0x52/0x4f0 [sunrpc] svc_addsock+0x20d/0x400 [sunrpc] __write_ports_addfd+0x209/0x390 [nfsd] write_ports+0x239/0x2c0 [nfsd] nfsctl_transaction_write+0xac/0x110 [nfsd] vfs_write+0x1c3/0xae0 ksys_write+0xed/0x1c0 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 102551: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x50 __kasan_slab_free+0x106/0x190 __kmem_cache_free+0x133/0x270 svc_xprt_free+0x1e2/0x350 [sunrpc] svc_xprt_destroy_all+0x25a/0x440 [sunrpc] nfsd_put+0x125/0x240 [nfsd] nfsd_svc+0x2cb/0x3c0 [nfsd] write_threads+0x1ac/0x2a0 [nfsd] nfsctl_transaction_write+0xac/0x110 [nfsd] vfs_write+0x1c3/0xae0 ksys_write+0xed/0x1c0 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc Fix the UAF by simply doing nothing in svc_tcp_listen_data_ready() if state != TCP_LISTEN, that will avoid dereferencing svsk for all child socket. Link: https://lore.kernel.org/lkml/20230507091131.23540-1-dinghui@sangfor.com.cn/ Fixes: fa9251afc33c ("SUNRPC: Call the default socket callbacks instead of open coding") Signed-off-by: Ding Hui Cc: Signed-off-by: Chuck Lever Signed-off-by: Greg Kroah-Hartman --- net/sunrpc/svcsock.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 6d5bb8bfed38..3d5ee042c501 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -692,12 +692,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; - if (svsk) { - /* Refer to svc_setup_socket() for details. */ - rmb(); - svsk->sk_odata(sk); - } - /* * This callback may called twice when a new connection * is established as a child socket inherits everything @@ -706,13 +700,18 @@ static void svc_tcp_listen_data_ready(struct sock *sk) * when one of child sockets become ESTABLISHED. * 2) data_ready method of the child socket may be called * when it receives data before the socket is accepted. - * In case of 2, we should ignore it silently. + * In case of 2, we should ignore it silently and DO NOT + * dereference svsk. */ - if (sk->sk_state == TCP_LISTEN) { - if (svsk) { - set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); - svc_xprt_enqueue(&svsk->sk_xprt); - } + if (sk->sk_state != TCP_LISTEN) + return; + + if (svsk) { + /* Refer to svc_setup_socket() for details. */ + rmb(); + svsk->sk_odata(sk); + set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); + svc_xprt_enqueue(&svsk->sk_xprt); } } From a27aeae714cdf7249914a57e14627581cefc1336 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Thu, 27 Apr 2023 13:21:52 +0200 Subject: [PATCH 3951/4345] w1: w1_therm: fix locking behavior in convert_t [ Upstream commit dca5480ab7b77a889088ab7cac81934604510ac7 ] The commit 67b392f7b8ed ("w1_therm: optimizing temperature read timings") accidentially inverted the logic for lock handling of the bus mutex. Before: pullup -> release lock before sleep no pullup -> release lock after sleep After: pullup -> release lock after sleep no pullup -> release lock before sleep This cause spurious measurements of 85 degree (powerup value) on the Tarragon board with connected 1-w temperature sensor (w1_therm.w1_strong_pull=0). In the meantime a new feature for polling the conversion completion has been integrated in these branches with commit 021da53e65fd ("w1: w1_therm: Add sysfs entries to control conversion time and driver features"). But this feature isn't available for parasite power mode, so handle this separately. Link: https://lore.kernel.org/regressions/2023042645-attentive-amends-7b0b@gregkh/T/ Fixes: 67b392f7b8ed ("w1_therm: optimizing temperature read timings") Signed-off-by: Stefan Wahren Link: https://lore.kernel.org/r/20230427112152.12313-1-stefan.wahren@i2se.com Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- drivers/w1/slaves/w1_therm.c | 31 ++++++++++++++----------------- 1 file changed, 14 insertions(+), 17 deletions(-) diff --git a/drivers/w1/slaves/w1_therm.c b/drivers/w1/slaves/w1_therm.c index 6546d029c7fd..3888643a22f6 100644 --- a/drivers/w1/slaves/w1_therm.c +++ b/drivers/w1/slaves/w1_therm.c @@ -1094,29 +1094,26 @@ static int convert_t(struct w1_slave *sl, struct therm_info *info) w1_write_8(dev_master, W1_CONVERT_TEMP); - if (strong_pullup) { /*some device need pullup */ + if (SLAVE_FEATURES(sl) & W1_THERM_POLL_COMPLETION) { + ret = w1_poll_completion(dev_master, W1_POLL_CONVERT_TEMP); + if (ret) { + dev_dbg(&sl->dev, "%s: Timeout\n", __func__); + goto mt_unlock; + } + mutex_unlock(&dev_master->bus_mutex); + } else if (!strong_pullup) { /*no device need pullup */ sleep_rem = msleep_interruptible(t_conv); if (sleep_rem != 0) { ret = -EINTR; goto mt_unlock; } mutex_unlock(&dev_master->bus_mutex); - } else { /*no device need pullup */ - if (SLAVE_FEATURES(sl) & W1_THERM_POLL_COMPLETION) { - ret = w1_poll_completion(dev_master, W1_POLL_CONVERT_TEMP); - if (ret) { - dev_dbg(&sl->dev, "%s: Timeout\n", __func__); - goto mt_unlock; - } - mutex_unlock(&dev_master->bus_mutex); - } else { - /* Fixed delay */ - mutex_unlock(&dev_master->bus_mutex); - sleep_rem = msleep_interruptible(t_conv); - if (sleep_rem != 0) { - ret = -EINTR; - goto dec_refcnt; - } + } else { /*some device need pullup */ + mutex_unlock(&dev_master->bus_mutex); + sleep_rem = msleep_interruptible(t_conv); + if (sleep_rem != 0) { + ret = -EINTR; + goto dec_refcnt; } } ret = read_scratchpad(sl, info); From a7890637b3b9b485ffd6a8bfc4276fab03b8e9f5 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 19 May 2021 17:17:45 +0300 Subject: [PATCH 3952/4345] w1: fix loop in w1_fini() [ Upstream commit 83f3fcf96fcc7e5405b37d9424c7ef26bfa203f8 ] The __w1_remove_master_device() function calls: list_del(&dev->w1_master_entry); So presumably this can cause an endless loop. Fixes: 7785925dd8e0 ("[PATCH] w1: cleanups.") Signed-off-by: Dan Carpenter Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sasha Levin --- drivers/w1/w1.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 15842377c8d2..1c1a9438f4b6 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -1228,10 +1228,10 @@ err_out_exit_init: static void __exit w1_fini(void) { - struct w1_master *dev; + struct w1_master *dev, *n; /* Set netlink removal messages and some cleanup */ - list_for_each_entry(dev, &w1_masters, w1_master_entry) + list_for_each_entry_safe(dev, n, &w1_masters, w1_master_entry) __w1_remove_master_device(dev); w1_fini_netlink(); From ed68e8e22ee1110934efbe2908640baa3056dbcb Mon Sep 17 00:00:00 2001 From: John Paul Adrian Glaubitz Date: Wed, 3 May 2023 14:57:41 +0200 Subject: [PATCH 3953/4345] sh: j2: Use ioremap() to translate device tree address into kernel memory [ Upstream commit bc9d1f0cecd2407cfb2364a7d4be2f52d1d46a9d ] Addresses the following warning when building j2_defconfig: arch/sh/kernel/cpu/sh2/probe.c: In function 'scan_cache': arch/sh/kernel/cpu/sh2/probe.c:24:16: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] 24 | j2_ccr_base = (u32 __iomem *)of_flat_dt_translate_address(node); | Fixes: 5a846abad07f ("sh: add support for J-Core J2 processor") Reviewed-by: Geert Uytterhoeven Tested-by: Rob Landley Signed-off-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230503125746.331835-1-glaubitz@physik.fu-berlin.de Signed-off-by: John Paul Adrian Glaubitz Signed-off-by: Sasha Levin --- arch/sh/kernel/cpu/sh2/probe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/kernel/cpu/sh2/probe.c b/arch/sh/kernel/cpu/sh2/probe.c index d342ea08843f..70a07f4f2142 100644 --- a/arch/sh/kernel/cpu/sh2/probe.c +++ b/arch/sh/kernel/cpu/sh2/probe.c @@ -21,7 +21,7 @@ static int __init scan_cache(unsigned long node, const char *uname, if (!of_flat_dt_is_compatible(node, "jcore,cache")) return 0; - j2_ccr_base = (u32 __iomem *)of_flat_dt_translate_address(node); + j2_ccr_base = ioremap(of_flat_dt_translate_address(node), 4); return 1; } From bb81ca33ace3b4089c1c4fe07b0c39a453cdcad7 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 8 May 2023 11:20:11 +0300 Subject: [PATCH 3954/4345] serial: 8250: omap: Fix freeing of resources on failed register MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b9ab22c2bc8652324a803b3e2be69838920b4025 ] If serial8250_register_8250_port() fails, the SoC can hang as the deferred PMQoS work will still run as is not flushed and removed. Fixes: 61929cf0169d ("tty: serial: Add 8250-core based omap driver") Signed-off-by: Tony Lindgren Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230508082014.23083-2-tony@atomide.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_omap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 483fff3a95c9..6b255e1633fd 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -1469,7 +1469,9 @@ static int omap8250_probe(struct platform_device *pdev) err: pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_put_sync(&pdev->dev); + flush_work(&priv->qos_work); pm_runtime_disable(&pdev->dev); + cpu_latency_qos_remove_request(&priv->pm_qos_request); return ret; } From 32809afb6063197c45e522b62cf7dced2e3c20ed Mon Sep 17 00:00:00 2001 From: Mantas Pucka Date: Tue, 25 Apr 2023 12:11:49 +0300 Subject: [PATCH 3955/4345] clk: qcom: gcc-ipq6018: Use floor ops for sdcc clocks [ Upstream commit 56e5ae0116aef87273cf1812d608645b076e4f02 ] SDCC clocks must be rounded down to avoid overclocking the controller. Fixes: d9db07f088af ("clk: qcom: Add ipq6018 Global Clock Controller support") Signed-off-by: Mantas Pucka Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/1682413909-24927-1-git-send-email-mantas@8devices.com Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-ipq6018.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c index 3f9c2f61a5d9..5c5d1b04ea7a 100644 --- a/drivers/clk/qcom/gcc-ipq6018.c +++ b/drivers/clk/qcom/gcc-ipq6018.c @@ -1654,7 +1654,7 @@ static struct clk_rcg2 sdcc1_apps_clk_src = { .name = "sdcc1_apps_clk_src", .parent_data = gcc_xo_gpll0_gpll2_gpll0_out_main_div2, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, }, }; From 5f3f4aa673a03cd04030f2bec2c825e476082583 Mon Sep 17 00:00:00 2001 From: Daniil Dulov Date: Tue, 14 Mar 2023 10:04:49 -0700 Subject: [PATCH 3956/4345] media: usb: Check az6007_read() return value [ Upstream commit fdaca63186f59fc664b346c45b76576624b48e57 ] If az6007_read() returns error, there is no sence to continue. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 3af2f4f15a61 ("[media] az6007: Change the az6007 read/write routine parameter") Signed-off-by: Daniil Dulov Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/usb/dvb-usb-v2/az6007.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/usb/dvb-usb-v2/az6007.c b/drivers/media/usb/dvb-usb-v2/az6007.c index 62ee09f28a0b..7524c90f5da6 100644 --- a/drivers/media/usb/dvb-usb-v2/az6007.c +++ b/drivers/media/usb/dvb-usb-v2/az6007.c @@ -202,7 +202,8 @@ static int az6007_rc_query(struct dvb_usb_device *d) unsigned code; enum rc_proto proto; - az6007_read(d, AZ6007_READ_IR, 0, 0, st->data, 10); + if (az6007_read(d, AZ6007_READ_IR, 0, 0, st->data, 10) < 0) + return -EIO; if (st->data[1] == 0x44) return 0; From 300388887cbba2bb92e2d81dc20448cd67e06391 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 18 May 2023 15:36:49 +0200 Subject: [PATCH 3957/4345] media: videodev2.h: Fix struct v4l2_input tuner index comment [ Upstream commit 26ae58f65e64fa7ba61d64bae752e59e08380c6a ] VIDIOC_ENUMINPUT documentation describes the tuner field of struct v4l2_input as index: Documentation/userspace-api/media/v4l/vidioc-enuminput.rst " * - __u32 - ``tuner`` - Capture devices can have zero or more tuners (RF demodulators). When the ``type`` is set to ``V4L2_INPUT_TYPE_TUNER`` this is an RF connector and this field identifies the tuner. It corresponds to struct :c:type:`v4l2_tuner` field ``index``. For details on tuners see :ref:`tuner`. " Drivers I could find also use the 'tuner' field as an index, e.g.: drivers/media/pci/bt8xx/bttv-driver.c bttv_enum_input() drivers/media/usb/go7007/go7007-v4l2.c vidioc_enum_input() However, the UAPI comment claims this field is 'enum v4l2_tuner_type': include/uapi/linux/videodev2.h This field being 'enum v4l2_tuner_type' is unlikely as it seems to be never used that way in drivers, and documentation confirms it. It seem this comment got in accidentally in the commit which this patch fixes. Fix the UAPI comment to stop confusion. This was pointed out by Dmitry while reviewing VIDIOC_ENUMINPUT support for strace. Fixes: 6016af82eafc ("[media] v4l2: use __u32 rather than enums in ioctl() structs") Signed-off-by: Marek Vasut Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- include/uapi/linux/videodev2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index b28817c59fdf..55b8c4b82479 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1644,7 +1644,7 @@ struct v4l2_input { __u8 name[32]; /* Label */ __u32 type; /* Type of input */ __u32 audioset; /* Associated audios (bitfield) */ - __u32 tuner; /* enum v4l2_tuner_type */ + __u32 tuner; /* Tuner index */ v4l2_std_id std; __u32 status; __u32 capabilities; From d87ef4e857b790f1616809eccda6b4d0c9c3da11 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Tue, 23 May 2023 07:59:32 +0800 Subject: [PATCH 3958/4345] media: usb: siano: Fix warning due to null work_func_t function pointer [ Upstream commit 6f489a966fbeb0da63d45c2c66a8957eab604bf6 ] The previous commit ebad8e731c1c ("media: usb: siano: Fix use after free bugs caused by do_submit_urb") adds cancel_work_sync() in smsusb_stop_streaming(). But smsusb_stop_streaming() may be called, even if the work_struct surb->wq has not been initialized. As a result, the warning will occur. One of the processes that could lead to warning is shown below: smsusb_probe() smsusb_init_device() if (!dev->in_ep || !dev->out_ep || align < 0) { smsusb_term_device(intf); smsusb_stop_streaming() cancel_work_sync(&dev->surbs[i].wq); __cancel_work_timer() __flush_work() if (WARN_ON(!work->func)) // work->func is null The log reported by syzbot is shown below: WARNING: CPU: 0 PID: 897 at kernel/workqueue.c:3066 __flush_work+0x798/0xa80 kernel/workqueue.c:3063 Modules linked in: CPU: 0 PID: 897 Comm: kworker/0:2 Not tainted 6.2.0-rc1-syzkaller #0 RIP: 0010:__flush_work+0x798/0xa80 kernel/workqueue.c:3066 ... RSP: 0018:ffffc9000464ebf8 EFLAGS: 00010246 RAX: 1ffff11002dbb420 RBX: 0000000000000021 RCX: 1ffffffff204fa4e RDX: dffffc0000000000 RSI: 0000000000000001 RDI: ffff888016dda0e8 RBP: ffffc9000464ed98 R08: 0000000000000001 R09: ffffffff90253b2f R10: 0000000000000001 R11: 0000000000000000 R12: ffff888016dda0e8 R13: ffff888016dda0e8 R14: ffff888016dda100 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880b9a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffd4331efe8 CR3: 000000000b48e000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __cancel_work_timer+0x315/0x460 kernel/workqueue.c:3160 smsusb_stop_streaming drivers/media/usb/siano/smsusb.c:182 [inline] smsusb_term_device+0xda/0x2d0 drivers/media/usb/siano/smsusb.c:344 smsusb_init_device+0x400/0x9ce drivers/media/usb/siano/smsusb.c:419 smsusb_probe+0xbbd/0xc55 drivers/media/usb/siano/smsusb.c:567 ... This patch adds check before cancel_work_sync(). If surb->wq has not been initialized, the cancel_work_sync() will not be executed. Reported-by: syzbot+27b0b464864741b18b99@syzkaller.appspotmail.com Fixes: ebad8e731c1c ("media: usb: siano: Fix use after free bugs caused by do_submit_urb") Signed-off-by: Duoming Zhou Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin --- drivers/media/usb/siano/smsusb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c index 1babfe6e2c36..5c223b5498b4 100644 --- a/drivers/media/usb/siano/smsusb.c +++ b/drivers/media/usb/siano/smsusb.c @@ -179,7 +179,8 @@ static void smsusb_stop_streaming(struct smsusb_device_t *dev) for (i = 0; i < MAX_URBS; i++) { usb_kill_urb(&dev->surbs[i].urb); - cancel_work_sync(&dev->surbs[i].wq); + if (dev->surbs[i].wq.func) + cancel_work_sync(&dev->surbs[i].wq); if (dev->surbs[i].cb) { smscore_putbuffer(dev->coredev, dev->surbs[i].cb); From 35fd1a213fa4435f8941f27782b5315a93fb915b Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Wed, 6 Jul 2022 15:41:29 +0200 Subject: [PATCH 3959/4345] clk: qcom: reset: Allow specifying custom reset delay [ Upstream commit 2cb8a39b6781ea23accd1fa93b3ad000d0948aec ] The amount of time required between asserting and deasserting the reset signal can vary depending on the involved hardware component. Sometimes 1 us might not be enough and a larger delay is necessary to conform to the specifications. Usually this is worked around in the consuming drivers, by replacing reset_control_reset() with a sequence of reset_control_assert(), waiting for a custom delay, followed by reset_control_deassert(). However, in some cases the driver making use of the reset is generic and can be used with different reset controllers. In this case the reset time requirement is better handled directly by the reset controller driver. Make this possible by adding an "udelay" field to the qcom_reset_map that allows setting a different reset delay (in microseconds). Signed-off-by: Stephan Gerhold Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220706134132.3623415-4-stephan.gerhold@kernkonzept.com Stable-dep-of: 349b5bed539b ("clk: qcom: ipq6018: fix networking resets") Signed-off-by: Sasha Levin --- drivers/clk/qcom/reset.c | 4 +++- drivers/clk/qcom/reset.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/clk/qcom/reset.c b/drivers/clk/qcom/reset.c index 819d194be8f7..2a16adb572d2 100644 --- a/drivers/clk/qcom/reset.c +++ b/drivers/clk/qcom/reset.c @@ -13,8 +13,10 @@ static int qcom_reset(struct reset_controller_dev *rcdev, unsigned long id) { + struct qcom_reset_controller *rst = to_qcom_reset_controller(rcdev); + rcdev->ops->assert(rcdev, id); - udelay(1); + udelay(rst->reset_map[id].udelay ?: 1); /* use 1 us as default */ rcdev->ops->deassert(rcdev, id); return 0; } diff --git a/drivers/clk/qcom/reset.h b/drivers/clk/qcom/reset.h index 2a08b5e282c7..b8c113582072 100644 --- a/drivers/clk/qcom/reset.h +++ b/drivers/clk/qcom/reset.h @@ -11,6 +11,7 @@ struct qcom_reset_map { unsigned int reg; u8 bit; + u8 udelay; }; struct regmap; From ee3f494cfc3e6b6102c5ae7fc84b600bc6c008fd Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Mon, 7 Nov 2022 14:28:59 +0100 Subject: [PATCH 3960/4345] clk: qcom: reset: support resetting multiple bits [ Upstream commit 4a5210893625f89723ea210d7c630b730abb37ad ] This patch adds the support for giving the complete bitmask in reset structure and reset operation will use this bitmask for all reset operations. Currently, reset structure only takes a single bit for each reset and then calculates the bitmask by using the BIT() macro. However, this is not sufficient anymore for newer SoC-s like IPQ8074, IPQ6018 and more, since their networking resets require multiple bits to be asserted in order to properly reset the HW block completely. So, in order to allow asserting multiple bits add "bitmask" field to qcom_reset_map, and then use that bitmask value if its populated in the driver, if its not populated, then we just default to existing behaviour and calculate the bitmask on the fly. Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20221107132901.489240-1-robimarko@gmail.com Stable-dep-of: 349b5bed539b ("clk: qcom: ipq6018: fix networking resets") Signed-off-by: Sasha Levin --- drivers/clk/qcom/reset.c | 4 ++-- drivers/clk/qcom/reset.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/reset.c b/drivers/clk/qcom/reset.c index 2a16adb572d2..0e914ec7aeae 100644 --- a/drivers/clk/qcom/reset.c +++ b/drivers/clk/qcom/reset.c @@ -30,7 +30,7 @@ qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) rst = to_qcom_reset_controller(rcdev); map = &rst->reset_map[id]; - mask = BIT(map->bit); + mask = map->bitmask ? map->bitmask : BIT(map->bit); return regmap_update_bits(rst->regmap, map->reg, mask, mask); } @@ -44,7 +44,7 @@ qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) rst = to_qcom_reset_controller(rcdev); map = &rst->reset_map[id]; - mask = BIT(map->bit); + mask = map->bitmask ? map->bitmask : BIT(map->bit); return regmap_update_bits(rst->regmap, map->reg, mask, 0); } diff --git a/drivers/clk/qcom/reset.h b/drivers/clk/qcom/reset.h index b8c113582072..9a47c838d9b1 100644 --- a/drivers/clk/qcom/reset.h +++ b/drivers/clk/qcom/reset.h @@ -12,6 +12,7 @@ struct qcom_reset_map { unsigned int reg; u8 bit; u8 udelay; + u32 bitmask; }; struct regmap; From bdce16c1e650106bead98171adac36cfc7f339d8 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 26 May 2023 21:08:55 +0200 Subject: [PATCH 3961/4345] clk: qcom: ipq6018: fix networking resets [ Upstream commit 349b5bed539b491b7894a5186a895751fd8ba6c7 ] Networking resets in IPQ6018 all use bitmask as they require multiple bits to be set and cleared instead of a single bit. So, current networking resets have the same register and bit 0 set which is clearly incorrect. Fixes: d9db07f088af ("clk: qcom: Add ipq6018 Global Clock Controller support") Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230526190855.2941291-2-robimarko@gmail.com Signed-off-by: Sasha Levin --- drivers/clk/qcom/gcc-ipq6018.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c index 5c5d1b04ea7a..cde62a11f573 100644 --- a/drivers/clk/qcom/gcc-ipq6018.c +++ b/drivers/clk/qcom/gcc-ipq6018.c @@ -4517,24 +4517,24 @@ static const struct qcom_reset_map gcc_ipq6018_resets[] = { [GCC_PCIE0_AHB_ARES] = { 0x75040, 5 }, [GCC_PCIE0_AXI_MASTER_STICKY_ARES] = { 0x75040, 6 }, [GCC_PCIE0_AXI_SLAVE_STICKY_ARES] = { 0x75040, 7 }, - [GCC_PPE_FULL_RESET] = { 0x68014, 0 }, - [GCC_UNIPHY0_SOFT_RESET] = { 0x56004, 0 }, + [GCC_PPE_FULL_RESET] = { .reg = 0x68014, .bitmask = 0xf0000 }, + [GCC_UNIPHY0_SOFT_RESET] = { .reg = 0x56004, .bitmask = 0x3ff2 }, [GCC_UNIPHY0_XPCS_RESET] = { 0x56004, 2 }, - [GCC_UNIPHY1_SOFT_RESET] = { 0x56104, 0 }, + [GCC_UNIPHY1_SOFT_RESET] = { .reg = 0x56104, .bitmask = 0x32 }, [GCC_UNIPHY1_XPCS_RESET] = { 0x56104, 2 }, - [GCC_EDMA_HW_RESET] = { 0x68014, 0 }, - [GCC_NSSPORT1_RESET] = { 0x68014, 0 }, - [GCC_NSSPORT2_RESET] = { 0x68014, 0 }, - [GCC_NSSPORT3_RESET] = { 0x68014, 0 }, - [GCC_NSSPORT4_RESET] = { 0x68014, 0 }, - [GCC_NSSPORT5_RESET] = { 0x68014, 0 }, - [GCC_UNIPHY0_PORT1_ARES] = { 0x56004, 0 }, - [GCC_UNIPHY0_PORT2_ARES] = { 0x56004, 0 }, - [GCC_UNIPHY0_PORT3_ARES] = { 0x56004, 0 }, - [GCC_UNIPHY0_PORT4_ARES] = { 0x56004, 0 }, - [GCC_UNIPHY0_PORT5_ARES] = { 0x56004, 0 }, - [GCC_UNIPHY0_PORT_4_5_RESET] = { 0x56004, 0 }, - [GCC_UNIPHY0_PORT_4_RESET] = { 0x56004, 0 }, + [GCC_EDMA_HW_RESET] = { .reg = 0x68014, .bitmask = 0x300000 }, + [GCC_NSSPORT1_RESET] = { .reg = 0x68014, .bitmask = 0x1000003 }, + [GCC_NSSPORT2_RESET] = { .reg = 0x68014, .bitmask = 0x200000c }, + [GCC_NSSPORT3_RESET] = { .reg = 0x68014, .bitmask = 0x4000030 }, + [GCC_NSSPORT4_RESET] = { .reg = 0x68014, .bitmask = 0x8000300 }, + [GCC_NSSPORT5_RESET] = { .reg = 0x68014, .bitmask = 0x10000c00 }, + [GCC_UNIPHY0_PORT1_ARES] = { .reg = 0x56004, .bitmask = 0x30 }, + [GCC_UNIPHY0_PORT2_ARES] = { .reg = 0x56004, .bitmask = 0xc0 }, + [GCC_UNIPHY0_PORT3_ARES] = { .reg = 0x56004, .bitmask = 0x300 }, + [GCC_UNIPHY0_PORT4_ARES] = { .reg = 0x56004, .bitmask = 0xc00 }, + [GCC_UNIPHY0_PORT5_ARES] = { .reg = 0x56004, .bitmask = 0x3000 }, + [GCC_UNIPHY0_PORT_4_5_RESET] = { .reg = 0x56004, .bitmask = 0x3c02 }, + [GCC_UNIPHY0_PORT_4_RESET] = { .reg = 0x56004, .bitmask = 0xc02 }, [GCC_LPASS_BCR] = {0x1F000, 0}, [GCC_UBI32_TBU_BCR] = {0x65000, 0}, [GCC_LPASS_TBU_BCR] = {0x6C000, 0}, From 74f8606ddfa450d2255b4e61472a7632def1e8c4 Mon Sep 17 00:00:00 2001 From: Vladislav Efanov Date: Wed, 17 May 2023 20:25:18 +0300 Subject: [PATCH 3962/4345] usb: dwc3: qcom: Fix potential memory leak [ Upstream commit 097fb3ee710d4de83b8d4f5589e8ee13e0f0541e ] Function dwc3_qcom_probe() allocates memory for resource structure which is pointed by parent_res pointer. This memory is not freed. This leads to memory leak. Use stack memory to prevent memory leak. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 2bc02355f8ba ("usb: dwc3: qcom: Add support for booting with ACPI") Signed-off-by: Vladislav Efanov Acked-by: Shawn Guo Link: https://lore.kernel.org/r/20230517172518.442591-1-VEfanov@ispras.ru Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/dwc3/dwc3-qcom.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index dac13fe97811..5c66efb05d7f 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -722,6 +722,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct dwc3_qcom *qcom; struct resource *res, *parent_res = NULL; + struct resource local_res; int ret, i; bool ignore_pipe_clk; @@ -772,9 +773,8 @@ static int dwc3_qcom_probe(struct platform_device *pdev) if (np) { parent_res = res; } else { - parent_res = kmemdup(res, sizeof(struct resource), GFP_KERNEL); - if (!parent_res) - return -ENOMEM; + memcpy(&local_res, res, sizeof(struct resource)); + parent_res = &local_res; parent_res->start = res->start + qcom->acpi_pdata->qscratch_base_offset; From 2788a3553f7497075653210b42e2aeb6ba95e28e Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Fri, 5 May 2023 14:48:37 +0530 Subject: [PATCH 3963/4345] usb: gadget: u_serial: Add null pointer check in gserial_suspend [ Upstream commit 2f6ecb89fe8feb2b60a53325b0eeb9866d88909a ] Consider a case where gserial_disconnect has already cleared gser->ioport. And if gserial_suspend gets called afterwards, it will lead to accessing of gser->ioport and thus causing null pointer dereference. Avoid this by adding a null pointer check. Added a static spinlock to prevent gser->ioport from becoming null after the newly added null pointer check. Fixes: aba3a8d01d62 ("usb: gadget: u_serial: add suspend resume callbacks") Signed-off-by: Prashanth K Link: https://lore.kernel.org/r/1683278317-11774-1-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/gadget/function/u_serial.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 7b54e814aefb..3b5a6430e241 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -1421,10 +1421,19 @@ EXPORT_SYMBOL_GPL(gserial_disconnect); void gserial_suspend(struct gserial *gser) { - struct gs_port *port = gser->ioport; + struct gs_port *port; unsigned long flags; - spin_lock_irqsave(&port->port_lock, flags); + spin_lock_irqsave(&serial_port_lock, flags); + port = gser->ioport; + + if (!port) { + spin_unlock_irqrestore(&serial_port_lock, flags); + return; + } + + spin_lock(&port->port_lock); + spin_unlock(&serial_port_lock); port->suspended = true; spin_unlock_irqrestore(&port->port_lock, flags); } From dac7d7efcb545692a110df611c9c195737967451 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 22 Mar 2023 16:39:52 +0200 Subject: [PATCH 3964/4345] extcon: Fix kernel doc of property fields to avoid warnings [ Upstream commit 7e77e0b7a9f4cdf91cb0950749b40c840ea63efc ] Kernel documentation has to be synchronized with a code, otherwise the validator is not happy: Function parameter or member 'usb_propval' not described in 'extcon_cable' Function parameter or member 'chg_propval' not described in 'extcon_cable' Function parameter or member 'jack_propval' not described in 'extcon_cable' Function parameter or member 'disp_propval' not described in 'extcon_cable' Describe the fields added in the past. Fixes: 067c1652e7a7 ("extcon: Add the support for extcon property according to extcon type") Signed-off-by: Andy Shevchenko Signed-off-by: Chanwoo Choi Signed-off-by: Sasha Levin --- drivers/extcon/extcon.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index 356610404bb4..3bc83feb5a34 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -196,6 +196,10 @@ static const struct __extcon_info { * @attr_name: "name" sysfs entry * @attr_state: "state" sysfs entry * @attrs: the array pointing to attr_name and attr_state for attr_g + * @usb_propval: the array of USB connector properties + * @chg_propval: the array of charger connector properties + * @jack_propval: the array of jack connector properties + * @disp_propval: the array of display connector properties */ struct extcon_cable { struct extcon_dev *edev; From 6538e5d9f7eb90ea7cd50eb24ee18a205cfa9d00 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 22 Mar 2023 16:39:53 +0200 Subject: [PATCH 3965/4345] extcon: Fix kernel doc of property capability fields to avoid warnings [ Upstream commit 73346b9965ebda2feb7fef8629e9b28baee820e3 ] Kernel documentation has to be synchronized with a code, otherwise the validator is not happy: Function parameter or member 'usb_bits' not described in 'extcon_cable' Function parameter or member 'chg_bits' not described in 'extcon_cable' Function parameter or member 'jack_bits' not described in 'extcon_cable' Function parameter or member 'disp_bits' not described in 'extcon_cable' Describe the fields added in the past. Fixes: ceaa98f442cf ("extcon: Add the support for the capability of each property") Signed-off-by: Andy Shevchenko Signed-off-by: Chanwoo Choi Signed-off-by: Sasha Levin --- drivers/extcon/extcon.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index 3bc83feb5a34..fa08dec389dc 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -200,6 +200,10 @@ static const struct __extcon_info { * @chg_propval: the array of charger connector properties * @jack_propval: the array of jack connector properties * @disp_propval: the array of display connector properties + * @usb_bits: the bit array of the USB connector property capabilities + * @chg_bits: the bit array of the charger connector property capabilities + * @jack_bits: the bit array of the jack connector property capabilities + * @disp_bits: the bit array of the display connector property capabilities */ struct extcon_cable { struct extcon_dev *edev; From 56901de563359de20513e16a9ae008ae2c22e9a9 Mon Sep 17 00:00:00 2001 From: Li Yang Date: Thu, 20 Apr 2023 22:08:31 +0800 Subject: [PATCH 3966/4345] usb: phy: phy-tahvo: fix memory leak in tahvo_usb_probe() [ Upstream commit 342161c11403ea00e9febc16baab1d883d589d04 ] Smatch reports: drivers/usb/phy/phy-tahvo.c: tahvo_usb_probe() warn: missing unwind goto? After geting irq, if ret < 0, it will return without error handling to free memory. Just add error handling to fix this problem. Fixes: 0d45a1373e66 ("usb: phy: tahvo: add IRQ check") Signed-off-by: Li Yang Reviewed-by: Dongliang Mu Link: https://lore.kernel.org/r/20230420140832.9110-1-lidaxian@hust.edu.cn Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/phy/phy-tahvo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/phy/phy-tahvo.c b/drivers/usb/phy/phy-tahvo.c index a3e043e3e4aa..d0672b671298 100644 --- a/drivers/usb/phy/phy-tahvo.c +++ b/drivers/usb/phy/phy-tahvo.c @@ -395,7 +395,7 @@ static int tahvo_usb_probe(struct platform_device *pdev) tu->irq = ret = platform_get_irq(pdev, 0); if (ret < 0) - return ret; + goto err_remove_phy; ret = request_threaded_irq(tu->irq, NULL, tahvo_usb_vbus_interrupt, IRQF_ONESHOT, "tahvo-vbus", tu); From d66ddb61fa23ed67a7aafc8cacab75e88dc62f49 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 22:17:42 +0200 Subject: [PATCH 3967/4345] usb: hide unused usbfs_notify_suspend/resume functions [ Upstream commit 8e6bd945e6dde64fbc60ec3fe252164493a8d3a2 ] The declaration is in an #ifdef, which causes warnings when building with 'make W=1' and without CONFIG_PM: drivers/usb/core/devio.c:742:6: error: no previous prototype for 'usbfs_notify_suspend' drivers/usb/core/devio.c:747:6: error: no previous prototype for 'usbfs_notify_resume' Use the same #ifdef check around the function definitions to avoid the warnings and slightly shrink the USB core. Fixes: 7794f486ed0b ("usbfs: Add ioctls for runtime power management") Signed-off-by: Arnd Bergmann Reviewed-by: Sebastian Reichel Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230516202103.558301-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/core/devio.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 2fe29319de44..1b95035d179f 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -734,6 +734,7 @@ static int driver_resume(struct usb_interface *intf) return 0; } +#ifdef CONFIG_PM /* The following routines apply to the entire device, not interfaces */ void usbfs_notify_suspend(struct usb_device *udev) { @@ -752,6 +753,7 @@ void usbfs_notify_resume(struct usb_device *udev) } mutex_unlock(&usbfs_mutex); } +#endif struct usb_driver usbfs_driver = { .name = "usbfs", From 8d65d0a2bfd5f38d539a1aa9866421177b417380 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 25 May 2023 11:37:54 +0206 Subject: [PATCH 3968/4345] serial: 8250: lock port for stop_rx() in omap8250_irq() [ Upstream commit ca73a892c5bec4b08a2fa22b3015e98ed905abb7 ] The uarts_ops stop_rx() callback expects that the port->lock is taken and interrupts are disabled. Fixes: 1fe0e1fa3209 ("serial: 8250_omap: Handle optional overrun-throttle-ms property") Signed-off-by: John Ogness Reviewed-by: Tony Lindgren Link: https://lore.kernel.org/r/20230525093159.223817-4-john.ogness@linutronix.de Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_omap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 6b255e1633fd..6043d4fa08cc 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -655,7 +655,9 @@ static irqreturn_t omap8250_irq(int irq, void *dev_id) up->ier = port->serial_in(port, UART_IER); if (up->ier & (UART_IER_RLSI | UART_IER_RDI)) { + spin_lock(&port->lock); port->ops->stop_rx(port); + spin_unlock(&port->lock); } else { /* Keep restarting the timer until * the input overrun subsides. From a59f64a83516a2507920dd86ba3beee35d71cc6d Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 25 May 2023 11:37:58 +0206 Subject: [PATCH 3969/4345] serial: 8250: lock port for UART_IER access in omap8250_irq() [ Upstream commit 25614735a647693c1260f253dc3ab32127697806 ] omap8250_irq() accesses UART_IER. This register is modified twice by each console write (serial8250_console_write()) under the port lock. omap8250_irq() must also take the port lock to guanentee synchronized access to UART_IER. Since the port lock is already being taken for the stop_rx() callback and since it is safe to call cancel_delayed_work() while holding the port lock, simply extend the port lock region to include UART_IER access. Fixes: 1fe0e1fa3209 ("serial: 8250_omap: Handle optional overrun-throttle-ms property") Signed-off-by: John Ogness Reviewed-by: Tony Lindgren Link: https://lore.kernel.org/r/20230525093159.223817-8-john.ogness@linutronix.de Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_omap.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 6043d4fa08cc..af39a2c4c2ee 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -653,17 +653,18 @@ static irqreturn_t omap8250_irq(int irq, void *dev_id) if ((lsr & UART_LSR_OE) && up->overrun_backoff_time_ms > 0) { unsigned long delay; + /* Synchronize UART_IER access against the console. */ + spin_lock(&port->lock); up->ier = port->serial_in(port, UART_IER); if (up->ier & (UART_IER_RLSI | UART_IER_RDI)) { - spin_lock(&port->lock); port->ops->stop_rx(port); - spin_unlock(&port->lock); } else { /* Keep restarting the timer until * the input overrun subsides. */ cancel_delayed_work(&up->overrun_backoff); } + spin_unlock(&port->lock); delay = msecs_to_jiffies(up->overrun_backoff_time_ms); schedule_delayed_work(&up->overrun_backoff, delay); From 018eddcb6beff0c7e4f417a4cf05122b6c6d57db Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 23 May 2023 10:40:17 +0800 Subject: [PATCH 3970/4345] kernfs: fix missing kernfs_idr_lock to remove an ID from the IDR [ Upstream commit 30480b988f88c279752f3202a26b6fee5f586aef ] The root->ino_idr is supposed to be protected by kernfs_idr_lock, fix it. Fixes: 488dee96bb62 ("kernfs: allow creating kernfs objects with arbitrary uid/gid") Signed-off-by: Muchun Song Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20230523024017.24851-1-songmuchun@bytedance.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- fs/kernfs/dir.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 8b3c86a502da..c91ee05cce74 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -679,7 +679,9 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, return kn; err_out3: + spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); + spin_unlock(&kernfs_idr_lock); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: From e52019c095352af3d0fd2b2416c1307a54939337 Mon Sep 17 00:00:00 2001 From: James Clark Date: Tue, 25 Apr 2023 15:35:28 +0100 Subject: [PATCH 3971/4345] coresight: Fix loss of connection info when a module is unloaded [ Upstream commit c45b2835e7b205783bdfe08cc98fa86a7c5eeb74 ] child_fwnode should be a read only property based on the DT or ACPI. If it's cleared on the parent device when a child is unloaded, then when the child is loaded again the connection won't be remade. child_dev should be cleared instead which signifies that the connection should be remade when the child_fwnode registers a new coresight_device. Similarly the reference count shouldn't be decremented as long as the parent device exists. The correct place to drop the reference is in coresight_release_platform_data() which is already done. Reproducible on Juno with the following steps: # load all coresight modules. $ cd /sys/bus/coresight/devices/ $ echo 1 > tmc_etr0/enable_sink $ echo 1 > etm0/enable_source # Works fine ^ $ echo 0 > etm0/enable_source $ rmmod coresight-funnel $ modprobe coresight-funnel $ echo 1 > etm0/enable_source -bash: echo: write error: Invalid argument Fixes: 37ea1ffddffa ("coresight: Use fwnode handle instead of device names") Fixes: 2af89ebacf29 ("coresight: Clear the connection field properly") Tested-by: Suzuki K Poulose Reviewed-by: Mike Leach Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230425143542.2305069-2-james.clark@arm.com Signed-off-by: Sasha Levin --- drivers/hwtracing/coresight/coresight-core.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index 5ddc8103503b..c4b805b04531 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -1376,13 +1376,8 @@ static int coresight_remove_match(struct device *dev, void *data) if (csdev->dev.fwnode == conn->child_fwnode) { iterator->orphan = true; coresight_remove_links(iterator, conn); - /* - * Drop the reference to the handle for the remote - * device acquired in parsing the connections from - * platform data. - */ - fwnode_handle_put(conn->child_fwnode); - conn->child_fwnode = NULL; + + conn->child_dev = NULL; /* No need to continue */ break; } From 02b22660231db3c1a55d6709c5b9db165d0794c7 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Mon, 15 May 2023 22:57:10 +0200 Subject: [PATCH 3972/4345] mfd: rt5033: Drop rt5033-battery sub-device [ Upstream commit 43db1344e0f8c1eb687a1d6cd5b0de3009ab66cb ] The fuel gauge in the RT5033 PMIC (rt5033-battery) has its own I2C bus and interrupt lines. Therefore, it is not part of the MFD device and needs to be specified separately in the device tree. Fixes: 0b271258544b ("mfd: rt5033: Add Richtek RT5033 driver core.") Signed-off-by: Stephan Gerhold Signed-off-by: Jakob Hauser Reviewed-by: Linus Walleij Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/6a8a19bc67b5be3732882e8131ad2ffcb546ac03.1684182964.git.jahau@rocketmail.com Signed-off-by: Sasha Levin --- drivers/mfd/rt5033.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/mfd/rt5033.c b/drivers/mfd/rt5033.c index 48381d9bf740..302115dabff4 100644 --- a/drivers/mfd/rt5033.c +++ b/drivers/mfd/rt5033.c @@ -41,9 +41,6 @@ static const struct mfd_cell rt5033_devs[] = { { .name = "rt5033-charger", .of_compatible = "richtek,rt5033-charger", - }, { - .name = "rt5033-battery", - .of_compatible = "richtek,rt5033-battery", }, { .name = "rt5033-led", .of_compatible = "richtek,rt5033-led", From b754ea60e690ffae053e8da79bc78d2f9d1f6e1f Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Sat, 12 Sep 2020 20:03:01 +0100 Subject: [PATCH 3973/4345] media: venus: helpers: Fix ALIGN() of non power of two [ Upstream commit 927e78ac8bc58155316cf6f46026e1912bbbbcfc ] ALIGN() expects its second argument to be a power of 2, otherwise incorrect results are produced for some inputs. The output can be both larger or smaller than what is expected. For example, ALIGN(304, 192) equals 320 instead of 384, and ALIGN(65, 192) equals 256 instead of 192. However, nestling two ALIGN() as is done in this case seem to only produce results equal to or bigger than the expected result if ALIGN() had handled non powers of two, and that in turn results in framesizes that are either the correct size or too large. Fortunately, since 192 * 4 / 3 equals 256, it turns out that one ALIGN() is sufficient. Fixes: ab1eda449c6e ("media: venus: vdec: handle 10bit bitstreams") Signed-off-by: Rikard Falkeborn Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/platform/qcom/venus/helpers.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c index 5ca3920237c5..5fdce5f07364 100644 --- a/drivers/media/platform/qcom/venus/helpers.c +++ b/drivers/media/platform/qcom/venus/helpers.c @@ -917,8 +917,8 @@ static u32 get_framesize_raw_yuv420_tp10_ubwc(u32 width, u32 height) u32 extradata = SZ_16K; u32 size; - y_stride = ALIGN(ALIGN(width, 192) * 4 / 3, 256); - uv_stride = ALIGN(ALIGN(width, 192) * 4 / 3, 256); + y_stride = ALIGN(width * 4 / 3, 256); + uv_stride = ALIGN(width * 4 / 3, 256); y_sclines = ALIGN(height, 16); uv_sclines = ALIGN((height + 1) >> 1, 16); From 4e8e838fce5e34b81fd8c17560be7ca27b212660 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 26 May 2023 12:53:23 +0100 Subject: [PATCH 3974/4345] media: atomisp: gmin_platform: fix out_len in gmin_get_config_dsm_var() [ Upstream commit 1657f2934daf89e8d9fa4b2697008909eb22c73e ] Ideally, strlen(cur->string.pointer) and strlen(out) would be the same. But this code is using strscpy() to avoid a potential buffer overflow. So in the same way we should take the strlen() of the smaller string to avoid a buffer overflow in the caller, gmin_get_var_int(). Link: https://lore.kernel.org/r/26124bcd-8132-4483-9d67-225c87d424e8@kili.mountain Fixes: 387041cda44e ("media: atomisp: improve sensor detection code to use _DSM table") Signed-off-by: Dan Carpenter Signed-off-by: Hans de Goede Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c b/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c index c9ee85037644..f0387486eb17 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c +++ b/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c @@ -1198,7 +1198,7 @@ static int gmin_get_config_dsm_var(struct device *dev, dev_info(dev, "found _DSM entry for '%s': %s\n", var, cur->string.pointer); strscpy(out, cur->string.pointer, *out_len); - *out_len = strlen(cur->string.pointer); + *out_len = strlen(out); ACPI_FREE(obj); return 0; From 96898fb476d17704149d9f23716a399b6efbb522 Mon Sep 17 00:00:00 2001 From: Nico Boehr Date: Fri, 24 Mar 2023 15:54:23 +0100 Subject: [PATCH 3975/4345] KVM: s390: fix KVM_S390_GET_CMMA_BITS for GFNs in memslot holes [ Upstream commit 285cff4c0454340a4dc53f46e67f2cb1c293bd74 ] The KVM_S390_GET_CMMA_BITS ioctl may return incorrect values when userspace specifies a start_gfn outside of memslots. This can occur when a VM has multiple memslots with a hole in between: +-----+----------+--------+--------+ | ... | Slot N-1 | | Slot N | +-----+----------+--------+--------+ ^ ^ ^ ^ | | | | GFN A A+B | | A+B+C | A+B+C+D When userspace specifies a GFN in [A+B, A+B+C), it would expect to get the CMMA values of the first dirty page in Slot N. However, userspace may get a start_gfn of A+B+C+D with a count of 0, hence completely skipping over any dirty pages in slot N. The error is in kvm_s390_next_dirty_cmma(), which assumes gfn_to_memslot_approx() will return the memslot _below_ the specified GFN when the specified GFN lies outside a memslot. In reality it may return either the memslot below or above the specified GFN. When a memslot above the specified GFN is returned this happens: - ofs is calculated, but since the memslot's base_gfn is larger than the specified cur_gfn, ofs will underflow to a huge number. - ofs is passed to find_next_bit(). Since ofs will exceed the memslot's number of pages, the number of pages in the memslot is returned, completely skipping over all bits in the memslot userspace would be interested in. Fix this by resetting ofs to zero when a memslot _above_ cur_gfn is returned (cur_gfn < ms->base_gfn). Signed-off-by: Nico Boehr Reviewed-by: Claudio Imbrenda Fixes: afdad61615cc ("KVM: s390: Fix storage attributes migration with memory slots") Message-Id: <20230324145424.293889-2-nrb@linux.ibm.com> Signed-off-by: Claudio Imbrenda Signed-off-by: Janosch Frank Signed-off-by: Sasha Levin --- arch/s390/kvm/kvm-s390.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 7ffc73ba220f..7a326d03087a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2005,6 +2005,10 @@ static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots, ms = slots->memslots + slotidx; ofs = 0; } + + if (cur_gfn < ms->base_gfn) + ofs = 0; + ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs); while ((slotidx > 0) && (ofs >= ms->npages)) { slotidx--; From a6171452085bad41d13e68dcb58d3ccb16c75552 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 4 Jun 2023 17:04:37 +0200 Subject: [PATCH 3976/4345] usb: dwc3: qcom: Release the correct resources in dwc3_qcom_remove() [ Upstream commit 8fd95da2cfb5046c4bb5a3cdc9eb7963ba8b10dd ] In the probe, some resources are allocated with dwc3_qcom_of_register_core() or dwc3_qcom_acpi_register_core(). The corresponding resources are already coorectly freed in the error handling path of the probe, but not in the remove function. Fix it. Fixes: 2bc02355f8ba ("usb: dwc3: qcom: Add support for booting with ACPI") Signed-off-by: Christophe JAILLET Reviewed-by: Andrew Halaney Message-ID: Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/dwc3/dwc3-qcom.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index 5c66efb05d7f..495d8bb8f156 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -869,10 +869,14 @@ reset_assert: static int dwc3_qcom_remove(struct platform_device *pdev) { struct dwc3_qcom *qcom = platform_get_drvdata(pdev); + struct device_node *np = pdev->dev.of_node; struct device *dev = &pdev->dev; int i; - of_platform_depopulate(dev); + if (np) + of_platform_depopulate(&pdev->dev); + else + platform_device_put(pdev); for (i = qcom->num_clocks - 1; i >= 0; i--) { clk_disable_unprepare(qcom->clks[i]); From 0e9e127835c8ac157d9110be203ebfd639f526ef Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 4 Jun 2023 16:56:34 +0200 Subject: [PATCH 3977/4345] usb: dwc3: qcom: Fix an error handling path in dwc3_qcom_probe() [ Upstream commit 4a944da707123686d372ec01ea60056902fadf35 ] If dwc3_qcom_create_urs_usb_platdev() fails, some resources still need to be released, as already done in the other error handling path of the probe. Fixes: c25c210f590e ("usb: dwc3: qcom: add URS Host support for sdm845 ACPI boot") Signed-off-by: Christophe JAILLET Reviewed-by: Andrew Halaney Message-ID: Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/dwc3/dwc3-qcom.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index 495d8bb8f156..ec8c43231746 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -786,9 +786,10 @@ static int dwc3_qcom_probe(struct platform_device *pdev) if (IS_ERR_OR_NULL(qcom->urs_usb)) { dev_err(dev, "failed to create URS USB platdev\n"); if (!qcom->urs_usb) - return -ENODEV; + ret = -ENODEV; else - return PTR_ERR(qcom->urs_usb); + ret = PTR_ERR(qcom->urs_usb); + goto clk_disable; } } } From 7ade555ac58d12d1de6c5b4c5a79d631b1d06233 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Wed, 31 May 2023 20:11:14 +0530 Subject: [PATCH 3978/4345] usb: common: usb-conn-gpio: Set last role to unknown before initial detection [ Upstream commit edd60d24bd858cef165274e4cd6cab43bdc58d15 ] Currently if we bootup a device without cable connected, then usb-conn-gpio won't call set_role() since last_role is same as current role. This happens because during probe last_role gets initialised to zero. To avoid this, added a new constant in enum usb_role, last_role is set to USB_ROLE_UNKNOWN before performing initial detection. While at it, also handle default case for the usb_role switch in cdns3, intel-xhci-usb-role-switch & musb/jz4740 to avoid build warnings. Fixes: 4602f3bff266 ("usb: common: add USB GPIO based connection detection driver") Signed-off-by: Prashanth K Reviewed-by: AngeloGioacchino Del Regno Message-ID: <1685544074-17337-1-git-send-email-quic_prashk@quicinc.com> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/cdns3/core.c | 2 ++ drivers/usb/common/usb-conn-gpio.c | 3 +++ drivers/usb/musb/jz4740.c | 2 ++ drivers/usb/roles/intel-xhci-usb-role-switch.c | 2 ++ include/linux/usb/role.h | 1 + 5 files changed, 10 insertions(+) diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index 8fe7420de033..e5fe640b2bb0 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -243,6 +243,8 @@ static enum usb_role cdns3_hw_role_state_machine(struct cdns3 *cdns) if (!vbus) role = USB_ROLE_NONE; break; + default: + break; } dev_dbg(cdns->dev, "role %d -> %d\n", cdns->role, role); diff --git a/drivers/usb/common/usb-conn-gpio.c b/drivers/usb/common/usb-conn-gpio.c index c9545a4eff66..5754e467c16a 100644 --- a/drivers/usb/common/usb-conn-gpio.c +++ b/drivers/usb/common/usb-conn-gpio.c @@ -276,6 +276,9 @@ static int usb_conn_probe(struct platform_device *pdev) platform_set_drvdata(pdev, info); + /* Set last role to unknown before performing the initial detection */ + info->last_role = USB_ROLE_UNKNOWN; + /* Perform initial detection */ usb_conn_queue_dwork(info, 0); diff --git a/drivers/usb/musb/jz4740.c b/drivers/usb/musb/jz4740.c index c4fe1f4cd17a..f283629091ec 100644 --- a/drivers/usb/musb/jz4740.c +++ b/drivers/usb/musb/jz4740.c @@ -91,6 +91,8 @@ static int jz4740_musb_role_switch_set(struct usb_role_switch *sw, case USB_ROLE_HOST: atomic_notifier_call_chain(&phy->notifier, USB_EVENT_ID, phy); break; + default: + break; } return 0; diff --git a/drivers/usb/roles/intel-xhci-usb-role-switch.c b/drivers/usb/roles/intel-xhci-usb-role-switch.c index 5c96e929acea..4d6a3dd06e01 100644 --- a/drivers/usb/roles/intel-xhci-usb-role-switch.c +++ b/drivers/usb/roles/intel-xhci-usb-role-switch.c @@ -97,6 +97,8 @@ static int intel_xhci_usb_set_role(struct usb_role_switch *sw, val |= SW_VBUS_VALID; drd_config = DRD_CONFIG_STATIC_DEVICE; break; + default: + break; } val |= SW_IDPIN_EN; if (data->enable_sw_switch) { diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h index b9ccaeb8a4ae..aecfce46d354 100644 --- a/include/linux/usb/role.h +++ b/include/linux/usb/role.h @@ -11,6 +11,7 @@ enum usb_role { USB_ROLE_NONE, USB_ROLE_HOST, USB_ROLE_DEVICE, + USB_ROLE_UNKNOWN, }; typedef int (*usb_role_switch_set_t)(struct usb_role_switch *sw, From 1dc07edc01d26880065b17aba55f2d9884171198 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 10 Jun 2023 15:32:52 +0200 Subject: [PATCH 3979/4345] usb: dwc3-meson-g12a: Fix an error handling path in dwc3_meson_g12a_probe() [ Upstream commit 01052b91c9808e3c3b068ae2721cb728ec9aa4c0 ] If dwc3_meson_g12a_otg_init() fails, resources allocated by the previous of_platform_populate() call should be released, as already done in the error handling path. Fixes: 1e355f21d3fb ("usb: dwc3: Add Amlogic A1 DWC3 glue") Signed-off-by: Christophe JAILLET Reviewed-by: Martin Blumenstingl Reviewed-by: Neil Armstrong Message-ID: <9d28466de1808ccc756b4cc25fc72c482d133d13.1686403934.git.christophe.jaillet@wanadoo.fr> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/dwc3/dwc3-meson-g12a.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c index d0f9b7c296b0..69ec06efd7f2 100644 --- a/drivers/usb/dwc3/dwc3-meson-g12a.c +++ b/drivers/usb/dwc3/dwc3-meson-g12a.c @@ -805,7 +805,7 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev) ret = dwc3_meson_g12a_otg_init(pdev, priv); if (ret) - goto err_phys_power; + goto err_plat_depopulate; pm_runtime_set_active(dev); pm_runtime_enable(dev); @@ -813,6 +813,9 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev) return 0; +err_plat_depopulate: + of_platform_depopulate(dev); + err_phys_power: for (i = 0 ; i < PHY_COUNT ; ++i) phy_power_off(priv->phys[i]); From a81e1f22e17f4e18a119f07d3cdf3ec906621113 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Fri, 9 Jun 2023 09:48:18 +0800 Subject: [PATCH 3980/4345] mfd: intel-lpss: Add missing check for platform_get_resource [ Upstream commit d918e0d5824495a75d00b879118b098fcab36fdb ] Add the missing check for platform_get_resource and return error if it fails. Fixes: 4b45efe85263 ("mfd: Add support for Intel Sunrisepoint LPSS devices") Signed-off-by: Jiasheng Jiang Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230609014818.28475-1-jiasheng@iscas.ac.cn Signed-off-by: Sasha Levin --- drivers/mfd/intel-lpss-acpi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mfd/intel-lpss-acpi.c b/drivers/mfd/intel-lpss-acpi.c index 045cbf0cbe53..993e305a232c 100644 --- a/drivers/mfd/intel-lpss-acpi.c +++ b/drivers/mfd/intel-lpss-acpi.c @@ -114,6 +114,9 @@ static int intel_lpss_acpi_probe(struct platform_device *pdev) return -ENOMEM; info->mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!info->mem) + return -ENODEV; + info->irq = platform_get_irq(pdev, 0); ret = intel_lpss_probe(&pdev->dev, info); From 8e00ae25a37159e8fa619ade9204c58cdfa7370e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 15 Jun 2023 11:30:35 +0200 Subject: [PATCH 3981/4345] Revert "usb: common: usb-conn-gpio: Set last role to unknown before initial detection" [ Upstream commit df49f2a0ac4a34c0cb4b5c233fcfa0add644c43c ] This reverts commit edd60d24bd858cef165274e4cd6cab43bdc58d15. Heikki reports that this should not be a global flag just to work around one broken driver and should be fixed differently, so revert it. Reported-by: Heikki Krogerus Fixes: edd60d24bd85 ("usb: common: usb-conn-gpio: Set last role to unknown before initial detection") Link: https://lore.kernel.org/r/ZImE4L3YgABnCIsP@kuha.fi.intel.com Cc: Prashanth K Cc: AngeloGioacchino Del Regno Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/usb/cdns3/core.c | 2 -- drivers/usb/common/usb-conn-gpio.c | 3 --- drivers/usb/musb/jz4740.c | 2 -- drivers/usb/roles/intel-xhci-usb-role-switch.c | 2 -- include/linux/usb/role.h | 1 - 5 files changed, 10 deletions(-) diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c index e5fe640b2bb0..8fe7420de033 100644 --- a/drivers/usb/cdns3/core.c +++ b/drivers/usb/cdns3/core.c @@ -243,8 +243,6 @@ static enum usb_role cdns3_hw_role_state_machine(struct cdns3 *cdns) if (!vbus) role = USB_ROLE_NONE; break; - default: - break; } dev_dbg(cdns->dev, "role %d -> %d\n", cdns->role, role); diff --git a/drivers/usb/common/usb-conn-gpio.c b/drivers/usb/common/usb-conn-gpio.c index 5754e467c16a..c9545a4eff66 100644 --- a/drivers/usb/common/usb-conn-gpio.c +++ b/drivers/usb/common/usb-conn-gpio.c @@ -276,9 +276,6 @@ static int usb_conn_probe(struct platform_device *pdev) platform_set_drvdata(pdev, info); - /* Set last role to unknown before performing the initial detection */ - info->last_role = USB_ROLE_UNKNOWN; - /* Perform initial detection */ usb_conn_queue_dwork(info, 0); diff --git a/drivers/usb/musb/jz4740.c b/drivers/usb/musb/jz4740.c index f283629091ec..c4fe1f4cd17a 100644 --- a/drivers/usb/musb/jz4740.c +++ b/drivers/usb/musb/jz4740.c @@ -91,8 +91,6 @@ static int jz4740_musb_role_switch_set(struct usb_role_switch *sw, case USB_ROLE_HOST: atomic_notifier_call_chain(&phy->notifier, USB_EVENT_ID, phy); break; - default: - break; } return 0; diff --git a/drivers/usb/roles/intel-xhci-usb-role-switch.c b/drivers/usb/roles/intel-xhci-usb-role-switch.c index 4d6a3dd06e01..5c96e929acea 100644 --- a/drivers/usb/roles/intel-xhci-usb-role-switch.c +++ b/drivers/usb/roles/intel-xhci-usb-role-switch.c @@ -97,8 +97,6 @@ static int intel_xhci_usb_set_role(struct usb_role_switch *sw, val |= SW_VBUS_VALID; drd_config = DRD_CONFIG_STATIC_DEVICE; break; - default: - break; } val |= SW_IDPIN_EN; if (data->enable_sw_switch) { diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h index aecfce46d354..b9ccaeb8a4ae 100644 --- a/include/linux/usb/role.h +++ b/include/linux/usb/role.h @@ -11,7 +11,6 @@ enum usb_role { USB_ROLE_NONE, USB_ROLE_HOST, USB_ROLE_DEVICE, - USB_ROLE_UNKNOWN, }; typedef int (*usb_role_switch_set_t)(struct usb_role_switch *sw, From 5b31ac1d6d889bdd2e7bd97cfa8b993323ae300b Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 14 Jun 2023 07:59:19 +0300 Subject: [PATCH 3982/4345] serial: 8250_omap: Use force_suspend and resume for system suspend [ Upstream commit 20a41a62618df85f3a2981008edec5cadd785e0a ] We should not rely on autosuspend timeout for system suspend. Instead, let's use force_suspend and force_resume functions. Otherwise the serial port controller device may not be idled on suspend. As we are doing a register write on suspend to configure the serial port, we still need to runtime PM resume the port on suspend. While at it, let's switch to pm_runtime_resume_and_get() and check for errors returned. And let's add the missing line break before return to the suspend function while at it. Fixes: 09d8b2bdbc5c ("serial: 8250: omap: Provide ability to enable/disable UART as wakeup source") Signed-off-by: Tony Lindgren Tested-by: Dhruva Gole Message-ID: <20230614045922.4798-1-tony@atomide.com> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- drivers/tty/serial/8250/8250_omap.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index af39a2c4c2ee..e26ac3f42e05 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -1521,25 +1521,35 @@ static int omap8250_suspend(struct device *dev) { struct omap8250_priv *priv = dev_get_drvdata(dev); struct uart_8250_port *up = serial8250_get_port(priv->line); + int err; serial8250_suspend_port(priv->line); - pm_runtime_get_sync(dev); + err = pm_runtime_resume_and_get(dev); + if (err) + return err; if (!device_may_wakeup(dev)) priv->wer = 0; serial_out(up, UART_OMAP_WER, priv->wer); - pm_runtime_mark_last_busy(dev); - pm_runtime_put_autosuspend(dev); - + err = pm_runtime_force_suspend(dev); flush_work(&priv->qos_work); - return 0; + + return err; } static int omap8250_resume(struct device *dev) { struct omap8250_priv *priv = dev_get_drvdata(dev); + int err; + err = pm_runtime_force_resume(dev); + if (err) + return err; serial8250_resume_port(priv->line); + /* Paired with pm_runtime_resume_and_get() in omap8250_suspend() */ + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + return 0; } #else From 4d2405147385e6e281585230c3e7a54464876ea5 Mon Sep 17 00:00:00 2001 From: Mirsad Goran Todorovac Date: Tue, 6 Jun 2023 09:08:10 +0200 Subject: [PATCH 3983/4345] test_firmware: return ENOMEM instead of ENOSPC on failed memory allocation [ Upstream commit 7dae593cd226a0bca61201cf85ceb9335cf63682 ] In a couple of situations like name = kstrndup(buf, count, GFP_KERNEL); if (!name) return -ENOSPC; the error is not actually "No space left on device", but "Out of memory". It is semantically correct to return -ENOMEM in all failed kstrndup() and kzalloc() cases in this driver, as it is not a problem with disk space, but with kernel memory allocator failing allocation. The semantically correct should be: name = kstrndup(buf, count, GFP_KERNEL); if (!name) return -ENOMEM; Cc: Dan Carpenter Cc: Takashi Iwai Cc: Kees Cook Cc: "Luis R. Rodriguez" Cc: Scott Branden Cc: Hans de Goede Cc: Brian Norris Fixes: c92316bf8e948 ("test_firmware: add batched firmware tests") Fixes: 0a8adf584759c ("test: add firmware_class loader test") Fixes: 548193cba2a7d ("test_firmware: add support for firmware_request_platform") Fixes: eb910947c82f9 ("test: firmware_class: add asynchronous request trigger") Fixes: 061132d2b9c95 ("test_firmware: add test custom fallback trigger") Fixes: 7feebfa487b92 ("test_firmware: add support for request_firmware_into_buf") Signed-off-by: Mirsad Goran Todorovac Reviewed-by: Dan Carpenter Message-ID: <20230606070808.9300-1-mirsad.todorovac@alu.unizg.hr> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin --- lib/test_firmware.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index ed0455a9ded8..25dc9eb6c902 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -183,7 +183,7 @@ static int __kstrncpy(char **dst, const char *name, size_t count, gfp_t gfp) { *dst = kstrndup(name, count, gfp); if (!*dst) - return -ENOSPC; + return -ENOMEM; return count; } @@ -606,7 +606,7 @@ static ssize_t trigger_request_store(struct device *dev, name = kstrndup(buf, count, GFP_KERNEL); if (!name) - return -ENOSPC; + return -ENOMEM; pr_info("loading '%s'\n", name); @@ -654,7 +654,7 @@ static ssize_t trigger_request_platform_store(struct device *dev, name = kstrndup(buf, count, GFP_KERNEL); if (!name) - return -ENOSPC; + return -ENOMEM; pr_info("inserting test platform fw '%s'\n", name); efi_embedded_fw.name = name; @@ -707,7 +707,7 @@ static ssize_t trigger_async_request_store(struct device *dev, name = kstrndup(buf, count, GFP_KERNEL); if (!name) - return -ENOSPC; + return -ENOMEM; pr_info("loading '%s'\n", name); @@ -752,7 +752,7 @@ static ssize_t trigger_custom_fallback_store(struct device *dev, name = kstrndup(buf, count, GFP_KERNEL); if (!name) - return -ENOSPC; + return -ENOMEM; pr_info("loading '%s' using custom fallback mechanism\n", name); @@ -803,7 +803,7 @@ static int test_fw_run_batch_request(void *data) test_buf = kzalloc(TEST_FIRMWARE_BUF_SIZE, GFP_KERNEL); if (!test_buf) - return -ENOSPC; + return -ENOMEM; if (test_fw_config->partial) req->rc = request_partial_firmware_into_buf From 30ead8b9bf0d6fa9e760e8c1c6467fac4376d165 Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Fri, 9 Jun 2023 11:28:03 +0200 Subject: [PATCH 3984/4345] mfd: stmfx: Fix error path in stmfx_chip_init [ Upstream commit f592cf624531286f8b52e40dcfc157a5a7fb115c ] In error path, disable vdd regulator if it exists, but don't overload ret. Because if regulator_disable() is successful, stmfx_chip_init will exit successfully while chip init failed. Fixes: 06252ade9156 ("mfd: Add ST Multi-Function eXpander (STMFX) core driver") Signed-off-by: Amelie Delaunay Link: https://lore.kernel.org/r/20230609092804.793100-1-amelie.delaunay@foss.st.com Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/stmfx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mfd/stmfx.c b/drivers/mfd/stmfx.c index 988e2ba6dd0f..41e74b5dd990 100644 --- a/drivers/mfd/stmfx.c +++ b/drivers/mfd/stmfx.c @@ -387,7 +387,7 @@ static int stmfx_chip_init(struct i2c_client *client) err: if (stmfx->vdd) - return regulator_disable(stmfx->vdd); + regulator_disable(stmfx->vdd); return ret; } From c5e2f6f2bb66a53e9f7283a5c5f2cc0a6ed7b3e9 Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Fri, 9 Jun 2023 11:28:04 +0200 Subject: [PATCH 3985/4345] mfd: stmfx: Nullify stmfx->vdd in case of error [ Upstream commit 7c81582c0bccb4757186176f0ee12834597066ad ] Nullify stmfx->vdd in case devm_regulator_get_optional() returns an error. And simplify code by returning an error only if return code is not -ENODEV, which means there is no vdd regulator and it is not an issue. Fixes: d75846ed08e6 ("mfd: stmfx: Fix dev_err_probe() call in stmfx_chip_init()") Signed-off-by: Amelie Delaunay Link: https://lore.kernel.org/r/20230609092804.793100-2-amelie.delaunay@foss.st.com Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/stmfx.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/mfd/stmfx.c b/drivers/mfd/stmfx.c index 41e74b5dd990..b45d7b0b842c 100644 --- a/drivers/mfd/stmfx.c +++ b/drivers/mfd/stmfx.c @@ -330,9 +330,8 @@ static int stmfx_chip_init(struct i2c_client *client) stmfx->vdd = devm_regulator_get_optional(&client->dev, "vdd"); ret = PTR_ERR_OR_ZERO(stmfx->vdd); if (ret) { - if (ret == -ENODEV) - stmfx->vdd = NULL; - else + stmfx->vdd = NULL; + if (ret != -ENODEV) return dev_err_probe(&client->dev, ret, "Failed to get VDD regulator\n"); } From 724448d6021d44a7aebaaf748dbe96104ac828c3 Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Wed, 10 May 2023 17:42:58 +0200 Subject: [PATCH 3986/4345] KVM: s390: vsie: fix the length of APCB bitmap [ Upstream commit 246be7d2720ea9a795b576067ecc5e5c7a1e7848 ] bit_and() uses the count of bits as the woking length. Fix the previous implementation and effectively use the right bitmap size. Fixes: 19fd83a64718 ("KVM: s390: vsie: allow CRYCB FORMAT-1") Fixes: 56019f9aca22 ("KVM: s390: vsie: Allow CRYCB FORMAT-2") Signed-off-by: Pierre Morel Reviewed-by: Janosch Frank Link: https://lore.kernel.org/kvm/20230511094719.9691-1-pmorel@linux.ibm.com/ Signed-off-by: Janosch Frank Signed-off-by: Sasha Levin --- arch/s390/kvm/vsie.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index ff58decfef5e..192eacc8fbb7 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -168,7 +168,8 @@ static int setup_apcb00(struct kvm_vcpu *vcpu, unsigned long *apcb_s, sizeof(struct kvm_s390_apcb0))) return -EFAULT; - bitmap_and(apcb_s, apcb_s, apcb_h, sizeof(struct kvm_s390_apcb0)); + bitmap_and(apcb_s, apcb_s, apcb_h, + BITS_PER_BYTE * sizeof(struct kvm_s390_apcb0)); return 0; } @@ -190,7 +191,8 @@ static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s, sizeof(struct kvm_s390_apcb1))) return -EFAULT; - bitmap_and(apcb_s, apcb_s, apcb_h, sizeof(struct kvm_s390_apcb1)); + bitmap_and(apcb_s, apcb_s, apcb_h, + BITS_PER_BYTE * sizeof(struct kvm_s390_apcb1)); return 0; } From 442e1a98bd0220d1e17ec0f37052e636e2222d7f Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 17 Jun 2023 12:43:16 +0200 Subject: [PATCH 3987/4345] mfd: stmpe: Only disable the regulators if they are enabled [ Upstream commit 104d32bd81f620bb9f67fbf7d1159c414e89f05f ] In stmpe_probe(), if some regulator_enable() calls fail, probing continues and there is only a dev_warn(). So, if stmpe_probe() is called the regulator may not be enabled. It is cleaner to test it before calling regulator_disable() in the remove function. Fixes: 9c9e321455fb ("mfd: stmpe: add optional regulators") Signed-off-by: Christophe JAILLET Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/8de3aaf297931d655b9ad6aed548f4de8b85425a.1686998575.git.christophe.jaillet@wanadoo.fr Signed-off-by: Lee Jones Signed-off-by: Sasha Levin --- drivers/mfd/stmpe.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c index 508349399f8a..7f758fb60c1f 100644 --- a/drivers/mfd/stmpe.c +++ b/drivers/mfd/stmpe.c @@ -1494,9 +1494,9 @@ int stmpe_probe(struct stmpe_client_info *ci, enum stmpe_partnum partnum) int stmpe_remove(struct stmpe *stmpe) { - if (!IS_ERR(stmpe->vio)) + if (!IS_ERR(stmpe->vio) && regulator_is_enabled(stmpe->vio)) regulator_disable(stmpe->vio); - if (!IS_ERR(stmpe->vcc)) + if (!IS_ERR(stmpe->vcc) && regulator_is_enabled(stmpe->vcc)) regulator_disable(stmpe->vcc); __stmpe_disable(stmpe, STMPE_BLOCK_ADC); From e4845cdea71e280de71946577e7a47ba48dc84af Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Wed, 31 May 2023 10:39:50 +0300 Subject: [PATCH 3988/4345] phy: tegra: xusb: check return value of devm_kzalloc() [ Upstream commit 44faada0f38fc333d392af04c343b0e23f8f5d81 ] devm_kzalloc() returns a pointer to dynamically allocated memory. Pointer could be NULL in case allocation fails. Check pointer validity. Identified with coccinelle (kmerr.cocci script). Fixes: f67213cee2b3 ("phy: tegra: xusb: Add usb-role-switch support") Signed-off-by: Claudiu Beznea Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20230531073950.145339-1-claudiu.beznea@microchip.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/tegra/xusb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index f93be3c4a4a6..8f11b293c48d 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -663,6 +663,9 @@ static int tegra_xusb_setup_usb_role_switch(struct tegra_xusb_port *port) port->dev.driver = devm_kzalloc(&port->dev, sizeof(struct device_driver), GFP_KERNEL); + if (!port->dev.driver) + return -ENOMEM; + port->dev.driver->owner = THIS_MODULE; port->usb_role_sw = usb_role_switch_register(&port->dev, From 8a0413be8a1e352d15b8634e0551c3111a4f919f Mon Sep 17 00:00:00 2001 From: Fancy Fang Date: Fri, 5 May 2023 14:58:39 +0800 Subject: [PATCH 3989/4345] pwm: imx-tpm: force 'real_period' to be zero in suspend MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 661dfb7f46298e53f6c3deaa772fa527aae86193 ] During suspend, all the tpm registers will lose values. So the 'real_period' value of struct 'imx_tpm_pwm_chip' should be forced to be zero to force the period update code can be executed after system resume back. Signed-off-by: Fancy Fang Signed-off-by: Clark Wang Acked-by: Uwe Kleine-König Fixes: 738a1cfec2ed ("pwm: Add i.MX TPM PWM driver support") Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/pwm-imx-tpm.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/pwm/pwm-imx-tpm.c b/drivers/pwm/pwm-imx-tpm.c index fcdf6befb838..871527b78aa4 100644 --- a/drivers/pwm/pwm-imx-tpm.c +++ b/drivers/pwm/pwm-imx-tpm.c @@ -403,6 +403,13 @@ static int __maybe_unused pwm_imx_tpm_suspend(struct device *dev) if (tpm->enable_count > 0) return -EBUSY; + /* + * Force 'real_period' to be zero to force period update code + * can be executed after system resume back, since suspend causes + * the period related registers to become their reset values. + */ + tpm->real_period = 0; + clk_disable_unprepare(tpm->clk); return 0; From aa70e5dd72683ea4acc66dfd4ae0e554930d637c Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 12 May 2023 18:47:36 +0200 Subject: [PATCH 3990/4345] pwm: sysfs: Do not apply state to already disabled PWMs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 38ba83598633373f47951384cfc389181c8d1bed ] If the PWM is exported but not enabled, do not call pwm_class_apply_state(). First of all, in this case, period may still be unconfigured and this would make pwm_class_apply_state() return -EINVAL, and then suspend would fail. Second, it makes little sense to apply state onto PWM that is not enabled before suspend. Failing case: " $ echo 1 > /sys/class/pwm/pwmchip4/export $ echo mem > /sys/power/state ... pwm pwmchip4: PM: dpm_run_callback(): pwm_class_suspend+0x1/0xa8 returns -22 pwm pwmchip4: PM: failed to suspend: error -22 PM: Some devices failed to suspend, or early wake event detected " Working case: " $ echo 1 > /sys/class/pwm/pwmchip4/export $ echo 100 > /sys/class/pwm/pwmchip4/pwm1/period $ echo 10 > /sys/class/pwm/pwmchip4/pwm1/duty_cycle $ echo mem > /sys/power/state ... " Do not call pwm_class_apply_state() in case the PWM is disabled to fix this issue. Fixes: 7fd4edc57bbae ("pwm: sysfs: Add suspend/resume support") Signed-off-by: Marek Vasut Fixes: ef2bf4997f7d ("pwm: Improve args checking in pwm_apply_state()") Reviewed-by: Brian Norris Reviewed-by: Uwe Kleine-König Signed-off-by: Thierry Reding Signed-off-by: Sasha Levin --- drivers/pwm/sysfs.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c index 9903c3a7eced..b8417a8d2ef9 100644 --- a/drivers/pwm/sysfs.c +++ b/drivers/pwm/sysfs.c @@ -424,6 +424,13 @@ static int pwm_class_resume_npwm(struct device *parent, unsigned int npwm) if (!export) continue; + /* If pwmchip was not enabled before suspend, do nothing. */ + if (!export->suspend.enabled) { + /* release lock taken in pwm_class_get_state */ + mutex_unlock(&export->lock); + continue; + } + state.enabled = export->suspend.enabled; ret = pwm_class_apply_state(export, pwm, &state); if (ret < 0) @@ -448,7 +455,17 @@ static int __maybe_unused pwm_class_suspend(struct device *parent) if (!export) continue; + /* + * If pwmchip was not enabled before suspend, save + * state for resume time and do nothing else. + */ export->suspend = state; + if (!state.enabled) { + /* release lock taken in pwm_class_get_state */ + mutex_unlock(&export->lock); + continue; + } + state.enabled = false; ret = pwm_class_apply_state(export, pwm, &state); if (ret < 0) { From f733a7bfe8f8aec45b9442c54f1ab293fc815d37 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 8 Jun 2023 21:11:42 +0200 Subject: [PATCH 3991/4345] rtc: st-lpc: Release some resources in st_rtc_probe() in case of error [ Upstream commit 06c6e1b01d9261f03629cefd1f3553503291e6cf ] If an error occurs after clk_get(), the corresponding resources should be released. Use devm_clk_get() to fix it. Fixes: b5b2bdfc2893 ("rtc: st: Add new driver for ST's LPC RTC") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/866af6adbc7454a7b4505eb6c28fbdc86ccff39e.1686251455.git.christophe.jaillet@wanadoo.fr Signed-off-by: Alexandre Belloni Signed-off-by: Sasha Levin --- drivers/rtc/rtc-st-lpc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-st-lpc.c b/drivers/rtc/rtc-st-lpc.c index 7d53f7e2febc..c4ea3f3f0884 100644 --- a/drivers/rtc/rtc-st-lpc.c +++ b/drivers/rtc/rtc-st-lpc.c @@ -228,7 +228,7 @@ static int st_rtc_probe(struct platform_device *pdev) enable_irq_wake(rtc->irq); disable_irq(rtc->irq); - rtc->clk = clk_get(&pdev->dev, NULL); + rtc->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(rtc->clk)) { dev_err(&pdev->dev, "Unable to request clock\n"); return PTR_ERR(rtc->clk); From 620993d5ee5bc1833d7995d658c9ad63527bef4b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 8 Jun 2023 04:54:35 +0200 Subject: [PATCH 3992/4345] media: cec: i2c: ch7322: also select REGMAP [ Upstream commit 29f96ac23648b2259f42d40703c47dd18fd172ca ] Selecting only REGMAP_I2C can leave REGMAP unset, causing build errors, so also select REGMAP to prevent the build errors. ../drivers/media/cec/i2c/ch7322.c:158:21: error: variable 'ch7322_regmap' has initializer but incomplete type 158 | static const struct regmap_config ch7322_regmap = { ../drivers/media/cec/i2c/ch7322.c:159:10: error: 'const struct regmap_config' has no member named 'reg_bits' 159 | .reg_bits = 8, ../drivers/media/cec/i2c/ch7322.c:159:21: warning: excess elements in struct initializer 159 | .reg_bits = 8, ../drivers/media/cec/i2c/ch7322.c:160:10: error: 'const struct regmap_config' has no member named 'val_bits' 160 | .val_bits = 8, ../drivers/media/cec/i2c/ch7322.c:160:21: warning: excess elements in struct initializer 160 | .val_bits = 8, ../drivers/media/cec/i2c/ch7322.c:161:10: error: 'const struct regmap_config' has no member named 'max_register' 161 | .max_register = 0x7f, ../drivers/media/cec/i2c/ch7322.c:161:25: warning: excess elements in struct initializer 161 | .max_register = 0x7f, ../drivers/media/cec/i2c/ch7322.c:162:10: error: 'const struct regmap_config' has no member named 'disable_locking' 162 | .disable_locking = true, ../drivers/media/cec/i2c/ch7322.c:162:28: warning: excess elements in struct initializer 162 | .disable_locking = true, ../drivers/media/cec/i2c/ch7322.c: In function 'ch7322_probe': ../drivers/media/cec/i2c/ch7322.c:468:26: error: implicit declaration of function 'devm_regmap_init_i2c' [-Werror=implicit-function-declaration] 468 | ch7322->regmap = devm_regmap_init_i2c(client, &ch7322_regmap); ../drivers/media/cec/i2c/ch7322.c:468:24: warning: assignment to 'struct regmap *' from 'int' makes pointer from integer without a cast [-Wint-conversion] 468 | ch7322->regmap = devm_regmap_init_i2c(client, &ch7322_regmap); ../drivers/media/cec/i2c/ch7322.c: At top level: ../drivers/media/cec/i2c/ch7322.c:158:35: error: storage size of 'ch7322_regmap' isn't known 158 | static const struct regmap_config ch7322_regmap = { Link: https://lore.kernel.org/linux-media/20230608025435.29249-1-rdunlap@infradead.org Fixes: 21b9a47e0ec7 ("media: cec: i2c: ch7322: Add ch7322 CEC controller driver") Signed-off-by: Randy Dunlap Cc: Jeff Chase Cc: Hans Verkuil Cc: Joe Tessler Cc: Arnd Bergmann Cc: Mark Brown Cc: Masahiro Yamada Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Sasha Levin --- drivers/media/cec/i2c/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/cec/i2c/Kconfig b/drivers/media/cec/i2c/Kconfig index 70432a1d6918..d912d143fb31 100644 --- a/drivers/media/cec/i2c/Kconfig +++ b/drivers/media/cec/i2c/Kconfig @@ -5,6 +5,7 @@ config CEC_CH7322 tristate "Chrontel CH7322 CEC controller" depends on I2C + select REGMAP select REGMAP_I2C select CEC_CORE help From 6d2243ab783bf79d1d674ff0ca26229233c56508 Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Tue, 27 Jun 2023 12:03:40 +0000 Subject: [PATCH 3993/4345] sctp: fix potential deadlock on &net->sctp.addr_wq_lock [ Upstream commit 6feb37b3b06e9049e20dcf7e23998f92c9c5be9a ] As &net->sctp.addr_wq_lock is also acquired by the timer sctp_addr_wq_timeout_handler() in protocal.c, the same lock acquisition at sctp_auto_asconf_init() seems should disable irq since it is called from sctp_accept() under process context. Possible deadlock scenario: sctp_accept() -> sctp_sock_migrate() -> sctp_auto_asconf_init() -> spin_lock(&net->sctp.addr_wq_lock) -> sctp_addr_wq_timeout_handler() -> spin_lock_bh(&net->sctp.addr_wq_lock); (deadlock here) This flaw was found using an experimental static analysis tool we are developing for irq-related deadlock. The tentative patch fix the potential deadlock by spin_lock_bh(). Signed-off-by: Chengfeng Ye Fixes: 34e5b0118685 ("sctp: delay auto_asconf init until binding the first addr") Acked-by: Xin Long Link: https://lore.kernel.org/r/20230627120340.19432-1-dg573847474@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sctp/socket.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 4a7f811abae4..534364bb871a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -362,9 +362,9 @@ static void sctp_auto_asconf_init(struct sctp_sock *sp) struct net *net = sock_net(&sp->inet.sk); if (net->sctp.default_auto_asconf) { - spin_lock(&net->sctp.addr_wq_lock); + spin_lock_bh(&net->sctp.addr_wq_lock); list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist); - spin_unlock(&net->sctp.addr_wq_lock); + spin_unlock_bh(&net->sctp.addr_wq_lock); sp->do_auto_asconf = 1; } } From c377451012cec94f01b6c698409fec865e55dd3f Mon Sep 17 00:00:00 2001 From: Tobias Heider Date: Wed, 28 Jun 2023 02:13:32 +0200 Subject: [PATCH 3994/4345] Add MODULE_FIRMWARE() for FIRMWARE_TG357766. [ Upstream commit 046f753da6143ee16452966915087ec8b0de3c70 ] Fixes a bug where on the M1 mac mini initramfs-tools fails to include the necessary firmware into the initrd. Fixes: c4dab50697ff ("tg3: Download 57766 EEE service patch firmware") Signed-off-by: Tobias Heider Reviewed-by: Michael Chan Link: https://lore.kernel.org/r/ZJt7LKzjdz8+dClx@tobhe.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/tg3.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 613ca6124e3c..d14f37be1eb3 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -224,6 +224,7 @@ MODULE_AUTHOR("David S. Miller (davem@redhat.com) and Jeff Garzik (jgarzik@pobox MODULE_DESCRIPTION("Broadcom Tigon3 ethernet driver"); MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_TG3); +MODULE_FIRMWARE(FIRMWARE_TG357766); MODULE_FIRMWARE(FIRMWARE_TG3TSO); MODULE_FIRMWARE(FIRMWARE_TG3TSO5); From 1f3643f9cfca51c2211fd82cf7c403fb84c27095 Mon Sep 17 00:00:00 2001 From: Pawel Dembicki Date: Wed, 28 Jun 2023 21:43:27 +0200 Subject: [PATCH 3995/4345] net: dsa: vsc73xx: fix MTU configuration [ Upstream commit 3cf62c8177adb0db9e15c8b898c44f997acf3ebf ] Switch in MAXLEN register stores the maximum size of a data frame. The MTU size is 18 bytes smaller than the frame size. The current settings are causing problems with packet forwarding. This patch fixes the MTU settings to proper values. Fixes: fb77ffc6ec86 ("net: dsa: vsc73xx: make the MTU configurable") Reviewed-by: Linus Walleij Signed-off-by: Pawel Dembicki Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230628194327.1765644-1-paweldembicki@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/dsa/vitesse-vsc73xx-core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index 19ce4aa0973b..80eadf509c0a 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -1025,17 +1025,17 @@ static int vsc73xx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) struct vsc73xx *vsc = ds->priv; return vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, - VSC73XX_MAXLEN, new_mtu); + VSC73XX_MAXLEN, new_mtu + ETH_HLEN + ETH_FCS_LEN); } /* According to application not "VSC7398 Jumbo Frames" setting - * up the MTU to 9.6 KB does not affect the performance on standard + * up the frame size to 9.6 KB does not affect the performance on standard * frames. It is clear from the application note that * "9.6 kilobytes" == 9600 bytes. */ static int vsc73xx_get_max_mtu(struct dsa_switch *ds, int port) { - return 9600; + return 9600 - ETH_HLEN - ETH_FCS_LEN; } static const struct dsa_switch_ops vsc73xx_ds_ops = { From 32b9c8f7892c19f7f5c9fed5fb410b9fd5990bb6 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Thu, 29 Jun 2023 15:43:05 +0200 Subject: [PATCH 3996/4345] spi: bcm-qspi: return error if neither hif_mspi nor mspi is available [ Upstream commit 7c1f23ad34fcdace50275a6aa1e1969b41c6233f ] If neither a "hif_mspi" nor "mspi" resource is present, the driver will just early exit in probe but still return success. Apart from not doing anything meaningful, this would then also lead to a null pointer access on removal, as platform_get_drvdata() would return NULL, which it would then try to dereference when trying to unregister the spi master. Fix this by unconditionally calling devm_ioremap_resource(), as it can handle a NULL res and will then return a viable ERR_PTR() if we get one. The "return 0;" was previously a "goto qspi_resource_err;" where then ret was returned, but since ret was still initialized to 0 at this place this was a valid conversion in 63c5395bb7a9 ("spi: bcm-qspi: Fix use-after-free on unbind"). The issue was not introduced by this commit, only made more obvious. Fixes: fa236a7ef240 ("spi: bcm-qspi: Add Broadcom MSPI driver") Signed-off-by: Jonas Gorski Reviewed-by: Kamal Dasu Link: https://lore.kernel.org/r/20230629134306.95823-1-jonas.gorski@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-bcm-qspi.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 766b00350e39..2c734ea0784b 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1369,13 +1369,9 @@ int bcm_qspi_probe(struct platform_device *pdev, res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mspi"); - if (res) { - qspi->base[MSPI] = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->base[MSPI])) - return PTR_ERR(qspi->base[MSPI]); - } else { - return 0; - } + qspi->base[MSPI] = devm_ioremap_resource(dev, res); + if (IS_ERR(qspi->base[MSPI])) + return PTR_ERR(qspi->base[MSPI]); res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "bspi"); if (res) { From 358145cc379707d3b73d21cd8f3b34db953450c9 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Tue, 20 Jun 2023 20:00:22 -0500 Subject: [PATCH 3997/4345] mailbox: ti-msgmgr: Fill non-message tx data fields with 0x0 [ Upstream commit 1b712f18c461bd75f018033a15cf381e712806b5 ] Sec proxy/message manager data buffer is 60 bytes with the last of the registers indicating transmission completion. This however poses a bit of a challenge. The backing memory for sec_proxy / message manager is regular memory, and all sec proxy does is to trigger a burst of all 60 bytes of data over to the target thread backing ring accelerator. It doesn't do a memory scrub when it moves data out in the burst. When we transmit multiple messages, remnants of previous message is also transmitted which results in some random data being set in TISCI fields of messages that have been expanded forward. The entire concept of backward compatibility hinges on the fact that the unused message fields remain 0x0 allowing for 0x0 value to be specially considered when backward compatibility of message extension is done. So, instead of just writing the completion register, we continue to fill the message buffer up with 0x0 (note: for partial message involving completion, we already do this). This allows us to scale and introduce ABI changes back also work with other boot stages that may have left data in the internal memory. While at this, be consistent and explicit with the data_reg pointer increment. Fixes: aace66b170ce ("mailbox: Introduce TI message manager driver") Signed-off-by: Nishanth Menon Signed-off-by: Jassi Brar Signed-off-by: Sasha Levin --- drivers/mailbox/ti-msgmgr.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/mailbox/ti-msgmgr.c b/drivers/mailbox/ti-msgmgr.c index 0130628f4d9d..535fe73ce310 100644 --- a/drivers/mailbox/ti-msgmgr.c +++ b/drivers/mailbox/ti-msgmgr.c @@ -385,14 +385,20 @@ static int ti_msgmgr_send_data(struct mbox_chan *chan, void *data) /* Ensure all unused data is 0 */ data_trail &= 0xFFFFFFFF >> (8 * (sizeof(u32) - trail_bytes)); writel(data_trail, data_reg); - data_reg++; + data_reg += sizeof(u32); } + /* * 'data_reg' indicates next register to write. If we did not already * write on tx complete reg(last reg), we must do so for transmit + * In addition, we also need to make sure all intermediate data + * registers(if any required), are reset to 0 for TISCI backward + * compatibility to be maintained. */ - if (data_reg <= qinst->queue_buff_end) - writel(0, qinst->queue_buff_end); + while (data_reg <= qinst->queue_buff_end) { + writel(0, data_reg); + data_reg += sizeof(u32); + } return 0; } From 5ded9e8aa53e88f3aa81948c2622ba5e14aaef3d Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 29 Jun 2023 09:41:02 +0800 Subject: [PATCH 3998/4345] f2fs: fix error path handling in truncate_dnode() [ Upstream commit 0135c482fa97e2fd8245cb462784112a00ed1211 ] If truncate_node() fails in truncate_dnode(), it missed to call f2fs_put_page(), fix it. Fixes: 7735730d39d7 ("f2fs: fix to propagate error from __get_meta_page()") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Sasha Levin --- fs/f2fs/node.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index c63274d4b74b..02cb1c806c3e 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -884,8 +884,10 @@ static int truncate_dnode(struct dnode_of_data *dn) dn->ofs_in_node = 0; f2fs_truncate_data_blocks(dn); err = truncate_node(dn); - if (err) + if (err) { + f2fs_put_page(page, 1); return err; + } return 1; } From f970b05c9b76b820b2e87eea39f8b2050086f03a Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Fri, 30 Jun 2023 11:58:43 +0530 Subject: [PATCH 3999/4345] octeontx2-af: Fix mapping for NIX block from CGX connection [ Upstream commit 2e7bc57b976bb016c6569a54d95c1b8d88f9450a ] Firmware configures NIX block mapping for all MAC blocks. The current implementation reads the configuration and creates the mapping between RVU PF and NIX blocks. But this configuration is only valid for silicons that support multiple blocks. For all other silicons, all MAC blocks map to NIX0. This patch corrects the mapping by adding a check for the same. Fixes: c5a73b632b90 ("octeontx2-af: Map NIX block from CGX connection") Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Goutham Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeontx2/af/rvu.h | 11 +++++++++++ drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c | 2 +- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index fc6d785b98dd..ec9a291e866c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -20,6 +20,7 @@ #define PCI_DEVID_OCTEONTX2_RVU_AF 0xA065 /* Subsystem Device ID */ +#define PCI_SUBSYS_DEVID_98XX 0xB100 #define PCI_SUBSYS_DEVID_96XX 0xB200 /* PCI BAR nos */ @@ -403,6 +404,16 @@ static inline bool is_rvu_96xx_B0(struct rvu *rvu) (pdev->subsystem_device == PCI_SUBSYS_DEVID_96XX); } +static inline bool is_rvu_supports_nix1(struct rvu *rvu) +{ + struct pci_dev *pdev = rvu->pdev; + + if (pdev->subsystem_device == PCI_SUBSYS_DEVID_98XX) + return true; + + return false; +} + /* Function Prototypes * RVU */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 6c6b411e78fd..83743e15326d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -84,7 +84,7 @@ static void rvu_map_cgx_nix_block(struct rvu *rvu, int pf, p2x = cgx_lmac_get_p2x(cgx_id, lmac_id); /* Firmware sets P2X_SELECT as either NIX0 or NIX1 */ pfvf->nix_blkaddr = BLKADDR_NIX0; - if (p2x == CMR_P2X_SEL_NIX1) + if (is_rvu_supports_nix1(rvu) && p2x == CMR_P2X_SEL_NIX1) pfvf->nix_blkaddr = BLKADDR_NIX1; } From 9a9d468fdcca6a75f7bdf405dff7a46f53647d64 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 30 Jun 2023 22:47:12 -0700 Subject: [PATCH 4000/4345] powerpc: allow PPC_EARLY_DEBUG_CPM only when SERIAL_CPM=y MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 39f49684036d24af800ff194c33c7b2653c591d7 ] In a randconfig with CONFIG_SERIAL_CPM=m and CONFIG_PPC_EARLY_DEBUG_CPM=y, there is a build error: ERROR: modpost: "udbg_putc" [drivers/tty/serial/cpm_uart/cpm_uart.ko] undefined! Prevent the build error by allowing PPC_EARLY_DEBUG_CPM only when SERIAL_CPM=y. Fixes: c374e00e17f1 ("[POWERPC] Add early debug console for CPM serial ports.") Signed-off-by: Randy Dunlap Reviewed-by: Pali Rohár Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20230701054714.30512-1-rdunlap@infradead.org Signed-off-by: Sasha Levin --- arch/powerpc/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 52abca88b5b2..e03fb9154420 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -234,7 +234,7 @@ config PPC_EARLY_DEBUG_40x config PPC_EARLY_DEBUG_CPM bool "Early serial debugging for Freescale CPM-based serial ports" - depends on SERIAL_CPM + depends on SERIAL_CPM=y help Select this to enable early debugging for Freescale chips using a CPM-based serial port. This assumes that the bootwrapper From 73f512bedfd47b5f3b515c6269ea650a55a6f579 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 30 Jun 2023 19:41:18 +0300 Subject: [PATCH 4001/4345] net: bridge: keep ports without IFF_UNICAST_FLT in BR_PROMISC mode [ Upstream commit 6ca3c005d0604e8d2b439366e3923ea58db99641 ] According to the synchronization rules for .ndo_get_stats() as seen in Documentation/networking/netdevices.rst, acquiring a plain spin_lock() should not be illegal, but the bridge driver implementation makes it so. After running these commands, I am being faced with the following lockdep splat: $ ip link add link swp0 name macsec0 type macsec encrypt on && ip link set swp0 up $ ip link add dev br0 type bridge vlan_filtering 1 && ip link set br0 up $ ip link set macsec0 master br0 && ip link set macsec0 up ======================================================== WARNING: possible irq lock inversion dependency detected 6.4.0-04295-g31b577b4bd4a #603 Not tainted -------------------------------------------------------- swapper/1/0 just changed the state of lock: ffff6bd348724cd8 (&br->lock){+.-.}-{3:3}, at: br_forward_delay_timer_expired+0x34/0x198 but this lock took another, SOFTIRQ-unsafe lock in the past: (&ocelot->stats_lock){+.+.}-{3:3} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Chain exists of: &br->lock --> &br->hash_lock --> &ocelot->stats_lock Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&ocelot->stats_lock); local_irq_disable(); lock(&br->lock); lock(&br->hash_lock); lock(&br->lock); *** DEADLOCK *** (details about the 3 locks skipped) swp0 is instantiated by drivers/net/dsa/ocelot/felix.c, and this only matters to the extent that its .ndo_get_stats64() method calls spin_lock(&ocelot->stats_lock). Documentation/locking/lockdep-design.rst says: | A lock is irq-safe means it was ever used in an irq context, while a lock | is irq-unsafe means it was ever acquired with irq enabled. (...) | Furthermore, the following usage based lock dependencies are not allowed | between any two lock-classes:: | | -> | -> Lockdep marks br->hash_lock as softirq-safe, because it is sometimes taken in softirq context (for example br_fdb_update() which runs in NET_RX softirq), and when it's not in softirq context it blocks softirqs by using spin_lock_bh(). Lockdep marks ocelot->stats_lock as softirq-unsafe, because it never blocks softirqs from running, and it is never taken from softirq context. So it can always be interrupted by softirqs. There is a call path through which a function that holds br->hash_lock: fdb_add_hw_addr() will call a function that acquires ocelot->stats_lock: ocelot_port_get_stats64(). This can be seen below: ocelot_port_get_stats64+0x3c/0x1e0 felix_get_stats64+0x20/0x38 dsa_slave_get_stats64+0x3c/0x60 dev_get_stats+0x74/0x2c8 rtnl_fill_stats+0x4c/0x150 rtnl_fill_ifinfo+0x5cc/0x7b8 rtmsg_ifinfo_build_skb+0xe4/0x150 rtmsg_ifinfo+0x5c/0xb0 __dev_notify_flags+0x58/0x200 __dev_set_promiscuity+0xa0/0x1f8 dev_set_promiscuity+0x30/0x70 macsec_dev_change_rx_flags+0x68/0x88 __dev_set_promiscuity+0x1a8/0x1f8 __dev_set_rx_mode+0x74/0xa8 dev_uc_add+0x74/0xa0 fdb_add_hw_addr+0x68/0xd8 fdb_add_local+0xc4/0x110 br_fdb_add_local+0x54/0x88 br_add_if+0x338/0x4a0 br_add_slave+0x20/0x38 do_setlink+0x3a4/0xcb8 rtnl_newlink+0x758/0x9d0 rtnetlink_rcv_msg+0x2f0/0x550 netlink_rcv_skb+0x128/0x148 rtnetlink_rcv+0x24/0x38 the plain English explanation for it is: The macsec0 bridge port is created without p->flags & BR_PROMISC, because it is what br_manage_promisc() decides for a VLAN filtering bridge with a single auto port. As part of the br_add_if() procedure, br_fdb_add_local() is called for the MAC address of the device, and this results in a call to dev_uc_add() for macsec0 while the softirq-safe br->hash_lock is taken. Because macsec0 does not have IFF_UNICAST_FLT, dev_uc_add() ends up calling __dev_set_promiscuity() for macsec0, which is propagated by its implementation, macsec_dev_change_rx_flags(), to the lower device: swp0. This triggers the call path: dev_set_promiscuity(swp0) -> rtmsg_ifinfo() -> dev_get_stats() -> ocelot_port_get_stats64() with a calling context that lockdep doesn't like (br->hash_lock held). Normally we don't see this, because even though many drivers that can be bridge ports don't support IFF_UNICAST_FLT, we need a driver that (a) doesn't support IFF_UNICAST_FLT, *and* (b) it forwards the IFF_PROMISC flag to another driver, and (c) *that* driver implements ndo_get_stats64() using a softirq-unsafe spinlock. Condition (b) is necessary because the first __dev_set_rx_mode() calls __dev_set_promiscuity() with "bool notify=false", and thus, the rtmsg_ifinfo() code path won't be entered. The same criteria also hold true for DSA switches which don't report IFF_UNICAST_FLT. When the DSA master uses a spin_lock() in its ndo_get_stats64() method, the same lockdep splat can be seen. I think the deadlock possibility is real, even though I didn't reproduce it, and I'm thinking of the following situation to support that claim: fdb_add_hw_addr() runs on a CPU A, in a context with softirqs locally disabled and br->hash_lock held, and may end up attempting to acquire ocelot->stats_lock. In parallel, ocelot->stats_lock is currently held by a thread B (say, ocelot_check_stats_work()), which is interrupted while holding it by a softirq which attempts to lock br->hash_lock. Thread B cannot make progress because br->hash_lock is held by A. Whereas thread A cannot make progress because ocelot->stats_lock is held by B. When taking the issue at face value, the bridge can avoid that problem by simply making the ports promiscuous from a code path with a saner calling context (br->hash_lock not held). A bridge port without IFF_UNICAST_FLT is going to become promiscuous as soon as we call dev_uc_add() on it (which we do unconditionally), so why not be preemptive and make it promiscuous right from the beginning, so as to not be taken by surprise. With this, we've broken the links between code that holds br->hash_lock or br->lock and code that calls into the ndo_change_rx_flags() or ndo_get_stats64() ops of the bridge port. Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.") Signed-off-by: Vladimir Oltean Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/bridge/br_if.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 1d87bf51f384..e35488fde9c8 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -157,8 +157,9 @@ void br_manage_promisc(struct net_bridge *br) * This lets us disable promiscuous mode and write * this config to hw. */ - if (br->auto_cnt == 0 || - (br->auto_cnt == 1 && br_auto_port(p))) + if ((p->dev->priv_flags & IFF_UNICAST_FLT) && + (br->auto_cnt == 0 || + (br->auto_cnt == 1 && br_auto_port(p)))) br_port_clear_promisc(p); else br_port_set_promisc(p); From b785ba0acc82f894c05ec5ceb0c1c4720972aa8e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 29 Jun 2023 16:41:50 +0000 Subject: [PATCH 4002/4345] tcp: annotate data races in __tcp_oow_rate_limited() [ Upstream commit 998127cdb4699b9d470a9348ffe9f1154346be5f ] request sockets are lockless, __tcp_oow_rate_limited() could be called on the same object from different cpus. This is harmless. Add READ_ONCE()/WRITE_ONCE() annotations to avoid a KCSAN report. Fixes: 4ce7e93cb3fe ("tcp: rate limit ACK sent by SYN_RECV request sockets") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/tcp_input.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b98b7920c402..d6dfbb88dcf5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3560,8 +3560,11 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, u32 *last_oow_ack_time) { - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time); + /* Paired with the WRITE_ONCE() in this function. */ + u32 val = READ_ONCE(*last_oow_ack_time); + + if (val) { + s32 elapsed = (s32)(tcp_jiffies32 - val); if (0 <= elapsed && elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) { @@ -3570,7 +3573,10 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, } } - *last_oow_ack_time = tcp_jiffies32; + /* Paired with the prior READ_ONCE() and with itself, + * as we might be lockless. + */ + WRITE_ONCE(*last_oow_ack_time, tcp_jiffies32); return false; /* not rate-limited: go ahead, send dupack now! */ } From 2434a6715f599958f233e76e8b37a5b9dd5ba439 Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Mon, 3 Jul 2023 19:53:29 +0200 Subject: [PATCH 4003/4345] xsk: Honor SO_BINDTODEVICE on bind [ Upstream commit f7306acec9aae9893d15e745c8791124d42ab10a ] Initial creation of an AF_XDP socket requires CAP_NET_RAW capability. A privileged process might create the socket and pass it to a non-privileged process for later use. However, that process will be able to bind the socket to any network interface. Even though it will not be able to receive any traffic without modification of the BPF map, the situation is not ideal. Sockets already have a mechanism that can be used to restrict what interface they can be attached to. That is SO_BINDTODEVICE. To change the SO_BINDTODEVICE binding the process will need CAP_NET_RAW. Make xsk_bind() honor the SO_BINDTODEVICE in order to allow safer workflow when non-privileged process is using AF_XDP. The intended workflow is following: 1. First process creates a bare socket with socket(AF_XDP, ...). 2. First process loads the XSK program to the interface. 3. First process adds the socket fd to a BPF map. 4. First process ties socket fd to a particular interface using SO_BINDTODEVICE. 5. First process sends socket fd to a second process. 6. Second process allocates UMEM. 7. Second process binds socket to the interface with bind(...). 8. Second process sends/receives the traffic. All the steps above are possible today if the first process is privileged and the second one has sufficient RLIMIT_MEMLOCK and no capabilities. However, the second process will be able to bind the socket to any interface it wants on step 7 and send traffic from it. With the proposed change, the second process will be able to bind the socket only to a specific interface chosen by the first process at step 4. Fixes: 965a99098443 ("xsk: add support for bind for Rx") Signed-off-by: Ilya Maximets Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Acked-by: John Fastabend Acked-by: Jason Wang Link: https://lore.kernel.org/bpf/20230703175329.3259672-1-i.maximets@ovn.org Signed-off-by: Sasha Levin --- Documentation/networking/af_xdp.rst | 9 +++++++++ net/xdp/xsk.c | 5 +++++ 2 files changed, 14 insertions(+) diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst index 2ccc5644cc98..70623cb135d3 100644 --- a/Documentation/networking/af_xdp.rst +++ b/Documentation/networking/af_xdp.rst @@ -433,6 +433,15 @@ start N bytes into the buffer leaving the first N bytes for the application to use. The final option is the flags field, but it will be dealt with in separate sections for each UMEM flag. +SO_BINDTODEVICE setsockopt +-------------------------- + +This is a generic SOL_SOCKET option that can be used to tie AF_XDP +socket to a particular network interface. It is useful when a socket +is created by a privileged process and passed to a non-privileged one. +Once the option is set, kernel will refuse attempts to bind that socket +to a different interface. Updating the value requires CAP_NET_RAW. + XDP_STATISTICS getsockopt ------------------------- diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 691841dc6d33..d04f91f4d09d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -667,6 +667,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev; + int bound_dev_if; u32 flags, qid; int err = 0; @@ -680,6 +681,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) XDP_USE_NEED_WAKEUP)) return -EINVAL; + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + if (bound_dev_if && bound_dev_if != sxdp->sxdp_ifindex) + return -EINVAL; + rtnl_lock(); mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { From 0b08ff091f3131a6a35525173d857c5158c08cdc Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Mon, 3 Jul 2023 19:08:42 +0800 Subject: [PATCH 4004/4345] net/sched: act_pedit: Add size check for TCA_PEDIT_PARMS_EX [ Upstream commit 30c45b5361d39b4b793780ffac5538090b9e2eb1 ] The attribute TCA_PEDIT_PARMS_EX is not be included in pedit_policy and one malicious user could fake a TCA_PEDIT_PARMS_EX whose length is smaller than the intended sizeof(struct tc_pedit). Hence, the dereference in tcf_pedit_init() could access dirty heap data. static int tcf_pedit_init(...) { // ... pattr = tb[TCA_PEDIT_PARMS]; // TCA_PEDIT_PARMS is included if (!pattr) pattr = tb[TCA_PEDIT_PARMS_EX]; // but this is not // ... parm = nla_data(pattr); index = parm->index; // parm is able to be smaller than 4 bytes // and this dereference gets dirty skb_buff // data created in netlink_sendmsg } This commit adds TCA_PEDIT_PARMS_EX length in pedit_policy which avoid the above case, just like the TCA_PEDIT_PARMS. Fixes: 71d0ed7079df ("net/act_pedit: Support using offset relative to the conventional network headers") Signed-off-by: Lin Ma Reviewed-by: Pedro Tammela Link: https://lore.kernel.org/r/20230703110842.590282-1-linma@zju.edu.cn Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/act_pedit.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index db0d3bff19eb..a44101b2f441 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -26,6 +26,7 @@ static struct tc_action_ops act_pedit_ops; static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, + [TCA_PEDIT_PARMS_EX] = { .len = sizeof(struct tc_pedit) }, [TCA_PEDIT_KEYS_EX] = { .type = NLA_NESTED }, }; From 2758fb81bbc9ad01dab30dd051b7ed936de34cca Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Mon, 3 Jul 2023 19:14:46 +0200 Subject: [PATCH 4005/4345] pptp: Fix fib lookup calls. [ Upstream commit 84bef5b6037c15180ef88ac4216dc621d16df1a6 ] PPTP uses pppox sockets (struct pppox_sock). These sockets don't embed an inet_sock structure, so it's invalid to call inet_sk() on them. Therefore, the ip_route_output_ports() call in pptp_connect() has two problems: * The tos variable is set with RT_CONN_FLAGS(sk), which calls inet_sk() on the pppox socket. * ip_route_output_ports() tries to retrieve routing flags using inet_sk_flowi_flags(), which is also going to call inet_sk() on the pppox socket. While PPTP doesn't use inet sockets, it's actually really layered on top of IP and therefore needs a proper way to do fib lookups. So let's define pptp_route_output() to get a struct rtable from a pptp socket. Let's also replace the ip_route_output_ports() call of pptp_xmit() for consistency. In practice, this means that: * pptp_connect() sets ->flowi4_tos and ->flowi4_flags to zero instead of using bits of unrelated struct pppox_sock fields. * pptp_xmit() now respects ->sk_mark and ->sk_uid. * pptp_xmit() now calls the security_sk_classify_flow() security hook, thus allowing to set ->flowic_secid. * pptp_xmit() now passes the pppox socket to xfrm_lookup_route(). Found by code inspection. Fixes: 00959ade36ac ("PPTP: PPP over IPv4 (Point-to-Point Tunneling Protocol)") Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ppp/pptp.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index ee5058445d06..05a75b5a8b68 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -128,6 +129,23 @@ static void del_chan(struct pppox_sock *sock) spin_unlock(&chan_lock); } +static struct rtable *pptp_route_output(struct pppox_sock *po, + struct flowi4 *fl4) +{ + struct sock *sk = &po->sk; + struct net *net; + + net = sock_net(sk); + flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, 0, + RT_SCOPE_UNIVERSE, IPPROTO_GRE, 0, + po->proto.pptp.dst_addr.sin_addr.s_addr, + po->proto.pptp.src_addr.sin_addr.s_addr, + 0, 0, sock_net_uid(net, sk)); + security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); + + return ip_route_output_flow(net, fl4, sk); +} + static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) { struct sock *sk = (struct sock *) chan->private; @@ -151,11 +169,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) if (sk_pppox(po)->sk_state & PPPOX_DEAD) goto tx_error; - rt = ip_route_output_ports(net, &fl4, NULL, - opt->dst_addr.sin_addr.s_addr, - opt->src_addr.sin_addr.s_addr, - 0, 0, IPPROTO_GRE, - RT_TOS(0), sk->sk_bound_dev_if); + rt = pptp_route_output(po, &fl4); if (IS_ERR(rt)) goto tx_error; @@ -440,12 +454,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, po->chan.private = sk; po->chan.ops = &pptp_chan_ops; - rt = ip_route_output_ports(sock_net(sk), &fl4, sk, - opt->dst_addr.sin_addr.s_addr, - opt->src_addr.sin_addr.s_addr, - 0, 0, - IPPROTO_GRE, RT_CONN_FLAGS(sk), - sk->sk_bound_dev_if); + rt = pptp_route_output(po, &fl4); if (IS_ERR(rt)) { error = -EHOSTUNREACH; goto end; From 9f5548e4214d260ed0c9ec0394d7b4bae4015029 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 4 Jul 2023 01:05:44 +0300 Subject: [PATCH 4006/4345] net: dsa: tag_sja1105: fix MAC DA patching from meta frames [ Upstream commit 1dcf6efd5f0c1f4496b3ef7ec5a7db104a53b38c ] The SJA1105 manual says that at offset 4 into the meta frame payload we have "MAC destination byte 2" and at offset 5 we have "MAC destination byte 1". These are counted from the LSB, so byte 1 is h_dest[ETH_HLEN-2] aka h_dest[4] and byte 2 is h_dest[ETH_HLEN-3] aka h_dest[3]. The sja1105_meta_unpack() function decodes these the other way around, so a frame with MAC DA 01:80:c2:11:22:33 is received by the network stack as having 01:80:c2:22:11:33. Fixes: e53e18a6fe4d ("net: dsa: sja1105: Receive and decode meta frames") Signed-off-by: Vladimir Oltean Reviewed-by: Simon Horman Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/dsa/tag_sja1105.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 50496013cdb7..07876160edd2 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -48,8 +48,8 @@ static void sja1105_meta_unpack(const struct sk_buff *skb, * a unified unpacking command for both device series. */ packing(buf, &meta->tstamp, 31, 0, 4, UNPACK, 0); - packing(buf + 4, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0); - packing(buf + 5, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0); + packing(buf + 4, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0); + packing(buf + 5, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0); packing(buf + 6, &meta->source_port, 7, 0, 1, UNPACK, 0); packing(buf + 7, &meta->switch_id, 7, 0, 1, UNPACK, 0); } From 37750131d2a5a95d2b83e43dbfd8738c72c4eb59 Mon Sep 17 00:00:00 2001 From: Thorsten Winkler Date: Tue, 4 Jul 2023 16:41:21 +0200 Subject: [PATCH 4007/4345] s390/qeth: Fix vipa deletion [ Upstream commit 80de809bd35e2a8999edf9f5aaa2d8de18921f11 ] Change boolean parameter of function "qeth_l3_vipa_store" inside the "qeth_l3_dev_vipa_del4_store" function from "true" to "false" because "true" is used for adding a virtual ip address and "false" for deleting. Fixes: 2390166a6b45 ("s390/qeth: clean up L3 sysfs code") Reviewed-by: Alexandra Winter Reviewed-by: Wenjia Zhang Signed-off-by: Thorsten Winkler Signed-off-by: Alexandra Winter Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/s390/net/qeth_l3_sys.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index 997fbb7006a7..316f8622f3cc 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -652,7 +652,7 @@ static QETH_DEVICE_ATTR(vipa_add4, add4, 0644, static ssize_t qeth_l3_dev_vipa_del4_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - return qeth_l3_vipa_store(dev, buf, true, count, QETH_PROT_IPV4); + return qeth_l3_vipa_store(dev, buf, false, count, QETH_PROT_IPV4); } static QETH_DEVICE_ATTR(vipa_del4, del4, 0200, NULL, From d1c946552af299f4fa85bf7da15e328123771128 Mon Sep 17 00:00:00 2001 From: Artur Rojek Date: Sat, 27 May 2023 18:44:50 +0200 Subject: [PATCH 4008/4345] sh: dma: Fix DMA channel offset calculation [ Upstream commit e82e47584847129a20b8c9f4a1dcde09374fb0e0 ] Various SoCs of the SH3, SH4 and SH4A family, which use this driver, feature a differing number of DMA channels, which can be distributed between up to two DMAC modules. The existing implementation fails to correctly accommodate for all those variations, resulting in wrong channel offset calculations and leading to kernel panics. Rewrite dma_base_addr() in order to properly calculate channel offsets in a DMAC module. Fix dmaor_read_reg() and dmaor_write_reg(), so that the correct DMAC module base is selected for the DMAOR register. Fixes: 7f47c7189b3e8f19 ("sh: dma: More legacy cpu dma chainsawing.") Signed-off-by: Artur Rojek Reviewed-by: Geert Uytterhoeven Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230527164452.64797-2-contact@artur-rojek.eu Signed-off-by: John Paul Adrian Glaubitz Signed-off-by: Sasha Levin --- arch/sh/drivers/dma/dma-sh.c | 37 +++++++++++++++++++++++------------- 1 file changed, 24 insertions(+), 13 deletions(-) diff --git a/arch/sh/drivers/dma/dma-sh.c b/arch/sh/drivers/dma/dma-sh.c index 96c626c2cd0a..306fba1564e5 100644 --- a/arch/sh/drivers/dma/dma-sh.c +++ b/arch/sh/drivers/dma/dma-sh.c @@ -18,6 +18,18 @@ #include #include +/* + * Some of the SoCs feature two DMAC modules. In such a case, the channels are + * distributed equally among them. + */ +#ifdef SH_DMAC_BASE1 +#define SH_DMAC_NR_MD_CH (CONFIG_NR_ONCHIP_DMA_CHANNELS / 2) +#else +#define SH_DMAC_NR_MD_CH CONFIG_NR_ONCHIP_DMA_CHANNELS +#endif + +#define SH_DMAC_CH_SZ 0x10 + /* * Define the default configuration for dual address memory-memory transfer. * The 0x400 value represents auto-request, external->external. @@ -29,7 +41,7 @@ static unsigned long dma_find_base(unsigned int chan) unsigned long base = SH_DMAC_BASE0; #ifdef SH_DMAC_BASE1 - if (chan >= 6) + if (chan >= SH_DMAC_NR_MD_CH) base = SH_DMAC_BASE1; #endif @@ -40,13 +52,13 @@ static unsigned long dma_base_addr(unsigned int chan) { unsigned long base = dma_find_base(chan); - /* Normalize offset calculation */ - if (chan >= 9) - chan -= 6; - if (chan >= 4) - base += 0x10; + chan = (chan % SH_DMAC_NR_MD_CH) * SH_DMAC_CH_SZ; - return base + (chan * 0x10); + /* DMAOR is placed inside the channel register space. Step over it. */ + if (chan >= DMAOR) + base += SH_DMAC_CH_SZ; + + return base + chan; } #ifdef CONFIG_SH_DMA_IRQ_MULTI @@ -250,12 +262,11 @@ static int sh_dmac_get_dma_residue(struct dma_channel *chan) #define NR_DMAOR 1 #endif -/* - * DMAOR bases are broken out amongst channel groups. DMAOR0 manages - * channels 0 - 5, DMAOR1 6 - 11 (optional). - */ -#define dmaor_read_reg(n) __raw_readw(dma_find_base((n)*6)) -#define dmaor_write_reg(n, data) __raw_writew(data, dma_find_base(n)*6) +#define dmaor_read_reg(n) __raw_readw(dma_find_base((n) * \ + SH_DMAC_NR_MD_CH) + DMAOR) +#define dmaor_write_reg(n, data) __raw_writew(data, \ + dma_find_base((n) * \ + SH_DMAC_NR_MD_CH) + DMAOR) static inline int dmaor_reset(int no) { From 023bd9dc410cd58e3a7357d18990a0ae377ef33f Mon Sep 17 00:00:00 2001 From: Danila Chernetsov Date: Tue, 4 Apr 2023 19:05:49 +0000 Subject: [PATCH 4009/4345] apparmor: fix missing error check for rhashtable_insert_fast [ Upstream commit 000518bc5aef25d3f703592a0296d578c98b1517 ] rhashtable_insert_fast() could return err value when memory allocation is failed. but unpack_profile() do not check values and this always returns success value. This patch just adds error check code. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: e025be0f26d5 ("apparmor: support querying extended trusted helper extra data") Signed-off-by: Danila Chernetsov Signed-off-by: John Johansen Signed-off-by: Sasha Levin --- security/apparmor/policy_unpack.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 519656e68582..10896d69c442 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -909,8 +909,13 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) goto fail; } - rhashtable_insert_fast(profile->data, &data->head, - profile->data->p); + if (rhashtable_insert_fast(profile->data, &data->head, + profile->data->p)) { + kfree_sensitive(data->key); + kfree_sensitive(data); + info = "failed to insert data to table"; + goto fail; + } } if (!unpack_nameX(e, AA_STRUCTEND, NULL)) { From b6eefa7a27a6f58e84da80a91f50c60e1a1bb171 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 23 Aug 2021 23:41:42 +0200 Subject: [PATCH 4010/4345] i2c: xiic: Defer xiic_wakeup() and __xiic_start_xfer() in xiic_process() [ Upstream commit 743e227a895923c37a333eb2ebf3e391f00c406d ] The __xiic_start_xfer() manipulates the interrupt flags, xiic_wakeup() may result in return from xiic_xfer() early. Defer both to the end of the xiic_process() interrupt thread, so that they are executed after all the other interrupt bits handling completed and once it completely safe to perform changes to the interrupt bits in the hardware. Signed-off-by: Marek Vasut Acked-by: Michal Simek Signed-off-by: Wolfram Sang Stable-dep-of: cb6e45c9a0ad ("i2c: xiic: Don't try to handle more interrupt events after error") Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-xiic.c | 37 ++++++++++++++++++++++++----------- 1 file changed, 26 insertions(+), 11 deletions(-) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 3b564e68130b..8b93c22f3c40 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -375,6 +375,9 @@ static irqreturn_t xiic_process(int irq, void *dev_id) struct xiic_i2c *i2c = dev_id; u32 pend, isr, ier; u32 clr = 0; + int xfer_more = 0; + int wakeup_req = 0; + int wakeup_code = 0; /* Get the interrupt Status from the IPIF. There is no clearing of * interrupts in the IPIF. Interrupts must be cleared at the source. @@ -411,10 +414,14 @@ static irqreturn_t xiic_process(int irq, void *dev_id) */ xiic_reinit(i2c); - if (i2c->rx_msg) - xiic_wakeup(i2c, STATE_ERROR); - if (i2c->tx_msg) - xiic_wakeup(i2c, STATE_ERROR); + if (i2c->rx_msg) { + wakeup_req = 1; + wakeup_code = STATE_ERROR; + } + if (i2c->tx_msg) { + wakeup_req = 1; + wakeup_code = STATE_ERROR; + } } if (pend & XIIC_INTR_RX_FULL_MASK) { /* Receive register/FIFO is full */ @@ -448,8 +455,7 @@ static irqreturn_t xiic_process(int irq, void *dev_id) i2c->tx_msg++; dev_dbg(i2c->adap.dev.parent, "%s will start next...\n", __func__); - - __xiic_start_xfer(i2c); + xfer_more = 1; } } } @@ -463,11 +469,13 @@ static irqreturn_t xiic_process(int irq, void *dev_id) if (!i2c->tx_msg) goto out; - if ((i2c->nmsgs == 1) && !i2c->rx_msg && - xiic_tx_space(i2c) == 0) - xiic_wakeup(i2c, STATE_DONE); + wakeup_req = 1; + + if (i2c->nmsgs == 1 && !i2c->rx_msg && + xiic_tx_space(i2c) == 0) + wakeup_code = STATE_DONE; else - xiic_wakeup(i2c, STATE_ERROR); + wakeup_code = STATE_ERROR; } if (pend & (XIIC_INTR_TX_EMPTY_MASK | XIIC_INTR_TX_HALF_MASK)) { /* Transmit register/FIFO is empty or ½ empty */ @@ -491,7 +499,7 @@ static irqreturn_t xiic_process(int irq, void *dev_id) if (i2c->nmsgs > 1) { i2c->nmsgs--; i2c->tx_msg++; - __xiic_start_xfer(i2c); + xfer_more = 1; } else { xiic_irq_dis(i2c, XIIC_INTR_TX_HALF_MASK); @@ -509,6 +517,13 @@ out: dev_dbg(i2c->adap.dev.parent, "%s clr: 0x%x\n", __func__, clr); xiic_setreg32(i2c, XIIC_IISR_OFFSET, clr); + if (xfer_more) + __xiic_start_xfer(i2c); + if (wakeup_req) + xiic_wakeup(i2c, wakeup_code); + + WARN_ON(xfer_more && wakeup_req); + mutex_unlock(&i2c->lock); return IRQ_HANDLED; } From e71714ad24d8c43bb51050c23997d9456f408a00 Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Tue, 6 Jun 2023 12:25:58 -0600 Subject: [PATCH 4011/4345] i2c: xiic: Don't try to handle more interrupt events after error [ Upstream commit cb6e45c9a0ad9e0f8664fd06db0227d185dc76ab ] In xiic_process, it is possible that error events such as arbitration lost or TX error can be raised in conjunction with other interrupt flags such as TX FIFO empty or bus not busy. Error events result in the controller being reset and the error returned to the calling request, but the function could potentially try to keep handling the other events, such as by writing more messages into the TX FIFO. Since the transaction has already failed, this is not helpful and will just cause issues. This problem has been present ever since: commit 7f9906bd7f72 ("i2c: xiic: Service all interrupts in isr") which allowed non-error events to be handled after errors, but became more obvious after: commit 743e227a8959 ("i2c: xiic: Defer xiic_wakeup() and __xiic_start_xfer() in xiic_process()") which reworked the code to add a WARN_ON which triggers if both the xfer_more and wakeup_req flags were set, since this combination is not supposed to happen, but was occurring in this scenario. Skip further interrupt handling after error flags are detected to avoid this problem. Fixes: 7f9906bd7f72 ("i2c: xiic: Service all interrupts in isr") Signed-off-by: Robert Hancock Acked-by: Andi Shyti Signed-off-by: Wolfram Sang Signed-off-by: Sasha Levin --- drivers/i2c/busses/i2c-xiic.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 8b93c22f3c40..568e97c3896d 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -422,6 +422,8 @@ static irqreturn_t xiic_process(int irq, void *dev_id) wakeup_req = 1; wakeup_code = STATE_ERROR; } + /* don't try to handle other events */ + goto out; } if (pend & XIIC_INTR_RX_FULL_MASK) { /* Receive register/FIFO is full */ From e41a8e46156105ee91436d4fe9ceaeaa943b372d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 6 Jul 2023 17:53:57 +0200 Subject: [PATCH 4012/4345] ALSA: jack: Fix mutex call in snd_jack_report() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 89dbb335cb6a627a4067bc42caa09c8bc3326d40 ] snd_jack_report() is supposed to be callable from an IRQ context, too, and it's indeed used in that way from virtsnd driver. The fix for input_dev race in commit 1b6a6fc5280e ("ALSA: jack: Access input_dev under mutex"), however, introduced a mutex lock in snd_jack_report(), and this resulted in a potential sleep-in-atomic. For addressing that problem, this patch changes the relevant code to use the object get/put and removes the mutex usage. That is, snd_jack_report(), it takes input_get_device() and leaves with input_put_device() for assuring the input_dev being assigned. Although the whole mutex could be reduced, we keep it because it can be still a protection for potential races between creation and deletion. Fixes: 1b6a6fc5280e ("ALSA: jack: Access input_dev under mutex") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/cf95f7fe-a748-4990-8378-000491b40329@moroto.mountain Tested-by: Amadeusz Sławiński Cc: Link: https://lore.kernel.org/r/20230706155357.3470-1-tiwai@suse.de Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/core/jack.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/sound/core/jack.c b/sound/core/jack.c index 45e28db6ea38..8a9baa084191 100644 --- a/sound/core/jack.c +++ b/sound/core/jack.c @@ -364,6 +364,7 @@ void snd_jack_report(struct snd_jack *jack, int status) { struct snd_jack_kctl *jack_kctl; #ifdef CONFIG_SND_JACK_INPUT_DEV + struct input_dev *idev; int i; #endif @@ -375,30 +376,28 @@ void snd_jack_report(struct snd_jack *jack, int status) status & jack_kctl->mask_bits); #ifdef CONFIG_SND_JACK_INPUT_DEV - mutex_lock(&jack->input_dev_lock); - if (!jack->input_dev) { - mutex_unlock(&jack->input_dev_lock); + idev = input_get_device(jack->input_dev); + if (!idev) return; - } for (i = 0; i < ARRAY_SIZE(jack->key); i++) { int testbit = SND_JACK_BTN_0 >> i; if (jack->type & testbit) - input_report_key(jack->input_dev, jack->key[i], + input_report_key(idev, jack->key[i], status & testbit); } for (i = 0; i < ARRAY_SIZE(jack_switch_types); i++) { int testbit = 1 << i; if (jack->type & testbit) - input_report_switch(jack->input_dev, + input_report_switch(idev, jack_switch_types[i], status & testbit); } - input_sync(jack->input_dev); - mutex_unlock(&jack->input_dev_lock); + input_sync(idev); + input_put_device(idev); #endif /* CONFIG_SND_JACK_INPUT_DEV */ } EXPORT_SYMBOL(snd_jack_report); From 8d36cb6d1aed7d5c9f752f817614a3831e54e11b Mon Sep 17 00:00:00 2001 From: Shuai Jiang Date: Tue, 18 Apr 2023 21:56:12 +0800 Subject: [PATCH 4013/4345] i2c: qup: Add missing unwind goto in qup_i2c_probe() commit cd9489623c29aa2f8cc07088168afb6e0d5ef06d upstream. Smatch Warns: drivers/i2c/busses/i2c-qup.c:1784 qup_i2c_probe() warn: missing unwind goto? The goto label "fail_runtime" and "fail" will disable qup->pclk, but here qup->pclk failed to obtain, in order to be consistent, change the direct return to goto label "fail_dma". Fixes: 9cedf3b2f099 ("i2c: qup: Add bam dma capabilities") Signed-off-by: Shuai Jiang Reviewed-by: Dongliang Mu Reviewed-by: Andi Shyti Signed-off-by: Wolfram Sang Cc: # v4.6+ Signed-off-by: Greg Kroah-Hartman --- drivers/i2c/busses/i2c-qup.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c index 5a47915869ae..576c12670bd8 100644 --- a/drivers/i2c/busses/i2c-qup.c +++ b/drivers/i2c/busses/i2c-qup.c @@ -1752,16 +1752,21 @@ nodma: if (!clk_freq || clk_freq > I2C_MAX_FAST_MODE_PLUS_FREQ) { dev_err(qup->dev, "clock frequency not supported %d\n", clk_freq); - return -EINVAL; + ret = -EINVAL; + goto fail_dma; } qup->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(qup->base)) - return PTR_ERR(qup->base); + if (IS_ERR(qup->base)) { + ret = PTR_ERR(qup->base); + goto fail_dma; + } qup->irq = platform_get_irq(pdev, 0); - if (qup->irq < 0) - return qup->irq; + if (qup->irq < 0) { + ret = qup->irq; + goto fail_dma; + } if (has_acpi_companion(qup->dev)) { ret = device_property_read_u32(qup->dev, @@ -1775,13 +1780,15 @@ nodma: qup->clk = devm_clk_get(qup->dev, "core"); if (IS_ERR(qup->clk)) { dev_err(qup->dev, "Could not get core clock\n"); - return PTR_ERR(qup->clk); + ret = PTR_ERR(qup->clk); + goto fail_dma; } qup->pclk = devm_clk_get(qup->dev, "iface"); if (IS_ERR(qup->pclk)) { dev_err(qup->dev, "Could not get iface clock\n"); - return PTR_ERR(qup->pclk); + ret = PTR_ERR(qup->pclk); + goto fail_dma; } qup_i2c_enable_clocks(qup); src_clk_freq = clk_get_rate(qup->clk); From 8482ac2e5a261f59675e2f1488fdf332d39c3626 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Tue, 6 Jun 2023 16:41:02 -0700 Subject: [PATCH 4014/4345] NFSD: add encoding of op_recall flag for write delegation commit 58f5d894006d82ed7335e1c37182fbc5f08c2f51 upstream. Modified nfsd4_encode_open to encode the op_recall flag properly for OPEN result with write delegation granted. Signed-off-by: Dai Ngo Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/nfsd/nfs4xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 1e3410a9b03e..c7e8e641d3e5 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3705,7 +3705,7 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op p = xdr_reserve_space(xdr, 32); if (!p) return nfserr_resource; - *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(open->op_recall); /* * TODO: space_limit's in delegations From 28e649dc9947e6525c95e32aa9a8e147925e3f56 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 11 Jun 2023 21:14:09 -0600 Subject: [PATCH 4015/4345] io_uring: wait interruptibly for request completions on exit commit 4826c59453b3b4677d6bf72814e7ababdea86949 upstream. WHen the ring exits, cleanup is done and the final cancelation and waiting on completions is done by io_ring_exit_work. That function is invoked by kworker, which doesn't take any signals. Because of that, it doesn't really matter if we wait for completions in TASK_INTERRUPTIBLE or TASK_UNINTERRUPTIBLE state. However, it does matter to the hung task detection checker! Normally we expect cancelations and completions to happen rather quickly. Some test cases, however, will exit the ring and park the owning task stopped (eg via SIGSTOP). If the owning task needs to run task_work to complete requests, then io_ring_exit_work won't make any progress until the task is runnable again. Hence io_ring_exit_work can trigger the hung task detection, which is particularly problematic if panic-on-hung-task is enabled. As the ring exit doesn't take signals to begin with, have it wait interruptibly rather than uninterruptibly. io_uring has a separate stuck-exit warning that triggers independently anyway, so we're not really missing anything by making this switch. Cc: stable@vger.kernel.org # 5.10+ Link: https://lore.kernel.org/r/b0e4aaef-7088-56ce-244c-976edeac0e66@kernel.dk Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index bce80ed27c4d..25f201fc3ffd 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -9543,7 +9543,18 @@ static void io_ring_exit_work(struct work_struct *work) /* there is little hope left, don't run it too often */ interval = HZ * 60; } - } while (!wait_for_completion_timeout(&ctx->ref_comp, interval)); + /* + * This is really an uninterruptible wait, as it has to be + * complete. But it's also run from a kworker, which doesn't + * take signals, so it's fine to make it interruptible. This + * avoids scenarios where we knowingly can wait much longer + * on completions, for example if someone does a SIGSTOP on + * a task that needs to finish task_work to make this loop + * complete. That's a synthetic situation that should not + * cause a stuck task backtrace, and hence a potential panic + * on stuck tasks if that is enabled. + */ + } while (!wait_for_completion_interruptible_timeout(&ctx->ref_comp, interval)); init_completion(&exit.completion); init_task_work(&exit.task_work, io_tctx_exit_cb); @@ -9568,7 +9579,12 @@ static void io_ring_exit_work(struct work_struct *work) wake_up_process(node->task); mutex_unlock(&ctx->uring_lock); - wait_for_completion(&exit.completion); + /* + * See comment above for + * wait_for_completion_interruptible_timeout() on why this + * wait is marked as interruptible. + */ + wait_for_completion_interruptible(&exit.completion); mutex_lock(&ctx->uring_lock); } mutex_unlock(&ctx->uring_lock); From 6f9708e5c110a88750b3ca3b7013679f149bb1b0 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Mon, 19 Jun 2023 21:35:58 +0200 Subject: [PATCH 4016/4345] mmc: core: disable TRIM on Kingston EMMC04G-M627 commit f1738a1f816233e6dfc2407f24a31d596643fd90 upstream. It seems that Kingston EMMC04G-M627 despite advertising TRIM support does not work when the core is trying to use REQ_OP_WRITE_ZEROES. We are seeing I/O errors in OpenWrt under 6.1 on Zyxel NBG7815 that we did not previously have and tracked it down to REQ_OP_WRITE_ZEROES. Trying to use fstrim seems to also throw errors like: [93010.835112] I/O error, dev loop0, sector 16902 op 0x3:(DISCARD) flags 0x800 phys_seg 1 prio class 2 Disabling TRIM makes the error go away, so lets add a quirk for this eMMC to disable TRIM. Signed-off-by: Robert Marko Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230619193621.437358-1-robimarko@gmail.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/core/quirks.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h index c8c0f50a2076..3da45dd05666 100644 --- a/drivers/mmc/core/quirks.h +++ b/drivers/mmc/core/quirks.h @@ -99,6 +99,13 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = { MMC_FIXUP("V10016", CID_MANFID_KINGSTON, CID_OEMID_ANY, add_quirk_mmc, MMC_QUIRK_TRIM_BROKEN), + /* + * Kingston EMMC04G-M627 advertises TRIM but it does not seems to + * support being used to offload WRITE_ZEROES. + */ + MMC_FIXUP("M62704", CID_MANFID_KINGSTON, 0x0100, add_quirk_mmc, + MMC_QUIRK_TRIM_BROKEN), + /* * Some SD cards reports discard support while they don't */ From 02c8c2b5f68086c2aa7883f23d35a28ed0993725 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Tue, 30 May 2023 23:32:59 +0200 Subject: [PATCH 4017/4345] mmc: core: disable TRIM on Micron MTFC4GACAJCN-1M commit dbfbddcddcebc9ce8a08757708d4e4a99d238e44 upstream. It seems that Micron MTFC4GACAJCN-1M despite advertising TRIM support does not work when the core is trying to use REQ_OP_WRITE_ZEROES. We are seeing the following errors in OpenWrt under 6.1 on Qnap Qhora 301W that we did not previously have and tracked it down to REQ_OP_WRITE_ZEROES: [ 18.085950] I/O error, dev loop0, sector 596 op 0x9:(WRITE_ZEROES) flags 0x800 phys_seg 0 prio class 2 Disabling TRIM makes the error go away, so lets add a quirk for this eMMC to disable TRIM. Signed-off-by: Robert Marko Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230530213259.1776512-1-robimarko@gmail.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/core/quirks.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h index 3da45dd05666..afe8d8c5fa8a 100644 --- a/drivers/mmc/core/quirks.h +++ b/drivers/mmc/core/quirks.h @@ -106,6 +106,13 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = { MMC_FIXUP("M62704", CID_MANFID_KINGSTON, 0x0100, add_quirk_mmc, MMC_QUIRK_TRIM_BROKEN), + /* + * Micron MTFC4GACAJCN-1M advertises TRIM but it does not seems to + * support being used to offload WRITE_ZEROES. + */ + MMC_FIXUP("Q2J54A", CID_MANFID_MICRON, 0x014e, add_quirk_mmc, + MMC_QUIRK_TRIM_BROKEN), + /* * Some SD cards reports discard support while they don't */ From 191628e2d96ae92d438573028d1084ea3b1b79c4 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 12 Jun 2023 16:37:30 +0200 Subject: [PATCH 4018/4345] mmc: mmci: Set PROBE_PREFER_ASYNCHRONOUS commit 3108eb2e8aa7e955a9dd3a4c1bf19a7898961822 upstream. All mmc host drivers should have the asynchronous probe option enabled, but it seems like we failed to set it for mmci, so let's do that now. Fixes: 21b2cec61c04 ("mmc: Set PROBE_PREFER_ASYNCHRONOUS for drivers that existed in v4.4") Signed-off-by: Ulf Hansson Tested-by: Linus Walleij Tested-by: Yann Gautier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230612143730.210390-1-ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/mmci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 9cfffcecc9eb..a72ca7416138 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -2386,6 +2386,7 @@ static struct amba_driver mmci_driver = { .drv = { .name = DRIVER_NAME, .pm = &mmci_dev_pm_ops, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, .probe = mmci_probe, .remove = mmci_remove, From dc3287206a32e935151be592d15aa587ed60f773 Mon Sep 17 00:00:00 2001 From: Chevron Li Date: Tue, 23 May 2023 19:11:14 +0800 Subject: [PATCH 4019/4345] mmc: sdhci: fix DMA configure compatibility issue when 64bit DMA mode is used. commit 20dbd07ef0a8bc29eb03d6a95258ac8934cbe52d upstream. Bayhub SD host has hardware limitation: 1.The upper 32bit address is inhibited to be written at SD Host Register [03E][13]=0 (32bits addressing) mode, is admitted to be written only at SD Host Register [03E][13]=1 (64bits addressing) mode. 2.Because of above item#1, need to configure SD Host Register [03E][13] to 1(64bits addressing mode) before set 64bit ADMA system address's higher 32bits SD Host Register [05F~05C] if 64 bits addressing mode is used. The hardware limitation is reasonable for below reasons: 1.Normal flow should set DMA working mode first, then do DMA-transfer-related configuration, such as system address. 2.The hardware limitation may avoid the software to configure wrong higher 32bit address at 32bits addressing mode although it is redundant. The change that set 32bits/64bits addressing mode before set ADMA address, has no side-effect to other host IPs for below reason: The setting order is reasonable and standard: DMA Mode setting first and then DMA address setting. It meets all DMA setting sequence. Signed-off-by: Chevron Li Acked-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230523111114.18124-1-chevron_li@126.com Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/sdhci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 133f0d376480..bad01cc6823f 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1145,6 +1145,8 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd) } } + sdhci_config_dma(host); + if (host->flags & SDHCI_REQ_USE_DMA) { int sg_cnt = sdhci_pre_dma_transfer(host, data, COOKIE_MAPPED); @@ -1164,8 +1166,6 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd) } } - sdhci_config_dma(host); - if (!(host->flags & SDHCI_REQ_USE_DMA)) { int flags; From bcb295778afda4f2feb0d3c0289a53fd43d5a3a6 Mon Sep 17 00:00:00 2001 From: Mingzhe Zou Date: Thu, 15 Jun 2023 20:12:23 +0800 Subject: [PATCH 4020/4345] bcache: fixup btree_cache_wait list damage commit f0854489fc07d2456f7cc71a63f4faf9c716ffbe upstream. We get a kernel crash about "list_add corruption. next->prev should be prev (ffff9c801bc01210), but was ffff9c77b688237c. (next=ffffae586d8afe68)." crash> struct list_head 0xffff9c801bc01210 struct list_head { next = 0xffffae586d8afe68, prev = 0xffffae586d8afe68 } crash> struct list_head 0xffff9c77b688237c struct list_head { next = 0x0, prev = 0x0 } crash> struct list_head 0xffffae586d8afe68 struct list_head struct: invalid kernel virtual address: ffffae586d8afe68 type: "gdb_readmem_callback" Cannot access memory at address 0xffffae586d8afe68 [230469.019492] Call Trace: [230469.032041] prepare_to_wait+0x8a/0xb0 [230469.044363] ? bch_btree_keys_free+0x6c/0xc0 [escache] [230469.056533] mca_cannibalize_lock+0x72/0x90 [escache] [230469.068788] mca_alloc+0x2ae/0x450 [escache] [230469.080790] bch_btree_node_get+0x136/0x2d0 [escache] [230469.092681] bch_btree_check_thread+0x1e1/0x260 [escache] [230469.104382] ? finish_wait+0x80/0x80 [230469.115884] ? bch_btree_check_recurse+0x1a0/0x1a0 [escache] [230469.127259] kthread+0x112/0x130 [230469.138448] ? kthread_flush_work_fn+0x10/0x10 [230469.149477] ret_from_fork+0x35/0x40 bch_btree_check_thread() and bch_dirty_init_thread() may call mca_cannibalize() to cannibalize other cached btree nodes. Only one thread can do it at a time, so the op of other threads will be added to the btree_cache_wait list. We must call finish_wait() to remove op from btree_cache_wait before free it's memory address. Otherwise, the list will be damaged. Also should call bch_cannibalize_unlock() to release the btree_cache_alloc_lock and wake_up other waiters. Fixes: 8e7102273f59 ("bcache: make bch_btree_check() to be multithreaded") Fixes: b144e45fc576 ("bcache: make bch_sectors_dirty_init() to be multithreaded") Cc: stable@vger.kernel.org Signed-off-by: Mingzhe Zou Signed-off-by: Coly Li Link: https://lore.kernel.org/r/20230615121223.22502-7-colyli@suse.de Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/md/bcache/btree.c | 11 ++++++++++- drivers/md/bcache/btree.h | 1 + drivers/md/bcache/writeback.c | 10 ++++++++++ 3 files changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index b47c00dea0f2..9a5c5fbe9b85 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -885,7 +885,7 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op, * cannibalize_bucket() will take. This means every time we unlock the root of * the btree, we need to release this lock if we have it held. */ -static void bch_cannibalize_unlock(struct cache_set *c) +void bch_cannibalize_unlock(struct cache_set *c) { spin_lock(&c->btree_cannibalize_lock); if (c->btree_cache_alloc_lock == current) { @@ -1968,6 +1968,15 @@ static int bch_btree_check_thread(void *arg) c->gc_stats.nodes++; bch_btree_op_init(&op, 0); ret = bcache_btree(check_recurse, p, c->root, &op); + /* + * The op may be added to cache_set's btree_cache_wait + * in mca_cannibalize(), must ensure it is removed from + * the list and release btree_cache_alloc_lock before + * free op memory. + * Otherwise, the btree_cache_wait will be damaged. + */ + bch_cannibalize_unlock(c); + finish_wait(&c->btree_cache_wait, &(&op)->wait); if (ret) goto out; } diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 1b5fdbc0d83e..a2920bbfcad5 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -282,6 +282,7 @@ void bch_initial_gc_finish(struct cache_set *c); void bch_moving_gc(struct cache_set *c); int bch_btree_check(struct cache_set *c); void bch_initial_mark_key(struct cache_set *c, int level, struct bkey *k); +void bch_cannibalize_unlock(struct cache_set *c); static inline void wake_up_gc(struct cache_set *c) { diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 3aa73da2c67b..6324c922f6ba 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -834,6 +834,16 @@ static int bch_root_node_dirty_init(struct cache_set *c, if (ret < 0) pr_warn("sectors dirty init failed, ret=%d!\n", ret); + /* + * The op may be added to cache_set's btree_cache_wait + * in mca_cannibalize(), must ensure it is removed from + * the list and release btree_cache_alloc_lock before + * free op memory. + * Otherwise, the btree_cache_wait will be damaged. + */ + bch_cannibalize_unlock(c); + finish_wait(&c->btree_cache_wait, &(&op.op)->wait); + return ret; } From db9439cef0b5efccf8021fe89f4953e0f901e85b Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Thu, 15 Jun 2023 20:12:21 +0800 Subject: [PATCH 4021/4345] bcache: Remove unnecessary NULL point check in node allocations commit 028ddcac477b691dd9205c92f991cc15259d033e upstream. Due to the previous fix of __bch_btree_node_alloc, the return value will never be a NULL pointer. So IS_ERR is enough to handle the failure situation. Fix it by replacing IS_ERR_OR_NULL check by an IS_ERR check. Fixes: cafe56359144 ("bcache: A block layer cache") Cc: stable@vger.kernel.org Signed-off-by: Zheng Wang Signed-off-by: Coly Li Link: https://lore.kernel.org/r/20230615121223.22502-5-colyli@suse.de Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/md/bcache/btree.c | 10 +++++----- drivers/md/bcache/super.c | 4 ++-- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 9a5c5fbe9b85..941c15a0f32d 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1138,7 +1138,7 @@ static struct btree *btree_node_alloc_replacement(struct btree *b, { struct btree *n = bch_btree_node_alloc(b->c, op, b->level, b->parent); - if (!IS_ERR_OR_NULL(n)) { + if (!IS_ERR(n)) { mutex_lock(&n->write_lock); bch_btree_sort_into(&b->keys, &n->keys, &b->c->sort); bkey_copy_key(&n->key, &b->key); @@ -1340,7 +1340,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, memset(new_nodes, 0, sizeof(new_nodes)); closure_init_stack(&cl); - while (nodes < GC_MERGE_NODES && !IS_ERR_OR_NULL(r[nodes].b)) + while (nodes < GC_MERGE_NODES && !IS_ERR(r[nodes].b)) keys += r[nodes++].keys; blocks = btree_default_blocks(b->c) * 2 / 3; @@ -1352,7 +1352,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, for (i = 0; i < nodes; i++) { new_nodes[i] = btree_node_alloc_replacement(r[i].b, NULL); - if (IS_ERR_OR_NULL(new_nodes[i])) + if (IS_ERR(new_nodes[i])) goto out_nocoalesce; } @@ -1487,7 +1487,7 @@ out_nocoalesce: bch_keylist_free(&keylist); for (i = 0; i < nodes; i++) - if (!IS_ERR_OR_NULL(new_nodes[i])) { + if (!IS_ERR(new_nodes[i])) { btree_node_free(new_nodes[i]); rw_unlock(true, new_nodes[i]); } @@ -1669,7 +1669,7 @@ static int bch_btree_gc_root(struct btree *b, struct btree_op *op, if (should_rewrite) { n = btree_node_alloc_replacement(b, NULL); - if (!IS_ERR_OR_NULL(n)) { + if (!IS_ERR(n)) { bch_btree_node_write_sync(n); bch_btree_set_root(n); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 7f5ea2509643..e8c8077667f9 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1748,7 +1748,7 @@ static void cache_set_flush(struct closure *cl) if (!IS_ERR_OR_NULL(c->gc_thread)) kthread_stop(c->gc_thread); - if (!IS_ERR_OR_NULL(c->root)) + if (!IS_ERR(c->root)) list_add(&c->root->list, &c->btree_cache); /* @@ -2112,7 +2112,7 @@ static int run_cache_set(struct cache_set *c) err = "cannot allocate new btree root"; c->root = __bch_btree_node_alloc(c, NULL, 0, true, NULL); - if (IS_ERR_OR_NULL(c->root)) + if (IS_ERR(c->root)) goto err; mutex_lock(&c->root->write_lock); From a4405f6ee03323410d7b10966fd67b35f71b1944 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Thu, 15 Jun 2023 20:12:22 +0800 Subject: [PATCH 4022/4345] bcache: Fix __bch_btree_node_alloc to make the failure behavior consistent commit 80fca8a10b604afad6c14213fdfd816c4eda3ee4 upstream. In some specific situations, the return value of __bch_btree_node_alloc may be NULL. This may lead to a potential NULL pointer dereference in caller function like a calling chain : btree_split->bch_btree_node_alloc->__bch_btree_node_alloc. Fix it by initializing the return value in __bch_btree_node_alloc. Fixes: cafe56359144 ("bcache: A block layer cache") Cc: stable@vger.kernel.org Signed-off-by: Zheng Wang Signed-off-by: Coly Li Link: https://lore.kernel.org/r/20230615121223.22502-6-colyli@suse.de Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/md/bcache/btree.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 941c15a0f32d..24c57bb85b35 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1090,10 +1090,12 @@ struct btree *__bch_btree_node_alloc(struct cache_set *c, struct btree_op *op, struct btree *parent) { BKEY_PADDED(key) k; - struct btree *b = ERR_PTR(-EAGAIN); + struct btree *b; mutex_lock(&c->bucket_lock); retry: + /* return ERR_PTR(-EAGAIN) when it fails */ + b = ERR_PTR(-EAGAIN); if (__bch_bucket_alloc_set(c, RESERVE_BTREE, &k.key, wait)) goto err; From 9658a03f80b24f40ff6329b52ffd484145187b6b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 6 Jun 2023 15:24:45 -0700 Subject: [PATCH 4023/4345] um: Use HOST_DIR for mrproper commit a5a319ec2c2236bb96d147c16196d2f1f3799301 upstream. When HEADER_ARCH was introduced, the MRPROPER_FILES (then MRPROPER_DIRS) list wasn't adjusted, leaving SUBARCH as part of the path argument. This resulted in the "mrproper" target not cleaning up arch/x86/... when SUBARCH was specified. Since HOST_DIR is arch/$(HEADER_ARCH), use it instead to get the correct path. Cc: Richard Weinberger Cc: Anton Ivanov Cc: Johannes Berg Cc: Azeem Shaikh Cc: linux-um@lists.infradead.org Fixes: 7bbe7204e937 ("um: merge Makefile-{i386,x86_64}") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230606222442.never.807-kees@kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/um/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/Makefile b/arch/um/Makefile index 775615141339..56e5320da762 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -147,7 +147,7 @@ export LDFLAGS_vmlinux := $(LDFLAGS_EXECSTACK) # When cleaning we don't include .config, so we don't include # TT or skas makefiles and don't clean skas_ptregs.h. CLEAN_FILES += linux x.i gmon.out -MRPROPER_FILES += arch/$(SUBARCH)/include/generated +MRPROPER_FILES += $(HOST_DIR)/include/generated archclean: @find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \ From 8bf91a8d4871d7b1a82c76c0ee51f6789ed4f0b2 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Thu, 1 Jun 2023 14:42:44 +0800 Subject: [PATCH 4024/4345] integrity: Fix possible multiple allocation in integrity_inode_get() commit 9df6a4870dc371136e90330cfbbc51464ee66993 upstream. When integrity_inode_get() is querying and inserting the cache, there is a conditional race in the concurrent environment. The race condition is the result of not properly implementing "double-checked locking". In this case, it first checks to see if the iint cache record exists before taking the lock, but doesn't check again after taking the integrity_iint_lock. Fixes: bf2276d10ce5 ("ima: allocating iint improvements") Signed-off-by: Tianjia Zhang Cc: Dmitry Kasatkin Cc: # v3.10+ Signed-off-by: Mimi Zohar Signed-off-by: Greg Kroah-Hartman --- security/integrity/iint.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/security/integrity/iint.c b/security/integrity/iint.c index 0ba01847e836..9ed2d5bfbed5 100644 --- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -43,12 +43,10 @@ static struct integrity_iint_cache *__integrity_iint_find(struct inode *inode) else if (inode > iint->inode) n = n->rb_right; else - break; + return iint; } - if (!n) - return NULL; - return iint; + return NULL; } /* @@ -121,10 +119,15 @@ struct integrity_iint_cache *integrity_inode_get(struct inode *inode) parent = *p; test_iint = rb_entry(parent, struct integrity_iint_cache, rb_node); - if (inode < test_iint->inode) + if (inode < test_iint->inode) { p = &(*p)->rb_left; - else + } else if (inode > test_iint->inode) { p = &(*p)->rb_right; + } else { + write_unlock(&integrity_iint_lock); + kmem_cache_free(iint_cache, iint); + return test_iint; + } } iint->inode = inode; From 79bef379d55a66deaad5f491af4e4261b61b2470 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 May 2023 10:19:35 +0200 Subject: [PATCH 4025/4345] autofs: use flexible array in ioctl structure commit e910c8e3aa02dc456e2f4c32cb479523c326b534 upstream. Commit df8fc4e934c1 ("kbuild: Enable -fstrict-flex-arrays=3") introduced a warning for the autofs_dev_ioctl structure: In function 'check_name', inlined from 'validate_dev_ioctl' at fs/autofs/dev-ioctl.c:131:9, inlined from '_autofs_dev_ioctl' at fs/autofs/dev-ioctl.c:624:8: fs/autofs/dev-ioctl.c:33:14: error: 'strchr' reading 1 or more bytes from a region of size 0 [-Werror=stringop-overread] 33 | if (!strchr(name, '/')) | ^~~~~~~~~~~~~~~~~ In file included from include/linux/auto_dev-ioctl.h:10, from fs/autofs/autofs_i.h:10, from fs/autofs/dev-ioctl.c:14: include/uapi/linux/auto_dev-ioctl.h: In function '_autofs_dev_ioctl': include/uapi/linux/auto_dev-ioctl.h:112:14: note: source object 'path' of size 0 112 | char path[0]; | ^~~~ This is easily fixed by changing the gnu 0-length array into a c99 flexible array. Since this is a uapi structure, we have to be careful about possible regressions but this one should be fine as they are equivalent here. While it would break building with ancient gcc versions that predate c99, it helps building with --std=c99 and -Wpedantic builds in user space, as well as non-gnu compilers. This means we probably also want it fixed in stable kernels. Cc: stable@vger.kernel.org Cc: Kees Cook Cc: "Gustavo A. R. Silva" Signed-off-by: Arnd Bergmann Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230523081944.581710-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/autofs-mount-control.rst | 2 +- Documentation/filesystems/autofs.rst | 2 +- include/uapi/linux/auto_dev-ioctl.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/filesystems/autofs-mount-control.rst b/Documentation/filesystems/autofs-mount-control.rst index bf4b511cdbe8..b5a379d25c40 100644 --- a/Documentation/filesystems/autofs-mount-control.rst +++ b/Documentation/filesystems/autofs-mount-control.rst @@ -196,7 +196,7 @@ information and return operation results:: struct args_ismountpoint ismountpoint; }; - char path[0]; + char path[]; }; The ioctlfd field is a mount point file descriptor of an autofs mount diff --git a/Documentation/filesystems/autofs.rst b/Documentation/filesystems/autofs.rst index 681c6a492bc0..1b495768e7aa 100644 --- a/Documentation/filesystems/autofs.rst +++ b/Documentation/filesystems/autofs.rst @@ -467,7 +467,7 @@ Each ioctl is passed a pointer to an `autofs_dev_ioctl` structure:: struct args_ismountpoint ismountpoint; }; - char path[0]; + char path[]; }; For the **OPEN_MOUNT** and **IS_MOUNTPOINT** commands, the target diff --git a/include/uapi/linux/auto_dev-ioctl.h b/include/uapi/linux/auto_dev-ioctl.h index 62e625356dc8..08be539605fc 100644 --- a/include/uapi/linux/auto_dev-ioctl.h +++ b/include/uapi/linux/auto_dev-ioctl.h @@ -109,7 +109,7 @@ struct autofs_dev_ioctl { struct args_ismountpoint ismountpoint; }; - char path[0]; + char path[]; }; static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) From 5fada375113767b3b57f1b04f7a4fe64ffaa626f Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Wed, 7 Jun 2023 18:15:23 +0200 Subject: [PATCH 4026/4345] shmem: use ramfs_kill_sb() for kill_sb method of ramfs-based tmpfs commit 36ce9d76b0a93bae799e27e4f5ac35478c676592 upstream. As the ramfs-based tmpfs uses ramfs_init_fs_context() for the init_fs_context method, which allocates fc->s_fs_info, use ramfs_kill_sb() to free it and avoid a memory leak. Link: https://lkml.kernel.org/r/20230607161523.2876433-1-roberto.sassu@huaweicloud.com Fixes: c3b1b1cbf002 ("ramfs: add support for "mode=" mount option") Signed-off-by: Roberto Sassu Cc: Hugh Dickins Cc: David Howells Cc: Al Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/ramfs/inode.c | 2 +- include/linux/ramfs.h | 1 + mm/shmem.c | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index ee179a81b3da..23d2c333066f 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -264,7 +264,7 @@ int ramfs_init_fs_context(struct fs_context *fc) return 0; } -static void ramfs_kill_sb(struct super_block *sb) +void ramfs_kill_sb(struct super_block *sb) { kfree(sb->s_fs_info); kill_litter_super(sb); diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 917528d102c4..d506dc63dd47 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -7,6 +7,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode, dev_t dev); extern int ramfs_init_fs_context(struct fs_context *fc); +extern void ramfs_kill_sb(struct super_block *sb); #ifdef CONFIG_MMU static inline int diff --git a/mm/shmem.c b/mm/shmem.c index d3d8c5e7a296..cfa8f43cb3a6 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -4128,7 +4128,7 @@ static struct file_system_type shmem_fs_type = { .name = "tmpfs", .init_fs_context = ramfs_init_fs_context, .parameters = ramfs_fs_parameters, - .kill_sb = kill_litter_super, + .kill_sb = ramfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; From 988a5d791156450d8d996b3a0a0a754469aa8961 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Sat, 6 May 2023 06:56:12 +0200 Subject: [PATCH 4027/4345] jffs2: reduce stack usage in jffs2_build_xattr_subsystem() commit 1168f095417643f663caa341211e117db552989f upstream. Use kcalloc() for allocation/flush of 128 pointers table to reduce stack usage. Function now returns -ENOMEM or 0 on success. stackusage Before: ./fs/jffs2/xattr.c:775 jffs2_build_xattr_subsystem 1208 dynamic,bounded After: ./fs/jffs2/xattr.c:775 jffs2_build_xattr_subsystem 192 dynamic,bounded Also update definition when CONFIG_JFFS2_FS_XATTR is not enabled Tested with an MTD mount point and some user set/getfattr. Many current target on OpenWRT also suffer from a compilation warning (that become an error with CONFIG_WERROR) with the following output: fs/jffs2/xattr.c: In function 'jffs2_build_xattr_subsystem': fs/jffs2/xattr.c:887:1: error: the frame size of 1088 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] 887 | } | ^ Using dynamic allocation fix this compilation warning. Fixes: c9f700f840bd ("[JFFS2][XATTR] using 'delete marker' for xdatum/xref deletion") Reported-by: Tim Gardner Reported-by: kernel test robot Reported-by: Ron Economos Reported-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Fabian Frederick Signed-off-by: Christian Marangi Cc: stable@vger.kernel.org Message-Id: <20230506045612.16616-1-ansuelsmth@gmail.com> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/jffs2/build.c | 5 ++++- fs/jffs2/xattr.c | 13 +++++++++---- fs/jffs2/xattr.h | 4 ++-- 3 files changed, 15 insertions(+), 7 deletions(-) diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index 837cd55fd4c5..6ae9d6fefb86 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -211,7 +211,10 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) ic->scan_dents = NULL; cond_resched(); } - jffs2_build_xattr_subsystem(c); + ret = jffs2_build_xattr_subsystem(c); + if (ret) + goto exit; + c->flags &= ~JFFS2_SB_FLAG_BUILDING; dbg_fsbuild("FS build complete\n"); diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index da3e18503c65..acb4492f5970 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -772,10 +772,10 @@ void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c) } #define XREF_TMPHASH_SIZE (128) -void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) +int jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) { struct jffs2_xattr_ref *ref, *_ref; - struct jffs2_xattr_ref *xref_tmphash[XREF_TMPHASH_SIZE]; + struct jffs2_xattr_ref **xref_tmphash; struct jffs2_xattr_datum *xd, *_xd; struct jffs2_inode_cache *ic; struct jffs2_raw_node_ref *raw; @@ -784,9 +784,12 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) BUG_ON(!(c->flags & JFFS2_SB_FLAG_BUILDING)); + xref_tmphash = kcalloc(XREF_TMPHASH_SIZE, + sizeof(struct jffs2_xattr_ref *), GFP_KERNEL); + if (!xref_tmphash) + return -ENOMEM; + /* Phase.1 : Merge same xref */ - for (i=0; i < XREF_TMPHASH_SIZE; i++) - xref_tmphash[i] = NULL; for (ref=c->xref_temp; ref; ref=_ref) { struct jffs2_xattr_ref *tmp; @@ -884,6 +887,8 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) "%u of xref (%u dead, %u orphan) found.\n", xdatum_count, xdatum_unchecked_count, xdatum_orphan_count, xref_count, xref_dead_count, xref_orphan_count); + kfree(xref_tmphash); + return 0; } struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, diff --git a/fs/jffs2/xattr.h b/fs/jffs2/xattr.h index 720007b2fd65..1b5030a3349d 100644 --- a/fs/jffs2/xattr.h +++ b/fs/jffs2/xattr.h @@ -71,7 +71,7 @@ static inline int is_xattr_ref_dead(struct jffs2_xattr_ref *ref) #ifdef CONFIG_JFFS2_FS_XATTR extern void jffs2_init_xattr_subsystem(struct jffs2_sb_info *c); -extern void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c); +extern int jffs2_build_xattr_subsystem(struct jffs2_sb_info *c); extern void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c); extern struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, @@ -103,7 +103,7 @@ extern ssize_t jffs2_listxattr(struct dentry *, char *, size_t); #else #define jffs2_init_xattr_subsystem(c) -#define jffs2_build_xattr_subsystem(c) +#define jffs2_build_xattr_subsystem(c) (0) #define jffs2_clear_xattr_subsystem(c) #define jffs2_xattr_do_crccheck_inode(c, ic) From 5e7d18a52c889b5a762c7dc8c0242fd2e1cdd195 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Wed, 7 Jun 2023 19:28:48 +0200 Subject: [PATCH 4028/4345] fs: avoid empty option when generating legacy mount string MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 62176420274db5b5127cd7a0083a9aeb461756ee upstream. As each option string fragment is always prepended with a comma it would happen that the whole string always starts with a comma. This could be interpreted by filesystem drivers as an empty option and may produce errors. For example the NTFS driver from ntfs.ko behaves like this and fails when mounted via the new API. Link: https://github.com/util-linux/util-linux/issues/2298 Signed-off-by: Thomas Weißschuh Fixes: 3e1aeb00e6d1 ("vfs: Implement a filesystem superblock creation/configuration context") Cc: stable@vger.kernel.org Message-Id: <20230607-fs-empty-option-v1-1-20c8dbf4671b@weissschuh.net> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/fs_context.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/fs_context.c b/fs/fs_context.c index 740322dff4a3..e6ef7e040743 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -543,7 +543,8 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) return -ENOMEM; } - ctx->legacy_data[size++] = ','; + if (size) + ctx->legacy_data[size++] = ','; len = strlen(param->key); memcpy(ctx->legacy_data + size, param->key, len); size += len; From 2b563acd2dfaeef839661716498bfaa484cda9c7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 1 Jun 2023 12:58:21 +0200 Subject: [PATCH 4029/4345] ext4: Remove ext4 locking of moved directory commit 3658840cd363f2be094f5dfd2f0b174a9055dd0f upstream. Remove locking of moved directory in ext4_rename2(). We will take care of it in VFS instead. This effectively reverts commit 0813299c586b ("ext4: Fix possible corruption when moving a directory") and followup fixes. CC: Ted Tso CC: stable@vger.kernel.org Signed-off-by: Jan Kara Message-Id: <20230601105830.13168-1-jack@suse.cz> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/ext4/namei.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 45f719c1e002..ca3d2a33a08c 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3863,19 +3863,10 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, return retval; } - /* - * We need to protect against old.inode directory getting converted - * from inline directory format into a normal one. - */ - if (S_ISDIR(old.inode->i_mode)) - inode_lock_nested(old.inode, I_MUTEX_NONDIR2); - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, &old.inlined); - if (IS_ERR(old.bh)) { - retval = PTR_ERR(old.bh); - goto unlock_moved_dir; - } + if (IS_ERR(old.bh)) + return PTR_ERR(old.bh); /* * Check for inode number is _not_ due to possible IO errors. @@ -4065,10 +4056,6 @@ release_bh: brelse(old.bh); brelse(new.bh); -unlock_moved_dir: - if (S_ISDIR(old.inode->i_mode)) - inode_unlock(old.inode); - return retval; } From 4b03f503b730ac44e404fb39f2b0e53603e3745a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 1 Jun 2023 12:58:23 +0200 Subject: [PATCH 4030/4345] Revert "f2fs: fix potential corruption when moving a directory" commit cde3c9d7e2a359e337216855dcb333a19daaa436 upstream. This reverts commit d94772154e524b329a168678836745d2773a6e02. The locking is going to be provided by VFS. CC: Jaegeuk Kim CC: stable@vger.kernel.org Signed-off-by: Jan Kara Message-Id: <20230601105830.13168-3-jack@suse.cz> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/namei.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 98263180c0ea..72b109685db4 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -969,20 +969,12 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; } - /* - * Copied from ext4_rename: we need to protect against old.inode - * directory getting converted from inline directory format into - * a normal one. - */ - if (S_ISDIR(old_inode->i_mode)) - inode_lock_nested(old_inode, I_MUTEX_NONDIR2); - err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) err = PTR_ERR(old_page); - goto out_unlock_old; + goto out; } if (S_ISDIR(old_inode->i_mode)) { @@ -1090,9 +1082,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_unlock_op(sbi); - if (S_ISDIR(old_inode->i_mode)) - inode_unlock(old_inode); - if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); @@ -1107,9 +1096,6 @@ out_dir: f2fs_put_page(old_dir_page, 0); out_old: f2fs_put_page(old_page, 0); -out_unlock_old: - if (S_ISDIR(old_inode->i_mode)) - inode_unlock(old_inode); out: if (whiteout) iput(whiteout); From c5b5e72df13dabbf6187305b08453d3b58d1736f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 1 Jun 2023 12:58:24 +0200 Subject: [PATCH 4031/4345] fs: Establish locking order for unrelated directories commit f23ce757185319886ca80c4864ce5f81ac6cc9e9 upstream. Currently the locking order of inode locks for directories that are not in ancestor relationship is not defined because all operations that needed to lock two directories like this were serialized by sb->s_vfs_rename_mutex. However some filesystems need to lock two subdirectories for RENAME_EXCHANGE operations and for this we need the locking order established even for two tree-unrelated directories. Provide a helper function lock_two_inodes() that establishes lock ordering for any two inodes and use it in lock_two_directories(). CC: stable@vger.kernel.org Signed-off-by: Jan Kara Message-Id: <20230601105830.13168-4-jack@suse.cz> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/inode.c | 42 ++++++++++++++++++++++++++++++++++++++++++ fs/internal.h | 2 ++ fs/namei.c | 4 ++-- 3 files changed, 46 insertions(+), 2 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 7ec90788d8be..311237e8d359 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1015,6 +1015,48 @@ void discard_new_inode(struct inode *inode) } EXPORT_SYMBOL(discard_new_inode); +/** + * lock_two_inodes - lock two inodes (may be regular files but also dirs) + * + * Lock any non-NULL argument. The caller must make sure that if he is passing + * in two directories, one is not ancestor of the other. Zero, one or two + * objects may be locked by this function. + * + * @inode1: first inode to lock + * @inode2: second inode to lock + * @subclass1: inode lock subclass for the first lock obtained + * @subclass2: inode lock subclass for the second lock obtained + */ +void lock_two_inodes(struct inode *inode1, struct inode *inode2, + unsigned subclass1, unsigned subclass2) +{ + if (!inode1 || !inode2) { + /* + * Make sure @subclass1 will be used for the acquired lock. + * This is not strictly necessary (no current caller cares) but + * let's keep things consistent. + */ + if (!inode1) + swap(inode1, inode2); + goto lock; + } + + /* + * If one object is directory and the other is not, we must make sure + * to lock directory first as the other object may be its child. + */ + if (S_ISDIR(inode2->i_mode) == S_ISDIR(inode1->i_mode)) { + if (inode1 > inode2) + swap(inode1, inode2); + } else if (!S_ISDIR(inode1->i_mode)) + swap(inode1, inode2); +lock: + if (inode1) + inode_lock_nested(inode1, subclass1); + if (inode2 && inode2 != inode1) + inode_lock_nested(inode2, subclass2); +} + /** * lock_two_nondirectories - take two i_mutexes on non-directory objects * diff --git a/fs/internal.h b/fs/internal.h index d5d9fcdae10c..39193250a4ed 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -150,6 +150,8 @@ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); extern void inode_add_lru(struct inode *inode); extern int dentry_needs_remove_privs(struct dentry *dentry); bool in_group_or_capable(const struct inode *inode, kgid_t gid); +void lock_two_inodes(struct inode *inode1, struct inode *inode2, + unsigned subclass1, unsigned subclass2); /* * fs-writeback.c diff --git a/fs/namei.c b/fs/namei.c index 3d98db9802a7..be5cedfd6926 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2782,8 +2782,8 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) return p; } - inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); + lock_two_inodes(p1->d_inode, p2->d_inode, + I_MUTEX_PARENT, I_MUTEX_PARENT2); return NULL; } EXPORT_SYMBOL(lock_rename); From 59efb86711051d33388b9615990a83cc4452d961 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 1 Jun 2023 12:58:25 +0200 Subject: [PATCH 4032/4345] fs: Lock moved directories commit 28eceeda130f5058074dd007d9c59d2e8bc5af2e upstream. When a directory is moved to a different directory, some filesystems (udf, ext4, ocfs2, f2fs, and likely gfs2, reiserfs, and others) need to update their pointer to the parent and this must not race with other operations on the directory. Lock the directories when they are moved. Although not all filesystems need this locking, we perform it in vfs_rename() because getting the lock ordering right is really difficult and we don't want to expose these locking details to filesystems. CC: stable@vger.kernel.org Signed-off-by: Jan Kara Message-Id: <20230601105830.13168-5-jack@suse.cz> Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- .../filesystems/directory-locking.rst | 26 ++++++++++--------- fs/namei.c | 22 ++++++++++------ 2 files changed, 28 insertions(+), 20 deletions(-) diff --git a/Documentation/filesystems/directory-locking.rst b/Documentation/filesystems/directory-locking.rst index 504ba940c36c..dccd61c7c5c3 100644 --- a/Documentation/filesystems/directory-locking.rst +++ b/Documentation/filesystems/directory-locking.rst @@ -22,12 +22,11 @@ exclusive. 3) object removal. Locking rules: caller locks parent, finds victim, locks victim and calls the method. Locks are exclusive. -4) rename() that is _not_ cross-directory. Locking rules: caller locks -the parent and finds source and target. In case of exchange (with -RENAME_EXCHANGE in flags argument) lock both. In any case, -if the target already exists, lock it. If the source is a non-directory, -lock it. If we need to lock both, lock them in inode pointer order. -Then call the method. All locks are exclusive. +4) rename() that is _not_ cross-directory. Locking rules: caller locks the +parent and finds source and target. We lock both (provided they exist). If we +need to lock two inodes of different type (dir vs non-dir), we lock directory +first. If we need to lock two inodes of the same type, lock them in inode +pointer order. Then call the method. All locks are exclusive. NB: we might get away with locking the source (and target in exchange case) shared. @@ -44,15 +43,17 @@ All locks are exclusive. rules: * lock the filesystem - * lock parents in "ancestors first" order. + * lock parents in "ancestors first" order. If one is not ancestor of + the other, lock them in inode pointer order. * find source and target. * if old parent is equal to or is a descendent of target fail with -ENOTEMPTY * if new parent is equal to or is a descendent of source fail with -ELOOP - * If it's an exchange, lock both the source and the target. - * If the target exists, lock it. If the source is a non-directory, - lock it. If we need to lock both, do so in inode pointer order. + * Lock both the source and the target provided they exist. If we + need to lock two inodes of different type (dir vs non-dir), we lock + the directory first. If we need to lock two inodes of the same type, + lock them in inode pointer order. * call the method. All ->i_rwsem are taken exclusive. Again, we might get away with locking @@ -66,8 +67,9 @@ If no directory is its own ancestor, the scheme above is deadlock-free. Proof: - First of all, at any moment we have a partial ordering of the - objects - A < B iff A is an ancestor of B. + First of all, at any moment we have a linear ordering of the + objects - A < B iff (A is an ancestor of B) or (B is not an ancestor + of A and ptr(A) < ptr(B)). That ordering can change. However, the following is true: diff --git a/fs/namei.c b/fs/namei.c index be5cedfd6926..fa7e5511d7c8 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4264,7 +4264,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we have to lock _four_ objects - parents and victim (if it exists), - * and source (if it is not a directory). + * and source. * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change @@ -4341,10 +4341,16 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); - if (!is_dir || (flags & RENAME_EXCHANGE)) - lock_two_nondirectories(source, target); - else if (target) - inode_lock(target); + /* + * Lock all moved children. Moved directories may need to change parent + * pointer so they need the lock to prevent against concurrent + * directory changes moving parent pointer. For regular files we've + * historically always done this. The lockdep locking subclasses are + * somewhat arbitrary but RENAME_EXCHANGE in particular can swap + * regular files and directories so it's difficult to tell which + * subclasses to use. + */ + lock_two_inodes(source, target, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) @@ -4388,9 +4394,9 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, d_exchange(old_dentry, new_dentry); } out: - if (!is_dir || (flags & RENAME_EXCHANGE)) - unlock_two_nondirectories(source, target); - else if (target) + if (source) + inode_unlock(source); + if (target) inode_unlock(target); dput(new_dentry); if (!error) { From a3fbd156bd2cd16e3c64e250ebce33eb9f2ef612 Mon Sep 17 00:00:00 2001 From: Matt Corallo Date: Mon, 5 Jun 2023 16:49:45 -0700 Subject: [PATCH 4033/4345] btrfs: add handling for RAID1C23/DUP to btrfs_reduce_alloc_profile commit 160fe8f6fdb13da6111677be6263e5d65e875987 upstream. Callers of `btrfs_reduce_alloc_profile` expect it to return exactly one allocation profile flag, and failing to do so may ultimately result in a WARN_ON and remount-ro when allocating new blocks, like the below transaction abort on 6.1. `btrfs_reduce_alloc_profile` has two ways of determining the profile, first it checks if a conversion balance is currently running and uses the profile we're converting to. If no balance is currently running, it returns the max-redundancy profile which at least one block in the selected block group has. This works by simply checking each known allocation profile bit in redundancy order. However, `btrfs_reduce_alloc_profile` has not been updated as new flags have been added - first with the `DUP` profile and later with the RAID1C34 profiles. Because of the way it checks, if we have blocks with different profiles and at least one is known, that profile will be selected. However, if none are known we may return a flag set with multiple allocation profiles set. This is currently only possible when a balance from one of the three unhandled profiles to another of the unhandled profiles is canceled after allocating at least one block using the new profile. In that case, a transaction abort like the below will occur and the filesystem will need to be mounted with -o skip_balance to get it mounted rw again (but the balance cannot be resumed without a similar abort). [770.648] ------------[ cut here ]------------ [770.648] BTRFS: Transaction aborted (error -22) [770.648] WARNING: CPU: 43 PID: 1159593 at fs/btrfs/extent-tree.c:4122 find_free_extent+0x1d94/0x1e00 [btrfs] [770.648] CPU: 43 PID: 1159593 Comm: btrfs Tainted: G W 6.1.0-0.deb11.7-powerpc64le #1 Debian 6.1.20-2~bpo11+1a~test [770.648] Hardware name: T2P9D01 REV 1.00 POWER9 0x4e1202 opal:skiboot-bc106a0 PowerNV [770.648] NIP: c00800000f6784fc LR: c00800000f6784f8 CTR: c000000000d746c0 [770.648] REGS: c000200089afe9a0 TRAP: 0700 Tainted: G W (6.1.0-0.deb11.7-powerpc64le Debian 6.1.20-2~bpo11+1a~test) [770.648] MSR: 9000000002029033 CR: 28848282 XER: 20040000 [770.648] CFAR: c000000000135110 IRQMASK: 0 GPR00: c00800000f6784f8 c000200089afec40 c00800000f7ea800 0000000000000026 GPR04: 00000001004820c2 c000200089afea00 c000200089afe9f8 0000000000000027 GPR08: c000200ffbfe7f98 c000000002127f90 ffffffffffffffd8 0000000026d6a6e8 GPR12: 0000000028848282 c000200fff7f3800 5deadbeef0000122 c00000002269d000 GPR16: c0002008c7797c40 c000200089afef17 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000001 c000200008bc5a98 0000000000000001 GPR24: 0000000000000000 c0000003c73088d0 c000200089afef17 c000000016d3a800 GPR28: c0000003c7308800 c00000002269d000 ffffffffffffffea 0000000000000001 [770.648] NIP [c00800000f6784fc] find_free_extent+0x1d94/0x1e00 [btrfs] [770.648] LR [c00800000f6784f8] find_free_extent+0x1d90/0x1e00 [btrfs] [770.648] Call Trace: [770.648] [c000200089afec40] [c00800000f6784f8] find_free_extent+0x1d90/0x1e00 [btrfs] (unreliable) [770.648] [c000200089afed30] [c00800000f681398] btrfs_reserve_extent+0x1a0/0x2f0 [btrfs] [770.648] [c000200089afeea0] [c00800000f681bf0] btrfs_alloc_tree_block+0x108/0x670 [btrfs] [770.648] [c000200089afeff0] [c00800000f66bd68] __btrfs_cow_block+0x170/0x850 [btrfs] [770.648] [c000200089aff100] [c00800000f66c58c] btrfs_cow_block+0x144/0x288 [btrfs] [770.648] [c000200089aff1b0] [c00800000f67113c] btrfs_search_slot+0x6b4/0xcb0 [btrfs] [770.648] [c000200089aff2a0] [c00800000f679f60] lookup_inline_extent_backref+0x128/0x7c0 [btrfs] [770.648] [c000200089aff3b0] [c00800000f67b338] lookup_extent_backref+0x70/0x190 [btrfs] [770.648] [c000200089aff470] [c00800000f67b54c] __btrfs_free_extent+0xf4/0x1490 [btrfs] [770.648] [c000200089aff5a0] [c00800000f67d770] __btrfs_run_delayed_refs+0x328/0x1530 [btrfs] [770.648] [c000200089aff740] [c00800000f67ea2c] btrfs_run_delayed_refs+0xb4/0x3e0 [btrfs] [770.648] [c000200089aff800] [c00800000f699aa4] btrfs_commit_transaction+0x8c/0x12b0 [btrfs] [770.648] [c000200089aff8f0] [c00800000f6dc628] reset_balance_state+0x1c0/0x290 [btrfs] [770.648] [c000200089aff9a0] [c00800000f6e2f7c] btrfs_balance+0x1164/0x1500 [btrfs] [770.648] [c000200089affb40] [c00800000f6f8e4c] btrfs_ioctl+0x2b54/0x3100 [btrfs] [770.648] [c000200089affc80] [c00000000053be14] sys_ioctl+0x794/0x1310 [770.648] [c000200089affd70] [c00000000002af98] system_call_exception+0x138/0x250 [770.648] [c000200089affe10] [c00000000000c654] system_call_common+0xf4/0x258 [770.648] --- interrupt: c00 at 0x7fff94126800 [770.648] NIP: 00007fff94126800 LR: 0000000107e0b594 CTR: 0000000000000000 [770.648] REGS: c000200089affe80 TRAP: 0c00 Tainted: G W (6.1.0-0.deb11.7-powerpc64le Debian 6.1.20-2~bpo11+1a~test) [770.648] MSR: 900000000000d033 CR: 24002848 XER: 00000000 [770.648] IRQMASK: 0 GPR00: 0000000000000036 00007fffc9439da0 00007fff94217100 0000000000000003 GPR04: 00000000c4009420 00007fffc9439ee8 0000000000000000 0000000000000000 GPR08: 00000000803c7416 0000000000000000 0000000000000000 0000000000000000 GPR12: 0000000000000000 00007fff9467d120 0000000107e64c9c 0000000107e64d0a GPR16: 0000000107e64d06 0000000107e64cf1 0000000107e64cc4 0000000107e64c73 GPR20: 0000000107e64c31 0000000107e64bf1 0000000107e64be7 0000000000000000 GPR24: 0000000000000000 00007fffc9439ee0 0000000000000003 0000000000000001 GPR28: 00007fffc943f713 0000000000000000 00007fffc9439ee8 0000000000000000 [770.648] NIP [00007fff94126800] 0x7fff94126800 [770.648] LR [0000000107e0b594] 0x107e0b594 [770.648] --- interrupt: c00 [770.648] Instruction dump: [770.648] 3b00ffe4 e8898828 481175f5 60000000 4bfff4fc 3be00000 4bfff570 3d220000 [770.648] 7fc4f378 e8698830 4811cd95 e8410018 <0fe00000> f9c10060 f9e10068 fa010070 [770.648] ---[ end trace 0000000000000000 ]--- [770.648] BTRFS: error (device dm-2: state A) in find_free_extent_update_loop:4122: errno=-22 unknown [770.648] BTRFS info (device dm-2: state EA): forced readonly [770.648] BTRFS: error (device dm-2: state EA) in __btrfs_free_extent:3070: errno=-22 unknown [770.648] BTRFS error (device dm-2: state EA): failed to run delayed ref for logical 17838685708288 num_bytes 24576 type 184 action 2 ref_mod 1: -22 [770.648] BTRFS: error (device dm-2: state EA) in btrfs_run_delayed_refs:2144: errno=-22 unknown [770.648] BTRFS: error (device dm-2: state EA) in reset_balance_state:3599: errno=-22 unknown Fixes: 47e6f7423b91 ("btrfs: add support for 3-copy replication (raid1c3)") Fixes: 8d6fac0087e5 ("btrfs: add support for 4-copy replication (raid1c4)") CC: stable@vger.kernel.org # 5.10+ Signed-off-by: Matt Corallo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/block-group.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index d0fecbd28232..c4e3c1a5de05 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -77,14 +77,21 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_fs_info *fs_info, u64 flags) } allowed &= flags; - if (allowed & BTRFS_BLOCK_GROUP_RAID6) + /* Select the highest-redundancy RAID level. */ + if (allowed & BTRFS_BLOCK_GROUP_RAID1C4) + allowed = BTRFS_BLOCK_GROUP_RAID1C4; + else if (allowed & BTRFS_BLOCK_GROUP_RAID6) allowed = BTRFS_BLOCK_GROUP_RAID6; + else if (allowed & BTRFS_BLOCK_GROUP_RAID1C3) + allowed = BTRFS_BLOCK_GROUP_RAID1C3; else if (allowed & BTRFS_BLOCK_GROUP_RAID5) allowed = BTRFS_BLOCK_GROUP_RAID5; else if (allowed & BTRFS_BLOCK_GROUP_RAID10) allowed = BTRFS_BLOCK_GROUP_RAID10; else if (allowed & BTRFS_BLOCK_GROUP_RAID1) allowed = BTRFS_BLOCK_GROUP_RAID1; + else if (allowed & BTRFS_BLOCK_GROUP_DUP) + allowed = BTRFS_BLOCK_GROUP_DUP; else if (allowed & BTRFS_BLOCK_GROUP_RAID0) allowed = BTRFS_BLOCK_GROUP_RAID0; From 6819bb0b8552dcc5f82ca606c8911b8c67e0628f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 19 Jun 2023 17:21:47 +0100 Subject: [PATCH 4034/4345] btrfs: fix race when deleting quota root from the dirty cow roots list commit b31cb5a6eb7a48b0a7bfdf06832b1fd5088d8c79 upstream. When disabling quotas we are deleting the quota root from the list fs_info->dirty_cowonly_roots without taking the lock that protects it, which is struct btrfs_fs_info::trans_lock. This unsynchronized list manipulation may cause chaos if there's another concurrent manipulation of this list, such as when adding a root to it with ctree.c:add_root_to_dirty_list(). This can result in all sorts of weird failures caused by a race, such as the following crash: [337571.278245] general protection fault, probably for non-canonical address 0xdead000000000108: 0000 [#1] PREEMPT SMP PTI [337571.278933] CPU: 1 PID: 115447 Comm: btrfs Tainted: G W 6.4.0-rc6-btrfs-next-134+ #1 [337571.279153] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [337571.279572] RIP: 0010:commit_cowonly_roots+0x11f/0x250 [btrfs] [337571.279928] Code: 85 38 06 00 (...) [337571.280363] RSP: 0018:ffff9f63446efba0 EFLAGS: 00010206 [337571.280582] RAX: ffff942d98ec2638 RBX: ffff9430b82b4c30 RCX: 0000000449e1c000 [337571.280798] RDX: dead000000000100 RSI: ffff9430021e4900 RDI: 0000000000036070 [337571.281015] RBP: ffff942d98ec2000 R08: ffff942d98ec2000 R09: 000000000000015b [337571.281254] R10: 0000000000000009 R11: 0000000000000001 R12: ffff942fe8fbf600 [337571.281476] R13: ffff942dabe23040 R14: ffff942dabe20800 R15: ffff942d92cf3b48 [337571.281723] FS: 00007f478adb7340(0000) GS:ffff94349fa40000(0000) knlGS:0000000000000000 [337571.281950] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [337571.282184] CR2: 00007f478ab9a3d5 CR3: 000000001e02c001 CR4: 0000000000370ee0 [337571.282416] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [337571.282647] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [337571.282874] Call Trace: [337571.283101] [337571.283327] ? __die_body+0x1b/0x60 [337571.283570] ? die_addr+0x39/0x60 [337571.283796] ? exc_general_protection+0x22e/0x430 [337571.284022] ? asm_exc_general_protection+0x22/0x30 [337571.284251] ? commit_cowonly_roots+0x11f/0x250 [btrfs] [337571.284531] btrfs_commit_transaction+0x42e/0xf90 [btrfs] [337571.284803] ? _raw_spin_unlock+0x15/0x30 [337571.285031] ? release_extent_buffer+0x103/0x130 [btrfs] [337571.285305] reset_balance_state+0x152/0x1b0 [btrfs] [337571.285578] btrfs_balance+0xa50/0x11e0 [btrfs] [337571.285864] ? __kmem_cache_alloc_node+0x14a/0x410 [337571.286086] btrfs_ioctl+0x249a/0x3320 [btrfs] [337571.286358] ? mod_objcg_state+0xd2/0x360 [337571.286577] ? refill_obj_stock+0xb0/0x160 [337571.286798] ? seq_release+0x25/0x30 [337571.287016] ? __rseq_handle_notify_resume+0x3ba/0x4b0 [337571.287235] ? percpu_counter_add_batch+0x2e/0xa0 [337571.287455] ? __x64_sys_ioctl+0x88/0xc0 [337571.287675] __x64_sys_ioctl+0x88/0xc0 [337571.287901] do_syscall_64+0x38/0x90 [337571.288126] entry_SYSCALL_64_after_hwframe+0x72/0xdc [337571.288352] RIP: 0033:0x7f478aaffe9b So fix this by locking struct btrfs_fs_info::trans_lock before deleting the quota root from that list. Fixes: bed92eae26cc ("Btrfs: qgroup implementation and prototypes") CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/qgroup.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 3fc689154bb5..94edc74c8979 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1270,7 +1270,9 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) goto out; } + spin_lock(&fs_info->trans_lock); list_del("a_root->dirty_list); + spin_unlock(&fs_info->trans_lock); btrfs_tree_lock(quota_root->node); btrfs_clean_tree_block(quota_root->node); From 1dac8584be0c33cd209f5dc04fdc4ef1e45804a9 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Mon, 12 Jun 2023 11:05:32 +0200 Subject: [PATCH 4035/4345] ASoC: mediatek: mt8173: Fix irq error path commit f9c058d14f4fe23ef523a7ff73734d51c151683c upstream. After reordering the irq probe, the error path was not properly done. Lets fix it. Reported-by: Dan Carpenter Cc: stable@kernel.org Fixes: 4cbb264d4e91 ("ASoC: mediatek: mt8173: Enable IRQ when pdata is ready") Signed-off-by: Ricardo Ribalda Delgado Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230612-mt8173-fixup-v2-2-432aa99ce24d@chromium.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/mediatek/mt8173/mt8173-afe-pcm.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c index 619d6733091c..cf8f66c2f289 100644 --- a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c +++ b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c @@ -1072,6 +1072,10 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) afe->dev = &pdev->dev; + irq_id = platform_get_irq(pdev, 0); + if (irq_id <= 0) + return irq_id < 0 ? irq_id : -ENXIO; + afe->base_addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(afe->base_addr)) return PTR_ERR(afe->base_addr); @@ -1177,14 +1181,11 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) if (ret) goto err_cleanup_components; - irq_id = platform_get_irq(pdev, 0); - if (irq_id <= 0) - return irq_id < 0 ? irq_id : -ENXIO; ret = devm_request_irq(afe->dev, irq_id, mt8173_afe_irq_handler, 0, "Afe_ISR_Handle", (void *)afe); if (ret) { dev_err(afe->dev, "could not request_irq\n"); - goto err_pm_disable; + goto err_cleanup_components; } dev_info(&pdev->dev, "MT8173 AFE driver initialized.\n"); From 9b0f7940e212134441fb783517ba33e0f03281f7 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Mon, 12 Jun 2023 11:05:31 +0200 Subject: [PATCH 4036/4345] ASoC: mediatek: mt8173: Fix snd_soc_component_initialize error path commit a46d37012a5be1737393b8f82fd35665e4556eee upstream. If the second component fails to initialize, cleanup the first on. Reported-by: Dan Carpenter Cc: stable@kernel.org Fixes: f1b5bf07365d ("ASoC: mt2701/mt8173: replace platform to component") Signed-off-by: Ricardo Ribalda Delgado Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230612-mt8173-fixup-v2-1-432aa99ce24d@chromium.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/mediatek/mt8173/mt8173-afe-pcm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c index cf8f66c2f289..3f6d9659ee95 100644 --- a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c +++ b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c @@ -1162,14 +1162,14 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev) comp_hdmi = devm_kzalloc(&pdev->dev, sizeof(*comp_hdmi), GFP_KERNEL); if (!comp_hdmi) { ret = -ENOMEM; - goto err_pm_disable; + goto err_cleanup_components; } ret = snd_soc_component_initialize(comp_hdmi, &mt8173_afe_hdmi_dai_component, &pdev->dev); if (ret) - goto err_pm_disable; + goto err_cleanup_components; #ifdef CONFIG_DEBUG_FS comp_hdmi->debugfs_prefix = "hdmi"; From 5d6fbb624576bdd29f8d95e7085abf9c5cb5c007 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 17:31:05 +0200 Subject: [PATCH 4037/4345] ARM: orion5x: fix d2net gpio initialization commit f8ef1233939495c405a9faa4bd1ae7d3f581bae4 upstream. The DT version of this board has a custom file with the gpio device. However, it does nothing because the d2net_init() has no caller or prototype: arch/arm/mach-orion5x/board-d2net.c:101:13: error: no previous prototype for 'd2net_init' Call it from the board-dt file as intended. Fixes: 94b0bd366e36 ("ARM: orion5x: convert d2net to Device Tree") Reviewed-by: Andrew Lunn Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230516153109.514251-10-arnd@kernel.org Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-orion5x/board-dt.c | 3 +++ arch/arm/mach-orion5x/common.h | 6 ++++++ 2 files changed, 9 insertions(+) diff --git a/arch/arm/mach-orion5x/board-dt.c b/arch/arm/mach-orion5x/board-dt.c index 3d36f1d95196..3f651df3a71c 100644 --- a/arch/arm/mach-orion5x/board-dt.c +++ b/arch/arm/mach-orion5x/board-dt.c @@ -63,6 +63,9 @@ static void __init orion5x_dt_init(void) if (of_machine_is_compatible("maxtor,shared-storage-2")) mss2_init(); + if (of_machine_is_compatible("lacie,d2-network")) + d2net_init(); + of_platform_default_populate(NULL, orion5x_auxdata_lookup, NULL); } diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h index eb96009e21c4..b9cfdb456456 100644 --- a/arch/arm/mach-orion5x/common.h +++ b/arch/arm/mach-orion5x/common.h @@ -75,6 +75,12 @@ extern void mss2_init(void); static inline void mss2_init(void) {} #endif +#ifdef CONFIG_MACH_D2NET_DT +void d2net_init(void); +#else +static inline void d2net_init(void) {} +#endif + /***************************************************************************** * Helpers to access Orion registers ****************************************************************************/ From 66a0647cdc56b91ecc10712327aa503bfed57310 Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Wed, 19 Apr 2023 23:07:39 +0200 Subject: [PATCH 4038/4345] leds: trigger: netdev: Recheck NETDEV_LED_MODE_LINKUP on dev rename commit cee4bd16c3195a701be683f7da9e88c6e11acb73 upstream. Dev can be renamed also while up for supported device. We currently wrongly clear the NETDEV_LED_MODE_LINKUP flag on NETDEV_CHANGENAME event. Fix this by rechecking if the carrier is ok on NETDEV_CHANGENAME and correctly set the NETDEV_LED_MODE_LINKUP bit. Fixes: 5f820ed52371 ("leds: trigger: netdev: fix handling on interface rename") Cc: stable@vger.kernel.org # v5.5+ Signed-off-by: Christian Marangi Reviewed-by: Andrew Lunn Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230419210743.3594-2-ansuelsmth@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/leds/trigger/ledtrig-netdev.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index d5e774d83021..f4d670ec30bc 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -318,6 +318,9 @@ static int netdev_trig_notify(struct notifier_block *nb, clear_bit(NETDEV_LED_MODE_LINKUP, &trigger_data->mode); switch (evt) { case NETDEV_CHANGENAME: + if (netif_carrier_ok(dev)) + set_bit(NETDEV_LED_MODE_LINKUP, &trigger_data->mode); + fallthrough; case NETDEV_REGISTER: if (trigger_data->net_dev) dev_put(trigger_data->net_dev); From 5cb46b80ecdae8dc83ee957cad41238393eae326 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 3 Jul 2023 16:49:11 +0200 Subject: [PATCH 4039/4345] fs: no need to check source commit 66d8fc0539b0d49941f313c9509a8384e4245ac1 upstream. The @source inode must be valid. It is even checked via IS_SWAPFILE() above making it pretty clear. So no need to check it when we unlock. What doesn't need to exist is the @target inode. The lock_two_inodes() helper currently swaps the @inode1 and @inode2 arguments if @inode1 is NULL to have consistent lock class usage. However, we know that at least for vfs_rename() that @inode1 is @source and thus is never NULL as per above. We also know that @source is a different inode than @target as that is checked right at the beginning of vfs_rename(). So we know that @source is valid and locked and that @target is locked. So drop the check whether @source is non-NULL. Fixes: 28eceeda130f ("fs: Lock moved directories") Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202307030026.9sE2pk2x-lkp@intel.com Message-Id: <20230703-vfs-rename-source-v1-1-37eebb29b65b@kernel.org> [brauner: use commit message from patch I sent concurrently] Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- fs/namei.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index fa7e5511d7c8..bc5e633a5954 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4394,8 +4394,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, d_exchange(old_dentry, new_dentry); } out: - if (source) - inode_unlock(source); + inode_unlock(source); if (target) inode_unlock(target); dput(new_dentry); From 5bf73af8b3820e2cd381efb6231dca1b273ed238 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 29 Jun 2023 07:20:44 +0300 Subject: [PATCH 4040/4345] fanotify: disallow mount/sb marks on kernel internal pseudo fs commit 69562eb0bd3e6bb8e522a7b254334e0fb30dff0c upstream. Hopefully, nobody is trying to abuse mount/sb marks for watching all anonymous pipes/inodes. I cannot think of a good reason to allow this - it looks like an oversight that dated back to the original fanotify API. Link: https://lore.kernel.org/linux-fsdevel/20230628101132.kvchg544mczxv2pm@quack3/ Fixes: 0ff21db9fcc3 ("fanotify: hooks the fanotify_mark syscall to the vfsmount code") Signed-off-by: Amir Goldstein Reviewed-by: Christian Brauner Signed-off-by: Jan Kara Message-Id: <20230629042044.25723-1-amir73il@gmail.com> [backport to 5.x.y] Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/notify/fanotify/fanotify_user.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 18e014fa0648..84de9f97bbc0 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1090,8 +1090,11 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) return 0; } -static int fanotify_events_supported(struct path *path, __u64 mask) +static int fanotify_events_supported(struct path *path, __u64 mask, + unsigned int flags) { + unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; + /* * Some filesystems such as 'proc' acquire unusual locks when opening * files. For them fanotify permission events have high chances of @@ -1103,6 +1106,21 @@ static int fanotify_events_supported(struct path *path, __u64 mask) if (mask & FANOTIFY_PERM_EVENTS && path->mnt->mnt_sb->s_type->fs_flags & FS_DISALLOW_NOTIFY_PERM) return -EINVAL; + + /* + * mount and sb marks are not allowed on kernel internal pseudo fs, + * like pipe_mnt, because that would subscribe to events on all the + * anonynous pipes in the system. + * + * SB_NOUSER covers all of the internal pseudo fs whose objects are not + * exposed to user's mount namespace, but there are other SB_KERNMOUNT + * fs, like nsfs, debugfs, for which the value of allowing sb and mount + * mark is questionable. For now we leave them alone. + */ + if (mark_type != FAN_MARK_INODE && + path->mnt->mnt_sb->s_flags & SB_NOUSER) + return -EINVAL; + return 0; } @@ -1218,7 +1236,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, goto fput_and_out; if (flags & FAN_MARK_ADD) { - ret = fanotify_events_supported(&path, mask); + ret = fanotify_events_supported(&path, mask, flags); if (ret) goto path_put_and_out; } From 88bffb61bc037884c23a72359785d4854b23407b Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Thu, 24 Nov 2022 14:55:35 +0100 Subject: [PATCH 4041/4345] tpm, tpm_tis: Claim locality in interrupt handler MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 0e069265bce5a40c4eee52e2364bbbd4dabee94a upstream. Writing the TPM_INT_STATUS register in the interrupt handler to clear the interrupts only has effect if a locality is held. Since this is not guaranteed at the time the interrupt is fired, claim the locality explicitly in the handler. Signed-off-by: Lino Sanfilippo Tested-by: Michael Niewöhner Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm_tis_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 512c867495ea..365761055df3 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -731,7 +731,9 @@ static irqreturn_t tis_int_handler(int dummy, void *dev_id) wake_up_interruptible(&priv->int_queue); /* Clear interrupts handled with TPM_EOI */ + tpm_tis_request_locality(chip, 0); rc = tpm_tis_write32(priv, TPM_INT_STATUS(priv->locality), interrupt); + tpm_tis_relinquish_locality(chip, 0); if (rc < 0) return IRQ_NONE; From f0aec6c403a0508165e8e8e4bc8213dc567af3a7 Mon Sep 17 00:00:00 2001 From: Gilad Reti Date: Wed, 13 Jan 2021 07:38:08 +0200 Subject: [PATCH 4042/4345] selftests/bpf: Add verifier test for PTR_TO_MEM spill commit 4237e9f4a96228ccc8a7abe5e4b30834323cd353 upstream. Add a test to check that the verifier is able to recognize spilling of PTR_TO_MEM registers, by reserving a ringbuf buffer, forcing the spill of a pointer holding the buffer address to the stack, filling it back in from the stack and writing to the memory area pointed by it. The patch was partially contributed by CyberArk Software, Inc. Signed-off-by: Gilad Reti Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20210113053810.13518-2-gilad.reti@gmail.com Cc: Lorenz Bauer Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/bpf/test_verifier.c | 12 +++++++- .../selftests/bpf/verifier/spill_fill.c | 30 +++++++++++++++++++ 2 files changed, 41 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 0fb92d9a319b..961c17b4681e 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -50,7 +50,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 20 +#define MAX_NR_MAPS 21 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -87,6 +87,7 @@ struct bpf_test { int fixup_sk_storage_map[MAX_FIXUPS]; int fixup_map_event_output[MAX_FIXUPS]; int fixup_map_reuseport_array[MAX_FIXUPS]; + int fixup_map_ringbuf[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t insn_processed; @@ -640,6 +641,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_sk_storage_map = test->fixup_sk_storage_map; int *fixup_map_event_output = test->fixup_map_event_output; int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; + int *fixup_map_ringbuf = test->fixup_map_ringbuf; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -817,6 +819,14 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_reuseport_array++; } while (*fixup_map_reuseport_array); } + if (*fixup_map_ringbuf) { + map_fds[20] = create_map(BPF_MAP_TYPE_RINGBUF, 0, + 0, 4096); + do { + prog[*fixup_map_ringbuf].imm = map_fds[20]; + fixup_map_ringbuf++; + } while (*fixup_map_ringbuf); + } } struct libcap { diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 45d43bf82f26..0b943897aaf6 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -28,6 +28,36 @@ .result = ACCEPT, .result_unpriv = ACCEPT, }, +{ + "check valid spill/fill, ptr to mem", + .insns = { + /* reserve 8 byte ringbuf memory */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve), + /* store a pointer to the reserved memory in R6 */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* check whether the reservation was successful */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + /* spill R6(mem) into the stack */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + /* fill it back in R7 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8), + /* should be able to access *(R7) = 0 */ + BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0), + /* submit the reserved ringbuf memory */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_ringbuf = { 1 }, + .result = ACCEPT, + .result_unpriv = ACCEPT, +}, { "check corrupted spill/fill", .insns = { From 87410743b548f66e937e927a59f17de5a2c9fc4a Mon Sep 17 00:00:00 2001 From: Michael Schmitz Date: Wed, 21 Jun 2023 08:17:25 +1200 Subject: [PATCH 4043/4345] block: add overflow checks for Amiga partition support commit b6f3f28f604ba3de4724ad82bea6adb1300c0b5f upstream. The Amiga partition parser module uses signed int for partition sector address and count, which will overflow for disks larger than 1 TB. Use u64 as type for sector address and size to allow using disks up to 2 TB without LBD support, and disks larger than 2 TB with LBD. The RBD format allows to specify disk sizes up to 2^128 bytes (though native OS limitations reduce this somewhat, to max 2^68 bytes), so check for u64 overflow carefully to protect against overflowing sector_t. Bail out if sector addresses overflow 32 bits on kernels without LBD support. This bug was reported originally in 2012, and the fix was created by the RDB author, Joanne Dow . A patch had been discussed and reviewed on linux-m68k at that time but never officially submitted (now resubmitted as patch 1 in this series). This patch adds additional error checking and warning messages. Reported-by: Martin Steigerwald Closes: https://bugzilla.kernel.org/show_bug.cgi?id=43511 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Message-ID: <201206192146.09327.Martin@lichtvoll.de> Cc: # 5.2 Signed-off-by: Michael Schmitz Reviewed-by: Geert Uytterhoeven Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230620201725.7020-4-schmitzmic@gmail.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/partitions/amiga.c | 103 ++++++++++++++++++++++++++++++++------- 1 file changed, 85 insertions(+), 18 deletions(-) diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c index 64f0844468aa..7abc09d8fc73 100644 --- a/block/partitions/amiga.c +++ b/block/partitions/amiga.c @@ -11,10 +11,18 @@ #define pr_fmt(fmt) fmt #include +#include +#include #include #include "check.h" +/* magic offsets in partition DosEnvVec */ +#define NR_HD 3 +#define NR_SECT 5 +#define LO_CYL 9 +#define HI_CYL 10 + static __inline__ u32 checksum_block(__be32 *m, int size) { @@ -31,9 +39,12 @@ int amiga_partition(struct parsed_partitions *state) unsigned char *data; struct RigidDiskBlock *rdb; struct PartitionBlock *pb; - sector_t start_sect, nr_sects; - int blk, part, res = 0; - int blksize = 1; /* Multiplier for disk block size */ + u64 start_sect, nr_sects; + sector_t blk, end_sect; + u32 cylblk; /* rdb_CylBlocks = nr_heads*sect_per_track */ + u32 nr_hd, nr_sect, lo_cyl, hi_cyl; + int part, res = 0; + unsigned int blksize = 1; /* Multiplier for disk block size */ int slot = 1; char b[BDEVNAME_SIZE]; @@ -42,7 +53,7 @@ int amiga_partition(struct parsed_partitions *state) goto rdb_done; data = read_part_sector(state, blk, §); if (!data) { - pr_err("Dev %s: unable to read RDB block %d\n", + pr_err("Dev %s: unable to read RDB block %llu\n", bdevname(state->bdev, b), blk); res = -1; goto rdb_done; @@ -59,12 +70,12 @@ int amiga_partition(struct parsed_partitions *state) *(__be32 *)(data+0xdc) = 0; if (checksum_block((__be32 *)data, be32_to_cpu(rdb->rdb_SummedLongs) & 0x7F)==0) { - pr_err("Trashed word at 0xd0 in block %d ignored in checksum calculation\n", + pr_err("Trashed word at 0xd0 in block %llu ignored in checksum calculation\n", blk); break; } - pr_err("Dev %s: RDB in block %d has bad checksum\n", + pr_err("Dev %s: RDB in block %llu has bad checksum\n", bdevname(state->bdev, b), blk); } @@ -81,10 +92,15 @@ int amiga_partition(struct parsed_partitions *state) blk = be32_to_cpu(rdb->rdb_PartitionList); put_dev_sector(sect); for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) { - blk *= blksize; /* Read in terms partition table understands */ + /* Read in terms partition table understands */ + if (check_mul_overflow(blk, (sector_t) blksize, &blk)) { + pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n", + bdevname(state->bdev, b), blk, part); + break; + } data = read_part_sector(state, blk, §); if (!data) { - pr_err("Dev %s: unable to read partition block %d\n", + pr_err("Dev %s: unable to read partition block %llu\n", bdevname(state->bdev, b), blk); res = -1; goto rdb_done; @@ -96,19 +112,70 @@ int amiga_partition(struct parsed_partitions *state) if (checksum_block((__be32 *)pb, be32_to_cpu(pb->pb_SummedLongs) & 0x7F) != 0 ) continue; - /* Tell Kernel about it */ + /* RDB gives us more than enough rope to hang ourselves with, + * many times over (2^128 bytes if all fields max out). + * Some careful checks are in order, so check for potential + * overflows. + * We are multiplying four 32 bit numbers to one sector_t! + */ + + nr_hd = be32_to_cpu(pb->pb_Environment[NR_HD]); + nr_sect = be32_to_cpu(pb->pb_Environment[NR_SECT]); + + /* CylBlocks is total number of blocks per cylinder */ + if (check_mul_overflow(nr_hd, nr_sect, &cylblk)) { + pr_err("Dev %s: heads*sects %u overflows u32, skipping partition!\n", + bdevname(state->bdev, b), cylblk); + continue; + } + + /* check for consistency with RDB defined CylBlocks */ + if (cylblk > be32_to_cpu(rdb->rdb_CylBlocks)) { + pr_warn("Dev %s: cylblk %u > rdb_CylBlocks %u!\n", + bdevname(state->bdev, b), cylblk, + be32_to_cpu(rdb->rdb_CylBlocks)); + } + + /* RDB allows for variable logical block size - + * normalize to 512 byte blocks and check result. + */ + + if (check_mul_overflow(cylblk, blksize, &cylblk)) { + pr_err("Dev %s: partition %u bytes per cyl. overflows u32, skipping partition!\n", + bdevname(state->bdev, b), part); + continue; + } + + /* Calculate partition start and end. Limit of 32 bit on cylblk + * guarantees no overflow occurs if LBD support is enabled. + */ + + lo_cyl = be32_to_cpu(pb->pb_Environment[LO_CYL]); + start_sect = ((u64) lo_cyl * cylblk); + + hi_cyl = be32_to_cpu(pb->pb_Environment[HI_CYL]); + nr_sects = (((u64) hi_cyl - lo_cyl + 1) * cylblk); - nr_sects = ((sector_t)be32_to_cpu(pb->pb_Environment[10]) + 1 - - be32_to_cpu(pb->pb_Environment[9])) * - be32_to_cpu(pb->pb_Environment[3]) * - be32_to_cpu(pb->pb_Environment[5]) * - blksize; if (!nr_sects) continue; - start_sect = (sector_t)be32_to_cpu(pb->pb_Environment[9]) * - be32_to_cpu(pb->pb_Environment[3]) * - be32_to_cpu(pb->pb_Environment[5]) * - blksize; + + /* Warn user if partition end overflows u32 (AmigaDOS limit) */ + + if ((start_sect + nr_sects) > UINT_MAX) { + pr_warn("Dev %s: partition %u (%llu-%llu) needs 64 bit device support!\n", + bdevname(state->bdev, b), part, + start_sect, start_sect + nr_sects); + } + + if (check_add_overflow(start_sect, nr_sects, &end_sect)) { + pr_err("Dev %s: partition %u (%llu-%llu) needs LBD device support, skipping partition!\n", + bdevname(state->bdev, b), part, + start_sect, end_sect); + continue; + } + + /* Tell Kernel about it */ + put_partition(state,slot++,start_sect,nr_sects); { /* Be even more informative to aid mounting */ From 01248dd65155baf43721a15995d53f88cabfbca2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 15 Sep 2021 15:50:04 +0200 Subject: [PATCH 4044/4345] sh: pgtable-3level: Fix cast to pointer from integer of different size MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8518e694203d0bfd202ea4a80356785b6992322e upstream. If X2TLB=y (CPU_SHX2=y or CPU_SHX3=y, e.g. migor_defconfig), pgd_t.pgd is "unsigned long long", causing: In file included from arch/sh/include/asm/pgtable.h:13, from include/linux/pgtable.h:6, from include/linux/mm.h:33, from arch/sh/kernel/asm-offsets.c:14: arch/sh/include/asm/pgtable-3level.h: In function ‘pud_pgtable’: arch/sh/include/asm/pgtable-3level.h:37:9: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] 37 | return (pmd_t *)pud_val(pud); | ^ Fix this by adding an intermediate cast to "unsigned long", which is basically what the old code did before. Fixes: 9cf6fa2458443118 ("mm: rename pud_page_vaddr to pud_pgtable and make it return pmd_t *") Signed-off-by: Geert Uytterhoeven Tested-by: Daniel Palmer Acked-by: Rob Landley Tested-by: John Paul Adrian Glaubitz Signed-off-by: Rich Felker Signed-off-by: Greg Kroah-Hartman --- arch/sh/include/asm/pgtable-3level.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index 56bf35c2f29c..cdced80a7ffa 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -34,7 +34,7 @@ typedef struct { unsigned long long pmd; } pmd_t; static inline pmd_t *pud_pgtable(pud_t pud) { - return (pmd_t *)pud_val(pud); + return (pmd_t *)(unsigned long)pud_val(pud); } /* only used by the stubbed out hugetlb gup code, should never be called */ From 3f51f1157f67e9f16602db2694492a3b0e9aec2e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Jul 2023 10:48:49 +0200 Subject: [PATCH 4045/4345] netfilter: nf_tables: use net_generic infra for transaction data [ Upstream commit 0854db2aaef3fcdd3498a9d299c60adea2aa3dc6 ] This moves all nf_tables pernet data from struct net to a net_generic extension, with the exception of the gencursor. The latter is used in the data path and also outside of the nf_tables core. All others are only used from the configuration plane. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 10 + include/net/netns/nftables.h | 7 - net/netfilter/nf_tables_api.c | 382 ++++++++++++++++++------------ net/netfilter/nf_tables_offload.c | 30 ++- net/netfilter/nft_chain_filter.c | 11 +- net/netfilter/nft_dynset.c | 6 +- 6 files changed, 279 insertions(+), 167 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 030237f3d82a..5e184c20bc55 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1535,4 +1535,14 @@ void nf_tables_trans_destroy_flush_work(void); int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); __be64 nf_jiffies64_to_msecs(u64 input); +struct nftables_pernet { + struct list_head tables; + struct list_head commit_list; + struct list_head module_list; + struct list_head notify_list; + struct mutex commit_mutex; + unsigned int base_seq; + u8 validate_state; +}; + #endif /* _NET_NF_TABLES_H */ diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index 6c0806bd8d1e..8c77832d0240 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -5,14 +5,7 @@ #include struct netns_nftables { - struct list_head tables; - struct list_head commit_list; - struct list_head module_list; - struct list_head notify_list; - struct mutex commit_mutex; - unsigned int base_seq; u8 gencursor; - u8 validate_state; }; #endif diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e59cad1f7a36..e3865f29ae83 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -21,10 +21,13 @@ #include #include #include +#include #include #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +unsigned int nf_tables_net_id __read_mostly; + static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); @@ -103,7 +106,9 @@ static const u8 nft2audit_op[NFT_MSG_MAX] = { // enum nf_tables_msg_types static void nft_validate_state_update(struct net *net, u8 new_validate_state) { - switch (net->nft.validate_state) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO); break; @@ -114,7 +119,7 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state) return; } - net->nft.validate_state = new_validate_state; + nft_net->validate_state = new_validate_state; } static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); @@ -170,13 +175,15 @@ static void nft_trans_destroy(struct nft_trans *trans) static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) { + struct nftables_pernet *nft_net; struct net *net = ctx->net; struct nft_trans *trans; if (!nft_set_is_anonymous(set)) return; - list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWSET: if (nft_trans_set(trans) == set) @@ -270,6 +277,14 @@ static void nf_tables_unregister_hook(struct net *net, nf_unregister_net_hook(net, &basechain->ops); } +static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) +{ + struct nftables_pernet *nft_net; + + nft_net = net_generic(net, nf_tables_net_id); + list_add_tail(&trans->list, &nft_net->commit_list); +} + static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) { struct nft_trans *trans; @@ -281,7 +296,7 @@ static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) if (msg_type == NFT_MSG_NEWTABLE) nft_activate_next(ctx->net, ctx->table); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -314,7 +329,7 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) } } - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } @@ -387,7 +402,7 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); } nft_trans_rule(trans) = rule; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } @@ -453,7 +468,7 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, set); } nft_trans_set(trans) = set; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -485,7 +500,7 @@ static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, obj); nft_trans_obj(trans) = obj; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -519,7 +534,7 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); nft_trans_flowtable(trans) = flowtable; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -547,13 +562,15 @@ static struct nft_table *nft_table_lookup(const struct net *net, const struct nlattr *nla, u8 family, u8 genmask) { + struct nftables_pernet *nft_net; struct nft_table *table; if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry_rcu(table, &net->nft.tables, list, - lockdep_is_held(&net->nft.commit_mutex)) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_rcu(table, &nft_net->tables, list, + lockdep_is_held(&nft_net->commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) @@ -567,9 +584,11 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, u8 genmask) { + struct nftables_pernet *nft_net; struct nft_table *table; - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && nft_active_genmask(table, genmask)) return table; @@ -621,6 +640,7 @@ struct nft_module_request { static int nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; + struct nftables_pernet *nft_net; struct nft_module_request *req; va_list args; int ret; @@ -631,7 +651,8 @@ static int nft_request_module(struct net *net, const char *fmt, ...) if (ret >= MODULE_NAME_LEN) return 0; - list_for_each_entry(req, &net->nft.module_list, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry(req, &nft_net->module_list, list) { if (!strcmp(req->module, module_name)) { if (req->done) return 0; @@ -647,7 +668,7 @@ static int nft_request_module(struct net *net, const char *fmt, ...) req->done = false; strlcpy(req->module, module_name, MODULE_NAME_LEN); - list_add_tail(&req->list, &net->nft.module_list); + list_add_tail(&req->list, &nft_net->module_list); return -EAGAIN; } @@ -685,7 +706,9 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, static __be16 nft_base_seq(const struct net *net) { - return htons(net->nft.base_seq & 0xffff); + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + return htons(nft_net->base_seq & 0xffff); } static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { @@ -743,6 +766,7 @@ static void nft_notify_enqueue(struct sk_buff *skb, bool report, static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { + struct nftables_pernet *nft_net; struct sk_buff *skb; int err; @@ -761,7 +785,8 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_net = net_generic(ctx->net, nf_tables_net_id); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -771,15 +796,17 @@ static int nf_tables_dump_tables(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + struct nftables_pernet *nft_net; const struct nft_table *table; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -954,7 +981,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) goto err; nft_trans_table_update(trans) = true; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err: nft_trans_destroy(trans); @@ -1017,6 +1044,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; @@ -1026,7 +1054,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, u32 flags = 0; int err; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask); if (IS_ERR(table)) { @@ -1084,7 +1112,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (err < 0) goto err_trans; - list_add_tail_rcu(&table->list, &net->nft.tables); + list_add_tail_rcu(&table->list, &nft_net->tables); return 0; err_trans: rhltable_destroy(&table->chains_ht); @@ -1172,11 +1200,12 @@ out: static int nft_flush(struct nft_ctx *ctx, int family) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct nft_table *table, *nt; const struct nlattr * const *nla = ctx->nla; int err = 0; - list_for_each_entry_safe(table, nt, &ctx->net->nft.tables, list) { + list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (family != AF_UNSPEC && table->family != family) continue; @@ -1291,7 +1320,9 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) static bool lockdep_commit_lock_is_held(const struct net *net) { #ifdef CONFIG_PROVE_LOCKING - return lockdep_is_held(&net->nft.commit_mutex); + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + return lockdep_is_held(&nft_net->commit_mutex); #else return true; #endif @@ -1494,6 +1525,7 @@ nla_put_failure: static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) { + struct nftables_pernet *nft_net; struct sk_buff *skb; int err; @@ -1513,7 +1545,8 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_net = net_generic(ctx->net, nf_tables_net_id); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -1528,11 +1561,13 @@ static int nf_tables_dump_chains(struct sk_buff *skb, unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -1847,11 +1882,12 @@ static int nft_chain_parse_hook(struct net *net, struct nft_chain_hook *hook, u8 family, bool autoload) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nlattr *ha[NFTA_HOOK_MAX + 1]; const struct nft_chain_type *type; int err; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); err = nla_parse_nested_deprecated(ha, NFTA_HOOK_MAX, @@ -2244,6 +2280,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (nla[NFTA_CHAIN_HANDLE] && nla[NFTA_CHAIN_NAME]) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct nft_trans *tmp; char *name; @@ -2253,7 +2290,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, goto err; err = -EEXIST; - list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + list_for_each_entry(tmp, &nft_net->commit_list, list) { if (tmp->msg_type == NFT_MSG_NEWCHAIN && tmp->ctx.table == table && nft_trans_chain_update(tmp) && @@ -2267,7 +2304,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nft_trans_chain_name(trans) = name; } - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err: @@ -2280,10 +2317,11 @@ static struct nft_chain *nft_chain_lookup_byid(const struct net *net, const struct nft_table *table, const struct nlattr *nla) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWCHAIN && @@ -2299,6 +2337,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; @@ -2310,7 +2349,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, u64 handle = 0; u32 flags = 0; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); if (IS_ERR(table)) { @@ -2848,6 +2887,7 @@ nla_put_failure: static void nf_tables_rule_notify(const struct nft_ctx *ctx, const struct nft_rule *rule, int event) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct sk_buff *skb; int err; @@ -2867,7 +2907,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -2925,11 +2965,13 @@ static int nf_tables_dump_rules(struct sk_buff *skb, unsigned int idx = 0; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -3161,6 +3203,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); struct nft_expr_info *info = NULL; @@ -3178,7 +3221,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, int err, rem; u64 handle, pos_handle; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); if (IS_ERR(table)) { @@ -3351,7 +3394,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, kvfree(info); chain->use++; - if (net->nft.validate_state == NFT_VALIDATE_DO) + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { @@ -3381,10 +3424,11 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { struct nft_rule *rule = nft_trans_rule(trans); if (trans->msg_type == NFT_MSG_NEWRULE && @@ -3497,13 +3541,14 @@ nft_select_set_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, enum nft_set_policies policy) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; const struct nft_set_type *type; u32 flags = 0; int i; - lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); if (nla[NFTA_SET_FLAGS] != NULL) @@ -3641,10 +3686,11 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans; u32 id = ntohl(nla_get_be32(nla)); - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWSET) { struct nft_set *set = nft_trans_set(trans); @@ -3867,6 +3913,7 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, const struct nft_set *set, int event, gfp_t gfp_flags) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct sk_buff *skb; u32 portid = ctx->portid; int err; @@ -3885,7 +3932,7 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -3898,14 +3945,16 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; struct net *net = sock_net(skb->sk); struct nft_ctx *ctx = cb->data, ctx_set; + struct nftables_pernet *nft_net; if (cb->args[1]) return skb->len; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && ctx->family != table->family) continue; @@ -4706,6 +4755,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { struct nft_set_dump_ctx *dump_ctx = cb->data; struct net *net = sock_net(skb->sk); + struct nftables_pernet *nft_net; struct nft_table *table; struct nft_set *set; struct nft_set_dump_args args; @@ -4716,7 +4766,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) int event; rcu_read_lock(); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && dump_ctx->ctx.family != table->family) continue; @@ -4995,6 +5046,7 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set_elem *elem, int event, u16 flags) { + struct nftables_pernet *nft_net; struct net *net = ctx->net; u32 portid = ctx->portid; struct sk_buff *skb; @@ -5014,7 +5066,8 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_net = net_generic(net, nf_tables_net_id); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -5410,7 +5463,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_set_full: @@ -5441,6 +5494,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); u8 genmask = nft_genmask_next(net); const struct nlattr *attr; struct nft_set *set; @@ -5470,7 +5524,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, return err; } - if (net->nft.validate_state == NFT_VALIDATE_DO) + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, ctx.table); return 0; @@ -5606,7 +5660,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, nft_set_elem_deactivate(ctx->net, set, &elem); nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; fail_ops: @@ -5640,7 +5694,7 @@ static int nft_flush_set(const struct nft_ctx *ctx, nft_set_elem_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err1: @@ -5939,7 +5993,7 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, nft_trans_obj(trans) = obj; nft_trans_obj_update(trans) = true; nft_trans_obj_newobj(trans) = newobj; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -6102,6 +6156,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) struct nft_obj_filter *filter = cb->data; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; struct nft_object *obj; bool reset = false; @@ -6109,9 +6164,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) reset = true; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -6134,7 +6190,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, - net->nft.base_seq); + nft_net->base_seq); audit_log_nfcfg(buf, family, @@ -6255,8 +6311,11 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, reset = true; if (reset) { - char *buf = kasprintf(GFP_ATOMIC, "%s:%u", - table->name, net->nft.base_seq); + const struct nftables_pernet *nft_net; + char *buf; + + nft_net = net_generic(net, nf_tables_net_id); + buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); audit_log_nfcfg(buf, family, @@ -6341,10 +6400,11 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, int family, int report, gfp_t gfp) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct sk_buff *skb; int err; char *buf = kasprintf(gfp, "%s:%u", - table->name, net->nft.base_seq); + table->name, nft_net->base_seq); audit_log_nfcfg(buf, family, @@ -6370,7 +6430,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, goto err; } - nft_notify_enqueue(skb, report, &net->nft.notify_list); + nft_notify_enqueue(skb, report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -6706,7 +6766,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); list_splice(&flowtable_hook.list, &nft_trans_flowtable_hooks(trans)); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -6896,7 +6956,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, list_splice(&flowtable_del_list, &nft_trans_flowtable_hooks(trans)); nft_flowtable_hook_release(&flowtable_hook); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -7022,12 +7082,14 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; const struct nft_table *table; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -7162,6 +7224,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, struct list_head *hook_list, int event) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct sk_buff *skb; int err; @@ -7181,7 +7244,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -7206,6 +7269,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nlmsghdr *nlh; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); @@ -7215,7 +7279,7 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, if (!nlh) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)) || + if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; @@ -7250,6 +7314,7 @@ static int nf_tables_flowtable_event(struct notifier_block *this, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; struct nft_table *table; struct net *net; @@ -7257,13 +7322,14 @@ static int nf_tables_flowtable_event(struct notifier_block *this, return 0; net = dev_net(dev); - mutex_lock(&net->nft.commit_mutex); - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(flowtable, &table->flowtables, list) { nft_flowtable_event(event, dev, flowtable); } } - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } @@ -7444,16 +7510,17 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { static int nf_tables_validate(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_table *table; - switch (net->nft.validate_state) { + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: break; case NFT_VALIDATE_NEED: nft_validate_state_update(net, NFT_VALIDATE_DO); fallthrough; case NFT_VALIDATE_DO: - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_validate(net, table) < 0) return -EAGAIN; } @@ -7630,9 +7697,10 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha static void nf_tables_commit_chain_prepare_cancel(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWRULE || @@ -7730,10 +7798,11 @@ void nft_chain_del(struct nft_chain *chain) static void nf_tables_module_autoload_cleanup(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_module_request *req, *next; - WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); - list_for_each_entry_safe(req, next, &net->nft.module_list, list) { + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + list_for_each_entry_safe(req, next, &nft_net->module_list, list) { WARN_ON_ONCE(!req->done); list_del(&req->list); kfree(req); @@ -7742,6 +7811,7 @@ static void nf_tables_module_autoload_cleanup(struct net *net) static void nf_tables_commit_release(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans; /* all side effects have to be made visible. @@ -7751,35 +7821,36 @@ static void nf_tables_commit_release(struct net *net) * Memory reclaim happens asynchronously from work queue * to prevent expensive synchronize_rcu() in commit phase. */ - if (list_empty(&net->nft.commit_list)) { + if (list_empty(&nft_net->commit_list)) { nf_tables_module_autoload_cleanup(net); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return; } - trans = list_last_entry(&net->nft.commit_list, + trans = list_last_entry(&nft_net->commit_list, struct nft_trans, list); get_net(trans->ctx.net); WARN_ON_ONCE(trans->put_net); trans->put_net = true; spin_lock(&nf_tables_destroy_list_lock); - list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list); + list_splice_tail_init(&nft_net->commit_list, &nf_tables_destroy_list); spin_unlock(&nf_tables_destroy_list_lock); nf_tables_module_autoload_cleanup(net); schedule_work(&trans_destroy_work); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); } static void nft_commit_notify(struct net *net, u32 portid) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct sk_buff *batch_skb = NULL, *nskb, *skb; unsigned char *data; int len; - list_for_each_entry_safe(skb, nskb, &net->nft.notify_list, list) { + list_for_each_entry_safe(skb, nskb, &nft_net->notify_list, list) { if (!batch_skb) { new_batch: batch_skb = skb; @@ -7805,7 +7876,7 @@ new_batch: NFT_CB(batch_skb).report, GFP_KERNEL); } - WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); + WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } static int nf_tables_commit_audit_alloc(struct list_head *adl, @@ -7871,6 +7942,7 @@ static void nf_tables_commit_audit_log(struct list_head *adl, u32 generation) static int nf_tables_commit(struct net *net, struct sk_buff *skb) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; struct nft_trans_elem *te; struct nft_chain *chain; @@ -7878,8 +7950,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) LIST_HEAD(adl); int err; - if (list_empty(&net->nft.commit_list)) { - mutex_unlock(&net->nft.commit_mutex); + if (list_empty(&nft_net->commit_list)) { + mutex_unlock(&nft_net->commit_mutex); return 0; } @@ -7892,7 +7964,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return err; /* 1. Allocate space for next generation rules_gen_X[] */ - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { int ret; ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); @@ -7915,7 +7987,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } /* step 2. Make rules_gen_X visible to packet path */ - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(chain, &table->chains, list) nf_tables_commit_chain(net, chain); } @@ -7924,12 +7996,13 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ - while (++net->nft.base_seq == 0); + while (++nft_net->base_seq == 0) + ; /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { nf_tables_commit_audit_collect(&adl, trans->ctx.table, trans->msg_type); switch (trans->msg_type) { @@ -8089,7 +8162,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); - nf_tables_commit_audit_log(&adl, net->nft.base_seq); + nf_tables_commit_audit_log(&adl, nft_net->base_seq); nf_tables_commit_release(net); return 0; @@ -8097,17 +8170,18 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) static void nf_tables_module_autoload(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_module_request *req, *next; LIST_HEAD(module_list); - list_splice_init(&net->nft.module_list, &module_list); - mutex_unlock(&net->nft.commit_mutex); + list_splice_init(&nft_net->module_list, &module_list); + mutex_unlock(&nft_net->commit_mutex); list_for_each_entry_safe(req, next, &module_list, list) { request_module("%s", req->module); req->done = true; } - mutex_lock(&net->nft.commit_mutex); - list_splice(&module_list, &net->nft.module_list); + mutex_lock(&nft_net->commit_mutex); + list_splice(&module_list, &nft_net->module_list); } static void nf_tables_abort_release(struct nft_trans *trans) @@ -8144,6 +8218,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; struct nft_trans_elem *te; @@ -8151,7 +8226,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nf_tables_validate(net) < 0) return -EAGAIN; - list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, + list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: @@ -8277,7 +8352,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) synchronize_rcu(); list_for_each_entry_safe_reverse(trans, next, - &net->nft.commit_list, list) { + &nft_net->commit_list, list) { list_del(&trans->list); nf_tables_abort_release(trans); } @@ -8293,22 +8368,24 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) static int nf_tables_abort(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); int ret = __nf_tables_abort(net, action); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return ret; } static bool nf_tables_valid_genid(struct net *net, u32 genid) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); bool genid_ok; - mutex_lock(&net->nft.commit_mutex); + mutex_lock(&nft_net->commit_mutex); - genid_ok = genid == 0 || net->nft.base_seq == genid; + genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); /* else, commit mutex has to be released by commit or abort function */ return genid_ok; @@ -8909,19 +8986,19 @@ EXPORT_SYMBOL_GPL(__nft_release_basechain); static void __nft_release_hooks(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_table *table; struct nft_chain *chain; - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(chain, &table->chains, list) nf_tables_unregister_hook(net, table, chain); } } -static void __nft_release_tables(struct net *net) +static void __nft_release_table(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable, *nf; - struct nft_table *table, *nt; struct nft_chain *chain, *nc; struct nft_object *obj, *ne; struct nft_rule *rule, *nr; @@ -8931,79 +9008,94 @@ static void __nft_release_tables(struct net *net) .family = NFPROTO_NETDEV, }; - list_for_each_entry_safe(table, nt, &net->nft.tables, list) { - ctx.family = table->family; - ctx.table = table; - list_for_each_entry(chain, &table->chains, list) { - ctx.chain = chain; - list_for_each_entry_safe(rule, nr, &chain->rules, list) { - list_del(&rule->list); - chain->use--; - nf_tables_rule_release(&ctx, rule); - } + ctx.family = table->family; + ctx.table = table; + list_for_each_entry(chain, &table->chains, list) { + ctx.chain = chain; + list_for_each_entry_safe(rule, nr, &chain->rules, list) { + list_del(&rule->list); + chain->use--; + nf_tables_rule_release(&ctx, rule); } - list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { - list_del(&flowtable->list); - table->use--; - nf_tables_flowtable_destroy(flowtable); - } - list_for_each_entry_safe(set, ns, &table->sets, list) { - list_del(&set->list); - table->use--; - nft_set_destroy(&ctx, set); - } - list_for_each_entry_safe(obj, ne, &table->objects, list) { - nft_obj_del(obj); - table->use--; - nft_obj_destroy(&ctx, obj); - } - list_for_each_entry_safe(chain, nc, &table->chains, list) { - ctx.chain = chain; - nft_chain_del(chain); - table->use--; - nf_tables_chain_destroy(&ctx); - } - list_del(&table->list); - nf_tables_table_destroy(&ctx); } + list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { + list_del(&flowtable->list); + table->use--; + nf_tables_flowtable_destroy(flowtable); + } + list_for_each_entry_safe(set, ns, &table->sets, list) { + list_del(&set->list); + table->use--; + nft_set_destroy(&ctx, set); + } + list_for_each_entry_safe(obj, ne, &table->objects, list) { + nft_obj_del(obj); + table->use--; + nft_obj_destroy(&ctx, obj); + } + list_for_each_entry_safe(chain, nc, &table->chains, list) { + ctx.chain = chain; + nft_chain_del(chain); + table->use--; + nf_tables_chain_destroy(&ctx); + } + list_del(&table->list); + nf_tables_table_destroy(&ctx); +} + +static void __nft_release_tables(struct net *net) +{ + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + struct nft_table *table, *nt; + + list_for_each_entry_safe(table, nt, &nft_net->tables, list) + __nft_release_table(net, table); } static int __net_init nf_tables_init_net(struct net *net) { - INIT_LIST_HEAD(&net->nft.tables); - INIT_LIST_HEAD(&net->nft.commit_list); - INIT_LIST_HEAD(&net->nft.module_list); - INIT_LIST_HEAD(&net->nft.notify_list); - mutex_init(&net->nft.commit_mutex); - net->nft.base_seq = 1; - net->nft.validate_state = NFT_VALIDATE_SKIP; + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + INIT_LIST_HEAD(&nft_net->tables); + INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->module_list); + INIT_LIST_HEAD(&nft_net->notify_list); + mutex_init(&nft_net->commit_mutex); + nft_net->base_seq = 1; + nft_net->validate_state = NFT_VALIDATE_SKIP; return 0; } static void __net_exit nf_tables_pre_exit_net(struct net *net) { - mutex_lock(&net->nft.commit_mutex); + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + mutex_lock(&nft_net->commit_mutex); __nft_release_hooks(net); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); } static void __net_exit nf_tables_exit_net(struct net *net) { - mutex_lock(&net->nft.commit_mutex); - if (!list_empty(&net->nft.commit_list)) + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + mutex_lock(&nft_net->commit_mutex); + if (!list_empty(&nft_net->commit_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); __nft_release_tables(net); - mutex_unlock(&net->nft.commit_mutex); - WARN_ON_ONCE(!list_empty(&net->nft.tables)); - WARN_ON_ONCE(!list_empty(&net->nft.module_list)); - WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); + mutex_unlock(&nft_net->commit_mutex); + WARN_ON_ONCE(!list_empty(&nft_net->tables)); + WARN_ON_ONCE(!list_empty(&nft_net->module_list)); + WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, + .id = &nf_tables_net_id, + .size = sizeof(struct nftables_pernet), }; static int __init nf_tables_module_init(void) diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 4e99b1731b3f..5cfbb29d8a34 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -7,6 +7,8 @@ #include #include +extern unsigned int nf_tables_net_id; + static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) { struct nft_flow_rule *flow; @@ -371,16 +373,18 @@ static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; + struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); - mutex_lock(&net->nft.commit_mutex); + nft_net = net_generic(net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, @@ -476,9 +480,10 @@ static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); int err = 0; - list_for_each_entry_continue_reverse(trans, &net->nft.commit_list, list) { + list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; @@ -524,11 +529,12 @@ static void nft_flow_rule_offload_abort(struct net *net, int nft_flow_rule_offload_commit(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans; int err = 0; u8 policy; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; @@ -580,7 +586,7 @@ int nft_flow_rule_offload_commit(struct net *net) } } - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; @@ -600,15 +606,15 @@ int nft_flow_rule_offload_commit(struct net *net) return err; } -static struct nft_chain *__nft_offload_get_chain(struct net_device *dev) +static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, + struct net_device *dev) { struct nft_base_chain *basechain; - struct net *net = dev_net(dev); struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; @@ -640,19 +646,21 @@ static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - mutex_lock(&net->nft.commit_mutex); - chain = __nft_offload_get_chain(dev); + nft_net = net_generic(net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); + chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index ff8528ad3dc6..7a9aa57b195b 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include #include @@ -10,6 +11,8 @@ #include #include +extern unsigned int nf_tables_net_id; + #ifdef CONFIG_NF_TABLES_IPV4 static unsigned int nft_do_chain_ipv4(void *priv, struct sk_buff *skb, @@ -355,6 +358,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nftables_pernet *nft_net; struct nft_table *table; struct nft_chain *chain, *nr; struct nft_ctx ctx = { @@ -365,8 +369,9 @@ static int nf_tables_netdev_event(struct notifier_block *this, event != NETDEV_CHANGENAME) return NOTIFY_DONE; - mutex_lock(&ctx.net->nft.commit_mutex); - list_for_each_entry(table, &ctx.net->nft.tables, list) { + nft_net = net_generic(ctx.net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; @@ -380,7 +385,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, nft_netdev_event(event, dev, &ctx); } } - mutex_unlock(&ctx.net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 038588d4d80e..8d47782b778f 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -11,6 +11,9 @@ #include #include #include +#include + +extern unsigned int nf_tables_net_id; struct nft_dynset { struct nft_set *set; @@ -106,13 +109,14 @@ static int nft_dynset_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct nft_dynset *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_set *set; u64 timeout; int err; - lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); if (tb[NFTA_DYNSET_SET_NAME] == NULL || tb[NFTA_DYNSET_OP] == NULL || From e546e6ebb19d89a79d0569e968fc788879f86e5d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Jul 2023 10:48:50 +0200 Subject: [PATCH 4046/4345] netfilter: nf_tables: add rescheduling points during loop detection walks [ Upstream commit 81ea010667417ef3f218dfd99b69769fe66c2b67 ] Add explicit rescheduling points during ruleset walk. Switching to a faster algorithm is possible but this is a much smaller change, suitable for nf tree. Link: https://bugzilla.netfilter.org/show_bug.cgi?id=1460 Signed-off-by: Florian Westphal Acked-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e3865f29ae83..3c9292d3f826 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3164,6 +3164,8 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } + + cond_resched(); } return 0; @@ -8506,9 +8508,13 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, break; } } + + cond_resched(); } list_for_each_entry(set, &ctx->table->sets, list) { + cond_resched(); + if (!nft_is_active_next(ctx->net, set)) continue; if (!(set->flags & NFT_SET_MAP) || From 8180fc2fadd48dde4966f2db2c716c2ce7510d0b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 13 Jul 2023 10:48:51 +0200 Subject: [PATCH 4047/4345] netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE [ Upstream commit 1240eb93f0616b21c675416516ff3d74798fdc97 ] In case of error when adding a new rule that refers to an anonymous set, deactivate expressions via NFT_TRANS_PREPARE state, not NFT_TRANS_RELEASE. Thus, the lookup expression marks anonymous sets as inactive in the next generation to ensure it is not reachable in this transaction anymore and decrement the set refcount as introduced by c1592a89942e ("netfilter: nf_tables: deactivate anonymous set from preparation phase"). The abort step takes care of undoing the anonymous set. This is also consistent with rule deletion, where NFT_TRANS_PREPARE is used. Note that this error path is exercised in the preparation step of the commit protocol. This patch replaces nf_tables_rule_release() by the deactivate and destroy calls, this time with NFT_TRANS_PREPARE. Due to this incorrect error handling, it is possible to access a dangling pointer to the anonymous set that remains in the transaction list. [1009.379054] BUG: KASAN: use-after-free in nft_set_lookup_global+0x147/0x1a0 [nf_tables] [1009.379106] Read of size 8 at addr ffff88816c4c8020 by task nft-rule-add/137110 [1009.379116] CPU: 7 PID: 137110 Comm: nft-rule-add Not tainted 6.4.0-rc4+ #256 [1009.379128] Call Trace: [1009.379132] [1009.379135] dump_stack_lvl+0x33/0x50 [1009.379146] ? nft_set_lookup_global+0x147/0x1a0 [nf_tables] [1009.379191] print_address_description.constprop.0+0x27/0x300 [1009.379201] kasan_report+0x107/0x120 [1009.379210] ? nft_set_lookup_global+0x147/0x1a0 [nf_tables] [1009.379255] nft_set_lookup_global+0x147/0x1a0 [nf_tables] [1009.379302] nft_lookup_init+0xa5/0x270 [nf_tables] [1009.379350] nf_tables_newrule+0x698/0xe50 [nf_tables] [1009.379397] ? nf_tables_rule_release+0xe0/0xe0 [nf_tables] [1009.379441] ? kasan_unpoison+0x23/0x50 [1009.379450] nfnetlink_rcv_batch+0x97c/0xd90 [nfnetlink] [1009.379470] ? nfnetlink_rcv_msg+0x480/0x480 [nfnetlink] [1009.379485] ? __alloc_skb+0xb8/0x1e0 [1009.379493] ? __alloc_skb+0xb8/0x1e0 [1009.379502] ? entry_SYSCALL_64_after_hwframe+0x46/0xb0 [1009.379509] ? unwind_get_return_address+0x2a/0x40 [1009.379517] ? write_profile+0xc0/0xc0 [1009.379524] ? avc_lookup+0x8f/0xc0 [1009.379532] ? __rcu_read_unlock+0x43/0x60 Fixes: 958bee14d071 ("netfilter: nf_tables: use new transaction infrastructure to handle sets") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3c9292d3f826..b32838974ff1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3409,7 +3409,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return 0; err2: - nf_tables_rule_release(&ctx, rule); + nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE); + nf_tables_rule_destroy(&ctx, rule); err1: for (i = 0; i < n; i++) { if (info[i].ops) { From d53c295c1f43b7460d28ba0f0f98a602084fdcb6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 13 Jul 2023 10:48:52 +0200 Subject: [PATCH 4048/4345] netfilter: nf_tables: fix chain binding transaction logic [ Upstream commit 4bedf9eee016286c835e3d8fa981ddece5338795 ] Add bound flag to rule and chain transactions as in 6a0a8d10a366 ("netfilter: nf_tables: use-after-free in failing rule with bound set") to skip them in case that the chain is already bound from the abort path. This patch fixes an imbalance in the chain use refcnt that triggers a WARN_ON on the table and chain destroy path. This patch also disallows nested chain bindings, which is not supported from userspace. The logic to deal with chain binding in nft_data_hold() and nft_data_release() is not correct. The NFT_TRANS_PREPARE state needs a special handling in case a chain is bound but next expressions in the same rule fail to initialize as described by 1240eb93f061 ("netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE"). The chain is left bound if rule construction fails, so the objects stored in this chain (and the chain itself) are released by the transaction records from the abort path, follow up patch ("netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain") completes this error handling. When deleting an existing rule, chain bound flag is set off so the rule expression .destroy path releases the objects. Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 21 +++++++- net/netfilter/nf_tables_api.c | 86 +++++++++++++++++++----------- net/netfilter/nft_immediate.c | 87 +++++++++++++++++++++++++++---- 3 files changed, 153 insertions(+), 41 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5e184c20bc55..28b3d4fbebae 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -907,7 +907,10 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) return (void *)&rule->data[rule->dlen]; } -void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, + enum nft_trans_phase phase); +void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule); static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, struct nft_regs *regs, @@ -966,6 +969,7 @@ struct nft_chain { }; int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); +int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, @@ -1002,11 +1006,17 @@ int nft_chain_validate_dependency(const struct nft_chain *chain, int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags); +static inline bool nft_chain_binding(const struct nft_chain *chain) +{ + return chain->flags & NFT_CHAIN_BINDING; +} + static inline bool nft_chain_is_bound(struct nft_chain *chain) { return (chain->flags & NFT_CHAIN_BINDING) && chain->bound; } +int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); void nf_tables_chain_destroy(struct nft_ctx *ctx); @@ -1431,6 +1441,7 @@ struct nft_trans_rule { struct nft_rule *rule; struct nft_flow_rule *flow; u32 rule_id; + bool bound; }; #define nft_trans_rule(trans) \ @@ -1439,6 +1450,8 @@ struct nft_trans_rule { (((struct nft_trans_rule *)trans->data)->flow) #define nft_trans_rule_id(trans) \ (((struct nft_trans_rule *)trans->data)->rule_id) +#define nft_trans_rule_bound(trans) \ + (((struct nft_trans_rule *)trans->data)->bound) struct nft_trans_set { struct nft_set *set; @@ -1454,13 +1467,17 @@ struct nft_trans_set { (((struct nft_trans_set *)trans->data)->bound) struct nft_trans_chain { + struct nft_chain *chain; bool update; char *name; struct nft_stats __percpu *stats; u8 policy; + bool bound; u32 chain_id; }; +#define nft_trans_chain(trans) \ + (((struct nft_trans_chain *)trans->data)->chain) #define nft_trans_chain_update(trans) \ (((struct nft_trans_chain *)trans->data)->update) #define nft_trans_chain_name(trans) \ @@ -1469,6 +1486,8 @@ struct nft_trans_chain { (((struct nft_trans_chain *)trans->data)->stats) #define nft_trans_chain_policy(trans) \ (((struct nft_trans_chain *)trans->data)->policy) +#define nft_trans_chain_bound(trans) \ + (((struct nft_trans_chain *)trans->data)->bound) #define nft_trans_chain_id(trans) \ (((struct nft_trans_chain *)trans->data)->chain_id) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index b32838974ff1..10ec55f3f80a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -197,6 +197,48 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) } } +static void nft_chain_trans_bind(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + struct nftables_pernet *nft_net; + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_chain_binding(chain)) + return; + + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { + switch (trans->msg_type) { + case NFT_MSG_NEWCHAIN: + if (nft_trans_chain(trans) == chain) + nft_trans_chain_bound(trans) = true; + break; + case NFT_MSG_NEWRULE: + if (trans->ctx.chain == chain) + nft_trans_rule_bound(trans) = true; + break; + } + } +} + +int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + if (!nft_chain_binding(chain)) + return 0; + + if (nft_chain_binding(ctx->chain)) + return -EOPNOTSUPP; + + if (chain->bound) + return -EBUSY; + + chain->bound = true; + chain->use++; + nft_chain_trans_bind(ctx, chain); + + return 0; +} + static int nft_netdev_register_hooks(struct net *net, struct list_head *hook_list) { @@ -328,8 +370,9 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID])); } } - + nft_trans_chain(trans) = ctx->chain; nft_trans_commit_list_add_tail(ctx->net, trans); + return trans; } @@ -347,8 +390,7 @@ static int nft_delchain(struct nft_ctx *ctx) return 0; } -static void nft_rule_expr_activate(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr; @@ -361,9 +403,8 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } } -static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule, - enum nft_trans_phase phase) +void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr; @@ -2017,7 +2058,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, return 0; } -static int nft_chain_add(struct nft_table *table, struct nft_chain *chain) +int nft_chain_add(struct nft_table *table, struct nft_chain *chain) { int err; @@ -3118,8 +3159,7 @@ err_fill_rule_info: return err; } -static void nf_tables_rule_destroy(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr, *next; @@ -3136,7 +3176,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, kfree(rule); } -void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) +static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); @@ -5547,7 +5587,6 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { struct nft_chain *chain; - struct nft_rule *rule; if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { @@ -5555,15 +5594,6 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) case NFT_GOTO: chain = data->verdict.chain; chain->use++; - - if (!nft_chain_is_bound(chain)) - break; - - chain->table->use++; - list_for_each_entry(rule, &chain->rules, list) - chain->use++; - - nft_chain_add(chain->table, chain); break; } } @@ -8254,7 +8284,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { - if (nft_chain_is_bound(trans->ctx.chain)) { + if (nft_trans_chain_bound(trans)) { nft_trans_destroy(trans); break; } @@ -8271,6 +8301,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: + if (nft_trans_rule_bound(trans)) { + nft_trans_destroy(trans); + break; + } trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, @@ -8796,22 +8830,12 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, static void nft_verdict_uninit(const struct nft_data *data) { struct nft_chain *chain; - struct nft_rule *rule; switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; chain->use--; - - if (!nft_chain_is_bound(chain)) - break; - - chain->table->use--; - list_for_each_entry(rule, &chain->rules, list) - chain->use--; - - nft_chain_del(chain); break; } } diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index fcdbc5ed3f36..9d4248898ce4 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -76,11 +76,9 @@ static int nft_immediate_init(const struct nft_ctx *ctx, switch (priv->data.verdict.code) { case NFT_JUMP: case NFT_GOTO: - if (nft_chain_is_bound(chain)) { - err = -EBUSY; - goto err1; - } - chain->bound = true; + err = nf_tables_bind_chain(ctx, chain); + if (err < 0) + return err; break; default: break; @@ -98,6 +96,31 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data = &priv->data; + struct nft_ctx chain_ctx; + struct nft_chain *chain; + struct nft_rule *rule; + + if (priv->dreg == NFT_REG_VERDICT) { + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + chain = data->verdict.chain; + if (!nft_chain_binding(chain)) + break; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nft_rule_expr_activate(&chain_ctx, rule); + + nft_clear(ctx->net, chain); + break; + default: + break; + } + } return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg)); } @@ -107,6 +130,40 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data = &priv->data; + struct nft_ctx chain_ctx; + struct nft_chain *chain; + struct nft_rule *rule; + + if (priv->dreg == NFT_REG_VERDICT) { + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + chain = data->verdict.chain; + if (!nft_chain_binding(chain)) + break; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nft_rule_expr_deactivate(&chain_ctx, rule, phase); + + switch (phase) { + case NFT_TRANS_PREPARE: + nft_deactivate_next(ctx->net, chain); + break; + default: + nft_chain_del(chain); + chain->bound = false; + chain->table->use--; + break; + } + break; + default: + break; + } + } if (phase == NFT_TRANS_COMMIT) return; @@ -131,15 +188,27 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, case NFT_GOTO: chain = data->verdict.chain; - if (!nft_chain_is_bound(chain)) + if (!nft_chain_binding(chain)) break; + /* Rule construction failed, but chain is already bound: + * let the transaction records release this chain and its rules. + */ + if (chain->bound) { + chain->use--; + break; + } + + /* Rule has been deleted, release chain and its rules. */ chain_ctx = *ctx; chain_ctx.chain = chain; - list_for_each_entry_safe(rule, n, &chain->rules, list) - nf_tables_rule_release(&chain_ctx, rule); - + chain->use--; + list_for_each_entry_safe(rule, n, &chain->rules, list) { + chain->use--; + list_del(&rule->list); + nf_tables_rule_destroy(&chain_ctx, rule); + } nf_tables_chain_destroy(&chain_ctx); break; default: From 34d09fe49f59d3d7cb79ace1785b138b3b8d9e52 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 13 Jul 2023 10:48:53 +0200 Subject: [PATCH 4049/4345] netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain [ Upstream commit 26b5a5712eb85e253724e56a54c17f8519bd8e4e ] Add a new state to deal with rule expressions deactivation from the newrule error path, otherwise the anonymous set remains in the list in inactive state for the next generation. Mark the set/chain transaction as unbound so the abort path releases this object, set it as inactive in the next generation so it is not reachable anymore from this transaction and reference counter is dropped. Fixes: 1240eb93f061 ("netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 2 ++ net/netfilter/nf_tables_api.c | 45 ++++++++++++++++++++++++++----- net/netfilter/nft_immediate.c | 3 +++ 3 files changed, 43 insertions(+), 7 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 28b3d4fbebae..03886052491e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -777,6 +777,7 @@ struct nft_expr_type { enum nft_trans_phase { NFT_TRANS_PREPARE, + NFT_TRANS_PREPARE_ERROR, NFT_TRANS_ABORT, NFT_TRANS_COMMIT, NFT_TRANS_RELEASE @@ -970,6 +971,7 @@ struct nft_chain { int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); +void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 10ec55f3f80a..c646537efaf5 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -173,7 +173,8 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } -static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +static void __nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set, + bool bind) { struct nftables_pernet *nft_net; struct net *net = ctx->net; @@ -187,17 +188,28 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) switch (trans->msg_type) { case NFT_MSG_NEWSET: if (nft_trans_set(trans) == set) - nft_trans_set_bound(trans) = true; + nft_trans_set_bound(trans) = bind; break; case NFT_MSG_NEWSETELEM: if (nft_trans_elem_set(trans) == set) - nft_trans_elem_set_bound(trans) = true; + nft_trans_elem_set_bound(trans) = bind; break; } } } -static void nft_chain_trans_bind(const struct nft_ctx *ctx, struct nft_chain *chain) +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + return __nft_set_trans_bind(ctx, set, true); +} + +static void nft_set_trans_unbind(const struct nft_ctx *ctx, struct nft_set *set) +{ + return __nft_set_trans_bind(ctx, set, false); +} + +static void __nft_chain_trans_bind(const struct nft_ctx *ctx, + struct nft_chain *chain, bool bind) { struct nftables_pernet *nft_net; struct net *net = ctx->net; @@ -211,16 +223,22 @@ static void nft_chain_trans_bind(const struct nft_ctx *ctx, struct nft_chain *ch switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (nft_trans_chain(trans) == chain) - nft_trans_chain_bound(trans) = true; + nft_trans_chain_bound(trans) = bind; break; case NFT_MSG_NEWRULE: if (trans->ctx.chain == chain) - nft_trans_rule_bound(trans) = true; + nft_trans_rule_bound(trans) = bind; break; } } } +static void nft_chain_trans_bind(const struct nft_ctx *ctx, + struct nft_chain *chain) +{ + __nft_chain_trans_bind(ctx, chain, true); +} + int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) { if (!nft_chain_binding(chain)) @@ -239,6 +257,11 @@ int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) return 0; } +void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + __nft_chain_trans_bind(ctx, chain, false); +} + static int nft_netdev_register_hooks(struct net *net, struct list_head *hook_list) { @@ -3449,7 +3472,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return 0; err2: - nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE); + nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE_ERROR); nf_tables_rule_destroy(&ctx, rule); err1: for (i = 0; i < n; i++) { @@ -4585,6 +4608,13 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, enum nft_trans_phase phase) { switch (phase) { + case NFT_TRANS_PREPARE_ERROR: + nft_set_trans_unbind(ctx, set); + if (nft_set_is_anonymous(set)) + nft_deactivate_next(ctx->net, set); + + set->use--; + break; case NFT_TRANS_PREPARE: if (nft_set_is_anonymous(set)) nft_deactivate_next(ctx->net, set); @@ -6525,6 +6555,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, enum nft_trans_phase phase) { switch (phase) { + case NFT_TRANS_PREPARE_ERROR: case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 9d4248898ce4..6b0efab4fad0 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -150,6 +150,9 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, nft_rule_expr_deactivate(&chain_ctx, rule, phase); switch (phase) { + case NFT_TRANS_PREPARE_ERROR: + nf_tables_unbind_chain(ctx, chain); + fallthrough; case NFT_TRANS_PREPARE: nft_deactivate_next(ctx->net, chain); break; From 0205dd16edebee8074ac53cc67de98d959a24b60 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 13 Jul 2023 10:48:54 +0200 Subject: [PATCH 4050/4345] netfilter: nf_tables: reject unbound anonymous set before commit phase [ Upstream commit 938154b93be8cd611ddfd7bafc1849f3c4355201 ] Add a new list to track set transaction and to check for unbound anonymous sets before entering the commit phase. Bail out at the end of the transaction handling if an anonymous set remains unbound. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 3 +++ net/netfilter/nf_tables_api.c | 34 ++++++++++++++++++++++++++++--- 2 files changed, 34 insertions(+), 3 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 03886052491e..716a974a7263 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1426,6 +1426,7 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) * struct nft_trans - nf_tables object update in transaction * * @list: used internally + * @binding_list: list of objects with possible bindings * @msg_type: message type * @put_net: ctx->net needs to be put * @ctx: transaction context @@ -1433,6 +1434,7 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) */ struct nft_trans { struct list_head list; + struct list_head binding_list; int msg_type; bool put_net; struct nft_ctx ctx; @@ -1559,6 +1561,7 @@ __be64 nf_jiffies64_to_msecs(u64 input); struct nftables_pernet { struct list_head tables; struct list_head commit_list; + struct list_head binding_list; struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c646537efaf5..ff65de8119c3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -155,6 +155,7 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, return NULL; INIT_LIST_HEAD(&trans->list); + INIT_LIST_HEAD(&trans->binding_list); trans->msg_type = msg_type; trans->ctx = *ctx; @@ -167,9 +168,15 @@ static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx, return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL); } -static void nft_trans_destroy(struct nft_trans *trans) +static void nft_trans_list_del(struct nft_trans *trans) { list_del(&trans->list); + list_del(&trans->binding_list); +} + +static void nft_trans_destroy(struct nft_trans *trans) +{ + nft_trans_list_del(trans); kfree(trans); } @@ -347,6 +354,14 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr struct nftables_pernet *nft_net; nft_net = net_generic(net, nf_tables_net_id); + + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (nft_set_is_anonymous(nft_trans_set(trans))) + list_add_tail(&trans->binding_list, &nft_net->binding_list); + break; + } + list_add_tail(&trans->list, &nft_net->commit_list); } @@ -7717,7 +7732,7 @@ static void nf_tables_trans_destroy_work(struct work_struct *w) synchronize_rcu(); list_for_each_entry_safe(trans, next, &head, list) { - list_del(&trans->list); + nft_trans_list_del(trans); nft_commit_release(trans); } } @@ -8019,6 +8034,18 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return 0; } + list_for_each_entry(trans, &nft_net->binding_list, binding_list) { + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (nft_set_is_anonymous(nft_trans_set(trans)) && + !nft_trans_set_bound(trans)) { + pr_warn_once("nftables ruleset with unbound set\n"); + return -EINVAL; + } + break; + } + } + /* 0. Validate ruleset, otherwise roll back for error reporting. */ if (nf_tables_validate(net) < 0) return -EAGAIN; @@ -8421,7 +8448,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { - list_del(&trans->list); + nft_trans_list_del(trans); nf_tables_abort_release(trans); } @@ -9120,6 +9147,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->tables); INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->binding_list); INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); From 237f37f7b9f075c34bf0468c390cdd7e2725d8b0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 13 Jul 2023 10:48:55 +0200 Subject: [PATCH 4051/4345] netfilter: nf_tables: reject unbound chain set before commit phase [ Upstream commit 62e1e94b246e685d89c3163aaef4b160e42ceb02 ] Use binding list to track set transaction and to check for unbound chains before entering the commit phase. Bail out if chain binding remain unused before entering the commit step. Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ff65de8119c3..ef965056bcca 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -360,6 +360,11 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr if (nft_set_is_anonymous(nft_trans_set(trans))) list_add_tail(&trans->binding_list, &nft_net->binding_list); break; + case NFT_MSG_NEWCHAIN: + if (!nft_trans_chain_update(trans) && + nft_chain_binding(nft_trans_chain(trans))) + list_add_tail(&trans->binding_list, &nft_net->binding_list); + break; } list_add_tail(&trans->list, &nft_net->commit_list); @@ -8043,6 +8048,14 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return -EINVAL; } break; + case NFT_MSG_NEWCHAIN: + if (!nft_trans_chain_update(trans) && + nft_chain_binding(nft_trans_chain(trans)) && + !nft_trans_chain_bound(trans)) { + pr_warn_once("nftables ruleset with unbound chain\n"); + return -EINVAL; + } + break; } } From 21cf0d66ef889f8e1f7181cb8960554142396912 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 13 Jul 2023 10:48:56 +0200 Subject: [PATCH 4052/4345] netfilter: nftables: rename set element data activation/deactivation functions [ Upstream commit f8bb7889af58d8e74d2d61c76b1418230f1610fa ] Rename: - nft_set_elem_activate() to nft_set_elem_data_activate(). - nft_set_elem_deactivate() to nft_set_elem_data_deactivate(). To prepare for updates in the set element infrastructure to add support for the special catch-all element. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ef965056bcca..5af9290af34f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5270,8 +5270,8 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); -/* Only called from commit path, nft_set_elem_deactivate() already deals with - * the refcounting from the preparation phase. +/* Only called from commit path, nft_setelem_data_deactivate() already deals + * with the refcounting from the preparation phase. */ static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, void *elem) @@ -5649,9 +5649,9 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) } } -static void nft_set_elem_activate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5661,9 +5661,9 @@ static void nft_set_elem_activate(const struct net *net, (*nft_set_ext_obj(ext))->use++; } -static void nft_set_elem_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5740,7 +5740,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, kfree(elem.priv); elem.priv = priv; - nft_set_elem_deactivate(ctx->net, set, &elem); + nft_setelem_data_deactivate(ctx->net, set, &elem); nft_trans_elem(trans) = elem; nft_trans_commit_list_add_tail(ctx->net, trans); @@ -5774,7 +5774,7 @@ static int nft_flush_set(const struct nft_ctx *ctx, } set->ndeact++; - nft_set_elem_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; nft_trans_commit_list_add_tail(ctx->net, trans); @@ -8413,7 +8413,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_set_elem_activate(net, te->set, &te->elem); + nft_setelem_data_activate(net, te->set, &te->elem); te->set->ops->activate(net, te->set, &te->elem); te->set->ndeact--; From a136b7942ad2a50de708f76ea299ccb45ac7a7f9 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 13 Jul 2023 10:48:57 +0200 Subject: [PATCH 4053/4345] netfilter: nf_tables: drop map element references from preparation phase [ Upstream commit 628bd3e49cba1c066228e23d71a852c23e26da73 ] set .destroy callback releases the references to other objects in maps. This is very late and it results in spurious EBUSY errors. Drop refcount from the preparation phase instead, update set backend not to drop reference counter from set .destroy path. Exceptions: NFT_TRANS_PREPARE_ERROR does not require to drop the reference counter because the transaction abort path releases the map references for each element since the set is unbound. The abort path also deals with releasing reference counter for new elements added to unbound sets. Fixes: 591054469b3e ("netfilter: nf_tables: revisit chain/object refcounting from elements") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_tables.h | 5 +- net/netfilter/nf_tables_api.c | 89 +++++++++++++++++++++++++++---- net/netfilter/nft_set_bitmap.c | 5 +- net/netfilter/nft_set_hash.c | 23 ++++++-- net/netfilter/nft_set_pipapo.c | 14 +++-- net/netfilter/nft_set_rbtree.c | 5 +- 6 files changed, 117 insertions(+), 24 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 716a974a7263..fb3c5f690750 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -382,7 +382,8 @@ struct nft_set_ops { int (*init)(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]); - void (*destroy)(const struct nft_set *set); + void (*destroy)(const struct nft_ctx *ctx, + const struct nft_set *set); void (*gc_init)(const struct nft_set *set); unsigned int elemsize; @@ -686,6 +687,8 @@ void *nft_set_elem_init(const struct nft_set *set, u64 timeout, u64 expiration, gfp_t gfp); void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr); +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem); /** * struct nft_set_gc_batch_head - nf_tables set garbage collection batch diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5af9290af34f..6f6e8c567892 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -557,6 +557,31 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, return 0; } +static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_deactivate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_deactivate(ctx->net, set, elem); + + return 0; +} + +static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_deactivate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); +} + static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) { int err; @@ -565,6 +590,9 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) if (err < 0) return err; + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + nft_deactivate_next(ctx->net, set); ctx->table->use--; @@ -4474,7 +4502,7 @@ err_set_expr_alloc: if (set->expr) nft_expr_destroy(&ctx, set->expr); - ops->destroy(set); + ops->destroy(&ctx, set); err_set_init: kfree(set->name); err_set_name: @@ -4490,7 +4518,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) if (set->expr) nft_expr_destroy(ctx, set->expr); - set->ops->destroy(set); + set->ops->destroy(ctx, set); kfree(set->name); kvfree(set); } @@ -4614,10 +4642,39 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, } } +static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_activate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_activate(ctx->net, set, elem); + + return 0; +} + +static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_activate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); +} + void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (nft_set_is_anonymous(set)) + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(ctx, set); + nft_clear(ctx->net, set); + } set->use++; } @@ -4636,13 +4693,20 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, set->use--; break; case NFT_TRANS_PREPARE: - if (nft_set_is_anonymous(set)) - nft_deactivate_next(ctx->net, set); + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + nft_deactivate_next(ctx->net, set); + } set->use--; return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: + if (nft_set_is_anonymous(set) && + set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + set->use--; fallthrough; default: @@ -5249,6 +5313,7 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, } } +/* Drop references and destroy. Called from gc, dynset and abort path. */ void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr) { @@ -5270,11 +5335,11 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); -/* Only called from commit path, nft_setelem_data_deactivate() already deals - * with the refcounting from the preparation phase. +/* Destroy element. References have been already dropped in the preparation + * path via nft_setelem_data_deactivate(). */ -static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, - const struct nft_set *set, void *elem) +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); @@ -8399,6 +8464,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELSET: trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_set(trans)); + if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(&trans->ctx, nft_trans_set(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: @@ -9128,6 +9196,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); table->use--; + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(&ctx, set); + nft_set_destroy(&ctx, set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 2a81ea421819..3c63f8acebd8 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -270,13 +270,14 @@ static int nft_bitmap_init(const struct nft_set *set, return 0; } -static void nft_bitmap_destroy(const struct nft_set *set) +static void nft_bitmap_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be, *n; list_for_each_entry_safe(be, n, &priv->list, head) - nft_set_elem_destroy(set, be, true); + nf_tables_set_elem_destroy(ctx, set, be); } static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index a5cfb321ae23..51d3e6f0934a 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -380,19 +380,31 @@ static int nft_rhash_init(const struct nft_set *set, return 0; } +struct nft_rhash_ctx { + const struct nft_ctx ctx; + const struct nft_set *set; +}; + static void nft_rhash_elem_destroy(void *ptr, void *arg) { - nft_set_elem_destroy(arg, ptr, true); + struct nft_rhash_ctx *rhash_ctx = arg; + + nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, ptr); } -static void nft_rhash_destroy(const struct nft_set *set) +static void nft_rhash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_ctx rhash_ctx = { + .ctx = *ctx, + .set = set, + }; cancel_delayed_work_sync(&priv->gc_work); rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, - (void *)set); + (void *)&rhash_ctx); } /* Number of buckets is stored in u32, so cap our result to 1U<<31 */ @@ -621,7 +633,8 @@ static int nft_hash_init(const struct nft_set *set, return 0; } -static void nft_hash_destroy(const struct nft_set *set) +static void nft_hash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_hash *priv = nft_set_priv(set); struct nft_hash_elem *he; @@ -631,7 +644,7 @@ static void nft_hash_destroy(const struct nft_set *set) for (i = 0; i < priv->buckets; i++) { hlist_for_each_entry_safe(he, next, &priv->table[i], node) { hlist_del_rcu(&he->node); - nft_set_elem_destroy(set, he, true); + nf_tables_set_elem_destroy(ctx, set, he); } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index eb5934eb3adf..7c759e9b4d84 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2127,10 +2127,12 @@ out_scratch: /** * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array + * @ctx: context * @set: nftables API set representation * @m: matching data pointing to key mapping array */ -static void nft_set_pipapo_match_destroy(const struct nft_set *set, +static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo_field *f; @@ -2147,15 +2149,17 @@ static void nft_set_pipapo_match_destroy(const struct nft_set *set, e = f->mt[r].e; - nft_set_elem_destroy(set, e, true); + nf_tables_set_elem_destroy(ctx, set, e); } } /** * nft_pipapo_destroy() - Free private data for set and all committed elements + * @ctx: context * @set: nftables API set representation */ -static void nft_pipapo_destroy(const struct nft_set *set) +static void nft_pipapo_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; @@ -2165,7 +2169,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) if (m) { rcu_barrier(); - nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m); #ifdef NFT_PIPAPO_ALIGN free_percpu(m->scratch_aligned); @@ -2182,7 +2186,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) m = priv->clone; if (priv->dirty) - nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m); #ifdef NFT_PIPAPO_ALIGN free_percpu(priv->clone->scratch_aligned); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 1ffb24f4c74c..172b994790a0 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -657,7 +657,8 @@ static int nft_rbtree_init(const struct nft_set *set, return 0; } -static void nft_rbtree_destroy(const struct nft_set *set) +static void nft_rbtree_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; @@ -668,7 +669,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_set_elem_destroy(set, rbe, true); + nf_tables_set_elem_destroy(ctx, set, rbe); } } From a07e415be383d0a91d4a6e6470f34663a5ef6600 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 13 Jul 2023 10:48:58 +0200 Subject: [PATCH 4054/4345] netfilter: nf_tables: unbind non-anonymous set if rule construction fails [ Upstream commit 3e70489721b6c870252c9082c496703677240f53 ] Otherwise a dangling reference to a rule object that is gone remains in the set binding list. Fixes: 26b5a5712eb8 ("netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 6f6e8c567892..25b834868eac 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4689,6 +4689,8 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_set_trans_unbind(ctx, set); if (nft_set_is_anonymous(set)) nft_deactivate_next(ctx->net, set); + else + list_del_rcu(&binding->list); set->use--; break; From be6478f5cce6fba311282a8e948a4d9852f38edd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Jul 2023 10:48:59 +0200 Subject: [PATCH 4055/4345] netfilter: nf_tables: fix scheduling-while-atomic splat [ Upstream commit 2024439bd5ceb145eeeb428b2a59e9b905153ac3 ] nf_tables_check_loops() can be called from rhashtable list walk so cond_resched() cannot be used here. Fixes: 81ea01066741 ("netfilter: nf_tables: add rescheduling points during loop detection walks") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 25b834868eac..7e037daaa613 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8684,13 +8684,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, break; } } - - cond_resched(); } list_for_each_entry(set, &ctx->table->sets, list) { - cond_resched(); - if (!nft_is_active_next(ctx->net, set)) continue; if (!(set->flags & NFT_SET_MAP) || From 8289d422f5e484efe4a565fe18e862ecd621c175 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Mon, 3 Jul 2023 16:52:16 +0200 Subject: [PATCH 4056/4345] netfilter: conntrack: Avoid nf_ct_helper_hash uses after free commit 6eef7a2b933885a17679eb8ed0796ddf0ee5309b upstream. If nf_conntrack_init_start() fails (for example due to a register_nf_conntrack_bpf() failure), the nf_conntrack_helper_fini() clean-up path frees the nf_ct_helper_hash map. When built with NF_CONNTRACK=y, further netfilter modules (e.g: netfilter_conntrack_ftp) can still be loaded and call nf_conntrack_helpers_register(), independently of whether nf_conntrack initialized correctly. This accesses the nf_ct_helper_hash dangling pointer and causes a uaf, possibly leading to random memory corruption. This patch guards nf_conntrack_helper_register() from accessing a freed or uninitialized nf_ct_helper_hash pointer and fixes possible uses-after-free when loading a conntrack module. Cc: stable@vger.kernel.org Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure") Signed-off-by: Florent Revest Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conntrack_helper.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 118f415928ae..32cc91f5ba99 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -404,6 +404,9 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES); BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); + if (!nf_ct_helper_hash) + return -ENOENT; + if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT) return -EINVAL; @@ -587,4 +590,5 @@ void nf_conntrack_helper_fini(void) { nf_ct_extend_unregister(&helper_extend); kvfree(nf_ct_helper_hash); + nf_ct_helper_hash = NULL; } From 4ae2e501331aaa506eaf760339bb2f43e5769395 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Wed, 5 Jul 2023 09:12:55 -0300 Subject: [PATCH 4057/4345] netfilter: nf_tables: do not ignore genmask when looking up chain by id commit 515ad530795c118f012539ed76d02bacfd426d89 upstream. When adding a rule to a chain referring to its ID, if that chain had been deleted on the same batch, the rule might end up referring to a deleted chain. This will lead to a WARNING like following: [ 33.098431] ------------[ cut here ]------------ [ 33.098678] WARNING: CPU: 5 PID: 69 at net/netfilter/nf_tables_api.c:2037 nf_tables_chain_destroy+0x23d/0x260 [ 33.099217] Modules linked in: [ 33.099388] CPU: 5 PID: 69 Comm: kworker/5:1 Not tainted 6.4.0+ #409 [ 33.099726] Workqueue: events nf_tables_trans_destroy_work [ 33.100018] RIP: 0010:nf_tables_chain_destroy+0x23d/0x260 [ 33.100306] Code: 8b 7c 24 68 e8 64 9c ed fe 4c 89 e7 e8 5c 9c ed fe 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 89 c6 89 c7 c3 cc cc cc cc <0f> 0b 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 89 c6 89 c7 [ 33.101271] RSP: 0018:ffffc900004ffc48 EFLAGS: 00010202 [ 33.101546] RAX: 0000000000000001 RBX: ffff888006fc0a28 RCX: 0000000000000000 [ 33.101920] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 33.102649] RBP: ffffc900004ffc78 R08: 0000000000000000 R09: 0000000000000000 [ 33.103018] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8880135ef500 [ 33.103385] R13: 0000000000000000 R14: dead000000000122 R15: ffff888006fc0a10 [ 33.103762] FS: 0000000000000000(0000) GS:ffff888024c80000(0000) knlGS:0000000000000000 [ 33.104184] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 33.104493] CR2: 00007fe863b56a50 CR3: 00000000124b0001 CR4: 0000000000770ee0 [ 33.104872] PKRU: 55555554 [ 33.104999] Call Trace: [ 33.105113] [ 33.105214] ? show_regs+0x72/0x90 [ 33.105371] ? __warn+0xa5/0x210 [ 33.105520] ? nf_tables_chain_destroy+0x23d/0x260 [ 33.105732] ? report_bug+0x1f2/0x200 [ 33.105902] ? handle_bug+0x46/0x90 [ 33.106546] ? exc_invalid_op+0x19/0x50 [ 33.106762] ? asm_exc_invalid_op+0x1b/0x20 [ 33.106995] ? nf_tables_chain_destroy+0x23d/0x260 [ 33.107249] ? nf_tables_chain_destroy+0x30/0x260 [ 33.107506] nf_tables_trans_destroy_work+0x669/0x680 [ 33.107782] ? mark_held_locks+0x28/0xa0 [ 33.107996] ? __pfx_nf_tables_trans_destroy_work+0x10/0x10 [ 33.108294] ? _raw_spin_unlock_irq+0x28/0x70 [ 33.108538] process_one_work+0x68c/0xb70 [ 33.108755] ? lock_acquire+0x17f/0x420 [ 33.108977] ? __pfx_process_one_work+0x10/0x10 [ 33.109218] ? do_raw_spin_lock+0x128/0x1d0 [ 33.109435] ? _raw_spin_lock_irq+0x71/0x80 [ 33.109634] worker_thread+0x2bd/0x700 [ 33.109817] ? __pfx_worker_thread+0x10/0x10 [ 33.110254] kthread+0x18b/0x1d0 [ 33.110410] ? __pfx_kthread+0x10/0x10 [ 33.110581] ret_from_fork+0x29/0x50 [ 33.110757] [ 33.110866] irq event stamp: 1651 [ 33.111017] hardirqs last enabled at (1659): [] __up_console_sem+0x79/0xa0 [ 33.111379] hardirqs last disabled at (1666): [] __up_console_sem+0x5e/0xa0 [ 33.111740] softirqs last enabled at (1616): [] __irq_exit_rcu+0x9e/0xe0 [ 33.112094] softirqs last disabled at (1367): [] __irq_exit_rcu+0x9e/0xe0 [ 33.112453] ---[ end trace 0000000000000000 ]--- This is due to the nft_chain_lookup_byid ignoring the genmask. After this change, adding the new rule will fail as it will not find the chain. Fixes: 837830a4b439 ("netfilter: nf_tables: add NFTA_RULE_CHAIN_ID attribute") Cc: stable@vger.kernel.org Reported-by: Mingi Cho of Theori working with ZDI Signed-off-by: Thadeu Lima de Souza Cascardo Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_tables_api.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7e037daaa613..d56f5d7fa545 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2427,7 +2427,7 @@ err: static struct nft_chain *nft_chain_lookup_byid(const struct net *net, const struct nft_table *table, - const struct nlattr *nla) + const struct nlattr *nla, u8 genmask) { struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); u32 id = ntohl(nla_get_be32(nla)); @@ -2438,7 +2438,8 @@ static struct nft_chain *nft_chain_lookup_byid(const struct net *net, if (trans->msg_type == NFT_MSG_NEWCHAIN && chain->table == table && - id == nft_trans_chain_id(trans)) + id == nft_trans_chain_id(trans) && + nft_active_genmask(chain, genmask)) return chain; } return ERR_PTR(-ENOENT); @@ -3353,7 +3354,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return -EOPNOTSUPP; } else if (nla[NFTA_RULE_CHAIN_ID]) { - chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID]); + chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID], + genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN_ID]); return PTR_ERR(chain); @@ -8937,7 +8939,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, genmask); } else if (tb[NFTA_VERDICT_CHAIN_ID]) { chain = nft_chain_lookup_byid(ctx->net, ctx->table, - tb[NFTA_VERDICT_CHAIN_ID]); + tb[NFTA_VERDICT_CHAIN_ID], + genmask); if (IS_ERR(chain)) return PTR_ERR(chain); } else { From ea213922249c7e448d217a0a0441c6f86a8155fd Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Wed, 5 Jul 2023 18:05:35 -0300 Subject: [PATCH 4058/4345] netfilter: nf_tables: prevent OOB access in nft_byteorder_eval commit caf3ef7468f7534771b5c44cd8dbd6f7f87c2cbd upstream. When evaluating byteorder expressions with size 2, a union with 32-bit and 16-bit members is used. Since the 16-bit members are aligned to 32-bit, the array accesses will be out-of-bounds. It may lead to a stack-out-of-bounds access like the one below: [ 23.095215] ================================================================== [ 23.095625] BUG: KASAN: stack-out-of-bounds in nft_byteorder_eval+0x13c/0x320 [ 23.096020] Read of size 2 at addr ffffc90000007948 by task ping/115 [ 23.096358] [ 23.096456] CPU: 0 PID: 115 Comm: ping Not tainted 6.4.0+ #413 [ 23.096770] Call Trace: [ 23.096910] [ 23.097030] dump_stack_lvl+0x60/0xc0 [ 23.097218] print_report+0xcf/0x630 [ 23.097388] ? nft_byteorder_eval+0x13c/0x320 [ 23.097577] ? kasan_addr_to_slab+0xd/0xc0 [ 23.097760] ? nft_byteorder_eval+0x13c/0x320 [ 23.097949] kasan_report+0xc9/0x110 [ 23.098106] ? nft_byteorder_eval+0x13c/0x320 [ 23.098298] __asan_load2+0x83/0xd0 [ 23.098453] nft_byteorder_eval+0x13c/0x320 [ 23.098659] nft_do_chain+0x1c8/0xc50 [ 23.098852] ? __pfx_nft_do_chain+0x10/0x10 [ 23.099078] ? __kasan_check_read+0x11/0x20 [ 23.099295] ? __pfx___lock_acquire+0x10/0x10 [ 23.099535] ? __pfx___lock_acquire+0x10/0x10 [ 23.099745] ? __kasan_check_read+0x11/0x20 [ 23.099929] nft_do_chain_ipv4+0xfe/0x140 [ 23.100105] ? __pfx_nft_do_chain_ipv4+0x10/0x10 [ 23.100327] ? lock_release+0x204/0x400 [ 23.100515] ? nf_hook.constprop.0+0x340/0x550 [ 23.100779] nf_hook_slow+0x6c/0x100 [ 23.100977] ? __pfx_nft_do_chain_ipv4+0x10/0x10 [ 23.101223] nf_hook.constprop.0+0x334/0x550 [ 23.101443] ? __pfx_ip_local_deliver_finish+0x10/0x10 [ 23.101677] ? __pfx_nf_hook.constprop.0+0x10/0x10 [ 23.101882] ? __pfx_ip_rcv_finish+0x10/0x10 [ 23.102071] ? __pfx_ip_local_deliver_finish+0x10/0x10 [ 23.102291] ? rcu_read_lock_held+0x4b/0x70 [ 23.102481] ip_local_deliver+0xbb/0x110 [ 23.102665] ? __pfx_ip_rcv+0x10/0x10 [ 23.102839] ip_rcv+0x199/0x2a0 [ 23.102980] ? __pfx_ip_rcv+0x10/0x10 [ 23.103140] __netif_receive_skb_one_core+0x13e/0x150 [ 23.103362] ? __pfx___netif_receive_skb_one_core+0x10/0x10 [ 23.103647] ? mark_held_locks+0x48/0xa0 [ 23.103819] ? process_backlog+0x36c/0x380 [ 23.103999] __netif_receive_skb+0x23/0xc0 [ 23.104179] process_backlog+0x91/0x380 [ 23.104350] __napi_poll.constprop.0+0x66/0x360 [ 23.104589] ? net_rx_action+0x1cb/0x610 [ 23.104811] net_rx_action+0x33e/0x610 [ 23.105024] ? _raw_spin_unlock+0x23/0x50 [ 23.105257] ? __pfx_net_rx_action+0x10/0x10 [ 23.105485] ? mark_held_locks+0x48/0xa0 [ 23.105741] __do_softirq+0xfa/0x5ab [ 23.105956] ? __dev_queue_xmit+0x765/0x1c00 [ 23.106193] do_softirq.part.0+0x49/0xc0 [ 23.106423] [ 23.106547] [ 23.106670] __local_bh_enable_ip+0xf5/0x120 [ 23.106903] __dev_queue_xmit+0x789/0x1c00 [ 23.107131] ? __pfx___dev_queue_xmit+0x10/0x10 [ 23.107381] ? find_held_lock+0x8e/0xb0 [ 23.107585] ? lock_release+0x204/0x400 [ 23.107798] ? neigh_resolve_output+0x185/0x350 [ 23.108049] ? mark_held_locks+0x48/0xa0 [ 23.108265] ? neigh_resolve_output+0x185/0x350 [ 23.108514] neigh_resolve_output+0x246/0x350 [ 23.108753] ? neigh_resolve_output+0x246/0x350 [ 23.109003] ip_finish_output2+0x3c3/0x10b0 [ 23.109250] ? __pfx_ip_finish_output2+0x10/0x10 [ 23.109510] ? __pfx_nf_hook+0x10/0x10 [ 23.109732] __ip_finish_output+0x217/0x390 [ 23.109978] ip_finish_output+0x2f/0x130 [ 23.110207] ip_output+0xc9/0x170 [ 23.110404] ip_push_pending_frames+0x1a0/0x240 [ 23.110652] raw_sendmsg+0x102e/0x19e0 [ 23.110871] ? __pfx_raw_sendmsg+0x10/0x10 [ 23.111093] ? lock_release+0x204/0x400 [ 23.111304] ? __mod_lruvec_page_state+0x148/0x330 [ 23.111567] ? find_held_lock+0x8e/0xb0 [ 23.111777] ? find_held_lock+0x8e/0xb0 [ 23.111993] ? __rcu_read_unlock+0x7c/0x2f0 [ 23.112225] ? aa_sk_perm+0x18a/0x550 [ 23.112431] ? filemap_map_pages+0x4f1/0x900 [ 23.112665] ? __pfx_aa_sk_perm+0x10/0x10 [ 23.112880] ? find_held_lock+0x8e/0xb0 [ 23.113098] inet_sendmsg+0xa0/0xb0 [ 23.113297] ? inet_sendmsg+0xa0/0xb0 [ 23.113500] ? __pfx_inet_sendmsg+0x10/0x10 [ 23.113727] sock_sendmsg+0xf4/0x100 [ 23.113924] ? move_addr_to_kernel.part.0+0x4f/0xa0 [ 23.114190] __sys_sendto+0x1d4/0x290 [ 23.114391] ? __pfx___sys_sendto+0x10/0x10 [ 23.114621] ? __pfx_mark_lock.part.0+0x10/0x10 [ 23.114869] ? lock_release+0x204/0x400 [ 23.115076] ? find_held_lock+0x8e/0xb0 [ 23.115287] ? rcu_is_watching+0x23/0x60 [ 23.115503] ? __rseq_handle_notify_resume+0x6e2/0x860 [ 23.115778] ? __kasan_check_write+0x14/0x30 [ 23.116008] ? blkcg_maybe_throttle_current+0x8d/0x770 [ 23.116285] ? mark_held_locks+0x28/0xa0 [ 23.116503] ? do_syscall_64+0x37/0x90 [ 23.116713] __x64_sys_sendto+0x7f/0xb0 [ 23.116924] do_syscall_64+0x59/0x90 [ 23.117123] ? irqentry_exit_to_user_mode+0x25/0x30 [ 23.117387] ? irqentry_exit+0x77/0xb0 [ 23.117593] ? exc_page_fault+0x92/0x140 [ 23.117806] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 23.118081] RIP: 0033:0x7f744aee2bba [ 23.118282] Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 [ 23.119237] RSP: 002b:00007ffd04a7c9f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 23.119644] RAX: ffffffffffffffda RBX: 00007ffd04a7e0a0 RCX: 00007f744aee2bba [ 23.120023] RDX: 0000000000000040 RSI: 000056488e9e6300 RDI: 0000000000000003 [ 23.120413] RBP: 000056488e9e6300 R08: 00007ffd04a80320 R09: 0000000000000010 [ 23.120809] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040 [ 23.121219] R13: 00007ffd04a7dc38 R14: 00007ffd04a7ca00 R15: 00007ffd04a7e0a0 [ 23.121617] [ 23.121749] [ 23.121845] The buggy address belongs to the virtual mapping at [ 23.121845] [ffffc90000000000, ffffc90000009000) created by: [ 23.121845] irq_init_percpu_irqstack+0x1cf/0x270 [ 23.122707] [ 23.122803] The buggy address belongs to the physical page: [ 23.123104] page:0000000072ac19f0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x24a09 [ 23.123609] flags: 0xfffffc0001000(reserved|node=0|zone=1|lastcpupid=0x1fffff) [ 23.123998] page_type: 0xffffffff() [ 23.124194] raw: 000fffffc0001000 ffffea0000928248 ffffea0000928248 0000000000000000 [ 23.124610] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 [ 23.125023] page dumped because: kasan: bad access detected [ 23.125326] [ 23.125421] Memory state around the buggy address: [ 23.125682] ffffc90000007800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 23.126072] ffffc90000007880: 00 00 00 00 00 f1 f1 f1 f1 f1 f1 00 00 f2 f2 00 [ 23.126455] >ffffc90000007900: 00 00 00 00 00 00 00 00 00 f2 f2 f2 f2 00 00 00 [ 23.126840] ^ [ 23.127138] ffffc90000007980: 00 00 00 00 00 00 00 00 00 00 00 00 00 f3 f3 f3 [ 23.127522] ffffc90000007a00: f3 00 00 00 00 00 00 00 00 00 00 00 f1 f1 f1 f1 [ 23.127906] ================================================================== [ 23.128324] Disabling lock debugging due to kernel taint Using simple s16 pointers for the 16-bit accesses fixes the problem. For the 32-bit accesses, src and dst can be used directly. Fixes: 96518518cc41 ("netfilter: add nftables") Cc: stable@vger.kernel.org Reported-by: Tanguy DUBROCA (@SidewayRE) from @Synacktiv working with ZDI Signed-off-by: Thadeu Lima de Souza Cascardo Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nft_byteorder.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 9d5947ab8d4e..7b0b8fecb220 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -30,11 +30,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, const struct nft_byteorder *priv = nft_expr_priv(expr); u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; - union { u32 u32; u16 u16; } *s, *d; + u16 *s16, *d16; unsigned int i; - s = (void *)src; - d = (void *)dst; + s16 = (void *)src; + d16 = (void *)dst; switch (priv->size) { case 8: { @@ -61,11 +61,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = ntohl((__force __be32)s[i].u32); + dst[i] = ntohl((__force __be32)src[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = (__force __u32)htonl(s[i].u32); + dst[i] = (__force __u32)htonl(src[i]); break; } break; @@ -73,11 +73,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = ntohs((__force __be16)s[i].u16); + d16[i] = ntohs((__force __be16)s16[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = (__force __u16)htons(s[i].u16); + d16[i] = (__force __u16)htons(s16[i]); break; } break; From 1b7107040596222982bbc0aa646692b0ef92e5fd Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 3 Jul 2023 03:27:04 +0200 Subject: [PATCH 4059/4345] wireguard: queueing: use saner cpu selection wrapping commit 7387943fa35516f6f8017a3b0e9ce48a3bef9faa upstream. Using `% nr_cpumask_bits` is slow and complicated, and not totally robust toward dynamic changes to CPU topologies. Rather than storing the next CPU in the round-robin, just store the last one, and also return that value. This simplifies the loop drastically into a much more common pattern. Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable@vger.kernel.org Reported-by: Linus Torvalds Tested-by: Manuel Leiner Signed-off-by: Jason A. Donenfeld Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireguard/queueing.c | 1 + drivers/net/wireguard/queueing.h | 25 +++++++++++-------------- drivers/net/wireguard/receive.c | 2 +- drivers/net/wireguard/send.c | 2 +- 4 files changed, 14 insertions(+), 16 deletions(-) diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c index 8084e7408c0a..26d235d15235 100644 --- a/drivers/net/wireguard/queueing.c +++ b/drivers/net/wireguard/queueing.c @@ -28,6 +28,7 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, int ret; memset(queue, 0, sizeof(*queue)); + queue->last_cpu = -1; ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL); if (ret) return ret; diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index e2388107f7fd..a2e702f8c582 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -119,20 +119,17 @@ static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id) return cpu; } -/* This function is racy, in the sense that next is unlocked, so it could return - * the same CPU twice. A race-free version of this would be to instead store an - * atomic sequence number, do an increment-and-return, and then iterate through - * every possible CPU until we get to that index -- choose_cpu. However that's - * a bit slower, and it doesn't seem like this potential race actually - * introduces any performance loss, so we live with it. +/* This function is racy, in the sense that it's called while last_cpu is + * unlocked, so it could return the same CPU twice. Adding locking or using + * atomic sequence numbers is slower though, and the consequences of racing are + * harmless, so live with it. */ -static inline int wg_cpumask_next_online(int *next) +static inline int wg_cpumask_next_online(int *last_cpu) { - int cpu = *next; - - while (unlikely(!cpumask_test_cpu(cpu, cpu_online_mask))) - cpu = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits; - *next = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits; + int cpu = cpumask_next(*last_cpu, cpu_online_mask); + if (cpu >= nr_cpu_ids) + cpu = cpumask_first(cpu_online_mask); + *last_cpu = cpu; return cpu; } @@ -161,7 +158,7 @@ static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue) static inline int wg_queue_enqueue_per_device_and_peer( struct crypt_queue *device_queue, struct prev_queue *peer_queue, - struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu) + struct sk_buff *skb, struct workqueue_struct *wq) { int cpu; @@ -175,7 +172,7 @@ static inline int wg_queue_enqueue_per_device_and_peer( /* Then we queue it up in the device queue, which consumes the * packet as soon as it can. */ - cpu = wg_cpumask_next_online(next_cpu); + cpu = wg_cpumask_next_online(&device_queue->last_cpu); if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb))) return -EPIPE; queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work); diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 7b8df406c773..f500aaf67837 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -531,7 +531,7 @@ static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb, - wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu); + wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD); if (likely(!ret || ret == -EPIPE)) { diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 5368f7c35b4b..95c853b59e1d 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -318,7 +318,7 @@ static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, - wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu); + wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: From 999f3b6104ed6ea7376a0f2bcabd5709813c3549 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 3 Jul 2023 03:27:05 +0200 Subject: [PATCH 4060/4345] wireguard: netlink: send staged packets when setting initial private key commit f58d0a9b4c6a7a5199c3af967e43cc8b654604d4 upstream. Packets bound for peers can queue up prior to the device private key being set. For example, if persistent keepalive is set, a packet is queued up to be sent as soon as the device comes up. However, if the private key hasn't been set yet, the handshake message never sends, and no timer is armed to retry, since that would be pointless. But, if a user later sets a private key, the expectation is that those queued packets, such as a persistent keepalive, are actually sent. So adjust the configuration logic to account for this edge case, and add a test case to make sure this works. Maxim noticed this with a wg-quick(8) config to the tune of: [Interface] PostUp = wg set %i private-key somefile [Peer] PublicKey = ... Endpoint = ... PersistentKeepalive = 25 Here, the private key gets set after the device comes up using a PostUp script, triggering the bug. Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable@vger.kernel.org Reported-by: Maxim Cournoyer Tested-by: Maxim Cournoyer Link: https://lore.kernel.org/wireguard/87fs7xtqrv.fsf@gmail.com/ Signed-off-by: Jason A. Donenfeld Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireguard/netlink.c | 14 ++++++---- tools/testing/selftests/wireguard/netns.sh | 30 +++++++++++++++++++--- 2 files changed, 35 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 5c804bcabfe6..f5bc279c9a8c 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -546,6 +546,7 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info) u8 *private_key = nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]); u8 public_key[NOISE_PUBLIC_KEY_LEN]; struct wg_peer *peer, *temp; + bool send_staged_packets; if (!crypto_memneq(wg->static_identity.static_private, private_key, NOISE_PUBLIC_KEY_LEN)) @@ -564,14 +565,17 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info) } down_write(&wg->static_identity.lock); - wg_noise_set_static_identity_private_key(&wg->static_identity, - private_key); - list_for_each_entry_safe(peer, temp, &wg->peer_list, - peer_list) { + send_staged_packets = !wg->static_identity.has_identity && netif_running(wg->dev); + wg_noise_set_static_identity_private_key(&wg->static_identity, private_key); + send_staged_packets = send_staged_packets && wg->static_identity.has_identity; + + wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); + list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) { wg_noise_precompute_static_static(peer); wg_noise_expire_current_peer_keypairs(peer); + if (send_staged_packets) + wg_packet_send_staged_packets(peer); } - wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); up_write(&wg->static_identity.lock); } skip_set_private_key: diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 8a9461aa0878..93e44410f170 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -502,10 +502,32 @@ n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' n1 ping -W 1 -c 1 192.168.241.2 [[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.3:1" ]] -ip1 link del veth1 -ip1 link del veth3 -ip1 link del wg0 -ip2 link del wg0 +ip1 link del dev veth3 +ip1 link del dev wg0 +ip2 link del dev wg0 + +# Make sure persistent keep alives are sent when an adapter comes up +ip1 link add dev wg0 type wireguard +n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" endpoint 10.0.0.1:1 persistent-keepalive 1 +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -eq 0 ]] +ip1 link set dev wg0 up +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -gt 0 ]] +ip1 link del dev wg0 +# This should also happen even if the private key is set later +ip1 link add dev wg0 type wireguard +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.1:1 persistent-keepalive 1 +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -eq 0 ]] +ip1 link set dev wg0 up +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -eq 0 ]] +n1 wg set wg0 private-key <(echo "$key1") +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -gt 0 ]] +ip1 link del dev veth1 +ip1 link del dev wg0 # We test that Netlink/IPC is working properly by doing things that usually cause split responses ip0 link add dev wg0 type wireguard From 83be9fd7843c12b8a8d79a0267b004b3909b19e0 Mon Sep 17 00:00:00 2001 From: Sherry Sun Date: Mon, 19 Jun 2023 16:06:13 +0800 Subject: [PATCH 4061/4345] tty: serial: fsl_lpuart: add earlycon for imx8ulp platform commit e0edfdc15863ec80a1d9ac6e174dbccc00206dd0 upstream. Add earlycon support for imx8ulp platform. Signed-off-by: Sherry Sun Cc: stable Link: https://lore.kernel.org/r/20230619080613.16522-1-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index ca22a1125821..a4cf00756681 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2589,6 +2589,7 @@ OF_EARLYCON_DECLARE(lpuart, "fsl,vf610-lpuart", lpuart_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1021a-lpuart", lpuart32_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1028a-lpuart", ls1028a_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,imx7ulp-lpuart", lpuart32_imx_early_console_setup); +OF_EARLYCON_DECLARE(lpuart32, "fsl,imx8ulp-lpuart", lpuart32_imx_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,imx8qxp-lpuart", lpuart32_imx_early_console_setup); EARLYCON_DECLARE(lpuart, lpuart_early_console_setup); EARLYCON_DECLARE(lpuart32, lpuart32_early_console_setup); From 058f077d09ba09095eed4ae65e6abfe35dfe38e9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 15 Jul 2023 00:47:09 +0000 Subject: [PATCH 4062/4345] rcu-tasks: Mark ->trc_reader_nesting data races [ Upstream commit bdb0cca0d11060fce8a8a44588ac1470c25d62bc ] There are several ->trc_reader_nesting data races that are too low-probability for KCSAN to notice, but which will happen sooner or later. This commit therefore marks these accesses, and comments one that cannot race. Cc: # 5.10.x Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/rcu/tasks.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index c66d47685b28..2b16a86163af 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -848,7 +848,7 @@ static void trc_read_check_handler(void *t_in) // If the task is not in a read-side critical section, and // if this is the last reader, awaken the grace-period kthread. - if (likely(!t->trc_reader_nesting)) { + if (likely(!READ_ONCE(t->trc_reader_nesting))) { if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end))) wake_up(&trc_wait); // Mark as checked after decrement to avoid false @@ -857,7 +857,7 @@ static void trc_read_check_handler(void *t_in) goto reset_ipi; } // If we are racing with an rcu_read_unlock_trace(), try again later. - if (unlikely(t->trc_reader_nesting < 0)) { + if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0)) { if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end))) wake_up(&trc_wait); goto reset_ipi; @@ -904,6 +904,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) n_heavy_reader_ofl_updates++; in_qs = true; } else { + // The task is not running, so C-language access is safe. in_qs = likely(!t->trc_reader_nesting); } @@ -936,7 +937,7 @@ static void trc_wait_for_one_reader(struct task_struct *t, // The current task had better be in a quiescent state. if (t == current) { t->trc_reader_checked = true; - WARN_ON_ONCE(t->trc_reader_nesting); + WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting)); return; } @@ -1046,7 +1047,7 @@ static void show_stalled_task_trace(struct task_struct *t, bool *firstreport) ".I"[READ_ONCE(t->trc_ipi_to_cpu) > 0], ".i"[is_idle_task(t)], ".N"[cpu > 0 && tick_nohz_full_cpu(cpu)], - t->trc_reader_nesting, + READ_ONCE(t->trc_reader_nesting), " N"[!!t->trc_reader_special.b.need_qs], cpu); sched_show_task(t); @@ -1141,7 +1142,7 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp) static void exit_tasks_rcu_finish_trace(struct task_struct *t) { WRITE_ONCE(t->trc_reader_checked, true); - WARN_ON_ONCE(t->trc_reader_nesting); + WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting)); WRITE_ONCE(t->trc_reader_nesting, 0); if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs))) rcu_read_unlock_trace_special(t, 0); From 3a64cd01cdd6bea5b97cdb914cd2462fa8e2d47a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 15 Jul 2023 00:47:10 +0000 Subject: [PATCH 4063/4345] rcu-tasks: Mark ->trc_reader_special.b.need_qs data races [ Upstream commit f8ab3fad80dddf3f2cecb53983063c4431058ca1 ] There are several ->trc_reader_special.b.need_qs data races that are too low-probability for KCSAN to notice, but which will happen sooner or later. This commit therefore marks these accesses. Cc: # 5.10.x Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/rcu/tasks.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 2b16a86163af..aef2e96c3854 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -801,7 +801,7 @@ static DEFINE_IRQ_WORK(rcu_tasks_trace_iw, rcu_read_unlock_iw); /* If we are the last reader, wake up the grace-period kthread. */ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting) { - int nq = t->trc_reader_special.b.need_qs; + int nq = READ_ONCE(t->trc_reader_special.b.need_qs); if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && t->trc_reader_special.b.need_mb) @@ -867,7 +867,7 @@ static void trc_read_check_handler(void *t_in) // Get here if the task is in a read-side critical section. Set // its state so that it will awaken the grace-period kthread upon // exit from that critical section. - WARN_ON_ONCE(t->trc_reader_special.b.need_qs); + WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)); WRITE_ONCE(t->trc_reader_special.b.need_qs, true); reset_ipi: @@ -919,7 +919,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) // state so that it will awaken the grace-period kthread upon exit // from that critical section. atomic_inc(&trc_n_readers_need_end); // One more to wait on. - WARN_ON_ONCE(t->trc_reader_special.b.need_qs); + WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)); WRITE_ONCE(t->trc_reader_special.b.need_qs, true); return true; } @@ -1048,7 +1048,7 @@ static void show_stalled_task_trace(struct task_struct *t, bool *firstreport) ".i"[is_idle_task(t)], ".N"[cpu > 0 && tick_nohz_full_cpu(cpu)], READ_ONCE(t->trc_reader_nesting), - " N"[!!t->trc_reader_special.b.need_qs], + " N"[!!READ_ONCE(t->trc_reader_special.b.need_qs)], cpu); sched_show_task(t); } From 4f91de9a81bd389cd835211b19d5d1fca69f6acc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 15 Jul 2023 00:47:11 +0000 Subject: [PATCH 4064/4345] rcu-tasks: Simplify trc_read_check_handler() atomic operations [ Upstream commit 96017bf9039763a2e02dcc6adaa18592cd73a39d ] Currently, trc_wait_for_one_reader() atomically increments the trc_n_readers_need_end counter before sending the IPI invoking trc_read_check_handler(). All failure paths out of trc_read_check_handler() and also from the smp_call_function_single() within trc_wait_for_one_reader() must carefully atomically decrement this counter. This is more complex than it needs to be. This commit therefore simplifies things and saves a few lines of code by dispensing with the atomic decrements in favor of having trc_read_check_handler() do the atomic increment only in the success case. In theory, this represents no change in functionality. Cc: # 5.10.x Signed-off-by: Paul E. McKenney Signed-off-by: Joel Fernandes (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/rcu/tasks.h | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index aef2e96c3854..23101ebbbe1e 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -841,32 +841,24 @@ static void trc_read_check_handler(void *t_in) // If the task is no longer running on this CPU, leave. if (unlikely(texp != t)) { - if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end))) - wake_up(&trc_wait); goto reset_ipi; // Already on holdout list, so will check later. } // If the task is not in a read-side critical section, and // if this is the last reader, awaken the grace-period kthread. if (likely(!READ_ONCE(t->trc_reader_nesting))) { - if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end))) - wake_up(&trc_wait); - // Mark as checked after decrement to avoid false - // positives on the above WARN_ON_ONCE(). WRITE_ONCE(t->trc_reader_checked, true); goto reset_ipi; } // If we are racing with an rcu_read_unlock_trace(), try again later. - if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0)) { - if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end))) - wake_up(&trc_wait); + if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0)) goto reset_ipi; - } WRITE_ONCE(t->trc_reader_checked, true); // Get here if the task is in a read-side critical section. Set // its state so that it will awaken the grace-period kthread upon // exit from that critical section. + atomic_inc(&trc_n_readers_need_end); // One more to wait on. WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)); WRITE_ONCE(t->trc_reader_special.b.need_qs, true); @@ -960,21 +952,15 @@ static void trc_wait_for_one_reader(struct task_struct *t, if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0) return; - atomic_inc(&trc_n_readers_need_end); per_cpu(trc_ipi_to_cpu, cpu) = true; t->trc_ipi_to_cpu = cpu; rcu_tasks_trace.n_ipis++; - if (smp_call_function_single(cpu, - trc_read_check_handler, t, 0)) { + if (smp_call_function_single(cpu, trc_read_check_handler, t, 0)) { // Just in case there is some other reason for // failure than the target CPU being offline. rcu_tasks_trace.n_ipis_fails++; per_cpu(trc_ipi_to_cpu, cpu) = false; t->trc_ipi_to_cpu = cpu; - if (atomic_dec_and_test(&trc_n_readers_need_end)) { - WARN_ON_ONCE(1); - wake_up(&trc_wait); - } } } } From bb2f7e4bfe815150e63633aacd276fb88735e458 Mon Sep 17 00:00:00 2001 From: Michael Schmitz Date: Wed, 5 Jul 2023 11:38:08 +1200 Subject: [PATCH 4065/4345] block/partition: fix signedness issue for Amiga partitions commit 7eb1e47696aa231b1a567846bbe3a1e1befe1854 upstream. Making 'blk' sector_t (i.e. 64 bit if LBD support is active) fails the 'blk>0' test in the partition block loop if a value of (signed int) -1 is used to mark the end of the partition block list. Explicitly cast 'blk' to signed int to allow use of -1 to terminate the partition block linked list. Fixes: b6f3f28f604b ("block: add overflow checks for Amiga partition support") Reported-by: Christian Zigotzky Link: https://lore.kernel.org/r/024ce4fa-cc6d-50a2-9aae-3701d0ebf668@xenosoft.de Signed-off-by: Michael Schmitz Reviewed-by: Martin Steigerwald Tested-by: Christian Zigotzky Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/partitions/amiga.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c index 7abc09d8fc73..a99ec7f1a174 100644 --- a/block/partitions/amiga.c +++ b/block/partitions/amiga.c @@ -91,7 +91,7 @@ int amiga_partition(struct parsed_partitions *state) } blk = be32_to_cpu(rdb->rdb_PartitionList); put_dev_sector(sect); - for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) { + for (part = 1; (s32) blk>0 && part<=16; part++, put_dev_sector(sect)) { /* Read in terms partition table understands */ if (check_mul_overflow(blk, (sector_t) blksize, &blk)) { pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n", From 297883bbcab1b48e97aeb8f1dd3dd99d13238a44 Mon Sep 17 00:00:00 2001 From: Andres Freund Date: Sun, 16 Jul 2023 12:07:03 -0600 Subject: [PATCH 4066/4345] io_uring: Use io_schedule* in cqring wait Commit 8a796565cec3601071cbbd27d6304e202019d014 upstream. I observed poor performance of io_uring compared to synchronous IO. That turns out to be caused by deeper CPU idle states entered with io_uring, due to io_uring using plain schedule(), whereas synchronous IO uses io_schedule(). The losses due to this are substantial. On my cascade lake workstation, t/io_uring from the fio repository e.g. yields regressions between 20% and 40% with the following command: ./t/io_uring -r 5 -X0 -d 1 -s 1 -c 1 -p 0 -S$use_sync -R 0 /mnt/t2/fio/write.0.0 This is repeatable with different filesystems, using raw block devices and using different block devices. Use io_schedule_prepare() / io_schedule_finish() in io_cqring_wait_schedule() to address the difference. After that using io_uring is on par or surpassing synchronous IO (using registered files etc makes it reliably win, but arguably is a less fair comparison). There are other calls to schedule() in io_uring/, but none immediately jump out to be similarly situated, so I did not touch them. Similarly, it's possible that mutex_lock_io() should be used, but it's not clear if there are cases where that matters. Cc: stable@vger.kernel.org # 5.10+ Cc: Pavel Begunkov Cc: io-uring@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Andres Freund Link: https://lore.kernel.org/r/20230707162007.194068-1-andres@anarazel.de [axboe: minor style fixup] Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 25f201fc3ffd..3d5fb465eed7 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -7625,7 +7625,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, ktime_t *timeout) { - int ret; + int token, ret; /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); @@ -7635,9 +7635,17 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, if (test_bit(0, &ctx->check_cq_overflow)) return 1; + /* + * Use io_schedule_prepare/finish, so cpufreq can take into account + * that the task is waiting for IO - turns out to be important for low + * QD IO. + */ + token = io_schedule_prepare(); + ret = 1; if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) - return -ETIME; - return 1; + ret = -ETIME; + io_schedule_finish(token); + return ret; } /* From dc4a25fa75659515fd61980d77e071b406db73b0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 17 Jul 2023 10:27:20 -0600 Subject: [PATCH 4067/4345] io_uring: add reschedule point to handle_tw_list() Commit f58680085478dd292435727210122960d38e8014 upstream. If CONFIG_PREEMPT_NONE is set and the task_work chains are long, we could be running into issues blocking others for too long. Add a reschedule check in handle_tw_list(), and flush the ctx if we need to reschedule. Cc: stable@vger.kernel.org # 5.10+ Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- io_uring/io_uring.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 3d5fb465eed7..51e6ebe72caf 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2214,9 +2214,12 @@ static void tctx_task_work(struct callback_head *cb) } req->io_task_work.func(req, &locked); node = next; + if (unlikely(need_resched())) { + ctx_flush_and_put(ctx, &locked); + ctx = NULL; + cond_resched(); + } } while (node); - - cond_resched(); } ctx_flush_and_put(ctx, &locked); From fc359e5b45da6ef1c40436cecc18b201dce95df8 Mon Sep 17 00:00:00 2001 From: Moritz Fischer Date: Tue, 27 Jun 2023 03:50:00 +0000 Subject: [PATCH 4068/4345] net: lan743x: Don't sleep in atomic context commit 7a8227b2e76be506b2ac64d2beac950ca04892a5 upstream. dev_set_rx_mode() grabs a spin_lock, and the lan743x implementation proceeds subsequently to go to sleep using readx_poll_timeout(). Introduce a helper wrapping the readx_poll_timeout_atomic() function and use it to replace the calls to readx_polL_timeout(). Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver") Cc: stable@vger.kernel.org Cc: Bryan Whitehead Cc: UNGLinuxDriver@microchip.com Signed-off-by: Moritz Fischer Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230627035000.1295254-1-moritzf@google.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/microchip/lan743x_main.c | 21 +++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 481f89d193f7..50cb1c5251f7 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -83,6 +83,18 @@ static int lan743x_csr_light_reset(struct lan743x_adapter *adapter) !(data & HW_CFG_LRST_), 100000, 10000000); } +static int lan743x_csr_wait_for_bit_atomic(struct lan743x_adapter *adapter, + int offset, u32 bit_mask, + int target_value, int udelay_min, + int udelay_max, int count) +{ + u32 data; + + return readx_poll_timeout_atomic(LAN743X_CSR_READ_OP, offset, data, + target_value == !!(data & bit_mask), + udelay_max, udelay_min * count); +} + static int lan743x_csr_wait_for_bit(struct lan743x_adapter *adapter, int offset, u32 bit_mask, int target_value, int usleep_min, @@ -678,8 +690,8 @@ static int lan743x_dp_write(struct lan743x_adapter *adapter, u32 dp_sel; int i; - if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, - 1, 40, 100, 100)) + if (lan743x_csr_wait_for_bit_atomic(adapter, DP_SEL, DP_SEL_DPRDY_, + 1, 40, 100, 100)) return -EIO; dp_sel = lan743x_csr_read(adapter, DP_SEL); dp_sel &= ~DP_SEL_MASK_; @@ -690,8 +702,9 @@ static int lan743x_dp_write(struct lan743x_adapter *adapter, lan743x_csr_write(adapter, DP_ADDR, addr + i); lan743x_csr_write(adapter, DP_DATA_0, buf[i]); lan743x_csr_write(adapter, DP_CMD, DP_CMD_WRITE_); - if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, - 1, 40, 100, 100)) + if (lan743x_csr_wait_for_bit_atomic(adapter, DP_SEL, + DP_SEL_DPRDY_, + 1, 40, 100, 100)) return -EIO; } From 13c353dc5c2e6c0412cd6009218af0ddc8fcd81e Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 23 Jun 2023 12:08:14 -0700 Subject: [PATCH 4069/4345] workqueue: clean up WORK_* constant types, clarify masking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit afa4bb778e48d79e4a642ed41e3b4e0de7489a6c upstream. Dave Airlie reports that gcc-13.1.1 has started complaining about some of the workqueue code in 32-bit arm builds: kernel/workqueue.c: In function ‘get_work_pwq’: kernel/workqueue.c:713:24: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] 713 | return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); | ^ [ ... a couple of other cases ... ] and while it's not immediately clear exactly why gcc started complaining about it now, I suspect it's some C23-induced enum type handlign fixup in gcc-13 is the cause. Whatever the reason for starting to complain, the code and data types are indeed disgusting enough that the complaint is warranted. The wq code ends up creating various "helper constants" (like that WORK_STRUCT_WQ_DATA_MASK) using an enum type, which is all kinds of confused. The mask needs to be 'unsigned long', not some unspecified enum type. To make matters worse, the actual "mask and cast to a pointer" is repeated a couple of times, and the cast isn't even always done to the right pointer, but - as the error case above - to a 'void *' with then the compiler finishing the job. That's now how we roll in the kernel. So create the masks using the proper types rather than some ambiguous enumeration, and use a nice helper that actually does the type conversion in one well-defined place. Incidentally, this magically makes clang generate better code. That, admittedly, is really just a sign of clang having been seriously confused before, and cleaning up the typing unconfuses the compiler too. Reported-by: Dave Airlie Link: https://lore.kernel.org/lkml/CAPM=9twNnV4zMCvrPkw3H-ajZOH-01JVh_kDrxdPYQErz8ZTdA@mail.gmail.com/ Cc: Arnd Bergmann Cc: Tejun Heo Cc: Nick Desaulniers Cc: Nathan Chancellor Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/workqueue.h | 15 ++++++++------- kernel/workqueue.c | 13 ++++++++----- 2 files changed, 16 insertions(+), 12 deletions(-) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 2fa9b311e566..460c58fa011a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -73,7 +73,6 @@ enum { WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, - WORK_OFFQ_CANCELING = (1 << __WORK_OFFQ_CANCELING), /* * When a work item is off queue, its high bits point to the last @@ -84,12 +83,6 @@ enum { WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, - WORK_OFFQ_POOL_NONE = (1LU << WORK_OFFQ_POOL_BITS) - 1, - - /* convenience constants */ - WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, - WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, - WORK_STRUCT_NO_POOL = (unsigned long)WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, @@ -99,6 +92,14 @@ enum { WORKER_DESC_LEN = 24, }; +/* Convenience constants - of type 'unsigned long', not 'enum'! */ +#define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING) +#define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) +#define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) + +#define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) +#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) + struct work_struct { atomic_long_t data; struct list_head entry; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b9041ab881bc..fa0a0e59b385 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -679,12 +679,17 @@ static void clear_work_data(struct work_struct *work) set_work_data(work, WORK_STRUCT_NO_POOL, 0); } +static inline struct pool_workqueue *work_struct_pwq(unsigned long data) +{ + return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK); +} + static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) - return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); + return work_struct_pwq(data); else return NULL; } @@ -712,8 +717,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work) assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) - return ((struct pool_workqueue *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool; + return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) @@ -734,8 +738,7 @@ static int get_work_pool_id(struct work_struct *work) unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) - return ((struct pool_workqueue *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool->id; + return work_struct_pwq(data)->pool->id; return data >> WORK_OFFQ_POOL_SHIFT; } From 547ab8ea86c1e7d078845454afac6319029e2819 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 20 Jun 2023 08:22:02 -0300 Subject: [PATCH 4070/4345] drm/panel: simple: Add connector_type for innolux_at043tn24 [ Upstream commit 2c56a751845ddfd3078ebe79981aaaa182629163 ] The innolux at043tn24 display is a parallel LCD. Pass the 'connector_type' information to avoid the following warning: panel-simple panel: Specify missing connector_type Signed-off-by: Fabio Estevam Fixes: 41bcceb4de9c ("drm/panel: simple: Add support for Innolux AT043TN24") Reviewed-by: Sam Ravnborg Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230620112202.654981-1-festevam@gmail.com Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-simple.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index b0b92f436879..ffda99c20435 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2091,6 +2091,7 @@ static const struct panel_desc innolux_at043tn24 = { .height = 54, }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, + .connector_type = DRM_MODE_CONNECTOR_DPI, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE, }; From 2a587b71c532977498fdd5d19b3384442a0057b7 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 15 Jun 2023 22:16:02 +0200 Subject: [PATCH 4071/4345] drm/panel: simple: Add Powertip PH800480T013 drm_display_mode flags [ Upstream commit 1c519980aced3da1fae37c1339cf43b24eccdee7 ] Add missing drm_display_mode DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC flags. Those are used by various bridges in the pipeline to correctly configure its sync signals polarity. Fixes: d69de69f2be1 ("drm/panel: simple: Add Powertip PH800480T013 panel") Signed-off-by: Marek Vasut Reviewed-by: Sam Ravnborg Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230615201602.565948-1-marex@denx.de Signed-off-by: Sasha Levin --- drivers/gpu/drm/panel/panel-simple.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index ffda99c20435..7b69f81444eb 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -3153,6 +3153,7 @@ static const struct drm_display_mode powertip_ph800480t013_idf02_mode = { .vsync_start = 480 + 49, .vsync_end = 480 + 49 + 2, .vtotal = 480 + 49 + 2 + 22, + .flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC, }; static const struct panel_desc powertip_ph800480t013_idf02 = { From 3d4bba694aed2b10be5f925a46a3ffe40d904bdc Mon Sep 17 00:00:00 2001 From: Muhammad Husaini Zulkifli Date: Wed, 17 May 2023 08:18:12 +0800 Subject: [PATCH 4072/4345] igc: Remove delay during TX ring configuration [ Upstream commit cca28ceac7c7857bc2d313777017585aef00bcc4 ] Remove unnecessary delay during the TX ring configuration. This will cause delay, especially during link down and link up activity. Furthermore, old SKUs like as I225 will call the reset_adapter to reset the controller during TSN mode Gate Control List (GCL) setting. This will add more time to the configuration of the real-time use case. It doesn't mentioned about this delay in the Software User Manual. It might have been ported from legacy code I210 in the past. Fixes: 13b5b7fd6a4a ("igc: Add support for Tx/Rx rings") Signed-off-by: Muhammad Husaini Zulkifli Acked-by: Sasha Neftin Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index a15e4b6d7fa4..2b51ee87a2de 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -600,7 +600,6 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter, /* disable the queue */ wr32(IGC_TXDCTL(reg_idx), 0); wrfl(); - mdelay(10); wr32(IGC_TDLEN(reg_idx), ring->count * sizeof(union igc_adv_tx_desc)); From de6e6b07974c45141835ca1176ba8bc9f59346f2 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 28 Jun 2023 08:59:34 +0800 Subject: [PATCH 4073/4345] net/mlx5e: fix double free in mlx5e_destroy_flow_table [ Upstream commit 884abe45a9014d0de2e6edb0630dfd64f23f1d1b ] In function accel_fs_tcp_create_groups(), when the ft->g memory is successfully allocated but the 'in' memory fails to be allocated, the memory pointed to by ft->g is released once. And in function accel_fs_tcp_create_table, mlx5e_destroy_flow_table is called to release the memory pointed to by ft->g again. This will cause double free problem. Fixes: c062d52ac24c ("net/mlx5e: Receive flow steering framework for accelerated TCP flows") Signed-off-by: Zhengchao Shao Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c index e51f60b55daa..2da90f6649d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c @@ -194,6 +194,7 @@ static int accel_fs_tcp_create_groups(struct mlx5e_flow_table *ft, in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } From 30c281a77fb1b2d362030ea243dd663201d62a21 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 8 Jun 2023 09:32:10 +0200 Subject: [PATCH 4074/4345] net/mlx5e: Check for NOT_READY flag state after locking [ Upstream commit 65e64640e97c0f223e77f9ea69b5a46186b93470 ] Currently the check for NOT_READY flag is performed before obtaining the necessary lock. This opens a possibility for race condition when the flow is concurrently removed from unready_flows list by the workqueue task, which causes a double-removal from the list and a crash[0]. Fix the issue by moving the flag check inside the section protected by uplink_priv->unready_flows_lock mutex. [0]: [44376.389654] general protection fault, probably for non-canonical address 0xdead000000000108: 0000 [#1] SMP [44376.391665] CPU: 7 PID: 59123 Comm: tc Not tainted 6.4.0-rc4+ #1 [44376.392984] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [44376.395342] RIP: 0010:mlx5e_tc_del_fdb_flow+0xb3/0x340 [mlx5_core] [44376.396857] Code: 00 48 8b b8 68 ce 02 00 e8 8a 4d 02 00 4c 8d a8 a8 01 00 00 4c 89 ef e8 8b 79 88 e1 48 8b 83 98 06 00 00 48 8b 93 90 06 00 00 <48> 89 42 08 48 89 10 48 b8 00 01 00 00 00 00 ad de 48 89 83 90 06 [44376.399167] RSP: 0018:ffff88812cc97570 EFLAGS: 00010246 [44376.399680] RAX: dead000000000122 RBX: ffff8881088e3800 RCX: ffff8881881bac00 [44376.400337] RDX: dead000000000100 RSI: ffff88812cc97500 RDI: ffff8881242f71b0 [44376.401001] RBP: ffff88811cbb0940 R08: 0000000000000400 R09: 0000000000000001 [44376.401663] R10: 0000000000000001 R11: 0000000000000000 R12: ffff88812c944000 [44376.402342] R13: ffff8881242f71a8 R14: ffff8881222b4000 R15: 0000000000000000 [44376.402999] FS: 00007f0451104800(0000) GS:ffff88852cb80000(0000) knlGS:0000000000000000 [44376.403787] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [44376.404343] CR2: 0000000000489108 CR3: 0000000123a79003 CR4: 0000000000370ea0 [44376.405004] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [44376.405665] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [44376.406339] Call Trace: [44376.406651] [44376.406939] ? die_addr+0x33/0x90 [44376.407311] ? exc_general_protection+0x192/0x390 [44376.407795] ? asm_exc_general_protection+0x22/0x30 [44376.408292] ? mlx5e_tc_del_fdb_flow+0xb3/0x340 [mlx5_core] [44376.408876] __mlx5e_tc_del_fdb_peer_flow+0xbc/0xe0 [mlx5_core] [44376.409482] mlx5e_tc_del_flow+0x42/0x210 [mlx5_core] [44376.410055] mlx5e_flow_put+0x25/0x50 [mlx5_core] [44376.410529] mlx5e_delete_flower+0x24b/0x350 [mlx5_core] [44376.411043] tc_setup_cb_reoffload+0x22/0x80 [44376.411462] fl_reoffload+0x261/0x2f0 [cls_flower] [44376.411907] ? mlx5e_rep_indr_setup_ft_cb+0x160/0x160 [mlx5_core] [44376.412481] ? mlx5e_rep_indr_setup_ft_cb+0x160/0x160 [mlx5_core] [44376.413044] tcf_block_playback_offloads+0x76/0x170 [44376.413497] tcf_block_unbind+0x7b/0xd0 [44376.413881] tcf_block_setup+0x17d/0x1c0 [44376.414269] tcf_block_offload_cmd.isra.0+0xf1/0x130 [44376.414725] tcf_block_offload_unbind+0x43/0x70 [44376.415153] __tcf_block_put+0x82/0x150 [44376.415532] ingress_destroy+0x22/0x30 [sch_ingress] [44376.415986] qdisc_destroy+0x3b/0xd0 [44376.416343] qdisc_graft+0x4d0/0x620 [44376.416706] tc_get_qdisc+0x1c9/0x3b0 [44376.417074] rtnetlink_rcv_msg+0x29c/0x390 [44376.419978] ? rep_movs_alternative+0x3a/0xa0 [44376.420399] ? rtnl_calcit.isra.0+0x120/0x120 [44376.420813] netlink_rcv_skb+0x54/0x100 [44376.421192] netlink_unicast+0x1f6/0x2c0 [44376.421573] netlink_sendmsg+0x232/0x4a0 [44376.421980] sock_sendmsg+0x38/0x60 [44376.422328] ____sys_sendmsg+0x1d0/0x1e0 [44376.422709] ? copy_msghdr_from_user+0x6d/0xa0 [44376.423127] ___sys_sendmsg+0x80/0xc0 [44376.423495] ? ___sys_recvmsg+0x8b/0xc0 [44376.423869] __sys_sendmsg+0x51/0x90 [44376.424226] do_syscall_64+0x3d/0x90 [44376.424587] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [44376.425046] RIP: 0033:0x7f045134f887 [44376.425403] Code: 0a 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 [44376.426914] RSP: 002b:00007ffd63a82b98 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [44376.427592] RAX: ffffffffffffffda RBX: 000000006481955f RCX: 00007f045134f887 [44376.428195] RDX: 0000000000000000 RSI: 00007ffd63a82c00 RDI: 0000000000000003 [44376.428796] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 [44376.429404] R10: 00007f0451208708 R11: 0000000000000246 R12: 0000000000000001 [44376.430039] R13: 0000000000409980 R14: 000000000047e538 R15: 0000000000485400 [44376.430644] [44376.430907] Modules linked in: mlx5_ib mlx5_core act_mirred act_tunnel_key cls_flower vxlan dummy sch_ingress openvswitch nsh rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm ib_uverbs ib_core xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_g ss_krb5 auth_rpcgss oid_registry overlay zram zsmalloc fuse [last unloaded: mlx5_core] [44376.433936] ---[ end trace 0000000000000000 ]--- [44376.434373] RIP: 0010:mlx5e_tc_del_fdb_flow+0xb3/0x340 [mlx5_core] [44376.434951] Code: 00 48 8b b8 68 ce 02 00 e8 8a 4d 02 00 4c 8d a8 a8 01 00 00 4c 89 ef e8 8b 79 88 e1 48 8b 83 98 06 00 00 48 8b 93 90 06 00 00 <48> 89 42 08 48 89 10 48 b8 00 01 00 00 00 00 ad de 48 89 83 90 06 [44376.436452] RSP: 0018:ffff88812cc97570 EFLAGS: 00010246 [44376.436924] RAX: dead000000000122 RBX: ffff8881088e3800 RCX: ffff8881881bac00 [44376.437530] RDX: dead000000000100 RSI: ffff88812cc97500 RDI: ffff8881242f71b0 [44376.438179] RBP: ffff88811cbb0940 R08: 0000000000000400 R09: 0000000000000001 [44376.438786] R10: 0000000000000001 R11: 0000000000000000 R12: ffff88812c944000 [44376.439393] R13: ffff8881242f71a8 R14: ffff8881222b4000 R15: 0000000000000000 [44376.439998] FS: 00007f0451104800(0000) GS:ffff88852cb80000(0000) knlGS:0000000000000000 [44376.440714] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [44376.441225] CR2: 0000000000489108 CR3: 0000000123a79003 CR4: 0000000000370ea0 [44376.441843] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [44376.442471] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Fixes: ad86755b18d5 ("net/mlx5e: Protect unready flows with dedicated lock") Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 16846442717d..c6a81a51530d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1334,7 +1334,8 @@ static void remove_unready_flow(struct mlx5e_tc_flow *flow) uplink_priv = &rpriv->uplink_priv; mutex_lock(&uplink_priv->unready_flows_lock); - unready_flow_del(flow); + if (flow_flag_test(flow, NOT_READY)) + unready_flow_del(flow); mutex_unlock(&uplink_priv->unready_flows_lock); } @@ -1475,8 +1476,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5e_put_flow_tunnel_id(flow); - if (flow_flag_test(flow, NOT_READY)) - remove_unready_flow(flow); + remove_unready_flow(flow); if (mlx5e_is_offloaded_flow(flow)) { if (flow_flag_test(flow, SLOW)) From b687b7836157d3a8afbe778957f7199003d7460f Mon Sep 17 00:00:00 2001 From: Prasad Koya Date: Mon, 5 Jun 2023 11:09:01 -0700 Subject: [PATCH 4075/4345] igc: set TP bit in 'supported' and 'advertising' fields of ethtool_link_ksettings [ Upstream commit 9ac3fc2f42e5ffa1e927dcbffb71b15fa81459e2 ] set TP bit in the 'supported' and 'advertising' fields. i225/226 parts only support twisted pair copper. Fixes: 8c5ad0dae93c ("igc: Add ethtool support") Signed-off-by: Prasad Koya Acked-by: Sasha Neftin Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_ethtool.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index da259cd59add..d28ac3a025ab 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1673,6 +1673,8 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, /* twisted pair */ cmd->base.port = PORT_TP; cmd->base.phy_address = hw->phy.addr; + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); /* advertising link modes */ if (hw->phy.autoneg_advertised & ADVERTISE_10_HALF) From c175603d84d3b83e180204b48cda15514e395e22 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 26 Jun 2023 13:58:47 +0300 Subject: [PATCH 4076/4345] scsi: qla2xxx: Fix error code in qla2x00_start_sp() [ Upstream commit e579b007eff3ff8d29d59d16214cd85fb9e573f7 ] This should be negative -EAGAIN instead of positive. The callers treat non-zero error codes the same so it doesn't really impact runtime beyond some trivial differences to debug output. Fixes: 80676d054e5a ("scsi: qla2xxx: Fix session cleanup hang") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/49866d28-4cfe-47b0-842b-78f110e61aab@moroto.mountain Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/qla2xxx/qla_iocb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index e54cc2a761dd..f0af76c3de7e 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -3713,7 +3713,7 @@ qla2x00_start_sp(srb_t *sp) spin_lock_irqsave(qp->qp_lock_ptr, flags); pkt = __qla2x00_alloc_iocbs(sp->qpair, sp); if (!pkt) { - rval = EAGAIN; + rval = -EAGAIN; ql_log(ql_log_warn, vha, 0x700c, "qla2x00_alloc_iocbs failed.\n"); goto done; From d341f246123e144b3d0ce908d254dee5664f2ff4 Mon Sep 17 00:00:00 2001 From: Klaus Kudielka Date: Wed, 5 Jul 2023 07:37:12 +0200 Subject: [PATCH 4077/4345] net: mvneta: fix txq_map in case of txq_number==1 [ Upstream commit 21327f81db6337c8843ce755b01523c7d3df715b ] If we boot with mvneta.txq_number=1, the txq_map is set incorrectly: MVNETA_CPU_TXQ_ACCESS(1) refers to TX queue 1, but only TX queue 0 is initialized. Fix this. Fixes: 50bf8cb6fc9c ("net: mvneta: Configure XPS support") Signed-off-by: Klaus Kudielka Reviewed-by: Michal Kubiak Link: https://lore.kernel.org/r/20230705053712.3914-1-klaus.kudielka@gmail.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/mvneta.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index f5567d485e91..3656a3937eca 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1471,7 +1471,7 @@ static void mvneta_defaults_set(struct mvneta_port *pp) */ if (txq_number == 1) txq_map = (cpu == pp->rxq_def) ? - MVNETA_CPU_TXQ_ACCESS(1) : 0; + MVNETA_CPU_TXQ_ACCESS(0) : 0; } else { txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK; @@ -4165,7 +4165,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) */ if (txq_number == 1) txq_map = (cpu == elected_cpu) ? - MVNETA_CPU_TXQ_ACCESS(1) : 0; + MVNETA_CPU_TXQ_ACCESS(0) : 0; else txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) & MVNETA_CPU_TXQ_ACCESS_ALL_MASK; From 80e0e8d5f54397c5048fa2274144134dd9dc91b5 Mon Sep 17 00:00:00 2001 From: M A Ramdhan Date: Wed, 5 Jul 2023 12:15:30 -0400 Subject: [PATCH 4078/4345] net/sched: cls_fw: Fix improper refcount update leads to use-after-free [ Upstream commit 0323bce598eea038714f941ce2b22541c46d488f ] In the event of a failure in tcf_change_indev(), fw_set_parms() will immediately return an error after incrementing or decrementing reference counter in tcf_bind_filter(). If attacker can control reference counter to zero and make reference freed, leading to use after free. In order to prevent this, move the point of possible failure above the point where the TC_FW_CLASSID is handled. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: M A Ramdhan Signed-off-by: M A Ramdhan Acked-by: Jamal Hadi Salim Reviewed-by: Pedro Tammela Message-ID: <20230705161530.52003-1-ramdhan@starlabs.sg> Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/sched/cls_fw.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index ec945294626a..41f0898a5a56 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -210,11 +210,6 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, if (err < 0) return err; - if (tb[TCA_FW_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); - tcf_bind_filter(tp, &f->res, base); - } - if (tb[TCA_FW_INDEV]) { int ret; ret = tcf_change_indev(net, tb[TCA_FW_INDEV], extack); @@ -231,6 +226,11 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, } else if (head->mask != 0xFFFFFFFF) return err; + if (tb[TCA_FW_CLASSID]) { + f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); + tcf_bind_filter(tp, &f->res, base); + } + return 0; } From 9085429821b442f32d93b4af67d7adb2bb881820 Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 6 Jul 2023 12:41:28 +0800 Subject: [PATCH 4079/4345] gve: Set default duplex configuration to full [ Upstream commit 0503efeadbf6bb8bf24397613a73b67e665eac5f ] Current duplex mode was unset in the driver, resulting in the default parameter being set to 0, which corresponds to half duplex. It might mislead users to have incorrect expectation about the driver's transmission capabilities. Set the default duplex configuration to full, as the driver runs in full duplex mode at this point. Fixes: 7e074d5a76ca ("gve: Enable Link Speed Reporting in the driver.") Signed-off-by: Junfeng Guo Reviewed-by: Leon Romanovsky Message-ID: <20230706044128.2726747-1-junfeng.guo@intel.com> Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/google/gve/gve_ethtool.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index e0449cc24fbd..cbfd00744935 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -516,6 +516,9 @@ static int gve_get_link_ksettings(struct net_device *netdev, err = gve_adminq_report_link_speed(priv); cmd->base.speed = priv->link_speed; + + cmd->base.duplex = DUPLEX_FULL; + return err; } From f8cc4fd99a325505e15c3da95d6de266efd3d9b5 Mon Sep 17 00:00:00 2001 From: Nitya Sunkad Date: Thu, 6 Jul 2023 11:20:06 -0700 Subject: [PATCH 4080/4345] ionic: remove WARN_ON to prevent panic_on_warn [ Upstream commit abfb2a58a5377ebab717d4362d6180f901b6e5c1 ] Remove unnecessary early code development check and the WARN_ON that it uses. The irq alloc and free paths have long been cleaned up and this check shouldn't have stuck around so long. Fixes: 77ceb68e29cc ("ionic: Add notifyq support") Signed-off-by: Nitya Sunkad Signed-off-by: Shannon Nelson Reviewed-by: Jacob Keller Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index fcd4213c99b8..098772601df8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -433,11 +433,6 @@ static void ionic_qcqs_free(struct ionic_lif *lif) static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, struct ionic_qcq *n_qcq) { - if (WARN_ON(n_qcq->flags & IONIC_QCQ_F_INTR)) { - ionic_intr_free(n_qcq->cq.lif->ionic, n_qcq->intr.index); - n_qcq->flags &= ~IONIC_QCQ_F_INTR; - } - n_qcq->intr.vector = src_qcq->intr.vector; n_qcq->intr.index = src_qcq->intr.index; } From cddd04f341245949258d304f0bc961d298560f61 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 7 Jul 2023 08:53:25 +0200 Subject: [PATCH 4081/4345] net: bgmac: postpone turning IRQs off to avoid SoC hangs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit e7731194fdf085f46d58b1adccfddbd0dfee4873 ] Turning IRQs off is done by accessing Ethernet controller registers. That can't be done until device's clock is enabled. It results in a SoC hang otherwise. This bug remained unnoticed for years as most bootloaders keep all Ethernet interfaces turned on. It seems to only affect a niche SoC family BCM47189. It has two Ethernet controllers but CFE bootloader uses only the first one. Fixes: 34322615cbaa ("net: bgmac: Mask interrupts during probe") Signed-off-by: Rafał Miłecki Reviewed-by: Michal Kubiak Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bgmac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index bb999e67d773..ab8ee9331635 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1492,8 +1492,6 @@ int bgmac_enet_probe(struct bgmac *bgmac) bgmac->in_init = true; - bgmac_chip_intrs_off(bgmac); - net_dev->irq = bgmac->irq; SET_NETDEV_DEV(net_dev, bgmac->dev); dev_set_drvdata(bgmac->dev, bgmac); @@ -1511,6 +1509,8 @@ int bgmac_enet_probe(struct bgmac *bgmac) */ bgmac_clk_enable(bgmac, 0); + bgmac_chip_intrs_off(bgmac); + /* This seems to be fixing IRQ by assigning OOB #6 to the core */ if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6) From bc3ab5d2ab69823f5cff89cf74ef78ffa0386c9a Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 7 Jul 2023 10:11:10 +0200 Subject: [PATCH 4082/4345] net: prevent skb corruption on frag list segmentation [ Upstream commit c329b261afe71197d9da83c1f18eb45a7e97e089 ] Ian reported several skb corruptions triggered by rx-gro-list, collecting different oops alike: [ 62.624003] BUG: kernel NULL pointer dereference, address: 00000000000000c0 [ 62.631083] #PF: supervisor read access in kernel mode [ 62.636312] #PF: error_code(0x0000) - not-present page [ 62.641541] PGD 0 P4D 0 [ 62.644174] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 62.648629] CPU: 1 PID: 913 Comm: napi/eno2-79 Not tainted 6.4.0 #364 [ 62.655162] Hardware name: Supermicro Super Server/A2SDi-12C-HLN4F, BIOS 1.7a 10/13/2022 [ 62.663344] RIP: 0010:__udp_gso_segment (./include/linux/skbuff.h:2858 ./include/linux/udp.h:23 net/ipv4/udp_offload.c:228 net/ipv4/udp_offload.c:261 net/ipv4/udp_offload.c:277) [ 62.687193] RSP: 0018:ffffbd3a83b4f868 EFLAGS: 00010246 [ 62.692515] RAX: 00000000000000ce RBX: 0000000000000000 RCX: 0000000000000000 [ 62.699743] RDX: ffffa124def8a000 RSI: 0000000000000079 RDI: ffffa125952a14d4 [ 62.706970] RBP: ffffa124def8a000 R08: 0000000000000022 R09: 00002000001558c9 [ 62.714199] R10: 0000000000000000 R11: 00000000be554639 R12: 00000000000000e2 [ 62.721426] R13: ffffa125952a1400 R14: ffffa125952a1400 R15: 00002000001558c9 [ 62.728654] FS: 0000000000000000(0000) GS:ffffa127efa40000(0000) knlGS:0000000000000000 [ 62.736852] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 62.742702] CR2: 00000000000000c0 CR3: 00000001034b0000 CR4: 00000000003526e0 [ 62.749948] Call Trace: [ 62.752498] [ 62.779267] inet_gso_segment (net/ipv4/af_inet.c:1398) [ 62.787605] skb_mac_gso_segment (net/core/gro.c:141) [ 62.791906] __skb_gso_segment (net/core/dev.c:3403 (discriminator 2)) [ 62.800492] validate_xmit_skb (./include/linux/netdevice.h:4862 net/core/dev.c:3659) [ 62.804695] validate_xmit_skb_list (net/core/dev.c:3710) [ 62.809158] sch_direct_xmit (net/sched/sch_generic.c:330) [ 62.813198] __dev_queue_xmit (net/core/dev.c:3805 net/core/dev.c:4210) net/netfilter/core.c:626) [ 62.821093] br_dev_queue_push_xmit (net/bridge/br_forward.c:55) [ 62.825652] maybe_deliver (net/bridge/br_forward.c:193) [ 62.829420] br_flood (net/bridge/br_forward.c:233) [ 62.832758] br_handle_frame_finish (net/bridge/br_input.c:215) [ 62.837403] br_handle_frame (net/bridge/br_input.c:298 net/bridge/br_input.c:416) [ 62.851417] __netif_receive_skb_core.constprop.0 (net/core/dev.c:5387) [ 62.866114] __netif_receive_skb_list_core (net/core/dev.c:5570) [ 62.871367] netif_receive_skb_list_internal (net/core/dev.c:5638 net/core/dev.c:5727) [ 62.876795] napi_complete_done (./include/linux/list.h:37 ./include/net/gro.h:434 ./include/net/gro.h:429 net/core/dev.c:6067) [ 62.881004] ixgbe_poll (drivers/net/ethernet/intel/ixgbe/ixgbe_main.c:3191) [ 62.893534] __napi_poll (net/core/dev.c:6498) [ 62.897133] napi_threaded_poll (./include/linux/netpoll.h:89 net/core/dev.c:6640) [ 62.905276] kthread (kernel/kthread.c:379) [ 62.913435] ret_from_fork (arch/x86/entry/entry_64.S:314) [ 62.917119] In the critical scenario, rx-gro-list GRO-ed packets are fed, via a bridge, both to the local input path and to an egress device (tun). The segmentation of such packets unsafely writes to the cloned skbs with shared heads. This change addresses the issue by uncloning as needed the to-be-segmented skbs. Reported-by: Ian Kumlien Tested-by: Ian Kumlien Fixes: 3a1296a38d0c ("net: Support GRO/GSO fraglist chaining.") Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/core/skbuff.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e203172b9b9e..b10285d06a2c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3685,6 +3685,11 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_push(skb, -skb_network_offset(skb) + offset); + /* Ensure the head is writeable before touching the shared info */ + err = skb_unclone(skb, GFP_ATOMIC); + if (err) + goto err_linearize; + skb_shinfo(skb)->frag_list = NULL; while (list_skb) { From d30ddd7ff15df9d91a793ce3f06f0190ff7afacc Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 7 Jul 2023 18:43:27 -0700 Subject: [PATCH 4083/4345] icmp6: Fix null-ptr-deref of ip6_null_entry->rt6i_idev in icmp6_dev(). [ Upstream commit 2aaa8a15de73874847d62eb595c6683bface80fd ] With some IPv6 Ext Hdr (RPL, SRv6, etc.), we can send a packet that has the link-local address as src and dst IP and will be forwarded to an external IP in the IPv6 Ext Hdr. For example, the script below generates a packet whose src IP is the link-local address and dst is updated to 11::. # for f in $(find /proc/sys/net/ -name *seg6_enabled*); do echo 1 > $f; done # python3 >>> from socket import * >>> from scapy.all import * >>> >>> SRC_ADDR = DST_ADDR = "fe80::5054:ff:fe12:3456" >>> >>> pkt = IPv6(src=SRC_ADDR, dst=DST_ADDR) >>> pkt /= IPv6ExtHdrSegmentRouting(type=4, addresses=["11::", "22::"], segleft=1) >>> >>> sk = socket(AF_INET6, SOCK_RAW, IPPROTO_RAW) >>> sk.sendto(bytes(pkt), (DST_ADDR, 0)) For such a packet, we call ip6_route_input() to look up a route for the next destination in these three functions depending on the header type. * ipv6_rthdr_rcv() * ipv6_rpl_srh_rcv() * ipv6_srh_rcv() If no route is found, ip6_null_entry is set to skb, and the following dst_input(skb) calls ip6_pkt_drop(). Finally, in icmp6_dev(), we dereference skb_rt6_info(skb)->rt6i_idev->dev as the input device is the loopback interface. Then, we have to check if skb_rt6_info(skb)->rt6i_idev is NULL or not to avoid NULL pointer deref for ip6_null_entry. BUG: kernel NULL pointer dereference, address: 0000000000000000 PF: supervisor read access in kernel mode PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 157 Comm: python3 Not tainted 6.4.0-11996-gb121d614371c #35 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:icmp6_send (net/ipv6/icmp.c:436 net/ipv6/icmp.c:503) Code: fe ff ff 48 c7 40 30 c0 86 5d 83 e8 c6 44 1c 00 e9 c8 fc ff ff 49 8b 46 58 48 83 e0 fe 0f 84 4a fb ff ff 48 8b 80 d0 00 00 00 <48> 8b 00 44 8b 88 e0 00 00 00 e9 34 fb ff ff 4d 85 ed 0f 85 69 01 RSP: 0018:ffffc90000003c70 EFLAGS: 00000286 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 00000000000000e0 RDX: 0000000000000021 RSI: 0000000000000000 RDI: ffff888006d72a18 RBP: ffffc90000003d80 R08: 0000000000000000 R09: 0000000000000001 R10: ffffc90000003d98 R11: 0000000000000040 R12: ffff888006d72a10 R13: 0000000000000000 R14: ffff8880057fb800 R15: ffffffff835d86c0 FS: 00007f9dc72ee740(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000057b2000 CR4: 00000000007506f0 PKRU: 55555554 Call Trace: ip6_pkt_drop (net/ipv6/route.c:4513) ipv6_rthdr_rcv (net/ipv6/exthdrs.c:640 net/ipv6/exthdrs.c:686) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:437 (discriminator 5)) ip6_input_finish (./include/linux/rcupdate.h:781 net/ipv6/ip6_input.c:483) __netif_receive_skb_one_core (net/core/dev.c:5455) process_backlog (./include/linux/rcupdate.h:781 net/core/dev.c:5895) __napi_poll (net/core/dev.c:6460) net_rx_action (net/core/dev.c:6529 net/core/dev.c:6660) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:554) do_softirq (kernel/softirq.c:454 kernel/softirq.c:441) __local_bh_enable_ip (kernel/softirq.c:381) __dev_queue_xmit (net/core/dev.c:4231) ip6_finish_output2 (./include/net/neighbour.h:544 net/ipv6/ip6_output.c:135) rawv6_sendmsg (./include/net/dst.h:458 ./include/linux/netfilter.h:303 net/ipv6/raw.c:656 net/ipv6/raw.c:914) sock_sendmsg (net/socket.c:725 net/socket.c:748) __sys_sendto (net/socket.c:2134) __x64_sys_sendto (net/socket.c:2146 net/socket.c:2142 net/socket.c:2142) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f9dc751baea Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 RSP: 002b:00007ffe98712c38 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007ffe98712cf8 RCX: 00007f9dc751baea RDX: 0000000000000060 RSI: 00007f9dc6460b90 RDI: 0000000000000003 RBP: 00007f9dc56e8be0 R08: 00007ffe98712d70 R09: 000000000000001c R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: ffffffffc4653600 R14: 0000000000000001 R15: 00007f9dc6af5d1b Modules linked in: CR2: 0000000000000000 ---[ end trace 0000000000000000 ]--- RIP: 0010:icmp6_send (net/ipv6/icmp.c:436 net/ipv6/icmp.c:503) Code: fe ff ff 48 c7 40 30 c0 86 5d 83 e8 c6 44 1c 00 e9 c8 fc ff ff 49 8b 46 58 48 83 e0 fe 0f 84 4a fb ff ff 48 8b 80 d0 00 00 00 <48> 8b 00 44 8b 88 e0 00 00 00 e9 34 fb ff ff 4d 85 ed 0f 85 69 01 RSP: 0018:ffffc90000003c70 EFLAGS: 00000286 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 00000000000000e0 RDX: 0000000000000021 RSI: 0000000000000000 RDI: ffff888006d72a18 RBP: ffffc90000003d80 R08: 0000000000000000 R09: 0000000000000001 R10: ffffc90000003d98 R11: 0000000000000040 R12: ffff888006d72a10 R13: 0000000000000000 R14: ffff8880057fb800 R15: ffffffff835d86c0 FS: 00007f9dc72ee740(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000057b2000 CR4: 00000000007506f0 PKRU: 55555554 Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: disabled Fixes: 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address") Reported-by: Wang Yufen Closes: https://lore.kernel.org/netdev/c41403a9-c2f6-3b7e-0c96-e1901e605cd0@huawei.com/ Signed-off-by: Kuniyuki Iwashima Reviewed-by: David Ahern Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/icmp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index fd1f896115c1..d01165bb6a32 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -429,7 +429,10 @@ static struct net_device *icmp6_dev(const struct sk_buff *skb) if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); - if (rt6) + /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.), + * and ip6_null_entry could be set to skb if no route is found. + */ + if (rt6 && rt6->rt6i_idev) dev = rt6->rt6i_idev->dev; } From 3e8fed805cf3f8597bdfd0bea923f5a756fbe726 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 8 Jul 2023 08:29:58 +0000 Subject: [PATCH 4084/4345] udp6: fix udp6_ehashfn() typo [ Upstream commit 51d03e2f2203e76ed02d33fb5ffbb5fc85ffaf54 ] Amit Klein reported that udp6_ehash_secret was initialized but never used. Fixes: 1bbdceef1e53 ("inet: convert inet_ehash_secret and ipv6_hash_secret to net_get_random_once") Reported-by: Amit Klein Signed-off-by: Eric Dumazet Cc: Willy Tarreau Cc: Willem de Bruijn Cc: David Ahern Cc: Hannes Frederic Sowa Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/udp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 19c0721399d9..788bb19f32e9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -87,7 +87,7 @@ static u32 udp6_ehashfn(const struct net *net, fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, - udp_ipv6_hash_secret + net_hash_mix(net)); + udp6_ehash_secret + net_hash_mix(net)); } int udp_v6_get_port(struct sock *sk, unsigned short snum) From 0bb2683b0cde42cec4eae87a3ecc064b9714253e Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Sat, 5 Nov 2022 09:43:01 +0000 Subject: [PATCH 4085/4345] ntb: idt: Fix error handling in idt_pci_driver_init() [ Upstream commit c012968259b451dc4db407f2310fe131eaefd800 ] A problem about ntb_hw_idt create debugfs failed is triggered with the following log given: [ 1236.637636] IDT PCI-E Non-Transparent Bridge Driver 2.0 [ 1236.639292] debugfs: Directory 'ntb_hw_idt' with parent '/' already present! The reason is that idt_pci_driver_init() returns pci_register_driver() directly without checking its return value, if pci_register_driver() failed, it returns without destroy the newly created debugfs, resulting the debugfs of ntb_hw_idt can never be created later. idt_pci_driver_init() debugfs_create_dir() # create debugfs directory pci_register_driver() driver_register() bus_add_driver() priv = kzalloc(...) # OOM happened # return without destroy debugfs directory Fix by removing debugfs when pci_register_driver() returns error. Fixes: bf2a952d31d2 ("NTB: Add IDT 89HPESxNTx PCIe-switches support") Signed-off-by: Yuan Can Signed-off-by: Jon Mason Signed-off-by: Sasha Levin --- drivers/ntb/hw/idt/ntb_hw_idt.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c index d54261f50851..99711dd0b6e8 100644 --- a/drivers/ntb/hw/idt/ntb_hw_idt.c +++ b/drivers/ntb/hw/idt/ntb_hw_idt.c @@ -2902,6 +2902,7 @@ static struct pci_driver idt_pci_driver = { static int __init idt_pci_driver_init(void) { + int ret; pr_info("%s %s\n", NTB_DESC, NTB_VER); /* Create the top DebugFS directory if the FS is initialized */ @@ -2909,7 +2910,11 @@ static int __init idt_pci_driver_init(void) dbgfs_topdir = debugfs_create_dir(KBUILD_MODNAME, NULL); /* Register the NTB hardware driver to handle the PCI device */ - return pci_register_driver(&idt_pci_driver); + ret = pci_register_driver(&idt_pci_driver); + if (ret) + debugfs_remove_recursive(dbgfs_topdir); + + return ret; } module_init(idt_pci_driver_init); From 23e09f0a868f059b75d46b65770e4bab081bad94 Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Sat, 5 Nov 2022 09:43:09 +0000 Subject: [PATCH 4086/4345] NTB: amd: Fix error handling in amd_ntb_pci_driver_init() [ Upstream commit 98af0a33c1101c29b3ce4f0cf4715fd927c717f9 ] A problem about ntb_hw_amd create debugfs failed is triggered with the following log given: [ 618.431232] AMD(R) PCI-E Non-Transparent Bridge Driver 1.0 [ 618.433284] debugfs: Directory 'ntb_hw_amd' with parent '/' already present! The reason is that amd_ntb_pci_driver_init() returns pci_register_driver() directly without checking its return value, if pci_register_driver() failed, it returns without destroy the newly created debugfs, resulting the debugfs of ntb_hw_amd can never be created later. amd_ntb_pci_driver_init() debugfs_create_dir() # create debugfs directory pci_register_driver() driver_register() bus_add_driver() priv = kzalloc(...) # OOM happened # return without destroy debugfs directory Fix by removing debugfs when pci_register_driver() returns error. Fixes: a1b3695820aa ("NTB: Add support for AMD PCI-Express Non-Transparent Bridge") Signed-off-by: Yuan Can Signed-off-by: Jon Mason Signed-off-by: Sasha Levin --- drivers/ntb/hw/amd/ntb_hw_amd.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 71428d8cbcfc..ac401ad7884a 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -1344,12 +1344,17 @@ static struct pci_driver amd_ntb_pci_driver = { static int __init amd_ntb_pci_driver_init(void) { + int ret; pr_info("%s %s\n", NTB_DESC, NTB_VER); if (debugfs_initialized()) debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL); - return pci_register_driver(&amd_ntb_pci_driver); + ret = pci_register_driver(&amd_ntb_pci_driver); + if (ret) + debugfs_remove_recursive(debugfs_dir); + + return ret; } module_init(amd_ntb_pci_driver_init); From 03cfa0653406ee0bc615006129a63044c46263bc Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Sat, 5 Nov 2022 09:43:22 +0000 Subject: [PATCH 4087/4345] ntb: intel: Fix error handling in intel_ntb_pci_driver_init() [ Upstream commit 4c3c796aca02883ad35bb117468938cc4022ca41 ] A problem about ntb_hw_intel create debugfs failed is triggered with the following log given: [ 273.112733] Intel(R) PCI-E Non-Transparent Bridge Driver 2.0 [ 273.115342] debugfs: Directory 'ntb_hw_intel' with parent '/' already present! The reason is that intel_ntb_pci_driver_init() returns pci_register_driver() directly without checking its return value, if pci_register_driver() failed, it returns without destroy the newly created debugfs, resulting the debugfs of ntb_hw_intel can never be created later. intel_ntb_pci_driver_init() debugfs_create_dir() # create debugfs directory pci_register_driver() driver_register() bus_add_driver() priv = kzalloc(...) # OOM happened # return without destroy debugfs directory Fix by removing debugfs when pci_register_driver() returns error. Fixes: e26a5843f7f5 ("NTB: Split ntb_hw_intel and ntb_transport drivers") Signed-off-by: Yuan Can Acked-by: Dave Jiang Signed-off-by: Jon Mason Signed-off-by: Sasha Levin --- drivers/ntb/hw/intel/ntb_hw_gen1.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/ntb/hw/intel/ntb_hw_gen1.c b/drivers/ntb/hw/intel/ntb_hw_gen1.c index 093dd20057b9..4f1add57d81d 100644 --- a/drivers/ntb/hw/intel/ntb_hw_gen1.c +++ b/drivers/ntb/hw/intel/ntb_hw_gen1.c @@ -2068,12 +2068,17 @@ static struct pci_driver intel_ntb_pci_driver = { static int __init intel_ntb_pci_driver_init(void) { + int ret; pr_info("%s %s\n", NTB_DESC, NTB_VER); if (debugfs_initialized()) debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL); - return pci_register_driver(&intel_ntb_pci_driver); + ret = pci_register_driver(&intel_ntb_pci_driver); + if (ret) + debugfs_remove_recursive(debugfs_dir); + + return ret; } module_init(intel_ntb_pci_driver_init); From 41c6d8ff71cd93748153cd186ff713e23c6f5e2a Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 10 Nov 2022 23:19:17 +0800 Subject: [PATCH 4088/4345] NTB: ntb_transport: fix possible memory leak while device_register() fails [ Upstream commit 8623ccbfc55d962e19a3537652803676ad7acb90 ] If device_register() returns error, the name allocated by dev_set_name() need be freed. As comment of device_register() says, it should use put_device() to give up the reference in the error path. So fix this by calling put_device(), then the name can be freed in kobject_cleanup(), and client_dev is freed in ntb_transport_client_release(). Fixes: fce8a7bb5b4b ("PCI-Express Non-Transparent Bridge Support") Signed-off-by: Yang Yingliang Reviewed-by: Dave Jiang Signed-off-by: Jon Mason Signed-off-by: Sasha Levin --- drivers/ntb/ntb_transport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 4a02561cfb96..d18cb4476560 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -412,7 +412,7 @@ int ntb_transport_register_client_dev(char *device_name) rc = device_register(dev); if (rc) { - kfree(client_dev); + put_device(dev); goto err; } From 8271145523a5f6e71fd82ae706225a8bd8e6efc7 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Tue, 22 Nov 2022 11:32:44 +0800 Subject: [PATCH 4089/4345] NTB: ntb_tool: Add check for devm_kcalloc [ Upstream commit 2790143f09938776a3b4f69685b380bae8fd06c7 ] As the devm_kcalloc may return NULL pointer, it should be better to add check for the return value, as same as the others. Fixes: 7f46c8b3a552 ("NTB: ntb_tool: Add full multi-port NTB API support") Signed-off-by: Jiasheng Jiang Reviewed-by: Serge Semin Reviewed-by: Dave Jiang Signed-off-by: Jon Mason Signed-off-by: Sasha Levin --- drivers/ntb/test/ntb_tool.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c index 5ee0afa621a9..eeeb4b1c97d2 100644 --- a/drivers/ntb/test/ntb_tool.c +++ b/drivers/ntb/test/ntb_tool.c @@ -998,6 +998,8 @@ static int tool_init_mws(struct tool_ctx *tc) tc->peers[pidx].outmws = devm_kcalloc(&tc->ntb->dev, tc->peers[pidx].outmw_cnt, sizeof(*tc->peers[pidx].outmws), GFP_KERNEL); + if (tc->peers[pidx].outmws == NULL) + return -ENOMEM; for (widx = 0; widx < tc->peers[pidx].outmw_cnt; widx++) { tc->peers[pidx].outmws[widx].pidx = pidx; From 2ad31ce40e8182860b631e37209e93e543790b7c Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Sat, 8 Jul 2023 14:59:10 +0800 Subject: [PATCH 4090/4345] ipv6/addrconf: fix a potential refcount underflow for idev [ Upstream commit 06a0716949c22e2aefb648526580671197151acc ] Now in addrconf_mod_rs_timer(), reference idev depends on whether rs_timer is not pending. Then modify rs_timer timeout. There is a time gap in [1], during which if the pending rs_timer becomes not pending. It will miss to hold idev, but the rs_timer is activated. Thus rs_timer callback function addrconf_rs_timer() will be executed and put idev later without holding idev. A refcount underflow issue for idev can be caused by this. if (!timer_pending(&idev->rs_timer)) in6_dev_hold(idev); <--------------[1] mod_timer(&idev->rs_timer, jiffies + when); To fix the issue, hold idev if mod_timer() return 0. Fixes: b7b1bfce0bb6 ("ipv6: split duplicate address detection and router solicitation timer") Suggested-by: Eric Dumazet Signed-off-by: Ziyang Xuan Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/addrconf.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ed1e5bfc97b3..d5d10496b4ae 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -314,9 +314,8 @@ static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) static void addrconf_mod_rs_timer(struct inet6_dev *idev, unsigned long when) { - if (!timer_pending(&idev->rs_timer)) + if (!mod_timer(&idev->rs_timer, jiffies + when)) in6_dev_hold(idev); - mod_timer(&idev->rs_timer, jiffies + when); } static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, From 88dfb592d2c15bcb5cb37f40e3f2cbe61260b7e9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20P=C5=91cze?= Date: Sat, 4 Sep 2021 17:55:16 +0000 Subject: [PATCH 4091/4345] platform/x86: wmi: remove unnecessary argument MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 84eacf7e6413d5e2d2f4f9dddf9216c18a3631cf ] The GUID block is available for `wmi_create_device()` through `wblock->gblock`. Use that consistently in the function instead of using a mix of `gblock` and `wblock->gblock`. Signed-off-by: Barnabás Pőcze Link: https://lore.kernel.org/r/20210904175450.156801-8-pobrn@protonmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Stable-dep-of: 028e6e204ace ("platform/x86: wmi: Break possible infinite loop when parsing GUID") Signed-off-by: Sasha Levin --- drivers/platform/x86/wmi.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 1f80b2628162..9a6dc2717e1d 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -1042,7 +1042,6 @@ static const struct device_type wmi_type_data = { }; static int wmi_create_device(struct device *wmi_bus_dev, - const struct guid_block *gblock, struct wmi_block *wblock, struct acpi_device *device) { @@ -1050,12 +1049,12 @@ static int wmi_create_device(struct device *wmi_bus_dev, char method[5]; int result; - if (gblock->flags & ACPI_WMI_EVENT) { + if (wblock->gblock.flags & ACPI_WMI_EVENT) { wblock->dev.dev.type = &wmi_type_event; goto out_init; } - if (gblock->flags & ACPI_WMI_METHOD) { + if (wblock->gblock.flags & ACPI_WMI_METHOD) { wblock->dev.dev.type = &wmi_type_method; mutex_init(&wblock->char_mutex); goto out_init; @@ -1105,7 +1104,7 @@ static int wmi_create_device(struct device *wmi_bus_dev, wblock->dev.dev.bus = &wmi_bus_type; wblock->dev.dev.parent = wmi_bus_dev; - dev_set_name(&wblock->dev.dev, "%pUL", gblock->guid); + dev_set_name(&wblock->dev.dev, "%pUL", wblock->gblock.guid); device_initialize(&wblock->dev.dev); @@ -1197,7 +1196,7 @@ static int parse_wdg(struct device *wmi_bus_dev, struct acpi_device *device) wblock->acpi_device = device; wblock->gblock = gblock[i]; - retval = wmi_create_device(wmi_bus_dev, &gblock[i], wblock, device); + retval = wmi_create_device(wmi_bus_dev, wblock, device); if (retval) { kfree(wblock); continue; From 4bb2bb69bd9a4f806dc12a0633e76c1904790117 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20P=C5=91cze?= Date: Sat, 4 Sep 2021 17:55:39 +0000 Subject: [PATCH 4092/4345] platform/x86: wmi: use guid_t and guid_equal() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 67f472fdacf4a691b1c3c20c27800b23ce31e2de ] Instead of hard-coding a 16 long byte array, use the available `guid_t` type and related methods. Signed-off-by: Barnabás Pőcze Link: https://lore.kernel.org/r/20210904175450.156801-15-pobrn@protonmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Stable-dep-of: 028e6e204ace ("platform/x86: wmi: Break possible infinite loop when parsing GUID") Signed-off-by: Sasha Levin --- drivers/platform/x86/wmi.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 9a6dc2717e1d..18c4080d4a71 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -40,7 +40,7 @@ MODULE_LICENSE("GPL"); static LIST_HEAD(wmi_block_list); struct guid_block { - char guid[16]; + guid_t guid; union { char object_id[2]; struct { @@ -121,7 +121,7 @@ static bool find_guid(const char *guid_string, struct wmi_block **out) list_for_each_entry(wblock, &wmi_block_list, list) { block = &wblock->gblock; - if (memcmp(block->guid, &guid_input, 16) == 0) { + if (guid_equal(&block->guid, &guid_input)) { if (out) *out = wblock; return true; @@ -145,7 +145,7 @@ static const void *find_guid_context(struct wmi_block *wblock, while (*id->guid_string) { if (guid_parse(id->guid_string, &guid_input)) continue; - if (!memcmp(wblock->gblock.guid, &guid_input, 16)) + if (guid_equal(&wblock->gblock.guid, &guid_input)) return id->context; id++; } @@ -457,7 +457,7 @@ EXPORT_SYMBOL_GPL(wmi_set_block); static void wmi_dump_wdg(const struct guid_block *g) { - pr_info("%pUL:\n", g->guid); + pr_info("%pUL:\n", &g->guid); if (g->flags & ACPI_WMI_EVENT) pr_info("\tnotify_id: 0x%02X\n", g->notify_id); else @@ -539,7 +539,7 @@ wmi_notify_handler handler, void *data) list_for_each_entry(block, &wmi_block_list, list) { acpi_status wmi_status; - if (memcmp(block->gblock.guid, &guid_input, 16) == 0) { + if (guid_equal(&block->gblock.guid, &guid_input)) { if (block->handler && block->handler != wmi_notify_debug) return AE_ALREADY_ACQUIRED; @@ -579,7 +579,7 @@ acpi_status wmi_remove_notify_handler(const char *guid) list_for_each_entry(block, &wmi_block_list, list) { acpi_status wmi_status; - if (memcmp(block->gblock.guid, &guid_input, 16) == 0) { + if (guid_equal(&block->gblock.guid, &guid_input)) { if (!block->handler || block->handler == wmi_notify_debug) return AE_NULL_ENTRY; @@ -685,7 +685,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, { struct wmi_block *wblock = dev_to_wblock(dev); - return sprintf(buf, "wmi:%pUL\n", wblock->gblock.guid); + return sprintf(buf, "wmi:%pUL\n", &wblock->gblock.guid); } static DEVICE_ATTR_RO(modalias); @@ -694,7 +694,7 @@ static ssize_t guid_show(struct device *dev, struct device_attribute *attr, { struct wmi_block *wblock = dev_to_wblock(dev); - return sprintf(buf, "%pUL\n", wblock->gblock.guid); + return sprintf(buf, "%pUL\n", &wblock->gblock.guid); } static DEVICE_ATTR_RO(guid); @@ -777,10 +777,10 @@ static int wmi_dev_uevent(struct device *dev, struct kobj_uevent_env *env) { struct wmi_block *wblock = dev_to_wblock(dev); - if (add_uevent_var(env, "MODALIAS=wmi:%pUL", wblock->gblock.guid)) + if (add_uevent_var(env, "MODALIAS=wmi:%pUL", &wblock->gblock.guid)) return -ENOMEM; - if (add_uevent_var(env, "WMI_GUID=%pUL", wblock->gblock.guid)) + if (add_uevent_var(env, "WMI_GUID=%pUL", &wblock->gblock.guid)) return -ENOMEM; return 0; @@ -808,7 +808,7 @@ static int wmi_dev_match(struct device *dev, struct device_driver *driver) if (WARN_ON(guid_parse(id->guid_string, &driver_guid))) continue; - if (!memcmp(&driver_guid, wblock->gblock.guid, 16)) + if (guid_equal(&driver_guid, &wblock->gblock.guid)) return 1; id++; @@ -1104,7 +1104,7 @@ static int wmi_create_device(struct device *wmi_bus_dev, wblock->dev.dev.bus = &wmi_bus_type; wblock->dev.dev.parent = wmi_bus_dev; - dev_set_name(&wblock->dev.dev, "%pUL", wblock->gblock.guid); + dev_set_name(&wblock->dev.dev, "%pUL", &wblock->gblock.guid); device_initialize(&wblock->dev.dev); @@ -1124,12 +1124,12 @@ static void wmi_free_devices(struct acpi_device *device) } } -static bool guid_already_parsed(struct acpi_device *device, const u8 *guid) +static bool guid_already_parsed(struct acpi_device *device, const guid_t *guid) { struct wmi_block *wblock; list_for_each_entry(wblock, &wmi_block_list, list) { - if (memcmp(wblock->gblock.guid, guid, 16) == 0) { + if (guid_equal(&wblock->gblock.guid, guid)) { /* * Because we historically didn't track the relationship * between GUIDs and ACPI nodes, we don't know whether @@ -1184,7 +1184,7 @@ static int parse_wdg(struct device *wmi_bus_dev, struct acpi_device *device) * case yet, so for now, we'll just ignore the duplicate * for device creation. */ - if (guid_already_parsed(device, gblock[i].guid)) + if (guid_already_parsed(device, &gblock[i].guid)) continue; wblock = kzalloc(sizeof(struct wmi_block), GFP_KERNEL); @@ -1221,7 +1221,7 @@ static int parse_wdg(struct device *wmi_bus_dev, struct acpi_device *device) retval = device_add(&wblock->dev.dev); if (retval) { dev_err(wmi_bus_dev, "failed to register %pUL\n", - wblock->gblock.guid); + &wblock->gblock.guid); if (debug_event) wmi_method_enable(wblock, 0); list_del(&wblock->list); @@ -1335,7 +1335,7 @@ static void acpi_wmi_notify_handler(acpi_handle handle, u32 event, } if (debug_event) - pr_info("DEBUG Event GUID: %pUL\n", wblock->gblock.guid); + pr_info("DEBUG Event GUID: %pUL\n", &wblock->gblock.guid); acpi_bus_generate_netlink_event( wblock->acpi_device->pnp.device_class, From 7157ee0de522b588f08a61f3432bec5b88ccb1f1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Barnab=C3=A1s=20P=C5=91cze?= Date: Sat, 4 Sep 2021 17:56:10 +0000 Subject: [PATCH 4093/4345] platform/x86: wmi: move variables MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit f5431bf1e6781e876bdc8ae10fb1e7da6f1aa9b5 ] Move some variables in order to keep them in the narrowest possible scope. Signed-off-by: Barnabás Pőcze Link: https://lore.kernel.org/r/20210904175450.156801-22-pobrn@protonmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Stable-dep-of: 028e6e204ace ("platform/x86: wmi: Break possible infinite loop when parsing GUID") Signed-off-by: Sasha Levin --- drivers/platform/x86/wmi.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 18c4080d4a71..5e4c03f7db7c 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -134,7 +134,6 @@ static const void *find_guid_context(struct wmi_block *wblock, struct wmi_driver *wdriver) { const struct wmi_device_id *id; - guid_t guid_input; if (wblock == NULL || wdriver == NULL) return NULL; @@ -143,6 +142,8 @@ static const void *find_guid_context(struct wmi_block *wblock, id = wdriver->id_table; while (*id->guid_string) { + guid_t guid_input; + if (guid_parse(id->guid_string, &guid_input)) continue; if (guid_equal(&wblock->gblock.guid, &guid_input)) @@ -615,7 +616,6 @@ acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out) { struct acpi_object_list input; union acpi_object params[1]; - struct guid_block *gblock; struct wmi_block *wblock; input.count = 1; @@ -624,7 +624,7 @@ acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out) params[0].integer.value = event; list_for_each_entry(wblock, &wmi_block_list, list) { - gblock = &wblock->gblock; + struct guid_block *gblock = &wblock->gblock; if ((gblock->flags & ACPI_WMI_EVENT) && (gblock->notify_id == event)) @@ -1281,12 +1281,11 @@ acpi_wmi_ec_space_handler(u32 function, acpi_physical_address address, static void acpi_wmi_notify_handler(acpi_handle handle, u32 event, void *context) { - struct guid_block *block; struct wmi_block *wblock; bool found_it = false; list_for_each_entry(wblock, &wmi_block_list, list) { - block = &wblock->gblock; + struct guid_block *block = &wblock->gblock; if (wblock->acpi_device->handle == handle && (block->flags & ACPI_WMI_EVENT) && From cdf5b9af92dae93311098178cfa9dc42f96e7c0a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 21 Jun 2023 18:11:54 +0300 Subject: [PATCH 4094/4345] platform/x86: wmi: Break possible infinite loop when parsing GUID [ Upstream commit 028e6e204ace1f080cfeacd72c50397eb8ae8883 ] The while-loop may break on one of the two conditions, either ID string is empty or GUID matches. The second one, may never be reached if the parsed string is not correct GUID. In such a case the loop will never advance to check the next ID. Break possible infinite loop by factoring out guid_parse_and_compare() helper which may be moved to the generic header for everyone later on and preventing from similar mistake in the future. Interestingly that firstly it appeared when WMI was turned into a bus driver, but later when duplicated GUIDs were checked, the while-loop has been replaced by for-loop and hence no mistake made again. Fixes: a48e23385fcf ("platform/x86: wmi: add context pointer field to struct wmi_device_id") Fixes: 844af950da94 ("platform/x86: wmi: Turn WMI into a bus driver") Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230621151155.78279-1-andriy.shevchenko@linux.intel.com Tested-by: Armin Wolf Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/wmi.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 5e4c03f7db7c..567c28705cb1 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -130,6 +130,16 @@ static bool find_guid(const char *guid_string, struct wmi_block **out) return false; } +static bool guid_parse_and_compare(const char *string, const guid_t *guid) +{ + guid_t guid_input; + + if (guid_parse(string, &guid_input)) + return false; + + return guid_equal(&guid_input, guid); +} + static const void *find_guid_context(struct wmi_block *wblock, struct wmi_driver *wdriver) { @@ -142,11 +152,7 @@ static const void *find_guid_context(struct wmi_block *wblock, id = wdriver->id_table; while (*id->guid_string) { - guid_t guid_input; - - if (guid_parse(id->guid_string, &guid_input)) - continue; - if (guid_equal(&wblock->gblock.guid, &guid_input)) + if (guid_parse_and_compare(id->guid_string, &wblock->gblock.guid)) return id->context; id++; } @@ -804,11 +810,7 @@ static int wmi_dev_match(struct device *dev, struct device_driver *driver) return 0; while (*id->guid_string) { - guid_t driver_guid; - - if (WARN_ON(guid_parse(id->guid_string, &driver_guid))) - continue; - if (guid_equal(&driver_guid, &wblock->gblock.guid)) + if (guid_parse_and_compare(id->guid_string, &wblock->gblock.guid)) return 1; id++; From c48e8ee81ad35ceace0e971b37948887d4411da8 Mon Sep 17 00:00:00 2001 From: Florian Kauer Date: Wed, 14 Jun 2023 16:07:13 +0200 Subject: [PATCH 4095/4345] igc: Fix launchtime before start of cycle [ Upstream commit c1bca9ac0bcb355be11354c2e68bc7bf31f5ac5a ] It is possible (verified on a running system) that frames are processed by igc_tx_launchtime with a txtime before the start of the cycle (baset_est). However, the result of txtime - baset_est is written into a u32, leading to a wrap around to a positive number. The following launchtime > 0 check will only branch to executing launchtime = 0 if launchtime is already 0. Fix it by using a s32 before checking launchtime > 0. Fixes: db0b124f02ba ("igc: Enhance Qbv scheduling by using first flag bit") Signed-off-by: Florian Kauer Reviewed-by: Kurt Kanzenbach Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 2b51ee87a2de..051b1048eb41 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -905,7 +905,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime, ktime_t base_time = adapter->base_time; ktime_t now = ktime_get_clocktai(); ktime_t baset_est, end_of_cycle; - u32 launchtime; + s32 launchtime; s64 n; n = div64_s64(ktime_sub_ns(now, base_time), cycle_time); From 83579a626169b35553945ff48aa5936b5db06ed2 Mon Sep 17 00:00:00 2001 From: Florian Kauer Date: Wed, 14 Jun 2023 16:07:14 +0200 Subject: [PATCH 4096/4345] igc: Fix inserting of empty frame for launchtime [ Upstream commit 0bcc62858d6ba62cbade957d69745e6adeed5f3d ] The insertion of an empty frame was introduced with commit db0b124f02ba ("igc: Enhance Qbv scheduling by using first flag bit") in order to ensure that the current cycle has at least one packet if there is some packet to be scheduled for the next cycle. However, the current implementation does not properly check if a packet is already scheduled for the current cycle. Currently, an empty packet is always inserted if and only if txtime >= end_of_cycle && txtime > last_tx_cycle but since last_tx_cycle is always either the end of the current cycle (end_of_cycle) or the end of a previous cycle, the second part (txtime > last_tx_cycle) is always true unless txtime == last_tx_cycle. What actually needs to be checked here is if the last_tx_cycle was already written within the current cycle, so an empty frame should only be inserted if and only if txtime >= end_of_cycle && end_of_cycle > last_tx_cycle. This patch does not only avoid an unnecessary insertion, but it can actually be harmful to insert an empty packet if packets are already scheduled in the current cycle, because it can lead to a situation where the empty packet is actually processed as the first packet in the upcoming cycle shifting the packet with the first_flag even one cycle into the future, finally leading to a TX hang. The TX hang can be reproduced on a i225 with: sudo tc qdisc replace dev enp1s0 parent root handle 100 taprio \ num_tc 1 \ map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 \ queues 1@0 \ base-time 0 \ sched-entry S 01 300000 \ flags 0x1 \ txtime-delay 500000 \ clockid CLOCK_TAI sudo tc qdisc replace dev enp1s0 parent 100:1 etf \ clockid CLOCK_TAI \ delta 500000 \ offload \ skip_sock_check and traffic generator sudo trafgen -i traffic.cfg -o enp1s0 --cpp -n0 -q -t1400ns with traffic.cfg #define ETH_P_IP 0x0800 { /* Ethernet Header */ 0x30, 0x1f, 0x9a, 0xd0, 0xf0, 0x0e, # MAC Dest - adapt as needed 0x24, 0x5e, 0xbe, 0x57, 0x2e, 0x36, # MAC Src - adapt as needed const16(ETH_P_IP), /* IPv4 Header */ 0b01000101, 0, # IPv4 version, IHL, TOS const16(1028), # IPv4 total length (UDP length + 20 bytes (IP header)) const16(2), # IPv4 ident 0b01000000, 0, # IPv4 flags, fragmentation off 64, # IPv4 TTL 17, # Protocol UDP csumip(14, 33), # IPv4 checksum /* UDP Header */ 10, 0, 48, 1, # IP Src - adapt as needed 10, 0, 48, 10, # IP Dest - adapt as needed const16(5555), # UDP Src Port const16(6666), # UDP Dest Port const16(1008), # UDP length (UDP header 8 bytes + payload length) csumudp(14, 34), # UDP checksum /* Payload */ fill('W', 1000), } and the observed message with that is for example igc 0000:01:00.0 enp1s0: Detected Tx Unit Hang Tx Queue <0> TDH <32> TDT <3c> next_to_use <3c> next_to_clean <32> buffer_info[next_to_clean] time_stamp next_to_watch <00000000632a1828> jiffies desc.status <1048000> Fixes: db0b124f02ba ("igc: Enhance Qbv scheduling by using first flag bit") Signed-off-by: Florian Kauer Reviewed-by: Kurt Kanzenbach Tested-by: Naama Meir Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 051b1048eb41..631ce793fb2e 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -918,7 +918,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime, *first_flag = true; ring->last_ff_cycle = baset_est; - if (ktime_compare(txtime, ring->last_tx_cycle) > 0) + if (ktime_compare(end_of_cycle, ring->last_tx_cycle) > 0) *insert_empty = true; } } From 7c616437981f40a1c93fb28e6cb17ea25d87be2b Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Tue, 30 Mar 2021 02:24:54 +0800 Subject: [PATCH 4097/4345] riscv: bpf: Move bpf_jit_alloc_exec() and bpf_jit_free_exec() to core [ Upstream commit 1d27d854425faec98f352cf88ec3e2a8844429a4 ] We will drop the executable permissions of the code pages from the mapping at allocation time soon. Move bpf_jit_alloc_exec() and bpf_jit_free_exec() to bpf_jit_core.c so that they can be shared by both RV64I and RV32I. Signed-off-by: Jisheng Zhang Acked-by: Luke Nelson Signed-off-by: Palmer Dabbelt Stable-dep-of: c56fb2aab235 ("riscv, bpf: Fix inconsistent JIT image generation") Signed-off-by: Sasha Levin --- arch/riscv/net/bpf_jit_comp64.c | 13 ------------- arch/riscv/net/bpf_jit_core.c | 13 +++++++++++++ 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index c113ae818b14..053dc83e323b 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -1144,16 +1144,3 @@ void bpf_jit_build_epilogue(struct rv_jit_context *ctx) { __build_epilogue(false, ctx); } - -void *bpf_jit_alloc_exec(unsigned long size) -{ - return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, - BPF_JIT_REGION_END, GFP_KERNEL, - PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, - __builtin_return_address(0)); -} - -void bpf_jit_free_exec(void *addr) -{ - return vfree(addr); -} diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index cbf7d2414886..e295c9eed9e9 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -165,3 +165,16 @@ out: tmp : orig_prog); return prog; } + +void *bpf_jit_alloc_exec(unsigned long size) +{ + return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, + BPF_JIT_REGION_END, GFP_KERNEL, + PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + __builtin_return_address(0)); +} + +void bpf_jit_free_exec(void *addr) +{ + return vfree(addr); +} From eb3d1d84f3d68c293579495728d2fef8be35c11a Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Tue, 30 Mar 2021 02:25:21 +0800 Subject: [PATCH 4098/4345] riscv: bpf: Avoid breaking W^X [ Upstream commit fc8504765ec5e812135b8ccafca7101069a0c6d8 ] We allocate Non-executable pages, then call bpf_jit_binary_lock_ro() to enable executable permission after mapping them read-only. This is to prepare for STRICT_MODULE_RWX in following patch. Signed-off-by: Jisheng Zhang Signed-off-by: Palmer Dabbelt Stable-dep-of: c56fb2aab235 ("riscv, bpf: Fix inconsistent JIT image generation") Signed-off-by: Sasha Levin --- arch/riscv/net/bpf_jit_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index e295c9eed9e9..5d247198c30d 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -153,6 +153,7 @@ skip_init_ctx: bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); if (!prog->is_func || extra_pass) { + bpf_jit_binary_lock_ro(jit_data->header); out_offset: kfree(ctx->offset); kfree(jit_data); @@ -170,7 +171,7 @@ void *bpf_jit_alloc_exec(unsigned long size) { return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, BPF_JIT_REGION_END, GFP_KERNEL, - PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); } From a976adc3bca46e9f60345e9387d59463c58b8c7d Mon Sep 17 00:00:00 2001 From: Pu Lehui Date: Mon, 30 May 2022 17:28:11 +0800 Subject: [PATCH 4099/4345] bpf, riscv: Support riscv jit to provide bpf_line_info [ Upstream commit 3cb70413041fdf028fa1ba3986fd0c6aec9e3dcb ] Add support for riscv jit to provide bpf_line_info. We need to consider the prologue offset in ctx->offset, but unlike x86 and arm64, ctx->offset of riscv does not provide an extra slot for the prologue, so here we just calculate the len of prologue and add it to ctx->offset at the end. Both RV64 and RV32 have been tested. Signed-off-by: Pu Lehui Signed-off-by: Daniel Borkmann Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220530092815.1112406-3-pulehui@huawei.com Stable-dep-of: c56fb2aab235 ("riscv, bpf: Fix inconsistent JIT image generation") Signed-off-by: Sasha Levin --- arch/riscv/net/bpf_jit.h | 1 + arch/riscv/net/bpf_jit_core.c | 8 +++++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index 75c1e9996867..ab0cd6d10ccf 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -69,6 +69,7 @@ struct rv_jit_context { struct bpf_prog *prog; u16 *insns; /* RV insns */ int ninsns; + int body_len; int epilogue_offset; int *offset; /* BPF to RV */ unsigned long flags; diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index 5d247198c30d..750b15c319d5 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -43,7 +43,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { bool tmp_blinded = false, extra_pass = false; struct bpf_prog *tmp, *orig_prog = prog; - int pass = 0, prev_ninsns = 0, i; + int pass = 0, prev_ninsns = 0, prologue_len, i; struct rv_jit_data *jit_data; struct rv_jit_context *ctx; unsigned int image_size = 0; @@ -95,6 +95,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = orig_prog; goto out_offset; } + ctx->body_len = ctx->ninsns; bpf_jit_build_prologue(ctx); ctx->epilogue_offset = ctx->ninsns; bpf_jit_build_epilogue(ctx); @@ -154,6 +155,11 @@ skip_init_ctx: if (!prog->is_func || extra_pass) { bpf_jit_binary_lock_ro(jit_data->header); + prologue_len = ctx->epilogue_offset - ctx->body_len; + for (i = 0; i < prog->len; i++) + ctx->offset[i] = ninsns_rvoff(prologue_len + + ctx->offset[i]); + bpf_prog_fill_jited_linfo(prog, ctx->offset); out_offset: kfree(ctx->offset); kfree(jit_data); From bbc500ff3f2c2c3c3fd1ff2953e1965874cc9418 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Mon, 10 Jul 2023 09:41:31 +0200 Subject: [PATCH 4100/4345] riscv, bpf: Fix inconsistent JIT image generation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c56fb2aab23505bb7160d06097c8de100b82b851 ] In order to generate the prologue and epilogue, the BPF JIT needs to know which registers that are clobbered. Therefore, the during pre-final passes, the prologue is generated after the body of the program body-prologue-epilogue. Then, in the final pass, a proper prologue-body-epilogue JITted image is generated. This scheme has worked most of the time. However, for some large programs with many jumps, e.g. the test_kmod.sh BPF selftest with hardening enabled (blinding constants), this has shown to be incorrect. For the final pass, when the proper prologue-body-epilogue is generated, the image has not converged. This will lead to that the final image will have incorrect jump offsets. The following is an excerpt from an incorrect image: | ... | 3b8: 00c50663 beq a0,a2,3c4 <.text+0x3c4> | 3bc: 0020e317 auipc t1,0x20e | 3c0: 49630067 jalr zero,1174(t1) # 20e852 <.text+0x20e852> | ... | 20e84c: 8796 c.mv a5,t0 | 20e84e: 6422 c.ldsp s0,8(sp) # Epilogue start | 20e850: 6141 c.addi16sp sp,16 | 20e852: 853e c.mv a0,a5 # Incorrect jump target | 20e854: 8082 c.jr ra The image has shrunk, and the epilogue offset is incorrect in the final pass. Correct the problem by always generating proper prologue-body-epilogue outputs, which means that the first pass will only generate the body to track what registers that are touched. Fixes: 2353ecc6f91f ("bpf, riscv: add BPF JIT for RV64G") Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20230710074131.19596-1-bjorn@kernel.org Signed-off-by: Sasha Levin --- arch/riscv/net/bpf_jit.h | 6 +++--- arch/riscv/net/bpf_jit_core.c | 19 +++++++++++++------ 2 files changed, 16 insertions(+), 9 deletions(-) diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index ab0cd6d10ccf..ef336fe16004 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -69,7 +69,7 @@ struct rv_jit_context { struct bpf_prog *prog; u16 *insns; /* RV insns */ int ninsns; - int body_len; + int prologue_len; int epilogue_offset; int *offset; /* BPF to RV */ unsigned long flags; @@ -215,8 +215,8 @@ static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx) int from, to; off++; /* BPF branch is from PC+1, RV is from PC */ - from = (insn > 0) ? ctx->offset[insn - 1] : 0; - to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0; + from = (insn > 0) ? ctx->offset[insn - 1] : ctx->prologue_len; + to = (insn + off > 0) ? ctx->offset[insn + off - 1] : ctx->prologue_len; return ninsns_rvoff(to - from); } diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index 750b15c319d5..ef17bc8055d4 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -43,7 +43,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { bool tmp_blinded = false, extra_pass = false; struct bpf_prog *tmp, *orig_prog = prog; - int pass = 0, prev_ninsns = 0, prologue_len, i; + int pass = 0, prev_ninsns = 0, i; struct rv_jit_data *jit_data; struct rv_jit_context *ctx; unsigned int image_size = 0; @@ -83,6 +83,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = orig_prog; goto out_offset; } + + if (build_body(ctx, extra_pass, NULL)) { + prog = orig_prog; + goto out_offset; + } + for (i = 0; i < prog->len; i++) { prev_ninsns += 32; ctx->offset[i] = prev_ninsns; @@ -91,12 +97,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) for (i = 0; i < NR_JIT_ITERATIONS; i++) { pass++; ctx->ninsns = 0; + + bpf_jit_build_prologue(ctx); + ctx->prologue_len = ctx->ninsns; + if (build_body(ctx, extra_pass, ctx->offset)) { prog = orig_prog; goto out_offset; } - ctx->body_len = ctx->ninsns; - bpf_jit_build_prologue(ctx); + ctx->epilogue_offset = ctx->ninsns; bpf_jit_build_epilogue(ctx); @@ -155,10 +164,8 @@ skip_init_ctx: if (!prog->is_func || extra_pass) { bpf_jit_binary_lock_ro(jit_data->header); - prologue_len = ctx->epilogue_offset - ctx->body_len; for (i = 0; i < prog->len; i++) - ctx->offset[i] = ninsns_rvoff(prologue_len + - ctx->offset[i]); + ctx->offset[i] = ninsns_rvoff(ctx->offset[i]); bpf_prog_fill_jited_linfo(prog, ctx->offset); out_offset: kfree(ctx->offset); From 4511499138aecce6b6f93191e8a6605650ebc6ba Mon Sep 17 00:00:00 2001 From: Chunhai Guo Date: Mon, 10 Jul 2023 17:34:10 +0800 Subject: [PATCH 4101/4345] erofs: avoid infinite loop in z_erofs_do_read_page() when reading beyond EOF [ Upstream commit 8191213a5835b0317c5e4d0d337ae1ae00c75253 ] z_erofs_do_read_page() may loop infinitely due to the inappropriate truncation in the below statement. Since the offset is 64 bits and min_t() truncates the result to 32 bits. The solution is to replace unsigned int with a 64-bit type, such as erofs_off_t. cur = end - min_t(unsigned int, offset + end - map->m_la, end); - For example: - offset = 0x400160000 - end = 0x370 - map->m_la = 0x160370 - offset + end - map->m_la = 0x400000000 - offset + end - map->m_la = 0x00000000 (truncated as unsigned int) - Expected result: - cur = 0 - Actual result: - cur = 0x370 Signed-off-by: Chunhai Guo Fixes: 3883a79abd02 ("staging: erofs: introduce VLE decompression support") Reviewed-by: Gao Xiang Reviewed-by: Chao Yu Link: https://lore.kernel.org/r/20230710093410.44071-1-guochunhai@vivo.com Signed-off-by: Gao Xiang Signed-off-by: Sasha Levin --- fs/erofs/zdata.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 8cb2cf612e49..9cff92738259 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -629,7 +629,7 @@ hitted: tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED && clt->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE); - cur = end - min_t(unsigned int, offset + end - map->m_la, end); + cur = end - min_t(erofs_off_t, offset + end - map->m_la, end); if (!(map->m_flags & EROFS_MAP_MAPPED)) { zero_user_segment(page, cur, end); goto next_part; From 934c85b8ecd15c2c1eb9b4769fb790e35737545a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 9 Jul 2023 06:31:54 -0700 Subject: [PATCH 4102/4345] wifi: airo: avoid uninitialized warning in airo_get_rate() [ Upstream commit 9373771aaed17f5c2c38485f785568abe3a9f8c1 ] Quieten a gcc (11.3.0) build error or warning by checking the function call status and returning -EBUSY if the function call failed. This is similar to what several other wireless drivers do for the SIOCGIWRATE ioctl call when there is a locking problem. drivers/net/wireless/cisco/airo.c: error: 'status_rid.currentXmitRate' is used uninitialized [-Werror=uninitialized] Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Randy Dunlap Reported-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/39abf2c7-24a-f167-91da-ed4c5435d1c4@linux-m68k.org Link: https://lore.kernel.org/r/20230709133154.26206-1-rdunlap@infradead.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/wireless/cisco/airo.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index 8c9c6bfbaeee..aa1d12f6f5c3 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -6150,8 +6150,11 @@ static int airo_get_rate(struct net_device *dev, { struct airo_info *local = dev->ml_priv; StatusRid status_rid; /* Card status info */ + int ret; - readStatusRid(local, &status_rid, 1); + ret = readStatusRid(local, &status_rid, 1); + if (ret) + return -EBUSY; vwrq->value = le16_to_cpu(status_rid.currentXmitRate) * 500000; /* If more than one rate, set auto */ From 9b69cdb6e534b5d3c461ceb4c895bc805883ecb7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 11 Jul 2023 10:08:09 +0300 Subject: [PATCH 4103/4345] net/sched: flower: Ensure both minimum and maximum ports are specified [ Upstream commit d3f87278bcb80bd7f9519669d928b43320363d4f ] The kernel does not currently validate that both the minimum and maximum ports of a port range are specified. This can lead user space to think that a filter matching on a port range was successfully added, when in fact it was not. For example, with a patched (buggy) iproute2 that only sends the minimum port, the following commands do not return an error: # tc filter add dev swp1 ingress pref 1 proto ip flower ip_proto udp src_port 100-200 action pass # tc filter add dev swp1 ingress pref 1 proto ip flower ip_proto udp dst_port 100-200 action pass # tc filter show dev swp1 ingress filter protocol ip pref 1 flower chain 0 filter protocol ip pref 1 flower chain 0 handle 0x1 eth_type ipv4 ip_proto udp not_in_hw action order 1: gact action pass random type none pass val 0 index 1 ref 1 bind 1 filter protocol ip pref 1 flower chain 0 handle 0x2 eth_type ipv4 ip_proto udp not_in_hw action order 1: gact action pass random type none pass val 0 index 2 ref 1 bind 1 Fix by returning an error unless both ports are specified: # tc filter add dev swp1 ingress pref 1 proto ip flower ip_proto udp src_port 100-200 action pass Error: Both min and max source ports must be specified. We have an error talking to the kernel # tc filter add dev swp1 ingress pref 1 proto ip flower ip_proto udp dst_port 100-200 action pass Error: Both min and max destination ports must be specified. We have an error talking to the kernel Fixes: 5c72299fba9d ("net: sched: cls_flower: Classify packets using port ranges") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/sched/cls_flower.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index caf1a05bfbde..dcf21d99f132 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -778,6 +778,16 @@ static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); + if (mask->tp_range.tp_min.dst != mask->tp_range.tp_max.dst) { + NL_SET_ERR_MSG(extack, + "Both min and max destination ports must be specified"); + return -EINVAL; + } + if (mask->tp_range.tp_min.src != mask->tp_range.tp_max.src) { + NL_SET_ERR_MSG(extack, + "Both min and max source ports must be specified"); + return -EINVAL; + } if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && ntohs(key->tp_range.tp_max.dst) <= ntohs(key->tp_range.tp_min.dst)) { From d5ca61b7642b74d068a0beef585b6d812541d482 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 11 Jul 2023 11:52:26 +0300 Subject: [PATCH 4104/4345] netdevsim: fix uninitialized data in nsim_dev_trap_fa_cookie_write() [ Upstream commit f72207a5c0dbaaf6921cf9a6c0d2fd0bc249ea78 ] The simple_write_to_buffer() function is designed to handle partial writes. It returns negatives on error, otherwise it returns the number of bytes that were able to be copied. This code doesn't check the return properly. We only know that the first byte is written, the rest of the buffer might be uninitialized. There is no need to use the simple_write_to_buffer() function. Partial writes are prohibited by the "if (*ppos != 0)" check at the start of the function. Just use memdup_user() and copy the whole buffer. Fixes: d3cbb907ae57 ("netdevsim: add ACL trap reporting cookie as a metadata") Signed-off-by: Dan Carpenter Reviewed-by: Pavan Chebbi Reviewed-by: Ido Schimmel Link: https://lore.kernel.org/r/7c1f950b-3a7d-4252-82a6-876e53078ef7@moroto.mountain Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/netdevsim/dev.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 9bbecf4d159b..bcf354719745 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -149,13 +149,10 @@ static ssize_t nsim_dev_trap_fa_cookie_write(struct file *file, cookie_len = (count - 1) / 2; if ((count - 1) % 2) return -EINVAL; - buf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN); - if (!buf) - return -ENOMEM; - ret = simple_write_to_buffer(buf, count, ppos, data, count); - if (ret < 0) - goto free_buf; + buf = memdup_user(data, count); + if (IS_ERR(buf)) + return PTR_ERR(buf); fa_cookie = kmalloc(sizeof(*fa_cookie) + cookie_len, GFP_KERNEL | __GFP_NOWARN); From 1d7ae38daac74122aee4fead96fd745718bcacb6 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Mon, 10 Jul 2023 23:16:34 -0300 Subject: [PATCH 4105/4345] net/sched: make psched_mtu() RTNL-less safe [ Upstream commit 150e33e62c1fa4af5aaab02776b6c3812711d478 ] Eric Dumazet says[1]: ------- Speaking of psched_mtu(), I see that net/sched/sch_pie.c is using it without holding RTNL, so dev->mtu can be changed underneath. KCSAN could issue a warning. ------- Annotate dev->mtu with READ_ONCE() so KCSAN don't issue a warning. [1] https://lore.kernel.org/all/CANn89iJoJO5VtaJ-2=_d2aOQhb0Xw8iBT_Cxqp2HyuS-zj6azw@mail.gmail.com/ v1 -> v2: Fix commit message Fixes: d4b36210c2e6 ("net: pkt_sched: PIE AQM scheme") Suggested-by: Eric Dumazet Signed-off-by: Pedro Tammela Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230711021634.561598-1-pctammela@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/pkt_sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index ba781e0aaf56..e186b2bd8c86 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -136,7 +136,7 @@ extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; */ static inline unsigned int psched_mtu(const struct net_device *dev) { - return dev->mtu + dev->hard_header_len; + return READ_ONCE(dev->mtu) + dev->hard_header_len; } static inline struct net *qdisc_net(struct Qdisc *q) From 5bef780e06d2948b9665e22e0fcdb2fba8dd4653 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Sat, 22 Apr 2023 12:56:11 -0300 Subject: [PATCH 4106/4345] net/sched: sch_qfq: refactor parsing of netlink parameters [ Upstream commit 25369891fcef373540f8b4e0b3bccf77a04490d5 ] Two parameters can be transformed into netlink policies and validated while parsing the netlink message. Reviewed-by: Simon Horman Acked-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Signed-off-by: David S. Miller Stable-dep-of: 3e337087c3b5 ("net/sched: sch_qfq: account for stab overhead in qfq_enqueue") Signed-off-by: Sasha Levin --- net/sched/sch_qfq.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index cad7deacf60a..975e444f2d82 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -113,6 +113,7 @@ #define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ +#define QFQ_MAX_LMAX (1UL << QFQ_MTU_SHIFT) #define QFQ_MAX_AGG_CLASSES 8 /* max num classes per aggregate allowed */ @@ -214,9 +215,14 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) return container_of(clc, struct qfq_class, common); } +static struct netlink_range_validation lmax_range = { + .min = QFQ_MIN_LMAX, + .max = QFQ_MAX_LMAX, +}; + static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { - [TCA_QFQ_WEIGHT] = { .type = NLA_U32 }, - [TCA_QFQ_LMAX] = { .type = NLA_U32 }, + [TCA_QFQ_WEIGHT] = NLA_POLICY_RANGE(NLA_U32, 1, QFQ_MAX_WEIGHT), + [TCA_QFQ_LMAX] = NLA_POLICY_FULL_RANGE(NLA_U32, &lmax_range), }; /* @@ -408,17 +414,13 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } err = nla_parse_nested_deprecated(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], - qfq_policy, NULL); + qfq_policy, extack); if (err < 0) return err; - if (tb[TCA_QFQ_WEIGHT]) { + if (tb[TCA_QFQ_WEIGHT]) weight = nla_get_u32(tb[TCA_QFQ_WEIGHT]); - if (!weight || weight > (1UL << QFQ_MAX_WSHIFT)) { - pr_notice("qfq: invalid weight %u\n", weight); - return -EINVAL; - } - } else + else weight = 1; if (tb[TCA_QFQ_LMAX]) @@ -426,11 +428,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, else lmax = psched_mtu(qdisc_dev(sch)); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); - return -EINVAL; - } - inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; From 8359ee85fd6dabc5c134ed69fb22faadd8a44071 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Tue, 11 Jul 2023 18:01:02 -0300 Subject: [PATCH 4107/4345] net/sched: sch_qfq: account for stab overhead in qfq_enqueue [ Upstream commit 3e337087c3b5805fe0b8a46ba622a962880b5d64 ] Lion says: ------- In the QFQ scheduler a similar issue to CVE-2023-31436 persists. Consider the following code in net/sched/sch_qfq.c: static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb), gso_segs; // ... if (unlikely(cl->agg->lmax < len)) { pr_debug("qfq: increasing maxpkt from %u to %u for class %u", cl->agg->lmax, len, cl->common.classid); err = qfq_change_agg(sch, cl, cl->agg->class_weight, len); if (err) { cl->qstats.drops++; return qdisc_drop(skb, sch, to_free); } // ... } Similarly to CVE-2023-31436, "lmax" is increased without any bounds checks according to the packet length "len". Usually this would not impose a problem because packet sizes are naturally limited. This is however not the actual packet length, rather the "qdisc_pkt_len(skb)" which might apply size transformations according to "struct qdisc_size_table" as created by "qdisc_get_stab()" in net/sched/sch_api.c if the TCA_STAB option was set when modifying the qdisc. A user may choose virtually any size using such a table. As a result the same issue as in CVE-2023-31436 can occur, allowing heap out-of-bounds read / writes in the kmalloc-8192 cache. ------- We can create the issue with the following commands: tc qdisc add dev $DEV root handle 1: stab mtu 2048 tsize 512 mpu 0 \ overhead 999999999 linklayer ethernet qfq tc class add dev $DEV parent 1: classid 1:1 htb rate 6mbit burst 15k tc filter add dev $DEV parent 1: matchall classid 1:1 ping -I $DEV 1.1.1.2 This is caused by incorrectly assuming that qdisc_pkt_len() returns a length within the QFQ_MIN_LMAX < len < QFQ_MAX_LMAX. Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost") Reported-by: Lion Reviewed-by: Eric Dumazet Signed-off-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/sched/sch_qfq.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 975e444f2d82..616d1798cfef 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -381,8 +381,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, u32 lmax) { struct qfq_sched *q = qdisc_priv(sch); - struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight); + struct qfq_aggregate *new_agg; + /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */ + if (lmax > QFQ_MAX_LMAX) + return -EINVAL; + + new_agg = qfq_find_agg(q, lmax, weight); if (new_agg == NULL) { /* create new aggregate */ new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC); if (new_agg == NULL) From f4ff3798123585c9c7dd48ab7ef169fb505e0774 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 13 Jul 2023 17:26:20 +0800 Subject: [PATCH 4108/4345] nvme-pci: fix DMA direction of unmapping integrity data [ Upstream commit b8f6446b6853768cb99e7c201bddce69ca60c15e ] DMA direction should be taken in dma_unmap_page() for unmapping integrity data. Fix this DMA direction, and reported in Guangwu's test. Reported-by: Guangwu Zhang Fixes: 4aedb705437f ("nvme-pci: split metadata handling from nvme_map_data / nvme_unmap_data") Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Sasha Levin --- drivers/nvme/host/pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c47512da9872..3aaead9b3a57 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -968,7 +968,8 @@ static void nvme_pci_complete_rq(struct request *req) if (blk_integrity_rq(req)) dma_unmap_page(dev->dev, iod->meta_dma, - rq_integrity_vec(req)->bv_len, rq_data_dir(req)); + rq_integrity_vec(req)->bv_len, rq_dma_dir(req)); + if (blk_rq_nr_phys_segments(req)) nvme_unmap_data(dev, req); nvme_complete_rq(req); From b39ef5b52f10b819bd0ceeb22e8f7df7800880ca Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 23 May 2023 14:17:25 +0800 Subject: [PATCH 4109/4345] f2fs: fix to avoid NULL pointer dereference f2fs_write_end_io() commit d8189834d4348ae608083e1f1f53792cfcc2a9bc upstream. butt3rflyh4ck reports a bug as below: When a thread always calls F2FS_IOC_RESIZE_FS to resize fs, if resize fs is failed, f2fs kernel thread would invoke callback function to update f2fs io info, it would call f2fs_write_end_io and may trigger null-ptr-deref in NODE_MAPPING. general protection fault, probably for non-canonical address KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037] RIP: 0010:NODE_MAPPING fs/f2fs/f2fs.h:1972 [inline] RIP: 0010:f2fs_write_end_io+0x727/0x1050 fs/f2fs/data.c:370 bio_endio+0x5af/0x6c0 block/bio.c:1608 req_bio_endio block/blk-mq.c:761 [inline] blk_update_request+0x5cc/0x1690 block/blk-mq.c:906 blk_mq_end_request+0x59/0x4c0 block/blk-mq.c:1023 lo_complete_rq+0x1c6/0x280 drivers/block/loop.c:370 blk_complete_reqs+0xad/0xe0 block/blk-mq.c:1101 __do_softirq+0x1d4/0x8ef kernel/softirq.c:571 run_ksoftirqd kernel/softirq.c:939 [inline] run_ksoftirqd+0x31/0x60 kernel/softirq.c:931 smpboot_thread_fn+0x659/0x9e0 kernel/smpboot.c:164 kthread+0x33e/0x440 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 The root cause is below race case can cause leaving dirty metadata in f2fs after filesystem is remount as ro: Thread A Thread B - f2fs_ioc_resize_fs - f2fs_readonly --- return false - f2fs_resize_fs - f2fs_remount - write_checkpoint - set f2fs as ro - free_segment_range - update meta_inode's data Then, if f2fs_put_super() fails to write_checkpoint due to readonly status, and meta_inode's dirty data will be writebacked after node_inode is put, finally, f2fs_write_end_io will access NULL pointer on sbi->node_inode. Thread A IRQ context - f2fs_put_super - write_checkpoint fails - iput(node_inode) - node_inode = NULL - iput(meta_inode) - write_inode_now - f2fs_write_meta_page - f2fs_write_end_io - NODE_MAPPING(sbi) : access NULL pointer on node_inode Fixes: b4b10061ef98 ("f2fs: refactor resize_fs to avoid meta updates in progress") Reported-by: butt3rflyh4ck Closes: https://lore.kernel.org/r/1684480657-2375-1-git-send-email-yangtiezhu@loongson.cn Tested-by: butt3rflyh4ck Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Stefan Ghinea Signed-off-by: Greg Kroah-Hartman --- fs/f2fs/f2fs.h | 2 +- fs/f2fs/file.c | 2 +- fs/f2fs/gc.c | 22 +++++++++++++++++++--- 3 files changed, 21 insertions(+), 5 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 62b7848f1f71..83ebc860508b 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3483,7 +3483,7 @@ block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background, bool force, unsigned int segno); void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); -int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count); +int f2fs_resize_fs(struct file *filp, __u64 block_count); int __init f2fs_create_garbage_collection_cache(void); void f2fs_destroy_garbage_collection_cache(void); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index a0d8aa52b696..6e91be5b8c30 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3356,7 +3356,7 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg) sizeof(block_count))) return -EFAULT; - return f2fs_resize_fs(sbi, block_count); + return f2fs_resize_fs(filp, block_count); } static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 66ac048cc899..8e4daee0171f 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -7,6 +7,7 @@ */ #include #include +#include #include #include #include @@ -1976,8 +1977,9 @@ static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs) } } -int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) +int f2fs_resize_fs(struct file *filp, __u64 block_count) { + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); __u64 old_block_count, shrunk_blocks; struct cp_control cpc = { CP_RESIZE, 0, 0, 0 }; unsigned int secs; @@ -2015,12 +2017,18 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) return -EINVAL; } + err = mnt_want_write_file(filp); + if (err) + return err; + shrunk_blocks = old_block_count - block_count; secs = div_u64(shrunk_blocks, BLKS_PER_SEC(sbi)); /* stop other GC */ - if (!down_write_trylock(&sbi->gc_lock)) - return -EAGAIN; + if (!down_write_trylock(&sbi->gc_lock)) { + err = -EAGAIN; + goto out_drop_write; + } /* stop CP to protect MAIN_SEC in free_segment_range */ f2fs_lock_op(sbi); @@ -2040,10 +2048,18 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) out_unlock: f2fs_unlock_op(sbi); up_write(&sbi->gc_lock); +out_drop_write: + mnt_drop_write_file(filp); if (err) return err; freeze_super(sbi->sb); + + if (f2fs_readonly(sbi->sb)) { + thaw_super(sbi->sb); + return -EROFS; + } + down_write(&sbi->gc_lock); mutex_lock(&sbi->cp_mutex); From 3674b9c056adb653f260c5665591b16b3ef71683 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 21 Apr 2023 07:06:22 -0500 Subject: [PATCH 4110/4345] pinctrl: amd: Fix mistake in handling clearing pins at startup commit a855724dc08b8cb0c13ab1e065a4922f1e5a7552 upstream. commit 4e5a04be88fe ("pinctrl: amd: disable and mask interrupts on probe") had a mistake in loop iteration 63 that it would clear offset 0xFC instead of 0x100. Offset 0xFC is actually `WAKE_INT_MASTER_REG`. This was clearing bits 13 and 15 from the register which significantly changed the expected handling for some platforms for GPIO0. Cc: stable@vger.kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=217315 Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230421120625.3366-3-mario.limonciello@amd.com Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-amd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 82b658a3c220..6ddbffdb2b6c 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -784,9 +784,9 @@ static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) raw_spin_lock_irqsave(&gpio_dev->lock, flags); - pin_reg = readl(gpio_dev->base + i * 4); + pin_reg = readl(gpio_dev->base + pin * 4); pin_reg &= ~mask; - writel(pin_reg, gpio_dev->base + i * 4); + writel(pin_reg, gpio_dev->base + pin * 4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); } From 4f77a87ce9198b2fc738e7d6c7cd8c43372d0e32 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 21 Apr 2023 07:06:21 -0500 Subject: [PATCH 4111/4345] pinctrl: amd: Detect internal GPIO0 debounce handling commit 968ab9261627fa305307e3935ca1a32fcddd36cb upstream. commit 4e5a04be88fe ("pinctrl: amd: disable and mask interrupts on probe") had a mistake in loop iteration 63 that it would clear offset 0xFC instead of 0x100. Offset 0xFC is actually `WAKE_INT_MASTER_REG`. This was clearing bits 13 and 15 from the register which significantly changed the expected handling for some platforms for GPIO0. commit b26cd9325be4 ("pinctrl: amd: Disable and mask interrupts on resume") actually fixed this bug, but lead to regressions on Lenovo Z13 and some other systems. This is because there was no handling in the driver for bit 15 debounce behavior. Quoting a public BKDG: ``` EnWinBlueBtn. Read-write. Reset: 0. 0=GPIO0 detect debounced power button; Power button override is 4 seconds. 1=GPIO0 detect debounced power button in S3/S5/S0i3, and detect "pressed less than 2 seconds" and "pressed 2~10 seconds" in S0; Power button override is 10 seconds ``` Cross referencing the same master register in Windows it's obvious that Windows doesn't use debounce values in this configuration. So align the Linux driver to do this as well. This fixes wake on lid when WAKE_INT_MASTER_REG is properly programmed. Cc: stable@vger.kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=217315 Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230421120625.3366-2-mario.limonciello@amd.com Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-amd.c | 7 +++++++ drivers/pinctrl/pinctrl-amd.h | 1 + 2 files changed, 8 insertions(+) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 6ddbffdb2b6c..c983d3306607 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -126,6 +126,12 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, struct amd_gpio *gpio_dev = gpiochip_get_data(gc); raw_spin_lock_irqsave(&gpio_dev->lock, flags); + + /* Use special handling for Pin0 debounce */ + pin_reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG); + if (pin_reg & INTERNAL_GPIO0_DEBOUNCE) + debounce = 0; + pin_reg = readl(gpio_dev->base + offset * 4); if (debounce) { @@ -215,6 +221,7 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) char *output_value; char *output_enable; + seq_printf(s, "WAKE_INT_MASTER_REG: 0x%08x\n", readl(gpio_dev->base + WAKE_INT_MASTER_REG)); for (bank = 0; bank < gpio_dev->hwbank_num; bank++) { seq_printf(s, "GPIO bank%d\t", bank); diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h index 95e763424042..9f95ec9e2201 100644 --- a/drivers/pinctrl/pinctrl-amd.h +++ b/drivers/pinctrl/pinctrl-amd.h @@ -17,6 +17,7 @@ #define AMD_GPIO_PINS_BANK3 32 #define WAKE_INT_MASTER_REG 0xfc +#define INTERNAL_GPIO0_DEBOUNCE (1 << 15) #define EOI_MASK (1 << 29) #define WAKE_INT_STATUS_REG0 0x2f8 From 59490249c2c09f7d5b9440a1428ae9c66a1e142f Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 5 Jul 2023 08:30:02 -0500 Subject: [PATCH 4112/4345] pinctrl: amd: Only use special debounce behavior for GPIO 0 commit 0d5ace1a07f7e846d0f6d972af60d05515599d0b upstream. It's uncommon to use debounce on any other pin, but technically we should only set debounce to 0 when working off GPIO0. Cc: stable@vger.kernel.org Tested-by: Jan Visser Fixes: 968ab9261627 ("pinctrl: amd: Detect internal GPIO0 debounce handling") Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230705133005.577-2-mario.limonciello@amd.com Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/pinctrl-amd.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index c983d3306607..0d71151575ee 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -128,9 +128,11 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, raw_spin_lock_irqsave(&gpio_dev->lock, flags); /* Use special handling for Pin0 debounce */ - pin_reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG); - if (pin_reg & INTERNAL_GPIO0_DEBOUNCE) - debounce = 0; + if (offset == 0) { + pin_reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG); + if (pin_reg & INTERNAL_GPIO0_DEBOUNCE) + debounce = 0; + } pin_reg = readl(gpio_dev->base + offset * 4); From 9ff7fcb3a2ed0e9b895bb5b4c13872d584a8815b Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Tue, 16 May 2023 01:25:54 +0300 Subject: [PATCH 4113/4345] tpm: tpm_vtpm_proxy: fix a race condition in /dev/vtpmx creation commit f4032d615f90970d6c3ac1d9c0bce3351eb4445c upstream. /dev/vtpmx is made visible before 'workqueue' is initialized, which can lead to a memory corruption in the worst case scenario. Address this by initializing 'workqueue' as the very first step of the driver initialization. Cc: stable@vger.kernel.org Fixes: 6f99612e2500 ("tpm: Proxy driver for supporting multiple emulated TPMs") Reviewed-by: Stefan Berger Signed-off-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm_vtpm_proxy.c | 30 +++++++----------------------- 1 file changed, 7 insertions(+), 23 deletions(-) diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c index 91c772e38bb5..ff2ec71d592e 100644 --- a/drivers/char/tpm/tpm_vtpm_proxy.c +++ b/drivers/char/tpm/tpm_vtpm_proxy.c @@ -683,37 +683,21 @@ static struct miscdevice vtpmx_miscdev = { .fops = &vtpmx_fops, }; -static int vtpmx_init(void) -{ - return misc_register(&vtpmx_miscdev); -} - -static void vtpmx_cleanup(void) -{ - misc_deregister(&vtpmx_miscdev); -} - static int __init vtpm_module_init(void) { int rc; - rc = vtpmx_init(); - if (rc) { - pr_err("couldn't create vtpmx device\n"); - return rc; - } - workqueue = create_workqueue("tpm-vtpm"); if (!workqueue) { pr_err("couldn't create workqueue\n"); - rc = -ENOMEM; - goto err_vtpmx_cleanup; + return -ENOMEM; } - return 0; - -err_vtpmx_cleanup: - vtpmx_cleanup(); + rc = misc_register(&vtpmx_miscdev); + if (rc) { + pr_err("couldn't create vtpmx device\n"); + destroy_workqueue(workqueue); + } return rc; } @@ -721,7 +705,7 @@ err_vtpmx_cleanup: static void __exit vtpm_module_exit(void) { destroy_workqueue(workqueue); - vtpmx_cleanup(); + misc_deregister(&vtpmx_miscdev); } module_init(vtpm_module_init); From 21d5d3eb36bf843d208742a3d942e8b86c202400 Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Thu, 15 Jun 2023 11:08:15 +0300 Subject: [PATCH 4114/4345] mtd: rawnand: meson: fix unaligned DMA buffers handling commit 98480a181a08ceeede417e5b28f6d0429d8ae156 upstream. Meson NAND controller requires 8 bytes alignment for DMA addresses, otherwise it "aligns" passed address by itself thus accessing invalid location in the provided buffer. This patch makes unaligned buffers to be reallocated to become valid. Fixes: 8fae856c5350 ("mtd: rawnand: meson: add support for Amlogic NAND flash controller") Cc: Signed-off-by: Arseniy Krasnov Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230615080815.3291006-1-AVKrasnov@sberdevices.ru Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/raw/meson_nand.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 228612d82f31..ee3976b7e197 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -72,6 +72,7 @@ #define GENCMDIADDRH(aih, addr) ((aih) | (((addr) >> 16) & 0xffff)) #define DMA_DIR(dir) ((dir) ? NFC_CMD_N2M : NFC_CMD_M2N) +#define DMA_ADDR_ALIGN 8 #define ECC_CHECK_RETURN_FF (-1) @@ -838,6 +839,9 @@ static int meson_nfc_read_oob(struct nand_chip *nand, int page) static bool meson_nfc_is_buffer_dma_safe(const void *buffer) { + if ((uintptr_t)buffer % DMA_ADDR_ALIGN) + return false; + if (virt_addr_valid(buffer) && (!object_is_on_stack(buffer))) return true; return false; From fe1ae1fb507a2e14578fe0fb24209cef8a02b436 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 22 Jun 2023 03:31:07 -0700 Subject: [PATCH 4115/4345] net: bcmgenet: Ensure MDIO unregistration has clocks enabled commit 1b5ea7ffb7a3bdfffb4b7f40ce0d20a3372ee405 upstream. With support for Ethernet PHY LEDs having been added, while unregistering a MDIO bus and its child device liks PHYs there may be "late" accesses to the MDIO bus. One typical use case is setting the PHY LEDs brightness to OFF for instance. We need to ensure that the MDIO bus controller remains entirely functional since it runs off the main GENET adapter clock. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20230617155500.4005881-1-andrew@lunn.ch/ Fixes: 9a4e79697009 ("net: bcmgenet: utilize generic Broadcom UniMAC MDIO controller driver") Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230622103107.1760280-1-florian.fainelli@broadcom.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/broadcom/genet/bcmmii.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 4b875838a646..99aba64f03c2 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -624,5 +624,7 @@ void bcmgenet_mii_exit(struct net_device *dev) if (of_phy_is_fixed_link(dn)) of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); + clk_prepare_enable(priv->clk); platform_device_unregister(priv->mii_pdev); + clk_disable_unprepare(priv->clk); } From 3d1d037f274940201b95d67dfc223b184cc009ce Mon Sep 17 00:00:00 2001 From: Naveen N Rao Date: Tue, 30 May 2023 11:44:36 +0530 Subject: [PATCH 4116/4345] powerpc: Fail build if using recordmcount with binutils v2.37 commit 25ea739ea1d4d3de41acc4f4eb2d1a97eee0eb75 upstream. binutils v2.37 drops unused section symbols, which prevents recordmcount from capturing mcount locations in sections that have no non-weak symbols. This results in a build failure with a message such as: Cannot find symbol for section 12: .text.perf_callchain_kernel. kernel/events/callchain.o: failed The change to binutils was reverted for v2.38, so this behavior is specific to binutils v2.37: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=c09c8b42021180eee9495bd50d8b35e683d3901b Objtool is able to cope with such sections, so this issue is specific to recordmcount. Fail the build and print a warning if binutils v2.37 is detected and if we are using recordmcount. Cc: stable@vger.kernel.org Suggested-by: Joel Stanley Signed-off-by: Naveen N Rao Signed-off-by: Michael Ellerman Link: https://msgid.link/20230530061436.56925-1-naveen@kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/Makefile | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index a3f66ade09b3..912e64ab5f24 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -429,3 +429,11 @@ checkbin: echo -n '*** Please use a different binutils version.' ; \ false ; \ fi + @if test "x${CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT}" = "xy" -a \ + "x${CONFIG_LD_IS_BFD}" = "xy" -a \ + "${CONFIG_LD_VERSION}" = "23700" ; then \ + echo -n '*** binutils 2.37 drops unused section symbols, which recordmcount ' ; \ + echo 'is unable to handle.' ; \ + echo '*** Please use a different binutils version.' ; \ + false ; \ + fi From 3bd4d316b1a8d68b28216c807801b7b72a270ab9 Mon Sep 17 00:00:00 2001 From: Ekansh Gupta Date: Wed, 14 Jun 2023 17:24:45 +0530 Subject: [PATCH 4117/4345] misc: fastrpc: Create fastrpc scalar with correct buffer count commit 0b4e32df3e09406b835d8230b9331273f2805058 upstream. A process can spawn a PD on DSP with some attributes that can be associated with the PD during spawn and run. The invocation corresponding to the create request with attributes has total 4 buffers at the DSP side implementation. If this number is not correct, the invocation is expected to fail on DSP. Added change to use correct number of buffer count for creating fastrpc scalar. Fixes: d73f71c7c6ee ("misc: fastrpc: Add support for create remote init process") Cc: stable Tested-by: Ekansh Gupta Signed-off-by: Ekansh Gupta Message-ID: <1686743685-21715-1-git-send-email-quic_ekangupt@quicinc.com> Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 2488a9a67d18..eed047e971e7 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1106,7 +1106,7 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl, sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_CREATE, 4, 0); if (init.attrs) - sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_CREATE_ATTR, 6, 0); + sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_CREATE_ATTR, 4, 0); err = fastrpc_internal_invoke(fl, true, FASTRPC_INIT_HANDLE, sc, args); From 8c723eef989bc419585237daa467b787ddca5415 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Thu, 1 Jun 2023 19:23:41 +0800 Subject: [PATCH 4118/4345] erofs: fix compact 4B support for 16k block size commit 001b8ccd0650727e54ec16ef72bf1b8eeab7168e upstream. In compact 4B, two adjacent lclusters are packed together as a unit to form on-disk indexes for effective random access, as below: (amortized = 4, vcnt = 2) _____________________________________________ |___@_____ encoded bits __________|_ blkaddr _| 0 . amortized * vcnt = 8 . . . . amortized * vcnt - 4 = 4 . . .____________________________. |_type (2 bits)_|_clusterofs_| Therefore, encoded bits for each pack are 32 bits (4 bytes). IOWs, since each lcluster can get 16 bits for its type and clusterofs, the maximum supported lclustersize for compact 4B format is 16k (14 bits). Fix this to enable compact 4B format for 16k lclusters (blocks), which is tested on an arm64 server with 16k page size. Fixes: 152a333a5895 ("staging: erofs: add compacted compression indexes support") Signed-off-by: Gao Xiang Link: https://lore.kernel.org/r/20230601112341.56960-1-hsiangkao@linux.alibaba.com Signed-off-by: Greg Kroah-Hartman --- fs/erofs/zmap.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index f18194fd8d77..a5537a9f8f36 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -215,7 +215,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, int i; u8 *in, type; - if (1 << amortizedshift == 4) + if (1 << amortizedshift == 4 && lclusterbits <= 14) vcnt = 2; else if (1 << amortizedshift == 2 && lclusterbits == 12) vcnt = 16; @@ -273,7 +273,6 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); - const unsigned int lclusterbits = vi->z_logical_clusterbits; const erofs_off_t ebase = ALIGN(iloc(EROFS_I_SB(inode), vi->nid) + vi->inode_isize + vi->xattr_isize, 8) + sizeof(struct z_erofs_map_header); @@ -283,9 +282,6 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, erofs_off_t pos; int err; - if (lclusterbits != 12) - return -EOPNOTSUPP; - if (lcn >= totalidx) return -EINVAL; From 8fbe951d65464db28005803b1fa1b091342289d3 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Mon, 26 Jun 2023 15:50:14 +0800 Subject: [PATCH 4119/4345] MIPS: Loongson: Fix cpu_probe_loongson() again commit 65fee014dc41a774bcd94896f3fb380bc39d8dda upstream. Commit 7db5e9e9e5e6c10d7d ("MIPS: loongson64: fix FTLB configuration") move decode_configs() from the beginning of cpu_probe_loongson() to the end in order to fix FTLB configuration. However, it breaks the CPUCFG decoding because decode_configs() use "c->options = xxxx" rather than "c->options |= xxxx", all information get from CPUCFG by decode_cpucfg() is lost. This causes error when creating a KVM guest on Loongson-3A4000: Exception Code: 4 not handled @ PC: 0000000087ad5981, inst: 0xcb7a1898 BadVaddr: 0x0 Status: 0x0 Fix this by moving the c->cputype setting to the beginning and moving decode_configs() after that. Fixes: 7db5e9e9e5e6c10d7d ("MIPS: loongson64: fix FTLB configuration") Cc: stable@vger.kernel.org Cc: Huang Pei Signed-off-by: Huacai Chen Signed-off-by: Thomas Bogendoerfer Signed-off-by: Greg Kroah-Hartman --- arch/mips/kernel/cpu-probe.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index d120201910ac..f8d1933bfe82 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1721,7 +1721,10 @@ static inline void decode_cpucfg(struct cpuinfo_mips *c) static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { + c->cputype = CPU_LOONGSON64; + /* All Loongson processors covered here define ExcCode 16 as GSExc. */ + decode_configs(c); c->options |= MIPS_CPU_GSEXCEX; switch (c->processor_id & PRID_IMP_MASK) { @@ -1731,7 +1734,6 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) case PRID_REV_LOONGSON2K_R1_1: case PRID_REV_LOONGSON2K_R1_2: case PRID_REV_LOONGSON2K_R1_3: - c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "Loongson-2K"; set_elf_platform(cpu, "gs264e"); set_isa(c, MIPS_CPU_ISA_M64R2); @@ -1744,14 +1746,12 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) switch (c->processor_id & PRID_REV_MASK) { case PRID_REV_LOONGSON3A_R2_0: case PRID_REV_LOONGSON3A_R2_1: - c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); break; case PRID_REV_LOONGSON3A_R3_0: case PRID_REV_LOONGSON3A_R3_1: - c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); @@ -1771,7 +1771,6 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is incomplete */ break; case PRID_IMP_LOONGSON_64G: - c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); @@ -1781,8 +1780,6 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) panic("Unknown Loongson Processor ID!"); break; } - - decode_configs(c); } #else static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { } From be99faf0c4dbf99c6c7d4097a23c1ebb2b6192f9 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 15 Mar 2023 09:31:23 +0800 Subject: [PATCH 4120/4345] ext4: Fix reusing stale buffer heads from last failed mounting commit 26fb5290240dc31cae99b8b4dd2af7f46dfcba6b upstream. Following process makes ext4 load stale buffer heads from last failed mounting in a new mounting operation: mount_bdev ext4_fill_super | ext4_load_and_init_journal | ext4_load_journal | jbd2_journal_load | load_superblock | journal_get_superblock | set_buffer_verified(bh) // buffer head is verified | jbd2_journal_recover // failed caused by EIO | goto failed_mount3a // skip 'sb->s_root' initialization deactivate_locked_super kill_block_super generic_shutdown_super if (sb->s_root) // false, skip ext4_put_super->invalidate_bdev-> // invalidate_mapping_pages->mapping_evict_folio-> // filemap_release_folio->try_to_free_buffers, which // cannot drop buffer head. blkdev_put blkdev_put_whole if (atomic_dec_and_test(&bdev->bd_openers)) // false, systemd-udev happens to open the device. Then // blkdev_flush_mapping->kill_bdev->truncate_inode_pages-> // truncate_inode_folio->truncate_cleanup_folio-> // folio_invalidate->block_invalidate_folio-> // filemap_release_folio->try_to_free_buffers will be skipped, // dropping buffer head is missed again. Second mount: ext4_fill_super ext4_load_and_init_journal ext4_load_journal ext4_get_journal jbd2_journal_init_inode journal_init_common bh = getblk_unmovable bh = __find_get_block // Found stale bh in last failed mounting journal->j_sb_buffer = bh jbd2_journal_load load_superblock journal_get_superblock if (buffer_verified(bh)) // true, skip journal->j_format_version = 2, value is 0 jbd2_journal_recover do_one_pass next_log_block += count_tags(journal, bh) // According to journal_tag_bytes(), 'tag_bytes' calculating is // affected by jbd2_has_feature_csum3(), jbd2_has_feature_csum3() // returns false because 'j->j_format_version >= 2' is not true, // then we get wrong next_log_block. The do_one_pass may exit // early whenoccuring non JBD2_MAGIC_NUMBER in 'next_log_block'. The filesystem is corrupted here, journal is partially replayed, and new journal sequence number actually is already used by last mounting. The invalidate_bdev() can drop all buffer heads even racing with bare reading block device(eg. systemd-udev), so we can fix it by invalidating bdev in error handling path in __ext4_fill_super(). Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217171 Fixes: 25ed6e8a54df ("jbd2: enable journal clients to enable v2 checksumming") Cc: stable@vger.kernel.org # v3.5 Signed-off-by: Zhihao Cheng Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230315013128.3911115-2-chengzhihao1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/super.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 84b4fc9833e3..e386d67cff9d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1091,6 +1091,12 @@ static void ext4_blkdev_remove(struct ext4_sb_info *sbi) struct block_device *bdev; bdev = sbi->s_journal_bdev; if (bdev) { + /* + * Invalidate the journal device's buffers. We don't want them + * floating about in memory - the physical journal device may + * hotswapped, and it breaks the `ro-after' testing code. + */ + invalidate_bdev(bdev); ext4_blkdev_put(bdev); sbi->s_journal_bdev = NULL; } @@ -1230,13 +1236,7 @@ static void ext4_put_super(struct super_block *sb) sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); if (sbi->s_journal_bdev && sbi->s_journal_bdev != sb->s_bdev) { - /* - * Invalidate the journal device's buffers. We don't want them - * floating about in memory - the physical journal device may - * hotswapped, and it breaks the `ro-after' testing code. - */ sync_blockdev(sbi->s_journal_bdev); - invalidate_bdev(sbi->s_journal_bdev); ext4_blkdev_remove(sbi); } @@ -5206,6 +5206,7 @@ failed_mount: brelse(bh); ext4_blkdev_remove(sbi); out_fail: + invalidate_bdev(sb->s_bdev); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); out_free_base: From d054422eb609da97699d900959bc9a351761f313 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Sat, 3 Jun 2023 23:03:18 +0800 Subject: [PATCH 4121/4345] ext4: fix wrong unit use in ext4_mb_clear_bb commit 247c3d214c23dfeeeb892e91a82ac1188bdaec9f upstream. Function ext4_issue_discard need count in cluster. Pass count_clusters instead of count to fix the mismatch. Signed-off-by: Kemeng Shi Cc: stable@kernel.org Reviewed-by: Ojaswin Mujoo Link: https://lore.kernel.org/r/20230603150327.3596033-11-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/mballoc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 8a51448b7670..d847d836d83e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5549,8 +5549,8 @@ do_more: * them with group lock_held */ if (test_opt(sb, DISCARD)) { - err = ext4_issue_discard(sb, block_group, bit, count, - NULL); + err = ext4_issue_discard(sb, block_group, bit, + count_clusters, NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%u block:%d count:%lu failed" From 514220246aa8aa6394bba5e1ab35c8e40a7b566e Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Sat, 3 Jun 2023 23:03:16 +0800 Subject: [PATCH 4122/4345] ext4: get block from bh in ext4_free_blocks for fast commit replay commit 11b6890be0084ad4df0e06d89a9fdcc948472c65 upstream. ext4_free_blocks will retrieve block from bh if block parameter is zero. Retrieve block before ext4_free_blocks_simple to avoid potentially passing wrong block to ext4_free_blocks_simple. Signed-off-by: Kemeng Shi Cc: stable@kernel.org Reviewed-by: Ojaswin Mujoo Link: https://lore.kernel.org/r/20230603150327.3596033-9-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/mballoc.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index d847d836d83e..f0483306eb8d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5634,12 +5634,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); - if (sbi->s_mount_state & EXT4_FC_REPLAY) { - ext4_free_blocks_simple(inode, block, count); - return; - } - - might_sleep(); if (bh) { if (block) BUG_ON(block != bh->b_blocknr); @@ -5647,6 +5641,13 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, block = bh->b_blocknr; } + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + ext4_free_blocks_simple(inode, block, count); + return; + } + + might_sleep(); + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " From 0a5d12e7107e2ba2c27f57cd33bb2b3380324be5 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Sat, 3 Jun 2023 23:03:19 +0800 Subject: [PATCH 4123/4345] ext4: fix wrong unit use in ext4_mb_new_blocks commit 2ec6d0a5ea72689a79e6f725fd8b443a788ae279 upstream. Function ext4_free_blocks_simple needs count in cluster. Function ext4_free_blocks accepts count in block. Convert count to cluster to fix the mismatch. Signed-off-by: Kemeng Shi Cc: stable@kernel.org Reviewed-by: Ojaswin Mujoo Link: https://lore.kernel.org/r/20230603150327.3596033-12-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/mballoc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f0483306eb8d..3a7192884671 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5642,7 +5642,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, } if (sbi->s_mount_state & EXT4_FC_REPLAY) { - ext4_free_blocks_simple(inode, block, count); + ext4_free_blocks_simple(inode, block, EXT4_NUM_B2C(sbi, count)); return; } From 84293af5455b17bc674510c962e33f6a7bdd2f97 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Mon, 24 Apr 2023 11:38:35 +0800 Subject: [PATCH 4124/4345] ext4: only update i_reserved_data_blocks on successful block allocation commit de25d6e9610a8b30cce9bbb19b50615d02ebca02 upstream. In our fault injection test, we create an ext4 file, migrate it to non-extent based file, then punch a hole and finally trigger a WARN_ON in the ext4_da_update_reserve_space(): EXT4-fs warning (device sda): ext4_da_update_reserve_space:369: ino 14, used 11 with only 10 reserved data blocks When writing back a non-extent based file, if we enable delalloc, the number of reserved blocks will be subtracted from the number of blocks mapped by ext4_ind_map_blocks(), and the extent status tree will be updated. We update the extent status tree by first removing the old extent_status and then inserting the new extent_status. If the block range we remove happens to be in an extent, then we need to allocate another extent_status with ext4_es_alloc_extent(). use old to remove to add new |----------|------------|------------| old extent_status The problem is that the allocation of a new extent_status failed due to a fault injection, and __es_shrink() did not get free memory, resulting in a return of -ENOMEM. Then do_writepages() retries after receiving -ENOMEM, we map to the same extent again, and the number of reserved blocks is again subtracted from the number of blocks in that extent. Since the blocks in the same extent are subtracted twice, we end up triggering WARN_ON at ext4_da_update_reserve_space() because used > ei->i_reserved_data_blocks. For non-extent based file, we update the number of reserved blocks after ext4_ind_map_blocks() is executed, which causes a problem that when we call ext4_ind_map_blocks() to create a block, it doesn't always create a block, but we always reduce the number of reserved blocks. So we move the logic for updating reserved blocks to ext4_ind_map_blocks() to ensure that the number of reserved blocks is updated only after we do succeed in allocating some new blocks. Fixes: 5f634d064c70 ("ext4: Fix quota accounting error with fallocate") Cc: stable@kernel.org Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230424033846.4732-2-libaokun1@huawei.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/indirect.c | 8 ++++++++ fs/ext4/inode.c | 10 ---------- 2 files changed, 8 insertions(+), 10 deletions(-) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 237983cd8cdc..c2bb2ff3fbb6 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -649,6 +649,14 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, ext4_update_inode_fsync_trans(handle, inode, 1); count = ar.len; + + /* + * Update reserved blocks/metadata blocks after successful block + * allocation which had been deferred till now. + */ + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) + ext4_da_update_reserve_space(inode, count, 1); + got_it: map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = le32_to_cpu(chain[depth-1].key); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d3143746bcdb..365c4d3a434a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -654,16 +654,6 @@ found: */ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); } - - /* - * Update reserved blocks/metadata blocks after successful - * block allocation which had been deferred till now. We don't - * support fallocate for non extent files. So we can update - * reserve space here. - */ - if ((retval > 0) && - (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)) - ext4_da_update_reserve_space(inode, retval, 1); } if (retval > 0) { From 47b7eaae08e8b2f25bdf37bc14d21be090bcb20f Mon Sep 17 00:00:00 2001 From: Siddh Raman Pant Date: Tue, 20 Jun 2023 22:17:00 +0530 Subject: [PATCH 4125/4345] jfs: jfs_dmap: Validate db_l2nbperpage while mounting commit 11509910c599cbd04585ec35a6d5e1a0053d84c1 upstream. In jfs_dmap.c at line 381, BLKTODMAP is used to get a logical block number inside dbFree(). db_l2nbperpage, which is the log2 number of blocks per page, is passed as an argument to BLKTODMAP which uses it for shifting. Syzbot reported a shift out-of-bounds crash because db_l2nbperpage is too big. This happens because the large value is set without any validation in dbMount() at line 181. Thus, make sure that db_l2nbperpage is correct while mounting. Max number of blocks per page = Page size / Min block size => log2(Max num_block per page) = log2(Page size / Min block size) = log2(Page size) - log2(Min block size) => Max db_l2nbperpage = L2PSIZE - L2MINBLOCKSIZE Reported-and-tested-by: syzbot+d2cd27dcf8e04b232eb2@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?id=2a70a453331db32ed491f5cbb07e81bf2d225715 Cc: stable@vger.kernel.org Suggested-by: Dave Kleikamp Signed-off-by: Siddh Raman Pant Signed-off-by: Dave Kleikamp Signed-off-by: Greg Kroah-Hartman --- fs/jfs/jfs_dmap.c | 6 ++++++ fs/jfs/jfs_filsys.h | 2 ++ 2 files changed, 8 insertions(+) diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 501263355ef4..bd9af2be352f 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -178,7 +178,13 @@ int dbMount(struct inode *ipbmap) dbmp_le = (struct dbmap_disk *) mp->data; bmp->db_mapsize = le64_to_cpu(dbmp_le->dn_mapsize); bmp->db_nfree = le64_to_cpu(dbmp_le->dn_nfree); + bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); + if (bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE) { + err = -EINVAL; + goto err_release_metapage; + } + bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag); if (!bmp->db_numag) { err = -EINVAL; diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index b5d702df7111..33ef13a0b110 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -122,7 +122,9 @@ #define NUM_INODE_PER_IAG INOSPERIAG #define MINBLOCKSIZE 512 +#define L2MINBLOCKSIZE 9 #define MAXBLOCKSIZE 4096 +#define L2MAXBLOCKSIZE 12 #define MAXFILESIZE ((s64)1 << 52) #define JFS_LINK_MAX 0xffffffff From 5a89a5cc817e924fa1705f0cbd0e320638f0fc01 Mon Sep 17 00:00:00 2001 From: Martin Kaiser Date: Thu, 15 Jun 2023 15:49:59 +0100 Subject: [PATCH 4126/4345] hwrng: imx-rngc - fix the timeout for init and self check commit d744ae7477190967a3ddc289e2cd4ae59e8b1237 upstream. Fix the timeout that is used for the initialisation and for the self test. wait_for_completion_timeout expects a timeout in jiffies, but RNGC_TIMEOUT is in milliseconds. Call msecs_to_jiffies to do the conversion. Cc: stable@vger.kernel.org Fixes: 1d5449445bd0 ("hwrng: mx-rngc - add a driver for Freescale RNGC") Signed-off-by: Martin Kaiser Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/char/hw_random/imx-rngc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/char/hw_random/imx-rngc.c b/drivers/char/hw_random/imx-rngc.c index 9b182e5bfa87..dbb2da630611 100644 --- a/drivers/char/hw_random/imx-rngc.c +++ b/drivers/char/hw_random/imx-rngc.c @@ -110,7 +110,7 @@ static int imx_rngc_self_test(struct imx_rngc *rngc) cmd = readl(rngc->base + RNGC_COMMAND); writel(cmd | RNGC_CMD_SELF_TEST, rngc->base + RNGC_COMMAND); - ret = wait_for_completion_timeout(&rngc->rng_op_done, RNGC_TIMEOUT); + ret = wait_for_completion_timeout(&rngc->rng_op_done, msecs_to_jiffies(RNGC_TIMEOUT)); imx_rngc_irq_mask_clear(rngc); if (!ret) return -ETIMEDOUT; @@ -187,9 +187,7 @@ static int imx_rngc_init(struct hwrng *rng) cmd = readl(rngc->base + RNGC_COMMAND); writel(cmd | RNGC_CMD_SEED, rngc->base + RNGC_COMMAND); - ret = wait_for_completion_timeout(&rngc->rng_op_done, - RNGC_TIMEOUT); - + ret = wait_for_completion_timeout(&rngc->rng_op_done, msecs_to_jiffies(RNGC_TIMEOUT)); if (!ret) { ret = -ETIMEDOUT; goto err; From d3bab5de91c62a845ca328834e7805122d48a60b Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Wed, 14 Jun 2023 09:42:53 +0200 Subject: [PATCH 4127/4345] PCI/PM: Avoid putting EloPOS E2/S2/H2 PCIe Ports in D3cold commit 9e30fd26f43b89cb6b4e850a86caa2e50dedb454 upstream. The quirk for Elo i2 introduced in commit 92597f97a40b ("PCI/PM: Avoid putting Elo i2 PCIe Ports in D3cold") is also needed by EloPOS E2/S2/H2 which uses the same Continental Z2 board. Change the quirk to match the board instead of system. Link: https://bugzilla.kernel.org/show_bug.cgi?id=215715 Link: https://lore.kernel.org/r/20230614074253.22318-1-linux@zary.sk Signed-off-by: Ondrej Zary Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/pci.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d37013d007b6..1f8106ec7094 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2830,13 +2830,13 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { { /* * Downstream device is not accessible after putting a root port - * into D3cold and back into D0 on Elo i2. + * into D3cold and back into D0 on Elo Continental Z2 board */ - .ident = "Elo i2", + .ident = "Elo Continental Z2", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Elo Touch Solutions"), - DMI_MATCH(DMI_PRODUCT_NAME, "Elo i2"), - DMI_MATCH(DMI_PRODUCT_VERSION, "RevB"), + DMI_MATCH(DMI_BOARD_VENDOR, "Elo Touch Solutions"), + DMI_MATCH(DMI_BOARD_NAME, "Geminilake"), + DMI_MATCH(DMI_BOARD_VERSION, "Continental Z2"), }, }, #endif From aca71b004a66475fa03172b1a8ee62a5590b0d88 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 7 Jun 2023 18:18:47 +0100 Subject: [PATCH 4128/4345] PCI: Add function 1 DMA alias quirk for Marvell 88SE9235 commit 88d341716b83abd355558523186ca488918627ee upstream. Marvell's own product brief implies the 92xx series are a closely related family, and sure enough it turns out that 9235 seems to need the same quirk as the other three, although possibly only when certain ports are used. Link: https://lore.kernel.org/linux-iommu/2a699a99-545c-1324-e052-7d2f41fed1ae@yahoo.co.uk/ Link: https://lore.kernel.org/r/731507e05d70239aec96fcbfab6e65d8ce00edd2.1686157165.git.robin.murphy@arm.com Reported-by: Jason Adriaanse Signed-off-by: Robin Murphy Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/quirks.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index c1ebd5e12b06..c0d113481191 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4123,6 +4123,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9220, /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c49 */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9230, quirk_dma_func1_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9235, + quirk_dma_func1_alias); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TTI, 0x0642, quirk_dma_func1_alias); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TTI, 0x0645, From 48e11e7c81b91002a120a513312a4de9f5ba7f08 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 19 Jun 2023 20:34:00 +0530 Subject: [PATCH 4129/4345] PCI: qcom: Disable write access to read only registers for IP v2.3.3 commit a33d700e8eea76c62120cb3dbf5e01328f18319a upstream. In the post init sequence of v2.9.0, write access to read only registers are not disabled after updating the registers. Fix it by disabling the access after register update. Link: https://lore.kernel.org/r/20230619150408.8468-2-manivannan.sadhasivam@linaro.org Fixes: 5d76117f070d ("PCI: qcom: Add support for IPQ8074 PCIe controller") Signed-off-by: Manivannan Sadhasivam Signed-off-by: Lorenzo Pieralisi Cc: Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/dwc/pcie-qcom.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index c68e14271c02..737cc9d6fa6a 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -771,6 +771,8 @@ static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie) return PTR_ERR(res->phy_ahb_reset); } + dw_pcie_dbi_ro_wr_dis(pci); + return 0; } From bec3e0f7f2724141ba5ad9ef952fc144a88ebf08 Mon Sep 17 00:00:00 2001 From: Rick Wertenbroek Date: Tue, 18 Apr 2023 09:46:50 +0200 Subject: [PATCH 4130/4345] PCI: rockchip: Assert PCI Configuration Enable bit after probe commit f397fd4ac1fa3afcabd8cee030f953ccaed2a364 upstream. Assert PCI Configuration Enable bit after probe. When this bit is left to 0 in the endpoint mode, the RK3399 PCIe endpoint core will generate configuration request retry status (CRS) messages back to the root complex. Assert this bit after probe to allow the RK3399 PCIe endpoint core to reply to configuration requests from the root complex. This is documented in section 17.5.8.1.2 of the RK3399 TRM. Link: https://lore.kernel.org/r/20230418074700.1083505-4-rick.wertenbroek@gmail.com Fixes: cf590b078391 ("PCI: rockchip: Add EP driver for Rockchip PCIe controller") Tested-by: Damien Le Moal Signed-off-by: Rick Wertenbroek Signed-off-by: Lorenzo Pieralisi Reviewed-by: Damien Le Moal Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pcie-rockchip-ep.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 379cde59988c..8af1b9b9e8db 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -631,6 +631,9 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev) ep->irq_pci_addr = ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR; + rockchip_pcie_write(rockchip, PCIE_CLIENT_CONF_ENABLE, + PCIE_CLIENT_CONFIG); + return 0; err_epc_mem_exit: pci_epc_mem_exit(epc); From ddda61419af341ad9ee033d66f24970b391c56f2 Mon Sep 17 00:00:00 2001 From: Rick Wertenbroek Date: Tue, 18 Apr 2023 09:46:49 +0200 Subject: [PATCH 4131/4345] PCI: rockchip: Write PCI Device ID to correct register commit 1f1c42ece18de365c976a060f3c8eb481b038e3a upstream. Write PCI Device ID (DID) to the correct register. The Device ID was not updated through the correct register. Device ID was written to a read-only register and therefore did not work. The Device ID is now set through the correct register. This is documented in the RK3399 TRM section 17.6.6.1.1 Link: https://lore.kernel.org/r/20230418074700.1083505-3-rick.wertenbroek@gmail.com Fixes: cf590b078391 ("PCI: rockchip: Add EP driver for Rockchip PCIe controller") Tested-by: Damien Le Moal Signed-off-by: Rick Wertenbroek Signed-off-by: Lorenzo Pieralisi Reviewed-by: Damien Le Moal Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pcie-rockchip-ep.c | 6 ++++-- drivers/pci/controller/pcie-rockchip.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 8af1b9b9e8db..2e28ed780acd 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -125,6 +125,7 @@ static void rockchip_pcie_prog_ep_ob_atu(struct rockchip_pcie *rockchip, u8 fn, static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, struct pci_epf_header *hdr) { + u32 reg; struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; @@ -137,8 +138,9 @@ static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, PCIE_CORE_CONFIG_VENDOR); } - rockchip_pcie_write(rockchip, hdr->deviceid << 16, - ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + PCI_VENDOR_ID); + reg = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_DID_VID); + reg = (reg & 0xFFFF) | (hdr->deviceid << 16); + rockchip_pcie_write(rockchip, reg, PCIE_EP_CONFIG_DID_VID); rockchip_pcie_write(rockchip, hdr->revid | diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index c7d0178fc8c2..173f47d4fa7b 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -132,6 +132,8 @@ #define PCIE_RC_RP_ATS_BASE 0x400000 #define PCIE_RC_CONFIG_NORMAL_BASE 0x800000 #define PCIE_RC_CONFIG_BASE 0xa00000 +#define PCIE_EP_CONFIG_BASE 0xa00000 +#define PCIE_EP_CONFIG_DID_VID (PCIE_EP_CONFIG_BASE + 0x00) #define PCIE_RC_CONFIG_RID_CCR (PCIE_RC_CONFIG_BASE + 0x08) #define PCIE_RC_CONFIG_SCC_SHIFT 16 #define PCIE_RC_CONFIG_DCR (PCIE_RC_CONFIG_BASE + 0xc4) From c417a4c7de1d5112a13ffc304a0a29bf7bd1107f Mon Sep 17 00:00:00 2001 From: Rick Wertenbroek Date: Tue, 18 Apr 2023 09:46:51 +0200 Subject: [PATCH 4132/4345] PCI: rockchip: Add poll and timeout to wait for PHY PLLs to be locked commit 9dd3c7c4c8c3f7f010d9cdb7c3f42506d93c9527 upstream. The RK3399 PCIe controller should wait until the PHY PLLs are locked. Add poll and timeout to wait for PHY PLLs to be locked. If they cannot be locked generate error message and jump to error handler. Accessing registers in the PHY clock domain when PLLs are not locked causes hang The PHY PLLs status is checked through a side channel register. This is documented in the TRM section 17.5.8.1 "PCIe Initialization Sequence". Link: https://lore.kernel.org/r/20230418074700.1083505-5-rick.wertenbroek@gmail.com Fixes: cf590b078391 ("PCI: rockchip: Add EP driver for Rockchip PCIe controller") Tested-by: Damien Le Moal Signed-off-by: Rick Wertenbroek Signed-off-by: Lorenzo Pieralisi Reviewed-by: Damien Le Moal Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pcie-rockchip.c | 17 +++++++++++++++++ drivers/pci/controller/pcie-rockchip.h | 2 ++ 2 files changed, 19 insertions(+) diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c index 990a00e08bc5..1aa84035a8bc 100644 --- a/drivers/pci/controller/pcie-rockchip.c +++ b/drivers/pci/controller/pcie-rockchip.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -153,6 +154,12 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) } EXPORT_SYMBOL_GPL(rockchip_pcie_parse_dt); +#define rockchip_pcie_read_addr(addr) rockchip_pcie_read(rockchip, addr) +/* 100 ms max wait time for PHY PLLs to lock */ +#define RK_PHY_PLL_LOCK_TIMEOUT_US 100000 +/* Sleep should be less than 20ms */ +#define RK_PHY_PLL_LOCK_SLEEP_US 1000 + int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) { struct device *dev = rockchip->dev; @@ -254,6 +261,16 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) } } + err = readx_poll_timeout(rockchip_pcie_read_addr, + PCIE_CLIENT_SIDE_BAND_STATUS, + regs, !(regs & PCIE_CLIENT_PHY_ST), + RK_PHY_PLL_LOCK_SLEEP_US, + RK_PHY_PLL_LOCK_TIMEOUT_US); + if (err) { + dev_err(dev, "PHY PLLs could not lock, %d\n", err); + goto err_power_off_phy; + } + /* * Please don't reorder the deassert sequence of the following * four reset pins. diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index 173f47d4fa7b..3503fdc266c6 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -37,6 +37,8 @@ #define PCIE_CLIENT_MODE_EP HIWORD_UPDATE(0x0040, 0) #define PCIE_CLIENT_GEN_SEL_1 HIWORD_UPDATE(0x0080, 0) #define PCIE_CLIENT_GEN_SEL_2 HIWORD_UPDATE_BIT(0x0080) +#define PCIE_CLIENT_SIDE_BAND_STATUS (PCIE_CLIENT_BASE + 0x20) +#define PCIE_CLIENT_PHY_ST BIT(12) #define PCIE_CLIENT_DEBUG_OUT_0 (PCIE_CLIENT_BASE + 0x3c) #define PCIE_CLIENT_DEBUG_LTSSM_MASK GENMASK(5, 0) #define PCIE_CLIENT_DEBUG_LTSSM_L1 0x18 From 36eb13031227e117ccedbdd090032fd8508e97f4 Mon Sep 17 00:00:00 2001 From: Rick Wertenbroek Date: Tue, 18 Apr 2023 09:46:54 +0200 Subject: [PATCH 4133/4345] PCI: rockchip: Fix legacy IRQ generation for RK3399 PCIe endpoint core commit 166e89d99dd85a856343cca51eee781b793801f2 upstream. Fix legacy IRQ generation for RK3399 PCIe endpoint core according to the technical reference manual (TRM). Assert and deassert legacy interrupt (INTx) through the legacy interrupt control register ("PCIE_CLIENT_LEGACY_INT_CTRL") instead of manually generating a PCIe message. The generation of the legacy interrupt was tested and validated with the PCIe endpoint test driver. Link: https://lore.kernel.org/r/20230418074700.1083505-8-rick.wertenbroek@gmail.com Fixes: cf590b078391 ("PCI: rockchip: Add EP driver for Rockchip PCIe controller") Tested-by: Damien Le Moal Signed-off-by: Rick Wertenbroek Signed-off-by: Lorenzo Pieralisi Reviewed-by: Damien Le Moal Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pcie-rockchip-ep.c | 45 ++++++----------------- drivers/pci/controller/pcie-rockchip.h | 6 ++- 2 files changed, 16 insertions(+), 35 deletions(-) diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 2e28ed780acd..f929b9dbb7e4 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -347,48 +347,25 @@ static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) } static void rockchip_pcie_ep_assert_intx(struct rockchip_pcie_ep *ep, u8 fn, - u8 intx, bool is_asserted) + u8 intx, bool do_assert) { struct rockchip_pcie *rockchip = &ep->rockchip; - u32 r = ep->max_regions - 1; - u32 offset; - u32 status; - u8 msg_code; - - if (unlikely(ep->irq_pci_addr != ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR || - ep->irq_pci_fn != fn)) { - rockchip_pcie_prog_ep_ob_atu(rockchip, fn, r, - AXI_WRAPPER_NOR_MSG, - ep->irq_phys_addr, 0, 0); - ep->irq_pci_addr = ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR; - ep->irq_pci_fn = fn; - } intx &= 3; - if (is_asserted) { + + if (do_assert) { ep->irq_pending |= BIT(intx); - msg_code = ROCKCHIP_PCIE_MSG_CODE_ASSERT_INTA + intx; + rockchip_pcie_write(rockchip, + PCIE_CLIENT_INT_IN_ASSERT | + PCIE_CLIENT_INT_PEND_ST_PEND, + PCIE_CLIENT_LEGACY_INT_CTRL); } else { ep->irq_pending &= ~BIT(intx); - msg_code = ROCKCHIP_PCIE_MSG_CODE_DEASSERT_INTA + intx; + rockchip_pcie_write(rockchip, + PCIE_CLIENT_INT_IN_DEASSERT | + PCIE_CLIENT_INT_PEND_ST_NORMAL, + PCIE_CLIENT_LEGACY_INT_CTRL); } - - status = rockchip_pcie_read(rockchip, - ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + - ROCKCHIP_PCIE_EP_CMD_STATUS); - status &= ROCKCHIP_PCIE_EP_CMD_STATUS_IS; - - if ((status != 0) ^ (ep->irq_pending != 0)) { - status ^= ROCKCHIP_PCIE_EP_CMD_STATUS_IS; - rockchip_pcie_write(rockchip, status, - ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + - ROCKCHIP_PCIE_EP_CMD_STATUS); - } - - offset = - ROCKCHIP_PCIE_MSG_ROUTING(ROCKCHIP_PCIE_MSG_ROUTING_LOCAL_INTX) | - ROCKCHIP_PCIE_MSG_CODE(msg_code) | ROCKCHIP_PCIE_MSG_NO_DATA; - writel(0, ep->irq_cpu_addr + offset); } static int rockchip_pcie_ep_send_legacy_irq(struct rockchip_pcie_ep *ep, u8 fn, diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index 3503fdc266c6..b714cc2410d0 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -37,6 +37,11 @@ #define PCIE_CLIENT_MODE_EP HIWORD_UPDATE(0x0040, 0) #define PCIE_CLIENT_GEN_SEL_1 HIWORD_UPDATE(0x0080, 0) #define PCIE_CLIENT_GEN_SEL_2 HIWORD_UPDATE_BIT(0x0080) +#define PCIE_CLIENT_LEGACY_INT_CTRL (PCIE_CLIENT_BASE + 0x0c) +#define PCIE_CLIENT_INT_IN_ASSERT HIWORD_UPDATE_BIT(0x0002) +#define PCIE_CLIENT_INT_IN_DEASSERT HIWORD_UPDATE(0x0002, 0) +#define PCIE_CLIENT_INT_PEND_ST_PEND HIWORD_UPDATE_BIT(0x0001) +#define PCIE_CLIENT_INT_PEND_ST_NORMAL HIWORD_UPDATE(0x0001, 0) #define PCIE_CLIENT_SIDE_BAND_STATUS (PCIE_CLIENT_BASE + 0x20) #define PCIE_CLIENT_PHY_ST BIT(12) #define PCIE_CLIENT_DEBUG_OUT_0 (PCIE_CLIENT_BASE + 0x3c) @@ -234,7 +239,6 @@ #define ROCKCHIP_PCIE_EP_MSI_CTRL_ME BIT(16) #define ROCKCHIP_PCIE_EP_MSI_CTRL_MASK_MSI_CAP BIT(24) #define ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR 0x1 -#define ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR 0x3 #define ROCKCHIP_PCIE_EP_FUNC_BASE(fn) (((fn) << 12) & GENMASK(19, 12)) #define ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar) \ (PCIE_RC_RP_ATS_BASE + 0x0840 + (fn) * 0x0040 + (bar) * 0x0008) From f1986416cfb4474651916f87af948da581b1bccf Mon Sep 17 00:00:00 2001 From: Rick Wertenbroek Date: Tue, 18 Apr 2023 09:46:56 +0200 Subject: [PATCH 4134/4345] PCI: rockchip: Use u32 variable to access 32-bit registers commit 8962b2cb39119cbda4fc69a1f83957824f102f81 upstream. Previously u16 variables were used to access 32-bit registers, this resulted in not all of the data being read from the registers. Also the left shift of more than 16-bits would result in moving data out of the variable. Use u32 variables to access 32-bit registers Link: https://lore.kernel.org/r/20230418074700.1083505-10-rick.wertenbroek@gmail.com Fixes: cf590b078391 ("PCI: rockchip: Add EP driver for Rockchip PCIe controller") Tested-by: Damien Le Moal Signed-off-by: Rick Wertenbroek Signed-off-by: Lorenzo Pieralisi Reviewed-by: Damien Le Moal Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pcie-rockchip-ep.c | 10 +++++----- drivers/pci/controller/pcie-rockchip.h | 1 + 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index f929b9dbb7e4..a199ac2c7d5b 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -314,15 +314,15 @@ static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; - u16 flags; + u32 flags; flags = rockchip_pcie_read(rockchip, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK; flags |= - ((multi_msg_cap << 1) << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) | - PCI_MSI_FLAGS_64BIT; + (multi_msg_cap << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) | + (PCI_MSI_FLAGS_64BIT << ROCKCHIP_PCIE_EP_MSI_FLAGS_OFFSET); flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MASK_MSI_CAP; rockchip_pcie_write(rockchip, flags, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + @@ -334,7 +334,7 @@ static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; - u16 flags; + u32 flags; flags = rockchip_pcie_read(rockchip, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + @@ -395,7 +395,7 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, u8 interrupt_num) { struct rockchip_pcie *rockchip = &ep->rockchip; - u16 flags, mme, data, data_mask; + u32 flags, mme, data, data_mask; u8 msi_count; u64 pci_addr, pci_addr_mask = 0xff; diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index b714cc2410d0..76a5f96bfd0a 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -232,6 +232,7 @@ #define ROCKCHIP_PCIE_EP_CMD_STATUS 0x4 #define ROCKCHIP_PCIE_EP_CMD_STATUS_IS BIT(19) #define ROCKCHIP_PCIE_EP_MSI_CTRL_REG 0x90 +#define ROCKCHIP_PCIE_EP_MSI_FLAGS_OFFSET 16 #define ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET 17 #define ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK GENMASK(19, 17) #define ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET 20 From 8c90c466e38e2002e358445d62f927c1805e0e52 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 18 Apr 2023 09:46:58 +0200 Subject: [PATCH 4135/4345] PCI: rockchip: Set address alignment for endpoint mode commit 7e6689b34a815bd379dfdbe9855d36f395ef056c upstream. The address translation unit of the rockchip EP controller does not use the lower 8 bits of a PCIe-space address to map local memory. Thus we must set the align feature field to 256 to let the user know about this constraint. Link: https://lore.kernel.org/r/20230418074700.1083505-12-rick.wertenbroek@gmail.com Fixes: cf590b078391 ("PCI: rockchip: Add EP driver for Rockchip PCIe controller") Signed-off-by: Damien Le Moal Signed-off-by: Rick Wertenbroek Signed-off-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/pci/controller/pcie-rockchip-ep.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index a199ac2c7d5b..dba8bdc3fc94 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -485,6 +485,7 @@ static const struct pci_epc_features rockchip_pcie_epc_features = { .linkup_notifier = false, .msi_capable = true, .msix_capable = false, + .align = 256, }; static const struct pci_epc_features* From cdf9a7e2cdc7a5464e3cc6d0b715ba2b1d215521 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sat, 15 Apr 2023 11:35:39 +0900 Subject: [PATCH 4136/4345] misc: pci_endpoint_test: Free IRQs before removing the device commit f61b7634a3249d12b9daa36ffbdb9965b6f24c6c upstream. In pci_endpoint_test_remove(), freeing the IRQs after removing the device creates a small race window for IRQs to be received with the test device memory already released, causing the IRQ handler to access invalid memory, resulting in an oops. Free the device IRQs before removing the device to avoid this issue. Link: https://lore.kernel.org/r/20230415023542.77601-15-dlemoal@kernel.org Fixes: e03327122e2c ("pci_endpoint_test: Add 2 ioctl commands") Signed-off-by: Damien Le Moal Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/pci_endpoint_test.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index 48eec5fe7397..ab54fa39b9b0 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -935,6 +935,9 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev) if (id < 0) return; + pci_endpoint_test_release_irq(test); + pci_endpoint_test_free_irq_vectors(test); + misc_deregister(&test->miscdev); kfree(misc_device->name); kfree(test->name); @@ -944,9 +947,6 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev) pci_iounmap(pdev, test->bar[bar]); } - pci_endpoint_test_release_irq(test); - pci_endpoint_test_free_irq_vectors(test); - pci_release_regions(pdev); pci_disable_device(pdev); } From 8e3c7776405a31400999160247bf9443c35c2a3b Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sat, 15 Apr 2023 11:35:40 +0900 Subject: [PATCH 4137/4345] misc: pci_endpoint_test: Re-init completion for every test commit fb620ae73b70c2f57b9d3e911fc24c024ba2324f upstream. The irq_raised completion used to detect the end of a test case is initialized when the test device is probed, but never reinitialized again before a test case. As a result, the irq_raised completion synchronization is effective only for the first ioctl test case executed. Any subsequent call to wait_for_completion() by another ioctl() call will immediately return, potentially too early, leading to false positive failures. Fix this by reinitializing the irq_raised completion before starting a new ioctl() test command. Link: https://lore.kernel.org/r/20230415023542.77601-16-dlemoal@kernel.org Fixes: 2c156ac71c6b ("misc: Add host side PCI driver for PCI test function device") Signed-off-by: Damien Le Moal Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/pci_endpoint_test.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index ab54fa39b9b0..6c4c85eb7147 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -727,6 +727,10 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, struct pci_dev *pdev = test->pdev; mutex_lock(&test->mutex); + + reinit_completion(&test->irq_raised); + test->last_irq = -ENODATA; + switch (cmd) { case PCITEST_BAR: bar = arg; From 5e9aff5b10c2c98217217c3f14ccd10042e50bbe Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 23 Jun 2023 14:05:23 -0400 Subject: [PATCH 4138/4345] md/raid0: add discard support for the 'original' layout commit e836007089ba8fdf24e636ef2b007651fb4582e6 upstream. We've found that using raid0 with the 'original' layout and discard enabled with different disk sizes (such that at least two zones are created) can result in data corruption. This is due to the fact that the discard handling in 'raid0_handle_discard()' assumes the 'alternate' layout. We've seen this corruption using ext4 but other filesystems are likely susceptible as well. More specifically, while multiple zones are necessary to create the corruption, the corruption may not occur with multiple zones if they layout in such a way the layout matches what the 'alternate' layout would have produced. Thus, not all raid0 devices with the 'original' layout, different size disks and discard enabled will encounter this corruption. The 3.14 kernel inadvertently changed the raid0 disk layout for different size disks. Thus, running a pre-3.14 kernel and post-3.14 kernel on the same raid0 array could corrupt data. This lead to the creation of the 'original' layout (to match the pre-3.14 layout) and the 'alternate' layout (to match the post 3.14 layout) in the 5.4 kernel time frame and an option to tell the kernel which layout to use (since it couldn't be autodetected). However, when the 'original' layout was added back to 5.4 discard support for the 'original' layout was not added leading this issue. I've been able to reliably reproduce the corruption with the following test case: 1. create raid0 array with different size disks using original layout 2. mkfs 3. mount -o discard 4. create lots of files 5. remove 1/2 the files 6. fstrim -a (or just the mount point for the raid0 array) 7. umount 8. fsck -fn /dev/md0 (spews all sorts of corruptions) Let's fix this by adding proper discard support to the 'original' layout. The fix 'maps' the 'original' layout disks to the order in which they are read/written such that we can compare the disks in the same way that the current 'alternate' layout does. A 'disk_shift' field is added to 'struct strip_zone'. This could be computed on the fly in raid0_handle_discard() but by adding this field, we save some computation in the discard path. Note we could also potentially fix this by re-ordering the disks in the zones that follow the first one, and then always read/writing them using the 'alternate' layout. However, that is seen as a more substantial change, and we are attempting the least invasive fix at this time to remedy the corruption. I've verified the change using the reproducer mentioned above. Typically, the corruption is seen after less than 3 iterations, while the patch has run 500+ iterations. Cc: NeilBrown Cc: Song Liu Fixes: c84a1372df92 ("md/raid0: avoid RAID0 data corruption due to layout confusion.") Cc: stable@vger.kernel.org Signed-off-by: Jason Baron Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230623180523.1901230-1-jbaron@akamai.com Signed-off-by: Greg Kroah-Hartman --- drivers/md/raid0.c | 62 ++++++++++++++++++++++++++++++++++++++++------ drivers/md/raid0.h | 1 + 2 files changed, 55 insertions(+), 8 deletions(-) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index a20332e755e8..ee2cfd6c2dfb 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -274,6 +274,18 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) goto abort; } + if (conf->layout == RAID0_ORIG_LAYOUT) { + for (i = 1; i < conf->nr_strip_zones; i++) { + sector_t first_sector = conf->strip_zone[i-1].zone_end; + + sector_div(first_sector, mddev->chunk_sectors); + zone = conf->strip_zone + i; + /* disk_shift is first disk index used in the zone */ + zone->disk_shift = sector_div(first_sector, + zone->nb_dev); + } + } + pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; @@ -427,6 +439,20 @@ static void raid0_free(struct mddev *mddev, void *priv) kfree(conf); } +/* + * Convert disk_index to the disk order in which it is read/written. + * For example, if we have 4 disks, they are numbered 0,1,2,3. If we + * write the disks starting at disk 3, then the read/write order would + * be disk 3, then 0, then 1, and then disk 2 and we want map_disk_shift() + * to map the disks as follows 0,1,2,3 => 1,2,3,0. So disk 0 would map + * to 1, 1 to 2, 2 to 3, and 3 to 0. That way we can compare disks in + * that 'output' space to understand the read/write disk ordering. + */ +static int map_disk_shift(int disk_index, int num_disks, int disk_shift) +{ + return ((disk_index + num_disks - disk_shift) % num_disks); +} + static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) { struct r0conf *conf = mddev->private; @@ -440,7 +466,9 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) sector_t end_disk_offset; unsigned int end_disk_index; unsigned int disk; + sector_t orig_start, orig_end; + orig_start = start; zone = find_zone(conf, &start); if (bio_end_sector(bio) > zone->zone_end) { @@ -454,6 +482,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) } else end = bio_end_sector(bio); + orig_end = end; if (zone != conf->strip_zone) end = end - zone[-1].zone_end; @@ -465,13 +494,26 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) last_stripe_index = end; sector_div(last_stripe_index, stripe_size); - start_disk_index = (int)(start - first_stripe_index * stripe_size) / - mddev->chunk_sectors; + /* In the first zone the original and alternate layouts are the same */ + if ((conf->layout == RAID0_ORIG_LAYOUT) && (zone != conf->strip_zone)) { + sector_div(orig_start, mddev->chunk_sectors); + start_disk_index = sector_div(orig_start, zone->nb_dev); + start_disk_index = map_disk_shift(start_disk_index, + zone->nb_dev, + zone->disk_shift); + sector_div(orig_end, mddev->chunk_sectors); + end_disk_index = sector_div(orig_end, zone->nb_dev); + end_disk_index = map_disk_shift(end_disk_index, + zone->nb_dev, zone->disk_shift); + } else { + start_disk_index = (int)(start - first_stripe_index * stripe_size) / + mddev->chunk_sectors; + end_disk_index = (int)(end - last_stripe_index * stripe_size) / + mddev->chunk_sectors; + } start_disk_offset = ((int)(start - first_stripe_index * stripe_size) % mddev->chunk_sectors) + first_stripe_index * mddev->chunk_sectors; - end_disk_index = (int)(end - last_stripe_index * stripe_size) / - mddev->chunk_sectors; end_disk_offset = ((int)(end - last_stripe_index * stripe_size) % mddev->chunk_sectors) + last_stripe_index * mddev->chunk_sectors; @@ -480,18 +522,22 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) sector_t dev_start, dev_end; struct bio *discard_bio = NULL; struct md_rdev *rdev; + int compare_disk; - if (disk < start_disk_index) + compare_disk = map_disk_shift(disk, zone->nb_dev, + zone->disk_shift); + + if (compare_disk < start_disk_index) dev_start = (first_stripe_index + 1) * mddev->chunk_sectors; - else if (disk > start_disk_index) + else if (compare_disk > start_disk_index) dev_start = first_stripe_index * mddev->chunk_sectors; else dev_start = start_disk_offset; - if (disk < end_disk_index) + if (compare_disk < end_disk_index) dev_end = (last_stripe_index + 1) * mddev->chunk_sectors; - else if (disk > end_disk_index) + else if (compare_disk > end_disk_index) dev_end = last_stripe_index * mddev->chunk_sectors; else dev_end = end_disk_offset; diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h index 3816e5477db1..8cc761ca7423 100644 --- a/drivers/md/raid0.h +++ b/drivers/md/raid0.h @@ -6,6 +6,7 @@ struct strip_zone { sector_t zone_end; /* Start of the next zone (in sectors) */ sector_t dev_start; /* Zone offset in real dev (in sectors) */ int nb_dev; /* # of devices attached to the zone */ + int disk_shift; /* start disk for the original layout */ }; /* Linux 3.14 (20d0189b101) made an unintended change to From 23d5004ee7aaa0688accdd5fea6e82a7e6e3d151 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 19 May 2023 11:21:24 -0400 Subject: [PATCH 4139/4345] fs: dlm: return positive pid value for F_GETLK commit 92655fbda5c05950a411eaabc19e025e86e2a291 upstream. The GETLK pid values have all been negated since commit 9d5b86ac13c5 ("fs/locks: Remove fl_nspid and use fs-specific l_pid for remote locks"). Revert this for local pids, and leave in place negative pids for remote owners. Cc: stable@vger.kernel.org Fixes: 9d5b86ac13c5 ("fs/locks: Remove fl_nspid and use fs-specific l_pid for remote locks") Signed-off-by: Alexander Aring Signed-off-by: David Teigland Signed-off-by: Greg Kroah-Hartman --- fs/dlm/plock.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index a10d2bcfe75a..edce0b25cd90 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -363,7 +363,9 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file, locks_init_lock(fl); fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK; fl->fl_flags = FL_POSIX; - fl->fl_pid = -op->info.pid; + fl->fl_pid = op->info.pid; + if (op->info.nodeid != dlm_our_nodeid()) + fl->fl_pid = -fl->fl_pid; fl->fl_start = op->info.start; fl->fl_end = op->info.end; rv = 0; From b9ec9372a47a09377c50dc6eb8c3c8709d2790f8 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Mon, 9 Jan 2023 17:18:16 -0800 Subject: [PATCH 4140/4345] drm/atomic: Allow vblank-enabled + self-refresh "disable" commit 9d0e3cac3517942a6e00eeecfe583a98715edb16 upstream. The self-refresh helper framework overloads "disable" to sometimes mean "go into self-refresh mode," and this mode activates automatically (e.g., after some period of unchanging display output). In such cases, the display pipe is still considered "on", and user-space is not aware that we went into self-refresh mode. Thus, users may expect that vblank-related features (such as DRM_IOCTL_WAIT_VBLANK) still work properly. However, we trigger the WARN_ONCE() here if a CRTC driver tries to leave vblank enabled. Add a different expectation: that CRTCs *should* leave vblank enabled when going into self-refresh. This patch is preparation for another patch -- "drm/rockchip: vop: Leave vblank enabled in self-refresh" -- which resolves conflicts between the above self-refresh behavior and the API tests in IGT's kms_vblank test module. == Some alternatives discussed: == It's likely that on many display controllers, vblank interrupts will turn off when the CRTC is disabled, and so in some cases, self-refresh may not support vblank. To support such cases, we might consider additions to the generic helpers such that we fire vblank events based on a timer. However, there is currently only one driver using the common self-refresh helpers (i.e., rockchip), and at least as of commit bed030a49f3e ("drm/rockchip: Don't fully disable vop on self refresh"), the CRTC hardware is powered enough to continue to generate vblank interrupts. So we chose the simpler option of leaving vblank interrupts enabled. We can reevaluate this decision and perhaps augment the helpers if/when we gain a second driver that has different requirements. v3: * include discussion summary v2: * add 'ret != 0' warning case for self-refresh * describe failing test case and relation to drm/rockchip patch better Cc: # dependency for "drm/rockchip: vop: Leave # vblank enabled in self-refresh" Signed-off-by: Brian Norris Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20230109171809.v3.1.I3904f697863649eb1be540ecca147a66e42bfad7@changeid Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_atomic_helper.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 7fc8e7000046..0fde260b7edd 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1113,7 +1113,16 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state) continue; ret = drm_crtc_vblank_get(crtc); - WARN_ONCE(ret != -EINVAL, "driver forgot to call drm_crtc_vblank_off()\n"); + /* + * Self-refresh is not a true "disable"; ensure vblank remains + * enabled. + */ + if (new_crtc_state->self_refresh_active) + WARN_ONCE(ret != 0, + "driver disabled vblank in self-refresh\n"); + else + WARN_ONCE(ret != -EINVAL, + "driver forgot to call drm_crtc_vblank_off()\n"); if (ret == 0) drm_crtc_vblank_put(crtc); } From d89bd2ecd39bf30ff643ecee52e0955c2871efd3 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Mon, 9 Jan 2023 17:18:17 -0800 Subject: [PATCH 4141/4345] drm/rockchip: vop: Leave vblank enabled in self-refresh commit 2bdba9d4a3baa758c2ca7f5b37b35c7b3391dc42 upstream. If we disable vblank when entering self-refresh, vblank APIs (like DRM_IOCTL_WAIT_VBLANK) no longer work. But user space is not aware when we enter self-refresh, so this appears to be an API violation -- that DRM_IOCTL_WAIT_VBLANK fails with EINVAL whenever the display is idle and enters self-refresh. The downstream driver used by many of these systems never used to disable vblank for PSR, and in fact, even upstream, we didn't do that until radically redesigning the state machine in commit 6c836d965bad ("drm/rockchip: Use the helpers for PSR"). Thus, it seems like a reasonable API fix to simply restore that behavior, and leave vblank enabled. Note that this appears to potentially unbalance the drm_crtc_vblank_{off,on}() calls in some cases, but: (a) drm_crtc_vblank_on() documents this as OK and (b) if I do the naive balancing, I find state machine issues such that we're not in sync properly; so it's easier to take advantage of (a). This issue was exposed by IGT's kms_vblank tests, and reported by KernelCI. The bug has been around a while (longer than KernelCI noticed), but was only exposed once self-refresh was bugfixed more recently, and so KernelCI could properly test it. Some other notes in: https://lore.kernel.org/dri-devel/Y6OCg9BPnJvimQLT@google.com/ Re: renesas/master bisection: igt-kms-rockchip.kms_vblank.pipe-A-wait-forked on rk3399-gru-kevin == Backporting notes: == Marking as 'Fixes' commit 6c836d965bad ("drm/rockchip: Use the helpers for PSR"), but it probably depends on commit bed030a49f3e ("drm/rockchip: Don't fully disable vop on self refresh") as well. We also need the previous patch ("drm/atomic: Allow vblank-enabled + self-refresh "disable""), of course. v3: * no update v2: * skip unnecessary lock/unlock Fixes: 6c836d965bad ("drm/rockchip: Use the helpers for PSR") Cc: Reported-by: "kernelci.org bot" Link: https://lore.kernel.org/dri-devel/Y5itf0+yNIQa6fU4@sirena.org.uk/ Signed-off-by: Brian Norris Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20230109171809.v3.2.Ic07cba4ab9a7bd3618a9e4258b8f92ea7d10ae5a@changeid Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index af98bfcde518..65dde9df9793 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -702,13 +702,13 @@ static void vop_crtc_atomic_disable(struct drm_crtc *crtc, if (crtc->state->self_refresh_active) rockchip_drm_set_win_enabled(crtc, false); + if (crtc->state->self_refresh_active) + goto out; + mutex_lock(&vop->vop_lock); drm_crtc_vblank_off(crtc); - if (crtc->state->self_refresh_active) - goto out; - /* * Vop standby will take effect at end of current frame, * if dsp hold valid irq happen, it means standby complete. @@ -740,9 +740,9 @@ static void vop_crtc_atomic_disable(struct drm_crtc *crtc, vop_core_clks_disable(vop); pm_runtime_put(vop->dev); -out: mutex_unlock(&vop->vop_lock); +out: if (crtc->state->event && !crtc->state->active) { spin_lock_irq(&crtc->dev->event_lock); drm_crtc_send_vblank_event(crtc, crtc->state->event); From 4016d36fec633f8e48be5807f656f38d7f97b5d2 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 23 Jun 2023 10:05:19 -0500 Subject: [PATCH 4142/4345] drm/amd/display: Correct `DMUB_FW_VERSION` macro commit 274d205cb59f43815542e04b42a9e6d0b9b95eff upstream. The `DMUB_FW_VERSION` macro has a mistake in that the revision field is off by one byte. The last byte is typically used for other purposes and not a revision. Cc: stable@vger.kernel.org Cc: Sean Wang Cc: Marc Rossi Cc: Hamza Mahfooz Cc: Tsung-hua (Ryan) Lin Reviewed-by: Leo Li Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/amd/display/dmub/dmub_srv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index c6a8d6c54621..882b4e2816b5 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -347,7 +347,7 @@ struct dmub_srv { * of a firmware to know if feature or functionality is supported or present. */ #define DMUB_FW_VERSION(major, minor, revision) \ - ((((major) & 0xFF) << 24) | (((minor) & 0xFF) << 16) | ((revision) & 0xFFFF)) + ((((major) & 0xFF) << 24) | (((minor) & 0xFF) << 16) | (((revision) & 0xFF) << 8)) /** * dmub_srv_create() - creates the DMUB service. From 08673739ed85bb4c465bcddf0c874a01033ac029 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 19 Jun 2023 12:45:17 +0300 Subject: [PATCH 4143/4345] serial: atmel: don't enable IRQs prematurely commit 27a826837ec9a3e94cc44bd9328b8289b0fcecd7 upstream. The atmel_complete_tx_dma() function disables IRQs at the start of the function by calling spin_lock_irqsave(&port->lock, flags); There is no need to disable them a second time using the spin_lock_irq() function and, in fact, doing so is a bug because it will enable IRQs prematurely when we call spin_unlock_irq(). Just use spin_lock/unlock() instead without disabling or enabling IRQs. Fixes: 08f738be88bb ("serial: at91: add tx dma support") Signed-off-by: Dan Carpenter Reviewed-by: Jiri Slaby Acked-by: Richard Genoud Link: https://lore.kernel.org/r/cb7c39a9-c004-4673-92e1-be4e34b85368@moroto.mountain Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/atmel_serial.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 02fd0e79c8f7..a1249bed6636 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -873,11 +873,11 @@ static void atmel_complete_tx_dma(void *arg) port->icount.tx += atmel_port->tx_len; - spin_lock_irq(&atmel_port->lock_tx); + spin_lock(&atmel_port->lock_tx); async_tx_ack(atmel_port->desc_tx); atmel_port->cookie_tx = -EINVAL; atmel_port->desc_tx = NULL; - spin_unlock_irq(&atmel_port->lock_tx); + spin_unlock(&atmel_port->lock_tx); if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) uart_write_wakeup(port); From a49e5a05121c8bc471a57b4916c5393749c24de5 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 10 Jun 2023 17:59:25 +0200 Subject: [PATCH 4144/4345] tty: serial: samsung_tty: Fix a memory leak in s3c24xx_serial_getclk() in case of error commit a9c09546e903f1068acfa38e1ee18bded7114b37 upstream. If clk_get_rate() fails, the clk that has just been allocated needs to be freed. Cc: # v3.3+ Reviewed-by: Krzysztof Kozlowski Reviewed-by: Andi Shyti Fixes: 5f5a7a5578c5 ("serial: samsung: switch to clkdev based clock lookup") Signed-off-by: Christophe JAILLET Reviewed-by: Jiri Slaby Message-ID: Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/samsung_tty.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index 263c33260d8a..b14f918998d0 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -1313,8 +1313,12 @@ static unsigned int s3c24xx_serial_getclk(struct s3c24xx_uart_port *ourport, continue; rate = clk_get_rate(clk); - if (!rate) + if (!rate) { + dev_err(ourport->port.dev, + "Failed to get clock rate for %s.\n", clkname); + clk_put(clk); continue; + } if (ourport->info->has_divslot) { unsigned long div = rate / req_baud; From 1962717c4649e026a4252fe6625175affd28a593 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 10 Jun 2023 17:59:26 +0200 Subject: [PATCH 4145/4345] tty: serial: samsung_tty: Fix a memory leak in s3c24xx_serial_getclk() when iterating clk commit 832e231cff476102e8204a9e7bddfe5c6154a375 upstream. When the best clk is searched, we iterate over all possible clk. If we find a better match, the previous one, if any, needs to be freed. If a better match has already been found, we still need to free the new one, otherwise it leaks. Cc: # v3.3+ Reviewed-by: Krzysztof Kozlowski Reviewed-by: Andi Shyti Fixes: 5f5a7a5578c5 ("serial: samsung: switch to clkdev based clock lookup") Signed-off-by: Christophe JAILLET Reviewed-by: Jiri Slaby Message-ID: Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/samsung_tty.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index b14f918998d0..fa5b1321d9b1 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -1344,10 +1344,18 @@ static unsigned int s3c24xx_serial_getclk(struct s3c24xx_uart_port *ourport, calc_deviation = -calc_deviation; if (calc_deviation < deviation) { + /* + * If we find a better clk, release the previous one, if + * any. + */ + if (!IS_ERR(*best_clk)) + clk_put(*best_clk); *best_clk = clk; best_quot = quot; *clk_num = cnt; deviation = calc_deviation; + } else { + clk_put(clk); } } From c04ed61ebf01968d7699b121663982493ed577fb Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 13 Jun 2023 16:15:21 -0500 Subject: [PATCH 4146/4345] firmware: stratix10-svc: Fix a potential resource leak in svc_create_memory_pool() commit 1995f15590ca222f91193ed11461862b450abfd6 upstream. svc_create_memory_pool() is only called from stratix10_svc_drv_probe(). Most of resources in the probe are managed, but not this memremap() call. There is also no memunmap() call in the file. So switch to devm_memremap() to avoid a resource leak. Cc: stable@vger.kernel.org Fixes: 7ca5ce896524 ("firmware: add Intel Stratix10 service layer driver") Link: https://lore.kernel.org/all/783e9dfbba34e28505c9efa8bba41f97fd0fa1dc.1686109400.git.christophe.jaillet@wanadoo.fr/ Signed-off-by: Christophe JAILLET Signed-off-by: Dinh Nguyen Message-ID: <20230613211521.16366-1-dinguyen@kernel.org> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/stratix10-svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index 78a446cb4348..f432fe7cb60d 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -622,7 +622,7 @@ svc_create_memory_pool(struct platform_device *pdev, end = rounddown(sh_memory->addr + sh_memory->size, PAGE_SIZE); paddr = begin; size = end - begin; - va = memremap(paddr, size, MEMREMAP_WC); + va = devm_memremap(dev, paddr, size, MEMREMAP_WC); if (!va) { dev_err(dev, "fail to remap shared memory\n"); return ERR_PTR(-EINVAL); From 8e807eadf0b9654c8c5b2313a9ed72f68dbfbc21 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 28 Jun 2023 07:57:09 +0800 Subject: [PATCH 4147/4345] ceph: don't let check_caps skip sending responses for revoke msgs commit 257e6172ab36ebbe295a6c9ee9a9dd0fe54c1dc2 upstream. If a client sends out a cap update dropping caps with the prior 'seq' just before an incoming cap revoke request, then the client may drop the revoke because it believes it's already released the requested capabilities. This causes the MDS to wait indefinitely for the client to respond to the revoke. It's therefore always a good idea to ack the cap revoke request with the bumped up 'seq'. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/61782 Signed-off-by: Xiubo Li Reviewed-by: Milind Changire Reviewed-by: Patrick Donnelly Signed-off-by: Ilya Dryomov Signed-off-by: Greg Kroah-Hartman --- fs/ceph/caps.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index e1fda3923944..432dc2a16e28 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -3574,6 +3574,15 @@ static void handle_cap_grant(struct inode *inode, } BUG_ON(cap->issued & ~cap->implemented); + /* don't let check_caps skip sending a response to MDS for revoke msgs */ + if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { + cap->mds_wanted = 0; + if (cap == ci->i_auth_cap) + check_caps = 1; /* check auth cap only */ + else + check_caps = 2; /* check all caps */ + } + if (extra_info->inline_version > 0 && extra_info->inline_version >= ci->i_inline_version) { ci->i_inline_version = extra_info->inline_version; From b56a07c2a550025d6f3700b64fdd135b3e266726 Mon Sep 17 00:00:00 2001 From: Weitao Wang Date: Fri, 2 Jun 2023 17:40:06 +0300 Subject: [PATCH 4148/4345] xhci: Fix resume issue of some ZHAOXIN hosts commit f927728186f0de1167262d6a632f9f7e96433d1a upstream. On ZHAOXIN ZX-100 project, xHCI can't work normally after resume from system Sx state. To fix this issue, when resume from system Sx state, reinitialize xHCI instead of restore. So, Add XHCI_RESET_ON_RESUME quirk for ZX-100 to fix issue of resuming from system Sx state. Cc: stable@vger.kernel.org Signed-off-by: Weitao Wang Signed-off-by: Mathias Nyman Message-ID: <20230602144009.1225632-9-mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index aff65cefead2..b71e29aad9cc 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -330,6 +330,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4)) xhci->quirks |= XHCI_NO_SOFT_RETRY; + if (pdev->vendor == PCI_VENDOR_ID_ZHAOXIN) { + if (pdev->device == 0x9202) + xhci->quirks |= XHCI_RESET_ON_RESUME; + } + /* xHC spec requires PCI devices to support D3hot and D3cold */ if (xhci->hci_version >= 0x120) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; From c52e04c58dedfff62b066cacd6f6dd6423eccd99 Mon Sep 17 00:00:00 2001 From: Weitao Wang Date: Fri, 2 Jun 2023 17:40:07 +0300 Subject: [PATCH 4149/4345] xhci: Fix TRB prefetch issue of ZHAOXIN hosts commit 2a865a652299f5666f3b785cbe758c5f57453036 upstream. On some ZHAOXIN hosts, xHCI will prefetch TRB for performance improvement. However this TRB prefetch mechanism may cross page boundary, which may access memory not allocated by xHCI driver. In order to fix this issue, two pages was allocated for a segment and only the first page will be used. And add a quirk XHCI_ZHAOXIN_TRB_FETCH for this issue. Cc: stable@vger.kernel.org Signed-off-by: Weitao Wang Signed-off-by: Mathias Nyman Message-ID: <20230602144009.1225632-10-mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 8 ++++++-- drivers/usb/host/xhci-pci.c | 7 ++++++- drivers/usb/host/xhci.h | 1 + 3 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index a8a9addb4d25..cba05bb9ac37 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -2472,8 +2472,12 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) * and our use of dma addresses in the trb_address_map radix tree needs * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need. */ - xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, - TRB_SEGMENT_SIZE, TRB_SEGMENT_SIZE, xhci->page_size); + if (xhci->quirks & XHCI_ZHAOXIN_TRB_FETCH) + xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, + TRB_SEGMENT_SIZE * 2, TRB_SEGMENT_SIZE * 2, xhci->page_size * 2); + else + xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, + TRB_SEGMENT_SIZE, TRB_SEGMENT_SIZE, xhci->page_size); /* See Table 46 and Note on Figure 55 */ xhci->device_pool = dma_pool_create("xHCI input/output contexts", dev, diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index b71e29aad9cc..8b772c9df435 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -331,8 +331,13 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_NO_SOFT_RETRY; if (pdev->vendor == PCI_VENDOR_ID_ZHAOXIN) { - if (pdev->device == 0x9202) + if (pdev->device == 0x9202) { xhci->quirks |= XHCI_RESET_ON_RESUME; + xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH; + } + + if (pdev->device == 0x9203) + xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH; } /* xHC spec requires PCI devices to support D3hot and D3cold */ diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index c7749f6e3474..c8c873620583 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1895,6 +1895,7 @@ struct xhci_hcd { #define XHCI_EP_CTX_BROKEN_DCS BIT_ULL(42) #define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43) #define XHCI_RESET_TO_DEFAULT BIT_ULL(44) +#define XHCI_ZHAOXIN_TRB_FETCH BIT_ULL(45) unsigned int num_active_eps; unsigned int limit_active_eps; From 790e4e82c57d07fdc011f63db028005691a0b7ab Mon Sep 17 00:00:00 2001 From: Weitao Wang Date: Fri, 2 Jun 2023 17:40:08 +0300 Subject: [PATCH 4150/4345] xhci: Show ZHAOXIN xHCI root hub speed correctly commit d9b0328d0b8b8298dfdc97cd8e0e2371d4bcc97b upstream. Some ZHAOXIN xHCI controllers follow usb3.1 spec, but only support gen1 speed 5Gbps. While in Linux kernel, if xHCI suspport usb3.1, root hub speed will show on 10Gbps. To fix this issue of ZHAOXIN xHCI platforms, read usb speed ID supported by xHCI to determine root hub speed. And add a quirk XHCI_ZHAOXIN_HOST for this issue. [fix warning about uninitialized symbol -Mathias] Suggested-by: Mathias Nyman Cc: stable@vger.kernel.org Signed-off-by: Weitao Wang Signed-off-by: Mathias Nyman Message-ID: <20230602144009.1225632-11-mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 31 ++++++++++++++++++++++++------- drivers/usb/host/xhci-pci.c | 2 ++ drivers/usb/host/xhci.h | 1 + 3 files changed, 27 insertions(+), 7 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index cba05bb9ac37..390bdf823e08 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -2146,7 +2146,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, { u32 temp, port_offset, port_count; int i; - u8 major_revision, minor_revision; + u8 major_revision, minor_revision, tmp_minor_revision; struct xhci_hub *rhub; struct device *dev = xhci_to_hcd(xhci)->self.sysdev; struct xhci_port_cap *port_cap; @@ -2166,6 +2166,15 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, */ if (minor_revision > 0x00 && minor_revision < 0x10) minor_revision <<= 4; + /* + * Some zhaoxin's xHCI controller that follow usb3.1 spec + * but only support Gen1. + */ + if (xhci->quirks & XHCI_ZHAOXIN_HOST) { + tmp_minor_revision = minor_revision; + minor_revision = 0; + } + } else if (major_revision <= 0x02) { rhub = &xhci->usb2_rhub; } else { @@ -2175,10 +2184,6 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, /* Ignoring port protocol we can't understand. FIXME */ return; } - rhub->maj_rev = XHCI_EXT_PORT_MAJOR(temp); - - if (rhub->min_rev < minor_revision) - rhub->min_rev = minor_revision; /* Port offset and count in the third dword, see section 7.2 */ temp = readl(addr + 2); @@ -2197,8 +2202,6 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, if (xhci->num_port_caps > max_caps) return; - port_cap->maj_rev = major_revision; - port_cap->min_rev = minor_revision; port_cap->psi_count = XHCI_EXT_PORT_PSIC(temp); if (port_cap->psi_count) { @@ -2219,6 +2222,11 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, XHCI_EXT_PORT_PSIV(port_cap->psi[i - 1]))) port_cap->psi_uid_count++; + if (xhci->quirks & XHCI_ZHAOXIN_HOST && + major_revision == 0x03 && + XHCI_EXT_PORT_PSIV(port_cap->psi[i]) >= 5) + minor_revision = tmp_minor_revision; + xhci_dbg(xhci, "PSIV:%d PSIE:%d PLT:%d PFD:%d LP:%d PSIM:%d\n", XHCI_EXT_PORT_PSIV(port_cap->psi[i]), XHCI_EXT_PORT_PSIE(port_cap->psi[i]), @@ -2228,6 +2236,15 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, XHCI_EXT_PORT_PSIM(port_cap->psi[i])); } } + + rhub->maj_rev = major_revision; + + if (rhub->min_rev < minor_revision) + rhub->min_rev = minor_revision; + + port_cap->maj_rev = major_revision; + port_cap->min_rev = minor_revision; + /* cache usb2 port capabilities */ if (major_revision < 0x03 && xhci->num_ext_caps < max_caps) xhci->ext_caps[xhci->num_ext_caps++] = temp; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 8b772c9df435..8034e643a4af 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -331,6 +331,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_NO_SOFT_RETRY; if (pdev->vendor == PCI_VENDOR_ID_ZHAOXIN) { + xhci->quirks |= XHCI_ZHAOXIN_HOST; + if (pdev->device == 0x9202) { xhci->quirks |= XHCI_RESET_ON_RESUME; xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index c8c873620583..6a7c05940e66 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1896,6 +1896,7 @@ struct xhci_hcd { #define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43) #define XHCI_RESET_TO_DEFAULT BIT_ULL(44) #define XHCI_ZHAOXIN_TRB_FETCH BIT_ULL(45) +#define XHCI_ZHAOXIN_HOST BIT_ULL(46) unsigned int num_active_eps; unsigned int limit_active_eps; From 7f2f0e6ec561f6feeabefc1fc25e416d7cf05715 Mon Sep 17 00:00:00 2001 From: George Stark Date: Tue, 6 Jun 2023 19:53:57 +0300 Subject: [PATCH 4151/4345] meson saradc: fix clock divider mask length commit c57fa0037024c92c2ca34243e79e857da5d2c0a9 upstream. According to the datasheets of supported meson SoCs length of ADC_CLK_DIV field is 6-bit. Although all supported SoCs have the register with that field documented later SoCs use external clock rather than ADC internal clock so this patch affects only meson8 family (S8* SoCs). Fixes: 3adbf3427330 ("iio: adc: add a driver for the SAR ADC found in Amlogic Meson SoCs") Signed-off-by: George Stark Reviewed-by: Andy Shevchenko Reviewed-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20230606165357.42417-1-gnstark@sberdevices.ru Cc: Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/meson_saradc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c index e03988698755..e771299fac9d 100644 --- a/drivers/iio/adc/meson_saradc.c +++ b/drivers/iio/adc/meson_saradc.c @@ -71,7 +71,7 @@ #define MESON_SAR_ADC_REG3_PANEL_DETECT_COUNT_MASK GENMASK(20, 18) #define MESON_SAR_ADC_REG3_PANEL_DETECT_FILTER_TB_MASK GENMASK(17, 16) #define MESON_SAR_ADC_REG3_ADC_CLK_DIV_SHIFT 10 - #define MESON_SAR_ADC_REG3_ADC_CLK_DIV_WIDTH 5 + #define MESON_SAR_ADC_REG3_ADC_CLK_DIV_WIDTH 6 #define MESON_SAR_ADC_REG3_BLOCK_DLY_SEL_MASK GENMASK(9, 8) #define MESON_SAR_ADC_REG3_BLOCK_DLY_MASK GENMASK(7, 0) From 5f4a1111ad04ad08d582f6452779b3371b227192 Mon Sep 17 00:00:00 2001 From: Jiaqing Zhao Date: Mon, 19 Jun 2023 15:57:44 +0000 Subject: [PATCH 4152/4345] Revert "8250: add support for ASIX devices with a FIFO bug" commit a82d62f708545d22859584e0e0620da8e3759bbc upstream. This reverts commit eb26dfe8aa7eeb5a5aa0b7574550125f8aa4c3b3. Commit eb26dfe8aa7e ("8250: add support for ASIX devices with a FIFO bug") merged on Jul 13, 2012 adds a quirk for PCI_VENDOR_ID_ASIX (0x9710). But that ID is the same as PCI_VENDOR_ID_NETMOS defined in 1f8b061050c7 ("[PATCH] Netmos parallel/serial/combo support") merged on Mar 28, 2005. In pci_serial_quirks array, the NetMos entry always takes precedence over the ASIX entry even since it was initially merged, code in that commit is always unreachable. In my tests, adding the FIFO workaround to pci_netmos_init() makes no difference, and the vendor driver also does not have such workaround. Given that the code was never used for over a decade, it's safe to revert it. Also, the real PCI_VENDOR_ID_ASIX should be 0x125b, which is used on their newer AX99100 PCIe serial controllers released on 2016. The FIFO workaround should not be intended for these newer controllers, and it was never implemented in vendor driver. Fixes: eb26dfe8aa7e ("8250: add support for ASIX devices with a FIFO bug") Cc: stable Signed-off-by: Jiaqing Zhao Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230619155743.827859-1-jiaqing.zhao@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250.h | 1 - drivers/tty/serial/8250/8250_pci.c | 19 ------------------- drivers/tty/serial/8250/8250_port.c | 11 +++-------- include/linux/serial_8250.h | 1 - 4 files changed, 3 insertions(+), 29 deletions(-) diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 0771cd226581..61b11490ae5b 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -87,7 +87,6 @@ struct serial8250_config { #define UART_BUG_TXEN (1 << 1) /* UART has buggy TX IIR status */ #define UART_BUG_NOMSR (1 << 2) /* UART has buggy MSR status bits (Au1x00) */ #define UART_BUG_THRE (1 << 3) /* UART has buggy THRE reassertion */ -#define UART_BUG_PARITY (1 << 4) /* UART mishandles parity if FIFO enabled */ #define UART_BUG_TXRACE (1 << 5) /* UART Tx fails to set remote DR */ diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 9617f7ad332d..fd857d434326 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1044,14 +1044,6 @@ static int pci_oxsemi_tornado_init(struct pci_dev *dev) return number_uarts; } -static int pci_asix_setup(struct serial_private *priv, - const struct pciserial_board *board, - struct uart_8250_port *port, int idx) -{ - port->bugs |= UART_BUG_PARITY; - return pci_default_setup(priv, board, port, idx); -} - /* Quatech devices have their own extra interface features */ struct quatech_feature { @@ -1874,7 +1866,6 @@ pci_moxa_setup(struct serial_private *priv, #define PCI_DEVICE_ID_WCH_CH355_4S 0x7173 #define PCI_VENDOR_ID_AGESTAR 0x5372 #define PCI_DEVICE_ID_AGESTAR_9375 0x6872 -#define PCI_VENDOR_ID_ASIX 0x9710 #define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 0x818e @@ -2684,16 +2675,6 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .exit = pci_wch_ch38x_exit, .setup = pci_wch_ch38x_setup, }, - /* - * ASIX devices with FIFO bug - */ - { - .vendor = PCI_VENDOR_ID_ASIX, - .device = PCI_ANY_ID, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .setup = pci_asix_setup, - }, /* * Broadcom TruManage (NetXtreme) */ diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index b19908779e3b..432a438929e6 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2577,11 +2577,8 @@ static unsigned char serial8250_compute_lcr(struct uart_8250_port *up, if (c_cflag & CSTOPB) cval |= UART_LCR_STOP; - if (c_cflag & PARENB) { + if (c_cflag & PARENB) cval |= UART_LCR_PARITY; - if (up->bugs & UART_BUG_PARITY) - up->fifo_bug = true; - } if (!(c_cflag & PARODD)) cval |= UART_LCR_EPAR; #ifdef CMSPAR @@ -2744,8 +2741,7 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, up->lcr = cval; /* Save computed LCR */ if (up->capabilities & UART_CAP_FIFO && port->fifosize > 1) { - /* NOTE: If fifo_bug is not set, a user can set RX_trigger. */ - if ((baud < 2400 && !up->dma) || up->fifo_bug) { + if (baud < 2400 && !up->dma) { up->fcr &= ~UART_FCR_TRIGGER_MASK; up->fcr |= UART_FCR_TRIGGER_1; } @@ -3081,8 +3077,7 @@ static int do_set_rxtrig(struct tty_port *port, unsigned char bytes) struct uart_8250_port *up = up_to_u8250p(uport); int rxtrig; - if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1 || - up->fifo_bug) + if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1) return -EINVAL; rxtrig = bytes_to_fcr_rxtrig(up, bytes); diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 92f3b778d8c2..abb928361270 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -98,7 +98,6 @@ struct uart_8250_port { struct list_head list; /* ports on this IRQ */ u32 capabilities; /* port capabilities */ unsigned short bugs; /* port bugs */ - bool fifo_bug; /* min RX trigger if enabled */ unsigned int tx_loadsz; /* transmit fifo load size */ unsigned char acr; unsigned char fcr; From 07edd294b16a837714aa89885d3c621f23404892 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 22 Jun 2023 14:55:08 +0200 Subject: [PATCH 4153/4345] s390/decompressor: fix misaligned symbol build error commit 938f0c35d7d93a822ab9c9728e3205e8e57409d0 upstream. Nathan Chancellor reported a kernel build error on Fedora 39: $ clang --version | head -1 clang version 16.0.5 (Fedora 16.0.5-1.fc39) $ s390x-linux-gnu-ld --version | head -1 GNU ld version 2.40-1.fc39 $ make -skj"$(nproc)" ARCH=s390 CC=clang CROSS_COMPILE=s390x-linux-gnu- olddefconfig all s390x-linux-gnu-ld: arch/s390/boot/startup.o(.text+0x5b4): misaligned symbol `_decompressor_end' (0x35b0f) for relocation R_390_PC32DBL make[3]: *** [.../arch/s390/boot/Makefile:78: arch/s390/boot/vmlinux] Error 1 It turned out that the problem with misaligned symbols on s390 was fixed with commit 80ddf5ce1c92 ("s390: always build relocatable kernel") for the kernel image, but did not take into account that the decompressor uses its own set of CFLAGS, which come without -fPIE. Add the -fPIE flag also to the decompresser CFLAGS to fix this. Reported-by: Nathan Chancellor Tested-by: Nathan Chancellor Reported-by: CKI Suggested-by: Ulrich Weigand Link: https://github.com/ClangBuiltLinux/linux/issues/1747 Link: https://lore.kernel.org/32935.123062114500601371@us-mta-9.us.mimecast.lan/ Link: https://lore.kernel.org/r/20230622125508.1068457-1-hca@linux.ibm.com Cc: Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev Signed-off-by: Greg Kroah-Hartman --- arch/s390/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/Makefile b/arch/s390/Makefile index a8cb00f30a7c..39ffcd4389f1 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -29,6 +29,7 @@ KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables KBUILD_CFLAGS_DECOMPRESSOR += -ffreestanding KBUILD_CFLAGS_DECOMPRESSOR += -fno-stack-protector +KBUILD_CFLAGS_DECOMPRESSOR += -fPIE KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) From 1576f0df7b4d1f82db588d6654b89d796fa06929 Mon Sep 17 00:00:00 2001 From: Mohamed Khalfella Date: Wed, 12 Jul 2023 22:30:21 +0000 Subject: [PATCH 4154/4345] tracing/histograms: Add histograms to hist_vars if they have referenced variables commit 6018b585e8c6fa7d85d4b38d9ce49a5b67be7078 upstream. Hist triggers can have referenced variables without having direct variables fields. This can be the case if referenced variables are added for trigger actions. In this case the newly added references will not have field variables. Not taking such referenced variables into consideration can result in a bug where it would be possible to remove hist trigger with variables being refenced. This will result in a bug that is easily reproducable like so $ cd /sys/kernel/tracing $ echo 'synthetic_sys_enter char[] comm; long id' >> synthetic_events $ echo 'hist:keys=common_pid.execname,id.syscall:vals=hitcount:comm=common_pid.execname' >> events/raw_syscalls/sys_enter/trigger $ echo 'hist:keys=common_pid.execname,id.syscall:onmatch(raw_syscalls.sys_enter).synthetic_sys_enter($comm, id)' >> events/raw_syscalls/sys_enter/trigger $ echo '!hist:keys=common_pid.execname,id.syscall:vals=hitcount:comm=common_pid.execname' >> events/raw_syscalls/sys_enter/trigger [ 100.263533] ================================================================== [ 100.264634] BUG: KASAN: slab-use-after-free in resolve_var_refs+0xc7/0x180 [ 100.265520] Read of size 8 at addr ffff88810375d0f0 by task bash/439 [ 100.266320] [ 100.266533] CPU: 2 PID: 439 Comm: bash Not tainted 6.5.0-rc1 #4 [ 100.267277] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-20220807_005459-localhost 04/01/2014 [ 100.268561] Call Trace: [ 100.268902] [ 100.269189] dump_stack_lvl+0x4c/0x70 [ 100.269680] print_report+0xc5/0x600 [ 100.270165] ? resolve_var_refs+0xc7/0x180 [ 100.270697] ? kasan_complete_mode_report_info+0x80/0x1f0 [ 100.271389] ? resolve_var_refs+0xc7/0x180 [ 100.271913] kasan_report+0xbd/0x100 [ 100.272380] ? resolve_var_refs+0xc7/0x180 [ 100.272920] __asan_load8+0x71/0xa0 [ 100.273377] resolve_var_refs+0xc7/0x180 [ 100.273888] event_hist_trigger+0x749/0x860 [ 100.274505] ? kasan_save_stack+0x2a/0x50 [ 100.275024] ? kasan_set_track+0x29/0x40 [ 100.275536] ? __pfx_event_hist_trigger+0x10/0x10 [ 100.276138] ? ksys_write+0xd1/0x170 [ 100.276607] ? do_syscall_64+0x3c/0x90 [ 100.277099] ? entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 100.277771] ? destroy_hist_data+0x446/0x470 [ 100.278324] ? event_hist_trigger_parse+0xa6c/0x3860 [ 100.278962] ? __pfx_event_hist_trigger_parse+0x10/0x10 [ 100.279627] ? __kasan_check_write+0x18/0x20 [ 100.280177] ? mutex_unlock+0x85/0xd0 [ 100.280660] ? __pfx_mutex_unlock+0x10/0x10 [ 100.281200] ? kfree+0x7b/0x120 [ 100.281619] ? ____kasan_slab_free+0x15d/0x1d0 [ 100.282197] ? event_trigger_write+0xac/0x100 [ 100.282764] ? __kasan_slab_free+0x16/0x20 [ 100.283293] ? __kmem_cache_free+0x153/0x2f0 [ 100.283844] ? sched_mm_cid_remote_clear+0xb1/0x250 [ 100.284550] ? __pfx_sched_mm_cid_remote_clear+0x10/0x10 [ 100.285221] ? event_trigger_write+0xbc/0x100 [ 100.285781] ? __kasan_check_read+0x15/0x20 [ 100.286321] ? __bitmap_weight+0x66/0xa0 [ 100.286833] ? _find_next_bit+0x46/0xe0 [ 100.287334] ? task_mm_cid_work+0x37f/0x450 [ 100.287872] event_triggers_call+0x84/0x150 [ 100.288408] trace_event_buffer_commit+0x339/0x430 [ 100.289073] ? ring_buffer_event_data+0x3f/0x60 [ 100.292189] trace_event_raw_event_sys_enter+0x8b/0xe0 [ 100.295434] syscall_trace_enter.constprop.0+0x18f/0x1b0 [ 100.298653] syscall_enter_from_user_mode+0x32/0x40 [ 100.301808] do_syscall_64+0x1a/0x90 [ 100.304748] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 100.307775] RIP: 0033:0x7f686c75c1cb [ 100.310617] Code: 73 01 c3 48 8b 0d 65 3c 10 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 21 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 35 3c 10 00 f7 d8 64 89 01 48 [ 100.317847] RSP: 002b:00007ffc60137a38 EFLAGS: 00000246 ORIG_RAX: 0000000000000021 [ 100.321200] RAX: ffffffffffffffda RBX: 000055f566469ea0 RCX: 00007f686c75c1cb [ 100.324631] RDX: 0000000000000001 RSI: 0000000000000001 RDI: 000000000000000a [ 100.328104] RBP: 00007ffc60137ac0 R08: 00007f686c818460 R09: 000000000000000a [ 100.331509] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000009 [ 100.334992] R13: 0000000000000007 R14: 000000000000000a R15: 0000000000000007 [ 100.338381] We hit the bug because when second hist trigger has was created has_hist_vars() returned false because hist trigger did not have variables. As a result of that save_hist_vars() was not called to add the trigger to trace_array->hist_vars. Later on when we attempted to remove the first histogram find_any_var_ref() failed to detect it is being used because it did not find the second trigger in hist_vars list. With this change we wait until trigger actions are created so we can take into consideration if hist trigger has variable references. Also, now we check the return value of save_hist_vars() and fail trigger creation if save_hist_vars() fails. Link: https://lore.kernel.org/linux-trace-kernel/20230712223021.636335-1-mkhalfella@purestorage.com Cc: stable@vger.kernel.org Fixes: 067fe038e70f6 ("tracing: Add variable reference handling to hist triggers") Signed-off-by: Mohamed Khalfella Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_events_hist.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9ed65191888e..ae71cefb46bb 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5817,13 +5817,15 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, if (get_named_trigger_data(trigger_data)) goto enable; - if (has_hist_vars(hist_data)) - save_hist_vars(hist_data); - ret = create_actions(hist_data); if (ret) goto out_unreg; + if (has_hist_vars(hist_data) || hist_data->n_var_refs) { + if (save_hist_vars(hist_data)) + goto out_unreg; + } + ret = tracing_map_init(hist_data->map); if (ret) goto out_unreg; From 1f2a8f083575d1791b29adc4690b6a28475813fc Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Thu, 27 Apr 2023 16:06:59 +0200 Subject: [PATCH 4155/4345] samples: ftrace: Save required argument registers in sample trampolines commit 8564c315876ab86fcaf8e7f558d6a84cb2ce5590 upstream. The ftrace-direct-too sample traces the handle_mm_fault function whose signature changed since the introduction of the sample. Since: commit bce617edecad ("mm: do page fault accounting in handle_mm_fault") handle_mm_fault now has 4 arguments. Therefore, the sample trampoline should save 4 argument registers. s390 saves all argument registers already so it does not need a change but x86_64 needs an extra push and pop. This also evolves the signature of the tracing function to make it mirror the signature of the traced function. Link: https://lkml.kernel.org/r/20230427140700.625241-2-revest@chromium.org Cc: stable@vger.kernel.org Fixes: bce617edecad ("mm: do page fault accounting in handle_mm_fault") Reviewed-by: Steven Rostedt (Google) Reviewed-by: Mark Rutland Acked-by: Catalin Marinas Signed-off-by: Florent Revest Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- samples/ftrace/ftrace-direct-too.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c index 3927cb880d1a..4bdd67916ce4 100644 --- a/samples/ftrace/ftrace-direct-too.c +++ b/samples/ftrace/ftrace-direct-too.c @@ -4,14 +4,14 @@ #include /* for handle_mm_fault() */ #include -extern void my_direct_func(struct vm_area_struct *vma, - unsigned long address, unsigned int flags); +extern void my_direct_func(struct vm_area_struct *vma, unsigned long address, + unsigned int flags, struct pt_regs *regs); -void my_direct_func(struct vm_area_struct *vma, - unsigned long address, unsigned int flags) +void my_direct_func(struct vm_area_struct *vma, unsigned long address, + unsigned int flags, struct pt_regs *regs) { - trace_printk("handle mm fault vma=%p address=%lx flags=%x\n", - vma, address, flags); + trace_printk("handle mm fault vma=%p address=%lx flags=%x regs=%p\n", + vma, address, flags, regs); } extern void my_tramp(void *); @@ -26,7 +26,9 @@ asm ( " pushq %rdi\n" " pushq %rsi\n" " pushq %rdx\n" +" pushq %rcx\n" " call my_direct_func\n" +" popq %rcx\n" " popq %rdx\n" " popq %rsi\n" " popq %rdi\n" From 1e760b2d18bf129b3da052c2946c02758e97d15e Mon Sep 17 00:00:00 2001 From: Krister Johansen Date: Mon, 10 Jul 2023 18:36:21 -0700 Subject: [PATCH 4156/4345] net: ena: fix shift-out-of-bounds in exponential backoff commit 1e9cb763e9bacf0c932aa948f50dcfca6f519a26 upstream. The ENA adapters on our instances occasionally reset. Once recently logged a UBSAN failure to console in the process: UBSAN: shift-out-of-bounds in build/linux/drivers/net/ethernet/amazon/ena/ena_com.c:540:13 shift exponent 32 is too large for 32-bit type 'unsigned int' CPU: 28 PID: 70012 Comm: kworker/u72:2 Kdump: loaded not tainted 5.15.117 Hardware name: Amazon EC2 c5d.9xlarge/, BIOS 1.0 10/16/2017 Workqueue: ena ena_fw_reset_device [ena] Call Trace: dump_stack_lvl+0x4a/0x63 dump_stack+0x10/0x16 ubsan_epilogue+0x9/0x36 __ubsan_handle_shift_out_of_bounds.cold+0x61/0x10e ? __const_udelay+0x43/0x50 ena_delay_exponential_backoff_us.cold+0x16/0x1e [ena] wait_for_reset_state+0x54/0xa0 [ena] ena_com_dev_reset+0xc8/0x110 [ena] ena_down+0x3fe/0x480 [ena] ena_destroy_device+0xeb/0xf0 [ena] ena_fw_reset_device+0x30/0x50 [ena] process_one_work+0x22b/0x3d0 worker_thread+0x4d/0x3f0 ? process_one_work+0x3d0/0x3d0 kthread+0x12a/0x150 ? set_kthread_struct+0x50/0x50 ret_from_fork+0x22/0x30 Apparently, the reset delays are getting so large they can trigger a UBSAN panic. Looking at the code, the current timeout is capped at 5000us. Using a base value of 100us, the current code will overflow after (1<<29). Even at values before 32, this function wraps around, perhaps unintentionally. Cap the value of the exponent used for this backoff at (1<<16) which is larger than currently necessary, but large enough to support bigger values in the future. Cc: stable@vger.kernel.org Fixes: 4bb7f4cf60e3 ("net: ena: reduce driver load time") Signed-off-by: Krister Johansen Reviewed-by: Leon Romanovsky Reviewed-by: Shay Agroskin Link: https://lore.kernel.org/r/20230711013621.GE1926@templeofstupid.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/amazon/ena/ena_com.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 5f8769aa469d..d59ea5148c16 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -35,6 +35,8 @@ #define ENA_REGS_ADMIN_INTR_MASK 1 +#define ENA_MAX_BACKOFF_DELAY_EXP 16U + #define ENA_MIN_ADMIN_POLL_US 100 #define ENA_MAX_ADMIN_POLL_US 5000 @@ -522,6 +524,7 @@ static int ena_com_comp_status_to_errno(u8 comp_status) static void ena_delay_exponential_backoff_us(u32 exp, u32 delay_us) { + exp = min_t(u32, exp, ENA_MAX_BACKOFF_DELAY_EXP); delay_us = max_t(u32, ENA_MIN_ADMIN_POLL_US, delay_us); delay_us = min_t(u32, delay_us * (1U << exp), ENA_MAX_ADMIN_POLL_US); usleep_range(delay_us, 2 * delay_us); From 5e68f1f3a20fe9b6bde018e353269fbfa289609c Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Sun, 9 Jul 2023 06:51:44 +0800 Subject: [PATCH 4157/4345] ring-buffer: Fix deadloop issue on reading trace_pipe commit 7e42907f3a7b4ce3a2d1757f6d78336984daf8f5 upstream. Soft lockup occurs when reading file 'trace_pipe': watchdog: BUG: soft lockup - CPU#6 stuck for 22s! [cat:4488] [...] RIP: 0010:ring_buffer_empty_cpu+0xed/0x170 RSP: 0018:ffff88810dd6fc48 EFLAGS: 00000246 RAX: 0000000000000000 RBX: 0000000000000246 RCX: ffffffff93d1aaeb RDX: ffff88810a280040 RSI: 0000000000000008 RDI: ffff88811164b218 RBP: ffff88811164b218 R08: 0000000000000000 R09: ffff88815156600f R10: ffffed102a2acc01 R11: 0000000000000001 R12: 0000000051651901 R13: 0000000000000000 R14: ffff888115e49500 R15: 0000000000000000 [...] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f8d853c2000 CR3: 000000010dcd8000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __find_next_entry+0x1a8/0x4b0 ? peek_next_entry+0x250/0x250 ? down_write+0xa5/0x120 ? down_write_killable+0x130/0x130 trace_find_next_entry_inc+0x3b/0x1d0 tracing_read_pipe+0x423/0xae0 ? tracing_splice_read_pipe+0xcb0/0xcb0 vfs_read+0x16b/0x490 ksys_read+0x105/0x210 ? __ia32_sys_pwrite64+0x200/0x200 ? switch_fpu_return+0x108/0x220 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x61/0xc6 Through the vmcore, I found it's because in tracing_read_pipe(), ring_buffer_empty_cpu() found some buffer is not empty but then it cannot read anything due to "rb_num_of_entries() == 0" always true, Then it infinitely loop the procedure due to user buffer not been filled, see following code path: tracing_read_pipe() { ... ... waitagain: tracing_wait_pipe() // 1. find non-empty buffer here trace_find_next_entry_inc() // 2. loop here try to find an entry __find_next_entry() ring_buffer_empty_cpu(); // 3. find non-empty buffer peek_next_entry() // 4. but peek always return NULL ring_buffer_peek() rb_buffer_peek() rb_get_reader_page() // 5. because rb_num_of_entries() == 0 always true here // then return NULL // 6. user buffer not been filled so goto 'waitgain' // and eventually leads to an deadloop in kernel!!! } By some analyzing, I found that when resetting ringbuffer, the 'entries' of its pages are not all cleared (see rb_reset_cpu()). Then when reducing the ringbuffer, and if some reduced pages exist dirty 'entries' data, they will be added into 'cpu_buffer->overrun' (see rb_remove_pages()), which cause wrong 'overrun' count and eventually cause the deadloop issue. To fix it, we need to clear every pages in rb_reset_cpu(). Link: https://lore.kernel.org/linux-trace-kernel/20230708225144.3785600-1-zhengyejian1@huawei.com Cc: stable@vger.kernel.org Fixes: a5fb833172eca ("ring-buffer: Fix uninitialized read_stamp") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ring_buffer.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f08904914166..593e446f6c48 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4954,28 +4954,34 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_size); +static void rb_clear_buffer_page(struct buffer_page *page) +{ + local_set(&page->write, 0); + local_set(&page->entries, 0); + rb_init_page(page->page); + page->read = 0; +} + static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) { + struct buffer_page *page; + rb_head_page_deactivate(cpu_buffer); cpu_buffer->head_page = list_entry(cpu_buffer->pages, struct buffer_page, list); - local_set(&cpu_buffer->head_page->write, 0); - local_set(&cpu_buffer->head_page->entries, 0); - local_set(&cpu_buffer->head_page->page->commit, 0); - - cpu_buffer->head_page->read = 0; + rb_clear_buffer_page(cpu_buffer->head_page); + list_for_each_entry(page, cpu_buffer->pages, list) { + rb_clear_buffer_page(page); + } cpu_buffer->tail_page = cpu_buffer->head_page; cpu_buffer->commit_page = cpu_buffer->head_page; INIT_LIST_HEAD(&cpu_buffer->reader_page->list); INIT_LIST_HEAD(&cpu_buffer->new_pages); - local_set(&cpu_buffer->reader_page->write, 0); - local_set(&cpu_buffer->reader_page->entries, 0); - local_set(&cpu_buffer->reader_page->page->commit, 0); - cpu_buffer->reader_page->read = 0; + rb_clear_buffer_page(cpu_buffer->reader_page); local_set(&cpu_buffer->entries_bytes, 0); local_set(&cpu_buffer->overrun, 0); From 81fb8a58d4ec10c489ee87b315bca5fbcbf155bc Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Mon, 3 Jul 2023 11:01:42 -0700 Subject: [PATCH 4158/4345] xtensa: ISS: fix call to split_if_spec commit bc8d5916541fa19ca5bc598eb51a5f78eb891a36 upstream. split_if_spec expects a NULL-pointer as an end marker for the argument list, but tuntap_probe never supplied that terminating NULL. As a result incorrectly formatted interface specification string may cause a crash because of the random memory access. Fix that by adding NULL terminator to the split_if_spec argument list. Cc: stable@vger.kernel.org Fixes: 7282bee78798 ("[PATCH] xtensa: Architecture support for Tensilica Xtensa Part 8") Signed-off-by: Max Filippov Signed-off-by: Greg Kroah-Hartman --- arch/xtensa/platforms/iss/network.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 08d70c868c13..1270de83435e 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -231,7 +231,7 @@ static int tuntap_probe(struct iss_net_private *lp, int index, char *init) init += sizeof(TRANSPORT_TUNTAP_NAME) - 1; if (*init == ',') { - rem = split_if_spec(init + 1, &mac_str, &dev_name); + rem = split_if_spec(init + 1, &mac_str, &dev_name, NULL); if (rem != NULL) { pr_err("%s: extra garbage on specification : '%s'\n", dev->name, rem); From 7060e5aac6dc195124c106f49106d653a416323a Mon Sep 17 00:00:00 2001 From: Mateusz Stachyra Date: Tue, 4 Jul 2023 12:27:06 +0200 Subject: [PATCH 4159/4345] tracing: Fix null pointer dereference in tracing_err_log_open() commit 02b0095e2fbbc060560c1065f86a211d91e27b26 upstream. Fix an issue in function 'tracing_err_log_open'. The function doesn't call 'seq_open' if the file is opened only with write permissions, which results in 'file->private_data' being left as null. If we then use 'lseek' on that opened file, 'seq_lseek' dereferences 'file->private_data' in 'mutex_lock(&m->lock)', resulting in a kernel panic. Writing to this node requires root privileges, therefore this bug has very little security impact. Tracefs node: /sys/kernel/tracing/error_log Example Kernel panic: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000038 Call trace: mutex_lock+0x30/0x110 seq_lseek+0x34/0xb8 __arm64_sys_lseek+0x6c/0xb8 invoke_syscall+0x58/0x13c el0_svc_common+0xc4/0x10c do_el0_svc+0x24/0x98 el0_svc+0x24/0x88 el0t_64_sync_handler+0x84/0xe4 el0t_64_sync+0x1b4/0x1b8 Code: d503201f aa0803e0 aa1f03e1 aa0103e9 (c8e97d02) ---[ end trace 561d1b49c12cf8a5 ]--- Kernel panic - not syncing: Oops: Fatal exception Link: https://lore.kernel.org/linux-trace-kernel/20230703155237eucms1p4dfb6a19caa14c79eb6c823d127b39024@eucms1p4 Link: https://lore.kernel.org/linux-trace-kernel/20230704102706eucms1p30d7ecdcc287f46ad67679fc8491b2e0f@eucms1p3 Cc: stable@vger.kernel.org Fixes: 8a062902be725 ("tracing: Add tracing error log") Signed-off-by: Mateusz Stachyra Suggested-by: Steven Rostedt Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 70526400e05c..4dd8c16f023b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7529,7 +7529,7 @@ static const struct file_operations tracing_err_log_fops = { .open = tracing_err_log_open, .write = tracing_err_log_write, .read = seq_read, - .llseek = seq_lseek, + .llseek = tracing_lseek, .release = tracing_err_log_release, }; From 6ea2a408d3e3cb8a97700d72f1733d95d465e50a Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 11 Jul 2023 23:15:38 +0900 Subject: [PATCH 4160/4345] tracing/probes: Fix not to count error code to total length commit b41326b5e0f82e93592c4366359917b5d67b529f upstream. Fix not to count the error code (which is minus value) to the total used length of array, because it can mess up the return code of process_fetch_insn_bottom(). Also clear the 'ret' value because it will be used for calculating next data_loc entry. Link: https://lore.kernel.org/all/168908493827.123124.2175257289106364229.stgit@devnote2/ Reported-by: Dan Carpenter Closes: https://lore.kernel.org/all/8819b154-2ba1-43c3-98a2-cbde20892023@moroto.mountain/ Fixes: 9b960a38835f ("tracing: probeevent: Unify fetch_insn processing common part") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_probe_tmpl.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index e5282828f4a6..29348874ebde 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -143,6 +143,8 @@ stage3: array: /* the last stage: Loop on array */ if (code->op == FETCH_OP_LP_ARRAY) { + if (ret < 0) + ret = 0; total += ret; if (++i < code->param) { code = s3; From a9fe97fb7b4ee21bffb76f2acb05769bad27ae70 Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Fri, 28 Apr 2023 00:53:38 -0700 Subject: [PATCH 4161/4345] scsi: qla2xxx: Wait for io return on terminate rport commit fc0cba0c7be8261a1625098bd1d695077ec621c9 upstream. System crash due to use after free. Current code allows terminate_rport_io to exit before making sure all IOs has returned. For FCP-2 device, IO's can hang on in HW because driver has not tear down the session in FW at first sign of cable pull. When dev_loss_tmo timer pops, terminate_rport_io is called and upper layer is about to free various resources. Terminate_rport_io trigger qla to do the final cleanup, but the cleanup might not be fast enough where it leave qla still holding on to the same resource. Wait for IO's to return to upper layer before resources are freed. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230428075339.32551-7-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_attr.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 61b9dc511d90..12e27ee8c5c7 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2698,6 +2698,7 @@ static void qla2x00_terminate_rport_io(struct fc_rport *rport) { fc_port_t *fcport = *(fc_port_t **)rport->dd_data; + scsi_qla_host_t *vha; if (!fcport) return; @@ -2707,9 +2708,12 @@ qla2x00_terminate_rport_io(struct fc_rport *rport) if (test_bit(ABORT_ISP_ACTIVE, &fcport->vha->dpc_flags)) return; + vha = fcport->vha; if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) { qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16); + qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, + 0, WAIT_TARGET); return; } /* @@ -2724,6 +2728,15 @@ qla2x00_terminate_rport_io(struct fc_rport *rport) else qla2x00_port_logout(fcport->vha, fcport); } + + /* check for any straggling io left behind */ + if (qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, 0, WAIT_TARGET)) { + ql_log(ql_log_warn, vha, 0x300b, + "IO not return. Resetting. \n"); + set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags); + qla2xxx_wake_dpc(vha); + qla2x00_wait_for_chip_reset(vha); + } } static int From bcd773969a87d9802053c0db5be84abd6594a024 Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Wed, 7 Jun 2023 17:08:36 +0530 Subject: [PATCH 4162/4345] scsi: qla2xxx: Array index may go out of bound commit d721b591b95cf3f290f8a7cbe90aa2ee0368388d upstream. Klocwork reports array 'vha->host_str' of size 16 may use index value(s) 16..19. Use snprintf() instead of sprintf(). Cc: stable@vger.kernel.org Co-developed-by: Bikash Hazarika Signed-off-by: Bikash Hazarika Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230607113843.37185-2-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_os.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 38b8ff87ec0a..cbc5af26303a 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4877,7 +4877,8 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, } INIT_DELAYED_WORK(&vha->scan.scan_work, qla_scan_work_fn); - sprintf(vha->host_str, "%s_%lu", QLA2XXX_DRIVER_NAME, vha->host_no); + snprintf(vha->host_str, sizeof(vha->host_str), "%s_%lu", + QLA2XXX_DRIVER_NAME, vha->host_no); ql_dbg(ql_dbg_init, vha, 0x0041, "Allocated the host=%p hw=%p vha=%p dev_name=%s", vha->host, vha->hw, vha, From eecb8a491c824a9376155d26ec95b6d0054c059c Mon Sep 17 00:00:00 2001 From: Quinn Tran Date: Wed, 7 Jun 2023 17:08:40 +0530 Subject: [PATCH 4163/4345] scsi: qla2xxx: Fix buffer overrun commit b68710a8094fdffe8dd4f7a82c82649f479bb453 upstream. Klocwork warning: Buffer Overflow - Array Index Out of Bounds Driver uses fc_els_flogi to calculate size of buffer. The actual buffer is nested inside of fc_els_flogi which is smaller. Replace structure name to allow proper size calculation. Cc: stable@vger.kernel.org Signed-off-by: Quinn Tran Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230607113843.37185-6-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 422ff67038d1..3d1a53ba86ac 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -5107,7 +5107,7 @@ static void qla_get_login_template(scsi_qla_host_t *vha) __be32 *q; memset(ha->init_cb, 0, ha->init_cb_size); - sz = min_t(int, sizeof(struct fc_els_flogi), ha->init_cb_size); + sz = min_t(int, sizeof(struct fc_els_csp), ha->init_cb_size); rval = qla24xx_get_port_login_templ(vha, ha->init_cb_dma, ha->init_cb, sz); if (rval != QLA_SUCCESS) { From 2bea9c1c983152c5411f5a2f1113cb790ce1389d Mon Sep 17 00:00:00 2001 From: Bikash Hazarika Date: Wed, 7 Jun 2023 17:08:37 +0530 Subject: [PATCH 4164/4345] scsi: qla2xxx: Fix potential NULL pointer dereference commit 464ea494a40c6e3e0e8f91dd325408aaf21515ba upstream. Klocwork tool reported 'cur_dsd' may be dereferenced. Add fix to validate pointer before dereferencing the pointer. Cc: stable@vger.kernel.org Signed-off-by: Bikash Hazarika Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230607113843.37185-3-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_iocb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index f0af76c3de7e..54fc0afbc02a 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -601,7 +601,8 @@ qla24xx_build_scsi_type_6_iocbs(srb_t *sp, struct cmd_type_6 *cmd_pkt, put_unaligned_le32(COMMAND_TYPE_6, &cmd_pkt->entry_type); /* No data transfer */ - if (!scsi_bufflen(cmd) || cmd->sc_data_direction == DMA_NONE) { + if (!scsi_bufflen(cmd) || cmd->sc_data_direction == DMA_NONE || + tot_dsds == 0) { cmd_pkt->byte_count = cpu_to_le32(0); return 0; } From 921d6844625527a92d1178262a633cc88a8e61bd Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Wed, 7 Jun 2023 17:08:39 +0530 Subject: [PATCH 4165/4345] scsi: qla2xxx: Check valid rport returned by fc_bsg_to_rport() commit af73f23a27206ffb3c477cac75b5fcf03410556e upstream. Klocwork reported warning of rport maybe NULL and will be dereferenced. rport returned by call to fc_bsg_to_rport() could be NULL and dereferenced. Check valid rport returned by fc_bsg_to_rport(). Cc: stable@vger.kernel.org Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230607113843.37185-5-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_bsg.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index 1fd292a6ac88..d5e96523ba12 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -268,6 +268,10 @@ qla2x00_process_els(struct bsg_job *bsg_job) if (bsg_request->msgcode == FC_BSG_RPT_ELS) { rport = fc_bsg_to_rport(bsg_job); + if (!rport) { + rval = -ENOMEM; + goto done; + } fcport = *(fc_port_t **) rport->dd_data; host = rport_to_shost(rport); vha = shost_priv(host); From e8de73238d5d5db64b94474023adc26223088a3f Mon Sep 17 00:00:00 2001 From: Bikash Hazarika Date: Wed, 7 Jun 2023 17:08:42 +0530 Subject: [PATCH 4166/4345] scsi: qla2xxx: Correct the index of array commit b1b9d3825df4c757d653d0b1df66f084835db9c3 upstream. Klocwork reported array 'port_dstate_str' of size 10 may use index value(s) 10..15. Add a fix to correct the index of array. Cc: stable@vger.kernel.org Signed-off-by: Bikash Hazarika Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230607113843.37185-8-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_inline.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index e80e41b6c9e1..7e8b59a0954b 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -109,11 +109,13 @@ qla2x00_set_fcport_disc_state(fc_port_t *fcport, int state) { int old_val; uint8_t shiftbits, mask; + uint8_t port_dstate_str_sz; /* This will have to change when the max no. of states > 16 */ shiftbits = 4; mask = (1 << shiftbits) - 1; + port_dstate_str_sz = sizeof(port_dstate_str) / sizeof(char *); fcport->disc_state = state; while (1) { old_val = atomic_read(&fcport->shadow_disc_state); @@ -121,7 +123,8 @@ qla2x00_set_fcport_disc_state(fc_port_t *fcport, int state) old_val, (old_val << shiftbits) | state)) { ql_dbg(ql_dbg_disc, fcport->vha, 0x2134, "FCPort %8phC disc_state transition: %s to %s - portid=%06x.\n", - fcport->port_name, port_dstate_str[old_val & mask], + fcport->port_name, (old_val & mask) < port_dstate_str_sz ? + port_dstate_str[old_val & mask] : "Unknown", port_dstate_str[state], fcport->d_id.b24); return; } From 5addd62586a94a572359418464ce0ae12fa46187 Mon Sep 17 00:00:00 2001 From: Shreyas Deodhar Date: Wed, 7 Jun 2023 17:08:41 +0530 Subject: [PATCH 4167/4345] scsi: qla2xxx: Pointer may be dereferenced commit 00eca15319d9ce8c31cdf22f32a3467775423df4 upstream. Klocwork tool reported pointer 'rport' returned from call to function fc_bsg_to_rport() may be NULL and will be dereferenced. Add a fix to validate rport before dereferencing. Cc: stable@vger.kernel.org Signed-off-by: Shreyas Deodhar Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230607113843.37185-7-njavali@marvell.com Reviewed-by: Himanshu Madhani Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_bsg.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index d5e96523ba12..804cac4c3476 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -2545,6 +2545,8 @@ qla24xx_bsg_request(struct bsg_job *bsg_job) if (bsg_request->msgcode == FC_BSG_RPT_ELS) { rport = fc_bsg_to_rport(bsg_job); + if (!rport) + return ret; host = rport_to_shost(rport); vha = shost_priv(host); } else { From 0b1ce92fabdb7d02ddf8641230a06e2752ae5baa Mon Sep 17 00:00:00 2001 From: Manish Rangankar Date: Thu, 15 Jun 2023 13:16:33 +0530 Subject: [PATCH 4168/4345] scsi: qla2xxx: Remove unused nvme_ls_waitq wait queue commit 20fce500b232b970e40312a9c97e7f3b6d7a709c upstream. System crash when qla2x00_start_sp(sp) returns error code EGAIN and wake_up gets called for uninitialized wait queue sp->nvme_ls_waitq. qla2xxx [0000:37:00.1]-2121:5: Returning existing qpair of ffff8ae2c0513400 for idx=0 qla2xxx [0000:37:00.1]-700e:5: qla2x00_start_sp failed = 11 BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI Hardware name: HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 09/03/2021 Workqueue: nvme-wq nvme_fc_connect_ctrl_work [nvme_fc] RIP: 0010:__wake_up_common+0x4c/0x190 RSP: 0018:ffff95f3e0cb7cd0 EFLAGS: 00010086 RAX: 0000000000000000 RBX: ffff8b08d3b26328 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000003 RDI: ffff8b08d3b26320 RBP: 0000000000000001 R08: 0000000000000000 R09: ffffffffffffffe8 R10: 0000000000000000 R11: ffff95f3e0cb7a60 R12: ffff95f3e0cb7d20 R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8b2fdf6c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000002f1e410002 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: __wake_up_common_lock+0x7c/0xc0 qla_nvme_ls_req+0x355/0x4c0 [qla2xxx] ? __nvme_fc_send_ls_req+0x260/0x380 [nvme_fc] ? nvme_fc_send_ls_req.constprop.42+0x1a/0x45 [nvme_fc] ? nvme_fc_connect_ctrl_work.cold.63+0x1e3/0xa7d [nvme_fc] Remove unused nvme_ls_waitq wait queue. nvme_ls_waitq logic was removed previously in the commits tagged Fixed: below. Fixes: 219d27d7147e ("scsi: qla2xxx: Fix race conditions in the code for aborting SCSI commands") Fixes: 5621b0dd7453 ("scsi: qla2xxx: Simpify unregistration of FC-NVMe local/remote ports") Cc: stable@vger.kernel.org Signed-off-by: Manish Rangankar Signed-off-by: Nilesh Javali Link: https://lore.kernel.org/r/20230615074633.12721-1-njavali@marvell.com Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/qla2xxx/qla_def.h | 1 - drivers/scsi/qla2xxx/qla_nvme.c | 3 --- 2 files changed, 4 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 6afce455b9d8..06b0ad2b51bb 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -639,7 +639,6 @@ typedef struct srb { struct iocb_resource iores; struct kref cmd_kref; /* need to migrate ref_count over to this */ void *priv; - wait_queue_head_t nvme_ls_waitq; struct fc_port *fcport; struct scsi_qla_host *vha; unsigned int start_timer:1; diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 695dd89be330..8b0c8f9bdef0 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -331,7 +331,6 @@ static int qla_nvme_ls_req(struct nvme_fc_local_port *lport, if (rval != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x700e, "qla2x00_start_sp failed = %d\n", rval); - wake_up(&sp->nvme_ls_waitq); sp->priv = NULL; priv->sp = NULL; qla2x00_rel_sp(sp); @@ -590,7 +589,6 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, if (!sp) return -EBUSY; - init_waitqueue_head(&sp->nvme_ls_waitq); kref_init(&sp->cmd_kref); spin_lock_init(&priv->cmd_lock); sp->priv = priv; @@ -608,7 +606,6 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, if (rval != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x212d, "qla2x00_start_nvme_mq failed = %d\n", rval); - wake_up(&sp->nvme_ls_waitq); sp->priv = NULL; priv->sp = NULL; qla2xxx_rel_qpair_sp(sp->qpair, sp); From 73e72a5380a27ec5cd15a03d02ff881b0777a605 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Tue, 11 Jul 2023 18:01:00 -0300 Subject: [PATCH 4169/4345] net/sched: sch_qfq: reintroduce lmax bound check for MTU commit 158810b261d02fc7dd92ca9c392d8f8a211a2401 upstream. 25369891fcef deletes a check for the case where no 'lmax' is specified which 3037933448f6 previously fixed as 'lmax' could be set to the device's MTU without any bound checking for QFQ_LMAX_MIN and QFQ_LMAX_MAX. Therefore, reintroduce the check. Fixes: 25369891fcef ("net/sched: sch_qfq: refactor parsing of netlink parameters") Acked-by: Jamal Hadi Salim Reviewed-by: Eric Dumazet Signed-off-by: Pedro Tammela Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman --- net/sched/sch_qfq.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 616d1798cfef..d5a1e4b237b1 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -428,10 +428,17 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, else weight = 1; - if (tb[TCA_QFQ_LMAX]) + if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - else + } else { + /* MTU size is user controlled */ lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > QFQ_MAX_LMAX) { + NL_SET_ERR_MSG_MOD(extack, + "MTU size out of bounds for qfq"); + return -EINVAL; + } + } inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; From 9a085fa9b7d644a234465091e038c1911e1a4f2a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 16 Sep 2021 15:34:46 -0300 Subject: [PATCH 4170/4345] RDMA/cma: Ensure rdma_addr_cancel() happens before issuing more requests commit 305d568b72f17f674155a2a8275f865f207b3808 upstream. The FSM can run in a circle allowing rdma_resolve_ip() to be called twice on the same id_priv. While this cannot happen without going through the work, it violates the invariant that the same address resolution background request cannot be active twice. CPU 1 CPU 2 rdma_resolve_addr(): RDMA_CM_IDLE -> RDMA_CM_ADDR_QUERY rdma_resolve_ip(addr_handler) #1 process_one_req(): for #1 addr_handler(): RDMA_CM_ADDR_QUERY -> RDMA_CM_ADDR_BOUND mutex_unlock(&id_priv->handler_mutex); [.. handler still running ..] rdma_resolve_addr(): RDMA_CM_ADDR_BOUND -> RDMA_CM_ADDR_QUERY rdma_resolve_ip(addr_handler) !! two requests are now on the req_list rdma_destroy_id(): destroy_id_handler_unlock(): _destroy_id(): cma_cancel_operation(): rdma_addr_cancel() // process_one_req() self removes it spin_lock_bh(&lock); cancel_delayed_work(&req->work); if (!list_empty(&req->list)) == true ! rdma_addr_cancel() returns after process_on_req #1 is done kfree(id_priv) process_one_req(): for #2 addr_handler(): mutex_lock(&id_priv->handler_mutex); !! Use after free on id_priv rdma_addr_cancel() expects there to be one req on the list and only cancels the first one. The self-removal behavior of the work only happens after the handler has returned. This yields a situations where the req_list can have two reqs for the same "handle" but rdma_addr_cancel() only cancels the first one. The second req remains active beyond rdma_destroy_id() and will use-after-free id_priv once it inevitably triggers. Fix this by remembering if the id_priv has called rdma_resolve_ip() and always cancel before calling it again. This ensures the req_list never gets more than one item in it and doesn't cost anything in the normal flow that never uses this strange error path. Link: https://lore.kernel.org/r/0-v1-3bc675b8006d+22-syz_cancel_uaf_jgg@nvidia.com Cc: stable@vger.kernel.org Fixes: e51060f08a61 ("IB: IP address based RDMA connection manager") Reported-by: syzbot+dc3dfba010d7671e05f5@syzkaller.appspotmail.com Signed-off-by: Jason Gunthorpe Signed-off-by: Anton Gusev Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/core/cma.c | 23 +++++++++++++++++++++++ drivers/infiniband/core/cma_priv.h | 1 + 2 files changed, 24 insertions(+) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index db24f7dfa00f..805678f6fe57 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1792,6 +1792,14 @@ static void cma_cancel_operation(struct rdma_id_private *id_priv, { switch (state) { case RDMA_CM_ADDR_QUERY: + /* + * We can avoid doing the rdma_addr_cancel() based on state, + * only RDMA_CM_ADDR_QUERY has a work that could still execute. + * Notice that the addr_handler work could still be exiting + * outside this state, however due to the interaction with the + * handler_mutex the work is guaranteed not to touch id_priv + * during exit. + */ rdma_addr_cancel(&id_priv->id.route.addr.dev_addr); break; case RDMA_CM_ROUTE_QUERY: @@ -3401,6 +3409,21 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, if (dst_addr->sa_family == AF_IB) { ret = cma_resolve_ib_addr(id_priv); } else { + /* + * The FSM can return back to RDMA_CM_ADDR_BOUND after + * rdma_resolve_ip() is called, eg through the error + * path in addr_handler(). If this happens the existing + * request must be canceled before issuing a new one. + * Since canceling a request is a bit slow and this + * oddball path is rare, keep track once a request has + * been issued. The track turns out to be a permanent + * state since this is the only cancel as it is + * immediately before rdma_resolve_ip(). + */ + if (id_priv->used_resolve_ip) + rdma_addr_cancel(&id->route.addr.dev_addr); + else + id_priv->used_resolve_ip = 1; ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, &id->route.addr.dev_addr, timeout_ms, addr_handler, diff --git a/drivers/infiniband/core/cma_priv.h b/drivers/infiniband/core/cma_priv.h index caece96ebcf5..b53f4fa5e3fb 100644 --- a/drivers/infiniband/core/cma_priv.h +++ b/drivers/infiniband/core/cma_priv.h @@ -89,6 +89,7 @@ struct rdma_id_private { u8 reuseaddr; u8 afonly; u8 timeout; + u8 used_resolve_ip; enum ib_gid_type gid_type; /* From f09c0ac142c59495262dd80545f261b2aeeba538 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 21 Jul 2023 15:58:38 +0200 Subject: [PATCH 4171/4345] drm/atomic: Fix potential use-after-free in nonblocking commits commit 4e076c73e4f6e90816b30fcd4a0d7ab365087255 upstream. This requires a bit of background. Properly done a modeset driver's unload/remove sequence should be drm_dev_unplug(); drm_atomic_helper_shutdown(); drm_dev_put(); The trouble is that the drm_dev_unplugged() checks are by design racy, they do not synchronize against all outstanding ioctl. This is because those ioctl could block forever (both for modeset and for driver specific ioctls), leading to deadlocks in hotunplug. Instead the code sections that touch the hardware need to be annotated with drm_dev_enter/exit, to avoid accessing hardware resources after the unload/remove has finished. To avoid use-after-free issues all the involved userspace visible objects are supposed to hold a reference on the underlying drm_device, like drm_file does. The issue now is that we missed one, the atomic modeset ioctl can be run in a nonblocking fashion, and in that case it cannot rely on the implied drm_device reference provided by the ioctl calling context. This can result in a use-after-free if an nonblocking atomic commit is carefully raced against a driver unload. Fix this by unconditionally grabbing a drm_device reference for any drm_atomic_state structures. Strictly speaking this isn't required for blocking commits and TEST_ONLY calls, but it's the simpler approach. Thanks to shanzhulig for the initial idea of grabbing an unconditional reference, I just added comments, a condensed commit message and fixed a minor potential issue in where exactly we drop the final reference. Reported-by: shanzhulig Suggested-by: shanzhulig Reviewed-by: Maxime Ripard Cc: Maarten Lankhorst Cc: Thomas Zimmermann Cc: David Airlie Cc: stable@kernel.org Signed-off-by: Daniel Vetter Signed-off-by: Daniel Vetter Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_atomic.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 98b659981f1a..b10ba5057735 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -98,6 +98,12 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state) if (!state->planes) goto fail; + /* + * Because drm_atomic_state can be committed asynchronously we need our + * own reference and cannot rely on the on implied by drm_file in the + * ioctl call. + */ + drm_dev_get(dev); state->dev = dev; DRM_DEBUG_ATOMIC("Allocated atomic state %p\n", state); @@ -257,7 +263,8 @@ EXPORT_SYMBOL(drm_atomic_state_clear); void __drm_atomic_state_free(struct kref *ref) { struct drm_atomic_state *state = container_of(ref, typeof(*state), ref); - struct drm_mode_config *config = &state->dev->mode_config; + struct drm_device *dev = state->dev; + struct drm_mode_config *config = &dev->mode_config; drm_atomic_state_clear(state); @@ -269,6 +276,8 @@ void __drm_atomic_state_free(struct kref *ref) drm_atomic_state_default_release(state); kfree(state); } + + drm_dev_put(dev); } EXPORT_SYMBOL(__drm_atomic_state_free); From ce2a7e7b504c9adaac52b51186acb3b9b18022a8 Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Thu, 13 Jul 2023 15:57:13 +0800 Subject: [PATCH 4172/4345] ALSA: hda/realtek - remove 3k pull low procedure commit 69ea4c9d02b7947cdd612335a61cc1a02e544ccd upstream. This was the ALC283 depop procedure. Maybe this procedure wasn't suitable with new codec. So, let us remove it. But HP 15z-fc000 must do 3k pull low. If it reboot with plugged headset, it will have errors show don't find codec error messages. Run 3k pull low will solve issues. So, let AMD chipset will run this for workarround. Fixes: 5aec98913095 ("ALSA: hda/realtek - ALC236 headset MIC recording issue") Signed-off-by: Kailang Yang Cc: Reported-by: Joseph C. Sible Closes: https://lore.kernel.org/r/CABpewhE4REgn9RJZduuEU6Z_ijXNeQWnrxO1tg70Gkw=F8qNYg@mail.gmail.com/ Link: https://lore.kernel.org/r/4678992299664babac4403d9978e7ba7@realtek.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7d6a36b647a7..244278fb8067 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -121,6 +121,7 @@ struct alc_spec { unsigned int ultra_low_power:1; unsigned int has_hs_key:1; unsigned int no_internal_mic_pin:1; + unsigned int en_3kpull_low:1; /* for PLL fix */ hda_nid_t pll_nid; @@ -3617,6 +3618,7 @@ static void alc256_shutup(struct hda_codec *codec) if (!hp_pin) hp_pin = 0x21; + alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */ hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); if (hp_pin_sense) @@ -3633,8 +3635,7 @@ static void alc256_shutup(struct hda_codec *codec) /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly * when booting with headset plugged. So skip setting it for the codec alc257 */ - if (codec->core.vendor_id != 0x10ec0236 && - codec->core.vendor_id != 0x10ec0257) + if (spec->en_3kpull_low) alc_update_coef_idx(codec, 0x46, 0, 3 << 12); if (!spec->no_shutup_pins) @@ -10065,6 +10066,8 @@ static int patch_alc269(struct hda_codec *codec) spec->shutup = alc256_shutup; spec->init_hook = alc256_init; spec->gen.mixer_nid = 0; /* ALC256 does not have any loopback mixer path */ + if (codec->bus->pci->vendor == PCI_VENDOR_ID_AMD) + spec->en_3kpull_low = true; break; case 0x10ec0257: spec->codec_variant = ALC269_TYPE_ALC257; From a26208e184ae30cd1a0f256f92e53d53834a2eb5 Mon Sep 17 00:00:00 2001 From: Luka Guzenko Date: Tue, 18 Jul 2023 18:12:41 +0200 Subject: [PATCH 4173/4345] ALSA: hda/realtek: Enable Mute LED on HP Laptop 15s-eq2xxx commit 0659400f18c0e6c0c69d74fe5d09e7f6fbbd52a2 upstream. The HP Laptop 15s-eq2xxx uses ALC236 codec and controls the mute LED using COEF 0x07 index 1. No existing quirk covers this configuration. Adds a new quirk and enables it for the device. Signed-off-by: Luka Guzenko Cc: Link: https://lore.kernel.org/r/20230718161241.393181-1-l.guzenko@web.de Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 244278fb8067..6bfc7e28515a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4559,6 +4559,21 @@ static void alc236_fixup_hp_mute_led_coefbit(struct hda_codec *codec, } } +static void alc236_fixup_hp_mute_led_coefbit2(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->mute_led_polarity = 0; + spec->mute_led_coef.idx = 0x07; + spec->mute_led_coef.mask = 1; + spec->mute_led_coef.on = 1; + spec->mute_led_coef.off = 0; + snd_hda_gen_add_mute_led_cdev(codec, coef_mute_led_set); + } +} + /* turn on/off mic-mute LED per capture hook by coef bit */ static int coef_micmute_led_set(struct led_classdev *led_cdev, enum led_brightness brightness) @@ -6878,6 +6893,7 @@ enum { ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED, + ALC236_FIXUP_HP_MUTE_LED_COEFBIT2, ALC236_FIXUP_HP_GPIO_LED, ALC236_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF, @@ -8250,6 +8266,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_spectre_x360_mute_led, }, + [ALC236_FIXUP_HP_MUTE_LED_COEFBIT2] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc236_fixup_hp_mute_led_coefbit2, + }, [ALC236_FIXUP_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, .v.func = alc236_fixup_hp_gpio_led, @@ -9004,6 +9024,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x886d, "HP ZBook Fury 17.3 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8870, "HP ZBook Fury 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8873, "HP ZBook Studio 15.6 Inch G8 Mobile Workstation PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x887a, "HP Laptop 15s-eq2xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x888d, "HP ZBook Power 15.6 inch G8 Mobile Workstation PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8895, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_SPEAKERS_MICMUTE_LED), SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED), From 0a6b0ca58685be34979236f83f2b322635b80b32 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Thu, 23 Mar 2023 14:04:12 +0100 Subject: [PATCH 4174/4345] keys: Fix linking a duplicate key to a keyring's assoc_array commit d55901522f96082a43b9842d34867363c0cdbac5 upstream. When making a DNS query inside the kernel using dns_query(), the request code can in rare cases end up creating a duplicate index key in the assoc_array of the destination keyring. It is eventually found by a BUG_ON() check in the assoc_array implementation and results in a crash. Example report: [2158499.700025] kernel BUG at ../lib/assoc_array.c:652! [2158499.700039] invalid opcode: 0000 [#1] SMP PTI [2158499.700065] CPU: 3 PID: 31985 Comm: kworker/3:1 Kdump: loaded Not tainted 5.3.18-150300.59.90-default #1 SLE15-SP3 [2158499.700096] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020 [2158499.700351] Workqueue: cifsiod cifs_resolve_server [cifs] [2158499.700380] RIP: 0010:assoc_array_insert+0x85f/0xa40 [2158499.700401] Code: ff 74 2b 48 8b 3b 49 8b 45 18 4c 89 e6 48 83 e7 fe e8 95 ec 74 00 3b 45 88 7d db 85 c0 79 d4 0f 0b 0f 0b 0f 0b e8 41 f2 be ff <0f> 0b 0f 0b 81 7d 88 ff ff ff 7f 4c 89 eb 4c 8b ad 58 ff ff ff 0f [2158499.700448] RSP: 0018:ffffc0bd6187faf0 EFLAGS: 00010282 [2158499.700470] RAX: ffff9f1ea7da2fe8 RBX: ffff9f1ea7da2fc1 RCX: 0000000000000005 [2158499.700492] RDX: 0000000000000000 RSI: 0000000000000005 RDI: 0000000000000000 [2158499.700515] RBP: ffffc0bd6187fbb0 R08: ffff9f185faf1100 R09: 0000000000000000 [2158499.700538] R10: ffff9f1ea7da2cc0 R11: 000000005ed8cec8 R12: ffffc0bd6187fc28 [2158499.700561] R13: ffff9f15feb8d000 R14: ffff9f1ea7da2fc0 R15: ffff9f168dc0d740 [2158499.700585] FS: 0000000000000000(0000) GS:ffff9f185fac0000(0000) knlGS:0000000000000000 [2158499.700610] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [2158499.700630] CR2: 00007fdd94fca238 CR3: 0000000809d8c006 CR4: 00000000003706e0 [2158499.700702] Call Trace: [2158499.700741] ? key_alloc+0x447/0x4b0 [2158499.700768] ? __key_link_begin+0x43/0xa0 [2158499.700790] __key_link_begin+0x43/0xa0 [2158499.700814] request_key_and_link+0x2c7/0x730 [2158499.700847] ? dns_resolver_read+0x20/0x20 [dns_resolver] [2158499.700873] ? key_default_cmp+0x20/0x20 [2158499.700898] request_key_tag+0x43/0xa0 [2158499.700926] dns_query+0x114/0x2ca [dns_resolver] [2158499.701127] dns_resolve_server_name_to_ip+0x194/0x310 [cifs] [2158499.701164] ? scnprintf+0x49/0x90 [2158499.701190] ? __switch_to_asm+0x40/0x70 [2158499.701211] ? __switch_to_asm+0x34/0x70 [2158499.701405] reconn_set_ipaddr_from_hostname+0x81/0x2a0 [cifs] [2158499.701603] cifs_resolve_server+0x4b/0xd0 [cifs] [2158499.701632] process_one_work+0x1f8/0x3e0 [2158499.701658] worker_thread+0x2d/0x3f0 [2158499.701682] ? process_one_work+0x3e0/0x3e0 [2158499.701703] kthread+0x10d/0x130 [2158499.701723] ? kthread_park+0xb0/0xb0 [2158499.701746] ret_from_fork+0x1f/0x40 The situation occurs as follows: * Some kernel facility invokes dns_query() to resolve a hostname, for example, "abcdef". The function registers its global DNS resolver cache as current->cred.thread_keyring and passes the query to request_key_net() -> request_key_tag() -> request_key_and_link(). * Function request_key_and_link() creates a keyring_search_context object. Its match_data.cmp method gets set via a call to type->match_preparse() (resolves to dns_resolver_match_preparse()) to dns_resolver_cmp(). * Function request_key_and_link() continues and invokes search_process_keyrings_rcu() which returns that a given key was not found. The control is then passed to request_key_and_link() -> construct_alloc_key(). * Concurrently to that, a second task similarly makes a DNS query for "abcdef." and its result gets inserted into the DNS resolver cache. * Back on the first task, function construct_alloc_key() first runs __key_link_begin() to determine an assoc_array_edit operation to insert a new key. Index keys in the array are compared exactly as-is, using keyring_compare_object(). The operation finds that "abcdef" is not yet present in the destination keyring. * Function construct_alloc_key() continues and checks if a given key is already present on some keyring by again calling search_process_keyrings_rcu(). This search is done using dns_resolver_cmp() and "abcdef" gets matched with now present key "abcdef.". * The found key is linked on the destination keyring by calling __key_link() and using the previously calculated assoc_array_edit operation. This inserts the "abcdef." key in the array but creates a duplicity because the same index key is already present. Fix the problem by postponing __key_link_begin() in construct_alloc_key() until an actual key which should be linked into the destination keyring is determined. [jarkko@kernel.org: added a fixes tag and cc to stable] Cc: stable@vger.kernel.org # v5.3+ Fixes: df593ee23e05 ("keys: Hoist locking out of __key_link_begin()") Signed-off-by: Petr Pavlu Reviewed-by: Joey Lee Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- security/keys/request_key.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 07a0ef2baacd..a7673ad86d18 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -401,17 +401,21 @@ static int construct_alloc_key(struct keyring_search_context *ctx, set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags); if (dest_keyring) { - ret = __key_link_lock(dest_keyring, &ctx->index_key); + ret = __key_link_lock(dest_keyring, &key->index_key); if (ret < 0) goto link_lock_failed; - ret = __key_link_begin(dest_keyring, &ctx->index_key, &edit); - if (ret < 0) - goto link_prealloc_failed; } - /* attach the key to the destination keyring under lock, but we do need + /* + * Attach the key to the destination keyring under lock, but we do need * to do another check just in case someone beat us to it whilst we - * waited for locks */ + * waited for locks. + * + * The caller might specify a comparison function which looks for keys + * that do not exactly match but are still equivalent from the caller's + * perspective. The __key_link_begin() operation must be done only after + * an actual key is determined. + */ mutex_lock(&key_construction_mutex); rcu_read_lock(); @@ -420,12 +424,16 @@ static int construct_alloc_key(struct keyring_search_context *ctx, if (!IS_ERR(key_ref)) goto key_already_present; - if (dest_keyring) + if (dest_keyring) { + ret = __key_link_begin(dest_keyring, &key->index_key, &edit); + if (ret < 0) + goto link_alloc_failed; __key_link(dest_keyring, key, &edit); + } mutex_unlock(&key_construction_mutex); if (dest_keyring) - __key_link_end(dest_keyring, &ctx->index_key, edit); + __key_link_end(dest_keyring, &key->index_key, edit); mutex_unlock(&user->cons_lock); *_key = key; kleave(" = 0 [%d]", key_serial(key)); @@ -438,10 +446,13 @@ key_already_present: mutex_unlock(&key_construction_mutex); key = key_ref_to_ptr(key_ref); if (dest_keyring) { + ret = __key_link_begin(dest_keyring, &key->index_key, &edit); + if (ret < 0) + goto link_alloc_failed_unlocked; ret = __key_link_check_live_key(dest_keyring, key); if (ret == 0) __key_link(dest_keyring, key, &edit); - __key_link_end(dest_keyring, &ctx->index_key, edit); + __key_link_end(dest_keyring, &key->index_key, edit); if (ret < 0) goto link_check_failed; } @@ -456,8 +467,10 @@ link_check_failed: kleave(" = %d [linkcheck]", ret); return ret; -link_prealloc_failed: - __key_link_end(dest_keyring, &ctx->index_key, edit); +link_alloc_failed: + mutex_unlock(&key_construction_mutex); +link_alloc_failed_unlocked: + __key_link_end(dest_keyring, &key->index_key, edit); link_lock_failed: mutex_unlock(&user->cons_lock); key_put(key); From 4410f4a938ae80ffe1c788351dd3756974745a66 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Georg=20M=C3=BCller?= Date: Wed, 28 Jun 2023 10:45:50 +0200 Subject: [PATCH 4175/4345] perf probe: Add test for regression introduced by switch to die_get_decl_file() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 56cbeacf143530576905623ac72ae0964f3293a6 upstream. This patch adds a test to validate that 'perf probe' works for binaries where DWARF info is split into multiple CUs Signed-off-by: Georg Müller Acked-by: Masami Hiramatsu (Google) Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: regressions@lists.linux.dev Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230628084551.1860532-5-georgmueller@gmx.net Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- .../shell/test_uprobe_from_different_cu.sh | 77 +++++++++++++++++++ 1 file changed, 77 insertions(+) create mode 100644 tools/perf/tests/shell/test_uprobe_from_different_cu.sh diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh new file mode 100644 index 000000000000..00d2e0e2e0c2 --- /dev/null +++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh @@ -0,0 +1,77 @@ +#!/bin/bash +# test perf probe of function from different CU +# SPDX-License-Identifier: GPL-2.0 + +set -e + +temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX) + +cleanup() +{ + trap - EXIT TERM INT + if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then + echo "--- Cleaning up ---" + perf probe -x ${temp_dir}/testfile -d foo + rm -f "${temp_dir}/"* + rmdir "${temp_dir}" + fi +} + +trap_cleanup() +{ + cleanup + exit 1 +} + +trap trap_cleanup EXIT TERM INT + +cat > ${temp_dir}/testfile-foo.h << EOF +struct t +{ + int *p; + int c; +}; + +extern int foo (int i, struct t *t); +EOF + +cat > ${temp_dir}/testfile-foo.c << EOF +#include "testfile-foo.h" + +int +foo (int i, struct t *t) +{ + int j, res = 0; + for (j = 0; j < i && j < t->c; j++) + res += t->p[j]; + + return res; +} +EOF + +cat > ${temp_dir}/testfile-main.c << EOF +#include "testfile-foo.h" + +static struct t g; + +int +main (int argc, char **argv) +{ + int i; + int j[argc]; + g.c = argc; + g.p = j; + for (i = 0; i < argc; i++) + j[i] = (int) argv[i][0]; + return foo (3, &g); +} +EOF + +gcc -g -Og -flto -c ${temp_dir}/testfile-foo.c -o ${temp_dir}/testfile-foo.o +gcc -g -Og -c ${temp_dir}/testfile-main.c -o ${temp_dir}/testfile-main.o +gcc -g -Og -o ${temp_dir}/testfile ${temp_dir}/testfile-foo.o ${temp_dir}/testfile-main.o + +perf probe -x ${temp_dir}/testfile --funcs foo +perf probe -x ${temp_dir}/testfile foo + +cleanup From d2c667cc18314c9bad3ec86ae071c0342132aa09 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 14 Jul 2023 13:42:06 +0100 Subject: [PATCH 4176/4345] btrfs: fix warning when putting transaction with qgroups enabled after abort commit aa84ce8a78a1a5c10cdf9c7a5fb0c999fbc2c8d6 upstream. If we have a transaction abort with qgroups enabled we get a warning triggered when doing the final put on the transaction, like this: [552.6789] ------------[ cut here ]------------ [552.6815] WARNING: CPU: 4 PID: 81745 at fs/btrfs/transaction.c:144 btrfs_put_transaction+0x123/0x130 [btrfs] [552.6817] Modules linked in: btrfs blake2b_generic xor (...) [552.6819] CPU: 4 PID: 81745 Comm: btrfs-transacti Tainted: G W 6.4.0-rc6-btrfs-next-134+ #1 [552.6819] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 [552.6819] RIP: 0010:btrfs_put_transaction+0x123/0x130 [btrfs] [552.6821] Code: bd a0 01 00 (...) [552.6821] RSP: 0018:ffffa168c0527e28 EFLAGS: 00010286 [552.6821] RAX: ffff936042caed00 RBX: ffff93604a3eb448 RCX: 0000000000000000 [552.6821] RDX: ffff93606421b028 RSI: ffffffff92ff0878 RDI: ffff93606421b010 [552.6821] RBP: ffff93606421b000 R08: 0000000000000000 R09: ffffa168c0d07c20 [552.6821] R10: 0000000000000000 R11: ffff93608dc52950 R12: ffffa168c0527e70 [552.6821] R13: ffff93606421b000 R14: ffff93604a3eb420 R15: ffff93606421b028 [552.6821] FS: 0000000000000000(0000) GS:ffff93675fb00000(0000) knlGS:0000000000000000 [552.6821] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [552.6821] CR2: 0000558ad262b000 CR3: 000000014feda005 CR4: 0000000000370ee0 [552.6822] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [552.6822] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [552.6822] Call Trace: [552.6822] [552.6822] ? __warn+0x80/0x130 [552.6822] ? btrfs_put_transaction+0x123/0x130 [btrfs] [552.6824] ? report_bug+0x1f4/0x200 [552.6824] ? handle_bug+0x42/0x70 [552.6824] ? exc_invalid_op+0x14/0x70 [552.6824] ? asm_exc_invalid_op+0x16/0x20 [552.6824] ? btrfs_put_transaction+0x123/0x130 [btrfs] [552.6826] btrfs_cleanup_transaction+0xe7/0x5e0 [btrfs] [552.6828] ? _raw_spin_unlock_irqrestore+0x23/0x40 [552.6828] ? try_to_wake_up+0x94/0x5e0 [552.6828] ? __pfx_process_timeout+0x10/0x10 [552.6828] transaction_kthread+0x103/0x1d0 [btrfs] [552.6830] ? __pfx_transaction_kthread+0x10/0x10 [btrfs] [552.6832] kthread+0xee/0x120 [552.6832] ? __pfx_kthread+0x10/0x10 [552.6832] ret_from_fork+0x29/0x50 [552.6832] [552.6832] ---[ end trace 0000000000000000 ]--- This corresponds to this line of code: void btrfs_put_transaction(struct btrfs_transaction *transaction) { (...) WARN_ON(!RB_EMPTY_ROOT( &transaction->delayed_refs.dirty_extent_root)); (...) } The warning happens because btrfs_qgroup_destroy_extent_records(), called in the transaction abort path, we free all entries from the rbtree "dirty_extent_root" with rbtree_postorder_for_each_entry_safe(), but we don't actually empty the rbtree - it's still pointing to nodes that were freed. So set the rbtree's root node to NULL to avoid this warning (assign RB_ROOT). Fixes: 81f7eb00ff5b ("btrfs: destroy qgroup extent records on transaction abort") CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Josef Bacik Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/qgroup.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 94edc74c8979..828a7ff4aebe 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -4376,4 +4376,5 @@ void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans) ulist_free(entry->old_roots); kfree(entry); } + *root = RB_ROOT; } From dad97c205af2ac0af419b98c2d6fa267f7ced8dd Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 7 Jun 2023 17:49:20 +0200 Subject: [PATCH 4177/4345] fuse: revalidate: don't invalidate if interrupted commit a9d1c4c6df0e568207907c04aed9e7beb1294c42 upstream. If the LOOKUP request triggered from fuse_dentry_revalidate() is interrupted, then the dentry will be invalidated, possibly resulting in submounts being unmounted. Reported-by: Xu Rongbo Closes: https://lore.kernel.org/all/CAJfpegswN_CJJ6C3RZiaK6rpFmNyWmXfaEpnQUJ42KCwNF5tWw@mail.gmail.com/ Fixes: 9e6268db496a ("[PATCH] FUSE - read-write operations") Cc: Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/fuse/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index e3b9b7d188e6..b0c701c007c6 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -249,7 +249,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) spin_unlock(&fi->lock); } kfree(forget); - if (ret == -ENOMEM) + if (ret == -ENOMEM || ret == -EINTR) goto out; if (ret || fuse_invalid_attr(&outarg.attr) || fuse_stale_inode(inode, outarg.generation, &outarg.attr)) From 1ab5aa1846a5542be9a5af1455408930d22b347e Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Thu, 13 Jul 2023 23:16:44 +0200 Subject: [PATCH 4178/4345] selftests: tc: set timeout to 15 minutes commit fda05798c22a354efde09a76bdfc276b2d591829 upstream. When looking for something else in LKFT reports [1], I noticed that the TC selftest ended with a timeout error: not ok 1 selftests: tc-testing: tdc.sh # TIMEOUT 45 seconds The timeout had been introduced 3 years ago, see the Fixes commit below. This timeout is only in place when executing the selftests via the kselftests runner scripts. I guess this is not what most TC devs are using and nobody noticed the issue before. The new timeout is set to 15 minutes as suggested by Pedro [2]. It looks like it is plenty more time than what it takes in "normal" conditions. Fixes: 852c8cbf34d3 ("selftests/kselftest/runner.sh: Add 45 second timeout per test") Cc: stable@vger.kernel.org Link: https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20230711/testrun/18267241/suite/kselftest-tc-testing/test/tc-testing_tdc_sh/log [1] Link: https://lore.kernel.org/netdev/0e061d4a-9a23-9f58-3b35-d8919de332d7@tessares.net/T/ [2] Suggested-by: Pedro Tammela Signed-off-by: Matthieu Baerts Reviewed-by: Zhengchao Shao Link: https://lore.kernel.org/r/20230713-tc-selftests-lkft-v1-1-1eb4fd3a96e7@tessares.net Acked-by: Jamal Hadi Salim Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/tc-testing/settings | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/tc-testing/settings diff --git a/tools/testing/selftests/tc-testing/settings b/tools/testing/selftests/tc-testing/settings new file mode 100644 index 000000000000..e2206265f67c --- /dev/null +++ b/tools/testing/selftests/tc-testing/settings @@ -0,0 +1 @@ +timeout=900 From 4935761daa339656ac2417835d54c85a99fda386 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Thu, 13 Jul 2023 23:16:45 +0200 Subject: [PATCH 4179/4345] selftests: tc: add 'ct' action kconfig dep commit 719b4774a8cb1a501e2d22a5a4a3a0a870e427d5 upstream. When looking for something else in LKFT reports [1], I noticed most of the tests were skipped because the "teardown stage" did not complete successfully. Pedro found out this is due to the fact CONFIG_NF_FLOW_TABLE is required but not listed in the 'config' file. Adding it to the list fixes the issues on LKFT side. CONFIG_NET_ACT_CT is now set to 'm' in the final kconfig. Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Cc: stable@vger.kernel.org Link: https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20230711/testrun/18267241/suite/kselftest-tc-testing/test/tc-testing_tdc_sh/log [1] Link: https://lore.kernel.org/netdev/0e061d4a-9a23-9f58-3b35-d8919de332d7@tessares.net/T/ [2] Suggested-by: Pedro Tammela Signed-off-by: Matthieu Baerts Tested-by: Zhengchao Shao Link: https://lore.kernel.org/r/20230713-tc-selftests-lkft-v1-2-1eb4fd3a96e7@tessares.net Acked-by: Jamal Hadi Salim Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/tc-testing/config | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index b71828df5a6d..5f581c3a1131 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -5,6 +5,7 @@ CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_LABELS=y +CONFIG_NF_FLOW_TABLE=m CONFIG_NF_NAT=m CONFIG_NET_SCHED=y From 8b3dd8d23fa0cf790699244dad126591254793f2 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 12 Jul 2023 12:16:39 +0100 Subject: [PATCH 4180/4345] regmap: Drop initial version of maximum transfer length fixes commit bc64734825c59e18a27ac266b07e14944c111fd8 upstream. When problems were noticed with the register address not being taken into account when limiting raw transfers with I2C devices we fixed this in the core. Unfortunately it has subsequently been realised that a lot of buses were relying on the prior behaviour, partly due to unclear documentation not making it obvious what was intended in the core. This is all more involved to fix than is sensible for a fix commit so let's just drop the original fixes, a separate commit will fix the originally observed problem in an I2C specific way Fixes: 3981514180c9 ("regmap: Account for register length when chunking") Fixes: c8e796895e23 ("regmap: spi-avmm: Fix regmap_bus max_raw_write") Signed-off-by: Mark Brown Reviewed-by: Xu Yilun Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230712-regmap-max-transfer-v1-1-80e2aed22e83@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/base/regmap/regmap-spi-avmm.c | 2 +- drivers/base/regmap/regmap.c | 6 ++---- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/base/regmap/regmap-spi-avmm.c b/drivers/base/regmap/regmap-spi-avmm.c index 67f89937219c..ad1da83e849f 100644 --- a/drivers/base/regmap/regmap-spi-avmm.c +++ b/drivers/base/regmap/regmap-spi-avmm.c @@ -666,7 +666,7 @@ static const struct regmap_bus regmap_spi_avmm_bus = { .reg_format_endian_default = REGMAP_ENDIAN_NATIVE, .val_format_endian_default = REGMAP_ENDIAN_NATIVE, .max_raw_read = SPI_AVMM_VAL_SIZE * MAX_READ_CNT, - .max_raw_write = SPI_AVMM_REG_SIZE + SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, + .max_raw_write = SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, .free_context = spi_avmm_bridge_ctx_free, }; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 2a3c3dfefdce..55a30afc14a0 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1998,8 +1998,6 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, size_t val_count = val_len / val_bytes; size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; - size_t max_data = map->max_raw_write - map->format.reg_bytes - - map->format.pad_bytes; int ret, i; if (!val_count) @@ -2007,8 +2005,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, if (map->use_single_write) chunk_regs = 1; - else if (map->max_raw_write && val_len > max_data) - chunk_regs = max_data / val_bytes; + else if (map->max_raw_write && val_len > map->max_raw_write) + chunk_regs = map->max_raw_write / val_bytes; chunk_count = val_count / chunk_regs; chunk_bytes = chunk_regs * val_bytes; From 3e412b6e2b57658905b1c89ddec05504f4342232 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 12 Jul 2023 12:16:40 +0100 Subject: [PATCH 4181/4345] regmap: Account for register length in SMBus I/O limits commit 0c9d2eb5e94792fe64019008a04d4df5e57625af upstream. The SMBus I2C buses have limits on the size of transfers they can do but do not factor in the register length meaning we may try to do a transfer longer than our length limit, the core will not take care of this. Future changes will factor this out into the core but there are a number of users that assume current behaviour so let's just do something conservative here. This does not take account padding bits but practically speaking these are very rarely if ever used on I2C buses given that they generally run slowly enough to mean there's no issue. Cc: stable@kernel.org Signed-off-by: Mark Brown Reviewed-by: Xu Yilun Link: https://lore.kernel.org/r/20230712-regmap-max-transfer-v1-2-80e2aed22e83@kernel.org Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/base/regmap/regmap-i2c.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c index 62b95a9212ae..051c10e730f9 100644 --- a/drivers/base/regmap/regmap-i2c.c +++ b/drivers/base/regmap/regmap-i2c.c @@ -242,8 +242,8 @@ static int regmap_i2c_smbus_i2c_read(void *context, const void *reg, static const struct regmap_bus regmap_i2c_smbus_i2c_block = { .write = regmap_i2c_smbus_i2c_write, .read = regmap_i2c_smbus_i2c_read, - .max_raw_read = I2C_SMBUS_BLOCK_MAX, - .max_raw_write = I2C_SMBUS_BLOCK_MAX, + .max_raw_read = I2C_SMBUS_BLOCK_MAX - 1, + .max_raw_write = I2C_SMBUS_BLOCK_MAX - 1, }; static int regmap_i2c_smbus_i2c_write_reg16(void *context, const void *data, @@ -299,8 +299,8 @@ static int regmap_i2c_smbus_i2c_read_reg16(void *context, const void *reg, static const struct regmap_bus regmap_i2c_smbus_i2c_block_reg16 = { .write = regmap_i2c_smbus_i2c_write_reg16, .read = regmap_i2c_smbus_i2c_read_reg16, - .max_raw_read = I2C_SMBUS_BLOCK_MAX, - .max_raw_write = I2C_SMBUS_BLOCK_MAX, + .max_raw_read = I2C_SMBUS_BLOCK_MAX - 2, + .max_raw_write = I2C_SMBUS_BLOCK_MAX - 2, }; static const struct regmap_bus *regmap_get_i2c_bus(struct i2c_client *i2c, From cf254b4f68e480e73dab055014e002b77aed30ed Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Sat, 15 Jul 2023 17:25:43 +0800 Subject: [PATCH 4182/4345] can: bcm: Fix UAF in bcm_proc_show() commit 55c3b96074f3f9b0aee19bf93cd71af7516582bb upstream. BUG: KASAN: slab-use-after-free in bcm_proc_show+0x969/0xa80 Read of size 8 at addr ffff888155846230 by task cat/7862 CPU: 1 PID: 7862 Comm: cat Not tainted 6.5.0-rc1-00153-gc8746099c197 #230 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Call Trace: dump_stack_lvl+0xd5/0x150 print_report+0xc1/0x5e0 kasan_report+0xba/0xf0 bcm_proc_show+0x969/0xa80 seq_read_iter+0x4f6/0x1260 seq_read+0x165/0x210 proc_reg_read+0x227/0x300 vfs_read+0x1d5/0x8d0 ksys_read+0x11e/0x240 do_syscall_64+0x35/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd Allocated by task 7846: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 __kasan_kmalloc+0x9e/0xa0 bcm_sendmsg+0x264b/0x44e0 sock_sendmsg+0xda/0x180 ____sys_sendmsg+0x735/0x920 ___sys_sendmsg+0x11d/0x1b0 __sys_sendmsg+0xfa/0x1d0 do_syscall_64+0x35/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 7846: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 kasan_save_free_info+0x27/0x40 ____kasan_slab_free+0x161/0x1c0 slab_free_freelist_hook+0x119/0x220 __kmem_cache_free+0xb4/0x2e0 rcu_core+0x809/0x1bd0 bcm_op is freed before procfs entry be removed in bcm_release(), this lead to bcm_proc_show() may read the freed bcm_op. Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol") Signed-off-by: YueHaibing Reviewed-by: Oliver Hartkopp Acked-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20230715092543.15548-1-yuehaibing@huawei.com Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde Signed-off-by: Greg Kroah-Hartman --- net/can/bcm.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/can/bcm.c b/net/can/bcm.c index ddba4e12da78..2388c619f29c 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1521,6 +1521,12 @@ static int bcm_release(struct socket *sock) lock_sock(sk); +#if IS_ENABLED(CONFIG_PROC_FS) + /* remove procfs entry */ + if (net->can.bcmproc_dir && bo->bcm_proc_read) + remove_proc_entry(bo->procname, net->can.bcmproc_dir); +#endif /* CONFIG_PROC_FS */ + list_for_each_entry_safe(op, next, &bo->tx_ops, list) bcm_remove_op(op); @@ -1556,12 +1562,6 @@ static int bcm_release(struct socket *sock) list_for_each_entry_safe(op, next, &bo->rx_ops, list) bcm_remove_op(op); -#if IS_ENABLED(CONFIG_PROC_FS) - /* remove procfs entry */ - if (net->can.bcmproc_dir && bo->bcm_proc_read) - remove_proc_entry(bo->procname, net->can.bcmproc_dir); -#endif /* CONFIG_PROC_FS */ - /* remove device reference */ if (bo->bound) { bo->bound = 0; From 105275879a80503686a8108af2f5c579a1c5aef4 Mon Sep 17 00:00:00 2001 From: Jocelyn Falempe Date: Tue, 11 Jul 2023 11:20:43 +0200 Subject: [PATCH 4183/4345] drm/client: Fix memory leak in drm_client_target_cloned commit c2a88e8bdf5f6239948d75283d0ae7e0c7945b03 upstream. dmt_mode is allocated and never freed in this function. It was found with the ast driver, but most drivers using generic fbdev setup are probably affected. This fixes the following kmemleak report: backtrace: [<00000000b391296d>] drm_mode_duplicate+0x45/0x220 [drm] [<00000000e45bb5b3>] drm_client_target_cloned.constprop.0+0x27b/0x480 [drm] [<00000000ed2d3a37>] drm_client_modeset_probe+0x6bd/0xf50 [drm] [<0000000010e5cc9d>] __drm_fb_helper_initial_config_and_unlock+0xb4/0x2c0 [drm_kms_helper] [<00000000909f82ca>] drm_fbdev_client_hotplug+0x2bc/0x4d0 [drm_kms_helper] [<00000000063a69aa>] drm_client_register+0x169/0x240 [drm] [<00000000a8c61525>] ast_pci_probe+0x142/0x190 [ast] [<00000000987f19bb>] local_pci_probe+0xdc/0x180 [<000000004fca231b>] work_for_cpu_fn+0x4e/0xa0 [<0000000000b85301>] process_one_work+0x8b7/0x1540 [<000000003375b17c>] worker_thread+0x70a/0xed0 [<00000000b0d43cd9>] kthread+0x29f/0x340 [<000000008d770833>] ret_from_fork+0x1f/0x30 unreferenced object 0xff11000333089a00 (size 128): cc: Fixes: 1d42bbc8f7f9 ("drm/fbdev: fix cloning on fbcon") Reported-by: Zhang Yi Signed-off-by: Jocelyn Falempe Reviewed-by: Javier Martinez Canillas Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230711092203.68157-2-jfalempe@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_client_modeset.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index b7e9e1c2564c..844a60ad96bf 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -308,6 +308,9 @@ static bool drm_client_target_cloned(struct drm_device *dev, can_clone = true; dmt_mode = drm_mode_find_dmt(dev, 1024, 768, 60, false); + if (!dmt_mode) + goto fail; + for (i = 0; i < connector_count; i++) { if (!enabled[i]) continue; @@ -323,11 +326,13 @@ static bool drm_client_target_cloned(struct drm_device *dev, if (!modes[i]) can_clone = false; } + kfree(dmt_mode); if (can_clone) { DRM_DEBUG_KMS("can clone using 1024x768\n"); return true; } +fail: DRM_INFO("kms: can't enable cloning when we probably wanted to.\n"); return false; } From 5f2a12f64347f535c6ef55fa7eb36a2874d69b59 Mon Sep 17 00:00:00 2001 From: Jocelyn Falempe Date: Tue, 11 Jul 2023 11:20:44 +0200 Subject: [PATCH 4184/4345] drm/client: Fix memory leak in drm_client_modeset_probe commit 2329cc7a101af1a844fbf706c0724c0baea38365 upstream. When a new mode is set to modeset->mode, the previous mode should be freed. This fixes the following kmemleak report: drm_mode_duplicate+0x45/0x220 [drm] drm_client_modeset_probe+0x944/0xf50 [drm] __drm_fb_helper_initial_config_and_unlock+0xb4/0x2c0 [drm_kms_helper] drm_fbdev_client_hotplug+0x2bc/0x4d0 [drm_kms_helper] drm_client_register+0x169/0x240 [drm] ast_pci_probe+0x142/0x190 [ast] local_pci_probe+0xdc/0x180 work_for_cpu_fn+0x4e/0xa0 process_one_work+0x8b7/0x1540 worker_thread+0x70a/0xed0 kthread+0x29f/0x340 ret_from_fork+0x1f/0x30 cc: Reported-by: Zhang Yi Signed-off-by: Jocelyn Falempe Reviewed-by: Javier Martinez Canillas Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230711092203.68157-3-jfalempe@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_client_modeset.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 844a60ad96bf..d5fd41823624 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -864,6 +864,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, break; } + kfree(modeset->mode); modeset->mode = drm_mode_duplicate(dev, mode); drm_connector_get(connector); modeset->connectors[modeset->num_connectors++] = connector; From 48aa5393758493fe1069ccca4bd4abac06fc3976 Mon Sep 17 00:00:00 2001 From: Matus Gajdos Date: Wed, 12 Jul 2023 14:49:33 +0200 Subject: [PATCH 4185/4345] ASoC: fsl_sai: Disable bit clock with transmitter commit 269f399dc19f0e5c51711c3ba3bd06e0ef6ef403 upstream. Otherwise bit clock remains running writing invalid data to the DAC. Signed-off-by: Matus Gajdos Acked-by: Shengjiu Wang Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230712124934.32232-1-matuszpd@gmail.com Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/fsl/fsl_sai.c | 2 +- sound/soc/fsl/fsl_sai.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 6a5d2b08e271..03731d14d475 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -552,7 +552,7 @@ static void fsl_sai_config_disable(struct fsl_sai *sai, int dir) u32 xcsr, count = 100; regmap_update_bits(sai->regmap, FSL_SAI_xCSR(tx, ofs), - FSL_SAI_CSR_TERE, 0); + FSL_SAI_CSR_TERE | FSL_SAI_CSR_BCE, 0); /* TERE will remain set till the end of current frame */ do { diff --git a/sound/soc/fsl/fsl_sai.h b/sound/soc/fsl/fsl_sai.h index 8923c680f0e0..691847d54b17 100644 --- a/sound/soc/fsl/fsl_sai.h +++ b/sound/soc/fsl/fsl_sai.h @@ -87,6 +87,7 @@ /* SAI Transmit/Receive Control Register */ #define FSL_SAI_CSR_TERE BIT(31) #define FSL_SAI_CSR_SE BIT(30) +#define FSL_SAI_CSR_BCE BIT(28) #define FSL_SAI_CSR_FR BIT(25) #define FSL_SAI_CSR_SR BIT(24) #define FSL_SAI_CSR_xF_SHIFT 16 From 5d5aa5b64887689d73ef7a4d5c17c2dfcfb26812 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Mon, 22 May 2023 14:15:20 -0400 Subject: [PATCH 4186/4345] ext4: correct inline offset when handling xattrs in inode body commit 6909cf5c4101214f4305a62d582a5b93c7e1eb9a upstream. When run on a file system where the inline_data feature has been enabled, xfstests generic/269, generic/270, and generic/476 cause ext4 to emit error messages indicating that inline directory entries are corrupted. This occurs because the inline offset used to locate inline directory entries in the inode body is not updated when an xattr in that shared region is deleted and the region is shifted in memory to recover the space it occupied. If the deleted xattr precedes the system.data attribute, which points to the inline directory entries, that attribute will be moved further up in the region. The inline offset continues to point to whatever is located in system.data's former location, with unfortunate effects when used to access directory entries or (presumably) inline data in the inode body. Cc: stable@kernel.org Signed-off-by: Eric Whitney Link: https://lore.kernel.org/r/20230522181520.1570360-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/xattr.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index ed39101dc7b6..5bf858fc271f 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1725,6 +1725,20 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, memmove(here, (void *)here + size, (void *)last - (void *)here + sizeof(__u32)); memset(last, 0, size); + + /* + * Update i_inline_off - moved ibody region might contain + * system.data attribute. Handling a failure here won't + * cause other complications for setting an xattr. + */ + if (!is_block && ext4_has_inline_data(inode)) { + ret = ext4_find_inline_data_nolock(inode); + if (ret) { + ext4_warning_inode(inode, + "unable to update i_inline_off"); + goto out; + } + } } else if (s->not_found) { /* Insert new name. */ size_t size = EXT4_XATTR_LEN(name_len); From 5f84a34b646f6e52fa8d39bd6f586264c0e68703 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Wed, 7 Jun 2023 19:19:02 +0900 Subject: [PATCH 4187/4345] debugobjects: Recheck debug_objects_enabled before reporting [ Upstream commit 8b64d420fe2450f82848178506d3e3a0bd195539 ] syzbot is reporting false a positive ODEBUG message immediately after ODEBUG was disabled due to OOM. [ 1062.309646][T22911] ODEBUG: Out of memory. ODEBUG disabled [ 1062.886755][ T5171] ------------[ cut here ]------------ [ 1062.892770][ T5171] ODEBUG: assert_init not available (active state 0) object: ffffc900056afb20 object type: timer_list hint: process_timeout+0x0/0x40 CPU 0 [ T5171] CPU 1 [T22911] -------------- -------------- debug_object_assert_init() { if (!debug_objects_enabled) return; db = get_bucket(addr); lookup_object_or_alloc() { debug_objects_enabled = 0; return NULL; } debug_objects_oom() { pr_warn("Out of memory. ODEBUG disabled\n"); // all buckets get emptied here, and } lookup_object_or_alloc(addr, db, descr, false, true) { // this bucket is already empty. return ERR_PTR(-ENOENT); } // Emits false positive warning. debug_print_object(&o, "assert_init"); } Recheck debug_object_enabled in debug_print_object() to avoid that. Reported-by: syzbot Suggested-by: Thomas Gleixner Signed-off-by: Tetsuo Handa Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/492fe2ae-5141-d548-ebd5-62f5fe2e57f7@I-love.SAKURA.ne.jp Closes: https://syzkaller.appspot.com/bug?extid=7937ba6a50bdd00fffdf Signed-off-by: Sasha Levin --- lib/debugobjects.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 4c39678c03ee..4dd9283f6fea 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -501,6 +501,15 @@ static void debug_print_object(struct debug_obj *obj, char *msg) const struct debug_obj_descr *descr = obj->descr; static int limit; + /* + * Don't report if lookup_object_or_alloc() by the current thread + * failed because lookup_object_or_alloc()/debug_objects_oom() by a + * concurrent thread turned off debug_objects_enabled and cleared + * the hash buckets. + */ + if (!debug_objects_enabled) + return; + if (limit < 5 && descr != descr_test) { void *hint = descr->debug_hint ? descr->debug_hint(obj->object) : NULL; From 4a2c62c8d67cdbf42f217744ffa0fd9d077a589f Mon Sep 17 00:00:00 2001 From: Zhong Jinghua Date: Mon, 5 Jun 2023 20:21:59 +0800 Subject: [PATCH 4188/4345] nbd: Add the maximum limit of allocated index in nbd_dev_add [ Upstream commit f12bc113ce904777fd6ca003b473b427782b3dde ] If the index allocated by idr_alloc greater than MINORMASK >> part_shift, the device number will overflow, resulting in failure to create a block device. Fix it by imiting the size of the max allocation. Signed-off-by: Zhong Jinghua Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230605122159.2134384-1-zhongjinghua@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- drivers/block/nbd.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index b6940f0a9c90..e0f805ca0e72 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1723,7 +1723,8 @@ static int nbd_dev_add(int index) if (err == -ENOSPC) err = -EEXIST; } else { - err = idr_alloc(&nbd_index_idr, nbd, 0, 0, GFP_KERNEL); + err = idr_alloc(&nbd_index_idr, nbd, 0, + (MINORMASK >> part_shift) + 1, GFP_KERNEL); if (err >= 0) index = err; } From b02939413e5c9bbea58e220c1e9733930edb6d1a Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 12 May 2023 09:56:07 +0800 Subject: [PATCH 4189/4345] md: fix data corruption for raid456 when reshape restart while grow up [ Upstream commit 873f50ece41aad5c4f788a340960c53774b5526e ] Currently, if reshape is interrupted, echo "reshape" to sync_action will restart reshape from scratch, for example: echo frozen > sync_action echo reshape > sync_action This will corrupt data before reshape_position if the array is growing, fix the problem by continue reshape from reshape_position. Reported-by: Peter Neuwirth Link: https://lore.kernel.org/linux-raid/e2f96772-bfbc-f43b-6da1-f520e5164536@online.de/ Signed-off-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230512015610.821290-3-yukuai1@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/md.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index bbf39abc32b7..ae0a857d6076 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4890,11 +4890,21 @@ action_store(struct mddev *mddev, const char *page, size_t len) return -EINVAL; err = mddev_lock(mddev); if (!err) { - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { err = -EBUSY; - else { + } else if (mddev->reshape_position == MaxSector || + mddev->pers->check_reshape == NULL || + mddev->pers->check_reshape(mddev)) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); err = mddev->pers->start_reshape(mddev); + } else { + /* + * If reshape is still in progress, and + * md_check_recovery() can continue to reshape, + * don't restart reshape because data can be + * corrupted for raid456. + */ + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } mddev_unlock(mddev); } From 634daf6b2c81015cc5e28bf694a6a94a50c641cd Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 29 May 2023 21:11:00 +0800 Subject: [PATCH 4190/4345] md/raid10: prevent soft lockup while flush writes [ Upstream commit 010444623e7f4da6b4a4dd603a7da7469981e293 ] Currently, there is no limit for raid1/raid10 plugged bio. While flushing writes, raid1 has cond_resched() while raid10 doesn't, and too many writes can cause soft lockup. Follow up soft lockup can be triggered easily with writeback test for raid10 with ramdisks: watchdog: BUG: soft lockup - CPU#10 stuck for 27s! [md0_raid10:1293] Call Trace: call_rcu+0x16/0x20 put_object+0x41/0x80 __delete_object+0x50/0x90 delete_object_full+0x2b/0x40 kmemleak_free+0x46/0xa0 slab_free_freelist_hook.constprop.0+0xed/0x1a0 kmem_cache_free+0xfd/0x300 mempool_free_slab+0x1f/0x30 mempool_free+0x3a/0x100 bio_free+0x59/0x80 bio_put+0xcf/0x2c0 free_r10bio+0xbf/0xf0 raid_end_bio_io+0x78/0xb0 one_write_done+0x8a/0xa0 raid10_end_write_request+0x1b4/0x430 bio_endio+0x175/0x320 brd_submit_bio+0x3b9/0x9b7 [brd] __submit_bio+0x69/0xe0 submit_bio_noacct_nocheck+0x1e6/0x5a0 submit_bio_noacct+0x38c/0x7e0 flush_pending_writes+0xf0/0x240 raid10d+0xac/0x1ed0 Fix the problem by adding cond_resched() to raid10 like what raid1 did. Note that unlimited plugged bio still need to be optimized, for example, in the case of lots of dirty pages writeback, this will take lots of memory and io will spend a long time in plug, hence io latency is bad. Signed-off-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230529131106.2123367-2-yukuai1@huaweicloud.com Signed-off-by: Sasha Levin --- drivers/md/raid10.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 32a917e5103a..55144f7d9303 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -902,6 +902,7 @@ static void flush_pending_writes(struct r10conf *conf) else submit_bio_noacct(bio); bio = next; + cond_resched(); } blk_finish_plug(&plug); } else @@ -1095,6 +1096,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) else submit_bio_noacct(bio); bio = next; + cond_resched(); } kfree(plug); } From 322377cc909defcca9451487484845e7e1d20d1b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 1 Jun 2023 20:58:47 +0200 Subject: [PATCH 4191/4345] posix-timers: Ensure timer ID search-loop limit is valid [ Upstream commit 8ce8849dd1e78dadcee0ec9acbd259d239b7069f ] posix_timer_add() tries to allocate a posix timer ID by starting from the cached ID which was stored by the last successful allocation. This is done in a loop searching the ID space for a free slot one by one. The loop has to terminate when the search wrapped around to the starting point. But that's racy vs. establishing the starting point. That is read out lockless, which leads to the following problem: CPU0 CPU1 posix_timer_add() start = sig->posix_timer_id; lock(hash_lock); ... posix_timer_add() if (++sig->posix_timer_id < 0) start = sig->posix_timer_id; sig->posix_timer_id = 0; So CPU1 can observe a negative start value, i.e. -1, and the loop break never happens because the condition can never be true: if (sig->posix_timer_id == start) break; While this is unlikely to ever turn into an endless loop as the ID space is huge (INT_MAX), the racy read of the start value caught the attention of KCSAN and Dmitry unearthed that incorrectness. Rewrite it so that all id operations are under the hash lock. Reported-by: syzbot+5c54bd3eb218bb595aa9@syzkaller.appspotmail.com Reported-by: Dmitry Vyukov Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/r/87bkhzdn6g.ffs@tglx Signed-off-by: Sasha Levin --- include/linux/sched/signal.h | 2 +- kernel/time/posix-timers.c | 31 ++++++++++++++++++------------- 2 files changed, 19 insertions(+), 14 deletions(-) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index ae60f838ebb9..2c634010cc7b 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -125,7 +125,7 @@ struct signal_struct { #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ - int posix_timer_id; + unsigned int next_posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 6d12a724d2b6..29569b1c3d8c 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -140,25 +140,30 @@ static struct k_itimer *posix_timer_by_id(timer_t id) static int posix_timer_add(struct k_itimer *timer) { struct signal_struct *sig = current->signal; - int first_free_id = sig->posix_timer_id; struct hlist_head *head; - int ret = -ENOENT; + unsigned int cnt, id; - do { + /* + * FIXME: Replace this by a per signal struct xarray once there is + * a plan to handle the resulting CRIU regression gracefully. + */ + for (cnt = 0; cnt <= INT_MAX; cnt++) { spin_lock(&hash_lock); - head = &posix_timers_hashtable[hash(sig, sig->posix_timer_id)]; - if (!__posix_timers_find(head, sig, sig->posix_timer_id)) { + id = sig->next_posix_timer_id; + + /* Write the next ID back. Clamp it to the positive space */ + sig->next_posix_timer_id = (id + 1) & INT_MAX; + + head = &posix_timers_hashtable[hash(sig, id)]; + if (!__posix_timers_find(head, sig, id)) { hlist_add_head_rcu(&timer->t_hash, head); - ret = sig->posix_timer_id; + spin_unlock(&hash_lock); + return id; } - if (++sig->posix_timer_id < 0) - sig->posix_timer_id = 0; - if ((sig->posix_timer_id == first_free_id) && (ret == -ENOENT)) - /* Loop over all possible ids completed */ - ret = -EAGAIN; spin_unlock(&hash_lock); - } while (ret == -ENOENT); - return ret; + } + /* POSIX return code when no timer ID could be allocated */ + return -EAGAIN; } static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) From ae51eb90bcca2f8a9e4b76fe35cc76df0d915621 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 4 Apr 2023 00:06:02 +0200 Subject: [PATCH 4192/4345] btrfs: add xxhash to fast checksum implementations [ Upstream commit efcfcbc6a36195c42d98e0ee697baba36da94dc8 ] The implementation of XXHASH is now CPU only but still fast enough to be considered for the synchronous checksumming, like non-generic crc32c. A userspace benchmark comparing it to various implementations (patched hash-speedtest from btrfs-progs): Block size: 4096 Iterations: 1000000 Implementation: builtin Units: CPU cycles NULL-NOP: cycles: 73384294, cycles/i 73 NULL-MEMCPY: cycles: 228033868, cycles/i 228, 61664.320 MiB/s CRC32C-ref: cycles: 24758559416, cycles/i 24758, 567.950 MiB/s CRC32C-NI: cycles: 1194350470, cycles/i 1194, 11773.433 MiB/s CRC32C-ADLERSW: cycles: 6150186216, cycles/i 6150, 2286.372 MiB/s CRC32C-ADLERHW: cycles: 626979180, cycles/i 626, 22427.453 MiB/s CRC32C-PCL: cycles: 466746732, cycles/i 466, 30126.699 MiB/s XXHASH: cycles: 860656400, cycles/i 860, 16338.188 MiB/s Comparing purely software implementation (ref), current outdated accelerated using crc32q instruction (NI), optimized implementations by M. Adler (https://stackoverflow.com/questions/17645167/implementing-sse-4-2s-crc32c-in-software/17646775#17646775) and the best one that was taken from kernel using the PCLMULQDQ instruction (PCL). Reviewed-by: Christoph Hellwig Signed-off-by: David Sterba Signed-off-by: Sasha Levin --- fs/btrfs/disk-io.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5a114cad988a..608b939a4d28 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2256,6 +2256,9 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) if (!strstr(crypto_shash_driver_name(csum_shash), "generic")) set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); break; + case BTRFS_CSUM_TYPE_XXHASH: + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; default: break; } From e090f70ae4cc1805c8442e719e40e7e0fbb964f1 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 29 Apr 2023 12:38:41 +0200 Subject: [PATCH 4193/4345] ACPI: button: Add lid disable DMI quirk for Nextbook Ares 8A [ Upstream commit 4fd5556608bfa9c2bf276fc115ef04288331aded ] The LID0 device on the Nextbook Ares 8A tablet always reports lid closed causing userspace to suspend the device as soon as booting is complete. Add a DMI quirk to disable the broken lid functionality. Signed-off-by: Hans de Goede Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/button.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 0d93a5ef4d07..4861aad1a9e9 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -82,6 +82,15 @@ static const struct dmi_system_id dmi_lid_quirks[] = { }, .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED, }, + { + /* Nextbook Ares 8A tablet, _LID device always reports lid closed */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "CherryTrail"), + DMI_MATCH(DMI_BIOS_VERSION, "M882"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED, + }, { /* * Medion Akoya E2215T, notification of the LID device only From 776a72f612a82ea0ea7fc5727226e3f57ea82545 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 17 May 2023 11:23:58 +0200 Subject: [PATCH 4194/4345] ACPI: video: Add backlight=native DMI quirk for Apple iMac11,3 [ Upstream commit 48436f2e9834b46b47b038b605c8142a1c07bc85 ] Linux defaults to picking the non-working ACPI video backlight interface on the Apple iMac11,3 . Add a DMI quirk to pick the working native radeon_bl0 interface instead. Signed-off-by: Hans de Goede Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/video_detect.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 038542b3a80a..872b5351f0d8 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -332,6 +332,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82BK"), }, }, + { + .callback = video_detect_force_native, + /* Apple iMac11,3 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac11,3"), + }, + }, { /* https://bugzilla.redhat.com/show_bug.cgi?id=1217249 */ .callback = video_detect_force_native, From 71e3f2354072c98921f9a3f89f3aad171c3575c6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 17 May 2023 11:23:59 +0200 Subject: [PATCH 4195/4345] ACPI: video: Add backlight=native DMI quirk for Lenovo ThinkPad X131e (3371 AMD version) [ Upstream commit bd5d93df86a7ddf98a2a37e9c3751e3cb334a66c ] Linux defaults to picking the non-working ACPI video backlight interface on the Lenovo ThinkPad X131e (3371 AMD version). Add a DMI quirk to pick the working native radeon_bl0 interface instead. Signed-off-by: Hans de Goede Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- drivers/acpi/video_detect.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 872b5351f0d8..b02d381e7848 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -332,6 +332,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82BK"), }, }, + { + .callback = video_detect_force_native, + /* Lenovo ThinkPad X131e (3371 AMD version) */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "3371"), + }, + }, { .callback = video_detect_force_native, /* Apple iMac11,3 */ From c71d6934c6ac40a97146a410e0320768c7b1bb3c Mon Sep 17 00:00:00 2001 From: Youngmin Nam Date: Mon, 24 Apr 2023 10:04:36 +0900 Subject: [PATCH 4196/4345] arm64: set __exception_irq_entry with __irq_entry as a default [ Upstream commit f6794950f0e5ba37e3bbedda4d6ab0aad7395dd3 ] filter_irq_stacks() is supposed to cut entries which are related irq entries from its call stack. And in_irqentry_text() which is called by filter_irq_stacks() uses __irqentry_text_start/end symbol to find irq entries in callstack. But it doesn't work correctly as without "CONFIG_FUNCTION_GRAPH_TRACER", arm64 kernel doesn't include gic_handle_irq which is entry point of arm64 irq between __irqentry_text_start and __irqentry_text_end as we discussed in below link. https://lore.kernel.org/all/CACT4Y+aReMGLYua2rCLHgFpS9io5cZC04Q8GLs-uNmrn1ezxYQ@mail.gmail.com/#t This problem can makes unintentional deep call stack entries especially in KASAN enabled situation as below. [ 2479.383395]I[0:launcher-loader: 1719] Stack depot reached limit capacity [ 2479.383538]I[0:launcher-loader: 1719] WARNING: CPU: 0 PID: 1719 at lib/stackdepot.c:129 __stack_depot_save+0x464/0x46c [ 2479.385693]I[0:launcher-loader: 1719] pstate: 624000c5 (nZCv daIF +PAN -UAO +TCO -DIT -SSBS BTYPE=--) [ 2479.385724]I[0:launcher-loader: 1719] pc : __stack_depot_save+0x464/0x46c [ 2479.385751]I[0:launcher-loader: 1719] lr : __stack_depot_save+0x460/0x46c [ 2479.385774]I[0:launcher-loader: 1719] sp : ffffffc0080073c0 [ 2479.385793]I[0:launcher-loader: 1719] x29: ffffffc0080073e0 x28: ffffffd00b78a000 x27: 0000000000000000 [ 2479.385839]I[0:launcher-loader: 1719] x26: 000000000004d1dd x25: ffffff891474f000 x24: 00000000ca64d1dd [ 2479.385882]I[0:launcher-loader: 1719] x23: 0000000000000200 x22: 0000000000000220 x21: 0000000000000040 [ 2479.385925]I[0:launcher-loader: 1719] x20: ffffffc008007440 x19: 0000000000000000 x18: 0000000000000000 [ 2479.385969]I[0:launcher-loader: 1719] x17: 2065726568207475 x16: 000000000000005e x15: 2d2d2d2d2d2d2d20 [ 2479.386013]I[0:launcher-loader: 1719] x14: 5d39313731203a72 x13: 00000000002f6b30 x12: 00000000002f6af8 [ 2479.386057]I[0:launcher-loader: 1719] x11: 00000000ffffffff x10: ffffffb90aacf000 x9 : e8a74a6c16008800 [ 2479.386101]I[0:launcher-loader: 1719] x8 : e8a74a6c16008800 x7 : 00000000002f6b30 x6 : 00000000002f6af8 [ 2479.386145]I[0:launcher-loader: 1719] x5 : ffffffc0080070c8 x4 : ffffffd00b192380 x3 : ffffffd0092b313c [ 2479.386189]I[0:launcher-loader: 1719] x2 : 0000000000000001 x1 : 0000000000000004 x0 : 0000000000000022 [ 2479.386231]I[0:launcher-loader: 1719] Call trace: [ 2479.386248]I[0:launcher-loader: 1719] __stack_depot_save+0x464/0x46c [ 2479.386273]I[0:launcher-loader: 1719] kasan_save_stack+0x58/0x70 [ 2479.386303]I[0:launcher-loader: 1719] save_stack_info+0x34/0x138 [ 2479.386331]I[0:launcher-loader: 1719] kasan_save_free_info+0x18/0x24 [ 2479.386358]I[0:launcher-loader: 1719] ____kasan_slab_free+0x16c/0x170 [ 2479.386385]I[0:launcher-loader: 1719] __kasan_slab_free+0x10/0x20 [ 2479.386410]I[0:launcher-loader: 1719] kmem_cache_free+0x238/0x53c [ 2479.386435]I[0:launcher-loader: 1719] mempool_free_slab+0x1c/0x28 [ 2479.386460]I[0:launcher-loader: 1719] mempool_free+0x7c/0x1a0 [ 2479.386484]I[0:launcher-loader: 1719] bvec_free+0x34/0x80 [ 2479.386514]I[0:launcher-loader: 1719] bio_free+0x60/0x98 [ 2479.386540]I[0:launcher-loader: 1719] bio_put+0x50/0x21c [ 2479.386567]I[0:launcher-loader: 1719] f2fs_write_end_io+0x4ac/0x4d0 [ 2479.386594]I[0:launcher-loader: 1719] bio_endio+0x2dc/0x300 [ 2479.386622]I[0:launcher-loader: 1719] __dm_io_complete+0x324/0x37c [ 2479.386650]I[0:launcher-loader: 1719] dm_io_dec_pending+0x60/0xa4 [ 2479.386676]I[0:launcher-loader: 1719] clone_endio+0xf8/0x2f0 [ 2479.386700]I[0:launcher-loader: 1719] bio_endio+0x2dc/0x300 [ 2479.386727]I[0:launcher-loader: 1719] blk_update_request+0x258/0x63c [ 2479.386754]I[0:launcher-loader: 1719] scsi_end_request+0x50/0x304 [ 2479.386782]I[0:launcher-loader: 1719] scsi_io_completion+0x88/0x160 [ 2479.386808]I[0:launcher-loader: 1719] scsi_finish_command+0x17c/0x194 [ 2479.386833]I[0:launcher-loader: 1719] scsi_complete+0xcc/0x158 [ 2479.386859]I[0:launcher-loader: 1719] blk_mq_complete_request+0x4c/0x5c [ 2479.386885]I[0:launcher-loader: 1719] scsi_done_internal+0xf4/0x1e0 [ 2479.386910]I[0:launcher-loader: 1719] scsi_done+0x14/0x20 [ 2479.386935]I[0:launcher-loader: 1719] ufshcd_compl_one_cqe+0x578/0x71c [ 2479.386963]I[0:launcher-loader: 1719] ufshcd_mcq_poll_cqe_nolock+0xc8/0x150 [ 2479.386991]I[0:launcher-loader: 1719] ufshcd_intr+0x868/0xc0c [ 2479.387017]I[0:launcher-loader: 1719] __handle_irq_event_percpu+0xd0/0x348 [ 2479.387044]I[0:launcher-loader: 1719] handle_irq_event_percpu+0x24/0x74 [ 2479.387068]I[0:launcher-loader: 1719] handle_irq_event+0x74/0xe0 [ 2479.387091]I[0:launcher-loader: 1719] handle_fasteoi_irq+0x174/0x240 [ 2479.387118]I[0:launcher-loader: 1719] handle_irq_desc+0x7c/0x2c0 [ 2479.387147]I[0:launcher-loader: 1719] generic_handle_domain_irq+0x1c/0x28 [ 2479.387174]I[0:launcher-loader: 1719] gic_handle_irq+0x64/0x158 [ 2479.387204]I[0:launcher-loader: 1719] call_on_irq_stack+0x2c/0x54 [ 2479.387231]I[0:launcher-loader: 1719] do_interrupt_handler+0x70/0xa0 [ 2479.387258]I[0:launcher-loader: 1719] el1_interrupt+0x34/0x68 [ 2479.387283]I[0:launcher-loader: 1719] el1h_64_irq_handler+0x18/0x24 [ 2479.387308]I[0:launcher-loader: 1719] el1h_64_irq+0x68/0x6c [ 2479.387332]I[0:launcher-loader: 1719] blk_attempt_bio_merge+0x8/0x170 [ 2479.387356]I[0:launcher-loader: 1719] blk_mq_attempt_bio_merge+0x78/0x98 [ 2479.387383]I[0:launcher-loader: 1719] blk_mq_submit_bio+0x324/0xa40 [ 2479.387409]I[0:launcher-loader: 1719] __submit_bio+0x104/0x138 [ 2479.387436]I[0:launcher-loader: 1719] submit_bio_noacct_nocheck+0x1d0/0x4a0 [ 2479.387462]I[0:launcher-loader: 1719] submit_bio_noacct+0x618/0x804 [ 2479.387487]I[0:launcher-loader: 1719] submit_bio+0x164/0x180 [ 2479.387511]I[0:launcher-loader: 1719] f2fs_submit_read_bio+0xe4/0x1c4 [ 2479.387537]I[0:launcher-loader: 1719] f2fs_mpage_readpages+0x888/0xa4c [ 2479.387563]I[0:launcher-loader: 1719] f2fs_readahead+0xd4/0x19c [ 2479.387587]I[0:launcher-loader: 1719] read_pages+0xb0/0x4ac [ 2479.387614]I[0:launcher-loader: 1719] page_cache_ra_unbounded+0x238/0x288 [ 2479.387642]I[0:launcher-loader: 1719] do_page_cache_ra+0x60/0x6c [ 2479.387669]I[0:launcher-loader: 1719] page_cache_ra_order+0x318/0x364 [ 2479.387695]I[0:launcher-loader: 1719] ondemand_readahead+0x30c/0x3d8 [ 2479.387722]I[0:launcher-loader: 1719] page_cache_sync_ra+0xb4/0xc8 [ 2479.387749]I[0:launcher-loader: 1719] filemap_read+0x268/0xd24 [ 2479.387777]I[0:launcher-loader: 1719] f2fs_file_read_iter+0x1a0/0x62c [ 2479.387806]I[0:launcher-loader: 1719] vfs_read+0x258/0x34c [ 2479.387831]I[0:launcher-loader: 1719] ksys_pread64+0x8c/0xd0 [ 2479.387857]I[0:launcher-loader: 1719] __arm64_sys_pread64+0x48/0x54 [ 2479.387881]I[0:launcher-loader: 1719] invoke_syscall+0x58/0x158 [ 2479.387909]I[0:launcher-loader: 1719] el0_svc_common+0xf0/0x134 [ 2479.387935]I[0:launcher-loader: 1719] do_el0_svc+0x44/0x114 [ 2479.387961]I[0:launcher-loader: 1719] el0_svc+0x2c/0x80 [ 2479.387985]I[0:launcher-loader: 1719] el0t_64_sync_handler+0x48/0x114 [ 2479.388010]I[0:launcher-loader: 1719] el0t_64_sync+0x190/0x194 [ 2479.388038]I[0:launcher-loader: 1719] Kernel panic - not syncing: kernel: panic_on_warn set ... So let's set __exception_irq_entry with __irq_entry as a default. Applying this patch, we can see gic_hande_irq is included in Systemp.map as below. * Before ffffffc008010000 T __do_softirq ffffffc008010000 T __irqentry_text_end ffffffc008010000 T __irqentry_text_start ffffffc008010000 T __softirqentry_text_start ffffffc008010000 T _stext ffffffc00801066c T __softirqentry_text_end ffffffc008010670 T __entry_text_start * After ffffffc008010000 T __irqentry_text_start ffffffc008010000 T _stext ffffffc008010000 t gic_handle_irq ffffffc00801013c t gic_handle_irq ffffffc008010294 T __irqentry_text_end ffffffc008010298 T __do_softirq ffffffc008010298 T __softirqentry_text_start ffffffc008010904 T __softirqentry_text_end ffffffc008010908 T __entry_text_start Signed-off-by: Youngmin Nam Signed-off-by: SEO HOYOUNG Reviewed-by: Mark Rutland Link: https://lore.kernel.org/r/20230424010436.779733-1-youngmin.nam@samsung.com Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- arch/arm64/include/asm/exception.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 0756191f44f6..59c3facb8a56 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -8,16 +8,11 @@ #define __ASM_EXCEPTION_H #include -#include #include #include -#ifdef CONFIG_FUNCTION_GRAPH_TRACER #define __exception_irq_entry __irq_entry -#else -#define __exception_irq_entry __kprobes -#endif static inline u32 disr_to_esr(u64 disr) { From 32020fc2a8373d3de35ae6d029d5969a42651e7a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 15 Jun 2023 11:26:28 +0100 Subject: [PATCH 4197/4345] arm64: mm: fix VA-range sanity check [ Upstream commit ab9b4008092c86dc12497af155a0901cc1156999 ] Both create_mapping_noalloc() and update_mapping_prot() sanity-check their 'virt' parameter, but the check itself doesn't make much sense. The condition used today appears to be a historical accident. The sanity-check condition: if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { [ ... warning here ... ] return; } ... can only be true for the KASAN shadow region or the module region, and there's no reason to exclude these specifically for creating and updateing mappings. When arm64 support was first upstreamed in commit: c1cc1552616d0f35 ("arm64: MMU initialisation") ... the condition was: if (virt < VMALLOC_START) { [ ... warning here ... ] return; } At the time, VMALLOC_START was the lowest kernel address, and this was checking whether 'virt' would be translated via TTBR1. Subsequently in commit: 14c127c957c1c607 ("arm64: mm: Flip kernel VA space") ... the condition was changed to: if ((virt >= VA_START) && (virt < VMALLOC_START)) { [ ... warning here ... ] return; } This appear to have been a thinko. The commit moved the linear map to the bottom of the kernel address space, with VMALLOC_START being at the halfway point. The old condition would warn for changes to the linear map below this, and at the time VA_START was the end of the linear map. Subsequently we cleaned up the naming of VA_START in commit: 77ad4ce69321abbe ("arm64: memory: rename VA_START to PAGE_END") ... keeping the erroneous condition as: if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { [ ... warning here ... ] return; } Correct the condition to check against the start of the TTBR1 address space, which is currently PAGE_OFFSET. This simplifies the logic, and more clearly matches the "outside kernel range" message in the warning. Signed-off-by: Mark Rutland Cc: Russell King Cc: Steve Capper Cc: Will Deacon Reviewed-by: Russell King (Oracle) Link: https://lore.kernel.org/r/20230615102628.1052103-1-mark.rutland@arm.com Signed-off-by: Catalin Marinas Signed-off-by: Sasha Levin --- arch/arm64/mm/mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 3284709ef567..78f9fb638c9c 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -421,7 +421,7 @@ static phys_addr_t pgd_pgtable_alloc(int shift) static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { + if (virt < PAGE_OFFSET) { pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; @@ -448,7 +448,7 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, static void update_mapping_prot(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { + if (virt < PAGE_OFFSET) { pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; From 6b0c79aa33075b34c3cdcea4132c0afb3fc42d68 Mon Sep 17 00:00:00 2001 From: Yicong Yang Date: Tue, 30 May 2023 16:25:07 +0800 Subject: [PATCH 4198/4345] sched/fair: Don't balance task to its current running CPU [ Upstream commit 0dd37d6dd33a9c23351e6115ae8cdac7863bc7de ] We've run into the case that the balancer tries to balance a migration disabled task and trigger the warning in set_task_cpu() like below: ------------[ cut here ]------------ WARNING: CPU: 7 PID: 0 at kernel/sched/core.c:3115 set_task_cpu+0x188/0x240 Modules linked in: hclgevf xt_CHECKSUM ipt_REJECT nf_reject_ipv4 <...snip> CPU: 7 PID: 0 Comm: swapper/7 Kdump: loaded Tainted: G O 6.1.0-rc4+ #1 Hardware name: Huawei TaiShan 2280 V2/BC82AMDC, BIOS 2280-V2 CS V5.B221.01 12/09/2021 pstate: 604000c9 (nZCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : set_task_cpu+0x188/0x240 lr : load_balance+0x5d0/0xc60 sp : ffff80000803bc70 x29: ffff80000803bc70 x28: ffff004089e190e8 x27: ffff004089e19040 x26: ffff007effcabc38 x25: 0000000000000000 x24: 0000000000000001 x23: ffff80000803be84 x22: 000000000000000c x21: ffffb093e79e2a78 x20: 000000000000000c x19: ffff004089e19040 x18: 0000000000000000 x17: 0000000000001fad x16: 0000000000000030 x15: 0000000000000000 x14: 0000000000000003 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000001 x10: 0000000000000400 x9 : ffffb093e4cee530 x8 : 00000000fffffffe x7 : 0000000000ce168a x6 : 000000000000013e x5 : 00000000ffffffe1 x4 : 0000000000000001 x3 : 0000000000000b2a x2 : 0000000000000b2a x1 : ffffb093e6d6c510 x0 : 0000000000000001 Call trace: set_task_cpu+0x188/0x240 load_balance+0x5d0/0xc60 rebalance_domains+0x26c/0x380 _nohz_idle_balance.isra.0+0x1e0/0x370 run_rebalance_domains+0x6c/0x80 __do_softirq+0x128/0x3d8 ____do_softirq+0x18/0x24 call_on_irq_stack+0x2c/0x38 do_softirq_own_stack+0x24/0x3c __irq_exit_rcu+0xcc/0xf4 irq_exit_rcu+0x18/0x24 el1_interrupt+0x4c/0xe4 el1h_64_irq_handler+0x18/0x2c el1h_64_irq+0x74/0x78 arch_cpu_idle+0x18/0x4c default_idle_call+0x58/0x194 do_idle+0x244/0x2b0 cpu_startup_entry+0x30/0x3c secondary_start_kernel+0x14c/0x190 __secondary_switched+0xb0/0xb4 ---[ end trace 0000000000000000 ]--- Further investigation shows that the warning is superfluous, the migration disabled task is just going to be migrated to its current running CPU. This is because that on load balance if the dst_cpu is not allowed by the task, we'll re-select a new_dst_cpu as a candidate. If no task can be balanced to dst_cpu we'll try to balance the task to the new_dst_cpu instead. In this case when the migration disabled task is not on CPU it only allows to run on its current CPU, load balance will select its current CPU as new_dst_cpu and later triggers the warning above. The new_dst_cpu is chosen from the env->dst_grpmask. Currently it contains CPUs in sched_group_span() and if we have overlapped groups it's possible to run into this case. This patch makes env->dst_grpmask of group_balance_mask() which exclude any CPUs from the busiest group and solve the issue. For balancing in a domain with no overlapped groups the behaviour keeps same as before. Suggested-by: Vincent Guittot Signed-off-by: Yicong Yang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot Link: https://lore.kernel.org/r/20230530082507.10444-1-yangyicong@huawei.com Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 45c1d03aff73..d53f57ac7609 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9883,7 +9883,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, .sd = sd, .dst_cpu = this_cpu, .dst_rq = this_rq, - .dst_grpmask = sched_group_span(sd->groups), + .dst_grpmask = group_balance_mask(sd->groups), .idle = idle, .loop_break = sched_nr_migrate_break, .cpus = cpus, From 532f8bac60419eb28158770470b9bb655de207c8 Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Fri, 21 Apr 2023 16:54:45 +0200 Subject: [PATCH 4199/4345] wifi: ath11k: fix registration of 6Ghz-only phy without the full channel range [ Upstream commit e2ceb1de2f83aafd8003f0b72dfd4b7441e97d14 ] Because of what seems to be a typo, a 6Ghz-only phy for which the BDF does not allow the 7115Mhz channel will fail to register: WARNING: CPU: 2 PID: 106 at net/wireless/core.c:907 wiphy_register+0x914/0x954 Modules linked in: ath11k_pci sbsa_gwdt CPU: 2 PID: 106 Comm: kworker/u8:5 Not tainted 6.3.0-rc7-next-20230418-00549-g1e096a17625a-dirty #9 Hardware name: Freebox V7R Board (DT) Workqueue: ath11k_qmi_driver_event ath11k_qmi_driver_event_work pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : wiphy_register+0x914/0x954 lr : ieee80211_register_hw+0x67c/0xc10 sp : ffffff800b123aa0 x29: ffffff800b123aa0 x28: 0000000000000000 x27: 0000000000000000 x26: 0000000000000000 x25: 0000000000000006 x24: ffffffc008d51418 x23: ffffffc008cb0838 x22: ffffff80176c2460 x21: 0000000000000168 x20: ffffff80176c0000 x19: ffffff80176c03e0 x18: 0000000000000014 x17: 00000000cbef338c x16: 00000000d2a26f21 x15: 00000000ad6bb85f x14: 0000000000000020 x13: 0000000000000020 x12: 00000000ffffffbd x11: 0000000000000208 x10: 00000000fffffdf7 x9 : ffffffc009394718 x8 : ffffff80176c0528 x7 : 000000007fffffff x6 : 0000000000000006 x5 : 0000000000000005 x4 : ffffff800b304284 x3 : ffffff800b304284 x2 : ffffff800b304d98 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: wiphy_register+0x914/0x954 ieee80211_register_hw+0x67c/0xc10 ath11k_mac_register+0x7c4/0xe10 ath11k_core_qmi_firmware_ready+0x1f4/0x570 ath11k_qmi_driver_event_work+0x198/0x590 process_one_work+0x1b8/0x328 worker_thread+0x6c/0x414 kthread+0x100/0x104 ret_from_fork+0x10/0x20 ---[ end trace 0000000000000000 ]--- ath11k_pci 0002:01:00.0: ieee80211 registration failed: -22 ath11k_pci 0002:01:00.0: failed register the radio with mac80211: -22 ath11k_pci 0002:01:00.0: failed to create pdev core: -22 Signed-off-by: Maxime Bizon Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230421145445.2612280-1-mbizon@freebox.fr Signed-off-by: Sasha Levin --- drivers/net/wireless/ath/ath11k/mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 67faf62999de..3170c54c97b7 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -6044,7 +6044,7 @@ static int ath11k_mac_setup_channels_rates(struct ath11k *ar, } if (supported_bands & WMI_HOST_WLAN_5G_CAP) { - if (reg_cap->high_5ghz_chan >= ATH11K_MAX_6G_FREQ) { + if (reg_cap->high_5ghz_chan >= ATH11K_MIN_6G_FREQ) { channels = kmemdup(ath11k_6ghz_channels, sizeof(ath11k_6ghz_channels), GFP_KERNEL); if (!channels) { From b6d9a4062c944ad095b34dc112bf646a84156f60 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 10 May 2023 21:37:48 -0700 Subject: [PATCH 4200/4345] bpf: Address KCSAN report on bpf_lru_list [ Upstream commit ee9fd0ac3017c4313be91a220a9ac4c99dde7ad4 ] KCSAN reported a data-race when accessing node->ref. Although node->ref does not have to be accurate, take this chance to use a more common READ_ONCE() and WRITE_ONCE() pattern instead of data_race(). There is an existing bpf_lru_node_is_ref() and bpf_lru_node_set_ref(). This patch also adds bpf_lru_node_clear_ref() to do the WRITE_ONCE(node->ref, 0) also. ================================================================== BUG: KCSAN: data-race in __bpf_lru_list_rotate / __htab_lru_percpu_map_update_elem write to 0xffff888137038deb of 1 bytes by task 11240 on cpu 1: __bpf_lru_node_move kernel/bpf/bpf_lru_list.c:113 [inline] __bpf_lru_list_rotate_active kernel/bpf/bpf_lru_list.c:149 [inline] __bpf_lru_list_rotate+0x1bf/0x750 kernel/bpf/bpf_lru_list.c:240 bpf_lru_list_pop_free_to_local kernel/bpf/bpf_lru_list.c:329 [inline] bpf_common_lru_pop_free kernel/bpf/bpf_lru_list.c:447 [inline] bpf_lru_pop_free+0x638/0xe20 kernel/bpf/bpf_lru_list.c:499 prealloc_lru_pop kernel/bpf/hashtab.c:290 [inline] __htab_lru_percpu_map_update_elem+0xe7/0x820 kernel/bpf/hashtab.c:1316 bpf_percpu_hash_update+0x5e/0x90 kernel/bpf/hashtab.c:2313 bpf_map_update_value+0x2a9/0x370 kernel/bpf/syscall.c:200 generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1687 bpf_map_do_batch+0x2d9/0x3d0 kernel/bpf/syscall.c:4534 __sys_bpf+0x338/0x810 __do_sys_bpf kernel/bpf/syscall.c:5096 [inline] __se_sys_bpf kernel/bpf/syscall.c:5094 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5094 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888137038deb of 1 bytes by task 11241 on cpu 0: bpf_lru_node_set_ref kernel/bpf/bpf_lru_list.h:70 [inline] __htab_lru_percpu_map_update_elem+0x2f1/0x820 kernel/bpf/hashtab.c:1332 bpf_percpu_hash_update+0x5e/0x90 kernel/bpf/hashtab.c:2313 bpf_map_update_value+0x2a9/0x370 kernel/bpf/syscall.c:200 generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1687 bpf_map_do_batch+0x2d9/0x3d0 kernel/bpf/syscall.c:4534 __sys_bpf+0x338/0x810 __do_sys_bpf kernel/bpf/syscall.c:5096 [inline] __se_sys_bpf kernel/bpf/syscall.c:5094 [inline] __x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5094 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x01 -> 0x00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 11241 Comm: syz-executor.3 Not tainted 6.3.0-rc7-syzkaller-00136-g6a66fdd29ea1 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023 ================================================================== Reported-by: syzbot+ebe648a84e8784763f82@syzkaller.appspotmail.com Signed-off-by: Martin KaFai Lau Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20230511043748.1384166-1-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin --- kernel/bpf/bpf_lru_list.c | 21 +++++++++++++-------- kernel/bpf/bpf_lru_list.h | 7 ++----- 2 files changed, 15 insertions(+), 13 deletions(-) diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c index d99e89f113c4..3dabdd137d10 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -41,7 +41,12 @@ static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l) /* bpf_lru_node helpers */ static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node) { - return node->ref; + return READ_ONCE(node->ref); +} + +static void bpf_lru_node_clear_ref(struct bpf_lru_node *node) +{ + WRITE_ONCE(node->ref, 0); } static void bpf_lru_list_count_inc(struct bpf_lru_list *l, @@ -89,7 +94,7 @@ static void __bpf_lru_node_move_in(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, &l->lists[tgt_type]); } @@ -110,7 +115,7 @@ static void __bpf_lru_node_move(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; } - node->ref = 0; + bpf_lru_node_clear_ref(node); /* If the moving node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. @@ -353,7 +358,7 @@ static void __local_list_add_pending(struct bpf_lru *lru, *(u32 *)((void *)node + lru->hash_offset) = hash; node->cpu = cpu; node->type = BPF_LRU_LOCAL_LIST_T_PENDING; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, local_pending_list(loc_l)); } @@ -419,7 +424,7 @@ static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, if (!list_empty(free_list)) { node = list_first_entry(free_list, struct bpf_lru_node, list); *(u32 *)((void *)node + lru->hash_offset) = hash; - node->ref = 0; + bpf_lru_node_clear_ref(node); __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); } @@ -522,7 +527,7 @@ static void bpf_common_lru_push_free(struct bpf_lru *lru, } node->type = BPF_LRU_LOCAL_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, local_free_list(loc_l)); raw_spin_unlock_irqrestore(&loc_l->lock, flags); @@ -568,7 +573,7 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf, node = (struct bpf_lru_node *)(buf + node_offset); node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; } @@ -594,7 +599,7 @@ again: node = (struct bpf_lru_node *)(buf + node_offset); node->cpu = cpu; node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); i++; buf += elem_size; diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 6b12f06ee18c..9c12ee453c61 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -63,11 +63,8 @@ struct bpf_lru { static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) { - /* ref is an approximation on access frequency. It does not - * have to be very accurate. Hence, no protection is used. - */ - if (!node->ref) - node->ref = 1; + if (!READ_ONCE(node->ref)) + WRITE_ONCE(node->ref, 1); } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, From 2864cc9a1fd13666ed7fd9064dc3f2c51a85de32 Mon Sep 17 00:00:00 2001 From: Petr Oros Date: Thu, 15 Jun 2023 11:54:47 +0200 Subject: [PATCH 4201/4345] devlink: report devlink_port_type_warn source device [ Upstream commit a52305a81d6bb74b90b400dfa56455d37872fe4b ] devlink_port_type_warn is scheduled for port devlink and warning when the port type is not set. But from this warning it is not easy found out which device (driver) has no devlink port set. [ 3709.975552] Type was not set for devlink port. [ 3709.975579] WARNING: CPU: 1 PID: 13092 at net/devlink/leftover.c:6775 devlink_port_type_warn+0x11/0x20 [ 3709.993967] Modules linked in: openvswitch nf_conncount nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nfnetlink bluetooth rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs vhost_net vhost vhost_iotlb tap tun bridge stp llc qrtr intel_rapl_msr intel_rapl_common i10nm_edac nfit libnvdimm x86_pkg_temp_thermal mlx5_ib intel_powerclamp coretemp dell_wmi ledtrig_audio sparse_keymap ipmi_ssif kvm_intel ib_uverbs rfkill ib_core video kvm iTCO_wdt acpi_ipmi intel_vsec irqbypass ipmi_si iTCO_vendor_support dcdbas ipmi_devintf mei_me ipmi_msghandler rapl mei intel_cstate isst_if_mmio isst_if_mbox_pci dell_smbios intel_uncore isst_if_common i2c_i801 dell_wmi_descriptor wmi_bmof i2c_smbus intel_pch_thermal pcspkr acpi_power_meter xfs libcrc32c sd_mod sg nvme_tcp mgag200 i2c_algo_bit nvme_fabrics drm_shmem_helper drm_kms_helper nvme syscopyarea ahci sysfillrect sysimgblt nvme_core fb_sys_fops crct10dif_pclmul libahci mlx5_core sfc crc32_pclmul nvme_common drm [ 3709.994030] crc32c_intel mtd t10_pi mlxfw libata tg3 mdio megaraid_sas psample ghash_clmulni_intel pci_hyperv_intf wmi dm_multipath sunrpc dm_mirror dm_region_hash dm_log dm_mod be2iscsi bnx2i cnic uio cxgb4i cxgb4 tls libcxgbi libcxgb qla4xxx iscsi_boot_sysfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi fuse [ 3710.108431] CPU: 1 PID: 13092 Comm: kworker/1:1 Kdump: loaded Not tainted 5.14.0-319.el9.x86_64 #1 [ 3710.108435] Hardware name: Dell Inc. PowerEdge R750/0PJ80M, BIOS 1.8.2 09/14/2022 [ 3710.108437] Workqueue: events devlink_port_type_warn [ 3710.108440] RIP: 0010:devlink_port_type_warn+0x11/0x20 [ 3710.108443] Code: 84 76 fe ff ff 48 c7 03 20 0e 1a ad 31 c0 e9 96 fd ff ff 66 0f 1f 44 00 00 0f 1f 44 00 00 48 c7 c7 18 24 4e ad e8 ef 71 62 ff <0f> 0b c3 cc cc cc cc 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 f6 87 [ 3710.108445] RSP: 0018:ff3b6d2e8b3c7e90 EFLAGS: 00010282 [ 3710.108447] RAX: 0000000000000000 RBX: ff366d6580127080 RCX: 0000000000000027 [ 3710.108448] RDX: 0000000000000027 RSI: 00000000ffff86de RDI: ff366d753f41f8c8 [ 3710.108449] RBP: ff366d658ff5a0c0 R08: ff366d753f41f8c0 R09: ff3b6d2e8b3c7e18 [ 3710.108450] R10: 0000000000000001 R11: 0000000000000023 R12: ff366d753f430600 [ 3710.108451] R13: ff366d753f436900 R14: 0000000000000000 R15: ff366d753f436905 [ 3710.108452] FS: 0000000000000000(0000) GS:ff366d753f400000(0000) knlGS:0000000000000000 [ 3710.108453] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3710.108454] CR2: 00007f1c57bc74e0 CR3: 000000111d26a001 CR4: 0000000000773ee0 [ 3710.108456] PKRU: 55555554 [ 3710.108457] Call Trace: [ 3710.108458] [ 3710.108459] process_one_work+0x1e2/0x3b0 [ 3710.108466] ? rescuer_thread+0x390/0x390 [ 3710.108468] worker_thread+0x50/0x3a0 [ 3710.108471] ? rescuer_thread+0x390/0x390 [ 3710.108473] kthread+0xdd/0x100 [ 3710.108477] ? kthread_complete_and_exit+0x20/0x20 [ 3710.108479] ret_from_fork+0x1f/0x30 [ 3710.108485] [ 3710.108486] ---[ end trace 1b4b23cd0c65d6a0 ]--- After patch: [ 402.473064] ice 0000:41:00.0: Type was not set for devlink port. [ 402.473064] ice 0000:41:00.1: Type was not set for devlink port. Signed-off-by: Petr Oros Reviewed-by: Pavan Chebbi Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230615095447.8259-1-poros@redhat.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/core/devlink.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/devlink.c b/net/core/devlink.c index 72047750dcd9..00c6944ed634 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -8092,7 +8092,10 @@ EXPORT_SYMBOL_GPL(devlink_free); static void devlink_port_type_warn(struct work_struct *work) { - WARN(true, "Type was not set for devlink port."); + struct devlink_port *port = container_of(to_delayed_work(work), + struct devlink_port, + type_warn_dw); + dev_warn(port->devlink->dev, "Type was not set for devlink port."); } static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) From 85cf0d5f45cb73c4b67b87152fe5481092ed3b4b Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 15 Jun 2023 12:04:07 -0600 Subject: [PATCH 4202/4345] wifi: wext-core: Fix -Wstringop-overflow warning in ioctl_standard_iw_point() [ Upstream commit 71e7552c90db2a2767f5c17c7ec72296b0d92061 ] -Wstringop-overflow is legitimately warning us about extra_size pontentially being zero at some point, hence potenially ending up _allocating_ zero bytes of memory for extra pointer and then trying to access such object in a call to copy_from_user(). Fix this by adding a sanity check to ensure we never end up trying to allocate zero bytes of data for extra pointer, before continue executing the rest of the code in the function. Address the following -Wstringop-overflow warning seen when built m68k architecture with allyesconfig configuration: from net/wireless/wext-core.c:11: In function '_copy_from_user', inlined from 'copy_from_user' at include/linux/uaccess.h:183:7, inlined from 'ioctl_standard_iw_point' at net/wireless/wext-core.c:825:7: arch/m68k/include/asm/string.h:48:25: warning: '__builtin_memset' writing 1 or more bytes into a region of size 0 overflows the destination [-Wstringop-overflow=] 48 | #define memset(d, c, n) __builtin_memset(d, c, n) | ^~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/uaccess.h:153:17: note: in expansion of macro 'memset' 153 | memset(to + (n - res), 0, res); | ^~~~~~ In function 'kmalloc', inlined from 'kzalloc' at include/linux/slab.h:694:9, inlined from 'ioctl_standard_iw_point' at net/wireless/wext-core.c:819:10: include/linux/slab.h:577:16: note: at offset 1 into destination object of size 0 allocated by '__kmalloc' 577 | return __kmalloc(size, flags); | ^~~~~~~~~~~~~~~~~~~~~~ This help with the ongoing efforts to globally enable -Wstringop-overflow. Link: https://github.com/KSPP/linux/issues/315 Signed-off-by: Gustavo A. R. Silva Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/ZItSlzvIpjdjNfd8@work Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/wireless/wext-core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 76a80a41615b..a57f54bc0e1a 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -796,6 +796,12 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, } } + /* Sanity-check to ensure we never end up _allocating_ zero + * bytes of data for extra. + */ + if (extra_size <= 0) + return -EFAULT; + /* kzalloc() ensures NULL-termination for essid_compat. */ extra = kzalloc(extra_size, GFP_KERNEL); if (!extra) From a956c3af70fad096654a06d9dceb4e5641e29f08 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 20 Jun 2023 13:04:02 +0300 Subject: [PATCH 4203/4345] wifi: iwlwifi: mvm: avoid baid size integer overflow [ Upstream commit 1a528ab1da324d078ec60283c34c17848580df24 ] Roee reported various hard-to-debug crashes with pings in EHT aggregation scenarios. Enabling KASAN showed that we access the BAID allocation out of bounds, and looking at the code a bit shows that since the reorder buffer entry (struct iwl_mvm_reorder_buf_entry) is 128 bytes if debug such as lockdep is enabled, then staring from an agg size 512 we overflow the size calculation, and allocate a much smaller structure than we should, causing slab corruption once we initialize this. Fix this by simply using u32 instead of u16. Reported-by: Roee Goldfiner Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230620125813.f428c856030d.I2c2bb808e945adb71bc15f5b2bac2d8957ea90eb@changeid Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 09f870c48a4f..141581fa74c8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2590,7 +2590,7 @@ int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta, } if (iwl_mvm_has_new_rx_api(mvm) && start) { - u16 reorder_buf_size = buf_size * sizeof(baid_data->entries[0]); + u32 reorder_buf_size = buf_size * sizeof(baid_data->entries[0]); /* sparse doesn't like the __align() so don't check */ #ifndef __CHECKER__ From 994c2ceb70ea99264ccc6f09e6703ca267dad63c Mon Sep 17 00:00:00 2001 From: Ying Hsu Date: Tue, 20 Jun 2023 10:47:32 -0700 Subject: [PATCH 4204/4345] igb: Fix igb_down hung on surprise removal [ Upstream commit 004d25060c78fc31f66da0fa439c544dda1ac9d5 ] In a setup where a Thunderbolt hub connects to Ethernet and a display through USB Type-C, users may experience a hung task timeout when they remove the cable between the PC and the Thunderbolt hub. This is because the igb_down function is called multiple times when the Thunderbolt hub is unplugged. For example, the igb_io_error_detected triggers the first call, and the igb_remove triggers the second call. The second call to igb_down will block at napi_synchronize. Here's the call trace: __schedule+0x3b0/0xddb ? __mod_timer+0x164/0x5d3 schedule+0x44/0xa8 schedule_timeout+0xb2/0x2a4 ? run_local_timers+0x4e/0x4e msleep+0x31/0x38 igb_down+0x12c/0x22a [igb 6615058754948bfde0bf01429257eb59f13030d4] __igb_close+0x6f/0x9c [igb 6615058754948bfde0bf01429257eb59f13030d4] igb_close+0x23/0x2b [igb 6615058754948bfde0bf01429257eb59f13030d4] __dev_close_many+0x95/0xec dev_close_many+0x6e/0x103 unregister_netdevice_many+0x105/0x5b1 unregister_netdevice_queue+0xc2/0x10d unregister_netdev+0x1c/0x23 igb_remove+0xa7/0x11c [igb 6615058754948bfde0bf01429257eb59f13030d4] pci_device_remove+0x3f/0x9c device_release_driver_internal+0xfe/0x1b4 pci_stop_bus_device+0x5b/0x7f pci_stop_bus_device+0x30/0x7f pci_stop_bus_device+0x30/0x7f pci_stop_and_remove_bus_device+0x12/0x19 pciehp_unconfigure_device+0x76/0xe9 pciehp_disable_slot+0x6e/0x131 pciehp_handle_presence_or_link_change+0x7a/0x3f7 pciehp_ist+0xbe/0x194 irq_thread_fn+0x22/0x4d ? irq_thread+0x1fd/0x1fd irq_thread+0x17b/0x1fd ? irq_forced_thread_fn+0x5f/0x5f kthread+0x142/0x153 ? __irq_get_irqchip_state+0x46/0x46 ? kthread_associate_blkcg+0x71/0x71 ret_from_fork+0x1f/0x30 In this case, igb_io_error_detected detaches the network interface and requests a PCIE slot reset, however, the PCIE reset callback is not being invoked and thus the Ethernet connection breaks down. As the PCIE error in this case is a non-fatal one, requesting a slot reset can be avoided. This patch fixes the task hung issue and preserves Ethernet connection by ignoring non-fatal PCIE errors. Signed-off-by: Ying Hsu Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230620174732.4145155-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/igb/igb_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index c5f465814dec..446598210012 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -9453,6 +9453,11 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev); + if (state == pci_channel_io_normal) { + dev_warn(&pdev->dev, "Non-correctable non-fatal error reported.\n"); + return PCI_ERS_RESULT_CAN_RECOVER; + } + netif_device_detach(netdev); if (state == pci_channel_io_perm_failure) From 6e88cc510f2706462210abb6adce4bdf8521a6cf Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Thu, 29 Jun 2023 09:14:52 +0200 Subject: [PATCH 4205/4345] spi: bcm63xx: fix max prepend length [ Upstream commit 5158814cbb37bbb38344b3ecddc24ba2ed0365f2 ] The command word is defined as following: /* Command */ #define SPI_CMD_COMMAND_SHIFT 0 #define SPI_CMD_DEVICE_ID_SHIFT 4 #define SPI_CMD_PREPEND_BYTE_CNT_SHIFT 8 #define SPI_CMD_ONE_BYTE_SHIFT 11 #define SPI_CMD_ONE_WIRE_SHIFT 12 If the prepend byte count field starts at bit 8, and the next defined bit is SPI_CMD_ONE_BYTE at bit 11, it can be at most 3 bits wide, and thus the max value is 7, not 15. Fixes: b17de076062a ("spi/bcm63xx: work around inability to keep CS up") Signed-off-by: Jonas Gorski Link: https://lore.kernel.org/r/20230629071453.62024-1-jonas.gorski@gmail.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- drivers/spi/spi-bcm63xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c index 96d075e633f4..d36384fef0d7 100644 --- a/drivers/spi/spi-bcm63xx.c +++ b/drivers/spi/spi-bcm63xx.c @@ -126,7 +126,7 @@ enum bcm63xx_regs_spi { SPI_MSG_DATA_SIZE, }; -#define BCM63XX_SPI_MAX_PREPEND 15 +#define BCM63XX_SPI_MAX_PREPEND 7 #define BCM63XX_SPI_MAX_CS 8 #define BCM63XX_SPI_BUS_NUM 0 From 7041605e8594c41149e69222f8a42250cc42d2ef Mon Sep 17 00:00:00 2001 From: Martin Kaiser Date: Wed, 28 Jun 2023 15:24:37 +0200 Subject: [PATCH 4206/4345] fbdev: imxfb: warn about invalid left/right margin [ Upstream commit 4e47382fbca916d7db95cbf9e2d7ca2e9d1ca3fe ] Warn about invalid var->left_margin or var->right_margin. Their values are read from the device tree. We store var->left_margin-3 and var->right_margin-1 in register fields. These fields should be >= 0. Fixes: 7e8549bcee00 ("imxfb: Fix margin settings") Signed-off-by: Martin Kaiser Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/imxfb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index 564bd0407ed8..d663e080b157 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -602,10 +602,10 @@ static int imxfb_activate_var(struct fb_var_screeninfo *var, struct fb_info *inf if (var->hsync_len < 1 || var->hsync_len > 64) printk(KERN_ERR "%s: invalid hsync_len %d\n", info->fix.id, var->hsync_len); - if (var->left_margin > 255) + if (var->left_margin < 3 || var->left_margin > 255) printk(KERN_ERR "%s: invalid left_margin %d\n", info->fix.id, var->left_margin); - if (var->right_margin > 255) + if (var->right_margin < 1 || var->right_margin > 255) printk(KERN_ERR "%s: invalid right_margin %d\n", info->fix.id, var->right_margin); if (var->yres < 1 || var->yres > ymax_mask) From 54aa4c03861e125e77deb84358db4a8637af456c Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 5 Jul 2023 08:30:03 -0500 Subject: [PATCH 4207/4345] pinctrl: amd: Use amd_pinconf_set() for all config options [ Upstream commit 635a750d958e158e17af0f524bedc484b27fbb93 ] On ASUS TUF A16 it is reported that the ITE5570 ACPI device connected to GPIO 7 is causing an interrupt storm. This issue doesn't happen on Windows. Comparing the GPIO register configuration between Windows and Linux bit 20 has been configured as a pull up on Windows, but not on Linux. Checking GPIO declaration from the firmware it is clear it *should* have been a pull up on Linux as well. ``` GpioInt (Level, ActiveLow, Exclusive, PullUp, 0x0000, "\\_SB.GPIO", 0x00, ResourceConsumer, ,) { // Pin list 0x0007 } ``` On Linux amd_gpio_set_config() is currently only used for programming the debounce. Actually the GPIO core calls it with all the arguments that are supported by a GPIO, pinctrl-amd just responds `-ENOTSUPP`. To solve this issue expand amd_gpio_set_config() to support the other arguments amd_pinconf_set() supports, namely `PIN_CONFIG_BIAS_PULL_DOWN`, `PIN_CONFIG_BIAS_PULL_UP`, and `PIN_CONFIG_DRIVE_STRENGTH`. Reported-by: Nik P Reported-by: Nathan Schulte Reported-by: Friedrich Vock Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217336 Reported-by: dridri85@gmail.com Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217493 Link: https://lore.kernel.org/linux-input/20230530154058.17594-1-friedrich.vock@gmx.de/ Tested-by: Jan Visser Fixes: 2956b5d94a76 ("pinctrl / gpio: Introduce .set_config() callback for GPIO chips") Signed-off-by: Mario Limonciello Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230705133005.577-3-mario.limonciello@amd.com Signed-off-by: Linus Walleij Signed-off-by: Sasha Levin --- drivers/pinctrl/pinctrl-amd.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 0d71151575ee..3a05ebb9aa25 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -189,18 +189,6 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, return ret; } -static int amd_gpio_set_config(struct gpio_chip *gc, unsigned offset, - unsigned long config) -{ - u32 debounce; - - if (pinconf_to_config_param(config) != PIN_CONFIG_INPUT_DEBOUNCE) - return -ENOTSUPP; - - debounce = pinconf_to_config_argument(config); - return amd_gpio_set_debounce(gc, offset, debounce); -} - #ifdef CONFIG_DEBUG_FS static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) { @@ -676,7 +664,7 @@ static int amd_pinconf_get(struct pinctrl_dev *pctldev, } static int amd_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, - unsigned long *configs, unsigned num_configs) + unsigned long *configs, unsigned int num_configs) { int i; u32 arg; @@ -766,6 +754,20 @@ static int amd_pinconf_group_set(struct pinctrl_dev *pctldev, return 0; } +static int amd_gpio_set_config(struct gpio_chip *gc, unsigned int pin, + unsigned long config) +{ + struct amd_gpio *gpio_dev = gpiochip_get_data(gc); + + if (pinconf_to_config_param(config) == PIN_CONFIG_INPUT_DEBOUNCE) { + u32 debounce = pinconf_to_config_argument(config); + + return amd_gpio_set_debounce(gc, pin, debounce); + } + + return amd_pinconf_set(gpio_dev->pctrl, pin, &config, 1); +} + static const struct pinconf_ops amd_pinconf_ops = { .pin_config_get = amd_pinconf_get, .pin_config_set = amd_pinconf_set, From f6d311b95394cdd0b661eeb7a2b395ef19ead9d8 Mon Sep 17 00:00:00 2001 From: Tanmay Patil Date: Wed, 12 Jul 2023 16:36:57 +0530 Subject: [PATCH 4208/4345] net: ethernet: ti: cpsw_ale: Fix cpsw_ale_get_field()/cpsw_ale_set_field() [ Upstream commit b685f1a58956fa36cc01123f253351b25bfacfda ] CPSW ALE has 75 bit ALE entries which are stored within three 32 bit words. The cpsw_ale_get_field() and cpsw_ale_set_field() functions assume that the field will be strictly contained within one word. However, this is not guaranteed to be the case and it is possible for ALE field entries to span across up to two words at the most. Fix the methods to handle getting/setting fields spanning up to two words. Fixes: db82173f23c5 ("netdev: driver: ethernet: add cpsw address lookup engine support") Signed-off-by: Tanmay Patil [s-vadapalli@ti.com: rephrased commit message and added Fixes tag] Signed-off-by: Siddharth Vadapalli Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/ti/cpsw_ale.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index a6a455c32628..73efc8b45364 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -104,23 +104,37 @@ struct cpsw_ale_dev_id { static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits) { - int idx; + int idx, idx2; + u32 hi_val = 0; idx = start / 32; + idx2 = (start + bits - 1) / 32; + /* Check if bits to be fetched exceed a word */ + if (idx != idx2) { + idx2 = 2 - idx2; /* flip */ + hi_val = ale_entry[idx2] << ((idx2 * 32) - start); + } start -= idx * 32; idx = 2 - idx; /* flip */ - return (ale_entry[idx] >> start) & BITMASK(bits); + return (hi_val + (ale_entry[idx] >> start)) & BITMASK(bits); } static inline void cpsw_ale_set_field(u32 *ale_entry, u32 start, u32 bits, u32 value) { - int idx; + int idx, idx2; value &= BITMASK(bits); - idx = start / 32; + idx = start / 32; + idx2 = (start + bits - 1) / 32; + /* Check if bits to be set exceed a word */ + if (idx != idx2) { + idx2 = 2 - idx2; /* flip */ + ale_entry[idx2] &= ~(BITMASK(bits + start - (idx2 * 32))); + ale_entry[idx2] |= (value >> ((idx2 * 32) - start)); + } start -= idx * 32; - idx = 2 - idx; /* flip */ + idx = 2 - idx; /* flip */ ale_entry[idx] &= ~(BITMASK(bits) << start); ale_entry[idx] |= (value << start); } From b37bc3b07eabe9853635b2accdcc9998a1bad0b1 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 12 Jul 2023 08:44:49 -0700 Subject: [PATCH 4209/4345] bridge: Add extack warning when enabling STP in netns. [ Upstream commit 56a16035bb6effb37177867cea94c13a8382f745 ] When we create an L2 loop on a bridge in netns, we will see packets storm even if STP is enabled. # unshare -n # ip link add br0 type bridge # ip link add veth0 type veth peer name veth1 # ip link set veth0 master br0 up # ip link set veth1 master br0 up # ip link set br0 type bridge stp_state 1 # ip link set br0 up # sleep 30 # ip -s link show br0 2: br0: mtu 1500 qdisc noqueue state UP mode DEFAULT group default qlen 1000 link/ether b6:61:98:1c:1c:b5 brd ff:ff:ff:ff:ff:ff RX: bytes packets errors dropped missed mcast 956553768 12861249 0 0 0 12861249 <-. Keep TX: bytes packets errors dropped carrier collsns | increasing 1027834 11951 0 0 0 0 <-' rapidly This is because llc_rcv() drops all packets in non-root netns and BPDU is dropped. Let's add extack warning when enabling STP in netns. # unshare -n # ip link add br0 type bridge # ip link set br0 type bridge stp_state 1 Warning: bridge: STP does not work in non-root netns. Note this commit will be reverted later when we namespacify the whole LLC infra. Fixes: e730c15519d0 ("[NET]: Make packet reception network namespace safe") Suggested-by: Harry Coin Link: https://lore.kernel.org/netdev/0f531295-e289-022d-5add-5ceffa0df9bc@quietfountain.com/ Suggested-by: Ido Schimmel Signed-off-by: Kuniyuki Iwashima Acked-by: Nikolay Aleksandrov Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/bridge/br_stp_if.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index ba55851fe132..3326dfced68a 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -201,6 +201,9 @@ int br_stp_set_enabled(struct net_bridge *br, unsigned long val, { ASSERT_RTNL(); + if (!net_eq(dev_net(br->dev), &init_net)) + NL_SET_ERR_MSG_MOD(extack, "STP does not work in non-root netns"); + if (br_mrp_enabled(br)) { NL_SET_ERR_MSG_MOD(extack, "STP can't be enabled if MRP is already enabled"); From a4635f190f332304db4a49e827ece790b804b5db Mon Sep 17 00:00:00 2001 From: Ding Hui Date: Tue, 9 May 2023 19:11:47 +0800 Subject: [PATCH 4210/4345] iavf: Fix use-after-free in free_netdev [ Upstream commit 5f4fa1672d98fe99d2297b03add35346f1685d6b ] We do netif_napi_add() for all allocated q_vectors[], but potentially do netif_napi_del() for part of them, then kfree q_vectors and leave invalid pointers at dev->napi_list. Reproducer: [root@host ~]# cat repro.sh #!/bin/bash pf_dbsf="0000:41:00.0" vf0_dbsf="0000:41:02.0" g_pids=() function do_set_numvf() { echo 2 >/sys/bus/pci/devices/${pf_dbsf}/sriov_numvfs sleep $((RANDOM%3+1)) echo 0 >/sys/bus/pci/devices/${pf_dbsf}/sriov_numvfs sleep $((RANDOM%3+1)) } function do_set_channel() { local nic=$(ls -1 --indicator-style=none /sys/bus/pci/devices/${vf0_dbsf}/net/) [ -z "$nic" ] && { sleep $((RANDOM%3)) ; return 1; } ifconfig $nic 192.168.18.5 netmask 255.255.255.0 ifconfig $nic up ethtool -L $nic combined 1 ethtool -L $nic combined 4 sleep $((RANDOM%3)) } function on_exit() { local pid for pid in "${g_pids[@]}"; do kill -0 "$pid" &>/dev/null && kill "$pid" &>/dev/null done g_pids=() } trap "on_exit; exit" EXIT while :; do do_set_numvf ; done & g_pids+=($!) while :; do do_set_channel ; done & g_pids+=($!) wait Result: [ 4093.900222] ================================================================== [ 4093.900230] BUG: KASAN: use-after-free in free_netdev+0x308/0x390 [ 4093.900232] Read of size 8 at addr ffff88b4dc145640 by task repro.sh/6699 [ 4093.900233] [ 4093.900236] CPU: 10 PID: 6699 Comm: repro.sh Kdump: loaded Tainted: G O --------- -t - 4.18.0 #1 [ 4093.900238] Hardware name: Powerleader PR2008AL/H12DSi-N6, BIOS 2.0 04/09/2021 [ 4093.900239] Call Trace: [ 4093.900244] dump_stack+0x71/0xab [ 4093.900249] print_address_description+0x6b/0x290 [ 4093.900251] ? free_netdev+0x308/0x390 [ 4093.900252] kasan_report+0x14a/0x2b0 [ 4093.900254] free_netdev+0x308/0x390 [ 4093.900261] iavf_remove+0x825/0xd20 [iavf] [ 4093.900265] pci_device_remove+0xa8/0x1f0 [ 4093.900268] device_release_driver_internal+0x1c6/0x460 [ 4093.900271] pci_stop_bus_device+0x101/0x150 [ 4093.900273] pci_stop_and_remove_bus_device+0xe/0x20 [ 4093.900275] pci_iov_remove_virtfn+0x187/0x420 [ 4093.900277] ? pci_iov_add_virtfn+0xe10/0xe10 [ 4093.900278] ? pci_get_subsys+0x90/0x90 [ 4093.900280] sriov_disable+0xed/0x3e0 [ 4093.900282] ? bus_find_device+0x12d/0x1a0 [ 4093.900290] i40e_free_vfs+0x754/0x1210 [i40e] [ 4093.900298] ? i40e_reset_all_vfs+0x880/0x880 [i40e] [ 4093.900299] ? pci_get_device+0x7c/0x90 [ 4093.900300] ? pci_get_subsys+0x90/0x90 [ 4093.900306] ? pci_vfs_assigned.part.7+0x144/0x210 [ 4093.900309] ? __mutex_lock_slowpath+0x10/0x10 [ 4093.900315] i40e_pci_sriov_configure+0x1fa/0x2e0 [i40e] [ 4093.900318] sriov_numvfs_store+0x214/0x290 [ 4093.900320] ? sriov_totalvfs_show+0x30/0x30 [ 4093.900321] ? __mutex_lock_slowpath+0x10/0x10 [ 4093.900323] ? __check_object_size+0x15a/0x350 [ 4093.900326] kernfs_fop_write+0x280/0x3f0 [ 4093.900329] vfs_write+0x145/0x440 [ 4093.900330] ksys_write+0xab/0x160 [ 4093.900332] ? __ia32_sys_read+0xb0/0xb0 [ 4093.900334] ? fput_many+0x1a/0x120 [ 4093.900335] ? filp_close+0xf0/0x130 [ 4093.900338] do_syscall_64+0xa0/0x370 [ 4093.900339] ? page_fault+0x8/0x30 [ 4093.900341] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 4093.900357] RIP: 0033:0x7f16ad4d22c0 [ 4093.900359] Code: 73 01 c3 48 8b 0d d8 cb 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 89 24 2d 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 fe dd 01 00 48 89 04 24 [ 4093.900360] RSP: 002b:00007ffd6491b7f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 4093.900362] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f16ad4d22c0 [ 4093.900363] RDX: 0000000000000002 RSI: 0000000001a41408 RDI: 0000000000000001 [ 4093.900364] RBP: 0000000001a41408 R08: 00007f16ad7a1780 R09: 00007f16ae1f2700 [ 4093.900364] R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000002 [ 4093.900365] R13: 0000000000000001 R14: 00007f16ad7a0620 R15: 0000000000000001 [ 4093.900367] [ 4093.900368] Allocated by task 820: [ 4093.900371] kasan_kmalloc+0xa6/0xd0 [ 4093.900373] __kmalloc+0xfb/0x200 [ 4093.900376] iavf_init_interrupt_scheme+0x63b/0x1320 [iavf] [ 4093.900380] iavf_watchdog_task+0x3d51/0x52c0 [iavf] [ 4093.900382] process_one_work+0x56a/0x11f0 [ 4093.900383] worker_thread+0x8f/0xf40 [ 4093.900384] kthread+0x2a0/0x390 [ 4093.900385] ret_from_fork+0x1f/0x40 [ 4093.900387] 0xffffffffffffffff [ 4093.900387] [ 4093.900388] Freed by task 6699: [ 4093.900390] __kasan_slab_free+0x137/0x190 [ 4093.900391] kfree+0x8b/0x1b0 [ 4093.900394] iavf_free_q_vectors+0x11d/0x1a0 [iavf] [ 4093.900397] iavf_remove+0x35a/0xd20 [iavf] [ 4093.900399] pci_device_remove+0xa8/0x1f0 [ 4093.900400] device_release_driver_internal+0x1c6/0x460 [ 4093.900401] pci_stop_bus_device+0x101/0x150 [ 4093.900402] pci_stop_and_remove_bus_device+0xe/0x20 [ 4093.900403] pci_iov_remove_virtfn+0x187/0x420 [ 4093.900404] sriov_disable+0xed/0x3e0 [ 4093.900409] i40e_free_vfs+0x754/0x1210 [i40e] [ 4093.900415] i40e_pci_sriov_configure+0x1fa/0x2e0 [i40e] [ 4093.900416] sriov_numvfs_store+0x214/0x290 [ 4093.900417] kernfs_fop_write+0x280/0x3f0 [ 4093.900418] vfs_write+0x145/0x440 [ 4093.900419] ksys_write+0xab/0x160 [ 4093.900420] do_syscall_64+0xa0/0x370 [ 4093.900421] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 4093.900422] 0xffffffffffffffff [ 4093.900422] [ 4093.900424] The buggy address belongs to the object at ffff88b4dc144200 which belongs to the cache kmalloc-8k of size 8192 [ 4093.900425] The buggy address is located 5184 bytes inside of 8192-byte region [ffff88b4dc144200, ffff88b4dc146200) [ 4093.900425] The buggy address belongs to the page: [ 4093.900427] page:ffffea00d3705000 refcount:1 mapcount:0 mapping:ffff88bf04415c80 index:0x0 compound_mapcount: 0 [ 4093.900430] flags: 0x10000000008100(slab|head) [ 4093.900433] raw: 0010000000008100 dead000000000100 dead000000000200 ffff88bf04415c80 [ 4093.900434] raw: 0000000000000000 0000000000030003 00000001ffffffff 0000000000000000 [ 4093.900434] page dumped because: kasan: bad access detected [ 4093.900435] [ 4093.900435] Memory state around the buggy address: [ 4093.900436] ffff88b4dc145500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900437] ffff88b4dc145580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900438] >ffff88b4dc145600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900438] ^ [ 4093.900439] ffff88b4dc145680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900440] ffff88b4dc145700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 4093.900440] ================================================================== Although the patch #2 (of 2) can avoid the issue triggered by this repro.sh, there still are other potential risks that if num_active_queues is changed to less than allocated q_vectors[] by unexpected, the mismatched netif_napi_add/del() can also cause UAF. Since we actually call netif_napi_add() for all allocated q_vectors unconditionally in iavf_alloc_q_vectors(), so we should fix it by letting netif_napi_del() match to netif_napi_add(). Fixes: 5eae00c57f5e ("i40evf: main driver core") Signed-off-by: Ding Hui Cc: Donglin Peng Cc: Huang Cun Reviewed-by: Simon Horman Reviewed-by: Madhu Chittim Reviewed-by: Leon Romanovsky Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index e45f3a1a11f3..b64801bc216b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1377,19 +1377,16 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) static void iavf_free_q_vectors(struct iavf_adapter *adapter) { int q_idx, num_q_vectors; - int napi_vectors; if (!adapter->q_vectors) return; num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; - napi_vectors = adapter->num_active_queues; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; - if (q_idx < napi_vectors) - netif_napi_del(&q_vector->napi); + netif_napi_del(&q_vector->napi); } kfree(adapter->q_vectors); adapter->q_vectors = NULL; From b92defe4e8ee86996c16417ad8c804cb4395fddd Mon Sep 17 00:00:00 2001 From: Ding Hui Date: Tue, 9 May 2023 19:11:48 +0800 Subject: [PATCH 4211/4345] iavf: Fix out-of-bounds when setting channels on remove [ Upstream commit 7c4bced3caa749ce468b0c5de711c98476b23a52 ] If we set channels greater during iavf_remove(), and waiting reset done would be timeout, then returned with error but changed num_active_queues directly, that will lead to OOB like the following logs. Because the num_active_queues is greater than tx/rx_rings[] allocated actually. Reproducer: [root@host ~]# cat repro.sh #!/bin/bash pf_dbsf="0000:41:00.0" vf0_dbsf="0000:41:02.0" g_pids=() function do_set_numvf() { echo 2 >/sys/bus/pci/devices/${pf_dbsf}/sriov_numvfs sleep $((RANDOM%3+1)) echo 0 >/sys/bus/pci/devices/${pf_dbsf}/sriov_numvfs sleep $((RANDOM%3+1)) } function do_set_channel() { local nic=$(ls -1 --indicator-style=none /sys/bus/pci/devices/${vf0_dbsf}/net/) [ -z "$nic" ] && { sleep $((RANDOM%3)) ; return 1; } ifconfig $nic 192.168.18.5 netmask 255.255.255.0 ifconfig $nic up ethtool -L $nic combined 1 ethtool -L $nic combined 4 sleep $((RANDOM%3)) } function on_exit() { local pid for pid in "${g_pids[@]}"; do kill -0 "$pid" &>/dev/null && kill "$pid" &>/dev/null done g_pids=() } trap "on_exit; exit" EXIT while :; do do_set_numvf ; done & g_pids+=($!) while :; do do_set_channel ; done & g_pids+=($!) wait Result: [ 3506.152887] iavf 0000:41:02.0: Removing device [ 3510.400799] ================================================================== [ 3510.400820] BUG: KASAN: slab-out-of-bounds in iavf_free_all_tx_resources+0x156/0x160 [iavf] [ 3510.400823] Read of size 8 at addr ffff88b6f9311008 by task repro.sh/55536 [ 3510.400823] [ 3510.400830] CPU: 101 PID: 55536 Comm: repro.sh Kdump: loaded Tainted: G O --------- -t - 4.18.0 #1 [ 3510.400832] Hardware name: Powerleader PR2008AL/H12DSi-N6, BIOS 2.0 04/09/2021 [ 3510.400835] Call Trace: [ 3510.400851] dump_stack+0x71/0xab [ 3510.400860] print_address_description+0x6b/0x290 [ 3510.400865] ? iavf_free_all_tx_resources+0x156/0x160 [iavf] [ 3510.400868] kasan_report+0x14a/0x2b0 [ 3510.400873] iavf_free_all_tx_resources+0x156/0x160 [iavf] [ 3510.400880] iavf_remove+0x2b6/0xc70 [iavf] [ 3510.400884] ? iavf_free_all_rx_resources+0x160/0x160 [iavf] [ 3510.400891] ? wait_woken+0x1d0/0x1d0 [ 3510.400895] ? notifier_call_chain+0xc1/0x130 [ 3510.400903] pci_device_remove+0xa8/0x1f0 [ 3510.400910] device_release_driver_internal+0x1c6/0x460 [ 3510.400916] pci_stop_bus_device+0x101/0x150 [ 3510.400919] pci_stop_and_remove_bus_device+0xe/0x20 [ 3510.400924] pci_iov_remove_virtfn+0x187/0x420 [ 3510.400927] ? pci_iov_add_virtfn+0xe10/0xe10 [ 3510.400929] ? pci_get_subsys+0x90/0x90 [ 3510.400932] sriov_disable+0xed/0x3e0 [ 3510.400936] ? bus_find_device+0x12d/0x1a0 [ 3510.400953] i40e_free_vfs+0x754/0x1210 [i40e] [ 3510.400966] ? i40e_reset_all_vfs+0x880/0x880 [i40e] [ 3510.400968] ? pci_get_device+0x7c/0x90 [ 3510.400970] ? pci_get_subsys+0x90/0x90 [ 3510.400982] ? pci_vfs_assigned.part.7+0x144/0x210 [ 3510.400987] ? __mutex_lock_slowpath+0x10/0x10 [ 3510.400996] i40e_pci_sriov_configure+0x1fa/0x2e0 [i40e] [ 3510.401001] sriov_numvfs_store+0x214/0x290 [ 3510.401005] ? sriov_totalvfs_show+0x30/0x30 [ 3510.401007] ? __mutex_lock_slowpath+0x10/0x10 [ 3510.401011] ? __check_object_size+0x15a/0x350 [ 3510.401018] kernfs_fop_write+0x280/0x3f0 [ 3510.401022] vfs_write+0x145/0x440 [ 3510.401025] ksys_write+0xab/0x160 [ 3510.401028] ? __ia32_sys_read+0xb0/0xb0 [ 3510.401031] ? fput_many+0x1a/0x120 [ 3510.401032] ? filp_close+0xf0/0x130 [ 3510.401038] do_syscall_64+0xa0/0x370 [ 3510.401041] ? page_fault+0x8/0x30 [ 3510.401043] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 3510.401073] RIP: 0033:0x7f3a9bb842c0 [ 3510.401079] Code: 73 01 c3 48 8b 0d d8 cb 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 89 24 2d 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 fe dd 01 00 48 89 04 24 [ 3510.401080] RSP: 002b:00007ffc05f1fe18 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 3510.401083] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f3a9bb842c0 [ 3510.401085] RDX: 0000000000000002 RSI: 0000000002327408 RDI: 0000000000000001 [ 3510.401086] RBP: 0000000002327408 R08: 00007f3a9be53780 R09: 00007f3a9c8a4700 [ 3510.401086] R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000002 [ 3510.401087] R13: 0000000000000001 R14: 00007f3a9be52620 R15: 0000000000000001 [ 3510.401090] [ 3510.401093] Allocated by task 76795: [ 3510.401098] kasan_kmalloc+0xa6/0xd0 [ 3510.401099] __kmalloc+0xfb/0x200 [ 3510.401104] iavf_init_interrupt_scheme+0x26f/0x1310 [iavf] [ 3510.401108] iavf_watchdog_task+0x1d58/0x4050 [iavf] [ 3510.401114] process_one_work+0x56a/0x11f0 [ 3510.401115] worker_thread+0x8f/0xf40 [ 3510.401117] kthread+0x2a0/0x390 [ 3510.401119] ret_from_fork+0x1f/0x40 [ 3510.401122] 0xffffffffffffffff [ 3510.401123] In timeout handling, we should keep the original num_active_queues and reset num_req_queues to 0. Fixes: 4e5e6b5d9d13 ("iavf: Fix return of set the new channel count") Signed-off-by: Ding Hui Cc: Donglin Peng Cc: Huang Cun Reviewed-by: Leon Romanovsky Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Signed-off-by: Sasha Levin --- drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 4680a2fe6d3c..05cd70579c16 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -968,7 +968,7 @@ static int iavf_set_channels(struct net_device *netdev, } if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; - adapter->num_active_queues = num_req; + adapter->num_req_queues = 0; return -EOPNOTSUPP; } From 5bc78ba88905fdd1f2fc4e848f0cdbb67fd7789b Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Wed, 14 Jun 2023 10:18:25 +0800 Subject: [PATCH 4212/4345] security: keys: Modify mismatched function name [ Upstream commit 2a4152742025c5f21482e8cebc581702a0fa5b01 ] No functional modification involved. security/keys/trusted-keys/trusted_tpm2.c:203: warning: expecting prototype for tpm_buf_append_auth(). Prototype was for tpm2_buf_append_auth() instead. Fixes: 2e19e10131a0 ("KEYS: trusted: Move TPM2 trusted keys code") Reported-by: Abaci Robot Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=5524 Signed-off-by: Jiapeng Chong Reviewed-by: Paul Moore Signed-off-by: Jarkko Sakkinen Signed-off-by: Sasha Levin --- security/keys/trusted-keys/trusted_tpm2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index 4c19d3abddbe..65f68856414a 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -21,7 +21,7 @@ static struct tpm2_hash tpm2_hash_map[] = { }; /** - * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. + * tpm2_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. * * @buf: an allocated tpm_buf instance * @session_handle: session handle From 41b00238699a7ed473bdd9f632bcd9f1aad2c09c Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Sun, 16 Jul 2023 15:07:41 +0530 Subject: [PATCH 4213/4345] octeontx2-pf: Dont allocate BPIDs for LBK interfaces [ Upstream commit 8fcd7c7b3a38ab5e452f542fda8f7940e77e479a ] Current driver enables backpressure for LBK interfaces. But these interfaces do not support this feature. Hence, this patch fixes the issue by skipping the backpressure configuration for these interfaces. Fixes: 75f36270990c ("octeontx2-pf: Support to enable/disable pause frames via ethtool"). Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Goutham Link: https://lore.kernel.org/r/20230716093741.28063-1-gakula@marvell.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 54aeb276b9a0..000dd89c4baf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1311,8 +1311,9 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) if (err) goto err_free_npa_lf; - /* Enable backpressure */ - otx2_nix_config_bp(pf, true); + /* Enable backpressure for CGX mapped PF/VFs */ + if (!is_otx2_lbkvf(pf->pdev)) + otx2_nix_config_bp(pf, true); /* Init Auras and pools used by NIX RQ, for free buffer ptrs */ err = otx2_rq_aura_pool_init(pf); From 937105d2b0bf024382de3f24eaf1966db7c9a0ff Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Jul 2023 14:44:45 +0000 Subject: [PATCH 4214/4345] tcp: annotate data-races around tcp_rsk(req)->ts_recent [ Upstream commit eba20811f32652bc1a52d5e7cc403859b86390d9 ] TCP request sockets are lockless, tcp_rsk(req)->ts_recent can change while being read by another cpu as syzbot noticed. This is harmless, but we should annotate the known races. Note that tcp_check_req() changes req->ts_recent a bit early, we might change this in the future. BUG: KCSAN: data-race in tcp_check_req / tcp_check_req write to 0xffff88813c8afb84 of 4 bytes by interrupt on cpu 1: tcp_check_req+0x694/0xc70 net/ipv4/tcp_minisocks.c:762 tcp_v4_rcv+0x12db/0x1b70 net/ipv4/tcp_ipv4.c:2071 ip_protocol_deliver_rcu+0x356/0x6d0 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x13c/0x1a0 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:303 [inline] ip_local_deliver+0xec/0x1c0 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:468 [inline] ip_rcv_finish net/ipv4/ip_input.c:449 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip_rcv+0x197/0x270 net/ipv4/ip_input.c:569 __netif_receive_skb_one_core net/core/dev.c:5493 [inline] __netif_receive_skb+0x90/0x1b0 net/core/dev.c:5607 process_backlog+0x21f/0x380 net/core/dev.c:5935 __napi_poll+0x60/0x3b0 net/core/dev.c:6498 napi_poll net/core/dev.c:6565 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6698 __do_softirq+0xc1/0x265 kernel/softirq.c:571 do_softirq+0x7e/0xb0 kernel/softirq.c:472 __local_bh_enable_ip+0x64/0x70 kernel/softirq.c:396 local_bh_enable+0x1f/0x20 include/linux/bottom_half.h:33 rcu_read_unlock_bh include/linux/rcupdate.h:843 [inline] __dev_queue_xmit+0xabb/0x1d10 net/core/dev.c:4271 dev_queue_xmit include/linux/netdevice.h:3088 [inline] neigh_hh_output include/net/neighbour.h:528 [inline] neigh_output include/net/neighbour.h:542 [inline] ip_finish_output2+0x700/0x840 net/ipv4/ip_output.c:229 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:317 NF_HOOK_COND include/linux/netfilter.h:292 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:431 dst_output include/net/dst.h:458 [inline] ip_local_out net/ipv4/ip_output.c:126 [inline] __ip_queue_xmit+0xa4d/0xa70 net/ipv4/ip_output.c:533 ip_queue_xmit+0x38/0x40 net/ipv4/ip_output.c:547 __tcp_transmit_skb+0x1194/0x16e0 net/ipv4/tcp_output.c:1399 tcp_transmit_skb net/ipv4/tcp_output.c:1417 [inline] tcp_write_xmit+0x13ff/0x2fd0 net/ipv4/tcp_output.c:2693 __tcp_push_pending_frames+0x6a/0x1a0 net/ipv4/tcp_output.c:2877 tcp_push_pending_frames include/net/tcp.h:1952 [inline] __tcp_sock_set_cork net/ipv4/tcp.c:3336 [inline] tcp_sock_set_cork+0xe8/0x100 net/ipv4/tcp.c:3343 rds_tcp_xmit_path_complete+0x3b/0x40 net/rds/tcp_send.c:52 rds_send_xmit+0xf8d/0x1420 net/rds/send.c:422 rds_send_worker+0x42/0x1d0 net/rds/threads.c:200 process_one_work+0x3e6/0x750 kernel/workqueue.c:2408 worker_thread+0x5f2/0xa10 kernel/workqueue.c:2555 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 read to 0xffff88813c8afb84 of 4 bytes by interrupt on cpu 0: tcp_check_req+0x32a/0xc70 net/ipv4/tcp_minisocks.c:622 tcp_v4_rcv+0x12db/0x1b70 net/ipv4/tcp_ipv4.c:2071 ip_protocol_deliver_rcu+0x356/0x6d0 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x13c/0x1a0 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:303 [inline] ip_local_deliver+0xec/0x1c0 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:468 [inline] ip_rcv_finish net/ipv4/ip_input.c:449 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip_rcv+0x197/0x270 net/ipv4/ip_input.c:569 __netif_receive_skb_one_core net/core/dev.c:5493 [inline] __netif_receive_skb+0x90/0x1b0 net/core/dev.c:5607 process_backlog+0x21f/0x380 net/core/dev.c:5935 __napi_poll+0x60/0x3b0 net/core/dev.c:6498 napi_poll net/core/dev.c:6565 [inline] net_rx_action+0x32b/0x750 net/core/dev.c:6698 __do_softirq+0xc1/0x265 kernel/softirq.c:571 run_ksoftirqd+0x17/0x20 kernel/softirq.c:939 smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164 kthread+0x1d7/0x210 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x1cd237f1 -> 0x1cd237f2 Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230717144445.653164-3-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_minisocks.c | 9 ++++++--- net/ipv4/tcp_output.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 4 files changed, 9 insertions(+), 6 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d62d5d7764ad..b40780fde791 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -960,7 +960,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, + READ_ONCE(req->ts_recent), 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 8d854feebdb0..01e27620b7ee 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -523,7 +523,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd; if (newtp->rx_opt.tstamp_ok) { - newtp->rx_opt.ts_recent = req->ts_recent; + newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { @@ -586,7 +586,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { - tmp_opt.ts_recent = req->ts_recent; + tmp_opt.ts_recent = READ_ONCE(req->ts_recent); if (tmp_opt.rcv_tsecr) tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off; /* We do not store true stamp, but it is not required, @@ -726,8 +726,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ + /* TODO: We probably should defer ts_recent change once + * we take ownership of @req. + */ if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - req->ts_recent = tmp_opt.rcv_tsval; + WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval); if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e4ad274ec7a3..86e896351364 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -874,7 +874,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; - opts->tsecr = req->ts_recent; + opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5392aebd48f1..79d6f6ea3c54 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1151,7 +1151,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, sk->sk_bound_dev_if, + READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority); } From 1a478ad1297a40675350d834871b8f6a4729eef6 Mon Sep 17 00:00:00 2001 From: Wang Ming Date: Mon, 17 Jul 2023 17:59:19 +0800 Subject: [PATCH 4215/4345] net: ipv4: Use kfree_sensitive instead of kfree [ Upstream commit daa751444fd9d4184270b1479d8af49aaf1a1ee6 ] key might contain private part of the key, so better use kfree_sensitive to free it. Fixes: 38320c70d282 ("[IPSEC]: Use crypto_aead and authenc in ESP") Signed-off-by: Wang Ming Reviewed-by: Tariq Toukan Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv4/esp4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 20d738137841..28252029bd79 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1134,7 +1134,7 @@ static int esp_init_authenc(struct xfrm_state *x) err = crypto_aead_setkey(aead, key, keylen); free_key: - kfree(key); + kfree_sensitive(key); error: return err; From d06fc7b39199e7d2930ff6de20e52fc6f0ee86f4 Mon Sep 17 00:00:00 2001 From: Yuanjun Gong Date: Mon, 17 Jul 2023 22:45:19 +0800 Subject: [PATCH 4216/4345] net:ipv6: check return value of pskb_trim() [ Upstream commit 4258faa130be4ea43e5e2d839467da421b8ff274 ] goto tx_err if an unexpected result is returned by pskb_tirm() in ip6erspan_tunnel_xmit(). Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support") Signed-off-by: Yuanjun Gong Reviewed-by: David Ahern Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- net/ipv6/ip6_gre.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 7b50e1811678..2df1036330f8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -955,7 +955,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto tx_err; truncate = true; } From bc9d4d432f78e3f7b37602eb96c2956b54703220 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 17 Jul 2023 14:59:18 -0700 Subject: [PATCH 4217/4345] Revert "tcp: avoid the lookup process failing to get sk in ehash table" [ Upstream commit 81b3ade5d2b98ad6e0a473b0e1e420a801275592 ] This reverts commit 3f4ca5fafc08881d7a57daa20449d171f2887043. Commit 3f4ca5fafc08 ("tcp: avoid the lookup process failing to get sk in ehash table") reversed the order in how a socket is inserted into ehash to fix an issue that ehash-lookup could fail when reqsk/full sk/twsk are swapped. However, it introduced another lookup failure. The full socket in ehash is allocated from a slab with SLAB_TYPESAFE_BY_RCU and does not have SOCK_RCU_FREE, so the socket could be reused even while it is being referenced on another CPU doing RCU lookup. Let's say a socket is reused and inserted into the same hash bucket during lookup. After the blamed commit, a new socket is inserted at the end of the list. If that happens, we will skip sockets placed after the previous position of the reused socket, resulting in ehash lookup failure. As described in Documentation/RCU/rculist_nulls.rst, we should insert a new socket at the head of the list to avoid such an issue. This issue, the swap-lookup-failure, and another variant reported in [0] can all be handled properly by adding a locked ehash lookup suggested by Eric Dumazet [1]. However, this issue could occur for every packet, thus more likely than the other two races, so let's revert the change for now. Link: https://lore.kernel.org/netdev/20230606064306.9192-1-duanmuquan@baidu.com/ [0] Link: https://lore.kernel.org/netdev/CANn89iK8snOz8TYOhhwfimC7ykYA78GA3Nyv8x06SZYa1nKdyA@mail.gmail.com/ [1] Fixes: 3f4ca5fafc08 ("tcp: avoid the lookup process failing to get sk in ehash table") Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230717215918.15723-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/inet_hashtables.c | 17 ++--------------- net/ipv4/inet_timewait_sock.c | 8 ++++---- 2 files changed, 6 insertions(+), 19 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 79bf550c9dfc..ad050f8476b8 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -571,20 +571,8 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_hashed(osk); - if (ret) { - /* Before deleting the node, we insert a new one to make - * sure that the look-up-sk process would not miss either - * of them and that at least one node would exist in ehash - * table all the time. Otherwise there's a tiny chance - * that lookup process could find nothing in ehash table. - */ - __sk_nulls_add_node_tail_rcu(sk, list); - sk_nulls_del_node_init_rcu(osk); - } - goto unlock; - } - if (found_dup_sk) { + ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -593,7 +581,6 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); -unlock: spin_unlock(lock); return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index a00102d7c7fd..c411c87ae865 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -81,10 +81,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_tail_rcu(&tw->tw_node, list); + hlist_nulls_add_head_rcu(&tw->tw_node, list); } static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -120,7 +120,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); - inet_twsk_add_node_tail_rcu(tw, &ehead->chain); + inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) From 49e435ca02c797e6e877bb79a9c3c3f580462fdb Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sat, 15 Jul 2023 16:16:56 +0800 Subject: [PATCH 4218/4345] fbdev: au1200fb: Fix missing IRQ check in au1200fb_drv_probe [ Upstream commit 4e88761f5f8c7869f15a2046b1a1116f4fab4ac8 ] This func misses checking for platform_get_irq()'s call and may passes the negative error codes to request_irq(), which takes unsigned IRQ #, causing it to fail with -EINVAL, overriding an original error code. Fix this by stop calling request_irq() with invalid IRQ #s. Fixes: 1630d85a8312 ("au1200fb: fix hardcoded IRQ") Signed-off-by: Zhang Shurong Signed-off-by: Helge Deller Signed-off-by: Sasha Levin --- drivers/video/fbdev/au1200fb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c index a8a0a448cdb5..80f54111baec 100644 --- a/drivers/video/fbdev/au1200fb.c +++ b/drivers/video/fbdev/au1200fb.c @@ -1732,6 +1732,9 @@ static int au1200fb_drv_probe(struct platform_device *dev) /* Now hook interrupt too */ irq = platform_get_irq(dev, 0); + if (irq < 0) + return irq; + ret = request_irq(irq, au1200fb_handle_irq, IRQF_SHARED, "lcd", (void *)dev); if (ret) { From a6f1988780a7c9e5f54a1d6d363db99e850106fc Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 18 Jul 2023 10:41:51 -0700 Subject: [PATCH 4219/4345] llc: Don't drop packet from non-root netns. [ Upstream commit 6631463b6e6673916d2481f692938f393148aa82 ] Now these upper layer protocol handlers can be called from llc_rcv() as sap->rcv_func(), which is registered by llc_sap_open(). * function which is passed to register_8022_client() -> no in-kernel user calls register_8022_client(). * snap_rcv() `- proto->rcvfunc() : registered by register_snap_client() -> aarp_rcv() and atalk_rcv() drop packets from non-root netns * stp_pdu_rcv() `- garp_protos[]->rcv() : registered by stp_proto_register() -> garp_pdu_rcv() and br_stp_rcv() are netns-aware So, we can safely remove the netns restriction in llc_rcv(). Fixes: e730c15519d0 ("[NET]: Make packet reception network namespace safe") Signed-off-by: Kuniyuki Iwashima Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin --- net/llc/llc_input.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index c309b72a5877..7cac441862e2 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -163,9 +163,6 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, void (*sta_handler)(struct sk_buff *skb); void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb); - if (!net_eq(dev_net(dev), &init_net)) - goto drop; - /* * When the interface is in promisc. mode, drop all the crap that it * receives, do not try to analyse it. From 533193a23914558127190e7bf7cb505ab6389acd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 20 Jul 2023 00:29:58 +0200 Subject: [PATCH 4220/4345] netfilter: nf_tables: fix spurious set element insertion failure [ Upstream commit ddbd8be68941985f166f5107109a90ce13147c44 ] On some platforms there is a padding hole in the nft_verdict structure, between the verdict code and the chain pointer. On element insertion, if the new element clashes with an existing one and NLM_F_EXCL flag isn't set, we want to ignore the -EEXIST error as long as the data associated with duplicated element is the same as the existing one. The data equality check uses memcmp. For normal data (NFT_DATA_VALUE) this works fine, but for NFT_DATA_VERDICT padding area leads to spurious failure even if the verdict data is the same. This then makes the insertion fail with 'already exists' error, even though the new "key : data" matches an existing entry and userspace told the kernel that it doesn't want to receive an error indication. Fixes: c016c7e45ddf ("netfilter: nf_tables: honor NLM_F_EXCL flag in set element insertion") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d56f5d7fa545..9c3a9e3f1ede 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8914,6 +8914,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (!tb[NFTA_VERDICT_CODE]) return -EINVAL; + + /* zero padding hole for memcmp */ + memset(data, 0, sizeof(*data)); data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { From 9c2df17e3cfc3e7674de20d3acf249c768400674 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 18 Jul 2023 01:30:33 +0200 Subject: [PATCH 4221/4345] netfilter: nf_tables: can't schedule in nft_chain_validate [ Upstream commit 314c82841602a111c04a7210c21dc77e0d560242 ] Can be called via nft set element list iteration, which may acquire rcu and/or bh read lock (depends on set type). BUG: sleeping function called from invalid context at net/netfilter/nf_tables_api.c:3353 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 1232, name: nft preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 2 locks held by nft/1232: #0: ffff8881180e3ea8 (&nft_net->commit_mutex){+.+.}-{3:3}, at: nf_tables_valid_genid #1: ffffffff83f5f540 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire Call Trace: nft_chain_validate nft_lookup_validate_setelem nft_pipapo_walk nft_lookup_validate nft_chain_validate nft_immediate_validate nft_chain_validate nf_tables_validate nf_tables_abort No choice but to move it to nf_tables_validate(). Fixes: 81ea01066741 ("netfilter: nf_tables: add rescheduling points during loop detection walks") Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9c3a9e3f1ede..a8d316a58e44 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3276,8 +3276,6 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } - - cond_resched(); } return 0; @@ -3301,6 +3299,8 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) err = nft_chain_validate(&ctx, chain); if (err < 0) return err; + + cond_resched(); } return 0; From 3a91099ecd59a42d1632fcb152bf7222f268ea2b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 19 Jul 2023 21:08:21 +0200 Subject: [PATCH 4222/4345] netfilter: nft_set_pipapo: fix improper element removal [ Upstream commit 87b5a5c209405cb6b57424cdfa226a6dbd349232 ] end key should be equal to start unless NFT_SET_EXT_KEY_END is present. Its possible to add elements that only have a start key ("{ 1.0.0.0 . 2.0.0.0 }") without an internval end. Insertion treats this via: if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) end = (const u8 *)nft_set_ext_key_end(ext)->data; else end = start; but removal side always uses nft_set_ext_key_end(). This is wrong and leads to garbage remaining in the set after removal next lookup/insert attempt will give: BUG: KASAN: slab-use-after-free in pipapo_get+0x8eb/0xb90 Read of size 1 at addr ffff888100d50586 by task nft-pipapo_uaf_/1399 Call Trace: kasan_report+0x105/0x140 pipapo_get+0x8eb/0xb90 nft_pipapo_insert+0x1dc/0x1710 nf_tables_newsetelem+0x31f5/0x4e00 .. Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Reported-by: lonial con Reviewed-by: Stefano Brivio Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nft_set_pipapo.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 7c759e9b4d84..3be93175b3ff 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1904,7 +1904,11 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, int i, start, rules_fx; match_start = data; - match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + + if (nft_set_ext_exists(&e->ext, NFT_SET_EXT_KEY_END)) + match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + else + match_end = data; start = first_rule; rules_fx = rules_f0; From 94c10c0fa51b78ae39af7f093c8d8db1fc39477e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 19 Jul 2023 20:19:43 +0200 Subject: [PATCH 4223/4345] netfilter: nf_tables: skip bound chain in netns release path [ Upstream commit 751d460ccff3137212f47d876221534bf0490996 ] Skip bound chain from netns release path, the rule that owns this chain releases these objects. Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a8d316a58e44..40ed4dd530c5 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9185,6 +9185,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { + if (nft_chain_is_bound(chain)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); From 30e5460d69e631c0e84db37dba2d8f98648778d4 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 20 Jul 2023 09:17:21 +0200 Subject: [PATCH 4224/4345] netfilter: nf_tables: skip bound chain on rule flush [ Upstream commit 6eaf41e87a223ae6f8e7a28d6e78384ad7e407f8 ] Skip bound chain when flushing table rules, the rule that owns this chain releases these objects. Otherwise, the following warning is triggered: WARNING: CPU: 2 PID: 1217 at net/netfilter/nf_tables_api.c:2013 nf_tables_chain_destroy+0x1f7/0x210 [nf_tables] CPU: 2 PID: 1217 Comm: chain-flush Not tainted 6.1.39 #1 RIP: 0010:nf_tables_chain_destroy+0x1f7/0x210 [nf_tables] Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: Kevin Rich Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin --- net/netfilter/nf_tables_api.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 40ed4dd530c5..356416564d9f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3611,6 +3611,8 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; + if (nft_chain_is_bound(chain)) + continue; ctx.chain = chain; err = nft_delrule_by_chain(&ctx); From 1d4f2c4be1365afdb1411884d71bf3b04a2c9b1e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:47 +0000 Subject: [PATCH 4225/4345] tcp: annotate data-races around tp->tcp_tx_delay [ Upstream commit 348b81b68b13ebd489a3e6a46aa1c384c731c919 ] do_tcp_getsockopt() reads tp->tcp_tx_delay while another cpu might change its value. Fixes: a842fe1425cb ("tcp: add optional per socket transmit delay") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-2-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cc42ceadc112..39919d1436ce 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3447,7 +3447,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); - tp->tcp_tx_delay = val; + WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; @@ -3902,7 +3902,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TX_DELAY: - val = tp->tcp_tx_delay; + val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: From 7b52a78a91fd3145909d5cc7ec3c727061e4ad21 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:49 +0000 Subject: [PATCH 4226/4345] tcp: annotate data-races around tp->keepalive_time [ Upstream commit 4164245c76ff906c9086758e1c3f87082a7f5ef5 ] do_tcp_getsockopt() reads tp->keepalive_time while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-4-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp.h | 7 +++++-- net/ipv4/tcp.c | 3 ++- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index e231101e5001..92de7c049f19 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1459,9 +1459,12 @@ static inline int keepalive_intvl_when(const struct tcp_sock *tp) static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_time ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */ + val = READ_ONCE(tp->keepalive_time); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 39919d1436ce..053e4880d8f0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3093,7 +3093,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val) if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; - tp->keepalive_time = val * HZ; + /* Paired with WRITE_ONCE() in keepalive_time_when() */ + WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); From 93715448f1162a54e86f93c18c6b4bb8a86bf4d9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:50 +0000 Subject: [PATCH 4227/4345] tcp: annotate data-races around tp->keepalive_intvl [ Upstream commit 5ecf9d4f52ff2f1d4d44c9b68bc75688e82f13b4 ] do_tcp_getsockopt() reads tp->keepalive_intvl while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-5-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp.h | 9 +++++++-- net/ipv4/tcp.c | 4 ++-- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 92de7c049f19..428f84f6e0d0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1451,9 +1451,14 @@ void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_intvl ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepintvl() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_intvl); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 053e4880d8f0..b5a05b098414 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3126,7 +3126,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_intvl = val * HZ; + WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); release_sock(sk); return 0; } @@ -3324,7 +3324,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPINTVL) err = -EINVAL; else - tp->keepalive_intvl = val * HZ; + WRITE_ONCE(tp->keepalive_intvl, val * HZ); break; case TCP_KEEPCNT: if (val < 1 || val > MAX_TCP_KEEPCNT) From a5c30a51876470499b068f752a89621f52a0d5e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:51 +0000 Subject: [PATCH 4228/4345] tcp: annotate data-races around tp->keepalive_probes [ Upstream commit 6e5e1de616bf5f3df1769abc9292191dfad9110a ] do_tcp_getsockopt() reads tp->keepalive_probes while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-6-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp.h | 9 +++++++-- net/ipv4/tcp.c | 5 +++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 428f84f6e0d0..be81a930b91f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1475,9 +1475,14 @@ static inline int keepalive_time_when(const struct tcp_sock *tp) static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_probes ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_probes); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b5a05b098414..80212bb0400c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3138,7 +3138,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_probes = val; + /* Paired with READ_ONCE() in keepalive_probes() */ + WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); release_sock(sk); return 0; } @@ -3330,7 +3331,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPCNT) err = -EINVAL; else - tp->keepalive_probes = val; + WRITE_ONCE(tp->keepalive_probes, val); break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT) From cf6c06ac74879726c88fe1ec013727006cdbdd58 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Sat, 12 Jun 2021 21:32:14 +0900 Subject: [PATCH 4229/4345] net: Introduce net.ipv4.tcp_migrate_req. [ Upstream commit f9ac779f881c2ec3d1cdcd7fa9d4f9442bf60e80 ] This commit adds a new sysctl option: net.ipv4.tcp_migrate_req. If this option is enabled or eBPF program is attached, we will be able to migrate child sockets from a listener to another in the same reuseport group after close() or shutdown() syscalls. Signed-off-by: Kuniyuki Iwashima Signed-off-by: Daniel Borkmann Reviewed-by: Benjamin Herrenschmidt Reviewed-by: Eric Dumazet Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210612123224.12525-2-kuniyu@amazon.co.jp Stable-dep-of: 3a037f0f3c4b ("tcp: annotate data-races around icsk->icsk_syn_retries") Signed-off-by: Sasha Levin --- Documentation/networking/ip-sysctl.rst | 25 +++++++++++++++++++++++++ include/net/netns/ipv4.h | 1 + net/ipv4/sysctl_net_ipv4.c | 9 +++++++++ 3 files changed, 35 insertions(+) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index df26cf4110ef..252212998378 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -713,6 +713,31 @@ tcp_syncookies - INTEGER network connections you can set this knob to 2 to enable unconditionally generation of syncookies. +tcp_migrate_req - BOOLEAN + The incoming connection is tied to a specific listening socket when + the initial SYN packet is received during the three-way handshake. + When a listener is closed, in-flight request sockets during the + handshake and established sockets in the accept queue are aborted. + + If the listener has SO_REUSEPORT enabled, other listeners on the + same port should have been able to accept such connections. This + option makes it possible to migrate such child sockets to another + listener after close() or shutdown(). + + The BPF_SK_REUSEPORT_SELECT_OR_MIGRATE type of eBPF program should + usually be used to define the policy to pick an alive listener. + Otherwise, the kernel will randomly pick an alive listener only if + this option is enabled. + + Note that migration between listeners with different settings may + crash applications. Let's say migration happens from listener A to + B, and only B has TCP_SAVE_SYN enabled. B cannot read SYN data from + the requests migrated from A. To avoid such a situation, cancel + migration by returning SK_DROP in the type of eBPF program, or + disable this option. + + Default: 0 + tcp_fastopen - INTEGER Enable TCP Fast Open (RFC7413) to send and accept data in the opening SYN packet. diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 4a4a5270ff6f..9b0d8649ae5b 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -131,6 +131,7 @@ struct netns_ipv4 { u8 sysctl_tcp_syn_retries; u8 sysctl_tcp_synack_retries; u8 sysctl_tcp_syncookies; + u8 sysctl_tcp_migrate_req; int sysctl_tcp_reordering; u8 sysctl_tcp_retries1; u8 sysctl_tcp_retries2; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 5aa8bde3e9c8..59ba518a85b9 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -878,6 +878,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dou8vec_minmax, }, #endif + { + .procname = "tcp_migrate_req", + .data = &init_net.ipv4.sysctl_tcp_migrate_req, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, { .procname = "tcp_reordering", .data = &init_net.ipv4.sysctl_tcp_reordering, From 7b0084918c5f7da21dbb91ec24da7a554edd3209 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 15 Jul 2022 10:17:46 -0700 Subject: [PATCH 4230/4345] tcp: Fix data-races around sysctl_tcp_syn(ack)?_retries. [ Upstream commit 20a3b1c0f603e8c55c3396abd12dfcfb523e4d3c ] While reading sysctl_tcp_syn(ack)?_retries, they can be changed concurrently. Thus, we need to add READ_ONCE() to their readers. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Stable-dep-of: 3a037f0f3c4b ("tcp: annotate data-races around icsk->icsk_syn_retries") Signed-off-by: Sasha Levin --- net/ipv4/inet_connection_sock.c | 3 ++- net/ipv4/tcp.c | 3 ++- net/ipv4/tcp_timer.c | 10 +++++++--- 3 files changed, 11 insertions(+), 5 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 406305aaec90..dfea3088bc7e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -740,7 +740,8 @@ static void reqsk_timer_handler(struct timer_list *t) if (inet_sk_state_load(sk_listener) != TCP_LISTEN) goto drop; - max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; + max_syn_ack_retries = icsk->icsk_syn_retries ? : + READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 80212bb0400c..fc4d560909b5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3743,7 +3743,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; + val = icsk->icsk_syn_retries ? : + READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: val = tp->linger2; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 888683f2ff3e..715fdfa3e2ae 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -239,7 +239,8 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) __dst_negative_advice(sk); - retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; + retry_until = icsk->icsk_syn_retries ? : + READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); expired = icsk->icsk_retransmits >= retry_until; } else { if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { @@ -406,12 +407,15 @@ abort: tcp_write_err(sk); static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); - int max_retries = icsk->icsk_syn_retries ? : - sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct tcp_sock *tp = tcp_sk(sk); + int max_retries; req->rsk_ops->syn_ack_timeout(req); + /* add one more retry for fastopen */ + max_retries = icsk->icsk_syn_retries ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; + if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; From 9168bd8f54c53020d642836abd6a20e6a682bce6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:52 +0000 Subject: [PATCH 4231/4345] tcp: annotate data-races around icsk->icsk_syn_retries [ Upstream commit 3a037f0f3c4bfe44518f2fbb478aa2f99a9cd8bb ] do_tcp_getsockopt() and reqsk_timer_handler() read icsk->icsk_syn_retries while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-7-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/tcp.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index dfea3088bc7e..5f71a1c74e7e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -740,7 +740,7 @@ static void reqsk_timer_handler(struct timer_list *t) if (inet_sk_state_load(sk_listener) != TCP_LISTEN) goto drop; - max_syn_ack_retries = icsk->icsk_syn_retries ? : + max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fc4d560909b5..e172348fc5c6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3072,7 +3072,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - inet_csk(sk)->icsk_syn_retries = val; + WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); release_sock(sk); return 0; } @@ -3337,7 +3337,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_SYNCNT) err = -EINVAL; else - icsk->icsk_syn_retries = val; + WRITE_ONCE(icsk->icsk_syn_retries, val); break; case TCP_SAVE_SYN: @@ -3743,7 +3743,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : + val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: From f891375eba6e24c3a077c07d13e418ba681e0dac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:53 +0000 Subject: [PATCH 4232/4345] tcp: annotate data-races around tp->linger2 [ Upstream commit 9df5335ca974e688389c875546e5819778a80d59 ] do_tcp_getsockopt() reads tp->linger2 while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-8-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e172348fc5c6..f7c951463d9c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3350,11 +3350,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_LINGER2: if (val < 0) - tp->linger2 = -1; + WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) - tp->linger2 = TCP_FIN_TIMEOUT_MAX; + WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else - tp->linger2 = val * HZ; + WRITE_ONCE(tp->linger2, val * HZ); break; case TCP_DEFER_ACCEPT: @@ -3747,7 +3747,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: - val = tp->linger2; + val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; From 9c786d5faf3ad271138c14655bfc9f642d6c0c92 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:54 +0000 Subject: [PATCH 4233/4345] tcp: annotate data-races around rskq_defer_accept [ Upstream commit ae488c74422fb1dcd807c0201804b3b5e8a322a3 ] do_tcp_getsockopt() reads rskq_defer_accept while another cpu might change its value. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-9-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f7c951463d9c..50d674d35e52 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3359,9 +3359,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ - icsk->icsk_accept_queue.rskq_defer_accept = - secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, - TCP_RTO_MAX / HZ); + WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ)); break; case TCP_WINDOW_CLAMP: @@ -3752,8 +3752,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: - val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, - TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); + val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); + val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; From 3cf0a0f11d39e183000df4ce090409181834b677 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:55 +0000 Subject: [PATCH 4234/4345] tcp: annotate data-races around tp->notsent_lowat [ Upstream commit 1aeb87bc1440c5447a7fa2d6e3c2cca52cbd206b ] tp->notsent_lowat can be read locklessly from do_tcp_getsockopt() and tcp_poll(). Fixes: c9bee3b7fdec ("tcp: TCP_NOTSENT_LOWAT socket option") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-10-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/net/tcp.h | 6 +++++- net/ipv4/tcp.c | 4 ++-- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index be81a930b91f..dcca41f3a224 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1991,7 +1991,11 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); + u32 val; + + val = READ_ONCE(tp->notsent_lowat); + + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } /* @wake is one when sk_stream_write_space() calls us. diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 50d674d35e52..8a441dfd258d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3437,7 +3437,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; + WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: @@ -3913,7 +3913,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = tcp_time_stamp_raw() + tp->tsoffset; break; case TCP_NOTSENT_LOWAT: - val = tp->notsent_lowat; + val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; From d01afbfc2f7df4fc943edd5414589cdc1bffb4bd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:56 +0000 Subject: [PATCH 4235/4345] tcp: annotate data-races around icsk->icsk_user_timeout [ Upstream commit 26023e91e12c68669db416b97234328a03d8e499 ] This field can be read locklessly from do_tcp_getsockopt() Fixes: dca43c75e7e5 ("tcp: Add TCP_USER_TIMEOUT socket option.") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-11-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- net/ipv4/tcp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8a441dfd258d..0a5f61b3423b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3081,7 +3081,7 @@ EXPORT_SYMBOL(tcp_sock_set_syncnt); void tcp_sock_set_user_timeout(struct sock *sk, u32 val) { lock_sock(sk); - inet_csk(sk)->icsk_user_timeout = val; + WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_user_timeout); @@ -3393,7 +3393,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 0) err = -EINVAL; else - icsk->icsk_user_timeout = val; + WRITE_ONCE(icsk->icsk_user_timeout, val); break; case TCP_FASTOPEN: @@ -3890,7 +3890,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_USER_TIMEOUT: - val = icsk->icsk_user_timeout; + val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: From e0ac63e194f49a5b5e7b79b8017635b3c49f1994 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 19 Jul 2023 21:28:57 +0000 Subject: [PATCH 4236/4345] tcp: annotate data-races around fastopenq.max_qlen [ Upstream commit 70f360dd7042cb843635ece9d28335a4addff9eb ] This field can be read locklessly. Fixes: 1536e2857bd3 ("tcp: Add a TCP_FASTOPEN socket option to get a max backlog on its listner") Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230719212857.3943972-12-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- include/linux/tcp.h | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_fastopen.c | 6 ++++-- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 6e3340379d85..11a98144bda0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -473,7 +473,7 @@ static inline void fastopen_queue_tune(struct sock *sk, int backlog) struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn); - queue->fastopenq.max_qlen = min_t(unsigned int, backlog, somaxconn); + WRITE_ONCE(queue->fastopenq.max_qlen, min_t(unsigned int, backlog, somaxconn)); } static inline void tcp_move_syn(struct tcp_sock *tp, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0a5f61b3423b..3dd9b76f4055 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3894,7 +3894,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - val = icsk->icsk_accept_queue.fastopenq.max_qlen; + val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 39fb037ce5f3..92d63cf3e50b 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -312,6 +312,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; + int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying @@ -324,10 +325,11 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; - if (fastopenq->max_qlen == 0) + max_qlen = READ_ONCE(fastopenq->max_qlen); + if (max_qlen == 0) return false; - if (fastopenq->qlen >= fastopenq->max_qlen) { + if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; From e3da59f428200bf109fda878e95d1023647a5bd7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 20 Jul 2023 03:02:31 +0300 Subject: [PATCH 4237/4345] net: phy: prevent stale pointer dereference in phy_init() [ Upstream commit 1c613beaf877c0c0d755853dc62687e2013e55c4 ] mdio_bus_init() and phy_driver_register() both have error paths, and if those are ever hit, ethtool will have a stale pointer to the phy_ethtool_phy_ops stub structure, which references memory from a module that failed to load (phylib). It is probably hard to force an error in this code path even manually, but the error teardown path of phy_init() should be the same as phy_exit(), which is now simply not the case. Fixes: 55d8f053ce1b ("net: phy: Register ethtool PHY operations") Link: https://lore.kernel.org/netdev/ZLaiJ4G6TaJYGJyU@shell.armlinux.org.uk/ Suggested-by: Russell King (Oracle) Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230720000231.1939689-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin --- drivers/net/phy/phy_device.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index e771e0e8a9bc..095d16ceafcf 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3024,23 +3024,30 @@ static int __init phy_init(void) { int rc; + ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops); + rc = mdio_bus_init(); if (rc) - return rc; + goto err_ethtool_phy_ops; - ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops); features_init(); rc = phy_driver_register(&genphy_c45_driver, THIS_MODULE); if (rc) - goto err_c45; + goto err_mdio_bus; rc = phy_driver_register(&genphy_driver, THIS_MODULE); - if (rc) { - phy_driver_unregister(&genphy_c45_driver); + if (rc) + goto err_c45; + + return 0; + err_c45: - mdio_bus_exit(); - } + phy_driver_unregister(&genphy_c45_driver); +err_mdio_bus: + mdio_bus_exit(); +err_ethtool_phy_ops: + ethtool_set_ethtool_phy_ops(NULL); return rc; } From 43e786aa51b80e5856c8f1c4ad46a5784364ebe6 Mon Sep 17 00:00:00 2001 From: Mohamed Khalfella Date: Fri, 14 Jul 2023 20:33:41 +0000 Subject: [PATCH 4238/4345] tracing/histograms: Return an error if we fail to add histogram to hist_vars list commit 4b8b3905165ef98386a3c06f196c85d21292d029 upstream. Commit 6018b585e8c6 ("tracing/histograms: Add histograms to hist_vars if they have referenced variables") added a check to fail histogram creation if save_hist_vars() failed to add histogram to hist_vars list. But the commit failed to set ret to failed return code before jumping to unregister histogram, fix it. Link: https://lore.kernel.org/linux-trace-kernel/20230714203341.51396-1-mkhalfella@purestorage.com Cc: stable@vger.kernel.org Fixes: 6018b585e8c6 ("tracing/histograms: Add histograms to hist_vars if they have referenced variables") Signed-off-by: Mohamed Khalfella Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_events_hist.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index ae71cefb46bb..059a106e62be 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5822,7 +5822,8 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, goto out_unreg; if (has_hist_vars(hist_data) || hist_data->n_var_refs) { - if (save_hist_vars(hist_data)) + ret = save_hist_vars(hist_data); + if (ret) goto out_unreg; } From 1a1e793e021d75cd0accd8f329ec9456e5cd105e Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Thu, 13 Jul 2023 22:14:35 +0800 Subject: [PATCH 4239/4345] tracing: Fix memory leak of iter->temp when reading trace_pipe commit d5a821896360cc8b93a15bd888fabc858c038dc0 upstream. kmemleak reports: unreferenced object 0xffff88814d14e200 (size 256): comm "cat", pid 336, jiffies 4294871818 (age 779.490s) hex dump (first 32 bytes): 04 00 01 03 00 00 00 00 08 00 00 00 00 00 00 00 ................ 0c d8 c8 9b ff ff ff ff 04 5a ca 9b ff ff ff ff .........Z...... backtrace: [] __kmalloc+0x4f/0x140 [] trace_find_next_entry+0xbb/0x1d0 [] trace_print_lat_context+0xaf/0x4e0 [] print_trace_line+0x3e0/0x950 [] tracing_read_pipe+0x2d9/0x5a0 [] vfs_read+0x143/0x520 [] ksys_read+0xbd/0x160 [] do_syscall_64+0x3f/0x90 [] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 when reading file 'trace_pipe', 'iter->temp' is allocated or relocated in trace_find_next_entry() but not freed before 'trace_pipe' is closed. To fix it, free 'iter->temp' in tracing_release_pipe(). Link: https://lore.kernel.org/linux-trace-kernel/20230713141435.1133021-1-zhengyejian1@huawei.com Cc: stable@vger.kernel.org Fixes: ff895103a84ab ("tracing: Save off entry when peeking at next entry") Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) [Fix conflict due to lack of 649e72070cbbb8600eb823833e4748f5a0815116] Signed-off-by: Zheng Yejian Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4dd8c16f023b..7867fc39c4fc 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6250,6 +6250,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) mutex_unlock(&trace_types_lock); free_cpumask_var(iter->started); + kfree(iter->temp); mutex_destroy(&iter->mutex); kfree(iter); From 115b19f8935339b69635fae7e1530b3bff262e40 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 1 Apr 2021 16:14:17 -0400 Subject: [PATCH 4240/4345] ftrace: Store the order of pages allocated in ftrace_page commit db42523b4f3e83ff86b53cdda219a9767c8b047f upstream. Instead of saving the size of the records field of the ftrace_page, store the order it uses to allocate the pages, as that is what is needed to know in order to free the pages. This simplifies the code. Link: https://lore.kernel.org/lkml/CAHk-=whyMxheOqXAORt9a7JK9gc9eHTgCJ55Pgs4p=X3RrQubQ@mail.gmail.com/ Signed-off-by: Linus Torvalds [ change log written by Steven Rostedt ] Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Zheng Yejian Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ftrace.c | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3dab978c156d..acba76c0c5c3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1091,7 +1091,7 @@ struct ftrace_page { struct ftrace_page *next; struct dyn_ftrace *records; int index; - int size; + int order; }; #define ENTRY_SIZE sizeof(struct dyn_ftrace) @@ -3188,7 +3188,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) ftrace_number_of_groups++; cnt = (PAGE_SIZE << order) / ENTRY_SIZE; - pg->size = cnt; + pg->order = order; if (cnt > count) cnt = count; @@ -3201,7 +3201,6 @@ ftrace_allocate_pages(unsigned long num_to_init) { struct ftrace_page *start_pg; struct ftrace_page *pg; - int order; int cnt; if (!num_to_init) @@ -3237,13 +3236,13 @@ ftrace_allocate_pages(unsigned long num_to_init) free_pages: pg = start_pg; while (pg) { - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - if (order >= 0) - free_pages((unsigned long)pg->records, order); + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } start_pg = pg->next; kfree(pg); pg = start_pg; - ftrace_number_of_pages -= 1 << order; ftrace_number_of_groups--; } pr_info("ftrace: FAILED to allocate memory for functions\n"); @@ -6239,6 +6238,7 @@ static int ftrace_process_locs(struct module *mod, p = start; pg = start_pg; while (p < end) { + unsigned long end_offset; addr = ftrace_call_adjust(*p++); /* * Some architecture linkers will pad between @@ -6249,7 +6249,8 @@ static int ftrace_process_locs(struct module *mod, if (!addr) continue; - if (pg->index == pg->size) { + end_offset = (pg->index+1) * sizeof(pg->records[0]); + if (end_offset > PAGE_SIZE << pg->order) { /* We should have allocated enough */ if (WARN_ON(!pg->next)) break; @@ -6418,7 +6419,6 @@ void ftrace_release_mod(struct module *mod) struct ftrace_page **last_pg; struct ftrace_page *tmp_page = NULL; struct ftrace_page *pg; - int order; mutex_lock(&ftrace_lock); @@ -6469,12 +6469,12 @@ void ftrace_release_mod(struct module *mod) /* Needs to be called outside of ftrace_lock */ clear_mod_from_hashes(pg); - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - if (order >= 0) - free_pages((unsigned long)pg->records, order); + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } tmp_page = pg->next; kfree(pg); - ftrace_number_of_pages -= 1 << order; ftrace_number_of_groups--; } } @@ -6792,7 +6792,6 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) struct ftrace_mod_map *mod_map = NULL; struct ftrace_init_func *func, *func_next; struct list_head clear_hash; - int order; INIT_LIST_HEAD(&clear_hash); @@ -6830,10 +6829,10 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) ftrace_update_tot_cnt--; if (!pg->index) { *last_pg = pg->next; - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - if (order >= 0) - free_pages((unsigned long)pg->records, order); - ftrace_number_of_pages -= 1 << order; + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } ftrace_number_of_groups--; kfree(pg); pg = container_of(last_pg, struct ftrace_page, next); From edce5fba78ccf7ddf8a74906339225383fe54811 Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Wed, 12 Jul 2023 14:04:52 +0800 Subject: [PATCH 4241/4345] ftrace: Fix possible warning on checking all pages used in ftrace_process_locs() commit 26efd79c4624294e553aeaa3439c646729bad084 upstream. As comments in ftrace_process_locs(), there may be NULL pointers in mcount_loc section: > Some architecture linkers will pad between > the different mcount_loc sections of different > object files to satisfy alignments. > Skip any NULL pointers. After commit 20e5227e9f55 ("ftrace: allow NULL pointers in mcount_loc"), NULL pointers will be accounted when allocating ftrace pages but skipped before adding into ftrace pages, this may result in some pages not being used. Then after commit 706c81f87f84 ("ftrace: Remove extra helper functions"), warning may occur at: WARN_ON(pg->next); To fix it, only warn for case that no pointers skipped but pages not used up, then free those unused pages after releasing ftrace_lock. Link: https://lore.kernel.org/linux-trace-kernel/20230712060452.3175675-1-zhengyejian1@huawei.com Cc: stable@vger.kernel.org Fixes: 706c81f87f84 ("ftrace: Remove extra helper functions") Suggested-by: Steven Rostedt Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman --- kernel/trace/ftrace.c | 45 +++++++++++++++++++++++++++++-------------- 1 file changed, 31 insertions(+), 14 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index acba76c0c5c3..31fec924b7c4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3196,6 +3196,22 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) return cnt; } +static void ftrace_free_pages(struct ftrace_page *pages) +{ + struct ftrace_page *pg = pages; + + while (pg) { + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } + pages = pg->next; + kfree(pg); + pg = pages; + ftrace_number_of_groups--; + } +} + static struct ftrace_page * ftrace_allocate_pages(unsigned long num_to_init) { @@ -3234,17 +3250,7 @@ ftrace_allocate_pages(unsigned long num_to_init) return start_pg; free_pages: - pg = start_pg; - while (pg) { - if (pg->records) { - free_pages((unsigned long)pg->records, pg->order); - ftrace_number_of_pages -= 1 << pg->order; - } - start_pg = pg->next; - kfree(pg); - pg = start_pg; - ftrace_number_of_groups--; - } + ftrace_free_pages(start_pg); pr_info("ftrace: FAILED to allocate memory for functions\n"); return NULL; } @@ -6190,9 +6196,11 @@ static int ftrace_process_locs(struct module *mod, unsigned long *start, unsigned long *end) { + struct ftrace_page *pg_unuse = NULL; struct ftrace_page *start_pg; struct ftrace_page *pg; struct dyn_ftrace *rec; + unsigned long skipped = 0; unsigned long count; unsigned long *p; unsigned long addr; @@ -6246,8 +6254,10 @@ static int ftrace_process_locs(struct module *mod, * object files to satisfy alignments. * Skip any NULL pointers. */ - if (!addr) + if (!addr) { + skipped++; continue; + } end_offset = (pg->index+1) * sizeof(pg->records[0]); if (end_offset > PAGE_SIZE << pg->order) { @@ -6261,8 +6271,10 @@ static int ftrace_process_locs(struct module *mod, rec->ip = addr; } - /* We should have used all pages */ - WARN_ON(pg->next); + if (pg->next) { + pg_unuse = pg->next; + pg->next = NULL; + } /* Assign the last page to ftrace_pages */ ftrace_pages = pg; @@ -6284,6 +6296,11 @@ static int ftrace_process_locs(struct module *mod, out: mutex_unlock(&ftrace_lock); + /* We should have used all pages unless we skipped some */ + if (pg_unuse) { + WARN_ON(!skipped); + ftrace_free_pages(pg_unuse); + } return ret; } From 3602dbc57b556eff2456715301d35a1ef8964bba Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 27 Jul 2023 08:44:44 +0200 Subject: [PATCH 4242/4345] Linux 5.10.188 Link: https://lore.kernel.org/r/20230725104553.588743331@linuxfoundation.org Tested-by: Jon Hunter Tested-by: Shuah Khan Tested-by: Florian Fainelli Link: https://lore.kernel.org/r/20230726045328.327600022@linuxfoundation.org Tested-by: Linux Kernel Functional Testing Tested-by: Florian Fainelli Tested-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 2aaf3b0b9250..7f9e1667d87d 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 187 +SUBLEVEL = 188 EXTRAVERSION = NAME = Dare mighty things From 8e164a95fb357a2e237a2b1457fa88182270ebbc Mon Sep 17 00:00:00 2001 From: Vatsal Parasrampuria Date: Thu, 3 Aug 2023 12:49:24 +0000 Subject: [PATCH 4243/4345] ANDROID: GKI: Update symbols to symbol list Leaf changes summary: 2 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 1 Added function Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 1 Added variable 1 Added function: [A] 'function int __traceiter_android_vh_wakeup_bypass(void*, int*)' 1 Added variable: [A] 'tracepoint __tracepoint_android_vh_wakeup_bypass' Bug: 225120081 Change-Id: Ica87e21b53ab0736c4d1f9e8b44443ea881c5f2a Signed-off-by: Vatsal Parasrampuria --- android/abi_gki_aarch64.xml | 4688 +++++++++++++++++---------------- android/abi_gki_aarch64_zebra | 3 + build.config.gki.aarch64 | 1 + 3 files changed, 2350 insertions(+), 2342 deletions(-) create mode 100644 android/abi_gki_aarch64_zebra diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index af1caade63e1..431d1d2eb876 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -710,6 +710,7 @@ + @@ -6782,6 +6783,7 @@ + @@ -7046,12 +7048,12 @@ - + - + - + @@ -7308,14 +7310,6 @@ - - - - - - - - @@ -7559,15 +7553,15 @@ - + - + - + - + @@ -7941,71 +7935,71 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -8528,12 +8522,12 @@ - + - + - + @@ -8758,6 +8752,14 @@ + + + + + + + + @@ -8789,12 +8791,12 @@ - + - + - + @@ -9485,12 +9487,12 @@ - + - + - + @@ -9995,7 +9997,7 @@ - + @@ -10004,7 +10006,7 @@ - + @@ -10839,13 +10841,13 @@ - + - + - + @@ -12335,18 +12337,18 @@ - + - + - + - + - + @@ -12780,21 +12782,21 @@ - + - + - + - + - + - + @@ -12887,15 +12889,15 @@ - + - + - + - + @@ -13768,12 +13770,12 @@ - + - + - + @@ -14744,12 +14746,12 @@ - + - + - + @@ -15294,45 +15296,45 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -16563,12 +16565,12 @@ - + - + - + @@ -17376,69 +17378,69 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -17462,18 +17464,18 @@ - + - + - + - + - + @@ -18801,7 +18803,7 @@ - + @@ -19180,12 +19182,12 @@ - + - + - + @@ -22129,12 +22131,12 @@ - + - + - + @@ -22395,18 +22397,18 @@ - + - + - + - + - + @@ -23816,12 +23818,12 @@ - + - + - + @@ -24546,9 +24548,6 @@ - - - @@ -24972,27 +24971,27 @@ - + - + - + - + - + - + - + - + @@ -25304,7 +25303,7 @@ - + @@ -25421,27 +25420,27 @@ - + - + - + - + - + - + - + - + @@ -26838,12 +26837,12 @@ - + - + - + @@ -26865,15 +26864,15 @@ - + - + - + - + @@ -27219,18 +27218,18 @@ - + - + - + - + - + @@ -27435,12 +27434,12 @@ - + - + - + @@ -28803,198 +28802,198 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -31153,12 +31152,12 @@ - + - + - + @@ -31666,12 +31665,12 @@ - + - + - + @@ -32063,7 +32062,7 @@ - + @@ -32216,36 +32215,36 @@ - + - + - + - + - + - + - + - + - + - + - + @@ -34693,18 +34692,18 @@ - + - + - + - + - + @@ -36094,153 +36093,153 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -37209,12 +37208,12 @@ - + - + - + @@ -37436,12 +37435,12 @@ - + - + - + @@ -38733,18 +38732,18 @@ - + - + - + - + - + @@ -39657,60 +39656,60 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -42293,435 +42292,435 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -43202,7 +43201,7 @@ - + @@ -43953,7 +43952,7 @@ - + @@ -44656,23 +44655,7 @@ - - - - - - - - - - - - - - - - - + @@ -44734,7 +44717,7 @@ - + @@ -45375,15 +45358,15 @@ - + - + - + - + @@ -49012,7 +48995,6 @@ - @@ -49915,33 +49897,33 @@ - + - + - + - + - + - + - + - + - + - + @@ -52005,12 +51987,12 @@ - + - + - + @@ -52385,162 +52367,162 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -53970,13 +53952,6 @@ - - - - - - - @@ -54261,12 +54236,12 @@ - + - + - + @@ -54709,24 +54684,24 @@ - + - + - + - + - + - + - + @@ -56402,21 +56377,21 @@ - + - + - + - + - + - + @@ -56908,12 +56883,12 @@ - + - + - + @@ -57292,39 +57267,39 @@ - + - + - + - + - + - + - + - + - + - + - + - + @@ -57581,75 +57556,75 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -59166,15 +59141,15 @@ - + - + - + - + @@ -61774,7 +61749,7 @@ - + @@ -63224,21 +63199,21 @@ - + - + - + - + - + - + @@ -63890,12 +63865,12 @@ - + - + - + @@ -65126,7 +65101,26 @@ - + + + + + + + + + + + + + + + + + + + + @@ -66575,33 +66569,33 @@ - + - + - + - + - + - + - + - + - + - + @@ -66623,13 +66617,6 @@ - - - - - - - @@ -70679,7 +70666,7 @@ - + @@ -70767,7 +70754,7 @@ - + @@ -70799,12 +70786,12 @@ - + - + - + @@ -71629,17 +71616,7 @@ - - - - - - - - - - - + @@ -72514,45 +72491,45 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -73494,12 +73471,12 @@ - + - + - + @@ -75220,12 +75197,12 @@ - + - + - + @@ -76591,18 +76568,18 @@ - + - + - + - + - + @@ -78349,18 +78326,18 @@ - + - + - + - + - + @@ -78739,234 +78716,234 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -80452,108 +80429,108 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -80600,12 +80577,12 @@ - + - + - + @@ -81205,21 +81182,21 @@ - + - + - + - + - + - + @@ -81242,7 +81219,7 @@ - + @@ -81732,12 +81709,12 @@ - + - + - + @@ -82604,15 +82581,15 @@ - + - + - + - + @@ -83846,15 +83823,15 @@ - + - + - + - + @@ -84066,240 +84043,240 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -84811,18 +84788,18 @@ - + - + - + - + - + @@ -87549,12 +87526,12 @@ - + - + - + @@ -88419,9 +88396,9 @@ - + - + @@ -91431,7 +91408,6 @@ - @@ -92313,15 +92289,15 @@ - + - + - + - + @@ -92765,12 +92741,12 @@ - + - + - + @@ -93717,15 +93693,15 @@ - + - + - + - + @@ -94433,18 +94409,18 @@ - + - + - + - + - + @@ -96303,12 +96279,12 @@ - + - + - + @@ -98073,9 +98049,9 @@ - + - + @@ -98340,18 +98316,18 @@ - + - + - + - + - + @@ -99137,15 +99113,15 @@ - + - + - + - + @@ -100099,15 +100075,15 @@ - + - + - + - + @@ -101178,12 +101154,12 @@ - + - + - + @@ -101592,18 +101568,18 @@ - + - + - + - + - + @@ -103199,12 +103175,6 @@ - - - - - - @@ -105776,18 +105746,18 @@ - + - + - + - + - + @@ -106032,12 +106002,12 @@ - + - + - + @@ -106611,7 +106581,29 @@ - + + + + + + + + + + + + + + + + + + + + + + + @@ -108747,12 +108739,12 @@ - + - + - + @@ -108797,30 +108789,30 @@ - + - + - + - + - + - + - + - + - + @@ -109537,6 +109529,13 @@ + + + + + + + @@ -110488,36 +110487,36 @@ - + - + - + - + - + - + - + - + - + - + - + @@ -110756,12 +110755,12 @@ - + - + - + @@ -111422,7 +111421,6 @@ - @@ -112626,15 +112624,15 @@ - + - + - + - + @@ -112784,9 +112782,9 @@ - + - + @@ -113910,78 +113908,78 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -114000,7 +113998,7 @@ - + @@ -114809,18 +114807,18 @@ - + - + - + - + - + @@ -114929,33 +114927,33 @@ - + - + - + - + - + - + - + - + - + - + @@ -115648,15 +115646,15 @@ - + - + - + - + @@ -116496,9 +116494,9 @@ - + - + @@ -116878,16 +116876,16 @@ - - - - - + + + + + - - - + + + @@ -116895,14 +116893,14 @@ - - - + + + - - - + + + @@ -117543,9 +117541,9 @@ - - - + + + @@ -117611,8 +117609,8 @@ - - + + @@ -117647,21 +117645,21 @@ - - + + - - + + - - - + + + @@ -117670,8 +117668,8 @@ - - + + @@ -117681,11 +117679,11 @@ - - - - - + + + + + @@ -117713,13 +117711,13 @@ - - - - - - - + + + + + + + @@ -117732,12 +117730,12 @@ - - + + - - + + @@ -117872,8 +117870,8 @@ - - + + @@ -118021,9 +118019,9 @@ - - - + + + @@ -118086,8 +118084,8 @@ - - + + @@ -118106,10 +118104,10 @@ - - - - + + + + @@ -118144,9 +118142,9 @@ - - - + + + @@ -120849,6 +120847,11 @@ + + + + + @@ -121691,6 +121694,7 @@ + @@ -121763,10 +121767,10 @@ - - - - + + + + @@ -121796,16 +121800,16 @@ - - - - - - - - - - + + + + + + + + + + @@ -121834,12 +121838,12 @@ - - - - - - + + + + + + @@ -121978,11 +121982,11 @@ - - - - - + + + + + @@ -122063,10 +122067,10 @@ - - - - + + + + @@ -122253,11 +122257,11 @@ - - - - - + + + + + @@ -122303,9 +122307,9 @@ - - - + + + @@ -122336,31 +122340,31 @@ - - + + - - - - + + + + - - - + + + - - - + + + - - + + - + @@ -122414,13 +122418,13 @@ - - - - - - - + + + + + + + @@ -122434,12 +122438,12 @@ - - - - - - + + + + + + @@ -122691,17 +122695,17 @@ - - + + - - + + - - - + + + @@ -123511,130 +123515,130 @@ - - - - - - - - - - - - - - - - - - - - + - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - + + + + + - - - - - + + + + + + - - - - - - + + + + + + + - - - - - - - + + + + + + + + - - - - - - - - + + + + + + + + + - - - - - - - - - + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + @@ -123686,17 +123690,17 @@ - - - + + + - - + + - - + + @@ -123763,9 +123767,9 @@ - - - + + + @@ -124578,8 +124582,8 @@ - - + + @@ -124614,9 +124618,9 @@ - - - + + + @@ -124954,9 +124958,9 @@ - - - + + + @@ -125092,14 +125096,14 @@ - - + + - - - - + + + + @@ -125136,8 +125140,8 @@ - - + + @@ -125145,13 +125149,13 @@ - - + + - - - + + + @@ -125190,12 +125194,12 @@ - - - - - - + + + + + + @@ -125204,20 +125208,20 @@ - - - + + + - - - + + + - - - - + + + + @@ -125250,9 +125254,9 @@ - - - + + + @@ -125286,13 +125290,13 @@ - - + + - - - + + + @@ -125385,14 +125389,14 @@ - - - - + + + + - - + + @@ -125411,9 +125415,9 @@ - - - + + + @@ -125447,13 +125451,13 @@ - - + + - - - + + + @@ -125859,16 +125863,16 @@ - - - - + + + + - - - - + + + + @@ -125903,9 +125907,9 @@ - - - + + + @@ -125937,9 +125941,9 @@ - - - + + + @@ -126283,19 +126287,19 @@ - - + + - - - - + + + + - - - + + + @@ -126442,8 +126446,8 @@ - - + + @@ -126556,19 +126560,19 @@ - - - + + + - - - + + + - - - + + + @@ -126618,8 +126622,8 @@ - - + + @@ -127285,15 +127289,15 @@ - - - + + + - - - - + + + + @@ -128172,8 +128176,8 @@ - - + + @@ -128413,8 +128417,8 @@ - - + + @@ -128794,24 +128798,24 @@ - - - + + + - - - + + + - - - + + + - - - + + + @@ -128819,9 +128823,9 @@ - - - + + + @@ -130026,8 +130030,8 @@ - - + + @@ -130071,27 +130075,27 @@ - - + + - + - - + + - - + + - - + + @@ -130986,16 +130990,16 @@ - - - - + + + + - - - - + + + + @@ -131684,8 +131688,8 @@ - - + + @@ -132007,8 +132011,8 @@ - - + + @@ -132449,14 +132453,14 @@ - - - + + + - - - + + + @@ -132572,15 +132576,15 @@ - + - - + + - - + + @@ -132664,8 +132668,8 @@ - - + + @@ -134051,8 +134055,8 @@ - - + + @@ -134662,12 +134666,12 @@ - - - - - - + + + + + + @@ -135176,7 +135180,7 @@ - + @@ -135531,119 +135535,119 @@ - - - + + + - - - - + + + + - - - - + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + - + - - - - - - - - - - - - - - - - - - - - + - + - - - - - + + + + - - - - + + + + - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -135816,9 +135820,9 @@ - - - + + + @@ -136074,18 +136078,18 @@ - - - + + + - - - + + + - - + + @@ -136094,10 +136098,10 @@ - - - - + + + + @@ -137015,8 +137019,8 @@ - - + + @@ -137135,11 +137139,11 @@ - - - - - + + + + + @@ -137147,9 +137151,9 @@ - - - + + + @@ -137157,27 +137161,27 @@ - - + + - - - + + + - - - + + + - - + + - - + + @@ -137186,16 +137190,16 @@ - - - + + + - - - - - + + + + + @@ -137203,9 +137207,9 @@ - - - + + + @@ -137213,55 +137217,55 @@ - - + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - + + + + @@ -137269,43 +137273,43 @@ - - - - + + + + - - + + - - - + + + - - + + - - - - + + + + - - - + + + - - - + + + @@ -137317,79 +137321,79 @@ - - + + - - + + - - - - - + + + + + - - + + - - + + - - + + - - + + - - + + - - + + - - - + + + - - - + + + - - - - + + + + - - - + + + - - + + - - + + - - - - - + + + + + @@ -137410,12 +137414,12 @@ - - + + - - + + @@ -137425,21 +137429,21 @@ - - + + - - + + - - - + + + @@ -137448,26 +137452,26 @@ - - - + + + - - - - + + + + - - - + + + - - - - + + + + @@ -137725,9 +137729,9 @@ - - - + + + @@ -137792,19 +137796,19 @@ - - - - + + + + - - - + + + @@ -138744,10 +138748,10 @@ - - - - + + + + @@ -140490,95 +140494,95 @@ - - - - + + + + - - - + + + - - + + - - - + + + - - - - - + + + + + - - + + - - - - + + + + - + - - - - + + + + - - + + - - - + + + - - + + - - - - + + + + - - - - + + + + - - - - + + + + - - - - + + + + - - + + - - + + @@ -140854,8 +140858,8 @@ - - + + @@ -141079,7 +141083,7 @@ - + @@ -141096,7 +141100,7 @@ - + @@ -141115,8 +141119,8 @@ - - + + @@ -141128,7 +141132,7 @@ - + @@ -141152,20 +141156,20 @@ - - + + - - + + - - + + - - + + @@ -141226,34 +141230,34 @@ - - - + + + - - - + + + - - - - + + + + - - + + - - - - + + + + @@ -141321,12 +141325,12 @@ - - + + - - + + @@ -141373,17 +141377,17 @@ - - - + + + - - + + - - + + @@ -141407,8 +141411,8 @@ - - + + @@ -141417,18 +141421,18 @@ - - - - - + + + + + - - - - - + + + + + @@ -141446,18 +141450,18 @@ - - - + + + - - - - - - - + + + + + + + @@ -141477,65 +141481,65 @@ - - - - + + + + - - - - + + + + - - - - - + + + + + - - - - - + + + + + - - - - - + + + + + - - - - + + + + - - - - + + + + - - - - + + + + - - - - - - - - + + + + + + + + @@ -141544,29 +141548,29 @@ - - - + + + - - - + + + - - - + + + - - - - + + + + - - + + @@ -141574,34 +141578,34 @@ - - + + - - - + + + - - + + - - + + - - - + + + @@ -141609,60 +141613,60 @@ - - + + - - + + - - + + - - + + - - - + + + - - + + - - + + - - + + - - - - + + + + - - - + + + @@ -141704,24 +141708,24 @@ - - - - + + + + - - + + - - - + + + - - - + + + @@ -141734,10 +141738,10 @@ - - - - + + + + @@ -141746,24 +141750,24 @@ - - - + + + - - - + + + - - - - + + + + @@ -141771,34 +141775,34 @@ - - - - + + + + - - - - + + + + - - - + + + - - + + - - + + - - - + + + @@ -142327,7 +142331,7 @@ - + @@ -142530,11 +142534,11 @@ - - - - - + + + + + @@ -142601,38 +142605,38 @@ - - + + - - + + - - - - + + + + - - + + - - + + - - + + - - + + - - + + @@ -142703,8 +142707,8 @@ - - + + @@ -142723,23 +142727,23 @@ - - + + - - - - - + + + + + - - + + - - + + @@ -142826,8 +142830,8 @@ - - + + @@ -143309,49 +143313,49 @@ - - + + - - - - + + + + - - - - - + + + + + - - - + + + - - - - + + + + - - + + - - + + - - - + + + @@ -143362,12 +143366,12 @@ - - + + - - + + @@ -143378,9 +143382,9 @@ - - - + + + @@ -143704,8 +143708,8 @@ - - + + @@ -143761,7 +143765,7 @@ - + @@ -143779,7 +143783,7 @@ - + @@ -143846,8 +143850,8 @@ - - + + @@ -143866,9 +143870,9 @@ - - - + + + @@ -143923,9 +143927,9 @@ - - - + + + @@ -143939,10 +143943,10 @@ - - - - + + + + @@ -144015,9 +144019,9 @@ - - - + + + @@ -144058,7 +144062,7 @@ - + @@ -144934,9 +144938,9 @@ - - - + + + @@ -145225,7 +145229,7 @@ - + @@ -145498,17 +145502,17 @@ - - + + - - - + + + - - + + @@ -145827,7 +145831,7 @@ - + @@ -145859,18 +145863,18 @@ - - - + + + - - - + + + @@ -145879,8 +145883,8 @@ - - + + @@ -145903,26 +145907,26 @@ - - - + + + - - + + - + - + - + @@ -146162,34 +146166,34 @@ - - + + - - - + + + - - - + + + - - - - - - - - - + + + + + + + + + - - - + + + @@ -146245,21 +146249,21 @@ - - + + - - + + - - + + - - - + + + @@ -146267,36 +146271,36 @@ - - - + + + - - + + - - + + - - + + - - + + - - - - - + + + + + - - + + @@ -146407,12 +146411,12 @@ - - + + - - + + @@ -146673,9 +146677,9 @@ - - - + + + @@ -146943,22 +146947,22 @@ - - + + - - - - + + + + - - + + @@ -146968,114 +146972,114 @@ - - + + - - + + - - + + - - - - - + + + + + - - - - + + + + - - + + - - + + - - + + - - - - + + + + - - - - - + + + + + - - + + - - + + - - + + - - - + + + - - - + + + - - - + + + - - - + + + - - - + + + - - - - + + + + - - - + + + - - + + - - + + - - + + @@ -147677,21 +147681,21 @@ - - + + - - + + - - - + + + @@ -147738,12 +147742,12 @@ - - + + - - + + @@ -147813,17 +147817,17 @@ - - - - - + + + + + - - - - + + + + @@ -148075,20 +148079,20 @@ - - - + + + - - - - - + + + + + @@ -148179,8 +148183,8 @@ - - + + @@ -148202,8 +148206,8 @@ - - + + @@ -148314,9 +148318,9 @@ - - - + + + @@ -148398,8 +148402,8 @@ - - + + @@ -148414,8 +148418,8 @@ - - + + @@ -150153,7 +150157,7 @@ - + @@ -150244,7 +150248,7 @@ - + @@ -150391,9 +150395,9 @@ - - - + + + @@ -150529,15 +150533,15 @@ - - - - + + + + - - - + + + @@ -150561,19 +150565,19 @@ - - - + + + - - - - + + + + @@ -150586,13 +150590,13 @@ - - - + + + - - + + @@ -150610,9 +150614,9 @@ - - - + + + @@ -150635,14 +150639,14 @@ - - - + + + - - - + + + @@ -150663,8 +150667,8 @@ - - + + @@ -150672,9 +150676,9 @@ - - - + + + @@ -150687,8 +150691,8 @@ - - + + diff --git a/android/abi_gki_aarch64_zebra b/android/abi_gki_aarch64_zebra new file mode 100644 index 000000000000..2ca38a60d508 --- /dev/null +++ b/android/abi_gki_aarch64_zebra @@ -0,0 +1,3 @@ +[abi_symbol_list] + __traceiter_android_vh_wakeup_bypass + __tracepoint_android_vh_wakeup_bypass diff --git a/build.config.gki.aarch64 b/build.config.gki.aarch64 index 1134cb881e0e..ba3c113c45cf 100644 --- a/build.config.gki.aarch64 +++ b/build.config.gki.aarch64 @@ -32,6 +32,7 @@ android/abi_gki_aarch64_unisoc android/abi_gki_aarch64_virtual_device android/abi_gki_aarch64_vivo android/abi_gki_aarch64_xiaomi +android/abi_gki_aarch64_zebra android/abi_gki_aarch64_asus android/abi_gki_aarch64_transsion android/abi_gki_aarch64_tuxera From 986fd89af0659a1295fde5aecbb4e2784cc00a43 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 3 Aug 2023 14:26:32 +0000 Subject: [PATCH 4244/4345] Revert "Revert "8250: add support for ASIX devices with a FIFO bug"" This reverts commit 5f4a1111ad04ad08d582f6452779b3371b227192 which is commit a82d62f708545d22859584e0e0620da8e3759bbc upstream. It changes the serial port ABI, which Android cares about. As the issue isn't really a problem at all for any Android devices, just revert it keeping the fix present for now, to preserve the abi. Bug: 161946584 Change-Id: Ie9b3f9aa8e705c63680fb9556e579e6241589d74 Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250.h | 1 + drivers/tty/serial/8250/8250_pci.c | 19 +++++++++++++++++++ drivers/tty/serial/8250/8250_port.c | 11 ++++++++--- include/linux/serial_8250.h | 1 + 4 files changed, 29 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 61b11490ae5b..0771cd226581 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -87,6 +87,7 @@ struct serial8250_config { #define UART_BUG_TXEN (1 << 1) /* UART has buggy TX IIR status */ #define UART_BUG_NOMSR (1 << 2) /* UART has buggy MSR status bits (Au1x00) */ #define UART_BUG_THRE (1 << 3) /* UART has buggy THRE reassertion */ +#define UART_BUG_PARITY (1 << 4) /* UART mishandles parity if FIFO enabled */ #define UART_BUG_TXRACE (1 << 5) /* UART Tx fails to set remote DR */ diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index fd857d434326..9617f7ad332d 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1044,6 +1044,14 @@ static int pci_oxsemi_tornado_init(struct pci_dev *dev) return number_uarts; } +static int pci_asix_setup(struct serial_private *priv, + const struct pciserial_board *board, + struct uart_8250_port *port, int idx) +{ + port->bugs |= UART_BUG_PARITY; + return pci_default_setup(priv, board, port, idx); +} + /* Quatech devices have their own extra interface features */ struct quatech_feature { @@ -1866,6 +1874,7 @@ pci_moxa_setup(struct serial_private *priv, #define PCI_DEVICE_ID_WCH_CH355_4S 0x7173 #define PCI_VENDOR_ID_AGESTAR 0x5372 #define PCI_DEVICE_ID_AGESTAR_9375 0x6872 +#define PCI_VENDOR_ID_ASIX 0x9710 #define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 0x818e @@ -2675,6 +2684,16 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .exit = pci_wch_ch38x_exit, .setup = pci_wch_ch38x_setup, }, + /* + * ASIX devices with FIFO bug + */ + { + .vendor = PCI_VENDOR_ID_ASIX, + .device = PCI_ANY_ID, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_asix_setup, + }, /* * Broadcom TruManage (NetXtreme) */ diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 1d92fb550f6b..a47a9577ff06 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2574,8 +2574,11 @@ static unsigned char serial8250_compute_lcr(struct uart_8250_port *up, if (c_cflag & CSTOPB) cval |= UART_LCR_STOP; - if (c_cflag & PARENB) + if (c_cflag & PARENB) { cval |= UART_LCR_PARITY; + if (up->bugs & UART_BUG_PARITY) + up->fifo_bug = true; + } if (!(c_cflag & PARODD)) cval |= UART_LCR_EPAR; #ifdef CMSPAR @@ -2738,7 +2741,8 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, up->lcr = cval; /* Save computed LCR */ if (up->capabilities & UART_CAP_FIFO && port->fifosize > 1) { - if (baud < 2400 && !up->dma) { + /* NOTE: If fifo_bug is not set, a user can set RX_trigger. */ + if ((baud < 2400 && !up->dma) || up->fifo_bug) { up->fcr &= ~UART_FCR_TRIGGER_MASK; up->fcr |= UART_FCR_TRIGGER_1; } @@ -3074,7 +3078,8 @@ static int do_set_rxtrig(struct tty_port *port, unsigned char bytes) struct uart_8250_port *up = up_to_u8250p(uport); int rxtrig; - if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1) + if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1 || + up->fifo_bug) return -EINVAL; rxtrig = bytes_to_fcr_rxtrig(up, bytes); diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 870bb036b2a7..2b70f736b091 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -97,6 +97,7 @@ struct uart_8250_port { struct list_head list; /* ports on this IRQ */ u32 capabilities; /* port capabilities */ unsigned short bugs; /* port bugs */ + bool fifo_bug; /* min RX trigger if enabled */ unsigned int tx_loadsz; /* transmit fifo load size */ unsigned char acr; unsigned char fcr; From 938b8658b91ab8620b244cabd83153450628ef24 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Aug 2023 07:19:15 +0000 Subject: [PATCH 4245/4345] Revert "posix-timers: Ensure timer ID search-loop limit is valid" This reverts commit 322377cc909defcca9451487484845e7e1d20d1b which is commit 8ce8849dd1e78dadcee0ec9acbd259d239b7069f upstream. It breaks the Android abi. If it is required in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: I44be0f7b4df730e599bf80939b6d40d4f8d04a57 Signed-off-by: Greg Kroah-Hartman --- include/linux/sched/signal.h | 2 +- kernel/time/posix-timers.c | 31 +++++++++++++------------------ 2 files changed, 14 insertions(+), 19 deletions(-) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3ed7cfd16a06..fb0b3899a86f 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -126,7 +126,7 @@ struct signal_struct { #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ - unsigned int next_posix_timer_id; + int posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 29569b1c3d8c..6d12a724d2b6 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -140,30 +140,25 @@ static struct k_itimer *posix_timer_by_id(timer_t id) static int posix_timer_add(struct k_itimer *timer) { struct signal_struct *sig = current->signal; + int first_free_id = sig->posix_timer_id; struct hlist_head *head; - unsigned int cnt, id; + int ret = -ENOENT; - /* - * FIXME: Replace this by a per signal struct xarray once there is - * a plan to handle the resulting CRIU regression gracefully. - */ - for (cnt = 0; cnt <= INT_MAX; cnt++) { + do { spin_lock(&hash_lock); - id = sig->next_posix_timer_id; - - /* Write the next ID back. Clamp it to the positive space */ - sig->next_posix_timer_id = (id + 1) & INT_MAX; - - head = &posix_timers_hashtable[hash(sig, id)]; - if (!__posix_timers_find(head, sig, id)) { + head = &posix_timers_hashtable[hash(sig, sig->posix_timer_id)]; + if (!__posix_timers_find(head, sig, sig->posix_timer_id)) { hlist_add_head_rcu(&timer->t_hash, head); - spin_unlock(&hash_lock); - return id; + ret = sig->posix_timer_id; } + if (++sig->posix_timer_id < 0) + sig->posix_timer_id = 0; + if ((sig->posix_timer_id == first_free_id) && (ret == -ENOENT)) + /* Loop over all possible ids completed */ + ret = -EAGAIN; spin_unlock(&hash_lock); - } - /* POSIX return code when no timer ID could be allocated */ - return -EAGAIN; + } while (ret == -ENOENT); + return ret; } static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) From 08315eedaa6931251b08ddfbaaef9e3a63420665 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Aug 2023 07:21:31 +0000 Subject: [PATCH 4246/4345] Revert "tcp: annotate data-races around icsk->icsk_syn_retries" This reverts commit 9168bd8f54c53020d642836abd6a20e6a682bce6 which is commit 3a037f0f3c4bfe44518f2fbb478aa2f99a9cd8bb upstream. It breaks the Android abi. If it is required in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: Id57985508ae583aa995368a9efe6d27083a9fa01 Signed-off-by: Greg Kroah-Hartman --- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/tcp.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e7807e939a2d..e6dcbe971398 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -740,7 +740,7 @@ static void reqsk_timer_handler(struct timer_list *t) if (inet_sk_state_load(sk_listener) != TCP_LISTEN) goto drop; - max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : + max_syn_ack_retries = icsk->icsk_syn_retries ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a85f90f16387..c2e1ab8fd1f5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3045,7 +3045,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); + inet_csk(sk)->icsk_syn_retries = val; release_sock(sk); return 0; } @@ -3310,7 +3310,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_SYNCNT) err = -EINVAL; else - WRITE_ONCE(icsk->icsk_syn_retries, val); + icsk->icsk_syn_retries = val; break; case TCP_SAVE_SYN: @@ -3716,7 +3716,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = READ_ONCE(icsk->icsk_syn_retries) ? : + val = icsk->icsk_syn_retries ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: From 2afed824a4df1bef1aba1b3e76c2c95c2f9400dd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Aug 2023 07:21:40 +0000 Subject: [PATCH 4247/4345] Revert "tcp: Fix data-races around sysctl_tcp_syn(ack)?_retries." This reverts commit 7b0084918c5f7da21dbb91ec24da7a554edd3209 which is commit 20a3b1c0f603e8c55c3396abd12dfcfb523e4d3c upstream. It breaks the Android abi. If it is required in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: Id6fdb41a7797ed851cc37b4fe141fc69a069b640 Signed-off-by: Greg Kroah-Hartman --- net/ipv4/inet_connection_sock.c | 3 +-- net/ipv4/tcp.c | 3 +-- net/ipv4/tcp_timer.c | 10 +++------- 3 files changed, 5 insertions(+), 11 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e6dcbe971398..4fbc23e1e640 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -740,8 +740,7 @@ static void reqsk_timer_handler(struct timer_list *t) if (inet_sk_state_load(sk_listener) != TCP_LISTEN) goto drop; - max_syn_ack_retries = icsk->icsk_syn_retries ? : - READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); + max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c2e1ab8fd1f5..c430e2511513 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3716,8 +3716,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : - READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); + val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; break; case TCP_LINGER2: val = READ_ONCE(tp->linger2); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 715fdfa3e2ae..888683f2ff3e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -239,8 +239,7 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) __dst_negative_advice(sk); - retry_until = icsk->icsk_syn_retries ? : - READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); + retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; expired = icsk->icsk_retransmits >= retry_until; } else { if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { @@ -407,15 +406,12 @@ abort: tcp_write_err(sk); static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); + int max_retries = icsk->icsk_syn_retries ? : + sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct tcp_sock *tp = tcp_sk(sk); - int max_retries; req->rsk_ops->syn_ack_timeout(req); - /* add one more retry for fastopen */ - max_retries = icsk->icsk_syn_retries ? : - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; - if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; From 64414277da82dcb26dd03186d4e2c41f280e2be2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Aug 2023 07:22:29 +0000 Subject: [PATCH 4248/4345] Revert "net: Introduce net.ipv4.tcp_migrate_req." This reverts commit cf6c06ac74879726c88fe1ec013727006cdbdd58 which is commit f9ac779f881c2ec3d1cdcd7fa9d4f9442bf60e80 upstream. It breaks the Android abi. If it is required in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: Ia4d18c9acdd553b1806ca844c47e34a76f6c6b93 Signed-off-by: Greg Kroah-Hartman --- Documentation/networking/ip-sysctl.rst | 25 ------------------------- include/net/netns/ipv4.h | 1 - net/ipv4/sysctl_net_ipv4.c | 9 --------- 3 files changed, 35 deletions(-) diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index d0bf386d1239..eedce7474ad3 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -711,31 +711,6 @@ tcp_syncookies - INTEGER network connections you can set this knob to 2 to enable unconditionally generation of syncookies. -tcp_migrate_req - BOOLEAN - The incoming connection is tied to a specific listening socket when - the initial SYN packet is received during the three-way handshake. - When a listener is closed, in-flight request sockets during the - handshake and established sockets in the accept queue are aborted. - - If the listener has SO_REUSEPORT enabled, other listeners on the - same port should have been able to accept such connections. This - option makes it possible to migrate such child sockets to another - listener after close() or shutdown(). - - The BPF_SK_REUSEPORT_SELECT_OR_MIGRATE type of eBPF program should - usually be used to define the policy to pick an alive listener. - Otherwise, the kernel will randomly pick an alive listener only if - this option is enabled. - - Note that migration between listeners with different settings may - crash applications. Let's say migration happens from listener A to - B, and only B has TCP_SAVE_SYN enabled. B cannot read SYN data from - the requests migrated from A. To avoid such a situation, cancel - migration by returning SK_DROP in the type of eBPF program, or - disable this option. - - Default: 0 - tcp_fastopen - INTEGER Enable TCP Fast Open (RFC7413) to send and accept data in the opening SYN packet. diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 084ced1e9446..fb94551d03e6 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -133,7 +133,6 @@ struct netns_ipv4 { int sysctl_tcp_syn_retries; int sysctl_tcp_synack_retries; int sysctl_tcp_syncookies; - u8 sysctl_tcp_migrate_req; int sysctl_tcp_reordering; int sysctl_tcp_retries1; int sysctl_tcp_retries2; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index eb5a96d905b4..3e3542bb8be6 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -884,15 +884,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, #endif - { - .procname = "tcp_migrate_req", - .data = &init_net.ipv4.sysctl_tcp_migrate_req, - .maxlen = sizeof(u8), - .mode = 0644, - .proc_handler = proc_dou8vec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE - }, { .procname = "tcp_reordering", .data = &init_net.ipv4.sysctl_tcp_reordering, From 117f73f9a7f1d30d44463b15051bcfaaacdba24f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Aug 2023 11:35:33 +0000 Subject: [PATCH 4249/4345] Revert "sctp: add bpf_bypass_getsockopt proto callback" This reverts commit b190ced50a5e98a604e9d029080f93ea78d63400 which is commit 2598619e012cee5273a2821441b9a051ad931249 upstream. It breaks the Android abi. If it is required in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: Idc0dcb0bd8bec4f81b6a66e99f68b724558a1a73 Signed-off-by: Greg Kroah-Hartman --- net/sctp/socket.c | 18 ------------------ 1 file changed, 18 deletions(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index bf470a046e05..4d2c54daae58 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8044,22 +8044,6 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, return retval; } -static bool sctp_bpf_bypass_getsockopt(int level, int optname) -{ - if (level == SOL_SCTP) { - switch (optname) { - case SCTP_SOCKOPT_PEELOFF: - case SCTP_SOCKOPT_PEELOFF_FLAGS: - case SCTP_SOCKOPT_CONNECTX3: - return true; - default: - return false; - } - } - - return false; -} - static int sctp_hash(struct sock *sk) { /* STUB */ @@ -9428,7 +9412,6 @@ struct proto sctp_prot = { .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, - .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, @@ -9481,7 +9464,6 @@ struct proto sctpv6_prot = { .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, - .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt, .sendmsg = sctp_sendmsg, .recvmsg = sctp_recvmsg, .bind = sctp_bind, From 49c25af89c6ad02b60a1a2bcbe16ecef330782cf Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 4 Aug 2023 11:35:54 +0000 Subject: [PATCH 4250/4345] Revert "bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE" This reverts commit 08f61a34913558e06576e7b6318bf583f273c1be which is commit 9cacf81f8161111db25f98e78a7a0e32ae142b3f upstream. It breaks the Android abi. If it is required in the future, it can come back in an abi-safe way. Bug: 161946584 Change-Id: I83c4a094c650eee44a2f7160aab6ccc6e442e726 Signed-off-by: Greg Kroah-Hartman --- include/linux/bpf-cgroup.h | 27 +- include/linux/indirect_call_wrapper.h | 6 - include/net/sock.h | 2 - include/net/tcp.h | 1 - kernel/bpf/cgroup.c | 46 --- net/ipv4/tcp.c | 14 - net/ipv4/tcp_ipv4.c | 1 - net/ipv6/tcp_ipv6.c | 1 - net/socket.c | 3 - tools/include/uapi/linux/tcp.h | 357 ------------------ .../selftests/bpf/prog_tests/bpf_tcp_ca.c | 1 - .../selftests/bpf/prog_tests/cls_redirect.c | 1 - .../selftests/bpf/prog_tests/sockmap_basic.c | 1 - .../selftests/bpf/prog_tests/sockopt_sk.c | 28 -- .../testing/selftests/bpf/progs/sockopt_sk.c | 23 +- tools/testing/selftests/bpf/test_progs.h | 1 + 16 files changed, 7 insertions(+), 506 deletions(-) delete mode 100644 tools/include/uapi/linux/tcp.h diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 53702b83ce5f..91b966978541 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -158,10 +158,6 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int __user *optlen, int max_optlen, int retval); -int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, - int optname, void *optval, - int *optlen, int retval); - static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -408,23 +404,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, ({ \ int __ret = retval; \ if (cgroup_bpf_enabled) \ - if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ - !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ - tcp_bpf_bypass_getsockopt, \ - level, optname)) \ - __ret = __cgroup_bpf_run_filter_getsockopt( \ - sock, level, optname, optval, optlen, \ - max_optlen, retval); \ - __ret; \ -}) - -#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ - optlen, retval) \ -({ \ - int __ret = retval; \ - if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ - sock, level, optname, optval, optlen, retval); \ + __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \ + optname, optval, \ + optlen, max_optlen, \ + retval); \ __ret; \ }) @@ -510,8 +493,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) -#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ - optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) ({ 0; }) diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index cfcfef37b2f1..54c02c84906a 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -60,10 +60,4 @@ #define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__) #endif -#if IS_ENABLED(CONFIG_INET) -#define INDIRECT_CALL_INET_1(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) -#else -#define INDIRECT_CALL_INET_1(f, f1, ...) f(__VA_ARGS__) -#endif - #endif diff --git a/include/net/sock.h b/include/net/sock.h index cf281e09edb4..016b694fa46b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1224,8 +1224,6 @@ struct proto { int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); - bool (*bpf_bypass_getsockopt)(int level, - int optname); void (*release_cb)(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index c63224a0a839..2f7e4441f471 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -400,7 +400,6 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); -bool tcp_bpf_bypass_getsockopt(int level, int optname); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 85927c2aa343..d3593a520bb7 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1546,52 +1546,6 @@ out: sockopt_free_buf(&ctx); return ret; } - -int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, - int optname, void *optval, - int *optlen, int retval) -{ - struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - struct bpf_sockopt_kern ctx = { - .sk = sk, - .level = level, - .optname = optname, - .retval = retval, - .optlen = *optlen, - .optval = optval, - .optval_end = optval + *optlen, - }; - int ret; - - /* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy - * user data back into BPF buffer when reval != 0. This is - * done as an optimization to avoid extra copy, assuming - * kernel won't populate the data in case of an error. - * Here we always pass the data and memset() should - * be called if that data shouldn't be "exported". - */ - - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], - &ctx, BPF_PROG_RUN); - if (!ret) - return -EPERM; - - if (ctx.optlen > *optlen) - return -EFAULT; - - /* BPF programs only allowed to set retval to 0, not some - * arbitrary value. - */ - if (ctx.retval != 0 && ctx.retval != retval) - return -EFAULT; - - /* BPF programs can shrink the buffer, export the modifications. - */ - if (ctx.optlen != 0) - *optlen = ctx.optlen; - - return ctx.retval; -} #endif static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c430e2511513..9e3ed6d2c2ac 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3946,8 +3946,6 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc); - err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, - &zc, &len, err); release_sock(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, err)) goto zerocopy_rcv_sk_err; @@ -3982,18 +3980,6 @@ zerocopy_rcv_out: return 0; } -bool tcp_bpf_bypass_getsockopt(int level, int optname) -{ - /* TCP do_tcp_getsockopt has optimized getsockopt implementation - * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE. - */ - if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE) - return true; - - return false; -} -EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); - int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bd41a25b9fc7..45939b6c99c2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2796,7 +2796,6 @@ struct proto tcp_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, - .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index a45a03b730af..a68f75d3664e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2132,7 +2132,6 @@ struct proto tcpv6_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, - .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, diff --git a/net/socket.c b/net/socket.c index d983fef5e0ed..8aefd9114ab2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2138,9 +2138,6 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, return __sys_setsockopt(fd, level, optname, optval, optlen); } -INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, - int optname)); - /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. diff --git a/tools/include/uapi/linux/tcp.h b/tools/include/uapi/linux/tcp.h deleted file mode 100644 index 13ceeb395eb8..000000000000 --- a/tools/include/uapi/linux/tcp.h +++ /dev/null @@ -1,357 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -/* - * INET An implementation of the TCP/IP protocol suite for the LINUX - * operating system. INET is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * Definitions for the TCP protocol. - * - * Version: @(#)tcp.h 1.0.2 04/28/93 - * - * Author: Fred N. van Kempen, - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#ifndef _UAPI_LINUX_TCP_H -#define _UAPI_LINUX_TCP_H - -#include -#include -#include - -struct tcphdr { - __be16 source; - __be16 dest; - __be32 seq; - __be32 ack_seq; -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u16 res1:4, - doff:4, - fin:1, - syn:1, - rst:1, - psh:1, - ack:1, - urg:1, - ece:1, - cwr:1; -#elif defined(__BIG_ENDIAN_BITFIELD) - __u16 doff:4, - res1:4, - cwr:1, - ece:1, - urg:1, - ack:1, - psh:1, - rst:1, - syn:1, - fin:1; -#else -#error "Adjust your defines" -#endif - __be16 window; - __sum16 check; - __be16 urg_ptr; -}; - -/* - * The union cast uses a gcc extension to avoid aliasing problems - * (union is compatible to any of its members) - * This means this part of the code is -fstrict-aliasing safe now. - */ -union tcp_word_hdr { - struct tcphdr hdr; - __be32 words[5]; -}; - -#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) - -enum { - TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000), - TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000), - TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000), - TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000), - TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000), - TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000), - TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000), - TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000), - TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000), - TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000) -}; - -/* - * TCP general constants - */ -#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */ -#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */ - -/* TCP socket options */ -#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */ -#define TCP_MAXSEG 2 /* Limit MSS */ -#define TCP_CORK 3 /* Never send partially complete segments */ -#define TCP_KEEPIDLE 4 /* Start keeplives after this period */ -#define TCP_KEEPINTVL 5 /* Interval between keepalives */ -#define TCP_KEEPCNT 6 /* Number of keepalives before death */ -#define TCP_SYNCNT 7 /* Number of SYN retransmits */ -#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */ -#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */ -#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */ -#define TCP_INFO 11 /* Information about this connection. */ -#define TCP_QUICKACK 12 /* Block/reenable quick acks */ -#define TCP_CONGESTION 13 /* Congestion control algorithm */ -#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ -#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ -#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ -#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */ -#define TCP_REPAIR 19 /* TCP sock is under repair right now */ -#define TCP_REPAIR_QUEUE 20 -#define TCP_QUEUE_SEQ 21 -#define TCP_REPAIR_OPTIONS 22 -#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */ -#define TCP_TIMESTAMP 24 -#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */ -#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */ -#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */ -#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */ -#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */ -#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */ -#define TCP_ULP 31 /* Attach a ULP to a TCP connection */ -#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */ -#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */ -#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */ -#define TCP_ZEROCOPY_RECEIVE 35 -#define TCP_INQ 36 /* Notify bytes available to read as a cmsg on read */ - -#define TCP_CM_INQ TCP_INQ - -#define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */ - - -#define TCP_REPAIR_ON 1 -#define TCP_REPAIR_OFF 0 -#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ - -struct tcp_repair_opt { - __u32 opt_code; - __u32 opt_val; -}; - -struct tcp_repair_window { - __u32 snd_wl1; - __u32 snd_wnd; - __u32 max_window; - - __u32 rcv_wnd; - __u32 rcv_wup; -}; - -enum { - TCP_NO_QUEUE, - TCP_RECV_QUEUE, - TCP_SEND_QUEUE, - TCP_QUEUES_NR, -}; - -/* why fastopen failed from client perspective */ -enum tcp_fastopen_client_fail { - TFO_STATUS_UNSPEC, /* catch-all */ - TFO_COOKIE_UNAVAILABLE, /* if not in TFO_CLIENT_NO_COOKIE mode */ - TFO_DATA_NOT_ACKED, /* SYN-ACK did not ack SYN data */ - TFO_SYN_RETRANSMITTED, /* SYN-ACK did not ack SYN data after timeout */ -}; - -/* for TCP_INFO socket option */ -#define TCPI_OPT_TIMESTAMPS 1 -#define TCPI_OPT_SACK 2 -#define TCPI_OPT_WSCALE 4 -#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */ -#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */ -#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */ - -/* - * Sender's congestion state indicating normal or abnormal situations - * in the last round of packets sent. The state is driven by the ACK - * information and timer events. - */ -enum tcp_ca_state { - /* - * Nothing bad has been observed recently. - * No apparent reordering, packet loss, or ECN marks. - */ - TCP_CA_Open = 0, -#define TCPF_CA_Open (1< -#include #include #include "bpf_dctcp.skel.h" #include "bpf_cubic.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c index e075d03ab630..9781d85cb223 100644 --- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -7,7 +7,6 @@ #include #include -#include #include diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index b8b48cac2ac3..85f73261fab0 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2020 Cloudflare #include -#include #include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index d5b44b135c00..b25c9c45c148 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -2,12 +2,6 @@ #include #include "cgroup_helpers.h" -#include - -#ifndef SOL_TCP -#define SOL_TCP IPPROTO_TCP -#endif - #define SOL_CUSTOM 0xdeadbeef static int getsetsockopt(void) @@ -17,7 +11,6 @@ static int getsetsockopt(void) char u8[4]; __u32 u32; char cc[16]; /* TCP_CA_NAME_MAX */ - struct tcp_zerocopy_receive zc; } buf = {}; socklen_t optlen; char *big_buf = NULL; @@ -161,27 +154,6 @@ static int getsetsockopt(void) goto err; } - /* TCP_ZEROCOPY_RECEIVE triggers */ - memset(&buf, 0, sizeof(buf)); - optlen = sizeof(buf.zc); - err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); - if (err) { - log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", - err, errno); - goto err; - } - - memset(&buf, 0, sizeof(buf)); - buf.zc.address = 12345; /* rejected by BPF */ - optlen = sizeof(buf.zc); - errno = 0; - err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); - if (errno != EPERM) { - log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", - err, errno); - goto err; - } - free(big_buf); close(fd); return 0; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index d3597f81e6e9..712df7b49cb1 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include -#include #include +#include +#include #include char _license[] SEC("license") = "GPL"; @@ -12,10 +12,6 @@ __u32 _version SEC("version") = 1; #define PAGE_SIZE 4096 #endif -#ifndef SOL_TCP -#define SOL_TCP IPPROTO_TCP -#endif - #define SOL_CUSTOM 0xdeadbeef struct sockopt_sk { @@ -61,21 +57,6 @@ int _getsockopt(struct bpf_sockopt *ctx) return 1; } - if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) { - /* Verify that TCP_ZEROCOPY_RECEIVE triggers. - * It has a custom implementation for performance - * reasons. - */ - - if (optval + sizeof(struct tcp_zerocopy_receive) > optval_end) - return 0; /* EPERM, bounds check */ - - if (((struct tcp_zerocopy_receive *)optval)->address != 0) - return 0; /* EPERM, unexpected data */ - - return 1; - } - if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 1d429d67f8dd..238f5f61189e 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -16,6 +16,7 @@ typedef __u16 __sum16; #include #include #include +#include #include #include #include From 6e606e681873b37aa252486d43be4cf007544e85 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:22 +0200 Subject: [PATCH 4251/4345] init: Provide arch_cpu_finalize_init() commit 7725acaa4f0c04fbefb0e0d342635b967bb7d414 upstream check_bugs() has become a dumping ground for all sorts of activities to finalize the CPU initialization before running the rest of the init code. Most are empty, a few do actual bug checks, some do alternative patching and some cobble a CPU advertisement string together.... Aside of that the current implementation requires duplicated function declaration and mostly empty header files for them. Provide a new function arch_cpu_finalize_init(). Provide a generic declaration if CONFIG_ARCH_HAS_CPU_FINALIZE_INIT is selected and a stub inline otherwise. This requires a temporary #ifdef in start_kernel() which will be removed along with check_bugs() once the architectures are converted over. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224544.957805717@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/Kconfig | 3 +++ include/linux/cpu.h | 6 ++++++ init/main.c | 5 +++++ 3 files changed, 14 insertions(+) diff --git a/arch/Kconfig b/arch/Kconfig index 632d60e13494..240277d5626c 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -290,6 +290,9 @@ config ARCH_HAS_DMA_SET_UNCACHED config ARCH_HAS_DMA_CLEAR_UNCACHED bool +config ARCH_HAS_CPU_FINALIZE_INIT + bool + # Select if arch init_task must go in the __init_task_data section config ARCH_TASK_STRUCT_ON_STACK bool diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 24e5f237244d..ef084a2fc6d5 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -188,6 +188,12 @@ void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); void arch_cpu_idle_dead(void); +#ifdef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT +void arch_cpu_finalize_init(void); +#else +static inline void arch_cpu_finalize_init(void) { } +#endif + int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); diff --git a/init/main.c b/init/main.c index d8bfe61b5a88..18abf3a5d789 100644 --- a/init/main.c +++ b/init/main.c @@ -1044,7 +1044,12 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) delayacct_init(); poking_init(); + + arch_cpu_finalize_init(); + /* Temporary conditional until everything has been converted */ +#ifndef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT check_bugs(); +#endif acpi_subsystem_init(); arch_post_acpi_subsys_init(); From e5eb18e164d08986543f8259d0cc10e120fb8746 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:24 +0200 Subject: [PATCH 4252/4345] x86/cpu: Switch to arch_cpu_finalize_init() commit 7c7077a72674402654f3291354720cd73cdf649e upstream check_bugs() is a dumping ground for finalizing the CPU bringup. Only parts of it has to do with actual CPU bugs. Split it apart into arch_cpu_finalize_init() and cpu_select_mitigations(). Fixup the bogus 32bit comments while at it. No functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20230613224545.019583869@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/Kconfig | 1 + arch/x86/include/asm/bugs.h | 2 -- arch/x86/kernel/cpu/bugs.c | 51 +--------------------------------- arch/x86/kernel/cpu/common.c | 53 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/cpu.h | 1 + 5 files changed, 56 insertions(+), 52 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2284666e8c90..d1c734289bdd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -59,6 +59,7 @@ config X86 select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE select ARCH_HAS_DEVMEM_IS_ALLOWED diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h index 92ae28389940..f25ca2d709d4 100644 --- a/arch/x86/include/asm/bugs.h +++ b/arch/x86/include/asm/bugs.h @@ -4,8 +4,6 @@ #include -extern void check_bugs(void); - #if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32) int ppro_with_ram_bug(void); #else diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c81b8b029b68..1ac943f1c99e 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,7 +9,6 @@ * - Andrew D. Balsa (code cleanup). */ #include -#include #include #include #include @@ -27,8 +26,6 @@ #include #include #include -#include -#include #include #include #include @@ -116,21 +113,8 @@ EXPORT_SYMBOL_GPL(mds_idle_clear); DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear); EXPORT_SYMBOL_GPL(mmio_stale_data_clear); -void __init check_bugs(void) +void __init cpu_select_mitigations(void) { - identify_boot_cpu(); - - /* - * identify_boot_cpu() initialized SMT support information, let the - * core code know. - */ - cpu_smt_check_topology(); - - if (!IS_ENABLED(CONFIG_SMP)) { - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); - } - /* * Read the SPEC_CTRL MSR to account for reserved bits which may * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD @@ -166,39 +150,6 @@ void __init check_bugs(void) l1tf_select_mitigation(); md_clear_select_mitigation(); srbds_select_mitigation(); - - arch_smt_update(); - -#ifdef CONFIG_X86_32 - /* - * Check whether we are able to run this kernel safely on SMP. - * - * - i386 is no longer supported. - * - In order to run on anything without a TSC, we need to be - * compiled for a i486. - */ - if (boot_cpu_data.x86 < 4) - panic("Kernel requires i486+ for 'invlpg' and other features"); - - init_utsname()->machine[1] = - '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); - alternative_instructions(); - - fpu__init_check_bugs(); -#else /* CONFIG_X86_64 */ - alternative_instructions(); - - /* - * Make sure the first 2MB area is not mapped by huge pages - * There are typically fixed size MTRRs in there and overlapping - * MTRRs into large pages causes slow downs. - * - * Right now we don't do that with gbpages because there seems - * very little benefit for that case. - */ - if (!direct_gbpages) - set_memory_4k((unsigned long)__va(0), 1); -#endif } /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f41781d06a5f..3e7bd3d2ce00 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -19,10 +19,13 @@ #include #include #include +#include #include #include #include +#include +#include #include #include #include @@ -58,6 +61,7 @@ #include #include #include +#include #include "cpu.h" @@ -2188,3 +2192,52 @@ void arch_smt_update(void) /* Check whether IPI broadcasting can be enabled */ apic_smt_update(); } + +void __init arch_cpu_finalize_init(void) +{ + identify_boot_cpu(); + + /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology(); + + if (!IS_ENABLED(CONFIG_SMP)) { + pr_info("CPU: "); + print_cpu_info(&boot_cpu_data); + } + + cpu_select_mitigations(); + + arch_smt_update(); + + if (IS_ENABLED(CONFIG_X86_32)) { + /* + * Check whether this is a real i386 which is not longer + * supported and fixup the utsname. + */ + if (boot_cpu_data.x86 < 4) + panic("Kernel requires i486+ for 'invlpg' and other features"); + + init_utsname()->machine[1] = + '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); + } + + alternative_instructions(); + + if (IS_ENABLED(CONFIG_X86_64)) { + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); + } else { + fpu__init_check_bugs(); + } +} diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 91df90abc1d9..215416e8a8de 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -78,6 +78,7 @@ extern void detect_ht(struct cpuinfo_x86 *c); extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); From c0fff20d4efa3bdb3ef203a8ae6e703e0c010199 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:25 +0200 Subject: [PATCH 4253/4345] ARM: cpu: Switch to arch_cpu_finalize_init() commit ee31bb0524a2e7c99b03f50249a411cc1eaa411f upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.078124882@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/arm/Kconfig | 1 + arch/arm/include/asm/bugs.h | 4 ---- arch/arm/kernel/bugs.c | 3 ++- 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 985ab0b091a6..335308aff6ce 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -4,6 +4,7 @@ config ARM default y select ARCH_32BIT_OFF_T select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CPU_FINALIZE_INIT if MMU select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE diff --git a/arch/arm/include/asm/bugs.h b/arch/arm/include/asm/bugs.h index 97a312ba0840..fe385551edec 100644 --- a/arch/arm/include/asm/bugs.h +++ b/arch/arm/include/asm/bugs.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * arch/arm/include/asm/bugs.h - * * Copyright (C) 1995-2003 Russell King */ #ifndef __ASM_BUGS_H @@ -10,10 +8,8 @@ extern void check_writebuffer_bugs(void); #ifdef CONFIG_MMU -extern void check_bugs(void); extern void check_other_bugs(void); #else -#define check_bugs() do { } while (0) #define check_other_bugs() do { } while (0) #endif diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c index 14c8dbbb7d2d..087bce6ec8e9 100644 --- a/arch/arm/kernel/bugs.c +++ b/arch/arm/kernel/bugs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include @@ -11,7 +12,7 @@ void check_other_bugs(void) #endif } -void __init check_bugs(void) +void __init arch_cpu_finalize_init(void) { check_writebuffer_bugs(); check_other_bugs(); From 12d93c6c98d5478128d90ad4fbdf705753a0197e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:27 +0200 Subject: [PATCH 4254/4345] ia64/cpu: Switch to arch_cpu_finalize_init() commit 6c38e3005621800263f117fb00d6787a76e16de7 upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.137045745@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/ia64/Kconfig | 1 + arch/ia64/include/asm/bugs.h | 20 -------------------- arch/ia64/kernel/setup.c | 3 +-- 3 files changed, 2 insertions(+), 22 deletions(-) delete mode 100644 arch/ia64/include/asm/bugs.h diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 1d0579bc9d65..975b00b6034b 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -8,6 +8,7 @@ menu "Processor type and features" config IA64 bool + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_DMA_MARK_CLEAN select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO diff --git a/arch/ia64/include/asm/bugs.h b/arch/ia64/include/asm/bugs.h deleted file mode 100644 index 0d6b9bded56c..000000000000 --- a/arch/ia64/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - * - * Based on . - * - * Modified 1998, 1999, 2003 - * David Mosberger-Tang , Hewlett-Packard Co. - */ -#ifndef _ASM_IA64_BUGS_H -#define _ASM_IA64_BUGS_H - -#include - -extern void check_bugs (void); - -#endif /* _ASM_IA64_BUGS_H */ diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index dd595fbd8006..e7dd6756d5cb 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -1071,8 +1071,7 @@ cpu_init (void) } } -void __init -check_bugs (void) +void __init arch_cpu_finalize_init(void) { ia64_patch_mckinley_e9((unsigned long) __start___mckinley_e9_bundles, (unsigned long) __end___mckinley_e9_bundles); From 1cd3fc18eb169e2f81a34eeaf8147f9395ee8a11 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:30 +0200 Subject: [PATCH 4255/4345] m68k/cpu: Switch to arch_cpu_finalize_init() commit 9ceecc2589b9d7cef6b321339ed8de484eac4b20 upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Acked-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230613224545.254342916@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/m68k/Kconfig | 1 + arch/m68k/include/asm/bugs.h | 21 --------------------- arch/m68k/kernel/setup_mm.c | 3 ++- 3 files changed, 3 insertions(+), 22 deletions(-) delete mode 100644 arch/m68k/include/asm/bugs.h diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 372e4e69c43a..ad7a4ffd65c9 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -4,6 +4,7 @@ config M68K default y select ARCH_32BIT_OFF_T select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CPU_FINALIZE_INIT if MMU select ARCH_HAS_DMA_PREP_COHERENT if HAS_DMA && MMU && !COLDFIRE select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS diff --git a/arch/m68k/include/asm/bugs.h b/arch/m68k/include/asm/bugs.h deleted file mode 100644 index 745530651e0b..000000000000 --- a/arch/m68k/include/asm/bugs.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/asm-m68k/bugs.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -#ifdef CONFIG_MMU -extern void check_bugs(void); /* in arch/m68k/kernel/setup.c */ -#else -static void check_bugs(void) -{ -} -#endif diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index ab8aa7be260f..f8116660417f 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -10,6 +10,7 @@ */ #include +#include #include #include #include @@ -523,7 +524,7 @@ static int __init proc_hardware_init(void) module_init(proc_hardware_init); #endif -void check_bugs(void) +void __init arch_cpu_finalize_init(void) { #if defined(CONFIG_FPU) && !defined(CONFIG_M68KFPU_EMU) if (m68k_fputype == 0) { From 75bb54c951e92714a50cdc063f9953d11e8d36a2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:32 +0200 Subject: [PATCH 4256/4345] mips/cpu: Switch to arch_cpu_finalize_init() commit 7f066a22fe353a827a402ee2835e81f045b1574d upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.312438573@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/mips/Kconfig | 1 + arch/mips/include/asm/bugs.h | 17 ----------------- arch/mips/kernel/setup.c | 13 +++++++++++++ 3 files changed, 14 insertions(+), 17 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 3442bdd4314c..57839f63074f 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -4,6 +4,7 @@ config MIPS default y select ARCH_32BIT_OFF_T if !64BIT select ARCH_BINFMT_ELF_STATE if MIPS_FP_SUPPORT + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_KCOV select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if !EVA diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index d72dc6e1cf3c..8d4cf29861b8 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -1,17 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * This is included by init/main.c to check for architecture-dependent bugs. - * * Copyright (C) 2007 Maciej W. Rozycki - * - * Needs: - * void check_bugs(void); */ #ifndef _ASM_BUGS_H #define _ASM_BUGS_H #include -#include #include #include @@ -30,17 +24,6 @@ static inline void check_bugs_early(void) check_bugs64_early(); } -static inline void check_bugs(void) -{ - unsigned int cpu = smp_processor_id(); - - cpu_data[cpu].udelay_val = loops_per_jiffy; - check_bugs32(); - - if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) - check_bugs64(); -} - static inline int r4k_daddiu_bug(void) { if (!IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index b49ad569e469..b7eb7dd96e17 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -11,6 +11,8 @@ * Copyright (C) 2000, 2001, 2002, 2007 Maciej W. Rozycki */ #include +#include +#include #include #include #include @@ -829,3 +831,14 @@ static int __init setnocoherentio(char *str) } early_param("nocoherentio", setnocoherentio); #endif + +void __init arch_cpu_finalize_init(void) +{ + unsigned int cpu = smp_processor_id(); + + cpu_data[cpu].udelay_val = loops_per_jiffy; + check_bugs32(); + + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64(); +} From 3c45134b38b417d17103f1f0b9a8b32f98ac358c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:33 +0200 Subject: [PATCH 4257/4345] sh/cpu: Switch to arch_cpu_finalize_init() commit 01eb454e9bfe593f320ecbc9aaec60bf87cd453d upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.371697797@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/sh/Kconfig | 1 + arch/sh/include/asm/bugs.h | 74 --------------------------------- arch/sh/include/asm/processor.h | 2 + arch/sh/kernel/idle.c | 1 + arch/sh/kernel/setup.c | 55 ++++++++++++++++++++++++ 5 files changed, 59 insertions(+), 74 deletions(-) delete mode 100644 arch/sh/include/asm/bugs.h diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index b6f3d49991d3..44dffe7ce50a 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -5,6 +5,7 @@ config SUPERH select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) select ARCH_HAS_BINFMT_FLAT if !MMU + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_PTE_SPECIAL diff --git a/arch/sh/include/asm/bugs.h b/arch/sh/include/asm/bugs.h deleted file mode 100644 index fe52abb69cea..000000000000 --- a/arch/sh/include/asm/bugs.h +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_SH_BUGS_H -#define __ASM_SH_BUGS_H - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -/* - * I don't know of any Super-H bugs yet. - */ - -#include - -extern void select_idle_routine(void); - -static void __init check_bugs(void) -{ - extern unsigned long loops_per_jiffy; - char *p = &init_utsname()->machine[2]; /* "sh" */ - - select_idle_routine(); - - current_cpu_data.loops_per_jiffy = loops_per_jiffy; - - switch (current_cpu_data.family) { - case CPU_FAMILY_SH2: - *p++ = '2'; - break; - case CPU_FAMILY_SH2A: - *p++ = '2'; - *p++ = 'a'; - break; - case CPU_FAMILY_SH3: - *p++ = '3'; - break; - case CPU_FAMILY_SH4: - *p++ = '4'; - break; - case CPU_FAMILY_SH4A: - *p++ = '4'; - *p++ = 'a'; - break; - case CPU_FAMILY_SH4AL_DSP: - *p++ = '4'; - *p++ = 'a'; - *p++ = 'l'; - *p++ = '-'; - *p++ = 'd'; - *p++ = 's'; - *p++ = 'p'; - break; - case CPU_FAMILY_UNKNOWN: - /* - * Specifically use CPU_FAMILY_UNKNOWN rather than - * default:, so we're able to have the compiler whine - * about unhandled enumerations. - */ - break; - } - - printk("CPU: %s\n", get_cpu_subtype(¤t_cpu_data)); - -#ifndef __LITTLE_ENDIAN__ - /* 'eb' means 'Endian Big' */ - *p++ = 'e'; - *p++ = 'b'; -#endif - *p = '\0'; -} -#endif /* __ASM_SH_BUGS_H */ diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h index 3820d698846e..97af2d9b0269 100644 --- a/arch/sh/include/asm/processor.h +++ b/arch/sh/include/asm/processor.h @@ -167,6 +167,8 @@ extern unsigned int instruction_size(unsigned int insn); #define instruction_size(insn) (2) #endif +void select_idle_routine(void); + #endif /* __ASSEMBLY__ */ #include diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index f59814983bd5..a80b2a5b25c7 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 556e463a43d2..805c02eef5ac 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -357,3 +358,57 @@ int test_mode_pin(int pin) { return sh_mv.mv_mode_pins() & pin; } + +void __init arch_cpu_finalize_init(void) +{ + char *p = &init_utsname()->machine[2]; /* "sh" */ + + select_idle_routine(); + + current_cpu_data.loops_per_jiffy = loops_per_jiffy; + + switch (current_cpu_data.family) { + case CPU_FAMILY_SH2: + *p++ = '2'; + break; + case CPU_FAMILY_SH2A: + *p++ = '2'; + *p++ = 'a'; + break; + case CPU_FAMILY_SH3: + *p++ = '3'; + break; + case CPU_FAMILY_SH4: + *p++ = '4'; + break; + case CPU_FAMILY_SH4A: + *p++ = '4'; + *p++ = 'a'; + break; + case CPU_FAMILY_SH4AL_DSP: + *p++ = '4'; + *p++ = 'a'; + *p++ = 'l'; + *p++ = '-'; + *p++ = 'd'; + *p++ = 's'; + *p++ = 'p'; + break; + case CPU_FAMILY_UNKNOWN: + /* + * Specifically use CPU_FAMILY_UNKNOWN rather than + * default:, so we're able to have the compiler whine + * about unhandled enumerations. + */ + break; + } + + pr_info("CPU: %s\n", get_cpu_subtype(¤t_cpu_data)); + +#ifndef __LITTLE_ENDIAN__ + /* 'eb' means 'Endian Big' */ + *p++ = 'e'; + *p++ = 'b'; +#endif + *p = '\0'; +} From 2edb3b39ca793bf13a123ea6a25da640be36e7a5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:35 +0200 Subject: [PATCH 4258/4345] sparc/cpu: Switch to arch_cpu_finalize_init() commit 44ade508e3bfac45ae97864587de29eb1a881ec0 upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Sam Ravnborg Link: https://lore.kernel.org/r/20230613224545.431995857@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/sparc/Kconfig | 1 + arch/sparc/include/asm/bugs.h | 18 ------------------ arch/sparc/kernel/setup_32.c | 7 +++++++ 3 files changed, 8 insertions(+), 18 deletions(-) delete mode 100644 arch/sparc/include/asm/bugs.h diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index b5ed89342059..7e2ce4c8d657 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -56,6 +56,7 @@ config SPARC config SPARC32 def_bool !64BIT select ARCH_32BIT_OFF_T + select ARCH_HAS_CPU_FINALIZE_INIT if !SMP select ARCH_HAS_SYNC_DMA_FOR_CPU select GENERIC_ATOMIC64 select CLZ_TAB diff --git a/arch/sparc/include/asm/bugs.h b/arch/sparc/include/asm/bugs.h deleted file mode 100644 index 02fa369b9c21..000000000000 --- a/arch/sparc/include/asm/bugs.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* include/asm/bugs.h: Sparc probes for various bugs. - * - * Copyright (C) 1996, 2007 David S. Miller (davem@davemloft.net) - */ - -#ifdef CONFIG_SPARC32 -#include -#endif - -extern unsigned long loops_per_jiffy; - -static void __init check_bugs(void) -{ -#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP) - cpu_data(0).udelay_val = loops_per_jiffy; -#endif -} diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index eea43a1aef1b..8e2c7c1aad83 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -415,3 +415,10 @@ static int __init topology_init(void) } subsys_initcall(topology_init); + +#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP) +void __init arch_cpu_finalize_init(void) +{ + cpu_data(0).udelay_val = loops_per_jiffy; +} +#endif From b05031c2bca790afed717bc59cde2dac722efb94 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:36 +0200 Subject: [PATCH 4259/4345] um/cpu: Switch to arch_cpu_finalize_init() commit 9349b5cd0908f8afe95529fc7a8cbb1417df9b0c upstream check_bugs() is about to be phased out. Switch over to the new arch_cpu_finalize_init() implementation. No functional change. Signed-off-by: Thomas Gleixner Acked-by: Richard Weinberger Link: https://lore.kernel.org/r/20230613224545.493148694@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/um/Kconfig | 1 + arch/um/include/asm/bugs.h | 7 ------- arch/um/kernel/um_arch.c | 3 ++- 3 files changed, 3 insertions(+), 8 deletions(-) delete mode 100644 arch/um/include/asm/bugs.h diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 1c57599b82fa..eb1c6880bde4 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -5,6 +5,7 @@ menu "UML-specific options" config UML bool default y + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_KCOV select ARCH_NO_PREEMPT select HAVE_ARCH_AUDITSYSCALL diff --git a/arch/um/include/asm/bugs.h b/arch/um/include/asm/bugs.h deleted file mode 100644 index 4473942a0839..000000000000 --- a/arch/um/include/asm/bugs.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_BUGS_H -#define __UM_BUGS_H - -void check_bugs(void); - -#endif diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 55930ca498e9..ca5383a8a988 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -3,6 +3,7 @@ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) */ +#include #include #include #include @@ -353,7 +354,7 @@ void __init setup_arch(char **cmdline_p) setup_hostinfo(host_info, sizeof host_info); } -void __init check_bugs(void) +void __init arch_cpu_finalize_init(void) { arch_check_bugs(); os_check_bugs(); From bf2fa3a9d0e65326917273d17a8e9c6880d7b97c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:38 +0200 Subject: [PATCH 4260/4345] init: Remove check_bugs() leftovers commit 61235b24b9cb37c13fcad5b9596d59a1afdcec30 upstream Everything is converted over to arch_cpu_finalize_init(). Remove the check_bugs() leftovers including the empty stubs in asm-generic, alpha, parisc, powerpc and xtensa. Signed-off-by: Thomas Gleixner Reviewed-by: Richard Henderson Link: https://lore.kernel.org/r/20230613224545.553215951@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/alpha/include/asm/bugs.h | 20 -------------------- arch/parisc/include/asm/bugs.h | 20 -------------------- arch/powerpc/include/asm/bugs.h | 15 --------------- arch/xtensa/include/asm/bugs.h | 18 ------------------ include/asm-generic/bugs.h | 11 ----------- init/main.c | 5 ----- 6 files changed, 89 deletions(-) delete mode 100644 arch/alpha/include/asm/bugs.h delete mode 100644 arch/parisc/include/asm/bugs.h delete mode 100644 arch/powerpc/include/asm/bugs.h delete mode 100644 arch/xtensa/include/asm/bugs.h delete mode 100644 include/asm-generic/bugs.h diff --git a/arch/alpha/include/asm/bugs.h b/arch/alpha/include/asm/bugs.h deleted file mode 100644 index 78030d1c7e7e..000000000000 --- a/arch/alpha/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * include/asm-alpha/bugs.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -/* - * I don't know of any alpha bugs yet.. Nice chip - */ - -static void check_bugs(void) -{ -} diff --git a/arch/parisc/include/asm/bugs.h b/arch/parisc/include/asm/bugs.h deleted file mode 100644 index 0a7f9db6bd1c..000000000000 --- a/arch/parisc/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/asm-parisc/bugs.h - * - * Copyright (C) 1999 Mike Shaver - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -#include - -static inline void check_bugs(void) -{ -// identify_cpu(&boot_cpu_data); -} diff --git a/arch/powerpc/include/asm/bugs.h b/arch/powerpc/include/asm/bugs.h deleted file mode 100644 index 01b8f6ca4dbb..000000000000 --- a/arch/powerpc/include/asm/bugs.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_POWERPC_BUGS_H -#define _ASM_POWERPC_BUGS_H - -/* - */ - -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* _ASM_POWERPC_BUGS_H */ diff --git a/arch/xtensa/include/asm/bugs.h b/arch/xtensa/include/asm/bugs.h deleted file mode 100644 index 69b29d198249..000000000000 --- a/arch/xtensa/include/asm/bugs.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * include/asm-xtensa/bugs.h - * - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Xtensa processors don't have any bugs. :) - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file "COPYING" in the main directory of - * this archive for more details. - */ - -#ifndef _XTENSA_BUGS_H -#define _XTENSA_BUGS_H - -static void check_bugs(void) { } - -#endif /* _XTENSA_BUGS_H */ diff --git a/include/asm-generic/bugs.h b/include/asm-generic/bugs.h deleted file mode 100644 index 69021830f078..000000000000 --- a/include/asm-generic/bugs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_BUGS_H -#define __ASM_GENERIC_BUGS_H -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* __ASM_GENERIC_BUGS_H */ diff --git a/init/main.c b/init/main.c index 18abf3a5d789..3999d860f364 100644 --- a/init/main.c +++ b/init/main.c @@ -100,7 +100,6 @@ #include #include -#include #include #include #include @@ -1046,10 +1045,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) poking_init(); arch_cpu_finalize_init(); - /* Temporary conditional until everything has been converted */ -#ifndef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT - check_bugs(); -#endif acpi_subsystem_init(); arch_post_acpi_subsys_init(); From 09658b81d158c15112a56323d8db8fed83e8cd4a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:39 +0200 Subject: [PATCH 4261/4345] init: Invoke arch_cpu_finalize_init() earlier commit 9df9d2f0471b4c4702670380b8d8a45b40b23a7d upstream X86 is reworking the boot process so that initializations which are not required during early boot can be moved into the late boot process and out of the fragile and restricted initial boot phase. arch_cpu_finalize_init() is the obvious place to do such initializations, but arch_cpu_finalize_init() is invoked too late in start_kernel() e.g. for initializing the FPU completely. fork_init() requires that the FPU is initialized as the size of task_struct on X86 depends on the size of the required FPU register buffer. Fortunately none of the init calls between calibrate_delay() and arch_cpu_finalize_init() is relevant for the functionality of arch_cpu_finalize_init(). Invoke it right after calibrate_delay() where everything which is relevant for arch_cpu_finalize_init() has been set up already. No functional change intended. Signed-off-by: Thomas Gleixner Reviewed-by: Rick Edgecombe Link: https://lore.kernel.org/r/20230613224545.612182854@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- init/main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/init/main.c b/init/main.c index 3999d860f364..845c563fa8e7 100644 --- a/init/main.c +++ b/init/main.c @@ -1016,6 +1016,9 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) late_time_init(); sched_clock_init(); calibrate_delay(); + + arch_cpu_finalize_init(); + pid_idr_init(); anon_vma_init(); #ifdef CONFIG_X86 @@ -1044,8 +1047,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) poking_init(); - arch_cpu_finalize_init(); - acpi_subsystem_init(); arch_post_acpi_subsys_init(); sfi_init_late(); From 18fcd72da1ed6166f1cbb03f713bed50c839fc22 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:41 +0200 Subject: [PATCH 4262/4345] init, x86: Move mem_encrypt_init() into arch_cpu_finalize_init() commit 439e17576eb47f26b78c5bbc72e344d4206d2327 upstream Invoke the X86ism mem_encrypt_init() from X86 arch_cpu_finalize_init() and remove the weak fallback from the core code. No functional change. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.670360645@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/mem_encrypt.h | 7 ++++--- arch/x86/kernel/cpu/common.c | 11 +++++++++++ init/main.c | 11 ----------- 3 files changed, 15 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 8f3fa55d43ce..4406d58cf7cb 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -47,14 +47,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); void __init mem_encrypt_free_decrypted_mem(void); -/* Architecture __weak replacement functions */ -void __init mem_encrypt_init(void); - void __init sev_es_init_vc_handling(void); bool sme_active(void); bool sev_active(void); bool sev_es_active(void); +void __init mem_encrypt_init(void); + #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -86,6 +85,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; static inline void mem_encrypt_free_decrypted_mem(void) { } +static inline void mem_encrypt_init(void) { } + #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3e7bd3d2ce00..a27ceb622d58 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -2240,4 +2241,14 @@ void __init arch_cpu_finalize_init(void) } else { fpu__init_check_bugs(); } + + /* + * This needs to be called before any devices perform DMA + * operations that might use the SWIOTLB bounce buffers. It will + * mark the bounce buffers as decrypted so that their usage will + * not cause "plain-text" data to be decrypted when accessed. It + * must be called after late_time_init() so that Hyper-V x86/x64 + * hypercalls work when the SWIOTLB bounce buffers are decrypted. + */ + mem_encrypt_init(); } diff --git a/init/main.c b/init/main.c index 845c563fa8e7..1a3d0bea5735 100644 --- a/init/main.c +++ b/init/main.c @@ -95,7 +95,6 @@ #include #include #include -#include #include #include @@ -773,8 +772,6 @@ void __init __weak thread_stack_cache_init(void) } #endif -void __init __weak mem_encrypt_init(void) { } - void __init __weak poking_init(void) { } void __init __weak pgtable_cache_init(void) { } @@ -992,14 +989,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) */ locking_selftest(); - /* - * This needs to be called before any devices perform DMA - * operations that might use the SWIOTLB bounce buffers. It will - * mark the bounce buffers as decrypted so that their usage will - * not cause "plain-text" data to be decrypted when accessed. - */ - mem_encrypt_init(); - #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start && !initrd_below_start_ok && page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) { From 7a2f42bce9ab23fb9e59fe6de45bfedb5d611eee Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:43 +0200 Subject: [PATCH 4263/4345] x86/fpu: Remove cpuinfo argument from init functions commit 1f34bb2a24643e0087652d81078e4f616562738d upstream Nothing in the call chain requires it Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.783704297@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/fpu/internal.h | 2 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/fpu/init.c | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 70b9bc5403c5..94c07151a9e5 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -42,7 +42,7 @@ extern int fpu__exception_code(struct fpu *fpu, int trap_nr); extern void fpu__init_cpu(void); extern void fpu__init_system_xstate(void); extern void fpu__init_cpu_xstate(void); -extern void fpu__init_system(struct cpuinfo_x86 *c); +extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); extern u64 fpu__get_supported_xfeatures_mask(void); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a27ceb622d58..b302b3fff891 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1418,7 +1418,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_set_core_cap_bits(c); - fpu__init_system(c); + fpu__init_system(); #ifdef CONFIG_X86_32 /* diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 3c0a621b9792..fc76816f184f 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -67,7 +67,7 @@ static bool fpu__probe_without_cpuid(void) return fsw == 0 && (fcw & 0x103f) == 0x003f; } -static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +static void fpu__init_system_early_generic(void) { if (!boot_cpu_has(X86_FEATURE_CPUID) && !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { @@ -237,9 +237,9 @@ static void __init fpu__init_system_ctx_switch(void) * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: */ -void __init fpu__init_system(struct cpuinfo_x86 *c) +void __init fpu__init_system(void) { - fpu__init_system_early_generic(c); + fpu__init_system_early_generic(); /* * The FPU has to be operational for some of the From 2462bc3ef0611646d94658ff250bb16669347361 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:45 +0200 Subject: [PATCH 4264/4345] x86/fpu: Mark init functions __init commit 1703db2b90c91b2eb2d699519fc505fe431dde0e upstream No point in keeping them around. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.841685728@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/fpu/init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index fc76816f184f..ed73f9b40706 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -49,7 +49,7 @@ void fpu__init_cpu(void) fpu__init_cpu_xstate(); } -static bool fpu__probe_without_cpuid(void) +static bool __init fpu__probe_without_cpuid(void) { unsigned long cr0; u16 fsw, fcw; @@ -67,7 +67,7 @@ static bool fpu__probe_without_cpuid(void) return fsw == 0 && (fcw & 0x103f) == 0x003f; } -static void fpu__init_system_early_generic(void) +static void __init fpu__init_system_early_generic(void) { if (!boot_cpu_has(X86_FEATURE_CPUID) && !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { From 4ae1cbb730bd574d57d3996d4c20974972d47009 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Jun 2023 01:39:46 +0200 Subject: [PATCH 4265/4345] x86/fpu: Move FPU initialization into arch_cpu_finalize_init() commit b81fac906a8f9e682e513ddd95697ec7a20878d4 upstream Initializing the FPU during the early boot process is a pointless exercise. Early boot is convoluted and fragile enough. Nothing requires that the FPU is set up early. It has to be initialized before fork_init() because the task_struct size depends on the FPU register buffer size. Move the initialization to arch_cpu_finalize_init() which is the perfect place to do so. No functional change. This allows to remove quite some of the custom early command line parsing, but that's subject to the next installment. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230613224545.902376621@linutronix.de Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/common.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b302b3fff891..977edd149e40 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1418,8 +1418,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_set_core_cap_bits(c); - fpu__init_system(); - #ifdef CONFIG_X86_32 /* * Regardless of whether PCID is enumerated, the SDM says @@ -2114,8 +2112,6 @@ void cpu_init(void) doublefault_init_cpu_tss(); - fpu__init_cpu(); - if (is_uv_system()) uv_cpu_init(); @@ -2131,6 +2127,7 @@ void cpu_init_secondary(void) */ cpu_init_exception_handling(); cpu_init(); + fpu__init_cpu(); } #endif @@ -2225,6 +2222,13 @@ void __init arch_cpu_finalize_init(void) '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); } + /* + * Must be before alternatives because it might set or clear + * feature bits. + */ + fpu__init_system(); + fpu__init_cpu(); + alternative_instructions(); if (IS_ENABLED(CONFIG_X86_64)) { From 288a2f6bc1ce03ddb3f05fd8c79b00d5d7160b4a Mon Sep 17 00:00:00 2001 From: Daniel Sneddon Date: Wed, 12 Jul 2023 19:43:11 -0700 Subject: [PATCH 4266/4345] x86/speculation: Add Gather Data Sampling mitigation commit 8974eb588283b7d44a7c91fa09fcbaf380339f3a upstream Gather Data Sampling (GDS) is a hardware vulnerability which allows unprivileged speculative access to data which was previously stored in vector registers. Intel processors that support AVX2 and AVX512 have gather instructions that fetch non-contiguous data elements from memory. On vulnerable hardware, when a gather instruction is transiently executed and encounters a fault, stale data from architectural or internal vector registers may get transiently stored to the destination vector register allowing an attacker to infer the stale data using typical side channel techniques like cache timing attacks. This mitigation is different from many earlier ones for two reasons. First, it is enabled by default and a bit must be set to *DISABLE* it. This is the opposite of normal mitigation polarity. This means GDS can be mitigated simply by updating microcode and leaving the new control bit alone. Second, GDS has a "lock" bit. This lock bit is there because the mitigation affects the hardware security features KeyLocker and SGX. It needs to be enabled and *STAY* enabled for these features to be mitigated against GDS. The mitigation is enabled in the microcode by default. Disable it by setting gather_data_sampling=off or by disabling all mitigations with mitigations=off. The mitigation status can be checked by reading: /sys/devices/system/cpu/vulnerabilities/gather_data_sampling Signed-off-by: Daniel Sneddon Signed-off-by: Dave Hansen Acked-by: Josh Poimboeuf Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- .../ABI/testing/sysfs-devices-system-cpu | 15 +- .../hw-vuln/gather_data_sampling.rst | 99 ++++++++++++++ Documentation/admin-guide/hw-vuln/index.rst | 1 + .../admin-guide/kernel-parameters.txt | 35 +++-- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/msr-index.h | 11 ++ arch/x86/kernel/cpu/bugs.c | 129 ++++++++++++++++++ arch/x86/kernel/cpu/common.c | 34 +++-- arch/x86/kernel/cpu/cpu.h | 1 + drivers/base/cpu.c | 8 ++ 10 files changed, 308 insertions(+), 26 deletions(-) create mode 100644 Documentation/admin-guide/hw-vuln/gather_data_sampling.rst diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 500d5d8937cb..bfb4f4fada33 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -501,17 +501,18 @@ Description: information about CPUs heterogeneity. cpu_capacity: capacity of cpu#. What: /sys/devices/system/cpu/vulnerabilities - /sys/devices/system/cpu/vulnerabilities/meltdown - /sys/devices/system/cpu/vulnerabilities/spectre_v1 - /sys/devices/system/cpu/vulnerabilities/spectre_v2 - /sys/devices/system/cpu/vulnerabilities/spec_store_bypass + /sys/devices/system/cpu/vulnerabilities/gather_data_sampling + /sys/devices/system/cpu/vulnerabilities/itlb_multihit /sys/devices/system/cpu/vulnerabilities/l1tf /sys/devices/system/cpu/vulnerabilities/mds - /sys/devices/system/cpu/vulnerabilities/srbds - /sys/devices/system/cpu/vulnerabilities/tsx_async_abort - /sys/devices/system/cpu/vulnerabilities/itlb_multihit + /sys/devices/system/cpu/vulnerabilities/meltdown /sys/devices/system/cpu/vulnerabilities/mmio_stale_data /sys/devices/system/cpu/vulnerabilities/retbleed + /sys/devices/system/cpu/vulnerabilities/spec_store_bypass + /sys/devices/system/cpu/vulnerabilities/spectre_v1 + /sys/devices/system/cpu/vulnerabilities/spectre_v2 + /sys/devices/system/cpu/vulnerabilities/srbds + /sys/devices/system/cpu/vulnerabilities/tsx_async_abort Date: January 2018 Contact: Linux kernel mailing list Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst new file mode 100644 index 000000000000..74dab6af7fe1 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst @@ -0,0 +1,99 @@ +.. SPDX-License-Identifier: GPL-2.0 + +GDS - Gather Data Sampling +========================== + +Gather Data Sampling is a hardware vulnerability which allows unprivileged +speculative access to data which was previously stored in vector registers. + +Problem +------- +When a gather instruction performs loads from memory, different data elements +are merged into the destination vector register. However, when a gather +instruction that is transiently executed encounters a fault, stale data from +architectural or internal vector registers may get transiently forwarded to the +destination vector register instead. This will allow a malicious attacker to +infer stale data using typical side channel techniques like cache timing +attacks. GDS is a purely sampling-based attack. + +The attacker uses gather instructions to infer the stale vector register data. +The victim does not need to do anything special other than use the vector +registers. The victim does not need to use gather instructions to be +vulnerable. + +Because the buffers are shared between Hyper-Threads cross Hyper-Thread attacks +are possible. + +Attack scenarios +---------------- +Without mitigation, GDS can infer stale data across virtually all +permission boundaries: + + Non-enclaves can infer SGX enclave data + Userspace can infer kernel data + Guests can infer data from hosts + Guest can infer guest from other guests + Users can infer data from other users + +Because of this, it is important to ensure that the mitigation stays enabled in +lower-privilege contexts like guests and when running outside SGX enclaves. + +The hardware enforces the mitigation for SGX. Likewise, VMMs should ensure +that guests are not allowed to disable the GDS mitigation. If a host erred and +allowed this, a guest could theoretically disable GDS mitigation, mount an +attack, and re-enable it. + +Mitigation mechanism +-------------------- +This issue is mitigated in microcode. The microcode defines the following new +bits: + + ================================ === ============================ + IA32_ARCH_CAPABILITIES[GDS_CTRL] R/O Enumerates GDS vulnerability + and mitigation support. + IA32_ARCH_CAPABILITIES[GDS_NO] R/O Processor is not vulnerable. + IA32_MCU_OPT_CTRL[GDS_MITG_DIS] R/W Disables the mitigation + 0 by default. + IA32_MCU_OPT_CTRL[GDS_MITG_LOCK] R/W Locks GDS_MITG_DIS=0. Writes + to GDS_MITG_DIS are ignored + Can't be cleared once set. + ================================ === ============================ + +GDS can also be mitigated on systems that don't have updated microcode by +disabling AVX. This can be done by setting "clearcpuid=avx" on the kernel +command-line. + +Mitigation control on the kernel command line +--------------------------------------------- +The mitigation can be disabled by setting "gather_data_sampling=off" or +"mitigations=off" on the kernel command line. Not specifying either will +default to the mitigation being enabled. + +GDS System Information +------------------------ +The kernel provides vulnerability status information through sysfs. For +GDS this can be accessed by the following sysfs file: + +/sys/devices/system/cpu/vulnerabilities/gather_data_sampling + +The possible values contained in this file are: + + ============================== ============================================= + Not affected Processor not vulnerable. + Vulnerable Processor vulnerable and mitigation disabled. + Vulnerable: No microcode Processor vulnerable and microcode is missing + mitigation. + Mitigation: Microcode Processor is vulnerable and mitigation is in + effect. + Mitigation: Microcode (locked) Processor is vulnerable and mitigation is in + effect and cannot be disabled. + Unknown: Dependent on + hypervisor status Running on a virtual guest processor that is + affected but with no way to know if host + processor is mitigated or vulnerable. + ============================== ============================================= + +GDS Default mitigation +---------------------- +The updated microcode will enable the mitigation by default. The kernel's +default action is to leave the mitigation enabled. diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 2adec1e6520a..245468b0f2be 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -16,3 +16,4 @@ are configurable at compile, boot or run time. multihit.rst special-register-buffer-data-sampling.rst processor_mmio_stale_data.rst + gather_data_sampling.rst diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 1f4a0523dc1a..2de3ba280a92 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1447,6 +1447,20 @@ Format: off | on default: on + gather_data_sampling= + [X86,INTEL] Control the Gather Data Sampling (GDS) + mitigation. + + Gather Data Sampling is a hardware vulnerability which + allows unprivileged speculative access to data which was + previously stored in vector registers. + + This issue is mitigated by default in updated microcode. + The mitigation may have a performance impact but can be + disabled. + + off: Disable GDS mitigation. + gcov_persist= [GCOV] When non-zero (default), profiling data for kernel modules is saved and remains accessible via debugfs, even when the module is unloaded/reloaded. @@ -2887,22 +2901,23 @@ Disable all optional CPU mitigations. This improves system performance, but it may also expose users to several CPU vulnerabilities. - Equivalent to: nopti [X86,PPC] + Equivalent to: gather_data_sampling=off [X86] kpti=0 [ARM64] - nospectre_v1 [X86,PPC] - nobp=0 [S390] - nospectre_v2 [X86,PPC,S390,ARM64] - spectre_v2_user=off [X86] - spec_store_bypass_disable=off [X86,PPC] - ssbd=force-off [ARM64] + kvm.nx_huge_pages=off [X86] l1tf=off [X86] mds=off [X86] - tsx_async_abort=off [X86] - kvm.nx_huge_pages=off [X86] + mmio_stale_data=off [X86] no_entry_flush [PPC] no_uaccess_flush [PPC] - mmio_stale_data=off [X86] + nobp=0 [S390] + nopti [X86,PPC] + nospectre_v1 [X86,PPC] + nospectre_v2 [X86,PPC,S390,ARM64] retbleed=off [X86] + spec_store_bypass_disable=off [X86,PPC] + spectre_v2_user=off [X86] + ssbd=force-off [ARM64] + tsx_async_abort=off [X86] Exceptions: This does not have any effect on diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1fcda8263554..f68182300799 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -433,5 +433,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_GDS X86_BUG(29) /* CPU is affected by Gather Data Sampling */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3fab152809ab..83849e37cd20 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -156,6 +156,15 @@ * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. */ +#define ARCH_CAP_GDS_CTRL BIT(25) /* + * CPU is vulnerable to Gather + * Data Sampling (GDS) and + * has controls for mitigation. + */ +#define ARCH_CAP_GDS_NO BIT(26) /* + * CPU is not vulnerable to Gather + * Data Sampling (GDS). + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -174,6 +183,8 @@ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 #define RNGDS_MITG_DIS BIT(0) #define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ +#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */ +#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1ac943f1c99e..f114d4e51a86 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -45,6 +45,7 @@ static void __init md_clear_select_mitigation(void); static void __init taa_select_mitigation(void); static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); +static void __init gds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -150,6 +151,7 @@ void __init cpu_select_mitigations(void) l1tf_select_mitigation(); md_clear_select_mitigation(); srbds_select_mitigation(); + gds_select_mitigation(); } /* @@ -607,6 +609,120 @@ static int __init srbds_parse_cmdline(char *str) } early_param("srbds", srbds_parse_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "GDS: " fmt + +enum gds_mitigations { + GDS_MITIGATION_OFF, + GDS_MITIGATION_UCODE_NEEDED, + GDS_MITIGATION_FULL, + GDS_MITIGATION_FULL_LOCKED, + GDS_MITIGATION_HYPERVISOR, +}; + +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; + +static const char * const gds_strings[] = { + [GDS_MITIGATION_OFF] = "Vulnerable", + [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [GDS_MITIGATION_FULL] = "Mitigation: Microcode", + [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)", + [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +void update_gds_msr(void) +{ + u64 mcu_ctrl_after; + u64 mcu_ctrl; + + switch (gds_mitigation) { + case GDS_MITIGATION_OFF: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl |= GDS_MITG_DIS; + break; + case GDS_MITIGATION_FULL_LOCKED: + /* + * The LOCKED state comes from the boot CPU. APs might not have + * the same state. Make sure the mitigation is enabled on all + * CPUs. + */ + case GDS_MITIGATION_FULL: + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + mcu_ctrl &= ~GDS_MITG_DIS; + break; + case GDS_MITIGATION_UCODE_NEEDED: + case GDS_MITIGATION_HYPERVISOR: + return; + }; + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + /* + * Check to make sure that the WRMSR value was not ignored. Writes to + * GDS_MITG_DIS will be ignored if this processor is locked but the boot + * processor was not. + */ + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after); + WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after); +} + +static void __init gds_select_mitigation(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + gds_mitigation = GDS_MITIGATION_HYPERVISOR; + goto out; + } + + if (cpu_mitigations_off()) + gds_mitigation = GDS_MITIGATION_OFF; + /* Will verify below that mitigation _can_ be disabled */ + + /* No microcode */ + if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + goto out; + } + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + if (mcu_ctrl & GDS_MITG_LOCKED) { + if (gds_mitigation == GDS_MITIGATION_OFF) + pr_warn("Mitigation locked. Disable failed.\n"); + + /* + * The mitigation is selected from the boot CPU. All other CPUs + * _should_ have the same state. If the boot CPU isn't locked + * but others are then update_gds_msr() will WARN() of the state + * mismatch. If the boot CPU is locked update_gds_msr() will + * ensure the other CPUs have the mitigation enabled. + */ + gds_mitigation = GDS_MITIGATION_FULL_LOCKED; + } + + update_gds_msr(); +out: + pr_info("%s\n", gds_strings[gds_mitigation]); +} + +static int __init gds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_GDS)) + return 0; + + if (!strcmp(str, "off")) + gds_mitigation = GDS_MITIGATION_OFF; + + return 0; +} +early_param("gather_data_sampling", gds_parse_cmdline); + #undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt @@ -2286,6 +2402,11 @@ static ssize_t retbleed_show_state(char *buf) return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } +static ssize_t gds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2335,6 +2456,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RETBLEED: return retbleed_show_state(buf); + case X86_BUG_GDS: + return gds_show_state(buf); + default: break; } @@ -2399,4 +2523,9 @@ ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, cha { return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); } + +ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_GDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 977edd149e40..d31fd6a0fbad 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1127,6 +1127,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define MMIO_SBDS BIT(2) /* CPU is affected by RETbleed, speculating where you would not expect it */ #define RETBLEED BIT(3) +/* CPU is affected by GDS */ +#define GDS BIT(4) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1139,19 +1141,21 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), + VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS), + VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), @@ -1277,6 +1281,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !(ia32_cap & ARCH_CAP_PBRSB_NO)) setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + /* + * Check if CPU is vulnerable to GDS. If running in a virtual machine on + * an affected processor, the VMM may have disabled the use of GATHER by + * disabling AVX2. The only way to do this in HW is to clear XCR0[2], + * which means that AVX will be disabled. + */ + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + boot_cpu_has(X86_FEATURE_AVX)) + setup_force_cpu_bug(X86_BUG_GDS); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -1795,6 +1809,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); + if (boot_cpu_has_bug(X86_BUG_GDS)) + update_gds_msr(); } static __init int setup_noclflush(char *arg) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 215416e8a8de..66e19380a899 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -82,6 +82,7 @@ void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); +extern void update_gds_msr(void); extern u64 x86_read_arch_cap_msr(void); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 33e0526907eb..0cb8ec80ddfd 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -579,6 +579,12 @@ ssize_t __weak cpu_show_retbleed(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_gds(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -590,6 +596,7 @@ static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); +static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -603,6 +610,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_srbds.attr, &dev_attr_mmio_stale_data.attr, &dev_attr_retbleed.attr, + &dev_attr_gather_data_sampling.attr, NULL }; From 363c98f9cfa8124cc49b2dfc5d48666b138f7e2e Mon Sep 17 00:00:00 2001 From: Daniel Sneddon Date: Wed, 12 Jul 2023 19:43:12 -0700 Subject: [PATCH 4267/4345] x86/speculation: Add force option to GDS mitigation commit 553a5c03e90a6087e88f8ff878335ef0621536fb upstream The Gather Data Sampling (GDS) vulnerability allows malicious software to infer stale data previously stored in vector registers. This may include sensitive data such as cryptographic keys. GDS is mitigated in microcode, and systems with up-to-date microcode are protected by default. However, any affected system that is running with older microcode will still be vulnerable to GDS attacks. Since the gather instructions used by the attacker are part of the AVX2 and AVX512 extensions, disabling these extensions prevents gather instructions from being executed, thereby mitigating the system from GDS. Disabling AVX2 is sufficient, but we don't have the granularity to do this. The XCR0[2] disables AVX, with no option to just disable AVX2. Add a kernel parameter gather_data_sampling=force that will enable the microcode mitigation if available, otherwise it will disable AVX on affected systems. This option will be ignored if cmdline mitigations=off. This is a *big* hammer. It is known to break buggy userspace that uses incomplete, buggy AVX enumeration. Unfortunately, such userspace does exist in the wild: https://www.mail-archive.com/bug-coreutils@gnu.org/msg33046.html [ dhansen: add some more ominous warnings about disabling AVX ] Signed-off-by: Daniel Sneddon Signed-off-by: Dave Hansen Acked-by: Josh Poimboeuf Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- .../hw-vuln/gather_data_sampling.rst | 18 +++++++++++++---- .../admin-guide/kernel-parameters.txt | 8 +++++++- arch/x86/kernel/cpu/bugs.c | 20 ++++++++++++++++++- 3 files changed, 40 insertions(+), 6 deletions(-) diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst index 74dab6af7fe1..40b7a6260010 100644 --- a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst +++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst @@ -60,14 +60,21 @@ bits: ================================ === ============================ GDS can also be mitigated on systems that don't have updated microcode by -disabling AVX. This can be done by setting "clearcpuid=avx" on the kernel -command-line. +disabling AVX. This can be done by setting gather_data_sampling="force" or +"clearcpuid=avx" on the kernel command-line. + +If used, these options will disable AVX use by turning on XSAVE YMM support. +However, the processor will still enumerate AVX support. Userspace that +does not follow proper AVX enumeration to check both AVX *and* XSAVE YMM +support will break. Mitigation control on the kernel command line --------------------------------------------- The mitigation can be disabled by setting "gather_data_sampling=off" or -"mitigations=off" on the kernel command line. Not specifying either will -default to the mitigation being enabled. +"mitigations=off" on the kernel command line. Not specifying either will default +to the mitigation being enabled. Specifying "gather_data_sampling=force" will +use the microcode mitigation when available or disable AVX on affected systems +where the microcode hasn't been updated to include the mitigation. GDS System Information ------------------------ @@ -83,6 +90,9 @@ The possible values contained in this file are: Vulnerable Processor vulnerable and mitigation disabled. Vulnerable: No microcode Processor vulnerable and microcode is missing mitigation. + Mitigation: AVX disabled, + no microcode Processor is vulnerable and microcode is missing + mitigation. AVX disabled as mitigation. Mitigation: Microcode Processor is vulnerable and mitigation is in effect. Mitigation: Microcode (locked) Processor is vulnerable and mitigation is in diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 2de3ba280a92..074e39deef04 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1457,7 +1457,13 @@ This issue is mitigated by default in updated microcode. The mitigation may have a performance impact but can be - disabled. + disabled. On systems without the microcode mitigation + disabling AVX serves as a mitigation. + + force: Disable AVX to mitigate systems without + microcode mitigation. No effect if the microcode + mitigation is present. Known to cause crashes in + userspace with buggy AVX enumeration. off: Disable GDS mitigation. diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index f114d4e51a86..010d487f627c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -615,6 +615,7 @@ early_param("srbds", srbds_parse_cmdline); enum gds_mitigations { GDS_MITIGATION_OFF, GDS_MITIGATION_UCODE_NEEDED, + GDS_MITIGATION_FORCE, GDS_MITIGATION_FULL, GDS_MITIGATION_FULL_LOCKED, GDS_MITIGATION_HYPERVISOR, @@ -625,6 +626,7 @@ static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL static const char * const gds_strings[] = { [GDS_MITIGATION_OFF] = "Vulnerable", [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [GDS_MITIGATION_FORCE] = "Mitigation: AVX disabled, no microcode", [GDS_MITIGATION_FULL] = "Mitigation: Microcode", [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)", [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", @@ -650,6 +652,7 @@ void update_gds_msr(void) rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); mcu_ctrl &= ~GDS_MITG_DIS; break; + case GDS_MITIGATION_FORCE: case GDS_MITIGATION_UCODE_NEEDED: case GDS_MITIGATION_HYPERVISOR: return; @@ -684,10 +687,23 @@ static void __init gds_select_mitigation(void) /* No microcode */ if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { - gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + if (gds_mitigation == GDS_MITIGATION_FORCE) { + /* + * This only needs to be done on the boot CPU so do it + * here rather than in update_gds_msr() + */ + setup_clear_cpu_cap(X86_FEATURE_AVX); + pr_warn("Microcode update needed! Disabling AVX as mitigation.\n"); + } else { + gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; + } goto out; } + /* Microcode has mitigation, use it */ + if (gds_mitigation == GDS_MITIGATION_FORCE) + gds_mitigation = GDS_MITIGATION_FULL; + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); if (mcu_ctrl & GDS_MITG_LOCKED) { if (gds_mitigation == GDS_MITIGATION_OFF) @@ -718,6 +734,8 @@ static int __init gds_parse_cmdline(char *str) if (!strcmp(str, "off")) gds_mitigation = GDS_MITIGATION_OFF; + else if (!strcmp(str, "force")) + gds_mitigation = GDS_MITIGATION_FORCE; return 0; } From 7db4ddcb8d8e356387a773728b2479d390488b1e Mon Sep 17 00:00:00 2001 From: Daniel Sneddon Date: Wed, 12 Jul 2023 19:43:13 -0700 Subject: [PATCH 4268/4345] x86/speculation: Add Kconfig option for GDS commit 53cf5797f114ba2bd86d23a862302119848eff19 upstream Gather Data Sampling (GDS) is mitigated in microcode. However, on systems that haven't received the updated microcode, disabling AVX can act as a mitigation. Add a Kconfig option that uses the microcode mitigation if available and disables AVX otherwise. Setting this option has no effect on systems not affected by GDS. This is the equivalent of setting gather_data_sampling=force. Signed-off-by: Daniel Sneddon Signed-off-by: Dave Hansen Acked-by: Josh Poimboeuf Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/Kconfig | 19 +++++++++++++++++++ arch/x86/kernel/cpu/bugs.c | 4 ++++ 2 files changed, 23 insertions(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d1c734289bdd..25fda0590e5d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2485,6 +2485,25 @@ config SLS against straight line speculation. The kernel image might be slightly larger. +config GDS_FORCE_MITIGATION + bool "Force GDS Mitigation" + depends on CPU_SUP_INTEL + default n + help + Gather Data Sampling (GDS) is a hardware vulnerability which allows + unprivileged speculative access to data which was previously stored in + vector registers. + + This option is equivalent to setting gather_data_sampling=force on the + command line. The microcode mitigation is used if present, otherwise + AVX is disabled as a mitigation. On affected systems that are missing + the microcode any userspace code that unconditionally uses AVX will + break with this option set. + + Setting this option on systems not vulnerable to GDS has no effect. + + If in doubt, say N. + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 010d487f627c..ed263807f62c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -621,7 +621,11 @@ enum gds_mitigations { GDS_MITIGATION_HYPERVISOR, }; +#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION) +static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; +#else static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; +#endif static const char * const gds_strings[] = { [GDS_MITIGATION_OFF] = "Vulnerable", From eb13cce488745176db654b20ea438f4b5b91ab9c Mon Sep 17 00:00:00 2001 From: Daniel Sneddon Date: Wed, 12 Jul 2023 19:43:14 -0700 Subject: [PATCH 4269/4345] KVM: Add GDS_NO support to KVM commit 81ac7e5d741742d650b4ed6186c4826c1a0631a7 upstream Gather Data Sampling (GDS) is a transient execution attack using gather instructions from the AVX2 and AVX512 extensions. This attack allows malicious code to infer data that was previously stored in vector registers. Systems that are not vulnerable to GDS will set the GDS_NO bit of the IA32_ARCH_CAPABILITIES MSR. This is useful for VM guests that may think they are on vulnerable systems that are, in fact, not affected. Guests that are running on affected hosts where the mitigation is enabled are protected as if they were running on an unaffected system. On all hosts that are not affected or that are mitigated, set the GDS_NO bit. Signed-off-by: Daniel Sneddon Signed-off-by: Dave Hansen Acked-by: Josh Poimboeuf Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/bugs.c | 7 +++++++ arch/x86/kvm/x86.c | 7 ++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index ed263807f62c..21f4bdbcfb4b 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -636,6 +636,13 @@ static const char * const gds_strings[] = { [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", }; +bool gds_ucode_mitigated(void) +{ + return (gds_mitigation == GDS_MITIGATION_FULL || + gds_mitigation == GDS_MITIGATION_FULL_LOCKED); +} +EXPORT_SYMBOL_GPL(gds_ucode_mitigated); + void update_gds_msr(void) { u64 mcu_ctrl_after; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 34670943f543..cf4739200566 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -255,6 +255,8 @@ static struct kmem_cache *x86_fpu_cache; static struct kmem_cache *x86_emulator_cache; +extern bool gds_ucode_mitigated(void); + /* * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. @@ -1389,7 +1391,7 @@ static unsigned int num_msr_based_features; ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1446,6 +1448,9 @@ static u64 kvm_get_arch_capabilities(void) */ } + if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) + data |= ARCH_CAP_GDS_NO; + return data; } From 583016037a092e4189c86bad7946c6d88669b4ca Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 3 Jul 2023 15:00:32 +0200 Subject: [PATCH 4270/4345] x86/xen: Fix secondary processors' FPU initialization commit fe3e0a13e597c1c8617814bf9b42ab732db5c26e upstream. Moving the call of fpu__init_cpu() from cpu_init() to start_secondary() broke Xen PV guests, as those don't call start_secondary() for APs. Call fpu__init_cpu() in Xen's cpu_bringup(), which is the Xen PV replacement of start_secondary(). Fixes: b81fac906a8f ("x86/fpu: Move FPU initialization into arch_cpu_finalize_init()") Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Boris Ostrovsky Acked-by: Thomas Gleixner Link: https://lore.kernel.org/r/20230703130032.22916-1-jgross@suse.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/xen/smp_pv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 64873937cd1d..755e939db3ed 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -63,6 +64,7 @@ static void cpu_bringup(void) cr4_init(); cpu_init(); + fpu__init_cpu(); touch_softlockup_watchdog(); preempt_disable(); From f076d081787803b972a9939e477c6456f0c8fd70 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 9 Jan 2023 16:09:22 +0100 Subject: [PATCH 4271/4345] x86/mm: fix poking_init() for Xen PV guests commit 26ce6ec364f18d2915923bc05784084e54a5c4cc upstream. Commit 3f4c8211d982 ("x86/mm: Use mm_alloc() in poking_init()") broke the kernel for running as Xen PV guest. It seems as if the new address space is never activated before being used, resulting in Xen rejecting to accept the new CR3 value (the PGD isn't pinned). Fix that by adding the now missing call of paravirt_arch_dup_mmap() to poking_init(). That call was previously done by dup_mm()->dup_mmap() and it is a NOP for all cases but for Xen PV, where it is just doing the pinning of the PGD. Fixes: 3f4c8211d982 ("x86/mm: Use mm_alloc() in poking_init()") Signed-off-by: Juergen Gross Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230109150922.10578-1-jgross@suse.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/init.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index ff3b0d8fe048..2234d1c3f412 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -27,6 +27,7 @@ #include #include #include +#include /* * We need to define the tracepoints somewhere, and tlb.c @@ -807,6 +808,9 @@ void __init poking_init(void) poking_mm = copy_init_mm(); BUG_ON(!poking_mm); + /* Xen PV guests need the PGD to be pinned. */ + paravirt_arch_dup_mmap(NULL, poking_mm); + /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, From 6ee042fd240fb669f4637f8cd89899b15911e5df Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Oct 2022 21:38:21 +0200 Subject: [PATCH 4272/4345] x86/mm: Use mm_alloc() in poking_init() commit 3f4c8211d982099be693be9aa7d6fc4607dff290 upstream. Instead of duplicating init_mm, allocate a fresh mm. The advantage is that mm_alloc() has much simpler dependencies. Additionally it makes more conceptual sense, init_mm has no (and must not have) user state to duplicate. Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20221025201057.816175235@infradead.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/init.c | 3 ++- include/linux/sched/task.h | 1 - kernel/fork.c | 5 ----- 3 files changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 2234d1c3f412..dd15fdee4536 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -805,7 +806,7 @@ void __init poking_init(void) spinlock_t *ptl; pte_t *ptep; - poking_mm = copy_init_mm(); + poking_mm = mm_alloc(); BUG_ON(!poking_mm); /* Xen PV guests need the PGD to be pinned. */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 2832cc6be062..90c04195f939 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -89,7 +89,6 @@ extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); -struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); diff --git a/kernel/fork.c b/kernel/fork.c index c6a289317e89..6386ab077d8a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2424,11 +2424,6 @@ struct task_struct * __init fork_idle(int cpu) return task; } -struct mm_struct *copy_init_mm(void) -{ - return dup_mm(NULL, &init_mm); -} - /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. From 1ff14defdfc9180bfcfd76a70463a5feb188a5db Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Oct 2022 21:38:18 +0200 Subject: [PATCH 4273/4345] mm: Move mm_cachep initialization to mm_init() commit af80602799681c78f14fbe20b6185a56020dedee upstream. In order to allow using mm_alloc() much earlier, move initializing mm_cachep into mm_init(). Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20221025201057.751153381@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/sched/task.h | 1 + init/main.c | 1 + kernel/fork.c | 32 ++++++++++++++++++-------------- 3 files changed, 20 insertions(+), 14 deletions(-) diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 90c04195f939..e8304e929e28 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -63,6 +63,7 @@ extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); void __noreturn make_task_dead(int signr); +extern void mm_cache_init(void); extern void proc_caches_init(void); extern void fork_init(void); diff --git a/init/main.c b/init/main.c index 1a3d0bea5735..402d290f0fc4 100644 --- a/init/main.c +++ b/init/main.c @@ -835,6 +835,7 @@ static void __init mm_init(void) init_espfix_bsp(); /* Should be run after espfix64 is set up. */ pti_init(); + mm_cache_init(); } void __init __weak arch_call_rest_init(void) diff --git a/kernel/fork.c b/kernel/fork.c index 6386ab077d8a..31455f5ab015 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2818,10 +2818,27 @@ static void sighand_ctor(void *data) init_waitqueue_head(&sighand->signalfd_wqh); } -void __init proc_caches_init(void) +void __init mm_cache_init(void) { unsigned int mm_size; + /* + * The mm_cpumask is located at the end of mm_struct, and is + * dynamically sized based on the maximum CPU number this system + * can have, taking hotplug into account (nr_cpu_ids). + */ + mm_size = sizeof(struct mm_struct) + cpumask_size(); + + mm_cachep = kmem_cache_create_usercopy("mm_struct", + mm_size, ARCH_MIN_MMSTRUCT_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, + offsetof(struct mm_struct, saved_auxv), + sizeof_field(struct mm_struct, saved_auxv), + NULL); +} + +void __init proc_caches_init(void) +{ sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| @@ -2839,19 +2856,6 @@ void __init proc_caches_init(void) SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); - /* - * The mm_cpumask is located at the end of mm_struct, and is - * dynamically sized based on the maximum CPU number this system - * can have, taking hotplug into account (nr_cpu_ids). - */ - mm_size = sizeof(struct mm_struct) + cpumask_size(); - - mm_cachep = kmem_cache_create_usercopy("mm_struct", - mm_size, ARCH_MIN_MMSTRUCT_ALIGN, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, - offsetof(struct mm_struct, saved_auxv), - sizeof_field(struct mm_struct, saved_auxv), - NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); From 79972c2b95eca5e7d3d237d728339b21e9075629 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Oct 2022 21:38:25 +0200 Subject: [PATCH 4274/4345] x86/mm: Initialize text poking earlier commit 5b93a83649c7cba3a15eb7e8959b250841acb1b1 upstream. Move poking_init() up a bunch; specifically move it right after mm_init() which is right before ftrace_init(). This will allow simplifying ftrace text poking which currently has a bunch of exceptions for early boot. Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20221025201057.881703081@infradead.org Signed-off-by: Greg Kroah-Hartman --- init/main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/init/main.c b/init/main.c index 402d290f0fc4..298989b0d4e8 100644 --- a/init/main.c +++ b/init/main.c @@ -900,7 +900,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) sort_main_extable(); trap_init(); mm_init(); - + poking_init(); ftrace_init(); /* trace_printk can be enabled here */ @@ -1035,8 +1035,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) taskstats_init_early(); delayacct_init(); - poking_init(); - acpi_subsystem_init(); arch_post_acpi_subsys_init(); sfi_init_late(); From 6750468784314bc8a336f80493cd82cde2afa655 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 1 Aug 2023 07:31:07 -0700 Subject: [PATCH 4275/4345] Documentation/x86: Fix backwards on/off logic about YMM support commit 1b0fc0345f2852ffe54fb9ae0e12e2ee69ad6a20 upstream These options clearly turn *off* XSAVE YMM support. Correct the typo. Reported-by: Ben Hutchings Fixes: 553a5c03e90a ("x86/speculation: Add force option to GDS mitigation") Signed-off-by: Dave Hansen Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/hw-vuln/gather_data_sampling.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst index 40b7a6260010..264bfa937f7d 100644 --- a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst +++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst @@ -63,7 +63,7 @@ GDS can also be mitigated on systems that don't have updated microcode by disabling AVX. This can be done by setting gather_data_sampling="force" or "clearcpuid=avx" on the kernel command-line. -If used, these options will disable AVX use by turning on XSAVE YMM support. +If used, these options will disable AVX use by turning off XSAVE YMM support. However, the processor will still enumerate AVX support. Userspace that does not follow proper AVX enumeration to check both AVX *and* XSAVE YMM support will break. From baf6d6c39e2390ef91bec12d057294dd507d1115 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Thu, 10 Dec 2020 11:09:36 -0600 Subject: [PATCH 4276/4345] x86/cpu: Add VM page flush MSR availablility as a CPUID feature commit 69372cf01290b9587d2cee8fbe161d75d55c3adc upstream. On systems that do not have hardware enforced cache coherency between encrypted and unencrypted mappings of the same physical page, the hypervisor can use the VM page flush MSR (0xc001011e) to flush the cache contents of an SEV guest page. When a small number of pages are being flushed, this can be used in place of issuing a WBINVD across all CPUs. CPUID 0x8000001f_eax[2] is used to determine if the VM page flush MSR is available. Add a CPUID feature to indicate it is supported and define the MSR. Signed-off-by: Tom Lendacky Message-Id: Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/msr-index.h | 1 + arch/x86/kernel/cpu/scattered.c | 1 + 3 files changed, 3 insertions(+) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index f68182300799..fe8c66cb0789 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -237,6 +237,7 @@ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ #define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_VM_PAGE_FLUSH ( 8*32+21) /* "" VM Page Flush MSR is supported */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 83849e37cd20..2bc4fa9ad3e5 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -530,6 +530,7 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 82fe492121bb..9bca00693005 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -45,6 +45,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 }, { X86_FEATURE_SEV_ES, CPUID_EAX, 3, 0x8000001f, 0 }, { X86_FEATURE_SME_COHERENT, CPUID_EAX, 10, 0x8000001f, 0 }, + { X86_FEATURE_VM_PAGE_FLUSH, CPUID_EAX, 2, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; From 437fa179f2136d349fda78331fd28696e40def9d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 22 Jan 2021 12:40:46 -0800 Subject: [PATCH 4277/4345] x86/cpufeatures: Assign dedicated feature word for CPUID_0x8000001F[EAX] commit fb35d30fe5b06cc24444f0405da8fbe0be5330d1 upstream. Collect the scattered SME/SEV related feature flags into a dedicated word. There are now five recognized features in CPUID.0x8000001F.EAX, with at least one more on the horizon (SEV-SNP). Using a dedicated word allows KVM to use its automagic CPUID adjustment logic when reporting the set of supported features to userspace. No functional change intended. Signed-off-by: Sean Christopherson Signed-off-by: Borislav Petkov Reviewed-by: Brijesh Singh Link: https://lkml.kernel.org/r/20210122204047.2860075-2-seanjc@google.com Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeature.h | 7 +++++-- arch/x86/include/asm/cpufeatures.h | 17 +++++++++++------ arch/x86/include/asm/disabled-features.h | 3 ++- arch/x86/include/asm/required-features.h | 3 ++- arch/x86/kernel/cpu/common.c | 3 +++ arch/x86/kernel/cpu/scattered.c | 5 ----- tools/arch/x86/include/asm/disabled-features.h | 3 ++- tools/arch/x86/include/asm/required-features.h | 3 ++- 8 files changed, 27 insertions(+), 17 deletions(-) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index f4cbc01c0bc4..b0f206681fde 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -31,6 +31,7 @@ enum cpuid_leafs CPUID_7_ECX, CPUID_8000_0007_EBX, CPUID_7_EDX, + CPUID_8000_001F_EAX, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -89,8 +90,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 19)) + BUILD_BUG_ON_ZERO(NCAPINTS != 20)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -112,8 +114,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 19)) + BUILD_BUG_ON_ZERO(NCAPINTS != 20)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index fe8c66cb0789..c1058ab69d5c 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 19 /* N 32-bit words worth of info */ +#define NCAPINTS 20 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -96,7 +96,7 @@ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -#define X86_FEATURE_SME_COHERENT ( 3*32+17) /* "" AMD hardware-enforced cache coherency */ +/* FREE! ( 3*32+17) */ #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ @@ -201,7 +201,7 @@ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ +/* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ #define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ @@ -211,7 +211,7 @@ #define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ +/* FREE! ( 7*32+20) */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ @@ -236,8 +236,6 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ -#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_VM_PAGE_FLUSH ( 8*32+21) /* "" VM Page Flush MSR is supported */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -394,6 +392,13 @@ #define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ +/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ +#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ + /* * BUG word(s) */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 16c24915210d..da21405ea11c 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -101,6 +101,7 @@ DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) +#define DISABLED_MASK19 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 3ff0d48469f2..b2d504f11937 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -101,6 +101,7 @@ #define REQUIRED_MASK16 0 #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) +#define REQUIRED_MASK19 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d31fd6a0fbad..28e0147d7915 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -966,6 +966,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); + if (c->extended_cpuid_level >= 0x8000001f) + c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f); + init_scattered_cpuid_features(c); init_speculation_control(c); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 9bca00693005..f1cd1b6fb99e 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -41,11 +41,6 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, - { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, - { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 }, - { X86_FEATURE_SEV_ES, CPUID_EAX, 3, 0x8000001f, 0 }, - { X86_FEATURE_SME_COHERENT, CPUID_EAX, 10, 0x8000001f, 0 }, - { X86_FEATURE_VM_PAGE_FLUSH, CPUID_EAX, 2, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index d109c5ec967c..a50f075244b4 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -104,6 +104,7 @@ DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) +#define DISABLED_MASK19 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index 3ff0d48469f2..b2d504f11937 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -101,6 +101,7 @@ #define REQUIRED_MASK16 0 #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) +#define REQUIRED_MASK19 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ From 9b7fe7c6fbc007564f97805ff45882e79f0c70d0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 2 Mar 2021 17:16:17 -0300 Subject: [PATCH 4278/4345] tools headers cpufeatures: Sync with the kernel sources commit 1a9bcadd0058a3e81c1beca48e5e08dee9446a01 upstream. To pick the changes from: 3b9c723ed7cfa4e1 ("KVM: SVM: Add support for SVM instruction address check change") b85a0425d8056f3b ("Enumerate AVX Vector Neural Network instructions") fb35d30fe5b06cc2 ("x86/cpufeatures: Assign dedicated feature word for CPUID_0x8000001F[EAX]") This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Cc: Borislav Petkov Cc: Kyung Min Park Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Wei Huang Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/arch/x86/include/asm/cpufeatures.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index ec53f52a06a5..d06ed44c4827 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 19 /* N 32-bit words worth of info */ +#define NCAPINTS 20 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -96,7 +96,7 @@ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -#define X86_FEATURE_SME_COHERENT ( 3*32+17) /* "" AMD hardware-enforced cache coherency */ +/* FREE! ( 3*32+17) */ #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ @@ -201,7 +201,7 @@ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ +/* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ #define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ @@ -211,7 +211,7 @@ #define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ +/* FREE! ( 7*32+20) */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ @@ -236,7 +236,6 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ -#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -299,6 +298,7 @@ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM-Exit when EIBRS is enabled */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ +#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ @@ -343,6 +343,7 @@ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ +#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ @@ -389,6 +390,13 @@ #define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ +/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ +#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ + /* * BUG word(s) */ From 073a28a9b50662991e7d6956c2cf2fc5d54f28cd Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Sat, 8 Jul 2023 10:21:35 +0200 Subject: [PATCH 4279/4345] x86/bugs: Increase the x86 bugs vector size to two u32s Upstream commit: 0e52740ffd10c6c316837c6c128f460f1aaba1ea There was never a doubt in my mind that they would not fit into a single u32 eventually. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 2 +- tools/arch/x86/include/asm/cpufeatures.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index c1058ab69d5c..29c05123b40a 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 20 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index d06ed44c4827..2ae4d74ee73b 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -14,7 +14,7 @@ * Defines x86 CPU feature bits */ #define NCAPINTS 20 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NBUGINTS 2 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used From 34f23ba8a399ecd38b45c84da257b91d278e88aa Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Tue, 10 Jan 2023 16:46:37 -0600 Subject: [PATCH 4280/4345] x86/cpu, kvm: Add support for CPUID_80000021_EAX commit 8415a74852d7c24795007ee9862d25feb519007c upstream. Add support for CPUID leaf 80000021, EAX. The majority of the features will be used in the kernel and thus a separate leaf is appropriate. Include KVM's reverse_cpuid entry because features are used by VM guests, too. [ bp: Massage commit message. ] Signed-off-by: Kim Phillips Signed-off-by: Borislav Petkov (AMD) Acked-by: Sean Christopherson Link: https://lore.kernel.org/r/20230124163319.2277355-2-kim.phillips@amd.com [bwh: Backported to 6.1: adjust context] Signed-off-by: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeature.h | 7 +++++-- arch/x86/include/asm/cpufeatures.h | 2 +- arch/x86/include/asm/disabled-features.h | 3 ++- arch/x86/include/asm/required-features.h | 3 ++- arch/x86/kernel/cpu/common.c | 3 +++ arch/x86/kvm/cpuid.h | 1 + 6 files changed, 14 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index b0f206681fde..cc3f62f5d551 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -32,6 +32,7 @@ enum cpuid_leafs CPUID_8000_0007_EBX, CPUID_7_EDX, CPUID_8000_001F_EAX, + CPUID_8000_0021_EAX, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -91,8 +92,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 20)) + BUILD_BUG_ON_ZERO(NCAPINTS != 21)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -115,8 +117,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 20)) + BUILD_BUG_ON_ZERO(NCAPINTS != 21)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 29c05123b40a..074860357896 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 20 /* N 32-bit words worth of info */ +#define NCAPINTS 21 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index da21405ea11c..3c24378e67be 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -102,6 +102,7 @@ #define DISABLED_MASK17 0 #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define DISABLED_MASK20 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index b2d504f11937..9bf60a8b9e9c 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -102,6 +102,7 @@ #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20) +#define REQUIRED_MASK20 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 28e0147d7915..7f92145913e5 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -969,6 +969,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x8000001f) c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f); + if (c->extended_cpuid_level >= 0x80000021) + c->x86_capability[CPUID_8000_0021_EAX] = cpuid_eax(0x80000021); + init_scattered_cpuid_features(c); init_speculation_control(c); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index dc921d76e42e..1ba9313d26b9 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -63,6 +63,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX}, [CPUID_7_EDX] = { 7, 0, CPUID_EDX}, [CPUID_7_1_EAX] = { 7, 1, CPUID_EAX}, + [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, }; /* From 3f9b7101bea1dcb63410c016ceb266f6e9f733c9 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Wed, 28 Jun 2023 11:02:39 +0200 Subject: [PATCH 4281/4345] x86/srso: Add a Speculative RAS Overflow mitigation Upstream commit: fb3bd914b3ec28f5fb697ac55c4846ac2d542855 Add a mitigation for the speculative return address stack overflow vulnerability found on AMD processors. The mitigation works by ensuring all RET instructions speculate to a controlled location, similar to how speculation is controlled in the retpoline sequence. To accomplish this, the __x86_return_thunk forces the CPU to mispredict every function return using a 'safe return' sequence. To ensure the safety of this mitigation, the kernel must ensure that the safe return sequence is itself free from attacker interference. In Zen3 and Zen4, this is accomplished by creating a BTB alias between the untraining function srso_untrain_ret_alias() and the safe return function srso_safe_ret_alias() which results in evicting a potentially poisoned BTB entry and using that safe one for all function returns. In older Zen1 and Zen2, this is accomplished using a reinterpretation technique similar to Retbleed one: srso_untrain_ret() and srso_safe_ret(). Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/hw-vuln/index.rst | 1 + Documentation/admin-guide/hw-vuln/srso.rst | 133 ++++++++++++++++++ .../admin-guide/kernel-parameters.txt | 11 ++ arch/x86/Kconfig | 7 + arch/x86/include/asm/cpufeatures.h | 5 + arch/x86/include/asm/nospec-branch.h | 9 +- arch/x86/include/asm/processor.h | 2 + arch/x86/kernel/alternative.c | 4 +- arch/x86/kernel/cpu/amd.c | 14 ++ arch/x86/kernel/cpu/bugs.c | 106 ++++++++++++++ arch/x86/kernel/cpu/common.c | 8 +- arch/x86/kernel/vmlinux.lds.S | 32 ++++- arch/x86/lib/retpoline.S | 81 ++++++++++- drivers/base/cpu.c | 8 ++ include/linux/cpu.h | 2 + tools/objtool/arch/x86/decode.c | 5 +- 16 files changed, 419 insertions(+), 9 deletions(-) create mode 100644 Documentation/admin-guide/hw-vuln/srso.rst diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 245468b0f2be..84742be223ff 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -17,3 +17,4 @@ are configurable at compile, boot or run time. special-register-buffer-data-sampling.rst processor_mmio_stale_data.rst gather_data_sampling.rst + srso diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst new file mode 100644 index 000000000000..2f923c805802 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/srso.rst @@ -0,0 +1,133 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Speculative Return Stack Overflow (SRSO) +======================================== + +This is a mitigation for the speculative return stack overflow (SRSO) +vulnerability found on AMD processors. The mechanism is by now the well +known scenario of poisoning CPU functional units - the Branch Target +Buffer (BTB) and Return Address Predictor (RAP) in this case - and then +tricking the elevated privilege domain (the kernel) into leaking +sensitive data. + +AMD CPUs predict RET instructions using a Return Address Predictor (aka +Return Address Stack/Return Stack Buffer). In some cases, a non-architectural +CALL instruction (i.e., an instruction predicted to be a CALL but is +not actually a CALL) can create an entry in the RAP which may be used +to predict the target of a subsequent RET instruction. + +The specific circumstances that lead to this varies by microarchitecture +but the concern is that an attacker can mis-train the CPU BTB to predict +non-architectural CALL instructions in kernel space and use this to +control the speculative target of a subsequent kernel RET, potentially +leading to information disclosure via a speculative side-channel. + +The issue is tracked under CVE-2023-20569. + +Affected processors +------------------- + +AMD Zen, generations 1-4. That is, all families 0x17 and 0x19. Older +processors have not been investigated. + +System information and options +------------------------------ + +First of all, it is required that the latest microcode be loaded for +mitigations to be effective. + +The sysfs file showing SRSO mitigation status is: + + /sys/devices/system/cpu/vulnerabilities/spec_rstack_overflow + +The possible values in this file are: + + - 'Not affected' The processor is not vulnerable + + - 'Vulnerable: no microcode' The processor is vulnerable, no + microcode extending IBPB functionality + to address the vulnerability has been + applied. + + - 'Mitigation: microcode' Extended IBPB functionality microcode + patch has been applied. It does not + address User->Kernel and Guest->Host + transitions protection but it does + address User->User and VM->VM attack + vectors. + + (spec_rstack_overflow=microcode) + + - 'Mitigation: safe RET' Software-only mitigation. It complements + the extended IBPB microcode patch + functionality by addressing User->Kernel + and Guest->Host transitions protection. + + Selected by default or by + spec_rstack_overflow=safe-ret + + - 'Mitigation: IBPB' Similar protection as "safe RET" above + but employs an IBPB barrier on privilege + domain crossings (User->Kernel, + Guest->Host). + + (spec_rstack_overflow=ibpb) + + - 'Mitigation: IBPB on VMEXIT' Mitigation addressing the cloud provider + scenario - the Guest->Host transitions + only. + + (spec_rstack_overflow=ibpb-vmexit) + +In order to exploit vulnerability, an attacker needs to: + + - gain local access on the machine + + - break kASLR + + - find gadgets in the running kernel in order to use them in the exploit + + - potentially create and pin an additional workload on the sibling + thread, depending on the microarchitecture (not necessary on fam 0x19) + + - run the exploit + +Considering the performance implications of each mitigation type, the +default one is 'Mitigation: safe RET' which should take care of most +attack vectors, including the local User->Kernel one. + +As always, the user is advised to keep her/his system up-to-date by +applying software updates regularly. + +The default setting will be reevaluated when needed and especially when +new attack vectors appear. + +As one can surmise, 'Mitigation: safe RET' does come at the cost of some +performance depending on the workload. If one trusts her/his userspace +and does not want to suffer the performance impact, one can always +disable the mitigation with spec_rstack_overflow=off. + +Similarly, 'Mitigation: IBPB' is another full mitigation type employing +an indrect branch prediction barrier after having applied the required +microcode patch for one's system. This mitigation comes also at +a performance cost. + +Mitigation: safe RET +-------------------- + +The mitigation works by ensuring all RET instructions speculate to +a controlled location, similar to how speculation is controlled in the +retpoline sequence. To accomplish this, the __x86_return_thunk forces +the CPU to mispredict every function return using a 'safe return' +sequence. + +To ensure the safety of this mitigation, the kernel must ensure that the +safe return sequence is itself free from attacker interference. In Zen3 +and Zen4, this is accomplished by creating a BTB alias between the +untraining function srso_untrain_ret_alias() and the safe return +function srso_safe_ret_alias() which results in evicting a potentially +poisoned BTB entry and using that safe one for all function returns. + +In older Zen1 and Zen2, this is accomplished using a reinterpretation +technique similar to Retbleed one: srso_untrain_ret() and +srso_safe_ret(). diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 074e39deef04..f1f7c068cf65 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5141,6 +5141,17 @@ Not specifying this option is equivalent to spectre_v2_user=auto. + spec_rstack_overflow= + [X86] Control RAS overflow mitigation on AMD Zen CPUs + + off - Disable mitigation + microcode - Enable microcode mitigation only + safe-ret - Enable sw-only safe RET mitigation (default) + ibpb - Enable mitigation by issuing IBPB on + kernel entry + ibpb-vmexit - Issue IBPB only on VMEXIT + (cloud-specific mitigation) + spec_store_bypass_disable= [HW] Control Speculative Store Bypass (SSB) Disable mitigation (Speculative Store Bypass vulnerability) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 25fda0590e5d..6dc670e36393 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2476,6 +2476,13 @@ config CPU_IBRS_ENTRY This mitigates both spectre_v2 and retbleed at great cost to performance. +config CPU_SRSO + bool "Mitigate speculative RAS overflow on AMD" + depends on CPU_SUP_AMD && X86_64 && RETHUNK + default y + help + Enable the SRSO mitigation needed on AMD Zen1-4 machines. + config SLS bool "Mitigate Straight-Line-Speculation" depends on CC_HAS_SLS && X86_64 diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 074860357896..f54207b90cad 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -301,6 +301,9 @@ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+18) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ + /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -441,4 +444,6 @@ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_GDS X86_BUG(29) /* CPU is affected by Gather Data Sampling */ +/* BUG word 2 */ +#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f14cdf951249..e882fea99e13 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -112,7 +112,7 @@ * eventually turn into it's own annotation. */ .macro ANNOTATE_UNRET_END -#ifdef CONFIG_DEBUG_ENTRY +#if (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif @@ -179,6 +179,11 @@ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif + +#ifdef CONFIG_CPU_SRSO + ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \ + "call srso_untrain_ret_alias", X86_FEATURE_SRSO_ALIAS +#endif .endm #else /* __ASSEMBLY__ */ @@ -191,6 +196,8 @@ extern void __x86_return_thunk(void); extern void zen_untrain_ret(void); +extern void srso_untrain_ret(void); +extern void srso_untrain_ret_alias(void); extern void entry_ibpb(void); #ifdef CONFIG_RETPOLINE diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 60514502ead6..6a9de5b1fe45 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -808,9 +808,11 @@ DECLARE_PER_CPU(u64, msr_misc_features_shadow); #ifdef CONFIG_CPU_SUP_AMD extern u16 amd_get_nb_id(int cpu); extern u32 amd_get_nodes_per_socket(void); +extern bool cpu_has_ibpb_brtype_microcode(void); #else static inline u16 amd_get_nb_id(int cpu) { return 0; } static inline u32 amd_get_nodes_per_socket(void) { return 0; } +static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } #endif static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index e6e63a9d27cb..50b4047991ae 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -678,7 +678,9 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_feature_enabled(X86_FEATURE_RETHUNK) || + cpu_feature_enabled(X86_FEATURE_SRSO) || + cpu_feature_enabled(X86_FEATURE_SRSO_ALIAS)) return -1; bytes[i++] = RET_INSN_OPCODE; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 3d99a823ffac..a5239ecbc2c6 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1282,6 +1282,20 @@ void set_dr_addr_mask(unsigned long mask, int dr) } } +bool cpu_has_ibpb_brtype_microcode(void) +{ + u8 fam = boot_cpu_data.x86; + + if (fam == 0x17) { + /* Zen1/2 IBPB flushes branch type predictions too. */ + return boot_cpu_has(X86_FEATURE_AMD_IBPB); + } else if (fam == 0x19) { + return false; + } + + return false; +} + static void zenbleed_check_cpu(void *unused) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 21f4bdbcfb4b..e41b271abbda 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -46,6 +46,7 @@ static void __init taa_select_mitigation(void); static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init gds_select_mitigation(void); +static void __init srso_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -152,6 +153,7 @@ void __init cpu_select_mitigations(void) md_clear_select_mitigation(); srbds_select_mitigation(); gds_select_mitigation(); + srso_select_mitigation(); } /* @@ -2233,6 +2235,95 @@ static int __init l1tf_cmdline(char *str) } early_param("l1tf", l1tf_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "Speculative Return Stack Overflow: " fmt + +enum srso_mitigation { + SRSO_MITIGATION_NONE, + SRSO_MITIGATION_MICROCODE, + SRSO_MITIGATION_SAFE_RET, +}; + +enum srso_mitigation_cmd { + SRSO_CMD_OFF, + SRSO_CMD_MICROCODE, + SRSO_CMD_SAFE_RET, +}; + +static const char * const srso_strings[] = { + [SRSO_MITIGATION_NONE] = "Vulnerable", + [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", + [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", +}; + +static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; +static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET; + +static int __init srso_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + srso_cmd = SRSO_CMD_OFF; + else if (!strcmp(str, "microcode")) + srso_cmd = SRSO_CMD_MICROCODE; + else if (!strcmp(str, "safe-ret")) + srso_cmd = SRSO_CMD_SAFE_RET; + else + pr_err("Ignoring unknown SRSO option (%s).", str); + + return 0; +} +early_param("spec_rstack_overflow", srso_parse_cmdline); + +#define SRSO_NOTICE "WARNING: See https://kernel.org/doc/html/latest/admin-guide/hw-vuln/srso.html for mitigation options." + +static void __init srso_select_mitigation(void) +{ + bool has_microcode; + + if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) + return; + + has_microcode = cpu_has_ibpb_brtype_microcode(); + if (!has_microcode) { + pr_warn("IBPB-extending microcode not applied!\n"); + pr_warn(SRSO_NOTICE); + } + + switch (srso_cmd) { + case SRSO_CMD_OFF: + return; + + case SRSO_CMD_MICROCODE: + if (has_microcode) { + srso_mitigation = SRSO_MITIGATION_MICROCODE; + pr_warn(SRSO_NOTICE); + } + break; + + case SRSO_CMD_SAFE_RET: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (boot_cpu_data.x86 == 0x19) + setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); + else + setup_force_cpu_cap(X86_FEATURE_SRSO); + srso_mitigation = SRSO_MITIGATION_SAFE_RET; + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + return; + } + break; + + default: + break; + + } + + pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); +} + #undef pr_fmt #define pr_fmt(fmt) fmt @@ -2436,6 +2527,13 @@ static ssize_t gds_show_state(char *buf) return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); } +static ssize_t srso_show_state(char *buf) +{ + return sysfs_emit(buf, "%s%s\n", + srso_strings[srso_mitigation], + (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -2488,6 +2586,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_GDS: return gds_show_state(buf); + case X86_BUG_SRSO: + return srso_show_state(buf); + default: break; } @@ -2557,4 +2658,9 @@ ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_GDS); } + +ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 7f92145913e5..a924608ccf04 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1135,6 +1135,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define RETBLEED BIT(3) /* CPU is affected by GDS */ #define GDS BIT(4) +/* CPU is affected by SRSO */ +#define SRSO BIT(5) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1168,8 +1170,9 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED), + VULNBL_AMD(0x17, RETBLEED | SRSO), VULNBL_HYGON(0x18, RETBLEED), + VULNBL_AMD(0x19, SRSO), {} }; @@ -1297,6 +1300,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); + if (cpu_matches(cpu_vuln_blacklist, SRSO)) + setup_force_cpu_bug(X86_BUG_SRSO); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a21cd2381fa8..4955cb5cc001 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -133,7 +133,20 @@ SECTIONS LOCK_TEXT KPROBES_TEXT ALIGN_ENTRY_TEXT_BEGIN +#ifdef CONFIG_CPU_SRSO + *(.text.__x86.rethunk_untrain) +#endif + ENTRY_TEXT + +#ifdef CONFIG_CPU_SRSO + /* + * See the comment above srso_untrain_ret_alias()'s + * definition. + */ + . = srso_untrain_ret_alias | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20); + *(.text.__x86.rethunk_safe) +#endif ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT STATIC_CALL_TEXT @@ -142,13 +155,15 @@ SECTIONS #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; - *(.text.__x86.*) + *(.text.__x86.indirect_thunk) + *(.text.__x86.return_thunk) __indirect_thunk_end = .; #endif } :text =0xcccc /* End of text section, which should occupy whole number of pages */ _etext = .; + . = ALIGN(PAGE_SIZE); X86_ALIGN_RODATA_BEGIN @@ -502,6 +517,21 @@ INIT_PER_CPU(irq_stack_backing_store); "fixed_percpu_data is not at start of per-cpu area"); #endif +#ifdef CONFIG_RETHUNK +. = ASSERT((__ret & 0x3f) == 0, "__ret not cacheline-aligned"); +. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); +#endif + +#ifdef CONFIG_CPU_SRSO +/* + * GNU ld cannot do XOR so do: (A | B) - (A & B) in order to compute the XOR + * of the two function addresses: + */ +. = ASSERT(((srso_untrain_ret_alias | srso_safe_ret_alias) - + (srso_untrain_ret_alias & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), + "SRSO function pair won't alias"); +#endif + #endif /* CONFIG_X86_32 */ #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 1221bb099afb..5f7eed97487e 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -9,6 +9,7 @@ #include #include #include +#include .section .text.__x86.indirect_thunk @@ -73,6 +74,45 @@ SYM_CODE_END(__x86_indirect_thunk_array) */ #ifdef CONFIG_RETHUNK +/* + * srso_untrain_ret_alias() and srso_safe_ret_alias() are placed at + * special addresses: + * + * - srso_untrain_ret_alias() is 2M aligned + * - srso_safe_ret_alias() is also in the same 2M page but bits 2, 8, 14 + * and 20 in its virtual address are set (while those bits in the + * srso_untrain_ret_alias() function are cleared). + * + * This guarantees that those two addresses will alias in the branch + * target buffer of Zen3/4 generations, leading to any potential + * poisoned entries at that BTB slot to get evicted. + * + * As a result, srso_safe_ret_alias() becomes a safe return. + */ +#ifdef CONFIG_CPU_SRSO + .section .text.__x86.rethunk_untrain + +SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) + ASM_NOP2 + lfence + jmp __x86_return_thunk +SYM_FUNC_END(srso_untrain_ret_alias) +__EXPORT_THUNK(srso_untrain_ret_alias) + + .section .text.__x86.rethunk_safe +#endif + +/* Needs a definition for the __x86_return_thunk alternative below. */ +SYM_START(srso_safe_ret_alias, SYM_L_GLOBAL, SYM_A_NONE) +#ifdef CONFIG_CPU_SRSO + add $8, %_ASM_SP + UNWIND_HINT_FUNC +#endif + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_FUNC_END(srso_safe_ret_alias) + .section .text.__x86.return_thunk /* @@ -85,7 +125,7 @@ SYM_CODE_END(__x86_indirect_thunk_array) * from re-poisioning the BTB prediction. */ .align 64 - .skip 63, 0xcc + .skip 64 - (__ret - zen_untrain_ret), 0xcc SYM_FUNC_START_NOALIGN(zen_untrain_ret); /* @@ -117,10 +157,10 @@ SYM_FUNC_START_NOALIGN(zen_untrain_ret); * evicted, __x86_return_thunk will suffer Straight Line Speculation * which will be contained safely by the INT3. */ -SYM_INNER_LABEL(__x86_return_thunk, SYM_L_GLOBAL) +SYM_INNER_LABEL(__ret, SYM_L_GLOBAL) ret int3 -SYM_CODE_END(__x86_return_thunk) +SYM_CODE_END(__ret) /* * Ensure the TEST decoding / BTB invalidation is complete. @@ -131,11 +171,44 @@ SYM_CODE_END(__x86_return_thunk) * Jump back and execute the RET in the middle of the TEST instruction. * INT3 is for SLS protection. */ - jmp __x86_return_thunk + jmp __ret int3 SYM_FUNC_END(zen_untrain_ret) __EXPORT_THUNK(zen_untrain_ret) +/* + * SRSO untraining sequence for Zen1/2, similar to zen_untrain_ret() + * above. On kernel entry, srso_untrain_ret() is executed which is a + * + * movabs $0xccccccc308c48348,%rax + * + * and when the return thunk executes the inner label srso_safe_ret() + * later, it is a stack manipulation and a RET which is mispredicted and + * thus a "safe" one to use. + */ + .align 64 + .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc +SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + .byte 0x48, 0xb8 + +SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) + add $8, %_ASM_SP + ret + int3 + int3 + int3 + lfence + call srso_safe_ret + int3 +SYM_CODE_END(srso_safe_ret) +SYM_FUNC_END(srso_untrain_ret) +__EXPORT_THUNK(srso_untrain_ret) + +SYM_FUNC_START(__x86_return_thunk) + ALTERNATIVE_2 "jmp __ret", "call srso_safe_ret", X86_FEATURE_SRSO, \ + "call srso_safe_ret_alias", X86_FEATURE_SRSO_ALIAS + int3 +SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) #endif /* CONFIG_RETHUNK */ diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 0cb8ec80ddfd..2db1e0e8c1a7 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -585,6 +585,12 @@ ssize_t __weak cpu_show_gds(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_spec_rstack_overflow(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -597,6 +603,7 @@ static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); +static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -611,6 +618,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_mmio_stale_data.attr, &dev_attr_retbleed.attr, &dev_attr_gather_data_sampling.attr, + &dev_attr_spec_rstack_overflow.attr, NULL }; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ef084a2fc6d5..358905a85993 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -70,6 +70,8 @@ extern ssize_t cpu_show_mmio_stale_data(struct device *dev, char *buf); extern ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index d8f47704fd85..5b915ebb6116 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -652,5 +652,8 @@ bool arch_is_retpoline(struct symbol *sym) bool arch_is_rethunk(struct symbol *sym) { - return !strcmp(sym->name, "__x86_return_thunk"); + return !strcmp(sym->name, "__x86_return_thunk") || + !strcmp(sym->name, "srso_untrain_ret") || + !strcmp(sym->name, "srso_safe_ret") || + !strcmp(sym->name, "__ret"); } From df76a59feba549825f426cb1586bfa86b49c08fa Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Tue, 18 Jul 2023 11:13:40 +0200 Subject: [PATCH 4282/4345] x86/srso: Add IBPB_BRTYPE support Upstream commit: 79113e4060aba744787a81edb9014f2865193854 Add support for the synthetic CPUID flag which "if this bit is 1, it indicates that MSR 49h (PRED_CMD) bit 0 (IBPB) flushes all branch type predictions from the CPU branch predictor." This flag is there so that this capability in guests can be detected easily (otherwise one would have to track microcode revisions which is impossible for guests). It is also needed only for Zen3 and -4. The other two (Zen1 and -2) always flush branch type predictions by default. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 2 ++ arch/x86/kernel/cpu/bugs.c | 12 +++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index f54207b90cad..2c43af9e836c 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -402,6 +402,8 @@ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ + /* * BUG word(s) */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index e41b271abbda..90a91ef0fc64 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2286,10 +2286,20 @@ static void __init srso_select_mitigation(void) if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) return; - has_microcode = cpu_has_ibpb_brtype_microcode(); + /* + * The first check is for the kernel running as a guest in order + * for guests to verify whether IBPB is a viable mitigation. + */ + has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode(); if (!has_microcode) { pr_warn("IBPB-extending microcode not applied!\n"); pr_warn(SRSO_NOTICE); + } else { + /* + * Enable the synthetic (even if in a real CPUID leaf) + * flag for guests. + */ + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); } switch (srso_cmd) { From e47af0c255aed7da91202f26250558a8e34e1c26 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Thu, 29 Jun 2023 17:43:40 +0200 Subject: [PATCH 4283/4345] x86/srso: Add SRSO_NO support Upstream commit: 1b5277c0ea0b247393a9c426769fde18cff5e2f6 Add support for the CPUID flag which denotes that the CPU is not affected by SRSO. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 2 ++ arch/x86/include/asm/msr-index.h | 1 + arch/x86/include/asm/nospec-branch.h | 6 +++--- arch/x86/kernel/cpu/amd.c | 12 ++++++------ arch/x86/kernel/cpu/bugs.c | 24 ++++++++++++++++++++---- arch/x86/kernel/cpu/common.c | 6 ++++-- arch/x86/kvm/cpuid.c | 3 +++ 7 files changed, 39 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 2c43af9e836c..b9f921a86db3 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -402,7 +402,9 @@ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ /* * BUG word(s) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 2bc4fa9ad3e5..202a52e42a36 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -60,6 +60,7 @@ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index e882fea99e13..84e944a23bab 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -307,11 +307,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) : "memory"); } +extern u64 x86_pred_cmd; + static inline void indirect_branch_prediction_barrier(void) { - u64 val = PRED_CMD_IBPB; - - alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); + alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB); } /* The Intel SPEC CTRL MSR base value cache */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index a5239ecbc2c6..8c257db23d90 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1286,14 +1286,14 @@ bool cpu_has_ibpb_brtype_microcode(void) { u8 fam = boot_cpu_data.x86; - if (fam == 0x17) { - /* Zen1/2 IBPB flushes branch type predictions too. */ + /* Zen1/2 IBPB flushes branch type predictions too. */ + if (fam == 0x17) return boot_cpu_has(X86_FEATURE_AMD_IBPB); - } else if (fam == 0x19) { + /* Poke the MSR bit on Zen3/4 to check its presence. */ + else if (fam == 0x19) + return !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB); + else return false; - } - - return false; } static void zenbleed_check_cpu(void *unused) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 90a91ef0fc64..7bb6750fbd75 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -56,6 +56,9 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); +u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; +EXPORT_SYMBOL_GPL(x86_pred_cmd); + static DEFINE_MUTEX(spec_ctrl_mutex); /* Update SPEC_CTRL MSR and its cached copy unconditionally */ @@ -2284,7 +2287,7 @@ static void __init srso_select_mitigation(void) bool has_microcode; if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) - return; + goto pred_cmd; /* * The first check is for the kernel running as a guest in order @@ -2297,9 +2300,18 @@ static void __init srso_select_mitigation(void) } else { /* * Enable the synthetic (even if in a real CPUID leaf) - * flag for guests. + * flags for guests. */ setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + setup_force_cpu_cap(X86_FEATURE_SBPB); + + /* + * Zen1/2 with SMT off aren't vulnerable after the right + * IBPB microcode has been applied. + */ + if ((boot_cpu_data.x86 < 0x19) && + (cpu_smt_control == CPU_SMT_DISABLED)) + setup_force_cpu_cap(X86_FEATURE_SRSO_NO); } switch (srso_cmd) { @@ -2322,16 +2334,20 @@ static void __init srso_select_mitigation(void) srso_mitigation = SRSO_MITIGATION_SAFE_RET; } else { pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); - return; + goto pred_cmd; } break; default: break; - } pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); + +pred_cmd: + if (boot_cpu_has(X86_FEATURE_SRSO_NO) || + srso_cmd == SRSO_CMD_OFF) + x86_pred_cmd = PRED_CMD_SBPB; } #undef pr_fmt diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a924608ccf04..f437efbb7e76 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1300,8 +1300,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); - if (cpu_matches(cpu_vuln_blacklist, SRSO)) - setup_force_cpu_bug(X86_BUG_SRSO); + if (!cpu_has(c, X86_FEATURE_SRSO_NO)) { + if (cpu_matches(cpu_vuln_blacklist, SRSO)) + setup_force_cpu_bug(X86_BUG_SRSO); + } if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index de4b171cb76b..8b07e48612d7 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -491,6 +491,9 @@ void kvm_set_cpu_caps(void) !boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); + if (cpu_feature_enabled(X86_FEATURE_SRSO_NO)) + kvm_cpu_cap_set(X86_FEATURE_SRSO_NO); + /* * Hide all SVM features by default, SVM will set the cap bits for * features it emulates and/or exposes for L1. From 4acaea47e3bcb7cd55cc56c7fd4e5fb60eebdada Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Thu, 6 Jul 2023 15:04:35 +0200 Subject: [PATCH 4284/4345] x86/srso: Add IBPB Upstream commit: 233d6f68b98d480a7c42ebe78c38f79d44741ca9 Add the option to mitigate using IBPB on a kernel entry. Pull in the Retbleed alternative so that the IBPB call from there can be used. Also, if Retbleed mitigation is done using IBPB, the same mitigation can and must be used here. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 3 ++- arch/x86/kernel/cpu/bugs.c | 23 +++++++++++++++++++++++ 2 files changed, 25 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 84e944a23bab..99fbce2c1c7c 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -173,7 +173,8 @@ * where we have a stack but before any RET instruction. */ .macro UNTRAIN_RET -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ + defined(CONFIG_CPU_SRSO) ANNOTATE_UNRET_END ALTERNATIVE_2 "", \ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 7bb6750fbd75..3a996197dc46 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2245,18 +2245,21 @@ enum srso_mitigation { SRSO_MITIGATION_NONE, SRSO_MITIGATION_MICROCODE, SRSO_MITIGATION_SAFE_RET, + SRSO_MITIGATION_IBPB, }; enum srso_mitigation_cmd { SRSO_CMD_OFF, SRSO_CMD_MICROCODE, SRSO_CMD_SAFE_RET, + SRSO_CMD_IBPB, }; static const char * const srso_strings[] = { [SRSO_MITIGATION_NONE] = "Vulnerable", [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", + [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", }; static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; @@ -2273,6 +2276,8 @@ static int __init srso_parse_cmdline(char *str) srso_cmd = SRSO_CMD_MICROCODE; else if (!strcmp(str, "safe-ret")) srso_cmd = SRSO_CMD_SAFE_RET; + else if (!strcmp(str, "ibpb")) + srso_cmd = SRSO_CMD_IBPB; else pr_err("Ignoring unknown SRSO option (%s).", str); @@ -2314,6 +2319,14 @@ static void __init srso_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_SRSO_NO); } + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { + if (has_microcode) { + pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n"); + srso_mitigation = SRSO_MITIGATION_IBPB; + goto pred_cmd; + } + } + switch (srso_cmd) { case SRSO_CMD_OFF: return; @@ -2338,6 +2351,16 @@ static void __init srso_select_mitigation(void) } break; + case SRSO_CMD_IBPB: + if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + if (has_microcode) { + setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + srso_mitigation = SRSO_MITIGATION_IBPB; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + goto pred_cmd; + } default: break; } From 384d41bea948a18288aff668b7bdf3b522b7bf73 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Fri, 7 Jul 2023 13:53:41 +0200 Subject: [PATCH 4285/4345] x86/srso: Add IBPB on VMEXIT Upstream commit: d893832d0e1ef41c72cdae444268c1d64a2be8ad Add the option to flush IBPB only on VMEXIT in order to protect from malicious guests but one otherwise trusts the software that runs on the hypervisor. Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/bugs.c | 19 +++++++++++++++++++ arch/x86/kvm/svm/svm.c | 4 +++- arch/x86/kvm/svm/vmenter.S | 3 +++ 4 files changed, 26 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b9f921a86db3..2c0c495b9cb6 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -303,6 +303,7 @@ #define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ #define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 3a996197dc46..fea905305394 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2246,6 +2246,7 @@ enum srso_mitigation { SRSO_MITIGATION_MICROCODE, SRSO_MITIGATION_SAFE_RET, SRSO_MITIGATION_IBPB, + SRSO_MITIGATION_IBPB_ON_VMEXIT, }; enum srso_mitigation_cmd { @@ -2253,6 +2254,7 @@ enum srso_mitigation_cmd { SRSO_CMD_MICROCODE, SRSO_CMD_SAFE_RET, SRSO_CMD_IBPB, + SRSO_CMD_IBPB_ON_VMEXIT, }; static const char * const srso_strings[] = { @@ -2260,6 +2262,7 @@ static const char * const srso_strings[] = { [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", + [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" }; static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; @@ -2278,6 +2281,8 @@ static int __init srso_parse_cmdline(char *str) srso_cmd = SRSO_CMD_SAFE_RET; else if (!strcmp(str, "ibpb")) srso_cmd = SRSO_CMD_IBPB; + else if (!strcmp(str, "ibpb-vmexit")) + srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT; else pr_err("Ignoring unknown SRSO option (%s).", str); @@ -2361,6 +2366,20 @@ static void __init srso_select_mitigation(void) pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); goto pred_cmd; } + break; + + case SRSO_CMD_IBPB_ON_VMEXIT: + if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); + srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + } + } else { + pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + goto pred_cmd; + } + break; + default: break; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7b2b61309d8a..8544bca6b335 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1392,7 +1392,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (sd->current_vmcb != svm->vmcb) { sd->current_vmcb = svm->vmcb; - indirect_branch_prediction_barrier(); + + if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT)) + indirect_branch_prediction_barrier(); } avic_vcpu_load(vcpu, cpu); } diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index c18d812d00cd..a8859c173258 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -137,6 +137,9 @@ SYM_FUNC_START(__svm_vcpu_run) */ UNTRAIN_RET + /* SRSO */ + ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT + /* * Clear all general purpose registers except RSP and RAX to prevent * speculative use of the guest's values, even those that are reloaded From 4873939c0e1cec2fd04a38ddf2c03a05e4eeb7ef Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 28 Jul 2023 17:28:43 -0500 Subject: [PATCH 4286/4345] x86/srso: Fix return thunks in generated code Upstream commit: 238ec850b95a02dcdff3edc86781aa913549282f Set X86_FEATURE_RETHUNK when enabling the SRSO mitigation so that generated code (e.g., ftrace, static call, eBPF) generates "jmp __x86_return_thunk" instead of RET. [ bp: Add a comment. ] Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Signed-off-by: Josh Poimboeuf Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/alternative.c | 4 +--- arch/x86/kernel/cpu/bugs.c | 6 ++++++ 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 50b4047991ae..e6e63a9d27cb 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -678,9 +678,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK) || - cpu_feature_enabled(X86_FEATURE_SRSO) || - cpu_feature_enabled(X86_FEATURE_SRSO_ALIAS)) + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) return -1; bytes[i++] = RET_INSN_OPCODE; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index fea905305394..99bca21a3e62 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2345,6 +2345,12 @@ static void __init srso_select_mitigation(void) case SRSO_CMD_SAFE_RET: if (IS_ENABLED(CONFIG_CPU_SRSO)) { + /* + * Enable the return thunk for generated code + * like ftrace, static_call, etc. + */ + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + if (boot_cpu_data.x86 == 0x19) setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); else From 8457fb5740b14311a8941044ff4eb5a3945de9b2 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Mon, 7 Aug 2023 10:46:04 +0200 Subject: [PATCH 4287/4345] x86/srso: Tie SBPB bit setting to microcode patch detection commit 5a15d8348881e9371afdf9f5357a135489496955 upstream. The SBPB bit in MSR_IA32_PRED_CMD is supported only after a microcode patch has been applied so set X86_FEATURE_SBPB only then. Otherwise, guests would attempt to set that bit and #GP on the MSR write. While at it, make SMT detection more robust as some guests - depending on how and what CPUID leafs their report - lead to cpu_smt_control getting set to CPU_SMT_NOT_SUPPORTED but SRSO_NO should be set for any guest incarnation where one simply cannot do SMT, for whatever reason. Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") Reported-by: Konrad Rzeszutek Wilk Reported-by: Salvatore Bonaccorso Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/amd.c | 19 ++++++++++++------- arch/x86/kernel/cpu/bugs.c | 7 +++---- 2 files changed, 15 insertions(+), 11 deletions(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 8c257db23d90..ffecf4e9444e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1284,16 +1284,21 @@ void set_dr_addr_mask(unsigned long mask, int dr) bool cpu_has_ibpb_brtype_microcode(void) { - u8 fam = boot_cpu_data.x86; - + switch (boot_cpu_data.x86) { /* Zen1/2 IBPB flushes branch type predictions too. */ - if (fam == 0x17) + case 0x17: return boot_cpu_has(X86_FEATURE_AMD_IBPB); - /* Poke the MSR bit on Zen3/4 to check its presence. */ - else if (fam == 0x19) - return !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB); - else + case 0x19: + /* Poke the MSR bit on Zen3/4 to check its presence. */ + if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { + setup_force_cpu_cap(X86_FEATURE_SBPB); + return true; + } else { + return false; + } + default: return false; + } } static void zenbleed_check_cpu(void *unused) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 99bca21a3e62..d31639e3ce28 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2313,14 +2313,13 @@ static void __init srso_select_mitigation(void) * flags for guests. */ setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); - setup_force_cpu_cap(X86_FEATURE_SBPB); /* * Zen1/2 with SMT off aren't vulnerable after the right * IBPB microcode has been applied. */ if ((boot_cpu_data.x86 < 0x19) && - (cpu_smt_control == CPU_SMT_DISABLED)) + (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED))) setup_force_cpu_cap(X86_FEATURE_SRSO_NO); } @@ -2393,8 +2392,8 @@ static void __init srso_select_mitigation(void) pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); pred_cmd: - if (boot_cpu_has(X86_FEATURE_SRSO_NO) || - srso_cmd == SRSO_CMD_OFF) + if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) && + boot_cpu_has(X86_FEATURE_SBPB)) x86_pred_cmd = PRED_CMD_SBPB; } From f9167a2d6b943f30743de6ff8163d1981c34f9a9 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Thu, 3 Aug 2023 08:41:22 +0200 Subject: [PATCH 4288/4345] xen/netback: Fix buffer overrun triggered by unusual packet commit 534fc31d09b706a16d83533e16b5dc855caf7576 upstream. It is possible that a guest can send a packet that contains a head + 18 slots and yet has a len <= XEN_NETBACK_TX_COPY_LEN. This causes nr_slots to underflow in xenvif_get_requests() which then causes the subsequent loop's termination condition to be wrong, causing a buffer overrun of queue->tx_map_ops. Rework the code to account for the extra frag_overflow slots. This is CVE-2023-34319 / XSA-432. Fixes: ad7f402ae4f4 ("xen/netback: Ensure protocol headers don't fall in the non-linear area") Signed-off-by: Ross Lagerwall Reviewed-by: Paul Durrant Reviewed-by: Wei Liu Signed-off-by: Juergen Gross Signed-off-by: Greg Kroah-Hartman --- drivers/net/xen-netback/netback.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 379ac9ca60b7..1c366ddf62bc 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -396,7 +396,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue, struct gnttab_map_grant_ref *gop = queue->tx_map_ops + *map_ops; struct xen_netif_tx_request *txp = first; - nr_slots = shinfo->nr_frags + 1; + nr_slots = shinfo->nr_frags + frag_overflow + 1; copy_count(skb) = 0; XENVIF_TX_CB(skb)->split_mask = 0; @@ -462,8 +462,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } } - for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, gop++) { + for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; + shinfo->nr_frags++, gop++, nr_slots--) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; xenvif_tx_create_map_op(queue, pending_idx, txp, @@ -476,12 +476,12 @@ static void xenvif_get_requests(struct xenvif_queue *queue, txp++; } - if (frag_overflow) { + if (nr_slots > 0) { shinfo = skb_shinfo(nskb); frags = shinfo->frags; - for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; shinfo->nr_frags++, txp++, gop++) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; @@ -492,6 +492,11 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } skb_shinfo(skb)->frag_list = nskb; + } else if (nskb) { + /* A frag_list skb was allocated but it is no longer needed + * because enough slots were converted to copy ops above. + */ + kfree_skb(nskb); } (*copy_ops) = cop - queue->tx_copy_ops; From 2ae9a73819a79c68cf9d411d164d3e417a118e44 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 8 Aug 2023 19:20:48 +0200 Subject: [PATCH 4289/4345] x86: fix backwards merge of GDS/SRSO bit Stable-tree-only change. Due to the way the GDS and SRSO patches flowed into the stable tree, it was a 50% chance that the merge of the which value GDS and SRSO should be. Of course, I lost that bet, and chose the opposite of what Linus chose in commit 64094e7e3118 ("Merge tag 'gds-for-linus-2023-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip") Fix this up by switching the values to match what is now in Linus's tree as that is the correct value to mirror. Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/common.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f437efbb7e76..c1f236030912 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1133,10 +1133,12 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define MMIO_SBDS BIT(2) /* CPU is affected by RETbleed, speculating where you would not expect it */ #define RETBLEED BIT(3) -/* CPU is affected by GDS */ -#define GDS BIT(4) +/* CPU is affected by SMT (cross-thread) return predictions */ +#define SMT_RSB BIT(4) /* CPU is affected by SRSO */ #define SRSO BIT(5) +/* CPU is affected by GDS */ +#define GDS BIT(6) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), From de5f63612d1631c89e72ecffc089f948392cf24a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 8 Aug 2023 19:57:41 +0200 Subject: [PATCH 4290/4345] Linux 5.10.189 Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 7f9e1667d87d..36047436fae3 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 188 +SUBLEVEL = 189 EXTRAVERSION = NAME = Dare mighty things From 67f65c7764d6a9800f8104d0193448ad8c2b77be Mon Sep 17 00:00:00 2001 From: Author Name Date: Wed, 9 Aug 2023 16:49:22 +0530 Subject: [PATCH 4291/4345] ANDROID: GKI: Update symbols to symbol list Leaf changes summary: 1 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 1 Added function 1 Added function: [A] 'function int tty_termios_hw_change(const struct*, const struct*)' Bug: 295132162 Change-Id: I2e9b0d77260e20e9e2d6f907d96eedc76663fba0 Signed-off-by: Aravindh Senthilkumar --- android/abi_gki_aarch64.xml | 8 ++++++++ android/abi_gki_aarch64_zebra | 1 + 2 files changed, 9 insertions(+) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 431d1d2eb876..dfb8ddeb4435 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -5642,6 +5642,7 @@ + @@ -28225,6 +28226,7 @@ + @@ -97901,6 +97903,7 @@ + @@ -147065,6 +147068,11 @@ + + + + + diff --git a/android/abi_gki_aarch64_zebra b/android/abi_gki_aarch64_zebra index 2ca38a60d508..59367a252ab5 100644 --- a/android/abi_gki_aarch64_zebra +++ b/android/abi_gki_aarch64_zebra @@ -1,3 +1,4 @@ [abi_symbol_list] __traceiter_android_vh_wakeup_bypass __tracepoint_android_vh_wakeup_bypass + tty_termios_hw_change From 028e0fb3a4f065cb7a2144817bb0a14f60e64f57 Mon Sep 17 00:00:00 2001 From: Andrew Yang Date: Fri, 30 Jun 2023 17:22:02 +0800 Subject: [PATCH 4292/4345] FROMGIT: fs: drop_caches: draining pages before dropping caches We expect a file page access after dropping caches should be a major fault, but sometimes it's still a minor fault. That's because a file page can't be dropped if it's in a per-cpu pagevec. Draining all pages from per-cpu pagevec to lru list before trying to drop caches. Link: https://lkml.kernel.org/r/20230630092203.16080-1-andrew.yang@mediatek.com Change-Id: I9b03c53e39b87134d5ddd0c40ac9b36cf4d190cd Signed-off-by: Andrew Yang Cc: Al Viro Cc: AngeloGioacchino Del Regno Cc: Christian Brauner Cc: Matthias Brugger Signed-off-by: Andrew Morton Bug: 285794522 (cherry picked from commit a481c6fdf3e4fdf31bda91098dfbf46098037e76 https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-unstable) --- fs/drop_caches.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index f00fcc4a4f72..345f8644dc57 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "internal.h" /* A global variable is a bit ugly, but it keeps the code simple */ @@ -58,6 +59,7 @@ int drop_caches_sysctl_handler(struct ctl_table *table, int write, static int stfu; if (sysctl_drop_caches & 1) { + lru_add_drain_all(); iterate_supers(drop_pagecache_sb, NULL); count_vm_event(DROP_PAGECACHE); } From ec3f57af0ad99e19bbbfb9c6c94e1f3044c37fc9 Mon Sep 17 00:00:00 2001 From: xieliujie Date: Fri, 4 Aug 2023 14:12:55 +0800 Subject: [PATCH 4293/4345] ANDROID: vendor_hook: fix the error record position of mutex Make sure vendorhook trace_android_vh_record_mutex_lock_starttime woking both in fastpath unlock and slowpath unlock. Fixes: 57750518de5b ("ANDROID: vendor_hook: Avoid clearing protect-flag before waking waiters") Bug: 286024926 Change-Id: Ib91c1b88d27aaa4ef872d44102969ffc3c9adb58 Signed-off-by: xieliujie --- kernel/locking/mutex.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index be121ed70d7c..943f6c3a7c67 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -761,8 +761,10 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne void __sched mutex_unlock(struct mutex *lock) { #ifndef CONFIG_DEBUG_LOCK_ALLOC - if (__mutex_unlock_fast(lock)) + if (__mutex_unlock_fast(lock)) { + trace_android_vh_record_mutex_lock_starttime(current, 0); return; + } #endif __mutex_unlock_slowpath(lock, _RET_IP_); trace_android_vh_record_mutex_lock_starttime(current, 0); From 6efa28db9a5fbd0cf2f10d2f5740fd5b3e430e66 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 4 Jul 2023 17:50:34 +0200 Subject: [PATCH 4294/4345] BACKPORT: FROMGIT: irqchip/gic-v3: Workaround for GIC-700 erratum 2941627 GIC700 erratum 2941627 may cause GIC-700 missing SPIs wake requests when SPIs are deactivated while targeting a sleeping CPU - ie a CPU for which the redistributor: GICR_WAKER.ProcessorSleep == 1 This runtime situation can happen if an SPI that has been activated on a core is retargeted to a different core, it becomes pending and the target core subsequently enters a power state quiescing the respective redistributor. When this situation is hit, the de-activation carried out on the core that activated the SPI (through either ICC_EOIR1_EL1 or ICC_DIR_EL1 register writes) does not trigger a wake requests for the sleeping GIC redistributor even if the SPI is pending. Work around the erratum by de-activating the SPI using the redistributor GICD_ICACTIVER register if the runtime conditions require it (ie the IRQ was retargeted between activation and de-activation). Bug: 292459437 Change-Id: Ide915b8c925a631a7fc9ccebca19d9175def162e Signed-off-by: Lorenzo Pieralisi Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230704155034.148262-1-lpieralisi@kernel.org (cherry picked from commit 6fe5c68ee6a1aae0ef291a56001e7888de547fa2 https://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms.git irq/irqchip-fixes) [Defined CPUIF_MAP for ICC_EOIR1_EL1 register] Signed-off-by: Carlos Galo --- Documentation/arm64/silicon-errata.rst | 3 ++ arch/arm/include/asm/arch_gicv3.h | 1 + drivers/irqchip/irq-gic-v3.c | 65 +++++++++++++++++++++++++- 3 files changed, 67 insertions(+), 2 deletions(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 3ec065727d9b..be29300f3cca 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -113,6 +113,9 @@ stable kernels. | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ +| ARM | GIC-700 | #2941627 | ARM64_ERRATUM_2941627 | ++----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ | Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_845719 | +----------------+-----------------+-----------------+-----------------------------+ | Broadcom | Brahma-B53 | N/A | ARM64_ERRATUM_843419 | diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 413abfb42989..59ec3a6845f7 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -48,6 +48,7 @@ static inline u32 read_ ## a64(void) \ return read_sysreg(a32); \ } \ +CPUIF_MAP(ICC_EOIR1, ICC_EOIR1_EL1) CPUIF_MAP(ICC_PMR, ICC_PMR_EL1) CPUIF_MAP(ICC_AP0R0, ICC_AP0R0_EL1) CPUIF_MAP(ICC_AP0R1, ICC_AP0R1_EL1) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index e14a57e5e4a8..192a9b1be185 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -51,6 +51,8 @@ struct redist_region { bool single_redist; }; +static DEFINE_STATIC_KEY_FALSE(gic_arm64_2941627_erratum); + static struct gic_chip_data gic_data __read_mostly; static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); @@ -542,9 +544,39 @@ static void gic_irq_nmi_teardown(struct irq_data *d) gic_irq_set_prio(d, GICD_INT_DEF_PRI); } +static bool gic_arm64_erratum_2941627_needed(struct irq_data *d) +{ + enum gic_intid_range range; + + if (!static_branch_unlikely(&gic_arm64_2941627_erratum)) + return false; + + range = get_intid_range(d); + + /* + * The workaround is needed if the IRQ is an SPI and + * the target cpu is different from the one we are + * executing on. + */ + return (range == SPI_RANGE || range == ESPI_RANGE) && + !cpumask_test_cpu(raw_smp_processor_id(), + irq_data_get_effective_affinity_mask(d)); +} + static void gic_eoi_irq(struct irq_data *d) { - gic_write_eoir(gic_irq(d)); + write_gicreg(gic_irq(d), ICC_EOIR1_EL1); + isb(); + + if (gic_arm64_erratum_2941627_needed(d)) { + /* + * Make sure the GIC stream deactivate packet + * issued by ICC_EOIR1_EL1 has completed before + * deactivating through GICD_IACTIVER. + */ + dsb(sy); + gic_poke_irq(d, GICD_ICACTIVER); + } } static void gic_eoimode1_eoi_irq(struct irq_data *d) @@ -555,7 +587,11 @@ static void gic_eoimode1_eoi_irq(struct irq_data *d) */ if (gic_irq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d)) return; - gic_write_dir(gic_irq(d)); + + if (!gic_arm64_erratum_2941627_needed(d)) + gic_write_dir(gic_irq(d)); + else + gic_poke_irq(d, GICD_ICACTIVER); } static int gic_set_type(struct irq_data *d, unsigned int type) @@ -1642,6 +1678,12 @@ static bool gic_enable_quirk_hip06_07(void *data) return false; } +static bool gic_enable_quirk_arm64_2941627(void *data) +{ + static_branch_enable(&gic_arm64_2941627_erratum); + return true; +} + static const struct gic_quirk gic_quirks[] = { { .desc = "GICv3: Qualcomm MSM8996 broken firmware", @@ -1678,6 +1720,25 @@ static const struct gic_quirk gic_quirks[] = { .mask = 0xe8f00fff, .init = gic_enable_quirk_cavium_38539, }, + { + /* + * GIC-700: 2941627 workaround - IP variant [0,1] + * + */ + .desc = "GICv3: ARM64 erratum 2941627", + .iidr = 0x0400043b, + .mask = 0xff0e0fff, + .init = gic_enable_quirk_arm64_2941627, + }, + { + /* + * GIC-700: 2941627 workaround - IP variant [2] + */ + .desc = "GICv3: ARM64 erratum 2941627", + .iidr = 0x0402043b, + .mask = 0xff0f0fff, + .init = gic_enable_quirk_arm64_2941627, + }, { } }; From 0fa8d8cd99fcb06c4ac4b2d30a033fcfb7d91e9c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 19 Jul 2023 21:08:21 +0200 Subject: [PATCH 4295/4345] UPSTREAM: netfilter: nft_set_pipapo: fix improper element removal [ Upstream commit 87b5a5c209405cb6b57424cdfa226a6dbd349232 ] end key should be equal to start unless NFT_SET_EXT_KEY_END is present. Its possible to add elements that only have a start key ("{ 1.0.0.0 . 2.0.0.0 }") without an internval end. Insertion treats this via: if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) end = (const u8 *)nft_set_ext_key_end(ext)->data; else end = start; but removal side always uses nft_set_ext_key_end(). This is wrong and leads to garbage remaining in the set after removal next lookup/insert attempt will give: BUG: KASAN: slab-use-after-free in pipapo_get+0x8eb/0xb90 Read of size 1 at addr ffff888100d50586 by task nft-pipapo_uaf_/1399 Call Trace: kasan_report+0x105/0x140 pipapo_get+0x8eb/0xb90 nft_pipapo_insert+0x1dc/0x1710 nf_tables_newsetelem+0x31f5/0x4e00 .. Bug: 293587745 Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Reported-by: lonial con Reviewed-by: Stefano Brivio Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin (cherry picked from commit 90c3955beb858bb52a9e5c4380ed0e520e3730d1) Signed-off-by: Lee Jones Change-Id: I51a423aaa2c31c4df89776505b602aa2c1523b82 --- net/netfilter/nft_set_pipapo.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 30cf0673d6c1..4781cdb63431 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1904,7 +1904,11 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, int i, start, rules_fx; match_start = data; - match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + + if (nft_set_ext_exists(&e->ext, NFT_SET_EXT_KEY_END)) + match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + else + match_end = data; start = first_rule; rules_fx = rules_f0; From 84f8556570eefa5f50caaa140aad87cae3bb143d Mon Sep 17 00:00:00 2001 From: Chaoyuan Peng Date: Tue, 18 Jul 2023 04:39:43 +0000 Subject: [PATCH 4296/4345] UPSTREAM: tty: n_gsm: fix UAF in gsm_cleanup_mux commit 9b9c8195f3f0d74a826077fc1c01b9ee74907239 upstream. In gsm_cleanup_mux() the 'gsm->dlci' pointer was not cleaned properly, leaving it a dangling pointer after gsm_dlci_release. This leads to use-after-free where 'gsm->dlci[0]' are freed and accessed by the subsequent gsm_cleanup_mux(). Such is the case in the following call trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e3/0x2cb lib/dump_stack.c:106 print_address_description+0x63/0x3b0 mm/kasan/report.c:248 __kasan_report mm/kasan/report.c:434 [inline] kasan_report+0x16b/0x1c0 mm/kasan/report.c:451 gsm_cleanup_mux+0x76a/0x850 drivers/tty/n_gsm.c:2397 gsm_config drivers/tty/n_gsm.c:2653 [inline] gsmld_ioctl+0xaae/0x15b0 drivers/tty/n_gsm.c:2986 tty_ioctl+0x8ff/0xc50 drivers/tty/tty_io.c:2816 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl+0xf1/0x160 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x61/0xcb Allocated by task 3501: kasan_save_stack mm/kasan/common.c:38 [inline] kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] ____kasan_kmalloc+0xba/0xf0 mm/kasan/common.c:513 kasan_kmalloc include/linux/kasan.h:264 [inline] kmem_cache_alloc_trace+0x143/0x290 mm/slub.c:3247 kmalloc include/linux/slab.h:591 [inline] kzalloc include/linux/slab.h:721 [inline] gsm_dlci_alloc+0x53/0x3a0 drivers/tty/n_gsm.c:1932 gsm_activate_mux+0x1c/0x330 drivers/tty/n_gsm.c:2438 gsm_config drivers/tty/n_gsm.c:2677 [inline] gsmld_ioctl+0xd46/0x15b0 drivers/tty/n_gsm.c:2986 tty_ioctl+0x8ff/0xc50 drivers/tty/tty_io.c:2816 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl+0xf1/0x160 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x61/0xcb Freed by task 3501: kasan_save_stack mm/kasan/common.c:38 [inline] kasan_set_track+0x4b/0x80 mm/kasan/common.c:46 kasan_set_free_info+0x1f/0x40 mm/kasan/generic.c:360 ____kasan_slab_free+0xd8/0x120 mm/kasan/common.c:366 kasan_slab_free include/linux/kasan.h:230 [inline] slab_free_hook mm/slub.c:1705 [inline] slab_free_freelist_hook+0xdd/0x160 mm/slub.c:1731 slab_free mm/slub.c:3499 [inline] kfree+0xf1/0x270 mm/slub.c:4559 dlci_put drivers/tty/n_gsm.c:1988 [inline] gsm_dlci_release drivers/tty/n_gsm.c:2021 [inline] gsm_cleanup_mux+0x574/0x850 drivers/tty/n_gsm.c:2415 gsm_config drivers/tty/n_gsm.c:2653 [inline] gsmld_ioctl+0xaae/0x15b0 drivers/tty/n_gsm.c:2986 tty_ioctl+0x8ff/0xc50 drivers/tty/tty_io.c:2816 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl+0xf1/0x160 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x61/0xcb Bug: 291178675 Fixes: aa371e96f05d ("tty: n_gsm: fix restart handling via CLD command") Signed-off-by: Chaoyuan Peng Cc: stable Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 9615ca54bc138e35353a001e8b5d4824dce72188) Signed-off-by: Lee Jones Change-Id: I947cad0e8080378b40d4098add48992ade5fe638 --- drivers/tty/n_gsm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 23b014b8c919..d439afef9212 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2178,8 +2178,10 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) /* Free up any link layer users and finally the control channel */ for (i = NUM_DLCI - 1; i >= 0; i--) - if (gsm->dlci[i]) + if (gsm->dlci[i]) { gsm_dlci_release(gsm->dlci[i]); + gsm->dlci[i] = NULL; + } mutex_unlock(&gsm->mutex); /* Now wipe the queues */ tty_ldisc_flush(gsm->tty); From bad8adda4142ff5ba522511c03756324b83fb124 Mon Sep 17 00:00:00 2001 From: M A Ramdhan Date: Wed, 5 Jul 2023 12:15:30 -0400 Subject: [PATCH 4297/4345] UPSTREAM: net/sched: cls_fw: Fix improper refcount update leads to use-after-free [ Upstream commit 0323bce598eea038714f941ce2b22541c46d488f ] In the event of a failure in tcf_change_indev(), fw_set_parms() will immediately return an error after incrementing or decrementing reference counter in tcf_bind_filter(). If attacker can control reference counter to zero and make reference freed, leading to use after free. In order to prevent this, move the point of possible failure above the point where the TC_FW_CLASSID is handled. Bug: 292252062 Bug: 290783303 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: M A Ramdhan Signed-off-by: M A Ramdhan Acked-by: Jamal Hadi Salim Reviewed-by: Pedro Tammela Message-ID: <20230705161530.52003-1-ramdhan@starlabs.sg> Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin (cherry picked from commit c91fb29bb07ee4dd40aabd1e41f19c0f92ac3199) Signed-off-by: Lee Jones Change-Id: I9bf6f540b4eb23ea5641fb3efe6f3e621d7b6151 --- net/sched/cls_fw.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index ec945294626a..41f0898a5a56 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -210,11 +210,6 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, if (err < 0) return err; - if (tb[TCA_FW_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); - tcf_bind_filter(tp, &f->res, base); - } - if (tb[TCA_FW_INDEV]) { int ret; ret = tcf_change_indev(net, tb[TCA_FW_INDEV], extack); @@ -231,6 +226,11 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, } else if (head->mask != 0xFFFFFFFF) return err; + if (tb[TCA_FW_CLASSID]) { + f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); + tcf_bind_filter(tp, &f->res, base); + } + return 0; } From 28b82089b299db6fa9efaeac2cee2c5b4fa7d5f0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 20 Jul 2023 09:17:21 +0200 Subject: [PATCH 4298/4345] UPSTREAM: netfilter: nf_tables: skip bound chain on rule flush [ Upstream commit 6eaf41e87a223ae6f8e7a28d6e78384ad7e407f8 ] Skip bound chain when flushing table rules, the rule that owns this chain releases these objects. Otherwise, the following warning is triggered: WARNING: CPU: 2 PID: 1217 at net/netfilter/nf_tables_api.c:2013 nf_tables_chain_destroy+0x1f7/0x210 [nf_tables] CPU: 2 PID: 1217 Comm: chain-flush Not tainted 6.1.39 #1 RIP: 0010:nf_tables_chain_destroy+0x1f7/0x210 [nf_tables] Bug: 294357305 Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: Kevin Rich Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin (cherry picked from commit e18922ce3e3169eb97838d1dcba2d679bcca446c) Signed-off-by: Lee Jones Change-Id: I48f43d0ce3410efec2513479a1f4c7708a097b01 --- net/netfilter/nf_tables_api.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fe51cedd9cc3..9d6902e6a8c7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3451,6 +3451,8 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; + if (nft_chain_is_bound(chain)) + continue; ctx.chain = chain; err = nft_delrule_by_chain(&ctx); From e172f5cfc0c19f514fe1fb37c83217b3ab0a47f6 Mon Sep 17 00:00:00 2001 From: wangshuai12 Date: Tue, 15 Aug 2023 22:08:10 +0800 Subject: [PATCH 4299/4345] ANDROID: GKI: update xiaomi symbol list Add symbols required by mq-deadline module: blk_mq_debugfs_rq_show seq_list_start seq_list_next __blk_mq_debugfs_rq_show Bug: 295968464 Change-Id: I14bad6ff43c9a43a9bd1f854302d833d828996e5 Signed-off-by: wangshuai12 Signed-off-by: Aleksei Vetrov --- android/abi_gki_aarch64_xiaomi | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/android/abi_gki_aarch64_xiaomi b/android/abi_gki_aarch64_xiaomi index 67c83533d643..71ffa17ffb77 100644 --- a/android/abi_gki_aarch64_xiaomi +++ b/android/abi_gki_aarch64_xiaomi @@ -63,6 +63,12 @@ utf16s_to_utf8s wait_for_completion_io_timeout +#required by mq-deadline module + blk_mq_debugfs_rq_show + seq_list_start + seq_list_next + __blk_mq_debugfs_rq_show + #required by cs35l41 module regcache_drop_region regmap_async_complete From 45edbf4058171657ed6715f8d122d7fbe8a6fb74 Mon Sep 17 00:00:00 2001 From: valis Date: Sat, 29 Jul 2023 08:32:00 -0400 Subject: [PATCH 4300/4345] UPSTREAM: net/sched: cls_u32: No longer copy tcf_result on update to avoid use-after-free [ Upstream commit 3044b16e7c6fe5d24b1cdbcf1bd0a9d92d1ebd81 ] When u32_change() is called on an existing filter, the whole tcf_result struct is always copied into the new instance of the filter. This causes a problem when updating a filter bound to a class, as tcf_unbind_filter() is always called on the old instance in the success path, decreasing filter_cnt of the still referenced class and allowing it to be deleted, leading to a use-after-free. Fix this by no longer copying the tcf_result struct from the old filter. Bug: 296347075 Fixes: de5df63228fc ("net: sched: cls_u32 changes to knode must appear atomic to readers") Reported-by: valis Reported-by: M A Ramdhan Signed-off-by: valis Signed-off-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Reviewed-by: M A Ramdhan Link: https://lore.kernel.org/r/20230729123202.72406-2-jhs@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin (cherry picked from commit aab2d095ce4dd8d01ca484c0cc641fb497bf74db) Signed-off-by: Lee Jones Change-Id: I1a8381c308cc97cf61d6f95a02992d2c553455c5 --- net/sched/cls_u32.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 1ac8ff445a6d..b8c44ead0c16 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -812,7 +812,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->ifindex = n->ifindex; new->fshift = n->fshift; - new->res = n->res; new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); From 0ebe76176b67f66f865497d2d5a9234949a71125 Mon Sep 17 00:00:00 2001 From: valis Date: Sat, 29 Jul 2023 08:32:01 -0400 Subject: [PATCH 4301/4345] UPSTREAM: net/sched: cls_fw: No longer copy tcf_result on update to avoid use-after-free [ Upstream commit 76e42ae831991c828cffa8c37736ebfb831ad5ec ] When fw_change() is called on an existing filter, the whole tcf_result struct is always copied into the new instance of the filter. This causes a problem when updating a filter bound to a class, as tcf_unbind_filter() is always called on the old instance in the success path, decreasing filter_cnt of the still referenced class and allowing it to be deleted, leading to a use-after-free. Fix this by no longer copying the tcf_result struct from the old filter. Bug: 296347075 Fixes: e35a8ee5993b ("net: sched: fw use RCU") Reported-by: valis Reported-by: Bing-Jhong Billy Jheng Signed-off-by: valis Signed-off-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Reviewed-by: M A Ramdhan Link: https://lore.kernel.org/r/20230729123202.72406-3-jhs@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin (cherry picked from commit 7f691439b29be0aae68f83ad5eecfddc11007724) Signed-off-by: Lee Jones Change-Id: I33c91c83d1cd8e889a7261adfa3779ca6c141088 --- net/sched/cls_fw.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 41f0898a5a56..08c41f1976c4 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -266,7 +266,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; fnew->id = f->id; - fnew->res = f->res; fnew->ifindex = f->ifindex; fnew->tp = f->tp; From 6f01e099d8da4ca8ba559d3797de96d2cf50aed9 Mon Sep 17 00:00:00 2001 From: valis Date: Sat, 29 Jul 2023 08:32:02 -0400 Subject: [PATCH 4302/4345] UPSTREAM: net/sched: cls_route: No longer copy tcf_result on update to avoid use-after-free [ Upstream commit b80b829e9e2c1b3f7aae34855e04d8f6ecaf13c8 ] When route4_change() is called on an existing filter, the whole tcf_result struct is always copied into the new instance of the filter. This causes a problem when updating a filter bound to a class, as tcf_unbind_filter() is always called on the old instance in the success path, decreasing filter_cnt of the still referenced class and allowing it to be deleted, leading to a use-after-free. Fix this by no longer copying the tcf_result struct from the old filter. Bug: 296347075 Fixes: 1109c00547fc ("net: sched: RCU cls_route") Reported-by: valis Reported-by: Bing-Jhong Billy Jheng Signed-off-by: valis Signed-off-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Reviewed-by: Pedro Tammela Reviewed-by: M A Ramdhan Link: https://lore.kernel.org/r/20230729123202.72406-4-jhs@mojatatu.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin (cherry picked from commit d4d3b53a4c66004e8e864fea744b3a2b86a73b62) Signed-off-by: Lee Jones Change-Id: Iefbd201b92847ec1349f92c107d7ef5aec3fb359 --- net/sched/cls_route.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index b775e681cb56..1ad4b3e60eb3 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -511,7 +511,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (fold) { f->id = fold->id; f->iif = fold->iif; - f->res = fold->res; f->handle = fold->handle; f->tp = fold->tp; From 6d38ae2f4c5f1232666b2b922f9a0547f9a29dfb Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Thu, 6 Apr 2023 16:21:43 -0700 Subject: [PATCH 4303/4345] UPSTREAM: usb: dwc3: gadget: Stall and restart EP0 if host is unresponsive It was observed that there are hosts that may complete pending SETUP transactions before the stop active transfers and controller halt occurs, leading to lingering endxfer commands on DEPs on subsequent pullup/gadget start iterations. dwc3_gadget_ep_disable name=ep8in flags=0x3009 direction=1 dwc3_gadget_ep_disable name=ep4in flags=1 direction=1 dwc3_gadget_ep_disable name=ep3out flags=1 direction=0 usb_gadget_disconnect deactivated=0 connected=0 ret=0 The sequence shows that the USB gadget disconnect (dwc3_gadget_pullup(0)) routine completed successfully, allowing for the USB gadget to proceed with a USB gadget connect. However, if this occurs the system runs into an issue where: BUG: spinlock already unlocked on CPU spin_bug+0x0 dwc3_remove_requests+0x278 dwc3_ep0_out_start+0xb0 __dwc3_gadget_start+0x25c This is due to the pending endxfers, leading to gadget start (w/o lock held) to execute the remove requests, which will unlock the dwc3 spinlock as part of giveback. To mitigate this, resolve the pending endxfers on the pullup disable path by re-locating the SETUP phase check after stop active transfers, since that is where the DWC3_EP_DELAY_STOP is potentially set. This also allows for handling of a host that may be unresponsive by using the completion timeout to trigger the stall and restart for EP0. Fixes: c96683798e27 ("usb: dwc3: ep0: Don't prepare beyond Setup stage") Signed-off-by: Wesley Cheng Fixes: c96683798e27 ("usb: dwc3: ep0: Don't prepare beyond Setup stage") Cc: stable@vger.kernel.org Acked-by: Thinh Nguyen Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/20230413195742.11821-2-quic_wcheng@quicinc.com Signed-off-by: Greg Kroah-Hartman Bug: 280741172 Bug: 277690231 Bug: 296168017 (cherry picked from commit 02435a739b81ae24aff5d6e930efef9458e2af3c usb-linus) Change-Id: Ifa9aeab01a4f45feaae59c2d393e6712f5370f08 Signed-off-by: Wesley Cheng Signed-off-by: Udipto Goswami (cherry picked from commit 5dd4405fee1bf7505d4211c083c695a2cf7adaea) (cherry picked from commit 82aad30f43743df34ce5b31be89ba8fc64233fa0) --- drivers/usb/dwc3/gadget.c | 49 +++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 17 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 3ec65523bdc5..12385775b98f 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2512,29 +2512,17 @@ static int __dwc3_gadget_start(struct dwc3 *dwc); static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) { unsigned long flags; + int ret; spin_lock_irqsave(&dwc->lock, flags); dwc->connected = false; /* - * Per databook, when we want to stop the gadget, if a control transfer - * is still in process, complete it and get the core into setup phase. + * Attempt to end pending SETUP status phase, and not wait for the + * function to do so. */ - if (dwc->ep0state != EP0_SETUP_PHASE) { - int ret; - - if (dwc->delayed_status) - dwc3_ep0_send_delayed_status(dwc); - - reinit_completion(&dwc->ep0_in_setup); - - spin_unlock_irqrestore(&dwc->lock, flags); - ret = wait_for_completion_timeout(&dwc->ep0_in_setup, - msecs_to_jiffies(DWC3_PULL_UP_TIMEOUT)); - spin_lock_irqsave(&dwc->lock, flags); - if (ret == 0) - dev_warn(dwc->dev, "timed out waiting for SETUP phase\n"); - } + if (dwc->delayed_status) + dwc3_ep0_send_delayed_status(dwc); /* * In the Synopsys DesignWare Cores USB3 Databook Rev. 3.30a @@ -2547,6 +2535,33 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); + /* + * Per databook, when we want to stop the gadget, if a control transfer + * is still in process, complete it and get the core into setup phase. + * In case the host is unresponsive to a SETUP transaction, forcefully + * stall the transfer, and move back to the SETUP phase, so that any + * pending endxfers can be executed. + */ + if (dwc->ep0state != EP0_SETUP_PHASE) { + reinit_completion(&dwc->ep0_in_setup); + + ret = wait_for_completion_timeout(&dwc->ep0_in_setup, + msecs_to_jiffies(DWC3_PULL_UP_TIMEOUT)); + if (ret == 0) { + unsigned int dir; + + dev_warn(dwc->dev, "wait for SETUP phase timed out\n"); + spin_lock_irqsave(&dwc->lock, flags); + dir = !!dwc->ep0_expect_in; + if (dwc->ep0state == EP0_DATA_PHASE) + dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); + else + dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); + dwc3_ep0_stall_and_restart(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); + } + } + /* * Note: if the GEVNTCOUNT indicates events in the event buffer, the * driver needs to acknowledge them before the controller can halt. From f2545eebf062f2dddb122463daff4771ffb1fd04 Mon Sep 17 00:00:00 2001 From: Krishna Kurapati Date: Wed, 16 Aug 2023 14:32:08 +0530 Subject: [PATCH 4304/4345] BACKPORT: UPSTREAM: usb: dwc3: gadget: Execute gadget stop after halting the controller Do not call gadget stop until the poll for controller halt is completed. DEVTEN is cleared as part of gadget stop, so the intention to allow ep0 events to continue while waiting for controller halt is not happening. Fixes: c96683798e27 ("usb: dwc3: ep0: Don't prepare beyond Setup stage") Cc: stable@vger.kernel.org Acked-by: Thinh Nguyen Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/20230420212759.29429-2-quic_wcheng@quicinc.com Signed-off-by: Greg Kroah-Hartman Bug: 280741172 Bug: 277690231 Bug: 296168017 [ugoswami: Modified the function dwc3_gadget_run_stop to remove dependency from cleanup patch.] (cherry picked from commit 39674be56fba1cd3a03bf4617f523a35f85fd2c1 usb-linus) Change-Id: I2a8a42e938a680cefc0d1a56274caf155a4f99cd Signed-off-by: Wesley Cheng Signed-off-by: Udipto Goswami Signed-off-by: Krishna Kurapati (cherry picked from commit 45902380021d3fe742f9e6d49337ad3746f00d64) (cherry picked from commit 1ce1603175dafecd3e19ed7b8422c16b538a849b) --- drivers/usb/dwc3/gadget.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 12385775b98f..f27cbe9a39ae 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2532,7 +2532,6 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) * bit. */ dwc3_stop_active_transfers(dwc); - __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); /* @@ -2569,7 +2568,19 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) * remaining event generated by the controller while polling for * DSTS.DEVCTLHLT. */ - return dwc3_gadget_run_stop(dwc, false, false); + ret = dwc3_gadget_run_stop(dwc, false, false); + + /* + * Stop the gadget after controller is halted, so that if needed, the + * events to update EP0 state can still occur while the run/stop + * routine polls for the halted state. DEVTEN is cleared as part of + * gadget stop. + */ + spin_lock_irqsave(&dwc->lock, flags); + __dwc3_gadget_stop(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); + + return ret; } static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) From 819a8605da765d34b549a9f2a07b6e3a4a324186 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 23 Jul 2023 16:41:48 +0200 Subject: [PATCH 4305/4345] UPSTREAM: netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID [ Upstream commit 0ebc1064e4874d5987722a2ddbc18f94aa53b211 ] Bail out with EOPNOTSUPP when adding rule to bound chain via NFTA_RULE_CHAIN_ID. The following warning splat is shown when adding a rule to a deleted bound chain: WARNING: CPU: 2 PID: 13692 at net/netfilter/nf_tables_api.c:2013 nf_tables_chain_destroy+0x1f7/0x210 [nf_tables] CPU: 2 PID: 13692 Comm: chain-bound-rul Not tainted 6.1.39 #1 RIP: 0010:nf_tables_chain_destroy+0x1f7/0x210 [nf_tables] Bug: 296128351 Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: Kevin Rich Signed-off-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Sasha Levin (cherry picked from commit 268cb07ef3ee17b5454a7c4b23376802c5b00c79) Signed-off-by: Lee Jones Change-Id: Icf97f57d18bb2b30ed28a3de6cdd18661d7f1c3d --- net/netfilter/nf_tables_api.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9d6902e6a8c7..0d2835965e6e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3193,8 +3193,6 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) - return -EOPNOTSUPP; } else if (nla[NFTA_RULE_CHAIN_ID]) { chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID]); @@ -3206,6 +3204,9 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return -EINVAL; } + if (nft_chain_is_bound(chain)) + return -EOPNOTSUPP; + if (nla[NFTA_RULE_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE])); rule = __nft_rule_lookup(chain, handle); From 169c9f103fad5030504961d0296fd3396921b1e4 Mon Sep 17 00:00:00 2001 From: Laszlo Ersek Date: Mon, 31 Jul 2023 18:42:36 +0200 Subject: [PATCH 4306/4345] UPSTREAM: net: tun_chr_open(): set sk_uid from current_fsuid() commit 9bc3047374d5bec163e83e743709e23753376f0c upstream. Commit a096ccca6e50 initializes the "sk_uid" field in the protocol socket (struct sock) from the "/dev/net/tun" device node's owner UID. Per original commit 86741ec25462 ("net: core: Add a UID field to struct sock.", 2016-11-04), that's wrong: the idea is to cache the UID of the userspace process that creates the socket. Commit 86741ec25462 mentions socket() and accept(); with "tun", the action that creates the socket is open("/dev/net/tun"). Therefore the device node's owner UID is irrelevant. In most cases, "/dev/net/tun" will be owned by root, so in practice, commit a096ccca6e50 has no observable effect: - before, "sk_uid" would be zero, due to undefined behavior (CVE-2023-1076), - after, "sk_uid" would be zero, due to "/dev/net/tun" being owned by root. What matters is the (fs)UID of the process performing the open(), so cache that in "sk_uid". Bug: 295995961 Cc: Eric Dumazet Cc: Lorenzo Colitti Cc: Paolo Abeni Cc: Pietro Borrello Cc: netdev@vger.kernel.org Cc: stable@vger.kernel.org Fixes: a096ccca6e50 ("tun: tun_chr_open(): correctly initialize socket uid") Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2173435 Signed-off-by: Laszlo Ersek Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman (cherry picked from commit b6846d7c408b33e4701f4f5ca28932e2a08e0a2e) Signed-off-by: Lee Jones Change-Id: I2540ac5876ca7dad39e1b867a5e09a5c9c69bb86 --- drivers/net/tun.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index f1d46aea8a2b..0e70877c932c 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3457,7 +3457,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; - sock_init_data_uid(&tfile->socket, &tfile->sk, inode->i_uid); + sock_init_data_uid(&tfile->socket, &tfile->sk, current_fsuid()); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; From b019a989a2344872f8172024cdff6e3ec49cb6a0 Mon Sep 17 00:00:00 2001 From: Laszlo Ersek Date: Mon, 31 Jul 2023 18:42:37 +0200 Subject: [PATCH 4307/4345] UPSTREAM: net: tap_open(): set sk_uid from current_fsuid() commit 5c9241f3ceab3257abe2923a59950db0dc8bb737 upstream. Commit 66b2c338adce initializes the "sk_uid" field in the protocol socket (struct sock) from the "/dev/tapX" device node's owner UID. Per original commit 86741ec25462 ("net: core: Add a UID field to struct sock.", 2016-11-04), that's wrong: the idea is to cache the UID of the userspace process that creates the socket. Commit 86741ec25462 mentions socket() and accept(); with "tap", the action that creates the socket is open("/dev/tapX"). Therefore the device node's owner UID is irrelevant. In most cases, "/dev/tapX" will be owned by root, so in practice, commit 66b2c338adce has no observable effect: - before, "sk_uid" would be zero, due to undefined behavior (CVE-2023-1076), - after, "sk_uid" would be zero, due to "/dev/tapX" being owned by root. What matters is the (fs)UID of the process performing the open(), so cache that in "sk_uid". Bug: 295995961 Cc: Eric Dumazet Cc: Lorenzo Colitti Cc: Paolo Abeni Cc: Pietro Borrello Cc: netdev@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 66b2c338adce ("tap: tap_open(): correctly initialize socket uid") Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2173435 Signed-off-by: Laszlo Ersek Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 767800fc402deac438c5aed9c82f0e71a70c86fd) Signed-off-by: Lee Jones Change-Id: Ib5f80015e5c0280acf9f35124d3ff267ff0420f0 --- drivers/net/tap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index f9b3eb2d8d8b..41ee56015a45 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -523,7 +523,7 @@ static int tap_open(struct inode *inode, struct file *file) q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; - sock_init_data_uid(&q->sock, &q->sk, inode->i_uid); + sock_init_data_uid(&q->sock, &q->sk, current_fsuid()); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; From 8af1bc562213c4a4aaa2c97a14e86bfe18b5dc4d Mon Sep 17 00:00:00 2001 From: Zichun Zheng Date: Mon, 21 Aug 2023 19:29:53 +0800 Subject: [PATCH 4308/4345] ANDROID: GKI: export symbols to modify lru stats Export the symbols below to modify LRU state: __mod_lruvec_state mem_cgroup_update_lru_size Bug: 296526618 Change-Id: Ie05a2d21fa6ad400877b1c41d732346232452f78 Signed-off-by: Lianjun Huang (cherry picked from commit I7804b30282b865a004f5a7193537aea688901043) Signed-off-by: Zichun Zheng --- mm/memcontrol.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 88b188c20763..09b894394bcb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -858,6 +858,7 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, if (!mem_cgroup_disabled()) __mod_memcg_lruvec_state(lruvec, idx, val); } +EXPORT_SYMBOL_GPL(__mod_lruvec_state); void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { @@ -1442,6 +1443,7 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, if (nr_pages > 0) *lru_size += nr_pages; } +EXPORT_SYMBOL_GPL(mem_cgroup_update_lru_size); /** * mem_cgroup_margin - calculate chargeable space of a memory cgroup From 98a66e87c13c2cbc694fd0857acf42cb7bfc9a31 Mon Sep 17 00:00:00 2001 From: Zichun Zheng Date: Tue, 22 Aug 2023 12:06:22 +0800 Subject: [PATCH 4309/4345] ANDROID: Export symbols to do reverse mapping within memcg in kernel modules. Export the symbols below to do reverse mapping within memcg: root_mem_cgroup page_referenced Bug: 296526618 Change-Id: Ia9c5876bd97d3f13c92b28af2ca5e74b3f91bd5a Signed-off-by: Zichun Zheng --- mm/memcontrol.c | 1 + mm/rmap.c | 1 + 2 files changed, 2 insertions(+) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 09b894394bcb..b6f6bfc0a700 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -73,6 +73,7 @@ struct cgroup_subsys memory_cgrp_subsys __read_mostly; EXPORT_SYMBOL(memory_cgrp_subsys); struct mem_cgroup *root_mem_cgroup __read_mostly; +EXPORT_SYMBOL_GPL(root_mem_cgroup); /* Active memory cgroup to use from an interrupt context */ DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg); diff --git a/mm/rmap.c b/mm/rmap.c index 422b3d0deb8f..5338a8b1d846 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -915,6 +915,7 @@ int page_referenced(struct page *page, return rwc.contended ? -1 : pra.referenced; } +EXPORT_SYMBOL_GPL(page_referenced); static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) From 14ce45e3c76adca6594c89fccd0a39cfd1fcfa25 Mon Sep 17 00:00:00 2001 From: Zichun Zheng Date: Tue, 22 Aug 2023 20:18:31 +0800 Subject: [PATCH 4310/4345] ANDROID: ABI: Update oplus symbol list Leaf changes summary: 4 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 3 Added functions Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 1 Added variable 3 Added functions: [A] 'function void __mod_lruvec_state(lruvec*, node_stat_item, int)' [A] 'function void mem_cgroup_update_lru_size(lruvec*, lru_list, int, int)' [A] 'function int page_referenced(page*, int, mem_cgroup*, unsigned long int*)' 1 Added variable: [A] 'mem_cgroup* root_mem_cgroup' Bug: 296526618 Change-Id: I519edbc96555a7156863c5f4507cf8335fa5cb96 Signed-off-by: Zichun Zheng --- android/abi_gki_aarch64.xml | 89 ++++++++++++++++++++++------------- android/abi_gki_aarch64_oplus | 4 ++ 2 files changed, 61 insertions(+), 32 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index dfb8ddeb4435..105201c59166 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -190,6 +190,7 @@ + @@ -3551,6 +3552,7 @@ + @@ -3999,6 +4001,7 @@ + @@ -6995,6 +6998,7 @@ + @@ -117616,6 +117620,12 @@ + + + + + + @@ -128195,7 +128205,7 @@ - + @@ -130999,10 +131009,10 @@ - - - - + + + + @@ -132508,8 +132518,8 @@ - - + + @@ -132671,8 +132681,8 @@ - - + + @@ -136314,10 +136324,17 @@ - - + + + + + + + + + @@ -136326,7 +136343,7 @@ - + @@ -136346,7 +136363,7 @@ - + @@ -137122,16 +137139,16 @@ - - + + - - + + - - + + @@ -138556,8 +138573,8 @@ - - + + @@ -138586,6 +138603,13 @@ + + + + + + + @@ -138600,9 +138624,9 @@ - - - + + + @@ -142102,6 +142126,7 @@ + @@ -150412,18 +150437,18 @@ - - - + + + - - - + + + - - + + diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index 51738dc7cd4d..59b2cd34eaf8 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -1549,6 +1549,7 @@ __memcat_p memcg_kmem_enabled_key mem_cgroup_from_id + mem_cgroup_update_lru_size memchr memchr_inv memcmp @@ -1616,6 +1617,7 @@ mmc_send_tuning mmput mod_delayed_work_on + __mod_lruvec_state mod_node_page_state mod_timer mod_timer_pending @@ -1815,6 +1817,7 @@ __page_mapcount page_mapping __page_pinner_migration_failed + page_referenced page_symlink page_to_lruvec panic @@ -2253,6 +2256,7 @@ rndis_set_param_vendor rndis_signal_connect rndis_uninit + root_mem_cgroup root_task_group round_jiffies round_jiffies_relative From 8e682bb18a9b11bc7d036eae0f562dd6cf8e2eff Mon Sep 17 00:00:00 2001 From: Sungwoo Kim Date: Wed, 31 May 2023 01:39:56 -0400 Subject: [PATCH 4311/4345] UPSTREAM: Bluetooth: L2CAP: Fix use-after-free in l2cap_sock_ready_cb commit 1728137b33c00d5a2b5110ed7aafb42e7c32e4a1 upstream. l2cap_sock_release(sk) frees sk. However, sk's children are still alive and point to the already free'd sk's address. To fix this, l2cap_sock_release(sk) also cleans sk's children. ================================================================== BUG: KASAN: use-after-free in l2cap_sock_ready_cb+0xb7/0x100 net/bluetooth/l2cap_sock.c:1650 Read of size 8 at addr ffff888104617aa8 by task kworker/u3:0/276 CPU: 0 PID: 276 Comm: kworker/u3:0 Not tainted 6.2.0-00001-gef397bd4d5fb-dirty #59 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: hci2 hci_rx_work Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x72/0x95 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:306 [inline] print_report+0x175/0x478 mm/kasan/report.c:417 kasan_report+0xb1/0x130 mm/kasan/report.c:517 l2cap_sock_ready_cb+0xb7/0x100 net/bluetooth/l2cap_sock.c:1650 l2cap_chan_ready+0x10e/0x1e0 net/bluetooth/l2cap_core.c:1386 l2cap_config_req+0x753/0x9f0 net/bluetooth/l2cap_core.c:4480 l2cap_bredr_sig_cmd net/bluetooth/l2cap_core.c:5739 [inline] l2cap_sig_channel net/bluetooth/l2cap_core.c:6509 [inline] l2cap_recv_frame+0xe2e/0x43c0 net/bluetooth/l2cap_core.c:7788 l2cap_recv_acldata+0x6ed/0x7e0 net/bluetooth/l2cap_core.c:8506 hci_acldata_packet net/bluetooth/hci_core.c:3813 [inline] hci_rx_work+0x66e/0xbc0 net/bluetooth/hci_core.c:4048 process_one_work+0x4ea/0x8e0 kernel/workqueue.c:2289 worker_thread+0x364/0x8e0 kernel/workqueue.c:2436 kthread+0x1b9/0x200 kernel/kthread.c:376 ret_from_fork+0x2c/0x50 arch/x86/entry/entry_64.S:308 Allocated by task 288: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:374 [inline] __kasan_kmalloc+0x82/0x90 mm/kasan/common.c:383 kasan_kmalloc include/linux/kasan.h:211 [inline] __do_kmalloc_node mm/slab_common.c:968 [inline] __kmalloc+0x5a/0x140 mm/slab_common.c:981 kmalloc include/linux/slab.h:584 [inline] sk_prot_alloc+0x113/0x1f0 net/core/sock.c:2040 sk_alloc+0x36/0x3c0 net/core/sock.c:2093 l2cap_sock_alloc.constprop.0+0x39/0x1c0 net/bluetooth/l2cap_sock.c:1852 l2cap_sock_create+0x10d/0x220 net/bluetooth/l2cap_sock.c:1898 bt_sock_create+0x183/0x290 net/bluetooth/af_bluetooth.c:132 __sock_create+0x226/0x380 net/socket.c:1518 sock_create net/socket.c:1569 [inline] __sys_socket_create net/socket.c:1606 [inline] __sys_socket_create net/socket.c:1591 [inline] __sys_socket+0x112/0x200 net/socket.c:1639 __do_sys_socket net/socket.c:1652 [inline] __se_sys_socket net/socket.c:1650 [inline] __x64_sys_socket+0x40/0x50 net/socket.c:1650 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 288: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x50 mm/kasan/generic.c:523 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free mm/kasan/common.c:200 [inline] __kasan_slab_free+0x10a/0x190 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook mm/slub.c:1807 [inline] slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x88/0x1f0 mm/slub.c:3800 sk_prot_free net/core/sock.c:2076 [inline] __sk_destruct+0x347/0x430 net/core/sock.c:2168 sk_destruct+0x9c/0xb0 net/core/sock.c:2183 __sk_free+0x82/0x220 net/core/sock.c:2194 sk_free+0x7c/0xa0 net/core/sock.c:2205 sock_put include/net/sock.h:1991 [inline] l2cap_sock_kill+0x256/0x2b0 net/bluetooth/l2cap_sock.c:1257 l2cap_sock_release+0x1a7/0x220 net/bluetooth/l2cap_sock.c:1428 __sock_release+0x80/0x150 net/socket.c:650 sock_close+0x19/0x30 net/socket.c:1368 __fput+0x17a/0x5c0 fs/file_table.c:320 task_work_run+0x132/0x1c0 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x113/0x120 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x21/0x50 kernel/entry/common.c:296 do_syscall_64+0x4c/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x72/0xdc The buggy address belongs to the object at ffff888104617800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 680 bytes inside of 1024-byte region [ffff888104617800, ffff888104617c00) The buggy address belongs to the physical page: page:00000000dbca6a80 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888104614000 pfn:0x104614 head:00000000dbca6a80 order:2 compound_mapcount:0 subpages_mapcount:0 compound_pincount:0 flags: 0x200000000010200(slab|head|node=0|zone=2) raw: 0200000000010200 ffff888100041dc0 ffffea0004212c10 ffffea0004234b10 raw: ffff888104614000 0000000000080002 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888104617980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888104617a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888104617a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888104617b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888104617b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Bug: 297025149 Ack: This bug is found by FuzzBT with a modified Syzkaller. Other contributors are Ruoyu Wu and Hui Peng. Signed-off-by: Sungwoo Kim Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 29fac18499332211b2615ade356e2bd8b3269f98) Signed-off-by: Lee Jones Change-Id: I1f4cf5a928b4825c63488bde0d5589517cc84ef8 --- net/bluetooth/l2cap_sock.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index a267c9b6bcef..756523e5402a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -45,6 +45,7 @@ static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern); +static void l2cap_sock_cleanup_listen(struct sock *parent); bool l2cap_is_socket(struct socket *sock) { @@ -1414,6 +1415,7 @@ static int l2cap_sock_release(struct socket *sock) if (!sk) return 0; + l2cap_sock_cleanup_listen(sk); bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, SHUT_RDWR); From 8001debfc11998c8d6ea9695f5062b2839468ea3 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Tue, 23 May 2023 07:59:32 +0800 Subject: [PATCH 4312/4345] UPSTREAM: media: usb: siano: Fix warning due to null work_func_t function pointer [ Upstream commit 6f489a966fbeb0da63d45c2c66a8957eab604bf6 ] The previous commit ebad8e731c1c ("media: usb: siano: Fix use after free bugs caused by do_submit_urb") adds cancel_work_sync() in smsusb_stop_streaming(). But smsusb_stop_streaming() may be called, even if the work_struct surb->wq has not been initialized. As a result, the warning will occur. One of the processes that could lead to warning is shown below: smsusb_probe() smsusb_init_device() if (!dev->in_ep || !dev->out_ep || align < 0) { smsusb_term_device(intf); smsusb_stop_streaming() cancel_work_sync(&dev->surbs[i].wq); __cancel_work_timer() __flush_work() if (WARN_ON(!work->func)) // work->func is null The log reported by syzbot is shown below: WARNING: CPU: 0 PID: 897 at kernel/workqueue.c:3066 __flush_work+0x798/0xa80 kernel/workqueue.c:3063 Modules linked in: CPU: 0 PID: 897 Comm: kworker/0:2 Not tainted 6.2.0-rc1-syzkaller #0 RIP: 0010:__flush_work+0x798/0xa80 kernel/workqueue.c:3066 ... RSP: 0018:ffffc9000464ebf8 EFLAGS: 00010246 RAX: 1ffff11002dbb420 RBX: 0000000000000021 RCX: 1ffffffff204fa4e RDX: dffffc0000000000 RSI: 0000000000000001 RDI: ffff888016dda0e8 RBP: ffffc9000464ed98 R08: 0000000000000001 R09: ffffffff90253b2f R10: 0000000000000001 R11: 0000000000000000 R12: ffff888016dda0e8 R13: ffff888016dda0e8 R14: ffff888016dda100 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880b9a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffd4331efe8 CR3: 000000000b48e000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __cancel_work_timer+0x315/0x460 kernel/workqueue.c:3160 smsusb_stop_streaming drivers/media/usb/siano/smsusb.c:182 [inline] smsusb_term_device+0xda/0x2d0 drivers/media/usb/siano/smsusb.c:344 smsusb_init_device+0x400/0x9ce drivers/media/usb/siano/smsusb.c:419 smsusb_probe+0xbbd/0xc55 drivers/media/usb/siano/smsusb.c:567 ... This patch adds check before cancel_work_sync(). If surb->wq has not been initialized, the cancel_work_sync() will not be executed. Bug: 295075980 Reported-by: syzbot+27b0b464864741b18b99@syzkaller.appspotmail.com Fixes: ebad8e731c1c ("media: usb: siano: Fix use after free bugs caused by do_submit_urb") Signed-off-by: Duoming Zhou Signed-off-by: Hans Verkuil Signed-off-by: Sasha Levin (cherry picked from commit 8abb53c5167cfb5bb275512a3da4ec2468478626) Signed-off-by: Lee Jones Change-Id: Ie2946408cfde466d0138c23093ec6738b7e51161 --- drivers/media/usb/siano/smsusb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c index 1babfe6e2c36..5c223b5498b4 100644 --- a/drivers/media/usb/siano/smsusb.c +++ b/drivers/media/usb/siano/smsusb.c @@ -179,7 +179,8 @@ static void smsusb_stop_streaming(struct smsusb_device_t *dev) for (i = 0; i < MAX_URBS; i++) { usb_kill_urb(&dev->surbs[i].urb); - cancel_work_sync(&dev->surbs[i].wq); + if (dev->surbs[i].wq.func) + cancel_work_sync(&dev->surbs[i].wq); if (dev->surbs[i].cb) { smscore_putbuffer(dev->coredev, dev->surbs[i].cb); From a8b58500cb6b8b9c2c489d69451a7706c87adac3 Mon Sep 17 00:00:00 2001 From: Amit Pundir Date: Wed, 26 Jul 2023 18:57:19 +0530 Subject: [PATCH 4313/4345] FROMGIT: arm64: dts: qcom: sdm845-db845c: Mark cont splash memory region as reserved Adding a reserved memory region for the framebuffer memory (the splash memory region set up by the bootloader). It fixes a kernel panic (arm-smmu: Unhandled context fault at this particular memory region) reported on DB845c running v5.10.y. Cc: stable@vger.kernel.org # v5.10+ Reviewed-by: Caleb Connolly Signed-off-by: Amit Pundir Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230726132719.2117369-2-amit.pundir@linaro.org Signed-off-by: Bjorn Andersson Bug: 146449535 (cherry picked from commit 110e70fccce4 https://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux.git tags/qcom-arm64-for-6.6) Signed-off-by: Amit Pundir Change-Id: Ib369b94c3bacc694a4ecf70a9bc4b85355d4c32a --- arch/arm64/boot/dts/qcom/sdm845-db845c.dts | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index 1e889ca932e4..67cd869de352 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -85,6 +85,14 @@ }; }; + reserved-memory { + /* Cont splash region set up by the bootloader */ + cont_splash_mem: framebuffer@9d400000 { + reg = <0x0 0x9d400000 0x0 0x2400000>; + no-map; + }; + }; + lt9611_1v8: lt9611-vdd18-regulator { compatible = "regulator-fixed"; regulator-name = "LT9611_1V8"; @@ -482,6 +490,7 @@ }; &mdss { + memory-region = <&cont_splash_mem>; status = "okay"; }; From dcb17f36f37e648a8f6aebe7ee735f09197827c3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Tue, 25 Jul 2023 05:36:23 -0700 Subject: [PATCH 4314/4345] BACKPORT: FROMGIT: netfilter: nfnetlink_log: always add a timestamp MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Compared to all the other work we're already doing to deliver an skb to userspace this is very cheap - at worse an extra call to ktime_get_real() - and very useful. (and indeed it may even be cheaper if we're running from other hooks) (background: Android occasionally logs packets which caused wake from sleep/suspend and we'd like to have timestamps reliably associated with these events) Cc: Pablo Neira Ayuso Cc: Martin KaFai Lau Cc: Florian Westphal Signed-off-by: Maciej Żenczykowski (cherry picked from commit 1d85594fd3e7e39e63b53b1bdc2d89db43b6ecd5 https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git main) Bug: 276360178 Change-Id: I254a8d39cb7a232d47865a04cd6e0279606fa40e --- net/netfilter/nfnetlink_log.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index f087baa95b07..26ab27981ad4 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -583,9 +583,9 @@ __build_packet_message(struct nfnl_log_net *log, goto nla_put_failure; } - if (hooknum <= NF_INET_FORWARD && skb->tstamp) { + if (hooknum <= NF_INET_FORWARD) { struct nfulnl_msg_packet_timestamp ts; - struct timespec64 kts = ktime_to_timespec64(skb->tstamp); + struct timespec64 kts = ktime_to_timespec64(skb->tstamp ?: ktime_get_real()); ts.sec = cpu_to_be64(kts.tv_sec); ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC); From 966df87a17dafeb8c10024938ae5fcdc54102284 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 13 Jul 2023 21:59:37 +0900 Subject: [PATCH 4315/4345] UPSTREAM: exfat: check if filename entries exceeds max filename length [ Upstream commit d42334578eba1390859012ebb91e1e556d51db49 ] exfat_extract_uni_name copies characters from a given file name entry into the 'uniname' variable. This variable is actually defined on the stack of the exfat_readdir() function. According to the definition of the 'exfat_uni_name' type, the file name should be limited 255 characters (+ null teminator space), but the exfat_get_uniname_from_ext_entry() function can write more characters because there is no check if filename entries exceeds max filename length. This patch add the check not to copy filename characters when exceeding max filename length. Bug: 296393077 Cc: stable@vger.kernel.org Cc: Yuezhang Mo Reported-by: Maxim Suhanov Reviewed-by: Sungjong Seo Signed-off-by: Namjae Jeon Signed-off-by: Sasha Levin (cherry picked from commit c2fdf827f8fc6a571e1b7cc38a61041f0321adf5) Signed-off-by: Lee Jones Change-Id: I57a9ab007a5eac9c3415aa460df324c9044908c0 --- fs/exfat/dir.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 148bc9901e91..57e679a23d0f 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -33,6 +33,7 @@ static void exfat_get_uniname_from_ext_entry(struct super_block *sb, { int i; struct exfat_entry_set_cache *es; + unsigned int uni_len = 0, len; es = exfat_get_dentry_set(sb, p_dir, entry, ES_ALL_ENTRIES); if (!es) @@ -51,7 +52,10 @@ static void exfat_get_uniname_from_ext_entry(struct super_block *sb, if (exfat_get_entry_type(ep) != TYPE_EXTEND) break; - exfat_extract_uni_name(ep, uniname); + len = exfat_extract_uni_name(ep, uniname); + uni_len += len; + if (len != EXFAT_FILE_NAME_LEN || uni_len >= MAX_NAME_LENGTH) + break; uniname += EXFAT_FILE_NAME_LEN; } @@ -1023,7 +1027,8 @@ rewind: if (entry_type == TYPE_EXTEND) { unsigned short entry_uniname[16], unichar; - if (step != DIRENT_STEP_NAME) { + if (step != DIRENT_STEP_NAME || + name_len >= MAX_NAME_LENGTH) { step = DIRENT_STEP_FILE; continue; } From d26e92d681b9aa8a16946f3eff64cc5363e93f90 Mon Sep 17 00:00:00 2001 From: Enlin Mu Date: Tue, 1 Aug 2023 14:04:32 +0800 Subject: [PATCH 4316/4345] FROMGIT: pstore/ram: Check start of empty przs during init After commit 30696378f68a ("pstore/ram: Do not treat empty buffers as valid"), initialization would assume a prz was valid after seeing that the buffer_size is zero (regardless of the buffer start position). This unchecked start value means it could be outside the bounds of the buffer, leading to future access panics when written to: sysdump_panic_event+0x3b4/0x5b8 atomic_notifier_call_chain+0x54/0x90 panic+0x1c8/0x42c die+0x29c/0x2a8 die_kernel_fault+0x68/0x78 __do_kernel_fault+0x1c4/0x1e0 do_bad_area+0x40/0x100 do_translation_fault+0x68/0x80 do_mem_abort+0x68/0xf8 el1_da+0x1c/0xc0 __raw_writeb+0x38/0x174 __memcpy_toio+0x40/0xac persistent_ram_update+0x44/0x12c persistent_ram_write+0x1a8/0x1b8 ramoops_pstore_write+0x198/0x1e8 pstore_console_write+0x94/0xe0 ... To avoid this, also check if the prz start is 0 during the initialization phase. If not, the next prz sanity check case will discover it (start > size) and zap the buffer back to a sane state. Bug: 293538531 Fixes: 30696378f68a ("pstore/ram: Do not treat empty buffers as valid") Cc: Yunlong Xing Cc: stable@vger.kernel.org Change-Id: I6ff3a11b8b21f6f5ab37d8432751e5d33a441d8c Signed-off-by: Enlin Mu Link: https://lore.kernel.org/r/20230801060432.1307717-1-yunlong.xing@unisoc.com [kees: update commit log with backtrace and clarifications] (cherry picked from commit fe8c3623ab06603eb760444a032d426542212021 https://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/pstore) Signed-off-by: Kees Cook Signed-off-by: Chunhui Li (cherry picked from commit cd018c99fa2f79262262a2698455f9ee3e5f5076) --- fs/pstore/ram_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 879efc6833d6..551ab9c2b893 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -518,7 +518,7 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, sig ^= PERSISTENT_RAM_SIG; if (prz->buffer->sig == sig) { - if (buffer_size(prz) == 0) { + if (buffer_size(prz) == 0 && buffer_start(prz) == 0) { pr_debug("found existing empty buffer\n"); return 0; } From a9c0f622606835e4b9cb19e2833ba8a33a4843a3 Mon Sep 17 00:00:00 2001 From: Pratyush Brahma Date: Thu, 17 Aug 2023 15:38:28 +0530 Subject: [PATCH 4317/4345] ANDROID: mm: Export page_owner_inited and __set_page_owner Export page_owner_inited and __set_page_owner symbol for loadable vendor modules. Bug: 296348400 Change-Id: I220ec1b94326ca3c6cc809d54646c51194645197 Signed-off-by: Pratyush Brahma --- mm/page_owner.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/page_owner.c b/mm/page_owner.c index 8dd3f27db21a..b3e5f98f299b 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -33,6 +33,7 @@ struct page_owner { bool page_owner_enabled; DEFINE_STATIC_KEY_FALSE(page_owner_inited); +EXPORT_SYMBOL_GPL(page_owner_inited); static depot_stack_handle_t dummy_handle; static depot_stack_handle_t failure_handle; @@ -222,6 +223,7 @@ noinline void __set_page_owner(struct page *page, unsigned int order, __set_page_owner_handle(page, page_ext, handle, order, gfp_mask); page_ext_put(page_ext); } +EXPORT_SYMBOL_GPL(__set_page_owner); void __set_page_owner_migrate_reason(struct page *page, int reason) { From 300d1ff660bee3625303ab4a4a29c7206952cdef Mon Sep 17 00:00:00 2001 From: Pratyush Brahma Date: Mon, 21 Aug 2023 14:48:15 +0530 Subject: [PATCH 4318/4345] ANDROID: GKI: Update abi_gki_aarch64_qcom for page_owner symbols Update abi_gki_aarch64_qcom to include __set_page_owner and page_owner_inited symbols. Bug: 296348400 Change-Id: I3dec65fb596764e51897dd0251aada539a34feca Signed-off-by: Pratyush Brahma --- android/abi_gki_aarch64.xml | 15 ++++++++++++--- android/abi_gki_aarch64_qcom | 2 ++ 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 105201c59166..eb2020aed4b0 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -271,6 +271,7 @@ + @@ -6969,6 +6970,7 @@ + @@ -118078,6 +118080,12 @@ + + + + + + @@ -132544,9 +132552,9 @@ - - - + + + @@ -138577,6 +138585,7 @@ + diff --git a/android/abi_gki_aarch64_qcom b/android/abi_gki_aarch64_qcom index b269c937101c..3f4e8ded9169 100644 --- a/android/abi_gki_aarch64_qcom +++ b/android/abi_gki_aarch64_qcom @@ -1659,6 +1659,7 @@ overflowuid page_endio page_mapping + page_owner_inited __page_pinner_migration_failed __pagevec_release panic @@ -2187,6 +2188,7 @@ set_normalized_timespec64 set_page_dirty_lock __SetPageMovable + __set_page_owner set_task_cpu set_user_nice sg_alloc_table From 00c7bec87c460abfa95b61b5bbe61f26de8a3282 Mon Sep 17 00:00:00 2001 From: wangyongqiang Date: Mon, 31 Jul 2023 15:46:34 +0800 Subject: [PATCH 4319/4345] ANDROID: ABI: Update oplus symbol list ashmem: is_ashmem_file Export is_ashmem_file function which will be used by the minidump module to get ashmem info. Bug: 193397560 Change-Id: I5a54fba62dc28b04ae5c93f359709297c39ebbaa Signed-off-by: wangyongqiang1@oppo.com --- android/abi_gki_aarch64.xml | 5 +++++ android/abi_gki_aarch64_oplus | 1 + 2 files changed, 6 insertions(+) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index eb2020aed4b0..44a30600dc4e 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -3298,6 +3298,7 @@ + @@ -135040,6 +135041,10 @@ + + + + diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index 59b2cd34eaf8..124791f30bd2 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -1357,6 +1357,7 @@ irq_work_queue irq_work_queue_on irq_work_sync + is_ashmem_file is_dma_buf_file isolate_and_split_free_page isolate_anon_lru_page From ad067abfe132b612236d3bc232524318323df320 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 25 Jun 2023 17:10:07 +0800 Subject: [PATCH 4320/4345] BACKPORT: net: nfc: Fix use-after-free caused by nfc_llcp_find_local [ Upstream commit 6709d4b7bc2e079241fdef15d1160581c5261c10 ] This commit fixes several use-after-free that caused by function nfc_llcp_find_local(). For example, one UAF can happen when below buggy time window occurs. // nfc_genl_llc_get_params | // nfc_unregister_device | dev = nfc_get_device(idx); | device_lock(...) if (!dev) | dev->shutting_down = true; return -ENODEV; | device_unlock(...); | device_lock(...); | // nfc_llcp_unregister_device | nfc_llcp_find_local() nfc_llcp_find_local(...); | | local_cleanup() if (!local) { | rc = -ENODEV; | // nfc_llcp_local_put goto exit; | kref_put(.., local_release) } | | // local_release | list_del(&local->list) // nfc_genl_send_params | kfree() local->dev->idx !!!UAF!!! | | and the crash trace for the one of the discussed UAF like: BUG: KASAN: slab-use-after-free in nfc_genl_llc_get_params+0x72f/0x780 net/nfc/netlink.c:1045 Read of size 8 at addr ffff888105b0e410 by task 20114 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x72/0xa0 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:319 [inline] print_report+0xcc/0x620 mm/kasan/report.c:430 kasan_report+0xb2/0xe0 mm/kasan/report.c:536 nfc_genl_send_params net/nfc/netlink.c:999 [inline] nfc_genl_llc_get_params+0x72f/0x780 net/nfc/netlink.c:1045 genl_family_rcv_msg_doit.isra.0+0x1ee/0x2e0 net/netlink/genetlink.c:968 genl_family_rcv_msg net/netlink/genetlink.c:1048 [inline] genl_rcv_msg+0x503/0x7d0 net/netlink/genetlink.c:1065 netlink_rcv_skb+0x161/0x430 net/netlink/af_netlink.c:2548 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1076 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x644/0x900 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x934/0xe70 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b6/0x200 net/socket.c:747 ____sys_sendmsg+0x6e9/0x890 net/socket.c:2501 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2555 __sys_sendmsg+0xf7/0x1d0 net/socket.c:2584 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f34640a2389 RSP: 002b:00007f3463415168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f34641c1f80 RCX: 00007f34640a2389 RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000006 RBP: 00007f34640ed493 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe38449ecf R14: 00007f3463415300 R15: 0000000000022000 Allocated by task 20116: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:374 [inline] __kasan_kmalloc+0x7f/0x90 mm/kasan/common.c:383 kmalloc include/linux/slab.h:580 [inline] kzalloc include/linux/slab.h:720 [inline] nfc_llcp_register_device+0x49/0xa40 net/nfc/llcp_core.c:1567 nfc_register_device+0x61/0x260 net/nfc/core.c:1124 nci_register_device+0x776/0xb20 net/nfc/nci/core.c:1257 virtual_ncidev_open+0x147/0x230 drivers/nfc/virtual_ncidev.c:148 misc_open+0x379/0x4a0 drivers/char/misc.c:165 chrdev_open+0x26c/0x780 fs/char_dev.c:414 do_dentry_open+0x6c4/0x12a0 fs/open.c:920 do_open fs/namei.c:3560 [inline] path_openat+0x24fe/0x37e0 fs/namei.c:3715 do_filp_open+0x1ba/0x410 fs/namei.c:3742 do_sys_openat2+0x171/0x4c0 fs/open.c:1356 do_sys_open fs/open.c:1372 [inline] __do_sys_openat fs/open.c:1388 [inline] __se_sys_openat fs/open.c:1383 [inline] __x64_sys_openat+0x143/0x200 fs/open.c:1383 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 20115: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x50 mm/kasan/generic.c:521 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free mm/kasan/common.c:200 [inline] __kasan_slab_free+0x10a/0x190 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:162 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook mm/slub.c:1807 [inline] slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x7a/0x190 mm/slub.c:3800 local_release net/nfc/llcp_core.c:174 [inline] kref_put include/linux/kref.h:65 [inline] nfc_llcp_local_put net/nfc/llcp_core.c:182 [inline] nfc_llcp_local_put net/nfc/llcp_core.c:177 [inline] nfc_llcp_unregister_device+0x206/0x290 net/nfc/llcp_core.c:1620 nfc_unregister_device+0x160/0x1d0 net/nfc/core.c:1179 virtual_ncidev_close+0x52/0xa0 drivers/nfc/virtual_ncidev.c:163 __fput+0x252/0xa20 fs/file_table.c:321 task_work_run+0x174/0x270 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x108/0x110 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x21/0x50 kernel/entry/common.c:297 do_syscall_64+0x4c/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x72/0xdc Last potentially related work creation: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 __kasan_record_aux_stack+0x95/0xb0 mm/kasan/generic.c:491 kvfree_call_rcu+0x29/0xa80 kernel/rcu/tree.c:3328 drop_sysctl_table+0x3be/0x4e0 fs/proc/proc_sysctl.c:1735 unregister_sysctl_table.part.0+0x9c/0x190 fs/proc/proc_sysctl.c:1773 unregister_sysctl_table+0x24/0x30 fs/proc/proc_sysctl.c:1753 neigh_sysctl_unregister+0x5f/0x80 net/core/neighbour.c:3895 addrconf_notify+0x140/0x17b0 net/ipv6/addrconf.c:3684 notifier_call_chain+0xbe/0x210 kernel/notifier.c:87 call_netdevice_notifiers_info+0xb5/0x150 net/core/dev.c:1937 call_netdevice_notifiers_extack net/core/dev.c:1975 [inline] call_netdevice_notifiers net/core/dev.c:1989 [inline] dev_change_name+0x3c3/0x870 net/core/dev.c:1211 dev_ifsioc+0x800/0xf70 net/core/dev_ioctl.c:376 dev_ioctl+0x3d9/0xf80 net/core/dev_ioctl.c:542 sock_do_ioctl+0x160/0x260 net/socket.c:1213 sock_ioctl+0x3f9/0x670 net/socket.c:1316 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x19e/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc The buggy address belongs to the object at ffff888105b0e400 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 16 bytes inside of freed 1024-byte region [ffff888105b0e400, ffff888105b0e800) The buggy address belongs to the physical page: head:ffffea000416c200 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0x200000000010200(slab|head|node=0|zone=2) raw: 0200000000010200 ffff8881000430c0 ffffea00044c7010 ffffea0004510e10 raw: 0000000000000000 00000000000a000a 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888105b0e300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888105b0e380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888105b0e400: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888105b0e480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888105b0e500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb In summary, this patch solves those use-after-free by 1. Re-implement the nfc_llcp_find_local(). The current version does not grab the reference when getting the local from the linked list. For example, the llcp_sock_bind() gets the reference like below: // llcp_sock_bind() local = nfc_llcp_find_local(dev); // A ..... \ | raceable ..... / llcp_sock->local = nfc_llcp_local_get(local); // B There is an apparent race window that one can drop the reference and free the local object fetched in (A) before (B) gets the reference. 2. Some callers of the nfc_llcp_find_local() do not grab the reference at all. For example, the nfc_genl_llc_{{get/set}_params/sdreq} functions. We add the nfc_llcp_local_put() for them. Moreover, we add the necessary error handling function to put the reference. 3. Add the nfc_llcp_remove_local() helper. The local object is removed from the linked list in local_release() when all reference is gone. This patch removes it when nfc_llcp_unregister_device() is called. Therefore, every caller of nfc_llcp_find_local() will get a reference even when the nfc_llcp_unregister_device() is called. This promises no use-after-free for the local object is ever possible. Bug: 294167961 Fixes: 52feb444a903 ("NFC: Extend netlink interface for LTO, RW, and MIUX parameters support") Fixes: c7aa12252f51 ("NFC: Take a reference on the LLCP local pointer when creating a socket") Signed-off-by: Lin Ma Reviewed-by: Simon Horman Signed-off-by: David S. Miller Signed-off-by: Sasha Levin (cherry picked from commit 425d9d3a92df7d96b3cfb7ee5c240293a21cbde3) [Lee: Fix merge conflict - patch should render the same resulting diff added] Signed-off-by: Lee Jones Change-Id: I8e7e7101ce0d5c81da9b8febd4ad78dd1affc4a5 --- net/nfc/llcp.h | 1 - net/nfc/llcp_commands.c | 12 +++++++--- net/nfc/llcp_core.c | 51 ++++++++++++++++++++++++++++++++++------- net/nfc/llcp_sock.c | 18 +++++++++------ net/nfc/netlink.c | 20 ++++++++++++---- net/nfc/nfc.h | 1 + 6 files changed, 79 insertions(+), 24 deletions(-) diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index 97853c9cefc7..6f1ac54559af 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -202,7 +202,6 @@ void nfc_llcp_sock_link(struct llcp_sock_list *l, struct sock *s); void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *s); void nfc_llcp_socket_remote_param_init(struct nfc_llcp_sock *sock); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); -struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local); int nfc_llcp_local_put(struct nfc_llcp_local *local); u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, struct nfc_llcp_sock *sock); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 475061c79c44..1916dde99c96 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -359,6 +359,7 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) struct sk_buff *skb; struct nfc_llcp_local *local; u16 size = 0; + int err; pr_debug("Sending SYMM\n"); @@ -370,8 +371,10 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; skb = alloc_skb(size, GFP_KERNEL); - if (skb == NULL) - return -ENOMEM; + if (skb == NULL) { + err = -ENOMEM; + goto out; + } skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); @@ -381,8 +384,11 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX); - return nfc_data_exchange(dev, local->target_idx, skb, + err = nfc_data_exchange(dev, local->target_idx, skb, nfc_llcp_recv, local); +out: + nfc_llcp_local_put(local); + return err; } int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index edadebb3efd2..71dabf4e1024 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -17,6 +17,8 @@ static u8 llcp_magic[3] = {0x46, 0x66, 0x6d}; static LIST_HEAD(llcp_devices); +/* Protects llcp_devices list */ +static DEFINE_SPINLOCK(llcp_devices_lock); static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb); @@ -143,7 +145,7 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, write_unlock(&local->raw_sockets.lock); } -struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) +static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { kref_get(&local->ref); @@ -171,7 +173,6 @@ static void local_release(struct kref *ref) local = container_of(ref, struct nfc_llcp_local, ref); - list_del(&local->list); local_cleanup(local); kfree(local); } @@ -284,12 +285,33 @@ static void nfc_llcp_sdreq_timer(struct timer_list *t) struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev) { struct nfc_llcp_local *local; + struct nfc_llcp_local *res = NULL; + spin_lock(&llcp_devices_lock); list_for_each_entry(local, &llcp_devices, list) - if (local->dev == dev) - return local; + if (local->dev == dev) { + res = nfc_llcp_local_get(local); + break; + } + spin_unlock(&llcp_devices_lock); - pr_debug("No device found\n"); + return res; +} + +static struct nfc_llcp_local *nfc_llcp_remove_local(struct nfc_dev *dev) +{ + struct nfc_llcp_local *local, *tmp; + + spin_lock(&llcp_devices_lock); + list_for_each_entry_safe(local, tmp, &llcp_devices, list) + if (local->dev == dev) { + list_del(&local->list); + spin_unlock(&llcp_devices_lock); + return local; + } + spin_unlock(&llcp_devices_lock); + + pr_warn("Shutting down device not found\n"); return NULL; } @@ -610,12 +632,15 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) *general_bytes_len = local->gb_len; + nfc_llcp_local_put(local); + return local->gb; } int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) { struct nfc_llcp_local *local; + int err; if (gb_len < 3 || gb_len > NFC_MAX_GT_LEN) return -EINVAL; @@ -632,12 +657,16 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) if (memcmp(local->remote_gb, llcp_magic, 3)) { pr_err("MAC does not support LLCP\n"); - return -EINVAL; + err = -EINVAL; + goto out; } - return nfc_llcp_parse_gb_tlv(local, + err = nfc_llcp_parse_gb_tlv(local, &local->remote_gb[3], local->remote_gb_len - 3); +out: + nfc_llcp_local_put(local); + return err; } static u8 nfc_llcp_dsap(struct sk_buff *pdu) @@ -1523,6 +1552,8 @@ int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb) __nfc_llcp_recv(local, skb); + nfc_llcp_local_put(local); + return 0; } @@ -1539,6 +1570,8 @@ void nfc_llcp_mac_is_down(struct nfc_dev *dev) /* Close and purge all existing sockets */ nfc_llcp_socket_release(local, true, 0); + + nfc_llcp_local_put(local); } void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, @@ -1564,6 +1597,8 @@ void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, mod_timer(&local->link_timer, jiffies + msecs_to_jiffies(local->remote_lto)); } + + nfc_llcp_local_put(local); } int nfc_llcp_register_device(struct nfc_dev *ndev) @@ -1614,7 +1649,7 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) void nfc_llcp_unregister_device(struct nfc_dev *dev) { - struct nfc_llcp_local *local = nfc_llcp_find_local(dev); + struct nfc_llcp_local *local = nfc_llcp_remove_local(dev); if (local == NULL) { pr_debug("No such device\n"); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 0b93a17b9f11..d3bce424eda8 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -99,7 +99,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; llcp_sock->service_name_len = min_t(unsigned int, llcp_addr.service_name_len, @@ -181,7 +181,7 @@ static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr, } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; nfc_llcp_sock_link(&local->raw_sockets, sk); @@ -698,24 +698,24 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, if (dev->dep_link_up == false) { ret = -ENOLINK; device_unlock(&dev->dev); - goto put_dev; + goto sock_llcp_put_local; } device_unlock(&dev->dev); if (local->rf_mode == NFC_RF_INITIATOR && addr->target_idx != local->target_idx) { ret = -ENOLINK; - goto put_dev; + goto sock_llcp_put_local; } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { nfc_llcp_local_put(llcp_sock->local); llcp_sock->local = NULL; ret = -ENOMEM; - goto put_dev; + goto sock_llcp_nullify; } llcp_sock->reserved_ssap = llcp_sock->ssap; @@ -760,9 +760,13 @@ sock_unlink: sock_llcp_release: nfc_llcp_put_ssap(local, llcp_sock->ssap); - nfc_llcp_local_put(llcp_sock->local); + +sock_llcp_nullify: llcp_sock->local = NULL; +sock_llcp_put_local: + nfc_llcp_local_put(local); + put_dev: nfc_put_device(dev); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index e0e116865511..1c5b3ce1e8b1 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1039,11 +1039,14 @@ static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { rc = -ENOMEM; - goto exit; + goto put_local; } rc = nfc_genl_send_params(msg, local, info->snd_portid, info->snd_seq); +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); @@ -1105,7 +1108,7 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NFC_ATTR_LLC_PARAM_LTO]) { if (dev->dep_link_up) { rc = -EINPROGRESS; - goto exit; + goto put_local; } local->lto = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_LTO]); @@ -1117,6 +1120,9 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) local->miux = cpu_to_be16(miux); +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); @@ -1172,7 +1178,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) if (rc != 0) { rc = -EINVAL; - goto exit; + goto put_local; } if (!sdp_attrs[NFC_SDP_ATTR_URI]) @@ -1191,7 +1197,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) sdreq = nfc_llcp_build_sdreq_tlv(tid, uri, uri_len); if (sdreq == NULL) { rc = -ENOMEM; - goto exit; + goto put_local; } tlvs_len += sdreq->tlv_len; @@ -1201,10 +1207,14 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) if (hlist_empty(&sdreq_list)) { rc = -EINVAL; - goto exit; + goto put_local; } rc = nfc_llcp_send_snl_sdreq(local, &sdreq_list, tlvs_len); + +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index 889fefd64e56..bf53e8006208 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -52,6 +52,7 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len); u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len); int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); +int nfc_llcp_local_put(struct nfc_llcp_local *local); int __init nfc_llcp_init(void); void nfc_llcp_exit(void); void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp); From a96eb7c2caeb1d59a5599df67aa98e5641879832 Mon Sep 17 00:00:00 2001 From: Amit Pundir Date: Thu, 31 Aug 2023 12:37:25 +0530 Subject: [PATCH 4321/4345] ANDROID: arm64: dts: qcom: sdm845-db845c: Do not point MDSS to the boot splash memory region MSM display subsystem is not happy with this new reserved memory-region assigned to it and DB845c is running into hard crashes on boot. Bug: 146449535 Fixes: a8b58500cb6b ("FROMGIT: arm64: dts: qcom: sdm845-db845c: Mark cont splash memory region as reserved") Signed-off-by: Amit Pundir Change-Id: Ie5c2cf0cf02e941c0bd1ba653277c89db0afd90a --- arch/arm64/boot/dts/qcom/sdm845-db845c.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index 67cd869de352..75731fe9fd7a 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -490,7 +490,6 @@ }; &mdss { - memory-region = <&cont_splash_mem>; status = "okay"; }; From 216e24b08c743f918428bf34dcb289b1a26fc5c8 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 23 May 2023 11:58:22 +0800 Subject: [PATCH 4322/4345] BACKPORT: f2fs: don't reset unchangable mount option in f2fs_remount() syzbot reports a bug as below: general protection fault, probably for non-canonical address 0xdffffc0000000009: 0000 [#1] PREEMPT SMP KASAN RIP: 0010:__lock_acquire+0x69/0x2000 kernel/locking/lockdep.c:4942 Call Trace: lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5691 __raw_write_lock include/linux/rwlock_api_smp.h:209 [inline] _raw_write_lock+0x2e/0x40 kernel/locking/spinlock.c:300 __drop_extent_tree+0x3ac/0x660 fs/f2fs/extent_cache.c:1100 f2fs_drop_extent_tree+0x17/0x30 fs/f2fs/extent_cache.c:1116 f2fs_insert_range+0x2d5/0x3c0 fs/f2fs/file.c:1664 f2fs_fallocate+0x4e4/0x6d0 fs/f2fs/file.c:1838 vfs_fallocate+0x54b/0x6b0 fs/open.c:324 ksys_fallocate fs/open.c:347 [inline] __do_sys_fallocate fs/open.c:355 [inline] __se_sys_fallocate fs/open.c:353 [inline] __x64_sys_fallocate+0xbd/0x100 fs/open.c:353 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The root cause is race condition as below: - since it tries to remount rw filesystem, so that do_remount won't call sb_prepare_remount_readonly to block fallocate, there may be race condition in between remount and fallocate. - in f2fs_remount(), default_options() will reset mount option to default one, and then update it based on result of parse_options(), so there is a hole which race condition can happen. Thread A Thread B - f2fs_fill_super - parse_options - clear_opt(READ_EXTENT_CACHE) - f2fs_remount - default_options - set_opt(READ_EXTENT_CACHE) - f2fs_fallocate - f2fs_insert_range - f2fs_drop_extent_tree - __drop_extent_tree - __may_extent_tree - test_opt(READ_EXTENT_CACHE) return true - write_lock(&et->lock) access NULL pointer - parse_options - clear_opt(READ_EXTENT_CACHE) Bug: 295824459 Cc: Reported-by: syzbot+d015b6c2fbb5c383bf08@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/20230522124203.3838360-1-chao@kernel.org Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim (cherry picked from commit 458c15dfbce62c35fefd9ca637b20a051309c9f1) Change-Id: I933beab715c85836b98e8b4cb85223000714176f --- fs/f2fs/super.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index f4c582f396f2..33b5e07c4997 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1927,9 +1927,17 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) return 0; } -static void default_options(struct f2fs_sb_info *sbi) +static void default_options(struct f2fs_sb_info *sbi, bool remount) { /* init some FS parameters */ + if (!remount) { + set_opt(sbi, READ_EXTENT_CACHE); + clear_opt(sbi, DISABLE_CHECKPOINT); + + if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) + set_opt(sbi, DISCARD); + } + if (f2fs_sb_has_readonly(sbi)) F2FS_OPTION(sbi).active_logs = NR_CURSEG_RO_TYPE; else @@ -1953,14 +1961,11 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, INLINE_XATTR); set_opt(sbi, INLINE_DATA); set_opt(sbi, INLINE_DENTRY); - set_opt(sbi, READ_EXTENT_CACHE); set_opt(sbi, NOHEAP); - clear_opt(sbi, DISABLE_CHECKPOINT); set_opt(sbi, MERGE_CHECKPOINT); F2FS_OPTION(sbi).unusable_cap = 0; sbi->sb->s_flags |= SB_LAZYTIME; set_opt(sbi, FLUSH_MERGE); - set_opt(sbi, DISCARD); if (f2fs_sb_has_blkzoned(sbi)) F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; else @@ -2124,7 +2129,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) clear_sbi_flag(sbi, SBI_NEED_SB_WRITE); } - default_options(sbi); + default_options(sbi, true); /* parse mount options */ err = parse_options(sb, data, true); @@ -3891,7 +3896,7 @@ try_onemore: sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid, sizeof(raw_super->uuid)); - default_options(sbi); + default_options(sbi, false); /* parse mount options */ options = kstrdup((const char *)data, GFP_KERNEL); if (data && !options) { From e95427763fcb4cc717fff219ea4f27f1c21be013 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Sat, 22 Apr 2023 12:56:11 -0300 Subject: [PATCH 4323/4345] UPSTREAM: net/sched: sch_qfq: refactor parsing of netlink parameters [ Upstream commit 25369891fcef373540f8b4e0b3bccf77a04490d5 ] Two parameters can be transformed into netlink policies and validated while parsing the netlink message. Bug: 2675079 Reviewed-by: Simon Horman Acked-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Signed-off-by: David S. Miller Stable-dep-of: 3e337087c3b5 ("net/sched: sch_qfq: account for stab overhead in qfq_enqueue") Signed-off-by: Sasha Levin (cherry picked from commit 8e0326cbc4d59a99f307493fb4c7c428bff03373) Signed-off-by: Lee Jones Change-Id: Ia7e9430b223b9c0149b7be4d9c57735d427c72d5 --- net/sched/sch_qfq.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index cad7deacf60a..975e444f2d82 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -113,6 +113,7 @@ #define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ +#define QFQ_MAX_LMAX (1UL << QFQ_MTU_SHIFT) #define QFQ_MAX_AGG_CLASSES 8 /* max num classes per aggregate allowed */ @@ -214,9 +215,14 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) return container_of(clc, struct qfq_class, common); } +static struct netlink_range_validation lmax_range = { + .min = QFQ_MIN_LMAX, + .max = QFQ_MAX_LMAX, +}; + static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { - [TCA_QFQ_WEIGHT] = { .type = NLA_U32 }, - [TCA_QFQ_LMAX] = { .type = NLA_U32 }, + [TCA_QFQ_WEIGHT] = NLA_POLICY_RANGE(NLA_U32, 1, QFQ_MAX_WEIGHT), + [TCA_QFQ_LMAX] = NLA_POLICY_FULL_RANGE(NLA_U32, &lmax_range), }; /* @@ -408,17 +414,13 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } err = nla_parse_nested_deprecated(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], - qfq_policy, NULL); + qfq_policy, extack); if (err < 0) return err; - if (tb[TCA_QFQ_WEIGHT]) { + if (tb[TCA_QFQ_WEIGHT]) weight = nla_get_u32(tb[TCA_QFQ_WEIGHT]); - if (!weight || weight > (1UL << QFQ_MAX_WSHIFT)) { - pr_notice("qfq: invalid weight %u\n", weight); - return -EINVAL; - } - } else + else weight = 1; if (tb[TCA_QFQ_LMAX]) @@ -426,11 +428,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, else lmax = psched_mtu(qdisc_dev(sch)); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); - return -EINVAL; - } - inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; From 3e9ba88034b83ba24bdd32cc7742fc3eccbb3576 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 9 Jan 2023 11:49:20 +0800 Subject: [PATCH 4324/4345] BACKPORT: f2fs: fix to do sanity check on extent cache correctly In do_read_inode(), sanity_check_inode() should be called after f2fs_init_read_extent_tree(), fix it. Fixes: 72840cccc0a1 ("f2fs: allocate the extent_cache by default") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim (cherry picked from commit d48a7b3a72f121655d95b5157c32c7d555e44c05) [Lee: Removed call to f2fs_handle_error() - not in original hunk] Signed-off-by: Lee Jones Change-Id: I1a8695fc5eda522e010468093ad78ffebd7dada5 --- fs/f2fs/inode.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 5bf4f1cccd71..a88c8e737ef7 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -401,11 +401,6 @@ static int do_read_inode(struct inode *inode) fi->i_inline_xattr_size = 0; } - if (!sanity_check_inode(inode, node_page)) { - f2fs_put_page(node_page, 1); - return -EFSCORRUPTED; - } - /* check data exist */ if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode)) __recover_inline_status(inode, node_page); @@ -472,6 +467,11 @@ static int do_read_inode(struct inode *inode) f2fs_init_read_extent_tree(inode, node_page); f2fs_init_age_extent_tree(inode); + if (!sanity_check_inode(inode, node_page)) { + f2fs_put_page(node_page, 1); + return -EFSCORRUPTED; + } + f2fs_put_page(node_page, 1); stat_inc_inline_xattr(inode); From 1e1986dd44253d1ae1b6a9fd46eec4e2176ec361 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 31 Jan 2023 22:47:00 +0800 Subject: [PATCH 4325/4345] UPSTREAM: f2fs: fix to update age extent correctly during truncation nr_free may be less than len, we should update age extent cache w/ range [fofs, len] rather than [fofs, nr_free]. Bug: 254441685 Fixes: 71644dff4811 ("f2fs: add block_age-based extent cache") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim (cherry picked from commit 8c0ed062ce27f6b7f0a568cb241e2b4dd2d9e6a6) Signed-off-by: Lee Jones Change-Id: I86dccb39f6e844b180046dc8560e3904700fb4e1 --- fs/f2fs/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 720ab6582cb6..ce1c56808076 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -608,7 +608,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + ofs; f2fs_update_read_extent_cache_range(dn, fofs, 0, len); - f2fs_update_age_extent_cache_range(dn, fofs, nr_free); + f2fs_update_age_extent_cache_range(dn, fofs, len); dec_valid_block_count(sbi, dn->inode, nr_free); } dn->ofs_in_node = ofs; From 72a7bbb4a32659b38e30bc10317852eb234c0a21 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 31 Jan 2023 22:47:01 +0800 Subject: [PATCH 4326/4345] UPSTREAM: f2fs: fix to update age extent in f2fs_do_zero_range() We should update age extent in f2fs_do_zero_range() like we did in f2fs_truncate_data_blocks_range(). Bug: 254441685 Fixes: 71644dff4811 ("f2fs: add block_age-based extent cache") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim (cherry picked from commit a84153f939808102dfa10904aa0f743e734a3e1d) Signed-off-by: Lee Jones Change-Id: I775351141745194b08c5f149be36cd275ab84e4c --- fs/f2fs/file.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ce1c56808076..74ec317cbb7c 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1432,6 +1432,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, } f2fs_update_read_extent_cache_range(dn, start, 0, index - start); + f2fs_update_age_extent_cache_range(dn, start, index - start); return ret; } From b155bf30863f16c0e7d32a5eace3c9dc298bf7d8 Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Thu, 16 Feb 2023 11:15:15 +0800 Subject: [PATCH 4327/4345] UPSTREAM: usb: typec: tcpm: fix warning when handle discover_identity message Since both source and sink device can send discover_identity message in PD3, kernel may dump below warning: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 169 at drivers/usb/typec/tcpm/tcpm.c:1446 tcpm_queue_vdm+0xe0/0xf0 Modules linked in: CPU: 0 PID: 169 Comm: 1-0050 Not tainted 6.1.1-00038-g6a3c36cf1da2-dirty #567 Hardware name: NXP i.MX8MPlus EVK board (DT) pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : tcpm_queue_vdm+0xe0/0xf0 lr : tcpm_queue_vdm+0x2c/0xf0 sp : ffff80000c19bcd0 x29: ffff80000c19bcd0 x28: 0000000000000001 x27: ffff0000d11c8ab8 x26: ffff0000d11cc000 x25: 0000000000000000 x24: 00000000ff008081 x23: 0000000000000001 x22: 00000000ff00a081 x21: ffff80000c19bdbc x20: 0000000000000000 x19: ffff0000d11c8080 x18: ffffffffffffffff x17: 0000000000000000 x16: 0000000000000000 x15: ffff0000d716f580 x14: 0000000000000001 x13: ffff0000d716f507 x12: 0000000000000001 x11: 0000000000000000 x10: 0000000000000020 x9 : 00000000000ee098 x8 : 00000000ffffffff x7 : 000000000000001c x6 : ffff0000d716f580 x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000 x2 : ffff80000c19bdbc x1 : 00000000ff00a081 x0 : 0000000000000004 Call trace: tcpm_queue_vdm+0xe0/0xf0 tcpm_pd_rx_handler+0x340/0x1ab0 kthread_worker_fn+0xcc/0x18c kthread+0x10c/0x110 ret_from_fork+0x10/0x20 ---[ end trace 0000000000000000 ]--- Below sequences may trigger this warning: tcpm_send_discover_work(work) tcpm_send_vdm(port, USB_SID_PD, CMD_DISCOVER_IDENT, NULL, 0); tcpm_queue_vdm(port, header, data, count); port->vdm_state = VDM_STATE_READY; vdm_state_machine_work(work); <-- received discover_identity from partner vdm_run_state_machine(port); port->vdm_state = VDM_STATE_SEND_MESSAGE; mod_vdm_delayed_work(port, x); tcpm_pd_rx_handler(work); tcpm_pd_data_request(port, msg); tcpm_handle_vdm_request(port, msg->payload, cnt); tcpm_queue_vdm(port, response[0], &response[1], rlen - 1); --> WARN_ON(port->vdm_state > VDM_STATE_DONE); For this case, the state machine could still send out discover identity message later if we skip current discover_identity message. So we should handle the received message firstly and override the pending discover_identity message without warning in this case. Then, a delayed send_discover work will send discover_identity message again. Bug: 254441685 Fixes: e00943e91678 ("usb: typec: tcpm: PD3.0 sinks can send Discover Identity even in device mode") cc: Signed-off-by: Xu Yang Reviewed-by: Guenter Roeck Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230216031515.4151117-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit abfc4fa28f0160df61c7149567da4f6494dfb488) Signed-off-by: Lee Jones Change-Id: I6989a29a09a10393b97bc5a5d5e3c055bb397e05 --- drivers/usb/typec/tcpm/tcpm.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 0849d4b5fdff..8dd7c2e50545 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1444,10 +1444,18 @@ static int tcpm_ams_start(struct tcpm_port *port, enum tcpm_ams ams) static void tcpm_queue_vdm(struct tcpm_port *port, const u32 header, const u32 *data, int cnt) { + u32 vdo_hdr = port->vdo_data[0]; + WARN_ON(!mutex_is_locked(&port->lock)); - /* Make sure we are not still processing a previous VDM packet */ - WARN_ON(port->vdm_state > VDM_STATE_DONE); + /* If is sending discover_identity, handle received message first */ + if (PD_VDO_SVDM(vdo_hdr) && PD_VDO_CMD(vdo_hdr) == CMD_DISCOVER_IDENT) { + port->send_discover = true; + mod_send_discover_delayed_work(port, SEND_DISCOVER_RETRY_MS); + } else { + /* Make sure we are not still processing a previous VDM packet */ + WARN_ON(port->vdm_state > VDM_STATE_DONE); + } port->vdo_count = cnt + 1; port->vdo_data[0] = header; @@ -1964,11 +1972,13 @@ static void vdm_run_state_machine(struct tcpm_port *port) switch (PD_VDO_CMD(vdo_hdr)) { case CMD_DISCOVER_IDENT: res = tcpm_ams_start(port, DISCOVER_IDENTITY); - if (res == 0) + if (res == 0) { port->send_discover = false; - else if (res == -EAGAIN) + } else if (res == -EAGAIN) { + port->vdo_data[0] = 0; mod_send_discover_delayed_work(port, SEND_DISCOVER_RETRY_MS); + } break; case CMD_DISCOVER_SVID: res = tcpm_ams_start(port, DISCOVER_SVIDS); @@ -2051,6 +2061,7 @@ static void vdm_run_state_machine(struct tcpm_port *port) unsigned long timeout; port->vdm_retries = 0; + port->vdo_data[0] = 0; port->vdm_state = VDM_STATE_BUSY; timeout = vdm_ready_timeout(vdo_hdr); mod_vdm_delayed_work(port, timeout); From b3bad92280afedb37722d53046824c407fdd77a1 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 21 Mar 2023 10:45:30 +0000 Subject: [PATCH 4328/4345] UPSTREAM: coresight: etm4x: Do not access TRCIDR1 for identification CoreSight ETM4x architecture clearly provides ways to identify a device via registers in the "Management" class, TRCDEVARCH and TRCDEVTYPE. These registers can be accessed without the Trace domain being powered on. We additionally added TRCIDR1 as fallback in order to cover for any ETMs that may not have implemented TRCDEVARCH. So far, nobody has reported hitting a WARNING we placed to catch such systems. Also, more importantly it is problematic to access TRCIDR1, which is a "Trace" register via MMIO access, without clearing the OSLK. But we cannot mess with the OSLK until we know for sure that this is an ETMv4 device. Thus, this kind of creates a chicken and egg problem unnecessarily for systems "which are compliant" to the ETMv4 architecture. Let us remove the TRCIDR1 fall back check and rely only on TRCDEVARCH. Bug: 254441685 Fixes: 8b94db1edaee ("coresight: etm4x: Use TRCDEVARCH for component discovery") Cc: stable@vger.kernel.org Reported-by: Steve Clevenger Link: https://lore.kernel.org/all/143540e5623d4c7393d24833f2b80600d8d745d2.1677881753.git.scclevenger@os.amperecomputing.com/ Cc: Mike Leach Cc: James Clark Reviewed-by: Mike Leach Reviewed-by: Anshuman Khandual Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230321104530.1547136-1-suzuki.poulose@arm.com (cherry picked from commit 735e7b30a53a1679c050cddb73f5e5316105d2e3) Signed-off-by: Lee Jones Change-Id: Ic4bdaf1f2669951437ef8e540c8a61b6a96196ab --- .../coresight/coresight-etm4x-core.c | 22 ++++++++----------- drivers/hwtracing/coresight/coresight-etm4x.h | 20 +++++------------ 2 files changed, 15 insertions(+), 27 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 12bbb5169440..146c8934dcf7 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -960,25 +960,21 @@ static bool etm4_init_iomem_access(struct etmv4_drvdata *drvdata, struct csdev_access *csa) { u32 devarch = readl_relaxed(drvdata->base + TRCDEVARCH); - u32 idr1 = readl_relaxed(drvdata->base + TRCIDR1); /* * All ETMs must implement TRCDEVARCH to indicate that - * the component is an ETMv4. To support any broken - * implementations we fall back to TRCIDR1 check, which - * is not really reliable. + * the component is an ETMv4. Even though TRCIDR1 also + * contains the information, it is part of the "Trace" + * register and must be accessed with the OSLK cleared, + * with MMIO. But we cannot touch the OSLK until we are + * sure this is an ETM. So rely only on the TRCDEVARCH. */ - if ((devarch & ETM_DEVARCH_ID_MASK) == ETM_DEVARCH_ETMv4x_ARCH) { - drvdata->arch = etm_devarch_to_arch(devarch); - } else { - pr_warn("CPU%d: ETM4x incompatible TRCDEVARCH: %x, falling back to TRCIDR1\n", - smp_processor_id(), devarch); - - if (ETM_TRCIDR1_ARCH_MAJOR(idr1) != ETM_TRCIDR1_ARCH_ETMv4) - return false; - drvdata->arch = etm_trcidr_to_arch(idr1); + if ((devarch & ETM_DEVARCH_ID_MASK) != ETM_DEVARCH_ETMv4x_ARCH) { + pr_warn_once("TRCDEVARCH doesn't match ETMv4 architecture\n"); + return false; } + drvdata->arch = etm_devarch_to_arch(devarch); *csa = CSDEV_ACCESS_IOMEM(drvdata->base); return true; } diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 3c4d69b096ca..1ac4a0632a4b 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -668,14 +668,12 @@ * TRCDEVARCH - CoreSight architected register * - Bits[15:12] - Major version * - Bits[19:16] - Minor version - * TRCIDR1 - ETM architected register - * - Bits[11:8] - Major version - * - Bits[7:4] - Minor version - * We must rely on TRCDEVARCH for the version information, - * however we don't want to break the support for potential - * old implementations which might not implement it. Thus - * we fall back to TRCIDR1 if TRCDEVARCH is not implemented - * for memory mapped components. + * + * We must rely only on TRCDEVARCH for the version information. Even though, + * TRCIDR1 also provides the architecture version, it is a "Trace" register + * and as such must be accessed only with Trace power domain ON. This may + * not be available at probe time. + * * Now to make certain decisions easier based on the version * we use an internal representation of the version in the * driver, as follows : @@ -701,12 +699,6 @@ static inline u8 etm_devarch_to_arch(u32 devarch) ETM_DEVARCH_REVISION(devarch)); } -static inline u8 etm_trcidr_to_arch(u32 trcidr1) -{ - return ETM_ARCH_VERSION(ETM_TRCIDR1_ARCH_MAJOR(trcidr1), - ETM_TRCIDR1_ARCH_MINOR(trcidr1)); -} - enum etm_impdef_type { ETM4_IMPDEF_HISI_CORE_COMMIT, ETM4_IMPDEF_FEATURE_MAX, From bc78acae08cd3fc2f7c954f13dd0db6fc4e248d5 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 16 Mar 2023 23:47:04 +0100 Subject: [PATCH 4329/4345] UPSTREAM: kfence: avoid passing -g for test Nathan reported that when building with GNU as and a version of clang that defaults to DWARF5: $ make -skj"$(nproc)" ARCH=riscv CROSS_COMPILE=riscv64-linux-gnu- \ LLVM=1 LLVM_IAS=0 O=build \ mrproper allmodconfig mm/kfence/kfence_test.o /tmp/kfence_test-08a0a0.s: Assembler messages: /tmp/kfence_test-08a0a0.s:14627: Error: non-constant .uleb128 is not supported /tmp/kfence_test-08a0a0.s:14628: Error: non-constant .uleb128 is not supported /tmp/kfence_test-08a0a0.s:14632: Error: non-constant .uleb128 is not supported /tmp/kfence_test-08a0a0.s:14633: Error: non-constant .uleb128 is not supported /tmp/kfence_test-08a0a0.s:14639: Error: non-constant .uleb128 is not supported ... This is because `-g` defaults to the compiler debug info default. If the assembler does not support some of the directives used, the above errors occur. To fix, remove the explicit passing of `-g`. All the test wants is that stack traces print valid function names, and debug info is not required for that. (I currently cannot recall why I added the explicit `-g`.) Bug: 254441685 Link: https://lkml.kernel.org/r/20230316224705.709984-1-elver@google.com Fixes: bc8fbc5f305a ("kfence: add test suite") Signed-off-by: Marco Elver Reported-by: Nathan Chancellor Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Signed-off-by: Andrew Morton (cherry picked from commit 2e08ca1802441224f5b7cc6bffbb687f7406de95) Signed-off-by: Lee Jones Change-Id: I79d57b803087295e1f07087a1bb855a6d6bce108 --- mm/kfence/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kfence/Makefile b/mm/kfence/Makefile index 6872cd5e5390..cb2bcf773083 100644 --- a/mm/kfence/Makefile +++ b/mm/kfence/Makefile @@ -2,5 +2,5 @@ obj-$(CONFIG_KFENCE) := core.o report.o -CFLAGS_kfence_test.o := -g -fno-omit-frame-pointer -fno-optimize-sibling-calls +CFLAGS_kfence_test.o := -fno-omit-frame-pointer -fno-optimize-sibling-calls obj-$(CONFIG_KFENCE_KUNIT_TEST) += kfence_test.o From 6388400ba5b61408afbc7528f7f2e7760fb4fe07 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 15 May 2023 16:40:59 +0300 Subject: [PATCH 4330/4345] UPSTREAM: xhci: Fix incorrect tracking of free space on transfer rings This incorrect tracking caused unnecessary ring expansion in some usecases which over days of use consume a lot of memory. xhci driver tries to keep track of free transfer blocks (TRBs) on the ring buffer, but failed to add back some cancelled transfers that were turned into no-op operations instead of just moving past them. This can happen if there are several queued pending transfers which then are cancelled in reverse order. Solve this by counting the numer of steps we move the dequeue pointer once we complete a transfer, and add it to the number of free trbs instead of just adding the trb number of the current transfer. This way we ensure we count the no-op trbs on the way as well. Bug: 254441685 Fixes: 55f6153d8cc8 ("xhci: remove extra loop in interrupt context") Cc: stable@vger.kernel.org Reported-by: Miller Hunter Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217242 Tested-by: Miller Hunter Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230515134059.161110-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit fe82f16aafdaf8002281d3b9524291d4a4a28460) Signed-off-by: Lee Jones Change-Id: Iba6c2cfad83029fcd567b5064f8ce80ccda0a701 --- drivers/usb/host/xhci-ring.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index b4efe3e6d88b..1df649cc611b 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -277,6 +277,26 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring, trace_xhci_inc_enq(ring); } +static int xhci_num_trbs_to(struct xhci_segment *start_seg, union xhci_trb *start, + struct xhci_segment *end_seg, union xhci_trb *end, + unsigned int num_segs) +{ + union xhci_trb *last_on_seg; + int num = 0; + int i = 0; + + do { + if (start_seg == end_seg && end >= start) + return num + (end - start); + last_on_seg = &start_seg->trbs[TRBS_PER_SEGMENT - 1]; + num += last_on_seg - start; + start_seg = start_seg->next; + start = start_seg->trbs; + } while (i++ <= num_segs); + + return -EINVAL; +} + /* * Check to see if there's room to enqueue num_trbs on the ring and make sure * enqueue pointer will not advance into dequeue segment. See rules above. @@ -2209,6 +2229,7 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, u32 trb_comp_code) { struct xhci_ep_ctx *ep_ctx; + int trbs_freed; ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); @@ -2280,9 +2301,15 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, } /* Update ring dequeue pointer */ + trbs_freed = xhci_num_trbs_to(ep_ring->deq_seg, ep_ring->dequeue, + td->last_trb_seg, td->last_trb, + ep_ring->num_segs); + if (trbs_freed < 0) + xhci_dbg(xhci, "Failed to count freed trbs at TD finish\n"); + else + ep_ring->num_trbs_free += trbs_freed; ep_ring->dequeue = td->last_trb; ep_ring->deq_seg = td->last_trb_seg; - ep_ring->num_trbs_free += td->num_trbs - 1; inc_deq(xhci, ep_ring); return xhci_td_cleanup(xhci, td, ep_ring, td->status); From 37d958fa8871b14db29738088a29b16c40f05ba1 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 7 Jun 2023 12:05:40 +0200 Subject: [PATCH 4331/4345] UPSTREAM: USB: dwc3: fix use-after-free on core driver unbind Some dwc3 glue drivers are currently accessing the driver data of the child core device directly, which is clearly a bad idea as the child may not have probed yet or may have been unbound from its driver. As a workaround until the glue drivers have been fixed, clear the driver data pointer before allowing the glue parent device to runtime suspend to prevent its driver from accessing data that has been freed during unbind. Bug: 254441685 Fixes: 6dd2565989b4 ("usb: dwc3: add imx8mp dwc3 glue layer driver") Fixes: 6895ea55c385 ("usb: dwc3: qcom: Configure wakeup interrupts during suspend") Cc: stable@vger.kernel.org # 5.12 Cc: Li Jun Cc: Sandeep Maheswaram Cc: Krishna Kurapati Signed-off-by: Johan Hovold Acked-by: Thinh Nguyen Reviewed-by: Manivannan Sadhasivam Message-ID: <20230607100540.31045-3-johan+linaro@kernel.org> Signed-off-by: Greg Kroah-Hartman (cherry picked from commit e3dbb657571509044be15184a13134fa7c1fdca1) Signed-off-by: Lee Jones Change-Id: I9c546e159867e0a9271c56d8340daa1506436855 --- drivers/usb/dwc3/core.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 0d76648ad3a6..2f323826dd99 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1720,6 +1720,11 @@ static int dwc3_remove(struct platform_device *pdev) pm_runtime_allow(&pdev->dev); pm_runtime_disable(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); + /* + * HACK: Clear the driver data, which is currently accessed by parent + * glue drivers, before allowing the parent to suspend. + */ + platform_set_drvdata(pdev, NULL); pm_runtime_set_suspended(&pdev->dev); dwc3_free_event_buffers(dwc); From 1a6995cf14b2c5c9cf0300fe2ae565124fecaad2 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 21 Aug 2023 10:55:05 -0700 Subject: [PATCH 4332/4345] UPSTREAM: af_unix: Fix null-ptr-deref in unix_stream_sendpage(). Bing-Jhong Billy Jheng reported null-ptr-deref in unix_stream_sendpage() with detailed analysis and a nice repro. unix_stream_sendpage() tries to add data to the last skb in the peer's recv queue without locking the queue. If the peer's FD is passed to another socket and the socket's FD is passed to the peer, there is a loop between them. If we close both sockets without receiving FD, the sockets will be cleaned up by garbage collection. The garbage collection iterates such sockets and unlinks skb with FD from the socket's receive queue under the queue's lock. So, there is a race where unix_stream_sendpage() could access an skb locklessly that is being released by garbage collection, resulting in use-after-free. To avoid the issue, unix_stream_sendpage() must lock the peer's recv queue. Note the issue does not exist in 6.5+ thanks to the recent sendpage() refactoring. This patch is originally written by Linus Torvalds. BUG: unable to handle page fault for address: ffff988004dd6870 PF: supervisor read access in kernel mode PF: error_code(0x0000) - not-present page PGD 0 P4D 0 PREEMPT SMP PTI CPU: 4 PID: 297 Comm: garbage_uaf Not tainted 6.1.46 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:kmem_cache_alloc_node+0xa2/0x1e0 Code: c0 0f 84 32 01 00 00 41 83 fd ff 74 10 48 8b 00 48 c1 e8 3a 41 39 c5 0f 85 1c 01 00 00 41 8b 44 24 28 49 8b 3c 24 48 8d 4a 40 <49> 8b 1c 06 4c 89 f0 65 48 0f c7 0f 0f 94 c0 84 c0 74 a1 41 8b 44 RSP: 0018:ffffc9000079fac0 EFLAGS: 00000246 RAX: 0000000000000070 RBX: 0000000000000005 RCX: 000000000001a284 RDX: 000000000001a244 RSI: 0000000000400cc0 RDI: 000000000002eee0 RBP: 0000000000400cc0 R08: 0000000000400cc0 R09: 0000000000000003 R10: 0000000000000001 R11: 0000000000000000 R12: ffff888003970f00 R13: 00000000ffffffff R14: ffff988004dd6800 R15: 00000000000000e8 FS: 00007f174d6f3600(0000) GS:ffff88807db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff988004dd6870 CR3: 00000000092be000 CR4: 00000000007506e0 PKRU: 55555554 Call Trace: ? __die_body.cold+0x1a/0x1f ? page_fault_oops+0xa9/0x1e0 ? fixup_exception+0x1d/0x310 ? exc_page_fault+0xa8/0x150 ? asm_exc_page_fault+0x22/0x30 ? kmem_cache_alloc_node+0xa2/0x1e0 ? __alloc_skb+0x16c/0x1e0 __alloc_skb+0x16c/0x1e0 alloc_skb_with_frags+0x48/0x1e0 sock_alloc_send_pskb+0x234/0x270 unix_stream_sendmsg+0x1f5/0x690 sock_sendmsg+0x5d/0x60 ____sys_sendmsg+0x210/0x260 ___sys_sendmsg+0x83/0xd0 ? kmem_cache_alloc+0xc6/0x1c0 ? avc_disable+0x20/0x20 ? percpu_counter_add_batch+0x53/0xc0 ? alloc_empty_file+0x5d/0xb0 ? alloc_file+0x91/0x170 ? alloc_file_pseudo+0x94/0x100 ? __fget_light+0x9f/0x120 __sys_sendmsg+0x54/0xa0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x69/0xd3 RIP: 0033:0x7f174d639a7d Code: 28 89 54 24 1c 48 89 74 24 10 89 7c 24 08 e8 8a c1 f4 ff 8b 54 24 1c 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 33 44 89 c7 48 89 44 24 08 e8 de c1 f4 ff 48 RSP: 002b:00007ffcb563ea50 EFLAGS: 00000293 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f174d639a7d RDX: 0000000000000000 RSI: 00007ffcb563eab0 RDI: 0000000000000007 RBP: 00007ffcb563eb10 R08: 0000000000000000 R09: 00000000ffffffff R10: 00000000004040a0 R11: 0000000000000293 R12: 00007ffcb563ec28 R13: 0000000000401398 R14: 0000000000403e00 R15: 00007f174d72c000 Bug: 299922588 Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support") Reported-by: Bing-Jhong Billy Jheng Reviewed-by: Bing-Jhong Billy Jheng Co-developed-by: Linus Torvalds Signed-off-by: Linus Torvalds Signed-off-by: Kuniyuki Iwashima Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 790c2f9d15b594350ae9bca7b236f2b1859de02c) Signed-off-by: Lee Jones Change-Id: Ied4a40e6ae0e594ef84f36287bc6194602935585 --- net/unix/af_unix.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ed25cb6b147c..70184051cf26 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2008,6 +2008,7 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, if (false) { alloc_skb: + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, @@ -2047,6 +2048,7 @@ alloc_skb: init_scm = false; } + spin_lock(&other->sk_receive_queue.lock); skb = skb_peek_tail(&other->sk_receive_queue); if (tail && tail == skb) { skb = newskb; @@ -2077,14 +2079,11 @@ alloc_skb: refcount_add(size, &sk->sk_wmem_alloc); if (newskb) { - err = unix_scm_to_skb(&scm, skb, false); - if (err) - goto err_state_unlock; - spin_lock(&other->sk_receive_queue.lock); + unix_scm_to_skb(&scm, skb, false); __skb_queue_tail(&other->sk_receive_queue, newskb); - spin_unlock(&other->sk_receive_queue.lock); } + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); From 88525fa7d909df70d4d447fbfbfe2cdf8aebfcb1 Mon Sep 17 00:00:00 2001 From: p-liuqi1 Date: Mon, 11 Sep 2023 14:34:32 +0800 Subject: [PATCH 4333/4345] ANDROID: GKI update xiaomi symbols list ABI DIFFERENCES HAVE BEEN DETECTED! 2 Added functions: [A] 'function int mmc_set_blocklen(mmc_card*, unsigned int)' [A] 'function unsigned long int nr_free_buffer_pages()' Bug: 299962441 Change-Id: Ic63dc8380ad39ba789efee8e7de63c56db66a085 Signed-off-by: p-liuqi1 --- android/abi_gki_aarch64.xml | 100 ++++++++++++++++++--------------- android/abi_gki_aarch64_xiaomi | 2 + 2 files changed, 57 insertions(+), 45 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 44a30600dc4e..607576e857cb 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -3297,8 +3297,8 @@ + - @@ -3691,6 +3691,7 @@ + @@ -3806,6 +3807,7 @@ + @@ -135039,12 +135041,12 @@ - - - - + + + + @@ -137001,6 +137003,11 @@ + + + + + @@ -137595,6 +137602,9 @@ + + + @@ -146291,21 +146301,21 @@ - - + + - - + + - - + + - - - + + + @@ -146313,36 +146323,36 @@ - - - + + + - - + + - - + + - - + + - - + + - - - - - + + + + + - - + + @@ -150657,8 +150667,8 @@ - - + + @@ -150678,12 +150688,12 @@ - - - - - - + + + + + + @@ -150705,8 +150715,8 @@ - - + + @@ -150733,9 +150743,9 @@ - - - + + + diff --git a/android/abi_gki_aarch64_xiaomi b/android/abi_gki_aarch64_xiaomi index 71ffa17ffb77..b3b2d86330fe 100644 --- a/android/abi_gki_aarch64_xiaomi +++ b/android/abi_gki_aarch64_xiaomi @@ -62,6 +62,8 @@ ufshcd_update_evt_hist utf16s_to_utf8s wait_for_completion_io_timeout + nr_free_buffer_pages + mmc_set_blocklen #required by mq-deadline module blk_mq_debugfs_rq_show From 9f68d2976a348570bbd01d1d444dfbf5679cd514 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Tue, 11 Jul 2023 18:01:02 -0300 Subject: [PATCH 4334/4345] UPSTREAM: net/sched: sch_qfq: account for stab overhead in qfq_enqueue [ Upstream commit 3e337087c3b5805fe0b8a46ba622a962880b5d64 ] Lion says: ------- In the QFQ scheduler a similar issue to CVE-2023-31436 persists. Consider the following code in net/sched/sch_qfq.c: static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb), gso_segs; // ... if (unlikely(cl->agg->lmax < len)) { pr_debug("qfq: increasing maxpkt from %u to %u for class %u", cl->agg->lmax, len, cl->common.classid); err = qfq_change_agg(sch, cl, cl->agg->class_weight, len); if (err) { cl->qstats.drops++; return qdisc_drop(skb, sch, to_free); } // ... } Similarly to CVE-2023-31436, "lmax" is increased without any bounds checks according to the packet length "len". Usually this would not impose a problem because packet sizes are naturally limited. This is however not the actual packet length, rather the "qdisc_pkt_len(skb)" which might apply size transformations according to "struct qdisc_size_table" as created by "qdisc_get_stab()" in net/sched/sch_api.c if the TCA_STAB option was set when modifying the qdisc. A user may choose virtually any size using such a table. As a result the same issue as in CVE-2023-31436 can occur, allowing heap out-of-bounds read / writes in the kmalloc-8192 cache. ------- We can create the issue with the following commands: tc qdisc add dev $DEV root handle 1: stab mtu 2048 tsize 512 mpu 0 \ overhead 999999999 linklayer ethernet qfq tc class add dev $DEV parent 1: classid 1:1 htb rate 6mbit burst 15k tc filter add dev $DEV parent 1: matchall classid 1:1 ping -I $DEV 1.1.1.2 This is caused by incorrectly assuming that qdisc_pkt_len() returns a length within the QFQ_MIN_LMAX < len < QFQ_MAX_LMAX. Bug: 292249631 Bug: 293987452 Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost") Reported-by: Lion Reviewed-by: Eric Dumazet Signed-off-by: Jamal Hadi Salim Signed-off-by: Pedro Tammela Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin (cherry picked from commit 8359ee85fd6dabc5c134ed69fb22faadd8a44071) Signed-off-by: Lee Jones Change-Id: I69bec7b092e980fe8e0946c26ed9b5ac7c57bf3d --- net/sched/sch_qfq.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 975e444f2d82..616d1798cfef 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -381,8 +381,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, u32 lmax) { struct qfq_sched *q = qdisc_priv(sch); - struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight); + struct qfq_aggregate *new_agg; + /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */ + if (lmax > QFQ_MAX_LMAX) + return -EINVAL; + + new_agg = qfq_find_agg(q, lmax, weight); if (new_agg == NULL) { /* create new aggregate */ new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC); if (new_agg == NULL) From 7ba85ae1038be0c11200d0b73f27d12d66f768f7 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Wed, 5 Jul 2023 18:05:35 -0300 Subject: [PATCH 4335/4345] UPSTREAM: netfilter: nf_tables: prevent OOB access in nft_byteorder_eval commit caf3ef7468f7534771b5c44cd8dbd6f7f87c2cbd upstream. When evaluating byteorder expressions with size 2, a union with 32-bit and 16-bit members is used. Since the 16-bit members are aligned to 32-bit, the array accesses will be out-of-bounds. It may lead to a stack-out-of-bounds access like the one below: [ 23.095215] ================================================================== [ 23.095625] BUG: KASAN: stack-out-of-bounds in nft_byteorder_eval+0x13c/0x320 [ 23.096020] Read of size 2 at addr ffffc90000007948 by task ping/115 [ 23.096358] [ 23.096456] CPU: 0 PID: 115 Comm: ping Not tainted 6.4.0+ #413 [ 23.096770] Call Trace: [ 23.096910] [ 23.097030] dump_stack_lvl+0x60/0xc0 [ 23.097218] print_report+0xcf/0x630 [ 23.097388] ? nft_byteorder_eval+0x13c/0x320 [ 23.097577] ? kasan_addr_to_slab+0xd/0xc0 [ 23.097760] ? nft_byteorder_eval+0x13c/0x320 [ 23.097949] kasan_report+0xc9/0x110 [ 23.098106] ? nft_byteorder_eval+0x13c/0x320 [ 23.098298] __asan_load2+0x83/0xd0 [ 23.098453] nft_byteorder_eval+0x13c/0x320 [ 23.098659] nft_do_chain+0x1c8/0xc50 [ 23.098852] ? __pfx_nft_do_chain+0x10/0x10 [ 23.099078] ? __kasan_check_read+0x11/0x20 [ 23.099295] ? __pfx___lock_acquire+0x10/0x10 [ 23.099535] ? __pfx___lock_acquire+0x10/0x10 [ 23.099745] ? __kasan_check_read+0x11/0x20 [ 23.099929] nft_do_chain_ipv4+0xfe/0x140 [ 23.100105] ? __pfx_nft_do_chain_ipv4+0x10/0x10 [ 23.100327] ? lock_release+0x204/0x400 [ 23.100515] ? nf_hook.constprop.0+0x340/0x550 [ 23.100779] nf_hook_slow+0x6c/0x100 [ 23.100977] ? __pfx_nft_do_chain_ipv4+0x10/0x10 [ 23.101223] nf_hook.constprop.0+0x334/0x550 [ 23.101443] ? __pfx_ip_local_deliver_finish+0x10/0x10 [ 23.101677] ? __pfx_nf_hook.constprop.0+0x10/0x10 [ 23.101882] ? __pfx_ip_rcv_finish+0x10/0x10 [ 23.102071] ? __pfx_ip_local_deliver_finish+0x10/0x10 [ 23.102291] ? rcu_read_lock_held+0x4b/0x70 [ 23.102481] ip_local_deliver+0xbb/0x110 [ 23.102665] ? __pfx_ip_rcv+0x10/0x10 [ 23.102839] ip_rcv+0x199/0x2a0 [ 23.102980] ? __pfx_ip_rcv+0x10/0x10 [ 23.103140] __netif_receive_skb_one_core+0x13e/0x150 [ 23.103362] ? __pfx___netif_receive_skb_one_core+0x10/0x10 [ 23.103647] ? mark_held_locks+0x48/0xa0 [ 23.103819] ? process_backlog+0x36c/0x380 [ 23.103999] __netif_receive_skb+0x23/0xc0 [ 23.104179] process_backlog+0x91/0x380 [ 23.104350] __napi_poll.constprop.0+0x66/0x360 [ 23.104589] ? net_rx_action+0x1cb/0x610 [ 23.104811] net_rx_action+0x33e/0x610 [ 23.105024] ? _raw_spin_unlock+0x23/0x50 [ 23.105257] ? __pfx_net_rx_action+0x10/0x10 [ 23.105485] ? mark_held_locks+0x48/0xa0 [ 23.105741] __do_softirq+0xfa/0x5ab [ 23.105956] ? __dev_queue_xmit+0x765/0x1c00 [ 23.106193] do_softirq.part.0+0x49/0xc0 [ 23.106423] [ 23.106547] [ 23.106670] __local_bh_enable_ip+0xf5/0x120 [ 23.106903] __dev_queue_xmit+0x789/0x1c00 [ 23.107131] ? __pfx___dev_queue_xmit+0x10/0x10 [ 23.107381] ? find_held_lock+0x8e/0xb0 [ 23.107585] ? lock_release+0x204/0x400 [ 23.107798] ? neigh_resolve_output+0x185/0x350 [ 23.108049] ? mark_held_locks+0x48/0xa0 [ 23.108265] ? neigh_resolve_output+0x185/0x350 [ 23.108514] neigh_resolve_output+0x246/0x350 [ 23.108753] ? neigh_resolve_output+0x246/0x350 [ 23.109003] ip_finish_output2+0x3c3/0x10b0 [ 23.109250] ? __pfx_ip_finish_output2+0x10/0x10 [ 23.109510] ? __pfx_nf_hook+0x10/0x10 [ 23.109732] __ip_finish_output+0x217/0x390 [ 23.109978] ip_finish_output+0x2f/0x130 [ 23.110207] ip_output+0xc9/0x170 [ 23.110404] ip_push_pending_frames+0x1a0/0x240 [ 23.110652] raw_sendmsg+0x102e/0x19e0 [ 23.110871] ? __pfx_raw_sendmsg+0x10/0x10 [ 23.111093] ? lock_release+0x204/0x400 [ 23.111304] ? __mod_lruvec_page_state+0x148/0x330 [ 23.111567] ? find_held_lock+0x8e/0xb0 [ 23.111777] ? find_held_lock+0x8e/0xb0 [ 23.111993] ? __rcu_read_unlock+0x7c/0x2f0 [ 23.112225] ? aa_sk_perm+0x18a/0x550 [ 23.112431] ? filemap_map_pages+0x4f1/0x900 [ 23.112665] ? __pfx_aa_sk_perm+0x10/0x10 [ 23.112880] ? find_held_lock+0x8e/0xb0 [ 23.113098] inet_sendmsg+0xa0/0xb0 [ 23.113297] ? inet_sendmsg+0xa0/0xb0 [ 23.113500] ? __pfx_inet_sendmsg+0x10/0x10 [ 23.113727] sock_sendmsg+0xf4/0x100 [ 23.113924] ? move_addr_to_kernel.part.0+0x4f/0xa0 [ 23.114190] __sys_sendto+0x1d4/0x290 [ 23.114391] ? __pfx___sys_sendto+0x10/0x10 [ 23.114621] ? __pfx_mark_lock.part.0+0x10/0x10 [ 23.114869] ? lock_release+0x204/0x400 [ 23.115076] ? find_held_lock+0x8e/0xb0 [ 23.115287] ? rcu_is_watching+0x23/0x60 [ 23.115503] ? __rseq_handle_notify_resume+0x6e2/0x860 [ 23.115778] ? __kasan_check_write+0x14/0x30 [ 23.116008] ? blkcg_maybe_throttle_current+0x8d/0x770 [ 23.116285] ? mark_held_locks+0x28/0xa0 [ 23.116503] ? do_syscall_64+0x37/0x90 [ 23.116713] __x64_sys_sendto+0x7f/0xb0 [ 23.116924] do_syscall_64+0x59/0x90 [ 23.117123] ? irqentry_exit_to_user_mode+0x25/0x30 [ 23.117387] ? irqentry_exit+0x77/0xb0 [ 23.117593] ? exc_page_fault+0x92/0x140 [ 23.117806] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 23.118081] RIP: 0033:0x7f744aee2bba [ 23.118282] Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 [ 23.119237] RSP: 002b:00007ffd04a7c9f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 23.119644] RAX: ffffffffffffffda RBX: 00007ffd04a7e0a0 RCX: 00007f744aee2bba [ 23.120023] RDX: 0000000000000040 RSI: 000056488e9e6300 RDI: 0000000000000003 [ 23.120413] RBP: 000056488e9e6300 R08: 00007ffd04a80320 R09: 0000000000000010 [ 23.120809] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040 [ 23.121219] R13: 00007ffd04a7dc38 R14: 00007ffd04a7ca00 R15: 00007ffd04a7e0a0 [ 23.121617] [ 23.121749] [ 23.121845] The buggy address belongs to the virtual mapping at [ 23.121845] [ffffc90000000000, ffffc90000009000) created by: [ 23.121845] irq_init_percpu_irqstack+0x1cf/0x270 [ 23.122707] [ 23.122803] The buggy address belongs to the physical page: [ 23.123104] page:0000000072ac19f0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x24a09 [ 23.123609] flags: 0xfffffc0001000(reserved|node=0|zone=1|lastcpupid=0x1fffff) [ 23.123998] page_type: 0xffffffff() [ 23.124194] raw: 000fffffc0001000 ffffea0000928248 ffffea0000928248 0000000000000000 [ 23.124610] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 [ 23.125023] page dumped because: kasan: bad access detected [ 23.125326] [ 23.125421] Memory state around the buggy address: [ 23.125682] ffffc90000007800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 23.126072] ffffc90000007880: 00 00 00 00 00 f1 f1 f1 f1 f1 f1 00 00 f2 f2 00 [ 23.126455] >ffffc90000007900: 00 00 00 00 00 00 00 00 00 f2 f2 f2 f2 00 00 00 [ 23.126840] ^ [ 23.127138] ffffc90000007980: 00 00 00 00 00 00 00 00 00 00 00 00 00 f3 f3 f3 [ 23.127522] ffffc90000007a00: f3 00 00 00 00 00 00 00 00 00 00 00 f1 f1 f1 f1 [ 23.127906] ================================================================== [ 23.128324] Disabling lock debugging due to kernel taint Using simple s16 pointers for the 16-bit accesses fixes the problem. For the 32-bit accesses, src and dst can be used directly. Bug: 291031528 Fixes: 96518518cc41 ("netfilter: add nftables") Cc: stable@vger.kernel.org Reported-by: Tanguy DUBROCA (@SidewayRE) from @Synacktiv working with ZDI Signed-off-by: Thadeu Lima de Souza Cascardo Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 870dcc31c0cf47cb15a568ade4168dc644b3ccfb) Signed-off-by: Lee Jones Change-Id: I4a76c2be021867c923684f0034d4564f7797b48b --- net/netfilter/nft_byteorder.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 9d5947ab8d4e..7b0b8fecb220 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -30,11 +30,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, const struct nft_byteorder *priv = nft_expr_priv(expr); u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; - union { u32 u32; u16 u16; } *s, *d; + u16 *s16, *d16; unsigned int i; - s = (void *)src; - d = (void *)dst; + s16 = (void *)src; + d16 = (void *)dst; switch (priv->size) { case 8: { @@ -61,11 +61,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = ntohl((__force __be32)s[i].u32); + dst[i] = ntohl((__force __be32)src[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = (__force __u32)htonl(s[i].u32); + dst[i] = (__force __u32)htonl(src[i]); break; } break; @@ -73,11 +73,11 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = ntohs((__force __be16)s[i].u16); + d16[i] = ntohs((__force __be16)s16[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = (__force __u16)htons(s[i].u16); + d16[i] = (__force __u16)htons(s16[i]); break; } break; From bd34b88730b2f1fd754972380a5843aca33dcf58 Mon Sep 17 00:00:00 2001 From: Yi Yang Date: Fri, 11 Aug 2023 11:11:21 +0800 Subject: [PATCH 4336/4345] UPSTREAM: tty: n_gsm: fix the UAF caused by race condition in gsm_cleanup_mux commit 3c4f8333b582487a2d1e02171f1465531cde53e3 upstream. In commit 9b9c8195f3f0 ("tty: n_gsm: fix UAF in gsm_cleanup_mux"), the UAF problem is not completely fixed. There is a race condition in gsm_cleanup_mux(), which caused this UAF. The UAF problem is triggered by the following race: task[5046] task[5054] ----------------------- ----------------------- gsm_cleanup_mux(); dlci = gsm->dlci[0]; mutex_lock(&gsm->mutex); gsm_cleanup_mux(); dlci = gsm->dlci[0]; //Didn't take the lock gsm_dlci_release(gsm->dlci[i]); gsm->dlci[i] = NULL; mutex_unlock(&gsm->mutex); mutex_lock(&gsm->mutex); dlci->dead = true; //UAF Fix it by assigning values after mutex_lock(). Bug: 291178675 Link: https://syzkaller.appspot.com/text?tag=CrashReport&x=176188b5a80000 Cc: stable Fixes: 9b9c8195f3f0 ("tty: n_gsm: fix UAF in gsm_cleanup_mux") Fixes: aa371e96f05d ("tty: n_gsm: fix restart handling via CLD command") Signed-off-by: Yi Yang Co-developed-by: Qiumiao Zhang Signed-off-by: Qiumiao Zhang Link: https://lore.kernel.org/r/20230811031121.153237-1-yiyang13@huawei.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 31311a9a4baae0ad47c85e448af21b2120344ff0) Signed-off-by: Lee Jones Change-Id: I460a0f21f4121531d7732e09643a451382dfa2da --- drivers/tty/n_gsm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index d439afef9212..94c963462d74 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2159,12 +2159,13 @@ static void gsm_error(struct gsm_mux *gsm, static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) { int i; - struct gsm_dlci *dlci = gsm->dlci[0]; + struct gsm_dlci *dlci; struct gsm_msg *txq, *ntxq; gsm->dead = true; mutex_lock(&gsm->mutex); + dlci = gsm->dlci[0]; if (dlci) { if (disc && dlci->state != DLCI_CLOSED) { gsm_dlci_begin_close(dlci); From 6356ed35b9e7f51b8c43af4277f5c7395cc7b864 Mon Sep 17 00:00:00 2001 From: Lincheng Yang Date: Thu, 7 Sep 2023 11:19:43 +0800 Subject: [PATCH 4337/4345] ANDROID: add vendor hook of add/delete/iterate node for swap_avail_heads Our Android phones occur Panic as follows: [77522.303024][ T9734] Call trace: [77522.303039][ T9734] dump_backtrace.cfi_jt+0x0/0x8 [77522.303052][ T9734] dump_stack_lvl+0xc4/0x140 [77522.303061][ T9734] dump_stack+0x1c/0x2c [77522.303123][ T9734] mrdump_common_die+0x3a8/0x544 [mrdump] [77522.303177][ T9734] ipanic_die+0x24/0x38 [mrdump] [77522.303189][ T9734] die+0x340/0x698 [77522.303199][ T9734] bug_handler+0x48/0x108 [77522.303210][ T9734] brk_handler+0xac/0x1a8 [77522.303221][ T9734] do_debug_exception+0xe0/0x1e0 [77522.303233][ T9734] el1_dbg+0x38/0x54 [77522.303242][ T9734] el1_sync_handler+0x40/0x88 [77522.303255][ T9734] el1_sync+0x8c/0x140 [77522.303264][ T9734] plist_requeue+0xd4/0x110 [77522.303297][ T9734] tran_get_swap_pages+0xc8/0x364 [memfusion] [77522.303329][ T9734] probe_android_vh_get_swap_page+0x1b4/0x220 [memfusion] [77522.303342][ T9734] get_swap_page+0x258/0x304 [77522.303352][ T9734] shrink_page_list+0xe00/0x1e0c [77522.303361][ T9734] shrink_inactive_list+0x2f4/0xac8 [77522.303373][ T9734] shrink_lruvec+0x1a4/0x34c [77522.303383][ T9734] shrink_node_memcgs+0x84/0x3b0 [77522.303391][ T9734] shrink_node+0x2c4/0x6e4 [77522.303400][ T9734] shrink_zones+0x16c/0x29c [77522.303410][ T9734] do_try_to_free_pages+0xe4/0x2bc [77522.303418][ T9734] try_to_free_pages+0x388/0x7b4 [77522.303429][ T9734] __alloc_pages_direct_reclaim+0x88/0x278 [77522.303438][ T9734] __alloc_pages_slowpath+0x464/0xb24 [77522.303447][ T9734] __alloc_pages_nodemask+0x1f4/0x3dc [77522.303458][ T9734] do_anonymous_page+0x164/0x914 [77522.303466][ T9734] handle_pte_fault+0x15c/0x9f8 [77522.303476][ T9734] ___handle_speculative_fault+0x234/0xe18 [77522.303485][ T9734] __handle_speculative_fault+0x78/0x21c [77522.303497][ T9734] do_page_fault+0x36c/0x754 [77522.303506][ T9734] do_translation_fault+0x48/0x64 [77522.303514][ T9734] do_mem_abort+0x6c/0x164 [77522.303522][ T9734] el0_da+0x24/0x34 [77522.303531][ T9734] el0_sync_handler+0xc8/0xf0 [77522.303539][ T9734] el0_sync+0x1b4/0x1c0 The analysis shows that when we iterate the swap_avail_heads list, we get node A, but before we access node A, node A is maybe deleted, and by the time we actually access node A, it no longer exists, as follows: CPU1 thread1 CPU2 thread2 plist_for_each_entry_safe() get si->avail_lists[node] from swap_avail_heads remove si->avail_lists[node] from swap_avail_heads plist_requeue(&si->avail_lists[node]) BUG_ON(plist_node_empty(node)); // trigger Due to when we use vendor hook of get_swap_page, the get_swap_pages() function is overridden, use our own spin_lock to protect when iterate swap_avail_heads list, but now use native swap_avail_lock spin_lock protect when the swap_avail_heads list to add and delete nodes, so there will be concurrent access. So add vendor hook of add/delete/iterate node for avail_list, in this way, we can use our own spin_lock to protect the swap_avail_heads list to add, delete and iterate node. Due to enable_swap_info function to call vendor hook of add_to_avail_list, need first init swap_avail_heads, so also add vendor hook of swap_avail_heads_init. Due to the vendor hook of __cgroup_throttle_swaprate need to call blkcg_schedule_throttle function, so export it also. Bug: 225795494 Change-Id: I03107cbda6310fa7ae85e41b8cf1fa8225cafe78 Signed-off-by: Lincheng Yang Suggested-by: Bing Han --- block/blk-cgroup.c | 1 + drivers/android/vendor_hooks.c | 4 ++++ include/trace/hooks/mm.h | 12 ++++++++++++ mm/swapfile.c | 18 ++++++++++++++++++ 4 files changed, 35 insertions(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index d7054c186845..10cc2e6fd6c6 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1794,6 +1794,7 @@ void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) current->use_memdelay = use_memdelay; set_notify_resume(current); } +EXPORT_SYMBOL_GPL(blkcg_schedule_throttle); /** * blkcg_add_delay - add delay to this blkg diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index 815c5efb5c22..8b1929a3a486 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -468,12 +468,16 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_free_swap_slot); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_free_swap_slot); EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_get_swap_page); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_get_swap_page); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_add_to_avail_list); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_del_from_avail_list); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh___cgroup_throttle_swaprate); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_madvise_cold_or_pageout); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_page_isolated_for_reclaim); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_inactive_is_low); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_snapshot_refaults); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_account_swap_pages); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_unuse_swap_page); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_swap_avail_heads_init); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_init_swap_info_struct); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_si_swapinfo); EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_alloc_si); diff --git a/include/trace/hooks/mm.h b/include/trace/hooks/mm.h index 480880a49d32..dd980641cb27 100644 --- a/include/trace/hooks/mm.h +++ b/include/trace/hooks/mm.h @@ -287,6 +287,15 @@ DECLARE_HOOK(android_vh_get_swap_page, TP_PROTO(struct page *page, swp_entry_t *entry, struct swap_slots_cache *cache, bool *found), TP_ARGS(page, entry, cache, found)); +DECLARE_HOOK(android_vh_add_to_avail_list, + TP_PROTO(struct swap_info_struct *p, bool *skip), + TP_ARGS(p, skip)); +DECLARE_HOOK(android_vh_del_from_avail_list, + TP_PROTO(struct swap_info_struct *p, bool *skip), + TP_ARGS(p, skip)); +DECLARE_HOOK(android_vh___cgroup_throttle_swaprate, + TP_PROTO(int nid, bool *skip), + TP_ARGS(nid, skip)); DECLARE_HOOK(android_vh_madvise_cold_or_pageout, TP_PROTO(struct vm_area_struct *vma, bool *allow_shared), TP_ARGS(vma, allow_shared)); @@ -299,6 +308,9 @@ DECLARE_HOOK(android_vh_account_swap_pages, DECLARE_HOOK(android_vh_unuse_swap_page, TP_PROTO(struct swap_info_struct *si, struct page *page), TP_ARGS(si, page)); +DECLARE_HOOK(android_vh_swap_avail_heads_init, + TP_PROTO(struct plist_head *swap_avail_heads), + TP_ARGS(swap_avail_heads)); DECLARE_HOOK(android_vh_init_swap_info_struct, TP_PROTO(struct swap_info_struct *p, struct plist_head *swap_avail_heads), TP_ARGS(p, swap_avail_heads)); diff --git a/mm/swapfile.c b/mm/swapfile.c index a31d90fdb19f..cc1ce66cb492 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -675,6 +675,12 @@ static void __del_from_avail_list(struct swap_info_struct *p) static void del_from_avail_list(struct swap_info_struct *p) { + bool skip = false; + + trace_android_vh_del_from_avail_list(p, &skip); + if (skip) + return; + spin_lock(&swap_avail_lock); __del_from_avail_list(p); spin_unlock(&swap_avail_lock); @@ -700,6 +706,11 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, static void add_to_avail_list(struct swap_info_struct *p) { int nid; + bool skip = false; + + trace_android_vh_add_to_avail_list(p, &skip); + if (skip) + return; spin_lock(&swap_avail_lock); for_each_node(nid) { @@ -3394,6 +3405,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; + + trace_android_vh_swap_avail_heads_init(swap_avail_heads); enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); trace_android_vh_init_swap_info_struct(p, swap_avail_heads); @@ -3848,6 +3861,7 @@ void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { struct swap_info_struct *si, *next; int nid = page_to_nid(page); + bool skip = false; if (!(gfp_mask & __GFP_IO)) return; @@ -3862,6 +3876,10 @@ void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) if (current->throttle_queue) return; + trace_android_vh___cgroup_throttle_swaprate(nid, &skip); + if (skip) + return; + spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { From 909a83a97dc0dc809d8512db773c5cf1dfb3d88c Mon Sep 17 00:00:00 2001 From: Lincheng Yang Date: Thu, 7 Sep 2023 11:19:58 +0800 Subject: [PATCH 4338/4345] ANDROID: GKI: Update symbols to symbol list Leaf changes summary: 9 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 5 Added functions Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 4 Added variables 5 Added functions: [A] 'function int __traceiter_android_vh___cgroup_throttle_swaprate(void*, int, bool*)' [A] 'function int __traceiter_android_vh_add_to_avail_list(void*, swap_info_struct*, bool*)' [A] 'function int __traceiter_android_vh_del_from_avail_list(void*, swap_info_struct*, bool*)' [A] 'function int __traceiter_android_vh_swap_avail_heads_init(void*, plist_head*)' [A] 'function void blkcg_schedule_throttle(request_queue*, bool)' 4 Added variables: [A] 'tracepoint __tracepoint_android_vh___cgroup_throttle_swaprate' [A] 'tracepoint __tracepoint_android_vh_add_to_avail_list' [A] 'tracepoint __tracepoint_android_vh_del_from_avail_list' [A] 'tracepoint __tracepoint_android_vh_swap_avail_heads_init' Bug: 225795494 Change-Id: Iacf77eda13e252c2e9218b0a71cb2884ee3dc5f5 Signed-off-by: Lincheng Yang --- android/abi_gki_aarch64.xml | 293 +++++++++++++++++------------- android/abi_gki_aarch64_transsion | 9 + 2 files changed, 176 insertions(+), 126 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 607576e857cb..d42c1ab75c7a 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -417,9 +417,11 @@ + + @@ -487,6 +489,7 @@ + @@ -671,6 +674,7 @@ + @@ -1094,6 +1098,7 @@ + @@ -6496,9 +6501,11 @@ + + @@ -6566,6 +6573,7 @@ + @@ -6750,6 +6758,7 @@ + @@ -116506,9 +116515,9 @@ - + - + @@ -117748,12 +117757,12 @@ - - + + - - + + @@ -118277,10 +118286,10 @@ - - - - + + + + @@ -118994,12 +119003,18 @@ - + - + + + + + + + @@ -119014,6 +119029,12 @@ + + + + + + @@ -119038,22 +119059,22 @@ - - - - - - - + + + + + + + - - - - - - - + + + + + + + @@ -119070,10 +119091,10 @@ - - - - + + + + @@ -119380,9 +119401,9 @@ - - - + + + @@ -119465,6 +119486,12 @@ + + + + + + @@ -119613,10 +119640,10 @@ - - - - + + + + @@ -119791,10 +119818,10 @@ - - - - + + + + @@ -119900,30 +119927,30 @@ - - - - - - + + + + + + - - - - + + + + - - - - + + + + - - - - + + + + @@ -120090,10 +120117,10 @@ - - - - + + + + @@ -120217,9 +120244,9 @@ - - - + + + @@ -120475,9 +120502,9 @@ - - - + + + @@ -120566,10 +120593,10 @@ - - - - + + + + @@ -120602,6 +120629,11 @@ + + + + + @@ -120625,9 +120657,9 @@ - - - + + + @@ -120803,10 +120835,10 @@ - - - - + + + + @@ -121313,7 +121345,7 @@ - + @@ -121423,17 +121455,19 @@ - + + + - - + + - + @@ -121479,7 +121513,7 @@ - + @@ -121493,6 +121527,7 @@ + @@ -121515,7 +121550,7 @@ - + @@ -121543,7 +121578,7 @@ - + @@ -121560,10 +121595,10 @@ - - - - + + + + @@ -121591,7 +121626,7 @@ - + @@ -121612,7 +121647,7 @@ - + @@ -121657,7 +121692,7 @@ - + @@ -121671,17 +121706,18 @@ - + + - + @@ -121708,7 +121744,7 @@ - + @@ -122281,11 +122317,11 @@ - - - - - + + + + + @@ -122776,13 +122812,13 @@ - - + + - - - + + + @@ -122790,9 +122826,9 @@ - - - + + + @@ -123434,6 +123470,11 @@ + + + + + @@ -142586,11 +142627,11 @@ - - - - - + + + + + @@ -143760,8 +143801,8 @@ - - + + @@ -145915,18 +145956,18 @@ - - - + + + - - - + + + @@ -145935,8 +145976,8 @@ - - + + diff --git a/android/abi_gki_aarch64_transsion b/android/abi_gki_aarch64_transsion index 26f1a25320be..558f6f7dcac7 100644 --- a/android/abi_gki_aarch64_transsion +++ b/android/abi_gki_aarch64_transsion @@ -9,12 +9,16 @@ swap_alloc_cluster swapcache_free_entries swap_type_to_swap_info + blkcg_schedule_throttle __traceiter_android_rvh_alloc_si __traceiter_android_rvh_alloc_swap_slot_cache __traceiter_android_rvh_drain_slots_cache_cpu __traceiter_android_rvh_free_swap_slot __traceiter_android_rvh_get_swap_page __traceiter_android_rvh_handle_pte_fault_end + __traceiter_android_vh_add_to_avail_list + __traceiter_android_vh_del_from_avail_list + __traceiter_android_vh___cgroup_throttle_swaprate __traceiter_android_vh_account_swap_pages __traceiter_android_vh_alloc_si __traceiter_android_vh_alloc_swap_slot_cache @@ -28,6 +32,7 @@ __traceiter_android_vh_get_swap_page __traceiter_android_vh_handle_pte_fault_end __traceiter_android_vh_inactive_is_low + __traceiter_android_vh_swap_avail_heads_init __traceiter_android_vh_init_swap_info_struct __traceiter_android_vh_migrate_page_states __traceiter_android_vh_page_isolated_for_reclaim @@ -46,6 +51,9 @@ __tracepoint_android_rvh_free_swap_slot __tracepoint_android_rvh_get_swap_page __tracepoint_android_rvh_handle_pte_fault_end + __tracepoint_android_vh_add_to_avail_list + __tracepoint_android_vh_del_from_avail_list + __tracepoint_android_vh___cgroup_throttle_swaprate __tracepoint_android_vh_account_swap_pages __tracepoint_android_vh_alloc_si __tracepoint_android_vh_alloc_swap_slot_cache @@ -59,6 +67,7 @@ __tracepoint_android_vh_get_swap_page __tracepoint_android_vh_handle_pte_fault_end __tracepoint_android_vh_inactive_is_low + __tracepoint_android_vh_swap_avail_heads_init __tracepoint_android_vh_init_swap_info_struct __tracepoint_android_vh_migrate_page_states __tracepoint_android_vh_page_isolated_for_reclaim From 3718ea1e770b8d6cb970ba6f637a948537bd1427 Mon Sep 17 00:00:00 2001 From: Xiaojun Ji Date: Thu, 14 Sep 2023 15:48:05 +0800 Subject: [PATCH 4339/4345] ANDROID: vendor_hook: Add hook to skip swapcache We want to skip swapcache in some scenarios to reduce swap cache Bug: 300857016 Change-Id: I8cbc45733d861be6f56628b40a1ef936cae3b45d Signed-off-by: Xiaojun Ji --- drivers/android/vendor_hooks.c | 1 + include/trace/hooks/mm.h | 3 +++ mm/memory.c | 4 +++- 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index 8b1929a3a486..1021ca51ede6 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -496,6 +496,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_rvh_dma_buf_stats_teardown); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_madvise_cold_or_pageout_abort); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_compact_finished); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_wakeup_bypass); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_skip_swapcache); /* * For type visibility */ diff --git a/include/trace/hooks/mm.h b/include/trace/hooks/mm.h index dd980641cb27..4628e4aa1cc6 100644 --- a/include/trace/hooks/mm.h +++ b/include/trace/hooks/mm.h @@ -356,6 +356,9 @@ DECLARE_HOOK(android_vh_compact_finished, DECLARE_HOOK(android_vh_madvise_cold_or_pageout_abort, TP_PROTO(struct vm_area_struct *vma, bool *abort_madvise), TP_ARGS(vma, abort_madvise)); +DECLARE_HOOK(android_vh_skip_swapcache, + TP_PROTO(swp_entry_t entry, bool *skip), + TP_ARGS(entry, skip)); /* macro versions of hooks are no longer required */ #endif /* _TRACE_HOOK_MM_H */ diff --git a/mm/memory.c b/mm/memory.c index df62ea2ef8f2..857cfc90893f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3663,8 +3663,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!page) { struct swap_info_struct *si = swp_swap_info(entry); + bool skip_swapcache = false; - if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && + trace_android_vh_skip_swapcache(entry, &skip_swapcache); + if ((data_race(si->flags & SWP_SYNCHRONOUS_IO) || skip_swapcache) && __swap_count(entry) == 1) { /* skip swapcache */ gfp_t flags = GFP_HIGHUSER_MOVABLE; From e22810eb27096fd0c640d0c30a102b102f1ac42a Mon Sep 17 00:00:00 2001 From: Xiaojun Ji Date: Fri, 15 Sep 2023 11:22:56 +0800 Subject: [PATCH 4340/4345] ANDROID: GKI: Update moto symbols list Leaf changes summary: 2 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 1 Added function Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 1 Added variable 1 Added function: [A] 'function int __traceiter_android_vh_skip_swapcache(void*, swp_entry_t, bool*)' 1 Added variable: [A] 'tracepoint __tracepoint_android_vh_skip_swapcache' Bug: 300857016 Change-Id: I58877d09416b0277f188445d10c9eef73e664ffb Signed-off-by: Xiaojun Ji --- android/abi_gki_aarch64.xml | 130 +++++++++++++++++++++++++++++++---- android/abi_gki_aarch64_moto | 3 + 2 files changed, 120 insertions(+), 13 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index d42c1ab75c7a..5eb543dc62e3 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -669,6 +669,7 @@ + @@ -6753,6 +6754,7 @@ + @@ -21583,6 +21585,14 @@ + + + + + + + + @@ -41042,6 +41052,17 @@ + + + + + + + + + + + @@ -42851,6 +42872,7 @@ + @@ -55396,6 +55418,7 @@ + @@ -63356,7 +63379,65 @@ - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -68145,6 +68226,11 @@ + + + + + @@ -84012,6 +84098,7 @@ + @@ -84556,6 +84643,14 @@ + + + + + + + + @@ -96237,6 +96332,7 @@ + @@ -116308,6 +116404,7 @@ + @@ -116515,9 +116612,9 @@ - + - + @@ -120599,6 +120696,12 @@ + + + + + + @@ -121707,6 +121810,7 @@ + @@ -122273,12 +122377,12 @@ - - - - - - + + + + + + @@ -131697,10 +131801,10 @@ - - - - + + + + diff --git a/android/abi_gki_aarch64_moto b/android/abi_gki_aarch64_moto index 009165749001..71a0d1b1e3d7 100644 --- a/android/abi_gki_aarch64_moto +++ b/android/abi_gki_aarch64_moto @@ -1,3 +1,6 @@ [abi_symbol_list] + swp_swap_info + __traceiter_android_vh_skip_swapcache __traceiter_android_vh_tune_mmap_readaround + __tracepoint_android_vh_skip_swapcache __tracepoint_android_vh_tune_mmap_readaround From ff86e87c7e99f8bdce332c7f287d305c72fc95cd Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 7 Sep 2023 11:11:00 -0700 Subject: [PATCH 4341/4345] FROMGIT: f2fs: split initial and dynamic conditions for extent_cache Let's allocate the extent_cache tree without dynamic conditions to avoid a missing condition causing a panic as below. # create a file w/ a compressed flag # disable the compression # panic while updating extent_cache F2FS-fs (dm-64): Swapfile: last extent is not aligned to section F2FS-fs (dm-64): Swapfile (3) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * N) Adding 124996k swap on ./swap-file. Priority:0 extents:2 across:17179494468k ================================================================== BUG: KASAN: null-ptr-deref in instrument_atomic_read_write out/common/include/linux/instrumented.h:101 [inline] BUG: KASAN: null-ptr-deref in atomic_try_cmpxchg_acquire out/common/include/asm-generic/atomic-instrumented.h:705 [inline] BUG: KASAN: null-ptr-deref in queued_write_lock out/common/include/asm-generic/qrwlock.h:92 [inline] BUG: KASAN: null-ptr-deref in __raw_write_lock out/common/include/linux/rwlock_api_smp.h:211 [inline] BUG: KASAN: null-ptr-deref in _raw_write_lock+0x5a/0x110 out/common/kernel/locking/spinlock.c:295 Write of size 4 at addr 0000000000000030 by task syz-executor154/3327 CPU: 0 PID: 3327 Comm: syz-executor154 Tainted: G O 5.10.185 #1 Hardware name: emulation qemu-x86/qemu-x86, BIOS 2023.01-21885-gb3cc1cd24d 01/01/2023 Call Trace: __dump_stack out/common/lib/dump_stack.c:77 [inline] dump_stack_lvl+0x17e/0x1c4 out/common/lib/dump_stack.c:118 __kasan_report+0x16c/0x260 out/common/mm/kasan/report.c:415 kasan_report+0x51/0x70 out/common/mm/kasan/report.c:428 kasan_check_range+0x2f3/0x340 out/common/mm/kasan/generic.c:186 __kasan_check_write+0x14/0x20 out/common/mm/kasan/shadow.c:37 instrument_atomic_read_write out/common/include/linux/instrumented.h:101 [inline] atomic_try_cmpxchg_acquire out/common/include/asm-generic/atomic-instrumented.h:705 [inline] queued_write_lock out/common/include/asm-generic/qrwlock.h:92 [inline] __raw_write_lock out/common/include/linux/rwlock_api_smp.h:211 [inline] _raw_write_lock+0x5a/0x110 out/common/kernel/locking/spinlock.c:295 __drop_extent_tree+0xdf/0x2f0 out/common/fs/f2fs/extent_cache.c:1155 f2fs_drop_extent_tree+0x17/0x30 out/common/fs/f2fs/extent_cache.c:1172 f2fs_insert_range out/common/fs/f2fs/file.c:1600 [inline] f2fs_fallocate+0x19fd/0x1f40 out/common/fs/f2fs/file.c:1764 vfs_fallocate+0x514/0x9b0 out/common/fs/open.c:310 ksys_fallocate out/common/fs/open.c:333 [inline] __do_sys_fallocate out/common/fs/open.c:341 [inline] __se_sys_fallocate out/common/fs/open.c:339 [inline] __x64_sys_fallocate+0xb8/0x100 out/common/fs/open.c:339 do_syscall_64+0x35/0x50 out/common/arch/x86/entry/common.c:46 Bug: 295824459 (cherry picked from commit f803982190f0265fd36cf84670aa6daefc2b0768 https://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git dev) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-f2fs-devel/20230907210859.3698691-1-jaegeuk@kernel.org/T/#u Fixes: 72840cccc0a1 ("f2fs: allocate the extent_cache by default") Reported-and-tested-by: syzbot+d342e330a37b48c094b7@syzkaller.appspotmail.com Signed-off-by: Jaegeuk Kim Change-Id: Ie814c99098487e76b7abdcfdcda342a7e1c1fcf0 --- fs/f2fs/extent_cache.c | 54 ++++++++++++++++-------------------------- 1 file changed, 21 insertions(+), 33 deletions(-) diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 33eb6dea04f0..dadddb3b94b8 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -41,41 +41,14 @@ static void __set_extent_info(struct extent_info *ei, } } -static bool __may_read_extent_tree(struct inode *inode) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - - if (!test_opt(sbi, READ_EXTENT_CACHE)) - return false; - if (is_inode_flag_set(inode, FI_NO_EXTENT)) - return false; - if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) && - !f2fs_sb_has_readonly(sbi)) - return false; - return S_ISREG(inode->i_mode); -} - -static bool __may_age_extent_tree(struct inode *inode) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - - if (!test_opt(sbi, AGE_EXTENT_CACHE)) - return false; - /* don't cache block age info for cold file */ - if (is_inode_flag_set(inode, FI_COMPRESSED_FILE)) - return false; - if (file_is_cold(inode)) - return false; - - return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode); -} - static bool __init_may_extent_tree(struct inode *inode, enum extent_type type) { if (type == EX_READ) - return __may_read_extent_tree(inode); - else if (type == EX_BLOCK_AGE) - return __may_age_extent_tree(inode); + return test_opt(F2FS_I_SB(inode), READ_EXTENT_CACHE) && + S_ISREG(inode->i_mode); + if (type == EX_BLOCK_AGE) + return test_opt(F2FS_I_SB(inode), AGE_EXTENT_CACHE) && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)); return false; } @@ -88,7 +61,22 @@ static bool __may_extent_tree(struct inode *inode, enum extent_type type) if (list_empty(&F2FS_I_SB(inode)->s_list)) return false; - return __init_may_extent_tree(inode, type); + if (!__init_may_extent_tree(inode, type)) + return false; + + if (type == EX_READ) { + if (is_inode_flag_set(inode, FI_NO_EXTENT)) + return false; + if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) && + !f2fs_sb_has_readonly(F2FS_I_SB(inode))) + return false; + } else if (type == EX_BLOCK_AGE) { + if (is_inode_flag_set(inode, FI_COMPRESSED_FILE)) + return false; + if (file_is_cold(inode)) + return false; + } + return true; } static void __try_update_largest_extent(struct extent_tree *et, From 6b6202b762a814c847cb65ca3f83376071cc5f1a Mon Sep 17 00:00:00 2001 From: Budimir Markovic Date: Thu, 24 Aug 2023 01:49:05 -0700 Subject: [PATCH 4342/4345] UPSTREAM: net/sched: sch_hfsc: Ensure inner classes have fsc curve [ Upstream commit b3d26c5702c7d6c45456326e56d2ccf3f103e60f ] HFSC assumes that inner classes have an fsc curve, but it is currently possible for classes without an fsc curve to become parents. This leads to bugs including a use-after-free. Don't allow non-root classes without HFSC_FSC to become parents. Bug: 299921101 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Budimir Markovic Signed-off-by: Budimir Markovic Acked-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20230824084905.422-1-markovicbudimir@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin (cherry picked from commit 4cf994d3f4ff42d604fae2b461bdd5195a7dfabd) Signed-off-by: Lee Jones Change-Id: I5b44ae6bb340b978372ed9657ba2e23f75b850e5 --- net/sched/sch_hfsc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index cdc43a06aa9b..6076294a632c 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1012,6 +1012,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (parent == NULL) return -ENOENT; } + if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { + NL_SET_ERR_MSG(extack, "Invalid parent - parent class must have FSC"); + return -EINVAL; + } if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0) return -EINVAL; From 180ea0f6d4f90261d585ceda38d3fcfdb8b47bae Mon Sep 17 00:00:00 2001 From: valis Date: Fri, 1 Sep 2023 12:22:37 -0400 Subject: [PATCH 4343/4345] UPSTREAM: net: sched: sch_qfq: Fix UAF in qfq_dequeue() [ Upstream commit 8fc134fee27f2263988ae38920bc03da416b03d8 ] When the plug qdisc is used as a class of the qfq qdisc it could trigger a UAF. This issue can be reproduced with following commands: tc qdisc add dev lo root handle 1: qfq tc class add dev lo parent 1: classid 1:1 qfq weight 1 maxpkt 512 tc qdisc add dev lo parent 1:1 handle 2: plug tc filter add dev lo parent 1: basic classid 1:1 ping -c1 127.0.0.1 and boom: [ 285.353793] BUG: KASAN: slab-use-after-free in qfq_dequeue+0xa7/0x7f0 [ 285.354910] Read of size 4 at addr ffff8880bad312a8 by task ping/144 [ 285.355903] [ 285.356165] CPU: 1 PID: 144 Comm: ping Not tainted 6.5.0-rc3+ #4 [ 285.357112] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 [ 285.358376] Call Trace: [ 285.358773] [ 285.359109] dump_stack_lvl+0x44/0x60 [ 285.359708] print_address_description.constprop.0+0x2c/0x3c0 [ 285.360611] kasan_report+0x10c/0x120 [ 285.361195] ? qfq_dequeue+0xa7/0x7f0 [ 285.361780] qfq_dequeue+0xa7/0x7f0 [ 285.362342] __qdisc_run+0xf1/0x970 [ 285.362903] net_tx_action+0x28e/0x460 [ 285.363502] __do_softirq+0x11b/0x3de [ 285.364097] do_softirq.part.0+0x72/0x90 [ 285.364721] [ 285.365072] [ 285.365422] __local_bh_enable_ip+0x77/0x90 [ 285.366079] __dev_queue_xmit+0x95f/0x1550 [ 285.366732] ? __pfx_csum_and_copy_from_iter+0x10/0x10 [ 285.367526] ? __pfx___dev_queue_xmit+0x10/0x10 [ 285.368259] ? __build_skb_around+0x129/0x190 [ 285.368960] ? ip_generic_getfrag+0x12c/0x170 [ 285.369653] ? __pfx_ip_generic_getfrag+0x10/0x10 [ 285.370390] ? csum_partial+0x8/0x20 [ 285.370961] ? raw_getfrag+0xe5/0x140 [ 285.371559] ip_finish_output2+0x539/0xa40 [ 285.372222] ? __pfx_ip_finish_output2+0x10/0x10 [ 285.372954] ip_output+0x113/0x1e0 [ 285.373512] ? __pfx_ip_output+0x10/0x10 [ 285.374130] ? icmp_out_count+0x49/0x60 [ 285.374739] ? __pfx_ip_finish_output+0x10/0x10 [ 285.375457] ip_push_pending_frames+0xf3/0x100 [ 285.376173] raw_sendmsg+0xef5/0x12d0 [ 285.376760] ? do_syscall_64+0x40/0x90 [ 285.377359] ? __static_call_text_end+0x136578/0x136578 [ 285.378173] ? do_syscall_64+0x40/0x90 [ 285.378772] ? kasan_enable_current+0x11/0x20 [ 285.379469] ? __pfx_raw_sendmsg+0x10/0x10 [ 285.380137] ? __sock_create+0x13e/0x270 [ 285.380673] ? __sys_socket+0xf3/0x180 [ 285.381174] ? __x64_sys_socket+0x3d/0x50 [ 285.381725] ? entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.382425] ? __rcu_read_unlock+0x48/0x70 [ 285.382975] ? ip4_datagram_release_cb+0xd8/0x380 [ 285.383608] ? __pfx_ip4_datagram_release_cb+0x10/0x10 [ 285.384295] ? preempt_count_sub+0x14/0xc0 [ 285.384844] ? __list_del_entry_valid+0x76/0x140 [ 285.385467] ? _raw_spin_lock_bh+0x87/0xe0 [ 285.386014] ? __pfx__raw_spin_lock_bh+0x10/0x10 [ 285.386645] ? release_sock+0xa0/0xd0 [ 285.387148] ? preempt_count_sub+0x14/0xc0 [ 285.387712] ? freeze_secondary_cpus+0x348/0x3c0 [ 285.388341] ? aa_sk_perm+0x177/0x390 [ 285.388856] ? __pfx_aa_sk_perm+0x10/0x10 [ 285.389441] ? check_stack_object+0x22/0x70 [ 285.390032] ? inet_send_prepare+0x2f/0x120 [ 285.390603] ? __pfx_inet_sendmsg+0x10/0x10 [ 285.391172] sock_sendmsg+0xcc/0xe0 [ 285.391667] __sys_sendto+0x190/0x230 [ 285.392168] ? __pfx___sys_sendto+0x10/0x10 [ 285.392727] ? kvm_clock_get_cycles+0x14/0x30 [ 285.393328] ? set_normalized_timespec64+0x57/0x70 [ 285.393980] ? _raw_spin_unlock_irq+0x1b/0x40 [ 285.394578] ? __x64_sys_clock_gettime+0x11c/0x160 [ 285.395225] ? __pfx___x64_sys_clock_gettime+0x10/0x10 [ 285.395908] ? _copy_to_user+0x3e/0x60 [ 285.396432] ? exit_to_user_mode_prepare+0x1a/0x120 [ 285.397086] ? syscall_exit_to_user_mode+0x22/0x50 [ 285.397734] ? do_syscall_64+0x71/0x90 [ 285.398258] __x64_sys_sendto+0x74/0x90 [ 285.398786] do_syscall_64+0x64/0x90 [ 285.399273] ? exit_to_user_mode_prepare+0x1a/0x120 [ 285.399949] ? syscall_exit_to_user_mode+0x22/0x50 [ 285.400605] ? do_syscall_64+0x71/0x90 [ 285.401124] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.401807] RIP: 0033:0x495726 [ 285.402233] Code: ff ff ff f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 11 b8 2c 00 00 00 0f 09 [ 285.404683] RSP: 002b:00007ffcc25fb618 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 285.405677] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 0000000000495726 [ 285.406628] RDX: 0000000000000040 RSI: 0000000002518750 RDI: 0000000000000000 [ 285.407565] RBP: 00000000005205ef R08: 00000000005f8838 R09: 000000000000001c [ 285.408523] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000002517634 [ 285.409460] R13: 00007ffcc25fb6f0 R14: 0000000000000003 R15: 0000000000000000 [ 285.410403] [ 285.410704] [ 285.410929] Allocated by task 144: [ 285.411402] kasan_save_stack+0x1e/0x40 [ 285.411926] kasan_set_track+0x21/0x30 [ 285.412442] __kasan_slab_alloc+0x55/0x70 [ 285.412973] kmem_cache_alloc_node+0x187/0x3d0 [ 285.413567] __alloc_skb+0x1b4/0x230 [ 285.414060] __ip_append_data+0x17f7/0x1b60 [ 285.414633] ip_append_data+0x97/0xf0 [ 285.415144] raw_sendmsg+0x5a8/0x12d0 [ 285.415640] sock_sendmsg+0xcc/0xe0 [ 285.416117] __sys_sendto+0x190/0x230 [ 285.416626] __x64_sys_sendto+0x74/0x90 [ 285.417145] do_syscall_64+0x64/0x90 [ 285.417624] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.418306] [ 285.418531] Freed by task 144: [ 285.418960] kasan_save_stack+0x1e/0x40 [ 285.419469] kasan_set_track+0x21/0x30 [ 285.419988] kasan_save_free_info+0x27/0x40 [ 285.420556] ____kasan_slab_free+0x109/0x1a0 [ 285.421146] kmem_cache_free+0x1c2/0x450 [ 285.421680] __netif_receive_skb_core+0x2ce/0x1870 [ 285.422333] __netif_receive_skb_one_core+0x97/0x140 [ 285.423003] process_backlog+0x100/0x2f0 [ 285.423537] __napi_poll+0x5c/0x2d0 [ 285.424023] net_rx_action+0x2be/0x560 [ 285.424510] __do_softirq+0x11b/0x3de [ 285.425034] [ 285.425254] The buggy address belongs to the object at ffff8880bad31280 [ 285.425254] which belongs to the cache skbuff_head_cache of size 224 [ 285.426993] The buggy address is located 40 bytes inside of [ 285.426993] freed 224-byte region [ffff8880bad31280, ffff8880bad31360) [ 285.428572] [ 285.428798] The buggy address belongs to the physical page: [ 285.429540] page:00000000f4b77674 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xbad31 [ 285.430758] flags: 0x100000000000200(slab|node=0|zone=1) [ 285.431447] page_type: 0xffffffff() [ 285.431934] raw: 0100000000000200 ffff88810094a8c0 dead000000000122 0000000000000000 [ 285.432757] raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000 [ 285.433562] page dumped because: kasan: bad access detected [ 285.434144] [ 285.434320] Memory state around the buggy address: [ 285.434828] ffff8880bad31180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.435580] ffff8880bad31200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.436264] >ffff8880bad31280: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 285.436777] ^ [ 285.437106] ffff8880bad31300: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc [ 285.437616] ffff8880bad31380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.438126] ================================================================== [ 285.438662] Disabling lock debugging due to kernel taint Fix this by: 1. Changing sch_plug's .peek handler to qdisc_peek_dequeued(), a function compatible with non-work-conserving qdiscs 2. Checking the return value of qdisc_dequeue_peeked() in sch_qfq. Bug: 300131820 Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost") Reported-by: valis Signed-off-by: valis Signed-off-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20230901162237.11525-1-jhs@mojatatu.com Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin (cherry picked from commit a18349dc8d916a64d7c93f05da98953e3386d8e9) Signed-off-by: Lee Jones Change-Id: I2be4a7b7eb1448df8281c145ee2ca441bd746c9a --- net/sched/sch_plug.c | 2 +- net/sched/sch_qfq.c | 22 +++++++++++++++++----- 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index cbc2ebca4548..339990bb5981 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -210,7 +210,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .priv_size = sizeof(struct plug_sched_data), .enqueue = plug_enqueue, .dequeue = plug_dequeue, - .peek = qdisc_peek_head, + .peek = qdisc_peek_dequeued, .init = plug_init, .change = plug_change, .reset = qdisc_reset_queue, diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 616d1798cfef..10688d8ffd10 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -972,10 +972,13 @@ static void qfq_update_eligible(struct qfq_sched *q) } /* Dequeue head packet of the head class in the DRR queue of the aggregate. */ -static void agg_dequeue(struct qfq_aggregate *agg, - struct qfq_class *cl, unsigned int len) +static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, + struct qfq_class *cl, unsigned int len) { - qdisc_dequeue_peeked(cl->qdisc); + struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc); + + if (!skb) + return NULL; cl->deficit -= (int) len; @@ -985,6 +988,8 @@ static void agg_dequeue(struct qfq_aggregate *agg, cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); } + + return skb; } static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, @@ -1130,11 +1135,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) if (!skb) return NULL; - qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; + + skb = agg_dequeue(in_serv_agg, cl, len); + + if (!skb) { + sch->q.qlen++; + return NULL; + } + + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); - agg_dequeue(in_serv_agg, cl, len); /* If lmax is lowered, through qfq_change_class, for a class * owning pending packets with larger size than the new value * of lmax, then the following condition may hold. From d3961f624b240bb1c489a7253a86f404bb21aa94 Mon Sep 17 00:00:00 2001 From: xieliujie Date: Tue, 26 Sep 2023 10:26:32 +0800 Subject: [PATCH 4344/4345] ANDROID: vendor_hooks: Add hooks for oem percpu-rwsem optimaton Recently we have discovered many lag issues caused by percpu_rwsem lock-holding tasks not being scheduled for a long time. we need to identify them and provide appropriate scheduling protection in our oem scheduler. To support this, we add one hook below: trace_android_vh_percpu_rwsem_wq_add Bug: 301066838 Change-Id: Id770c1a7978842abfc62d3fa9aeb5ac7a1904972 Signed-off-by: xieliujie (cherry picked from commit f451f4a59950135ea9a6ede218c58f10dbb3abaa) --- drivers/android/vendor_hooks.c | 1 + include/trace/hooks/dtask.h | 6 ++++++ kernel/locking/percpu-rwsem.c | 1 + 3 files changed, 8 insertions(+) diff --git a/drivers/android/vendor_hooks.c b/drivers/android/vendor_hooks.c index 1021ca51ede6..7b945c3cce28 100644 --- a/drivers/android/vendor_hooks.c +++ b/drivers/android/vendor_hooks.c @@ -106,6 +106,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_binder_wakeup_ilocked); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_do_send_sig_info); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_process_killed); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_killed_process); +EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_percpu_rwsem_wq_add); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_init); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_wake); EXPORT_TRACEPOINT_SYMBOL_GPL(android_vh_rwsem_write_finished); diff --git a/include/trace/hooks/dtask.h b/include/trace/hooks/dtask.h index 081a60af0e26..d8fa440ea6e9 100644 --- a/include/trace/hooks/dtask.h +++ b/include/trace/hooks/dtask.h @@ -99,6 +99,12 @@ DECLARE_HOOK(android_vh_record_pcpu_rwsem_starttime, TP_PROTO(struct task_struct *tsk, unsigned long settime_jiffies), TP_ARGS(tsk, settime_jiffies)); +struct percpu_rw_semaphore; +DECLARE_HOOK(android_vh_percpu_rwsem_wq_add, + TP_PROTO(struct percpu_rw_semaphore *sem, bool reader), + TP_ARGS(sem, reader)); + + /* macro versions of hooks are no longer required */ #endif /* _TRACE_HOOK_DTASK_H */ diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 915c045a15f3..b00db54994d8 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -166,6 +166,7 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader) if (wait) { wq_entry.flags |= WQ_FLAG_EXCLUSIVE | reader * WQ_FLAG_CUSTOM; __add_wait_queue_entry_tail(&sem->waiters, &wq_entry); + trace_android_vh_percpu_rwsem_wq_add(sem, reader); } spin_unlock_irq(&sem->waiters.lock); From 785004172f0154abc54da48e168d5789038882d5 Mon Sep 17 00:00:00 2001 From: xieliujie Date: Wed, 27 Sep 2023 09:58:28 +0800 Subject: [PATCH 4345/4345] ANDROID: ABI: Update oplus symbol list Leaf changes summary: 2 artifacts changed Changed leaf types summary: 0 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 0 Changed, 1 Added function Removed/Changed/Added variables summary: 0 Removed, 0 Changed, 1 Added variable 1 Added function: [A] 'function int __traceiter_android_vh_percpu_rwsem_wq_add(void*, percpu_rw_semaphore*, bool)' 1 Added variable: [A] 'tracepoint __tracepoint_android_vh_percpu_rwsem_wq_add' Bug: 301066838 Change-Id: Iaa2d29e282e58a1de044f3a8fde5158070163d93 Signed-off-by: xieliujie --- android/abi_gki_aarch64.xml | 139 +++++----------------------------- android/abi_gki_aarch64_oplus | 2 + 2 files changed, 22 insertions(+), 119 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index 5eb543dc62e3..9d5dc942ce59 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -598,6 +598,7 @@ + @@ -6683,6 +6684,7 @@ + @@ -21585,14 +21587,6 @@ - - - - - - - - @@ -41052,17 +41046,6 @@ - - - - - - - - - - - @@ -42872,7 +42855,6 @@ - @@ -45447,9 +45429,6 @@ - - - @@ -55418,7 +55397,6 @@ - @@ -63379,65 +63357,7 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + @@ -68226,11 +68146,6 @@ - - - - - @@ -84098,7 +84013,6 @@ - @@ -84643,14 +84557,6 @@ - - - - - - - - @@ -96332,7 +96238,6 @@ - @@ -96845,17 +96750,7 @@ - - - - - - - - - - - + @@ -116404,7 +116299,6 @@ - @@ -116612,9 +116506,9 @@ - + - + @@ -117897,9 +117791,9 @@ - - - + + + @@ -120278,6 +120172,12 @@ + + + + + + @@ -121739,6 +121639,7 @@ + @@ -139539,8 +139440,8 @@ - - + + @@ -139571,8 +139472,8 @@ - - + + diff --git a/android/abi_gki_aarch64_oplus b/android/abi_gki_aarch64_oplus index 124791f30bd2..aef23e847499 100644 --- a/android/abi_gki_aarch64_oplus +++ b/android/abi_gki_aarch64_oplus @@ -2884,6 +2884,7 @@ __traceiter_android_vh_process_killed __traceiter_android_vh_record_mutex_lock_starttime __traceiter_android_vh_record_pcpu_rwsem_starttime + __traceiter_android_vh_percpu_rwsem_wq_add __traceiter_android_vh_record_rtmutex_lock_starttime __traceiter_android_vh_record_rwsem_lock_starttime __traceiter_android_vh_remove_vmalloc_stack @@ -3151,6 +3152,7 @@ __tracepoint_android_vh_process_killed __tracepoint_android_vh_record_mutex_lock_starttime __tracepoint_android_vh_record_pcpu_rwsem_starttime + __tracepoint_android_vh_percpu_rwsem_wq_add __tracepoint_android_vh_record_rtmutex_lock_starttime __tracepoint_android_vh_record_rwsem_lock_starttime __tracepoint_android_vh_remove_vmalloc_stack